5529 files changed, 242834 insertions, 101178 deletions

diff --git a/.gitignore b/.gitignore
index 42fa0d5626a..f4c0b091dcf 100644
--- a/.gitignore
+++ b/.gitignore
@@ -22,7 +22,6 @@
 *.lst
 *.symtypes
 *.order
-modules.builtin
 *.elf
 *.bin
 *.gz
@@ -33,6 +32,8 @@ modules.builtin
 *.lzo
 *.patch
 *.gcno
+modules.builtin
+Module.symvers
 
 #
 # Top-level generic files
@@ -44,7 +45,6 @@ modules.builtin
 /vmlinuz
 /System.map
 /Module.markers
-/Module.symvers
 
 #
 # Debian directory (make deb-pkg)
diff --git a/.mailmap b/.mailmap
index df1baba43a6..1ad68731fb4 100644
--- a/.mailmap
+++ b/.mailmap
@@ -62,6 +62,11 @@ Jeff Garzik <jgarzik@pretzel.yyz.us>
 Jens Axboe <axboe@suse.de>
 Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 John Stultz <johnstul@us.ibm.com>
+<josh@joshtriplett.org> <josh@freedesktop.org>
+<josh@joshtriplett.org> <josh@kernel.org>
+<josh@joshtriplett.org> <josht@linux.vnet.ibm.com>
+<josh@joshtriplett.org> <josht@us.ibm.com>
+<josh@joshtriplett.org> <josht@vnet.ibm.com>
 Juha Yrjola <at solidboot.com>
 Juha Yrjola <juha.yrjola@nokia.com>
 Juha Yrjola <juha.yrjola@solidboot.com>
diff --git a/CREDITS b/CREDITS
index c322dcfb926..a80b66718f6 100644
--- a/CREDITS
+++ b/CREDITS
@@ -9,6 +9,10 @@
 			Linus
 ----------
 
+M: Matt Mackal
+E: mpm@selenic.com
+D: SLOB slab allocator
+
 N: Matti Aarnio
 E: mea@nic.funet.fi
 D: Alpha systems hacking, IPv6 and other network related stuff
@@ -3507,10 +3511,11 @@ S: MacGregor A.C.T 2615
 S: Australia
 
 N: Josh Triplett
-E: josh@freedesktop.org
-P: 1024D/D0FE7AFB B24A 65C9 1D71 2AC2 DE87  CA26 189B 9946 D0FE 7AFB
-D: rcutorture maintainer
+E: josh@joshtriplett.org
+P: 4096R/8AFF873D 758E 5042 E397 4BA3 3A9C  1E67 0ED9 A3DF 8AFF 873D
+D: RCU and rcutorture
 D: lock annotations, finding and fixing lock bugs
+D: kernel tinification
 
 N: Winfried Trümper
 E: winni@xpilot.org
diff --git a/Documentation/ABI/stable/sysfs-devices-system-cpu b/Documentation/ABI/stable/sysfs-devices-system-cpu
new file mode 100644
index 00000000000..33c133e2a63
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-devices-system-cpu
@@ -0,0 +1,25 @@
+What: 		/sys/devices/system/cpu/dscr_default
+Date:		13-May-2014
+KernelVersion:	v3.15.0
+Contact:
+Description:	Writes are equivalent to writing to
+		/sys/devices/system/cpu/cpuN/dscr on all CPUs.
+		Reads return the last written value or 0.
+		This value is not a global default: it is a way to set
+		all per-CPU defaults at the same time.
+Values:		64 bit unsigned integer (bit field)
+
+What: 		/sys/devices/system/cpu/cpu[0-9]+/dscr
+Date:		13-May-2014
+KernelVersion:	v3.15.0
+Contact:
+Description:	Default value for the Data Stream Control Register (DSCR) on
+		a CPU.
+		This default value is used when the kernel is executing and
+		for any process that has not set the DSCR itself.
+		If a process ever sets the DSCR (via direct access to the
+		SPR) that value will be persisted for that process and used
+		on any CPU where it executes (overriding the value described
+		here).
+		If set by a process it will be inherited by child processes.
+Values:		64 bit unsigned integer (bit field)
diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy
index f1c5cc9d17a..4c3efe43480 100644
--- a/Documentation/ABI/testing/ima_policy
+++ b/Documentation/ABI/testing/ima_policy
@@ -23,7 +23,7 @@ Description:
 				 [fowner]]
 			lsm:	[[subj_user=] [subj_role=] [subj_type=]
 				 [obj_user=] [obj_role=] [obj_type=]]
-			option:	[[appraise_type=]]
+			option:	[[appraise_type=]] [permit_directio]
 
 		base: 	func:= [BPRM_CHECK][MMAP_CHECK][FILE_CHECK][MODULE_CHECK]
 			mask:= [MAY_READ] [MAY_WRITE] [MAY_APPEND] [MAY_EXEC]
diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net
index d922060e455..416c5d59f52 100644
--- a/Documentation/ABI/testing/sysfs-class-net
+++ b/Documentation/ABI/testing/sysfs-class-net
@@ -169,6 +169,14 @@ Description:
 		"unknown", "notpresent", "down", "lowerlayerdown", "testing",
 		"dormant", "up".
 
+What:		/sys/class/net/<iface>/phys_port_id
+Date:		July 2013
+KernelVersion:	3.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the interface unique physical port identifier within
+		the NIC, as a string.
+
 What:		/sys/class/net/<iface>/speed
 Date:		October 2009
 KernelVersion:	2.6.33
diff --git a/Documentation/ABI/testing/sysfs-class-net-cdc_ncm b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
new file mode 100644
index 00000000000..5cedf72df35
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
@@ -0,0 +1,149 @@
+What:		/sys/class/net/<iface>/cdc_ncm/min_tx_pkt
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		The driver will pad NCM Transfer Blocks (NTBs) longer
+		than this to tx_max, allowing the device to receive
+		tx_max sized frames with no terminating short
+		packet. NTBs shorter than this limit are transmitted
+		as-is, without any padding, and are terminated with a
+		short USB packet.
+
+		Padding to tx_max allows the driver to transmit NTBs
+		back-to-back without any interleaving short USB
+		packets.  This reduces the number of short packet
+		interrupts in the device, and represents a tradeoff
+		between USB bus bandwidth and device DMA optimization.
+
+		Set to 0 to pad all frames. Set greater than tx_max to
+		disable all padding.
+
+What:		/sys/class/net/<iface>/cdc_ncm/rx_max
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		The maximum NTB size for RX.  Cannot exceed the
+		maximum value supported by the device. Must allow at
+		least one max sized datagram plus headers.
+
+		The actual limits are device dependent.  See
+		dwNtbInMaxSize.
+
+		Note: Some devices will silently ignore changes to
+		this value, resulting in oversized NTBs and
+		corresponding framing errors.
+
+What:		/sys/class/net/<iface>/cdc_ncm/tx_max
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		The maximum NTB size for TX.  Cannot exceed the
+		maximum value supported by the device.  Must allow at
+		least one max sized datagram plus headers.
+
+		The actual limits are device dependent.  See
+		dwNtbOutMaxSize.
+
+What:		/sys/class/net/<iface>/cdc_ncm/tx_timer_usecs
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Datagram aggregation timeout in µs. The driver will
+		wait up to 3 times this timeout for more datagrams to
+		aggregate before transmitting an NTB frame.
+
+		Valid range: 5 to 4000000
+
+		Set to 0 to disable aggregation.
+
+The following read-only attributes all represent fields of the
+structure defined in section 6.2.1 "GetNtbParameters" of "Universal
+Serial Bus Communications Class Subclass Specifications for Network
+Control Model Devices" (CDC NCM), Revision 1.0 (Errata 1), November
+24, 2010 from USB Implementers Forum, Inc.  The descriptions are
+quoted from table 6-3 of CDC NCM: "NTB Parameter Structure".
+
+What:		/sys/class/net/<iface>/cdc_ncm/bmNtbFormatsSupported
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Bit 0: 16-bit NTB supported (set to 1)
+		Bit 1: 32-bit NTB supported
+		Bits 2 – 15: reserved (reset to zero; must be ignored by host)
+
+What:		/sys/class/net/<iface>/cdc_ncm/dwNtbInMaxSize
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		IN NTB Maximum Size in bytes
+
+What:		/sys/class/net/<iface>/cdc_ncm/wNdpInDivisor
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Divisor used for IN NTB Datagram payload alignment
+
+What:		/sys/class/net/<iface>/cdc_ncm/wNdpInPayloadRemainder
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Remainder used to align input datagram payload within
+		the NTB: (Payload Offset) mod (wNdpInDivisor) =
+		wNdpInPayloadRemainder
+
+What:		/sys/class/net/<iface>/cdc_ncm/wNdpInAlignment
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		NDP alignment modulus for NTBs on the IN pipe. Shall
+		be a power of 2, and shall be at least 4.
+
+What:		/sys/class/net/<iface>/cdc_ncm/dwNtbOutMaxSize
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		OUT NTB Maximum Size
+
+What:		/sys/class/net/<iface>/cdc_ncm/wNdpOutDivisor
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		OUT NTB Datagram alignment modulus
+
+What:		/sys/class/net/<iface>/cdc_ncm/wNdpOutPayloadRemainder
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Remainder used to align output datagram payload
+		offsets within the NTB: Padding, shall be transmitted
+		as zero by function, and ignored by host.  (Payload
+		Offset) mod (wNdpOutDivisor) = wNdpOutPayloadRemainder
+
+What:		/sys/class/net/<iface>/cdc_ncm/wNdpOutAlignment
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		NDP alignment modulus for use in NTBs on the OUT
+		pipe. Shall be a power of 2, and shall be at least 4.
+
+What:		/sys/class/net/<iface>/cdc_ncm/wNtbOutMaxDatagrams
+Date:		May 2014
+KernelVersion:	3.16
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Maximum number of datagrams that the host may pack
+		into a single OUT NTB. Zero means that the device
+		imposes no limit.
diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues
new file mode 100644
index 00000000000..5e9aeb91d35
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-net-queues
@@ -0,0 +1,79 @@
+What:		/sys/class/<iface>/queues/rx-<queue>/rps_cpus
+Date:		March 2010
+KernelVersion:	2.6.35
+Contact:	netdev@vger.kernel.org
+Description:
+		Mask of the CPU(s) currently enabled to participate into the
+		Receive Packet Steering packet processing flow for this
+		network device queue. Possible values depend on the number
+		of available CPU(s) in the system.
+
+What:		/sys/class/<iface>/queues/rx-<queue>/rps_flow_cnt
+Date:		April 2010
+KernelVersion:	2.6.35
+Contact:	netdev@vger.kernel.org
+Description:
+		Number of Receive Packet Steering flows being currently
+		processed by this particular network device receive queue.
+
+What:		/sys/class/<iface>/queues/tx-<queue>/tx_timeout
+Date:		November 2011
+KernelVersion:	3.3
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of transmit timeout events seen by this
+		network interface transmit queue.
+
+What:		/sys/class/<iface>/queues/tx-<queue>/xps_cpus
+Date:		November 2010
+KernelVersion:	2.6.38
+Contact:	netdev@vger.kernel.org
+Description:
+		Mask of the CPU(s) currently enabled to participate into the
+		Transmit Packet Steering packet processing flow for this
+		network device transmit queue. Possible vaules depend on the
+		number of available CPU(s) in the system.
+
+What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
+Date:		November 2011
+KernelVersion:	3.3
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the hold time in milliseconds to measure the slack
+		of this particular network device transmit queue.
+		Default value is 1000.
+
+What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
+Date:		November 2011
+KernelVersion:	3.3
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of bytes (objects) in flight on this
+		network device transmit queue.
+
+What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit
+Date:		November 2011
+KernelVersion:	3.3
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the current limit of bytes allowed to be queued
+		on this network device transmit queue. This value is clamped
+		to be within the bounds defined by limit_max and limit_min.
+
+What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
+Date:		November 2011
+KernelVersion:	3.3
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the absolute maximum limit of bytes allowed to be
+		queued on this network device transmit queue. See
+		include/linux/dynamic_queue_limits.h for the default value.
+
+What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
+Date:		November 2011
+KernelVersion:	3.3
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the absolute minimum limit of bytes allowed to be
+		queued on this network device transmit queue. Default value is
+		0.
diff --git a/Documentation/ABI/testing/sysfs-class-net-statistics b/Documentation/ABI/testing/sysfs-class-net-statistics
new file mode 100644
index 00000000000..397118de7b5
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-net-statistics
@@ -0,0 +1,201 @@
+What:		/sys/class/<iface>/statistics/collisions
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of collisions seen by this network device.
+		This value might not be relevant with all MAC layers.
+
+What:		/sys/class/<iface>/statistics/multicast
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of multicast packets received by this
+		network device.
+
+What:		/sys/class/<iface>/statistics/rx_bytes
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of bytes received by this network device.
+		See the network driver for the exact meaning of when this
+		value is incremented.
+
+What:		/sys/class/<iface>/statistics/rx_compressed
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of compressed packets received by this
+		network device. This value might only be relevant for interfaces
+		that support packet compression (e.g: PPP).
+
+What:		/sys/class/<iface>/statistics/rx_crc_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets received with a CRC (FCS) error
+		by this network device. Note that the specific meaning might
+		depend on the MAC layer used by the interface.
+
+What:		/sys/class/<iface>/statistics/rx_dropped
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets received by the network device
+		but dropped, that are not forwarded to the upper layers for
+		packet processing. See the network driver for the exact
+		meaning of this value.
+
+What:		/sys/class/<iface>/statistics/rx_fifo_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of receive FIFO errors seen by this
+		network device. See the network driver for the exact
+		meaning of this value.
+
+What:		/sys/class/<iface>/statistics/rx_frame_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of received frames with error, such as
+		alignment errors. Note that the specific meaning depends on
+		on the MAC layer protocol used. See the network driver for
+		the exact meaning of this value.
+
+What:		/sys/class/<iface>/statistics/rx_length_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of received error packet with a length
+		error, oversized or undersized. See the network driver for the
+		exact meaning of this value.
+
+What:		/sys/class/<iface>/statistics/rx_missed_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of received packets that have been missed
+		due to lack of capacity in the receive side. See the network
+		driver for the exact meaning of this value.
+
+What:		/sys/class/<iface>/statistics/rx_over_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of received packets that are oversized
+		compared to what the network device is configured to accept
+		(e.g: larger than MTU). See the network driver for the exact
+		meaning of this value.
+
+What:		/sys/class/<iface>/statistics/rx_packets
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the total number of good packets received by this
+		network device.
+
+What:		/sys/class/<iface>/statistics/tx_aborted_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets that have been aborted
+		during transmission by a network device (e.g: because of
+		a medium collision). See the network driver for the exact
+		meaning of this value.
+
+What:		/sys/class/<iface>/statistics/tx_bytes
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of bytes transmitted by a network
+		device. See the network driver for the exact meaning of this
+		value, in particular whether this accounts for all successfully
+		transmitted packets or all packets that have been queued for
+		transmission.
+
+What:		/sys/class/<iface>/statistics/tx_carrier_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets that could not be transmitted
+		because of carrier errors (e.g: physical link down). See the
+		network driver for the exact meaning of this value.
+
+What:		/sys/class/<iface>/statistics/tx_compressed
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of transmitted compressed packets. Note
+		this might only be relevant for devices that support
+		compression (e.g: PPP).
+
+What:		/sys/class/<iface>/statistics/tx_dropped
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets dropped during transmission.
+		See the driver for the exact reasons as to why the packets were
+		dropped.
+
+What:		/sys/class/<iface>/statistics/tx_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets in error during transmission by
+		a network device. See the driver for the exact reasons as to
+		why the packets were dropped.
+
+What:		/sys/class/<iface>/statistics/tx_fifo_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets having caused a transmit
+		FIFO error. See the driver for the exact reasons as to why the
+		packets were dropped.
+
+What:		/sys/class/<iface>/statistics/tx_heartbeat_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets transmitted that have been
+		reported as heartbeat errors. See the driver for the exact
+		reasons as to why the packets were dropped.
+
+What:		/sys/class/<iface>/statistics/tx_packets
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets transmitted by a network
+		device. See the driver for whether this reports the number of all
+		attempted or successful transmissions.
+
+What:		/sys/class/<iface>/statistics/tx_window_errors
+Date:		April 2005
+KernelVersion:	2.6.12
+Contact:	netdev@vger.kernel.org
+Description:
+		Indicates the number of packets not successfully transmitted
+		due to a window collision. The specific meaning depends on the
+		MAC layer used.  On Ethernet this is usually used to report
+		late collisions errors.
diff --git a/Documentation/Changes b/Documentation/Changes
index 2254db0f00a..227bec88021 100644
--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -280,12 +280,9 @@ that is possible.
 mcelog
 ------
 
-In Linux 2.6.31+ the i386 kernel needs to run the mcelog utility
-as a regular cronjob similar to the x86-64 kernel to process and log
-machine check events when CONFIG_X86_NEW_MCE is enabled. Machine check
-events are errors reported by the CPU. Processing them is strongly encouraged.
-All x86-64 kernels since 2.6.4 require the mcelog utility to
-process machine checks.
+On x86 kernels the mcelog utility is needed to process and log machine check
+events when CONFIG_X86_MCE is enabled. Machine check events are errors reported
+by the CPU. Processing them is strongly encouraged.
 
 Getting updated software
 ========================
diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl
index 044b76436e8..d9b9416c989 100644
--- a/Documentation/DocBook/80211.tmpl
+++ b/Documentation/DocBook/80211.tmpl
@@ -100,6 +100,7 @@
 !Finclude/net/cfg80211.h wdev_priv
 !Finclude/net/cfg80211.h ieee80211_iface_limit
 !Finclude/net/cfg80211.h ieee80211_iface_combination
+!Finclude/net/cfg80211.h cfg80211_check_combinations
       </chapter>
       <chapter>
       <title>Actions and configuration</title>
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index ba60d93c185..7df3134ebc0 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -142,6 +142,12 @@
       to register it with the DRM subsystem.
     </para>
     <para>
+      Newer drivers that no longer require a <structname>drm_bus</structname>
+      structure can alternatively use the low-level device initialization and
+      registration functions such as <function>drm_dev_alloc()</function> and
+      <function>drm_dev_register()</function> directly.
+    </para>
+    <para>
       The <structname>drm_driver</structname> structure contains static
       information that describes the driver and features it supports, and
       pointers to methods that the DRM core will call to implement the DRM API.
@@ -282,6 +288,36 @@ char *date;</synopsis>
       </sect3>
     </sect2>
     <sect2>
+      <title>Device Registration</title>
+      <para>
+        A number of functions are provided to help with device registration.
+        The functions deal with PCI, USB and platform devices, respectively.
+      </para>
+!Edrivers/gpu/drm/drm_pci.c
+!Edrivers/gpu/drm/drm_usb.c
+!Edrivers/gpu/drm/drm_platform.c
+      <para>
+        New drivers that no longer rely on the services provided by the
+        <structname>drm_bus</structname> structure can call the low-level
+        device registration functions directly. The
+        <function>drm_dev_alloc()</function> function can be used to allocate
+        and initialize a new <structname>drm_device</structname> structure.
+        Drivers will typically want to perform some additional setup on this
+        structure, such as allocating driver-specific data and storing a
+        pointer to it in the DRM device's <structfield>dev_private</structfield>
+        field. Drivers should also set the device's unique name using the
+        <function>drm_dev_set_unique()</function> function. After it has been
+        set up a device can be registered with the DRM subsystem by calling
+        <function>drm_dev_register()</function>. This will cause the device to
+        be exposed to userspace and will call the driver's
+        <structfield>.load()</structfield> implementation. When a device is
+        removed, the DRM device can safely be unregistered and freed by calling
+        <function>drm_dev_unregister()</function> followed by a call to
+        <function>drm_dev_unref()</function>.
+      </para>
+!Edrivers/gpu/drm/drm_stub.c
+    </sect2>
+    <sect2>
       <title>Driver Load</title>
       <para>
         The <methodname>load</methodname> method is the driver and device
@@ -342,21 +378,13 @@ char *date;</synopsis>
         <sect4>
           <title>Managed IRQ Registration</title>
           <para>
-            Both the <function>drm_irq_install</function> and
-	    <function>drm_irq_uninstall</function> functions get the device IRQ by
-	    calling <function>drm_dev_to_irq</function>. This inline function will
-	    call a bus-specific operation to retrieve the IRQ number. For platform
-	    devices, <function>platform_get_irq</function>(..., 0) is used to
-	    retrieve the IRQ number.
-          </para>
-          <para>
             <function>drm_irq_install</function> starts by calling the
             <methodname>irq_preinstall</methodname> driver operation. The operation
             is optional and must make sure that the interrupt will not get fired by
             clearing all pending interrupt flags or disabling the interrupt.
           </para>
           <para>
-            The IRQ will then be requested by a call to
+            The passed-in IRQ will then be requested by a call to
             <function>request_irq</function>. If the DRIVER_IRQ_SHARED driver
             feature flag is set, a shared (IRQF_SHARED) IRQ handler will be
             requested.
@@ -1799,6 +1827,12 @@ void intel_crt_init(struct drm_device *dev)
       <title>KMS API Functions</title>
 !Edrivers/gpu/drm/drm_crtc.c
     </sect2>
+    <sect2>
+      <title>KMS Locking</title>
+!Pdrivers/gpu/drm/drm_modeset_lock.c kms locking
+!Iinclude/drm/drm_modeset_lock.h
+!Edrivers/gpu/drm/drm_modeset_lock.c
+    </sect2>
   </sect1>
 
   <!-- Internals: kms helper functions -->
@@ -1903,8 +1937,8 @@ void intel_crt_init(struct drm_device *dev)
           <para>
             The function filters out modes larger than
             <parameter>max_width</parameter> and <parameter>max_height</parameter>
-            if specified. It then calls the connector
-            <methodname>mode_valid</methodname> helper operation for  each mode in
+            if specified. It then calls the optional connector
+            <methodname>mode_valid</methodname> helper operation for each mode in
             the probed list to check whether the mode is valid for the connector.
           </para>
         </listitem>
@@ -2265,7 +2299,7 @@ void intel_crt_init(struct drm_device *dev)
           <para>
             Verify whether a mode is valid for the connector. Return MODE_OK for
             supported modes and one of the enum drm_mode_status values (MODE_*)
-            for unsupported modes. This operation is mandatory.
+            for unsupported modes. This operation is optional.
           </para>
           <para>
             As the mode rejection reason is currently not used beside for
@@ -2450,6 +2484,863 @@ void intel_crt_init(struct drm_device *dev)
       pointer to the target object, a pointer to the previously created property
       and an initial instance value.
     </para>
+    <sect2>
+	<title>Existing KMS Properties</title>
+	<para>
+	The following table gives description of drm properties exposed by various
+	modules/drivers.
+	</para>
+	<table border="1" cellpadding="0" cellspacing="0">
+	<tbody>
+	<tr style="font-weight: bold;">
+	<td valign="top" >Owner Module/Drivers</td>
+	<td valign="top" >Group</td>
+	<td valign="top" >Property Name</td>
+	<td valign="top" >Type</td>
+	<td valign="top" >Property Values</td>
+	<td valign="top" >Object attached</td>
+	<td valign="top" >Description/Restrictions</td>
+	</tr>
+	<tr>
+	<td rowspan="20" valign="top" >DRM</td>
+	<td rowspan="2" valign="top" >Generic</td>
+	<td valign="top" >“EDID�</td>
+	<td valign="top" >BLOB | IMMUTABLE</td>
+	<td valign="top" >0</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >Contains id of edid blob ptr object.</td>
+	</tr>
+	<tr>
+	<td valign="top" >“DPMS�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ “On�, “Standby�, “Suspend�, “Off� }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >Contains DPMS operation mode value.</td>
+	</tr>
+	<tr>
+	<td rowspan="1" valign="top" >Plane</td>
+	<td valign="top" >“type�</td>
+	<td valign="top" >ENUM | IMMUTABLE</td>
+	<td valign="top" >{ "Overlay", "Primary", "Cursor" }</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >Plane type</td>
+	</tr>
+	<tr>
+	<td rowspan="2" valign="top" >DVI-I</td>
+	<td valign="top" >“subconnector�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ “Unknown�, “DVI-D�, “DVI-A� }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“select subconnector�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ “Automatic�, “DVI-D�, “DVI-A� }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="13" valign="top" >TV</td>
+	<td valign="top" >“subconnector�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "Unknown", "Composite", "SVIDEO", "Component", "SCART" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“select subconnector�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "Automatic", "Composite", "SVIDEO", "Component", "SCART" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“mode�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "NTSC_M", "NTSC_J", "NTSC_443", "PAL_B" } etc.</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“left margin�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“right margin�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“top margin�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“bottom margin�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“brightness�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“contrast�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“flicker reduction�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“overscan�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“saturation�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“hue�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="2" valign="top" >Optional</td>
+	<td valign="top" >“scaling mode�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "None", "Full", "Center", "Full aspect" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“dirty�</td>
+	<td valign="top" >ENUM | IMMUTABLE</td>
+	<td valign="top" >{ "Off", "On", "Annotate" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="21" valign="top" >i915</td>
+	<td rowspan="3" valign="top" >Generic</td>
+	<td valign="top" >"Broadcast RGB"</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "Automatic", "Full", "Limited 16:235" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“audio�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "force-dvi", "off", "auto", "on" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >Standard name as in DRM</td>
+	<td valign="top" >Standard type as in DRM</td>
+	<td valign="top" >Standard value as in DRM</td>
+	<td valign="top" >Standard Object as in DRM</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="17" valign="top" >SDVO-TV</td>
+	<td valign="top" >“mode�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "NTSC_M", "NTSC_J", "NTSC_443", "PAL_B" } etc.</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"left_margin"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"right_margin"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"top_margin"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"bottom_margin"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“hpos�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“vpos�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“contrast�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“saturation�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“hue�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“sharpness�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“flicker_filter�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“flicker_filter_adaptive�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“flicker_filter_2d�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“tv_chroma_filter�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“tv_luma_filter�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“dot_crawl�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=1</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >SDVO-TV/LVDS</td>
+	<td valign="top" >“brightness�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="3" valign="top" >CDV gma-500</td>
+	<td rowspan="3" valign="top" >Generic</td>
+	<td valign="top" >"Broadcast RGB"</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ “Full�, “Limited 16:235� }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"Broadcast RGB"</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ “off�, “auto�, “on� }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >Standard name as in DRM</td>
+	<td valign="top" >Standard type as in DRM</td>
+	<td valign="top" >Standard value as in DRM</td>
+	<td valign="top" >Standard Object as in DRM</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="20" valign="top" >Poulsbo</td>
+	<td rowspan="2" valign="top" >Generic</td>
+	<td valign="top" >“backlight�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=100</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >Standard name as in DRM</td>
+	<td valign="top" >Standard type as in DRM</td>
+	<td valign="top" >Standard value as in DRM</td>
+	<td valign="top" >Standard Object as in DRM</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="17" valign="top" >SDVO-TV</td>
+	<td valign="top" >“mode�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "NTSC_M", "NTSC_J", "NTSC_443", "PAL_B" } etc.</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"left_margin"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"right_margin"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"top_margin"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"bottom_margin"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“hpos�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“vpos�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“contrast�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“saturation�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“hue�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“sharpness�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“flicker_filter�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“flicker_filter_adaptive�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“flicker_filter_2d�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“tv_chroma_filter�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“tv_luma_filter�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“dot_crawl�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=1</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >SDVO-TV/LVDS</td>
+	<td valign="top" >“brightness�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max= SDVO dependent</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="11" valign="top" >armada</td>
+	<td rowspan="2" valign="top" >CRTC</td>
+	<td valign="top" >"CSC_YUV"</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "Auto" , "CCIR601", "CCIR709" }</td>
+	<td valign="top" >CRTC</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"CSC_RGB"</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "Auto", "Computer system", "Studio" }</td>
+	<td valign="top" >CRTC</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="9" valign="top" >Overlay</td>
+	<td valign="top" >"colorkey"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0xffffff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"colorkey_min"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0xffffff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"colorkey_max"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0xffffff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"colorkey_val"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0xffffff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"colorkey_alpha"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0xffffff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"colorkey_mode"</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "disabled", "Y component", "U component"
+	, "V component", "RGB", “R component", "G component", "B component" }</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"brightness"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=256 + 255</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"contrast"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0x7fff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"saturation"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0x7fff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="2" valign="top" >exynos</td>
+	<td valign="top" >CRTC</td>
+	<td valign="top" >“mode�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "normal", "blank" }</td>
+	<td valign="top" >CRTC</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >Overlay</td>
+	<td valign="top" >“zpos�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=MAX_PLANE-1</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="3" valign="top" >i2c/ch7006_drv</td>
+	<td valign="top" >Generic</td>
+	<td valign="top" >“scale�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=2</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="2" valign="top" >TV</td>
+	<td valign="top" >Standard names as in DRM</td>
+	<td valign="top" >Standard types as in DRM</td>
+	<td valign="top" >Standard Values as in DRM</td>
+	<td valign="top" >Standard object as in DRM</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“mode�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "PAL", "PAL-M","PAL-N"}, �PAL-Nc"
+	, "PAL-60", "NTSC-M", "NTSC-J" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="16" valign="top" >nouveau</td>
+	<td rowspan="6" valign="top" >NV10 Overlay</td>
+	<td valign="top" >"colorkey"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0x01ffffff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“contrast�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=8192-1</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“brightness�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=1024</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“hue�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=359</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“saturation�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=8192-1</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“iturbt_709�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=1</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="2" valign="top" >Nv04 Overlay</td>
+	<td valign="top" >“colorkey�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0x01ffffff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“brightness�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=1024</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="7" valign="top" >Display</td>
+	<td valign="top" >“dithering mode�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "auto", "off", "on" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“dithering depth�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "auto", "off", "on", "static 2x2", "dynamic 2x2", "temporal" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“underscan�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "auto", "6 bpc", "8 bpc" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“underscan hborder�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=128</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“underscan vborder�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=128</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“vibrant hue�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=180</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“color vibrance�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=200</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >Generic</td>
+	<td valign="top" >Standard name as in DRM</td>
+	<td valign="top" >Standard type as in DRM</td>
+	<td valign="top" >Standard value as in DRM</td>
+	<td valign="top" >Standard Object as in DRM</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="2" valign="top" >omap</td>
+	<td rowspan="2" valign="top" >Generic</td>
+	<td valign="top" >“rotation�</td>
+	<td valign="top" >BITMASK</td>
+	<td valign="top" >{ 0, "rotate-0" },
+	{ 1, "rotate-90" },
+	{ 2, "rotate-180" },
+	{ 3, "rotate-270" },
+	{ 4, "reflect-x" },
+	{ 5, "reflect-y" }</td>
+	<td valign="top" >CRTC, Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >“zorder�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=3</td>
+	<td valign="top" >CRTC, Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >qxl</td>
+	<td valign="top" >Generic</td>
+	<td valign="top" >“hotplug_mode_update"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=1</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="10" valign="top" >radeon</td>
+	<td valign="top" >DVI-I</td>
+	<td valign="top" >“coherent�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=1</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >DAC enable load detect</td>
+	<td valign="top" >“load detection�</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=1</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >TV Standard</td>
+	<td valign="top" >"tv standard"</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "ntsc", "pal", "pal-m", "pal-60", "ntsc-j"
+	, "scart-pal", "pal-cn", "secam" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >legacy TMDS PLL detect</td>
+	<td valign="top" >"tmds_pll"</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "driver", "bios" }</td>
+	<td valign="top" >-</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="3" valign="top" >Underscan</td>
+	<td valign="top" >"underscan"</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "off", "on", "auto" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"underscan hborder"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=128</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"underscan vborder"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=128</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >Audio</td>
+	<td valign="top" >“audio�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "off", "on", "auto" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >FMT Dithering</td>
+	<td valign="top" >“dither�</td>
+	<td valign="top" >ENUM</td>
+	<td valign="top" >{ "off", "on" }</td>
+	<td valign="top" >Connector</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >Generic</td>
+	<td valign="top" >Standard name as in DRM</td>
+	<td valign="top" >Standard type as in DRM</td>
+	<td valign="top" >Standard value as in DRM</td>
+	<td valign="top" >Standard Object as in DRM</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td rowspan="3" valign="top" >rcar-du</td>
+	<td rowspan="3" valign="top" >Generic</td>
+	<td valign="top" >"alpha"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=255</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"colorkey"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=0, Max=0x01ffffff</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	<tr>
+	<td valign="top" >"zpos"</td>
+	<td valign="top" >RANGE</td>
+	<td valign="top" >Min=1, Max=7</td>
+	<td valign="top" >Plane</td>
+	<td valign="top" >TBD</td>
+	</tr>
+	</tbody>
+	</table>
+    </sect2>
   </sect1>
 
   <!-- Internals: vertical blanking -->
@@ -2527,6 +3418,10 @@ void (*disable_vblank) (struct drm_device *dev, int crtc);</synopsis>
       with a call to <function>drm_vblank_cleanup</function> in the driver
       <methodname>unload</methodname> operation handler.
     </para>
+    <sect2>
+      <title>Vertical Blanking and Interrupt Handling Functions Reference</title>
+!Edrivers/gpu/drm/drm_irq.c
+    </sect2>
   </sect1>
 
   <!-- Internals: open/close, file operations and ioctls -->
@@ -2869,17 +3764,16 @@ int num_ioctls;</synopsis>
             <term>DRM_IOCTL_MODESET_CTL</term>
             <listitem>
               <para>
-                This should be called by application level drivers before and
-                after mode setting, since on many devices the vertical blank
-                counter is reset at that time.  Internally, the DRM snapshots
-                the last vblank count when the ioctl is called with the
-                _DRM_PRE_MODESET command, so that the counter won't go backwards
-                (which is dealt with when _DRM_POST_MODESET is used).
+		This was only used for user-mode-settind drivers around
+		modesetting changes to allow the kernel to update the vblank
+		interrupt after mode setting, since on many devices the vertical
+		blank counter is reset to 0 at some point during modeset. Modern
+		drivers should not call this any more since with kernel mode
+		setting it is a no-op.
               </para>
             </listitem>
           </varlistentry>
         </variablelist>
-<!--!Edrivers/char/drm/drm_irq.c-->
       </para>
     </sect1>
 
@@ -2942,6 +3836,96 @@ int num_ioctls;</synopsis>
 	  probing, so those sections fully apply.
         </para>
       </sect2>
+      <sect2>
+        <title>DPIO</title>
+!Pdrivers/gpu/drm/i915/i915_reg.h DPIO
+	<table id="dpiox2">
+	  <title>Dual channel PHY (VLV/CHV)</title>
+	  <tgroup cols="8">
+	    <colspec colname="c0" />
+	    <colspec colname="c1" />
+	    <colspec colname="c2" />
+	    <colspec colname="c3" />
+	    <colspec colname="c4" />
+	    <colspec colname="c5" />
+	    <colspec colname="c6" />
+	    <colspec colname="c7" />
+	    <spanspec spanname="ch0" namest="c0" nameend="c3" />
+	    <spanspec spanname="ch1" namest="c4" nameend="c7" />
+	    <spanspec spanname="ch0pcs01" namest="c0" nameend="c1" />
+	    <spanspec spanname="ch0pcs23" namest="c2" nameend="c3" />
+	    <spanspec spanname="ch1pcs01" namest="c4" nameend="c5" />
+	    <spanspec spanname="ch1pcs23" namest="c6" nameend="c7" />
+	    <thead>
+	      <row>
+		<entry spanname="ch0">CH0</entry>
+		<entry spanname="ch1">CH1</entry>
+	      </row>
+	    </thead>
+	    <tbody valign="top" align="center">
+	      <row>
+		<entry spanname="ch0">CMN/PLL/REF</entry>
+		<entry spanname="ch1">CMN/PLL/REF</entry>
+	      </row>
+	      <row>
+		<entry spanname="ch0pcs01">PCS01</entry>
+		<entry spanname="ch0pcs23">PCS23</entry>
+		<entry spanname="ch1pcs01">PCS01</entry>
+		<entry spanname="ch1pcs23">PCS23</entry>
+	      </row>
+	      <row>
+		<entry>TX0</entry>
+		<entry>TX1</entry>
+		<entry>TX2</entry>
+		<entry>TX3</entry>
+		<entry>TX0</entry>
+		<entry>TX1</entry>
+		<entry>TX2</entry>
+		<entry>TX3</entry>
+	      </row>
+	      <row>
+		<entry spanname="ch0">DDI0</entry>
+		<entry spanname="ch1">DDI1</entry>
+	      </row>
+	    </tbody>
+	  </tgroup>
+	</table>
+	<table id="dpiox1">
+	  <title>Single channel PHY (CHV)</title>
+	  <tgroup cols="4">
+	    <colspec colname="c0" />
+	    <colspec colname="c1" />
+	    <colspec colname="c2" />
+	    <colspec colname="c3" />
+	    <spanspec spanname="ch0" namest="c0" nameend="c3" />
+	    <spanspec spanname="ch0pcs01" namest="c0" nameend="c1" />
+	    <spanspec spanname="ch0pcs23" namest="c2" nameend="c3" />
+	    <thead>
+	      <row>
+		<entry spanname="ch0">CH0</entry>
+	      </row>
+	    </thead>
+	    <tbody valign="top" align="center">
+	      <row>
+		<entry spanname="ch0">CMN/PLL/REF</entry>
+	      </row>
+	      <row>
+		<entry spanname="ch0pcs01">PCS01</entry>
+		<entry spanname="ch0pcs23">PCS23</entry>
+	      </row>
+	      <row>
+		<entry>TX0</entry>
+		<entry>TX1</entry>
+		<entry>TX2</entry>
+		<entry>TX3</entry>
+	      </row>
+	      <row>
+		<entry spanname="ch0">DDI2</entry>
+	      </row>
+	    </tbody>
+	  </tgroup>
+	</table>
+      </sect2>
     </sect1>
 
     <sect1>
@@ -2950,6 +3934,11 @@ int num_ioctls;</synopsis>
 	This sections covers all things related to the GEM implementation in the
 	i915 driver.
       </para>
+      <sect2>
+        <title>Batchbuffer Parsing</title>
+!Pdrivers/gpu/drm/i915/i915_cmd_parser.c batch buffer command parser
+!Idrivers/gpu/drm/i915/i915_cmd_parser.c
+      </sect2>
     </sect1>
   </chapter>
 </part>
diff --git a/Documentation/DocBook/gadget.tmpl b/Documentation/DocBook/gadget.tmpl
index 4017f147ba2..2c425d70f7e 100644
--- a/Documentation/DocBook/gadget.tmpl
+++ b/Documentation/DocBook/gadget.tmpl
@@ -708,7 +708,7 @@ hardware level details could be very different.
 
 <para>Systems need specialized hardware support to implement OTG,
 notably including a special <emphasis>Mini-AB</emphasis> jack
-and associated transciever to support <emphasis>Dual-Role</emphasis>
+and associated transceiver to support <emphasis>Dual-Role</emphasis>
 operation:
 they can act either as a host, using the standard
 Linux-USB host side driver stack,
diff --git a/Documentation/DocBook/genericirq.tmpl b/Documentation/DocBook/genericirq.tmpl
index 46347f60335..59fb5c07754 100644
--- a/Documentation/DocBook/genericirq.tmpl
+++ b/Documentation/DocBook/genericirq.tmpl
@@ -182,7 +182,7 @@
 	<para>
 	Each interrupt is described by an interrupt descriptor structure
 	irq_desc. The interrupt is referenced by an 'unsigned int' numeric
-	value which selects the corresponding interrupt decription structure
+	value which selects the corresponding interrupt description structure
 	in the descriptor structures array.
 	The descriptor structure contains status information and pointers
 	to the interrupt flow method and the interrupt chip structure
@@ -470,7 +470,7 @@ if (desc->irq_data.chip->irq_eoi)
      <para>
        To avoid copies of identical implementations of IRQ chips the
        core provides a configurable generic interrupt chip
-       implementation. Developers should check carefuly whether the
+       implementation. Developers should check carefully whether the
        generic chip fits their needs before implementing the same
        functionality slightly differently themselves.
      </para>
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index 19f2a5a5a5b..e584ee12a1e 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -1760,7 +1760,7 @@ as it would be on UP.
 </para>
 
 <para>
-There is a furthur optimization possible here: remember our original
+There is a further optimization possible here: remember our original
 cache code, where there were no reference counts and the caller simply
 held the lock whenever using the object?  This is still possible: if
 you hold the lock, no one can delete the object, so you don't need to
diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl
index deb71baed32..d7fcdc5a437 100644
--- a/Documentation/DocBook/libata.tmpl
+++ b/Documentation/DocBook/libata.tmpl
@@ -677,7 +677,7 @@ and other resources, etc.
 
 	<listitem>
 	<para>
-	ATA_QCFLAG_ACTIVE is clared from qc->flags.
+	ATA_QCFLAG_ACTIVE is cleared from qc->flags.
 	</para>
 	</listitem>
 
@@ -708,7 +708,7 @@ and other resources, etc.
 
 	   <listitem>
 	   <para>
-	   qc->waiting is claread &amp; completed (in that order).
+	   qc->waiting is cleared &amp; completed (in that order).
 	   </para>
 	   </listitem>
 
@@ -1163,7 +1163,7 @@ and other resources, etc.
 
 	<para>
 	Once sense data is acquired, this type of errors can be
-	handled similary to other SCSI errors.  Note that sense data
+	handled similarly to other SCSI errors.  Note that sense data
 	may indicate ATA bus error (e.g. Sense Key 04h HARDWARE ERROR
 	&amp;&amp; ASC/ASCQ 47h/00h SCSI PARITY ERROR).  In such
 	cases, the error should be considered as an ATA bus error and
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index 1d27f0a1abd..639e7485796 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -202,8 +202,8 @@ $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
 
 $(MEDIA_OBJ_DIR)/v4l2.xml: $(OBJIMGFILES)
 	@$($(quiet)gen_xml)
-	@(ln -sf $(MEDIA_SRC_DIR)/v4l/*xml $(MEDIA_OBJ_DIR)/)
-	@(ln -sf $(MEDIA_SRC_DIR)/dvb/*xml $(MEDIA_OBJ_DIR)/)
+	@(ln -sf `cd $(MEDIA_SRC_DIR) && /bin/pwd`/v4l/*xml $(MEDIA_OBJ_DIR)/)
+	@(ln -sf `cd $(MEDIA_SRC_DIR) && /bin/pwd`/dvb/*xml $(MEDIA_OBJ_DIR)/)
 
 $(MEDIA_OBJ_DIR)/videodev2.h.xml: $(srctree)/include/uapi/linux/videodev2.h $(MEDIA_OBJ_DIR)/v4l2.xml
 	@$($(quiet)gen_xml)
diff --git a/Documentation/DocBook/media_api.tmpl b/Documentation/DocBook/media_api.tmpl
index 4decb46bfa7..03f9a1f8d41 100644
--- a/Documentation/DocBook/media_api.tmpl
+++ b/Documentation/DocBook/media_api.tmpl
@@ -68,7 +68,7 @@
 		several digital tv standards. While it is called as DVB API,
 		in fact it covers several different video standards including
 		DVB-T, DVB-S, DVB-C and ATSC. The API is currently being updated
-		to documment support also for DVB-S2, ISDB-T and ISDB-S.</para>
+		to document support also for DVB-S2, ISDB-T and ISDB-S.</para>
 	<para>The third part covers the Remote Controller API.</para>
 	<para>The fourth part covers the Media Controller API.</para>
 	<para>For additional information and for the latest development code,
diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl
index cd11926e07c..7da8f0402af 100644
--- a/Documentation/DocBook/mtdnand.tmpl
+++ b/Documentation/DocBook/mtdnand.tmpl
@@ -91,7 +91,7 @@
 		<listitem><para>
 	  	[MTD Interface]</para><para>
 		These functions provide the interface to the MTD kernel API. 
-		They are not replacable and provide functionality
+		They are not replaceable and provide functionality
 		which is complete hardware independent.
 		</para></listitem>
 		<listitem><para>
@@ -100,14 +100,14 @@
 		</para></listitem>
 		<listitem><para>
 	  	[GENERIC]</para><para>
-		Generic functions are not replacable and provide functionality
+		Generic functions are not replaceable and provide functionality
 		which is complete hardware independent.
 		</para></listitem>
 		<listitem><para>
 	  	[DEFAULT]</para><para>
 		Default functions provide hardware related functionality which is suitable
 		for most of the implementations. These functions can be replaced by the
-		board driver if neccecary. Those functions are called via pointers in the
+		board driver if necessary. Those functions are called via pointers in the
 		NAND chip description structure. The board driver can set the functions which
 		should be replaced by board dependent functions before calling nand_scan().
 		If the function pointer is NULL on entry to nand_scan() then the pointer
@@ -264,7 +264,7 @@ static void board_hwcontrol(struct mtd_info *mtd, int cmd)
 			is set up nand_scan() is called. This function tries to
 			detect and identify then chip. If a chip is found all the
 			internal data fields are initialized accordingly.
-			The structure(s) have to be zeroed out first and then filled with the neccecary 
+			The structure(s) have to be zeroed out first and then filled with the necessary
 			information about the device.
 		</para>
 		<programlisting>
@@ -327,7 +327,7 @@ module_init(board_init);
 	<sect1 id="Exit_function">
 		<title>Exit function</title>
 		<para>
-			The exit function is only neccecary if the driver is
+			The exit function is only necessary if the driver is
 			compiled as a module. It releases all resources which
 			are held by the chip driver and unregisters the partitions
 			in the MTD layer.
@@ -494,7 +494,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 				in this case. See rts_from4.c and diskonchip.c for 
 				implementation reference. In those cases we must also
 				use bad block tables on FLASH, because the ECC layout is
-				interferring with the bad block marker positions.
+				interfering with the bad block marker positions.
 				See bad block table support for details.
 			</para>
 		</sect2>
@@ -542,7 +542,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 		<para>	
 			nand_scan() calls the function nand_default_bbt(). 
 			nand_default_bbt() selects appropriate default
-			bad block table desriptors depending on the chip information
+			bad block table descriptors depending on the chip information
 			which was retrieved by nand_scan().
 		</para>
 		<para>
@@ -554,7 +554,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 		<sect2 id="Flash_based_tables">
 			<title>Flash based tables</title>
 			<para>
-				It may be desired or neccecary to keep a bad block table in FLASH. 
+				It may be desired or necessary to keep a bad block table in FLASH.
 				For AG-AND chips this is mandatory, as they have no factory marked
 				bad blocks. They have factory marked good blocks. The marker pattern
 				is erased when the block is erased to be reused. So in case of
@@ -565,10 +565,10 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 				of the blocks.
 			</para>
 			<para>
-				The blocks in which the tables are stored are procteted against
+				The blocks in which the tables are stored are protected against
 				accidental access by marking them bad in the memory bad block
 				table. The bad block table management functions are allowed
-				to circumvernt this protection.
+				to circumvent this protection.
 			</para>
 			<para>
 				The simplest way to activate the FLASH based bad block table support 
@@ -592,7 +592,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 				User defined tables are created by filling out a 
 				nand_bbt_descr structure and storing the pointer in the
 				nand_chip structure member bbt_td before calling nand_scan(). 
-				If a mirror table is neccecary a second structure must be
+				If a mirror table is necessary a second structure must be
 				created and a pointer to this structure must be stored
 				in bbt_md inside the nand_chip structure. If the bbt_md 
 				member is set to NULL then only the main table is used
@@ -666,7 +666,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
 				<para>
 				For automatic placement some blocks must be reserved for
 				bad block table storage. The number of reserved blocks is defined 
-				in the maxblocks member of the babd block table description structure.
+				in the maxblocks member of the bad block table description structure.
 				Reserving 4 blocks for mirrored tables should be a reasonable number. 
 				This also limits the number of blocks which are scanned for the bad
 				block table ident pattern.
@@ -1068,11 +1068,11 @@ in this page</entry>
   <chapter id="filesystems">
      	<title>Filesystem support</title>
 	<para>
-		The NAND driver provides all neccecary functions for a
+		The NAND driver provides all necessary functions for a
 		filesystem via the MTD interface.
 	</para>
 	<para>
-		Filesystems must be aware of the NAND pecularities and
+		Filesystems must be aware of the NAND peculiarities and
 		restrictions. One major restrictions of NAND Flash is, that you cannot 
 		write as often as you want to a page. The consecutive writes to a page, 
 		before erasing it again, are restricted to 1-3 writes, depending on the 
@@ -1222,7 +1222,7 @@ in this page</entry>
 #define NAND_BBT_VERSION	0x00000100
 /* Create a bbt if none axists */
 #define NAND_BBT_CREATE		0x00000200
-/* Write bbt if neccecary */
+/* Write bbt if necessary */
 #define NAND_BBT_WRITE		0x00001000
 /* Read and write back block contents when writing bbt */
 #define NAND_BBT_SAVECONTENT	0x00002000
diff --git a/Documentation/DocBook/regulator.tmpl b/Documentation/DocBook/regulator.tmpl
index 346e552fa2c..3b08a085d2c 100644
--- a/Documentation/DocBook/regulator.tmpl
+++ b/Documentation/DocBook/regulator.tmpl
@@ -155,7 +155,7 @@
        release regulators.  Functions are
        provided to <link linkend='API-regulator-enable'>enable</link>
        and <link linkend='API-regulator-disable'>disable</link> the
-       reguator and to get and set the runtime parameters of the
+       regulator and to get and set the runtime parameters of the
        regulator.
      </para>
      <para>
diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl
index 95618159e29..bbe9c1fd5ce 100644
--- a/Documentation/DocBook/uio-howto.tmpl
+++ b/Documentation/DocBook/uio-howto.tmpl
@@ -766,10 +766,10 @@ framework to set up sysfs files for this region. Simply leave it alone.
 	<para>
 	The dynamic memory regions will be allocated when the UIO device file,
 	<varname>/dev/uioX</varname> is opened.
-	Simiar to static memory resources, the memory region information for
+	Similar to static memory resources, the memory region information for
 	dynamic regions is then visible via sysfs at
 	<varname>/sys/class/uio/uioX/maps/mapY/*</varname>.
-	The dynmaic memory regions will be freed when the UIO device file is
+	The dynamic memory regions will be freed when the UIO device file is
 	closed. When no processes are holding the device file open, the address
 	returned to userspace is ~0.
 	</para>
diff --git a/Documentation/DocBook/usb.tmpl b/Documentation/DocBook/usb.tmpl
index 8d57c1888dc..85fc0e28576 100644
--- a/Documentation/DocBook/usb.tmpl
+++ b/Documentation/DocBook/usb.tmpl
@@ -153,7 +153,7 @@
 
 	<listitem><para>The Linux USB API supports synchronous calls for
 	control and bulk messages.
-	It also supports asynchnous calls for all kinds of data transfer,
+	It also supports asynchronous calls for all kinds of data transfer,
 	using request structures called "URBs" (USB Request Blocks).
 	</para></listitem>
 
diff --git a/Documentation/DocBook/writing-an-alsa-driver.tmpl b/Documentation/DocBook/writing-an-alsa-driver.tmpl
index d0056a4e9c5..6f639d9530b 100644
--- a/Documentation/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/DocBook/writing-an-alsa-driver.tmpl
@@ -5696,7 +5696,7 @@ struct _snd_pcm_runtime {
 	suspending the PCM operations via
 	<function>snd_pcm_suspend_all()</function> or
 	<function>snd_pcm_suspend()</function>.  It means that the PCM
-	streams are already stoppped when the register snapshot is
+	streams are already stopped when the register snapshot is
 	taken.  But, remember that you don't have to restart the PCM
 	stream in the resume callback. It'll be restarted via 
 	trigger call with <constant>SNDRV_PCM_TRIGGER_RESUME</constant>
diff --git a/Documentation/EDID/1024x768.S b/Documentation/EDID/1024x768.S
index 4b486fe31b3..6f3e4b75e49 100644
--- a/Documentation/EDID/1024x768.S
+++ b/Documentation/EDID/1024x768.S
@@ -36,7 +36,7 @@
 #define DPI 72
 #define VFREQ 60 /* Hz */
 #define TIMING_NAME "Linux XGA"
-#define ESTABLISHED_TIMINGS_BITS 0x08 /* Bit 3 -> 1024x768 @60 Hz */
+#define ESTABLISHED_TIMING2_BITS 0x08 /* Bit 3 -> 1024x768 @60 Hz */
 #define HSYNC_POL 0
 #define VSYNC_POL 0
 #define CRC 0x55
diff --git a/Documentation/EDID/1280x1024.S b/Documentation/EDID/1280x1024.S
index a2799fe33a4..bd9bef2a65a 100644
--- a/Documentation/EDID/1280x1024.S
+++ b/Documentation/EDID/1280x1024.S
@@ -36,7 +36,7 @@
 #define DPI 72
 #define VFREQ 60 /* Hz */
 #define TIMING_NAME "Linux SXGA"
-#define ESTABLISHED_TIMINGS_BITS 0x00 /* none */
+/* No ESTABLISHED_TIMINGx_BITS */
 #define HSYNC_POL 1
 #define VSYNC_POL 1
 #define CRC 0xa0
diff --git a/Documentation/EDID/1600x1200.S b/Documentation/EDID/1600x1200.S
index 0ded64cfd1f..a45101c6160 100644
--- a/Documentation/EDID/1600x1200.S
+++ b/Documentation/EDID/1600x1200.S
@@ -36,7 +36,7 @@
 #define DPI 72
 #define VFREQ 60 /* Hz */
 #define TIMING_NAME "Linux UXGA"
-#define ESTABLISHED_TIMINGS_BITS 0x00 /* none */
+/* No ESTABLISHED_TIMINGx_BITS */
 #define HSYNC_POL 1
 #define VSYNC_POL 1
 #define CRC 0x9d
diff --git a/Documentation/EDID/1680x1050.S b/Documentation/EDID/1680x1050.S
index 96f67cafcf2..b0d7c69282b 100644
--- a/Documentation/EDID/1680x1050.S
+++ b/Documentation/EDID/1680x1050.S
@@ -36,7 +36,7 @@
 #define DPI 96
 #define VFREQ 60 /* Hz */
 #define TIMING_NAME "Linux WSXGA"
-#define ESTABLISHED_TIMINGS_BITS 0x00 /* none */
+/* No ESTABLISHED_TIMINGx_BITS */
 #define HSYNC_POL 1
 #define VSYNC_POL 1
 #define CRC 0x26
diff --git a/Documentation/EDID/1920x1080.S b/Documentation/EDID/1920x1080.S
index 36ed5d571d0..3084355e81e 100644
--- a/Documentation/EDID/1920x1080.S
+++ b/Documentation/EDID/1920x1080.S
@@ -36,7 +36,7 @@
 #define DPI 96
 #define VFREQ 60 /* Hz */
 #define TIMING_NAME "Linux FHD"
-#define ESTABLISHED_TIMINGS_BITS 0x00 /* none */
+/* No ESTABLISHED_TIMINGx_BITS */
 #define HSYNC_POL 1
 #define VSYNC_POL 1
 #define CRC 0x05
diff --git a/Documentation/EDID/800x600.S b/Documentation/EDID/800x600.S
new file mode 100644
index 00000000000..6644e26d580
--- /dev/null
+++ b/Documentation/EDID/800x600.S
@@ -0,0 +1,41 @@
+/*
+   800x600.S: EDID data set for standard 800x600 60 Hz monitor
+
+   Copyright (C) 2011 Carsten Emde <C.Emde@osadl.org>
+   Copyright (C) 2014 Linaro Limited
+
+   This program is free software; you can redistribute it and/or
+   modify it under the terms of the GNU General Public License
+   as published by the Free Software Foundation; either version 2
+   of the License, or (at your option) any later version.
+
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+*/
+
+/* EDID */
+#define VERSION 1
+#define REVISION 3
+
+/* Display */
+#define CLOCK 40000 /* kHz */
+#define XPIX 800
+#define YPIX 600
+#define XY_RATIO XY_RATIO_4_3
+#define XBLANK 256
+#define YBLANK 28
+#define XOFFSET 40
+#define XPULSE 128
+#define YOFFSET (63+1)
+#define YPULSE (63+4)
+#define DPI 72
+#define VFREQ 60 /* Hz */
+#define TIMING_NAME "Linux SVGA"
+#define ESTABLISHED_TIMING1_BITS 0x01 /* Bit 0: 800x600 @ 60Hz */
+#define HSYNC_POL 1
+#define VSYNC_POL 1
+#define CRC 0xc2
+
+#include "edid.S"
diff --git a/Documentation/EDID/HOWTO.txt b/Documentation/EDID/HOWTO.txt
index 7146db1d9e8..835db332289 100644
--- a/Documentation/EDID/HOWTO.txt
+++ b/Documentation/EDID/HOWTO.txt
@@ -18,7 +18,7 @@ CONFIG_DRM_LOAD_EDID_FIRMWARE was introduced. It allows to provide an
 individually prepared or corrected EDID data set in the /lib/firmware
 directory from where it is loaded via the firmware interface. The code
 (see drivers/gpu/drm/drm_edid_load.c) contains built-in data sets for
-commonly used screen resolutions (1024x768, 1280x1024, 1600x1200,
+commonly used screen resolutions (800x600, 1024x768, 1280x1024, 1600x1200,
 1680x1050, 1920x1080) as binary blobs, but the kernel source tree does
 not contain code to create these data. In order to elucidate the origin
 of the built-in binary EDID blobs and to facilitate the creation of
diff --git a/Documentation/EDID/edid.S b/Documentation/EDID/edid.S
index ea97ae275fc..7ac03276d7a 100644
--- a/Documentation/EDID/edid.S
+++ b/Documentation/EDID/edid.S
@@ -33,6 +33,17 @@
 #define XY_RATIO_5_4	0b10
 #define XY_RATIO_16_9	0b11
 
+/* Provide defaults for the timing bits */
+#ifndef ESTABLISHED_TIMING1_BITS
+#define ESTABLISHED_TIMING1_BITS 0x00
+#endif
+#ifndef ESTABLISHED_TIMING2_BITS
+#define ESTABLISHED_TIMING2_BITS 0x00
+#endif
+#ifndef ESTABLISHED_TIMING3_BITS
+#define ESTABLISHED_TIMING3_BITS 0x00
+#endif
+
 #define mfgname2id(v1,v2,v3) \
 	((((v1-'@')&0x1f)<<10)+(((v2-'@')&0x1f)<<5)+((v3-'@')&0x1f))
 #define swap16(v1) ((v1>>8)+((v1&0xff)<<8))
@@ -139,7 +150,7 @@ white_x_y_msb:	.byte	0x50,0x54
    Bit 2	640x480 @ 75 Hz
    Bit 1	800x600 @ 56 Hz
    Bit 0	800x600 @ 60 Hz */
-estbl_timing1:	.byte	0x00
+estbl_timing1:	.byte	ESTABLISHED_TIMING1_BITS
 
 /* Bit 7	800x600 @ 72 Hz
    Bit 6	800x600 @ 75 Hz
@@ -149,11 +160,11 @@ estbl_timing1:	.byte	0x00
    Bit 2	1024x768 @ 72 Hz
    Bit 1	1024x768 @ 75 Hz
    Bit 0	1280x1024 @ 75 Hz */
-estbl_timing2:	.byte	ESTABLISHED_TIMINGS_BITS
+estbl_timing2:	.byte	ESTABLISHED_TIMING2_BITS
 
 /* Bit 7	1152x870 @ 75 Hz (Apple Macintosh II)
    Bits 6-0 	Other manufacturer-specific display mod */
-estbl_timing3:	.byte	0x00
+estbl_timing3:	.byte	ESTABLISHED_TIMING3_BITS
 
 /* Standard timing */
 /* X resolution, less 31, divided by 8 (256-2288 pixels) */
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index 2f0fcb2112d..f29bcbc463e 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -2451,8 +2451,8 @@ lot of {Linux} into your technology!!!"
 ,month="February"
 ,year="2010"
 ,note="Available:
-\url{http://kerneltrap.com/mailarchive/linux-netdev/2010/2/26/6270589}
-[Viewed March 20, 2011]"
+\url{http://thread.gmane.org/gmane.linux.network/153338}
+[Viewed June 9, 2014]"
 ,annotation={
 	Use a pair of list_head structures to support RCU-protected
 	resizable hash tables.
diff --git a/Documentation/RCU/rcuref.txt b/Documentation/RCU/rcuref.txt
index 141d531aa14..613033ff2b9 100644
--- a/Documentation/RCU/rcuref.txt
+++ b/Documentation/RCU/rcuref.txt
@@ -1,5 +1,14 @@
 Reference-count design for elements of lists/arrays protected by RCU.
 
+
+Please note that the percpu-ref feature is likely your first
+stop if you need to combine reference counts and RCU.  Please see
+include/linux/percpu-refcount.h for more information.  However, in
+those unusual cases where percpu-ref would consume too much memory,
+please read on.
+
+------------------------------------------------------------------------
+
 Reference counting on elements of lists which are protected by traditional
 reader/writer spinlocks or semaphores are straightforward:
 
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index c6a06b71594..f40578026a0 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -314,6 +314,7 @@ int main(int argc, char *argv[])
 			break;
 		case 'm':
 			strncpy(cpumask, optarg, sizeof(cpumask));
+			cpumask[sizeof(cpumask) - 1] = '\0';
 			maskset = 1;
 			printf("cpumask %s maskset %d\n", cpumask, maskset);
 			break;
diff --git a/Documentation/acpi/enumeration.txt b/Documentation/acpi/enumeration.txt
index fd786ea13a1..e182be5e3c8 100644
--- a/Documentation/acpi/enumeration.txt
+++ b/Documentation/acpi/enumeration.txt
@@ -60,12 +60,6 @@ If the driver needs to perform more complex initialization like getting and
 configuring GPIOs it can get its ACPI handle and extract this information
 from ACPI tables.
 
-Currently the kernel is not able to automatically determine from which ACPI
-device it should make the corresponding platform device so we need to add
-the ACPI device explicitly to acpi_platform_device_ids list defined in
-drivers/acpi/acpi_platform.c. This limitation is only for the platform
-devices, SPI and I2C devices are created automatically as described below.
-
 DMA support
 ~~~~~~~~~~~
 DMA controllers enumerated via ACPI should be registered in the system to
diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index 37fc4f63217..85af34d55ce 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -72,27 +72,54 @@ The decompressed kernel image contains a 64-byte header as follows:
 
   u32 code0;			/* Executable code */
   u32 code1;			/* Executable code */
-  u64 text_offset;		/* Image load offset */
-  u64 res0	= 0;		/* reserved */
-  u64 res1	= 0;		/* reserved */
+  u64 text_offset;		/* Image load offset, little endian */
+  u64 image_size;		/* Effective Image size, little endian */
+  u64 flags;			/* kernel flags, little endian */
   u64 res2	= 0;		/* reserved */
   u64 res3	= 0;		/* reserved */
   u64 res4	= 0;		/* reserved */
   u32 magic	= 0x644d5241;	/* Magic number, little endian, "ARM\x64" */
-  u32 res5 = 0;      		/* reserved */
+  u32 res5;      		/* reserved (used for PE COFF offset) */
 
 
 Header notes:
 
+- As of v3.17, all fields are little endian unless stated otherwise.
+
 - code0/code1 are responsible for branching to stext.
+
 - when booting through EFI, code0/code1 are initially skipped.
   res5 is an offset to the PE header and the PE header has the EFI
-  entry point (efi_stub_entry). When the stub has done its work, it
+  entry point (efi_stub_entry).  When the stub has done its work, it
   jumps to code0 to resume the normal boot process.
 
-The image must be placed at the specified offset (currently 0x80000)
-from the start of the system RAM and called there. The start of the
-system RAM must be aligned to 2MB.
+- Prior to v3.17, the endianness of text_offset was not specified.  In
+  these cases image_size is zero and text_offset is 0x80000 in the
+  endianness of the kernel.  Where image_size is non-zero image_size is
+  little-endian and must be respected.  Where image_size is zero,
+  text_offset can be assumed to be 0x80000.
+
+- The flags field (introduced in v3.17) is a little-endian 64-bit field
+  composed as follows:
+  Bit 0: 	Kernel endianness.  1 if BE, 0 if LE.
+  Bits 1-63:	Reserved.
+
+- When image_size is zero, a bootloader should attempt to keep as much
+  memory as possible free for use by the kernel immediately after the
+  end of the kernel image. The amount of space required will vary
+  depending on selected features, and is effectively unbound.
+
+The Image must be placed text_offset bytes from a 2MB aligned base
+address near the start of usable system RAM and called there. Memory
+below that base address is currently unusable by Linux, and therefore it
+is strongly recommended that this location is the start of system RAM.
+At least image_size bytes from the start of the image must be free for
+use by the kernel.
+
+Any memory described to the kernel (even that below the 2MB aligned base
+address) which is not marked as reserved from the kernel e.g. with a
+memreserve region in the device tree) will be considered as available to
+the kernel.
 
 Before jumping into the kernel, the following conditions must be met:
 
diff --git a/Documentation/arm64/memory.txt b/Documentation/arm64/memory.txt
index d50fa618371..344e85cc732 100644
--- a/Documentation/arm64/memory.txt
+++ b/Documentation/arm64/memory.txt
@@ -2,18 +2,18 @@
 		     ==============================
 
 Author: Catalin Marinas <catalin.marinas@arm.com>
-Date  : 20 February 2012
 
 This document describes the virtual memory layout used by the AArch64
 Linux kernel. The architecture allows up to 4 levels of translation
 tables with a 4KB page size and up to 3 levels with a 64KB page size.
 
-AArch64 Linux uses 3 levels of translation tables with the 4KB page
-configuration, allowing 39-bit (512GB) virtual addresses for both user
-and kernel. With 64KB pages, only 2 levels of translation tables are
-used but the memory layout is the same.
+AArch64 Linux uses either 3 levels or 4 levels of translation tables
+with the 4KB page configuration, allowing 39-bit (512GB) or 48-bit
+(256TB) virtual addresses, respectively, for both user and kernel. With
+64KB pages, only 2 levels of translation tables, allowing 42-bit (4TB)
+virtual address, are used but the memory layout is the same.
 
-User addresses have bits 63:39 set to 0 while the kernel addresses have
+User addresses have bits 63:48 set to 0 while the kernel addresses have
 the same bits set to 1. TTBRx selection is given by bit 63 of the
 virtual address. The swapper_pg_dir contains only kernel (global)
 mappings while the user pgd contains only user (non-global) mappings.
@@ -21,58 +21,40 @@ The swapper_pgd_dir address is written to TTBR1 and never written to
 TTBR0.
 
 
-AArch64 Linux memory layout with 4KB pages:
+AArch64 Linux memory layout with 4KB pages + 3 levels:
 
 Start			End			Size		Use
 -----------------------------------------------------------------------
 0000000000000000	0000007fffffffff	 512GB		user
+ffffff8000000000	ffffffffffffffff	 512GB		kernel
 
-ffffff8000000000	ffffffbbfffeffff	~240GB		vmalloc
 
-ffffffbbffff0000	ffffffbbffffffff	  64KB		[guard page]
+AArch64 Linux memory layout with 4KB pages + 4 levels:
 
-ffffffbc00000000	ffffffbdffffffff	   8GB		vmemmap
-
-ffffffbe00000000	ffffffbffbbfffff	  ~8GB		[guard, future vmmemap]
-
-ffffffbffa000000	ffffffbffaffffff	  16MB		PCI I/O space
-
-ffffffbffb000000	ffffffbffbbfffff	  12MB		[guard]
-
-ffffffbffbc00000	ffffffbffbdfffff	   2MB		fixed mappings
-
-ffffffbffbe00000	ffffffbffbffffff	   2MB		[guard]
-
-ffffffbffc000000	ffffffbfffffffff	  64MB		modules
-
-ffffffc000000000	ffffffffffffffff	 256GB		kernel logical memory map
+Start			End			Size		Use
+-----------------------------------------------------------------------
+0000000000000000	0000ffffffffffff	 256TB		user
+ffff000000000000	ffffffffffffffff	 256TB		kernel
 
 
-AArch64 Linux memory layout with 64KB pages:
+AArch64 Linux memory layout with 64KB pages + 2 levels:
 
 Start			End			Size		Use
 -----------------------------------------------------------------------
 0000000000000000	000003ffffffffff	   4TB		user
+fffffc0000000000	ffffffffffffffff	   4TB		kernel
 
-fffffc0000000000	fffffdfbfffeffff	  ~2TB		vmalloc
 
-fffffdfbffff0000	fffffdfbffffffff	  64KB		[guard page]
+AArch64 Linux memory layout with 64KB pages + 3 levels:
 
-fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
-
-fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
-
-fffffdfffa000000	fffffdfffaffffff	  16MB		PCI I/O space
-
-fffffdfffb000000	fffffdfffbbfffff	  12MB		[guard]
-
-fffffdfffbc00000	fffffdfffbdfffff	   2MB		fixed mappings
-
-fffffdfffbe00000	fffffdfffbffffff	   2MB		[guard]
+Start			End			Size		Use
+-----------------------------------------------------------------------
+0000000000000000	0000ffffffffffff	 256TB		user
+ffff000000000000	ffffffffffffffff	 256TB		kernel
 
-fffffdfffc000000	fffffdffffffffff	  64MB		modules
 
-fffffe0000000000	ffffffffffffffff	   2TB		kernel logical memory map
+For details of the virtual kernel memory layout please see the kernel
+booting log.
 
 
 Translation table lookup with 4KB pages:
@@ -86,7 +68,7 @@ Translation table lookup with 4KB pages:
  |                 |         |         |         +-> [20:12] L3 index
  |                 |         |         +-----------> [29:21] L2 index
  |                 |         +---------------------> [38:30] L1 index
- |                 +-------------------------------> [47:39] L0 index (not used)
+ |                 +-------------------------------> [47:39] L0 index
  +-------------------------------------------------> [63] TTBR0/1
 
 
@@ -99,10 +81,11 @@ Translation table lookup with 64KB pages:
  |                 |    |               |              v
  |                 |    |               |            [15:0]  in-page offset
  |                 |    |               +----------> [28:16] L3 index
- |                 |    +--------------------------> [41:29] L2 index (only 38:29 used)
- |                 +-------------------------------> [47:42] L1 index (not used)
+ |                 |    +--------------------------> [41:29] L2 index
+ |                 +-------------------------------> [47:42] L1 index
  +-------------------------------------------------> [63] TTBR0/1
 
+
 When using KVM, the hypervisor maps kernel pages in EL2, at a fixed
 offset from the kernel VA (top 24bits of the kernel VA set to zero):
 
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 821de56d158..10c949b293e 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -599,6 +599,20 @@ fork. If this method returns 0 (success) then this should remain valid
 while the caller holds cgroup_mutex and it is ensured that either
 attach() or cancel_attach() will be called in future.
 
+void css_reset(struct cgroup_subsys_state *css)
+(cgroup_mutex held by caller)
+
+An optional operation which should restore @css's configuration to the
+initial state.  This is currently only used on the unified hierarchy
+when a subsystem is disabled on a cgroup through
+"cgroup.subtree_control" but should remain enabled because other
+subsystems depend on it.  cgroup core makes such a css invisible by
+removing the associated interface files and invokes this callback so
+that the hidden subsystem can return to the initial neutral state.
+This prevents unexpected resource control from a hidden css and
+ensures that the configuration is in the initial state when it is made
+visible again later.
+
 void cancel_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 (cgroup_mutex held by caller)
 
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index b3429aec444..02ab997a1ed 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -458,15 +458,11 @@ About use_hierarchy, see Section 6.
 
 5.1 force_empty
   memory.force_empty interface is provided to make cgroup's memory usage empty.
-  You can use this interface only when the cgroup has no tasks.
   When writing anything to this
 
   # echo 0 > memory.force_empty
 
-  Almost all pages tracked by this memory cgroup will be unmapped and freed.
-  Some pages cannot be freed because they are locked or in-use. Such pages are
-  moved to parent (if use_hierarchy==1) or root (if use_hierarchy==0) and this
-  cgroup will be empty.
+  the cgroup will be reclaimed and as many pages reclaimed as possible.
 
   The typical use case for this interface is before calling rmdir().
   Because rmdir() moves all pages to parent, some out-of-use page caches can be
diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt
new file mode 100644
index 00000000000..4f456327786
--- /dev/null
+++ b/Documentation/cgroups/unified-hierarchy.txt
@@ -0,0 +1,382 @@
+
+Cgroup unified hierarchy
+
+April, 2014		Tejun Heo <tj@kernel.org>
+
+This document describes the changes made by unified hierarchy and
+their rationales.  It will eventually be merged into the main cgroup
+documentation.
+
+CONTENTS
+
+1. Background
+2. Basic Operation
+  2-1. Mounting
+  2-2. cgroup.subtree_control
+  2-3. cgroup.controllers
+3. Structural Constraints
+  3-1. Top-down
+  3-2. No internal tasks
+4. Other Changes
+  4-1. [Un]populated Notification
+  4-2. Other Core Changes
+  4-3. Per-Controller Changes
+    4-3-1. blkio
+    4-3-2. cpuset
+    4-3-3. memory
+5. Planned Changes
+  5-1. CAP for resource control
+
+
+1. Background
+
+cgroup allows an arbitrary number of hierarchies and each hierarchy
+can host any number of controllers.  While this seems to provide a
+high level of flexibility, it isn't quite useful in practice.
+
+For example, as there is only one instance of each controller, utility
+type controllers such as freezer which can be useful in all
+hierarchies can only be used in one.  The issue is exacerbated by the
+fact that controllers can't be moved around once hierarchies are
+populated.  Another issue is that all controllers bound to a hierarchy
+are forced to have exactly the same view of the hierarchy.  It isn't
+possible to vary the granularity depending on the specific controller.
+
+In practice, these issues heavily limit which controllers can be put
+on the same hierarchy and most configurations resort to putting each
+controller on its own hierarchy.  Only closely related ones, such as
+the cpu and cpuacct controllers, make sense to put on the same
+hierarchy.  This often means that userland ends up managing multiple
+similar hierarchies repeating the same steps on each hierarchy
+whenever a hierarchy management operation is necessary.
+
+Unfortunately, support for multiple hierarchies comes at a steep cost.
+Internal implementation in cgroup core proper is dazzlingly
+complicated but more importantly the support for multiple hierarchies
+restricts how cgroup is used in general and what controllers can do.
+
+There's no limit on how many hierarchies there may be, which means
+that a task's cgroup membership can't be described in finite length.
+The key may contain any varying number of entries and is unlimited in
+length, which makes it highly awkward to handle and leads to addition
+of controllers which exist only to identify membership, which in turn
+exacerbates the original problem.
+
+Also, as a controller can't have any expectation regarding what shape
+of hierarchies other controllers would be on, each controller has to
+assume that all other controllers are operating on completely
+orthogonal hierarchies.  This makes it impossible, or at least very
+cumbersome, for controllers to cooperate with each other.
+
+In most use cases, putting controllers on hierarchies which are
+completely orthogonal to each other isn't necessary.  What usually is
+called for is the ability to have differing levels of granularity
+depending on the specific controller.  In other words, hierarchy may
+be collapsed from leaf towards root when viewed from specific
+controllers.  For example, a given configuration might not care about
+how memory is distributed beyond a certain level while still wanting
+to control how CPU cycles are distributed.
+
+Unified hierarchy is the next version of cgroup interface.  It aims to
+address the aforementioned issues by having more structure while
+retaining enough flexibility for most use cases.  Various other
+general and controller-specific interface issues are also addressed in
+the process.
+
+
+2. Basic Operation
+
+2-1. Mounting
+
+Currently, unified hierarchy can be mounted with the following mount
+command.  Note that this is still under development and scheduled to
+change soon.
+
+ mount -t cgroup -o __DEVEL__sane_behavior cgroup $MOUNT_POINT
+
+All controllers which support the unified hierarchy and are not bound
+to other hierarchies are automatically bound to unified hierarchy and
+show up at the root of it.  Controllers which are enabled only in the
+root of unified hierarchy can be bound to other hierarchies.  This
+allows mixing unified hierarchy with the traditional multiple
+hierarchies in a fully backward compatible way.
+
+For development purposes, the following boot parameter makes all
+controllers to appear on the unified hierarchy whether supported or
+not.
+
+ cgroup__DEVEL__legacy_files_on_dfl
+
+A controller can be moved across hierarchies only after the controller
+is no longer referenced in its current hierarchy.  Because per-cgroup
+controller states are destroyed asynchronously and controllers may
+have lingering references, a controller may not show up immediately on
+the unified hierarchy after the final umount of the previous
+hierarchy.  Similarly, a controller should be fully disabled to be
+moved out of the unified hierarchy and it may take some time for the
+disabled controller to become available for other hierarchies;
+furthermore, due to dependencies among controllers, other controllers
+may need to be disabled too.
+
+While useful for development and manual configurations, dynamically
+moving controllers between the unified and other hierarchies is
+strongly discouraged for production use.  It is recommended to decide
+the hierarchies and controller associations before starting using the
+controllers.
+
+
+2-2. cgroup.subtree_control
+
+All cgroups on unified hierarchy have a "cgroup.subtree_control" file
+which governs which controllers are enabled on the children of the
+cgroup.  Let's assume a hierarchy like the following.
+
+  root - A - B - C
+               \ D
+
+root's "cgroup.subtree_control" file determines which controllers are
+enabled on A.  A's on B.  B's on C and D.  This coincides with the
+fact that controllers on the immediate sub-level are used to
+distribute the resources of the parent.  In fact, it's natural to
+assume that resource control knobs of a child belong to its parent.
+Enabling a controller in a "cgroup.subtree_control" file declares that
+distribution of the respective resources of the cgroup will be
+controlled.  Note that this means that controller enable states are
+shared among siblings.
+
+When read, the file contains a space-separated list of currently
+enabled controllers.  A write to the file should contain a
+space-separated list of controllers with '+' or '-' prefixed (without
+the quotes).  Controllers prefixed with '+' are enabled and '-'
+disabled.  If a controller is listed multiple times, the last entry
+wins.  The specific operations are executed atomically - either all
+succeed or fail.
+
+
+2-3. cgroup.controllers
+
+Read-only "cgroup.controllers" file contains a space-separated list of
+controllers which can be enabled in the cgroup's
+"cgroup.subtree_control" file.
+
+In the root cgroup, this lists controllers which are not bound to
+other hierarchies and the content changes as controllers are bound to
+and unbound from other hierarchies.
+
+In non-root cgroups, the content of this file equals that of the
+parent's "cgroup.subtree_control" file as only controllers enabled
+from the parent can be used in its children.
+
+
+3. Structural Constraints
+
+3-1. Top-down
+
+As it doesn't make sense to nest control of an uncontrolled resource,
+all non-root "cgroup.subtree_control" files can only contain
+controllers which are enabled in the parent's "cgroup.subtree_control"
+file.  A controller can be enabled only if the parent has the
+controller enabled and a controller can't be disabled if one or more
+children have it enabled.
+
+
+3-2. No internal tasks
+
+One long-standing issue that cgroup faces is the competition between
+tasks belonging to the parent cgroup and its children cgroups.  This
+is inherently nasty as two different types of entities compete and
+there is no agreed-upon obvious way to handle it.  Different
+controllers are doing different things.
+
+The cpu controller considers tasks and cgroups as equivalents and maps
+nice levels to cgroup weights.  This works for some cases but falls
+flat when children should be allocated specific ratios of CPU cycles
+and the number of internal tasks fluctuates - the ratios constantly
+change as the number of competing entities fluctuates.  There also are
+other issues.  The mapping from nice level to weight isn't obvious or
+universal, and there are various other knobs which simply aren't
+available for tasks.
+
+The blkio controller implicitly creates a hidden leaf node for each
+cgroup to host the tasks.  The hidden leaf has its own copies of all
+the knobs with "leaf_" prefixed.  While this allows equivalent control
+over internal tasks, it's with serious drawbacks.  It always adds an
+extra layer of nesting which may not be necessary, makes the interface
+messy and significantly complicates the implementation.
+
+The memory controller currently doesn't have a way to control what
+happens between internal tasks and child cgroups and the behavior is
+not clearly defined.  There have been attempts to add ad-hoc behaviors
+and knobs to tailor the behavior to specific workloads.  Continuing
+this direction will lead to problems which will be extremely difficult
+to resolve in the long term.
+
+Multiple controllers struggle with internal tasks and came up with
+different ways to deal with it; unfortunately, all the approaches in
+use now are severely flawed and, furthermore, the widely different
+behaviors make cgroup as whole highly inconsistent.
+
+It is clear that this is something which needs to be addressed from
+cgroup core proper in a uniform way so that controllers don't need to
+worry about it and cgroup as a whole shows a consistent and logical
+behavior.  To achieve that, unified hierarchy enforces the following
+structural constraint:
+
+ Except for the root, only cgroups which don't contain any task may
+ have controllers enabled in their "cgroup.subtree_control" files.
+
+Combined with other properties, this guarantees that, when a
+controller is looking at the part of the hierarchy which has it
+enabled, tasks are always only on the leaves.  This rules out
+situations where child cgroups compete against internal tasks of the
+parent.
+
+There are two things to note.  Firstly, the root cgroup is exempt from
+the restriction.  Root contains tasks and anonymous resource
+consumption which can't be associated with any other cgroup and
+requires special treatment from most controllers.  How resource
+consumption in the root cgroup is governed is up to each controller.
+
+Secondly, the restriction doesn't take effect if there is no enabled
+controller in the cgroup's "cgroup.subtree_control" file.  This is
+important as otherwise it wouldn't be possible to create children of a
+populated cgroup.  To control resource distribution of a cgroup, the
+cgroup must create children and transfer all its tasks to the children
+before enabling controllers in its "cgroup.subtree_control" file.
+
+
+4. Other Changes
+
+4-1. [Un]populated Notification
+
+cgroup users often need a way to determine when a cgroup's
+subhierarchy becomes empty so that it can be cleaned up.  cgroup
+currently provides release_agent for it; unfortunately, this mechanism
+is riddled with issues.
+
+- It delivers events by forking and execing a userland binary
+  specified as the release_agent.  This is a long deprecated method of
+  notification delivery.  It's extremely heavy, slow and cumbersome to
+  integrate with larger infrastructure.
+
+- There is single monitoring point at the root.  There's no way to
+  delegate management of a subtree.
+
+- The event isn't recursive.  It triggers when a cgroup doesn't have
+  any tasks or child cgroups.  Events for internal nodes trigger only
+  after all children are removed.  This again makes it impossible to
+  delegate management of a subtree.
+
+- Events are filtered from the kernel side.  A "notify_on_release"
+  file is used to subscribe to or suppress release events.  This is
+  unnecessarily complicated and probably done this way because event
+  delivery itself was expensive.
+
+Unified hierarchy implements an interface file "cgroup.populated"
+which can be used to monitor whether the cgroup's subhierarchy has
+tasks in it or not.  Its value is 0 if there is no task in the cgroup
+and its descendants; otherwise, 1.  poll and [id]notify events are
+triggered when the value changes.
+
+This is significantly lighter and simpler and trivially allows
+delegating management of subhierarchy - subhierarchy monitoring can
+block further propagation simply by putting itself or another process
+in the subhierarchy and monitor events that it's interested in from
+there without interfering with monitoring higher in the tree.
+
+In unified hierarchy, the release_agent mechanism is no longer
+supported and the interface files "release_agent" and
+"notify_on_release" do not exist.
+
+
+4-2. Other Core Changes
+
+- None of the mount options is allowed.
+
+- remount is disallowed.
+
+- rename(2) is disallowed.
+
+- The "tasks" file is removed.  Everything should at process
+  granularity.  Use the "cgroup.procs" file instead.
+
+- The "cgroup.procs" file is not sorted.  pids will be unique unless
+  they got recycled in-between reads.
+
+- The "cgroup.clone_children" file is removed.
+
+
+4-3. Per-Controller Changes
+
+4-3-1. blkio
+
+- blk-throttle becomes properly hierarchical.
+
+
+4-3-2. cpuset
+
+- Tasks are kept in empty cpusets after hotplug and take on the masks
+  of the nearest non-empty ancestor, instead of being moved to it.
+
+- A task can be moved into an empty cpuset, and again it takes on the
+  masks of the nearest non-empty ancestor.
+
+
+4-3-3. memory
+
+- use_hierarchy is on by default and the cgroup file for the flag is
+  not created.
+
+
+5. Planned Changes
+
+5-1. CAP for resource control
+
+Unified hierarchy will require one of the capabilities(7), which is
+yet to be decided, for all resource control related knobs.  Process
+organization operations - creation of sub-cgroups and migration of
+processes in sub-hierarchies may be delegated by changing the
+ownership and/or permissions on the cgroup directory and
+"cgroup.procs" interface file; however, all operations which affect
+resource control - writes to a "cgroup.subtree_control" file or any
+controller-specific knobs - will require an explicit CAP privilege.
+
+This, in part, is to prevent the cgroup interface from being
+inadvertently promoted to programmable API used by non-privileged
+binaries.  cgroup exposes various aspects of the system in ways which
+aren't properly abstracted for direct consumption by regular programs.
+This is an administration interface much closer to sysctl knobs than
+system calls.  Even the basic access model, being filesystem path
+based, isn't suitable for direct consumption.  There's no way to
+access "my cgroup" in a race-free way or make multiple operations
+atomic against migration to another cgroup.
+
+Another aspect is that, for better or for worse, the cgroup interface
+goes through far less scrutiny than regular interfaces for
+unprivileged userland.  The upside is that cgroup is able to expose
+useful features which may not be suitable for general consumption in a
+reasonable time frame.  It provides a relatively short path between
+internal details and userland-visible interface.  Of course, this
+shortcut comes with high risk.  We go through what we go through for
+general kernel APIs for good reasons.  It may end up leaking internal
+details in a way which can exert significant pain by locking the
+kernel into a contract that can't be maintained in a reasonable
+manner.
+
+Also, due to the specific nature, cgroup and its controllers don't
+tend to attract attention from a wide scope of developers.  cgroup's
+short history is already fraught with severely mis-designed
+interfaces, unnecessary commitments to and exposing of internal
+details, broken and dangerous implementations of various features.
+
+Keeping cgroup as an administration interface is both advantageous for
+its role and imperative given its nature.  Some of the cgroup features
+may make sense for unprivileged access.  If deemed justified, those
+must be further abstracted and implemented as a different interface,
+be it a system call or process-private filesystem, and survive through
+the scrutiny that any interface for general consumption is required to
+go through.
+
+Requiring CAP is not a complete solution but should serve as a
+significant deterrent against spraying cgroup usages in non-privileged
+programs.
diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt
index b045fe54986..14f4e6336d8 100644
--- a/Documentation/cpu-freq/cpu-drivers.txt
+++ b/Documentation/cpu-freq/cpu-drivers.txt
@@ -26,6 +26,7 @@ Contents:
 1.4  target/target_index or setpolicy?
 1.5  target/target_index
 1.6  setpolicy
+1.7  get_intermediate and target_intermediate
 2.   Frequency Table Helpers
 
 
@@ -79,6 +80,10 @@ cpufreq_driver.attr -		A pointer to a NULL-terminated list of
 				"struct freq_attr" which allow to
 				export values to sysfs.
 
+cpufreq_driver.get_intermediate
+and target_intermediate		Used to switch to stable frequency while
+				changing CPU frequency.
+
 
 1.2 Per-CPU Initialization
 --------------------------
@@ -151,7 +156,7 @@ Some cpufreq-capable processors switch the frequency between certain
 limits on their own. These shall use the ->setpolicy call
 
 
-1.4. target/target_index
+1.5. target/target_index
 -------------
 
 The target_index call has two arguments: struct cpufreq_policy *policy,
@@ -160,6 +165,9 @@ and unsigned int index (into the exposed frequency table).
 The CPUfreq driver must set the new frequency when called here. The
 actual frequency must be determined by freq_table[index].frequency.
 
+It should always restore to earlier frequency (i.e. policy->restore_freq) in
+case of errors, even if we switched to intermediate frequency earlier.
+
 Deprecated:
 ----------
 The target call has three arguments: struct cpufreq_policy *policy,
@@ -179,7 +187,7 @@ Here again the frequency table helper might assist you - see section 2
 for details.
 
 
-1.5 setpolicy
+1.6 setpolicy
 ---------------
 
 The setpolicy call only takes a struct cpufreq_policy *policy as
@@ -190,6 +198,23 @@ setting when policy->policy is CPUFREQ_POLICY_PERFORMANCE, and a
 powersaving-oriented setting when CPUFREQ_POLICY_POWERSAVE. Also check
 the reference implementation in drivers/cpufreq/longrun.c
 
+1.7 get_intermediate and target_intermediate
+--------------------------------------------
+
+Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION unset.
+
+get_intermediate should return a stable intermediate frequency platform wants to
+switch to, and target_intermediate() should set CPU to to that frequency, before
+jumping to the frequency corresponding to 'index'. Core will take care of
+sending notifications and driver doesn't have to handle them in
+target_intermediate() or target_index().
+
+Drivers can return '0' from get_intermediate() in case they don't wish to switch
+to intermediate frequency for some target frequency. In that case core will
+directly call ->target_index().
+
+NOTE: ->target_index() should restore to policy->restore_freq in case of
+failures as core would send notifications for that.
 
 
 2. Frequency Table Helpers
diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt
index e742d21dbd9..a69ffe1d54d 100644
--- a/Documentation/cpu-freq/intel-pstate.txt
+++ b/Documentation/cpu-freq/intel-pstate.txt
@@ -15,10 +15,13 @@ New sysfs files for controlling P state selection have been added to
 /sys/devices/system/cpu/intel_pstate/
 
       max_perf_pct: limits the maximum P state that will be requested by
-      the driver stated as a percentage of the available performance.
+      the driver stated as a percentage of the available performance. The
+      available (P states) performance may be reduced by the no_turbo
+      setting described below.
 
       min_perf_pct: limits the minimum P state that will be  requested by
-      the driver stated as a percentage of the available performance.
+      the driver stated as a percentage of the max (non-turbo)
+      performance level.
 
       no_turbo: limits the driver to selecting P states below the turbo
       frequency range.
diff --git a/Documentation/devicetree/bindings/arm/armada-38x.txt b/Documentation/devicetree/bindings/arm/armada-38x.txt
index 11f2330a655..ad9f8ed4d9b 100644
--- a/Documentation/devicetree/bindings/arm/armada-38x.txt
+++ b/Documentation/devicetree/bindings/arm/armada-38x.txt
@@ -6,5 +6,15 @@ following property:
 
 Required root node property:
 
- - compatible: must contain either "marvell,armada380" or
-   "marvell,armada385" depending on the variant of the SoC being used.
+ - compatible: must contain "marvell,armada380"
+
+In addition, boards using the Marvell Armada 385 SoC shall have the
+following property before the previous one:
+
+Required root node property:
+
+compatible: must contain "marvell,armada385"
+
+Example:
+
+compatible = "marvell,a385-rd", "marvell,armada385", "marvell,armada380";
diff --git a/Documentation/devicetree/bindings/arm/exynos/power_domain.txt b/Documentation/devicetree/bindings/arm/exynos/power_domain.txt
index 5216b419016..8b4f7b7fe88 100644
--- a/Documentation/devicetree/bindings/arm/exynos/power_domain.txt
+++ b/Documentation/devicetree/bindings/arm/exynos/power_domain.txt
@@ -9,6 +9,18 @@ Required Properties:
 - reg: physical base address of the controller and length of memory mapped
     region.
 
+Optional Properties:
+- clocks: List of clock handles. The parent clocks of the input clocks to the
+	devices in this power domain are set to oscclk before power gating
+	and restored back after powering on a domain. This is required for
+	all domains which are powered on and off and not required for unused
+	domains.
+- clock-names: The following clocks can be specified:
+	- oscclk: Oscillator clock.
+	- pclkN, clkN: Pairs of parent of input clock and input clock to the
+		devices in this power domain. Maximum of 4 pairs (N = 0 to 3)
+		are supported currently.
+
 Node of a device using power domains must have a samsung,power-domain property
 defined with a phandle to respective power domain.
 
@@ -19,6 +31,14 @@ Example:
 		reg = <0x10023C00 0x10>;
 	};
 
+	mfc_pd: power-domain@10044060 {
+		compatible = "samsung,exynos4210-pd";
+		reg = <0x10044060 0x20>;
+		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MOUT_SW_ACLK333>,
+			<&clock CLK_MOUT_USER_ACLK333>;
+		clock-names = "oscclk", "pclk0", "clk0";
+	};
+
 Example of the node using power domain:
 
 	node {
diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
index b513cb8196f..af527ee111c 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -40,6 +40,9 @@ Optional properties:
 - arm,filter-ranges : <start length> Starting address and length of window to
   filter. Addresses in the filter window are directed to the M1 port. Other
   addresses will go to the M0 port.
+- arm,io-coherent : indicates that the system is operating in an hardware
+  I/O coherent mode. Valid only when the arm,pl310-cache compatible
+  string is used.
 - interrupts : 1 combined interrupt.
 - cache-id-part: cache id part number to be used if it is not present
   on hardware
diff --git a/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt b/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
index 5d49f2b37f6..832fe8cc24d 100644
--- a/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/exynos-adc.txt
@@ -48,7 +48,7 @@ adc@12D10000 {
 
 	/* NTC thermistor is a hwmon device */
 	ncp15wb473@0 {
-		compatible = "ntc,ncp15wb473";
+		compatible = "murata,ncp15wb473";
 		pullup-uv = <1800000>;
 		pullup-ohm = <47000>;
 		pulldown-ohm = <0>;
diff --git a/Documentation/devicetree/bindings/arm/samsung/pmu.txt b/Documentation/devicetree/bindings/arm/samsung/pmu.txt
index 2a4ab046a8a..f9865e77e0b 100644
--- a/Documentation/devicetree/bindings/arm/samsung/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/pmu.txt
@@ -12,8 +12,38 @@ Properties:
 
  - reg : offset and length of the register set.
 
+ - #clock-cells : must be <1>, since PMU requires once cell as clock specifier.
+		The single specifier cell is used as index to list of clocks
+		provided by PMU, which is currently:
+			0 : SoC clock output (CLKOUT pin)
+
+ - clock-names : list of clock names for particular CLKOUT mux inputs in
+		following format:
+			"clkoutN", where N is a decimal number corresponding to
+			CLKOUT mux control bits value for given input, e.g.
+				"clkout0", "clkout7", "clkout15".
+
+ - clocks : list of phandles and specifiers to all input clocks listed in
+		clock-names property.
+
 Example :
 pmu_system_controller: system-controller@10040000 {
 	compatible = "samsung,exynos5250-pmu", "syscon";
 	reg = <0x10040000 0x5000>;
+	#clock-cells = <1>;
+	clock-names = "clkout0", "clkout1", "clkout2", "clkout3",
+			"clkout4", "clkout8", "clkout9";
+	clocks = <&clock CLK_OUT_DMC>, <&clock CLK_OUT_TOP>,
+		<&clock CLK_OUT_LEFTBUS>, <&clock CLK_OUT_RIGHTBUS>,
+		<&clock CLK_OUT_CPU>, <&clock CLK_XXTI>,
+		<&clock CLK_XUSBXTI>;
+};
+
+Example of clock consumer :
+
+usb3503: usb3503@08 {
+	/* ... */
+	clock-names = "refclk";
+	clocks = <&pmu_system_controller 0>;
+	/* ... */
 };
diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt
index 48b285ffa3a..4ab09f2202d 100644
--- a/Documentation/devicetree/bindings/ata/ahci-platform.txt
+++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt
@@ -3,22 +3,43 @@
 SATA nodes are defined to describe on-chip Serial ATA controllers.
 Each SATA controller should have its own node.
 
+It is possible, but not required, to represent each port as a sub-node.
+It allows to enable each port independently when dealing with multiple
+PHYs.
+
 Required properties:
-- compatible        : compatible list, one of "snps,spear-ahci",
-                      "snps,exynos5440-ahci", "ibm,476gtr-ahci",
-                      "allwinner,sun4i-a10-ahci", "fsl,imx53-ahci"
-                      "fsl,imx6q-ahci" or "snps,dwc-ahci"
+- compatible        : compatible string, one of:
+  - "allwinner,sun4i-a10-ahci"
+  - "hisilicon,hisi-ahci"
+  - "ibm,476gtr-ahci"
+  - "marvell,armada-380-ahci"
+  - "snps,dwc-ahci"
+  - "snps,exynos5440-ahci"
+  - "snps,spear-ahci"
+  - "generic-ahci"
 - interrupts        : <interrupt mapping for SATA IRQ>
 - reg               : <registers mapping>
 
+Please note that when using "generic-ahci" you must also specify a SoC specific
+compatible:
+	compatible = "manufacturer,soc-model-ahci", "generic-ahci";
+
 Optional properties:
 - dma-coherent      : Present if dma operations are coherent
 - clocks            : a list of phandle + clock specifier pairs
 - target-supply     : regulator for SATA target power
+- phys              : reference to the SATA PHY node
+- phy-names         : must be "sata-phy"
+
+Required properties when using sub-nodes:
+- #address-cells    : number of cells to encode an address
+- #size-cells       : number of cells representing the size of an address
+
+
+Sub-nodes required properties:
+- reg               : the port number
+- phys              : reference to the SATA PHY node
 
-"fsl,imx53-ahci", "fsl,imx6q-ahci" required properties:
-- clocks            : must contain the sata, sata_ref and ahb clocks
-- clock-names       : must contain "ahb" for the ahb clock
 
 Examples:
         sata@ffe08000 {
@@ -34,3 +55,23 @@ Examples:
 		clocks = <&pll6 0>, <&ahb_gates 25>;
 		target-supply = <&reg_ahci_5v>;
 	};
+
+With sub-nodes:
+	sata@f7e90000 {
+		compatible = "marvell,berlin2q-achi", "generic-ahci";
+		reg = <0xe90000 0x1000>;
+		interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&chip CLKID_SATA>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		sata0: sata-port@0 {
+			reg = <0>;
+			phys = <&sata_phy 0>;
+		};
+
+		sata1: sata-port@1 {
+			reg = <1>;
+			phys = <&sata_phy 1>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/ata/ahci-st.txt b/Documentation/devicetree/bindings/ata/ahci-st.txt
new file mode 100644
index 00000000000..0574a77a0b9
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/ahci-st.txt
@@ -0,0 +1,31 @@
+STMicroelectronics STi SATA controller
+
+This binding describes a SATA device.
+
+Required properties:
+ - compatible	   : Must be "st,sti-ahci"
+ - reg		   : Physical base addresses and length of register sets
+ - interrupts	   : Interrupt associated with the SATA device
+ - interrupt-names :   Associated name must be; "hostc"
+ - resets	   : The power-down and soft-reset lines of SATA IP
+ - reset-names	   :   Associated names must be; "pwr-dwn" and "sw-rst"
+ - clocks	   : The phandle for the clock
+ - clock-names	   :   Associated name must be; "ahci_clk"
+ - phys		   : The phandle for the PHY device
+ - phy-names	   :   Associated name must be; "ahci_phy"
+
+Example:
+
+	sata0: sata@fe380000 {
+		compatible      = "st,sti-ahci";
+		reg             = <0xfe380000 0x1000>;
+		interrupts      = <GIC_SPI 157 IRQ_TYPE_NONE>;
+		interrupt-names = "hostc";
+		phys	        = <&miphy365x_phy MIPHY_PORT_0 MIPHY_TYPE_SATA>;
+		phy-names       = "ahci_phy";
+		resets	        = <&powerdown STIH416_SATA0_POWERDOWN>,
+				  <&softreset STIH416_SATA0_SOFTRESET>;
+		reset-names     = "pwr-dwn", "sw-rst";
+		clocks	        = <&clk_s_a0_ls CLK_ICN_REG>;
+		clock-names     = "ahci_clk";
+	};
diff --git a/Documentation/devicetree/bindings/ata/imx-sata.txt b/Documentation/devicetree/bindings/ata/imx-sata.txt
new file mode 100644
index 00000000000..fa511db1840
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/imx-sata.txt
@@ -0,0 +1,36 @@
+* Freescale i.MX AHCI SATA Controller
+
+The Freescale i.MX SATA controller mostly conforms to the AHCI interface
+with some special extensions at integration level.
+
+Required properties:
+- compatible : should be one of the following:
+   - "fsl,imx53-ahci" for i.MX53 SATA controller
+   - "fsl,imx6q-ahci" for i.MX6Q SATA controller
+- interrupts : interrupt mapping for SATA IRQ
+- reg : registers mapping
+- clocks : list of clock specifiers, must contain an entry for each
+  required entry in clock-names
+- clock-names : should include "sata", "sata_ref" and "ahb" entries
+
+Optional properties:
+- fsl,transmit-level-mV : transmit voltage level, in millivolts.
+- fsl,transmit-boost-mdB : transmit boost level, in milli-decibels
+- fsl,transmit-atten-16ths : transmit attenuation, in 16ths
+- fsl,receive-eq-mdB : receive equalisation, in milli-decibels
+  Please refer to the technical documentation or the driver source code
+  for the list of legal values for these options.
+- fsl,no-spread-spectrum : disable spread-spectrum clocking on the SATA
+  link.
+
+Examples:
+
+sata@02200000 {
+	compatible = "fsl,imx6q-ahci";
+	reg = <0x02200000 0x4000>;
+	interrupts = <0 39 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&clks IMX6QDL_CLK_SATA>,
+		 <&clks IMX6QDL_CLK_SATA_REF_100M>,
+		 <&clks IMX6QDL_CLK_AHB>;
+	clock-names = "sata", "sata_ref", "ahb";
+};
diff --git a/Documentation/devicetree/bindings/ata/tegra-sata.txt b/Documentation/devicetree/bindings/ata/tegra-sata.txt
new file mode 100644
index 00000000000..946f2072570
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/tegra-sata.txt
@@ -0,0 +1,30 @@
+Tegra124 SoC SATA AHCI controller
+
+Required properties :
+- compatible : "nvidia,tegra124-ahci".
+- reg : Should contain 2 entries:
+  - AHCI register set (SATA BAR5)
+  - SATA register set
+- interrupts : Defines the interrupt used by SATA
+- clocks : Must contain an entry for each entry in clock-names.
+  See ../clocks/clock-bindings.txt for details.
+- clock-names : Must include the following entries:
+  - sata
+  - sata-oob
+  - cml1
+  - pll_e
+- resets : Must contain an entry for each entry in reset-names.
+  See ../reset/reset.txt for details.
+- reset-names : Must include the following entries:
+  - sata
+  - sata-oob
+  - sata-cold
+- phys : Must contain an entry for each entry in phy-names.
+  See ../phy/phy-bindings.txt for details.
+- phy-names : Must include the following entries:
+  - sata-phy : XUSB PADCTL SATA PHY
+- hvdd-supply : Defines the SATA HVDD regulator
+- vddio-supply : Defines the SATA VDDIO regulator
+- avdd-supply : Defines the SATA AVDD regulator
+- target-5v-supply : Defines the SATA 5V power regulator
+- target-12v-supply : Defines the SATA 12V power regulator
diff --git a/Documentation/devicetree/bindings/clock/clk-palmas-clk32kg-clocks.txt b/Documentation/devicetree/bindings/clock/clk-palmas-clk32kg-clocks.txt
new file mode 100644
index 00000000000..4208886d834
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/clk-palmas-clk32kg-clocks.txt
@@ -0,0 +1,35 @@
+* Palmas 32KHz clocks *
+
+Palmas device has two clock output pins for 32KHz, KG and KG_AUDIO.
+
+This binding uses the common clock binding ./clock-bindings.txt.
+
+Required properties:
+- compatible :	"ti,palmas-clk32kg" for clk32kg clock
+		"ti,palmas-clk32kgaudio" for clk32kgaudio clock
+- #clock-cells : shall be set to 0.
+
+Optional property:
+- ti,external-sleep-control: The external enable input pins controlled the
+	enable/disable of clocks.  The external enable input pins ENABLE1,
+	ENABLE2 and NSLEEP. The valid values for the external pins are:
+		PALMAS_EXT_CONTROL_PIN_ENABLE1 for ENABLE1 pin
+		PALMAS_EXT_CONTROL_PIN_ENABLE2 for ENABLE2 pin
+		PALMAS_EXT_CONTROL_PIN_NSLEEP for NSLEEP pin
+	Option 0 or missing this property means the clock is enabled/disabled
+	via register access and these pins do not have any control.
+	The macros of external control pins for DTS is defined at
+	dt-bindings/mfd/palmas.h
+
+Example:
+	#include <dt-bindings/mfd/palmas.h>
+	...
+	palmas: tps65913@58 {
+		...
+		clk32kg: palmas_clk32k@0 {
+			compatible = "ti,palmas-clk32kg";
+			#clock-cells = <0>;
+			ti,external-sleep-control = <PALMAS_EXT_CONTROL_PIN_NSLEEP>;
+		};
+		...
+	};
diff --git a/Documentation/devicetree/bindings/clock/clock-bindings.txt b/Documentation/devicetree/bindings/clock/clock-bindings.txt
index f15787817d6..06fc6d541c8 100644
--- a/Documentation/devicetree/bindings/clock/clock-bindings.txt
+++ b/Documentation/devicetree/bindings/clock/clock-bindings.txt
@@ -131,3 +131,39 @@ clock signal, and a UART.
   ("pll" and "pll-switched").
 * The UART has its baud clock connected the external oscillator and its
   register clock connected to the PLL clock (the "pll-switched" signal)
+
+==Assigned clock parents and rates==
+
+Some platforms may require initial configuration of default parent clocks
+and clock frequencies. Such a configuration can be specified in a device tree
+node through assigned-clocks, assigned-clock-parents and assigned-clock-rates
+properties. The assigned-clock-parents property should contain a list of parent
+clocks in form of phandle and clock specifier pairs, the assigned-clock-parents
+property the list of assigned clock frequency values - corresponding to clocks
+listed in the assigned-clocks property.
+
+To skip setting parent or rate of a clock its corresponding entry should be
+set to 0, or can be omitted if it is not followed by any non-zero entry.
+
+    uart@a000 {
+        compatible = "fsl,imx-uart";
+        reg = <0xa000 0x1000>;
+        ...
+        clocks = <&osc 0>, <&pll 1>;
+        clock-names = "baud", "register";
+
+        assigned-clocks = <&clkcon 0>, <&pll 2>;
+        assigned-clock-parents = <&pll 2>;
+        assigned-clock-rates = <0>, <460800>;
+    };
+
+In this example the <&pll 2> clock is set as parent of clock <&clkcon 0> and
+the <&pll 2> clock is assigned a frequency value of 460800 Hz.
+
+Configuring a clock's parent and rate through the device node that consumes
+the clock can be done only for clocks that have a single user. Specifying
+conflicting parent or rate configuration in multiple consumer nodes for
+a shared clock is forbidden.
+
+Configuration of common clocks, which affect multiple consumer devices can
+be similarly specified in the clock provider node.
diff --git a/Documentation/devicetree/bindings/clock/clps711x-clock.txt b/Documentation/devicetree/bindings/clock/clps711x-clock.txt
new file mode 100644
index 00000000000..ce5a7476f05
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/clps711x-clock.txt
@@ -0,0 +1,19 @@
+* Clock bindings for the Cirrus Logic CLPS711X CPUs
+
+Required properties:
+- compatible       : Shall contain "cirrus,clps711x-clk".
+- reg              : Address of the internal register set.
+- startup-frequency: Factory set CPU startup frequency in HZ.
+- #clock-cells     : Should be <1>.
+
+The clock consumer should specify the desired clock by having the clock
+ID in its "clocks" phandle cell. See include/dt-bindings/clock/clps711x-clock.h
+for the full list of CLPS711X clock IDs.
+
+Example:
+	clks: clks@80000000 {
+		#clock-cells = <1>;
+		compatible = "cirrus,ep7312-clk", "cirrus,clps711x-clk";
+		reg = <0x80000000 0xc000>;
+		startup-frequency = <73728000>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc.txt b/Documentation/devicetree/bindings/clock/qcom,gcc.txt
index 9cfcb4f2bc9..aba3d254e03 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gcc.txt
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc.txt
@@ -5,6 +5,8 @@ Required properties :
 - compatible : shall contain only one of the following:
 
 			"qcom,gcc-apq8064"
+			"qcom,gcc-apq8084"
+			"qcom,gcc-ipq8064"
 			"qcom,gcc-msm8660"
 			"qcom,gcc-msm8960"
 			"qcom,gcc-msm8974"
diff --git a/Documentation/devicetree/bindings/clock/qcom,mmcc.txt b/Documentation/devicetree/bindings/clock/qcom,mmcc.txt
index d572e9964c5..29ebf84d25a 100644
--- a/Documentation/devicetree/bindings/clock/qcom,mmcc.txt
+++ b/Documentation/devicetree/bindings/clock/qcom,mmcc.txt
@@ -4,6 +4,8 @@ Qualcomm Multimedia Clock & Reset Controller Binding
 Required properties :
 - compatible : shall contain only one of the following:
 
+			"qcom,mmcc-apq8064"
+			"qcom,mmcc-apq8084"
 			"qcom,mmcc-msm8660"
 			"qcom,mmcc-msm8960"
 			"qcom,mmcc-msm8974"
diff --git a/Documentation/devicetree/bindings/clock/corenet-clock.txt b/Documentation/devicetree/bindings/clock/qoriq-clock.txt
index 24711af48e3..5666812fc42 100644
--- a/Documentation/devicetree/bindings/clock/corenet-clock.txt
+++ b/Documentation/devicetree/bindings/clock/qoriq-clock.txt
@@ -7,6 +7,14 @@ which can then be passed to a variety of internal logic, including
 cores and peripheral IP blocks.
 Please refer to the Reference Manual for details.
 
+All references to "1.0" and "2.0" refer to the QorIQ chassis version to
+which the chip complies.
+
+Chassis Version		Example Chips
+---------------		-------------
+1.0			p4080, p5020, p5040
+2.0			t4240, b4860, t1040
+
 1. Clock Block Binding
 
 Required properties:
@@ -85,7 +93,7 @@ Example for clock block and clock provider:
 			#clock-cells = <0>;
 			compatible = "fsl,qoriq-sysclk-1.0";
 			clock-output-names = "sysclk";
-		}
+		};
 
 		pll0: pll0@800 {
 			#clock-cells = <1>;
diff --git a/Documentation/devicetree/bindings/clock/rockchip,rk3188-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,rk3188-cru.txt
new file mode 100644
index 00000000000..0c2bf5eba43
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/rockchip,rk3188-cru.txt
@@ -0,0 +1,61 @@
+* Rockchip RK3188/RK3066 Clock and Reset Unit
+
+The RK3188/RK3066 clock controller generates and supplies clock to various
+controllers within the SoC and also implements a reset controller for SoC
+peripherals.
+
+Required Properties:
+
+- compatible: should be "rockchip,rk3188-cru", "rockchip,rk3188a-cru" or
+			"rockchip,rk3066a-cru"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Optional Properties:
+
+- rockchip,grf: phandle to the syscon managing the "general register files"
+  If missing pll rates are not changable, due to the missing pll lock status.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. All available clocks are defined as
+preprocessor macros in the dt-bindings/clock/rk3188-cru.h and
+dt-bindings/clock/rk3066-cru.h headers and can be used in device tree sources.
+Similar macros exist for the reset sources in these files.
+
+External clocks:
+
+There are several clocks that are generated outside the SoC. It is expected
+that they are defined using standard clock bindings with following
+clock-output-names:
+ - "xin24m" - crystal input - required,
+ - "xin32k" - rtc clock - optional,
+ - "xin27m" - 27mhz crystal input on rk3066 - optional,
+ - "ext_hsadc" - external HSADC clock - optional,
+ - "ext_cif0" - external camera clock - optional,
+ - "ext_rmii" - external RMII clock - optional,
+ - "ext_jtag" - externalJTAG clock - optional
+
+Example: Clock controller node:
+
+	cru: cru@20000000 {
+		compatible = "rockchip,rk3188-cru";
+		reg = <0x20000000 0x1000>;
+		rockchip,grf = <&grf>;
+
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+Example: UART controller node that consumes the clock generated by the clock
+  controller:
+
+	uart0: serial@10124000 {
+		compatible = "snps,dw-apb-uart";
+		reg = <0x10124000 0x400>;
+		interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <1>;
+		clocks = <&cru SCLK_UART0>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/rockchip,rk3288-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,rk3288-cru.txt
new file mode 100644
index 00000000000..c9fbb76573e
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/rockchip,rk3288-cru.txt
@@ -0,0 +1,61 @@
+* Rockchip RK3288 Clock and Reset Unit
+
+The RK3288 clock controller generates and supplies clock to various
+controllers within the SoC and also implements a reset controller for SoC
+peripherals.
+
+Required Properties:
+
+- compatible: should be "rockchip,rk3288-cru"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Optional Properties:
+
+- rockchip,grf: phandle to the syscon managing the "general register files"
+  If missing pll rates are not changable, due to the missing pll lock status.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. All available clocks are defined as
+preprocessor macros in the dt-bindings/clock/rk3288-cru.h headers and can be
+used in device tree sources. Similar macros exist for the reset sources in
+these files.
+
+External clocks:
+
+There are several clocks that are generated outside the SoC. It is expected
+that they are defined using standard clock bindings with following
+clock-output-names:
+ - "xin24m" - crystal input - required,
+ - "xin32k" - rtc clock - optional,
+ - "ext_i2s" - external I2S clock - optional,
+ - "ext_hsadc" - external HSADC clock - optional,
+ - "ext_edp_24m" - external display port clock - optional,
+ - "ext_vip" - external VIP clock - optional,
+ - "ext_isp" - external ISP clock - optional,
+ - "ext_jtag" - external JTAG clock - optional
+
+Example: Clock controller node:
+
+	cru: cru@20000000 {
+		compatible = "rockchip,rk3188-cru";
+		reg = <0x20000000 0x1000>;
+		rockchip,grf = <&grf>;
+
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+Example: UART controller node that consumes the clock generated by the clock
+  controller:
+
+	uart0: serial@10124000 {
+		compatible = "snps,dw-apb-uart";
+		reg = <0x10124000 0x400>;
+		interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <1>;
+		clocks = <&cru SCLK_UART0>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/rockchip.txt b/Documentation/devicetree/bindings/clock/rockchip.txt
index a891c823ed4..22f6769e5d4 100644
--- a/Documentation/devicetree/bindings/clock/rockchip.txt
+++ b/Documentation/devicetree/bindings/clock/rockchip.txt
@@ -6,6 +6,9 @@ This binding uses the common clock binding[1].
 
 == Gate clocks ==
 
+These bindings are deprecated!
+Please use the soc specific CRU bindings instead.
+
 The gate registers form a continuos block which makes the dt node
 structure a matter of taste, as either all gates can be put into
 one gate clock spanning all registers or they can be divided into
diff --git a/Documentation/devicetree/bindings/clock/st/st,clkgen-divmux.txt b/Documentation/devicetree/bindings/clock/st/st,clkgen-divmux.txt
index ae56315fcec..6247652044a 100644
--- a/Documentation/devicetree/bindings/clock/st/st,clkgen-divmux.txt
+++ b/Documentation/devicetree/bindings/clock/st/st,clkgen-divmux.txt
@@ -24,26 +24,26 @@ Required properties:
 
 Example:
 
-	clockgenA@fd345000 {
+	clockgen-a@fd345000 {
 		reg = <0xfd345000 0xb50>;
 
-		CLK_M_A1_DIV1: CLK_M_A1_DIV1 {
+		clk_m_a1_div1: clk-m-a1-div1 {
 			#clock-cells = <1>;
 			compatible = "st,clkgena-divmux-c32-odf1",
 				     "st,clkgena-divmux";
 
-			clocks = <&CLK_M_A1_OSC_PREDIV>,
-				 <&CLK_M_A1_PLL0 1>, /* PLL0 PHI1 */
-				 <&CLK_M_A1_PLL1 1>; /* PLL1 PHI1 */
-
-			clock-output-names = "CLK_M_RX_ICN_TS",
-					     "CLK_M_RX_ICN_VDP_0",
-					     "", /* Unused */
-					     "CLK_M_PRV_T1_BUS",
-					     "CLK_M_ICN_REG_12",
-					     "CLK_M_ICN_REG_10",
-					     "", /* Unused */
-					     "CLK_M_ICN_ST231";
+			clocks = <&clk_m_a1_osc_prediv>,
+				 <&clk_m_a1_pll0 1>, /* PLL0 PHI1 */
+				 <&clk_m_a1_pll1 1>; /* PLL1 PHI1 */
+
+			clock-output-names = "clk-m-rx-icn-ts",
+					     "clk-m-rx-icn-vdp-0",
+					     "", /* unused */
+					     "clk-m-prv-t1-bus",
+					     "clk-m-icn-reg-12",
+					     "clk-m-icn-reg-10",
+					     "", /* unused */
+					     "clk-m-icn-st231";
 		};
 	};
 
diff --git a/Documentation/devicetree/bindings/clock/st/st,clkgen-mux.txt b/Documentation/devicetree/bindings/clock/st/st,clkgen-mux.txt
index 943e0808e21..f1fa91c6876 100644
--- a/Documentation/devicetree/bindings/clock/st/st,clkgen-mux.txt
+++ b/Documentation/devicetree/bindings/clock/st/st,clkgen-mux.txt
@@ -17,7 +17,7 @@ Required properties:
 	"st,stih416-clkgenf-vcc-sd",	"st,clkgen-mux"
 	"st,stih415-clkgen-a9-mux",	"st,clkgen-mux"
 	"st,stih416-clkgen-a9-mux",	"st,clkgen-mux"
-
+	"st,stih407-clkgen-a9-mux",	"st,clkgen-mux"
 
 - #clock-cells : from common clock binding; shall be set to 0.
 
@@ -27,10 +27,10 @@ Required properties:
 
 Example:
 
-	CLK_M_HVA: CLK_M_HVA {
+	clk_m_hva: clk-m-hva@fd690868 {
 		#clock-cells = <0>;
 		compatible = "st,stih416-clkgenf-vcc-hva", "st,clkgen-mux";
 		reg = <0xfd690868 4>;
 
-		clocks = <&CLOCKGEN_F 1>, <&CLK_M_A1_DIV0 3>;
+		clocks = <&clockgen_f 1>, <&clk_m_a1_div0 3>;
 	};
diff --git a/Documentation/devicetree/bindings/clock/st/st,clkgen-pll.txt b/Documentation/devicetree/bindings/clock/st/st,clkgen-pll.txt
index 81eb3855ab9..efb51cf0c84 100644
--- a/Documentation/devicetree/bindings/clock/st/st,clkgen-pll.txt
+++ b/Documentation/devicetree/bindings/clock/st/st,clkgen-pll.txt
@@ -19,11 +19,14 @@ Required properties:
 	"st,stih415-plls-c32-ddr",	"st,clkgen-plls-c32"
 	"st,stih416-plls-c32-a9",	"st,clkgen-plls-c32"
 	"st,stih416-plls-c32-ddr",	"st,clkgen-plls-c32"
+	"st,stih407-plls-c32-a0",	"st,clkgen-plls-c32"
+	"st,stih407-plls-c32-a9",	"st,clkgen-plls-c32"
+	"st,stih407-plls-c32-c0_0",	"st,clkgen-plls-c32"
+	"st,stih407-plls-c32-c0_1",	"st,clkgen-plls-c32"
 
 	"st,stih415-gpu-pll-c32",	"st,clkgengpu-pll-c32"
 	"st,stih416-gpu-pll-c32",	"st,clkgengpu-pll-c32"
 
-
 - #clock-cells : From common clock binding; shall be set to 1.
 
 - clocks : From common clock binding
@@ -32,17 +35,17 @@ Required properties:
 
 Example:
 
-	clockgenA@fee62000 {
+	clockgen-a@fee62000 {
 		reg = <0xfee62000 0xb48>;
 
-		CLK_S_A0_PLL: CLK_S_A0_PLL {
+		clk_s_a0_pll: clk-s-a0-pll {
 			#clock-cells = <1>;
 			compatible = "st,clkgena-plls-c65";
 
-			clocks = <&CLK_SYSIN>;
+			clocks = <&clk_sysin>;
 
-			clock-output-names = "CLK_S_A0_PLL0_HS",
-					     "CLK_S_A0_PLL0_LS",
-					     "CLK_S_A0_PLL1";
+			clock-output-names = "clk-s-a0-pll0-hs",
+					     "clk-s-a0-pll0-ls",
+					     "clk-s-a0-pll1";
 		};
 	};
diff --git a/Documentation/devicetree/bindings/clock/st/st,clkgen-prediv.txt b/Documentation/devicetree/bindings/clock/st/st,clkgen-prediv.txt
index 566c9d79ed3..604766c2619 100644
--- a/Documentation/devicetree/bindings/clock/st/st,clkgen-prediv.txt
+++ b/Documentation/devicetree/bindings/clock/st/st,clkgen-prediv.txt
@@ -20,17 +20,17 @@ Required properties:
 
 Example:
 
-	clockgenA@fd345000 {
+	clockgen-a@fd345000 {
 		reg = <0xfd345000 0xb50>;
 
-		CLK_M_A2_OSC_PREDIV: CLK_M_A2_OSC_PREDIV {
+		clk_m_a2_osc_prediv: clk-m-a2-osc-prediv {
 			#clock-cells = <0>;
 			compatible = "st,clkgena-prediv-c32",
 				     "st,clkgena-prediv";
 
-			clocks = <&CLK_SYSIN>;
+			clocks = <&clk_sysin>;
 
-			clock-output-names = "CLK_M_A2_OSC_PREDIV";
+			clock-output-names = "clk-m-a2-osc-prediv";
 		};
 	};
 
diff --git a/Documentation/devicetree/bindings/clock/st/st,clkgen-vcc.txt b/Documentation/devicetree/bindings/clock/st/st,clkgen-vcc.txt
index 4e3ff28b04c..109b3eddcb1 100644
--- a/Documentation/devicetree/bindings/clock/st/st,clkgen-vcc.txt
+++ b/Documentation/devicetree/bindings/clock/st/st,clkgen-vcc.txt
@@ -32,22 +32,30 @@ Required properties:
 
 Example:
 
-	CLOCKGEN_C_VCC: CLOCKGEN_C_VCC {
+	clockgen_c_vcc: clockgen-c-vcc@0xfe8308ac {
 		#clock-cells = <1>;
 		compatible = "st,stih416-clkgenc", "st,clkgen-vcc";
 		reg = <0xfe8308ac 12>;
 
-		clocks = <&CLK_S_VCC_HD>, <&CLOCKGEN_C 1>,
-			<&CLK_S_TMDS_FROMPHY>, <&CLOCKGEN_C 2>;
-
-		clock-output-names  =
-			"CLK_S_PIX_HDMI",  "CLK_S_PIX_DVO",
-			"CLK_S_OUT_DVO",   "CLK_S_PIX_HD",
-			"CLK_S_HDDAC",     "CLK_S_DENC",
-			"CLK_S_SDDAC",     "CLK_S_PIX_MAIN",
-			"CLK_S_PIX_AUX",   "CLK_S_STFE_FRC_0",
-			"CLK_S_REF_MCRU",  "CLK_S_SLAVE_MCRU",
-			"CLK_S_TMDS_HDMI", "CLK_S_HDMI_REJECT_PLL",
-			"CLK_S_THSENS";
+		clocks = <&clk_s_vcc_hd>,
+			 <&clockgen_c 1>,
+			 <&clk_s_tmds_fromphy>,
+			 <&clockgen_c 2>;
+
+		clock-output-names  = "clk-s-pix-hdmi",
+				      "clk-s-pix-dvo",
+				      "clk-s-out-dvo",
+				      "clk-s-pix-hd",
+				      "clk-s-hddac",
+				      "clk-s-denc",
+				      "clk-s-sddac",
+				      "clk-s-pix-main",
+				      "clk-s-pix-aux",
+				      "clk-s-stfe-frc-0",
+				      "clk-s-ref-mcru",
+				      "clk-s-slave-mcru",
+				      "clk-s-tmds-hdmi",
+				      "clk-s-hdmi-reject-pll",
+				      "clk-s-thsens";
 	};
 
diff --git a/Documentation/devicetree/bindings/clock/st/st,clkgen.txt b/Documentation/devicetree/bindings/clock/st/st,clkgen.txt
index 49ec5ae18b5..78978f1f515 100644
--- a/Documentation/devicetree/bindings/clock/st/st,clkgen.txt
+++ b/Documentation/devicetree/bindings/clock/st/st,clkgen.txt
@@ -24,60 +24,77 @@ address is common of all subnode.
 		quadfs_node {
 			...
 		};
+
+		mux_node {
+			...
+		};
+
+		vcc_node {
+			...
+		};
+
+		flexgen_node {
+			...
+		};
 		...
 	};
 
 This binding uses the common clock binding[1].
-Each subnode should use the binding discribe in [2]..[4]
+Each subnode should use the binding discribe in [2]..[7]
 
 [1] Documentation/devicetree/bindings/clock/clock-bindings.txt
-[2] Documentation/devicetree/bindings/clock/st,quadfs.txt
-[3] Documentation/devicetree/bindings/clock/st,quadfs.txt
-[4] Documentation/devicetree/bindings/clock/st,quadfs.txt
+[2] Documentation/devicetree/bindings/clock/st,clkgen-divmux.txt
+[3] Documentation/devicetree/bindings/clock/st,clkgen-mux.txt
+[4] Documentation/devicetree/bindings/clock/st,clkgen-pll.txt
+[5] Documentation/devicetree/bindings/clock/st,clkgen-prediv.txt
+[6] Documentation/devicetree/bindings/clock/st,vcc.txt
+[7] Documentation/devicetree/bindings/clock/st,quadfs.txt
+[8] Documentation/devicetree/bindings/clock/st,flexgen.txt
+
 
 Required properties:
 - reg : A Base address and length of the register set.
 
 Example:
 
-	clockgenA@fee62000 {
+	clockgen-a@fee62000 {
 
 		reg = <0xfee62000 0xb48>;
 
-		CLK_S_A0_PLL: CLK_S_A0_PLL {
+		clk_s_a0_pll: clk-s-a0-pll {
 			#clock-cells = <1>;
 			compatible = "st,clkgena-plls-c65";
 
-			clocks = <&CLK_SYSIN>;
+			clocks = <&clk-sysin>;
 
-			clock-output-names = "CLK_S_A0_PLL0_HS",
-					     "CLK_S_A0_PLL0_LS",
-					     "CLK_S_A0_PLL1";
+			clock-output-names = "clk-s-a0-pll0-hs",
+					     "clk-s-a0-pll0-ls",
+					     "clk-s-a0-pll1";
 		};
 
-		CLK_S_A0_OSC_PREDIV: CLK_S_A0_OSC_PREDIV {
+		clk_s_a0_osc_prediv: clk-s-a0-osc-prediv {
 			#clock-cells = <0>;
 			compatible = "st,clkgena-prediv-c65",
 				     "st,clkgena-prediv";
 
-			clocks = <&CLK_SYSIN>;
+			clocks = <&clk_sysin>;
 
-			clock-output-names = "CLK_S_A0_OSC_PREDIV";
+			clock-output-names = "clk-s-a0-osc-prediv";
 		};
 
-		CLK_S_A0_HS: CLK_S_A0_HS {
+		clk_s_a0_hs: clk-s-a0-hs {
 			#clock-cells = <1>;
 			compatible = "st,clkgena-divmux-c65-hs",
 				     "st,clkgena-divmux";
 
-			clocks = <&CLK_S_A0_OSC_PREDIV>,
-				 <&CLK_S_A0_PLL 0>, /* PLL0 HS */
-				 <&CLK_S_A0_PLL 2>; /* PLL1 */
+			clocks = <&clk-s_a0_osc_prediv>,
+				 <&clk-s_a0_pll 0>, /* pll0 hs */
+				 <&clk-s_a0_pll 2>; /* pll1 */
 
-			clock-output-names = "CLK_S_FDMA_0",
-					     "CLK_S_FDMA_1",
-					     ""; /* CLK_S_JIT_SENSE */
-					     /* Fourth output unused */
+			clock-output-names = "clk-s-fdma-0",
+					     "clk-s-fdma-1",
+					     ""; /* clk-s-jit-sense */
+					     /* fourth output unused */
 		};
 	};
 
diff --git a/Documentation/devicetree/bindings/clock/st/st,flexgen.txt b/Documentation/devicetree/bindings/clock/st/st,flexgen.txt
new file mode 100644
index 00000000000..1d3ace08817
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/st/st,flexgen.txt
@@ -0,0 +1,119 @@
+Binding for a type of flexgen structure found on certain
+STMicroelectronics consumer electronics SoC devices
+
+This structure includes:
+- a clock cross bar (represented by a mux element)
+- a pre and final dividers (represented by a divider and gate elements)
+
+Flexgen structure is a part of Clockgen[1].
+
+Please find an example below:
+
+    Clockgen block diagram
+    -------------------------------------------------------------------
+   |                     Flexgen stucture                              |
+   |                  ---------------------------------------------    |
+   |                 |    -------       --------       --------    |   |
+clk_sysin            |   |       |     |        |     |        |   |   |
+---|-----------------|-->|       |     |        |     |        |   |   |
+   | |               |   |       |     |        |     |        |   |   |
+   | |   -------     |   |       |     |Pre     |     |Final   |   |   |
+   | |  |PLL0   |    |   |       |     |Dividers|     |Dividers|   |   |
+   | |->|       |    |   |       |     |  x32   |     |  x32   |   |   |
+   | |  |  odf_0|----|-->|       |     |        |     |        |   |   |
+   | |  |       |    |   |       |     |        |     |        |   |   |
+   | |  |       |    |   |       |     |        |     |        |   |   |
+   | |  |       |    |   |       |     |        |     |        |   |   |
+   | |  |       |    |   |       |     |        |     |        |   |   |
+   | |   -------     |   |       |     |        |     |        |   |   |
+   | |               |   |       |     |        |     |        |   |   |
+   | |   -------     |   | Clock |     |        |     |        |   |   |
+   | |  |PLL1   |    |   |       |     |        |     |        |   |   |
+   | |->|       |    |   | Cross |     |        |     |        |   |   |
+   | |  |  odf_0|----|-->|       |     |        |     |        | CLK_DIV[31:0]
+   | |  |       |    |   | Bar   |====>|        |====>|        |===|=========>
+   | |  |       |    |   |       |     |        |     |        |   |   |
+   | |  |       |    |   |       |     |        |     |        |   |   |
+   | |  |       |    |   |       |     |        |     |        |   |   |
+   | |   -------     |   |       |     |        |     |        |   |   |
+   | |               |   |       |     |        |     |        |   |   |
+   | |   -------     |   |       |     |        |     |        |   |   |
+   | |  |QUADFS |    |   |       |     |        |     |        |   |   |
+   | |->|    ch0|----|-->|       |     |        |     |        |   |   |
+   |    |       |    |   |       |     |        |     |        |   |   |
+   |    |    ch1|----|-->|       |     |        |     |        |   |   |
+   |    |       |    |   |       |     |        |     |        |   |   |
+   |    |    ch2|----|-->|       |     | DIV    |     | DIV    |   |   |
+   |    |       |    |   |       |     |  1 to  |     |  1 to  |   |   |
+   |    |    ch3|----|-->|       |     |   1024 |     |     64 |   |   |
+   |     -------     |   |       |     |        |     |        |   |   |
+   |                 |    -------       --------       --------    |   |
+   |                   --------------------------------------------    |
+   |                                                                   |
+    -------------------------------------------------------------------
+
+This binding uses the common clock binding[2].
+
+[1] Documentation/devicetree/bindings/clock/st/st,clkgen.txt
+[2] Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Required properties:
+- compatible : shall be:
+  "st,flexgen"
+
+- #clock-cells : from common clock binding; shall be set to 1 (multiple clock
+  outputs).
+
+- clocks : must be set to the parent's phandle. it's could be output clocks of
+  a quadsfs or/and a pll or/and clk_sysin (up to 7 clocks)
+
+- clock-output-names : List of strings used to name the clock outputs.
+
+Example:
+
+	clk_s_c0_flexgen: clk-s-c0-flexgen {
+
+		#clock-cells = <1>;
+		compatible = "st,flexgen";
+
+		clocks = <&clk_s_c0_pll0 0>,
+			 <&clk_s_c0_pll1 0>,
+			 <&clk_s_c0_quadfs 0>,
+			 <&clk_s_c0_quadfs 1>,
+			 <&clk_s_c0_quadfs 2>,
+			 <&clk_s_c0_quadfs 3>,
+			 <&clk_sysin>;
+
+		clock-output-names = "clk-icn-gpu",
+				     "clk-fdma",
+				     "clk-nand",
+				     "clk-hva",
+				     "clk-proc-stfe",
+				     "clk-proc-tp",
+				     "clk-rx-icn-dmu",
+				     "clk-rx-icn-hva",
+				     "clk-icn-cpu",
+				     "clk-tx-icn-dmu",
+				     "clk-mmc-0",
+				     "clk-mmc-1",
+				     "clk-jpegdec",
+				     "clk-ext2fa9",
+				     "clk-ic-bdisp-0",
+				     "clk-ic-bdisp-1",
+				     "clk-pp-dmu",
+				     "clk-vid-dmu",
+				     "clk-dss-lpc",
+				     "clk-st231-aud-0",
+				     "clk-st231-gp-1",
+				     "clk-st231-dmu",
+				     "clk-icn-lmi",
+				     "clk-tx-icn-disp-1",
+				     "clk-icn-sbc",
+				     "clk-stfe-frc2",
+				     "clk-eth-phy",
+				     "clk-eth-ref-phyclk",
+				     "clk-flash-promip",
+				     "clk-main-disp",
+				     "clk-aux-disp",
+				     "clk-compo-dvp";
+	};
diff --git a/Documentation/devicetree/bindings/clock/st/st,quadfs.txt b/Documentation/devicetree/bindings/clock/st/st,quadfs.txt
index ec86d62ca28..cedeb9cc820 100644
--- a/Documentation/devicetree/bindings/clock/st/st,quadfs.txt
+++ b/Documentation/devicetree/bindings/clock/st/st,quadfs.txt
@@ -15,6 +15,9 @@ Required properties:
   "st,stih416-quadfs432",	"st,quadfs"
   "st,stih416-quadfs660-E",	"st,quadfs"
   "st,stih416-quadfs660-F",	"st,quadfs"
+  "st,stih407-quadfs660-C",	"st,quadfs"
+  "st,stih407-quadfs660-D",	"st,quadfs"
+
 
 - #clock-cells : from common clock binding; shall be set to 1.
 
@@ -32,14 +35,14 @@ Required properties:
 
 Example:
 
-	CLOCKGEN_E: CLOCKGEN_E {
+	clockgen_e: clockgen-e@fd3208bc {
                 #clock-cells = <1>;
                 compatible = "st,stih416-quadfs660-E", "st,quadfs";
                 reg = <0xfd3208bc 0xB0>;
 
-                clocks = <&CLK_SYSIN>;
-                clock-output-names = "CLK_M_PIX_MDTP_0",
-                                        "CLK_M_PIX_MDTP_1",
-                                        "CLK_M_PIX_MDTP_2",
-                                        "CLK_M_MPELPC";
+                clocks = <&clk_sysin>;
+                clock-output-names = "clk-m-pix-mdtp-0",
+				     "clk-m-pix-mdtp-1",
+				     "clk-m-pix-mdtp-2",
+				     "clk-m-mpelpc";
         };
diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt
index a5160d8cbb5..d3a5c3c6d67 100644
--- a/Documentation/devicetree/bindings/clock/sunxi.txt
+++ b/Documentation/devicetree/bindings/clock/sunxi.txt
@@ -9,24 +9,32 @@ Required properties:
 	"allwinner,sun4i-a10-osc-clk" - for a gatable oscillator
 	"allwinner,sun4i-a10-pll1-clk" - for the main PLL clock and PLL4
 	"allwinner,sun6i-a31-pll1-clk" - for the main PLL clock on A31
+	"allwinner,sun8i-a23-pll1-clk" - for the main PLL clock on A23
 	"allwinner,sun4i-a10-pll5-clk" - for the PLL5 clock
 	"allwinner,sun4i-a10-pll6-clk" - for the PLL6 clock
 	"allwinner,sun6i-a31-pll6-clk" - for the PLL6 clock on A31
 	"allwinner,sun4i-a10-cpu-clk" - for the CPU multiplexer clock
 	"allwinner,sun4i-a10-axi-clk" - for the AXI clock
+	"allwinner,sun8i-a23-axi-clk" - for the AXI clock on A23
 	"allwinner,sun4i-a10-axi-gates-clk" - for the AXI gates
 	"allwinner,sun4i-a10-ahb-clk" - for the AHB clock
 	"allwinner,sun4i-a10-ahb-gates-clk" - for the AHB gates on A10
 	"allwinner,sun5i-a13-ahb-gates-clk" - for the AHB gates on A13
 	"allwinner,sun5i-a10s-ahb-gates-clk" - for the AHB gates on A10s
 	"allwinner,sun7i-a20-ahb-gates-clk" - for the AHB gates on A20
+	"allwinner,sun6i-a31-ar100-clk" - for the AR100 on A31
 	"allwinner,sun6i-a31-ahb1-mux-clk" - for the AHB1 multiplexer on A31
 	"allwinner,sun6i-a31-ahb1-gates-clk" - for the AHB1 gates on A31
+	"allwinner,sun8i-a23-ahb1-gates-clk" - for the AHB1 gates on A23
 	"allwinner,sun4i-a10-apb0-clk" - for the APB0 clock
+	"allwinner,sun6i-a31-apb0-clk" - for the APB0 clock on A31
+	"allwinner,sun8i-a23-apb0-clk" - for the APB0 clock on A23
 	"allwinner,sun4i-a10-apb0-gates-clk" - for the APB0 gates on A10
 	"allwinner,sun5i-a13-apb0-gates-clk" - for the APB0 gates on A13
 	"allwinner,sun5i-a10s-apb0-gates-clk" - for the APB0 gates on A10s
+	"allwinner,sun6i-a31-apb0-gates-clk" - for the APB0 gates on A31
 	"allwinner,sun7i-a20-apb0-gates-clk" - for the APB0 gates on A20
+	"allwinner,sun8i-a23-apb0-gates-clk" - for the APB0 gates on A23
 	"allwinner,sun4i-a10-apb1-clk" - for the APB1 clock
 	"allwinner,sun4i-a10-apb1-mux-clk" - for the APB1 clock muxing
 	"allwinner,sun4i-a10-apb1-gates-clk" - for the APB1 gates on A10
@@ -34,13 +42,16 @@ Required properties:
 	"allwinner,sun5i-a10s-apb1-gates-clk" - for the APB1 gates on A10s
 	"allwinner,sun6i-a31-apb1-gates-clk" - for the APB1 gates on A31
 	"allwinner,sun7i-a20-apb1-gates-clk" - for the APB1 gates on A20
+	"allwinner,sun8i-a23-apb1-gates-clk" - for the APB1 gates on A23
 	"allwinner,sun6i-a31-apb2-div-clk" - for the APB2 gates on A31
 	"allwinner,sun6i-a31-apb2-gates-clk" - for the APB2 gates on A31
+	"allwinner,sun8i-a23-apb2-gates-clk" - for the APB2 gates on A23
 	"allwinner,sun4i-a10-mod0-clk" - for the module 0 family of clocks
 	"allwinner,sun7i-a20-out-clk" - for the external output clocks
 	"allwinner,sun7i-a20-gmac-clk" - for the GMAC clock module on A20/A31
 	"allwinner,sun4i-a10-usb-clk" - for usb gates + resets on A10 / A20
 	"allwinner,sun5i-a13-usb-clk" - for usb gates + resets on A13
+	"allwinner,sun6i-a31-usb-clk" - for usb gates + resets on A31
 
 Required properties for all clocks:
 - reg : shall be the control register address for the clock.
diff --git a/Documentation/devicetree/bindings/clock/ti/apll.txt b/Documentation/devicetree/bindings/clock/ti/apll.txt
index 7faf5a68b3b..ade4dd4c30f 100644
--- a/Documentation/devicetree/bindings/clock/ti/apll.txt
+++ b/Documentation/devicetree/bindings/clock/ti/apll.txt
@@ -14,18 +14,32 @@ a subtype of a DPLL [2], although a simplified one at that.
 [2] Documentation/devicetree/bindings/clock/ti/dpll.txt
 
 Required properties:
-- compatible : shall be "ti,dra7-apll-clock"
+- compatible : shall be "ti,dra7-apll-clock" or "ti,omap2-apll-clock"
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : link phandles of parent clocks (clk-ref and clk-bypass)
 - reg : address and length of the register set for controlling the APLL.
   It contains the information of registers in the following order:
-	"control" - contains the control register base address
-	"idlest" - contains the idlest register base address
+	"control" - contains the control register offset
+	"idlest" - contains the idlest register offset
+	"autoidle" - contains the autoidle register offset (OMAP2 only)
+- ti,clock-frequency : static clock frequency for the clock (OMAP2 only)
+- ti,idlest-shift : bit-shift for the idlest field (OMAP2 only)
+- ti,bit-shift : bit-shift for enable and autoidle fields (OMAP2 only)
 
 Examples:
-	apll_pcie_ck: apll_pcie_ck@4a008200 {
+	apll_pcie_ck: apll_pcie_ck {
 		#clock-cells = <0>;
 		clocks = <&apll_pcie_in_clk_mux>, <&dpll_pcie_ref_ck>;
-		reg = <0x4a00821c 0x4>, <0x4a008220 0x4>;
+		reg = <0x021c>, <0x0220>;
 		compatible = "ti,dra7-apll-clock";
 	};
+
+	apll96_ck: apll96_ck {
+		#clock-cells = <0>;
+		compatible = "ti,omap2-apll-clock";
+		clocks = <&sys_ck>;
+		ti,bit-shift = <2>;
+		ti,idlest-shift = <8>;
+		ti,clock-frequency = <96000000>;
+		reg = <0x0500>, <0x0530>, <0x0520>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/ti/dpll.txt b/Documentation/devicetree/bindings/clock/ti/dpll.txt
index 30bfdb7c9f1..df57009ff8e 100644
--- a/Documentation/devicetree/bindings/clock/ti/dpll.txt
+++ b/Documentation/devicetree/bindings/clock/ti/dpll.txt
@@ -24,12 +24,14 @@ Required properties:
 		"ti,omap4-dpll-core-clock",
 		"ti,omap4-dpll-m4xen-clock",
 		"ti,omap4-dpll-j-type-clock",
+		"ti,omap5-mpu-dpll-clock",
 		"ti,am3-dpll-no-gate-clock",
 		"ti,am3-dpll-j-type-clock",
 		"ti,am3-dpll-no-gate-j-type-clock",
 		"ti,am3-dpll-clock",
 		"ti,am3-dpll-core-clock",
 		"ti,am3-dpll-x2-clock",
+		"ti,omap2-dpll-core-clock",
 
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : link phandles of parent clocks, first entry lists reference clock
@@ -41,6 +43,7 @@ Required properties:
 	"mult-div1" - contains the multiplier / divider register base address
 	"autoidle" - contains the autoidle register base address (optional)
   ti,am3-* dpll types do not have autoidle register
+  ti,omap2-* dpll type does not support idlest / autoidle registers
 
 Optional properties:
 - DPLL mode setting - defining any one or more of the following overrides
@@ -73,3 +76,10 @@ Examples:
 		clocks = <&sys_clkin_ck>, <&sys_clkin_ck>;
 		reg = <0x90>, <0x5c>, <0x68>;
 	};
+
+	dpll_ck: dpll_ck {
+		#clock-cells = <0>;
+		compatible = "ti,omap2-dpll-core-clock";
+		clocks = <&sys_ck>, <&sys_ck>;
+		reg = <0x0500>, <0x0540>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt b/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt
new file mode 100644
index 00000000000..585e8c191f5
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt
@@ -0,0 +1,96 @@
+Device Tree Clock bindings for ATL (Audio Tracking Logic) of DRA7 SoC.
+
+The ATL IP is used to generate clock to be used to synchronize baseband and
+audio codec. A single ATL IP provides four ATL clock instances sharing the same
+functional clock but can be configured to provide different clocks.
+ATL can maintain a clock averages to some desired frequency based on the bws/aws
+signals - can compensate the drift between the two ws signal.
+
+In order to provide the support for ATL and it's output clocks (which can be used
+internally within the SoC or external components) two sets of bindings is needed:
+
+Clock tree binding:
+This binding uses the common clock binding[1].
+To be able to integrate the ATL clocks with DT clock tree.
+Provides ccf level representation of the ATL clocks to be used by drivers.
+Since the clock instances are part of a single IP this binding is used as a node
+for the DT clock tree, the IP driver is needed to handle the actual configuration
+of the IP.
+
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+Required properties:
+- compatible : shall be "ti,dra7-atl-clock"
+- #clock-cells : from common clock binding; shall be set to 0.
+- clocks : link phandles to functional clock of ATL
+
+Binding for the IP driver:
+This binding is used to configure the IP driver which is going to handle the
+configuration of the IP for the ATL clock instances.
+
+Required properties:
+- compatible : shall be "ti,dra7-atl"
+- reg : base address for the ATL IP
+- ti,provided-clocks : List of phandles to the clocks associated with the ATL
+- clocks : link phandles to functional clock of ATL
+- clock-names : Shall be set to "fck"
+- ti,hwmods : Shall be set to "atl"
+
+Optional properties:
+Configuration of ATL instances:
+- atl{0/1/2/3} {
+	- bws : Baseband word select signal selection
+	- aws : Audio word select signal selection
+};
+
+For valid word select signals, see the dt-bindings/clk/ti-dra7-atl.h include
+file.
+
+Examples:
+/* clock bindings for atl provided clocks */
+atl_clkin0_ck: atl_clkin0_ck {
+	#clock-cells = <0>;
+	compatible = "ti,dra7-atl-clock";
+	clocks = <&atl_gfclk_mux>;
+};
+
+atl_clkin1_ck: atl_clkin1_ck {
+	#clock-cells = <0>;
+	compatible = "ti,dra7-atl-clock";
+	clocks = <&atl_gfclk_mux>;
+};
+
+atl_clkin2_ck: atl_clkin2_ck {
+	#clock-cells = <0>;
+	compatible = "ti,dra7-atl-clock";
+	clocks = <&atl_gfclk_mux>;
+};
+
+atl_clkin3_ck: atl_clkin3_ck {
+	#clock-cells = <0>;
+	compatible = "ti,dra7-atl-clock";
+	clocks = <&atl_gfclk_mux>;
+};
+
+/* binding for the IP */
+atl: atl@4843c000 {
+	compatible = "ti,dra7-atl";
+	reg = <0x4843c000 0x3ff>;
+	ti,hwmods = "atl";
+	ti,provided-clocks = <&atl_clkin0_ck>, <&atl_clkin1_ck>,
+				<&atl_clkin2_ck>, <&atl_clkin3_ck>;
+	clocks = <&atl_gfclk_mux>;
+	clock-names = "fck";
+	status = "disabled";
+};
+
+#include <dt-bindings/clk/ti-dra7-atl.h>
+
+&atl {
+	status = "okay";
+
+	atl2 {
+		bws = <DRA7_ATL_WS_MCASP2_FSX>;
+		aws = <DRA7_ATL_WS_MCASP3_FSX>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/clock/ti/gate.txt b/Documentation/devicetree/bindings/clock/ti/gate.txt
index 125281aaa4c..03f8fdee62a 100644
--- a/Documentation/devicetree/bindings/clock/ti/gate.txt
+++ b/Documentation/devicetree/bindings/clock/ti/gate.txt
@@ -25,6 +25,11 @@ Required properties:
 			  to map clockdomains properly
   "ti,hsdiv-gate-clock" - gate clock with OMAP36xx specific hardware handling,
 			  required for a hardware errata
+  "ti,composite-gate-clock" - composite gate clock, to be part of composite
+			      clock
+  "ti,composite-no-wait-gate-clock" - composite gate clock that does not wait
+				      for clock to be active before returning
+				      from clk_enable()
 - #clock-cells : from common clock binding; shall be set to 0
 - clocks : link to phandle of parent clock
 - reg : offset for register controlling adjustable gate, not needed for
@@ -41,7 +46,7 @@ Examples:
 		#clock-cells = <0>;
 		compatible = "ti,gate-clock";
 		clocks = <&core_96m_fck>;
-		reg = <0x48004a00 0x4>;
+		reg = <0x0a00>;
 		ti,bit-shift = <25>;
 	};
 
@@ -57,7 +62,7 @@ Examples:
 		#clock-cells = <0>;
 		compatible = "ti,dss-gate-clock";
 		clocks = <&dpll4_m4x2_ck>;
-		reg = <0x48004e00 0x4>;
+		reg = <0x0e00>;
 		ti,bit-shift = <0>;
 	};
 
@@ -65,7 +70,7 @@ Examples:
 		#clock-cells = <0>;
 		compatible = "ti,am35xx-gate-clock";
 		clocks = <&ipss_ick>;
-		reg = <0x4800259c 0x4>;
+		reg = <0x059c>;
 		ti,bit-shift = <1>;
 	};
 
@@ -80,6 +85,22 @@ Examples:
 		compatible = "ti,hsdiv-gate-clock";
 		clocks = <&dpll4_m2x2_mul_ck>;
 		ti,bit-shift = <0x1b>;
-		reg = <0x48004d00 0x4>;
+		reg = <0x0d00>;
 		ti,set-bit-to-disable;
 	};
+
+	vlynq_gate_fck: vlynq_gate_fck {
+		#clock-cells = <0>;
+		compatible = "ti,composite-gate-clock";
+		clocks = <&core_ck>;
+		ti,bit-shift = <3>;
+		reg = <0x0200>;
+	};
+
+	sys_clkout2_src_gate: sys_clkout2_src_gate {
+		#clock-cells = <0>;
+		compatible = "ti,composite-no-wait-gate-clock";
+		clocks = <&core_ck>;
+		ti,bit-shift = <15>;
+		reg = <0x0070>;
+	};
diff --git a/Documentation/devicetree/bindings/clock/ti/interface.txt b/Documentation/devicetree/bindings/clock/ti/interface.txt
index 064e8caccac..3111a409fea 100644
--- a/Documentation/devicetree/bindings/clock/ti/interface.txt
+++ b/Documentation/devicetree/bindings/clock/ti/interface.txt
@@ -21,6 +21,8 @@ Required properties:
   "ti,omap3-dss-interface-clock" - interface clock with DSS specific HW handling
   "ti,omap3-ssi-interface-clock" - interface clock with SSI specific HW handling
   "ti,am35xx-interface-clock" - interface clock with AM35xx specific HW handling
+  "ti,omap2430-interface-clock" - interface clock with OMAP2430 specific HW
+				  handling
 - #clock-cells : from common clock binding; shall be set to 0
 - clocks : link to phandle of parent clock
 - reg : base address for the control register
diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt b/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt
index f055515d2b6..366690cb86a 100644
--- a/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt
+++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-cpu0.txt
@@ -8,10 +8,12 @@ Both required and optional properties listed below must be defined
 under node /cpus/cpu@0.
 
 Required properties:
-- operating-points: Refer to Documentation/devicetree/bindings/power/opp.txt
-  for details
+- None
 
 Optional properties:
+- operating-points: Refer to Documentation/devicetree/bindings/power/opp.txt for
+  details. OPPs *must* be supplied either via DT, i.e. this property, or
+  populated at runtime.
 - clock-latency: Specify the possible maximum transition latency for clock,
   in unit of nanoseconds.
 - voltage-tolerance: Specify the CPU voltage tolerance in percentage.
diff --git a/Documentation/devicetree/bindings/crypto/amd-ccp.txt b/Documentation/devicetree/bindings/crypto/amd-ccp.txt
new file mode 100644
index 00000000000..8c61183b41e
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/amd-ccp.txt
@@ -0,0 +1,19 @@
+* AMD Cryptographic Coprocessor driver (ccp)
+
+Required properties:
+- compatible: Should be "amd,ccp-seattle-v1a"
+- reg: Address and length of the register set for the device
+- interrupt-parent: Should be the phandle for the interrupt controller
+  that services interrupts for this device
+- interrupts: Should contain the CCP interrupt
+
+Optional properties:
+- dma-coherent: Present if dma operations are coherent
+
+Example:
+	ccp@e0100000 {
+		compatible = "amd,ccp-seattle-v1a";
+		reg = <0 0xe0100000 0 0x10000>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 3 4>;
+	};
diff --git a/Documentation/devicetree/bindings/crypto/qcom-qce.txt b/Documentation/devicetree/bindings/crypto/qcom-qce.txt
new file mode 100644
index 00000000000..fdd53b184ba
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/qcom-qce.txt
@@ -0,0 +1,25 @@
+Qualcomm crypto engine driver
+
+Required properties:
+
+- compatible  : should be "qcom,crypto-v5.1"
+- reg         : specifies base physical address and size of the registers map
+- clocks      : phandle to clock-controller plus clock-specifier pair
+- clock-names : "iface" clocks register interface
+                "bus" clocks data transfer interface
+                "core" clocks rest of the crypto block
+- dmas        : DMA specifiers for tx and rx dma channels. For more see
+                Documentation/devicetree/bindings/dma/dma.txt
+- dma-names   : DMA request names should be "rx" and "tx"
+
+Example:
+	crypto@fd45a000 {
+		compatible = "qcom,crypto-v5.1";
+		reg = <0xfd45a000 0x6000>;
+		clocks = <&gcc GCC_CE2_AHB_CLK>,
+			 <&gcc GCC_CE2_AXI_CLK>,
+			 <&gcc GCC_CE2_CLK>;
+		clock-names = "iface", "bus", "core";
+		dmas = <&cryptobam 2>, <&cryptobam 3>;
+		dma-names = "rx", "tx";
+	};
diff --git a/Documentation/devicetree/bindings/dma/mmp-dma.txt b/Documentation/devicetree/bindings/dma/mmp-dma.txt
index a4fa4efa1d8..7a802f64e5b 100644
--- a/Documentation/devicetree/bindings/dma/mmp-dma.txt
+++ b/Documentation/devicetree/bindings/dma/mmp-dma.txt
@@ -1,17 +1,20 @@
 * MARVELL MMP DMA controller
 
 Marvell Peripheral DMA Controller
-Used platfroms: pxa688, pxa910, pxa3xx, etc
+Used platforms: pxa688, pxa910, pxa3xx, etc
 
 Required properties:
 - compatible: Should be "marvell,pdma-1.0"
 - reg: Should contain DMA registers location and length.
 - interrupts: Either contain all of the per-channel DMA interrupts
 		or one irq for pdma device
-- #dma-channels: Number of DMA channels supported by the controller.
+
+Optional properties:
+- #dma-channels: Number of DMA channels supported by the controller (defaults
+  to 32 when not specified)
 
 "marvell,pdma-1.0"
-Used platfroms: pxa25x, pxa27x, pxa3xx, pxa93x, pxa168, pxa910, pxa688.
+Used platforms: pxa25x, pxa27x, pxa3xx, pxa93x, pxa168, pxa910, pxa688.
 
 Examples:
 
@@ -45,7 +48,7 @@ pdma: dma-controller@d4000000 {
 
 
 Marvell Two Channel DMA Controller used specifically for audio
-Used platfroms: pxa688, pxa910
+Used platforms: pxa688, pxa910
 
 Required properties:
 - compatible: Should be "marvell,adma-1.0" or "marvell,pxa910-squ"
diff --git a/Documentation/devicetree/bindings/dma/xilinx/xilinx_vdma.txt b/Documentation/devicetree/bindings/dma/xilinx/xilinx_vdma.txt
new file mode 100644
index 00000000000..1405ed071bb
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/xilinx/xilinx_vdma.txt
@@ -0,0 +1,75 @@
+Xilinx AXI VDMA engine, it does transfers between memory and video devices.
+It can be configured to have one channel or two channels. If configured
+as two channels, one is to transmit to the video device and another is
+to receive from the video device.
+
+Required properties:
+- compatible: Should be "xlnx,axi-vdma-1.00.a"
+- #dma-cells: Should be <1>, see "dmas" property below
+- reg: Should contain VDMA registers location and length.
+- xlnx,num-fstores: Should be the number of framebuffers as configured in h/w.
+- dma-channel child node: Should have at least one channel and can have up to
+	two channels per device. This node specifies the properties of each
+	DMA channel (see child node properties below).
+
+Optional properties:
+- xlnx,include-sg: Tells configured for Scatter-mode in
+	the hardware.
+- xlnx,flush-fsync: Tells which channel to Flush on Frame sync.
+	It takes following values:
+	{1}, flush both channels
+	{2}, flush mm2s channel
+	{3}, flush s2mm channel
+
+Required child node properties:
+- compatible: It should be either "xlnx,axi-vdma-mm2s-channel" or
+	"xlnx,axi-vdma-s2mm-channel".
+- interrupts: Should contain per channel VDMA interrupts.
+- xlnx,data-width: Should contain the stream data width, take values
+	{32,64...1024}.
+
+Optional child node properties:
+- xlnx,include-dre: Tells hardware is configured for Data
+	Realignment Engine.
+- xlnx,genlock-mode: Tells Genlock synchronization is
+	enabled/disabled in hardware.
+
+Example:
+++++++++
+
+axi_vdma_0: axivdma@40030000 {
+	compatible = "xlnx,axi-vdma-1.00.a";
+	#dma_cells = <1>;
+	reg = < 0x40030000 0x10000 >;
+	xlnx,num-fstores = <0x8>;
+	xlnx,flush-fsync = <0x1>;
+	dma-channel@40030000 {
+		compatible = "xlnx,axi-vdma-mm2s-channel";
+		interrupts = < 0 54 4 >;
+		xlnx,datawidth = <0x40>;
+	} ;
+	dma-channel@40030030 {
+		compatible = "xlnx,axi-vdma-s2mm-channel";
+		interrupts = < 0 53 4 >;
+		xlnx,datawidth = <0x40>;
+	} ;
+} ;
+
+
+* DMA client
+
+Required properties:
+- dmas: a list of <[Video DMA device phandle] [Channel ID]> pairs,
+	where Channel ID is '0' for write/tx and '1' for read/rx
+	channel.
+- dma-names: a list of DMA channel names, one per "dmas" entry
+
+Example:
+++++++++
+
+vdmatest_0: vdmatest@0 {
+	compatible ="xlnx,axi-vdma-test-1.00.a";
+	dmas = <&axi_vdma_0 0
+		&axi_vdma_0 1>;
+	dma-names = "vdma0", "vdma1";
+} ;
diff --git a/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt b/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt
index efa8b8451f9..b48f4ef31d9 100644
--- a/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt
+++ b/Documentation/devicetree/bindings/gpu/nvidia,tegra20-host1x.txt
@@ -136,6 +136,7 @@ of the following host1x client modules:
   - compatible: "nvidia,tegra<chip>-hdmi"
   - reg: Physical base address and length of the controller's registers.
   - interrupts: The interrupt outputs from the controller.
+  - hdmi-supply: supply for the +5V HDMI connector pin
   - vdd-supply: regulator for supply voltage
   - pll-supply: regulator for PLL
   - clocks: Must contain an entry for each entry in clock-names.
@@ -180,6 +181,7 @@ of the following host1x client modules:
     See ../reset/reset.txt for details.
   - reset-names: Must include the following entries:
     - dsi
+  - avdd-dsi-supply: phandle of a supply that powers the DSI controller
   - nvidia,mipi-calibrate: Should contain a phandle and a specifier specifying
     which pads are used by this DSI output and need to be calibrated. See also
     ../mipi/nvidia,tegra114-mipi.txt.
diff --git a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
index c6f66674f19..b117b2e9e1a 100644
--- a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
+++ b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt
@@ -3,11 +3,19 @@ NTC Thermistor hwmon sensors
 
 Requires node properties:
 - "compatible" value : one of
-	"ntc,ncp15wb473"
-	"ntc,ncp18wb473"
-	"ntc,ncp21wb473"
-	"ntc,ncp03wb473"
-	"ntc,ncp15wl333"
+	"murata,ncp15wb473"
+	"murata,ncp18wb473"
+	"murata,ncp21wb473"
+	"murata,ncp03wb473"
+	"murata,ncp15wl333"
+
+/* Usage of vendor name "ntc" is deprecated */
+<DEPRECATED>	"ntc,ncp15wb473"
+<DEPRECATED>	"ntc,ncp18wb473"
+<DEPRECATED>	"ntc,ncp21wb473"
+<DEPRECATED>	"ntc,ncp03wb473"
+<DEPRECATED>	"ntc,ncp15wl333"
+
 - "pullup-uv"	Pull up voltage in micro volts
 - "pullup-ohm"	Pull up resistor value in ohms
 - "pulldown-ohm" Pull down resistor value in ohms
@@ -21,7 +29,7 @@ Read more about iio bindings at
 
 Example:
 	ncp15wb473@0 {
-		compatible = "ntc,ncp15wb473";
+		compatible = "murata,ncp15wb473";
 		pullup-uv = <1800000>;
 		pullup-ohm = <47000>;
 		pulldown-ohm = <0>;
diff --git a/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt b/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt
new file mode 100644
index 00000000000..dde6c22ce91
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt
@@ -0,0 +1,42 @@
+* Rockchip RK3xxx I2C controller
+
+This driver interfaces with the native I2C controller present in Rockchip
+RK3xxx SoCs.
+
+Required properties :
+
+ - reg : Offset and length of the register set for the device
+ - compatible : should be "rockchip,rk3066-i2c", "rockchip,rk3188-i2c" or
+		"rockchip,rk3288-i2c".
+ - interrupts : interrupt number
+ - clocks : parent clock
+
+Required on RK3066, RK3188 :
+
+ - rockchip,grf : the phandle of the syscon node for the general register
+		  file (GRF)
+ - on those SoCs an alias with the correct I2C bus ID (bit offset in the GRF)
+   is also required.
+
+Optional properties :
+
+ - clock-frequency : SCL frequency to use (in Hz). If omitted, 100kHz is used.
+
+Example:
+
+aliases {
+	i2c0 = &i2c0;
+}
+
+i2c0: i2c@2002d000 {
+	compatible = "rockchip,rk3188-i2c";
+	reg = <0x2002d000 0x1000>;
+	interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	rockchip,grf = <&grf>;
+
+	clock-names = "i2c";
+	clocks = <&cru PCLK_I2C0>;
+};
diff --git a/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt b/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt
new file mode 100644
index 00000000000..6b765485af7
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt
@@ -0,0 +1,41 @@
+
+* Allwinner P2WI (Push/Pull 2 Wire Interface) controller
+
+Required properties :
+
+ - reg             : Offset and length of the register set for the device.
+ - compatible      : Should one of the following:
+                     - "allwinner,sun6i-a31-p2wi"
+ - interrupts      : The interrupt line connected to the P2WI peripheral.
+ - clocks          : The gate clk connected to the P2WI peripheral.
+ - resets          : The reset line connected to the P2WI peripheral.
+
+Optional properties :
+
+ - clock-frequency : Desired P2WI bus clock frequency in Hz. If not set the
+default frequency is 100kHz
+
+A P2WI may contain one child node encoding a P2WI slave device.
+
+Slave device properties:
+  Required properties:
+   - reg           : the I2C slave address used during the initialization
+                     process to switch from I2C to P2WI mode
+
+Example:
+
+	p2wi@01f03400 {
+		compatible = "allwinner,sun6i-a31-p2wi";
+		reg = <0x01f03400 0x400>;
+		interrupts = <0 39 4>;
+		clocks = <&apb0_gates 3>;
+		clock-frequency = <6000000>;
+		resets = <&apb0_rst 3>;
+
+		axp221: pmic@68 {
+			compatible = "x-powers,axp221";
+			reg = <0x68>;
+
+			/* ... */
+		};
+	};
diff --git a/Documentation/devicetree/bindings/gpio/gpio_keys.txt b/Documentation/devicetree/bindings/input/gpio-keys.txt
index 5c2c02140a6..5c2c02140a6 100644
--- a/Documentation/devicetree/bindings/gpio/gpio_keys.txt
+++ b/Documentation/devicetree/bindings/input/gpio-keys.txt
diff --git a/Documentation/devicetree/bindings/input/st-keyscan.txt b/Documentation/devicetree/bindings/input/st-keyscan.txt
new file mode 100644
index 00000000000..51eb428e5c8
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/st-keyscan.txt
@@ -0,0 +1,60 @@
+* ST Keyscan controller Device Tree bindings
+
+The ST keyscan controller Device Tree binding is based on the
+matrix-keymap.
+
+Required properties:
+- compatible: "st,sti-keyscan"
+
+- reg: Register base address and size of st-keyscan controller.
+
+- interrupts: Interrupt number for the st-keyscan controller.
+
+- clocks: Must contain one entry, for the module clock.
+  See ../clocks/clock-bindings.txt for details.
+
+- pinctrl: Should specify pin control groups used for this controller.
+  See ../pinctrl/pinctrl-bindings.txt for details.
+
+- linux,keymap: The keymap for keys as described in the binding document
+  devicetree/bindings/input/matrix-keymap.txt.
+
+- keypad,num-rows: Number of row lines connected to the keypad controller.
+
+- keypad,num-columns: Number of column lines connected to the keypad
+  controller.
+
+Optional property:
+- st,debounce_us: Debouncing interval time in microseconds
+
+Example:
+
+keyscan: keyscan@fe4b0000 {
+	compatible = "st,sti-keyscan";
+	reg = <0xfe4b0000 0x2000>;
+	interrupts = <GIC_SPI 212 IRQ_TYPE_NONE>;
+	clocks	= <&CLK_SYSIN>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_keyscan>;
+
+	keypad,num-rows = <4>;
+	keypad,num-columns = <4>;
+	st,debounce_us = <5000>;
+
+	linux,keymap = < MATRIX_KEY(0x00, 0x00, KEY_F13)
+			 MATRIX_KEY(0x00, 0x01, KEY_F9)
+			 MATRIX_KEY(0x00, 0x02, KEY_F5)
+			 MATRIX_KEY(0x00, 0x03, KEY_F1)
+			 MATRIX_KEY(0x01, 0x00, KEY_F14)
+			 MATRIX_KEY(0x01, 0x01, KEY_F10)
+			 MATRIX_KEY(0x01, 0x02, KEY_F6)
+			 MATRIX_KEY(0x01, 0x03, KEY_F2)
+			 MATRIX_KEY(0x02, 0x00, KEY_F15)
+			 MATRIX_KEY(0x02, 0x01, KEY_F11)
+			 MATRIX_KEY(0x02, 0x02, KEY_F7)
+			 MATRIX_KEY(0x02, 0x03, KEY_F3)
+			 MATRIX_KEY(0x03, 0x00, KEY_F16)
+			 MATRIX_KEY(0x03, 0x01, KEY_F12)
+			 MATRIX_KEY(0x03, 0x02, KEY_F8)
+			 MATRIX_KEY(0x03, 0x03, KEY_F4) >;
+	};
diff --git a/Documentation/devicetree/bindings/input/touchscreen/sun4i.txt b/Documentation/devicetree/bindings/input/touchscreen/sun4i.txt
new file mode 100644
index 00000000000..aef57791f40
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/sun4i.txt
@@ -0,0 +1,20 @@
+sun4i resistive touchscreen controller
+--------------------------------------
+
+Required properties:
+ - compatible: "allwinner,sun4i-a10-ts"
+ - reg: mmio address range of the chip
+ - interrupts: interrupt to which the chip is connected
+
+Optional properties:
+ - allwinner,ts-attached: boolean indicating that an actual touchscreen is
+			  attached to the controller
+
+Example:
+
+	rtp: rtp@01c25000 {
+		compatible = "allwinner,sun4i-a10-ts";
+		reg = <0x01c25000 0x100>;
+		interrupts = <29>;
+		allwinner,ts-attached;
+	};
diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.txt b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.txt
new file mode 100644
index 00000000000..d8e06163c54
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.txt
@@ -0,0 +1,27 @@
+General Touchscreen Properties:
+
+Optional properties for Touchscreens:
+ - touchscreen-size-x		: horizontal resolution of touchscreen
+				  (in pixels)
+ - touchscreen-size-y		: vertical resolution of touchscreen
+				  (in pixels)
+ - touchscreen-max-pressure	: maximum reported pressure (arbitrary range
+				  dependent on the controller)
+ - touchscreen-fuzz-x		: horizontal noise value of the absolute input
+				  device (in pixels)
+ - touchscreen-fuzz-y		: vertical noise value of the absolute input
+				  device (in pixels)
+ - touchscreen-fuzz-pressure	: pressure noise value of the absolute input
+				  device (arbitrary range dependent on the
+				  controller)
+ - touchscreen-inverted-x	: X axis is inverted (boolean)
+ - touchscreen-inverted-y	: Y axis is inverted (boolean)
+
+Deprecated properties for Touchscreens:
+ - x-size			: deprecated name for touchscreen-size-x
+ - y-size			: deprecated name for touchscreen-size-y
+ - moving-threshold		: deprecated name for a combination of
+				  touchscreen-fuzz-x and touchscreen-fuzz-y
+ - contact-threshold		: deprecated name for touchscreen-fuzz-pressure
+ - x-invert			: deprecated name for touchscreen-inverted-x
+ - y-invert			: deprecated name for touchscreen-inverted-y
diff --git a/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt b/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt
new file mode 100644
index 00000000000..4b641c7bf1c
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt
@@ -0,0 +1,42 @@
+* Texas Instruments tsc2005 touchscreen controller
+
+Required properties:
+ - compatible		      : "ti,tsc2005"
+ - reg			      : SPI device address
+ - spi-max-frequency	      : Maximal SPI speed
+ - interrupts		      : IRQ specifier
+ - reset-gpios		      : GPIO specifier
+ - vio-supply                 : Regulator specifier
+
+Optional properties:
+ - ti,x-plate-ohms	      : integer, resistance of the touchscreen's X plates
+				in ohm (defaults to 280)
+ - ti,esd-recovery-timeout-ms : integer, if the touchscreen does not respond after
+				the configured time (in milli seconds), the driver
+				will reset it. This is disabled by default.
+ - properties defined in touchscreen.txt
+
+Example:
+
+&mcspi1 {
+	tsc2005@0 {
+		compatible = "ti,tsc2005";
+		spi-max-frequency = <6000000>;
+		reg = <0>;
+
+		vio-supply = <&vio>;
+
+		reset-gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>; /* 104 */
+		interrupts-extended = <&gpio4 4 IRQ_TYPE_EDGE_RISING>; /* 100 */
+
+		touchscreen-fuzz-x = <4>;
+		touchscreen-fuzz-y = <7>;
+		touchscreen-fuzz-pressure = <2>;
+		touchscreen-max-x = <4096>;
+		touchscreen-max-y = <4096>;
+		touchscreen-max-pressure = <2048>;
+
+		ti,x-plate-ohms = <280>;
+		ti,esd-recovery-timeout-ms = <8000>;
+	};
+}
diff --git a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
index c55b8c016a9..1b66a413fb9 100644
--- a/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
+++ b/Documentation/devicetree/bindings/leds/leds-lp55xx.txt
@@ -1,7 +1,13 @@
 Binding for TI/National Semiconductor LP55xx Led Drivers
 
 Required properties:
-- compatible: "national,lp5521" or "national,lp5523" or "ti,lp5562" or "ti,lp8501"
+- compatible: one of
+	national,lp5521
+	national,lp5523
+	ti,lp55231
+	ti,lp5562
+	ti,lp8501
+
 - reg: I2C slave address
 - clock-mode: Input clock mode, (0: automode, 1: internal, 2: external)
 
diff --git a/Documentation/devicetree/bindings/leds/leds-pwm.txt b/Documentation/devicetree/bindings/leds/leds-pwm.txt
index 7297107cf83..6c6583c35f2 100644
--- a/Documentation/devicetree/bindings/leds/leds-pwm.txt
+++ b/Documentation/devicetree/bindings/leds/leds-pwm.txt
@@ -13,6 +13,8 @@ LED sub-node properties:
   For the pwms and pwm-names property please refer to:
   Documentation/devicetree/bindings/pwm/pwm.txt
 - max-brightness : Maximum brightness possible for the LED
+- active-low : (optional) For PWMs where the LED is wired to supply
+  rather than ground.
 - label :  (optional)
   see Documentation/devicetree/bindings/leds/common.txt
 - linux,default-trigger :  (optional)
diff --git a/Documentation/devicetree/bindings/mfd/bfticu.txt b/Documentation/devicetree/bindings/mfd/bfticu.txt
new file mode 100644
index 00000000000..65c90776c62
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/bfticu.txt
@@ -0,0 +1,25 @@
+KEYMILE bfticu Chassis Management FPGA
+
+The bfticu is a multifunction device that manages the whole chassis.
+Its main functionality is to collect IRQs from the whole chassis and signals
+them to a single controller.
+
+Required properties:
+- compatible: "keymile,bfticu"
+- interrupt-controller: the bfticu FPGA is an interrupt controller
+- interrupts: the main IRQ line to signal the collected IRQs
+- #interrupt-cells : is 2 and their usage is compliant to the 2 cells variant
+  of Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+- interrupt-parent: the parent IRQ ctrl the main IRQ is connected to
+- reg: access on the parent local bus (chip select, offset in chip select, size)
+
+Example:
+
+	chassis-mgmt@3,0 {
+		compatible = "keymile,bfticu";
+		interrupt-controller;
+		#interrupt-cells = <2>;
+		reg = <3 0 0x100>;
+		interrupt-parent = <&mpic>;
+		interrupts = <6 1 0 0>;
+	};
diff --git a/Documentation/devicetree/bindings/mfd/qriox.txt b/Documentation/devicetree/bindings/mfd/qriox.txt
new file mode 100644
index 00000000000..f301e2d4ce7
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/qriox.txt
@@ -0,0 +1,17 @@
+KEYMILE qrio Board Control CPLD
+
+The qrio is a multifunction device that controls the KEYMILE boards based on
+the kmp204x design.
+It is consists of a reset controller, watchdog timer, LEDs, and 2 IRQ capable
+GPIO blocks.
+
+Required properties:
+- compatible: "keymile,qriox"
+- reg: access on the parent local bus (chip select, offset in chip select, size)
+
+Example:
+
+	board-control@1,0 {
+		compatible = "keymile,qriox";
+		reg = <1 0 0x80>;
+	};
diff --git a/Documentation/devicetree/bindings/mfd/twl4030-power.txt b/Documentation/devicetree/bindings/mfd/twl4030-power.txt
index 8e15ec35ac9..b9ee7b98d3e 100644
--- a/Documentation/devicetree/bindings/mfd/twl4030-power.txt
+++ b/Documentation/devicetree/bindings/mfd/twl4030-power.txt
@@ -5,7 +5,22 @@ to control the power resources, including power scripts. For now, the
 binding only supports the complete shutdown of the system after poweroff.
 
 Required properties:
-- compatible : must be "ti,twl4030-power"
+- compatible : must be one of the following
+	"ti,twl4030-power"
+	"ti,twl4030-power-reset"
+	"ti,twl4030-power-idle"
+	"ti,twl4030-power-idle-osc-off"
+
+The use of ti,twl4030-power-reset is recommended at least on
+3530 that needs a special configuration for warm reset to work.
+
+When using ti,twl4030-power-idle, the TI recommended configuration
+for idle modes is loaded to the tlw4030 PMIC.
+
+When using ti,twl4030-power-idle-osc-off, the TI recommended
+configuration is used with the external oscillator being shut
+down during off-idle. Note that this does not work on all boards
+depending on how the external oscillator is wired.
 
 Optional properties:
 - ti,use_poweroff: With this flag, the chip will initiates an ACTIVE-to-OFF or
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index 9dce540771f..3c18001dfd5 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -38,6 +38,8 @@ Optional properties:
 - mmc-highspeed-ddr-1_2v: eMMC high-speed DDR mode(1.2V I/O) is supported
 - mmc-hs200-1_8v: eMMC HS200 mode(1.8V I/O) is supported
 - mmc-hs200-1_2v: eMMC HS200 mode(1.2V I/O) is supported
+- mmc-hs400-1_8v: eMMC HS400 mode(1.8V I/O) is supported
+- mmc-hs400-1_2v: eMMC HS400 mode(1.2V I/O) is supported
 
 *NOTE* on CD and WP polarity. To use common for all SD/MMC host controllers line
 polarity properties, we have to fix the meaning of the "normal" and "inverted"
diff --git a/Documentation/devicetree/bindings/mmc/moxa,moxart-mmc.txt b/Documentation/devicetree/bindings/mmc/moxa,moxart-mmc.txt
new file mode 100644
index 00000000000..b63819149f2
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/moxa,moxart-mmc.txt
@@ -0,0 +1,30 @@
+MOXA ART MMC Host Controller Interface
+
+  Inherits from mmc binding[1].
+
+  [1] Documentation/devicetree/bindings/mmc/mmc.txt
+
+Required properties:
+
+- compatible :	Must be "moxa,moxart-mmc" or "faraday,ftsdc010"
+- reg :		Should contain registers location and length
+- interrupts :	Should contain the interrupt number
+- clocks :	Should contain phandle for the clock feeding the MMC controller
+
+Optional properties:
+
+- dmas :	Should contain two DMA channels, line request number must be 5 for
+		both channels
+- dma-names :	Must be "tx", "rx"
+
+Example:
+
+	mmc: mmc@98e00000 {
+		compatible = "moxa,moxart-mmc";
+		reg = <0x98e00000 0x5C>;
+		interrupts = <5 0>;
+		clocks = <&clk_apb>;
+		dmas =  <&dma 5>,
+			<&dma 5>;
+		dma-names = "tx", "rx";
+	};
diff --git a/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
index 8f3f1331535..2d4a7258a10 100644
--- a/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
@@ -69,10 +69,6 @@ Optional properties:
 
 * supports-highspeed: Enables support for high speed cards (up to 50MHz)
 
-* caps2-mmc-hs200-1_8v: Supports mmc HS200 SDR 1.8V mode
-
-* caps2-mmc-hs200-1_2v: Supports mmc HS200 SDR 1.2V mode
-
 * broken-cd: as documented in mmc core bindings.
 
 * vmmc-supply: The phandle to the regulator to use for vmmc.  If this is
@@ -103,7 +99,6 @@ board specific portions as listed below.
 		clock-freq-min-max = <400000 200000000>;
 		num-slots = <1>;
 		supports-highspeed;
-		caps2-mmc-hs200-1_8v;
 		broken-cd;
 		fifo-depth = <0x80>;
 		card-detect-delay = <200>;
diff --git a/Documentation/devicetree/bindings/mmc/usdhi6rol0.txt b/Documentation/devicetree/bindings/mmc/usdhi6rol0.txt
new file mode 100644
index 00000000000..8babdaa8623
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/usdhi6rol0.txt
@@ -0,0 +1,33 @@
+* Renesas usdhi6rol0 SD/SDIO host controller
+
+Required properties:
+
+- compatible:	must be
+		"renesas,usdhi6rol0"
+- interrupts:	3 interrupts, named "card detect", "data" and "SDIO" must be
+		specified
+- clocks:	a clock binding for the IMCLK input
+
+Optional properties:
+
+- vmmc-supply:	a phandle of a regulator, supplying Vcc to the card
+- vqmmc-supply:	a phandle of a regulator, supplying VccQ to the card
+
+Additionally any standard mmc bindings from mmc.txt can be used.
+
+Example:
+
+sd0: sd@ab000000 {
+	compatible = "renesas,usdhi6rol0";
+	reg = <0xab000000 0x200>;
+	interrupts = <0 23 0x4
+		      0 24 0x4
+		      0 25 0x4>;
+	interrupt-names = "card detect", "data", "SDIO";
+	bus-width = <4>;
+	max-frequency = <50000000>;
+	cap-power-off-card;
+	clocks = <&imclk>;
+	vmmc-supply = <&vcc_sd0>;
+	vqmmc-supply = <&vccq_sd0>;
+};
diff --git a/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
new file mode 100644
index 00000000000..823d1341219
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/fsl-quadspi.txt
@@ -0,0 +1,35 @@
+* Freescale Quad Serial Peripheral Interface(QuadSPI)
+
+Required properties:
+  - compatible : Should be "fsl,vf610-qspi"
+  - reg : the first contains the register location and length,
+          the second contains the memory mapping address and length
+  - reg-names: Should contain the reg names "QuadSPI" and "QuadSPI-memory"
+  - interrupts : Should contain the interrupt for the device
+  - clocks : The clocks needed by the QuadSPI controller
+  - clock-names : the name of the clocks
+
+Optional properties:
+  - fsl,qspi-has-second-chip: The controller has two buses, bus A and bus B.
+                              Each bus can be connected with two NOR flashes.
+			      Most of the time, each bus only has one NOR flash
+			      connected, this is the default case.
+			      But if there are two NOR flashes connected to the
+			      bus, you should enable this property.
+			      (Please check the board's schematic.)
+
+Example:
+
+qspi0: quadspi@40044000 {
+	compatible = "fsl,vf610-qspi";
+	reg = <0x40044000 0x1000>, <0x20000000 0x10000000>;
+	reg-names = "QuadSPI", "QuadSPI-memory";
+	interrupts = <0 24 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&clks VF610_CLK_QSPI0_EN>,
+		<&clks VF610_CLK_QSPI0>;
+	clock-names = "qspi_en", "qspi";
+
+	flash0: s25fl128s@0 {
+		....
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
index eb05255b678..65f4f7c4313 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
@@ -28,6 +28,8 @@ Optional properties:
 		"ham1"		1-bit Hamming ecc code
 		"bch4"		4-bit BCH ecc code
 		"bch8"		8-bit BCH ecc code
+		"bch16"		16-bit BCH ECC code
+		Refer below "How to select correct ECC scheme for your device ?"
 
  - ti,nand-xfer-type:		A string setting the data transfer type. One of:
 
@@ -90,3 +92,46 @@ Example for an AM33xx board:
 		};
 	};
 
+How to select correct ECC scheme for your device ?
+--------------------------------------------------
+Higher ECC scheme usually means better protection against bit-flips and
+increased system lifetime. However, selection of ECC scheme is dependent
+on various other factors also like;
+
+(1) support of built in hardware engines.
+	Some legacy OMAP SoC do not have ELM harware engine, so those SoC cannot
+	support ecc-schemes with hardware error-correction (BCHx_HW). However
+	such SoC can use ecc-schemes with software library for error-correction
+	(BCHx_HW_DETECTION_SW). The error correction capability with software
+	library remains equivalent to their hardware counter-part, but there is
+	slight CPU penalty when too many bit-flips are detected during reads.
+
+(2) Device parameters like OOBSIZE.
+	Other factor which governs the selection of ecc-scheme is oob-size.
+	Higher ECC schemes require more OOB/Spare area to store ECC syndrome,
+	so the device should have enough free bytes available its OOB/Spare
+	area to accomodate ECC for entire page. In general following expression
+	helps in determining if given device can accomodate ECC syndrome:
+	"2 + (PAGESIZE / 512) * ECC_BYTES" >= OOBSIZE"
+	where
+		OOBSIZE		number of bytes in OOB/spare area
+		PAGESIZE	number of bytes in main-area of device page
+		ECC_BYTES	number of ECC bytes generated to protect
+		                512 bytes of data, which is:
+				'3' for HAM1_xx ecc schemes
+				'7' for BCH4_xx ecc schemes
+				'14' for BCH8_xx ecc schemes
+				'26' for BCH16_xx ecc schemes
+
+	Example(a): For a device with PAGESIZE = 2048 and OOBSIZE = 64 and
+		trying to use BCH16 (ECC_BYTES=26) ecc-scheme.
+		Number of ECC bytes per page = (2 + (2048 / 512) * 26) = 106 B
+		which is greater than capacity of NAND device (OOBSIZE=64)
+		Hence, BCH16 cannot be supported on given device. But it can
+		probably use lower ecc-schemes like BCH8.
+
+	Example(b): For a device with PAGESIZE = 2048 and OOBSIZE = 128 and
+		trying to use BCH16 (ECC_BYTES=26) ecc-scheme.
+		Number of ECC bytes per page = (2 + (2048 / 512) * 26) = 106 B
+		which can be accomodate in the OOB/Spare area of this device
+		(OOBSIZE=128). So this device can use BCH16 ecc-scheme.
diff --git a/Documentation/devicetree/bindings/mtd/m25p80.txt b/Documentation/devicetree/bindings/mtd/m25p80.txt
index 6d3d5760947..4611aa83531 100644
--- a/Documentation/devicetree/bindings/mtd/m25p80.txt
+++ b/Documentation/devicetree/bindings/mtd/m25p80.txt
@@ -5,8 +5,8 @@ Required properties:
   representing partitions.
 - compatible : Should be the manufacturer and the name of the chip. Bear in mind
                the DT binding is not Linux-only, but in case of Linux, see the
-               "m25p_ids" table in drivers/mtd/devices/m25p80.c for the list of
-               supported chips.
+               "spi_nor_ids" table in drivers/mtd/spi-nor/spi-nor.c for the list
+               of supported chips.
 - reg : Chip-Select number
 - spi-max-frequency : Maximum frequency of the SPI bus the chip can operate at
 
diff --git a/Documentation/devicetree/bindings/mtd/pxa3xx-nand.txt b/Documentation/devicetree/bindings/mtd/pxa3xx-nand.txt
index 86e0a5601ff..de8b517a552 100644
--- a/Documentation/devicetree/bindings/mtd/pxa3xx-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/pxa3xx-nand.txt
@@ -17,6 +17,14 @@ Optional properties:
  - num-cs:			Number of chipselect lines to usw
  - nand-on-flash-bbt: 		boolean to enable on flash bbt option if
 				not present false
+ - nand-ecc-strength:           number of bits to correct per ECC step
+ - nand-ecc-step-size:          number of data bytes covered by a single ECC step
+
+The following ECC strength and step size are currently supported:
+
+ - nand-ecc-strength = <1>, nand-ecc-step-size = <512>
+ - nand-ecc-strength = <4>, nand-ecc-step-size = <512>
+ - nand-ecc-strength = <8>, nand-ecc-step-size = <512>
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt b/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt
new file mode 100644
index 00000000000..d01ed63d3eb
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt
@@ -0,0 +1,17 @@
+* AMD 10GbE PHY driver (amd-xgbe-phy)
+
+Required properties:
+- compatible: Should be "amd,xgbe-phy-seattle-v1a" and
+  "ethernet-phy-ieee802.3-c45"
+- reg: Address and length of the register sets for the device
+   - SerDes Rx/Tx registers
+   - SerDes integration registers (1/2)
+   - SerDes integration registers (2/2)
+
+Example:
+	xgbe_phy@e1240800 {
+		compatible = "amd,xgbe-phy-seattle-v1a", "ethernet-phy-ieee802.3-c45";
+		reg = <0 0xe1240800 0 0x00400>,
+		      <0 0xe1250000 0 0x00060>,
+		      <0 0xe1250080 0 0x00004>;
+	};
diff --git a/Documentation/devicetree/bindings/net/amd-xgbe.txt b/Documentation/devicetree/bindings/net/amd-xgbe.txt
new file mode 100644
index 00000000000..ea0c7908a3b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/amd-xgbe.txt
@@ -0,0 +1,34 @@
+* AMD 10GbE driver (amd-xgbe)
+
+Required properties:
+- compatible: Should be "amd,xgbe-seattle-v1a"
+- reg: Address and length of the register sets for the device
+   - MAC registers
+   - PCS registers
+- interrupt-parent: Should be the phandle for the interrupt controller
+  that services interrupts for this device
+- interrupts: Should contain the amd-xgbe interrupt
+- clocks: Should be the DMA clock for the amd-xgbe device (used for
+  calculating the correct Rx interrupt watchdog timer value on a DMA
+  channel for coalescing)
+- clock-names: Should be the name of the DMA clock, "dma_clk"
+- phy-handle: See ethernet.txt file in the same directory
+- phy-mode: See ethernet.txt file in the same directory
+
+Optional properties:
+- mac-address: mac address to be assigned to the device. Can be overridden
+  by UEFI.
+
+Example:
+	xgbe@e0700000 {
+		compatible = "amd,xgbe-seattle-v1a";
+		reg = <0 0xe0700000 0 0x80000>,
+		      <0 0xe0780000 0 0x80000>;
+		interrupt-parent = <&gic>;
+		interrupts = <0 325 4>;
+		clocks = <&xgbe_clk>;
+		clock-names = "dma_clk";
+		phy-handle = <&phy>;
+		phy-mode = "xgmii";
+		mac-address = [ 02 a1 a2 a3 a4 a5 ];
+	};
diff --git a/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt b/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt
index f2febb94550..451fef26b4d 100644
--- a/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt
+++ b/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt
@@ -24,7 +24,7 @@ Optional properties:
 - fixed-link: When the GENET interface is connected to a MoCA hardware block or
   when operating in a RGMII to RGMII type of connection, or when the MDIO bus is
   voluntarily disabled, this property should be used to describe the "fixed link".
-  See Documentation/devicetree/bindings/net/fsl-tsec-phy.txt for information on
+  See Documentation/devicetree/bindings/net/fixed-link.txt for information on
   the property specifics
 
 Required child nodes:
diff --git a/Documentation/devicetree/bindings/net/broadcom-systemport.txt b/Documentation/devicetree/bindings/net/broadcom-systemport.txt
new file mode 100644
index 00000000000..c183ea90d9b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/broadcom-systemport.txt
@@ -0,0 +1,29 @@
+* Broadcom BCM7xxx Ethernet Systemport Controller (SYSTEMPORT)
+
+Required properties:
+- compatible: should be one of "brcm,systemport-v1.00" or "brcm,systemport"
+- reg: address and length of the register set for the device.
+- interrupts: interrupts for the device, first cell must be for the the rx
+  interrupts, and the second cell should be for the transmit queues
+- local-mac-address: Ethernet MAC address (48 bits) of this adapter
+- phy-mode: Should be a string describing the PHY interface to the
+  Ethernet switch/PHY, see Documentation/devicetree/bindings/net/ethernet.txt
+- fixed-link: see Documentation/devicetree/bindings/net/fixed-link.txt for
+  the property specific details
+
+Optional properties:
+- systemport,num-tier2-arb: number of tier 2 arbiters, an integer
+- systemport,num-tier1-arb: number of tier 1 arbiters, an integer
+- systemport,num-txq: number of HW transmit queues, an integer
+- systemport,num-rxq: number of HW receive queues, an integer
+
+Example:
+ethernet@f04a0000 {
+	compatible = "brcm,systemport-v1.00";
+	reg = <0xf04a0000 0x4650>;
+	local-mac-address = [ 00 11 22 33 44 55 ];
+	fixed-link = <0 1 1000 0 0>;
+	phy-mode = "gmii";
+	interrupts = <0x0 0x16 0x0>,
+		<0x0 0x17 0x0>;
+};
diff --git a/Documentation/devicetree/bindings/net/can/xilinx_can.txt b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
new file mode 100644
index 00000000000..fe38847d8e2
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
@@ -0,0 +1,44 @@
+Xilinx Axi CAN/Zynq CANPS controller Device Tree Bindings
+---------------------------------------------------------
+
+Required properties:
+- compatible		: Should be "xlnx,zynq-can-1.0" for Zynq CAN
+			  controllers and "xlnx,axi-can-1.00.a" for Axi CAN
+			  controllers.
+- reg			: Physical base address and size of the Axi CAN/Zynq
+			  CANPS registers map.
+- interrupts		: Property with a value describing the interrupt
+			  number.
+- interrupt-parent	: Must be core interrupt controller
+- clock-names		: List of input clock names - "can_clk", "pclk"
+			  (For CANPS), "can_clk" , "s_axi_aclk"(For AXI CAN)
+			  (See clock bindings for details).
+- clocks		: Clock phandles (see clock bindings for details).
+- tx-fifo-depth		: Can Tx fifo depth.
+- rx-fifo-depth		: Can Rx fifo depth.
+
+
+Example:
+
+For Zynq CANPS Dts file:
+	zynq_can_0: can@e0008000 {
+			compatible = "xlnx,zynq-can-1.0";
+			clocks = <&clkc 19>, <&clkc 36>;
+			clock-names = "can_clk", "pclk";
+			reg = <0xe0008000 0x1000>;
+			interrupts = <0 28 4>;
+			interrupt-parent = <&intc>;
+			tx-fifo-depth = <0x40>;
+			rx-fifo-depth = <0x40>;
+		};
+For Axi CAN Dts file:
+	axi_can_0: axi-can@40000000 {
+			compatible = "xlnx,axi-can-1.00.a";
+			clocks = <&clkc 0>, <&clkc 1>;
+			clock-names = "can_clk","s_axi_aclk" ;
+			reg = <0x40000000 0x10000>;
+			interrupt-parent = <&intc>;
+			interrupts = <0 59 1>;
+			tx-fifo-depth = <0x40>;
+			rx-fifo-depth = <0x40>;
+		};
diff --git a/Documentation/devicetree/bindings/net/cpsw-phy-sel.txt b/Documentation/devicetree/bindings/net/cpsw-phy-sel.txt
index 7ff57a119f8..764c0c79b43 100644
--- a/Documentation/devicetree/bindings/net/cpsw-phy-sel.txt
+++ b/Documentation/devicetree/bindings/net/cpsw-phy-sel.txt
@@ -2,7 +2,9 @@ TI CPSW Phy mode Selection Device Tree Bindings
 -----------------------------------------------
 
 Required properties:
-- compatible		: Should be "ti,am3352-cpsw-phy-sel"
+- compatible		: Should be "ti,am3352-cpsw-phy-sel" for am335x platform and
+			  "ti,dra7xx-cpsw-phy-sel" for dra7xx platform
+			  "ti,am43xx-cpsw-phy-sel" for am43xx platform
 - reg			: physical base address and size of the cpsw
 			  registers map
 - reg-names		: names of the register map given in "reg" node
diff --git a/Documentation/devicetree/bindings/net/fixed-link.txt b/Documentation/devicetree/bindings/net/fixed-link.txt
new file mode 100644
index 00000000000..82bf7e0f47b
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/fixed-link.txt
@@ -0,0 +1,42 @@
+Fixed link Device Tree binding
+------------------------------
+
+Some Ethernet MACs have a "fixed link", and are not connected to a
+normal MDIO-managed PHY device. For those situations, a Device Tree
+binding allows to describe a "fixed link".
+
+Such a fixed link situation is described by creating a 'fixed-link'
+sub-node of the Ethernet MAC device node, with the following
+properties:
+
+* 'speed' (integer, mandatory), to indicate the link speed. Accepted
+  values are 10, 100 and 1000
+* 'full-duplex' (boolean, optional), to indicate that full duplex is
+  used. When absent, half duplex is assumed.
+* 'pause' (boolean, optional), to indicate that pause should be
+  enabled.
+* 'asym-pause' (boolean, optional), to indicate that asym_pause should
+  be enabled.
+
+Old, deprecated 'fixed-link' binding:
+
+* A 'fixed-link' property in the Ethernet MAC node, with 5 cells, of the
+  form <a b c d e> with the following accepted values:
+  - a: emulated PHY ID, choose any but but unique to the all specified
+    fixed-links, from 0 to 31
+  - b: duplex configuration: 0 for half duplex, 1 for full duplex
+  - c: link speed in Mbits/sec, accepted values are: 10, 100 and 1000
+  - d: pause configuration: 0 for no pause, 1 for pause
+  - e: asymmetric pause configuration: 0 for no asymmetric pause, 1 for
+    asymmetric pause
+
+Example:
+
+ethernet@0 {
+	...
+	fixed-link {
+	      speed = <1000>;
+	      full-duplex;
+	};
+	...
+};
diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
index 737cdef4f90..be6ea8960f2 100644
--- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
+++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
@@ -42,10 +42,7 @@ Properties:
     interrupt.  For TSEC and eTSEC devices, the first interrupt is
     transmit, the second is receive, and the third is error.
   - phy-handle : See ethernet.txt file in the same directory.
-  - fixed-link : <a b c d e> where a is emulated phy id - choose any,
-    but unique to the all specified fixed-links, b is duplex - 0 half,
-    1 full, c is link speed - d#10/d#100/d#1000, d is pause - 0 no
-    pause, 1 pause, e is asym_pause - 0 no asym_pause, 1 asym_pause.
+  - fixed-link : See fixed-link.txt in the same directory.
   - phy-connection-type : See ethernet.txt file in the same directory.
     This property is only really needed if the connection is of type
     "rgmii-id", as all other connection types are detected by hardware.
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt b/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt
new file mode 100644
index 00000000000..75d398bb1fb
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/hisilicon-hix5hd2-gmac.txt
@@ -0,0 +1,36 @@
+Hisilicon hix5hd2 gmac controller
+
+Required properties:
+- compatible: should be "hisilicon,hix5hd2-gmac".
+- reg: specifies base physical address(s) and size of the device registers.
+  The first region is the MAC register base and size.
+  The second region is external interface control register.
+- interrupts: should contain the MAC interrupt.
+- #address-cells: must be <1>.
+- #size-cells: must be <0>.
+- phy-mode: see ethernet.txt [1].
+- phy-handle: see ethernet.txt [1].
+- mac-address: see ethernet.txt [1].
+- clocks: clock phandle and specifier pair.
+
+- PHY subnode: inherits from phy binding [2]
+
+[1] Documentation/devicetree/bindings/net/ethernet.txt
+[2] Documentation/devicetree/bindings/net/phy.txt
+
+Example:
+	gmac0: ethernet@f9840000 {
+		compatible = "hisilicon,hix5hd2-gmac";
+		reg = <0xf9840000 0x1000>,<0xf984300c 0x4>;
+		interrupts = <0 71 4>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		phy-mode = "mii";
+		phy-handle = <&phy2>;
+		mac-address = [00 00 00 00 00 00];
+		clocks = <&clock HIX5HD2_MAC0_CLK>;
+
+		phy2: ethernet-phy@2 {
+			reg = <2>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt b/Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt
new file mode 100644
index 00000000000..d3bbdded4cb
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt
@@ -0,0 +1,23 @@
+* AT86RF230 IEEE 802.15.4 *
+
+Required properties:
+  - compatible:		should be "atmel,at86rf230", "atmel,at86rf231",
+			"atmel,at86rf233" or "atmel,at86rf212"
+  - spi-max-frequency:	maximal bus speed, should be set to 7500000 depends
+			sync or async operation mode
+  - reg:		the chipselect index
+  - interrupts:		the interrupt generated by the device
+
+Optional properties:
+  - reset-gpio:		GPIO spec for the rstn pin
+  - sleep-gpio:		GPIO spec for the slp_tr pin
+
+Example:
+
+	at86rf231@0 {
+		compatible = "atmel,at86rf231";
+		spi-max-frequency = <7500000>;
+		reg = <0>;
+		interrupts = <19 1>;
+		interrupt-parent = <&gpio3>;
+	};
diff --git a/Documentation/devicetree/bindings/net/micrel-ks8851.txt b/Documentation/devicetree/bindings/net/micrel-ks8851.txt
index d54d0cc7948..bbdf9a7359a 100644
--- a/Documentation/devicetree/bindings/net/micrel-ks8851.txt
+++ b/Documentation/devicetree/bindings/net/micrel-ks8851.txt
@@ -1,9 +1,18 @@
-Micrel KS8851 Ethernet mac
+Micrel KS8851 Ethernet mac (MLL)
 
 Required properties:
-- compatible = "micrel,ks8851-ml" of parallel interface
+- compatible = "micrel,ks8851-mll" of parallel interface
 - reg : 2 physical address and size of registers for data and command
 - interrupts : interrupt connection
 
+Micrel KS8851 Ethernet mac (SPI)
+
+Required properties:
+- compatible = "micrel,ks8851" or the deprecated "ks8851"
+- reg : chip select number
+- interrupts : interrupt connection
+
 Optional properties:
-- vdd-supply:	supply for Ethernet mac
+- vdd-supply: analog 3.3V supply for Ethernet mac
+- vdd-io-supply: digital 1.8V IO supply for Ethernet mac
+- reset-gpios: reset_n input pin
diff --git a/Documentation/devicetree/bindings/net/micrel-ksz9021.txt b/Documentation/devicetree/bindings/net/micrel-ksz9021.txt
deleted file mode 100644
index 997a63f1aea..00000000000
--- a/Documentation/devicetree/bindings/net/micrel-ksz9021.txt
+++ /dev/null
@@ -1,49 +0,0 @@
-Micrel KSZ9021 Gigabit Ethernet PHY
-
-Some boards require special tuning values, particularly when it comes to
-clock delays.  You can specify clock delay values by adding
-micrel-specific properties to an Ethernet OF device node.
-
-All skew control options are specified in picoseconds.  The minimum
-value is 0, and the maximum value is 3000.
-
-Optional properties:
- - rxc-skew-ps : Skew control of RXC pad
- - rxdv-skew-ps : Skew control of RX CTL pad
- - txc-skew-ps : Skew control of TXC pad
- - txen-skew-ps : Skew control of TX_CTL pad
- - rxd0-skew-ps : Skew control of RX data 0 pad
- - rxd1-skew-ps : Skew control of RX data 1 pad
- - rxd2-skew-ps : Skew control of RX data 2 pad
- - rxd3-skew-ps : Skew control of RX data 3 pad
- - txd0-skew-ps : Skew control of TX data 0 pad
- - txd1-skew-ps : Skew control of TX data 1 pad
- - txd2-skew-ps : Skew control of TX data 2 pad
- - txd3-skew-ps : Skew control of TX data 3 pad
-
-Examples:
-
-	/* Attach to an Ethernet device with autodetected PHY */
-	&enet {
-		rxc-skew-ps = <3000>;
-		rxdv-skew-ps = <0>;
-		txc-skew-ps = <3000>;
-		txen-skew-ps = <0>;
-		status = "okay";
-	};
-
-	/* Attach to an explicitly-specified PHY */
-	mdio {
-		phy0: ethernet-phy@0 {
-			rxc-skew-ps = <3000>;
-			rxdv-skew-ps = <0>;
-			txc-skew-ps = <3000>;
-			txen-skew-ps = <0>;
-			reg = <0>;
-		};
-	};
-	ethernet@70000 {
-		status = "okay";
-		phy = <&phy0>;
-		phy-mode = "rgmii-id";
-	};
diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
new file mode 100644
index 00000000000..692076fda0e
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt
@@ -0,0 +1,83 @@
+Micrel KSZ9021/KSZ9031 Gigabit Ethernet PHY
+
+Some boards require special tuning values, particularly when it comes to
+clock delays. You can specify clock delay values by adding
+micrel-specific properties to an Ethernet OF device node.
+
+Note that these settings are applied after any phy-specific fixup from
+phy_fixup_list (see phy_init_hw() from drivers/net/phy/phy_device.c),
+and therefore may overwrite them.
+
+KSZ9021:
+
+  All skew control options are specified in picoseconds. The minimum
+  value is 0, the maximum value is 3000, and it is incremented by 200ps
+  steps.
+
+  Optional properties:
+
+    - rxc-skew-ps : Skew control of RXC pad
+    - rxdv-skew-ps : Skew control of RX CTL pad
+    - txc-skew-ps : Skew control of TXC pad
+    - txen-skew-ps : Skew control of TX CTL pad
+    - rxd0-skew-ps : Skew control of RX data 0 pad
+    - rxd1-skew-ps : Skew control of RX data 1 pad
+    - rxd2-skew-ps : Skew control of RX data 2 pad
+    - rxd3-skew-ps : Skew control of RX data 3 pad
+    - txd0-skew-ps : Skew control of TX data 0 pad
+    - txd1-skew-ps : Skew control of TX data 1 pad
+    - txd2-skew-ps : Skew control of TX data 2 pad
+    - txd3-skew-ps : Skew control of TX data 3 pad
+
+KSZ9031:
+
+  All skew control options are specified in picoseconds. The minimum
+  value is 0, and the maximum is property-dependent. The increment
+  step is 60ps.
+
+  Optional properties:
+
+    Maximum value of 1860:
+
+      - rxc-skew-ps : Skew control of RX clock pad
+      - txc-skew-ps : Skew control of TX clock pad
+
+    Maximum value of 900:
+
+      - rxdv-skew-ps : Skew control of RX CTL pad
+      - txen-skew-ps : Skew control of TX CTL pad
+      - rxd0-skew-ps : Skew control of RX data 0 pad
+      - rxd1-skew-ps : Skew control of RX data 1 pad
+      - rxd2-skew-ps : Skew control of RX data 2 pad
+      - rxd3-skew-ps : Skew control of RX data 3 pad
+      - txd0-skew-ps : Skew control of TX data 0 pad
+      - txd1-skew-ps : Skew control of TX data 1 pad
+      - txd2-skew-ps : Skew control of TX data 2 pad
+      - txd3-skew-ps : Skew control of TX data 3 pad
+
+Examples:
+
+	/* Attach to an Ethernet device with autodetected PHY */
+	&enet {
+		rxc-skew-ps = <3000>;
+		rxdv-skew-ps = <0>;
+		txc-skew-ps = <3000>;
+		txen-skew-ps = <0>;
+		status = "okay";
+	};
+
+	/* Attach to an explicitly-specified PHY */
+	mdio {
+		phy0: ethernet-phy@0 {
+			rxc-skew-ps = <3000>;
+			rxdv-skew-ps = <0>;
+			txc-skew-ps = <3000>;
+			txen-skew-ps = <0>;
+			reg = <0>;
+		};
+	};
+	ethernet@70000 {
+		status = "okay";
+		phy = <&phy0>;
+		phy-mode = "rgmii-id";
+	};
diff --git a/Documentation/devicetree/bindings/net/nfc/pn544.txt b/Documentation/devicetree/bindings/net/nfc/pn544.txt
new file mode 100644
index 00000000000..dab69f36167
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/nfc/pn544.txt
@@ -0,0 +1,35 @@
+* NXP Semiconductors PN544 NFC Controller
+
+Required properties:
+- compatible: Should be "nxp,pn544-i2c".
+- clock-frequency: I²C work frequency.
+- reg: address on the bus
+- interrupt-parent: phandle for the interrupt gpio controller
+- interrupts: GPIO interrupt to which the chip is connected
+- enable-gpios: Output GPIO pin used for enabling/disabling the PN544
+- firmware-gpios: Output GPIO pin used to enter firmware download mode
+
+Optional SoC Specific Properties:
+- pinctrl-names: Contains only one value - "default".
+- pintctrl-0: Specifies the pin control groups used for this controller.
+
+Example (for ARM-based BeagleBone with PN544 on I2C2):
+
+&i2c2 {
+
+	status = "okay";
+
+	pn544: pn544@28 {
+
+		compatible = "nxp,pn544-i2c";
+
+		reg = <0x28>;
+		clock-frequency = <400000>;
+
+		interrupt-parent = <&gpio1>;
+		interrupts = <17 GPIO_ACTIVE_HIGH>;
+
+		enable-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>;
+		firmware-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/nfc/st21nfca.txt b/Documentation/devicetree/bindings/net/nfc/st21nfca.txt
new file mode 100644
index 00000000000..e4faa2e8dfe
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/nfc/st21nfca.txt
@@ -0,0 +1,33 @@
+* STMicroelectronics SAS. ST21NFCA NFC Controller
+
+Required properties:
+- compatible: Should be "st,st21nfca_i2c".
+- clock-frequency: I²C work frequency.
+- reg: address on the bus
+- interrupt-parent: phandle for the interrupt gpio controller
+- interrupts: GPIO interrupt to which the chip is connected
+- enable-gpios: Output GPIO pin used for enabling/disabling the ST21NFCA
+
+Optional SoC Specific Properties:
+- pinctrl-names: Contains only one value - "default".
+- pintctrl-0: Specifies the pin control groups used for this controller.
+
+Example (for ARM-based BeagleBoard xM with ST21NFCA on I2C2):
+
+&i2c2 {
+
+	status = "okay";
+
+	st21nfca: st21nfca@1 {
+
+		compatible = "st,st21nfca_i2c";
+
+		reg = <0x01>;
+		clock-frequency = <400000>;
+
+		interrupt-parent = <&gpio5>;
+		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
+
+		enable-gpios = <&gpio5 29 GPIO_ACTIVE_HIGH>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
index 8dd3ef7bc56..1e436133685 100644
--- a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
+++ b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
@@ -12,6 +12,7 @@ Required properties:
 Optional SoC Specific Properties:
 - pinctrl-names: Contains only one value - "default".
 - pintctrl-0: Specifies the pin control groups used for this controller.
+- autosuspend-delay: Specify autosuspend delay in milliseconds.
 
 Example (for ARM-based BeagleBone with TRF7970A on SPI1):
 
@@ -29,6 +30,7 @@ Example (for ARM-based BeagleBone with TRF7970A on SPI1):
 		ti,enable-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>,
 				  <&gpio2 5 GPIO_ACTIVE_LOW>;
 		vin-supply = <&ldo3_reg>;
+		autosuspend-delay = <30000>;
 		status = "okay";
 	};
 };
diff --git a/Documentation/devicetree/bindings/net/via-rhine.txt b/Documentation/devicetree/bindings/net/via-rhine.txt
new file mode 100644
index 00000000000..334eca2bf93
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/via-rhine.txt
@@ -0,0 +1,17 @@
+* VIA Rhine 10/100 Network Controller
+
+Required properties:
+- compatible : Should be "via,vt8500-rhine" for integrated
+	Rhine controllers found in VIA VT8500, WonderMedia WM8950
+	and similar. These are listed as 1106:3106 rev. 0x84 on the
+	virtual PCI bus under vendor-provided kernels
+- reg : Address and length of the io space
+- interrupts : Should contain the controller interrupt line
+
+Examples:
+
+ethernet@d8004000 {
+	compatible = "via,vt8500-rhine";
+	reg = <0xd8004000 0x100>;
+	interrupts = <10>;
+};
diff --git a/Documentation/devicetree/bindings/panel/auo,b133xtn01.txt b/Documentation/devicetree/bindings/panel/auo,b133xtn01.txt
new file mode 100644
index 00000000000..7443b7c7676
--- /dev/null
+++ b/Documentation/devicetree/bindings/panel/auo,b133xtn01.txt
@@ -0,0 +1,7 @@
+AU Optronics Corporation 13.3" WXGA (1366x768) TFT LCD panel
+
+Required properties:
+- compatible: should be "auo,b133xtn01"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/panel/edt,et057090dhu.txt b/Documentation/devicetree/bindings/panel/edt,et057090dhu.txt
new file mode 100644
index 00000000000..4903d7b1d94
--- /dev/null
+++ b/Documentation/devicetree/bindings/panel/edt,et057090dhu.txt
@@ -0,0 +1,7 @@
+Emerging Display Technology Corp. 5.7" VGA TFT LCD panel
+
+Required properties:
+- compatible: should be "edt,et057090dhu"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/panel/edt,et070080dh6.txt b/Documentation/devicetree/bindings/panel/edt,et070080dh6.txt
new file mode 100644
index 00000000000..20cb38e836e
--- /dev/null
+++ b/Documentation/devicetree/bindings/panel/edt,et070080dh6.txt
@@ -0,0 +1,10 @@
+Emerging Display Technology Corp. ET070080DH6 7.0" WVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "edt,et070080dh6"
+
+This panel is the same as ETM0700G0DH6 except for the touchscreen.
+ET070080DH6 is the model with resistive touch.
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/panel/edt,etm0700g0dh6.txt b/Documentation/devicetree/bindings/panel/edt,etm0700g0dh6.txt
new file mode 100644
index 00000000000..ee4b18053e4
--- /dev/null
+++ b/Documentation/devicetree/bindings/panel/edt,etm0700g0dh6.txt
@@ -0,0 +1,10 @@
+Emerging Display Technology Corp. ETM0700G0DH6 7.0" WVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "edt,etm0700g0dh6"
+
+This panel is the same as ET070080DH6 except for the touchscreen.
+ETM0700G0DH6 is the model with capacitive multitouch.
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/pci/designware-pcie.txt b/Documentation/devicetree/bindings/pci/designware-pcie.txt
index d6fae13ff06..d0d15ee4283 100644
--- a/Documentation/devicetree/bindings/pci/designware-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/designware-pcie.txt
@@ -1,15 +1,7 @@
 * Synopsys Designware PCIe interface
 
 Required properties:
-- compatible: should contain "snps,dw-pcie" to identify the
-	core, plus an identifier for the specific instance, such
-	as "samsung,exynos5440-pcie" or "fsl,imx6q-pcie".
-- reg: base addresses and lengths of the pcie controller,
-	the phy controller, additional register for the phy controller.
-- interrupts: interrupt values for level interrupt,
-	pulse interrupt, special interrupt.
-- clocks: from common clock binding: handle to pci clock.
-- clock-names: from common clock binding: should be "pcie" and "pcie_bus".
+- compatible: should contain "snps,dw-pcie" to identify the core.
 - #address-cells: set to <3>
 - #size-cells: set to <2>
 - device_type: set to "pci"
@@ -19,65 +11,11 @@ Required properties:
 	to define the mapping of the PCIe interface to interrupt
 	numbers.
 - num-lanes: number of lanes to use
+- clocks: Must contain an entry for each entry in clock-names.
+	See ../clocks/clock-bindings.txt for details.
+- clock-names: Must include the following entries:
+	- "pcie"
+	- "pcie_bus"
 
 Optional properties:
 - reset-gpio: gpio pin number of power good signal
-
-Optional properties for fsl,imx6q-pcie
-- power-on-gpio: gpio pin number of power-enable signal
-- wake-up-gpio: gpio pin number of incoming wakeup signal
-- disable-gpio: gpio pin number of outgoing rfkill/endpoint disable signal
-
-Example:
-
-SoC specific DT Entry:
-
-	pcie@290000 {
-		compatible = "samsung,exynos5440-pcie", "snps,dw-pcie";
-		reg = <0x290000 0x1000
-			0x270000 0x1000
-			0x271000 0x40>;
-		interrupts = <0 20 0>, <0 21 0>, <0 22 0>;
-		clocks = <&clock 28>, <&clock 27>;
-		clock-names = "pcie", "pcie_bus";
-		#address-cells = <3>;
-		#size-cells = <2>;
-		device_type = "pci";
-		ranges = <0x00000800 0 0x40000000 0x40000000 0 0x00001000   /* configuration space */
-			  0x81000000 0 0	  0x40001000 0 0x00010000   /* downstream I/O */
-			  0x82000000 0 0x40011000 0x40011000 0 0x1ffef000>; /* non-prefetchable memory */
-		#interrupt-cells = <1>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0x0 0 &gic 53>;
-		num-lanes = <4>;
-	};
-
-	pcie@2a0000 {
-		compatible = "samsung,exynos5440-pcie", "snps,dw-pcie";
-		reg = <0x2a0000 0x1000
-			0x272000 0x1000
-			0x271040 0x40>;
-		interrupts = <0 23 0>, <0 24 0>, <0 25 0>;
-		clocks = <&clock 29>, <&clock 27>;
-		clock-names = "pcie", "pcie_bus";
-		#address-cells = <3>;
-		#size-cells = <2>;
-		device_type = "pci";
-		ranges = <0x00000800 0 0x60000000 0x60000000 0 0x00001000   /* configuration space */
-			  0x81000000 0 0	  0x60001000 0 0x00010000   /* downstream I/O */
-			  0x82000000 0 0x60011000 0x60011000 0 0x1ffef000>; /* non-prefetchable memory */
-		#interrupt-cells = <1>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0x0 0 &gic 56>;
-		num-lanes = <4>;
-	};
-
-Board specific DT Entry:
-
-	pcie@290000 {
-		reset-gpio = <&pin_ctrl 5 0>;
-	};
-
-	pcie@2a0000 {
-		reset-gpio = <&pin_ctrl 22 0>;
-	};
diff --git a/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt
new file mode 100644
index 00000000000..9455fd0ec83
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt
@@ -0,0 +1,38 @@
+* Freescale i.MX6 PCIe interface
+
+This PCIe host controller is based on the Synopsis Designware PCIe IP
+and thus inherits all the common properties defined in designware-pcie.txt.
+
+Required properties:
+- compatible: "fsl,imx6q-pcie"
+- reg: base addresse and length of the pcie controller
+- interrupts: A list of interrupt outputs of the controller. Must contain an
+  entry for each entry in the interrupt-names property.
+- interrupt-names: Must include the following entries:
+	- "msi": The interrupt that is asserted when an MSI is received
+- clock-names: Must include the following additional entries:
+	- "pcie_phy"
+
+Example:
+
+	pcie@0x01000000 {
+		compatible = "fsl,imx6q-pcie", "snps,dw-pcie";
+		reg = <0x01ffc000 0x4000>;
+		#address-cells = <3>;
+		#size-cells = <2>;
+		device_type = "pci";
+		ranges = <0x00000800 0 0x01f00000 0x01f00000 0 0x00080000
+			  0x81000000 0 0          0x01f80000 0 0x00010000
+			  0x82000000 0 0x01000000 0x01000000 0 0x00f00000>;
+		num-lanes = <1>;
+		interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "msi";
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 0x7>;
+		interrupt-map = <0 0 0 1 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+		                <0 0 0 2 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+		                <0 0 0 3 &intc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+		                <0 0 0 4 &intc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&clks 144>, <&clks 206>, <&clks 189>;
+		clock-names = "pcie", "pcie_bus", "pcie_phy";
+	};
diff --git a/Documentation/devicetree/bindings/pci/samsung,exynos5440-pcie.txt b/Documentation/devicetree/bindings/pci/samsung,exynos5440-pcie.txt
new file mode 100644
index 00000000000..4f9d23d2ed6
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/samsung,exynos5440-pcie.txt
@@ -0,0 +1,65 @@
+* Samsung Exynos 5440 PCIe interface
+
+This PCIe host controller is based on the Synopsis Designware PCIe IP
+and thus inherits all the common properties defined in designware-pcie.txt.
+
+Required properties:
+- compatible: "samsung,exynos5440-pcie"
+- reg: base addresses and lengths of the pcie controller,
+	the phy controller, additional register for the phy controller.
+- interrupts: A list of interrupt outputs for level interrupt,
+	pulse interrupt, special interrupt.
+
+Example:
+
+SoC specific DT Entry:
+
+	pcie@290000 {
+		compatible = "samsung,exynos5440-pcie", "snps,dw-pcie";
+		reg = <0x290000 0x1000
+			0x270000 0x1000
+			0x271000 0x40>;
+		interrupts = <0 20 0>, <0 21 0>, <0 22 0>;
+		clocks = <&clock 28>, <&clock 27>;
+		clock-names = "pcie", "pcie_bus";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		device_type = "pci";
+		ranges = <0x00000800 0 0x40000000 0x40000000 0 0x00001000   /* configuration space */
+			  0x81000000 0 0	  0x40001000 0 0x00010000   /* downstream I/O */
+			  0x82000000 0 0x40011000 0x40011000 0 0x1ffef000>; /* non-prefetchable memory */
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 0>;
+		interrupt-map = <0 0 0 0 &gic GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
+		num-lanes = <4>;
+	};
+
+	pcie@2a0000 {
+		compatible = "samsung,exynos5440-pcie", "snps,dw-pcie";
+		reg = <0x2a0000 0x1000
+			0x272000 0x1000
+			0x271040 0x40>;
+		interrupts = <0 23 0>, <0 24 0>, <0 25 0>;
+		clocks = <&clock 29>, <&clock 27>;
+		clock-names = "pcie", "pcie_bus";
+		#address-cells = <3>;
+		#size-cells = <2>;
+		device_type = "pci";
+		ranges = <0x00000800 0 0x60000000 0x60000000 0 0x00001000   /* configuration space */
+			  0x81000000 0 0	  0x60001000 0 0x00010000   /* downstream I/O */
+			  0x82000000 0 0x60011000 0x60011000 0 0x1ffef000>; /* non-prefetchable memory */
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 0 0>;
+		interrupt-map = <0 0 0 0 &gic GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
+		num-lanes = <4>;
+	};
+
+Board specific DT Entry:
+
+	pcie@290000 {
+		reset-gpio = <&pin_ctrl 5 0>;
+	};
+
+	pcie@2a0000 {
+		reset-gpio = <&pin_ctrl 22 0>;
+	};
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt b/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt
new file mode 100644
index 00000000000..db939210e29
--- /dev/null
+++ b/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt
@@ -0,0 +1,54 @@
+
+IBM Akebono board device tree
+=============================
+
+The IBM Akebono board is a development board for the PPC476GTR SoC.
+
+0) The root node
+
+   Required properties:
+
+   - model : "ibm,akebono".
+   - compatible : "ibm,akebono" , "ibm,476gtr".
+
+1.a) The Secure Digital Host Controller Interface (SDHCI) node
+
+  Represent the Secure Digital Host Controller Interfaces.
+
+  Required properties:
+
+   - compatible : should be "ibm,476gtr-sdhci","generic-sdhci".
+   - reg : should contain the SDHCI registers location and length.
+   - interrupt-parent : a phandle for the interrupt controller.
+   - interrupts : should contain the SDHCI interrupt.
+
+1.b) The Advanced Host Controller Interface (AHCI) SATA node
+
+  Represents the advanced host controller SATA interface.
+
+  Required properties:
+
+   - compatible : should be "ibm,476gtr-ahci".
+   - reg : should contain the AHCI registers location and length.
+   - interrupt-parent : a phandle for the interrupt controller.
+   - interrupts : should contain the AHCI interrupt.
+
+1.c) The FPGA node
+
+  The Akebono board stores some board information such as the revision
+  number in an FPGA which is represented by this node.
+
+  Required properties:
+
+   - compatible : should be "ibm,akebono-fpga".
+   - reg : should contain the FPGA registers location and length.
+
+1.d) The AVR node
+
+  The Akebono board has an Atmel AVR microprocessor attached to the I2C
+  bus as a power controller for the board.
+
+  Required properties:
+
+   - compatible : should be "ibm,akebono-avr".
+   - reg : should contain the I2C bus address for the AVR.
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt b/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt
new file mode 100644
index 00000000000..c737c833870
--- /dev/null
+++ b/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt
@@ -0,0 +1,19 @@
+
+ppc476gtr High Speed Serial Assist (HSTA) node
+==============================================
+
+The 476gtr SoC contains a high speed serial assist module attached
+between the plb4 and plb6 system buses to provide high speed data
+transfer between memory and system peripherals as well as support for
+PCI message signalled interrupts.
+
+Currently only the MSI support is used by Linux using the following
+device tree entries:
+
+Require properties:
+- compatible		: "ibm,476gtr-hsta-msi", "ibm,hsta-msi"
+- reg			: register mapping for the HSTA MSI space
+- interrupt-parent	: parent controller for mapping interrupts
+- interrupts		: ordered interrupt mapping for each MSI in the register
+			  space. The first interrupt should be associated with a
+			  register offset of 0x00, the second to 0x10, etc.
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/board.txt b/Documentation/devicetree/bindings/powerpc/fsl/board.txt
index 380914e965e..700dec4774f 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/board.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/board.txt
@@ -67,3 +67,20 @@ Example:
 			gpio-controller;
 		};
 	};
+
+* Freescale on-board FPGA connected on I2C bus
+
+Some Freescale boards like BSC9132QDS have on board FPGA connected on
+the i2c bus.
+
+Required properties:
+- compatible: Should be a board-specific string followed by a string
+  indicating the type of FPGA.  Example:
+	"fsl,<board>-fpga", "fsl,fpga-qixis-i2c"
+- reg: Should contain the address of the FPGA
+
+Example:
+	fpga: fpga@66 {
+		compatible = "fsl,bsc9132qds-fpga", "fsl,fpga-qixis-i2c";
+		reg = <0x66>;
+	};
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/ccf.txt b/Documentation/devicetree/bindings/powerpc/fsl/ccf.txt
new file mode 100644
index 00000000000..454da7e08ac
--- /dev/null
+++ b/Documentation/devicetree/bindings/powerpc/fsl/ccf.txt
@@ -0,0 +1,46 @@
+Freescale CoreNet Coherency Fabric(CCF) Device Tree Binding
+
+DESCRIPTION
+
+The CoreNet coherency fabric is a fabric-oriented, connectivity infrastructure
+that enables the implementation of coherent, multicore systems.
+
+Required properties:
+
+- compatible: <string list>
+		fsl,corenet1-cf - CoreNet coherency fabric version 1.
+		Example chips: T4240, B4860
+
+		fsl,corenet2-cf - CoreNet coherency fabric version 2.
+		Example chips: P5040, P5020, P4080, P3041, P2041
+
+		fsl,corenet-cf - Used to represent the common registers
+		between CCF version 1 and CCF version 2.  This compatible
+		is retained for compatibility reasons, as it was already
+		used for both CCF version 1 chips and CCF version 2
+		chips.  It should be specified after either
+		"fsl,corenet1-cf" or "fsl,corenet2-cf".
+
+- reg: <prop-encoded-array>
+		A standard property. Represents the CCF registers.
+
+- interrupts: <prop-encoded-array>
+		Interrupt mapping for CCF error interrupt.
+
+- fsl,ccf-num-csdids: <u32>
+		Specifies the number of Coherency Subdomain ID Port Mapping
+		Registers that are supported by the CCF.
+
+- fsl,ccf-num-snoopids: <u32>
+		Specifies the number of Snoop ID Port Mapping Registers that
+		are supported by CCF.
+
+Example:
+
+	corenet-cf@18000 {
+		compatible = "fsl,corenet2-cf", "fsl,corenet-cf";
+		reg = <0x18000 0x1000>;
+		interrupts = <16 2 1 31>;
+		fsl,ccf-num-csdids = <32>;
+		fsl,ccf-num-snoopids = <32>;
+	};
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/cpus.txt b/Documentation/devicetree/bindings/powerpc/fsl/cpus.txt
index 922c30ad90d..f8cd2397aa0 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/cpus.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/cpus.txt
@@ -20,3 +20,14 @@ PROPERTIES
 	a property named fsl,eref-[CAT], where [CAT] is the abbreviated category
 	name with all uppercase letters converted to lowercase, indicates that
 	the category is supported by the implementation.
+
+    - fsl,portid-mapping
+	Usage: optional
+	Value type: <u32>
+	Definition: The Coherency Subdomain ID Port Mapping Registers and
+	Snoop ID Port Mapping registers, which are part of the CoreNet
+	Coherency fabric (CCF), provide a CoreNet Coherency Subdomain
+	ID/CoreNet Snoop ID to cpu mapping functions.  Certain bits from
+	these registers should be set if the coresponding CPU should be
+	snooped.  This property defines a bitmask which selects the bit
+	that should be set if this cpu should be snooped.
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt b/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt
index 1f5e329f756..c2b2899885f 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt
@@ -34,6 +34,15 @@ Optional properties:
 		  for legacy drivers.
 - interrupt-parent : <phandle>
 		  Phandle to interrupt controller
+- fsl,portid-mapping : <u32>
+		  The Coherency Subdomain ID Port Mapping Registers and
+		  Snoop ID Port Mapping registers, which are part of the
+		  CoreNet Coherency fabric (CCF), provide a CoreNet
+		  Coherency Subdomain ID/CoreNet Snoop ID to pamu mapping
+		  functions.  Certain bits from these registers should be
+		  set if PAMUs should be snooped.  This property defines
+		  a bitmask which selects the bits that should be set if
+		  PAMUs should be snooped.
 
 Child nodes:
 
@@ -88,6 +97,7 @@ Example:
 		compatible = "fsl,pamu-v1.0", "fsl,pamu";
 		reg = <0x20000 0x5000>;
 		ranges = <0 0x20000 0x5000>;
+		fsl,portid-mapping = <0xf80000>;
 		#address-cells = <1>;
 		#size-cells = <1>;
 		interrupts = <
diff --git a/Documentation/devicetree/bindings/pwm/bcm-kona-pwm.txt b/Documentation/devicetree/bindings/pwm/bcm-kona-pwm.txt
new file mode 100644
index 00000000000..8eae9fe7841
--- /dev/null
+++ b/Documentation/devicetree/bindings/pwm/bcm-kona-pwm.txt
@@ -0,0 +1,21 @@
+Broadcom Kona PWM controller device tree bindings
+
+This controller has 6 channels.
+
+Required Properties :
+- compatible: should contain "brcm,kona-pwm"
+- reg: physical base address and length of the controller's registers
+- clocks: phandle + clock specifier pair for the external clock
+- #pwm-cells: Should be 3. See pwm.txt in this directory for a
+  description of the cells format.
+
+Refer to clocks/clock-bindings.txt for generic clock consumer properties.
+
+Example:
+
+pwm: pwm@3e01a000 {
+	compatible = "brcm,bcm11351-pwm", "brcm,kona-pwm";
+	reg = <0x3e01a000 0xc4>;
+	clocks = <&pwm_clk>;
+	#pwm-cells = <3>;
+};
diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
index 64fd7dec1bb..b3556609a06 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -4,6 +4,13 @@ Required properties:
 
   - compatible: Must contain one of the following:
 
+    - "renesas,scifa-sh73a0" for SH73A0 (SH-Mobile AG5) SCIFA compatible UART.
+    - "renesas,scifb-sh73a0" for SH73A0 (SH-Mobile AG5) SCIFB compatible UART.
+    - "renesas,scifa-r8a73a4" for R8A73A4 (R-Mobile APE6) SCIFA compatible UART.
+    - "renesas,scifb-r8a73a4" for R8A73A4 (R-Mobile APE6) SCIFB compatible UART.
+    - "renesas,scifa-r8a7740" for R8A7740 (R-Mobile A1) SCIFA compatible UART.
+    - "renesas,scifb-r8a7740" for R8A7740 (R-Mobile A1) SCIFB compatible UART.
+    - "renesas,scif-r8a7778" for R8A7778 (R-Car M1) SCIF compatible UART.
     - "renesas,scif-r8a7779" for R8A7779 (R-Car H1) SCIF compatible UART.
     - "renesas,scif-r8a7790" for R8A7790 (R-Car H2) SCIF compatible UART.
     - "renesas,scifa-r8a7790" for R8A7790 (R-Car H2) SCIFA compatible UART.
diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-qup.txt b/Documentation/devicetree/bindings/spi/qcom,spi-qup.txt
index b82a268f1bd..bee6ff204ba 100644
--- a/Documentation/devicetree/bindings/spi/qcom,spi-qup.txt
+++ b/Documentation/devicetree/bindings/spi/qcom,spi-qup.txt
@@ -23,6 +23,12 @@ Optional properties:
 - spi-max-frequency: Specifies maximum SPI clock frequency,
                      Units - Hz. Definition as per
                      Documentation/devicetree/bindings/spi/spi-bus.txt
+- num-cs:	total number of chipselects
+- cs-gpios:	should specify GPIOs used for chipselects.
+		The gpios will be referred to as reg = <index> in the SPI child
+		nodes.  If unspecified, a single SPI device without a chip
+		select can be used.
+
 
 SPI slave nodes must be children of the SPI master node and can contain
 properties described in Documentation/devicetree/bindings/spi/spi-bus.txt
diff --git a/Documentation/devicetree/bindings/thermal/armada-thermal.txt b/Documentation/devicetree/bindings/thermal/armada-thermal.txt
index fff93d5f92d..4cf024929a3 100644
--- a/Documentation/devicetree/bindings/thermal/armada-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/armada-thermal.txt
@@ -1,11 +1,21 @@
-* Marvell Armada 370/XP thermal management
+* Marvell Armada 370/375/380/XP thermal management
 
 Required properties:
 
 - compatible:	Should be set to one of the following:
 		marvell,armada370-thermal
+		marvell,armada375-thermal
+		marvell,armada375-z1-thermal
+		marvell,armada380-thermal
 		marvell,armadaxp-thermal
 
+		Note: As the name suggests, "marvell,armada375-z1-thermal"
+		applies for the SoC Z1 stepping only. On such stepping
+		some quirks need to be done and the register offset differs
+		from the one in the A0 stepping.
+		The operating system may auto-detect the SoC stepping and
+		update the compatible and register offsets at runtime.
+
 - reg:		Device's register space.
 		Two entries are expected, see the examples below.
 		The first one is required for the sensor register;
diff --git a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
index 284f5300fd8..c94909215c0 100644
--- a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
@@ -6,16 +6,35 @@
 	       "samsung,exynos4412-tmu"
 	       "samsung,exynos4210-tmu"
 	       "samsung,exynos5250-tmu"
+	       "samsung,exynos5260-tmu"
+	       "samsung,exynos5420-tmu" for TMU channel 0, 1 on Exynos5420
+	       "samsung,exynos5420-tmu-ext-triminfo" for TMU channels 2, 3 and 4
+			Exynos5420 (Must pass triminfo base and triminfo clock)
 	       "samsung,exynos5440-tmu"
 - interrupt-parent : The phandle for the interrupt controller
 - reg : Address range of the thermal registers. For soc's which has multiple
 	instances of TMU and some registers are shared across all TMU's like
 	interrupt related then 2 set of register has to supplied. First set
-	belongs	to each instance of TMU and second set belongs to common TMU
-	registers.
+	belongs	to register set of TMU instance and second set belongs to
+	registers shared with the TMU instance.
+
+  NOTE: On Exynos5420, the TRIMINFO register is misplaced for TMU
+	channels 2, 3 and 4
+	Use "samsung,exynos5420-tmu-ext-triminfo" in cases, there is a misplaced
+	register, also provide clock to access that base.
+
+	TRIMINFO at 0x1006c000 contains data for TMU channel 3
+	TRIMINFO at 0x100a0000 contains data for TMU channel 4
+	TRIMINFO at 0x10068000 contains data for TMU channel 2
+
 - interrupts : Should contain interrupt for thermal system
-- clocks : The main clock for TMU device
+- clocks : The main clocks for TMU device
+	-- 1. operational clock for TMU channel
+	-- 2. optional clock to access the shared registers of TMU channel
 - clock-names : Thermal system clock name
+	-- "tmu_apbif" operational clock for current TMU channel
+	-- "tmu_triminfo_apbif" clock to access the shared triminfo register
+		for current TMU channel
 - vtmu-supply: This entry is optional and provides the regulator node supplying
 		voltage to TMU. If needed this entry can be placed inside
 		board/platform specific dts file.
@@ -43,6 +62,31 @@ Example 2):
 		clock-names = "tmu_apbif";
 	};
 
+Example 3): (In case of Exynos5420 "with misplaced TRIMINFO register")
+	tmu_cpu2: tmu@10068000 {
+		compatible = "samsung,exynos5420-tmu-ext-triminfo";
+		reg = <0x10068000 0x100>, <0x1006c000 0x4>;
+		interrupts = <0 184 0>;
+		clocks = <&clock 318>, <&clock 318>;
+		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
+	};
+
+	tmu_cpu3: tmu@1006c000 {
+		compatible = "samsung,exynos5420-tmu-ext-triminfo";
+		reg = <0x1006c000 0x100>, <0x100a0000 0x4>;
+		interrupts = <0 185 0>;
+		clocks = <&clock 318>, <&clock 319>;
+		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
+	};
+
+	tmu_gpu: tmu@100a0000 {
+		compatible = "samsung,exynos5420-tmu-ext-triminfo";
+		reg = <0x100a0000 0x100>, <0x10068000 0x4>;
+		interrupts = <0 215 0>;
+		clocks = <&clock 319>, <&clock 318>;
+		clock-names = "tmu_apbif", "tmu_triminfo_apbif";
+	};
+
 Note: For multi-instance tmu each instance should have an alias correctly
 numbered in "aliases" node.
 
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 5261271046c..46a311e728a 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -83,6 +83,7 @@ mosaixtech	Mosaix Technologies, Inc.
 moxa	Moxa
 mpl	MPL AG
 mundoreader	Mundo Reader S.L.
+murata	Murata Manufacturing Co., Ltd.
 mxicy	Macronix International Co., Ltd.
 national	National Semiconductor
 neonode		Neonode Inc.
@@ -142,3 +143,4 @@ wm	Wondermedia Technologies, Inc.
 xes	Extreme Engineering Solutions (X-ES)
 xlnx	Xilinx
 zyxel	ZyXEL Communications Corp.
+zarlink	Zarlink Semiconductor
diff --git a/Documentation/devicetree/bindings/video/exynos_dp.txt b/Documentation/devicetree/bindings/video/exynos_dp.txt
index 57ccdde02c3..53dbccfa80c 100644
--- a/Documentation/devicetree/bindings/video/exynos_dp.txt
+++ b/Documentation/devicetree/bindings/video/exynos_dp.txt
@@ -62,6 +62,10 @@ Optional properties for dp-controller:
 	-hsync-active-high:
 		HSYNC polarity configuration.
 			High if defined, Low if not defined
+	-samsung,hpd-gpio:
+		Hotplug detect GPIO.
+			Indicates which GPIO should be used for hotplug
+			detection
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/video/exynos_hdmi.txt b/Documentation/devicetree/bindings/video/exynos_hdmi.txt
index f9187a25925..1fd8cf9cbfa 100644
--- a/Documentation/devicetree/bindings/video/exynos_hdmi.txt
+++ b/Documentation/devicetree/bindings/video/exynos_hdmi.txt
@@ -5,6 +5,7 @@ Required properties:
 	1) "samsung,exynos5-hdmi" <DEPRECATED>
 	2) "samsung,exynos4210-hdmi"
 	3) "samsung,exynos4212-hdmi"
+	4) "samsung,exynos5420-hdmi"
 - reg: physical base address of the hdmi and length of memory mapped
 	region.
 - interrupts: interrupt number to the cpu.
@@ -27,6 +28,7 @@ Required properties:
 	"hdmi", "sclk_hdmi", "sclk_pixel", "sclk_hdmiphy" and "mout_hdmi".
 - ddc: phandle to the hdmi ddc node
 - phy: phandle to the hdmi phy node
+- samsung,syscon-phandle: phandle for system controller node for PMU.
 
 Example:
 
@@ -37,4 +39,5 @@ Example:
 		hpd-gpio = <&gpx3 7 1>;
 		ddc = <&hdmi_ddc_node>;
 		phy = <&hdmi_phy_node>;
+		samsung,syscon-phandle = <&pmu_system_controller>;
 	};
diff --git a/Documentation/devicetree/bindings/watchdog/marvel.txt b/Documentation/devicetree/bindings/watchdog/marvel.txt
index de11eb4c121..97223fddb7b 100644
--- a/Documentation/devicetree/bindings/watchdog/marvel.txt
+++ b/Documentation/devicetree/bindings/watchdog/marvel.txt
@@ -5,11 +5,18 @@ Required Properties:
 - Compatibility : "marvell,orion-wdt"
 		  "marvell,armada-370-wdt"
 		  "marvell,armada-xp-wdt"
+		  "marvell,armada-375-wdt"
+		  "marvell,armada-380-wdt"
 
 - reg		: Should contain two entries: first one with the
 		  timer control address, second one with the
 		  rstout enable address.
 
+For "marvell,armada-375-wdt" and "marvell,armada-380-wdt":
+
+- reg		: A third entry is mandatory and should contain the
+                  shared mask/unmask RSTOUT address.
+
 Optional properties:
 
 - interrupts	: Contains the IRQ for watchdog expiration
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index 89472558011..1525e30483f 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -318,3 +318,8 @@ GPIO
   devm_gpiod_get_optional()
   devm_gpiod_get_index_optional()
   devm_gpiod_put()
+
+MDIO
+  devm_mdiobus_alloc()
+  devm_mdiobus_alloc_size()
+  devm_mdiobus_free()
diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt
index 4e30ebaa9e5..9af538be375 100644
--- a/Documentation/email-clients.txt
+++ b/Documentation/email-clients.txt
@@ -1,6 +1,17 @@
 Email clients info for Linux
 ======================================================================
 
+Git
+----------------------------------------------------------------------
+These days most developers use `git send-email` instead of regular
+email clients.  The man page for this is quite good.  On the receiving
+end, maintainers use `git am` to apply the patches.
+
+If you are new to git then send your first patch to yourself.  Save it
+as raw text including all the headers.  Run `git am raw_email.txt` and
+then review the changelog with `git log`.  When that works then send
+the patch to the appropriate mailing list(s).
+
 General Preferences
 ----------------------------------------------------------------------
 Patches for the Linux kernel are submitted via email, preferably as
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index eba79013425..b18dd177902 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -196,8 +196,7 @@ prototypes:
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
-	int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs);
+	int (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
 	int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **,
 				unsigned long *);
 	int (*migratepage)(struct address_space *, struct page *, struct page *);
@@ -431,6 +430,8 @@ prototypes:
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
+	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
+	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
diff --git a/Documentation/filesystems/caching/operations.txt b/Documentation/filesystems/caching/operations.txt
index bee2a5f93d6..a1c052cbba3 100644
--- a/Documentation/filesystems/caching/operations.txt
+++ b/Documentation/filesystems/caching/operations.txt
@@ -90,7 +90,7 @@ operations:
      to be cleared before proceeding:
 
 		wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
-			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			    TASK_UNINTERRUPTIBLE);
 
 
  (2) The operation may be fast asynchronous (FSCACHE_OP_FAST), in which case it
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index 25311e113e7..51afba17bba 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -461,11 +461,11 @@ The number of blocks and buckets are determined by,
   # of blocks in level #n = |
                             `- 4, Otherwise
 
-                             ,- 2^ (n + dir_level),
-			     |            if n < MAX_DIR_HASH_DEPTH / 2,
+                             ,- 2^(n + dir_level),
+			     |        if n + dir_level < MAX_DIR_HASH_DEPTH / 2,
   # of buckets in level #n = |
-                             `- 2^((MAX_DIR_HASH_DEPTH / 2 + dir_level) - 1),
-			                  Otherwise
+                             `- 2^((MAX_DIR_HASH_DEPTH / 2) - 1),
+			              Otherwise
 
 When F2FS finds a file name in a directory, at first a hash value of the file
 name is calculated. Then, F2FS scans the hash table in level #0 to find the
diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index b930ad08778..c49cd7e796e 100644
--- a/Documentation/filesystems/nfs/nfs41-server.txt
+++ b/Documentation/filesystems/nfs/nfs41-server.txt
@@ -176,7 +176,5 @@ Nonstandard compound limitations:
   ca_maxrequestsize request and a ca_maxresponsesize reply, so we may
   fail to live up to the promise we made in CREATE_SESSION fore channel
   negotiation.
-* No more than one read-like operation allowed per compound; encoding
-  replies that cross page boundaries (except for read data) not handled.
 
 See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 617f6d70c07..a1d0d7a3016 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -589,8 +589,7 @@ struct address_space_operations {
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
-	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs);
+	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
 	struct page* (*get_xip_page)(struct address_space *, sector_t,
 			int);
 	/* migrate the contents of a page to the specified target */
@@ -807,6 +806,8 @@ struct file_operations {
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
+	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
+	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
@@ -837,11 +838,15 @@ otherwise noted.
 
   read: called by read(2) and related system calls
 
-  aio_read: called by io_submit(2) and other asynchronous I/O operations
+  aio_read: vectored, possibly asynchronous read
+
+  read_iter: possibly asynchronous read with iov_iter as destination
 
   write: called by write(2) and related system calls
 
-  aio_write: called by io_submit(2) and other asynchronous I/O operations
+  aio_write: vectored, possibly asynchronous write
+
+  write_iter: possibly asynchronous write with iov_iter as source
 
   iterate: called when the VFS needs to read the directory contents
 
diff --git a/Documentation/hwmon/ntc_thermistor b/Documentation/hwmon/ntc_thermistor
index 3bfda94096f..057b77029f2 100644
--- a/Documentation/hwmon/ntc_thermistor
+++ b/Documentation/hwmon/ntc_thermistor
@@ -1,7 +1,7 @@
 Kernel driver ntc_thermistor
 =================
 
-Supported thermistors:
+Supported thermistors from Murata:
 * Murata NTC Thermistors NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, NCP15WL333
   Prefixes: 'ncp15wb473', 'ncp18wb473', 'ncp21wb473', 'ncp03wb473', 'ncp15wl333'
   Datasheet: Publicly available at Murata
@@ -15,9 +15,9 @@ Authors:
 Description
 -----------
 
-The NTC thermistor is a simple thermistor that requires users to provide the
-resistance and lookup the corresponding compensation table to get the
-temperature input.
+The NTC (Negative Temperature Coefficient) thermistor is a simple thermistor
+that requires users to provide the resistance and lookup the corresponding
+compensation table to get the temperature input.
 
 The NTC driver provides lookup tables with a linear approximation function
 and four circuit models with an option not to use any of the four models.
diff --git a/Documentation/hwmon/shtc1 b/Documentation/hwmon/shtc1
new file mode 100644
index 00000000000..6b1e05458f0
--- /dev/null
+++ b/Documentation/hwmon/shtc1
@@ -0,0 +1,43 @@
+Kernel driver shtc1
+===================
+
+Supported chips:
+  * Sensirion SHTC1
+    Prefix: 'shtc1'
+    Addresses scanned: none
+    Datasheet: http://www.sensirion.com/file/datasheet_shtc1
+
+  * Sensirion SHTW1
+    Prefix: 'shtw1'
+    Addresses scanned: none
+    Datasheet: Not publicly available
+
+Author:
+  Johannes Winkelmann <johannes.winkelmann@sensirion.com>
+
+Description
+-----------
+
+This driver implements support for the Sensirion SHTC1 chip, a humidity and
+temperature sensor. Temperature is measured in degrees celsius, relative
+humidity is expressed as a percentage. Driver can be used as well for SHTW1
+chip, which has the same electrical interface.
+
+The device communicates with the I2C protocol. All sensors are set to I2C
+address 0x70. See Documentation/i2c/instantiating-devices for methods to
+instantiate the device.
+
+There are two options configurable by means of shtc1_platform_data:
+1. blocking (pull the I2C clock line down while performing the measurement) or
+   non-blocking mode. Blocking mode will guarantee the fastest result but
+   the I2C bus will be busy during that time. By default, non-blocking mode
+   is used. Make sure clock-stretching works properly on your device if you
+   want to use blocking mode.
+2. high or low accuracy. High accuracy is used by default and using it is
+   strongly recommended.
+
+sysfs-Interface
+---------------
+
+temp1_input - temperature input
+humidity1_input - humidity input
diff --git a/Documentation/input/event-codes.txt b/Documentation/input/event-codes.txt
index f1ea2c69648..c587a966413 100644
--- a/Documentation/input/event-codes.txt
+++ b/Documentation/input/event-codes.txt
@@ -281,6 +281,19 @@ gestures can normally be extracted from it.
 If INPUT_PROP_SEMI_MT is not set, the device is assumed to be a true MT
 device.
 
+INPUT_PROP_TOPBUTTONPAD:
+-----------------------
+Some laptops, most notably the Lenovo *40 series provide a trackstick
+device but do not have physical buttons associated with the trackstick
+device. Instead, the top area of the touchpad is marked to show
+visual/haptic areas for left, middle, right buttons intended to be used
+with the trackstick.
+
+If INPUT_PROP_TOPBUTTONPAD is set, userspace should emulate buttons
+accordingly. This property does not affect kernel behavior.
+The kernel does not provide button emulation for such devices but treats
+them as any other INPUT_PROP_BUTTONPAD device.
+
 Guidelines:
 ==========
 The guidelines below ensure proper single-touch and multi-finger functionality.
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index d7e43fa8857..7e240a7c9ab 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -197,6 +197,7 @@ Code  Seq#(hex)	Include File		Comments
 					<mailto:gregkh@linuxfoundation.org>
 'a'	all	linux/atm*.h, linux/sonet.h	ATM on linux
 					<http://lrcwww.epfl.ch/>
+'a'	00-0F	drivers/crypto/qat/qat_common/adf_cfg_common.h	conflict! qat driver
 'b'	00-FF				conflict! bit3 vme host bridge
 					<mailto:natalia@nikhefk.nikhef.nl>
 'c'	all	linux/cm4000_cs.h	conflict!
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index d567a7cc552..c600e2f44a6 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -1171,7 +1171,7 @@ When kbuild executes, the following steps are followed (roughly):
 	      obvious reason.
 
     dtc
-	Create flattend device tree blob object suitable for linking
+	Create flattened device tree blob object suitable for linking
 	into vmlinux. Device tree blobs linked into vmlinux are placed
 	in an init section in the image. Platform code *must* copy the
 	blob to non-init memory prior to calling unflatten_device_tree().
diff --git a/Documentation/kbuild/modules.txt b/Documentation/kbuild/modules.txt
index 69372fb98cf..3fb39e0116b 100644
--- a/Documentation/kbuild/modules.txt
+++ b/Documentation/kbuild/modules.txt
@@ -470,7 +470,7 @@ build.
 
 	Sometimes, an external module uses exported symbols from
 	another external module. kbuild needs to have full knowledge of
-	all symbols to avoid spliitting out warnings about undefined
+	all symbols to avoid spitting out warnings about undefined
 	symbols. Three solutions exist for this situation.
 
 	NOTE: The method with a top-level kbuild file is recommended
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b9f67781c57..90f6139608f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1,27 +1,37 @@
                           Kernel Parameters
                           ~~~~~~~~~~~~~~~~~
 
-The following is a consolidated list of the kernel parameters as implemented
-(mostly) by the __setup() macro and sorted into English Dictionary order
-(defined as ignoring all punctuation and sorting digits before letters in a
-case insensitive manner), and with descriptions where known.
-
-Module parameters for loadable modules are specified only as the
-parameter name with optional '=' and value as appropriate, such as:
-
-	modprobe usbcore blinkenlights=1
-
-Module parameters for modules that are built into the kernel image
-are specified on the kernel command line with the module name plus
-'.' plus parameter name, with '=' and value if appropriate, such as:
-
-	usbcore.blinkenlights=1
+The following is a consolidated list of the kernel parameters as
+implemented by the __setup(), core_param() and module_param() macros
+and sorted into English Dictionary order (defined as ignoring all
+punctuation and sorting digits before letters in a case insensitive
+manner), and with descriptions where known.
+
+The kernel parses parameters from the kernel command line up to "--";
+if it doesn't recognize a parameter and it doesn't contain a '.', the
+parameter gets passed to init: parameters with '=' go into init's
+environment, others are passed as command line arguments to init.
+Everything after "--" is passed as an argument to init.
+
+Module parameters can be specified in two ways: via the kernel command
+line with a module name prefix, or via modprobe, e.g.:
+
+	(kernel command line) usbcore.blinkenlights=1
+	(modprobe command line) modprobe usbcore blinkenlights=1
+
+Parameters for modules which are built into the kernel need to be
+specified on the kernel command line.  modprobe looks through the
+kernel command line (/proc/cmdline) and collects module parameters
+when it loads a module, so the kernel command line can be used for
+loadable modules too.
 
 Hyphens (dashes) and underscores are equivalent in parameter names, so
 	log_buf_len=1M print-fatal-signals=1
 can also be entered as
 	log-buf-len=1M print_fatal_signals=1
 
+Double-quotes can be used to protect spaces in values, e.g.:
+	param="spaces in here"
 
 This document may not be entirely up to date and comprehensive. The command
 "modinfo -p ${modulename}" shows a current list of all parameters of a loadable
@@ -1087,6 +1097,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			that can be changed at run time by the
 			set_graph_function file in the debugfs tracing directory.
 
+	ftrace_graph_notrace=[function-list]
+			[FTRACE] Do not trace from the functions specified in
+			function-list.  This list is a comma separated list of
+			functions that can be changed at run time by the
+			set_graph_notrace file in the debugfs tracing directory.
+
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
 			support via parallel port (up to 5 devices per port)
@@ -1464,6 +1480,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	js=		[HW,JOY] Analog joystick
 			See Documentation/input/joystick.txt.
 
+	kaslr/nokaslr	[X86]
+			Enable/disable kernel and module base offset ASLR
+			(Address Space Layout Randomization) if built into
+			the kernel. When CONFIG_HIBERNATION is selected,
+			kASLR is disabled by default. When kASLR is enabled,
+			hibernation will be disabled.
+
 	keepinitrd	[HW,ARM]
 
 	kernelcore=nn[KMG]	[KNL,X86,IA-64,PPC] This parameter
@@ -2100,10 +2123,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
-	nokaslr		[X86]
-			Disable kernel and module base offset ASLR (Address
-			Space Layout Randomization) if built into the kernel.
-
 	noautogroup	Disable scheduler automatic task group creation.
 
 	nobats		[PPC] Do not use BATs for mapping kernel lowmem
@@ -2174,6 +2193,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			in certain environments such as networked servers or
 			real-time systems.
 
+	nohibernate	[HIBERNATION] Disable hibernation and resume.
+
 	nohz=		[KNL] Boottime enable/disable dynamic ticks
 			Valid arguments: on, off
 			Default: on
@@ -2775,6 +2796,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			leaf rcu_node structure.  Useful for very large
 			systems.
 
+	rcutree.jiffies_till_sched_qs= [KNL]
+			Set required age in jiffies for a
+			given grace period before RCU starts
+			soliciting quiescent-state help from
+			rcu_note_context_switch().
+
 	rcutree.jiffies_till_first_fqs= [KNL]
 			Set delay from grace-period initialization to
 			first attempt to force quiescent states.
@@ -2786,6 +2813,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			quiescent states.  Units are jiffies, minimum
 			value is one, and maximum value is HZ.
 
+	rcutree.rcu_nocb_leader_stride= [KNL]
+			Set the number of NOCB kthread groups, which
+			defaults to the square root of the number of
+			CPUs.  Larger numbers reduces the wakeup overhead
+			on the per-CPU grace-period kthreads, but increases
+			that same overhead on each group's leader.
+
 	rcutree.qhimark= [KNL]
 			Set threshold of queued RCU callbacks beyond which
 			batch limiting is disabled.
@@ -2970,6 +3004,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 		noresume	Don't check if there's a hibernation image
 				present during boot.
 		nocompress	Don't compress/decompress hibernation images.
+		no		Disable hibernation and resume.
 
 	retain_initrd	[RAM] Keep initrd memory after extraction
 
@@ -3114,6 +3149,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			[KNL] Should the soft-lockup detector generate panics.
 			Format: <integer>
 
+	softlockup_all_cpu_backtrace=
+			[KNL] Should the soft-lockup detector generate
+			backtraces on all cpus.
+			Format: <integer>
+
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/laptops/sonypi.txt
 
@@ -3505,7 +3545,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			the allocated input device; If set to 0, video driver
 			will only send out the event without touching backlight
 			brightness level.
-			default: 0
+			default: 1
 
 	virtio_mmio.device=
 			[VMMIO] Memory mapped virtio (platform) device.
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 0cfb00fd86f..4bbeca8483e 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -22,8 +22,9 @@ Appendix B: The kprobes sysctl interface
 
 Kprobes enables you to dynamically break into any kernel routine and
 collect debugging and performance information non-disruptively. You
-can trap at almost any kernel code address, specifying a handler
+can trap at almost any kernel code address(*), specifying a handler
 routine to be invoked when the breakpoint is hit.
+(*: some parts of the kernel code can not be trapped, see 1.5 Blacklist)
 
 There are currently three types of probes: kprobes, jprobes, and
 kretprobes (also called return probes).  A kprobe can be inserted
@@ -273,6 +274,19 @@ using one of the following techniques:
  or
 - Execute 'sysctl -w debug.kprobes_optimization=n'
 
+1.5 Blacklist
+
+Kprobes can probe most of the kernel except itself. This means
+that there are some functions where kprobes cannot probe. Probing
+(trapping) such functions can cause a recursive trap (e.g. double
+fault) or the nested probe handler may never be called.
+Kprobes manages such functions as a blacklist.
+If you want to add a function into the blacklist, you just need
+to (1) include linux/kprobes.h and (2) use NOKPROBE_SYMBOL() macro
+to specify a blacklisted function.
+Kprobes checks the given probe address against the blacklist and
+rejects registering it, if the given address is in the blacklist.
+
 2. Architectures Supported
 
 Kprobes, jprobes, and return probes are implemented on the following
diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX
index d13b9a9a9e0..d399ae1fc72 100644
--- a/Documentation/laptops/00-INDEX
+++ b/Documentation/laptops/00-INDEX
@@ -8,8 +8,8 @@ disk-shock-protection.txt
 	- information on hard disk shock protection.
 dslm.c
 	- Simple Disk Sleep Monitor program
-hpfall.c
-	- (HP) laptop accelerometer program for disk protection.
+freefall.c
+	- (HP/DELL) laptop accelerometer program for disk protection.
 laptop-mode.txt
 	- how to conserve battery power using laptop-mode.
 sony-laptop.txt
diff --git a/Documentation/laptops/hpfall.c b/Documentation/laptops/freefall.c
index b85dbbac049..aab2ff09e86 100644
--- a/Documentation/laptops/hpfall.c
+++ b/Documentation/laptops/freefall.c
@@ -1,7 +1,9 @@
-/* Disk protection for HP machines.
+/* Disk protection for HP/DELL machines.
  *
  * Copyright 2008 Eric Piel
  * Copyright 2009 Pavel Machek <pavel@ucw.cz>
+ * Copyright 2012 Sonal Santan
+ * Copyright 2014 Pali Rohár <pali.rohar@gmail.com>
  *
  * GPLv2.
  */
@@ -18,24 +20,31 @@
 #include <signal.h>
 #include <sys/mman.h>
 #include <sched.h>
+#include <syslog.h>
 
-char unload_heads_path[64];
+static int noled;
+static char unload_heads_path[64];
+static char device_path[32];
+static const char app_name[] = "FREE FALL";
 
-int set_unload_heads_path(char *device)
+static int set_unload_heads_path(char *device)
 {
 	char devname[64];
 
 	if (strlen(device) <= 5 || strncmp(device, "/dev/", 5) != 0)
 		return -EINVAL;
-	strncpy(devname, device + 5, sizeof(devname));
+	strncpy(devname, device + 5, sizeof(devname) - 1);
+	strncpy(device_path, device, sizeof(device_path) - 1);
 
 	snprintf(unload_heads_path, sizeof(unload_heads_path) - 1,
 				"/sys/block/%s/device/unload_heads", devname);
 	return 0;
 }
-int valid_disk(void)
+
+static int valid_disk(void)
 {
 	int fd = open(unload_heads_path, O_RDONLY);
+
 	if (fd < 0) {
 		perror(unload_heads_path);
 		return 0;
@@ -45,43 +54,54 @@ int valid_disk(void)
 	return 1;
 }
 
-void write_int(char *path, int i)
+static void write_int(char *path, int i)
 {
 	char buf[1024];
 	int fd = open(path, O_RDWR);
+
 	if (fd < 0) {
 		perror("open");
 		exit(1);
 	}
+
 	sprintf(buf, "%d", i);
+
 	if (write(fd, buf, strlen(buf)) != strlen(buf)) {
 		perror("write");
 		exit(1);
 	}
+
 	close(fd);
 }
 
-void set_led(int on)
+static void set_led(int on)
 {
+	if (noled)
+		return;
 	write_int("/sys/class/leds/hp::hddprotect/brightness", on);
 }
 
-void protect(int seconds)
+static void protect(int seconds)
 {
+	const char *str = (seconds == 0) ? "Unparked" : "Parked";
+
 	write_int(unload_heads_path, seconds*1000);
+	syslog(LOG_INFO, "%s %s disk head\n", str, device_path);
 }
 
-int on_ac(void)
+static int on_ac(void)
 {
-//	/sys/class/power_supply/AC0/online
+	/* /sys/class/power_supply/AC0/online */
+	return 1;
 }
 
-int lid_open(void)
+static int lid_open(void)
 {
-//	/proc/acpi/button/lid/LID/state
+	/* /proc/acpi/button/lid/LID/state */
+	return 1;
 }
 
-void ignore_me(void)
+static void ignore_me(int signum)
 {
 	protect(0);
 	set_led(0);
@@ -90,6 +110,7 @@ void ignore_me(void)
 int main(int argc, char **argv)
 {
 	int fd, ret;
+	struct stat st;
 	struct sched_param param;
 
 	if (argc == 1)
@@ -111,7 +132,16 @@ int main(int argc, char **argv)
 		return EXIT_FAILURE;
 	}
 
-	daemon(0, 0);
+	if (stat("/sys/class/leds/hp::hddprotect/brightness", &st))
+		noled = 1;
+
+	if (daemon(0, 0) != 0) {
+		perror("daemon");
+		return EXIT_FAILURE;
+	}
+
+	openlog(app_name, LOG_CONS | LOG_PID | LOG_NDELAY, LOG_LOCAL1);
+
 	param.sched_priority = sched_get_priority_max(SCHED_FIFO);
 	sched_setscheduler(0, SCHED_FIFO, &param);
 	mlockall(MCL_CURRENT|MCL_FUTURE);
@@ -141,6 +171,7 @@ int main(int argc, char **argv)
 			alarm(20);
 	}
 
+	closelog();
 	close(fd);
 	return EXIT_SUCCESS;
 }
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index f1dc4a21559..a4de88fb55f 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -757,10 +757,14 @@ SMP BARRIER PAIRING
 When dealing with CPU-CPU interactions, certain types of memory barrier should
 always be paired.  A lack of appropriate pairing is almost certainly an error.
 
-A write barrier should always be paired with a data dependency barrier or read
-barrier, though a general barrier would also be viable.  Similarly a read
-barrier or a data dependency barrier should always be paired with at least an
-write barrier, though, again, a general barrier is viable:
+General barriers pair with each other, though they also pair with
+most other types of barriers, albeit without transitivity.  An acquire
+barrier pairs with a release barrier, but both may also pair with other
+barriers, including of course general barriers.  A write barrier pairs
+with a data dependency barrier, an acquire barrier, a release barrier,
+a read barrier, or a general barrier.  Similarly a read barrier or a
+data dependency barrier pairs with a write barrier, an acquire barrier,
+a release barrier, or a general barrier:
 
 	CPU 1		      CPU 2
 	===============	      ===============
@@ -1893,6 +1897,21 @@ between the STORE to indicate the event and the STORE to set TASK_RUNNING:
 	    <general barrier>		  STORE current->state
 	LOAD event_indicated
 
+To repeat, this write memory barrier is present if and only if something
+is actually awakened.  To see this, consider the following sequence of
+events, where X and Y are both initially zero:
+
+	CPU 1				CPU 2
+	===============================	===============================
+	X = 1;				STORE event_indicated
+	smp_mb();			wake_up();
+	Y = 1;				wait_event(wq, Y == 1);
+	wake_up();			  load from Y sees 1, no memory barrier
+					load from X might see 0
+
+In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed
+to see 1.
+
 The available waker functions include:
 
 	complete();
diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index f304edb8fbe..45134dc2385 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -209,15 +209,12 @@ If memory device is found, memory hotplug code will be called.
 
 4.2 Notify memory hot-add event by hand
 ------------
-On powerpc, the firmware does not notify a memory hotplug event to the kernel.
-Therefore, "probe" interface is supported to notify the event to the kernel.
-This interface depends on CONFIG_ARCH_MEMORY_PROBE.
-
-CONFIG_ARCH_MEMORY_PROBE is supported on powerpc only. On x86, this config
-option is disabled by default since ACPI notifies a memory hotplug event to
-the kernel, which performs its hotplug operation as the result. Please
-enable this option if you need the "probe" interface for testing purposes
-on x86.
+On some architectures, the firmware may not notify the kernel of a memory
+hotplug event.  Therefore, the memory "probe" interface is supported to
+explicitly notify the kernel.  This interface depends on
+CONFIG_ARCH_MEMORY_PROBE and can be configured on powerpc, sh, and x86
+if hotplug is supported, although for x86 this should be handled by ACPI
+notification.
 
 Probe interface is located at
 /sys/devices/system/memory/probe
diff --git a/Documentation/mtd/spi-nor.txt b/Documentation/mtd/spi-nor.txt
new file mode 100644
index 00000000000..548d6306ebc
--- /dev/null
+++ b/Documentation/mtd/spi-nor.txt
@@ -0,0 +1,62 @@
+                          SPI NOR framework
+               ============================================
+
+Part I - Why do we need this framework?
+---------------------------------------
+
+SPI bus controllers (drivers/spi/) only deal with streams of bytes; the bus
+controller operates agnostic of the specific device attached. However, some
+controllers (such as Freescale's QuadSPI controller) cannot easily handle
+arbitrary streams of bytes, but rather are designed specifically for SPI NOR.
+
+In particular, Freescale's QuadSPI controller must know the NOR commands to
+find the right LUT sequence. Unfortunately, the SPI subsystem has no notion of
+opcodes, addresses, or data payloads; a SPI controller simply knows to send or
+receive bytes (Tx and Rx). Therefore, we must define a new layering scheme under
+which the controller driver is aware of the opcodes, addressing, and other
+details of the SPI NOR protocol.
+
+Part II - How does the framework work?
+--------------------------------------
+
+This framework just adds a new layer between the MTD and the SPI bus driver.
+With this new layer, the SPI NOR controller driver does not depend on the
+m25p80 code anymore.
+
+   Before this framework, the layer is like:
+
+                   MTD
+         ------------------------
+                  m25p80
+         ------------------------
+	       SPI bus driver
+         ------------------------
+	        SPI NOR chip
+
+   After this framework, the layer is like:
+                   MTD
+         ------------------------
+              SPI NOR framework
+         ------------------------
+                  m25p80
+         ------------------------
+	       SPI bus driver
+         ------------------------
+	       SPI NOR chip
+
+  With the SPI NOR controller driver (Freescale QuadSPI), it looks like:
+                   MTD
+         ------------------------
+              SPI NOR framework
+         ------------------------
+                fsl-quadSPI
+         ------------------------
+	       SPI NOR chip
+
+Part III - How can drivers use the framework?
+---------------------------------------------
+
+The main API is spi_nor_scan(). Before you call the hook, a driver should
+initialize the necessary fields for spi_nor{}. Please see
+drivers/mtd/spi-nor/spi-nor.c for detail. Please also refer to fsl-quadspi.c
+when you want to write a new driver for a SPI NOR controller.
diff --git a/Documentation/mutex-design.txt b/Documentation/mutex-design.txt
index 1dfe62c3641..ee231ed09ec 100644
--- a/Documentation/mutex-design.txt
+++ b/Documentation/mutex-design.txt
@@ -1,139 +1,157 @@
 Generic Mutex Subsystem
 
 started by Ingo Molnar <mingo@redhat.com>
+updated by Davidlohr Bueso <davidlohr@hp.com>
 
-  "Why on earth do we need a new mutex subsystem, and what's wrong
-   with semaphores?"
+What are mutexes?
+-----------------
 
-firstly, there's nothing wrong with semaphores. But if the simpler
-mutex semantics are sufficient for your code, then there are a couple
-of advantages of mutexes:
+In the Linux kernel, mutexes refer to a particular locking primitive
+that enforces serialization on shared memory systems, and not only to
+the generic term referring to 'mutual exclusion' found in academia
+or similar theoretical text books. Mutexes are sleeping locks which
+behave similarly to binary semaphores, and were introduced in 2006[1]
+as an alternative to these. This new data structure provided a number
+of advantages, including simpler interfaces, and at that time smaller
+code (see Disadvantages).
 
- - 'struct mutex' is smaller on most architectures: E.g. on x86,
-   'struct semaphore' is 20 bytes, 'struct mutex' is 16 bytes.
-   A smaller structure size means less RAM footprint, and better
-   CPU-cache utilization.
+[1] http://lwn.net/Articles/164802/
 
- - tighter code. On x86 i get the following .text sizes when
-   switching all mutex-alike semaphores in the kernel to the mutex
-   subsystem:
+Implementation
+--------------
 
-        text    data     bss     dec     hex filename
-     3280380  868188  396860 4545428  455b94 vmlinux-semaphore
-     3255329  865296  396732 4517357  44eded vmlinux-mutex
+Mutexes are represented by 'struct mutex', defined in include/linux/mutex.h
+and implemented in kernel/locking/mutex.c. These locks use a three
+state atomic counter (->count) to represent the different possible
+transitions that can occur during the lifetime of a lock:
 
-   that's 25051 bytes of code saved, or a 0.76% win - off the hottest
-   codepaths of the kernel. (The .data savings are 2892 bytes, or 0.33%)
-   Smaller code means better icache footprint, which is one of the
-   major optimization goals in the Linux kernel currently.
+	  1: unlocked
+	  0: locked, no waiters
+   negative: locked, with potential waiters
 
- - the mutex subsystem is slightly faster and has better scalability for
-   contended workloads. On an 8-way x86 system, running a mutex-based
-   kernel and testing creat+unlink+close (of separate, per-task files)
-   in /tmp with 16 parallel tasks, the average number of ops/sec is:
+In its most basic form it also includes a wait-queue and a spinlock
+that serializes access to it. CONFIG_SMP systems can also include
+a pointer to the lock task owner (->owner) as well as a spinner MCS
+lock (->osq), both described below in (ii).
 
-    Semaphores:                        Mutexes:
+When acquiring a mutex, there are three possible paths that can be
+taken, depending on the state of the lock:
 
-    $ ./test-mutex V 16 10             $ ./test-mutex V 16 10
-    8 CPUs, running 16 tasks.          8 CPUs, running 16 tasks.
-    checking VFS performance.          checking VFS performance.
-    avg loops/sec:      34713          avg loops/sec:      84153
-    CPU utilization:    63%            CPU utilization:    22%
+(i) fastpath: tries to atomically acquire the lock by decrementing the
+    counter. If it was already taken by another task it goes to the next
+    possible path. This logic is architecture specific. On x86-64, the
+    locking fastpath is 2 instructions:
 
-   i.e. in this workload, the mutex based kernel was 2.4 times faster
-   than the semaphore based kernel, _and_ it also had 2.8 times less CPU
-   utilization. (In terms of 'ops per CPU cycle', the semaphore kernel
-   performed 551 ops/sec per 1% of CPU time used, while the mutex kernel
-   performed 3825 ops/sec per 1% of CPU time used - it was 6.9 times
-   more efficient.)
-
-   the scalability difference is visible even on a 2-way P4 HT box:
-
-    Semaphores:                        Mutexes:
-
-    $ ./test-mutex V 16 10             $ ./test-mutex V 16 10
-    4 CPUs, running 16 tasks.          8 CPUs, running 16 tasks.
-    checking VFS performance.          checking VFS performance.
-    avg loops/sec:      127659         avg loops/sec:      181082
-    CPU utilization:    100%           CPU utilization:    34%
-
-   (the straight performance advantage of mutexes is 41%, the per-cycle
-    efficiency of mutexes is 4.1 times better.)
-
- - there are no fastpath tradeoffs, the mutex fastpath is just as tight
-   as the semaphore fastpath. On x86, the locking fastpath is 2
-   instructions:
-
-    c0377ccb <mutex_lock>:
-    c0377ccb:       f0 ff 08                lock decl (%eax)
-    c0377cce:       78 0e                   js     c0377cde <.text..lock.mutex>
-    c0377cd0:       c3                      ret
+    0000000000000e10 <mutex_lock>:
+    e21:   f0 ff 0b                lock decl (%rbx)
+    e24:   79 08                   jns    e2e <mutex_lock+0x1e>
 
    the unlocking fastpath is equally tight:
 
-    c0377cd1 <mutex_unlock>:
-    c0377cd1:       f0 ff 00                lock incl (%eax)
-    c0377cd4:       7e 0f                   jle    c0377ce5 <.text..lock.mutex+0x7>
-    c0377cd6:       c3                      ret
-
- - 'struct mutex' semantics are well-defined and are enforced if
-   CONFIG_DEBUG_MUTEXES is turned on. Semaphores on the other hand have
-   virtually no debugging code or instrumentation. The mutex subsystem
-   checks and enforces the following rules:
-
-   * - only one task can hold the mutex at a time
-   * - only the owner can unlock the mutex
-   * - multiple unlocks are not permitted
-   * - recursive locking is not permitted
-   * - a mutex object must be initialized via the API
-   * - a mutex object must not be initialized via memset or copying
-   * - task may not exit with mutex held
-   * - memory areas where held locks reside must not be freed
-   * - held mutexes must not be reinitialized
-   * - mutexes may not be used in hardware or software interrupt
-   *   contexts such as tasklets and timers
-
-   furthermore, there are also convenience features in the debugging
-   code:
-
-   * - uses symbolic names of mutexes, whenever they are printed in debug output
-   * - point-of-acquire tracking, symbolic lookup of function names
-   * - list of all locks held in the system, printout of them
-   * - owner tracking
-   * - detects self-recursing locks and prints out all relevant info
-   * - detects multi-task circular deadlocks and prints out all affected
-   *   locks and tasks (and only those tasks)
+    0000000000000bc0 <mutex_unlock>:
+    bc8:   f0 ff 07                lock incl (%rdi)
+    bcb:   7f 0a                   jg     bd7 <mutex_unlock+0x17>
+
+
+(ii) midpath: aka optimistic spinning, tries to spin for acquisition
+     while the lock owner is running and there are no other tasks ready
+     to run that have higher priority (need_resched). The rationale is
+     that if the lock owner is running, it is likely to release the lock
+     soon. The mutex spinners are queued up using MCS lock so that only
+     one spinner can compete for the mutex.
+
+     The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spinlock
+     with the desirable properties of being fair and with each cpu trying
+     to acquire the lock spinning on a local variable. It avoids expensive
+     cacheline bouncing that common test-and-set spinlock implementations
+     incur. An MCS-like lock is specially tailored for optimistic spinning
+     for sleeping lock implementation. An important feature of the customized
+     MCS lock is that it has the extra property that spinners are able to exit
+     the MCS spinlock queue when they need to reschedule. This further helps
+     avoid situations where MCS spinners that need to reschedule would continue
+     waiting to spin on mutex owner, only to go directly to slowpath upon
+     obtaining the MCS lock.
+
+
+(iii) slowpath: last resort, if the lock is still unable to be acquired,
+      the task is added to the wait-queue and sleeps until woken up by the
+      unlock path. Under normal circumstances it blocks as TASK_UNINTERRUPTIBLE.
+
+While formally kernel mutexes are sleepable locks, it is path (ii) that
+makes them more practically a hybrid type. By simply not interrupting a
+task and busy-waiting for a few cycles instead of immediately sleeping,
+the performance of this lock has been seen to significantly improve a
+number of workloads. Note that this technique is also used for rw-semaphores.
+
+Semantics
+---------
+
+The mutex subsystem checks and enforces the following rules:
+
+    - Only one task can hold the mutex at a time.
+    - Only the owner can unlock the mutex.
+    - Multiple unlocks are not permitted.
+    - Recursive locking/unlocking is not permitted.
+    - A mutex must only be initialized via the API (see below).
+    - A task may not exit with a mutex held.
+    - Memory areas where held locks reside must not be freed.
+    - Held mutexes must not be reinitialized.
+    - Mutexes may not be used in hardware or software interrupt
+      contexts such as tasklets and timers.
+
+These semantics are fully enforced when CONFIG DEBUG_MUTEXES is enabled.
+In addition, the mutex debugging code also implements a number of other
+features that make lock debugging easier and faster:
+
+    - Uses symbolic names of mutexes, whenever they are printed
+      in debug output.
+    - Point-of-acquire tracking, symbolic lookup of function names,
+      list of all locks held in the system, printout of them.
+    - Owner tracking.
+    - Detects self-recursing locks and prints out all relevant info.
+    - Detects multi-task circular deadlocks and prints out all affected
+      locks and tasks (and only those tasks).
+
+
+Interfaces
+----------
+Statically define the mutex:
+   DEFINE_MUTEX(name);
+
+Dynamically initialize the mutex:
+   mutex_init(mutex);
+
+Acquire the mutex, uninterruptible:
+   void mutex_lock(struct mutex *lock);
+   void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
+   int  mutex_trylock(struct mutex *lock);
+
+Acquire the mutex, interruptible:
+   int mutex_lock_interruptible_nested(struct mutex *lock,
+				       unsigned int subclass);
+   int mutex_lock_interruptible(struct mutex *lock);
+
+Acquire the mutex, interruptible, if dec to 0:
+   int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
+
+Unlock the mutex:
+   void mutex_unlock(struct mutex *lock);
+
+Test if the mutex is taken:
+   int mutex_is_locked(struct mutex *lock);
 
 Disadvantages
 -------------
 
-The stricter mutex API means you cannot use mutexes the same way you
-can use semaphores: e.g. they cannot be used from an interrupt context,
-nor can they be unlocked from a different context that which acquired
-it. [ I'm not aware of any other (e.g. performance) disadvantages from
-using mutexes at the moment, please let me know if you find any. ]
-
-Implementation of mutexes
--------------------------
-
-'struct mutex' is the new mutex type, defined in include/linux/mutex.h and
-implemented in kernel/locking/mutex.c. It is a counter-based mutex with a
-spinlock and a wait-list. The counter has 3 states: 1 for "unlocked", 0 for
-"locked" and negative numbers (usually -1) for "locked, potential waiters
-queued".
-
-the APIs of 'struct mutex' have been streamlined:
-
- DEFINE_MUTEX(name);
+Unlike its original design and purpose, 'struct mutex' is larger than
+most locks in the kernel. E.g: on x86-64 it is 40 bytes, almost twice
+as large as 'struct semaphore' (24 bytes) and 8 bytes shy of the
+'struct rw_semaphore' variant. Larger structure sizes mean more CPU
+cache and memory footprint.
 
- mutex_init(mutex);
+When to use mutexes
+-------------------
 
- void mutex_lock(struct mutex *lock);
- int  mutex_lock_interruptible(struct mutex *lock);
- int  mutex_trylock(struct mutex *lock);
- void mutex_unlock(struct mutex *lock);
- int  mutex_is_locked(struct mutex *lock);
- void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
- int  mutex_lock_interruptible_nested(struct mutex *lock,
-                                      unsigned int subclass);
- int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
+Unless the strict semantics of mutexes are unsuitable and/or the critical
+region prevents the lock from being shared, always prefer them to any other
+locking primitive.
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index a383c00392d..9c723ecd002 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -585,13 +585,19 @@ mode
 	balance-tlb or 5
 
 		Adaptive transmit load balancing: channel bonding that
-		does not require any special switch support.  The
-		outgoing traffic is distributed according to the
-		current load (computed relative to the speed) on each
-		slave.  Incoming traffic is received by the current
-		slave.  If the receiving slave fails, another slave
-		takes over the MAC address of the failed receiving
-		slave.
+		does not require any special switch support.
+
+		In tlb_dynamic_lb=1 mode; the outgoing traffic is
+		distributed according to the current load (computed
+		relative to the speed) on each slave.
+
+		In tlb_dynamic_lb=0 mode; the load balancing based on
+		current load is disabled and the load is distributed
+		only using the hash distribution.
+
+		Incoming traffic is received by the current slave.
+		If the receiving slave fails, another slave takes over
+		the MAC address of the failed receiving slave.
 
 		Prerequisite:
 
@@ -736,6 +742,28 @@ primary_reselect
 
 	This option was added for bonding version 3.6.0.
 
+tlb_dynamic_lb
+
+	Specifies if dynamic shuffling of flows is enabled in tlb
+	mode. The value has no effect on any other modes.
+
+	The default behavior of tlb mode is to shuffle active flows across
+	slaves based on the load in that interval. This gives nice lb
+	characteristics but can cause packet reordering. If re-ordering is
+	a concern use this variable to disable flow shuffling and rely on
+	load balancing provided solely by the hash distribution.
+	xmit-hash-policy can be used to select the appropriate hashing for
+	the setup.
+
+	The sysfs entry can be used to change the setting per bond device
+	and the initial value is derived from the module parameter. The
+	sysfs entry is allowed to be changed only if the bond device is
+	down.
+
+	The default value is "1" that enables flow shuffling while value "0"
+	disables it. This option was added in bonding driver 3.7.1
+
+
 updelay
 
 	Specifies the time, in milliseconds, to wait before enabling a
@@ -769,7 +797,7 @@ use_carrier
 xmit_hash_policy
 
 	Selects the transmit hash policy to use for slave selection in
-	balance-xor and 802.3ad modes.  Possible values are:
+	balance-xor, 802.3ad, and tlb modes.  Possible values are:
 
 	layer2
 
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index 4f7ae526136..2236d6dcb7d 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -469,6 +469,41 @@ solution for a couple of reasons:
   having this 'send only' use-case we may remove the receive list in the
   Kernel to save a little (really a very little!) CPU usage.
 
+  4.1.1.1 CAN filter usage optimisation
+
+  The CAN filters are processed in per-device filter lists at CAN frame
+  reception time. To reduce the number of checks that need to be performed
+  while walking through the filter lists the CAN core provides an optimized
+  filter handling when the filter subscription focusses on a single CAN ID.
+
+  For the possible 2048 SFF CAN identifiers the identifier is used as an index
+  to access the corresponding subscription list without any further checks.
+  For the 2^29 possible EFF CAN identifiers a 10 bit XOR folding is used as
+  hash function to retrieve the EFF table index.
+
+  To benefit from the optimized filters for single CAN identifiers the
+  CAN_SFF_MASK or CAN_EFF_MASK have to be set into can_filter.mask together
+  with set CAN_EFF_FLAG and CAN_RTR_FLAG bits. A set CAN_EFF_FLAG bit in the
+  can_filter.mask makes clear that it matters whether a SFF or EFF CAN ID is
+  subscribed. E.g. in the example from above
+
+    rfilter[0].can_id   = 0x123;
+    rfilter[0].can_mask = CAN_SFF_MASK;
+
+  both SFF frames with CAN ID 0x123 and EFF frames with 0xXXXXX123 can pass.
+
+  To filter for only 0x123 (SFF) and 0x12345678 (EFF) CAN identifiers the
+  filter has to be defined in this way to benefit from the optimized filters:
+
+    struct can_filter rfilter[2];
+
+    rfilter[0].can_id   = 0x123;
+    rfilter[0].can_mask = (CAN_EFF_FLAG | CAN_RTR_FLAG | CAN_SFF_MASK);
+    rfilter[1].can_id   = 0x12345678 | CAN_EFF_FLAG;
+    rfilter[1].can_mask = (CAN_EFF_FLAG | CAN_RTR_FLAG | CAN_EFF_MASK);
+
+    setsockopt(s, SOL_CAN_RAW, CAN_RAW_FILTER, &rfilter, sizeof(rfilter));
+
   4.1.2 RAW socket option CAN_RAW_ERR_FILTER
 
   As described in chapter 3.4 the CAN interface driver can generate so
diff --git a/Documentation/networking/cdc_mbim.txt b/Documentation/networking/cdc_mbim.txt
new file mode 100644
index 00000000000..a15ea602aa5
--- /dev/null
+++ b/Documentation/networking/cdc_mbim.txt
@@ -0,0 +1,339 @@
+     cdc_mbim - Driver for CDC MBIM Mobile Broadband modems
+    ========================================================
+
+The cdc_mbim driver supports USB devices conforming to the "Universal
+Serial Bus Communications Class Subclass Specification for Mobile
+Broadband Interface Model" [1], which is a further development of
+"Universal Serial Bus Communications Class Subclass Specifications for
+Network Control Model Devices" [2] optimized for Mobile Broadband
+devices, aka "3G/LTE modems".
+
+
+Command Line Parameters
+=======================
+
+The cdc_mbim driver has no parameters of its own.  But the probing
+behaviour for NCM 1.0 backwards compatible MBIM functions (an
+"NCM/MBIM function" as defined in section 3.2 of [1]) is affected
+by a cdc_ncm driver parameter:
+
+prefer_mbim
+-----------
+Type:          Boolean
+Valid Range:   N/Y (0-1)
+Default Value: Y (MBIM is preferred)
+
+This parameter sets the system policy for NCM/MBIM functions.  Such
+functions will be handled by either the cdc_ncm driver or the cdc_mbim
+driver depending on the prefer_mbim setting.  Setting prefer_mbim=N
+makes the cdc_mbim driver ignore these functions and lets the cdc_ncm
+driver handle them instead.
+
+The parameter is writable, and can be changed at any time. A manual
+unbind/bind is required to make the change effective for NCM/MBIM
+functions bound to the "wrong" driver
+
+
+Basic usage
+===========
+
+MBIM functions are inactive when unmanaged. The cdc_mbim driver only
+provides an userspace interface to the MBIM control channel, and will
+not participate in the management of the function. This implies that a
+userspace MBIM management application always is required to enable a
+MBIM function.
+
+Such userspace applications includes, but are not limited to:
+ - mbimcli (included with the libmbim [3] library), and
+ - ModemManager [4]
+
+Establishing a MBIM IP session reequires at least these actions by the
+management application:
+ - open the control channel
+ - configure network connection settings
+ - connect to network
+ - configure IP interface
+
+Management application development
+----------------------------------
+The driver <-> userspace interfaces are described below.  The MBIM
+control channel protocol is described in [1].
+
+
+MBIM control channel userspace ABI
+==================================
+
+/dev/cdc-wdmX character device
+------------------------------
+The driver creates a two-way pipe to the MBIM function control channel
+using the cdc-wdm driver as a subdriver.  The userspace end of the
+control channel pipe is a /dev/cdc-wdmX character device.
+
+The cdc_mbim driver does not process or police messages on the control
+channel.  The channel is fully delegated to the userspace management
+application.  It is therefore up to this application to ensure that it
+complies with all the control channel requirements in [1].
+
+The cdc-wdmX device is created as a child of the MBIM control
+interface USB device.  The character device associated with a specific
+MBIM function can be looked up using sysfs.  For example:
+
+ bjorn@nemi:~$ ls /sys/bus/usb/drivers/cdc_mbim/2-4:2.12/usbmisc
+ cdc-wdm0
+
+ bjorn@nemi:~$ grep . /sys/bus/usb/drivers/cdc_mbim/2-4:2.12/usbmisc/cdc-wdm0/dev
+ 180:0
+
+
+USB configuration descriptors
+-----------------------------
+The wMaxControlMessage field of the CDC MBIM functional descriptor
+limits the maximum control message size. The managament application is
+responsible for negotiating a control message size complying with the
+requirements in section 9.3.1 of [1], taking this descriptor field
+into consideration.
+
+The userspace application can access the CDC MBIM functional
+descriptor of a MBIM function using either of the two USB
+configuration descriptor kernel interfaces described in [6] or [7].
+
+See also the ioctl documentation below.
+
+
+Fragmentation
+-------------
+The userspace application is responsible for all control message
+fragmentation and defragmentaion, as described in section 9.5 of [1].
+
+
+/dev/cdc-wdmX write()
+---------------------
+The MBIM control messages from the management application *must not*
+exceed the negotiated control message size.
+
+
+/dev/cdc-wdmX read()
+--------------------
+The management application *must* accept control messages of up the
+negotiated control message size.
+
+
+/dev/cdc-wdmX ioctl()
+--------------------
+IOCTL_WDM_MAX_COMMAND: Get Maximum Command Size
+This ioctl returns the wMaxControlMessage field of the CDC MBIM
+functional descriptor for MBIM devices.  This is intended as a
+convenience, eliminating the need to parse the USB descriptors from
+userspace.
+
+	#include <stdio.h>
+	#include <fcntl.h>
+	#include <sys/ioctl.h>
+	#include <linux/types.h>
+	#include <linux/usb/cdc-wdm.h>
+	int main()
+	{
+		__u16 max;
+		int fd = open("/dev/cdc-wdm0", O_RDWR);
+		if (!ioctl(fd, IOCTL_WDM_MAX_COMMAND, &max))
+			printf("wMaxControlMessage is %d\n", max);
+	}
+
+
+Custom device services
+----------------------
+The MBIM specification allows vendors to freely define additional
+services.  This is fully supported by the cdc_mbim driver.
+
+Support for new MBIM services, including vendor specified services, is
+implemented entirely in userspace, like the rest of the MBIM control
+protocol
+
+New services should be registered in the MBIM Registry [5].
+
+
+
+MBIM data channel userspace ABI
+===============================
+
+wwanY network device
+--------------------
+The cdc_mbim driver represents the MBIM data channel as a single
+network device of the "wwan" type. This network device is initially
+mapped to MBIM IP session 0.
+
+
+Multiplexed IP sessions (IPS)
+-----------------------------
+MBIM allows multiplexing up to 256 IP sessions over a single USB data
+channel.  The cdc_mbim driver models such IP sessions as 802.1q VLAN
+subdevices of the master wwanY device, mapping MBIM IP session Z to
+VLAN ID Z for all values of Z greater than 0.
+
+The device maximum Z is given in the MBIM_DEVICE_CAPS_INFO structure
+described in section 10.5.1 of [1].
+
+The userspace management application is responsible for adding new
+VLAN links prior to establishing MBIM IP sessions where the SessionId
+is greater than 0. These links can be added by using the normal VLAN
+kernel interfaces, either ioctl or netlink.
+
+For example, adding a link for a MBIM IP session with SessionId 3:
+
+  ip link add link wwan0 name wwan0.3 type vlan id 3
+
+The driver will automatically map the "wwan0.3" network device to MBIM
+IP session 3.
+
+
+Device Service Streams (DSS)
+----------------------------
+MBIM also allows up to 256 non-IP data streams to be multiplexed over
+the same shared USB data channel.  The cdc_mbim driver models these
+sessions as another set of 802.1q VLAN subdevices of the master wwanY
+device, mapping MBIM DSS session A to VLAN ID (256 + A) for all values
+of A.
+
+The device maximum A is given in the MBIM_DEVICE_SERVICES_INFO
+structure described in section 10.5.29 of [1].
+
+The DSS VLAN subdevices are used as a practical interface between the
+shared MBIM data channel and a MBIM DSS aware userspace application.
+It is not intended to be presented as-is to an end user. The
+assumption is that an userspace application initiating a DSS session
+also takes care of the necessary framing of the DSS data, presenting
+the stream to the end user in an appropriate way for the stream type.
+
+The network device ABI requires a dummy ethernet header for every DSS
+data frame being transported.  The contents of this header is
+arbitrary, with the following exceptions:
+ - TX frames using an IP protocol (0x0800 or 0x86dd) will be dropped
+ - RX frames will have the protocol field set to ETH_P_802_3 (but will
+   not be properly formatted 802.3 frames)
+ - RX frames will have the destination address set to the hardware
+   address of the master device
+
+The DSS supporting userspace management application is responsible for
+adding the dummy ethernet header on TX and stripping it on RX.
+
+This is a simple example using tools commonly available, exporting
+DssSessionId 5 as a pty character device pointed to by a /dev/nmea
+symlink:
+
+  ip link add link wwan0 name wwan0.dss5 type vlan id 261
+  ip link set dev wwan0.dss5 up
+  socat INTERFACE:wwan0.dss5,type=2 PTY:,echo=0,link=/dev/nmea
+
+This is only an example, most suitable for testing out a DSS
+service. Userspace applications supporting specific MBIM DSS services
+are expected to use the tools and programming interfaces required by
+that service.
+
+Note that adding VLAN links for DSS sessions is entirely optional.  A
+management application may instead choose to bind a packet socket
+directly to the master network device, using the received VLAN tags to
+map frames to the correct DSS session and adding 18 byte VLAN ethernet
+headers with the appropriate tag on TX.  In this case using a socket
+filter is recommended, matching only the DSS VLAN subset. This avoid
+unnecessary copying of unrelated IP session data to userspace.  For
+example:
+
+  static struct sock_filter dssfilter[] = {
+	/* use special negative offsets to get VLAN tag */
+	BPF_STMT(BPF_LD|BPF_B|BPF_ABS, SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT),
+	BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, 1, 0, 6), /* true */
+
+	/* verify DSS VLAN range */
+	BPF_STMT(BPF_LD|BPF_H|BPF_ABS, SKF_AD_OFF + SKF_AD_VLAN_TAG),
+	BPF_JUMP(BPF_JMP|BPF_JGE|BPF_K, 256, 0, 4),	/* 256 is first DSS VLAN */
+	BPF_JUMP(BPF_JMP|BPF_JGE|BPF_K, 512, 3, 0),	/* 511 is last DSS VLAN */
+
+	/* verify ethertype */
+        BPF_STMT(BPF_LD|BPF_H|BPF_ABS, 2 * ETH_ALEN),
+        BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, ETH_P_802_3, 0, 1),
+
+        BPF_STMT(BPF_RET|BPF_K, (u_int)-1),	/* accept */
+        BPF_STMT(BPF_RET|BPF_K, 0),		/* ignore */
+  };
+
+
+
+Tagged IP session 0 VLAN
+------------------------
+As described above, MBIM IP session 0 is treated as special by the
+driver.  It is initially mapped to untagged frames on the wwanY
+network device.
+
+This mapping implies a few restrictions on multiplexed IPS and DSS
+sessions, which may not always be practical:
+ - no IPS or DSS session can use a frame size greater than the MTU on
+   IP session 0
+ - no IPS or DSS session can be in the up state unless the network
+   device representing IP session 0 also is up
+
+These problems can be avoided by optionally making the driver map IP
+session 0 to a VLAN subdevice, similar to all other IP sessions.  This
+behaviour is triggered by adding a VLAN link for the magic VLAN ID
+4094.  The driver will then immediately start mapping MBIM IP session
+0 to this VLAN, and will drop untagged frames on the master wwanY
+device.
+
+Tip: It might be less confusing to the end user to name this VLAN
+subdevice after the MBIM SessionID instead of the VLAN ID.  For
+example:
+
+  ip link add link wwan0 name wwan0.0 type vlan id 4094
+
+
+VLAN mapping
+------------
+
+Summarizing the cdc_mbim driver mapping described above, we have this
+relationship between VLAN tags on the wwanY network device and MBIM
+sessions on the shared USB data channel:
+
+  VLAN ID       MBIM type   MBIM SessionID           Notes
+  ---------------------------------------------------------
+  untagged      IPS         0                        a)
+  1 - 255       IPS         1 - 255 <VLANID>
+  256 - 511     DSS         0 - 255 <VLANID - 256>
+  512 - 4093                                         b)
+  4094          IPS         0                        c)
+
+    a) if no VLAN ID 4094 link exists, else dropped
+    b) unsupported VLAN range, unconditionally dropped
+    c) if a VLAN ID 4094 link exists, else dropped
+
+
+
+
+References
+==========
+
+[1] USB Implementers Forum, Inc. - "Universal Serial Bus
+      Communications Class Subclass Specification for Mobile Broadband
+      Interface Model", Revision 1.0 (Errata 1), May 1, 2013
+      - http://www.usb.org/developers/docs/devclass_docs/
+
+[2] USB Implementers Forum, Inc. - "Universal Serial Bus
+      Communications Class Subclass Specifications for Network Control
+      Model Devices", Revision 1.0 (Errata 1), November 24, 2010
+      - http://www.usb.org/developers/docs/devclass_docs/
+
+[3] libmbim - "a glib-based library for talking to WWAN modems and
+      devices which speak the Mobile Interface Broadband Model (MBIM)
+      protocol"
+      - http://www.freedesktop.org/wiki/Software/libmbim/
+
+[4] ModemManager - "a DBus-activated daemon which controls mobile
+      broadband (2G/3G/4G) devices and connections"
+      - http://www.freedesktop.org/wiki/Software/ModemManager/
+
+[5] "MBIM (Mobile Broadband Interface Model) Registry"
+       - http://compliance.usb.org/mbim/
+
+[6] "/proc/bus/usb filesystem output"
+       - Documentation/usb/proc_usb_info.txt
+
+[7] "/sys/bus/usb/devices/.../descriptors"
+       - Documentation/ABI/stable/sysfs-bus-usb
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index e3ba753cb71..ee78eba78a9 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -281,6 +281,7 @@ Possible BPF extensions are shown in the following table:
   cpu                                   raw_smp_processor_id()
   vlan_tci                              vlan_tx_tag_get(skb)
   vlan_pr                               vlan_tx_tag_present(skb)
+  rand                                  prandom_u32()
 
 These extensions can also be prefixed with '#'.
 Examples for low-level BPF:
@@ -308,6 +309,18 @@ Examples for low-level BPF:
   ret #-1
   drop: ret #0
 
+** icmp random packet sampling, 1 in 4
+  ldh [12]
+  jne #0x800, drop
+  ldb [23]
+  jneq #1, drop
+  # get a random uint32 number
+  ld rand
+  mod #4
+  jneq #1, drop
+  ret #-1
+  drop: ret #0
+
 ** SECCOMP filter example:
 
   ld [4]                  /* offsetof(struct seccomp_data, arch) */
@@ -548,42 +561,43 @@ toolchain for developing and testing the kernel's JIT compiler.
 
 BPF kernel internals
 --------------------
-Internally, for the kernel interpreter, a different BPF instruction set
+Internally, for the kernel interpreter, a different instruction set
 format with similar underlying principles from BPF described in previous
 paragraphs is being used. However, the instruction set format is modelled
 closer to the underlying architecture to mimic native instruction sets, so
-that a better performance can be achieved (more details later).
+that a better performance can be achieved (more details later). This new
+ISA is called 'eBPF' or 'internal BPF' interchangeably. (Note: eBPF which
+originates from [e]xtended BPF is not the same as BPF extensions! While
+eBPF is an ISA, BPF extensions date back to classic BPF's 'overloading'
+of BPF_LD | BPF_{B,H,W} | BPF_ABS instruction.)
 
 It is designed to be JITed with one to one mapping, which can also open up
-the possibility for GCC/LLVM compilers to generate optimized BPF code through
-a BPF backend that performs almost as fast as natively compiled code.
+the possibility for GCC/LLVM compilers to generate optimized eBPF code through
+an eBPF backend that performs almost as fast as natively compiled code.
 
 The new instruction set was originally designed with the possible goal in
-mind to write programs in "restricted C" and compile into BPF with a optional
+mind to write programs in "restricted C" and compile into eBPF with a optional
 GCC/LLVM backend, so that it can just-in-time map to modern 64-bit CPUs with
-minimal performance overhead over two steps, that is, C -> BPF -> native code.
+minimal performance overhead over two steps, that is, C -> eBPF -> native code.
 
 Currently, the new format is being used for running user BPF programs, which
 includes seccomp BPF, classic socket filters, cls_bpf traffic classifier,
 team driver's classifier for its load-balancing mode, netfilter's xt_bpf
 extension, PTP dissector/classifier, and much more. They are all internally
 converted by the kernel into the new instruction set representation and run
-in the extended interpreter. For in-kernel handlers, this all works
-transparently by using sk_unattached_filter_create() for setting up the
-filter, resp. sk_unattached_filter_destroy() for destroying it. The macro
-SK_RUN_FILTER(filter, ctx) transparently invokes the right BPF function to
-run the filter. 'filter' is a pointer to struct sk_filter that we got from
-sk_unattached_filter_create(), and 'ctx' the given context (e.g. skb pointer).
-All constraints and restrictions from sk_chk_filter() apply before a
-conversion to the new layout is being done behind the scenes!
-
-Currently, for JITing, the user BPF format is being used and current BPF JIT
-compilers reused whenever possible. In other words, we do not (yet!) perform
-a JIT compilation in the new layout, however, future work will successively
-migrate traditional JIT compilers into the new instruction format as well, so
-that they will profit from the very same benefits. Thus, when speaking about
-JIT in the following, a JIT compiler (TBD) for the new instruction format is
-meant in this context.
+in the eBPF interpreter. For in-kernel handlers, this all works transparently
+by using sk_unattached_filter_create() for setting up the filter, resp.
+sk_unattached_filter_destroy() for destroying it. The macro
+SK_RUN_FILTER(filter, ctx) transparently invokes eBPF interpreter or JITed
+code to run the filter. 'filter' is a pointer to struct sk_filter that we
+got from sk_unattached_filter_create(), and 'ctx' the given context (e.g.
+skb pointer). All constraints and restrictions from sk_chk_filter() apply
+before a conversion to the new layout is being done behind the scenes!
+
+Currently, the classic BPF format is being used for JITing on most of the
+architectures. Only x86-64 performs JIT compilation from eBPF instruction set,
+however, future work will migrate other JIT compilers as well, so that they
+will profit from the very same benefits.
 
 Some core changes of the new internal format:
 
@@ -592,35 +606,35 @@ Some core changes of the new internal format:
   The old format had two registers A and X, and a hidden frame pointer. The
   new layout extends this to be 10 internal registers and a read-only frame
   pointer. Since 64-bit CPUs are passing arguments to functions via registers
-  the number of args from BPF program to in-kernel function is restricted
+  the number of args from eBPF program to in-kernel function is restricted
   to 5 and one register is used to accept return value from an in-kernel
   function. Natively, x86_64 passes first 6 arguments in registers, aarch64/
   sparcv9/mips64 have 7 - 8 registers for arguments; x86_64 has 6 callee saved
   registers, and aarch64/sparcv9/mips64 have 11 or more callee saved registers.
 
-  Therefore, BPF calling convention is defined as:
+  Therefore, eBPF calling convention is defined as:
 
-    * R0	- return value from in-kernel function
-    * R1 - R5	- arguments from BPF program to in-kernel function
+    * R0	- return value from in-kernel function, and exit value for eBPF program
+    * R1 - R5	- arguments from eBPF program to in-kernel function
     * R6 - R9	- callee saved registers that in-kernel function will preserve
     * R10	- read-only frame pointer to access stack
 
-  Thus, all BPF registers map one to one to HW registers on x86_64, aarch64,
-  etc, and BPF calling convention maps directly to ABIs used by the kernel on
+  Thus, all eBPF registers map one to one to HW registers on x86_64, aarch64,
+  etc, and eBPF calling convention maps directly to ABIs used by the kernel on
   64-bit architectures.
 
   On 32-bit architectures JIT may map programs that use only 32-bit arithmetic
   and may let more complex programs to be interpreted.
 
-  R0 - R5 are scratch registers and BPF program needs spill/fill them if
-  necessary across calls. Note that there is only one BPF program (== one BPF
-  main routine) and it cannot call other BPF functions, it can only call
-  predefined in-kernel functions, though.
+  R0 - R5 are scratch registers and eBPF program needs spill/fill them if
+  necessary across calls. Note that there is only one eBPF program (== one
+  eBPF main routine) and it cannot call other eBPF functions, it can only
+  call predefined in-kernel functions, though.
 
 - Register width increases from 32-bit to 64-bit:
 
   Still, the semantics of the original 32-bit ALU operations are preserved
-  via 32-bit subregisters. All BPF registers are 64-bit with 32-bit lower
+  via 32-bit subregisters. All eBPF registers are 64-bit with 32-bit lower
   subregisters that zero-extend into 64-bit if they are being written to.
   That behavior maps directly to x86_64 and arm64 subregister definition, but
   makes other JITs more difficult.
@@ -631,8 +645,8 @@ Some core changes of the new internal format:
 
   Operation is 64-bit, because on 64-bit architectures, pointers are also
   64-bit wide, and we want to pass 64-bit values in/out of kernel functions,
-  so 32-bit BPF registers would otherwise require to define register-pair
-  ABI, thus, there won't be able to use a direct BPF register to HW register
+  so 32-bit eBPF registers would otherwise require to define register-pair
+  ABI, thus, there won't be able to use a direct eBPF register to HW register
   mapping and JIT would need to do combine/split/move operations for every
   register in and out of the function, which is complex, bug prone and slow.
   Another reason is the use of atomic 64-bit counters.
@@ -646,14 +660,145 @@ Some core changes of the new internal format:
 - Introduces bpf_call insn and register passing convention for zero overhead
   calls from/to other kernel functions:
 
-  After a kernel function call, R1 - R5 are reset to unreadable and R0 has a
-  return type of the function. Since R6 - R9 are callee saved, their state is
-  preserved across the call.
-
-Also in the new design, BPF is limited to 4096 insns, which means that any
+  Before an in-kernel function call, the internal BPF program needs to
+  place function arguments into R1 to R5 registers to satisfy calling
+  convention, then the interpreter will take them from registers and pass
+  to in-kernel function. If R1 - R5 registers are mapped to CPU registers
+  that are used for argument passing on given architecture, the JIT compiler
+  doesn't need to emit extra moves. Function arguments will be in the correct
+  registers and BPF_CALL instruction will be JITed as single 'call' HW
+  instruction. This calling convention was picked to cover common call
+  situations without performance penalty.
+
+  After an in-kernel function call, R1 - R5 are reset to unreadable and R0 has
+  a return value of the function. Since R6 - R9 are callee saved, their state
+  is preserved across the call.
+
+  For example, consider three C functions:
+
+  u64 f1() { return (*_f2)(1); }
+  u64 f2(u64 a) { return f3(a + 1, a); }
+  u64 f3(u64 a, u64 b) { return a - b; }
+
+  GCC can compile f1, f3 into x86_64:
+
+  f1:
+    movl $1, %edi
+    movq _f2(%rip), %rax
+    jmp  *%rax
+  f3:
+    movq %rdi, %rax
+    subq %rsi, %rax
+    ret
+
+  Function f2 in eBPF may look like:
+
+  f2:
+    bpf_mov R2, R1
+    bpf_add R1, 1
+    bpf_call f3
+    bpf_exit
+
+  If f2 is JITed and the pointer stored to '_f2'. The calls f1 -> f2 -> f3 and
+  returns will be seamless. Without JIT, __sk_run_filter() interpreter needs to
+  be used to call into f2.
+
+  For practical reasons all eBPF programs have only one argument 'ctx' which is
+  already placed into R1 (e.g. on __sk_run_filter() startup) and the programs
+  can call kernel functions with up to 5 arguments. Calls with 6 or more arguments
+  are currently not supported, but these restrictions can be lifted if necessary
+  in the future.
+
+  On 64-bit architectures all register map to HW registers one to one. For
+  example, x86_64 JIT compiler can map them as ...
+
+    R0 - rax
+    R1 - rdi
+    R2 - rsi
+    R3 - rdx
+    R4 - rcx
+    R5 - r8
+    R6 - rbx
+    R7 - r13
+    R8 - r14
+    R9 - r15
+    R10 - rbp
+
+  ... since x86_64 ABI mandates rdi, rsi, rdx, rcx, r8, r9 for argument passing
+  and rbx, r12 - r15 are callee saved.
+
+  Then the following internal BPF pseudo-program:
+
+    bpf_mov R6, R1 /* save ctx */
+    bpf_mov R2, 2
+    bpf_mov R3, 3
+    bpf_mov R4, 4
+    bpf_mov R5, 5
+    bpf_call foo
+    bpf_mov R7, R0 /* save foo() return value */
+    bpf_mov R1, R6 /* restore ctx for next call */
+    bpf_mov R2, 6
+    bpf_mov R3, 7
+    bpf_mov R4, 8
+    bpf_mov R5, 9
+    bpf_call bar
+    bpf_add R0, R7
+    bpf_exit
+
+  After JIT to x86_64 may look like:
+
+    push %rbp
+    mov %rsp,%rbp
+    sub $0x228,%rsp
+    mov %rbx,-0x228(%rbp)
+    mov %r13,-0x220(%rbp)
+    mov %rdi,%rbx
+    mov $0x2,%esi
+    mov $0x3,%edx
+    mov $0x4,%ecx
+    mov $0x5,%r8d
+    callq foo
+    mov %rax,%r13
+    mov %rbx,%rdi
+    mov $0x2,%esi
+    mov $0x3,%edx
+    mov $0x4,%ecx
+    mov $0x5,%r8d
+    callq bar
+    add %r13,%rax
+    mov -0x228(%rbp),%rbx
+    mov -0x220(%rbp),%r13
+    leaveq
+    retq
+
+  Which is in this example equivalent in C to:
+
+    u64 bpf_filter(u64 ctx)
+    {
+        return foo(ctx, 2, 3, 4, 5) + bar(ctx, 6, 7, 8, 9);
+    }
+
+  In-kernel functions foo() and bar() with prototype: u64 (*)(u64 arg1, u64
+  arg2, u64 arg3, u64 arg4, u64 arg5); will receive arguments in proper
+  registers and place their return value into '%rax' which is R0 in eBPF.
+  Prologue and epilogue are emitted by JIT and are implicit in the
+  interpreter. R0-R5 are scratch registers, so eBPF program needs to preserve
+  them across the calls as defined by calling convention.
+
+  For example the following program is invalid:
+
+    bpf_mov R1, 1
+    bpf_call foo
+    bpf_mov R0, R1
+    bpf_exit
+
+  After the call the registers R1-R5 contain junk values and cannot be read.
+  In the future an eBPF verifier can be used to validate internal BPF programs.
+
+Also in the new design, eBPF is limited to 4096 insns, which means that any
 program will terminate quickly and will only call a fixed number of kernel
 functions. Original BPF and the new format are two operand instructions,
-which helps to do one-to-one mapping between BPF insn and x86 insn during JIT.
+which helps to do one-to-one mapping between eBPF insn and x86 insn during JIT.
 
 The input context pointer for invoking the interpreter function is generic,
 its content is defined by a specific use case. For seccomp register R1 points
@@ -661,7 +806,26 @@ to seccomp_data, for converted BPF filters R1 points to a skb.
 
 A program, that is translated internally consists of the following elements:
 
-  op:16, jt:8, jf:8, k:32    ==>    op:8, a_reg:4, x_reg:4, off:16, imm:32
+  op:16, jt:8, jf:8, k:32    ==>    op:8, dst_reg:4, src_reg:4, off:16, imm:32
+
+So far 87 internal BPF instructions were implemented. 8-bit 'op' opcode field
+has room for new instructions. Some of them may use 16/24/32 byte encoding. New
+instructions must be multiple of 8 bytes to preserve backward compatibility.
+
+Internal BPF is a general purpose RISC instruction set. Not every register and
+every instruction are used during translation from original BPF to new format.
+For example, socket filters are not using 'exclusive add' instruction, but
+tracing filters may do to maintain counters of events, for example. Register R9
+is not used by socket filters either, but more complex filters may be running
+out of registers and would have to resort to spill/fill to stack.
+
+Internal BPF can used as generic assembler for last step performance
+optimizations, socket filters and seccomp are using it as assembler. Tracing
+filters may use it as assembler to generate code from kernel. In kernel usage
+may not be bounded by security considerations, since generated internal BPF code
+may be optimizing internal code path and not being exposed to the user space.
+Safety of internal BPF can come from a verifier (TBD). In such use cases as
+described, it may be used as safe instruction set.
 
 Just like the original BPF, the new format runs within a controlled environment,
 is deterministic and the kernel can easily prove that. The safety of the program
@@ -670,6 +834,181 @@ loops and other CFG validation; second step starts from the first insn and
 descends all possible paths. It simulates execution of every insn and observes
 the state change of registers and stack.
 
+eBPF opcode encoding
+--------------------
+
+eBPF is reusing most of the opcode encoding from classic to simplify conversion
+of classic BPF to eBPF. For arithmetic and jump instructions the 8-bit 'code'
+field is divided into three parts:
+
+  +----------------+--------+--------------------+
+  |   4 bits       |  1 bit |   3 bits           |
+  | operation code | source | instruction class  |
+  +----------------+--------+--------------------+
+  (MSB)                                      (LSB)
+
+Three LSB bits store instruction class which is one of:
+
+  Classic BPF classes:    eBPF classes:
+
+  BPF_LD    0x00          BPF_LD    0x00
+  BPF_LDX   0x01          BPF_LDX   0x01
+  BPF_ST    0x02          BPF_ST    0x02
+  BPF_STX   0x03          BPF_STX   0x03
+  BPF_ALU   0x04          BPF_ALU   0x04
+  BPF_JMP   0x05          BPF_JMP   0x05
+  BPF_RET   0x06          [ class 6 unused, for future if needed ]
+  BPF_MISC  0x07          BPF_ALU64 0x07
+
+When BPF_CLASS(code) == BPF_ALU or BPF_JMP, 4th bit encodes source operand ...
+
+  BPF_K     0x00
+  BPF_X     0x08
+
+ * in classic BPF, this means:
+
+  BPF_SRC(code) == BPF_X - use register X as source operand
+  BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand
+
+ * in eBPF, this means:
+
+  BPF_SRC(code) == BPF_X - use 'src_reg' register as source operand
+  BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand
+
+... and four MSB bits store operation code.
+
+If BPF_CLASS(code) == BPF_ALU or BPF_ALU64 [ in eBPF ], BPF_OP(code) is one of:
+
+  BPF_ADD   0x00
+  BPF_SUB   0x10
+  BPF_MUL   0x20
+  BPF_DIV   0x30
+  BPF_OR    0x40
+  BPF_AND   0x50
+  BPF_LSH   0x60
+  BPF_RSH   0x70
+  BPF_NEG   0x80
+  BPF_MOD   0x90
+  BPF_XOR   0xa0
+  BPF_MOV   0xb0  /* eBPF only: mov reg to reg */
+  BPF_ARSH  0xc0  /* eBPF only: sign extending shift right */
+  BPF_END   0xd0  /* eBPF only: endianness conversion */
+
+If BPF_CLASS(code) == BPF_JMP, BPF_OP(code) is one of:
+
+  BPF_JA    0x00
+  BPF_JEQ   0x10
+  BPF_JGT   0x20
+  BPF_JGE   0x30
+  BPF_JSET  0x40
+  BPF_JNE   0x50  /* eBPF only: jump != */
+  BPF_JSGT  0x60  /* eBPF only: signed '>' */
+  BPF_JSGE  0x70  /* eBPF only: signed '>=' */
+  BPF_CALL  0x80  /* eBPF only: function call */
+  BPF_EXIT  0x90  /* eBPF only: function return */
+
+So BPF_ADD | BPF_X | BPF_ALU means 32-bit addition in both classic BPF
+and eBPF. There are only two registers in classic BPF, so it means A += X.
+In eBPF it means dst_reg = (u32) dst_reg + (u32) src_reg; similarly,
+BPF_XOR | BPF_K | BPF_ALU means A ^= imm32 in classic BPF and analogous
+src_reg = (u32) src_reg ^ (u32) imm32 in eBPF.
+
+Classic BPF is using BPF_MISC class to represent A = X and X = A moves.
+eBPF is using BPF_MOV | BPF_X | BPF_ALU code instead. Since there are no
+BPF_MISC operations in eBPF, the class 7 is used as BPF_ALU64 to mean
+exactly the same operations as BPF_ALU, but with 64-bit wide operands
+instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.:
+dst_reg = dst_reg + src_reg
+
+Classic BPF wastes the whole BPF_RET class to represent a single 'ret'
+operation. Classic BPF_RET | BPF_K means copy imm32 into return register
+and perform function exit. eBPF is modeled to match CPU, so BPF_JMP | BPF_EXIT
+in eBPF means function exit only. The eBPF program needs to store return
+value into register R0 before doing a BPF_EXIT. Class 6 in eBPF is currently
+unused and reserved for future use.
+
+For load and store instructions the 8-bit 'code' field is divided as:
+
+  +--------+--------+-------------------+
+  | 3 bits | 2 bits |   3 bits          |
+  |  mode  |  size  | instruction class |
+  +--------+--------+-------------------+
+  (MSB)                             (LSB)
+
+Size modifier is one of ...
+
+  BPF_W   0x00    /* word */
+  BPF_H   0x08    /* half word */
+  BPF_B   0x10    /* byte */
+  BPF_DW  0x18    /* eBPF only, double word */
+
+... which encodes size of load/store operation:
+
+ B  - 1 byte
+ H  - 2 byte
+ W  - 4 byte
+ DW - 8 byte (eBPF only)
+
+Mode modifier is one of:
+
+  BPF_IMM  0x00  /* classic BPF only, reserved in eBPF */
+  BPF_ABS  0x20
+  BPF_IND  0x40
+  BPF_MEM  0x60
+  BPF_LEN  0x80  /* classic BPF only, reserved in eBPF */
+  BPF_MSH  0xa0  /* classic BPF only, reserved in eBPF */
+  BPF_XADD 0xc0  /* eBPF only, exclusive add */
+
+eBPF has two non-generic instructions: (BPF_ABS | <size> | BPF_LD) and
+(BPF_IND | <size> | BPF_LD) which are used to access packet data.
+
+They had to be carried over from classic to have strong performance of
+socket filters running in eBPF interpreter. These instructions can only
+be used when interpreter context is a pointer to 'struct sk_buff' and
+have seven implicit operands. Register R6 is an implicit input that must
+contain pointer to sk_buff. Register R0 is an implicit output which contains
+the data fetched from the packet. Registers R1-R5 are scratch registers
+and must not be used to store the data across BPF_ABS | BPF_LD or
+BPF_IND | BPF_LD instructions.
+
+These instructions have implicit program exit condition as well. When
+eBPF program is trying to access the data beyond the packet boundary,
+the interpreter will abort the execution of the program. JIT compilers
+therefore must preserve this property. src_reg and imm32 fields are
+explicit inputs to these instructions.
+
+For example:
+
+  BPF_IND | BPF_W | BPF_LD means:
+
+    R0 = ntohl(*(u32 *) (((struct sk_buff *) R6)->data + src_reg + imm32))
+    and R1 - R5 were scratched.
+
+Unlike classic BPF instruction set, eBPF has generic load/store operations:
+
+BPF_MEM | <size> | BPF_STX:  *(size *) (dst_reg + off) = src_reg
+BPF_MEM | <size> | BPF_ST:   *(size *) (dst_reg + off) = imm32
+BPF_MEM | <size> | BPF_LDX:  dst_reg = *(size *) (src_reg + off)
+BPF_XADD | BPF_W  | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg
+BPF_XADD | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg
+
+Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. Note that 1 and
+2 byte atomic increments are not supported.
+
+Testing
+-------
+
+Next to the BPF toolchain, the kernel also ships a test module that contains
+various test cases for classic and internal BPF that can be executed against
+the BPF interpreter and JIT compiler. It can be found in lib/test_bpf.c and
+enabled via Kconfig:
+
+  CONFIG_TEST_BPF=m
+
+After the module has been built and installed, the test suite can be executed
+via insmod or modprobe against 'test_bpf' module. Results of the test cases
+including timings in nsec can be found in the kernel log (dmesg).
+
 Misc
 ----
 
diff --git a/Documentation/platform/x86-laptop-drivers.txt b/Documentation/platform/x86-laptop-drivers.txt
new file mode 100644
index 00000000000..01facd2590b
--- /dev/null
+++ b/Documentation/platform/x86-laptop-drivers.txt
@@ -0,0 +1,18 @@
+compal-laptop
+=============
+List of supported hardware:
+
+by Compal:
+	Compal FL90/IFL90
+	Compal FL91/IFL91
+	Compal FL92/JFL92
+	Compal FT00/IFT00
+
+by Dell:
+	Dell Vostro 1200
+	Dell Mini 9 (Inspiron 910)
+	Dell Mini 10 (Inspiron 1010)
+	Dell Mini 10v (Inspiron 1011)
+	Dell Mini 1012 (Inspiron 1012)
+	Dell Inspiron 11z (Inspiron 1110)
+	Dell Mini 12 (Inspiron 1210)
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
index e13dafc8e8f..2850df3bf95 100644
--- a/Documentation/power/suspend-and-cpuhotplug.txt
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -1,6 +1,6 @@
 Interaction of Suspend code (S3) with the CPU hotplug infrastructure
 
-     (C) 2011 Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
+     (C) 2011 - 2014 Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
 
 
 I. How does the regular CPU hotplug code differ from how the Suspend-to-RAM
diff --git a/Documentation/powerpc/cpu_families.txt b/Documentation/powerpc/cpu_families.txt
new file mode 100644
index 00000000000..fc08e22feb1
--- /dev/null
+++ b/Documentation/powerpc/cpu_families.txt
@@ -0,0 +1,221 @@
+CPU Families
+============
+
+This document tries to summarise some of the different cpu families that exist
+and are supported by arch/powerpc.
+
+
+Book3S (aka sPAPR)
+------------------
+
+ - Hash MMU
+ - Mix of 32 & 64 bit
+
+   +--------------+                 +----------------+
+   |  Old POWER   | --------------> | RS64 (threads) |
+   +--------------+                 +----------------+
+          |
+          |
+          v
+   +--------------+                 +----------------+      +------+
+   |     601      | --------------> |      603       | ---> | e300 |
+   +--------------+                 +----------------+      +------+
+          |                                 |
+          |                                 |
+          v                                 v
+   +--------------+                 +----------------+      +-------+
+   |     604      |                 |    750 (G3)    | ---> | 750CX |
+   +--------------+                 +----------------+      +-------+
+          |                                 |                   |
+          |                                 |                   |
+          v                                 v                   v
+   +--------------+                 +----------------+      +-------+
+   | 620 (64 bit) |                 |      7400      |      | 750CL |
+   +--------------+                 +----------------+      +-------+
+          |                                 |                   |
+          |                                 |                   |
+          v                                 v                   v
+   +--------------+                 +----------------+      +-------+
+   |  POWER3/630  |                 |      7410      |      | 750FX |
+   +--------------+                 +----------------+      +-------+
+          |                                 |
+          |                                 |
+          v                                 v
+   +--------------+                 +----------------+
+   |   POWER3+    |                 |      7450      |
+   +--------------+                 +----------------+
+          |                                 |
+          |                                 |
+          v                                 v
+   +--------------+                 +----------------+
+   |    POWER4    |                 |      7455      |
+   +--------------+                 +----------------+
+          |                                 |
+          |                                 |
+          v                                 v
+   +--------------+     +-------+   +----------------+
+   |   POWER4+    | --> |  970  |   |      7447      |
+   +--------------+     +-------+   +----------------+
+          |                 |               |
+          |                 |               |
+          v                 v               v
+   +--------------+     +-------+   +----------------+
+   |    POWER5    |     | 970FX |   |      7448      |
+   +--------------+     +-------+   +----------------+
+          |                 |               |
+          |                 |               |
+          v                 v               v
+   +--------------+     +-------+   +----------------+
+   |   POWER5+    |     | 970MP |   |      e600      |
+   +--------------+     +-------+   +----------------+
+          |
+          |
+          v
+   +--------------+
+   |   POWER5++   |
+   +--------------+
+          |
+          |
+          v
+   +--------------+       +-------+
+   |    POWER6    | <-?-> | Cell  |
+   +--------------+       +-------+
+          |
+          |
+          v
+   +--------------+
+   |    POWER7    |
+   +--------------+
+          |
+          |
+          v
+   +--------------+
+   |   POWER7+    |
+   +--------------+
+          |
+          |
+          v
+   +--------------+
+   |    POWER8    |
+   +--------------+
+
+
+   +---------------+
+   | PA6T (64 bit) |
+   +---------------+
+
+
+IBM BookE
+---------
+
+ - Software loaded TLB.
+ - All 32 bit
+
+   +--------------+
+   |     401      |
+   +--------------+
+          |
+          |
+          v
+   +--------------+
+   |     403      |
+   +--------------+
+          |
+          |
+          v
+   +--------------+
+   |     405      |
+   +--------------+
+          |
+          |
+          v
+   +--------------+
+   |     440      |
+   +--------------+
+          |
+          |
+          v
+   +--------------+     +----------------+
+   |     450      | --> |      BG/P      |
+   +--------------+     +----------------+
+          |
+          |
+          v
+   +--------------+
+   |     460      |
+   +--------------+
+          |
+          |
+          v
+   +--------------+
+   |     476      |
+   +--------------+
+
+
+Motorola/Freescale 8xx
+----------------------
+
+ - Software loaded with hardware assist.
+ - All 32 bit
+
+   +-------------+
+   | MPC8xx Core |
+   +-------------+
+
+
+Freescale BookE
+---------------
+
+ - Software loaded TLB.
+ - e6500 adds HW loaded indirect TLB entries.
+ - Mix of 32 & 64 bit
+
+   +--------------+
+   |     e200     |
+   +--------------+
+
+
+   +--------------------------------+
+   |              e500              |
+   +--------------------------------+
+                   |
+                   |
+                   v
+   +--------------------------------+
+   |             e500v2             |
+   +--------------------------------+
+                   |
+                   |
+                   v
+   +--------------------------------+
+   |        e500mc (Book3e)         |
+   +--------------------------------+
+                   |
+                   |
+                   v
+   +--------------------------------+
+   |          e5500 (64 bit)        |
+   +--------------------------------+
+                   |
+                   |
+                   v
+   +--------------------------------+
+   | e6500 (HW TLB) (Multithreaded) |
+   +--------------------------------+
+
+
+IBM A2 core
+-----------
+
+ - Book3E, software loaded TLB + HW loaded indirect TLB entries.
+ - 64 bit
+
+   +--------------+     +----------------+
+   |   A2 core    | --> |      WSP       |
+   +--------------+     +----------------+
+           |
+           |
+           v
+   +--------------+
+   |     BG/Q     |
+   +--------------+
diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c
index f1ac2dae999..ba1d50200c4 100644
--- a/Documentation/ptp/testptp.c
+++ b/Documentation/ptp/testptp.c
@@ -17,6 +17,7 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
+#define _GNU_SOURCE
 #include <errno.h>
 #include <fcntl.h>
 #include <inttypes.h>
@@ -46,12 +47,14 @@
 #define CLOCK_INVALID -1
 #endif
 
-/* When glibc offers the syscall, this will go away. */
+/* clock_adjtime is not available in GLIBC < 2.14 */
+#if !__GLIBC_PREREQ(2, 14)
 #include <sys/syscall.h>
 static int clock_adjtime(clockid_t id, struct timex *tx)
 {
 	return syscall(__NR_clock_adjtime, id, tx);
 }
+#endif
 
 static clockid_t get_clockid(int fd)
 {
diff --git a/Documentation/pwm.txt b/Documentation/pwm.txt
index 93cb9797498..ca895fd211e 100644
--- a/Documentation/pwm.txt
+++ b/Documentation/pwm.txt
@@ -19,7 +19,8 @@ should instead register a static mapping that can be used to match PWM
 consumers to providers, as given in the following example:
 
 	static struct pwm_lookup board_pwm_lookup[] = {
-		PWM_LOOKUP("tegra-pwm", 0, "pwm-backlight", NULL),
+		PWM_LOOKUP("tegra-pwm", 0, "pwm-backlight", NULL,
+			   50000, PWM_POLARITY_NORMAL),
 	};
 
 	static void __init board_init(void)
@@ -97,6 +98,13 @@ pwm_chip as argument which provides a description of the PWM chip, the
 number of PWM devices provided by the chip and the chip-specific
 implementation of the supported PWM operations to the framework.
 
+When implementing polarity support in a PWM driver, make sure to respect the
+signal conventions in the PWM framework. By definition, normal polarity
+characterizes a signal starts high for the duration of the duty cycle and
+goes low for the remainder of the period. Conversely, a signal with inversed
+polarity starts low for the duration of the duty cycle and goes high for the
+remainder of the period.
+
 Locking
 -------
 
diff --git a/Documentation/scsi/LICENSE.qla2xxx b/Documentation/scsi/LICENSE.qla2xxx
index 5020b7b5a24..52f0b435923 100644
--- a/Documentation/scsi/LICENSE.qla2xxx
+++ b/Documentation/scsi/LICENSE.qla2xxx
@@ -1,4 +1,4 @@
-Copyright (c) 2003-2013 QLogic Corporation
+Copyright (c) 2003-2014 QLogic Corporation
 QLogic Linux FC-FCoE Driver
 
 This program includes a device driver for Linux 3.x.
diff --git a/Documentation/security/Smack.txt b/Documentation/security/Smack.txt
index 5ea996f21d6..b6ef7e9dba3 100644
--- a/Documentation/security/Smack.txt
+++ b/Documentation/security/Smack.txt
@@ -204,6 +204,16 @@ onlycap
 	these capabilities are effective at for processes with any
 	label. The value is set by writing the desired label to the
 	file or cleared by writing "-" to the file.
+ptrace
+	This is used to define the current ptrace policy
+	0 - default: this is the policy that relies on smack access rules.
+	    For the PTRACE_READ a subject needs to have a read access on
+	    object. For the PTRACE_ATTACH a read-write access is required.
+	1 - exact: this is the policy that limits PTRACE_ATTACH. Attach is
+	    only allowed when subject's and object's labels are equal.
+	    PTRACE_READ is not affected. Can be overriden with CAP_SYS_PTRACE.
+	2 - draconian: this policy behaves like the 'exact' above with an
+	    exception that it can't be overriden with CAP_SYS_PTRACE.
 revoke-subject
 	Writing a Smack label here sets the access to '-' for all access
 	rules with that subject label.
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index 85c362d8ea3..d1ab5e17eb1 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -286,6 +286,11 @@ STAC92HD83*
   hp-inv-led	HP with broken BIOS for inverted mute LED
   auto		BIOS setup (default)
 
+STAC92HD95
+==========
+  hp-led	LED support for HP laptops
+  hp-bass	Bass HPF setup for HP Spectre 13
+
 STAC9872
 ========
   vaio		VAIO laptop without SPDIF
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 708bb7f1b7e..c14374e7177 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -75,6 +75,7 @@ show up in /proc/sys/kernel:
 - shmall
 - shmmax                      [ sysv ipc ]
 - shmmni
+- softlockup_all_cpu_backtrace
 - stop-a                      [ SPARC only ]
 - sysrq                       ==> Documentation/sysrq.txt
 - sysctl_writes_strict
@@ -783,6 +784,22 @@ via the /proc/sys interface:
 
 ==============================================================
 
+softlockup_all_cpu_backtrace:
+
+This value controls the soft lockup detector thread's behavior
+when a soft lockup condition is detected as to whether or not
+to gather further debug information. If enabled, each cpu will
+be issued an NMI and instructed to capture stack trace.
+
+This feature is only applicable for architectures which support
+NMI.
+
+0: do nothing. This is the default behavior.
+
+1: on detection capture more debug information.
+
+==============================================================
+
 tainted:
 
 Non-zero if the kernel has been tainted.  Numeric values, which
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index bd4b34c0373..4415aa91568 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -702,7 +702,8 @@ The batch value of each per cpu pagelist is also updated as a result.  It is
 set to pcp->high/4.  The upper limit of batch is (PAGE_SHIFT * 8)
 
 The initial value is zero.  Kernel does not use this value at boot time to set
-the high water marks for each per cpu page list.
+the high water marks for each per cpu page list.  If the user writes '0' to this
+sysctl, it will revert to this default behavior.
 
 ==============================================================
 
diff --git a/Documentation/thermal/nouveau_thermal b/Documentation/thermal/nouveau_thermal
index efceb7828f5..60bc29357ac 100644
--- a/Documentation/thermal/nouveau_thermal
+++ b/Documentation/thermal/nouveau_thermal
@@ -4,7 +4,7 @@ Kernel driver nouveau
 Supported chips:
 * NV43+
 
-Authors: Martin Peres (mupuf) <martin.peres@labri.fr>
+Authors: Martin Peres (mupuf) <martin.peres@free.fr>
 
 Description
 ---------
@@ -68,8 +68,9 @@ Your fan can be driven in different modes:
 
 NOTE: Be sure to use the manual mode if you want to drive the fan speed manually
 
-NOTE2: Not all fan management modes may be supported on all chipsets. We are
-working on it.
+NOTE2: When operating in manual mode outside the vbios-defined
+[PWM_min, PWM_max] range, the reported fan speed (RPM) may not be accurate
+depending on your hardware.
 
 Bug reports
 ---------
diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt
index 3f669b9e885..dd5f916b351 100644
--- a/Documentation/trace/ftrace-design.txt
+++ b/Documentation/trace/ftrace-design.txt
@@ -102,30 +102,6 @@ extern void mcount(void);
 EXPORT_SYMBOL(mcount);
 
 
-HAVE_FUNCTION_TRACE_MCOUNT_TEST
--------------------------------
-
-This is an optional optimization for the normal case when tracing is turned off
-in the system.  If you do not enable this Kconfig option, the common ftrace
-code will take care of doing the checking for you.
-
-To support this feature, you only need to check the function_trace_stop
-variable in the mcount function.  If it is non-zero, there is no tracing to be
-done at all, so you can return.
-
-This additional pseudo code would simply be:
-void mcount(void)
-{
-	/* save any bare state needed in order to do initial checking */
-
-+	if (function_trace_stop)
-+		return;
-
-	extern void (*ftrace_trace_function)(unsigned long, unsigned long);
-	if (ftrace_trace_function != ftrace_stub)
-...
-
-
 HAVE_FUNCTION_GRAPH_TRACER
 --------------------------
 
@@ -328,8 +304,6 @@ void mcount(void)
 
 void ftrace_caller(void)
 {
-	/* implement HAVE_FUNCTION_TRACE_MCOUNT_TEST if you desire */
-
 	/* save all state needed by the ABI (see paragraph above) */
 
 	unsigned long frompc = ...;
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index bd365988e8d..4da42616939 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -1515,7 +1515,7 @@ Doing the same with chrt -r 5 and function-trace set.
   <idle>-0       3d.h4    1us+:      0:120:R   + [003]  2448: 94:R sleep
   <idle>-0       3d.h4    2us : ttwu_do_activate.constprop.87 <-try_to_wake_up
   <idle>-0       3d.h3    3us : check_preempt_curr <-ttwu_do_wakeup
-  <idle>-0       3d.h3    3us : resched_task <-check_preempt_curr
+  <idle>-0       3d.h3    3us : resched_curr <-check_preempt_curr
   <idle>-0       3dNh3    4us : task_woken_rt <-ttwu_do_wakeup
   <idle>-0       3dNh3    4us : _raw_spin_unlock <-try_to_wake_up
   <idle>-0       3dNh3    4us : sub_preempt_count <-_raw_spin_unlock
@@ -2003,6 +2003,32 @@ want, depending on your needs.
   360.774530 |   1)   0.594 us    |                                          __phys_addr();
 
 
+The function name is always displayed after the closing bracket
+for a function if the start of that function is not in the
+trace buffer.
+
+Display of the function name after the closing bracket may be
+enabled for functions whose start is in the trace buffer,
+allowing easier searching with grep for function durations.
+It is default disabled.
+
+	hide: echo nofuncgraph-tail > trace_options
+	show: echo funcgraph-tail > trace_options
+
+  Example with nofuncgraph-tail (default):
+  0)               |      putname() {
+  0)               |        kmem_cache_free() {
+  0)   0.518 us    |          __phys_addr();
+  0)   1.757 us    |        }
+  0)   2.861 us    |      }
+
+  Example with funcgraph-tail:
+  0)               |      putname() {
+  0)               |        kmem_cache_free() {
+  0)   0.518 us    |          __phys_addr();
+  0)   1.757 us    |        } /* kmem_cache_free() */
+  0)   2.861 us    |      } /* putname() */
+
 You can put some comments on specific functions by using
 trace_printk() For example, if you want to put a comment inside
 the __might_sleep() function, you just have to include
diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
index 00e425faa2f..78c9a7b2b58 100644
--- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
+++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
@@ -47,7 +47,6 @@ use constant HIGH_KSWAPD_REWAKEUP		=> 21;
 use constant HIGH_NR_SCANNED			=> 22;
 use constant HIGH_NR_TAKEN			=> 23;
 use constant HIGH_NR_RECLAIMED			=> 24;
-use constant HIGH_NR_CONTIG_DIRTY		=> 25;
 
 my %perprocesspid;
 my %perprocess;
@@ -105,7 +104,7 @@ my $regex_direct_end_default = 'nr_reclaimed=([0-9]*)';
 my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)';
 my $regex_kswapd_sleep_default = 'nid=([0-9]*)';
 my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*)';
-my $regex_lru_isolate_default = 'isolate_mode=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_taken=([0-9]*) contig_taken=([0-9]*) contig_dirty=([0-9]*) contig_failed=([0-9]*)';
+my $regex_lru_isolate_default = 'isolate_mode=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_taken=([0-9]*) file=([0-9]*)';
 my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) zid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)';
 my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_rotated=([0-9]*) priority=([0-9]*)';
 my $regex_writepage_default = 'page=([0-9a-f]*) pfn=([0-9]*) flags=([A-Z_|]*)';
@@ -200,7 +199,7 @@ $regex_lru_isolate = generate_traceevent_regex(
 			$regex_lru_isolate_default,
 			"isolate_mode", "order",
 			"nr_requested", "nr_scanned", "nr_taken",
-			"contig_taken", "contig_dirty", "contig_failed");
+			"file");
 $regex_lru_shrink_inactive = generate_traceevent_regex(
 			"vmscan/mm_vmscan_lru_shrink_inactive",
 			$regex_lru_shrink_inactive_default,
@@ -375,7 +374,6 @@ EVENT_PROCESS:
 			}
 			my $isolate_mode = $1;
 			my $nr_scanned = $4;
-			my $nr_contig_dirty = $7;
 
 			# To closer match vmstat scanning statistics, only count isolate_both
 			# and isolate_inactive as scanning. isolate_active is rotation
@@ -385,7 +383,6 @@ EVENT_PROCESS:
 			if ($isolate_mode != 2) {
 				$perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
 			}
-			$perprocesspid{$process_pid}->{HIGH_NR_CONTIG_DIRTY} += $nr_contig_dirty;
 		} elsif ($tracepoint eq "mm_vmscan_lru_shrink_inactive") {
 			$details = $6;
 			if ($details !~ /$regex_lru_shrink_inactive/o) {
@@ -539,13 +536,6 @@ sub dump_stats {
 				}
 			}
 		}
-		if ($stats{$process_pid}->{HIGH_NR_CONTIG_DIRTY}) {
-			print "      ";
-			my $count = $stats{$process_pid}->{HIGH_NR_CONTIG_DIRTY};
-			if ($count != 0) {
-				print "contig-dirty=$count ";
-			}
-		}
 
 		print "\n";
 	}
diff --git a/Documentation/trace/tracepoints.txt b/Documentation/trace/tracepoints.txt
index 6b018b53177..a3efac621c5 100644
--- a/Documentation/trace/tracepoints.txt
+++ b/Documentation/trace/tracepoints.txt
@@ -115,6 +115,30 @@ If the tracepoint has to be used in kernel modules, an
 EXPORT_TRACEPOINT_SYMBOL_GPL() or EXPORT_TRACEPOINT_SYMBOL() can be
 used to export the defined tracepoints.
 
+If you need to do a bit of work for a tracepoint parameter, and
+that work is only used for the tracepoint, that work can be encapsulated
+within an if statement with the following:
+
+	if (trace_foo_bar_enabled()) {
+		int i;
+		int tot = 0;
+
+		for (i = 0; i < count; i++)
+			tot += calculate_nuggets();
+
+		trace_foo_bar(tot);
+	}
+
+All trace_<tracepoint>() calls have a matching trace_<tracepoint>_enabled()
+function defined that returns true if the tracepoint is enabled and
+false otherwise. The trace_<tracepoint>() should always be within the
+block of the if (trace_<tracepoint>_enabled()) to prevent races between
+the tracepoint being enabled and the check being seen.
+
+The advantage of using the trace_<tracepoint>_enabled() is that it uses
+the static_key of the tracepoint to allow the if statement to be implemented
+with jump labels and avoid conditional branches.
+
 Note: The convenience macro TRACE_EVENT provides an alternative way to
       define tracepoints. Check http://lwn.net/Articles/379903,
       http://lwn.net/Articles/381064 and http://lwn.net/Articles/383362
diff --git a/Documentation/vDSO/parse_vdso.c b/Documentation/vDSO/parse_vdso.c
index 85870208edc..1dbb4b87268 100644
--- a/Documentation/vDSO/parse_vdso.c
+++ b/Documentation/vDSO/parse_vdso.c
@@ -1,6 +1,6 @@
 /*
  * parse_vdso.c: Linux reference vDSO parser
- * Written by Andrew Lutomirski, 2011.
+ * Written by Andrew Lutomirski, 2011-2014.
  *
  * This code is meant to be linked in to various programs that run on Linux.
  * As such, it is available with as few restrictions as possible.  This file
@@ -11,13 +11,14 @@
  * it starts a program.  It works equally well in statically and dynamically
  * linked binaries.
  *
- * This code is tested on x86_64.  In principle it should work on any 64-bit
+ * This code is tested on x86.  In principle it should work on any
  * architecture that has a vDSO.
  */
 
 #include <stdbool.h>
 #include <stdint.h>
 #include <string.h>
+#include <limits.h>
 #include <elf.h>
 
 /*
@@ -45,11 +46,18 @@ extern void *vdso_sym(const char *version, const char *name);
 
 
 /* And here's the code. */
-
-#ifndef __x86_64__
-# error Not yet ported to non-x86_64 architectures
+#ifndef ELF_BITS
+# if ULONG_MAX > 0xffffffffUL
+#  define ELF_BITS 64
+# else
+#  define ELF_BITS 32
+# endif
 #endif
 
+#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x
+#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
+#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x)
+
 static struct vdso_info
 {
 	bool valid;
@@ -59,14 +67,14 @@ static struct vdso_info
 	uintptr_t load_offset;  /* load_addr - recorded vaddr */
 
 	/* Symbol table */
-	Elf64_Sym *symtab;
+	ELF(Sym) *symtab;
 	const char *symstrings;
-	Elf64_Word *bucket, *chain;
-	Elf64_Word nbucket, nchain;
+	ELF(Word) *bucket, *chain;
+	ELF(Word) nbucket, nchain;
 
 	/* Version table */
-	Elf64_Versym *versym;
-	Elf64_Verdef *verdef;
+	ELF(Versym) *versym;
+	ELF(Verdef) *verdef;
 } vdso_info;
 
 /* Straight from the ELF specification. */
@@ -92,9 +100,14 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
 
 	vdso_info.load_addr = base;
 
-	Elf64_Ehdr *hdr = (Elf64_Ehdr*)base;
-	Elf64_Phdr *pt = (Elf64_Phdr*)(vdso_info.load_addr + hdr->e_phoff);
-	Elf64_Dyn *dyn = 0;
+	ELF(Ehdr) *hdr = (ELF(Ehdr)*)base;
+	if (hdr->e_ident[EI_CLASS] !=
+	    (ELF_BITS == 32 ? ELFCLASS32 : ELFCLASS64)) {
+		return;  /* Wrong ELF class -- check ELF_BITS */
+	}
+
+	ELF(Phdr) *pt = (ELF(Phdr)*)(vdso_info.load_addr + hdr->e_phoff);
+	ELF(Dyn) *dyn = 0;
 
 	/*
 	 * We need two things from the segment table: the load offset
@@ -108,7 +121,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
 				+ (uintptr_t)pt[i].p_offset
 				- (uintptr_t)pt[i].p_vaddr;
 		} else if (pt[i].p_type == PT_DYNAMIC) {
-			dyn = (Elf64_Dyn*)(base + pt[i].p_offset);
+			dyn = (ELF(Dyn)*)(base + pt[i].p_offset);
 		}
 	}
 
@@ -118,7 +131,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
 	/*
 	 * Fish out the useful bits of the dynamic table.
 	 */
-	Elf64_Word *hash = 0;
+	ELF(Word) *hash = 0;
 	vdso_info.symstrings = 0;
 	vdso_info.symtab = 0;
 	vdso_info.versym = 0;
@@ -131,22 +144,22 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
 				 + vdso_info.load_offset);
 			break;
 		case DT_SYMTAB:
-			vdso_info.symtab = (Elf64_Sym *)
+			vdso_info.symtab = (ELF(Sym) *)
 				((uintptr_t)dyn[i].d_un.d_ptr
 				 + vdso_info.load_offset);
 			break;
 		case DT_HASH:
-			hash = (Elf64_Word *)
+			hash = (ELF(Word) *)
 				((uintptr_t)dyn[i].d_un.d_ptr
 				 + vdso_info.load_offset);
 			break;
 		case DT_VERSYM:
-			vdso_info.versym = (Elf64_Versym *)
+			vdso_info.versym = (ELF(Versym) *)
 				((uintptr_t)dyn[i].d_un.d_ptr
 				 + vdso_info.load_offset);
 			break;
 		case DT_VERDEF:
-			vdso_info.verdef = (Elf64_Verdef *)
+			vdso_info.verdef = (ELF(Verdef) *)
 				((uintptr_t)dyn[i].d_un.d_ptr
 				 + vdso_info.load_offset);
 			break;
@@ -168,8 +181,8 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
 	vdso_info.valid = true;
 }
 
-static bool vdso_match_version(Elf64_Versym ver,
-			       const char *name, Elf64_Word hash)
+static bool vdso_match_version(ELF(Versym) ver,
+			       const char *name, ELF(Word) hash)
 {
 	/*
 	 * This is a helper function to check if the version indexed by
@@ -188,7 +201,7 @@ static bool vdso_match_version(Elf64_Versym ver,
 
 	/* First step: find the version definition */
 	ver &= 0x7fff;  /* Apparently bit 15 means "hidden" */
-	Elf64_Verdef *def = vdso_info.verdef;
+	ELF(Verdef) *def = vdso_info.verdef;
 	while(true) {
 		if ((def->vd_flags & VER_FLG_BASE) == 0
 		    && (def->vd_ndx & 0x7fff) == ver)
@@ -197,11 +210,11 @@ static bool vdso_match_version(Elf64_Versym ver,
 		if (def->vd_next == 0)
 			return false;  /* No definition. */
 
-		def = (Elf64_Verdef *)((char *)def + def->vd_next);
+		def = (ELF(Verdef) *)((char *)def + def->vd_next);
 	}
 
 	/* Now figure out whether it matches. */
-	Elf64_Verdaux *aux = (Elf64_Verdaux*)((char *)def + def->vd_aux);
+	ELF(Verdaux) *aux = (ELF(Verdaux)*)((char *)def + def->vd_aux);
 	return def->vd_hash == hash
 		&& !strcmp(name, vdso_info.symstrings + aux->vda_name);
 }
@@ -213,10 +226,10 @@ void *vdso_sym(const char *version, const char *name)
 		return 0;
 
 	ver_hash = elf_hash(version);
-	Elf64_Word chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket];
+	ELF(Word) chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket];
 
 	for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) {
-		Elf64_Sym *sym = &vdso_info.symtab[chain];
+		ELF(Sym) *sym = &vdso_info.symtab[chain];
 
 		/* Check for a defined global or weak function w/ right name. */
 		if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
@@ -243,7 +256,7 @@ void *vdso_sym(const char *version, const char *name)
 
 void vdso_init_from_auxv(void *auxv)
 {
-	Elf64_auxv_t *elf_auxv = auxv;
+	ELF(auxv_t) *elf_auxv = auxv;
 	for (int i = 0; elf_auxv[i].a_type != AT_NULL; i++)
 	{
 		if (elf_auxv[i].a_type == AT_SYSINFO_EHDR) {
diff --git a/Documentation/vDSO/vdso_standalone_test_x86.c b/Documentation/vDSO/vdso_standalone_test_x86.c
new file mode 100644
index 00000000000..d46240265c5
--- /dev/null
+++ b/Documentation/vDSO/vdso_standalone_test_x86.c
@@ -0,0 +1,128 @@
+/*
+ * vdso_test.c: Sample code to test parse_vdso.c on x86
+ * Copyright (c) 2011-2014 Andy Lutomirski
+ * Subject to the GNU General Public License, version 2
+ *
+ * You can amuse yourself by compiling with:
+ * gcc -std=gnu99 -nostdlib
+ *     -Os -fno-asynchronous-unwind-tables -flto -lgcc_s
+ *      vdso_standalone_test_x86.c parse_vdso.c
+ * to generate a small binary.  On x86_64, you can omit -lgcc_s
+ * if you want the binary to be completely standalone.
+ */
+
+#include <sys/syscall.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <stdint.h>
+
+extern void *vdso_sym(const char *version, const char *name);
+extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
+extern void vdso_init_from_auxv(void *auxv);
+
+/* We need a libc functions... */
+int strcmp(const char *a, const char *b)
+{
+	/* This implementation is buggy: it never returns -1. */
+	while (*a || *b) {
+		if (*a != *b)
+			return 1;
+		if (*a == 0 || *b == 0)
+			return 1;
+		a++;
+		b++;
+	}
+
+	return 0;
+}
+
+/* ...and two syscalls.  This is x86-specific. */
+static inline long x86_syscall3(long nr, long a0, long a1, long a2)
+{
+	long ret;
+#ifdef __x86_64__
+	asm volatile ("syscall" : "=a" (ret) : "a" (nr),
+		      "D" (a0), "S" (a1), "d" (a2) :
+		      "cc", "memory", "rcx",
+		      "r8", "r9", "r10", "r11" );
+#else
+	asm volatile ("int $0x80" : "=a" (ret) : "a" (nr),
+		      "b" (a0), "c" (a1), "d" (a2) :
+		      "cc", "memory" );
+#endif
+	return ret;
+}
+
+static inline long linux_write(int fd, const void *data, size_t len)
+{
+	return x86_syscall3(__NR_write, fd, (long)data, (long)len);
+}
+
+static inline void linux_exit(int code)
+{
+	x86_syscall3(__NR_exit, code, 0, 0);
+}
+
+void to_base10(char *lastdig, uint64_t n)
+{
+	while (n) {
+		*lastdig = (n % 10) + '0';
+		n /= 10;
+		lastdig--;
+	}
+}
+
+__attribute__((externally_visible)) void c_main(void **stack)
+{
+	/* Parse the stack */
+	long argc = (long)*stack;
+	stack += argc + 2;
+
+	/* Now we're pointing at the environment.  Skip it. */
+	while(*stack)
+		stack++;
+	stack++;
+
+	/* Now we're pointing at auxv.  Initialize the vDSO parser. */
+	vdso_init_from_auxv((void *)stack);
+
+	/* Find gettimeofday. */
+	typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);
+	gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
+
+	if (!gtod)
+		linux_exit(1);
+
+	struct timeval tv;
+	long ret = gtod(&tv, 0);
+
+	if (ret == 0) {
+		char buf[] = "The time is                     .000000\n";
+		to_base10(buf + 31, tv.tv_sec);
+		to_base10(buf + 38, tv.tv_usec);
+		linux_write(1, buf, sizeof(buf) - 1);
+	} else {
+		linux_exit(ret);
+	}
+
+	linux_exit(0);
+}
+
+/*
+ * This is the real entry point.  It passes the initial stack into
+ * the C entry point.
+ */
+asm (
+	".text\n"
+	".global _start\n"
+	".type _start,@function\n"
+	"_start:\n\t"
+#ifdef __x86_64__
+	"mov %rsp,%rdi\n\t"
+	"jmp c_main"
+#else
+	"push %esp\n\t"
+	"call c_main\n\t"
+	"int $3"
+#endif
+	);
diff --git a/Documentation/vDSO/vdso_test.c b/Documentation/vDSO/vdso_test.c
index fff633432df..8daeb7d7032 100644
--- a/Documentation/vDSO/vdso_test.c
+++ b/Documentation/vDSO/vdso_test.c
@@ -1,111 +1,52 @@
 /*
- * vdso_test.c: Sample code to test parse_vdso.c on x86_64
- * Copyright (c) 2011 Andy Lutomirski
+ * vdso_test.c: Sample code to test parse_vdso.c
+ * Copyright (c) 2014 Andy Lutomirski
  * Subject to the GNU General Public License, version 2
  *
- * You can amuse yourself by compiling with:
- * gcc -std=gnu99 -nostdlib
- *     -Os -fno-asynchronous-unwind-tables -flto
- *      vdso_test.c parse_vdso.c -o vdso_test
- * to generate a small binary with no dependencies at all.
+ * Compile with:
+ * gcc -std=gnu99 vdso_test.c parse_vdso.c
+ *
+ * Tested on x86, 32-bit and 64-bit.  It may work on other architectures, too.
  */
 
-#include <sys/syscall.h>
-#include <sys/time.h>
-#include <unistd.h>
 #include <stdint.h>
+#include <elf.h>
+#include <stdio.h>
+#include <sys/auxv.h>
+#include <sys/time.h>
 
 extern void *vdso_sym(const char *version, const char *name);
 extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
 extern void vdso_init_from_auxv(void *auxv);
 
-/* We need a libc functions... */
-int strcmp(const char *a, const char *b)
+int main(int argc, char **argv)
 {
-	/* This implementation is buggy: it never returns -1. */
-	while (*a || *b) {
-		if (*a != *b)
-			return 1;
-		if (*a == 0 || *b == 0)
-			return 1;
-		a++;
-		b++;
+	unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
+	if (!sysinfo_ehdr) {
+		printf("AT_SYSINFO_EHDR is not present!\n");
+		return 0;
 	}
 
-	return 0;
-}
-
-/* ...and two syscalls.  This is x86_64-specific. */
-static inline long linux_write(int fd, const void *data, size_t len)
-{
-
-	long ret;
-	asm volatile ("syscall" : "=a" (ret) : "a" (__NR_write),
-		      "D" (fd), "S" (data), "d" (len) :
-		      "cc", "memory", "rcx",
-		      "r8", "r9", "r10", "r11" );
-	return ret;
-}
-
-static inline void linux_exit(int code)
-{
-	asm volatile ("syscall" : : "a" (__NR_exit), "D" (code));
-}
-
-void to_base10(char *lastdig, uint64_t n)
-{
-	while (n) {
-		*lastdig = (n % 10) + '0';
-		n /= 10;
-		lastdig--;
-	}
-}
-
-__attribute__((externally_visible)) void c_main(void **stack)
-{
-	/* Parse the stack */
-	long argc = (long)*stack;
-	stack += argc + 2;
-
-	/* Now we're pointing at the environment.  Skip it. */
-	while(*stack)
-		stack++;
-	stack++;
-
-	/* Now we're pointing at auxv.  Initialize the vDSO parser. */
-	vdso_init_from_auxv((void *)stack);
+	vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
 
 	/* Find gettimeofday. */
 	typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);
 	gtod_t gtod = (gtod_t)vdso_sym("LINUX_2.6", "__vdso_gettimeofday");
 
-	if (!gtod)
-		linux_exit(1);
+	if (!gtod) {
+		printf("Could not find __vdso_gettimeofday\n");
+		return 1;
+	}
 
 	struct timeval tv;
 	long ret = gtod(&tv, 0);
 
 	if (ret == 0) {
-		char buf[] = "The time is                     .000000\n";
-		to_base10(buf + 31, tv.tv_sec);
-		to_base10(buf + 38, tv.tv_usec);
-		linux_write(1, buf, sizeof(buf) - 1);
+		printf("The time is %lld.%06lld\n",
+		       (long long)tv.tv_sec, (long long)tv.tv_usec);
 	} else {
-		linux_exit(ret);
+		printf("__vdso_gettimeofday failed\n");
 	}
 
-	linux_exit(0);
+	return 0;
 }
-
-/*
- * This is the real entry point.  It passes the initial stack into
- * the C entry point.
- */
-asm (
-	".text\n"
-	".global _start\n"
-        ".type _start,@function\n"
-        "_start:\n\t"
-        "mov %rsp,%rdi\n\t"
-        "jmp c_main"
-	);
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 0fe36497642..68cda1fc3d5 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -297,6 +297,15 @@ struct kvm_regs {
 	__u64 rip, rflags;
 };
 
+/* mips */
+struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 gpr[32];
+	__u64 hi;
+	__u64 lo;
+	__u64 pc;
+};
+
 
 4.12 KVM_SET_REGS
 
@@ -378,7 +387,7 @@ struct kvm_translation {
 4.16 KVM_INTERRUPT
 
 Capability: basic
-Architectures: x86, ppc
+Architectures: x86, ppc, mips
 Type: vcpu ioctl
 Parameters: struct kvm_interrupt (in)
 Returns: 0 on success, -1 on error
@@ -423,6 +432,11 @@ c) KVM_INTERRUPT_SET_LEVEL
 Note that any value for 'irq' other than the ones stated above is invalid
 and incurs unexpected behavior.
 
+MIPS:
+
+Queues an external interrupt to be injected into the virtual CPU. A negative
+interrupt number dequeues the interrupt.
+
 
 4.17 KVM_DEBUG_GUEST
 
@@ -512,7 +526,7 @@ struct kvm_cpuid {
 4.21 KVM_SET_SIGNAL_MASK
 
 Capability: basic
-Architectures: x86
+Architectures: all
 Type: vcpu ioctl
 Parameters: struct kvm_signal_mask (in)
 Returns: 0 on success, -1 on error
@@ -974,7 +988,7 @@ for vm-wide capabilities.
 4.38 KVM_GET_MP_STATE
 
 Capability: KVM_CAP_MP_STATE
-Architectures: x86, ia64
+Architectures: x86, ia64, s390
 Type: vcpu ioctl
 Parameters: struct kvm_mp_state (out)
 Returns: 0 on success; -1 on error
@@ -988,24 +1002,32 @@ uniprocessor guests).
 
 Possible values are:
 
- - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running
+ - KVM_MP_STATE_RUNNABLE:        the vcpu is currently running [x86, ia64]
  - KVM_MP_STATE_UNINITIALIZED:   the vcpu is an application processor (AP)
-                                 which has not yet received an INIT signal
+                                 which has not yet received an INIT signal [x86,
+                                 ia64]
  - KVM_MP_STATE_INIT_RECEIVED:   the vcpu has received an INIT signal, and is
-                                 now ready for a SIPI
+                                 now ready for a SIPI [x86, ia64]
  - KVM_MP_STATE_HALTED:          the vcpu has executed a HLT instruction and
-                                 is waiting for an interrupt
+                                 is waiting for an interrupt [x86, ia64]
  - KVM_MP_STATE_SIPI_RECEIVED:   the vcpu has just received a SIPI (vector
-                                 accessible via KVM_GET_VCPU_EVENTS)
+                                 accessible via KVM_GET_VCPU_EVENTS) [x86, ia64]
+ - KVM_MP_STATE_STOPPED:         the vcpu is stopped [s390]
+ - KVM_MP_STATE_CHECK_STOP:      the vcpu is in a special error state [s390]
+ - KVM_MP_STATE_OPERATING:       the vcpu is operating (running or halted)
+                                 [s390]
+ - KVM_MP_STATE_LOAD:            the vcpu is in a special load/startup state
+                                 [s390]
 
-This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
-irqchip, the multiprocessing state must be maintained by userspace.
+On x86 and ia64, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
 
 
 4.39 KVM_SET_MP_STATE
 
 Capability: KVM_CAP_MP_STATE
-Architectures: x86, ia64
+Architectures: x86, ia64, s390
 Type: vcpu ioctl
 Parameters: struct kvm_mp_state (in)
 Returns: 0 on success; -1 on error
@@ -1013,8 +1035,9 @@ Returns: 0 on success; -1 on error
 Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
 arguments.
 
-This ioctl is only useful after KVM_CREATE_IRQCHIP.  Without an in-kernel
-irqchip, the multiprocessing state must be maintained by userspace.
+On x86 and ia64, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
 
 
 4.40 KVM_SET_IDENTITY_MAP_ADDR
@@ -1774,122 +1797,151 @@ and architecture specific registers. Each have their own range of operation
 and their own constants and width. To keep track of the implemented
 registers, find a list below:
 
-  Arch  |       Register        | Width (bits)
-        |                       |
-  PPC   | KVM_REG_PPC_HIOR      | 64
-  PPC   | KVM_REG_PPC_IAC1      | 64
-  PPC   | KVM_REG_PPC_IAC2      | 64
-  PPC   | KVM_REG_PPC_IAC3      | 64
-  PPC   | KVM_REG_PPC_IAC4      | 64
-  PPC   | KVM_REG_PPC_DAC1      | 64
-  PPC   | KVM_REG_PPC_DAC2      | 64
-  PPC   | KVM_REG_PPC_DABR      | 64
-  PPC   | KVM_REG_PPC_DSCR      | 64
-  PPC   | KVM_REG_PPC_PURR      | 64
-  PPC   | KVM_REG_PPC_SPURR     | 64
-  PPC   | KVM_REG_PPC_DAR       | 64
-  PPC   | KVM_REG_PPC_DSISR     | 32
-  PPC   | KVM_REG_PPC_AMR       | 64
-  PPC   | KVM_REG_PPC_UAMOR     | 64
-  PPC   | KVM_REG_PPC_MMCR0     | 64
-  PPC   | KVM_REG_PPC_MMCR1     | 64
-  PPC   | KVM_REG_PPC_MMCRA     | 64
-  PPC   | KVM_REG_PPC_MMCR2     | 64
-  PPC   | KVM_REG_PPC_MMCRS     | 64
-  PPC   | KVM_REG_PPC_SIAR      | 64
-  PPC   | KVM_REG_PPC_SDAR      | 64
-  PPC   | KVM_REG_PPC_SIER      | 64
-  PPC   | KVM_REG_PPC_PMC1      | 32
-  PPC   | KVM_REG_PPC_PMC2      | 32
-  PPC   | KVM_REG_PPC_PMC3      | 32
-  PPC   | KVM_REG_PPC_PMC4      | 32
-  PPC   | KVM_REG_PPC_PMC5      | 32
-  PPC   | KVM_REG_PPC_PMC6      | 32
-  PPC   | KVM_REG_PPC_PMC7      | 32
-  PPC   | KVM_REG_PPC_PMC8      | 32
-  PPC   | KVM_REG_PPC_FPR0      | 64
+  Arch  |           Register            | Width (bits)
+        |                               |
+  PPC   | KVM_REG_PPC_HIOR              | 64
+  PPC   | KVM_REG_PPC_IAC1              | 64
+  PPC   | KVM_REG_PPC_IAC2              | 64
+  PPC   | KVM_REG_PPC_IAC3              | 64
+  PPC   | KVM_REG_PPC_IAC4              | 64
+  PPC   | KVM_REG_PPC_DAC1              | 64
+  PPC   | KVM_REG_PPC_DAC2              | 64
+  PPC   | KVM_REG_PPC_DABR              | 64
+  PPC   | KVM_REG_PPC_DSCR              | 64
+  PPC   | KVM_REG_PPC_PURR              | 64
+  PPC   | KVM_REG_PPC_SPURR             | 64
+  PPC   | KVM_REG_PPC_DAR               | 64
+  PPC   | KVM_REG_PPC_DSISR             | 32
+  PPC   | KVM_REG_PPC_AMR               | 64
+  PPC   | KVM_REG_PPC_UAMOR             | 64
+  PPC   | KVM_REG_PPC_MMCR0             | 64
+  PPC   | KVM_REG_PPC_MMCR1             | 64
+  PPC   | KVM_REG_PPC_MMCRA             | 64
+  PPC   | KVM_REG_PPC_MMCR2             | 64
+  PPC   | KVM_REG_PPC_MMCRS             | 64
+  PPC   | KVM_REG_PPC_SIAR              | 64
+  PPC   | KVM_REG_PPC_SDAR              | 64
+  PPC   | KVM_REG_PPC_SIER              | 64
+  PPC   | KVM_REG_PPC_PMC1              | 32
+  PPC   | KVM_REG_PPC_PMC2              | 32
+  PPC   | KVM_REG_PPC_PMC3              | 32
+  PPC   | KVM_REG_PPC_PMC4              | 32
+  PPC   | KVM_REG_PPC_PMC5              | 32
+  PPC   | KVM_REG_PPC_PMC6              | 32
+  PPC   | KVM_REG_PPC_PMC7              | 32
+  PPC   | KVM_REG_PPC_PMC8              | 32
+  PPC   | KVM_REG_PPC_FPR0              | 64
+          ...
+  PPC   | KVM_REG_PPC_FPR31             | 64
+  PPC   | KVM_REG_PPC_VR0               | 128
           ...
-  PPC   | KVM_REG_PPC_FPR31     | 64
-  PPC   | KVM_REG_PPC_VR0       | 128
+  PPC   | KVM_REG_PPC_VR31              | 128
+  PPC   | KVM_REG_PPC_VSR0              | 128
           ...
-  PPC   | KVM_REG_PPC_VR31      | 128
-  PPC   | KVM_REG_PPC_VSR0      | 128
+  PPC   | KVM_REG_PPC_VSR31             | 128
+  PPC   | KVM_REG_PPC_FPSCR             | 64
+  PPC   | KVM_REG_PPC_VSCR              | 32
+  PPC   | KVM_REG_PPC_VPA_ADDR          | 64
+  PPC   | KVM_REG_PPC_VPA_SLB           | 128
+  PPC   | KVM_REG_PPC_VPA_DTL           | 128
+  PPC   | KVM_REG_PPC_EPCR              | 32
+  PPC   | KVM_REG_PPC_EPR               | 32
+  PPC   | KVM_REG_PPC_TCR               | 32
+  PPC   | KVM_REG_PPC_TSR               | 32
+  PPC   | KVM_REG_PPC_OR_TSR            | 32
+  PPC   | KVM_REG_PPC_CLEAR_TSR         | 32
+  PPC   | KVM_REG_PPC_MAS0              | 32
+  PPC   | KVM_REG_PPC_MAS1              | 32
+  PPC   | KVM_REG_PPC_MAS2              | 64
+  PPC   | KVM_REG_PPC_MAS7_3            | 64
+  PPC   | KVM_REG_PPC_MAS4              | 32
+  PPC   | KVM_REG_PPC_MAS6              | 32
+  PPC   | KVM_REG_PPC_MMUCFG            | 32
+  PPC   | KVM_REG_PPC_TLB0CFG           | 32
+  PPC   | KVM_REG_PPC_TLB1CFG           | 32
+  PPC   | KVM_REG_PPC_TLB2CFG           | 32
+  PPC   | KVM_REG_PPC_TLB3CFG           | 32
+  PPC   | KVM_REG_PPC_TLB0PS            | 32
+  PPC   | KVM_REG_PPC_TLB1PS            | 32
+  PPC   | KVM_REG_PPC_TLB2PS            | 32
+  PPC   | KVM_REG_PPC_TLB3PS            | 32
+  PPC   | KVM_REG_PPC_EPTCFG            | 32
+  PPC   | KVM_REG_PPC_ICP_STATE         | 64
+  PPC   | KVM_REG_PPC_TB_OFFSET         | 64
+  PPC   | KVM_REG_PPC_SPMC1             | 32
+  PPC   | KVM_REG_PPC_SPMC2             | 32
+  PPC   | KVM_REG_PPC_IAMR              | 64
+  PPC   | KVM_REG_PPC_TFHAR             | 64
+  PPC   | KVM_REG_PPC_TFIAR             | 64
+  PPC   | KVM_REG_PPC_TEXASR            | 64
+  PPC   | KVM_REG_PPC_FSCR              | 64
+  PPC   | KVM_REG_PPC_PSPB              | 32
+  PPC   | KVM_REG_PPC_EBBHR             | 64
+  PPC   | KVM_REG_PPC_EBBRR             | 64
+  PPC   | KVM_REG_PPC_BESCR             | 64
+  PPC   | KVM_REG_PPC_TAR               | 64
+  PPC   | KVM_REG_PPC_DPDES             | 64
+  PPC   | KVM_REG_PPC_DAWR              | 64
+  PPC   | KVM_REG_PPC_DAWRX             | 64
+  PPC   | KVM_REG_PPC_CIABR             | 64
+  PPC   | KVM_REG_PPC_IC                | 64
+  PPC   | KVM_REG_PPC_VTB               | 64
+  PPC   | KVM_REG_PPC_CSIGR             | 64
+  PPC   | KVM_REG_PPC_TACR              | 64
+  PPC   | KVM_REG_PPC_TCSCR             | 64
+  PPC   | KVM_REG_PPC_PID               | 64
+  PPC   | KVM_REG_PPC_ACOP              | 64
+  PPC   | KVM_REG_PPC_VRSAVE            | 32
+  PPC   | KVM_REG_PPC_LPCR              | 64
+  PPC   | KVM_REG_PPC_PPR               | 64
+  PPC   | KVM_REG_PPC_ARCH_COMPAT       | 32
+  PPC   | KVM_REG_PPC_DABRX             | 32
+  PPC   | KVM_REG_PPC_WORT              | 64
+  PPC   | KVM_REG_PPC_TM_GPR0           | 64
           ...
-  PPC   | KVM_REG_PPC_VSR31     | 128
-  PPC   | KVM_REG_PPC_FPSCR     | 64
-  PPC   | KVM_REG_PPC_VSCR      | 32
-  PPC   | KVM_REG_PPC_VPA_ADDR  | 64
-  PPC   | KVM_REG_PPC_VPA_SLB   | 128
-  PPC   | KVM_REG_PPC_VPA_DTL   | 128
-  PPC   | KVM_REG_PPC_EPCR	| 32
-  PPC   | KVM_REG_PPC_EPR	| 32
-  PPC   | KVM_REG_PPC_TCR	| 32
-  PPC   | KVM_REG_PPC_TSR	| 32
-  PPC   | KVM_REG_PPC_OR_TSR	| 32
-  PPC   | KVM_REG_PPC_CLEAR_TSR	| 32
-  PPC   | KVM_REG_PPC_MAS0	| 32
-  PPC   | KVM_REG_PPC_MAS1	| 32
-  PPC   | KVM_REG_PPC_MAS2	| 64
-  PPC   | KVM_REG_PPC_MAS7_3	| 64
-  PPC   | KVM_REG_PPC_MAS4	| 32
-  PPC   | KVM_REG_PPC_MAS6	| 32
-  PPC   | KVM_REG_PPC_MMUCFG	| 32
-  PPC   | KVM_REG_PPC_TLB0CFG	| 32
-  PPC   | KVM_REG_PPC_TLB1CFG	| 32
-  PPC   | KVM_REG_PPC_TLB2CFG	| 32
-  PPC   | KVM_REG_PPC_TLB3CFG	| 32
-  PPC   | KVM_REG_PPC_TLB0PS	| 32
-  PPC   | KVM_REG_PPC_TLB1PS	| 32
-  PPC   | KVM_REG_PPC_TLB2PS	| 32
-  PPC   | KVM_REG_PPC_TLB3PS	| 32
-  PPC   | KVM_REG_PPC_EPTCFG	| 32
-  PPC   | KVM_REG_PPC_ICP_STATE | 64
-  PPC   | KVM_REG_PPC_TB_OFFSET	| 64
-  PPC   | KVM_REG_PPC_SPMC1	| 32
-  PPC   | KVM_REG_PPC_SPMC2	| 32
-  PPC   | KVM_REG_PPC_IAMR	| 64
-  PPC   | KVM_REG_PPC_TFHAR	| 64
-  PPC   | KVM_REG_PPC_TFIAR	| 64
-  PPC   | KVM_REG_PPC_TEXASR	| 64
-  PPC   | KVM_REG_PPC_FSCR	| 64
-  PPC   | KVM_REG_PPC_PSPB	| 32
-  PPC   | KVM_REG_PPC_EBBHR	| 64
-  PPC   | KVM_REG_PPC_EBBRR	| 64
-  PPC   | KVM_REG_PPC_BESCR	| 64
-  PPC   | KVM_REG_PPC_TAR	| 64
-  PPC   | KVM_REG_PPC_DPDES	| 64
-  PPC   | KVM_REG_PPC_DAWR	| 64
-  PPC   | KVM_REG_PPC_DAWRX	| 64
-  PPC   | KVM_REG_PPC_CIABR	| 64
-  PPC   | KVM_REG_PPC_IC	| 64
-  PPC   | KVM_REG_PPC_VTB	| 64
-  PPC   | KVM_REG_PPC_CSIGR	| 64
-  PPC   | KVM_REG_PPC_TACR	| 64
-  PPC   | KVM_REG_PPC_TCSCR	| 64
-  PPC   | KVM_REG_PPC_PID	| 64
-  PPC   | KVM_REG_PPC_ACOP	| 64
-  PPC   | KVM_REG_PPC_VRSAVE	| 32
-  PPC   | KVM_REG_PPC_LPCR	| 64
-  PPC   | KVM_REG_PPC_PPR	| 64
-  PPC   | KVM_REG_PPC_ARCH_COMPAT 32
-  PPC   | KVM_REG_PPC_DABRX     | 32
-  PPC   | KVM_REG_PPC_WORT      | 64
-  PPC   | KVM_REG_PPC_TM_GPR0	| 64
+  PPC   | KVM_REG_PPC_TM_GPR31          | 64
+  PPC   | KVM_REG_PPC_TM_VSR0           | 128
           ...
-  PPC   | KVM_REG_PPC_TM_GPR31	| 64
-  PPC   | KVM_REG_PPC_TM_VSR0	| 128
+  PPC   | KVM_REG_PPC_TM_VSR63          | 128
+  PPC   | KVM_REG_PPC_TM_CR             | 64
+  PPC   | KVM_REG_PPC_TM_LR             | 64
+  PPC   | KVM_REG_PPC_TM_CTR            | 64
+  PPC   | KVM_REG_PPC_TM_FPSCR          | 64
+  PPC   | KVM_REG_PPC_TM_AMR            | 64
+  PPC   | KVM_REG_PPC_TM_PPR            | 64
+  PPC   | KVM_REG_PPC_TM_VRSAVE         | 64
+  PPC   | KVM_REG_PPC_TM_VSCR           | 32
+  PPC   | KVM_REG_PPC_TM_DSCR           | 64
+  PPC   | KVM_REG_PPC_TM_TAR            | 64
+        |                               |
+  MIPS  | KVM_REG_MIPS_R0               | 64
           ...
-  PPC   | KVM_REG_PPC_TM_VSR63	| 128
-  PPC   | KVM_REG_PPC_TM_CR	| 64
-  PPC   | KVM_REG_PPC_TM_LR	| 64
-  PPC   | KVM_REG_PPC_TM_CTR	| 64
-  PPC   | KVM_REG_PPC_TM_FPSCR	| 64
-  PPC   | KVM_REG_PPC_TM_AMR	| 64
-  PPC   | KVM_REG_PPC_TM_PPR	| 64
-  PPC   | KVM_REG_PPC_TM_VRSAVE	| 64
-  PPC   | KVM_REG_PPC_TM_VSCR	| 32
-  PPC   | KVM_REG_PPC_TM_DSCR	| 64
-  PPC   | KVM_REG_PPC_TM_TAR	| 64
+  MIPS  | KVM_REG_MIPS_R31              | 64
+  MIPS  | KVM_REG_MIPS_HI               | 64
+  MIPS  | KVM_REG_MIPS_LO               | 64
+  MIPS  | KVM_REG_MIPS_PC               | 64
+  MIPS  | KVM_REG_MIPS_CP0_INDEX        | 32
+  MIPS  | KVM_REG_MIPS_CP0_CONTEXT      | 64
+  MIPS  | KVM_REG_MIPS_CP0_USERLOCAL    | 64
+  MIPS  | KVM_REG_MIPS_CP0_PAGEMASK     | 32
+  MIPS  | KVM_REG_MIPS_CP0_WIRED        | 32
+  MIPS  | KVM_REG_MIPS_CP0_HWRENA       | 32
+  MIPS  | KVM_REG_MIPS_CP0_BADVADDR     | 64
+  MIPS  | KVM_REG_MIPS_CP0_COUNT        | 32
+  MIPS  | KVM_REG_MIPS_CP0_ENTRYHI      | 64
+  MIPS  | KVM_REG_MIPS_CP0_COMPARE      | 32
+  MIPS  | KVM_REG_MIPS_CP0_STATUS       | 32
+  MIPS  | KVM_REG_MIPS_CP0_CAUSE        | 32
+  MIPS  | KVM_REG_MIPS_CP0_EPC          | 64
+  MIPS  | KVM_REG_MIPS_CP0_CONFIG       | 32
+  MIPS  | KVM_REG_MIPS_CP0_CONFIG1      | 32
+  MIPS  | KVM_REG_MIPS_CP0_CONFIG2      | 32
+  MIPS  | KVM_REG_MIPS_CP0_CONFIG3      | 32
+  MIPS  | KVM_REG_MIPS_CP0_CONFIG7      | 32
+  MIPS  | KVM_REG_MIPS_CP0_ERROREPC     | 64
+  MIPS  | KVM_REG_MIPS_COUNT_CTL        | 64
+  MIPS  | KVM_REG_MIPS_COUNT_RESUME     | 64
+  MIPS  | KVM_REG_MIPS_COUNT_HZ         | 64
 
 ARM registers are mapped using the lower 32 bits.  The upper 16 of that
 is the register group type, or coprocessor number:
@@ -1928,6 +1980,22 @@ arm64 CCSIDR registers are demultiplexed by CSSELR value:
 arm64 system registers have the following id bit patterns:
   0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
 
+
+MIPS registers are mapped using the lower 32 bits.  The upper 16 of that is
+the register group type:
+
+MIPS core registers (see above) have the following id bit patterns:
+  0x7030 0000 0000 <reg:16>
+
+MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit
+patterns depending on whether they're 32-bit or 64-bit registers:
+  0x7020 0000 0001 00 <reg:5> <sel:3>   (32-bit)
+  0x7030 0000 0001 00 <reg:5> <sel:3>   (64-bit)
+
+MIPS KVM control registers (see above) have the following id bit patterns:
+  0x7030 0000 0002 <reg:16>
+
+
 4.69 KVM_GET_ONE_REG
 
 Capability: KVM_CAP_ONE_REG
@@ -2415,7 +2483,7 @@ in VCPU matching underlying host.
 4.84 KVM_GET_REG_LIST
 
 Capability: basic
-Architectures: arm, arm64
+Architectures: arm, arm64, mips
 Type: vcpu ioctl
 Parameters: struct kvm_reg_list (in/out)
 Returns: 0 on success; -1 on error
@@ -2866,15 +2934,18 @@ The fields in each entry are defined as follows:
 6. Capabilities that can be enabled
 -----------------------------------
 
-There are certain capabilities that change the behavior of the virtual CPU when
-enabled. To enable them, please see section 4.37. Below you can find a list of
-capabilities and what their effect on the vCPU is when enabling them.
+There are certain capabilities that change the behavior of the virtual CPU or
+the virtual machine when enabled. To enable them, please see section 4.37.
+Below you can find a list of capabilities and what their effect on the vCPU or
+the virtual machine is when enabling them.
 
 The following information is provided along with the description:
 
   Architectures: which instruction set architectures provide this ioctl.
       x86 includes both i386 and x86_64.
 
+  Target: whether this is a per-vcpu or per-vm capability.
+
   Parameters: what parameters are accepted by the capability.
 
   Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
@@ -2884,6 +2955,7 @@ The following information is provided along with the description:
 6.1 KVM_CAP_PPC_OSI
 
 Architectures: ppc
+Target: vcpu
 Parameters: none
 Returns: 0 on success; -1 on error
 
@@ -2898,6 +2970,7 @@ When this capability is enabled, KVM_EXIT_OSI can occur.
 6.2 KVM_CAP_PPC_PAPR
 
 Architectures: ppc
+Target: vcpu
 Parameters: none
 Returns: 0 on success; -1 on error
 
@@ -2917,6 +2990,7 @@ When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
 6.3 KVM_CAP_SW_TLB
 
 Architectures: ppc
+Target: vcpu
 Parameters: args[0] is the address of a struct kvm_config_tlb
 Returns: 0 on success; -1 on error
 
@@ -2959,6 +3033,7 @@ For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
 6.4 KVM_CAP_S390_CSS_SUPPORT
 
 Architectures: s390
+Target: vcpu
 Parameters: none
 Returns: 0 on success; -1 on error
 
@@ -2970,9 +3045,13 @@ handled in-kernel, while the other I/O instructions are passed to userspace.
 When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
 SUBCHANNEL intercepts.
 
+Note that even though this capability is enabled per-vcpu, the complete
+virtual machine is affected.
+
 6.5 KVM_CAP_PPC_EPR
 
 Architectures: ppc
+Target: vcpu
 Parameters: args[0] defines whether the proxy facility is active
 Returns: 0 on success; -1 on error
 
@@ -2998,7 +3077,17 @@ This capability connects the vcpu to an in-kernel MPIC device.
 6.7 KVM_CAP_IRQ_XICS
 
 Architectures: ppc
+Target: vcpu
 Parameters: args[0] is the XICS device fd
             args[1] is the XICS CPU number (server ID) for this vcpu
 
 This capability connects the vcpu to an in-kernel XICS device.
+
+6.8 KVM_CAP_S390_IRQCHIP
+
+Architectures: s390
+Target: vm
+Parameters: none
+
+This capability enables the in-kernel irqchip for s390. Please refer to
+"4.24 KVM_CREATE_IRQCHIP" for details.
diff --git a/MAINTAINERS b/MAINTAINERS
index 1b22565c59a..1acc624ecfd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -70,6 +70,8 @@ Descriptions of section entries:
 
 	P: Person (obsolete)
 	M: Mail patches to: FullName <address@domain>
+	R: Designated reviewer: FullName <address@domain>
+	   These reviewers should be CCed on patches.
 	L: Mailing list that is relevant to this area
 	W: Web-page with status/info
 	Q: Patchwork web based patch tracking system site
@@ -156,7 +158,6 @@ F:	drivers/net/hamradio/6pack.c
 
 8169 10/100/1000 GIGABIT ETHERNET DRIVER
 M:	Realtek linux nic maintainers <nic_swsd@realtek.com>
-M:	Francois Romieu <romieu@fr.zoreil.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/realtek/r8169.c
@@ -604,6 +605,13 @@ L:	amd64-microcode@amd64.org
 S:	Maintained
 F:	arch/x86/kernel/microcode_amd.c
 
+AMD XGBE DRIVER
+M:	Tom Lendacky <thomas.lendacky@amd.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/ethernet/amd/xgbe/
+F:	drivers/net/phy/amd-xgbe-phy.c
+
 AMS (Apple Motion Sensor) DRIVER
 M:	Michael Hanselmann <linux-kernel@hansmi.ch>
 S:	Supported
@@ -936,16 +944,10 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
 F:	arch/arm/mach-imx/
+F:	arch/arm/mach-mxs/
 F:	arch/arm/boot/dts/imx*
 F:	arch/arm/configs/imx*_defconfig
 
-ARM/FREESCALE MXS ARM ARCHITECTURE
-M:	Shawn Guo <shawn.guo@linaro.org>
-L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S:	Maintained
-T:	git git://git.linaro.org/people/shawnguo/linux-2.6.git
-F:	arch/arm/mach-mxs/
-
 ARM/GLOMATION GESBC9312SX MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1045,9 +1047,33 @@ M:	Santosh Shilimkar <santosh.shilimkar@ti.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-keystone/
-F:	drivers/clk/keystone/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux-keystone.git
 
+ARM/TEXAS INSTRUMENT KEYSTONE CLOCK FRAMEWORK
+M:	Santosh Shilimkar <santosh.shilimkar@ti.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/clk/keystone/
+
+ARM/TEXAS INSTRUMENT KEYSTONE ClOCKSOURCE
+M:	Santosh Shilimkar <santosh.shilimkar@ti.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/clocksource/timer-keystone.c
+
+ARM/TEXAS INSTRUMENT KEYSTONE RESET DRIVER
+M:	Santosh Shilimkar <santosh.shilimkar@ti.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/power/reset/keystone-reset.c
+
+ARM/TEXAS INSTRUMENT AEMIF/EMIF DRIVERS
+M:	Santosh Shilimkar <santosh.shilimkar@ti.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/memory/*emif*
+
 ARM/LOGICPD PXA270 MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1289,6 +1315,20 @@ W:	http://oss.renesas.com
 Q:	http://patchwork.kernel.org/project/linux-sh/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next
 S:	Supported
+F:	arch/arm/boot/dts/emev2*
+F:	arch/arm/boot/dts/r7s*
+F:	arch/arm/boot/dts/r8a*
+F:	arch/arm/boot/dts/sh*
+F:	arch/arm/configs/ape6evm_defconfig
+F:	arch/arm/configs/armadillo800eva_defconfig
+F:	arch/arm/configs/bockw_defconfig
+F:	arch/arm/configs/genmai_defconfig
+F:	arch/arm/configs/koelsch_defconfig
+F:	arch/arm/configs/kzm9g_defconfig
+F:	arch/arm/configs/lager_defconfig
+F:	arch/arm/configs/mackerel_defconfig
+F:	arch/arm/configs/marzen_defconfig
+F:	arch/arm/configs/shmobile_defconfig
 F:	arch/arm/mach-shmobile/
 F:	drivers/sh/
 
@@ -1894,7 +1934,7 @@ F:	drivers/net/ethernet/broadcom/bnx2.*
 F:	drivers/net/ethernet/broadcom/bnx2_*
 
 BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-M:	Ariel Elior <ariele@broadcom.com>
+M:	Ariel Elior <ariel.elior@qlogic.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
@@ -1974,6 +2014,12 @@ S:	Maintained
 F:	drivers/bcma/
 F:	include/linux/bcma/
 
+BROADCOM SYSTEMPORT ETHERNET DRIVER
+M:	Florian Fainelli <f.fainelli@gmail.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/ethernet/broadcom/bcmsysport.*
+
 BROCADE BFA FC SCSI DRIVER
 M:	Anil Gurumurthy <anil.gurumurthy@qlogic.com>
 M:	Sudarsana Kalluru <sudarsana.kalluru@qlogic.com>
@@ -2230,9 +2276,8 @@ F:	drivers/platform/chrome/
 CISCO VIC ETHERNET NIC DRIVER
 M:	Christian Benvenuti <benve@cisco.com>
 M:	Sujith Sankar <ssujith@cisco.com>
-M:	Govindarajulu Varadarajan <govindarajulu90@gmail.com>
+M:	Govindarajulu Varadarajan <_govind@gmx.com>
 M:	Neel Patel <neepatel@cisco.com>
-M:	Nishank Trivedi <nistrive@cisco.com>
 S:	Supported
 F:	drivers/net/ethernet/cisco/enic/
 
@@ -2384,16 +2429,35 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/connector/
 
-CONTROL GROUPS (CGROUPS)
+CONTROL GROUP (CGROUP)
 M:	Tejun Heo <tj@kernel.org>
 M:	Li Zefan <lizefan@huawei.com>
-L:	containers@lists.linux-foundation.org
 L:	cgroups@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
 S:	Maintained
+F:	Documentation/cgroups/
 F:	include/linux/cgroup*
 F:	kernel/cgroup*
-F:	mm/*cgroup*
+
+CONTROL GROUP - CPUSET
+M:	Li Zefan <lizefan@huawei.com>
+L:	cgroups@vger.kernel.org
+W:	http://www.bullopensource.org/cpuset/
+W:	http://oss.sgi.com/projects/cpusets/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
+S:	Maintained
+F:	Documentation/cgroups/cpusets.txt
+F:	include/linux/cpuset.h
+F:	kernel/cpuset.c
+
+CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
+M:	Johannes Weiner <hannes@cmpxchg.org>
+M:	Michal Hocko <mhocko@suse.cz>
+L:	cgroups@vger.kernel.org
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	mm/memcontrol.c
+F:	mm/page_cgroup.c
 
 CORETEMP HARDWARE MONITORING DRIVER
 M:	Fenghua Yu <fenghua.yu@intel.com>
@@ -2464,17 +2528,6 @@ M:	Thomas Renninger <trenn@suse.de>
 S:	Maintained
 F:	tools/power/cpupower/
 
-CPUSETS
-M:	Li Zefan <lizefan@huawei.com>
-L:	cgroups@vger.kernel.org
-W:	http://www.bullopensource.org/cpuset/
-W:	http://oss.sgi.com/projects/cpusets/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
-S:	Maintained
-F:	Documentation/cgroups/cpusets.txt
-F:	include/linux/cpuset.h
-F:	kernel/cpuset.c
-
 CRAMFS FILESYSTEM
 W:	http://sourceforge.net/projects/cramfs/
 S:	Orphan / Obsolete
@@ -2574,7 +2627,7 @@ S:	Supported
 F:	drivers/infiniband/hw/cxgb3/
 
 CXGB4 ETHERNET DRIVER (CXGB4)
-M:	Dimitris Michailidis <dm@chelsio.com>
+M:	Hariprasad S <hariprasad@chelsio.com>
 L:	netdev@vger.kernel.org
 W:	http://www.chelsio.com
 S:	Supported
@@ -2692,6 +2745,15 @@ S:	Orphan
 F:	Documentation/networking/decnet.txt
 F:	net/decnet/
 
+DECSTATION PLATFORM SUPPORT
+M:	"Maciej W. Rozycki" <macro@linux-mips.org>
+L:	linux-mips@linux-mips.org
+W:	http://www.linux-mips.org/wiki/DECstation
+S:	Maintained
+F:	arch/mips/dec/
+F:	arch/mips/include/asm/dec/
+F:	arch/mips/include/asm/mach-dec/
+
 DEFXX FDDI NETWORK DRIVER
 M:	"Maciej W. Rozycki" <macro@linux-mips.org>
 S:	Maintained
@@ -2888,6 +2950,9 @@ L:	linux-doc@vger.kernel.org
 T:	quilt http://www.infradead.org/~rdunlap/Doc/patches/
 S:	Maintained
 F:	Documentation/
+X:	Documentation/ABI/
+X:	Documentation/devicetree/
+X:	Documentation/[a-z][a-z]_[A-Z][A-Z]/
 
 DOUBLETALK DRIVER
 M:	"James R. Van Zandt" <jrv@vanzandt.mv.com>
@@ -2935,6 +3000,7 @@ L:	dri-devel@lists.freedesktop.org
 T:	git git://people.freedesktop.org/~airlied/linux
 S:	Maintained
 F:	drivers/gpu/drm/
+F:	drivers/gpu/vga/
 F:	include/drm/
 F:	include/uapi/drm/
 
@@ -3159,14 +3225,6 @@ L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	drivers/scsi/eata_pio.*
 
-EBTABLES
-L:	netfilter-devel@vger.kernel.org
-W:	http://ebtables.sourceforge.net/
-S:	Orphan
-F:	include/linux/netfilter_bridge/ebt_*.h
-F:	include/uapi/linux/netfilter_bridge/ebt_*.h
-F:	net/bridge/netfilter/ebt*.c
-
 EC100 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
@@ -3294,6 +3352,13 @@ W:	bluesmoke.sourceforge.net
 S:	Maintained
 F:	drivers/edac/i82975x_edac.c
 
+EDAC-IE31200
+M:	Jason Baron <jbaron@akamai.com>
+L:	linux-edac@vger.kernel.org
+W:	bluesmoke.sourceforge.net
+S:	Maintained
+F:	drivers/edac/ie31200_edac.c
+
 EDAC-MPC85XX
 M:	Johannes Thumshirn <johannes.thumshirn@men.de>
 L:	linux-edac@vger.kernel.org
@@ -3775,7 +3840,8 @@ F:	fs/fscache/
 F:	include/linux/fscache*.h
 
 F2FS FILE SYSTEM
-M:	Jaegeuk Kim <jaegeuk.kim@samsung.com>
+M:	Jaegeuk Kim <jaegeuk@kernel.org>
+M:	Changman Lee <cm224.lee@samsung.com>
 L:	linux-f2fs-devel@lists.sourceforge.net
 W:	http://en.wikipedia.org/wiki/F2FS
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
@@ -4373,7 +4439,7 @@ S:	Supported
 F:	drivers/crypto/nx/
 
 IBM Power 842 compression accelerator
-M:	Robert Jennings <rcj@linux.vnet.ibm.com>
+M:	Nathan Fontenot <nfont@linux.vnet.ibm.com>
 S:	Supported
 F:	drivers/crypto/nx/nx-842.c
 F:	include/linux/nx842.h
@@ -4389,12 +4455,18 @@ L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/ibm/ibmveth.*
 
-IBM Power Virtual SCSI/FC Device Drivers
-M:	Robert Jennings <rcj@linux.vnet.ibm.com>
+IBM Power Virtual SCSI Device Drivers
+M:	Nathan Fontenot <nfont@linux.vnet.ibm.com>
+L:	linux-scsi@vger.kernel.org
+S:	Supported
+F:	drivers/scsi/ibmvscsi/ibmvscsi*
+F:	drivers/scsi/ibmvscsi/viosrp.h
+
+IBM Power Virtual FC Device Drivers
+M:	Brian King <brking@linux.vnet.ibm.com>
 L:	linux-scsi@vger.kernel.org
 S:	Supported
-F:	drivers/scsi/ibmvscsi/
-X:	drivers/scsi/ibmvscsi/ibmvstgt.c
+F:	drivers/scsi/ibmvscsi/ibmvfc*
 
 IBM ServeRAID RAID DRIVER
 P:	Jack Hammer
@@ -4447,8 +4519,7 @@ S:	Supported
 F:	drivers/idle/i7300_idle.c
 
 IEEE 802.15.4 SUBSYSTEM
-M:	Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
-M:	Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+M:	Alexander Aring <alex.aring@gmail.com>
 L:	linux-zigbee-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://apps.sourceforge.net/trac/linux-zigbee
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lowpan/lowpan.git
@@ -5480,10 +5551,11 @@ S:	Maintained
 F:	arch/arm/mach-lpc32xx/
 
 LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI)
-M:	Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com>
-M:	Sreekanth Reddy <Sreekanth.Reddy@lsi.com>
-M:	support@lsi.com
-L:	DL-MPTFusionLinux@lsi.com
+M:	Nagalakshmi Nandigama <nagalakshmi.nandigama@avagotech.com>
+M:	Praveen Krishnamoorthy <praveen.krishnamoorthy@avagotech.com>
+M:	Sreekanth Reddy <sreekanth.reddy@avagotech.com>
+M:	Abhijit Mahajan <abhijit.mahajan@avagotech.com>
+L:	MPT-FusionLinux.pdl@avagotech.com
 L:	linux-scsi@vger.kernel.org
 W:	http://www.lsilogic.com/support
 S:	Supported
@@ -5757,17 +5829,6 @@ F:	include/linux/memory_hotplug.h
 F:	include/linux/vmalloc.h
 F:	mm/
 
-MEMORY RESOURCE CONTROLLER
-M:	Johannes Weiner <hannes@cmpxchg.org>
-M:	Michal Hocko <mhocko@suse.cz>
-M:	Balbir Singh <bsingharora@gmail.com>
-M:	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
-L:	cgroups@vger.kernel.org
-L:	linux-mm@kvack.org
-S:	Maintained
-F:	mm/memcontrol.c
-F:	mm/page_cgroup.c
-
 MEMORY TECHNOLOGY DEVICES (MTD)
 M:	David Woodhouse <dwmw2@infradead.org>
 M:	Brian Norris <computersforpeace@gmail.com>
@@ -5961,6 +6022,7 @@ M:	Chris Ball <chris@printf.net>
 M:	Ulf Hansson <ulf.hansson@linaro.org>
 L:	linux-mmc@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc.git
+T:	git git://git.linaro.org/people/ulf.hansson/mmc.git
 S:	Maintained
 F:	drivers/mmc/
 F:	include/linux/mmc/
@@ -6022,6 +6084,28 @@ M:	Petr Vandrovec <petr@vandrovec.name>
 S:	Odd Fixes
 F:	fs/ncpfs/
 
+NCR 5380 SCSI DRIVERS
+M:	Finn Thain <fthain@telegraphics.com.au>
+M:	Michael Schmitz <schmitzmic@gmail.com>
+L:	linux-scsi@vger.kernel.org
+S:	Maintained
+F:	Documentation/scsi/g_NCR5380.txt
+F:	drivers/scsi/NCR5380.*
+F:	drivers/scsi/arm/cumana_1.c
+F:	drivers/scsi/arm/oak.c
+F:	drivers/scsi/atari_NCR5380.c
+F:	drivers/scsi/atari_scsi.*
+F:	drivers/scsi/dmx3191d.c
+F:	drivers/scsi/dtc.*
+F:	drivers/scsi/g_NCR5380.*
+F:	drivers/scsi/g_NCR5380_mmio.c
+F:	drivers/scsi/mac_scsi.*
+F:	drivers/scsi/pas16.*
+F:	drivers/scsi/sun3_NCR5380.c
+F:	drivers/scsi/sun3_scsi.*
+F:	drivers/scsi/sun3_scsi_vme.c
+F:	drivers/scsi/t128.*
+
 NCR DUAL 700 SCSI DRIVER (MICROCHANNEL)
 M:	"James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
 L:	linux-scsi@vger.kernel.org
@@ -6056,12 +6140,11 @@ F:	Documentation/networking/s2io.txt
 F:	Documentation/networking/vxge.txt
 F:	drivers/net/ethernet/neterion/
 
-NETFILTER/IPTABLES
+NETFILTER ({IP,IP6,ARP,EB,NF}TABLES)
 M:	Pablo Neira Ayuso <pablo@netfilter.org>
 M:	Patrick McHardy <kaber@trash.net>
 M:	Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
 L:	netfilter-devel@vger.kernel.org
-L:	netfilter@vger.kernel.org
 L:	coreteam@netfilter.org
 W:	http://www.netfilter.org/
 W:	http://www.iptables.org/
@@ -6131,6 +6214,7 @@ F:	include/uapi/linux/netdevice.h
 F:	tools/net/
 F:	tools/testing/selftests/net/
 F:	lib/random32.c
+F:	lib/test_bpf.c
 
 NETWORKING [IPv4/IPv6]
 M:	"David S. Miller" <davem@davemloft.net>
@@ -6724,7 +6808,7 @@ F:	arch/x86/kernel/quirks.c
 
 PCI DRIVER FOR IMX6
 M:	Richard Zhu <r65037@freescale.com>
-M:	Shawn Guo <shawn.guo@linaro.org>
+M:	Shawn Guo <shawn.guo@freescale.com>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
@@ -6881,6 +6965,12 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/pinctrl/pinctrl-at91.c
 
+PIN CONTROLLER - RENESAS
+M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+L:	linux-sh@vger.kernel.org
+S:	Maintained
+F:	drivers/pinctrl/sh-pfc/
+
 PIN CONTROLLER - SAMSUNG
 M:	Tomasz Figa <t.figa@samsung.com>
 M:	Thomas Abraham <thomas.abraham@linaro.org>
@@ -6910,7 +7000,7 @@ PKUNITY SOC DRIVERS
 M:	Guan Xuetao <gxt@mprc.pku.edu.cn>
 W:	http://mprc.pku.edu.cn/~guanxuetao/linux
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/epip/linux-2.6-unicore32.git
+T:	git git://github.com/gxt/linux.git
 F:	drivers/input/serio/i8042-unicore32io.h
 F:	drivers/i2c/busses/i2c-puv3.c
 F:	drivers/video/fb-puv3.c
@@ -7162,6 +7252,12 @@ M:	Robert Jarzmik <robert.jarzmik@free.fr>
 L:	rtc-linux@googlegroups.com
 S:	Maintained
 
+QAT DRIVER
+M:      Tadeusz Struk <tadeusz.struk@intel.com>
+L:      qat-linux@intel.com
+S:      Supported
+F:      drivers/crypto/qat/
+
 QIB DRIVER
 M:	Mike Marciniszyn <infinipath@intel.com>
 L:	linux-rdma@vger.kernel.org
@@ -7343,16 +7439,20 @@ S:	Orphan
 F:	drivers/net/wireless/ray*
 
 RCUTORTURE MODULE
-M:	Josh Triplett <josh@freedesktop.org>
+M:	Josh Triplett <josh@joshtriplett.org>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/torture.txt
-F:	kernel/rcu/torture.c
+F:	kernel/rcu/rcutorture.c
 
 RCUTORTURE TEST FRAMEWORK
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+M:	Josh Triplett <josh@joshtriplett.org>
+R:	Steven Rostedt <rostedt@goodmis.org>
+R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+R:	Lai Jiangshan <laijs@cn.fujitsu.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
@@ -7375,8 +7475,11 @@ S:	Supported
 F:	net/rds/
 
 READ-COPY UPDATE (RCU)
-M:	Dipankar Sarma <dipankar@in.ibm.com>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+M:	Josh Triplett <josh@joshtriplett.org>
+R:	Steven Rostedt <rostedt@goodmis.org>
+R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+R:	Lai Jiangshan <laijs@cn.fujitsu.com>
 L:	linux-kernel@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
@@ -7386,7 +7489,7 @@ X:	Documentation/RCU/torture.txt
 F:	include/linux/rcu*
 X:	include/linux/srcu.h
 F:	kernel/rcu/
-X:	kernel/rcu/torture.c
+X:	kernel/torture.c
 
 REAL TIME CLOCK (RTC) SUBSYSTEM
 M:	Alessandro Zummo <a.zummo@towertech.it>
@@ -7898,6 +8001,7 @@ F:	drivers/mmc/host/sdhci-spear.c
 
 SECURITY SUBSYSTEM
 M:	James Morris <james.l.morris@oracle.com>
+M:	Serge E. Hallyn <serge@hallyn.com>
 L:	linux-security-module@vger.kernel.org (suggested Cc:)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security.git
 W:	http://kernsec.org/
@@ -7943,6 +8047,16 @@ F:	drivers/ata/
 F:	include/linux/ata.h
 F:	include/linux/libata.h
 
+SERIAL ATA AHCI PLATFORM devices support
+M:	Hans de Goede <hdegoede@redhat.com>
+M:	Tejun Heo <tj@kernel.org>
+L:	linux-ide@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
+S:	Supported
+F:	drivers/ata/ahci_platform.c
+F:	drivers/ata/libahci_platform.c
+F:	include/linux/ahci_platform.h
+
 SERVER ENGINES 10Gbps iSCSI - BladeEngine 2 DRIVER
 M:	Jayamohan Kallickal <jayamohan.kallickal@emulex.com>
 L:	linux-scsi@vger.kernel.org
@@ -8145,17 +8259,22 @@ S:	Maintained
 F:	drivers/usb/misc/sisusbvga/
 
 SLAB ALLOCATOR
-M:	Christoph Lameter <cl@linux-foundation.org>
+M:	Christoph Lameter <cl@linux.com>
 M:	Pekka Enberg <penberg@kernel.org>
-M:	Matt Mackall <mpm@selenic.com>
+M:	David Rientjes <rientjes@google.com>
+M:	Joonsoo Kim <iamjoonsoo.kim@lge.com>
+M:	Andrew Morton <akpm@linux-foundation.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	include/linux/sl?b*.h
-F:	mm/sl?b.c
+F:	mm/sl?b*
 
 SLEEPABLE READ-COPY UPDATE (SRCU)
 M:	Lai Jiangshan <laijs@cn.fujitsu.com>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+M:	Josh Triplett <josh@joshtriplett.org>
+R:	Steven Rostedt <rostedt@goodmis.org>
+R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 L:	linux-kernel@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
@@ -8828,7 +8947,7 @@ M:	Stephen Warren <swarren@wwwdotorg.org>
 M:	Thierry Reding <thierry.reding@gmail.com>
 L:	linux-tegra@vger.kernel.org
 Q:	http://patchwork.ozlabs.org/project/linux-tegra/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/swarren/linux-tegra.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tegra/linux.git
 S:	Supported
 N:	[^a-z]tegra
 
@@ -8918,7 +9037,7 @@ F:	drivers/media/radio/radio-raremono.c
 
 THERMAL
 M:	Zhang Rui <rui.zhang@intel.com>
-M:	Eduardo Valentin <eduardo.valentin@ti.com>
+M:	Eduardo Valentin <edubezval@gmail.com>
 L:	linux-pm@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git
@@ -8945,11 +9064,18 @@ S:	Maintained
 F:	drivers/platform/x86/thinkpad_acpi.c
 
 TI BANDGAP AND THERMAL DRIVER
-M:	Eduardo Valentin <eduardo.valentin@ti.com>
+M:	Eduardo Valentin <edubezval@gmail.com>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 F:	drivers/thermal/ti-soc-thermal/
 
+TI CLOCK DRIVER
+M:	Tero Kristo <t-kristo@ti.com>
+L:	linux-omap@vger.kernel.org
+S:	Maintained
+F:	drivers/clk/ti/
+F:	include/linux/clk/ti.h
+
 TI FLASH MEDIA INTERFACE DRIVER
 M:	Alex Dubov <oakad@yahoo.com>
 S:	Maintained
@@ -9068,7 +9194,7 @@ F:	include/linux/toshiba.h
 F:	include/uapi/linux/toshiba.h
 
 TMIO MMC DRIVER
-M:	Ian Molton <ian@mnementh.co.uk>
+M:	Ian Molton <ian.molton@codethink.co.uk>
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/tmio_mmc*
@@ -9109,7 +9235,6 @@ F:	drivers/char/tpm/
 
 TRACING
 M:	Steven Rostedt <rostedt@goodmis.org>
-M:	Frederic Weisbecker <fweisbec@gmail.com>
 M:	Ingo Molnar <mingo@redhat.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core
 S:	Maintained
@@ -9227,7 +9352,7 @@ UNICORE32 ARCHITECTURE:
 M:	Guan Xuetao <gxt@mprc.pku.edu.cn>
 W:	http://mprc.pku.edu.cn/~guanxuetao/linux
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/epip/linux-2.6-unicore32.git
+T:	git git://github.com/gxt/linux.git
 F:	arch/unicore32/
 
 UNIFDEF
@@ -9360,12 +9485,6 @@ S:	Maintained
 F:	drivers/usb/host/isp116x*
 F:	include/linux/usb/isp116x.h
 
-USB KAWASAKI LSI DRIVER
-M:	Oliver Neukum <oliver@neukum.org>
-L:	linux-usb@vger.kernel.org
-S:	Maintained
-F:	drivers/usb/serial/kl5kusb105.*
-
 USB MASS STORAGE DRIVER
 M:	Matthew Dharm <mdharm-usb@one-eyed-alien.net>
 L:	linux-usb@vger.kernel.org
@@ -9393,12 +9512,6 @@ S:	Maintained
 F:	Documentation/usb/ohci.txt
 F:	drivers/usb/host/ohci*
 
-USB OPTION-CARD DRIVER
-M:	Matthias Urlichs <smurf@smurf.noris.de>
-L:	linux-usb@vger.kernel.org
-S:	Maintained
-F:	drivers/usb/serial/option.c
-
 USB PEGASUS DRIVER
 M:	Petko Manolov <petkan@nucleusys.com>
 L:	linux-usb@vger.kernel.org
@@ -9431,7 +9544,7 @@ S:	Maintained
 F:	drivers/net/usb/rtl8150.c
 
 USB SERIAL SUBSYSTEM
-M:	Johan Hovold <jhovold@gmail.com>
+M:	Johan Hovold <johan@kernel.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	Documentation/usb/usb-serial.txt
@@ -9694,6 +9807,14 @@ L:	virtualization@lists.linux-foundation.org
 S:	Supported
 F:	arch/x86/kernel/cpu/vmware.c
 
+VMWARE BALLOON DRIVER
+M:	Xavier Deguillard <xdeguillard@vmware.com>
+M:	Philip Moltmann <moltmann@vmware.com>
+M:	"VMware, Inc." <pv-drivers@vmware.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	drivers/misc/vmw_balloon.c
+
 VMWARE VMXNET3 ETHERNET DRIVER
 M:	Shreyas Bhatewara <sbhatewara@vmware.com>
 M:	"VMware, Inc." <pv-drivers@vmware.com>
diff --git a/Makefile b/Makefile
index 6d1e304943a..d0901b46b4b 100644
--- a/Makefile
+++ b/Makefile
@@ -1,5 +1,5 @@
 VERSION = 3
-PATCHLEVEL = 15
+PATCHLEVEL = 16
 SUBLEVEL = 0
 EXTRAVERSION =
 NAME = Shuffling Zombie Juror
@@ -41,6 +41,29 @@ unexport GREP_OPTIONS
 # descending is started. They are now explicitly listed as the
 # prepare rule.
 
+# Beautify output
+# ---------------------------------------------------------------------------
+#
+# Normally, we echo the whole command before executing it. By making
+# that echo $($(quiet)$(cmd)), we now have the possibility to set
+# $(quiet) to choose other forms of output instead, e.g.
+#
+#         quiet_cmd_cc_o_c = Compiling $(RELDIR)/$@
+#         cmd_cc_o_c       = $(CC) $(c_flags) -c -o $@ $<
+#
+# If $(quiet) is empty, the whole command will be printed.
+# If it is set to "quiet_", only the short version will be printed.
+# If it is set to "silent_", nothing will be printed at all, since
+# the variable $(silent_cmd_cc_o_c) doesn't exist.
+#
+# A simple variant is to prefix commands with $(Q) - that's useful
+# for commands that shall be hidden in non-verbose mode.
+#
+#	$(Q)ln $@ :<
+#
+# If KBUILD_VERBOSE equals 0 then the above command will be hidden.
+# If KBUILD_VERBOSE equals 1 then the above command is displayed.
+#
 # To put more focus on warnings, be less verbose as default
 # Use 'make V=1' to see the full commands
 
@@ -51,6 +74,29 @@ ifndef KBUILD_VERBOSE
   KBUILD_VERBOSE = 0
 endif
 
+ifeq ($(KBUILD_VERBOSE),1)
+  quiet =
+  Q =
+else
+  quiet=quiet_
+  Q = @
+endif
+
+# If the user is running make -s (silent mode), suppress echoing of
+# commands
+
+ifneq ($(filter 4.%,$(MAKE_VERSION)),)	# make-4
+ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
+  quiet=silent_
+endif
+else					# make-3.8x
+ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
+  quiet=silent_
+endif
+endif
+
+export quiet Q KBUILD_VERBOSE
+
 # Call a source code checker (by default, "sparse") as part of the
 # C compilation.
 #
@@ -105,10 +151,6 @@ ifeq ("$(origin O)", "command line")
   KBUILD_OUTPUT := $(O)
 endif
 
-ifeq ("$(origin W)", "command line")
-  export KBUILD_ENABLE_EXTRA_GCC_CHECKS := $(W)
-endif
-
 # That's our default target when none is given on the command line
 PHONY := _all
 _all:
@@ -130,7 +172,13 @@ PHONY += $(MAKECMDGOALS) sub-make
 $(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make
 	@:
 
+# Fake the "Entering directory" message once, so that IDEs/editors are
+# able to understand relative filenames.
+       echodir := @echo
+ quiet_echodir := @echo
+silent_echodir := @:
 sub-make: FORCE
+	$($(quiet)echodir) "make[1]: Entering directory \`$(KBUILD_OUTPUT)'"
 	$(if $(KBUILD_VERBOSE:1=),@)$(MAKE) -C $(KBUILD_OUTPUT) \
 	KBUILD_SRC=$(CURDIR) \
 	KBUILD_EXTMOD="$(KBUILD_EXTMOD)" -f $(CURDIR)/Makefile \
@@ -153,8 +201,18 @@ else
 _all: modules
 endif
 
-srctree		:= $(if $(KBUILD_SRC),$(KBUILD_SRC),$(CURDIR))
-objtree		:= $(CURDIR)
+ifeq ($(KBUILD_SRC),)
+        # building in the source tree
+        srctree := .
+else
+        ifeq ($(KBUILD_SRC)/,$(dir $(CURDIR)))
+                # building in a subdirectory of the source tree
+                srctree := ..
+        else
+                srctree := $(KBUILD_SRC)
+        endif
+endif
+objtree		:= .
 src		:= $(srctree)
 obj		:= $(objtree)
 
@@ -166,7 +224,7 @@ export srctree objtree VPATH
 # SUBARCH tells the usermode build what the underlying arch is.  That is set
 # first, and if a usermode build is happening, the "ARCH=um" on the command
 # line overrides the setting of ARCH below.  If a native build is happening,
-# then ARCH is assigned, getting whatever value it gets normally, and 
+# then ARCH is assigned, getting whatever value it gets normally, and
 # SUBARCH is subsequently ignored.
 
 SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
@@ -259,18 +317,18 @@ endif
 KBUILD_MODULES :=
 KBUILD_BUILTIN := 1
 
-#	If we have only "make modules", don't compile built-in objects.
-#	When we're building modules with modversions, we need to consider
-#	the built-in objects during the descend as well, in order to
-#	make sure the checksums are up to date before we record them.
+# If we have only "make modules", don't compile built-in objects.
+# When we're building modules with modversions, we need to consider
+# the built-in objects during the descend as well, in order to
+# make sure the checksums are up to date before we record them.
 
 ifeq ($(MAKECMDGOALS),modules)
   KBUILD_BUILTIN := $(if $(CONFIG_MODVERSIONS),1)
 endif
 
-#	If we have "make <whatever> modules", compile modules
-#	in addition to whatever we do anyway.
-#	Just "make" or "make all" shall build modules as well
+# If we have "make <whatever> modules", compile modules
+# in addition to whatever we do anyway.
+# Just "make" or "make all" shall build modules as well
 
 ifneq ($(filter all _all modules,$(MAKECMDGOALS)),)
   KBUILD_MODULES := 1
@@ -283,52 +341,6 @@ endif
 export KBUILD_MODULES KBUILD_BUILTIN
 export KBUILD_CHECKSRC KBUILD_SRC KBUILD_EXTMOD
 
-# Beautify output
-# ---------------------------------------------------------------------------
-#
-# Normally, we echo the whole command before executing it. By making
-# that echo $($(quiet)$(cmd)), we now have the possibility to set
-# $(quiet) to choose other forms of output instead, e.g.
-#
-#         quiet_cmd_cc_o_c = Compiling $(RELDIR)/$@
-#         cmd_cc_o_c       = $(CC) $(c_flags) -c -o $@ $<
-#
-# If $(quiet) is empty, the whole command will be printed.
-# If it is set to "quiet_", only the short version will be printed. 
-# If it is set to "silent_", nothing will be printed at all, since
-# the variable $(silent_cmd_cc_o_c) doesn't exist.
-#
-# A simple variant is to prefix commands with $(Q) - that's useful
-# for commands that shall be hidden in non-verbose mode.
-#
-#	$(Q)ln $@ :<
-#
-# If KBUILD_VERBOSE equals 0 then the above command will be hidden.
-# If KBUILD_VERBOSE equals 1 then the above command is displayed.
-
-ifeq ($(KBUILD_VERBOSE),1)
-  quiet =
-  Q =
-else
-  quiet=quiet_
-  Q = @
-endif
-
-# If the user is running make -s (silent mode), suppress echoing of
-# commands
-
-ifneq ($(filter 4.%,$(MAKE_VERSION)),)	# make-4
-ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
-  quiet=silent_
-endif
-else					# make-3.8x
-ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
-  quiet=silent_
-endif
-endif
-
-export quiet Q KBUILD_VERBOSE
-
 ifneq ($(CC),)
 ifeq ($(shell $(CC) -v 2>&1 | grep -c "clang version"), 1)
 COMPILER := clang
@@ -346,7 +358,6 @@ $(srctree)/scripts/Kbuild.include: ;
 include $(srctree)/scripts/Kbuild.include
 
 # Make variables (CC, etc...)
-
 AS		= $(CROSS_COMPILE)as
 LD		= $(CROSS_COMPILE)ld
 CC		= $(CROSS_COMPILE)gcc
@@ -395,8 +406,8 @@ KBUILD_CPPFLAGS := -D__KERNEL__
 KBUILD_CFLAGS   := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -fno-common \
 		   -Werror-implicit-function-declaration \
-		   -Wno-format-security \
-		   $(call cc-option,-fno-delete-null-pointer-checks,)
+		   -Wno-format-security
+
 KBUILD_AFLAGS_KERNEL :=
 KBUILD_CFLAGS_KERNEL :=
 KBUILD_AFLAGS   := -D__ASSEMBLY__
@@ -504,8 +515,16 @@ ifeq ($(mixed-targets),1)
 # We're called with mixed targets (*config and build targets).
 # Handle them one by one.
 
-%:: FORCE
-	$(Q)$(MAKE) -C $(srctree) KBUILD_SRC= $@
+PHONY += $(MAKECMDGOALS) __build_one_by_one
+
+$(filter-out __build_one_by_one, $(MAKECMDGOALS)): __build_one_by_one
+	@:
+
+__build_one_by_one:
+	$(Q)set -e; \
+	for i in $(MAKECMDGOALS); do \
+		$(MAKE) -f $(srctree)/Makefile $$i; \
+	done
 
 else
 ifeq ($(config-targets),1)
@@ -520,11 +539,9 @@ include $(srctree)/arch/$(SRCARCH)/Makefile
 export KBUILD_DEFCONFIG KBUILD_KCONFIG
 
 config: scripts_basic outputmakefile FORCE
-	$(Q)mkdir -p include/linux include/config
 	$(Q)$(MAKE) $(build)=scripts/kconfig $@
 
 %config: scripts_basic outputmakefile FORCE
-	$(Q)mkdir -p include/linux include/config
 	$(Q)$(MAKE) $(build)=scripts/kconfig $@
 
 else
@@ -594,14 +611,16 @@ endif # $(dot-config)
 # Defaults to vmlinux, but the arch makefile usually adds further targets
 all: vmlinux
 
+include $(srctree)/arch/$(SRCARCH)/Makefile
+
+KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
+
 ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 KBUILD_CFLAGS	+= -Os $(call cc-disable-warning,maybe-uninitialized,)
 else
 KBUILD_CFLAGS	+= -O2
 endif
 
-include $(srctree)/arch/$(SRCARCH)/Makefile
-
 ifdef CONFIG_READABLE_ASM
 # Disable optimizations that make assembler listings hard to read.
 # reorder blocks reorders the control in the function
@@ -669,9 +688,11 @@ KBUILD_CFLAGS	+= -fomit-frame-pointer
 endif
 endif
 
+KBUILD_CFLAGS   += $(call cc-option, -fno-var-tracking-assignments)
+
 ifdef CONFIG_DEBUG_INFO
 KBUILD_CFLAGS	+= -g
-KBUILD_AFLAGS	+= -Wa,--gdwarf-2
+KBUILD_AFLAGS	+= -Wa,-gdwarf-2
 endif
 
 ifdef CONFIG_DEBUG_INFO_REDUCED
@@ -731,6 +752,8 @@ ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
 	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
 endif
 
+include $(srctree)/scripts/Makefile.extrawarn
+
 # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
 KBUILD_CPPFLAGS += $(KCPPFLAGS)
 KBUILD_AFLAGS += $(KAFLAGS)
@@ -775,10 +798,10 @@ MODLIB	= $(INSTALL_MOD_PATH)/lib/modules/$(KERNELRELEASE)
 export MODLIB
 
 #
-#  INSTALL_MOD_STRIP, if defined, will cause modules to be
-#  stripped after they are installed.  If INSTALL_MOD_STRIP is '1', then
-#  the default option --strip-debug will be used.  Otherwise,
-#  INSTALL_MOD_STRIP value will be used as the options to the strip command.
+# INSTALL_MOD_STRIP, if defined, will cause modules to be
+# stripped after they are installed.  If INSTALL_MOD_STRIP is '1', then
+# the default option --strip-debug will be used.  Otherwise,
+# INSTALL_MOD_STRIP value will be used as the options to the strip command.
 
 ifdef INSTALL_MOD_STRIP
 ifeq ($(INSTALL_MOD_STRIP),1)
@@ -863,7 +886,7 @@ ifdef CONFIG_BUILD_DOCSRC
 endif
 	+$(call if_changed,link-vmlinux)
 
-# The actual objects are generated when descending, 
+# The actual objects are generated when descending,
 # make sure no implicit rule kicks in
 $(sort $(vmlinux-deps)): $(vmlinux-dirs) ;
 
@@ -1021,11 +1044,11 @@ ifdef CONFIG_MODULES
 
 all: modules
 
-#	Build modules
+# Build modules
 #
-#	A module can be listed more than once in obj-m resulting in
-#	duplicate lines in modules.order files.  Those are removed
-#	using awk while concatenating to the final file.
+# A module can be listed more than once in obj-m resulting in
+# duplicate lines in modules.order files.  Those are removed
+# using awk while concatenating to the final file.
 
 PHONY += modules
 modules: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux) modules.builtin
@@ -1054,10 +1077,10 @@ _modinst_:
 	@rm -rf $(MODLIB)/kernel
 	@rm -f $(MODLIB)/source
 	@mkdir -p $(MODLIB)/kernel
-	@ln -s $(srctree) $(MODLIB)/source
+	@ln -s `cd $(srctree) && /bin/pwd` $(MODLIB)/source
 	@if [ ! $(objtree) -ef  $(MODLIB)/build ]; then \
 		rm -f $(MODLIB)/build ; \
-		ln -s $(objtree) $(MODLIB)/build ; \
+		ln -s $(CURDIR) $(MODLIB)/build ; \
 	fi
 	@cp -f $(objtree)/modules.order $(MODLIB)/
 	@cp -f $(objtree)/modules.builtin $(MODLIB)/
@@ -1104,7 +1127,7 @@ CLEAN_DIRS  += $(MODVERDIR)
 
 # Directories & files removed with 'make mrproper'
 MRPROPER_DIRS  += include/config usr/include include/generated          \
-                  arch/*/include/generated .tmp_objdiff
+		  arch/*/include/generated .tmp_objdiff
 MRPROPER_FILES += .config .config.old .version .old_version $(version_h) \
 		  Module.symvers tags TAGS cscope* GPATH GTAGS GRTAGS GSYMS \
 		  signing_key.priv signing_key.x509 x509.genkey		\
@@ -1155,7 +1178,7 @@ distclean: mrproper
 # Packaging of the kernel to various formats
 # ---------------------------------------------------------------------------
 # rpm target kept for backward compatibility
-package-dir	:= $(srctree)/scripts/package
+package-dir	:= scripts/package
 
 %src-pkg: FORCE
 	$(Q)$(MAKE) $(build)=$(package-dir) $@
@@ -1478,7 +1501,7 @@ endif
 	$(build)=$(build-dir) $(@:.ko=.o)
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
 
-# FIXME Should go into a make.lib or something 
+# FIXME Should go into a make.lib or something
 # ===========================================================================
 
 quiet_cmd_rmdirs = $(if $(wildcard $(rm-dirs)),CLEAN   $(wildcard $(rm-dirs)))
diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h
index 6cb7fe85c4b..b4cf0369039 100644
--- a/arch/alpha/include/asm/processor.h
+++ b/arch/alpha/include/asm/processor.h
@@ -57,6 +57,7 @@ unsigned long get_wchan(struct task_struct *p);
   ((tsk) == current ? rdusp() : task_thread_info(tsk)->pcb.usp)
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 #define ARCH_HAS_PREFETCH
 #define ARCH_HAS_PREFETCHW
diff --git a/arch/arc/boot/dts/angel4.dts b/arch/arc/boot/dts/angel4.dts
index bcf662d21a5..5bb2fdaca02 100644
--- a/arch/arc/boot/dts/angel4.dts
+++ b/arch/arc/boot/dts/angel4.dts
@@ -17,7 +17,7 @@
 	interrupt-parent = <&intc>;
 
 	chosen {
-		bootargs = "console=ttyARC0,115200n8";
+		bootargs = "console=ttyARC0,115200n8 earlyprintk=ttyARC0";
 	};
 
 	aliases {
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 2fd3162ec4d..b3c750979aa 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -55,4 +55,31 @@ extern void read_decode_cache_bcr(void);
 
 #endif	/* !__ASSEMBLY__ */
 
+/* Instruction cache related Auxiliary registers */
+#define ARC_REG_IC_BCR		0x77	/* Build Config reg */
+#define ARC_REG_IC_IVIC		0x10
+#define ARC_REG_IC_CTRL		0x11
+#define ARC_REG_IC_IVIL		0x19
+#if defined(CONFIG_ARC_MMU_V3)
+#define ARC_REG_IC_PTAG		0x1E
+#endif
+
+/* Bit val in IC_CTRL */
+#define IC_CTRL_CACHE_DISABLE   0x1
+
+/* Data cache related Auxiliary registers */
+#define ARC_REG_DC_BCR		0x72	/* Build Config reg */
+#define ARC_REG_DC_IVDC		0x47
+#define ARC_REG_DC_CTRL		0x48
+#define ARC_REG_DC_IVDL		0x4A
+#define ARC_REG_DC_FLSH		0x4B
+#define ARC_REG_DC_FLDL		0x4C
+#if defined(CONFIG_ARC_MMU_V3)
+#define ARC_REG_DC_PTAG		0x5C
+#endif
+
+/* Bit val in DC_CTRL */
+#define DC_CTRL_INV_MODE_FLUSH  0x40
+#define DC_CTRL_FLUSH_STATUS    0x100
+
 #endif /* _ASM_CACHE_H */
diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h
index 291a70db68b..fb4efb64897 100644
--- a/arch/arc/include/asm/irq.h
+++ b/arch/arc/include/asm/irq.h
@@ -19,8 +19,6 @@
 #include <asm-generic/irq.h>
 
 extern void arc_init_IRQ(void);
-extern int get_hw_config_num_irq(void);
-
-void arc_local_timer_setup(unsigned int cpu);
+void arc_local_timer_setup(void);
 
 #endif
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index 15334ab66b5..82588f3ba77 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -18,7 +18,6 @@
 
 #ifndef __ASSEMBLY__
 
-#include <asm/arcregs.h>	/* for STATUS_E1_MASK et all */
 #include <asm/ptrace.h>
 
 /* Arch specific stuff which needs to be saved per task.
@@ -41,15 +40,13 @@ struct thread_struct {
 /* Forward declaration, a strange C thing */
 struct task_struct;
 
-/*
- * Return saved PC of a blocked thread.
- */
+/* Return saved PC of a blocked thread  */
 unsigned long thread_saved_pc(struct task_struct *t);
 
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_SIZE + (void *)task_stack_page(p)) - 1)
 
-/* Free all resources held by a thread. */
+/* Free all resources held by a thread */
 #define release_thread(thread) do { } while (0)
 
 /* Prepare to copy thread state - unlazy all lazy status */
@@ -65,6 +62,8 @@ unsigned long thread_saved_pc(struct task_struct *t);
 #define cpu_relax()	do { } while (0)
 #endif
 
+#define cpu_relax_lowlatency() cpu_relax()
+
 #define copy_segments(tsk, mm)      do { } while (0)
 #define release_segments(mm)        do { } while (0)
 
@@ -82,26 +81,8 @@ unsigned long thread_saved_pc(struct task_struct *t);
 #define KSTK_BLINK(tsk) KSTK_REG(tsk, 4)
 #define KSTK_FP(tsk)    KSTK_REG(tsk, 0)
 
-/*
- * Do necessary setup to start up a newly executed thread.
- *
- * E1,E2 so that Interrupts are enabled in user mode
- * L set, so Loop inhibited to begin with
- * lp_start and lp_end seeded with bogus non-zero values so to easily catch
- * the ARC700 sr to lp_start hardware bug
- */
-#define start_thread(_regs, _pc, _usp)				\
-do {								\
-	set_fs(USER_DS); /* reads from user space */		\
-	(_regs)->ret = (_pc);					\
-	/* Interrupts enabled in User Mode */			\
-	(_regs)->status32 = STATUS_U_MASK | STATUS_L_MASK	\
-		| STATUS_E1_MASK | STATUS_E2_MASK;		\
-	(_regs)->sp = (_usp);					\
-	/* bogus seed values for debugging */			\
-	(_regs)->lp_start = 0x10;				\
-	(_regs)->lp_end = 0x80;					\
-} while (0)
+extern void start_thread(struct pt_regs * regs, unsigned long pc,
+			 unsigned long usp);
 
 extern unsigned int get_wchan(struct task_struct *p);
 
diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild
index 18fefaea73f..f50d02df78d 100644
--- a/arch/arc/include/uapi/asm/Kbuild
+++ b/arch/arc/include/uapi/asm/Kbuild
@@ -2,11 +2,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 header-y += elf.h
 header-y += page.h
-header-y += setup.h
-header-y += byteorder.h
 header-y += cachectl.h
-header-y += ptrace.h
-header-y += sigcontext.h
-header-y += signal.h
-header-y += swab.h
-header-y += unistd.h
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 2618cc13ba7..76a7739aab1 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -11,6 +11,7 @@
 #ifndef _UAPI__ASM_ARC_PTRACE_H
 #define _UAPI__ASM_ARC_PTRACE_H
 
+#define PTRACE_GET_THREAD_AREA	25
 
 #ifndef __ASSEMBLY__
 /*
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
index 2ff0347a2fd..e248594097e 100644
--- a/arch/arc/kernel/ctx_sw_asm.S
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -10,9 +10,9 @@
  *  -This is the more "natural" hand written assembler
  */
 
+#include <linux/linkage.h>
 #include <asm/entry.h>       /* For the SAVE_* macros */
 #include <asm/asm-offsets.h>
-#include <asm/linkage.h>
 
 #define KSP_WORD_OFF 	((TASK_THREAD + THREAD_KSP) / 4)
 
diff --git a/arch/arc/kernel/devtree.c b/arch/arc/kernel/devtree.c
index 0b3ef4025d8..fffdb5e41b2 100644
--- a/arch/arc/kernel/devtree.c
+++ b/arch/arc/kernel/devtree.c
@@ -41,7 +41,7 @@ const struct machine_desc * __init setup_machine_fdt(void *dt)
 {
 	const struct machine_desc *mdesc;
 	unsigned long dt_root;
-	void *clk;
+	const void *clk;
 	int len;
 
 	if (!early_init_dt_scan(dt))
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 29b82adbf0b..83a046a7cd0 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -156,7 +156,7 @@ ARCFP_DATA int1_saved_reg
 int1_saved_reg:
 	.zero 4
 
-/* Each Interrupt level needs it's own scratch */
+/* Each Interrupt level needs its own scratch */
 #ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
 
 ARCFP_DATA int2_saved_reg
@@ -473,7 +473,7 @@ trap_with_param:
 	lr  r0, [efa]
 	mov r1, sp
 
-	; Now that we have read EFA, its safe to do "fake" rtie
+	; Now that we have read EFA, it is safe to do "fake" rtie
 	;   and get out of CPU exception mode
 	FAKE_RET_FROM_EXCPN r11
 
@@ -678,9 +678,9 @@ not_exception:
 	brne r9, event_IRQ2, 149f
 
 	;------------------------------------------------------------------
-	; if L2 IRQ interrupted a L1 ISR,  we'd disbaled preemption earlier
-	; so that sched doesnt move to new task, causing L1 to be delayed
-	; undeterministically. Now that we've achieved that, lets reset
+	; if L2 IRQ interrupted an L1 ISR,  we'd disabled preemption earlier
+	; so that sched doesn't move to new task, causing L1 to be delayed
+	; undeterministically. Now that we've achieved that, let's reset
 	; things to what they were, before returning from L2 context
 	;----------------------------------------------------------------
 
@@ -736,7 +736,7 @@ ENTRY(ret_from_fork)
 	; put last task in scheduler queue
 	bl   @schedule_tail
 
-	; If kernel thread, jump to it's entry-point
+	; If kernel thread, jump to its entry-point
 	ld   r9, [sp, PT_status32]
 	brne r9, 0, 1f
 
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 4ad04915dc6..4d2481bd8b9 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -12,10 +12,42 @@
  *      to skip certain things during boot on simulator
  */
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 #include <asm/entry.h>
-#include <linux/linkage.h>
 #include <asm/arcregs.h>
+#include <asm/cache.h>
+
+.macro CPU_EARLY_SETUP
+
+	; Setting up Vectror Table (in case exception happens in early boot
+	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+
+	; Disable I-cache/D-cache if kernel so configured
+	lr	r5, [ARC_REG_IC_BCR]
+	breq    r5, 0, 1f		; I$ doesn't exist
+	lr	r5, [ARC_REG_IC_CTRL]
+#ifdef CONFIG_ARC_HAS_ICACHE
+	bclr	r5, r5, 0		; 0 - Enable, 1 is Disable
+#else
+	bset	r5, r5, 0		; I$ exists, but is not used
+#endif
+	sr	r5, [ARC_REG_IC_CTRL]
+
+1:
+	lr	r5, [ARC_REG_DC_BCR]
+	breq    r5, 0, 1f		; D$ doesn't exist
+	lr	r5, [ARC_REG_DC_CTRL]
+	bclr	r5, r5, 6		; Invalidate (discard w/o wback)
+#ifdef CONFIG_ARC_HAS_DCACHE
+	bclr	r5, r5, 0		; Enable (+Inv)
+#else
+	bset	r5, r5, 0		; Disable (+Inv)
+#endif
+	sr	r5, [ARC_REG_DC_CTRL]
+
+1:
+.endm
 
 	.cpu A7
 
@@ -27,7 +59,7 @@ stext:
 	; Don't clobber r0-r2 yet. It might have bootloader provided info
 	;-------------------------------------------------------------------
 
-	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+	CPU_EARLY_SETUP
 
 #ifdef CONFIG_SMP
 	; Ensure Boot (Master) proceeds. Others wait in platform dependent way
@@ -45,10 +77,11 @@ stext:
 	; Clear BSS before updating any globals
 	; XXX: use ZOL here
 	mov	r5, __bss_start
-	mov	r6, __bss_stop
+	sub	r6, __bss_stop, r5
+	lsr.f	lp_count, r6, 2
+	lpnz	1f
+	st.ab   0, [r5, 4]
 1:
-	st.ab   0, [r5,4]
-	brlt    r5, r6, 1b
 
 	; Uboot - kernel ABI
 	;    r0 = [0] No uboot interaction, [1] cmdline in r2, [2] DTB in r2
@@ -90,7 +123,7 @@ stext:
 
 first_lines_of_secondary:
 
-	sr	@_int_vec_base_lds, [AUX_INTR_VEC_BASE]
+	CPU_EARLY_SETUP
 
 	; setup per-cpu idle task as "current" on this CPU
 	ld	r0, [@secondary_idle_tsk]
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index a4b141ee9a6..7d653c0d077 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -150,24 +150,6 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
-int get_hw_config_num_irq(void)
-{
-	uint32_t val = read_aux_reg(ARC_REG_VECBASE_BCR);
-
-	switch (val & 0x03) {
-	case 0:
-		return 16;
-	case 1:
-		return 32;
-	case 2:
-		return 8;
-	default:
-		return 0;
-	}
-
-	return 0;
-}
-
 /*
  * arch_local_irq_enable - Enable interrupts.
  *
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 63177e4cb66..b9a5685a990 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -99,10 +99,6 @@ static int arc_pmu_event_init(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int ret;
 
-	/* ARC 700 PMU does not support sampling events */
-	if (is_sampling_event(event))
-		return -ENOENT;
-
 	switch (event->attr.type) {
 	case PERF_TYPE_HARDWARE:
 		if (event->attr.config >= PERF_COUNT_HW_MAX)
@@ -298,6 +294,9 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		.read		= arc_pmu_read,
 	};
 
+	/* ARC 700 PMU does not support sampling events */
+	arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	ret = perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
 
 	return ret;
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 07a3a968fe4..fdd89715d2d 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -151,6 +151,29 @@ int copy_thread(unsigned long clone_flags,
 }
 
 /*
+ * Do necessary setup to start up a new user task
+ */
+void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp)
+{
+	set_fs(USER_DS); /* user space */
+
+	regs->sp = usp;
+	regs->ret = pc;
+
+	/*
+	 * [U]ser Mode bit set
+	 * [L] ZOL loop inhibited to begin with - cleared by a LP insn
+	 * Interrupts enabled
+	 */
+	regs->status32 = STATUS_U_MASK | STATUS_L_MASK |
+			 STATUS_E1_MASK | STATUS_E2_MASK;
+
+	/* bogus seed values for debugging */
+	regs->lp_start = 0x10;
+	regs->lp_end = 0x80;
+}
+
+/*
  * Some archs flush debug and FPU info here
  */
 void flush_thread(void)
diff --git a/arch/arc/kernel/ptrace.c b/arch/arc/kernel/ptrace.c
index 5d76706139d..13b3ffb27a3 100644
--- a/arch/arc/kernel/ptrace.c
+++ b/arch/arc/kernel/ptrace.c
@@ -146,6 +146,10 @@ long arch_ptrace(struct task_struct *child, long request,
 	pr_debug("REQ=%ld: ADDR =0x%lx, DATA=0x%lx)\n", request, addr, data);
 
 	switch (request) {
+	case PTRACE_GET_THREAD_AREA:
+		ret = put_user(task_thread_info(child)->thr_ptr,
+			       (unsigned long __user *)data);
+		break;
 	default:
 		ret = ptrace_request(child, request, addr, data);
 		break;
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 40859e5619f..c802bb50060 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -138,7 +138,7 @@ void start_kernel_secondary(void)
 	if (machine_desc->init_smp)
 		machine_desc->init_smp(smp_processor_id());
 
-	arc_local_timer_setup(cpu);
+	arc_local_timer_setup();
 
 	local_irq_enable();
 	preempt_disable();
@@ -337,8 +337,19 @@ irqreturn_t do_IPI(int irq, void *dev_id)
  * API called by platform code to hookup arch-common ISR to their IPI IRQ
  */
 static DEFINE_PER_CPU(int, ipi_dev);
+
+static struct irqaction arc_ipi_irq = {
+        .name    = "IPI Interrupt",
+        .flags   = IRQF_PERCPU,
+        .handler = do_IPI,
+};
+
 int smp_ipi_irq_setup(int cpu, int irq)
 {
-	int *dev_id = &per_cpu(ipi_dev, smp_processor_id());
-	return request_percpu_irq(irq, do_IPI, "IPI Interrupt", dev_id);
+	if (!cpu)
+		return setup_irq(irq, &arc_ipi_irq);
+	else
+		arch_unmask_irq(irq);
+
+	return 0;
 }
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index 71c42521c77..36c2aa99436 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -219,12 +219,13 @@ static struct irqaction arc_timer_irq = {
 /*
  * Setup the local event timer for @cpu
  */
-void arc_local_timer_setup(unsigned int cpu)
+void arc_local_timer_setup()
 {
-	struct clock_event_device *clk = &per_cpu(arc_clockevent_device, cpu);
+	struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device);
+	int cpu = smp_processor_id();
 
-	clk->cpumask = cpumask_of(cpu);
-	clockevents_config_and_register(clk, arc_get_core_freq(),
+	evt->cpumask = cpumask_of(cpu);
+	clockevents_config_and_register(evt, arc_get_core_freq(),
 					0, ARC_TIMER_MAX);
 
 	/*
@@ -261,7 +262,7 @@ void __init time_init(void)
 		clocksource_register_hz(&arc_counter, arc_get_core_freq());
 
 	/* sets up the periodic event timer */
-	arc_local_timer_setup(smp_processor_id());
+	arc_local_timer_setup();
 
 	if (machine_desc->init_time)
 		machine_desc->init_time();
diff --git a/arch/arc/kernel/vmlinux.lds.S b/arch/arc/kernel/vmlinux.lds.S
index 2555f5886af..dd35bde39f6 100644
--- a/arch/arc/kernel/vmlinux.lds.S
+++ b/arch/arc/kernel/vmlinux.lds.S
@@ -116,7 +116,7 @@ SECTIONS
 
 	_edata = .;
 
-	BSS_SECTION(0, 0, 0)
+	BSS_SECTION(4, 4, 4)
 
 #ifdef CONFIG_ARC_DW2_UNWIND
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 89edf7961a2..353b202c37c 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -73,33 +73,6 @@
 #include <asm/cachectl.h>
 #include <asm/setup.h>
 
-/* Instruction cache related Auxiliary registers */
-#define ARC_REG_IC_BCR		0x77	/* Build Config reg */
-#define ARC_REG_IC_IVIC		0x10
-#define ARC_REG_IC_CTRL		0x11
-#define ARC_REG_IC_IVIL		0x19
-#if (CONFIG_ARC_MMU_VER > 2)
-#define ARC_REG_IC_PTAG		0x1E
-#endif
-
-/* Bit val in IC_CTRL */
-#define IC_CTRL_CACHE_DISABLE   0x1
-
-/* Data cache related Auxiliary registers */
-#define ARC_REG_DC_BCR		0x72	/* Build Config reg */
-#define ARC_REG_DC_IVDC		0x47
-#define ARC_REG_DC_CTRL		0x48
-#define ARC_REG_DC_IVDL		0x4A
-#define ARC_REG_DC_FLSH		0x4B
-#define ARC_REG_DC_FLDL		0x4C
-#if (CONFIG_ARC_MMU_VER > 2)
-#define ARC_REG_DC_PTAG		0x5C
-#endif
-
-/* Bit val in DC_CTRL */
-#define DC_CTRL_INV_MODE_FLUSH  0x40
-#define DC_CTRL_FLUSH_STATUS    0x100
-
 char *arc_cache_mumbojumbo(int c, char *buf, int len)
 {
 	int n = 0;
@@ -168,72 +141,43 @@ void read_decode_cache_bcr(void)
  */
 void arc_cache_init(void)
 {
-	unsigned int cpu = smp_processor_id();
-	struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
-	struct cpuinfo_arc_cache *dc = &cpuinfo_arc700[cpu].dcache;
-	unsigned int dcache_does_alias, temp;
+	unsigned int __maybe_unused cpu = smp_processor_id();
+	struct cpuinfo_arc_cache __maybe_unused *ic, __maybe_unused *dc;
 	char str[256];
 
 	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
 
-	if (!ic->ver)
-		goto chk_dc;
-
 #ifdef CONFIG_ARC_HAS_ICACHE
-	/* 1. Confirm some of I-cache params which Linux assumes */
-	if (ic->line_len != L1_CACHE_BYTES)
-		panic("Cache H/W doesn't match kernel Config");
-
-	if (ic->ver != CONFIG_ARC_MMU_VER)
-		panic("Cache ver doesn't match MMU ver\n");
-#endif
-
-	/* Enable/disable I-Cache */
-	temp = read_aux_reg(ARC_REG_IC_CTRL);
-
-#ifdef CONFIG_ARC_HAS_ICACHE
-	temp &= ~IC_CTRL_CACHE_DISABLE;
-#else
-	temp |= IC_CTRL_CACHE_DISABLE;
+	ic = &cpuinfo_arc700[cpu].icache;
+	if (ic->ver) {
+		if (ic->line_len != L1_CACHE_BYTES)
+			panic("ICache line [%d] != kernel Config [%d]",
+			      ic->line_len, L1_CACHE_BYTES);
+
+		if (ic->ver != CONFIG_ARC_MMU_VER)
+			panic("Cache ver [%d] doesn't match MMU ver [%d]\n",
+			      ic->ver, CONFIG_ARC_MMU_VER);
+	}
 #endif
 
-	write_aux_reg(ARC_REG_IC_CTRL, temp);
-
-chk_dc:
-	if (!dc->ver)
-		return;
-
 #ifdef CONFIG_ARC_HAS_DCACHE
-	if (dc->line_len != L1_CACHE_BYTES)
-		panic("Cache H/W doesn't match kernel Config");
+	dc = &cpuinfo_arc700[cpu].dcache;
+	if (dc->ver) {
+		unsigned int dcache_does_alias;
 
-	/* check for D-Cache aliasing */
-	dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE;
+		if (dc->line_len != L1_CACHE_BYTES)
+			panic("DCache line [%d] != kernel Config [%d]",
+			      dc->line_len, L1_CACHE_BYTES);
 
-	if (dcache_does_alias && !cache_is_vipt_aliasing())
-		panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-	else if (!dcache_does_alias && cache_is_vipt_aliasing())
-		panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n");
-#endif
-
-	/* Set the default Invalidate Mode to "simpy discard dirty lines"
-	 *  as this is more frequent then flush before invalidate
-	 * Ofcourse we toggle this default behviour when desired
-	 */
-	temp = read_aux_reg(ARC_REG_DC_CTRL);
-	temp &= ~DC_CTRL_INV_MODE_FLUSH;
+		/* check for D-Cache aliasing */
+		dcache_does_alias = (dc->sz / dc->assoc) > PAGE_SIZE;
 
-#ifdef CONFIG_ARC_HAS_DCACHE
-	/* Enable D-Cache: Clear Bit 0 */
-	write_aux_reg(ARC_REG_DC_CTRL, temp & ~IC_CTRL_CACHE_DISABLE);
-#else
-	/* Flush D cache */
-	write_aux_reg(ARC_REG_DC_FLSH, 0x1);
-	/* Disable D cache */
-	write_aux_reg(ARC_REG_DC_CTRL, temp | IC_CTRL_CACHE_DISABLE);
+		if (dcache_does_alias && !cache_is_vipt_aliasing())
+			panic("Enable CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+		else if (!dcache_does_alias && cache_is_vipt_aliasing())
+			panic("Don't need CONFIG_ARC_CACHE_VIPT_ALIASING\n");
+	}
 #endif
-
-	return;
 }
 
 #define OP_INV		0x1
@@ -253,12 +197,16 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
 
 	if (cacheop == OP_INV_IC) {
 		aux_cmd = ARC_REG_IC_IVIL;
+#if (CONFIG_ARC_MMU_VER > 2)
 		aux_tag = ARC_REG_IC_PTAG;
+#endif
 	}
 	else {
 		/* d$ cmd: INV (discard or wback-n-discard) OR FLUSH (wback) */
 		aux_cmd = cacheop & OP_INV ? ARC_REG_DC_IVDL : ARC_REG_DC_FLDL;
+#if (CONFIG_ARC_MMU_VER > 2)
 		aux_tag = ARC_REG_DC_PTAG;
+#endif
 	}
 
 	/* Ensure we properly floor/ceil the non-line aligned/sized requests
@@ -441,7 +389,7 @@ static inline void __dc_line_op(unsigned long paddr, unsigned long vaddr,
 /***********************************************************
  * Machine specific helper for per line I-Cache invalidate.
  */
-static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr,
+static void __ic_line_inv_vaddr_local(unsigned long paddr, unsigned long vaddr,
 				unsigned long sz)
 {
 	unsigned long flags;
@@ -457,6 +405,23 @@ static inline void __ic_entire_inv(void)
 	read_aux_reg(ARC_REG_IC_CTRL);	/* blocks */
 }
 
+struct ic_line_inv_vaddr_ipi {
+	unsigned long paddr, vaddr;
+	int sz;
+};
+
+static void __ic_line_inv_vaddr_helper(void *info)
+{
+        struct ic_line_inv_vaddr_ipi *ic_inv = (struct ic_line_inv_vaddr_ipi*) info;
+        __ic_line_inv_vaddr_local(ic_inv->paddr, ic_inv->vaddr, ic_inv->sz);
+}
+
+static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr,
+				unsigned long sz)
+{
+	struct ic_line_inv_vaddr_ipi ic_inv = { paddr, vaddr , sz};
+	on_each_cpu(__ic_line_inv_vaddr_helper, &ic_inv, 1);
+}
 #else
 
 #define __ic_entire_inv()
@@ -605,12 +570,8 @@ void flush_icache_range(unsigned long kstart, unsigned long kend)
  */
 void __sync_icache_dcache(unsigned long paddr, unsigned long vaddr, int len)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__ic_line_inv_vaddr(paddr, vaddr, len);
 	__dc_line_op(paddr, vaddr, len, OP_FLUSH_N_INV);
-	local_irq_restore(flags);
+	__ic_line_inv_vaddr(paddr, vaddr, len);
 }
 
 /* wrapper to compile time eliminate alignment checks in flush loop */
diff --git a/arch/arc/plat-arcfpga/Kconfig b/arch/arc/plat-arcfpga/Kconfig
index 33058aa40e7..e27bb5cc3c1 100644
--- a/arch/arc/plat-arcfpga/Kconfig
+++ b/arch/arc/plat-arcfpga/Kconfig
@@ -48,36 +48,4 @@ config ARC_SERIAL_BAUD
 	help
 	  Baud rate for the ARC UART
 
-menuconfig ARC_HAS_BVCI_LAT_UNIT
-	bool "BVCI Bus Latency Unit"
-	depends on ARC_BOARD_ML509 || ARC_BOARD_ANGEL4
-	help
-	  IP to add artificial latency to BVCI Bus Based FPGA builds.
-	  The default latency (even worst case) for FPGA is non-realistic
-	  (~10 SDRAM, ~5 SSRAM).
-
-config BVCI_LAT_UNITS
-	hex "Latency Unit(s) Bitmap"
-	default "0x0"
-	depends on ARC_HAS_BVCI_LAT_UNIT
-	help
-	  There are multiple Latency Units corresponding to the many
-	  interfaces of the system bus arbiter (both CPU side as well as
-	  the peripheral side).
-	  To add latency to ALL memory transaction, choose Unit 0, otherwise
-	  for finer grainer - interface wise latency, specify a bitmap (1 bit
-	  per unit) of all units. e.g. 1,2,12 will be 0x1003
-
-	  Unit  0 - System Arb and Mem Controller
-	  Unit  1 - I$ and System Bus
-	  Unit  2 - D$ and System Bus
-	  ..
-	  Unit 12 - IDE Disk controller and System Bus
-
-config BVCI_LAT_CYCLES
-	int "Latency Value in cycles"
-	range 0 63
-	default "30"
-	depends on ARC_HAS_BVCI_LAT_UNIT
-
 endif
diff --git a/arch/arc/plat-arcfpga/Makefile b/arch/arc/plat-arcfpga/Makefile
index a44e22ebc1b..4d1bddc34b5 100644
--- a/arch/arc/plat-arcfpga/Makefile
+++ b/arch/arc/plat-arcfpga/Makefile
@@ -9,4 +9,4 @@
 KBUILD_CFLAGS	+= -Iarch/arc/plat-arcfpga/include
 
 obj-y := platform.o irq.o
-obj-$(CONFIG_SMP)		+= smp.o
+obj-$(CONFIG_ISS_SMP_EXTN)		+= smp.o
diff --git a/arch/arc/plat-arcfpga/platform.c b/arch/arc/plat-arcfpga/platform.c
index 19b76b61f44..61c7e599738 100644
--- a/arch/arc/plat-arcfpga/platform.c
+++ b/arch/arc/plat-arcfpga/platform.c
@@ -22,59 +22,6 @@
 #include <plat/smp.h>
 #include <plat/irq.h>
 
-/*-----------------------BVCI Latency Unit -----------------------------*/
-
-#ifdef CONFIG_ARC_HAS_BVCI_LAT_UNIT
-
-int lat_cycles = CONFIG_BVCI_LAT_CYCLES;
-
-/* BVCI Bus Profiler: Latency Unit */
-static void __init setup_bvci_lat_unit(void)
-{
-#define MAX_BVCI_UNITS 12
-
-	unsigned int i;
-	unsigned int *base = (unsigned int *)BVCI_LAT_UNIT_BASE;
-	const unsigned long units_req = CONFIG_BVCI_LAT_UNITS;
-	const unsigned int REG_UNIT = 21;
-	const unsigned int REG_VAL = 22;
-
-	/*
-	 * There are multiple Latency Units corresponding to the many
-	 * interfaces of the system bus arbiter (both CPU side as well as
-	 * the peripheral side).
-	 *
-	 * Unit  0 - System Arb and Mem Controller - adds latency to all
-	 *	    memory trasactions
-	 * Unit  1 - I$ and System Bus
-	 * Unit  2 - D$ and System Bus
-	 * ..
-	 * Unit 12 - IDE Disk controller and System Bus
-	 *
-	 * The programmers model requires writing to lat_unit reg first
-	 * and then the latency value (cycles) to lat_value reg
-	 */
-
-	if (CONFIG_BVCI_LAT_UNITS == 0) {
-		writel(0, base + REG_UNIT);
-		writel(lat_cycles, base + REG_VAL);
-		pr_info("BVCI Latency for all Memory Transactions %d cycles\n",
-			lat_cycles);
-	} else {
-		for_each_set_bit(i, &units_req, MAX_BVCI_UNITS) {
-			writel(i + 1, base + REG_UNIT); /* loop is 0 based */
-			writel(lat_cycles, base + REG_VAL);
-			pr_info("BVCI Latency for Unit[%d] = %d cycles\n",
-				(i + 1), lat_cycles);
-		}
-	}
-}
-#else
-static void __init setup_bvci_lat_unit(void)
-{
-}
-#endif
-
 /*----------------------- Platform Devices -----------------------------*/
 
 #if IS_ENABLED(CONFIG_SERIAL_ARC)
@@ -132,16 +79,11 @@ static void arc_fpga_serial_init(void)
 				   ARRAY_SIZE(fpga_early_devs));
 
 	/*
-	 * ARC console driver registers itself as an early platform driver
-	 * of class "earlyprintk".
-	 * Install it here, followed by probe of devices.
-	 * The installation here doesn't require earlyprintk in command line
-	 * To do so however, replace the lines below with
-	 *	parse_early_param();
-	 *	early_platform_driver_probe("earlyprintk", 1, 1);
-	 *						      ^^
+	 * ARC console driver registers (build time) as an early platform driver
+	 * of class "earlyprintk". However it needs explicit cmdline toggle
+	 * "earlyprintk=ttyARC0" to be successfuly runtime registered.
+	 * Otherwise the early probe below fails to find the driver
 	 */
-	early_platform_driver_register_all("earlyprintk");
 	early_platform_driver_probe("earlyprintk", 1, 0);
 
 	/*
@@ -165,11 +107,9 @@ static void __init plat_fpga_early_init(void)
 {
 	pr_info("[plat-arcfpga]: registering early dev resources\n");
 
-	setup_bvci_lat_unit();
-
 	arc_fpga_serial_init();
 
-#ifdef CONFIG_SMP
+#ifdef CONFIG_ISS_SMP_EXTN
 	iss_model_init_early_smp();
 #endif
 }
@@ -211,7 +151,7 @@ MACHINE_START(ANGEL4, "angel4")
 	.init_early	= plat_fpga_early_init,
 	.init_machine	= plat_fpga_populate_dev,
 	.init_irq	= plat_fpga_init_IRQ,
-#ifdef CONFIG_SMP
+#ifdef CONFIG_ISS_SMP_EXTN
 	.init_smp	= iss_model_init_smp,
 #endif
 MACHINE_END
diff --git a/arch/arc/plat-arcfpga/smp.c b/arch/arc/plat-arcfpga/smp.c
index 8a12741f5f7..92bad912207 100644
--- a/arch/arc/plat-arcfpga/smp.c
+++ b/arch/arc/plat-arcfpga/smp.c
@@ -42,6 +42,24 @@ static void iss_model_smp_wakeup_cpu(int cpu, unsigned long pc)
 
 }
 
+static inline int get_hw_config_num_irq(void)
+{
+	uint32_t val = read_aux_reg(ARC_REG_VECBASE_BCR);
+
+	switch (val & 0x03) {
+	case 0:
+		return 16;
+	case 1:
+		return 32;
+	case 2:
+		return 8;
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
 /*
  * Any SMP specific init any CPU does when it comes up.
  * Here we setup the CPU to enable Inter-Processor-Interrupts
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 87b63fde06d..290f02ee015 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -6,6 +6,7 @@ config ARM
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -175,13 +176,6 @@ config ARCH_HAS_ILOG2_U32
 config ARCH_HAS_ILOG2_U64
 	bool
 
-config ARCH_HAS_CPUFREQ
-	bool
-	help
-	  Internal node to signify that the ARCH has CPUFREQ support
-	  and that the relevant menu configurations are displayed for
-	  it.
-
 config ARCH_HAS_BANDGAP
 	bool
 
@@ -318,9 +312,8 @@ config ARCH_MULTIPLATFORM
 
 config ARCH_INTEGRATOR
 	bool "ARM Ltd. Integrator family"
-	select ARCH_HAS_CPUFREQ
 	select ARM_AMBA
-	select ARM_PATCH_PHYS_VIRT
+	select ARM_PATCH_PHYS_VIRT if MMU
 	select AUTO_ZRELADDR
 	select COMMON_CLK
 	select COMMON_CLK_VERSATILE
@@ -538,7 +531,6 @@ config ARCH_DOVE
 
 config ARCH_KIRKWOOD
 	bool "Marvell Kirkwood"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
 	select GENERIC_CLOCKEVENTS
@@ -637,7 +629,6 @@ config ARCH_LPC32XX
 config ARCH_PXA
 	bool "PXA2xx/PXA3xx-based"
 	depends on MMU
-	select ARCH_HAS_CPUFREQ
 	select ARCH_MTD_XIP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_CPU_SUSPEND if PM
@@ -668,7 +659,7 @@ config ARCH_MSM
 config ARCH_SHMOBILE_LEGACY
 	bool "Renesas ARM SoCs (non-multiplatform)"
 	select ARCH_SHMOBILE
-	select ARM_PATCH_PHYS_VIRT
+	select ARM_PATCH_PHYS_VIRT if MMU
 	select CLKDEV_LOOKUP
 	select GENERIC_CLOCKEVENTS
 	select HAVE_ARM_SCU if SMP
@@ -707,7 +698,6 @@ config ARCH_RPC
 
 config ARCH_SA1100
 	bool "SA1100-based"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_MTD_XIP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SPARSEMEM_ENABLE
@@ -725,7 +715,6 @@ config ARCH_SA1100
 
 config ARCH_S3C24XX
 	bool "Samsung S3C24XX SoCs"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select ATAGS
 	select CLKDEV_LOOKUP
@@ -746,7 +735,6 @@ config ARCH_S3C24XX
 
 config ARCH_S3C64XX
 	bool "Samsung S3C64XX"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_VIC
@@ -809,7 +797,6 @@ config ARCH_S5PC100
 
 config ARCH_S5PV210
 	bool "Samsung S5PV210/S5PC110"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_SPARSEMEM_ENABLE
 	select ATAGS
@@ -845,7 +832,6 @@ config ARCH_DAVINCI
 config ARCH_OMAP1
 	bool "TI OMAP1"
 	depends on MMU
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
 	select ARCH_REQUIRE_GPIOLIB
@@ -1009,8 +995,6 @@ source "arch/arm/mach-rockchip/Kconfig"
 
 source "arch/arm/mach-sa1100/Kconfig"
 
-source "arch/arm/plat-samsung/Kconfig"
-
 source "arch/arm/mach-socfpga/Kconfig"
 
 source "arch/arm/mach-spear/Kconfig"
@@ -1028,6 +1012,7 @@ source "arch/arm/mach-s5pc100/Kconfig"
 source "arch/arm/mach-s5pv210/Kconfig"
 
 source "arch/arm/mach-exynos/Kconfig"
+source "arch/arm/plat-samsung/Kconfig"
 
 source "arch/arm/mach-shmobile/Kconfig"
 
@@ -2109,9 +2094,7 @@ endmenu
 
 menu "CPU Power Management"
 
-if ARCH_HAS_CPUFREQ
 source "drivers/cpufreq/Kconfig"
-endif
 
 source "drivers/cpuidle/Kconfig"
 
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index 5986ff63b90..adb5ed9e269 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -357,7 +357,7 @@ dtb-$(CONFIG_ARCH_STI)+= stih407-b2120.dtb \
 	stih415-b2020.dtb \
 	stih416-b2000.dtb \
 	stih416-b2020.dtb \
-	stih416-b2020-revE.dtb
+	stih416-b2020e.dtb
 dtb-$(CONFIG_MACH_SUN4I) += \
 	sun4i-a10-a1000.dtb \
 	sun4i-a10-cubieboard.dtb \
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index ecb267767cf..e2156a583de 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -529,8 +529,8 @@
 		serial-dir = <  /* 0: INACTIVE, 1: TX, 2: RX */
 			0 0 1 2
 		>;
-		tx-num-evt = <1>;
-		rx-num-evt = <1>;
+		tx-num-evt = <32>;
+		rx-num-evt = <32>;
 };
 
 &tps {
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index ab9a34ce524..80a3b215e7d 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -560,8 +560,8 @@
 		serial-dir = <  /* 0: INACTIVE, 1: TX, 2: RX */
 			0 0 1 2
 		>;
-		tx-num-evt = <1>;
-		rx-num-evt = <1>;
+		tx-num-evt = <32>;
+		rx-num-evt = <32>;
 };
 
 &tscadc {
diff --git a/arch/arm/boot/dts/am335x-igep0033.dtsi b/arch/arm/boot/dts/am335x-igep0033.dtsi
index 8a0a72dc7dd..a1a0cc5eb35 100644
--- a/arch/arm/boot/dts/am335x-igep0033.dtsi
+++ b/arch/arm/boot/dts/am335x-igep0033.dtsi
@@ -105,10 +105,16 @@
 
 &cpsw_emac0 {
 	phy_id = <&davinci_mdio>, <0>;
+	phy-mode = "rmii";
 };
 
 &cpsw_emac1 {
 	phy_id = <&davinci_mdio>, <1>;
+	phy-mode = "rmii";
+};
+
+&phy_sel {
+	rmii-clock-ext;
 };
 
 &elm {
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 9f53e824b03..4a4e02d0ce9 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -662,6 +662,8 @@
 		mac: ethernet@4a100000 {
 			compatible = "ti,cpsw";
 			ti,hwmods = "cpgmac0";
+			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>;
+			clock-names = "fck", "cpts";
 			cpdma_channels = <8>;
 			ale_entries = <1024>;
 			bd_ram_size = <0x2000>;
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index 794c73e5c4e..49fa5962225 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -490,6 +490,8 @@
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ti,hwmods = "cpgmac0";
+			clocks = <&cpsw_125mhz_gclk>, <&cpsw_cpts_rft_clk>;
+			clock-names = "fck", "cpts";
 			status = "disabled";
 			cpdma_channels = <8>;
 			ale_entries = <1024>;
@@ -857,6 +859,35 @@
 			ti,hwmods = "hdq1w";
 			status = "disabled";
 		};
+
+		dss: dss@4832a000 {
+			compatible = "ti,omap3-dss";
+			reg = <0x4832a000 0x200>;
+			status = "disabled";
+			ti,hwmods = "dss_core";
+			clocks = <&disp_clk>;
+			clock-names = "fck";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			dispc@4832a400 {
+				compatible = "ti,omap3-dispc";
+				reg = <0x4832a400 0x400>;
+				interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>;
+				ti,hwmods = "dss_dispc";
+				clocks = <&disp_clk>;
+				clock-names = "fck";
+			};
+
+			rfbi: rfbi@4832a800 {
+				compatible = "ti,omap3-rfbi";
+				reg = <0x4832a800 0x100>;
+				ti,hwmods = "dss_rfbi";
+				clocks = <&disp_clk>;
+				clock-names = "fck";
+			};
+		};
 	};
 };
 
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index c25d15837ce..003766c47bb 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -19,6 +19,10 @@
 	model = "TI AM437x GP EVM";
 	compatible = "ti,am437x-gp-evm","ti,am4372","ti,am43";
 
+	aliases {
+		display0 = &lcd0;
+	};
+
 	vmmcsd_fixed: fixedregulator-sd {
 		compatible = "regulator-fixed";
 		regulator-name = "vmmcsd_fixed";
@@ -64,6 +68,44 @@
 				0x02000069      /* LEFT */
 				0x0201006c>;      /* DOWN */
 		};
+
+	lcd0: display {
+		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
+		label = "lcd";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_pins>;
+
+		/*
+		 * SelLCDorHDMI, LOW to select HDMI. This is not really the
+		 * panel's enable GPIO, but we don't have HDMI driver support nor
+		 * support to switch between two displays, so using this gpio as
+		 * panel's enable should be safe.
+		 */
+		enable-gpios = <&gpio5 8 GPIO_ACTIVE_HIGH>;
+
+		panel-timing {
+			clock-frequency = <33000000>;
+			hactive = <800>;
+			vactive = <480>;
+			hfront-porch = <210>;
+			hback-porch = <16>;
+			hsync-len = <30>;
+			vback-porch = <10>;
+			vfront-porch = <22>;
+			vsync-len = <13>;
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <1>;
+			pixelclk-active = <1>;
+		};
+
+		port {
+			lcd_in: endpoint {
+				remote-endpoint = <&dpi_out>;
+			};
+		};
+	};
 };
 
 &am43xx_pinmux {
@@ -171,6 +213,47 @@
 			0x9c (PIN_OUTPUT | MUX_MODE0)		/* gpmc_be0n_cle.gpmc_be0n_cle */
 		>;
 	};
+
+	dss_pins: dss_pins {
+		pinctrl-single,pins = <
+			0x020 (PIN_OUTPUT_PULLUP | MUX_MODE1) /*gpmc ad 8 -> DSS DATA 23 */
+			0x024 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+			0x028 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+			0x02c (PIN_OUTPUT_PULLUP | MUX_MODE1)
+			0x030 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+			0x034 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+			0x038 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+			0x03c (PIN_OUTPUT_PULLUP | MUX_MODE1) /*gpmc ad 15 -> DSS DATA 16 */
+			0x0a0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS DATA 0 */
+			0x0a4 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0a8 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0ac (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0b0 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0b4 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0b8 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0bc (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0c0 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0c4 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0c8 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0cc (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0d0 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0d4 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0d8 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+			0x0dc (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS DATA 15 */
+			0x0e0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS VSYNC */
+			0x0e4 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS HSYNC */
+			0x0e8 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS PCLK */
+			0x0ec (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS AC BIAS EN */
+
+		>;
+	};
+
+	lcd_pins: lcd_pins {
+		pinctrl-single,pins = <
+			/* GPIO 5_8 to select LCD / HDMI */
+			0x238 (PIN_OUTPUT_PULLUP | MUX_MODE7)
+		>;
+	};
 };
 
 &i2c0 {
@@ -359,3 +442,17 @@
 		};
 	};
 };
+
+&dss {
+	status = "ok";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_pins>;
+
+	port {
+		dpi_out: endpoint@0 {
+			remote-endpoint = <&lcd_in>;
+			data-lines = <24>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index ad362c50e32..90098f98a5c 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -19,6 +19,10 @@
 	model = "TI AM43x EPOS EVM";
 	compatible = "ti,am43x-epos-evm","ti,am4372","ti,am43";
 
+	aliases {
+		display0 = &lcd0;
+	};
+
 	vmmcsd_fixed: fixedregulator-sd {
 		compatible = "regulator-fixed";
 		regulator-name = "vmmcsd_fixed";
@@ -27,6 +31,44 @@
 		enable-active-high;
 	};
 
+	lcd0: display {
+		compatible = "osddisplays,osd057T0559-34ts", "panel-dpi";
+		label = "lcd";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&lcd_pins>;
+
+		/*
+		 * SelLCDorHDMI, LOW to select HDMI. This is not really the
+		 * panel's enable GPIO, but we don't have HDMI driver support nor
+		 * support to switch between two displays, so using this gpio as
+		 * panel's enable should be safe.
+		 */
+		enable-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
+
+		panel-timing {
+			clock-frequency = <33000000>;
+			hactive = <800>;
+			vactive = <480>;
+			hfront-porch = <210>;
+			hback-porch = <16>;
+			hsync-len = <30>;
+			vback-porch = <10>;
+			vfront-porch = <22>;
+			vsync-len = <13>;
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <1>;
+			pixelclk-active = <1>;
+		};
+
+		port {
+			lcd_in: endpoint {
+				remote-endpoint = <&dpi_out>;
+			};
+		};
+	};
+
 	am43xx_pinmux: pinmux@44e10800 {
 		cpsw_default: cpsw_default {
 			pinctrl-single,pins = <
@@ -161,6 +203,46 @@
 				0x234 (PIN_INPUT_PULLUP | MUX_MODE1)    /* cam1_wen.hdq_gpio */
 			>;
 		};
+
+		dss_pins: dss_pins {
+			pinctrl-single,pins = <
+				0x020 (PIN_OUTPUT_PULLUP | MUX_MODE1) /*gpmc ad 8 -> DSS DATA 23 */
+				0x024 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+				0x028 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+				0x02C (PIN_OUTPUT_PULLUP | MUX_MODE1)
+				0x030 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+				0x034 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+				0x038 (PIN_OUTPUT_PULLUP | MUX_MODE1)
+				0x03C (PIN_OUTPUT_PULLUP | MUX_MODE1) /*gpmc ad 15 -> DSS DATA 16 */
+				0x0A0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS DATA 0 */
+				0x0A4 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0A8 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0AC (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0B0 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0B4 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0B8 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0BC (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0C0 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0C4 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0C8 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0CC (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0D0 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0D4 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0D8 (PIN_OUTPUT_PULLUP | MUX_MODE0)
+				0x0DC (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS DATA 15 */
+				0x0E0 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS VSYNC */
+				0x0E4 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS HSYNC */
+				0x0E8 (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS PCLK */
+				0x0EC (PIN_OUTPUT_PULLUP | MUX_MODE0) /* DSS AC BIAS EN */
+			>;
+		};
+
+		lcd_pins: lcd_pins {
+			pinctrl-single,pins = <
+				/* GPMC CLK -> GPIO 2_1 to select LCD / HDMI */
+				0x08C (PIN_OUTPUT_PULLUP | MUX_MODE7)
+			>;
+		};
 	};
 
 	matrix_keypad: matrix_keypad@0 {
@@ -237,6 +319,10 @@
 	phy-mode = "rmii";
 };
 
+&phy_sel {
+	rmii-clock-ext;
+};
+
 &i2c0 {
 	status = "okay";
 	pinctrl-names = "default";
@@ -468,3 +554,17 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&hdq_pins>;
 };
+
+&dss {
+	status = "ok";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_pins>;
+
+	port {
+		dpi_out: endpoint@0 {
+			remote-endpoint = <&lcd_in>;
+			data-lines = <24>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/armada-375-db.dts b/arch/arm/boot/dts/armada-375-db.dts
index 772fec2d26c..1e2919d43d7 100644
--- a/arch/arm/boot/dts/armada-375-db.dts
+++ b/arch/arm/boot/dts/armada-375-db.dts
@@ -91,6 +91,8 @@
 				marvell,nand-keep-config;
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
 
 				partition@0 {
 					label = "U-Boot";
diff --git a/arch/arm/boot/dts/armada-380.dtsi b/arch/arm/boot/dts/armada-380.dtsi
index e69bc6759c3..4173a8ab34e 100644
--- a/arch/arm/boot/dts/armada-380.dtsi
+++ b/arch/arm/boot/dts/armada-380.dtsi
@@ -16,7 +16,7 @@
 
 / {
 	model = "Marvell Armada 380 family SoC";
-	compatible = "marvell,armada380", "marvell,armada38x";
+	compatible = "marvell,armada380";
 
 	cpus {
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/armada-385-db.dts b/arch/arm/boot/dts/armada-385-db.dts
index ff9637dd8d0..1af886f1e48 100644
--- a/arch/arm/boot/dts/armada-385-db.dts
+++ b/arch/arm/boot/dts/armada-385-db.dts
@@ -16,7 +16,7 @@
 
 / {
 	model = "Marvell Armada 385 Development Board";
-	compatible = "marvell,a385-db", "marvell,armada385", "marvell,armada38x";
+	compatible = "marvell,a385-db", "marvell,armada385", "marvell,armada380";
 
 	chosen {
 		bootargs = "console=ttyS0,115200 earlyprintk";
@@ -98,6 +98,8 @@
 				marvell,nand-keep-config;
 				marvell,nand-enable-arbiter;
 				nand-on-flash-bbt;
+				nand-ecc-strength = <4>;
+				nand-ecc-step-size = <512>;
 
 				partition@0 {
 					label = "U-Boot";
diff --git a/arch/arm/boot/dts/armada-385-rd.dts b/arch/arm/boot/dts/armada-385-rd.dts
index 40893255a3f..aaca2861dc8 100644
--- a/arch/arm/boot/dts/armada-385-rd.dts
+++ b/arch/arm/boot/dts/armada-385-rd.dts
@@ -17,7 +17,7 @@
 
 / {
 	model = "Marvell Armada 385 Reference Design";
-	compatible = "marvell,a385-rd", "marvell,armada385", "marvell,armada38x";
+	compatible = "marvell,a385-rd", "marvell,armada385", "marvell,armada380";
 
 	chosen {
 		bootargs = "console=ttyS0,115200 earlyprintk";
diff --git a/arch/arm/boot/dts/armada-385.dtsi b/arch/arm/boot/dts/armada-385.dtsi
index f011009bf4c..6283d7912f7 100644
--- a/arch/arm/boot/dts/armada-385.dtsi
+++ b/arch/arm/boot/dts/armada-385.dtsi
@@ -16,7 +16,7 @@
 
 / {
 	model = "Marvell Armada 385 family SoC";
-	compatible = "marvell,armada385", "marvell,armada38x";
+	compatible = "marvell,armada385", "marvell,armada380";
 
 	cpus {
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 3de364e81b5..689fa1a4672 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -20,7 +20,7 @@
 
 / {
 	model = "Marvell Armada 38x family SoC";
-	compatible = "marvell,armada38x";
+	compatible = "marvell,armada380";
 
 	aliases {
 		gpio0 = &gpio0;
diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts
index 25674fe81f7..7e291e2ef4b 100644
--- a/arch/arm/boot/dts/armada-xp-matrix.dts
+++ b/arch/arm/boot/dts/armada-xp-matrix.dts
@@ -57,6 +57,10 @@
 			ethernet@30000 {
 				status = "okay";
 				phy-mode = "sgmii";
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+				};
 			};
 
 			pcie-controller {
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index e5c6a0492ca..4e5a59ee150 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -25,7 +25,7 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0 0x00000000 0 0xC0000000>; /* 3 GB */
+		reg = <0 0x00000000 0 0x40000000>; /* 1 GB soldered on */
 	};
 
 	soc {
diff --git a/arch/arm/boot/dts/at91sam9261.dtsi b/arch/arm/boot/dts/at91sam9261.dtsi
index b309c1c6e84..04927db1d6b 100644
--- a/arch/arm/boot/dts/at91sam9261.dtsi
+++ b/arch/arm/boot/dts/at91sam9261.dtsi
@@ -568,24 +568,17 @@
 				#size-cells = <0>;
 				#interrupt-cells = <1>;
 
-				slow_rc_osc: slow_rc_osc {
-					compatible = "fixed-clock";
+				main_osc: main_osc {
+					compatible = "atmel,at91rm9200-clk-main-osc";
 					#clock-cells = <0>;
-					clock-frequency = <32768>;
-					clock-accuracy = <50000000>;
-				};
-
-				clk32k: slck {
-					compatible = "atmel,at91sam9260-clk-slow";
-					#clock-cells = <0>;
-					clocks = <&slow_rc_osc &slow_xtal>;
+					interrupts-extended = <&pmc AT91_PMC_MOSCS>;
+					clocks = <&main_xtal>;
 				};
 
 				main: mainck {
 					compatible = "atmel,at91rm9200-clk-main";
 					#clock-cells = <0>;
-					interrupts-extended = <&pmc AT91_PMC_MOSCS>;
-					clocks = <&main_xtal>;
+					clocks = <&main_osc>;
 				};
 
 				plla: pllack {
@@ -615,7 +608,7 @@
 					compatible = "atmel,at91rm9200-clk-master";
 					#clock-cells = <0>;
 					interrupts-extended = <&pmc AT91_PMC_MCKRDY>;
-					clocks = <&clk32k>, <&main>, <&plla>, <&pllb>;
+					clocks = <&slow_xtal>, <&main>, <&plla>, <&pllb>;
 					atmel,clk-output-range = <0 94000000>;
 					atmel,clk-divisors = <1 2 4 0>;
 				};
@@ -632,7 +625,7 @@
 					#address-cells = <1>;
 					#size-cells = <0>;
 					interrupt-parent = <&pmc>;
-					clocks = <&clk32k>, <&main>, <&plla>, <&pllb>;
+					clocks = <&slow_xtal>, <&main>, <&plla>, <&pllb>;
 
 					prog0: prog0 {
 						#clock-cells = <0>;
diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts
index c6683ea8b74..aa35a7aec9a 100644
--- a/arch/arm/boot/dts/at91sam9261ek.dts
+++ b/arch/arm/boot/dts/at91sam9261ek.dts
@@ -20,6 +20,10 @@
 		reg = <0x20000000 0x4000000>;
 	};
 
+	slow_xtal {
+		clock-frequency = <32768>;
+	};
+
 	main_xtal {
 		clock-frequency = <18432000>;
 	};
diff --git a/arch/arm/boot/dts/at91sam9n12.dtsi b/arch/arm/boot/dts/at91sam9n12.dtsi
index d1b82e6635d..b84bac5bada 100644
--- a/arch/arm/boot/dts/at91sam9n12.dtsi
+++ b/arch/arm/boot/dts/at91sam9n12.dtsi
@@ -132,8 +132,8 @@
 								      <595000000 650000000 3 0>,
 								      <545000000 600000000 0 1>,
 								      <495000000 555000000 1 1>,
-								      <445000000 500000000 1 2>,
-								      <400000000 450000000 1 3>;
+								      <445000000 500000000 2 1>,
+								      <400000000 450000000 3 1>;
 				};
 
 				plladiv: plladivck {
@@ -925,7 +925,7 @@
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00500000 0x00100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>,
+			clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>,
 				 <&uhpck>;
 			clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck";
 			status = "disabled";
diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi
index 1a57298636a..2c0d6ea3ab4 100644
--- a/arch/arm/boot/dts/at91sam9x5.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5.dtsi
@@ -140,8 +140,8 @@
 								       595000000 650000000 3 0
 								       545000000 600000000 0 1
 								       495000000 555000000 1 1
-								       445000000 500000000 1 2
-								       400000000 450000000 1 3>;
+								       445000000 500000000 2 1
+								       400000000 450000000 3 1>;
 				};
 
 				plladiv: plladivck {
@@ -1045,6 +1045,8 @@
 				reg = <0x00500000 0x80000
 				       0xf803c000 0x400>;
 				interrupts = <23 IRQ_TYPE_LEVEL_HIGH 0>;
+				clocks = <&usb>, <&udphs_clk>;
+				clock-names = "hclk", "pclk";
 				status = "disabled";
 
 				ep0 {
@@ -1122,6 +1124,7 @@
 				compatible = "atmel,at91sam9rl-pwm";
 				reg = <0xf8034000 0x300>;
 				interrupts = <18 IRQ_TYPE_LEVEL_HIGH 4>;
+				clocks = <&pwm_clk>;
 				#pwm-cells = <3>;
 				status = "disabled";
 			};
@@ -1153,8 +1156,7 @@
 			compatible = "atmel,at91rm9200-ohci", "usb-ohci";
 			reg = <0x00600000 0x100000>;
 			interrupts = <22 IRQ_TYPE_LEVEL_HIGH 2>;
-			clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>,
-				 <&uhpck>;
+			clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>;
 			clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck";
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
index 4adc28039c3..83089540e32 100644
--- a/arch/arm/boot/dts/dra7-evm.dts
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -240,6 +240,7 @@
 					regulator-name = "ldo3";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
 					regulator-boot-on;
 				};
 
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index c29945e07c5..80127638b37 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -773,7 +773,6 @@
 			clocks = <&qspi_gfclk_div>;
 			clock-names = "fck";
 			num-cs = <4>;
-			interrupts = <0 343 0x4>;
 			status = "disabled";
 		};
 
@@ -984,6 +983,17 @@
 			#size-cells = <1>;
 			status = "disabled";
 		};
+
+		atl: atl@4843c000 {
+			compatible = "ti,dra7-atl";
+			reg = <0x4843c000 0x3ff>;
+			ti,hwmods = "atl";
+			ti,provided-clocks = <&atl_clkin0_ck>, <&atl_clkin1_ck>,
+					     <&atl_clkin2_ck>, <&atl_clkin3_ck>;
+			clocks = <&atl_gfclk_mux>;
+			clock-names = "fck";
+			status = "disabled";
+		};
 	};
 };
 
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index c7676871d9c..dc7a292fe93 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -10,26 +10,26 @@
 &cm_core_aon_clocks {
 	atl_clkin0_ck: atl_clkin0_ck {
 		#clock-cells = <0>;
-		compatible = "fixed-clock";
-		clock-frequency = <0>;
+		compatible = "ti,dra7-atl-clock";
+		clocks = <&atl_gfclk_mux>;
 	};
 
 	atl_clkin1_ck: atl_clkin1_ck {
 		#clock-cells = <0>;
-		compatible = "fixed-clock";
-		clock-frequency = <0>;
+		compatible = "ti,dra7-atl-clock";
+		clocks = <&atl_gfclk_mux>;
 	};
 
 	atl_clkin2_ck: atl_clkin2_ck {
 		#clock-cells = <0>;
-		compatible = "fixed-clock";
-		clock-frequency = <0>;
+		compatible = "ti,dra7-atl-clock";
+		clocks = <&atl_gfclk_mux>;
 	};
 
-	atlclkin3_ck: atlclkin3_ck {
+	atl_clkin3_ck: atl_clkin3_ck {
 		#clock-cells = <0>;
-		compatible = "fixed-clock";
-		clock-frequency = <0>;
+		compatible = "ti,dra7-atl-clock";
+		clocks = <&atl_gfclk_mux>;
 	};
 
 	hdmi_clkin_ck: hdmi_clkin_ck {
@@ -277,7 +277,7 @@
 
 	dpll_mpu_ck: dpll_mpu_ck {
 		#clock-cells = <0>;
-		compatible = "ti,omap4-dpll-clock";
+		compatible = "ti,omap5-mpu-dpll-clock";
 		clocks = <&sys_clkin1>, <&mpu_dpll_hs_clk_div>;
 		reg = <0x0160>, <0x0164>, <0x016c>, <0x0168>;
 	};
@@ -673,10 +673,12 @@
 
 	l3_iclk_div: l3_iclk_div {
 		#clock-cells = <0>;
-		compatible = "fixed-factor-clock";
+		compatible = "ti,divider-clock";
+		ti,max-div = <2>;
+		ti,bit-shift = <4>;
+		reg = <0x0100>;
 		clocks = <&dpll_core_h12x2_ck>;
-		clock-mult = <1>;
-		clock-div = <1>;
+		ti,index-power-of-two;
 	};
 
 	l4_root_clk_div: l4_root_clk_div {
@@ -684,7 +686,7 @@
 		compatible = "fixed-factor-clock";
 		clocks = <&l3_iclk_div>;
 		clock-mult = <1>;
-		clock-div = <1>;
+		clock-div = <2>;
 	};
 
 	video1_clk2_div: video1_clk2_div {
@@ -730,7 +732,7 @@
 	mcasp1_ahclkr_mux: mcasp1_ahclkr_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <28>;
 		reg = <0x0550>;
 	};
@@ -738,7 +740,7 @@
 	mcasp1_ahclkx_mux: mcasp1_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x0550>;
 	};
@@ -1639,7 +1641,7 @@
 	mcasp2_ahclkr_mux: mcasp2_ahclkr_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <28>;
 		reg = <0x1860>;
 	};
@@ -1647,7 +1649,7 @@
 	mcasp2_ahclkx_mux: mcasp2_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1860>;
 	};
@@ -1663,7 +1665,7 @@
 	mcasp3_ahclkx_mux: mcasp3_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1868>;
 	};
@@ -1679,7 +1681,7 @@
 	mcasp4_ahclkx_mux: mcasp4_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1898>;
 	};
@@ -1695,7 +1697,7 @@
 	mcasp5_ahclkx_mux: mcasp5_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1878>;
 	};
@@ -1711,7 +1713,7 @@
 	mcasp6_ahclkx_mux: mcasp6_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1904>;
 	};
@@ -1727,7 +1729,7 @@
 	mcasp7_ahclkx_mux: mcasp7_ahclkx_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <24>;
 		reg = <0x1908>;
 	};
@@ -1743,7 +1745,7 @@
 	mcasp8_ahclk_mux: mcasp8_ahclk_mux {
 		#clock-cells = <0>;
 		compatible = "ti,mux-clock";
-		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atlclkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
+		clocks = <&abe_24m_fclk>, <&abe_sys_clk_div>, <&func_24m_clk>, <&atl_clkin3_ck>, <&atl_clkin2_ck>, <&atl_clkin1_ck>, <&atl_clkin0_ck>, <&sys_clkin2>, <&ref_clkin0_ck>, <&ref_clkin1_ck>, <&ref_clkin2_ck>, <&ref_clkin3_ck>, <&mlb_clk>, <&mlbp_clk>;
 		ti,bit-shift = <22>;
 		reg = <0x1890>;
 	};
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index b8ece4be41c..17b22e9cc2a 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -113,7 +113,7 @@
 		compatible = "arm,cortex-a9-gic";
 		#interrupt-cells = <3>;
 		interrupt-controller;
-		reg = <0x10490000 0x1000>, <0x10480000 0x100>;
+		reg = <0x10490000 0x10000>, <0x10480000 0x10000>;
 	};
 
 	combiner: interrupt-controller@10440000 {
@@ -554,7 +554,7 @@
 		interrupts = <0 37 0>, <0 38 0>, <0 39 0>, <0 40 0>, <0 41 0>;
 		clocks = <&clock CLK_PWM>;
 		clock-names = "timers";
-		#pwm-cells = <2>;
+		#pwm-cells = <3>;
 		status = "disabled";
 	};
 
diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi
index ee3001f3882..97ea7a9b1f6 100644
--- a/arch/arm/boot/dts/exynos4210.dtsi
+++ b/arch/arm/boot/dts/exynos4210.dtsi
@@ -31,6 +31,16 @@
 		pinctrl2 = &pinctrl_2;
 	};
 
+	pmu_system_controller: system-controller@10020000 {
+		clock-names = "clkout0", "clkout1", "clkout2", "clkout3",
+				"clkout4", "clkout8", "clkout9";
+		clocks = <&clock CLK_OUT_DMC>, <&clock CLK_OUT_TOP>,
+			<&clock CLK_OUT_LEFTBUS>, <&clock CLK_OUT_RIGHTBUS>,
+			<&clock CLK_OUT_CPU>, <&clock CLK_XXTI>,
+			<&clock CLK_XUSBXTI>;
+		#clock-cells = <1>;
+	};
+
 	sysram@02020000 {
 		compatible = "mmio-sram";
 		reg = <0x02020000 0x20000>;
diff --git a/arch/arm/boot/dts/exynos4x12.dtsi b/arch/arm/boot/dts/exynos4x12.dtsi
index c5a943df1cd..de1f9c77b58 100644
--- a/arch/arm/boot/dts/exynos4x12.dtsi
+++ b/arch/arm/boot/dts/exynos4x12.dtsi
@@ -139,6 +139,13 @@
 
 	pmu_system_controller: system-controller@10020000 {
 		compatible = "samsung,exynos4212-pmu", "syscon";
+		clock-names = "clkout0", "clkout1", "clkout2", "clkout3",
+				"clkout4", "clkout8", "clkout9";
+		clocks = <&clock CLK_OUT_DMC>, <&clock CLK_OUT_TOP>,
+			<&clock CLK_OUT_LEFTBUS>, <&clock CLK_OUT_RIGHTBUS>,
+			<&clock CLK_OUT_CPU>, <&clock CLK_XXTI>,
+			<&clock CLK_XUSBXTI>;
+		#clock-cells = <1>;
 	};
 
 	g2d@10800000 {
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index 834fb5a5306..492e1eff37b 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -191,6 +191,9 @@
 	pmu_system_controller: system-controller@10040000 {
 		compatible = "samsung,exynos5250-pmu", "syscon";
 		reg = <0x10040000 0x5000>;
+		clock-names = "clkout16";
+		clocks = <&clock CLK_FIN_PLL>;
+		#clock-cells = <1>;
 	};
 
 	sysreg_system_controller: syscon@10050000 {
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index e38532271ef..a40a5c2b5a4 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -167,7 +167,7 @@
 		compatible = "samsung,exynos5420-audss-clock";
 		reg = <0x03810000 0x0C>;
 		#clock-cells = <1>;
-		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_FOUT_EPLL>,
+		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MAU_EPLL>,
 			 <&clock CLK_SCLK_MAUDIO0>, <&clock CLK_SCLK_MAUPCM0>;
 		clock-names = "pll_ref", "pll_in", "sclk_audio", "sclk_pcm_in";
 	};
@@ -260,6 +260,9 @@
 	mfc_pd: power-domain@10044060 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10044060 0x20>;
+		clocks = <&clock CLK_FIN_PLL>, <&clock CLK_MOUT_SW_ACLK333>,
+			<&clock CLK_MOUT_USER_ACLK333>;
+		clock-names = "oscclk", "pclk0", "clk0";
 	};
 
 	disp_pd: power-domain@100440C0 {
@@ -724,6 +727,9 @@
 	pmu_system_controller: system-controller@10040000 {
 		compatible = "samsung,exynos5420-pmu", "syscon";
 		reg = <0x10040000 0x5000>;
+		clock-names = "clkout16";
+		clocks = <&clock CLK_FIN_PLL>;
+		#clock-cells = <1>;
 	};
 
 	sysreg_system_controller: syscon@10050000 {
diff --git a/arch/arm/boot/dts/hi3620.dtsi b/arch/arm/boot/dts/hi3620.dtsi
index ab1116d086b..83a5b8685bd 100644
--- a/arch/arm/boot/dts/hi3620.dtsi
+++ b/arch/arm/boot/dts/hi3620.dtsi
@@ -73,7 +73,7 @@
 
 		L2: l2-cache {
 			compatible = "arm,pl310-cache";
-			reg = <0xfc10000 0x100000>;
+			reg = <0x100000 0x100000>;
 			interrupts = <0 15 4>;
 			cache-unified;
 			cache-level = <2>;
diff --git a/arch/arm/boot/dts/imx51-babbage.dts b/arch/arm/boot/dts/imx51-babbage.dts
index 6bc3243a80d..181d77fa2fa 100644
--- a/arch/arm/boot/dts/imx51-babbage.dts
+++ b/arch/arm/boot/dts/imx51-babbage.dts
@@ -315,15 +315,15 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	fsl,cd-controller;
-	fsl,wp-controller;
+	cd-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
 &esdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc2>;
-	cd-gpios = <&gpio1 6 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio1 6 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio1 5 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
@@ -468,8 +468,8 @@
 				MX51_PAD_SD1_DATA1__SD1_DATA1		0x20d5
 				MX51_PAD_SD1_DATA2__SD1_DATA2		0x20d5
 				MX51_PAD_SD1_DATA3__SD1_DATA3		0x20d5
-				MX51_PAD_GPIO1_0__SD1_CD		0x20d5
-				MX51_PAD_GPIO1_1__SD1_WP		0x20d5
+				MX51_PAD_GPIO1_0__GPIO1_0		0x100
+				MX51_PAD_GPIO1_1__GPIO1_1		0x100
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts b/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
index 75e66c9c614..31cfb7f2b02 100644
--- a/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
+++ b/arch/arm/boot/dts/imx51-eukrea-mbimxsd51-baseboard.dts
@@ -107,7 +107,7 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1 &pinctrl_esdhc1_cd>;
-	fsl,cd-controller;
+	cd-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
@@ -206,7 +206,7 @@
 
 		pinctrl_esdhc1_cd: esdhc1_cd {
 			fsl,pins = <
-				MX51_PAD_GPIO1_0__SD1_CD 0x20d5
+				MX51_PAD_GPIO1_0__GPIO1_0 0xd5
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/imx53-m53evk.dts b/arch/arm/boot/dts/imx53-m53evk.dts
index d5d146a8b14..c4956b0ffb3 100644
--- a/arch/arm/boot/dts/imx53-m53evk.dts
+++ b/arch/arm/boot/dts/imx53-m53evk.dts
@@ -21,27 +21,25 @@
 		      <0xb0000000 0x20000000>;
 	};
 
-	soc {
-		display1: display@di1 {
-			compatible = "fsl,imx-parallel-display";
-			interface-pix-fmt = "bgr666";
-			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_ipu_disp1>;
-
-			display-timings {
-				800x480p60 {
-					native-mode;
-					clock-frequency = <31500000>;
-					hactive = <800>;
-					vactive = <480>;
-					hfront-porch = <40>;
-					hback-porch = <88>;
-					hsync-len = <128>;
-					vback-porch = <33>;
-					vfront-porch = <9>;
-					vsync-len = <3>;
-					vsync-active = <1>;
-				};
+	display1: display@di1 {
+		compatible = "fsl,imx-parallel-display";
+		interface-pix-fmt = "bgr666";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_ipu_disp1>;
+
+		display-timings {
+			800x480p60 {
+				native-mode;
+				clock-frequency = <31500000>;
+				hactive = <800>;
+				vactive = <480>;
+				hfront-porch = <40>;
+				hback-porch = <88>;
+				hsync-len = <128>;
+				vback-porch = <33>;
+				vfront-porch = <9>;
+				vsync-len = <3>;
+				vsync-active = <1>;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/imx6dl-hummingboard.dts b/arch/arm/boot/dts/imx6dl-hummingboard.dts
index 5373a5f2782..c8e51dd41b8 100644
--- a/arch/arm/boot/dts/imx6dl-hummingboard.dts
+++ b/arch/arm/boot/dts/imx6dl-hummingboard.dts
@@ -143,6 +143,14 @@
 			fsl,pins = <MX6QDL_PAD_GPIO_0__GPIO1_IO00 0x1b0b0>;
 		};
 
+		pinctrl_hummingboard_usbotg_id: hummingboard-usbotg-id {
+			/*
+			 * Similar to pinctrl_usbotg_2, but we want it
+			 * pulled down for a fixed host connection.
+			 */
+			fsl,pins = <MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x13059>;
+		};
+
 		pinctrl_hummingboard_usbotg_vbus: hummingboard-usbotg-vbus {
 			fsl,pins = <MX6QDL_PAD_EIM_D22__GPIO3_IO22 0x1b0b0>;
 		};
@@ -178,6 +186,8 @@
 };
 
 &usbotg {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_hummingboard_usbotg_id>;
 	vbus-supply = <&reg_usbotg_vbus>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6q-gw51xx.dts b/arch/arm/boot/dts/imx6q-gw51xx.dts
index af4929aee07..0e1406e58ef 100644
--- a/arch/arm/boot/dts/imx6q-gw51xx.dts
+++ b/arch/arm/boot/dts/imx6q-gw51xx.dts
@@ -11,7 +11,7 @@
 
 /dts-v1/;
 #include "imx6q.dtsi"
-#include "imx6qdl-gw54xx.dtsi"
+#include "imx6qdl-gw51xx.dtsi"
 
 / {
 	model = "Gateworks Ventana i.MX6 Quad GW51XX";
diff --git a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
index 25da82a0311..e8e781656b3 100644
--- a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
@@ -12,6 +12,19 @@
 		pinctrl-0 = <&pinctrl_cubox_i_ir>;
 	};
 
+	pwmleds {
+		compatible = "pwm-leds";
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_cubox_i_pwm1>;
+
+		front {
+			active-low;
+			label = "imx6:red:front";
+			max-brightness = <248>;
+			pwms = <&pwm1 0 50000>;
+		};
+	};
+
 	regulators {
 		compatible = "simple-bus";
 
@@ -109,6 +122,10 @@
 			>;
 		};
 
+		pinctrl_cubox_i_pwm1: cubox-i-pwm1-front-led {
+			fsl,pins = <MX6QDL_PAD_DISP0_DAT8__PWM1_OUT 0x1b0b0>;
+		};
+
 		pinctrl_cubox_i_spdif: cubox-i-spdif {
 			fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x13091>;
 		};
@@ -117,6 +134,14 @@
 			fsl,pins = <MX6QDL_PAD_GPIO_0__GPIO1_IO00 0x4001b0b0>;
 		};
 
+		pinctrl_cubox_i_usbotg_id: cubox-i-usbotg-id {
+			/*
+			 * The Cubox-i pulls this low, but as it's pointless
+			 * leaving it as a pull-up, even if it is just 10uA.
+			 */
+			fsl,pins = <MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x13059>;
+		};
+
 		pinctrl_cubox_i_usbotg_vbus: cubox-i-usbotg-vbus {
 			fsl,pins = <MX6QDL_PAD_EIM_D22__GPIO3_IO22 0x4001b0b0>;
 		};
@@ -153,6 +178,8 @@
 };
 
 &usbotg {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_cubox_i_usbotg_id>;
 	vbus-supply = <&reg_usbotg_vbus>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
index 31665adcbf3..0db15af41cb 100644
--- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi
@@ -161,7 +161,7 @@
 	status = "okay";
 
 	pmic: ltc3676@3c {
-		compatible = "ltc,ltc3676";
+		compatible = "lltc,ltc3676";
 		reg = <0x3c>;
 
 		regulators {
diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
index 367af3ec943..744c8a2d81f 100644
--- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
@@ -220,7 +220,7 @@
 	};
 
 	pmic: ltc3676@3c {
-		compatible = "ltc,ltc3676";
+		compatible = "lltc,ltc3676";
 		reg = <0x3c>;
 
 		regulators {
@@ -288,7 +288,7 @@
 	codec: sgtl5000@0a {
 		compatible = "fsl,sgtl5000";
 		reg = <0x0a>;
-		clocks = <&clks 169>;
+		clocks = <&clks 201>;
 		VDDA-supply = <&reg_1p8v>;
 		VDDIO-supply = <&reg_3p3v>;
 	};
diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
index c91b5a6c769..adf150c1be9 100644
--- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
@@ -234,7 +234,7 @@
 	};
 
 	pmic: ltc3676@3c {
-		compatible = "ltc,ltc3676";
+		compatible = "lltc,ltc3676";
 		reg = <0x3c>;
 
 		regulators {
diff --git a/arch/arm/boot/dts/imx6qdl-microsom.dtsi b/arch/arm/boot/dts/imx6qdl-microsom.dtsi
index d729d0b15f2..79eac6849d4 100644
--- a/arch/arm/boot/dts/imx6qdl-microsom.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-microsom.dtsi
@@ -10,14 +10,6 @@
 				MX6QDL_PAD_CSI0_DAT11__UART1_RX_DATA	0x1b0b1
 			>;
 		};
-
-		pinctrl_microsom_usbotg: microsom-usbotg {
-			/*
-			 * Similar to pinctrl_usbotg_2, but we want it
-			 * pulled down for a fixed host connection.
-			 */
-			fsl,pins = <MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x13059>;
-		};
 	};
 };
 
@@ -26,8 +18,3 @@
 	pinctrl-0 = <&pinctrl_microsom_uart1>;
 	status = "okay";
 };
-
-&usbotg {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_microsom_usbotg>;
-};
diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi
index 2d4e5285f3f..57d4abe03a9 100644
--- a/arch/arm/boot/dts/imx6sl.dtsi
+++ b/arch/arm/boot/dts/imx6sl.dtsi
@@ -686,7 +686,7 @@
 				compatible = "fsl,imx6sl-fec", "fsl,imx25-fec";
 				reg = <0x02188000 0x4000>;
 				interrupts = <0 114 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX6SL_CLK_ENET_REF>,
+				clocks = <&clks IMX6SL_CLK_ENET>,
 					 <&clks IMX6SL_CLK_ENET_REF>;
 				clock-names = "ipg", "ahb";
 				status = "disabled";
diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi
index d9f99e7deb8..c1414cb81fd 100644
--- a/arch/arm/boot/dts/keystone.dtsi
+++ b/arch/arm/boot/dts/keystone.dtsi
@@ -66,9 +66,21 @@
 		ranges = <0x0 0x0 0x0 0xc0000000>;
 		dma-ranges = <0x80000000 0x8 0x00000000 0x80000000>;
 
+		pllctrl: pll-controller@02310000 {
+			compatible = "ti,keystone-pllctrl", "syscon";
+			reg = <0x02310000 0x200>;
+		};
+
+		devctrl: device-state-control@02620000 {
+			compatible = "ti,keystone-devctrl", "syscon";
+			reg = <0x02620000 0x1000>;
+		};
+
 		rstctrl: reset-controller {
 			compatible = "ti,keystone-reset";
-			reg = <0x023100e8 4>;	/* pll reset control reg */
+			ti,syscon-pll = <&pllctrl 0xe4>;
+			ti,syscon-dev = <&devctrl 0x328>;
+			ti,wdt-list = <0>;
 		};
 
 		/include/ "keystone-clocks.dtsi"
diff --git a/arch/arm/boot/dts/kirkwood-guruplug-server-plus.dts b/arch/arm/boot/dts/kirkwood-guruplug-server-plus.dts
index c5a1fc75c7a..b2d9834bf45 100644
--- a/arch/arm/boot/dts/kirkwood-guruplug-server-plus.dts
+++ b/arch/arm/boot/dts/kirkwood-guruplug-server-plus.dts
@@ -105,7 +105,6 @@
 		compatible = "ethernet-phy-id0141.0cb0",
 		             "ethernet-phy-ieee802.3-c22";
 		reg = <0>;
-		phy-connection-type = "rgmii-id";
 	};
 
 	ethphy1: ethernet-phy@1 {
@@ -113,7 +112,6 @@
 		compatible = "ethernet-phy-id0141.0cb0",
 		             "ethernet-phy-ieee802.3-c22";
 		reg = <1>;
-		phy-connection-type = "rgmii-id";
 	};
 };
 
@@ -121,6 +119,7 @@
 	status = "okay";
 	ethernet0-port@0 {
 		phy-handle = <&ethphy0>;
+		phy-connection-type = "rgmii-id";
 	};
 };
 
@@ -128,5 +127,6 @@
 	status = "okay";
 	ethernet1-port@0 {
 		phy-handle = <&ethphy1>;
+		phy-connection-type = "rgmii-id";
 	};
 };
diff --git a/arch/arm/boot/dts/omap3-beagle-xm.dts b/arch/arm/boot/dts/omap3-beagle-xm.dts
index cf0be662297..1becefce821 100644
--- a/arch/arm/boot/dts/omap3-beagle-xm.dts
+++ b/arch/arm/boot/dts/omap3-beagle-xm.dts
@@ -251,6 +251,11 @@
 			codec {
 			};
 		};
+
+		twl_power: power {
+			compatible = "ti,twl4030-power-beagleboard-xm", "ti,twl4030-power-idle-osc-off";
+			ti,use_poweroff;
+		};
 	};
 };
 
@@ -301,6 +306,7 @@
 };
 
 &uart3 {
+	interrupts-extended = <&intc 74 &omap3_pmx_core OMAP3_UART3_RX>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&uart3_pins>;
 };
diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts
index 9cba94bed7a..a8bd4349c7d 100644
--- a/arch/arm/boot/dts/omap3-evm-37xx.dts
+++ b/arch/arm/boot/dts/omap3-evm-37xx.dts
@@ -26,7 +26,44 @@
 	};
 };
 
+&dss {
+	pinctrl-names = "default";
+	pinctrl-0 = <
+		&dss_dpi_pins1
+		&dss_dpi_pins2
+	>;
+};
+
 &omap3_pmx_core {
+	dss_dpi_pins1: pinmux_dss_dpi_pins2 {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0)   /* dss_pclk.dss_pclk */
+			OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT | MUX_MODE0)   /* dss_hsync.dss_hsync */
+			OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT | MUX_MODE0)   /* dss_vsync.dss_vsync */
+			OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT | MUX_MODE0)   /* dss_acbias.dss_acbias */
+
+			OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT | MUX_MODE0)   /* dss_data6.dss_data6 */
+			OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT | MUX_MODE0)   /* dss_data7.dss_data7 */
+			OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT | MUX_MODE0)   /* dss_data8.dss_data8 */
+			OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT | MUX_MODE0)   /* dss_data9.dss_data9 */
+			OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT | MUX_MODE0)   /* dss_data10.dss_data10 */
+			OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT | MUX_MODE0)   /* dss_data11.dss_data11 */
+			OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT | MUX_MODE0)   /* dss_data12.dss_data12 */
+			OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT | MUX_MODE0)   /* dss_data13.dss_data13 */
+			OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT | MUX_MODE0)   /* dss_data14.dss_data14 */
+			OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT | MUX_MODE0)   /* dss_data15.dss_data15 */
+			OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT | MUX_MODE0)   /* dss_data16.dss_data16 */
+			OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE0)   /* dss_data17.dss_data17 */
+
+			OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE3)   /* dss_data18.dss_data0 */
+			OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT | MUX_MODE3)   /* dss_data19.dss_data1 */
+			OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT | MUX_MODE3)   /* dss_data20.dss_data2 */
+			OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE3)   /* dss_data21.dss_data3 */
+			OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE3)   /* dss_data22.dss_data4 */
+			OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE3)   /* dss_data23.dss_data5 */
+		>;
+	};
+
 	mmc1_pins: pinmux_mmc1_pins {
 		pinctrl-single,pins = <
 			0x114 (PIN_OUTPUT_PULLUP | MUX_MODE0)	/* sdmmc1_clk.sdmmc1_clk */
@@ -75,6 +112,19 @@
 	};
 };
 
+&omap3_pmx_wkup {
+	dss_dpi_pins2: pinmux_dss_dpi_pins1 {
+		pinctrl-single,pins = <
+			0x0a (PIN_OUTPUT | MUX_MODE3)   /* sys_boot0.dss_data18 */
+			0x0c (PIN_OUTPUT | MUX_MODE3)   /* sys_boot1.dss_data19 */
+			0x10 (PIN_OUTPUT | MUX_MODE3)   /* sys_boot3.dss_data20 */
+			0x12 (PIN_OUTPUT | MUX_MODE3)   /* sys_boot4.dss_data21 */
+			0x14 (PIN_OUTPUT | MUX_MODE3)   /* sys_boot5.dss_data22 */
+			0x16 (PIN_OUTPUT | MUX_MODE3)   /* sys_boot6.dss_data23 */
+		>;
+	};
+};
+
 &mmc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc1_pins>;
diff --git a/arch/arm/boot/dts/omap3-evm-common.dtsi b/arch/arm/boot/dts/omap3-evm-common.dtsi
index 3007e79c9cd..c8747c7f1cc 100644
--- a/arch/arm/boot/dts/omap3-evm-common.dtsi
+++ b/arch/arm/boot/dts/omap3-evm-common.dtsi
@@ -44,6 +44,18 @@
 
 #include "twl4030.dtsi"
 #include "twl4030_omap3.dtsi"
+#include "omap3-panel-sharp-ls037v7dw01.dtsi"
+
+&backlight0 {
+	gpios = <&twl_gpio 18 GPIO_ACTIVE_LOW>;
+};
+
+&twl {
+	twl_power: power {
+		compatible = "ti,twl4030-power-omap3-evm", "ti,twl4030-power-idle";
+		ti,use_poweroff;
+	};
+};
 
 &i2c2 {
 	clock-frequency = <400000>;
@@ -61,6 +73,27 @@
 	};
 };
 
+&lcd_3v3 {
+	gpio = <&gpio5 25 GPIO_ACTIVE_LOW>;	/* gpio153 */
+	enable-active-low;
+};
+
+&lcd0 {
+	enable-gpios = <&gpio5 24 GPIO_ACTIVE_HIGH>;	/* gpio152, lcd INI */
+	reset-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd RESB */
+	mode-gpios = <&gpio5 26 GPIO_ACTIVE_HIGH	/* gpio154, lcd MO */
+		      &gpio1 2 GPIO_ACTIVE_HIGH		/* gpio2, lcd LR */
+		      &gpio1 3 GPIO_ACTIVE_HIGH>;	/* gpio3, lcd UD */
+};
+
+&mcspi1 {
+	tsc2046@0 {
+		interrupt-parent = <&gpio6>;
+		interrupts = <15 0>;		/* gpio175 */
+		pendown-gpio = <&gpio6 15 0>;
+	};
+};
+
 &mmc1 {
 	vmmc-supply = <&vmmc1>;
 	vmmc_aux-supply = <&vsim>;
diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts
index f8ad125fa46..021311f7964 100644
--- a/arch/arm/boot/dts/omap3-gta04.dts
+++ b/arch/arm/boot/dts/omap3-gta04.dts
@@ -44,6 +44,36 @@
 		ti,mcbsp = <&mcbsp2>;
 		ti,codec = <&twl_audio>;
 	};
+
+	spi_lcd {
+		compatible = "spi-gpio";
+		#address-cells = <0x1>;
+		#size-cells = <0x0>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&spi_gpio_pins>;
+
+		gpio-sck = <&gpio1 12 0>;
+		gpio-miso = <&gpio1 18 0>;
+		gpio-mosi = <&gpio1 20 0>;
+		cs-gpios = <&gpio1 19 0>;
+		num-chipselects = <1>;
+
+		/* lcd panel */
+		lcd: td028ttec1@0 {
+			compatible = "toppoly,td028ttec1";
+			reg = <0>;
+			spi-max-frequency = <100000>;
+			spi-cpol;
+			spi-cpha;
+
+			label = "lcd";
+			port {
+				lcd_in: endpoint {
+					remote-endpoint = <&dpi_out>;
+				};
+			};
+		};
+	};
 };
 
 &omap3_pmx_core {
@@ -78,6 +108,47 @@
 			0x11e (PIN_INPUT_PULLUP | MUX_MODE0)	/* sdmmc1_dat3.sdmmc1_dat3 */
 		>;
 	};
+
+	dss_dpi_pins: pinmux_dss_dpi_pins {
+               pinctrl-single,pins = <
+                       0x0a4 (PIN_OUTPUT | MUX_MODE0)   /* dss_pclk.dss_pclk */
+                       0x0a6 (PIN_OUTPUT | MUX_MODE0)   /* dss_hsync.dss_hsync */
+                       0x0a8 (PIN_OUTPUT | MUX_MODE0)   /* dss_vsync.dss_vsync */
+                       0x0aa (PIN_OUTPUT | MUX_MODE0)   /* dss_acbias.dss_acbias */
+                       0x0ac (PIN_OUTPUT | MUX_MODE0)   /* dss_data0.dss_data0 */
+                       0x0ae (PIN_OUTPUT | MUX_MODE0)   /* dss_data1.dss_data1 */
+                       0x0b0 (PIN_OUTPUT | MUX_MODE0)   /* dss_data2.dss_data2 */
+                       0x0b2 (PIN_OUTPUT | MUX_MODE0)   /* dss_data3.dss_data3 */
+                       0x0b4 (PIN_OUTPUT | MUX_MODE0)   /* dss_data4.dss_data4 */
+                       0x0b6 (PIN_OUTPUT | MUX_MODE0)   /* dss_data5.dss_data5 */
+                       0x0b8 (PIN_OUTPUT | MUX_MODE0)   /* dss_data6.dss_data6 */
+                       0x0ba (PIN_OUTPUT | MUX_MODE0)   /* dss_data7.dss_data7 */
+                       0x0bc (PIN_OUTPUT | MUX_MODE0)   /* dss_data8.dss_data8 */
+                       0x0be (PIN_OUTPUT | MUX_MODE0)   /* dss_data9.dss_data9 */
+                       0x0c0 (PIN_OUTPUT | MUX_MODE0)   /* dss_data10.dss_data10 */
+                       0x0c2 (PIN_OUTPUT | MUX_MODE0)   /* dss_data11.dss_data11 */
+                       0x0c4 (PIN_OUTPUT | MUX_MODE0)   /* dss_data12.dss_data12 */
+                       0x0c6 (PIN_OUTPUT | MUX_MODE0)   /* dss_data13.dss_data13 */
+                       0x0c8 (PIN_OUTPUT | MUX_MODE0)   /* dss_data14.dss_data14 */
+                       0x0ca (PIN_OUTPUT | MUX_MODE0)   /* dss_data15.dss_data15 */
+                       0x0cc (PIN_OUTPUT | MUX_MODE0)   /* dss_data16.dss_data16 */
+                       0x0ce (PIN_OUTPUT | MUX_MODE0)   /* dss_data17.dss_data17 */
+                       0x0d0 (PIN_OUTPUT | MUX_MODE0)   /* dss_data18.dss_data18 */
+                       0x0d2 (PIN_OUTPUT | MUX_MODE0)   /* dss_data19.dss_data19 */
+                       0x0d4 (PIN_OUTPUT | MUX_MODE0)   /* dss_data20.dss_data20 */
+                       0x0d6 (PIN_OUTPUT | MUX_MODE0)   /* dss_data21.dss_data21 */
+                       0x0d8 (PIN_OUTPUT | MUX_MODE0)   /* dss_data22.dss_data22 */
+                       0x0da (PIN_OUTPUT | MUX_MODE0)   /* dss_data23.dss_data23 */
+               >;
+       };
+
+	spi_gpio_pins: spi_gpio_pinmux {
+		pinctrl-single,pins = <0x5a8 (PIN_OUTPUT | MUX_MODE4) /* clk */
+			0x5b6 (PIN_OUTPUT | MUX_MODE4) /* cs */
+			0x5b8 (PIN_OUTPUT | MUX_MODE4) /* tx */
+			0x5b4 (PIN_INPUT | MUX_MODE4) /* rx */
+		>;
+	};
 };
 
 &i2c1 {
@@ -219,3 +290,22 @@
 	regulator-min-microvolt = <2800000>;
 	regulator-max-microvolt = <3150000>;
 };
+
+/* Needed to power the DPI pins */
+&vpll2 {
+	regulator-always-on;
+};
+
+&dss {
+	pinctrl-names = "default";
+	pinctrl-0 = < &dss_dpi_pins >;
+
+	status = "okay";
+
+	port {
+		dpi_out: endpoint {
+			remote-endpoint = <&lcd_in>;
+			data-lines = <24>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-ldp.dts b/arch/arm/boot/dts/omap3-ldp.dts
index 476ff158ddb..af272c156e2 100644
--- a/arch/arm/boot/dts/omap3-ldp.dts
+++ b/arch/arm/boot/dts/omap3-ldp.dts
@@ -164,6 +164,11 @@
 
 #include "twl4030.dtsi"
 #include "twl4030_omap3.dtsi"
+#include "omap3-panel-sharp-ls037v7dw01.dtsi"
+
+&backlight0 {
+	gpios = <&twl_gpio 7 GPIO_ACTIVE_HIGH>;
+};
 
 &i2c2 {
 	clock-frequency = <400000>;
@@ -173,6 +178,25 @@
 	clock-frequency = <400000>;
 };
 
+/* tps61130rsa enabled by twl4030 regen */
+&lcd_3v3 {
+	regulator-always-on;
+};
+
+&lcd0 {
+	enable-gpios = <&twl_gpio 15 GPIO_ACTIVE_HIGH>;	/* lcd INI */
+	reset-gpios = <&gpio2 23 GPIO_ACTIVE_HIGH>;	/* gpio55, lcd RESB */
+	mode-gpios = <&gpio2 24 GPIO_ACTIVE_HIGH>;	/* gpio56, lcd MO */
+};
+
+&mcspi1 {
+	tsc2046@0 {
+		interrupt-parent = <&gpio2>;
+		interrupts = <22 0>;		/* gpio54 */
+		pendown-gpio = <&gpio2 22 0>;
+	};
+};
+
 &mmc1 {
 	/* See 35xx errata 2.1.1.128 in SPRZ278F */
 	compatible = "ti,omap3-pre-es3-hsmmc";
@@ -251,8 +275,3 @@
 	/* Needed for ads7846 */
         regulator-name = "vcc";
 };
-
-&vpll2 {
-       /* Needed for DSS */
-       regulator-name = "vdds_dsi";
-};
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 059a8ff1e6a..b15f1a77d68 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -351,6 +351,11 @@
 		compatible = "ti,twl4030-audio";
 		ti,enable-vibra = <1>;
 	};
+
+	twl_power: power {
+		compatible = "ti,twl4030-power-n900";
+		ti,use_poweroff;
+	};
 };
 
 &twl_keypad {
@@ -651,9 +656,24 @@
 	 * Also... order in the device tree actually matters here.
 	 */
 	tsc2005@0 {
-		compatible = "tsc2005";
+		compatible = "ti,tsc2005";
 		spi-max-frequency = <6000000>;
 		reg = <0>;
+
+		vio-supply = <&vio>;
+
+		reset-gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>; /* 104 */
+		interrupts-extended = <&gpio4 4 IRQ_TYPE_EDGE_RISING>; /* 100 */
+
+		touchscreen-fuzz-x = <4>;
+		touchscreen-fuzz-y = <7>;
+		touchscreen-fuzz-pressure = <2>;
+		touchscreen-max-x = <4096>;
+		touchscreen-max-y = <4096>;
+		touchscreen-max-pressure = <2048>;
+
+		ti,x-plate-ohms = <280>;
+		ti,esd-recovery-timeout-ms = <8000>;
 	};
 
 	acx565akm@2 {
diff --git a/arch/arm/boot/dts/omap3-overo-alto35-common.dtsi b/arch/arm/boot/dts/omap3-overo-alto35-common.dtsi
index 19d64864a10..7aae8fb82c1 100644
--- a/arch/arm/boot/dts/omap3-overo-alto35-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-alto35-common.dtsi
@@ -11,6 +11,7 @@
  */
 
 #include "omap3-overo-common-peripherals.dtsi"
+#include "omap3-overo-common-lcd35.dtsi"
 
 #include <dt-bindings/input/input.h>
 
diff --git a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
index 19de6ff7968..17b82f82638 100644
--- a/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-chestnut43-common.dtsi
@@ -11,6 +11,7 @@
  */
 
 #include "omap3-overo-common-peripherals.dtsi"
+#include "omap3-overo-common-lcd43.dtsi"
 
 #include <dt-bindings/input/input.h>
 
diff --git a/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi b/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi
new file mode 100644
index 00000000000..802f704f67e
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-common-dvi.dtsi
@@ -0,0 +1,111 @@
+/*
+ * Copyright (C) 2014 Florian Vaussard, EPFL Mobots group
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * DVI output for some Gumstix Overo boards (Tobi and Summit)
+ */
+
+&omap3_pmx_core {
+	dss_dpi_pins: pinmux_dss_dpi_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0)	/* dss_pclk.dss_pclk */
+			OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT | MUX_MODE0)	/* dss_hsync.dss_hsync */
+			OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT | MUX_MODE0)	/* dss_vsync.dss_vsync */
+			OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT | MUX_MODE0)	/* dss_acbias.dss_acbias */
+			OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE0)	/* dss_data0.dss_data0 */
+			OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT | MUX_MODE0)	/* dss_data1.dss_data1 */
+			OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT | MUX_MODE0)	/* dss_data2.dss_data2 */
+			OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE0)	/* dss_data3.dss_data3 */
+			OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE0)	/* dss_data4.dss_data4 */
+			OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE0)	/* dss_data5.dss_data5 */
+			OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT | MUX_MODE0)	/* dss_data6.dss_data6 */
+			OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT | MUX_MODE0)	/* dss_data7.dss_data7 */
+			OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT | MUX_MODE0)	/* dss_data8.dss_data8 */
+			OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT | MUX_MODE0)	/* dss_data9.dss_data9 */
+			OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT | MUX_MODE0)	/* dss_data10.dss_data10 */
+			OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT | MUX_MODE0)	/* dss_data11.dss_data11 */
+			OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT | MUX_MODE0)	/* dss_data12.dss_data12 */
+			OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT | MUX_MODE0)	/* dss_data13.dss_data13 */
+			OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT | MUX_MODE0)	/* dss_data14.dss_data14 */
+			OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT | MUX_MODE0)	/* dss_data15.dss_data15 */
+			OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT | MUX_MODE0)	/* dss_data16.dss_data16 */
+			OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE0)	/* dss_data17.dss_data17 */
+			OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE0)	/* dss_data18.dss_data18 */
+			OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT | MUX_MODE0)	/* dss_data19.dss_data19 */
+			OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT | MUX_MODE0)	/* dss_data20.dss_data20 */
+			OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE0)	/* dss_data21.dss_data21 */
+			OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE0)	/* dss_data22.dss_data22 */
+			OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE0)	/* dss_data23.dss_data23 */
+		>;
+	};
+};
+
+/* Needed to power the DPI pins */
+&vpll2 {
+	regulator-always-on;
+};
+
+&dss {
+	status = "ok";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_dpi_pins>;
+
+	port {
+		dpi_out: endpoint {
+			remote-endpoint = <&tfp410_in>;
+			data-lines = <24>;
+		};
+	};
+};
+
+/ {
+	aliases {
+		display0 = &dvi0;
+	};
+
+	tfp410: encoder@0 {
+		compatible = "ti,tfp410";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				tfp410_in: endpoint@0 {
+					remote-endpoint = <&dpi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				tfp410_out: endpoint@0 {
+					remote-endpoint = <&dvi_connector_in>;
+				};
+			};
+		};
+	};
+
+	dvi0: connector@0 {
+		compatible = "dvi-connector";
+		label = "dvi";
+
+		digital;
+		ddc-i2c-bus = <&i2c3>;
+
+		port {
+			dvi_connector_in: endpoint {
+				remote-endpoint = <&tfp410_out>;
+			};
+		};
+	};
+};
+
diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
new file mode 100644
index 00000000000..233c69e50ae
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
@@ -0,0 +1,165 @@
+/*
+ * Copyright (C) 2014 Florian Vaussard, EPFL Mobots group
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * 4.3'' LCD panel output for some Gumstix Overo boards (Gallop43, Chestnut43)
+ */
+
+&omap3_pmx_core {
+	dss_dpi_pins: pinmux_dss_dpi_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0)	/* dss_pclk.dss_pclk */
+			OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT | MUX_MODE0)	/* dss_hsync.dss_hsync */
+			OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT | MUX_MODE0)	/* dss_vsync.dss_vsync */
+			OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT | MUX_MODE0)	/* dss_acbias.dss_acbias */
+			OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE0)	/* dss_data0.dss_data0 */
+			OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT | MUX_MODE0)	/* dss_data1.dss_data1 */
+			OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT | MUX_MODE0)	/* dss_data2.dss_data2 */
+			OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE0)	/* dss_data3.dss_data3 */
+			OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE0)	/* dss_data4.dss_data4 */
+			OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE0)	/* dss_data5.dss_data5 */
+			OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT | MUX_MODE0)	/* dss_data6.dss_data6 */
+			OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT | MUX_MODE0)	/* dss_data7.dss_data7 */
+			OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT | MUX_MODE0)	/* dss_data8.dss_data8 */
+			OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT | MUX_MODE0)	/* dss_data9.dss_data9 */
+			OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT | MUX_MODE0)	/* dss_data10.dss_data10 */
+			OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT | MUX_MODE0)	/* dss_data11.dss_data11 */
+			OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT | MUX_MODE0)	/* dss_data12.dss_data12 */
+			OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT | MUX_MODE0)	/* dss_data13.dss_data13 */
+			OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT | MUX_MODE0)	/* dss_data14.dss_data14 */
+			OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT | MUX_MODE0)	/* dss_data15.dss_data15 */
+			OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT | MUX_MODE0)	/* dss_data16.dss_data16 */
+			OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE0)	/* dss_data17.dss_data17 */
+			OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE0)	/* dss_data18.dss_data18 */
+			OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT | MUX_MODE0)	/* dss_data19.dss_data19 */
+			OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT | MUX_MODE0)	/* dss_data20.dss_data20 */
+			OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE0)	/* dss_data21.dss_data21 */
+			OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE0)	/* dss_data22.dss_data22 */
+			OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE0)	/* dss_data23.dss_data23 */
+		>;
+	};
+
+	lb035_pins: pinmux_lb035_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2174, PIN_OUTPUT | MUX_MODE4)	/* uart2_cts.gpio_144 */
+		>;
+	};
+
+	backlight_pins: pinmux_backlight_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE4)	/* uart2_rts.gpio_145 */
+		>;
+	};
+
+	mcspi1_pins: pinmux_mcspi1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21c8, PIN_INPUT | MUX_MODE0)	/* mcspi1_clk.mcspi1_clk */
+			OMAP3_CORE1_IOPAD(0x21ca, PIN_INPUT | MUX_MODE0)	/* mcspi1_simo.mcspi1_simo */
+			OMAP3_CORE1_IOPAD(0x21cc, PIN_INPUT | MUX_MODE0)	/* mcspi1_somi.mcspi1_somi */
+			OMAP3_CORE1_IOPAD(0x21ce, PIN_INPUT | MUX_MODE0)	/* mcspi1_cs0.mcspi1_cs0 */
+		>;
+	};
+
+	ads7846_pins: pinmux_ads7846_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2138, PIN_INPUT_PULLDOWN | MUX_MODE4)	/* csi2_dx1.gpio_114 */
+		>;
+	};
+};
+
+/* Needed to power the DPI pins */
+&vpll2 {
+	regulator-always-on;
+};
+
+&dss {
+	status = "ok";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_dpi_pins>;
+
+	port {
+		dpi_out: endpoint {
+			remote-endpoint = <&lcd_in>;
+			data-lines = <24>;
+		};
+	};
+};
+
+/ {
+	aliases {
+		display0 = &lcd0;
+	};
+
+	ads7846reg: ads7846-reg {
+		compatible = "regulator-fixed";
+		regulator-name = "ads7846-reg";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	backlight {
+		compatible = "gpio-backlight";
+		
+		pinctrl-names = "default";
+		pinctrl-0 = <&backlight_pins>;
+		gpios = <&gpio5 17 GPIO_ACTIVE_HIGH>;		/* gpio_145 */
+
+		default-on;
+	};
+};
+
+&mcspi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcspi1_pins>;
+
+	lcd0: display@0 {
+		compatible = "lgphilips,lb035q02";
+		label = "lcd";
+
+		reg = <1>;					/* CS1 */
+		spi-max-frequency = <10000000>;
+		spi-cpol;
+		spi-cpha;
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&lb035_pins>;
+		enable-gpios = <&gpio5 16 GPIO_ACTIVE_HIGH>;	/* gpio_144 */
+
+		port {
+			lcd_in: endpoint {
+				remote-endpoint = <&dpi_out>;
+			};
+		};
+	};
+
+	/* touch controller */
+	ads7846@0 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&ads7846_pins>;
+
+		compatible = "ti,ads7846";
+		vcc-supply = <&ads7846reg>;
+
+		reg = <0>;				/* CS0 */
+		spi-max-frequency = <1500000>;
+
+		interrupt-parent = <&gpio4>;
+		interrupts = <18 0>;			/* gpio_114 */
+		pendown-gpio = <&gpio4 18 0>;
+
+		ti,x-min = /bits/ 16 <0x0>;
+		ti,x-max = /bits/ 16 <0x0fff>;
+		ti,y-min = /bits/ 16 <0x0>;
+		ti,y-max = /bits/ 16 <0x0fff>;
+		ti,x-plate-ohms = /bits/ 16 <180>;
+		ti,pressure-max = /bits/ 16 <255>;
+
+		linux,wakeup;
+	};
+};
diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
new file mode 100644
index 00000000000..f5395b7da91
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
@@ -0,0 +1,178 @@
+/*
+ * Copyright (C) 2014 Florian Vaussard, EPFL Mobots group
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * 4.3'' LCD panel output for some Gumstix Overo boards (Gallop43, Chestnut43)
+ */
+
+&omap3_pmx_core {
+	dss_dpi_pins: pinmux_dss_dpi_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x20d4, PIN_OUTPUT | MUX_MODE0)	/* dss_pclk.dss_pclk */
+			OMAP3_CORE1_IOPAD(0x20d6, PIN_OUTPUT | MUX_MODE0)	/* dss_hsync.dss_hsync */
+			OMAP3_CORE1_IOPAD(0x20d8, PIN_OUTPUT | MUX_MODE0)	/* dss_vsync.dss_vsync */
+			OMAP3_CORE1_IOPAD(0x20da, PIN_OUTPUT | MUX_MODE0)	/* dss_acbias.dss_acbias */
+			OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE0)	/* dss_data0.dss_data0 */
+			OMAP3_CORE1_IOPAD(0x20de, PIN_OUTPUT | MUX_MODE0)	/* dss_data1.dss_data1 */
+			OMAP3_CORE1_IOPAD(0x20e0, PIN_OUTPUT | MUX_MODE0)	/* dss_data2.dss_data2 */
+			OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE0)	/* dss_data3.dss_data3 */
+			OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE0)	/* dss_data4.dss_data4 */
+			OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE0)	/* dss_data5.dss_data5 */
+			OMAP3_CORE1_IOPAD(0x20e8, PIN_OUTPUT | MUX_MODE0)	/* dss_data6.dss_data6 */
+			OMAP3_CORE1_IOPAD(0x20ea, PIN_OUTPUT | MUX_MODE0)	/* dss_data7.dss_data7 */
+			OMAP3_CORE1_IOPAD(0x20ec, PIN_OUTPUT | MUX_MODE0)	/* dss_data8.dss_data8 */
+			OMAP3_CORE1_IOPAD(0x20ee, PIN_OUTPUT | MUX_MODE0)	/* dss_data9.dss_data9 */
+			OMAP3_CORE1_IOPAD(0x20f0, PIN_OUTPUT | MUX_MODE0)	/* dss_data10.dss_data10 */
+			OMAP3_CORE1_IOPAD(0x20f2, PIN_OUTPUT | MUX_MODE0)	/* dss_data11.dss_data11 */
+			OMAP3_CORE1_IOPAD(0x20f4, PIN_OUTPUT | MUX_MODE0)	/* dss_data12.dss_data12 */
+			OMAP3_CORE1_IOPAD(0x20f6, PIN_OUTPUT | MUX_MODE0)	/* dss_data13.dss_data13 */
+			OMAP3_CORE1_IOPAD(0x20f8, PIN_OUTPUT | MUX_MODE0)	/* dss_data14.dss_data14 */
+			OMAP3_CORE1_IOPAD(0x20fa, PIN_OUTPUT | MUX_MODE0)	/* dss_data15.dss_data15 */
+			OMAP3_CORE1_IOPAD(0x20fc, PIN_OUTPUT | MUX_MODE0)	/* dss_data16.dss_data16 */
+			OMAP3_CORE1_IOPAD(0x20fe, PIN_OUTPUT | MUX_MODE0)	/* dss_data17.dss_data17 */
+			OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE0)	/* dss_data18.dss_data18 */
+			OMAP3_CORE1_IOPAD(0x2102, PIN_OUTPUT | MUX_MODE0)	/* dss_data19.dss_data19 */
+			OMAP3_CORE1_IOPAD(0x2104, PIN_OUTPUT | MUX_MODE0)	/* dss_data20.dss_data20 */
+			OMAP3_CORE1_IOPAD(0x2106, PIN_OUTPUT | MUX_MODE0)	/* dss_data21.dss_data21 */
+			OMAP3_CORE1_IOPAD(0x2108, PIN_OUTPUT | MUX_MODE0)	/* dss_data22.dss_data22 */
+			OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE0)	/* dss_data23.dss_data23 */
+		>;
+	};
+
+	lte430_pins: pinmux_lte430_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2174, PIN_OUTPUT | MUX_MODE4)	/* uart2_cts.gpio_144 */
+		>;
+	};
+
+	backlight_pins: pinmux_backlight_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE4)	/* uart2_rts.gpio_145 */
+		>;
+	};
+
+	mcspi1_pins: pinmux_mcspi1_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21c8, PIN_INPUT | MUX_MODE0)	/* mcspi1_clk.mcspi1_clk */
+			OMAP3_CORE1_IOPAD(0x21ca, PIN_INPUT | MUX_MODE0)	/* mcspi1_simo.mcspi1_simo */
+			OMAP3_CORE1_IOPAD(0x21cc, PIN_INPUT | MUX_MODE0)	/* mcspi1_somi.mcspi1_somi */
+			OMAP3_CORE1_IOPAD(0x21ce, PIN_INPUT | MUX_MODE0)	/* mcspi1_cs0.mcspi1_cs0 */
+		>;
+	};
+
+	ads7846_pins: pinmux_ads7846_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x2138, PIN_INPUT_PULLDOWN | MUX_MODE4)	/* csi2_dx1.gpio_114 */
+		>;
+	};
+};
+
+/* Needed to power the DPI pins */
+&vpll2 {
+	regulator-always-on;
+};
+
+&dss {
+	status = "ok";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_dpi_pins>;
+
+	port {
+		dpi_out: endpoint {
+			remote-endpoint = <&lcd_in>;
+			data-lines = <24>;
+		};
+	};
+};
+
+/ {
+	aliases {
+		display0 = &lcd0;
+	};
+
+	lcd0: display@0 {
+		compatible = "samsung,lte430wq-f0c", "panel-dpi";
+		label = "lcd";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&lte430_pins>;
+		enable-gpios = <&gpio5 16 GPIO_ACTIVE_HIGH>;		/* gpio_144 */
+
+		port {
+			lcd_in: endpoint {
+				remote-endpoint = <&dpi_out>;
+			};
+		};
+
+		panel-timing {
+			clock-frequency = <9200000>;
+			hactive = <480>;
+			vactive = <272>;
+			hfront-porch = <8>;
+			hback-porch = <4>;
+			hsync-len = <41>;
+			vback-porch = <2>;
+			vfront-porch = <4>;
+			vsync-len = <10>;
+
+			hsync-active = <0>;
+			vsync-active = <0>;
+			de-active = <1>;
+			pixelclk-active = <1>;
+		};
+	};
+
+	ads7846reg: ads7846-reg {
+		compatible = "regulator-fixed";
+		regulator-name = "ads7846-reg";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
+	backlight {
+		compatible = "gpio-backlight";
+		
+		pinctrl-names = "default";
+		pinctrl-0 = <&backlight_pins>;
+		gpios = <&gpio5 17 GPIO_ACTIVE_HIGH>;		/* gpio_145 */
+
+		default-on;
+	};
+};
+
+&mcspi1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&mcspi1_pins>;
+
+	/* touch controller */
+	ads7846@0 {
+		pinctrl-names = "default";
+		pinctrl-0 = <&ads7846_pins>;
+
+		compatible = "ti,ads7846";
+		vcc-supply = <&ads7846reg>;
+
+		reg = <0>;				/* CS0 */
+		spi-max-frequency = <1500000>;
+
+		interrupt-parent = <&gpio4>;
+		interrupts = <18 0>;			/* gpio_114 */
+		pendown-gpio = <&gpio4 18 0>;
+
+		ti,x-min = /bits/ 16 <0x0>;
+		ti,x-max = /bits/ 16 <0x0fff>;
+		ti,y-min = /bits/ 16 <0x0>;
+		ti,y-max = /bits/ 16 <0x0fff>;
+		ti,x-plate-ohms = /bits/ 16 <180>;
+		ti,pressure-max = /bits/ 16 <255>;
+
+		linux,wakeup;
+	};
+};
+
diff --git a/arch/arm/boot/dts/omap3-overo-gallop43-common.dtsi b/arch/arm/boot/dts/omap3-overo-gallop43-common.dtsi
index 5e848c26986..49d2254a99b 100644
--- a/arch/arm/boot/dts/omap3-overo-gallop43-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-gallop43-common.dtsi
@@ -11,6 +11,7 @@
  */
 
 #include "omap3-overo-common-peripherals.dtsi"
+#include "omap3-overo-common-lcd43.dtsi"
 
 #include <dt-bindings/input/input.h>
 
diff --git a/arch/arm/boot/dts/omap3-overo-palo43-common.dtsi b/arch/arm/boot/dts/omap3-overo-palo43-common.dtsi
index abea232825b..087aedf5b90 100644
--- a/arch/arm/boot/dts/omap3-overo-palo43-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-palo43-common.dtsi
@@ -11,6 +11,7 @@
  */
 
 #include "omap3-overo-common-peripherals.dtsi"
+#include "omap3-overo-common-lcd43.dtsi"
 
 #include <dt-bindings/input/input.h>
 
diff --git a/arch/arm/boot/dts/omap3-overo-summit-common.dtsi b/arch/arm/boot/dts/omap3-overo-summit-common.dtsi
index 999d1cd4a09..0ac97ba9854 100644
--- a/arch/arm/boot/dts/omap3-overo-summit-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-summit-common.dtsi
@@ -11,6 +11,7 @@
  */
 
 #include "omap3-overo-common-peripherals.dtsi"
+#include "omap3-overo-common-dvi.dtsi"
 
 / {
 	leds {
diff --git a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
index 13df50b3944..9e24b6a1d07 100644
--- a/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi
@@ -11,6 +11,7 @@
  */
 
 #include "omap3-overo-common-peripherals.dtsi"
+#include "omap3-overo-common-dvi.dtsi"
 
 / {
 	leds {
diff --git a/arch/arm/boot/dts/omap3-panel-sharp-ls037v7dw01.dtsi b/arch/arm/boot/dts/omap3-panel-sharp-ls037v7dw01.dtsi
new file mode 100644
index 00000000000..f4b1a61853e
--- /dev/null
+++ b/arch/arm/boot/dts/omap3-panel-sharp-ls037v7dw01.dtsi
@@ -0,0 +1,71 @@
+/*
+ * Common file for omap dpi panels with QVGA and reset pins
+ *
+ * Note that the board specifc DTS file needs to specify
+ * at minimum the GPIO enable-gpios for display, and
+ * gpios for gpio-backlight.
+ */
+
+/ {
+	aliases {
+		display0 = &lcd0;
+	};
+
+	backlight0: backlight {
+		compatible = "gpio-backlight";
+		default-on;
+	};
+
+	/* 3.3V GPIO controlled regulator for LCD_ENVDD */
+	lcd_3v3: regulator-lcd-3v3 {
+		compatible = "regulator-fixed";
+		regulator-name = "lcd_3v3";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+		startup-delay-us = <70000>;
+	};
+
+	lcd0: display {
+		compatible = "sharp,ls037v7dw01";
+		label = "lcd";
+		power-supply = <&lcd_3v3>;
+
+		port {
+			lcd_in: endpoint {
+				remote-endpoint = <&dpi_out>;
+			};
+		};
+	};
+};
+
+/* Needed to power the DPI pins */
+&vpll2 {
+	regulator-always-on;
+};
+
+&dss {
+	status = "ok";
+	port {
+		dpi_out: endpoint {
+			remote-endpoint = <&lcd_in>;
+			data-lines = <18>;
+		};
+	};
+};
+
+&mcspi1 {
+	tsc2046@0 {
+		reg = <0>;			/* CS0 */
+		compatible = "ti,tsc2046";
+		spi-max-frequency = <1000000>;
+		vcc-supply = <&lcd_3v3>;
+		ti,x-min = /bits/ 16 <0>;
+		ti,x-max = /bits/ 16 <8000>;
+		ti,y-min = /bits/ 16 <0>;
+		ti,y-max = /bits/ 16 <4800>;
+		ti,x-plate-ohms = /bits/ 16 <40>;
+		ti,pressure-max = /bits/ 16 <255>;
+		ti,swap-xy;
+		linux,wakeup;
+	};
+};
diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts
index cd53a64d8f2..6dc84d9f9b4 100644
--- a/arch/arm/boot/dts/omap4-duovero-parlor.dts
+++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts
@@ -15,6 +15,10 @@
 	model = "OMAP4430 Gumstix Duovero on Parlor";
 	compatible = "gumstix,omap4-duovero-parlor", "gumstix,omap4-duovero", "ti,omap4430", "ti,omap4";
 
+	aliases {
+		display0 = &hdmi0;
+	};
+
 	leds {
 		compatible = "gpio-leds";
 		led0 {
@@ -35,6 +39,21 @@
 			gpio-key,wakeup;
 		};
 	};
+
+	hdmi0: connector@0 {
+		compatible = "hdmi-connector";
+		label = "hdmi";
+
+		type = "d";
+
+		hpd-gpios = <&gpio2 31 GPIO_ACTIVE_HIGH>;	/* gpio_63 */
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&hdmi_out>;
+			};
+		};
+	};
 };
 
 &omap4_pmx_core {
@@ -77,6 +96,15 @@
 			OMAP4_IOPAD(0x070, PIN_INPUT_PULLUP | MUX_MODE3)	/* gpmc_a24.gpio_48: amdix enabled */
 		>;
 	};
+
+	dss_hdmi_pins: pinmux_dss_hdmi_pins {
+		pinctrl-single,pins = <
+			OMAP4_IOPAD(0x098, PIN_INPUT | MUX_MODE3)		/* hdmi_hpd.gpio_63 */
+			OMAP4_IOPAD(0x09a, PIN_INPUT_PULLUP | MUX_MODE0)	/* hdmi_cec.hdmi_cec */
+			OMAP4_IOPAD(0x09c, PIN_INPUT_PULLUP | MUX_MODE0)	/* hdmi_ddc_scl.hdmi_ddc_scl */
+			OMAP4_IOPAD(0x09e, PIN_INPUT_PULLUP | MUX_MODE0)	/* hdmi_ddc_sda.hdmi_ddc_sda */
+		>;
+	};
 };
 
 &i2c2 {
@@ -143,4 +171,20 @@
 	};
 };
 
+&dss {
+	status = "ok";
+};
+
+&hdmi {
+	status = "ok";
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_hdmi_pins>;
+
+	port {
+		hdmi_out: endpoint {
+			remote-endpoint = <&hdmi_connector_in>;
+		};
+	};
+};
 
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 43a587e097d..7e26d222bfe 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -922,6 +922,8 @@
 				ti,hwmods = "dss_hdmi";
 				clocks = <&dss_48mhz_clk>, <&dss_sys_clk>;
 				clock-names = "fck", "sys_clk";
+				dmas = <&sdma 76>;
+				dma-names = "audio_tx";
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 3b99ec25b74..1e1b05768ce 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -20,6 +20,10 @@
 		reg = <0x80000000 0x7F000000>; /* 2032 MB */
 	};
 
+	aliases {
+		display0 = &hdmi0;
+	};
+
 	vmmcsd_fixed: fixedregulator-mmcsd {
 		compatible = "regulator-fixed";
 		regulator-name = "vmmcsd_fixed";
@@ -51,6 +55,51 @@
 			default-state = "off";
 		};
 	};
+
+	tpd12s015: encoder@0 {
+		compatible = "ti,tpd12s015";
+
+		pinctrl-names = "default";
+		pinctrl-0 = <&tpd12s015_pins>;
+
+		gpios = <&gpio9 0 GPIO_ACTIVE_HIGH>,	/* TCA6424A P01, CT CP HPD */
+			<&gpio9 1 GPIO_ACTIVE_HIGH>,	/* TCA6424A P00, LS OE */
+			<&gpio7 1 GPIO_ACTIVE_HIGH>;	/* GPIO 193, HPD */
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+
+				tpd12s015_in: endpoint@0 {
+					remote-endpoint = <&hdmi_out>;
+				};
+			};
+
+			port@1 {
+				reg = <1>;
+
+				tpd12s015_out: endpoint@0 {
+					remote-endpoint = <&hdmi_connector_in>;
+				};
+			};
+		};
+	};
+
+	hdmi0: connector@0 {
+		compatible = "hdmi-connector";
+		label = "hdmi";
+
+		type = "b";
+
+		port {
+			hdmi_connector_in: endpoint {
+				remote-endpoint = <&tpd12s015_out>;
+			};
+		};
+	};
 };
 
 &omap5_pmx_core {
@@ -183,6 +232,19 @@
 		>;
 	};
 
+	dss_hdmi_pins: pinmux_dss_hdmi_pins {
+		pinctrl-single,pins = <
+			0x0fc (PIN_INPUT_PULLUP | MUX_MODE0)	/* hdmi_cec.hdmi_cec */
+			0x100 (PIN_INPUT | MUX_MODE0)	/* hdmi_ddc_scl.hdmi_ddc_scl */
+			0x102 (PIN_INPUT | MUX_MODE0)	/* hdmi_ddc_sda.hdmi_ddc_sda */
+		>;
+	};
+
+	tpd12s015_pins: pinmux_tpd12s015_pins {
+		pinctrl-single,pins = <
+			0x0fe (PIN_INPUT_PULLDOWN | MUX_MODE6)	/* hdmi_hpd.gpio7_193 */
+		>;
+	};
 };
 
 &omap5_pmx_wkup {
@@ -434,6 +496,13 @@
 	pinctrl-0 = <&i2c5_pins>;
 
 	clock-frequency = <400000>;
+
+	gpio9: gpio@22 {
+		compatible = "ti,tca6424";
+		reg = <0x22>;
+		gpio-controller;
+		#gpio-cells = <2>;
+	};
 };
 
 &mcbsp3 {
@@ -491,3 +560,21 @@
 &cpu0 {
 	cpu0-supply = <&smps123_reg>;
 };
+
+&dss {
+	status = "ok";
+};
+
+&hdmi {
+	status = "ok";
+	vdda-supply = <&ldo4_reg>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&dss_hdmi_pins>;
+
+	port {
+		hdmi_out: endpoint {
+			remote-endpoint = <&tpd12s015_in>;
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index e58be57984a..a4ed5498886 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -45,7 +45,6 @@
 
 			operating-points = <
 				/* kHz    uV */
-				500000  880000
 				1000000 1060000
 				1500000 1250000
 			>;
@@ -924,6 +923,68 @@
 			ti,hwmods = "sata";
 		};
 
+		dss: dss@58000000 {
+			compatible = "ti,omap5-dss";
+			reg = <0x58000000 0x80>;
+			status = "disabled";
+			ti,hwmods = "dss_core";
+			clocks = <&dss_dss_clk>;
+			clock-names = "fck";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges;
+
+			dispc@58001000 {
+				compatible = "ti,omap5-dispc";
+				reg = <0x58001000 0x1000>;
+				interrupts = <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>;
+				ti,hwmods = "dss_dispc";
+				clocks = <&dss_dss_clk>;
+				clock-names = "fck";
+			};
+
+			dsi1: encoder@58004000 {
+				compatible = "ti,omap5-dsi";
+				reg = <0x58004000 0x200>,
+				      <0x58004200 0x40>,
+				      <0x58004300 0x40>;
+				reg-names = "proto", "phy", "pll";
+				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+				ti,hwmods = "dss_dsi1";
+				clocks = <&dss_dss_clk>, <&dss_sys_clk>;
+				clock-names = "fck", "sys_clk";
+			};
+
+			dsi2: encoder@58005000 {
+				compatible = "ti,omap5-dsi";
+				reg = <0x58009000 0x200>,
+				      <0x58009200 0x40>,
+				      <0x58009300 0x40>;
+				reg-names = "proto", "phy", "pll";
+				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+				ti,hwmods = "dss_dsi2";
+				clocks = <&dss_dss_clk>, <&dss_sys_clk>;
+				clock-names = "fck", "sys_clk";
+			};
+
+			hdmi: encoder@58060000 {
+				compatible = "ti,omap5-hdmi";
+				reg = <0x58040000 0x200>,
+				      <0x58040200 0x80>,
+				      <0x58040300 0x80>,
+				      <0x58060000 0x19000>;
+				reg-names = "wp", "pll", "phy", "core";
+				interrupts = <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>;
+				status = "disabled";
+				ti,hwmods = "dss_hdmi";
+				clocks = <&dss_48mhz_clk>, <&dss_sys_clk>;
+				clock-names = "fck", "sys_clk";
+				dmas = <&sdma 76>;
+				dma-names = "audio_tx";
+			};
+		};
 	};
 };
 
diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi
index aeb142ce8e9..e67a23b5d78 100644
--- a/arch/arm/boot/dts/omap54xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi
@@ -335,7 +335,7 @@
 
 	dpll_mpu_ck: dpll_mpu_ck {
 		#clock-cells = <0>;
-		compatible = "ti,omap4-dpll-clock";
+		compatible = "ti,omap5-mpu-dpll-clock";
 		clocks = <&sys_clkin>, <&mpu_dpll_hs_clk_div>;
 		reg = <0x0160>, <0x0164>, <0x016c>, <0x0168>;
 	};
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 8d7ffaeff6e..79f68acfd5d 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -540,9 +540,9 @@
 			#clock-cells = <0>;
 			clock-output-names = "sd1";
 		};
-		sd2_clk: sd3_clk@e615007c {
+		sd2_clk: sd3_clk@e615026c {
 			compatible = "renesas,r8a7791-div6-clock", "renesas,cpg-div6-clock";
-			reg = <0 0xe615007c 0 4>;
+			reg = <0 0xe615026c 0 4>;
 			clocks = <&pll1_div2_clk>;
 			#clock-cells = <0>;
 			clock-output-names = "sd2";
diff --git a/arch/arm/boot/dts/ste-nomadik-s8815.dts b/arch/arm/boot/dts/ste-nomadik-s8815.dts
index f557feb997f..90d8b6c7a20 100644
--- a/arch/arm/boot/dts/ste-nomadik-s8815.dts
+++ b/arch/arm/boot/dts/ste-nomadik-s8815.dts
@@ -4,7 +4,7 @@
  */
 
 /dts-v1/;
-/include/ "ste-nomadik-stn8815.dtsi"
+#include "ste-nomadik-stn8815.dtsi"
 
 / {
 	model = "Calao Systems USB-S8815";
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index d316c955bd5..dbcf521b017 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -1,7 +1,9 @@
 /*
  * Device Tree for the ST-Ericsson Nomadik 8815 STn8815 SoC
  */
-/include/ "skeleton.dtsi"
+
+#include <dt-bindings/gpio/gpio.h>
+#include "skeleton.dtsi"
 
 / {
 	#address-cells = <1>;
@@ -842,8 +844,7 @@
 			bus-width = <4>;
 			cap-mmc-highspeed;
 			cap-sd-highspeed;
-			cd-gpios = <&gpio3 15 0x1>;
-			cd-inverted;
+			cd-gpios = <&gpio3 15 GPIO_ACTIVE_LOW>;
 			pinctrl-names = "default";
 			pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>;
 			vmmc-supply = <&vmmc_regulator>;
diff --git a/arch/arm/boot/dts/stih415.dtsi b/arch/arm/boot/dts/stih415.dtsi
index d6f254f302f..a0f6f75fe3b 100644
--- a/arch/arm/boot/dts/stih415.dtsi
+++ b/arch/arm/boot/dts/stih415.dtsi
@@ -169,8 +169,8 @@
 
 			pinctrl-names 	= "default";
 			pinctrl-0	= <&pinctrl_mii0>;
-			clock-names	= "stmmaceth";
-			clocks		= <&clk_s_a1_ls CLK_GMAC0_PHY>;
+			clock-names	= "stmmaceth", "sti-ethclk";
+			clocks		= <&clk_s_a1_ls CLK_ICN_IF_2>, <&clk_s_a1_ls CLK_GMAC0_PHY>;
 		};
 
 		ethernet1: dwmac@fef08000 {
@@ -192,8 +192,8 @@
 			reset-names		= "stmmaceth";
 			pinctrl-names 	= "default";
 			pinctrl-0	= <&pinctrl_mii1>;
-			clock-names	= "stmmaceth";
-			clocks		= <&clk_s_a0_ls CLK_ETH1_PHY>;
+			clock-names	= "stmmaceth", "sti-ethclk";
+			clocks		= <&clk_s_a0_ls CLK_ICN_REG>, <&clk_s_a0_ls CLK_ETH1_PHY>;
 		};
 
 		rc: rc@fe518000 {
diff --git a/arch/arm/boot/dts/stih416-b2020-revE.dts b/arch/arm/boot/dts/stih416-b2020e.dts
index ba0fa2caaf1..ba0fa2caaf1 100644
--- a/arch/arm/boot/dts/stih416-b2020-revE.dts
+++ b/arch/arm/boot/dts/stih416-b2020e.dts
diff --git a/arch/arm/boot/dts/stih416.dtsi b/arch/arm/boot/dts/stih416.dtsi
index 06473c5d9ea..84758d76d06 100644
--- a/arch/arm/boot/dts/stih416.dtsi
+++ b/arch/arm/boot/dts/stih416.dtsi
@@ -175,8 +175,8 @@
 			reset-names		= "stmmaceth";
 			pinctrl-names 	= "default";
 			pinctrl-0	= <&pinctrl_mii0>;
-			clock-names	= "stmmaceth";
-			clocks		= <&clk_s_a1_ls CLK_GMAC0_PHY>;
+			clock-names	= "stmmaceth", "sti-ethclk";
+			clocks		= <&clk_s_a1_ls CLK_ICN_IF_2>, <&clk_s_a1_ls CLK_GMAC0_PHY>;
 		};
 
 		ethernet1: dwmac@fef08000 {
@@ -197,8 +197,8 @@
 			reset-names	= "stmmaceth";
 			pinctrl-names 	= "default";
 			pinctrl-0	= <&pinctrl_mii1>;
-			clock-names	= "stmmaceth";
-			clocks		= <&clk_s_a0_ls CLK_ETH1_PHY>;
+			clock-names	= "stmmaceth", "sti-ethclk";
+			clocks		= <&clk_s_a0_ls CLK_ICN_REG>, <&clk_s_a0_ls CLK_ETH1_PHY>;
 		};
 
 		rc: rc@fe518000 {
diff --git a/arch/arm/boot/dts/vt8500.dtsi b/arch/arm/boot/dts/vt8500.dtsi
index 51d0e912c8f..1929ad390d8 100644
--- a/arch/arm/boot/dts/vt8500.dtsi
+++ b/arch/arm/boot/dts/vt8500.dtsi
@@ -165,5 +165,11 @@
 			reg = <0xd8100000 0x10000>;
 			interrupts = <48>;
 		};
+
+		ethernet@d8004000 {
+			compatible = "via,vt8500-rhine";
+			reg = <0xd8004000 0x100>;
+			interrupts = <10>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi
index 7525982262a..b1c59a766a1 100644
--- a/arch/arm/boot/dts/wm8650.dtsi
+++ b/arch/arm/boot/dts/wm8650.dtsi
@@ -218,5 +218,11 @@
 			reg = <0xd8100000 0x10000>;
 			interrupts = <48>;
 		};
+
+		ethernet@d8004000 {
+			compatible = "via,vt8500-rhine";
+			reg = <0xd8004000 0x100>;
+			interrupts = <10>;
+		};
 	};
 };
diff --git a/arch/arm/boot/dts/wm8850.dtsi b/arch/arm/boot/dts/wm8850.dtsi
index d98386dd288..8fbccfbe75f 100644
--- a/arch/arm/boot/dts/wm8850.dtsi
+++ b/arch/arm/boot/dts/wm8850.dtsi
@@ -298,5 +298,11 @@
 			bus-width = <4>;
 			sdon-inverted;
 		};
+
+		ethernet@d8004000 {
+			compatible = "via,vt8500-rhine";
+			reg = <0xd8004000 0x100>;
+			interrupts = <10>;
+                };
 	};
 };
diff --git a/arch/arm/common/scoop.c b/arch/arm/common/scoop.c
index 6ef146edd0c..a20fa80776d 100644
--- a/arch/arm/common/scoop.c
+++ b/arch/arm/common/scoop.c
@@ -182,7 +182,6 @@ static int scoop_probe(struct platform_device *pdev)
 	struct scoop_config *inf;
 	struct resource *mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	int ret;
-	int temp;
 
 	if (!mem)
 		return -EINVAL;
diff --git a/arch/arm/configs/bcm_defconfig b/arch/arm/configs/bcm_defconfig
index 9d13dae9912..4bf72264b17 100644
--- a/arch/arm/configs/bcm_defconfig
+++ b/arch/arm/configs/bcm_defconfig
@@ -94,10 +94,10 @@ CONFIG_BACKLIGHT_CLASS_DEVICE=y
 CONFIG_BACKLIGHT_PWM=y
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
-CONFIG_MMC_UNSAFE_RESUME=y
 CONFIG_MMC_BLOCK_MINORS=32
 CONFIG_MMC_TEST=y
 CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_BCM_KONA=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index ef8815327e5..59b7e45142d 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -186,6 +186,7 @@ CONFIG_VIDEO_MX3=y
 CONFIG_V4L_MEM2MEM_DRIVERS=y
 CONFIG_VIDEO_CODA=y
 CONFIG_SOC_CAMERA_OV2640=y
+CONFIG_IMX_IPUV3_CORE=y
 CONFIG_DRM=y
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
diff --git a/arch/arm/configs/integrator_defconfig b/arch/arm/configs/integrator_defconfig
index 5bae1955759..c1f5adc5493 100644
--- a/arch/arm/configs/integrator_defconfig
+++ b/arch/arm/configs/integrator_defconfig
@@ -73,7 +73,6 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_LEDS_TRIGGER_CPU=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_PL030=y
-CONFIG_COMMON_CLK_DEBUG=y
 CONFIG_EXT2_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig
index 095bb52671f..932ae40fb12 100644
--- a/arch/arm/configs/keystone_defconfig
+++ b/arch/arm/configs/keystone_defconfig
@@ -112,6 +112,7 @@ CONFIG_MTD_PLATRAM=y
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_DAVINCI=y
+CONFIG_MTD_SPI_NOR=y
 CONFIG_MTD_UBI=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
@@ -131,6 +132,9 @@ CONFIG_SPI=y
 CONFIG_SPI_DAVINCI=y
 CONFIG_SPI_SPIDEV=y
 # CONFIG_HWMON is not set
+CONFIG_POWER_SUPPLY=y
+CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_KEYSTONE=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_CORE=y
 CONFIG_DAVINCI_WATCHDOG=y
@@ -145,7 +149,6 @@ CONFIG_USB_DWC3_VERBOSE=y
 CONFIG_KEYSTONE_USB_PHY=y
 CONFIG_DMADEVICES=y
 CONFIG_TI_EDMA=y
-CONFIG_COMMON_CLK_DEBUG=y
 CONFIG_MEMORY=y
 CONFIG_TI_AEMIF=y
 CONFIG_EXT4_FS=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index e2d62048e19..53483649799 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -223,12 +223,12 @@ CONFIG_POWER_RESET_GPIO=y
 CONFIG_POWER_RESET_SUN6I=y
 CONFIG_SENSORS_LM90=y
 CONFIG_THERMAL=y
-CONFIG_DOVE_THERMAL=y
 CONFIG_ARMADA_THERMAL=y
 CONFIG_WATCHDOG=y
 CONFIG_ORION_WATCHDOG=y
 CONFIG_SUNXI_WATCHDOG=y
 CONFIG_MFD_AS3722=y
+CONFIG_MFD_BCM590XX=y
 CONFIG_MFD_CROS_EC=y
 CONFIG_MFD_CROS_EC_SPI=y
 CONFIG_MFD_MAX8907=y
@@ -240,6 +240,7 @@ CONFIG_MFD_TPS65910=y
 CONFIG_REGULATOR_VIRTUAL_CONSUMER=y
 CONFIG_REGULATOR_AB8500=y
 CONFIG_REGULATOR_AS3722=y
+CONFIG_REGULATOR_BCM590XX=y
 CONFIG_REGULATOR_GPIO=y
 CONFIG_REGULATOR_MAX8907=y
 CONFIG_REGULATOR_PALMAS=y
@@ -300,6 +301,7 @@ CONFIG_MMC=y
 CONFIG_MMC_BLOCK_MINORS=16
 CONFIG_MMC_ARMMMCI=y
 CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_OF_ARASAN=y
 CONFIG_MMC_SDHCI_ESDHC_IMX=y
 CONFIG_MMC_SDHCI_DOVE=y
@@ -352,6 +354,7 @@ CONFIG_MFD_NVEC=y
 CONFIG_KEYBOARD_NVEC=y
 CONFIG_SERIO_NVEC_PS2=y
 CONFIG_NVEC_POWER=y
+CONFIG_QCOM_GSBI=y
 CONFIG_COMMON_CLK_QCOM=y
 CONFIG_MSM_GCC_8660=y
 CONFIG_MSM_MMCC_8960=y
diff --git a/arch/arm/configs/mvebu_v7_defconfig b/arch/arm/configs/mvebu_v7_defconfig
index e11170e3744..b0bfefa2390 100644
--- a/arch/arm/configs/mvebu_v7_defconfig
+++ b/arch/arm/configs/mvebu_v7_defconfig
@@ -14,6 +14,7 @@ CONFIG_MACH_ARMADA_370=y
 CONFIG_MACH_ARMADA_375=y
 CONFIG_MACH_ARMADA_38X=y
 CONFIG_MACH_ARMADA_XP=y
+CONFIG_MACH_DOVE=y
 CONFIG_NEON=y
 # CONFIG_CACHE_L2X0 is not set
 # CONFIG_SWP_EMULATE is not set
@@ -52,6 +53,7 @@ CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_GPIO=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_I2C=y
 CONFIG_SPI=y
 CONFIG_SPI_ORION=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 59066cf0271..536a137863c 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -32,6 +32,7 @@ CONFIG_SOC_OMAP5=y
 CONFIG_SOC_AM33XX=y
 CONFIG_SOC_AM43XX=y
 CONFIG_SOC_DRA7XX=y
+CONFIG_CACHE_L2X0=y
 CONFIG_ARM_THUMBEE=y
 CONFIG_ARM_ERRATA_411920=y
 CONFIG_SMP=y
diff --git a/arch/arm/configs/vt8500_v6_v7_defconfig b/arch/arm/configs/vt8500_v6_v7_defconfig
index f0520176acd..9e7a2563969 100644
--- a/arch/arm/configs/vt8500_v6_v7_defconfig
+++ b/arch/arm/configs/vt8500_v6_v7_defconfig
@@ -73,7 +73,6 @@ CONFIG_LEDS_TRIGGERS=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_VT8500=y
 CONFIG_DMADEVICES=y
-CONFIG_COMMON_CLK_DEBUG=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_PWM=y
 CONFIG_PWM_VT8500=y
diff --git a/arch/arm/crypto/aesbs-glue.c b/arch/arm/crypto/aesbs-glue.c
index 4522366da75..15468fbbdea 100644
--- a/arch/arm/crypto/aesbs-glue.c
+++ b/arch/arm/crypto/aesbs-glue.c
@@ -137,7 +137,7 @@ static int aesbs_cbc_encrypt(struct blkcipher_desc *desc,
 				dst += AES_BLOCK_SIZE;
 			} while (--blocks);
 		}
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -158,7 +158,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
 		bsaes_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->dec, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	while (walk.nbytes) {
 		u32 blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -182,7 +182,7 @@ static int aesbs_cbc_decrypt(struct blkcipher_desc *desc,
 			dst += AES_BLOCK_SIZE;
 			src += AES_BLOCK_SIZE;
 		} while (--blocks);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -268,7 +268,7 @@ static int aesbs_xts_encrypt(struct blkcipher_desc *desc,
 		bsaes_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->enc, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
@@ -292,7 +292,7 @@ static int aesbs_xts_decrypt(struct blkcipher_desc *desc,
 		bsaes_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr,
 				  walk.nbytes, &ctx->dec, walk.iv);
 		kernel_neon_end();
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	return err;
 }
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index eb577f4f5f7..39eb16b0066 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -52,7 +52,7 @@ extern inline void *return_address(unsigned int level)
 
 #endif
 
-#define ftrace_return_addr(n) return_address(n)
+#define ftrace_return_address(n) return_address(n)
 
 #endif /* ifndef __ASSEMBLY__ */
 
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index c81adc08b3f..a3c24cd5b7c 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -130,22 +130,22 @@
 #endif
 
 #ifndef __ASSEMBLER__
-extern inline void nop_flush_icache_all(void) { }
-extern inline void nop_flush_kern_cache_all(void) { }
-extern inline void nop_flush_kern_cache_louis(void) { }
-extern inline void nop_flush_user_cache_all(void) { }
-extern inline void nop_flush_user_cache_range(unsigned long a,
+static inline void nop_flush_icache_all(void) { }
+static inline void nop_flush_kern_cache_all(void) { }
+static inline void nop_flush_kern_cache_louis(void) { }
+static inline void nop_flush_user_cache_all(void) { }
+static inline void nop_flush_user_cache_range(unsigned long a,
 		unsigned long b, unsigned int c) { }
 
-extern inline void nop_coherent_kern_range(unsigned long a, unsigned long b) { }
-extern inline int nop_coherent_user_range(unsigned long a,
+static inline void nop_coherent_kern_range(unsigned long a, unsigned long b) { }
+static inline int nop_coherent_user_range(unsigned long a,
 		unsigned long b) { return 0; }
-extern inline void nop_flush_kern_dcache_area(void *a, size_t s) { }
+static inline void nop_flush_kern_dcache_area(void *a, size_t s) { }
 
-extern inline void nop_dma_flush_range(const void *a, const void *b) { }
+static inline void nop_dma_flush_range(const void *a, const void *b) { }
 
-extern inline void nop_dma_map_area(const void *s, size_t l, int f) { }
-extern inline void nop_dma_unmap_area(const void *s, size_t l, int f) { }
+static inline void nop_dma_map_area(const void *s, size_t l, int f) { }
+static inline void nop_dma_unmap_area(const void *s, size_t l, int f) { }
 #endif
 
 #ifndef MULTI_CACHE
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 060a75e9926..0406cb3f1af 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -50,6 +50,7 @@ struct machine_desc {
 	struct smp_operations	*smp;		/* SMP operations	*/
 	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **);
+	void			(*dt_fixup)(void);
 	void			(*init_meminfo)(void);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index d9702eb0b02..94060adba17 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -208,8 +208,6 @@ struct sync_struct {
 	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
 };
 
-extern unsigned long sync_phys;	/* physical address of *mcpm_sync */
-
 void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster);
 void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster);
 void __mcpm_outbound_leave_critical(unsigned int cluster, int state);
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index c3d5fc124a0..8a1e8e995da 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -82,6 +82,8 @@ unsigned long get_wchan(struct task_struct *p);
 #define cpu_relax()			barrier()
 #endif
 
+#define cpu_relax_lowlatency()                cpu_relax()
+
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index f989d7c22dc..e4e4208a913 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -114,8 +114,14 @@ static inline struct thread_info *current_thread_info(void)
 	((unsigned long)(task_thread_info(tsk)->cpu_context.pc))
 #define thread_saved_sp(tsk)	\
 	((unsigned long)(task_thread_info(tsk)->cpu_context.sp))
+
+#ifndef CONFIG_THUMB2_KERNEL
 #define thread_saved_fp(tsk)	\
 	((unsigned long)(task_thread_info(tsk)->cpu_context.fp))
+#else
+#define thread_saved_fp(tsk)	\
+	((unsigned long)(task_thread_info(tsk)->cpu_context.r7))
+#endif
 
 extern void crunch_task_disable(struct thread_info *);
 extern void crunch_task_copy(struct thread_info *, void *);
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index e94a157ddff..11c54de9f8c 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -212,7 +212,7 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 	mdesc_best = &__mach_desc_GENERIC_DT;
 #endif
 
-	if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys)))
+	if (!dt_phys || !early_init_dt_verify(phys_to_virt(dt_phys)))
 		return NULL;
 
 	mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach);
@@ -237,6 +237,12 @@ const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
 		dump_machine_table(); /* does not return */
 	}
 
+	/* We really don't want to do this, but sometimes firmware provides buggy data */
+	if (mdesc->dt_fixup)
+		mdesc->dt_fixup();
+
+	early_init_dt_scan_nodes();
+
 	/* Change machine number to match the mdesc we're using */
 	__machine_arch_type = mdesc->nr;
 
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index a5599cfc43c..2b32978ae90 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -94,13 +94,19 @@ ENTRY(iwmmxt_task_enable)
 
 	mrc	p15, 0, r2, c2, c0, 0
 	mov	r2, r2				@ cpwait
+	bl	concan_save
 
-	teq	r1, #0				@ test for last ownership
-	mov	lr, r9				@ normal exit from exception
-	beq	concan_load			@ no owner, skip save
+#ifdef CONFIG_PREEMPT_COUNT
+	get_thread_info r10
+#endif
+4:	dec_preempt_count r10, r3
+	mov	pc, r9				@ normal exit from exception
 
 concan_save:
 
+	teq	r1, #0				@ test for last ownership
+	beq	concan_load			@ no owner, skip save
+
 	tmrc	r2, wCon
 
 	@ CUP? wCx
@@ -138,7 +144,7 @@ concan_dump:
 	wstrd	wR15, [r1, #MMX_WR15]
 
 2:	teq	r0, #0				@ anything to load?
-	beq	3f
+	moveq	pc, lr				@ if not, return
 
 concan_load:
 
@@ -171,14 +177,9 @@ concan_load:
 	@ clear CUP/MUP (only if r1 != 0)
 	teq	r1, #0
 	mov 	r2, #0
-	beq	3f
-	tmcr	wCon, r2
+	moveq	pc, lr
 
-3:
-#ifdef CONFIG_PREEMPT_COUNT
-	get_thread_info r10
-#endif
-4:	dec_preempt_count r10, r3
+	tmcr	wCon, r2
 	mov	pc, lr
 
 /*
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index 778c2f7024f..a74b53c1b7d 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -160,12 +160,16 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr)
 static struct undef_hook kgdb_brkpt_hook = {
 	.instr_mask		= 0xffffffff,
 	.instr_val		= KGDB_BREAKINST,
+	.cpsr_mask		= MODE_MASK,
+	.cpsr_val		= SVC_MODE,
 	.fn			= kgdb_brk_fn
 };
 
 static struct undef_hook kgdb_compiled_brkpt_hook = {
 	.instr_mask		= 0xffffffff,
 	.instr_val		= KGDB_COMPILED_BREAK,
+	.cpsr_mask		= MODE_MASK,
+	.cpsr_val		= SVC_MODE,
 	.fn			= kgdb_compiled_brk_fn
 };
 
diff --git a/arch/arm/kernel/kprobes-test-arm.c b/arch/arm/kernel/kprobes-test-arm.c
index 9db4b659d03..cb1424240ff 100644
--- a/arch/arm/kernel/kprobes-test-arm.c
+++ b/arch/arm/kernel/kprobes-test-arm.c
@@ -74,8 +74,6 @@ void kprobe_arm_test_cases(void)
 	TEST_RRR( op "lt" s "	r11, r",11,VAL1,", r",14,N(val),", asr r",7, 6,"")\
 	TEST_RR(  op "gt" s "	r12, r13"       ", r",14,val, ", ror r",14,7,"")\
 	TEST_RR(  op "le" s "	r14, r",0, val, ", r13"       ", lsl r",14,8,"")\
-	TEST_RR(  op s "	r12, pc"        ", r",14,val, ", ror r",14,7,"")\
-	TEST_RR(  op s "	r14, r",0, val, ", pc"        ", lsl r",14,8,"")\
 	TEST_R(   op "eq" s "	r0,  r",11,VAL1,", #0xf5")			\
 	TEST_R(   op "ne" s "	r11, r",0, VAL1,", #0xf5000000")		\
 	TEST_R(   op s "	r7,  r",8, VAL2,", #0x000af000")		\
@@ -103,8 +101,6 @@ void kprobe_arm_test_cases(void)
 	TEST_RRR( op "ge	r",11,VAL1,", r",14,N(val),", asr r",7, 6,"")	\
 	TEST_RR(  op "le	r13"       ", r",14,val, ", ror r",14,7,"")	\
 	TEST_RR(  op "gt	r",0, val, ", r13"       ", lsl r",14,8,"")	\
-	TEST_RR(  op "	pc"        ", r",14,val, ", ror r",14,7,"")		\
-	TEST_RR(  op "	r",0, val, ", pc"        ", lsl r",14,8,"")		\
 	TEST_R(   op "eq	r",11,VAL1,", #0xf5")				\
 	TEST_R(   op "ne	r",0, VAL1,", #0xf5000000")			\
 	TEST_R(   op "	r",8, VAL2,", #0x000af000")
@@ -125,7 +121,6 @@ void kprobe_arm_test_cases(void)
 	TEST_RR(  op "ge" s "	r11, r",11,N(val),", asr r",7, 6,"")	\
 	TEST_RR(  op "lt" s "	r12, r",11,val, ", ror r",14,7,"")	\
 	TEST_R(   op "gt" s "	r14, r13"       ", lsl r",14,8,"")	\
-	TEST_R(   op "le" s "	r14, pc"        ", lsl r",14,8,"")	\
 	TEST(     op "eq" s "	r0,  #0xf5")				\
 	TEST(     op "ne" s "	r11, #0xf5000000")			\
 	TEST(     op s "	r7,  #0x000af000")			\
@@ -159,12 +154,19 @@ void kprobe_arm_test_cases(void)
 	TEST_SUPPORTED("cmp	pc, #0x1000");
 	TEST_SUPPORTED("cmp	sp, #0x1000");
 
-	/* Data-processing with PC as shift*/
+	/* Data-processing with PC and a shift count in a register */
 	TEST_UNSUPPORTED(__inst_arm(0xe15c0f1e) "	@ cmp	r12, r14, asl pc")
 	TEST_UNSUPPORTED(__inst_arm(0xe1a0cf1e) "	@ mov	r12, r14, asl pc")
 	TEST_UNSUPPORTED(__inst_arm(0xe08caf1e) "	@ add	r10, r12, r14, asl pc")
-
-	/* Data-processing with PC as shift*/
+	TEST_UNSUPPORTED(__inst_arm(0xe151021f) "	@ cmp	r1, pc, lsl r2")
+	TEST_UNSUPPORTED(__inst_arm(0xe17f0211) "	@ cmn	pc, r1, lsl r2")
+	TEST_UNSUPPORTED(__inst_arm(0xe1a0121f) "	@ mov	r1, pc, lsl r2")
+	TEST_UNSUPPORTED(__inst_arm(0xe1a0f211) "	@ mov	pc, r1, lsl r2")
+	TEST_UNSUPPORTED(__inst_arm(0xe042131f) "	@ sub	r1, r2, pc, lsl r3")
+	TEST_UNSUPPORTED(__inst_arm(0xe1cf1312) "	@ bic	r1, pc, r2, lsl r3")
+	TEST_UNSUPPORTED(__inst_arm(0xe081f312) "	@ add	pc, r1, r2, lsl r3")
+
+	/* Data-processing with PC as a target and status registers updated */
 	TEST_UNSUPPORTED("movs	pc, r1")
 	TEST_UNSUPPORTED("movs	pc, r1, lsl r2")
 	TEST_UNSUPPORTED("movs	pc, #0x10000")
@@ -187,14 +189,14 @@ void kprobe_arm_test_cases(void)
 	TEST_BF_R ("add	pc, pc, r",14,2f-1f-8,"")
 	TEST_BF_R ("add	pc, r",14,2f-1f-8,", pc")
 	TEST_BF_R ("mov	pc, r",0,2f,"")
-	TEST_BF_RR("mov	pc, r",0,2f,", asl r",1,0,"")
+	TEST_BF_R ("add	pc, pc, r",14,(2f-1f-8)*2,", asr #1")
 	TEST_BB(   "sub	pc, pc, #1b-2b+8")
 #if __LINUX_ARM_ARCH__ == 6 && !defined(CONFIG_CPU_V7)
 	TEST_BB(   "sub	pc, pc, #1b-2b+8-2") /* UNPREDICTABLE before and after ARMv6 */
 #endif
 	TEST_BB_R( "sub	pc, pc, r",14, 1f-2f+8,"")
 	TEST_BB_R( "rsb	pc, r",14,1f-2f+8,", pc")
-	TEST_RR(   "add	pc, pc, r",10,-2,", asl r",11,1,"")
+	TEST_R(    "add	pc, pc, r",10,-2,", asl #1")
 #ifdef CONFIG_THUMB2_KERNEL
 	TEST_ARM_TO_THUMB_INTERWORK_R("add	pc, pc, r",0,3f-1f-8+1,"")
 	TEST_ARM_TO_THUMB_INTERWORK_R("sub	pc, r",0,3f+8+1,", #8")
@@ -216,6 +218,7 @@ void kprobe_arm_test_cases(void)
 	TEST_BB_R("bx	r",7,2f,"")
 	TEST_BF_R("bxeq	r",14,2f,"")
 
+#if __LINUX_ARM_ARCH__ >= 5
 	TEST_R("clz	r0, r",0, 0x0,"")
 	TEST_R("clzeq	r7, r",14,0x1,"")
 	TEST_R("clz	lr, r",7, 0xffffffff,"")
@@ -337,6 +340,7 @@ void kprobe_arm_test_cases(void)
 	TEST_UNSUPPORTED(__inst_arm(0xe16f02e1) " @ smultt pc, r1, r2")
 	TEST_UNSUPPORTED(__inst_arm(0xe16002ef) " @ smultt r0, pc, r2")
 	TEST_UNSUPPORTED(__inst_arm(0xe1600fe1) " @ smultt r0, r1, pc")
+#endif
 
 	TEST_GROUP("Multiply and multiply-accumulate")
 
@@ -559,6 +563,7 @@ void kprobe_arm_test_cases(void)
 	TEST_UNSUPPORTED("ldrsht	r1, [r2], #48")
 #endif
 
+#if __LINUX_ARM_ARCH__ >= 5
 	TEST_RPR(  "strd	r",0, VAL1,", [r",1, 48,", -r",2,24,"]")
 	TEST_RPR(  "strccd	r",8, VAL2,", [r",13,0, ", r",12,48,"]")
 	TEST_RPR(  "strd	r",4, VAL1,", [r",2, 24,", r",3, 48,"]!")
@@ -595,6 +600,7 @@ void kprobe_arm_test_cases(void)
 	TEST_UNSUPPORTED(__inst_arm(0xe1efc3d0) "	@ ldrd r12, [pc, #48]!")
 	TEST_UNSUPPORTED(__inst_arm(0xe0c9f3d0) "	@ ldrd pc, [r9], #48")
 	TEST_UNSUPPORTED(__inst_arm(0xe0c9e3d0) "	@ ldrd lr, [r9], #48")
+#endif
 
 	TEST_GROUP("Miscellaneous")
 
@@ -1227,7 +1233,9 @@ void kprobe_arm_test_cases(void)
 	TEST_COPROCESSOR( "mrc"two"	0, 0, r0, cr0, cr0, 0")
 
 	COPROCESSOR_INSTRUCTIONS_ST_LD("",e)
+#if __LINUX_ARM_ARCH__ >= 5
 	COPROCESSOR_INSTRUCTIONS_MC_MR("",e)
+#endif
 	TEST_UNSUPPORTED("svc	0")
 	TEST_UNSUPPORTED("svc	0xffffff")
 
@@ -1287,7 +1295,9 @@ void kprobe_arm_test_cases(void)
 	TEST(	"blx	__dummy_thumb_subroutine_odd")
 #endif /* __LINUX_ARM_ARCH__ >= 6 */
 
+#if __LINUX_ARM_ARCH__ >= 5
 	COPROCESSOR_INSTRUCTIONS_ST_LD("2",f)
+#endif
 #if __LINUX_ARM_ARCH__ >= 6
 	COPROCESSOR_INSTRUCTIONS_MC_MR("2",f)
 #endif
diff --git a/arch/arm/kernel/kprobes-test.c b/arch/arm/kernel/kprobes-test.c
index 379639998d5..08d731294bc 100644
--- a/arch/arm/kernel/kprobes-test.c
+++ b/arch/arm/kernel/kprobes-test.c
@@ -225,6 +225,7 @@ static int pre_handler_called;
 static int post_handler_called;
 static int jprobe_func_called;
 static int kretprobe_handler_called;
+static int tests_failed;
 
 #define FUNC_ARG1 0x12345678
 #define FUNC_ARG2 0xabcdef
@@ -461,6 +462,13 @@ static int run_api_tests(long (*func)(long, long))
 
 	pr_info("    jprobe\n");
 	ret = test_jprobe(func);
+#if defined(CONFIG_THUMB2_KERNEL) && !defined(MODULE)
+	if (ret == -EINVAL) {
+		pr_err("FAIL: Known longtime bug with jprobe on Thumb kernels\n");
+		tests_failed = ret;
+		ret = 0;
+	}
+#endif
 	if (ret < 0)
 		return ret;
 
@@ -1672,6 +1680,8 @@ static int __init run_all_tests(void)
 
 out:
 	if (ret == 0)
+		ret = tests_failed;
+	if (ret == 0)
 		pr_info("Finished kprobe tests OK\n");
 	else
 		pr_err("kprobe tests failed\n");
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index a6bc431cde7..4238bcba9d6 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -410,7 +410,7 @@ __hw_perf_event_init(struct perf_event *event)
 	 */
 	hwc->config_base	    |= (unsigned long)mapping;
 
-	if (!hwc->sample_period) {
+	if (!is_sampling_event(event)) {
 		/*
 		 * For non-sampling runs, limit the sample_period to half
 		 * of the counter width. That way, the new counter value
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index a71ae152362..af9e35e8836 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -126,8 +126,8 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 	if (irqs < 1) {
-		pr_err("no irqs for PMUs defined\n");
-		return -ENODEV;
+		printk_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
+		return 0;
 	}
 
 	irq = platform_get_irq(pmu_device, 0);
@@ -191,6 +191,10 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	/* Ensure the PMU has sane values out of reset. */
 	if (cpu_pmu->reset)
 		on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
+
+	/* If no interrupts available, set the corresponding capability flag */
+	if (!platform_get_irq(cpu_pmu->plat_device, 0))
+		cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 }
 
 /*
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 2037f720598..1d37568c547 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1924,7 +1924,7 @@ static int krait_pmu_get_event_idx(struct pmu_hw_events *cpuc,
 				   struct perf_event *event)
 {
 	int idx;
-	int bit;
+	int bit = -1;
 	unsigned int prefix;
 	unsigned int region;
 	unsigned int code;
@@ -1953,7 +1953,7 @@ static int krait_pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	}
 
 	idx = armv7pmu_get_event_idx(cpuc, event);
-	if (idx < 0 && krait_event)
+	if (idx < 0 && bit >= 0)
 		clear_bit(bit, cpuc->used_mask);
 
 	return idx;
diff --git a/arch/arm/kernel/probes-arm.c b/arch/arm/kernel/probes-arm.c
index 51a13a02798..8eaef81d834 100644
--- a/arch/arm/kernel/probes-arm.c
+++ b/arch/arm/kernel/probes-arm.c
@@ -341,12 +341,12 @@ static const union decode_item arm_cccc_000x_table[] = {
 	/* CMP (reg-shift reg)	cccc 0001 0101 xxxx xxxx xxxx 0xx1 xxxx */
 	/* CMN (reg-shift reg)	cccc 0001 0111 xxxx xxxx xxxx 0xx1 xxxx */
 	DECODE_EMULATEX	(0x0f900090, 0x01100010, PROBES_DATA_PROCESSING_REG,
-						 REGS(ANY, 0, NOPC, 0, ANY)),
+						 REGS(NOPC, 0, NOPC, 0, NOPC)),
 
 	/* MOV (reg-shift reg)	cccc 0001 101x xxxx xxxx xxxx 0xx1 xxxx */
 	/* MVN (reg-shift reg)	cccc 0001 111x xxxx xxxx xxxx 0xx1 xxxx */
 	DECODE_EMULATEX	(0x0fa00090, 0x01a00010, PROBES_DATA_PROCESSING_REG,
-						 REGS(0, ANY, NOPC, 0, ANY)),
+						 REGS(0, NOPC, NOPC, 0, NOPC)),
 
 	/* AND (reg-shift reg)	cccc 0000 000x xxxx xxxx xxxx 0xx1 xxxx */
 	/* EOR (reg-shift reg)	cccc 0000 001x xxxx xxxx xxxx 0xx1 xxxx */
@@ -359,7 +359,7 @@ static const union decode_item arm_cccc_000x_table[] = {
 	/* ORR (reg-shift reg)	cccc 0001 100x xxxx xxxx xxxx 0xx1 xxxx */
 	/* BIC (reg-shift reg)	cccc 0001 110x xxxx xxxx xxxx 0xx1 xxxx */
 	DECODE_EMULATEX	(0x0e000090, 0x00000010, PROBES_DATA_PROCESSING_REG,
-						 REGS(ANY, ANY, NOPC, 0, ANY)),
+						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
 
 	DECODE_END
 };
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 0dd3b79b15c..0c27ed6f3f2 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -908,7 +908,7 @@ enum ptrace_syscall_dir {
 	PTRACE_SYSCALL_EXIT,
 };
 
-static int tracehook_report_syscall(struct pt_regs *regs,
+static void tracehook_report_syscall(struct pt_regs *regs,
 				    enum ptrace_syscall_dir dir)
 {
 	unsigned long ip;
@@ -926,7 +926,6 @@ static int tracehook_report_syscall(struct pt_regs *regs,
 		current_thread_info()->syscall = -1;
 
 	regs->ARM_ip = ip;
-	return current_thread_info()->syscall;
 }
 
 asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
@@ -938,7 +937,9 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
 		return -1;
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
-		scno = tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
+
+	scno = current_thread_info()->syscall;
 
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, scno);
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 3997c411c14..e35d880f977 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -26,30 +26,30 @@
 #include <asm/topology.h>
 
 /*
- * cpu power scale management
+ * cpu capacity scale management
  */
 
 /*
- * cpu power table
+ * cpu capacity table
  * This per cpu data structure describes the relative capacity of each core.
  * On a heteregenous system, cores don't have the same computation capacity
- * and we reflect that difference in the cpu_power field so the scheduler can
- * take this difference into account during load balance. A per cpu structure
- * is preferred because each CPU updates its own cpu_power field during the
- * load balance except for idle cores. One idle core is selected to run the
- * rebalance_domains for all idle cores and the cpu_power can be updated
- * during this sequence.
+ * and we reflect that difference in the cpu_capacity field so the scheduler
+ * can take this difference into account during load balance. A per cpu
+ * structure is preferred because each CPU updates its own cpu_capacity field
+ * during the load balance except for idle cores. One idle core is selected
+ * to run the rebalance_domains for all idle cores and the cpu_capacity can be
+ * updated during this sequence.
  */
 static DEFINE_PER_CPU(unsigned long, cpu_scale);
 
-unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
 {
 	return per_cpu(cpu_scale, cpu);
 }
 
-static void set_power_scale(unsigned int cpu, unsigned long power)
+static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
 {
-	per_cpu(cpu_scale, cpu) = power;
+	per_cpu(cpu_scale, cpu) = capacity;
 }
 
 #ifdef CONFIG_OF
@@ -62,11 +62,11 @@ struct cpu_efficiency {
  * Table of relative efficiency of each processors
  * The efficiency value must fit in 20bit and the final
  * cpu_scale value must be in the range
- *   0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ *   0 < cpu_scale < 3*SCHED_CAPACITY_SCALE/2
  * in order to return at most 1 when DIV_ROUND_CLOSEST
  * is used to compute the capacity of a CPU.
  * Processors that are not defined in the table,
- * use the default SCHED_POWER_SCALE value for cpu_scale.
+ * use the default SCHED_CAPACITY_SCALE value for cpu_scale.
  */
 static const struct cpu_efficiency table_efficiency[] = {
 	{"arm,cortex-a15", 3891},
@@ -83,9 +83,9 @@ static unsigned long middle_capacity = 1;
  * Iterate all CPUs' descriptor in DT and compute the efficiency
  * (as per table_efficiency). Also calculate a middle efficiency
  * as close as possible to  (max{eff_i} - min{eff_i}) / 2
- * This is later used to scale the cpu_power field such that an
- * 'average' CPU is of middle power. Also see the comments near
- * table_efficiency[] and update_cpu_power().
+ * This is later used to scale the cpu_capacity field such that an
+ * 'average' CPU is of middle capacity. Also see the comments near
+ * table_efficiency[] and update_cpu_capacity().
  */
 static void __init parse_dt_topology(void)
 {
@@ -141,15 +141,15 @@ static void __init parse_dt_topology(void)
 	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
 	 * compute a middle_capacity factor that will ensure that the capacity
 	 * of an 'average' CPU of the system will be as close as possible to
-	 * SCHED_POWER_SCALE, which is the default value, but with the
+	 * SCHED_CAPACITY_SCALE, which is the default value, but with the
 	 * constraint explained near table_efficiency[].
 	 */
 	if (4*max_capacity < (3*(max_capacity + min_capacity)))
 		middle_capacity = (min_capacity + max_capacity)
-				>> (SCHED_POWER_SHIFT+1);
+				>> (SCHED_CAPACITY_SHIFT+1);
 	else
 		middle_capacity = ((max_capacity / 3)
-				>> (SCHED_POWER_SHIFT-1)) + 1;
+				>> (SCHED_CAPACITY_SHIFT-1)) + 1;
 
 }
 
@@ -158,20 +158,20 @@ static void __init parse_dt_topology(void)
  * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
  * function returns directly for SMP system.
  */
-static void update_cpu_power(unsigned int cpu)
+static void update_cpu_capacity(unsigned int cpu)
 {
 	if (!cpu_capacity(cpu))
 		return;
 
-	set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+	set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity);
 
-	printk(KERN_INFO "CPU%u: update cpu_power %lu\n",
-		cpu, arch_scale_freq_power(NULL, cpu));
+	printk(KERN_INFO "CPU%u: update cpu_capacity %lu\n",
+		cpu, arch_scale_freq_capacity(NULL, cpu));
 }
 
 #else
 static inline void parse_dt_topology(void) {}
-static inline void update_cpu_power(unsigned int cpuid) {}
+static inline void update_cpu_capacity(unsigned int cpuid) {}
 #endif
 
  /*
@@ -267,7 +267,7 @@ void store_cpu_topology(unsigned int cpuid)
 
 	update_siblings_masks(cpuid);
 
-	update_cpu_power(cpuid);
+	update_cpu_capacity(cpuid);
 
 	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
 		cpuid, cpu_topology[cpuid].thread_id,
@@ -275,7 +275,7 @@ void store_cpu_topology(unsigned int cpuid)
 		cpu_topology[cpuid].socket_id, mpidr);
 }
 
-static inline const int cpu_corepower_flags(void)
+static inline int cpu_corepower_flags(void)
 {
 	return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
 }
@@ -297,7 +297,7 @@ void __init init_cpu_topology(void)
 {
 	unsigned int cpu;
 
-	/* init core mask and power*/
+	/* init core mask and capacity */
 	for_each_possible_cpu(cpu) {
 		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
 
@@ -307,7 +307,7 @@ void __init init_cpu_topology(void)
 		cpumask_clear(&cpu_topo->core_sibling);
 		cpumask_clear(&cpu_topo->thread_sibling);
 
-		set_power_scale(cpu, SCHED_POWER_SCALE);
+		set_capacity_scale(cpu, SCHED_CAPACITY_SCALE);
 	}
 	smp_wmb();
 
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index cb791ac6a00..e67682f02cb 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -31,7 +31,7 @@
 #warning Your compiler does not have EABI support.
 #warning    ARM unwind is known to compile only with EABI compilers.
 #warning    Change compiler or disable ARM_UNWIND option.
-#elif (__GNUC__ == 4 && __GNUC_MINOR__ <= 2)
+#elif (__GNUC__ == 4 && __GNUC_MINOR__ <= 2) && !defined(__clang__)
 #warning Your compiler is too buggy; it is known to not compile ARM unwind support.
 #warning    Change compiler or disable ARM_UNWIND option.
 #endif
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index 9bc6db1c134..41c839167e8 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -1,10 +1,9 @@
-config ARCH_BCM
+menuconfig ARCH_BCM
 	bool "Broadcom SoC Support" if ARCH_MULTI_V6_V7
 	help
 	  This enables support for Broadcom ARM based SoC chips
 
-menu "Broadcom SoC Selection"
-	depends on ARCH_BCM
+if ARCH_BCM
 
 config ARCH_BCM_MOBILE
 	bool "Broadcom Mobile SoC Support" if ARCH_MULTI_V7
@@ -88,4 +87,4 @@ config ARCH_BCM_5301X
 	  different SoC or with the older BCM47XX and BCM53XX based
 	  network SoC using a MIPS CPU, they are supported by arch/mips/bcm47xx
 
-endmenu
+endif
diff --git a/arch/arm/mach-berlin/Kconfig b/arch/arm/mach-berlin/Kconfig
index 101e0f35673..2631cfc5ab0 100644
--- a/arch/arm/mach-berlin/Kconfig
+++ b/arch/arm/mach-berlin/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_BERLIN
+menuconfig ARCH_BERLIN
 	bool "Marvell Berlin SoCs" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_GIC
@@ -9,8 +9,6 @@ config ARCH_BERLIN
 
 if ARCH_BERLIN
 
-menu "Marvell Berlin SoC variants"
-
 config MACH_BERLIN_BG2
 	bool "Marvell Armada 1500 (BG2)"
 	select CACHE_L2X0
@@ -30,6 +28,4 @@ config MACH_BERLIN_BG2Q
 	select HAVE_ARM_TWD if SMP
 	select PINCTRL_BERLIN_BG2Q
 
-endmenu
-
 endif
diff --git a/arch/arm/mach-cns3xxx/Kconfig b/arch/arm/mach-cns3xxx/Kconfig
index 66838f42037..3c22a1990ec 100644
--- a/arch/arm/mach-cns3xxx/Kconfig
+++ b/arch/arm/mach-cns3xxx/Kconfig
@@ -1,12 +1,11 @@
-config ARCH_CNS3XXX
+menuconfig ARCH_CNS3XXX
 	bool "Cavium Networks CNS3XXX family" if ARCH_MULTI_V6
 	select ARM_GIC
 	select PCI_DOMAINS if PCI
 	help
 	  Support for Cavium Networks CNS3XXX platform.
 
-menu "CNS3XXX platform type"
-	depends on ARCH_CNS3XXX
+if ARCH_CNS3XXX
 
 config MACH_CNS3420VB
 	bool "Support for CNS3420 Validation Board"
@@ -17,4 +16,4 @@ config MACH_CNS3420VB
 	  This is a platform with an on-board ARM11 MPCore and has support
 	  for USB, USB-OTG, MMC/SD/SDIO, SATA, PCI-E, etc.
 
-endmenu
+endif
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index db18ef86659..584e8d4e289 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -39,7 +39,6 @@ config ARCH_DAVINCI_DA830
 config ARCH_DAVINCI_DA850
 	bool "DA850/OMAP-L138/AM18x based system"
 	select ARCH_DAVINCI_DA8XX
-	select ARCH_HAS_CPUFREQ
 	select CP_INTC
 
 config ARCH_DAVINCI_DA8XX
diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig
index d58995c9a95..8f9b66c4ac7 100644
--- a/arch/arm/mach-exynos/Kconfig
+++ b/arch/arm/mach-exynos/Kconfig
@@ -7,10 +7,9 @@
 
 # Configuration options for the EXYNOS4
 
-config ARCH_EXYNOS
+menuconfig ARCH_EXYNOS
 	bool "Samsung EXYNOS" if ARCH_MULTI_V7
 	select ARCH_HAS_BANDGAP
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
@@ -30,8 +29,6 @@ config ARCH_EXYNOS
 
 if ARCH_EXYNOS
 
-menu "SAMSUNG EXYNOS SoCs Support"
-
 config ARCH_EXYNOS3
 	bool "SAMSUNG EXYNOS3"
 	select ARM_CPU_SUSPEND if PM
@@ -118,8 +115,6 @@ config SOC_EXYNOS5800
 	default y
 	depends on SOC_EXYNOS5420
 
-endmenu
-
 config EXYNOS5420_MCPM
 	bool "Exynos5420 Multi-Cluster PM support"
 	depends on MCPM && SOC_EXYNOS5420
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index 16617bdb37a..1ee91763fa7 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -118,6 +118,7 @@ extern void __iomem *sysram_ns_base_addr;
 extern void __iomem *sysram_base_addr;
 void exynos_init_io(void);
 void exynos_restart(enum reboot_mode mode, const char *cmd);
+void exynos_sysram_init(void);
 void exynos_cpuidle_init(void);
 void exynos_cpufreq_init(void);
 void exynos_init_late(void);
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index 90aab4d75d0..66c9b9614f3 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -173,10 +173,8 @@ static struct platform_device exynos_cpuidle = {
 
 void __init exynos_cpuidle_init(void)
 {
-	if (soc_is_exynos5440())
-		return;
-
-	platform_device_register(&exynos_cpuidle);
+	if (soc_is_exynos4210() || soc_is_exynos5250())
+		platform_device_register(&exynos_cpuidle);
 }
 
 void __init exynos_cpufreq_init(void)
@@ -184,6 +182,28 @@ void __init exynos_cpufreq_init(void)
 	platform_device_register_simple("exynos-cpufreq", -1, NULL, 0);
 }
 
+void __iomem *sysram_base_addr;
+void __iomem *sysram_ns_base_addr;
+
+void __init exynos_sysram_init(void)
+{
+	struct device_node *node;
+
+	for_each_compatible_node(node, NULL, "samsung,exynos4210-sysram") {
+		if (!of_device_is_available(node))
+			continue;
+		sysram_base_addr = of_iomap(node, 0);
+		break;
+	}
+
+	for_each_compatible_node(node, NULL, "samsung,exynos4210-sysram-ns") {
+		if (!of_device_is_available(node))
+			continue;
+		sysram_ns_base_addr = of_iomap(node, 0);
+		break;
+	}
+}
+
 void __init exynos_init_late(void)
 {
 	if (of_machine_is_compatible("samsung,exynos5440"))
@@ -198,7 +218,7 @@ static int __init exynos_fdt_map_chipid(unsigned long node, const char *uname,
 					int depth, void *data)
 {
 	struct map_desc iodesc;
-	__be32 *reg;
+	const __be32 *reg;
 	int len;
 
 	if (!of_flat_dt_is_compatible(node, "samsung,exynos4210-chipid") &&
@@ -271,6 +291,13 @@ static void __init exynos_dt_machine_init(void)
 		}
 	}
 
+	/*
+	 * This is called from smp_prepare_cpus if we've built for SMP, but
+	 * we still need to set it up for PM and firmware ops if not.
+	 */
+	if (!IS_ENABLED(CONFIG_SMP))
+		exynos_sysram_init();
+
 	exynos_cpuidle_init();
 	exynos_cpufreq_init();
 
@@ -308,6 +335,15 @@ static void __init exynos_reserve(void)
 #endif
 }
 
+static void __init exynos_dt_fixup(void)
+{
+	/*
+	 * Some versions of uboot pass garbage entries in the memory node,
+	 * use the old CONFIG_ARM_NR_BANKS
+	 */
+	of_fdt_limit_memory(8);
+}
+
 DT_MACHINE_START(EXYNOS_DT, "SAMSUNG EXYNOS (Flattened Device Tree)")
 	/* Maintainer: Thomas Abraham <thomas.abraham@linaro.org> */
 	/* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
@@ -321,4 +357,5 @@ DT_MACHINE_START(EXYNOS_DT, "SAMSUNG EXYNOS (Flattened Device Tree)")
 	.dt_compat	= exynos_dt_compat,
 	.restart	= exynos_restart,
 	.reserve	= exynos_reserve,
+	.dt_fixup	= exynos_dt_fixup,
 MACHINE_END
diff --git a/arch/arm/mach-exynos/firmware.c b/arch/arm/mach-exynos/firmware.c
index eb91d2350f8..e8797bb7887 100644
--- a/arch/arm/mach-exynos/firmware.c
+++ b/arch/arm/mach-exynos/firmware.c
@@ -57,8 +57,13 @@ static int exynos_set_cpu_boot_addr(int cpu, unsigned long boot_addr)
 
 	boot_reg = sysram_ns_base_addr + 0x1c;
 
-	if (!soc_is_exynos4212() && !soc_is_exynos3250())
-		boot_reg += 4*cpu;
+	/*
+	 * Almost all Exynos-series of SoCs that run in secure mode don't need
+	 * additional offset for every CPU, with Exynos4412 being the only
+	 * exception.
+	 */
+	if (soc_is_exynos4412())
+		boot_reg += 4 * cpu;
 
 	__raw_writel(boot_addr, boot_reg);
 	return 0;
diff --git a/arch/arm/mach-exynos/hotplug.c b/arch/arm/mach-exynos/hotplug.c
index 69fa4839739..920a4baa53c 100644
--- a/arch/arm/mach-exynos/hotplug.c
+++ b/arch/arm/mach-exynos/hotplug.c
@@ -40,21 +40,17 @@ static inline void cpu_leave_lowpower(void)
 
 static inline void platform_do_lowpower(unsigned int cpu, int *spurious)
 {
+	u32 mpidr = cpu_logical_map(cpu);
+	u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+
 	for (;;) {
 
-		/* make cpu1 to be turned off at next WFI command */
-		if (cpu == 1)
-			exynos_cpu_power_down(cpu);
+		/* Turn the CPU off on next WFI instruction. */
+		exynos_cpu_power_down(core_id);
 
-		/*
-		 * here's the WFI
-		 */
-		asm(".word	0xe320f003\n"
-		    :
-		    :
-		    : "memory", "cc");
+		wfi();
 
-		if (pen_release == cpu_logical_map(cpu)) {
+		if (pen_release == core_id) {
 			/*
 			 * OK, proper wakeup, we're done
 			 */
diff --git a/arch/arm/mach-exynos/mcpm-exynos.c b/arch/arm/mach-exynos/mcpm-exynos.c
index 0498d0b887e..ace0ed61747 100644
--- a/arch/arm/mach-exynos/mcpm-exynos.c
+++ b/arch/arm/mach-exynos/mcpm-exynos.c
@@ -25,7 +25,6 @@
 
 #define EXYNOS5420_CPUS_PER_CLUSTER	4
 #define EXYNOS5420_NR_CLUSTERS		2
-#define MCPM_BOOT_ADDR_OFFSET		0x1c
 
 /*
  * The common v7_exit_coherency_flush API could not be used because of the
@@ -343,11 +342,13 @@ static int __init exynos_mcpm_init(void)
 	pr_info("Exynos MCPM support installed\n");
 
 	/*
-	 * Future entries into the kernel can now go
-	 * through the cluster entry vectors.
+	 * U-Boot SPL is hardcoded to jump to the start of ns_sram_base_addr
+	 * as part of secondary_cpu_start().  Let's redirect it to the
+	 * mcpm_entry_point().
 	 */
-	__raw_writel(virt_to_phys(mcpm_entry_point),
-			ns_sram_base_addr + MCPM_BOOT_ADDR_OFFSET);
+	__raw_writel(0xe59f0000, ns_sram_base_addr);     /* ldr r0, [pc, #0] */
+	__raw_writel(0xe12fff10, ns_sram_base_addr + 4); /* bx  r0 */
+	__raw_writel(virt_to_phys(mcpm_entry_point), ns_sram_base_addr + 8);
 
 	iounmap(ns_sram_base_addr);
 
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index ec02422e849..50b9aad5e27 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -32,28 +32,6 @@
 
 extern void exynos4_secondary_startup(void);
 
-void __iomem *sysram_base_addr;
-void __iomem *sysram_ns_base_addr;
-
-static void __init exynos_smp_prepare_sysram(void)
-{
-	struct device_node *node;
-
-	for_each_compatible_node(node, NULL, "samsung,exynos4210-sysram") {
-		if (!of_device_is_available(node))
-			continue;
-		sysram_base_addr = of_iomap(node, 0);
-		break;
-	}
-
-	for_each_compatible_node(node, NULL, "samsung,exynos4210-sysram-ns") {
-		if (!of_device_is_available(node))
-			continue;
-		sysram_ns_base_addr = of_iomap(node, 0);
-		break;
-	}
-}
-
 static inline void __iomem *cpu_boot_reg_base(void)
 {
 	if (soc_is_exynos4210() && samsung_rev() == EXYNOS4210_REV_1_1)
@@ -112,7 +90,8 @@ static void exynos_secondary_init(unsigned int cpu)
 static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
 	unsigned long timeout;
-	unsigned long phys_cpu = cpu_logical_map(cpu);
+	u32 mpidr = cpu_logical_map(cpu);
+	u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 	int ret = -ENOSYS;
 
 	/*
@@ -126,17 +105,18 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * the holding pen - release it, then wait for it to flag
 	 * that it has been released by resetting pen_release.
 	 *
-	 * Note that "pen_release" is the hardware CPU ID, whereas
+	 * Note that "pen_release" is the hardware CPU core ID, whereas
 	 * "cpu" is Linux's internal ID.
 	 */
-	write_pen_release(phys_cpu);
+	write_pen_release(core_id);
 
-	if (!exynos_cpu_power_state(cpu)) {
-		exynos_cpu_power_up(cpu);
+	if (!exynos_cpu_power_state(core_id)) {
+		exynos_cpu_power_up(core_id);
 		timeout = 10;
 
 		/* wait max 10 ms until cpu1 is on */
-		while (exynos_cpu_power_state(cpu) != S5P_CORE_LOCAL_PWR_EN) {
+		while (exynos_cpu_power_state(core_id)
+		       != S5P_CORE_LOCAL_PWR_EN) {
 			if (timeout-- == 0)
 				break;
 
@@ -167,20 +147,20 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 		 * Try to set boot address using firmware first
 		 * and fall back to boot register if it fails.
 		 */
-		ret = call_firmware_op(set_cpu_boot_addr, phys_cpu, boot_addr);
+		ret = call_firmware_op(set_cpu_boot_addr, core_id, boot_addr);
 		if (ret && ret != -ENOSYS)
 			goto fail;
 		if (ret == -ENOSYS) {
-			void __iomem *boot_reg = cpu_boot_reg(phys_cpu);
+			void __iomem *boot_reg = cpu_boot_reg(core_id);
 
 			if (IS_ERR(boot_reg)) {
 				ret = PTR_ERR(boot_reg);
 				goto fail;
 			}
-			__raw_writel(boot_addr, cpu_boot_reg(phys_cpu));
+			__raw_writel(boot_addr, cpu_boot_reg(core_id));
 		}
 
-		call_firmware_op(cpu_boot, phys_cpu);
+		call_firmware_op(cpu_boot, core_id);
 
 		arch_send_wakeup_ipi_mask(cpumask_of(cpu));
 
@@ -234,11 +214,11 @@ static void __init exynos_smp_prepare_cpus(unsigned int max_cpus)
 {
 	int i;
 
+	exynos_sysram_init();
+
 	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
 		scu_enable(scu_base_addr());
 
-	exynos_smp_prepare_sysram();
-
 	/*
 	 * Write the address of secondary startup into the
 	 * system-wide flags register. The boot monitor waits
@@ -249,22 +229,24 @@ static void __init exynos_smp_prepare_cpus(unsigned int max_cpus)
 	 * boot register if it fails.
 	 */
 	for (i = 1; i < max_cpus; ++i) {
-		unsigned long phys_cpu;
 		unsigned long boot_addr;
+		u32 mpidr;
+		u32 core_id;
 		int ret;
 
-		phys_cpu = cpu_logical_map(i);
+		mpidr = cpu_logical_map(i);
+		core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 		boot_addr = virt_to_phys(exynos4_secondary_startup);
 
-		ret = call_firmware_op(set_cpu_boot_addr, phys_cpu, boot_addr);
+		ret = call_firmware_op(set_cpu_boot_addr, core_id, boot_addr);
 		if (ret && ret != -ENOSYS)
 			break;
 		if (ret == -ENOSYS) {
-			void __iomem *boot_reg = cpu_boot_reg(phys_cpu);
+			void __iomem *boot_reg = cpu_boot_reg(core_id);
 
 			if (IS_ERR(boot_reg))
 				break;
-			__raw_writel(boot_addr, cpu_boot_reg(phys_cpu));
+			__raw_writel(boot_addr, cpu_boot_reg(core_id));
 		}
 	}
 }
diff --git a/arch/arm/mach-exynos/pm.c b/arch/arm/mach-exynos/pm.c
index 87c0d34c7fb..202ca73e49c 100644
--- a/arch/arm/mach-exynos/pm.c
+++ b/arch/arm/mach-exynos/pm.c
@@ -300,7 +300,7 @@ static int exynos_pm_suspend(void)
 	tmp = (S5P_USE_STANDBY_WFI0 | S5P_USE_STANDBY_WFE0);
 	__raw_writel(tmp, S5P_CENTRAL_SEQ_OPTION);
 
-	if (!soc_is_exynos5250())
+	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
 		exynos_cpu_save_register();
 
 	return 0;
@@ -334,7 +334,7 @@ static void exynos_pm_resume(void)
 	if (exynos_pm_central_resume())
 		goto early_wakeup;
 
-	if (!soc_is_exynos5250())
+	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
 		exynos_cpu_restore_register();
 
 	/* For release retention */
@@ -353,7 +353,7 @@ static void exynos_pm_resume(void)
 
 	s3c_pm_do_restore_core(exynos_core_save, ARRAY_SIZE(exynos_core_save));
 
-	if (!soc_is_exynos5250())
+	if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
 		scu_enable(S5P_VA_SCU);
 
 early_wakeup:
@@ -440,15 +440,18 @@ static int exynos_cpu_pm_notifier(struct notifier_block *self,
 	case CPU_PM_ENTER:
 		if (cpu == 0) {
 			exynos_pm_central_suspend();
-			exynos_cpu_save_register();
+			if (read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9)
+				exynos_cpu_save_register();
 		}
 		break;
 
 	case CPU_PM_EXIT:
 		if (cpu == 0) {
-			if (!soc_is_exynos5250())
+			if (read_cpuid_part_number() ==
+					ARM_CPU_PART_CORTEX_A9) {
 				scu_enable(S5P_VA_SCU);
-			exynos_cpu_restore_register();
+				exynos_cpu_restore_register();
+			}
 			exynos_pm_central_resume();
 		}
 		break;
diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c
index fe6570ebbdd..797cb134bff 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/arch/arm/mach-exynos/pm_domains.c
@@ -17,6 +17,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/pm_domain.h>
+#include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
@@ -24,6 +25,8 @@
 
 #include "regs-pmu.h"
 
+#define MAX_CLK_PER_DOMAIN	4
+
 /*
  * Exynos specific wrapper around the generic power domain
  */
@@ -32,6 +35,9 @@ struct exynos_pm_domain {
 	char const *name;
 	bool is_off;
 	struct generic_pm_domain pd;
+	struct clk *oscclk;
+	struct clk *clk[MAX_CLK_PER_DOMAIN];
+	struct clk *pclk[MAX_CLK_PER_DOMAIN];
 };
 
 static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
@@ -44,6 +50,19 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
 	pd = container_of(domain, struct exynos_pm_domain, pd);
 	base = pd->base;
 
+	/* Set oscclk before powering off a domain*/
+	if (!power_on) {
+		int i;
+
+		for (i = 0; i < MAX_CLK_PER_DOMAIN; i++) {
+			if (IS_ERR(pd->clk[i]))
+				break;
+			if (clk_set_parent(pd->clk[i], pd->oscclk))
+				pr_err("%s: error setting oscclk as parent to clock %d\n",
+						pd->name, i);
+		}
+	}
+
 	pwr = power_on ? S5P_INT_LOCAL_PWR_EN : 0;
 	__raw_writel(pwr, base);
 
@@ -60,6 +79,20 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on)
 		cpu_relax();
 		usleep_range(80, 100);
 	}
+
+	/* Restore clocks after powering on a domain*/
+	if (power_on) {
+		int i;
+
+		for (i = 0; i < MAX_CLK_PER_DOMAIN; i++) {
+			if (IS_ERR(pd->clk[i]))
+				break;
+			if (clk_set_parent(pd->clk[i], pd->pclk[i]))
+				pr_err("%s: error setting parent to clock%d\n",
+						pd->name, i);
+		}
+	}
+
 	return 0;
 }
 
@@ -152,9 +185,11 @@ static __init int exynos4_pm_init_power_domain(void)
 
 	for_each_compatible_node(np, NULL, "samsung,exynos4210-pd") {
 		struct exynos_pm_domain *pd;
-		int on;
+		int on, i;
+		struct device *dev;
 
 		pdev = of_find_device_by_node(np);
+		dev = &pdev->dev;
 
 		pd = kzalloc(sizeof(*pd), GFP_KERNEL);
 		if (!pd) {
@@ -170,6 +205,30 @@ static __init int exynos4_pm_init_power_domain(void)
 		pd->pd.power_on = exynos_pd_power_on;
 		pd->pd.of_node = np;
 
+		pd->oscclk = clk_get(dev, "oscclk");
+		if (IS_ERR(pd->oscclk))
+			goto no_clk;
+
+		for (i = 0; i < MAX_CLK_PER_DOMAIN; i++) {
+			char clk_name[8];
+
+			snprintf(clk_name, sizeof(clk_name), "clk%d", i);
+			pd->clk[i] = clk_get(dev, clk_name);
+			if (IS_ERR(pd->clk[i]))
+				break;
+			snprintf(clk_name, sizeof(clk_name), "pclk%d", i);
+			pd->pclk[i] = clk_get(dev, clk_name);
+			if (IS_ERR(pd->pclk[i])) {
+				clk_put(pd->clk[i]);
+				pd->clk[i] = ERR_PTR(-EINVAL);
+				break;
+			}
+		}
+
+		if (IS_ERR(pd->clk[0]))
+			clk_put(pd->oscclk);
+
+no_clk:
 		platform_set_drvdata(pdev, pd);
 
 		on = __raw_readl(pd->base + 0x4) & S5P_INT_LOCAL_PWR_EN;
diff --git a/arch/arm/mach-highbank/Kconfig b/arch/arm/mach-highbank/Kconfig
index 830b76e7025..a5960e2ac09 100644
--- a/arch/arm/mach-highbank/Kconfig
+++ b/arch/arm/mach-highbank/Kconfig
@@ -1,7 +1,6 @@
 config ARCH_HIGHBANK
 	bool "Calxeda ECX-1000/2000 (Highbank/Midway)" if ARCH_MULTI_V7
 	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_HAS_OPP
 	select ARCH_SUPPORTS_BIG_ENDIAN
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 8d42eab76d5..4b5185748f7 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -1,6 +1,5 @@
-config ARCH_MXC
+menuconfig ARCH_MXC
 	bool "Freescale i.MX family" if ARCH_MULTI_V4_V5 || ARCH_MULTI_V6_V7
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_CPU_SUSPEND if PM
@@ -13,8 +12,7 @@ config ARCH_MXC
 	help
 	  Support for Freescale MXC/iMX-based family of processors
 
-menu "Freescale i.MX support"
-	depends on ARCH_MXC
+if ARCH_MXC
 
 config MXC_TZIC
 	bool
@@ -99,7 +97,6 @@ config SOC_IMX25
 
 config SOC_IMX27
 	bool
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select CPU_ARM926T
 	select IMX_HAVE_IOMUX_V1
@@ -124,7 +121,6 @@ config SOC_IMX35
 
 config SOC_IMX5
 	bool
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select ARCH_MXC_IOMUX_V3
 	select MXC_TZIC
@@ -738,9 +734,9 @@ config SOC_IMX6
 	select HAVE_IMX_MMDC
 	select HAVE_IMX_SRC
 	select MFD_SYSCON
-	select PL310_ERRATA_588369 if CACHE_PL310
-	select PL310_ERRATA_727915 if CACHE_PL310
-	select PL310_ERRATA_769419 if CACHE_PL310
+	select PL310_ERRATA_588369 if CACHE_L2X0
+	select PL310_ERRATA_727915 if CACHE_L2X0
+	select PL310_ERRATA_769419 if CACHE_L2X0
 
 config SOC_IMX6Q
 	bool "i.MX6 Quad/DualLite support"
@@ -775,9 +771,9 @@ config SOC_VF610
 	select ARM_GIC
 	select PINCTRL_VF610
 	select VF_PIT_TIMER
-	select PL310_ERRATA_588369 if CACHE_PL310
-	select PL310_ERRATA_727915 if CACHE_PL310
-	select PL310_ERRATA_769419 if CACHE_PL310
+	select PL310_ERRATA_588369 if CACHE_L2X0
+	select PL310_ERRATA_727915 if CACHE_L2X0
+	select PL310_ERRATA_769419 if CACHE_L2X0
 
 	help
 	  This enable support for Freescale Vybrid VF610 processor.
@@ -786,4 +782,4 @@ endif
 
 source "arch/arm/mach-imx/devices/Kconfig"
 
-endmenu
+endif
diff --git a/arch/arm/mach-imx/clk-gate2.c b/arch/arm/mach-imx/clk-gate2.c
index 4ba587da89d..84acdfd1d71 100644
--- a/arch/arm/mach-imx/clk-gate2.c
+++ b/arch/arm/mach-imx/clk-gate2.c
@@ -67,8 +67,12 @@ static void clk_gate2_disable(struct clk_hw *hw)
 
 	spin_lock_irqsave(gate->lock, flags);
 
-	if (gate->share_count && --(*gate->share_count) > 0)
-		goto out;
+	if (gate->share_count) {
+		if (WARN_ON(*gate->share_count == 0))
+			goto out;
+		else if (--(*gate->share_count) > 0)
+			goto out;
+	}
 
 	reg = readl(gate->reg);
 	reg &= ~(3 << gate->bit_idx);
@@ -78,19 +82,26 @@ out:
 	spin_unlock_irqrestore(gate->lock, flags);
 }
 
-static int clk_gate2_is_enabled(struct clk_hw *hw)
+static int clk_gate2_reg_is_enabled(void __iomem *reg, u8 bit_idx)
 {
-	u32 reg;
-	struct clk_gate2 *gate = to_clk_gate2(hw);
+	u32 val = readl(reg);
 
-	reg = readl(gate->reg);
-
-	if (((reg >> gate->bit_idx) & 1) == 1)
+	if (((val >> bit_idx) & 1) == 1)
 		return 1;
 
 	return 0;
 }
 
+static int clk_gate2_is_enabled(struct clk_hw *hw)
+{
+	struct clk_gate2 *gate = to_clk_gate2(hw);
+
+	if (gate->share_count)
+		return !!(*gate->share_count);
+	else
+		return clk_gate2_reg_is_enabled(gate->reg, gate->bit_idx);
+}
+
 static struct clk_ops clk_gate2_ops = {
 	.enable = clk_gate2_enable,
 	.disable = clk_gate2_disable,
@@ -116,6 +127,10 @@ struct clk *clk_register_gate2(struct device *dev, const char *name,
 	gate->bit_idx = bit_idx;
 	gate->flags = clk_gate2_flags;
 	gate->lock = lock;
+
+	/* Initialize share_count per hardware state */
+	if (share_count)
+		*share_count = clk_gate2_reg_is_enabled(reg, bit_idx) ? 1 : 0;
 	gate->share_count = share_count;
 
 	init.name = name;
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 8e795dea02e..8556c787e59 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -70,7 +70,7 @@ static const char *cko_sels[] = { "cko1", "cko2", };
 static const char *lvds_sels[] = {
 	"dummy", "dummy", "dummy", "dummy", "dummy", "dummy",
 	"pll4_audio", "pll5_video", "pll8_mlb", "enet_ref",
-	"pcie_ref", "sata_ref",
+	"pcie_ref_125m", "sata_ref_100m",
 };
 
 enum mx6q_clks {
@@ -491,7 +491,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 
 	/* All existing boards with PCIe use LVDS1 */
 	if (IS_ENABLED(CONFIG_PCI_IMX6))
-		clk_set_parent(clk[lvds1_sel], clk[sata_ref]);
+		clk_set_parent(clk[lvds1_sel], clk[sata_ref_100m]);
 
 	/* Set initial power mode */
 	imx6q_set_lpm(WAIT_CLOCKED);
diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c
index 21cf06cebad..5408ca70c8d 100644
--- a/arch/arm/mach-imx/clk-imx6sl.c
+++ b/arch/arm/mach-imx/clk-imx6sl.c
@@ -312,6 +312,7 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SL_CLK_ECSPI2]       = imx_clk_gate2("ecspi2",       "ecspi_root",        base + 0x6c, 2);
 	clks[IMX6SL_CLK_ECSPI3]       = imx_clk_gate2("ecspi3",       "ecspi_root",        base + 0x6c, 4);
 	clks[IMX6SL_CLK_ECSPI4]       = imx_clk_gate2("ecspi4",       "ecspi_root",        base + 0x6c, 6);
+	clks[IMX6SL_CLK_ENET]         = imx_clk_gate2("enet",         "ipg",               base + 0x6c, 10);
 	clks[IMX6SL_CLK_EPIT1]        = imx_clk_gate2("epit1",        "perclk",            base + 0x6c, 12);
 	clks[IMX6SL_CLK_EPIT2]        = imx_clk_gate2("epit2",        "perclk",            base + 0x6c, 14);
 	clks[IMX6SL_CLK_EXTERN_AUDIO] = imx_clk_gate2("extern_audio", "extern_audio_podf", base + 0x6c, 16);
diff --git a/arch/arm/mach-integrator/Kconfig b/arch/arm/mach-integrator/Kconfig
index ba43321001d..64f8e2564a3 100644
--- a/arch/arm/mach-integrator/Kconfig
+++ b/arch/arm/mach-integrator/Kconfig
@@ -28,7 +28,7 @@ config ARCH_CINTEGRATOR
 	bool
 
 config INTEGRATOR_IMPD1
-	tristate "Include support for Integrator/IM-PD1"
+	bool "Include support for Integrator/IM-PD1"
 	depends on ARCH_INTEGRATOR_AP
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_VIC
diff --git a/arch/arm/mach-integrator/impd1.c b/arch/arm/mach-integrator/impd1.c
index 0e870ea818c..3ce880729cf 100644
--- a/arch/arm/mach-integrator/impd1.c
+++ b/arch/arm/mach-integrator/impd1.c
@@ -308,7 +308,12 @@ static struct impd1_device impd1_devs[] = {
  */
 #define IMPD1_VALID_IRQS 0x00000bffU
 
-static int __init impd1_probe(struct lm_device *dev)
+/*
+ * As this module is bool, it is OK to have this as __init_refok() - no
+ * probe calls will be done after the initial system bootup, as devices
+ * are discovered as part of the machine startup.
+ */
+static int __init_refok impd1_probe(struct lm_device *dev)
 {
 	struct impd1_module *impd1;
 	int irq_base;
@@ -397,6 +402,11 @@ static void impd1_remove(struct lm_device *dev)
 static struct lm_driver impd1_driver = {
 	.drv = {
 		.name	= "impd1",
+		/*
+		 * As we're dropping the probe() function, suppress driver
+		 * binding from sysfs.
+		 */
+		.suppress_bind_attrs = true,
 	},
 	.probe		= impd1_probe,
 	.remove		= impd1_remove,
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index dd0cc677d59..660ca6feff4 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -480,25 +480,18 @@ static const struct of_device_id ebi_match[] = {
 static void __init ap_init_of(void)
 {
 	unsigned long sc_dec;
-	struct device_node *root;
 	struct device_node *syscon;
 	struct device_node *ebi;
 	struct device *parent;
 	struct soc_device *soc_dev;
 	struct soc_device_attribute *soc_dev_attr;
 	u32 ap_sc_id;
-	int err;
 	int i;
 
-	/* Here we create an SoC device for the root node */
-	root = of_find_node_by_path("/");
-	if (!root)
-		return;
-
-	syscon = of_find_matching_node(root, ap_syscon_match);
+	syscon = of_find_matching_node(NULL, ap_syscon_match);
 	if (!syscon)
 		return;
-	ebi = of_find_matching_node(root, ebi_match);
+	ebi = of_find_matching_node(NULL, ebi_match);
 	if (!ebi)
 		return;
 
@@ -509,19 +502,17 @@ static void __init ap_init_of(void)
 	if (!ebi_base)
 		return;
 
+	of_platform_populate(NULL, of_default_bus_match_table,
+			ap_auxdata_lookup, NULL);
+
 	ap_sc_id = readl(ap_syscon_base);
 
 	soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL);
 	if (!soc_dev_attr)
 		return;
 
-	err = of_property_read_string(root, "compatible",
-				      &soc_dev_attr->soc_id);
-	if (err)
-		return;
-	err = of_property_read_string(root, "model", &soc_dev_attr->machine);
-	if (err)
-		return;
+	soc_dev_attr->soc_id = "XVC";
+	soc_dev_attr->machine = "Integrator/AP";
 	soc_dev_attr->family = "Integrator";
 	soc_dev_attr->revision = kasprintf(GFP_KERNEL, "%c",
 					   'A' + (ap_sc_id & 0x0f));
@@ -536,9 +527,6 @@ static void __init ap_init_of(void)
 	parent = soc_device_to_device(soc_dev);
 	integrator_init_sysfs(parent, ap_sc_id);
 
-	of_platform_populate(root, of_default_bus_match_table,
-			ap_auxdata_lookup, parent);
-
 	sc_dec = readl(ap_syscon_base + INTEGRATOR_SC_DEC_OFFSET);
 	for (i = 0; i < 4; i++) {
 		struct lm_device *lmdev;
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index a938242b0c9..0e57f8f820a 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -279,20 +279,13 @@ static const struct of_device_id intcp_syscon_match[] = {
 
 static void __init intcp_init_of(void)
 {
-	struct device_node *root;
 	struct device_node *cpcon;
 	struct device *parent;
 	struct soc_device *soc_dev;
 	struct soc_device_attribute *soc_dev_attr;
 	u32 intcp_sc_id;
-	int err;
 
-	/* Here we create an SoC device for the root node */
-	root = of_find_node_by_path("/");
-	if (!root)
-		return;
-
-	cpcon = of_find_matching_node(root, intcp_syscon_match);
+	cpcon = of_find_matching_node(NULL, intcp_syscon_match);
 	if (!cpcon)
 		return;
 
@@ -300,19 +293,17 @@ static void __init intcp_init_of(void)
 	if (!intcp_con_base)
 		return;
 
+	of_platform_populate(NULL, of_default_bus_match_table,
+			     intcp_auxdata_lookup, NULL);
+
 	intcp_sc_id = readl(intcp_con_base);
 
 	soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL);
 	if (!soc_dev_attr)
 		return;
 
-	err = of_property_read_string(root, "compatible",
-				      &soc_dev_attr->soc_id);
-	if (err)
-		return;
-	err = of_property_read_string(root, "model", &soc_dev_attr->machine);
-	if (err)
-		return;
+	soc_dev_attr->soc_id = "XCV";
+	soc_dev_attr->machine = "Integrator/CP";
 	soc_dev_attr->family = "Integrator";
 	soc_dev_attr->revision = kasprintf(GFP_KERNEL, "%c",
 					   'A' + (intcp_sc_id & 0x0f));
@@ -326,8 +317,6 @@ static void __init intcp_init_of(void)
 
 	parent = soc_device_to_device(soc_dev);
 	integrator_init_sysfs(parent, intcp_sc_id);
-	of_platform_populate(root, of_default_bus_match_table,
-			intcp_auxdata_lookup, parent);
 }
 
 static const char * intcp_dt_board_compat[] = {
diff --git a/arch/arm/mach-keystone/Kconfig b/arch/arm/mach-keystone/Kconfig
index f50bc936cb8..98a156afaa9 100644
--- a/arch/arm/mach-keystone/Kconfig
+++ b/arch/arm/mach-keystone/Kconfig
@@ -1,6 +1,7 @@
 config ARCH_KEYSTONE
 	bool "Texas Instruments Keystone Devices"
 	depends on ARCH_MULTI_V7
+	depends on ARM_PATCH_PHYS_VIRT
 	select ARM_GIC
 	select HAVE_ARM_ARCH_TIMER
 	select CLKSRC_MMIO
diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c
index e0b9e1b9cf3..7f352de2609 100644
--- a/arch/arm/mach-keystone/keystone.c
+++ b/arch/arm/mach-keystone/keystone.c
@@ -14,60 +14,100 @@
 #include <linux/init.h>
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
 #include <asm/smp_plat.h>
+#include <asm/memory.h>
 
-#include "keystone.h"
+#include "memory.h"
 
-#define PLL_RESET_WRITE_KEY_MASK		0xffff0000
-#define PLL_RESET_WRITE_KEY			0x5a69
-#define PLL_RESET				BIT(16)
+#include "keystone.h"
 
-static void __iomem *keystone_rstctrl;
+static struct notifier_block platform_nb;
+static unsigned long keystone_dma_pfn_offset __read_mostly;
 
-static void __init keystone_init(void)
+static int keystone_platform_notifier(struct notifier_block *nb,
+				      unsigned long event, void *data)
 {
-	struct device_node *node;
+	struct device *dev = data;
 
-	node = of_find_compatible_node(NULL, NULL, "ti,keystone-reset");
-	if (WARN_ON(!node))
-		pr_warn("ti,keystone-reset node undefined\n");
+	if (event != BUS_NOTIFY_ADD_DEVICE)
+		return NOTIFY_DONE;
 
-	keystone_rstctrl = of_iomap(node, 0);
-	if (WARN_ON(!keystone_rstctrl))
-		pr_warn("ti,keystone-reset iomap error\n");
+	if (!dev)
+		return NOTIFY_BAD;
 
+	if (!dev->of_node) {
+		dev->dma_pfn_offset = keystone_dma_pfn_offset;
+		dev_err(dev, "set dma_pfn_offset%08lx\n",
+			dev->dma_pfn_offset);
+	}
+	return NOTIFY_OK;
+}
+
+static void __init keystone_init(void)
+{
 	keystone_pm_runtime_init();
+	if (platform_nb.notifier_call)
+		bus_register_notifier(&platform_bus_type, &platform_nb);
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
-static const char *keystone_match[] __initconst = {
-	"ti,keystone",
-	NULL,
-};
+static phys_addr_t keystone_virt_to_idmap(unsigned long x)
+{
+	return (phys_addr_t)(x) - CONFIG_PAGE_OFFSET + KEYSTONE_LOW_PHYS_START;
+}
 
-void keystone_restart(enum reboot_mode mode, const char *cmd)
+static void __init keystone_init_meminfo(void)
 {
-	u32 val;
+	bool lpae = IS_ENABLED(CONFIG_ARM_LPAE);
+	bool pvpatch = IS_ENABLED(CONFIG_ARM_PATCH_PHYS_VIRT);
+	phys_addr_t offset = PHYS_OFFSET - KEYSTONE_LOW_PHYS_START;
+	phys_addr_t mem_start, mem_end;
+
+	mem_start = memblock_start_of_DRAM();
+	mem_end = memblock_end_of_DRAM();
+
+	/* nothing to do if we are running out of the <32-bit space */
+	if (mem_start >= KEYSTONE_LOW_PHYS_START &&
+	    mem_end   <= KEYSTONE_LOW_PHYS_END)
+		return;
+
+	if (!lpae || !pvpatch) {
+		pr_crit("Enable %s%s%s to run outside 32-bit space\n",
+		      !lpae ? __stringify(CONFIG_ARM_LPAE) : "",
+		      (!lpae && !pvpatch) ? " and " : "",
+		      !pvpatch ? __stringify(CONFIG_ARM_PATCH_PHYS_VIRT) : "");
+	}
+
+	if (mem_start < KEYSTONE_HIGH_PHYS_START ||
+	    mem_end   > KEYSTONE_HIGH_PHYS_END) {
+		pr_crit("Invalid address space for memory (%08llx-%08llx)\n",
+		      (u64)mem_start, (u64)mem_end);
+	}
 
-	BUG_ON(!keystone_rstctrl);
+	offset += KEYSTONE_HIGH_PHYS_START;
+	__pv_phys_pfn_offset = PFN_DOWN(offset);
+	__pv_offset = (offset - PAGE_OFFSET);
 
-	/* Enable write access to RSTCTRL */
-	val = readl(keystone_rstctrl);
-	val &= PLL_RESET_WRITE_KEY_MASK;
-	val |= PLL_RESET_WRITE_KEY;
-	writel(val, keystone_rstctrl);
+	/* Populate the arch idmap hook */
+	arch_virt_to_idmap = keystone_virt_to_idmap;
+	platform_nb.notifier_call = keystone_platform_notifier;
+	keystone_dma_pfn_offset = PFN_DOWN(KEYSTONE_HIGH_PHYS_START -
+						KEYSTONE_LOW_PHYS_START);
 
-	/* Reset the SOC */
-	val = readl(keystone_rstctrl);
-	val &= ~PLL_RESET;
-	writel(val, keystone_rstctrl);
+	pr_info("Switching to high address space at 0x%llx\n", (u64)offset);
 }
 
+static const char *keystone_match[] __initconst = {
+	"ti,keystone",
+	NULL,
+};
+
 DT_MACHINE_START(KEYSTONE, "Keystone")
 #if defined(CONFIG_ZONE_DMA) && defined(CONFIG_ARM_LPAE)
 	.dma_zone_size	= SZ_2G,
@@ -75,5 +115,5 @@ DT_MACHINE_START(KEYSTONE, "Keystone")
 	.smp		= smp_ops(keystone_smp_ops),
 	.init_machine	= keystone_init,
 	.dt_compat	= keystone_match,
-	.restart	= keystone_restart,
+	.init_meminfo   = keystone_init_meminfo,
 MACHINE_END
diff --git a/arch/arm/mach-keystone/memory.h b/arch/arm/mach-keystone/memory.h
new file mode 100644
index 00000000000..b854fb18eef
--- /dev/null
+++ b/arch/arm/mach-keystone/memory.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright 2014 Texas Instruments, Inc.
+ *	Santosh Shilimkar <santosh.shilimkar@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+#ifndef __MEMORY_H
+#define __MEMORY_H
+
+#define MAX_PHYSMEM_BITS	36
+#define SECTION_SIZE_BITS	34
+
+#define KEYSTONE_LOW_PHYS_START		0x80000000ULL
+#define KEYSTONE_LOW_PHYS_SIZE		0x80000000ULL /* 2G */
+#define KEYSTONE_LOW_PHYS_END		(KEYSTONE_LOW_PHYS_START + \
+					 KEYSTONE_LOW_PHYS_SIZE - 1)
+
+#define KEYSTONE_HIGH_PHYS_START	0x800000000ULL
+#define KEYSTONE_HIGH_PHYS_SIZE		0x400000000ULL	/* 16G */
+#define KEYSTONE_HIGH_PHYS_END		(KEYSTONE_HIGH_PHYS_START + \
+					 KEYSTONE_HIGH_PHYS_SIZE - 1)
+#endif /* __MEMORY_H */
diff --git a/arch/arm/mach-keystone/platsmp.c b/arch/arm/mach-keystone/platsmp.c
index 5cf0683577e..5f46a7cf907 100644
--- a/arch/arm/mach-keystone/platsmp.c
+++ b/arch/arm/mach-keystone/platsmp.c
@@ -17,13 +17,16 @@
 #include <linux/io.h>
 
 #include <asm/smp_plat.h>
+#include <asm/prom.h>
+#include <asm/tlbflush.h>
+#include <asm/pgtable.h>
 
 #include "keystone.h"
 
 static int keystone_smp_boot_secondary(unsigned int cpu,
 						struct task_struct *idle)
 {
-	unsigned long start = virt_to_phys(&secondary_startup);
+	unsigned long start = virt_to_idmap(&secondary_startup);
 	int error;
 
 	pr_debug("keystone-smp: booting cpu %d, vector %08lx\n",
@@ -36,6 +39,19 @@ static int keystone_smp_boot_secondary(unsigned int cpu,
 	return error;
 }
 
+#ifdef CONFIG_ARM_LPAE
+static void __cpuinit keystone_smp_secondary_initmem(unsigned int cpu)
+{
+	pgd_t *pgd0 = pgd_offset_k(0);
+	cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET);
+	local_flush_tlb_all();
+}
+#else
+static inline void __cpuinit keystone_smp_secondary_initmem(unsigned int cpu)
+{}
+#endif
+
 struct smp_operations keystone_smp_ops __initdata = {
 	.smp_boot_secondary	= keystone_smp_boot_secondary,
+	.smp_secondary_init     = keystone_smp_secondary_initmem,
 };
diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig
index 82a4ba8578a..f49328c39be 100644
--- a/arch/arm/mach-moxart/Kconfig
+++ b/arch/arm/mach-moxart/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_MOXART
+menuconfig ARCH_MOXART
 	bool "MOXA ART SoC" if ARCH_MULTI_V4
 	select CPU_FA526
 	select ARM_DMA_MEM_BUFFERABLE
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index 6090b9eb00c..b9bc599a5fd 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_MVEBU
+menuconfig ARCH_MVEBU
 	bool "Marvell Engineering Business Unit (MVEBU) SoCs" if (ARCH_MULTI_V7 || ARCH_MULTI_V5)
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select CLKSRC_MMIO
@@ -10,15 +10,15 @@ config ARCH_MVEBU
 	select ZONE_DMA if ARM_LPAE
 	select ARCH_REQUIRE_GPIOLIB
 	select PCI_QUIRKS if PCI
+	select OF_ADDRESS_PCI
 
 if ARCH_MVEBU
 
-menu "Marvell EBU SoC variants"
-
 config MACH_MVEBU_V7
 	bool
 	select ARMADA_370_XP_TIMER
 	select CACHE_L2X0
+	select ARM_CPU_SUSPEND
 
 config MACH_ARMADA_370
 	bool "Marvell Armada 370 boards" if ARCH_MULTI_V7
@@ -84,7 +84,6 @@ config MACH_DOVE
 
 config MACH_KIRKWOOD
 	bool "Marvell Kirkwood boards" if ARCH_MULTI_V5
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select CPU_FEROCEON
 	select KIRKWOOD_CLK
@@ -97,6 +96,4 @@ config MACH_KIRKWOOD
 	  Say 'Y' here if you want your kernel to support boards based
 	  on the Marvell Kirkwood device tree.
 
-endmenu
-
 endif
diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile
index 2ecb828e4a8..1636cdbef01 100644
--- a/arch/arm/mach-mvebu/Makefile
+++ b/arch/arm/mach-mvebu/Makefile
@@ -7,7 +7,7 @@ CFLAGS_pmsu.o			:= -march=armv7-a
 obj-y				 += system-controller.o mvebu-soc-id.o
 
 ifeq ($(CONFIG_MACH_MVEBU_V7),y)
-obj-y				 += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o
+obj-y				 += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o pmsu_ll.o
 obj-$(CONFIG_SMP)		 += platsmp.o headsmp.o platsmp-a9.o headsmp-a9.o
 obj-$(CONFIG_HOTPLUG_CPU)	 += hotplug.o
 endif
diff --git a/arch/arm/mach-mvebu/board-v7.c b/arch/arm/mach-mvebu/board-v7.c
index 8bb742fdf5c..b2524d689f2 100644
--- a/arch/arm/mach-mvebu/board-v7.c
+++ b/arch/arm/mach-mvebu/board-v7.c
@@ -23,6 +23,7 @@
 #include <linux/mbus.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
+#include <linux/irqchip.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -71,17 +72,23 @@ static int armada_375_external_abort_wa(unsigned long addr, unsigned int fsr,
 	return 1;
 }
 
-static void __init mvebu_timer_and_clk_init(void)
+static void __init mvebu_init_irq(void)
 {
-	of_clk_init(NULL);
-	clocksource_of_init();
+	irqchip_init();
 	mvebu_scu_enable();
 	coherency_init();
 	BUG_ON(mvebu_mbus_dt_init(coherency_available()));
+}
+
+static void __init external_abort_quirk(void)
+{
+	u32 dev, rev;
 
-	if (of_machine_is_compatible("marvell,armada375"))
-		hook_fault_code(16 + 6, armada_375_external_abort_wa, SIGBUS, 0,
-				"imprecise external abort");
+	if (mvebu_get_soc_id(&dev, &rev) == 0 && rev > ARMADA_375_Z1_REV)
+		return;
+
+	hook_fault_code(16 + 6, armada_375_external_abort_wa, SIGBUS, 0,
+			"imprecise external abort");
 }
 
 static void __init i2c_quirk(void)
@@ -169,8 +176,10 @@ static void __init mvebu_dt_init(void)
 {
 	if (of_machine_is_compatible("plathome,openblocks-ax3-4"))
 		i2c_quirk();
-	if (of_machine_is_compatible("marvell,a375-db"))
+	if (of_machine_is_compatible("marvell,a375-db")) {
+		external_abort_quirk();
 		thermal_quirk();
+	}
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
@@ -185,7 +194,7 @@ DT_MACHINE_START(ARMADA_370_XP_DT, "Marvell Armada 370/XP (Device Tree)")
 	.l2c_aux_mask	= ~0,
 	.smp		= smp_ops(armada_xp_smp_ops),
 	.init_machine	= mvebu_dt_init,
-	.init_time	= mvebu_timer_and_clk_init,
+	.init_irq       = mvebu_init_irq,
 	.restart	= mvebu_restart,
 	.dt_compat	= armada_370_xp_dt_compat,
 MACHINE_END
@@ -198,7 +207,7 @@ static const char * const armada_375_dt_compat[] = {
 DT_MACHINE_START(ARMADA_375_DT, "Marvell Armada 375 (Device Tree)")
 	.l2c_aux_val	= 0,
 	.l2c_aux_mask	= ~0,
-	.init_time	= mvebu_timer_and_clk_init,
+	.init_irq       = mvebu_init_irq,
 	.init_machine	= mvebu_dt_init,
 	.restart	= mvebu_restart,
 	.dt_compat	= armada_375_dt_compat,
@@ -213,7 +222,7 @@ static const char * const armada_38x_dt_compat[] = {
 DT_MACHINE_START(ARMADA_38X_DT, "Marvell Armada 380/385 (Device Tree)")
 	.l2c_aux_val	= 0,
 	.l2c_aux_mask	= ~0,
-	.init_time	= mvebu_timer_and_clk_init,
+	.init_irq       = mvebu_init_irq,
 	.restart	= mvebu_restart,
 	.dt_compat	= armada_38x_dt_compat,
 MACHINE_END
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 477202fd39c..2bdc3233abe 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -292,6 +292,10 @@ static struct notifier_block mvebu_hwcc_nb = {
 	.notifier_call = mvebu_hwcc_notifier,
 };
 
+static struct notifier_block mvebu_hwcc_pci_nb = {
+	.notifier_call = mvebu_hwcc_notifier,
+};
+
 static void __init armada_370_coherency_init(struct device_node *np)
 {
 	struct resource res;
@@ -427,7 +431,7 @@ static int __init coherency_pci_init(void)
 {
 	if (coherency_available())
 		bus_register_notifier(&pci_bus_type,
-				       &mvebu_hwcc_nb);
+				       &mvebu_hwcc_pci_nb);
 	return 0;
 }
 
diff --git a/arch/arm/mach-mvebu/headsmp-a9.S b/arch/arm/mach-mvebu/headsmp-a9.S
index 5925366bc03..da5bb292b91 100644
--- a/arch/arm/mach-mvebu/headsmp-a9.S
+++ b/arch/arm/mach-mvebu/headsmp-a9.S
@@ -15,6 +15,8 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 
+#include <asm/assembler.h>
+
 	__CPUINIT
 #define CPU_RESUME_ADDR_REG 0xf10182d4
 
@@ -22,13 +24,18 @@
 .global armada_375_smp_cpu1_enable_code_end
 
 armada_375_smp_cpu1_enable_code_start:
-	ldr     r0, [pc, #4]
+ARM_BE8(setend	be)
+	adr     r0, 1f
+	ldr	r0, [r0]
 	ldr     r1, [r0]
+ARM_BE8(rev	r1, r1)
 	mov     pc, r1
+1:
 	.word   CPU_RESUME_ADDR_REG
 armada_375_smp_cpu1_enable_code_end:
 
 ENTRY(mvebu_cortex_a9_secondary_startup)
+ARM_BE8(setend	be)
 	bl      v7_invalidate_l1
 	b	secondary_startup
 ENDPROC(mvebu_cortex_a9_secondary_startup)
diff --git a/arch/arm/mach-mvebu/pmsu.c b/arch/arm/mach-mvebu/pmsu.c
index 53a55c8520b..25aa8237d66 100644
--- a/arch/arm/mach-mvebu/pmsu.c
+++ b/arch/arm/mach-mvebu/pmsu.c
@@ -66,6 +66,8 @@ static void __iomem *pmsu_mp_base;
 extern void ll_disable_coherency(void);
 extern void ll_enable_coherency(void);
 
+extern void armada_370_xp_cpu_resume(void);
+
 static struct platform_device armada_xp_cpuidle_device = {
 	.name = "cpuidle-armada-370-xp",
 };
@@ -140,13 +142,6 @@ static void armada_370_xp_pmsu_enable_l2_powerdown_onidle(void)
 	writel(reg, pmsu_mp_base + L2C_NFABRIC_PM_CTL);
 }
 
-static void armada_370_xp_cpu_resume(void)
-{
-	asm volatile("bl    ll_add_cpu_to_smp_group\n\t"
-		     "bl    ll_enable_coherency\n\t"
-		     "b	    cpu_resume\n\t");
-}
-
 /* No locking is needed because we only access per-CPU registers */
 void armada_370_xp_pmsu_idle_prepare(bool deepidle)
 {
@@ -206,12 +201,12 @@ static noinline int do_armada_370_xp_cpu_suspend(unsigned long deepidle)
 
 	/* Test the CR_C bit and set it if it was cleared */
 	asm volatile(
-	"mrc	p15, 0, %0, c1, c0, 0 \n\t"
-	"tst	%0, #(1 << 2) \n\t"
-	"orreq	%0, %0, #(1 << 2) \n\t"
-	"mcreq	p15, 0, %0, c1, c0, 0 \n\t"
+	"mrc	p15, 0, r0, c1, c0, 0 \n\t"
+	"tst	r0, #(1 << 2) \n\t"
+	"orreq	r0, r0, #(1 << 2) \n\t"
+	"mcreq	p15, 0, r0, c1, c0, 0 \n\t"
 	"isb	"
-	: : "r" (0));
+	: : : "r0");
 
 	pr_warn("Failed to suspend the system\n");
 
diff --git a/arch/arm/mach-mvebu/pmsu_ll.S b/arch/arm/mach-mvebu/pmsu_ll.S
new file mode 100644
index 00000000000..fc3de68d8c5
--- /dev/null
+++ b/arch/arm/mach-mvebu/pmsu_ll.S
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2014 Marvell
+ *
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ * Gregory Clement <gregory.clement@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * This is the entry point through which CPUs exiting cpuidle deep
+ * idle state are going.
+ */
+ENTRY(armada_370_xp_cpu_resume)
+ARM_BE8(setend	be )			@ go BE8 if entered LE
+	bl	ll_add_cpu_to_smp_group
+	bl	ll_enable_coherency
+	b	cpu_resume
+ENDPROC(armada_370_xp_cpu_resume)
+
diff --git a/arch/arm/mach-nomadik/Kconfig b/arch/arm/mach-nomadik/Kconfig
index 486d301f43f..3c61096c862 100644
--- a/arch/arm/mach-nomadik/Kconfig
+++ b/arch/arm/mach-nomadik/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_NOMADIK
+menuconfig ARCH_NOMADIK
 	bool "ST-Ericsson Nomadik"
 	depends on ARCH_MULTI_V5
 	select ARCH_REQUIRE_GPIOLIB
@@ -15,7 +15,6 @@ config ARCH_NOMADIK
 	  Support for the Nomadik platform by ST-Ericsson
 
 if ARCH_NOMADIK
-menu "Nomadik boards"
 
 config MACH_NOMADIK_8815NHK
 	bool "ST 8815 Nomadik Hardware Kit (evaluation board)"
@@ -24,7 +23,6 @@ config MACH_NOMADIK_8815NHK
 	select I2C_ALGOBIT
 	select I2C_NOMADIK
 
-endmenu
 endif
 
 config NOMADIK_8815
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 0ba482638eb..1c1ed737f7a 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -1,3 +1,6 @@
+menu "TI OMAP/AM/DM/DRA Family"
+	depends on ARCH_MULTI_V6 || ARCH_MULTI_V7
+
 config ARCH_OMAP
 	bool
 
@@ -28,12 +31,11 @@ config ARCH_OMAP4
 	select ARM_CPU_SUSPEND if PM
 	select ARM_ERRATA_720789
 	select ARM_GIC
-	select CACHE_L2X0
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
 	select OMAP_INTERCONNECT
-	select PL310_ERRATA_588369
-	select PL310_ERRATA_727915
+	select PL310_ERRATA_588369 if CACHE_L2X0
+	select PL310_ERRATA_727915 if CACHE_L2X0
 	select PM_OPP if PM
 	select PM_RUNTIME if CPU_IDLE
 	select ARM_ERRATA_754322
@@ -80,7 +82,6 @@ config SOC_DRA7XX
 config ARCH_OMAP2PLUS
 	bool
 	select ARCH_HAS_BANDGAP
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_HOLES_MEMORYMODEL
 	select ARCH_OMAP
 	select ARCH_REQUIRE_GPIOLIB
@@ -343,3 +344,5 @@ config OMAP4_ERRATA_I688
 endmenu
 
 endif
+
+endmenu
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 8421f38cf44..8ca99e9321e 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -110,14 +110,16 @@ obj-y					+= prm_common.o cm_common.o
 obj-$(CONFIG_ARCH_OMAP2)		+= prm2xxx_3xxx.o prm2xxx.o cm2xxx.o
 obj-$(CONFIG_ARCH_OMAP3)		+= prm2xxx_3xxx.o prm3xxx.o cm3xxx.o
 obj-$(CONFIG_ARCH_OMAP3)		+= vc3xxx_data.o vp3xxx_data.o
-obj-$(CONFIG_SOC_AM33XX)		+= prm33xx.o cm33xx.o
 omap-prcm-4-5-common			=  cminst44xx.o cm44xx.o prm44xx.o \
 					   prcm_mpu44xx.o prminst44xx.o \
 					   vc44xx_data.o vp44xx_data.o
 obj-$(CONFIG_ARCH_OMAP4)		+= $(omap-prcm-4-5-common)
 obj-$(CONFIG_SOC_OMAP5)			+= $(omap-prcm-4-5-common)
 obj-$(CONFIG_SOC_DRA7XX)		+= $(omap-prcm-4-5-common)
-obj-$(CONFIG_SOC_AM43XX)		+= $(omap-prcm-4-5-common)
+am33xx-43xx-prcm-common			+= prm33xx.o cm33xx.o
+obj-$(CONFIG_SOC_AM33XX)		+= $(am33xx-43xx-prcm-common)
+obj-$(CONFIG_SOC_AM43XX)		+= $(omap-prcm-4-5-common) \
+					   $(am33xx-43xx-prcm-common)
 
 # OMAP voltage domains
 voltagedomain-common			:= voltage.o vc.o vp.o
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index 660bfc5a70d..e2e52031f05 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -60,7 +60,8 @@
 
 static struct pwm_lookup pwm_lookup[] = {
 	/* LEDB -> PMU_STAT */
-	PWM_LOOKUP("twl-pwmled", 1, "leds_pwm", "beagleboard::pmu_stat"),
+	PWM_LOOKUP("twl-pwmled", 1, "leds_pwm", "beagleboard::pmu_stat",
+		   7812500, PWM_POLARITY_NORMAL),
 };
 
 static struct led_pwm pwm_leds[] = {
diff --git a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
index b935ed2922d..85e0b0c0671 100644
--- a/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
+++ b/arch/arm/mach-omap2/clkt2xxx_virt_prcm_set.c
@@ -208,3 +208,56 @@ void omap2xxx_clkt_vps_late_init(void)
 		clk_put(c);
 	}
 }
+
+#ifdef CONFIG_OF
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+
+static const struct clk_ops virt_prcm_set_ops = {
+	.recalc_rate	= &omap2_table_mpu_recalc,
+	.set_rate	= &omap2_select_table_rate,
+	.round_rate	= &omap2_round_to_table_rate,
+};
+
+/**
+ * omap2xxx_clkt_vps_init - initialize virt_prcm_set clock
+ *
+ * Does a manual init for the virtual prcm DVFS clock for OMAP2. This
+ * function is called only from omap2 DT clock init, as the virtual
+ * node is not modelled in the DT clock data.
+ */
+void omap2xxx_clkt_vps_init(void)
+{
+	struct clk_init_data init = { NULL };
+	struct clk_hw_omap *hw = NULL;
+	struct clk *clk;
+	const char *parent_name = "mpu_ck";
+	struct clk_lookup *lookup = NULL;
+
+	omap2xxx_clkt_vps_late_init();
+	omap2xxx_clkt_vps_check_bootloader_rates();
+
+	hw = kzalloc(sizeof(*hw), GFP_KERNEL);
+	lookup = kzalloc(sizeof(*lookup), GFP_KERNEL);
+	if (!hw || !lookup)
+		goto cleanup;
+	init.name = "virt_prcm_set";
+	init.ops = &virt_prcm_set_ops;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+
+	hw->hw.init = &init;
+
+	clk = clk_register(NULL, &hw->hw);
+
+	lookup->dev_id = NULL;
+	lookup->con_id = "cpufreq_ck";
+	lookup->clk = clk;
+
+	clkdev_add(lookup);
+	return;
+cleanup:
+	kfree(hw);
+	kfree(lookup);
+}
+#endif
diff --git a/arch/arm/mach-omap2/clkt_dpll.c b/arch/arm/mach-omap2/clkt_dpll.c
index 332af927f4d..67fd26a1844 100644
--- a/arch/arm/mach-omap2/clkt_dpll.c
+++ b/arch/arm/mach-omap2/clkt_dpll.c
@@ -76,7 +76,7 @@
  * (assuming that it is counting N upwards), or -2 if the enclosing loop
  * should skip to the next iteration (again assuming N is increasing).
  */
-static int _dpll_test_fint(struct clk_hw_omap *clk, u8 n)
+static int _dpll_test_fint(struct clk_hw_omap *clk, unsigned int n)
 {
 	struct dpll_data *dd;
 	long fint, fint_min, fint_max;
diff --git a/arch/arm/mach-omap2/clock.h b/arch/arm/mach-omap2/clock.h
index bda767a9dea..12f54d428d7 100644
--- a/arch/arm/mach-omap2/clock.h
+++ b/arch/arm/mach-omap2/clock.h
@@ -178,17 +178,6 @@ struct clksel {
 	const struct clksel_rate *rates;
 };
 
-struct clk_hw_omap_ops {
-	void			(*find_idlest)(struct clk_hw_omap *oclk,
-					void __iomem **idlest_reg,
-					u8 *idlest_bit, u8 *idlest_val);
-	void			(*find_companion)(struct clk_hw_omap *oclk,
-					void __iomem **other_reg,
-					u8 *other_bit);
-	void			(*allow_idle)(struct clk_hw_omap *oclk);
-	void			(*deny_idle)(struct clk_hw_omap *oclk);
-};
-
 unsigned long omap_fixed_divisor_recalc(struct clk_hw *hw,
 					unsigned long parent_rate);
 
@@ -279,8 +268,6 @@ extern const struct clk_hw_omap_ops clkhwops_omap3430es2_hsotgusb_wait;
 extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait;
 extern const struct clk_hw_omap_ops clkhwops_apll54;
 extern const struct clk_hw_omap_ops clkhwops_apll96;
-extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll;
-extern const struct clk_hw_omap_ops clkhwops_omap2430_i2chs_wait;
 
 /* clksel_rate blocks shared between OMAP44xx and AM33xx */
 extern const struct clksel_rate div_1_0_rates[];
diff --git a/arch/arm/mach-omap2/clock2xxx.h b/arch/arm/mach-omap2/clock2xxx.h
index 539dc08afbb..45f41a41160 100644
--- a/arch/arm/mach-omap2/clock2xxx.h
+++ b/arch/arm/mach-omap2/clock2xxx.h
@@ -21,10 +21,6 @@ unsigned long omap2xxx_sys_clk_recalc(struct clk_hw *clk,
 				      unsigned long parent_rate);
 unsigned long omap2_osc_clk_recalc(struct clk_hw *clk,
 				   unsigned long parent_rate);
-unsigned long omap2_dpllcore_recalc(struct clk_hw *hw,
-				    unsigned long parent_rate);
-int omap2_reprogram_dpllcore(struct clk_hw *clk, unsigned long rate,
-			     unsigned long parent_rate);
 void omap2xxx_clkt_dpllcore_init(struct clk_hw *hw);
 unsigned long omap2_clk_apll54_recalc(struct clk_hw *hw,
 				      unsigned long parent_rate);
diff --git a/arch/arm/mach-omap2/cm-regbits-34xx.h b/arch/arm/mach-omap2/cm-regbits-34xx.h
index 04dab2fcf86..ee6c784cd6b 100644
--- a/arch/arm/mach-omap2/cm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/cm-regbits-34xx.h
@@ -26,11 +26,14 @@
 #define OMAP3430_EN_WDT3_SHIFT				12
 #define OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_MASK		(1 << 0)
 #define OMAP3430_CM_FCLKEN_IVA2_EN_IVA2_SHIFT		0
+#define OMAP3430_IVA2_DPLL_FREQSEL_SHIFT		4
 #define OMAP3430_IVA2_DPLL_FREQSEL_MASK			(0xf << 4)
 #define OMAP3430_EN_IVA2_DPLL_DRIFTGUARD_SHIFT		3
+#define OMAP3430_EN_IVA2_DPLL_SHIFT			0
 #define OMAP3430_EN_IVA2_DPLL_MASK			(0x7 << 0)
 #define OMAP3430_ST_IVA2_SHIFT				0
 #define OMAP3430_ST_IVA2_CLK_MASK			(1 << 0)
+#define OMAP3430_AUTO_IVA2_DPLL_SHIFT			0
 #define OMAP3430_AUTO_IVA2_DPLL_MASK			(0x7 << 0)
 #define OMAP3430_IVA2_CLK_SRC_SHIFT			19
 #define OMAP3430_IVA2_CLK_SRC_WIDTH			3
diff --git a/arch/arm/mach-omap2/cm33xx.h b/arch/arm/mach-omap2/cm33xx.h
index 15a778ce770..bd244179077 100644
--- a/arch/arm/mach-omap2/cm33xx.h
+++ b/arch/arm/mach-omap2/cm33xx.h
@@ -380,7 +380,7 @@ void am33xx_cm_clkdm_disable_hwsup(u16 inst, u16 cdoffs);
 void am33xx_cm_clkdm_force_sleep(u16 inst, u16 cdoffs);
 void am33xx_cm_clkdm_force_wakeup(u16 inst, u16 cdoffs);
 
-#ifdef CONFIG_SOC_AM33XX
+#if defined(CONFIG_SOC_AM33XX) || defined(CONFIG_SOC_AM43XX)
 extern int am33xx_cm_wait_module_idle(u16 inst, s16 cdoffs,
 					u16 clkctrl_offs);
 extern void am33xx_cm_module_enable(u8 mode, u16 inst, s16 cdoffs,
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index ff029737c8f..dc571f1d3b8 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -91,7 +91,14 @@ extern void omap3_sync32k_timer_init(void);
 extern void omap3_secure_sync32k_timer_init(void);
 extern void omap3_gptimer_timer_init(void);
 extern void omap4_local_timer_init(void);
+#ifdef CONFIG_CACHE_L2X0
 int omap_l2_cache_init(void);
+#else
+static inline int omap_l2_cache_init(void)
+{
+	return 0;
+}
+#endif
 extern void omap5_realtime_timer_init(void);
 
 void omap2420_init_early(void);
@@ -155,7 +162,8 @@ static inline void omap3xxx_restart(enum reboot_mode mode, const char *cmd)
 }
 #endif
 
-#if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5)
+#if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \
+	defined(CONFIG_SOC_DRA7XX) || defined(CONFIG_SOC_AM43XX)
 void omap44xx_restart(enum reboot_mode mode, const char *cmd);
 #else
 static inline void omap44xx_restart(enum reboot_mode mode, const char *cmd)
@@ -241,7 +249,6 @@ static inline void __iomem *omap4_get_scu_base(void)
 }
 #endif
 
-extern void __init gic_init_irq(void);
 extern void gic_dist_disable(void);
 extern void gic_dist_enable(void);
 extern bool gic_dist_disabled(void);
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index e58609b312c..b6f8f348296 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -18,7 +18,6 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/pinctrl/machine.h>
-#include <linux/platform_data/omap4-keypad.h>
 #include <linux/platform_data/mailbox-omap.h>
 
 #include <asm/mach-types.h>
@@ -29,7 +28,6 @@
 #include "iomap.h"
 #include "omap_hwmod.h"
 #include "omap_device.h"
-#include "omap4-keypad.h"
 
 #include "soc.h"
 #include "common.h"
@@ -255,37 +253,6 @@ static inline void omap_init_camera(void)
 #endif
 }
 
-int __init omap4_keyboard_init(struct omap4_keypad_platform_data
-			*sdp4430_keypad_data, struct omap_board_data *bdata)
-{
-	struct platform_device *pdev;
-	struct omap_hwmod *oh;
-	struct omap4_keypad_platform_data *keypad_data;
-	unsigned int id = -1;
-	char *oh_name = "kbd";
-	char *name = "omap4-keypad";
-
-	oh = omap_hwmod_lookup(oh_name);
-	if (!oh) {
-		pr_err("Could not look up %s\n", oh_name);
-		return -ENODEV;
-	}
-
-	keypad_data = sdp4430_keypad_data;
-
-	pdev = omap_device_build(name, id, oh, keypad_data,
-				 sizeof(struct omap4_keypad_platform_data));
-
-	if (IS_ERR(pdev)) {
-		WARN(1, "Can't build omap_device for %s:%s.\n",
-						name, oh->name);
-		return PTR_ERR(pdev);
-	}
-	oh->mux = omap_hwmod_mux_init(bdata->pads, bdata->pads_cnt);
-
-	return 0;
-}
-
 #if defined(CONFIG_OMAP2PLUS_MBOX) || defined(CONFIG_OMAP2PLUS_MBOX_MODULE)
 static inline void __init omap_init_mbox(void)
 {
@@ -330,33 +297,6 @@ static void omap_init_audio(void)
 static inline void omap_init_audio(void) {}
 #endif
 
-#if defined(CONFIG_SND_OMAP_SOC_OMAP_HDMI) || \
-		defined(CONFIG_SND_OMAP_SOC_OMAP_HDMI_MODULE)
-
-static struct platform_device omap_hdmi_audio = {
-	.name	= "omap-hdmi-audio",
-	.id	= -1,
-};
-
-static void __init omap_init_hdmi_audio(void)
-{
-	struct omap_hwmod *oh;
-	struct platform_device *pdev;
-
-	oh = omap_hwmod_lookup("dss_hdmi");
-	if (!oh)
-		return;
-
-	pdev = omap_device_build("omap-hdmi-audio-dai", -1, oh, NULL, 0);
-	WARN(IS_ERR(pdev),
-	     "Can't build omap_device for omap-hdmi-audio-dai.\n");
-
-	platform_device_register(&omap_hdmi_audio);
-}
-#else
-static inline void omap_init_hdmi_audio(void) {}
-#endif
-
 #if defined(CONFIG_SPI_OMAP24XX) || defined(CONFIG_SPI_OMAP24XX_MODULE)
 
 #include <linux/platform_data/spi-omap2-mcspi.h>
@@ -492,7 +432,6 @@ static int __init omap2_init_devices(void)
 	 */
 	omap_init_audio();
 	omap_init_camera();
-	omap_init_hdmi_audio();
 	omap_init_mbox();
 	/* If dtb is there, the devices will be created dynamically */
 	if (!of_have_populated_dt()) {
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index fcd8036af91..6d7ba37e225 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -319,6 +319,15 @@ static int omap3_noncore_dpll_program(struct clk_hw_omap *clk, u16 freqsel)
 
 	/* Set DPLL multiplier, divider */
 	v = omap2_clk_readl(clk, dd->mult_div1_reg);
+
+	/* Handle Duty Cycle Correction */
+	if (dd->dcc_mask) {
+		if (dd->last_rounded_rate >= dd->dcc_rate)
+			v |= dd->dcc_mask; /* Enable DCC */
+		else
+			v &= ~dd->dcc_mask; /* Disable DCC */
+	}
+
 	v &= ~(dd->mult_mask | dd->div1_mask);
 	v |= dd->last_rounded_m << __ffs(dd->mult_mask);
 	v |= (dd->last_rounded_n - 1) << __ffs(dd->div1_mask);
diff --git a/arch/arm/mach-omap2/dsp.c b/arch/arm/mach-omap2/dsp.c
index b8208b4b1bd..f7492df1cbb 100644
--- a/arch/arm/mach-omap2/dsp.c
+++ b/arch/arm/mach-omap2/dsp.c
@@ -29,6 +29,7 @@
 #ifdef CONFIG_TIDSPBRIDGE_DVFS
 #include "omap-pm.h"
 #endif
+#include "soc.h"
 
 #include <linux/platform_data/dsp-omap.h>
 
@@ -59,6 +60,9 @@ void __init omap_dsp_reserve_sdram_memblock(void)
 	phys_addr_t size = CONFIG_TIDSPBRIDGE_MEMPOOL_SIZE;
 	phys_addr_t paddr;
 
+	if (!cpu_is_omap34xx())
+		return;
+
 	if (!size)
 		return;
 
@@ -83,6 +87,9 @@ static int __init omap_dsp_init(void)
 	int err = -ENOMEM;
 	struct omap_dsp_platform_data *pdata = &omap_dsp_pdata;
 
+	if (!cpu_is_omap34xx())
+		return 0;
+
 	pdata->phys_mempool_base = omap_dsp_get_mempool_base();
 
 	if (pdata->phys_mempool_base) {
@@ -115,6 +122,9 @@ module_init(omap_dsp_init);
 
 static void __exit omap_dsp_exit(void)
 {
+	if (!cpu_is_omap34xx())
+		return;
+
 	platform_device_unregister(omap_dsp_pdev);
 }
 module_exit(omap_dsp_exit);
diff --git a/arch/arm/mach-omap2/gpmc-nand.c b/arch/arm/mach-omap2/gpmc-nand.c
index 17cd39360af..93914d22006 100644
--- a/arch/arm/mach-omap2/gpmc-nand.c
+++ b/arch/arm/mach-omap2/gpmc-nand.c
@@ -50,6 +50,16 @@ static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt)
 		 soc_is_omap54xx() || soc_is_dra7xx())
 		return 1;
 
+	if (ecc_opt == OMAP_ECC_BCH4_CODE_HW_DETECTION_SW ||
+		 ecc_opt == OMAP_ECC_BCH8_CODE_HW_DETECTION_SW) {
+		if (cpu_is_omap24xx())
+			return 0;
+		else if (cpu_is_omap3630() && (GET_OMAP_REVISION() == 0))
+			return 0;
+		else
+			return 1;
+	}
+
 	/* OMAP3xxx do not have ELM engine, so cannot support ECC schemes
 	 * which require H/W based ECC error detection */
 	if ((cpu_is_omap34xx() || cpu_is_omap3630()) &&
@@ -57,14 +67,6 @@ static bool gpmc_hwecc_bch_capable(enum omap_ecc ecc_opt)
 		 (ecc_opt == OMAP_ECC_BCH8_CODE_HW)))
 		return 0;
 
-	/*
-	 * For now, assume 4-bit mode is only supported on OMAP3630 ES1.x, x>=1
-	 * and AM33xx derivates. Other chips may be added if confirmed to work.
-	 */
-	if ((ecc_opt == OMAP_ECC_BCH4_CODE_HW_DETECTION_SW) &&
-	    (!cpu_is_omap3630() || (GET_OMAP_REVISION() == 0)))
-		return 0;
-
 	/* legacy platforms support only HAM1 (1-bit Hamming) ECC scheme */
 	if (ecc_opt == OMAP_ECC_HAM1_CODE_HW)
 		return 1;
diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c
index 852b19a367f..8bc13380f0a 100644
--- a/arch/arm/mach-omap2/gpmc.c
+++ b/arch/arm/mach-omap2/gpmc.c
@@ -68,6 +68,9 @@
 #define	GPMC_ECC_BCH_RESULT_1	0x244	/* not available on OMAP2 */
 #define	GPMC_ECC_BCH_RESULT_2	0x248	/* not available on OMAP2 */
 #define	GPMC_ECC_BCH_RESULT_3	0x24c	/* not available on OMAP2 */
+#define	GPMC_ECC_BCH_RESULT_4	0x300	/* not available on OMAP2 */
+#define	GPMC_ECC_BCH_RESULT_5	0x304	/* not available on OMAP2 */
+#define	GPMC_ECC_BCH_RESULT_6	0x308	/* not available on OMAP2 */
 
 /* GPMC ECC control settings */
 #define GPMC_ECC_CTRL_ECCCLEAR		0x100
@@ -677,6 +680,12 @@ void gpmc_update_nand_reg(struct gpmc_nand_regs *reg, int cs)
 					   GPMC_BCH_SIZE * i;
 		reg->gpmc_bch_result3[i] = gpmc_base + GPMC_ECC_BCH_RESULT_3 +
 					   GPMC_BCH_SIZE * i;
+		reg->gpmc_bch_result4[i] = gpmc_base + GPMC_ECC_BCH_RESULT_4 +
+					   i * GPMC_BCH_SIZE;
+		reg->gpmc_bch_result5[i] = gpmc_base + GPMC_ECC_BCH_RESULT_5 +
+					   i * GPMC_BCH_SIZE;
+		reg->gpmc_bch_result6[i] = gpmc_base + GPMC_ECC_BCH_RESULT_6 +
+					   i * GPMC_BCH_SIZE;
 	}
 }
 
@@ -1412,6 +1421,12 @@ static int gpmc_probe_nand_child(struct platform_device *pdev,
 		else
 			gpmc_nand_data->ecc_opt =
 				OMAP_ECC_BCH8_CODE_HW_DETECTION_SW;
+	else if (!strcmp(s, "bch16"))
+		if (gpmc_nand_data->elm_of_node)
+			gpmc_nand_data->ecc_opt =
+				OMAP_ECC_BCH16_CODE_HW;
+		else
+			pr_err("%s: BCH16 requires ELM support\n", __func__);
 	else
 		pr_err("%s: ti,nand-ecc-opt invalid value\n", __func__);
 
@@ -1600,7 +1615,7 @@ static int gpmc_probe_dt(struct platform_device *pdev)
 		return ret;
 	}
 
-	for_each_child_of_node(pdev->dev.of_node, child) {
+	for_each_available_child_of_node(pdev->dev.of_node, child) {
 
 		if (!child->name)
 			continue;
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index 43969da5d50..d42022f2a71 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -649,6 +649,18 @@ void __init dra7xxx_check_revision(void)
 		}
 		break;
 
+	case 0xb9bc:
+		switch (rev) {
+		case 0:
+			omap_revision = DRA722_REV_ES1_0;
+			break;
+		default:
+			/* If we have no new revisions */
+			omap_revision = DRA722_REV_ES1_0;
+			break;
+		}
+		break;
+
 	default:
 		/* Unknown default to latest silicon rev as default*/
 		pr_warn("%s: unknown idcode=0x%08x (hawkeye=0x%08x,rev=0x%d)\n",
diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c
index fd88edeb027..f62f7537d89 100644
--- a/arch/arm/mach-omap2/mux.c
+++ b/arch/arm/mach-omap2/mux.c
@@ -183,8 +183,10 @@ static int __init _omap_mux_get_by_name(struct omap_mux_partition *partition,
 		m0_entry = mux->muxnames[0];
 
 		/* First check for full name in mode0.muxmode format */
-		if (mode0_len && strncmp(muxname, m0_entry, mode0_len))
-			continue;
+		if (mode0_len)
+			if (strncmp(muxname, m0_entry, mode0_len) ||
+			    (strlen(m0_entry) != mode0_len))
+				continue;
 
 		/* Then check for muxmode only */
 		for (i = 0; i < OMAP_MUX_NR_MODES; i++) {
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index 326cd982a3c..a0fe747634c 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -102,26 +102,6 @@ void __init omap_barriers_init(void)
 {}
 #endif
 
-void __init gic_init_irq(void)
-{
-	void __iomem *omap_irq_base;
-
-	/* Static mapping, never released */
-	gic_dist_base_addr = ioremap(OMAP44XX_GIC_DIST_BASE, SZ_4K);
-	BUG_ON(!gic_dist_base_addr);
-
-	twd_base = ioremap(OMAP44XX_LOCAL_TWD_BASE, SZ_4K);
-	BUG_ON(!twd_base);
-
-	/* Static mapping, never released */
-	omap_irq_base = ioremap(OMAP44XX_GIC_CPU_BASE, SZ_512);
-	BUG_ON(!omap_irq_base);
-
-	omap_wakeupgen_init();
-
-	gic_init(0, 29, gic_dist_base_addr, omap_irq_base);
-}
-
 void gic_dist_disable(void)
 {
 	if (gic_dist_base_addr)
@@ -188,6 +168,10 @@ static void omap4_l2c310_write_sec(unsigned long val, unsigned reg)
 		smc_op = OMAP4_MON_L2X0_PREFETCH_INDEX;
 		break;
 
+	case L310_POWER_CTRL:
+		pr_info_once("OMAP L2C310: ROM does not support power control setting\n");
+		return;
+
 	default:
 		WARN_ONCE(1, "OMAP L2C310: ignoring write to reg 0x%x\n", reg);
 		return;
diff --git a/arch/arm/mach-omap2/omap4-keypad.h b/arch/arm/mach-omap2/omap4-keypad.h
deleted file mode 100644
index 20de0d5a7e7..00000000000
--- a/arch/arm/mach-omap2/omap4-keypad.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef ARCH_ARM_PLAT_OMAP4_KEYPAD_H
-#define ARCH_ARM_PLAT_OMAP4_KEYPAD_H
-
-struct omap_board_data;
-
-extern int omap4_keyboard_init(struct omap4_keypad_platform_data *,
-				struct omap_board_data *);
-#endif
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index f7bb435bb54..6c074f37cdd 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -4251,9 +4251,9 @@ void __init omap_hwmod_init(void)
 		soc_ops.enable_module = _omap4_enable_module;
 		soc_ops.disable_module = _omap4_disable_module;
 		soc_ops.wait_target_ready = _omap4_wait_target_ready;
-		soc_ops.assert_hardreset = _omap4_assert_hardreset;
-		soc_ops.deassert_hardreset = _omap4_deassert_hardreset;
-		soc_ops.is_hardreset_asserted = _omap4_is_hardreset_asserted;
+		soc_ops.assert_hardreset = _am33xx_assert_hardreset;
+		soc_ops.deassert_hardreset = _am33xx_deassert_hardreset;
+		soc_ops.is_hardreset_asserted = _am33xx_is_hardreset_asserted;
 		soc_ops.init_clkdm = _init_clkdm;
 	} else if (soc_is_am33xx()) {
 		soc_ops.enable_module = _am33xx_enable_module;
diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
index 290213f2cbe..1103aa0e0d2 100644
--- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
@@ -2020,6 +2020,77 @@ static struct omap_hwmod omap54xx_wd_timer2_hwmod = {
 	},
 };
 
+/*
+ * 'ocp2scp' class
+ * bridge to transform ocp interface protocol to scp (serial control port)
+ * protocol
+ */
+/* ocp2scp3 */
+static struct omap_hwmod omap54xx_ocp2scp3_hwmod;
+/* l4_cfg -> ocp2scp3 */
+static struct omap_hwmod_ocp_if omap54xx_l4_cfg__ocp2scp3 = {
+	.master		= &omap54xx_l4_cfg_hwmod,
+	.slave		= &omap54xx_ocp2scp3_hwmod,
+	.clk		= "l4_root_clk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+static struct omap_hwmod omap54xx_ocp2scp3_hwmod = {
+	.name		= "ocp2scp3",
+	.class		= &omap54xx_ocp2scp_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = OMAP54XX_CM_L3INIT_OCP2SCP3_CLKCTRL_OFFSET,
+			.context_offs = OMAP54XX_RM_L3INIT_OCP2SCP3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_HWCTRL,
+		},
+	},
+};
+
+/*
+ * 'sata' class
+ * sata:  serial ata interface  gen2 compliant   ( 1 rx/ 1 tx)
+ */
+
+static struct omap_hwmod_class_sysconfig omap54xx_sata_sysc = {
+	.sysc_offs	= 0x0000,
+	.sysc_flags	= (SYSC_HAS_MIDLEMODE | SYSC_HAS_SIDLEMODE),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP | MSTANDBY_FORCE | MSTANDBY_NO |
+			   MSTANDBY_SMART | MSTANDBY_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
+static struct omap_hwmod_class omap54xx_sata_hwmod_class = {
+	.name	= "sata",
+	.sysc	= &omap54xx_sata_sysc,
+};
+
+/* sata */
+static struct omap_hwmod omap54xx_sata_hwmod = {
+	.name		= "sata",
+	.class		= &omap54xx_sata_hwmod_class,
+	.clkdm_name	= "l3init_clkdm",
+	.flags		= HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY,
+	.main_clk	= "func_48m_fclk",
+	.mpu_rt_idx	= 1,
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = OMAP54XX_CM_L3INIT_SATA_CLKCTRL_OFFSET,
+			.context_offs = OMAP54XX_RM_L3INIT_SATA_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+};
+
+/* l4_cfg -> sata */
+static struct omap_hwmod_ocp_if omap54xx_l4_cfg__sata = {
+	.master		= &omap54xx_l4_cfg_hwmod,
+	.slave		= &omap54xx_sata_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
 
 /*
  * Interfaces
@@ -2765,6 +2836,8 @@ static struct omap_hwmod_ocp_if *omap54xx_hwmod_ocp_ifs[] __initdata = {
 	&omap54xx_l4_cfg__usb_tll_hs,
 	&omap54xx_l4_cfg__usb_otg_ss,
 	&omap54xx_l4_wkup__wd_timer2,
+	&omap54xx_l4_cfg__ocp2scp3,
+	&omap54xx_l4_cfg__sata,
 	NULL,
 };
 
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 20b4398cec0..284324f2b98 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1268,9 +1268,6 @@ static struct omap_hwmod_class dra7xx_sata_hwmod_class = {
 };
 
 /* sata */
-static struct omap_hwmod_opt_clk sata_opt_clks[] = {
-	{ .role = "ref_clk", .clk = "sata_ref_clk" },
-};
 
 static struct omap_hwmod dra7xx_sata_hwmod = {
 	.name		= "sata",
@@ -1278,6 +1275,7 @@ static struct omap_hwmod dra7xx_sata_hwmod = {
 	.clkdm_name	= "l3init_clkdm",
 	.flags		= HWMOD_SWSUP_SIDLE | HWMOD_SWSUP_MSTANDBY,
 	.main_clk	= "func_48m_fclk",
+	.mpu_rt_idx	= 1,
 	.prcm = {
 		.omap4 = {
 			.clkctrl_offs = DRA7XX_CM_L3INIT_SATA_CLKCTRL_OFFSET,
@@ -1285,8 +1283,6 @@ static struct omap_hwmod dra7xx_sata_hwmod = {
 			.modulemode   = MODULEMODE_SWCTRL,
 		},
 	},
-	.opt_clks	= sata_opt_clks,
-	.opt_clks_cnt	= ARRAY_SIZE(sata_opt_clks),
 };
 
 /*
@@ -1731,8 +1727,20 @@ static struct omap_hwmod dra7xx_uart6_hwmod = {
  *
  */
 
+static struct omap_hwmod_class_sysconfig dra7xx_usb_otg_ss_sysc = {
+	.rev_offs	= 0x0000,
+	.sysc_offs	= 0x0010,
+	.sysc_flags	= (SYSC_HAS_DMADISABLE | SYSC_HAS_MIDLEMODE |
+			   SYSC_HAS_SIDLEMODE),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			   SIDLE_SMART_WKUP | MSTANDBY_FORCE | MSTANDBY_NO |
+			   MSTANDBY_SMART | MSTANDBY_SMART_WKUP),
+	.sysc_fields	= &omap_hwmod_sysc_type2,
+};
+
 static struct omap_hwmod_class dra7xx_usb_otg_ss_hwmod_class = {
 	.name	= "usb_otg_ss",
+	.sysc	= &dra7xx_usb_otg_ss_sysc,
 };
 
 /* usb_otg_ss1 */
diff --git a/arch/arm/mach-omap2/prm-regbits-34xx.h b/arch/arm/mach-omap2/prm-regbits-34xx.h
index 106132db532..cbefbd7cfdb 100644
--- a/arch/arm/mach-omap2/prm-regbits-34xx.h
+++ b/arch/arm/mach-omap2/prm-regbits-34xx.h
@@ -35,6 +35,8 @@
 #define OMAP3430_LOGICSTATEST_MASK			(1 << 2)
 #define OMAP3430_LASTLOGICSTATEENTERED_MASK		(1 << 2)
 #define OMAP3430_LASTPOWERSTATEENTERED_MASK		(0x3 << 0)
+#define OMAP3430_GRPSEL_MCBSP5_MASK			(1 << 10)
+#define OMAP3430_GRPSEL_MCBSP1_MASK			(1 << 9)
 #define OMAP3630_GRPSEL_UART4_MASK			(1 << 18)
 #define OMAP3430_GRPSEL_GPIO6_MASK			(1 << 17)
 #define OMAP3430_GRPSEL_GPIO5_MASK			(1 << 16)
@@ -42,6 +44,10 @@
 #define OMAP3430_GRPSEL_GPIO3_MASK			(1 << 14)
 #define OMAP3430_GRPSEL_GPIO2_MASK			(1 << 13)
 #define OMAP3430_GRPSEL_UART3_MASK			(1 << 11)
+#define OMAP3430_GRPSEL_GPT8_MASK			(1 << 9)
+#define OMAP3430_GRPSEL_GPT7_MASK			(1 << 8)
+#define OMAP3430_GRPSEL_GPT6_MASK			(1 << 7)
+#define OMAP3430_GRPSEL_GPT5_MASK			(1 << 6)
 #define OMAP3430_GRPSEL_MCBSP4_MASK			(1 << 2)
 #define OMAP3430_GRPSEL_MCBSP3_MASK			(1 << 1)
 #define OMAP3430_GRPSEL_MCBSP2_MASK			(1 << 0)
diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h
index de2a34c423a..01ca8086fb6 100644
--- a/arch/arm/mach-omap2/soc.h
+++ b/arch/arm/mach-omap2/soc.h
@@ -462,6 +462,7 @@ IS_OMAP_TYPE(3430, 0x3430)
 #define DRA7XX_CLASS		0x07000000
 #define DRA752_REV_ES1_0	(DRA7XX_CLASS | (0x52 << 16) | (0x10 << 8))
 #define DRA752_REV_ES1_1	(DRA7XX_CLASS | (0x52 << 16) | (0x11 << 8))
+#define DRA722_REV_ES1_0	(DRA7XX_CLASS | (0x22 << 16) | (0x10 << 8))
 
 void omap2xxx_check_revision(void);
 void omap3xxx_check_revision(void);
diff --git a/arch/arm/mach-orion5x/board-dt.c b/arch/arm/mach-orion5x/board-dt.c
index 35d418faf8f..79f033b1ddf 100644
--- a/arch/arm/mach-orion5x/board-dt.c
+++ b/arch/arm/mach-orion5x/board-dt.c
@@ -45,7 +45,7 @@ static void __init orion5x_dt_init(void)
 	orion5x_id(&dev, &rev, &dev_name);
 	printk(KERN_INFO "Orion ID: %s. TCLK=%d.\n", dev_name, orion5x_tclk);
 
-	BUG_ON(mvebu_mbus_dt_init());
+	BUG_ON(mvebu_mbus_dt_init(false));
 
 	/*
 	 * Setup Orion address map
diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig
index e4e505f52ba..042f693ef42 100644
--- a/arch/arm/mach-prima2/Kconfig
+++ b/arch/arm/mach-prima2/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_SIRF
+menuconfig ARCH_SIRF
 	bool "CSR SiRF" if ARCH_MULTI_V7
 	select ARCH_HAS_RESET_CONTROLLER
 	select ARCH_REQUIRE_GPIOLIB
@@ -11,7 +11,7 @@ config ARCH_SIRF
 
 if ARCH_SIRF
 
-menu "CSR SiRF atlas6/primaII/Marco/Polo Specific Features"
+comment "CSR SiRF atlas6/primaII/Marco/Polo Specific Features"
 
 config ARCH_ATLAS6
 	bool "CSR SiRFSoC ATLAS6 ARM Cortex A9 Platform"
@@ -37,8 +37,6 @@ config ARCH_MARCO
 	help
           Support for CSR SiRFSoC ARM Cortex A9 Platform
 
-endmenu
-
 config SIRF_IRQ
 	bool
 
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index a7c30eb0c8d..c66ad4edc5e 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -574,7 +574,8 @@ static struct platform_device backlight = {
 };
 
 static struct pwm_lookup hx4700_pwm_lookup[] = {
-	PWM_LOOKUP("pxa27x-pwm.1", 0, "pwm-backlight", NULL),
+	PWM_LOOKUP("pxa27x-pwm.1", 0, "pwm-backlight", NULL,
+		   30923, PWM_POLARITY_NORMAL),
 };
 
 /*
diff --git a/arch/arm/mach-qcom/Kconfig b/arch/arm/mach-qcom/Kconfig
index fd2b99dceb8..ee5697ba05b 100644
--- a/arch/arm/mach-qcom/Kconfig
+++ b/arch/arm/mach-qcom/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_QCOM
+menuconfig ARCH_QCOM
 	bool "Qualcomm Support" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_GIC
@@ -11,8 +11,6 @@ config ARCH_QCOM
 
 if ARCH_QCOM
 
-menu "Qualcomm SoC Selection"
-
 config ARCH_MSM8X60
 	bool "Enable support for MSM8X60"
 	select CLKSRC_QCOM
@@ -25,8 +23,6 @@ config ARCH_MSM8974
 	bool "Enable support for MSM8974"
 	select HAVE_ARM_ARCH_TIMER
 
-endmenu
-
 config QCOM_SCM
 	bool
 
diff --git a/arch/arm/mach-rockchip/Kconfig b/arch/arm/mach-rockchip/Kconfig
index 1caee6d548b..e4564c259ed 100644
--- a/arch/arm/mach-rockchip/Kconfig
+++ b/arch/arm/mach-rockchip/Kconfig
@@ -2,6 +2,7 @@ config ARCH_ROCKCHIP
 	bool "Rockchip RK2928 and RK3xxx SOCs" if ARCH_MULTI_V7
 	select PINCTRL
 	select PINCTRL_ROCKCHIP
+	select ARCH_HAS_RESET_CONTROLLER
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_GIC
 	select CACHE_L2X0
diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index 04284de7aca..ad5316ae524 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -117,7 +117,7 @@ config S3C24XX_SETUP_TS
 	  Compile in platform device definition for Samsung TouchScreen.
 
 config S3C24XX_DMA
-	bool "S3C2410 DMA support"
+	bool "S3C2410 DMA support (deprecated)"
 	select S3C_DMA
 	help
 	  S3C2410 DMA support. This is needed for drivers like sound which
diff --git a/arch/arm/mach-s3c64xx/Kconfig b/arch/arm/mach-s3c64xx/Kconfig
index 3136d86b0d6..26ca2427e53 100644
--- a/arch/arm/mach-s3c64xx/Kconfig
+++ b/arch/arm/mach-s3c64xx/Kconfig
@@ -18,9 +18,9 @@ config CPU_S3C6410
 	  Enable S3C6410 CPU support
 
 config S3C64XX_PL080
-	bool "S3C64XX DMA using generic PL08x driver"
+	def_bool DMADEVICES
+	select ARM_AMBA
 	select AMBA_PL08X
-	select SAMSUNG_DMADEV
 
 config S3C64XX_SETUP_SDHCI
 	bool
diff --git a/arch/arm/mach-s5p64x0/Kconfig b/arch/arm/mach-s5p64x0/Kconfig
index bb2111b3751..26003e23796 100644
--- a/arch/arm/mach-s5p64x0/Kconfig
+++ b/arch/arm/mach-s5p64x0/Kconfig
@@ -9,16 +9,18 @@ if ARCH_S5P64X0
 
 config CPU_S5P6440
 	bool
+	select ARM_AMBA
+	select PL330_DMA if DMADEVICES
 	select S5P_SLEEP if PM
-	select SAMSUNG_DMADEV
 	select SAMSUNG_WAKEMASK if PM
 	help
 	  Enable S5P6440 CPU support
 
 config CPU_S5P6450
 	bool
+	select ARM_AMBA
+	select PL330_DMA if DMADEVICES
 	select S5P_SLEEP if PM
-	select SAMSUNG_DMADEV
 	select SAMSUNG_WAKEMASK if PM
 	help
 	  Enable S5P6450 CPU support
diff --git a/arch/arm/mach-s5pc100/Kconfig b/arch/arm/mach-s5pc100/Kconfig
index 15170be97a7..c5e3a969b06 100644
--- a/arch/arm/mach-s5pc100/Kconfig
+++ b/arch/arm/mach-s5pc100/Kconfig
@@ -9,8 +9,9 @@ if ARCH_S5PC100
 
 config CPU_S5PC100
 	bool
+	select ARM_AMBA
+	select PL330_DMA if DMADEVICES
 	select S5P_EXT_INT
-	select SAMSUNG_DMADEV
 	help
 	  Enable S5PC100 CPU support
 
diff --git a/arch/arm/mach-s5pv210/Kconfig b/arch/arm/mach-s5pv210/Kconfig
index 8c3abe52175..f60f2862856 100644
--- a/arch/arm/mach-s5pv210/Kconfig
+++ b/arch/arm/mach-s5pv210/Kconfig
@@ -11,10 +11,11 @@ if ARCH_S5PV210
 
 config CPU_S5PV210
 	bool
+	select ARM_AMBA
+	select PL330_DMA if DMADEVICES
 	select S5P_EXT_INT
 	select S5P_PM if PM
 	select S5P_SLEEP if PM
-	select SAMSUNG_DMADEV
 	help
 	  Enable S5PV210 CPU support
 
diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c
index 6c719eccb94..c1ce921c408 100644
--- a/arch/arm/mach-s5pv210/mach-goni.c
+++ b/arch/arm/mach-s5pv210/mach-goni.c
@@ -234,14 +234,6 @@ static void __init goni_radio_init(void)
 
 /* TSP */
 static struct mxt_platform_data qt602240_platform_data = {
-	.x_line		= 17,
-	.y_line		= 11,
-	.x_size		= 800,
-	.y_size		= 480,
-	.blen		= 0x21,
-	.threshold	= 0x28,
-	.voltage	= 2800000,              /* 2.8V */
-	.orient		= MXT_DIAGONAL,
 	.irqflags	= IRQF_TRIGGER_FALLING,
 };
 
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index f9874ba60cc..108939f8d05 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -329,6 +329,11 @@ static struct mtd_partition collie_partitions[] = {
 		.name		= "rootfs",
 		.offset 	= MTDPART_OFS_APPEND,
 		.size		= 0x00e20000,
+	}, {
+		.name		= "bootblock",
+		.offset		= MTDPART_OFS_APPEND,
+		.size		= 0x00020000,
+		.mask_flags	= MTD_WRITEABLE
 	}
 };
 
@@ -356,7 +361,7 @@ static void collie_flash_exit(void)
 }
 
 static struct flash_platform_data collie_flash_data = {
-	.map_name	= "jedec_probe",
+	.map_name	= "cfi_probe",
 	.init		= collie_flash_init,
 	.set_vpp	= collie_set_vpp,
 	.exit		= collie_flash_exit,
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index dbd954e61aa..798073057e5 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -1,7 +1,7 @@
 config ARCH_SHMOBILE
 	bool
 
-config ARCH_SHMOBILE_MULTI
+menuconfig ARCH_SHMOBILE_MULTI
 	bool "Renesas ARM SoCs" if ARCH_MULTI_V7
 	depends on MMU
 	select ARCH_SHMOBILE
@@ -15,7 +15,7 @@ config ARCH_SHMOBILE_MULTI
 
 if ARCH_SHMOBILE_MULTI
 
-comment "Renesas ARM SoCs System Type"
+#comment "Renesas ARM SoCs System Type"
 
 config ARCH_EMEV2
 	bool "Emma Mobile EV2"
@@ -85,7 +85,6 @@ config ARCH_R8A73A4
 	select CPU_V7
 	select SH_CLK_CPG
 	select RENESAS_IRQC
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select SYS_SUPPORTS_SH_CMT
 	select SYS_SUPPORTS_SH_TMU
@@ -264,7 +263,6 @@ config MACH_KOELSCH
 config MACH_KZM9G
 	bool "KZM-A9-GT board"
 	depends on ARCH_SH73A0
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select ARCH_REQUIRE_GPIOLIB
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index 01f81100c33..30fcac73a54 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -31,7 +31,7 @@
 #include <linux/gpio_keys.h>
 #include <linux/regulator/driver.h>
 #include <linux/pinctrl/machine.h>
-#include <linux/platform_data/pwm-renesas-tpu.h>
+#include <linux/pwm.h>
 #include <linux/pwm_backlight.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/gpio-regulator.h>
@@ -399,24 +399,16 @@ static struct resource pwm_resources[] = {
 	},
 };
 
-static struct tpu_pwm_platform_data pwm_device_data = {
-	.channels[2] = {
-		.polarity = PWM_POLARITY_INVERSED,
-	}
-};
-
 static struct platform_device pwm_device = {
 	.name = "renesas-tpu-pwm",
 	.id = -1,
-	.dev = {
-		.platform_data = &pwm_device_data,
-	},
 	.num_resources = ARRAY_SIZE(pwm_resources),
 	.resource = pwm_resources,
 };
 
 static struct pwm_lookup pwm_lookup[] = {
-	PWM_LOOKUP("renesas-tpu-pwm", 2, "pwm-backlight.0", NULL),
+	PWM_LOOKUP("renesas-tpu-pwm", 2, "pwm-backlight.0", NULL,
+		   33333, PWM_POLARITY_INVERSED),
 };
 
 /* LCDC and backlight */
diff --git a/arch/arm/mach-spear/Kconfig b/arch/arm/mach-spear/Kconfig
index 0786249b283..90df2022276 100644
--- a/arch/arm/mach-spear/Kconfig
+++ b/arch/arm/mach-spear/Kconfig
@@ -14,7 +14,6 @@ if PLAT_SPEAR
 config ARCH_SPEAR13XX
 	bool "ST SPEAr13xx"
 	depends on ARCH_MULTI_V7 || PLAT_SPEAR_SINGLE
-	select ARCH_HAS_CPUFREQ
 	select ARM_GIC
 	select GPIO_SPEAR_SPICS
 	select HAVE_ARM_SCU if SMP
diff --git a/arch/arm/mach-sti/Kconfig b/arch/arm/mach-sti/Kconfig
index abf9ee9bbc3..878e9ec97d0 100644
--- a/arch/arm/mach-sti/Kconfig
+++ b/arch/arm/mach-sti/Kconfig
@@ -1,5 +1,5 @@
 menuconfig ARCH_STI
-	bool "STMicroelectronics Consumer Electronics SOCs with Device Trees" if ARCH_MULTI_V7
+	bool "STMicroelectronics Consumer Electronics SOCs" if ARCH_MULTI_V7
 	select ARM_GIC
 	select ARM_GLOBAL_TIMER
 	select PINCTRL
@@ -11,8 +11,8 @@ menuconfig ARCH_STI
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_764369 if SMP
 	select ARM_ERRATA_775420
-	select PL310_ERRATA_753970 if CACHE_PL310
-	select PL310_ERRATA_769419 if CACHE_PL310
+	select PL310_ERRATA_753970 if CACHE_L2X0
+	select PL310_ERRATA_769419 if CACHE_L2X0
 	help
 	  Include support for STiH41x SOCs like STiH415/416 using the device tree
 	  for discovery
diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c
index 3f9587bb51f..b6085084e0f 100644
--- a/arch/arm/mach-sunxi/sunxi.c
+++ b/arch/arm/mach-sunxi/sunxi.c
@@ -12,8 +12,81 @@
 
 #include <linux/clk-provider.h>
 #include <linux/clocksource.h>
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/io.h>
+#include <linux/reboot.h>
 
 #include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/system_misc.h>
+
+#define SUN4I_WATCHDOG_CTRL_REG		0x00
+#define SUN4I_WATCHDOG_CTRL_RESTART		BIT(0)
+#define SUN4I_WATCHDOG_MODE_REG		0x04
+#define SUN4I_WATCHDOG_MODE_ENABLE		BIT(0)
+#define SUN4I_WATCHDOG_MODE_RESET_ENABLE	BIT(1)
+
+#define SUN6I_WATCHDOG1_IRQ_REG		0x00
+#define SUN6I_WATCHDOG1_CTRL_REG	0x10
+#define SUN6I_WATCHDOG1_CTRL_RESTART		BIT(0)
+#define SUN6I_WATCHDOG1_CONFIG_REG	0x14
+#define SUN6I_WATCHDOG1_CONFIG_RESTART		BIT(0)
+#define SUN6I_WATCHDOG1_CONFIG_IRQ		BIT(1)
+#define SUN6I_WATCHDOG1_MODE_REG	0x18
+#define SUN6I_WATCHDOG1_MODE_ENABLE		BIT(0)
+
+static void __iomem *wdt_base;
+
+static void sun4i_restart(enum reboot_mode mode, const char *cmd)
+{
+	if (!wdt_base)
+		return;
+
+	/* Enable timer and set reset bit in the watchdog */
+	writel(SUN4I_WATCHDOG_MODE_ENABLE | SUN4I_WATCHDOG_MODE_RESET_ENABLE,
+	       wdt_base + SUN4I_WATCHDOG_MODE_REG);
+
+	/*
+	 * Restart the watchdog. The default (and lowest) interval
+	 * value for the watchdog is 0.5s.
+	 */
+	writel(SUN4I_WATCHDOG_CTRL_RESTART, wdt_base + SUN4I_WATCHDOG_CTRL_REG);
+
+	while (1) {
+		mdelay(5);
+		writel(SUN4I_WATCHDOG_MODE_ENABLE | SUN4I_WATCHDOG_MODE_RESET_ENABLE,
+		       wdt_base + SUN4I_WATCHDOG_MODE_REG);
+	}
+}
+
+static struct of_device_id sunxi_restart_ids[] = {
+	{ .compatible = "allwinner,sun4i-a10-wdt" },
+	{ /*sentinel*/ }
+};
+
+static void sunxi_setup_restart(void)
+{
+	struct device_node *np;
+
+	np = of_find_matching_node(NULL, sunxi_restart_ids);
+	if (WARN(!np, "unable to setup watchdog restart"))
+		return;
+
+	wdt_base = of_iomap(np, 0);
+	WARN(!wdt_base, "failed to map watchdog base address");
+}
+
+static void __init sunxi_dt_init(void)
+{
+	sunxi_setup_restart();
+
+	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
+}
 
 static const char * const sunxi_board_dt_compat[] = {
 	"allwinner,sun4i-a10",
@@ -23,7 +96,9 @@ static const char * const sunxi_board_dt_compat[] = {
 };
 
 DT_MACHINE_START(SUNXI_DT, "Allwinner A1X (Device Tree)")
+	.init_machine	= sunxi_dt_init,
 	.dt_compat	= sunxi_board_dt_compat,
+	.restart	= sun4i_restart,
 MACHINE_END
 
 static const char * const sun6i_board_dt_compat[] = {
@@ -51,5 +126,7 @@ static const char * const sun7i_board_dt_compat[] = {
 };
 
 DT_MACHINE_START(SUN7I_DT, "Allwinner sun7i (A20) Family")
+	.init_machine	= sunxi_dt_init,
 	.dt_compat	= sun7i_board_dt_compat,
+	.restart	= sun4i_restart,
 MACHINE_END
diff --git a/arch/arm/mach-tegra/Kconfig b/arch/arm/mach-tegra/Kconfig
index e16999e5b73..095399618ca 100644
--- a/arch/arm/mach-tegra/Kconfig
+++ b/arch/arm/mach-tegra/Kconfig
@@ -1,6 +1,5 @@
-config ARCH_TEGRA
+menuconfig ARCH_TEGRA
 	bool "NVIDIA Tegra" if ARCH_MULTI_V7
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SUPPORTS_TRUSTED_FOUNDATIONS
 	select ARM_GIC
@@ -16,8 +15,7 @@ config ARCH_TEGRA
 	help
 	  This enables support for NVIDIA Tegra based systems.
 
-menu "NVIDIA Tegra options"
-	depends on ARCH_TEGRA
+if ARCH_TEGRA
 
 config ARCH_TEGRA_2x_SOC
 	bool "Enable support for Tegra20 family"
@@ -69,4 +67,4 @@ config TEGRA_AHB
 	  which controls AHB bus master arbitration and some
 	  performance parameters(priority, prefech size).
 
-endmenu
+endif
diff --git a/arch/arm/mach-tegra/board-paz00.c b/arch/arm/mach-tegra/board-paz00.c
index e4dec9fcb08..9c6029ba526 100644
--- a/arch/arm/mach-tegra/board-paz00.c
+++ b/arch/arm/mach-tegra/board-paz00.c
@@ -23,9 +23,7 @@
 #include "board.h"
 
 static struct rfkill_gpio_platform_data wifi_rfkill_platform_data = {
-	.name		= "wifi_rfkill",
-	.reset_gpio	= 25, /* PD1 */
-	.shutdown_gpio	= 85, /* PK5 */
+	.name	= "wifi_rfkill",
 	.type	= RFKILL_TYPE_WLAN,
 };
 
diff --git a/arch/arm/mach-u300/Kconfig b/arch/arm/mach-u300/Kconfig
index e3a96d7302e..bc51a71394a 100644
--- a/arch/arm/mach-u300/Kconfig
+++ b/arch/arm/mach-u300/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_U300
+menuconfig ARCH_U300
 	bool "ST-Ericsson U300 Series" if ARCH_MULTI_V5
 	depends on MMU
 	select ARCH_REQUIRE_GPIOLIB
@@ -16,8 +16,6 @@ config ARCH_U300
 
 if ARCH_U300
 
-menu "ST-Ericsson AB U300/U335 Platform"
-
 config MACH_U300
 	depends on ARCH_U300
 	bool "U300"
@@ -43,6 +41,4 @@ config MACH_U300_SPIDUMMY
 		you don't need it. Selecting this will activate the
 		SPI framework and ARM PL022 support.
 
-endmenu
-
 endif
diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig
index b41a42da150..699e8601dbf 100644
--- a/arch/arm/mach-ux500/Kconfig
+++ b/arch/arm/mach-ux500/Kconfig
@@ -1,9 +1,8 @@
-config ARCH_U8500
+menuconfig ARCH_U8500
 	bool "ST-Ericsson U8500 Series" if ARCH_MULTI_V7
 	depends on MMU
 	select AB8500_CORE
 	select ABX500_CORE
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_AMBA
 	select ARM_ERRATA_754322
@@ -16,7 +15,7 @@ config ARCH_U8500
 	select PINCTRL
 	select PINCTRL_ABX500
 	select PINCTRL_NOMADIK
-	select PL310_ERRATA_753970 if CACHE_PL310
+	select PL310_ERRATA_753970 if CACHE_L2X0
 	help
 	  Support for ST-Ericsson's Ux500 architecture
 
@@ -34,8 +33,6 @@ config UX500_SOC_DB8500
 	select REGULATOR
 	select REGULATOR_DB8500_PRCMU
 
-menu "Ux500 target platform (boards)"
-
 config MACH_MOP500
 	bool "U8500 Development platform, MOP500 versions"
 	select I2C
@@ -68,8 +65,6 @@ config UX500_AUTO_PLATFORM
 	  a working kernel. If everything else is disabled, this
 	  automatically enables MACH_MOP500.
 
-endmenu
-
 config UX500_DEBUG_UART
 	int "Ux500 UART to use for low-level debug"
 	default 2
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 90249cfc37b..d8b9330f896 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -1,4 +1,4 @@
-config ARCH_VEXPRESS
+menuconfig ARCH_VEXPRESS
 	bool "ARM Ltd. Versatile Express family" if ARCH_MULTI_V7
 	select ARCH_REQUIRE_GPIOLIB
 	select ARCH_SUPPORTS_BIG_ENDIAN
@@ -37,14 +37,13 @@ config ARCH_VEXPRESS
 	  platforms. The traditional (ATAGs) boot method is not usable on
 	  these boards with this option.
 
-menu "Versatile Express platform type"
-	depends on ARCH_VEXPRESS
+if ARCH_VEXPRESS
 
 config ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA
 	bool "Enable A5 and A9 only errata work-arounds"
 	default y
 	select ARM_ERRATA_720789
-	select PL310_ERRATA_753970 if CACHE_PL310
+	select PL310_ERRATA_753970 if CACHE_L2X0
 	help
 	  Provides common dependencies for Versatile Express platforms
 	  based on Cortex-A5 and Cortex-A9 processors. In order to
@@ -65,7 +64,6 @@ config ARCH_VEXPRESS_DCSCB
 
 config ARCH_VEXPRESS_SPC
 	bool "Versatile Express Serial Power Controller (SPC)"
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select PM_OPP
 	help
@@ -83,4 +81,4 @@ config ARCH_VEXPRESS_TC2_PM
 	  Support for CPU and cluster power management on Versatile Express
 	  with a TC2 (A15x2 A7x3) big.LITTLE core tile.
 
-endmenu
+endif
diff --git a/arch/arm/mach-vt8500/Kconfig b/arch/arm/mach-vt8500/Kconfig
index 08f56a41cb5..aaaa24fe4d7 100644
--- a/arch/arm/mach-vt8500/Kconfig
+++ b/arch/arm/mach-vt8500/Kconfig
@@ -1,6 +1,5 @@
 config ARCH_VT8500
 	bool
-	select ARCH_HAS_CPUFREQ
 	select ARCH_REQUIRE_GPIOLIB
 	select CLKDEV_LOOKUP
 	select VT8500_TIMER
diff --git a/arch/arm/mach-zynq/Kconfig b/arch/arm/mach-zynq/Kconfig
index 573e0db1d0f..0c164f81e72 100644
--- a/arch/arm/mach-zynq/Kconfig
+++ b/arch/arm/mach-zynq/Kconfig
@@ -1,6 +1,5 @@
 config ARCH_ZYNQ
 	bool "Xilinx Zynq ARM Cortex A9 Platform" if ARCH_MULTI_V7
-	select ARCH_HAS_CPUFREQ
 	select ARCH_HAS_OPP
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select ARM_AMBA
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index eda0dd0ab97..c348eaee7ee 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -889,9 +889,10 @@ config CACHE_L2X0
 	help
 	  This option enables the L2x0 PrimeCell.
 
+if CACHE_L2X0
+
 config CACHE_PL310
 	bool
-	depends on CACHE_L2X0
 	default y if CPU_V7 && !(CPU_V6 || CPU_V6K)
 	help
 	  This option enables optimisations for the PL310 cache
@@ -899,7 +900,6 @@ config CACHE_PL310
 
 config PL310_ERRATA_588369
 	bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines"
-	depends on CACHE_L2X0
 	help
 	   The PL310 L2 cache controller implements three types of Clean &
 	   Invalidate maintenance operations: by Physical Address
@@ -912,7 +912,6 @@ config PL310_ERRATA_588369
 
 config PL310_ERRATA_727915
 	bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption"
-	depends on CACHE_L2X0
 	help
 	  PL310 implements the Clean & Invalidate by Way L2 cache maintenance
 	  operation (offset 0x7FC). This operation runs in background so that
@@ -923,7 +922,6 @@ config PL310_ERRATA_727915
 
 config PL310_ERRATA_753970
 	bool "PL310 errata: cache sync operation may be faulty"
-	depends on CACHE_PL310
 	help
 	  This option enables the workaround for the 753970 PL310 (r3p0) erratum.
 
@@ -938,7 +936,6 @@ config PL310_ERRATA_753970
 
 config PL310_ERRATA_769419
 	bool "PL310 errata: no automatic Store Buffer drain"
-	depends on CACHE_L2X0
 	help
 	  On revisions of the PL310 prior to r3p2, the Store Buffer does
 	  not automatically drain. This can cause normal, non-cacheable
@@ -948,6 +945,8 @@ config PL310_ERRATA_769419
 	  on systems with an outer cache, the store buffer is drained
 	  explicitly.
 
+endif
+
 config CACHE_TAUROS2
 	bool "Enable the Tauros2 L2 cache controller"
 	depends on (ARCH_DOVE || ARCH_MMP || CPU_PJ4)
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index efc5cabf70e..7c3fb41a462 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -664,7 +664,7 @@ static int l2c310_cpu_enable_flz(struct notifier_block *nb, unsigned long act, v
 
 static void __init l2c310_enable(void __iomem *base, u32 aux, unsigned num_lock)
 {
-	unsigned rev = readl_relaxed(base + L2X0_CACHE_ID) & L2X0_CACHE_ID_PART_MASK;
+	unsigned rev = readl_relaxed(base + L2X0_CACHE_ID) & L2X0_CACHE_ID_RTL_MASK;
 	bool cortex_a9 = read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9;
 
 	if (rev >= L310_CACHE_ID_RTL_R2P0) {
@@ -1069,6 +1069,33 @@ static const struct l2c_init_data of_l2c310_data __initconst = {
 };
 
 /*
+ * This is a variant of the of_l2c310_data with .sync set to
+ * NULL. Outer sync operations are not needed when the system is I/O
+ * coherent, and potentially harmful in certain situations (PCIe/PL310
+ * deadlock on Armada 375/38x due to hardware I/O coherency). The
+ * other operations are kept because they are infrequent (therefore do
+ * not cause the deadlock in practice) and needed for secondary CPU
+ * boot and other power management activities.
+ */
+static const struct l2c_init_data of_l2c310_coherent_data __initconst = {
+	.type = "L2C-310 Coherent",
+	.way_size_0 = SZ_8K,
+	.num_lock = 8,
+	.of_parse = l2c310_of_parse,
+	.enable = l2c310_enable,
+	.fixup = l2c310_fixup,
+	.save  = l2c310_save,
+	.outer_cache = {
+		.inv_range   = l2c210_inv_range,
+		.clean_range = l2c210_clean_range,
+		.flush_range = l2c210_flush_range,
+		.flush_all   = l2c210_flush_all,
+		.disable     = l2c310_disable,
+		.resume      = l2c310_resume,
+	},
+};
+
+/*
  * Note that the end addresses passed to Linux primitives are
  * noninclusive, while the hardware cache range operations use
  * inclusive start and end addresses.
@@ -1487,6 +1514,10 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 
 	data = of_match_node(l2x0_ids, np)->data;
 
+	if (of_device_is_compatible(np, "arm,pl310-cache") &&
+	    of_property_read_bool(np, "arm,io-coherent"))
+		data = &of_l2c310_coherent_data;
+
 	old_aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
 	if (old_aux != ((old_aux & aux_mask) | aux_val)) {
 		pr_warn("L2C: platform modifies aux control register: 0x%08x -> 0x%08x\n",
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4c88935654c..1f88db06b13 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -461,12 +461,21 @@ void __init dma_contiguous_remap(void)
 		map.type = MT_MEMORY_DMA_READY;
 
 		/*
-		 * Clear previous low-memory mapping
+		 * Clear previous low-memory mapping to ensure that the
+		 * TLB does not see any conflicting entries, then flush
+		 * the TLB of the old entries before creating new mappings.
+		 *
+		 * This ensures that any speculatively loaded TLB entries
+		 * (even though they may be rare) can not cause any problems,
+		 * and ensures that this code is architecturally compliant.
 		 */
 		for (addr = __phys_to_virt(start); addr < __phys_to_virt(end);
 		     addr += PMD_SIZE)
 			pmd_clear(pmd_off_k(addr));
 
+		flush_tlb_kernel_range(__phys_to_virt(start),
+				       __phys_to_virt(end));
+
 		iotable_init(&map, 1);
 	}
 }
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 8e0e52eb76b..c447ec70e86 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -9,6 +9,11 @@
 #include <asm/sections.h>
 #include <asm/system_info.h>
 
+/*
+ * Note: accesses outside of the kernel image and the identity map area
+ * are not supported on any CPU using the idmap tables as its current
+ * page tables.
+ */
 pgd_t *idmap_pgd;
 phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
 
@@ -25,6 +30,13 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 			pr_warning("Failed to allocate identity pmd.\n");
 			return;
 		}
+		/*
+		 * Copy the original PMD to ensure that the PMD entries for
+		 * the kernel image are preserved.
+		 */
+		if (!pud_none(*pud))
+			memcpy(pmd, pmd_offset(pud, 0),
+			       PTRS_PER_PMD * sizeof(pmd_t));
 		pud_populate(&init_mm, pud, pmd);
 		pmd += pmd_index(addr);
 	} else
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index ab14b79b03f..6e3ba8d112a 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1406,8 +1406,8 @@ void __init early_paging_init(const struct machine_desc *mdesc,
 		return;
 
 	/* remap kernel code and data */
-	map_start = init_mm.start_code;
-	map_end   = init_mm.brk;
+	map_start = init_mm.start_code & PMD_MASK;
+	map_end   = ALIGN(init_mm.brk, PMD_SIZE);
 
 	/* get a handle on things... */
 	pgd0 = pgd_offset_k(0);
@@ -1442,7 +1442,7 @@ void __init early_paging_init(const struct machine_desc *mdesc,
 	}
 
 	/* remap pmds for kernel mapping */
-	phys = __pa(map_start) & PMD_MASK;
+	phys = __pa(map_start);
 	do {
 		*pmdk++ = __pmd(phys | pmdprot);
 		phys += PMD_SIZE;
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index da1874f9f8c..a014dfacd5c 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -300,6 +300,7 @@ void __init sanity_check_meminfo(void)
 	sanity_check_meminfo_mpu();
 	end = memblock_end_of_DRAM();
 	high_memory = __va(end - 1) + 1;
+	memblock_set_current_limit(end);
 }
 
 /*
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index 97448c3acf3..ba0d58e1a2a 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -502,6 +502,7 @@ __\name\()_proc_info:
 	.long	\cpu_val
 	.long	\cpu_mask
 	.long   PMD_TYPE_SECT | \
+		PMD_SECT_CACHEABLE | \
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 6f879c319a9..fb5503ce016 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -136,7 +136,7 @@ static u16 saved_regs(struct jit_ctx *ctx)
 	u16 ret = 0;
 
 	if ((ctx->skf->len > 1) ||
-	    (ctx->skf->insns[0].code == BPF_S_RET_A))
+	    (ctx->skf->insns[0].code == (BPF_RET | BPF_A)))
 		ret |= 1 << r_A;
 
 #ifdef CONFIG_FRAME_POINTER
@@ -164,18 +164,10 @@ static inline int mem_words_used(struct jit_ctx *ctx)
 static inline bool is_load_to_a(u16 inst)
 {
 	switch (inst) {
-	case BPF_S_LD_W_LEN:
-	case BPF_S_LD_W_ABS:
-	case BPF_S_LD_H_ABS:
-	case BPF_S_LD_B_ABS:
-	case BPF_S_ANC_CPU:
-	case BPF_S_ANC_IFINDEX:
-	case BPF_S_ANC_MARK:
-	case BPF_S_ANC_PROTOCOL:
-	case BPF_S_ANC_RXHASH:
-	case BPF_S_ANC_VLAN_TAG:
-	case BPF_S_ANC_VLAN_TAG_PRESENT:
-	case BPF_S_ANC_QUEUE:
+	case BPF_LD | BPF_W | BPF_LEN:
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
 		return true;
 	default:
 		return false;
@@ -215,7 +207,7 @@ static void build_prologue(struct jit_ctx *ctx)
 		emit(ARM_MOV_I(r_X, 0), ctx);
 
 	/* do not leak kernel data to userspace */
-	if ((first_inst != BPF_S_RET_K) && !(is_load_to_a(first_inst)))
+	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
 		emit(ARM_MOV_I(r_A, 0), ctx);
 
 	/* stack space for the BPF_MEM words */
@@ -480,36 +472,39 @@ static int build_body(struct jit_ctx *ctx)
 	u32 k;
 
 	for (i = 0; i < prog->len; i++) {
+		u16 code;
+
 		inst = &(prog->insns[i]);
 		/* K as an immediate value operand */
 		k = inst->k;
+		code = bpf_anc_helper(inst);
 
 		/* compute offsets only in the fake pass */
 		if (ctx->target == NULL)
 			ctx->offsets[i] = ctx->idx * 4;
 
-		switch (inst->code) {
-		case BPF_S_LD_IMM:
+		switch (code) {
+		case BPF_LD | BPF_IMM:
 			emit_mov_i(r_A, k, ctx);
 			break;
-		case BPF_S_LD_W_LEN:
+		case BPF_LD | BPF_W | BPF_LEN:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
 			emit(ARM_LDR_I(r_A, r_skb,
 				       offsetof(struct sk_buff, len)), ctx);
 			break;
-		case BPF_S_LD_MEM:
+		case BPF_LD | BPF_MEM:
 			/* A = scratch[k] */
 			ctx->seen |= SEEN_MEM_WORD(k);
 			emit(ARM_LDR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
 			break;
-		case BPF_S_LD_W_ABS:
+		case BPF_LD | BPF_W | BPF_ABS:
 			load_order = 2;
 			goto load;
-		case BPF_S_LD_H_ABS:
+		case BPF_LD | BPF_H | BPF_ABS:
 			load_order = 1;
 			goto load;
-		case BPF_S_LD_B_ABS:
+		case BPF_LD | BPF_B | BPF_ABS:
 			load_order = 0;
 load:
 			/* the interpreter will deal with the negative K */
@@ -552,31 +547,31 @@ load_common:
 			emit_err_ret(ARM_COND_NE, ctx);
 			emit(ARM_MOV_R(r_A, ARM_R0), ctx);
 			break;
-		case BPF_S_LD_W_IND:
+		case BPF_LD | BPF_W | BPF_IND:
 			load_order = 2;
 			goto load_ind;
-		case BPF_S_LD_H_IND:
+		case BPF_LD | BPF_H | BPF_IND:
 			load_order = 1;
 			goto load_ind;
-		case BPF_S_LD_B_IND:
+		case BPF_LD | BPF_B | BPF_IND:
 			load_order = 0;
 load_ind:
 			OP_IMM3(ARM_ADD, r_off, r_X, k, ctx);
 			goto load_common;
-		case BPF_S_LDX_IMM:
+		case BPF_LDX | BPF_IMM:
 			ctx->seen |= SEEN_X;
 			emit_mov_i(r_X, k, ctx);
 			break;
-		case BPF_S_LDX_W_LEN:
+		case BPF_LDX | BPF_W | BPF_LEN:
 			ctx->seen |= SEEN_X | SEEN_SKB;
 			emit(ARM_LDR_I(r_X, r_skb,
 				       offsetof(struct sk_buff, len)), ctx);
 			break;
-		case BPF_S_LDX_MEM:
+		case BPF_LDX | BPF_MEM:
 			ctx->seen |= SEEN_X | SEEN_MEM_WORD(k);
 			emit(ARM_LDR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
 			break;
-		case BPF_S_LDX_B_MSH:
+		case BPF_LDX | BPF_B | BPF_MSH:
 			/* x = ((*(frame + k)) & 0xf) << 2; */
 			ctx->seen |= SEEN_X | SEEN_DATA | SEEN_CALL;
 			/* the interpreter should deal with the negative K */
@@ -606,113 +601,113 @@ load_ind:
 			emit(ARM_AND_I(r_X, ARM_R0, 0x00f), ctx);
 			emit(ARM_LSL_I(r_X, r_X, 2), ctx);
 			break;
-		case BPF_S_ST:
+		case BPF_ST:
 			ctx->seen |= SEEN_MEM_WORD(k);
 			emit(ARM_STR_I(r_A, ARM_SP, SCRATCH_OFF(k)), ctx);
 			break;
-		case BPF_S_STX:
+		case BPF_STX:
 			update_on_xread(ctx);
 			ctx->seen |= SEEN_MEM_WORD(k);
 			emit(ARM_STR_I(r_X, ARM_SP, SCRATCH_OFF(k)), ctx);
 			break;
-		case BPF_S_ALU_ADD_K:
+		case BPF_ALU | BPF_ADD | BPF_K:
 			/* A += K */
 			OP_IMM3(ARM_ADD, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ALU_ADD_X:
+		case BPF_ALU | BPF_ADD | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_ADD_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_SUB_K:
+		case BPF_ALU | BPF_SUB | BPF_K:
 			/* A -= K */
 			OP_IMM3(ARM_SUB, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ALU_SUB_X:
+		case BPF_ALU | BPF_SUB | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_SUB_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_MUL_K:
+		case BPF_ALU | BPF_MUL | BPF_K:
 			/* A *= K */
 			emit_mov_i(r_scratch, k, ctx);
 			emit(ARM_MUL(r_A, r_A, r_scratch), ctx);
 			break;
-		case BPF_S_ALU_MUL_X:
+		case BPF_ALU | BPF_MUL | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_MUL(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_DIV_K:
+		case BPF_ALU | BPF_DIV | BPF_K:
 			if (k == 1)
 				break;
 			emit_mov_i(r_scratch, k, ctx);
 			emit_udiv(r_A, r_A, r_scratch, ctx);
 			break;
-		case BPF_S_ALU_DIV_X:
+		case BPF_ALU | BPF_DIV | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_CMP_I(r_X, 0), ctx);
 			emit_err_ret(ARM_COND_EQ, ctx);
 			emit_udiv(r_A, r_A, r_X, ctx);
 			break;
-		case BPF_S_ALU_OR_K:
+		case BPF_ALU | BPF_OR | BPF_K:
 			/* A |= K */
 			OP_IMM3(ARM_ORR, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ALU_OR_X:
+		case BPF_ALU | BPF_OR | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_ORR_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_XOR_K:
+		case BPF_ALU | BPF_XOR | BPF_K:
 			/* A ^= K; */
 			OP_IMM3(ARM_EOR, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ANC_ALU_XOR_X:
-		case BPF_S_ALU_XOR_X:
+		case BPF_ANC | SKF_AD_ALU_XOR_X:
+		case BPF_ALU | BPF_XOR | BPF_X:
 			/* A ^= X */
 			update_on_xread(ctx);
 			emit(ARM_EOR_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_AND_K:
+		case BPF_ALU | BPF_AND | BPF_K:
 			/* A &= K */
 			OP_IMM3(ARM_AND, r_A, r_A, k, ctx);
 			break;
-		case BPF_S_ALU_AND_X:
+		case BPF_ALU | BPF_AND | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_AND_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_LSH_K:
+		case BPF_ALU | BPF_LSH | BPF_K:
 			if (unlikely(k > 31))
 				return -1;
 			emit(ARM_LSL_I(r_A, r_A, k), ctx);
 			break;
-		case BPF_S_ALU_LSH_X:
+		case BPF_ALU | BPF_LSH | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_LSL_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_RSH_K:
+		case BPF_ALU | BPF_RSH | BPF_K:
 			if (unlikely(k > 31))
 				return -1;
 			emit(ARM_LSR_I(r_A, r_A, k), ctx);
 			break;
-		case BPF_S_ALU_RSH_X:
+		case BPF_ALU | BPF_RSH | BPF_X:
 			update_on_xread(ctx);
 			emit(ARM_LSR_R(r_A, r_A, r_X), ctx);
 			break;
-		case BPF_S_ALU_NEG:
+		case BPF_ALU | BPF_NEG:
 			/* A = -A */
 			emit(ARM_RSB_I(r_A, r_A, 0), ctx);
 			break;
-		case BPF_S_JMP_JA:
+		case BPF_JMP | BPF_JA:
 			/* pc += K */
 			emit(ARM_B(b_imm(i + k + 1, ctx)), ctx);
 			break;
-		case BPF_S_JMP_JEQ_K:
+		case BPF_JMP | BPF_JEQ | BPF_K:
 			/* pc += (A == K) ? pc->jt : pc->jf */
 			condt  = ARM_COND_EQ;
 			goto cmp_imm;
-		case BPF_S_JMP_JGT_K:
+		case BPF_JMP | BPF_JGT | BPF_K:
 			/* pc += (A > K) ? pc->jt : pc->jf */
 			condt  = ARM_COND_HI;
 			goto cmp_imm;
-		case BPF_S_JMP_JGE_K:
+		case BPF_JMP | BPF_JGE | BPF_K:
 			/* pc += (A >= K) ? pc->jt : pc->jf */
 			condt  = ARM_COND_HS;
 cmp_imm:
@@ -731,22 +726,22 @@ cond_jump:
 				_emit(condt ^ 1, ARM_B(b_imm(i + inst->jf + 1,
 							     ctx)), ctx);
 			break;
-		case BPF_S_JMP_JEQ_X:
+		case BPF_JMP | BPF_JEQ | BPF_X:
 			/* pc += (A == X) ? pc->jt : pc->jf */
 			condt   = ARM_COND_EQ;
 			goto cmp_x;
-		case BPF_S_JMP_JGT_X:
+		case BPF_JMP | BPF_JGT | BPF_X:
 			/* pc += (A > X) ? pc->jt : pc->jf */
 			condt   = ARM_COND_HI;
 			goto cmp_x;
-		case BPF_S_JMP_JGE_X:
+		case BPF_JMP | BPF_JGE | BPF_X:
 			/* pc += (A >= X) ? pc->jt : pc->jf */
 			condt   = ARM_COND_CS;
 cmp_x:
 			update_on_xread(ctx);
 			emit(ARM_CMP_R(r_A, r_X), ctx);
 			goto cond_jump;
-		case BPF_S_JMP_JSET_K:
+		case BPF_JMP | BPF_JSET | BPF_K:
 			/* pc += (A & K) ? pc->jt : pc->jf */
 			condt  = ARM_COND_NE;
 			/* not set iff all zeroes iff Z==1 iff EQ */
@@ -759,16 +754,16 @@ cmp_x:
 				emit(ARM_TST_I(r_A, imm12), ctx);
 			}
 			goto cond_jump;
-		case BPF_S_JMP_JSET_X:
+		case BPF_JMP | BPF_JSET | BPF_X:
 			/* pc += (A & X) ? pc->jt : pc->jf */
 			update_on_xread(ctx);
 			condt  = ARM_COND_NE;
 			emit(ARM_TST_R(r_A, r_X), ctx);
 			goto cond_jump;
-		case BPF_S_RET_A:
+		case BPF_RET | BPF_A:
 			emit(ARM_MOV_R(ARM_R0, r_A), ctx);
 			goto b_epilogue;
-		case BPF_S_RET_K:
+		case BPF_RET | BPF_K:
 			if ((k == 0) && (ctx->ret0_fp_idx < 0))
 				ctx->ret0_fp_idx = i;
 			emit_mov_i(ARM_R0, k, ctx);
@@ -776,17 +771,17 @@ b_epilogue:
 			if (i != ctx->skf->len - 1)
 				emit(ARM_B(b_imm(prog->len, ctx)), ctx);
 			break;
-		case BPF_S_MISC_TAX:
+		case BPF_MISC | BPF_TAX:
 			/* X = A */
 			ctx->seen |= SEEN_X;
 			emit(ARM_MOV_R(r_X, r_A), ctx);
 			break;
-		case BPF_S_MISC_TXA:
+		case BPF_MISC | BPF_TXA:
 			/* A = X */
 			update_on_xread(ctx);
 			emit(ARM_MOV_R(r_A, r_X), ctx);
 			break;
-		case BPF_S_ANC_PROTOCOL:
+		case BPF_ANC | SKF_AD_PROTOCOL:
 			/* A = ntohs(skb->protocol) */
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
@@ -795,7 +790,7 @@ b_epilogue:
 			emit(ARM_LDRH_I(r_scratch, r_skb, off), ctx);
 			emit_swap16(r_A, r_scratch, ctx);
 			break;
-		case BPF_S_ANC_CPU:
+		case BPF_ANC | SKF_AD_CPU:
 			/* r_scratch = current_thread_info() */
 			OP_IMM3(ARM_BIC, r_scratch, ARM_SP, THREAD_SIZE - 1, ctx);
 			/* A = current_thread_info()->cpu */
@@ -803,7 +798,7 @@ b_epilogue:
 			off = offsetof(struct thread_info, cpu);
 			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
 			break;
-		case BPF_S_ANC_IFINDEX:
+		case BPF_ANC | SKF_AD_IFINDEX:
 			/* A = skb->dev->ifindex */
 			ctx->seen |= SEEN_SKB;
 			off = offsetof(struct sk_buff, dev);
@@ -817,30 +812,30 @@ b_epilogue:
 			off = offsetof(struct net_device, ifindex);
 			emit(ARM_LDR_I(r_A, r_scratch, off), ctx);
 			break;
-		case BPF_S_ANC_MARK:
+		case BPF_ANC | SKF_AD_MARK:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
 			off = offsetof(struct sk_buff, mark);
 			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
 			break;
-		case BPF_S_ANC_RXHASH:
+		case BPF_ANC | SKF_AD_RXHASH:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
 			off = offsetof(struct sk_buff, hash);
 			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
 			break;
-		case BPF_S_ANC_VLAN_TAG:
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
+		case BPF_ANC | SKF_AD_VLAN_TAG:
+		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
 			off = offsetof(struct sk_buff, vlan_tci);
 			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
-			if (inst->code == BPF_S_ANC_VLAN_TAG)
+			if (code == (BPF_ANC | SKF_AD_VLAN_TAG))
 				OP_IMM3(ARM_AND, r_A, r_A, VLAN_VID_MASK, ctx);
 			else
 				OP_IMM3(ARM_AND, r_A, r_A, VLAN_TAG_PRESENT, ctx);
 			break;
-		case BPF_S_ANC_QUEUE:
+		case BPF_ANC | SKF_AD_QUEUE:
 			ctx->seen |= SEEN_SKB;
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
 						  queue_mapping) != 2);
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index 243dfcb2ca0..301b892d97d 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -35,27 +35,15 @@ config SAMSUNG_PM
 	  Base platform power management code for samsung code
 
 if PLAT_SAMSUNG
+menu "Samsung Common options"
 
 # boot configurations
 
 comment "Boot options"
 
-config S3C_BOOT_ERROR_RESET
-	bool "S3C Reboot on decompression error"
-	help
-	  Say y here to use the watchdog to reset the system if the
-	  kernel decompressor detects an error during decompression.
-
-config S3C_BOOT_UART_FORCE_FIFO
-       bool "Force UART FIFO on during boot process"
-       default y
-       help
-         Say Y here to force the UART FIFOs on during the kernel
-	 uncompressor
-
-
 config S3C_LOWLEVEL_UART_PORT
 	int "S3C UART to use for low-level messages"
+	depends on ARCH_S3C64XX
 	default 0
 	help
 	  Choice of which UART port to use for the low-level messages,
@@ -407,17 +395,16 @@ config SAMSUNG_PM_GPIO
 	  Include legacy GPIO power management code for platforms not using
 	  pinctrl-samsung driver.
 
-endif
-
 config SAMSUNG_DMADEV
-	bool
-	select ARM_AMBA
+	bool "Use legacy Samsung DMA abstraction"
+	depends on CPU_S5PV210 || CPU_S5PC100 || ARCH_S5P64X0 || ARCH_S3C64XX
 	select DMADEVICES
-	select PL330_DMA if (ARCH_EXYNOS5 || ARCH_EXYNOS4 || CPU_S5PV210 || CPU_S5PC100 || \
-					CPU_S5P6450 || CPU_S5P6440)
+	default y
 	help
 	  Use DMA device engine for PL330 DMAC.
 
+endif
+
 config S5P_DEV_MFC
 	bool
 	help
@@ -503,4 +490,5 @@ config DEBUG_S3C_UART
 	default "2" if DEBUG_S3C_UART2
 	default "3" if DEBUG_S3C_UART3
 
+endmenu
 endif
diff --git a/arch/arm/plat-samsung/dev-backlight.c b/arch/arm/plat-samsung/dev-backlight.c
index be4ad0b21c0..2157c5b539e 100644
--- a/arch/arm/plat-samsung/dev-backlight.c
+++ b/arch/arm/plat-samsung/dev-backlight.c
@@ -124,8 +124,6 @@ void __init samsung_bl_set(struct samsung_bl_gpio_info *gpio_info,
 		samsung_bl_data->pwm_period_ns = bl_data->pwm_period_ns;
 	if (bl_data->enable_gpio >= 0)
 		samsung_bl_data->enable_gpio = bl_data->enable_gpio;
-	if (bl_data->enable_gpio_flags)
-		samsung_bl_data->enable_gpio_flags = bl_data->enable_gpio_flags;
 	if (bl_data->init)
 		samsung_bl_data->init = bl_data->init;
 	if (bl_data->notify)
diff --git a/arch/arm/xen/grant-table.c b/arch/arm/xen/grant-table.c
index 859a9bb002d..91cf08ba1e9 100644
--- a/arch/arm/xen/grant-table.c
+++ b/arch/arm/xen/grant-table.c
@@ -51,3 +51,8 @@ int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
 {
 	return -ENOSYS;
 }
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
+{
+	return 0;
+}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7295419165e..b0f9c9db959 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,14 +1,17 @@
 config ARM64
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
 	select ARM_AMBA
 	select ARM_ARCH_TIMER
 	select ARM_GIC
+	select AUDIT_ARCH_COMPAT_GENERIC
+	select ARM_GIC_V3
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
@@ -27,10 +30,12 @@ config ARM64
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select HARDIRQS_SW_RESEND
+	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_C_RECORDMCOUNT
+	select HAVE_CC_STACKPROTECTOR
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
@@ -61,6 +66,7 @@ config ARM64
 	select RTC_LIB
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
+	select HAVE_CONTEXT_TRACKING
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -153,14 +159,63 @@ endmenu
 
 menu "Kernel Features"
 
+choice
+	prompt "Page size"
+	default ARM64_4K_PAGES
+	help
+	  Page size (translation granule) configuration.
+
+config ARM64_4K_PAGES
+	bool "4KB"
+	help
+	  This feature enables 4KB pages support.
+
 config ARM64_64K_PAGES
-	bool "Enable 64KB pages support"
+	bool "64KB"
 	help
 	  This feature enables 64KB pages support (4KB by default)
 	  allowing only two levels of page tables and faster TLB
 	  look-up. AArch32 emulation is not available when this feature
 	  is enabled.
 
+endchoice
+
+choice
+	prompt "Virtual address space size"
+	default ARM64_VA_BITS_39 if ARM64_4K_PAGES
+	default ARM64_VA_BITS_42 if ARM64_64K_PAGES
+	help
+	  Allows choosing one of multiple possible virtual address
+	  space sizes. The level of translation table is determined by
+	  a combination of page size and virtual address space size.
+
+config ARM64_VA_BITS_39
+	bool "39-bit"
+	depends on ARM64_4K_PAGES
+
+config ARM64_VA_BITS_42
+	bool "42-bit"
+	depends on ARM64_64K_PAGES
+
+config ARM64_VA_BITS_48
+	bool "48-bit"
+	depends on BROKEN
+
+endchoice
+
+config ARM64_VA_BITS
+	int
+	default 39 if ARM64_VA_BITS_39
+	default 42 if ARM64_VA_BITS_42
+	default 48 if ARM64_VA_BITS_48
+
+config ARM64_PGTABLE_LEVELS
+	int
+	default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42
+	default 3 if ARM64_64K_PAGES && ARM64_VA_BITS_48
+	default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39
+	default 4 if ARM64_4K_PAGES && ARM64_VA_BITS_48
+
 config CPU_BIG_ENDIAN
        bool "Build big-endian kernel"
        help
@@ -292,12 +347,18 @@ config CMDLINE_FORCE
 	  This is useful if you cannot or don't want to change the
 	  command-line options your boot loader passes to the kernel.
 
+config EFI_STUB
+	bool
+
 config EFI
 	bool "UEFI runtime support"
 	depends on OF && !CPU_BIG_ENDIAN
 	select LIBFDT
 	select UCS2_STRING
 	select EFI_PARAMS_FROM_FDT
+	select EFI_RUNTIME_WRAPPERS
+	select EFI_STUB
+	select EFI_ARMSTUB
 	default y
 	help
 	  This option provides support for runtime services provided
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 1c1b7562984..4ee8e90b7a4 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -28,4 +28,19 @@ config PID_IN_CONTEXTIDR
 	  instructions during context switch. Say Y here only if you are
 	  planning to use hardware trace tools with this kernel.
 
+config ARM64_RANDOMIZE_TEXT_OFFSET
+	bool "Randomize TEXT_OFFSET at build time"
+	help
+	  Say Y here if you want the image load offset (AKA TEXT_OFFSET)
+	  of the kernel to be randomized at build-time. When selected,
+	  this option will cause TEXT_OFFSET to be randomized upon any
+	  build of the kernel, and the offset will be reflected in the
+	  text_offset field of the resulting Image. This can be used to
+	  fuzz-test bootloaders which respect text_offset.
+
+	  This option is intended for bootloader and/or kernel testing
+	  only. Bootloaders must make no assumptions regarding the value
+	  of TEXT_OFFSET and platforms must not require a specific
+	  value.
+
 endmenu
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 8185a913c5e..57833546bf0 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -38,7 +38,11 @@ CHECKFLAGS	+= -D__aarch64__
 head-y		:= arch/arm64/kernel/head.o
 
 # The byte offset of the kernel image in RAM from the start of RAM.
+ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y)
+TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%04x0\n", int(65535 * rand())}')
+else
 TEXT_OFFSET := 0x00080000
+endif
 
 export	TEXT_OFFSET GZFLAGS
 
@@ -48,6 +52,7 @@ core-$(CONFIG_XEN) += arch/arm64/xen/
 core-$(CONFIG_CRYPTO) += arch/arm64/crypto/
 libs-y		:= arch/arm64/lib/ $(libs-y)
 libs-y		+= $(LIBGCC)
+libs-$(CONFIG_EFI_STUB) += drivers/firmware/efi/libstub/
 
 # Default target when executing plain make
 KBUILD_IMAGE	:= Image.gz
diff --git a/arch/arm64/boot/dts/apm-mustang.dts b/arch/arm64/boot/dts/apm-mustang.dts
index 1247ca1200b..6541962f5d7 100644
--- a/arch/arm64/boot/dts/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm-mustang.dts
@@ -24,3 +24,7 @@
 		reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */
 	};
 };
+
+&serial0 {
+	status = "ok";
+};
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index c5f0a47a137..40aa96ce13c 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -273,8 +273,9 @@
 		};
 
 		serial0: serial@1c020000 {
+			status = "disabled";
 			device_type = "serial";
-			compatible = "ns16550";
+			compatible = "ns16550a";
 			reg = <0 0x1c020000 0x0 0x1000>;
 			reg-shift = <2>;
 			clock-frequency = <10000000>; /* Updated by bootloader */
@@ -282,6 +283,39 @@
 			interrupts = <0x0 0x4c 0x4>;
 		};
 
+		serial1: serial@1c021000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c021000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4d 0x4>;
+		};
+
+		serial2: serial@1c022000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c022000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4e 0x4>;
+		};
+
+		serial3: serial@1c023000 {
+			status = "disabled";
+			device_type = "serial";
+			compatible = "ns16550a";
+			reg = <0 0x1c023000 0x0 0x1000>;
+			reg-shift = <2>;
+			clock-frequency = <10000000>; /* Updated by bootloader */
+			interrupt-parent = <&gic>;
+			interrupts = <0x0 0x4f 0x4>;
+		};
+
 		phy1: phy@1f21a000 {
 			compatible = "apm,xgene-phy";
 			reg = <0x0 0x1f21a000 0x0 0x100>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 157e1d8d9a4..1e52b741d80 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -6,9 +6,18 @@ CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_SWAP=y
+CONFIG_MEMCG_KMEM=y
+CONFIG_CGROUP_HUGETLB=y
 # CONFIG_UTS_NS is not set
 # CONFIG_IPC_NS is not set
 # CONFIG_PID_NS is not set
@@ -27,6 +36,7 @@ CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_XGENE=y
 CONFIG_SMP=y
 CONFIG_PREEMPT=y
+CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_CMA=y
 CONFIG_CMDLINE="console=ttyAMA0"
@@ -42,9 +52,13 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
+CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_DMA_CMA=y
+CONFIG_BLK_DEV_LOOP=y
 CONFIG_VIRTIO_BLK=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
@@ -53,6 +67,8 @@ CONFIG_ATA=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_PATA_OF_PLATFORM=y
 CONFIG_NETDEVICES=y
+CONFIG_TUN=y
+CONFIG_VIRTIO_NET=y
 CONFIG_SMC91X=y
 CONFIG_SMSC911X=y
 # CONFIG_WLAN is not set
@@ -64,6 +80,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_VIRTIO_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 CONFIG_REGULATOR=y
@@ -78,6 +95,7 @@ CONFIG_USB_ISP1760_HCD=y
 CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_MMC_ARMMMCI=y
+CONFIG_VIRTIO_BALLOON=y
 CONFIG_VIRTIO_MMIO=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -85,6 +103,8 @@ CONFIG_EXT3_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 # CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
+CONFIG_FANOTIFY=y
+CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=y
 CONFIG_VFAT_FS=y
@@ -93,6 +113,7 @@ CONFIG_HUGETLBFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_NFS_FS=y
 CONFIG_ROOT_NFS=y
+CONFIG_9P_FS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_VIRTUALIZATION=y
@@ -104,6 +125,7 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_LOCKUP_DETECTOR=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_FTRACE is not set
+CONFIG_SECURITY=y
 CONFIG_CRYPTO_ANSI_CPRNG=y
 CONFIG_ARM64_CRYPTO=y
 CONFIG_CRYPTO_SHA1_ARM64_CE=y
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index 2070a56ecc4..a3f935fde97 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -35,4 +35,4 @@ AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
 CFLAGS_aes-glue-ce.o	:= -DUSE_V8_CRYPTO_EXTENSIONS
 
 $(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
-	$(call if_changed_dep,cc_o_c)
+	$(call if_changed_rule,cc_o_c)
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 60f2f4c1225..79cd911ef88 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -106,7 +106,7 @@ static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
 		aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_enc, rounds, blocks, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -128,7 +128,7 @@ static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
 		aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_dec, rounds, blocks, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -151,7 +151,7 @@ static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
 				first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -174,7 +174,7 @@ static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key_dec, rounds, blocks, walk.iv,
 				first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 	return err;
@@ -243,7 +243,7 @@ static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_enc, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 
@@ -267,7 +267,7 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_dec, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
-		err = blkcipher_walk_done(desc, &walk, 0);
+		err = blkcipher_walk_done(desc, &walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
 	kernel_neon_end();
 
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index b9e6eaf41c9..dc457015884 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -3,14 +3,6 @@
  *
  * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
- * Based on arch/x86/crypto/ghash-pmullni-intel_asm.S
- *
- * Copyright (c) 2009 Intel Corp.
- *   Author: Huang Ying <ying.huang@intel.com>
- *           Vinodh Gopal
- *           Erdinc Ozturk
- *           Deniz Karakoyunlu
- *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published
  * by the Free Software Foundation.
@@ -19,13 +11,15 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-	DATA	.req	v0
-	SHASH	.req	v1
-	IN1	.req	v2
+	SHASH	.req	v0
+	SHASH2	.req	v1
 	T1	.req	v2
 	T2	.req	v3
-	T3	.req	v4
-	VZR	.req	v5
+	MASK	.req	v4
+	XL	.req	v5
+	XM	.req	v6
+	XH	.req	v7
+	IN1	.req	v7
 
 	.text
 	.arch		armv8-a+crypto
@@ -35,61 +29,51 @@
 	 *			   struct ghash_key const *k, const char *head)
 	 */
 ENTRY(pmull_ghash_update)
-	ld1		{DATA.16b}, [x1]
 	ld1		{SHASH.16b}, [x3]
-	eor		VZR.16b, VZR.16b, VZR.16b
+	ld1		{XL.16b}, [x1]
+	movi		MASK.16b, #0xe1
+	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+	shl		MASK.2d, MASK.2d, #57
+	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	/* do the head block first, if supplied */
 	cbz		x4, 0f
-	ld1		{IN1.2d}, [x4]
+	ld1		{T1.2d}, [x4]
 	b		1f
 
-0:	ld1		{IN1.2d}, [x2], #16
+0:	ld1		{T1.2d}, [x2], #16
 	sub		w0, w0, #1
-1:	ext		IN1.16b, IN1.16b, IN1.16b, #8
-CPU_LE(	rev64		IN1.16b, IN1.16b	)
-	eor		DATA.16b, DATA.16b, IN1.16b
 
-	/* multiply DATA by SHASH in GF(2^128) */
-	ext		T2.16b, DATA.16b, DATA.16b, #8
-	ext		T3.16b, SHASH.16b, SHASH.16b, #8
-	eor		T2.16b, T2.16b, DATA.16b
-	eor		T3.16b, T3.16b, SHASH.16b
+1:	/* multiply XL by SHASH in GF(2^128) */
+CPU_LE(	rev64		T1.16b, T1.16b	)
 
-	pmull2		T1.1q, SHASH.2d, DATA.2d	// a1 * b1
-	pmull		DATA.1q, SHASH.1d, DATA.1d	// a0 * b0
-	pmull		T2.1q, T2.1d, T3.1d		// (a1 + a0)(b1 + b0)
-	eor		T2.16b, T2.16b, T1.16b		// (a0 * b1) + (a1 * b0)
-	eor		T2.16b, T2.16b, DATA.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
+	ext		IN1.16b, T1.16b, T1.16b, #8
+	eor		T1.16b, T1.16b, T2.16b
+	eor		XL.16b, XL.16b, IN1.16b
 
-	ext		T3.16b, VZR.16b, T2.16b, #8
-	ext		T2.16b, T2.16b, VZR.16b, #8
-	eor		DATA.16b, DATA.16b, T3.16b
-	eor		T1.16b, T1.16b, T2.16b	// <T1:DATA> is result of
-						// carry-less multiplication
+	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
+	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
 
-	/* first phase of the reduction */
-	shl		T3.2d, DATA.2d, #1
-	eor		T3.16b, T3.16b, DATA.16b
-	shl		T3.2d, T3.2d, #5
-	eor		T3.16b, T3.16b, DATA.16b
-	shl		T3.2d, T3.2d, #57
-	ext		T2.16b, VZR.16b, T3.16b, #8
-	ext		T3.16b, T3.16b, VZR.16b, #8
-	eor		DATA.16b, DATA.16b, T2.16b
-	eor		T1.16b, T1.16b, T3.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		T2.16b, XL.16b, XH.16b
+	eor		XM.16b, XM.16b, T1.16b
+	eor		XM.16b, XM.16b, T2.16b
+	pmull		T2.1q, XL.1d, MASK.1d
 
-	/* second phase of the reduction */
-	ushr		T2.2d, DATA.2d, #5
-	eor		T2.16b, T2.16b, DATA.16b
-	ushr		T2.2d, T2.2d, #1
-	eor		T2.16b, T2.16b, DATA.16b
-	ushr		T2.2d, T2.2d, #1
-	eor		T1.16b, T1.16b, T2.16b
-	eor		DATA.16b, DATA.16b, T1.16b
+	mov		XH.d[0], XM.d[1]
+	mov		XM.d[1], XL.d[0]
+
+	eor		XL.16b, XM.16b, T2.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
+	pmull		XL.1q, XL.1d, MASK.1d
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
 
 	cbnz		w0, 0b
 
-	st1		{DATA.16b}, [x1]
+	st1		{XL.16b}, [x1]
 	ret
 ENDPROC(pmull_ghash_update)
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index b92baf3f68c..833ec1e3f3e 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -67,11 +67,12 @@ static int ghash_update(struct shash_desc *desc, const u8 *src,
 		blocks = len / GHASH_BLOCK_SIZE;
 		len %= GHASH_BLOCK_SIZE;
 
-		kernel_neon_begin_partial(6);
+		kernel_neon_begin_partial(8);
 		pmull_ghash_update(blocks, ctx->digest, src, key,
 				   partial ? ctx->buf : NULL);
 		kernel_neon_end();
 		src += blocks * GHASH_BLOCK_SIZE;
+		partial = 0;
 	}
 	if (len)
 		memcpy(ctx->buf + partial, src, len);
@@ -88,7 +89,7 @@ static int ghash_final(struct shash_desc *desc, u8 *dst)
 
 		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
 
-		kernel_neon_begin_partial(6);
+		kernel_neon_begin_partial(8);
 		pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
 		kernel_neon_end();
 	}
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 42c7eecd2bb..0b3fcf86e6b 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -30,7 +30,6 @@ generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += pci.h
 generic-y += poll.h
-generic-y += posix_types.h
 generic-y += preempt.h
 generic-y += resource.h
 generic-y += rwsem.h
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index a5176cf32da..f2defe1c380 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -138,19 +138,10 @@ static inline void __flush_icache_all(void)
 #define flush_icache_page(vma,page)	do { } while (0)
 
 /*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
- * caches, since the direct-mappings of these pages may contain cached
- * data, we need to do a full cache flush to ensure that writebacks
- * don't corrupt data placed into these pages via the new mappings.
+ * Not required on AArch64 (PIPT or VIPT non-aliasing D-cache).
  */
 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 {
-	/*
-	 * set_pte_at() called from vmap_pte_range() does not
-	 * have a DSB after cleaning the cache line.
-	 */
-	dsb(ish);
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
diff --git a/arch/arm64/include/asm/cachetype.h b/arch/arm64/include/asm/cachetype.h
index 4b23e758d5e..7a2e0762cb4 100644
--- a/arch/arm64/include/asm/cachetype.h
+++ b/arch/arm64/include/asm/cachetype.h
@@ -30,10 +30,14 @@
 
 #ifndef __ASSEMBLY__
 
-static inline u32 icache_policy(void)
-{
-	return (read_cpuid_cachetype() >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK;
-}
+#include <linux/bitops.h>
+
+#define CTR_L1IP(ctr)	(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
+
+#define ICACHEF_ALIASING	BIT(0)
+#define ICACHEF_AIVIVT		BIT(1)
+
+extern unsigned long __icache_flags;
 
 /*
  * Whilst the D-side always behaves as PIPT on AArch64, aliasing is
@@ -41,12 +45,12 @@ static inline u32 icache_policy(void)
  */
 static inline int icache_is_aliasing(void)
 {
-	return icache_policy() != ICACHE_POLICY_PIPT;
+	return test_bit(ICACHEF_ALIASING, &__icache_flags);
 }
 
 static inline int icache_is_aivivt(void)
 {
-	return icache_policy() == ICACHE_POLICY_AIVIVT;
+	return test_bit(ICACHEF_AIVIVT, &__icache_flags);
 }
 
 static inline u32 cache_type_cwg(void)
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
new file mode 100644
index 00000000000..05644308601
--- /dev/null
+++ b/arch/arm64/include/asm/cpu.h
@@ -0,0 +1,59 @@
+/*
+  * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_CPU_H
+#define __ASM_CPU_H
+
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+
+/*
+ * Records attributes of an individual CPU.
+ */
+struct cpuinfo_arm64 {
+	struct cpu	cpu;
+	u32		reg_ctr;
+	u32		reg_cntfrq;
+	u32		reg_dczid;
+	u32		reg_midr;
+
+	u64		reg_id_aa64isar0;
+	u64		reg_id_aa64isar1;
+	u64		reg_id_aa64mmfr0;
+	u64		reg_id_aa64mmfr1;
+	u64		reg_id_aa64pfr0;
+	u64		reg_id_aa64pfr1;
+
+	u32		reg_id_isar0;
+	u32		reg_id_isar1;
+	u32		reg_id_isar2;
+	u32		reg_id_isar3;
+	u32		reg_id_isar4;
+	u32		reg_id_isar5;
+	u32		reg_id_mmfr0;
+	u32		reg_id_mmfr1;
+	u32		reg_id_mmfr2;
+	u32		reg_id_mmfr3;
+	u32		reg_id_pfr0;
+	u32		reg_id_pfr1;
+};
+
+DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
+
+void cpuinfo_store_cpu(void);
+void __init cpuinfo_store_boot_cpu(void);
+
+#endif /* __ASM_CPU_H */
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 27f54a7cc81..379d0b87432 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -18,6 +18,8 @@
 
 #define INVALID_HWID		ULONG_MAX
 
+#define MPIDR_UP_BITMASK	(0x1 << 30)
+#define MPIDR_MT_BITMASK	(0x1 << 24)
 #define MPIDR_HWID_BITMASK	0xff00ffffff
 
 #define MPIDR_LEVEL_BITS_SHIFT	3
@@ -36,15 +38,34 @@
 	__val;								\
 })
 
+#define MIDR_REVISION_MASK	0xf
+#define MIDR_REVISION(midr)	((midr) & MIDR_REVISION_MASK)
+#define MIDR_PARTNUM_SHIFT	4
+#define MIDR_PARTNUM_MASK	(0xfff << MIDR_PARTNUM_SHIFT)
+#define MIDR_PARTNUM(midr)	\
+	(((midr) & MIDR_PARTNUM_MASK) >> MIDR_PARTNUM_SHIFT)
+#define MIDR_ARCHITECTURE_SHIFT	16
+#define MIDR_ARCHITECTURE_MASK	(0xf << MIDR_ARCHITECTURE_SHIFT)
+#define MIDR_ARCHITECTURE(midr)	\
+	(((midr) & MIDR_ARCHITECTURE_MASK) >> MIDR_ARCHITECTURE_SHIFT)
+#define MIDR_VARIANT_SHIFT	20
+#define MIDR_VARIANT_MASK	(0xf << MIDR_VARIANT_SHIFT)
+#define MIDR_VARIANT(midr)	\
+	(((midr) & MIDR_VARIANT_MASK) >> MIDR_VARIANT_SHIFT)
+#define MIDR_IMPLEMENTOR_SHIFT	24
+#define MIDR_IMPLEMENTOR_MASK	(0xff << MIDR_IMPLEMENTOR_SHIFT)
+#define MIDR_IMPLEMENTOR(midr)	\
+	(((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT)
+
 #define ARM_CPU_IMP_ARM		0x41
 #define ARM_CPU_IMP_APM		0x50
 
-#define ARM_CPU_PART_AEM_V8	0xD0F0
-#define ARM_CPU_PART_FOUNDATION	0xD000
-#define ARM_CPU_PART_CORTEX_A53	0xD030
-#define ARM_CPU_PART_CORTEX_A57	0xD070
+#define ARM_CPU_PART_AEM_V8	0xD0F
+#define ARM_CPU_PART_FOUNDATION	0xD00
+#define ARM_CPU_PART_CORTEX_A57	0xD07
+#define ARM_CPU_PART_CORTEX_A53	0xD03
 
-#define APM_CPU_PART_POTENZA	0x0000
+#define APM_CPU_PART_POTENZA	0x000
 
 #ifndef __ASSEMBLY__
 
@@ -65,12 +86,12 @@ static inline u64 __attribute_const__ read_cpuid_mpidr(void)
 
 static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
 {
-	return (read_cpuid_id() & 0xFF000000) >> 24;
+	return MIDR_IMPLEMENTOR(read_cpuid_id());
 }
 
 static inline unsigned int __attribute_const__ read_cpuid_part_number(void)
 {
-	return (read_cpuid_id() & 0xFFF0);
+	return MIDR_PARTNUM(read_cpuid_id());
 }
 
 static inline u32 __attribute_const__ read_cpuid_cachetype(void)
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 3a4572ec327..dc82e52acdb 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -26,8 +26,6 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define ARCH_HAS_DMA_GET_REQUIRED_MASK
-
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
 extern struct dma_map_ops coherent_swiotlb_dma_ops;
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 5a46c4e7f53..a34fd3b12e2 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -2,6 +2,7 @@
 #define _ASM_EFI_H
 
 #include <asm/io.h>
+#include <asm/neon.h>
 
 #ifdef CONFIG_EFI
 extern void efi_init(void);
@@ -11,4 +12,36 @@ extern void efi_idmap_init(void);
 #define efi_idmap_init()
 #endif
 
+#define efi_call_virt(f, ...)						\
+({									\
+	efi_##f##_t *__f = efi.systab->runtime->f;			\
+	efi_status_t __s;						\
+									\
+	kernel_neon_begin();						\
+	__s = __f(__VA_ARGS__);						\
+	kernel_neon_end();						\
+	__s;								\
+})
+
+#define __efi_call_virt(f, ...)						\
+({									\
+	efi_##f##_t *__f = efi.systab->runtime->f;			\
+									\
+	kernel_neon_begin();						\
+	__f(__VA_ARGS__);						\
+	kernel_neon_end();						\
+})
+
+/* arch specific definitions used by the stub code */
+
+/*
+ * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from
+ * start of kernel and may not cross a 2MiB boundary. We set alignment to
+ * 2MiB so we know it won't cross a 2MiB boundary.
+ */
+#define EFI_FDT_ALIGN	SZ_2M   /* used by allocate_new_fdt_and_exit_boot() */
+#define MAX_FDT_OFFSET	SZ_512M
+
+#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
+
 #endif /* _ASM_EFI_H */
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index 768414d55e6..007618b8188 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -40,6 +40,19 @@
 	str	w\tmpnr, [\state, #16 * 2 + 4]
 .endm
 
+.macro fpsimd_restore_fpcr state, tmp
+	/*
+	 * Writes to fpcr may be self-synchronising, so avoid restoring
+	 * the register if it hasn't changed.
+	 */
+	mrs	\tmp, fpcr
+	cmp	\tmp, \state
+	b.eq	9999f
+	msr	fpcr, \state
+9999:
+.endm
+
+/* Clobbers \state */
 .macro fpsimd_restore state, tmpnr
 	ldp	q0, q1, [\state, #16 * 0]
 	ldp	q2, q3, [\state, #16 * 2]
@@ -60,7 +73,7 @@
 	ldr	w\tmpnr, [\state, #16 * 2]
 	msr	fpsr, x\tmpnr
 	ldr	w\tmpnr, [\state, #16 * 2 + 4]
-	msr	fpcr, x\tmpnr
+	fpsimd_restore_fpcr x\tmpnr, \state
 .endm
 
 .altmacro
@@ -84,7 +97,7 @@
 .macro fpsimd_restore_partial state, tmpnr1, tmpnr2
 	ldp	w\tmpnr1, w\tmpnr2, [\state]
 	msr	fpsr, x\tmpnr1
-	msr	fpcr, x\tmpnr2
+	fpsimd_restore_fpcr x\tmpnr2, x\tmpnr1
 	adr	x\tmpnr1, 0f
 	ldr	w\tmpnr2, [\state, #8]
 	add	\state, \state, x\tmpnr2, lsl #4
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 993bce527b8..ccc7087d3c4 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -41,11 +41,7 @@
  * The module space lives between the addresses given by TASK_SIZE
  * and PAGE_OFFSET - it must be within 128MB of the kernel text.
  */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define VA_BITS			(42)
-#else
-#define VA_BITS			(39)
-#endif
+#define VA_BITS			(CONFIG_ARM64_VA_BITS)
 #define PAGE_OFFSET		(UL(0xffffffffffffffff) << (VA_BITS - 1))
 #define MODULES_END		(PAGE_OFFSET)
 #define MODULES_VADDR		(MODULES_END - SZ_64M)
@@ -56,6 +52,8 @@
 #define TASK_SIZE_32		UL(0x100000000)
 #define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
 				TASK_SIZE_32 : TASK_SIZE_64)
+#define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
+				TASK_SIZE_32 : TASK_SIZE_64)
 #else
 #define TASK_SIZE		TASK_SIZE_64
 #endif /* CONFIG_COMPAT */
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 46bf66628b6..7a3f462133b 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -31,14 +31,26 @@
 /* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
 #define __HAVE_ARCH_GATE_AREA		1
 
-#ifndef __ASSEMBLY__
-
+/*
+ * The idmap and swapper page tables need some space reserved in the kernel
+ * image. Both require pgd, pud (4 levels only) and pmd tables to (section)
+ * map the kernel. With the 64K page configuration, swapper and idmap need to
+ * map to pte level. The swapper also maps the FDT (see __create_page_tables
+ * for more information).
+ */
 #ifdef CONFIG_ARM64_64K_PAGES
-#include <asm/pgtable-2level-types.h>
+#define SWAPPER_PGTABLE_LEVELS	(CONFIG_ARM64_PGTABLE_LEVELS)
 #else
-#include <asm/pgtable-3level-types.h>
+#define SWAPPER_PGTABLE_LEVELS	(CONFIG_ARM64_PGTABLE_LEVELS - 1)
 #endif
 
+#define SWAPPER_DIR_SIZE	(SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
+#define IDMAP_DIR_SIZE		(SWAPPER_DIR_SIZE)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/pgtable-types.h>
+
 extern void __cpu_clear_user_page(void *p, unsigned long user);
 extern void __cpu_copy_user_page(void *to, const void *from,
 				 unsigned long user);
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 9bea6e74a00..d5bed02073d 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
 
 #define check_pgt_cache()		do { } while (0)
 
-#ifndef CONFIG_ARM64_64K_PAGES
+#if CONFIG_ARM64_PGTABLE_LEVELS > 2
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
@@ -44,7 +44,27 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 	set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE));
 }
 
-#endif	/* CONFIG_ARM64_64K_PAGES */
+#endif	/* CONFIG_ARM64_PGTABLE_LEVELS > 2 */
+
+#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT);
+}
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
+	free_page((unsigned long)pud);
+}
+
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+{
+	set_pgd(pgd, __pgd(__pa(pud) | PUD_TYPE_TABLE));
+}
+
+#endif	/* CONFIG_ARM64_PGTABLE_LEVELS > 3 */
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
diff --git a/arch/arm64/include/asm/pgtable-2level-hwdef.h b/arch/arm64/include/asm/pgtable-2level-hwdef.h
deleted file mode 100644
index 2593b490c56..00000000000
--- a/arch/arm64/include/asm/pgtable-2level-hwdef.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_PGTABLE_2LEVEL_HWDEF_H
-#define __ASM_PGTABLE_2LEVEL_HWDEF_H
-
-/*
- * With LPAE and 64KB pages, there are 2 levels of page tables. Each level has
- * 8192 entries of 8 bytes each, occupying a 64KB page. Levels 0 and 1 are not
- * used. The 2nd level table (PGD for Linux) can cover a range of 4TB, each
- * entry representing 512MB. The user and kernel address spaces are limited to
- * 4TB in the 64KB page configuration.
- */
-#define PTRS_PER_PTE		8192
-#define PTRS_PER_PGD		8192
-
-/*
- * PGDIR_SHIFT determines the size a top-level page table entry can map.
- */
-#define PGDIR_SHIFT		29
-#define PGDIR_SIZE		(_AC(1, UL) << PGDIR_SHIFT)
-#define PGDIR_MASK		(~(PGDIR_SIZE-1))
-
-/*
- * section address mask and size definitions.
- */
-#define SECTION_SHIFT		29
-#define SECTION_SIZE		(_AC(1, UL) << SECTION_SHIFT)
-#define SECTION_MASK		(~(SECTION_SIZE-1))
-
-#endif
diff --git a/arch/arm64/include/asm/pgtable-2level-types.h b/arch/arm64/include/asm/pgtable-2level-types.h
deleted file mode 100644
index 5f101e63dfc..00000000000
--- a/arch/arm64/include/asm/pgtable-2level-types.h
+++ /dev/null
@@ -1,62 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_PGTABLE_2LEVEL_TYPES_H
-#define __ASM_PGTABLE_2LEVEL_TYPES_H
-
-#include <asm/types.h>
-
-typedef u64 pteval_t;
-typedef u64 pgdval_t;
-typedef pgdval_t pmdval_t;
-
-#undef STRICT_MM_TYPECHECKS
-
-#ifdef STRICT_MM_TYPECHECKS
-
-/*
- * These are used to make use of C type-checking..
- */
-typedef struct { pteval_t pte; } pte_t;
-typedef struct { pgdval_t pgd; } pgd_t;
-typedef struct { pteval_t pgprot; } pgprot_t;
-
-#define pte_val(x)      ((x).pte)
-#define pgd_val(x)	((x).pgd)
-#define pgprot_val(x)   ((x).pgprot)
-
-#define __pte(x)        ((pte_t) { (x) } )
-#define __pgd(x)	((pgd_t) { (x) } )
-#define __pgprot(x)     ((pgprot_t) { (x) } )
-
-#else	/* !STRICT_MM_TYPECHECKS */
-
-typedef pteval_t pte_t;
-typedef pgdval_t pgd_t;
-typedef pteval_t pgprot_t;
-
-#define pte_val(x)	(x)
-#define pgd_val(x)	(x)
-#define pgprot_val(x)	(x)
-
-#define __pte(x)	(x)
-#define __pgd(x)	(x)
-#define __pgprot(x)	(x)
-
-#endif	/* STRICT_MM_TYPECHECKS */
-
-#include <asm-generic/pgtable-nopmd.h>
-
-#endif	/* __ASM_PGTABLE_2LEVEL_TYPES_H */
diff --git a/arch/arm64/include/asm/pgtable-3level-hwdef.h b/arch/arm64/include/asm/pgtable-3level-hwdef.h
deleted file mode 100644
index 3dbf941d776..00000000000
--- a/arch/arm64/include/asm/pgtable-3level-hwdef.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_PGTABLE_3LEVEL_HWDEF_H
-#define __ASM_PGTABLE_3LEVEL_HWDEF_H
-
-/*
- * With LPAE and 4KB pages, there are 3 levels of page tables. Each level has
- * 512 entries of 8 bytes each, occupying a 4K page. The first level table
- * covers a range of 512GB, each entry representing 1GB. The user and kernel
- * address spaces are limited to 512GB each.
- */
-#define PTRS_PER_PTE		512
-#define PTRS_PER_PMD		512
-#define PTRS_PER_PGD		512
-
-/*
- * PGDIR_SHIFT determines the size a top-level page table entry can map.
- */
-#define PGDIR_SHIFT		30
-#define PGDIR_SIZE		(_AC(1, UL) << PGDIR_SHIFT)
-#define PGDIR_MASK		(~(PGDIR_SIZE-1))
-
-/*
- * PMD_SHIFT determines the size a middle-level page table entry can map.
- */
-#define PMD_SHIFT		21
-#define PMD_SIZE		(_AC(1, UL) << PMD_SHIFT)
-#define PMD_MASK		(~(PMD_SIZE-1))
-
-/*
- * section address mask and size definitions.
- */
-#define SECTION_SHIFT		21
-#define SECTION_SIZE		(_AC(1, UL) << SECTION_SHIFT)
-#define SECTION_MASK		(~(SECTION_SIZE-1))
-
-#endif
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 955e8c5f0af..88174e0bfaf 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -16,18 +16,50 @@
 #ifndef __ASM_PGTABLE_HWDEF_H
 #define __ASM_PGTABLE_HWDEF_H
 
-#ifdef CONFIG_ARM64_64K_PAGES
-#include <asm/pgtable-2level-hwdef.h>
-#else
-#include <asm/pgtable-3level-hwdef.h>
+#define PTRS_PER_PTE		(1 << (PAGE_SHIFT - 3))
+
+/*
+ * PMD_SHIFT determines the size a level 2 page table entry can map.
+ */
+#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+#define PMD_SHIFT		((PAGE_SHIFT - 3) * 2 + 3)
+#define PMD_SIZE		(_AC(1, UL) << PMD_SHIFT)
+#define PMD_MASK		(~(PMD_SIZE-1))
+#define PTRS_PER_PMD		PTRS_PER_PTE
+#endif
+
+/*
+ * PUD_SHIFT determines the size a level 1 page table entry can map.
+ */
+#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+#define PUD_SHIFT		((PAGE_SHIFT - 3) * 3 + 3)
+#define PUD_SIZE		(_AC(1, UL) << PUD_SHIFT)
+#define PUD_MASK		(~(PUD_SIZE-1))
+#define PTRS_PER_PUD		PTRS_PER_PTE
 #endif
 
 /*
+ * PGDIR_SHIFT determines the size a top-level page table entry can map
+ * (depending on the configuration, this level can be 0, 1 or 2).
+ */
+#define PGDIR_SHIFT		((PAGE_SHIFT - 3) * CONFIG_ARM64_PGTABLE_LEVELS + 3)
+#define PGDIR_SIZE		(_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+#define PTRS_PER_PGD		(1 << (VA_BITS - PGDIR_SHIFT))
+
+/*
+ * Section address mask and size definitions.
+ */
+#define SECTION_SHIFT		PMD_SHIFT
+#define SECTION_SIZE		(_AC(1, UL) << SECTION_SHIFT)
+#define SECTION_MASK		(~(SECTION_SIZE-1))
+
+/*
  * Hardware page table definitions.
  *
  * Level 1 descriptor (PUD).
  */
-
+#define PUD_TYPE_TABLE		(_AT(pudval_t, 3) << 0)
 #define PUD_TABLE_BIT		(_AT(pgdval_t, 1) << 1)
 #define PUD_TYPE_MASK		(_AT(pgdval_t, 3) << 0)
 #define PUD_TYPE_SECT		(_AT(pgdval_t, 1) << 0)
diff --git a/arch/arm64/include/asm/pgtable-3level-types.h b/arch/arm64/include/asm/pgtable-types.h
index 4e94424938a..ca9df80af89 100644
--- a/arch/arm64/include/asm/pgtable-3level-types.h
+++ b/arch/arm64/include/asm/pgtable-types.h
@@ -1,7 +1,10 @@
 /*
- * Copyright (C) 2012 ARM Ltd.
+ * Page table types definitions.
  *
- * This program is free software; you can redistribute it and/or modify
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  *
@@ -13,13 +16,15 @@
  * You should have received a copy of the GNU General Public License
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-#ifndef __ASM_PGTABLE_3LEVEL_TYPES_H
-#define __ASM_PGTABLE_3LEVEL_TYPES_H
+
+#ifndef __ASM_PGTABLE_TYPES_H
+#define __ASM_PGTABLE_TYPES_H
 
 #include <asm/types.h>
 
 typedef u64 pteval_t;
 typedef u64 pmdval_t;
+typedef u64 pudval_t;
 typedef u64 pgdval_t;
 
 #undef STRICT_MM_TYPECHECKS
@@ -30,39 +35,61 @@ typedef u64 pgdval_t;
  * These are used to make use of C type-checking..
  */
 typedef struct { pteval_t pte; } pte_t;
+#define pte_val(x)	((x).pte)
+#define __pte(x)	((pte_t) { (x) } )
+
+#if CONFIG_ARM64_PGTABLE_LEVELS > 2
 typedef struct { pmdval_t pmd; } pmd_t;
-typedef struct { pgdval_t pgd; } pgd_t;
-typedef struct { pteval_t pgprot; } pgprot_t;
+#define pmd_val(x)	((x).pmd)
+#define __pmd(x)	((pmd_t) { (x) } )
+#endif
 
-#define pte_val(x)      ((x).pte)
-#define pmd_val(x)      ((x).pmd)
-#define pgd_val(x)	((x).pgd)
-#define pgprot_val(x)   ((x).pgprot)
+#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+typedef struct { pudval_t pud; } pud_t;
+#define pud_val(x)	((x).pud)
+#define __pud(x)	((pud_t) { (x) } )
+#endif
 
-#define __pte(x)        ((pte_t) { (x) } )
-#define __pmd(x)        ((pmd_t) { (x) } )
+typedef struct { pgdval_t pgd; } pgd_t;
+#define pgd_val(x)	((x).pgd)
 #define __pgd(x)	((pgd_t) { (x) } )
-#define __pgprot(x)     ((pgprot_t) { (x) } )
+
+typedef struct { pteval_t pgprot; } pgprot_t;
+#define pgprot_val(x)	((x).pgprot)
+#define __pgprot(x)	((pgprot_t) { (x) } )
 
 #else	/* !STRICT_MM_TYPECHECKS */
 
 typedef pteval_t pte_t;
-typedef pmdval_t pmd_t;
-typedef pgdval_t pgd_t;
-typedef pteval_t pgprot_t;
-
 #define pte_val(x)	(x)
-#define pmd_val(x)	(x)
-#define pgd_val(x)	(x)
-#define pgprot_val(x)	(x)
-
 #define __pte(x)	(x)
+
+#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+typedef pmdval_t pmd_t;
+#define pmd_val(x)	(x)
 #define __pmd(x)	(x)
+#endif
+
+#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+typedef pudval_t pud_t;
+#define pud_val(x)	(x)
+#define __pud(x)	(x)
+#endif
+
+typedef pgdval_t pgd_t;
+#define pgd_val(x)	(x)
 #define __pgd(x)	(x)
+
+typedef pteval_t pgprot_t;
+#define pgprot_val(x)	(x)
 #define __pgprot(x)	(x)
 
-#endif	/* STRICT_MM_TYPECHECKS */
+#endif /* STRICT_MM_TYPECHECKS */
 
+#if CONFIG_ARM64_PGTABLE_LEVELS == 2
+#include <asm-generic/pgtable-nopmd.h>
+#elif CONFIG_ARM64_PGTABLE_LEVELS == 3
 #include <asm-generic/pgtable-nopud.h>
+#endif
 
-#endif	/* __ASM_PGTABLE_3LEVEL_TYPES_H */
+#endif	/* __ASM_PGTABLE_TYPES_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 598cc384fc1..ffe1ba0506d 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -33,9 +33,16 @@
 
 /*
  * VMALLOC and SPARSEMEM_VMEMMAP ranges.
+ *
+ * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array
+ *	(rounded up to PUD_SIZE).
+ * VMALLOC_START: beginning of the kernel VA space
+ * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space,
+ *	fixed mappings and modules
  */
+#define VMEMMAP_SIZE		ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE)
 #define VMALLOC_START		(UL(0xffffffffffffffff) << VA_BITS)
-#define VMALLOC_END		(PAGE_OFFSET - UL(0x400000000) - SZ_64K)
+#define VMALLOC_END		(PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
 
 #define vmemmap			((struct page *)(VMALLOC_END + SZ_64K))
 
@@ -44,14 +51,9 @@
 #ifndef __ASSEMBLY__
 extern void __pte_error(const char *file, int line, unsigned long val);
 extern void __pmd_error(const char *file, int line, unsigned long val);
+extern void __pud_error(const char *file, int line, unsigned long val);
 extern void __pgd_error(const char *file, int line, unsigned long val);
 
-#define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
-#ifndef CONFIG_ARM64_64K_PAGES
-#define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd_val(pmd))
-#endif
-#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
-
 #ifdef CONFIG_SMP
 #define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
@@ -112,6 +114,8 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 extern struct page *empty_zero_page;
 #define ZERO_PAGE(vaddr)	(empty_zero_page)
 
+#define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
+
 #define pte_pfn(pte)		((pte_val(pte) & PHYS_MASK) >> PAGE_SHIFT)
 
 #define pfn_pte(pfn,prot)	(__pte(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
@@ -119,6 +123,10 @@ extern struct page *empty_zero_page;
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_clear(mm,addr,ptep)	set_pte(ptep, __pte(0))
 #define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))
+
+/* Find an entry in the third-level page table. */
+#define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+
 #define pte_offset_kernel(dir,addr)	(pmd_page_vaddr(*(dir)) + pte_index(addr))
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
@@ -138,6 +146,8 @@ extern struct page *empty_zero_page;
 
 #define pte_valid_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
+#define pte_valid_not_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
@@ -184,6 +194,15 @@ static inline pte_t pte_mkspecial(pte_t pte)
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
+
+	/*
+	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
+	 * or update_mmu_cache() have the necessary barriers.
+	 */
+	if (pte_valid_not_user(pte)) {
+		dsb(ishst);
+		isb();
+	}
 }
 
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
@@ -246,7 +265,7 @@ static inline pmd_t pte_pmd(pte_t pte)
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) &= ~PMD_TYPE_MASK))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
@@ -292,7 +311,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 #define pmd_sect(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
 				 PMD_TYPE_SECT)
 
-#ifdef ARM64_64K_PAGES
+#ifdef CONFIG_ARM64_64K_PAGES
 #define pud_sect(pud)		(0)
 #else
 #define pud_sect(pud)		((pud_val(pud) & PUD_TYPE_MASK) == \
@@ -303,6 +322,7 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	*pmdp = pmd;
 	dsb(ishst);
+	isb();
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -323,7 +343,9 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
  */
 #define mk_pte(page,prot)	pfn_pte(page_to_pfn(page),prot)
 
-#ifndef CONFIG_ARM64_64K_PAGES
+#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+
+#define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd_val(pmd))
 
 #define pud_none(pud)		(!pud_val(pud))
 #define pud_bad(pud)		(!(pud_val(pud) & 2))
@@ -333,6 +355,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 {
 	*pudp = pud;
 	dsb(ishst);
+	isb();
 }
 
 static inline void pud_clear(pud_t *pudp)
@@ -345,7 +368,51 @@ static inline pmd_t *pud_page_vaddr(pud_t pud)
 	return __va(pud_val(pud) & PHYS_MASK & (s32)PAGE_MASK);
 }
 
-#endif	/* CONFIG_ARM64_64K_PAGES */
+/* Find an entry in the second-level page table. */
+#define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
+{
+	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
+}
+
+#endif	/* CONFIG_ARM64_PGTABLE_LEVELS > 2 */
+
+#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+
+#define pud_ERROR(pud)		__pud_error(__FILE__, __LINE__, pud_val(pud))
+
+#define pgd_none(pgd)		(!pgd_val(pgd))
+#define pgd_bad(pgd)		(!(pgd_val(pgd) & 2))
+#define pgd_present(pgd)	(pgd_val(pgd))
+
+static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	*pgdp = pgd;
+	dsb(ishst);
+}
+
+static inline void pgd_clear(pgd_t *pgdp)
+{
+	set_pgd(pgdp, __pgd(0));
+}
+
+static inline pud_t *pgd_page_vaddr(pgd_t pgd)
+{
+	return __va(pgd_val(pgd) & PHYS_MASK & (s32)PAGE_MASK);
+}
+
+/* Find an entry in the frst-level page table. */
+#define pud_index(addr)		(((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+
+static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr)
+{
+	return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(addr);
+}
+
+#endif  /* CONFIG_ARM64_PGTABLE_LEVELS > 3 */
+
+#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
 
 /* to find an entry in a page-table-directory */
 #define pgd_index(addr)		(((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
@@ -355,18 +422,6 @@ static inline pmd_t *pud_page_vaddr(pud_t pud)
 /* to find an entry in a kernel page-table-directory */
 #define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
 
-/* Find an entry in the second-level page table.. */
-#ifndef CONFIG_ARM64_64K_PAGES
-#define pmd_index(addr)		(((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
-static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
-{
-	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(addr);
-}
-#endif
-
-/* Find an entry in the third-level page table.. */
-#define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
@@ -383,9 +438,6 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
-#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
-#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
-
 /*
  * Encode and decode a swap entry:
  *	bits 0-1:	present (must be zero)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 34de2a8f7d9..3df21feeabd 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -129,6 +129,7 @@ extern void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
 #define cpu_relax()			barrier()
+#define cpu_relax_lowlatency()                cpu_relax()
 
 /* Thread switching */
 extern struct task_struct *cpu_switch_to(struct task_struct *prev,
@@ -137,8 +138,8 @@ extern struct task_struct *cpu_switch_to(struct task_struct *prev,
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 
-#define KSTK_EIP(tsk)	task_pt_regs(tsk)->pc
-#define KSTK_ESP(tsk)	task_pt_regs(tsk)->sp
+#define KSTK_EIP(tsk)	((unsigned long)task_pt_regs(tsk)->pc)
+#define KSTK_ESP(tsk)	((unsigned long)task_pt_regs(tsk)->sp)
 
 /*
  * Prefetching support
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index a429b5940be..501000fadb6 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -21,6 +21,10 @@
 
 #include <uapi/asm/ptrace.h>
 
+/* Current Exception Level values, as contained in CurrentEL */
+#define CurrentEL_EL1		(1 << 2)
+#define CurrentEL_EL2		(2 << 2)
+
 /* AArch32-specific ptrace requests */
 #define COMPAT_PTRACE_GETREGS		12
 #define COMPAT_PTRACE_SETREGS		13
diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h
new file mode 100644
index 00000000000..fe5e287dc56
--- /dev/null
+++ b/arch/arm64/include/asm/stackprotector.h
@@ -0,0 +1,38 @@
+/*
+ * GCC stack protector support.
+ *
+ * Stack protector works by putting predefined pattern at the start of
+ * the stack frame and verifying that it hasn't been overwritten when
+ * returning from the function.  The pattern is called stack canary
+ * and gcc expects it to be defined by a global variable called
+ * "__stack_chk_guard" on ARM.  This unfortunately means that on SMP
+ * we cannot have a different canary value per task.
+ */
+
+#ifndef __ASM_STACKPROTECTOR_H
+#define __ASM_STACKPROTECTOR_H
+
+#include <linux/random.h>
+#include <linux/version.h>
+
+extern unsigned long __stack_chk_guard;
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	unsigned long canary;
+
+	/* Try to get a semi random initial value. */
+	get_random_bytes(&canary, sizeof(canary));
+	canary ^= LINUX_VERSION_CODE;
+
+	current->stack_canary = canary;
+	__stack_chk_guard = current->stack_canary;
+}
+
+#endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 383771eb0b8..709a574468f 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_SYSCALL_H
 #define __ASM_SYSCALL_H
 
+#include <uapi/linux/audit.h>
+#include <linux/compat.h>
 #include <linux/err.h>
 
 extern const void *sys_call_table[];
@@ -105,4 +107,16 @@ static inline void syscall_set_arguments(struct task_struct *task,
 	memcpy(&regs->regs[i], args, n * sizeof(args[0]));
 }
 
+/*
+ * We don't care about endianness (__AUDIT_ARCH_LE bit) here because
+ * AArch64 has the same system calls both on little- and big- endian.
+ */
+static inline int syscall_get_arch(void)
+{
+	if (is_compat_task())
+		return AUDIT_ARCH_ARM;
+
+	return AUDIT_ARCH_AARCH64;
+}
+
 #endif	/* __ASM_SYSCALL_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
new file mode 100644
index 00000000000..5c89df0acbc
--- /dev/null
+++ b/arch/arm64/include/asm/sysreg.h
@@ -0,0 +1,60 @@
+/*
+ * Macros for accessing system registers with older binutils.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ASM_SYSREG_H
+#define __ASM_SYSREG_H
+
+#define sys_reg(op0, op1, crn, crm, op2) \
+	((((op0)-2)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
+
+#ifdef __ASSEMBLY__
+
+	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
+	.equ	__reg_num_x\num, \num
+	.endr
+	.equ	__reg_num_xzr, 31
+
+	.macro	mrs_s, rt, sreg
+	.inst	0xd5300000|(\sreg)|(__reg_num_\rt)
+	.endm
+
+	.macro	msr_s, sreg, rt
+	.inst	0xd5100000|(\sreg)|(__reg_num_\rt)
+	.endm
+
+#else
+
+asm(
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
+"	.equ	__reg_num_x\\num, \\num\n"
+"	.endr\n"
+"	.equ	__reg_num_xzr, 31\n"
+"\n"
+"	.macro	mrs_s, rt, sreg\n"
+"	.inst	0xd5300000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.endm\n"
+"\n"
+"	.macro	msr_s, sreg, rt\n"
+"	.inst	0xd5100000|(\\sreg)|(__reg_num_\\rt)\n"
+"	.endm\n"
+);
+
+#endif
+
+#endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index e40b6d06d51..45108d802f5 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -103,6 +103,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NEED_RESCHED	1
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
+#define TIF_NOHZ		7
 #define TIF_SYSCALL_TRACE	8
 #define TIF_SYSCALL_AUDIT	9
 #define TIF_SYSCALL_TRACEPOINT	10
@@ -118,6 +119,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_FOREIGN_FPSTATE	(1 << TIF_FOREIGN_FPSTATE)
+#define _TIF_NOHZ		(1 << TIF_NOHZ)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
@@ -128,7 +130,8 @@ static inline struct thread_info *current_thread_info(void)
 				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
-				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP)
+				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
+				 _TIF_NOHZ)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_THREAD_INFO_H */
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 80e2c08900d..62731ef9749 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -91,7 +91,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 	tlb_remove_page(tlb, pte);
 }
 
-#ifndef CONFIG_ARM64_64K_PAGES
+#if CONFIG_ARM64_PGTABLE_LEVELS > 2
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
@@ -100,6 +100,15 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 }
 #endif
 
+#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
+				  unsigned long addr)
+{
+	tlb_add_flush(tlb, addr);
+	tlb_remove_page(tlb, virt_to_page(pudp));
+}
+#endif
+
 static inline void __tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp,
 						unsigned long address)
 {
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index b9349c4513e..73f0ce570fb 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -98,8 +98,8 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 	dsb(ish);
 }
 
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-					unsigned long start, unsigned long end)
+static inline void __flush_tlb_range(struct vm_area_struct *vma,
+				     unsigned long start, unsigned long end)
 {
 	unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48;
 	unsigned long addr;
@@ -112,7 +112,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	dsb(ish);
 }
 
-static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+static inline void __flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
 	start >>= 12;
@@ -122,6 +122,30 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
 		asm("tlbi vaae1is, %0" : : "r"(addr));
 	dsb(ish);
+	isb();
+}
+
+/*
+ * This is meant to avoid soft lock-ups on large TLB flushing ranges and not
+ * necessarily a performance improvement.
+ */
+#define MAX_TLB_RANGE	(1024UL << PAGE_SHIFT)
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+	if ((end - start) <= MAX_TLB_RANGE)
+		__flush_tlb_range(vma, start, end);
+	else
+		flush_tlb_mm(vma->vm_mm);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	if ((end - start) <= MAX_TLB_RANGE)
+		__flush_tlb_kernel_range(start, end);
+	else
+		flush_tlb_all();
 }
 
 /*
@@ -131,8 +155,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 				    unsigned long addr, pte_t *ptep)
 {
 	/*
-	 * set_pte() does not have a DSB, so make sure that the page table
-	 * write is visible.
+	 * set_pte() does not have a DSB for user mappings, so make sure that
+	 * the page table write is visible.
 	 */
 	dsb(ishst);
 }
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index e5f47df00c2..4bc95d27e06 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -26,7 +26,24 @@
 #define __ARCH_WANT_COMPAT_SYS_SENDFILE
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_VFORK
+
+/*
+ * Compat syscall numbers used by the AArch64 kernel.
+ */
+#define __NR_compat_restart_syscall	0
+#define __NR_compat_sigreturn		119
+#define __NR_compat_rt_sigreturn	173
+
+/*
+ * The following SVCs are ARM private.
+ */
+#define __ARM_NR_COMPAT_BASE		0x0f0000
+#define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
+#define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
+
+#define __NR_compat_syscalls		383
 #endif
+
 #define __ARCH_WANT_SYS_CLONE
 #include <uapi/asm/unistd.h>
 
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index c8d8fc17bd5..e242600c404 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -21,403 +21,769 @@
 #define __SYSCALL(x, y)
 #endif
 
-__SYSCALL(0,   sys_restart_syscall)
-__SYSCALL(1,   sys_exit)
-__SYSCALL(2,   sys_fork)
-__SYSCALL(3,   sys_read)
-__SYSCALL(4,   sys_write)
-__SYSCALL(5,   compat_sys_open)
-__SYSCALL(6,   sys_close)
-__SYSCALL(7,   sys_ni_syscall)			/* 7 was sys_waitpid */
-__SYSCALL(8,   sys_creat)
-__SYSCALL(9,   sys_link)
-__SYSCALL(10,  sys_unlink)
-__SYSCALL(11,  compat_sys_execve)
-__SYSCALL(12,  sys_chdir)
-__SYSCALL(13,  sys_ni_syscall)			/* 13 was sys_time */
-__SYSCALL(14,  sys_mknod)
-__SYSCALL(15,  sys_chmod)
-__SYSCALL(16,  sys_lchown16)
-__SYSCALL(17,  sys_ni_syscall)			/* 17 was sys_break */
-__SYSCALL(18,  sys_ni_syscall)			/* 18 was sys_stat */
-__SYSCALL(19,  compat_sys_lseek)
-__SYSCALL(20,  sys_getpid)
-__SYSCALL(21,  compat_sys_mount)
-__SYSCALL(22,  sys_ni_syscall)			/* 22 was sys_umount */
-__SYSCALL(23,  sys_setuid16)
-__SYSCALL(24,  sys_getuid16)
-__SYSCALL(25,  sys_ni_syscall)			/* 25 was sys_stime */
-__SYSCALL(26,  compat_sys_ptrace)
-__SYSCALL(27,  sys_ni_syscall)			/* 27 was sys_alarm */
-__SYSCALL(28,  sys_ni_syscall)			/* 28 was sys_fstat */
-__SYSCALL(29,  sys_pause)
-__SYSCALL(30,  sys_ni_syscall)			/* 30 was sys_utime */
-__SYSCALL(31,  sys_ni_syscall)			/* 31 was sys_stty */
-__SYSCALL(32,  sys_ni_syscall)			/* 32 was sys_gtty */
-__SYSCALL(33,  sys_access)
-__SYSCALL(34,  sys_nice)
-__SYSCALL(35,  sys_ni_syscall)			/* 35 was sys_ftime */
-__SYSCALL(36,  sys_sync)
-__SYSCALL(37,  sys_kill)
-__SYSCALL(38,  sys_rename)
-__SYSCALL(39,  sys_mkdir)
-__SYSCALL(40,  sys_rmdir)
-__SYSCALL(41,  sys_dup)
-__SYSCALL(42,  sys_pipe)
-__SYSCALL(43,  compat_sys_times)
-__SYSCALL(44,  sys_ni_syscall)			/* 44 was sys_prof */
-__SYSCALL(45,  sys_brk)
-__SYSCALL(46,  sys_setgid16)
-__SYSCALL(47,  sys_getgid16)
-__SYSCALL(48,  sys_ni_syscall)			/* 48 was sys_signal */
-__SYSCALL(49,  sys_geteuid16)
-__SYSCALL(50,  sys_getegid16)
-__SYSCALL(51,  sys_acct)
-__SYSCALL(52,  sys_umount)
-__SYSCALL(53,  sys_ni_syscall)			/* 53 was sys_lock */
-__SYSCALL(54,  compat_sys_ioctl)
-__SYSCALL(55,  compat_sys_fcntl)
-__SYSCALL(56,  sys_ni_syscall)			/* 56 was sys_mpx */
-__SYSCALL(57,  sys_setpgid)
-__SYSCALL(58,  sys_ni_syscall)			/* 58 was sys_ulimit */
-__SYSCALL(59,  sys_ni_syscall)			/* 59 was sys_olduname */
-__SYSCALL(60,  sys_umask)
-__SYSCALL(61,  sys_chroot)
-__SYSCALL(62,  compat_sys_ustat)
-__SYSCALL(63,  sys_dup2)
-__SYSCALL(64,  sys_getppid)
-__SYSCALL(65,  sys_getpgrp)
-__SYSCALL(66,  sys_setsid)
-__SYSCALL(67,  compat_sys_sigaction)
-__SYSCALL(68,  sys_ni_syscall)			/* 68 was sys_sgetmask */
-__SYSCALL(69,  sys_ni_syscall)			/* 69 was sys_ssetmask */
-__SYSCALL(70,  sys_setreuid16)
-__SYSCALL(71,  sys_setregid16)
-__SYSCALL(72,  sys_sigsuspend)
-__SYSCALL(73,  compat_sys_sigpending)
-__SYSCALL(74,  sys_sethostname)
-__SYSCALL(75,  compat_sys_setrlimit)
-__SYSCALL(76,  sys_ni_syscall)			/* 76 was compat_sys_getrlimit */
-__SYSCALL(77,  compat_sys_getrusage)
-__SYSCALL(78,  compat_sys_gettimeofday)
-__SYSCALL(79,  compat_sys_settimeofday)
-__SYSCALL(80,  sys_getgroups16)
-__SYSCALL(81,  sys_setgroups16)
-__SYSCALL(82,  sys_ni_syscall)			/* 82 was compat_sys_select */
-__SYSCALL(83,  sys_symlink)
-__SYSCALL(84,  sys_ni_syscall)			/* 84 was sys_lstat */
-__SYSCALL(85,  sys_readlink)
-__SYSCALL(86,  sys_uselib)
-__SYSCALL(87,  sys_swapon)
-__SYSCALL(88,  sys_reboot)
-__SYSCALL(89,  sys_ni_syscall)			/* 89 was sys_readdir */
-__SYSCALL(90,  sys_ni_syscall)			/* 90 was sys_mmap */
-__SYSCALL(91,  sys_munmap)
-__SYSCALL(92,  compat_sys_truncate)
-__SYSCALL(93,  compat_sys_ftruncate)
-__SYSCALL(94,  sys_fchmod)
-__SYSCALL(95,  sys_fchown16)
-__SYSCALL(96,  sys_getpriority)
-__SYSCALL(97,  sys_setpriority)
-__SYSCALL(98,  sys_ni_syscall)			/* 98 was sys_profil */
-__SYSCALL(99,  compat_sys_statfs)
-__SYSCALL(100, compat_sys_fstatfs)
-__SYSCALL(101, sys_ni_syscall)			/* 101 was sys_ioperm */
-__SYSCALL(102, sys_ni_syscall)			/* 102 was sys_socketcall */
-__SYSCALL(103, sys_syslog)
-__SYSCALL(104, compat_sys_setitimer)
-__SYSCALL(105, compat_sys_getitimer)
-__SYSCALL(106, compat_sys_newstat)
-__SYSCALL(107, compat_sys_newlstat)
-__SYSCALL(108, compat_sys_newfstat)
-__SYSCALL(109, sys_ni_syscall)			/* 109 was sys_uname */
-__SYSCALL(110, sys_ni_syscall)			/* 110 was sys_iopl */
-__SYSCALL(111, sys_vhangup)
-__SYSCALL(112, sys_ni_syscall)			/* 112 was sys_idle */
-__SYSCALL(113, sys_ni_syscall)			/* 113 was sys_syscall */
-__SYSCALL(114, compat_sys_wait4)
-__SYSCALL(115, sys_swapoff)
-__SYSCALL(116, compat_sys_sysinfo)
-__SYSCALL(117, sys_ni_syscall)			/* 117 was sys_ipc */
-__SYSCALL(118, sys_fsync)
-__SYSCALL(119, compat_sys_sigreturn_wrapper)
-__SYSCALL(120, sys_clone)
-__SYSCALL(121, sys_setdomainname)
-__SYSCALL(122, sys_newuname)
-__SYSCALL(123, sys_ni_syscall)			/* 123 was sys_modify_ldt */
-__SYSCALL(124, compat_sys_adjtimex)
-__SYSCALL(125, sys_mprotect)
-__SYSCALL(126, compat_sys_sigprocmask)
-__SYSCALL(127, sys_ni_syscall)			/* 127 was sys_create_module */
-__SYSCALL(128, sys_init_module)
-__SYSCALL(129, sys_delete_module)
-__SYSCALL(130, sys_ni_syscall)			/* 130 was sys_get_kernel_syms */
-__SYSCALL(131, sys_quotactl)
-__SYSCALL(132, sys_getpgid)
-__SYSCALL(133, sys_fchdir)
-__SYSCALL(134, sys_bdflush)
-__SYSCALL(135, sys_sysfs)
-__SYSCALL(136, sys_personality)
-__SYSCALL(137, sys_ni_syscall)			/* 137 was sys_afs_syscall */
-__SYSCALL(138, sys_setfsuid16)
-__SYSCALL(139, sys_setfsgid16)
-__SYSCALL(140, sys_llseek)
-__SYSCALL(141, compat_sys_getdents)
-__SYSCALL(142, compat_sys_select)
-__SYSCALL(143, sys_flock)
-__SYSCALL(144, sys_msync)
-__SYSCALL(145, compat_sys_readv)
-__SYSCALL(146, compat_sys_writev)
-__SYSCALL(147, sys_getsid)
-__SYSCALL(148, sys_fdatasync)
-__SYSCALL(149, compat_sys_sysctl)
-__SYSCALL(150, sys_mlock)
-__SYSCALL(151, sys_munlock)
-__SYSCALL(152, sys_mlockall)
-__SYSCALL(153, sys_munlockall)
-__SYSCALL(154, sys_sched_setparam)
-__SYSCALL(155, sys_sched_getparam)
-__SYSCALL(156, sys_sched_setscheduler)
-__SYSCALL(157, sys_sched_getscheduler)
-__SYSCALL(158, sys_sched_yield)
-__SYSCALL(159, sys_sched_get_priority_max)
-__SYSCALL(160, sys_sched_get_priority_min)
-__SYSCALL(161, compat_sys_sched_rr_get_interval)
-__SYSCALL(162, compat_sys_nanosleep)
-__SYSCALL(163, sys_mremap)
-__SYSCALL(164, sys_setresuid16)
-__SYSCALL(165, sys_getresuid16)
-__SYSCALL(166, sys_ni_syscall)			/* 166 was sys_vm86 */
-__SYSCALL(167, sys_ni_syscall)			/* 167 was sys_query_module */
-__SYSCALL(168, sys_poll)
-__SYSCALL(169, sys_ni_syscall)
-__SYSCALL(170, sys_setresgid16)
-__SYSCALL(171, sys_getresgid16)
-__SYSCALL(172, sys_prctl)
-__SYSCALL(173, compat_sys_rt_sigreturn_wrapper)
-__SYSCALL(174, compat_sys_rt_sigaction)
-__SYSCALL(175, compat_sys_rt_sigprocmask)
-__SYSCALL(176, compat_sys_rt_sigpending)
-__SYSCALL(177, compat_sys_rt_sigtimedwait)
-__SYSCALL(178, compat_sys_rt_sigqueueinfo)
-__SYSCALL(179, compat_sys_rt_sigsuspend)
-__SYSCALL(180, compat_sys_pread64_wrapper)
-__SYSCALL(181, compat_sys_pwrite64_wrapper)
-__SYSCALL(182, sys_chown16)
-__SYSCALL(183, sys_getcwd)
-__SYSCALL(184, sys_capget)
-__SYSCALL(185, sys_capset)
-__SYSCALL(186, compat_sys_sigaltstack)
-__SYSCALL(187, compat_sys_sendfile)
-__SYSCALL(188, sys_ni_syscall)			/* 188 reserved */
-__SYSCALL(189, sys_ni_syscall)			/* 189 reserved */
-__SYSCALL(190, sys_vfork)
-__SYSCALL(191, compat_sys_getrlimit)		/* SuS compliant getrlimit */
-__SYSCALL(192, sys_mmap_pgoff)
-__SYSCALL(193, compat_sys_truncate64_wrapper)
-__SYSCALL(194, compat_sys_ftruncate64_wrapper)
-__SYSCALL(195, sys_stat64)
-__SYSCALL(196, sys_lstat64)
-__SYSCALL(197, sys_fstat64)
-__SYSCALL(198, sys_lchown)
-__SYSCALL(199, sys_getuid)
-__SYSCALL(200, sys_getgid)
-__SYSCALL(201, sys_geteuid)
-__SYSCALL(202, sys_getegid)
-__SYSCALL(203, sys_setreuid)
-__SYSCALL(204, sys_setregid)
-__SYSCALL(205, sys_getgroups)
-__SYSCALL(206, sys_setgroups)
-__SYSCALL(207, sys_fchown)
-__SYSCALL(208, sys_setresuid)
-__SYSCALL(209, sys_getresuid)
-__SYSCALL(210, sys_setresgid)
-__SYSCALL(211, sys_getresgid)
-__SYSCALL(212, sys_chown)
-__SYSCALL(213, sys_setuid)
-__SYSCALL(214, sys_setgid)
-__SYSCALL(215, sys_setfsuid)
-__SYSCALL(216, sys_setfsgid)
-__SYSCALL(217, compat_sys_getdents64)
-__SYSCALL(218, sys_pivot_root)
-__SYSCALL(219, sys_mincore)
-__SYSCALL(220, sys_madvise)
-__SYSCALL(221, compat_sys_fcntl64)
-__SYSCALL(222, sys_ni_syscall)			/* 222 for tux */
-__SYSCALL(223, sys_ni_syscall)			/* 223 is unused */
-__SYSCALL(224, sys_gettid)
-__SYSCALL(225, compat_sys_readahead_wrapper)
-__SYSCALL(226, sys_setxattr)
-__SYSCALL(227, sys_lsetxattr)
-__SYSCALL(228, sys_fsetxattr)
-__SYSCALL(229, sys_getxattr)
-__SYSCALL(230, sys_lgetxattr)
-__SYSCALL(231, sys_fgetxattr)
-__SYSCALL(232, sys_listxattr)
-__SYSCALL(233, sys_llistxattr)
-__SYSCALL(234, sys_flistxattr)
-__SYSCALL(235, sys_removexattr)
-__SYSCALL(236, sys_lremovexattr)
-__SYSCALL(237, sys_fremovexattr)
-__SYSCALL(238, sys_tkill)
-__SYSCALL(239, sys_sendfile64)
-__SYSCALL(240, compat_sys_futex)
-__SYSCALL(241, compat_sys_sched_setaffinity)
-__SYSCALL(242, compat_sys_sched_getaffinity)
-__SYSCALL(243, compat_sys_io_setup)
-__SYSCALL(244, sys_io_destroy)
-__SYSCALL(245, compat_sys_io_getevents)
-__SYSCALL(246, compat_sys_io_submit)
-__SYSCALL(247, sys_io_cancel)
-__SYSCALL(248, sys_exit_group)
-__SYSCALL(249, compat_sys_lookup_dcookie)
-__SYSCALL(250, sys_epoll_create)
-__SYSCALL(251, sys_epoll_ctl)
-__SYSCALL(252, sys_epoll_wait)
-__SYSCALL(253, sys_remap_file_pages)
-__SYSCALL(254, sys_ni_syscall)			/* 254 for set_thread_area */
-__SYSCALL(255, sys_ni_syscall)			/* 255 for get_thread_area */
-__SYSCALL(256, sys_set_tid_address)
-__SYSCALL(257, compat_sys_timer_create)
-__SYSCALL(258, compat_sys_timer_settime)
-__SYSCALL(259, compat_sys_timer_gettime)
-__SYSCALL(260, sys_timer_getoverrun)
-__SYSCALL(261, sys_timer_delete)
-__SYSCALL(262, compat_sys_clock_settime)
-__SYSCALL(263, compat_sys_clock_gettime)
-__SYSCALL(264, compat_sys_clock_getres)
-__SYSCALL(265, compat_sys_clock_nanosleep)
-__SYSCALL(266, compat_sys_statfs64_wrapper)
-__SYSCALL(267, compat_sys_fstatfs64_wrapper)
-__SYSCALL(268, sys_tgkill)
-__SYSCALL(269, compat_sys_utimes)
-__SYSCALL(270, compat_sys_fadvise64_64_wrapper)
-__SYSCALL(271, sys_pciconfig_iobase)
-__SYSCALL(272, sys_pciconfig_read)
-__SYSCALL(273, sys_pciconfig_write)
-__SYSCALL(274, compat_sys_mq_open)
-__SYSCALL(275, sys_mq_unlink)
-__SYSCALL(276, compat_sys_mq_timedsend)
-__SYSCALL(277, compat_sys_mq_timedreceive)
-__SYSCALL(278, compat_sys_mq_notify)
-__SYSCALL(279, compat_sys_mq_getsetattr)
-__SYSCALL(280, compat_sys_waitid)
-__SYSCALL(281, sys_socket)
-__SYSCALL(282, sys_bind)
-__SYSCALL(283, sys_connect)
-__SYSCALL(284, sys_listen)
-__SYSCALL(285, sys_accept)
-__SYSCALL(286, sys_getsockname)
-__SYSCALL(287, sys_getpeername)
-__SYSCALL(288, sys_socketpair)
-__SYSCALL(289, sys_send)
-__SYSCALL(290, sys_sendto)
-__SYSCALL(291, compat_sys_recv)
-__SYSCALL(292, compat_sys_recvfrom)
-__SYSCALL(293, sys_shutdown)
-__SYSCALL(294, compat_sys_setsockopt)
-__SYSCALL(295, compat_sys_getsockopt)
-__SYSCALL(296, compat_sys_sendmsg)
-__SYSCALL(297, compat_sys_recvmsg)
-__SYSCALL(298, sys_semop)
-__SYSCALL(299, sys_semget)
-__SYSCALL(300, compat_sys_semctl)
-__SYSCALL(301, compat_sys_msgsnd)
-__SYSCALL(302, compat_sys_msgrcv)
-__SYSCALL(303, sys_msgget)
-__SYSCALL(304, compat_sys_msgctl)
-__SYSCALL(305, compat_sys_shmat)
-__SYSCALL(306, sys_shmdt)
-__SYSCALL(307, sys_shmget)
-__SYSCALL(308, compat_sys_shmctl)
-__SYSCALL(309, sys_add_key)
-__SYSCALL(310, sys_request_key)
-__SYSCALL(311, compat_sys_keyctl)
-__SYSCALL(312, compat_sys_semtimedop)
-__SYSCALL(313, sys_ni_syscall)
-__SYSCALL(314, sys_ioprio_set)
-__SYSCALL(315, sys_ioprio_get)
-__SYSCALL(316, sys_inotify_init)
-__SYSCALL(317, sys_inotify_add_watch)
-__SYSCALL(318, sys_inotify_rm_watch)
-__SYSCALL(319, compat_sys_mbind)
-__SYSCALL(320, compat_sys_get_mempolicy)
-__SYSCALL(321, compat_sys_set_mempolicy)
-__SYSCALL(322, compat_sys_openat)
-__SYSCALL(323, sys_mkdirat)
-__SYSCALL(324, sys_mknodat)
-__SYSCALL(325, sys_fchownat)
-__SYSCALL(326, compat_sys_futimesat)
-__SYSCALL(327, sys_fstatat64)
-__SYSCALL(328, sys_unlinkat)
-__SYSCALL(329, sys_renameat)
-__SYSCALL(330, sys_linkat)
-__SYSCALL(331, sys_symlinkat)
-__SYSCALL(332, sys_readlinkat)
-__SYSCALL(333, sys_fchmodat)
-__SYSCALL(334, sys_faccessat)
-__SYSCALL(335, compat_sys_pselect6)
-__SYSCALL(336, compat_sys_ppoll)
-__SYSCALL(337, sys_unshare)
-__SYSCALL(338, compat_sys_set_robust_list)
-__SYSCALL(339, compat_sys_get_robust_list)
-__SYSCALL(340, sys_splice)
-__SYSCALL(341, compat_sys_sync_file_range2_wrapper)
-__SYSCALL(342, sys_tee)
-__SYSCALL(343, compat_sys_vmsplice)
-__SYSCALL(344, compat_sys_move_pages)
-__SYSCALL(345, sys_getcpu)
-__SYSCALL(346, compat_sys_epoll_pwait)
-__SYSCALL(347, compat_sys_kexec_load)
-__SYSCALL(348, compat_sys_utimensat)
-__SYSCALL(349, compat_sys_signalfd)
-__SYSCALL(350, sys_timerfd_create)
-__SYSCALL(351, sys_eventfd)
-__SYSCALL(352, compat_sys_fallocate_wrapper)
-__SYSCALL(353, compat_sys_timerfd_settime)
-__SYSCALL(354, compat_sys_timerfd_gettime)
-__SYSCALL(355, compat_sys_signalfd4)
-__SYSCALL(356, sys_eventfd2)
-__SYSCALL(357, sys_epoll_create1)
-__SYSCALL(358, sys_dup3)
-__SYSCALL(359, sys_pipe2)
-__SYSCALL(360, sys_inotify_init1)
-__SYSCALL(361, compat_sys_preadv)
-__SYSCALL(362, compat_sys_pwritev)
-__SYSCALL(363, compat_sys_rt_tgsigqueueinfo)
-__SYSCALL(364, sys_perf_event_open)
-__SYSCALL(365, compat_sys_recvmmsg)
-__SYSCALL(366, sys_accept4)
-__SYSCALL(367, sys_fanotify_init)
-__SYSCALL(368, compat_sys_fanotify_mark)
-__SYSCALL(369, sys_prlimit64)
-__SYSCALL(370, sys_name_to_handle_at)
-__SYSCALL(371, compat_sys_open_by_handle_at)
-__SYSCALL(372, compat_sys_clock_adjtime)
-__SYSCALL(373, sys_syncfs)
-__SYSCALL(374, compat_sys_sendmmsg)
-__SYSCALL(375, sys_setns)
-__SYSCALL(376, compat_sys_process_vm_readv)
-__SYSCALL(377, compat_sys_process_vm_writev)
-__SYSCALL(378, sys_kcmp)
-__SYSCALL(379, sys_finit_module)
-__SYSCALL(380, sys_sched_setattr)
-__SYSCALL(381, sys_sched_getattr)
-__SYSCALL(382, sys_renameat2)
-
-#define __NR_compat_syscalls		383
-
-/*
- * Compat syscall numbers used by the AArch64 kernel.
- */
-#define __NR_compat_restart_syscall	0
-#define __NR_compat_sigreturn		119
-#define __NR_compat_rt_sigreturn	173
-
-
-/*
- * The following SVCs are ARM private.
- */
-#define __ARM_NR_COMPAT_BASE		0x0f0000
-#define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
-#define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
+#define __NR_restart_syscall 0
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_exit 1
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_fork 2
+__SYSCALL(__NR_fork, sys_fork)
+#define __NR_read 3
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 4
+__SYSCALL(__NR_write, sys_write)
+#define __NR_open 5
+__SYSCALL(__NR_open, compat_sys_open)
+#define __NR_close 6
+__SYSCALL(__NR_close, sys_close)
+			/* 7 was sys_waitpid */
+__SYSCALL(7, sys_ni_syscall)
+#define __NR_creat 8
+__SYSCALL(__NR_creat, sys_creat)
+#define __NR_link 9
+__SYSCALL(__NR_link, sys_link)
+#define __NR_unlink 10
+__SYSCALL(__NR_unlink, sys_unlink)
+#define __NR_execve 11
+__SYSCALL(__NR_execve, compat_sys_execve)
+#define __NR_chdir 12
+__SYSCALL(__NR_chdir, sys_chdir)
+			/* 13 was sys_time */
+__SYSCALL(13, sys_ni_syscall)
+#define __NR_mknod 14
+__SYSCALL(__NR_mknod, sys_mknod)
+#define __NR_chmod 15
+__SYSCALL(__NR_chmod, sys_chmod)
+#define __NR_lchown 16
+__SYSCALL(__NR_lchown, sys_lchown16)
+			/* 17 was sys_break */
+__SYSCALL(17, sys_ni_syscall)
+			/* 18 was sys_stat */
+__SYSCALL(18, sys_ni_syscall)
+#define __NR_lseek 19
+__SYSCALL(__NR_lseek, compat_sys_lseek)
+#define __NR_getpid 20
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_mount 21
+__SYSCALL(__NR_mount, compat_sys_mount)
+			/* 22 was sys_umount */
+__SYSCALL(22, sys_ni_syscall)
+#define __NR_setuid 23
+__SYSCALL(__NR_setuid, sys_setuid16)
+#define __NR_getuid 24
+__SYSCALL(__NR_getuid, sys_getuid16)
+			/* 25 was sys_stime */
+__SYSCALL(25, sys_ni_syscall)
+#define __NR_ptrace 26
+__SYSCALL(__NR_ptrace, compat_sys_ptrace)
+			/* 27 was sys_alarm */
+__SYSCALL(27, sys_ni_syscall)
+			/* 28 was sys_fstat */
+__SYSCALL(28, sys_ni_syscall)
+#define __NR_pause 29
+__SYSCALL(__NR_pause, sys_pause)
+			/* 30 was sys_utime */
+__SYSCALL(30, sys_ni_syscall)
+			/* 31 was sys_stty */
+__SYSCALL(31, sys_ni_syscall)
+			/* 32 was sys_gtty */
+__SYSCALL(32, sys_ni_syscall)
+#define __NR_access 33
+__SYSCALL(__NR_access, sys_access)
+#define __NR_nice 34
+__SYSCALL(__NR_nice, sys_nice)
+			/* 35 was sys_ftime */
+__SYSCALL(35, sys_ni_syscall)
+#define __NR_sync 36
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_kill 37
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_rename 38
+__SYSCALL(__NR_rename, sys_rename)
+#define __NR_mkdir 39
+__SYSCALL(__NR_mkdir, sys_mkdir)
+#define __NR_rmdir 40
+__SYSCALL(__NR_rmdir, sys_rmdir)
+#define __NR_dup 41
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_pipe 42
+__SYSCALL(__NR_pipe, sys_pipe)
+#define __NR_times 43
+__SYSCALL(__NR_times, compat_sys_times)
+			/* 44 was sys_prof */
+__SYSCALL(44, sys_ni_syscall)
+#define __NR_brk 45
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_setgid 46
+__SYSCALL(__NR_setgid, sys_setgid16)
+#define __NR_getgid 47
+__SYSCALL(__NR_getgid, sys_getgid16)
+			/* 48 was sys_signal */
+__SYSCALL(48, sys_ni_syscall)
+#define __NR_geteuid 49
+__SYSCALL(__NR_geteuid, sys_geteuid16)
+#define __NR_getegid 50
+__SYSCALL(__NR_getegid, sys_getegid16)
+#define __NR_acct 51
+__SYSCALL(__NR_acct, sys_acct)
+#define __NR_umount2 52
+__SYSCALL(__NR_umount2, sys_umount)
+			/* 53 was sys_lock */
+__SYSCALL(53, sys_ni_syscall)
+#define __NR_ioctl 54
+__SYSCALL(__NR_ioctl, compat_sys_ioctl)
+#define __NR_fcntl 55
+__SYSCALL(__NR_fcntl, compat_sys_fcntl)
+			/* 56 was sys_mpx */
+__SYSCALL(56, sys_ni_syscall)
+#define __NR_setpgid 57
+__SYSCALL(__NR_setpgid, sys_setpgid)
+			/* 58 was sys_ulimit */
+__SYSCALL(58, sys_ni_syscall)
+			/* 59 was sys_olduname */
+__SYSCALL(59, sys_ni_syscall)
+#define __NR_umask 60
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_chroot 61
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_ustat 62
+__SYSCALL(__NR_ustat, compat_sys_ustat)
+#define __NR_dup2 63
+__SYSCALL(__NR_dup2, sys_dup2)
+#define __NR_getppid 64
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getpgrp 65
+__SYSCALL(__NR_getpgrp, sys_getpgrp)
+#define __NR_setsid 66
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_sigaction 67
+__SYSCALL(__NR_sigaction, compat_sys_sigaction)
+			/* 68 was sys_sgetmask */
+__SYSCALL(68, sys_ni_syscall)
+			/* 69 was sys_ssetmask */
+__SYSCALL(69, sys_ni_syscall)
+#define __NR_setreuid 70
+__SYSCALL(__NR_setreuid, sys_setreuid16)
+#define __NR_setregid 71
+__SYSCALL(__NR_setregid, sys_setregid16)
+#define __NR_sigsuspend 72
+__SYSCALL(__NR_sigsuspend, sys_sigsuspend)
+#define __NR_sigpending 73
+__SYSCALL(__NR_sigpending, compat_sys_sigpending)
+#define __NR_sethostname 74
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setrlimit 75
+__SYSCALL(__NR_setrlimit, compat_sys_setrlimit)
+			/* 76 was compat_sys_getrlimit */
+__SYSCALL(76, sys_ni_syscall)
+#define __NR_getrusage 77
+__SYSCALL(__NR_getrusage, compat_sys_getrusage)
+#define __NR_gettimeofday 78
+__SYSCALL(__NR_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 79
+__SYSCALL(__NR_settimeofday, compat_sys_settimeofday)
+#define __NR_getgroups 80
+__SYSCALL(__NR_getgroups, sys_getgroups16)
+#define __NR_setgroups 81
+__SYSCALL(__NR_setgroups, sys_setgroups16)
+			/* 82 was compat_sys_select */
+__SYSCALL(82, sys_ni_syscall)
+#define __NR_symlink 83
+__SYSCALL(__NR_symlink, sys_symlink)
+			/* 84 was sys_lstat */
+__SYSCALL(84, sys_ni_syscall)
+#define __NR_readlink 85
+__SYSCALL(__NR_readlink, sys_readlink)
+#define __NR_uselib 86
+__SYSCALL(__NR_uselib, sys_uselib)
+#define __NR_swapon 87
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_reboot 88
+__SYSCALL(__NR_reboot, sys_reboot)
+			/* 89 was sys_readdir */
+__SYSCALL(89, sys_ni_syscall)
+			/* 90 was sys_mmap */
+__SYSCALL(90, sys_ni_syscall)
+#define __NR_munmap 91
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_truncate 92
+__SYSCALL(__NR_truncate, compat_sys_truncate)
+#define __NR_ftruncate 93
+__SYSCALL(__NR_ftruncate, compat_sys_ftruncate)
+#define __NR_fchmod 94
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchown 95
+__SYSCALL(__NR_fchown, sys_fchown16)
+#define __NR_getpriority 96
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_setpriority 97
+__SYSCALL(__NR_setpriority, sys_setpriority)
+			/* 98 was sys_profil */
+__SYSCALL(98, sys_ni_syscall)
+#define __NR_statfs 99
+__SYSCALL(__NR_statfs, compat_sys_statfs)
+#define __NR_fstatfs 100
+__SYSCALL(__NR_fstatfs, compat_sys_fstatfs)
+			/* 101 was sys_ioperm */
+__SYSCALL(101, sys_ni_syscall)
+			/* 102 was sys_socketcall */
+__SYSCALL(102, sys_ni_syscall)
+#define __NR_syslog 103
+__SYSCALL(__NR_syslog, sys_syslog)
+#define __NR_setitimer 104
+__SYSCALL(__NR_setitimer, compat_sys_setitimer)
+#define __NR_getitimer 105
+__SYSCALL(__NR_getitimer, compat_sys_getitimer)
+#define __NR_stat 106
+__SYSCALL(__NR_stat, compat_sys_newstat)
+#define __NR_lstat 107
+__SYSCALL(__NR_lstat, compat_sys_newlstat)
+#define __NR_fstat 108
+__SYSCALL(__NR_fstat, compat_sys_newfstat)
+			/* 109 was sys_uname */
+__SYSCALL(109, sys_ni_syscall)
+			/* 110 was sys_iopl */
+__SYSCALL(110, sys_ni_syscall)
+#define __NR_vhangup 111
+__SYSCALL(__NR_vhangup, sys_vhangup)
+			/* 112 was sys_idle */
+__SYSCALL(112, sys_ni_syscall)
+			/* 113 was sys_syscall */
+__SYSCALL(113, sys_ni_syscall)
+#define __NR_wait4 114
+__SYSCALL(__NR_wait4, compat_sys_wait4)
+#define __NR_swapoff 115
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_sysinfo 116
+__SYSCALL(__NR_sysinfo, compat_sys_sysinfo)
+			/* 117 was sys_ipc */
+__SYSCALL(117, sys_ni_syscall)
+#define __NR_fsync 118
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_sigreturn 119
+__SYSCALL(__NR_sigreturn, compat_sys_sigreturn_wrapper)
+#define __NR_clone 120
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_setdomainname 121
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+#define __NR_uname 122
+__SYSCALL(__NR_uname, sys_newuname)
+			/* 123 was sys_modify_ldt */
+__SYSCALL(123, sys_ni_syscall)
+#define __NR_adjtimex 124
+__SYSCALL(__NR_adjtimex, compat_sys_adjtimex)
+#define __NR_mprotect 125
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_sigprocmask 126
+__SYSCALL(__NR_sigprocmask, compat_sys_sigprocmask)
+			/* 127 was sys_create_module */
+__SYSCALL(127, sys_ni_syscall)
+#define __NR_init_module 128
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 129
+__SYSCALL(__NR_delete_module, sys_delete_module)
+			/* 130 was sys_get_kernel_syms */
+__SYSCALL(130, sys_ni_syscall)
+#define __NR_quotactl 131
+__SYSCALL(__NR_quotactl, sys_quotactl)
+#define __NR_getpgid 132
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_fchdir 133
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_bdflush 134
+__SYSCALL(__NR_bdflush, sys_bdflush)
+#define __NR_sysfs 135
+__SYSCALL(__NR_sysfs, sys_sysfs)
+#define __NR_personality 136
+__SYSCALL(__NR_personality, sys_personality)
+			/* 137 was sys_afs_syscall */
+__SYSCALL(137, sys_ni_syscall)
+#define __NR_setfsuid 138
+__SYSCALL(__NR_setfsuid, sys_setfsuid16)
+#define __NR_setfsgid 139
+__SYSCALL(__NR_setfsgid, sys_setfsgid16)
+#define __NR__llseek 140
+__SYSCALL(__NR__llseek, sys_llseek)
+#define __NR_getdents 141
+__SYSCALL(__NR_getdents, compat_sys_getdents)
+#define __NR__newselect 142
+__SYSCALL(__NR__newselect, compat_sys_select)
+#define __NR_flock 143
+__SYSCALL(__NR_flock, sys_flock)
+#define __NR_msync 144
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_readv 145
+__SYSCALL(__NR_readv, compat_sys_readv)
+#define __NR_writev 146
+__SYSCALL(__NR_writev, compat_sys_writev)
+#define __NR_getsid 147
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_fdatasync 148
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#define __NR__sysctl 149
+__SYSCALL(__NR__sysctl, compat_sys_sysctl)
+#define __NR_mlock 150
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 151
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 152
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 153
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_sched_setparam 154
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_getparam 155
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setscheduler 156
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 157
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_yield 158
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 159
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 160
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval 161
+__SYSCALL(__NR_sched_rr_get_interval, compat_sys_sched_rr_get_interval)
+#define __NR_nanosleep 162
+__SYSCALL(__NR_nanosleep, compat_sys_nanosleep)
+#define __NR_mremap 163
+__SYSCALL(__NR_mremap, sys_mremap)
+#define __NR_setresuid 164
+__SYSCALL(__NR_setresuid, sys_setresuid16)
+#define __NR_getresuid 165
+__SYSCALL(__NR_getresuid, sys_getresuid16)
+			/* 166 was sys_vm86 */
+__SYSCALL(166, sys_ni_syscall)
+			/* 167 was sys_query_module */
+__SYSCALL(167, sys_ni_syscall)
+#define __NR_poll 168
+__SYSCALL(__NR_poll, sys_poll)
+#define __NR_nfsservctl 169
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+#define __NR_setresgid 170
+__SYSCALL(__NR_setresgid, sys_setresgid16)
+#define __NR_getresgid 171
+__SYSCALL(__NR_getresgid, sys_getresgid16)
+#define __NR_prctl 172
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_rt_sigreturn 173
+__SYSCALL(__NR_rt_sigreturn, compat_sys_rt_sigreturn_wrapper)
+#define __NR_rt_sigaction 174
+__SYSCALL(__NR_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 175
+__SYSCALL(__NR_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 176
+__SYSCALL(__NR_rt_sigpending, compat_sys_rt_sigpending)
+#define __NR_rt_sigtimedwait 177
+__SYSCALL(__NR_rt_sigtimedwait, compat_sys_rt_sigtimedwait)
+#define __NR_rt_sigqueueinfo 178
+__SYSCALL(__NR_rt_sigqueueinfo, compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigsuspend 179
+__SYSCALL(__NR_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_pread64 180
+__SYSCALL(__NR_pread64, compat_sys_pread64_wrapper)
+#define __NR_pwrite64 181
+__SYSCALL(__NR_pwrite64, compat_sys_pwrite64_wrapper)
+#define __NR_chown 182
+__SYSCALL(__NR_chown, sys_chown16)
+#define __NR_getcwd 183
+__SYSCALL(__NR_getcwd, sys_getcwd)
+#define __NR_capget 184
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 185
+__SYSCALL(__NR_capset, sys_capset)
+#define __NR_sigaltstack 186
+__SYSCALL(__NR_sigaltstack, compat_sys_sigaltstack)
+#define __NR_sendfile 187
+__SYSCALL(__NR_sendfile, compat_sys_sendfile)
+			/* 188 reserved */
+__SYSCALL(188, sys_ni_syscall)
+			/* 189 reserved */
+__SYSCALL(189, sys_ni_syscall)
+#define __NR_vfork 190
+__SYSCALL(__NR_vfork, sys_vfork)
+#define __NR_ugetrlimit 191	/* SuS compliant getrlimit */
+__SYSCALL(__NR_ugetrlimit, compat_sys_getrlimit)		/* SuS compliant getrlimit */
+#define __NR_mmap2 192
+__SYSCALL(__NR_mmap2, sys_mmap_pgoff)
+#define __NR_truncate64 193
+__SYSCALL(__NR_truncate64, compat_sys_truncate64_wrapper)
+#define __NR_ftruncate64 194
+__SYSCALL(__NR_ftruncate64, compat_sys_ftruncate64_wrapper)
+#define __NR_stat64 195
+__SYSCALL(__NR_stat64, sys_stat64)
+#define __NR_lstat64 196
+__SYSCALL(__NR_lstat64, sys_lstat64)
+#define __NR_fstat64 197
+__SYSCALL(__NR_fstat64, sys_fstat64)
+#define __NR_lchown32 198
+__SYSCALL(__NR_lchown32, sys_lchown)
+#define __NR_getuid32 199
+__SYSCALL(__NR_getuid32, sys_getuid)
+#define __NR_getgid32 200
+__SYSCALL(__NR_getgid32, sys_getgid)
+#define __NR_geteuid32 201
+__SYSCALL(__NR_geteuid32, sys_geteuid)
+#define __NR_getegid32 202
+__SYSCALL(__NR_getegid32, sys_getegid)
+#define __NR_setreuid32 203
+__SYSCALL(__NR_setreuid32, sys_setreuid)
+#define __NR_setregid32 204
+__SYSCALL(__NR_setregid32, sys_setregid)
+#define __NR_getgroups32 205
+__SYSCALL(__NR_getgroups32, sys_getgroups)
+#define __NR_setgroups32 206
+__SYSCALL(__NR_setgroups32, sys_setgroups)
+#define __NR_fchown32 207
+__SYSCALL(__NR_fchown32, sys_fchown)
+#define __NR_setresuid32 208
+__SYSCALL(__NR_setresuid32, sys_setresuid)
+#define __NR_getresuid32 209
+__SYSCALL(__NR_getresuid32, sys_getresuid)
+#define __NR_setresgid32 210
+__SYSCALL(__NR_setresgid32, sys_setresgid)
+#define __NR_getresgid32 211
+__SYSCALL(__NR_getresgid32, sys_getresgid)
+#define __NR_chown32 212
+__SYSCALL(__NR_chown32, sys_chown)
+#define __NR_setuid32 213
+__SYSCALL(__NR_setuid32, sys_setuid)
+#define __NR_setgid32 214
+__SYSCALL(__NR_setgid32, sys_setgid)
+#define __NR_setfsuid32 215
+__SYSCALL(__NR_setfsuid32, sys_setfsuid)
+#define __NR_setfsgid32 216
+__SYSCALL(__NR_setfsgid32, sys_setfsgid)
+#define __NR_getdents64 217
+__SYSCALL(__NR_getdents64, compat_sys_getdents64)
+#define __NR_pivot_root 218
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+#define __NR_mincore 219
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 220
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_fcntl64 221
+__SYSCALL(__NR_fcntl64, compat_sys_fcntl64)
+			/* 222 for tux */
+__SYSCALL(222, sys_ni_syscall)
+			/* 223 is unused */
+__SYSCALL(223, sys_ni_syscall)
+#define __NR_gettid 224
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_readahead 225
+__SYSCALL(__NR_readahead, compat_sys_readahead_wrapper)
+#define __NR_setxattr 226
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 227
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 228
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 229
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 230
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 231
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 232
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 233
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 234
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 235
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 236
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 237
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+#define __NR_tkill 238
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_sendfile64 239
+__SYSCALL(__NR_sendfile64, sys_sendfile64)
+#define __NR_futex 240
+__SYSCALL(__NR_futex, compat_sys_futex)
+#define __NR_sched_setaffinity 241
+__SYSCALL(__NR_sched_setaffinity, compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 242
+__SYSCALL(__NR_sched_getaffinity, compat_sys_sched_getaffinity)
+#define __NR_io_setup 243
+__SYSCALL(__NR_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 244
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_getevents 245
+__SYSCALL(__NR_io_getevents, compat_sys_io_getevents)
+#define __NR_io_submit 246
+__SYSCALL(__NR_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 247
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_exit_group 248
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_lookup_dcookie 249
+__SYSCALL(__NR_lookup_dcookie, compat_sys_lookup_dcookie)
+#define __NR_epoll_create 250
+__SYSCALL(__NR_epoll_create, sys_epoll_create)
+#define __NR_epoll_ctl 251
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_wait 252
+__SYSCALL(__NR_epoll_wait, sys_epoll_wait)
+#define __NR_remap_file_pages 253
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+			/* 254 for set_thread_area */
+__SYSCALL(254, sys_ni_syscall)
+			/* 255 for get_thread_area */
+__SYSCALL(255, sys_ni_syscall)
+#define __NR_set_tid_address 256
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_timer_create 257
+__SYSCALL(__NR_timer_create, compat_sys_timer_create)
+#define __NR_timer_settime 258
+__SYSCALL(__NR_timer_settime, compat_sys_timer_settime)
+#define __NR_timer_gettime 259
+__SYSCALL(__NR_timer_gettime, compat_sys_timer_gettime)
+#define __NR_timer_getoverrun 260
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_delete 261
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime 262
+__SYSCALL(__NR_clock_settime, compat_sys_clock_settime)
+#define __NR_clock_gettime 263
+__SYSCALL(__NR_clock_gettime, compat_sys_clock_gettime)
+#define __NR_clock_getres 264
+__SYSCALL(__NR_clock_getres, compat_sys_clock_getres)
+#define __NR_clock_nanosleep 265
+__SYSCALL(__NR_clock_nanosleep, compat_sys_clock_nanosleep)
+#define __NR_statfs64 266
+__SYSCALL(__NR_statfs64, compat_sys_statfs64_wrapper)
+#define __NR_fstatfs64 267
+__SYSCALL(__NR_fstatfs64, compat_sys_fstatfs64_wrapper)
+#define __NR_tgkill 268
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_utimes 269
+__SYSCALL(__NR_utimes, compat_sys_utimes)
+#define __NR_arm_fadvise64_64 270
+__SYSCALL(__NR_arm_fadvise64_64, compat_sys_fadvise64_64_wrapper)
+#define __NR_pciconfig_iobase 271
+__SYSCALL(__NR_pciconfig_iobase, sys_pciconfig_iobase)
+#define __NR_pciconfig_read 272
+__SYSCALL(__NR_pciconfig_read, sys_pciconfig_read)
+#define __NR_pciconfig_write 273
+__SYSCALL(__NR_pciconfig_write, sys_pciconfig_write)
+#define __NR_mq_open 274
+__SYSCALL(__NR_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 275
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend 276
+__SYSCALL(__NR_mq_timedsend, compat_sys_mq_timedsend)
+#define __NR_mq_timedreceive 277
+__SYSCALL(__NR_mq_timedreceive, compat_sys_mq_timedreceive)
+#define __NR_mq_notify 278
+__SYSCALL(__NR_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 279
+__SYSCALL(__NR_mq_getsetattr, compat_sys_mq_getsetattr)
+#define __NR_waitid 280
+__SYSCALL(__NR_waitid, compat_sys_waitid)
+#define __NR_socket 281
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_bind 282
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_connect 283
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_listen 284
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 285
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_getsockname 286
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 287
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_socketpair 288
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_send 289
+__SYSCALL(__NR_send, sys_send)
+#define __NR_sendto 290
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recv 291
+__SYSCALL(__NR_recv, compat_sys_recv)
+#define __NR_recvfrom 292
+__SYSCALL(__NR_recvfrom, compat_sys_recvfrom)
+#define __NR_shutdown 293
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_setsockopt 294
+__SYSCALL(__NR_setsockopt, compat_sys_setsockopt)
+#define __NR_getsockopt 295
+__SYSCALL(__NR_getsockopt, compat_sys_getsockopt)
+#define __NR_sendmsg 296
+__SYSCALL(__NR_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 297
+__SYSCALL(__NR_recvmsg, compat_sys_recvmsg)
+#define __NR_semop 298
+__SYSCALL(__NR_semop, sys_semop)
+#define __NR_semget 299
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 300
+__SYSCALL(__NR_semctl, compat_sys_semctl)
+#define __NR_msgsnd 301
+__SYSCALL(__NR_msgsnd, compat_sys_msgsnd)
+#define __NR_msgrcv 302
+__SYSCALL(__NR_msgrcv, compat_sys_msgrcv)
+#define __NR_msgget 303
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 304
+__SYSCALL(__NR_msgctl, compat_sys_msgctl)
+#define __NR_shmat 305
+__SYSCALL(__NR_shmat, compat_sys_shmat)
+#define __NR_shmdt 306
+__SYSCALL(__NR_shmdt, sys_shmdt)
+#define __NR_shmget 307
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 308
+__SYSCALL(__NR_shmctl, compat_sys_shmctl)
+#define __NR_add_key 309
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 310
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 311
+__SYSCALL(__NR_keyctl, compat_sys_keyctl)
+#define __NR_semtimedop 312
+__SYSCALL(__NR_semtimedop, compat_sys_semtimedop)
+#define __NR_vserver 313
+__SYSCALL(__NR_vserver, sys_ni_syscall)
+#define __NR_ioprio_set 314
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 315
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+#define __NR_inotify_init 316
+__SYSCALL(__NR_inotify_init, sys_inotify_init)
+#define __NR_inotify_add_watch 317
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 318
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+#define __NR_mbind 319
+__SYSCALL(__NR_mbind, compat_sys_mbind)
+#define __NR_get_mempolicy 320
+__SYSCALL(__NR_get_mempolicy, compat_sys_get_mempolicy)
+#define __NR_set_mempolicy 321
+__SYSCALL(__NR_set_mempolicy, compat_sys_set_mempolicy)
+#define __NR_openat 322
+__SYSCALL(__NR_openat, compat_sys_openat)
+#define __NR_mkdirat 323
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_mknodat 324
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_fchownat 325
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_futimesat 326
+__SYSCALL(__NR_futimesat, compat_sys_futimesat)
+#define __NR_fstatat64 327
+__SYSCALL(__NR_fstatat64, sys_fstatat64)
+#define __NR_unlinkat 328
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_renameat 329
+__SYSCALL(__NR_renameat, sys_renameat)
+#define __NR_linkat 330
+__SYSCALL(__NR_linkat, sys_linkat)
+#define __NR_symlinkat 331
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_readlinkat 332
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR_fchmodat 333
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_faccessat 334
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_pselect6 335
+__SYSCALL(__NR_pselect6, compat_sys_pselect6)
+#define __NR_ppoll 336
+__SYSCALL(__NR_ppoll, compat_sys_ppoll)
+#define __NR_unshare 337
+__SYSCALL(__NR_unshare, sys_unshare)
+#define __NR_set_robust_list 338
+__SYSCALL(__NR_set_robust_list, compat_sys_set_robust_list)
+#define __NR_get_robust_list 339
+__SYSCALL(__NR_get_robust_list, compat_sys_get_robust_list)
+#define __NR_splice 340
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_sync_file_range2 341
+__SYSCALL(__NR_sync_file_range2, compat_sys_sync_file_range2_wrapper)
+#define __NR_tee 342
+__SYSCALL(__NR_tee, sys_tee)
+#define __NR_vmsplice 343
+__SYSCALL(__NR_vmsplice, compat_sys_vmsplice)
+#define __NR_move_pages 344
+__SYSCALL(__NR_move_pages, compat_sys_move_pages)
+#define __NR_getcpu 345
+__SYSCALL(__NR_getcpu, sys_getcpu)
+#define __NR_epoll_pwait 346
+__SYSCALL(__NR_epoll_pwait, compat_sys_epoll_pwait)
+#define __NR_kexec_load 347
+__SYSCALL(__NR_kexec_load, compat_sys_kexec_load)
+#define __NR_utimensat 348
+__SYSCALL(__NR_utimensat, compat_sys_utimensat)
+#define __NR_signalfd 349
+__SYSCALL(__NR_signalfd, compat_sys_signalfd)
+#define __NR_timerfd_create 350
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_eventfd 351
+__SYSCALL(__NR_eventfd, sys_eventfd)
+#define __NR_fallocate 352
+__SYSCALL(__NR_fallocate, compat_sys_fallocate_wrapper)
+#define __NR_timerfd_settime 353
+__SYSCALL(__NR_timerfd_settime, compat_sys_timerfd_settime)
+#define __NR_timerfd_gettime 354
+__SYSCALL(__NR_timerfd_gettime, compat_sys_timerfd_gettime)
+#define __NR_signalfd4 355
+__SYSCALL(__NR_signalfd4, compat_sys_signalfd4)
+#define __NR_eventfd2 356
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+#define __NR_epoll_create1 357
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_dup3 358
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR_pipe2 359
+__SYSCALL(__NR_pipe2, sys_pipe2)
+#define __NR_inotify_init1 360
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_preadv 361
+__SYSCALL(__NR_preadv, compat_sys_preadv)
+#define __NR_pwritev 362
+__SYSCALL(__NR_pwritev, compat_sys_pwritev)
+#define __NR_rt_tgsigqueueinfo 363
+__SYSCALL(__NR_rt_tgsigqueueinfo, compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 364
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_recvmmsg 365
+__SYSCALL(__NR_recvmmsg, compat_sys_recvmmsg)
+#define __NR_accept4 366
+__SYSCALL(__NR_accept4, sys_accept4)
+#define __NR_fanotify_init 367
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 368
+__SYSCALL(__NR_fanotify_mark, compat_sys_fanotify_mark)
+#define __NR_prlimit64 369
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_name_to_handle_at 370
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at 371
+__SYSCALL(__NR_open_by_handle_at, compat_sys_open_by_handle_at)
+#define __NR_clock_adjtime 372
+__SYSCALL(__NR_clock_adjtime, compat_sys_clock_adjtime)
+#define __NR_syncfs 373
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_sendmmsg 374
+__SYSCALL(__NR_sendmmsg, compat_sys_sendmmsg)
+#define __NR_setns 375
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_process_vm_readv 376
+__SYSCALL(__NR_process_vm_readv, compat_sys_process_vm_readv)
+#define __NR_process_vm_writev 377
+__SYSCALL(__NR_process_vm_writev, compat_sys_process_vm_writev)
+#define __NR_kcmp 378
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 379
+__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 380
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 381
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 382
+__SYSCALL(__NR_renameat2, sys_renameat2)
diff --git a/arch/arm64/include/uapi/asm/posix_types.h b/arch/arm64/include/uapi/asm/posix_types.h
new file mode 100644
index 00000000000..7985ff60ca3
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/posix_types.h
@@ -0,0 +1,10 @@
+#ifndef __ASM_POSIX_TYPES_H
+#define __ASM_POSIX_TYPES_H
+
+typedef unsigned short __kernel_old_uid_t;
+typedef unsigned short __kernel_old_gid_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
+
+#include <asm-generic/posix_types.h>
+
+#endif /*  __ASM_POSIX_TYPES_H */
diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index b72cf405b3f..ee469be1ae1 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -58,7 +58,7 @@ struct fpsimd_context {
 
 struct esr_context {
 	struct _aarch64_ctx head;
-	u64 esr;
+	__u64 esr;
 };
 
 #endif /* _UAPI__ASM_SIGCONTEXT_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index cdaedad3afe..df7ef8768fc 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -4,8 +4,7 @@
 
 CPPFLAGS_vmlinux.lds	:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
-CFLAGS_efi-stub.o 	:= -DTEXT_OFFSET=$(TEXT_OFFSET) \
-			   -I$(src)/../../../scripts/dtc/libfdt
+CFLAGS_efi-stub.o 	:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_insn.o = -pg
@@ -15,7 +14,8 @@ CFLAGS_REMOVE_return_address.o = -pg
 arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o cpu_ops.o insn.o return_address.o
+			   hyp-stub.o psci.o cpu_ops.o insn.o return_address.o	\
+			   cpuinfo.o
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
 					   sys_compat.o
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index d62d12fb36c..cce952440c6 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -30,8 +30,8 @@ const struct cpu_operations *cpu_ops[NR_CPUS];
 static const struct cpu_operations *supported_cpu_ops[] __initconst = {
 #ifdef CONFIG_SMP
 	&smp_spin_table_ops,
-	&cpu_psci_ops,
 #endif
+	&cpu_psci_ops,
 	NULL,
 };
 
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
new file mode 100644
index 00000000000..f798f66634a
--- /dev/null
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -0,0 +1,192 @@
+/*
+ * Record and handle CPU attributes.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <asm/arch_timer.h>
+#include <asm/cachetype.h>
+#include <asm/cpu.h>
+#include <asm/cputype.h>
+
+#include <linux/bitops.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/printk.h>
+#include <linux/smp.h>
+
+/*
+ * In case the boot CPU is hotpluggable, we record its initial state and
+ * current state separately. Certain system registers may contain different
+ * values depending on configuration at or after reset.
+ */
+DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data);
+static struct cpuinfo_arm64 boot_cpu_data;
+
+static char *icache_policy_str[] = {
+	[ICACHE_POLICY_RESERVED] = "RESERVED/UNKNOWN",
+	[ICACHE_POLICY_AIVIVT] = "AIVIVT",
+	[ICACHE_POLICY_VIPT] = "VIPT",
+	[ICACHE_POLICY_PIPT] = "PIPT",
+};
+
+unsigned long __icache_flags;
+
+static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
+{
+	unsigned int cpu = smp_processor_id();
+	u32 l1ip = CTR_L1IP(info->reg_ctr);
+
+	if (l1ip != ICACHE_POLICY_PIPT)
+		set_bit(ICACHEF_ALIASING, &__icache_flags);
+	if (l1ip == ICACHE_POLICY_AIVIVT);
+		set_bit(ICACHEF_AIVIVT, &__icache_flags);
+
+	pr_info("Detected %s I-cache on CPU%d\n", icache_policy_str[l1ip], cpu);
+}
+
+static int check_reg_mask(char *name, u64 mask, u64 boot, u64 cur, int cpu)
+{
+	if ((boot & mask) == (cur & mask))
+		return 0;
+
+	pr_warn("SANITY CHECK: Unexpected variation in %s. Boot CPU: %#016lx, CPU%d: %#016lx\n",
+		name, (unsigned long)boot, cpu, (unsigned long)cur);
+
+	return 1;
+}
+
+#define CHECK_MASK(field, mask, boot, cur, cpu) \
+	check_reg_mask(#field, mask, (boot)->reg_ ## field, (cur)->reg_ ## field, cpu)
+
+#define CHECK(field, boot, cur, cpu) \
+	CHECK_MASK(field, ~0ULL, boot, cur, cpu)
+
+/*
+ * Verify that CPUs don't have unexpected differences that will cause problems.
+ */
+static void cpuinfo_sanity_check(struct cpuinfo_arm64 *cur)
+{
+	unsigned int cpu = smp_processor_id();
+	struct cpuinfo_arm64 *boot = &boot_cpu_data;
+	unsigned int diff = 0;
+
+	/*
+	 * The kernel can handle differing I-cache policies, but otherwise
+	 * caches should look identical. Userspace JITs will make use of
+	 * *minLine.
+	 */
+	diff |= CHECK_MASK(ctr, 0xffff3fff, boot, cur, cpu);
+
+	/*
+	 * Userspace may perform DC ZVA instructions. Mismatched block sizes
+	 * could result in too much or too little memory being zeroed if a
+	 * process is preempted and migrated between CPUs.
+	 */
+	diff |= CHECK(dczid, boot, cur, cpu);
+
+	/* If different, timekeeping will be broken (especially with KVM) */
+	diff |= CHECK(cntfrq, boot, cur, cpu);
+
+	/*
+	 * Even in big.LITTLE, processors should be identical instruction-set
+	 * wise.
+	 */
+	diff |= CHECK(id_aa64isar0, boot, cur, cpu);
+	diff |= CHECK(id_aa64isar1, boot, cur, cpu);
+
+	/*
+	 * Differing PARange support is fine as long as all peripherals and
+	 * memory are mapped within the minimum PARange of all CPUs.
+	 * Linux should not care about secure memory.
+	 * ID_AA64MMFR1 is currently RES0.
+	 */
+	diff |= CHECK_MASK(id_aa64mmfr0, 0xffffffffffff0ff0, boot, cur, cpu);
+	diff |= CHECK(id_aa64mmfr1, boot, cur, cpu);
+
+	/*
+	 * EL3 is not our concern.
+	 * ID_AA64PFR1 is currently RES0.
+	 */
+	diff |= CHECK_MASK(id_aa64pfr0, 0xffffffffffff0fff, boot, cur, cpu);
+	diff |= CHECK(id_aa64pfr1, boot, cur, cpu);
+
+	/*
+	 * If we have AArch32, we care about 32-bit features for compat. These
+	 * registers should be RES0 otherwise.
+	 */
+	diff |= CHECK(id_isar0, boot, cur, cpu);
+	diff |= CHECK(id_isar1, boot, cur, cpu);
+	diff |= CHECK(id_isar2, boot, cur, cpu);
+	diff |= CHECK(id_isar3, boot, cur, cpu);
+	diff |= CHECK(id_isar4, boot, cur, cpu);
+	diff |= CHECK(id_isar5, boot, cur, cpu);
+	diff |= CHECK(id_mmfr0, boot, cur, cpu);
+	diff |= CHECK(id_mmfr1, boot, cur, cpu);
+	diff |= CHECK(id_mmfr2, boot, cur, cpu);
+	diff |= CHECK(id_mmfr3, boot, cur, cpu);
+	diff |= CHECK(id_pfr0, boot, cur, cpu);
+	diff |= CHECK(id_pfr1, boot, cur, cpu);
+
+	/*
+	 * Mismatched CPU features are a recipe for disaster. Don't even
+	 * pretend to support them.
+	 */
+	WARN_TAINT_ONCE(diff, TAINT_CPU_OUT_OF_SPEC,
+			"Unsupported CPU feature variation.");
+}
+
+static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
+{
+	info->reg_cntfrq = arch_timer_get_cntfrq();
+	info->reg_ctr = read_cpuid_cachetype();
+	info->reg_dczid = read_cpuid(DCZID_EL0);
+	info->reg_midr = read_cpuid_id();
+
+	info->reg_id_aa64isar0 = read_cpuid(ID_AA64ISAR0_EL1);
+	info->reg_id_aa64isar1 = read_cpuid(ID_AA64ISAR1_EL1);
+	info->reg_id_aa64mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
+	info->reg_id_aa64mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
+	info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
+	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
+
+	info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
+	info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
+	info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
+	info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1);
+	info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1);
+	info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1);
+	info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1);
+	info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1);
+	info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1);
+	info->reg_id_mmfr3 = read_cpuid(ID_MMFR3_EL1);
+	info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
+	info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
+
+	cpuinfo_detect_icache_policy(info);
+}
+
+void cpuinfo_store_cpu(void)
+{
+	struct cpuinfo_arm64 *info = this_cpu_ptr(&cpu_data);
+	__cpuinfo_store_cpu(info);
+	cpuinfo_sanity_check(info);
+}
+
+void __init cpuinfo_store_boot_cpu(void)
+{
+	struct cpuinfo_arm64 *info = &per_cpu(cpu_data, 0);
+	__cpuinfo_store_cpu(info);
+
+	boot_cpu_data = *info;
+}
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index a7fb874b595..fe5b94078d8 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -315,20 +315,20 @@ static int brk_handler(unsigned long addr, unsigned int esr,
 {
 	siginfo_t info;
 
-	if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
-		return 0;
+	if (user_mode(regs)) {
+		info = (siginfo_t) {
+			.si_signo = SIGTRAP,
+			.si_errno = 0,
+			.si_code  = TRAP_BRKPT,
+			.si_addr  = (void __user *)instruction_pointer(regs),
+		};
 
-	if (!user_mode(regs))
+		force_sig_info(SIGTRAP, &info, current);
+	} else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
+		pr_warning("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
+	}
 
-	info = (siginfo_t) {
-		.si_signo = SIGTRAP,
-		.si_errno = 0,
-		.si_code  = TRAP_BRKPT,
-		.si_addr  = (void __user *)instruction_pointer(regs),
-	};
-
-	force_sig_info(SIGTRAP, &info, current);
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 66716c9b9e5..619b1dd7bcd 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -78,8 +78,7 @@ ENTRY(efi_stub_entry)
 
 	/* Turn off Dcache and MMU */
 	mrs	x0, CurrentEL
-	cmp	x0, #PSR_MODE_EL2t
-	ccmp	x0, #PSR_MODE_EL2h, #0x4, ne
+	cmp	x0, #CurrentEL_EL2
 	b.ne	1f
 	mrs	x0, sctlr_el2
 	bic	x0, x0, #1 << 0	// clear SCTLR.M
diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c
index 60e98a639ac..1317fef8dde 100644
--- a/arch/arm64/kernel/efi-stub.c
+++ b/arch/arm64/kernel/efi-stub.c
@@ -10,48 +10,16 @@
  *
  */
 #include <linux/efi.h>
-#include <linux/libfdt.h>
+#include <asm/efi.h>
 #include <asm/sections.h>
-#include <generated/compile.h>
-#include <generated/utsrelease.h>
 
-/*
- * AArch64 requires the DTB to be 8-byte aligned in the first 512MiB from
- * start of kernel and may not cross a 2MiB boundary. We set alignment to
- * 2MiB so we know it won't cross a 2MiB boundary.
- */
-#define EFI_FDT_ALIGN	SZ_2M   /* used by allocate_new_fdt_and_exit_boot() */
-#define MAX_FDT_OFFSET	SZ_512M
-
-#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
-
-static void efi_char16_printk(efi_system_table_t *sys_table_arg,
-			      efi_char16_t *str);
-
-static efi_status_t efi_open_volume(efi_system_table_t *sys_table,
-				    void *__image, void **__fh);
-static efi_status_t efi_file_close(void *handle);
-
-static efi_status_t
-efi_file_read(void *handle, unsigned long *size, void *addr);
-
-static efi_status_t
-efi_file_size(efi_system_table_t *sys_table, void *__fh,
-	      efi_char16_t *filename_16, void **handle, u64 *file_sz);
-
-/* Include shared EFI stub code */
-#include "../../../drivers/firmware/efi/efi-stub-helper.c"
-#include "../../../drivers/firmware/efi/fdt.c"
-#include "../../../drivers/firmware/efi/arm-stub.c"
-
-
-static efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
-					unsigned long *image_addr,
-					unsigned long *image_size,
-					unsigned long *reserve_addr,
-					unsigned long *reserve_size,
-					unsigned long dram_base,
-					efi_loaded_image_t *image)
+efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
+				 unsigned long *image_addr,
+				 unsigned long *image_size,
+				 unsigned long *reserve_addr,
+				 unsigned long *reserve_size,
+				 unsigned long dram_base,
+				 efi_loaded_image_t *image)
 {
 	efi_status_t status;
 	unsigned long kernel_size, kernel_memsize = 0;
@@ -71,7 +39,7 @@ static efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 		if (*image_addr != (dram_base + TEXT_OFFSET)) {
 			pr_efi_err(sys_table, "Failed to alloc kernel memory\n");
 			efi_free(sys_table, kernel_memsize, *image_addr);
-			return EFI_ERROR;
+			return EFI_LOAD_ERROR;
 		}
 		*image_size = kernel_memsize;
 	}
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 14db1f6e8d7..e72f3100958 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -414,13 +414,24 @@ static int __init arm64_enter_virtual_mode(void)
 	for_each_efi_memory_desc(&memmap, md) {
 		if (!(md->attribute & EFI_MEMORY_RUNTIME))
 			continue;
-		if (remap_region(md, &virt_md))
-			++count;
+		if (!remap_region(md, &virt_md))
+			goto err_unmap;
+		++count;
 	}
 
 	efi.systab = (__force void *)efi_lookup_mapped_addr(efi_system_table);
-	if (efi.systab)
-		set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+	if (!efi.systab) {
+		/*
+		 * If we have no virtual mapping for the System Table at this
+		 * point, the memory map doesn't cover the physical offset where
+		 * it resides. This means the System Table will be inaccessible
+		 * to Runtime Services themselves once the virtual mapping is
+		 * installed.
+		 */
+		pr_err("Failed to remap EFI System Table -- buggy firmware?\n");
+		goto err_unmap;
+	}
+	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
 
 	local_irq_save(flags);
 	cpu_switch_mm(idmap_pg_dir, &init_mm);
@@ -449,21 +460,18 @@ static int __init arm64_enter_virtual_mode(void)
 
 	/* Set up runtime services function pointers */
 	runtime = efi.systab->runtime;
-	efi.get_time = runtime->get_time;
-	efi.set_time = runtime->set_time;
-	efi.get_wakeup_time = runtime->get_wakeup_time;
-	efi.set_wakeup_time = runtime->set_wakeup_time;
-	efi.get_variable = runtime->get_variable;
-	efi.get_next_variable = runtime->get_next_variable;
-	efi.set_variable = runtime->set_variable;
-	efi.query_variable_info = runtime->query_variable_info;
-	efi.update_capsule = runtime->update_capsule;
-	efi.query_capsule_caps = runtime->query_capsule_caps;
-	efi.get_next_high_mono_count = runtime->get_next_high_mono_count;
-	efi.reset_system = runtime->reset_system;
-
+	efi_native_runtime_setup();
 	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 
 	return 0;
+
+err_unmap:
+	/* unmap all mappings that succeeded: there are 'count' of those */
+	for (virt_md = virtmap; count--; virt_md += memmap.desc_size) {
+		md = virt_md;
+		iounmap((__force void __iomem *)md->virt_addr);
+	}
+	kfree(virtmap);
+	return -1;
 }
 early_initcall(arm64_enter_virtual_mode);
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index d358ccacfc0..c44a82f146b 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -52,7 +52,7 @@ ENDPROC(fpsimd_load_state)
 ENTRY(fpsimd_save_partial_state)
 	fpsimd_save_partial x0, 1, 8, 9
 	ret
-ENDPROC(fpsimd_load_partial_state)
+ENDPROC(fpsimd_save_partial_state)
 
 /*
  * Load the bottom n FP registers.
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index b051871f296..38e704e597f 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -96,11 +96,6 @@
  *     - ftrace_graph_caller to set up an exit hook
  */
 ENTRY(_mcount)
-#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	ldr	x0, =ftrace_trace_stop
-	ldr	x0, [x0]		// if ftrace_trace_stop
-	ret				//   return;
-#endif
 	mcount_enter
 
 	ldr	x0, =ftrace_trace_function
@@ -205,7 +200,7 @@ ENDPROC(ftrace_graph_caller)
  *
  * Run ftrace_return_to_handler() before going back to parent.
  * @fp is checked against the value passed by ftrace_graph_caller()
- * only when CONFIG_FUNCTION_GRAPH_FP_TEST is enabled.
+ * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
  */
 ENTRY(return_to_handler)
 	str	x0, [sp, #-16]!
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index bf017f4ffb4..f0b5e5120a8 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -27,7 +27,32 @@
 #include <asm/esr.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
-#include <asm/unistd32.h>
+
+/*
+ * Context tracking subsystem.  Used to instrument transitions
+ * between user and kernel mode.
+ */
+	.macro ct_user_exit, syscall = 0
+#ifdef CONFIG_CONTEXT_TRACKING
+	bl	context_tracking_user_exit
+	.if \syscall == 1
+	/*
+	 * Save/restore needed during syscalls.  Restore syscall arguments from
+	 * the values already saved on stack during kernel_entry.
+	 */
+	ldp	x0, x1, [sp]
+	ldp	x2, x3, [sp, #S_X2]
+	ldp	x4, x5, [sp, #S_X4]
+	ldp	x6, x7, [sp, #S_X6]
+	.endif
+#endif
+	.endm
+
+	.macro ct_user_enter
+#ifdef CONFIG_CONTEXT_TRACKING
+	bl	context_tracking_user_enter
+#endif
+	.endm
 
 /*
  * Bad Abort numbers
@@ -91,6 +116,7 @@
 	.macro	kernel_exit, el, ret = 0
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
+	ct_user_enter
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
 	.endif
 	.if	\ret
@@ -279,7 +305,6 @@ el1_sp_pc:
 	 */
 	mrs	x0, far_el1
 	enable_dbg
-	mov	x1, x25
 	mov	x2, sp
 	b	do_sp_pc_abort
 el1_undef:
@@ -354,7 +379,6 @@ el0_sync:
 	lsr	x24, x25, #ESR_EL1_EC_SHIFT	// exception class
 	cmp	x24, #ESR_EL1_EC_SVC64		// SVC in 64-bit state
 	b.eq	el0_svc
-	adr	lr, ret_to_user
 	cmp	x24, #ESR_EL1_EC_DABT_EL0	// data abort in EL0
 	b.eq	el0_da
 	cmp	x24, #ESR_EL1_EC_IABT_EL0	// instruction abort in EL0
@@ -383,7 +407,6 @@ el0_sync_compat:
 	lsr	x24, x25, #ESR_EL1_EC_SHIFT	// exception class
 	cmp	x24, #ESR_EL1_EC_SVC32		// SVC in 32-bit state
 	b.eq	el0_svc_compat
-	adr	lr, ret_to_user
 	cmp	x24, #ESR_EL1_EC_DABT_EL0	// data abort in EL0
 	b.eq	el0_da
 	cmp	x24, #ESR_EL1_EC_IABT_EL0	// instruction abort in EL0
@@ -426,48 +449,59 @@ el0_da:
 	/*
 	 * Data abort handling
 	 */
-	mrs	x0, far_el1
-	bic	x0, x0, #(0xff << 56)
+	mrs	x26, far_el1
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
+	ct_user_exit
+	bic	x0, x26, #(0xff << 56)
 	mov	x1, x25
 	mov	x2, sp
+	adr	lr, ret_to_user
 	b	do_mem_abort
 el0_ia:
 	/*
 	 * Instruction abort handling
 	 */
-	mrs	x0, far_el1
+	mrs	x26, far_el1
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
+	ct_user_exit
+	mov	x0, x26
 	orr	x1, x25, #1 << 24		// use reserved ISS bit for instruction aborts
 	mov	x2, sp
+	adr	lr, ret_to_user
 	b	do_mem_abort
 el0_fpsimd_acc:
 	/*
 	 * Floating Point or Advanced SIMD access
 	 */
 	enable_dbg
+	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
+	adr	lr, ret_to_user
 	b	do_fpsimd_acc
 el0_fpsimd_exc:
 	/*
 	 * Floating Point or Advanced SIMD exception
 	 */
 	enable_dbg
+	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
+	adr	lr, ret_to_user
 	b	do_fpsimd_exc
 el0_sp_pc:
 	/*
 	 * Stack or PC alignment exception handling
 	 */
-	mrs	x0, far_el1
+	mrs	x26, far_el1
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
+	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
+	adr	lr, ret_to_user
 	b	do_sp_pc_abort
 el0_undef:
 	/*
@@ -475,7 +509,9 @@ el0_undef:
 	 */
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
+	ct_user_exit
 	mov	x0, sp
+	adr	lr, ret_to_user
 	b	do_undefinstr
 el0_dbg:
 	/*
@@ -487,12 +523,15 @@ el0_dbg:
 	mov	x2, sp
 	bl	do_debug_exception
 	enable_dbg
+	ct_user_exit
 	b	ret_to_user
 el0_inv:
 	enable_dbg
+	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mrs	x2, esr_el1
+	adr	lr, ret_to_user
 	b	bad_mode
 ENDPROC(el0_sync)
 
@@ -505,6 +544,7 @@ el0_irq_naked:
 	bl	trace_hardirqs_off
 #endif
 
+	ct_user_exit
 	irq_handler
 
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -609,6 +649,7 @@ el0_svc:
 el0_svc_naked:					// compat entry point
 	stp	x0, scno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
 	enable_dbg_and_irq
+	ct_user_exit 1
 
 	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall hooks
 	tst	x16, #_TIF_SYSCALL_WORK
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index a96d3a6a63f..144f10567f8 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -22,6 +22,7 @@
 
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
@@ -35,37 +36,31 @@
 #include <asm/page.h>
 #include <asm/virt.h>
 
-/*
- * swapper_pg_dir is the virtual address of the initial page table. We place
- * the page tables 3 * PAGE_SIZE below KERNEL_RAM_VADDR. The idmap_pg_dir has
- * 2 pages and is placed below swapper_pg_dir.
- */
 #define KERNEL_RAM_VADDR	(PAGE_OFFSET + TEXT_OFFSET)
 
-#if (KERNEL_RAM_VADDR & 0xfffff) != 0x80000
-#error KERNEL_RAM_VADDR must start at 0xXXX80000
+#if (TEXT_OFFSET & 0xf) != 0
+#error TEXT_OFFSET must be at least 16B aligned
+#elif (PAGE_OFFSET & 0xfffff) != 0
+#error PAGE_OFFSET must be at least 2MB aligned
+#elif TEXT_OFFSET > 0xfffff
+#error TEXT_OFFSET must be less than 2MB
 #endif
 
-#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
-#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
-
-	.globl	swapper_pg_dir
-	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - SWAPPER_DIR_SIZE
-
-	.globl	idmap_pg_dir
-	.equ	idmap_pg_dir, swapper_pg_dir - IDMAP_DIR_SIZE
-
-	.macro	pgtbl, ttb0, ttb1, phys
-	add	\ttb1, \phys, #TEXT_OFFSET - SWAPPER_DIR_SIZE
-	sub	\ttb0, \ttb1, #IDMAP_DIR_SIZE
+	.macro	pgtbl, ttb0, ttb1, virt_to_phys
+	ldr	\ttb1, =swapper_pg_dir
+	ldr	\ttb0, =idmap_pg_dir
+	add	\ttb1, \ttb1, \virt_to_phys
+	add	\ttb0, \ttb0, \virt_to_phys
 	.endm
 
 #ifdef CONFIG_ARM64_64K_PAGES
 #define BLOCK_SHIFT	PAGE_SHIFT
 #define BLOCK_SIZE	PAGE_SIZE
+#define TABLE_SHIFT	PMD_SHIFT
 #else
 #define BLOCK_SHIFT	SECTION_SHIFT
 #define BLOCK_SIZE	SECTION_SIZE
+#define TABLE_SHIFT	PUD_SHIFT
 #endif
 
 #define KERNEL_START	KERNEL_RAM_VADDR
@@ -120,9 +115,9 @@ efi_head:
 	b	stext				// branch to kernel start, magic
 	.long	0				// reserved
 #endif
-	.quad	TEXT_OFFSET			// Image load offset from start of RAM
-	.quad	0				// reserved
-	.quad	0				// reserved
+	.quad	_kernel_offset_le		// Image load offset from start of RAM, little-endian
+	.quad	_kernel_size_le			// Effective size of kernel image, little-endian
+	.quad	_kernel_flags_le		// Informative flags, little-endian
 	.quad	0				// reserved
 	.quad	0				// reserved
 	.quad	0				// reserved
@@ -270,8 +265,7 @@ ENDPROC(stext)
  */
 ENTRY(el2_setup)
 	mrs	x0, CurrentEL
-	cmp	x0, #PSR_MODE_EL2t
-	ccmp	x0, #PSR_MODE_EL2h, #0x4, ne
+	cmp	x0, #CurrentEL_EL2
 	b.ne	1f
 	mrs	x0, sctlr_el2
 CPU_BE(	orr	x0, x0, #(1 << 25)	)	// Set the EE bit for EL2
@@ -296,6 +290,23 @@ CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	msr	cnthctl_el2, x0
 	msr	cntvoff_el2, xzr		// Clear virtual offset
 
+#ifdef CONFIG_ARM_GIC_V3
+	/* GICv3 system register access */
+	mrs	x0, id_aa64pfr0_el1
+	ubfx	x0, x0, #24, #4
+	cmp	x0, #1
+	b.ne	3f
+
+	mrs_s	x0, ICC_SRE_EL2
+	orr	x0, x0, #ICC_SRE_EL2_SRE	// Set ICC_SRE_EL2.SRE==1
+	orr	x0, x0, #ICC_SRE_EL2_ENABLE	// Set ICC_SRE_EL2.Enable==1
+	msr_s	ICC_SRE_EL2, x0
+	isb					// Make sure SRE is now set
+	msr_s	ICH_HCR_EL2, xzr		// Reset ICC_HCR_EL2 to defaults
+
+3:
+#endif
+
 	/* Populate ID registers. */
 	mrs	x0, midr_el1
 	mrs	x1, mpidr_el1
@@ -414,7 +425,7 @@ ENTRY(secondary_startup)
 	mov	x23, x0				// x23=current cpu_table
 	cbz	x23, __error_p			// invalid processor (x23=0)?
 
-	pgtbl	x25, x26, x24			// x25=TTBR0, x26=TTBR1
+	pgtbl	x25, x26, x28			// x25=TTBR0, x26=TTBR1
 	ldr	x12, [x23, #CPU_INFO_SETUP]
 	add	x12, x12, x28			// __virt_to_phys
 	blr	x12				// initialise processor
@@ -456,8 +467,13 @@ ENDPROC(__enable_mmu)
  *  x27 = *virtual* address to jump to upon completion
  *
  * other registers depend on the function called upon completion
+ *
+ * We align the entire function to the smallest power of two larger than it to
+ * ensure it fits within a single block map entry. Otherwise were PHYS_OFFSET
+ * close to the end of a 512MB or 1GB block we might require an additional
+ * table to map the entire function.
  */
-	.align	6
+	.align	4
 __turn_mmu_on:
 	msr	sctlr_el1, x0
 	isb
@@ -480,17 +496,38 @@ ENDPROC(__calc_phys_offset)
 	.quad	PAGE_OFFSET
 
 /*
- * Macro to populate the PGD for the corresponding block entry in the next
- * level (tbl) for the given virtual address.
+ * Macro to create a table entry to the next page.
+ *
+ *	tbl:	page table address
+ *	virt:	virtual address
+ *	shift:	#imm page table shift
+ *	ptrs:	#imm pointers per table page
+ *
+ * Preserves:	virt
+ * Corrupts:	tmp1, tmp2
+ * Returns:	tbl -> next level table page address
+ */
+	.macro	create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2
+	lsr	\tmp1, \virt, #\shift
+	and	\tmp1, \tmp1, #\ptrs - 1	// table index
+	add	\tmp2, \tbl, #PAGE_SIZE
+	orr	\tmp2, \tmp2, #PMD_TYPE_TABLE	// address of next table and entry type
+	str	\tmp2, [\tbl, \tmp1, lsl #3]
+	add	\tbl, \tbl, #PAGE_SIZE		// next level table page
+	.endm
+
+/*
+ * Macro to populate the PGD (and possibily PUD) for the corresponding
+ * block entry in the next level (tbl) for the given virtual address.
  *
- * Preserves:	pgd, tbl, virt
+ * Preserves:	tbl, next, virt
  * Corrupts:	tmp1, tmp2
  */
-	.macro	create_pgd_entry, pgd, tbl, virt, tmp1, tmp2
-	lsr	\tmp1, \virt, #PGDIR_SHIFT
-	and	\tmp1, \tmp1, #PTRS_PER_PGD - 1	// PGD index
-	orr	\tmp2, \tbl, #3			// PGD entry table type
-	str	\tmp2, [\pgd, \tmp1, lsl #3]
+	.macro	create_pgd_entry, tbl, virt, tmp1, tmp2
+	create_table_entry \tbl, \virt, PGDIR_SHIFT, PTRS_PER_PGD, \tmp1, \tmp2
+#if SWAPPER_PGTABLE_LEVELS == 3
+	create_table_entry \tbl, \virt, TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2
+#endif
 	.endm
 
 /*
@@ -523,7 +560,7 @@ ENDPROC(__calc_phys_offset)
  *   - pgd entry for fixed mappings (TTBR1)
  */
 __create_page_tables:
-	pgtbl	x25, x26, x24			// idmap_pg_dir and swapper_pg_dir addresses
+	pgtbl	x25, x26, x28			// idmap_pg_dir and swapper_pg_dir addresses
 	mov	x27, lr
 
 	/*
@@ -551,10 +588,10 @@ __create_page_tables:
 	/*
 	 * Create the identity mapping.
 	 */
-	add	x0, x25, #PAGE_SIZE		// section table address
+	mov	x0, x25				// idmap_pg_dir
 	ldr	x3, =KERNEL_START
 	add	x3, x3, x28			// __pa(KERNEL_START)
-	create_pgd_entry x25, x0, x3, x5, x6
+	create_pgd_entry x0, x3, x5, x6
 	ldr	x6, =KERNEL_END
 	mov	x5, x3				// __pa(KERNEL_START)
 	add	x6, x6, x28			// __pa(KERNEL_END)
@@ -563,9 +600,9 @@ __create_page_tables:
 	/*
 	 * Map the kernel image (starting with PHYS_OFFSET).
 	 */
-	add	x0, x26, #PAGE_SIZE		// section table address
+	mov	x0, x26				// swapper_pg_dir
 	mov	x5, #PAGE_OFFSET
-	create_pgd_entry x26, x0, x5, x3, x6
+	create_pgd_entry x0, x5, x3, x6
 	ldr	x6, =KERNEL_END
 	mov	x3, x24				// phys offset
 	create_block_map x0, x7, x3, x5, x6
@@ -587,13 +624,6 @@ __create_page_tables:
 	create_block_map x0, x7, x3, x5, x6
 1:
 	/*
-	 * Create the pgd entry for the fixed mappings.
-	 */
-	ldr	x5, =FIXADDR_TOP		// Fixed mapping virtual address
-	add	x0, x26, #2 * PAGE_SIZE		// section table address
-	create_pgd_entry x26, x0, x5, x6, x7
-
-	/*
 	 * Since the page tables have been populated with non-cacheable
 	 * accesses (MMU disabled), invalidate the idmap and swapper page
 	 * tables again to remove any speculatively loaded cache lines.
@@ -612,7 +642,7 @@ ENDPROC(__create_page_tables)
 __switch_data:
 	.quad	__mmap_switched
 	.quad	__bss_start			// x6
-	.quad	_end				// x7
+	.quad	__bss_stop			// x7
 	.quad	processor_id			// x4
 	.quad	__fdt_pointer			// x5
 	.quad	memstart_addr			// x6
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 0959611d9ff..a272f335c28 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -19,6 +19,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
 #include <asm/ptrace.h>
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
new file mode 100644
index 00000000000..8fae0756e17
--- /dev/null
+++ b/arch/arm64/kernel/image.h
@@ -0,0 +1,62 @@
+/*
+ * Linker script macros to generate Image header fields.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_IMAGE_H
+#define __ASM_IMAGE_H
+
+#ifndef LINKER_SCRIPT
+#error This file should only be included in vmlinux.lds.S
+#endif
+
+/*
+ * There aren't any ELF relocations we can use to endian-swap values known only
+ * at link time (e.g. the subtraction of two symbol addresses), so we must get
+ * the linker to endian-swap certain values before emitting them.
+ */
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define DATA_LE64(data)					\
+	((((data) & 0x00000000000000ff) << 56) |	\
+	 (((data) & 0x000000000000ff00) << 40) |	\
+	 (((data) & 0x0000000000ff0000) << 24) |	\
+	 (((data) & 0x00000000ff000000) << 8)  |	\
+	 (((data) & 0x000000ff00000000) >> 8)  |	\
+	 (((data) & 0x0000ff0000000000) >> 24) |	\
+	 (((data) & 0x00ff000000000000) >> 40) |	\
+	 (((data) & 0xff00000000000000) >> 56))
+#else
+#define DATA_LE64(data) ((data) & 0xffffffffffffffff)
+#endif
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define __HEAD_FLAG_BE	1
+#else
+#define __HEAD_FLAG_BE	0
+#endif
+
+#define __HEAD_FLAGS	(__HEAD_FLAG_BE << 0)
+
+/*
+ * These will output as part of the Image header, which should be little-endian
+ * regardless of the endianness of the kernel. While constant values could be
+ * endian swapped in head.S, all are done here for consistency.
+ */
+#define HEAD_SYMBOLS						\
+	_kernel_size_le		= DATA_LE64(_end - _text);	\
+	_kernel_offset_le	= DATA_LE64(TEXT_OFFSET);	\
+	_kernel_flags_le	= DATA_LE64(__HEAD_FLAGS);
+
+#endif /* __ASM_IMAGE_H */
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 7787208e8cc..997e6b27ff6 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -28,7 +28,7 @@
  * See Documentation/arm/kernel_user_helpers.txt for formal definitions.
  */
 
-#include <asm/unistd32.h>
+#include <asm/unistd.h>
 
 	.align	5
 	.globl	__kuser_helper_start
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 43b7c34f92c..1309d64aa92 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -51,6 +51,12 @@
 #include <asm/processor.h>
 #include <asm/stacktrace.h>
 
+#ifdef CONFIG_CC_STACKPROTECTOR
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __read_mostly;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
 static void setup_restart(void)
 {
 	/*
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 9e9798f9117..553954771a6 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -235,7 +235,7 @@ static void psci_sys_poweroff(void)
  * PSCI Function IDs for v0.2+ are well defined so use
  * standard values.
  */
-static int psci_0_2_init(struct device_node *np)
+static int __init psci_0_2_init(struct device_node *np)
 {
 	int err, ver;
 
@@ -296,7 +296,7 @@ out_put_node:
 /*
  * PSCI < v0.2 get PSCI Function IDs via DT.
  */
-static int psci_0_1_init(struct device_node *np)
+static int __init psci_0_1_init(struct device_node *np)
 {
 	u32 id;
 	int err;
@@ -434,9 +434,11 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	return 0;
 }
 #endif
+#endif
 
 const struct cpu_operations cpu_psci_ops = {
 	.name		= "psci",
+#ifdef CONFIG_SMP
 	.cpu_init	= cpu_psci_cpu_init,
 	.cpu_prepare	= cpu_psci_cpu_prepare,
 	.cpu_boot	= cpu_psci_cpu_boot,
@@ -445,6 +447,6 @@ const struct cpu_operations cpu_psci_ops = {
 	.cpu_die	= cpu_psci_cpu_die,
 	.cpu_kill	= cpu_psci_cpu_kill,
 #endif
+#endif
 };
 
-#endif
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 3e926b9c064..0310811bd77 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -19,6 +19,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/audit.h>
 #include <linux/compat.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
@@ -39,6 +40,7 @@
 #include <asm/compat.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
+#include <asm/syscall.h>
 #include <asm/traps.h>
 #include <asm/system_misc.h>
 
@@ -655,11 +657,16 @@ static int compat_gpr_get(struct task_struct *target,
 			reg = task_pt_regs(target)->regs[idx];
 		}
 
-		ret = copy_to_user(ubuf, &reg, sizeof(reg));
-		if (ret)
-			break;
+		if (kbuf) {
+			memcpy(kbuf, &reg, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
+			ret = copy_to_user(ubuf, &reg, sizeof(reg));
+			if (ret)
+				break;
 
-		ubuf += sizeof(reg);
+			ubuf += sizeof(reg);
+		}
 	}
 
 	return ret;
@@ -689,11 +696,16 @@ static int compat_gpr_set(struct task_struct *target,
 		unsigned int idx = start + i;
 		compat_ulong_t reg;
 
-		ret = copy_from_user(&reg, ubuf, sizeof(reg));
-		if (ret)
-			return ret;
+		if (kbuf) {
+			memcpy(&reg, kbuf, sizeof(reg));
+			kbuf += sizeof(reg);
+		} else {
+			ret = copy_from_user(&reg, ubuf, sizeof(reg));
+			if (ret)
+				return ret;
 
-		ubuf += sizeof(reg);
+			ubuf += sizeof(reg);
+		}
 
 		switch (idx) {
 		case 15:
@@ -827,6 +839,7 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off,
 				    compat_ulong_t val)
 {
 	int ret;
+	mm_segment_t old_fs = get_fs();
 
 	if (off & 3 || off >= COMPAT_USER_SZ)
 		return -EIO;
@@ -834,10 +847,13 @@ static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off,
 	if (off >= sizeof(compat_elf_gregset_t))
 		return 0;
 
+	set_fs(KERNEL_DS);
 	ret = copy_regset_from_user(tsk, &user_aarch32_view,
 				    REGSET_COMPAT_GPR, off,
 				    sizeof(compat_ulong_t),
 				    &val);
+	set_fs(old_fs);
+
 	return ret;
 }
 
@@ -1099,11 +1115,20 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, regs->syscallno);
 
+#ifdef CONFIG_AUDITSYSCALL
+	audit_syscall_entry(syscall_get_arch(), regs->syscallno,
+		regs->orig_x0, regs->regs[1], regs->regs[2], regs->regs[3]);
+#endif
+
 	return regs->syscallno;
 }
 
 asmlinkage void syscall_trace_exit(struct pt_regs *regs)
 {
+#ifdef CONFIG_AUDITSYSCALL
+	audit_syscall_exit(regs);
+#endif
+
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_exit(regs, regs_return_value(regs));
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 46d1125571f..f6f0ccf35ae 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -45,6 +45,7 @@
 #include <linux/efi.h>
 
 #include <asm/fixmap.h>
+#include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/cputable.h>
@@ -77,7 +78,6 @@ unsigned int compat_elf_hwcap2 __read_mostly;
 #endif
 
 static const char *cpu_name;
-static const char *machine_name;
 phys_addr_t __fdt_pointer __initdata;
 
 /*
@@ -219,6 +219,8 @@ static void __init setup_processor(void)
 	sprintf(init_utsname()->machine, ELF_PLATFORM);
 	elf_hwcap = 0;
 
+	cpuinfo_store_boot_cpu();
+
 	/*
 	 * Check for sane CTR_EL0.CWG value.
 	 */
@@ -307,8 +309,6 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys)
 		while (true)
 			cpu_relax();
 	}
-
-	machine_name = of_flat_dt_get_machine_name();
 }
 
 /*
@@ -417,14 +417,12 @@ static int __init arm64_device_init(void)
 }
 arch_initcall_sync(arm64_device_init);
 
-static DEFINE_PER_CPU(struct cpu, cpu_data);
-
 static int __init topology_init(void)
 {
 	int i;
 
 	for_each_possible_cpu(i) {
-		struct cpu *cpu = &per_cpu(cpu_data, i);
+		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
 		cpu->hotpluggable = 1;
 		register_cpu(cpu, i);
 	}
@@ -449,10 +447,21 @@ static int c_show(struct seq_file *m, void *v)
 {
 	int i;
 
-	seq_printf(m, "Processor\t: %s rev %d (%s)\n",
-		   cpu_name, read_cpuid_id() & 15, ELF_PLATFORM);
+	/*
+	 * Dump out the common processor features in a single line. Userspace
+	 * should read the hwcaps with getauxval(AT_HWCAP) rather than
+	 * attempting to parse this.
+	 */
+	seq_puts(m, "features\t:");
+	for (i = 0; hwcap_str[i]; i++)
+		if (elf_hwcap & (1 << i))
+			seq_printf(m, " %s", hwcap_str[i]);
+	seq_puts(m, "\n\n");
 
 	for_each_online_cpu(i) {
+		struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
+		u32 midr = cpuinfo->reg_midr;
+
 		/*
 		 * glibc reads /proc/cpuinfo to determine the number of
 		 * online processors, looking for lines beginning with
@@ -461,25 +470,13 @@ static int c_show(struct seq_file *m, void *v)
 #ifdef CONFIG_SMP
 		seq_printf(m, "processor\t: %d\n", i);
 #endif
+		seq_printf(m, "implementer\t: 0x%02x\n",
+			   MIDR_IMPLEMENTOR(midr));
+		seq_printf(m, "variant\t\t: 0x%x\n", MIDR_VARIANT(midr));
+		seq_printf(m, "partnum\t\t: 0x%03x\n", MIDR_PARTNUM(midr));
+		seq_printf(m, "revision\t: 0x%x\n\n", MIDR_REVISION(midr));
 	}
 
-	/* dump out the processor features */
-	seq_puts(m, "Features\t: ");
-
-	for (i = 0; hwcap_str[i]; i++)
-		if (elf_hwcap & (1 << i))
-			seq_printf(m, "%s ", hwcap_str[i]);
-
-	seq_printf(m, "\nCPU implementer\t: 0x%02x\n", read_cpuid_id() >> 24);
-	seq_printf(m, "CPU architecture: AArch64\n");
-	seq_printf(m, "CPU variant\t: 0x%x\n", (read_cpuid_id() >> 20) & 15);
-	seq_printf(m, "CPU part\t: 0x%03x\n", (read_cpuid_id() >> 4) & 0xfff);
-	seq_printf(m, "CPU revision\t: %d\n", read_cpuid_id() & 15);
-
-	seq_puts(m, "\n");
-
-	seq_printf(m, "Hardware\t: %s\n", machine_name);
-
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 3491c638f17..c5ee208321c 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -27,7 +27,7 @@
 #include <asm/fpsimd.h>
 #include <asm/signal32.h>
 #include <asm/uaccess.h>
-#include <asm/unistd32.h>
+#include <asm/unistd.h>
 
 struct compat_sigcontext {
 	/* We always set these two fields to 0 */
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 40f38f46c8e..3e2f5ebbf63 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -39,6 +39,7 @@
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
+#include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
 #include <asm/mmu_context.h>
@@ -155,6 +156,11 @@ asmlinkage void secondary_start_kernel(void)
 		cpu_ops[cpu]->cpu_postboot();
 
 	/*
+	 * Log the CPU info before it is marked online and might get read.
+	 */
+	cpuinfo_store_cpu();
+
+	/*
 	 * Enable GIC and timers.
 	 */
 	notify_cpu_starting(cpu);
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 1fa9ce4afd8..55a99b9a97e 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -119,7 +119,7 @@ int cpu_suspend(unsigned long arg)
 extern struct sleep_save_sp sleep_save_sp;
 extern phys_addr_t sleep_idmap_phys;
 
-static int cpu_suspend_init(void)
+static int __init cpu_suspend_init(void)
 {
 	void *ctx_ptr;
 
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 26e9c4eeaba..de2b0226e06 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -26,7 +26,7 @@
 #include <linux/uaccess.h>
 
 #include <asm/cacheflush.h>
-#include <asm/unistd32.h>
+#include <asm/unistd.h>
 
 static inline void
 do_compat_cache_op(unsigned long start, unsigned long end, int flags)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 43514f90591..b6ee26b0939 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/sched.h>
 
+#include <asm/cputype.h>
 #include <asm/topology.h>
 
 static int __init get_cpu_for_node(struct device_node *node)
@@ -188,13 +189,9 @@ static int __init parse_dt_topology(void)
 	 * Check that all cores are in the topology; the SMP code will
 	 * only mark cores described in the DT as possible.
 	 */
-	for_each_possible_cpu(cpu) {
-		if (cpu_topology[cpu].cluster_id == -1) {
-			pr_err("CPU%d: No topology information specified\n",
-			       cpu);
+	for_each_possible_cpu(cpu)
+		if (cpu_topology[cpu].cluster_id == -1)
 			ret = -EINVAL;
-		}
-	}
 
 out_map:
 	of_node_put(map);
@@ -219,14 +216,6 @@ static void update_siblings_masks(unsigned int cpuid)
 	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
 	int cpu;
 
-	if (cpuid_topo->cluster_id == -1) {
-		/*
-		 * DT does not contain topology information for this cpu.
-		 */
-		pr_debug("CPU%u: No topology information configured\n", cpuid);
-		return;
-	}
-
 	/* update core and thread sibling masks */
 	for_each_possible_cpu(cpu) {
 		cpu_topo = &cpu_topology[cpu];
@@ -249,6 +238,36 @@ static void update_siblings_masks(unsigned int cpuid)
 
 void store_cpu_topology(unsigned int cpuid)
 {
+	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
+	u64 mpidr;
+
+	if (cpuid_topo->cluster_id != -1)
+		goto topology_populated;
+
+	mpidr = read_cpuid_mpidr();
+
+	/* Uniprocessor systems can rely on default topology values */
+	if (mpidr & MPIDR_UP_BITMASK)
+		return;
+
+	/* Create cpu topology mapping based on MPIDR. */
+	if (mpidr & MPIDR_MT_BITMASK) {
+		/* Multiprocessor system : Multi-threads per core */
+		cpuid_topo->thread_id  = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+		cpuid_topo->cluster_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+	} else {
+		/* Multiprocessor system : Single-thread per core */
+		cpuid_topo->thread_id  = -1;
+		cpuid_topo->core_id    = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+		cpuid_topo->cluster_id = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	}
+
+	pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n",
+		 cpuid, cpuid_topo->cluster_id, cpuid_topo->core_id,
+		 cpuid_topo->thread_id, mpidr);
+
+topology_populated:
 	update_siblings_masks(cpuid);
 }
 
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c43cfa9b830..02cd3f023e9 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -156,7 +156,7 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 		frame.pc = thread_saved_pc(tsk);
 	}
 
-	printk("Call trace:\n");
+	pr_emerg("Call trace:\n");
 	while (1) {
 		unsigned long where = frame.pc;
 		int ret;
@@ -331,17 +331,22 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 
 void __pte_error(const char *file, int line, unsigned long val)
 {
-	printk("%s:%d: bad pte %016lx.\n", file, line, val);
+	pr_crit("%s:%d: bad pte %016lx.\n", file, line, val);
 }
 
 void __pmd_error(const char *file, int line, unsigned long val)
 {
-	printk("%s:%d: bad pmd %016lx.\n", file, line, val);
+	pr_crit("%s:%d: bad pmd %016lx.\n", file, line, val);
+}
+
+void __pud_error(const char *file, int line, unsigned long val)
+{
+	pr_crit("%s:%d: bad pud %016lx.\n", file, line, val);
 }
 
 void __pgd_error(const char *file, int line, unsigned long val)
 {
-	printk("%s:%d: bad pgd %016lx.\n", file, line, val);
+	pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val);
 }
 
 void __init trap_init(void)
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 50384fec56c..24f2e8c6247 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -88,22 +88,29 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = AARCH32_VECTORS_BASE;
-	int ret;
+	static struct vm_special_mapping spec = {
+		.name	= "[vectors]",
+		.pages	= vectors_page,
+
+	};
+	void *ret;
 
 	down_write(&mm->mmap_sem);
 	current->mm->context.vdso = (void *)addr;
 
 	/* Map vectors page at the high address. */
-	ret = install_special_mapping(mm, addr, PAGE_SIZE,
-				      VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC,
-				      vectors_page);
+	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
+				       VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC,
+				       &spec);
 
 	up_write(&mm->mmap_sem);
 
-	return ret;
+	return PTR_ERR_OR_ZERO(ret);
 }
 #endif /* CONFIG_COMPAT */
 
+static struct vm_special_mapping vdso_spec[2];
+
 static int __init vdso_init(void)
 {
 	int i;
@@ -114,8 +121,8 @@ static int __init vdso_init(void)
 	}
 
 	vdso_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
-	pr_info("vdso: %ld pages (%ld code, %ld data) at base %p\n",
-		vdso_pages + 1, vdso_pages, 1L, &vdso_start);
+	pr_info("vdso: %ld pages (%ld code @ %p, %ld data @ %p)\n",
+		vdso_pages + 1, vdso_pages, &vdso_start, 1L, vdso_data);
 
 	/* Allocate the vDSO pagelist, plus a page for the data. */
 	vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
@@ -123,12 +130,23 @@ static int __init vdso_init(void)
 	if (vdso_pagelist == NULL)
 		return -ENOMEM;
 
+	/* Grab the vDSO data page. */
+	vdso_pagelist[0] = virt_to_page(vdso_data);
+
 	/* Grab the vDSO code pages. */
 	for (i = 0; i < vdso_pages; i++)
-		vdso_pagelist[i] = virt_to_page(&vdso_start + i * PAGE_SIZE);
+		vdso_pagelist[i + 1] = virt_to_page(&vdso_start + i * PAGE_SIZE);
 
-	/* Grab the vDSO data page. */
-	vdso_pagelist[i] = virt_to_page(vdso_data);
+	/* Populate the special mapping structures */
+	vdso_spec[0] = (struct vm_special_mapping) {
+		.name	= "[vvar]",
+		.pages	= vdso_pagelist,
+	};
+
+	vdso_spec[1] = (struct vm_special_mapping) {
+		.name	= "[vdso]",
+		.pages	= &vdso_pagelist[1],
+	};
 
 	return 0;
 }
@@ -138,52 +156,42 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 				int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
-	unsigned long vdso_base, vdso_mapping_len;
-	int ret;
+	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+	void *ret;
 
+	vdso_text_len = vdso_pages << PAGE_SHIFT;
 	/* Be sure to map the data page */
-	vdso_mapping_len = (vdso_pages + 1) << PAGE_SHIFT;
+	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
 
 	down_write(&mm->mmap_sem);
 	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
-		ret = vdso_base;
+		ret = ERR_PTR(vdso_base);
 		goto up_fail;
 	}
-	mm->context.vdso = (void *)vdso_base;
-
-	ret = install_special_mapping(mm, vdso_base, vdso_mapping_len,
-				      VM_READ|VM_EXEC|
-				      VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				      vdso_pagelist);
-	if (ret) {
-		mm->context.vdso = NULL;
+	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
+				       VM_READ|VM_MAYREAD,
+				       &vdso_spec[0]);
+	if (IS_ERR(ret))
 		goto up_fail;
-	}
 
-up_fail:
-	up_write(&mm->mmap_sem);
+	vdso_base += PAGE_SIZE;
+	mm->context.vdso = (void *)vdso_base;
+	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
+				       VM_READ|VM_EXEC|
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       &vdso_spec[1]);
+	if (IS_ERR(ret))
+		goto up_fail;
 
-	return ret;
-}
 
-const char *arch_vma_name(struct vm_area_struct *vma)
-{
-	/*
-	 * We can re-use the vdso pointer in mm_context_t for identifying
-	 * the vectors page for compat applications. The vDSO will always
-	 * sit above TASK_UNMAPPED_BASE and so we don't need to worry about
-	 * it conflicting with the vectors base.
-	 */
-	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) {
-#ifdef CONFIG_COMPAT
-		if (vma->vm_start == AARCH32_VECTORS_BASE)
-			return "[vectors]";
-#endif
-		return "[vdso]";
-	}
+	up_write(&mm->mmap_sem);
+	return 0;
 
-	return NULL;
+up_fail:
+	mm->context.vdso = NULL;
+	up_write(&mm->mmap_sem);
+	return PTR_ERR(ret);
 }
 
 /*
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 6d20b7d162d..ff3bddea482 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -43,13 +43,13 @@ $(obj)/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
 	$(call if_changed,vdsosym)
 
 # Assembly rules for the .S files
-$(obj-vdso): %.o: %.S
+$(obj-vdso): %.o: %.S FORCE
 	$(call if_changed_dep,vdsoas)
 
 # Actual build commands
-quiet_cmd_vdsold = VDSOL $@
+quiet_cmd_vdsold = VDSOL   $@
       cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
-quiet_cmd_vdsoas = VDSOA $@
+quiet_cmd_vdsoas = VDSOA   $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
 # Install commands for the unstripped file
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index 8154b8d1c82..beca249bc2f 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -28,6 +28,7 @@ OUTPUT_ARCH(aarch64)
 
 SECTIONS
 {
+	PROVIDE(_vdso_data = . - PAGE_SIZE);
 	. = VDSO_LBASE + SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text
@@ -57,9 +58,6 @@ SECTIONS
 	_end = .;
 	PROVIDE(end = .);
 
-	. = ALIGN(PAGE_SIZE);
-	PROVIDE(_vdso_data = .);
-
 	/DISCARD/	: {
 		*(.note.GNU-stack)
 		*(.data .data.* .gnu.linkonce.d.* .sdata*)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index f1e6d5c032e..97f0c0429df 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -9,6 +9,8 @@
 #include <asm/memory.h>
 #include <asm/page.h>
 
+#include "image.h"
+
 #define ARM_EXIT_KEEP(x)
 #define ARM_EXIT_DISCARD(x)	x
 
@@ -104,9 +106,18 @@ SECTIONS
 	_edata = .;
 
 	BSS_SECTION(0, 0, 0)
+
+	. = ALIGN(PAGE_SIZE);
+	idmap_pg_dir = .;
+	. += IDMAP_DIR_SIZE;
+	swapper_pg_dir = .;
+	. += SWAPPER_DIR_SIZE;
+
 	_end = .;
 
 	STABS_DEBUG
+
+	HEAD_SYMBOLS
 }
 
 /*
@@ -114,3 +125,8 @@ SECTIONS
  */
 ASSERT(((__hyp_idmap_text_start + PAGE_SIZE) > __hyp_idmap_text_end),
        "HYP init code too big")
+
+/*
+ * If padding is applied before .head.text, virt<->phys conversions will fail.
+ */
+ASSERT(_text == (PAGE_OFFSET + TEXT_OFFSET), "HEAD is misaligned")
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 9aecbace412..13bbc3be6f5 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -27,8 +27,10 @@ void __cpu_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr)
 	copy_page(kto, kfrom);
 	__flush_dcache_area(kto, PAGE_SIZE);
 }
+EXPORT_SYMBOL_GPL(__cpu_copy_user_page);
 
 void __cpu_clear_user_page(void *kaddr, unsigned long vaddr)
 {
 	clear_page(kaddr);
 }
+EXPORT_SYMBOL_GPL(__cpu_clear_user_page);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index bcc965e2cce..41cb6d3d607 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -62,6 +62,7 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 			break;
 
 		pud = pud_offset(pgd, addr);
+		printk(", *pud=%016llx", pud_val(*pud));
 		if (pud_none(*pud) || pud_bad(*pud))
 			break;
 
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index e4193e3adc7..0d64089d28b 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -79,7 +79,8 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
 		return;
 
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags)) {
-		__flush_dcache_area(page_address(page), PAGE_SIZE);
+		__flush_dcache_area(page_address(page),
+				PAGE_SIZE << compound_order(page));
 		__flush_icache_all();
 	} else if (icache_is_aivivt()) {
 		__flush_icache_all();
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 091d428d64a..5b4526ee3a0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -33,6 +33,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 
+#include <asm/fixmap.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/sizes.h>
@@ -60,6 +61,17 @@ static int __init early_initrd(char *p)
 early_param("initrd", early_initrd);
 #endif
 
+/*
+ * Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
+ * currently assumes that for memory starting above 4G, 32-bit devices will
+ * use a DMA offset.
+ */
+static phys_addr_t max_zone_dma_phys(void)
+{
+	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
+	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
+}
+
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
@@ -70,9 +82,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 	/* 4GB maximum for 32-bit only capable devices */
 	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
-		unsigned long max_dma_phys =
-			(unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1);
-		max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
+		max_dma = PFN_DOWN(max_zone_dma_phys());
 		zone_size[ZONE_DMA] = max_dma - min;
 	}
 	zone_size[ZONE_NORMAL] = max - max_dma;
@@ -126,22 +136,24 @@ static void arm64_memory_present(void)
 
 void __init arm64_memblock_init(void)
 {
-	/* Register the kernel text, kernel data and initrd with memblock */
+	phys_addr_t dma_phys_limit = 0;
+
+	/*
+	 * Register the kernel text, kernel data, initrd, and initial
+	 * pagetables with memblock.
+	 */
 	memblock_reserve(__pa(_text), _end - _text);
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (initrd_start)
 		memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start);
 #endif
 
-	/*
-	 * Reserve the page tables.  These are already in use,
-	 * and can only be in node 0.
-	 */
-	memblock_reserve(__pa(swapper_pg_dir), SWAPPER_DIR_SIZE);
-	memblock_reserve(__pa(idmap_pg_dir), IDMAP_DIR_SIZE);
-
 	early_init_fdt_scan_reserved_mem();
-	dma_contiguous_reserve(0);
+
+	/* 4GB maximum for 32-bit only capable devices */
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		dma_phys_limit = max_zone_dma_phys();
+	dma_contiguous_reserve(dma_phys_limit);
 
 	memblock_allow_resize();
 	memblock_dump_all();
@@ -254,26 +266,33 @@ void __init mem_init(void)
 
 #define MLK(b, t) b, t, ((t) - (b)) >> 10
 #define MLM(b, t) b, t, ((t) - (b)) >> 20
+#define MLG(b, t) b, t, ((t) - (b)) >> 30
 #define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K)
 
 	pr_notice("Virtual kernel memory layout:\n"
-		  "    vmalloc : 0x%16lx - 0x%16lx   (%6ld MB)\n"
+		  "    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n"
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-		  "    vmemmap : 0x%16lx - 0x%16lx   (%6ld MB)\n"
+		  "    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n"
+		  "              0x%16lx - 0x%16lx   (%6ld MB actual)\n"
 #endif
+		  "    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n"
+		  "    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n"
 		  "    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n"
 		  "    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n"
-		  "      .init : 0x%p" " - 0x%p" "   (%6ld kB)\n"
-		  "      .text : 0x%p" " - 0x%p" "   (%6ld kB)\n"
-		  "      .data : 0x%p" " - 0x%p" "   (%6ld kB)\n",
-		  MLM(VMALLOC_START, VMALLOC_END),
+		  "      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n"
+		  "      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n"
+		  "      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+		  MLG(VMALLOC_START, VMALLOC_END),
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
+		  MLG((unsigned long)vmemmap,
+		      (unsigned long)vmemmap + VMEMMAP_SIZE),
 		  MLM((unsigned long)virt_to_page(PAGE_OFFSET),
 		      (unsigned long)virt_to_page(high_memory)),
 #endif
+		  MLM((unsigned long)PCI_IOBASE, (unsigned long)PCI_IOBASE + SZ_16M),
+		  MLK(FIXADDR_START, FIXADDR_TOP),
 		  MLM(MODULES_VADDR, MODULES_END),
 		  MLM(PAGE_OFFSET, (unsigned long)high_memory),
-
 		  MLK_ROUNDUP(__init_begin, __init_end),
 		  MLK_ROUNDUP(_text, _etext),
 		  MLK_ROUNDUP(_sdata, _edata));
diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c
index 7ec328392ae..fa324bd5a5c 100644
--- a/arch/arm64/mm/ioremap.c
+++ b/arch/arm64/mm/ioremap.c
@@ -103,19 +103,28 @@ void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size)
 }
 EXPORT_SYMBOL(ioremap_cache);
 
-#ifndef CONFIG_ARM64_64K_PAGES
 static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
+#if CONFIG_ARM64_PGTABLE_LEVELS > 2
+static pte_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss;
+#endif
+#if CONFIG_ARM64_PGTABLE_LEVELS > 3
+static pte_t bm_pud[PTRS_PER_PUD] __page_aligned_bss;
 #endif
 
-static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
+static inline pud_t * __init early_ioremap_pud(unsigned long addr)
 {
 	pgd_t *pgd;
-	pud_t *pud;
 
 	pgd = pgd_offset_k(addr);
 	BUG_ON(pgd_none(*pgd) || pgd_bad(*pgd));
 
-	pud = pud_offset(pgd, addr);
+	return pud_offset(pgd, addr);
+}
+
+static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
+{
+	pud_t *pud = early_ioremap_pud(addr);
+
 	BUG_ON(pud_none(*pud) || pud_bad(*pud));
 
 	return pmd_offset(pud, addr);
@@ -132,13 +141,18 @@ static inline pte_t * __init early_ioremap_pte(unsigned long addr)
 
 void __init early_ioremap_init(void)
 {
+	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
+	unsigned long addr = fix_to_virt(FIX_BTMAP_BEGIN);
 
-	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
-#ifndef CONFIG_ARM64_64K_PAGES
-	/* need to populate pmd for 4k pagesize only */
+	pgd = pgd_offset_k(addr);
+	pgd_populate(&init_mm, pgd, bm_pud);
+	pud = pud_offset(pgd, addr);
+	pud_populate(&init_mm, pud, bm_pmd);
+	pmd = pmd_offset(pud, addr);
 	pmd_populate_kernel(&init_mm, pmd, bm_pte);
-#endif
+
 	/*
 	 * The boot-ioremap range spans multiple pmds, for which
 	 * we are not prepared:
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index c43f1dd1948..c55567283cd 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -32,6 +32,7 @@
 #include <asm/setup.h>
 #include <asm/sizes.h>
 #include <asm/tlb.h>
+#include <asm/memblock.h>
 #include <asm/mmu_context.h>
 
 #include "mm.h"
@@ -204,9 +205,16 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
 				  unsigned long end, unsigned long phys,
 				  int map_io)
 {
-	pud_t *pud = pud_offset(pgd, addr);
+	pud_t *pud;
 	unsigned long next;
 
+	if (pgd_none(*pgd)) {
+		pud = early_alloc(PTRS_PER_PUD * sizeof(pud_t));
+		pgd_populate(&init_mm, pgd, pud);
+	}
+	BUG_ON(pgd_bad(*pgd));
+
+	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
 
@@ -290,10 +298,10 @@ static void __init map_mem(void)
 	 * memory addressable from the initial direct kernel mapping.
 	 *
 	 * The initial direct kernel mapping, located at swapper_pg_dir,
-	 * gives us PGDIR_SIZE memory starting from PHYS_OFFSET (which must be
+	 * gives us PUD_SIZE memory starting from PHYS_OFFSET (which must be
 	 * aligned to 2MB as per Documentation/arm64/booting.txt).
 	 */
-	limit = PHYS_OFFSET + PGDIR_SIZE;
+	limit = PHYS_OFFSET + PUD_SIZE;
 	memblock_set_current_limit(limit);
 
 	/* map all the memory banks */
diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h
index 972adcc1e8f..941593c7d9f 100644
--- a/arch/avr32/include/asm/processor.h
+++ b/arch/avr32/include/asm/processor.h
@@ -92,6 +92,7 @@ extern struct avr32_cpuinfo boot_cpu_data;
 #define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))
 
 #define cpu_relax()		barrier()
+#define cpu_relax_lowlatency()        cpu_relax()
 #define cpu_sync_pipeline()	asm volatile("sub pc, -2" : : : "memory")
 
 struct cpu_context {
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index f81e7b989ff..ed30699cc63 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -18,7 +18,6 @@ config BLACKFIN
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_IDE
 	select HAVE_KERNEL_GZIP if RAMKERNEL
 	select HAVE_KERNEL_BZIP2 if RAMKERNEL
diff --git a/arch/blackfin/configs/BF526-EZBRD_defconfig b/arch/blackfin/configs/BF526-EZBRD_defconfig
index 1759fad5401..e66ba31ef84 100644
--- a/arch/blackfin/configs/BF526-EZBRD_defconfig
+++ b/arch/blackfin/configs/BF526-EZBRD_defconfig
@@ -53,7 +53,6 @@ CONFIG_IP_PNP=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
@@ -63,6 +62,7 @@ CONFIG_MTD_COMPLEX_MAPPINGS=y
 CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=m
+CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
diff --git a/arch/blackfin/configs/BF527-EZKIT-V2_defconfig b/arch/blackfin/configs/BF527-EZKIT-V2_defconfig
index 357729682c0..0207c588c19 100644
--- a/arch/blackfin/configs/BF527-EZKIT-V2_defconfig
+++ b/arch/blackfin/configs/BF527-EZKIT-V2_defconfig
@@ -58,7 +58,6 @@ CONFIG_BFIN_SIR0=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=m
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_JEDECPROBE=m
 CONFIG_MTD_RAM=y
@@ -66,6 +65,7 @@ CONFIG_MTD_ROM=m
 CONFIG_MTD_COMPLEX_MAPPINGS=y
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=m
+CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
diff --git a/arch/blackfin/configs/BF527-EZKIT_defconfig b/arch/blackfin/configs/BF527-EZKIT_defconfig
index 2e73a5d33da..99c131ba7d9 100644
--- a/arch/blackfin/configs/BF527-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF527-EZKIT_defconfig
@@ -57,7 +57,6 @@ CONFIG_BFIN_SIR0=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=m
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_JEDECPROBE=m
 CONFIG_MTD_RAM=y
@@ -65,6 +64,7 @@ CONFIG_MTD_ROM=m
 CONFIG_MTD_COMPLEX_MAPPINGS=y
 CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=m
+CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
diff --git a/arch/blackfin/configs/BF548-EZKIT_defconfig b/arch/blackfin/configs/BF548-EZKIT_defconfig
index f0a2ddf5de4..38cb17d218d 100644
--- a/arch/blackfin/configs/BF548-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF548-EZKIT_defconfig
@@ -64,7 +64,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_FW_LOADER=m
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
@@ -75,6 +74,7 @@ CONFIG_MTD_M25P80=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_BF5XX=y
 # CONFIG_MTD_NAND_BF5XX_HWECC is not set
+CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_RAM=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
diff --git a/arch/blackfin/configs/BF609-EZKIT_defconfig b/arch/blackfin/configs/BF609-EZKIT_defconfig
index 4ca39ab6b2b..fcec5ce7139 100644
--- a/arch/blackfin/configs/BF609-EZKIT_defconfig
+++ b/arch/blackfin/configs/BF609-EZKIT_defconfig
@@ -57,7 +57,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_FW_LOADER=m
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
@@ -65,6 +64,7 @@ CONFIG_MTD_CFI_STAA=y
 CONFIG_MTD_COMPLEX_MAPPINGS=y
 CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_M25P80=y
+CONFIG_MTD_SPI_NOR=y
 CONFIG_MTD_UBI=m
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
@@ -102,7 +102,7 @@ CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_BLACKFIN_TWI=y
 CONFIG_I2C_BLACKFIN_TWI_CLK_KHZ=100
 CONFIG_SPI=y
-CONFIG_SPI_BFIN_V3=y
+CONFIG_SPI_ADI_V3=y
 CONFIG_GPIOLIB=y
 CONFIG_GPIO_SYSFS=y
 # CONFIG_HWMON is not set
diff --git a/arch/blackfin/configs/BlackStamp_defconfig b/arch/blackfin/configs/BlackStamp_defconfig
index 3853c473b44..f4a9200e1ab 100644
--- a/arch/blackfin/configs/BlackStamp_defconfig
+++ b/arch/blackfin/configs/BlackStamp_defconfig
@@ -45,7 +45,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=m
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=m
 CONFIG_MTD_CFI_AMDSTD=m
@@ -53,7 +52,7 @@ CONFIG_MTD_RAM=y
 CONFIG_MTD_ROM=m
 CONFIG_MTD_COMPLEX_MAPPINGS=y
 CONFIG_MTD_M25P80=y
-# CONFIG_M25PXX_USE_FAST_READ is not set
+CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=y
 CONFIG_BLK_DEV_RAM=y
diff --git a/arch/blackfin/configs/H8606_defconfig b/arch/blackfin/configs/H8606_defconfig
index f754e490bbf..0ff97d8d047 100644
--- a/arch/blackfin/configs/H8606_defconfig
+++ b/arch/blackfin/configs/H8606_defconfig
@@ -36,13 +36,12 @@ CONFIG_IRTTY_SIR=m
 # CONFIG_WIRELESS is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_ROM=y
 CONFIG_MTD_COMPLEX_MAPPINGS=y
 CONFIG_MTD_M25P80=y
-# CONFIG_M25PXX_USE_FAST_READ is not set
+CONFIG_MTD_SPI_NOR=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_AT25=y
diff --git a/arch/blackfin/include/asm/dma.h b/arch/blackfin/include/asm/dma.h
index 8d1e4c2d2c3..40e9c2bbc6e 100644
--- a/arch/blackfin/include/asm/dma.h
+++ b/arch/blackfin/include/asm/dma.h
@@ -316,6 +316,8 @@ static inline void disable_dma(unsigned int channel)
 }
 static inline void enable_dma(unsigned int channel)
 {
+	dma_ch[channel].regs->curr_x_count = 0;
+	dma_ch[channel].regs->curr_y_count = 0;
 	dma_ch[channel].regs->cfg |= DMAEN;
 }
 int set_dma_callback(unsigned int channel, irq_handler_t callback, void *data);
diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h
index d0e72e9475a..7acd46653df 100644
--- a/arch/blackfin/include/asm/processor.h
+++ b/arch/blackfin/include/asm/processor.h
@@ -99,7 +99,7 @@ unsigned long get_wchan(struct task_struct *p);
 #define	KSTK_ESP(tsk)	((tsk) == current ? rdusp() : (tsk)->thread.usp)
 
 #define cpu_relax()    	smp_mb()
-
+#define cpu_relax_lowlatency() cpu_relax()
 
 /* Get the Silicon Revision of the chip */
 static inline uint32_t __pure bfin_revid(void)
diff --git a/arch/blackfin/kernel/ftrace-entry.S b/arch/blackfin/kernel/ftrace-entry.S
index 7eed00bbd26..28d05954042 100644
--- a/arch/blackfin/kernel/ftrace-entry.S
+++ b/arch/blackfin/kernel/ftrace-entry.S
@@ -33,15 +33,6 @@ ENDPROC(__mcount)
  * function will be waiting there.  mmmm pie.
  */
 ENTRY(_ftrace_caller)
-# ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	/* optional micro optimization: return if stopped */
-	p1.l = _function_trace_stop;
-	p1.h = _function_trace_stop;
-	r3 = [p1];
-	cc = r3 == 0;
-	if ! cc jump _ftrace_stub (bp);
-# endif
-
 	/* save first/second/third function arg and the return register */
 	[--sp] = r2;
 	[--sp] = r0;
@@ -83,15 +74,6 @@ ENDPROC(_ftrace_caller)
 
 /* See documentation for _ftrace_caller */
 ENTRY(__mcount)
-# ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	/* optional micro optimization: return if stopped */
-	p1.l = _function_trace_stop;
-	p1.h = _function_trace_stop;
-	r3 = [p1];
-	cc = r3 == 0;
-	if ! cc jump _ftrace_stub (bp);
-# endif
-
 	/* save third function arg early so we can do testing below */
 	[--sp] = r2;
 
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 974e55496db..ea2032013cc 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -389,14 +389,6 @@ static int bfin_pmu_event_init(struct perf_event *event)
 	if (attr->exclude_hv || attr->exclude_idle)
 		return -EPERM;
 
-	/*
-	 * All of the on-chip counters are "limited", in that they have
-	 * no interrupts, and are therefore unable to do sampling without
-	 * further work and timer assistance.
-	 */
-	if (hwc->sample_period)
-		return -EINVAL;
-
 	ret = 0;
 	switch (attr->type) {
 	case PERF_TYPE_RAW:
@@ -490,6 +482,13 @@ static int __init bfin_pmu_init(void)
 {
 	int ret;
 
+	/*
+	 * All of the on-chip counters are "limited", in that they have
+	 * no interrupts, and are therefore unable to do sampling without
+	 * further work and timer assistance.
+	 */
+	pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	ret = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	if (!ret)
 		perf_cpu_notifier(bfin_pmu_notifier);
diff --git a/arch/blackfin/kernel/vmlinux.lds.S b/arch/blackfin/kernel/vmlinux.lds.S
index ba35864b2b7..c9eec84aa25 100644
--- a/arch/blackfin/kernel/vmlinux.lds.S
+++ b/arch/blackfin/kernel/vmlinux.lds.S
@@ -145,7 +145,7 @@ SECTIONS
 
 	.text_l1 L1_CODE_START : AT(LOADADDR(.exit.data) + SIZEOF(.exit.data))
 #else
-	.init.data : AT(__data_lma + __data_len)
+	.init.data : AT(__data_lma + __data_len + 32)
 	{
 		__sinitdata = .;
 		INIT_DATA
diff --git a/arch/blackfin/mach-bf533/boards/blackstamp.c b/arch/blackfin/mach-bf533/boards/blackstamp.c
index 63b0e4fe760..0ccf0cf4daa 100644
--- a/arch/blackfin/mach-bf533/boards/blackstamp.c
+++ b/arch/blackfin/mach-bf533/boards/blackstamp.c
@@ -20,6 +20,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/flash.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
diff --git a/arch/blackfin/mach-bf533/boards/stamp.c b/arch/blackfin/mach-bf533/boards/stamp.c
index d0989290f54..6f4bac969bf 100644
--- a/arch/blackfin/mach-bf533/boards/stamp.c
+++ b/arch/blackfin/mach-bf533/boards/stamp.c
@@ -17,6 +17,7 @@
 #if IS_ENABLED(CONFIG_USB_ISP1362_HCD)
 #include <linux/usb/isp1362.h>
 #endif
+#include <linux/gpio.h>
 #include <linux/irq.h>
 #include <linux/i2c.h>
 #include <asm/dma.h>
diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537e.c b/arch/blackfin/mach-bf537/boards/cm_bf537e.c
index c65c6dbda3d..1e7290ef352 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537e.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537e.c
@@ -21,6 +21,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
diff --git a/arch/blackfin/mach-bf537/boards/cm_bf537u.c b/arch/blackfin/mach-bf537/boards/cm_bf537u.c
index af58454b4bf..c7495dc7469 100644
--- a/arch/blackfin/mach-bf537/boards/cm_bf537u.c
+++ b/arch/blackfin/mach-bf537/boards/cm_bf537u.c
@@ -21,6 +21,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
diff --git a/arch/blackfin/mach-bf537/boards/tcm_bf537.c b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
index a0211225748..6b988ad653d 100644
--- a/arch/blackfin/mach-bf537/boards/tcm_bf537.c
+++ b/arch/blackfin/mach-bf537/boards/tcm_bf537.c
@@ -21,6 +21,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
diff --git a/arch/blackfin/mach-bf548/boards/ezkit.c b/arch/blackfin/mach-bf548/boards/ezkit.c
index 90138e6112c..1fe7ff28661 100644
--- a/arch/blackfin/mach-bf548/boards/ezkit.c
+++ b/arch/blackfin/mach-bf548/boards/ezkit.c
@@ -2118,7 +2118,7 @@ static struct pinctrl_map __initdata bfin_pinmux_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-rotary",  "pinctrl-adi2.0", NULL, "rotary"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.0",  "pinctrl-adi2.0", NULL, "can0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.1",  "pinctrl-adi2.0", NULL, "can1"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-lq043",  "pinctrl-adi2.0", NULL, "ppi0_24b"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-lq043",  "pinctrl-adi2.0", "ppi0_24bgrp", "ppi0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-ac97.0",  "pinctrl-adi2.0", NULL, "sport0"),
@@ -2140,7 +2140,9 @@ static struct pinctrl_map __initdata bfin_pinmux_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("pata-bf54x",  "pinctrl-adi2.0", NULL, "atapi_alter"),
 #endif
 	PIN_MAP_MUX_GROUP_DEFAULT("bf5xx-nand.0",  "pinctrl-adi2.0", NULL, "nfc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-keys",  "pinctrl-adi2.0", NULL, "keys_4x4"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bf54x-keys",  "pinctrl-adi2.0", "keys_4x4grp", "keys"),
+	PIN_MAP_MUX_GROUP("bf54x-keys", "4bit",  "pinctrl-adi2.0", "keys_4x4grp", "keys"),
+	PIN_MAP_MUX_GROUP("bf54x-keys", "8bit",  "pinctrl-adi2.0", "keys_8x8grp", "keys"),
 };
 
 static int __init ezkit_init(void)
diff --git a/arch/blackfin/mach-bf561/boards/acvilon.c b/arch/blackfin/mach-bf561/boards/acvilon.c
index 430b16d5ccb..6ab951534d7 100644
--- a/arch/blackfin/mach-bf561/boards/acvilon.c
+++ b/arch/blackfin/mach-bf561/boards/acvilon.c
@@ -44,6 +44,7 @@
 #include <linux/spi/flash.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
+#include <linux/gpio.h>
 #include <linux/jiffies.h>
 #include <linux/i2c-pca-platform.h>
 #include <linux/delay.h>
diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c
index 9f777df4cac..e862f7823e6 100644
--- a/arch/blackfin/mach-bf561/boards/cm_bf561.c
+++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c
@@ -18,6 +18,7 @@
 #endif
 #include <linux/ata_platform.h>
 #include <linux/irq.h>
+#include <linux/gpio.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
 #include <asm/portmux.h>
diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c
index 88dee43e7ab..2de71e8c104 100644
--- a/arch/blackfin/mach-bf561/boards/ezkit.c
+++ b/arch/blackfin/mach-bf561/boards/ezkit.c
@@ -14,6 +14,7 @@
 #include <linux/spi/spi.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
+#include <linux/gpio.h>
 #include <linux/delay.h>
 #include <asm/dma.h>
 #include <asm/bfin5xx_spi.h>
diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c
index 1ba4600de69..e2c0b024ce8 100644
--- a/arch/blackfin/mach-bf609/boards/ezkit.c
+++ b/arch/blackfin/mach-bf609/boards/ezkit.c
@@ -698,8 +698,6 @@ int bf609_nor_flash_init(struct platform_device *pdev)
 {
 #define CONFIG_SMC_GCTL_VAL     0x00000010
 
-	if (!devm_pinctrl_get_select_default(&pdev->dev))
-		return -EBUSY;
 	bfin_write32(SMC_GCTL, CONFIG_SMC_GCTL_VAL);
 	bfin_write32(SMC_B0CTL, 0x01002011);
 	bfin_write32(SMC_B0TIM, 0x08170977);
@@ -709,7 +707,6 @@ int bf609_nor_flash_init(struct platform_device *pdev)
 
 void bf609_nor_flash_exit(struct platform_device *pdev)
 {
-	devm_pinctrl_put(pdev->dev.pins->p);
 	bfin_write32(SMC_GCTL, 0);
 }
 
@@ -2058,15 +2055,14 @@ static struct pinctrl_map __initdata bfin_pinmux_map[] = {
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-rotary",  "pinctrl-adi2.0", NULL, "rotary"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin_can.0",  "pinctrl-adi2.0", NULL, "can0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("physmap-flash.0",  "pinctrl-adi2.0", NULL, "smc0"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bf609_nl8048.2",  "pinctrl-adi2.0", NULL, "ppi2_16b"),
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_display.0",  "pinctrl-adi2.0", NULL, "ppi0_16b"),
-#if IS_ENABLED(CONFIG_VIDEO_MT9M114)
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", NULL, "ppi0_8b"),
-#elif IS_ENABLED(CONFIG_VIDEO_VS6624)
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", NULL, "ppi0_16b"),
-#else
-	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", NULL, "ppi0_24b"),
-#endif
+	PIN_MAP_MUX_GROUP_DEFAULT("bf609_nl8048.2",  "pinctrl-adi2.0", "ppi2_16bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP("bfin_display.0", "8bit",  "pinctrl-adi2.0", "ppi2_8bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bfin_display.0",  "pinctrl-adi2.0", "ppi2_16bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP("bfin_display.0", "16bit",  "pinctrl-adi2.0", "ppi2_16bgrp", "ppi2"),
+	PIN_MAP_MUX_GROUP("bfin_capture.0", "8bit",  "pinctrl-adi2.0", "ppi0_8bgrp", "ppi0"),
+	PIN_MAP_MUX_GROUP_DEFAULT("bfin_capture.0",  "pinctrl-adi2.0", "ppi0_16bgrp", "ppi0"),
+	PIN_MAP_MUX_GROUP("bfin_capture.0", "16bit",  "pinctrl-adi2.0", "ppi0_16bgrp", "ppi0"),
+	PIN_MAP_MUX_GROUP("bfin_capture.0", "24bit",  "pinctrl-adi2.0", "ppi0_24bgrp", "ppi0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-tdm.0",  "pinctrl-adi2.0", NULL, "sport0"),
 	PIN_MAP_MUX_GROUP_DEFAULT("bfin-i2s.1",  "pinctrl-adi2.0", NULL, "sport1"),
diff --git a/arch/blackfin/mach-bf609/include/mach/pm.h b/arch/blackfin/mach-bf609/include/mach/pm.h
index 3ca0fb96563..a1efd936dd3 100644
--- a/arch/blackfin/mach-bf609/include/mach/pm.h
+++ b/arch/blackfin/mach-bf609/include/mach/pm.h
@@ -10,6 +10,7 @@
 #define __MACH_BF609_PM_H__
 
 #include <linux/suspend.h>
+#include <linux/platform_device.h>
 
 extern int bfin609_pm_enter(suspend_state_t state);
 extern int bf609_pm_prepare(void);
@@ -19,6 +20,6 @@ void bf609_hibernate(void);
 void bfin_sec_raise_irq(unsigned int sid);
 void coreb_enable(void);
 
-int bf609_nor_flash_init(void);
-void bf609_nor_flash_exit(void);
+int bf609_nor_flash_init(struct platform_device *pdev);
+void bf609_nor_flash_exit(struct platform_device *pdev);
 #endif
diff --git a/arch/blackfin/mach-bf609/pm.c b/arch/blackfin/mach-bf609/pm.c
index 0cdd6955c7b..b1bfcf434d1 100644
--- a/arch/blackfin/mach-bf609/pm.c
+++ b/arch/blackfin/mach-bf609/pm.c
@@ -291,13 +291,13 @@ static struct bfin_cpu_pm_fns bf609_cpu_pm = {
 #if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE)
 static int smc_pm_syscore_suspend(void)
 {
-	bf609_nor_flash_exit();
+	bf609_nor_flash_exit(NULL);
 	return 0;
 }
 
 static void smc_pm_syscore_resume(void)
 {
-	bf609_nor_flash_init();
+	bf609_nor_flash_init(NULL);
 }
 
 static struct syscore_ops smc_pm_syscore_ops = {
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index 867b7cef204..1f94784eab6 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -1208,8 +1208,6 @@ int __init init_arch_irq(void)
 
 	bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority);
 
-	bfin_sec_set_priority(CONFIG_SEC_IRQ_PRIORITY_LEVELS, sec_int_priority);
-
 	/* Enable interrupts IVG7-15 */
 	bfin_irq_flags |= IMASK_IVG15 |
 	    IMASK_IVG14 | IMASK_IVG13 | IMASK_IVG12 | IMASK_IVG11 |
diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h
index b9eb3da7f27..f2ef31be2f8 100644
--- a/arch/c6x/include/asm/processor.h
+++ b/arch/c6x/include/asm/processor.h
@@ -121,6 +121,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(task)	(task_pt_regs(task)->sp)
 
 #define cpu_relax()		do { } while (0)
+#define cpu_relax_lowlatency()        cpu_relax()
 
 extern const struct seq_operations cpuinfo_op;
 
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index 15b815df29c..862126b5811 100644
--- a/arch/cris/include/asm/processor.h
+++ b/arch/cris/include/asm/processor.h
@@ -63,6 +63,7 @@ static inline void release_thread(struct task_struct *dead_task)
 #define init_stack      (init_thread_union.stack)
 
 #define cpu_relax()     barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 void default_idle(void);
 
diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h
index 45a825402f6..d8501137c8d 100644
--- a/arch/hexagon/include/asm/processor.h
+++ b/arch/hexagon/include/asm/processor.h
@@ -56,6 +56,7 @@ struct thread_struct {
 }
 
 #define cpu_relax() __vmyield()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * Decides where the kernel will search for a free chunk of vm space during
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 1a871b78e57..344387a5540 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -242,7 +242,7 @@ struct ioc {
 	struct pci_dev	*sac_only_dev;
 };
 
-static struct ioc *ioc_list;
+static struct ioc *ioc_list, *ioc_found;
 static int reserve_sba_gart = 1;
 
 static SBA_INLINE void sba_mark_invalid(struct ioc *, dma_addr_t, size_t);
@@ -1809,20 +1809,13 @@ static struct ioc_iommu ioc_iommu_info[] __initdata = {
 	{ SX2000_IOC_ID, "sx2000", NULL },
 };
 
-static struct ioc *
-ioc_init(unsigned long hpa, void *handle)
+static void ioc_init(unsigned long hpa, struct ioc *ioc)
 {
-	struct ioc *ioc;
 	struct ioc_iommu *info;
 
-	ioc = kzalloc(sizeof(*ioc), GFP_KERNEL);
-	if (!ioc)
-		return NULL;
-
 	ioc->next = ioc_list;
 	ioc_list = ioc;
 
-	ioc->handle = handle;
 	ioc->ioc_hpa = ioremap(hpa, 0x1000);
 
 	ioc->func_id = READ_REG(ioc->ioc_hpa + IOC_FUNC_ID);
@@ -1863,8 +1856,6 @@ ioc_init(unsigned long hpa, void *handle)
 		"%s %d.%d HPA 0x%lx IOVA space %dMb at 0x%lx\n",
 		ioc->name, (ioc->rev >> 4) & 0xF, ioc->rev & 0xF,
 		hpa, ioc->iov_size >> 20, ioc->ibase);
-
-	return ioc;
 }
 
 
@@ -2031,22 +2022,21 @@ sba_map_ioc_to_node(struct ioc *ioc, acpi_handle handle)
 #endif
 }
 
-static int
-acpi_sba_ioc_add(struct acpi_device *device,
-		 const struct acpi_device_id *not_used)
+static void acpi_sba_ioc_add(struct ioc *ioc)
 {
-	struct ioc *ioc;
+	acpi_handle handle = ioc->handle;
 	acpi_status status;
 	u64 hpa, length;
 	struct acpi_device_info *adi;
 
-	status = hp_acpi_csr_space(device->handle, &hpa, &length);
+	ioc_found = ioc->next;
+	status = hp_acpi_csr_space(handle, &hpa, &length);
 	if (ACPI_FAILURE(status))
-		return 1;
+		goto err;
 
-	status = acpi_get_object_info(device->handle, &adi);
+	status = acpi_get_object_info(handle, &adi);
 	if (ACPI_FAILURE(status))
-		return 1;
+		goto err;
 
 	/*
 	 * For HWP0001, only SBA appears in ACPI namespace.  It encloses the PCI
@@ -2067,13 +2057,13 @@ acpi_sba_ioc_add(struct acpi_device *device,
 	if (!iovp_shift)
 		iovp_shift = 12;
 
-	ioc = ioc_init(hpa, device->handle);
-	if (!ioc)
-		return 1;
-
+	ioc_init(hpa, ioc);
 	/* setup NUMA node association */
-	sba_map_ioc_to_node(ioc, device->handle);
-	return 0;
+	sba_map_ioc_to_node(ioc, handle);
+	return;
+
+ err:
+	kfree(ioc);
 }
 
 static const struct acpi_device_id hp_ioc_iommu_device_ids[] = {
@@ -2081,9 +2071,26 @@ static const struct acpi_device_id hp_ioc_iommu_device_ids[] = {
 	{"HWP0004", 0},
 	{"", 0},
 };
+
+static int acpi_sba_ioc_attach(struct acpi_device *device,
+			       const struct acpi_device_id *not_used)
+{
+	struct ioc *ioc;
+
+	ioc = kzalloc(sizeof(*ioc), GFP_KERNEL);
+	if (!ioc)
+		return -ENOMEM;
+
+	ioc->next = ioc_found;
+	ioc_found = ioc;
+	ioc->handle = device->handle;
+	return 1;
+}
+
+
 static struct acpi_scan_handler acpi_sba_ioc_handler = {
 	.ids	= hp_ioc_iommu_device_ids,
-	.attach	= acpi_sba_ioc_add,
+	.attach	= acpi_sba_ioc_attach,
 };
 
 static int __init acpi_sba_ioc_init_acpi(void)
@@ -2118,9 +2125,12 @@ sba_init(void)
 #endif
 
 	/*
-	 * ioc_list should be populated by the acpi_sba_ioc_handler's .attach()
+	 * ioc_found should be populated by the acpi_sba_ioc_handler's .attach()
 	 * routine, but that only happens if acpi_scan_init() has already run.
 	 */
+	while (ioc_found)
+		acpi_sba_ioc_add(ioc_found);
+
 	if (!ioc_list) {
 #ifdef CONFIG_IA64_GENERIC
 		/*
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 0d2bcb37ec3..bee0acd52f7 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -426,6 +426,7 @@ extern void iounmap (volatile void __iomem *addr);
 extern void __iomem * early_ioremap (unsigned long phys_addr, unsigned long size);
 #define early_memremap(phys_addr, size)        early_ioremap(phys_addr, size)
 extern void early_iounmap (volatile void __iomem *addr, unsigned long size);
+#define early_memunmap(addr, size)             early_iounmap(addr, size)
 static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned long size)
 {
 	return ioremap(phys_addr, size);
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index efd1b927ccb..c7367130ab1 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -548,6 +548,7 @@ ia64_eoi (void)
 }
 
 #define cpu_relax()	ia64_hint(ia64_hint_pause)
+#define cpu_relax_lowlatency() cpu_relax()
 
 static inline int
 ia64_get_irr(unsigned int vector)
diff --git a/arch/ia64/include/uapi/asm/fcntl.h b/arch/ia64/include/uapi/asm/fcntl.h
index 1dd275dc8f6..7b485876cad 100644
--- a/arch/ia64/include/uapi/asm/fcntl.h
+++ b/arch/ia64/include/uapi/asm/fcntl.h
@@ -8,6 +8,7 @@
 #define force_o_largefile()	\
 		(personality(current->personality) != PER_LINUX32)
 
+#include <linux/personality.h>
 #include <asm-generic/fcntl.h>
 
 #endif /* _ASM_IA64_FCNTL_H */
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 55d4ba47a90..deed6fa96bb 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -662,7 +662,7 @@ void
 machine_restart (char *restart_cmd)
 {
 	(void) notify_die(DIE_MACHINE_RESTART, restart_cmd, NULL, 0, 0, 0);
-	(*efi.reset_system)(EFI_RESET_WARM, 0, 0, NULL);
+	efi_reboot(REBOOT_WARM, NULL);
 }
 
 void
diff --git a/arch/ia64/pci/fixup.c b/arch/ia64/pci/fixup.c
index 1fe9aa5068e..ec73b2cf912 100644
--- a/arch/ia64/pci/fixup.c
+++ b/arch/ia64/pci/fixup.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/vgaarb.h>
+#include <linux/screen_info.h>
 
 #include <asm/machvec.h>
 
@@ -37,6 +38,27 @@ static void pci_fixup_video(struct pci_dev *pdev)
 		return;
 	/* Maybe, this machine supports legacy memory map. */
 
+	if (!vga_default_device()) {
+		resource_size_t start, end;
+		int i;
+
+		/* Does firmware framebuffer belong to us? */
+		for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+			if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM))
+				continue;
+
+			start = pci_resource_start(pdev, i);
+			end  = pci_resource_end(pdev, i);
+
+			if (!start || !end)
+				continue;
+
+			if (screen_info.lfb_base >= start &&
+			    (screen_info.lfb_base + screen_info.lfb_size) < end)
+				vga_set_default_device(pdev);
+		}
+	}
+
 	/* Is VGA routed to us? */
 	bus = pdev->bus;
 	while (bus) {
diff --git a/arch/ia64/sn/kernel/bte.c b/arch/ia64/sn/kernel/bte.c
index cad775a1a15..b2eb4849075 100644
--- a/arch/ia64/sn/kernel/bte.c
+++ b/arch/ia64/sn/kernel/bte.c
@@ -114,7 +114,7 @@ bte_result_t bte_copy(u64 src, u64 dest, u64 len, u64 mode, void *notification)
 		if (mode & BTE_USE_ANY) {
 			nasid_to_try[1] = my_nasid;
 		} else {
-			nasid_to_try[1] = (int)NULL;
+			nasid_to_try[1] = 0;
 		}
 	} else {
 		/* try local then remote */
@@ -122,7 +122,7 @@ bte_result_t bte_copy(u64 src, u64 dest, u64 len, u64 mode, void *notification)
 		if (mode & BTE_USE_ANY) {
 			nasid_to_try[1] = NASID_GET(dest);
 		} else {
-			nasid_to_try[1] = (int)NULL;
+			nasid_to_try[1] = 0;
 		}
 	}
 
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index 53b01b8e2f1..36182c84363 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/arch/ia64/sn/kernel/setup.c
@@ -579,7 +579,7 @@ void sn_cpu_init(void)
 		       (sn_prom_type == 1) ? "real" : "fake");
 	}
 
-	memset(pda, 0, sizeof(pda));
+	memset(pda, 0, sizeof(*pda));
 	if (ia64_sn_get_sn_info(0, &sn_hub_info->shub2,
 				&sn_hub_info->nasid_bitmask,
 				&sn_hub_info->nasid_shift,
diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h
index 5767367550c..9f8fd9bef70 100644
--- a/arch/m32r/include/asm/processor.h
+++ b/arch/m32r/include/asm/processor.h
@@ -133,5 +133,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)  ((tsk)->thread.sp)
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 #endif /* _ASM_M32R_PROCESSOR_H */
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index b0768a65792..20dda1d4b86 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -176,5 +176,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define task_pt_regs(tsk)	((struct pt_regs *) ((tsk)->thread.esp0))
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 #endif
diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index f868506e335..0931388de47 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -12,10 +12,6 @@
 
 #include <asm/tlb.h>
 
-/* FIXME - when we get this compiling */
-/* erm, now that it's compiling, what do we do with it? */
-#define _KERNPG_TABLE 0
-
 extern const char bad_pmd_string[];
 
 #define pmd_alloc_one(mm,address)       ({ BUG(); ((pmd_t *)2); })
diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index dbb118e1a4e..a54788458ca 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -921,7 +921,8 @@ L(nocon):
 	jls	1f
 	lsrl	#1,%d1
 1:
-	movel	%d1,m68k_init_mapped_size
+	lea	%pc@(m68k_init_mapped_size),%a0
+	movel	%d1,%a0@
 	mmu_map	#PAGE_OFFSET,%pc@(L(phys_kernel_start)),%d1,\
 		%pc@(m68k_supervisor_cachemode)
 
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 958f1adb9d0..3857737e395 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/export.h>
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -30,6 +31,7 @@
 
 
 unsigned long (*mach_random_get_entropy)(void);
+EXPORT_SYMBOL_GPL(mach_random_get_entropy);
 
 
 /*
diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig
index 499b7610eaa..0b389a81c43 100644
--- a/arch/metag/Kconfig
+++ b/arch/metag/Kconfig
@@ -13,7 +13,6 @@ config METAG
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index a8a37477c66..881071c0794 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -155,6 +155,7 @@ unsigned long get_wchan(struct task_struct *p);
 #define user_stack_pointer(regs)        ((regs)->ctx.AX[0].U0)
 
 #define cpu_relax()     barrier()
+#define cpu_relax_lowlatency()  cpu_relax()
 
 extern void setup_priv(void);
 
diff --git a/arch/metag/kernel/ftrace_stub.S b/arch/metag/kernel/ftrace_stub.S
index e70bff745bd..3acc288217c 100644
--- a/arch/metag/kernel/ftrace_stub.S
+++ b/arch/metag/kernel/ftrace_stub.S
@@ -16,13 +16,6 @@ _mcount_wrapper:
 	.global _ftrace_caller
 	.type	_ftrace_caller,function
 _ftrace_caller:
-	MOVT    D0Re0,#HI(_function_trace_stop)
-	ADD	D0Re0,D0Re0,#LO(_function_trace_stop)
-	GETD	D0Re0,[D0Re0]
-	CMP	D0Re0,#0
-	BEQ	$Lcall_stub
-	MOV	PC,D0.4
-$Lcall_stub:
 	MSETL   [A0StP], D0Ar6, D0Ar4, D0Ar2, D0.4
 	MOV     D1Ar1, D0.4
 	MOV     D0Ar2, D1RtP
@@ -42,13 +35,6 @@ _ftrace_call:
 	.global	_mcount_wrapper
 	.type	_mcount_wrapper,function
 _mcount_wrapper:
-	MOVT    D0Re0,#HI(_function_trace_stop)
-	ADD	D0Re0,D0Re0,#LO(_function_trace_stop)
-	GETD	D0Re0,[D0Re0]
-	CMP	D0Re0,#0
-	BEQ	$Lcall_mcount
-	MOV	PC,D0.4
-$Lcall_mcount:
 	MSETL   [A0StP], D0Ar6, D0Ar4, D0Ar2, D0.4
 	MOV     D1Ar1, D0.4
 	MOV     D0Ar2, D1RtP
diff --git a/arch/metag/kernel/perf/perf_event.c b/arch/metag/kernel/perf/perf_event.c
index 5cc4d4dcf3c..02c08737f6a 100644
--- a/arch/metag/kernel/perf/perf_event.c
+++ b/arch/metag/kernel/perf/perf_event.c
@@ -568,16 +568,6 @@ static int _hw_perf_event_init(struct perf_event *event)
 		return -EINVAL;
 
 	/*
-	 * Early cores have "limited" counters - they have no overflow
-	 * interrupts - and so are unable to do sampling without extra work
-	 * and timer assistance.
-	 */
-	if (metag_pmu->max_period == 0) {
-		if (hwc->sample_period)
-			return -EINVAL;
-	}
-
-	/*
 	 * Don't assign an index until the event is placed into the hardware.
 	 * -1 signifies that we're still deciding where to put it. On SMP
 	 * systems each core has its own set of counters, so we can't do any
@@ -866,6 +856,15 @@ static int __init init_hw_perf_events(void)
 	pr_info("enabled with %s PMU driver, %d counters available\n",
 			metag_pmu->name, metag_pmu->max_events);
 
+	/*
+	 * Early cores have "limited" counters - they have no overflow
+	 * interrupts - and so are unable to do sampling without extra work
+	 * and timer assistance.
+	 */
+	if (metag_pmu->max_period == 0) {
+		metag_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+	}
+
 	/* Initialise the active events and reservation mutex */
 	atomic_set(&metag_pmu->active_events, 0);
 	mutex_init(&metag_pmu->reserve_mutex);
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 9ae08541e30..40e1c1dd0e2 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -22,7 +22,6 @@ config MICROBLAZE
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_FUNCTION_TRACER
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 9d31b057c35..497a988d79c 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -22,6 +22,7 @@
 extern const struct seq_operations cpuinfo_op;
 
 # define cpu_relax()		barrier()
+# define cpu_relax_lowlatency()	cpu_relax()
 
 #define task_pt_regs(tsk) \
 		(((struct pt_regs *)(THREAD_SIZE + task_stack_page(tsk))) - 1)
diff --git a/arch/microblaze/kernel/ftrace.c b/arch/microblaze/kernel/ftrace.c
index bbcd2533766..fc7b48a52cd 100644
--- a/arch/microblaze/kernel/ftrace.c
+++ b/arch/microblaze/kernel/ftrace.c
@@ -27,6 +27,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
+	if (unlikely(ftrace_graph_is_dead()))
+		return;
+
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
diff --git a/arch/microblaze/kernel/mcount.S b/arch/microblaze/kernel/mcount.S
index fc1e1322ce4..fed9da5de8c 100644
--- a/arch/microblaze/kernel/mcount.S
+++ b/arch/microblaze/kernel/mcount.S
@@ -91,11 +91,6 @@ ENTRY(ftrace_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 	SAVE_REGS
 	swi	r15, r1, 0;
-	/* MS: HAVE_FUNCTION_TRACE_MCOUNT_TEST begin of checking */
-	lwi	r5, r0, function_trace_stop;
-	bneid	r5, end;
-	nop;
-	/* MS: HAVE_FUNCTION_TRACE_MCOUNT_TEST end of checking */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #ifndef CONFIG_DYNAMIC_FTRACE
 	lwi	r5, r0, ftrace_graph_return;
diff --git a/arch/mips/Kbuild b/arch/mips/Kbuild
index d2cfe45f332..dd295335891 100644
--- a/arch/mips/Kbuild
+++ b/arch/mips/Kbuild
@@ -16,7 +16,7 @@ obj- := $(platform-)
 
 obj-y += kernel/
 obj-y += mm/
-obj-y += math-emu/
+obj-y += net/
 
 ifdef CONFIG_KVM
 obj-y += kvm/
diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms
index 6e239123d6f..f5e18bf3275 100644
--- a/arch/mips/Kbuild.platforms
+++ b/arch/mips/Kbuild.platforms
@@ -18,6 +18,7 @@ platforms += loongson1
 platforms += mti-malta
 platforms += mti-sead3
 platforms += netlogic
+platforms += paravirt
 platforms += pmcs-msp71xx
 platforms += pnx833x
 platforms += ralink
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 5e0014e864f..10f270bd3e2 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -12,9 +12,9 @@ config MIPS
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_BPF_JIT if !CPU_MICROMIPS
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_C_RECORDMCOUNT
@@ -50,6 +50,8 @@ config MIPS
 	select CLONE_BACKWARDS
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_CC_STACKPROTECTOR
+	select CPU_PM if CPU_IDLE
+	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 
 menu "Machine selection"
 
@@ -83,6 +85,7 @@ config AR7
 	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
+	select SYS_SUPPORTS_MIPS16
 	select SYS_SUPPORTS_ZBOOT_UART16550
 	select ARCH_REQUIRE_GPIOLIB
 	select VLYNQ
@@ -106,6 +109,7 @@ config ATH79
 	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
+	select SYS_SUPPORTS_MIPS16
 	help
 	  Support for the Atheros AR71XX/AR724X/AR913X SoCs.
 
@@ -122,6 +126,7 @@ config BCM47XX
 	select NO_EXCEPT_FILL
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
+	select SYS_SUPPORTS_MIPS16
 	select SYS_HAS_EARLY_PRINTK
 	select USE_GENERIC_EARLY_PRINTK_8250
 	help
@@ -168,9 +173,9 @@ config MACH_DECSTATION
 	bool "DECstations"
 	select BOOT_ELF32
 	select CEVT_DS1287
-	select CEVT_R4K
+	select CEVT_R4K if CPU_R4X00
 	select CSRC_IOASIC
-	select CSRC_R4K
+	select CSRC_R4K if CPU_R4X00
 	select CPU_DADDI_WORKAROUNDS if 64BIT
 	select CPU_R4000_WORKAROUNDS if 64BIT
 	select CPU_R4400_WORKAROUNDS if 64BIT
@@ -248,6 +253,7 @@ config LANTIQ
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_32BIT_KERNEL
+	select SYS_SUPPORTS_MIPS16
 	select SYS_SUPPORTS_MULTITHREADING
 	select SYS_HAS_EARLY_PRINTK
 	select ARCH_REQUIRE_GPIOLIB
@@ -262,6 +268,7 @@ config LANTIQ
 config LASAT
 	bool "LASAT Networks platforms"
 	select CEVT_R4K
+	select CRC32
 	select CSRC_R4K
 	select DMA_NONCOHERENT
 	select SYS_HAS_EARLY_PRINTK
@@ -330,6 +337,7 @@ config MIPS_MALTA
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_MIPS_CMP
 	select SYS_SUPPORTS_MIPS_CPS
+	select SYS_SUPPORTS_MIPS16
 	select SYS_SUPPORTS_MULTITHREADING
 	select SYS_SUPPORTS_SMARTMIPS
 	select SYS_SUPPORTS_ZBOOT
@@ -361,6 +369,7 @@ config MIPS_SEAD3
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_SMARTMIPS
 	select SYS_SUPPORTS_MICROMIPS
+	select SYS_SUPPORTS_MIPS16
 	select USB_EHCI_BIG_ENDIAN_DESC
 	select USB_EHCI_BIG_ENDIAN_MMIO
 	select USE_OF
@@ -380,6 +389,7 @@ config MACH_VR41XX
 	select CEVT_R4K
 	select CSRC_R4K
 	select SYS_HAS_CPU_VR41XX
+	select SYS_SUPPORTS_MIPS16
 	select ARCH_REQUIRE_GPIOLIB
 
 config NXP_STB220
@@ -407,6 +417,7 @@ config PMC_MSP
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
+	select SYS_SUPPORTS_MIPS16
 	select IRQ_CPU
 	select SERIAL_8250
 	select SERIAL_8250_CONSOLE
@@ -430,6 +441,7 @@ config RALINK
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
+	select SYS_SUPPORTS_MIPS16
 	select SYS_HAS_EARLY_PRINTK
 	select HAVE_MACH_CLKDEV
 	select CLKDEV_LOOKUP
@@ -674,7 +686,6 @@ config SNI_RM
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
 	select SYS_SUPPORTS_LITTLE_ENDIAN
-	select USE_GENERIC_EARLY_PRINTK_8250
 	help
 	  The SNI RM200/300/400 are MIPS-based machines manufactured by
 	  Siemens Nixdorf Informationssysteme (SNI), parent company of Pyramid
@@ -721,6 +732,11 @@ config CAVIUM_OCTEON_SOC
 	select ZONE_DMA32
 	select HOLES_IN_ZONE
 	select ARCH_REQUIRE_GPIOLIB
+	select LIBFDT
+	select USE_OF
+	select ARCH_SPARSEMEM_ENABLE
+	select SYS_SUPPORTS_SMP
+	select NR_CPUS_DEFAULT_16
 	help
 	  This option supports all of the Octeon reference boards from Cavium
 	  Networks. It builds a kernel that dynamically determines the Octeon
@@ -789,6 +805,25 @@ config NLM_XLP_BOARD
 	  This board is based on Netlogic XLP Processor.
 	  Say Y here if you have a XLP based board.
 
+config MIPS_PARAVIRT
+	bool "Para-Virtualized guest system"
+	select CEVT_R4K
+	select CSRC_R4K
+	select DMA_COHERENT
+	select SYS_SUPPORTS_64BIT_KERNEL
+	select SYS_SUPPORTS_32BIT_KERNEL
+	select SYS_SUPPORTS_BIG_ENDIAN
+	select SYS_SUPPORTS_SMP
+	select NR_CPUS_DEFAULT_4
+	select SYS_HAS_EARLY_PRINTK
+	select SYS_HAS_CPU_MIPS32_R2
+	select SYS_HAS_CPU_MIPS64_R2
+	select SYS_HAS_CPU_CAVIUM_OCTEON
+	select HW_HAS_PCI
+	select SWAP_IO_SPACE
+	help
+	  This option supports guest running under ????
+
 endchoice
 
 source "arch/mips/alchemy/Kconfig"
@@ -809,6 +844,7 @@ source "arch/mips/cavium-octeon/Kconfig"
 source "arch/mips/loongson/Kconfig"
 source "arch/mips/loongson1/Kconfig"
 source "arch/mips/netlogic/Kconfig"
+source "arch/mips/paravirt/Kconfig"
 
 endmenu
 
@@ -1059,6 +1095,7 @@ config SOC_PNX833X
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_BIG_ENDIAN
+	select SYS_SUPPORTS_MIPS16
 	select CPU_MIPSR2_IRQ_VI
 
 config SOC_PNX8335
@@ -1398,16 +1435,11 @@ config CPU_SB1
 config CPU_CAVIUM_OCTEON
 	bool "Cavium Octeon processor"
 	depends on SYS_HAS_CPU_CAVIUM_OCTEON
-	select ARCH_SPARSEMEM_ENABLE
 	select CPU_HAS_PREFETCH
 	select CPU_SUPPORTS_64BIT_KERNEL
-	select SYS_SUPPORTS_SMP
-	select NR_CPUS_DEFAULT_16
 	select WEAK_ORDERING
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
-	select LIBFDT
-	select USE_OF
 	select USB_EHCI_BIG_ENDIAN_MMIO
 	select MIPS_L1_CACHE_SHIFT_7
 	help
@@ -1659,6 +1691,12 @@ config SYS_HAS_CPU_XLR
 config SYS_HAS_CPU_XLP
 	bool
 
+config MIPS_MALTA_PM
+	depends on MIPS_MALTA
+	depends on PCI
+	bool
+	default y
+
 #
 # CPU may reorder R->R, R->W, W->R, W->W
 # Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC
@@ -1842,7 +1880,7 @@ config FORCE_MAX_ZONEORDER
 
 config CEVT_GIC
 	bool "Use GIC global counter for clock events"
-	depends on IRQ_GIC && !(MIPS_SEAD3 || MIPS_MT_SMTC)
+	depends on IRQ_GIC && !MIPS_SEAD3
 	help
 	  Use the GIC global counter for the clock events. The R4K clock
 	  event driver is always present, so if the platform ends up not
@@ -1895,19 +1933,8 @@ config CPU_R4K_CACHE_TLB
 	bool
 	default y if !(CPU_R3000 || CPU_R8000 || CPU_SB1 || CPU_TX39XX || CPU_CAVIUM_OCTEON)
 
-choice
-	prompt "MIPS MT options"
-
-config MIPS_MT_DISABLED
-	bool "Disable multithreading support"
-	help
-	  Use this option if your platform does not support the MT ASE
-	  which is hardware multithreading support. On systems without
-	  an MT-enabled processor, this will be the only option that is
-	  available in this menu.
-
 config MIPS_MT_SMP
-	bool "Use 1 TC on each available VPE for SMP"
+	bool "MIPS MT SMP support (1 TC on each available VPE)"
 	depends on SYS_SUPPORTS_MULTITHREADING
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
@@ -1926,26 +1953,6 @@ config MIPS_MT_SMP
 	  Intel Hyperthreading feature. For further information go to
 	  <http://www.imgtec.com/mips/mips-multithreading.asp>.
 
-config MIPS_MT_SMTC
-	bool "Use all TCs on all VPEs for SMP (DEPRECATED)"
-	depends on CPU_MIPS32_R2
-	depends on SYS_SUPPORTS_MULTITHREADING
-	depends on !MIPS_CPS
-	select CPU_MIPSR2_IRQ_VI
-	select CPU_MIPSR2_IRQ_EI
-	select MIPS_MT
-	select SMP
-	select SMP_UP
-	select SYS_SUPPORTS_SMP
-	select NR_CPUS_DEFAULT_8
-	help
-	  This is a kernel model which is known as SMTC. This is
-	  supported on cores with the MT ASE and presents all TCs
-	  available on all VPEs to support SMP. For further
-	  information see <http://www.linux-mips.org/wiki/34K#SMTC>.
-
-endchoice
-
 config MIPS_MT
 	bool
 
@@ -1967,7 +1974,7 @@ config SYS_SUPPORTS_MULTITHREADING
 config MIPS_MT_FPAFF
 	bool "Dynamic FPU affinity for FP-intensive threads"
 	default y
-	depends on MIPS_MT_SMP || MIPS_MT_SMTC
+	depends on MIPS_MT_SMP
 
 config MIPS_VPE_LOADER
 	bool "VPE loader support."
@@ -1989,29 +1996,6 @@ config MIPS_VPE_LOADER_MT
 	default "y"
 	depends on MIPS_VPE_LOADER && !MIPS_CMP
 
-config MIPS_MT_SMTC_IM_BACKSTOP
-	bool "Use per-TC register bits as backstop for inhibited IM bits"
-	depends on MIPS_MT_SMTC
-	default n
-	help
-	  To support multiple TC microthreads acting as "CPUs" within
-	  a VPE, VPE-wide interrupt mask bits must be specially manipulated
-	  during interrupt handling. To support legacy drivers and interrupt
-	  controller management code, SMTC has a "backstop" to track and
-	  if necessary restore the interrupt mask. This has some performance
-	  impact on interrupt service overhead.
-
-config MIPS_MT_SMTC_IRQAFF
-	bool "Support IRQ affinity API"
-	depends on MIPS_MT_SMTC
-	default n
-	help
-	  Enables SMP IRQ affinity API (/proc/irq/*/smp_affinity, etc.)
-	  for SMTC Linux kernel. Requires platform support, of which
-	  an example can be found in the MIPS kernel i8259 and Malta
-	  platform code.  Adds some overhead to interrupt dispatch, and
-	  should be used only if you know what you are doing.
-
 config MIPS_VPE_LOADER_TOM
 	bool "Load VPE program into memory hidden from linux"
 	depends on MIPS_VPE_LOADER
@@ -2039,7 +2023,7 @@ config MIPS_VPE_APSP_API_MT
 
 config MIPS_CMP
 	bool "MIPS CMP framework support (DEPRECATED)"
-	depends on SYS_SUPPORTS_MIPS_CMP && !MIPS_MT_SMTC
+	depends on SYS_SUPPORTS_MIPS_CMP
 	select MIPS_GIC_IPI
 	select SYNC_R4K
 	select WEAK_ORDERING
@@ -2057,9 +2041,11 @@ config MIPS_CPS
 	depends on SYS_SUPPORTS_MIPS_CPS
 	select MIPS_CM
 	select MIPS_CPC
+	select MIPS_CPS_PM if HOTPLUG_CPU
 	select MIPS_GIC_IPI
 	select SMP
 	select SYNC_R4K if (CEVT_R4K || CSRC_R4K)
+	select SYS_SUPPORTS_HOTPLUG_CPU
 	select SYS_SUPPORTS_SMP
 	select WEAK_ORDERING
 	help
@@ -2069,6 +2055,9 @@ config MIPS_CPS
 	  no external assistance. It is safe to enable this when hardware
 	  support is unavailable.
 
+config MIPS_CPS_PM
+	bool
+
 config MIPS_GIC_IPI
 	bool
 
@@ -2199,6 +2188,13 @@ config SYS_SUPPORTS_SMARTMIPS
 config SYS_SUPPORTS_MICROMIPS
 	bool
 
+config SYS_SUPPORTS_MIPS16
+	bool
+	help
+	  This option must be set if a kernel might be executed on a MIPS16-
+	  enabled CPU even if MIPS16 is not actually being used.  In other
+	  words, it makes the kernel MIPS16-tolerant.
+
 config CPU_SUPPORTS_MSA
 	bool
 
@@ -2239,7 +2235,7 @@ config NODES_SHIFT
 
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"
-	depends on PERF_EVENTS && !MIPS_MT_SMTC && OPROFILE=n && (CPU_MIPS32 || CPU_MIPS64 || CPU_R10000 || CPU_SB1 || CPU_CAVIUM_OCTEON || CPU_XLP)
+	depends on PERF_EVENTS && OPROFILE=n && (CPU_MIPS32 || CPU_MIPS64 || CPU_R10000 || CPU_SB1 || CPU_CAVIUM_OCTEON || CPU_XLP)
 	default y
 	help
 	  Enable hardware performance counter support for perf events. If
@@ -2297,8 +2293,8 @@ config NR_CPUS_DEFAULT_64
 	bool
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-64)"
-	range 2 64
+	int "Maximum number of CPUs (2-256)"
+	range 2 256
 	depends on SMP
 	default "4" if NR_CPUS_DEFAULT_4
 	default "8" if NR_CPUS_DEFAULT_8
@@ -2671,12 +2667,16 @@ endmenu
 config MIPS_EXTERNAL_TIMER
 	bool
 
-if CPU_SUPPORTS_CPUFREQ && MIPS_EXTERNAL_TIMER
 menu "CPU Power Management"
+
+if CPU_SUPPORTS_CPUFREQ && MIPS_EXTERNAL_TIMER
 source "drivers/cpufreq/Kconfig"
-endmenu
 endif
 
+source "drivers/cpuidle/Kconfig"
+
+endmenu
+
 source "net/Kconfig"
 
 source "drivers/Kconfig"
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 25de29211d7..3a2b775e845 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -79,15 +79,6 @@ config CMDLINE_OVERRIDE
 
 	  Normally, you will choose 'N' here.
 
-config SMTC_IDLE_HOOK_DEBUG
-	bool "Enable additional debug checks before going into CPU idle loop"
-	depends on DEBUG_KERNEL && MIPS_MT_SMTC
-	help
-	  This option enables Enable additional debug checks before going into
-	  CPU idle loop.  For details on these checks, see
-	  arch/mips/kernel/smtc.c.  This debugging option result in significant
-	  overhead so should be disabled in production kernels.
-
 config SB1XXX_CORELIS
 	bool "Corelis Debugger"
 	depends on SIBYTE_SB1xxx_SOC
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 60a359cfa32..a8521de1479 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -120,7 +120,7 @@ cflags-$(CONFIG_SB1XXX_CORELIS)	+= $(call cc-option,-mno-sched-prolog) \
 				   -fno-omit-frame-pointer
 
 ifeq ($(CONFIG_CPU_HAS_MSA),y)
-toolchain-msa			:= $(call cc-option-yn,-mhard-float -mfp64 -mmsa)
+toolchain-msa	:= $(call cc-option-yn,-mhard-float -mfp64 -Wa$(comma)-mmsa)
 cflags-$(toolchain-msa)		+= -DTOOLCHAIN_SUPPORTS_MSA
 endif
 
@@ -251,6 +251,7 @@ OBJCOPYFLAGS		+= --remove-section=.reginfo
 head-y := arch/mips/kernel/head.o
 
 libs-y			+= arch/mips/lib/
+libs-y			+= arch/mips/math-emu/
 
 # See arch/mips/Kbuild for content of core part of the kernel
 core-y += arch/mips/
diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c
index bd551365029..3fb814be0e9 100644
--- a/arch/mips/alchemy/board-xxs1500.c
+++ b/arch/mips/alchemy/board-xxs1500.c
@@ -49,7 +49,7 @@ void __init prom_init(void)
 	prom_init_cmdline();
 
 	memsize_str = prom_getenv("memsize");
-	if (!memsize_str || strict_strtoul(memsize_str, 0, &memsize))
+	if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
 		memsize = 0x04000000;
 
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
diff --git a/arch/mips/alchemy/common/setup.c b/arch/mips/alchemy/common/setup.c
index 566a1743f68..8267e3c9772 100644
--- a/arch/mips/alchemy/common/setup.c
+++ b/arch/mips/alchemy/common/setup.c
@@ -67,6 +67,12 @@ void __init plat_mem_setup(void)
 	case ALCHEMY_CPU_AU1500:
 	case ALCHEMY_CPU_AU1100:
 		coherentio = 0;
+		break;
+	case ALCHEMY_CPU_AU1200:
+		/* Au1200 AB USB does not support coherent memory */
+		if (0 == (read_c0_prid() & PRID_REV_MASK))
+			coherentio = 0;
+		break;
 	}
 
 	board_setup();	/* board specific setup */
diff --git a/arch/mips/alchemy/common/usb.c b/arch/mips/alchemy/common/usb.c
index 2adc7edda49..d193dbea84a 100644
--- a/arch/mips/alchemy/common/usb.c
+++ b/arch/mips/alchemy/common/usb.c
@@ -355,47 +355,25 @@ static inline void __au1200_udc_control(void __iomem *base, int enable)
 	}
 }
 
-static inline int au1200_coherency_bug(void)
-{
-#if defined(CONFIG_DMA_COHERENT)
-	/* Au1200 AB USB does not support coherent memory */
-	if (!(read_c0_prid() & PRID_REV_MASK)) {
-		printk(KERN_INFO "Au1200 USB: this is chip revision AB !!\n");
-		printk(KERN_INFO "Au1200 USB: update your board or re-configure"
-				 " the kernel\n");
-		return -ENODEV;
-	}
-#endif
-	return 0;
-}
-
 static inline int au1200_usb_control(int block, int enable)
 {
 	void __iomem *base =
 			(void __iomem *)KSEG1ADDR(AU1200_USB_CTL_PHYS_ADDR);
-	int ret = 0;
 
 	switch (block) {
 	case ALCHEMY_USB_OHCI0:
-		ret = au1200_coherency_bug();
-		if (ret && enable)
-			goto out;
 		__au1200_ohci_control(base, enable);
 		break;
 	case ALCHEMY_USB_UDC0:
 		__au1200_udc_control(base, enable);
 		break;
 	case ALCHEMY_USB_EHCI0:
-		ret = au1200_coherency_bug();
-		if (ret && enable)
-			goto out;
 		__au1200_ehci_control(base, enable);
 		break;
 	default:
-		ret = -ENODEV;
+		return -ENODEV;
 	}
-out:
-	return ret;
+	return 0;
 }
 
 
diff --git a/arch/mips/alchemy/devboards/pm.c b/arch/mips/alchemy/devboards/pm.c
index b86bff31d1d..61e90fe9eab 100644
--- a/arch/mips/alchemy/devboards/pm.c
+++ b/arch/mips/alchemy/devboards/pm.c
@@ -158,7 +158,7 @@ static ssize_t db1x_pmattr_store(struct kobject *kobj,
 	int tmp;
 
 	if (ATTRCMP(timer_timeout)) {
-		tmp = strict_strtoul(instr, 0, &l);
+		tmp = kstrtoul(instr, 0, &l);
 		if (tmp)
 			return tmp;
 
@@ -181,7 +181,7 @@ static ssize_t db1x_pmattr_store(struct kobject *kobj,
 		}
 
 	} else if (ATTRCMP(wakemsk)) {
-		tmp = strict_strtoul(instr, 0, &l);
+		tmp = kstrtoul(instr, 0, &l);
 		if (tmp)
 			return tmp;
 
diff --git a/arch/mips/bcm47xx/prom.c b/arch/mips/bcm47xx/prom.c
index 0af808dfd1c..1a03a2f4349 100644
--- a/arch/mips/bcm47xx/prom.c
+++ b/arch/mips/bcm47xx/prom.c
@@ -69,15 +69,18 @@ static __init void prom_init_mem(void)
 	 * BCM47XX uses 128MB for addressing the ram, if the system contains
 	 * less that that amount of ram it remaps the ram more often into the
 	 * available space.
-	 * Accessing memory after 128MB will cause an exception.
-	 * max contains the biggest possible address supported by the platform.
-	 * If the method wants to try something above we assume 128MB ram.
 	 */
-	off = (unsigned long)prom_init;
-	max = off | ((128 << 20) - 1);
-	for (mem = (1 << 20); mem < (128 << 20); mem += (1 << 20)) {
-		if ((off + mem) > max) {
-			mem = (128 << 20);
+
+	/* Physical address, without mapping to any kernel segment */
+	off = CPHYSADDR((unsigned long)prom_init);
+
+	/* Accessing memory after 128 MiB will cause an exception */
+	max = 128 << 20;
+
+	for (mem = 1 << 20; mem < max; mem += 1 << 20) {
+		/* Loop condition may be not enough, off may be over 1 MiB */
+		if (off + mem >= max) {
+			mem = max;
 			printk(KERN_DEBUG "assume 128MB RAM\n");
 			break;
 		}
diff --git a/arch/mips/bcm47xx/sprom.c b/arch/mips/bcm47xx/sprom.c
index a8b5408dd34..da4cdb16844 100644
--- a/arch/mips/bcm47xx/sprom.c
+++ b/arch/mips/bcm47xx/sprom.c
@@ -168,6 +168,7 @@ static void nvram_read_alpha2(const char *prefix, const char *name,
 static void bcm47xx_fill_sprom_r1234589(struct ssb_sprom *sprom,
 					const char *prefix, bool fallback)
 {
+	nvram_read_u16(prefix, NULL, "devid", &sprom->dev_id, 0, fallback);
 	nvram_read_u8(prefix, NULL, "ledbh0", &sprom->gpio0, 0xff, fallback);
 	nvram_read_u8(prefix, NULL, "ledbh1", &sprom->gpio1, 0xff, fallback);
 	nvram_read_u8(prefix, NULL, "ledbh2", &sprom->gpio2, 0xff, fallback);
diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig
index 227705d9d5a..60286665793 100644
--- a/arch/mips/cavium-octeon/Kconfig
+++ b/arch/mips/cavium-octeon/Kconfig
@@ -10,6 +10,17 @@ config CAVIUM_CN63XXP1
 	  non-CN63XXP1 hardware, so it is recommended to select "n"
 	  unless it is known the workarounds are needed.
 
+config CAVIUM_OCTEON_CVMSEG_SIZE
+	int "Number of L1 cache lines reserved for CVMSEG memory"
+	range 0 54
+	default 1
+	help
+	  CVMSEG LM is a segment that accesses portions of the dcache as a
+	  local memory; the larger CVMSEG is, the smaller the cache is.
+	  This selects the size of CVMSEG LM, which is in cache blocks. The
+	  legally range is from zero to 54 cache blocks (i.e. CVMSEG LM is
+	  between zero and 6192 bytes).
+
 endif # CPU_CAVIUM_OCTEON
 
 if CAVIUM_OCTEON_SOC
@@ -23,17 +34,6 @@ config CAVIUM_OCTEON_2ND_KERNEL
 	  with this option to be run at the same time as one built without this
 	  option.
 
-config CAVIUM_OCTEON_CVMSEG_SIZE
-	int "Number of L1 cache lines reserved for CVMSEG memory"
-	range 0 54
-	default 1
-	help
-	  CVMSEG LM is a segment that accesses portions of the dcache as a
-	  local memory; the larger CVMSEG is, the smaller the cache is.
-	  This selects the size of CVMSEG LM, which is in cache blocks. The
-	  legally range is from zero to 54 cache blocks (i.e. CVMSEG LM is
-	  between zero and 6192 bytes).
-
 config CAVIUM_OCTEON_LOCK_L2
 	bool "Lock often used kernel code in the L2"
 	default "y"
@@ -86,7 +86,6 @@ config SWIOTLB
 	select IOMMU_HELPER
 	select NEED_SG_DMA_LENGTH
 
-
 config OCTEON_ILM
 	tristate "Module to measure interrupt latency using Octeon CIU Timer"
 	help
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c
index 8553ad5c72b..7e5cf7a5e2f 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c
@@ -106,6 +106,158 @@ int cvmx_helper_ports_on_interface(int interface)
 EXPORT_SYMBOL_GPL(cvmx_helper_ports_on_interface);
 
 /**
+ * @INTERNAL
+ * Return interface mode for CN68xx.
+ */
+static cvmx_helper_interface_mode_t __cvmx_get_mode_cn68xx(int interface)
+{
+	union cvmx_mio_qlmx_cfg qlm_cfg;
+	switch (interface) {
+	case 0:
+		qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(0));
+		/* QLM is disabled when QLM SPD is 15. */
+		if (qlm_cfg.s.qlm_spd == 15)
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+
+		if (qlm_cfg.s.qlm_cfg == 2)
+			return CVMX_HELPER_INTERFACE_MODE_SGMII;
+		else if (qlm_cfg.s.qlm_cfg == 3)
+			return CVMX_HELPER_INTERFACE_MODE_XAUI;
+		else
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+	case 2:
+	case 3:
+	case 4:
+		qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(interface));
+		/* QLM is disabled when QLM SPD is 15. */
+		if (qlm_cfg.s.qlm_spd == 15)
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+
+		if (qlm_cfg.s.qlm_cfg == 2)
+			return CVMX_HELPER_INTERFACE_MODE_SGMII;
+		else if (qlm_cfg.s.qlm_cfg == 3)
+			return CVMX_HELPER_INTERFACE_MODE_XAUI;
+		else
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+	case 7:
+		qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(3));
+		/* QLM is disabled when QLM SPD is 15. */
+		if (qlm_cfg.s.qlm_spd == 15) {
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+		} else if (qlm_cfg.s.qlm_cfg != 0) {
+			qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(1));
+			if (qlm_cfg.s.qlm_cfg != 0)
+				return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+		}
+		return CVMX_HELPER_INTERFACE_MODE_NPI;
+	case 8:
+		return CVMX_HELPER_INTERFACE_MODE_LOOP;
+	default:
+		return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+	}
+}
+
+/**
+ * @INTERNAL
+ * Return interface mode for an Octeon II
+ */
+static cvmx_helper_interface_mode_t __cvmx_get_mode_octeon2(int interface)
+{
+	union cvmx_gmxx_inf_mode mode;
+
+	if (OCTEON_IS_MODEL(OCTEON_CN68XX))
+		return __cvmx_get_mode_cn68xx(interface);
+
+	if (interface == 2)
+		return CVMX_HELPER_INTERFACE_MODE_NPI;
+
+	if (interface == 3)
+		return CVMX_HELPER_INTERFACE_MODE_LOOP;
+
+	/* Only present in CN63XX & CN66XX Octeon model */
+	if ((OCTEON_IS_MODEL(OCTEON_CN63XX) &&
+	     (interface == 4 || interface == 5)) ||
+	    (OCTEON_IS_MODEL(OCTEON_CN66XX) &&
+	     interface >= 4 && interface <= 7)) {
+		return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+	}
+
+	if (OCTEON_IS_MODEL(OCTEON_CN66XX)) {
+		union cvmx_mio_qlmx_cfg mio_qlm_cfg;
+
+		/* QLM2 is SGMII0 and QLM1 is SGMII1 */
+		if (interface == 0)
+			mio_qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(2));
+		else if (interface == 1)
+			mio_qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(1));
+		else
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+
+		if (mio_qlm_cfg.s.qlm_spd == 15)
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+
+		if (mio_qlm_cfg.s.qlm_cfg == 9)
+			return CVMX_HELPER_INTERFACE_MODE_SGMII;
+		else if (mio_qlm_cfg.s.qlm_cfg == 11)
+			return CVMX_HELPER_INTERFACE_MODE_XAUI;
+		else
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+	} else if (OCTEON_IS_MODEL(OCTEON_CN61XX)) {
+		union cvmx_mio_qlmx_cfg qlm_cfg;
+
+		if (interface == 0) {
+			qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(2));
+			if (qlm_cfg.s.qlm_cfg == 2)
+				return CVMX_HELPER_INTERFACE_MODE_SGMII;
+			else if (qlm_cfg.s.qlm_cfg == 3)
+				return CVMX_HELPER_INTERFACE_MODE_XAUI;
+			else
+				return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+		} else if (interface == 1) {
+			qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(0));
+			if (qlm_cfg.s.qlm_cfg == 2)
+				return CVMX_HELPER_INTERFACE_MODE_SGMII;
+			else if (qlm_cfg.s.qlm_cfg == 3)
+				return CVMX_HELPER_INTERFACE_MODE_XAUI;
+			else
+				return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+		}
+	} else if (OCTEON_IS_MODEL(OCTEON_CNF71XX)) {
+		if (interface == 0) {
+			union cvmx_mio_qlmx_cfg qlm_cfg;
+			qlm_cfg.u64 = cvmx_read_csr(CVMX_MIO_QLMX_CFG(0));
+			if (qlm_cfg.s.qlm_cfg == 2)
+				return CVMX_HELPER_INTERFACE_MODE_SGMII;
+		}
+		return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+	}
+
+	if (interface == 1 && OCTEON_IS_MODEL(OCTEON_CN63XX))
+		return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+
+	mode.u64 = cvmx_read_csr(CVMX_GMXX_INF_MODE(interface));
+
+	if (OCTEON_IS_MODEL(OCTEON_CN63XX)) {
+		switch (mode.cn63xx.mode) {
+		case 0:
+			return CVMX_HELPER_INTERFACE_MODE_SGMII;
+		case 1:
+			return CVMX_HELPER_INTERFACE_MODE_XAUI;
+		default:
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+		}
+	} else {
+		if (!mode.s.en)
+			return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+
+		if (mode.s.type)
+			return CVMX_HELPER_INTERFACE_MODE_GMII;
+		else
+			return CVMX_HELPER_INTERFACE_MODE_RGMII;
+	}
+}
+
+/**
  * Get the operating mode of an interface. Depending on the Octeon
  * chip and configuration, this function returns an enumeration
  * of the type of packet I/O supported by an interface.
@@ -118,6 +270,20 @@ EXPORT_SYMBOL_GPL(cvmx_helper_ports_on_interface);
 cvmx_helper_interface_mode_t cvmx_helper_interface_get_mode(int interface)
 {
 	union cvmx_gmxx_inf_mode mode;
+
+	if (interface < 0 ||
+	    interface >= cvmx_helper_get_number_of_interfaces())
+		return CVMX_HELPER_INTERFACE_MODE_DISABLED;
+
+	/*
+	 * Octeon II models
+	 */
+	if (OCTEON_IS_MODEL(OCTEON_CN6XXX) || OCTEON_IS_MODEL(OCTEON_CNF71XX))
+		return __cvmx_get_mode_octeon2(interface);
+
+	/*
+	 * Octeon and Octeon Plus models
+	 */
 	if (interface == 2)
 		return CVMX_HELPER_INTERFACE_MODE_NPI;
 
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 3aa5b46b2d4..1b82ac6921e 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1260,11 +1260,13 @@ static void __init octeon_irq_init_ciu(void)
 	for (i = 0; i < 4; i++)
 		octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_PCI_MSI0, 0, i + 40);
 
+	octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_TWSI, 0, 45);
 	octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_RML, 0, 46);
 	for (i = 0; i < 4; i++)
 		octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_TIMER0, 0, i + 52);
 
 	octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB0, 0, 56);
+	octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_TWSI2, 0, 59);
 
 	/* CIU_1 */
 	for (i = 0; i < 16; i++)
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index f1bec00d5a8..008e9c8b8ea 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -729,17 +729,6 @@ void __init prom_init(void)
 	octeon_write_lcd("Linux");
 #endif
 
-#ifdef CONFIG_CAVIUM_GDB
-	/*
-	 * When debugging the linux kernel, force the cores to enter
-	 * the debug exception handler to break in.
-	 */
-	if (octeon_get_boot_debug_flag()) {
-		cvmx_write_csr(CVMX_CIU_DINT, 1 << cvmx_get_core_num());
-		cvmx_read_csr(CVMX_CIU_DINT);
-	}
-#endif
-
 	octeon_setup_delays();
 
 	/*
@@ -779,12 +768,6 @@ void __init prom_init(void)
 				MAX_MEMORY = 32ull << 30;
 			if (*p == '@')
 				RESERVE_LOW_MEM = memparse(p + 1, &p);
-		} else if (strcmp(arg, "ecc_verbose") == 0) {
-#ifdef CONFIG_CAVIUM_REPORT_SINGLE_BIT_ECC
-			__cvmx_interrupt_ecc_report_single_bit_errors = 1;
-			pr_notice("Reporting of single bit ECC errors is "
-				  "turned on\n");
-#endif
 #ifdef CONFIG_KEXEC
 		} else if (strncmp(arg, "crashkernel=", 12) == 0) {
 			crashk_size = memparse(arg+12, &p);
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 67a078ffc46..a7b3ae104d8 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -218,15 +218,6 @@ void octeon_prepare_cpus(unsigned int max_cpus)
  */
 static void octeon_smp_finish(void)
 {
-#ifdef CONFIG_CAVIUM_GDB
-	unsigned long tmp;
-	/* Pulse MCD0 signal on Ctrl-C to stop all the cores. Also set the MCD0
-	   to be not masked by this core so we know the signal is received by
-	   someone */
-	asm volatile ("dmfc0 %0, $22\n"
-		      "ori   %0, %0, 0x9100\n" "dmtc0 %0, $22\n" : "=r" (tmp));
-#endif
-
 	octeon_user_io_init();
 
 	/* to generate the first CPU timer interrupt */
@@ -234,21 +225,6 @@ static void octeon_smp_finish(void)
 	local_irq_enable();
 }
 
-/**
- * Hook for after all CPUs are online
- */
-static void octeon_cpus_done(void)
-{
-#ifdef CONFIG_CAVIUM_GDB
-	unsigned long tmp;
-	/* Pulse MCD0 signal on Ctrl-C to stop all the cores. Also set the MCD0
-	   to be not masked by this core so we know the signal is received by
-	   someone */
-	asm volatile ("dmfc0 %0, $22\n"
-		      "ori   %0, %0, 0x9100\n" "dmtc0 %0, $22\n" : "=r" (tmp));
-#endif
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 
 /* State of each CPU. */
@@ -405,7 +381,6 @@ struct plat_smp_ops octeon_smp_ops = {
 	.send_ipi_mask		= octeon_send_ipi_mask,
 	.init_secondary		= octeon_init_secondary,
 	.smp_finish		= octeon_smp_finish,
-	.cpus_done		= octeon_cpus_done,
 	.boot_secondary		= octeon_boot_secondary,
 	.smp_setup		= octeon_smp_setup,
 	.prepare_cpus		= octeon_prepare_cpus,
diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig
index e3a3836508e..134879c1310 100644
--- a/arch/mips/configs/ath79_defconfig
+++ b/arch/mips/configs/ath79_defconfig
@@ -46,7 +46,6 @@ CONFIG_MTD=y
 CONFIG_MTD_REDBOOT_PARTS=y
 CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-2
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_JEDECPROBE=y
@@ -54,7 +53,7 @@ CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_COMPLEX_MAPPINGS=y
 CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_M25P80=y
-# CONFIG_M25PXX_USE_FAST_READ is not set
+CONFIG_MTD_SPI_NOR=y
 CONFIG_NETDEVICES=y
 # CONFIG_NET_PACKET_ENGINE is not set
 CONFIG_ATH_COMMON=m
diff --git a/arch/mips/configs/db1xxx_defconfig b/arch/mips/configs/db1xxx_defconfig
index c99b6eeda90..a64b30b96a0 100644
--- a/arch/mips/configs/db1xxx_defconfig
+++ b/arch/mips/configs/db1xxx_defconfig
@@ -113,6 +113,7 @@ CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_ECC_BCH=y
 CONFIG_MTD_NAND_AU1550=y
 CONFIG_MTD_NAND_PLATFORM=y
+CONFIG_MTD_SPI_NOR=y
 CONFIG_EEPROM_AT24=y
 CONFIG_EEPROM_AT25=y
 CONFIG_SCSI_TGT=y
diff --git a/arch/mips/configs/maltasmtc_defconfig b/arch/mips/configs/maltasmtc_defconfig
deleted file mode 100644
index eb316447588..00000000000
--- a/arch/mips/configs/maltasmtc_defconfig
+++ /dev/null
@@ -1,196 +0,0 @@
-CONFIG_MIPS_MALTA=y
-CONFIG_CPU_LITTLE_ENDIAN=y
-CONFIG_CPU_MIPS32_R2=y
-CONFIG_PAGE_SIZE_16KB=y
-CONFIG_MIPS_MT_SMTC=y
-# CONFIG_MIPS_MT_FPAFF is not set
-CONFIG_NR_CPUS=9
-CONFIG_HZ_48=y
-CONFIG_LOCALVERSION="smtc"
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_AUDIT=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=15
-CONFIG_SYSCTL_SYSCALL=y
-CONFIG_EMBEDDED=y
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PCI=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_ROUTE_MULTIPATH=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_NET_IPIP=m
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_IPCOMP=m
-# CONFIG_INET_LRO is not set
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_IPV6_TUNNEL=m
-CONFIG_BRIDGE=m
-CONFIG_VLAN_8021Q=m
-CONFIG_ATALK=m
-CONFIG_DEV_APPLETALK=m
-CONFIG_IPDDP=m
-CONFIG_IPDDP_ENCAP=y
-CONFIG_NET_SCHED=y
-CONFIG_NET_SCH_CBQ=m
-CONFIG_NET_SCH_HTB=m
-CONFIG_NET_SCH_HFSC=m
-CONFIG_NET_SCH_PRIO=m
-CONFIG_NET_SCH_RED=m
-CONFIG_NET_SCH_SFQ=m
-CONFIG_NET_SCH_TEQL=m
-CONFIG_NET_SCH_TBF=m
-CONFIG_NET_SCH_GRED=m
-CONFIG_NET_SCH_DSMARK=m
-CONFIG_NET_SCH_NETEM=m
-CONFIG_NET_SCH_INGRESS=m
-CONFIG_NET_CLS_BASIC=m
-CONFIG_NET_CLS_TCINDEX=m
-CONFIG_NET_CLS_ROUTE4=m
-CONFIG_NET_CLS_FW=m
-CONFIG_NET_CLS_U32=m
-CONFIG_NET_CLS_RSVP=m
-CONFIG_NET_CLS_RSVP6=m
-CONFIG_NET_CLS_ACT=y
-CONFIG_NET_ACT_POLICE=y
-CONFIG_NET_CLS_IND=y
-# CONFIG_WIRELESS is not set
-CONFIG_DEVTMPFS=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
-CONFIG_IDE=y
-# CONFIG_IDE_PROC_FS is not set
-# CONFIG_IDEPCI_PCIBUS_ORDER is not set
-CONFIG_BLK_DEV_GENERIC=y
-CONFIG_BLK_DEV_PIIX=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_SG=y
-# CONFIG_SCSI_LOWLEVEL is not set
-CONFIG_NETDEVICES=y
-# CONFIG_NET_VENDOR_3COM is not set
-# CONFIG_NET_VENDOR_ADAPTEC is not set
-# CONFIG_NET_VENDOR_ALTEON is not set
-CONFIG_PCNET32=y
-# CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_BROADCOM is not set
-# CONFIG_NET_VENDOR_BROCADE is not set
-# CONFIG_NET_VENDOR_CHELSIO is not set
-# CONFIG_NET_VENDOR_CISCO is not set
-# CONFIG_NET_VENDOR_DEC is not set
-# CONFIG_NET_VENDOR_DLINK is not set
-# CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_EXAR is not set
-# CONFIG_NET_VENDOR_HP is not set
-# CONFIG_NET_VENDOR_INTEL is not set
-# CONFIG_NET_VENDOR_MARVELL is not set
-# CONFIG_NET_VENDOR_MELLANOX is not set
-# CONFIG_NET_VENDOR_MICREL is not set
-# CONFIG_NET_VENDOR_MYRI is not set
-# CONFIG_NET_VENDOR_NATSEMI is not set
-# CONFIG_NET_VENDOR_NVIDIA is not set
-# CONFIG_NET_VENDOR_OKI is not set
-# CONFIG_NET_PACKET_ENGINE is not set
-# CONFIG_NET_VENDOR_QLOGIC is not set
-# CONFIG_NET_VENDOR_REALTEK is not set
-# CONFIG_NET_VENDOR_RDC is not set
-# CONFIG_NET_VENDOR_SEEQ is not set
-# CONFIG_NET_VENDOR_SILAN is not set
-# CONFIG_NET_VENDOR_SIS is not set
-# CONFIG_NET_VENDOR_SMSC is not set
-# CONFIG_NET_VENDOR_STMICRO is not set
-# CONFIG_NET_VENDOR_SUN is not set
-# CONFIG_NET_VENDOR_TEHUTI is not set
-# CONFIG_NET_VENDOR_TI is not set
-# CONFIG_NET_VENDOR_TOSHIBA is not set
-# CONFIG_NET_VENDOR_VIA is not set
-# CONFIG_WLAN is not set
-# CONFIG_VT is not set
-CONFIG_LEGACY_PTY_COUNT=16
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_HW_RANDOM=y
-# CONFIG_HWMON is not set
-CONFIG_VIDEO_OUTPUT_CONTROL=m
-CONFIG_FB=y
-CONFIG_FIRMWARE_EDID=y
-CONFIG_FB_MATROX=y
-CONFIG_FB_MATROX_G=y
-CONFIG_USB=y
-CONFIG_USB_EHCI_HCD=y
-# CONFIG_USB_EHCI_TT_NEWSCHED is not set
-CONFIG_USB_UHCI_HCD=y
-CONFIG_USB_STORAGE=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_IDE_DISK=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=y
-CONFIG_LEDS_TRIGGER_BACKLIGHT=y
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_CMOS=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_XFS_FS=y
-CONFIG_XFS_QUOTA=y
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_QUOTA=y
-CONFIG_QFMT_V2=y
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_CIFS=m
-CONFIG_CIFS_WEAK_PW_HASH=y
-CONFIG_CIFS_XATTR=y
-CONFIG_CIFS_POSIX=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_ISO8859_1=m
-# CONFIG_FTRACE is not set
-CONFIG_CRYPTO_NULL=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAST5=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRYPTO_HW is not set
diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig
index 10ef3bed5f4..f8a32315bb3 100644
--- a/arch/mips/configs/maltasmvp_defconfig
+++ b/arch/mips/configs/maltasmvp_defconfig
@@ -4,10 +4,9 @@ CONFIG_CPU_MIPS32_R2=y
 CONFIG_PAGE_SIZE_16KB=y
 CONFIG_MIPS_MT_SMP=y
 CONFIG_SCHED_SMT=y
-CONFIG_MIPS_CMP=y
+CONFIG_MIPS_CPS=y
 CONFIG_NR_CPUS=8
 CONFIG_HZ_100=y
-CONFIG_LOCALVERSION="cmp"
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_AUDIT=y
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index 2d3002cba10..c83338a3991 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -5,10 +5,9 @@ CONFIG_CPU_MIPS32_3_5_FEATURES=y
 CONFIG_PAGE_SIZE_16KB=y
 CONFIG_MIPS_MT_SMP=y
 CONFIG_SCHED_SMT=y
-CONFIG_MIPS_CMP=y
+CONFIG_MIPS_CPS=y
 CONFIG_NR_CPUS=8
 CONFIG_HZ_100=y
-CONFIG_LOCALVERSION="cmp"
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_AUDIT=y
diff --git a/arch/mips/configs/mips_paravirt_defconfig b/arch/mips/configs/mips_paravirt_defconfig
new file mode 100644
index 00000000000..84cfcb4bf2e
--- /dev/null
+++ b/arch/mips/configs/mips_paravirt_defconfig
@@ -0,0 +1,103 @@
+CONFIG_MIPS_PARAVIRT=y
+CONFIG_CPU_MIPS64_R2=y
+CONFIG_64BIT=y
+CONFIG_TRANSPARENT_HUGEPAGE=y
+CONFIG_SMP=y
+CONFIG_HZ_1000=y
+CONFIG_PREEMPT=y
+CONFIG_SYSVIPC=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_RELAY=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_SLAB=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PCI=y
+CONFIG_MIPS32_COMPAT=y
+CONFIG_MIPS32_O32=y
+CONFIG_MIPS32_N32=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+# CONFIG_INET_LRO is not set
+CONFIG_IPV6=y
+# CONFIG_WIRELESS is not set
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+# CONFIG_FW_LOADER is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+CONFIG_PHYLIB=y
+CONFIG_MARVELL_PHY=y
+CONFIG_BROADCOM_PHY=y
+CONFIG_BCM87XX_PHY=y
+# CONFIG_WLAN is not set
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+CONFIG_VIRTIO_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_MMIO=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_HUGETLBFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_UTF8=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_FTRACE is not set
+CONFIG_CRYPTO_CBC=y
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_DES=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
diff --git a/arch/mips/configs/rt305x_defconfig b/arch/mips/configs/rt305x_defconfig
index d1741bcf894..d14ae2fa7d1 100644
--- a/arch/mips/configs/rt305x_defconfig
+++ b/arch/mips/configs/rt305x_defconfig
@@ -81,7 +81,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
@@ -89,6 +88,7 @@ CONFIG_MTD_COMPLEX_MAPPINGS=y
 CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_MTD_M25P80=y
+CONFIG_MTD_SPI_NOR=y
 CONFIG_EEPROM_93CX6=m
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
diff --git a/arch/mips/dec/setup.c b/arch/mips/dec/setup.c
index 56e6e2c2368..41bbffd9cc0 100644
--- a/arch/mips/dec/setup.c
+++ b/arch/mips/dec/setup.c
@@ -23,6 +23,7 @@
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>
+#include <asm/cpu-type.h>
 #include <asm/irq.h>
 #include <asm/irq_cpu.h>
 #include <asm/mipsregs.h>
@@ -748,6 +749,10 @@ void __init arch_init_irq(void)
 		cpu_fpu_mask = 0;
 		dec_interrupt[DEC_IRQ_FPU] = -1;
 	}
+	/* Free the halt interrupt unused on R4k systems.  */
+	if (current_cpu_type() == CPU_R4000SC ||
+	    current_cpu_type() == CPU_R4400SC)
+		dec_interrupt[DEC_IRQ_HALT] = -1;
 
 	/* Register board interrupts: FPU and cascade. */
 	if (dec_interrupt[DEC_IRQ_FPU] >= 0)
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index b464b8b1147..935543f1453 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -17,26 +17,8 @@
 #ifdef CONFIG_64BIT
 #include <asm/asmmacro-64.h>
 #endif
-#ifdef CONFIG_MIPS_MT_SMTC
-#include <asm/mipsmtregs.h>
-#endif
-
-#ifdef CONFIG_MIPS_MT_SMTC
-	.macro	local_irq_enable reg=t0
-	mfc0	\reg, CP0_TCSTATUS
-	ori	\reg, \reg, TCSTATUS_IXMT
-	xori	\reg, \reg, TCSTATUS_IXMT
-	mtc0	\reg, CP0_TCSTATUS
-	_ehb
-	.endm
 
-	.macro	local_irq_disable reg=t0
-	mfc0	\reg, CP0_TCSTATUS
-	ori	\reg, \reg, TCSTATUS_IXMT
-	mtc0	\reg, CP0_TCSTATUS
-	_ehb
-	.endm
-#elif defined(CONFIG_CPU_MIPSR2)
+#ifdef CONFIG_CPU_MIPSR2
 	.macro	local_irq_enable reg=t0
 	ei
 	irq_enable_hazard
@@ -71,7 +53,7 @@
 	sw      \reg, TI_PRE_COUNT($28)
 #endif
 	.endm
-#endif /* CONFIG_MIPS_MT_SMTC */
+#endif /* CONFIG_CPU_MIPSR2 */
 
 	.macro	fpu_save_16even thread tmp=t0
 	cfc1	\tmp, fcr31
@@ -267,13 +249,35 @@
 	.set	pop
 	.endm
 #else
+
+#ifdef CONFIG_CPU_MICROMIPS
+#define CFC_MSA_INSN		0x587e0056
+#define CTC_MSA_INSN		0x583e0816
+#define LDD_MSA_INSN		0x58000837
+#define STD_MSA_INSN		0x5800083f
+#define COPY_UW_MSA_INSN	0x58f00056
+#define COPY_UD_MSA_INSN	0x58f80056
+#define INSERT_W_MSA_INSN	0x59300816
+#define INSERT_D_MSA_INSN	0x59380816
+#else
+#define CFC_MSA_INSN		0x787e0059
+#define CTC_MSA_INSN		0x783e0819
+#define LDD_MSA_INSN		0x78000823
+#define STD_MSA_INSN		0x78000827
+#define COPY_UW_MSA_INSN	0x78f00059
+#define COPY_UD_MSA_INSN	0x78f80059
+#define INSERT_W_MSA_INSN	0x79300819
+#define INSERT_D_MSA_INSN	0x79380819
+#endif
+
 	/*
 	 * Temporary until all toolchains in use include MSA support.
 	 */
 	.macro	cfcmsa	rd, cs
 	.set	push
 	.set	noat
-	.word	0x787e0059 | (\cs << 11)
+	.insn
+	.word	CFC_MSA_INSN | (\cs << 11)
 	move	\rd, $1
 	.set	pop
 	.endm
@@ -282,7 +286,7 @@
 	.set	push
 	.set	noat
 	move	$1, \rs
-	.word	0x783e0819 | (\cd << 6)
+	.word	CTC_MSA_INSN | (\cd << 6)
 	.set	pop
 	.endm
 
@@ -290,7 +294,7 @@
 	.set	push
 	.set	noat
 	add	$1, \base, \off
-	.word	0x78000823 | (\wd << 6)
+	.word	LDD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
 
@@ -298,14 +302,15 @@
 	.set	push
 	.set	noat
 	add	$1, \base, \off
-	.word	0x78000827 | (\wd << 6)
+	.word	STD_MSA_INSN | (\wd << 6)
 	.set	pop
 	.endm
 
 	.macro	copy_u_w	rd, ws, n
 	.set	push
 	.set	noat
-	.word	0x78f00059 | (\n << 16) | (\ws << 11)
+	.insn
+	.word	COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11)
 	/* move triggers an assembler bug... */
 	or	\rd, $1, zero
 	.set	pop
@@ -314,7 +319,8 @@
 	.macro	copy_u_d	rd, ws, n
 	.set	push
 	.set	noat
-	.word	0x78f80059 | (\n << 16) | (\ws << 11)
+	.insn
+	.word	COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11)
 	/* move triggers an assembler bug... */
 	or	\rd, $1, zero
 	.set	pop
@@ -325,7 +331,7 @@
 	.set	noat
 	/* move triggers an assembler bug... */
 	or	$1, \rs, zero
-	.word	0x79300819 | (\n << 16) | (\wd << 6)
+	.word	INSERT_W_MSA_INSN | (\n << 16) | (\wd << 6)
 	.set	pop
 	.endm
 
@@ -334,7 +340,7 @@
 	.set	noat
 	/* move triggers an assembler bug... */
 	or	$1, \rs, zero
-	.word	0x79380819 | (\n << 16) | (\wd << 6)
+	.word	INSERT_D_MSA_INSN | (\n << 16) | (\wd << 6)
 	.set	pop
 	.endm
 #endif
diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h
index e28a3e0eb3c..de781cf54bc 100644
--- a/arch/mips/include/asm/branch.h
+++ b/arch/mips/include/asm/branch.h
@@ -8,6 +8,8 @@
 #ifndef _ASM_BRANCH_H
 #define _ASM_BRANCH_H
 
+#include <asm/cpu-features.h>
+#include <asm/mipsregs.h>
 #include <asm/ptrace.h>
 #include <asm/inst.h>
 
@@ -18,12 +20,40 @@ extern int __compute_return_epc_for_insn(struct pt_regs *regs,
 extern int __microMIPS_compute_return_epc(struct pt_regs *regs);
 extern int __MIPS16e_compute_return_epc(struct pt_regs *regs);
 
+/*
+ * microMIPS bitfields
+ */
+#define MM_POOL32A_MINOR_MASK	0x3f
+#define MM_POOL32A_MINOR_SHIFT	0x6
+#define MM_MIPS32_COND_FC	0x30
+
+extern int __mm_isBranchInstr(struct pt_regs *regs,
+	struct mm_decoded_insn dec_insn, unsigned long *contpc);
+
+static inline int mm_isBranchInstr(struct pt_regs *regs,
+	struct mm_decoded_insn dec_insn, unsigned long *contpc)
+{
+	if (!cpu_has_mmips)
+		return 0;
+
+	return __mm_isBranchInstr(regs, dec_insn, contpc);
+}
 
 static inline int delay_slot(struct pt_regs *regs)
 {
 	return regs->cp0_cause & CAUSEF_BD;
 }
 
+static inline void clear_delay_slot(struct pt_regs *regs)
+{
+	regs->cp0_cause &= ~CAUSEF_BD;
+}
+
+static inline void set_delay_slot(struct pt_regs *regs)
+{
+	regs->cp0_cause |= CAUSEF_BD;
+}
+
 static inline unsigned long exception_epc(struct pt_regs *regs)
 {
 	if (likely(!delay_slot(regs)))
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index 69468ded282..e08381a37f8 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -113,6 +113,12 @@ unsigned long run_uncached(void *func);
 
 extern void *kmap_coherent(struct page *page, unsigned long addr);
 extern void kunmap_coherent(void);
+extern void *kmap_noncoherent(struct page *page, unsigned long addr);
+
+static inline void kunmap_noncoherent(void)
+{
+	kunmap_coherent();
+}
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
 static inline void flush_kernel_dcache_page(struct page *page)
diff --git a/arch/mips/include/asm/cmp.h b/arch/mips/include/asm/cmp.h
index 89a73fb93ae..033d97303c8 100644
--- a/arch/mips/include/asm/cmp.h
+++ b/arch/mips/include/asm/cmp.h
@@ -10,7 +10,6 @@ extern void cmp_smp_setup(void);
 extern void cmp_smp_finish(void);
 extern void cmp_boot_secondary(int cpu, struct task_struct *t);
 extern void cmp_init_secondary(void);
-extern void cmp_cpus_done(void);
 extern void cmp_prepare_cpus(unsigned int max_cpus);
 
 /* This is platform specific */
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index f56cc975b92..c7d8c997d93 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -110,9 +110,15 @@
 #ifndef cpu_has_smartmips
 #define cpu_has_smartmips	(cpu_data[0].ases & MIPS_ASE_SMARTMIPS)
 #endif
+
 #ifndef cpu_has_rixi
-#define cpu_has_rixi		(cpu_data[0].options & MIPS_CPU_RIXI)
+# ifdef CONFIG_64BIT
+# define cpu_has_rixi		(cpu_data[0].options & MIPS_CPU_RIXI)
+# else /* CONFIG_32BIT */
+# define cpu_has_rixi		((cpu_data[0].options & MIPS_CPU_RIXI) && !cpu_has_64bits)
+# endif
 #endif
+
 #ifndef cpu_has_mmips
 # ifdef CONFIG_SYS_SUPPORTS_MICROMIPS
 #  define cpu_has_mmips		(cpu_data[0].options & MIPS_CPU_MICROMIPS)
@@ -120,6 +126,7 @@
 #  define cpu_has_mmips		0
 # endif
 #endif
+
 #ifndef cpu_has_vtag_icache
 #define cpu_has_vtag_icache	(cpu_data[0].icache.flags & MIPS_CACHE_VTAG)
 #endif
@@ -183,6 +190,17 @@
 /*
  * Shortcuts ...
  */
+#define cpu_has_mips_2_3_4_5	(cpu_has_mips_2 | cpu_has_mips_3_4_5)
+#define cpu_has_mips_3_4_5	(cpu_has_mips_3 | cpu_has_mips_4_5)
+#define cpu_has_mips_4_5	(cpu_has_mips_4 | cpu_has_mips_5)
+
+#define cpu_has_mips_2_3_4_5_r	(cpu_has_mips_2 | cpu_has_mips_3_4_5_r)
+#define cpu_has_mips_3_4_5_r	(cpu_has_mips_3 | cpu_has_mips_4_5_r)
+#define cpu_has_mips_4_5_r	(cpu_has_mips_4 | cpu_has_mips_5_r)
+#define cpu_has_mips_5_r	(cpu_has_mips_5 | cpu_has_mips_r)
+
+#define cpu_has_mips_4_5_r2	(cpu_has_mips_4_5 | cpu_has_mips_r2)
+
 #define cpu_has_mips32	(cpu_has_mips32r1 | cpu_has_mips32r2)
 #define cpu_has_mips64	(cpu_has_mips64r1 | cpu_has_mips64r2)
 #define cpu_has_mips_r1 (cpu_has_mips32r1 | cpu_has_mips64r1)
diff --git a/arch/mips/include/asm/cpu-info.h b/arch/mips/include/asm/cpu-info.h
index ff2707ab329..47d5967ce7e 100644
--- a/arch/mips/include/asm/cpu-info.h
+++ b/arch/mips/include/asm/cpu-info.h
@@ -65,18 +65,13 @@ struct cpuinfo_mips {
 #ifdef CONFIG_64BIT
 	int			vmbits; /* Virtual memory size in bits */
 #endif
-#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
+#ifdef CONFIG_MIPS_MT_SMP
 	/*
-	 * In the MIPS MT "SMTC" model, each TC is considered
-	 * to be a "CPU" for the purposes of scheduling, but
-	 * exception resources, ASID spaces, etc, are common
-	 * to all TCs within the same VPE.
+	 * There is not necessarily a 1:1 mapping of VPE num to CPU number
+	 * in particular on multi-core systems.
 	 */
 	int			vpe_id;	 /* Virtual Processor number */
 #endif
-#ifdef CONFIG_MIPS_MT_SMTC
-	int			tc_id;	 /* Thread Context number */
-#endif
 	void			*data;	/* Additional data */
 	unsigned int		watch_reg_count;   /* Number that exist */
 	unsigned int		watch_reg_use_cnt; /* Usable by ptrace */
@@ -117,7 +112,7 @@ struct proc_cpuinfo_notifier_args {
 	unsigned long n;
 };
 
-#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
+#ifdef CONFIG_MIPS_MT_SMP
 # define cpu_vpe_id(cpuinfo)	((cpuinfo)->vpe_id)
 #else
 # define cpu_vpe_id(cpuinfo)	0
diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h
index 721906130a5..b4e2bd87df5 100644
--- a/arch/mips/include/asm/cpu-type.h
+++ b/arch/mips/include/asm/cpu-type.h
@@ -155,9 +155,6 @@ static inline int __pure __get_cpu_type(const int cpu_type)
 	case CPU_RM7000:
 	case CPU_SR71000:
 #endif
-#ifdef CONFIG_SYS_HAS_CPU_RM9000
-	case CPU_RM9000:
-#endif
 #ifdef CONFIG_SYS_HAS_CPU_SB1
 	case CPU_SB1:
 	case CPU_SB1A:
@@ -166,6 +163,7 @@ static inline int __pure __get_cpu_type(const int cpu_type)
 	case CPU_CAVIUM_OCTEON:
 	case CPU_CAVIUM_OCTEON_PLUS:
 	case CPU_CAVIUM_OCTEON2:
+	case CPU_CAVIUM_OCTEON3:
 #endif
 
 #if defined(CONFIG_SYS_HAS_CPU_BMIPS32_3300) || \
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 530eb8b3a68..129d08701e9 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -201,6 +201,7 @@
 #define PRID_IMP_NETLOGIC_XLP3XX	0x1100
 #define PRID_IMP_NETLOGIC_XLP2XX	0x1200
 #define PRID_IMP_NETLOGIC_XLP9XX	0x1500
+#define PRID_IMP_NETLOGIC_XLP5XX	0x1300
 
 /*
  * Particular Revision values for bits 7:0 of the PRId register.
@@ -281,7 +282,7 @@ enum cpu_type_enum {
 	CPU_R4700, CPU_R5000, CPU_R5500, CPU_NEVADA, CPU_R5432, CPU_R10000,
 	CPU_R12000, CPU_R14000, CPU_VR41XX, CPU_VR4111, CPU_VR4121, CPU_VR4122,
 	CPU_VR4131, CPU_VR4133, CPU_VR4181, CPU_VR4181A, CPU_RM7000,
-	CPU_SR71000, CPU_RM9000, CPU_TX49XX,
+	CPU_SR71000, CPU_TX49XX,
 
 	/*
 	 * R8000 class processors
diff --git a/arch/mips/include/asm/dec/kn05.h b/arch/mips/include/asm/dec/kn05.h
index 56d22dc8803..8e14f677e5e 100644
--- a/arch/mips/include/asm/dec/kn05.h
+++ b/arch/mips/include/asm/dec/kn05.h
@@ -49,12 +49,20 @@
 #define KN4K_RES_15	(15*IOASIC_SLOT_SIZE)	/* unused? */
 
 /*
+ * MB ASIC interrupt bits.
+ */
+#define KN4K_MB_INR_MB		4	/* ??? */
+#define KN4K_MB_INR_MT		3	/* memory, I/O bus read/write errors */
+#define KN4K_MB_INR_RES_2	2	/* unused */
+#define KN4K_MB_INR_RTC		1	/* RTC */
+#define KN4K_MB_INR_TC		0	/* I/O ASIC cascade */
+
+/*
  * Bits for the MB interrupt register.
  * The register appears read-only.
  */
-#define KN4K_MB_INT_TC		(1<<0)		/* TURBOchannel? */
-#define KN4K_MB_INT_RTC		(1<<1)		/* RTC? */
-#define KN4K_MB_INT_MT		(1<<3)		/* I/O ASIC cascade */
+#define KN4K_MB_INT_IRQ		(0x1f<<0)	/* CPU Int[4:0] status. */
+#define KN4K_MB_INT_IRQ_N(n)	(1<<(n))	/* Individual status bits. */
 
 /*
  * Bits for the MB control & status register.
@@ -70,6 +78,7 @@
 #define KN4K_MB_CSR_NC		(1<<14)		/* ??? */
 #define KN4K_MB_CSR_EE		(1<<15)		/* (bus) Exception Enable? */
 #define KN4K_MB_CSR_MSK		(0x1f<<16)	/* CPU Int[4:0] mask */
+#define KN4K_MB_CSR_MSK_N(n)	(1<<((n)+16))	/* Individual mask bits. */
 #define KN4K_MB_CSR_FW		(1<<21)		/* ??? */
 #define KN4K_MB_CSR_W		(1<<31)		/* ??? */
 
diff --git a/arch/mips/include/asm/fixmap.h b/arch/mips/include/asm/fixmap.h
index 8c012af2f45..6842ffafd1e 100644
--- a/arch/mips/include/asm/fixmap.h
+++ b/arch/mips/include/asm/fixmap.h
@@ -48,11 +48,7 @@
 enum fixed_addresses {
 #define FIX_N_COLOURS 8
 	FIX_CMAP_BEGIN,
-#ifdef CONFIG_MIPS_MT_SMTC
-	FIX_CMAP_END = FIX_CMAP_BEGIN + (FIX_N_COLOURS * NR_CPUS * 2),
-#else
 	FIX_CMAP_END = FIX_CMAP_BEGIN + (FIX_N_COLOURS * 2),
-#endif
 #ifdef CONFIG_HIGHMEM
 	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_BEGIN = FIX_CMAP_END + 1,
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 4d86b72750c..a939574f829 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -17,6 +17,7 @@
 #include <asm/mipsregs.h>
 #include <asm/cpu.h>
 #include <asm/cpu-features.h>
+#include <asm/fpu_emulator.h>
 #include <asm/hazards.h>
 #include <asm/processor.h>
 #include <asm/current.h>
@@ -28,7 +29,6 @@
 struct sigcontext;
 struct sigcontext32;
 
-extern void fpu_emulator_init_fpu(void);
 extern void _init_fpu(void);
 extern void _save_fp(struct task_struct *);
 extern void _restore_fp(struct task_struct *);
@@ -156,15 +156,16 @@ static inline int init_fpu(void)
 	int ret = 0;
 
 	preempt_disable();
+
 	if (cpu_has_fpu) {
 		ret = __own_fpu();
 		if (!ret)
 			_init_fpu();
-	} else {
+	} else
 		fpu_emulator_init_fpu();
-	}
 
 	preempt_enable();
+
 	return ret;
 }
 
diff --git a/arch/mips/include/asm/fpu_emulator.h b/arch/mips/include/asm/fpu_emulator.h
index 2abb587d5ab..0195745b4b1 100644
--- a/arch/mips/include/asm/fpu_emulator.h
+++ b/arch/mips/include/asm/fpu_emulator.h
@@ -23,9 +23,12 @@
 #ifndef _ASM_FPU_EMULATOR_H
 #define _ASM_FPU_EMULATOR_H
 
+#include <linux/sched.h>
 #include <asm/break.h>
+#include <asm/thread_info.h>
 #include <asm/inst.h>
 #include <asm/local.h>
+#include <asm/processor.h>
 
 #ifdef CONFIG_DEBUG_FS
 
@@ -36,6 +39,11 @@ struct mips_fpu_emulator_stats {
 	local_t cp1ops;
 	local_t cp1xops;
 	local_t errors;
+	local_t ieee754_inexact;
+	local_t ieee754_underflow;
+	local_t ieee754_overflow;
+	local_t ieee754_zerodiv;
+	local_t ieee754_invalidop;
 };
 
 DECLARE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
@@ -71,4 +79,17 @@ int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
  */
 #define BREAK_MATH (0x0000000d | (BRK_MEMU << 16))
 
+#define SIGNALLING_NAN 0x7ff800007ff80000LL
+
+static inline void fpu_emulator_init_fpu(void)
+{
+	struct task_struct *t = current;
+	int i;
+
+	t->thread.fpu.fcr31 = 0;
+
+	for (i = 0; i < 32; i++)
+		set_fpr64(&t->thread.fpu.fpr[i], 0, SIGNALLING_NAN);
+}
+
 #endif /* _ASM_FPU_EMULATOR_H */
diff --git a/arch/mips/include/asm/gic.h b/arch/mips/include/asm/gic.h
index 08271669058..10f6a99f92c 100644
--- a/arch/mips/include/asm/gic.h
+++ b/arch/mips/include/asm/gic.h
@@ -380,6 +380,7 @@ extern unsigned int gic_compare_int (void);
 extern cycle_t gic_read_count(void);
 extern cycle_t gic_read_compare(void);
 extern void gic_write_compare(cycle_t cnt);
+extern void gic_write_cpu_compare(cycle_t cnt, int cpu);
 extern void gic_send_ipi(unsigned int intr);
 extern unsigned int plat_ipi_call_int_xlate(unsigned int);
 extern unsigned int plat_ipi_resched_int_xlate(unsigned int);
diff --git a/arch/mips/include/asm/gio_device.h b/arch/mips/include/asm/gio_device.h
index 0878701712f..4be1a57cdbb 100644
--- a/arch/mips/include/asm/gio_device.h
+++ b/arch/mips/include/asm/gio_device.h
@@ -50,7 +50,7 @@ static inline void gio_device_free(struct gio_device *dev)
 extern int gio_register_driver(struct gio_driver *);
 extern void gio_unregister_driver(struct gio_driver *);
 
-#define gio_get_drvdata(_dev)	     drv_get_drvdata(&(_dev)->dev)
-#define gio_set_drvdata(_dev, data)  drv_set_drvdata(&(_dev)->dev, (data))
+#define gio_get_drvdata(_dev)	     dev_get_drvdata(&(_dev)->dev)
+#define gio_set_drvdata(_dev, data)  dev_set_drvdata(&(_dev)->dev, (data))
 
 extern void gio_set_master(struct gio_device *);
diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h
index d192158886b..d9f932de80e 100644
--- a/arch/mips/include/asm/idle.h
+++ b/arch/mips/include/asm/idle.h
@@ -1,6 +1,7 @@
 #ifndef __ASM_IDLE_H
 #define __ASM_IDLE_H
 
+#include <linux/cpuidle.h>
 #include <linux/linkage.h>
 
 extern void (*cpu_wait)(void);
@@ -20,4 +21,17 @@ static inline int address_is_in_r4k_wait_irqoff(unsigned long addr)
 	       addr < (unsigned long)__pastwait;
 }
 
+extern int mips_cpuidle_wait_enter(struct cpuidle_device *dev,
+				   struct cpuidle_driver *drv, int index);
+
+#define MIPS_CPUIDLE_WAIT_STATE {\
+	.enter			= mips_cpuidle_wait_enter,\
+	.exit_latency		= 1,\
+	.target_residency	= 1,\
+	.power_usage		= UINT_MAX,\
+	.flags			= CPUIDLE_FLAG_TIME_VALID,\
+	.name			= "wait",\
+	.desc			= "MIPS wait",\
+}
+
 #endif /* __ASM_IDLE_H  */
diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h
index 7bc2cdb3505..ae1f7b24dd1 100644
--- a/arch/mips/include/asm/irq.h
+++ b/arch/mips/include/asm/irq.h
@@ -26,104 +26,8 @@ static inline int irq_canonicalize(int irq)
 #define irq_canonicalize(irq) (irq)	/* Sane hardware, sane code ... */
 #endif
 
-#ifdef CONFIG_MIPS_MT_SMTC
-
-struct irqaction;
-
-extern unsigned long irq_hwmask[];
-extern int setup_irq_smtc(unsigned int irq, struct irqaction * new,
-			  unsigned long hwmask);
-
-static inline void smtc_im_ack_irq(unsigned int irq)
-{
-	if (irq_hwmask[irq] & ST0_IM)
-		set_c0_status(irq_hwmask[irq] & ST0_IM);
-}
-
-#else
-
-static inline void smtc_im_ack_irq(unsigned int irq)
-{
-}
-
-#endif /* CONFIG_MIPS_MT_SMTC */
-
-#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
-#include <linux/cpumask.h>
-
-extern int plat_set_irq_affinity(struct irq_data *d,
-				 const struct cpumask *affinity, bool force);
-extern void smtc_forward_irq(struct irq_data *d);
-
-/*
- * IRQ affinity hook invoked at the beginning of interrupt dispatch
- * if option is enabled.
- *
- * Up through Linux 2.6.22 (at least) cpumask operations are very
- * inefficient on MIPS.	 Initial prototypes of SMTC IRQ affinity
- * used a "fast path" per-IRQ-descriptor cache of affinity information
- * to reduce latency.  As there is a project afoot to optimize the
- * cpumask implementations, this version is optimistically assuming
- * that cpumask.h macro overhead is reasonable during interrupt dispatch.
- */
-static inline int handle_on_other_cpu(unsigned int irq)
-{
-	struct irq_data *d = irq_get_irq_data(irq);
-
-	if (cpumask_test_cpu(smp_processor_id(), d->affinity))
-		return 0;
-	smtc_forward_irq(d);
-	return 1;
-}
-
-#else /* Not doing SMTC affinity */
-
-static inline int handle_on_other_cpu(unsigned int irq) { return 0; }
-
-#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
-
-#ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP
-
-static inline void smtc_im_backstop(unsigned int irq)
-{
-	if (irq_hwmask[irq] & 0x0000ff00)
-		write_c0_tccontext(read_c0_tccontext() &
-				   ~(irq_hwmask[irq] & 0x0000ff00));
-}
-
-/*
- * Clear interrupt mask handling "backstop" if irq_hwmask
- * entry so indicates. This implies that the ack() or end()
- * functions will take over re-enabling the low-level mask.
- * Otherwise it will be done on return from exception.
- */
-static inline int smtc_handle_on_other_cpu(unsigned int irq)
-{
-	int ret = handle_on_other_cpu(irq);
-
-	if (!ret)
-		smtc_im_backstop(irq);
-	return ret;
-}
-
-#else
-
-static inline void smtc_im_backstop(unsigned int irq) { }
-static inline int smtc_handle_on_other_cpu(unsigned int irq)
-{
-	return handle_on_other_cpu(irq);
-}
-
-#endif
-
 extern void do_IRQ(unsigned int irq);
 
-#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
-
-extern void do_IRQ_no_affinity(unsigned int irq);
-
-#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
-
 extern void arch_init_irq(void);
 extern void spurious_interrupt(void);
 
diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h
index 45c00951888..0fa5fdcd1f0 100644
--- a/arch/mips/include/asm/irqflags.h
+++ b/arch/mips/include/asm/irqflags.h
@@ -17,7 +17,7 @@
 #include <linux/stringify.h>
 #include <asm/hazards.h>
 
-#if defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_MIPS_MT_SMTC)
+#ifdef CONFIG_CPU_MIPSR2
 
 static inline void arch_local_irq_disable(void)
 {
@@ -118,30 +118,15 @@ void arch_local_irq_disable(void);
 unsigned long arch_local_irq_save(void);
 void arch_local_irq_restore(unsigned long flags);
 void __arch_local_irq_restore(unsigned long flags);
-#endif /* if defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_MIPS_MT_SMTC) */
-
-
-extern void smtc_ipi_replay(void);
+#endif /* CONFIG_CPU_MIPSR2 */
 
 static inline void arch_local_irq_enable(void)
 {
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * SMTC kernel needs to do a software replay of queued
-	 * IPIs, at the cost of call overhead on each local_irq_enable()
-	 */
-	smtc_ipi_replay();
-#endif
 	__asm__ __volatile__(
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	$1, $2, 1	# SMTC - clear TCStatus.IXMT	\n"
-	"	ori	$1, 0x400					\n"
-	"	xori	$1, 0x400					\n"
-	"	mtc0	$1, $2, 1					\n"
-#elif defined(CONFIG_CPU_MIPSR2)
+#if   defined(CONFIG_CPU_MIPSR2)
 	"	ei							\n"
 #else
 	"	mfc0	$1,$12						\n"
@@ -163,11 +148,7 @@ static inline unsigned long arch_local_save_flags(void)
 	asm __volatile__(
 	"	.set	push						\n"
 	"	.set	reorder						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	%[flags], $2, 1					\n"
-#else
 	"	mfc0	%[flags], $12					\n"
-#endif
 	"	.set	pop						\n"
 	: [flags] "=r" (flags));
 
@@ -177,14 +158,7 @@ static inline unsigned long arch_local_save_flags(void)
 
 static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * SMTC model uses TCStatus.IXMT to disable interrupts for a thread/CPU
-	 */
-	return flags & 0x400;
-#else
 	return !(flags & 1);
-#endif
 }
 
 #endif /* #ifndef __ASSEMBLY__ */
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index b0aa9556575..7a3fc67bd7f 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -359,13 +359,17 @@ enum emulation_result {
 #define MIPS3_PG_FRAME		0x3fffffc0
 
 #define VPN2_MASK		0xffffe000
-#define TLB_IS_GLOBAL(x)	(((x).tlb_lo0 & MIPS3_PG_G) &&	\
+#define TLB_IS_GLOBAL(x)	(((x).tlb_lo0 & MIPS3_PG_G) &&		\
 				 ((x).tlb_lo1 & MIPS3_PG_G))
 #define TLB_VPN2(x)		((x).tlb_hi & VPN2_MASK)
 #define TLB_ASID(x)		((x).tlb_hi & ASID_MASK)
-#define TLB_IS_VALID(x, va)	(((va) & (1 << PAGE_SHIFT))	\
-				 ? ((x).tlb_lo1 & MIPS3_PG_V)	\
+#define TLB_IS_VALID(x, va)	(((va) & (1 << PAGE_SHIFT))		\
+				 ? ((x).tlb_lo1 & MIPS3_PG_V)		\
 				 : ((x).tlb_lo0 & MIPS3_PG_V))
+#define TLB_HI_VPN2_HIT(x, y)	((TLB_VPN2(x) & ~(x).tlb_mask) ==	\
+				 ((y) & VPN2_MASK & ~(x).tlb_mask))
+#define TLB_HI_ASID_HIT(x, y)	(TLB_IS_GLOBAL(x) ||			\
+				 TLB_ASID(x) == ((y) & ASID_MASK))
 
 struct kvm_mips_tlb {
 	long tlb_mask;
@@ -760,7 +764,7 @@ extern int kvm_mips_trans_mtc0(uint32_t inst, uint32_t *opc,
 			       struct kvm_vcpu *vcpu);
 
 /* Misc */
-extern int kvm_mips_dump_stats(struct kvm_vcpu *vcpu);
+extern void kvm_mips_dump_stats(struct kvm_vcpu *vcpu);
 extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm);
 
 
diff --git a/arch/mips/include/asm/kvm_para.h b/arch/mips/include/asm/kvm_para.h
new file mode 100644
index 00000000000..5a9aa918abe
--- /dev/null
+++ b/arch/mips/include/asm/kvm_para.h
@@ -0,0 +1,109 @@
+#ifndef _ASM_MIPS_KVM_PARA_H
+#define _ASM_MIPS_KVM_PARA_H
+
+#include <uapi/asm/kvm_para.h>
+
+#define KVM_HYPERCALL ".word 0x42000028"
+
+/*
+ * Hypercalls for KVM.
+ *
+ * Hypercall number is passed in v0.
+ * Return value will be placed in v0.
+ * Up to 3 arguments are passed in a0, a1, and a2.
+ */
+static inline unsigned long kvm_hypercall0(unsigned long num)
+{
+	register unsigned long n asm("v0");
+	register unsigned long r asm("v0");
+
+	n = num;
+	__asm__ __volatile__(
+		KVM_HYPERCALL
+		: "=r" (r) : "r" (n) : "memory"
+		);
+
+	return r;
+}
+
+static inline unsigned long kvm_hypercall1(unsigned long num,
+					unsigned long arg0)
+{
+	register unsigned long n asm("v0");
+	register unsigned long r asm("v0");
+	register unsigned long a0 asm("a0");
+
+	n = num;
+	a0 = arg0;
+	__asm__ __volatile__(
+		KVM_HYPERCALL
+		: "=r" (r) : "r" (n), "r" (a0) : "memory"
+		);
+
+	return r;
+}
+
+static inline unsigned long kvm_hypercall2(unsigned long num,
+					unsigned long arg0, unsigned long arg1)
+{
+	register unsigned long n asm("v0");
+	register unsigned long r asm("v0");
+	register unsigned long a0 asm("a0");
+	register unsigned long a1 asm("a1");
+
+	n = num;
+	a0 = arg0;
+	a1 = arg1;
+	__asm__ __volatile__(
+		KVM_HYPERCALL
+		: "=r" (r) : "r" (n), "r" (a0), "r" (a1) : "memory"
+		);
+
+	return r;
+}
+
+static inline unsigned long kvm_hypercall3(unsigned long num,
+	unsigned long arg0, unsigned long arg1, unsigned long arg2)
+{
+	register unsigned long n asm("v0");
+	register unsigned long r asm("v0");
+	register unsigned long a0 asm("a0");
+	register unsigned long a1 asm("a1");
+	register unsigned long a2 asm("a2");
+
+	n = num;
+	a0 = arg0;
+	a1 = arg1;
+	a2 = arg2;
+	__asm__ __volatile__(
+		KVM_HYPERCALL
+		: "=r" (r) : "r" (n), "r" (a0), "r" (a1), "r" (a2) : "memory"
+		);
+
+	return r;
+}
+
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return 0;
+}
+
+#ifdef CONFIG_MIPS_PARAVIRT
+static inline bool kvm_para_available(void)
+{
+	return true;
+}
+#else
+static inline bool kvm_para_available(void)
+{
+	return false;
+}
+#endif
+
+
+#endif /* _ASM_MIPS_KVM_PARA_H */
diff --git a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
index 94ed063eec9..cf802287289 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/cpu-feature-overrides.h
@@ -22,7 +22,6 @@
 #define cpu_has_3k_cache	0
 #define cpu_has_4k_cache	0
 #define cpu_has_tx39_cache	0
-#define cpu_has_fpu		0
 #define cpu_has_counter		1
 #define cpu_has_watch		1
 #define cpu_has_divec		1
diff --git a/arch/mips/include/asm/mach-cavium-octeon/irq.h b/arch/mips/include/asm/mach-cavium-octeon/irq.h
index 60fc4c347c4..cceae32a073 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/irq.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/irq.h
@@ -35,6 +35,8 @@ enum octeon_irq {
 	OCTEON_IRQ_PCI_MSI2,
 	OCTEON_IRQ_PCI_MSI3,
 
+	OCTEON_IRQ_TWSI,
+	OCTEON_IRQ_TWSI2,
 	OCTEON_IRQ_RML,
 	OCTEON_IRQ_TIMER0,
 	OCTEON_IRQ_TIMER1,
diff --git a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h
index 1bcb6421205..1dfe47453ea 100644
--- a/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ip22/cpu-feature-overrides.h
@@ -39,6 +39,10 @@
 #define cpu_has_nofpuex		0
 #define cpu_has_64bits		1
 
+#define cpu_has_mips_2		1
+#define cpu_has_mips_3		1
+#define cpu_has_mips_5		0
+
 #define cpu_has_mips32r1	0
 #define cpu_has_mips32r2	0
 #define cpu_has_mips64r1	0
diff --git a/arch/mips/include/asm/mach-malta/kernel-entry-init.h b/arch/mips/include/asm/mach-malta/kernel-entry-init.h
index 7c5e17a1784..77eeda77e73 100644
--- a/arch/mips/include/asm/mach-malta/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-malta/kernel-entry-init.h
@@ -80,36 +80,6 @@
 	.endm
 
 	.macro	kernel_entry_setup
-#ifdef CONFIG_MIPS_MT_SMTC
-	mfc0	t0, CP0_CONFIG
-	bgez	t0, 9f
-	mfc0	t0, CP0_CONFIG, 1
-	bgez	t0, 9f
-	mfc0	t0, CP0_CONFIG, 2
-	bgez	t0, 9f
-	mfc0	t0, CP0_CONFIG, 3
-	and	t0, 1<<2
-	bnez	t0, 0f
-9:
-	/* Assume we came from YAMON... */
-	PTR_LA	v0, 0x9fc00534	/* YAMON print */
-	lw	v0, (v0)
-	move	a0, zero
-	PTR_LA	a1, nonmt_processor
-	jal	v0
-
-	PTR_LA	v0, 0x9fc00520	/* YAMON exit */
-	lw	v0, (v0)
-	li	a0, 1
-	jal	v0
-
-1:	b	1b
-
-	__INITDATA
-nonmt_processor:
-	.asciz	"SMTC kernel requires the MT ASE to run\n"
-	__FINIT
-#endif
 
 #ifdef CONFIG_EVA
 	sync
diff --git a/arch/mips/include/asm/mach-malta/malta-pm.h b/arch/mips/include/asm/mach-malta/malta-pm.h
new file mode 100644
index 00000000000..c2c2e201013
--- /dev/null
+++ b/arch/mips/include/asm/mach-malta/malta-pm.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2014 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __ASM_MIPS_MACH_MALTA_PM_H__
+#define __ASM_MIPS_MACH_MALTA_PM_H__
+
+#include <asm/mips-boards/piix4.h>
+
+#ifdef CONFIG_MIPS_MALTA_PM
+
+/**
+ * mips_pm_suspend - enter a suspend state
+ * @state: the state to enter, one of PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_*
+ *
+ * Enters a suspend state via the Malta's PIIX4. If the state to be entered
+ * is one which loses context (eg. SOFF) then this function will never
+ * return.
+ */
+extern int mips_pm_suspend(unsigned state);
+
+#else /* !CONFIG_MIPS_MALTA_PM */
+
+static inline int mips_pm_suspend(unsigned state)
+{
+	return -EINVAL;
+}
+
+#endif /* !CONFIG_MIPS_MALTA_PM */
+
+#endif /* __ASM_MIPS_MACH_MALTA_PM_H__ */
diff --git a/arch/mips/include/asm/mach-netlogic/topology.h b/arch/mips/include/asm/mach-netlogic/topology.h
index 0da99fa11c3..ceeb1f5e712 100644
--- a/arch/mips/include/asm/mach-netlogic/topology.h
+++ b/arch/mips/include/asm/mach-netlogic/topology.h
@@ -10,10 +10,12 @@
 
 #include <asm/mach-netlogic/multi-node.h>
 
+#ifdef CONFIG_SMP
 #define topology_physical_package_id(cpu)	cpu_to_node(cpu)
 #define topology_core_id(cpu)	(cpu_logical_map(cpu) / NLM_THREADS_PER_CORE)
 #define topology_thread_cpumask(cpu)		(&cpu_sibling_map[cpu])
 #define topology_core_cpumask(cpu)	cpumask_of_node(cpu_to_node(cpu))
+#endif
 
 #include <asm-generic/topology.h>
 
diff --git a/arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h b/arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h
new file mode 100644
index 00000000000..725e1ed83f6
--- /dev/null
+++ b/arch/mips/include/asm/mach-paravirt/cpu-feature-overrides.h
@@ -0,0 +1,36 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 Cavium, Inc.
+ */
+#ifndef __ASM_MACH_PARAVIRT_CPU_FEATURE_OVERRIDES_H
+#define __ASM_MACH_PARAVIRT_CPU_FEATURE_OVERRIDES_H
+
+#define cpu_has_4kex		1
+#define cpu_has_3k_cache	0
+#define cpu_has_tx39_cache	0
+#define cpu_has_counter		1
+#define cpu_has_llsc		1
+/*
+ * We Disable LL/SC on non SMP systems as it is faster to disable
+ * interrupts for atomic access than a LL/SC.
+ */
+#ifdef CONFIG_SMP
+# define kernel_uses_llsc	1
+#else
+# define kernel_uses_llsc	0
+#endif
+
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+#define cpu_dcache_line_size()	128
+#define cpu_icache_line_size()	128
+#define cpu_has_octeon_cache	1
+#define cpu_has_4k_cache	0
+#else
+#define cpu_has_octeon_cache	0
+#define cpu_has_4k_cache	1
+#endif
+
+#endif /* __ASM_MACH_PARAVIRT_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mach-paravirt/irq.h b/arch/mips/include/asm/mach-paravirt/irq.h
new file mode 100644
index 00000000000..9b4d35eca97
--- /dev/null
+++ b/arch/mips/include/asm/mach-paravirt/irq.h
@@ -0,0 +1,19 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 Cavium, Inc.
+ */
+#ifndef __ASM_MACH_PARAVIRT_IRQ_H__
+#define  __ASM_MACH_PARAVIRT_IRQ_H__
+
+#define NR_IRQS 64
+#define MIPS_CPU_IRQ_BASE 1
+
+#define MIPS_IRQ_PCIA (MIPS_CPU_IRQ_BASE + 8)
+
+#define MIPS_IRQ_MBOX0 (MIPS_CPU_IRQ_BASE + 32)
+#define MIPS_IRQ_MBOX1 (MIPS_CPU_IRQ_BASE + 33)
+
+#endif /* __ASM_MACH_PARAVIRT_IRQ_H__ */
diff --git a/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
new file mode 100644
index 00000000000..2f82bfa3a77
--- /dev/null
+++ b/arch/mips/include/asm/mach-paravirt/kernel-entry-init.h
@@ -0,0 +1,50 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 Cavium, Inc
+ */
+#ifndef __ASM_MACH_PARAVIRT_KERNEL_ENTRY_H
+#define __ASM_MACH_PARAVIRT_KERNEL_ENTRY_H
+
+#define CP0_EBASE $15, 1
+
+	.macro  kernel_entry_setup
+	mfc0	t0, CP0_EBASE
+	andi	t0, t0, 0x3ff		# CPUNum
+	beqz	t0, 1f
+	# CPUs other than zero goto smp_bootstrap
+	j	smp_bootstrap
+
+1:
+	.endm
+
+/*
+ * Do SMP slave processor setup necessary before we can safely execute
+ * C code.
+ */
+	.macro  smp_slave_setup
+	mfc0	t0, CP0_EBASE
+	andi	t0, t0, 0x3ff		# CPUNum
+	slti	t1, t0, NR_CPUS
+	bnez	t1, 1f
+2:
+	di
+	wait
+	b	2b			# Unknown CPU, loop forever.
+1:
+	PTR_LA	t1, paravirt_smp_sp
+	PTR_SLL	t0, PTR_SCALESHIFT
+	PTR_ADDU t1, t1, t0
+3:
+	PTR_L	sp, 0(t1)
+	beqz	sp, 3b			# Spin until told to proceed.
+
+	PTR_LA	t1, paravirt_smp_gp
+	PTR_ADDU t1, t1, t0
+	sync
+	PTR_L	gp, 0(t1)
+	.endm
+
+#endif /* __ASM_MACH_PARAVIRT_KERNEL_ENTRY_H */
diff --git a/arch/mips/include/asm/mach-paravirt/war.h b/arch/mips/include/asm/mach-paravirt/war.h
new file mode 100644
index 00000000000..36d3afb9845
--- /dev/null
+++ b/arch/mips/include/asm/mach-paravirt/war.h
@@ -0,0 +1,25 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2002, 2004, 2007 by Ralf Baechle <ralf@linux-mips.org>
+ * Copyright (C) 2013 Cavium Networks <support@caviumnetworks.com>
+ */
+#ifndef __ASM_MIPS_MACH_PARAVIRT_WAR_H
+#define __ASM_MIPS_MACH_PARAVIRT_WAR_H
+
+#define R4600_V1_INDEX_ICACHEOP_WAR	0
+#define R4600_V1_HIT_CACHEOP_WAR	0
+#define R4600_V2_HIT_CACHEOP_WAR	0
+#define R5432_CP0_INTERRUPT_WAR		0
+#define BCM1250_M3_WAR			0
+#define SIBYTE_1956_WAR			0
+#define MIPS4K_ICACHE_REFILL_WAR	0
+#define MIPS_CACHE_SYNC_WAR		0
+#define TX49XX_ICACHE_INDEX_INV_WAR	0
+#define ICACHE_REFILLS_WORKAROUND_WAR	0
+#define R10000_LLSC_WAR			0
+#define MIPS34K_MISSED_ITLB_WAR		0
+
+#endif /* __ASM_MIPS_MACH_PARAVIRT_WAR_H */
diff --git a/arch/mips/include/asm/mach-pmcs-msp71xx/msp_usb.h b/arch/mips/include/asm/mach-pmcs-msp71xx/msp_usb.h
index aa45e6a0712..fe1566f2913 100644
--- a/arch/mips/include/asm/mach-pmcs-msp71xx/msp_usb.h
+++ b/arch/mips/include/asm/mach-pmcs-msp71xx/msp_usb.h
@@ -25,11 +25,7 @@
 #ifndef MSP_USB_H_
 #define MSP_USB_H_
 
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-#define NUM_USB_DEVS   2
-#else
 #define NUM_USB_DEVS   1
-#endif
 
 /* Register spaces for USB host 0 */
 #define MSP_USB0_MAB_START	(MSP_USB0_BASE + 0x0)
diff --git a/arch/mips/include/asm/mach-ralink/war.h b/arch/mips/include/asm/mach-ralink/war.h
index a7b712cf2d2..c074b5dc1f8 100644
--- a/arch/mips/include/asm/mach-ralink/war.h
+++ b/arch/mips/include/asm/mach-ralink/war.h
@@ -17,7 +17,6 @@
 #define MIPS4K_ICACHE_REFILL_WAR	0
 #define MIPS_CACHE_SYNC_WAR		0
 #define TX49XX_ICACHE_INDEX_INV_WAR	0
-#define RM9000_CDEX_SMP_WAR		0
 #define ICACHE_REFILLS_WORKAROUND_WAR	0
 #define R10000_LLSC_WAR			0
 #define MIPS34K_MISSED_ITLB_WAR		0
diff --git a/arch/mips/include/asm/mach-sead3/kernel-entry-init.h b/arch/mips/include/asm/mach-sead3/kernel-entry-init.h
index 3dfbd8e7947..6cccd4d558d 100644
--- a/arch/mips/include/asm/mach-sead3/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-sead3/kernel-entry-init.h
@@ -10,37 +10,6 @@
 #define __ASM_MACH_MIPS_KERNEL_ENTRY_INIT_H
 
 	.macro	kernel_entry_setup
-#ifdef CONFIG_MIPS_MT_SMTC
-	mfc0	t0, CP0_CONFIG
-	bgez	t0, 9f
-	mfc0	t0, CP0_CONFIG, 1
-	bgez	t0, 9f
-	mfc0	t0, CP0_CONFIG, 2
-	bgez	t0, 9f
-	mfc0	t0, CP0_CONFIG, 3
-	and	t0, 1<<2
-	bnez	t0, 0f
-9 :
-	/* Assume we came from YAMON... */
-	PTR_LA	v0, 0x9fc00534	/* YAMON print */
-	lw	v0, (v0)
-	move	a0, zero
-	PTR_LA	a1, nonmt_processor
-	jal	v0
-
-	PTR_LA	v0, 0x9fc00520	/* YAMON exit */
-	lw	v0, (v0)
-	li	a0, 1
-	jal	v0
-
-1 :	b	1b
-
-	__INITDATA
-nonmt_processor :
-	.asciz	"SMTC kernel requires the MT ASE to run\n"
-	__FINIT
-0 :
-#endif
 	.endm
 
 /*
diff --git a/arch/mips/include/asm/mips-boards/piix4.h b/arch/mips/include/asm/mips-boards/piix4.h
index 9cf54041d41..9e340be52a5 100644
--- a/arch/mips/include/asm/mips-boards/piix4.h
+++ b/arch/mips/include/asm/mips-boards/piix4.h
@@ -55,4 +55,16 @@
 #define PIIX4_FUNC3_PMREGMISC			0x80
 #define   PIIX4_FUNC3_PMREGMISC_EN			(1 << 0)
 
+/* Power Management IO Space */
+#define PIIX4_FUNC3IO_PMSTS			0x00
+#define   PIIX4_FUNC3IO_PMSTS_PWRBTN_STS		(1 << 8)
+#define PIIX4_FUNC3IO_PMCNTRL			0x04
+#define   PIIX4_FUNC3IO_PMCNTRL_SUS_EN			(1 << 13)
+#define   PIIX4_FUNC3IO_PMCNTRL_SUS_TYP			(0x7 << 10)
+#define   PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF		(0x0 << 10)
+#define   PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_STR		(0x1 << 10)
+
+/* Data for magic special PCI cycle */
+#define PIIX4_SUSPEND_MAGIC			0x00120002
+
 #endif /* __ASM_MIPS_BOARDS_PIIX4_H */
diff --git a/arch/mips/include/asm/mips-cpc.h b/arch/mips/include/asm/mips-cpc.h
index 988507e46d4..e139a534e0f 100644
--- a/arch/mips/include/asm/mips-cpc.h
+++ b/arch/mips/include/asm/mips-cpc.h
@@ -72,7 +72,12 @@ static inline bool mips_cpc_present(void)
 #define MIPS_CPC_COCB_OFS	0x4000
 
 /* Macros to ease the creation of register access functions */
-#define BUILD_CPC_R_(name, off) \
+#define BUILD_CPC_R_(name, off)					\
+static inline u32 *addr_cpc_##name(void)			\
+{								\
+	return (u32 *)(mips_cpc_base + (off));			\
+}								\
+								\
 static inline u32 read_cpc_##name(void)				\
 {								\
 	return __raw_readl(mips_cpc_base + (off));		\
@@ -147,4 +152,31 @@ BUILD_CPC_Cx_RW(other,		0x10)
 #define CPC_Cx_OTHER_CORENUM_SHF		16
 #define CPC_Cx_OTHER_CORENUM_MSK		(_ULCAST_(0xff) << 16)
 
+#ifdef CONFIG_MIPS_CPC
+
+/**
+ * mips_cpc_lock_other - lock access to another core
+ * core: the other core to be accessed
+ *
+ * Call before operating upon a core via the 'other' register region in
+ * order to prevent the region being moved during access. Must be followed
+ * by a call to mips_cpc_unlock_other.
+ */
+extern void mips_cpc_lock_other(unsigned int core);
+
+/**
+ * mips_cpc_unlock_other - unlock access to another core
+ *
+ * Call after operating upon another core via the 'other' register region.
+ * Must be called after mips_cpc_lock_other.
+ */
+extern void mips_cpc_unlock_other(void);
+
+#else /* !CONFIG_MIPS_CPC */
+
+static inline void mips_cpc_lock_other(unsigned int core) { }
+static inline void mips_cpc_unlock_other(void) { }
+
+#endif /* !CONFIG_MIPS_CPC */
+
 #endif /* __MIPS_ASM_MIPS_CPC_H__ */
diff --git a/arch/mips/include/asm/mips_mt.h b/arch/mips/include/asm/mips_mt.h
index a3df0c3faa0..f6ba004a771 100644
--- a/arch/mips/include/asm/mips_mt.h
+++ b/arch/mips/include/asm/mips_mt.h
@@ -1,7 +1,6 @@
 /*
- * Definitions and decalrations for MIPS MT support
- * that are common between SMTC, VSMP, and/or AP/SP
- * kernel models.
+ * Definitions and decalrations for MIPS MT support that are common between
+ * the VSMP, and AP/SP kernel models.
  */
 #ifndef __ASM_MIPS_MT_H
 #define __ASM_MIPS_MT_H
diff --git a/arch/mips/include/asm/mipsmtregs.h b/arch/mips/include/asm/mipsmtregs.h
index 6efa79a27b6..5f8052ce43b 100644
--- a/arch/mips/include/asm/mipsmtregs.h
+++ b/arch/mips/include/asm/mipsmtregs.h
@@ -36,6 +36,8 @@
 
 #define read_c0_tcbind()		__read_32bit_c0_register($2, 2)
 
+#define write_c0_tchalt(val)		__write_32bit_c0_register($2, 4, val)
+
 #define read_c0_tccontext()		__read_32bit_c0_register($2, 5)
 #define write_c0_tccontext(val)		__write_32bit_c0_register($2, 5, val)
 
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 3e025b5311d..98e9754a4b6 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -709,11 +709,18 @@
 #ifndef __ASSEMBLY__
 
 /*
- * Macros for handling the ISA mode bit for microMIPS.
+ * Macros for handling the ISA mode bit for MIPS16 and microMIPS.
  */
+#if defined(CONFIG_SYS_SUPPORTS_MIPS16) || \
+    defined(CONFIG_SYS_SUPPORTS_MICROMIPS)
 #define get_isa16_mode(x)		((x) & 0x1)
 #define msk_isa16_mode(x)		((x) & ~0x1)
 #define set_isa16_mode(x)		do { (x) |= 0x1; } while(0)
+#else
+#define get_isa16_mode(x)		0
+#define msk_isa16_mode(x)		(x)
+#define set_isa16_mode(x)		do { } while(0)
+#endif
 
 /*
  * microMIPS instructions can be 16-bit or 32-bit in length. This
@@ -1007,19 +1014,8 @@ do {									\
 #define write_c0_compare3(val)	__write_32bit_c0_register($11, 7, val)
 
 #define read_c0_status()	__read_32bit_c0_register($12, 0)
-#ifdef CONFIG_MIPS_MT_SMTC
-#define write_c0_status(val)						\
-do {									\
-	__write_32bit_c0_register($12, 0, val);				\
-	__ehb();							\
-} while (0)
-#else
-/*
- * Legacy non-SMTC code, which may be hazardous
- * but which might not support EHB
- */
+
 #define write_c0_status(val)	__write_32bit_c0_register($12, 0, val)
-#endif /* CONFIG_MIPS_MT_SMTC */
 
 #define read_c0_cause()		__read_32bit_c0_register($13, 0)
 #define write_c0_cause(val)	__write_32bit_c0_register($13, 0, val)
@@ -1743,11 +1739,6 @@ static inline void tlb_write_random(void)
 /*
  * Manipulate bits in a c0 register.
  */
-#ifndef CONFIG_MIPS_MT_SMTC
-/*
- * SMTC Linux requires shutting-down microthread scheduling
- * during CP0 register read-modify-write sequences.
- */
 #define __BUILD_SET_C0(name)					\
 static inline unsigned int					\
 set_c0_##name(unsigned int set)					\
@@ -1786,121 +1777,6 @@ change_c0_##name(unsigned int change, unsigned int val)		\
 	return res;						\
 }
 
-#else /* SMTC versions that manage MT scheduling */
-
-#include <linux/irqflags.h>
-
-/*
- * This is a duplicate of dmt() in mipsmtregs.h to avoid problems with
- * header file recursion.
- */
-static inline unsigned int __dmt(void)
-{
-	int res;
-
-	__asm__ __volatile__(
-	"	.set	push						\n"
-	"	.set	mips32r2					\n"
-	"	.set	noat						\n"
-	"	.word	0x41610BC1			# dmt $1	\n"
-	"	ehb							\n"
-	"	move	%0, $1						\n"
-	"	.set	pop						\n"
-	: "=r" (res));
-
-	instruction_hazard();
-
-	return res;
-}
-
-#define __VPECONTROL_TE_SHIFT	15
-#define __VPECONTROL_TE		(1UL << __VPECONTROL_TE_SHIFT)
-
-#define __EMT_ENABLE		__VPECONTROL_TE
-
-static inline void __emt(unsigned int previous)
-{
-	if ((previous & __EMT_ENABLE))
-		__asm__ __volatile__(
-		"	.set	mips32r2				\n"
-		"	.word	0x41600be1		# emt		\n"
-		"	ehb						\n"
-		"	.set	mips0					\n");
-}
-
-static inline void __ehb(void)
-{
-	__asm__ __volatile__(
-	"	.set	mips32r2					\n"
-	"	ehb							\n"		"	.set	mips0						\n");
-}
-
-/*
- * Note that local_irq_save/restore affect TC-specific IXMT state,
- * not Status.IE as in non-SMTC kernel.
- */
-
-#define __BUILD_SET_C0(name)					\
-static inline unsigned int					\
-set_c0_##name(unsigned int set)					\
-{								\
-	unsigned int res;					\
-	unsigned int new;					\
-	unsigned int omt;					\
-	unsigned long flags;					\
-								\
-	local_irq_save(flags);					\
-	omt = __dmt();						\
-	res = read_c0_##name();					\
-	new = res | set;					\
-	write_c0_##name(new);					\
-	__emt(omt);						\
-	local_irq_restore(flags);				\
-								\
-	return res;						\
-}								\
-								\
-static inline unsigned int					\
-clear_c0_##name(unsigned int clear)				\
-{								\
-	unsigned int res;					\
-	unsigned int new;					\
-	unsigned int omt;					\
-	unsigned long flags;					\
-								\
-	local_irq_save(flags);					\
-	omt = __dmt();						\
-	res = read_c0_##name();					\
-	new = res & ~clear;					\
-	write_c0_##name(new);					\
-	__emt(omt);						\
-	local_irq_restore(flags);				\
-								\
-	return res;						\
-}								\
-								\
-static inline unsigned int					\
-change_c0_##name(unsigned int change, unsigned int newbits)	\
-{								\
-	unsigned int res;					\
-	unsigned int new;					\
-	unsigned int omt;					\
-	unsigned long flags;					\
-								\
-	local_irq_save(flags);					\
-								\
-	omt = __dmt();						\
-	res = read_c0_##name();					\
-	new = res & ~change;					\
-	new |= (newbits & change);				\
-	write_c0_##name(new);					\
-	__emt(omt);						\
-	local_irq_restore(flags);				\
-								\
-	return res;						\
-}
-#endif
-
 __BUILD_SET_C0(status)
 __BUILD_SET_C0(cause)
 __BUILD_SET_C0(config)
@@ -1916,6 +1792,15 @@ __BUILD_SET_C0(brcm_cmt_ctrl)
 __BUILD_SET_C0(brcm_config)
 __BUILD_SET_C0(brcm_mode)
 
+/*
+ * Return low 10 bits of ebase.
+ * Note that under KVM (MIPSVZ) this returns vcpu id.
+ */
+static inline unsigned int get_ebase_cpunum(void)
+{
+	return read_c0_ebase() & 0x3ff;
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_MIPSREGS_H */
diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index e277bbad287..2e373da5f8e 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -18,10 +18,6 @@
 #include <asm/cacheflush.h>
 #include <asm/hazards.h>
 #include <asm/tlbflush.h>
-#ifdef CONFIG_MIPS_MT_SMTC
-#include <asm/mipsmtregs.h>
-#include <asm/smtc.h>
-#endif /* SMTC */
 #include <asm-generic/mm_hooks.h>
 
 #define TLBMISS_HANDLER_SETUP_PGD(pgd)					\
@@ -31,11 +27,15 @@ do {									\
 } while (0)
 
 #ifdef CONFIG_MIPS_PGD_C0_CONTEXT
+
+#define TLBMISS_HANDLER_RESTORE()					\
+	write_c0_xcontext((unsigned long) smp_processor_id() <<		\
+			  SMP_CPUID_REGSHIFT)
+
 #define TLBMISS_HANDLER_SETUP()						\
 	do {								\
 		TLBMISS_HANDLER_SETUP_PGD(swapper_pg_dir);		\
-		write_c0_xcontext((unsigned long) smp_processor_id() <<	\
-						SMP_CPUID_REGSHIFT);	\
+		TLBMISS_HANDLER_RESTORE();				\
 	} while (0)
 
 #else /* !CONFIG_MIPS_PGD_C0_CONTEXT: using  pgd_current*/
@@ -47,9 +47,12 @@ do {									\
  */
 extern unsigned long pgd_current[];
 
-#define TLBMISS_HANDLER_SETUP()						\
+#define TLBMISS_HANDLER_RESTORE()					\
 	write_c0_context((unsigned long) smp_processor_id() <<		\
-						SMP_CPUID_REGSHIFT);	\
+			 SMP_CPUID_REGSHIFT)
+
+#define TLBMISS_HANDLER_SETUP()						\
+	TLBMISS_HANDLER_RESTORE();					\
 	back_to_back_c0_hazard();					\
 	TLBMISS_HANDLER_SETUP_PGD(swapper_pg_dir)
 #endif /* CONFIG_MIPS_PGD_C0_CONTEXT*/
@@ -63,13 +66,6 @@ extern unsigned long pgd_current[];
 #define ASID_INC	0x10
 #define ASID_MASK	0xff0
 
-#elif defined(CONFIG_MIPS_MT_SMTC)
-
-#define ASID_INC	0x1
-extern unsigned long smtc_asid_mask;
-#define ASID_MASK	(smtc_asid_mask)
-#define HW_ASID_MASK	0xff
-/* End SMTC/34K debug hack */
 #else /* FIXME: not correct for R6000 */
 
 #define ASID_INC	0x1
@@ -92,7 +88,6 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 #define ASID_VERSION_MASK  ((unsigned long)~(ASID_MASK|(ASID_MASK-1)))
 #define ASID_FIRST_VERSION ((unsigned long)(~ASID_VERSION_MASK) + 1)
 
-#ifndef CONFIG_MIPS_MT_SMTC
 /* Normal, classic MIPS get_new_mmu_context */
 static inline void
 get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
@@ -115,12 +110,6 @@ get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
 	cpu_context(cpu, mm) = asid_cache(cpu) = asid;
 }
 
-#else /* CONFIG_MIPS_MT_SMTC */
-
-#define get_new_mmu_context(mm, cpu) smtc_get_new_mmu_context((mm), (cpu))
-
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 /*
  * Initialize the context related info for a new mm_struct
  * instance.
@@ -141,46 +130,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	unsigned int cpu = smp_processor_id();
 	unsigned long flags;
-#ifdef CONFIG_MIPS_MT_SMTC
-	unsigned long oldasid;
-	unsigned long mtflags;
-	int mytlb = (smtc_status & SMTC_TLB_SHARED) ? 0 : cpu_data[cpu].vpe_id;
 	local_irq_save(flags);
-	mtflags = dvpe();
-#else /* Not SMTC */
-	local_irq_save(flags);
-#endif /* CONFIG_MIPS_MT_SMTC */
 
 	/* Check if our ASID is of an older version and thus invalid */
 	if ((cpu_context(cpu, next) ^ asid_cache(cpu)) & ASID_VERSION_MASK)
 		get_new_mmu_context(next, cpu);
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * If the EntryHi ASID being replaced happens to be
-	 * the value flagged at ASID recycling time as having
-	 * an extended life, clear the bit showing it being
-	 * in use by this "CPU", and if that's the last bit,
-	 * free up the ASID value for use and flush any old
-	 * instances of it from the TLB.
-	 */
-	oldasid = (read_c0_entryhi() & ASID_MASK);
-	if(smtc_live_asid[mytlb][oldasid]) {
-		smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu);
-		if(smtc_live_asid[mytlb][oldasid] == 0)
-			smtc_flush_tlb_asid(oldasid);
-	}
-	/*
-	 * Tread softly on EntryHi, and so long as we support
-	 * having ASID_MASK smaller than the hardware maximum,
-	 * make sure no "soft" bits become "hard"...
-	 */
-	write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) |
-			 cpu_asid(cpu, next));
-	ehb(); /* Make sure it propagates to TCStatus */
-	evpe(mtflags);
-#else
 	write_c0_entryhi(cpu_asid(cpu, next));
-#endif /* CONFIG_MIPS_MT_SMTC */
 	TLBMISS_HANDLER_SETUP_PGD(next->pgd);
 
 	/*
@@ -213,34 +168,12 @@ activate_mm(struct mm_struct *prev, struct mm_struct *next)
 	unsigned long flags;
 	unsigned int cpu = smp_processor_id();
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	unsigned long oldasid;
-	unsigned long mtflags;
-	int mytlb = (smtc_status & SMTC_TLB_SHARED) ? 0 : cpu_data[cpu].vpe_id;
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 	local_irq_save(flags);
 
 	/* Unconditionally get a new ASID.  */
 	get_new_mmu_context(next, cpu);
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	/* See comments for similar code above */
-	mtflags = dvpe();
-	oldasid = read_c0_entryhi() & ASID_MASK;
-	if(smtc_live_asid[mytlb][oldasid]) {
-		smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu);
-		if(smtc_live_asid[mytlb][oldasid] == 0)
-			 smtc_flush_tlb_asid(oldasid);
-	}
-	/* See comments for similar code above */
-	write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK) |
-			 cpu_asid(cpu, next));
-	ehb(); /* Make sure it propagates to TCStatus */
-	evpe(mtflags);
-#else
 	write_c0_entryhi(cpu_asid(cpu, next));
-#endif /* CONFIG_MIPS_MT_SMTC */
 	TLBMISS_HANDLER_SETUP_PGD(next->pgd);
 
 	/* mark mmu ownership change */
@@ -258,48 +191,15 @@ static inline void
 drop_mmu_context(struct mm_struct *mm, unsigned cpu)
 {
 	unsigned long flags;
-#ifdef CONFIG_MIPS_MT_SMTC
-	unsigned long oldasid;
-	/* Can't use spinlock because called from TLB flush within DVPE */
-	unsigned int prevvpe;
-	int mytlb = (smtc_status & SMTC_TLB_SHARED) ? 0 : cpu_data[cpu].vpe_id;
-#endif /* CONFIG_MIPS_MT_SMTC */
 
 	local_irq_save(flags);
 
 	if (cpumask_test_cpu(cpu, mm_cpumask(mm)))  {
 		get_new_mmu_context(mm, cpu);
-#ifdef CONFIG_MIPS_MT_SMTC
-		/* See comments for similar code above */
-		prevvpe = dvpe();
-		oldasid = (read_c0_entryhi() & ASID_MASK);
-		if (smtc_live_asid[mytlb][oldasid]) {
-			smtc_live_asid[mytlb][oldasid] &= ~(0x1 << cpu);
-			if(smtc_live_asid[mytlb][oldasid] == 0)
-				smtc_flush_tlb_asid(oldasid);
-		}
-		/* See comments for similar code above */
-		write_c0_entryhi((read_c0_entryhi() & ~HW_ASID_MASK)
-				| cpu_asid(cpu, mm));
-		ehb(); /* Make sure it propagates to TCStatus */
-		evpe(prevvpe);
-#else /* not CONFIG_MIPS_MT_SMTC */
 		write_c0_entryhi(cpu_asid(cpu, mm));
-#endif /* CONFIG_MIPS_MT_SMTC */
 	} else {
 		/* will get a new context next time */
-#ifndef CONFIG_MIPS_MT_SMTC
 		cpu_context(cpu, mm) = 0;
-#else /* SMTC */
-		int i;
-
-		/* SMTC shares the TLB (and ASIDs) across VPEs */
-		for_each_online_cpu(i) {
-		    if((smtc_status & SMTC_TLB_SHARED)
-		    || (cpu_data[i].vpe_id == cpu_data[cpu].vpe_id))
-			cpu_context(i, mm) = 0;
-		}
-#endif /* CONFIG_MIPS_MT_SMTC */
 	}
 	local_irq_restore(flags);
 }
diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h
index c2edae382d5..800fe578dc9 100644
--- a/arch/mips/include/asm/module.h
+++ b/arch/mips/include/asm/module.h
@@ -144,13 +144,7 @@ search_module_dbetables(unsigned long addr)
 #define MODULE_KERNEL_TYPE "64BIT "
 #endif
 
-#ifdef CONFIG_MIPS_MT_SMTC
-#define MODULE_KERNEL_SMTC "MT_SMTC "
-#else
-#define MODULE_KERNEL_SMTC ""
-#endif
-
 #define MODULE_ARCH_VERMAGIC \
-	MODULE_PROC_FAMILY MODULE_KERNEL_TYPE MODULE_KERNEL_SMTC
+	MODULE_PROC_FAMILY MODULE_KERNEL_TYPE
 
 #endif /* _ASM_MODULE_H */
diff --git a/arch/mips/include/asm/msa.h b/arch/mips/include/asm/msa.h
index a2aba6c3ec0..538f6d482db 100644
--- a/arch/mips/include/asm/msa.h
+++ b/arch/mips/include/asm/msa.h
@@ -84,7 +84,7 @@ static inline void write_msa_##name(unsigned int val)		\
 	__asm__ __volatile__(					\
 	"	.set	push\n"					\
 	"	.set	msa\n"					\
-	"	cfcmsa	$" #cs ", %0\n"				\
+	"	ctcmsa	$" #cs ", %0\n"				\
 	"	.set	pop\n"					\
 	: : "r"(val));						\
 }
@@ -96,6 +96,13 @@ static inline void write_msa_##name(unsigned int val)		\
  * allow compilation with toolchains that do not support MSA. Once all
  * toolchains in use support MSA these can be removed.
  */
+#ifdef CONFIG_CPU_MICROMIPS
+#define CFC_MSA_INSN	0x587e0056
+#define CTC_MSA_INSN	0x583e0816
+#else
+#define CFC_MSA_INSN	0x787e0059
+#define CTC_MSA_INSN	0x783e0819
+#endif
 
 #define __BUILD_MSA_CTL_REG(name, cs)				\
 static inline unsigned int read_msa_##name(void)		\
@@ -104,7 +111,8 @@ static inline unsigned int read_msa_##name(void)		\
 	__asm__ __volatile__(					\
 	"	.set	push\n"					\
 	"	.set	noat\n"					\
-	"	.word	0x787e0059 | (" #cs " << 11)\n"		\
+	"	.insn\n"					\
+	"	.word	#CFC_MSA_INSN | (" #cs " << 11)\n"	\
 	"	move	%0, $1\n"				\
 	"	.set	pop\n"					\
 	: "=r"(reg));						\
@@ -117,7 +125,8 @@ static inline void write_msa_##name(unsigned int val)		\
 	"	.set	push\n"					\
 	"	.set	noat\n"					\
 	"	move	$1, %0\n"				\
-	"	.word	0x783e0819 | (" #cs " << 6)\n"		\
+	"	.insn\n"					\
+	"	.word	#CTC_MSA_INSN | (" #cs " << 6)\n"	\
 	"	.set	pop\n"					\
 	: : "r"(val));						\
 }
diff --git a/arch/mips/include/asm/netlogic/mips-extns.h b/arch/mips/include/asm/netlogic/mips-extns.h
index de9aada6f4c..06f1f75bfa9 100644
--- a/arch/mips/include/asm/netlogic/mips-extns.h
+++ b/arch/mips/include/asm/netlogic/mips-extns.h
@@ -146,9 +146,10 @@ static inline int hard_smp_processor_id(void)
 
 static inline int nlm_nodeid(void)
 {
-	uint32_t prid = read_c0_prid();
+	uint32_t prid = read_c0_prid() & PRID_IMP_MASK;
 
-	if ((prid & 0xff00) == PRID_IMP_NETLOGIC_XLP9XX)
+	if ((prid == PRID_IMP_NETLOGIC_XLP9XX) ||
+			(prid == PRID_IMP_NETLOGIC_XLP5XX))
 		return (__read_32bit_c0_register($15, 1) >> 7) & 0x7;
 	else
 		return (__read_32bit_c0_register($15, 1) >> 5) & 0x3;
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
index 1f23dfaa716..805bfd21f33 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
@@ -74,6 +74,8 @@
 #define XLP_IO_USB_OHCI2_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 2, 4)
 #define XLP_IO_USB_OHCI3_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 2, 5)
 
+#define XLP_IO_SATA_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 3, 2)
+
 /* XLP2xx has an updated USB block */
 #define XLP2XX_IO_USB_OFFSET(node, i)	XLP_HDR_OFFSET(node, 0, 4, i)
 #define XLP2XX_IO_USB_XHCI0_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 4, 1)
@@ -103,13 +105,11 @@
 #define XLP_IO_SYS_OFFSET(node)		XLP_HDR_OFFSET(node, 0, 6, 5)
 #define XLP_IO_JTAG_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 6, 6)
 
+/* Flash */
 #define XLP_IO_NOR_OFFSET(node)		XLP_HDR_OFFSET(node, 0, 7, 0)
 #define XLP_IO_NAND_OFFSET(node)	XLP_HDR_OFFSET(node, 0, 7, 1)
 #define XLP_IO_SPI_OFFSET(node)		XLP_HDR_OFFSET(node, 0, 7, 2)
-/* SD flash */
-#define XLP_IO_SD_OFFSET(node)		XLP_HDR_OFFSET(node, 0, 7, 3)
-#define XLP_IO_MMC_OFFSET(node, slot)	\
-		((XLP_IO_SD_OFFSET(node))+(slot*0x100)+XLP_IO_PCI_HDRSZ)
+#define XLP_IO_MMC_OFFSET(node)		XLP_HDR_OFFSET(node, 0, 7, 3)
 
 /* Things have changed drastically in XLP 9XX */
 #define XLP9XX_HDR_OFFSET(n, d, f)	\
@@ -120,6 +120,8 @@
 #define XLP9XX_IO_UART_OFFSET(node)	XLP9XX_HDR_OFFSET(node, 2, 2)
 #define XLP9XX_IO_SYS_OFFSET(node)	XLP9XX_HDR_OFFSET(node, 6, 0)
 #define XLP9XX_IO_FUSE_OFFSET(node)	XLP9XX_HDR_OFFSET(node, 6, 1)
+#define XLP9XX_IO_CLOCK_OFFSET(node)	XLP9XX_HDR_OFFSET(node, 6, 2)
+#define XLP9XX_IO_POWER_OFFSET(node)	XLP9XX_HDR_OFFSET(node, 6, 3)
 #define XLP9XX_IO_JTAG_OFFSET(node)	XLP9XX_HDR_OFFSET(node, 6, 4)
 
 #define XLP9XX_IO_PCIE_OFFSET(node, i)	XLP9XX_HDR_OFFSET(node, 1, i)
@@ -135,11 +137,11 @@
 /* XLP9XX on-chip SATA controller */
 #define XLP9XX_IO_SATA_OFFSET(node)		XLP9XX_HDR_OFFSET(node, 3, 2)
 
+/* Flash */
 #define XLP9XX_IO_NOR_OFFSET(node)		XLP9XX_HDR_OFFSET(node, 7, 0)
 #define XLP9XX_IO_NAND_OFFSET(node)		XLP9XX_HDR_OFFSET(node, 7, 1)
 #define XLP9XX_IO_SPI_OFFSET(node)		XLP9XX_HDR_OFFSET(node, 7, 2)
-/* SD flash */
-#define XLP9XX_IO_MMCSD_OFFSET(node)		XLP9XX_HDR_OFFSET(node, 7, 3)
+#define XLP9XX_IO_MMC_OFFSET(node)		XLP9XX_HDR_OFFSET(node, 7, 3)
 
 /* PCI config header register id's */
 #define XLP_PCI_CFGREG0			0x00
@@ -186,8 +188,10 @@
 #define PCI_DEVICE_ID_NLM_NOR		0x1015
 #define PCI_DEVICE_ID_NLM_NAND		0x1016
 #define PCI_DEVICE_ID_NLM_MMC		0x1018
-#define PCI_DEVICE_ID_NLM_XHCI		0x101d
+#define PCI_DEVICE_ID_NLM_SATA		0x101A
+#define PCI_DEVICE_ID_NLM_XHCI		0x101D
 
+#define PCI_DEVICE_ID_XLP9XX_MMC	0x9018
 #define PCI_DEVICE_ID_XLP9XX_SATA	0x901A
 #define PCI_DEVICE_ID_XLP9XX_XHCI	0x901D
 
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h b/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h
index d4deb87ad06..91540f41e1e 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h
@@ -69,6 +69,20 @@
 #define PCIE_9XX_BYTE_SWAP_IO_BASE	0x25e
 #define PCIE_9XX_BYTE_SWAP_IO_LIM	0x25f
 
+#define PCIE_9XX_BRIDGE_MSIX_ADDR_BASE	0x264
+#define PCIE_9XX_BRIDGE_MSIX_ADDR_LIMIT	0x265
+#define PCIE_9XX_MSI_STATUS		0x283
+#define PCIE_9XX_MSI_EN			0x284
+/* 128 MSIX vectors available in 9xx */
+#define PCIE_9XX_MSIX_STATUS0		0x286
+#define PCIE_9XX_MSIX_STATUSX(n)	(n + 0x286)
+#define PCIE_9XX_MSIX_VEC		0x296
+#define PCIE_9XX_MSIX_VECX(n)		(n + 0x296)
+#define PCIE_9XX_INT_STATUS0		0x397
+#define PCIE_9XX_INT_STATUS1		0x398
+#define PCIE_9XX_INT_EN0		0x399
+#define PCIE_9XX_INT_EN1		0x39a
+
 /* other */
 #define PCIE_NLINKS			4
 
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/pic.h b/arch/mips/include/asm/netlogic/xlp-hal/pic.h
index f10bf3bba58..41cefe94f0c 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/pic.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/pic.h
@@ -199,6 +199,10 @@
 #define PIC_IRT_PCIE_LINK_3_INDEX	81
 #define PIC_IRT_PCIE_LINK_INDEX(num)	((num) + PIC_IRT_PCIE_LINK_0_INDEX)
 
+#define PIC_9XX_IRT_PCIE_LINK_0_INDEX	191
+#define PIC_9XX_IRT_PCIE_LINK_INDEX(num) \
+				((num) + PIC_9XX_IRT_PCIE_LINK_0_INDEX)
+
 #define PIC_CLOCK_TIMER			7
 
 #if !defined(LOCORE) && !defined(__ASSEMBLY__)
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/sys.h b/arch/mips/include/asm/netlogic/xlp-hal/sys.h
index d9b107ffca9..bc7bddf25be 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/sys.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/sys.h
@@ -118,6 +118,10 @@
 #define SYS_SCRTCH3				0x4c
 
 /* PLL registers XLP2XX */
+#define SYS_CPU_PLL_CTRL0(core)			(0x1c0 + (core * 4))
+#define SYS_CPU_PLL_CTRL1(core)			(0x1c1 + (core * 4))
+#define SYS_CPU_PLL_CTRL2(core)			(0x1c2 + (core * 4))
+#define SYS_CPU_PLL_CTRL3(core)			(0x1c3 + (core * 4))
 #define SYS_PLL_CTRL0				0x240
 #define SYS_PLL_CTRL1				0x241
 #define SYS_PLL_CTRL2				0x242
@@ -147,6 +151,32 @@
 #define SYS_SYS_PLL_MEM_REQ			0x2a3
 #define SYS_PLL_MEM_STAT			0x2a4
 
+/* PLL registers XLP9XX */
+#define SYS_9XX_CPU_PLL_CTRL0(core)		(0xc0 + (core * 4))
+#define SYS_9XX_CPU_PLL_CTRL1(core)		(0xc1 + (core * 4))
+#define SYS_9XX_CPU_PLL_CTRL2(core)		(0xc2 + (core * 4))
+#define SYS_9XX_CPU_PLL_CTRL3(core)		(0xc3 + (core * 4))
+#define SYS_9XX_DMC_PLL_CTRL0			0x140
+#define SYS_9XX_DMC_PLL_CTRL1			0x141
+#define SYS_9XX_DMC_PLL_CTRL2			0x142
+#define SYS_9XX_DMC_PLL_CTRL3			0x143
+#define SYS_9XX_PLL_CTRL0			0x144
+#define SYS_9XX_PLL_CTRL1			0x145
+#define SYS_9XX_PLL_CTRL2			0x146
+#define SYS_9XX_PLL_CTRL3			0x147
+
+#define SYS_9XX_PLL_CTRL0_DEVX(x)		(0x148 + (x) * 4)
+#define SYS_9XX_PLL_CTRL1_DEVX(x)		(0x149 + (x) * 4)
+#define SYS_9XX_PLL_CTRL2_DEVX(x)		(0x14a + (x) * 4)
+#define SYS_9XX_PLL_CTRL3_DEVX(x)		(0x14b + (x) * 4)
+
+#define SYS_9XX_CPU_PLL_CHG_CTRL		0x188
+#define SYS_9XX_PLL_CHG_CTRL			0x189
+#define SYS_9XX_CLK_DEV_DIS			0x18a
+#define SYS_9XX_CLK_DEV_SEL			0x18b
+#define SYS_9XX_CLK_DEV_DIV			0x18d
+#define SYS_9XX_CLK_DEV_CHG			0x18f
+
 /* Registers changed on 9XX */
 #define SYS_9XX_POWER_ON_RESET_CFG		0x00
 #define SYS_9XX_CHIP_RESET			0x01
@@ -170,6 +200,11 @@
 #define nlm_get_fuse_regbase(node)	\
 			(nlm_get_fuse_pcibase(node) + XLP_IO_PCI_HDRSZ)
 
+#define nlm_get_clock_pcibase(node)	\
+			nlm_pcicfg_base(XLP9XX_IO_CLOCK_OFFSET(node))
+#define nlm_get_clock_regbase(node)	\
+			(nlm_get_clock_pcibase(node) + XLP_IO_PCI_HDRSZ)
+
 unsigned int nlm_get_pic_frequency(int node);
 #endif
 #endif
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
index 2b0c9599ebe..a862b93223c 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
@@ -58,6 +58,10 @@
 #define PIC_I2C_1_IRQ			31
 #define PIC_I2C_2_IRQ			32
 #define PIC_I2C_3_IRQ			33
+#define PIC_SPI_IRQ			34
+#define PIC_NAND_IRQ			37
+#define PIC_SATA_IRQ			38
+#define PIC_GPIO_IRQ			39
 
 #define PIC_PCIE_LINK_MSI_IRQ_BASE	44	/* 44 - 47 MSI IRQ */
 #define PIC_PCIE_LINK_MSI_IRQ(i)	(44 + (i))
@@ -66,8 +70,9 @@
 #define PIC_PCIE_MSIX_IRQ_BASE		48	/* 48 - 51 MSI-X IRQ */
 #define PIC_PCIE_MSIX_IRQ(i)		(48 + (i))
 
-#define NLM_MSIX_VEC_BASE		96	/* 96 - 127 - MSIX mapped */
-#define NLM_MSI_VEC_BASE		128	/* 128 -255 - MSI mapped */
+/* XLP9xx and XLP8xx has 128 and 32 MSIX vectors respectively */
+#define NLM_MSIX_VEC_BASE		96	/* 96 - 223 - MSIX mapped */
+#define NLM_MSI_VEC_BASE		224	/* 224 -351 - MSI mapped */
 
 #define NLM_PIC_INDIRECT_VEC_BASE	512
 #define NLM_GPIO_VEC_BASE		768
@@ -95,17 +100,19 @@ void *xlp_dt_init(void *fdtp);
 
 static inline int cpu_is_xlpii(void)
 {
-	int chip = read_c0_prid() & 0xff00;
+	int chip = read_c0_prid() & PRID_IMP_MASK;
 
 	return chip == PRID_IMP_NETLOGIC_XLP2XX ||
-		chip == PRID_IMP_NETLOGIC_XLP9XX;
+		chip == PRID_IMP_NETLOGIC_XLP9XX ||
+		chip == PRID_IMP_NETLOGIC_XLP5XX;
 }
 
 static inline int cpu_is_xlp9xx(void)
 {
-	int chip = read_c0_prid() & 0xff00;
+	int chip = read_c0_prid() & PRID_IMP_MASK;
 
-	return chip == PRID_IMP_NETLOGIC_XLP9XX;
+	return chip == PRID_IMP_NETLOGIC_XLP9XX ||
+		chip == PRID_IMP_NETLOGIC_XLP5XX;
 }
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_NLM_XLP_H */
diff --git a/arch/mips/include/asm/nile4.h b/arch/mips/include/asm/nile4.h
index 2e2436d0e94..99e97f8bfbc 100644
--- a/arch/mips/include/asm/nile4.h
+++ b/arch/mips/include/asm/nile4.h
@@ -1,7 +1,7 @@
 /*
  *  asm-mips/nile4.h -- NEC Vrc-5074 Nile 4 definitions
  *
- *  Copyright (C) 2000 Geert Uytterhoeven <geert@sonycom.com>
+ *  Copyright (C) 2000 Geert Uytterhoeven <geert@linux-m68k.org>
  *		       Sony Software Development Center Europe (SDCE), Brussels
  *
  *  This file is based on the following documentation:
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index f5d77b91537..d781f9e6688 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -211,7 +211,6 @@ union octeon_cvmemctl {
 
 extern void octeon_write_lcd(const char *s);
 extern void octeon_check_cpu_bist(void);
-extern int octeon_get_boot_debug_flag(void);
 extern int octeon_get_boot_uart(void);
 
 struct uart_port;
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 008324d1c26..539ddd148bb 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -32,6 +32,8 @@ struct vm_area_struct;
 				 _page_cachable_default)
 #define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \
 				 _PAGE_GLOBAL | _page_cachable_default)
+#define PAGE_KERNEL_NC	__pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \
+				 _PAGE_GLOBAL | _CACHE_CACHABLE_NONCOHERENT)
 #define PAGE_USERIO	__pgprot(_PAGE_PRESENT | (cpu_has_rixi ? 0 : _PAGE_READ) | _PAGE_WRITE | \
 				 _page_cachable_default)
 #define PAGE_KERNEL_UNCACHED __pgprot(_PAGE_PRESENT | __READABLE | \
diff --git a/arch/mips/include/asm/pm-cps.h b/arch/mips/include/asm/pm-cps.h
new file mode 100644
index 00000000000..625eda53d57
--- /dev/null
+++ b/arch/mips/include/asm/pm-cps.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright (C) 2014 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __MIPS_ASM_PM_CPS_H__
+#define __MIPS_ASM_PM_CPS_H__
+
+/*
+ * The CM & CPC can only handle coherence & power control on a per-core basis,
+ * thus in an MT system the VPEs within each core are coupled and can only
+ * enter or exit states requiring CM or CPC assistance in unison.
+ */
+#ifdef CONFIG_MIPS_MT
+# define coupled_coherence cpu_has_mipsmt
+#else
+# define coupled_coherence 0
+#endif
+
+/* Enumeration of possible PM states */
+enum cps_pm_state {
+	CPS_PM_NC_WAIT,		/* MIPS wait instruction, non-coherent */
+	CPS_PM_CLOCK_GATED,	/* Core clock gated */
+	CPS_PM_POWER_GATED,	/* Core power gated */
+	CPS_PM_STATE_COUNT,
+};
+
+/**
+ * cps_pm_support_state - determine whether the system supports a PM state
+ * @state: the state to test for support
+ *
+ * Returns true if the system supports the given state, otherwise false.
+ */
+extern bool cps_pm_support_state(enum cps_pm_state state);
+
+/**
+ * cps_pm_enter_state - enter a PM state
+ * @state: the state to enter
+ *
+ * Enter the given PM state. If coupled_coherence is non-zero then it is
+ * expected that this function be called at approximately the same time on
+ * each coupled CPU. Returns 0 on successful entry & exit, otherwise -errno.
+ */
+extern int cps_pm_enter_state(enum cps_pm_state state);
+
+#endif /* __MIPS_ASM_PM_CPS_H__ */
diff --git a/arch/mips/include/asm/pm.h b/arch/mips/include/asm/pm.h
new file mode 100644
index 00000000000..7c03469e043
--- /dev/null
+++ b/arch/mips/include/asm/pm.h
@@ -0,0 +1,159 @@
+/*
+ * Copyright (C) 2014 Imagination Technologies Ltd
+ *
+ * This program is free software; you can redistribute	it and/or modify it
+ * under  the terms of	the GNU General	 Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * PM helper macros for CPU power off (e.g. Suspend-to-RAM).
+ */
+
+#ifndef __ASM_PM_H
+#define __ASM_PM_H
+
+#ifdef __ASSEMBLY__
+
+#include <asm/asm-offsets.h>
+#include <asm/asm.h>
+#include <asm/mipsregs.h>
+#include <asm/regdef.h>
+
+/* Save CPU state to stack for suspend to RAM */
+.macro SUSPEND_SAVE_REGS
+	subu	sp, PT_SIZE
+	/* Call preserved GPRs */
+	LONG_S	$16, PT_R16(sp)
+	LONG_S	$17, PT_R17(sp)
+	LONG_S	$18, PT_R18(sp)
+	LONG_S	$19, PT_R19(sp)
+	LONG_S	$20, PT_R20(sp)
+	LONG_S	$21, PT_R21(sp)
+	LONG_S	$22, PT_R22(sp)
+	LONG_S	$23, PT_R23(sp)
+	LONG_S	$28, PT_R28(sp)
+	LONG_S	$30, PT_R30(sp)
+	LONG_S	$31, PT_R31(sp)
+	/* A couple of CP0 registers with space in pt_regs */
+	mfc0	k0, CP0_STATUS
+	LONG_S	k0, PT_STATUS(sp)
+.endm
+
+/* Restore CPU state from stack after resume from RAM */
+.macro RESUME_RESTORE_REGS_RETURN
+	.set	push
+	.set	noreorder
+	/* A couple of CP0 registers with space in pt_regs */
+	LONG_L	k0, PT_STATUS(sp)
+	mtc0	k0, CP0_STATUS
+	/* Call preserved GPRs */
+	LONG_L	$16, PT_R16(sp)
+	LONG_L	$17, PT_R17(sp)
+	LONG_L	$18, PT_R18(sp)
+	LONG_L	$19, PT_R19(sp)
+	LONG_L	$20, PT_R20(sp)
+	LONG_L	$21, PT_R21(sp)
+	LONG_L	$22, PT_R22(sp)
+	LONG_L	$23, PT_R23(sp)
+	LONG_L	$28, PT_R28(sp)
+	LONG_L	$30, PT_R30(sp)
+	LONG_L	$31, PT_R31(sp)
+	/* Pop and return */
+	jr	ra
+	 addiu	sp, PT_SIZE
+	.set	pop
+.endm
+
+/* Get address of static suspend state into t1 */
+.macro LA_STATIC_SUSPEND
+	la	t1, mips_static_suspend_state
+.endm
+
+/* Save important CPU state for early restoration to global data */
+.macro SUSPEND_SAVE_STATIC
+#ifdef CONFIG_EVA
+	/*
+	 * Segment configuration is saved in global data where it can be easily
+	 * reloaded without depending on the segment configuration.
+	 */
+	mfc0	k0, CP0_PAGEMASK, 2	/* SegCtl0 */
+	LONG_S	k0, SSS_SEGCTL0(t1)
+	mfc0	k0, CP0_PAGEMASK, 3	/* SegCtl1 */
+	LONG_S	k0, SSS_SEGCTL1(t1)
+	mfc0	k0, CP0_PAGEMASK, 4	/* SegCtl2 */
+	LONG_S	k0, SSS_SEGCTL2(t1)
+#endif
+	/* save stack pointer (pointing to GPRs) */
+	LONG_S	sp, SSS_SP(t1)
+.endm
+
+/* Restore important CPU state early from global data */
+.macro RESUME_RESTORE_STATIC
+#ifdef CONFIG_EVA
+	/*
+	 * Segment configuration must be restored prior to any access to
+	 * allocated memory, as it may reside outside of the legacy kernel
+	 * segments.
+	 */
+	LONG_L	k0, SSS_SEGCTL0(t1)
+	mtc0	k0, CP0_PAGEMASK, 2	/* SegCtl0 */
+	LONG_L	k0, SSS_SEGCTL1(t1)
+	mtc0	k0, CP0_PAGEMASK, 3	/* SegCtl1 */
+	LONG_L	k0, SSS_SEGCTL2(t1)
+	mtc0	k0, CP0_PAGEMASK, 4	/* SegCtl2 */
+	tlbw_use_hazard
+#endif
+	/* restore stack pointer (pointing to GPRs) */
+	LONG_L	sp, SSS_SP(t1)
+.endm
+
+/* flush caches to make sure context has reached memory */
+.macro SUSPEND_CACHE_FLUSH
+	.extern	__wback_cache_all
+	.set	push
+	.set	noreorder
+	la	t1, __wback_cache_all
+	LONG_L	t0, 0(t1)
+	jalr	t0
+	 nop
+	.set	pop
+ .endm
+
+/* Save suspend state and flush data caches to RAM */
+.macro SUSPEND_SAVE
+	SUSPEND_SAVE_REGS
+	LA_STATIC_SUSPEND
+	SUSPEND_SAVE_STATIC
+	SUSPEND_CACHE_FLUSH
+.endm
+
+/* Restore saved state after resume from RAM and return */
+.macro RESUME_RESTORE_RETURN
+	LA_STATIC_SUSPEND
+	RESUME_RESTORE_STATIC
+	RESUME_RESTORE_REGS_RETURN
+.endm
+
+#else /* __ASSEMBLY__ */
+
+/**
+ * struct mips_static_suspend_state - Core saved CPU state across S2R.
+ * @segctl:	CP0 Segment control registers.
+ * @sp:		Stack frame where GP register context is saved.
+ *
+ * This structure contains minimal CPU state that must be saved in static kernel
+ * data in order to be able to restore the rest of the state. This includes
+ * segmentation configuration in the case of EVA being enabled, as they must be
+ * restored prior to any kmalloc'd memory being referenced (even the stack
+ * pointer).
+ */
+struct mips_static_suspend_state {
+#ifdef CONFIG_EVA
+	unsigned long segctl[3];
+#endif
+	unsigned long sp;
+};
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_PM_HELPERS_H */
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index ad70cba8daf..d5098bc554f 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -367,6 +367,7 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * Return_address is a replacement for __builtin_return_address(count)
diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h
index bf1ac8d3578..7e6e682aece 100644
--- a/arch/mips/include/asm/ptrace.h
+++ b/arch/mips/include/asm/ptrace.h
@@ -39,9 +39,6 @@ struct pt_regs {
 	unsigned long cp0_badvaddr;
 	unsigned long cp0_cause;
 	unsigned long cp0_epc;
-#ifdef CONFIG_MIPS_MT_SMTC
-	unsigned long cp0_tcstatus;
-#endif /* CONFIG_MIPS_MT_SMTC */
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 	unsigned long long mpl[3];	  /* MTM{0,1,2} */
 	unsigned long long mtp[3];	  /* MTP{0,1,2} */
diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index ca64cbe4449..4520adc8699 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -19,6 +19,9 @@
 #include <asm/mipsmtregs.h>
 #include <asm/uaccess.h> /* for segment_eq() */
 
+extern void (*r4k_blast_dcache)(void);
+extern void (*r4k_blast_icache)(void);
+
 /*
  * This macro return a properly sign-extended address suitable as base address
  * for indexed cache operations.  Two issues here:
@@ -43,11 +46,10 @@
 	: "i" (op), "R" (*(unsigned char *)(addr)))
 
 #ifdef CONFIG_MIPS_MT
+
 /*
- * Temporary hacks for SMTC debug. Optionally force single-threaded
- * execution during I-cache flushes.
+ * Optionally force single-threaded execution during I-cache flushes.
  */
-
 #define PROTECT_CACHE_FLUSHES 1
 
 #ifdef PROTECT_CACHE_FLUSHES
@@ -524,6 +526,8 @@ __BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 32,
 __BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 64, )
 __BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 64, )
 __BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64, )
+__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 128, )
+__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 128, )
 __BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128, )
 
 __BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 16, )
diff --git a/arch/mips/include/asm/sgi/ip22.h b/arch/mips/include/asm/sgi/ip22.h
index 8db1a3588cf..87ec9eaa04e 100644
--- a/arch/mips/include/asm/sgi/ip22.h
+++ b/arch/mips/include/asm/sgi/ip22.h
@@ -69,6 +69,8 @@
 #define SGI_EISA_IRQ	SGINT_LOCAL2 + 3	/* EISA interrupts */
 #define SGI_KEYBD_IRQ	SGINT_LOCAL2 + 4	/* keyboard */
 #define SGI_SERIAL_IRQ	SGINT_LOCAL2 + 5	/* onboard serial */
+#define SGI_GIOEXP0_IRQ	(SGINT_LOCAL2 + 6)	/* Indy GIO EXP0 */
+#define SGI_GIOEXP1_IRQ	(SGINT_LOCAL2 + 7)	/* Indy GIO EXP1 */
 
 #define ip22_is_fullhouse()	(sgioc->sysid & SGIOC_SYSID_FULLHOUSE)
 
diff --git a/arch/mips/include/asm/sigcontext.h b/arch/mips/include/asm/sigcontext.h
index f54bdbe85c0..eeeb0f48c76 100644
--- a/arch/mips/include/asm/sigcontext.h
+++ b/arch/mips/include/asm/sigcontext.h
@@ -32,8 +32,6 @@ struct sigcontext32 {
 	__u32		sc_lo2;
 	__u32		sc_hi3;
 	__u32		sc_lo3;
-	__u64		sc_msaregs[32];	/* Most significant 64 bits */
-	__u32		sc_msa_csr;
 };
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 || _MIPS_SIM == _MIPS_SIM_NABI32 */
 #endif /* _ASM_SIGCONTEXT_H */
diff --git a/arch/mips/include/asm/smp-cps.h b/arch/mips/include/asm/smp-cps.h
index d60d1a2180d..a06a08a9afc 100644
--- a/arch/mips/include/asm/smp-cps.h
+++ b/arch/mips/include/asm/smp-cps.h
@@ -13,17 +13,28 @@
 
 #ifndef __ASSEMBLY__
 
-struct boot_config {
-	unsigned int core;
-	unsigned int vpe;
+struct vpe_boot_config {
 	unsigned long pc;
 	unsigned long sp;
 	unsigned long gp;
 };
 
-extern struct boot_config mips_cps_bootcfg;
+struct core_boot_config {
+	atomic_t vpe_mask;
+	struct vpe_boot_config *vpe_config;
+};
+
+extern struct core_boot_config *mips_cps_core_bootcfg;
 
 extern void mips_cps_core_entry(void);
+extern void mips_cps_core_init(void);
+
+extern struct vpe_boot_config *mips_cps_boot_vpes(void);
+
+extern bool mips_cps_smp_in_use(void);
+
+extern void mips_cps_pm_save(void);
+extern void mips_cps_pm_restore(void);
 
 #else /* __ASSEMBLY__ */
 
diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h
index 73d35b18fb6..6ba1fb8b11e 100644
--- a/arch/mips/include/asm/smp-ops.h
+++ b/arch/mips/include/asm/smp-ops.h
@@ -26,7 +26,6 @@ struct plat_smp_ops {
 	void (*send_ipi_mask)(const struct cpumask *mask, unsigned int action);
 	void (*init_secondary)(void);
 	void (*smp_finish)(void);
-	void (*cpus_done)(void);
 	void (*boot_secondary)(int cpu, struct task_struct *idle);
 	void (*smp_setup)(void);
 	void (*prepare_cpus)(unsigned int max_cpus);
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index efa02acd3dd..b037334fca2 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -46,6 +46,9 @@ extern int __cpu_logical_map[NR_CPUS];
 
 extern volatile cpumask_t cpu_callin_map;
 
+/* Mask of CPUs which are currently definitely operating coherently */
+extern cpumask_t cpu_coherent_mask;
+
 extern void asmlinkage smp_bootstrap(void);
 
 /*
diff --git a/arch/mips/include/asm/smtc.h b/arch/mips/include/asm/smtc.h
deleted file mode 100644
index e56b439b787..00000000000
--- a/arch/mips/include/asm/smtc.h
+++ /dev/null
@@ -1,78 +0,0 @@
-#ifndef _ASM_SMTC_MT_H
-#define _ASM_SMTC_MT_H
-
-/*
- * Definitions for SMTC multitasking on MIPS MT cores
- */
-
-#include <asm/mips_mt.h>
-#include <asm/smtc_ipi.h>
-
-/*
- * System-wide SMTC status information
- */
-
-extern unsigned int smtc_status;
-
-#define SMTC_TLB_SHARED 0x00000001
-#define SMTC_MTC_ACTIVE 0x00000002
-
-/*
- * TLB/ASID Management information
- */
-
-#define MAX_SMTC_TLBS 2
-#define MAX_SMTC_ASIDS 256
-#if NR_CPUS <= 8
-typedef char asiduse;
-#else
-#if NR_CPUS <= 16
-typedef short asiduse;
-#else
-typedef long asiduse;
-#endif
-#endif
-
-/*
- * VPE Management information
- */
-
-#define MAX_SMTC_VPES	MAX_SMTC_TLBS	/* FIXME: May not always be true. */
-
-extern asiduse smtc_live_asid[MAX_SMTC_TLBS][MAX_SMTC_ASIDS];
-
-struct mm_struct;
-struct task_struct;
-
-void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu);
-void self_ipi(struct smtc_ipi *);
-void smtc_flush_tlb_asid(unsigned long asid);
-extern int smtc_build_cpu_map(int startslot);
-extern void smtc_prepare_cpus(int cpus);
-extern void smtc_smp_finish(void);
-extern void smtc_boot_secondary(int cpu, struct task_struct *t);
-extern void smtc_cpus_done(void);
-extern void smtc_init_secondary(void);
-
-
-/*
- * Sharing the TLB between multiple VPEs means that the
- * "random" index selection function is not allowed to
- * select the current value of the Index register. To
- * avoid additional TLB pressure, the Index registers
- * are "parked" with an non-Valid value.
- */
-
-#define PARKED_INDEX	((unsigned int)0x80000000)
-
-/*
- * Define low-level interrupt mask for IPIs, if necessary.
- * By default, use SW interrupt 1, which requires no external
- * hardware support, but which works only for single-core
- * MIPS MT systems.
- */
-#ifndef MIPS_CPU_IPI_IRQ
-#define MIPS_CPU_IPI_IRQ 1
-#endif
-
-#endif /*  _ASM_SMTC_MT_H */
diff --git a/arch/mips/include/asm/smtc_ipi.h b/arch/mips/include/asm/smtc_ipi.h
deleted file mode 100644
index 15278dbd7e7..00000000000
--- a/arch/mips/include/asm/smtc_ipi.h
+++ /dev/null
@@ -1,129 +0,0 @@
-/*
- * Definitions used in MIPS MT SMTC "Interprocessor Interrupt" code.
- */
-#ifndef __ASM_SMTC_IPI_H
-#define __ASM_SMTC_IPI_H
-
-#include <linux/spinlock.h>
-
-//#define SMTC_IPI_DEBUG
-
-#ifdef SMTC_IPI_DEBUG
-#include <asm/mipsregs.h>
-#include <asm/mipsmtregs.h>
-#endif /* SMTC_IPI_DEBUG */
-
-/*
- * An IPI "message"
- */
-
-struct smtc_ipi {
-	struct smtc_ipi *flink;
-	int type;
-	void *arg;
-	int dest;
-#ifdef	SMTC_IPI_DEBUG
-	int sender;
-	long stamp;
-#endif /* SMTC_IPI_DEBUG */
-};
-
-/*
- * Defined IPI Types
- */
-
-#define LINUX_SMP_IPI 1
-#define SMTC_CLOCK_TICK 2
-#define IRQ_AFFINITY_IPI 3
-
-/*
- * A queue of IPI messages
- */
-
-struct smtc_ipi_q {
-	struct smtc_ipi *head;
-	spinlock_t lock;
-	struct smtc_ipi *tail;
-	int depth;
-	int resched_flag;	/* reschedule already queued */
-};
-
-static inline void smtc_ipi_nq(struct smtc_ipi_q *q, struct smtc_ipi *p)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&q->lock, flags);
-	if (q->head == NULL)
-		q->head = q->tail = p;
-	else
-		q->tail->flink = p;
-	p->flink = NULL;
-	q->tail = p;
-	q->depth++;
-#ifdef	SMTC_IPI_DEBUG
-	p->sender = read_c0_tcbind();
-	p->stamp = read_c0_count();
-#endif /* SMTC_IPI_DEBUG */
-	spin_unlock_irqrestore(&q->lock, flags);
-}
-
-static inline struct smtc_ipi *__smtc_ipi_dq(struct smtc_ipi_q *q)
-{
-	struct smtc_ipi *p;
-
-	if (q->head == NULL)
-		p = NULL;
-	else {
-		p = q->head;
-		q->head = q->head->flink;
-		q->depth--;
-		/* Arguably unnecessary, but leaves queue cleaner */
-		if (q->head == NULL)
-			q->tail = NULL;
-	}
-
-	return p;
-}
-
-static inline struct smtc_ipi *smtc_ipi_dq(struct smtc_ipi_q *q)
-{
-	unsigned long flags;
-	struct smtc_ipi *p;
-
-	spin_lock_irqsave(&q->lock, flags);
-	p = __smtc_ipi_dq(q);
-	spin_unlock_irqrestore(&q->lock, flags);
-
-	return p;
-}
-
-static inline void smtc_ipi_req(struct smtc_ipi_q *q, struct smtc_ipi *p)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&q->lock, flags);
-	if (q->head == NULL) {
-		q->head = q->tail = p;
-		p->flink = NULL;
-	} else {
-		p->flink = q->head;
-		q->head = p;
-	}
-	q->depth++;
-	spin_unlock_irqrestore(&q->lock, flags);
-}
-
-static inline int smtc_ipi_qdepth(struct smtc_ipi_q *q)
-{
-	unsigned long flags;
-	int retval;
-
-	spin_lock_irqsave(&q->lock, flags);
-	retval = q->depth;
-	spin_unlock_irqrestore(&q->lock, flags);
-	return retval;
-}
-
-extern void smtc_send_ipi(int cpu, int type, unsigned int action);
-
-#endif /* __ASM_SMTC_IPI_H */
diff --git a/arch/mips/include/asm/smtc_proc.h b/arch/mips/include/asm/smtc_proc.h
deleted file mode 100644
index 25da651f1f5..00000000000
--- a/arch/mips/include/asm/smtc_proc.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * Definitions for SMTC /proc entries
- * Copyright(C) 2005 MIPS Technologies Inc.
- */
-#ifndef __ASM_SMTC_PROC_H
-#define __ASM_SMTC_PROC_H
-
-/*
- * per-"CPU" statistics
- */
-
-struct smtc_cpu_proc {
-	unsigned long timerints;
-	unsigned long selfipis;
-};
-
-extern struct smtc_cpu_proc smtc_cpu_stats[NR_CPUS];
-
-/* Count of number of recoveries of "stolen" FPU access rights on 34K */
-
-extern atomic_t smtc_fpu_recoveries;
-
-#endif /* __ASM_SMTC_PROC_H */
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index d301e108d5b..b188c797565 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -19,22 +19,12 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 
-/*
- * For SMTC kernel, global IE should be left set, and interrupts
- * controlled exclusively via IXMT.
- */
-#ifdef CONFIG_MIPS_MT_SMTC
-#define STATMASK 0x1e
-#elif defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
+#if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
 #define STATMASK 0x3f
 #else
 #define STATMASK 0x1f
 #endif
 
-#ifdef CONFIG_MIPS_MT_SMTC
-#include <asm/mipsmtregs.h>
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 		.macro	SAVE_AT
 		.set	push
 		.set	noat
@@ -186,16 +176,6 @@
 		mfc0	v1, CP0_STATUS
 		LONG_S	$2, PT_R2(sp)
 		LONG_S	v1, PT_STATUS(sp)
-#ifdef CONFIG_MIPS_MT_SMTC
-		/*
-		 * Ideally, these instructions would be shuffled in
-		 * to cover the pipeline delay.
-		 */
-		.set	mips32
-		mfc0	k0, CP0_TCSTATUS
-		.set	mips0
-		LONG_S	k0, PT_TCSTATUS(sp)
-#endif /* CONFIG_MIPS_MT_SMTC */
 		LONG_S	$4, PT_R4(sp)
 		mfc0	v1, CP0_CAUSE
 		LONG_S	$5, PT_R5(sp)
@@ -321,36 +301,6 @@
 		.set	push
 		.set	reorder
 		.set	noat
-#ifdef CONFIG_MIPS_MT_SMTC
-		.set	mips32r2
-		/*
-		 * We need to make sure the read-modify-write
-		 * of Status below isn't perturbed by an interrupt
-		 * or cross-TC access, so we need to do at least a DMT,
-		 * protected by an interrupt-inhibit. But setting IXMT
-		 * also creates a few-cycle window where an IPI could
-		 * be queued and not be detected before potentially
-		 * returning to a WAIT or user-mode loop. It must be
-		 * replayed.
-		 *
-		 * We're in the middle of a context switch, and
-		 * we can't dispatch it directly without trashing
-		 * some registers, so we'll try to detect this unlikely
-		 * case and program a software interrupt in the VPE,
-		 * as would be done for a cross-VPE IPI.  To accommodate
-		 * the handling of that case, we're doing a DVPE instead
-		 * of just a DMT here to protect against other threads.
-		 * This is a lot of cruft to cover a tiny window.
-		 * If you can find a better design, implement it!
-		 *
-		 */
-		mfc0	v0, CP0_TCSTATUS
-		ori	v0, TCSTATUS_IXMT
-		mtc0	v0, CP0_TCSTATUS
-		_ehb
-		DVPE	5				# dvpe a1
-		jal	mips_ihb
-#endif /* CONFIG_MIPS_MT_SMTC */
 		mfc0	a0, CP0_STATUS
 		ori	a0, STATMASK
 		xori	a0, STATMASK
@@ -362,59 +312,6 @@
 		and	v0, v1
 		or	v0, a0
 		mtc0	v0, CP0_STATUS
-#ifdef CONFIG_MIPS_MT_SMTC
-/*
- * Only after EXL/ERL have been restored to status can we
- * restore TCStatus.IXMT.
- */
-		LONG_L	v1, PT_TCSTATUS(sp)
-		_ehb
-		mfc0	a0, CP0_TCSTATUS
-		andi	v1, TCSTATUS_IXMT
-		bnez	v1, 0f
-
-/*
- * We'd like to detect any IPIs queued in the tiny window
- * above and request an software interrupt to service them
- * when we ERET.
- *
- * Computing the offset into the IPIQ array of the executing
- * TC's IPI queue in-line would be tedious.  We use part of
- * the TCContext register to hold 16 bits of offset that we
- * can add in-line to find the queue head.
- */
-		mfc0	v0, CP0_TCCONTEXT
-		la	a2, IPIQ
-		srl	v0, v0, 16
-		addu	a2, a2, v0
-		LONG_L	v0, 0(a2)
-		beqz	v0, 0f
-/*
- * If we have a queue, provoke dispatch within the VPE by setting C_SW1
- */
-		mfc0	v0, CP0_CAUSE
-		ori	v0, v0, C_SW1
-		mtc0	v0, CP0_CAUSE
-0:
-		/*
-		 * This test should really never branch but
-		 * let's be prudent here.  Having atomized
-		 * the shared register modifications, we can
-		 * now EVPE, and must do so before interrupts
-		 * are potentially re-enabled.
-		 */
-		andi	a1, a1, MVPCONTROL_EVP
-		beqz	a1, 1f
-		evpe
-1:
-		/* We know that TCStatua.IXMT should be set from above */
-		xori	a0, a0, TCSTATUS_IXMT
-		or	a0, a0, v1
-		mtc0	a0, CP0_TCSTATUS
-		_ehb
-
-		.set	mips0
-#endif /* CONFIG_MIPS_MT_SMTC */
 		LONG_L	v1, PT_EPC(sp)
 		MTC0	v1, CP0_EPC
 		LONG_L	$31, PT_R31(sp)
@@ -467,33 +364,11 @@
  * Set cp0 enable bit as sign that we're running on the kernel stack
  */
 		.macro	CLI
-#if !defined(CONFIG_MIPS_MT_SMTC)
 		mfc0	t0, CP0_STATUS
 		li	t1, ST0_CU0 | STATMASK
 		or	t0, t1
 		xori	t0, STATMASK
 		mtc0	t0, CP0_STATUS
-#else /* CONFIG_MIPS_MT_SMTC */
-		/*
-		 * For SMTC, we need to set privilege
-		 * and disable interrupts only for the
-		 * current TC, using the TCStatus register.
-		 */
-		mfc0	t0, CP0_TCSTATUS
-		/* Fortunately CU 0 is in the same place in both registers */
-		/* Set TCU0, TMX, TKSU (for later inversion) and IXMT */
-		li	t1, ST0_CU0 | 0x08001c00
-		or	t0, t1
-		/* Clear TKSU, leave IXMT */
-		xori	t0, 0x00001800
-		mtc0	t0, CP0_TCSTATUS
-		_ehb
-		/* We need to leave the global IE bit set, but clear EXL...*/
-		mfc0	t0, CP0_STATUS
-		ori	t0, ST0_EXL | ST0_ERL
-		xori	t0, ST0_EXL | ST0_ERL
-		mtc0	t0, CP0_STATUS
-#endif /* CONFIG_MIPS_MT_SMTC */
 		irq_disable_hazard
 		.endm
 
@@ -502,35 +377,11 @@
  * Set cp0 enable bit as sign that we're running on the kernel stack
  */
 		.macro	STI
-#if !defined(CONFIG_MIPS_MT_SMTC)
 		mfc0	t0, CP0_STATUS
 		li	t1, ST0_CU0 | STATMASK
 		or	t0, t1
 		xori	t0, STATMASK & ~1
 		mtc0	t0, CP0_STATUS
-#else /* CONFIG_MIPS_MT_SMTC */
-		/*
-		 * For SMTC, we need to set privilege
-		 * and enable interrupts only for the
-		 * current TC, using the TCStatus register.
-		 */
-		_ehb
-		mfc0	t0, CP0_TCSTATUS
-		/* Fortunately CU 0 is in the same place in both registers */
-		/* Set TCU0, TKSU (for later inversion) and IXMT */
-		li	t1, ST0_CU0 | 0x08001c00
-		or	t0, t1
-		/* Clear TKSU *and* IXMT */
-		xori	t0, 0x00001c00
-		mtc0	t0, CP0_TCSTATUS
-		_ehb
-		/* We need to leave the global IE bit set, but clear EXL...*/
-		mfc0	t0, CP0_STATUS
-		ori	t0, ST0_EXL
-		xori	t0, ST0_EXL
-		mtc0	t0, CP0_STATUS
-		/* irq_enable_hazard below should expand to EHB for 24K/34K cpus */
-#endif /* CONFIG_MIPS_MT_SMTC */
 		irq_enable_hazard
 		.endm
 
@@ -540,32 +391,6 @@
  * Set cp0 enable bit as sign that we're running on the kernel stack
  */
 		.macro	KMODE
-#ifdef CONFIG_MIPS_MT_SMTC
-		/*
-		 * This gets baroque in SMTC.  We want to
-		 * protect the non-atomic clearing of EXL
-		 * with DMT/EMT, but we don't want to take
-		 * an interrupt while DMT is still in effect.
-		 */
-
-		/* KMODE gets invoked from both reorder and noreorder code */
-		.set	push
-		.set	mips32r2
-		.set	noreorder
-		mfc0	v0, CP0_TCSTATUS
-		andi	v1, v0, TCSTATUS_IXMT
-		ori	v0, TCSTATUS_IXMT
-		mtc0	v0, CP0_TCSTATUS
-		_ehb
-		DMT	2				# dmt	v0
-		/*
-		 * We don't know a priori if ra is "live"
-		 */
-		move	t0, ra
-		jal	mips_ihb
-		nop	/* delay slot */
-		move	ra, t0
-#endif /* CONFIG_MIPS_MT_SMTC */
 		mfc0	t0, CP0_STATUS
 		li	t1, ST0_CU0 | (STATMASK & ~1)
 #if defined(CONFIG_CPU_R3000) || defined(CONFIG_CPU_TX39XX)
@@ -576,25 +401,6 @@
 		or	t0, t1
 		xori	t0, STATMASK & ~1
 		mtc0	t0, CP0_STATUS
-#ifdef CONFIG_MIPS_MT_SMTC
-		_ehb
-		andi	v0, v0, VPECONTROL_TE
-		beqz	v0, 2f
-		nop	/* delay slot */
-		emt
-2:
-		mfc0	v0, CP0_TCSTATUS
-		/* Clear IXMT, then OR in previous value */
-		ori	v0, TCSTATUS_IXMT
-		xori	v0, TCSTATUS_IXMT
-		or	v0, v1, v0
-		mtc0	v0, CP0_TCSTATUS
-		/*
-		 * irq_disable_hazard below should expand to EHB
-		 * on 24K/34K CPUS
-		 */
-		.set pop
-#endif /* CONFIG_MIPS_MT_SMTC */
 		irq_disable_hazard
 		.endm
 
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index d2d961d6cb8..7de865805de 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -159,11 +159,7 @@ static inline struct thread_info *current_thread_info(void)
  * We stash processor id into a COP0 register to retrieve it fast
  * at kernel exception entry.
  */
-#if defined(CONFIG_MIPS_MT_SMTC)
-#define SMP_CPUID_REG		2, 2	/* TCBIND */
-#define ASM_SMP_CPUID_REG	$2, 2
-#define SMP_CPUID_PTRSHIFT	19
-#elif defined(CONFIG_MIPS_PGD_C0_CONTEXT)
+#if   defined(CONFIG_MIPS_PGD_C0_CONTEXT)
 #define SMP_CPUID_REG		20, 0	/* XCONTEXT */
 #define ASM_SMP_CPUID_REG	$20
 #define SMP_CPUID_PTRSHIFT	48
@@ -179,13 +175,8 @@ static inline struct thread_info *current_thread_info(void)
 #define SMP_CPUID_REGSHIFT	(SMP_CPUID_PTRSHIFT + 2)
 #endif
 
-#ifdef CONFIG_MIPS_MT_SMTC
-#define ASM_CPUID_MFC0		mfc0
-#define UASM_i_CPUID_MFC0	uasm_i_mfc0
-#else
 #define ASM_CPUID_MFC0		MFC0
 #define UASM_i_CPUID_MFC0	UASM_i_MFC0
-#endif
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/mips/include/asm/time.h b/arch/mips/include/asm/time.h
index 24f534a7fbc..8f3047d611e 100644
--- a/arch/mips/include/asm/time.h
+++ b/arch/mips/include/asm/time.h
@@ -52,14 +52,11 @@ extern int (*perf_irq)(void);
  */
 extern unsigned int __weak get_c0_compare_int(void);
 extern int r4k_clockevent_init(void);
-extern int smtc_clockevent_init(void);
 extern int gic_clockevent_init(void);
 
 static inline int mips_clockevent_init(void)
 {
-#ifdef CONFIG_MIPS_MT_SMTC
-	return smtc_clockevent_init();
-#elif defined(CONFIG_CEVT_GIC)
+#if   defined(CONFIG_CEVT_GIC)
 	return (gic_clockevent_init() | r4k_clockevent_init());
 #elif defined(CONFIG_CEVT_R4K)
 	return r4k_clockevent_init();
diff --git a/arch/mips/include/asm/timex.h b/arch/mips/include/asm/timex.h
index c5424757da6..b05bb70a2e4 100644
--- a/arch/mips/include/asm/timex.h
+++ b/arch/mips/include/asm/timex.h
@@ -4,12 +4,16 @@
  * for more details.
  *
  * Copyright (C) 1998, 1999, 2003 by Ralf Baechle
+ * Copyright (C) 2014 by Maciej W. Rozycki
  */
 #ifndef _ASM_TIMEX_H
 #define _ASM_TIMEX_H
 
 #ifdef __KERNEL__
 
+#include <linux/compiler.h>
+
+#include <asm/cpu.h>
 #include <asm/cpu-features.h>
 #include <asm/mipsregs.h>
 #include <asm/cpu-type.h>
@@ -45,29 +49,54 @@ typedef unsigned int cycles_t;
  * However for now the implementaton of this function doesn't get these
  * fine details right.
  */
-static inline cycles_t get_cycles(void)
+static inline int can_use_mips_counter(unsigned int prid)
 {
-	switch (boot_cpu_type()) {
-	case CPU_R4400PC:
-	case CPU_R4400SC:
-	case CPU_R4400MC:
-		if ((read_c0_prid() & 0xff) >= 0x0050)
-			return read_c0_count();
-		break;
+	int comp = (prid & PRID_COMP_MASK) != PRID_COMP_LEGACY;
 
-        case CPU_R4000PC:
-        case CPU_R4000SC:
-        case CPU_R4000MC:
-		break;
+	if (__builtin_constant_p(cpu_has_counter) && !cpu_has_counter)
+		return 0;
+	else if (__builtin_constant_p(cpu_has_mips_r) && cpu_has_mips_r)
+		return 1;
+	else if (likely(!__builtin_constant_p(cpu_has_mips_r) && comp))
+		return 1;
+	/* Make sure we don't peek at cpu_data[0].options in the fast path! */
+	if (!__builtin_constant_p(cpu_has_counter))
+		asm volatile("" : "=m" (cpu_data[0].options));
+	if (likely(cpu_has_counter &&
+		   prid >= (PRID_IMP_R4000 | PRID_REV_ENCODE_44(5, 0))))
+		return 1;
+	else
+		return 0;
+}
 
-	default:
-		if (cpu_has_counter)
-			return read_c0_count();
-		break;
-	}
+static inline cycles_t get_cycles(void)
+{
+	if (can_use_mips_counter(read_c0_prid()))
+		return read_c0_count();
+	else
+		return 0;	/* no usable counter */
+}
+
+/*
+ * Like get_cycles - but where c0_count is not available we desperately
+ * use c0_random in an attempt to get at least a little bit of entropy.
+ *
+ * R6000 and R6000A neither have a count register nor a random register.
+ * That leaves no entropy source in the CPU itself.
+ */
+static inline unsigned long random_get_entropy(void)
+{
+	unsigned int prid = read_c0_prid();
+	unsigned int imp = prid & PRID_IMP_MASK;
 
-	return 0;	/* no usable counter */
+	if (can_use_mips_counter(prid))
+		return read_c0_count();
+	else if (likely(imp != PRID_IMP_R6000 && imp != PRID_IMP_R6000A))
+		return read_c0_random();
+	else
+		return 0;	/* no usable register */
 }
+#define random_get_entropy random_get_entropy
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/mips/include/asm/uasm.h b/arch/mips/include/asm/uasm.h
index c33a9564fb4..708c5d41490 100644
--- a/arch/mips/include/asm/uasm.h
+++ b/arch/mips/include/asm/uasm.h
@@ -55,6 +55,9 @@ void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c)
 #define Ip_u2u1u3(op)							\
 void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c)
 
+#define Ip_u3u2u1(op)							\
+void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c)
+
 #define Ip_u3u1u2(op)							\
 void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c)
 
@@ -64,6 +67,9 @@ void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, signed int c)
 #define Ip_u2s3u1(op)							\
 void ISAOPC(op)(u32 **buf, unsigned int a, signed int b, unsigned int c)
 
+#define Ip_s3s1s2(op)							\
+void ISAOPC(op)(u32 **buf, int a, int b, int c)
+
 #define Ip_u2u1s3(op)							\
 void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, signed int c)
 
@@ -74,6 +80,9 @@ void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b, unsigned int c, \
 #define Ip_u1u2(op)							\
 void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b)
 
+#define Ip_u2u1(op)							\
+void ISAOPC(op)(u32 **buf, unsigned int a, unsigned int b)
+
 #define Ip_u1s2(op)							\
 void ISAOPC(op)(u32 **buf, unsigned int a, signed int b)
 
@@ -99,6 +108,7 @@ Ip_u2u1s3(_daddiu);
 Ip_u3u1u2(_daddu);
 Ip_u2u1msbu3(_dins);
 Ip_u2u1msbu3(_dinsm);
+Ip_u1u2(_divu);
 Ip_u1u2u3(_dmfc0);
 Ip_u1u2u3(_dmtc0);
 Ip_u2u1u3(_drotr);
@@ -114,16 +124,22 @@ Ip_u2u1msbu3(_ext);
 Ip_u2u1msbu3(_ins);
 Ip_u1(_j);
 Ip_u1(_jal);
+Ip_u2u1(_jalr);
 Ip_u1(_jr);
+Ip_u2s3u1(_lb);
 Ip_u2s3u1(_ld);
 Ip_u3u1u2(_ldx);
+Ip_u2s3u1(_lh);
 Ip_u2s3u1(_ll);
 Ip_u2s3u1(_lld);
 Ip_u1s2(_lui);
 Ip_u2s3u1(_lw);
 Ip_u3u1u2(_lwx);
 Ip_u1u2u3(_mfc0);
+Ip_u1(_mfhi);
+Ip_u1(_mflo);
 Ip_u1u2u3(_mtc0);
+Ip_u3u1u2(_mul);
 Ip_u3u1u2(_or);
 Ip_u2u1u3(_ori);
 Ip_u2s3u1(_pref);
@@ -133,17 +149,26 @@ Ip_u2s3u1(_sc);
 Ip_u2s3u1(_scd);
 Ip_u2s3u1(_sd);
 Ip_u2u1u3(_sll);
+Ip_u3u2u1(_sllv);
+Ip_s3s1s2(_slt);
+Ip_u2u1s3(_sltiu);
+Ip_u3u1u2(_sltu);
 Ip_u2u1u3(_sra);
 Ip_u2u1u3(_srl);
+Ip_u3u2u1(_srlv);
 Ip_u3u1u2(_subu);
 Ip_u2s3u1(_sw);
+Ip_u1(_sync);
 Ip_u1(_syscall);
 Ip_0(_tlbp);
 Ip_0(_tlbr);
 Ip_0(_tlbwi);
 Ip_0(_tlbwr);
+Ip_u1(_wait);
+Ip_u2u1(_wsbh);
 Ip_u3u1u2(_xor);
 Ip_u2u1u3(_xori);
+Ip_u2u1(_yield);
 
 
 /* Handle labels. */
@@ -264,6 +289,8 @@ void uasm_il_bbit0(u32 **p, struct uasm_reloc **r, unsigned int reg,
 		   unsigned int bit, int lid);
 void uasm_il_bbit1(u32 **p, struct uasm_reloc **r, unsigned int reg,
 		   unsigned int bit, int lid);
+void uasm_il_beq(u32 **p, struct uasm_reloc **r, unsigned int r1,
+		 unsigned int r2, int lid);
 void uasm_il_beqz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
 void uasm_il_beqzl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
 void uasm_il_bgezl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
diff --git a/arch/mips/include/uapi/asm/Kbuild b/arch/mips/include/uapi/asm/Kbuild
index be7196eacb8..96fe7395ed8 100644
--- a/arch/mips/include/uapi/asm/Kbuild
+++ b/arch/mips/include/uapi/asm/Kbuild
@@ -4,6 +4,7 @@ include include/uapi/asm-generic/Kbuild.asm
 generic-y += auxvec.h
 generic-y += ipcbuf.h
 
+header-y += bitfield.h
 header-y += bitsperlong.h
 header-y += break.h
 header-y += byteorder.h
diff --git a/arch/mips/include/uapi/asm/bitfield.h b/arch/mips/include/uapi/asm/bitfield.h
new file mode 100644
index 00000000000..ad9861359ce
--- /dev/null
+++ b/arch/mips/include/uapi/asm/bitfield.h
@@ -0,0 +1,29 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2014 by Ralf Baechle <ralf@linux-mips.org>
+ */
+#ifndef __UAPI_ASM_BITFIELD_H
+#define __UAPI_ASM_BITFIELD_H
+
+/*
+ *  * Damn ...  bitfields depend from byteorder :-(
+ *   */
+#ifdef __MIPSEB__
+#define __BITFIELD_FIELD(field, more)					\
+	field;								\
+	more
+
+#elif defined(__MIPSEL__)
+
+#define __BITFIELD_FIELD(field, more)					\
+	more								\
+	field;
+
+#else /* !defined (__MIPSEB__) && !defined (__MIPSEL__) */
+#error "MIPS but neither __MIPSEL__ nor __MIPSEB__?"
+#endif
+
+#endif /* __UAPI_ASM_BITFIELD_H */
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index 3125797f2a8..4bfdb9d4c18 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -13,6 +13,8 @@
 #ifndef _UAPI_ASM_INST_H
 #define _UAPI_ASM_INST_H
 
+#include <asm/bitfield.h>
+
 /*
  * Major opcodes; before MIPS IV cop1x was called cop3.
  */
@@ -74,16 +76,17 @@ enum spec2_op {
 enum spec3_op {
 	ext_op, dextm_op, dextu_op, dext_op,
 	ins_op, dinsm_op, dinsu_op, dins_op,
-	lx_op     = 0x0a, lwle_op   = 0x19,
-	lwre_op   = 0x1a, cachee_op = 0x1b,
-	sbe_op    = 0x1c, she_op    = 0x1d,
-	sce_op    = 0x1e, swe_op    = 0x1f,
-	bshfl_op  = 0x20, swle_op   = 0x21,
-	swre_op   = 0x22, prefe_op  = 0x23,
-	dbshfl_op = 0x24, lbue_op   = 0x28,
-	lhue_op   = 0x29, lbe_op    = 0x2c,
-	lhe_op    = 0x2d, lle_op    = 0x2e,
-	lwe_op    = 0x2f, rdhwr_op  = 0x3b
+	yield_op  = 0x09, lx_op     = 0x0a,
+	lwle_op   = 0x19, lwre_op   = 0x1a,
+	cachee_op = 0x1b, sbe_op    = 0x1c,
+	she_op    = 0x1d, sce_op    = 0x1e,
+	swe_op    = 0x1f, bshfl_op  = 0x20,
+	swle_op   = 0x21, swre_op   = 0x22,
+	prefe_op  = 0x23, dbshfl_op = 0x24,
+	lbue_op   = 0x28, lhue_op   = 0x29,
+	lbe_op    = 0x2c, lhe_op    = 0x2d,
+	lle_op    = 0x2e, lwe_op    = 0x2f,
+	rdhwr_op  = 0x3b
 };
 
 /*
@@ -125,7 +128,8 @@ enum bcop_op {
 enum cop0_coi_func {
 	tlbr_op	      = 0x01, tlbwi_op	    = 0x02,
 	tlbwr_op      = 0x06, tlbp_op	    = 0x08,
-	rfe_op	      = 0x10, eret_op	    = 0x18
+	rfe_op	      = 0x10, eret_op	    = 0x18,
+	wait_op       = 0x20,
 };
 
 /*
@@ -202,6 +206,16 @@ enum lx_func {
 };
 
 /*
+ * BSHFL opcodes
+ */
+enum bshfl_func {
+	wsbh_op = 0x2,
+	dshd_op = 0x5,
+	seb_op  = 0x10,
+	seh_op  = 0x18,
+};
+
+/*
  * (microMIPS) Major opcodes.
  */
 enum mm_major_op {
@@ -244,17 +258,23 @@ enum mm_32i_minor_op {
 enum mm_32a_minor_op {
 	mm_sll32_op = 0x000,
 	mm_ins_op = 0x00c,
+	mm_sllv32_op = 0x010,
 	mm_ext_op = 0x02c,
 	mm_pool32axf_op = 0x03c,
 	mm_srl32_op = 0x040,
 	mm_sra_op = 0x080,
+	mm_srlv32_op = 0x090,
 	mm_rotr_op = 0x0c0,
 	mm_lwxs_op = 0x118,
 	mm_addu32_op = 0x150,
 	mm_subu32_op = 0x1d0,
+	mm_wsbh_op = 0x1ec,
+	mm_mul_op = 0x210,
 	mm_and_op = 0x250,
 	mm_or32_op = 0x290,
 	mm_xor32_op = 0x310,
+	mm_slt_op = 0x350,
+	mm_sltu_op = 0x390,
 };
 
 /*
@@ -294,15 +314,20 @@ enum mm_32axf_minor_op {
 	mm_mfc0_op = 0x003,
 	mm_mtc0_op = 0x00b,
 	mm_tlbp_op = 0x00d,
+	mm_mfhi32_op = 0x035,
 	mm_jalr_op = 0x03c,
 	mm_tlbr_op = 0x04d,
+	mm_mflo32_op = 0x075,
 	mm_jalrhb_op = 0x07c,
 	mm_tlbwi_op = 0x08d,
 	mm_tlbwr_op = 0x0cd,
 	mm_jalrs_op = 0x13c,
 	mm_jalrshb_op = 0x17c,
+	mm_sync_op = 0x1ad,
 	mm_syscall_op = 0x22d,
+	mm_wait_op = 0x24d,
 	mm_eret_op = 0x3cd,
+	mm_divu_op = 0x5dc,
 };
 
 /*
@@ -480,24 +505,6 @@ enum MIPS6e_i8_func {
  */
 #define MM_NOP16	0x0c00
 
-/*
- * Damn ...  bitfields depend from byteorder :-(
- */
-#ifdef __MIPSEB__
-#define __BITFIELD_FIELD(field, more)					\
-	field;								\
-	more
-
-#elif defined(__MIPSEL__)
-
-#define __BITFIELD_FIELD(field, more)					\
-	more								\
-	field;
-
-#else /* !defined (__MIPSEB__) && !defined (__MIPSEL__) */
-#error "MIPS but neither __MIPSEL__ nor __MIPSEB__?"
-#endif
-
 struct j_format {
 	__BITFIELD_FIELD(unsigned int opcode : 6, /* Jump format */
 	__BITFIELD_FIELD(unsigned int target : 26,
diff --git a/arch/mips/include/uapi/asm/kvm_para.h b/arch/mips/include/uapi/asm/kvm_para.h
index 14fab8f0b95..7e16d7c42e6 100644
--- a/arch/mips/include/uapi/asm/kvm_para.h
+++ b/arch/mips/include/uapi/asm/kvm_para.h
@@ -1 +1,5 @@
-#include <asm-generic/kvm_para.h>
+#ifndef _UAPI_ASM_MIPS_KVM_PARA_H
+#define _UAPI_ASM_MIPS_KVM_PARA_H
+
+
+#endif /* _UAPI_ASM_MIPS_KVM_PARA_H */
diff --git a/arch/mips/include/uapi/asm/sigcontext.h b/arch/mips/include/uapi/asm/sigcontext.h
index 681c17603a4..6c9906f59c6 100644
--- a/arch/mips/include/uapi/asm/sigcontext.h
+++ b/arch/mips/include/uapi/asm/sigcontext.h
@@ -12,10 +12,6 @@
 #include <linux/types.h>
 #include <asm/sgidefs.h>
 
-/* Bits which may be set in sc_used_math */
-#define USEDMATH_FP	(1 << 0)
-#define USEDMATH_MSA	(1 << 1)
-
 #if _MIPS_SIM == _MIPS_SIM_ABI32
 
 /*
@@ -41,8 +37,6 @@ struct sigcontext {
 	unsigned long		sc_lo2;
 	unsigned long		sc_hi3;
 	unsigned long		sc_lo3;
-	unsigned long long	sc_msaregs[32];	/* Most significant 64 bits */
-	unsigned long		sc_msa_csr;
 };
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
@@ -76,8 +70,6 @@ struct sigcontext {
 	__u32	sc_used_math;
 	__u32	sc_dsp;
 	__u32	sc_reserved;
-	__u64	sc_msaregs[32];
-	__u32	sc_msa_csr;
 };
 
 
diff --git a/arch/mips/include/uapi/asm/types.h b/arch/mips/include/uapi/asm/types.h
index 7ac9d0baad8..f3dd9ff0cc0 100644
--- a/arch/mips/include/uapi/asm/types.h
+++ b/arch/mips/include/uapi/asm/types.h
@@ -14,9 +14,12 @@
 /*
  * We don't use int-l64.h for the kernel anymore but still use it for
  * userspace to avoid code changes.
+ *
+ * However, some user programs (e.g. perf) may not want this. They can
+ * flag __SANE_USERSPACE_TYPES__ to get int-ll64.h here.
  */
 #ifndef __KERNEL__
-# if _MIPS_SZLONG == 64
+# if _MIPS_SZLONG == 64 && !defined(__SANE_USERSPACE_TYPES__)
 #  include <asm-generic/int-l64.h>
 # else
 #  include <asm-generic/int-ll64.h>
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 277dab301ce..008a2fed058 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -17,7 +17,6 @@ endif
 
 obj-$(CONFIG_CEVT_BCM1480)	+= cevt-bcm1480.o
 obj-$(CONFIG_CEVT_R4K)		+= cevt-r4k.o
-obj-$(CONFIG_MIPS_MT_SMTC)	+= cevt-smtc.o
 obj-$(CONFIG_CEVT_DS1287)	+= cevt-ds1287.o
 obj-$(CONFIG_CEVT_GIC)		+= cevt-gic.o
 obj-$(CONFIG_CEVT_GT641XX)	+= cevt-gt641xx.o
@@ -42,7 +41,7 @@ obj-$(CONFIG_CPU_R4K_FPU)	+= r4k_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_R3000)		+= r2300_fpu.o r2300_switch.o
 obj-$(CONFIG_CPU_R6000)		+= r6000_fpu.o r4k_switch.o
 obj-$(CONFIG_CPU_TX39XX)	+= r2300_fpu.o r2300_switch.o
-obj-$(CONFIG_CPU_CAVIUM_OCTEON) += octeon_switch.o
+obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= r4k_fpu.o octeon_switch.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP_UP)		+= smp-up.o
@@ -50,7 +49,6 @@ obj-$(CONFIG_CPU_BMIPS)		+= smp-bmips.o bmips_vec.o
 
 obj-$(CONFIG_MIPS_MT)		+= mips-mt.o
 obj-$(CONFIG_MIPS_MT_FPAFF)	+= mips-mt-fpaff.o
-obj-$(CONFIG_MIPS_MT_SMTC)	+= smtc.o smtc-asm.o smtc-proc.o
 obj-$(CONFIG_MIPS_MT_SMP)	+= smp-mt.o
 obj-$(CONFIG_MIPS_CMP)		+= smp-cmp.o
 obj-$(CONFIG_MIPS_CPS)		+= smp-cps.o cps-vec.o
@@ -107,6 +105,9 @@ obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 obj-$(CONFIG_MIPS_CM)		+= mips-cm.o
 obj-$(CONFIG_MIPS_CPC)		+= mips-cpc.o
 
+obj-$(CONFIG_CPU_PM)		+= pm.o
+obj-$(CONFIG_MIPS_CPS_PM)	+= pm-cps.o
+
 #
 # DSP ASE supported for MIPS32 or MIPS64 Release 2 cores only. It is not
 # safe to unconditionnaly use the assembler -mdsp / -mdspr2 switches
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index 0ea75c244b4..4bb5107511e 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -14,6 +14,7 @@
 #include <linux/mm.h>
 #include <linux/kbuild.h>
 #include <linux/suspend.h>
+#include <asm/pm.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/smp-cps.h>
@@ -64,9 +65,6 @@ void output_ptreg_defines(void)
 	OFFSET(PT_BVADDR, pt_regs, cp0_badvaddr);
 	OFFSET(PT_STATUS, pt_regs, cp0_status);
 	OFFSET(PT_CAUSE, pt_regs, cp0_cause);
-#ifdef CONFIG_MIPS_MT_SMTC
-	OFFSET(PT_TCSTATUS, pt_regs, cp0_tcstatus);
-#endif /* CONFIG_MIPS_MT_SMTC */
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 	OFFSET(PT_MPL, pt_regs, mpl);
 	OFFSET(PT_MTP, pt_regs, mtp);
@@ -295,7 +293,6 @@ void output_sc_defines(void)
 	OFFSET(SC_LO2, sigcontext, sc_lo2);
 	OFFSET(SC_HI3, sigcontext, sc_hi3);
 	OFFSET(SC_LO3, sigcontext, sc_lo3);
-	OFFSET(SC_MSAREGS, sigcontext, sc_msaregs);
 	BLANK();
 }
 #endif
@@ -310,7 +307,6 @@ void output_sc_defines(void)
 	OFFSET(SC_MDLO, sigcontext, sc_mdlo);
 	OFFSET(SC_PC, sigcontext, sc_pc);
 	OFFSET(SC_FPC_CSR, sigcontext, sc_fpc_csr);
-	OFFSET(SC_MSAREGS, sigcontext, sc_msaregs);
 	BLANK();
 }
 #endif
@@ -322,7 +318,6 @@ void output_sc32_defines(void)
 	OFFSET(SC32_FPREGS, sigcontext32, sc_fpregs);
 	OFFSET(SC32_FPC_CSR, sigcontext32, sc_fpc_csr);
 	OFFSET(SC32_FPC_EIR, sigcontext32, sc_fpc_eir);
-	OFFSET(SC32_MSAREGS, sigcontext32, sc_msaregs);
 	BLANK();
 }
 #endif
@@ -404,6 +399,20 @@ void output_pbe_defines(void)
 }
 #endif
 
+#ifdef CONFIG_CPU_PM
+void output_pm_defines(void)
+{
+	COMMENT(" PM offsets. ");
+#ifdef CONFIG_EVA
+	OFFSET(SSS_SEGCTL0,	mips_static_suspend_state, segctl[0]);
+	OFFSET(SSS_SEGCTL1,	mips_static_suspend_state, segctl[1]);
+	OFFSET(SSS_SEGCTL2,	mips_static_suspend_state, segctl[2]);
+#endif
+	OFFSET(SSS_SP,		mips_static_suspend_state, sp);
+	BLANK();
+}
+#endif
+
 void output_kvm_defines(void)
 {
 	COMMENT(" KVM/MIPS Specfic offsets. ");
@@ -472,10 +481,14 @@ void output_kvm_defines(void)
 void output_cps_defines(void)
 {
 	COMMENT(" MIPS CPS offsets. ");
-	OFFSET(BOOTCFG_CORE, boot_config, core);
-	OFFSET(BOOTCFG_VPE, boot_config, vpe);
-	OFFSET(BOOTCFG_PC, boot_config, pc);
-	OFFSET(BOOTCFG_SP, boot_config, sp);
-	OFFSET(BOOTCFG_GP, boot_config, gp);
+
+	OFFSET(COREBOOTCFG_VPEMASK, core_boot_config, vpe_mask);
+	OFFSET(COREBOOTCFG_VPECONFIG, core_boot_config, vpe_config);
+	DEFINE(COREBOOTCFG_SIZE, sizeof(struct core_boot_config));
+
+	OFFSET(VPEBOOTCFG_PC, vpe_boot_config, pc);
+	OFFSET(VPEBOOTCFG_SP, vpe_boot_config, sp);
+	OFFSET(VPEBOOTCFG_GP, vpe_boot_config, gp);
+	DEFINE(VPEBOOTCFG_SIZE, sizeof(struct vpe_boot_config));
 }
 #endif
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index 76122ff5cb5..7b2df224f04 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -48,6 +48,202 @@ int __isa_exception_epc(struct pt_regs *regs)
 	return epc;
 }
 
+/* (microMIPS) Convert 16-bit register encoding to 32-bit register encoding. */
+static const unsigned int reg16to32map[8] = {16, 17, 2, 3, 4, 5, 6, 7};
+
+int __mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
+		       unsigned long *contpc)
+{
+	union mips_instruction insn = (union mips_instruction)dec_insn.insn;
+	int bc_false = 0;
+	unsigned int fcr31;
+	unsigned int bit;
+
+	if (!cpu_has_mmips)
+		return 0;
+
+	switch (insn.mm_i_format.opcode) {
+	case mm_pool32a_op:
+		if ((insn.mm_i_format.simmediate & MM_POOL32A_MINOR_MASK) ==
+		    mm_pool32axf_op) {
+			switch (insn.mm_i_format.simmediate >>
+				MM_POOL32A_MINOR_SHIFT) {
+			case mm_jalr_op:
+			case mm_jalrhb_op:
+			case mm_jalrs_op:
+			case mm_jalrshb_op:
+				if (insn.mm_i_format.rt != 0)	/* Not mm_jr */
+					regs->regs[insn.mm_i_format.rt] =
+						regs->cp0_epc +
+						dec_insn.pc_inc +
+						dec_insn.next_pc_inc;
+				*contpc = regs->regs[insn.mm_i_format.rs];
+				return 1;
+			}
+		}
+		break;
+	case mm_pool32i_op:
+		switch (insn.mm_i_format.rt) {
+		case mm_bltzals_op:
+		case mm_bltzal_op:
+			regs->regs[31] = regs->cp0_epc +
+				dec_insn.pc_inc +
+				dec_insn.next_pc_inc;
+			/* Fall through */
+		case mm_bltz_op:
+			if ((long)regs->regs[insn.mm_i_format.rs] < 0)
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			return 1;
+		case mm_bgezals_op:
+		case mm_bgezal_op:
+			regs->regs[31] = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			/* Fall through */
+		case mm_bgez_op:
+			if ((long)regs->regs[insn.mm_i_format.rs] >= 0)
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			return 1;
+		case mm_blez_op:
+			if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			return 1;
+		case mm_bgtz_op:
+			if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					dec_insn.next_pc_inc;
+			return 1;
+		case mm_bc2f_op:
+		case mm_bc1f_op:
+			bc_false = 1;
+			/* Fall through */
+		case mm_bc2t_op:
+		case mm_bc1t_op:
+			preempt_disable();
+			if (is_fpu_owner())
+				asm volatile("cfc1\t%0,$31" : "=r" (fcr31));
+			else
+				fcr31 = current->thread.fpu.fcr31;
+			preempt_enable();
+
+			if (bc_false)
+				fcr31 = ~fcr31;
+
+			bit = (insn.mm_i_format.rs >> 2);
+			bit += (bit != 0);
+			bit += 23;
+			if (fcr31 & (1 << bit))
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc +
+					(insn.mm_i_format.simmediate << 1);
+			else
+				*contpc = regs->cp0_epc +
+					dec_insn.pc_inc + dec_insn.next_pc_inc;
+			return 1;
+		}
+		break;
+	case mm_pool16c_op:
+		switch (insn.mm_i_format.rt) {
+		case mm_jalr16_op:
+		case mm_jalrs16_op:
+			regs->regs[31] = regs->cp0_epc +
+				dec_insn.pc_inc + dec_insn.next_pc_inc;
+			/* Fall through */
+		case mm_jr16_op:
+			*contpc = regs->regs[insn.mm_i_format.rs];
+			return 1;
+		}
+		break;
+	case mm_beqz16_op:
+		if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] == 0)
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				(insn.mm_b1_format.simmediate << 1);
+		else
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc + dec_insn.next_pc_inc;
+		return 1;
+	case mm_bnez16_op:
+		if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] != 0)
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				(insn.mm_b1_format.simmediate << 1);
+		else
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc + dec_insn.next_pc_inc;
+		return 1;
+	case mm_b16_op:
+		*contpc = regs->cp0_epc + dec_insn.pc_inc +
+			 (insn.mm_b0_format.simmediate << 1);
+		return 1;
+	case mm_beq32_op:
+		if (regs->regs[insn.mm_i_format.rs] ==
+		    regs->regs[insn.mm_i_format.rt])
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				(insn.mm_i_format.simmediate << 1);
+		else
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				dec_insn.next_pc_inc;
+		return 1;
+	case mm_bne32_op:
+		if (regs->regs[insn.mm_i_format.rs] !=
+		    regs->regs[insn.mm_i_format.rt])
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc +
+				(insn.mm_i_format.simmediate << 1);
+		else
+			*contpc = regs->cp0_epc +
+				dec_insn.pc_inc + dec_insn.next_pc_inc;
+		return 1;
+	case mm_jalx32_op:
+		regs->regs[31] = regs->cp0_epc +
+			dec_insn.pc_inc + dec_insn.next_pc_inc;
+		*contpc = regs->cp0_epc + dec_insn.pc_inc;
+		*contpc >>= 28;
+		*contpc <<= 28;
+		*contpc |= (insn.j_format.target << 2);
+		return 1;
+	case mm_jals32_op:
+	case mm_jal32_op:
+		regs->regs[31] = regs->cp0_epc +
+			dec_insn.pc_inc + dec_insn.next_pc_inc;
+		/* Fall through */
+	case mm_j32_op:
+		*contpc = regs->cp0_epc + dec_insn.pc_inc;
+		*contpc >>= 27;
+		*contpc <<= 27;
+		*contpc |= (insn.j_format.target << 1);
+		set_isa16_mode(*contpc);
+		return 1;
+	}
+	return 0;
+}
+
 /*
  * Compute return address and emulate branch in microMIPS mode after an
  * exception only. It does not handle compact branches/jumps and cannot
@@ -366,7 +562,11 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	case cop1_op:
 		preempt_disable();
 		if (is_fpu_owner())
-			asm volatile("cfc1\t%0,$31" : "=r" (fcr31));
+			asm volatile(
+				".set push\n"
+				"\t.set mips1\n"
+				"\tcfc1\t%0,$31\n"
+				"\t.set pop" : "=r" (fcr31));
 		else
 			fcr31 = current->thread.fpu.fcr31;
 		preempt_enable();
diff --git a/arch/mips/kernel/cevt-gic.c b/arch/mips/kernel/cevt-gic.c
index 594cbbf16d6..6093716980b 100644
--- a/arch/mips/kernel/cevt-gic.c
+++ b/arch/mips/kernel/cevt-gic.c
@@ -26,7 +26,7 @@ static int gic_next_event(unsigned long delta, struct clock_event_device *evt)
 
 	cnt = gic_read_count();
 	cnt += (u64)delta;
-	gic_write_compare(cnt);
+	gic_write_cpu_compare(cnt, cpumask_first(evt->cpumask));
 	res = ((int)(gic_read_count() - cnt) >= 0) ? -ETIME : 0;
 	return res;
 }
@@ -73,7 +73,8 @@ int gic_clockevent_init(void)
 	cd = &per_cpu(gic_clockevent_device, cpu);
 
 	cd->name		= "MIPS GIC";
-	cd->features		= CLOCK_EVT_FEAT_ONESHOT;
+	cd->features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_C3STOP;
 
 	clockevent_set_clock(cd, gic_frequency);
 
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 50d3f5a8d6b..bc127e22fda 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -12,17 +12,10 @@
 #include <linux/smp.h>
 #include <linux/irq.h>
 
-#include <asm/smtc_ipi.h>
 #include <asm/time.h>
 #include <asm/cevt-r4k.h>
 #include <asm/gic.h>
 
-/*
- * The SMTC Kernel for the 34K, 1004K, et. al. replaces several
- * of these routines with SMTC-specific variants.
- */
-
-#ifndef CONFIG_MIPS_MT_SMTC
 static int mips_next_event(unsigned long delta,
 			   struct clock_event_device *evt)
 {
@@ -36,8 +29,6 @@ static int mips_next_event(unsigned long delta,
 	return res;
 }
 
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 void mips_set_clock_mode(enum clock_event_mode mode,
 				struct clock_event_device *evt)
 {
@@ -47,7 +38,6 @@ void mips_set_clock_mode(enum clock_event_mode mode,
 DEFINE_PER_CPU(struct clock_event_device, mips_clockevent_device);
 int cp0_timer_irq_installed;
 
-#ifndef CONFIG_MIPS_MT_SMTC
 irqreturn_t c0_compare_interrupt(int irq, void *dev_id)
 {
 	const int r2 = cpu_has_mips_r2;
@@ -72,9 +62,6 @@ irqreturn_t c0_compare_interrupt(int irq, void *dev_id)
 		/* Clear Count/Compare Interrupt */
 		write_c0_compare(read_c0_compare());
 		cd = &per_cpu(mips_clockevent_device, cpu);
-#ifdef CONFIG_CEVT_GIC
-		if (!gic_present)
-#endif
 		cd->event_handler(cd);
 	}
 
@@ -82,8 +69,6 @@ out:
 	return IRQ_HANDLED;
 }
 
-#endif /* Not CONFIG_MIPS_MT_SMTC */
-
 struct irqaction c0_compare_irqaction = {
 	.handler = c0_compare_interrupt,
 	.flags = IRQF_PERCPU | IRQF_TIMER,
@@ -170,7 +155,6 @@ int c0_compare_int_usable(void)
 	return 1;
 }
 
-#ifndef CONFIG_MIPS_MT_SMTC
 int r4k_clockevent_init(void)
 {
 	unsigned int cpu = smp_processor_id();
@@ -195,7 +179,9 @@ int r4k_clockevent_init(void)
 	cd = &per_cpu(mips_clockevent_device, cpu);
 
 	cd->name		= "MIPS";
-	cd->features		= CLOCK_EVT_FEAT_ONESHOT;
+	cd->features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_C3STOP |
+				  CLOCK_EVT_FEAT_PERCPU;
 
 	clockevent_set_clock(cd, mips_hpt_frequency);
 
@@ -210,9 +196,6 @@ int r4k_clockevent_init(void)
 	cd->set_mode		= mips_set_clock_mode;
 	cd->event_handler	= mips_event_handler;
 
-#ifdef CONFIG_CEVT_GIC
-	if (!gic_present)
-#endif
 	clockevents_register_device(cd);
 
 	if (cp0_timer_irq_installed)
@@ -225,4 +208,3 @@ int r4k_clockevent_init(void)
 	return 0;
 }
 
-#endif /* Not CONFIG_MIPS_MT_SMTC */
diff --git a/arch/mips/kernel/cevt-smtc.c b/arch/mips/kernel/cevt-smtc.c
deleted file mode 100644
index b6cf0a60d89..00000000000
--- a/arch/mips/kernel/cevt-smtc.c
+++ /dev/null
@@ -1,324 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2007 MIPS Technologies, Inc.
- * Copyright (C) 2007 Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2008 Kevin D. Kissell, Paralogos sarl
- */
-#include <linux/clockchips.h>
-#include <linux/interrupt.h>
-#include <linux/percpu.h>
-#include <linux/smp.h>
-#include <linux/irq.h>
-
-#include <asm/smtc_ipi.h>
-#include <asm/time.h>
-#include <asm/cevt-r4k.h>
-
-/*
- * Variant clock event timer support for SMTC on MIPS 34K, 1004K
- * or other MIPS MT cores.
- *
- * Notes on SMTC Support:
- *
- * SMTC has multiple microthread TCs pretending to be Linux CPUs.
- * But there's only one Count/Compare pair per VPE, and Compare
- * interrupts are taken opportunisitically by available TCs
- * bound to the VPE with the Count register.  The new timer
- * framework provides for global broadcasts, but we really
- * want VPE-level multicasts for best behavior. So instead
- * of invoking the high-level clock-event broadcast code,
- * this version of SMTC support uses the historical SMTC
- * multicast mechanisms "under the hood", appearing to the
- * generic clock layer as if the interrupts are per-CPU.
- *
- * The approach taken here is to maintain a set of NR_CPUS
- * virtual timers, and track which "CPU" needs to be alerted
- * at each event.
- *
- * It's unlikely that we'll see a MIPS MT core with more than
- * 2 VPEs, but we *know* that we won't need to handle more
- * VPEs than we have "CPUs".  So NCPUs arrays of NCPUs elements
- * is always going to be overkill, but always going to be enough.
- */
-
-unsigned long smtc_nexttime[NR_CPUS][NR_CPUS];
-static int smtc_nextinvpe[NR_CPUS];
-
-/*
- * Timestamps stored are absolute values to be programmed
- * into Count register.	 Valid timestamps will never be zero.
- * If a Zero Count value is actually calculated, it is converted
- * to be a 1, which will introduce 1 or two CPU cycles of error
- * roughly once every four billion events, which at 1000 HZ means
- * about once every 50 days.  If that's actually a problem, one
- * could alternate squashing 0 to 1 and to -1.
- */
-
-#define MAKEVALID(x) (((x) == 0L) ? 1L : (x))
-#define ISVALID(x) ((x) != 0L)
-
-/*
- * Time comparison is subtle, as it's really truncated
- * modular arithmetic.
- */
-
-#define IS_SOONER(a, b, reference) \
-    (((a) - (unsigned long)(reference)) < ((b) - (unsigned long)(reference)))
-
-/*
- * CATCHUP_INCREMENT, used when the function falls behind the counter.
- * Could be an increasing function instead of a constant;
- */
-
-#define CATCHUP_INCREMENT 64
-
-static int mips_next_event(unsigned long delta,
-				struct clock_event_device *evt)
-{
-	unsigned long flags;
-	unsigned int mtflags;
-	unsigned long timestamp, reference, previous;
-	unsigned long nextcomp = 0L;
-	int vpe = current_cpu_data.vpe_id;
-	int cpu = smp_processor_id();
-	local_irq_save(flags);
-	mtflags = dmt();
-
-	/*
-	 * Maintain the per-TC virtual timer
-	 * and program the per-VPE shared Count register
-	 * as appropriate here...
-	 */
-	reference = (unsigned long)read_c0_count();
-	timestamp = MAKEVALID(reference + delta);
-	/*
-	 * To really model the clock, we have to catch the case
-	 * where the current next-in-VPE timestamp is the old
-	 * timestamp for the calling CPE, but the new value is
-	 * in fact later.  In that case, we have to do a full
-	 * scan and discover the new next-in-VPE CPU id and
-	 * timestamp.
-	 */
-	previous = smtc_nexttime[vpe][cpu];
-	if (cpu == smtc_nextinvpe[vpe] && ISVALID(previous)
-	    && IS_SOONER(previous, timestamp, reference)) {
-		int i;
-		int soonest = cpu;
-
-		/*
-		 * Update timestamp array here, so that new
-		 * value gets considered along with those of
-		 * other virtual CPUs on the VPE.
-		 */
-		smtc_nexttime[vpe][cpu] = timestamp;
-		for_each_online_cpu(i) {
-			if (ISVALID(smtc_nexttime[vpe][i])
-			    && IS_SOONER(smtc_nexttime[vpe][i],
-				smtc_nexttime[vpe][soonest], reference)) {
-				    soonest = i;
-			}
-		}
-		smtc_nextinvpe[vpe] = soonest;
-		nextcomp = smtc_nexttime[vpe][soonest];
-	/*
-	 * Otherwise, we don't have to process the whole array rank,
-	 * we just have to see if the event horizon has gotten closer.
-	 */
-	} else {
-		if (!ISVALID(smtc_nexttime[vpe][smtc_nextinvpe[vpe]]) ||
-		    IS_SOONER(timestamp,
-			smtc_nexttime[vpe][smtc_nextinvpe[vpe]], reference)) {
-			    smtc_nextinvpe[vpe] = cpu;
-			    nextcomp = timestamp;
-		}
-		/*
-		 * Since next-in-VPE may me the same as the executing
-		 * virtual CPU, we update the array *after* checking
-		 * its value.
-		 */
-		smtc_nexttime[vpe][cpu] = timestamp;
-	}
-
-	/*
-	 * It may be that, in fact, we don't need to update Compare,
-	 * but if we do, we want to make sure we didn't fall into
-	 * a crack just behind Count.
-	 */
-	if (ISVALID(nextcomp)) {
-		write_c0_compare(nextcomp);
-		ehb();
-		/*
-		 * We never return an error, we just make sure
-		 * that we trigger the handlers as quickly as
-		 * we can if we fell behind.
-		 */
-		while ((nextcomp - (unsigned long)read_c0_count())
-			> (unsigned long)LONG_MAX) {
-			nextcomp += CATCHUP_INCREMENT;
-			write_c0_compare(nextcomp);
-			ehb();
-		}
-	}
-	emt(mtflags);
-	local_irq_restore(flags);
-	return 0;
-}
-
-
-void smtc_distribute_timer(int vpe)
-{
-	unsigned long flags;
-	unsigned int mtflags;
-	int cpu;
-	struct clock_event_device *cd;
-	unsigned long nextstamp;
-	unsigned long reference;
-
-
-repeat:
-	nextstamp = 0L;
-	for_each_online_cpu(cpu) {
-	    /*
-	     * Find virtual CPUs within the current VPE who have
-	     * unserviced timer requests whose time is now past.
-	     */
-	    local_irq_save(flags);
-	    mtflags = dmt();
-	    if (cpu_data[cpu].vpe_id == vpe &&
-		ISVALID(smtc_nexttime[vpe][cpu])) {
-		reference = (unsigned long)read_c0_count();
-		if ((smtc_nexttime[vpe][cpu] - reference)
-			 > (unsigned long)LONG_MAX) {
-			    smtc_nexttime[vpe][cpu] = 0L;
-			    emt(mtflags);
-			    local_irq_restore(flags);
-			    /*
-			     * We don't send IPIs to ourself.
-			     */
-			    if (cpu != smp_processor_id()) {
-				smtc_send_ipi(cpu, SMTC_CLOCK_TICK, 0);
-			    } else {
-				cd = &per_cpu(mips_clockevent_device, cpu);
-				cd->event_handler(cd);
-			    }
-		} else {
-			/* Local to VPE but Valid Time not yet reached. */
-			if (!ISVALID(nextstamp) ||
-			    IS_SOONER(smtc_nexttime[vpe][cpu], nextstamp,
-			    reference)) {
-				smtc_nextinvpe[vpe] = cpu;
-				nextstamp = smtc_nexttime[vpe][cpu];
-			}
-			emt(mtflags);
-			local_irq_restore(flags);
-		}
-	    } else {
-		emt(mtflags);
-		local_irq_restore(flags);
-
-	    }
-	}
-	/* Reprogram for interrupt at next soonest timestamp for VPE */
-	if (ISVALID(nextstamp)) {
-		write_c0_compare(nextstamp);
-		ehb();
-		if ((nextstamp - (unsigned long)read_c0_count())
-			> (unsigned long)LONG_MAX)
-				goto repeat;
-	}
-}
-
-
-irqreturn_t c0_compare_interrupt(int irq, void *dev_id)
-{
-	int cpu = smp_processor_id();
-
-	/* If we're running SMTC, we've got MIPS MT and therefore MIPS32R2 */
-	handle_perf_irq(1);
-
-	if (read_c0_cause() & (1 << 30)) {
-		/* Clear Count/Compare Interrupt */
-		write_c0_compare(read_c0_compare());
-		smtc_distribute_timer(cpu_data[cpu].vpe_id);
-	}
-	return IRQ_HANDLED;
-}
-
-
-int smtc_clockevent_init(void)
-{
-	uint64_t mips_freq = mips_hpt_frequency;
-	unsigned int cpu = smp_processor_id();
-	struct clock_event_device *cd;
-	unsigned int irq;
-	int i;
-	int j;
-
-	if (!cpu_has_counter || !mips_hpt_frequency)
-		return -ENXIO;
-	if (cpu == 0) {
-		for (i = 0; i < num_possible_cpus(); i++) {
-			smtc_nextinvpe[i] = 0;
-			for (j = 0; j < num_possible_cpus(); j++)
-				smtc_nexttime[i][j] = 0L;
-		}
-		/*
-		 * SMTC also can't have the usablility test
-		 * run by secondary TCs once Compare is in use.
-		 */
-		if (!c0_compare_int_usable())
-			return -ENXIO;
-	}
-
-	/*
-	 * With vectored interrupts things are getting platform specific.
-	 * get_c0_compare_int is a hook to allow a platform to return the
-	 * interrupt number of it's liking.
-	 */
-	irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq;
-	if (get_c0_compare_int)
-		irq = get_c0_compare_int();
-
-	cd = &per_cpu(mips_clockevent_device, cpu);
-
-	cd->name		= "MIPS";
-	cd->features		= CLOCK_EVT_FEAT_ONESHOT;
-
-	/* Calculate the min / max delta */
-	cd->mult	= div_sc((unsigned long) mips_freq, NSEC_PER_SEC, 32);
-	cd->shift		= 32;
-	cd->max_delta_ns	= clockevent_delta2ns(0x7fffffff, cd);
-	cd->min_delta_ns	= clockevent_delta2ns(0x300, cd);
-
-	cd->rating		= 300;
-	cd->irq			= irq;
-	cd->cpumask		= cpumask_of(cpu);
-	cd->set_next_event	= mips_next_event;
-	cd->set_mode		= mips_set_clock_mode;
-	cd->event_handler	= mips_event_handler;
-
-	clockevents_register_device(cd);
-
-	/*
-	 * On SMTC we only want to do the data structure
-	 * initialization and IRQ setup once.
-	 */
-	if (cpu)
-		return 0;
-	/*
-	 * And we need the hwmask associated with the c0_compare
-	 * vector to be initialized.
-	 */
-	irq_hwmask[irq] = (0x100 << cp0_compare_irq);
-	if (cp0_timer_irq_installed)
-		return 0;
-
-	cp0_timer_irq_installed = 1;
-
-	setup_irq(irq, &c0_compare_irqaction);
-
-	return 0;
-}
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index f7a46db4b16..6f4f739dad9 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -14,19 +14,43 @@
 #include <asm/asmmacro.h>
 #include <asm/cacheops.h>
 #include <asm/mipsregs.h>
+#include <asm/mipsmtregs.h>
+#include <asm/pm.h>
 
-#define GCR_CL_COHERENCE_OFS 0x2008
+#define GCR_CL_COHERENCE_OFS	0x2008
+#define GCR_CL_ID_OFS		0x2028
+
+.extern mips_cm_base
+
+.set noreorder
+
+	/*
+	 * Set dest to non-zero if the core supports the MT ASE, else zero. If
+	 * MT is not supported then branch to nomt.
+	 */
+	.macro	has_mt	dest, nomt
+	mfc0	\dest, CP0_CONFIG
+	bgez	\dest, \nomt
+	 mfc0	\dest, CP0_CONFIG, 1
+	bgez	\dest, \nomt
+	 mfc0	\dest, CP0_CONFIG, 2
+	bgez	\dest, \nomt
+	 mfc0	\dest, CP0_CONFIG, 3
+	andi	\dest, \dest, MIPS_CONF3_MT
+	beqz	\dest, \nomt
+	.endm
 
 .section .text.cps-vec
 .balign 0x1000
-.set noreorder
 
 LEAF(mips_cps_core_entry)
 	/*
-	 * These first 8 bytes will be patched by cps_smp_setup to load the
-	 * base address of the CM GCRs into register v1.
+	 * These first 12 bytes will be patched by cps_smp_setup to load the
+	 * base address of the CM GCRs into register v1 and the CCA to use into
+	 * register s0.
 	 */
 	.quad	0
+	.word	0
 
 	/* Check whether we're here due to an NMI */
 	mfc0	k0, CP0_STATUS
@@ -117,10 +141,11 @@ icache_done:
 	 add	a0, a0, t0
 dcache_done:
 
-	/* Set Kseg0 cacheable, coherent, write-back, write-allocate */
+	/* Set Kseg0 CCA to that in s0 */
 	mfc0	t0, CP0_CONFIG
 	ori	t0, 0x7
-	xori	t0, 0x2
+	xori	t0, 0x7
+	or	t0, t0, s0
 	mtc0	t0, CP0_CONFIG
 	ehb
 
@@ -134,21 +159,24 @@ dcache_done:
 	jr	t0
 	 nop
 
-1:	/* We're up, cached & coherent */
+	/*
+	 * We're up, cached & coherent. Perform any further required core-level
+	 * initialisation.
+	 */
+1:	jal	mips_cps_core_init
+	 nop
 
 	/*
-	 * TODO: We should check the VPE number we intended to boot here, and
-	 *       if non-zero we should start that VPE and stop this one. For
-	 *       the moment this doesn't matter since CPUs are brought up
-	 *       sequentially and in order, but once hotplug is implemented
-	 *       this will need revisiting.
+	 * Boot any other VPEs within this core that should be online, and
+	 * deactivate this VPE if it should be offline.
 	 */
+	jal	mips_cps_boot_vpes
+	 nop
 
 	/* Off we go! */
-	la	t0, mips_cps_bootcfg
-	lw	t1, BOOTCFG_PC(t0)
-	lw	gp, BOOTCFG_GP(t0)
-	lw	sp, BOOTCFG_SP(t0)
+	lw	t1, VPEBOOTCFG_PC(v0)
+	lw	gp, VPEBOOTCFG_GP(v0)
+	lw	sp, VPEBOOTCFG_SP(v0)
 	jr	t1
 	 nop
 	END(mips_cps_core_entry)
@@ -189,3 +217,271 @@ LEAF(excep_ejtag)
 	jr	k0
 	 nop
 	END(excep_ejtag)
+
+LEAF(mips_cps_core_init)
+#ifdef CONFIG_MIPS_MT
+	/* Check that the core implements the MT ASE */
+	has_mt	t0, 3f
+	 nop
+
+	.set	push
+	.set	mt
+
+	/* Only allow 1 TC per VPE to execute... */
+	dmt
+
+	/* ...and for the moment only 1 VPE */
+	dvpe
+	la	t1, 1f
+	jr.hb	t1
+	 nop
+
+	/* Enter VPE configuration state */
+1:	mfc0	t0, CP0_MVPCONTROL
+	ori	t0, t0, MVPCONTROL_VPC
+	mtc0	t0, CP0_MVPCONTROL
+
+	/* Retrieve the number of VPEs within the core */
+	mfc0	t0, CP0_MVPCONF0
+	srl	t0, t0, MVPCONF0_PVPE_SHIFT
+	andi	t0, t0, (MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT)
+	addi	t7, t0, 1
+
+	/* If there's only 1, we're done */
+	beqz	t0, 2f
+	 nop
+
+	/* Loop through each VPE within this core */
+	li	t5, 1
+
+1:	/* Operate on the appropriate TC */
+	mtc0	t5, CP0_VPECONTROL
+	ehb
+
+	/* Bind TC to VPE (1:1 TC:VPE mapping) */
+	mttc0	t5, CP0_TCBIND
+
+	/* Set exclusive TC, non-active, master */
+	li	t0, VPECONF0_MVP
+	sll	t1, t5, VPECONF0_XTC_SHIFT
+	or	t0, t0, t1
+	mttc0	t0, CP0_VPECONF0
+
+	/* Set TC non-active, non-allocatable */
+	mttc0	zero, CP0_TCSTATUS
+
+	/* Set TC halted */
+	li	t0, TCHALT_H
+	mttc0	t0, CP0_TCHALT
+
+	/* Next VPE */
+	addi	t5, t5, 1
+	slt	t0, t5, t7
+	bnez	t0, 1b
+	 nop
+
+	/* Leave VPE configuration state */
+2:	mfc0	t0, CP0_MVPCONTROL
+	xori	t0, t0, MVPCONTROL_VPC
+	mtc0	t0, CP0_MVPCONTROL
+
+3:	.set	pop
+#endif
+	jr	ra
+	 nop
+	END(mips_cps_core_init)
+
+LEAF(mips_cps_boot_vpes)
+	/* Retrieve CM base address */
+	la	t0, mips_cm_base
+	lw	t0, 0(t0)
+
+	/* Calculate a pointer to this cores struct core_boot_config */
+	lw	t0, GCR_CL_ID_OFS(t0)
+	li	t1, COREBOOTCFG_SIZE
+	mul	t0, t0, t1
+	la	t1, mips_cps_core_bootcfg
+	lw	t1, 0(t1)
+	addu	t0, t0, t1
+
+	/* Calculate this VPEs ID. If the core doesn't support MT use 0 */
+	has_mt	t6, 1f
+	 li	t9, 0
+
+	/* Find the number of VPEs present in the core */
+	mfc0	t1, CP0_MVPCONF0
+	srl	t1, t1, MVPCONF0_PVPE_SHIFT
+	andi	t1, t1, MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT
+	addi	t1, t1, 1
+
+	/* Calculate a mask for the VPE ID from EBase.CPUNum */
+	clz	t1, t1
+	li	t2, 31
+	subu	t1, t2, t1
+	li	t2, 1
+	sll	t1, t2, t1
+	addiu	t1, t1, -1
+
+	/* Retrieve the VPE ID from EBase.CPUNum */
+	mfc0	t9, $15, 1
+	and	t9, t9, t1
+
+1:	/* Calculate a pointer to this VPEs struct vpe_boot_config */
+	li	t1, VPEBOOTCFG_SIZE
+	mul	v0, t9, t1
+	lw	t7, COREBOOTCFG_VPECONFIG(t0)
+	addu	v0, v0, t7
+
+#ifdef CONFIG_MIPS_MT
+
+	/* If the core doesn't support MT then return */
+	bnez	t6, 1f
+	 nop
+	jr	ra
+	 nop
+
+	.set	push
+	.set	mt
+
+1:	/* Enter VPE configuration state */
+	dvpe
+	la	t1, 1f
+	jr.hb	t1
+	 nop
+1:	mfc0	t1, CP0_MVPCONTROL
+	ori	t1, t1, MVPCONTROL_VPC
+	mtc0	t1, CP0_MVPCONTROL
+	ehb
+
+	/* Loop through each VPE */
+	lw	t6, COREBOOTCFG_VPEMASK(t0)
+	move	t8, t6
+	li	t5, 0
+
+	/* Check whether the VPE should be running. If not, skip it */
+1:	andi	t0, t6, 1
+	beqz	t0, 2f
+	 nop
+
+	/* Operate on the appropriate TC */
+	mfc0	t0, CP0_VPECONTROL
+	ori	t0, t0, VPECONTROL_TARGTC
+	xori	t0, t0, VPECONTROL_TARGTC
+	or	t0, t0, t5
+	mtc0	t0, CP0_VPECONTROL
+	ehb
+
+	/* Skip the VPE if its TC is not halted */
+	mftc0	t0, CP0_TCHALT
+	beqz	t0, 2f
+	 nop
+
+	/* Calculate a pointer to the VPEs struct vpe_boot_config */
+	li	t0, VPEBOOTCFG_SIZE
+	mul	t0, t0, t5
+	addu	t0, t0, t7
+
+	/* Set the TC restart PC */
+	lw	t1, VPEBOOTCFG_PC(t0)
+	mttc0	t1, CP0_TCRESTART
+
+	/* Set the TC stack pointer */
+	lw	t1, VPEBOOTCFG_SP(t0)
+	mttgpr	t1, sp
+
+	/* Set the TC global pointer */
+	lw	t1, VPEBOOTCFG_GP(t0)
+	mttgpr	t1, gp
+
+	/* Copy config from this VPE */
+	mfc0	t0, CP0_CONFIG
+	mttc0	t0, CP0_CONFIG
+
+	/* Ensure no software interrupts are pending */
+	mttc0	zero, CP0_CAUSE
+	mttc0	zero, CP0_STATUS
+
+	/* Set TC active, not interrupt exempt */
+	mftc0	t0, CP0_TCSTATUS
+	li	t1, ~TCSTATUS_IXMT
+	and	t0, t0, t1
+	ori	t0, t0, TCSTATUS_A
+	mttc0	t0, CP0_TCSTATUS
+
+	/* Clear the TC halt bit */
+	mttc0	zero, CP0_TCHALT
+
+	/* Set VPE active */
+	mftc0	t0, CP0_VPECONF0
+	ori	t0, t0, VPECONF0_VPA
+	mttc0	t0, CP0_VPECONF0
+
+	/* Next VPE */
+2:	srl	t6, t6, 1
+	addi	t5, t5, 1
+	bnez	t6, 1b
+	 nop
+
+	/* Leave VPE configuration state */
+	mfc0	t1, CP0_MVPCONTROL
+	xori	t1, t1, MVPCONTROL_VPC
+	mtc0	t1, CP0_MVPCONTROL
+	ehb
+	evpe
+
+	/* Check whether this VPE is meant to be running */
+	li	t0, 1
+	sll	t0, t0, t9
+	and	t0, t0, t8
+	bnez	t0, 2f
+	 nop
+
+	/* This VPE should be offline, halt the TC */
+	li	t0, TCHALT_H
+	mtc0	t0, CP0_TCHALT
+	la	t0, 1f
+1:	jr.hb	t0
+	 nop
+
+2:	.set	pop
+
+#endif /* CONFIG_MIPS_MT */
+
+	/* Return */
+	jr	ra
+	 nop
+	END(mips_cps_boot_vpes)
+
+#if defined(CONFIG_MIPS_CPS_PM) && defined(CONFIG_CPU_PM)
+
+	/* Calculate a pointer to this CPUs struct mips_static_suspend_state */
+	.macro	psstate	dest
+	.set	push
+	.set	noat
+	lw	$1, TI_CPU(gp)
+	sll	$1, $1, LONGLOG
+	la	\dest, __per_cpu_offset
+	addu	$1, $1, \dest
+	lw	$1, 0($1)
+	la	\dest, cps_cpu_state
+	addu	\dest, \dest, $1
+	.set	pop
+	.endm
+
+LEAF(mips_cps_pm_save)
+	/* Save CPU state */
+	SUSPEND_SAVE_REGS
+	psstate	t1
+	SUSPEND_SAVE_STATIC
+	jr	v0
+	 nop
+	END(mips_cps_pm_save)
+
+LEAF(mips_cps_pm_restore)
+	/* Restore CPU state */
+	psstate	t1
+	RESUME_RESTORE_STATIC
+	RESUME_RESTORE_REGS_RETURN
+	END(mips_cps_pm_restore)
+
+#endif /* CONFIG_MIPS_CPS_PM && CONFIG_CPU_PM */
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 6e8fb85ce7c..d74f957c561 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -62,7 +62,7 @@ static inline void check_errata(void)
 	case CPU_34K:
 		/*
 		 * Erratum "RPS May Cause Incorrect Instruction Execution"
-		 * This code only handles VPE0, any SMP/SMTC/RTOS code
+		 * This code only handles VPE0, any SMP/RTOS code
 		 * making use of VPE1 will be responsable for that VPE.
 		 */
 		if ((c->processor_id & PRID_REV_MASK) <= PRID_REV_34K_V1_0_2)
@@ -423,7 +423,7 @@ static void decode_configs(struct cpuinfo_mips *c)
 
 #ifndef CONFIG_MIPS_CPS
 	if (cpu_has_mips_r2) {
-		c->core = read_c0_ebase() & 0x3ff;
+		c->core = get_ebase_cpunum();
 		if (cpu_has_mipsmt)
 			c->core >>= fls(core_nvpes()) - 1;
 	}
@@ -684,21 +684,6 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 		 */
 		c->tlbsize = (read_c0_info() & (1 << 29)) ? 64 : 48;
 		break;
-	case PRID_IMP_RM9000:
-		c->cputype = CPU_RM9000;
-		__cpu_name[cpu] = "RM9000";
-		set_isa(c, MIPS_CPU_ISA_IV);
-		c->options = R4K_OPTS | MIPS_CPU_FPU | MIPS_CPU_32FPR |
-			     MIPS_CPU_LLSC;
-		/*
-		 * Bit 29 in the info register of the RM9000
-		 * indicates if the TLB has 48 or 64 entries.
-		 *
-		 * 29	   1 =>	   64 entry JTLB
-		 *	   0 =>	   48 entry JTLB
-		 */
-		c->tlbsize = (read_c0_info() & (1 << 29)) ? 64 : 48;
-		break;
 	case PRID_IMP_R8000:
 		c->cputype = CPU_R8000;
 		__cpu_name[cpu] = "RM8000";
@@ -1041,6 +1026,7 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu)
 	decode_configs(c);
 	/* JZRISC does not implement the CP0 counter. */
 	c->options &= ~MIPS_CPU_COUNTER;
+	BUG_ON(!__builtin_constant_p(cpu_has_counter) || cpu_has_counter);
 	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_JZRISC:
 		c->cputype = CPU_JZRISC;
@@ -1074,6 +1060,7 @@ static inline void cpu_probe_netlogic(struct cpuinfo_mips *c, int cpu)
 	switch (c->processor_id & PRID_IMP_MASK) {
 	case PRID_IMP_NETLOGIC_XLP2XX:
 	case PRID_IMP_NETLOGIC_XLP9XX:
+	case PRID_IMP_NETLOGIC_XLP5XX:
 		c->cputype = CPU_XLP;
 		__cpu_name[cpu] = "Broadcom XLPII";
 		break;
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index e5786858cdb..4353d323f01 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -16,9 +16,6 @@
 #include <asm/isadep.h>
 #include <asm/thread_info.h>
 #include <asm/war.h>
-#ifdef CONFIG_MIPS_MT_SMTC
-#include <asm/mipsmtregs.h>
-#endif
 
 #ifndef CONFIG_PREEMPT
 #define resume_kernel	restore_all
@@ -89,41 +86,6 @@ FEXPORT(syscall_exit)
 	bnez	t0, syscall_exit_work
 
 restore_all:				# restore full frame
-#ifdef CONFIG_MIPS_MT_SMTC
-#ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP
-/* Re-arm any temporarily masked interrupts not explicitly "acked" */
-	mfc0	v0, CP0_TCSTATUS
-	ori	v1, v0, TCSTATUS_IXMT
-	mtc0	v1, CP0_TCSTATUS
-	andi	v0, TCSTATUS_IXMT
-	_ehb
-	mfc0	t0, CP0_TCCONTEXT
-	DMT	9				# dmt t1
-	jal	mips_ihb
-	mfc0	t2, CP0_STATUS
-	andi	t3, t0, 0xff00
-	or	t2, t2, t3
-	mtc0	t2, CP0_STATUS
-	_ehb
-	andi	t1, t1, VPECONTROL_TE
-	beqz	t1, 1f
-	EMT
-1:
-	mfc0	v1, CP0_TCSTATUS
-	/* We set IXMT above, XOR should clear it here */
-	xori	v1, v1, TCSTATUS_IXMT
-	or	v1, v0, v1
-	mtc0	v1, CP0_TCSTATUS
-	_ehb
-	xor	t0, t0, t3
-	mtc0	t0, CP0_TCCONTEXT
-#endif /* CONFIG_MIPS_MT_SMTC_IM_BACKSTOP */
-/* Detect and execute deferred IPI "interrupts" */
-	LONG_L	s0, TI_REGS($28)
-	LONG_S	sp, TI_REGS($28)
-	jal	deferred_smtc_ipi
-	LONG_S	s0, TI_REGS($28)
-#endif /* CONFIG_MIPS_MT_SMTC */
 	.set	noat
 	RESTORE_TEMP
 	RESTORE_AT
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 60e7e5e45af..8b6538750fe 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -302,6 +302,9 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra,
 	    &return_to_handler;
 	int faulted, insns;
 
+	if (unlikely(ftrace_graph_is_dead()))
+		return;
+
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index a9ce3408be2..ac35e12cb1f 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -21,20 +21,6 @@
 #include <asm/war.h>
 #include <asm/thread_info.h>
 
-#ifdef CONFIG_MIPS_MT_SMTC
-#define PANIC_PIC(msg)					\
-		.set	push;				\
-		.set	nomicromips;			\
-		.set	reorder;			\
-		PTR_LA	a0,8f;				\
-		.set	noat;				\
-		PTR_LA	AT, panic;			\
-		jr	AT;				\
-9:		b	9b;				\
-		.set	pop;				\
-		TEXT(msg)
-#endif
-
 	__INIT
 
 /*
@@ -251,15 +237,6 @@ NESTED(except_vec_vi, 0, sp)
 	SAVE_AT
 	.set	push
 	.set	noreorder
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * To keep from blindly blocking *all* interrupts
-	 * during service by SMTC kernel, we also want to
-	 * pass the IM value to be cleared.
-	 */
-FEXPORT(except_vec_vi_mori)
-	ori	a0, $0, 0
-#endif /* CONFIG_MIPS_MT_SMTC */
 	PTR_LA	v1, except_vec_vi_handler
 FEXPORT(except_vec_vi_lui)
 	lui	v0, 0		/* Patched */
@@ -277,37 +254,10 @@ EXPORT(except_vec_vi_end)
 NESTED(except_vec_vi_handler, 0, sp)
 	SAVE_TEMP
 	SAVE_STATIC
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * SMTC has an interesting problem that interrupts are level-triggered,
-	 * and the CLI macro will clear EXL, potentially causing a duplicate
-	 * interrupt service invocation. So we need to clear the associated
-	 * IM bit of Status prior to doing CLI, and restore it after the
-	 * service routine has been invoked - we must assume that the
-	 * service routine will have cleared the state, and any active
-	 * level represents a new or otherwised unserviced event...
-	 */
-	mfc0	t1, CP0_STATUS
-	and	t0, a0, t1
-#ifdef CONFIG_MIPS_MT_SMTC_IM_BACKSTOP
-	mfc0	t2, CP0_TCCONTEXT
-	or	t2, t0, t2
-	mtc0	t2, CP0_TCCONTEXT
-#endif /* CONFIG_MIPS_MT_SMTC_IM_BACKSTOP */
-	xor	t1, t1, t0
-	mtc0	t1, CP0_STATUS
-	_ehb
-#endif /* CONFIG_MIPS_MT_SMTC */
 	CLI
 #ifdef CONFIG_TRACE_IRQFLAGS
 	move	s0, v0
-#ifdef CONFIG_MIPS_MT_SMTC
-	move	s1, a0
-#endif
 	TRACE_IRQS_OFF
-#ifdef CONFIG_MIPS_MT_SMTC
-	move	a0, s1
-#endif
 	move	v0, s0
 #endif
 
@@ -496,9 +446,6 @@ NESTED(nmi_handler, PT_SIZE, sp)
 
 	.align	5
 	LEAF(handle_ri_rdhwr_vivt)
-#ifdef CONFIG_MIPS_MT_SMTC
-	PANIC_PIC("handle_ri_rdhwr_vivt called")
-#else
 	.set	push
 	.set	noat
 	.set	noreorder
@@ -517,7 +464,6 @@ NESTED(nmi_handler, PT_SIZE, sp)
 	.set	pop
 	bltz	k1, handle_ri	/* slow path */
 	/* fall thru */
-#endif
 	END(handle_ri_rdhwr_vivt)
 
 	LEAF(handle_ri_rdhwr)
diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S
index e712dcf18b2..95afd663cd4 100644
--- a/arch/mips/kernel/head.S
+++ b/arch/mips/kernel/head.S
@@ -35,33 +35,12 @@
 	 */
 	.macro	setup_c0_status set clr
 	.set	push
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * For SMTC, we need to set privilege and disable interrupts only for
-	 * the current TC, using the TCStatus register.
-	 */
-	mfc0	t0, CP0_TCSTATUS
-	/* Fortunately CU 0 is in the same place in both registers */
-	/* Set TCU0, TMX, TKSU (for later inversion) and IXMT */
-	li	t1, ST0_CU0 | 0x08001c00
-	or	t0, t1
-	/* Clear TKSU, leave IXMT */
-	xori	t0, 0x00001800
-	mtc0	t0, CP0_TCSTATUS
-	_ehb
-	/* We need to leave the global IE bit set, but clear EXL...*/
-	mfc0	t0, CP0_STATUS
-	or	t0, ST0_CU0 | ST0_EXL | ST0_ERL | \set | \clr
-	xor	t0, ST0_EXL | ST0_ERL | \clr
-	mtc0	t0, CP0_STATUS
-#else
 	mfc0	t0, CP0_STATUS
 	or	t0, ST0_CU0|\set|0x1f|\clr
 	xor	t0, 0x1f|\clr
 	mtc0	t0, CP0_STATUS
 	.set	noreorder
 	sll	zero,3				# ehb
-#endif
 	.set	pop
 	.endm
 
@@ -115,24 +94,6 @@ NESTED(kernel_entry, 16, sp)			# kernel entry point
 	jr	t0
 0:
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * In SMTC kernel, "CLI" is thread-specific, in TCStatus.
-	 * We still need to enable interrupts globally in Status,
-	 * and clear EXL/ERL.
-	 *
-	 * TCContext is used to track interrupt levels under
-	 * service in SMTC kernel. Clear for boot TC before
-	 * allowing any interrupts.
-	 */
-	mtc0	zero, CP0_TCCONTEXT
-
-	mfc0	t0, CP0_STATUS
-	ori	t0, t0, 0xff1f
-	xori	t0, t0, 0x001e
-	mtc0	t0, CP0_STATUS
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 	PTR_LA		t0, __bss_start		# clear .bss
 	LONG_S		zero, (t0)
 	PTR_LA		t1, __bss_stop - LONGSIZE
@@ -164,25 +125,8 @@ NESTED(kernel_entry, 16, sp)			# kernel entry point
  * function after setting up the stack and gp registers.
  */
 NESTED(smp_bootstrap, 16, sp)
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * Read-modify-writes of Status must be atomic, and this
-	 * is one case where CLI is invoked without EXL being
-	 * necessarily set. The CLI and setup_c0_status will
-	 * in fact be redundant for all but the first TC of
-	 * each VPE being booted.
-	 */
-	DMT	10	# dmt t2 /* t0, t1 are used by CLI and setup_c0_status() */
-	jal	mips_ihb
-#endif /* CONFIG_MIPS_MT_SMTC */
 	smp_slave_setup
 	setup_c0_status_sec
-#ifdef CONFIG_MIPS_MT_SMTC
-	andi	t2, t2, VPECONTROL_TE
-	beqz	t2, 2f
-	EMT		# emt
-2:
-#endif /* CONFIG_MIPS_MT_SMTC */
 	j	start_secondary
 	END(smp_bootstrap)
 #endif /* CONFIG_SMP */
diff --git a/arch/mips/kernel/i8259.c b/arch/mips/kernel/i8259.c
index 2b91fe80c43..50b364897dd 100644
--- a/arch/mips/kernel/i8259.c
+++ b/arch/mips/kernel/i8259.c
@@ -42,9 +42,6 @@ static struct irq_chip i8259A_chip = {
 	.irq_disable		= disable_8259A_irq,
 	.irq_unmask		= enable_8259A_irq,
 	.irq_mask_ack		= mask_and_ack_8259A,
-#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
-	.irq_set_affinity	= plat_set_irq_affinity,
-#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
 };
 
 /*
@@ -180,7 +177,6 @@ handle_real_irq:
 		outb(cached_master_mask, PIC_MASTER_IMR);
 		outb(0x60+irq, PIC_MASTER_CMD); /* 'Specific EOI to master */
 	}
-	smtc_im_ack_irq(irq);
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 	return;
 
diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 837ff27950b..09ce4598075 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -224,29 +224,26 @@ void __init check_wait(void)
 		   cpu_wait = r4k_wait;
 		 */
 		break;
-	case CPU_RM9000:
-		if ((c->processor_id & 0x00ff) >= 0x40)
-			cpu_wait = r4k_wait;
-		break;
 	default:
 		break;
 	}
 }
 
-static void smtc_idle_hook(void)
-{
-#ifdef CONFIG_MIPS_MT_SMTC
-	void smtc_idle_loop_hook(void);
-
-	smtc_idle_loop_hook();
-#endif
-}
-
 void arch_cpu_idle(void)
 {
-	smtc_idle_hook();
 	if (cpu_wait)
 		cpu_wait();
 	else
 		local_irq_enable();
 }
+
+#ifdef CONFIG_CPU_IDLE
+
+int mips_cpuidle_wait_enter(struct cpuidle_device *dev,
+			    struct cpuidle_driver *drv, int index)
+{
+	arch_cpu_idle();
+	return index;
+}
+
+#endif
diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c
index 8520dad6d4e..88e4c323382 100644
--- a/arch/mips/kernel/irq-gic.c
+++ b/arch/mips/kernel/irq-gic.c
@@ -54,6 +54,21 @@ void gic_write_compare(cycle_t cnt)
 				(int)(cnt & 0xffffffff));
 }
 
+void gic_write_cpu_compare(cycle_t cnt, int cpu)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	GICWRITE(GIC_REG(VPE_LOCAL, GIC_VPE_OTHER_ADDR), cpu);
+	GICWRITE(GIC_REG(VPE_OTHER, GIC_VPE_COMPARE_HI),
+				(int)(cnt >> 32));
+	GICWRITE(GIC_REG(VPE_OTHER, GIC_VPE_COMPARE_LO),
+				(int)(cnt & 0xffffffff));
+
+	local_irq_restore(flags);
+}
+
 cycle_t gic_read_compare(void)
 {
 	unsigned int hi, lo;
diff --git a/arch/mips/kernel/irq-msc01.c b/arch/mips/kernel/irq-msc01.c
index fab40f7d2e0..a734b2c2f9e 100644
--- a/arch/mips/kernel/irq-msc01.c
+++ b/arch/mips/kernel/irq-msc01.c
@@ -53,13 +53,9 @@ static inline void unmask_msc_irq(struct irq_data *d)
  */
 static void level_mask_and_ack_msc_irq(struct irq_data *d)
 {
-	unsigned int irq = d->irq;
-
 	mask_msc_irq(d);
 	if (!cpu_has_veic)
 		MSCIC_WRITE(MSC01_IC_EOI, 0);
-	/* This actually needs to be a call into platform code */
-	smtc_im_ack_irq(irq);
 }
 
 /*
@@ -78,7 +74,6 @@ static void edge_mask_and_ack_msc_irq(struct irq_data *d)
 		MSCIC_WRITE(MSC01_IC_SUP+irq*8, r | ~MSC01_IC_SUP_EDGE_BIT);
 		MSCIC_WRITE(MSC01_IC_SUP+irq*8, r);
 	}
-	smtc_im_ack_irq(irq);
 }
 
 /*
@@ -131,7 +126,7 @@ void __init init_msc_irqs(unsigned long icubase, unsigned int irqbase, msc_irqma
 
 	board_bind_eic_interrupt = &msc_bind_eic_interrupt;
 
-	for (; nirq >= 0; nirq--, imp++) {
+	for (; nirq > 0; nirq--, imp++) {
 		int n = imp->im_irq;
 
 		switch (imp->im_type) {
diff --git a/arch/mips/kernel/irq.c b/arch/mips/kernel/irq.c
index 1818da4dbb8..d2bfbc2e899 100644
--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -73,7 +73,6 @@ void free_irqno(unsigned int irq)
  */
 void ack_bad_irq(unsigned int irq)
 {
-	smtc_im_ack_irq(irq);
 	printk("unexpected IRQ # %d\n", irq);
 }
 
@@ -142,23 +141,7 @@ void __irq_entry do_IRQ(unsigned int irq)
 {
 	irq_enter();
 	check_stack_overflow();
-	if (!smtc_handle_on_other_cpu(irq))
-		generic_handle_irq(irq);
-	irq_exit();
-}
-
-#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
-/*
- * To avoid inefficient and in some cases pathological re-checking of
- * IRQ affinity, we have this variant that skips the affinity check.
- */
-
-void __irq_entry do_IRQ_no_affinity(unsigned int irq)
-{
-	irq_enter();
-	smtc_im_backstop(irq);
 	generic_handle_irq(irq);
 	irq_exit();
 }
 
-#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 539b6294b61..00940d1d5c4 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -74,10 +74,6 @@ _mcount:
 #endif
 
 	/* When tracing is activated, it calls ftrace_caller+8 (aka here) */
-	lw	t1, function_trace_stop
-	bnez	t1, ftrace_stub
-	 nop
-
 	MCOUNT_SAVE_REGS
 #ifdef KBUILD_MCOUNT_RA_ADDRESS
 	PTR_S	MCOUNT_RA_ADDRESS_REG, PT_R12(sp)
@@ -105,9 +101,6 @@ ftrace_stub:
 #else	/* ! CONFIG_DYNAMIC_FTRACE */
 
 NESTED(_mcount, PT_SIZE, ra)
-	lw	t1, function_trace_stop
-	bnez	t1, ftrace_stub
-	 nop
 	PTR_LA	t1, ftrace_stub
 	PTR_L	t2, ftrace_trace_function /* Prepare t2 for (1) */
 	bne	t1, t2, static_trace
diff --git a/arch/mips/kernel/mips-cpc.c b/arch/mips/kernel/mips-cpc.c
index c9dc6740296..ba473608a34 100644
--- a/arch/mips/kernel/mips-cpc.c
+++ b/arch/mips/kernel/mips-cpc.c
@@ -9,12 +9,18 @@
  */
 
 #include <linux/errno.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
 
 #include <asm/mips-cm.h>
 #include <asm/mips-cpc.h>
 
 void __iomem *mips_cpc_base;
 
+static DEFINE_PER_CPU_ALIGNED(spinlock_t, cpc_core_lock);
+
+static DEFINE_PER_CPU_ALIGNED(unsigned long, cpc_core_lock_flags);
+
 phys_t __weak mips_cpc_phys_base(void)
 {
 	u32 cpc_base;
@@ -39,6 +45,10 @@ phys_t __weak mips_cpc_phys_base(void)
 int mips_cpc_probe(void)
 {
 	phys_t addr;
+	unsigned cpu;
+
+	for_each_possible_cpu(cpu)
+		spin_lock_init(&per_cpu(cpc_core_lock, cpu));
 
 	addr = mips_cpc_phys_base();
 	if (!addr)
@@ -50,3 +60,21 @@ int mips_cpc_probe(void)
 
 	return 0;
 }
+
+void mips_cpc_lock_other(unsigned int core)
+{
+	unsigned curr_core;
+	preempt_disable();
+	curr_core = current_cpu_data.core;
+	spin_lock_irqsave(&per_cpu(cpc_core_lock, curr_core),
+			  per_cpu(cpc_core_lock_flags, curr_core));
+	write_cpc_cl_other(core << CPC_Cx_OTHER_CORENUM_SHF);
+}
+
+void mips_cpc_unlock_other(void)
+{
+	unsigned curr_core = current_cpu_data.core;
+	spin_unlock_irqrestore(&per_cpu(cpc_core_lock, curr_core),
+			       per_cpu(cpc_core_lock_flags, curr_core));
+	preempt_enable();
+}
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index cb098628aee..362bb3707e6 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -1,5 +1,5 @@
 /*
- * General MIPS MT support routines, usable in AP/SP, SMVP, or SMTC kernels
+ * General MIPS MT support routines, usable in AP/SP and SMVP.
  * Copyright (C) 2005 Mips Technologies, Inc
  */
 #include <linux/cpu.h>
diff --git a/arch/mips/kernel/mips-mt.c b/arch/mips/kernel/mips-mt.c
index 6ded9bd1489..88b1ef5f868 100644
--- a/arch/mips/kernel/mips-mt.c
+++ b/arch/mips/kernel/mips-mt.c
@@ -1,5 +1,5 @@
 /*
- * General MIPS MT support routines, usable in AP/SP, SMVP, or SMTC kernels
+ * General MIPS MT support routines, usable in AP/SP and SMVP.
  * Copyright (C) 2005 Mips Technologies, Inc
  */
 
@@ -57,9 +57,6 @@ void mips_mt_regdump(unsigned long mvpctl)
 	int tc;
 	unsigned long haltval;
 	unsigned long tcstatval;
-#ifdef CONFIG_MIPS_MT_SMTC
-	void smtc_soft_dump(void);
-#endif /* CONFIG_MIPT_MT_SMTC */
 
 	local_irq_save(flags);
 	vpflags = dvpe();
@@ -116,9 +113,6 @@ void mips_mt_regdump(unsigned long mvpctl)
 		if (!haltval)
 			write_tc_c0_tchalt(0);
 	}
-#ifdef CONFIG_MIPS_MT_SMTC
-	smtc_soft_dump();
-#endif /* CONFIG_MIPT_MT_SMTC */
 	printk("===========================\n");
 	evpe(vpflags);
 	local_irq_restore(flags);
@@ -295,21 +289,11 @@ void mips_mt_set_cpuoptions(void)
 
 void mt_cflush_lockdown(void)
 {
-#ifdef CONFIG_MIPS_MT_SMTC
-	void smtc_cflush_lockdown(void);
-
-	smtc_cflush_lockdown();
-#endif /* CONFIG_MIPS_MT_SMTC */
 	/* FILL IN VSMP and AP/SP VERSIONS HERE */
 }
 
 void mt_cflush_release(void)
 {
-#ifdef CONFIG_MIPS_MT_SMTC
-	void smtc_cflush_release(void);
-
-	smtc_cflush_release();
-#endif /* CONFIG_MIPS_MT_SMTC */
 	/* FILL IN VSMP and AP/SP VERSIONS HERE */
 }
 
diff --git a/arch/mips/kernel/octeon_switch.S b/arch/mips/kernel/octeon_switch.S
index 029e002a4ea..f6547680c81 100644
--- a/arch/mips/kernel/octeon_switch.S
+++ b/arch/mips/kernel/octeon_switch.S
@@ -10,24 +10,12 @@
  * Copyright (C) 2000 MIPS Technologies, Inc.
  *    written by Carsten Langgaard, carstenl@mips.com
  */
-#include <asm/asm.h>
-#include <asm/cachectl.h>
-#include <asm/fpregdef.h>
-#include <asm/mipsregs.h>
-#include <asm/asm-offsets.h>
-#include <asm/pgtable-bits.h>
-#include <asm/regdef.h>
-#include <asm/stackframe.h>
-#include <asm/thread_info.h>
-
-#include <asm/asmmacro.h>
-
-/*
- * Offset to the current process status flags, the first 32 bytes of the
- * stack are not used.
- */
-#define ST_OFF (_THREAD_SIZE - 32 - PT_SIZE + PT_STATUS)
 
+#define USE_ALTERNATE_RESUME_IMPL 1
+	.set push
+	.set arch=mips64r2
+#include "r4k_switch.S"
+	.set pop
 /*
  * task_struct *resume(task_struct *prev, task_struct *next,
  *		       struct thread_info *next_ti, int usedfpu)
@@ -40,6 +28,61 @@
 	cpu_save_nonscratch a0
 	LONG_S	ra, THREAD_REG31(a0)
 
+	/*
+	 * check if we need to save FPU registers
+	 */
+	PTR_L	t3, TASK_THREAD_INFO(a0)
+	LONG_L	t0, TI_FLAGS(t3)
+	li	t1, _TIF_USEDFPU
+	and	t2, t0, t1
+	beqz	t2, 1f
+	nor	t1, zero, t1
+
+	and	t0, t0, t1
+	LONG_S	t0, TI_FLAGS(t3)
+
+	/*
+	 * clear saved user stack CU1 bit
+	 */
+	LONG_L	t0, ST_OFF(t3)
+	li	t1, ~ST0_CU1
+	and	t0, t0, t1
+	LONG_S	t0, ST_OFF(t3)
+
+	.set push
+	.set arch=mips64r2
+	fpu_save_double a0 t0 t1		# c0_status passed in t0
+						# clobbers t1
+	.set pop
+1:
+
+	/* check if we need to save COP2 registers */
+	PTR_L	t2, TASK_THREAD_INFO(a0)
+	LONG_L	t0, ST_OFF(t2)
+	bbit0	t0, 30, 1f
+
+	/* Disable COP2 in the stored process state */
+	li	t1, ST0_CU2
+	xor	t0, t1
+	LONG_S	t0, ST_OFF(t2)
+
+	/* Enable COP2 so we can save it */
+	mfc0	t0, CP0_STATUS
+	or	t0, t1
+	mtc0	t0, CP0_STATUS
+
+	/* Save COP2 */
+	daddu	a0, THREAD_CP2
+	jal octeon_cop2_save
+	dsubu	a0, THREAD_CP2
+
+	/* Disable COP2 now that we are done */
+	mfc0	t0, CP0_STATUS
+	li	t1, ST0_CU2
+	xor	t0, t1
+	mtc0	t0, CP0_STATUS
+
+1:
 #if CONFIG_CAVIUM_OCTEON_CVMSEG_SIZE > 0
 	/* Check if we need to store CVMSEG state */
 	mfc0	t0, $11,7	/* CvmMemCtl */
@@ -85,12 +128,7 @@
 	move	$28, a2
 	cpu_restore_nonscratch a1
 
-#if (_THREAD_SIZE - 32) < 0x8000
-	PTR_ADDIU	t0, $28, _THREAD_SIZE - 32
-#else
-	PTR_LI		t0, _THREAD_SIZE - 32
-	PTR_ADDU	t0, $28
-#endif
+	PTR_ADDU	t0, $28, _THREAD_SIZE - 32
 	set_saved_sp	t0, t1, t2
 
 	mfc0	t1, CP0_STATUS		/* Do we really need this? */
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
new file mode 100644
index 00000000000..c4c2069d3a2
--- /dev/null
+++ b/arch/mips/kernel/pm-cps.c
@@ -0,0 +1,716 @@
+/*
+ * Copyright (C) 2014 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+
+#include <asm/asm-offsets.h>
+#include <asm/cacheflush.h>
+#include <asm/cacheops.h>
+#include <asm/idle.h>
+#include <asm/mips-cm.h>
+#include <asm/mips-cpc.h>
+#include <asm/mipsmtregs.h>
+#include <asm/pm.h>
+#include <asm/pm-cps.h>
+#include <asm/smp-cps.h>
+#include <asm/uasm.h>
+
+/*
+ * cps_nc_entry_fn - type of a generated non-coherent state entry function
+ * @online: the count of online coupled VPEs
+ * @nc_ready_count: pointer to a non-coherent mapping of the core ready_count
+ *
+ * The code entering & exiting non-coherent states is generated at runtime
+ * using uasm, in order to ensure that the compiler cannot insert a stray
+ * memory access at an unfortunate time and to allow the generation of optimal
+ * core-specific code particularly for cache routines. If coupled_coherence
+ * is non-zero and this is the entry function for the CPS_PM_NC_WAIT state,
+ * returns the number of VPEs that were in the wait state at the point this
+ * VPE left it. Returns garbage if coupled_coherence is zero or this is not
+ * the entry function for CPS_PM_NC_WAIT.
+ */
+typedef unsigned (*cps_nc_entry_fn)(unsigned online, u32 *nc_ready_count);
+
+/*
+ * The entry point of the generated non-coherent idle state entry/exit
+ * functions. Actually per-core rather than per-CPU.
+ */
+static DEFINE_PER_CPU_READ_MOSTLY(cps_nc_entry_fn[CPS_PM_STATE_COUNT],
+				  nc_asm_enter);
+
+/* Bitmap indicating which states are supported by the system */
+DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT);
+
+/*
+ * Indicates the number of coupled VPEs ready to operate in a non-coherent
+ * state. Actually per-core rather than per-CPU.
+ */
+static DEFINE_PER_CPU_ALIGNED(u32*, ready_count);
+static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc);
+
+/* Indicates online CPUs coupled with the current CPU */
+static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled);
+
+/*
+ * Used to synchronize entry to deep idle states. Actually per-core rather
+ * than per-CPU.
+ */
+static DEFINE_PER_CPU_ALIGNED(atomic_t, pm_barrier);
+
+/* Saved CPU state across the CPS_PM_POWER_GATED state */
+DEFINE_PER_CPU_ALIGNED(struct mips_static_suspend_state, cps_cpu_state);
+
+/* A somewhat arbitrary number of labels & relocs for uasm */
+static struct uasm_label labels[32] __initdata;
+static struct uasm_reloc relocs[32] __initdata;
+
+/* CPU dependant sync types */
+static unsigned stype_intervention;
+static unsigned stype_memory;
+static unsigned stype_ordering;
+
+enum mips_reg {
+	zero, at, v0, v1, a0, a1, a2, a3,
+	t0, t1, t2, t3, t4, t5, t6, t7,
+	s0, s1, s2, s3, s4, s5, s6, s7,
+	t8, t9, k0, k1, gp, sp, fp, ra,
+};
+
+bool cps_pm_support_state(enum cps_pm_state state)
+{
+	return test_bit(state, state_support);
+}
+
+static void coupled_barrier(atomic_t *a, unsigned online)
+{
+	/*
+	 * This function is effectively the same as
+	 * cpuidle_coupled_parallel_barrier, which can't be used here since
+	 * there's no cpuidle device.
+	 */
+
+	if (!coupled_coherence)
+		return;
+
+	smp_mb__before_atomic();
+	atomic_inc(a);
+
+	while (atomic_read(a) < online)
+		cpu_relax();
+
+	if (atomic_inc_return(a) == online * 2) {
+		atomic_set(a, 0);
+		return;
+	}
+
+	while (atomic_read(a) > online)
+		cpu_relax();
+}
+
+int cps_pm_enter_state(enum cps_pm_state state)
+{
+	unsigned cpu = smp_processor_id();
+	unsigned core = current_cpu_data.core;
+	unsigned online, left;
+	cpumask_t *coupled_mask = this_cpu_ptr(&online_coupled);
+	u32 *core_ready_count, *nc_core_ready_count;
+	void *nc_addr;
+	cps_nc_entry_fn entry;
+	struct core_boot_config *core_cfg;
+	struct vpe_boot_config *vpe_cfg;
+
+	/* Check that there is an entry function for this state */
+	entry = per_cpu(nc_asm_enter, core)[state];
+	if (!entry)
+		return -EINVAL;
+
+	/* Calculate which coupled CPUs (VPEs) are online */
+#ifdef CONFIG_MIPS_MT
+	if (cpu_online(cpu)) {
+		cpumask_and(coupled_mask, cpu_online_mask,
+			    &cpu_sibling_map[cpu]);
+		online = cpumask_weight(coupled_mask);
+		cpumask_clear_cpu(cpu, coupled_mask);
+	} else
+#endif
+	{
+		cpumask_clear(coupled_mask);
+		online = 1;
+	}
+
+	/* Setup the VPE to run mips_cps_pm_restore when started again */
+	if (config_enabled(CONFIG_CPU_PM) && state == CPS_PM_POWER_GATED) {
+		core_cfg = &mips_cps_core_bootcfg[core];
+		vpe_cfg = &core_cfg->vpe_config[current_cpu_data.vpe_id];
+		vpe_cfg->pc = (unsigned long)mips_cps_pm_restore;
+		vpe_cfg->gp = (unsigned long)current_thread_info();
+		vpe_cfg->sp = 0;
+	}
+
+	/* Indicate that this CPU might not be coherent */
+	cpumask_clear_cpu(cpu, &cpu_coherent_mask);
+	smp_mb__after_atomic();
+
+	/* Create a non-coherent mapping of the core ready_count */
+	core_ready_count = per_cpu(ready_count, core);
+	nc_addr = kmap_noncoherent(virt_to_page(core_ready_count),
+				   (unsigned long)core_ready_count);
+	nc_addr += ((unsigned long)core_ready_count & ~PAGE_MASK);
+	nc_core_ready_count = nc_addr;
+
+	/* Ensure ready_count is zero-initialised before the assembly runs */
+	ACCESS_ONCE(*nc_core_ready_count) = 0;
+	coupled_barrier(&per_cpu(pm_barrier, core), online);
+
+	/* Run the generated entry code */
+	left = entry(online, nc_core_ready_count);
+
+	/* Remove the non-coherent mapping of ready_count */
+	kunmap_noncoherent();
+
+	/* Indicate that this CPU is definitely coherent */
+	cpumask_set_cpu(cpu, &cpu_coherent_mask);
+
+	/*
+	 * If this VPE is the first to leave the non-coherent wait state then
+	 * it needs to wake up any coupled VPEs still running their wait
+	 * instruction so that they return to cpuidle, which can then complete
+	 * coordination between the coupled VPEs & provide the governor with
+	 * a chance to reflect on the length of time the VPEs were in the
+	 * idle state.
+	 */
+	if (coupled_coherence && (state == CPS_PM_NC_WAIT) && (left == online))
+		arch_send_call_function_ipi_mask(coupled_mask);
+
+	return 0;
+}
+
+static void __init cps_gen_cache_routine(u32 **pp, struct uasm_label **pl,
+					 struct uasm_reloc **pr,
+					 const struct cache_desc *cache,
+					 unsigned op, int lbl)
+{
+	unsigned cache_size = cache->ways << cache->waybit;
+	unsigned i;
+	const unsigned unroll_lines = 32;
+
+	/* If the cache isn't present this function has it easy */
+	if (cache->flags & MIPS_CACHE_NOT_PRESENT)
+		return;
+
+	/* Load base address */
+	UASM_i_LA(pp, t0, (long)CKSEG0);
+
+	/* Calculate end address */
+	if (cache_size < 0x8000)
+		uasm_i_addiu(pp, t1, t0, cache_size);
+	else
+		UASM_i_LA(pp, t1, (long)(CKSEG0 + cache_size));
+
+	/* Start of cache op loop */
+	uasm_build_label(pl, *pp, lbl);
+
+	/* Generate the cache ops */
+	for (i = 0; i < unroll_lines; i++)
+		uasm_i_cache(pp, op, i * cache->linesz, t0);
+
+	/* Update the base address */
+	uasm_i_addiu(pp, t0, t0, unroll_lines * cache->linesz);
+
+	/* Loop if we haven't reached the end address yet */
+	uasm_il_bne(pp, pr, t0, t1, lbl);
+	uasm_i_nop(pp);
+}
+
+static int __init cps_gen_flush_fsb(u32 **pp, struct uasm_label **pl,
+				    struct uasm_reloc **pr,
+				    const struct cpuinfo_mips *cpu_info,
+				    int lbl)
+{
+	unsigned i, fsb_size = 8;
+	unsigned num_loads = (fsb_size * 3) / 2;
+	unsigned line_stride = 2;
+	unsigned line_size = cpu_info->dcache.linesz;
+	unsigned perf_counter, perf_event;
+	unsigned revision = cpu_info->processor_id & PRID_REV_MASK;
+
+	/*
+	 * Determine whether this CPU requires an FSB flush, and if so which
+	 * performance counter/event reflect stalls due to a full FSB.
+	 */
+	switch (__get_cpu_type(cpu_info->cputype)) {
+	case CPU_INTERAPTIV:
+		perf_counter = 1;
+		perf_event = 51;
+		break;
+
+	case CPU_PROAPTIV:
+		/* Newer proAptiv cores don't require this workaround */
+		if (revision >= PRID_REV_ENCODE_332(1, 1, 0))
+			return 0;
+
+		/* On older ones it's unavailable */
+		return -1;
+
+	/* CPUs which do not require the workaround */
+	case CPU_P5600:
+		return 0;
+
+	default:
+		WARN_ONCE(1, "pm-cps: FSB flush unsupported for this CPU\n");
+		return -1;
+	}
+
+	/*
+	 * Ensure that the fill/store buffer (FSB) is not holding the results
+	 * of a prefetch, since if it is then the CPC sequencer may become
+	 * stuck in the D3 (ClrBus) state whilst entering a low power state.
+	 */
+
+	/* Preserve perf counter setup */
+	uasm_i_mfc0(pp, t2, 25, (perf_counter * 2) + 0); /* PerfCtlN */
+	uasm_i_mfc0(pp, t3, 25, (perf_counter * 2) + 1); /* PerfCntN */
+
+	/* Setup perf counter to count FSB full pipeline stalls */
+	uasm_i_addiu(pp, t0, zero, (perf_event << 5) | 0xf);
+	uasm_i_mtc0(pp, t0, 25, (perf_counter * 2) + 0); /* PerfCtlN */
+	uasm_i_ehb(pp);
+	uasm_i_mtc0(pp, zero, 25, (perf_counter * 2) + 1); /* PerfCntN */
+	uasm_i_ehb(pp);
+
+	/* Base address for loads */
+	UASM_i_LA(pp, t0, (long)CKSEG0);
+
+	/* Start of clear loop */
+	uasm_build_label(pl, *pp, lbl);
+
+	/* Perform some loads to fill the FSB */
+	for (i = 0; i < num_loads; i++)
+		uasm_i_lw(pp, zero, i * line_size * line_stride, t0);
+
+	/*
+	 * Invalidate the new D-cache entries so that the cache will need
+	 * refilling (via the FSB) if the loop is executed again.
+	 */
+	for (i = 0; i < num_loads; i++) {
+		uasm_i_cache(pp, Hit_Invalidate_D,
+			     i * line_size * line_stride, t0);
+		uasm_i_cache(pp, Hit_Writeback_Inv_SD,
+			     i * line_size * line_stride, t0);
+	}
+
+	/* Completion barrier */
+	uasm_i_sync(pp, stype_memory);
+	uasm_i_ehb(pp);
+
+	/* Check whether the pipeline stalled due to the FSB being full */
+	uasm_i_mfc0(pp, t1, 25, (perf_counter * 2) + 1); /* PerfCntN */
+
+	/* Loop if it didn't */
+	uasm_il_beqz(pp, pr, t1, lbl);
+	uasm_i_nop(pp);
+
+	/* Restore perf counter 1. The count may well now be wrong... */
+	uasm_i_mtc0(pp, t2, 25, (perf_counter * 2) + 0); /* PerfCtlN */
+	uasm_i_ehb(pp);
+	uasm_i_mtc0(pp, t3, 25, (perf_counter * 2) + 1); /* PerfCntN */
+	uasm_i_ehb(pp);
+
+	return 0;
+}
+
+static void __init cps_gen_set_top_bit(u32 **pp, struct uasm_label **pl,
+				       struct uasm_reloc **pr,
+				       unsigned r_addr, int lbl)
+{
+	uasm_i_lui(pp, t0, uasm_rel_hi(0x80000000));
+	uasm_build_label(pl, *pp, lbl);
+	uasm_i_ll(pp, t1, 0, r_addr);
+	uasm_i_or(pp, t1, t1, t0);
+	uasm_i_sc(pp, t1, 0, r_addr);
+	uasm_il_beqz(pp, pr, t1, lbl);
+	uasm_i_nop(pp);
+}
+
+static void * __init cps_gen_entry_code(unsigned cpu, enum cps_pm_state state)
+{
+	struct uasm_label *l = labels;
+	struct uasm_reloc *r = relocs;
+	u32 *buf, *p;
+	const unsigned r_online = a0;
+	const unsigned r_nc_count = a1;
+	const unsigned r_pcohctl = t7;
+	const unsigned max_instrs = 256;
+	unsigned cpc_cmd;
+	int err;
+	enum {
+		lbl_incready = 1,
+		lbl_poll_cont,
+		lbl_secondary_hang,
+		lbl_disable_coherence,
+		lbl_flush_fsb,
+		lbl_invicache,
+		lbl_flushdcache,
+		lbl_hang,
+		lbl_set_cont,
+		lbl_secondary_cont,
+		lbl_decready,
+	};
+
+	/* Allocate a buffer to hold the generated code */
+	p = buf = kcalloc(max_instrs, sizeof(u32), GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	/* Clear labels & relocs ready for (re)use */
+	memset(labels, 0, sizeof(labels));
+	memset(relocs, 0, sizeof(relocs));
+
+	if (config_enabled(CONFIG_CPU_PM) && state == CPS_PM_POWER_GATED) {
+		/*
+		 * Save CPU state. Note the non-standard calling convention
+		 * with the return address placed in v0 to avoid clobbering
+		 * the ra register before it is saved.
+		 */
+		UASM_i_LA(&p, t0, (long)mips_cps_pm_save);
+		uasm_i_jalr(&p, v0, t0);
+		uasm_i_nop(&p);
+	}
+
+	/*
+	 * Load addresses of required CM & CPC registers. This is done early
+	 * because they're needed in both the enable & disable coherence steps
+	 * but in the coupled case the enable step will only run on one VPE.
+	 */
+	UASM_i_LA(&p, r_pcohctl, (long)addr_gcr_cl_coherence());
+
+	if (coupled_coherence) {
+		/* Increment ready_count */
+		uasm_i_sync(&p, stype_ordering);
+		uasm_build_label(&l, p, lbl_incready);
+		uasm_i_ll(&p, t1, 0, r_nc_count);
+		uasm_i_addiu(&p, t2, t1, 1);
+		uasm_i_sc(&p, t2, 0, r_nc_count);
+		uasm_il_beqz(&p, &r, t2, lbl_incready);
+		uasm_i_addiu(&p, t1, t1, 1);
+
+		/* Ordering barrier */
+		uasm_i_sync(&p, stype_ordering);
+
+		/*
+		 * If this is the last VPE to become ready for non-coherence
+		 * then it should branch below.
+		 */
+		uasm_il_beq(&p, &r, t1, r_online, lbl_disable_coherence);
+		uasm_i_nop(&p);
+
+		if (state < CPS_PM_POWER_GATED) {
+			/*
+			 * Otherwise this is not the last VPE to become ready
+			 * for non-coherence. It needs to wait until coherence
+			 * has been disabled before proceeding, which it will do
+			 * by polling for the top bit of ready_count being set.
+			 */
+			uasm_i_addiu(&p, t1, zero, -1);
+			uasm_build_label(&l, p, lbl_poll_cont);
+			uasm_i_lw(&p, t0, 0, r_nc_count);
+			uasm_il_bltz(&p, &r, t0, lbl_secondary_cont);
+			uasm_i_ehb(&p);
+			uasm_i_yield(&p, zero, t1);
+			uasm_il_b(&p, &r, lbl_poll_cont);
+			uasm_i_nop(&p);
+		} else {
+			/*
+			 * The core will lose power & this VPE will not continue
+			 * so it can simply halt here.
+			 */
+			uasm_i_addiu(&p, t0, zero, TCHALT_H);
+			uasm_i_mtc0(&p, t0, 2, 4);
+			uasm_build_label(&l, p, lbl_secondary_hang);
+			uasm_il_b(&p, &r, lbl_secondary_hang);
+			uasm_i_nop(&p);
+		}
+	}
+
+	/*
+	 * This is the point of no return - this VPE will now proceed to
+	 * disable coherence. At this point we *must* be sure that no other
+	 * VPE within the core will interfere with the L1 dcache.
+	 */
+	uasm_build_label(&l, p, lbl_disable_coherence);
+
+	/* Invalidate the L1 icache */
+	cps_gen_cache_routine(&p, &l, &r, &cpu_data[cpu].icache,
+			      Index_Invalidate_I, lbl_invicache);
+
+	/* Writeback & invalidate the L1 dcache */
+	cps_gen_cache_routine(&p, &l, &r, &cpu_data[cpu].dcache,
+			      Index_Writeback_Inv_D, lbl_flushdcache);
+
+	/* Completion barrier */
+	uasm_i_sync(&p, stype_memory);
+	uasm_i_ehb(&p);
+
+	/*
+	 * Disable all but self interventions. The load from COHCTL is defined
+	 * by the interAptiv & proAptiv SUMs as ensuring that the operation
+	 * resulting from the preceeding store is complete.
+	 */
+	uasm_i_addiu(&p, t0, zero, 1 << cpu_data[cpu].core);
+	uasm_i_sw(&p, t0, 0, r_pcohctl);
+	uasm_i_lw(&p, t0, 0, r_pcohctl);
+
+	/* Sync to ensure previous interventions are complete */
+	uasm_i_sync(&p, stype_intervention);
+	uasm_i_ehb(&p);
+
+	/* Disable coherence */
+	uasm_i_sw(&p, zero, 0, r_pcohctl);
+	uasm_i_lw(&p, t0, 0, r_pcohctl);
+
+	if (state >= CPS_PM_CLOCK_GATED) {
+		err = cps_gen_flush_fsb(&p, &l, &r, &cpu_data[cpu],
+					lbl_flush_fsb);
+		if (err)
+			goto out_err;
+
+		/* Determine the CPC command to issue */
+		switch (state) {
+		case CPS_PM_CLOCK_GATED:
+			cpc_cmd = CPC_Cx_CMD_CLOCKOFF;
+			break;
+		case CPS_PM_POWER_GATED:
+			cpc_cmd = CPC_Cx_CMD_PWRDOWN;
+			break;
+		default:
+			BUG();
+			goto out_err;
+		}
+
+		/* Issue the CPC command */
+		UASM_i_LA(&p, t0, (long)addr_cpc_cl_cmd());
+		uasm_i_addiu(&p, t1, zero, cpc_cmd);
+		uasm_i_sw(&p, t1, 0, t0);
+
+		if (state == CPS_PM_POWER_GATED) {
+			/* If anything goes wrong just hang */
+			uasm_build_label(&l, p, lbl_hang);
+			uasm_il_b(&p, &r, lbl_hang);
+			uasm_i_nop(&p);
+
+			/*
+			 * There's no point generating more code, the core is
+			 * powered down & if powered back up will run from the
+			 * reset vector not from here.
+			 */
+			goto gen_done;
+		}
+
+		/* Completion barrier */
+		uasm_i_sync(&p, stype_memory);
+		uasm_i_ehb(&p);
+	}
+
+	if (state == CPS_PM_NC_WAIT) {
+		/*
+		 * At this point it is safe for all VPEs to proceed with
+		 * execution. This VPE will set the top bit of ready_count
+		 * to indicate to the other VPEs that they may continue.
+		 */
+		if (coupled_coherence)
+			cps_gen_set_top_bit(&p, &l, &r, r_nc_count,
+					    lbl_set_cont);
+
+		/*
+		 * VPEs which did not disable coherence will continue
+		 * executing, after coherence has been disabled, from this
+		 * point.
+		 */
+		uasm_build_label(&l, p, lbl_secondary_cont);
+
+		/* Now perform our wait */
+		uasm_i_wait(&p, 0);
+	}
+
+	/*
+	 * Re-enable coherence. Note that for CPS_PM_NC_WAIT all coupled VPEs
+	 * will run this. The first will actually re-enable coherence & the
+	 * rest will just be performing a rather unusual nop.
+	 */
+	uasm_i_addiu(&p, t0, zero, CM_GCR_Cx_COHERENCE_COHDOMAINEN_MSK);
+	uasm_i_sw(&p, t0, 0, r_pcohctl);
+	uasm_i_lw(&p, t0, 0, r_pcohctl);
+
+	/* Completion barrier */
+	uasm_i_sync(&p, stype_memory);
+	uasm_i_ehb(&p);
+
+	if (coupled_coherence && (state == CPS_PM_NC_WAIT)) {
+		/* Decrement ready_count */
+		uasm_build_label(&l, p, lbl_decready);
+		uasm_i_sync(&p, stype_ordering);
+		uasm_i_ll(&p, t1, 0, r_nc_count);
+		uasm_i_addiu(&p, t2, t1, -1);
+		uasm_i_sc(&p, t2, 0, r_nc_count);
+		uasm_il_beqz(&p, &r, t2, lbl_decready);
+		uasm_i_andi(&p, v0, t1, (1 << fls(smp_num_siblings)) - 1);
+
+		/* Ordering barrier */
+		uasm_i_sync(&p, stype_ordering);
+	}
+
+	if (coupled_coherence && (state == CPS_PM_CLOCK_GATED)) {
+		/*
+		 * At this point it is safe for all VPEs to proceed with
+		 * execution. This VPE will set the top bit of ready_count
+		 * to indicate to the other VPEs that they may continue.
+		 */
+		cps_gen_set_top_bit(&p, &l, &r, r_nc_count, lbl_set_cont);
+
+		/*
+		 * This core will be reliant upon another core sending a
+		 * power-up command to the CPC in order to resume operation.
+		 * Thus an arbitrary VPE can't trigger the core leaving the
+		 * idle state and the one that disables coherence might as well
+		 * be the one to re-enable it. The rest will continue from here
+		 * after that has been done.
+		 */
+		uasm_build_label(&l, p, lbl_secondary_cont);
+
+		/* Ordering barrier */
+		uasm_i_sync(&p, stype_ordering);
+	}
+
+	/* The core is coherent, time to return to C code */
+	uasm_i_jr(&p, ra);
+	uasm_i_nop(&p);
+
+gen_done:
+	/* Ensure the code didn't exceed the resources allocated for it */
+	BUG_ON((p - buf) > max_instrs);
+	BUG_ON((l - labels) > ARRAY_SIZE(labels));
+	BUG_ON((r - relocs) > ARRAY_SIZE(relocs));
+
+	/* Patch branch offsets */
+	uasm_resolve_relocs(relocs, labels);
+
+	/* Flush the icache */
+	local_flush_icache_range((unsigned long)buf, (unsigned long)p);
+
+	return buf;
+out_err:
+	kfree(buf);
+	return NULL;
+}
+
+static int __init cps_gen_core_entries(unsigned cpu)
+{
+	enum cps_pm_state state;
+	unsigned core = cpu_data[cpu].core;
+	unsigned dlinesz = cpu_data[cpu].dcache.linesz;
+	void *entry_fn, *core_rc;
+
+	for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) {
+		if (per_cpu(nc_asm_enter, core)[state])
+			continue;
+		if (!test_bit(state, state_support))
+			continue;
+
+		entry_fn = cps_gen_entry_code(cpu, state);
+		if (!entry_fn) {
+			pr_err("Failed to generate core %u state %u entry\n",
+			       core, state);
+			clear_bit(state, state_support);
+		}
+
+		per_cpu(nc_asm_enter, core)[state] = entry_fn;
+	}
+
+	if (!per_cpu(ready_count, core)) {
+		core_rc = kmalloc(dlinesz * 2, GFP_KERNEL);
+		if (!core_rc) {
+			pr_err("Failed allocate core %u ready_count\n", core);
+			return -ENOMEM;
+		}
+		per_cpu(ready_count_alloc, core) = core_rc;
+
+		/* Ensure ready_count is aligned to a cacheline boundary */
+		core_rc += dlinesz - 1;
+		core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1));
+		per_cpu(ready_count, core) = core_rc;
+	}
+
+	return 0;
+}
+
+static int __init cps_pm_init(void)
+{
+	unsigned cpu;
+	int err;
+
+	/* Detect appropriate sync types for the system */
+	switch (current_cpu_data.cputype) {
+	case CPU_INTERAPTIV:
+	case CPU_PROAPTIV:
+	case CPU_M5150:
+	case CPU_P5600:
+		stype_intervention = 0x2;
+		stype_memory = 0x3;
+		stype_ordering = 0x10;
+		break;
+
+	default:
+		pr_warn("Power management is using heavyweight sync 0\n");
+	}
+
+	/* A CM is required for all non-coherent states */
+	if (!mips_cm_present()) {
+		pr_warn("pm-cps: no CM, non-coherent states unavailable\n");
+		goto out;
+	}
+
+	/*
+	 * If interrupts were enabled whilst running a wait instruction on a
+	 * non-coherent core then the VPE may end up processing interrupts
+	 * whilst non-coherent. That would be bad.
+	 */
+	if (cpu_wait == r4k_wait_irqoff)
+		set_bit(CPS_PM_NC_WAIT, state_support);
+	else
+		pr_warn("pm-cps: non-coherent wait unavailable\n");
+
+	/* Detect whether a CPC is present */
+	if (mips_cpc_present()) {
+		/* Detect whether clock gating is implemented */
+		if (read_cpc_cl_stat_conf() & CPC_Cx_STAT_CONF_CLKGAT_IMPL_MSK)
+			set_bit(CPS_PM_CLOCK_GATED, state_support);
+		else
+			pr_warn("pm-cps: CPC does not support clock gating\n");
+
+		/* Power gating is available with CPS SMP & any CPC */
+		if (mips_cps_smp_in_use())
+			set_bit(CPS_PM_POWER_GATED, state_support);
+		else
+			pr_warn("pm-cps: CPS SMP not in use, power gating unavailable\n");
+	} else {
+		pr_warn("pm-cps: no CPC, clock & power gating unavailable\n");
+	}
+
+	for_each_present_cpu(cpu) {
+		err = cps_gen_core_entries(cpu);
+		if (err)
+			return err;
+	}
+out:
+	return 0;
+}
+arch_initcall(cps_pm_init);
diff --git a/arch/mips/kernel/pm.c b/arch/mips/kernel/pm.c
new file mode 100644
index 00000000000..fefdf39d3df
--- /dev/null
+++ b/arch/mips/kernel/pm.c
@@ -0,0 +1,99 @@
+/*
+ * Copyright (C) 2014 Imagination Technologies Ltd.
+ *
+ * This program is free software; you can redistribute	it and/or modify it
+ * under  the terms of	the GNU General	 Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * CPU PM notifiers for saving/restoring general CPU state.
+ */
+
+#include <linux/cpu_pm.h>
+#include <linux/init.h>
+
+#include <asm/dsp.h>
+#include <asm/fpu.h>
+#include <asm/mmu_context.h>
+#include <asm/pm.h>
+#include <asm/watch.h>
+
+/* Used by PM helper macros in asm/pm.h */
+struct mips_static_suspend_state mips_static_suspend_state;
+
+/**
+ * mips_cpu_save() - Save general CPU state.
+ * Ensures that general CPU context is saved, notably FPU and DSP.
+ */
+static int mips_cpu_save(void)
+{
+	/* Save FPU state */
+	lose_fpu(1);
+
+	/* Save DSP state */
+	save_dsp(current);
+
+	return 0;
+}
+
+/**
+ * mips_cpu_restore() - Restore general CPU state.
+ * Restores important CPU context.
+ */
+static void mips_cpu_restore(void)
+{
+	unsigned int cpu = smp_processor_id();
+
+	/* Restore ASID */
+	if (current->mm)
+		write_c0_entryhi(cpu_asid(cpu, current->mm));
+
+	/* Restore DSP state */
+	restore_dsp(current);
+
+	/* Restore UserLocal */
+	if (cpu_has_userlocal)
+		write_c0_userlocal(current_thread_info()->tp_value);
+
+	/* Restore watch registers */
+	__restore_watch();
+}
+
+/**
+ * mips_pm_notifier() - Notifier for preserving general CPU context.
+ * @self:	Notifier block.
+ * @cmd:	CPU PM event.
+ * @v:		Private data (unused).
+ *
+ * This is called when a CPU power management event occurs, and is used to
+ * ensure that important CPU context is preserved across a CPU power down.
+ */
+static int mips_pm_notifier(struct notifier_block *self, unsigned long cmd,
+			    void *v)
+{
+	int ret;
+
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		ret = mips_cpu_save();
+		if (ret)
+			return NOTIFY_STOP;
+		break;
+	case CPU_PM_ENTER_FAILED:
+	case CPU_PM_EXIT:
+		mips_cpu_restore();
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block mips_pm_notifier_block = {
+	.notifier_call = mips_pm_notifier,
+};
+
+static int __init mips_pm_init(void)
+{
+	return cpu_pm_register_notifier(&mips_pm_notifier_block);
+}
+arch_initcall(mips_pm_init);
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 60e39dc7f1e..0a1ec0f3bef 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -140,13 +140,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	 */
 	childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * SMTC restores TCStatus after Status, and the CU bits
-	 * are aliased there.
-	 */
-	childregs->cp0_tcstatus &= ~(ST0_CU2|ST0_CU1);
-#endif
 	clear_tsk_thread_flag(p, TIF_USEDFPU);
 
 #ifdef CONFIG_MIPS_MT_FPAFF
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 71814272d14..8352523568e 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -13,7 +13,6 @@
  * Copyright (C) 1999, 2001 Silicon Graphics, Inc.
  */
 #include <asm/asm.h>
-#include <asm/asmmacro.h>
 #include <asm/errno.h>
 #include <asm/fpregdef.h>
 #include <asm/mipsregs.h>
@@ -246,218 +245,6 @@ LEAF(_restore_fp_context32)
 	END(_restore_fp_context32)
 #endif
 
-#ifdef CONFIG_CPU_HAS_MSA
-
-	.macro	save_sc_msareg	wr, off, sc, tmp
-#ifdef CONFIG_64BIT
-	copy_u_d \tmp, \wr, 1
-	EX sd	\tmp, (\off+(\wr*8))(\sc)
-#elif defined(CONFIG_CPU_LITTLE_ENDIAN)
-	copy_u_w \tmp, \wr, 2
-	EX sw	\tmp, (\off+(\wr*8)+0)(\sc)
-	copy_u_w \tmp, \wr, 3
-	EX sw	\tmp, (\off+(\wr*8)+4)(\sc)
-#else /* CONFIG_CPU_BIG_ENDIAN */
-	copy_u_w \tmp, \wr, 2
-	EX sw	\tmp, (\off+(\wr*8)+4)(\sc)
-	copy_u_w \tmp, \wr, 3
-	EX sw	\tmp, (\off+(\wr*8)+0)(\sc)
-#endif
-	.endm
-
-/*
- * int _save_msa_context(struct sigcontext *sc)
- *
- * Save the upper 64 bits of each vector register along with the MSA_CSR
- * register into sc. Returns zero on success, else non-zero.
- */
-LEAF(_save_msa_context)
-	save_sc_msareg	0, SC_MSAREGS, a0, t0
-	save_sc_msareg	1, SC_MSAREGS, a0, t0
-	save_sc_msareg	2, SC_MSAREGS, a0, t0
-	save_sc_msareg	3, SC_MSAREGS, a0, t0
-	save_sc_msareg	4, SC_MSAREGS, a0, t0
-	save_sc_msareg	5, SC_MSAREGS, a0, t0
-	save_sc_msareg	6, SC_MSAREGS, a0, t0
-	save_sc_msareg	7, SC_MSAREGS, a0, t0
-	save_sc_msareg	8, SC_MSAREGS, a0, t0
-	save_sc_msareg	9, SC_MSAREGS, a0, t0
-	save_sc_msareg	10, SC_MSAREGS, a0, t0
-	save_sc_msareg	11, SC_MSAREGS, a0, t0
-	save_sc_msareg	12, SC_MSAREGS, a0, t0
-	save_sc_msareg	13, SC_MSAREGS, a0, t0
-	save_sc_msareg	14, SC_MSAREGS, a0, t0
-	save_sc_msareg	15, SC_MSAREGS, a0, t0
-	save_sc_msareg	16, SC_MSAREGS, a0, t0
-	save_sc_msareg	17, SC_MSAREGS, a0, t0
-	save_sc_msareg	18, SC_MSAREGS, a0, t0
-	save_sc_msareg	19, SC_MSAREGS, a0, t0
-	save_sc_msareg	20, SC_MSAREGS, a0, t0
-	save_sc_msareg	21, SC_MSAREGS, a0, t0
-	save_sc_msareg	22, SC_MSAREGS, a0, t0
-	save_sc_msareg	23, SC_MSAREGS, a0, t0
-	save_sc_msareg	24, SC_MSAREGS, a0, t0
-	save_sc_msareg	25, SC_MSAREGS, a0, t0
-	save_sc_msareg	26, SC_MSAREGS, a0, t0
-	save_sc_msareg	27, SC_MSAREGS, a0, t0
-	save_sc_msareg	28, SC_MSAREGS, a0, t0
-	save_sc_msareg	29, SC_MSAREGS, a0, t0
-	save_sc_msareg	30, SC_MSAREGS, a0, t0
-	save_sc_msareg	31, SC_MSAREGS, a0, t0
-	jr	ra
-	 li	v0, 0
-	END(_save_msa_context)
-
-#ifdef CONFIG_MIPS32_COMPAT
-
-/*
- * int _save_msa_context32(struct sigcontext32 *sc)
- *
- * Save the upper 64 bits of each vector register along with the MSA_CSR
- * register into sc. Returns zero on success, else non-zero.
- */
-LEAF(_save_msa_context32)
-	save_sc_msareg	0, SC32_MSAREGS, a0, t0
-	save_sc_msareg	1, SC32_MSAREGS, a0, t0
-	save_sc_msareg	2, SC32_MSAREGS, a0, t0
-	save_sc_msareg	3, SC32_MSAREGS, a0, t0
-	save_sc_msareg	4, SC32_MSAREGS, a0, t0
-	save_sc_msareg	5, SC32_MSAREGS, a0, t0
-	save_sc_msareg	6, SC32_MSAREGS, a0, t0
-	save_sc_msareg	7, SC32_MSAREGS, a0, t0
-	save_sc_msareg	8, SC32_MSAREGS, a0, t0
-	save_sc_msareg	9, SC32_MSAREGS, a0, t0
-	save_sc_msareg	10, SC32_MSAREGS, a0, t0
-	save_sc_msareg	11, SC32_MSAREGS, a0, t0
-	save_sc_msareg	12, SC32_MSAREGS, a0, t0
-	save_sc_msareg	13, SC32_MSAREGS, a0, t0
-	save_sc_msareg	14, SC32_MSAREGS, a0, t0
-	save_sc_msareg	15, SC32_MSAREGS, a0, t0
-	save_sc_msareg	16, SC32_MSAREGS, a0, t0
-	save_sc_msareg	17, SC32_MSAREGS, a0, t0
-	save_sc_msareg	18, SC32_MSAREGS, a0, t0
-	save_sc_msareg	19, SC32_MSAREGS, a0, t0
-	save_sc_msareg	20, SC32_MSAREGS, a0, t0
-	save_sc_msareg	21, SC32_MSAREGS, a0, t0
-	save_sc_msareg	22, SC32_MSAREGS, a0, t0
-	save_sc_msareg	23, SC32_MSAREGS, a0, t0
-	save_sc_msareg	24, SC32_MSAREGS, a0, t0
-	save_sc_msareg	25, SC32_MSAREGS, a0, t0
-	save_sc_msareg	26, SC32_MSAREGS, a0, t0
-	save_sc_msareg	27, SC32_MSAREGS, a0, t0
-	save_sc_msareg	28, SC32_MSAREGS, a0, t0
-	save_sc_msareg	29, SC32_MSAREGS, a0, t0
-	save_sc_msareg	30, SC32_MSAREGS, a0, t0
-	save_sc_msareg	31, SC32_MSAREGS, a0, t0
-	jr	ra
-	 li	v0, 0
-	END(_save_msa_context32)
-
-#endif /* CONFIG_MIPS32_COMPAT */
-
-	.macro restore_sc_msareg	wr, off, sc, tmp
-#ifdef CONFIG_64BIT
-	EX ld	\tmp, (\off+(\wr*8))(\sc)
-	insert_d \wr, 1, \tmp
-#elif defined(CONFIG_CPU_LITTLE_ENDIAN)
-	EX lw	\tmp, (\off+(\wr*8)+0)(\sc)
-	insert_w \wr, 2, \tmp
-	EX lw	\tmp, (\off+(\wr*8)+4)(\sc)
-	insert_w \wr, 3, \tmp
-#else /* CONFIG_CPU_BIG_ENDIAN */
-	EX lw	\tmp, (\off+(\wr*8)+4)(\sc)
-	insert_w \wr, 2, \tmp
-	EX lw	\tmp, (\off+(\wr*8)+0)(\sc)
-	insert_w \wr, 3, \tmp
-#endif
-	.endm
-
-/*
- * int _restore_msa_context(struct sigcontext *sc)
- */
-LEAF(_restore_msa_context)
-	restore_sc_msareg	0, SC_MSAREGS, a0, t0
-	restore_sc_msareg	1, SC_MSAREGS, a0, t0
-	restore_sc_msareg	2, SC_MSAREGS, a0, t0
-	restore_sc_msareg	3, SC_MSAREGS, a0, t0
-	restore_sc_msareg	4, SC_MSAREGS, a0, t0
-	restore_sc_msareg	5, SC_MSAREGS, a0, t0
-	restore_sc_msareg	6, SC_MSAREGS, a0, t0
-	restore_sc_msareg	7, SC_MSAREGS, a0, t0
-	restore_sc_msareg	8, SC_MSAREGS, a0, t0
-	restore_sc_msareg	9, SC_MSAREGS, a0, t0
-	restore_sc_msareg	10, SC_MSAREGS, a0, t0
-	restore_sc_msareg	11, SC_MSAREGS, a0, t0
-	restore_sc_msareg	12, SC_MSAREGS, a0, t0
-	restore_sc_msareg	13, SC_MSAREGS, a0, t0
-	restore_sc_msareg	14, SC_MSAREGS, a0, t0
-	restore_sc_msareg	15, SC_MSAREGS, a0, t0
-	restore_sc_msareg	16, SC_MSAREGS, a0, t0
-	restore_sc_msareg	17, SC_MSAREGS, a0, t0
-	restore_sc_msareg	18, SC_MSAREGS, a0, t0
-	restore_sc_msareg	19, SC_MSAREGS, a0, t0
-	restore_sc_msareg	20, SC_MSAREGS, a0, t0
-	restore_sc_msareg	21, SC_MSAREGS, a0, t0
-	restore_sc_msareg	22, SC_MSAREGS, a0, t0
-	restore_sc_msareg	23, SC_MSAREGS, a0, t0
-	restore_sc_msareg	24, SC_MSAREGS, a0, t0
-	restore_sc_msareg	25, SC_MSAREGS, a0, t0
-	restore_sc_msareg	26, SC_MSAREGS, a0, t0
-	restore_sc_msareg	27, SC_MSAREGS, a0, t0
-	restore_sc_msareg	28, SC_MSAREGS, a0, t0
-	restore_sc_msareg	29, SC_MSAREGS, a0, t0
-	restore_sc_msareg	30, SC_MSAREGS, a0, t0
-	restore_sc_msareg	31, SC_MSAREGS, a0, t0
-	jr	ra
-	 li	v0, 0
-	END(_restore_msa_context)
-
-#ifdef CONFIG_MIPS32_COMPAT
-
-/*
- * int _restore_msa_context32(struct sigcontext32 *sc)
- */
-LEAF(_restore_msa_context32)
-	restore_sc_msareg	0, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	1, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	2, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	3, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	4, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	5, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	6, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	7, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	8, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	9, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	10, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	11, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	12, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	13, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	14, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	15, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	16, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	17, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	18, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	19, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	20, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	21, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	22, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	23, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	24, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	25, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	26, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	27, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	28, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	29, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	30, SC32_MSAREGS, a0, t0
-	restore_sc_msareg	31, SC32_MSAREGS, a0, t0
-	jr	ra
-	 li	v0, 0
-	END(_restore_msa_context32)
-
-#endif /* CONFIG_MIPS32_COMPAT */
-
-#endif /* CONFIG_CPU_HAS_MSA */
-
 	.set	reorder
 
 	.type	fault@function
diff --git a/arch/mips/kernel/r4k_switch.S b/arch/mips/kernel/r4k_switch.S
index abacac7c33e..81ca3f70fe2 100644
--- a/arch/mips/kernel/r4k_switch.S
+++ b/arch/mips/kernel/r4k_switch.S
@@ -28,6 +28,7 @@
  */
 #define ST_OFF (_THREAD_SIZE - 32 - PT_SIZE + PT_STATUS)
 
+#ifndef USE_ALTERNATE_RESUME_IMPL
 /*
  * task_struct *resume(task_struct *prev, task_struct *next,
  *		       struct thread_info *next_ti, s32 fp_save)
@@ -87,18 +88,6 @@
 
 	PTR_ADDU	t0, $28, _THREAD_SIZE - 32
 	set_saved_sp	t0, t1, t2
-#ifdef CONFIG_MIPS_MT_SMTC
-	/* Read-modify-writes of Status must be atomic on a VPE */
-	mfc0	t2, CP0_TCSTATUS
-	ori	t1, t2, TCSTATUS_IXMT
-	mtc0	t1, CP0_TCSTATUS
-	andi	t2, t2, TCSTATUS_IXMT
-	_ehb
-	DMT	8				# dmt	t0
-	move	t1,ra
-	jal	mips_ihb
-	move	ra,t1
-#endif /* CONFIG_MIPS_MT_SMTC */
 	mfc0	t1, CP0_STATUS		/* Do we really need this? */
 	li	a3, 0xff01
 	and	t1, a3
@@ -107,22 +96,12 @@
 	and	a2, a3
 	or	a2, t1
 	mtc0	a2, CP0_STATUS
-#ifdef CONFIG_MIPS_MT_SMTC
-	_ehb
-	andi	t0, t0, VPECONTROL_TE
-	beqz	t0, 1f
-	emt
-1:
-	mfc0	t1, CP0_TCSTATUS
-	xori	t1, t1, TCSTATUS_IXMT
-	or	t1, t1, t2
-	mtc0	t1, CP0_TCSTATUS
-	_ehb
-#endif /* CONFIG_MIPS_MT_SMTC */
 	move	v0, a0
 	jr	ra
 	END(resume)
 
+#endif /* USE_ALTERNATE_RESUME_IMPL */
+
 /*
  * Save a thread's fp context.
  */
@@ -176,19 +155,10 @@ LEAF(_restore_msa)
 #define FPU_DEFAULT  0x00000000
 
 LEAF(_init_fpu)
-#ifdef CONFIG_MIPS_MT_SMTC
-	/* Rather than manipulate per-VPE Status, set per-TC bit in TCStatus */
-	mfc0	t0, CP0_TCSTATUS
-	/* Bit position is the same for Status, TCStatus */
-	li	t1, ST0_CU1
-	or	t0, t1
-	mtc0	t0, CP0_TCSTATUS
-#else /* Normal MIPS CU1 enable */
 	mfc0	t0, CP0_STATUS
 	li	t1, ST0_CU1
 	or	t0, t1
 	mtc0	t0, CP0_STATUS
-#endif /* CONFIG_MIPS_MT_SMTC */
 	enable_fpu_hazard
 
 	li	t1, FPU_DEFAULT
diff --git a/arch/mips/kernel/rtlx-mt.c b/arch/mips/kernel/rtlx-mt.c
index 9c1aca00fd5..5a66b975989 100644
--- a/arch/mips/kernel/rtlx-mt.c
+++ b/arch/mips/kernel/rtlx-mt.c
@@ -36,7 +36,6 @@ static irqreturn_t rtlx_interrupt(int irq, void *dev_id)
 	unsigned long flags;
 	int i;
 
-	/* Ought not to be strictly necessary for SMTC builds */
 	local_irq_save(flags);
 	vpeflags = dvpe();
 	set_c0_status(0x100 << MIPS_CPU_RTLX_IRQ);
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 33133d3df3e..9e60d117e41 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -31,7 +31,6 @@
 #include <linux/bitops.h>
 #include <asm/cacheflush.h>
 #include <asm/fpu.h>
-#include <asm/msa.h>
 #include <asm/sim.h>
 #include <asm/ucontext.h>
 #include <asm/cpu-features.h>
@@ -48,9 +47,6 @@ static int (*restore_fp_context)(struct sigcontext __user *sc);
 extern asmlinkage int _save_fp_context(struct sigcontext __user *sc);
 extern asmlinkage int _restore_fp_context(struct sigcontext __user *sc);
 
-extern asmlinkage int _save_msa_context(struct sigcontext __user *sc);
-extern asmlinkage int _restore_msa_context(struct sigcontext __user *sc);
-
 struct sigframe {
 	u32 sf_ass[4];		/* argument save space for o32 */
 	u32 sf_pad[2];		/* Was: signal trampoline */
@@ -100,60 +96,20 @@ static int copy_fp_from_sigcontext(struct sigcontext __user *sc)
 }
 
 /*
- * These functions will save only the upper 64 bits of the vector registers,
- * since the lower 64 bits have already been saved as the scalar FP context.
- */
-static int copy_msa_to_sigcontext(struct sigcontext __user *sc)
-{
-	int i;
-	int err = 0;
-
-	for (i = 0; i < NUM_FPU_REGS; i++) {
-		err |=
-		    __put_user(get_fpr64(&current->thread.fpu.fpr[i], 1),
-			       &sc->sc_msaregs[i]);
-	}
-	err |= __put_user(current->thread.fpu.msacsr, &sc->sc_msa_csr);
-
-	return err;
-}
-
-static int copy_msa_from_sigcontext(struct sigcontext __user *sc)
-{
-	int i;
-	int err = 0;
-	u64 val;
-
-	for (i = 0; i < NUM_FPU_REGS; i++) {
-		err |= __get_user(val, &sc->sc_msaregs[i]);
-		set_fpr64(&current->thread.fpu.fpr[i], 1, val);
-	}
-	err |= __get_user(current->thread.fpu.msacsr, &sc->sc_msa_csr);
-
-	return err;
-}
-
-/*
  * Helper routines
  */
-static int protected_save_fp_context(struct sigcontext __user *sc,
-				     unsigned used_math)
+static int protected_save_fp_context(struct sigcontext __user *sc)
 {
 	int err;
-	bool save_msa = cpu_has_msa && (used_math & USEDMATH_MSA);
 #ifndef CONFIG_EVA
 	while (1) {
 		lock_fpu_owner();
 		if (is_fpu_owner()) {
 			err = save_fp_context(sc);
-			if (save_msa && !err)
-				err = _save_msa_context(sc);
 			unlock_fpu_owner();
 		} else {
 			unlock_fpu_owner();
 			err = copy_fp_to_sigcontext(sc);
-			if (save_msa && !err)
-				err = copy_msa_to_sigcontext(sc);
 		}
 		if (likely(!err))
 			break;
@@ -169,38 +125,24 @@ static int protected_save_fp_context(struct sigcontext __user *sc,
 	 * EVA does not have FPU EVA instructions so saving fpu context directly
 	 * does not work.
 	 */
-	disable_msa();
 	lose_fpu(1);
 	err = save_fp_context(sc); /* this might fail */
-	if (save_msa && !err)
-		err = copy_msa_to_sigcontext(sc);
 #endif
 	return err;
 }
 
-static int protected_restore_fp_context(struct sigcontext __user *sc,
-					unsigned used_math)
+static int protected_restore_fp_context(struct sigcontext __user *sc)
 {
 	int err, tmp __maybe_unused;
-	bool restore_msa = cpu_has_msa && (used_math & USEDMATH_MSA);
 #ifndef CONFIG_EVA
 	while (1) {
 		lock_fpu_owner();
 		if (is_fpu_owner()) {
 			err = restore_fp_context(sc);
-			if (restore_msa && !err) {
-				enable_msa();
-				err = _restore_msa_context(sc);
-			} else {
-				/* signal handler may have used MSA */
-				disable_msa();
-			}
 			unlock_fpu_owner();
 		} else {
 			unlock_fpu_owner();
 			err = copy_fp_from_sigcontext(sc);
-			if (!err && (used_math & USEDMATH_MSA))
-				err = copy_msa_from_sigcontext(sc);
 		}
 		if (likely(!err))
 			break;
@@ -216,11 +158,8 @@ static int protected_restore_fp_context(struct sigcontext __user *sc,
 	 * EVA does not have FPU EVA instructions so restoring fpu context
 	 * directly does not work.
 	 */
-	enable_msa();
 	lose_fpu(0);
 	err = restore_fp_context(sc); /* this might fail */
-	if (restore_msa && !err)
-		err = copy_msa_from_sigcontext(sc);
 #endif
 	return err;
 }
@@ -252,8 +191,7 @@ int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		err |= __put_user(rddsp(DSP_MASK), &sc->sc_dsp);
 	}
 
-	used_math = used_math() ? USEDMATH_FP : 0;
-	used_math |= thread_msa_context_live() ? USEDMATH_MSA : 0;
+	used_math = !!used_math();
 	err |= __put_user(used_math, &sc->sc_used_math);
 
 	if (used_math) {
@@ -261,7 +199,7 @@ int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 		 * Save FPU state to signal context. Signal handler
 		 * will "inherit" current FPU state.
 		 */
-		err |= protected_save_fp_context(sc, used_math);
+		err |= protected_save_fp_context(sc);
 	}
 	return err;
 }
@@ -286,14 +224,14 @@ int fpcsr_pending(unsigned int __user *fpcsr)
 }
 
 static int
-check_and_restore_fp_context(struct sigcontext __user *sc, unsigned used_math)
+check_and_restore_fp_context(struct sigcontext __user *sc)
 {
 	int err, sig;
 
 	err = sig = fpcsr_pending(&sc->sc_fpc_csr);
 	if (err > 0)
 		err = 0;
-	err |= protected_restore_fp_context(sc, used_math);
+	err |= protected_restore_fp_context(sc);
 	return err ?: sig;
 }
 
@@ -333,10 +271,9 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
 	if (used_math) {
 		/* restore fpu context if we have used it before */
 		if (!err)
-			err = check_and_restore_fp_context(sc, used_math);
+			err = check_and_restore_fp_context(sc);
 	} else {
-		/* signal handler may have used FPU or MSA. Disable them. */
-		disable_msa();
+		/* signal handler may have used FPU.  Give it up. */
 		lose_fpu(0);
 	}
 
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 299f956e4db..bae2e6ee210 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -30,7 +30,6 @@
 #include <asm/sim.h>
 #include <asm/ucontext.h>
 #include <asm/fpu.h>
-#include <asm/msa.h>
 #include <asm/war.h>
 #include <asm/vdso.h>
 #include <asm/dsp.h>
@@ -43,9 +42,6 @@ static int (*restore_fp_context32)(struct sigcontext32 __user *sc);
 extern asmlinkage int _save_fp_context32(struct sigcontext32 __user *sc);
 extern asmlinkage int _restore_fp_context32(struct sigcontext32 __user *sc);
 
-extern asmlinkage int _save_msa_context32(struct sigcontext32 __user *sc);
-extern asmlinkage int _restore_msa_context32(struct sigcontext32 __user *sc);
-
 /*
  * Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
  */
@@ -115,59 +111,19 @@ static int copy_fp_from_sigcontext32(struct sigcontext32 __user *sc)
 }
 
 /*
- * These functions will save only the upper 64 bits of the vector registers,
- * since the lower 64 bits have already been saved as the scalar FP context.
- */
-static int copy_msa_to_sigcontext32(struct sigcontext32 __user *sc)
-{
-	int i;
-	int err = 0;
-
-	for (i = 0; i < NUM_FPU_REGS; i++) {
-		err |=
-		    __put_user(get_fpr64(&current->thread.fpu.fpr[i], 1),
-			       &sc->sc_msaregs[i]);
-	}
-	err |= __put_user(current->thread.fpu.msacsr, &sc->sc_msa_csr);
-
-	return err;
-}
-
-static int copy_msa_from_sigcontext32(struct sigcontext32 __user *sc)
-{
-	int i;
-	int err = 0;
-	u64 val;
-
-	for (i = 0; i < NUM_FPU_REGS; i++) {
-		err |= __get_user(val, &sc->sc_msaregs[i]);
-		set_fpr64(&current->thread.fpu.fpr[i], 1, val);
-	}
-	err |= __get_user(current->thread.fpu.msacsr, &sc->sc_msa_csr);
-
-	return err;
-}
-
-/*
  * sigcontext handlers
  */
-static int protected_save_fp_context32(struct sigcontext32 __user *sc,
-				       unsigned used_math)
+static int protected_save_fp_context32(struct sigcontext32 __user *sc)
 {
 	int err;
-	bool save_msa = cpu_has_msa && (used_math & USEDMATH_MSA);
 	while (1) {
 		lock_fpu_owner();
 		if (is_fpu_owner()) {
 			err = save_fp_context32(sc);
-			if (save_msa && !err)
-				err = _save_msa_context32(sc);
 			unlock_fpu_owner();
 		} else {
 			unlock_fpu_owner();
 			err = copy_fp_to_sigcontext32(sc);
-			if (save_msa && !err)
-				err = copy_msa_to_sigcontext32(sc);
 		}
 		if (likely(!err))
 			break;
@@ -181,28 +137,17 @@ static int protected_save_fp_context32(struct sigcontext32 __user *sc,
 	return err;
 }
 
-static int protected_restore_fp_context32(struct sigcontext32 __user *sc,
-					  unsigned used_math)
+static int protected_restore_fp_context32(struct sigcontext32 __user *sc)
 {
 	int err, tmp __maybe_unused;
-	bool restore_msa = cpu_has_msa && (used_math & USEDMATH_MSA);
 	while (1) {
 		lock_fpu_owner();
 		if (is_fpu_owner()) {
 			err = restore_fp_context32(sc);
-			if (restore_msa && !err) {
-				enable_msa();
-				err = _restore_msa_context32(sc);
-			} else {
-				/* signal handler may have used MSA */
-				disable_msa();
-			}
 			unlock_fpu_owner();
 		} else {
 			unlock_fpu_owner();
 			err = copy_fp_from_sigcontext32(sc);
-			if (restore_msa && !err)
-				err = copy_msa_from_sigcontext32(sc);
 		}
 		if (likely(!err))
 			break;
@@ -241,8 +186,7 @@ static int setup_sigcontext32(struct pt_regs *regs,
 		err |= __put_user(mflo3(), &sc->sc_lo3);
 	}
 
-	used_math = used_math() ? USEDMATH_FP : 0;
-	used_math |= thread_msa_context_live() ? USEDMATH_MSA : 0;
+	used_math = !!used_math();
 	err |= __put_user(used_math, &sc->sc_used_math);
 
 	if (used_math) {
@@ -250,21 +194,20 @@ static int setup_sigcontext32(struct pt_regs *regs,
 		 * Save FPU state to signal context.  Signal handler
 		 * will "inherit" current FPU state.
 		 */
-		err |= protected_save_fp_context32(sc, used_math);
+		err |= protected_save_fp_context32(sc);
 	}
 	return err;
 }
 
 static int
-check_and_restore_fp_context32(struct sigcontext32 __user *sc,
-			       unsigned used_math)
+check_and_restore_fp_context32(struct sigcontext32 __user *sc)
 {
 	int err, sig;
 
 	err = sig = fpcsr_pending(&sc->sc_fpc_csr);
 	if (err > 0)
 		err = 0;
-	err |= protected_restore_fp_context32(sc, used_math);
+	err |= protected_restore_fp_context32(sc);
 	return err ?: sig;
 }
 
@@ -301,10 +244,9 @@ static int restore_sigcontext32(struct pt_regs *regs,
 	if (used_math) {
 		/* restore fpu context if we have used it before */
 		if (!err)
-			err = check_and_restore_fp_context32(sc, used_math);
+			err = check_and_restore_fp_context32(sc);
 	} else {
-		/* signal handler may have used FPU or MSA. Disable them. */
-		disable_msa();
+		/* signal handler may have used FPU.  Give it up. */
 		lose_fpu(0);
 	}
 
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index ea4c2dc3169..df9e2bd9b2c 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -281,13 +281,6 @@ static void bmips_smp_finish(void)
 }
 
 /*
- * Runs on CPU0 after all CPUs have been booted
- */
-static void bmips_cpus_done(void)
-{
-}
-
-/*
  * BMIPS5000 raceless IPIs
  *
  * Each CPU has two inbound SW IRQs which are independent of all other CPUs.
@@ -434,7 +427,6 @@ struct plat_smp_ops bmips43xx_smp_ops = {
 	.boot_secondary		= bmips_boot_secondary,
 	.smp_finish		= bmips_smp_finish,
 	.init_secondary		= bmips_init_secondary,
-	.cpus_done		= bmips_cpus_done,
 	.send_ipi_single	= bmips43xx_send_ipi_single,
 	.send_ipi_mask		= bmips43xx_send_ipi_mask,
 #ifdef CONFIG_HOTPLUG_CPU
@@ -449,7 +441,6 @@ struct plat_smp_ops bmips5000_smp_ops = {
 	.boot_secondary		= bmips_boot_secondary,
 	.smp_finish		= bmips_smp_finish,
 	.init_secondary		= bmips_init_secondary,
-	.cpus_done		= bmips_cpus_done,
 	.send_ipi_single	= bmips5000_send_ipi_single,
 	.send_ipi_mask		= bmips5000_send_ipi_mask,
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index 3ef55fb7ac0..fc8a5155342 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -49,14 +49,11 @@ static void cmp_init_secondary(void)
 
 	/* Enable per-cpu interrupts: platform specific */
 
-#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
+#ifdef CONFIG_MIPS_MT_SMP
 	if (cpu_has_mipsmt)
 		c->vpe_id = (read_c0_tcbind() >> TCBIND_CURVPE_SHIFT) &
 			TCBIND_CURVPE;
 #endif
-#ifdef CONFIG_MIPS_MT_SMTC
-	c->tc_id  = (read_c0_tcbind() & TCBIND_CURTC) >> TCBIND_CURTC_SHIFT;
-#endif
 }
 
 static void cmp_smp_finish(void)
@@ -75,11 +72,6 @@ static void cmp_smp_finish(void)
 	local_irq_enable();
 }
 
-static void cmp_cpus_done(void)
-{
-	pr_debug("SMPCMP: CPU%d: %s\n", smp_processor_id(), __func__);
-}
-
 /*
  * Setup the PC, SP, and GP of a secondary processor and start it running
  * smp_bootstrap is the place to resume from
@@ -135,10 +127,6 @@ void __init cmp_smp_setup(void)
 		unsigned int mvpconf0 = read_c0_mvpconf0();
 
 		nvpe = ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1;
-#elif defined(CONFIG_MIPS_MT_SMTC)
-		unsigned int mvpconf0 = read_c0_mvpconf0();
-
-		nvpe = ((mvpconf0 & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1;
 #endif
 		smp_num_siblings = nvpe;
 	}
@@ -165,7 +153,6 @@ struct plat_smp_ops cmp_smp_ops = {
 	.send_ipi_mask		= gic_send_ipi_mask,
 	.init_secondary		= cmp_init_secondary,
 	.smp_finish		= cmp_smp_finish,
-	.cpus_done		= cmp_cpus_done,
 	.boot_secondary		= cmp_boot_secondary,
 	.smp_setup		= cmp_smp_setup,
 	.prepare_cpus		= cmp_prepare_cpus,
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 536eec0d21b..949f2c6827a 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -20,104 +20,43 @@
 #include <asm/mips-cpc.h>
 #include <asm/mips_mt.h>
 #include <asm/mipsregs.h>
+#include <asm/pm-cps.h>
 #include <asm/smp-cps.h>
 #include <asm/time.h>
 #include <asm/uasm.h>
 
 static DECLARE_BITMAP(core_power, NR_CPUS);
 
-struct boot_config mips_cps_bootcfg;
+struct core_boot_config *mips_cps_core_bootcfg;
 
-static void init_core(void)
+static unsigned core_vpe_count(unsigned core)
 {
-	unsigned int nvpes, t;
-	u32 mvpconf0, vpeconf0, vpecontrol, tcstatus, tcbind, status;
+	unsigned cfg;
 
-	if (!cpu_has_mipsmt)
-		return;
-
-	/* Enter VPE configuration state */
-	dvpe();
-	set_c0_mvpcontrol(MVPCONTROL_VPC);
-
-	/* Retrieve the count of VPEs in this core */
-	mvpconf0 = read_c0_mvpconf0();
-	nvpes = ((mvpconf0 & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1;
-	smp_num_siblings = nvpes;
-
-	for (t = 1; t < nvpes; t++) {
-		/* Use a 1:1 mapping of TC index to VPE index */
-		settc(t);
-
-		/* Bind 1 TC to this VPE */
-		tcbind = read_tc_c0_tcbind();
-		tcbind &= ~TCBIND_CURVPE;
-		tcbind |= t << TCBIND_CURVPE_SHIFT;
-		write_tc_c0_tcbind(tcbind);
-
-		/* Set exclusive TC, non-active, master */
-		vpeconf0 = read_vpe_c0_vpeconf0();
-		vpeconf0 &= ~(VPECONF0_XTC | VPECONF0_VPA);
-		vpeconf0 |= t << VPECONF0_XTC_SHIFT;
-		vpeconf0 |= VPECONF0_MVP;
-		write_vpe_c0_vpeconf0(vpeconf0);
-
-		/* Declare TC non-active, non-allocatable & interrupt exempt */
-		tcstatus = read_tc_c0_tcstatus();
-		tcstatus &= ~(TCSTATUS_A | TCSTATUS_DA);
-		tcstatus |= TCSTATUS_IXMT;
-		write_tc_c0_tcstatus(tcstatus);
-
-		/* Halt the TC */
-		write_tc_c0_tchalt(TCHALT_H);
-
-		/* Allow only 1 TC to execute */
-		vpecontrol = read_vpe_c0_vpecontrol();
-		vpecontrol &= ~VPECONTROL_TE;
-		write_vpe_c0_vpecontrol(vpecontrol);
-
-		/* Copy (most of) Status from VPE 0 */
-		status = read_c0_status();
-		status &= ~(ST0_IM | ST0_IE | ST0_KSU);
-		status |= ST0_CU0;
-		write_vpe_c0_status(status);
-
-		/* Copy Config from VPE 0 */
-		write_vpe_c0_config(read_c0_config());
-		write_vpe_c0_config7(read_c0_config7());
-
-		/* Ensure no software interrupts are pending */
-		write_vpe_c0_cause(0);
-
-		/* Sync Count */
-		write_vpe_c0_count(read_c0_count());
-	}
+	if (!config_enabled(CONFIG_MIPS_MT_SMP) || !cpu_has_mipsmt)
+		return 1;
 
-	/* Leave VPE configuration state */
-	clear_c0_mvpcontrol(MVPCONTROL_VPC);
+	write_gcr_cl_other(core << CM_GCR_Cx_OTHER_CORENUM_SHF);
+	cfg = read_gcr_co_config() & CM_GCR_Cx_CONFIG_PVPE_MSK;
+	return (cfg >> CM_GCR_Cx_CONFIG_PVPE_SHF) + 1;
 }
 
 static void __init cps_smp_setup(void)
 {
 	unsigned int ncores, nvpes, core_vpes;
 	int c, v;
-	u32 core_cfg, *entry_code;
 
 	/* Detect & record VPE topology */
 	ncores = mips_cm_numcores();
 	pr_info("VPE topology ");
 	for (c = nvpes = 0; c < ncores; c++) {
-		if (cpu_has_mipsmt && config_enabled(CONFIG_MIPS_MT_SMP)) {
-			write_gcr_cl_other(c << CM_GCR_Cx_OTHER_CORENUM_SHF);
-			core_cfg = read_gcr_co_config();
-			core_vpes = ((core_cfg & CM_GCR_Cx_CONFIG_PVPE_MSK) >>
-				     CM_GCR_Cx_CONFIG_PVPE_SHF) + 1;
-		} else {
-			core_vpes = 1;
-		}
-
+		core_vpes = core_vpe_count(c);
 		pr_cont("%c%u", c ? ',' : '{', core_vpes);
 
+		/* Use the number of VPEs in core 0 for smp_num_siblings */
+		if (!c)
+			smp_num_siblings = core_vpes;
+
 		for (v = 0; v < min_t(int, core_vpes, NR_CPUS - nvpes); v++) {
 			cpu_data[nvpes + v].core = c;
 #ifdef CONFIG_MIPS_MT_SMP
@@ -137,19 +76,14 @@ static void __init cps_smp_setup(void)
 		__cpu_logical_map[v] = v;
 	}
 
+	/* Set a coherent default CCA (CWB) */
+	change_c0_config(CONF_CM_CMASK, 0x5);
+
 	/* Core 0 is powered up (we're running on it) */
 	bitmap_set(core_power, 0, 1);
 
-	/* Disable MT - we only want to run 1 TC per VPE */
-	if (cpu_has_mipsmt)
-		dmt();
-
 	/* Initialise core 0 */
-	init_core();
-
-	/* Patch the start of mips_cps_core_entry to provide the CM base */
-	entry_code = (u32 *)&mips_cps_core_entry;
-	UASM_i_LA(&entry_code, 3, (long)mips_cm_base);
+	mips_cps_core_init();
 
 	/* Make core 0 coherent with everything */
 	write_gcr_cl_coherence(0xff);
@@ -157,15 +91,99 @@ static void __init cps_smp_setup(void)
 
 static void __init cps_prepare_cpus(unsigned int max_cpus)
 {
+	unsigned ncores, core_vpes, c, cca;
+	bool cca_unsuitable;
+	u32 *entry_code;
+
 	mips_mt_set_cpuoptions();
+
+	/* Detect whether the CCA is unsuited to multi-core SMP */
+	cca = read_c0_config() & CONF_CM_CMASK;
+	switch (cca) {
+	case 0x4: /* CWBE */
+	case 0x5: /* CWB */
+		/* The CCA is coherent, multi-core is fine */
+		cca_unsuitable = false;
+		break;
+
+	default:
+		/* CCA is not coherent, multi-core is not usable */
+		cca_unsuitable = true;
+	}
+
+	/* Warn the user if the CCA prevents multi-core */
+	ncores = mips_cm_numcores();
+	if (cca_unsuitable && ncores > 1) {
+		pr_warn("Using only one core due to unsuitable CCA 0x%x\n",
+			cca);
+
+		for_each_present_cpu(c) {
+			if (cpu_data[c].core)
+				set_cpu_present(c, false);
+		}
+	}
+
+	/*
+	 * Patch the start of mips_cps_core_entry to provide:
+	 *
+	 * v0 = CM base address
+	 * s0 = kseg0 CCA
+	 */
+	entry_code = (u32 *)&mips_cps_core_entry;
+	UASM_i_LA(&entry_code, 3, (long)mips_cm_base);
+	uasm_i_addiu(&entry_code, 16, 0, cca);
+	dma_cache_wback_inv((unsigned long)&mips_cps_core_entry,
+			    (void *)entry_code - (void *)&mips_cps_core_entry);
+
+	/* Allocate core boot configuration structs */
+	mips_cps_core_bootcfg = kcalloc(ncores, sizeof(*mips_cps_core_bootcfg),
+					GFP_KERNEL);
+	if (!mips_cps_core_bootcfg) {
+		pr_err("Failed to allocate boot config for %u cores\n", ncores);
+		goto err_out;
+	}
+
+	/* Allocate VPE boot configuration structs */
+	for (c = 0; c < ncores; c++) {
+		core_vpes = core_vpe_count(c);
+		mips_cps_core_bootcfg[c].vpe_config = kcalloc(core_vpes,
+				sizeof(*mips_cps_core_bootcfg[c].vpe_config),
+				GFP_KERNEL);
+		if (!mips_cps_core_bootcfg[c].vpe_config) {
+			pr_err("Failed to allocate %u VPE boot configs\n",
+			       core_vpes);
+			goto err_out;
+		}
+	}
+
+	/* Mark this CPU as booted */
+	atomic_set(&mips_cps_core_bootcfg[current_cpu_data.core].vpe_mask,
+		   1 << cpu_vpe_id(&current_cpu_data));
+
+	return;
+err_out:
+	/* Clean up allocations */
+	if (mips_cps_core_bootcfg) {
+		for (c = 0; c < ncores; c++)
+			kfree(mips_cps_core_bootcfg[c].vpe_config);
+		kfree(mips_cps_core_bootcfg);
+		mips_cps_core_bootcfg = NULL;
+	}
+
+	/* Effectively disable SMP by declaring CPUs not present */
+	for_each_possible_cpu(c) {
+		if (c == 0)
+			continue;
+		set_cpu_present(c, false);
+	}
 }
 
-static void boot_core(struct boot_config *cfg)
+static void boot_core(unsigned core)
 {
 	u32 access;
 
 	/* Select the appropriate core */
-	write_gcr_cl_other(cfg->core << CM_GCR_Cx_OTHER_CORENUM_SHF);
+	write_gcr_cl_other(core << CM_GCR_Cx_OTHER_CORENUM_SHF);
 
 	/* Set its reset vector */
 	write_gcr_co_reset_base(CKSEG1ADDR((unsigned long)mips_cps_core_entry));
@@ -175,104 +193,74 @@ static void boot_core(struct boot_config *cfg)
 
 	/* Ensure the core can access the GCRs */
 	access = read_gcr_access();
-	access |= 1 << (CM_GCR_ACCESS_ACCESSEN_SHF + cfg->core);
+	access |= 1 << (CM_GCR_ACCESS_ACCESSEN_SHF + core);
 	write_gcr_access(access);
 
-	/* Copy cfg */
-	mips_cps_bootcfg = *cfg;
-
 	if (mips_cpc_present()) {
-		/* Select the appropriate core */
-		write_cpc_cl_other(cfg->core << CPC_Cx_OTHER_CORENUM_SHF);
-
 		/* Reset the core */
+		mips_cpc_lock_other(core);
 		write_cpc_co_cmd(CPC_Cx_CMD_RESET);
+		mips_cpc_unlock_other();
 	} else {
 		/* Take the core out of reset */
 		write_gcr_co_reset_release(0);
 	}
 
 	/* The core is now powered up */
-	bitmap_set(core_power, cfg->core, 1);
+	bitmap_set(core_power, core, 1);
 }
 
-static void boot_vpe(void *info)
+static void remote_vpe_boot(void *dummy)
 {
-	struct boot_config *cfg = info;
-	u32 tcstatus, vpeconf0;
-
-	/* Enter VPE configuration state */
-	dvpe();
-	set_c0_mvpcontrol(MVPCONTROL_VPC);
-
-	settc(cfg->vpe);
-
-	/* Set the TC restart PC */
-	write_tc_c0_tcrestart((unsigned long)&smp_bootstrap);
-
-	/* Activate the TC, allow interrupts */
-	tcstatus = read_tc_c0_tcstatus();
-	tcstatus &= ~TCSTATUS_IXMT;
-	tcstatus |= TCSTATUS_A;
-	write_tc_c0_tcstatus(tcstatus);
-
-	/* Clear the TC halt bit */
-	write_tc_c0_tchalt(0);
-
-	/* Activate the VPE */
-	vpeconf0 = read_vpe_c0_vpeconf0();
-	vpeconf0 |= VPECONF0_VPA;
-	write_vpe_c0_vpeconf0(vpeconf0);
-
-	/* Set the stack & global pointer registers */
-	write_tc_gpr_sp(cfg->sp);
-	write_tc_gpr_gp(cfg->gp);
-
-	/* Leave VPE configuration state */
-	clear_c0_mvpcontrol(MVPCONTROL_VPC);
-
-	/* Enable other VPEs to execute */
-	evpe(EVPE_ENABLE);
+	mips_cps_boot_vpes();
 }
 
 static void cps_boot_secondary(int cpu, struct task_struct *idle)
 {
-	struct boot_config cfg;
+	unsigned core = cpu_data[cpu].core;
+	unsigned vpe_id = cpu_vpe_id(&cpu_data[cpu]);
+	struct core_boot_config *core_cfg = &mips_cps_core_bootcfg[core];
+	struct vpe_boot_config *vpe_cfg = &core_cfg->vpe_config[vpe_id];
 	unsigned int remote;
 	int err;
 
-	cfg.core = cpu_data[cpu].core;
-	cfg.vpe = cpu_vpe_id(&cpu_data[cpu]);
-	cfg.pc = (unsigned long)&smp_bootstrap;
-	cfg.sp = __KSTK_TOS(idle);
-	cfg.gp = (unsigned long)task_thread_info(idle);
+	vpe_cfg->pc = (unsigned long)&smp_bootstrap;
+	vpe_cfg->sp = __KSTK_TOS(idle);
+	vpe_cfg->gp = (unsigned long)task_thread_info(idle);
+
+	atomic_or(1 << cpu_vpe_id(&cpu_data[cpu]), &core_cfg->vpe_mask);
 
-	if (!test_bit(cfg.core, core_power)) {
+	preempt_disable();
+
+	if (!test_bit(core, core_power)) {
 		/* Boot a VPE on a powered down core */
-		boot_core(&cfg);
-		return;
+		boot_core(core);
+		goto out;
 	}
 
-	if (cfg.core != current_cpu_data.core) {
+	if (core != current_cpu_data.core) {
 		/* Boot a VPE on another powered up core */
 		for (remote = 0; remote < NR_CPUS; remote++) {
-			if (cpu_data[remote].core != cfg.core)
+			if (cpu_data[remote].core != core)
 				continue;
 			if (cpu_online(remote))
 				break;
 		}
 		BUG_ON(remote >= NR_CPUS);
 
-		err = smp_call_function_single(remote, boot_vpe, &cfg, 1);
+		err = smp_call_function_single(remote, remote_vpe_boot,
+					       NULL, 1);
 		if (err)
 			panic("Failed to call remote CPU\n");
-		return;
+		goto out;
 	}
 
 	BUG_ON(!cpu_has_mipsmt);
 
 	/* Boot a VPE on this core */
-	boot_vpe(&cfg);
+	mips_cps_boot_vpes();
+out:
+	preempt_enable();
 }
 
 static void cps_init_secondary(void)
@@ -281,10 +269,6 @@ static void cps_init_secondary(void)
 	if (cpu_has_mipsmt)
 		dmt();
 
-	/* TODO: revisit this assumption once hotplug is implemented */
-	if (cpu_vpe_id(&current_cpu_data) == 0)
-		init_core();
-
 	change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 |
 				 STATUSF_IP6 | STATUSF_IP7);
 }
@@ -302,10 +286,148 @@ static void cps_smp_finish(void)
 	local_irq_enable();
 }
 
-static void cps_cpus_done(void)
+#ifdef CONFIG_HOTPLUG_CPU
+
+static int cps_cpu_disable(void)
+{
+	unsigned cpu = smp_processor_id();
+	struct core_boot_config *core_cfg;
+
+	if (!cpu)
+		return -EBUSY;
+
+	if (!cps_pm_support_state(CPS_PM_POWER_GATED))
+		return -EINVAL;
+
+	core_cfg = &mips_cps_core_bootcfg[current_cpu_data.core];
+	atomic_sub(1 << cpu_vpe_id(&current_cpu_data), &core_cfg->vpe_mask);
+	smp_mb__after_atomic();
+	set_cpu_online(cpu, false);
+	cpu_clear(cpu, cpu_callin_map);
+
+	return 0;
+}
+
+static DECLARE_COMPLETION(cpu_death_chosen);
+static unsigned cpu_death_sibling;
+static enum {
+	CPU_DEATH_HALT,
+	CPU_DEATH_POWER,
+} cpu_death;
+
+void play_dead(void)
+{
+	unsigned cpu, core;
+
+	local_irq_disable();
+	idle_task_exit();
+	cpu = smp_processor_id();
+	cpu_death = CPU_DEATH_POWER;
+
+	if (cpu_has_mipsmt) {
+		core = cpu_data[cpu].core;
+
+		/* Look for another online VPE within the core */
+		for_each_online_cpu(cpu_death_sibling) {
+			if (cpu_data[cpu_death_sibling].core != core)
+				continue;
+
+			/*
+			 * There is an online VPE within the core. Just halt
+			 * this TC and leave the core alone.
+			 */
+			cpu_death = CPU_DEATH_HALT;
+			break;
+		}
+	}
+
+	/* This CPU has chosen its way out */
+	complete(&cpu_death_chosen);
+
+	if (cpu_death == CPU_DEATH_HALT) {
+		/* Halt this TC */
+		write_c0_tchalt(TCHALT_H);
+		instruction_hazard();
+	} else {
+		/* Power down the core */
+		cps_pm_enter_state(CPS_PM_POWER_GATED);
+	}
+
+	/* This should never be reached */
+	panic("Failed to offline CPU %u", cpu);
+}
+
+static void wait_for_sibling_halt(void *ptr_cpu)
 {
+	unsigned cpu = (unsigned)ptr_cpu;
+	unsigned vpe_id = cpu_data[cpu].vpe_id;
+	unsigned halted;
+	unsigned long flags;
+
+	do {
+		local_irq_save(flags);
+		settc(vpe_id);
+		halted = read_tc_c0_tchalt();
+		local_irq_restore(flags);
+	} while (!(halted & TCHALT_H));
+}
+
+static void cps_cpu_die(unsigned int cpu)
+{
+	unsigned core = cpu_data[cpu].core;
+	unsigned stat;
+	int err;
+
+	/* Wait for the cpu to choose its way out */
+	if (!wait_for_completion_timeout(&cpu_death_chosen,
+					 msecs_to_jiffies(5000))) {
+		pr_err("CPU%u: didn't offline\n", cpu);
+		return;
+	}
+
+	/*
+	 * Now wait for the CPU to actually offline. Without doing this that
+	 * offlining may race with one or more of:
+	 *
+	 *   - Onlining the CPU again.
+	 *   - Powering down the core if another VPE within it is offlined.
+	 *   - A sibling VPE entering a non-coherent state.
+	 *
+	 * In the non-MT halt case (ie. infinite loop) the CPU is doing nothing
+	 * with which we could race, so do nothing.
+	 */
+	if (cpu_death == CPU_DEATH_POWER) {
+		/*
+		 * Wait for the core to enter a powered down or clock gated
+		 * state, the latter happening when a JTAG probe is connected
+		 * in which case the CPC will refuse to power down the core.
+		 */
+		do {
+			mips_cpc_lock_other(core);
+			stat = read_cpc_co_stat_conf();
+			stat &= CPC_Cx_STAT_CONF_SEQSTATE_MSK;
+			mips_cpc_unlock_other();
+		} while (stat != CPC_Cx_STAT_CONF_SEQSTATE_D0 &&
+			 stat != CPC_Cx_STAT_CONF_SEQSTATE_D2 &&
+			 stat != CPC_Cx_STAT_CONF_SEQSTATE_U2);
+
+		/* Indicate the core is powered off */
+		bitmap_clear(core_power, core, 1);
+	} else if (cpu_has_mipsmt) {
+		/*
+		 * Have a CPU with access to the offlined CPUs registers wait
+		 * for its TC to halt.
+		 */
+		err = smp_call_function_single(cpu_death_sibling,
+					       wait_for_sibling_halt,
+					       (void *)cpu, 1);
+		if (err)
+			panic("Failed to call remote sibling CPU\n");
+	}
 }
 
+#endif /* CONFIG_HOTPLUG_CPU */
+
 static struct plat_smp_ops cps_smp_ops = {
 	.smp_setup		= cps_smp_setup,
 	.prepare_cpus		= cps_prepare_cpus,
@@ -314,9 +436,18 @@ static struct plat_smp_ops cps_smp_ops = {
 	.smp_finish		= cps_smp_finish,
 	.send_ipi_single	= gic_send_ipi_single,
 	.send_ipi_mask		= gic_send_ipi_mask,
-	.cpus_done		= cps_cpus_done,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable		= cps_cpu_disable,
+	.cpu_die		= cps_cpu_die,
+#endif
 };
 
+bool mips_cps_smp_in_use(void)
+{
+	extern struct plat_smp_ops *mp_ops;
+	return mp_ops == &cps_smp_ops;
+}
+
 int register_cps_smp_ops(void)
 {
 	if (!mips_cm_present()) {
diff --git a/arch/mips/kernel/smp-gic.c b/arch/mips/kernel/smp-gic.c
index 3bb1f92ab52..3b21a96d1cc 100644
--- a/arch/mips/kernel/smp-gic.c
+++ b/arch/mips/kernel/smp-gic.c
@@ -15,12 +15,14 @@
 #include <linux/printk.h>
 
 #include <asm/gic.h>
+#include <asm/mips-cpc.h>
 #include <asm/smp-ops.h>
 
 void gic_send_ipi_single(int cpu, unsigned int action)
 {
 	unsigned long flags;
 	unsigned int intr;
+	unsigned int core = cpu_data[cpu].core;
 
 	pr_debug("CPU%d: %s cpu %d action %u status %08x\n",
 		 smp_processor_id(), __func__, cpu, action, read_c0_status());
@@ -41,6 +43,15 @@ void gic_send_ipi_single(int cpu, unsigned int action)
 	}
 
 	gic_send_ipi(intr);
+
+	if (mips_cpc_present() && (core != current_cpu_data.core)) {
+		while (!cpumask_test_cpu(cpu, &cpu_coherent_mask)) {
+			mips_cpc_lock_other(core);
+			write_cpc_co_cmd(CPC_Cx_CMD_PWRUP);
+			mips_cpc_unlock_other();
+		}
+	}
+
 	local_irq_restore(flags);
 }
 
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index f8e13149604..3babf6e4f89 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -183,10 +183,6 @@ static void vsmp_smp_finish(void)
 	local_irq_enable();
 }
 
-static void vsmp_cpus_done(void)
-{
-}
-
 /*
  * Setup the PC, SP, and GP of a secondary processor and start it
  * running!
@@ -287,7 +283,6 @@ struct plat_smp_ops vsmp_smp_ops = {
 	.send_ipi_mask		= vsmp_send_ipi_mask,
 	.init_secondary		= vsmp_init_secondary,
 	.smp_finish		= vsmp_smp_finish,
-	.cpus_done		= vsmp_cpus_done,
 	.boot_secondary		= vsmp_boot_secondary,
 	.smp_setup		= vsmp_smp_setup,
 	.prepare_cpus		= vsmp_prepare_cpus,
diff --git a/arch/mips/kernel/smp-up.c b/arch/mips/kernel/smp-up.c
index 7fde3e4d978..17878d71ef2 100644
--- a/arch/mips/kernel/smp-up.c
+++ b/arch/mips/kernel/smp-up.c
@@ -36,11 +36,6 @@ static void up_smp_finish(void)
 {
 }
 
-/* Hook for after all CPUs are online */
-static void up_cpus_done(void)
-{
-}
-
 /*
  * Firmware CPU startup hook
  */
@@ -73,7 +68,6 @@ struct plat_smp_ops up_smp_ops = {
 	.send_ipi_mask		= up_send_ipi_mask,
 	.init_secondary		= up_init_secondary,
 	.smp_finish		= up_smp_finish,
-	.cpus_done		= up_cpus_done,
 	.boot_secondary		= up_boot_secondary,
 	.smp_setup		= up_smp_setup,
 	.prepare_cpus		= up_prepare_cpus,
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 0a022ee33b2..9bad52ede90 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -43,10 +43,6 @@
 #include <asm/time.h>
 #include <asm/setup.h>
 
-#ifdef CONFIG_MIPS_MT_SMTC
-#include <asm/mipsmtregs.h>
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 volatile cpumask_t cpu_callin_map;	/* Bitmask of started secondaries */
 
 int __cpu_number_map[NR_CPUS];		/* Map physical to logical */
@@ -66,6 +62,8 @@ EXPORT_SYMBOL(cpu_sibling_map);
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
 
+cpumask_t cpu_coherent_mask;
+
 static inline void set_cpu_sibling_map(int cpu)
 {
 	int i;
@@ -102,12 +100,6 @@ asmlinkage void start_secondary(void)
 {
 	unsigned int cpu;
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	/* Only do cpu_probe for first TC of CPU */
-	if ((read_c0_tcbind() & TCBIND_CURTC) != 0)
-		__cpu_name[smp_processor_id()] = __cpu_name[0];
-	else
-#endif /* CONFIG_MIPS_MT_SMTC */
 	cpu_probe();
 	cpu_report();
 	per_cpu_trap_init(false);
@@ -124,6 +116,7 @@ asmlinkage void start_secondary(void)
 	cpu = smp_processor_id();
 	cpu_data[cpu].udelay_val = loops_per_jiffy;
 
+	cpu_set(cpu, cpu_coherent_mask);
 	notify_cpu_starting(cpu);
 
 	set_cpu_online(cpu, true);
@@ -173,7 +166,6 @@ void smp_send_stop(void)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	mp_ops->cpus_done();
 }
 
 /* called from main before smp_init() */
@@ -186,6 +178,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 #ifndef CONFIG_HOTPLUG_CPU
 	init_cpu_present(cpu_possible_mask);
 #endif
+	cpumask_copy(&cpu_coherent_mask, cpu_possible_mask);
 }
 
 /* preload SMP state for boot cpu */
@@ -238,13 +231,10 @@ static void flush_tlb_mm_ipi(void *mm)
  *  o collapses to normal function call on UP kernels
  *  o collapses to normal function call on systems with a single shared
  *    primary cache.
- *  o CONFIG_MIPS_MT_SMTC currently implies there is only one physical core.
  */
 static inline void smp_on_other_tlbs(void (*func) (void *info), void *info)
 {
-#ifndef CONFIG_MIPS_MT_SMTC
 	smp_call_function(func, info, 1);
-#endif
 }
 
 static inline void smp_on_each_tlb(void (*func) (void *info), void *info)
@@ -404,3 +394,46 @@ void dump_send_ipi(void (*dump_ipi_callback)(void *))
 }
 EXPORT_SYMBOL(dump_send_ipi);
 #endif
+
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+
+static DEFINE_PER_CPU(atomic_t, tick_broadcast_count);
+static DEFINE_PER_CPU(struct call_single_data, tick_broadcast_csd);
+
+void tick_broadcast(const struct cpumask *mask)
+{
+	atomic_t *count;
+	struct call_single_data *csd;
+	int cpu;
+
+	for_each_cpu(cpu, mask) {
+		count = &per_cpu(tick_broadcast_count, cpu);
+		csd = &per_cpu(tick_broadcast_csd, cpu);
+
+		if (atomic_inc_return(count) == 1)
+			smp_call_function_single_async(cpu, csd);
+	}
+}
+
+static void tick_broadcast_callee(void *info)
+{
+	int cpu = smp_processor_id();
+	tick_receive_broadcast();
+	atomic_set(&per_cpu(tick_broadcast_count, cpu), 0);
+}
+
+static int __init tick_broadcast_init(void)
+{
+	struct call_single_data *csd;
+	int cpu;
+
+	for (cpu = 0; cpu < NR_CPUS; cpu++) {
+		csd = &per_cpu(tick_broadcast_csd, cpu);
+		csd->func = tick_broadcast_callee;
+	}
+
+	return 0;
+}
+early_initcall(tick_broadcast_init);
+
+#endif /* CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */
diff --git a/arch/mips/kernel/smtc-asm.S b/arch/mips/kernel/smtc-asm.S
deleted file mode 100644
index 2866863a39d..00000000000
--- a/arch/mips/kernel/smtc-asm.S
+++ /dev/null
@@ -1,133 +0,0 @@
-/*
- * Assembly Language Functions for MIPS MT SMTC support
- */
-
-/*
- * This file should be built into the kernel only if CONFIG_MIPS_MT_SMTC is set. */
-
-#include <asm/regdef.h>
-#include <asm/asmmacro.h>
-#include <asm/stackframe.h>
-#include <asm/irqflags.h>
-
-/*
- * "Software Interrupt" linkage.
- *
- * This is invoked when an "Interrupt" is sent from one TC to another,
- * where the TC to be interrupted is halted, has it's Restart address
- * and Status values saved by the "remote control" thread, then modified
- * to cause execution to begin here, in kenel mode. This code then
- * disguises the TC state as that of an exception and transfers
- * control to the general exception or vectored interrupt handler.
- */
-	.set noreorder
-
-/*
-The __smtc_ipi_vector would use k0 and k1 as temporaries and
-1) Set EXL (this is per-VPE, so this can't be done by proxy!)
-2) Restore the K/CU and IXMT bits to the pre "exception" state
-   (EXL means no interrupts and access to the kernel map).
-3) Set EPC to be the saved value of TCRestart.
-4) Jump to the exception handler entry point passed by the sender.
-
-CAN WE PROVE THAT WE WON'T DO THIS IF INTS DISABLED??
-*/
-
-/*
- * Reviled and slandered vision: Set EXL and restore K/CU/IXMT
- * state of pre-halt thread, then save everything and call
- * thought some function pointer to imaginary_exception, which
- * will parse a register value or memory message queue to
- * deliver things like interprocessor interrupts. On return
- * from that function, jump to the global ret_from_irq code
- * to invoke the scheduler and return as appropriate.
- */
-
-#define PT_PADSLOT4 (PT_R0-8)
-#define PT_PADSLOT5 (PT_R0-4)
-
-	.text
-	.align 5
-FEXPORT(__smtc_ipi_vector)
-#ifdef CONFIG_CPU_MICROMIPS
-	nop
-#endif
-	.set	noat
-	/* Disable thread scheduling to make Status update atomic */
-	DMT	27					# dmt	k1
-	_ehb
-	/* Set EXL */
-	mfc0	k0,CP0_STATUS
-	ori	k0,k0,ST0_EXL
-	mtc0	k0,CP0_STATUS
-	_ehb
-	/* Thread scheduling now inhibited by EXL. Restore TE state. */
-	andi	k1,k1,VPECONTROL_TE
-	beqz	k1,1f
-	emt
-1:
-	/*
-	 * The IPI sender has put some information on the anticipated
-	 * kernel stack frame.	If we were in user mode, this will be
-	 * built above the saved kernel SP.  If we were already in the
-	 * kernel, it will be built above the current CPU SP.
-	 *
-	 * Were we in kernel mode, as indicated by CU0?
-	 */
-	sll	k1,k0,3
-	.set noreorder
-	bltz	k1,2f
-	move	k1,sp
-	.set reorder
-	/*
-	 * If previously in user mode, set CU0 and use kernel stack.
-	 */
-	li	k1,ST0_CU0
-	or	k1,k1,k0
-	mtc0	k1,CP0_STATUS
-	_ehb
-	get_saved_sp
-	/* Interrupting TC will have pre-set values in slots in the new frame */
-2:	subu	k1,k1,PT_SIZE
-	/* Load TCStatus Value */
-	lw	k0,PT_TCSTATUS(k1)
-	/* Write it to TCStatus to restore CU/KSU/IXMT state */
-	mtc0	k0,$2,1
-	_ehb
-	lw	k0,PT_EPC(k1)
-	mtc0	k0,CP0_EPC
-	/* Save all will redundantly recompute the SP, but use it for now */
-	SAVE_ALL
-	CLI
-	TRACE_IRQS_OFF
-	/* Function to be invoked passed stack pad slot 5 */
-	lw	t0,PT_PADSLOT5(sp)
-	/* Argument from sender passed in stack pad slot 4 */
-	lw	a0,PT_PADSLOT4(sp)
-	LONG_L	s0, TI_REGS($28)
-	LONG_S	sp, TI_REGS($28)
-	PTR_LA	ra, ret_from_irq
-	jr	t0
-
-/*
- * Called from idle loop to provoke processing of queued IPIs
- * First IPI message in queue passed as argument.
- */
-
-LEAF(self_ipi)
-	/* Before anything else, block interrupts */
-	mfc0	t0,CP0_TCSTATUS
-	ori	t1,t0,TCSTATUS_IXMT
-	mtc0	t1,CP0_TCSTATUS
-	_ehb
-	/* We know we're in kernel mode, so prepare stack frame */
-	subu	t1,sp,PT_SIZE
-	sw	ra,PT_EPC(t1)
-	sw	a0,PT_PADSLOT4(t1)
-	la	t2,ipi_decode
-	sw	t2,PT_PADSLOT5(t1)
-	/* Save pre-disable value of TCStatus */
-	sw	t0,PT_TCSTATUS(t1)
-	j	__smtc_ipi_vector
-	nop
-END(self_ipi)
diff --git a/arch/mips/kernel/smtc-proc.c b/arch/mips/kernel/smtc-proc.c
deleted file mode 100644
index 38635a996cb..00000000000
--- a/arch/mips/kernel/smtc-proc.c
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * /proc hooks for SMTC kernel
- * Copyright (C) 2005 Mips Technologies, Inc
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/cpumask.h>
-#include <linux/interrupt.h>
-
-#include <asm/cpu.h>
-#include <asm/processor.h>
-#include <linux/atomic.h>
-#include <asm/hardirq.h>
-#include <asm/mmu_context.h>
-#include <asm/mipsregs.h>
-#include <asm/cacheflush.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-
-#include <asm/smtc_proc.h>
-
-/*
- * /proc diagnostic and statistics hooks
- */
-
-/*
- * Statistics gathered
- */
-unsigned long selfipis[NR_CPUS];
-
-struct smtc_cpu_proc smtc_cpu_stats[NR_CPUS];
-
-atomic_t smtc_fpu_recoveries;
-
-static int smtc_proc_show(struct seq_file *m, void *v)
-{
-	int i;
-	extern unsigned long ebase;
-
-	seq_printf(m, "SMTC Status Word: 0x%08x\n", smtc_status);
-	seq_printf(m, "Config7: 0x%08x\n", read_c0_config7());
-	seq_printf(m, "EBASE: 0x%08lx\n", ebase);
-	seq_printf(m, "Counter Interrupts taken per CPU (TC)\n");
-	for (i=0; i < NR_CPUS; i++)
-		seq_printf(m, "%d: %ld\n", i, smtc_cpu_stats[i].timerints);
-	seq_printf(m, "Self-IPIs by CPU:\n");
-	for(i = 0; i < NR_CPUS; i++)
-		seq_printf(m, "%d: %ld\n", i, smtc_cpu_stats[i].selfipis);
-	seq_printf(m, "%d Recoveries of \"stolen\" FPU\n",
-		   atomic_read(&smtc_fpu_recoveries));
-	return 0;
-}
-
-static int smtc_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, smtc_proc_show, NULL);
-}
-
-static const struct file_operations smtc_proc_fops = {
-	.open		= smtc_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-void init_smtc_stats(void)
-{
-	int i;
-
-	for (i=0; i<NR_CPUS; i++) {
-		smtc_cpu_stats[i].timerints = 0;
-		smtc_cpu_stats[i].selfipis = 0;
-	}
-
-	atomic_set(&smtc_fpu_recoveries, 0);
-
-	proc_create("smtc", 0444, NULL, &smtc_proc_fops);
-}
-
-static int proc_cpuinfo_chain_call(struct notifier_block *nfb,
-	unsigned long action_unused, void *data)
-{
-	struct proc_cpuinfo_notifier_args *pcn = data;
-	struct seq_file *m = pcn->m;
-	unsigned long n = pcn->n;
-
-	if (!cpu_has_mipsmt)
-		return NOTIFY_OK;
-
-	seq_printf(m, "VPE\t\t\t: %d\n", cpu_data[n].vpe_id);
-	seq_printf(m, "TC\t\t\t: %d\n", cpu_data[n].tc_id);
-
-	return NOTIFY_OK;
-}
-
-static int __init proc_cpuinfo_notifier_init(void)
-{
-	return proc_cpuinfo_notifier(proc_cpuinfo_chain_call, 0);
-}
-
-subsys_initcall(proc_cpuinfo_notifier_init);
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
deleted file mode 100644
index c1681d65dd5..00000000000
--- a/arch/mips/kernel/smtc.c
+++ /dev/null
@@ -1,1528 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * Copyright (C) 2004 Mips Technologies, Inc
- * Copyright (C) 2008 Kevin D. Kissell
- */
-
-#include <linux/clockchips.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-#include <linux/cpumask.h>
-#include <linux/interrupt.h>
-#include <linux/kernel_stat.h>
-#include <linux/module.h>
-#include <linux/ftrace.h>
-#include <linux/slab.h>
-
-#include <asm/cpu.h>
-#include <asm/processor.h>
-#include <linux/atomic.h>
-#include <asm/hardirq.h>
-#include <asm/hazards.h>
-#include <asm/irq.h>
-#include <asm/idle.h>
-#include <asm/mmu_context.h>
-#include <asm/mipsregs.h>
-#include <asm/cacheflush.h>
-#include <asm/time.h>
-#include <asm/addrspace.h>
-#include <asm/smtc.h>
-#include <asm/smtc_proc.h>
-#include <asm/setup.h>
-
-/*
- * SMTC Kernel needs to manipulate low-level CPU interrupt mask
- * in do_IRQ. These are passed in setup_irq_smtc() and stored
- * in this table.
- */
-unsigned long irq_hwmask[NR_IRQS];
-
-#define LOCK_MT_PRA() \
-	local_irq_save(flags); \
-	mtflags = dmt()
-
-#define UNLOCK_MT_PRA() \
-	emt(mtflags); \
-	local_irq_restore(flags)
-
-#define LOCK_CORE_PRA() \
-	local_irq_save(flags); \
-	mtflags = dvpe()
-
-#define UNLOCK_CORE_PRA() \
-	evpe(mtflags); \
-	local_irq_restore(flags)
-
-/*
- * Data structures purely associated with SMTC parallelism
- */
-
-
-/*
- * Table for tracking ASIDs whose lifetime is prolonged.
- */
-
-asiduse smtc_live_asid[MAX_SMTC_TLBS][MAX_SMTC_ASIDS];
-
-/*
- * Number of InterProcessor Interrupt (IPI) message buffers to allocate
- */
-
-#define IPIBUF_PER_CPU 4
-
-struct smtc_ipi_q IPIQ[NR_CPUS];
-static struct smtc_ipi_q freeIPIq;
-
-
-/*
- * Number of FPU contexts for each VPE
- */
-
-static int smtc_nconf1[MAX_SMTC_VPES];
-
-
-/* Forward declarations */
-
-void ipi_decode(struct smtc_ipi *);
-static void post_direct_ipi(int cpu, struct smtc_ipi *pipi);
-static void setup_cross_vpe_interrupts(unsigned int nvpe);
-void init_smtc_stats(void);
-
-/* Global SMTC Status */
-
-unsigned int smtc_status;
-
-/* Boot command line configuration overrides */
-
-static int vpe0limit;
-static int ipibuffers;
-static int nostlb;
-static int asidmask;
-unsigned long smtc_asid_mask = 0xff;
-
-static int __init vpe0tcs(char *str)
-{
-	get_option(&str, &vpe0limit);
-
-	return 1;
-}
-
-static int __init ipibufs(char *str)
-{
-	get_option(&str, &ipibuffers);
-	return 1;
-}
-
-static int __init stlb_disable(char *s)
-{
-	nostlb = 1;
-	return 1;
-}
-
-static int __init asidmask_set(char *str)
-{
-	get_option(&str, &asidmask);
-	switch (asidmask) {
-	case 0x1:
-	case 0x3:
-	case 0x7:
-	case 0xf:
-	case 0x1f:
-	case 0x3f:
-	case 0x7f:
-	case 0xff:
-		smtc_asid_mask = (unsigned long)asidmask;
-		break;
-	default:
-		printk("ILLEGAL ASID mask 0x%x from command line\n", asidmask);
-	}
-	return 1;
-}
-
-__setup("vpe0tcs=", vpe0tcs);
-__setup("ipibufs=", ipibufs);
-__setup("nostlb", stlb_disable);
-__setup("asidmask=", asidmask_set);
-
-#ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG
-
-static int hang_trig;
-
-static int __init hangtrig_enable(char *s)
-{
-	hang_trig = 1;
-	return 1;
-}
-
-
-__setup("hangtrig", hangtrig_enable);
-
-#define DEFAULT_BLOCKED_IPI_LIMIT 32
-
-static int timerq_limit = DEFAULT_BLOCKED_IPI_LIMIT;
-
-static int __init tintq(char *str)
-{
-	get_option(&str, &timerq_limit);
-	return 1;
-}
-
-__setup("tintq=", tintq);
-
-static int imstuckcount[MAX_SMTC_VPES][8];
-/* vpemask represents IM/IE bits of per-VPE Status registers, low-to-high */
-static int vpemask[MAX_SMTC_VPES][8] = {
-	{0, 0, 1, 0, 0, 0, 0, 1},
-	{0, 0, 0, 0, 0, 0, 0, 1}
-};
-int tcnoprog[NR_CPUS];
-static atomic_t idle_hook_initialized = ATOMIC_INIT(0);
-static int clock_hang_reported[NR_CPUS];
-
-#endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */
-
-/*
- * Configure shared TLB - VPC configuration bit must be set by caller
- */
-
-static void smtc_configure_tlb(void)
-{
-	int i, tlbsiz, vpes;
-	unsigned long mvpconf0;
-	unsigned long config1val;
-
-	/* Set up ASID preservation table */
-	for (vpes=0; vpes<MAX_SMTC_TLBS; vpes++) {
-	    for(i = 0; i < MAX_SMTC_ASIDS; i++) {
-		smtc_live_asid[vpes][i] = 0;
-	    }
-	}
-	mvpconf0 = read_c0_mvpconf0();
-
-	if ((vpes = ((mvpconf0 & MVPCONF0_PVPE)
-			>> MVPCONF0_PVPE_SHIFT) + 1) > 1) {
-	    /* If we have multiple VPEs, try to share the TLB */
-	    if ((mvpconf0 & MVPCONF0_TLBS) && !nostlb) {
-		/*
-		 * If TLB sizing is programmable, shared TLB
-		 * size is the total available complement.
-		 * Otherwise, we have to take the sum of all
-		 * static VPE TLB entries.
-		 */
-		if ((tlbsiz = ((mvpconf0 & MVPCONF0_PTLBE)
-				>> MVPCONF0_PTLBE_SHIFT)) == 0) {
-		    /*
-		     * If there's more than one VPE, there had better
-		     * be more than one TC, because we need one to bind
-		     * to each VPE in turn to be able to read
-		     * its configuration state!
-		     */
-		    settc(1);
-		    /* Stop the TC from doing anything foolish */
-		    write_tc_c0_tchalt(TCHALT_H);
-		    mips_ihb();
-		    /* No need to un-Halt - that happens later anyway */
-		    for (i=0; i < vpes; i++) {
-			write_tc_c0_tcbind(i);
-			/*
-			 * To be 100% sure we're really getting the right
-			 * information, we exit the configuration state
-			 * and do an IHB after each rebinding.
-			 */
-			write_c0_mvpcontrol(
-				read_c0_mvpcontrol() & ~ MVPCONTROL_VPC );
-			mips_ihb();
-			/*
-			 * Only count if the MMU Type indicated is TLB
-			 */
-			if (((read_vpe_c0_config() & MIPS_CONF_MT) >> 7) == 1) {
-				config1val = read_vpe_c0_config1();
-				tlbsiz += ((config1val >> 25) & 0x3f) + 1;
-			}
-
-			/* Put core back in configuration state */
-			write_c0_mvpcontrol(
-				read_c0_mvpcontrol() | MVPCONTROL_VPC );
-			mips_ihb();
-		    }
-		}
-		write_c0_mvpcontrol(read_c0_mvpcontrol() | MVPCONTROL_STLB);
-		ehb();
-
-		/*
-		 * Setup kernel data structures to use software total,
-		 * rather than read the per-VPE Config1 value. The values
-		 * for "CPU 0" gets copied to all the other CPUs as part
-		 * of their initialization in smtc_cpu_setup().
-		 */
-
-		/* MIPS32 limits TLB indices to 64 */
-		if (tlbsiz > 64)
-			tlbsiz = 64;
-		cpu_data[0].tlbsize = current_cpu_data.tlbsize = tlbsiz;
-		smtc_status |= SMTC_TLB_SHARED;
-		local_flush_tlb_all();
-
-		printk("TLB of %d entry pairs shared by %d VPEs\n",
-			tlbsiz, vpes);
-	    } else {
-		printk("WARNING: TLB Not Sharable on SMTC Boot!\n");
-	    }
-	}
-}
-
-
-/*
- * Incrementally build the CPU map out of constituent MIPS MT cores,
- * using the specified available VPEs and TCs.	Plaform code needs
- * to ensure that each MIPS MT core invokes this routine on reset,
- * one at a time(!).
- *
- * This version of the build_cpu_map and prepare_cpus routines assumes
- * that *all* TCs of a MIPS MT core will be used for Linux, and that
- * they will be spread across *all* available VPEs (to minimise the
- * loss of efficiency due to exception service serialization).
- * An improved version would pick up configuration information and
- * possibly leave some TCs/VPEs as "slave" processors.
- *
- * Use c0_MVPConf0 to find out how many TCs are available, setting up
- * cpu_possible_mask and the logical/physical mappings.
- */
-
-int __init smtc_build_cpu_map(int start_cpu_slot)
-{
-	int i, ntcs;
-
-	/*
-	 * The CPU map isn't actually used for anything at this point,
-	 * so it's not clear what else we should do apart from set
-	 * everything up so that "logical" = "physical".
-	 */
-	ntcs = ((read_c0_mvpconf0() & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1;
-	for (i=start_cpu_slot; i<NR_CPUS && i<ntcs; i++) {
-		set_cpu_possible(i, true);
-		__cpu_number_map[i] = i;
-		__cpu_logical_map[i] = i;
-	}
-#ifdef CONFIG_MIPS_MT_FPAFF
-	/* Initialize map of CPUs with FPUs */
-	cpus_clear(mt_fpu_cpumask);
-#endif
-
-	/* One of those TC's is the one booting, and not a secondary... */
-	printk("%i available secondary CPU TC(s)\n", i - 1);
-
-	return i;
-}
-
-/*
- * Common setup before any secondaries are started
- * Make sure all CPUs are in a sensible state before we boot any of the
- * secondaries.
- *
- * For MIPS MT "SMTC" operation, we set up all TCs, spread as evenly
- * as possible across the available VPEs.
- */
-
-static void smtc_tc_setup(int vpe, int tc, int cpu)
-{
-	static int cp1contexts[MAX_SMTC_VPES];
-
-	/*
-	 * Make a local copy of the available FPU contexts in order
-	 * to keep track of TCs that can have one.
-	 */
-	if (tc == 1)
-	{
-		/*
-		 * FIXME: Multi-core SMTC hasn't been tested and the
-		 *	  maximum number of VPEs may change.
-		 */
-		cp1contexts[0] = smtc_nconf1[0] - 1;
-		cp1contexts[1] = smtc_nconf1[1];
-	}
-
-	settc(tc);
-	write_tc_c0_tchalt(TCHALT_H);
-	mips_ihb();
-	write_tc_c0_tcstatus((read_tc_c0_tcstatus()
-			& ~(TCSTATUS_TKSU | TCSTATUS_DA | TCSTATUS_IXMT))
-			| TCSTATUS_A);
-	/*
-	 * TCContext gets an offset from the base of the IPIQ array
-	 * to be used in low-level code to detect the presence of
-	 * an active IPI queue.
-	 */
-	write_tc_c0_tccontext((sizeof(struct smtc_ipi_q) * cpu) << 16);
-
-	/* Bind TC to VPE. */
-	write_tc_c0_tcbind(vpe);
-
-	/* In general, all TCs should have the same cpu_data indications. */
-	memcpy(&cpu_data[cpu], &cpu_data[0], sizeof(struct cpuinfo_mips));
-
-	/* Check to see if there is a FPU context available for this TC. */
-	if (!cp1contexts[vpe])
-		cpu_data[cpu].options &= ~MIPS_CPU_FPU;
-	else
-		cp1contexts[vpe]--;
-
-	/* Store the TC and VPE into the cpu_data structure. */
-	cpu_data[cpu].vpe_id = vpe;
-	cpu_data[cpu].tc_id = tc;
-
-	/* FIXME: Multi-core SMTC hasn't been tested, but be prepared. */
-	cpu_data[cpu].core = (read_vpe_c0_ebase() >> 1) & 0xff;
-}
-
-/*
- * Tweak to get Count registers synced as closely as possible. The
- * value seems good for 34K-class cores.
- */
-
-#define CP0_SKEW 8
-
-void smtc_prepare_cpus(int cpus)
-{
-	int i, vpe, tc, ntc, nvpe, tcpervpe[NR_CPUS], slop, cpu;
-	unsigned long flags;
-	unsigned long val;
-	int nipi;
-	struct smtc_ipi *pipi;
-
-	/* disable interrupts so we can disable MT */
-	local_irq_save(flags);
-	/* disable MT so we can configure */
-	dvpe();
-	dmt();
-
-	spin_lock_init(&freeIPIq.lock);
-
-	/*
-	 * We probably don't have as many VPEs as we do SMP "CPUs",
-	 * but it's possible - and in any case we'll never use more!
-	 */
-	for (i=0; i<NR_CPUS; i++) {
-		IPIQ[i].head = IPIQ[i].tail = NULL;
-		spin_lock_init(&IPIQ[i].lock);
-		IPIQ[i].depth = 0;
-		IPIQ[i].resched_flag = 0; /* No reschedules queued initially */
-	}
-
-	/* cpu_data index starts at zero */
-	cpu = 0;
-	cpu_data[cpu].vpe_id = 0;
-	cpu_data[cpu].tc_id = 0;
-	cpu_data[cpu].core = (read_c0_ebase() >> 1) & 0xff;
-	cpu++;
-
-	/* Report on boot-time options */
-	mips_mt_set_cpuoptions();
-	if (vpelimit > 0)
-		printk("Limit of %d VPEs set\n", vpelimit);
-	if (tclimit > 0)
-		printk("Limit of %d TCs set\n", tclimit);
-	if (nostlb) {
-		printk("Shared TLB Use Inhibited - UNSAFE for Multi-VPE Operation\n");
-	}
-	if (asidmask)
-		printk("ASID mask value override to 0x%x\n", asidmask);
-
-	/* Temporary */
-#ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG
-	if (hang_trig)
-		printk("Logic Analyser Trigger on suspected TC hang\n");
-#endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */
-
-	/* Put MVPE's into 'configuration state' */
-	write_c0_mvpcontrol( read_c0_mvpcontrol() | MVPCONTROL_VPC );
-
-	val = read_c0_mvpconf0();
-	nvpe = ((val & MVPCONF0_PVPE) >> MVPCONF0_PVPE_SHIFT) + 1;
-	if (vpelimit > 0 && nvpe > vpelimit)
-		nvpe = vpelimit;
-	ntc = ((val & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1;
-	if (ntc > NR_CPUS)
-		ntc = NR_CPUS;
-	if (tclimit > 0 && ntc > tclimit)
-		ntc = tclimit;
-	slop = ntc % nvpe;
-	for (i = 0; i < nvpe; i++) {
-		tcpervpe[i] = ntc / nvpe;
-		if (slop) {
-			if((slop - i) > 0) tcpervpe[i]++;
-		}
-	}
-	/* Handle command line override for VPE0 */
-	if (vpe0limit > ntc) vpe0limit = ntc;
-	if (vpe0limit > 0) {
-		int slopslop;
-		if (vpe0limit < tcpervpe[0]) {
-		    /* Reducing TC count - distribute to others */
-		    slop = tcpervpe[0] - vpe0limit;
-		    slopslop = slop % (nvpe - 1);
-		    tcpervpe[0] = vpe0limit;
-		    for (i = 1; i < nvpe; i++) {
-			tcpervpe[i] += slop / (nvpe - 1);
-			if(slopslop && ((slopslop - (i - 1) > 0)))
-				tcpervpe[i]++;
-		    }
-		} else if (vpe0limit > tcpervpe[0]) {
-		    /* Increasing TC count - steal from others */
-		    slop = vpe0limit - tcpervpe[0];
-		    slopslop = slop % (nvpe - 1);
-		    tcpervpe[0] = vpe0limit;
-		    for (i = 1; i < nvpe; i++) {
-			tcpervpe[i] -= slop / (nvpe - 1);
-			if(slopslop && ((slopslop - (i - 1) > 0)))
-				tcpervpe[i]--;
-		    }
-		}
-	}
-
-	/* Set up shared TLB */
-	smtc_configure_tlb();
-
-	for (tc = 0, vpe = 0 ; (vpe < nvpe) && (tc < ntc) ; vpe++) {
-		/* Get number of CP1 contexts for each VPE. */
-		if (tc == 0)
-		{
-			/*
-			 * Do not call settc() for TC0 or the FPU context
-			 * value will be incorrect. Besides, we know that
-			 * we are TC0 anyway.
-			 */
-			smtc_nconf1[0] = ((read_vpe_c0_vpeconf1() &
-				VPECONF1_NCP1) >> VPECONF1_NCP1_SHIFT);
-			if (nvpe == 2)
-			{
-				settc(1);
-				smtc_nconf1[1] = ((read_vpe_c0_vpeconf1() &
-					VPECONF1_NCP1) >> VPECONF1_NCP1_SHIFT);
-				settc(0);
-			}
-		}
-		if (tcpervpe[vpe] == 0)
-			continue;
-		if (vpe != 0)
-			printk(", ");
-		printk("VPE %d: TC", vpe);
-		for (i = 0; i < tcpervpe[vpe]; i++) {
-			/*
-			 * TC 0 is bound to VPE 0 at reset,
-			 * and is presumably executing this
-			 * code.  Leave it alone!
-			 */
-			if (tc != 0) {
-				smtc_tc_setup(vpe, tc, cpu);
-				if (vpe != 0) {
-					/*
-					 * Set MVP bit (possibly again).  Do it
-					 * here to catch CPUs that have no TCs
-					 * bound to the VPE at reset.  In that
-					 * case, a TC must be bound to the VPE
-					 * before we can set VPEControl[MVP]
-					 */
-					write_vpe_c0_vpeconf0(
-						read_vpe_c0_vpeconf0() |
-						VPECONF0_MVP);
-				}
-				cpu++;
-			}
-			printk(" %d", tc);
-			tc++;
-		}
-		if (vpe != 0) {
-			/*
-			 * Allow this VPE to control others.
-			 */
-			write_vpe_c0_vpeconf0(read_vpe_c0_vpeconf0() |
-					      VPECONF0_MVP);
-
-			/*
-			 * Clear any stale software interrupts from VPE's Cause
-			 */
-			write_vpe_c0_cause(0);
-
-			/*
-			 * Clear ERL/EXL of VPEs other than 0
-			 * and set restricted interrupt enable/mask.
-			 */
-			write_vpe_c0_status((read_vpe_c0_status()
-				& ~(ST0_BEV | ST0_ERL | ST0_EXL | ST0_IM))
-				| (STATUSF_IP0 | STATUSF_IP1 | STATUSF_IP7
-				| ST0_IE));
-			/*
-			 * set config to be the same as vpe0,
-			 *  particularly kseg0 coherency alg
-			 */
-			write_vpe_c0_config(read_c0_config());
-			/* Clear any pending timer interrupt */
-			write_vpe_c0_compare(0);
-			/* Propagate Config7 */
-			write_vpe_c0_config7(read_c0_config7());
-			write_vpe_c0_count(read_c0_count() + CP0_SKEW);
-			ehb();
-		}
-		/* enable multi-threading within VPE */
-		write_vpe_c0_vpecontrol(read_vpe_c0_vpecontrol() | VPECONTROL_TE);
-		/* enable the VPE */
-		write_vpe_c0_vpeconf0(read_vpe_c0_vpeconf0() | VPECONF0_VPA);
-	}
-
-	/*
-	 * Pull any physically present but unused TCs out of circulation.
-	 */
-	while (tc < (((val & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1)) {
-		set_cpu_possible(tc, false);
-		set_cpu_present(tc, false);
-		tc++;
-	}
-
-	/* release config state */
-	write_c0_mvpcontrol( read_c0_mvpcontrol() & ~ MVPCONTROL_VPC );
-
-	printk("\n");
-
-	/* Set up coprocessor affinity CPU mask(s) */
-
-#ifdef CONFIG_MIPS_MT_FPAFF
-	for (tc = 0; tc < ntc; tc++) {
-		if (cpu_data[tc].options & MIPS_CPU_FPU)
-			cpu_set(tc, mt_fpu_cpumask);
-	}
-#endif
-
-	/* set up ipi interrupts... */
-
-	/* If we have multiple VPEs running, set up the cross-VPE interrupt */
-
-	setup_cross_vpe_interrupts(nvpe);
-
-	/* Set up queue of free IPI "messages". */
-	nipi = NR_CPUS * IPIBUF_PER_CPU;
-	if (ipibuffers > 0)
-		nipi = ipibuffers;
-
-	pipi = kmalloc(nipi *sizeof(struct smtc_ipi), GFP_KERNEL);
-	if (pipi == NULL)
-		panic("kmalloc of IPI message buffers failed");
-	else
-		printk("IPI buffer pool of %d buffers\n", nipi);
-	for (i = 0; i < nipi; i++) {
-		smtc_ipi_nq(&freeIPIq, pipi);
-		pipi++;
-	}
-
-	/* Arm multithreading and enable other VPEs - but all TCs are Halted */
-	emt(EMT_ENABLE);
-	evpe(EVPE_ENABLE);
-	local_irq_restore(flags);
-	/* Initialize SMTC /proc statistics/diagnostics */
-	init_smtc_stats();
-}
-
-
-/*
- * Setup the PC, SP, and GP of a secondary processor and start it
- * running!
- * smp_bootstrap is the place to resume from
- * __KSTK_TOS(idle) is apparently the stack pointer
- * (unsigned long)idle->thread_info the gp
- *
- */
-void smtc_boot_secondary(int cpu, struct task_struct *idle)
-{
-	extern u32 kernelsp[NR_CPUS];
-	unsigned long flags;
-	int mtflags;
-
-	LOCK_MT_PRA();
-	if (cpu_data[cpu].vpe_id != cpu_data[smp_processor_id()].vpe_id) {
-		dvpe();
-	}
-	settc(cpu_data[cpu].tc_id);
-
-	/* pc */
-	write_tc_c0_tcrestart((unsigned long)&smp_bootstrap);
-
-	/* stack pointer */
-	kernelsp[cpu] = __KSTK_TOS(idle);
-	write_tc_gpr_sp(__KSTK_TOS(idle));
-
-	/* global pointer */
-	write_tc_gpr_gp((unsigned long)task_thread_info(idle));
-
-	smtc_status |= SMTC_MTC_ACTIVE;
-	write_tc_c0_tchalt(0);
-	if (cpu_data[cpu].vpe_id != cpu_data[smp_processor_id()].vpe_id) {
-		evpe(EVPE_ENABLE);
-	}
-	UNLOCK_MT_PRA();
-}
-
-void smtc_init_secondary(void)
-{
-}
-
-void smtc_smp_finish(void)
-{
-	int cpu = smp_processor_id();
-
-	/*
-	 * Lowest-numbered CPU per VPE starts a clock tick.
-	 * Like per_cpu_trap_init() hack, this assumes that
-	 * SMTC init code assigns TCs consdecutively and
-	 * in ascending order across available VPEs.
-	 */
-	if (cpu > 0 && (cpu_data[cpu].vpe_id != cpu_data[cpu - 1].vpe_id))
-		write_c0_compare(read_c0_count() + mips_hpt_frequency/HZ);
-
-	local_irq_enable();
-
-	printk("TC %d going on-line as CPU %d\n",
-		cpu_data[smp_processor_id()].tc_id, smp_processor_id());
-}
-
-void smtc_cpus_done(void)
-{
-}
-
-/*
- * Support for SMTC-optimized driver IRQ registration
- */
-
-/*
- * SMTC Kernel needs to manipulate low-level CPU interrupt mask
- * in do_IRQ. These are passed in setup_irq_smtc() and stored
- * in this table.
- */
-
-int setup_irq_smtc(unsigned int irq, struct irqaction * new,
-			unsigned long hwmask)
-{
-#ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG
-	unsigned int vpe = current_cpu_data.vpe_id;
-
-	vpemask[vpe][irq - MIPS_CPU_IRQ_BASE] = 1;
-#endif
-	irq_hwmask[irq] = hwmask;
-
-	return setup_irq(irq, new);
-}
-
-#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
-/*
- * Support for IRQ affinity to TCs
- */
-
-void smtc_set_irq_affinity(unsigned int irq, cpumask_t affinity)
-{
-	/*
-	 * If a "fast path" cache of quickly decodable affinity state
-	 * is maintained, this is where it gets done, on a call up
-	 * from the platform affinity code.
-	 */
-}
-
-void smtc_forward_irq(struct irq_data *d)
-{
-	unsigned int irq = d->irq;
-	int target;
-
-	/*
-	 * OK wise guy, now figure out how to get the IRQ
-	 * to be serviced on an authorized "CPU".
-	 *
-	 * Ideally, to handle the situation where an IRQ has multiple
-	 * eligible CPUS, we would maintain state per IRQ that would
-	 * allow a fair distribution of service requests.  Since the
-	 * expected use model is any-or-only-one, for simplicity
-	 * and efficiency, we just pick the easiest one to find.
-	 */
-
-	target = cpumask_first(d->affinity);
-
-	/*
-	 * We depend on the platform code to have correctly processed
-	 * IRQ affinity change requests to ensure that the IRQ affinity
-	 * mask has been purged of bits corresponding to nonexistent and
-	 * offline "CPUs", and to TCs bound to VPEs other than the VPE
-	 * connected to the physical interrupt input for the interrupt
-	 * in question.	 Otherwise we have a nasty problem with interrupt
-	 * mask management.  This is best handled in non-performance-critical
-	 * platform IRQ affinity setting code,	to minimize interrupt-time
-	 * checks.
-	 */
-
-	/* If no one is eligible, service locally */
-	if (target >= NR_CPUS)
-		do_IRQ_no_affinity(irq);
-	else
-		smtc_send_ipi(target, IRQ_AFFINITY_IPI, irq);
-}
-
-#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
-
-/*
- * IPI model for SMTC is tricky, because interrupts aren't TC-specific.
- * Within a VPE one TC can interrupt another by different approaches.
- * The easiest to get right would probably be to make all TCs except
- * the target IXMT and set a software interrupt, but an IXMT-based
- * scheme requires that a handler must run before a new IPI could
- * be sent, which would break the "broadcast" loops in MIPS MT.
- * A more gonzo approach within a VPE is to halt the TC, extract
- * its Restart, Status, and a couple of GPRs, and program the Restart
- * address to emulate an interrupt.
- *
- * Within a VPE, one can be confident that the target TC isn't in
- * a critical EXL state when halted, since the write to the Halt
- * register could not have issued on the writing thread if the
- * halting thread had EXL set. So k0 and k1 of the target TC
- * can be used by the injection code.  Across VPEs, one can't
- * be certain that the target TC isn't in a critical exception
- * state. So we try a two-step process of sending a software
- * interrupt to the target VPE, which either handles the event
- * itself (if it was the target) or injects the event within
- * the VPE.
- */
-
-static void smtc_ipi_qdump(void)
-{
-	int i;
-	struct smtc_ipi *temp;
-
-	for (i = 0; i < NR_CPUS ;i++) {
-		pr_info("IPIQ[%d]: head = 0x%x, tail = 0x%x, depth = %d\n",
-			i, (unsigned)IPIQ[i].head, (unsigned)IPIQ[i].tail,
-			IPIQ[i].depth);
-		temp = IPIQ[i].head;
-
-		while (temp != IPIQ[i].tail) {
-			pr_debug("%d %d %d: ", temp->type, temp->dest,
-			       (int)temp->arg);
-#ifdef	SMTC_IPI_DEBUG
-		    pr_debug("%u %lu\n", temp->sender, temp->stamp);
-#else
-		    pr_debug("\n");
-#endif
-		    temp = temp->flink;
-		}
-	}
-}
-
-/*
- * The standard atomic.h primitives don't quite do what we want
- * here: We need an atomic add-and-return-previous-value (which
- * could be done with atomic_add_return and a decrement) and an
- * atomic set/zero-and-return-previous-value (which can't really
- * be done with the atomic.h primitives). And since this is
- * MIPS MT, we can assume that we have LL/SC.
- */
-static inline int atomic_postincrement(atomic_t *v)
-{
-	unsigned long result;
-
-	unsigned long temp;
-
-	__asm__ __volatile__(
-	"1:	ll	%0, %2					\n"
-	"	addu	%1, %0, 1				\n"
-	"	sc	%1, %2					\n"
-	"	beqz	%1, 1b					\n"
-	__WEAK_LLSC_MB
-	: "=&r" (result), "=&r" (temp), "=m" (v->counter)
-	: "m" (v->counter)
-	: "memory");
-
-	return result;
-}
-
-void smtc_send_ipi(int cpu, int type, unsigned int action)
-{
-	int tcstatus;
-	struct smtc_ipi *pipi;
-	unsigned long flags;
-	int mtflags;
-	unsigned long tcrestart;
-	int set_resched_flag = (type == LINUX_SMP_IPI &&
-				action == SMP_RESCHEDULE_YOURSELF);
-
-	if (cpu == smp_processor_id()) {
-		printk("Cannot Send IPI to self!\n");
-		return;
-	}
-	if (set_resched_flag && IPIQ[cpu].resched_flag != 0)
-		return; /* There is a reschedule queued already */
-
-	/* Set up a descriptor, to be delivered either promptly or queued */
-	pipi = smtc_ipi_dq(&freeIPIq);
-	if (pipi == NULL) {
-		bust_spinlocks(1);
-		mips_mt_regdump(dvpe());
-		panic("IPI Msg. Buffers Depleted");
-	}
-	pipi->type = type;
-	pipi->arg = (void *)action;
-	pipi->dest = cpu;
-	if (cpu_data[cpu].vpe_id != cpu_data[smp_processor_id()].vpe_id) {
-		/* If not on same VPE, enqueue and send cross-VPE interrupt */
-		IPIQ[cpu].resched_flag |= set_resched_flag;
-		smtc_ipi_nq(&IPIQ[cpu], pipi);
-		LOCK_CORE_PRA();
-		settc(cpu_data[cpu].tc_id);
-		write_vpe_c0_cause(read_vpe_c0_cause() | C_SW1);
-		UNLOCK_CORE_PRA();
-	} else {
-		/*
-		 * Not sufficient to do a LOCK_MT_PRA (dmt) here,
-		 * since ASID shootdown on the other VPE may
-		 * collide with this operation.
-		 */
-		LOCK_CORE_PRA();
-		settc(cpu_data[cpu].tc_id);
-		/* Halt the targeted TC */
-		write_tc_c0_tchalt(TCHALT_H);
-		mips_ihb();
-
-		/*
-		 * Inspect TCStatus - if IXMT is set, we have to queue
-		 * a message. Otherwise, we set up the "interrupt"
-		 * of the other TC
-		 */
-		tcstatus = read_tc_c0_tcstatus();
-
-		if ((tcstatus & TCSTATUS_IXMT) != 0) {
-			/*
-			 * If we're in the the irq-off version of the wait
-			 * loop, we need to force exit from the wait and
-			 * do a direct post of the IPI.
-			 */
-			if (cpu_wait == r4k_wait_irqoff) {
-				tcrestart = read_tc_c0_tcrestart();
-				if (address_is_in_r4k_wait_irqoff(tcrestart)) {
-					write_tc_c0_tcrestart(__pastwait);
-					tcstatus &= ~TCSTATUS_IXMT;
-					write_tc_c0_tcstatus(tcstatus);
-					goto postdirect;
-				}
-			}
-			/*
-			 * Otherwise we queue the message for the target TC
-			 * to pick up when he does a local_irq_restore()
-			 */
-			write_tc_c0_tchalt(0);
-			UNLOCK_CORE_PRA();
-			IPIQ[cpu].resched_flag |= set_resched_flag;
-			smtc_ipi_nq(&IPIQ[cpu], pipi);
-		} else {
-postdirect:
-			post_direct_ipi(cpu, pipi);
-			write_tc_c0_tchalt(0);
-			UNLOCK_CORE_PRA();
-		}
-	}
-}
-
-/*
- * Send IPI message to Halted TC, TargTC/TargVPE already having been set
- */
-static void post_direct_ipi(int cpu, struct smtc_ipi *pipi)
-{
-	struct pt_regs *kstack;
-	unsigned long tcstatus;
-	unsigned long tcrestart;
-	extern u32 kernelsp[NR_CPUS];
-	extern void __smtc_ipi_vector(void);
-//printk("%s: on %d for %d\n", __func__, smp_processor_id(), cpu);
-
-	/* Extract Status, EPC from halted TC */
-	tcstatus = read_tc_c0_tcstatus();
-	tcrestart = read_tc_c0_tcrestart();
-	/* If TCRestart indicates a WAIT instruction, advance the PC */
-	if ((tcrestart & 0x80000000)
-	    && ((*(unsigned int *)tcrestart & 0xfe00003f) == 0x42000020)) {
-		tcrestart += 4;
-	}
-	/*
-	 * Save on TC's future kernel stack
-	 *
-	 * CU bit of Status is indicator that TC was
-	 * already running on a kernel stack...
-	 */
-	if (tcstatus & ST0_CU0)	 {
-		/* Note that this "- 1" is pointer arithmetic */
-		kstack = ((struct pt_regs *)read_tc_gpr_sp()) - 1;
-	} else {
-		kstack = ((struct pt_regs *)kernelsp[cpu]) - 1;
-	}
-
-	kstack->cp0_epc = (long)tcrestart;
-	/* Save TCStatus */
-	kstack->cp0_tcstatus = tcstatus;
-	/* Pass token of operation to be performed kernel stack pad area */
-	kstack->pad0[4] = (unsigned long)pipi;
-	/* Pass address of function to be called likewise */
-	kstack->pad0[5] = (unsigned long)&ipi_decode;
-	/* Set interrupt exempt and kernel mode */
-	tcstatus |= TCSTATUS_IXMT;
-	tcstatus &= ~TCSTATUS_TKSU;
-	write_tc_c0_tcstatus(tcstatus);
-	ehb();
-	/* Set TC Restart address to be SMTC IPI vector */
-	write_tc_c0_tcrestart(__smtc_ipi_vector);
-}
-
-static void ipi_resched_interrupt(void)
-{
-	scheduler_ipi();
-}
-
-static void ipi_call_interrupt(void)
-{
-	/* Invoke generic function invocation code in smp.c */
-	smp_call_function_interrupt();
-}
-
-DECLARE_PER_CPU(struct clock_event_device, mips_clockevent_device);
-
-static void __irq_entry smtc_clock_tick_interrupt(void)
-{
-	unsigned int cpu = smp_processor_id();
-	struct clock_event_device *cd;
-	int irq = MIPS_CPU_IRQ_BASE + 1;
-
-	irq_enter();
-	kstat_incr_irq_this_cpu(irq);
-	cd = &per_cpu(mips_clockevent_device, cpu);
-	cd->event_handler(cd);
-	irq_exit();
-}
-
-void ipi_decode(struct smtc_ipi *pipi)
-{
-	void *arg_copy = pipi->arg;
-	int type_copy = pipi->type;
-
-	smtc_ipi_nq(&freeIPIq, pipi);
-
-	switch (type_copy) {
-	case SMTC_CLOCK_TICK:
-		smtc_clock_tick_interrupt();
-		break;
-
-	case LINUX_SMP_IPI:
-		switch ((int)arg_copy) {
-		case SMP_RESCHEDULE_YOURSELF:
-			ipi_resched_interrupt();
-			break;
-		case SMP_CALL_FUNCTION:
-			ipi_call_interrupt();
-			break;
-		default:
-			printk("Impossible SMTC IPI Argument %p\n", arg_copy);
-			break;
-		}
-		break;
-#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
-	case IRQ_AFFINITY_IPI:
-		/*
-		 * Accept a "forwarded" interrupt that was initially
-		 * taken by a TC who doesn't have affinity for the IRQ.
-		 */
-		do_IRQ_no_affinity((int)arg_copy);
-		break;
-#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
-	default:
-		printk("Impossible SMTC IPI Type 0x%x\n", type_copy);
-		break;
-	}
-}
-
-/*
- * Similar to smtc_ipi_replay(), but invoked from context restore,
- * so it reuses the current exception frame rather than set up a
- * new one with self_ipi.
- */
-
-void deferred_smtc_ipi(void)
-{
-	int cpu = smp_processor_id();
-
-	/*
-	 * Test is not atomic, but much faster than a dequeue,
-	 * and the vast majority of invocations will have a null queue.
-	 * If irq_disabled when this was called, then any IPIs queued
-	 * after we test last will be taken on the next irq_enable/restore.
-	 * If interrupts were enabled, then any IPIs added after the
-	 * last test will be taken directly.
-	 */
-
-	while (IPIQ[cpu].head != NULL) {
-		struct smtc_ipi_q *q = &IPIQ[cpu];
-		struct smtc_ipi *pipi;
-		unsigned long flags;
-
-		/*
-		 * It may be possible we'll come in with interrupts
-		 * already enabled.
-		 */
-		local_irq_save(flags);
-		spin_lock(&q->lock);
-		pipi = __smtc_ipi_dq(q);
-		spin_unlock(&q->lock);
-		if (pipi != NULL) {
-			if (pipi->type == LINUX_SMP_IPI &&
-			    (int)pipi->arg == SMP_RESCHEDULE_YOURSELF)
-				IPIQ[cpu].resched_flag = 0;
-			ipi_decode(pipi);
-		}
-		/*
-		 * The use of the __raw_local restore isn't
-		 * as obviously necessary here as in smtc_ipi_replay(),
-		 * but it's more efficient, given that we're already
-		 * running down the IPI queue.
-		 */
-		__arch_local_irq_restore(flags);
-	}
-}
-
-/*
- * Cross-VPE interrupts in the SMTC prototype use "software interrupts"
- * set via cross-VPE MTTR manipulation of the Cause register. It would be
- * in some regards preferable to have external logic for "doorbell" hardware
- * interrupts.
- */
-
-static int cpu_ipi_irq = MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_IRQ;
-
-static irqreturn_t ipi_interrupt(int irq, void *dev_idm)
-{
-	int my_vpe = cpu_data[smp_processor_id()].vpe_id;
-	int my_tc = cpu_data[smp_processor_id()].tc_id;
-	int cpu;
-	struct smtc_ipi *pipi;
-	unsigned long tcstatus;
-	int sent;
-	unsigned long flags;
-	unsigned int mtflags;
-	unsigned int vpflags;
-
-	/*
-	 * So long as cross-VPE interrupts are done via
-	 * MFTR/MTTR read-modify-writes of Cause, we need
-	 * to stop other VPEs whenever the local VPE does
-	 * anything similar.
-	 */
-	local_irq_save(flags);
-	vpflags = dvpe();
-	clear_c0_cause(0x100 << MIPS_CPU_IPI_IRQ);
-	set_c0_status(0x100 << MIPS_CPU_IPI_IRQ);
-	irq_enable_hazard();
-	evpe(vpflags);
-	local_irq_restore(flags);
-
-	/*
-	 * Cross-VPE Interrupt handler: Try to directly deliver IPIs
-	 * queued for TCs on this VPE other than the current one.
-	 * Return-from-interrupt should cause us to drain the queue
-	 * for the current TC, so we ought not to have to do it explicitly here.
-	 */
-
-	for_each_online_cpu(cpu) {
-		if (cpu_data[cpu].vpe_id != my_vpe)
-			continue;
-
-		pipi = smtc_ipi_dq(&IPIQ[cpu]);
-		if (pipi != NULL) {
-			if (cpu_data[cpu].tc_id != my_tc) {
-				sent = 0;
-				LOCK_MT_PRA();
-				settc(cpu_data[cpu].tc_id);
-				write_tc_c0_tchalt(TCHALT_H);
-				mips_ihb();
-				tcstatus = read_tc_c0_tcstatus();
-				if ((tcstatus & TCSTATUS_IXMT) == 0) {
-					post_direct_ipi(cpu, pipi);
-					sent = 1;
-				}
-				write_tc_c0_tchalt(0);
-				UNLOCK_MT_PRA();
-				if (!sent) {
-					smtc_ipi_req(&IPIQ[cpu], pipi);
-				}
-			} else {
-				/*
-				 * ipi_decode() should be called
-				 * with interrupts off
-				 */
-				local_irq_save(flags);
-				if (pipi->type == LINUX_SMP_IPI &&
-				    (int)pipi->arg == SMP_RESCHEDULE_YOURSELF)
-					IPIQ[cpu].resched_flag = 0;
-				ipi_decode(pipi);
-				local_irq_restore(flags);
-			}
-		}
-	}
-
-	return IRQ_HANDLED;
-}
-
-static void ipi_irq_dispatch(void)
-{
-	do_IRQ(cpu_ipi_irq);
-}
-
-static struct irqaction irq_ipi = {
-	.handler	= ipi_interrupt,
-	.flags		= IRQF_PERCPU,
-	.name		= "SMTC_IPI"
-};
-
-static void setup_cross_vpe_interrupts(unsigned int nvpe)
-{
-	if (nvpe < 1)
-		return;
-
-	if (!cpu_has_vint)
-		panic("SMTC Kernel requires Vectored Interrupt support");
-
-	set_vi_handler(MIPS_CPU_IPI_IRQ, ipi_irq_dispatch);
-
-	setup_irq_smtc(cpu_ipi_irq, &irq_ipi, (0x100 << MIPS_CPU_IPI_IRQ));
-
-	irq_set_handler(cpu_ipi_irq, handle_percpu_irq);
-}
-
-/*
- * SMTC-specific hacks invoked from elsewhere in the kernel.
- */
-
- /*
-  * smtc_ipi_replay is called from raw_local_irq_restore
-  */
-
-void smtc_ipi_replay(void)
-{
-	unsigned int cpu = smp_processor_id();
-
-	/*
-	 * To the extent that we've ever turned interrupts off,
-	 * we may have accumulated deferred IPIs.  This is subtle.
-	 * we should be OK:  If we pick up something and dispatch
-	 * it here, that's great. If we see nothing, but concurrent
-	 * with this operation, another TC sends us an IPI, IXMT
-	 * is clear, and we'll handle it as a real pseudo-interrupt
-	 * and not a pseudo-pseudo interrupt.  The important thing
-	 * is to do the last check for queued message *after* the
-	 * re-enabling of interrupts.
-	 */
-	while (IPIQ[cpu].head != NULL) {
-		struct smtc_ipi_q *q = &IPIQ[cpu];
-		struct smtc_ipi *pipi;
-		unsigned long flags;
-
-		/*
-		 * It's just possible we'll come in with interrupts
-		 * already enabled.
-		 */
-		local_irq_save(flags);
-
-		spin_lock(&q->lock);
-		pipi = __smtc_ipi_dq(q);
-		spin_unlock(&q->lock);
-		/*
-		 ** But use a raw restore here to avoid recursion.
-		 */
-		__arch_local_irq_restore(flags);
-
-		if (pipi) {
-			self_ipi(pipi);
-			smtc_cpu_stats[cpu].selfipis++;
-		}
-	}
-}
-
-EXPORT_SYMBOL(smtc_ipi_replay);
-
-void smtc_idle_loop_hook(void)
-{
-#ifdef CONFIG_SMTC_IDLE_HOOK_DEBUG
-	int im;
-	int flags;
-	int mtflags;
-	int bit;
-	int vpe;
-	int tc;
-	int hook_ntcs;
-	/*
-	 * printk within DMT-protected regions can deadlock,
-	 * so buffer diagnostic messages for later output.
-	 */
-	char *pdb_msg;
-	char id_ho_db_msg[768]; /* worst-case use should be less than 700 */
-
-	if (atomic_read(&idle_hook_initialized) == 0) { /* fast test */
-		if (atomic_add_return(1, &idle_hook_initialized) == 1) {
-			int mvpconf0;
-			/* Tedious stuff to just do once */
-			mvpconf0 = read_c0_mvpconf0();
-			hook_ntcs = ((mvpconf0 & MVPCONF0_PTC) >> MVPCONF0_PTC_SHIFT) + 1;
-			if (hook_ntcs > NR_CPUS)
-				hook_ntcs = NR_CPUS;
-			for (tc = 0; tc < hook_ntcs; tc++) {
-				tcnoprog[tc] = 0;
-				clock_hang_reported[tc] = 0;
-			}
-			for (vpe = 0; vpe < 2; vpe++)
-				for (im = 0; im < 8; im++)
-					imstuckcount[vpe][im] = 0;
-			printk("Idle loop test hook initialized for %d TCs\n", hook_ntcs);
-			atomic_set(&idle_hook_initialized, 1000);
-		} else {
-			/* Someone else is initializing in parallel - let 'em finish */
-			while (atomic_read(&idle_hook_initialized) < 1000)
-				;
-		}
-	}
-
-	/* Have we stupidly left IXMT set somewhere? */
-	if (read_c0_tcstatus() & 0x400) {
-		write_c0_tcstatus(read_c0_tcstatus() & ~0x400);
-		ehb();
-		printk("Dangling IXMT in cpu_idle()\n");
-	}
-
-	/* Have we stupidly left an IM bit turned off? */
-#define IM_LIMIT 2000
-	local_irq_save(flags);
-	mtflags = dmt();
-	pdb_msg = &id_ho_db_msg[0];
-	im = read_c0_status();
-	vpe = current_cpu_data.vpe_id;
-	for (bit = 0; bit < 8; bit++) {
-		/*
-		 * In current prototype, I/O interrupts
-		 * are masked for VPE > 0
-		 */
-		if (vpemask[vpe][bit]) {
-			if (!(im & (0x100 << bit)))
-				imstuckcount[vpe][bit]++;
-			else
-				imstuckcount[vpe][bit] = 0;
-			if (imstuckcount[vpe][bit] > IM_LIMIT) {
-				set_c0_status(0x100 << bit);
-				ehb();
-				imstuckcount[vpe][bit] = 0;
-				pdb_msg += sprintf(pdb_msg,
-					"Dangling IM %d fixed for VPE %d\n", bit,
-					vpe);
-			}
-		}
-	}
-
-	emt(mtflags);
-	local_irq_restore(flags);
-	if (pdb_msg != &id_ho_db_msg[0])
-		printk("CPU%d: %s", smp_processor_id(), id_ho_db_msg);
-#endif /* CONFIG_SMTC_IDLE_HOOK_DEBUG */
-
-	smtc_ipi_replay();
-}
-
-void smtc_soft_dump(void)
-{
-	int i;
-
-	printk("Counter Interrupts taken per CPU (TC)\n");
-	for (i=0; i < NR_CPUS; i++) {
-		printk("%d: %ld\n", i, smtc_cpu_stats[i].timerints);
-	}
-	printk("Self-IPI invocations:\n");
-	for (i=0; i < NR_CPUS; i++) {
-		printk("%d: %ld\n", i, smtc_cpu_stats[i].selfipis);
-	}
-	smtc_ipi_qdump();
-	printk("%d Recoveries of \"stolen\" FPU\n",
-	       atomic_read(&smtc_fpu_recoveries));
-}
-
-
-/*
- * TLB management routines special to SMTC
- */
-
-void smtc_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu)
-{
-	unsigned long flags, mtflags, tcstat, prevhalt, asid;
-	int tlb, i;
-
-	/*
-	 * It would be nice to be able to use a spinlock here,
-	 * but this is invoked from within TLB flush routines
-	 * that protect themselves with DVPE, so if a lock is
-	 * held by another TC, it'll never be freed.
-	 *
-	 * DVPE/DMT must not be done with interrupts enabled,
-	 * so even so most callers will already have disabled
-	 * them, let's be really careful...
-	 */
-
-	local_irq_save(flags);
-	if (smtc_status & SMTC_TLB_SHARED) {
-		mtflags = dvpe();
-		tlb = 0;
-	} else {
-		mtflags = dmt();
-		tlb = cpu_data[cpu].vpe_id;
-	}
-	asid = asid_cache(cpu);
-
-	do {
-		if (!((asid += ASID_INC) & ASID_MASK) ) {
-			if (cpu_has_vtag_icache)
-				flush_icache_all();
-			/* Traverse all online CPUs (hack requires contiguous range) */
-			for_each_online_cpu(i) {
-				/*
-				 * We don't need to worry about our own CPU, nor those of
-				 * CPUs who don't share our TLB.
-				 */
-				if ((i != smp_processor_id()) &&
-				    ((smtc_status & SMTC_TLB_SHARED) ||
-				     (cpu_data[i].vpe_id == cpu_data[cpu].vpe_id))) {
-					settc(cpu_data[i].tc_id);
-					prevhalt = read_tc_c0_tchalt() & TCHALT_H;
-					if (!prevhalt) {
-						write_tc_c0_tchalt(TCHALT_H);
-						mips_ihb();
-					}
-					tcstat = read_tc_c0_tcstatus();
-					smtc_live_asid[tlb][(tcstat & ASID_MASK)] |= (asiduse)(0x1 << i);
-					if (!prevhalt)
-						write_tc_c0_tchalt(0);
-				}
-			}
-			if (!asid)		/* fix version if needed */
-				asid = ASID_FIRST_VERSION;
-			local_flush_tlb_all();	/* start new asid cycle */
-		}
-	} while (smtc_live_asid[tlb][(asid & ASID_MASK)]);
-
-	/*
-	 * SMTC shares the TLB within VPEs and possibly across all VPEs.
-	 */
-	for_each_online_cpu(i) {
-		if ((smtc_status & SMTC_TLB_SHARED) ||
-		    (cpu_data[i].vpe_id == cpu_data[cpu].vpe_id))
-			cpu_context(i, mm) = asid_cache(i) = asid;
-	}
-
-	if (smtc_status & SMTC_TLB_SHARED)
-		evpe(mtflags);
-	else
-		emt(mtflags);
-	local_irq_restore(flags);
-}
-
-/*
- * Invoked from macros defined in mmu_context.h
- * which must already have disabled interrupts
- * and done a DVPE or DMT as appropriate.
- */
-
-void smtc_flush_tlb_asid(unsigned long asid)
-{
-	int entry;
-	unsigned long ehi;
-
-	entry = read_c0_wired();
-
-	/* Traverse all non-wired entries */
-	while (entry < current_cpu_data.tlbsize) {
-		write_c0_index(entry);
-		ehb();
-		tlb_read();
-		ehb();
-		ehi = read_c0_entryhi();
-		if ((ehi & ASID_MASK) == asid) {
-		    /*
-		     * Invalidate only entries with specified ASID,
-		     * makiing sure all entries differ.
-		     */
-		    write_c0_entryhi(CKSEG0 + (entry << (PAGE_SHIFT + 1)));
-		    write_c0_entrylo0(0);
-		    write_c0_entrylo1(0);
-		    mtc0_tlbw_hazard();
-		    tlb_write_indexed();
-		}
-		entry++;
-	}
-	write_c0_index(PARKED_INDEX);
-	tlbw_use_hazard();
-}
-
-/*
- * Support for single-threading cache flush operations.
- */
-
-static int halt_state_save[NR_CPUS];
-
-/*
- * To really, really be sure that nothing is being done
- * by other TCs, halt them all.	 This code assumes that
- * a DVPE has already been done, so while their Halted
- * state is theoretically architecturally unstable, in
- * practice, it's not going to change while we're looking
- * at it.
- */
-
-void smtc_cflush_lockdown(void)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if (cpu != smp_processor_id()) {
-			settc(cpu_data[cpu].tc_id);
-			halt_state_save[cpu] = read_tc_c0_tchalt();
-			write_tc_c0_tchalt(TCHALT_H);
-		}
-	}
-	mips_ihb();
-}
-
-/* It would be cheating to change the cpu_online states during a flush! */
-
-void smtc_cflush_release(void)
-{
-	int cpu;
-
-	/*
-	 * Start with a hazard barrier to ensure
-	 * that all CACHE ops have played through.
-	 */
-	mips_ihb();
-
-	for_each_online_cpu(cpu) {
-		if (cpu != smp_processor_id()) {
-			settc(cpu_data[cpu].tc_id);
-			write_tc_c0_tchalt(halt_state_save[cpu]);
-		}
-	}
-	mips_ihb();
-}
diff --git a/arch/mips/kernel/sync-r4k.c b/arch/mips/kernel/sync-r4k.c
index c24ad5f4b32..2242bdd4370 100644
--- a/arch/mips/kernel/sync-r4k.c
+++ b/arch/mips/kernel/sync-r4k.c
@@ -6,8 +6,6 @@
  * not have done anything significant (but they may have had interrupts
  * enabled briefly - prom_smp_finish() should not be responsible for enabling
  * interrupts...)
- *
- * FIXME: broken for SMTC
  */
 
 #include <linux/kernel.h>
@@ -33,14 +31,6 @@ void synchronise_count_master(int cpu)
 	unsigned long flags;
 	unsigned int initcount;
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * SMTC needs to synchronise per VPE, not per CPU
-	 * ignore for now
-	 */
-	return;
-#endif
-
 	printk(KERN_INFO "Synchronize counters for CPU %u: ", cpu);
 
 	local_irq_save(flags);
@@ -110,14 +100,6 @@ void synchronise_count_slave(int cpu)
 	int i;
 	unsigned int initcount;
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * SMTC needs to synchronise per VPE, not per CPU
-	 * ignore for now
-	 */
-	return;
-#endif
-
 	/*
 	 * Not every cpu is online at the time this gets called,
 	 * so we first wait for the master to say everyone is ready
diff --git a/arch/mips/kernel/time.c b/arch/mips/kernel/time.c
index dcb8e5d3bb8..8d0170969e2 100644
--- a/arch/mips/kernel/time.c
+++ b/arch/mips/kernel/time.c
@@ -26,7 +26,6 @@
 #include <asm/cpu-features.h>
 #include <asm/cpu-type.h>
 #include <asm/div64.h>
-#include <asm/smtc_ipi.h>
 #include <asm/time.h>
 
 /*
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 8119ac2fdfc..51706d6dd5b 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -15,6 +15,7 @@
 #include <linux/bug.h>
 #include <linux/compiler.h>
 #include <linux/context_tracking.h>
+#include <linux/cpu_pm.h>
 #include <linux/kexec.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -370,9 +371,6 @@ void __noreturn die(const char *str, struct pt_regs *regs)
 {
 	static int die_counter;
 	int sig = SIGSEGV;
-#ifdef CONFIG_MIPS_MT_SMTC
-	unsigned long dvpret;
-#endif /* CONFIG_MIPS_MT_SMTC */
 
 	oops_enter();
 
@@ -382,13 +380,7 @@ void __noreturn die(const char *str, struct pt_regs *regs)
 
 	console_verbose();
 	raw_spin_lock_irq(&die_lock);
-#ifdef CONFIG_MIPS_MT_SMTC
-	dvpret = dvpe();
-#endif /* CONFIG_MIPS_MT_SMTC */
 	bust_spinlocks(1);
-#ifdef CONFIG_MIPS_MT_SMTC
-	mips_mt_regdump(dvpret);
-#endif /* CONFIG_MIPS_MT_SMTC */
 
 	printk("%s[#%d]:\n", str, ++die_counter);
 	show_registers(regs);
@@ -712,10 +704,12 @@ int process_fpemu_return(int sig, void __user *fault_addr)
 		si.si_addr = fault_addr;
 		si.si_signo = sig;
 		if (sig == SIGSEGV) {
+			down_read(&current->mm->mmap_sem);
 			if (find_vma(current->mm, (unsigned long)fault_addr))
 				si.si_code = SEGV_ACCERR;
 			else
 				si.si_code = SEGV_MAPERR;
+			up_read(&current->mm->mmap_sem);
 		} else {
 			si.si_code = BUS_ADRERR;
 		}
@@ -1759,19 +1753,6 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
 		extern char rollback_except_vec_vi;
 		char *vec_start = using_rollback_handler() ?
 			&rollback_except_vec_vi : &except_vec_vi;
-#ifdef CONFIG_MIPS_MT_SMTC
-		/*
-		 * We need to provide the SMTC vectored interrupt handler
-		 * not only with the address of the handler, but with the
-		 * Status.IM bit to be masked before going there.
-		 */
-		extern char except_vec_vi_mori;
-#if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
-		const int mori_offset = &except_vec_vi_mori - vec_start + 2;
-#else
-		const int mori_offset = &except_vec_vi_mori - vec_start;
-#endif
-#endif /* CONFIG_MIPS_MT_SMTC */
 #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN)
 		const int lui_offset = &except_vec_vi_lui - vec_start + 2;
 		const int ori_offset = &except_vec_vi_ori - vec_start + 2;
@@ -1795,12 +1776,6 @@ static void *set_vi_srs_handler(int n, vi_handler_t addr, int srs)
 #else
 				handler_len);
 #endif
-#ifdef CONFIG_MIPS_MT_SMTC
-		BUG_ON(n > 7);	/* Vector index %d exceeds SMTC maximum. */
-
-		h = (u16 *)(b + mori_offset);
-		*h = (0x100 << n);
-#endif /* CONFIG_MIPS_MT_SMTC */
 		h = (u16 *)(b + lui_offset);
 		*h = (handler >> 16) & 0xffff;
 		h = (u16 *)(b + ori_offset);
@@ -1865,32 +1840,16 @@ static int __init ulri_disable(char *s)
 }
 __setup("noulri", ulri_disable);
 
-void per_cpu_trap_init(bool is_boot_cpu)
+/* configure STATUS register */
+static void configure_status(void)
 {
-	unsigned int cpu = smp_processor_id();
-	unsigned int status_set = ST0_CU0;
-	unsigned int hwrena = cpu_hwrena_impl_bits;
-#ifdef CONFIG_MIPS_MT_SMTC
-	int secondaryTC = 0;
-	int bootTC = (cpu == 0);
-
-	/*
-	 * Only do per_cpu_trap_init() for first TC of Each VPE.
-	 * Note that this hack assumes that the SMTC init code
-	 * assigns TCs consecutively and in ascending order.
-	 */
-
-	if (((read_c0_tcbind() & TCBIND_CURTC) != 0) &&
-	    ((read_c0_tcbind() & TCBIND_CURVPE) == cpu_data[cpu - 1].vpe_id))
-		secondaryTC = 1;
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 	/*
 	 * Disable coprocessors and select 32-bit or 64-bit addressing
 	 * and the 16/32 or 32/32 FPR register model.  Reset the BEV
 	 * flag that some firmware may have left set and the TS bit (for
 	 * IP27).  Set XX for ISA IV code to work.
 	 */
+	unsigned int status_set = ST0_CU0;
 #ifdef CONFIG_64BIT
 	status_set |= ST0_FR|ST0_KX|ST0_SX|ST0_UX;
 #endif
@@ -1901,6 +1860,12 @@ void per_cpu_trap_init(bool is_boot_cpu)
 
 	change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX,
 			 status_set);
+}
+
+/* configure HWRENA register */
+static void configure_hwrena(void)
+{
+	unsigned int hwrena = cpu_hwrena_impl_bits;
 
 	if (cpu_has_mips_r2)
 		hwrena |= 0x0000000f;
@@ -1910,11 +1875,10 @@ void per_cpu_trap_init(bool is_boot_cpu)
 
 	if (hwrena)
 		write_c0_hwrena(hwrena);
+}
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	if (!secondaryTC) {
-#endif /* CONFIG_MIPS_MT_SMTC */
-
+static void configure_exception_vector(void)
+{
 	if (cpu_has_veic || cpu_has_vint) {
 		unsigned long sr = set_c0_status(ST0_BEV);
 		write_c0_ebase(ebase);
@@ -1930,6 +1894,16 @@ void per_cpu_trap_init(bool is_boot_cpu)
 		} else
 			set_c0_cause(CAUSEF_IV);
 	}
+}
+
+void per_cpu_trap_init(bool is_boot_cpu)
+{
+	unsigned int cpu = smp_processor_id();
+
+	configure_status();
+	configure_hwrena();
+
+	configure_exception_vector();
 
 	/*
 	 * Before R2 both interrupt numbers were fixed to 7, so on R2 only:
@@ -1949,10 +1923,6 @@ void per_cpu_trap_init(bool is_boot_cpu)
 		cp0_perfcount_irq = -1;
 	}
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	}
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 	if (!cpu_data[cpu].asid_cache)
 		cpu_data[cpu].asid_cache = ASID_FIRST_VERSION;
 
@@ -1961,23 +1931,10 @@ void per_cpu_trap_init(bool is_boot_cpu)
 	BUG_ON(current->mm);
 	enter_lazy_tlb(&init_mm, current);
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	if (bootTC) {
-#endif /* CONFIG_MIPS_MT_SMTC */
 		/* Boot CPU's cache setup in setup_arch(). */
 		if (!is_boot_cpu)
 			cpu_cache_init();
 		tlb_init();
-#ifdef CONFIG_MIPS_MT_SMTC
-	} else if (!secondaryTC) {
-		/*
-		 * First TC in non-boot VPE must do subset of tlb_init()
-		 * for MMU countrol registers.
-		 */
-		write_c0_pagemask(PM_DEFAULT_MASK);
-		write_c0_wired(0);
-	}
-#endif /* CONFIG_MIPS_MT_SMTC */
 	TLBMISS_HANDLER_SETUP();
 }
 
@@ -2185,3 +2142,32 @@ void __init trap_init(void)
 
 	cu2_notifier(default_cu2_call, 0x80000000);	/* Run last  */
 }
+
+static int trap_pm_notifier(struct notifier_block *self, unsigned long cmd,
+			    void *v)
+{
+	switch (cmd) {
+	case CPU_PM_ENTER_FAILED:
+	case CPU_PM_EXIT:
+		configure_status();
+		configure_hwrena();
+		configure_exception_vector();
+
+		/* Restore register with CPU number for TLB handlers */
+		TLBMISS_HANDLER_RESTORE();
+
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block trap_pm_notifier_block = {
+	.notifier_call = trap_pm_notifier,
+};
+
+static int __init trap_pm_init(void)
+{
+	return cpu_pm_register_notifier(&trap_pm_notifier_block);
+}
+arch_initcall(trap_pm_init);
diff --git a/arch/mips/kernel/vpe-mt.c b/arch/mips/kernel/vpe-mt.c
index 949ae0e1701..2e003b11a09 100644
--- a/arch/mips/kernel/vpe-mt.c
+++ b/arch/mips/kernel/vpe-mt.c
@@ -127,9 +127,8 @@ int vpe_run(struct vpe *v)
 	clear_c0_mvpcontrol(MVPCONTROL_VPC);
 
 	/*
-	 * SMTC/SMVP kernels manage VPE enable independently,
-	 * but uniprocessor kernels need to turn it on, even
-	 * if that wasn't the pre-dvpe() state.
+	 * SMVP kernels manage VPE enable independently, but uniprocessor
+	 * kernels need to turn it on, even if that wasn't the pre-dvpe() state.
 	 */
 #ifdef CONFIG_SMP
 	evpe(vpeflags);
@@ -454,12 +453,11 @@ int __init vpe_module_init(void)
 
 			settc(tc);
 
-			/* Any TC that is bound to VPE0 gets left as is - in
-			 * case we are running SMTC on VPE0. A TC that is bound
-			 * to any other VPE gets bound to VPE0, ideally I'd like
-			 * to make it homeless but it doesn't appear to let me
-			 * bind a TC to a non-existent VPE. Which is perfectly
-			 * reasonable.
+			/*
+			 * A TC that is bound to any other VPE gets bound to
+			 * VPE0, ideally I'd like to make it homeless but it
+			 * doesn't appear to let me bind a TC to a non-existent
+			 * VPE. Which is perfectly reasonable.
 			 *
 			 * The (un)bound state is visible to an EJTAG probe so
 			 * may notify GDB...
diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile
index 78d87bbc99d..401fe027c26 100644
--- a/arch/mips/kvm/Makefile
+++ b/arch/mips/kvm/Makefile
@@ -5,9 +5,9 @@ common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)
 
 EXTRA_CFLAGS += -Ivirt/kvm -Iarch/mips/kvm
 
-kvm-objs := $(common-objs) kvm_mips.o kvm_mips_emul.o kvm_locore.o \
-	    kvm_mips_int.o kvm_mips_stats.o kvm_mips_commpage.o \
-	    kvm_mips_dyntrans.o kvm_trap_emul.o
+kvm-objs := $(common-objs) mips.o emulate.o locore.o \
+	    interrupt.o stats.o commpage.o \
+	    dyntrans.o trap_emul.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
-obj-y			+= kvm_cb.o kvm_tlb.o
+obj-y			+= callback.o tlb.o
diff --git a/arch/mips/kvm/kvm_cb.c b/arch/mips/kvm/callback.c
index 313c2e37b97..313c2e37b97 100644
--- a/arch/mips/kvm/kvm_cb.c
+++ b/arch/mips/kvm/callback.c
diff --git a/arch/mips/kvm/commpage.c b/arch/mips/kvm/commpage.c
new file mode 100644
index 00000000000..2d6e976d1ad
--- /dev/null
+++ b/arch/mips/kvm/commpage.c
@@ -0,0 +1,33 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * commpage, currently used for Virtual COP0 registers.
+ * Mapped into the guest kernel @ 0x0.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <linux/bootmem.h>
+#include <asm/page.h>
+#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
+
+#include <linux/kvm_host.h>
+
+#include "commpage.h"
+
+void kvm_mips_commpage_init(struct kvm_vcpu *vcpu)
+{
+	struct kvm_mips_commpage *page = vcpu->arch.kseg0_commpage;
+
+	/* Specific init values for fields */
+	vcpu->arch.cop0 = &page->cop0;
+}
diff --git a/arch/mips/kvm/commpage.h b/arch/mips/kvm/commpage.h
new file mode 100644
index 00000000000..08c5fa2bbc0
--- /dev/null
+++ b/arch/mips/kvm/commpage.h
@@ -0,0 +1,24 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS: commpage: mapped into get kernel space
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
+
+#ifndef __KVM_MIPS_COMMPAGE_H__
+#define __KVM_MIPS_COMMPAGE_H__
+
+struct kvm_mips_commpage {
+	/* COP0 state is mapped into Guest kernel via commpage */
+	struct mips_coproc cop0;
+};
+
+#define KVM_MIPS_COMM_EIDI_OFFSET       0x0
+
+extern void kvm_mips_commpage_init(struct kvm_vcpu *vcpu);
+
+#endif /* __KVM_MIPS_COMMPAGE_H__ */
diff --git a/arch/mips/kvm/kvm_mips_dyntrans.c b/arch/mips/kvm/dyntrans.c
index b80e41d858f..521121bdebf 100644
--- a/arch/mips/kvm/kvm_mips_dyntrans.c
+++ b/arch/mips/kvm/dyntrans.c
@@ -1,13 +1,13 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* KVM/MIPS: Binary Patching for privileged instructions, reduces traps.
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS: Binary Patching for privileged instructions, reduces traps.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -18,7 +18,7 @@
 #include <linux/bootmem.h>
 #include <asm/cacheflush.h>
 
-#include "kvm_mips_comm.h"
+#include "commpage.h"
 
 #define SYNCI_TEMPLATE  0x041f0000
 #define SYNCI_BASE(x)   (((x) >> 21) & 0x1f)
@@ -28,9 +28,8 @@
 #define CLEAR_TEMPLATE  0x00000020
 #define SW_TEMPLATE     0xac000000
 
-int
-kvm_mips_trans_cache_index(uint32_t inst, uint32_t *opc,
-			   struct kvm_vcpu *vcpu)
+int kvm_mips_trans_cache_index(uint32_t inst, uint32_t *opc,
+			       struct kvm_vcpu *vcpu)
 {
 	int result = 0;
 	unsigned long kseg0_opc;
@@ -47,12 +46,11 @@ kvm_mips_trans_cache_index(uint32_t inst, uint32_t *opc,
 }
 
 /*
- *  Address based CACHE instructions are transformed into synci(s). A little heavy
- * for just D-cache invalidates, but avoids an expensive trap
+ * Address based CACHE instructions are transformed into synci(s). A little
+ * heavy for just D-cache invalidates, but avoids an expensive trap
  */
-int
-kvm_mips_trans_cache_va(uint32_t inst, uint32_t *opc,
-			struct kvm_vcpu *vcpu)
+int kvm_mips_trans_cache_va(uint32_t inst, uint32_t *opc,
+			    struct kvm_vcpu *vcpu)
 {
 	int result = 0;
 	unsigned long kseg0_opc;
@@ -72,8 +70,7 @@ kvm_mips_trans_cache_va(uint32_t inst, uint32_t *opc,
 	return result;
 }
 
-int
-kvm_mips_trans_mfc0(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu)
+int kvm_mips_trans_mfc0(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu)
 {
 	int32_t rt, rd, sel;
 	uint32_t mfc0_inst;
@@ -115,8 +112,7 @@ kvm_mips_trans_mfc0(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-int
-kvm_mips_trans_mtc0(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu)
+int kvm_mips_trans_mtc0(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu)
 {
 	int32_t rt, rd, sel;
 	uint32_t mtc0_inst = SW_TEMPLATE;
diff --git a/arch/mips/kvm/kvm_mips_emul.c b/arch/mips/kvm/emulate.c
index 8d484009008..fb3e8dfd1ff 100644
--- a/arch/mips/kvm/kvm_mips_emul.c
+++ b/arch/mips/kvm/emulate.c
@@ -1,13 +1,13 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* KVM/MIPS: Instruction/Exception emulation
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS: Instruction/Exception emulation
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -29,9 +29,9 @@
 #include <asm/r4kcache.h>
 #define CONFIG_MIPS_MT
 
-#include "kvm_mips_opcode.h"
-#include "kvm_mips_int.h"
-#include "kvm_mips_comm.h"
+#include "opcode.h"
+#include "interrupt.h"
+#include "commpage.h"
 
 #include "trace.h"
 
@@ -51,18 +51,14 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu,
 	if (epc & 3)
 		goto unaligned;
 
-	/*
-	 * Read the instruction
-	 */
+	/* Read the instruction */
 	insn.word = kvm_get_inst((uint32_t *) epc, vcpu);
 
 	if (insn.word == KVM_INVALID_INST)
 		return KVM_INVALID_INST;
 
 	switch (insn.i_format.opcode) {
-		/*
-		 * jr and jalr are in r_format format.
-		 */
+		/* jr and jalr are in r_format format. */
 	case spec_op:
 		switch (insn.r_format.func) {
 		case jalr_op:
@@ -124,18 +120,16 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu,
 
 			dspcontrol = rddsp(0x01);
 
-			if (dspcontrol >= 32) {
+			if (dspcontrol >= 32)
 				epc = epc + 4 + (insn.i_format.simmediate << 2);
-			} else
+			else
 				epc += 8;
 			nextpc = epc;
 			break;
 		}
 		break;
 
-		/*
-		 * These are unconditional and in j_format.
-		 */
+		/* These are unconditional and in j_format. */
 	case jal_op:
 		arch->gprs[31] = instpc + 8;
 	case j_op:
@@ -146,9 +140,7 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu,
 		nextpc = epc;
 		break;
 
-		/*
-		 * These are conditional and in i_format.
-		 */
+		/* These are conditional and in i_format. */
 	case beq_op:
 	case beql_op:
 		if (arch->gprs[insn.i_format.rs] ==
@@ -189,22 +181,20 @@ unsigned long kvm_compute_return_epc(struct kvm_vcpu *vcpu,
 		nextpc = epc;
 		break;
 
-		/*
-		 * And now the FPA/cp1 branch instructions.
-		 */
+		/* And now the FPA/cp1 branch instructions. */
 	case cop1_op:
-		printk("%s: unsupported cop1_op\n", __func__);
+		kvm_err("%s: unsupported cop1_op\n", __func__);
 		break;
 	}
 
 	return nextpc;
 
 unaligned:
-	printk("%s: unaligned epc\n", __func__);
+	kvm_err("%s: unaligned epc\n", __func__);
 	return nextpc;
 
 sigill:
-	printk("%s: DSP branch but not DSP ASE\n", __func__);
+	kvm_err("%s: DSP branch but not DSP ASE\n", __func__);
 	return nextpc;
 }
 
@@ -219,7 +209,8 @@ enum emulation_result update_pc(struct kvm_vcpu *vcpu, uint32_t cause)
 			er = EMULATE_FAIL;
 		} else {
 			vcpu->arch.pc = branch_pc;
-			kvm_debug("BD update_pc(): New PC: %#lx\n", vcpu->arch.pc);
+			kvm_debug("BD update_pc(): New PC: %#lx\n",
+				  vcpu->arch.pc);
 		}
 	} else
 		vcpu->arch.pc += 4;
@@ -240,6 +231,7 @@ enum emulation_result update_pc(struct kvm_vcpu *vcpu, uint32_t cause)
 static inline int kvm_mips_count_disabled(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
+
 	return	(vcpu->arch.count_ctl & KVM_REG_MIPS_COUNT_CTL_DC) ||
 		(kvm_read_c0_guest_cause(cop0) & CAUSEF_DC);
 }
@@ -392,7 +384,6 @@ static ktime_t kvm_mips_freeze_hrtimer(struct kvm_vcpu *vcpu,
 	return now;
 }
 
-
 /**
  * kvm_mips_resume_hrtimer() - Resume hrtimer, updating expiry.
  * @vcpu:	Virtual CPU.
@@ -760,8 +751,8 @@ enum emulation_result kvm_mips_emul_eret(struct kvm_vcpu *vcpu)
 		kvm_clear_c0_guest_status(cop0, ST0_ERL);
 		vcpu->arch.pc = kvm_read_c0_guest_errorepc(cop0);
 	} else {
-		printk("[%#lx] ERET when MIPS_SR_EXL|MIPS_SR_ERL == 0\n",
-		       vcpu->arch.pc);
+		kvm_err("[%#lx] ERET when MIPS_SR_EXL|MIPS_SR_ERL == 0\n",
+			vcpu->arch.pc);
 		er = EMULATE_FAIL;
 	}
 
@@ -770,8 +761,6 @@ enum emulation_result kvm_mips_emul_eret(struct kvm_vcpu *vcpu)
 
 enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu)
 {
-	enum emulation_result er = EMULATE_DONE;
-
 	kvm_debug("[%#lx] !!!WAIT!!! (%#lx)\n", vcpu->arch.pc,
 		  vcpu->arch.pending_exceptions);
 
@@ -781,8 +770,9 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu)
 		vcpu->arch.wait = 1;
 		kvm_vcpu_block(vcpu);
 
-		/* We we are runnable, then definitely go off to user space to check if any
-		 * I/O interrupts are pending.
+		/*
+		 * We we are runnable, then definitely go off to user space to
+		 * check if any I/O interrupts are pending.
 		 */
 		if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) {
 			clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
@@ -790,20 +780,20 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	return er;
+	return EMULATE_DONE;
 }
 
-/* XXXKYMA: Linux doesn't seem to use TLBR, return EMULATE_FAIL for now so that we can catch
- * this, if things ever change
+/*
+ * XXXKYMA: Linux doesn't seem to use TLBR, return EMULATE_FAIL for now so that
+ * we can catch this, if things ever change
  */
 enum emulation_result kvm_mips_emul_tlbr(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	enum emulation_result er = EMULATE_FAIL;
 	uint32_t pc = vcpu->arch.pc;
 
-	printk("[%#x] COP0_TLBR [%ld]\n", pc, kvm_read_c0_guest_index(cop0));
-	return er;
+	kvm_err("[%#x] COP0_TLBR [%ld]\n", pc, kvm_read_c0_guest_index(cop0));
+	return EMULATE_FAIL;
 }
 
 /* Write Guest TLB Entry @ Index */
@@ -811,88 +801,76 @@ enum emulation_result kvm_mips_emul_tlbwi(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	int index = kvm_read_c0_guest_index(cop0);
-	enum emulation_result er = EMULATE_DONE;
 	struct kvm_mips_tlb *tlb = NULL;
 	uint32_t pc = vcpu->arch.pc;
 
 	if (index < 0 || index >= KVM_MIPS_GUEST_TLB_SIZE) {
-		printk("%s: illegal index: %d\n", __func__, index);
-		printk
-		    ("[%#x] COP0_TLBWI [%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx, mask: %#lx)\n",
-		     pc, index, kvm_read_c0_guest_entryhi(cop0),
-		     kvm_read_c0_guest_entrylo0(cop0),
-		     kvm_read_c0_guest_entrylo1(cop0),
-		     kvm_read_c0_guest_pagemask(cop0));
+		kvm_debug("%s: illegal index: %d\n", __func__, index);
+		kvm_debug("[%#x] COP0_TLBWI [%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx, mask: %#lx)\n",
+			  pc, index, kvm_read_c0_guest_entryhi(cop0),
+			  kvm_read_c0_guest_entrylo0(cop0),
+			  kvm_read_c0_guest_entrylo1(cop0),
+			  kvm_read_c0_guest_pagemask(cop0));
 		index = (index & ~0x80000000) % KVM_MIPS_GUEST_TLB_SIZE;
 	}
 
 	tlb = &vcpu->arch.guest_tlb[index];
-#if 1
-	/* Probe the shadow host TLB for the entry being overwritten, if one matches, invalidate it */
+	/*
+	 * Probe the shadow host TLB for the entry being overwritten, if one
+	 * matches, invalidate it
+	 */
 	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
-#endif
 
 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
 	tlb->tlb_lo0 = kvm_read_c0_guest_entrylo0(cop0);
 	tlb->tlb_lo1 = kvm_read_c0_guest_entrylo1(cop0);
 
-	kvm_debug
-	    ("[%#x] COP0_TLBWI [%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx, mask: %#lx)\n",
-	     pc, index, kvm_read_c0_guest_entryhi(cop0),
-	     kvm_read_c0_guest_entrylo0(cop0), kvm_read_c0_guest_entrylo1(cop0),
-	     kvm_read_c0_guest_pagemask(cop0));
+	kvm_debug("[%#x] COP0_TLBWI [%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx, mask: %#lx)\n",
+		  pc, index, kvm_read_c0_guest_entryhi(cop0),
+		  kvm_read_c0_guest_entrylo0(cop0),
+		  kvm_read_c0_guest_entrylo1(cop0),
+		  kvm_read_c0_guest_pagemask(cop0));
 
-	return er;
+	return EMULATE_DONE;
 }
 
 /* Write Guest TLB Entry @ Random Index */
 enum emulation_result kvm_mips_emul_tlbwr(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	enum emulation_result er = EMULATE_DONE;
 	struct kvm_mips_tlb *tlb = NULL;
 	uint32_t pc = vcpu->arch.pc;
 	int index;
 
-#if 1
 	get_random_bytes(&index, sizeof(index));
 	index &= (KVM_MIPS_GUEST_TLB_SIZE - 1);
-#else
-	index = jiffies % KVM_MIPS_GUEST_TLB_SIZE;
-#endif
-
-	if (index < 0 || index >= KVM_MIPS_GUEST_TLB_SIZE) {
-		printk("%s: illegal index: %d\n", __func__, index);
-		return EMULATE_FAIL;
-	}
 
 	tlb = &vcpu->arch.guest_tlb[index];
 
-#if 1
-	/* Probe the shadow host TLB for the entry being overwritten, if one matches, invalidate it */
+	/*
+	 * Probe the shadow host TLB for the entry being overwritten, if one
+	 * matches, invalidate it
+	 */
 	kvm_mips_host_tlb_inv(vcpu, tlb->tlb_hi);
-#endif
 
 	tlb->tlb_mask = kvm_read_c0_guest_pagemask(cop0);
 	tlb->tlb_hi = kvm_read_c0_guest_entryhi(cop0);
 	tlb->tlb_lo0 = kvm_read_c0_guest_entrylo0(cop0);
 	tlb->tlb_lo1 = kvm_read_c0_guest_entrylo1(cop0);
 
-	kvm_debug
-	    ("[%#x] COP0_TLBWR[%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx)\n",
-	     pc, index, kvm_read_c0_guest_entryhi(cop0),
-	     kvm_read_c0_guest_entrylo0(cop0),
-	     kvm_read_c0_guest_entrylo1(cop0));
+	kvm_debug("[%#x] COP0_TLBWR[%d] (entryhi: %#lx, entrylo0: %#lx entrylo1: %#lx)\n",
+		  pc, index, kvm_read_c0_guest_entryhi(cop0),
+		  kvm_read_c0_guest_entrylo0(cop0),
+		  kvm_read_c0_guest_entrylo1(cop0));
 
-	return er;
+	return EMULATE_DONE;
 }
 
 enum emulation_result kvm_mips_emul_tlbp(struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	long entryhi = kvm_read_c0_guest_entryhi(cop0);
-	enum emulation_result er = EMULATE_DONE;
 	uint32_t pc = vcpu->arch.pc;
 	int index = -1;
 
@@ -903,12 +881,12 @@ enum emulation_result kvm_mips_emul_tlbp(struct kvm_vcpu *vcpu)
 	kvm_debug("[%#x] COP0_TLBP (entryhi: %#lx), index: %d\n", pc, entryhi,
 		  index);
 
-	return er;
+	return EMULATE_DONE;
 }
 
-enum emulation_result
-kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
-		     struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc,
+					   uint32_t cause, struct kvm_run *run,
+					   struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	enum emulation_result er = EMULATE_DONE;
@@ -922,9 +900,8 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 	 */
 	curr_pc = vcpu->arch.pc;
 	er = update_pc(vcpu, cause);
-	if (er == EMULATE_FAIL) {
+	if (er == EMULATE_FAIL)
 		return er;
-	}
 
 	copz = (inst >> 21) & 0x1f;
 	rt = (inst >> 16) & 0x1f;
@@ -949,7 +926,7 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 			er = kvm_mips_emul_tlbp(vcpu);
 			break;
 		case rfe_op:
-			printk("!!!COP0_RFE!!!\n");
+			kvm_err("!!!COP0_RFE!!!\n");
 			break;
 		case eret_op:
 			er = kvm_mips_emul_eret(vcpu);
@@ -973,8 +950,7 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 #ifdef CONFIG_KVM_MIPS_DYN_TRANS
 				kvm_mips_trans_mfc0(inst, opc, vcpu);
 #endif
-			}
-			else {
+			} else {
 				vcpu->arch.gprs[rt] = cop0->reg[rd][sel];
 
 #ifdef CONFIG_KVM_MIPS_DYN_TRANS
@@ -999,8 +975,8 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 			if ((rd == MIPS_CP0_TLB_INDEX)
 			    && (vcpu->arch.gprs[rt] >=
 				KVM_MIPS_GUEST_TLB_SIZE)) {
-				printk("Invalid TLB Index: %ld",
-				       vcpu->arch.gprs[rt]);
+				kvm_err("Invalid TLB Index: %ld",
+					vcpu->arch.gprs[rt]);
 				er = EMULATE_FAIL;
 				break;
 			}
@@ -1010,21 +986,19 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 				kvm_change_c0_guest_ebase(cop0,
 							  ~(C0_EBASE_CORE_MASK),
 							  vcpu->arch.gprs[rt]);
-				printk("MTCz, cop0->reg[EBASE]: %#lx\n",
-				       kvm_read_c0_guest_ebase(cop0));
+				kvm_err("MTCz, cop0->reg[EBASE]: %#lx\n",
+					kvm_read_c0_guest_ebase(cop0));
 			} else if (rd == MIPS_CP0_TLB_HI && sel == 0) {
 				uint32_t nasid =
-				    vcpu->arch.gprs[rt] & ASID_MASK;
-				if ((KSEGX(vcpu->arch.gprs[rt]) != CKSEG0)
-				    &&
+					vcpu->arch.gprs[rt] & ASID_MASK;
+				if ((KSEGX(vcpu->arch.gprs[rt]) != CKSEG0) &&
 				    ((kvm_read_c0_guest_entryhi(cop0) &
 				      ASID_MASK) != nasid)) {
-
-					kvm_debug
-					    ("MTCz, change ASID from %#lx to %#lx\n",
-					     kvm_read_c0_guest_entryhi(cop0) &
-					     ASID_MASK,
-					     vcpu->arch.gprs[rt] & ASID_MASK);
+					kvm_debug("MTCz, change ASID from %#lx to %#lx\n",
+						kvm_read_c0_guest_entryhi(cop0)
+						& ASID_MASK,
+						vcpu->arch.gprs[rt]
+						& ASID_MASK);
 
 					/* Blow away the shadow host TLBs */
 					kvm_mips_flush_host_tlb(1);
@@ -1049,7 +1023,10 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 			} else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) {
 				kvm_write_c0_guest_status(cop0,
 							  vcpu->arch.gprs[rt]);
-				/* Make sure that CU1 and NMI bits are never set */
+				/*
+				 * Make sure that CU1 and NMI bits are
+				 * never set
+				 */
 				kvm_clear_c0_guest_status(cop0,
 							  (ST0_CU1 | ST0_NMI));
 
@@ -1058,6 +1035,7 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 #endif
 			} else if ((rd == MIPS_CP0_CAUSE) && (sel == 0)) {
 				uint32_t old_cause, new_cause;
+
 				old_cause = kvm_read_c0_guest_cause(cop0);
 				new_cause = vcpu->arch.gprs[rt];
 				/* Update R/W bits */
@@ -1082,9 +1060,8 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 			break;
 
 		case dmtc_op:
-			printk
-			    ("!!!!!!![%#lx]dmtc_op: rt: %d, rd: %d, sel: %d!!!!!!\n",
-			     vcpu->arch.pc, rt, rd, sel);
+			kvm_err("!!!!!!![%#lx]dmtc_op: rt: %d, rd: %d, sel: %d!!!!!!\n",
+				vcpu->arch.pc, rt, rd, sel);
 			er = EMULATE_FAIL;
 			break;
 
@@ -1115,7 +1092,10 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 				    cop0->reg[MIPS_CP0_STATUS][2] & 0xf;
 				uint32_t pss =
 				    (cop0->reg[MIPS_CP0_STATUS][2] >> 6) & 0xf;
-				/* We don't support any shadow register sets, so SRSCtl[PSS] == SRSCtl[CSS] = 0 */
+				/*
+				 * We don't support any shadow register sets, so
+				 * SRSCtl[PSS] == SRSCtl[CSS] = 0
+				 */
 				if (css || pss) {
 					er = EMULATE_FAIL;
 					break;
@@ -1126,21 +1106,17 @@ kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause,
 			}
 			break;
 		default:
-			printk
-			    ("[%#lx]MachEmulateCP0: unsupported COP0, copz: 0x%x\n",
-			     vcpu->arch.pc, copz);
+			kvm_err("[%#lx]MachEmulateCP0: unsupported COP0, copz: 0x%x\n",
+				vcpu->arch.pc, copz);
 			er = EMULATE_FAIL;
 			break;
 		}
 	}
 
 done:
-	/*
-	 * Rollback PC only if emulation was unsuccessful
-	 */
-	if (er == EMULATE_FAIL) {
+	/* Rollback PC only if emulation was unsuccessful */
+	if (er == EMULATE_FAIL)
 		vcpu->arch.pc = curr_pc;
-	}
 
 dont_update_pc:
 	/*
@@ -1152,9 +1128,9 @@ dont_update_pc:
 	return er;
 }
 
-enum emulation_result
-kvm_mips_emulate_store(uint32_t inst, uint32_t cause,
-		       struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_store(uint32_t inst, uint32_t cause,
+					     struct kvm_run *run,
+					     struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DO_MMIO;
 	int32_t op, base, rt, offset;
@@ -1252,24 +1228,21 @@ kvm_mips_emulate_store(uint32_t inst, uint32_t cause,
 		break;
 
 	default:
-		printk("Store not yet supported");
+		kvm_err("Store not yet supported");
 		er = EMULATE_FAIL;
 		break;
 	}
 
-	/*
-	 * Rollback PC if emulation was unsuccessful
-	 */
-	if (er == EMULATE_FAIL) {
+	/* Rollback PC if emulation was unsuccessful */
+	if (er == EMULATE_FAIL)
 		vcpu->arch.pc = curr_pc;
-	}
 
 	return er;
 }
 
-enum emulation_result
-kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
-		      struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
+					    struct kvm_run *run,
+					    struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DO_MMIO;
 	int32_t op, base, rt, offset;
@@ -1364,7 +1337,7 @@ kvm_mips_emulate_load(uint32_t inst, uint32_t cause,
 		break;
 
 	default:
-		printk("Load not yet supported");
+		kvm_err("Load not yet supported");
 		er = EMULATE_FAIL;
 		break;
 	}
@@ -1383,7 +1356,7 @@ int kvm_mips_sync_icache(unsigned long va, struct kvm_vcpu *vcpu)
 	gfn = va >> PAGE_SHIFT;
 
 	if (gfn >= kvm->arch.guest_pmap_npages) {
-		printk("%s: Invalid gfn: %#llx\n", __func__, gfn);
+		kvm_err("%s: Invalid gfn: %#llx\n", __func__, gfn);
 		kvm_mips_dump_host_tlbs();
 		kvm_arch_vcpu_dump_regs(vcpu);
 		return -1;
@@ -1391,7 +1364,8 @@ int kvm_mips_sync_icache(unsigned long va, struct kvm_vcpu *vcpu)
 	pfn = kvm->arch.guest_pmap[gfn];
 	pa = (pfn << PAGE_SHIFT) | offset;
 
-	printk("%s: va: %#lx, unmapped: %#x\n", __func__, va, CKSEG0ADDR(pa));
+	kvm_debug("%s: va: %#lx, unmapped: %#x\n", __func__, va,
+		  CKSEG0ADDR(pa));
 
 	local_flush_icache_range(CKSEG0ADDR(pa), 32);
 	return 0;
@@ -1410,13 +1384,12 @@ int kvm_mips_sync_icache(unsigned long va, struct kvm_vcpu *vcpu)
 #define MIPS_CACHE_DCACHE               0x1
 #define MIPS_CACHE_SEC                  0x3
 
-enum emulation_result
-kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, uint32_t cause,
-		       struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc,
+					     uint32_t cause,
+					     struct kvm_run *run,
+					     struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	extern void (*r4k_blast_dcache) (void);
-	extern void (*r4k_blast_icache) (void);
 	enum emulation_result er = EMULATE_DONE;
 	int32_t offset, cache, op_inst, op, base;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
@@ -1443,22 +1416,23 @@ kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, uint32_t cause,
 	kvm_debug("CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
 		  cache, op, base, arch->gprs[base], offset);
 
-	/* Treat INDEX_INV as a nop, basically issued by Linux on startup to invalidate
-	 * the caches entirely by stepping through all the ways/indexes
+	/*
+	 * Treat INDEX_INV as a nop, basically issued by Linux on startup to
+	 * invalidate the caches entirely by stepping through all the
+	 * ways/indexes
 	 */
 	if (op == MIPS_CACHE_OP_INDEX_INV) {
-		kvm_debug
-		    ("@ %#lx/%#lx CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
-		     vcpu->arch.pc, vcpu->arch.gprs[31], cache, op, base,
-		     arch->gprs[base], offset);
+		kvm_debug("@ %#lx/%#lx CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
+			  vcpu->arch.pc, vcpu->arch.gprs[31], cache, op, base,
+			  arch->gprs[base], offset);
 
 		if (cache == MIPS_CACHE_DCACHE)
 			r4k_blast_dcache();
 		else if (cache == MIPS_CACHE_ICACHE)
 			r4k_blast_icache();
 		else {
-			printk("%s: unsupported CACHE INDEX operation\n",
-			       __func__);
+			kvm_err("%s: unsupported CACHE INDEX operation\n",
+				__func__);
 			return EMULATE_FAIL;
 		}
 
@@ -1470,21 +1444,19 @@ kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, uint32_t cause,
 
 	preempt_disable();
 	if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) {
-
-		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0) {
+		if (kvm_mips_host_tlb_lookup(vcpu, va) < 0)
 			kvm_mips_handle_kseg0_tlb_fault(va, vcpu);
-		}
 	} else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) ||
 		   KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) {
 		int index;
 
 		/* If an entry already exists then skip */
-		if (kvm_mips_host_tlb_lookup(vcpu, va) >= 0) {
+		if (kvm_mips_host_tlb_lookup(vcpu, va) >= 0)
 			goto skip_fault;
-		}
 
-		/* If address not in the guest TLB, then give the guest a fault, the
-		 * resulting handler will do the right thing
+		/*
+		 * If address not in the guest TLB, then give the guest a fault,
+		 * the resulting handler will do the right thing
 		 */
 		index = kvm_mips_guest_tlb_lookup(vcpu, (va & VPN2_MASK) |
 						  (kvm_read_c0_guest_entryhi
@@ -1499,23 +1471,28 @@ kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, uint32_t cause,
 			goto dont_update_pc;
 		} else {
 			struct kvm_mips_tlb *tlb = &vcpu->arch.guest_tlb[index];
-			/* Check if the entry is valid, if not then setup a TLB invalid exception to the guest */
+			/*
+			 * Check if the entry is valid, if not then setup a TLB
+			 * invalid exception to the guest
+			 */
 			if (!TLB_IS_VALID(*tlb, va)) {
 				er = kvm_mips_emulate_tlbinv_ld(cause, NULL,
 								run, vcpu);
 				preempt_enable();
 				goto dont_update_pc;
 			} else {
-				/* We fault an entry from the guest tlb to the shadow host TLB */
+				/*
+				 * We fault an entry from the guest tlb to the
+				 * shadow host TLB
+				 */
 				kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb,
 								     NULL,
 								     NULL);
 			}
 		}
 	} else {
-		printk
-		    ("INVALID CACHE INDEX/ADDRESS (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
-		     cache, op, base, arch->gprs[base], offset);
+		kvm_err("INVALID CACHE INDEX/ADDRESS (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
+			cache, op, base, arch->gprs[base], offset);
 		er = EMULATE_FAIL;
 		preempt_enable();
 		goto dont_update_pc;
@@ -1530,7 +1507,10 @@ skip_fault:
 		flush_dcache_line(va);
 
 #ifdef CONFIG_KVM_MIPS_DYN_TRANS
-		/* Replace the CACHE instruction, with a SYNCI, not the same, but avoids a trap */
+		/*
+		 * Replace the CACHE instruction, with a SYNCI, not the same,
+		 * but avoids a trap
+		 */
 		kvm_mips_trans_cache_va(inst, opc, vcpu);
 #endif
 	} else if (op == MIPS_CACHE_OP_HIT_INV && cache == MIPS_CACHE_ICACHE) {
@@ -1542,9 +1522,8 @@ skip_fault:
 		kvm_mips_trans_cache_va(inst, opc, vcpu);
 #endif
 	} else {
-		printk
-		    ("NO-OP CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
-		     cache, op, base, arch->gprs[base], offset);
+		kvm_err("NO-OP CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n",
+			cache, op, base, arch->gprs[base], offset);
 		er = EMULATE_FAIL;
 		preempt_enable();
 		goto dont_update_pc;
@@ -1552,28 +1531,23 @@ skip_fault:
 
 	preempt_enable();
 
-      dont_update_pc:
-	/*
-	 * Rollback PC
-	 */
+dont_update_pc:
+	/* Rollback PC */
 	vcpu->arch.pc = curr_pc;
-      done:
+done:
 	return er;
 }
 
-enum emulation_result
-kvm_mips_emulate_inst(unsigned long cause, uint32_t *opc,
-		      struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_inst(unsigned long cause, uint32_t *opc,
+					    struct kvm_run *run,
+					    struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DONE;
 	uint32_t inst;
 
-	/*
-	 *  Fetch the instruction.
-	 */
-	if (cause & CAUSEF_BD) {
+	/* Fetch the instruction. */
+	if (cause & CAUSEF_BD)
 		opc += 1;
-	}
 
 	inst = kvm_get_inst(opc, vcpu);
 
@@ -1601,8 +1575,8 @@ kvm_mips_emulate_inst(unsigned long cause, uint32_t *opc,
 		break;
 
 	default:
-		printk("Instruction emulation not supported (%p/%#x)\n", opc,
-		       inst);
+		kvm_err("Instruction emulation not supported (%p/%#x)\n", opc,
+			inst);
 		kvm_arch_vcpu_dump_regs(vcpu);
 		er = EMULATE_FAIL;
 		break;
@@ -1611,9 +1585,10 @@ kvm_mips_emulate_inst(unsigned long cause, uint32_t *opc,
 	return er;
 }
 
-enum emulation_result
-kvm_mips_emulate_syscall(unsigned long cause, uint32_t *opc,
-			 struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_syscall(unsigned long cause,
+					       uint32_t *opc,
+					       struct kvm_run *run,
+					       struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
@@ -1638,20 +1613,20 @@ kvm_mips_emulate_syscall(unsigned long cause, uint32_t *opc,
 		arch->pc = KVM_GUEST_KSEG0 + 0x180;
 
 	} else {
-		printk("Trying to deliver SYSCALL when EXL is already set\n");
+		kvm_err("Trying to deliver SYSCALL when EXL is already set\n");
 		er = EMULATE_FAIL;
 	}
 
 	return er;
 }
 
-enum emulation_result
-kvm_mips_emulate_tlbmiss_ld(unsigned long cause, uint32_t *opc,
-			    struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_tlbmiss_ld(unsigned long cause,
+						  uint32_t *opc,
+						  struct kvm_run *run,
+						  struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
-	enum emulation_result er = EMULATE_DONE;
 	unsigned long entryhi = (vcpu->arch.  host_cp0_badvaddr & VPN2_MASK) |
 				(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 
@@ -1688,16 +1663,16 @@ kvm_mips_emulate_tlbmiss_ld(unsigned long cause, uint32_t *opc,
 	/* Blow away the shadow host TLBs */
 	kvm_mips_flush_host_tlb(1);
 
-	return er;
+	return EMULATE_DONE;
 }
 
-enum emulation_result
-kvm_mips_emulate_tlbinv_ld(unsigned long cause, uint32_t *opc,
-			   struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_tlbinv_ld(unsigned long cause,
+						 uint32_t *opc,
+						 struct kvm_run *run,
+						 struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
-	enum emulation_result er = EMULATE_DONE;
 	unsigned long entryhi =
 		(vcpu->arch.host_cp0_badvaddr & VPN2_MASK) |
 		(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
@@ -1734,16 +1709,16 @@ kvm_mips_emulate_tlbinv_ld(unsigned long cause, uint32_t *opc,
 	/* Blow away the shadow host TLBs */
 	kvm_mips_flush_host_tlb(1);
 
-	return er;
+	return EMULATE_DONE;
 }
 
-enum emulation_result
-kvm_mips_emulate_tlbmiss_st(unsigned long cause, uint32_t *opc,
-			    struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_tlbmiss_st(unsigned long cause,
+						  uint32_t *opc,
+						  struct kvm_run *run,
+						  struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
-	enum emulation_result er = EMULATE_DONE;
 	unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) |
 				(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 
@@ -1778,16 +1753,16 @@ kvm_mips_emulate_tlbmiss_st(unsigned long cause, uint32_t *opc,
 	/* Blow away the shadow host TLBs */
 	kvm_mips_flush_host_tlb(1);
 
-	return er;
+	return EMULATE_DONE;
 }
 
-enum emulation_result
-kvm_mips_emulate_tlbinv_st(unsigned long cause, uint32_t *opc,
-			   struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_tlbinv_st(unsigned long cause,
+						 uint32_t *opc,
+						 struct kvm_run *run,
+						 struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
-	enum emulation_result er = EMULATE_DONE;
 	unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) |
 		(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 
@@ -1822,13 +1797,13 @@ kvm_mips_emulate_tlbinv_st(unsigned long cause, uint32_t *opc,
 	/* Blow away the shadow host TLBs */
 	kvm_mips_flush_host_tlb(1);
 
-	return er;
+	return EMULATE_DONE;
 }
 
 /* TLBMOD: store into address matching TLB with Dirty bit off */
-enum emulation_result
-kvm_mips_handle_tlbmod(unsigned long cause, uint32_t *opc,
-		       struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_handle_tlbmod(unsigned long cause, uint32_t *opc,
+					     struct kvm_run *run,
+					     struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DONE;
 #ifdef DEBUG
@@ -1837,9 +1812,7 @@ kvm_mips_handle_tlbmod(unsigned long cause, uint32_t *opc,
 				(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 	int index;
 
-	/*
-	 * If address not in the guest TLB, then we are in trouble
-	 */
+	/* If address not in the guest TLB, then we are in trouble */
 	index = kvm_mips_guest_tlb_lookup(vcpu, entryhi);
 	if (index < 0) {
 		/* XXXKYMA Invalidate and retry */
@@ -1856,15 +1829,15 @@ kvm_mips_handle_tlbmod(unsigned long cause, uint32_t *opc,
 	return er;
 }
 
-enum emulation_result
-kvm_mips_emulate_tlbmod(unsigned long cause, uint32_t *opc,
-			struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_tlbmod(unsigned long cause,
+					      uint32_t *opc,
+					      struct kvm_run *run,
+					      struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	unsigned long entryhi = (vcpu->arch.host_cp0_badvaddr & VPN2_MASK) |
 				(kvm_read_c0_guest_entryhi(cop0) & ASID_MASK);
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
-	enum emulation_result er = EMULATE_DONE;
 
 	if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) {
 		/* save old pc */
@@ -1895,16 +1868,16 @@ kvm_mips_emulate_tlbmod(unsigned long cause, uint32_t *opc,
 	/* Blow away the shadow host TLBs */
 	kvm_mips_flush_host_tlb(1);
 
-	return er;
+	return EMULATE_DONE;
 }
 
-enum emulation_result
-kvm_mips_emulate_fpu_exc(unsigned long cause, uint32_t *opc,
-			 struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_fpu_exc(unsigned long cause,
+					       uint32_t *opc,
+					       struct kvm_run *run,
+					       struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
-	enum emulation_result er = EMULATE_DONE;
 
 	if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) {
 		/* save old pc */
@@ -1924,12 +1897,13 @@ kvm_mips_emulate_fpu_exc(unsigned long cause, uint32_t *opc,
 				  (T_COP_UNUSABLE << CAUSEB_EXCCODE));
 	kvm_change_c0_guest_cause(cop0, (CAUSEF_CE), (0x1 << CAUSEB_CE));
 
-	return er;
+	return EMULATE_DONE;
 }
 
-enum emulation_result
-kvm_mips_emulate_ri_exc(unsigned long cause, uint32_t *opc,
-			struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_ri_exc(unsigned long cause,
+					      uint32_t *opc,
+					      struct kvm_run *run,
+					      struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
@@ -1961,9 +1935,10 @@ kvm_mips_emulate_ri_exc(unsigned long cause, uint32_t *opc,
 	return er;
 }
 
-enum emulation_result
-kvm_mips_emulate_bp_exc(unsigned long cause, uint32_t *opc,
-			struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause,
+					      uint32_t *opc,
+					      struct kvm_run *run,
+					      struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
@@ -1988,16 +1963,14 @@ kvm_mips_emulate_bp_exc(unsigned long cause, uint32_t *opc,
 		arch->pc = KVM_GUEST_KSEG0 + 0x180;
 
 	} else {
-		printk("Trying to deliver BP when EXL is already set\n");
+		kvm_err("Trying to deliver BP when EXL is already set\n");
 		er = EMULATE_FAIL;
 	}
 
 	return er;
 }
 
-/*
- * ll/sc, rdhwr, sync emulation
- */
+/* ll/sc, rdhwr, sync emulation */
 
 #define OPCODE 0xfc000000
 #define BASE   0x03e00000
@@ -2012,9 +1985,9 @@ kvm_mips_emulate_bp_exc(unsigned long cause, uint32_t *opc,
 #define SYNC   0x0000000f
 #define RDHWR  0x0000003b
 
-enum emulation_result
-kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
-		   struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
+					 struct kvm_run *run,
+					 struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
 	struct kvm_vcpu_arch *arch = &vcpu->arch;
@@ -2031,16 +2004,14 @@ kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 	if (er == EMULATE_FAIL)
 		return er;
 
-	/*
-	 *  Fetch the instruction.
-	 */
+	/* Fetch the instruction. */
 	if (cause & CAUSEF_BD)
 		opc += 1;
 
 	inst = kvm_get_inst(opc, vcpu);
 
 	if (inst == KVM_INVALID_INST) {
-		printk("%s: Cannot get inst @ %p\n", __func__, opc);
+		kvm_err("%s: Cannot get inst @ %p\n", __func__, opc);
 		return EMULATE_FAIL;
 	}
 
@@ -2099,15 +2070,15 @@ emulate_ri:
 	return kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
 }
 
-enum emulation_result
-kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run)
+enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu,
+						  struct kvm_run *run)
 {
 	unsigned long *gpr = &vcpu->arch.gprs[vcpu->arch.io_gpr];
 	enum emulation_result er = EMULATE_DONE;
 	unsigned long curr_pc;
 
 	if (run->mmio.len > sizeof(*gpr)) {
-		printk("Bad MMIO length: %d", run->mmio.len);
+		kvm_err("Bad MMIO length: %d", run->mmio.len);
 		er = EMULATE_FAIL;
 		goto done;
 	}
@@ -2142,18 +2113,18 @@ kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	}
 
 	if (vcpu->arch.pending_load_cause & CAUSEF_BD)
-		kvm_debug
-		    ("[%#lx] Completing %d byte BD Load to gpr %d (0x%08lx) type %d\n",
-		     vcpu->arch.pc, run->mmio.len, vcpu->arch.io_gpr, *gpr,
-		     vcpu->mmio_needed);
+		kvm_debug("[%#lx] Completing %d byte BD Load to gpr %d (0x%08lx) type %d\n",
+			  vcpu->arch.pc, run->mmio.len, vcpu->arch.io_gpr, *gpr,
+			  vcpu->mmio_needed);
 
 done:
 	return er;
 }
 
-static enum emulation_result
-kvm_mips_emulate_exc(unsigned long cause, uint32_t *opc,
-		     struct kvm_run *run, struct kvm_vcpu *vcpu)
+static enum emulation_result kvm_mips_emulate_exc(unsigned long cause,
+						  uint32_t *opc,
+						  struct kvm_run *run,
+						  struct kvm_vcpu *vcpu)
 {
 	uint32_t exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
@@ -2181,16 +2152,17 @@ kvm_mips_emulate_exc(unsigned long cause, uint32_t *opc,
 			  exccode, kvm_read_c0_guest_epc(cop0),
 			  kvm_read_c0_guest_badvaddr(cop0));
 	} else {
-		printk("Trying to deliver EXC when EXL is already set\n");
+		kvm_err("Trying to deliver EXC when EXL is already set\n");
 		er = EMULATE_FAIL;
 	}
 
 	return er;
 }
 
-enum emulation_result
-kvm_mips_check_privilege(unsigned long cause, uint32_t *opc,
-			 struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_check_privilege(unsigned long cause,
+					       uint32_t *opc,
+					       struct kvm_run *run,
+					       struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DONE;
 	uint32_t exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
@@ -2215,10 +2187,13 @@ kvm_mips_check_privilege(unsigned long cause, uint32_t *opc,
 			break;
 
 		case T_TLB_LD_MISS:
-			/* We we are accessing Guest kernel space, then send an address error exception to the guest */
+			/*
+			 * We we are accessing Guest kernel space, then send an
+			 * address error exception to the guest
+			 */
 			if (badvaddr >= (unsigned long) KVM_GUEST_KSEG0) {
-				printk("%s: LD MISS @ %#lx\n", __func__,
-				       badvaddr);
+				kvm_debug("%s: LD MISS @ %#lx\n", __func__,
+					  badvaddr);
 				cause &= ~0xff;
 				cause |= (T_ADDR_ERR_LD << CAUSEB_EXCCODE);
 				er = EMULATE_PRIV_FAIL;
@@ -2226,10 +2201,13 @@ kvm_mips_check_privilege(unsigned long cause, uint32_t *opc,
 			break;
 
 		case T_TLB_ST_MISS:
-			/* We we are accessing Guest kernel space, then send an address error exception to the guest */
+			/*
+			 * We we are accessing Guest kernel space, then send an
+			 * address error exception to the guest
+			 */
 			if (badvaddr >= (unsigned long) KVM_GUEST_KSEG0) {
-				printk("%s: ST MISS @ %#lx\n", __func__,
-				       badvaddr);
+				kvm_debug("%s: ST MISS @ %#lx\n", __func__,
+					  badvaddr);
 				cause &= ~0xff;
 				cause |= (T_ADDR_ERR_ST << CAUSEB_EXCCODE);
 				er = EMULATE_PRIV_FAIL;
@@ -2237,8 +2215,8 @@ kvm_mips_check_privilege(unsigned long cause, uint32_t *opc,
 			break;
 
 		case T_ADDR_ERR_ST:
-			printk("%s: address error ST @ %#lx\n", __func__,
-			       badvaddr);
+			kvm_debug("%s: address error ST @ %#lx\n", __func__,
+				  badvaddr);
 			if ((badvaddr & PAGE_MASK) == KVM_GUEST_COMMPAGE_ADDR) {
 				cause &= ~0xff;
 				cause |= (T_TLB_ST_MISS << CAUSEB_EXCCODE);
@@ -2246,8 +2224,8 @@ kvm_mips_check_privilege(unsigned long cause, uint32_t *opc,
 			er = EMULATE_PRIV_FAIL;
 			break;
 		case T_ADDR_ERR_LD:
-			printk("%s: address error LD @ %#lx\n", __func__,
-			       badvaddr);
+			kvm_debug("%s: address error LD @ %#lx\n", __func__,
+				  badvaddr);
 			if ((badvaddr & PAGE_MASK) == KVM_GUEST_COMMPAGE_ADDR) {
 				cause &= ~0xff;
 				cause |= (T_TLB_LD_MISS << CAUSEB_EXCCODE);
@@ -2260,21 +2238,23 @@ kvm_mips_check_privilege(unsigned long cause, uint32_t *opc,
 		}
 	}
 
-	if (er == EMULATE_PRIV_FAIL) {
+	if (er == EMULATE_PRIV_FAIL)
 		kvm_mips_emulate_exc(cause, opc, run, vcpu);
-	}
+
 	return er;
 }
 
-/* User Address (UA) fault, this could happen if
+/*
+ * User Address (UA) fault, this could happen if
  * (1) TLB entry not present/valid in both Guest and shadow host TLBs, in this
  *     case we pass on the fault to the guest kernel and let it handle it.
  * (2) TLB entry is present in the Guest TLB but not in the shadow, in this
  *     case we inject the TLB from the Guest TLB into the shadow host TLB
  */
-enum emulation_result
-kvm_mips_handle_tlbmiss(unsigned long cause, uint32_t *opc,
-			struct kvm_run *run, struct kvm_vcpu *vcpu)
+enum emulation_result kvm_mips_handle_tlbmiss(unsigned long cause,
+					      uint32_t *opc,
+					      struct kvm_run *run,
+					      struct kvm_vcpu *vcpu)
 {
 	enum emulation_result er = EMULATE_DONE;
 	uint32_t exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
@@ -2284,10 +2264,11 @@ kvm_mips_handle_tlbmiss(unsigned long cause, uint32_t *opc,
 	kvm_debug("kvm_mips_handle_tlbmiss: badvaddr: %#lx, entryhi: %#lx\n",
 		  vcpu->arch.host_cp0_badvaddr, vcpu->arch.host_cp0_entryhi);
 
-	/* KVM would not have got the exception if this entry was valid in the shadow host TLB
-	 * Check the Guest TLB, if the entry is not there then send the guest an
-	 * exception. The guest exc handler should then inject an entry into the
-	 * guest TLB
+	/*
+	 * KVM would not have got the exception if this entry was valid in the
+	 * shadow host TLB. Check the Guest TLB, if the entry is not there then
+	 * send the guest an exception. The guest exc handler should then inject
+	 * an entry into the guest TLB.
 	 */
 	index = kvm_mips_guest_tlb_lookup(vcpu,
 					  (va & VPN2_MASK) |
@@ -2299,13 +2280,17 @@ kvm_mips_handle_tlbmiss(unsigned long cause, uint32_t *opc,
 		} else if (exccode == T_TLB_ST_MISS) {
 			er = kvm_mips_emulate_tlbmiss_st(cause, opc, run, vcpu);
 		} else {
-			printk("%s: invalid exc code: %d\n", __func__, exccode);
+			kvm_err("%s: invalid exc code: %d\n", __func__,
+				exccode);
 			er = EMULATE_FAIL;
 		}
 	} else {
 		struct kvm_mips_tlb *tlb = &vcpu->arch.guest_tlb[index];
 
-		/* Check if the entry is valid, if not then setup a TLB invalid exception to the guest */
+		/*
+		 * Check if the entry is valid, if not then setup a TLB invalid
+		 * exception to the guest
+		 */
 		if (!TLB_IS_VALID(*tlb, va)) {
 			if (exccode == T_TLB_LD_MISS) {
 				er = kvm_mips_emulate_tlbinv_ld(cause, opc, run,
@@ -2314,15 +2299,17 @@ kvm_mips_handle_tlbmiss(unsigned long cause, uint32_t *opc,
 				er = kvm_mips_emulate_tlbinv_st(cause, opc, run,
 								vcpu);
 			} else {
-				printk("%s: invalid exc code: %d\n", __func__,
-				       exccode);
+				kvm_err("%s: invalid exc code: %d\n", __func__,
+					exccode);
 				er = EMULATE_FAIL;
 			}
 		} else {
-			kvm_debug
-			    ("Injecting hi: %#lx, lo0: %#lx, lo1: %#lx into shadow host TLB\n",
-			     tlb->tlb_hi, tlb->tlb_lo0, tlb->tlb_lo1);
-			/* OK we have a Guest TLB entry, now inject it into the shadow host TLB */
+			kvm_debug("Injecting hi: %#lx, lo0: %#lx, lo1: %#lx into shadow host TLB\n",
+				  tlb->tlb_hi, tlb->tlb_lo0, tlb->tlb_lo1);
+			/*
+			 * OK we have a Guest TLB entry, now inject it into the
+			 * shadow host TLB
+			 */
 			kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb, NULL,
 							     NULL);
 		}
diff --git a/arch/mips/kvm/kvm_mips_int.c b/arch/mips/kvm/interrupt.c
index 1e5de16afe2..9b4445940c2 100644
--- a/arch/mips/kvm/kvm_mips_int.c
+++ b/arch/mips/kvm/interrupt.c
@@ -1,13 +1,13 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* KVM/MIPS: Interrupt delivery
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS: Interrupt delivery
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -20,7 +20,7 @@
 
 #include <linux/kvm_host.h>
 
-#include "kvm_mips_int.h"
+#include "interrupt.h"
 
 void kvm_mips_queue_irq(struct kvm_vcpu *vcpu, uint32_t priority)
 {
@@ -34,7 +34,8 @@ void kvm_mips_dequeue_irq(struct kvm_vcpu *vcpu, uint32_t priority)
 
 void kvm_mips_queue_timer_int_cb(struct kvm_vcpu *vcpu)
 {
-	/* Cause bits to reflect the pending timer interrupt,
+	/*
+	 * Cause bits to reflect the pending timer interrupt,
 	 * the EXC code will be set when we are actually
 	 * delivering the interrupt:
 	 */
@@ -51,12 +52,13 @@ void kvm_mips_dequeue_timer_int_cb(struct kvm_vcpu *vcpu)
 	kvm_mips_dequeue_irq(vcpu, MIPS_EXC_INT_TIMER);
 }
 
-void
-kvm_mips_queue_io_int_cb(struct kvm_vcpu *vcpu, struct kvm_mips_interrupt *irq)
+void kvm_mips_queue_io_int_cb(struct kvm_vcpu *vcpu,
+			      struct kvm_mips_interrupt *irq)
 {
 	int intr = (int)irq->irq;
 
-	/* Cause bits to reflect the pending IO interrupt,
+	/*
+	 * Cause bits to reflect the pending IO interrupt,
 	 * the EXC code will be set when we are actually
 	 * delivering the interrupt:
 	 */
@@ -83,11 +85,11 @@ kvm_mips_queue_io_int_cb(struct kvm_vcpu *vcpu, struct kvm_mips_interrupt *irq)
 
 }
 
-void
-kvm_mips_dequeue_io_int_cb(struct kvm_vcpu *vcpu,
-			   struct kvm_mips_interrupt *irq)
+void kvm_mips_dequeue_io_int_cb(struct kvm_vcpu *vcpu,
+				struct kvm_mips_interrupt *irq)
 {
 	int intr = (int)irq->irq;
+
 	switch (intr) {
 	case -2:
 		kvm_clear_c0_guest_cause(vcpu->arch.cop0, (C_IRQ0));
@@ -111,9 +113,8 @@ kvm_mips_dequeue_io_int_cb(struct kvm_vcpu *vcpu,
 }
 
 /* Deliver the interrupt of the corresponding priority, if possible. */
-int
-kvm_mips_irq_deliver_cb(struct kvm_vcpu *vcpu, unsigned int priority,
-			uint32_t cause)
+int kvm_mips_irq_deliver_cb(struct kvm_vcpu *vcpu, unsigned int priority,
+			    uint32_t cause)
 {
 	int allowed = 0;
 	uint32_t exccode;
@@ -164,7 +165,6 @@ kvm_mips_irq_deliver_cb(struct kvm_vcpu *vcpu, unsigned int priority,
 
 	/* Are we allowed to deliver the interrupt ??? */
 	if (allowed) {
-
 		if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) {
 			/* save old pc */
 			kvm_write_c0_guest_epc(cop0, arch->pc);
@@ -195,9 +195,8 @@ kvm_mips_irq_deliver_cb(struct kvm_vcpu *vcpu, unsigned int priority,
 	return allowed;
 }
 
-int
-kvm_mips_irq_clear_cb(struct kvm_vcpu *vcpu, unsigned int priority,
-		      uint32_t cause)
+int kvm_mips_irq_clear_cb(struct kvm_vcpu *vcpu, unsigned int priority,
+			  uint32_t cause)
 {
 	return 1;
 }
diff --git a/arch/mips/kvm/kvm_mips_int.h b/arch/mips/kvm/interrupt.h
index 20da7d29eed..4ab4bdfad70 100644
--- a/arch/mips/kvm/kvm_mips_int.h
+++ b/arch/mips/kvm/interrupt.h
@@ -1,14 +1,15 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* KVM/MIPS: Interrupts
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS: Interrupts
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
-/* MIPS Exception Priorities, exceptions (including interrupts) are queued up
+/*
+ * MIPS Exception Priorities, exceptions (including interrupts) are queued up
  * for the guest in the order specified by their priorities
  */
 
@@ -27,6 +28,9 @@
 #define MIPS_EXC_MAX                12
 /* XXXSL More to follow */
 
+extern char mips32_exception[], mips32_exceptionEnd[];
+extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
+
 #define C_TI        (_ULCAST_(1) << 30)
 
 #define KVM_MIPS_IRQ_DELIVER_ALL_AT_ONCE (0)
diff --git a/arch/mips/kvm/kvm_mips_comm.h b/arch/mips/kvm/kvm_mips_comm.h
deleted file mode 100644
index a4a8c85cc8f..00000000000
--- a/arch/mips/kvm/kvm_mips_comm.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* KVM/MIPS: commpage: mapped into get kernel space
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
-
-#ifndef __KVM_MIPS_COMMPAGE_H__
-#define __KVM_MIPS_COMMPAGE_H__
-
-struct kvm_mips_commpage {
-	struct mips_coproc cop0;	/* COP0 state is mapped into Guest kernel via commpage */
-};
-
-#define KVM_MIPS_COMM_EIDI_OFFSET       0x0
-
-extern void kvm_mips_commpage_init(struct kvm_vcpu *vcpu);
-
-#endif /* __KVM_MIPS_COMMPAGE_H__ */
diff --git a/arch/mips/kvm/kvm_mips_commpage.c b/arch/mips/kvm/kvm_mips_commpage.c
deleted file mode 100644
index 3873b1ecc40..00000000000
--- a/arch/mips/kvm/kvm_mips_commpage.c
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* commpage, currently used for Virtual COP0 registers.
-* Mapped into the guest kernel @ 0x0.
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
-
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/vmalloc.h>
-#include <linux/fs.h>
-#include <linux/bootmem.h>
-#include <asm/page.h>
-#include <asm/cacheflush.h>
-#include <asm/mmu_context.h>
-
-#include <linux/kvm_host.h>
-
-#include "kvm_mips_comm.h"
-
-void kvm_mips_commpage_init(struct kvm_vcpu *vcpu)
-{
-	struct kvm_mips_commpage *page = vcpu->arch.kseg0_commpage;
-	memset(page, 0, sizeof(struct kvm_mips_commpage));
-
-	/* Specific init values for fields */
-	vcpu->arch.cop0 = &page->cop0;
-	memset(vcpu->arch.cop0, 0, sizeof(struct mips_coproc));
-
-	return;
-}
diff --git a/arch/mips/kvm/kvm_mips_opcode.h b/arch/mips/kvm/kvm_mips_opcode.h
deleted file mode 100644
index 86d3b4cc348..00000000000
--- a/arch/mips/kvm/kvm_mips_opcode.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
-
-/*
- * Define opcode values not defined in <asm/isnt.h>
- */
-
-#ifndef __KVM_MIPS_OPCODE_H__
-#define __KVM_MIPS_OPCODE_H__
-
-/* COP0 Ops */
-#define     mfmcz_op         0x0b	/*  01011  */
-#define     wrpgpr_op        0x0e	/*  01110  */
-
-/*  COP0 opcodes (only if COP0 and CO=1):  */
-#define     wait_op               0x20	/*  100000  */
-
-#endif /* __KVM_MIPS_OPCODE_H__ */
diff --git a/arch/mips/kvm/kvm_locore.S b/arch/mips/kvm/locore.S
index 033ac343e72..d7279c03c51 100644
--- a/arch/mips/kvm/kvm_locore.S
+++ b/arch/mips/kvm/locore.S
@@ -16,7 +16,6 @@
 #include <asm/stackframe.h>
 #include <asm/asm-offsets.h>
 
-
 #define _C_LABEL(x)     x
 #define MIPSX(name)     mips32_ ## name
 #define CALLFRAME_SIZ   32
@@ -91,7 +90,10 @@ FEXPORT(__kvm_mips_vcpu_run)
 	LONG_S	$24, PT_R24(k1)
 	LONG_S	$25, PT_R25(k1)
 
-	/* XXXKYMA k0/k1 not saved, not being used if we got here through an ioctl() */
+	/*
+	 * XXXKYMA k0/k1 not saved, not being used if we got here through
+	 * an ioctl()
+	 */
 
 	LONG_S	$28, PT_R28(k1)
 	LONG_S	$29, PT_R29(k1)
@@ -132,7 +134,10 @@ FEXPORT(__kvm_mips_vcpu_run)
 	/* Save the kernel gp as well */
 	LONG_S	gp, VCPU_HOST_GP(k1)
 
-	/* Setup status register for running the guest in UM, interrupts are disabled */
+	/*
+	 * Setup status register for running the guest in UM, interrupts
+	 * are disabled
+	 */
 	li	k0, (ST0_EXL | KSU_USER | ST0_BEV)
 	mtc0	k0, CP0_STATUS
 	ehb
@@ -152,7 +157,6 @@ FEXPORT(__kvm_mips_vcpu_run)
 	mtc0	k0, CP0_STATUS
 	ehb
 
-
 	/* Set Guest EPC */
 	LONG_L	t0, VCPU_PC(k1)
 	mtc0	t0, CP0_EPC
@@ -165,7 +169,7 @@ FEXPORT(__kvm_mips_load_asid)
 	 INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
 	INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
 1:
-	     /* t1: contains the base of the ASID array, need to get the cpu id  */
+	/* t1: contains the base of the ASID array, need to get the cpu id */
 	LONG_L	t2, TI_CPU($28)             /* smp_processor_id */
 	INT_SLL	t2, t2, 2                   /* x4 */
 	REG_ADDU t3, t1, t2
@@ -229,9 +233,7 @@ FEXPORT(__kvm_mips_load_k0k1)
 	eret
 
 VECTOR(MIPSX(exception), unknown)
-/*
- * Find out what mode we came from and jump to the proper handler.
- */
+/* Find out what mode we came from and jump to the proper handler. */
 	mtc0	k0, CP0_ERROREPC	#01: Save guest k0
 	ehb				#02:
 
@@ -239,7 +241,8 @@ VECTOR(MIPSX(exception), unknown)
 	INT_SRL	k0, k0, 10		#03: Get rid of CPUNum
 	INT_SLL	k0, k0, 10		#04
 	LONG_S	k1, 0x3000(k0)		#05: Save k1 @ offset 0x3000
-	INT_ADDIU k0, k0, 0x2000		#06: Exception handler is installed @ offset 0x2000
+	INT_ADDIU k0, k0, 0x2000	#06: Exception handler is
+					#    installed @ offset 0x2000
 	j	k0			#07: jump to the function
 	 nop				#08: branch delay slot
 VECTOR_END(MIPSX(exceptionEnd))
@@ -248,7 +251,6 @@ VECTOR_END(MIPSX(exceptionEnd))
 /*
  * Generic Guest exception handler. We end up here when the guest
  * does something that causes a trap to kernel mode.
- *
  */
 NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra)
 	/* Get the VCPU pointer from DDTATA_LO */
@@ -290,9 +292,7 @@ NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra)
 	LONG_S	$30, VCPU_R30(k1)
 	LONG_S	$31, VCPU_R31(k1)
 
-	/* We need to save hi/lo and restore them on
-	 * the way out
-	 */
+	/* We need to save hi/lo and restore them on the way out */
 	mfhi	t0
 	LONG_S	t0, VCPU_HI(k1)
 
@@ -321,8 +321,10 @@ NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra)
 	/* Save pointer to run in s0, will be saved by the compiler */
 	move	s0, a0
 
-	/* Save Host level EPC, BadVaddr and Cause to VCPU, useful to
-	 * process the exception */
+	/*
+	 * Save Host level EPC, BadVaddr and Cause to VCPU, useful to
+	 * process the exception
+	 */
 	mfc0	k0,CP0_EPC
 	LONG_S	k0, VCPU_PC(k1)
 
@@ -351,7 +353,6 @@ NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra)
 	LONG_L	k0, VCPU_HOST_EBASE(k1)
 	mtc0	k0,CP0_EBASE
 
-
 	/* Now that the new EBASE has been loaded, unset BEV and KSU_USER */
 	.set	at
 	and	v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE)
@@ -369,7 +370,8 @@ NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra)
 	/* Saved host state */
 	INT_ADDIU sp, sp, -PT_SIZE
 
-	/* XXXKYMA do we need to load the host ASID, maybe not because the
+	/*
+	 * XXXKYMA do we need to load the host ASID, maybe not because the
 	 * kernel entries are marked GLOBAL, need to verify
 	 */
 
@@ -383,9 +385,11 @@ NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra)
 
 	/* Jump to handler */
 FEXPORT(__kvm_mips_jump_to_handler)
-	/* XXXKYMA: not sure if this is safe, how large is the stack??
+	/*
+	 * XXXKYMA: not sure if this is safe, how large is the stack??
 	 * Now jump to the kvm_mips_handle_exit() to see if we can deal
-	 * with this in the kernel */
+	 * with this in the kernel
+	 */
 	PTR_LA	t9, kvm_mips_handle_exit
 	jalr.hb	t9
 	 INT_ADDIU sp, sp, -CALLFRAME_SIZ           /* BD Slot */
@@ -394,7 +398,8 @@ FEXPORT(__kvm_mips_jump_to_handler)
 	di
 	ehb
 
-	/* XXXKYMA: k0/k1 could have been blown away if we processed
+	/*
+	 * XXXKYMA: k0/k1 could have been blown away if we processed
 	 * an exception while we were handling the exception from the
 	 * guest, reload k1
 	 */
@@ -402,7 +407,8 @@ FEXPORT(__kvm_mips_jump_to_handler)
 	move	k1, s1
 	INT_ADDIU k1, k1, VCPU_HOST_ARCH
 
-	/* Check return value, should tell us if we are returning to the
+	/*
+	 * Check return value, should tell us if we are returning to the
 	 * host (handle I/O etc)or resuming the guest
 	 */
 	andi	t0, v0, RESUME_HOST
@@ -521,8 +527,10 @@ __kvm_mips_return_to_host:
 	LONG_L	$0, PT_R0(k1)
 	LONG_L	$1, PT_R1(k1)
 
-	/* r2/v0 is the return code, shift it down by 2 (arithmetic)
-	 * to recover the err code  */
+	/*
+	 * r2/v0 is the return code, shift it down by 2 (arithmetic)
+	 * to recover the err code
+	 */
 	INT_SRA	k0, v0, 2
 	move	$2, k0
 
@@ -566,7 +574,6 @@ __kvm_mips_return_to_host:
 	PTR_LI	k0, 0x2000000F
 	mtc0	k0,  CP0_HWRENA
 
-
 	/* Restore RA, which is the address we will return to */
 	LONG_L  ra, PT_R31(k1)
 	j       ra
diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/mips.c
index cd5e4f56843..4fda672cb58 100644
--- a/arch/mips/kvm/kvm_mips.c
+++ b/arch/mips/kvm/mips.c
@@ -7,7 +7,7 @@
  *
  * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
  * Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ */
 
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -21,8 +21,8 @@
 
 #include <linux/kvm_host.h>
 
-#include "kvm_mips_int.h"
-#include "kvm_mips_comm.h"
+#include "interrupt.h"
+#include "commpage.h"
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -31,38 +31,41 @@
 #define VECTORSPACING 0x100	/* for EI/VI mode */
 #endif
 
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x)
 struct kvm_stats_debugfs_item debugfs_entries[] = {
-	{ "wait", VCPU_STAT(wait_exits) },
-	{ "cache", VCPU_STAT(cache_exits) },
-	{ "signal", VCPU_STAT(signal_exits) },
-	{ "interrupt", VCPU_STAT(int_exits) },
-	{ "cop_unsuable", VCPU_STAT(cop_unusable_exits) },
-	{ "tlbmod", VCPU_STAT(tlbmod_exits) },
-	{ "tlbmiss_ld", VCPU_STAT(tlbmiss_ld_exits) },
-	{ "tlbmiss_st", VCPU_STAT(tlbmiss_st_exits) },
-	{ "addrerr_st", VCPU_STAT(addrerr_st_exits) },
-	{ "addrerr_ld", VCPU_STAT(addrerr_ld_exits) },
-	{ "syscall", VCPU_STAT(syscall_exits) },
-	{ "resvd_inst", VCPU_STAT(resvd_inst_exits) },
-	{ "break_inst", VCPU_STAT(break_inst_exits) },
-	{ "flush_dcache", VCPU_STAT(flush_dcache_exits) },
-	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
+	{ "wait",	  VCPU_STAT(wait_exits),	 KVM_STAT_VCPU },
+	{ "cache",	  VCPU_STAT(cache_exits),	 KVM_STAT_VCPU },
+	{ "signal",	  VCPU_STAT(signal_exits),	 KVM_STAT_VCPU },
+	{ "interrupt",	  VCPU_STAT(int_exits),		 KVM_STAT_VCPU },
+	{ "cop_unsuable", VCPU_STAT(cop_unusable_exits), KVM_STAT_VCPU },
+	{ "tlbmod",	  VCPU_STAT(tlbmod_exits),	 KVM_STAT_VCPU },
+	{ "tlbmiss_ld",	  VCPU_STAT(tlbmiss_ld_exits),	 KVM_STAT_VCPU },
+	{ "tlbmiss_st",	  VCPU_STAT(tlbmiss_st_exits),	 KVM_STAT_VCPU },
+	{ "addrerr_st",	  VCPU_STAT(addrerr_st_exits),	 KVM_STAT_VCPU },
+	{ "addrerr_ld",	  VCPU_STAT(addrerr_ld_exits),	 KVM_STAT_VCPU },
+	{ "syscall",	  VCPU_STAT(syscall_exits),	 KVM_STAT_VCPU },
+	{ "resvd_inst",	  VCPU_STAT(resvd_inst_exits),	 KVM_STAT_VCPU },
+	{ "break_inst",	  VCPU_STAT(break_inst_exits),	 KVM_STAT_VCPU },
+	{ "flush_dcache", VCPU_STAT(flush_dcache_exits), KVM_STAT_VCPU },
+	{ "halt_wakeup",  VCPU_STAT(halt_wakeup),	 KVM_STAT_VCPU },
 	{NULL}
 };
 
 static int kvm_mips_reset_vcpu(struct kvm_vcpu *vcpu)
 {
 	int i;
+
 	for_each_possible_cpu(i) {
 		vcpu->arch.guest_kernel_asid[i] = 0;
 		vcpu->arch.guest_user_asid[i] = 0;
 	}
+
 	return 0;
 }
 
-/* XXXKYMA: We are simulatoring a processor that has the WII bit set in Config7, so we
- * are "runnable" if interrupts are pending
+/*
+ * XXXKYMA: We are simulatoring a processor that has the WII bit set in
+ * Config7, so we are "runnable" if interrupts are pending
  */
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
@@ -94,16 +97,17 @@ void kvm_arch_hardware_unsetup(void)
 
 void kvm_arch_check_processor_compat(void *rtn)
 {
-	int *r = (int *)rtn;
-	*r = 0;
-	return;
+	*(int *)rtn = 0;
 }
 
 static void kvm_mips_init_tlbs(struct kvm *kvm)
 {
 	unsigned long wired;
 
-	/* Add a wired entry to the TLB, it is used to map the commpage to the Guest kernel */
+	/*
+	 * Add a wired entry to the TLB, it is used to map the commpage to
+	 * the Guest kernel
+	 */
 	wired = read_c0_wired();
 	write_c0_wired(wired + 1);
 	mtc0_tlbw_hazard();
@@ -130,7 +134,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		on_each_cpu(kvm_mips_init_vm_percpu, kvm, 1);
 	}
 
-
 	return 0;
 }
 
@@ -185,8 +188,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	}
 }
 
-long
-kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl,
+			unsigned long arg)
 {
 	return -ENOIOCTLCMD;
 }
@@ -207,20 +210,20 @@ void kvm_arch_memslots_updated(struct kvm *kvm)
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
-                                struct kvm_memory_slot *memslot,
-                                struct kvm_userspace_memory_region *mem,
-                                enum kvm_mr_change change)
+				   struct kvm_memory_slot *memslot,
+				   struct kvm_userspace_memory_region *mem,
+				   enum kvm_mr_change change)
 {
 	return 0;
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
-                                struct kvm_userspace_memory_region *mem,
-                                const struct kvm_memory_slot *old,
-                                enum kvm_mr_change change)
+				   struct kvm_userspace_memory_region *mem,
+				   const struct kvm_memory_slot *old,
+				   enum kvm_mr_change change)
 {
 	unsigned long npages = 0;
-	int i, err = 0;
+	int i;
 
 	kvm_debug("%s: kvm: %p slot: %d, GPA: %llx, size: %llx, QVA: %llx\n",
 		  __func__, kvm, mem->slot, mem->guest_phys_addr,
@@ -238,21 +241,17 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 
 			if (!kvm->arch.guest_pmap) {
 				kvm_err("Failed to allocate guest PMAP");
-				err = -ENOMEM;
-				goto out;
+				return;
 			}
 
 			kvm_debug("Allocated space for Guest PMAP Table (%ld pages) @ %p\n",
 				  npages, kvm->arch.guest_pmap);
 
 			/* Now setup the page table */
-			for (i = 0; i < npages; i++) {
+			for (i = 0; i < npages; i++)
 				kvm->arch.guest_pmap[i] = KVM_INVALID_PAGE;
-			}
 		}
 	}
-out:
-	return;
 }
 
 void kvm_arch_flush_shadow_all(struct kvm *kvm)
@@ -270,8 +269,6 @@ void kvm_arch_flush_shadow(struct kvm *kvm)
 
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
-	extern char mips32_exception[], mips32_exceptionEnd[];
-	extern char mips32_GuestException[], mips32_GuestExceptionEnd[];
 	int err, size, offset;
 	void *gebase;
 	int i;
@@ -290,14 +287,14 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 
 	kvm_debug("kvm @ %p: create cpu %d at %p\n", kvm, id, vcpu);
 
-	/* Allocate space for host mode exception handlers that handle
+	/*
+	 * Allocate space for host mode exception handlers that handle
 	 * guest mode exits
 	 */
-	if (cpu_has_veic || cpu_has_vint) {
+	if (cpu_has_veic || cpu_has_vint)
 		size = 0x200 + VECTORSPACING * 64;
-	} else {
+	else
 		size = 0x4000;
-	}
 
 	/* Save Linux EBASE */
 	vcpu->arch.host_ebase = (void *)read_c0_ebase();
@@ -345,7 +342,10 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	local_flush_icache_range((unsigned long)gebase,
 				(unsigned long)gebase + ALIGN(size, PAGE_SIZE));
 
-	/* Allocate comm page for guest kernel, a TLB will be reserved for mapping GVA @ 0xFFFF8000 to this page */
+	/*
+	 * Allocate comm page for guest kernel, a TLB will be reserved for
+	 * mapping GVA @ 0xFFFF8000 to this page
+	 */
 	vcpu->arch.kseg0_commpage = kzalloc(PAGE_SIZE << 1, GFP_KERNEL);
 
 	if (!vcpu->arch.kseg0_commpage) {
@@ -384,6 +384,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 
 	kfree(vcpu->arch.guest_ebase);
 	kfree(vcpu->arch.kseg0_commpage);
+	kfree(vcpu);
 }
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -391,9 +392,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_arch_vcpu_free(vcpu);
 }
 
-int
-kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
-				    struct kvm_guest_debug *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
 {
 	return -ENOIOCTLCMD;
 }
@@ -430,8 +430,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return r;
 }
 
-int
-kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_mips_interrupt *irq)
+int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
+			     struct kvm_mips_interrupt *irq)
 {
 	int intr = (int)irq->irq;
 	struct kvm_vcpu *dvcpu = NULL;
@@ -458,23 +458,20 @@ kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_mips_interrupt *irq)
 
 	dvcpu->arch.wait = 0;
 
-	if (waitqueue_active(&dvcpu->wq)) {
+	if (waitqueue_active(&dvcpu->wq))
 		wake_up_interruptible(&dvcpu->wq);
-	}
 
 	return 0;
 }
 
-int
-kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
-				struct kvm_mp_state *mp_state)
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
 {
 	return -ENOIOCTLCMD;
 }
 
-int
-kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
-				struct kvm_mp_state *mp_state)
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
 {
 	return -ENOIOCTLCMD;
 }
@@ -631,10 +628,12 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu,
 	}
 	if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64) {
 		u64 __user *uaddr64 = (u64 __user *)(long)reg->addr;
+
 		return put_user(v, uaddr64);
 	} else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U32) {
 		u32 __user *uaddr32 = (u32 __user *)(long)reg->addr;
 		u32 v32 = (u32)v;
+
 		return put_user(v32, uaddr32);
 	} else {
 		return -EINVAL;
@@ -727,8 +726,8 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-long
-kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl,
+			 unsigned long arg)
 {
 	struct kvm_vcpu *vcpu = filp->private_data;
 	void __user *argp = (void __user *)arg;
@@ -738,6 +737,7 @@ kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	case KVM_SET_ONE_REG:
 	case KVM_GET_ONE_REG: {
 		struct kvm_one_reg reg;
+
 		if (copy_from_user(&reg, argp, sizeof(reg)))
 			return -EFAULT;
 		if (ioctl == KVM_SET_ONE_REG)
@@ -772,6 +772,7 @@ kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	case KVM_INTERRUPT:
 		{
 			struct kvm_mips_interrupt irq;
+
 			r = -EFAULT;
 			if (copy_from_user(&irq, argp, sizeof(irq)))
 				goto out;
@@ -790,9 +791,7 @@ out:
 	return r;
 }
 
-/*
- * Get (and clear) the dirty memory log for a memory slot.
- */
+/* Get (and clear) the dirty memory log for a memory slot. */
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
 	struct kvm_memory_slot *memslot;
@@ -814,8 +813,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 		ga = memslot->base_gfn << PAGE_SHIFT;
 		ga_end = ga + (memslot->npages << PAGE_SHIFT);
 
-		printk("%s: dirty, ga: %#lx, ga_end %#lx\n", __func__, ga,
-		       ga_end);
+		kvm_info("%s: dirty, ga: %#lx, ga_end %#lx\n", __func__, ga,
+			 ga_end);
 
 		n = kvm_dirty_bitmap_bytes(memslot);
 		memset(memslot->dirty_bitmap, 0, n);
@@ -842,16 +841,12 @@ long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 
 int kvm_arch_init(void *opaque)
 {
-	int ret;
-
 	if (kvm_mips_callbacks) {
 		kvm_err("kvm: module already exists\n");
 		return -EEXIST;
 	}
 
-	ret = kvm_mips_emulation_init(&kvm_mips_callbacks);
-
-	return ret;
+	return kvm_mips_emulation_init(&kvm_mips_callbacks);
 }
 
 void kvm_arch_exit(void)
@@ -859,14 +854,14 @@ void kvm_arch_exit(void)
 	kvm_mips_callbacks = NULL;
 }
 
-int
-kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
 {
 	return -ENOIOCTLCMD;
 }
 
-int
-kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
 {
 	return -ENOIOCTLCMD;
 }
@@ -922,24 +917,25 @@ int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu)
 	if (!vcpu)
 		return -1;
 
-	printk("VCPU Register Dump:\n");
-	printk("\tpc = 0x%08lx\n", vcpu->arch.pc);
-	printk("\texceptions: %08lx\n", vcpu->arch.pending_exceptions);
+	kvm_debug("VCPU Register Dump:\n");
+	kvm_debug("\tpc = 0x%08lx\n", vcpu->arch.pc);
+	kvm_debug("\texceptions: %08lx\n", vcpu->arch.pending_exceptions);
 
 	for (i = 0; i < 32; i += 4) {
-		printk("\tgpr%02d: %08lx %08lx %08lx %08lx\n", i,
+		kvm_debug("\tgpr%02d: %08lx %08lx %08lx %08lx\n", i,
 		       vcpu->arch.gprs[i],
 		       vcpu->arch.gprs[i + 1],
 		       vcpu->arch.gprs[i + 2], vcpu->arch.gprs[i + 3]);
 	}
-	printk("\thi: 0x%08lx\n", vcpu->arch.hi);
-	printk("\tlo: 0x%08lx\n", vcpu->arch.lo);
+	kvm_debug("\thi: 0x%08lx\n", vcpu->arch.hi);
+	kvm_debug("\tlo: 0x%08lx\n", vcpu->arch.lo);
 
 	cop0 = vcpu->arch.cop0;
-	printk("\tStatus: 0x%08lx, Cause: 0x%08lx\n",
-	       kvm_read_c0_guest_status(cop0), kvm_read_c0_guest_cause(cop0));
+	kvm_debug("\tStatus: 0x%08lx, Cause: 0x%08lx\n",
+		  kvm_read_c0_guest_status(cop0),
+		  kvm_read_c0_guest_cause(cop0));
 
-	printk("\tEPC: 0x%08lx\n", kvm_read_c0_guest_epc(cop0));
+	kvm_debug("\tEPC: 0x%08lx\n", kvm_read_c0_guest_epc(cop0));
 
 	return 0;
 }
@@ -979,14 +975,11 @@ static void kvm_mips_comparecount_func(unsigned long data)
 	kvm_mips_callbacks->queue_timer_int(vcpu);
 
 	vcpu->arch.wait = 0;
-	if (waitqueue_active(&vcpu->wq)) {
+	if (waitqueue_active(&vcpu->wq))
 		wake_up_interruptible(&vcpu->wq);
-	}
 }
 
-/*
- * low level hrtimer wake routine.
- */
+/* low level hrtimer wake routine */
 static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
@@ -1007,11 +1000,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
-	return;
 }
 
-int
-kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr)
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+				  struct kvm_translation *tr)
 {
 	return 0;
 }
@@ -1022,8 +1014,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return kvm_mips_callbacks->vcpu_setup(vcpu);
 }
 
-static
-void kvm_mips_set_c0_status(void)
+static void kvm_mips_set_c0_status(void)
 {
 	uint32_t status = read_c0_status();
 
@@ -1053,7 +1044,10 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
 
-	/* Set the appropriate status bits based on host CPU features, before we hit the scheduler */
+	/*
+	 * Set the appropriate status bits based on host CPU features,
+	 * before we hit the scheduler
+	 */
 	kvm_mips_set_c0_status();
 
 	local_irq_enable();
@@ -1061,7 +1055,8 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	kvm_debug("kvm_mips_handle_exit: cause: %#x, PC: %p, kvm_run: %p, kvm_vcpu: %p\n",
 			cause, opc, run, vcpu);
 
-	/* Do a privilege check, if in UM most of these exit conditions end up
+	/*
+	 * Do a privilege check, if in UM most of these exit conditions end up
 	 * causing an exception to be delivered to the Guest Kernel
 	 */
 	er = kvm_mips_check_privilege(cause, opc, run, vcpu);
@@ -1080,9 +1075,8 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		++vcpu->stat.int_exits;
 		trace_kvm_exit(vcpu, INT_EXITS);
 
-		if (need_resched()) {
+		if (need_resched())
 			cond_resched();
-		}
 
 		ret = RESUME_GUEST;
 		break;
@@ -1094,9 +1088,8 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		trace_kvm_exit(vcpu, COP_UNUSABLE_EXITS);
 		ret = kvm_mips_callbacks->handle_cop_unusable(vcpu);
 		/* XXXKYMA: Might need to return to user space */
-		if (run->exit_reason == KVM_EXIT_IRQ_WINDOW_OPEN) {
+		if (run->exit_reason == KVM_EXIT_IRQ_WINDOW_OPEN)
 			ret = RESUME_HOST;
-		}
 		break;
 
 	case T_TLB_MOD:
@@ -1106,10 +1099,9 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		break;
 
 	case T_TLB_ST_MISS:
-		kvm_debug
-		    ("TLB ST fault:  cause %#x, status %#lx, PC: %p, BadVaddr: %#lx\n",
-		     cause, kvm_read_c0_guest_status(vcpu->arch.cop0), opc,
-		     badvaddr);
+		kvm_debug("TLB ST fault:  cause %#x, status %#lx, PC: %p, BadVaddr: %#lx\n",
+			  cause, kvm_read_c0_guest_status(vcpu->arch.cop0), opc,
+			  badvaddr);
 
 		++vcpu->stat.tlbmiss_st_exits;
 		trace_kvm_exit(vcpu, TLBMISS_ST_EXITS);
@@ -1156,10 +1148,9 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		break;
 
 	default:
-		kvm_err
-		    ("Exception Code: %d, not yet handled, @ PC: %p, inst: 0x%08x  BadVaddr: %#lx Status: %#lx\n",
-		     exccode, opc, kvm_get_inst(opc, vcpu), badvaddr,
-		     kvm_read_c0_guest_status(vcpu->arch.cop0));
+		kvm_err("Exception Code: %d, not yet handled, @ PC: %p, inst: 0x%08x  BadVaddr: %#lx Status: %#lx\n",
+			exccode, opc, kvm_get_inst(opc, vcpu), badvaddr,
+			kvm_read_c0_guest_status(vcpu->arch.cop0));
 		kvm_arch_vcpu_dump_regs(vcpu);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		ret = RESUME_HOST;
@@ -1174,7 +1165,7 @@ skip_emul:
 		kvm_mips_deliver_interrupts(vcpu, cause);
 
 	if (!(ret & RESUME_HOST)) {
-		/* Only check for signals if not already exiting to userspace  */
+		/* Only check for signals if not already exiting to userspace */
 		if (signal_pending(current)) {
 			run->exit_reason = KVM_EXIT_INTR;
 			ret = (-EINTR << 2) | RESUME_HOST;
@@ -1195,11 +1186,13 @@ int __init kvm_mips_init(void)
 	if (ret)
 		return ret;
 
-	/* On MIPS, kernel modules are executed from "mapped space", which requires TLBs.
-	 * The TLB handling code is statically linked with the rest of the kernel (kvm_tlb.c)
-	 * to avoid the possibility of double faulting. The issue is that the TLB code
-	 * references routines that are part of the the KVM module,
-	 * which are only available once the module is loaded.
+	/*
+	 * On MIPS, kernel modules are executed from "mapped space", which
+	 * requires TLBs. The TLB handling code is statically linked with
+	 * the rest of the kernel (tlb.c) to avoid the possibility of
+	 * double faulting. The issue is that the TLB code references
+	 * routines that are part of the the KVM module, which are only
+	 * available once the module is loaded.
 	 */
 	kvm_mips_gfn_to_pfn = gfn_to_pfn;
 	kvm_mips_release_pfn_clean = kvm_release_pfn_clean;
diff --git a/arch/mips/kvm/opcode.h b/arch/mips/kvm/opcode.h
new file mode 100644
index 00000000000..03a6ae84c7d
--- /dev/null
+++ b/arch/mips/kvm/opcode.h
@@ -0,0 +1,22 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
+
+/* Define opcode values not defined in <asm/isnt.h> */
+
+#ifndef __KVM_MIPS_OPCODE_H__
+#define __KVM_MIPS_OPCODE_H__
+
+/* COP0 Ops */
+#define mfmcz_op	0x0b	/* 01011 */
+#define wrpgpr_op	0x0e	/* 01110 */
+
+/* COP0 opcodes (only if COP0 and CO=1): */
+#define wait_op		0x20	/* 100000 */
+
+#endif /* __KVM_MIPS_OPCODE_H__ */
diff --git a/arch/mips/kvm/kvm_mips_stats.c b/arch/mips/kvm/stats.c
index 075904bcac1..a74d6024c5a 100644
--- a/arch/mips/kvm/kvm_mips_stats.c
+++ b/arch/mips/kvm/stats.c
@@ -1,13 +1,13 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* KVM/MIPS: COP0 access histogram
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS: COP0 access histogram
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #include <linux/kvm_host.h>
 
@@ -63,20 +63,18 @@ char *kvm_cop0_str[N_MIPS_COPROC_REGS] = {
 	"DESAVE"
 };
 
-int kvm_mips_dump_stats(struct kvm_vcpu *vcpu)
+void kvm_mips_dump_stats(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_KVM_MIPS_DEBUG_COP0_COUNTERS
 	int i, j;
 
-	printk("\nKVM VCPU[%d] COP0 Access Profile:\n", vcpu->vcpu_id);
+	kvm_info("\nKVM VCPU[%d] COP0 Access Profile:\n", vcpu->vcpu_id);
 	for (i = 0; i < N_MIPS_COPROC_REGS; i++) {
 		for (j = 0; j < N_MIPS_COPROC_SEL; j++) {
 			if (vcpu->arch.cop0->stat[i][j])
-				printk("%s[%d]: %lu\n", kvm_cop0_str[i], j,
-				       vcpu->arch.cop0->stat[i][j]);
+				kvm_info("%s[%d]: %lu\n", kvm_cop0_str[i], j,
+					 vcpu->arch.cop0->stat[i][j]);
 		}
 	}
 #endif
-
-	return 0;
 }
diff --git a/arch/mips/kvm/kvm_tlb.c b/arch/mips/kvm/tlb.c
index 8a5a700ad8d..bbcd8224205 100644
--- a/arch/mips/kvm/kvm_tlb.c
+++ b/arch/mips/kvm/tlb.c
@@ -1,14 +1,14 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* KVM/MIPS TLB handling, this file is part of the Linux host kernel so that
-* TLB handlers run from KSEG0
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS TLB handling, this file is part of the Linux host kernel so that
+ * TLB handlers run from KSEG0
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #include <linux/sched.h>
 #include <linux/smp.h>
@@ -18,7 +18,6 @@
 #include <linux/kvm_host.h>
 #include <linux/srcu.h>
 
-
 #include <asm/cpu.h>
 #include <asm/bootinfo.h>
 #include <asm/mmu_context.h>
@@ -39,13 +38,13 @@ atomic_t kvm_mips_instance;
 EXPORT_SYMBOL(kvm_mips_instance);
 
 /* These function pointers are initialized once the KVM module is loaded */
-pfn_t(*kvm_mips_gfn_to_pfn) (struct kvm *kvm, gfn_t gfn);
+pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn);
 EXPORT_SYMBOL(kvm_mips_gfn_to_pfn);
 
-void (*kvm_mips_release_pfn_clean) (pfn_t pfn);
+void (*kvm_mips_release_pfn_clean)(pfn_t pfn);
 EXPORT_SYMBOL(kvm_mips_release_pfn_clean);
 
-bool(*kvm_mips_is_error_pfn) (pfn_t pfn);
+bool (*kvm_mips_is_error_pfn)(pfn_t pfn);
 EXPORT_SYMBOL(kvm_mips_is_error_pfn);
 
 uint32_t kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu)
@@ -53,21 +52,17 @@ uint32_t kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu)
 	return vcpu->arch.guest_kernel_asid[smp_processor_id()] & ASID_MASK;
 }
 
-
 uint32_t kvm_mips_get_user_asid(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.guest_user_asid[smp_processor_id()] & ASID_MASK;
 }
 
-inline uint32_t kvm_mips_get_commpage_asid (struct kvm_vcpu *vcpu)
+inline uint32_t kvm_mips_get_commpage_asid(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->arch.commpage_tlb;
 }
 
-
-/*
- * Structure defining an tlb entry data set.
- */
+/* Structure defining an tlb entry data set. */
 
 void kvm_mips_dump_host_tlbs(void)
 {
@@ -82,8 +77,8 @@ void kvm_mips_dump_host_tlbs(void)
 	old_entryhi = read_c0_entryhi();
 	old_pagemask = read_c0_pagemask();
 
-	printk("HOST TLBs:\n");
-	printk("ASID: %#lx\n", read_c0_entryhi() & ASID_MASK);
+	kvm_info("HOST TLBs:\n");
+	kvm_info("ASID: %#lx\n", read_c0_entryhi() & ASID_MASK);
 
 	for (i = 0; i < current_cpu_data.tlbsize; i++) {
 		write_c0_index(i);
@@ -97,25 +92,26 @@ void kvm_mips_dump_host_tlbs(void)
 		tlb.tlb_lo1 = read_c0_entrylo1();
 		tlb.tlb_mask = read_c0_pagemask();
 
-		printk("TLB%c%3d Hi 0x%08lx ",
-		       (tlb.tlb_lo0 | tlb.tlb_lo1) & MIPS3_PG_V ? ' ' : '*',
-		       i, tlb.tlb_hi);
-		printk("Lo0=0x%09" PRIx64 " %c%c attr %lx ",
-		       (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo0),
-		       (tlb.tlb_lo0 & MIPS3_PG_D) ? 'D' : ' ',
-		       (tlb.tlb_lo0 & MIPS3_PG_G) ? 'G' : ' ',
-		       (tlb.tlb_lo0 >> 3) & 7);
-		printk("Lo1=0x%09" PRIx64 " %c%c attr %lx sz=%lx\n",
-		       (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo1),
-		       (tlb.tlb_lo1 & MIPS3_PG_D) ? 'D' : ' ',
-		       (tlb.tlb_lo1 & MIPS3_PG_G) ? 'G' : ' ',
-		       (tlb.tlb_lo1 >> 3) & 7, tlb.tlb_mask);
+		kvm_info("TLB%c%3d Hi 0x%08lx ",
+			 (tlb.tlb_lo0 | tlb.tlb_lo1) & MIPS3_PG_V ? ' ' : '*',
+			 i, tlb.tlb_hi);
+		kvm_info("Lo0=0x%09" PRIx64 " %c%c attr %lx ",
+			 (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo0),
+			 (tlb.tlb_lo0 & MIPS3_PG_D) ? 'D' : ' ',
+			 (tlb.tlb_lo0 & MIPS3_PG_G) ? 'G' : ' ',
+			 (tlb.tlb_lo0 >> 3) & 7);
+		kvm_info("Lo1=0x%09" PRIx64 " %c%c attr %lx sz=%lx\n",
+			 (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo1),
+			 (tlb.tlb_lo1 & MIPS3_PG_D) ? 'D' : ' ',
+			 (tlb.tlb_lo1 & MIPS3_PG_G) ? 'G' : ' ',
+			 (tlb.tlb_lo1 >> 3) & 7, tlb.tlb_mask);
 	}
 	write_c0_entryhi(old_entryhi);
 	write_c0_pagemask(old_pagemask);
 	mtc0_tlbw_hazard();
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL(kvm_mips_dump_host_tlbs);
 
 void kvm_mips_dump_guest_tlbs(struct kvm_vcpu *vcpu)
 {
@@ -123,26 +119,27 @@ void kvm_mips_dump_guest_tlbs(struct kvm_vcpu *vcpu)
 	struct kvm_mips_tlb tlb;
 	int i;
 
-	printk("Guest TLBs:\n");
-	printk("Guest EntryHi: %#lx\n", kvm_read_c0_guest_entryhi(cop0));
+	kvm_info("Guest TLBs:\n");
+	kvm_info("Guest EntryHi: %#lx\n", kvm_read_c0_guest_entryhi(cop0));
 
 	for (i = 0; i < KVM_MIPS_GUEST_TLB_SIZE; i++) {
 		tlb = vcpu->arch.guest_tlb[i];
-		printk("TLB%c%3d Hi 0x%08lx ",
-		       (tlb.tlb_lo0 | tlb.tlb_lo1) & MIPS3_PG_V ? ' ' : '*',
-		       i, tlb.tlb_hi);
-		printk("Lo0=0x%09" PRIx64 " %c%c attr %lx ",
-		       (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo0),
-		       (tlb.tlb_lo0 & MIPS3_PG_D) ? 'D' : ' ',
-		       (tlb.tlb_lo0 & MIPS3_PG_G) ? 'G' : ' ',
-		       (tlb.tlb_lo0 >> 3) & 7);
-		printk("Lo1=0x%09" PRIx64 " %c%c attr %lx sz=%lx\n",
-		       (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo1),
-		       (tlb.tlb_lo1 & MIPS3_PG_D) ? 'D' : ' ',
-		       (tlb.tlb_lo1 & MIPS3_PG_G) ? 'G' : ' ',
-		       (tlb.tlb_lo1 >> 3) & 7, tlb.tlb_mask);
+		kvm_info("TLB%c%3d Hi 0x%08lx ",
+			 (tlb.tlb_lo0 | tlb.tlb_lo1) & MIPS3_PG_V ? ' ' : '*',
+			 i, tlb.tlb_hi);
+		kvm_info("Lo0=0x%09" PRIx64 " %c%c attr %lx ",
+			 (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo0),
+			 (tlb.tlb_lo0 & MIPS3_PG_D) ? 'D' : ' ',
+			 (tlb.tlb_lo0 & MIPS3_PG_G) ? 'G' : ' ',
+			 (tlb.tlb_lo0 >> 3) & 7);
+		kvm_info("Lo1=0x%09" PRIx64 " %c%c attr %lx sz=%lx\n",
+			 (uint64_t) mips3_tlbpfn_to_paddr(tlb.tlb_lo1),
+			 (tlb.tlb_lo1 & MIPS3_PG_D) ? 'D' : ' ',
+			 (tlb.tlb_lo1 & MIPS3_PG_G) ? 'G' : ' ',
+			 (tlb.tlb_lo1 >> 3) & 7, tlb.tlb_mask);
 	}
 }
+EXPORT_SYMBOL(kvm_mips_dump_guest_tlbs);
 
 static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
 {
@@ -152,7 +149,7 @@ static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn)
 	if (kvm->arch.guest_pmap[gfn] != KVM_INVALID_PAGE)
 		return 0;
 
-        srcu_idx = srcu_read_lock(&kvm->srcu);
+	srcu_idx = srcu_read_lock(&kvm->srcu);
 	pfn = kvm_mips_gfn_to_pfn(kvm, gfn);
 
 	if (kvm_mips_is_error_pfn(pfn)) {
@@ -169,7 +166,7 @@ out:
 
 /* Translate guest KSEG0 addresses to Host PA */
 unsigned long kvm_mips_translate_guest_kseg0_to_hpa(struct kvm_vcpu *vcpu,
-	unsigned long gva)
+						    unsigned long gva)
 {
 	gfn_t gfn;
 	uint32_t offset = gva & ~PAGE_MASK;
@@ -194,20 +191,20 @@ unsigned long kvm_mips_translate_guest_kseg0_to_hpa(struct kvm_vcpu *vcpu,
 
 	return (kvm->arch.guest_pmap[gfn] << PAGE_SHIFT) + offset;
 }
+EXPORT_SYMBOL(kvm_mips_translate_guest_kseg0_to_hpa);
 
 /* XXXKYMA: Must be called with interrupts disabled */
 /* set flush_dcache_mask == 0 if no dcache flush required */
-int
-kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi,
-	unsigned long entrylo0, unsigned long entrylo1, int flush_dcache_mask)
+int kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi,
+			    unsigned long entrylo0, unsigned long entrylo1,
+			    int flush_dcache_mask)
 {
 	unsigned long flags;
 	unsigned long old_entryhi;
-	volatile int idx;
+	int idx;
 
 	local_irq_save(flags);
 
-
 	old_entryhi = read_c0_entryhi();
 	write_c0_entryhi(entryhi);
 	mtc0_tlbw_hazard();
@@ -240,12 +237,14 @@ kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi,
 	if (flush_dcache_mask) {
 		if (entrylo0 & MIPS3_PG_V) {
 			++vcpu->stat.flush_dcache_exits;
-			flush_data_cache_page((entryhi & VPN2_MASK) & ~flush_dcache_mask);
+			flush_data_cache_page((entryhi & VPN2_MASK) &
+					      ~flush_dcache_mask);
 		}
 		if (entrylo1 & MIPS3_PG_V) {
 			++vcpu->stat.flush_dcache_exits;
-			flush_data_cache_page(((entryhi & VPN2_MASK) & ~flush_dcache_mask) |
-				(0x1 << PAGE_SHIFT));
+			flush_data_cache_page(((entryhi & VPN2_MASK) &
+					       ~flush_dcache_mask) |
+					      (0x1 << PAGE_SHIFT));
 		}
 	}
 
@@ -257,10 +256,9 @@ kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi,
 	return 0;
 }
 
-
 /* XXXKYMA: Must be called with interrupts disabled */
 int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
-	struct kvm_vcpu *vcpu)
+				    struct kvm_vcpu *vcpu)
 {
 	gfn_t gfn;
 	pfn_t pfn0, pfn1;
@@ -270,7 +268,6 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
 	struct kvm *kvm = vcpu->kvm;
 	const int flush_dcache_mask = 0;
 
-
 	if (KVM_GUEST_KSEGX(badvaddr) != KVM_GUEST_KSEG0) {
 		kvm_err("%s: Invalid BadVaddr: %#lx\n", __func__, badvaddr);
 		kvm_mips_dump_host_tlbs();
@@ -302,14 +299,15 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr,
 	}
 
 	entryhi = (vaddr | kvm_mips_get_kernel_asid(vcpu));
-	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) | (1 << 2) |
-			(0x1 << 1);
-	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) | (1 << 2) |
-			(0x1 << 1);
+	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
+		   (1 << 2) | (0x1 << 1);
+	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
+		   (1 << 2) | (0x1 << 1);
 
 	return kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
 				       flush_dcache_mask);
 }
+EXPORT_SYMBOL(kvm_mips_handle_kseg0_tlb_fault);
 
 int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr,
 	struct kvm_vcpu *vcpu)
@@ -318,11 +316,10 @@ int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr,
 	unsigned long flags, old_entryhi = 0, vaddr = 0;
 	unsigned long entrylo0 = 0, entrylo1 = 0;
 
-
 	pfn0 = CPHYSADDR(vcpu->arch.kseg0_commpage) >> PAGE_SHIFT;
 	pfn1 = 0;
-	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) | (1 << 2) |
-			(0x1 << 1);
+	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
+		   (1 << 2) | (0x1 << 1);
 	entrylo1 = 0;
 
 	local_irq_save(flags);
@@ -341,9 +338,9 @@ int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr,
 	mtc0_tlbw_hazard();
 	tlbw_use_hazard();
 
-	kvm_debug ("@ %#lx idx: %2d [entryhi(R): %#lx] entrylo0 (R): 0x%08lx, entrylo1(R): 0x%08lx\n",
-	     vcpu->arch.pc, read_c0_index(), read_c0_entryhi(),
-	     read_c0_entrylo0(), read_c0_entrylo1());
+	kvm_debug("@ %#lx idx: %2d [entryhi(R): %#lx] entrylo0 (R): 0x%08lx, entrylo1(R): 0x%08lx\n",
+		  vcpu->arch.pc, read_c0_index(), read_c0_entryhi(),
+		  read_c0_entrylo0(), read_c0_entrylo1());
 
 	/* Restore old ASID */
 	write_c0_entryhi(old_entryhi);
@@ -353,28 +350,33 @@ int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr,
 
 	return 0;
 }
+EXPORT_SYMBOL(kvm_mips_handle_commpage_tlb_fault);
 
-int
-kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
-	struct kvm_mips_tlb *tlb, unsigned long *hpa0, unsigned long *hpa1)
+int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
+					 struct kvm_mips_tlb *tlb,
+					 unsigned long *hpa0,
+					 unsigned long *hpa1)
 {
 	unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
 	struct kvm *kvm = vcpu->kvm;
 	pfn_t pfn0, pfn1;
 
-
 	if ((tlb->tlb_hi & VPN2_MASK) == 0) {
 		pfn0 = 0;
 		pfn1 = 0;
 	} else {
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0) >> PAGE_SHIFT) < 0)
+		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
+					   >> PAGE_SHIFT) < 0)
 			return -1;
 
-		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1) >> PAGE_SHIFT) < 0)
+		if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
+					   >> PAGE_SHIFT) < 0)
 			return -1;
 
-		pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0) >> PAGE_SHIFT];
-		pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1) >> PAGE_SHIFT];
+		pfn0 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo0)
+					    >> PAGE_SHIFT];
+		pfn1 = kvm->arch.guest_pmap[mips3_tlbpfn_to_paddr(tlb->tlb_lo1)
+					    >> PAGE_SHIFT];
 	}
 
 	if (hpa0)
@@ -385,11 +387,12 @@ kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
 
 	/* Get attributes from the Guest TLB */
 	entryhi = (tlb->tlb_hi & VPN2_MASK) | (KVM_GUEST_KERNEL_MODE(vcpu) ?
-			kvm_mips_get_kernel_asid(vcpu) : kvm_mips_get_user_asid(vcpu));
+					       kvm_mips_get_kernel_asid(vcpu) :
+					       kvm_mips_get_user_asid(vcpu));
 	entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | (0x3 << 3) |
-			(tlb->tlb_lo0 & MIPS3_PG_D) | (tlb->tlb_lo0 & MIPS3_PG_V);
+		   (tlb->tlb_lo0 & MIPS3_PG_D) | (tlb->tlb_lo0 & MIPS3_PG_V);
 	entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | (0x3 << 3) |
-			(tlb->tlb_lo1 & MIPS3_PG_D) | (tlb->tlb_lo1 & MIPS3_PG_V);
+		   (tlb->tlb_lo1 & MIPS3_PG_D) | (tlb->tlb_lo1 & MIPS3_PG_V);
 
 	kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
 		  tlb->tlb_lo0, tlb->tlb_lo1);
@@ -397,6 +400,7 @@ kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu,
 	return kvm_mips_host_tlb_write(vcpu, entryhi, entrylo0, entrylo1,
 				       tlb->tlb_mask);
 }
+EXPORT_SYMBOL(kvm_mips_handle_mapped_seg_tlb_fault);
 
 int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long entryhi)
 {
@@ -404,10 +408,9 @@ int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long entryhi)
 	int index = -1;
 	struct kvm_mips_tlb *tlb = vcpu->arch.guest_tlb;
 
-
 	for (i = 0; i < KVM_MIPS_GUEST_TLB_SIZE; i++) {
-		if (((TLB_VPN2(tlb[i]) & ~tlb[i].tlb_mask) == ((entryhi & VPN2_MASK) & ~tlb[i].tlb_mask)) &&
-			(TLB_IS_GLOBAL(tlb[i]) || (TLB_ASID(tlb[i]) == (entryhi & ASID_MASK)))) {
+		if (TLB_HI_VPN2_HIT(tlb[i], entryhi) &&
+		    TLB_HI_ASID_HIT(tlb[i], entryhi)) {
 			index = i;
 			break;
 		}
@@ -418,21 +421,23 @@ int kvm_mips_guest_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long entryhi)
 
 	return index;
 }
+EXPORT_SYMBOL(kvm_mips_guest_tlb_lookup);
 
 int kvm_mips_host_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long vaddr)
 {
 	unsigned long old_entryhi, flags;
-	volatile int idx;
-
+	int idx;
 
 	local_irq_save(flags);
 
 	old_entryhi = read_c0_entryhi();
 
 	if (KVM_GUEST_KERNEL_MODE(vcpu))
-		write_c0_entryhi((vaddr & VPN2_MASK) | kvm_mips_get_kernel_asid(vcpu));
+		write_c0_entryhi((vaddr & VPN2_MASK) |
+				 kvm_mips_get_kernel_asid(vcpu));
 	else {
-		write_c0_entryhi((vaddr & VPN2_MASK) | kvm_mips_get_user_asid(vcpu));
+		write_c0_entryhi((vaddr & VPN2_MASK) |
+				 kvm_mips_get_user_asid(vcpu));
 	}
 
 	mtc0_tlbw_hazard();
@@ -452,6 +457,7 @@ int kvm_mips_host_tlb_lookup(struct kvm_vcpu *vcpu, unsigned long vaddr)
 
 	return idx;
 }
+EXPORT_SYMBOL(kvm_mips_host_tlb_lookup);
 
 int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va)
 {
@@ -460,7 +466,6 @@ int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va)
 
 	local_irq_save(flags);
 
-
 	old_entryhi = read_c0_entryhi();
 
 	write_c0_entryhi((va & VPN2_MASK) | kvm_mips_get_user_asid(vcpu));
@@ -499,8 +504,9 @@ int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va)
 
 	return 0;
 }
+EXPORT_SYMBOL(kvm_mips_host_tlb_inv);
 
-/* XXXKYMA: Fix Guest USER/KERNEL no longer share the same ASID*/
+/* XXXKYMA: Fix Guest USER/KERNEL no longer share the same ASID */
 int kvm_mips_host_tlb_inv_index(struct kvm_vcpu *vcpu, int index)
 {
 	unsigned long flags, old_entryhi;
@@ -510,7 +516,6 @@ int kvm_mips_host_tlb_inv_index(struct kvm_vcpu *vcpu, int index)
 
 	local_irq_save(flags);
 
-
 	old_entryhi = read_c0_entryhi();
 
 	write_c0_entryhi(UNIQUE_ENTRYHI(index));
@@ -546,7 +551,6 @@ void kvm_mips_flush_host_tlb(int skip_kseg0)
 	int entry = 0;
 	int maxentry = current_cpu_data.tlbsize;
 
-
 	local_irq_save(flags);
 
 	old_entryhi = read_c0_entryhi();
@@ -554,7 +558,6 @@ void kvm_mips_flush_host_tlb(int skip_kseg0)
 
 	/* Blast 'em all away. */
 	for (entry = 0; entry < maxentry; entry++) {
-
 		write_c0_index(entry);
 		mtc0_tlbw_hazard();
 
@@ -565,9 +568,8 @@ void kvm_mips_flush_host_tlb(int skip_kseg0)
 			entryhi = read_c0_entryhi();
 
 			/* Don't blow away guest kernel entries */
-			if (KVM_GUEST_KSEGX(entryhi) == KVM_GUEST_KSEG0) {
+			if (KVM_GUEST_KSEGX(entryhi) == KVM_GUEST_KSEG0)
 				continue;
-			}
 		}
 
 		/* Make sure all entries differ. */
@@ -591,17 +593,17 @@ void kvm_mips_flush_host_tlb(int skip_kseg0)
 
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL(kvm_mips_flush_host_tlb);
 
-void
-kvm_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu,
-			struct kvm_vcpu *vcpu)
+void kvm_get_new_mmu_context(struct mm_struct *mm, unsigned long cpu,
+			     struct kvm_vcpu *vcpu)
 {
 	unsigned long asid = asid_cache(cpu);
 
-	if (!((asid += ASID_INC) & ASID_MASK)) {
-		if (cpu_has_vtag_icache) {
+	asid += ASID_INC;
+	if (!(asid & ASID_MASK)) {
+		if (cpu_has_vtag_icache)
 			flush_icache_all();
-		}
 
 		kvm_local_flush_tlb_all();      /* start new asid cycle */
 
@@ -639,6 +641,7 @@ void kvm_local_flush_tlb_all(void)
 
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL(kvm_local_flush_tlb_all);
 
 /**
  * kvm_mips_migrate_count() - Migrate timer.
@@ -699,7 +702,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	}
 
 	if (!newasid) {
-		/* If we preempted while the guest was executing, then reload the pre-empted ASID */
+		/*
+		 * If we preempted while the guest was executing, then reload
+		 * the pre-empted ASID
+		 */
 		if (current->flags & PF_VCPU) {
 			write_c0_entryhi(vcpu->arch.
 					 preempt_entryhi & ASID_MASK);
@@ -708,9 +714,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	} else {
 		/* New ASIDs were allocated for the VM */
 
-		/* Were we in guest context? If so then the pre-empted ASID is no longer
-		 * valid, we need to set it to what it should be based on the mode of
-		 * the Guest (Kernel/User)
+		/*
+		 * Were we in guest context? If so then the pre-empted ASID is
+		 * no longer valid, we need to set it to what it should be based
+		 * on the mode of the Guest (Kernel/User)
 		 */
 		if (current->flags & PF_VCPU) {
 			if (KVM_GUEST_KERNEL_MODE(vcpu))
@@ -728,6 +735,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	local_irq_restore(flags);
 
 }
+EXPORT_SYMBOL(kvm_arch_vcpu_load);
 
 /* ASID can change if another task is scheduled during preemption */
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -739,7 +747,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 
 	cpu = smp_processor_id();
 
-
 	vcpu->arch.preempt_entryhi = read_c0_entryhi();
 	vcpu->arch.last_sched_cpu = cpu;
 
@@ -754,11 +761,12 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL(kvm_arch_vcpu_put);
 
 uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu)
 {
 	struct mips_coproc *cop0 = vcpu->arch.cop0;
-	unsigned long paddr, flags;
+	unsigned long paddr, flags, vpn2, asid;
 	uint32_t inst;
 	int index;
 
@@ -769,16 +777,12 @@ uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu)
 		if (index >= 0) {
 			inst = *(opc);
 		} else {
-			index =
-			    kvm_mips_guest_tlb_lookup(vcpu,
-						      ((unsigned long) opc & VPN2_MASK)
-						      |
-						      (kvm_read_c0_guest_entryhi
-						       (cop0) & ASID_MASK));
+			vpn2 = (unsigned long) opc & VPN2_MASK;
+			asid = kvm_read_c0_guest_entryhi(cop0) & ASID_MASK;
+			index = kvm_mips_guest_tlb_lookup(vcpu, vpn2 | asid);
 			if (index < 0) {
-				kvm_err
-				    ("%s: get_user_failed for %p, vcpu: %p, ASID: %#lx\n",
-				     __func__, opc, vcpu, read_c0_entryhi());
+				kvm_err("%s: get_user_failed for %p, vcpu: %p, ASID: %#lx\n",
+					__func__, opc, vcpu, read_c0_entryhi());
 				kvm_mips_dump_host_tlbs();
 				local_irq_restore(flags);
 				return KVM_INVALID_INST;
@@ -793,7 +797,7 @@ uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu)
 	} else if (KVM_GUEST_KSEGX(opc) == KVM_GUEST_KSEG0) {
 		paddr =
 		    kvm_mips_translate_guest_kseg0_to_hpa(vcpu,
-							 (unsigned long) opc);
+							  (unsigned long) opc);
 		inst = *(uint32_t *) CKSEG0ADDR(paddr);
 	} else {
 		kvm_err("%s: illegal address: %p\n", __func__, opc);
@@ -802,18 +806,4 @@ uint32_t kvm_get_inst(uint32_t *opc, struct kvm_vcpu *vcpu)
 
 	return inst;
 }
-
-EXPORT_SYMBOL(kvm_local_flush_tlb_all);
-EXPORT_SYMBOL(kvm_mips_handle_mapped_seg_tlb_fault);
-EXPORT_SYMBOL(kvm_mips_handle_commpage_tlb_fault);
-EXPORT_SYMBOL(kvm_mips_dump_host_tlbs);
-EXPORT_SYMBOL(kvm_mips_handle_kseg0_tlb_fault);
-EXPORT_SYMBOL(kvm_mips_host_tlb_lookup);
-EXPORT_SYMBOL(kvm_mips_flush_host_tlb);
-EXPORT_SYMBOL(kvm_mips_guest_tlb_lookup);
-EXPORT_SYMBOL(kvm_mips_host_tlb_inv);
-EXPORT_SYMBOL(kvm_mips_translate_guest_kseg0_to_hpa);
-EXPORT_SYMBOL(kvm_mips_dump_guest_tlbs);
 EXPORT_SYMBOL(kvm_get_inst);
-EXPORT_SYMBOL(kvm_arch_vcpu_load);
-EXPORT_SYMBOL(kvm_arch_vcpu_put);
diff --git a/arch/mips/kvm/trace.h b/arch/mips/kvm/trace.h
index bc9e0f406c0..c1388d40663 100644
--- a/arch/mips/kvm/trace.h
+++ b/arch/mips/kvm/trace.h
@@ -1,11 +1,11 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_KVM_H
@@ -17,9 +17,7 @@
 #define TRACE_INCLUDE_PATH .
 #define TRACE_INCLUDE_FILE trace
 
-/*
- * Tracepoints for VM eists
- */
+/* Tracepoints for VM eists */
 extern char *kvm_mips_exit_types_str[MAX_KVM_MIPS_EXIT_TYPES];
 
 TRACE_EVENT(kvm_exit,
diff --git a/arch/mips/kvm/kvm_trap_emul.c b/arch/mips/kvm/trap_emul.c
index 693f952b2fb..fd7257b70e6 100644
--- a/arch/mips/kvm/kvm_trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -1,13 +1,13 @@
 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* KVM/MIPS: Deliver/Emulate exceptions to the guest kernel
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * KVM/MIPS: Deliver/Emulate exceptions to the guest kernel
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -16,8 +16,8 @@
 
 #include <linux/kvm_host.h>
 
-#include "kvm_mips_opcode.h"
-#include "kvm_mips_int.h"
+#include "opcode.h"
+#include "interrupt.h"
 
 static gpa_t kvm_trap_emul_gva_to_gpa_cb(gva_t gva)
 {
@@ -27,7 +27,7 @@ static gpa_t kvm_trap_emul_gva_to_gpa_cb(gva_t gva)
 	if ((kseg == CKSEG0) || (kseg == CKSEG1))
 		gpa = CPHYSADDR(gva);
 	else {
-		printk("%s: cannot find GPA for GVA: %#lx\n", __func__, gva);
+		kvm_err("%s: cannot find GPA for GVA: %#lx\n", __func__, gva);
 		kvm_mips_dump_host_tlbs();
 		gpa = KVM_INVALID_ADDR;
 	}
@@ -37,7 +37,6 @@ static gpa_t kvm_trap_emul_gva_to_gpa_cb(gva_t gva)
 	return gpa;
 }
 
-
 static int kvm_trap_emul_handle_cop_unusable(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
@@ -46,9 +45,9 @@ static int kvm_trap_emul_handle_cop_unusable(struct kvm_vcpu *vcpu)
 	enum emulation_result er = EMULATE_DONE;
 	int ret = RESUME_GUEST;
 
-	if (((cause & CAUSEF_CE) >> CAUSEB_CE) == 1) {
+	if (((cause & CAUSEF_CE) >> CAUSEB_CE) == 1)
 		er = kvm_mips_emulate_fpu_exc(cause, opc, run, vcpu);
-	} else
+	else
 		er = kvm_mips_emulate_inst(cause, opc, run, vcpu);
 
 	switch (er) {
@@ -83,9 +82,8 @@ static int kvm_trap_emul_handle_tlb_mod(struct kvm_vcpu *vcpu)
 
 	if (KVM_GUEST_KSEGX(badvaddr) < KVM_GUEST_KSEG0
 	    || KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG23) {
-		kvm_debug
-		    ("USER/KSEG23 ADDR TLB MOD fault: cause %#lx, PC: %p, BadVaddr: %#lx\n",
-		     cause, opc, badvaddr);
+		kvm_debug("USER/KSEG23 ADDR TLB MOD fault: cause %#lx, PC: %p, BadVaddr: %#lx\n",
+			  cause, opc, badvaddr);
 		er = kvm_mips_handle_tlbmod(cause, opc, run, vcpu);
 
 		if (er == EMULATE_DONE)
@@ -95,20 +93,20 @@ static int kvm_trap_emul_handle_tlb_mod(struct kvm_vcpu *vcpu)
 			ret = RESUME_HOST;
 		}
 	} else if (KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG0) {
-		/* XXXKYMA: The guest kernel does not expect to get this fault when we are not
-		 * using HIGHMEM. Need to address this in a HIGHMEM kernel
+		/*
+		 * XXXKYMA: The guest kernel does not expect to get this fault
+		 * when we are not using HIGHMEM. Need to address this in a
+		 * HIGHMEM kernel
 		 */
-		printk
-		    ("TLB MOD fault not handled, cause %#lx, PC: %p, BadVaddr: %#lx\n",
-		     cause, opc, badvaddr);
+		kvm_err("TLB MOD fault not handled, cause %#lx, PC: %p, BadVaddr: %#lx\n",
+			cause, opc, badvaddr);
 		kvm_mips_dump_host_tlbs();
 		kvm_arch_vcpu_dump_regs(vcpu);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		ret = RESUME_HOST;
 	} else {
-		printk
-		    ("Illegal TLB Mod fault address , cause %#lx, PC: %p, BadVaddr: %#lx\n",
-		     cause, opc, badvaddr);
+		kvm_err("Illegal TLB Mod fault address , cause %#lx, PC: %p, BadVaddr: %#lx\n",
+			cause, opc, badvaddr);
 		kvm_mips_dump_host_tlbs();
 		kvm_arch_vcpu_dump_regs(vcpu);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -134,9 +132,8 @@ static int kvm_trap_emul_handle_tlb_st_miss(struct kvm_vcpu *vcpu)
 		}
 	} else if (KVM_GUEST_KSEGX(badvaddr) < KVM_GUEST_KSEG0
 		   || KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG23) {
-		kvm_debug
-		    ("USER ADDR TLB LD fault: cause %#lx, PC: %p, BadVaddr: %#lx\n",
-		     cause, opc, badvaddr);
+		kvm_debug("USER ADDR TLB LD fault: cause %#lx, PC: %p, BadVaddr: %#lx\n",
+			  cause, opc, badvaddr);
 		er = kvm_mips_handle_tlbmiss(cause, opc, run, vcpu);
 		if (er == EMULATE_DONE)
 			ret = RESUME_GUEST;
@@ -145,8 +142,9 @@ static int kvm_trap_emul_handle_tlb_st_miss(struct kvm_vcpu *vcpu)
 			ret = RESUME_HOST;
 		}
 	} else if (KVM_GUEST_KSEGX(badvaddr) == KVM_GUEST_KSEG0) {
-		/* All KSEG0 faults are handled by KVM, as the guest kernel does not
-		 * expect to ever get them
+		/*
+		 * All KSEG0 faults are handled by KVM, as the guest kernel does
+		 * not expect to ever get them
 		 */
 		if (kvm_mips_handle_kseg0_tlb_fault
 		    (vcpu->arch.host_cp0_badvaddr, vcpu) < 0) {
@@ -154,9 +152,8 @@ static int kvm_trap_emul_handle_tlb_st_miss(struct kvm_vcpu *vcpu)
 			ret = RESUME_HOST;
 		}
 	} else {
-		kvm_err
-		    ("Illegal TLB LD fault address , cause %#lx, PC: %p, BadVaddr: %#lx\n",
-		     cause, opc, badvaddr);
+		kvm_err("Illegal TLB LD fault address , cause %#lx, PC: %p, BadVaddr: %#lx\n",
+			cause, opc, badvaddr);
 		kvm_mips_dump_host_tlbs();
 		kvm_arch_vcpu_dump_regs(vcpu);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -185,11 +182,14 @@ static int kvm_trap_emul_handle_tlb_ld_miss(struct kvm_vcpu *vcpu)
 		kvm_debug("USER ADDR TLB ST fault: PC: %#lx, BadVaddr: %#lx\n",
 			  vcpu->arch.pc, badvaddr);
 
-		/* User Address (UA) fault, this could happen if
-		 * (1) TLB entry not present/valid in both Guest and shadow host TLBs, in this
-		 *     case we pass on the fault to the guest kernel and let it handle it.
-		 * (2) TLB entry is present in the Guest TLB but not in the shadow, in this
-		 *     case we inject the TLB from the Guest TLB into the shadow host TLB
+		/*
+		 * User Address (UA) fault, this could happen if
+		 * (1) TLB entry not present/valid in both Guest and shadow host
+		 *     TLBs, in this case we pass on the fault to the guest
+		 *     kernel and let it handle it.
+		 * (2) TLB entry is present in the Guest TLB but not in the
+		 *     shadow, in this case we inject the TLB from the Guest TLB
+		 *     into the shadow host TLB
 		 */
 
 		er = kvm_mips_handle_tlbmiss(cause, opc, run, vcpu);
@@ -206,9 +206,8 @@ static int kvm_trap_emul_handle_tlb_ld_miss(struct kvm_vcpu *vcpu)
 			ret = RESUME_HOST;
 		}
 	} else {
-		printk
-		    ("Illegal TLB ST fault address , cause %#lx, PC: %p, BadVaddr: %#lx\n",
-		     cause, opc, badvaddr);
+		kvm_err("Illegal TLB ST fault address , cause %#lx, PC: %p, BadVaddr: %#lx\n",
+			cause, opc, badvaddr);
 		kvm_mips_dump_host_tlbs();
 		kvm_arch_vcpu_dump_regs(vcpu);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -231,7 +230,7 @@ static int kvm_trap_emul_handle_addr_err_st(struct kvm_vcpu *vcpu)
 		kvm_debug("Emulate Store to MMIO space\n");
 		er = kvm_mips_emulate_inst(cause, opc, run, vcpu);
 		if (er == EMULATE_FAIL) {
-			printk("Emulate Store to MMIO space failed\n");
+			kvm_err("Emulate Store to MMIO space failed\n");
 			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 			ret = RESUME_HOST;
 		} else {
@@ -239,9 +238,8 @@ static int kvm_trap_emul_handle_addr_err_st(struct kvm_vcpu *vcpu)
 			ret = RESUME_HOST;
 		}
 	} else {
-		printk
-		    ("Address Error (STORE): cause %#lx, PC: %p, BadVaddr: %#lx\n",
-		     cause, opc, badvaddr);
+		kvm_err("Address Error (STORE): cause %#lx, PC: %p, BadVaddr: %#lx\n",
+			cause, opc, badvaddr);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		ret = RESUME_HOST;
 	}
@@ -261,7 +259,7 @@ static int kvm_trap_emul_handle_addr_err_ld(struct kvm_vcpu *vcpu)
 		kvm_debug("Emulate Load from MMIO space @ %#lx\n", badvaddr);
 		er = kvm_mips_emulate_inst(cause, opc, run, vcpu);
 		if (er == EMULATE_FAIL) {
-			printk("Emulate Load from MMIO space failed\n");
+			kvm_err("Emulate Load from MMIO space failed\n");
 			run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 			ret = RESUME_HOST;
 		} else {
@@ -269,9 +267,8 @@ static int kvm_trap_emul_handle_addr_err_ld(struct kvm_vcpu *vcpu)
 			ret = RESUME_HOST;
 		}
 	} else {
-		printk
-		    ("Address Error (LOAD): cause %#lx, PC: %p, BadVaddr: %#lx\n",
-		     cause, opc, badvaddr);
+		kvm_err("Address Error (LOAD): cause %#lx, PC: %p, BadVaddr: %#lx\n",
+			cause, opc, badvaddr);
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		ret = RESUME_HOST;
 		er = EMULATE_FAIL;
@@ -349,9 +346,9 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu)
 	uint32_t config1;
 	int vcpu_id = vcpu->vcpu_id;
 
-	/* Arch specific stuff, set up config registers properly so that the
-	 * guest will come up as expected, for now we simulate a
-	 * MIPS 24kc
+	/*
+	 * Arch specific stuff, set up config registers properly so that the
+	 * guest will come up as expected, for now we simulate a MIPS 24kc
 	 */
 	kvm_write_c0_guest_prid(cop0, 0x00019300);
 	kvm_write_c0_guest_config(cop0,
@@ -373,14 +370,15 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvm_write_c0_guest_config2(cop0, MIPS_CONFIG2);
 	/* MIPS_CONFIG2 | (read_c0_config2() & 0xfff) */
-	kvm_write_c0_guest_config3(cop0,
-				   MIPS_CONFIG3 | (0 << CP0C3_VInt) | (1 <<
-								       CP0C3_ULRI));
+	kvm_write_c0_guest_config3(cop0, MIPS_CONFIG3 | (0 << CP0C3_VInt) |
+					 (1 << CP0C3_ULRI));
 
 	/* Set Wait IE/IXMT Ignore in Config7, IAR, AR */
 	kvm_write_c0_guest_config7(cop0, (MIPS_CONF7_WII) | (1 << 10));
 
-	/* Setup IntCtl defaults, compatibilty mode for timer interrupts (HW5) */
+	/*
+	 * Setup IntCtl defaults, compatibilty mode for timer interrupts (HW5)
+	 */
 	kvm_write_c0_guest_intctl(cop0, 0xFC000000);
 
 	/* Put in vcpu id as CPUNum into Ebase Reg to handle SMP Guests */
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index 85685e1cdb8..030568a70ac 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -61,7 +61,7 @@
 /* we have a cascade of 8 irqs */
 #define MIPS_CPU_IRQ_CASCADE		8
 
-#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
+#ifdef CONFIG_MIPS_MT_SMP
 int gic_present;
 #endif
 
@@ -440,7 +440,7 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent)
 	arch_init_ipiirq(MIPS_CPU_IRQ_BASE + MIPS_CPU_IPI_CALL_IRQ, &irq_call);
 #endif
 
-#if !defined(CONFIG_MIPS_MT_SMP) && !defined(CONFIG_MIPS_MT_SMTC)
+#ifndef CONFIG_MIPS_MT_SMP
 	set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 |
 		IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
 #else
diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c
index 705cfb7c1a7..21d27c6819a 100644
--- a/arch/mips/lib/delay.c
+++ b/arch/mips/lib/delay.c
@@ -11,7 +11,9 @@
 #include <linux/module.h>
 #include <linux/param.h>
 #include <linux/smp.h>
+#include <linux/stringify.h>
 
+#include <asm/asm.h>
 #include <asm/compiler.h>
 #include <asm/war.h>
 
@@ -27,11 +29,7 @@ void __delay(unsigned long loops)
 	"	.set	noreorder				\n"
 	"	.align	3					\n"
 	"1:	bnez	%0, 1b					\n"
-#if BITS_PER_LONG == 32
-	"	subu	%0, %1					\n"
-#else
-	"	dsubu	%0, %1					\n"
-#endif
+	"	 " __stringify(LONG_SUBU) "	%0, %1		\n"
 	"	.set	reorder					\n"
 	: "=r" (loops)
 	: GCC_DADDI_IMM_ASM() (1), "0" (loops));
diff --git a/arch/mips/lib/mips-atomic.c b/arch/mips/lib/mips-atomic.c
index 6807f7172ea..57bcdaf1f1c 100644
--- a/arch/mips/lib/mips-atomic.c
+++ b/arch/mips/lib/mips-atomic.c
@@ -15,7 +15,7 @@
 #include <linux/export.h>
 #include <linux/stringify.h>
 
-#if !defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT_SMTC)
+#ifndef CONFIG_CPU_MIPSR2
 
 /*
  * For cli() we have to insert nops to make sure that the new value
@@ -42,12 +42,7 @@ notrace void arch_local_irq_disable(void)
 	__asm__ __volatile__(
 	"	.set	push						\n"
 	"	.set	noat						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	$1, $2, 1					\n"
-	"	ori	$1, 0x400					\n"
-	"	.set	noreorder					\n"
-	"	mtc0	$1, $2, 1					\n"
-#elif defined(CONFIG_CPU_MIPSR2)
+#if   defined(CONFIG_CPU_MIPSR2)
 	/* see irqflags.h for inline function */
 #else
 	"	mfc0	$1,$12						\n"
@@ -77,13 +72,7 @@ notrace unsigned long arch_local_irq_save(void)
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	%[flags], $2, 1				\n"
-	"	ori	$1, %[flags], 0x400				\n"
-	"	.set	noreorder					\n"
-	"	mtc0	$1, $2, 1					\n"
-	"	andi	%[flags], %[flags], 0x400			\n"
-#elif defined(CONFIG_CPU_MIPSR2)
+#if   defined(CONFIG_CPU_MIPSR2)
 	/* see irqflags.h for inline function */
 #else
 	"	mfc0	%[flags], $12					\n"
@@ -108,29 +97,13 @@ notrace void arch_local_irq_restore(unsigned long flags)
 {
 	unsigned long __tmp1;
 
-#ifdef CONFIG_MIPS_MT_SMTC
-	/*
-	 * SMTC kernel needs to do a software replay of queued
-	 * IPIs, at the cost of branch and call overhead on each
-	 * local_irq_restore()
-	 */
-	if (unlikely(!(flags & 0x0400)))
-		smtc_ipi_replay();
-#endif
 	preempt_disable();
 
 	__asm__ __volatile__(
 	"	.set	push						\n"
 	"	.set	noreorder					\n"
 	"	.set	noat						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	$1, $2, 1					\n"
-	"	andi	%[flags], 0x400					\n"
-	"	ori	$1, 0x400					\n"
-	"	xori	$1, 0x400					\n"
-	"	or	%[flags], $1					\n"
-	"	mtc0	%[flags], $2, 1					\n"
-#elif defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU)
+#if   defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU)
 	/* see irqflags.h for inline function */
 #elif defined(CONFIG_CPU_MIPSR2)
 	/* see irqflags.h for inline function */
@@ -163,14 +136,7 @@ notrace void __arch_local_irq_restore(unsigned long flags)
 	"	.set	push						\n"
 	"	.set	noreorder					\n"
 	"	.set	noat						\n"
-#ifdef CONFIG_MIPS_MT_SMTC
-	"	mfc0	$1, $2, 1					\n"
-	"	andi	%[flags], 0x400					\n"
-	"	ori	$1, 0x400					\n"
-	"	xori	$1, 0x400					\n"
-	"	or	%[flags], $1					\n"
-	"	mtc0	%[flags], $2, 1					\n"
-#elif defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU)
+#if   defined(CONFIG_CPU_MIPSR2) && defined(CONFIG_IRQ_CPU)
 	/* see irqflags.h for inline function */
 #elif defined(CONFIG_CPU_MIPSR2)
 	/* see irqflags.h for inline function */
@@ -192,4 +158,4 @@ notrace void __arch_local_irq_restore(unsigned long flags)
 }
 EXPORT_SYMBOL(__arch_local_irq_restore);
 
-#endif /* !defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_MIPS_MT_SMTC) */
+#endif /* !CONFIG_CPU_MIPSR2 */
diff --git a/arch/mips/loongson/Kconfig b/arch/mips/loongson/Kconfig
index 603d79a95f4..e6a86ccc442 100644
--- a/arch/mips/loongson/Kconfig
+++ b/arch/mips/loongson/Kconfig
@@ -95,10 +95,11 @@ config CS5536
 
 config CS5536_MFGPT
 	bool "CS5536 MFGPT Timer"
-	depends on CS5536
+	depends on CS5536 && !HIGH_RES_TIMERS
 	select MIPS_EXTERNAL_TIMER
 	help
-	  This option enables the mfgpt0 timer of AMD CS5536.
+	  This option enables the mfgpt0 timer of AMD CS5536. With this timer
+	  switched on you can not use high resolution timers.
 
 	  If you want to enable the Loongson2 CPUFreq Driver, Please enable
 	  this option at first, otherwise, You will get wrong system time.
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index c665fe16d4c..1e8894020ea 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -279,13 +279,6 @@ static void loongson3_boot_secondary(int cpu, struct task_struct *idle)
 	loongson3_ipi_write64(startargs[0], (void *)(ipi_mailbox_buf[cpu]+0x0));
 }
 
-/*
- * Final cleanup after all secondaries booted
- */
-static void __init loongson3_cpus_done(void)
-{
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 
 static int loongson3_cpu_disable(void)
@@ -432,7 +425,6 @@ struct plat_smp_ops loongson3_smp_ops = {
 	.send_ipi_mask = loongson3_send_ipi_mask,
 	.init_secondary = loongson3_init_secondary,
 	.smp_finish = loongson3_smp_finish,
-	.cpus_done = loongson3_cpus_done,
 	.boot_secondary = loongson3_boot_secondary,
 	.smp_setup = loongson3_smp_setup,
 	.prepare_cpus = loongson3_prepare_cpus,
diff --git a/arch/mips/loongson1/Kconfig b/arch/mips/loongson1/Kconfig
index fbf75f63579..e23c25d0996 100644
--- a/arch/mips/loongson1/Kconfig
+++ b/arch/mips/loongson1/Kconfig
@@ -14,6 +14,7 @@ config LOONGSON1_LS1B
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
+	select SYS_SUPPORTS_MIPS16
 	select SYS_HAS_EARLY_PRINTK
 	select COMMON_CLK
 
diff --git a/arch/mips/math-emu/Makefile b/arch/mips/math-emu/Makefile
index 121a848a359..619cfc1a244 100644
--- a/arch/mips/math-emu/Makefile
+++ b/arch/mips/math-emu/Makefile
@@ -2,10 +2,12 @@
 # Makefile for the Linux/MIPS kernel FPU emulation.
 #
 
-obj-y	:= cp1emu.o ieee754m.o ieee754d.o ieee754dp.o ieee754sp.o ieee754.o \
-	   ieee754xcpt.o dp_frexp.o dp_modf.o dp_div.o dp_mul.o dp_sub.o \
-	   dp_add.o dp_fsp.o dp_cmp.o dp_logb.o dp_scalb.o dp_simple.o \
-	   dp_tint.o dp_fint.o dp_tlong.o dp_flong.o sp_frexp.o sp_modf.o \
-	   sp_div.o sp_mul.o sp_sub.o sp_add.o sp_fdp.o sp_cmp.o sp_logb.o \
-	   sp_scalb.o sp_simple.o sp_tint.o sp_fint.o sp_tlong.o sp_flong.o \
-	   dp_sqrt.o sp_sqrt.o kernel_linkage.o dsemul.o
+obj-y	+= cp1emu.o ieee754dp.o ieee754sp.o ieee754.o dp_div.o dp_mul.o \
+	   dp_sub.o dp_add.o dp_fsp.o dp_cmp.o dp_simple.o dp_tint.o \
+	   dp_fint.o dp_tlong.o dp_flong.o sp_div.o sp_mul.o sp_sub.o \
+	   sp_add.o sp_fdp.o sp_cmp.o sp_simple.o sp_tint.o sp_fint.o \
+	   sp_tlong.o sp_flong.o dsemul.o
+
+lib-y	+= ieee754d.o dp_sqrt.o sp_sqrt.o
+
+obj-$(CONFIG_DEBUG_FS) += me-debugfs.o
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 7b3c9acae68..736c17a226e 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1,5 +1,5 @@
 /*
- * cp1emu.c: a MIPS coprocessor 1 (fpu) instruction emulator
+ * cp1emu.c: a MIPS coprocessor 1 (FPU) instruction emulator
  *
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
@@ -18,61 +18,46 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  *
  * A complete emulator for MIPS coprocessor 1 instructions.  This is
  * required for #float(switch) or #float(trap), where it catches all
  * COP1 instructions via the "CoProcessor Unusable" exception.
  *
  * More surprisingly it is also required for #float(ieee), to help out
- * the hardware fpu at the boundaries of the IEEE-754 representation
+ * the hardware FPU at the boundaries of the IEEE-754 representation
  * (denormalised values, infinities, underflow, etc).  It is made
  * quite nasty because emulation of some non-COP1 instructions is
  * required, e.g. in branch delay slots.
  *
- * Note if you know that you won't have an fpu, then you'll get much
+ * Note if you know that you won't have an FPU, then you'll get much
  * better performance by compiling with -msoft-float!
  */
 #include <linux/sched.h>
-#include <linux/module.h>
 #include <linux/debugfs.h>
+#include <linux/kconfig.h>
+#include <linux/percpu-defs.h>
 #include <linux/perf_event.h>
 
+#include <asm/branch.h>
 #include <asm/inst.h>
-#include <asm/bootinfo.h>
-#include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/signal.h>
-#include <asm/mipsregs.h>
+#include <asm/uaccess.h>
+
+#include <asm/processor.h>
 #include <asm/fpu_emulator.h>
 #include <asm/fpu.h>
-#include <asm/uaccess.h>
-#include <asm/branch.h>
 
 #include "ieee754.h"
 
-/* Strap kernel emulator for full MIPS IV emulation */
-
-#ifdef __mips
-#undef __mips
-#endif
-#define __mips 4
-
 /* Function which emulates a floating point instruction. */
 
 static int fpu_emu(struct pt_regs *, struct mips_fpu_struct *,
 	mips_instruction);
 
-#if __mips >= 4 && __mips != 32
 static int fpux_emu(struct pt_regs *,
 	struct mips_fpu_struct *, mips_instruction, void *__user *);
-#endif
-
-/* Further private data for which no space exists in mips_fpu_struct */
-
-#ifdef CONFIG_DEBUG_FS
-DEFINE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
-#endif
 
 /* Control registers */
 
@@ -82,27 +67,6 @@ DEFINE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
 /* Determine rounding mode from the RM bits of the FCSR */
 #define modeindex(v) ((v) & FPU_CSR_RM)
 
-/* microMIPS bitfields */
-#define MM_POOL32A_MINOR_MASK	0x3f
-#define MM_POOL32A_MINOR_SHIFT	0x6
-#define MM_MIPS32_COND_FC	0x30
-
-/* Convert Mips rounding mode (0..3) to IEEE library modes. */
-static const unsigned char ieee_rm[4] = {
-	[FPU_CSR_RN] = IEEE754_RN,
-	[FPU_CSR_RZ] = IEEE754_RZ,
-	[FPU_CSR_RU] = IEEE754_RU,
-	[FPU_CSR_RD] = IEEE754_RD,
-};
-/* Convert IEEE library modes to Mips rounding mode (0..3). */
-static const unsigned char mips_rm[4] = {
-	[IEEE754_RN] = FPU_CSR_RN,
-	[IEEE754_RZ] = FPU_CSR_RZ,
-	[IEEE754_RD] = FPU_CSR_RD,
-	[IEEE754_RU] = FPU_CSR_RU,
-};
-
-#if __mips >= 4
 /* convert condition code register number to csr bit */
 static const unsigned int fpucondbit[8] = {
 	FPU_CSR_COND0,
@@ -114,10 +78,6 @@ static const unsigned int fpucondbit[8] = {
 	FPU_CSR_COND6,
 	FPU_CSR_COND7
 };
-#endif
-
-/* (microMIPS) Convert 16-bit register encoding to 32-bit register encoding. */
-static const unsigned int reg16to32map[8] = {16, 17, 2, 3, 4, 5, 6, 7};
 
 /* (microMIPS) Convert certain microMIPS instructions to MIPS32 format. */
 static const int sd_format[] = {16, 17, 0, 0, 0, 0, 0, 0};
@@ -466,199 +426,6 @@ static int microMIPS32_to_MIPS32(union mips_instruction *insn_ptr)
 	return 0;
 }
 
-int mm_isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
-		     unsigned long *contpc)
-{
-	union mips_instruction insn = (union mips_instruction)dec_insn.insn;
-	int bc_false = 0;
-	unsigned int fcr31;
-	unsigned int bit;
-
-	if (!cpu_has_mmips)
-		return 0;
-
-	switch (insn.mm_i_format.opcode) {
-	case mm_pool32a_op:
-		if ((insn.mm_i_format.simmediate & MM_POOL32A_MINOR_MASK) ==
-		    mm_pool32axf_op) {
-			switch (insn.mm_i_format.simmediate >>
-				MM_POOL32A_MINOR_SHIFT) {
-			case mm_jalr_op:
-			case mm_jalrhb_op:
-			case mm_jalrs_op:
-			case mm_jalrshb_op:
-				if (insn.mm_i_format.rt != 0)	/* Not mm_jr */
-					regs->regs[insn.mm_i_format.rt] =
-						regs->cp0_epc +
-						dec_insn.pc_inc +
-						dec_insn.next_pc_inc;
-				*contpc = regs->regs[insn.mm_i_format.rs];
-				return 1;
-			}
-		}
-		break;
-	case mm_pool32i_op:
-		switch (insn.mm_i_format.rt) {
-		case mm_bltzals_op:
-		case mm_bltzal_op:
-			regs->regs[31] = regs->cp0_epc +
-				dec_insn.pc_inc +
-				dec_insn.next_pc_inc;
-			/* Fall through */
-		case mm_bltz_op:
-			if ((long)regs->regs[insn.mm_i_format.rs] < 0)
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc +
-					(insn.mm_i_format.simmediate << 1);
-			else
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc +
-					dec_insn.next_pc_inc;
-			return 1;
-		case mm_bgezals_op:
-		case mm_bgezal_op:
-			regs->regs[31] = regs->cp0_epc +
-					dec_insn.pc_inc +
-					dec_insn.next_pc_inc;
-			/* Fall through */
-		case mm_bgez_op:
-			if ((long)regs->regs[insn.mm_i_format.rs] >= 0)
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc +
-					(insn.mm_i_format.simmediate << 1);
-			else
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc +
-					dec_insn.next_pc_inc;
-			return 1;
-		case mm_blez_op:
-			if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc +
-					(insn.mm_i_format.simmediate << 1);
-			else
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc +
-					dec_insn.next_pc_inc;
-			return 1;
-		case mm_bgtz_op:
-			if ((long)regs->regs[insn.mm_i_format.rs] <= 0)
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc +
-					(insn.mm_i_format.simmediate << 1);
-			else
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc +
-					dec_insn.next_pc_inc;
-			return 1;
-		case mm_bc2f_op:
-		case mm_bc1f_op:
-			bc_false = 1;
-			/* Fall through */
-		case mm_bc2t_op:
-		case mm_bc1t_op:
-			preempt_disable();
-			if (is_fpu_owner())
-				asm volatile("cfc1\t%0,$31" : "=r" (fcr31));
-			else
-				fcr31 = current->thread.fpu.fcr31;
-			preempt_enable();
-
-			if (bc_false)
-				fcr31 = ~fcr31;
-
-			bit = (insn.mm_i_format.rs >> 2);
-			bit += (bit != 0);
-			bit += 23;
-			if (fcr31 & (1 << bit))
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc +
-					(insn.mm_i_format.simmediate << 1);
-			else
-				*contpc = regs->cp0_epc +
-					dec_insn.pc_inc + dec_insn.next_pc_inc;
-			return 1;
-		}
-		break;
-	case mm_pool16c_op:
-		switch (insn.mm_i_format.rt) {
-		case mm_jalr16_op:
-		case mm_jalrs16_op:
-			regs->regs[31] = regs->cp0_epc +
-				dec_insn.pc_inc + dec_insn.next_pc_inc;
-			/* Fall through */
-		case mm_jr16_op:
-			*contpc = regs->regs[insn.mm_i_format.rs];
-			return 1;
-		}
-		break;
-	case mm_beqz16_op:
-		if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] == 0)
-			*contpc = regs->cp0_epc +
-				dec_insn.pc_inc +
-				(insn.mm_b1_format.simmediate << 1);
-		else
-			*contpc = regs->cp0_epc +
-				dec_insn.pc_inc + dec_insn.next_pc_inc;
-		return 1;
-	case mm_bnez16_op:
-		if ((long)regs->regs[reg16to32map[insn.mm_b1_format.rs]] != 0)
-			*contpc = regs->cp0_epc +
-				dec_insn.pc_inc +
-				(insn.mm_b1_format.simmediate << 1);
-		else
-			*contpc = regs->cp0_epc +
-				dec_insn.pc_inc + dec_insn.next_pc_inc;
-		return 1;
-	case mm_b16_op:
-		*contpc = regs->cp0_epc + dec_insn.pc_inc +
-			 (insn.mm_b0_format.simmediate << 1);
-		return 1;
-	case mm_beq32_op:
-		if (regs->regs[insn.mm_i_format.rs] ==
-		    regs->regs[insn.mm_i_format.rt])
-			*contpc = regs->cp0_epc +
-				dec_insn.pc_inc +
-				(insn.mm_i_format.simmediate << 1);
-		else
-			*contpc = regs->cp0_epc +
-				dec_insn.pc_inc +
-				dec_insn.next_pc_inc;
-		return 1;
-	case mm_bne32_op:
-		if (regs->regs[insn.mm_i_format.rs] !=
-		    regs->regs[insn.mm_i_format.rt])
-			*contpc = regs->cp0_epc +
-				dec_insn.pc_inc +
-				(insn.mm_i_format.simmediate << 1);
-		else
-			*contpc = regs->cp0_epc +
-				dec_insn.pc_inc + dec_insn.next_pc_inc;
-		return 1;
-	case mm_jalx32_op:
-		regs->regs[31] = regs->cp0_epc +
-			dec_insn.pc_inc + dec_insn.next_pc_inc;
-		*contpc = regs->cp0_epc + dec_insn.pc_inc;
-		*contpc >>= 28;
-		*contpc <<= 28;
-		*contpc |= (insn.j_format.target << 2);
-		return 1;
-	case mm_jals32_op:
-	case mm_jal32_op:
-		regs->regs[31] = regs->cp0_epc +
-			dec_insn.pc_inc + dec_insn.next_pc_inc;
-		/* Fall through */
-	case mm_j32_op:
-		*contpc = regs->cp0_epc + dec_insn.pc_inc;
-		*contpc >>= 27;
-		*contpc <<= 27;
-		*contpc |= (insn.j_format.target << 1);
-		set_isa16_mode(*contpc);
-		return 1;
-	}
-	return 0;
-}
-
 /*
  * Redundant with logic already in kernel/branch.c,
  * embedded in compute_return_epc.  At some point,
@@ -817,7 +584,11 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
 		if (insn.i_format.rs == bc_op) {
 			preempt_disable();
 			if (is_fpu_owner())
-				asm volatile("cfc1\t%0,$31" : "=r" (fcr31));
+				asm volatile(
+					".set push\n"
+					"\t.set mips1\n"
+					"\tcfc1\t%0,$31\n"
+					"\t.set pop" : "=r" (fcr31));
 			else
 				fcr31 = current->thread.fpu.fcr31;
 			preempt_enable();
@@ -867,23 +638,25 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn,
  */
 static inline int cop1_64bit(struct pt_regs *xcp)
 {
-#if defined(CONFIG_64BIT) && !defined(CONFIG_MIPS32_O32)
-	return 1;
-#elif defined(CONFIG_32BIT) && !defined(CONFIG_MIPS_O32_FP64_SUPPORT)
-	return 0;
-#else
+	if (config_enabled(CONFIG_64BIT) && !config_enabled(CONFIG_MIPS32_O32))
+		return 1;
+	else if (config_enabled(CONFIG_32BIT) &&
+		 !config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT))
+		return 0;
+
 	return !test_thread_flag(TIF_32BIT_FPREGS);
-#endif
 }
 
-#define SIFROMREG(si, x) do {						\
+#define SIFROMREG(si, x)						\
+do {									\
 	if (cop1_64bit(xcp))						\
 		(si) = get_fpr32(&ctx->fpr[x], 0);			\
 	else								\
 		(si) = get_fpr32(&ctx->fpr[(x) & ~1], (x) & 1);		\
 } while (0)
 
-#define SITOREG(si, x) do {						\
+#define SITOREG(si, x)							\
+do {									\
 	if (cop1_64bit(xcp)) {						\
 		unsigned i;						\
 		set_fpr32(&ctx->fpr[x], 0, si);				\
@@ -896,17 +669,19 @@ static inline int cop1_64bit(struct pt_regs *xcp)
 
 #define SIFROMHREG(si, x)	((si) = get_fpr32(&ctx->fpr[x], 1))
 
-#define SITOHREG(si, x) do {						\
+#define SITOHREG(si, x)							\
+do {									\
 	unsigned i;							\
 	set_fpr32(&ctx->fpr[x], 1, si);					\
 	for (i = 2; i < ARRAY_SIZE(ctx->fpr[x].val32); i++)		\
 		set_fpr32(&ctx->fpr[x], i, 0);				\
 } while (0)
 
-#define DIFROMREG(di, x) \
+#define DIFROMREG(di, x)						\
 	((di) = get_fpr64(&ctx->fpr[(x) & ~(cop1_64bit(xcp) == 0)], 0))
 
-#define DITOREG(di, x) do {						\
+#define DITOREG(di, x)							\
+do {									\
 	unsigned fpr, i;						\
 	fpr = (x) & ~(cop1_64bit(xcp) == 0);				\
 	set_fpr64(&ctx->fpr[fpr], 0, di);				\
@@ -927,23 +702,36 @@ static inline int cop1_64bit(struct pt_regs *xcp)
 static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 		struct mm_decoded_insn dec_insn, void *__user *fault_addr)
 {
-	mips_instruction ir;
 	unsigned long contpc = xcp->cp0_epc + dec_insn.pc_inc;
-	unsigned int cond;
-	int pc_inc;
+	unsigned int cond, cbit;
+	mips_instruction ir;
+	int likely, pc_inc;
+	u32 __user *wva;
+	u64 __user *dva;
+	u32 value;
+	u32 wval;
+	u64 dval;
+	int sig;
+
+	/*
+	 * These are giving gcc a gentle hint about what to expect in
+	 * dec_inst in order to do better optimization.
+	 */
+	if (!cpu_has_mmips && dec_insn.micro_mips_mode)
+		unreachable();
 
 	/* XXX NEC Vr54xx bug workaround */
-	if (xcp->cp0_cause & CAUSEF_BD) {
+	if (delay_slot(xcp)) {
 		if (dec_insn.micro_mips_mode) {
 			if (!mm_isBranchInstr(xcp, dec_insn, &contpc))
-				xcp->cp0_cause &= ~CAUSEF_BD;
+				clear_delay_slot(xcp);
 		} else {
 			if (!isBranchInstr(xcp, dec_insn, &contpc))
-				xcp->cp0_cause &= ~CAUSEF_BD;
+				clear_delay_slot(xcp);
 		}
 	}
 
-	if (xcp->cp0_cause & CAUSEF_BD) {
+	if (delay_slot(xcp)) {
 		/*
 		 * The instruction to be emulated is in a branch delay slot
 		 * which means that we have to	emulate the branch instruction
@@ -985,96 +773,85 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			return SIGILL;
 	}
 
-      emul:
+emul:
 	perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, xcp, 0);
 	MIPS_FPU_EMU_INC_STATS(emulated);
 	switch (MIPSInst_OPCODE(ir)) {
-	case ldc1_op:{
-		u64 __user *va = (u64 __user *) (xcp->regs[MIPSInst_RS(ir)] +
-			MIPSInst_SIMM(ir));
-		u64 val;
-
+	case ldc1_op:
+		dva = (u64 __user *) (xcp->regs[MIPSInst_RS(ir)] +
+				     MIPSInst_SIMM(ir));
 		MIPS_FPU_EMU_INC_STATS(loads);
 
-		if (!access_ok(VERIFY_READ, va, sizeof(u64))) {
+		if (!access_ok(VERIFY_READ, dva, sizeof(u64))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
-			*fault_addr = va;
+			*fault_addr = dva;
 			return SIGBUS;
 		}
-		if (__get_user(val, va)) {
+		if (__get_user(dval, dva)) {
 			MIPS_FPU_EMU_INC_STATS(errors);
-			*fault_addr = va;
+			*fault_addr = dva;
 			return SIGSEGV;
 		}
-		DITOREG(val, MIPSInst_RT(ir));
+		DITOREG(dval, MIPSInst_RT(ir));
 		break;
-	}
-
-	case sdc1_op:{
-		u64 __user *va = (u64 __user *) (xcp->regs[MIPSInst_RS(ir)] +
-			MIPSInst_SIMM(ir));
-		u64 val;
 
+	case sdc1_op:
+		dva = (u64 __user *) (xcp->regs[MIPSInst_RS(ir)] +
+				      MIPSInst_SIMM(ir));
 		MIPS_FPU_EMU_INC_STATS(stores);
-		DIFROMREG(val, MIPSInst_RT(ir));
-		if (!access_ok(VERIFY_WRITE, va, sizeof(u64))) {
+		DIFROMREG(dval, MIPSInst_RT(ir));
+		if (!access_ok(VERIFY_WRITE, dva, sizeof(u64))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
-			*fault_addr = va;
+			*fault_addr = dva;
 			return SIGBUS;
 		}
-		if (__put_user(val, va)) {
+		if (__put_user(dval, dva)) {
 			MIPS_FPU_EMU_INC_STATS(errors);
-			*fault_addr = va;
+			*fault_addr = dva;
 			return SIGSEGV;
 		}
 		break;
-	}
-
-	case lwc1_op:{
-		u32 __user *va = (u32 __user *) (xcp->regs[MIPSInst_RS(ir)] +
-			MIPSInst_SIMM(ir));
-		u32 val;
 
+	case lwc1_op:
+		wva = (u32 __user *) (xcp->regs[MIPSInst_RS(ir)] +
+				      MIPSInst_SIMM(ir));
 		MIPS_FPU_EMU_INC_STATS(loads);
-		if (!access_ok(VERIFY_READ, va, sizeof(u32))) {
+		if (!access_ok(VERIFY_READ, wva, sizeof(u32))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
-			*fault_addr = va;
+			*fault_addr = wva;
 			return SIGBUS;
 		}
-		if (__get_user(val, va)) {
+		if (__get_user(wval, wva)) {
 			MIPS_FPU_EMU_INC_STATS(errors);
-			*fault_addr = va;
+			*fault_addr = wva;
 			return SIGSEGV;
 		}
-		SITOREG(val, MIPSInst_RT(ir));
+		SITOREG(wval, MIPSInst_RT(ir));
 		break;
-	}
-
-	case swc1_op:{
-		u32 __user *va = (u32 __user *) (xcp->regs[MIPSInst_RS(ir)] +
-			MIPSInst_SIMM(ir));
-		u32 val;
 
+	case swc1_op:
+		wva = (u32 __user *) (xcp->regs[MIPSInst_RS(ir)] +
+				      MIPSInst_SIMM(ir));
 		MIPS_FPU_EMU_INC_STATS(stores);
-		SIFROMREG(val, MIPSInst_RT(ir));
-		if (!access_ok(VERIFY_WRITE, va, sizeof(u32))) {
+		SIFROMREG(wval, MIPSInst_RT(ir));
+		if (!access_ok(VERIFY_WRITE, wva, sizeof(u32))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
-			*fault_addr = va;
+			*fault_addr = wva;
 			return SIGBUS;
 		}
-		if (__put_user(val, va)) {
+		if (__put_user(wval, wva)) {
 			MIPS_FPU_EMU_INC_STATS(errors);
-			*fault_addr = va;
+			*fault_addr = wva;
 			return SIGSEGV;
 		}
 		break;
-	}
 
 	case cop1_op:
 		switch (MIPSInst_RS(ir)) {
-
-#if defined(__mips64)
 		case dmfc_op:
+			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+				return SIGILL;
+
 			/* copregister fs -> gpr[rt] */
 			if (MIPSInst_RT(ir) != 0) {
 				DIFROMREG(xcp->regs[MIPSInst_RT(ir)],
@@ -1083,10 +860,12 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			break;
 
 		case dmtc_op:
+			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+				return SIGILL;
+
 			/* copregister fs <- rt */
 			DITOREG(xcp->regs[MIPSInst_RT(ir)], MIPSInst_RD(ir));
 			break;
-#endif
 
 		case mfhc_op:
 			if (!cpu_has_mips_r2)
@@ -1120,19 +899,14 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SITOREG(xcp->regs[MIPSInst_RT(ir)], MIPSInst_RD(ir));
 			break;
 
-		case cfc_op:{
+		case cfc_op:
 			/* cop control register rd -> gpr[rt] */
-			u32 value;
-
 			if (MIPSInst_RD(ir) == FPCREG_CSR) {
 				value = ctx->fcr31;
-				value = (value & ~FPU_CSR_RM) |
-					mips_rm[modeindex(value)];
-#ifdef CSRTRACE
-				printk("%p gpr[%d]<-csr=%08x\n",
-					(void *) (xcp->cp0_epc),
-					MIPSInst_RT(ir), value);
-#endif
+				value = (value & ~FPU_CSR_RM) | modeindex(value);
+				pr_debug("%p gpr[%d]<-csr=%08x\n",
+					 (void *) (xcp->cp0_epc),
+					 MIPSInst_RT(ir), value);
 			}
 			else if (MIPSInst_RD(ir) == FPCREG_RID)
 				value = 0;
@@ -1141,12 +915,9 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			if (MIPSInst_RT(ir))
 				xcp->regs[MIPSInst_RT(ir)] = value;
 			break;
-		}
 
-		case ctc_op:{
+		case ctc_op:
 			/* copregister rd <- rt */
-			u32 value;
-
 			if (MIPSInst_RT(ir) == 0)
 				value = 0;
 			else
@@ -1155,37 +926,33 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			/* we only have one writable control reg
 			 */
 			if (MIPSInst_RD(ir) == FPCREG_CSR) {
-#ifdef CSRTRACE
-				printk("%p gpr[%d]->csr=%08x\n",
-					(void *) (xcp->cp0_epc),
-					MIPSInst_RT(ir), value);
-#endif
+				pr_debug("%p gpr[%d]->csr=%08x\n",
+					 (void *) (xcp->cp0_epc),
+					 MIPSInst_RT(ir), value);
 
 				/*
 				 * Don't write reserved bits,
 				 * and convert to ieee library modes
 				 */
-				ctx->fcr31 = (value &
-						~(FPU_CSR_RSVD | FPU_CSR_RM)) |
-						ieee_rm[modeindex(value)];
+				ctx->fcr31 = (value & ~(FPU_CSR_RSVD | FPU_CSR_RM)) |
+					     modeindex(value);
 			}
 			if ((ctx->fcr31 >> 5) & ctx->fcr31 & FPU_CSR_ALL_E) {
 				return SIGFPE;
 			}
 			break;
-		}
 
-		case bc_op:{
-			int likely = 0;
-
-			if (xcp->cp0_cause & CAUSEF_BD)
+		case bc_op:
+			if (delay_slot(xcp))
 				return SIGILL;
 
-#if __mips >= 4
-			cond = ctx->fcr31 & fpucondbit[MIPSInst_RT(ir) >> 2];
-#else
-			cond = ctx->fcr31 & FPU_CSR_COND;
-#endif
+			if (cpu_has_mips_4_5_r)
+				cbit = fpucondbit[MIPSInst_RT(ir) >> 2];
+			else
+				cbit = FPU_CSR_COND;
+			cond = ctx->fcr31 & cbit;
+
+			likely = 0;
 			switch (MIPSInst_RT(ir) & 3) {
 			case bcfl_op:
 				likely = 1;
@@ -1201,10 +968,10 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 				return SIGILL;
 			}
 
-			xcp->cp0_cause |= CAUSEF_BD;
+			set_delay_slot(xcp);
 			if (cond) {
-				/* branch taken: emulate dslot
-				 * instruction
+				/*
+				 * Branch taken: emulate dslot instruction
 				 */
 				xcp->cp0_epc += dec_insn.pc_inc;
 
@@ -1238,23 +1005,37 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 
 				switch (MIPSInst_OPCODE(ir)) {
 				case lwc1_op:
+					goto emul;
+
 				case swc1_op:
-#if (__mips >= 2 || defined(__mips64))
+					goto emul;
+
 				case ldc1_op:
 				case sdc1_op:
-#endif
+					if (cpu_has_mips_2_3_4_5 ||
+					    cpu_has_mips64)
+						goto emul;
+
+					return SIGILL;
+					goto emul;
+
 				case cop1_op:
-#if __mips >= 4 && __mips != 32
-				case cop1x_op:
-#endif
-					/* its one of ours */
 					goto emul;
-#if __mips >= 4
+
+				case cop1x_op:
+					if (cpu_has_mips_4_5 || cpu_has_mips64)
+						/* its one of ours */
+						goto emul;
+
+					return SIGILL;
+
 				case spec_op:
+					if (!cpu_has_mips_4_5_r)
+						return SIGILL;
+
 					if (MIPSInst_FUNC(ir) == movc_op)
 						goto emul;
 					break;
-#endif
 				}
 
 				/*
@@ -1262,10 +1043,7 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 				 * instruction in the dslot
 				 */
 				return mips_dsemul(xcp, ir, contpc);
-			}
-			else {
-				/* branch not taken */
-				if (likely) {
+			} else if (likely) {	/* branch not taken */
 					/*
 					 * branch likely nullifies
 					 * dslot if not taken
@@ -1277,34 +1055,31 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 					 * dslot as normal insn
 					 */
 				}
-			}
 			break;
-		}
 
 		default:
 			if (!(MIPSInst_RS(ir) & 0x10))
 				return SIGILL;
-			{
-				int sig;
 
-				/* a real fpu computation instruction */
-				if ((sig = fpu_emu(xcp, ctx, ir)))
-					return sig;
-			}
+			/* a real fpu computation instruction */
+			if ((sig = fpu_emu(xcp, ctx, ir)))
+				return sig;
 		}
 		break;
 
-#if __mips >= 4 && __mips != 32
-	case cop1x_op:{
-		int sig = fpux_emu(xcp, ctx, ir, fault_addr);
+	case cop1x_op:
+		if (!cpu_has_mips_4_5 && !cpu_has_mips64)
+			return SIGILL;
+
+		sig = fpux_emu(xcp, ctx, ir, fault_addr);
 		if (sig)
 			return sig;
 		break;
-	}
-#endif
 
-#if __mips >= 4
 	case spec_op:
+		if (!cpu_has_mips_4_5_r)
+			return SIGILL;
+
 		if (MIPSInst_FUNC(ir) != movc_op)
 			return SIGILL;
 		cond = fpucondbit[MIPSInst_RT(ir) >> 2];
@@ -1312,8 +1087,6 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			xcp->regs[MIPSInst_RD(ir)] =
 				xcp->regs[MIPSInst_RS(ir)];
 		break;
-#endif
-
 	default:
 sigill:
 		return SIGILL;
@@ -1321,7 +1094,7 @@ sigill:
 
 	/* we did it !! */
 	xcp->cp0_epc = contpc;
-	xcp->cp0_cause &= ~CAUSEF_BD;
+	clear_delay_slot(xcp);
 
 	return 0;
 }
@@ -1342,44 +1115,42 @@ static const unsigned char cmptab[8] = {
 };
 
 
-#if __mips >= 4 && __mips != 32
-
 /*
  * Additional MIPS4 instructions
  */
 
-#define DEF3OP(name, p, f1, f2, f3) \
-static ieee754##p fpemu_##p##_##name(ieee754##p r, ieee754##p s, \
-    ieee754##p t) \
-{ \
-	struct _ieee754_csr ieee754_csr_save; \
-	s = f1(s, t); \
-	ieee754_csr_save = ieee754_csr; \
-	s = f2(s, r); \
-	ieee754_csr_save.cx |= ieee754_csr.cx; \
-	ieee754_csr_save.sx |= ieee754_csr.sx; \
-	s = f3(s); \
-	ieee754_csr.cx |= ieee754_csr_save.cx; \
-	ieee754_csr.sx |= ieee754_csr_save.sx; \
-	return s; \
+#define DEF3OP(name, p, f1, f2, f3)					\
+static union ieee754##p fpemu_##p##_##name(union ieee754##p r,		\
+	union ieee754##p s, union ieee754##p t)				\
+{									\
+	struct _ieee754_csr ieee754_csr_save;				\
+	s = f1(s, t);							\
+	ieee754_csr_save = ieee754_csr;					\
+	s = f2(s, r);							\
+	ieee754_csr_save.cx |= ieee754_csr.cx;				\
+	ieee754_csr_save.sx |= ieee754_csr.sx;				\
+	s = f3(s);							\
+	ieee754_csr.cx |= ieee754_csr_save.cx;				\
+	ieee754_csr.sx |= ieee754_csr_save.sx;				\
+	return s;							\
 }
 
-static ieee754dp fpemu_dp_recip(ieee754dp d)
+static union ieee754dp fpemu_dp_recip(union ieee754dp d)
 {
 	return ieee754dp_div(ieee754dp_one(0), d);
 }
 
-static ieee754dp fpemu_dp_rsqrt(ieee754dp d)
+static union ieee754dp fpemu_dp_rsqrt(union ieee754dp d)
 {
 	return ieee754dp_div(ieee754dp_one(0), ieee754dp_sqrt(d));
 }
 
-static ieee754sp fpemu_sp_recip(ieee754sp s)
+static union ieee754sp fpemu_sp_recip(union ieee754sp s)
 {
 	return ieee754sp_div(ieee754sp_one(0), s);
 }
 
-static ieee754sp fpemu_sp_rsqrt(ieee754sp s)
+static union ieee754sp fpemu_sp_rsqrt(union ieee754sp s)
 {
 	return ieee754sp_div(ieee754sp_one(0), ieee754sp_sqrt(s));
 }
@@ -1403,8 +1174,8 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	switch (MIPSInst_FMA_FFMT(ir)) {
 	case s_fmt:{		/* 0 */
 
-		ieee754sp(*handler) (ieee754sp, ieee754sp, ieee754sp);
-		ieee754sp fd, fr, fs, ft;
+		union ieee754sp(*handler) (union ieee754sp, union ieee754sp, union ieee754sp);
+		union ieee754sp fd, fr, fs, ft;
 		u32 __user *va;
 		u32 val;
 
@@ -1467,18 +1238,26 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			SPTOREG(fd, MIPSInst_FD(ir));
 
 		      copcsr:
-			if (ieee754_cxtest(IEEE754_INEXACT))
+			if (ieee754_cxtest(IEEE754_INEXACT)) {
+				MIPS_FPU_EMU_INC_STATS(ieee754_inexact);
 				rcsr |= FPU_CSR_INE_X | FPU_CSR_INE_S;
-			if (ieee754_cxtest(IEEE754_UNDERFLOW))
+			}
+			if (ieee754_cxtest(IEEE754_UNDERFLOW)) {
+				MIPS_FPU_EMU_INC_STATS(ieee754_underflow);
 				rcsr |= FPU_CSR_UDF_X | FPU_CSR_UDF_S;
-			if (ieee754_cxtest(IEEE754_OVERFLOW))
+			}
+			if (ieee754_cxtest(IEEE754_OVERFLOW)) {
+				MIPS_FPU_EMU_INC_STATS(ieee754_overflow);
 				rcsr |= FPU_CSR_OVF_X | FPU_CSR_OVF_S;
-			if (ieee754_cxtest(IEEE754_INVALID_OPERATION))
+			}
+			if (ieee754_cxtest(IEEE754_INVALID_OPERATION)) {
+				MIPS_FPU_EMU_INC_STATS(ieee754_invalidop);
 				rcsr |= FPU_CSR_INV_X | FPU_CSR_INV_S;
+			}
 
 			ctx->fcr31 = (ctx->fcr31 & ~FPU_CSR_ALL_X) | rcsr;
 			if ((ctx->fcr31 >> 5) & ctx->fcr31 & FPU_CSR_ALL_E) {
-				/*printk ("SIGFPE: fpu csr = %08x\n",
+				/*printk ("SIGFPE: FPU csr = %08x\n",
 				   ctx->fcr31); */
 				return SIGFPE;
 			}
@@ -1492,8 +1271,8 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	}
 
 	case d_fmt:{		/* 1 */
-		ieee754dp(*handler) (ieee754dp, ieee754dp, ieee754dp);
-		ieee754dp fd, fr, fs, ft;
+		union ieee754dp(*handler) (union ieee754dp, union ieee754dp, union ieee754dp);
+		union ieee754dp fd, fr, fs, ft;
 		u64 __user *va;
 		u64 val;
 
@@ -1574,7 +1353,6 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 
 	return 0;
 }
-#endif
 
 
 
@@ -1586,23 +1364,25 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 {
 	int rfmt;		/* resulting format */
 	unsigned rcsr = 0;	/* resulting csr */
+	unsigned int oldrm;
+	unsigned int cbit;
 	unsigned cond;
 	union {
-		ieee754dp d;
-		ieee754sp s;
+		union ieee754dp d;
+		union ieee754sp s;
 		int w;
-#ifdef __mips64
 		s64 l;
-#endif
 	} rv;			/* resulting value */
+	u64 bits;
 
 	MIPS_FPU_EMU_INC_STATS(cp1ops);
 	switch (rfmt = (MIPSInst_FFMT(ir) & 0xf)) {
-	case s_fmt:{		/* 0 */
+	case s_fmt: {		/* 0 */
 		union {
-			ieee754sp(*b) (ieee754sp, ieee754sp);
-			ieee754sp(*u) (ieee754sp);
+			union ieee754sp(*b) (union ieee754sp, union ieee754sp);
+			union ieee754sp(*u) (union ieee754sp);
 		} handler;
+		union ieee754sp fs, ft;
 
 		switch (MIPSInst_FUNC(ir)) {
 			/* binary ops */
@@ -1620,148 +1400,167 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			goto scopbop;
 
 			/* unary  ops */
-#if __mips >= 2 || defined(__mips64)
 		case fsqrt_op:
+			if (!cpu_has_mips_4_5_r)
+				return SIGILL;
+
 			handler.u = ieee754sp_sqrt;
 			goto scopuop;
-#endif
-#if __mips >= 4 && __mips != 32
+
+		/*
+		 * Note that on some MIPS IV implementations such as the
+		 * R5000 and R8000 the FSQRT and FRECIP instructions do not
+		 * achieve full IEEE-754 accuracy - however this emulator does.
+		 */
 		case frsqrt_op:
+			if (!cpu_has_mips_4_5_r2)
+				return SIGILL;
+
 			handler.u = fpemu_sp_rsqrt;
 			goto scopuop;
+
 		case frecip_op:
+			if (!cpu_has_mips_4_5_r2)
+				return SIGILL;
+
 			handler.u = fpemu_sp_recip;
 			goto scopuop;
-#endif
-#if __mips >= 4
+
 		case fmovc_op:
+			if (!cpu_has_mips_4_5_r)
+				return SIGILL;
+
 			cond = fpucondbit[MIPSInst_FT(ir) >> 2];
 			if (((ctx->fcr31 & cond) != 0) !=
 				((MIPSInst_FT(ir) & 1) != 0))
 				return 0;
 			SPFROMREG(rv.s, MIPSInst_FS(ir));
 			break;
+
 		case fmovz_op:
+			if (!cpu_has_mips_4_5_r)
+				return SIGILL;
+
 			if (xcp->regs[MIPSInst_FT(ir)] != 0)
 				return 0;
 			SPFROMREG(rv.s, MIPSInst_FS(ir));
 			break;
+
 		case fmovn_op:
+			if (!cpu_has_mips_4_5_r)
+				return SIGILL;
+
 			if (xcp->regs[MIPSInst_FT(ir)] == 0)
 				return 0;
 			SPFROMREG(rv.s, MIPSInst_FS(ir));
 			break;
-#endif
+
 		case fabs_op:
 			handler.u = ieee754sp_abs;
 			goto scopuop;
+
 		case fneg_op:
 			handler.u = ieee754sp_neg;
 			goto scopuop;
+
 		case fmov_op:
 			/* an easy one */
 			SPFROMREG(rv.s, MIPSInst_FS(ir));
 			goto copcsr;
 
 			/* binary op on handler */
-		      scopbop:
-			{
-				ieee754sp fs, ft;
-
-				SPFROMREG(fs, MIPSInst_FS(ir));
-				SPFROMREG(ft, MIPSInst_FT(ir));
-
-				rv.s = (*handler.b) (fs, ft);
-				goto copcsr;
-			}
-		      scopuop:
-			{
-				ieee754sp fs;
+scopbop:
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			SPFROMREG(ft, MIPSInst_FT(ir));
 
-				SPFROMREG(fs, MIPSInst_FS(ir));
-				rv.s = (*handler.u) (fs);
-				goto copcsr;
-			}
-		      copcsr:
-			if (ieee754_cxtest(IEEE754_INEXACT))
+			rv.s = (*handler.b) (fs, ft);
+			goto copcsr;
+scopuop:
+			SPFROMREG(fs, MIPSInst_FS(ir));
+			rv.s = (*handler.u) (fs);
+			goto copcsr;
+copcsr:
+			if (ieee754_cxtest(IEEE754_INEXACT)) {
+				MIPS_FPU_EMU_INC_STATS(ieee754_inexact);
 				rcsr |= FPU_CSR_INE_X | FPU_CSR_INE_S;
-			if (ieee754_cxtest(IEEE754_UNDERFLOW))
+			}
+			if (ieee754_cxtest(IEEE754_UNDERFLOW)) {
+				MIPS_FPU_EMU_INC_STATS(ieee754_underflow);
 				rcsr |= FPU_CSR_UDF_X | FPU_CSR_UDF_S;
-			if (ieee754_cxtest(IEEE754_OVERFLOW))
+			}
+			if (ieee754_cxtest(IEEE754_OVERFLOW)) {
+				MIPS_FPU_EMU_INC_STATS(ieee754_overflow);
 				rcsr |= FPU_CSR_OVF_X | FPU_CSR_OVF_S;
-			if (ieee754_cxtest(IEEE754_ZERO_DIVIDE))
+			}
+			if (ieee754_cxtest(IEEE754_ZERO_DIVIDE)) {
+				MIPS_FPU_EMU_INC_STATS(ieee754_zerodiv);
 				rcsr |= FPU_CSR_DIV_X | FPU_CSR_DIV_S;
-			if (ieee754_cxtest(IEEE754_INVALID_OPERATION))
+			}
+			if (ieee754_cxtest(IEEE754_INVALID_OPERATION)) {
+				MIPS_FPU_EMU_INC_STATS(ieee754_invalidop);
 				rcsr |= FPU_CSR_INV_X | FPU_CSR_INV_S;
+			}
 			break;
 
 			/* unary conv ops */
 		case fcvts_op:
 			return SIGILL;	/* not defined */
-		case fcvtd_op:{
-			ieee754sp fs;
 
+		case fcvtd_op:
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.d = ieee754dp_fsp(fs);
 			rfmt = d_fmt;
 			goto copcsr;
-		}
-		case fcvtw_op:{
-			ieee754sp fs;
 
+		case fcvtw_op:
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.w = ieee754sp_tint(fs);
 			rfmt = w_fmt;
 			goto copcsr;
-		}
 
-#if __mips >= 2 || defined(__mips64)
 		case fround_op:
 		case ftrunc_op:
 		case fceil_op:
-		case ffloor_op:{
-			unsigned int oldrm = ieee754_csr.rm;
-			ieee754sp fs;
+		case ffloor_op:
+			if (!cpu_has_mips_2_3_4_5 && !cpu_has_mips64)
+				return SIGILL;
 
+			oldrm = ieee754_csr.rm;
 			SPFROMREG(fs, MIPSInst_FS(ir));
-			ieee754_csr.rm = ieee_rm[modeindex(MIPSInst_FUNC(ir))];
+			ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir));
 			rv.w = ieee754sp_tint(fs);
 			ieee754_csr.rm = oldrm;
 			rfmt = w_fmt;
 			goto copcsr;
-		}
-#endif /* __mips >= 2 */
 
-#if defined(__mips64)
-		case fcvtl_op:{
-			ieee754sp fs;
+		case fcvtl_op:
+			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+				return SIGILL;
 
 			SPFROMREG(fs, MIPSInst_FS(ir));
 			rv.l = ieee754sp_tlong(fs);
 			rfmt = l_fmt;
 			goto copcsr;
-		}
 
 		case froundl_op:
 		case ftruncl_op:
 		case fceill_op:
-		case ffloorl_op:{
-			unsigned int oldrm = ieee754_csr.rm;
-			ieee754sp fs;
+		case ffloorl_op:
+			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+				return SIGILL;
 
+			oldrm = ieee754_csr.rm;
 			SPFROMREG(fs, MIPSInst_FS(ir));
-			ieee754_csr.rm = ieee_rm[modeindex(MIPSInst_FUNC(ir))];
+			ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir));
 			rv.l = ieee754sp_tlong(fs);
 			ieee754_csr.rm = oldrm;
 			rfmt = l_fmt;
 			goto copcsr;
-		}
-#endif /* defined(__mips64) */
 
 		default:
 			if (MIPSInst_FUNC(ir) >= fcmp_op) {
 				unsigned cmpop = MIPSInst_FUNC(ir) - fcmp_op;
-				ieee754sp fs, ft;
+				union ieee754sp fs, ft;
 
 				SPFROMREG(fs, MIPSInst_FS(ir));
 				SPFROMREG(ft, MIPSInst_FT(ir));
@@ -1774,19 +1573,18 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 				else
 					goto copcsr;
 
-			}
-			else {
+			} else
 				return SIGILL;
-			}
 			break;
 		}
 		break;
 	}
 
-	case d_fmt:{
+	case d_fmt: {
+		union ieee754dp fs, ft;
 		union {
-			ieee754dp(*b) (ieee754dp, ieee754dp);
-			ieee754dp(*u) (ieee754dp);
+			union ieee754dp(*b) (union ieee754dp, union ieee754dp);
+			union ieee754dp(*u) (union ieee754dp);
 		} handler;
 
 		switch (MIPSInst_FUNC(ir)) {
@@ -1805,21 +1603,33 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			goto dcopbop;
 
 			/* unary  ops */
-#if __mips >= 2 || defined(__mips64)
 		case fsqrt_op:
+			if (!cpu_has_mips_2_3_4_5_r)
+				return SIGILL;
+
 			handler.u = ieee754dp_sqrt;
 			goto dcopuop;
-#endif
-#if __mips >= 4 && __mips != 32
+		/*
+		 * Note that on some MIPS IV implementations such as the
+		 * R5000 and R8000 the FSQRT and FRECIP instructions do not
+		 * achieve full IEEE-754 accuracy - however this emulator does.
+		 */
 		case frsqrt_op:
+			if (!cpu_has_mips_4_5_r2)
+				return SIGILL;
+
 			handler.u = fpemu_dp_rsqrt;
 			goto dcopuop;
 		case frecip_op:
+			if (!cpu_has_mips_4_5_r2)
+				return SIGILL;
+
 			handler.u = fpemu_dp_recip;
 			goto dcopuop;
-#endif
-#if __mips >= 4
 		case fmovc_op:
+			if (!cpu_has_mips_4_5_r)
+				return SIGILL;
+
 			cond = fpucondbit[MIPSInst_FT(ir) >> 2];
 			if (((ctx->fcr31 & cond) != 0) !=
 				((MIPSInst_FT(ir) & 1) != 0))
@@ -1827,16 +1637,21 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			DPFROMREG(rv.d, MIPSInst_FS(ir));
 			break;
 		case fmovz_op:
+			if (!cpu_has_mips_4_5_r)
+				return SIGILL;
+
 			if (xcp->regs[MIPSInst_FT(ir)] != 0)
 				return 0;
 			DPFROMREG(rv.d, MIPSInst_FS(ir));
 			break;
 		case fmovn_op:
+			if (!cpu_has_mips_4_5_r)
+				return SIGILL;
+
 			if (xcp->regs[MIPSInst_FT(ir)] == 0)
 				return 0;
 			DPFROMREG(rv.d, MIPSInst_FS(ir));
 			break;
-#endif
 		case fabs_op:
 			handler.u = ieee754dp_abs;
 			goto dcopuop;
@@ -1851,91 +1666,78 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			goto copcsr;
 
 			/* binary op on handler */
-		      dcopbop:{
-				ieee754dp fs, ft;
-
-				DPFROMREG(fs, MIPSInst_FS(ir));
-				DPFROMREG(ft, MIPSInst_FT(ir));
-
-				rv.d = (*handler.b) (fs, ft);
-				goto copcsr;
-			}
-		      dcopuop:{
-				ieee754dp fs;
-
-				DPFROMREG(fs, MIPSInst_FS(ir));
-				rv.d = (*handler.u) (fs);
-				goto copcsr;
-			}
+dcopbop:
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			DPFROMREG(ft, MIPSInst_FT(ir));
 
-			/* unary conv ops */
-		case fcvts_op:{
-			ieee754dp fs;
+			rv.d = (*handler.b) (fs, ft);
+			goto copcsr;
+dcopuop:
+			DPFROMREG(fs, MIPSInst_FS(ir));
+			rv.d = (*handler.u) (fs);
+			goto copcsr;
 
+		/*
+		 * unary conv ops
+		 */
+		case fcvts_op:
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.s = ieee754sp_fdp(fs);
 			rfmt = s_fmt;
 			goto copcsr;
-		}
+
 		case fcvtd_op:
 			return SIGILL;	/* not defined */
 
-		case fcvtw_op:{
-			ieee754dp fs;
-
+		case fcvtw_op:
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.w = ieee754dp_tint(fs);	/* wrong */
 			rfmt = w_fmt;
 			goto copcsr;
-		}
 
-#if __mips >= 2 || defined(__mips64)
 		case fround_op:
 		case ftrunc_op:
 		case fceil_op:
-		case ffloor_op:{
-			unsigned int oldrm = ieee754_csr.rm;
-			ieee754dp fs;
+		case ffloor_op:
+			if (!cpu_has_mips_2_3_4_5_r)
+				return SIGILL;
 
+			oldrm = ieee754_csr.rm;
 			DPFROMREG(fs, MIPSInst_FS(ir));
-			ieee754_csr.rm = ieee_rm[modeindex(MIPSInst_FUNC(ir))];
+			ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir));
 			rv.w = ieee754dp_tint(fs);
 			ieee754_csr.rm = oldrm;
 			rfmt = w_fmt;
 			goto copcsr;
-		}
-#endif
 
-#if defined(__mips64)
-		case fcvtl_op:{
-			ieee754dp fs;
+		case fcvtl_op:
+			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+				return SIGILL;
 
 			DPFROMREG(fs, MIPSInst_FS(ir));
 			rv.l = ieee754dp_tlong(fs);
 			rfmt = l_fmt;
 			goto copcsr;
-		}
 
 		case froundl_op:
 		case ftruncl_op:
 		case fceill_op:
-		case ffloorl_op:{
-			unsigned int oldrm = ieee754_csr.rm;
-			ieee754dp fs;
+		case ffloorl_op:
+			if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+				return SIGILL;
 
+			oldrm = ieee754_csr.rm;
 			DPFROMREG(fs, MIPSInst_FS(ir));
-			ieee754_csr.rm = ieee_rm[modeindex(MIPSInst_FUNC(ir))];
+			ieee754_csr.rm = modeindex(MIPSInst_FUNC(ir));
 			rv.l = ieee754dp_tlong(fs);
 			ieee754_csr.rm = oldrm;
 			rfmt = l_fmt;
 			goto copcsr;
-		}
-#endif /* __mips >= 3 */
 
 		default:
 			if (MIPSInst_FUNC(ir) >= fcmp_op) {
 				unsigned cmpop = MIPSInst_FUNC(ir) - fcmp_op;
-				ieee754dp fs, ft;
+				union ieee754dp fs, ft;
 
 				DPFROMREG(fs, MIPSInst_FS(ir));
 				DPFROMREG(ft, MIPSInst_FT(ir));
@@ -1957,11 +1759,8 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			break;
 		}
 		break;
-	}
-
-	case w_fmt:{
-		ieee754sp fs;
 
+	case w_fmt:
 		switch (MIPSInst_FUNC(ir)) {
 		case fcvts_op:
 			/* convert word to single precision real */
@@ -1981,9 +1780,11 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 		break;
 	}
 
-#if defined(__mips64)
-	case l_fmt:{
-		u64 bits;
+	case l_fmt:
+
+		if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+			return SIGILL;
+
 		DIFROMREG(bits, MIPSInst_FS(ir));
 
 		switch (MIPSInst_FUNC(ir)) {
@@ -2001,8 +1802,6 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			return SIGILL;
 		}
 		break;
-	}
-#endif
 
 	default:
 		return SIGILL;
@@ -2017,7 +1816,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	 */
 	ctx->fcr31 = (ctx->fcr31 & ~FPU_CSR_ALL_X) | rcsr;
 	if ((ctx->fcr31 >> 5) & ctx->fcr31 & FPU_CSR_ALL_E) {
-		/*printk ("SIGFPE: fpu csr = %08x\n",ctx->fcr31); */
+		/*printk ("SIGFPE: FPU csr = %08x\n",ctx->fcr31); */
 		return SIGFPE;
 	}
 
@@ -2025,18 +1824,18 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	 * Now we can safely write the result back to the register file.
 	 */
 	switch (rfmt) {
-	case -1:{
-#if __mips >= 4
-		cond = fpucondbit[MIPSInst_FD(ir) >> 2];
-#else
-		cond = FPU_CSR_COND;
-#endif
+	case -1:
+
+		if (cpu_has_mips_4_5_r)
+			cbit = fpucondbit[MIPSInst_RT(ir) >> 2];
+		else
+			cbit = FPU_CSR_COND;
 		if (rv.w)
-			ctx->fcr31 |= cond;
+			ctx->fcr31 |= cbit;
 		else
-			ctx->fcr31 &= ~cond;
+			ctx->fcr31 &= ~cbit;
 		break;
-	}
+
 	case d_fmt:
 		DPTOREG(rv.d, MIPSInst_FD(ir));
 		break;
@@ -2046,11 +1845,12 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	case w_fmt:
 		SITOREG(rv.w, MIPSInst_FD(ir));
 		break;
-#if defined(__mips64)
 	case l_fmt:
+		if (!cpu_has_mips_3_4_5 && !cpu_has_mips64)
+			return SIGILL;
+
 		DITOREG(rv.l, MIPSInst_FD(ir));
 		break;
-#endif
 	default:
 		return SIGILL;
 	}
@@ -2138,11 +1938,7 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			 * ieee754_csr.	 But ieee754_csr.rm is ieee
 			 * library modes. (not mips rounding mode)
 			 */
-			/* convert to ieee library modes */
-			ieee754_csr.rm = ieee_rm[ieee754_csr.rm];
 			sig = cop1Emulate(xcp, ctx, dec_insn, fault_addr);
-			/* revert to mips rounding mode */
-			ieee754_csr.rm = mips_rm[ieee754_csr.rm];
 		}
 
 		if (has_fpu)
@@ -2155,58 +1951,8 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 
 	/* SIGILL indicates a non-fpu instruction */
 	if (sig == SIGILL && xcp->cp0_epc != oldepc)
-		/* but if epc has advanced, then ignore it */
+		/* but if EPC has advanced, then ignore it */
 		sig = 0;
 
 	return sig;
 }
-
-#ifdef CONFIG_DEBUG_FS
-
-static int fpuemu_stat_get(void *data, u64 *val)
-{
-	int cpu;
-	unsigned long sum = 0;
-	for_each_online_cpu(cpu) {
-		struct mips_fpu_emulator_stats *ps;
-		local_t *pv;
-		ps = &per_cpu(fpuemustats, cpu);
-		pv = (void *)ps + (unsigned long)data;
-		sum += local_read(pv);
-	}
-	*val = sum;
-	return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(fops_fpuemu_stat, fpuemu_stat_get, NULL, "%llu\n");
-
-extern struct dentry *mips_debugfs_dir;
-static int __init debugfs_fpuemu(void)
-{
-	struct dentry *d, *dir;
-
-	if (!mips_debugfs_dir)
-		return -ENODEV;
-	dir = debugfs_create_dir("fpuemustats", mips_debugfs_dir);
-	if (!dir)
-		return -ENOMEM;
-
-#define FPU_STAT_CREATE(M)						\
-	do {								\
-		d = debugfs_create_file(#M , S_IRUGO, dir,		\
-			(void *)offsetof(struct mips_fpu_emulator_stats, M), \
-			&fops_fpuemu_stat);				\
-		if (!d)							\
-			return -ENOMEM;					\
-	} while (0)
-
-	FPU_STAT_CREATE(emulated);
-	FPU_STAT_CREATE(loads);
-	FPU_STAT_CREATE(stores);
-	FPU_STAT_CREATE(cp1ops);
-	FPU_STAT_CREATE(cp1xops);
-	FPU_STAT_CREATE(errors);
-
-	return 0;
-}
-__initcall(debugfs_fpuemu);
-#endif
diff --git a/arch/mips/math-emu/dp_add.c b/arch/mips/math-emu/dp_add.c
index c57c8adc42c..7f64577df98 100644
--- a/arch/mips/math-emu/dp_add.c
+++ b/arch/mips/math-emu/dp_add.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,24 +16,22 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- *
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
-ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y)
+union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y)
 {
+	int s;
+
 	COMPXDP;
 	COMPYDP;
 
 	EXPLODEXDP;
 	EXPLODEYDP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXDP;
 	FLUSHYDP;
@@ -52,8 +48,8 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef(), "add", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_nanxcpt(ieee754dp_indef());
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -69,14 +65,14 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y)
 		return x;
 
 
-		/* Infinity handling
-		 */
-
+	/*
+	 * Infinity handling
+	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 		if (xs == ys)
 			return x;
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_xcpt(ieee754dp_indef(), "add", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_indef();
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -88,15 +84,14 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 		return x;
 
-		/* Zero handling
-		 */
-
+	/*
+	 * Zero handling
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
 		if (xs == ys)
 			return x;
 		else
-			return ieee754dp_zero(ieee754_csr.rm ==
-					      IEEE754_RD);
+			return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
@@ -125,20 +120,24 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y)
 	assert(xm & DP_HIDDEN_BIT);
 	assert(ym & DP_HIDDEN_BIT);
 
-	/* provide guard,round and stick bit space */
+	/*
+	 * Provide guard,round and stick bit space.
+	 */
 	xm <<= 3;
 	ym <<= 3;
 
 	if (xe > ye) {
-		/* have to shift y fraction right to align
+		/*
+		 * Have to shift y fraction right to align.
 		 */
-		int s = xe - ye;
+		s = xe - ye;
 		ym = XDPSRS(ym, s);
 		ye += s;
 	} else if (ye > xe) {
-		/* have to shift x fraction right to align
+		/*
+		 * Have to shift x fraction right to align.
 		 */
-		int s = ye - xe;
+		s = ye - xe;
 		xm = XDPSRS(xm, s);
 		xe += s;
 	}
@@ -146,14 +145,15 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y)
 	assert(xe <= DP_EMAX);
 
 	if (xs == ys) {
-		/* generate 28 bit result of adding two 27 bit numbers
-		 * leaving result in xm,xs,xe
+		/*
+		 * Generate 28 bit result of adding two 27 bit numbers
+		 * leaving result in xm, xs and xe.
 		 */
 		xm = xm + ym;
 		xe = xe;
 		xs = xs;
 
-		if (xm >> (DP_MBITS + 1 + 3)) { /* carry out */
+		if (xm >> (DP_FBITS + 1 + 3)) { /* carry out */
 			xm = XDPSRS1(xm);
 			xe++;
 		}
@@ -168,15 +168,16 @@ ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y)
 			xs = ys;
 		}
 		if (xm == 0)
-			return ieee754dp_zero(ieee754_csr.rm ==
-					      IEEE754_RD);
+			return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
 
-		/* normalize to rounding precision */
-		while ((xm >> (DP_MBITS + 3)) == 0) {
+		/*
+		 * Normalize to rounding precision.
+		 */
+		while ((xm >> (DP_FBITS + 3)) == 0) {
 			xm <<= 1;
 			xe--;
 		}
-
 	}
-	DPNORMRET2(xs, xe, xm, "add", x, y);
+
+	return ieee754dp_format(xs, xe, xm);
 }
diff --git a/arch/mips/math-emu/dp_cmp.c b/arch/mips/math-emu/dp_cmp.c
index 0f32486b0ed..30f95f6e9ac 100644
--- a/arch/mips/math-emu/dp_cmp.c
+++ b/arch/mips/math-emu/dp_cmp.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,16 +16,16 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
-int ieee754dp_cmp(ieee754dp x, ieee754dp y, int cmp, int sig)
+int ieee754dp_cmp(union ieee754dp x, union ieee754dp y, int cmp, int sig)
 {
+	s64 vx;
+	s64 vy;
+
 	COMPXDP;
 	COMPYDP;
 
@@ -35,21 +33,21 @@ int ieee754dp_cmp(ieee754dp x, ieee754dp y, int cmp, int sig)
 	EXPLODEYDP;
 	FLUSHXDP;
 	FLUSHYDP;
-	CLEARCX;	/* Even clear inexact flag here */
+	ieee754_clearcx();	/* Even clear inexact flag here */
 
 	if (ieee754dp_isnan(x) || ieee754dp_isnan(y)) {
 		if (sig || xc == IEEE754_CLASS_SNAN || yc == IEEE754_CLASS_SNAN)
-			SETCX(IEEE754_INVALID_OPERATION);
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
 		if (cmp & IEEE754_CUN)
 			return 1;
 		if (cmp & (IEEE754_CLT | IEEE754_CGT)) {
-			if (sig && SETANDTESTCX(IEEE754_INVALID_OPERATION))
-				return ieee754si_xcpt(0, "fcmpf", x);
+			if (sig && ieee754_setandtestcx(IEEE754_INVALID_OPERATION))
+				return 0;
 		}
 		return 0;
 	} else {
-		s64 vx = x.bits;
-		s64 vy = y.bits;
+		vx = x.bits;
+		vy = y.bits;
 
 		if (vx < 0)
 			vx = -vx ^ DP_SIGN_BIT;
diff --git a/arch/mips/math-emu/dp_div.c b/arch/mips/math-emu/dp_div.c
index a1bce1b7c09..bef0e55e593 100644
--- a/arch/mips/math-emu/dp_div.c
+++ b/arch/mips/math-emu/dp_div.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,23 +16,24 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
-ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y)
+union ieee754dp ieee754dp_div(union ieee754dp x, union ieee754dp y)
 {
+	u64 rm;
+	int re;
+	u64 bm;
+
 	COMPXDP;
 	COMPYDP;
 
 	EXPLODEXDP;
 	EXPLODEYDP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXDP;
 	FLUSHYDP;
@@ -51,8 +50,8 @@ ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef(), "div", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_nanxcpt(ieee754dp_indef());
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -68,12 +67,12 @@ ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y)
 		return x;
 
 
-		/* Infinity handling
-		 */
-
+	/*
+	 * Infinity handling
+	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_xcpt(ieee754dp_indef(), "div", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_indef();
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -85,17 +84,17 @@ ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 		return ieee754dp_inf(xs ^ ys);
 
-		/* Zero handling
-		 */
-
+	/*
+	 * Zero handling
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_xcpt(ieee754dp_indef(), "div", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_indef();
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
-		SETCX(IEEE754_ZERO_DIVIDE);
-		return ieee754dp_xcpt(ieee754dp_inf(xs ^ ys), "div", x, y);
+		ieee754_setcx(IEEE754_ZERO_DIVIDE);
+		return ieee754dp_inf(xs ^ ys);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
@@ -122,35 +121,34 @@ ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y)
 	xm <<= 3;
 	ym <<= 3;
 
-	{
-		/* now the dirty work */
-
-		u64 rm = 0;
-		int re = xe - ye;
-		u64 bm;
-
-		for (bm = DP_MBIT(DP_MBITS + 2); bm; bm >>= 1) {
-			if (xm >= ym) {
-				xm -= ym;
-				rm |= bm;
-				if (xm == 0)
-					break;
-			}
-			xm <<= 1;
-		}
-		rm <<= 1;
-		if (xm)
-			rm |= 1;	/* have remainder, set sticky */
+	/* now the dirty work */
 
-		assert(rm);
+	rm = 0;
+	re = xe - ye;
 
-		/* normalise rm to rounding precision ?
-		 */
-		while ((rm >> (DP_MBITS + 3)) == 0) {
-			rm <<= 1;
-			re--;
+	for (bm = DP_MBIT(DP_FBITS + 2); bm; bm >>= 1) {
+		if (xm >= ym) {
+			xm -= ym;
+			rm |= bm;
+			if (xm == 0)
+				break;
 		}
+		xm <<= 1;
+	}
+
+	rm <<= 1;
+	if (xm)
+		rm |= 1;	/* have remainder, set sticky */
 
-		DPNORMRET2(xs == ys ? 0 : 1, re, rm, "div", x, y);
+	assert(rm);
+
+	/*
+	 * Normalise rm to rounding precision ?
+	 */
+	while ((rm >> (DP_FBITS + 3)) == 0) {
+		rm <<= 1;
+		re--;
 	}
+
+	return ieee754dp_format(xs == ys ? 0 : 1, re, rm);
 }
diff --git a/arch/mips/math-emu/dp_fint.c b/arch/mips/math-emu/dp_fint.c
index 88571288c9e..10258f0afd6 100644
--- a/arch/mips/math-emu/dp_fint.c
+++ b/arch/mips/math-emu/dp_fint.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,21 +16,18 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
-ieee754dp ieee754dp_fint(int x)
+union ieee754dp ieee754dp_fint(int x)
 {
 	u64 xm;
 	int xe;
 	int xs;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	if (x == 0)
 		return ieee754dp_zero(0);
@@ -51,29 +46,11 @@ ieee754dp ieee754dp_fint(int x)
 		xm = x;
 	}
 
-#if 1
 	/* normalize - result can never be inexact or overflow */
-	xe = DP_MBITS;
-	while ((xm >> DP_MBITS) == 0) {
+	xe = DP_FBITS;
+	while ((xm >> DP_FBITS) == 0) {
 		xm <<= 1;
 		xe--;
 	}
 	return builddp(xs, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT);
-#else
-	/* normalize */
-	xe = DP_MBITS + 3;
-	while ((xm >> (DP_MBITS + 3)) == 0) {
-		xm <<= 1;
-		xe--;
-	}
-	DPNORMRET1(xs, xe, xm, "fint", x);
-#endif
-}
-
-ieee754dp ieee754dp_funs(unsigned int u)
-{
-	if ((int) u < 0)
-		return ieee754dp_add(ieee754dp_1e31(),
-				     ieee754dp_fint(u & ~(1 << 31)));
-	return ieee754dp_fint(u);
 }
diff --git a/arch/mips/math-emu/dp_flong.c b/arch/mips/math-emu/dp_flong.c
index 14fc01ec742..a267c2e39d7 100644
--- a/arch/mips/math-emu/dp_flong.c
+++ b/arch/mips/math-emu/dp_flong.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,21 +16,18 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
-ieee754dp ieee754dp_flong(s64 x)
+union ieee754dp ieee754dp_flong(s64 x)
 {
 	u64 xm;
 	int xe;
 	int xs;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	if (x == 0)
 		return ieee754dp_zero(0);
@@ -52,26 +47,19 @@ ieee754dp ieee754dp_flong(s64 x)
 	}
 
 	/* normalize */
-	xe = DP_MBITS + 3;
-	if (xm >> (DP_MBITS + 1 + 3)) {
+	xe = DP_FBITS + 3;
+	if (xm >> (DP_FBITS + 1 + 3)) {
 		/* shunt out overflow bits */
-		while (xm >> (DP_MBITS + 1 + 3)) {
+		while (xm >> (DP_FBITS + 1 + 3)) {
 			XDPSRSX1();
 		}
 	} else {
 		/* normalize in grs extended double precision */
-		while ((xm >> (DP_MBITS + 3)) == 0) {
+		while ((xm >> (DP_FBITS + 3)) == 0) {
 			xm <<= 1;
 			xe--;
 		}
 	}
-	DPNORMRET1(xs, xe, xm, "dp_flong", x);
-}
 
-ieee754dp ieee754dp_fulong(u64 u)
-{
-	if ((s64) u < 0)
-		return ieee754dp_add(ieee754dp_1e63(),
-				     ieee754dp_flong(u & ~(1ULL << 63)));
-	return ieee754dp_flong(u);
+	return ieee754dp_format(xs, xe, xm);
 }
diff --git a/arch/mips/math-emu/dp_frexp.c b/arch/mips/math-emu/dp_frexp.c
deleted file mode 100644
index cb15a5eaecb..00000000000
--- a/arch/mips/math-emu/dp_frexp.c
+++ /dev/null
@@ -1,52 +0,0 @@
-/* IEEE754 floating point arithmetic
- * double precision: common utilities
- */
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-
-#include "ieee754dp.h"
-
-/* close to ieeep754dp_logb
-*/
-ieee754dp ieee754dp_frexp(ieee754dp x, int *eptr)
-{
-	COMPXDP;
-	CLEARCX;
-	EXPLODEXDP;
-
-	switch (xc) {
-	case IEEE754_CLASS_SNAN:
-	case IEEE754_CLASS_QNAN:
-	case IEEE754_CLASS_INF:
-	case IEEE754_CLASS_ZERO:
-		*eptr = 0;
-		return x;
-	case IEEE754_CLASS_DNORM:
-		DPDNORMX;
-		break;
-	case IEEE754_CLASS_NORM:
-		break;
-	}
-	*eptr = xe + 1;
-	return builddp(xs, -1 + DP_EBIAS, xm & ~DP_HIDDEN_BIT);
-}
diff --git a/arch/mips/math-emu/dp_fsp.c b/arch/mips/math-emu/dp_fsp.c
index daed6834dc1..ffb69c5830b 100644
--- a/arch/mips/math-emu/dp_fsp.c
+++ b/arch/mips/math-emu/dp_fsp.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,56 +16,58 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
+#include "ieee754sp.h"
 #include "ieee754dp.h"
 
-ieee754dp ieee754dp_fsp(ieee754sp x)
+union ieee754dp ieee754dp_fsp(union ieee754sp x)
 {
 	COMPXSP;
 
 	EXPLODEXSP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXSP;
 
 	switch (xc) {
 	case IEEE754_CLASS_SNAN:
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef(), "fsp");
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_nanxcpt(ieee754dp_indef());
+
 	case IEEE754_CLASS_QNAN:
 		return ieee754dp_nanxcpt(builddp(xs,
 						 DP_EMAX + 1 + DP_EBIAS,
 						 ((u64) xm
-						  << (DP_MBITS -
-						      SP_MBITS))), "fsp",
-					 x);
+						  << (DP_FBITS -
+						      SP_FBITS))));
 	case IEEE754_CLASS_INF:
 		return ieee754dp_inf(xs);
+
 	case IEEE754_CLASS_ZERO:
 		return ieee754dp_zero(xs);
+
 	case IEEE754_CLASS_DNORM:
 		/* normalize */
-		while ((xm >> SP_MBITS) == 0) {
+		while ((xm >> SP_FBITS) == 0) {
 			xm <<= 1;
 			xe--;
 		}
 		break;
+
 	case IEEE754_CLASS_NORM:
 		break;
 	}
 
-	/* CAN'T possibly overflow,underflow, or need rounding
+	/*
+	 * Can't possibly overflow,underflow, or need rounding
 	 */
 
 	/* drop the hidden bit */
 	xm &= ~SP_HIDDEN_BIT;
 
 	return builddp(xs, xe + DP_EBIAS,
-		       (u64) xm << (DP_MBITS - SP_MBITS));
+		       (u64) xm << (DP_FBITS - SP_FBITS));
 }
diff --git a/arch/mips/math-emu/dp_logb.c b/arch/mips/math-emu/dp_logb.c
deleted file mode 100644
index 151127e59f5..00000000000
--- a/arch/mips/math-emu/dp_logb.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/* IEEE754 floating point arithmetic
- * double precision: common utilities
- */
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-
-#include "ieee754dp.h"
-
-ieee754dp ieee754dp_logb(ieee754dp x)
-{
-	COMPXDP;
-
-	CLEARCX;
-
-	EXPLODEXDP;
-
-	switch (xc) {
-	case IEEE754_CLASS_SNAN:
-		return ieee754dp_nanxcpt(x, "logb", x);
-	case IEEE754_CLASS_QNAN:
-		return x;
-	case IEEE754_CLASS_INF:
-		return ieee754dp_inf(0);
-	case IEEE754_CLASS_ZERO:
-		return ieee754dp_inf(1);
-	case IEEE754_CLASS_DNORM:
-		DPDNORMX;
-		break;
-	case IEEE754_CLASS_NORM:
-		break;
-	}
-	return ieee754dp_fint(xe);
-}
diff --git a/arch/mips/math-emu/dp_modf.c b/arch/mips/math-emu/dp_modf.c
deleted file mode 100644
index b01f9cf6d40..00000000000
--- a/arch/mips/math-emu/dp_modf.c
+++ /dev/null
@@ -1,79 +0,0 @@
-/* IEEE754 floating point arithmetic
- * double precision: common utilities
- */
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-
-#include "ieee754dp.h"
-
-/* modf function is always exact for a finite number
-*/
-ieee754dp ieee754dp_modf(ieee754dp x, ieee754dp *ip)
-{
-	COMPXDP;
-
-	CLEARCX;
-
-	EXPLODEXDP;
-
-	switch (xc) {
-	case IEEE754_CLASS_SNAN:
-	case IEEE754_CLASS_QNAN:
-	case IEEE754_CLASS_INF:
-	case IEEE754_CLASS_ZERO:
-		*ip = x;
-		return x;
-	case IEEE754_CLASS_DNORM:
-		/* far to small */
-		*ip = ieee754dp_zero(xs);
-		return x;
-	case IEEE754_CLASS_NORM:
-		break;
-	}
-	if (xe < 0) {
-		*ip = ieee754dp_zero(xs);
-		return x;
-	}
-	if (xe >= DP_MBITS) {
-		*ip = x;
-		return ieee754dp_zero(xs);
-	}
-	/* generate ipart mantissa by clearing bottom bits
-	 */
-	*ip = builddp(xs, xe + DP_EBIAS,
-		      ((xm >> (DP_MBITS - xe)) << (DP_MBITS - xe)) &
-		      ~DP_HIDDEN_BIT);
-
-	/* generate fpart mantissa by clearing top bits
-	 * and normalizing (must be able to normalize)
-	 */
-	xm = (xm << (64 - (DP_MBITS - xe))) >> (64 - (DP_MBITS - xe));
-	if (xm == 0)
-		return ieee754dp_zero(xs);
-
-	while ((xm >> DP_MBITS) == 0) {
-		xm <<= 1;
-		xe--;
-	}
-	return builddp(xs, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT);
-}
diff --git a/arch/mips/math-emu/dp_mul.c b/arch/mips/math-emu/dp_mul.c
index 09175f46192..d3acdedb5b9 100644
--- a/arch/mips/math-emu/dp_mul.c
+++ b/arch/mips/math-emu/dp_mul.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,23 +16,32 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
-ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y)
+union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y)
 {
+	int re;
+	int rs;
+	u64 rm;
+	unsigned lxm;
+	unsigned hxm;
+	unsigned lym;
+	unsigned hym;
+	u64 lrm;
+	u64 hrm;
+	u64 t;
+	u64 at;
+
 	COMPXDP;
 	COMPYDP;
 
 	EXPLODEXDP;
 	EXPLODEYDP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXDP;
 	FLUSHYDP;
@@ -51,8 +58,8 @@ ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef(), "mul", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_nanxcpt(ieee754dp_indef());
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -68,12 +75,13 @@ ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y)
 		return x;
 
 
-		/* Infinity handling */
-
+	/*
+	 * Infinity handling
+	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_xcpt(ieee754dp_indef(), "mul", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_indef();
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
@@ -107,70 +115,59 @@ ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y)
 	/* rm = xm * ym, re = xe+ye basically */
 	assert(xm & DP_HIDDEN_BIT);
 	assert(ym & DP_HIDDEN_BIT);
-	{
-		int re = xe + ye;
-		int rs = xs ^ ys;
-		u64 rm;
 
-		/* shunt to top of word */
-		xm <<= 64 - (DP_MBITS + 1);
-		ym <<= 64 - (DP_MBITS + 1);
+	re = xe + ye;
+	rs = xs ^ ys;
+
+	/* shunt to top of word */
+	xm <<= 64 - (DP_FBITS + 1);
+	ym <<= 64 - (DP_FBITS + 1);
 
-		/* multiply 32bits xm,ym to give high 32bits rm with stickness
-		 */
+	/*
+	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
+	 */
 
-		/* 32 * 32 => 64 */
+	/* 32 * 32 => 64 */
 #define DPXMULT(x, y)	((u64)(x) * (u64)y)
 
-		{
-			unsigned lxm = xm;
-			unsigned hxm = xm >> 32;
-			unsigned lym = ym;
-			unsigned hym = ym >> 32;
-			u64 lrm;
-			u64 hrm;
-
-			lrm = DPXMULT(lxm, lym);
-			hrm = DPXMULT(hxm, hym);
-
-			{
-				u64 t = DPXMULT(lxm, hym);
-				{
-					u64 at =
-					    lrm + (t << 32);
-					hrm += at < lrm;
-					lrm = at;
-				}
-				hrm = hrm + (t >> 32);
-			}
-
-			{
-				u64 t = DPXMULT(hxm, lym);
-				{
-					u64 at =
-					    lrm + (t << 32);
-					hrm += at < lrm;
-					lrm = at;
-				}
-				hrm = hrm + (t >> 32);
-			}
-			rm = hrm | (lrm != 0);
-		}
-
-		/*
-		 * sticky shift down to normal rounding precision
-		 */
-		if ((s64) rm < 0) {
-			rm =
-			    (rm >> (64 - (DP_MBITS + 1 + 3))) |
-			    ((rm << (DP_MBITS + 1 + 3)) != 0);
+	lxm = xm;
+	hxm = xm >> 32;
+	lym = ym;
+	hym = ym >> 32;
+
+	lrm = DPXMULT(lxm, lym);
+	hrm = DPXMULT(hxm, hym);
+
+	t = DPXMULT(lxm, hym);
+
+	at = lrm + (t << 32);
+	hrm += at < lrm;
+	lrm = at;
+
+	hrm = hrm + (t >> 32);
+
+	t = DPXMULT(hxm, lym);
+
+	at = lrm + (t << 32);
+	hrm += at < lrm;
+	lrm = at;
+
+	hrm = hrm + (t >> 32);
+
+	rm = hrm | (lrm != 0);
+
+	/*
+	 * Sticky shift down to normal rounding precision.
+	 */
+	if ((s64) rm < 0) {
+		rm = (rm >> (64 - (DP_FBITS + 1 + 3))) |
+		     ((rm << (DP_FBITS + 1 + 3)) != 0);
 			re++;
-		} else {
-			rm =
-			    (rm >> (64 - (DP_MBITS + 1 + 3 + 1))) |
-			    ((rm << (DP_MBITS + 1 + 3 + 1)) != 0);
-		}
-		assert(rm & (DP_HIDDEN_BIT << 3));
-		DPNORMRET2(rs, re, rm, "mul", x, y);
+	} else {
+		rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) |
+		     ((rm << (DP_FBITS + 1 + 3 + 1)) != 0);
 	}
+	assert(rm & (DP_HIDDEN_BIT << 3));
+
+	return ieee754dp_format(rs, re, rm);
 }
diff --git a/arch/mips/math-emu/dp_scalb.c b/arch/mips/math-emu/dp_scalb.c
deleted file mode 100644
index 6f5df438dda..00000000000
--- a/arch/mips/math-emu/dp_scalb.c
+++ /dev/null
@@ -1,57 +0,0 @@
-/* IEEE754 floating point arithmetic
- * double precision: common utilities
- */
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-
-#include "ieee754dp.h"
-
-ieee754dp ieee754dp_scalb(ieee754dp x, int n)
-{
-	COMPXDP;
-
-	CLEARCX;
-
-	EXPLODEXDP;
-
-	switch (xc) {
-	case IEEE754_CLASS_SNAN:
-		return ieee754dp_nanxcpt(x, "scalb", x, n);
-	case IEEE754_CLASS_QNAN:
-	case IEEE754_CLASS_INF:
-	case IEEE754_CLASS_ZERO:
-		return x;
-	case IEEE754_CLASS_DNORM:
-		DPDNORMX;
-		break;
-	case IEEE754_CLASS_NORM:
-		break;
-	}
-	DPNORMRET2(xs, xe + n, xm << 3, "scalb", x, n);
-}
-
-
-ieee754dp ieee754dp_ldexp(ieee754dp x, int n)
-{
-	return ieee754dp_scalb(x, n);
-}
diff --git a/arch/mips/math-emu/dp_simple.c b/arch/mips/math-emu/dp_simple.c
index 79ce2673a71..bccbe90efce 100644
--- a/arch/mips/math-emu/dp_simple.c
+++ b/arch/mips/math-emu/dp_simple.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,33 +16,17 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
-int ieee754dp_finite(ieee754dp x)
-{
-	return DPBEXP(x) != DP_EMAX + 1 + DP_EBIAS;
-}
-
-ieee754dp ieee754dp_copysign(ieee754dp x, ieee754dp y)
-{
-	CLEARCX;
-	DPSIGN(x) = DPSIGN(y);
-	return x;
-}
-
-
-ieee754dp ieee754dp_neg(ieee754dp x)
+union ieee754dp ieee754dp_neg(union ieee754dp x)
 {
 	COMPXDP;
 
 	EXPLODEXDP;
-	CLEARCX;
+	ieee754_clearcx();
 	FLUSHXDP;
 
 	/*
@@ -55,30 +37,29 @@ ieee754dp ieee754dp_neg(ieee754dp x)
 	DPSIGN(x) ^= 1;
 
 	if (xc == IEEE754_CLASS_SNAN) {
-		ieee754dp y = ieee754dp_indef();
-		SETCX(IEEE754_INVALID_OPERATION);
+		union ieee754dp y = ieee754dp_indef();
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
 		DPSIGN(y) = DPSIGN(x);
-		return ieee754dp_nanxcpt(y, "neg");
+		return ieee754dp_nanxcpt(y);
 	}
 
 	return x;
 }
 
-
-ieee754dp ieee754dp_abs(ieee754dp x)
+union ieee754dp ieee754dp_abs(union ieee754dp x)
 {
 	COMPXDP;
 
 	EXPLODEXDP;
-	CLEARCX;
+	ieee754_clearcx();
 	FLUSHXDP;
 
 	/* Clear sign ALWAYS, irrespective of NaN */
 	DPSIGN(x) = 0;
 
 	if (xc == IEEE754_CLASS_SNAN) {
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef(), "abs");
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_nanxcpt(ieee754dp_indef());
 	}
 
 	return x;
diff --git a/arch/mips/math-emu/dp_sqrt.c b/arch/mips/math-emu/dp_sqrt.c
index b874d60a942..041bbb6124b 100644
--- a/arch/mips/math-emu/dp_sqrt.c
+++ b/arch/mips/math-emu/dp_sqrt.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,12 +16,9 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
 static const unsigned table[] = {
@@ -34,44 +29,49 @@ static const unsigned table[] = {
 	1742, 661, 130
 };
 
-ieee754dp ieee754dp_sqrt(ieee754dp x)
+union ieee754dp ieee754dp_sqrt(union ieee754dp x)
 {
 	struct _ieee754_csr oldcsr;
-	ieee754dp y, z, t;
+	union ieee754dp y, z, t;
 	unsigned scalx, yh;
 	COMPXDP;
 
 	EXPLODEXDP;
-	CLEARCX;
+	ieee754_clearcx();
 	FLUSHXDP;
 
 	/* x == INF or NAN? */
 	switch (xc) {
 	case IEEE754_CLASS_QNAN:
 		/* sqrt(Nan) = Nan */
-		return ieee754dp_nanxcpt(x, "sqrt");
+		return ieee754dp_nanxcpt(x);
+
 	case IEEE754_CLASS_SNAN:
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef(), "sqrt");
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_nanxcpt(ieee754dp_indef());
+
 	case IEEE754_CLASS_ZERO:
 		/* sqrt(0) = 0 */
 		return x;
+
 	case IEEE754_CLASS_INF:
 		if (xs) {
 			/* sqrt(-Inf) = Nan */
-			SETCX(IEEE754_INVALID_OPERATION);
-			return ieee754dp_nanxcpt(ieee754dp_indef(), "sqrt");
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754dp_nanxcpt(ieee754dp_indef());
 		}
 		/* sqrt(+Inf) = Inf */
 		return x;
+
 	case IEEE754_CLASS_DNORM:
 		DPDNORMX;
 		/* fall through */
+
 	case IEEE754_CLASS_NORM:
 		if (xs) {
 			/* sqrt(-x) = Nan */
-			SETCX(IEEE754_INVALID_OPERATION);
-			return ieee754dp_nanxcpt(ieee754dp_indef(), "sqrt");
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754dp_nanxcpt(ieee754dp_indef());
 		}
 		break;
 	}
@@ -80,7 +80,7 @@ ieee754dp ieee754dp_sqrt(ieee754dp x)
 	oldcsr = ieee754_csr;
 	ieee754_csr.mx &= ~IEEE754_INEXACT;
 	ieee754_csr.sx &= ~IEEE754_INEXACT;
-	ieee754_csr.rm = IEEE754_RN;
+	ieee754_csr.rm = FPU_CSR_RN;
 
 	/* adjust exponent to prevent overflow */
 	scalx = 0;
@@ -110,19 +110,19 @@ ieee754dp ieee754dp_sqrt(ieee754dp x)
 	/* triple to almost 56 sig. bits: y ~= sqrt(x) to within 1 ulp */
 	/* t=y*y; z=t;	pt[n0]+=0x00100000; t+=z; z=(x-z)*y; */
 	z = t = ieee754dp_mul(y, y);
-	t.parts.bexp += 0x001;
+	t.bexp += 0x001;
 	t = ieee754dp_add(t, z);
 	z = ieee754dp_mul(ieee754dp_sub(x, z), y);
 
 	/* t=z/(t+x) ;	pt[n0]+=0x00100000; y+=t; */
 	t = ieee754dp_div(z, ieee754dp_add(t, x));
-	t.parts.bexp += 0x001;
+	t.bexp += 0x001;
 	y = ieee754dp_add(y, t);
 
 	/* twiddle last bit to force y correctly rounded */
 
 	/* set RZ, clear INEX flag */
-	ieee754_csr.rm = IEEE754_RZ;
+	ieee754_csr.rm = FPU_CSR_RZ;
 	ieee754_csr.sx &= ~IEEE754_INEXACT;
 
 	/* t=x/y; ...chopped quotient, possibly inexact */
@@ -139,10 +139,10 @@ ieee754dp ieee754dp_sqrt(ieee754dp x)
 		oldcsr.sx |= IEEE754_INEXACT;
 
 		switch (oldcsr.rm) {
-		case IEEE754_RP:
+		case FPU_CSR_RU:
 			y.bits += 1;
 			/* drop through */
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			t.bits += 1;
 			break;
 		}
@@ -155,7 +155,7 @@ ieee754dp ieee754dp_sqrt(ieee754dp x)
 	}
 
 	/* py[n0]=py[n0]+scalx; ...scale back y */
-	y.parts.bexp += scalx;
+	y.bexp += scalx;
 
 	/* restore rounding mode, possibly set inexact */
 	ieee754_csr = oldcsr;
diff --git a/arch/mips/math-emu/dp_sub.c b/arch/mips/math-emu/dp_sub.c
index 91e0a4b5cbc..7a174029043 100644
--- a/arch/mips/math-emu/dp_sub.c
+++ b/arch/mips/math-emu/dp_sub.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,23 +16,22 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
-ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y)
+union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y)
 {
+	int s;
+
 	COMPXDP;
 	COMPYDP;
 
 	EXPLODEXDP;
 	EXPLODEYDP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXDP;
 	FLUSHYDP;
@@ -51,8 +48,8 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_nanxcpt(ieee754dp_indef(), "sub", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_nanxcpt(ieee754dp_indef());
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -68,14 +65,14 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y)
 		return x;
 
 
-		/* Infinity handling
-		 */
-
+	/*
+	 * Infinity handling
+	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 		if (xs != ys)
 			return x;
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754dp_xcpt(ieee754dp_indef(), "sub", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754dp_indef();
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
@@ -87,15 +84,14 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y)
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 		return x;
 
-		/* Zero handling
-		 */
-
+	/*
+	 * Zero handling
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
 		if (xs != ys)
 			return x;
 		else
-			return ieee754dp_zero(ieee754_csr.rm ==
-					      IEEE754_RD);
+			return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD);
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
@@ -136,15 +132,17 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y)
 	ym <<= 3;
 
 	if (xe > ye) {
-		/* have to shift y fraction right to align
+		/*
+		 * Have to shift y fraction right to align
 		 */
-		int s = xe - ye;
+		s = xe - ye;
 		ym = XDPSRS(ym, s);
 		ye += s;
 	} else if (ye > xe) {
-		/* have to shift x fraction right to align
+		/*
+		 * Have to shift x fraction right to align
 		 */
-		int s = ye - xe;
+		s = ye - xe;
 		xm = XDPSRS(xm, s);
 		xe += s;
 	}
@@ -158,7 +156,7 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y)
 		xe = xe;
 		xs = xs;
 
-		if (xm >> (DP_MBITS + 1 + 3)) { /* carry out */
+		if (xm >> (DP_FBITS + 1 + 3)) { /* carry out */
 			xm = XDPSRS1(xm);	/* shift preserving sticky */
 			xe++;
 		}
@@ -173,7 +171,7 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y)
 			xs = ys;
 		}
 		if (xm == 0) {
-			if (ieee754_csr.rm == IEEE754_RD)
+			if (ieee754_csr.rm == FPU_CSR_RD)
 				return ieee754dp_zero(1);	/* round negative inf. => sign = -1 */
 			else
 				return ieee754dp_zero(0);	/* other round modes   => sign = 1 */
@@ -181,10 +179,11 @@ ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y)
 
 		/* normalize to rounding precision
 		 */
-		while ((xm >> (DP_MBITS + 3)) == 0) {
+		while ((xm >> (DP_FBITS + 3)) == 0) {
 			xm <<= 1;
 			xe--;
 		}
 	}
-	DPNORMRET2(xs, xe, xm, "sub", x, y);
+
+	return ieee754dp_format(xs, xe, xm);
 }
diff --git a/arch/mips/math-emu/dp_tint.c b/arch/mips/math-emu/dp_tint.c
index 0ebe8598b94..6ffc336c530 100644
--- a/arch/mips/math-emu/dp_tint.c
+++ b/arch/mips/math-emu/dp_tint.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,20 +16,21 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
-#include <linux/kernel.h>
 #include "ieee754dp.h"
 
-int ieee754dp_tint(ieee754dp x)
+int ieee754dp_tint(union ieee754dp x)
 {
+	u64 residue;
+	int round;
+	int sticky;
+	int odd;
+
 	COMPXDP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	EXPLODEXDP;
 	FLUSHXDP;
@@ -40,10 +39,12 @@ int ieee754dp_tint(ieee754dp x)
 	case IEEE754_CLASS_SNAN:
 	case IEEE754_CLASS_QNAN:
 	case IEEE754_CLASS_INF:
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754si_xcpt(ieee754si_indef(), "dp_tint", x);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754si_indef();
+
 	case IEEE754_CLASS_ZERO:
 		return 0;
+
 	case IEEE754_CLASS_DNORM:
 	case IEEE754_CLASS_NORM:
 		break;
@@ -51,44 +52,39 @@ int ieee754dp_tint(ieee754dp x)
 	if (xe > 31) {
 		/* Set invalid. We will only use overflow for floating
 		   point overflow */
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754si_xcpt(ieee754si_indef(), "dp_tint", x);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754si_indef();
 	}
 	/* oh gawd */
-	if (xe > DP_MBITS) {
-		xm <<= xe - DP_MBITS;
-	} else if (xe < DP_MBITS) {
-		u64 residue;
-		int round;
-		int sticky;
-		int odd;
-
+	if (xe > DP_FBITS) {
+		xm <<= xe - DP_FBITS;
+	} else if (xe < DP_FBITS) {
 		if (xe < -1) {
 			residue = xm;
 			round = 0;
 			sticky = residue != 0;
 			xm = 0;
 		} else {
-			residue = xm << (64 - DP_MBITS + xe);
+			residue = xm << (64 - DP_FBITS + xe);
 			round = (residue >> 63) != 0;
 			sticky = (residue << 1) != 0;
-			xm >>= DP_MBITS - xe;
+			xm >>= DP_FBITS - xe;
 		}
 		/* Note: At this point upper 32 bits of xm are guaranteed
 		   to be zero */
 		odd = (xm & 0x1) != 0x0;
 		switch (ieee754_csr.rm) {
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			if (round && (sticky || odd))
 				xm++;
 			break;
-		case IEEE754_RZ:
+		case FPU_CSR_RZ:
 			break;
-		case IEEE754_RU:	/* toward +Infinity */
+		case FPU_CSR_RU:	/* toward +Infinity */
 			if ((round || sticky) && !xs)
 				xm++;
 			break;
-		case IEEE754_RD:	/* toward -Infinity */
+		case FPU_CSR_RD:	/* toward -Infinity */
 			if ((round || sticky) && xs)
 				xm++;
 			break;
@@ -96,27 +92,14 @@ int ieee754dp_tint(ieee754dp x)
 		/* look for valid corner case 0x80000000 */
 		if ((xm >> 31) != 0 && (xs == 0 || xm != 0x80000000)) {
 			/* This can happen after rounding */
-			SETCX(IEEE754_INVALID_OPERATION);
-			return ieee754si_xcpt(ieee754si_indef(), "dp_tint", x);
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754si_indef();
 		}
 		if (round || sticky)
-			SETCX(IEEE754_INEXACT);
+			ieee754_setcx(IEEE754_INEXACT);
 	}
 	if (xs)
 		return -xm;
 	else
 		return xm;
 }
-
-
-unsigned int ieee754dp_tuns(ieee754dp x)
-{
-	ieee754dp hb = ieee754dp_1e31();
-
-	/* what if x < 0 ?? */
-	if (ieee754dp_lt(x, hb))
-		return (unsigned) ieee754dp_tint(x);
-
-	return (unsigned) ieee754dp_tint(ieee754dp_sub(x, hb)) |
-	    ((unsigned) 1 << 31);
-}
diff --git a/arch/mips/math-emu/dp_tlong.c b/arch/mips/math-emu/dp_tlong.c
index 133ce2ba001..9cdc145b75e 100644
--- a/arch/mips/math-emu/dp_tlong.c
+++ b/arch/mips/math-emu/dp_tlong.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,19 +16,21 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754dp.h"
 
-s64 ieee754dp_tlong(ieee754dp x)
+s64 ieee754dp_tlong(union ieee754dp x)
 {
+	u64 residue;
+	int round;
+	int sticky;
+	int odd;
+
 	COMPXDP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	EXPLODEXDP;
 	FLUSHXDP;
@@ -39,10 +39,12 @@ s64 ieee754dp_tlong(ieee754dp x)
 	case IEEE754_CLASS_SNAN:
 	case IEEE754_CLASS_QNAN:
 	case IEEE754_CLASS_INF:
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754di_xcpt(ieee754di_indef(), "dp_tlong", x);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754di_indef();
+
 	case IEEE754_CLASS_ZERO:
 		return 0;
+
 	case IEEE754_CLASS_DNORM:
 	case IEEE754_CLASS_NORM:
 		break;
@@ -53,18 +55,13 @@ s64 ieee754dp_tlong(ieee754dp x)
 			return -0x8000000000000000LL;
 		/* Set invalid. We will only use overflow for floating
 		   point overflow */
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754di_xcpt(ieee754di_indef(), "dp_tlong", x);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754di_indef();
 	}
 	/* oh gawd */
-	if (xe > DP_MBITS) {
-		xm <<= xe - DP_MBITS;
-	} else if (xe < DP_MBITS) {
-		u64 residue;
-		int round;
-		int sticky;
-		int odd;
-
+	if (xe > DP_FBITS) {
+		xm <<= xe - DP_FBITS;
+	} else if (xe < DP_FBITS) {
 		if (xe < -1) {
 			residue = xm;
 			round = 0;
@@ -75,51 +72,38 @@ s64 ieee754dp_tlong(ieee754dp x)
 			* so we do it in two steps. Be aware that xe
 			* may be -1 */
 			residue = xm << (xe + 1);
-			residue <<= 63 - DP_MBITS;
+			residue <<= 63 - DP_FBITS;
 			round = (residue >> 63) != 0;
 			sticky = (residue << 1) != 0;
-			xm >>= DP_MBITS - xe;
+			xm >>= DP_FBITS - xe;
 		}
 		odd = (xm & 0x1) != 0x0;
 		switch (ieee754_csr.rm) {
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			if (round && (sticky || odd))
 				xm++;
 			break;
-		case IEEE754_RZ:
+		case FPU_CSR_RZ:
 			break;
-		case IEEE754_RU:	/* toward +Infinity */
+		case FPU_CSR_RU:	/* toward +Infinity */
 			if ((round || sticky) && !xs)
 				xm++;
 			break;
-		case IEEE754_RD:	/* toward -Infinity */
+		case FPU_CSR_RD:	/* toward -Infinity */
 			if ((round || sticky) && xs)
 				xm++;
 			break;
 		}
 		if ((xm >> 63) != 0) {
 			/* This can happen after rounding */
-			SETCX(IEEE754_INVALID_OPERATION);
-			return ieee754di_xcpt(ieee754di_indef(), "dp_tlong", x);
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754di_indef();
 		}
 		if (round || sticky)
-			SETCX(IEEE754_INEXACT);
+			ieee754_setcx(IEEE754_INEXACT);
 	}
 	if (xs)
 		return -xm;
 	else
 		return xm;
 }
-
-
-u64 ieee754dp_tulong(ieee754dp x)
-{
-	ieee754dp hb = ieee754dp_1e63();
-
-	/* what if x < 0 ?? */
-	if (ieee754dp_lt(x, hb))
-		return (u64) ieee754dp_tlong(x);
-
-	return (u64) ieee754dp_tlong(ieee754dp_sub(x, hb)) |
-	    (1ULL << 63);
-}
diff --git a/arch/mips/math-emu/dsemul.c b/arch/mips/math-emu/dsemul.c
index 7ea622ab8da..4f514f3724c 100644
--- a/arch/mips/math-emu/dsemul.c
+++ b/arch/mips/math-emu/dsemul.c
@@ -1,30 +1,12 @@
-#include <linux/compiler.h>
-#include <linux/mm.h>
-#include <linux/signal.h>
-#include <linux/smp.h>
-
-#include <asm/asm.h>
-#include <asm/bootinfo.h>
-#include <asm/byteorder.h>
-#include <asm/cpu.h>
-#include <asm/inst.h>
-#include <asm/processor.h>
-#include <asm/uaccess.h>
 #include <asm/branch.h>
-#include <asm/mipsregs.h>
 #include <asm/cacheflush.h>
-
 #include <asm/fpu_emulator.h>
+#include <asm/inst.h>
+#include <asm/mipsregs.h>
+#include <asm/uaccess.h>
 
 #include "ieee754.h"
 
-/* Strap kernel emulator for full MIPS IV emulation */
-
-#ifdef __mips
-#undef __mips
-#endif
-#define __mips 4
-
 /*
  * Emulate the arbritrary instruction ir at xcp->cp0_epc.  Required when
  * we have to emulate the instruction in a COP1 branch delay slot.  Do
@@ -59,13 +41,11 @@ int mips_dsemul(struct pt_regs *regs, mips_instruction ir, unsigned long cpc)
 		(ir == 0)) {
 		/* NOP is easy */
 		regs->cp0_epc = cpc;
-		regs->cp0_cause &= ~CAUSEF_BD;
+		clear_delay_slot(regs);
 		return 0;
 	}
-#ifdef DSEMUL_TRACE
-	printk("dsemul %lx %lx\n", regs->cp0_epc, cpc);
 
-#endif
+	pr_debug("dsemul %lx %lx\n", regs->cp0_epc, cpc);
 
 	/*
 	 * The strategy is to push the instruction onto the user stack
@@ -167,9 +147,8 @@ int do_dsemulret(struct pt_regs *xcp)
 	 * emulating the branch delay instruction.
 	 */
 
-#ifdef DSEMUL_TRACE
-	printk("dsemulret\n");
-#endif
+	pr_debug("dsemulret\n");
+
 	if (__get_user(epc, &fr->epc)) {		/* Saved EPC */
 		/* This is not a good situation to be in */
 		force_sig(SIGBUS, current);
diff --git a/arch/mips/math-emu/ieee754.c b/arch/mips/math-emu/ieee754.c
index 0015cf1989d..8e97acbbe22 100644
--- a/arch/mips/math-emu/ieee754.c
+++ b/arch/mips/math-emu/ieee754.c
@@ -10,8 +10,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -23,105 +21,74 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
+#include <linux/compiler.h>
 
-#include "ieee754int.h"
+#include "ieee754.h"
 #include "ieee754sp.h"
 #include "ieee754dp.h"
 
-#define DP_EBIAS	1023
-#define DP_EMIN		(-1022)
-#define DP_EMAX		1023
-
-#define SP_EBIAS	127
-#define SP_EMIN		(-126)
-#define SP_EMAX		127
-
-/* special constants
-*/
-
-
-#if (defined(BYTE_ORDER) && BYTE_ORDER == LITTLE_ENDIAN) || defined(__MIPSEL__)
-#define SPSTR(s, b, m) {m, b, s}
-#define DPSTR(s, b, mh, ml) {ml, mh, b, s}
-#endif
+/*
+ * Special constants
+ */
 
-#ifdef __MIPSEB__
-#define SPSTR(s, b, m) {s, b, m}
-#define DPSTR(s, b, mh, ml) {s, b, mh, ml}
-#endif
+/*
+ * Older GCC requires the inner braces for initialization of union ieee754dp's
+ * anonymous struct member.  Without an error will result.
+ */
+#define xPCNST(s, b, m, ebias)						\
+{									\
+	{								\
+		.sign	= (s),						\
+		.bexp	= (b) + ebias,					\
+		.mant	= (m)						\
+	}								\
+}
 
-const struct ieee754dp_konst __ieee754dp_spcvals[] = {
-	DPSTR(0, DP_EMIN - 1 + DP_EBIAS, 0, 0), /* + zero   */
-	DPSTR(1, DP_EMIN - 1 + DP_EBIAS, 0, 0), /* - zero   */
-	DPSTR(0, DP_EBIAS, 0, 0),	/* + 1.0   */
-	DPSTR(1, DP_EBIAS, 0, 0),	/* - 1.0   */
-	DPSTR(0, 3 + DP_EBIAS, 0x40000, 0),	/* + 10.0   */
-	DPSTR(1, 3 + DP_EBIAS, 0x40000, 0),	/* - 10.0   */
-	DPSTR(0, DP_EMAX + 1 + DP_EBIAS, 0, 0), /* + infinity */
-	DPSTR(1, DP_EMAX + 1 + DP_EBIAS, 0, 0), /* - infinity */
-	DPSTR(0, DP_EMAX+1+DP_EBIAS, 0x7FFFF, 0xFFFFFFFF), /* + indef quiet Nan */
-	DPSTR(0, DP_EMAX + DP_EBIAS, 0xFFFFF, 0xFFFFFFFF),	/* + max */
-	DPSTR(1, DP_EMAX + DP_EBIAS, 0xFFFFF, 0xFFFFFFFF),	/* - max */
-	DPSTR(0, DP_EMIN + DP_EBIAS, 0, 0),	/* + min normal */
-	DPSTR(1, DP_EMIN + DP_EBIAS, 0, 0),	/* - min normal */
-	DPSTR(0, DP_EMIN - 1 + DP_EBIAS, 0, 1), /* + min denormal */
-	DPSTR(1, DP_EMIN - 1 + DP_EBIAS, 0, 1), /* - min denormal */
-	DPSTR(0, 31 + DP_EBIAS, 0, 0),	/* + 1.0e31 */
-	DPSTR(0, 63 + DP_EBIAS, 0, 0),	/* + 1.0e63 */
-};
+#define DPCNST(s, b, m)							\
+	xPCNST(s, b, m, DP_EBIAS)
 
-const struct ieee754sp_konst __ieee754sp_spcvals[] = {
-	SPSTR(0, SP_EMIN - 1 + SP_EBIAS, 0),	/* + zero   */
-	SPSTR(1, SP_EMIN - 1 + SP_EBIAS, 0),	/* - zero   */
-	SPSTR(0, SP_EBIAS, 0),	/* + 1.0   */
-	SPSTR(1, SP_EBIAS, 0),	/* - 1.0   */
-	SPSTR(0, 3 + SP_EBIAS, 0x200000),	/* + 10.0   */
-	SPSTR(1, 3 + SP_EBIAS, 0x200000),	/* - 10.0   */
-	SPSTR(0, SP_EMAX + 1 + SP_EBIAS, 0),	/* + infinity */
-	SPSTR(1, SP_EMAX + 1 + SP_EBIAS, 0),	/* - infinity */
-	SPSTR(0, SP_EMAX+1+SP_EBIAS, 0x3FFFFF),	    /* + indef quiet Nan  */
-	SPSTR(0, SP_EMAX + SP_EBIAS, 0x7FFFFF), /* + max normal */
-	SPSTR(1, SP_EMAX + SP_EBIAS, 0x7FFFFF), /* - max normal */
-	SPSTR(0, SP_EMIN + SP_EBIAS, 0),	/* + min normal */
-	SPSTR(1, SP_EMIN + SP_EBIAS, 0),	/* - min normal */
-	SPSTR(0, SP_EMIN - 1 + SP_EBIAS, 1),	/* + min denormal */
-	SPSTR(1, SP_EMIN - 1 + SP_EBIAS, 1),	/* - min denormal */
-	SPSTR(0, 31 + SP_EBIAS, 0),	/* + 1.0e31 */
-	SPSTR(0, 63 + SP_EBIAS, 0),	/* + 1.0e63 */
+const union ieee754dp __ieee754dp_spcvals[] = {
+	DPCNST(0, DP_EMIN - 1, 0x0000000000000ULL),	/* + zero   */
+	DPCNST(1, DP_EMIN - 1, 0x0000000000000ULL),	/* - zero   */
+	DPCNST(0, 0,	       0x0000000000000ULL),	/* + 1.0   */
+	DPCNST(1, 0,	       0x0000000000000ULL),	/* - 1.0   */
+	DPCNST(0, 3,           0x4000000000000ULL),	/* + 10.0   */
+	DPCNST(1, 3,           0x4000000000000ULL),	/* - 10.0   */
+	DPCNST(0, DP_EMAX + 1, 0x0000000000000ULL),	/* + infinity */
+	DPCNST(1, DP_EMAX + 1, 0x0000000000000ULL),	/* - infinity */
+	DPCNST(0, DP_EMAX + 1, 0x7FFFFFFFFFFFFULL),	/* + indef quiet Nan */
+	DPCNST(0, DP_EMAX,     0xFFFFFFFFFFFFFULL),	/* + max */
+	DPCNST(1, DP_EMAX,     0xFFFFFFFFFFFFFULL),	/* - max */
+	DPCNST(0, DP_EMIN,     0x0000000000000ULL),	/* + min normal */
+	DPCNST(1, DP_EMIN,     0x0000000000000ULL),	/* - min normal */
+	DPCNST(0, DP_EMIN - 1, 0x0000000000001ULL),	/* + min denormal */
+	DPCNST(1, DP_EMIN - 1, 0x0000000000001ULL),	/* - min denormal */
+	DPCNST(0, 31,          0x0000000000000ULL),	/* + 1.0e31 */
+	DPCNST(0, 63,          0x0000000000000ULL),	/* + 1.0e63 */
 };
 
+#define SPCNST(s, b, m)							\
+	xPCNST(s, b, m, SP_EBIAS)
 
-int ieee754si_xcpt(int r, const char *op, ...)
-{
-	struct ieee754xctx ax;
-
-	if (!TSTX())
-		return r;
-	ax.op = op;
-	ax.rt = IEEE754_RT_SI;
-	ax.rv.si = r;
-	va_start(ax.ap, op);
-	ieee754_xcpt(&ax);
-	va_end(ax.ap);
-	return ax.rv.si;
-}
-
-s64 ieee754di_xcpt(s64 r, const char *op, ...)
-{
-	struct ieee754xctx ax;
-
-	if (!TSTX())
-		return r;
-	ax.op = op;
-	ax.rt = IEEE754_RT_DI;
-	ax.rv.di = r;
-	va_start(ax.ap, op);
-	ieee754_xcpt(&ax);
-	va_end(ax.ap);
-	return ax.rv.di;
-}
+const union ieee754sp __ieee754sp_spcvals[] = {
+	SPCNST(0, SP_EMIN - 1, 0x000000),	/* + zero   */
+	SPCNST(1, SP_EMIN - 1, 0x000000),	/* - zero   */
+	SPCNST(0, 0,	       0x000000),	/* + 1.0   */
+	SPCNST(1, 0,	       0x000000),	/* - 1.0   */
+	SPCNST(0, 3,	       0x200000),	/* + 10.0   */
+	SPCNST(1, 3,	       0x200000),	/* - 10.0   */
+	SPCNST(0, SP_EMAX + 1, 0x000000),	/* + infinity */
+	SPCNST(1, SP_EMAX + 1, 0x000000),	/* - infinity */
+	SPCNST(0, SP_EMAX + 1, 0x3FFFFF),	/* + indef quiet Nan  */
+	SPCNST(0, SP_EMAX,     0x7FFFFF),	/* + max normal */
+	SPCNST(1, SP_EMAX,     0x7FFFFF),	/* - max normal */
+	SPCNST(0, SP_EMIN,     0x000000),	/* + min normal */
+	SPCNST(1, SP_EMIN,     0x000000),	/* - min normal */
+	SPCNST(0, SP_EMIN - 1, 0x000001),	/* + min denormal */
+	SPCNST(1, SP_EMIN - 1, 0x000001),	/* - min denormal */
+	SPCNST(0, 31,	       0x000000),	/* + 1.0e31 */
+	SPCNST(0, 63,	       0x000000),	/* + 1.0e63 */
+};
diff --git a/arch/mips/math-emu/ieee754.h b/arch/mips/math-emu/ieee754.h
index 22796e01206..43c4fb522ac 100644
--- a/arch/mips/math-emu/ieee754.h
+++ b/arch/mips/math-emu/ieee754.h
@@ -13,7 +13,7 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  *
  *  Nov 7, 2000
  *  Modification to allow integration with Linux kernel
@@ -24,186 +24,93 @@
 #ifndef __ARCH_MIPS_MATH_EMU_IEEE754_H
 #define __ARCH_MIPS_MATH_EMU_IEEE754_H
 
+#include <linux/compiler.h>
 #include <asm/byteorder.h>
+#include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <asm/bitfield.h>
 
-/*
- * Not very pretty, but the Linux kernel's normal va_list definition
- * does not allow it to be used as a structure element, as it is here.
- */
-#ifndef _STDARG_H
-#include <stdarg.h>
-#endif
-
-#ifdef __LITTLE_ENDIAN
-struct ieee754dp_konst {
-	unsigned mantlo:32;
-	unsigned manthi:20;
-	unsigned bexp:11;
-	unsigned sign:1;
-};
-struct ieee754sp_konst {
-	unsigned mant:23;
-	unsigned bexp:8;
-	unsigned sign:1;
-};
-
-typedef union _ieee754dp {
-	struct ieee754dp_konst oparts;
+union ieee754dp {
 	struct {
-		u64 mant:52;
-		unsigned int bexp:11;
-		unsigned int sign:1;
-	} parts;
+		__BITFIELD_FIELD(unsigned int sign:1,
+		__BITFIELD_FIELD(unsigned int bexp:11,
+		__BITFIELD_FIELD(u64 mant:52,
+		;)))
+	};
 	u64 bits;
-	double d;
-} ieee754dp;
-
-typedef union _ieee754sp {
-	struct ieee754sp_konst parts;
-	float f;
-	u32 bits;
-} ieee754sp;
-#endif
-
-#ifdef __BIG_ENDIAN
-struct ieee754dp_konst {
-	unsigned sign:1;
-	unsigned bexp:11;
-	unsigned manthi:20;
-	unsigned mantlo:32;
 };
 
-typedef union _ieee754dp {
-	struct ieee754dp_konst oparts;
+union ieee754sp {
 	struct {
-		unsigned int sign:1;
-		unsigned int bexp:11;
-		u64 mant:52;
-	} parts;
-	double d;
-	u64 bits;
-} ieee754dp;
-
-struct ieee754sp_konst {
-	unsigned sign:1;
-	unsigned bexp:8;
-	unsigned mant:23;
-};
-
-typedef union _ieee754sp {
-	struct ieee754sp_konst parts;
-	float f;
+		__BITFIELD_FIELD(unsigned sign:1,
+		__BITFIELD_FIELD(unsigned bexp:8,
+		__BITFIELD_FIELD(unsigned mant:23,
+		;)))
+	};
 	u32 bits;
-} ieee754sp;
-#endif
+};
 
 /*
  * single precision (often aka float)
 */
-int ieee754sp_finite(ieee754sp x);
-int ieee754sp_class(ieee754sp x);
-
-ieee754sp ieee754sp_abs(ieee754sp x);
-ieee754sp ieee754sp_neg(ieee754sp x);
-ieee754sp ieee754sp_scalb(ieee754sp x, int);
-ieee754sp ieee754sp_logb(ieee754sp x);
-
-/* x with sign of y */
-ieee754sp ieee754sp_copysign(ieee754sp x, ieee754sp y);
-
-ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y);
-ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y);
-ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y);
-ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y);
-
-ieee754sp ieee754sp_fint(int x);
-ieee754sp ieee754sp_funs(unsigned x);
-ieee754sp ieee754sp_flong(s64 x);
-ieee754sp ieee754sp_fulong(u64 x);
-ieee754sp ieee754sp_fdp(ieee754dp x);
-
-int ieee754sp_tint(ieee754sp x);
-unsigned int ieee754sp_tuns(ieee754sp x);
-s64 ieee754sp_tlong(ieee754sp x);
-u64 ieee754sp_tulong(ieee754sp x);
-
-int ieee754sp_cmp(ieee754sp x, ieee754sp y, int cop, int sig);
-/*
- * basic sp math
- */
-ieee754sp ieee754sp_modf(ieee754sp x, ieee754sp * ip);
-ieee754sp ieee754sp_frexp(ieee754sp x, int *exp);
-ieee754sp ieee754sp_ldexp(ieee754sp x, int exp);
+int ieee754sp_class(union ieee754sp x);
 
-ieee754sp ieee754sp_ceil(ieee754sp x);
-ieee754sp ieee754sp_floor(ieee754sp x);
-ieee754sp ieee754sp_trunc(ieee754sp x);
+union ieee754sp ieee754sp_abs(union ieee754sp x);
+union ieee754sp ieee754sp_neg(union ieee754sp x);
 
-ieee754sp ieee754sp_sqrt(ieee754sp x);
+union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y);
+union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y);
+union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y);
+union ieee754sp ieee754sp_div(union ieee754sp x, union ieee754sp y);
 
-/*
- * double precision (often aka double)
-*/
-int ieee754dp_finite(ieee754dp x);
-int ieee754dp_class(ieee754dp x);
+union ieee754sp ieee754sp_fint(int x);
+union ieee754sp ieee754sp_flong(s64 x);
+union ieee754sp ieee754sp_fdp(union ieee754dp x);
 
-/* x with sign of y */
-ieee754dp ieee754dp_copysign(ieee754dp x, ieee754dp y);
+int ieee754sp_tint(union ieee754sp x);
+s64 ieee754sp_tlong(union ieee754sp x);
 
-ieee754dp ieee754dp_add(ieee754dp x, ieee754dp y);
-ieee754dp ieee754dp_sub(ieee754dp x, ieee754dp y);
-ieee754dp ieee754dp_mul(ieee754dp x, ieee754dp y);
-ieee754dp ieee754dp_div(ieee754dp x, ieee754dp y);
+int ieee754sp_cmp(union ieee754sp x, union ieee754sp y, int cop, int sig);
 
-ieee754dp ieee754dp_abs(ieee754dp x);
-ieee754dp ieee754dp_neg(ieee754dp x);
-ieee754dp ieee754dp_scalb(ieee754dp x, int);
+union ieee754sp ieee754sp_sqrt(union ieee754sp x);
 
-/* return exponent as integer in floating point format
- */
-ieee754dp ieee754dp_logb(ieee754dp x);
+/*
+ * double precision (often aka double)
+*/
+int ieee754dp_class(union ieee754dp x);
 
-ieee754dp ieee754dp_fint(int x);
-ieee754dp ieee754dp_funs(unsigned x);
-ieee754dp ieee754dp_flong(s64 x);
-ieee754dp ieee754dp_fulong(u64 x);
-ieee754dp ieee754dp_fsp(ieee754sp x);
+union ieee754dp ieee754dp_add(union ieee754dp x, union ieee754dp y);
+union ieee754dp ieee754dp_sub(union ieee754dp x, union ieee754dp y);
+union ieee754dp ieee754dp_mul(union ieee754dp x, union ieee754dp y);
+union ieee754dp ieee754dp_div(union ieee754dp x, union ieee754dp y);
 
-ieee754dp ieee754dp_ceil(ieee754dp x);
-ieee754dp ieee754dp_floor(ieee754dp x);
-ieee754dp ieee754dp_trunc(ieee754dp x);
+union ieee754dp ieee754dp_abs(union ieee754dp x);
+union ieee754dp ieee754dp_neg(union ieee754dp x);
 
-int ieee754dp_tint(ieee754dp x);
-unsigned int ieee754dp_tuns(ieee754dp x);
-s64 ieee754dp_tlong(ieee754dp x);
-u64 ieee754dp_tulong(ieee754dp x);
+union ieee754dp ieee754dp_fint(int x);
+union ieee754dp ieee754dp_flong(s64 x);
+union ieee754dp ieee754dp_fsp(union ieee754sp x);
 
-int ieee754dp_cmp(ieee754dp x, ieee754dp y, int cop, int sig);
-/*
- * basic sp math
- */
-ieee754dp ieee754dp_modf(ieee754dp x, ieee754dp * ip);
-ieee754dp ieee754dp_frexp(ieee754dp x, int *exp);
-ieee754dp ieee754dp_ldexp(ieee754dp x, int exp);
+int ieee754dp_tint(union ieee754dp x);
+s64 ieee754dp_tlong(union ieee754dp x);
 
-ieee754dp ieee754dp_ceil(ieee754dp x);
-ieee754dp ieee754dp_floor(ieee754dp x);
-ieee754dp ieee754dp_trunc(ieee754dp x);
+int ieee754dp_cmp(union ieee754dp x, union ieee754dp y, int cop, int sig);
 
-ieee754dp ieee754dp_sqrt(ieee754dp x);
+union ieee754dp ieee754dp_sqrt(union ieee754dp x);
 
 
 
 /* 5 types of floating point number
 */
-#define IEEE754_CLASS_NORM	0x00
-#define IEEE754_CLASS_ZERO	0x01
-#define IEEE754_CLASS_DNORM	0x02
-#define IEEE754_CLASS_INF	0x03
-#define IEEE754_CLASS_SNAN	0x04
-#define IEEE754_CLASS_QNAN	0x05
+enum {
+	IEEE754_CLASS_NORM	= 0x00,
+	IEEE754_CLASS_ZERO	= 0x01,
+	IEEE754_CLASS_DNORM	= 0x02,
+	IEEE754_CLASS_INF	= 0x03,
+	IEEE754_CLASS_SNAN	= 0x04,
+	IEEE754_CLASS_QNAN	= 0x05,
+};
 
 /* exception numbers */
 #define IEEE754_INEXACT			0x01
@@ -219,114 +126,84 @@ ieee754dp ieee754dp_sqrt(ieee754dp x);
 #define IEEE754_CGT	0x04
 #define IEEE754_CUN	0x08
 
-/* rounding mode
-*/
-#define IEEE754_RN	0	/* round to nearest */
-#define IEEE754_RZ	1	/* round toward zero  */
-#define IEEE754_RD	2	/* round toward -Infinity */
-#define IEEE754_RU	3	/* round toward +Infinity */
-
-/* other naming */
-#define IEEE754_RM	IEEE754_RD
-#define IEEE754_RP	IEEE754_RU
-
 /* "normal" comparisons
 */
-static inline int ieee754sp_eq(ieee754sp x, ieee754sp y)
+static inline int ieee754sp_eq(union ieee754sp x, union ieee754sp y)
 {
 	return ieee754sp_cmp(x, y, IEEE754_CEQ, 0);
 }
 
-static inline int ieee754sp_ne(ieee754sp x, ieee754sp y)
+static inline int ieee754sp_ne(union ieee754sp x, union ieee754sp y)
 {
 	return ieee754sp_cmp(x, y,
 			     IEEE754_CLT | IEEE754_CGT | IEEE754_CUN, 0);
 }
 
-static inline int ieee754sp_lt(ieee754sp x, ieee754sp y)
+static inline int ieee754sp_lt(union ieee754sp x, union ieee754sp y)
 {
 	return ieee754sp_cmp(x, y, IEEE754_CLT, 0);
 }
 
-static inline int ieee754sp_le(ieee754sp x, ieee754sp y)
+static inline int ieee754sp_le(union ieee754sp x, union ieee754sp y)
 {
 	return ieee754sp_cmp(x, y, IEEE754_CLT | IEEE754_CEQ, 0);
 }
 
-static inline int ieee754sp_gt(ieee754sp x, ieee754sp y)
+static inline int ieee754sp_gt(union ieee754sp x, union ieee754sp y)
 {
 	return ieee754sp_cmp(x, y, IEEE754_CGT, 0);
 }
 
 
-static inline int ieee754sp_ge(ieee754sp x, ieee754sp y)
+static inline int ieee754sp_ge(union ieee754sp x, union ieee754sp y)
 {
 	return ieee754sp_cmp(x, y, IEEE754_CGT | IEEE754_CEQ, 0);
 }
 
-static inline int ieee754dp_eq(ieee754dp x, ieee754dp y)
+static inline int ieee754dp_eq(union ieee754dp x, union ieee754dp y)
 {
 	return ieee754dp_cmp(x, y, IEEE754_CEQ, 0);
 }
 
-static inline int ieee754dp_ne(ieee754dp x, ieee754dp y)
+static inline int ieee754dp_ne(union ieee754dp x, union ieee754dp y)
 {
 	return ieee754dp_cmp(x, y,
 			     IEEE754_CLT | IEEE754_CGT | IEEE754_CUN, 0);
 }
 
-static inline int ieee754dp_lt(ieee754dp x, ieee754dp y)
+static inline int ieee754dp_lt(union ieee754dp x, union ieee754dp y)
 {
 	return ieee754dp_cmp(x, y, IEEE754_CLT, 0);
 }
 
-static inline int ieee754dp_le(ieee754dp x, ieee754dp y)
+static inline int ieee754dp_le(union ieee754dp x, union ieee754dp y)
 {
 	return ieee754dp_cmp(x, y, IEEE754_CLT | IEEE754_CEQ, 0);
 }
 
-static inline int ieee754dp_gt(ieee754dp x, ieee754dp y)
+static inline int ieee754dp_gt(union ieee754dp x, union ieee754dp y)
 {
 	return ieee754dp_cmp(x, y, IEEE754_CGT, 0);
 }
 
-static inline int ieee754dp_ge(ieee754dp x, ieee754dp y)
+static inline int ieee754dp_ge(union ieee754dp x, union ieee754dp y)
 {
 	return ieee754dp_cmp(x, y, IEEE754_CGT | IEEE754_CEQ, 0);
 }
 
-
-/*
- * Like strtod
- */
-ieee754dp ieee754dp_fstr(const char *s, char **endp);
-char *ieee754dp_tstr(ieee754dp x, int prec, int fmt, int af);
-
-
 /*
  * The control status register
  */
 struct _ieee754_csr {
-#ifdef __BIG_ENDIAN
-	unsigned pad0:7;
-	unsigned nod:1;		/* set 1 for no denormalised numbers */
-	unsigned c:1;		/* condition */
-	unsigned pad1:5;
-	unsigned cx:6;		/* exceptions this operation */
-	unsigned mx:5;		/* exception enable  mask */
-	unsigned sx:5;		/* exceptions total */
-	unsigned rm:2;		/* current rounding mode */
-#endif
-#ifdef __LITTLE_ENDIAN
-	unsigned rm:2;		/* current rounding mode */
-	unsigned sx:5;		/* exceptions total */
-	unsigned mx:5;		/* exception enable  mask */
-	unsigned cx:6;		/* exceptions this operation */
-	unsigned pad1:5;
-	unsigned c:1;		/* condition */
-	unsigned nod:1;		/* set 1 for no denormalised numbers */
-	unsigned pad0:7;
-#endif
+	__BITFIELD_FIELD(unsigned pad0:7,
+	__BITFIELD_FIELD(unsigned nod:1,	/* set 1 for no denormalised numbers */
+	__BITFIELD_FIELD(unsigned c:1,		/* condition */
+	__BITFIELD_FIELD(unsigned pad1:5,
+	__BITFIELD_FIELD(unsigned cx:6,		/* exceptions this operation */
+	__BITFIELD_FIELD(unsigned mx:5,		/* exception enable  mask */
+	__BITFIELD_FIELD(unsigned sx:5,		/* exceptions total */
+	__BITFIELD_FIELD(unsigned rm:2,		/* current rounding mode */
+	;))))))))
 };
 #define ieee754_csr (*(struct _ieee754_csr *)(&current->thread.fpu.fcr31))
 
@@ -377,8 +254,8 @@ static inline int ieee754_sxtest(unsigned n)
 }
 
 /* debugging */
-ieee754sp ieee754sp_dump(char *s, ieee754sp x);
-ieee754dp ieee754dp_dump(char *s, ieee754dp x);
+union ieee754sp ieee754sp_dump(char *s, union ieee754sp x);
+union ieee754dp ieee754dp_dump(char *s, union ieee754dp x);
 
 #define IEEE754_SPCVAL_PZERO	0
 #define IEEE754_SPCVAL_NZERO	1
@@ -398,10 +275,10 @@ ieee754dp ieee754dp_dump(char *s, ieee754dp x);
 #define IEEE754_SPCVAL_P1E31	15	/* + 1.0e31 */
 #define IEEE754_SPCVAL_P1E63	16	/* + 1.0e63 */
 
-extern const struct ieee754dp_konst __ieee754dp_spcvals[];
-extern const struct ieee754sp_konst __ieee754sp_spcvals[];
-#define ieee754dp_spcvals ((const ieee754dp *)__ieee754dp_spcvals)
-#define ieee754sp_spcvals ((const ieee754sp *)__ieee754sp_spcvals)
+extern const union ieee754dp __ieee754dp_spcvals[];
+extern const union ieee754sp __ieee754sp_spcvals[];
+#define ieee754dp_spcvals ((const union ieee754dp *)__ieee754dp_spcvals)
+#define ieee754sp_spcvals ((const union ieee754sp *)__ieee754sp_spcvals)
 
 /*
  * Return infinity with given sign
@@ -431,28 +308,15 @@ extern const struct ieee754sp_konst __ieee754sp_spcvals[];
 /*
  * Indefinite integer value
  */
-#define ieee754si_indef()	INT_MAX
-#ifdef LONG_LONG_MAX
-#define ieee754di_indef()	LONG_LONG_MAX
-#else
-#define ieee754di_indef()	((s64)(~0ULL>>1))
-#endif
-
-/* IEEE exception context, passed to handler */
-struct ieee754xctx {
-	const char *op;		/* operation name */
-	int rt;			/* result type */
-	union {
-		ieee754sp sp;	/* single precision */
-		ieee754dp dp;	/* double precision */
-#ifdef IEEE854_XP
-		ieee754xp xp;	/* extended precision */
-#endif
-		int si;		/* standard signed integer (32bits) */
-		s64 di;		/* extended signed integer (64bits) */
-	} rv;			/* default result format implied by op */
-	va_list ap;
-};
+static inline int ieee754si_indef(void)
+{
+	return INT_MAX;
+}
+
+static inline s64 ieee754di_indef(void)
+{
+	return S64_MAX;
+}
 
 /* result types for xctx.rt */
 #define IEEE754_RT_SP	0
@@ -461,8 +325,6 @@ struct ieee754xctx {
 #define IEEE754_RT_SI	3
 #define IEEE754_RT_DI	4
 
-extern void ieee754_xcpt(struct ieee754xctx *xcp);
-
 /* compat */
 #define ieee754dp_fix(x)	ieee754dp_tint(x)
 #define ieee754sp_fix(x)	ieee754sp_tint(x)
diff --git a/arch/mips/math-emu/ieee754d.c b/arch/mips/math-emu/ieee754d.c
index 9599bdd3258..a04e8a7e5ac 100644
--- a/arch/mips/math-emu/ieee754d.c
+++ b/arch/mips/math-emu/ieee754d.c
@@ -16,7 +16,7 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  *
  *  Nov 7, 2000
  *  Modified to build and operate in Linux kernel environment.
@@ -25,38 +25,13 @@
  *  Copyright (C) 2000 MIPS Technologies, Inc. All rights reserved.
  */
 
-#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/printk.h>
 #include "ieee754.h"
+#include "ieee754sp.h"
+#include "ieee754dp.h"
 
-#define DP_EBIAS	1023
-#define DP_EMIN		(-1022)
-#define DP_EMAX		1023
-#define DP_FBITS	52
-
-#define SP_EBIAS	127
-#define SP_EMIN		(-126)
-#define SP_EMAX		127
-#define SP_FBITS	23
-
-#define DP_MBIT(x)	((u64)1 << (x))
-#define DP_HIDDEN_BIT	DP_MBIT(DP_FBITS)
-#define DP_SIGN_BIT	DP_MBIT(63)
-
-
-#define SP_MBIT(x)	((u32)1 << (x))
-#define SP_HIDDEN_BIT	SP_MBIT(SP_FBITS)
-#define SP_SIGN_BIT	SP_MBIT(31)
-
-
-#define SPSIGN(sp)	(sp.parts.sign)
-#define SPBEXP(sp)	(sp.parts.bexp)
-#define SPMANT(sp)	(sp.parts.mant)
-
-#define DPSIGN(dp)	(dp.parts.sign)
-#define DPBEXP(dp)	(dp.parts.bexp)
-#define DPMANT(dp)	(dp.parts.mant)
-
-ieee754dp ieee754dp_dump(char *m, ieee754dp x)
+union ieee754dp ieee754dp_dump(char *m, union ieee754dp x)
 {
 	int i;
 
@@ -96,7 +71,7 @@ ieee754dp ieee754dp_dump(char *m, ieee754dp x)
 	return x;
 }
 
-ieee754sp ieee754sp_dump(char *m, ieee754sp x)
+union ieee754sp ieee754sp_dump(char *m, union ieee754sp x)
 {
 	int i;
 
diff --git a/arch/mips/math-emu/ieee754dp.c b/arch/mips/math-emu/ieee754dp.c
index 068e56be8de..fd134675fc2 100644
--- a/arch/mips/math-emu/ieee754dp.c
+++ b/arch/mips/math-emu/ieee754dp.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,104 +16,68 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
+#include <linux/compiler.h>
 
 #include "ieee754dp.h"
 
-int ieee754dp_class(ieee754dp x)
+int ieee754dp_class(union ieee754dp x)
 {
 	COMPXDP;
 	EXPLODEXDP;
 	return xc;
 }
 
-int ieee754dp_isnan(ieee754dp x)
+int ieee754dp_isnan(union ieee754dp x)
 {
 	return ieee754dp_class(x) >= IEEE754_CLASS_SNAN;
 }
 
-int ieee754dp_issnan(ieee754dp x)
+static inline int ieee754dp_issnan(union ieee754dp x)
 {
 	assert(ieee754dp_isnan(x));
-	return ((DPMANT(x) & DP_MBIT(DP_MBITS-1)) == DP_MBIT(DP_MBITS-1));
+	return ((DPMANT(x) & DP_MBIT(DP_FBITS-1)) == DP_MBIT(DP_FBITS-1));
 }
 
 
-ieee754dp ieee754dp_xcpt(ieee754dp r, const char *op, ...)
-{
-	struct ieee754xctx ax;
-	if (!TSTX())
-		return r;
-
-	ax.op = op;
-	ax.rt = IEEE754_RT_DP;
-	ax.rv.dp = r;
-	va_start(ax.ap, op);
-	ieee754_xcpt(&ax);
-	va_end(ax.ap);
-	return ax.rv.dp;
-}
-
-ieee754dp ieee754dp_nanxcpt(ieee754dp r, const char *op, ...)
+union ieee754dp __cold ieee754dp_nanxcpt(union ieee754dp r)
 {
-	struct ieee754xctx ax;
-
 	assert(ieee754dp_isnan(r));
 
 	if (!ieee754dp_issnan(r))	/* QNAN does not cause invalid op !! */
 		return r;
 
-	if (!SETANDTESTCX(IEEE754_INVALID_OPERATION)) {
+	if (!ieee754_setandtestcx(IEEE754_INVALID_OPERATION)) {
 		/* not enabled convert to a quiet NaN */
-		DPMANT(r) &= (~DP_MBIT(DP_MBITS-1));
+		DPMANT(r) &= (~DP_MBIT(DP_FBITS-1));
 		if (ieee754dp_isnan(r))
 			return r;
 		else
 			return ieee754dp_indef();
 	}
 
-	ax.op = op;
-	ax.rt = 0;
-	ax.rv.dp = r;
-	va_start(ax.ap, op);
-	ieee754_xcpt(&ax);
-	va_end(ax.ap);
-	return ax.rv.dp;
+	return r;
 }
 
-ieee754dp ieee754dp_bestnan(ieee754dp x, ieee754dp y)
-{
-	assert(ieee754dp_isnan(x));
-	assert(ieee754dp_isnan(y));
-
-	if (DPMANT(x) > DPMANT(y))
-		return x;
-	else
-		return y;
-}
-
-
-static u64 get_rounding(int sn, u64 xm)
+static u64 ieee754dp_get_rounding(int sn, u64 xm)
 {
 	/* inexact must round of 3 bits
 	 */
 	if (xm & (DP_MBIT(3) - 1)) {
 		switch (ieee754_csr.rm) {
-		case IEEE754_RZ:
+		case FPU_CSR_RZ:
 			break;
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			xm += 0x3 + ((xm >> 3) & 1);
 			/* xm += (xm&0x8)?0x4:0x3 */
 			break;
-		case IEEE754_RU:	/* toward +Infinity */
+		case FPU_CSR_RU:	/* toward +Infinity */
 			if (!sn)	/* ?? */
 				xm += 0x8;
 			break;
-		case IEEE754_RD:	/* toward -Infinity */
+		case FPU_CSR_RD:	/* toward -Infinity */
 			if (sn) /* ?? */
 				xm += 0x8;
 			break;
@@ -130,11 +92,11 @@ static u64 get_rounding(int sn, u64 xm)
  * xe is an unbiased exponent
  * xm is 3bit extended precision value.
  */
-ieee754dp ieee754dp_format(int sn, int xe, u64 xm)
+union ieee754dp ieee754dp_format(int sn, int xe, u64 xm)
 {
 	assert(xm);		/* we don't gen exact zeros (probably should) */
 
-	assert((xm >> (DP_MBITS + 1 + 3)) == 0);	/* no execess */
+	assert((xm >> (DP_FBITS + 1 + 3)) == 0);	/* no execess */
 	assert(xm & (DP_HIDDEN_BIT << 3));
 
 	if (xe < DP_EMIN) {
@@ -142,32 +104,32 @@ ieee754dp ieee754dp_format(int sn, int xe, u64 xm)
 		int es = DP_EMIN - xe;
 
 		if (ieee754_csr.nod) {
-			SETCX(IEEE754_UNDERFLOW);
-			SETCX(IEEE754_INEXACT);
+			ieee754_setcx(IEEE754_UNDERFLOW);
+			ieee754_setcx(IEEE754_INEXACT);
 
 			switch(ieee754_csr.rm) {
-			case IEEE754_RN:
-			case IEEE754_RZ:
+			case FPU_CSR_RN:
+			case FPU_CSR_RZ:
 				return ieee754dp_zero(sn);
-			case IEEE754_RU:    /* toward +Infinity */
-				if(sn == 0)
+			case FPU_CSR_RU:    /* toward +Infinity */
+				if (sn == 0)
 					return ieee754dp_min(0);
 				else
 					return ieee754dp_zero(1);
-			case IEEE754_RD:    /* toward -Infinity */
-				if(sn == 0)
+			case FPU_CSR_RD:    /* toward -Infinity */
+				if (sn == 0)
 					return ieee754dp_zero(0);
 				else
 					return ieee754dp_min(1);
 			}
 		}
 
-		if (xe == DP_EMIN - 1
-				&& get_rounding(sn, xm) >> (DP_MBITS + 1 + 3))
+		if (xe == DP_EMIN - 1 &&
+		    ieee754dp_get_rounding(sn, xm) >> (DP_FBITS + 1 + 3))
 		{
 			/* Not tiny after rounding */
-			SETCX(IEEE754_INEXACT);
-			xm = get_rounding(sn, xm);
+			ieee754_setcx(IEEE754_INEXACT);
+			xm = ieee754dp_get_rounding(sn, xm);
 			xm >>= 1;
 			/* Clear grs bits */
 			xm &= ~(DP_MBIT(3) - 1);
@@ -183,17 +145,17 @@ ieee754dp ieee754dp_format(int sn, int xe, u64 xm)
 		}
 	}
 	if (xm & (DP_MBIT(3) - 1)) {
-		SETCX(IEEE754_INEXACT);
+		ieee754_setcx(IEEE754_INEXACT);
 		if ((xm & (DP_HIDDEN_BIT << 3)) == 0) {
-			SETCX(IEEE754_UNDERFLOW);
+			ieee754_setcx(IEEE754_UNDERFLOW);
 		}
 
 		/* inexact must round of 3 bits
 		 */
-		xm = get_rounding(sn, xm);
+		xm = ieee754dp_get_rounding(sn, xm);
 		/* adjust exponent for rounding add overflowing
 		 */
-		if (xm >> (DP_MBITS + 3 + 1)) {
+		if (xm >> (DP_FBITS + 3 + 1)) {
 			/* add causes mantissa overflow */
 			xm >>= 1;
 			xe++;
@@ -202,24 +164,24 @@ ieee754dp ieee754dp_format(int sn, int xe, u64 xm)
 	/* strip grs bits */
 	xm >>= 3;
 
-	assert((xm >> (DP_MBITS + 1)) == 0);	/* no execess */
+	assert((xm >> (DP_FBITS + 1)) == 0);	/* no execess */
 	assert(xe >= DP_EMIN);
 
 	if (xe > DP_EMAX) {
-		SETCX(IEEE754_OVERFLOW);
-		SETCX(IEEE754_INEXACT);
+		ieee754_setcx(IEEE754_OVERFLOW);
+		ieee754_setcx(IEEE754_INEXACT);
 		/* -O can be table indexed by (rm,sn) */
 		switch (ieee754_csr.rm) {
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			return ieee754dp_inf(sn);
-		case IEEE754_RZ:
+		case FPU_CSR_RZ:
 			return ieee754dp_max(sn);
-		case IEEE754_RU:	/* toward +Infinity */
+		case FPU_CSR_RU:	/* toward +Infinity */
 			if (sn == 0)
 				return ieee754dp_inf(0);
 			else
 				return ieee754dp_max(1);
-		case IEEE754_RD:	/* toward -Infinity */
+		case FPU_CSR_RD:	/* toward -Infinity */
 			if (sn == 0)
 				return ieee754dp_max(0);
 			else
@@ -232,10 +194,10 @@ ieee754dp ieee754dp_format(int sn, int xe, u64 xm)
 		/* we underflow (tiny/zero) */
 		assert(xe == DP_EMIN);
 		if (ieee754_csr.mx & IEEE754_UNDERFLOW)
-			SETCX(IEEE754_UNDERFLOW);
+			ieee754_setcx(IEEE754_UNDERFLOW);
 		return builddp(sn, DP_EMIN - 1 + DP_EBIAS, xm);
 	} else {
-		assert((xm >> (DP_MBITS + 1)) == 0);	/* no execess */
+		assert((xm >> (DP_FBITS + 1)) == 0);	/* no execess */
 		assert(xm & DP_HIDDEN_BIT);
 
 		return builddp(sn, xe + DP_EBIAS, xm & ~DP_HIDDEN_BIT);
diff --git a/arch/mips/math-emu/ieee754dp.h b/arch/mips/math-emu/ieee754dp.h
index f139c724c59..61fd6fd3135 100644
--- a/arch/mips/math-emu/ieee754dp.h
+++ b/arch/mips/math-emu/ieee754dp.h
@@ -6,8 +6,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -19,64 +17,66 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
+#include <linux/compiler.h>
 
 #include "ieee754int.h"
 
 #define assert(expr) ((void)0)
 
+#define DP_EBIAS	1023
+#define DP_EMIN		(-1022)
+#define DP_EMAX		1023
+#define DP_FBITS	52
+#define DP_MBITS	52
+
+#define DP_MBIT(x)	((u64)1 << (x))
+#define DP_HIDDEN_BIT	DP_MBIT(DP_FBITS)
+#define DP_SIGN_BIT	DP_MBIT(63)
+
+#define DPSIGN(dp)	(dp.sign)
+#define DPBEXP(dp)	(dp.bexp)
+#define DPMANT(dp)	(dp.mant)
+
+static inline int ieee754dp_finite(union ieee754dp x)
+{
+	return DPBEXP(x) != DP_EMAX + 1 + DP_EBIAS;
+}
+
 /* 3bit extended double precision sticky right shift */
 #define XDPSRS(v,rs)	\
-  ((rs > (DP_MBITS+3))?1:((v) >> (rs)) | ((v) << (64-(rs)) != 0))
+	((rs > (DP_FBITS+3))?1:((v) >> (rs)) | ((v) << (64-(rs)) != 0))
 
 #define XDPSRSX1() \
-  (xe++, (xm = (xm >> 1) | (xm & 1)))
+	(xe++, (xm = (xm >> 1) | (xm & 1)))
 
 #define XDPSRS1(v)	\
-  (((v) >> 1) | ((v) & 1))
+	(((v) >> 1) | ((v) & 1))
 
 /* convert denormal to normalized with extended exponent */
 #define DPDNORMx(m,e) \
-  while( (m >> DP_MBITS) == 0) { m <<= 1; e--; }
+	while ((m >> DP_FBITS) == 0) { m <<= 1; e--; }
 #define DPDNORMX	DPDNORMx(xm, xe)
 #define DPDNORMY	DPDNORMx(ym, ye)
 
-static inline ieee754dp builddp(int s, int bx, u64 m)
+static inline union ieee754dp builddp(int s, int bx, u64 m)
 {
-	ieee754dp r;
+	union ieee754dp r;
 
 	assert((s) == 0 || (s) == 1);
 	assert((bx) >= DP_EMIN - 1 + DP_EBIAS
 	       && (bx) <= DP_EMAX + 1 + DP_EBIAS);
-	assert(((m) >> DP_MBITS) == 0);
+	assert(((m) >> DP_FBITS) == 0);
 
-	r.parts.sign = s;
-	r.parts.bexp = bx;
-	r.parts.mant = m;
-	return r;
-}
+	r.sign = s;
+	r.bexp = bx;
+	r.mant = m;
 
-extern int ieee754dp_isnan(ieee754dp);
-extern int ieee754dp_issnan(ieee754dp);
-extern int ieee754si_xcpt(int, const char *, ...);
-extern s64 ieee754di_xcpt(s64, const char *, ...);
-extern ieee754dp ieee754dp_xcpt(ieee754dp, const char *, ...);
-extern ieee754dp ieee754dp_nanxcpt(ieee754dp, const char *, ...);
-extern ieee754dp ieee754dp_bestnan(ieee754dp, ieee754dp);
-extern ieee754dp ieee754dp_format(int, int, u64);
-
-
-#define DPNORMRET2(s, e, m, name, a0, a1) \
-{ \
-    ieee754dp V = ieee754dp_format(s, e, m); \
-    if(TSTX()) \
-      return ieee754dp_xcpt(V, name, a0, a1); \
-    else \
-      return V; \
+	return r;
 }
 
-#define DPNORMRET1(s, e, m, name, a0)  DPNORMRET2(s, e, m, name, a0, a0)
+extern int ieee754dp_isnan(union ieee754dp);
+extern union ieee754dp __cold ieee754dp_nanxcpt(union ieee754dp);
+extern union ieee754dp ieee754dp_format(int, int, u64);
diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h
index 4b6c6fb3530..f0365bb8674 100644
--- a/arch/mips/math-emu/ieee754int.h
+++ b/arch/mips/math-emu/ieee754int.h
@@ -6,8 +6,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -19,146 +17,125 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
-
+#ifndef __IEEE754INT_H
+#define __IEEE754INT_H
 
 #include "ieee754.h"
 
-#define DP_EBIAS	1023
-#define DP_EMIN		(-1022)
-#define DP_EMAX		1023
-#define DP_MBITS	52
-
-#define SP_EBIAS	127
-#define SP_EMIN		(-126)
-#define SP_EMAX		127
-#define SP_MBITS	23
-
-#define DP_MBIT(x)	((u64)1 << (x))
-#define DP_HIDDEN_BIT	DP_MBIT(DP_MBITS)
-#define DP_SIGN_BIT	DP_MBIT(63)
-
-#define SP_MBIT(x)	((u32)1 << (x))
-#define SP_HIDDEN_BIT	SP_MBIT(SP_MBITS)
-#define SP_SIGN_BIT	SP_MBIT(31)
-
-
-#define SPSIGN(sp)	(sp.parts.sign)
-#define SPBEXP(sp)	(sp.parts.bexp)
-#define SPMANT(sp)	(sp.parts.mant)
-
-#define DPSIGN(dp)	(dp.parts.sign)
-#define DPBEXP(dp)	(dp.parts.bexp)
-#define DPMANT(dp)	(dp.parts.mant)
-
 #define CLPAIR(x, y)	((x)*6+(y))
 
-#define CLEARCX \
-  (ieee754_csr.cx = 0)
-
-#define SETCX(x) \
-  (ieee754_csr.cx |= (x), ieee754_csr.sx |= (x))
+static inline void ieee754_clearcx(void)
+{
+	ieee754_csr.cx = 0;
+}
 
-#define SETANDTESTCX(x) \
-  (SETCX(x), ieee754_csr.mx & (x))
+static inline void ieee754_setcx(const unsigned int flags)
+{
+	ieee754_csr.cx |= flags;
+	ieee754_csr.sx |= flags;
+}
 
-#define TSTX()	\
-	(ieee754_csr.cx & ieee754_csr.mx)
+static inline int ieee754_setandtestcx(const unsigned int x)
+{
+	ieee754_setcx(x);
 
+	return ieee754_csr.mx & x;
+}
 
 #define COMPXSP \
-  unsigned xm; int xe; int xs __maybe_unused; int xc
+	unsigned xm; int xe; int xs __maybe_unused; int xc
 
 #define COMPYSP \
-  unsigned ym; int ye; int ys; int yc
-
-#define EXPLODESP(v, vc, vs, ve, vm) \
-{\
-    vs = SPSIGN(v);\
-    ve = SPBEXP(v);\
-    vm = SPMANT(v);\
-    if(ve == SP_EMAX+1+SP_EBIAS){\
-	if(vm == 0)\
-	  vc = IEEE754_CLASS_INF;\
-	else if(vm & SP_MBIT(SP_MBITS-1)) \
-	  vc = IEEE754_CLASS_SNAN;\
-	else \
-	  vc = IEEE754_CLASS_QNAN;\
-    } else if(ve == SP_EMIN-1+SP_EBIAS) {\
-	if(vm) {\
-	    ve = SP_EMIN;\
-	    vc = IEEE754_CLASS_DNORM;\
-	} else\
-	  vc = IEEE754_CLASS_ZERO;\
-    } else {\
-	ve -= SP_EBIAS;\
-	vm |= SP_HIDDEN_BIT;\
-	vc = IEEE754_CLASS_NORM;\
-    }\
+	unsigned ym; int ye; int ys; int yc
+
+#define EXPLODESP(v, vc, vs, ve, vm)					\
+{									\
+	vs = SPSIGN(v);							\
+	ve = SPBEXP(v);							\
+	vm = SPMANT(v);							\
+	if (ve == SP_EMAX+1+SP_EBIAS) {					\
+		if (vm == 0)						\
+			vc = IEEE754_CLASS_INF;				\
+		else if (vm & SP_MBIT(SP_FBITS-1))			\
+			vc = IEEE754_CLASS_SNAN;			\
+	else								\
+		vc = IEEE754_CLASS_QNAN;				\
+	} else if (ve == SP_EMIN-1+SP_EBIAS) {				\
+		if (vm) {						\
+			ve = SP_EMIN;					\
+			vc = IEEE754_CLASS_DNORM;			\
+		} else							\
+			vc = IEEE754_CLASS_ZERO;			\
+	} else {							\
+		ve -= SP_EBIAS;						\
+		vm |= SP_HIDDEN_BIT;					\
+		vc = IEEE754_CLASS_NORM;				\
+	}								\
 }
 #define EXPLODEXSP EXPLODESP(x, xc, xs, xe, xm)
 #define EXPLODEYSP EXPLODESP(y, yc, ys, ye, ym)
 
 
 #define COMPXDP \
-u64 xm; int xe; int xs __maybe_unused; int xc
+	u64 xm; int xe; int xs __maybe_unused; int xc
 
 #define COMPYDP \
-u64 ym; int ye; int ys; int yc
-
-#define EXPLODEDP(v, vc, vs, ve, vm) \
-{\
-    vm = DPMANT(v);\
-    vs = DPSIGN(v);\
-    ve = DPBEXP(v);\
-    if(ve == DP_EMAX+1+DP_EBIAS){\
-	if(vm == 0)\
-	  vc = IEEE754_CLASS_INF;\
-	else if(vm & DP_MBIT(DP_MBITS-1)) \
-	  vc = IEEE754_CLASS_SNAN;\
-	else \
-	  vc = IEEE754_CLASS_QNAN;\
-    } else if(ve == DP_EMIN-1+DP_EBIAS) {\
-	if(vm) {\
-	    ve = DP_EMIN;\
-	    vc = IEEE754_CLASS_DNORM;\
-	} else\
-	  vc = IEEE754_CLASS_ZERO;\
-    } else {\
-	ve -= DP_EBIAS;\
-	vm |= DP_HIDDEN_BIT;\
-	vc = IEEE754_CLASS_NORM;\
-    }\
+	u64 ym; int ye; int ys; int yc
+
+#define EXPLODEDP(v, vc, vs, ve, vm)					\
+{									\
+	vm = DPMANT(v);							\
+	vs = DPSIGN(v);							\
+	ve = DPBEXP(v);							\
+	if (ve == DP_EMAX+1+DP_EBIAS) {					\
+		if (vm == 0)						\
+			vc = IEEE754_CLASS_INF;				\
+		else if (vm & DP_MBIT(DP_FBITS-1))			\
+			vc = IEEE754_CLASS_SNAN;			\
+		else							\
+			vc = IEEE754_CLASS_QNAN;			\
+	} else if (ve == DP_EMIN-1+DP_EBIAS) {				\
+		if (vm) {						\
+			ve = DP_EMIN;					\
+			vc = IEEE754_CLASS_DNORM;			\
+	} else								\
+		vc = IEEE754_CLASS_ZERO;				\
+	} else {							\
+		ve -= DP_EBIAS;						\
+		vm |= DP_HIDDEN_BIT;					\
+		vc = IEEE754_CLASS_NORM;				\
+	}								\
 }
 #define EXPLODEXDP EXPLODEDP(x, xc, xs, xe, xm)
 #define EXPLODEYDP EXPLODEDP(y, yc, ys, ye, ym)
 
-#define FLUSHDP(v, vc, vs, ve, vm) \
-	if(vc==IEEE754_CLASS_DNORM) {\
-	    if(ieee754_csr.nod) {\
-		SETCX(IEEE754_INEXACT);\
-		vc = IEEE754_CLASS_ZERO;\
-		ve = DP_EMIN-1+DP_EBIAS;\
-		vm = 0;\
-		v = ieee754dp_zero(vs);\
-	    }\
+#define FLUSHDP(v, vc, vs, ve, vm)					\
+	if (vc==IEEE754_CLASS_DNORM) {					\
+		if (ieee754_csr.nod) {					\
+			ieee754_setcx(IEEE754_INEXACT);			\
+			vc = IEEE754_CLASS_ZERO;			\
+			ve = DP_EMIN-1+DP_EBIAS;			\
+			vm = 0;						\
+			v = ieee754dp_zero(vs);				\
+		}							\
 	}
 
-#define FLUSHSP(v, vc, vs, ve, vm) \
-	if(vc==IEEE754_CLASS_DNORM) {\
-	    if(ieee754_csr.nod) {\
-		SETCX(IEEE754_INEXACT);\
-		vc = IEEE754_CLASS_ZERO;\
-		ve = SP_EMIN-1+SP_EBIAS;\
-		vm = 0;\
-		v = ieee754sp_zero(vs);\
-	    }\
+#define FLUSHSP(v, vc, vs, ve, vm)					\
+	if (vc==IEEE754_CLASS_DNORM) {					\
+		if (ieee754_csr.nod) {					\
+			ieee754_setcx(IEEE754_INEXACT);			\
+			vc = IEEE754_CLASS_ZERO;			\
+			ve = SP_EMIN-1+SP_EBIAS;			\
+			vm = 0;						\
+			v = ieee754sp_zero(vs);				\
+		}							\
 	}
 
 #define FLUSHXDP FLUSHDP(x, xc, xs, xe, xm)
 #define FLUSHYDP FLUSHDP(y, yc, ys, ye, ym)
 #define FLUSHXSP FLUSHSP(x, xc, xs, xe, xm)
 #define FLUSHYSP FLUSHSP(y, yc, ys, ye, ym)
+
+#endif /* __IEEE754INT_H  */
diff --git a/arch/mips/math-emu/ieee754m.c b/arch/mips/math-emu/ieee754m.c
deleted file mode 100644
index 24190f3c9dd..00000000000
--- a/arch/mips/math-emu/ieee754m.c
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * floor, trunc, ceil
- */
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-
-#include "ieee754.h"
-
-ieee754dp ieee754dp_floor(ieee754dp x)
-{
-	ieee754dp i;
-
-	if (ieee754dp_lt(ieee754dp_modf(x, &i), ieee754dp_zero(0)))
-		return ieee754dp_sub(i, ieee754dp_one(0));
-	else
-		return i;
-}
-
-ieee754dp ieee754dp_ceil(ieee754dp x)
-{
-	ieee754dp i;
-
-	if (ieee754dp_gt(ieee754dp_modf(x, &i), ieee754dp_zero(0)))
-		return ieee754dp_add(i, ieee754dp_one(0));
-	else
-		return i;
-}
-
-ieee754dp ieee754dp_trunc(ieee754dp x)
-{
-	ieee754dp i;
-
-	(void) ieee754dp_modf(x, &i);
-	return i;
-}
diff --git a/arch/mips/math-emu/ieee754sp.c b/arch/mips/math-emu/ieee754sp.c
index 15d1e36cfe6..d348efe9144 100644
--- a/arch/mips/math-emu/ieee754sp.c
+++ b/arch/mips/math-emu/ieee754sp.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,105 +16,68 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
+#include <linux/compiler.h>
 
 #include "ieee754sp.h"
 
-int ieee754sp_class(ieee754sp x)
+int ieee754sp_class(union ieee754sp x)
 {
 	COMPXSP;
 	EXPLODEXSP;
 	return xc;
 }
 
-int ieee754sp_isnan(ieee754sp x)
+int ieee754sp_isnan(union ieee754sp x)
 {
 	return ieee754sp_class(x) >= IEEE754_CLASS_SNAN;
 }
 
-int ieee754sp_issnan(ieee754sp x)
+static inline int ieee754sp_issnan(union ieee754sp x)
 {
 	assert(ieee754sp_isnan(x));
-	return (SPMANT(x) & SP_MBIT(SP_MBITS-1));
+	return (SPMANT(x) & SP_MBIT(SP_FBITS-1));
 }
 
 
-ieee754sp ieee754sp_xcpt(ieee754sp r, const char *op, ...)
-{
-	struct ieee754xctx ax;
-
-	if (!TSTX())
-		return r;
-
-	ax.op = op;
-	ax.rt = IEEE754_RT_SP;
-	ax.rv.sp = r;
-	va_start(ax.ap, op);
-	ieee754_xcpt(&ax);
-	va_end(ax.ap);
-	return ax.rv.sp;
-}
-
-ieee754sp ieee754sp_nanxcpt(ieee754sp r, const char *op, ...)
+union ieee754sp __cold ieee754sp_nanxcpt(union ieee754sp r)
 {
-	struct ieee754xctx ax;
-
 	assert(ieee754sp_isnan(r));
 
 	if (!ieee754sp_issnan(r))	/* QNAN does not cause invalid op !! */
 		return r;
 
-	if (!SETANDTESTCX(IEEE754_INVALID_OPERATION)) {
+	if (!ieee754_setandtestcx(IEEE754_INVALID_OPERATION)) {
 		/* not enabled convert to a quiet NaN */
-		SPMANT(r) &= (~SP_MBIT(SP_MBITS-1));
+		SPMANT(r) &= (~SP_MBIT(SP_FBITS-1));
 		if (ieee754sp_isnan(r))
 			return r;
 		else
 			return ieee754sp_indef();
 	}
 
-	ax.op = op;
-	ax.rt = 0;
-	ax.rv.sp = r;
-	va_start(ax.ap, op);
-	ieee754_xcpt(&ax);
-	va_end(ax.ap);
-	return ax.rv.sp;
-}
-
-ieee754sp ieee754sp_bestnan(ieee754sp x, ieee754sp y)
-{
-	assert(ieee754sp_isnan(x));
-	assert(ieee754sp_isnan(y));
-
-	if (SPMANT(x) > SPMANT(y))
-		return x;
-	else
-		return y;
+	return r;
 }
 
-
-static unsigned get_rounding(int sn, unsigned xm)
+static unsigned ieee754sp_get_rounding(int sn, unsigned xm)
 {
 	/* inexact must round of 3 bits
 	 */
 	if (xm & (SP_MBIT(3) - 1)) {
 		switch (ieee754_csr.rm) {
-		case IEEE754_RZ:
+		case FPU_CSR_RZ:
 			break;
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			xm += 0x3 + ((xm >> 3) & 1);
 			/* xm += (xm&0x8)?0x4:0x3 */
 			break;
-		case IEEE754_RU:	/* toward +Infinity */
+		case FPU_CSR_RU:	/* toward +Infinity */
 			if (!sn)	/* ?? */
 				xm += 0x8;
 			break;
-		case IEEE754_RD:	/* toward -Infinity */
+		case FPU_CSR_RD:	/* toward -Infinity */
 			if (sn) /* ?? */
 				xm += 0x8;
 			break;
@@ -131,11 +92,11 @@ static unsigned get_rounding(int sn, unsigned xm)
  * xe is an unbiased exponent
  * xm is 3bit extended precision value.
  */
-ieee754sp ieee754sp_format(int sn, int xe, unsigned xm)
+union ieee754sp ieee754sp_format(int sn, int xe, unsigned xm)
 {
 	assert(xm);		/* we don't gen exact zeros (probably should) */
 
-	assert((xm >> (SP_MBITS + 1 + 3)) == 0);	/* no execess */
+	assert((xm >> (SP_FBITS + 1 + 3)) == 0);	/* no execess */
 	assert(xm & (SP_HIDDEN_BIT << 3));
 
 	if (xe < SP_EMIN) {
@@ -143,38 +104,37 @@ ieee754sp ieee754sp_format(int sn, int xe, unsigned xm)
 		int es = SP_EMIN - xe;
 
 		if (ieee754_csr.nod) {
-			SETCX(IEEE754_UNDERFLOW);
-			SETCX(IEEE754_INEXACT);
+			ieee754_setcx(IEEE754_UNDERFLOW);
+			ieee754_setcx(IEEE754_INEXACT);
 
 			switch(ieee754_csr.rm) {
-			case IEEE754_RN:
-			case IEEE754_RZ:
+			case FPU_CSR_RN:
+			case FPU_CSR_RZ:
 				return ieee754sp_zero(sn);
-			case IEEE754_RU:      /* toward +Infinity */
-				if(sn == 0)
+			case FPU_CSR_RU:      /* toward +Infinity */
+				if (sn == 0)
 					return ieee754sp_min(0);
 				else
 					return ieee754sp_zero(1);
-			case IEEE754_RD:      /* toward -Infinity */
-				if(sn == 0)
+			case FPU_CSR_RD:      /* toward -Infinity */
+				if (sn == 0)
 					return ieee754sp_zero(0);
 				else
 					return ieee754sp_min(1);
 			}
 		}
 
-		if (xe == SP_EMIN - 1
-				&& get_rounding(sn, xm) >> (SP_MBITS + 1 + 3))
+		if (xe == SP_EMIN - 1 &&
+		    ieee754sp_get_rounding(sn, xm) >> (SP_FBITS + 1 + 3))
 		{
 			/* Not tiny after rounding */
-			SETCX(IEEE754_INEXACT);
-			xm = get_rounding(sn, xm);
+			ieee754_setcx(IEEE754_INEXACT);
+			xm = ieee754sp_get_rounding(sn, xm);
 			xm >>= 1;
 			/* Clear grs bits */
 			xm &= ~(SP_MBIT(3) - 1);
 			xe++;
-		}
-		else {
+		} else {
 			/* sticky right shift es bits
 			 */
 			SPXSRSXn(es);
@@ -183,17 +143,17 @@ ieee754sp ieee754sp_format(int sn, int xe, unsigned xm)
 		}
 	}
 	if (xm & (SP_MBIT(3) - 1)) {
-		SETCX(IEEE754_INEXACT);
+		ieee754_setcx(IEEE754_INEXACT);
 		if ((xm & (SP_HIDDEN_BIT << 3)) == 0) {
-			SETCX(IEEE754_UNDERFLOW);
+			ieee754_setcx(IEEE754_UNDERFLOW);
 		}
 
 		/* inexact must round of 3 bits
 		 */
-		xm = get_rounding(sn, xm);
+		xm = ieee754sp_get_rounding(sn, xm);
 		/* adjust exponent for rounding add overflowing
 		 */
-		if (xm >> (SP_MBITS + 1 + 3)) {
+		if (xm >> (SP_FBITS + 1 + 3)) {
 			/* add causes mantissa overflow */
 			xm >>= 1;
 			xe++;
@@ -202,24 +162,24 @@ ieee754sp ieee754sp_format(int sn, int xe, unsigned xm)
 	/* strip grs bits */
 	xm >>= 3;
 
-	assert((xm >> (SP_MBITS + 1)) == 0);	/* no execess */
+	assert((xm >> (SP_FBITS + 1)) == 0);	/* no execess */
 	assert(xe >= SP_EMIN);
 
 	if (xe > SP_EMAX) {
-		SETCX(IEEE754_OVERFLOW);
-		SETCX(IEEE754_INEXACT);
+		ieee754_setcx(IEEE754_OVERFLOW);
+		ieee754_setcx(IEEE754_INEXACT);
 		/* -O can be table indexed by (rm,sn) */
 		switch (ieee754_csr.rm) {
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			return ieee754sp_inf(sn);
-		case IEEE754_RZ:
+		case FPU_CSR_RZ:
 			return ieee754sp_max(sn);
-		case IEEE754_RU:	/* toward +Infinity */
+		case FPU_CSR_RU:	/* toward +Infinity */
 			if (sn == 0)
 				return ieee754sp_inf(0);
 			else
 				return ieee754sp_max(1);
-		case IEEE754_RD:	/* toward -Infinity */
+		case FPU_CSR_RD:	/* toward -Infinity */
 			if (sn == 0)
 				return ieee754sp_max(0);
 			else
@@ -232,10 +192,10 @@ ieee754sp ieee754sp_format(int sn, int xe, unsigned xm)
 		/* we underflow (tiny/zero) */
 		assert(xe == SP_EMIN);
 		if (ieee754_csr.mx & IEEE754_UNDERFLOW)
-			SETCX(IEEE754_UNDERFLOW);
+			ieee754_setcx(IEEE754_UNDERFLOW);
 		return buildsp(sn, SP_EMIN - 1 + SP_EBIAS, xm);
 	} else {
-		assert((xm >> (SP_MBITS + 1)) == 0);	/* no execess */
+		assert((xm >> (SP_FBITS + 1)) == 0);	/* no execess */
 		assert(xm & SP_HIDDEN_BIT);
 
 		return buildsp(sn, xe + SP_EBIAS, xm & ~SP_HIDDEN_BIT);
diff --git a/arch/mips/math-emu/ieee754sp.h b/arch/mips/math-emu/ieee754sp.h
index 754fd54649b..ad268e33231 100644
--- a/arch/mips/math-emu/ieee754sp.h
+++ b/arch/mips/math-emu/ieee754sp.h
@@ -6,8 +6,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -19,70 +17,71 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
+#include <linux/compiler.h>
 
 #include "ieee754int.h"
 
 #define assert(expr) ((void)0)
 
+#define SP_EBIAS	127
+#define SP_EMIN		(-126)
+#define SP_EMAX		127
+#define SP_FBITS	23
+#define SP_MBITS	23
+
+#define SP_MBIT(x)	((u32)1 << (x))
+#define SP_HIDDEN_BIT	SP_MBIT(SP_FBITS)
+#define SP_SIGN_BIT	SP_MBIT(31)
+
+#define SPSIGN(sp)	(sp.sign)
+#define SPBEXP(sp)	(sp.bexp)
+#define SPMANT(sp)	(sp.mant)
+
+static inline int ieee754sp_finite(union ieee754sp x)
+{
+	return SPBEXP(x) != SP_EMAX + 1 + SP_EBIAS;
+}
+
 /* 3bit extended single precision sticky right shift */
-#define SPXSRSXn(rs) \
-  (xe += rs, \
-   xm = (rs > (SP_MBITS+3))?1:((xm) >> (rs)) | ((xm) << (32-(rs)) != 0))
+#define SPXSRSXn(rs)							\
+	(xe += rs,							\
+	 xm = (rs > (SP_FBITS+3))?1:((xm) >> (rs)) | ((xm) << (32-(rs)) != 0))
 
 #define SPXSRSX1() \
-  (xe++, (xm = (xm >> 1) | (xm & 1)))
+	(xe++, (xm = (xm >> 1) | (xm & 1)))
 
-#define SPXSRSYn(rs) \
-   (ye+=rs, \
-    ym = (rs > (SP_MBITS+3))?1:((ym) >> (rs)) | ((ym) << (32-(rs)) != 0))
+#define SPXSRSYn(rs)								\
+	(ye+=rs,								\
+	 ym = (rs > (SP_FBITS+3))?1:((ym) >> (rs)) | ((ym) << (32-(rs)) != 0))
 
 #define SPXSRSY1() \
-   (ye++, (ym = (ym >> 1) | (ym & 1)))
+	(ye++, (ym = (ym >> 1) | (ym & 1)))
 
 /* convert denormal to normalized with extended exponent */
 #define SPDNORMx(m,e) \
-  while( (m >> SP_MBITS) == 0) { m <<= 1; e--; }
+	while ((m >> SP_FBITS) == 0) { m <<= 1; e--; }
 #define SPDNORMX	SPDNORMx(xm, xe)
 #define SPDNORMY	SPDNORMx(ym, ye)
 
-static inline ieee754sp buildsp(int s, int bx, unsigned m)
+static inline union ieee754sp buildsp(int s, int bx, unsigned m)
 {
-	ieee754sp r;
+	union ieee754sp r;
 
 	assert((s) == 0 || (s) == 1);
 	assert((bx) >= SP_EMIN - 1 + SP_EBIAS
 	       && (bx) <= SP_EMAX + 1 + SP_EBIAS);
-	assert(((m) >> SP_MBITS) == 0);
+	assert(((m) >> SP_FBITS) == 0);
 
-	r.parts.sign = s;
-	r.parts.bexp = bx;
-	r.parts.mant = m;
+	r.sign = s;
+	r.bexp = bx;
+	r.mant = m;
 
 	return r;
 }
 
-extern int ieee754sp_isnan(ieee754sp);
-extern int ieee754sp_issnan(ieee754sp);
-extern int ieee754si_xcpt(int, const char *, ...);
-extern s64 ieee754di_xcpt(s64, const char *, ...);
-extern ieee754sp ieee754sp_xcpt(ieee754sp, const char *, ...);
-extern ieee754sp ieee754sp_nanxcpt(ieee754sp, const char *, ...);
-extern ieee754sp ieee754sp_bestnan(ieee754sp, ieee754sp);
-extern ieee754sp ieee754sp_format(int, int, unsigned);
-
-
-#define SPNORMRET2(s, e, m, name, a0, a1) \
-{ \
-    ieee754sp V = ieee754sp_format(s, e, m); \
-    if(TSTX()) \
-      return ieee754sp_xcpt(V, name, a0, a1); \
-    else \
-      return V; \
-}
-
-#define SPNORMRET1(s, e, m, name, a0)  SPNORMRET2(s, e, m, name, a0, a0)
+extern int ieee754sp_isnan(union ieee754sp);
+extern union ieee754sp __cold ieee754sp_nanxcpt(union ieee754sp);
+extern union ieee754sp ieee754sp_format(int, int, unsigned);
diff --git a/arch/mips/math-emu/ieee754xcpt.c b/arch/mips/math-emu/ieee754xcpt.c
deleted file mode 100644
index 967167116ae..00000000000
--- a/arch/mips/math-emu/ieee754xcpt.c
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-/**************************************************************************
- *  Nov 7, 2000
- *  Added preprocessor hacks to map to Linux kernel diagnostics.
- *
- *  Kevin D. Kissell, kevink@mips.com and Carsten Langgaard, carstenl@mips.com
- *  Copyright (C) 2000 MIPS Technologies, Inc.	All rights reserved.
- *************************************************************************/
-
-#include <linux/kernel.h>
-#include "ieee754.h"
-
-/*
- * Very naff exception handler (you can plug in your own and
- * override this).
- */
-
-static const char *const rtnames[] = {
-	"sp", "dp", "xp", "si", "di"
-};
-
-void ieee754_xcpt(struct ieee754xctx *xcp)
-{
-	printk(KERN_DEBUG "floating point exception in \"%s\", type=%s\n",
-		xcp->op, rtnames[xcp->rt]);
-}
diff --git a/arch/mips/math-emu/kernel_linkage.c b/arch/mips/math-emu/kernel_linkage.c
deleted file mode 100644
index eb58a85b315..00000000000
--- a/arch/mips/math-emu/kernel_linkage.c
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- *  Kevin D. Kissell, kevink@mips and Carsten Langgaard, carstenl@mips.com
- *  Copyright (C) 2000 MIPS Technologies, Inc.	All rights reserved.
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * Routines corresponding to Linux kernel FP context
- * manipulation primitives for the Algorithmics MIPS
- * FPU Emulator
- */
-#include <linux/sched.h>
-#include <asm/processor.h>
-#include <asm/signal.h>
-#include <asm/uaccess.h>
-
-#include <asm/fpu.h>
-#include <asm/fpu_emulator.h>
-
-#define SIGNALLING_NAN 0x7ff800007ff80000LL
-
-void fpu_emulator_init_fpu(void)
-{
-	static int first = 1;
-	int i;
-
-	if (first) {
-		first = 0;
-		printk("Algorithmics/MIPS FPU Emulator v1.5\n");
-	}
-
-	current->thread.fpu.fcr31 = 0;
-	for (i = 0; i < 32; i++)
-		set_fpr64(&current->thread.fpu.fpr[i], 0, SIGNALLING_NAN);
-}
diff --git a/arch/mips/math-emu/me-debugfs.c b/arch/mips/math-emu/me-debugfs.c
new file mode 100644
index 00000000000..becdd63e14a
--- /dev/null
+++ b/arch/mips/math-emu/me-debugfs.c
@@ -0,0 +1,67 @@
+#include <linux/cpumask.h>
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/types.h>
+#include <asm/fpu_emulator.h>
+#include <asm/local.h>
+
+DEFINE_PER_CPU(struct mips_fpu_emulator_stats, fpuemustats);
+
+static int fpuemu_stat_get(void *data, u64 *val)
+{
+	int cpu;
+	unsigned long sum = 0;
+
+	for_each_online_cpu(cpu) {
+		struct mips_fpu_emulator_stats *ps;
+		local_t *pv;
+
+		ps = &per_cpu(fpuemustats, cpu);
+		pv = (void *)ps + (unsigned long)data;
+		sum += local_read(pv);
+	}
+	*val = sum;
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_fpuemu_stat, fpuemu_stat_get, NULL, "%llu\n");
+
+extern struct dentry *mips_debugfs_dir;
+static int __init debugfs_fpuemu(void)
+{
+	struct dentry *d, *dir;
+
+	if (!mips_debugfs_dir)
+		return -ENODEV;
+	dir = debugfs_create_dir("fpuemustats", mips_debugfs_dir);
+	if (!dir)
+		return -ENOMEM;
+
+#define FPU_EMU_STAT_OFFSET(m)						\
+	offsetof(struct mips_fpu_emulator_stats, m)
+
+#define FPU_STAT_CREATE(m)						\
+do {									\
+	d = debugfs_create_file(#m , S_IRUGO, dir,			\
+				(void *)FPU_EMU_STAT_OFFSET(m),		\
+				&fops_fpuemu_stat);			\
+	if (!d)								\
+		return -ENOMEM;						\
+} while (0)
+
+	FPU_STAT_CREATE(emulated);
+	FPU_STAT_CREATE(loads);
+	FPU_STAT_CREATE(stores);
+	FPU_STAT_CREATE(cp1ops);
+	FPU_STAT_CREATE(cp1xops);
+	FPU_STAT_CREATE(errors);
+	FPU_STAT_CREATE(ieee754_inexact);
+	FPU_STAT_CREATE(ieee754_underflow);
+	FPU_STAT_CREATE(ieee754_overflow);
+	FPU_STAT_CREATE(ieee754_zerodiv);
+	FPU_STAT_CREATE(ieee754_invalidop);
+
+	return 0;
+}
+__initcall(debugfs_fpuemu);
diff --git a/arch/mips/math-emu/sp_add.c b/arch/mips/math-emu/sp_add.c
index c446e64637e..2d84d460cb6 100644
--- a/arch/mips/math-emu/sp_add.c
+++ b/arch/mips/math-emu/sp_add.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,23 +16,22 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
 
-ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y)
+union ieee754sp ieee754sp_add(union ieee754sp x, union ieee754sp y)
 {
+	int s;
+
 	COMPXSP;
 	COMPYSP;
 
 	EXPLODEXSP;
 	EXPLODEYSP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXSP;
 	FLUSHYSP;
@@ -51,8 +48,8 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef(), "add", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_nanxcpt(ieee754sp_indef());
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -68,14 +65,14 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y)
 		return x;
 
 
-		/* Infinity handling
-		 */
-
+	/*
+	 * Infinity handling
+	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 		if (xs == ys)
 			return x;
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_xcpt(ieee754sp_indef(), "add", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_indef();
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -87,15 +84,14 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 		return x;
 
-		/* Zero handling
-		 */
-
+	/*
+	 * Zero handling
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
 		if (xs == ys)
 			return x;
 		else
-			return ieee754sp_zero(ieee754_csr.rm ==
-					      IEEE754_RD);
+			return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
@@ -108,6 +104,8 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
 		SPDNORMX;
 
+		/* FALL THROUGH */
+
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM):
 		SPDNORMY;
 		break;
@@ -122,33 +120,38 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y)
 	assert(xm & SP_HIDDEN_BIT);
 	assert(ym & SP_HIDDEN_BIT);
 
-	/* provide guard,round and stick bit space */
+	/*
+	 * Provide guard, round and stick bit space.
+	 */
 	xm <<= 3;
 	ym <<= 3;
 
 	if (xe > ye) {
-		/* have to shift y fraction right to align
+		/*
+		 * Have to shift y fraction right to align.
 		 */
-		int s = xe - ye;
+		s = xe - ye;
 		SPXSRSYn(s);
 	} else if (ye > xe) {
-		/* have to shift x fraction right to align
+		/*
+		 * Have to shift x fraction right to align.
 		 */
-		int s = ye - xe;
+		s = ye - xe;
 		SPXSRSXn(s);
 	}
 	assert(xe == ye);
 	assert(xe <= SP_EMAX);
 
 	if (xs == ys) {
-		/* generate 28 bit result of adding two 27 bit numbers
-		 * leaving result in xm,xs,xe
+		/*
+		 * Generate 28 bit result of adding two 27 bit numbers
+		 * leaving result in xm, xs and xe.
 		 */
 		xm = xm + ym;
 		xe = xe;
 		xs = xs;
 
-		if (xm >> (SP_MBITS + 1 + 3)) { /* carry out */
+		if (xm >> (SP_FBITS + 1 + 3)) { /* carry out */
 			SPXSRSX1();
 		}
 	} else {
@@ -162,15 +165,16 @@ ieee754sp ieee754sp_add(ieee754sp x, ieee754sp y)
 			xs = ys;
 		}
 		if (xm == 0)
-			return ieee754sp_zero(ieee754_csr.rm ==
-					      IEEE754_RD);
+			return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
 
-		/* normalize in extended single precision */
-		while ((xm >> (SP_MBITS + 3)) == 0) {
+		/*
+		 * Normalize in extended single precision
+		 */
+		while ((xm >> (SP_FBITS + 3)) == 0) {
 			xm <<= 1;
 			xe--;
 		}
-
 	}
-	SPNORMRET2(xs, xe, xm, "add", x, y);
+
+	return ieee754sp_format(xs, xe, xm);
 }
diff --git a/arch/mips/math-emu/sp_cmp.c b/arch/mips/math-emu/sp_cmp.c
index 716cf37e246..addbccb2f55 100644
--- a/arch/mips/math-emu/sp_cmp.c
+++ b/arch/mips/math-emu/sp_cmp.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,16 +16,16 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
 
-int ieee754sp_cmp(ieee754sp x, ieee754sp y, int cmp, int sig)
+int ieee754sp_cmp(union ieee754sp x, union ieee754sp y, int cmp, int sig)
 {
+	int vx;
+	int vy;
+
 	COMPXSP;
 	COMPYSP;
 
@@ -35,21 +33,21 @@ int ieee754sp_cmp(ieee754sp x, ieee754sp y, int cmp, int sig)
 	EXPLODEYSP;
 	FLUSHXSP;
 	FLUSHYSP;
-	CLEARCX;	/* Even clear inexact flag here */
+	ieee754_clearcx();	/* Even clear inexact flag here */
 
 	if (ieee754sp_isnan(x) || ieee754sp_isnan(y)) {
 		if (sig || xc == IEEE754_CLASS_SNAN || yc == IEEE754_CLASS_SNAN)
-			SETCX(IEEE754_INVALID_OPERATION);
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
 		if (cmp & IEEE754_CUN)
 			return 1;
 		if (cmp & (IEEE754_CLT | IEEE754_CGT)) {
-			if (sig && SETANDTESTCX(IEEE754_INVALID_OPERATION))
-				return ieee754si_xcpt(0, "fcmpf", x);
+			if (sig && ieee754_setandtestcx(IEEE754_INVALID_OPERATION))
+				return 0;
 		}
 		return 0;
 	} else {
-		int vx = x.bits;
-		int vy = y.bits;
+		vx = x.bits;
+		vy = y.bits;
 
 		if (vx < 0)
 			vx = -vx ^ SP_SIGN_BIT;
diff --git a/arch/mips/math-emu/sp_div.c b/arch/mips/math-emu/sp_div.c
index d7747928c95..721f317aa87 100644
--- a/arch/mips/math-emu/sp_div.c
+++ b/arch/mips/math-emu/sp_div.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,23 +16,24 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
 
-ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y)
+union ieee754sp ieee754sp_div(union ieee754sp x, union ieee754sp y)
 {
+	unsigned rm;
+	int re;
+	unsigned bm;
+
 	COMPXSP;
 	COMPYSP;
 
 	EXPLODEXSP;
 	EXPLODEYSP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXSP;
 	FLUSHYSP;
@@ -51,8 +50,8 @@ ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef(), "div", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_nanxcpt(ieee754sp_indef());
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -68,12 +67,12 @@ ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y)
 		return x;
 
 
-		/* Infinity handling
-		 */
-
+	/*
+	 * Infinity handling
+	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_xcpt(ieee754sp_indef(), "div", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_indef();
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
@@ -85,17 +84,17 @@ ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 		return ieee754sp_inf(xs ^ ys);
 
-		/* Zero handling
-		 */
-
+	/*
+	 * Zero handling
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_xcpt(ieee754sp_indef(), "div", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_indef();
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
-		SETCX(IEEE754_ZERO_DIVIDE);
-		return ieee754sp_xcpt(ieee754sp_inf(xs ^ ys), "div", x, y);
+		ieee754_setcx(IEEE754_ZERO_DIVIDE);
+		return ieee754sp_inf(xs ^ ys);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
@@ -122,35 +121,33 @@ ieee754sp ieee754sp_div(ieee754sp x, ieee754sp y)
 	xm <<= 3;
 	ym <<= 3;
 
-	{
-		/* now the dirty work */
-
-		unsigned rm = 0;
-		int re = xe - ye;
-		unsigned bm;
-
-		for (bm = SP_MBIT(SP_MBITS + 2); bm; bm >>= 1) {
-			if (xm >= ym) {
-				xm -= ym;
-				rm |= bm;
-				if (xm == 0)
-					break;
-			}
-			xm <<= 1;
-		}
-		rm <<= 1;
-		if (xm)
-			rm |= 1;	/* have remainder, set sticky */
+	/* now the dirty work */
 
-		assert(rm);
+	rm = 0;
+	re = xe - ye;
 
-		/* normalise rm to rounding precision ?
-		 */
-		while ((rm >> (SP_MBITS + 3)) == 0) {
-			rm <<= 1;
-			re--;
+	for (bm = SP_MBIT(SP_FBITS + 2); bm; bm >>= 1) {
+		if (xm >= ym) {
+			xm -= ym;
+			rm |= bm;
+			if (xm == 0)
+				break;
 		}
+		xm <<= 1;
+	}
+
+	rm <<= 1;
+	if (xm)
+		rm |= 1;	/* have remainder, set sticky */
 
-		SPNORMRET2(xs == ys ? 0 : 1, re, rm, "div", x, y);
+	assert(rm);
+
+	/* normalise rm to rounding precision ?
+	 */
+	while ((rm >> (SP_FBITS + 3)) == 0) {
+		rm <<= 1;
+		re--;
 	}
+
+	return ieee754sp_format(xs == ys ? 0 : 1, re, rm);
 }
diff --git a/arch/mips/math-emu/sp_fdp.c b/arch/mips/math-emu/sp_fdp.c
index e1515aae016..1b266fb1697 100644
--- a/arch/mips/math-emu/sp_fdp.c
+++ b/arch/mips/math-emu/sp_fdp.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,59 +16,61 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
+#include "ieee754dp.h"
 
-ieee754sp ieee754sp_fdp(ieee754dp x)
+union ieee754sp ieee754sp_fdp(union ieee754dp x)
 {
+	u32 rm;
+
 	COMPXDP;
-	ieee754sp nan;
+	union ieee754sp nan;
 
 	EXPLODEXDP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXDP;
 
 	switch (xc) {
 	case IEEE754_CLASS_SNAN:
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef(), "fdp");
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_nanxcpt(ieee754sp_indef());
+
 	case IEEE754_CLASS_QNAN:
 		nan = buildsp(xs, SP_EMAX + 1 + SP_EBIAS, (u32)
-				(xm >> (DP_MBITS - SP_MBITS)));
+				(xm >> (DP_FBITS - SP_FBITS)));
 		if (!ieee754sp_isnan(nan))
 			nan = ieee754sp_indef();
-		return ieee754sp_nanxcpt(nan, "fdp", x);
+		return ieee754sp_nanxcpt(nan);
+
 	case IEEE754_CLASS_INF:
 		return ieee754sp_inf(xs);
+
 	case IEEE754_CLASS_ZERO:
 		return ieee754sp_zero(xs);
+
 	case IEEE754_CLASS_DNORM:
 		/* can't possibly be sp representable */
-		SETCX(IEEE754_UNDERFLOW);
-		SETCX(IEEE754_INEXACT);
-		if ((ieee754_csr.rm == IEEE754_RU && !xs) ||
-				(ieee754_csr.rm == IEEE754_RD && xs))
-			return ieee754sp_xcpt(ieee754sp_mind(xs), "fdp", x);
-		return ieee754sp_xcpt(ieee754sp_zero(xs), "fdp", x);
+		ieee754_setcx(IEEE754_UNDERFLOW);
+		ieee754_setcx(IEEE754_INEXACT);
+		if ((ieee754_csr.rm == FPU_CSR_RU && !xs) ||
+				(ieee754_csr.rm == FPU_CSR_RD && xs))
+			return ieee754sp_mind(xs);
+		return ieee754sp_zero(xs);
+
 	case IEEE754_CLASS_NORM:
 		break;
 	}
 
-	{
-		u32 rm;
-
-		/* convert from DP_MBITS to SP_MBITS+3 with sticky right shift
-		 */
-		rm = (xm >> (DP_MBITS - (SP_MBITS + 3))) |
-		    ((xm << (64 - (DP_MBITS - (SP_MBITS + 3)))) != 0);
+	/*
+	 * Convert from DP_FBITS to SP_FBITS+3 with sticky right shift.
+	 */
+	rm = (xm >> (DP_FBITS - (SP_FBITS + 3))) |
+	     ((xm << (64 - (DP_FBITS - (SP_FBITS + 3)))) != 0);
 
-		SPNORMRET1(xs, xe, rm, "fdp", x);
-	}
+	return ieee754sp_format(xs, xe, rm);
 }
diff --git a/arch/mips/math-emu/sp_fint.c b/arch/mips/math-emu/sp_fint.c
index 9694d6c016c..d5d8495b2cc 100644
--- a/arch/mips/math-emu/sp_fint.c
+++ b/arch/mips/math-emu/sp_fint.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,21 +16,18 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
 
-ieee754sp ieee754sp_fint(int x)
+union ieee754sp ieee754sp_fint(int x)
 {
 	unsigned xm;
 	int xe;
 	int xs;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	if (x == 0)
 		return ieee754sp_zero(0);
@@ -50,30 +45,21 @@ ieee754sp ieee754sp_fint(int x)
 	} else {
 		xm = x;
 	}
-	xe = SP_MBITS + 3;
+	xe = SP_FBITS + 3;
 
-	if (xm >> (SP_MBITS + 1 + 3)) {
+	if (xm >> (SP_FBITS + 1 + 3)) {
 		/* shunt out overflow bits
 		 */
-		while (xm >> (SP_MBITS + 1 + 3)) {
+		while (xm >> (SP_FBITS + 1 + 3)) {
 			SPXSRSX1();
 		}
 	} else {
 		/* normalize in grs extended single precision
 		 */
-		while ((xm >> (SP_MBITS + 3)) == 0) {
+		while ((xm >> (SP_FBITS + 3)) == 0) {
 			xm <<= 1;
 			xe--;
 		}
 	}
-	SPNORMRET1(xs, xe, xm, "fint", x);
-}
-
-
-ieee754sp ieee754sp_funs(unsigned int u)
-{
-	if ((int) u < 0)
-		return ieee754sp_add(ieee754sp_1e31(),
-				     ieee754sp_fint(u & ~(1 << 31)));
-	return ieee754sp_fint(u);
+	return ieee754sp_format(xs, xe, xm);
 }
diff --git a/arch/mips/math-emu/sp_flong.c b/arch/mips/math-emu/sp_flong.c
index 16a651f2986..012e30ce758 100644
--- a/arch/mips/math-emu/sp_flong.c
+++ b/arch/mips/math-emu/sp_flong.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,21 +16,18 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
 
-ieee754sp ieee754sp_flong(s64 x)
+union ieee754sp ieee754sp_flong(s64 x)
 {
 	u64 xm;		/* <--- need 64-bit mantissa temp */
 	int xe;
 	int xs;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	if (x == 0)
 		return ieee754sp_zero(0);
@@ -50,29 +45,20 @@ ieee754sp ieee754sp_flong(s64 x)
 	} else {
 		xm = x;
 	}
-	xe = SP_MBITS + 3;
+	xe = SP_FBITS + 3;
 
-	if (xm >> (SP_MBITS + 1 + 3)) {
+	if (xm >> (SP_FBITS + 1 + 3)) {
 		/* shunt out overflow bits
 		 */
-		while (xm >> (SP_MBITS + 1 + 3)) {
+		while (xm >> (SP_FBITS + 1 + 3)) {
 			SPXSRSX1();
 		}
 	} else {
 		/* normalize in grs extended single precision */
-		while ((xm >> (SP_MBITS + 3)) == 0) {
+		while ((xm >> (SP_FBITS + 3)) == 0) {
 			xm <<= 1;
 			xe--;
 		}
 	}
-	SPNORMRET1(xs, xe, xm, "sp_flong", x);
-}
-
-
-ieee754sp ieee754sp_fulong(u64 u)
-{
-	if ((s64) u < 0)
-		return ieee754sp_add(ieee754sp_1e63(),
-				     ieee754sp_flong(u & ~(1ULL << 63)));
-	return ieee754sp_flong(u);
+	return ieee754sp_format(xs, xe, xm);
 }
diff --git a/arch/mips/math-emu/sp_frexp.c b/arch/mips/math-emu/sp_frexp.c
deleted file mode 100644
index 5bc993c3004..00000000000
--- a/arch/mips/math-emu/sp_frexp.c
+++ /dev/null
@@ -1,52 +0,0 @@
-/* IEEE754 floating point arithmetic
- * single precision
- */
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-
-#include "ieee754sp.h"
-
-/* close to ieeep754sp_logb
-*/
-ieee754sp ieee754sp_frexp(ieee754sp x, int *eptr)
-{
-	COMPXSP;
-	CLEARCX;
-	EXPLODEXSP;
-
-	switch (xc) {
-	case IEEE754_CLASS_SNAN:
-	case IEEE754_CLASS_QNAN:
-	case IEEE754_CLASS_INF:
-	case IEEE754_CLASS_ZERO:
-		*eptr = 0;
-		return x;
-	case IEEE754_CLASS_DNORM:
-		SPDNORMX;
-		break;
-	case IEEE754_CLASS_NORM:
-		break;
-	}
-	*eptr = xe + 1;
-	return buildsp(xs, -1 + SP_EBIAS, xm & ~SP_HIDDEN_BIT);
-}
diff --git a/arch/mips/math-emu/sp_logb.c b/arch/mips/math-emu/sp_logb.c
deleted file mode 100644
index 9c14e0c75bd..00000000000
--- a/arch/mips/math-emu/sp_logb.c
+++ /dev/null
@@ -1,53 +0,0 @@
-/* IEEE754 floating point arithmetic
- * single precision
- */
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-
-#include "ieee754sp.h"
-
-ieee754sp ieee754sp_logb(ieee754sp x)
-{
-	COMPXSP;
-
-	CLEARCX;
-
-	EXPLODEXSP;
-
-	switch (xc) {
-	case IEEE754_CLASS_SNAN:
-		return ieee754sp_nanxcpt(x, "logb", x);
-	case IEEE754_CLASS_QNAN:
-		return x;
-	case IEEE754_CLASS_INF:
-		return ieee754sp_inf(0);
-	case IEEE754_CLASS_ZERO:
-		return ieee754sp_inf(1);
-	case IEEE754_CLASS_DNORM:
-		SPDNORMX;
-		break;
-	case IEEE754_CLASS_NORM:
-		break;
-	}
-	return ieee754sp_fint(xe);
-}
diff --git a/arch/mips/math-emu/sp_modf.c b/arch/mips/math-emu/sp_modf.c
deleted file mode 100644
index 25a0fbaa055..00000000000
--- a/arch/mips/math-emu/sp_modf.c
+++ /dev/null
@@ -1,79 +0,0 @@
-/* IEEE754 floating point arithmetic
- * single precision
- */
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-
-#include "ieee754sp.h"
-
-/* modf function is always exact for a finite number
-*/
-ieee754sp ieee754sp_modf(ieee754sp x, ieee754sp *ip)
-{
-	COMPXSP;
-
-	CLEARCX;
-
-	EXPLODEXSP;
-
-	switch (xc) {
-	case IEEE754_CLASS_SNAN:
-	case IEEE754_CLASS_QNAN:
-	case IEEE754_CLASS_INF:
-	case IEEE754_CLASS_ZERO:
-		*ip = x;
-		return x;
-	case IEEE754_CLASS_DNORM:
-		/* far to small */
-		*ip = ieee754sp_zero(xs);
-		return x;
-	case IEEE754_CLASS_NORM:
-		break;
-	}
-	if (xe < 0) {
-		*ip = ieee754sp_zero(xs);
-		return x;
-	}
-	if (xe >= SP_MBITS) {
-		*ip = x;
-		return ieee754sp_zero(xs);
-	}
-	/* generate ipart mantissa by clearing bottom bits
-	 */
-	*ip = buildsp(xs, xe + SP_EBIAS,
-		      ((xm >> (SP_MBITS - xe)) << (SP_MBITS - xe)) &
-		      ~SP_HIDDEN_BIT);
-
-	/* generate fpart mantissa by clearing top bits
-	 * and normalizing (must be able to normalize)
-	 */
-	xm = (xm << (32 - (SP_MBITS - xe))) >> (32 - (SP_MBITS - xe));
-	if (xm == 0)
-		return ieee754sp_zero(xs);
-
-	while ((xm >> SP_MBITS) == 0) {
-		xm <<= 1;
-		xe--;
-	}
-	return buildsp(xs, xe + SP_EBIAS, xm & ~SP_HIDDEN_BIT);
-}
diff --git a/arch/mips/math-emu/sp_mul.c b/arch/mips/math-emu/sp_mul.c
index fa4675cf2aa..890c13a2965 100644
--- a/arch/mips/math-emu/sp_mul.c
+++ b/arch/mips/math-emu/sp_mul.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,23 +16,32 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
 
-ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y)
+union ieee754sp ieee754sp_mul(union ieee754sp x, union ieee754sp y)
 {
+	int re;
+	int rs;
+	unsigned rm;
+	unsigned short lxm;
+	unsigned short hxm;
+	unsigned short lym;
+	unsigned short hym;
+	unsigned lrm;
+	unsigned hrm;
+	unsigned t;
+	unsigned at;
+
 	COMPXSP;
 	COMPYSP;
 
 	EXPLODEXSP;
 	EXPLODEYSP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXSP;
 	FLUSHYSP;
@@ -51,8 +58,8 @@ ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef(), "mul", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_nanxcpt(ieee754sp_indef());
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -68,12 +75,13 @@ ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y)
 		return x;
 
 
-		/* Infinity handling */
-
+	/*
+	 * Infinity handling
+	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_xcpt(ieee754sp_indef(), "mul", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_indef();
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
@@ -108,63 +116,50 @@ ieee754sp ieee754sp_mul(ieee754sp x, ieee754sp y)
 	assert(xm & SP_HIDDEN_BIT);
 	assert(ym & SP_HIDDEN_BIT);
 
-	{
-		int re = xe + ye;
-		int rs = xs ^ ys;
-		unsigned rm;
-
-		/* shunt to top of word */
-		xm <<= 32 - (SP_MBITS + 1);
-		ym <<= 32 - (SP_MBITS + 1);
-
-		/* multiply 32bits xm,ym to give high 32bits rm with stickness
-		 */
-		{
-			unsigned short lxm = xm & 0xffff;
-			unsigned short hxm = xm >> 16;
-			unsigned short lym = ym & 0xffff;
-			unsigned short hym = ym >> 16;
-			unsigned lrm;
-			unsigned hrm;
-
-			lrm = lxm * lym;	/* 16 * 16 => 32 */
-			hrm = hxm * hym;	/* 16 * 16 => 32 */
-
-			{
-				unsigned t = lxm * hym; /* 16 * 16 => 32 */
-				{
-					unsigned at = lrm + (t << 16);
-					hrm += at < lrm;
-					lrm = at;
-				}
-				hrm = hrm + (t >> 16);
-			}
-
-			{
-				unsigned t = hxm * lym; /* 16 * 16 => 32 */
-				{
-					unsigned at = lrm + (t << 16);
-					hrm += at < lrm;
-					lrm = at;
-				}
-				hrm = hrm + (t >> 16);
-			}
-			rm = hrm | (lrm != 0);
-		}
-
-		/*
-		 * sticky shift down to normal rounding precision
-		 */
-		if ((int) rm < 0) {
-			rm = (rm >> (32 - (SP_MBITS + 1 + 3))) |
-			    ((rm << (SP_MBITS + 1 + 3)) != 0);
-			re++;
-		} else {
-			rm = (rm >> (32 - (SP_MBITS + 1 + 3 + 1))) |
-			    ((rm << (SP_MBITS + 1 + 3 + 1)) != 0);
-		}
-		assert(rm & (SP_HIDDEN_BIT << 3));
-
-		SPNORMRET2(rs, re, rm, "mul", x, y);
+	re = xe + ye;
+	rs = xs ^ ys;
+
+	/* shunt to top of word */
+	xm <<= 32 - (SP_FBITS + 1);
+	ym <<= 32 - (SP_FBITS + 1);
+
+	/*
+	 * Multiply 32 bits xm, ym to give high 32 bits rm with stickness.
+	 */
+	lxm = xm & 0xffff;
+	hxm = xm >> 16;
+	lym = ym & 0xffff;
+	hym = ym >> 16;
+
+	lrm = lxm * lym;	/* 16 * 16 => 32 */
+	hrm = hxm * hym;	/* 16 * 16 => 32 */
+
+	t = lxm * hym; /* 16 * 16 => 32 */
+	at = lrm + (t << 16);
+	hrm += at < lrm;
+	lrm = at;
+	hrm = hrm + (t >> 16);
+
+	t = hxm * lym; /* 16 * 16 => 32 */
+	at = lrm + (t << 16);
+	hrm += at < lrm;
+	lrm = at;
+	hrm = hrm + (t >> 16);
+
+	rm = hrm | (lrm != 0);
+
+	/*
+	 * Sticky shift down to normal rounding precision.
+	 */
+	if ((int) rm < 0) {
+		rm = (rm >> (32 - (SP_FBITS + 1 + 3))) |
+		    ((rm << (SP_FBITS + 1 + 3)) != 0);
+		re++;
+	} else {
+		rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) |
+		     ((rm << (SP_FBITS + 1 + 3 + 1)) != 0);
 	}
+	assert(rm & (SP_HIDDEN_BIT << 3));
+
+	return ieee754sp_format(rs, re, rm);
 }
diff --git a/arch/mips/math-emu/sp_scalb.c b/arch/mips/math-emu/sp_scalb.c
deleted file mode 100644
index dd76196984c..00000000000
--- a/arch/mips/math-emu/sp_scalb.c
+++ /dev/null
@@ -1,57 +0,0 @@
-/* IEEE754 floating point arithmetic
- * single precision
- */
-/*
- * MIPS floating point support
- * Copyright (C) 1994-2000 Algorithmics Ltd.
- *
- * ########################################################################
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
- */
-
-
-#include "ieee754sp.h"
-
-ieee754sp ieee754sp_scalb(ieee754sp x, int n)
-{
-	COMPXSP;
-
-	CLEARCX;
-
-	EXPLODEXSP;
-
-	switch (xc) {
-	case IEEE754_CLASS_SNAN:
-		return ieee754sp_nanxcpt(x, "scalb", x, n);
-	case IEEE754_CLASS_QNAN:
-	case IEEE754_CLASS_INF:
-	case IEEE754_CLASS_ZERO:
-		return x;
-	case IEEE754_CLASS_DNORM:
-		SPDNORMX;
-		break;
-	case IEEE754_CLASS_NORM:
-		break;
-	}
-	SPNORMRET2(xs, xe + n, xm << 3, "scalb", x, n);
-}
-
-
-ieee754sp ieee754sp_ldexp(ieee754sp x, int n)
-{
-	return ieee754sp_scalb(x, n);
-}
diff --git a/arch/mips/math-emu/sp_simple.c b/arch/mips/math-emu/sp_simple.c
index ae4fcfafd85..f1ffaa9a17e 100644
--- a/arch/mips/math-emu/sp_simple.c
+++ b/arch/mips/math-emu/sp_simple.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,33 +16,17 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
 
-int ieee754sp_finite(ieee754sp x)
-{
-	return SPBEXP(x) != SP_EMAX + 1 + SP_EBIAS;
-}
-
-ieee754sp ieee754sp_copysign(ieee754sp x, ieee754sp y)
-{
-	CLEARCX;
-	SPSIGN(x) = SPSIGN(y);
-	return x;
-}
-
-
-ieee754sp ieee754sp_neg(ieee754sp x)
+union ieee754sp ieee754sp_neg(union ieee754sp x)
 {
 	COMPXSP;
 
 	EXPLODEXSP;
-	CLEARCX;
+	ieee754_clearcx();
 	FLUSHXSP;
 
 	/*
@@ -55,30 +37,29 @@ ieee754sp ieee754sp_neg(ieee754sp x)
 	SPSIGN(x) ^= 1;
 
 	if (xc == IEEE754_CLASS_SNAN) {
-		ieee754sp y = ieee754sp_indef();
-		SETCX(IEEE754_INVALID_OPERATION);
+		union ieee754sp y = ieee754sp_indef();
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
 		SPSIGN(y) = SPSIGN(x);
-		return ieee754sp_nanxcpt(y, "neg");
+		return ieee754sp_nanxcpt(y);
 	}
 
 	return x;
 }
 
-
-ieee754sp ieee754sp_abs(ieee754sp x)
+union ieee754sp ieee754sp_abs(union ieee754sp x)
 {
 	COMPXSP;
 
 	EXPLODEXSP;
-	CLEARCX;
+	ieee754_clearcx();
 	FLUSHXSP;
 
 	/* Clear sign ALWAYS, irrespective of NaN */
 	SPSIGN(x) = 0;
 
 	if (xc == IEEE754_CLASS_SNAN) {
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef(), "abs");
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_nanxcpt(ieee754sp_indef());
 	}
 
 	return x;
diff --git a/arch/mips/math-emu/sp_sqrt.c b/arch/mips/math-emu/sp_sqrt.c
index fed20175f5f..b7c098a86f9 100644
--- a/arch/mips/math-emu/sp_sqrt.c
+++ b/arch/mips/math-emu/sp_sqrt.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,15 +16,12 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
 
-ieee754sp ieee754sp_sqrt(ieee754sp x)
+union ieee754sp ieee754sp_sqrt(union ieee754sp x)
 {
 	int ix, s, q, m, t, i;
 	unsigned int r;
@@ -35,34 +30,38 @@ ieee754sp ieee754sp_sqrt(ieee754sp x)
 	/* take care of Inf and NaN */
 
 	EXPLODEXSP;
-	CLEARCX;
+	ieee754_clearcx();
 	FLUSHXSP;
 
 	/* x == INF or NAN? */
 	switch (xc) {
 	case IEEE754_CLASS_QNAN:
 		/* sqrt(Nan) = Nan */
-		return ieee754sp_nanxcpt(x, "sqrt");
+		return ieee754sp_nanxcpt(x);
+
 	case IEEE754_CLASS_SNAN:
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef(), "sqrt");
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_nanxcpt(ieee754sp_indef());
+
 	case IEEE754_CLASS_ZERO:
 		/* sqrt(0) = 0 */
 		return x;
+
 	case IEEE754_CLASS_INF:
 		if (xs) {
 			/* sqrt(-Inf) = Nan */
-			SETCX(IEEE754_INVALID_OPERATION);
-			return ieee754sp_nanxcpt(ieee754sp_indef(), "sqrt");
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754sp_nanxcpt(ieee754sp_indef());
 		}
 		/* sqrt(+Inf) = Inf */
 		return x;
+
 	case IEEE754_CLASS_DNORM:
 	case IEEE754_CLASS_NORM:
 		if (xs) {
 			/* sqrt(-x) = Nan */
-			SETCX(IEEE754_INVALID_OPERATION);
-			return ieee754sp_nanxcpt(ieee754sp_indef(), "sqrt");
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754sp_nanxcpt(ieee754sp_indef());
 		}
 		break;
 	}
@@ -99,12 +98,12 @@ ieee754sp ieee754sp_sqrt(ieee754sp x)
 	}
 
 	if (ix != 0) {
-		SETCX(IEEE754_INEXACT);
+		ieee754_setcx(IEEE754_INEXACT);
 		switch (ieee754_csr.rm) {
-		case IEEE754_RP:
+		case FPU_CSR_RU:
 			q += 2;
 			break;
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			q += (q & 1);
 			break;
 		}
diff --git a/arch/mips/math-emu/sp_sub.c b/arch/mips/math-emu/sp_sub.c
index e595c6f3d0b..8592e49032b 100644
--- a/arch/mips/math-emu/sp_sub.c
+++ b/arch/mips/math-emu/sp_sub.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,23 +16,22 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
 
-ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y)
+union ieee754sp ieee754sp_sub(union ieee754sp x, union ieee754sp y)
 {
+	int s;
+
 	COMPXSP;
 	COMPYSP;
 
 	EXPLODEXSP;
 	EXPLODEYSP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	FLUSHXSP;
 	FLUSHYSP;
@@ -51,8 +48,8 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF):
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_nanxcpt(ieee754sp_indef(), "sub", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_nanxcpt(ieee754sp_indef());
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN):
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN):
@@ -68,14 +65,14 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y)
 		return x;
 
 
-		/* Infinity handling
-		 */
-
+	/*
+	 * Infinity handling
+	 */
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
 		if (xs != ys)
 			return x;
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754sp_xcpt(ieee754sp_indef(), "sub", x, y);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754sp_indef();
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF):
@@ -87,15 +84,14 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 		return x;
 
-		/* Zero handling
-		 */
-
+	/*
+	 * Zero handling
+	 */
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
 		if (xs != ys)
 			return x;
 		else
-			return ieee754sp_zero(ieee754_csr.rm ==
-					      IEEE754_RD);
+			return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD);
 
 	case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO):
@@ -104,7 +100,7 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y)
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM):
 		/* quick fix up */
-		DPSIGN(y) ^= 1;
+		SPSIGN(y) ^= 1;
 		return y;
 
 	case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM):
@@ -133,14 +129,16 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y)
 	ym <<= 3;
 
 	if (xe > ye) {
-		/* have to shift y fraction right to align
+		/*
+		 * have to shift y fraction right to align
 		 */
-		int s = xe - ye;
+		s = xe - ye;
 		SPXSRSYn(s);
 	} else if (ye > xe) {
-		/* have to shift x fraction right to align
+		/*
+		 * have to shift x fraction right to align
 		 */
-		int s = ye - xe;
+		s = ye - xe;
 		SPXSRSXn(s);
 	}
 	assert(xe == ye);
@@ -153,7 +151,7 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y)
 		xe = xe;
 		xs = xs;
 
-		if (xm >> (SP_MBITS + 1 + 3)) { /* carry out */
+		if (xm >> (SP_FBITS + 1 + 3)) { /* carry out */
 			SPXSRSX1();	/* shift preserving sticky */
 		}
 	} else {
@@ -167,17 +165,18 @@ ieee754sp ieee754sp_sub(ieee754sp x, ieee754sp y)
 			xs = ys;
 		}
 		if (xm == 0) {
-			if (ieee754_csr.rm == IEEE754_RD)
+			if (ieee754_csr.rm == FPU_CSR_RD)
 				return ieee754sp_zero(1);	/* round negative inf. => sign = -1 */
 			else
 				return ieee754sp_zero(0);	/* other round modes   => sign = 1 */
 		}
 		/* normalize to rounding precision
 		 */
-		while ((xm >> (SP_MBITS + 3)) == 0) {
+		while ((xm >> (SP_FBITS + 3)) == 0) {
 			xm <<= 1;
 			xe--;
 		}
 	}
-	SPNORMRET2(xs, xe, xm, "sub", x, y);
+
+	return ieee754sp_format(xs, xe, xm);
 }
diff --git a/arch/mips/math-emu/sp_tint.c b/arch/mips/math-emu/sp_tint.c
index 0fe9acc7716..091299a3179 100644
--- a/arch/mips/math-emu/sp_tint.c
+++ b/arch/mips/math-emu/sp_tint.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,20 +16,21 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
-#include <linux/kernel.h>
 #include "ieee754sp.h"
 
-int ieee754sp_tint(ieee754sp x)
+int ieee754sp_tint(union ieee754sp x)
 {
+	u32 residue;
+	int round;
+	int sticky;
+	int odd;
+
 	COMPXSP;
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	EXPLODEXSP;
 	FLUSHXSP;
@@ -40,10 +39,12 @@ int ieee754sp_tint(ieee754sp x)
 	case IEEE754_CLASS_SNAN:
 	case IEEE754_CLASS_QNAN:
 	case IEEE754_CLASS_INF:
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754si_xcpt(ieee754si_indef(), "sp_tint", x);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754si_indef();
+
 	case IEEE754_CLASS_ZERO:
 		return 0;
+
 	case IEEE754_CLASS_DNORM:
 	case IEEE754_CLASS_NORM:
 		break;
@@ -54,18 +55,13 @@ int ieee754sp_tint(ieee754sp x)
 			return -0x80000000;
 		/* Set invalid. We will only use overflow for floating
 		   point overflow */
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754si_xcpt(ieee754si_indef(), "sp_tint", x);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754si_indef();
 	}
 	/* oh gawd */
-	if (xe > SP_MBITS) {
-		xm <<= xe - SP_MBITS;
+	if (xe > SP_FBITS) {
+		xm <<= xe - SP_FBITS;
 	} else {
-		u32 residue;
-		int round;
-		int sticky;
-		int odd;
-
 		if (xe < -1) {
 			residue = xm;
 			round = 0;
@@ -76,51 +72,38 @@ int ieee754sp_tint(ieee754sp x)
 			* so we do it in two steps. Be aware that xe
 			* may be -1 */
 			residue = xm << (xe + 1);
-			residue <<= 31 - SP_MBITS;
+			residue <<= 31 - SP_FBITS;
 			round = (residue >> 31) != 0;
 			sticky = (residue << 1) != 0;
-			xm >>= SP_MBITS - xe;
+			xm >>= SP_FBITS - xe;
 		}
 		odd = (xm & 0x1) != 0x0;
 		switch (ieee754_csr.rm) {
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			if (round && (sticky || odd))
 				xm++;
 			break;
-		case IEEE754_RZ:
+		case FPU_CSR_RZ:
 			break;
-		case IEEE754_RU:	/* toward +Infinity */
+		case FPU_CSR_RU:	/* toward +Infinity */
 			if ((round || sticky) && !xs)
 				xm++;
 			break;
-		case IEEE754_RD:	/* toward -Infinity */
+		case FPU_CSR_RD:	/* toward -Infinity */
 			if ((round || sticky) && xs)
 				xm++;
 			break;
 		}
 		if ((xm >> 31) != 0) {
 			/* This can happen after rounding */
-			SETCX(IEEE754_INVALID_OPERATION);
-			return ieee754si_xcpt(ieee754si_indef(), "sp_tint", x);
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754si_indef();
 		}
 		if (round || sticky)
-			SETCX(IEEE754_INEXACT);
+			ieee754_setcx(IEEE754_INEXACT);
 	}
 	if (xs)
 		return -xm;
 	else
 		return xm;
 }
-
-
-unsigned int ieee754sp_tuns(ieee754sp x)
-{
-	ieee754sp hb = ieee754sp_1e31();
-
-	/* what if x < 0 ?? */
-	if (ieee754sp_lt(x, hb))
-		return (unsigned) ieee754sp_tint(x);
-
-	return (unsigned) ieee754sp_tint(ieee754sp_sub(x, hb)) |
-	    ((unsigned) 1 << 31);
-}
diff --git a/arch/mips/math-emu/sp_tlong.c b/arch/mips/math-emu/sp_tlong.c
index d0ca6e22be2..9f3c742c1ce 100644
--- a/arch/mips/math-emu/sp_tlong.c
+++ b/arch/mips/math-emu/sp_tlong.c
@@ -5,8 +5,6 @@
  * MIPS floating point support
  * Copyright (C) 1994-2000 Algorithmics Ltd.
  *
- * ########################################################################
- *
  *  This program is free software; you can distribute it and/or modify it
  *  under the terms of the GNU General Public License (Version 2) as
  *  published by the Free Software Foundation.
@@ -18,19 +16,22 @@
  *
  *  You should have received a copy of the GNU General Public License along
  *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- *
- * ########################################################################
+ *  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA.
  */
 
-
 #include "ieee754sp.h"
+#include "ieee754dp.h"
 
-s64 ieee754sp_tlong(ieee754sp x)
+s64 ieee754sp_tlong(union ieee754sp x)
 {
+	u32 residue;
+	int round;
+	int sticky;
+	int odd;
+
 	COMPXDP;		/* <-- need 64-bit mantissa tmp */
 
-	CLEARCX;
+	ieee754_clearcx();
 
 	EXPLODEXSP;
 	FLUSHXSP;
@@ -39,10 +40,12 @@ s64 ieee754sp_tlong(ieee754sp x)
 	case IEEE754_CLASS_SNAN:
 	case IEEE754_CLASS_QNAN:
 	case IEEE754_CLASS_INF:
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754di_xcpt(ieee754di_indef(), "sp_tlong", x);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754di_indef();
+
 	case IEEE754_CLASS_ZERO:
 		return 0;
+
 	case IEEE754_CLASS_DNORM:
 	case IEEE754_CLASS_NORM:
 		break;
@@ -53,69 +56,51 @@ s64 ieee754sp_tlong(ieee754sp x)
 			return -0x8000000000000000LL;
 		/* Set invalid. We will only use overflow for floating
 		   point overflow */
-		SETCX(IEEE754_INVALID_OPERATION);
-		return ieee754di_xcpt(ieee754di_indef(), "sp_tlong", x);
+		ieee754_setcx(IEEE754_INVALID_OPERATION);
+		return ieee754di_indef();
 	}
 	/* oh gawd */
-	if (xe > SP_MBITS) {
-		xm <<= xe - SP_MBITS;
-	} else if (xe < SP_MBITS) {
-		u32 residue;
-		int round;
-		int sticky;
-		int odd;
-
+	if (xe > SP_FBITS) {
+		xm <<= xe - SP_FBITS;
+	} else if (xe < SP_FBITS) {
 		if (xe < -1) {
 			residue = xm;
 			round = 0;
 			sticky = residue != 0;
 			xm = 0;
 		} else {
-			residue = xm << (32 - SP_MBITS + xe);
+			residue = xm << (32 - SP_FBITS + xe);
 			round = (residue >> 31) != 0;
 			sticky = (residue << 1) != 0;
-			xm >>= SP_MBITS - xe;
+			xm >>= SP_FBITS - xe;
 		}
 		odd = (xm & 0x1) != 0x0;
 		switch (ieee754_csr.rm) {
-		case IEEE754_RN:
+		case FPU_CSR_RN:
 			if (round && (sticky || odd))
 				xm++;
 			break;
-		case IEEE754_RZ:
+		case FPU_CSR_RZ:
 			break;
-		case IEEE754_RU:	/* toward +Infinity */
+		case FPU_CSR_RU:	/* toward +Infinity */
 			if ((round || sticky) && !xs)
 				xm++;
 			break;
-		case IEEE754_RD:	/* toward -Infinity */
+		case FPU_CSR_RD:	/* toward -Infinity */
 			if ((round || sticky) && xs)
 				xm++;
 			break;
 		}
 		if ((xm >> 63) != 0) {
 			/* This can happen after rounding */
-			SETCX(IEEE754_INVALID_OPERATION);
-			return ieee754di_xcpt(ieee754di_indef(), "sp_tlong", x);
+			ieee754_setcx(IEEE754_INVALID_OPERATION);
+			return ieee754di_indef();
 		}
 		if (round || sticky)
-			SETCX(IEEE754_INEXACT);
+			ieee754_setcx(IEEE754_INEXACT);
 	}
 	if (xs)
 		return -xm;
 	else
 		return xm;
 }
-
-
-u64 ieee754sp_tulong(ieee754sp x)
-{
-	ieee754sp hb = ieee754sp_1e63();
-
-	/* what if x < 0 ?? */
-	if (ieee754sp_lt(x, hb))
-		return (u64) ieee754sp_tlong(x);
-
-	return (u64) ieee754sp_tlong(ieee754sp_sub(x, hb)) |
-	    (1ULL << 63);
-}
diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c
index f41a5c5b086..05b1d7cf951 100644
--- a/arch/mips/mm/c-octeon.c
+++ b/arch/mips/mm/c-octeon.c
@@ -137,8 +137,10 @@ static void octeon_flush_cache_sigtramp(unsigned long addr)
 {
 	struct vm_area_struct *vma;
 
+	down_read(&current->mm->mmap_sem);
 	vma = find_vma(current->mm, addr);
 	octeon_flush_icache_all_cores(vma);
+	up_read(&current->mm->mmap_sem);
 }
 
 
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 1c74a6ad072..f2e8302fa70 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -7,6 +7,7 @@
  * Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002 Ralf Baechle (ralf@gnu.org)
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
  */
+#include <linux/cpu_pm.h>
 #include <linux/hardirq.h>
 #include <linux/init.h>
 #include <linux/highmem.h>
@@ -50,7 +51,7 @@ static inline void r4k_on_each_cpu(void (*func) (void *info), void *info)
 {
 	preempt_disable();
 
-#if !defined(CONFIG_MIPS_MT_SMP) && !defined(CONFIG_MIPS_MT_SMTC)
+#ifndef CONFIG_MIPS_MT_SMP
 	smp_call_function(func, info, 1);
 #endif
 	func(info);
@@ -105,22 +106,37 @@ static inline void r4k_blast_dcache_page_dc32(unsigned long addr)
 
 static inline void r4k_blast_dcache_page_dc64(unsigned long addr)
 {
-	R4600_HIT_CACHEOP_WAR_IMPL;
 	blast_dcache64_page(addr);
 }
 
+static inline void r4k_blast_dcache_page_dc128(unsigned long addr)
+{
+	blast_dcache128_page(addr);
+}
+
 static void r4k_blast_dcache_page_setup(void)
 {
 	unsigned long  dc_lsize = cpu_dcache_line_size();
 
-	if (dc_lsize == 0)
+	switch (dc_lsize) {
+	case 0:
 		r4k_blast_dcache_page = (void *)cache_noop;
-	else if (dc_lsize == 16)
+		break;
+	case 16:
 		r4k_blast_dcache_page = blast_dcache16_page;
-	else if (dc_lsize == 32)
+		break;
+	case 32:
 		r4k_blast_dcache_page = r4k_blast_dcache_page_dc32;
-	else if (dc_lsize == 64)
+		break;
+	case 64:
 		r4k_blast_dcache_page = r4k_blast_dcache_page_dc64;
+		break;
+	case 128:
+		r4k_blast_dcache_page = r4k_blast_dcache_page_dc128;
+		break;
+	default:
+		break;
+	}
 }
 
 #ifndef CONFIG_EVA
@@ -159,6 +175,8 @@ static void r4k_blast_dcache_page_indexed_setup(void)
 		r4k_blast_dcache_page_indexed = blast_dcache32_page_indexed;
 	else if (dc_lsize == 64)
 		r4k_blast_dcache_page_indexed = blast_dcache64_page_indexed;
+	else if (dc_lsize == 128)
+		r4k_blast_dcache_page_indexed = blast_dcache128_page_indexed;
 }
 
 void (* r4k_blast_dcache)(void);
@@ -176,6 +194,8 @@ static void r4k_blast_dcache_setup(void)
 		r4k_blast_dcache = blast_dcache32;
 	else if (dc_lsize == 64)
 		r4k_blast_dcache = blast_dcache64;
+	else if (dc_lsize == 128)
+		r4k_blast_dcache = blast_dcache128;
 }
 
 /* force code alignment (used for TX49XX_ICACHE_INDEX_INV_WAR) */
@@ -265,6 +285,8 @@ static void r4k_blast_icache_page_setup(void)
 		r4k_blast_icache_page = blast_icache32_page;
 	else if (ic_lsize == 64)
 		r4k_blast_icache_page = blast_icache64_page;
+	else if (ic_lsize == 128)
+		r4k_blast_icache_page = blast_icache128_page;
 }
 
 #ifndef CONFIG_EVA
@@ -338,6 +360,8 @@ static void r4k_blast_icache_setup(void)
 			r4k_blast_icache = blast_icache32;
 	} else if (ic_lsize == 64)
 		r4k_blast_icache = blast_icache64;
+	else if (ic_lsize == 128)
+		r4k_blast_icache = blast_icache128;
 }
 
 static void (* r4k_blast_scache_page)(unsigned long addr);
@@ -428,7 +452,7 @@ static void r4k___flush_cache_all(void)
 
 static inline int has_valid_asid(const struct mm_struct *mm)
 {
-#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
+#ifdef CONFIG_MIPS_MT_SMP
 	int i;
 
 	for_each_online_cpu(i)
@@ -1094,6 +1118,21 @@ static void probe_pcache(void)
 		c->dcache.waybit = 0;
 		break;
 
+	case CPU_CAVIUM_OCTEON3:
+		/* For now lie about the number of ways. */
+		c->icache.linesz = 128;
+		c->icache.sets = 16;
+		c->icache.ways = 8;
+		c->icache.flags |= MIPS_CACHE_VTAG;
+		icache_size = c->icache.sets * c->icache.ways * c->icache.linesz;
+
+		c->dcache.linesz = 128;
+		c->dcache.ways = 8;
+		c->dcache.sets = 8;
+		dcache_size = c->dcache.sets * c->dcache.ways * c->dcache.linesz;
+		c->options |= MIPS_CPU_PREFETCH;
+		break;
+
 	default:
 		if (!(config & MIPS_CONF_M))
 			panic("Don't know how to probe P-caches on this cpu.");
@@ -1414,6 +1453,7 @@ static void setup_scache(void)
 		loongson3_sc_init();
 		return;
 
+	case CPU_CAVIUM_OCTEON3:
 	case CPU_XLP:
 		/* don't need to worry about L2, fully coherent */
 		return;
@@ -1644,3 +1684,26 @@ void r4k_cache_init(void)
 	coherency_setup();
 	board_cache_error_setup = r4k_cache_error_setup;
 }
+
+static int r4k_cache_pm_notifier(struct notifier_block *self, unsigned long cmd,
+			       void *v)
+{
+	switch (cmd) {
+	case CPU_PM_ENTER_FAILED:
+	case CPU_PM_EXIT:
+		coherency_setup();
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block r4k_cache_pm_notifier_block = {
+	.notifier_call = r4k_cache_pm_notifier,
+};
+
+int __init r4k_cache_init_pm(void)
+{
+	return cpu_pm_register_notifier(&r4k_cache_pm_notifier_block);
+}
+arch_initcall(r4k_cache_init_pm);
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 4fc74c78265..6e4413330e3 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -44,27 +44,6 @@
 #include <asm/tlb.h>
 #include <asm/fixmap.h>
 
-/* Atomicity and interruptability */
-#ifdef CONFIG_MIPS_MT_SMTC
-
-#include <asm/mipsmtregs.h>
-
-#define ENTER_CRITICAL(flags) \
-	{ \
-	unsigned int mvpflags; \
-	local_irq_save(flags);\
-	mvpflags = dvpe()
-#define EXIT_CRITICAL(flags) \
-	evpe(mvpflags); \
-	local_irq_restore(flags); \
-	}
-#else
-
-#define ENTER_CRITICAL(flags) local_irq_save(flags)
-#define EXIT_CRITICAL(flags) local_irq_restore(flags)
-
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 /*
  * We have up to 8 empty zeroed pages so we can map one of the right colour
  * when needed.	 This is necessary only on R4000 / R4400 SC and MC versions
@@ -100,21 +79,7 @@ void setup_zero_pages(void)
 	zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
 }
 
-#ifdef CONFIG_MIPS_MT_SMTC
-static pte_t *kmap_coherent_pte;
-static void __init kmap_coherent_init(void)
-{
-	unsigned long vaddr;
-
-	/* cache the first coherent kmap pte */
-	vaddr = __fix_to_virt(FIX_CMAP_BEGIN);
-	kmap_coherent_pte = kmap_get_fixmap_pte(vaddr);
-}
-#else
-static inline void kmap_coherent_init(void) {}
-#endif
-
-void *kmap_coherent(struct page *page, unsigned long addr)
+static void *__kmap_pgprot(struct page *page, unsigned long addr, pgprot_t prot)
 {
 	enum fixed_addresses idx;
 	unsigned long vaddr, flags, entrylo;
@@ -126,58 +91,48 @@ void *kmap_coherent(struct page *page, unsigned long addr)
 
 	pagefault_disable();
 	idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
-#ifdef CONFIG_MIPS_MT_SMTC
-	idx += FIX_N_COLOURS * smp_processor_id() +
-		(in_interrupt() ? (FIX_N_COLOURS * NR_CPUS) : 0);
-#else
 	idx += in_interrupt() ? FIX_N_COLOURS : 0;
-#endif
 	vaddr = __fix_to_virt(FIX_CMAP_END - idx);
-	pte = mk_pte(page, PAGE_KERNEL);
+	pte = mk_pte(page, prot);
 #if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
 	entrylo = pte.pte_high;
 #else
 	entrylo = pte_to_entrylo(pte_val(pte));
 #endif
 
-	ENTER_CRITICAL(flags);
+	local_irq_save(flags);
 	old_ctx = read_c0_entryhi();
 	write_c0_entryhi(vaddr & (PAGE_MASK << 1));
 	write_c0_entrylo0(entrylo);
 	write_c0_entrylo1(entrylo);
-#ifdef CONFIG_MIPS_MT_SMTC
-	set_pte(kmap_coherent_pte - (FIX_CMAP_END - idx), pte);
-	/* preload TLB instead of local_flush_tlb_one() */
-	mtc0_tlbw_hazard();
-	tlb_probe();
-	tlb_probe_hazard();
-	tlbidx = read_c0_index();
-	mtc0_tlbw_hazard();
-	if (tlbidx < 0)
-		tlb_write_random();
-	else
-		tlb_write_indexed();
-#else
 	tlbidx = read_c0_wired();
 	write_c0_wired(tlbidx + 1);
 	write_c0_index(tlbidx);
 	mtc0_tlbw_hazard();
 	tlb_write_indexed();
-#endif
 	tlbw_use_hazard();
 	write_c0_entryhi(old_ctx);
-	EXIT_CRITICAL(flags);
+	local_irq_restore(flags);
 
 	return (void*) vaddr;
 }
 
+void *kmap_coherent(struct page *page, unsigned long addr)
+{
+	return __kmap_pgprot(page, addr, PAGE_KERNEL);
+}
+
+void *kmap_noncoherent(struct page *page, unsigned long addr)
+{
+	return __kmap_pgprot(page, addr, PAGE_KERNEL_NC);
+}
+
 void kunmap_coherent(void)
 {
-#ifndef CONFIG_MIPS_MT_SMTC
 	unsigned int wired;
 	unsigned long flags, old_ctx;
 
-	ENTER_CRITICAL(flags);
+	local_irq_save(flags);
 	old_ctx = read_c0_entryhi();
 	wired = read_c0_wired() - 1;
 	write_c0_wired(wired);
@@ -189,8 +144,7 @@ void kunmap_coherent(void)
 	tlb_write_indexed();
 	tlbw_use_hazard();
 	write_c0_entryhi(old_ctx);
-	EXIT_CRITICAL(flags);
-#endif
+	local_irq_restore(flags);
 	pagefault_enable();
 }
 
@@ -256,7 +210,7 @@ EXPORT_SYMBOL_GPL(copy_from_user_page);
 void __init fixrange_init(unsigned long start, unsigned long end,
 	pgd_t *pgd_base)
 {
-#if defined(CONFIG_HIGHMEM) || defined(CONFIG_MIPS_MT_SMTC)
+#ifdef CONFIG_HIGHMEM
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
@@ -327,8 +281,6 @@ void __init paging_init(void)
 #ifdef CONFIG_HIGHMEM
 	kmap_init();
 #endif
-	kmap_coherent_init();
-
 #ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
 #endif
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index eeaf50f5df2..3914e27456f 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -8,6 +8,7 @@
  * Carsten Langgaard, carstenl@mips.com
  * Copyright (C) 2002 MIPS Technologies, Inc.  All rights reserved.
  */
+#include <linux/cpu_pm.h>
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
@@ -25,28 +26,6 @@
 
 extern void build_tlb_refill_handler(void);
 
-/* Atomicity and interruptability */
-#ifdef CONFIG_MIPS_MT_SMTC
-
-#include <asm/smtc.h>
-#include <asm/mipsmtregs.h>
-
-#define ENTER_CRITICAL(flags) \
-	{ \
-	unsigned int mvpflags; \
-	local_irq_save(flags);\
-	mvpflags = dvpe()
-#define EXIT_CRITICAL(flags) \
-	evpe(mvpflags); \
-	local_irq_restore(flags); \
-	}
-#else
-
-#define ENTER_CRITICAL(flags) local_irq_save(flags)
-#define EXIT_CRITICAL(flags) local_irq_restore(flags)
-
-#endif /* CONFIG_MIPS_MT_SMTC */
-
 /*
  * LOONGSON2/3 has a 4 entry itlb which is a subset of dtlb,
  * unfortunately, itlb is not totally transparent to software.
@@ -75,7 +54,7 @@ void local_flush_tlb_all(void)
 	unsigned long old_ctx;
 	int entry, ftlbhighset;
 
-	ENTER_CRITICAL(flags);
+	local_irq_save(flags);
 	/* Save old context and create impossible VPN2 value */
 	old_ctx = read_c0_entryhi();
 	write_c0_entrylo0(0);
@@ -112,7 +91,7 @@ void local_flush_tlb_all(void)
 	tlbw_use_hazard();
 	write_c0_entryhi(old_ctx);
 	flush_itlb();
-	EXIT_CRITICAL(flags);
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(local_flush_tlb_all);
 
@@ -142,7 +121,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 	if (cpu_context(cpu, mm) != 0) {
 		unsigned long size, flags;
 
-		ENTER_CRITICAL(flags);
+		local_irq_save(flags);
 		start = round_down(start, PAGE_SIZE << 1);
 		end = round_up(end, PAGE_SIZE << 1);
 		size = (end - start) >> (PAGE_SHIFT + 1);
@@ -176,7 +155,7 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			drop_mmu_context(mm, cpu);
 		}
 		flush_itlb();
-		EXIT_CRITICAL(flags);
+		local_irq_restore(flags);
 	}
 }
 
@@ -184,7 +163,7 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
 	unsigned long size, flags;
 
-	ENTER_CRITICAL(flags);
+	local_irq_save(flags);
 	size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 	size = (size + 1) >> 1;
 	if (size <= (current_cpu_data.tlbsizeftlbsets ?
@@ -220,7 +199,7 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
 		local_flush_tlb_all();
 	}
 	flush_itlb();
-	EXIT_CRITICAL(flags);
+	local_irq_restore(flags);
 }
 
 void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
@@ -233,7 +212,7 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 
 		newpid = cpu_asid(cpu, vma->vm_mm);
 		page &= (PAGE_MASK << 1);
-		ENTER_CRITICAL(flags);
+		local_irq_save(flags);
 		oldpid = read_c0_entryhi();
 		write_c0_entryhi(page | newpid);
 		mtc0_tlbw_hazard();
@@ -253,7 +232,7 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 	finish:
 		write_c0_entryhi(oldpid);
 		flush_itlb_vm(vma);
-		EXIT_CRITICAL(flags);
+		local_irq_restore(flags);
 	}
 }
 
@@ -266,7 +245,7 @@ void local_flush_tlb_one(unsigned long page)
 	unsigned long flags;
 	int oldpid, idx;
 
-	ENTER_CRITICAL(flags);
+	local_irq_save(flags);
 	oldpid = read_c0_entryhi();
 	page &= (PAGE_MASK << 1);
 	write_c0_entryhi(page);
@@ -285,7 +264,7 @@ void local_flush_tlb_one(unsigned long page)
 	}
 	write_c0_entryhi(oldpid);
 	flush_itlb();
-	EXIT_CRITICAL(flags);
+	local_irq_restore(flags);
 }
 
 /*
@@ -308,7 +287,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	if (current->active_mm != vma->vm_mm)
 		return;
 
-	ENTER_CRITICAL(flags);
+	local_irq_save(flags);
 
 	pid = read_c0_entryhi() & ASID_MASK;
 	address &= (PAGE_MASK << 1);
@@ -358,7 +337,7 @@ void __update_tlb(struct vm_area_struct * vma, unsigned long address, pte_t pte)
 	}
 	tlbw_use_hazard();
 	flush_itlb_vm(vma);
-	EXIT_CRITICAL(flags);
+	local_irq_restore(flags);
 }
 
 void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
@@ -369,7 +348,7 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
 	unsigned long old_pagemask;
 	unsigned long old_ctx;
 
-	ENTER_CRITICAL(flags);
+	local_irq_save(flags);
 	/* Save old context and create impossible VPN2 value */
 	old_ctx = read_c0_entryhi();
 	old_pagemask = read_c0_pagemask();
@@ -389,7 +368,7 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
 	tlbw_use_hazard();	/* What is the hazard here? */
 	write_c0_pagemask(old_pagemask);
 	local_flush_tlb_all();
-	EXIT_CRITICAL(flags);
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -399,13 +378,13 @@ int __init has_transparent_hugepage(void)
 	unsigned int mask;
 	unsigned long flags;
 
-	ENTER_CRITICAL(flags);
+	local_irq_save(flags);
 	write_c0_pagemask(PM_HUGE_MASK);
 	back_to_back_c0_hazard();
 	mask = read_c0_pagemask();
 	write_c0_pagemask(PM_DEFAULT_MASK);
 
-	EXIT_CRITICAL(flags);
+	local_irq_restore(flags);
 
 	return mask == PM_HUGE_MASK;
 }
@@ -421,7 +400,10 @@ static int __init set_ntlb(char *str)
 
 __setup("ntlb=", set_ntlb);
 
-void tlb_init(void)
+/*
+ * Configure TLB (for init or after a CPU has been powered off).
+ */
+static void r4k_tlb_configure(void)
 {
 	/*
 	 * You should never change this register:
@@ -453,6 +435,11 @@ void tlb_init(void)
 	local_flush_tlb_all();
 
 	/* Did I tell you that ARC SUCKS?  */
+}
+
+void tlb_init(void)
+{
+	r4k_tlb_configure();
 
 	if (ntlb) {
 		if (ntlb > 1 && ntlb <= current_cpu_data.tlbsize) {
@@ -466,3 +453,26 @@ void tlb_init(void)
 
 	build_tlb_refill_handler();
 }
+
+static int r4k_tlb_pm_notifier(struct notifier_block *self, unsigned long cmd,
+			       void *v)
+{
+	switch (cmd) {
+	case CPU_PM_ENTER_FAILED:
+	case CPU_PM_EXIT:
+		r4k_tlb_configure();
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block r4k_tlb_pm_notifier_block = {
+	.notifier_call = r4k_tlb_pm_notifier,
+};
+
+static int __init r4k_tlb_init_pm(void)
+{
+	return cpu_pm_register_notifier(&r4k_tlb_pm_notifier_block);
+}
+arch_initcall(r4k_tlb_init_pm);
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index f99ec587b15..e80e10bafc8 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1256,7 +1256,7 @@ static void build_r4000_tlb_refill_handler(void)
 	memset(relocs, 0, sizeof(relocs));
 	memset(final_handler, 0, sizeof(final_handler));
 
-	if ((scratch_reg >= 0 || scratchpad_available()) && use_bbit_insns()) {
+	if (IS_ENABLED(CONFIG_64BIT) && (scratch_reg >= 0 || scratchpad_available()) && use_bbit_insns()) {
 		htlb_info = build_fast_tlb_refill_handler(&p, &l, &r, K0, K1,
 							  scratch_reg);
 		vmalloc_mode = refill_scratch;
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index b8d580ca02e..8399ddf03a0 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -63,6 +63,7 @@ static struct insn insn_table_MM[] = {
 	{ insn_cache, M(mm_pool32b_op, 0, 0, mm_cache_func, 0, 0), RT | RS | SIMM },
 	{ insn_daddu, 0, 0 },
 	{ insn_daddiu, 0, 0 },
+	{ insn_divu, M(mm_pool32a_op, 0, 0, 0, mm_divu_op, mm_pool32axf_op), RT | RS },
 	{ insn_dmfc0, 0, 0 },
 	{ insn_dmtc0, 0, 0 },
 	{ insn_dsll, 0, 0 },
@@ -78,14 +79,20 @@ static struct insn insn_table_MM[] = {
 	{ insn_ext, M(mm_pool32a_op, 0, 0, 0, 0, mm_ext_op), RT | RS | RD | RE },
 	{ insn_j, M(mm_j32_op, 0, 0, 0, 0, 0), JIMM },
 	{ insn_jal, M(mm_jal32_op, 0, 0, 0, 0, 0), JIMM },
+	{ insn_jalr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RT | RS },
 	{ insn_jr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS },
+	{ insn_lb, M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
 	{ insn_ld, 0, 0 },
+	{ insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM },
 	{ insn_ll, M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM },
 	{ insn_lld, 0, 0 },
 	{ insn_lui, M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM },
 	{ insn_lw, M(mm_lw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
 	{ insn_mfc0, M(mm_pool32a_op, 0, 0, 0, mm_mfc0_op, mm_pool32axf_op), RT | RS | RD },
+	{ insn_mfhi, M(mm_pool32a_op, 0, 0, 0, mm_mfhi32_op, mm_pool32axf_op), RS },
+	{ insn_mflo, M(mm_pool32a_op, 0, 0, 0, mm_mflo32_op, mm_pool32axf_op), RS },
 	{ insn_mtc0, M(mm_pool32a_op, 0, 0, 0, mm_mtc0_op, mm_pool32axf_op), RT | RS | RD },
+	{ insn_mul, M(mm_pool32a_op, 0, 0, 0, 0, mm_mul_op), RT | RS | RD },
 	{ insn_or, M(mm_pool32a_op, 0, 0, 0, 0, mm_or32_op), RT | RS | RD },
 	{ insn_ori, M(mm_ori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM },
 	{ insn_pref, M(mm_pool32c_op, 0, 0, (mm_pref_func << 1), 0, 0), RT | RS | SIMM },
@@ -94,15 +101,23 @@ static struct insn insn_table_MM[] = {
 	{ insn_scd, 0, 0 },
 	{ insn_sd, 0, 0 },
 	{ insn_sll, M(mm_pool32a_op, 0, 0, 0, 0, mm_sll32_op), RT | RS | RD },
+	{ insn_sllv, M(mm_pool32a_op, 0, 0, 0, 0, mm_sllv32_op), RT | RS | RD },
+	{ insn_slt, M(mm_pool32a_op, 0, 0, 0, 0, mm_slt_op), RT | RS | RD },
+	{ insn_sltiu, M(mm_sltiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
+	{ insn_sltu, M(mm_pool32a_op, 0, 0, 0, 0, mm_sltu_op), RT | RS | RD },
 	{ insn_sra, M(mm_pool32a_op, 0, 0, 0, 0, mm_sra_op), RT | RS | RD },
 	{ insn_srl, M(mm_pool32a_op, 0, 0, 0, 0, mm_srl32_op), RT | RS | RD },
+	{ insn_srlv, M(mm_pool32a_op, 0, 0, 0, 0, mm_srlv32_op), RT | RS | RD },
 	{ insn_rotr, M(mm_pool32a_op, 0, 0, 0, 0, mm_rotr_op), RT | RS | RD },
 	{ insn_subu, M(mm_pool32a_op, 0, 0, 0, 0, mm_subu32_op), RT | RS | RD },
 	{ insn_sw, M(mm_sw32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
+	{ insn_sync, M(mm_pool32a_op, 0, 0, 0, mm_sync_op, mm_pool32axf_op), RS },
 	{ insn_tlbp, M(mm_pool32a_op, 0, 0, 0, mm_tlbp_op, mm_pool32axf_op), 0 },
 	{ insn_tlbr, M(mm_pool32a_op, 0, 0, 0, mm_tlbr_op, mm_pool32axf_op), 0 },
 	{ insn_tlbwi, M(mm_pool32a_op, 0, 0, 0, mm_tlbwi_op, mm_pool32axf_op), 0 },
 	{ insn_tlbwr, M(mm_pool32a_op, 0, 0, 0, mm_tlbwr_op, mm_pool32axf_op), 0 },
+	{ insn_wait, M(mm_pool32a_op, 0, 0, 0, mm_wait_op, mm_pool32axf_op), SCIMM },
+	{ insn_wsbh, M(mm_pool32a_op, 0, 0, 0, mm_wsbh_op, mm_pool32axf_op), RT | RS },
 	{ insn_xor, M(mm_pool32a_op, 0, 0, 0, 0, mm_xor32_op), RT | RS | RD },
 	{ insn_xori, M(mm_xori32_op, 0, 0, 0, 0, 0), RT | RS | UIMM },
 	{ insn_dins, 0, 0 },
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 3abd609518c..6708a2dbf93 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -67,6 +67,7 @@ static struct insn insn_table[] = {
 	{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
 	{ insn_dinsm, M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE },
 	{ insn_dins, M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE },
+	{ insn_divu, M(spec_op, 0, 0, 0, 0, divu_op), RS | RT },
 	{ insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET},
 	{ insn_dmtc0, M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET},
 	{ insn_drotr32, M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE },
@@ -82,17 +83,23 @@ static struct insn insn_table[] = {
 	{ insn_ins, M(spec3_op, 0, 0, 0, 0, ins_op), RS | RT | RD | RE },
 	{ insn_j,  M(j_op, 0, 0, 0, 0, 0),  JIMM },
 	{ insn_jal,  M(jal_op, 0, 0, 0, 0, 0),	JIMM },
+	{ insn_jalr,  M(spec_op, 0, 0, 0, 0, jalr_op), RS | RD },
 	{ insn_j,  M(j_op, 0, 0, 0, 0, 0),  JIMM },
 	{ insn_jr,  M(spec_op, 0, 0, 0, 0, jr_op),  RS },
+	{ insn_lb, M(lb_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_ld,  M(ld_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_ldx, M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD },
+	{ insn_lh,  M(lh_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_lld,  M(lld_op, 0, 0, 0, 0, 0),	RS | RT | SIMM },
 	{ insn_ll,  M(ll_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_lui,  M(lui_op, 0, 0, 0, 0, 0),	RT | SIMM },
 	{ insn_lw,  M(lw_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_lwx, M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD },
 	{ insn_mfc0,  M(cop0_op, mfc_op, 0, 0, 0, 0),  RT | RD | SET},
+	{ insn_mfhi,  M(spec_op, 0, 0, 0, 0, mfhi_op), RD },
+	{ insn_mflo,  M(spec_op, 0, 0, 0, 0, mflo_op), RD },
 	{ insn_mtc0,  M(cop0_op, mtc_op, 0, 0, 0, 0),  RT | RD | SET},
+	{ insn_mul, M(spec2_op, 0, 0, 0, 0, mul_op), RS | RT | RD},
 	{ insn_ori,  M(ori_op, 0, 0, 0, 0, 0),	RS | RT | UIMM },
 	{ insn_or,  M(spec_op, 0, 0, 0, 0, or_op),  RS | RT | RD },
 	{ insn_pref,  M(pref_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
@@ -102,17 +109,26 @@ static struct insn insn_table[] = {
 	{ insn_sc,  M(sc_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_sd,  M(sd_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_sll,  M(spec_op, 0, 0, 0, 0, sll_op),  RT | RD | RE },
+	{ insn_sllv,  M(spec_op, 0, 0, 0, 0, sllv_op),  RS | RT | RD },
+	{ insn_slt,  M(spec_op, 0, 0, 0, 0, slt_op),  RS | RT | RD },
+	{ insn_sltiu, M(sltiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
+	{ insn_sltu, M(spec_op, 0, 0, 0, 0, sltu_op), RS | RT | RD },
 	{ insn_sra,  M(spec_op, 0, 0, 0, 0, sra_op),  RT | RD | RE },
 	{ insn_srl,  M(spec_op, 0, 0, 0, 0, srl_op),  RT | RD | RE },
+	{ insn_srlv,  M(spec_op, 0, 0, 0, 0, srlv_op),  RS | RT | RD },
 	{ insn_subu,  M(spec_op, 0, 0, 0, 0, subu_op),	RS | RT | RD },
 	{ insn_sw,  M(sw_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+	{ insn_sync, M(spec_op, 0, 0, 0, 0, sync_op), RE },
 	{ insn_syscall, M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM},
 	{ insn_tlbp,  M(cop0_op, cop_op, 0, 0, 0, tlbp_op),  0 },
 	{ insn_tlbr,  M(cop0_op, cop_op, 0, 0, 0, tlbr_op),  0 },
 	{ insn_tlbwi,  M(cop0_op, cop_op, 0, 0, 0, tlbwi_op),  0 },
 	{ insn_tlbwr,  M(cop0_op, cop_op, 0, 0, 0, tlbwr_op),  0 },
+	{ insn_wait, M(cop0_op, cop_op, 0, 0, 0, wait_op), SCIMM },
+	{ insn_wsbh, M(spec3_op, 0, 0, 0, wsbh_op, bshfl_op), RT | RD },
 	{ insn_xori,  M(xori_op, 0, 0, 0, 0, 0),  RS | RT | UIMM },
 	{ insn_xor,  M(spec_op, 0, 0, 0, 0, xor_op),  RS | RT | RD },
+	{ insn_yield, M(spec3_op, 0, 0, 0, 0, yield_op), RS | RD },
 	{ insn_invalid, 0, 0 }
 };
 
diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c
index b9d14b6c7f5..a01b0d6cedd 100644
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@@ -47,14 +47,16 @@ enum opcode {
 	insn_addiu, insn_addu, insn_and, insn_andi, insn_bbit0, insn_bbit1,
 	insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl,
 	insn_bne, insn_cache, insn_daddiu, insn_daddu, insn_dins, insn_dinsm,
-	insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll,
+	insn_divu, insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll,
 	insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32, insn_dsubu, insn_eret,
-	insn_ext, insn_ins, insn_j, insn_jal, insn_jr, insn_ld, insn_ldx,
-	insn_ll, insn_lld, insn_lui, insn_lw, insn_lwx, insn_mfc0, insn_mtc0,
+	insn_ext, insn_ins, insn_j, insn_jal, insn_jalr, insn_jr, insn_lb,
+	insn_ld, insn_ldx, insn_lh, insn_ll, insn_lld, insn_lui, insn_lw,
+	insn_lwx, insn_mfc0, insn_mfhi, insn_mflo, insn_mtc0, insn_mul,
 	insn_or, insn_ori, insn_pref, insn_rfe, insn_rotr, insn_sc, insn_scd,
-	insn_sd, insn_sll, insn_sra, insn_srl, insn_subu, insn_sw,
-	insn_syscall, insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_xor,
-	insn_xori,
+	insn_sd, insn_sll, insn_sllv, insn_slt, insn_sltiu, insn_sltu, insn_sra,
+	insn_srl, insn_srlv, insn_subu, insn_sw, insn_sync, insn_syscall,
+	insn_tlbp, insn_tlbr, insn_tlbwi, insn_tlbwr, insn_wait, insn_wsbh,
+	insn_xor, insn_xori, insn_yield,
 };
 
 struct insn {
@@ -137,6 +139,13 @@ Ip_u1u2u3(op)						\
 }							\
 UASM_EXPORT_SYMBOL(uasm_i##op);
 
+#define I_s3s1s2(op)					\
+Ip_s3s1s2(op)						\
+{							\
+	build_insn(buf, insn##op, b, c, a);		\
+}							\
+UASM_EXPORT_SYMBOL(uasm_i##op);
+
 #define I_u2u1u3(op)					\
 Ip_u2u1u3(op)						\
 {							\
@@ -144,6 +153,13 @@ Ip_u2u1u3(op)						\
 }							\
 UASM_EXPORT_SYMBOL(uasm_i##op);
 
+#define I_u3u2u1(op)					\
+Ip_u3u2u1(op)						\
+{							\
+	build_insn(buf, insn##op, c, b, a);		\
+}							\
+UASM_EXPORT_SYMBOL(uasm_i##op);
+
 #define I_u3u1u2(op)					\
 Ip_u3u1u2(op)						\
 {							\
@@ -200,6 +216,13 @@ Ip_u1u2(op)						\
 }							\
 UASM_EXPORT_SYMBOL(uasm_i##op);
 
+#define I_u2u1(op)					\
+Ip_u1u2(op)						\
+{							\
+	build_insn(buf, insn##op, b, a);		\
+}							\
+UASM_EXPORT_SYMBOL(uasm_i##op);
+
 #define I_u1s2(op)					\
 Ip_u1s2(op)						\
 {							\
@@ -237,6 +260,7 @@ I_u1u2u3(_dmfc0)
 I_u1u2u3(_dmtc0)
 I_u2u1s3(_daddiu)
 I_u3u1u2(_daddu)
+I_u1u2(_divu)
 I_u2u1u3(_dsll)
 I_u2u1u3(_dsll32)
 I_u2u1u3(_dsra)
@@ -250,14 +274,20 @@ I_u2u1msbdu3(_ext)
 I_u2u1msbu3(_ins)
 I_u1(_j)
 I_u1(_jal)
+I_u2u1(_jalr)
 I_u1(_jr)
+I_u2s3u1(_lb)
 I_u2s3u1(_ld)
+I_u2s3u1(_lh)
 I_u2s3u1(_ll)
 I_u2s3u1(_lld)
 I_u1s2(_lui)
 I_u2s3u1(_lw)
 I_u1u2u3(_mfc0)
+I_u1(_mfhi)
+I_u1(_mflo)
 I_u1u2u3(_mtc0)
+I_u3u1u2(_mul)
 I_u2u1u3(_ori)
 I_u3u1u2(_or)
 I_0(_rfe)
@@ -265,17 +295,26 @@ I_u2s3u1(_sc)
 I_u2s3u1(_scd)
 I_u2s3u1(_sd)
 I_u2u1u3(_sll)
+I_u3u2u1(_sllv)
+I_s3s1s2(_slt)
+I_u2u1s3(_sltiu)
+I_u3u1u2(_sltu)
 I_u2u1u3(_sra)
 I_u2u1u3(_srl)
+I_u3u2u1(_srlv)
 I_u2u1u3(_rotr)
 I_u3u1u2(_subu)
 I_u2s3u1(_sw)
+I_u1(_sync)
 I_0(_tlbp)
 I_0(_tlbr)
 I_0(_tlbwi)
 I_0(_tlbwr)
+I_u1(_wait);
+I_u2u1(_wsbh)
 I_u3u1u2(_xor)
 I_u2u1u3(_xori)
+I_u2u1(_yield)
 I_u2u1msbu3(_dins);
 I_u2u1msb32u3(_dinsm);
 I_u1(_syscall);
@@ -469,6 +508,14 @@ void ISAFUNC(uasm_il_b)(u32 **p, struct uasm_reloc **r, int lid)
 }
 UASM_EXPORT_SYMBOL(ISAFUNC(uasm_il_b));
 
+void ISAFUNC(uasm_il_beq)(u32 **p, struct uasm_reloc **r, unsigned int r1,
+			  unsigned int r2, int lid)
+{
+	uasm_r_mips_pc16(r, *p, lid);
+	ISAFUNC(uasm_i_beq)(p, r1, r2, 0);
+}
+UASM_EXPORT_SYMBOL(ISAFUNC(uasm_il_beq));
+
 void ISAFUNC(uasm_il_beqz)(u32 **p, struct uasm_reloc **r, unsigned int reg,
 			   int lid)
 {
diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile
index eae0ba3876d..b9510ea8db5 100644
--- a/arch/mips/mti-malta/Makefile
+++ b/arch/mips/mti-malta/Makefile
@@ -9,5 +9,4 @@ obj-y				:= malta-amon.o malta-display.o malta-init.o \
 				   malta-int.o malta-memory.o malta-platform.o \
 				   malta-reset.o malta-setup.o malta-time.o
 
-# FIXME FIXME FIXME
-obj-$(CONFIG_MIPS_MT_SMTC)	+= malta-smtc.o
+obj-$(CONFIG_MIPS_MALTA_PM)	+= malta-pm.o
diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c
index 4f9e44d358b..0f60256d378 100644
--- a/arch/mips/mti-malta/malta-init.c
+++ b/arch/mips/mti-malta/malta-init.c
@@ -116,8 +116,6 @@ phys_t mips_cpc_default_phys_base(void)
 	return CPC_BASE_ADDR;
 }
 
-extern struct plat_smp_ops msmtc_smp_ops;
-
 void __init prom_init(void)
 {
 	mips_display_message("LINUX");
@@ -304,8 +302,4 @@ mips_pci_controller:
 		return;
 	if (!register_vsmp_smp_ops())
 		return;
-
-#ifdef CONFIG_MIPS_MT_SMTC
-	register_smp_ops(&msmtc_smp_ops);
-#endif
 }
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index b71ee809191..ecc2785f785 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -504,28 +504,9 @@ void __init arch_init_irq(void)
 	} else if (cpu_has_vint) {
 		set_vi_handler(MIPSCPU_INT_I8259A, malta_hw0_irqdispatch);
 		set_vi_handler(MIPSCPU_INT_COREHI, corehi_irqdispatch);
-#ifdef CONFIG_MIPS_MT_SMTC
-		setup_irq_smtc(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_I8259A, &i8259irq,
-			(0x100 << MIPSCPU_INT_I8259A));
-		setup_irq_smtc(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_COREHI,
-			&corehi_irqaction, (0x100 << MIPSCPU_INT_COREHI));
-		/*
-		 * Temporary hack to ensure that the subsidiary device
-		 * interrupts coing in via the i8259A, but associated
-		 * with low IRQ numbers, will restore the Status.IM
-		 * value associated with the i8259A.
-		 */
-		{
-			int i;
-
-			for (i = 0; i < 16; i++)
-				irq_hwmask[i] = (0x100 << MIPSCPU_INT_I8259A);
-		}
-#else /* Not SMTC */
 		setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_I8259A, &i8259irq);
 		setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_COREHI,
 						&corehi_irqaction);
-#endif /* CONFIG_MIPS_MT_SMTC */
 	} else {
 		setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_I8259A, &i8259irq);
 		setup_irq(MIPS_CPU_IRQ_BASE+MIPSCPU_INT_COREHI,
diff --git a/arch/mips/mti-malta/malta-memory.c b/arch/mips/mti-malta/malta-memory.c
index f2364e41968..6d977309675 100644
--- a/arch/mips/mti-malta/malta-memory.c
+++ b/arch/mips/mti-malta/malta-memory.c
@@ -26,8 +26,8 @@ unsigned long physical_memsize = 0L;
 
 fw_memblock_t * __init fw_getmdesc(int eva)
 {
-	char *memsize_str, *ememsize_str __maybe_unused = NULL, *ptr;
-	unsigned long memsize = 0, ememsize __maybe_unused = 0;
+	char *memsize_str, *ememsize_str = NULL, *ptr;
+	unsigned long memsize = 0, ememsize = 0;
 	static char cmdline[COMMAND_LINE_SIZE] __initdata;
 	int tmp;
 
diff --git a/arch/mips/mti-malta/malta-pm.c b/arch/mips/mti-malta/malta-pm.c
new file mode 100644
index 00000000000..c1e456c01a4
--- /dev/null
+++ b/arch/mips/mti-malta/malta-pm.c
@@ -0,0 +1,96 @@
+/*
+ * Copyright (C) 2014 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/pci.h>
+
+#include <asm/mach-malta/malta-pm.h>
+
+static struct pci_bus *pm_pci_bus;
+static resource_size_t pm_io_offset;
+
+int mips_pm_suspend(unsigned state)
+{
+	int spec_devid;
+	u16 sts;
+
+	if (!pm_pci_bus || !pm_io_offset)
+		return -ENODEV;
+
+	/* Ensure the power button status is clear */
+	while (1) {
+		sts = inw(pm_io_offset + PIIX4_FUNC3IO_PMSTS);
+		if (!(sts & PIIX4_FUNC3IO_PMSTS_PWRBTN_STS))
+			break;
+		outw(sts, pm_io_offset + PIIX4_FUNC3IO_PMSTS);
+	}
+
+	/* Enable entry to suspend */
+	outw(state | PIIX4_FUNC3IO_PMCNTRL_SUS_EN,
+	     pm_io_offset + PIIX4_FUNC3IO_PMCNTRL);
+
+	/* If the special cycle occurs too soon this doesn't work... */
+	mdelay(10);
+
+	/*
+	 * The PIIX4 will enter the suspend state only after seeing a special
+	 * cycle with the correct magic data on the PCI bus. Generate that
+	 * cycle now.
+	 */
+	spec_devid = PCI_DEVID(0, PCI_DEVFN(0x1f, 0x7));
+	pci_bus_write_config_dword(pm_pci_bus, spec_devid, 0,
+				   PIIX4_SUSPEND_MAGIC);
+
+	/* Give the system some time to power down */
+	mdelay(1000);
+
+	return 0;
+}
+
+static int __init malta_pm_setup(void)
+{
+	struct pci_dev *dev;
+	int res, io_region = PCI_BRIDGE_RESOURCES;
+
+	/* Find a reference to the PCI bus */
+	pm_pci_bus = pci_find_next_bus(NULL);
+	if (!pm_pci_bus) {
+		pr_warn("malta-pm: failed to find reference to PCI bus\n");
+		return -ENODEV;
+	}
+
+	/* Find the PIIX4 PM device */
+	dev = pci_get_subsys(PCI_VENDOR_ID_INTEL,
+			     PCI_DEVICE_ID_INTEL_82371AB_3, PCI_ANY_ID,
+			     PCI_ANY_ID, NULL);
+	if (!dev) {
+		pr_warn("malta-pm: failed to find PIIX4 PM\n");
+		return -ENODEV;
+	}
+
+	/* Request access to the PIIX4 PM IO registers */
+	res = pci_request_region(dev, io_region, "PIIX4 PM IO registers");
+	if (res) {
+		pr_warn("malta-pm: failed to request PM IO registers (%d)\n",
+			res);
+		pci_dev_put(dev);
+		return -ENODEV;
+	}
+
+	/* Find the offset to the PIIX4 PM IO registers */
+	pm_io_offset = pci_resource_start(dev, io_region);
+
+	pci_dev_put(dev);
+	return 0;
+}
+
+late_initcall(malta_pm_setup);
diff --git a/arch/mips/mti-malta/malta-reset.c b/arch/mips/mti-malta/malta-reset.c
index d627d4b2b47..2fd2cc2c503 100644
--- a/arch/mips/mti-malta/malta-reset.c
+++ b/arch/mips/mti-malta/malta-reset.c
@@ -10,6 +10,7 @@
 #include <linux/pm.h>
 
 #include <asm/reboot.h>
+#include <asm/mach-malta/malta-pm.h>
 
 #define SOFTRES_REG	0x1f000500
 #define GORESET		0x42
@@ -24,17 +25,22 @@ static void mips_machine_restart(char *command)
 
 static void mips_machine_halt(void)
 {
-	unsigned int __iomem *softres_reg =
-		ioremap(SOFTRES_REG, sizeof(unsigned int));
+	while (true);
+}
 
-	__raw_writel(GORESET, softres_reg);
+static void mips_machine_power_off(void)
+{
+	mips_pm_suspend(PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF);
+
+	pr_info("Failed to power down, resetting\n");
+	mips_machine_restart(NULL);
 }
 
 static int __init mips_reboot_setup(void)
 {
 	_machine_restart = mips_machine_restart;
 	_machine_halt = mips_machine_halt;
-	pm_power_off = mips_machine_halt;
+	pm_power_off = mips_machine_power_off;
 
 	return 0;
 }
diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index bf621516aff..db7c9e5826a 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -77,11 +77,7 @@ const char *get_system_type(void)
 	return "MIPS Malta";
 }
 
-#if defined(CONFIG_MIPS_MT_SMTC)
-const char display_string[] = "	      SMTC LINUX ON MALTA	";
-#else
 const char display_string[] = "	       LINUX ON MALTA	    ";
-#endif /* CONFIG_MIPS_MT_SMTC */
 
 #ifdef CONFIG_BLK_DEV_FD
 static void __init fd_activate(void)
diff --git a/arch/mips/mti-malta/malta-smtc.c b/arch/mips/mti-malta/malta-smtc.c
deleted file mode 100644
index c4849904f01..00000000000
--- a/arch/mips/mti-malta/malta-smtc.c
+++ /dev/null
@@ -1,162 +0,0 @@
-/*
- * Malta Platform-specific hooks for SMP operation
- */
-#include <linux/irq.h>
-#include <linux/init.h>
-
-#include <asm/mipsregs.h>
-#include <asm/mipsmtregs.h>
-#include <asm/smtc.h>
-#include <asm/smtc_ipi.h>
-
-/* VPE/SMP Prototype implements platform interfaces directly */
-
-/*
- * Cause the specified action to be performed on a targeted "CPU"
- */
-
-static void msmtc_send_ipi_single(int cpu, unsigned int action)
-{
-	/* "CPU" may be TC of same VPE, VPE of same CPU, or different CPU */
-	smtc_send_ipi(cpu, LINUX_SMP_IPI, action);
-}
-
-static void msmtc_send_ipi_mask(const struct cpumask *mask, unsigned int action)
-{
-	unsigned int i;
-
-	for_each_cpu(i, mask)
-		msmtc_send_ipi_single(i, action);
-}
-
-/*
- * Post-config but pre-boot cleanup entry point
- */
-static void msmtc_init_secondary(void)
-{
-	int myvpe;
-
-	/* Don't enable Malta I/O interrupts (IP2) for secondary VPEs */
-	myvpe = read_c0_tcbind() & TCBIND_CURVPE;
-	if (myvpe != 0) {
-		/* Ideally, this should be done only once per VPE, but... */
-		clear_c0_status(ST0_IM);
-		set_c0_status((0x100 << cp0_compare_irq)
-				| (0x100 << MIPS_CPU_IPI_IRQ));
-		if (cp0_perfcount_irq >= 0)
-			set_c0_status(0x100 << cp0_perfcount_irq);
-	}
-
-	smtc_init_secondary();
-}
-
-/*
- * Platform "CPU" startup hook
- */
-static void msmtc_boot_secondary(int cpu, struct task_struct *idle)
-{
-	smtc_boot_secondary(cpu, idle);
-}
-
-/*
- * SMP initialization finalization entry point
- */
-static void msmtc_smp_finish(void)
-{
-	smtc_smp_finish();
-}
-
-/*
- * Hook for after all CPUs are online
- */
-
-static void msmtc_cpus_done(void)
-{
-}
-
-/*
- * Platform SMP pre-initialization
- *
- * As noted above, we can assume a single CPU for now
- * but it may be multithreaded.
- */
-
-static void __init msmtc_smp_setup(void)
-{
-	/*
-	 * we won't get the definitive value until
-	 * we've run smtc_prepare_cpus later, but
-	 * we would appear to need an upper bound now.
-	 */
-	smp_num_siblings = smtc_build_cpu_map(0);
-}
-
-static void __init msmtc_prepare_cpus(unsigned int max_cpus)
-{
-	smtc_prepare_cpus(max_cpus);
-}
-
-struct plat_smp_ops msmtc_smp_ops = {
-	.send_ipi_single	= msmtc_send_ipi_single,
-	.send_ipi_mask		= msmtc_send_ipi_mask,
-	.init_secondary		= msmtc_init_secondary,
-	.smp_finish		= msmtc_smp_finish,
-	.cpus_done		= msmtc_cpus_done,
-	.boot_secondary		= msmtc_boot_secondary,
-	.smp_setup		= msmtc_smp_setup,
-	.prepare_cpus		= msmtc_prepare_cpus,
-};
-
-#ifdef CONFIG_MIPS_MT_SMTC_IRQAFF
-/*
- * IRQ affinity hook
- */
-
-
-int plat_set_irq_affinity(struct irq_data *d, const struct cpumask *affinity,
-			  bool force)
-{
-	cpumask_t tmask;
-	int cpu = 0;
-	void smtc_set_irq_affinity(unsigned int irq, cpumask_t aff);
-
-	/*
-	 * On the legacy Malta development board, all I/O interrupts
-	 * are routed through the 8259 and combined in a single signal
-	 * to the CPU daughterboard, and on the CoreFPGA2/3 34K models,
-	 * that signal is brought to IP2 of both VPEs. To avoid racing
-	 * concurrent interrupt service events, IP2 is enabled only on
-	 * one VPE, by convention VPE0.	 So long as no bits are ever
-	 * cleared in the affinity mask, there will never be any
-	 * interrupt forwarding.  But as soon as a program or operator
-	 * sets affinity for one of the related IRQs, we need to make
-	 * sure that we don't ever try to forward across the VPE boundary,
-	 * at least not until we engineer a system where the interrupt
-	 * _ack() or _end() function can somehow know that it corresponds
-	 * to an interrupt taken on another VPE, and perform the appropriate
-	 * restoration of Status.IM state using MFTR/MTTR instead of the
-	 * normal local behavior. We also ensure that no attempt will
-	 * be made to forward to an offline "CPU".
-	 */
-
-	cpumask_copy(&tmask, affinity);
-	for_each_cpu(cpu, affinity) {
-		if ((cpu_data[cpu].vpe_id != 0) || !cpu_online(cpu))
-			cpu_clear(cpu, tmask);
-	}
-	cpumask_copy(d->affinity, &tmask);
-
-	if (cpus_empty(tmask))
-		/*
-		 * We could restore a default mask here, but the
-		 * runtime code can anyway deal with the null set
-		 */
-		printk(KERN_WARNING
-		       "IRQ affinity leaves no legal CPU for IRQ %d\n", d->irq);
-
-	/* Do any generic SMTC IRQ affinity setup */
-	smtc_set_irq_affinity(d->irq, tmask);
-
-	return IRQ_SET_MASK_OK_NOCOPY;
-}
-#endif /* CONFIG_MIPS_MT_SMTC_IRQAFF */
diff --git a/arch/mips/mti-sead3/sead3-pic32-i2c-drv.c b/arch/mips/mti-sead3/sead3-pic32-i2c-drv.c
index b921e5ec507..80fe194cfa5 100644
--- a/arch/mips/mti-sead3/sead3-pic32-i2c-drv.c
+++ b/arch/mips/mti-sead3/sead3-pic32-i2c-drv.c
@@ -312,16 +312,13 @@ static int i2c_platform_probe(struct platform_device *pdev)
 
 	pr_debug("i2c_platform_probe\n");
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!r) {
-		ret = -ENODEV;
-		goto out;
-	}
+	if (!r)
+		return -ENODEV;
 
-	priv = kzalloc(sizeof(struct i2c_platform_data), GFP_KERNEL);
-	if (!priv) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	priv = devm_kzalloc(&pdev->dev, sizeof(struct i2c_platform_data),
+			    GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
 
 	/* FIXME: need to allocate resource in PIC32 space */
 #if 0
@@ -330,10 +327,8 @@ static int i2c_platform_probe(struct platform_device *pdev)
 #else
 	priv->base = r->start;
 #endif
-	if (!priv->base) {
-		ret = -EBUSY;
-		goto out_mem;
-	}
+	if (!priv->base)
+		return -EBUSY;
 
 	priv->xfer_timeout = 200;
 	priv->ack_timeout = 200;
@@ -348,17 +343,13 @@ static int i2c_platform_probe(struct platform_device *pdev)
 	i2c_platform_setup(priv);
 
 	ret = i2c_add_numbered_adapter(&priv->adap);
-	if (ret == 0) {
-		platform_set_drvdata(pdev, priv);
-		return 0;
+	if (ret) {
+		i2c_platform_disable(priv);
+		return ret;
 	}
 
-	i2c_platform_disable(priv);
-
-out_mem:
-	kfree(priv);
-out:
-	return ret;
+	platform_set_drvdata(pdev, priv);
+	return 0;
 }
 
 static int i2c_platform_remove(struct platform_device *pdev)
@@ -369,7 +360,6 @@ static int i2c_platform_remove(struct platform_device *pdev)
 	platform_set_drvdata(pdev, NULL);
 	i2c_del_adapter(&priv->adap);
 	i2c_platform_disable(priv);
-	kfree(priv);
 	return 0;
 }
 
diff --git a/arch/mips/net/Makefile b/arch/mips/net/Makefile
new file mode 100644
index 00000000000..ae74b3a91f5
--- /dev/null
+++ b/arch/mips/net/Makefile
@@ -0,0 +1,3 @@
+# MIPS networking code
+
+obj-$(CONFIG_BPF_JIT) += bpf_jit.o
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
new file mode 100644
index 00000000000..b87390a56a2
--- /dev/null
+++ b/arch/mips/net/bpf_jit.c
@@ -0,0 +1,1431 @@
+/*
+ * Just-In-Time compiler for BPF filters on MIPS
+ *
+ * Copyright (c) 2014 Imagination Technologies Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/filter.h>
+#include <linux/if_vlan.h>
+#include <linux/kconfig.h>
+#include <linux/moduleloader.h>
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <asm/bitops.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu-features.h>
+#include <asm/uasm.h>
+
+#include "bpf_jit.h"
+
+/* ABI
+ *
+ * s0	1st scratch register
+ * s1	2nd scratch register
+ * s2	offset register
+ * s3	BPF register A
+ * s4	BPF register X
+ * s5	*skb
+ * s6	*scratch memory
+ *
+ * On entry (*bpf_func)(*skb, *filter)
+ * a0 = MIPS_R_A0 = skb;
+ * a1 = MIPS_R_A1 = filter;
+ *
+ * Stack
+ * ...
+ * M[15]
+ * M[14]
+ * M[13]
+ * ...
+ * M[0] <-- r_M
+ * saved reg k-1
+ * saved reg k-2
+ * ...
+ * saved reg 0 <-- r_sp
+ * <no argument area>
+ *
+ *                     Packet layout
+ *
+ * <--------------------- len ------------------------>
+ * <--skb-len(r_skb_hl)-->< ----- skb->data_len ------>
+ * ----------------------------------------------------
+ * |                  skb->data                       |
+ * ----------------------------------------------------
+ */
+
+#define RSIZE	(sizeof(unsigned long))
+#define ptr typeof(unsigned long)
+
+/* ABI specific return values */
+#ifdef CONFIG_32BIT /* O32 */
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define r_err	MIPS_R_V1
+#define r_val	MIPS_R_V0
+#else /* CONFIG_CPU_LITTLE_ENDIAN */
+#define r_err	MIPS_R_V0
+#define r_val	MIPS_R_V1
+#endif
+#else /* N64 */
+#define r_err	MIPS_R_V0
+#define r_val	MIPS_R_V0
+#endif
+
+#define r_ret	MIPS_R_V0
+
+/*
+ * Use 2 scratch registers to avoid pipeline interlocks.
+ * There is no overhead during epilogue and prologue since
+ * any of the $s0-$s6 registers will only be preserved if
+ * they are going to actually be used.
+ */
+#define r_s0		MIPS_R_S0 /* scratch reg 1 */
+#define r_s1		MIPS_R_S1 /* scratch reg 2 */
+#define r_off		MIPS_R_S2
+#define r_A		MIPS_R_S3
+#define r_X		MIPS_R_S4
+#define r_skb		MIPS_R_S5
+#define r_M		MIPS_R_S6
+#define r_tmp_imm	MIPS_R_T6 /* No need to preserve this */
+#define r_tmp		MIPS_R_T7 /* No need to preserve this */
+#define r_zero		MIPS_R_ZERO
+#define r_sp		MIPS_R_SP
+#define r_ra		MIPS_R_RA
+
+#define SCRATCH_OFF(k)		(4 * (k))
+
+/* JIT flags */
+#define SEEN_CALL		(1 << BPF_MEMWORDS)
+#define SEEN_SREG_SFT		(BPF_MEMWORDS + 1)
+#define SEEN_SREG_BASE		(1 << SEEN_SREG_SFT)
+#define SEEN_SREG(x)		(SEEN_SREG_BASE << (x))
+#define SEEN_S0			SEEN_SREG(0)
+#define SEEN_S1			SEEN_SREG(1)
+#define SEEN_OFF		SEEN_SREG(2)
+#define SEEN_A			SEEN_SREG(3)
+#define SEEN_X			SEEN_SREG(4)
+#define SEEN_SKB		SEEN_SREG(5)
+#define SEEN_MEM		SEEN_SREG(6)
+
+/* Arguments used by JIT */
+#define ARGS_USED_BY_JIT	2 /* only applicable to 64-bit */
+
+#define SBIT(x)			(1 << (x)) /* Signed version of BIT() */
+
+/**
+ * struct jit_ctx - JIT context
+ * @skf:		The sk_filter
+ * @prologue_bytes:	Number of bytes for prologue
+ * @idx:		Instruction index
+ * @flags:		JIT flags
+ * @offsets:		Instruction offsets
+ * @target:		Memory location for the compiled filter
+ */
+struct jit_ctx {
+	const struct sk_filter *skf;
+	unsigned int prologue_bytes;
+	u32 idx;
+	u32 flags;
+	u32 *offsets;
+	u32 *target;
+};
+
+
+static inline int optimize_div(u32 *k)
+{
+	/* power of 2 divides can be implemented with right shift */
+	if (!(*k & (*k-1))) {
+		*k = ilog2(*k);
+		return 1;
+	}
+
+	return 0;
+}
+
+static inline void emit_jit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx);
+
+/* Simply emit the instruction if the JIT memory space has been allocated */
+#define emit_instr(ctx, func, ...)			\
+do {							\
+	if ((ctx)->target != NULL) {			\
+		u32 *p = &(ctx)->target[ctx->idx];	\
+		uasm_i_##func(&p, ##__VA_ARGS__);	\
+	}						\
+	(ctx)->idx++;					\
+} while (0)
+
+/* Determine if immediate is within the 16-bit signed range */
+static inline bool is_range16(s32 imm)
+{
+	return !(imm >= SBIT(15) || imm < -SBIT(15));
+}
+
+static inline void emit_addu(unsigned int dst, unsigned int src1,
+			     unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, addu, dst, src1, src2);
+}
+
+static inline void emit_nop(struct jit_ctx *ctx)
+{
+	emit_instr(ctx, nop);
+}
+
+/* Load a u32 immediate to a register */
+static inline void emit_load_imm(unsigned int dst, u32 imm, struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL) {
+		/* addiu can only handle s16 */
+		if (!is_range16(imm)) {
+			u32 *p = &ctx->target[ctx->idx];
+			uasm_i_lui(&p, r_tmp_imm, (s32)imm >> 16);
+			p = &ctx->target[ctx->idx + 1];
+			uasm_i_ori(&p, dst, r_tmp_imm, imm & 0xffff);
+		} else {
+			u32 *p = &ctx->target[ctx->idx];
+			uasm_i_addiu(&p, dst, r_zero, imm);
+		}
+	}
+	ctx->idx++;
+
+	if (!is_range16(imm))
+		ctx->idx++;
+}
+
+static inline void emit_or(unsigned int dst, unsigned int src1,
+			   unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, or, dst, src1, src2);
+}
+
+static inline void emit_ori(unsigned int dst, unsigned src, u32 imm,
+			    struct jit_ctx *ctx)
+{
+	if (imm >= BIT(16)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_or(dst, src, r_tmp, ctx);
+	} else {
+		emit_instr(ctx, ori, dst, src, imm);
+	}
+}
+
+
+static inline void emit_daddu(unsigned int dst, unsigned int src1,
+			      unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, daddu, dst, src1, src2);
+}
+
+static inline void emit_daddiu(unsigned int dst, unsigned int src,
+			       int imm, struct jit_ctx *ctx)
+{
+	/*
+	 * Only used for stack, so the imm is relatively small
+	 * and it fits in 15-bits
+	 */
+	emit_instr(ctx, daddiu, dst, src, imm);
+}
+
+static inline void emit_addiu(unsigned int dst, unsigned int src,
+			      u32 imm, struct jit_ctx *ctx)
+{
+	if (!is_range16(imm)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_addu(dst, r_tmp, src, ctx);
+	} else {
+		emit_instr(ctx, addiu, dst, src, imm);
+	}
+}
+
+static inline void emit_and(unsigned int dst, unsigned int src1,
+			    unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, and, dst, src1, src2);
+}
+
+static inline void emit_andi(unsigned int dst, unsigned int src,
+			     u32 imm, struct jit_ctx *ctx)
+{
+	/* If imm does not fit in u16 then load it to register */
+	if (imm >= BIT(16)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_and(dst, src, r_tmp, ctx);
+	} else {
+		emit_instr(ctx, andi, dst, src, imm);
+	}
+}
+
+static inline void emit_xor(unsigned int dst, unsigned int src1,
+			    unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, xor, dst, src1, src2);
+}
+
+static inline void emit_xori(ptr dst, ptr src, u32 imm, struct jit_ctx *ctx)
+{
+	/* If imm does not fit in u16 then load it to register */
+	if (imm >= BIT(16)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_xor(dst, src, r_tmp, ctx);
+	} else {
+		emit_instr(ctx, xori, dst, src, imm);
+	}
+}
+
+static inline void emit_stack_offset(int offset, struct jit_ctx *ctx)
+{
+	if (config_enabled(CONFIG_64BIT))
+		emit_instr(ctx, daddiu, r_sp, r_sp, offset);
+	else
+		emit_instr(ctx, addiu, r_sp, r_sp, offset);
+
+}
+
+static inline void emit_subu(unsigned int dst, unsigned int src1,
+			     unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, subu, dst, src1, src2);
+}
+
+static inline void emit_neg(unsigned int reg, struct jit_ctx *ctx)
+{
+	emit_subu(reg, r_zero, reg, ctx);
+}
+
+static inline void emit_sllv(unsigned int dst, unsigned int src,
+			     unsigned int sa, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, sllv, dst, src, sa);
+}
+
+static inline void emit_sll(unsigned int dst, unsigned int src,
+			    unsigned int sa, struct jit_ctx *ctx)
+{
+	/* sa is 5-bits long */
+	if (sa >= BIT(5))
+		/* Shifting >= 32 results in zero */
+		emit_jit_reg_move(dst, r_zero, ctx);
+	else
+		emit_instr(ctx, sll, dst, src, sa);
+}
+
+static inline void emit_srlv(unsigned int dst, unsigned int src,
+			     unsigned int sa, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, srlv, dst, src, sa);
+}
+
+static inline void emit_srl(unsigned int dst, unsigned int src,
+			    unsigned int sa, struct jit_ctx *ctx)
+{
+	/* sa is 5-bits long */
+	if (sa >= BIT(5))
+		/* Shifting >= 32 results in zero */
+		emit_jit_reg_move(dst, r_zero, ctx);
+	else
+		emit_instr(ctx, srl, dst, src, sa);
+}
+
+static inline void emit_slt(unsigned int dst, unsigned int src1,
+			    unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, slt, dst, src1, src2);
+}
+
+static inline void emit_sltu(unsigned int dst, unsigned int src1,
+			     unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, sltu, dst, src1, src2);
+}
+
+static inline void emit_sltiu(unsigned dst, unsigned int src,
+			      unsigned int imm, struct jit_ctx *ctx)
+{
+	/* 16 bit immediate */
+	if (!is_range16((s32)imm)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_sltu(dst, src, r_tmp, ctx);
+	} else {
+		emit_instr(ctx, sltiu, dst, src, imm);
+	}
+
+}
+
+/* Store register on the stack */
+static inline void emit_store_stack_reg(ptr reg, ptr base,
+					unsigned int offset,
+					struct jit_ctx *ctx)
+{
+	if (config_enabled(CONFIG_64BIT))
+		emit_instr(ctx, sd, reg, offset, base);
+	else
+		emit_instr(ctx, sw, reg, offset, base);
+}
+
+static inline void emit_store(ptr reg, ptr base, unsigned int offset,
+			      struct jit_ctx *ctx)
+{
+	emit_instr(ctx, sw, reg, offset, base);
+}
+
+static inline void emit_load_stack_reg(ptr reg, ptr base,
+				       unsigned int offset,
+				       struct jit_ctx *ctx)
+{
+	if (config_enabled(CONFIG_64BIT))
+		emit_instr(ctx, ld, reg, offset, base);
+	else
+		emit_instr(ctx, lw, reg, offset, base);
+}
+
+static inline void emit_load(unsigned int reg, unsigned int base,
+			     unsigned int offset, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, lw, reg, offset, base);
+}
+
+static inline void emit_load_byte(unsigned int reg, unsigned int base,
+				  unsigned int offset, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, lb, reg, offset, base);
+}
+
+static inline void emit_half_load(unsigned int reg, unsigned int base,
+				  unsigned int offset, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, lh, reg, offset, base);
+}
+
+static inline void emit_mul(unsigned int dst, unsigned int src1,
+			    unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, mul, dst, src1, src2);
+}
+
+static inline void emit_div(unsigned int dst, unsigned int src,
+			    struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL) {
+		u32 *p = &ctx->target[ctx->idx];
+		uasm_i_divu(&p, dst, src);
+		p = &ctx->target[ctx->idx + 1];
+		uasm_i_mflo(&p, dst);
+	}
+	ctx->idx += 2; /* 2 insts */
+}
+
+static inline void emit_mod(unsigned int dst, unsigned int src,
+			    struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL) {
+		u32 *p = &ctx->target[ctx->idx];
+		uasm_i_divu(&p, dst, src);
+		p = &ctx->target[ctx->idx + 1];
+		uasm_i_mflo(&p, dst);
+	}
+	ctx->idx += 2; /* 2 insts */
+}
+
+static inline void emit_dsll(unsigned int dst, unsigned int src,
+			     unsigned int sa, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, dsll, dst, src, sa);
+}
+
+static inline void emit_dsrl32(unsigned int dst, unsigned int src,
+			       unsigned int sa, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, dsrl32, dst, src, sa);
+}
+
+static inline void emit_wsbh(unsigned int dst, unsigned int src,
+			     struct jit_ctx *ctx)
+{
+	emit_instr(ctx, wsbh, dst, src);
+}
+
+/* load pointer to register */
+static inline void emit_load_ptr(unsigned int dst, unsigned int src,
+				     int imm, struct jit_ctx *ctx)
+{
+	/* src contains the base addr of the 32/64-pointer */
+	if (config_enabled(CONFIG_64BIT))
+		emit_instr(ctx, ld, dst, imm, src);
+	else
+		emit_instr(ctx, lw, dst, imm, src);
+}
+
+/* load a function pointer to register */
+static inline void emit_load_func(unsigned int reg, ptr imm,
+				  struct jit_ctx *ctx)
+{
+	if (config_enabled(CONFIG_64BIT)) {
+		/* At this point imm is always 64-bit */
+		emit_load_imm(r_tmp, (u64)imm >> 32, ctx);
+		emit_dsll(r_tmp_imm, r_tmp, 16, ctx); /* left shift by 16 */
+		emit_ori(r_tmp, r_tmp_imm, (imm >> 16) & 0xffff, ctx);
+		emit_dsll(r_tmp_imm, r_tmp, 16, ctx); /* left shift by 16 */
+		emit_ori(reg, r_tmp_imm, imm & 0xffff, ctx);
+	} else {
+		emit_load_imm(reg, imm, ctx);
+	}
+}
+
+/* Move to real MIPS register */
+static inline void emit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx)
+{
+	if (config_enabled(CONFIG_64BIT))
+		emit_daddu(dst, src, r_zero, ctx);
+	else
+		emit_addu(dst, src, r_zero, ctx);
+}
+
+/* Move to JIT (32-bit) register */
+static inline void emit_jit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx)
+{
+	emit_addu(dst, src, r_zero, ctx);
+}
+
+/* Compute the immediate value for PC-relative branches. */
+static inline u32 b_imm(unsigned int tgt, struct jit_ctx *ctx)
+{
+	if (ctx->target == NULL)
+		return 0;
+
+	/*
+	 * We want a pc-relative branch. We only do forward branches
+	 * so tgt is always after pc. tgt is the instruction offset
+	 * we want to jump to.
+
+	 * Branch on MIPS:
+	 * I: target_offset <- sign_extend(offset)
+	 * I+1: PC += target_offset (delay slot)
+	 *
+	 * ctx->idx currently points to the branch instruction
+	 * but the offset is added to the delay slot so we need
+	 * to subtract 4.
+	 */
+	return ctx->offsets[tgt] -
+		(ctx->idx * 4 - ctx->prologue_bytes) - 4;
+}
+
+static inline void emit_bcond(int cond, unsigned int reg1, unsigned int reg2,
+			     unsigned int imm, struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL) {
+		u32 *p = &ctx->target[ctx->idx];
+
+		switch (cond) {
+		case MIPS_COND_EQ:
+			uasm_i_beq(&p, reg1, reg2, imm);
+			break;
+		case MIPS_COND_NE:
+			uasm_i_bne(&p, reg1, reg2, imm);
+			break;
+		case MIPS_COND_ALL:
+			uasm_i_b(&p, imm);
+			break;
+		default:
+			pr_warn("%s: Unhandled branch conditional: %d\n",
+				__func__, cond);
+		}
+	}
+	ctx->idx++;
+}
+
+static inline void emit_b(unsigned int imm, struct jit_ctx *ctx)
+{
+	emit_bcond(MIPS_COND_ALL, r_zero, r_zero, imm, ctx);
+}
+
+static inline void emit_jalr(unsigned int link, unsigned int reg,
+			     struct jit_ctx *ctx)
+{
+	emit_instr(ctx, jalr, link, reg);
+}
+
+static inline void emit_jr(unsigned int reg, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, jr, reg);
+}
+
+static inline u16 align_sp(unsigned int num)
+{
+	/* Double word alignment for 32-bit, quadword for 64-bit */
+	unsigned int align = config_enabled(CONFIG_64BIT) ? 16 : 8;
+	num = (num + (align - 1)) & -align;
+	return num;
+}
+
+static bool is_load_to_a(u16 inst)
+{
+	switch (inst) {
+	case BPF_LD | BPF_W | BPF_LEN:
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset)
+{
+	int i = 0, real_off = 0;
+	u32 sflags, tmp_flags;
+
+	/* Adjust the stack pointer */
+	emit_stack_offset(-align_sp(offset), ctx);
+
+	if (ctx->flags & SEEN_CALL) {
+		/* Argument save area */
+		if (config_enabled(CONFIG_64BIT))
+			/* Bottom of current frame */
+			real_off = align_sp(offset) - RSIZE;
+		else
+			/* Top of previous frame */
+			real_off = align_sp(offset) + RSIZE;
+		emit_store_stack_reg(MIPS_R_A0, r_sp, real_off, ctx);
+		emit_store_stack_reg(MIPS_R_A1, r_sp, real_off + RSIZE, ctx);
+
+		real_off = 0;
+	}
+
+	tmp_flags = sflags = ctx->flags >> SEEN_SREG_SFT;
+	/* sflags is essentially a bitmap */
+	while (tmp_flags) {
+		if ((sflags >> i) & 0x1) {
+			emit_store_stack_reg(MIPS_R_S0 + i, r_sp, real_off,
+					     ctx);
+			real_off += RSIZE;
+		}
+		i++;
+		tmp_flags >>= 1;
+	}
+
+	/* save return address */
+	if (ctx->flags & SEEN_CALL) {
+		emit_store_stack_reg(r_ra, r_sp, real_off, ctx);
+		real_off += RSIZE;
+	}
+
+	/* Setup r_M leaving the alignment gap if necessary */
+	if (ctx->flags & SEEN_MEM) {
+		if (real_off % (RSIZE * 2))
+			real_off += RSIZE;
+		if (config_enabled(CONFIG_64BIT))
+			emit_daddiu(r_M, r_sp, real_off, ctx);
+		else
+			emit_addiu(r_M, r_sp, real_off, ctx);
+	}
+}
+
+static void restore_bpf_jit_regs(struct jit_ctx *ctx,
+				 unsigned int offset)
+{
+	int i, real_off = 0;
+	u32 sflags, tmp_flags;
+
+	if (ctx->flags & SEEN_CALL) {
+		if (config_enabled(CONFIG_64BIT))
+			/* Bottom of current frame */
+			real_off = align_sp(offset) - RSIZE;
+		else
+			/* Top of previous frame */
+			real_off = align_sp(offset) + RSIZE;
+		emit_load_stack_reg(MIPS_R_A0, r_sp, real_off, ctx);
+		emit_load_stack_reg(MIPS_R_A1, r_sp, real_off + RSIZE, ctx);
+
+		real_off = 0;
+	}
+
+	tmp_flags = sflags = ctx->flags >> SEEN_SREG_SFT;
+	/* sflags is a bitmap */
+	i = 0;
+	while (tmp_flags) {
+		if ((sflags >> i) & 0x1) {
+			emit_load_stack_reg(MIPS_R_S0 + i, r_sp, real_off,
+					    ctx);
+			real_off += RSIZE;
+		}
+		i++;
+		tmp_flags >>= 1;
+	}
+
+	/* restore return address */
+	if (ctx->flags & SEEN_CALL)
+		emit_load_stack_reg(r_ra, r_sp, real_off, ctx);
+
+	/* Restore the sp and discard the scrach memory */
+	emit_stack_offset(align_sp(offset), ctx);
+}
+
+static unsigned int get_stack_depth(struct jit_ctx *ctx)
+{
+	int sp_off = 0;
+
+
+	/* How may s* regs do we need to preserved? */
+	sp_off += hweight32(ctx->flags >> SEEN_SREG_SFT) * RSIZE;
+
+	if (ctx->flags & SEEN_MEM)
+		sp_off += 4 * BPF_MEMWORDS; /* BPF_MEMWORDS are 32-bit */
+
+	if (ctx->flags & SEEN_CALL)
+		/*
+		 * The JIT code make calls to external functions using 2
+		 * arguments. Therefore, for o32 we don't need to allocate
+		 * space because we don't care if the argumetns are lost
+		 * across calls. We do need however to preserve incoming
+		 * arguments but the space is already allocated for us by
+		 * the caller. On the other hand, for n64, we need to allocate
+		 * this space ourselves. We need to preserve $ra as well.
+		 */
+		sp_off += config_enabled(CONFIG_64BIT) ?
+			(ARGS_USED_BY_JIT + 1) * RSIZE : RSIZE;
+
+	/*
+	 * Subtract the bytes for the last registers since we only care about
+	 * the location on the stack pointer.
+	 */
+	return sp_off - RSIZE;
+}
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+	u16 first_inst = ctx->skf->insns[0].code;
+	int sp_off;
+
+	/* Calculate the total offset for the stack pointer */
+	sp_off = get_stack_depth(ctx);
+	save_bpf_jit_regs(ctx, sp_off);
+
+	if (ctx->flags & SEEN_SKB)
+		emit_reg_move(r_skb, MIPS_R_A0, ctx);
+
+	if (ctx->flags & SEEN_X)
+		emit_jit_reg_move(r_X, r_zero, ctx);
+
+	/* Do not leak kernel data to userspace */
+	if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst)))
+		emit_jit_reg_move(r_A, r_zero, ctx);
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	unsigned int sp_off;
+
+	/* Calculate the total offset for the stack pointer */
+
+	sp_off = get_stack_depth(ctx);
+	restore_bpf_jit_regs(ctx, sp_off);
+
+	/* Return */
+	emit_jr(r_ra, ctx);
+	emit_nop(ctx);
+}
+
+static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset)
+{
+	u8 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 1);
+
+	return (u64)err << 32 | ret;
+}
+
+static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset)
+{
+	u16 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 2);
+
+	return (u64)err << 32 | ntohs(ret);
+}
+
+static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
+{
+	u32 ret;
+	int err;
+
+	err = skb_copy_bits(skb, offset, &ret, 4);
+
+	return (u64)err << 32 | ntohl(ret);
+}
+
+#ifdef __BIG_ENDIAN_BITFIELD
+#define PKT_TYPE_MAX	(7 << 5)
+#else
+#define PKT_TYPE_MAX	7
+#endif
+static int pkt_type_offset(void)
+{
+	struct sk_buff skb_probe = {
+		.pkt_type = ~0,
+	};
+	u8 *ct = (u8 *)&skb_probe;
+	unsigned int off;
+
+	for (off = 0; off < sizeof(struct sk_buff); off++) {
+		if (ct[off] == PKT_TYPE_MAX)
+			return off;
+	}
+	pr_err_once("Please fix pkt_type_offset(), as pkt_type couldn't be found\n");
+	return -1;
+}
+
+static int build_body(struct jit_ctx *ctx)
+{
+	void *load_func[] = {jit_get_skb_b, jit_get_skb_h, jit_get_skb_w};
+	const struct sk_filter *prog = ctx->skf;
+	const struct sock_filter *inst;
+	unsigned int i, off, load_order, condt;
+	u32 k, b_off __maybe_unused;
+
+	for (i = 0; i < prog->len; i++) {
+		u16 code;
+
+		inst = &(prog->insns[i]);
+		pr_debug("%s: code->0x%02x, jt->0x%x, jf->0x%x, k->0x%x\n",
+			 __func__, inst->code, inst->jt, inst->jf, inst->k);
+		k = inst->k;
+		code = bpf_anc_helper(inst);
+
+		if (ctx->target == NULL)
+			ctx->offsets[i] = ctx->idx * 4;
+
+		switch (code) {
+		case BPF_LD | BPF_IMM:
+			/* A <- k ==> li r_A, k */
+			ctx->flags |= SEEN_A;
+			emit_load_imm(r_A, k, ctx);
+			break;
+		case BPF_LD | BPF_W | BPF_LEN:
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
+			/* A <- len ==> lw r_A, offset(skb) */
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			off = offsetof(struct sk_buff, len);
+			emit_load(r_A, r_skb, off, ctx);
+			break;
+		case BPF_LD | BPF_MEM:
+			/* A <- M[k] ==> lw r_A, offset(M) */
+			ctx->flags |= SEEN_MEM | SEEN_A;
+			emit_load(r_A, r_M, SCRATCH_OFF(k), ctx);
+			break;
+		case BPF_LD | BPF_W | BPF_ABS:
+			/* A <- P[k:4] */
+			load_order = 2;
+			goto load;
+		case BPF_LD | BPF_H | BPF_ABS:
+			/* A <- P[k:2] */
+			load_order = 1;
+			goto load;
+		case BPF_LD | BPF_B | BPF_ABS:
+			/* A <- P[k:1] */
+			load_order = 0;
+load:
+			/* the interpreter will deal with the negative K */
+			if ((int)k < 0)
+				return -ENOTSUPP;
+
+			emit_load_imm(r_off, k, ctx);
+load_common:
+			/*
+			 * We may got here from the indirect loads so
+			 * return if offset is negative.
+			 */
+			emit_slt(r_s0, r_off, r_zero, ctx);
+			emit_bcond(MIPS_COND_NE, r_s0, r_zero,
+				   b_imm(prog->len, ctx), ctx);
+			emit_reg_move(r_ret, r_zero, ctx);
+
+			ctx->flags |= SEEN_CALL | SEEN_OFF | SEEN_S0 |
+				SEEN_SKB | SEEN_A;
+
+			emit_load_func(r_s0, (ptr)load_func[load_order],
+				      ctx);
+			emit_reg_move(MIPS_R_A0, r_skb, ctx);
+			emit_jalr(MIPS_R_RA, r_s0, ctx);
+			/* Load second argument to delay slot */
+			emit_reg_move(MIPS_R_A1, r_off, ctx);
+			/* Check the error value */
+			if (config_enabled(CONFIG_64BIT)) {
+				/* Get error code from the top 32-bits */
+				emit_dsrl32(r_s0, r_val, 0, ctx);
+				/* Branch to 3 instructions ahead */
+				emit_bcond(MIPS_COND_NE, r_s0, r_zero, 3 << 2,
+					   ctx);
+			} else {
+				/* Branch to 3 instructions ahead */
+				emit_bcond(MIPS_COND_NE, r_err, r_zero, 3 << 2,
+					   ctx);
+			}
+			emit_nop(ctx);
+			/* We are good */
+			emit_b(b_imm(i + 1, ctx), ctx);
+			emit_jit_reg_move(r_A, r_val, ctx);
+			/* Return with error */
+			emit_b(b_imm(prog->len, ctx), ctx);
+			emit_reg_move(r_ret, r_zero, ctx);
+			break;
+		case BPF_LD | BPF_W | BPF_IND:
+			/* A <- P[X + k:4] */
+			load_order = 2;
+			goto load_ind;
+		case BPF_LD | BPF_H | BPF_IND:
+			/* A <- P[X + k:2] */
+			load_order = 1;
+			goto load_ind;
+		case BPF_LD | BPF_B | BPF_IND:
+			/* A <- P[X + k:1] */
+			load_order = 0;
+load_ind:
+			ctx->flags |= SEEN_OFF | SEEN_X;
+			emit_addiu(r_off, r_X, k, ctx);
+			goto load_common;
+		case BPF_LDX | BPF_IMM:
+			/* X <- k */
+			ctx->flags |= SEEN_X;
+			emit_load_imm(r_X, k, ctx);
+			break;
+		case BPF_LDX | BPF_MEM:
+			/* X <- M[k] */
+			ctx->flags |= SEEN_X | SEEN_MEM;
+			emit_load(r_X, r_M, SCRATCH_OFF(k), ctx);
+			break;
+		case BPF_LDX | BPF_W | BPF_LEN:
+			/* X <- len */
+			ctx->flags |= SEEN_X | SEEN_SKB;
+			off = offsetof(struct sk_buff, len);
+			emit_load(r_X, r_skb, off, ctx);
+			break;
+		case BPF_LDX | BPF_B | BPF_MSH:
+			/* the interpreter will deal with the negative K */
+			if ((int)k < 0)
+				return -ENOTSUPP;
+
+			/* X <- 4 * (P[k:1] & 0xf) */
+			ctx->flags |= SEEN_X | SEEN_CALL | SEEN_S0 | SEEN_SKB;
+			/* Load offset to a1 */
+			emit_load_func(r_s0, (ptr)jit_get_skb_b, ctx);
+			/*
+			 * This may emit two instructions so it may not fit
+			 * in the delay slot. So use a0 in the delay slot.
+			 */
+			emit_load_imm(MIPS_R_A1, k, ctx);
+			emit_jalr(MIPS_R_RA, r_s0, ctx);
+			emit_reg_move(MIPS_R_A0, r_skb, ctx); /* delay slot */
+			/* Check the error value */
+			if (config_enabled(CONFIG_64BIT)) {
+				/* Top 32-bits of $v0 on 64-bit */
+				emit_dsrl32(r_s0, r_val, 0, ctx);
+				emit_bcond(MIPS_COND_NE, r_s0, r_zero,
+					   3 << 2, ctx);
+			} else {
+				emit_bcond(MIPS_COND_NE, r_err, r_zero,
+					   3 << 2, ctx);
+			}
+			/* No need for delay slot */
+			/* We are good */
+			/* X <- P[1:K] & 0xf */
+			emit_andi(r_X, r_val, 0xf, ctx);
+			/* X << 2 */
+			emit_b(b_imm(i + 1, ctx), ctx);
+			emit_sll(r_X, r_X, 2, ctx); /* delay slot */
+			/* Return with error */
+			emit_b(b_imm(prog->len, ctx), ctx);
+			emit_load_imm(r_ret, 0, ctx); /* delay slot */
+			break;
+		case BPF_ST:
+			/* M[k] <- A */
+			ctx->flags |= SEEN_MEM | SEEN_A;
+			emit_store(r_A, r_M, SCRATCH_OFF(k), ctx);
+			break;
+		case BPF_STX:
+			/* M[k] <- X */
+			ctx->flags |= SEEN_MEM | SEEN_X;
+			emit_store(r_X, r_M, SCRATCH_OFF(k), ctx);
+			break;
+		case BPF_ALU | BPF_ADD | BPF_K:
+			/* A += K */
+			ctx->flags |= SEEN_A;
+			emit_addiu(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_ADD | BPF_X:
+			/* A += X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_addu(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_SUB | BPF_K:
+			/* A -= K */
+			ctx->flags |= SEEN_A;
+			emit_addiu(r_A, r_A, -k, ctx);
+			break;
+		case BPF_ALU | BPF_SUB | BPF_X:
+			/* A -= X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_subu(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_MUL | BPF_K:
+			/* A *= K */
+			/* Load K to scratch register before MUL */
+			ctx->flags |= SEEN_A | SEEN_S0;
+			emit_load_imm(r_s0, k, ctx);
+			emit_mul(r_A, r_A, r_s0, ctx);
+			break;
+		case BPF_ALU | BPF_MUL | BPF_X:
+			/* A *= X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_mul(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_DIV | BPF_K:
+			/* A /= k */
+			if (k == 1)
+				break;
+			if (optimize_div(&k)) {
+				ctx->flags |= SEEN_A;
+				emit_srl(r_A, r_A, k, ctx);
+				break;
+			}
+			ctx->flags |= SEEN_A | SEEN_S0;
+			emit_load_imm(r_s0, k, ctx);
+			emit_div(r_A, r_s0, ctx);
+			break;
+		case BPF_ALU | BPF_MOD | BPF_K:
+			/* A %= k */
+			if (k == 1 || optimize_div(&k)) {
+				ctx->flags |= SEEN_A;
+				emit_jit_reg_move(r_A, r_zero, ctx);
+			} else {
+				ctx->flags |= SEEN_A | SEEN_S0;
+				emit_load_imm(r_s0, k, ctx);
+				emit_mod(r_A, r_s0, ctx);
+			}
+			break;
+		case BPF_ALU | BPF_DIV | BPF_X:
+			/* A /= X */
+			ctx->flags |= SEEN_X | SEEN_A;
+			/* Check if r_X is zero */
+			emit_bcond(MIPS_COND_EQ, r_X, r_zero,
+				   b_imm(prog->len, ctx), ctx);
+			emit_load_imm(r_val, 0, ctx); /* delay slot */
+			emit_div(r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_MOD | BPF_X:
+			/* A %= X */
+			ctx->flags |= SEEN_X | SEEN_A;
+			/* Check if r_X is zero */
+			emit_bcond(MIPS_COND_EQ, r_X, r_zero,
+				   b_imm(prog->len, ctx), ctx);
+			emit_load_imm(r_val, 0, ctx); /* delay slot */
+			emit_mod(r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_OR | BPF_K:
+			/* A |= K */
+			ctx->flags |= SEEN_A;
+			emit_ori(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_OR | BPF_X:
+			/* A |= X */
+			ctx->flags |= SEEN_A;
+			emit_ori(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_XOR | BPF_K:
+			/* A ^= k */
+			ctx->flags |= SEEN_A;
+			emit_xori(r_A, r_A, k, ctx);
+			break;
+		case BPF_ANC | SKF_AD_ALU_XOR_X:
+		case BPF_ALU | BPF_XOR | BPF_X:
+			/* A ^= X */
+			ctx->flags |= SEEN_A;
+			emit_xor(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_AND | BPF_K:
+			/* A &= K */
+			ctx->flags |= SEEN_A;
+			emit_andi(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_AND | BPF_X:
+			/* A &= X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_and(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_LSH | BPF_K:
+			/* A <<= K */
+			ctx->flags |= SEEN_A;
+			emit_sll(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_LSH | BPF_X:
+			/* A <<= X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_sllv(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_RSH | BPF_K:
+			/* A >>= K */
+			ctx->flags |= SEEN_A;
+			emit_srl(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_RSH | BPF_X:
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_srlv(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_NEG:
+			/* A = -A */
+			ctx->flags |= SEEN_A;
+			emit_neg(r_A, ctx);
+			break;
+		case BPF_JMP | BPF_JA:
+			/* pc += K */
+			emit_b(b_imm(i + k + 1, ctx), ctx);
+			emit_nop(ctx);
+			break;
+		case BPF_JMP | BPF_JEQ | BPF_K:
+			/* pc += ( A == K ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_EQ | MIPS_COND_K;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JEQ | BPF_X:
+			ctx->flags |= SEEN_X;
+			/* pc += ( A == X ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_EQ | MIPS_COND_X;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JGE | BPF_K:
+			/* pc += ( A >= K ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_GE | MIPS_COND_K;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JGE | BPF_X:
+			ctx->flags |= SEEN_X;
+			/* pc += ( A >= X ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_GE | MIPS_COND_X;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JGT | BPF_K:
+			/* pc += ( A > K ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_GT | MIPS_COND_K;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JGT | BPF_X:
+			ctx->flags |= SEEN_X;
+			/* pc += ( A > X ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_GT | MIPS_COND_X;
+jmp_cmp:
+			/* Greater or Equal */
+			if ((condt & MIPS_COND_GE) ||
+			    (condt & MIPS_COND_GT)) {
+				if (condt & MIPS_COND_K) { /* K */
+					ctx->flags |= SEEN_S0 | SEEN_A;
+					emit_sltiu(r_s0, r_A, k, ctx);
+				} else { /* X */
+					ctx->flags |= SEEN_S0 | SEEN_A |
+						SEEN_X;
+					emit_sltu(r_s0, r_A, r_X, ctx);
+				}
+				/* A < (K|X) ? r_scrach = 1 */
+				b_off = b_imm(i + inst->jf + 1, ctx);
+				emit_bcond(MIPS_COND_NE, r_s0, r_zero, b_off,
+					   ctx);
+				emit_nop(ctx);
+				/* A > (K|X) ? scratch = 0 */
+				if (condt & MIPS_COND_GT) {
+					/* Checking for equality */
+					ctx->flags |= SEEN_S0 | SEEN_A | SEEN_X;
+					if (condt & MIPS_COND_K)
+						emit_load_imm(r_s0, k, ctx);
+					else
+						emit_jit_reg_move(r_s0, r_X,
+								  ctx);
+					b_off = b_imm(i + inst->jf + 1, ctx);
+					emit_bcond(MIPS_COND_EQ, r_A, r_s0,
+						   b_off, ctx);
+					emit_nop(ctx);
+					/* Finally, A > K|X */
+					b_off = b_imm(i + inst->jt + 1, ctx);
+					emit_b(b_off, ctx);
+					emit_nop(ctx);
+				} else {
+					/* A >= (K|X) so jump */
+					b_off = b_imm(i + inst->jt + 1, ctx);
+					emit_b(b_off, ctx);
+					emit_nop(ctx);
+				}
+			} else {
+				/* A == K|X */
+				if (condt & MIPS_COND_K) { /* K */
+					ctx->flags |= SEEN_S0 | SEEN_A;
+					emit_load_imm(r_s0, k, ctx);
+					/* jump true */
+					b_off = b_imm(i + inst->jt + 1, ctx);
+					emit_bcond(MIPS_COND_EQ, r_A, r_s0,
+						   b_off, ctx);
+					emit_nop(ctx);
+					/* jump false */
+					b_off = b_imm(i + inst->jf + 1,
+						      ctx);
+					emit_bcond(MIPS_COND_NE, r_A, r_s0,
+						   b_off, ctx);
+					emit_nop(ctx);
+				} else { /* X */
+					/* jump true */
+					ctx->flags |= SEEN_A | SEEN_X;
+					b_off = b_imm(i + inst->jt + 1,
+						      ctx);
+					emit_bcond(MIPS_COND_EQ, r_A, r_X,
+						   b_off, ctx);
+					emit_nop(ctx);
+					/* jump false */
+					b_off = b_imm(i + inst->jf + 1, ctx);
+					emit_bcond(MIPS_COND_NE, r_A, r_X,
+						   b_off, ctx);
+					emit_nop(ctx);
+				}
+			}
+			break;
+		case BPF_JMP | BPF_JSET | BPF_K:
+			ctx->flags |= SEEN_S0 | SEEN_S1 | SEEN_A;
+			/* pc += (A & K) ? pc -> jt : pc -> jf */
+			emit_load_imm(r_s1, k, ctx);
+			emit_and(r_s0, r_A, r_s1, ctx);
+			/* jump true */
+			b_off = b_imm(i + inst->jt + 1, ctx);
+			emit_bcond(MIPS_COND_NE, r_s0, r_zero, b_off, ctx);
+			emit_nop(ctx);
+			/* jump false */
+			b_off = b_imm(i + inst->jf + 1, ctx);
+			emit_b(b_off, ctx);
+			emit_nop(ctx);
+			break;
+		case BPF_JMP | BPF_JSET | BPF_X:
+			ctx->flags |= SEEN_S0 | SEEN_X | SEEN_A;
+			/* pc += (A & X) ? pc -> jt : pc -> jf */
+			emit_and(r_s0, r_A, r_X, ctx);
+			/* jump true */
+			b_off = b_imm(i + inst->jt + 1, ctx);
+			emit_bcond(MIPS_COND_NE, r_s0, r_zero, b_off, ctx);
+			emit_nop(ctx);
+			/* jump false */
+			b_off = b_imm(i + inst->jf + 1, ctx);
+			emit_b(b_off, ctx);
+			emit_nop(ctx);
+			break;
+		case BPF_RET | BPF_A:
+			ctx->flags |= SEEN_A;
+			if (i != prog->len - 1)
+				/*
+				 * If this is not the last instruction
+				 * then jump to the epilogue
+				 */
+				emit_b(b_imm(prog->len, ctx), ctx);
+			emit_reg_move(r_ret, r_A, ctx); /* delay slot */
+			break;
+		case BPF_RET | BPF_K:
+			/*
+			 * It can emit two instructions so it does not fit on
+			 * the delay slot.
+			 */
+			emit_load_imm(r_ret, k, ctx);
+			if (i != prog->len - 1) {
+				/*
+				 * If this is not the last instruction
+				 * then jump to the epilogue
+				 */
+				emit_b(b_imm(prog->len, ctx), ctx);
+				emit_nop(ctx);
+			}
+			break;
+		case BPF_MISC | BPF_TAX:
+			/* X = A */
+			ctx->flags |= SEEN_X | SEEN_A;
+			emit_jit_reg_move(r_X, r_A, ctx);
+			break;
+		case BPF_MISC | BPF_TXA:
+			/* A = X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_jit_reg_move(r_A, r_X, ctx);
+			break;
+		/* AUX */
+		case BPF_ANC | SKF_AD_PROTOCOL:
+			/* A = ntohs(skb->protocol */
+			ctx->flags |= SEEN_SKB | SEEN_OFF | SEEN_A;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  protocol) != 2);
+			off = offsetof(struct sk_buff, protocol);
+			emit_half_load(r_A, r_skb, off, ctx);
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			/* This needs little endian fixup */
+			if (cpu_has_mips_r2) {
+				/* R2 and later have the wsbh instruction */
+				emit_wsbh(r_A, r_A, ctx);
+			} else {
+				/* Get first byte */
+				emit_andi(r_tmp_imm, r_A, 0xff, ctx);
+				/* Shift it */
+				emit_sll(r_tmp, r_tmp_imm, 8, ctx);
+				/* Get second byte */
+				emit_srl(r_tmp_imm, r_A, 8, ctx);
+				emit_andi(r_tmp_imm, r_tmp_imm, 0xff, ctx);
+				/* Put everyting together in r_A */
+				emit_or(r_A, r_tmp, r_tmp_imm, ctx);
+			}
+#endif
+			break;
+		case BPF_ANC | SKF_AD_CPU:
+			ctx->flags |= SEEN_A | SEEN_OFF;
+			/* A = current_thread_info()->cpu */
+			BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info,
+						  cpu) != 4);
+			off = offsetof(struct thread_info, cpu);
+			/* $28/gp points to the thread_info struct */
+			emit_load(r_A, 28, off, ctx);
+			break;
+		case BPF_ANC | SKF_AD_IFINDEX:
+			/* A = skb->dev->ifindex */
+			ctx->flags |= SEEN_SKB | SEEN_A | SEEN_S0;
+			off = offsetof(struct sk_buff, dev);
+			/* Load *dev pointer */
+			emit_load_ptr(r_s0, r_skb, off, ctx);
+			/* error (0) in the delay slot */
+			emit_bcond(MIPS_COND_EQ, r_s0, r_zero,
+				   b_imm(prog->len, ctx), ctx);
+			emit_reg_move(r_ret, r_zero, ctx);
+			BUILD_BUG_ON(FIELD_SIZEOF(struct net_device,
+						  ifindex) != 4);
+			off = offsetof(struct net_device, ifindex);
+			emit_load(r_A, r_s0, off, ctx);
+			break;
+		case BPF_ANC | SKF_AD_MARK:
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+			off = offsetof(struct sk_buff, mark);
+			emit_load(r_A, r_skb, off, ctx);
+			break;
+		case BPF_ANC | SKF_AD_RXHASH:
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+			off = offsetof(struct sk_buff, hash);
+			emit_load(r_A, r_skb, off, ctx);
+			break;
+		case BPF_ANC | SKF_AD_VLAN_TAG:
+		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
+			ctx->flags |= SEEN_SKB | SEEN_S0 | SEEN_A;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  vlan_tci) != 2);
+			off = offsetof(struct sk_buff, vlan_tci);
+			emit_half_load(r_s0, r_skb, off, ctx);
+			if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
+				emit_andi(r_A, r_s0, (u16)~VLAN_TAG_PRESENT, ctx);
+			} else {
+				emit_andi(r_A, r_s0, VLAN_TAG_PRESENT, ctx);
+				/* return 1 if present */
+				emit_sltu(r_A, r_zero, r_A, ctx);
+			}
+			break;
+		case BPF_ANC | SKF_AD_PKTTYPE:
+			ctx->flags |= SEEN_SKB;
+
+			off = pkt_type_offset();
+
+			if (off < 0)
+				return -1;
+			emit_load_byte(r_tmp, r_skb, off, ctx);
+			/* Keep only the last 3 bits */
+			emit_andi(r_A, r_tmp, PKT_TYPE_MAX, ctx);
+#ifdef __BIG_ENDIAN_BITFIELD
+			/* Get the actual packet type to the lower 3 bits */
+			emit_srl(r_A, r_A, 5, ctx);
+#endif
+			break;
+		case BPF_ANC | SKF_AD_QUEUE:
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
+						  queue_mapping) != 2);
+			BUILD_BUG_ON(offsetof(struct sk_buff,
+					      queue_mapping) > 0xff);
+			off = offsetof(struct sk_buff, queue_mapping);
+			emit_half_load(r_A, r_skb, off, ctx);
+			break;
+		default:
+			pr_debug("%s: Unhandled opcode: 0x%02x\n", __FILE__,
+				 inst->code);
+			return -1;
+		}
+	}
+
+	/* compute offsets only during the first pass */
+	if (ctx->target == NULL)
+		ctx->offsets[i] = ctx->idx * 4;
+
+	return 0;
+}
+
+int bpf_jit_enable __read_mostly;
+
+void bpf_jit_compile(struct sk_filter *fp)
+{
+	struct jit_ctx ctx;
+	unsigned int alloc_size, tmp_idx;
+
+	if (!bpf_jit_enable)
+		return;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	ctx.offsets = kcalloc(fp->len, sizeof(*ctx.offsets), GFP_KERNEL);
+	if (ctx.offsets == NULL)
+		return;
+
+	ctx.skf = fp;
+
+	if (build_body(&ctx))
+		goto out;
+
+	tmp_idx = ctx.idx;
+	build_prologue(&ctx);
+	ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4;
+	/* just to complete the ctx.idx count */
+	build_epilogue(&ctx);
+
+	alloc_size = 4 * ctx.idx;
+	ctx.target = module_alloc(alloc_size);
+	if (ctx.target == NULL)
+		goto out;
+
+	/* Clean it */
+	memset(ctx.target, 0, alloc_size);
+
+	ctx.idx = 0;
+
+	/* Generate the actual JIT code */
+	build_prologue(&ctx);
+	build_body(&ctx);
+	build_epilogue(&ctx);
+
+	/* Update the icache */
+	flush_icache_range((ptr)ctx.target, (ptr)(ctx.target + ctx.idx));
+
+	if (bpf_jit_enable > 1)
+		/* Dump JIT code */
+		bpf_jit_dump(fp->len, alloc_size, 2, ctx.target);
+
+	fp->bpf_func = (void *)ctx.target;
+	fp->jited = 1;
+
+out:
+	kfree(ctx.offsets);
+}
+
+void bpf_jit_free(struct sk_filter *fp)
+{
+	if (fp->jited)
+		module_free(NULL, fp->bpf_func);
+	kfree(fp);
+}
diff --git a/arch/mips/net/bpf_jit.h b/arch/mips/net/bpf_jit.h
new file mode 100644
index 00000000000..3a5751b4335
--- /dev/null
+++ b/arch/mips/net/bpf_jit.h
@@ -0,0 +1,44 @@
+/*
+ * Just-In-Time compiler for BPF filters on MIPS
+ *
+ * Copyright (c) 2014 Imagination Technologies Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; version 2 of the License.
+ */
+
+#ifndef BPF_JIT_MIPS_OP_H
+#define BPF_JIT_MIPS_OP_H
+
+/* Registers used by JIT */
+#define MIPS_R_ZERO	0
+#define MIPS_R_V0	2
+#define MIPS_R_V1	3
+#define MIPS_R_A0	4
+#define MIPS_R_A1	5
+#define MIPS_R_T6	14
+#define MIPS_R_T7	15
+#define MIPS_R_S0	16
+#define MIPS_R_S1	17
+#define MIPS_R_S2	18
+#define MIPS_R_S3	19
+#define MIPS_R_S4	20
+#define MIPS_R_S5	21
+#define MIPS_R_S6	22
+#define MIPS_R_S7	23
+#define MIPS_R_SP	29
+#define MIPS_R_RA	31
+
+/* Conditional codes */
+#define MIPS_COND_EQ	0x1
+#define MIPS_COND_GE	(0x1 << 1)
+#define MIPS_COND_GT	(0x1 << 2)
+#define MIPS_COND_NE	(0x1 << 3)
+#define MIPS_COND_ALL	(0x1 << 4)
+/* Conditionals on X register or K immediate */
+#define MIPS_COND_X	(0x1 << 5)
+#define MIPS_COND_K	(0x1 << 6)
+
+#endif /* BPF_JIT_MIPS_OP_H */
diff --git a/arch/mips/netlogic/common/irq.c b/arch/mips/netlogic/common/irq.c
index 5afc4b7fce0..c100b9afa0a 100644
--- a/arch/mips/netlogic/common/irq.c
+++ b/arch/mips/netlogic/common/irq.c
@@ -203,6 +203,8 @@ void nlm_set_pic_extra_ack(int node, int irq, void (*xack)(struct irq_data *))
 
 	xirq = nlm_irq_to_xirq(node, irq);
 	pic_data = irq_get_handler_data(xirq);
+	if (WARN_ON(!pic_data))
+		return;
 	pic_data->extra_ack = xack;
 }
 
diff --git a/arch/mips/netlogic/common/reset.S b/arch/mips/netlogic/common/reset.S
index b231fe1e7a0..701c4bcb9e4 100644
--- a/arch/mips/netlogic/common/reset.S
+++ b/arch/mips/netlogic/common/reset.S
@@ -35,6 +35,7 @@
 
 #include <asm/asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/cpu.h>
 #include <asm/cacheops.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
@@ -74,13 +75,25 @@
 .endm
 
 /*
+ * Allow access to physical mem >64G by enabling ELPA in PAGEGRAIN
+ * register. This is needed before going to C code since the SP can
+ * in this region. Called from all HW threads.
+ */
+.macro xlp_early_mmu_init
+	mfc0	t0, CP0_PAGEMASK, 1
+	li	t1, (1 << 29)		/* ELPA bit */
+	or	t0, t1
+	mtc0	t0, CP0_PAGEMASK, 1
+.endm
+
+/*
  * L1D cache has to be flushed before enabling threads in XLP.
  * On XLP8xx/XLP3xx, we do a low level flush using processor control
  * registers. On XLPII CPUs, usual cache instructions work.
  */
 .macro	xlp_flush_l1_dcache
 	mfc0	t0, CP0_EBASE, 0
-	andi	t0, t0, 0xff00
+	andi	t0, t0, PRID_IMP_MASK
 	slt	t1, t0, 0x1200
 	beqz	t1, 15f
 	nop
@@ -159,11 +172,15 @@ FEXPORT(nlm_reset_entry)
 
 1:	/* Entry point on core wakeup */
 	mfc0	t0, CP0_EBASE, 0	/* processor ID */
-	andi	t0, 0xff00
+	andi	t0, PRID_IMP_MASK
 	li	t1, 0x1500		/* XLP 9xx */
 	beq	t0, t1, 2f		/* does not need to set coherent */
 	nop
 
+	li	t1, 0x1300		/* XLP 5xx */
+	beq	t0, t1, 2f		/* does not need to set coherent */
+	nop
+
 	/* set bit in SYS coherent register for the core */
 	mfc0	t0, CP0_EBASE, 1
 	mfc0	t1, CP0_EBASE, 1
@@ -197,6 +214,9 @@ FEXPORT(nlm_reset_entry)
 EXPORT(nlm_boot_siblings)
 	/* core L1D flush before enable threads */
 	xlp_flush_l1_dcache
+	/* save ra and sp, will be used later (only for boot cpu) */
+	dmtc0	ra, $22, 6
+	dmtc0	sp, $22, 7
 	/* Enable hw threads by writing to MAP_THREADMODE of the core */
 	li	t0, CKSEG1ADDR(RESET_DATA_PHYS)
 	lw	t1, BOOT_THREAD_MODE(t0)	/* t1 <- thread mode */
@@ -225,6 +245,8 @@ EXPORT(nlm_boot_siblings)
 #endif
 	mtc0	t1, CP0_STATUS
 
+	xlp_early_mmu_init
+
 	/* mark CPU ready */
 	li	t3, CKSEG1ADDR(RESET_DATA_PHYS)
 	ADDIU	t1, t3, BOOT_CPU_READY
@@ -238,14 +260,12 @@ EXPORT(nlm_boot_siblings)
 	nop
 
 	/*
-	 * For the boot CPU, we have to restore registers and
-	 * return
+	 * For the boot CPU, we have to restore ra and sp and return, rest
+	 * of the registers will be restored by the caller
 	 */
-4:	dmfc0	t0, $4, 2	/* restore SP from UserLocal */
-	li	t1, 0xfadebeef
-	dmtc0	t1, $4, 2	/* restore SP from UserLocal */
-	PTR_SUBU sp, t0, PT_SIZE
-	RESTORE_ALL
+4:
+	dmfc0	ra, $22, 6
+	dmfc0	sp, $22, 7
 	jr	ra
 	nop
 EXPORT(nlm_reset_entry_end)
@@ -253,6 +273,7 @@ EXPORT(nlm_reset_entry_end)
 LEAF(nlm_init_boot_cpu)
 #ifdef CONFIG_CPU_XLP
 	xlp_config_lsu
+	xlp_early_mmu_init
 #endif
 	jr	ra
 	nop
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index 6baae15cc7b..4fde7ac76cc 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -135,10 +135,6 @@ void nlm_smp_finish(void)
 	local_irq_enable();
 }
 
-void nlm_cpus_done(void)
-{
-}
-
 /*
  * Boot all other cpus in the system, initialize them, and bring them into
  * the boot function
@@ -198,7 +194,7 @@ void __init nlm_smp_setup(void)
 	cpumask_scnprintf(buf, ARRAY_SIZE(buf), cpu_possible_mask);
 	pr_info("Possible CPU mask: %s\n", buf);
 
-	/* check with the cores we have worken up */
+	/* check with the cores we have woken up */
 	for (ncore = 0, i = 0; i < NLM_NR_NODES; i++)
 		ncore += hweight32(nlm_get_node(i)->coremask);
 
@@ -213,6 +209,7 @@ static int nlm_parse_cpumask(cpumask_t *wakeup_mask)
 {
 	uint32_t core0_thr_mask, core_thr_mask;
 	int threadmode, i, j;
+	char buf[64];
 
 	core0_thr_mask = 0;
 	for (i = 0; i < NLM_THREADS_PER_CORE; i++)
@@ -247,8 +244,8 @@ static int nlm_parse_cpumask(cpumask_t *wakeup_mask)
 	return threadmode;
 
 unsupp:
-	panic("Unsupported CPU mask %lx",
-		(unsigned long)cpumask_bits(wakeup_mask)[0]);
+	cpumask_scnprintf(buf, ARRAY_SIZE(buf), wakeup_mask);
+	panic("Unsupported CPU mask %s", buf);
 	return 0;
 }
 
@@ -277,7 +274,6 @@ struct plat_smp_ops nlm_smp_ops = {
 	.send_ipi_mask		= nlm_send_ipi_mask,
 	.init_secondary		= nlm_init_secondary,
 	.smp_finish		= nlm_smp_finish,
-	.cpus_done		= nlm_cpus_done,
 	.boot_secondary		= nlm_boot_secondary,
 	.smp_setup		= nlm_smp_setup,
 	.prepare_cpus		= nlm_prepare_cpus,
diff --git a/arch/mips/netlogic/common/smpboot.S b/arch/mips/netlogic/common/smpboot.S
index 8597657c27f..805355b0bd0 100644
--- a/arch/mips/netlogic/common/smpboot.S
+++ b/arch/mips/netlogic/common/smpboot.S
@@ -54,8 +54,9 @@
 	.set	noat
 	.set	arch=xlr		/* for mfcr/mtcr, XLR is sufficient */
 
-FEXPORT(xlp_boot_core0_siblings)	/* "Master" cpu starts from here */
-	dmtc0	sp, $4, 2		/* SP saved in UserLocal */
+/* Called by the boot cpu to wake up its sibling threads */
+NESTED(xlp_boot_core0_siblings, PT_SIZE, sp)
+	/* CPU register contents lost when enabling threads, save them first */
 	SAVE_ALL
 	sync
 	/* find the location to which nlm_boot_siblings was relocated */
@@ -65,9 +66,12 @@ FEXPORT(xlp_boot_core0_siblings)	/* "Master" cpu starts from here */
 	dsubu	t2, t1
 	daddu	t2, t0
 	/* call it */
-	jr	t2
+	jalr	t2
 	nop
-	/* not reached */
+	RESTORE_ALL
+	jr	ra
+	nop
+END(xlp_boot_core0_siblings)
 
 NESTED(nlm_boot_secondary_cpus, 16, sp)
 	/* Initialize CP0 Status */
diff --git a/arch/mips/netlogic/common/time.c b/arch/mips/netlogic/common/time.c
index 13391b8a603..0c0a1a606f7 100644
--- a/arch/mips/netlogic/common/time.c
+++ b/arch/mips/netlogic/common/time.c
@@ -82,6 +82,7 @@ static struct clocksource csrc_pic = {
 static void nlm_init_pic_timer(void)
 {
 	uint64_t picbase = nlm_get_node(0)->picbase;
+	u32 picfreq;
 
 	nlm_pic_set_timer(picbase, PIC_CLOCK_TIMER, ~0ULL, 0, 0);
 	if (current_cpu_data.cputype == CPU_XLR) {
@@ -92,7 +93,9 @@ static void nlm_init_pic_timer(void)
 		csrc_pic.read	= nlm_get_pic_timer;
 	}
 	csrc_pic.rating = 1000;
-	clocksource_register_hz(&csrc_pic, pic_timer_freq());
+	picfreq = pic_timer_freq();
+	clocksource_register_hz(&csrc_pic, picfreq);
+	pr_info("PIC clock source added, frequency %d\n", picfreq);
 }
 
 void __init plat_time_init(void)
diff --git a/arch/mips/netlogic/dts/xlp_gvp.dts b/arch/mips/netlogic/dts/xlp_gvp.dts
index 047d27f5448..bb4ecd1d47f 100644
--- a/arch/mips/netlogic/dts/xlp_gvp.dts
+++ b/arch/mips/netlogic/dts/xlp_gvp.dts
@@ -26,11 +26,12 @@
 			interrupt-parent = <&pic>;
 			interrupts = <17>;
 		};
-		pic: pic@4000 {
-			interrupt-controller;
+		pic: pic@110000 {
+			compatible = "netlogic,xlp-pic";
 			#address-cells = <0>;
 			#interrupt-cells = <1>;
 			reg = <0 0x110000 0x200>;
+			interrupt-controller;
 		};
 
 		nor_flash@1,0 {
diff --git a/arch/mips/netlogic/xlp/Makefile b/arch/mips/netlogic/xlp/Makefile
index ed9a93c0465..be358a8050c 100644
--- a/arch/mips/netlogic/xlp/Makefile
+++ b/arch/mips/netlogic/xlp/Makefile
@@ -2,3 +2,5 @@ obj-y				+= setup.o nlm_hal.o cop2-ex.o dt.o
 obj-$(CONFIG_SMP)		+= wakeup.o
 obj-$(CONFIG_USB)		+= usb-init.o
 obj-$(CONFIG_USB)		+= usb-init-xlp2.o
+obj-$(CONFIG_SATA_AHCI)		+= ahci-init.o
+obj-$(CONFIG_SATA_AHCI)		+= ahci-init-xlp2.o
diff --git a/arch/mips/netlogic/xlp/ahci-init-xlp2.c b/arch/mips/netlogic/xlp/ahci-init-xlp2.c
new file mode 100644
index 00000000000..c83dbf3689e
--- /dev/null
+++ b/arch/mips/netlogic/xlp/ahci-init-xlp2.c
@@ -0,0 +1,377 @@
+/*
+ * Copyright (c) 2003-2014 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/irq.h>
+#include <linux/bitops.h>
+#include <linux/pci_ids.h>
+#include <linux/nodemask.h>
+
+#include <asm/cpu.h>
+#include <asm/mipsregs.h>
+
+#include <asm/netlogic/common.h>
+#include <asm/netlogic/haldefs.h>
+#include <asm/netlogic/mips-extns.h>
+#include <asm/netlogic/xlp-hal/xlp.h>
+#include <asm/netlogic/xlp-hal/iomap.h>
+
+#define SATA_CTL		0x0
+#define SATA_STATUS		0x1 /* Status Reg */
+#define SATA_INT		0x2 /* Interrupt Reg */
+#define SATA_INT_MASK		0x3 /* Interrupt Mask Reg */
+#define SATA_BIU_TIMEOUT	0x4
+#define AXIWRSPERRLOG		0x5
+#define AXIRDSPERRLOG		0x6
+#define BiuTimeoutLow		0x7
+#define BiuTimeoutHi		0x8
+#define BiuSlvErLow		0x9
+#define BiuSlvErHi		0xa
+#define IO_CONFIG_SWAP_DIS	0xb
+#define CR_REG_TIMER		0xc
+#define CORE_ID			0xd
+#define AXI_SLAVE_OPT1		0xe
+#define PHY_MEM_ACCESS		0xf
+#define PHY0_CNTRL		0x10
+#define PHY0_STAT		0x11
+#define PHY0_RX_ALIGN		0x12
+#define PHY0_RX_EQ_LO		0x13
+#define PHY0_RX_EQ_HI		0x14
+#define PHY0_BIST_LOOP		0x15
+#define PHY1_CNTRL		0x16
+#define PHY1_STAT		0x17
+#define PHY1_RX_ALIGN		0x18
+#define PHY1_RX_EQ_LO		0x19
+#define PHY1_RX_EQ_HI		0x1a
+#define PHY1_BIST_LOOP		0x1b
+#define RdExBase		0x1c
+#define RdExLimit		0x1d
+#define CacheAllocBase		0x1e
+#define CacheAllocLimit		0x1f
+#define BiuSlaveCmdGstNum	0x20
+
+/*SATA_CTL Bits */
+#define SATA_RST_N		BIT(0)  /* Active low reset sata_core phy */
+#define SataCtlReserve0		BIT(1)
+#define M_CSYSREQ		BIT(2)  /* AXI master low power, not used */
+#define S_CSYSREQ		BIT(3)  /* AXI slave low power, not used */
+#define P0_CP_DET		BIT(8)  /* Reserved, bring in from pad */
+#define P0_MP_SW		BIT(9)  /* Mech Switch */
+#define P0_DISABLE		BIT(10) /* disable p0 */
+#define P0_ACT_LED_EN		BIT(11) /* Active LED enable */
+#define P0_IRST_HARD_SYNTH	BIT(12) /* PHY hard synth reset */
+#define P0_IRST_HARD_TXRX	BIT(13) /* PHY lane hard reset */
+#define P0_IRST_POR		BIT(14) /* PHY power on reset*/
+#define P0_IPDTXL		BIT(15) /* PHY Tx lane dis/power down */
+#define P0_IPDRXL		BIT(16) /* PHY Rx lane dis/power down */
+#define P0_IPDIPDMSYNTH		BIT(17) /* PHY synthesizer dis/porwer down */
+#define P0_CP_POD_EN		BIT(18) /* CP_POD enable */
+#define P0_AT_BYPASS		BIT(19) /* P0 address translation by pass */
+#define P1_CP_DET		BIT(20) /* Reserved,Cold Detect */
+#define P1_MP_SW		BIT(21) /* Mech Switch */
+#define P1_DISABLE		BIT(22) /* disable p1 */
+#define P1_ACT_LED_EN		BIT(23) /* Active LED enable */
+#define P1_IRST_HARD_SYNTH	BIT(24) /* PHY hard synth reset */
+#define P1_IRST_HARD_TXRX	BIT(25) /* PHY lane hard reset */
+#define P1_IRST_POR		BIT(26) /* PHY power on reset*/
+#define P1_IPDTXL		BIT(27) /* PHY Tx lane dis/porwer down */
+#define P1_IPDRXL		BIT(28) /* PHY Rx lane dis/porwer down */
+#define P1_IPDIPDMSYNTH		BIT(29) /* PHY synthesizer dis/porwer down */
+#define P1_CP_POD_EN		BIT(30)
+#define P1_AT_BYPASS		BIT(31) /* P1 address translation by pass */
+
+/* Status register */
+#define M_CACTIVE		BIT(0)  /* m_cactive, not used */
+#define S_CACTIVE		BIT(1)  /* s_cactive, not used */
+#define P0_PHY_READY		BIT(8)  /* phy is ready */
+#define P0_CP_POD		BIT(9)  /* Cold PowerOn */
+#define P0_SLUMBER		BIT(10) /* power mode slumber */
+#define P0_PATIAL		BIT(11) /* power mode patial */
+#define P0_PHY_SIG_DET		BIT(12) /* phy dignal detect */
+#define P0_PHY_CALI		BIT(13) /* phy calibration done */
+#define P1_PHY_READY		BIT(16) /* phy is ready */
+#define P1_CP_POD		BIT(17) /* Cold PowerOn */
+#define P1_SLUMBER		BIT(18) /* power mode slumber */
+#define P1_PATIAL		BIT(19) /* power mode patial */
+#define P1_PHY_SIG_DET		BIT(20) /* phy dignal detect */
+#define P1_PHY_CALI		BIT(21) /* phy calibration done */
+
+/* SATA CR_REG_TIMER bits */
+#define CR_TIME_SCALE		(0x1000 << 0)
+
+/* SATA PHY specific registers start and end address */
+#define RXCDRCALFOSC0		0x0065
+#define CALDUTY			0x006e
+#define RXDPIF			0x8065
+#define PPMDRIFTMAX_HI		0x80A4
+
+#define nlm_read_sata_reg(b, r)		nlm_read_reg(b, r)
+#define nlm_write_sata_reg(b, r, v)	nlm_write_reg(b, r, v)
+#define nlm_get_sata_pcibase(node)	\
+		nlm_pcicfg_base(XLP9XX_IO_SATA_OFFSET(node))
+#define nlm_get_sata_regbase(node)	\
+		(nlm_get_sata_pcibase(node) + 0x100)
+
+/* SATA PHY config for register block 1 0x0065 .. 0x006e */
+static const u8 sata_phy_config1[]  = {
+	0xC9, 0xC9, 0x07, 0x07, 0x18, 0x18, 0x01, 0x01, 0x22, 0x00
+};
+
+/* SATA PHY config for register block 2 0x0x8065 .. 0x0x80A4 */
+static const u8 sata_phy_config2[]  = {
+	0xAA, 0x00, 0x4C, 0xC9, 0xC9, 0x07, 0x07, 0x18,
+	0x18, 0x05, 0x0C, 0x10, 0x00, 0x10, 0x00, 0xFF,
+	0xCF, 0xF7, 0xE1, 0xF5, 0xFD, 0xFD, 0xFF, 0xFF,
+	0xFF, 0xFF, 0xE3, 0xE7, 0xDB, 0xF5, 0xFD, 0xFD,
+	0xF5, 0xF5, 0xFF, 0xFF, 0xE3, 0xE7, 0xDB, 0xF5,
+	0xFD, 0xFD, 0xF5, 0xF5, 0xFF, 0xFF, 0xFF, 0xF5,
+	0x3F, 0x00, 0x32, 0x00, 0x03, 0x01, 0x05, 0x05,
+	0x04, 0x00, 0x00, 0x08, 0x04, 0x00, 0x00, 0x04,
+};
+
+const int sata_phy_debug = 0;	/* set to verify PHY writes */
+
+static void sata_clear_glue_reg(u64 regbase, u32 off, u32 bit)
+{
+	u32 reg_val;
+
+	reg_val = nlm_read_sata_reg(regbase, off);
+	nlm_write_sata_reg(regbase, off, (reg_val & ~bit));
+}
+
+static void sata_set_glue_reg(u64 regbase, u32 off, u32 bit)
+{
+	u32 reg_val;
+
+	reg_val = nlm_read_sata_reg(regbase, off);
+	nlm_write_sata_reg(regbase, off, (reg_val | bit));
+}
+
+static void write_phy_reg(u64 regbase, u32 addr, u32 physel, u8 data)
+{
+	nlm_write_sata_reg(regbase, PHY_MEM_ACCESS,
+		(1u << 31) | (physel << 24) | (data << 16) | addr);
+	udelay(850);
+}
+
+static u8 read_phy_reg(u64 regbase, u32 addr, u32 physel)
+{
+	u32 val;
+
+	nlm_write_sata_reg(regbase, PHY_MEM_ACCESS,
+		(0 << 31) | (physel << 24) | (0 << 16) | addr);
+	udelay(850);
+	val = nlm_read_sata_reg(regbase, PHY_MEM_ACCESS);
+	return (val >> 16) & 0xff;
+}
+
+static void config_sata_phy(u64 regbase)
+{
+	u32 port, i, reg;
+
+	for (port = 0; port < 2; port++) {
+		for (i = 0, reg = RXCDRCALFOSC0; reg <= CALDUTY; reg++, i++)
+			write_phy_reg(regbase, reg, port, sata_phy_config1[i]);
+
+		for (i = 0, reg = RXDPIF; reg <= PPMDRIFTMAX_HI; reg++, i++)
+			write_phy_reg(regbase, reg, port, sata_phy_config2[i]);
+	}
+}
+
+static void check_phy_register(u64 regbase, u32 addr, u32 physel, u8 xdata)
+{
+	u8 data;
+
+	data = read_phy_reg(regbase, addr, physel);
+	pr_info("PHY read addr = 0x%x physel = %d data = 0x%x %s\n",
+		addr, physel, data, data == xdata ? "TRUE" : "FALSE");
+}
+
+static void verify_sata_phy_config(u64 regbase)
+{
+	u32 port, i, reg;
+
+	for (port = 0; port < 2; port++) {
+		for (i = 0, reg = RXCDRCALFOSC0; reg <= CALDUTY; reg++, i++)
+			check_phy_register(regbase, reg, port,
+						sata_phy_config1[i]);
+
+		for (i = 0, reg = RXDPIF; reg <= PPMDRIFTMAX_HI; reg++, i++)
+			check_phy_register(regbase, reg, port,
+						sata_phy_config2[i]);
+	}
+}
+
+static void nlm_sata_firmware_init(int node)
+{
+	u32 reg_val;
+	u64 regbase;
+	int n;
+
+	pr_info("Initializing XLP9XX On-chip AHCI...\n");
+	regbase = nlm_get_sata_regbase(node);
+
+	/* Reset port0 */
+	sata_clear_glue_reg(regbase, SATA_CTL, P0_IRST_POR);
+	sata_clear_glue_reg(regbase, SATA_CTL, P0_IRST_HARD_TXRX);
+	sata_clear_glue_reg(regbase, SATA_CTL, P0_IRST_HARD_SYNTH);
+	sata_clear_glue_reg(regbase, SATA_CTL, P0_IPDTXL);
+	sata_clear_glue_reg(regbase, SATA_CTL, P0_IPDRXL);
+	sata_clear_glue_reg(regbase, SATA_CTL, P0_IPDIPDMSYNTH);
+
+	/* port1 */
+	sata_clear_glue_reg(regbase, SATA_CTL, P1_IRST_POR);
+	sata_clear_glue_reg(regbase, SATA_CTL, P1_IRST_HARD_TXRX);
+	sata_clear_glue_reg(regbase, SATA_CTL, P1_IRST_HARD_SYNTH);
+	sata_clear_glue_reg(regbase, SATA_CTL, P1_IPDTXL);
+	sata_clear_glue_reg(regbase, SATA_CTL, P1_IPDRXL);
+	sata_clear_glue_reg(regbase, SATA_CTL, P1_IPDIPDMSYNTH);
+	udelay(300);
+
+	/* Set PHY */
+	sata_set_glue_reg(regbase, SATA_CTL, P0_IPDTXL);
+	sata_set_glue_reg(regbase, SATA_CTL, P0_IPDRXL);
+	sata_set_glue_reg(regbase, SATA_CTL, P0_IPDIPDMSYNTH);
+	sata_set_glue_reg(regbase, SATA_CTL, P1_IPDTXL);
+	sata_set_glue_reg(regbase, SATA_CTL, P1_IPDRXL);
+	sata_set_glue_reg(regbase, SATA_CTL, P1_IPDIPDMSYNTH);
+
+	udelay(1000);
+	sata_set_glue_reg(regbase, SATA_CTL, P0_IRST_POR);
+	udelay(1000);
+	sata_set_glue_reg(regbase, SATA_CTL, P1_IRST_POR);
+	udelay(1000);
+
+	/* setup PHY */
+	config_sata_phy(regbase);
+	if (sata_phy_debug)
+		verify_sata_phy_config(regbase);
+
+	udelay(1000);
+	sata_set_glue_reg(regbase, SATA_CTL, P0_IRST_HARD_TXRX);
+	sata_set_glue_reg(regbase, SATA_CTL, P0_IRST_HARD_SYNTH);
+	sata_set_glue_reg(regbase, SATA_CTL, P1_IRST_HARD_TXRX);
+	sata_set_glue_reg(regbase, SATA_CTL, P1_IRST_HARD_SYNTH);
+	udelay(300);
+
+	/* Override reset in serial PHY mode */
+	sata_set_glue_reg(regbase, CR_REG_TIMER, CR_TIME_SCALE);
+	/* Set reset SATA */
+	sata_set_glue_reg(regbase, SATA_CTL, SATA_RST_N);
+	sata_set_glue_reg(regbase, SATA_CTL, M_CSYSREQ);
+	sata_set_glue_reg(regbase, SATA_CTL, S_CSYSREQ);
+
+	pr_debug("Waiting for PHYs to come up.\n");
+	n = 10000;
+	do {
+		reg_val = nlm_read_sata_reg(regbase, SATA_STATUS);
+		if ((reg_val & P1_PHY_READY) && (reg_val & P0_PHY_READY))
+			break;
+		udelay(10);
+	} while (--n > 0);
+
+	if (reg_val  & P0_PHY_READY)
+		pr_info("PHY0 is up.\n");
+	else
+		pr_info("PHY0 is down.\n");
+	if (reg_val  & P1_PHY_READY)
+		pr_info("PHY1 is up.\n");
+	else
+		pr_info("PHY1 is down.\n");
+
+	pr_info("XLP AHCI Init Done.\n");
+}
+
+static int __init nlm_ahci_init(void)
+{
+	int node;
+
+	if (!cpu_is_xlp9xx())
+		return 0;
+	for (node = 0; node < NLM_NR_NODES; node++)
+		if (nlm_node_present(node))
+			nlm_sata_firmware_init(node);
+	return 0;
+}
+
+static void nlm_sata_intr_ack(struct irq_data *data)
+{
+	u64 regbase;
+	u32 val;
+	int node;
+
+	node = data->irq / NLM_IRQS_PER_NODE;
+	regbase = nlm_get_sata_regbase(node);
+	val = nlm_read_sata_reg(regbase, SATA_INT);
+	sata_set_glue_reg(regbase, SATA_INT, val);
+}
+
+static void nlm_sata_fixup_bar(struct pci_dev *dev)
+{
+	dev->resource[5] = dev->resource[0];
+	memset(&dev->resource[0], 0, sizeof(dev->resource[0]));
+}
+
+static void nlm_sata_fixup_final(struct pci_dev *dev)
+{
+	u32 val;
+	u64 regbase;
+	int node;
+
+	/* Find end bridge function to find node */
+	node = xlp_socdev_to_node(dev);
+	regbase = nlm_get_sata_regbase(node);
+
+	/* clear pending interrupts and then enable them */
+	val = nlm_read_sata_reg(regbase, SATA_INT);
+	sata_set_glue_reg(regbase, SATA_INT, val);
+
+	/* Enable only the core interrupt */
+	sata_set_glue_reg(regbase, SATA_INT_MASK, 0x1);
+
+	dev->irq = nlm_irq_to_xirq(node, PIC_SATA_IRQ);
+	nlm_set_pic_extra_ack(node, PIC_SATA_IRQ, nlm_sata_intr_ack);
+}
+
+arch_initcall(nlm_ahci_init);
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_XLP9XX_SATA,
+		nlm_sata_fixup_bar);
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_BROADCOM, PCI_DEVICE_ID_XLP9XX_SATA,
+		nlm_sata_fixup_final);
diff --git a/arch/mips/netlogic/xlp/ahci-init.c b/arch/mips/netlogic/xlp/ahci-init.c
new file mode 100644
index 00000000000..a9d0fae0210
--- /dev/null
+++ b/arch/mips/netlogic/xlp/ahci-init.c
@@ -0,0 +1,209 @@
+/*
+ * Copyright (c) 2003-2014 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/irq.h>
+#include <linux/bitops.h>
+
+#include <asm/cpu.h>
+#include <asm/mipsregs.h>
+
+#include <asm/netlogic/haldefs.h>
+#include <asm/netlogic/xlp-hal/xlp.h>
+#include <asm/netlogic/common.h>
+#include <asm/netlogic/xlp-hal/iomap.h>
+#include <asm/netlogic/mips-extns.h>
+
+#define SATA_CTL		0x0
+#define SATA_STATUS		0x1	/* Status Reg */
+#define SATA_INT		0x2	/* Interrupt Reg */
+#define SATA_INT_MASK		0x3	/* Interrupt Mask Reg */
+#define SATA_CR_REG_TIMER	0x4	/* PHY Conrol Timer Reg */
+#define SATA_CORE_ID		0x5	/* Core ID Reg */
+#define SATA_AXI_SLAVE_OPT1	0x6	/* AXI Slave Options Reg */
+#define SATA_PHY_LOS_LEV	0x7	/* PHY LOS Level Reg */
+#define SATA_PHY_MULTI		0x8	/* PHY Multiplier Reg */
+#define SATA_PHY_CLK_SEL	0x9	/* Clock Select Reg */
+#define SATA_PHY_AMP1_GEN1	0xa	/* PHY Transmit Amplitude Reg 1 */
+#define SATA_PHY_AMP1_GEN2	0xb	/* PHY Transmit Amplitude Reg 2 */
+#define SATA_PHY_AMP1_GEN3	0xc	/* PHY Transmit Amplitude Reg 3 */
+#define SATA_PHY_PRE1		0xd	/* PHY Transmit Preemphasis Reg 1 */
+#define SATA_PHY_PRE2		0xe	/* PHY Transmit Preemphasis Reg 2 */
+#define SATA_PHY_PRE3		0xf	/* PHY Transmit Preemphasis Reg 3 */
+#define SATA_SPDMODE		0x10	/* Speed Mode Reg */
+#define SATA_REFCLK		0x11	/* Reference Clock Control Reg */
+#define SATA_BYTE_SWAP_DIS	0x12	/* byte swap disable */
+
+/*SATA_CTL Bits */
+#define SATA_RST_N		BIT(0)
+#define PHY0_RESET_N		BIT(16)
+#define PHY1_RESET_N		BIT(17)
+#define PHY2_RESET_N		BIT(18)
+#define PHY3_RESET_N		BIT(19)
+#define M_CSYSREQ		BIT(2)
+#define S_CSYSREQ		BIT(3)
+
+/*SATA_STATUS Bits */
+#define P0_PHY_READY		BIT(4)
+#define P1_PHY_READY		BIT(5)
+#define P2_PHY_READY		BIT(6)
+#define P3_PHY_READY		BIT(7)
+
+#define nlm_read_sata_reg(b, r)		nlm_read_reg(b, r)
+#define nlm_write_sata_reg(b, r, v)	nlm_write_reg(b, r, v)
+#define nlm_get_sata_pcibase(node)	\
+		nlm_pcicfg_base(XLP_IO_SATA_OFFSET(node))
+/* SATA device specific configuration registers are starts at 0x900 offset */
+#define nlm_get_sata_regbase(node)	\
+		(nlm_get_sata_pcibase(node) + 0x900)
+
+static void sata_clear_glue_reg(uint64_t regbase, uint32_t off, uint32_t bit)
+{
+	uint32_t reg_val;
+
+	reg_val = nlm_read_sata_reg(regbase, off);
+	nlm_write_sata_reg(regbase, off, (reg_val & ~bit));
+}
+
+static void sata_set_glue_reg(uint64_t regbase, uint32_t off, uint32_t bit)
+{
+	uint32_t reg_val;
+
+	reg_val = nlm_read_sata_reg(regbase, off);
+	nlm_write_sata_reg(regbase, off, (reg_val | bit));
+}
+
+static void nlm_sata_firmware_init(int node)
+{
+	uint32_t reg_val;
+	uint64_t regbase;
+	int i;
+
+	pr_info("XLP AHCI Initialization started.\n");
+	regbase = nlm_get_sata_regbase(node);
+
+	/* Reset SATA */
+	sata_clear_glue_reg(regbase, SATA_CTL, SATA_RST_N);
+	/* Reset PHY */
+	sata_clear_glue_reg(regbase, SATA_CTL,
+			(PHY3_RESET_N | PHY2_RESET_N
+			 | PHY1_RESET_N | PHY0_RESET_N));
+
+	/* Set SATA */
+	sata_set_glue_reg(regbase, SATA_CTL, SATA_RST_N);
+	/* Set PHY */
+	sata_set_glue_reg(regbase, SATA_CTL,
+			(PHY3_RESET_N | PHY2_RESET_N
+			 | PHY1_RESET_N | PHY0_RESET_N));
+
+	pr_debug("Waiting for PHYs to come up.\n");
+	i = 0;
+	do {
+		reg_val = nlm_read_sata_reg(regbase, SATA_STATUS);
+		i++;
+	} while (((reg_val & 0xF0) != 0xF0) && (i < 10000));
+
+	for (i = 0; i < 4; i++) {
+		if (reg_val  & (P0_PHY_READY << i))
+			pr_info("PHY%d is up.\n", i);
+		else
+			pr_info("PHY%d is down.\n", i);
+	}
+
+	pr_info("XLP AHCI init done.\n");
+}
+
+static int __init nlm_ahci_init(void)
+{
+	int node = 0;
+	int chip = read_c0_prid() & PRID_REV_MASK;
+
+	if (chip == PRID_IMP_NETLOGIC_XLP3XX)
+		nlm_sata_firmware_init(node);
+	return 0;
+}
+
+static void nlm_sata_intr_ack(struct irq_data *data)
+{
+	uint32_t val = 0;
+	uint64_t regbase;
+
+	regbase = nlm_get_sata_regbase(nlm_nodeid());
+	val = nlm_read_sata_reg(regbase, SATA_INT);
+	sata_set_glue_reg(regbase, SATA_INT, val);
+}
+
+static void nlm_sata_fixup_bar(struct pci_dev *dev)
+{
+	/*
+	 * The AHCI resource is in BAR 0, move it to
+	 * BAR 5, where it is expected
+	 */
+	dev->resource[5] = dev->resource[0];
+	memset(&dev->resource[0], 0, sizeof(dev->resource[0]));
+}
+
+static void nlm_sata_fixup_final(struct pci_dev *dev)
+{
+	uint32_t val;
+	uint64_t regbase;
+	int node = 0; /* XLP3XX does not support multi-node */
+
+	regbase = nlm_get_sata_regbase(node);
+
+	/* clear pending interrupts and then enable them */
+	val = nlm_read_sata_reg(regbase, SATA_INT);
+	sata_set_glue_reg(regbase, SATA_INT, val);
+
+	/* Mask the core interrupt. If all the interrupts
+	 * are enabled there are spurious interrupt flow
+	 * happening, to avoid only enable core interrupt
+	 * mask.
+	 */
+	sata_set_glue_reg(regbase, SATA_INT_MASK, 0x1);
+
+	dev->irq = PIC_SATA_IRQ;
+	nlm_set_pic_extra_ack(node, PIC_SATA_IRQ, nlm_sata_intr_ack);
+}
+
+arch_initcall(nlm_ahci_init);
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_NETLOGIC, PCI_DEVICE_ID_NLM_SATA,
+		nlm_sata_fixup_bar);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_NETLOGIC, PCI_DEVICE_ID_NLM_SATA,
+		nlm_sata_fixup_final);
diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c
index bdde33147bc..7cc46032b28 100644
--- a/arch/mips/netlogic/xlp/dt.c
+++ b/arch/mips/netlogic/xlp/dt.c
@@ -48,9 +48,10 @@ static void *xlp_fdt_blob;
 void __init *xlp_dt_init(void *fdtp)
 {
 	if (!fdtp) {
-		switch (current_cpu_data.processor_id & 0xff00) {
+		switch (current_cpu_data.processor_id & PRID_IMP_MASK) {
 #ifdef CONFIG_DT_XLP_GVP
 		case PRID_IMP_NETLOGIC_XLP9XX:
+		case PRID_IMP_NETLOGIC_XLP5XX:
 			fdtp = __dtb_xlp_gvp_begin;
 			break;
 #endif
diff --git a/arch/mips/netlogic/xlp/nlm_hal.c b/arch/mips/netlogic/xlp/nlm_hal.c
index 997cd9ee10d..bc24beb3a42 100644
--- a/arch/mips/netlogic/xlp/nlm_hal.c
+++ b/arch/mips/netlogic/xlp/nlm_hal.c
@@ -54,6 +54,8 @@ void nlm_node_init(int node)
 	struct nlm_soc_info *nodep;
 
 	nodep = nlm_get_node(node);
+	if (node == 0)
+		nodep->coremask = 1;	/* node 0, boot cpu */
 	nodep->sysbase = nlm_get_sys_regbase(node);
 	nodep->picbase = nlm_get_pic_regbase(node);
 	nodep->ebase = read_c0_ebase() & (~((1 << 12) - 1));
@@ -64,31 +66,39 @@ void nlm_node_init(int node)
 	spin_lock_init(&nodep->piclock);
 }
 
-int nlm_irq_to_irt(int irq)
+static int xlp9xx_irq_to_irt(int irq)
+{
+	switch (irq) {
+	case PIC_GPIO_IRQ:
+		return 12;
+	case PIC_9XX_XHCI_0_IRQ:
+		return 114;
+	case PIC_9XX_XHCI_1_IRQ:
+		return 115;
+	case PIC_UART_0_IRQ:
+		return 133;
+	case PIC_UART_1_IRQ:
+		return 134;
+	case PIC_SATA_IRQ:
+		return 143;
+	case PIC_SPI_IRQ:
+		return 152;
+	case PIC_MMC_IRQ:
+		return 153;
+	case PIC_PCIE_LINK_LEGACY_IRQ(0):
+	case PIC_PCIE_LINK_LEGACY_IRQ(1):
+	case PIC_PCIE_LINK_LEGACY_IRQ(2):
+	case PIC_PCIE_LINK_LEGACY_IRQ(3):
+		return 191 + irq - PIC_PCIE_LINK_LEGACY_IRQ_BASE;
+	}
+	return -1;
+}
+
+static int xlp_irq_to_irt(int irq)
 {
 	uint64_t pcibase;
 	int devoff, irt;
 
-	/* bypass for 9xx */
-	if (cpu_is_xlp9xx()) {
-		switch (irq) {
-		case PIC_9XX_XHCI_0_IRQ:
-			return 114;
-		case PIC_9XX_XHCI_1_IRQ:
-			return 115;
-		case PIC_UART_0_IRQ:
-			return 133;
-		case PIC_UART_1_IRQ:
-			return 134;
-		case PIC_PCIE_LINK_LEGACY_IRQ(0):
-		case PIC_PCIE_LINK_LEGACY_IRQ(1):
-		case PIC_PCIE_LINK_LEGACY_IRQ(2):
-		case PIC_PCIE_LINK_LEGACY_IRQ(3):
-			return 191 + irq - PIC_PCIE_LINK_LEGACY_IRQ_BASE;
-		}
-		return -1;
-	}
-
 	devoff = 0;
 	switch (irq) {
 	case PIC_UART_0_IRQ:
@@ -98,7 +108,7 @@ int nlm_irq_to_irt(int irq)
 		devoff = XLP_IO_UART1_OFFSET(0);
 		break;
 	case PIC_MMC_IRQ:
-		devoff = XLP_IO_SD_OFFSET(0);
+		devoff = XLP_IO_MMC_OFFSET(0);
 		break;
 	case PIC_I2C_0_IRQ:	/* I2C will be fixed up */
 	case PIC_I2C_1_IRQ:
@@ -109,6 +119,18 @@ int nlm_irq_to_irt(int irq)
 		else
 			devoff = XLP_IO_I2C0_OFFSET(0);
 		break;
+	case PIC_SATA_IRQ:
+		devoff = XLP_IO_SATA_OFFSET(0);
+		break;
+	case PIC_GPIO_IRQ:
+		devoff = XLP_IO_GPIO_OFFSET(0);
+		break;
+	case PIC_NAND_IRQ:
+		devoff = XLP_IO_NAND_OFFSET(0);
+		break;
+	case PIC_SPI_IRQ:
+		devoff = XLP_IO_SPI_OFFSET(0);
+		break;
 	default:
 		if (cpu_is_xlpii()) {
 			switch (irq) {
@@ -164,61 +186,123 @@ int nlm_irq_to_irt(int irq)
 		/* HW bug, PCI IRT entries are bad on early silicon, fix */
 		irt = PIC_IRT_PCIE_LINK_INDEX(irq -
 					PIC_PCIE_LINK_LEGACY_IRQ_BASE);
-	} else if (irq >= PIC_PCIE_LINK_MSI_IRQ(0) &&
-			irq <= PIC_PCIE_LINK_MSI_IRQ(3)) {
-		irt = -2;
-	} else if (irq >= PIC_PCIE_MSIX_IRQ(0) &&
-			irq <= PIC_PCIE_MSIX_IRQ(3)) {
-		irt = -2;
 	} else {
 		irt = -1;
 	}
 	return irt;
 }
 
-unsigned int nlm_get_core_frequency(int node, int core)
+int nlm_irq_to_irt(int irq)
 {
-	unsigned int pll_divf, pll_divr, dfs_div, ext_div;
-	unsigned int rstval, dfsval, denom;
-	uint64_t num, sysbase;
+	/* return -2 for irqs without 1-1 mapping */
+	if (irq >= PIC_PCIE_LINK_MSI_IRQ(0) && irq <= PIC_PCIE_LINK_MSI_IRQ(3))
+		return -2;
+	if (irq >= PIC_PCIE_MSIX_IRQ(0) && irq <= PIC_PCIE_MSIX_IRQ(3))
+		return -2;
 
-	sysbase = nlm_get_node(node)->sysbase;
 	if (cpu_is_xlp9xx())
-		rstval = nlm_read_sys_reg(sysbase, SYS_9XX_POWER_ON_RESET_CFG);
+		return xlp9xx_irq_to_irt(irq);
 	else
-		rstval = nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG);
-	if (cpu_is_xlpii()) {
-		num = 1000000ULL * (400 * 3 + 100 * (rstval >> 26));
-		denom = 3;
+		return xlp_irq_to_irt(irq);
+}
+
+static unsigned int nlm_xlp2_get_core_frequency(int node, int core)
+{
+	unsigned int pll_post_div, ctrl_val0, ctrl_val1, denom;
+	uint64_t num, sysbase, clockbase;
+
+	if (cpu_is_xlp9xx()) {
+		clockbase = nlm_get_clock_regbase(node);
+		ctrl_val0 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_CPU_PLL_CTRL0(core));
+		ctrl_val1 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_CPU_PLL_CTRL1(core));
 	} else {
-		dfsval = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIV_VALUE);
-		pll_divf = ((rstval >> 10) & 0x7f) + 1;
-		pll_divr = ((rstval >> 8)  & 0x3) + 1;
-		ext_div  = ((rstval >> 30) & 0x3) + 1;
-		dfs_div  = ((dfsval >> (core * 4)) & 0xf) + 1;
-
-		num = 800000000ULL * pll_divf;
-		denom = 3 * pll_divr * ext_div * dfs_div;
+		sysbase = nlm_get_node(node)->sysbase;
+		ctrl_val0 = nlm_read_sys_reg(sysbase,
+						SYS_CPU_PLL_CTRL0(core));
+		ctrl_val1 = nlm_read_sys_reg(sysbase,
+						SYS_CPU_PLL_CTRL1(core));
+	}
+
+	/* Find PLL post divider value */
+	switch ((ctrl_val0 >> 24) & 0x7) {
+	case 1:
+		pll_post_div = 2;
+		break;
+	case 3:
+		pll_post_div = 4;
+		break;
+	case 7:
+		pll_post_div = 8;
+		break;
+	case 6:
+		pll_post_div = 16;
+		break;
+	case 0:
+	default:
+		pll_post_div = 1;
+		break;
 	}
+
+	num = 1000000ULL * (400 * 3 + 100 * (ctrl_val1 & 0x3f));
+	denom = 3 * pll_post_div;
 	do_div(num, denom);
+
 	return (unsigned int)num;
 }
 
-/* Calculate Frequency to the PIC from PLL.
- * freq_out = ( ref_freq/2 * (6 + ctrl2[7:0]) + ctrl2[20:8]/2^13 ) /
- * ((2^ctrl0[7:5]) * Table(ctrl0[26:24]))
+static unsigned int nlm_xlp_get_core_frequency(int node, int core)
+{
+	unsigned int pll_divf, pll_divr, dfs_div, ext_div;
+	unsigned int rstval, dfsval, denom;
+	uint64_t num, sysbase;
+
+	sysbase = nlm_get_node(node)->sysbase;
+	rstval = nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG);
+	dfsval = nlm_read_sys_reg(sysbase, SYS_CORE_DFS_DIV_VALUE);
+	pll_divf = ((rstval >> 10) & 0x7f) + 1;
+	pll_divr = ((rstval >> 8)  & 0x3) + 1;
+	ext_div  = ((rstval >> 30) & 0x3) + 1;
+	dfs_div  = ((dfsval >> (core * 4)) & 0xf) + 1;
+
+	num = 800000000ULL * pll_divf;
+	denom = 3 * pll_divr * ext_div * dfs_div;
+	do_div(num, denom);
+
+	return (unsigned int)num;
+}
+
+unsigned int nlm_get_core_frequency(int node, int core)
+{
+	if (cpu_is_xlpii())
+		return nlm_xlp2_get_core_frequency(node, core);
+	else
+		return nlm_xlp_get_core_frequency(node, core);
+}
+
+/*
+ * Calculate PIC frequency from PLL registers.
+ * freq_out = (ref_freq/2 * (6 + ctrl2[7:0]) + ctrl2[20:8]/2^13) /
+ * 		((2^ctrl0[7:5]) * Table(ctrl0[26:24]))
  */
-static unsigned int nlm_2xx_get_pic_frequency(int node)
+static unsigned int nlm_xlp2_get_pic_frequency(int node)
 {
-	u32 ctrl_val0, ctrl_val2, vco_post_div, pll_post_div;
+	u32 ctrl_val0, ctrl_val2, vco_post_div, pll_post_div, cpu_xlp9xx;
 	u32 mdiv, fdiv, pll_out_freq_den, reg_select, ref_div, pic_div;
-	u64 ref_clk, sysbase, pll_out_freq_num, ref_clk_select;
+	u64 sysbase, pll_out_freq_num, ref_clk_select, clockbase, ref_clk;
 
 	sysbase = nlm_get_node(node)->sysbase;
+	clockbase = nlm_get_clock_regbase(node);
+	cpu_xlp9xx = cpu_is_xlp9xx();
 
 	/* Find ref_clk_base */
-	ref_clk_select =
-		(nlm_read_sys_reg(sysbase, SYS_POWER_ON_RESET_CFG) >> 18) & 0x3;
+	if (cpu_xlp9xx)
+		ref_clk_select = (nlm_read_sys_reg(sysbase,
+				SYS_9XX_POWER_ON_RESET_CFG) >> 18) & 0x3;
+	else
+		ref_clk_select = (nlm_read_sys_reg(sysbase,
+					SYS_POWER_ON_RESET_CFG) >> 18) & 0x3;
 	switch (ref_clk_select) {
 	case 0:
 		ref_clk = 200000000ULL;
@@ -239,30 +323,70 @@ static unsigned int nlm_2xx_get_pic_frequency(int node)
 	}
 
 	/* Find the clock source PLL device for PIC */
-	reg_select = (nlm_read_sys_reg(sysbase, SYS_CLK_DEV_SEL) >> 22) & 0x3;
-	switch (reg_select) {
-	case 0:
-		ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0);
-		ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2);
-		break;
-	case 1:
-		ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(0));
-		ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(0));
-		break;
-	case 2:
-		ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(1));
-		ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(1));
-		break;
-	case 3:
-		ctrl_val0 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL0_DEVX(2));
-		ctrl_val2 = nlm_read_sys_reg(sysbase, SYS_PLL_CTRL2_DEVX(2));
-		break;
+	if (cpu_xlp9xx) {
+		reg_select = nlm_read_sys_reg(clockbase,
+				SYS_9XX_CLK_DEV_SEL) & 0x3;
+		switch (reg_select) {
+		case 0:
+			ctrl_val0 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_PLL_CTRL0);
+			ctrl_val2 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_PLL_CTRL2);
+			break;
+		case 1:
+			ctrl_val0 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_PLL_CTRL0_DEVX(0));
+			ctrl_val2 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_PLL_CTRL2_DEVX(0));
+			break;
+		case 2:
+			ctrl_val0 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_PLL_CTRL0_DEVX(1));
+			ctrl_val2 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_PLL_CTRL2_DEVX(1));
+			break;
+		case 3:
+			ctrl_val0 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_PLL_CTRL0_DEVX(2));
+			ctrl_val2 = nlm_read_sys_reg(clockbase,
+					SYS_9XX_PLL_CTRL2_DEVX(2));
+			break;
+		}
+	} else {
+		reg_select = (nlm_read_sys_reg(sysbase,
+					SYS_CLK_DEV_SEL) >> 22) & 0x3;
+		switch (reg_select) {
+		case 0:
+			ctrl_val0 = nlm_read_sys_reg(sysbase,
+					SYS_PLL_CTRL0);
+			ctrl_val2 = nlm_read_sys_reg(sysbase,
+					SYS_PLL_CTRL2);
+			break;
+		case 1:
+			ctrl_val0 = nlm_read_sys_reg(sysbase,
+					SYS_PLL_CTRL0_DEVX(0));
+			ctrl_val2 = nlm_read_sys_reg(sysbase,
+					SYS_PLL_CTRL2_DEVX(0));
+			break;
+		case 2:
+			ctrl_val0 = nlm_read_sys_reg(sysbase,
+					SYS_PLL_CTRL0_DEVX(1));
+			ctrl_val2 = nlm_read_sys_reg(sysbase,
+					SYS_PLL_CTRL2_DEVX(1));
+			break;
+		case 3:
+			ctrl_val0 = nlm_read_sys_reg(sysbase,
+					SYS_PLL_CTRL0_DEVX(2));
+			ctrl_val2 = nlm_read_sys_reg(sysbase,
+					SYS_PLL_CTRL2_DEVX(2));
+			break;
+		}
 	}
 
 	vco_post_div = (ctrl_val0 >> 5) & 0x7;
 	pll_post_div = (ctrl_val0 >> 24) & 0x7;
 	mdiv = ctrl_val2 & 0xff;
-	fdiv = (ctrl_val2 >> 8) & 0xfff;
+	fdiv = (ctrl_val2 >> 8) & 0x1fff;
 
 	/* Find PLL post divider value */
 	switch (pll_post_div) {
@@ -292,7 +416,12 @@ static unsigned int nlm_2xx_get_pic_frequency(int node)
 		do_div(pll_out_freq_num, pll_out_freq_den);
 
 	/* PIC post divider, which happens after PLL */
-	pic_div = (nlm_read_sys_reg(sysbase, SYS_CLK_DEV_DIV) >> 22) & 0x3;
+	if (cpu_xlp9xx)
+		pic_div = nlm_read_sys_reg(clockbase,
+				SYS_9XX_CLK_DEV_DIV) & 0x3;
+	else
+		pic_div = (nlm_read_sys_reg(sysbase,
+					SYS_CLK_DEV_DIV) >> 22) & 0x3;
 	do_div(pll_out_freq_num, 1 << pic_div);
 
 	return pll_out_freq_num;
@@ -300,12 +429,8 @@ static unsigned int nlm_2xx_get_pic_frequency(int node)
 
 unsigned int nlm_get_pic_frequency(int node)
 {
-	/* TODO Has to calculate freq as like 2xx */
-	if (cpu_is_xlp9xx())
-		return 250000000;
-
 	if (cpu_is_xlpii())
-		return nlm_2xx_get_pic_frequency(node);
+		return nlm_xlp2_get_pic_frequency(node);
 	else
 		return 133333333;
 }
diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c
index 8c60a2dd9ef..4fdd9fd29d1 100644
--- a/arch/mips/netlogic/xlp/setup.c
+++ b/arch/mips/netlogic/xlp/setup.c
@@ -121,8 +121,9 @@ void __init plat_mem_setup(void)
 
 const char *get_system_type(void)
 {
-	switch (read_c0_prid() & 0xff00) {
+	switch (read_c0_prid() & PRID_IMP_MASK) {
 	case PRID_IMP_NETLOGIC_XLP9XX:
+	case PRID_IMP_NETLOGIC_XLP5XX:
 	case PRID_IMP_NETLOGIC_XLP2XX:
 		return "Broadcom XLPII Series";
 	default:
diff --git a/arch/mips/netlogic/xlp/wakeup.c b/arch/mips/netlogic/xlp/wakeup.c
index 9a92617a2af..e5f44d2605a 100644
--- a/arch/mips/netlogic/xlp/wakeup.c
+++ b/arch/mips/netlogic/xlp/wakeup.c
@@ -135,11 +135,19 @@ static void xlp_enable_secondary_cores(const cpumask_t *wakeup_mask)
 		if (cpu_is_xlp9xx()) {
 			fusebase = nlm_get_fuse_regbase(n);
 			fusemask = nlm_read_reg(fusebase, FUSE_9XX_DEVCFG6);
-			mask = 0xfffff;
+			switch (read_c0_prid() & PRID_IMP_MASK) {
+			case PRID_IMP_NETLOGIC_XLP5XX:
+				mask = 0xff;
+				break;
+			case PRID_IMP_NETLOGIC_XLP9XX:
+			default:
+				mask = 0xfffff;
+				break;
+			}
 		} else {
 			fusemask = nlm_read_sys_reg(nodep->sysbase,
 						SYS_EFUSE_DEVICE_CFG_STATUS0);
-			switch (read_c0_prid() & 0xff00) {
+			switch (read_c0_prid() & PRID_IMP_MASK) {
 			case PRID_IMP_NETLOGIC_XLP3XX:
 				mask = 0xf;
 				break;
@@ -159,10 +167,6 @@ static void xlp_enable_secondary_cores(const cpumask_t *wakeup_mask)
 		 */
 		syscoremask = (1 << hweight32(~fusemask & mask)) - 1;
 
-		/* The boot cpu */
-		if (n == 0)
-			nodep->coremask = 1;
-
 		pr_info("Node %d - SYS/FUSE coremask %x\n", n, syscoremask);
 		for (core = 0; core < nlm_cores_per_node(); core++) {
 			/* we will be on node 0 core 0 */
diff --git a/arch/mips/paravirt/Kconfig b/arch/mips/paravirt/Kconfig
new file mode 100644
index 00000000000..ecae5861b60
--- /dev/null
+++ b/arch/mips/paravirt/Kconfig
@@ -0,0 +1,6 @@
+if MIPS_PARAVIRT
+
+config MIPS_PCI_VIRTIO
+	def_bool y
+
+endif #  MIPS_PARAVIRT
diff --git a/arch/mips/paravirt/Makefile b/arch/mips/paravirt/Makefile
new file mode 100644
index 00000000000..5023af733a3
--- /dev/null
+++ b/arch/mips/paravirt/Makefile
@@ -0,0 +1,14 @@
+#
+# Makefile for MIPS para-virtualized specific kernel interface routines
+# under Linux.
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 2013 Cavium, Inc.
+#
+
+obj-y := setup.o serial.o paravirt-irq.o
+
+obj-$(CONFIG_SMP)		+= paravirt-smp.o
diff --git a/arch/mips/paravirt/Platform b/arch/mips/paravirt/Platform
new file mode 100644
index 00000000000..7e76ef25ea1
--- /dev/null
+++ b/arch/mips/paravirt/Platform
@@ -0,0 +1,8 @@
+#
+# Generic para-virtualized guest.
+#
+platform-$(CONFIG_MIPS_PARAVIRT)	+= paravirt/
+cflags-$(CONFIG_MIPS_PARAVIRT)		+=				\
+		-I$(srctree)/arch/mips/include/asm/mach-paravirt
+
+load-$(CONFIG_MIPS_PARAVIRT)	= 0xffffffff80010000
diff --git a/arch/mips/paravirt/paravirt-irq.c b/arch/mips/paravirt/paravirt-irq.c
new file mode 100644
index 00000000000..8987b06c9de
--- /dev/null
+++ b/arch/mips/paravirt/paravirt-irq.c
@@ -0,0 +1,368 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 Cavium, Inc.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/cpumask.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+
+#include <asm/io.h>
+
+#define MBOX_BITS_PER_CPU 2
+
+static int cpunum_for_cpu(int cpu)
+{
+#ifdef CONFIG_SMP
+	return cpu_logical_map(cpu);
+#else
+	return get_ebase_cpunum();
+#endif
+}
+
+struct core_chip_data {
+	struct mutex core_irq_mutex;
+	bool current_en;
+	bool desired_en;
+	u8 bit;
+};
+
+static struct core_chip_data irq_core_chip_data[8];
+
+static void irq_core_ack(struct irq_data *data)
+{
+	struct core_chip_data *cd = irq_data_get_irq_chip_data(data);
+	unsigned int bit = cd->bit;
+
+	/*
+	 * We don't need to disable IRQs to make these atomic since
+	 * they are already disabled earlier in the low level
+	 * interrupt code.
+	 */
+	clear_c0_status(0x100 << bit);
+	/* The two user interrupts must be cleared manually. */
+	if (bit < 2)
+		clear_c0_cause(0x100 << bit);
+}
+
+static void irq_core_eoi(struct irq_data *data)
+{
+	struct core_chip_data *cd = irq_data_get_irq_chip_data(data);
+
+	/*
+	 * We don't need to disable IRQs to make these atomic since
+	 * they are already disabled earlier in the low level
+	 * interrupt code.
+	 */
+	set_c0_status(0x100 << cd->bit);
+}
+
+static void irq_core_set_enable_local(void *arg)
+{
+	struct irq_data *data = arg;
+	struct core_chip_data *cd = irq_data_get_irq_chip_data(data);
+	unsigned int mask = 0x100 << cd->bit;
+
+	/*
+	 * Interrupts are already disabled, so these are atomic.
+	 */
+	if (cd->desired_en)
+		set_c0_status(mask);
+	else
+		clear_c0_status(mask);
+
+}
+
+static void irq_core_disable(struct irq_data *data)
+{
+	struct core_chip_data *cd = irq_data_get_irq_chip_data(data);
+	cd->desired_en = false;
+}
+
+static void irq_core_enable(struct irq_data *data)
+{
+	struct core_chip_data *cd = irq_data_get_irq_chip_data(data);
+	cd->desired_en = true;
+}
+
+static void irq_core_bus_lock(struct irq_data *data)
+{
+	struct core_chip_data *cd = irq_data_get_irq_chip_data(data);
+
+	mutex_lock(&cd->core_irq_mutex);
+}
+
+static void irq_core_bus_sync_unlock(struct irq_data *data)
+{
+	struct core_chip_data *cd = irq_data_get_irq_chip_data(data);
+
+	if (cd->desired_en != cd->current_en) {
+		on_each_cpu(irq_core_set_enable_local, data, 1);
+		cd->current_en = cd->desired_en;
+	}
+
+	mutex_unlock(&cd->core_irq_mutex);
+}
+
+static struct irq_chip irq_chip_core = {
+	.name = "Core",
+	.irq_enable = irq_core_enable,
+	.irq_disable = irq_core_disable,
+	.irq_ack = irq_core_ack,
+	.irq_eoi = irq_core_eoi,
+	.irq_bus_lock = irq_core_bus_lock,
+	.irq_bus_sync_unlock = irq_core_bus_sync_unlock,
+
+	.irq_cpu_online = irq_core_eoi,
+	.irq_cpu_offline = irq_core_ack,
+	.flags = IRQCHIP_ONOFFLINE_ENABLED,
+};
+
+static void __init irq_init_core(void)
+{
+	int i;
+	int irq;
+	struct core_chip_data *cd;
+
+	/* Start with a clean slate */
+	clear_c0_status(ST0_IM);
+	clear_c0_cause(CAUSEF_IP0 | CAUSEF_IP1);
+
+	for (i = 0; i < ARRAY_SIZE(irq_core_chip_data); i++) {
+		cd = irq_core_chip_data + i;
+		cd->current_en = false;
+		cd->desired_en = false;
+		cd->bit = i;
+		mutex_init(&cd->core_irq_mutex);
+
+		irq = MIPS_CPU_IRQ_BASE + i;
+
+		switch (i) {
+		case 0: /* SW0 */
+		case 1: /* SW1 */
+		case 5: /* IP5 */
+		case 6: /* IP6 */
+		case 7: /* IP7 */
+			irq_set_chip_data(irq, cd);
+			irq_set_chip_and_handler(irq, &irq_chip_core,
+						 handle_percpu_irq);
+			break;
+		default:
+			break;
+		}
+	}
+}
+
+static void __iomem *mips_irq_chip;
+#define MIPS_IRQ_CHIP_NUM_BITS 0
+#define MIPS_IRQ_CHIP_REGS 8
+
+static int mips_irq_cpu_stride;
+static int mips_irq_chip_reg_raw;
+static int mips_irq_chip_reg_src;
+static int mips_irq_chip_reg_en;
+static int mips_irq_chip_reg_raw_w1s;
+static int mips_irq_chip_reg_raw_w1c;
+static int mips_irq_chip_reg_en_w1s;
+static int mips_irq_chip_reg_en_w1c;
+
+static void irq_pci_enable(struct irq_data *data)
+{
+	u32 mask = 1u << data->irq;
+
+	__raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_en_w1s);
+}
+
+static void irq_pci_disable(struct irq_data *data)
+{
+	u32 mask = 1u << data->irq;
+
+	__raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_en_w1c);
+}
+
+static void irq_pci_ack(struct irq_data *data)
+{
+}
+
+static void irq_pci_mask(struct irq_data *data)
+{
+	u32 mask = 1u << data->irq;
+
+	__raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_en_w1c);
+}
+
+static void irq_pci_unmask(struct irq_data *data)
+{
+	u32 mask = 1u << data->irq;
+
+	__raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_en_w1s);
+}
+
+static struct irq_chip irq_chip_pci = {
+	.name = "PCI",
+	.irq_enable = irq_pci_enable,
+	.irq_disable = irq_pci_disable,
+	.irq_ack = irq_pci_ack,
+	.irq_mask = irq_pci_mask,
+	.irq_unmask = irq_pci_unmask,
+};
+
+static void irq_mbox_all(struct irq_data *data,  void __iomem *base)
+{
+	int cpu;
+	unsigned int mbox = data->irq - MIPS_IRQ_MBOX0;
+	u32 mask;
+
+	WARN_ON(mbox >= MBOX_BITS_PER_CPU);
+
+	for_each_online_cpu(cpu) {
+		unsigned int cpuid = cpunum_for_cpu(cpu);
+		mask = 1 << (cpuid * MBOX_BITS_PER_CPU + mbox);
+		__raw_writel(mask, base + (cpuid * mips_irq_cpu_stride));
+	}
+}
+
+static void irq_mbox_enable(struct irq_data *data)
+{
+	irq_mbox_all(data, mips_irq_chip + mips_irq_chip_reg_en_w1s + sizeof(u32));
+}
+
+static void irq_mbox_disable(struct irq_data *data)
+{
+	irq_mbox_all(data, mips_irq_chip + mips_irq_chip_reg_en_w1c + sizeof(u32));
+}
+
+static void irq_mbox_ack(struct irq_data *data)
+{
+	u32 mask;
+	unsigned int mbox = data->irq - MIPS_IRQ_MBOX0;
+
+	WARN_ON(mbox >= MBOX_BITS_PER_CPU);
+
+	mask = 1 << (get_ebase_cpunum() * MBOX_BITS_PER_CPU + mbox);
+	__raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_raw_w1c + sizeof(u32));
+}
+
+void irq_mbox_ipi(int cpu, unsigned int actions)
+{
+	unsigned int cpuid = cpunum_for_cpu(cpu);
+	u32 mask;
+
+	WARN_ON(actions >= (1 << MBOX_BITS_PER_CPU));
+
+	mask = actions << (cpuid * MBOX_BITS_PER_CPU);
+	__raw_writel(mask, mips_irq_chip + mips_irq_chip_reg_raw_w1s + sizeof(u32));
+}
+
+static void irq_mbox_cpu_onoffline(struct irq_data *data,  void __iomem *base)
+{
+	unsigned int mbox = data->irq - MIPS_IRQ_MBOX0;
+	unsigned int cpuid = get_ebase_cpunum();
+	u32 mask;
+
+	WARN_ON(mbox >= MBOX_BITS_PER_CPU);
+
+	mask = 1 << (cpuid * MBOX_BITS_PER_CPU + mbox);
+	__raw_writel(mask, base + (cpuid * mips_irq_cpu_stride));
+
+}
+
+static void irq_mbox_cpu_online(struct irq_data *data)
+{
+	irq_mbox_cpu_onoffline(data, mips_irq_chip + mips_irq_chip_reg_en_w1s + sizeof(u32));
+}
+
+static void irq_mbox_cpu_offline(struct irq_data *data)
+{
+	irq_mbox_cpu_onoffline(data, mips_irq_chip + mips_irq_chip_reg_en_w1c + sizeof(u32));
+}
+
+static struct irq_chip irq_chip_mbox = {
+	.name = "MBOX",
+	.irq_enable = irq_mbox_enable,
+	.irq_disable = irq_mbox_disable,
+	.irq_ack = irq_mbox_ack,
+	.irq_cpu_online = irq_mbox_cpu_online,
+	.irq_cpu_offline = irq_mbox_cpu_offline,
+	.flags = IRQCHIP_ONOFFLINE_ENABLED,
+};
+
+static void __init irq_pci_init(void)
+{
+	int i, stride;
+	u32 num_bits;
+
+	mips_irq_chip = ioremap(0x1e010000, 4096);
+
+	num_bits = __raw_readl(mips_irq_chip + MIPS_IRQ_CHIP_NUM_BITS);
+	stride = 8 * (1 + ((num_bits - 1) / 64));
+
+
+	pr_notice("mips_irq_chip: %u bits, reg stride: %d\n", num_bits, stride);
+	mips_irq_chip_reg_raw		= MIPS_IRQ_CHIP_REGS + 0 * stride;
+	mips_irq_chip_reg_raw_w1s	= MIPS_IRQ_CHIP_REGS + 1 * stride;
+	mips_irq_chip_reg_raw_w1c	= MIPS_IRQ_CHIP_REGS + 2 * stride;
+	mips_irq_chip_reg_src		= MIPS_IRQ_CHIP_REGS + 3 * stride;
+	mips_irq_chip_reg_en		= MIPS_IRQ_CHIP_REGS + 4 * stride;
+	mips_irq_chip_reg_en_w1s	= MIPS_IRQ_CHIP_REGS + 5 * stride;
+	mips_irq_chip_reg_en_w1c	= MIPS_IRQ_CHIP_REGS + 6 * stride;
+	mips_irq_cpu_stride		= stride * 4;
+
+	for (i = 0; i < 4; i++)
+		irq_set_chip_and_handler(i + MIPS_IRQ_PCIA, &irq_chip_pci, handle_level_irq);
+
+	for (i = 0; i < 2; i++)
+		irq_set_chip_and_handler(i + MIPS_IRQ_MBOX0, &irq_chip_mbox, handle_percpu_irq);
+
+
+	set_c0_status(STATUSF_IP2);
+}
+
+static void irq_pci_dispatch(void)
+{
+	unsigned int cpuid = get_ebase_cpunum();
+	u32 en;
+
+	en = __raw_readl(mips_irq_chip + mips_irq_chip_reg_src +
+			(cpuid * mips_irq_cpu_stride));
+
+	if (!en) {
+		en = __raw_readl(mips_irq_chip + mips_irq_chip_reg_src + (cpuid * mips_irq_cpu_stride) + sizeof(u32));
+		en = (en >> (2 * cpuid)) & 3;
+
+		if (!en)
+			spurious_interrupt();
+		else
+			do_IRQ(__ffs(en) + MIPS_IRQ_MBOX0);	/* MBOX type */
+	} else {
+		do_IRQ(__ffs(en));
+	}
+}
+
+
+void __init arch_init_irq(void)
+{
+	irq_init_core();
+	irq_pci_init();
+}
+
+asmlinkage void plat_irq_dispatch(void)
+{
+	unsigned int pending = read_c0_cause() & read_c0_status() & ST0_IM;
+	int ip;
+
+	if (unlikely(!pending)) {
+		spurious_interrupt();
+		return;
+	}
+
+	ip = ffs(pending) - 1 - STATUSB_IP0;
+	if (ip == 2)
+		irq_pci_dispatch();
+	else
+		do_IRQ(MIPS_CPU_IRQ_BASE + ip);
+}
diff --git a/arch/mips/paravirt/paravirt-smp.c b/arch/mips/paravirt/paravirt-smp.c
new file mode 100644
index 00000000000..0164b0c4835
--- /dev/null
+++ b/arch/mips/paravirt/paravirt-smp.c
@@ -0,0 +1,143 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 Cavium, Inc.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/cpumask.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+
+#include <asm/mipsregs.h>
+#include <asm/setup.h>
+#include <asm/time.h>
+#include <asm/smp.h>
+
+/*
+ * Writing the sp releases the CPU, so writes must be ordered, gp
+ * first, then sp.
+ */
+unsigned long paravirt_smp_sp[NR_CPUS];
+unsigned long paravirt_smp_gp[NR_CPUS];
+
+static int numcpus = 1;
+
+static int __init set_numcpus(char *str)
+{
+	int newval;
+
+	if (get_option(&str, &newval)) {
+		if (newval < 1 || newval >= NR_CPUS)
+			goto bad;
+		numcpus = newval;
+		return 0;
+	}
+bad:
+	return -EINVAL;
+}
+early_param("numcpus", set_numcpus);
+
+
+static void paravirt_smp_setup(void)
+{
+	int id;
+	unsigned int cpunum = get_ebase_cpunum();
+
+	if (WARN_ON(cpunum >= NR_CPUS))
+		return;
+
+	/* The present CPUs are initially just the boot cpu (CPU 0). */
+	for (id = 0; id < NR_CPUS; id++) {
+		set_cpu_possible(id, id == 0);
+		set_cpu_present(id, id == 0);
+	}
+	__cpu_number_map[cpunum] = 0;
+	__cpu_logical_map[0] = cpunum;
+
+	for (id = 0; id < numcpus; id++) {
+		set_cpu_possible(id, true);
+		set_cpu_present(id, true);
+		__cpu_number_map[id] = id;
+		__cpu_logical_map[id] = id;
+	}
+}
+
+void irq_mbox_ipi(int cpu, unsigned int actions);
+static void paravirt_send_ipi_single(int cpu, unsigned int action)
+{
+	irq_mbox_ipi(cpu, action);
+}
+
+static void paravirt_send_ipi_mask(const struct cpumask *mask, unsigned int action)
+{
+	unsigned int cpu;
+
+	for_each_cpu_mask(cpu, *mask)
+		paravirt_send_ipi_single(cpu, action);
+}
+
+static void paravirt_init_secondary(void)
+{
+	unsigned int sr;
+
+	sr = set_c0_status(ST0_BEV);
+	write_c0_ebase((u32)ebase);
+
+	sr |= STATUSF_IP2; /* Interrupt controller on IP2 */
+	write_c0_status(sr);
+
+	irq_cpu_online();
+}
+
+static void paravirt_smp_finish(void)
+{
+	/* to generate the first CPU timer interrupt */
+	write_c0_compare(read_c0_count() + mips_hpt_frequency / HZ);
+	local_irq_enable();
+}
+
+static void paravirt_boot_secondary(int cpu, struct task_struct *idle)
+{
+	paravirt_smp_gp[cpu] = (unsigned long)task_thread_info(idle);
+	smp_wmb();
+	paravirt_smp_sp[cpu] = __KSTK_TOS(idle);
+}
+
+static irqreturn_t paravirt_reched_interrupt(int irq, void *dev_id)
+{
+	scheduler_ipi();
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t paravirt_function_interrupt(int irq, void *dev_id)
+{
+	smp_call_function_interrupt();
+	return IRQ_HANDLED;
+}
+
+static void paravirt_prepare_cpus(unsigned int max_cpus)
+{
+	if (request_irq(MIPS_IRQ_MBOX0, paravirt_reched_interrupt,
+			IRQF_PERCPU | IRQF_NO_THREAD, "Scheduler",
+			paravirt_reched_interrupt)) {
+		panic("Cannot request_irq for SchedulerIPI");
+	}
+	if (request_irq(MIPS_IRQ_MBOX1, paravirt_function_interrupt,
+			IRQF_PERCPU | IRQF_NO_THREAD, "SMP-Call",
+			paravirt_function_interrupt)) {
+		panic("Cannot request_irq for SMP-Call");
+	}
+}
+
+struct plat_smp_ops paravirt_smp_ops = {
+	.send_ipi_single	= paravirt_send_ipi_single,
+	.send_ipi_mask		= paravirt_send_ipi_mask,
+	.init_secondary		= paravirt_init_secondary,
+	.smp_finish		= paravirt_smp_finish,
+	.boot_secondary		= paravirt_boot_secondary,
+	.smp_setup		= paravirt_smp_setup,
+	.prepare_cpus		= paravirt_prepare_cpus,
+};
diff --git a/arch/mips/paravirt/serial.c b/arch/mips/paravirt/serial.c
new file mode 100644
index 00000000000..02b665c0227
--- /dev/null
+++ b/arch/mips/paravirt/serial.c
@@ -0,0 +1,40 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 Cavium, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/virtio_console.h>
+#include <linux/kvm_para.h>
+
+/*
+ * Emit one character to the boot console.
+ */
+int prom_putchar(char c)
+{
+	kvm_hypercall3(KVM_HC_MIPS_CONSOLE_OUTPUT, 0 /*  port 0 */,
+		(unsigned long)&c, 1 /* len == 1 */);
+
+	return 1;
+}
+
+#ifdef CONFIG_VIRTIO_CONSOLE
+static int paravirt_put_chars(u32 vtermno, const char *buf, int count)
+{
+	kvm_hypercall3(KVM_HC_MIPS_CONSOLE_OUTPUT, vtermno,
+		(unsigned long)buf, count);
+
+	return count;
+}
+
+static int __init paravirt_cons_init(void)
+{
+	virtio_cons_early_init(paravirt_put_chars);
+	return 0;
+}
+core_initcall(paravirt_cons_init);
+
+#endif
diff --git a/arch/mips/paravirt/setup.c b/arch/mips/paravirt/setup.c
new file mode 100644
index 00000000000..cb8448b373a
--- /dev/null
+++ b/arch/mips/paravirt/setup.c
@@ -0,0 +1,67 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 Cavium, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kvm_para.h>
+
+#include <asm/reboot.h>
+#include <asm/bootinfo.h>
+#include <asm/smp-ops.h>
+#include <asm/time.h>
+
+extern struct plat_smp_ops paravirt_smp_ops;
+
+const char *get_system_type(void)
+{
+	return "MIPS Para-Virtualized Guest";
+}
+
+void __init plat_time_init(void)
+{
+	mips_hpt_frequency = kvm_hypercall0(KVM_HC_MIPS_GET_CLOCK_FREQ);
+
+	preset_lpj = mips_hpt_frequency / (2 * HZ);
+}
+
+static void pv_machine_halt(void)
+{
+	kvm_hypercall0(KVM_HC_MIPS_EXIT_VM);
+}
+
+/*
+ * Early entry point for arch setup
+ */
+void __init prom_init(void)
+{
+	int i;
+	int argc = fw_arg0;
+	char **argv = (char **)fw_arg1;
+
+#ifdef CONFIG_32BIT
+	set_io_port_base(KSEG1ADDR(0x1e000000));
+#else /* CONFIG_64BIT */
+	set_io_port_base(PHYS_TO_XKSEG_UNCACHED(0x1e000000));
+#endif
+
+	for (i = 0; i < argc; i++) {
+		strlcat(arcs_cmdline, argv[i], COMMAND_LINE_SIZE);
+		if (i < argc - 1)
+			strlcat(arcs_cmdline, " ", COMMAND_LINE_SIZE);
+	}
+	_machine_halt = pv_machine_halt;
+	register_smp_ops(&paravirt_smp_ops);
+}
+
+void __init plat_mem_setup(void)
+{
+	/* Do nothing, the "mem=???" parser handles our memory. */
+}
+
+void __init prom_free_prom_memory(void)
+{
+}
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index d61138a177c..ff8a5539b36 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -21,7 +21,7 @@ obj-$(CONFIG_BCM63XX)		+= pci-bcm63xx.o fixup-bcm63xx.o \
 obj-$(CONFIG_MIPS_ALCHEMY)	+= pci-alchemy.o
 obj-$(CONFIG_SOC_AR71XX)	+= pci-ar71xx.o
 obj-$(CONFIG_PCI_AR724X)	+= pci-ar724x.o
-
+obj-$(CONFIG_MIPS_PCI_VIRTIO)	+= pci-virtio-guest.o
 #
 # These are still pretty much in the old state, watch, go blind.
 #
diff --git a/arch/mips/pci/fixup-malta.c b/arch/mips/pci/fixup-malta.c
index 2f9e52a1a75..40e920c653c 100644
--- a/arch/mips/pci/fixup-malta.c
+++ b/arch/mips/pci/fixup-malta.c
@@ -68,6 +68,7 @@ static void malta_piix_func0_fixup(struct pci_dev *pdev)
 {
 	unsigned char reg_val;
 	u32 reg_val32;
+	u16 reg_val16;
 	/* PIIX PIRQC[A:D] irq mappings */
 	static int piixirqmap[PIIX4_FUNC0_PIRQRC_IRQ_ROUTING_MAX] = {
 		0,  0,	0,  3,
@@ -107,6 +108,11 @@ static void malta_piix_func0_fixup(struct pci_dev *pdev)
 	pci_read_config_byte(pdev, PIIX4_FUNC0_SERIRQC, &reg_val);
 	reg_val |= PIIX4_FUNC0_SERIRQC_EN | PIIX4_FUNC0_SERIRQC_CONT;
 	pci_write_config_byte(pdev, PIIX4_FUNC0_SERIRQC, reg_val);
+
+	/* Enable response to special cycles */
+	pci_read_config_word(pdev, PCI_COMMAND, &reg_val16);
+	pci_write_config_word(pdev, PCI_COMMAND,
+			      reg_val16 | PCI_COMMAND_SPECIAL);
 }
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_0,
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index 2b91b0e6156..ab0c5d14c6f 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -15,6 +15,7 @@
 #include <asm/octeon/cvmx-npi-defs.h>
 #include <asm/octeon/cvmx-pci-defs.h>
 #include <asm/octeon/cvmx-npei-defs.h>
+#include <asm/octeon/cvmx-sli-defs.h>
 #include <asm/octeon/cvmx-pexp-defs.h>
 #include <asm/octeon/pci-octeon.h>
 
@@ -162,6 +163,11 @@ msi_irq_allocated:
 		msg.address_lo = (0 + CVMX_NPEI_PCIE_MSI_RCV) & 0xffffffff;
 		msg.address_hi = (0 + CVMX_NPEI_PCIE_MSI_RCV) >> 32;
 		break;
+	case OCTEON_DMA_BAR_TYPE_PCIE2:
+		/* When using PCIe2, Bar 0 is based at 0 */
+		msg.address_lo = (0 + CVMX_SLI_PCIE_MSI_RCV) & 0xffffffff;
+		msg.address_hi = (0 + CVMX_SLI_PCIE_MSI_RCV) >> 32;
+		break;
 	default:
 		panic("arch_setup_msi_irq: Invalid octeon_dma_bar_type");
 	}
diff --git a/arch/mips/pci/msi-xlp.c b/arch/mips/pci/msi-xlp.c
index 3249685e03a..fa374fe3746 100644
--- a/arch/mips/pci/msi-xlp.c
+++ b/arch/mips/pci/msi-xlp.c
@@ -56,8 +56,8 @@
 #include <asm/netlogic/xlp-hal/bridge.h>
 
 #define XLP_MSIVEC_PER_LINK	32
-#define XLP_MSIXVEC_TOTAL	32
-#define XLP_MSIXVEC_PER_LINK	8
+#define XLP_MSIXVEC_TOTAL	(cpu_is_xlp9xx() ? 128 : 32)
+#define XLP_MSIXVEC_PER_LINK	(cpu_is_xlp9xx() ? 32 : 8)
 
 /* 128 MSI irqs per node, mapped starting at NLM_MSI_VEC_BASE */
 static inline int nlm_link_msiirq(int link, int msivec)
@@ -65,35 +65,44 @@ static inline int nlm_link_msiirq(int link, int msivec)
 	return NLM_MSI_VEC_BASE + link * XLP_MSIVEC_PER_LINK + msivec;
 }
 
+/* get the link MSI vector from irq number */
 static inline int nlm_irq_msivec(int irq)
 {
-	return irq % XLP_MSIVEC_PER_LINK;
+	return (irq - NLM_MSI_VEC_BASE) % XLP_MSIVEC_PER_LINK;
 }
 
+/* get the link from the irq number */
 static inline int nlm_irq_msilink(int irq)
 {
-	return (irq % (XLP_MSIVEC_PER_LINK * PCIE_NLINKS)) /
-						XLP_MSIVEC_PER_LINK;
+	int total_msivec = XLP_MSIVEC_PER_LINK * PCIE_NLINKS;
+
+	return ((irq - NLM_MSI_VEC_BASE) % total_msivec) /
+		XLP_MSIVEC_PER_LINK;
 }
 
 /*
- * Only 32 MSI-X vectors are possible because there are only 32 PIC
- * interrupts for MSI. We split them statically and use 8 MSI-X vectors
- * per link - this keeps the allocation and lookup simple.
+ * For XLP 8xx/4xx/3xx/2xx, only 32 MSI-X vectors are possible because
+ * there are only 32 PIC interrupts for MSI. We split them statically
+ * and use 8 MSI-X vectors per link - this keeps the allocation and
+ * lookup simple.
+ * On XLP 9xx, there are 32 vectors per link, and the interrupts are
+ * not routed thru PIC, so we can use all 128 MSI-X vectors.
  */
 static inline int nlm_link_msixirq(int link, int bit)
 {
 	return NLM_MSIX_VEC_BASE + link * XLP_MSIXVEC_PER_LINK + bit;
 }
 
+/* get the link MSI vector from irq number */
 static inline int nlm_irq_msixvec(int irq)
 {
-	return irq % XLP_MSIXVEC_TOTAL;  /* works when given xirq */
+	return (irq - NLM_MSIX_VEC_BASE) % XLP_MSIXVEC_TOTAL;
 }
 
-static inline int nlm_irq_msixlink(int irq)
+/* get the link from MSIX vec */
+static inline int nlm_irq_msixlink(int msixvec)
 {
-	return nlm_irq_msixvec(irq) / XLP_MSIXVEC_PER_LINK;
+	return msixvec / XLP_MSIXVEC_PER_LINK;
 }
 
 /*
@@ -129,7 +138,11 @@ static void xlp_msi_enable(struct irq_data *d)
 	vec = nlm_irq_msivec(d->irq);
 	spin_lock_irqsave(&md->msi_lock, flags);
 	md->msi_enabled_mask |= 1u << vec;
-	nlm_write_reg(md->lnkbase, PCIE_MSI_EN, md->msi_enabled_mask);
+	if (cpu_is_xlp9xx())
+		nlm_write_reg(md->lnkbase, PCIE_9XX_MSI_EN,
+				md->msi_enabled_mask);
+	else
+		nlm_write_reg(md->lnkbase, PCIE_MSI_EN, md->msi_enabled_mask);
 	spin_unlock_irqrestore(&md->msi_lock, flags);
 }
 
@@ -142,7 +155,11 @@ static void xlp_msi_disable(struct irq_data *d)
 	vec = nlm_irq_msivec(d->irq);
 	spin_lock_irqsave(&md->msi_lock, flags);
 	md->msi_enabled_mask &= ~(1u << vec);
-	nlm_write_reg(md->lnkbase, PCIE_MSI_EN, md->msi_enabled_mask);
+	if (cpu_is_xlp9xx())
+		nlm_write_reg(md->lnkbase, PCIE_9XX_MSI_EN,
+				md->msi_enabled_mask);
+	else
+		nlm_write_reg(md->lnkbase, PCIE_MSI_EN, md->msi_enabled_mask);
 	spin_unlock_irqrestore(&md->msi_lock, flags);
 }
 
@@ -156,11 +173,18 @@ static void xlp_msi_mask_ack(struct irq_data *d)
 	xlp_msi_disable(d);
 
 	/* Ack MSI on bridge */
-	nlm_write_reg(md->lnkbase, PCIE_MSI_STATUS, 1u << vec);
+	if (cpu_is_xlp9xx())
+		nlm_write_reg(md->lnkbase, PCIE_9XX_MSI_STATUS, 1u << vec);
+	else
+		nlm_write_reg(md->lnkbase, PCIE_MSI_STATUS, 1u << vec);
 
 	/* Ack at eirr and PIC */
 	ack_c0_eirr(PIC_PCIE_LINK_MSI_IRQ(link));
-	nlm_pic_ack(md->node->picbase, PIC_IRT_PCIE_LINK_INDEX(link));
+	if (cpu_is_xlp9xx())
+		nlm_pic_ack(md->node->picbase,
+				PIC_9XX_IRT_PCIE_LINK_INDEX(link));
+	else
+		nlm_pic_ack(md->node->picbase, PIC_IRT_PCIE_LINK_INDEX(link));
 }
 
 static struct irq_chip xlp_msi_chip = {
@@ -172,30 +196,45 @@ static struct irq_chip xlp_msi_chip = {
 };
 
 /*
- * The MSI-X interrupt handling is different from MSI, there are 32
- * MSI-X interrupts generated by the PIC and each of these correspond
- * to a MSI-X vector (0-31) that can be assigned.
+ * XLP8XX/4XX/3XX/2XX:
+ * The MSI-X interrupt handling is different from MSI, there are 32 MSI-X
+ * interrupts generated by the PIC and each of these correspond to a MSI-X
+ * vector (0-31) that can be assigned.
  *
- * We divide the MSI-X vectors to 8 per link and do a per-link
- * allocation
+ * We divide the MSI-X vectors to 8 per link and do a per-link allocation
+ *
+ * XLP9XX:
+ * 32 MSI-X vectors are available per link, and the interrupts are not routed
+ * thru the PIC. PIC ack not needed.
  *
  * Enable and disable done using standard MSI functions.
  */
 static void xlp_msix_mask_ack(struct irq_data *d)
 {
-	struct xlp_msi_data *md = irq_data_get_irq_handler_data(d);
+	struct xlp_msi_data *md;
 	int link, msixvec;
+	uint32_t status_reg, bit;
 
 	msixvec = nlm_irq_msixvec(d->irq);
-	link = nlm_irq_msixlink(d->irq);
+	link = nlm_irq_msixlink(msixvec);
 	mask_msi_irq(d);
+	md = irq_data_get_irq_handler_data(d);
 
 	/* Ack MSI on bridge */
-	nlm_write_reg(md->lnkbase, PCIE_MSIX_STATUS, 1u << msixvec);
+	if (cpu_is_xlp9xx()) {
+		status_reg = PCIE_9XX_MSIX_STATUSX(link);
+		bit = msixvec % XLP_MSIXVEC_PER_LINK;
+	} else {
+		status_reg = PCIE_MSIX_STATUS;
+		bit = msixvec;
+	}
+	nlm_write_reg(md->lnkbase, status_reg, 1u << bit);
 
 	/* Ack at eirr and PIC */
 	ack_c0_eirr(PIC_PCIE_MSIX_IRQ(link));
-	nlm_pic_ack(md->node->picbase, PIC_IRT_PCIE_MSIX_INDEX(msixvec));
+	if (!cpu_is_xlp9xx())
+		nlm_pic_ack(md->node->picbase,
+				PIC_IRT_PCIE_MSIX_INDEX(msixvec));
 }
 
 static struct irq_chip xlp_msix_chip = {
@@ -219,10 +258,18 @@ static void xlp_config_link_msi(uint64_t lnkbase, int lirq, uint64_t msiaddr)
 {
 	u32 val;
 
-	val = nlm_read_reg(lnkbase, PCIE_INT_EN0);
-	if ((val & 0x200) == 0) {
-		val |= 0x200;		/* MSI Interrupt enable */
-		nlm_write_reg(lnkbase, PCIE_INT_EN0, val);
+	if (cpu_is_xlp9xx()) {
+		val = nlm_read_reg(lnkbase, PCIE_9XX_INT_EN0);
+		if ((val & 0x200) == 0) {
+			val |= 0x200;		/* MSI Interrupt enable */
+			nlm_write_reg(lnkbase, PCIE_9XX_INT_EN0, val);
+		}
+	} else {
+		val = nlm_read_reg(lnkbase, PCIE_INT_EN0);
+		if ((val & 0x200) == 0) {
+			val |= 0x200;
+			nlm_write_reg(lnkbase, PCIE_INT_EN0, val);
+		}
 	}
 
 	val = nlm_read_reg(lnkbase, 0x1);	/* CMD */
@@ -269,9 +316,12 @@ static int xlp_setup_msi(uint64_t lnkbase, int node, int link,
 
 	spin_lock_irqsave(&md->msi_lock, flags);
 	if (md->msi_alloc_mask == 0) {
-		/* switch the link IRQ to MSI range */
 		xlp_config_link_msi(lnkbase, lirq, msiaddr);
-		irt = PIC_IRT_PCIE_LINK_INDEX(link);
+		/* switch the link IRQ to MSI range */
+		if (cpu_is_xlp9xx())
+			irt = PIC_9XX_IRT_PCIE_LINK_INDEX(link);
+		else
+			irt = PIC_IRT_PCIE_LINK_INDEX(link);
 		nlm_setup_pic_irq(node, lirq, lirq, irt);
 		nlm_pic_init_irt(nlm_get_node(node)->picbase, irt, lirq,
 				 node * nlm_threads_per_node(), 1 /*en */);
@@ -311,10 +361,19 @@ static void xlp_config_link_msix(uint64_t lnkbase, int lirq, uint64_t msixaddr)
 		val |= 0x80000000U;
 		nlm_write_reg(lnkbase, 0x2C, val);
 	}
-	val = nlm_read_reg(lnkbase, PCIE_INT_EN0);
-	if ((val & 0x200) == 0) {
-		val |= 0x200;		/* MSI Interrupt enable */
-		nlm_write_reg(lnkbase, PCIE_INT_EN0, val);
+
+	if (cpu_is_xlp9xx()) {
+		val = nlm_read_reg(lnkbase, PCIE_9XX_INT_EN0);
+		if ((val & 0x200) == 0) {
+			val |= 0x200;		/* MSI Interrupt enable */
+			nlm_write_reg(lnkbase, PCIE_9XX_INT_EN0, val);
+		}
+	} else {
+		val = nlm_read_reg(lnkbase, PCIE_INT_EN0);
+		if ((val & 0x200) == 0) {
+			val |= 0x200;		/* MSI Interrupt enable */
+			nlm_write_reg(lnkbase, PCIE_INT_EN0, val);
+		}
 	}
 
 	val = nlm_read_reg(lnkbase, 0x1);	/* CMD */
@@ -329,10 +388,19 @@ static void xlp_config_link_msix(uint64_t lnkbase, int lirq, uint64_t msixaddr)
 	val |= (1 << 8) | lirq;
 	nlm_write_pci_reg(lnkbase, 0xf, val);
 
-	/* MSI-X addresses */
-	nlm_write_reg(lnkbase, PCIE_BRIDGE_MSIX_ADDR_BASE, msixaddr >> 8);
-	nlm_write_reg(lnkbase, PCIE_BRIDGE_MSIX_ADDR_LIMIT,
-					(msixaddr + MSI_ADDR_SZ) >> 8);
+	if (cpu_is_xlp9xx()) {
+		/* MSI-X addresses */
+		nlm_write_reg(lnkbase, PCIE_9XX_BRIDGE_MSIX_ADDR_BASE,
+				msixaddr >> 8);
+		nlm_write_reg(lnkbase, PCIE_9XX_BRIDGE_MSIX_ADDR_LIMIT,
+				(msixaddr + MSI_ADDR_SZ) >> 8);
+	} else {
+		/* MSI-X addresses */
+		nlm_write_reg(lnkbase, PCIE_BRIDGE_MSIX_ADDR_BASE,
+				msixaddr >> 8);
+		nlm_write_reg(lnkbase, PCIE_BRIDGE_MSIX_ADDR_LIMIT,
+				(msixaddr + MSI_ADDR_SZ) >> 8);
+	}
 }
 
 /*
@@ -369,6 +437,7 @@ static int xlp_setup_msix(uint64_t lnkbase, int node, int link,
 
 	xirq += t;
 	msixvec = nlm_irq_msixvec(xirq);
+
 	msg.address_hi = msixaddr >> 32;
 	msg.address_lo = msixaddr & 0xffffffff;
 	msg.data = 0xc00 | msixvec;
@@ -409,7 +478,7 @@ void __init xlp_init_node_msi_irqs(int node, int link)
 {
 	struct nlm_soc_info *nodep;
 	struct xlp_msi_data *md;
-	int irq, i, irt, msixvec;
+	int irq, i, irt, msixvec, val;
 
 	pr_info("[%d %d] Init node PCI IRT\n", node, link);
 	nodep = nlm_get_node(node);
@@ -430,19 +499,28 @@ void __init xlp_init_node_msi_irqs(int node, int link)
 		irq_set_handler_data(i, md);
 	}
 
-	for (i = 0; i < XLP_MSIXVEC_PER_LINK; i++) {
-		/* Initialize MSI-X irts to generate one interrupt per link */
-		msixvec = link * XLP_MSIXVEC_PER_LINK + i;
-		irt = PIC_IRT_PCIE_MSIX_INDEX(msixvec);
-		nlm_pic_init_irt(nodep->picbase, irt, PIC_PCIE_MSIX_IRQ(link),
-			node * nlm_threads_per_node(), 1 /* enable */);
+	for (i = 0; i < XLP_MSIXVEC_PER_LINK ; i++) {
+		if (cpu_is_xlp9xx()) {
+			val = ((node * nlm_threads_per_node()) << 7 |
+				PIC_PCIE_MSIX_IRQ(link) << 1 | 0 << 0);
+			nlm_write_pcie_reg(md->lnkbase, PCIE_9XX_MSIX_VECX(i +
+					(link * XLP_MSIXVEC_PER_LINK)), val);
+		} else {
+			/* Initialize MSI-X irts to generate one interrupt
+			 * per link
+			 */
+			msixvec = link * XLP_MSIXVEC_PER_LINK + i;
+			irt = PIC_IRT_PCIE_MSIX_INDEX(msixvec);
+			nlm_pic_init_irt(nodep->picbase, irt,
+					PIC_PCIE_MSIX_IRQ(link),
+					node * nlm_threads_per_node(), 1);
+		}
 
 		/* Initialize MSI-X extended irq space for the link  */
 		irq = nlm_irq_to_xirq(node, nlm_link_msixirq(link, i));
 		irq_set_chip_and_handler(irq, &xlp_msix_chip, handle_level_irq);
 		irq_set_handler_data(irq, md);
 	}
-
 }
 
 void nlm_dispatch_msi(int node, int lirq)
@@ -454,7 +532,11 @@ void nlm_dispatch_msi(int node, int lirq)
 	link = lirq - PIC_PCIE_LINK_MSI_IRQ_BASE;
 	irqbase = nlm_irq_to_xirq(node, nlm_link_msiirq(link, 0));
 	md = irq_get_handler_data(irqbase);
-	status = nlm_read_reg(md->lnkbase, PCIE_MSI_STATUS) &
+	if (cpu_is_xlp9xx())
+		status = nlm_read_reg(md->lnkbase, PCIE_9XX_MSI_STATUS) &
+						md->msi_enabled_mask;
+	else
+		status = nlm_read_reg(md->lnkbase, PCIE_MSI_STATUS) &
 						md->msi_enabled_mask;
 	while (status) {
 		i = __ffs(status);
@@ -472,10 +554,14 @@ void nlm_dispatch_msix(int node, int lirq)
 	link = lirq - PIC_PCIE_MSIX_IRQ_BASE;
 	irqbase = nlm_irq_to_xirq(node, nlm_link_msixirq(link, 0));
 	md = irq_get_handler_data(irqbase);
-	status = nlm_read_reg(md->lnkbase, PCIE_MSIX_STATUS);
+	if (cpu_is_xlp9xx())
+		status = nlm_read_reg(md->lnkbase, PCIE_9XX_MSIX_STATUSX(link));
+	else
+		status = nlm_read_reg(md->lnkbase, PCIE_MSIX_STATUS);
 
 	/* narrow it down to the MSI-x vectors for our link */
-	status = (status >> (link * XLP_MSIXVEC_PER_LINK)) &
+	if (!cpu_is_xlp9xx())
+		status = (status >> (link * XLP_MSIXVEC_PER_LINK)) &
 			((1 << XLP_MSIXVEC_PER_LINK) - 1);
 
 	while (status) {
diff --git a/arch/mips/pci/ops-pmcmsp.c b/arch/mips/pci/ops-pmcmsp.c
index 3d27800edba..50034f985be 100644
--- a/arch/mips/pci/ops-pmcmsp.c
+++ b/arch/mips/pci/ops-pmcmsp.c
@@ -7,7 +7,7 @@
  * Author: Jun Sun, jsun@mvista.com or jsun@junsun.net
  *
  * Much of the code is derived from the original DDB5074 port by
- * Geert Uytterhoeven <geert@sonycom.com>
+ * Geert Uytterhoeven <geert@linux-m68k.org>
  *
  * This program is free software; you can redistribute	it and/or modify it
  * under  the terms of	the GNU General	 Public License as published by the
diff --git a/arch/mips/pci/ops-tx3927.c b/arch/mips/pci/ops-tx3927.c
index 02d64f77e96..d35dc9c9ab9 100644
--- a/arch/mips/pci/ops-tx3927.c
+++ b/arch/mips/pci/ops-tx3927.c
@@ -11,7 +11,7 @@
  *     Define the pci_ops for TX3927.
  *
  * Much of the code is derived from the original DDB5074 port by
- * Geert Uytterhoeven <geert@sonycom.com>
+ * Geert Uytterhoeven <geert@linux-m68k.org>
  *
  *  This program is free software; you can redistribute  it and/or modify it
  *  under  the terms of  the GNU General  Public License as published by the
diff --git a/arch/mips/pci/ops-tx4927.c b/arch/mips/pci/ops-tx4927.c
index 3d5df514d02..0e046d82e4e 100644
--- a/arch/mips/pci/ops-tx4927.c
+++ b/arch/mips/pci/ops-tx4927.c
@@ -202,17 +202,20 @@ char *tx4927_pcibios_setup(char *str)
 	unsigned long val;
 
 	if (!strncmp(str, "trdyto=", 7)) {
-		if (strict_strtoul(str + 7, 0, &val) == 0)
+		u8 val = 0;
+		if (kstrtou8(str + 7, 0, &val) == 0)
 			tx4927_pci_opts.trdyto = val;
 		return NULL;
 	}
 	if (!strncmp(str, "retryto=", 8)) {
-		if (strict_strtoul(str + 8, 0, &val) == 0)
+		u8 val = 0;
+		if (kstrtou8(str + 8, 0, &val) == 0)
 			tx4927_pci_opts.retryto = val;
 		return NULL;
 	}
 	if (!strncmp(str, "gbwc=", 5)) {
-		if (strict_strtoul(str + 5, 0, &val) == 0)
+		u16 val;
+		if (kstrtou16(str + 5, 0, &val) == 0)
 			tx4927_pci_opts.gbwc = val;
 		return NULL;
 	}
diff --git a/arch/mips/pci/pci-virtio-guest.c b/arch/mips/pci/pci-virtio-guest.c
new file mode 100644
index 00000000000..40a078bc461
--- /dev/null
+++ b/arch/mips/pci/pci-virtio-guest.c
@@ -0,0 +1,131 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2013 Cavium, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+
+#include <uapi/asm/bitfield.h>
+#include <asm/byteorder.h>
+#include <asm/io.h>
+
+#define PCI_CONFIG_ADDRESS	0xcf8
+#define PCI_CONFIG_DATA		0xcfc
+
+union pci_config_address {
+	struct {
+		__BITFIELD_FIELD(unsigned enable_bit	  : 1,	/* 31       */
+		__BITFIELD_FIELD(unsigned reserved	  : 7,	/* 30 .. 24 */
+		__BITFIELD_FIELD(unsigned bus_number	  : 8,	/* 23 .. 16 */
+		__BITFIELD_FIELD(unsigned devfn_number	  : 8,	/* 15 .. 8  */
+		__BITFIELD_FIELD(unsigned register_number : 8,	/* 7  .. 0  */
+		)))));
+	};
+	u32 w;
+};
+
+int pcibios_plat_dev_init(struct pci_dev *dev)
+{
+	return 0;
+}
+
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	return ((pin + slot) % 4)+ MIPS_IRQ_PCIA;
+}
+
+static void pci_virtio_guest_write_config_addr(struct pci_bus *bus,
+					unsigned int devfn, int reg)
+{
+	union pci_config_address pca = { .w = 0 };
+
+	pca.register_number = reg;
+	pca.devfn_number = devfn;
+	pca.bus_number = bus->number;
+	pca.enable_bit = 1;
+
+	outl(pca.w, PCI_CONFIG_ADDRESS);
+}
+
+static int pci_virtio_guest_write_config(struct pci_bus *bus,
+		unsigned int devfn, int reg, int size, u32 val)
+{
+	pci_virtio_guest_write_config_addr(bus, devfn, reg);
+
+	switch (size) {
+	case 1:
+		outb(val, PCI_CONFIG_DATA + (reg & 3));
+		break;
+	case 2:
+		outw(val, PCI_CONFIG_DATA + (reg & 2));
+		break;
+	case 4:
+		outl(val, PCI_CONFIG_DATA);
+		break;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int pci_virtio_guest_read_config(struct pci_bus *bus, unsigned int devfn,
+					int reg, int size, u32 *val)
+{
+	pci_virtio_guest_write_config_addr(bus, devfn, reg);
+
+	switch (size) {
+	case 1:
+		*val = inb(PCI_CONFIG_DATA + (reg & 3));
+		break;
+	case 2:
+		*val = inw(PCI_CONFIG_DATA + (reg & 2));
+		break;
+	case 4:
+		*val = inl(PCI_CONFIG_DATA);
+		break;
+	}
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops pci_virtio_guest_ops = {
+	.read  = pci_virtio_guest_read_config,
+	.write = pci_virtio_guest_write_config,
+};
+
+static struct resource pci_virtio_guest_mem_resource = {
+	.name = "Virtio MEM",
+	.flags = IORESOURCE_MEM,
+	.start	= 0x10000000,
+	.end	= 0x1dffffff
+};
+
+static struct resource pci_virtio_guest_io_resource = {
+	.name = "Virtio IO",
+	.flags = IORESOURCE_IO,
+	.start	= 0,
+	.end	= 0xffff
+};
+
+static struct pci_controller pci_virtio_guest_controller = {
+	.pci_ops = &pci_virtio_guest_ops,
+	.mem_resource = &pci_virtio_guest_mem_resource,
+	.io_resource = &pci_virtio_guest_io_resource,
+};
+
+static int __init pci_virtio_guest_setup(void)
+{
+	pr_err("pci_virtio_guest_setup\n");
+
+	/* Virtio comes pre-assigned */
+	pci_set_flags(PCI_PROBE_ONLY);
+
+	pci_virtio_guest_controller.io_map_base = mips_io_port_base;
+	register_pci_controller(&pci_virtio_guest_controller);
+	return 0;
+}
+arch_initcall(pci_virtio_guest_setup);
diff --git a/arch/mips/pmcs-msp71xx/Makefile b/arch/mips/pmcs-msp71xx/Makefile
index 9201c8b3858..d4f7220f248 100644
--- a/arch/mips/pmcs-msp71xx/Makefile
+++ b/arch/mips/pmcs-msp71xx/Makefile
@@ -10,4 +10,3 @@ obj-$(CONFIG_PCI) += msp_pci.o
 obj-$(CONFIG_MSP_HAS_MAC) += msp_eth.o
 obj-$(CONFIG_MSP_HAS_USB) += msp_usb.o
 obj-$(CONFIG_MIPS_MT_SMP) += msp_smp.o
-obj-$(CONFIG_MIPS_MT_SMTC) += msp_smtc.o
diff --git a/arch/mips/pmcs-msp71xx/msp_eth.c b/arch/mips/pmcs-msp71xx/msp_eth.c
index c584df393de..15679b427f4 100644
--- a/arch/mips/pmcs-msp71xx/msp_eth.c
+++ b/arch/mips/pmcs-msp71xx/msp_eth.c
@@ -38,73 +38,6 @@
 #define MSP_ETHERNET_GPIO1	15
 #define MSP_ETHERNET_GPIO2	16
 
-#ifdef CONFIG_MSP_HAS_TSMAC
-#define MSP_TSMAC_SIZE	0x10020
-#define MSP_TSMAC_ID	"pmc_tsmac"
-
-static struct resource msp_tsmac0_resources[] = {
-	[0] = {
-		.start	= MSP_MAC0_BASE,
-		.end	= MSP_MAC0_BASE + MSP_TSMAC_SIZE - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= MSP_INT_MAC0,
-		.end	= MSP_INT_MAC0,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource msp_tsmac1_resources[] = {
-	[0] = {
-		.start	= MSP_MAC1_BASE,
-		.end	= MSP_MAC1_BASE + MSP_TSMAC_SIZE - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= MSP_INT_MAC1,
-		.end	= MSP_INT_MAC1,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-static struct resource msp_tsmac2_resources[] = {
-	[0] = {
-		.start	= MSP_MAC2_BASE,
-		.end	= MSP_MAC2_BASE + MSP_TSMAC_SIZE - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= MSP_INT_SAR,
-		.end	= MSP_INT_SAR,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-
-static struct platform_device tsmac_device[] = {
-	[0] = {
-		.name	= MSP_TSMAC_ID,
-		.id	= 0,
-		.num_resources = ARRAY_SIZE(msp_tsmac0_resources),
-		.resource = msp_tsmac0_resources,
-	},
-	[1] = {
-		.name	= MSP_TSMAC_ID,
-		.id	= 1,
-		.num_resources = ARRAY_SIZE(msp_tsmac1_resources),
-		.resource = msp_tsmac1_resources,
-	},
-	[2] = {
-		.name	= MSP_TSMAC_ID,
-		.id	= 2,
-		.num_resources = ARRAY_SIZE(msp_tsmac2_resources),
-		.resource = msp_tsmac2_resources,
-	},
-};
-#define msp_eth_devs	tsmac_device
-
-#else
-/* If it is not TSMAC assume MSP_ETH (100Mbps) */
 #define MSP_ETH_ID	"pmc_mspeth"
 #define MSP_ETH_SIZE	0xE0
 static struct resource msp_eth0_resources[] = {
@@ -152,7 +85,6 @@ static struct platform_device mspeth_device[] = {
 };
 #define msp_eth_devs	mspeth_device
 
-#endif
 int __init msp_eth_setup(void)
 {
 	int i, ret = 0;
@@ -161,14 +93,6 @@ int __init msp_eth_setup(void)
 	msp_gpio_pin_mode(MSP_GPIO_OUTPUT, MSP_ETHERNET_GPIO0);
 	msp_gpio_pin_hi(MSP_ETHERNET_GPIO0);
 
-#ifdef CONFIG_MSP_HAS_TSMAC
-	/* 3 phys on boards with TSMAC */
-	msp_gpio_pin_mode(MSP_GPIO_OUTPUT, MSP_ETHERNET_GPIO1);
-	msp_gpio_pin_hi(MSP_ETHERNET_GPIO1);
-
-	msp_gpio_pin_mode(MSP_GPIO_OUTPUT, MSP_ETHERNET_GPIO2);
-	msp_gpio_pin_hi(MSP_ETHERNET_GPIO2);
-#endif
 	for (i = 0; i < ARRAY_SIZE(msp_eth_devs); i++) {
 		ret = platform_device_register(&msp_eth_devs[i]);
 		printk(KERN_INFO "device: %d, return value = %d\n", i, ret);
diff --git a/arch/mips/pmcs-msp71xx/msp_irq.c b/arch/mips/pmcs-msp71xx/msp_irq.c
index 9da5619c00a..941744aabb5 100644
--- a/arch/mips/pmcs-msp71xx/msp_irq.c
+++ b/arch/mips/pmcs-msp71xx/msp_irq.c
@@ -32,7 +32,7 @@ extern void msp_vsmp_int_init(void);
 
 /* vectored interrupt implementation */
 
-/* SW0/1 interrupts are used for SMP/SMTC */
+/* SW0/1 interrupts are used for SMP  */
 static inline void mac0_int_dispatch(void) { do_IRQ(MSP_INT_MAC0); }
 static inline void mac1_int_dispatch(void) { do_IRQ(MSP_INT_MAC1); }
 static inline void mac2_int_dispatch(void) { do_IRQ(MSP_INT_SAR); }
@@ -138,14 +138,6 @@ void __init arch_init_irq(void)
 	set_vi_handler(MSP_INT_SEC, sec_int_dispatch);
 #ifdef CONFIG_MIPS_MT_SMP
 	msp_vsmp_int_init();
-#elif defined CONFIG_MIPS_MT_SMTC
-	/*Set hwmask for all platform devices */
-	irq_hwmask[MSP_INT_MAC0] = C_IRQ0;
-	irq_hwmask[MSP_INT_MAC1] = C_IRQ1;
-	irq_hwmask[MSP_INT_USB] = C_IRQ2;
-	irq_hwmask[MSP_INT_SAR] = C_IRQ3;
-	irq_hwmask[MSP_INT_SEC] = C_IRQ5;
-
 #endif	/* CONFIG_MIPS_MT_SMP */
 #endif	/* CONFIG_MIPS_MT */
 	/* setup the cascaded interrupts */
@@ -153,8 +145,10 @@ void __init arch_init_irq(void)
 	setup_irq(MSP_INT_PER, &per_cascade_msp);
 
 #else
-	/* setup the 2nd-level SLP register based interrupt controller */
-	/* VSMP /SMTC support support is not enabled for SLP */
+	/*
+	 * Setup the 2nd-level SLP register based interrupt controller.
+	 * VSMP support support is not enabled for SLP.
+	 */
 	msp_slp_irq_init();
 
 	/* setup the cascaded SLP/PER interrupts */
diff --git a/arch/mips/pmcs-msp71xx/msp_irq_cic.c b/arch/mips/pmcs-msp71xx/msp_irq_cic.c
index e49b499f66d..b8df2f7b332 100644
--- a/arch/mips/pmcs-msp71xx/msp_irq_cic.c
+++ b/arch/mips/pmcs-msp71xx/msp_irq_cic.c
@@ -120,10 +120,9 @@ static void msp_cic_irq_ack(struct irq_data *d)
 	* hurt for the others
 	*/
 	*CIC_STS_REG = (1 << (d->irq - MSP_CIC_INTBASE));
-	smtc_im_ack_irq(d->irq);
 }
 
-/*Note: Limiting to VSMP . Not tested in SMTC */
+/* Note: Limiting to VSMP.  */
 
 #ifdef CONFIG_MIPS_MT_SMP
 static int msp_cic_irq_set_affinity(struct irq_data *d,
@@ -183,10 +182,6 @@ void __init msp_cic_irq_init(void)
 	for (i = MSP_CIC_INTBASE ; i < MSP_CIC_INTBASE + 32 ; i++) {
 		irq_set_chip_and_handler(i, &msp_cic_irq_controller,
 					 handle_level_irq);
-#ifdef CONFIG_MIPS_MT_SMTC
-		/* Mask of CIC interrupt */
-		irq_hwmask[i] = C_IRQ4;
-#endif
 	}
 
 	/* Initialize the PER interrupt sub-system */
diff --git a/arch/mips/pmcs-msp71xx/msp_irq_per.c b/arch/mips/pmcs-msp71xx/msp_irq_per.c
index d1fd530479d..a111836bcec 100644
--- a/arch/mips/pmcs-msp71xx/msp_irq_per.c
+++ b/arch/mips/pmcs-msp71xx/msp_irq_per.c
@@ -113,9 +113,6 @@ void __init msp_per_irq_init(void)
 	/* initialize all the IRQ descriptors */
 	for (i = MSP_PER_INTBASE; i < MSP_PER_INTBASE + 32; i++) {
 		irq_set_chip(i, &msp_per_irq_controller);
-#ifdef CONFIG_MIPS_MT_SMTC
-		irq_hwmask[i] = C_IRQ4;
-#endif
 	}
 }
 
diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c
index 7e980767679..4f925e06c41 100644
--- a/arch/mips/pmcs-msp71xx/msp_setup.c
+++ b/arch/mips/pmcs-msp71xx/msp_setup.c
@@ -27,7 +27,6 @@
 #endif
 
 extern void msp_serial_setup(void);
-extern void pmctwiled_setup(void);
 
 #if defined(CONFIG_PMC_MSP7120_EVAL) || \
     defined(CONFIG_PMC_MSP7120_GW) || \
@@ -148,8 +147,6 @@ void __init plat_mem_setup(void)
 	pm_power_off = msp_power_off;
 }
 
-extern struct plat_smp_ops msp_smtc_smp_ops;
-
 void __init prom_init(void)
 {
 	unsigned long family;
@@ -230,17 +227,5 @@ void __init prom_init(void)
 	 */
 	msp_serial_setup();
 
-	if (register_vsmp_smp_ops()) {
-#ifdef CONFIG_MIPS_MT_SMTC
-		register_smp_ops(&msp_smtc_smp_ops);
-#endif
-	}
-
-#ifdef CONFIG_PMCTWILED
-	/*
-	 * Setup LED states before the subsys_initcall loads other
-	 * dependent drivers/modules.
-	 */
-	pmctwiled_setup();
-#endif
+	register_vsmp_smp_ops();
 }
diff --git a/arch/mips/pmcs-msp71xx/msp_smtc.c b/arch/mips/pmcs-msp71xx/msp_smtc.c
deleted file mode 100644
index 6b5607fce27..00000000000
--- a/arch/mips/pmcs-msp71xx/msp_smtc.c
+++ /dev/null
@@ -1,104 +0,0 @@
-/*
- * MSP71xx Platform-specific hooks for SMP operation
- */
-#include <linux/irq.h>
-#include <linux/init.h>
-
-#include <asm/mipsmtregs.h>
-#include <asm/mipsregs.h>
-#include <asm/smtc.h>
-#include <asm/smtc_ipi.h>
-
-/* VPE/SMP Prototype implements platform interfaces directly */
-
-/*
- * Cause the specified action to be performed on a targeted "CPU"
- */
-
-static void msp_smtc_send_ipi_single(int cpu, unsigned int action)
-{
-	/* "CPU" may be TC of same VPE, VPE of same CPU, or different CPU */
-	smtc_send_ipi(cpu, LINUX_SMP_IPI, action);
-}
-
-static void msp_smtc_send_ipi_mask(const struct cpumask *mask,
-						unsigned int action)
-{
-	unsigned int i;
-
-	for_each_cpu(i, mask)
-		msp_smtc_send_ipi_single(i, action);
-}
-
-/*
- * Post-config but pre-boot cleanup entry point
- */
-static void msp_smtc_init_secondary(void)
-{
-	int myvpe;
-
-	/* Don't enable Malta I/O interrupts (IP2) for secondary VPEs */
-	myvpe = read_c0_tcbind() & TCBIND_CURVPE;
-	if (myvpe > 0)
-		change_c0_status(ST0_IM, STATUSF_IP0 | STATUSF_IP1 |
-				STATUSF_IP6 | STATUSF_IP7);
-	smtc_init_secondary();
-}
-
-/*
- * Platform "CPU" startup hook
- */
-static void msp_smtc_boot_secondary(int cpu, struct task_struct *idle)
-{
-	smtc_boot_secondary(cpu, idle);
-}
-
-/*
- * SMP initialization finalization entry point
- */
-static void msp_smtc_smp_finish(void)
-{
-	smtc_smp_finish();
-}
-
-/*
- * Hook for after all CPUs are online
- */
-
-static void msp_smtc_cpus_done(void)
-{
-}
-
-/*
- * Platform SMP pre-initialization
- *
- * As noted above, we can assume a single CPU for now
- * but it may be multithreaded.
- */
-
-static void __init msp_smtc_smp_setup(void)
-{
-	/*
-	 * we won't get the definitive value until
-	 * we've run smtc_prepare_cpus later, but
-	 */
-
-	if (read_c0_config3() & (1 << 2))
-		smp_num_siblings = smtc_build_cpu_map(0);
-}
-
-static void __init msp_smtc_prepare_cpus(unsigned int max_cpus)
-{
-	smtc_prepare_cpus(max_cpus);
-}
-
-struct plat_smp_ops msp_smtc_smp_ops = {
-	.send_ipi_single	= msp_smtc_send_ipi_single,
-	.send_ipi_mask		= msp_smtc_send_ipi_mask,
-	.init_secondary		= msp_smtc_init_secondary,
-	.smp_finish		= msp_smtc_smp_finish,
-	.cpus_done		= msp_smtc_cpus_done,
-	.boot_secondary		= msp_smtc_boot_secondary,
-	.smp_setup		= msp_smtc_smp_setup,
-	.prepare_cpus		= msp_smtc_prepare_cpus,
-};
diff --git a/arch/mips/pmcs-msp71xx/msp_usb.c b/arch/mips/pmcs-msp71xx/msp_usb.c
index 4dab915696e..c87c5f810cd 100644
--- a/arch/mips/pmcs-msp71xx/msp_usb.c
+++ b/arch/mips/pmcs-msp71xx/msp_usb.c
@@ -75,47 +75,6 @@ static struct mspusb_device msp_usbhost0_device = {
 		.resource	= msp_usbhost0_resources,
 	},
 };
-
-/* MSP7140/MSP82XX has two USB2 hosts. */
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-static u64 msp_usbhost1_dma_mask = 0xffffffffUL;
-
-static struct resource msp_usbhost1_resources[] = {
-	[0] = { /* EHCI-HS operational and capabilities registers */
-		.start	= MSP_USB1_HS_START,
-		.end	= MSP_USB1_HS_END,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= MSP_INT_USB,
-		.end	= MSP_INT_USB,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = { /* MSBus-to-AMBA bridge register space */
-		.start	= MSP_USB1_MAB_START,
-		.end	= MSP_USB1_MAB_END,
-		.flags	= IORESOURCE_MEM,
-	},
-	[3] = { /* Identification and general hardware parameters */
-		.start	= MSP_USB1_ID_START,
-		.end	= MSP_USB1_ID_END,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-static struct mspusb_device msp_usbhost1_device = {
-	.dev	= {
-		.name	= "pmcmsp-ehci",
-		.id	= 1,
-		.dev	= {
-			.dma_mask = &msp_usbhost1_dma_mask,
-			.coherent_dma_mask = 0xffffffffUL,
-		},
-		.num_resources	= ARRAY_SIZE(msp_usbhost1_resources),
-		.resource	= msp_usbhost1_resources,
-	},
-};
-#endif /* CONFIG_MSP_HAS_DUAL_USB */
 #endif /* CONFIG_USB_EHCI_HCD */
 
 #if defined(CONFIG_USB_GADGET)
@@ -157,46 +116,6 @@ static struct mspusb_device msp_usbdev0_device = {
 		.resource	= msp_usbdev0_resources,
 	},
 };
-
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-static struct resource msp_usbdev1_resources[] = {
-	[0] = { /* EHCI-HS operational and capabilities registers */
-		.start	= MSP_USB1_HS_START,
-		.end	= MSP_USB1_HS_END,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= MSP_INT_USB,
-		.end	= MSP_INT_USB,
-		.flags	= IORESOURCE_IRQ,
-	},
-	[2] = { /* MSBus-to-AMBA bridge register space */
-		.start	= MSP_USB1_MAB_START,
-		.end	= MSP_USB1_MAB_END,
-		.flags	= IORESOURCE_MEM,
-	},
-	[3] = { /* Identification and general hardware parameters */
-		.start	= MSP_USB1_ID_START,
-		.end	= MSP_USB1_ID_END,
-		.flags	= IORESOURCE_MEM,
-	},
-};
-
-/* This may need to be converted to a mspusb_device, too. */
-static struct mspusb_device msp_usbdev1_device = {
-	.dev	= {
-		.name	= "msp71xx_udc",
-		.id	= 0,
-		.dev	= {
-			.dma_mask = &msp_usbdev_dma_mask,
-			.coherent_dma_mask = 0xffffffffUL,
-		},
-		.num_resources	= ARRAY_SIZE(msp_usbdev1_resources),
-		.resource	= msp_usbdev1_resources,
-	},
-};
-
-#endif /* CONFIG_MSP_HAS_DUAL_USB */
 #endif /* CONFIG_USB_GADGET */
 
 static int __init msp_usb_setup(void)
@@ -231,10 +150,6 @@ static int __init msp_usb_setup(void)
 #if defined(CONFIG_USB_EHCI_HCD)
 		msp_devs[0] = &msp_usbhost0_device.dev;
 		ppfinit("platform add USB HOST done %s.\n", msp_devs[0]->name);
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-		msp_devs[1] = &msp_usbhost1_device.dev;
-		ppfinit("platform add USB HOST done %s.\n", msp_devs[1]->name);
-#endif
 #else
 		ppfinit("%s: echi_hcd not supported\n", __FILE__);
 #endif	/* CONFIG_USB_EHCI_HCD */
@@ -244,11 +159,6 @@ static int __init msp_usb_setup(void)
 		msp_devs[0] = &msp_usbdev0_device.dev;
 		ppfinit("platform add USB DEVICE done %s.\n"
 					, msp_devs[0]->name);
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-		msp_devs[1] = &msp_usbdev1_device.dev;
-		ppfinit("platform add USB DEVICE done %s.\n"
-					, msp_devs[1]->name);
-#endif
 #else
 		ppfinit("%s: usb_gadget not supported\n", __FILE__);
 #endif	/* CONFIG_USB_GADGET */
diff --git a/arch/mips/pnx833x/common/platform.c b/arch/mips/pnx833x/common/platform.c
index 2b7e837dc2e..b4b774bc317 100644
--- a/arch/mips/pnx833x/common/platform.c
+++ b/arch/mips/pnx833x/common/platform.c
@@ -33,11 +33,6 @@
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
 
-#ifdef CONFIG_I2C_PNX0105
-/* Until i2c driver available in kernel.*/
-#include <linux/i2c-pnx0105.h>
-#endif
-
 #include <irq.h>
 #include <irq-mapping.h>
 #include <pnx833x.h>
@@ -134,70 +129,6 @@ static struct platform_device pnx833x_usb_ehci_device = {
 	.resource	= pnx833x_usb_ehci_resources,
 };
 
-#ifdef CONFIG_I2C_PNX0105
-static struct resource pnx833x_i2c0_resources[] = {
-	{
-		.start		= PNX833X_I2C0_PORTS_START,
-		.end		= PNX833X_I2C0_PORTS_END,
-		.flags		= IORESOURCE_MEM,
-	},
-	{
-		.start		= PNX833X_PIC_I2C0_INT,
-		.end		= PNX833X_PIC_I2C0_INT,
-		.flags		= IORESOURCE_IRQ,
-	},
-};
-
-static struct resource pnx833x_i2c1_resources[] = {
-	{
-		.start		= PNX833X_I2C1_PORTS_START,
-		.end		= PNX833X_I2C1_PORTS_END,
-		.flags		= IORESOURCE_MEM,
-	},
-	{
-		.start		= PNX833X_PIC_I2C1_INT,
-		.end		= PNX833X_PIC_I2C1_INT,
-		.flags		= IORESOURCE_IRQ,
-	},
-};
-
-static struct i2c_pnx0105_dev pnx833x_i2c_dev[] = {
-	{
-		.base = PNX833X_I2C0_PORTS_START,
-		.irq = -1, /* should be PNX833X_PIC_I2C0_INT but polling is faster */
-		.clock = 6,	/* 0 == 400 kHz, 4 == 100 kHz(Maximum HDMI), 6 = 50kHz(Preferred HDCP) */
-		.bus_addr = 0,	/* no slave support */
-	},
-	{
-		.base = PNX833X_I2C1_PORTS_START,
-		.irq = -1,	/* on high freq, polling is faster */
-		/*.irq = PNX833X_PIC_I2C1_INT,*/
-		.clock = 4,	/* 0 == 400 kHz, 4 == 100 kHz. 100 kHz seems a safe default for now */
-		.bus_addr = 0,	/* no slave support */
-	},
-};
-
-static struct platform_device pnx833x_i2c0_device = {
-	.name		= "i2c-pnx0105",
-	.id		= 0,
-	.dev = {
-		.platform_data = &pnx833x_i2c_dev[0],
-	},
-	.num_resources	= ARRAY_SIZE(pnx833x_i2c0_resources),
-	.resource	= pnx833x_i2c0_resources,
-};
-
-static struct platform_device pnx833x_i2c1_device = {
-	.name		= "i2c-pnx0105",
-	.id		= 1,
-	.dev = {
-		.platform_data = &pnx833x_i2c_dev[1],
-	},
-	.num_resources	= ARRAY_SIZE(pnx833x_i2c1_resources),
-	.resource	= pnx833x_i2c1_resources,
-};
-#endif
-
 static u64 ethernet_dmamask = DMA_BIT_MASK(32);
 
 static struct resource pnx833x_ethernet_resources[] = {
@@ -294,10 +225,6 @@ static struct platform_device pnx833x_flash_nand = {
 static struct platform_device *pnx833x_platform_devices[] __initdata = {
 	&pnx833x_uart_device,
 	&pnx833x_usb_ehci_device,
-#ifdef CONFIG_I2C_PNX0105
-	&pnx833x_i2c0_device,
-	&pnx833x_i2c1_device,
-#endif
 	&pnx833x_ethernet_device,
 	&pnx833x_sata_device,
 	&pnx833x_flash_nand,
diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c
index ab0e379dc7e..8e52446286c 100644
--- a/arch/mips/sgi-ip22/ip22-gio.c
+++ b/arch/mips/sgi-ip22/ip22-gio.c
@@ -19,6 +19,9 @@ static struct {
 } gio_name_table[] = {
 	{ .name = "SGI Impact", .id = 0x10 },
 	{ .name = "Phobos G160", .id = 0x35 },
+	{ .name = "Phobos G130", .id = 0x36 },
+	{ .name = "Phobos G100", .id = 0x37 },
+	{ .name = "Set Engineering GFE", .id = 0x38 },
 	/* fake IDs */
 	{ .name = "SGI Newport", .id = 0x7e },
 	{ .name = "SGI GR2/GR3", .id = 0x7f },
@@ -293,7 +296,16 @@ static int ip22_gio_id(unsigned long addr, u32 *res)
 		 * data matches
 		 */
 		ptr8 = (void *)CKSEG1ADDR(addr + 3);
-		get_dbe(tmp8, ptr8);
+		if (get_dbe(tmp8, ptr8)) {
+			/*
+			 * 32bit access worked, but 8bit doesn't
+			 * so we don't see phantom reads on
+			 * a pipelined bus, but a real card which
+			 * doesn't support 8 bit reads
+			 */
+			*res = tmp32;
+			return 1;
+		}
 		ptr16 = (void *)CKSEG1ADDR(addr + 2);
 		get_dbe(tmp16, ptr16);
 		if (tmp8 == (tmp16 & 0xff) &&
@@ -324,7 +336,7 @@ static int ip22_is_gr2(unsigned long addr)
 }
 
 
-static void ip22_check_gio(int slotno, unsigned long addr)
+static void ip22_check_gio(int slotno, unsigned long addr, int irq)
 {
 	const char *name = "Unknown";
 	struct gio_device *gio_dev;
@@ -338,9 +350,9 @@ static void ip22_check_gio(int slotno, unsigned long addr)
 	else {
 		if (!ip22_gio_id(addr, &tmp)) {
 			/*
-			 * no GIO signature at start address of slot, but
-			 * Newport doesn't have one, so let's check usea
-			 * status register
+			 * no GIO signature at start address of slot
+			 * since Newport doesn't have one, we check if
+			 * user status register is readable
 			 */
 			if (ip22_gio_id(addr + NEWPORT_USTATUS_OFFS, &tmp))
 				tmp = 0x7e;
@@ -369,6 +381,7 @@ static void ip22_check_gio(int slotno, unsigned long addr)
 		gio_dev->resource.start = addr;
 		gio_dev->resource.end = addr + 0x3fffff;
 		gio_dev->resource.flags = IORESOURCE_MEM;
+		gio_dev->irq = irq;
 		dev_set_name(&gio_dev->dev, "%d", slotno);
 		gio_device_register(gio_dev);
 	} else
@@ -408,16 +421,17 @@ int __init ip22_gio_init(void)
 		request_resource(&iomem_resource, &gio_bus_resource);
 		printk(KERN_INFO "GIO: Probing bus...\n");
 
-		if (ip22_is_fullhouse() ||
-		    !get_dbe(pbdma, (unsigned int *)&hpc3c1->pbdma[1])) {
-			/* Indigo2 and ChallengeS */
-			ip22_check_gio(0, GIO_SLOT_GFX_BASE);
-			ip22_check_gio(1, GIO_SLOT_EXP0_BASE);
+		if (ip22_is_fullhouse()) {
+			/* Indigo2 */
+			ip22_check_gio(0, GIO_SLOT_GFX_BASE, SGI_GIO_1_IRQ);
+			ip22_check_gio(1, GIO_SLOT_EXP0_BASE, SGI_GIO_1_IRQ);
 		} else {
-			/* Indy */
-			ip22_check_gio(0, GIO_SLOT_GFX_BASE);
-			ip22_check_gio(1, GIO_SLOT_EXP0_BASE);
-			ip22_check_gio(2, GIO_SLOT_EXP1_BASE);
+			/* Indy/Challenge S */
+			if (get_dbe(pbdma, (unsigned int *)&hpc3c1->pbdma[1]))
+				ip22_check_gio(0, GIO_SLOT_GFX_BASE,
+					       SGI_GIO_0_IRQ);
+			ip22_check_gio(1, GIO_SLOT_EXP0_BASE, SGI_GIOEXP0_IRQ);
+			ip22_check_gio(2, GIO_SLOT_EXP1_BASE, SGI_GIOEXP1_IRQ);
 		}
 	} else
 		device_unregister(&gio_bus);
diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c
index 58b40ae5933..c66889fc491 100644
--- a/arch/mips/sgi-ip22/ip22-int.c
+++ b/arch/mips/sgi-ip22/ip22-int.c
@@ -119,9 +119,14 @@ static void indy_local0_irqdispatch(void)
 	} else
 		irq = lc0msk_to_irqnr[mask];
 
-	/* if irq == 0, then the interrupt has already been cleared */
+	/*
+	 * workaround for INT2 bug; if irq == 0, INT2 has seen a fifo full
+	 * irq, but failed to latch it into status register
+	 */
 	if (irq)
 		do_IRQ(irq);
+	else
+		do_IRQ(SGINT_LOCAL0 + 0);
 }
 
 static void indy_local1_irqdispatch(void)
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index f4ea8aa79ba..f9ae6a8fa7c 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -186,10 +186,6 @@ static void ip27_smp_finish(void)
 	local_irq_enable();
 }
 
-static void __init ip27_cpus_done(void)
-{
-}
-
 /*
  * Launch a slave into smp_bootstrap().	 It doesn't take an argument, and we
  * set sp to the kernel stack of the newly created idle process, gp to the proc
@@ -236,7 +232,6 @@ struct plat_smp_ops ip27_smp_ops = {
 	.send_ipi_mask		= ip27_send_ipi_mask,
 	.init_secondary		= ip27_init_secondary,
 	.smp_finish		= ip27_smp_finish,
-	.cpus_done		= ip27_cpus_done,
 	.boot_secondary		= ip27_boot_secondary,
 	.smp_setup		= ip27_smp_setup,
 	.prepare_cpus		= ip27_prepare_cpus,
diff --git a/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c
index 59cfe265977..373fbbc8425 100644
--- a/arch/mips/sibyte/bcm1480/irq.c
+++ b/arch/mips/sibyte/bcm1480/irq.c
@@ -347,19 +347,8 @@ asmlinkage void plat_irq_dispatch(void)
 	unsigned int cpu = smp_processor_id();
 	unsigned int pending;
 
-#ifdef CONFIG_SIBYTE_BCM1480_PROF
-	/* Set compare to count to silence count/compare timer interrupts */
-	write_c0_compare(read_c0_count());
-#endif
-
 	pending = read_c0_cause() & read_c0_status();
 
-#ifdef CONFIG_SIBYTE_BCM1480_PROF
-	if (pending & CAUSEF_IP7)	/* Cpu performance counter interrupt */
-		sbprof_cpu_intr();
-	else
-#endif
-
 	if (pending & CAUSEF_IP4)
 		do_IRQ(K_BCM1480_INT_TIMER_0 + cpu);
 #ifdef CONFIG_SMP
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index 70d9182b26f..af7d44edd9a 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -115,13 +115,6 @@ static void bcm1480_smp_finish(void)
 }
 
 /*
- * Final cleanup after all secondaries booted
- */
-static void bcm1480_cpus_done(void)
-{
-}
-
-/*
  * Setup the PC, SP, and GP of a secondary processor and start it
  * running!
  */
@@ -170,7 +163,6 @@ struct plat_smp_ops bcm1480_smp_ops = {
 	.send_ipi_mask		= bcm1480_send_ipi_mask,
 	.init_secondary		= bcm1480_init_secondary,
 	.smp_finish		= bcm1480_smp_finish,
-	.cpus_done		= bcm1480_cpus_done,
 	.boot_secondary		= bcm1480_boot_secondary,
 	.smp_setup		= bcm1480_smp_setup,
 	.prepare_cpus		= bcm1480_prepare_cpus,
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index db976117dd4..c0c4b3f88a0 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -103,13 +103,6 @@ static void sb1250_smp_finish(void)
 }
 
 /*
- * Final cleanup after all secondaries booted
- */
-static void sb1250_cpus_done(void)
-{
-}
-
-/*
  * Setup the PC, SP, and GP of a secondary processor and start it
  * running!
  */
@@ -158,7 +151,6 @@ struct plat_smp_ops sb_smp_ops = {
 	.send_ipi_mask		= sb1250_send_ipi_mask,
 	.init_secondary		= sb1250_init_secondary,
 	.smp_finish		= sb1250_smp_finish,
-	.cpus_done		= sb1250_cpus_done,
 	.boot_secondary		= sb1250_boot_secondary,
 	.smp_setup		= sb1250_smp_setup,
 	.prepare_cpus		= sb1250_prepare_cpus,
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 2b0b83c171e..dd2cf25b5ae 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -309,8 +309,8 @@ static void __init preprocess_cmdline(void)
 			txx9_board_vec = find_board_byname(str + 6);
 			continue;
 		} else if (strncmp(str, "masterclk=", 10) == 0) {
-			unsigned long val;
-			if (strict_strtoul(str + 10, 10, &val) == 0)
+			unsigned int val;
+			if (kstrtouint(str + 10, 10, &val) == 0)
 				txx9_master_clock = val;
 			continue;
 		} else if (strcmp(str, "icdisable") == 0) {
diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h
index 8b80b19d0c8..769d5ed8e99 100644
--- a/arch/mn10300/include/asm/processor.h
+++ b/arch/mn10300/include/asm/processor.h
@@ -68,7 +68,9 @@ extern struct mn10300_cpuinfo cpu_data[];
 extern void identify_cpu(struct mn10300_cpuinfo *);
 extern void print_cpu_info(struct mn10300_cpuinfo *);
 extern void dodgy_tsc(void);
+
 #define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * User space process size: 1.75GB (default).
diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h
index cab746fa9e8..4d235e3d253 100644
--- a/arch/openrisc/include/asm/processor.h
+++ b/arch/openrisc/include/asm/processor.h
@@ -101,6 +101,7 @@ extern unsigned long thread_saved_pc(struct task_struct *t);
 #define init_stack      (init_thread_union.stack)
 
 #define cpu_relax()     barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_OPENRISC_PROCESSOR_H */
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 108d48e652a..6e75e203092 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -6,7 +6,6 @@ config PARISC
 	select HAVE_OPROFILE
 	select HAVE_FUNCTION_TRACER if 64BIT
 	select HAVE_FUNCTION_GRAPH_TRACER if 64BIT
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST if 64BIT
 	select ARCH_WANT_FRAME_POINTERS
 	select RTC_CLASS
 	select RTC_DRV_GENERIC
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index d951c9681ab..689a8ade360 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -338,6 +338,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)	((tsk)->thread.regs.gr[30])
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /* Used as a macro to identify the combined VIPT/PIPT cached
  * CPUs which require a guarantee of coherency (no inequivalent
diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h
index a2fa297196b..f5645d6a89f 100644
--- a/arch/parisc/include/uapi/asm/signal.h
+++ b/arch/parisc/include/uapi/asm/signal.h
@@ -69,8 +69,6 @@
 #define SA_NOMASK	SA_NODEFER
 #define SA_ONESHOT	SA_RESETHAND
 
-#define SA_RESTORER	0x04000000 /* obsolete -- ignored */
-
 #define MINSIGSTKSZ	2048
 #define SIGSTKSZ	8192
 
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index 5beb97bafbb..559d400f938 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -112,6 +112,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	unsigned long long calltime;
 	struct ftrace_graph_ent trace;
 
+	if (unlikely(ftrace_graph_is_dead()))
+		return;
+
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
@@ -152,9 +155,6 @@ void ftrace_function_trampoline(unsigned long parent,
 {
 	extern ftrace_func_t ftrace_trace_function;
 
-	if (function_trace_stop)
-		return;
-
 	if (ftrace_trace_function != ftrace_stub) {
 		ftrace_trace_function(parent, self_addr);
 		return;
diff --git a/arch/parisc/kernel/hardware.c b/arch/parisc/kernel/hardware.c
index 608716f8496..af3bc359dc7 100644
--- a/arch/parisc/kernel/hardware.c
+++ b/arch/parisc/kernel/hardware.c
@@ -1210,7 +1210,8 @@ static struct hp_hardware hp_hardware_list[] = {
 	{HPHW_FIO, 0x004, 0x00320, 0x0, "Metheus Frame Buffer"}, 
 	{HPHW_FIO, 0x004, 0x00340, 0x0, "BARCO CX4500 VME Grphx Cnsl"}, 
 	{HPHW_FIO, 0x004, 0x00360, 0x0, "Hughes TOG VME FDDI"}, 
-	{HPHW_FIO, 0x076, 0x000AD, 0x00, "Crestone Peak RS-232"},
+	{HPHW_FIO, 0x076, 0x000AD, 0x0, "Crestone Peak Core RS-232"},
+	{HPHW_FIO, 0x077, 0x000AD, 0x0, "Crestone Peak Fast? Core RS-232"},
 	{HPHW_IOA, 0x185, 0x0000B, 0x00, "Java BC Summit Port"}, 
 	{HPHW_IOA, 0x1FF, 0x0000B, 0x00, "Hitachi Ghostview Summit Port"}, 
 	{HPHW_IOA, 0x580, 0x0000B, 0x10, "U2-IOA BC Runway Port"}, 
diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c
index bb9f3b64de5..93c1963d76f 100644
--- a/arch/parisc/kernel/sys_parisc32.c
+++ b/arch/parisc/kernel/sys_parisc32.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2000-2001 Hewlett Packard Company
  * Copyright (C) 2000 John Marvin
  * Copyright (C) 2001 Matthew Wilcox
+ * Copyright (C) 2014 Helge Deller <deller@gmx.de>
  *
  * These routines maintain argument size conversion between 32bit and 64bit
  * environment. Based heavily on sys_ia32.c and sys_sparc32.c.
@@ -11,44 +12,8 @@
 
 #include <linux/compat.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/fs.h> 
-#include <linux/mm.h> 
-#include <linux/file.h> 
-#include <linux/signal.h>
-#include <linux/resource.h>
-#include <linux/times.h>
-#include <linux/time.h>
-#include <linux/smp.h>
-#include <linux/sem.h>
-#include <linux/shm.h>
-#include <linux/slab.h>
-#include <linux/uio.h>
-#include <linux/ncp_fs.h>
-#include <linux/poll.h>
-#include <linux/personality.h>
-#include <linux/stat.h>
-#include <linux/highmem.h>
-#include <linux/highuid.h>
-#include <linux/mman.h>
-#include <linux/binfmts.h>
-#include <linux/namei.h>
-#include <linux/vfs.h>
-#include <linux/ptrace.h>
-#include <linux/swap.h>
 #include <linux/syscalls.h>
 
-#include <asm/types.h>
-#include <asm/uaccess.h>
-#include <asm/mmu_context.h>
-
-#undef DEBUG
-
-#ifdef DEBUG
-#define DBG(x)	printk x
-#else
-#define DBG(x)
-#endif
 
 asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23,
 	int r22, int r21, int r20)
@@ -57,3 +22,12 @@ asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23,
     	current->comm, current->pid, r20);
     return -ENOSYS;
 }
+
+asmlinkage long sys32_fanotify_mark(compat_int_t fanotify_fd, compat_uint_t flags,
+	compat_uint_t mask0, compat_uint_t mask1, compat_int_t dfd,
+	const char  __user * pathname)
+{
+	return sys_fanotify_mark(fanotify_fd, flags,
+			((__u64)mask1 << 32) | mask0,
+			 dfd, pathname);
+}
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index c5fa7a697fb..84c5d3a58fa 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -418,7 +418,7 @@
 	ENTRY_SAME(accept4)		/* 320 */
 	ENTRY_SAME(prlimit64)
 	ENTRY_SAME(fanotify_init)
-	ENTRY_COMP(fanotify_mark)
+	ENTRY_DIFF(fanotify_mark)
 	ENTRY_COMP(clock_adjtime)
 	ENTRY_SAME(name_to_handle_at)	/* 325 */
 	ENTRY_COMP(open_by_handle_at)
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index ae085ad0fba..0bef864264c 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -728,7 +728,6 @@ static void __init pagetable_init(void)
 #endif
 
 	empty_zero_page = alloc_bootmem_pages(PAGE_SIZE);
-	memset(empty_zero_page, 0, PAGE_SIZE);
 }
 
 static void __init gateway_init(void)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index e0998997943..80b94b0add1 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -145,6 +145,7 @@ config PPC
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK
 	select ARCH_USE_CMPXCHG_LOCKREF if PPC64
 	select HAVE_ARCH_AUDITSYSCALL
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
@@ -414,7 +415,7 @@ config KEXEC
 config CRASH_DUMP
 	bool "Build a kdump crash kernel"
 	depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP)
-	select RELOCATABLE if PPC64 || 44x || FSL_BOOKE
+	select RELOCATABLE if (PPC64 && !COMPILE_TEST) || 44x || FSL_BOOKE
 	help
 	  Build a kernel suitable for use as a kdump capture kernel.
 	  The same kernel binary can be used as production kernel and dump
@@ -453,6 +454,14 @@ config NODES_SHIFT
 	default "4"
 	depends on NEED_MULTIPLE_NODES
 
+config USE_PERCPU_NUMA_NODE_ID
+	def_bool y
+	depends on NUMA
+
+config HAVE_MEMORYLESS_NODES
+	def_bool y
+	depends on NUMA
+
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
 	depends on PPC64
@@ -1009,6 +1018,7 @@ endmenu
 if PPC64
 config RELOCATABLE
 	bool "Build a relocatable kernel"
+	depends on !COMPILE_TEST
 	select NONSTATIC_KERNEL
 	help
 	  This builds a kernel image that is capable of running anywhere
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 21c9f304e96..35d16bd2760 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -235,11 +235,6 @@ config PPC_EARLY_DEBUG_USBGECKO
 	  Select this to enable early debugging for Nintendo GameCube/Wii
 	  consoles via an external USB Gecko adapter.
 
-config PPC_EARLY_DEBUG_WSP
-	bool "Early debugging via WSP's internal UART"
-	depends on PPC_WSP
-	select PPC_UDBG_16550
-
 config PPC_EARLY_DEBUG_PS3GELIC
 	bool "Early debugging through the PS3 Ethernet port"
 	depends on PPC_PS3
@@ -308,7 +303,6 @@ config PPC_EARLY_DEBUG_OPAL_VTERMNO
 	  This correspond to which /dev/hvcN you want to use for early
 	  debug.
 
-	  On OPAL v1 (takeover) this should always be 0
 	  On OPAL v2, this will be 0 for network console and 1 or 2 for
 	  the machine built-in serial ports.
 
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index ce4c68a4a82..5687e299d0a 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -113,8 +113,13 @@ else
 endif
 endif
 
-CFLAGS-$(CONFIG_PPC64)	:= -mtraceback=no -mcall-aixdesc
-CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
+CFLAGS-$(CONFIG_PPC64)	:= -mtraceback=no
+ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
+CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2,-mcall-aixdesc)
+AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2)
+else
+CFLAGS-$(CONFIG_PPC64)	+= -mcall-aixdesc
+endif
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,-mminimal-toc)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
 CFLAGS-$(CONFIG_PPC32)	:= -ffixed-r2 $(MULTIPLEWORD)
@@ -153,7 +158,7 @@ CFLAGS-$(CONFIG_TUNE_CELL) += $(call cc-option,-mtune=cell)
 asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
 
 KBUILD_CPPFLAGS	+= -Iarch/$(ARCH) $(asinstr)
-KBUILD_AFLAGS	+= -Iarch/$(ARCH)
+KBUILD_AFLAGS	+= -Iarch/$(ARCH) $(AFLAGS-y)
 KBUILD_CFLAGS	+= -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y)
 CPP		= $(CC) -E $(KBUILD_CFLAGS)
 
@@ -161,6 +166,11 @@ CHECKFLAGS	+= -m$(CONFIG_WORD_SIZE) -D__powerpc__ -D__powerpc$(CONFIG_WORD_SIZE)
 
 KBUILD_LDFLAGS_MODULE += arch/powerpc/lib/crtsavres.o
 
+ifeq ($(CONFIG_476FPE_ERR46),y)
+	KBUILD_LDFLAGS_MODULE += --ppc476-workaround \
+		-T $(srctree)/arch/powerpc/platforms/44x/ppc476_modules.lds
+endif
+
 # No AltiVec or VSX instructions when building kernel
 KBUILD_CFLAGS += $(call cc-option,-mno-altivec)
 KBUILD_CFLAGS += $(call cc-option,-mno-vsx)
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index a1f8c7f1ec6..ccc25eddbcb 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -22,8 +22,14 @@ all: $(obj)/zImage
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		 -fno-strict-aliasing -Os -msoft-float -pipe \
 		 -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
-		 -isystem $(shell $(CROSS32CC) -print-file-name=include) \
-		 -mbig-endian
+		 -isystem $(shell $(CROSS32CC) -print-file-name=include)
+ifdef CONFIG_PPC64_BOOT_WRAPPER
+BOOTCFLAGS	+= -m64
+endif
+ifdef CONFIG_CPU_BIG_ENDIAN
+BOOTCFLAGS	+= -mbig-endian
+endif
+
 BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc
 
 ifdef CONFIG_DEBUG_INFO
@@ -47,6 +53,7 @@ $(obj)/cuboot-acadia.o: BOOTCFLAGS += -mcpu=405
 $(obj)/treeboot-walnut.o: BOOTCFLAGS += -mcpu=405
 $(obj)/treeboot-iss4xx.o: BOOTCFLAGS += -mcpu=405
 $(obj)/treeboot-currituck.o: BOOTCFLAGS += -mcpu=405
+$(obj)/treeboot-akebono.o: BOOTCFLAGS += -mcpu=405
 $(obj)/virtex405-head.o: BOOTAFLAGS += -mcpu=405
 
 
@@ -86,6 +93,7 @@ src-plat-$(CONFIG_44x) += treeboot-ebony.c cuboot-ebony.c treeboot-bamboo.c \
 				cuboot-taishan.c cuboot-katmai.c \
 				cuboot-warp.c cuboot-yosemite.c \
 				treeboot-iss4xx.c treeboot-currituck.c \
+				treeboot-akebono.c \
 				simpleboot.c fixed-head.S virtex.c
 src-plat-$(CONFIG_8xx) += cuboot-8xx.c fixed-head.S ep88xc.c redboot-8xx.c
 src-plat-$(CONFIG_PPC_MPC52xx) += cuboot-52xx.c
@@ -99,6 +107,11 @@ src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \
 src-plat-$(CONFIG_AMIGAONE) += cuboot-amigaone.c
 src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c
 src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c epapr-wrapper.c
+src-plat-$(CONFIG_PPC_PSERIES) += pseries-head.S
+src-plat-$(CONFIG_PPC_POWERNV) += pseries-head.S
+src-plat-$(CONFIG_PPC_IBM_CELL_BLADE) += pseries-head.S
+src-plat-$(CONFIG_PPC_CELLEB) += pseries-head.S
+src-plat-$(CONFIG_PPC_CELL_QPACE) += pseries-head.S
 
 src-wlib := $(sort $(src-wlib-y))
 src-plat := $(sort $(src-plat-y))
@@ -137,7 +150,11 @@ $(addprefix $(obj)/,$(libfdt) $(libfdtheader)): $(obj)/%: $(srctree)/scripts/dtc
 $(obj)/empty.c:
 	@touch $@
 
-$(obj)/zImage.lds $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds: $(obj)/%: $(srctree)/$(src)/%.S
+$(obj)/zImage.lds: $(obj)/%: $(srctree)/$(src)/%.S
+	$(CROSS32CC) $(cpp_flags) -E -Wp,-MD,$(depfile) -P -Upowerpc \
+		-D__ASSEMBLY__ -DLINKER_SCRIPT -o $@ $<
+
+$(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds : $(obj)/%: $(srctree)/$(src)/%.S
 	@cp $< $@
 
 clean-files := $(zlib) $(zlibheader) $(zliblinuxheader) \
@@ -235,6 +252,7 @@ image-$(CONFIG_YOSEMITE)		+= cuImage.yosemite
 image-$(CONFIG_ISS4xx)			+= treeImage.iss4xx \
 					   treeImage.iss4xx-mpic
 image-$(CONFIG_CURRITUCK)			+= treeImage.currituck
+image-$(CONFIG_AKEBONO)			+= treeImage.akebono
 
 # Board ports in arch/powerpc/platform/8xx/Kconfig
 image-$(CONFIG_MPC86XADS)		+= cuImage.mpc866ads
@@ -315,8 +333,8 @@ $(addprefix $(obj)/, $(initrd-y)): $(obj)/ramdisk.image.gz
 $(obj)/zImage.initrd.%: vmlinux $(wrapperbits)
 	$(call if_changed,wrap,$*,,,$(obj)/ramdisk.image.gz)
 
-$(obj)/zImage.%: vmlinux $(wrapperbits)
-	$(call if_changed,wrap,$*)
+$(addprefix $(obj)/, $(sort $(filter zImage.%, $(image-y)))): vmlinux $(wrapperbits)
+	$(call if_changed,wrap,$(subst $(obj)/zImage.,,$@))
 
 # dtbImage% - a dtbImage is a zImage with an embedded device tree blob
 $(obj)/dtbImage.initrd.%: vmlinux $(wrapperbits) $(obj)/%.dtb
diff --git a/arch/powerpc/boot/addnote.c b/arch/powerpc/boot/addnote.c
index 349b5530d2c..9d9f6f334d3 100644
--- a/arch/powerpc/boot/addnote.c
+++ b/arch/powerpc/boot/addnote.c
@@ -6,6 +6,8 @@
  *
  * Copyright 2000 Paul Mackerras.
  *
+ * Adapted for 64 bit little endian images by Andrew Tauferner.
+ *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
  * as published by the Free Software Foundation; either version
@@ -55,36 +57,61 @@ unsigned int rpanote[N_RPA_DESCR] = {
 
 #define ROUNDUP(len)	(((len) + 3) & ~3)
 
-unsigned char buf[512];
+unsigned char buf[1024];
+#define ELFDATA2LSB     1
+#define ELFDATA2MSB     2
+static int e_data = ELFDATA2MSB;
+#define ELFCLASS32      1
+#define ELFCLASS64      2
+static int e_class = ELFCLASS32;
 
 #define GET_16BE(off)	((buf[off] << 8) + (buf[(off)+1]))
-#define GET_32BE(off)	((GET_16BE(off) << 16) + GET_16BE((off)+2))
-
-#define PUT_16BE(off, v)	(buf[off] = ((v) >> 8) & 0xff, \
-				 buf[(off) + 1] = (v) & 0xff)
-#define PUT_32BE(off, v)	(PUT_16BE((off), (v) >> 16), \
-				 PUT_16BE((off) + 2, (v)))
+#define GET_32BE(off)	((GET_16BE(off) << 16U) + GET_16BE((off)+2U))
+#define GET_64BE(off)	((((unsigned long long)GET_32BE(off)) << 32ULL) + \
+			((unsigned long long)GET_32BE((off)+4ULL)))
+#define PUT_16BE(off, v)(buf[off] = ((v) >> 8) & 0xff, \
+			 buf[(off) + 1] = (v) & 0xff)
+#define PUT_32BE(off, v)(PUT_16BE((off), (v) >> 16L), PUT_16BE((off) + 2, (v)))
+#define PUT_64BE(off, v)((PUT_32BE((off), (v) >> 32L), \
+			  PUT_32BE((off) + 4, (v))))
+
+#define GET_16LE(off)	((buf[off]) + (buf[(off)+1] << 8))
+#define GET_32LE(off)	(GET_16LE(off) + (GET_16LE((off)+2U) << 16U))
+#define GET_64LE(off)	((unsigned long long)GET_32LE(off) + \
+			(((unsigned long long)GET_32LE((off)+4ULL)) << 32ULL))
+#define PUT_16LE(off, v) (buf[off] = (v) & 0xff, \
+			  buf[(off) + 1] = ((v) >> 8) & 0xff)
+#define PUT_32LE(off, v) (PUT_16LE((off), (v)), PUT_16LE((off) + 2, (v) >> 16L))
+#define PUT_64LE(off, v) (PUT_32LE((off), (v)), PUT_32LE((off) + 4, (v) >> 32L))
+
+#define GET_16(off)	(e_data == ELFDATA2MSB ? GET_16BE(off) : GET_16LE(off))
+#define GET_32(off)	(e_data == ELFDATA2MSB ? GET_32BE(off) : GET_32LE(off))
+#define GET_64(off)	(e_data == ELFDATA2MSB ? GET_64BE(off) : GET_64LE(off))
+#define PUT_16(off, v)	(e_data == ELFDATA2MSB ? PUT_16BE(off, v) : \
+			 PUT_16LE(off, v))
+#define PUT_32(off, v)  (e_data == ELFDATA2MSB ? PUT_32BE(off, v) : \
+			 PUT_32LE(off, v))
+#define PUT_64(off, v)  (e_data == ELFDATA2MSB ? PUT_64BE(off, v) : \
+			 PUT_64LE(off, v))
 
 /* Structure of an ELF file */
 #define E_IDENT		0	/* ELF header */
-#define	E_PHOFF		28
-#define E_PHENTSIZE	42
-#define E_PHNUM		44
-#define E_HSIZE		52	/* size of ELF header */
+#define	E_PHOFF		(e_class == ELFCLASS32 ? 28 : 32)
+#define E_PHENTSIZE	(e_class == ELFCLASS32 ? 42 : 54)
+#define E_PHNUM		(e_class == ELFCLASS32 ? 44 : 56)
+#define E_HSIZE		(e_class == ELFCLASS32 ? 52 : 64)
 
 #define EI_MAGIC	0	/* offsets in E_IDENT area */
 #define EI_CLASS	4
 #define EI_DATA		5
 
 #define PH_TYPE		0	/* ELF program header */
-#define PH_OFFSET	4
-#define PH_FILESZ	16
-#define PH_HSIZE	32	/* size of program header */
+#define PH_OFFSET	(e_class == ELFCLASS32 ? 4 : 8)
+#define PH_FILESZ	(e_class == ELFCLASS32 ? 16 : 32)
+#define PH_HSIZE	(e_class == ELFCLASS32 ? 32 : 56)
 
 #define PT_NOTE		4	/* Program header type = note */
 
-#define ELFCLASS32	1
-#define ELFDATA2MSB	2
 
 unsigned char elf_magic[4] = { 0x7f, 'E', 'L', 'F' };
 
@@ -92,8 +119,8 @@ int
 main(int ac, char **av)
 {
 	int fd, n, i;
-	int ph, ps, np;
-	int nnote, nnote2, ns;
+	unsigned long ph, ps, np;
+	long nnote, nnote2, ns;
 
 	if (ac != 2) {
 		fprintf(stderr, "Usage: %s elf-file\n", av[0]);
@@ -114,26 +141,27 @@ main(int ac, char **av)
 		exit(1);
 	}
 
-	if (n < E_HSIZE || memcmp(&buf[E_IDENT+EI_MAGIC], elf_magic, 4) != 0)
+	if (memcmp(&buf[E_IDENT+EI_MAGIC], elf_magic, 4) != 0)
+		goto notelf;
+	e_class = buf[E_IDENT+EI_CLASS];
+	if (e_class != ELFCLASS32 && e_class != ELFCLASS64)
+		goto notelf;
+	e_data = buf[E_IDENT+EI_DATA];
+	if (e_data != ELFDATA2MSB && e_data != ELFDATA2LSB)
+		goto notelf;
+	if (n < E_HSIZE)
 		goto notelf;
 
-	if (buf[E_IDENT+EI_CLASS] != ELFCLASS32
-	    || buf[E_IDENT+EI_DATA] != ELFDATA2MSB) {
-		fprintf(stderr, "%s is not a big-endian 32-bit ELF image\n",
-			av[1]);
-		exit(1);
-	}
-
-	ph = GET_32BE(E_PHOFF);
-	ps = GET_16BE(E_PHENTSIZE);
-	np = GET_16BE(E_PHNUM);
+	ph = (e_class == ELFCLASS32 ? GET_32(E_PHOFF) : GET_64(E_PHOFF));
+	ps = GET_16(E_PHENTSIZE);
+	np = GET_16(E_PHNUM);
 	if (ph < E_HSIZE || ps < PH_HSIZE || np < 1)
 		goto notelf;
 	if (ph + (np + 2) * ps + nnote + nnote2 > n)
 		goto nospace;
 
 	for (i = 0; i < np; ++i) {
-		if (GET_32BE(ph + PH_TYPE) == PT_NOTE) {
+		if (GET_32(ph + PH_TYPE) == PT_NOTE) {
 			fprintf(stderr, "%s already has a note entry\n",
 				av[1]);
 			exit(0);
@@ -148,15 +176,22 @@ main(int ac, char **av)
 
 	/* fill in the program header entry */
 	ns = ph + 2 * ps;
-	PUT_32BE(ph + PH_TYPE, PT_NOTE);
-	PUT_32BE(ph + PH_OFFSET, ns);
-	PUT_32BE(ph + PH_FILESZ, nnote);
+	PUT_32(ph + PH_TYPE, PT_NOTE);
+	if (e_class == ELFCLASS32)
+		PUT_32(ph + PH_OFFSET, ns);
+	else
+		PUT_64(ph + PH_OFFSET, ns);
+
+	if (e_class == ELFCLASS32)
+		PUT_32(ph + PH_FILESZ, nnote);
+	else
+		PUT_64(ph + PH_FILESZ, nnote);
 
 	/* fill in the note area we point to */
 	/* XXX we should probably make this a proper section */
-	PUT_32BE(ns, strlen(arch) + 1);
-	PUT_32BE(ns + 4, N_DESCR * 4);
-	PUT_32BE(ns + 8, 0x1275);
+	PUT_32(ns, strlen(arch) + 1);
+	PUT_32(ns + 4, N_DESCR * 4);
+	PUT_32(ns + 8, 0x1275);
 	strcpy((char *) &buf[ns + 12], arch);
 	ns += 12 + strlen(arch) + 1;
 	for (i = 0; i < N_DESCR; ++i, ns += 4)
@@ -164,21 +199,28 @@ main(int ac, char **av)
 
 	/* fill in the second program header entry and the RPA note area */
 	ph += ps;
-	PUT_32BE(ph + PH_TYPE, PT_NOTE);
-	PUT_32BE(ph + PH_OFFSET, ns);
-	PUT_32BE(ph + PH_FILESZ, nnote2);
+	PUT_32(ph + PH_TYPE, PT_NOTE);
+	if (e_class == ELFCLASS32)
+		PUT_32(ph + PH_OFFSET, ns);
+	else
+		PUT_64(ph + PH_OFFSET, ns);
+
+	if (e_class == ELFCLASS32)
+		PUT_32(ph + PH_FILESZ, nnote);
+	else
+		PUT_64(ph + PH_FILESZ, nnote2);
 
 	/* fill in the note area we point to */
-	PUT_32BE(ns, strlen(rpaname) + 1);
-	PUT_32BE(ns + 4, sizeof(rpanote));
-	PUT_32BE(ns + 8, 0x12759999);
+	PUT_32(ns, strlen(rpaname) + 1);
+	PUT_32(ns + 4, sizeof(rpanote));
+	PUT_32(ns + 8, 0x12759999);
 	strcpy((char *) &buf[ns + 12], rpaname);
 	ns += 12 + ROUNDUP(strlen(rpaname) + 1);
 	for (i = 0; i < N_RPA_DESCR; ++i, ns += 4)
 		PUT_32BE(ns, rpanote[i]);
 
 	/* Update the number of program headers */
-	PUT_16BE(E_PHNUM, np + 2);
+	PUT_16(E_PHNUM, np + 2);
 
 	/* write back */
 	lseek(fd, (long) 0, SEEK_SET);
diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S
index 0f7428a37ef..14de4f8778a 100644
--- a/arch/powerpc/boot/crt0.S
+++ b/arch/powerpc/boot/crt0.S
@@ -1,17 +1,20 @@
 /*
  * Copyright (C) Paul Mackerras 1997.
  *
+ * Adapted for 64 bit LE PowerPC by Andrew Tauferner
+ *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  *
- * NOTE: this code runs in 32 bit mode, is position-independent,
- * and is packaged as ELF32.
  */
 
 #include "ppc_asm.h"
 
+RELA = 7
+RELACOUNT = 0x6ffffff9
+
 	.text
 	/* A procedure descriptor used when booting this as a COFF file.
 	 * When making COFF, this comes first in the link and we're
@@ -21,6 +24,20 @@
 _zimage_start_opd:
 	.long	0x500000, 0, 0, 0
 
+#ifdef __powerpc64__
+.balign 8
+p_start:	.llong	_start
+p_etext:	.llong	_etext
+p_bss_start:	.llong	__bss_start
+p_end:		.llong	_end
+
+p_toc:		.llong	__toc_start + 0x8000 - p_base
+p_dyn:		.llong	__dynamic_start - p_base
+p_rela:		.llong	__rela_dyn_start - p_base
+p_prom:		.llong	0
+	.weak	_platform_stack_top
+p_pstack:	.llong	_platform_stack_top
+#else
 p_start:	.long	_start
 p_etext:	.long	_etext
 p_bss_start:	.long	__bss_start
@@ -28,6 +45,7 @@ p_end:		.long	_end
 
 	.weak	_platform_stack_top
 p_pstack:	.long	_platform_stack_top
+#endif
 
 	.weak	_zimage_start
 	.globl	_zimage_start
@@ -38,6 +56,7 @@ _zimage_start_lib:
 	   and the address where we're running. */
 	bl	.+4
 p_base:	mflr	r10		/* r10 now points to runtime addr of p_base */
+#ifndef __powerpc64__
 	/* grab the link address of the dynamic section in r11 */
 	addis	r11,r10,(_GLOBAL_OFFSET_TABLE_-p_base)@ha
 	lwz	r11,(_GLOBAL_OFFSET_TABLE_-p_base)@l(r11)
@@ -51,8 +70,6 @@ p_base:	mflr	r10		/* r10 now points to runtime addr of p_base */
 
 	/* The dynamic section contains a series of tagged entries.
 	 * We need the RELA and RELACOUNT entries. */
-RELA = 7
-RELACOUNT = 0x6ffffff9
 	li	r9,0
 	li	r0,0
 9:	lwz	r8,0(r12)	/* get tag */
@@ -120,9 +137,164 @@ RELACOUNT = 0x6ffffff9
 	li	r0,0
 	stwu	r0,-16(r1)	/* establish a stack frame */
 6:
+#else /* __powerpc64__ */
+	/* Save the prom pointer at p_prom. */
+	std	r5,(p_prom-p_base)(r10)
+
+	/* Set r2 to the TOC. */
+	ld	r2,(p_toc-p_base)(r10)
+	add	r2,r2,r10
+
+	/* Grab the link address of the dynamic section in r11. */
+	ld	r11,-32768(r2)
+	cmpwi	r11,0
+	beq	3f              /* if not linked -pie then no dynamic section */
+
+	ld	r11,(p_dyn-p_base)(r10)
+	add	r11,r11,r10
+	ld	r9,(p_rela-p_base)(r10)
+	add	r9,r9,r10
 
+	li	r7,0
+	li	r8,0
+9:	ld	r6,0(r11)       /* get tag */
+	cmpdi	r6,0
+	beq	12f              /* end of list */
+	cmpdi	r6,RELA
+	bne	10f
+	ld	r7,8(r11)       /* get RELA pointer in r7 */
+	b	11f
+10:	addis	r6,r6,(-RELACOUNT)@ha
+	cmpdi	r6,RELACOUNT@l
+	bne	11f
+	ld	r8,8(r11)       /* get RELACOUNT value in r8 */
+11:	addi	r11,r11,16
+	b	9b
+12:
+	cmpdi	r7,0            /* check we have both RELA and RELACOUNT */
+	cmpdi	cr1,r8,0
+	beq	3f
+	beq	cr1,3f
+
+	/* Calcuate the runtime offset. */
+	subf	r7,r7,r9
+
+	/* Run through the list of relocations and process the
+	 * R_PPC64_RELATIVE ones. */
+	mtctr	r8
+13:	ld	r0,8(r9)        /* ELF64_R_TYPE(reloc->r_info) */
+	cmpdi	r0,22           /* R_PPC64_RELATIVE */
+	bne	3f
+	ld	r6,0(r9)        /* reloc->r_offset */
+	ld	r0,16(r9)       /* reloc->r_addend */
+	add	r0,r0,r7
+	stdx	r0,r7,r6
+	addi	r9,r9,24
+	bdnz	13b
+
+	/* Do a cache flush for our text, in case the loader didn't */
+3:	ld	r9,p_start-p_base(r10)	/* note: these are relocated now */
+	ld	r8,p_etext-p_base(r10)
+4:	dcbf	r0,r9
+	icbi	r0,r9
+	addi	r9,r9,0x20
+	cmpld	cr0,r9,r8
+	blt	4b
+	sync
+	isync
+
+	/* Clear the BSS */
+	ld	r9,p_bss_start-p_base(r10)
+	ld	r8,p_end-p_base(r10)
+	li	r0,0
+5:	std	r0,0(r9)
+	addi	r9,r9,8
+	cmpld	cr0,r9,r8
+	blt	5b
+
+	/* Possibly set up a custom stack */
+	ld	r8,p_pstack-p_base(r10)
+	cmpdi	r8,0
+	beq	6f
+	ld	r1,0(r8)
+	li	r0,0
+	stdu	r0,-16(r1)	/* establish a stack frame */
+6:
+#endif  /* __powerpc64__ */
 	/* Call platform_init() */
 	bl	platform_init
 
 	/* Call start */
 	b	start
+
+#ifdef __powerpc64__
+
+#define PROM_FRAME_SIZE 512
+#define SAVE_GPR(n, base)       std     n,8*(n)(base)
+#define REST_GPR(n, base)       ld      n,8*(n)(base)
+#define SAVE_2GPRS(n, base)     SAVE_GPR(n, base); SAVE_GPR(n+1, base)
+#define SAVE_4GPRS(n, base)     SAVE_2GPRS(n, base); SAVE_2GPRS(n+2, base)
+#define SAVE_8GPRS(n, base)     SAVE_4GPRS(n, base); SAVE_4GPRS(n+4, base)
+#define SAVE_10GPRS(n, base)    SAVE_8GPRS(n, base); SAVE_2GPRS(n+8, base)
+#define REST_2GPRS(n, base)     REST_GPR(n, base); REST_GPR(n+1, base)
+#define REST_4GPRS(n, base)     REST_2GPRS(n, base); REST_2GPRS(n+2, base)
+#define REST_8GPRS(n, base)     REST_4GPRS(n, base); REST_4GPRS(n+4, base)
+#define REST_10GPRS(n, base)    REST_8GPRS(n, base); REST_2GPRS(n+8, base)
+
+/* prom handles the jump into and return from firmware.  The prom args pointer
+   is loaded in r3. */
+.globl prom
+prom:
+	mflr	r0
+	std	r0,16(r1)
+	stdu	r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */
+
+	SAVE_GPR(2, r1)
+	SAVE_GPR(13, r1)
+	SAVE_8GPRS(14, r1)
+	SAVE_10GPRS(22, r1)
+	mfcr    r10
+	std     r10,8*32(r1)
+	mfmsr   r10
+	std     r10,8*33(r1)
+
+	/* remove MSR_LE from msr but keep MSR_SF */
+	mfmsr	r10
+	rldicr	r10,r10,0,62
+	mtsrr1	r10
+
+	/* Load FW address, set LR to label 1, and jump to FW */
+	bl	0f
+0:	mflr	r10
+	addi	r11,r10,(1f-0b)
+	mtlr	r11
+
+	ld	r10,(p_prom-0b)(r10)
+	mtsrr0	r10
+
+	rfid
+
+1:	/* Return from OF */
+	FIXUP_ENDIAN
+
+	/* Restore registers and return. */
+	rldicl  r1,r1,0,32
+
+	/* Restore the MSR (back to 64 bits) */
+	ld      r10,8*(33)(r1)
+	mtmsr	r10
+	isync
+
+	/* Restore other registers */
+	REST_GPR(2, r1)
+	REST_GPR(13, r1)
+	REST_8GPRS(14, r1)
+	REST_10GPRS(22, r1)
+	ld      r10,8*32(r1)
+	mtcr	r10
+
+	addi    r1,r1,PROM_FRAME_SIZE
+	ld      r0,16(r1)
+	mtlr    r0
+	blr
+#endif
diff --git a/arch/powerpc/boot/dcr.h b/arch/powerpc/boot/dcr.h
index cc73f7a95e2..bf8f4ede192 100644
--- a/arch/powerpc/boot/dcr.h
+++ b/arch/powerpc/boot/dcr.h
@@ -15,6 +15,10 @@
 		asm volatile("mfdcrx %0,%1" : "=r"(rval) : "r"(rn)); \
 		rval; \
 	})
+#define mtdcrx(rn, val) \
+	({	\
+		asm volatile("mtdcrx %0,%1" : : "r"(rn), "r" (val)); \
+	})
 
 /* 440GP/440GX SDRAM controller DCRs */
 #define DCRN_SDRAM0_CFGADDR				0x010
diff --git a/arch/powerpc/boot/dts/akebono.dts b/arch/powerpc/boot/dts/akebono.dts
new file mode 100644
index 00000000000..f92ecfed3d2
--- /dev/null
+++ b/arch/powerpc/boot/dts/akebono.dts
@@ -0,0 +1,415 @@
+/*
+ * Device Tree Source for IBM Embedded PPC 476 Platform
+ *
+ * Copyright © 2013 Tony Breeds IBM Corporation
+ * Copyright © 2013 Alistair Popple IBM Corporation
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without
+ * any warranty of any kind, whether express or implied.
+ */
+
+/dts-v1/;
+
+/memreserve/ 0x01f00000 0x00100000;	// spin table
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	model = "ibm,akebono";
+	compatible = "ibm,akebono", "ibm,476gtr";
+	dcr-parent = <&{/cpus/cpu@0}>;
+
+	aliases {
+		serial0 = &UART0;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			model = "PowerPC,476";
+			reg = <0>;
+			clock-frequency = <1600000000>; // 1.6 GHz
+			timebase-frequency = <100000000>; // 100Mhz
+			i-cache-line-size = <32>;
+			d-cache-line-size = <32>;
+			i-cache-size = <32768>;
+			d-cache-size = <32768>;
+			dcr-controller;
+			dcr-access-method = "native";
+			status = "ok";
+		};
+		cpu@1 {
+			device_type = "cpu";
+			model = "PowerPC,476";
+			reg = <1>;
+			clock-frequency = <1600000000>; // 1.6 GHz
+			timebase-frequency = <100000000>; // 100Mhz
+			i-cache-line-size = <32>;
+			d-cache-line-size = <32>;
+			i-cache-size = <32768>;
+			d-cache-size = <32768>;
+			dcr-controller;
+			dcr-access-method = "native";
+			status = "disabled";
+			enable-method = "spin-table";
+			cpu-release-addr = <0x0 0x01f00000>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x0 0x0 0x0 0x0>; // filled in by zImage
+	};
+
+	MPIC: interrupt-controller {
+		compatible = "chrp,open-pic";
+		interrupt-controller;
+		dcr-reg = <0xffc00000 0x00040000>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		#interrupt-cells = <2>;
+		single-cpu-affinity;
+	};
+
+	plb {
+		compatible = "ibm,plb6";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+		clock-frequency = <200000000>; // 200Mhz
+
+		HSTA0: hsta@310000e0000 {
+			compatible = "ibm,476gtr-hsta-msi", "ibm,hsta-msi";
+			reg = <0x310 0x000e0000 0x0 0xf0>;
+			interrupt-parent = <&MPIC>;
+			interrupts = <108 0
+				      109 0
+				      110 0
+				      111 0
+				      112 0
+				      113 0
+				      114 0
+				      115 0
+				      116 0
+				      117 0
+				      118 0
+				      119 0
+				      120 0
+				      121 0
+				      122 0
+				      123 0>;
+		};
+
+		MAL0: mcmal {
+			compatible = "ibm,mcmal-476gtr", "ibm,mcmal2";
+			dcr-reg = <0xc0000000 0x062>;
+			num-tx-chans = <1>;
+			num-rx-chans = <1>;
+			#address-cells = <0>;
+			#size-cells = <0>;
+			interrupt-parent = <&MPIC>;
+			interrupts = <	/*TXEOB*/ 77 0x4
+					/*RXEOB*/ 78 0x4
+					/*SERR*/  76 0x4
+					/*TXDE*/  79 0x4
+					/*RXDE*/  80 0x4>;
+		};
+
+		SATA0: sata@30000010000 {
+			compatible = "ibm,476gtr-ahci";
+			reg = <0x300 0x00010000 0x0 0x10000>;
+			interrupt-parent = <&MPIC>;
+			interrupts = <93 2>;
+		};
+
+		EHCI0: ehci@30010000000 {
+			compatible = "ibm,476gtr-ehci", "generic-ehci";
+			reg = <0x300 0x10000000 0x0 0x10000>;
+			interrupt-parent = <&MPIC>;
+			interrupts = <85 2>;
+		};
+
+		SD0: sd@30000000000 {
+			compatible = "ibm,476gtr-sdhci", "generic-sdhci";
+			reg = <0x300 0x00000000 0x0 0x10000>;
+			interrupts = <91 2>;
+			interrupt-parent = <&MPIC>;
+		};
+
+		OHCI0: ohci@30010010000 {
+			compatible = "ibm,476gtr-ohci", "generic-ohci";
+			reg = <0x300 0x10010000 0x0 0x10000>;
+			interrupt-parent = <&MPIC>;
+			interrupts = <89 1>;
+			};
+
+		OHCI1: ohci@30010020000 {
+			compatible = "ibm,476gtr-ohci", "generic-ohci";
+			reg = <0x300 0x10020000 0x0 0x10000>;
+			interrupt-parent = <&MPIC>;
+			interrupts = <88 1>;
+			};
+
+		POB0: opb {
+			compatible = "ibm,opb-4xx", "ibm,opb";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			/* Wish there was a nicer way of specifying a full
+			 * 32-bit range
+			 */
+			ranges = <0x00000000 0x0000033f 0x00000000 0x80000000
+				  0x80000000 0x0000033f 0x80000000 0x80000000>;
+			clock-frequency = <100000000>;
+
+			RGMII0: emac-rgmii-wol@50004 {
+				compatible = "ibm,rgmii-wol-476gtr", "ibm,rgmii-wol";
+				reg = <0x50004 0x00000008>;
+				has-mdio;
+			};
+
+			EMAC0: ethernet@30000 {
+				device_type = "network";
+				compatible = "ibm,emac-476gtr", "ibm,emac4sync";
+				interrupt-parent = <&EMAC0>;
+				interrupts = <0x0 0x1>;
+				#interrupt-cells = <1>;
+				#address-cells = <0>;
+				#size-cells = <0>;
+				interrupt-map = </*Status*/ 0x0 &MPIC 81 0x4
+						 /*Wake*/   0x1 &MPIC 82 0x4>;
+				reg = <0x30000 0x78>;
+
+				/* local-mac-address will normally be added by
+				 * the wrapper. If your device doesn't support
+				 * passing data to the wrapper (in the form
+				 * local-mac-addr=<hwaddr>) then you will need
+				 * to set it manually here. */
+				//local-mac-address = [000000000000];
+
+				mal-device = <&MAL0>;
+				mal-tx-channel = <0>;
+				mal-rx-channel = <0>;
+				cell-index = <0>;
+				max-frame-size = <9000>;
+				rx-fifo-size = <4096>;
+				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
+				phy-mode = "rgmii";
+				phy-map = <0x00000000>;
+				rgmii-wol-device = <&RGMII0>;
+				has-inverted-stacr-oc;
+				has-new-stacr-staopc;
+			};
+
+			UART0: serial@10000 {
+				device_type = "serial";
+				compatible = "ns16750", "ns16550";
+				reg = <0x10000 0x00000008>;
+				virtual-reg = <0xe8010000>;
+				clock-frequency = <1851851>;
+				current-speed = <38400>;
+				interrupt-parent = <&MPIC>;
+				interrupts = <39 2>;
+			};
+
+			IIC0: i2c@00000000 {
+				compatible = "ibm,iic-476gtr", "ibm,iic";
+				reg = <0x0 0x00000020>;
+				interrupt-parent = <&MPIC>;
+				interrupts = <37 2>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				rtc@68 {
+					compatible = "stm,m41t80", "m41st85";
+					reg = <0x68>;
+				};
+			};
+
+			IIC1: i2c@00000100 {
+				compatible = "ibm,iic-476gtr", "ibm,iic";
+				reg = <0x100 0x00000020>;
+				interrupt-parent = <&MPIC>;
+				interrupts = <38 2>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				avr@58 {
+					compatible = "ibm,akebono-avr";
+					reg = <0x58>;
+				};
+			};
+
+			FPGA0: fpga@ebc00000 {
+				compatible = "ibm,akebono-fpga";
+				reg = <0xebc00000 0x8>;
+			};
+		};
+
+		PCIE0: pciex@10100000000 {
+			device_type = "pci";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			compatible = "ibm,plb-pciex-476fpe", "ibm,plb-pciex";
+			primary;
+			port = <0x0>; /* port number */
+			reg = <0x00000101 0x00000000 0x0 0x10000000	       /* Config space access */
+			       0x00000100 0x00000000 0x0 0x00001000>;	/* UTL Registers space access */
+			dcr-reg = <0xc0 0x20>;
+
+//                                pci_space  < pci_addr          > < cpu_addr          > < size       >
+			ranges = <0x02000000 0x00000000 0x80000000 0x00000110 0x80000000 0x0 0x80000000
+			          0x01000000 0x0        0x0        0x00000140 0x0        0x0 0x00010000>;
+
+			/* Inbound starting at 0x0 to 0x40000000000. In order to use MSI
+			 * PCI devices must be able to write to the HSTA module.
+			 */
+			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x400 0x0>;
+
+			/* This drives busses 0 to 0xf */
+			bus-range = <0x0 0xf>;
+
+			/* Legacy interrupts (note the weird polarity, the bridge seems
+			 * to invert PCIe legacy interrupts).
+			 * We are de-swizzling here because the numbers are actually for
+			 * port of the root complex virtual P2P bridge. But I want
+			 * to avoid putting a node for it in the tree, so the numbers
+			 * below are basically de-swizzled numbers.
+			 * The real slot is on idsel 0, so the swizzling is 1:1
+			 */
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <
+				0x0 0x0 0x0 0x1 &MPIC 45 0x2 /* int A */
+				0x0 0x0 0x0 0x2 &MPIC 46 0x2 /* int B */
+				0x0 0x0 0x0 0x3 &MPIC 47 0x2 /* int C */
+				0x0 0x0 0x0 0x4 &MPIC 48 0x2 /* int D */>;
+		};
+
+		PCIE1: pciex@20100000000 {
+			device_type = "pci";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			compatible = "ibm,plb-pciex-476fpe", "ibm,plb-pciex";
+			primary;
+			port = <0x1>; /* port number */
+			reg = <0x00000201 0x00000000 0x0 0x10000000	       /* Config space access */
+			       0x00000200 0x00000000 0x0 0x00001000>;	/* UTL Registers space access */
+			dcr-reg = <0x100 0x20>;
+
+//                                pci_space  < pci_addr          > < cpu_addr          > < size       >
+			ranges = <0x02000000 0x00000000 0x80000000 0x00000210 0x80000000 0x0 0x80000000
+			          0x01000000 0x0        0x0        0x00000240 0x0        0x0 0x00010000>;
+
+			/* Inbound starting at 0x0 to 0x40000000000. In order to use MSI
+			 * PCI devices must be able to write to the HSTA module.
+			 */
+			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x400 0x0>;
+
+			/* This drives busses 0 to 0xf */
+			bus-range = <0x0 0xf>;
+
+			/* Legacy interrupts (note the weird polarity, the bridge seems
+			 * to invert PCIe legacy interrupts).
+			 * We are de-swizzling here because the numbers are actually for
+			 * port of the root complex virtual P2P bridge. But I want
+			 * to avoid putting a node for it in the tree, so the numbers
+			 * below are basically de-swizzled numbers.
+			 * The real slot is on idsel 0, so the swizzling is 1:1
+			 */
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <
+				0x0 0x0 0x0 0x1 &MPIC 53 0x2 /* int A */
+				0x0 0x0 0x0 0x2 &MPIC 54 0x2 /* int B */
+				0x0 0x0 0x0 0x3 &MPIC 55 0x2 /* int C */
+				0x0 0x0 0x0 0x4 &MPIC 56 0x2 /* int D */>;
+		};
+
+		PCIE2: pciex@18100000000 {
+			device_type = "pci";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			compatible = "ibm,plb-pciex-476fpe", "ibm,plb-pciex";
+			primary;
+			port = <0x2>; /* port number */
+			reg = <0x00000181 0x00000000 0x0 0x10000000	       /* Config space access */
+			       0x00000180 0x00000000 0x0 0x00001000>;	/* UTL Registers space access */
+			dcr-reg = <0xe0 0x20>;
+
+//                                pci_space  < pci_addr          > < cpu_addr          > < size       >
+			ranges = <0x02000000 0x00000000 0x80000000 0x00000190 0x80000000 0x0 0x80000000
+			          0x01000000 0x0        0x0        0x000001c0 0x0        0x0 0x00010000>;
+
+			/* Inbound starting at 0x0 to 0x40000000000. In order to use MSI
+			 * PCI devices must be able to write to the HSTA module.
+			 */
+			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x400 0x0>;
+
+			/* This drives busses 0 to 0xf */
+			bus-range = <0x0 0xf>;
+
+			/* Legacy interrupts (note the weird polarity, the bridge seems
+			 * to invert PCIe legacy interrupts).
+			 * We are de-swizzling here because the numbers are actually for
+			 * port of the root complex virtual P2P bridge. But I want
+			 * to avoid putting a node for it in the tree, so the numbers
+			 * below are basically de-swizzled numbers.
+			 * The real slot is on idsel 0, so the swizzling is 1:1
+			 */
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <
+				0x0 0x0 0x0 0x1 &MPIC 61 0x2 /* int A */
+				0x0 0x0 0x0 0x2 &MPIC 62 0x2 /* int B */
+				0x0 0x0 0x0 0x3 &MPIC 63 0x2 /* int C */
+				0x0 0x0 0x0 0x4 &MPIC 64 0x2 /* int D */>;
+		};
+
+		PCIE3: pciex@28100000000 {
+			device_type = "pci";
+			#interrupt-cells = <1>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			compatible = "ibm,plb-pciex-476fpe", "ibm,plb-pciex";
+			primary;
+			port = <0x3>; /* port number */
+			reg = <0x00000281 0x00000000 0x0 0x10000000	       /* Config space access */
+			       0x00000280 0x00000000 0x0 0x00001000>;	/* UTL Registers space access */
+			dcr-reg = <0x120 0x20>;
+
+//                                pci_space  < pci_addr          > < cpu_addr          > < size       >
+			ranges = <0x02000000 0x00000000 0x80000000 0x00000290 0x80000000 0x0 0x80000000
+			          0x01000000 0x0        0x0        0x000002c0 0x0        0x0 0x00010000>;
+
+			/* Inbound starting at 0x0 to 0x40000000000. In order to use MSI
+			 * PCI devices must be able to write to the HSTA module.
+			 */
+			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x400 0x0>;
+
+			/* This drives busses 0 to 0xf */
+			bus-range = <0x0 0xf>;
+
+			/* Legacy interrupts (note the weird polarity, the bridge seems
+			 * to invert PCIe legacy interrupts).
+			 * We are de-swizzling here because the numbers are actually for
+			 * port of the root complex virtual P2P bridge. But I want
+			 * to avoid putting a node for it in the tree, so the numbers
+			 * below are basically de-swizzled numbers.
+			 * The real slot is on idsel 0, so the swizzling is 1:1
+			 */
+			interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+			interrupt-map = <
+				0x0 0x0 0x0 0x1 &MPIC 69 0x2 /* int A */
+				0x0 0x0 0x0 0x2 &MPIC 70 0x2 /* int B */
+				0x0 0x0 0x0 0x3 &MPIC 71 0x2 /* int C */
+				0x0 0x0 0x0 0x4 &MPIC 72 0x2 /* int D */>;
+		};
+	};
+
+	chosen {
+		linux,stdout-path = &UART0;
+	};
+};
diff --git a/arch/powerpc/boot/dts/b4860emu.dts b/arch/powerpc/boot/dts/b4860emu.dts
index 7290021f2df..85646b4f96e 100644
--- a/arch/powerpc/boot/dts/b4860emu.dts
+++ b/arch/powerpc/boot/dts/b4860emu.dts
@@ -61,21 +61,25 @@
 			device_type = "cpu";
 			reg = <0 1>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu1: PowerPC,e6500@2 {
 			device_type = "cpu";
 			reg = <2 3>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu2: PowerPC,e6500@4 {
 			device_type = "cpu";
 			reg = <4 5>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu3: PowerPC,e6500@6 {
 			device_type = "cpu";
 			reg = <6 7>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 	};
 };
@@ -157,7 +161,7 @@
 	};
 
 	corenet-cf@18000 {
-		compatible = "fsl,b4-corenet-cf";
+		compatible = "fsl,corenet2-cf", "fsl,corenet-cf";
 		reg = <0x18000 0x1000>;
 		interrupts = <16 2 1 0>;
 		fsl,ccf-num-csdids = <32>;
@@ -167,6 +171,7 @@
 	iommu@20000 {
 		compatible = "fsl,pamu-v1.0", "fsl,pamu";
 		reg = <0x20000 0x4000>;
+		fsl,portid-mapping = <0x8000>;
 		#address-cells = <1>;
 		#size-cells = <1>;
 		interrupts = <
diff --git a/arch/powerpc/boot/dts/bsc9132qds.dts b/arch/powerpc/boot/dts/bsc9132qds.dts
new file mode 100644
index 00000000000..6cab1062bc7
--- /dev/null
+++ b/arch/powerpc/boot/dts/bsc9132qds.dts
@@ -0,0 +1,35 @@
+/*
+ * BSC9132 QDS Device Tree Source
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/include/ "fsl/bsc9132si-pre.dtsi"
+
+/ {
+	model = "fsl,bsc9132qds";
+	compatible = "fsl,bsc9132qds";
+
+	memory {
+		device_type = "memory";
+	};
+
+	ifc: ifc@ff71e000 {
+		/* NOR, NAND Flash on board */
+		ranges = <0x0 0x0 0x0 0x88000000 0x08000000
+			  0x1 0x0 0x0 0xff800000 0x00010000>;
+		reg = <0x0 0xff71e000 0x0 0x2000>;
+	};
+
+	soc: soc@ff700000 {
+		ranges = <0x0 0x0 0xff700000 0x100000>;
+	};
+};
+
+/include/ "bsc9132qds.dtsi"
+/include/ "fsl/bsc9132si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/bsc9132qds.dtsi b/arch/powerpc/boot/dts/bsc9132qds.dtsi
new file mode 100644
index 00000000000..af8e8883022
--- /dev/null
+++ b/arch/powerpc/boot/dts/bsc9132qds.dtsi
@@ -0,0 +1,101 @@
+/*
+ * BSC9132 QDS Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&ifc {
+	nor@0,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "cfi-flash";
+		reg = <0x0 0x0 0x8000000>;
+		bank-width = <2>;
+		device-width = <1>;
+	};
+
+	nand@1,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "fsl,ifc-nand";
+		reg = <0x1 0x0 0x4000>;
+	};
+};
+
+&soc {
+	spi@7000 {
+		flash@0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "spansion,s25sl12801";
+			reg = <0>;
+			spi-max-frequency = <30000000>;
+		};
+	};
+
+	i2c@3000 {
+		fpga: fpga@66 {
+			compatible = "fsl,bsc9132qds-fpga", "fsl,fpga-qixis-i2c";
+			reg = <0x66>;
+		};
+	};
+
+	usb@22000 {
+		phy_type = "ulpi";
+	};
+
+	mdio@24000 {
+		phy0: ethernet-phy@0 {
+			reg = <0x0>;
+		};
+
+		phy1: ethernet-phy@1 {
+			reg = <0x1>;
+		};
+
+		tbi0: tbi-phy@11 {
+			reg = <0x1f>;
+			device_type = "tbi-phy";
+		};
+	};
+
+	enet0: ethernet@b0000 {
+		phy-handle = <&phy0>;
+		tbi-handle = <&tbi0>;
+		phy-connection-type = "sgmii";
+	};
+
+	enet1: ethernet@b1000 {
+		phy-handle = <&phy1>;
+		tbi-handle = <&tbi0>;
+		phy-connection-type = "sgmii";
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
index 60566f9927b..d67894459ac 100644
--- a/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4420si-post.dtsi
@@ -76,10 +76,6 @@
 		compatible = "fsl,b4420-l3-cache-controller", "cache";
 	};
 
-	corenet-cf@18000 {
-		compatible = "fsl,b4420-corenet-cf";
-	};
-
 	guts: global-utilities@e0000 {
 		compatible = "fsl,b4420-device-config", "fsl,qoriq-device-config-2.0";
 	};
diff --git a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
index 2419731c2c5..338af7e39dd 100644
--- a/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4420si-pre.dtsi
@@ -66,12 +66,14 @@
 			reg = <0 1>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu1: PowerPC,e6500@2 {
 			device_type = "cpu";
 			reg = <2 3>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
index cbc354b0511..582381dba1d 100644
--- a/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4860si-post.dtsi
@@ -120,10 +120,6 @@
 		compatible = "fsl,b4860-l3-cache-controller", "cache";
 	};
 
-	corenet-cf@18000 {
-		compatible = "fsl,b4860-corenet-cf";
-	};
-
 	guts: global-utilities@e0000 {
 		compatible = "fsl,b4860-device-config", "fsl,qoriq-device-config-2.0";
 	};
diff --git a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
index 142ac862cac..1948f73fd26 100644
--- a/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4860si-pre.dtsi
@@ -66,24 +66,28 @@
 			reg = <0 1>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu1: PowerPC,e6500@2 {
 			device_type = "cpu";
 			reg = <2 3>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu2: PowerPC,e6500@4 {
 			device_type = "cpu";
 			reg = <4 5>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu3: PowerPC,e6500@6 {
 			device_type = "cpu";
 			reg = <6 7>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
index 4f6e48277c4..1a54ba71f68 100644
--- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi
@@ -158,7 +158,7 @@
 	};
 
 	corenet-cf@18000 {
-		compatible = "fsl,b4-corenet-cf";
+		compatible = "fsl,corenet2-cf", "fsl,corenet-cf";
 		reg = <0x18000 0x1000>;
 		interrupts = <16 2 1 0>;
 		fsl,ccf-num-csdids = <32>;
@@ -168,6 +168,7 @@
 	iommu@20000 {
 		compatible =  "fsl,pamu-v1.0", "fsl,pamu";
 		reg = <0x20000 0x4000>;
+		fsl,portid-mapping = <0x8000>;
 		#address-cells = <1>;
 		#size-cells = <1>;
 		interrupts = <
diff --git a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi
new file mode 100644
index 00000000000..c7230719814
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi
@@ -0,0 +1,185 @@
+/*
+ * BSC9132 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&ifc {
+	#address-cells = <2>;
+	#size-cells = <1>;
+	compatible = "fsl,ifc", "simple-bus";
+	/* FIXME: Test whether interrupts are split */
+	interrupts = <16 2 0 0 20 2 0 0>;
+};
+
+&soc {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	device_type = "soc";
+	compatible = "fsl,bsc9132-immr", "simple-bus";
+	bus-frequency = <0>;		// Filled out by uboot.
+
+	ecm-law@0 {
+		compatible = "fsl,ecm-law";
+		reg = <0x0 0x1000>;
+		fsl,num-laws = <12>;
+	};
+
+	ecm@1000 {
+		compatible = "fsl,bsc9132-ecm", "fsl,ecm";
+		reg = <0x1000 0x1000>;
+		interrupts = <16 2 0 0>;
+	};
+
+	memory-controller@2000 {
+		compatible = "fsl,bsc9132-memory-controller";
+		reg = <0x2000 0x1000>;
+		interrupts = <16 2 1 8>;
+	};
+
+/include/ "pq3-i2c-0.dtsi"
+	i2c@3000 {
+		interrupts = <17 2 0 0>;
+	};
+
+/include/ "pq3-i2c-1.dtsi"
+	i2c@3100 {
+		interrupts = <17 2 0 0>;
+	};
+
+/include/ "pq3-duart-0.dtsi"
+	serial0: serial@4500 {
+		interrupts = <18 2 0 0>;
+	};
+
+	serial1: serial@4600 {
+		interrupts = <18 2 0 0 >;
+	};
+/include/ "pq3-espi-0.dtsi"
+	spi0: spi@7000 {
+		fsl,espi-num-chipselects = <1>;
+		interrupts = <22 0x2 0 0>;
+	};
+
+/include/ "pq3-gpio-0.dtsi"
+	gpio-controller@f000 {
+		interrupts = <19 0x2 0 0>;
+		};
+
+	L2: l2-cache-controller@20000 {
+		compatible = "fsl,bsc9132-l2-cache-controller";
+		reg = <0x20000 0x1000>;
+		cache-line-size = <32>;	// 32 bytes
+		cache-size = <0x40000>; // L2,256K
+		interrupts = <16 2 1 0>;
+	};
+
+/include/ "pq3-dma-0.dtsi"
+
+dma@21300 {
+
+	dma-channel@0 {
+		interrupts = <62 2 0 0>;
+	};
+
+	dma-channel@80 {
+		interrupts = <63 2 0 0>;
+	};
+
+	dma-channel@100 {
+		interrupts = <64 2 0 0>;
+	};
+
+	dma-channel@180 {
+		interrupts = <65 2 0 0>;
+	};
+};
+
+/include/ "pq3-usb2-dr-0.dtsi"
+usb@22000 {
+	compatible = "fsl-usb2-dr","fsl-usb2-dr-v2.2";
+	interrupts = <40 0x2 0 0>;
+};
+
+/include/ "pq3-esdhc-0.dtsi"
+	sdhc@2e000 {
+		fsl,sdhci-auto-cmd12;
+		interrupts = <41 0x2 0 0>;
+	};
+
+/include/ "pq3-sec4.4-0.dtsi"
+crypto@30000 {
+	interrupts	 = <57 2 0 0>;
+
+	sec_jr0: jr@1000 {
+		interrupts	 = <58 2 0 0>;
+	};
+
+	sec_jr1: jr@2000 {
+		interrupts	 = <59 2 0 0>;
+	};
+
+	sec_jr2: jr@3000 {
+		interrupts	 = <60 2 0 0>;
+	};
+
+	sec_jr3: jr@4000 {
+		interrupts	 = <61 2 0 0>;
+	};
+};
+
+/include/ "pq3-mpic.dtsi"
+/include/ "pq3-mpic-timer-B.dtsi"
+
+/include/ "pq3-etsec2-0.dtsi"
+enet0: ethernet@b0000 {
+	queue-group@b0000 {
+		fsl,rx-bit-map = <0xff>;
+		fsl,tx-bit-map = <0xff>;
+		interrupts = <26 2 0 0 27 2 0 0 28 2 0 0>;
+	};
+};
+
+/include/ "pq3-etsec2-1.dtsi"
+enet1: ethernet@b1000 {
+	queue-group@b1000 {
+		fsl,rx-bit-map = <0xff>;
+		fsl,tx-bit-map = <0xff>;
+		interrupts = <33 2 0 0 34 2 0 0 35 2 0 0>;
+	};
+};
+
+global-utilities@e0000 {
+		compatible = "fsl,bsc9132-guts";
+		reg = <0xe0000 0x1000>;
+		fsl,has-rstcr;
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi b/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi
new file mode 100644
index 00000000000..301a9dba579
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/bsc9132si-pre.dtsi
@@ -0,0 +1,66 @@
+/*
+ * BSC9132 Silicon/SoC Device Tree Source (pre include)
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/include/ "e500v2_power_isa.dtsi"
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	aliases {
+		serial0 = &serial0;
+		ethernet0 = &enet0;
+		ethernet1 = &enet1;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: PowerPC,e500v2@0 {
+			device_type = "cpu";
+			reg = <0x0>;
+			next-level-cache = <&L2>;
+		};
+
+		cpu1: PowerPC,e500v2@1 {
+			device_type = "cpu";
+			reg = <0x1>;
+			next-level-cache = <&L2>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
index e2987a33083..5290df83ff3 100644
--- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
@@ -246,7 +246,7 @@
 	};
 
 	corenet-cf@18000 {
-		compatible = "fsl,corenet-cf";
+		compatible = "fsl,corenet1-cf", "fsl,corenet-cf";
 		reg = <0x18000 0x1000>;
 		interrupts = <16 2 1 31>;
 		fsl,ccf-num-csdids = <32>;
@@ -262,6 +262,7 @@
 		interrupts = <
 			24 2 0 0
 			16 2 1 30>;
+		fsl,portid-mapping = <0x0f000000>;
 
 		pamu0: pamu@0 {
 			reg = <0 0x1000>;
diff --git a/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi
index 22f3b14517d..b1ea147f299 100644
--- a/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2041si-pre.dtsi
@@ -83,6 +83,7 @@
 			reg = <0>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_0>;
+			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -92,6 +93,7 @@
 			reg = <1>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -101,6 +103,7 @@
 			reg = <2>;
 			clocks = <&mux2>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x20000000>;
 			L2_2: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -110,6 +113,7 @@
 			reg = <3>;
 			clocks = <&mux3>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x10000000>;
 			L2_3: l2-cache {
 				next-level-cache = <&cpc>;
 			};
diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
index 7af6d45fd99..cd63cb1b104 100644
--- a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
@@ -273,7 +273,7 @@
 	};
 
 	corenet-cf@18000 {
-		compatible = "fsl,corenet-cf";
+		compatible = "fsl,corenet1-cf", "fsl,corenet-cf";
 		reg = <0x18000 0x1000>;
 		interrupts = <16 2 1 31>;
 		fsl,ccf-num-csdids = <32>;
@@ -289,6 +289,7 @@
 		interrupts = <
 			24 2 0 0
 			16 2 1 30>;
+		fsl,portid-mapping = <0x0f000000>;
 
 		pamu0: pamu@0 {
 			reg = <0 0x1000>;
diff --git a/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi
index 468e8be8ac6..dc5f4b362c2 100644
--- a/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p3041si-pre.dtsi
@@ -84,6 +84,7 @@
 			reg = <0>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_0>;
+			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -93,6 +94,7 @@
 			reg = <1>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -102,6 +104,7 @@
 			reg = <2>;
 			clocks = <&mux2>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x20000000>;
 			L2_2: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -111,6 +114,7 @@
 			reg = <3>;
 			clocks = <&mux3>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x10000000>;
 			L2_3: l2-cache {
 				next-level-cache = <&cpc>;
 			};
diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
index 2415e1f1d3f..12947ccddf2 100644
--- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi
@@ -281,7 +281,7 @@
 	};
 
 	corenet-cf@18000 {
-		compatible = "fsl,corenet-cf";
+		compatible = "fsl,corenet1-cf", "fsl,corenet-cf";
 		reg = <0x18000 0x1000>;
 		interrupts = <16 2 1 31>;
 		fsl,ccf-num-csdids = <32>;
@@ -297,6 +297,7 @@
 		interrupts = <
 			24 2 0 0
 			16 2 1 30>;
+		fsl,portid-mapping = <0x00f80000>;
 
 		pamu0: pamu@0 {
 			reg = <0 0x1000>;
diff --git a/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi
index 0040b5a5379..38bde095867 100644
--- a/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p4080si-pre.dtsi
@@ -83,6 +83,7 @@
 			reg = <0>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_0>;
+			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -92,6 +93,7 @@
 			reg = <1>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -101,6 +103,7 @@
 			reg = <2>;
 			clocks = <&mux2>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x20000000>;
 			L2_2: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -110,6 +113,7 @@
 			reg = <3>;
 			clocks = <&mux3>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x10000000>;
 			L2_3: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -119,6 +123,7 @@
 			reg = <4>;
 			clocks = <&mux4>;
 			next-level-cache = <&L2_4>;
+			fsl,portid-mapping = <0x08000000>;
 			L2_4: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -128,6 +133,7 @@
 			reg = <5>;
 			clocks = <&mux5>;
 			next-level-cache = <&L2_5>;
+			fsl,portid-mapping = <0x04000000>;
 			L2_5: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -137,6 +143,7 @@
 			reg = <6>;
 			clocks = <&mux6>;
 			next-level-cache = <&L2_6>;
+			fsl,portid-mapping = <0x02000000>;
 			L2_6: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -146,6 +153,7 @@
 			reg = <7>;
 			clocks = <&mux7>;
 			next-level-cache = <&L2_7>;
+			fsl,portid-mapping = <0x01000000>;
 			L2_7: l2-cache {
 				next-level-cache = <&cpc>;
 			};
diff --git a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
index 2985de4ad6b..4c4a2b0436b 100644
--- a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
@@ -278,7 +278,7 @@
 	};
 
 	corenet-cf@18000 {
-		compatible = "fsl,corenet-cf";
+		compatible = "fsl,corenet1-cf", "fsl,corenet-cf";
 		reg = <0x18000 0x1000>;
 		interrupts = <16 2 1 31>;
 		fsl,ccf-num-csdids = <32>;
@@ -294,6 +294,7 @@
 		interrupts = <
 			24 2 0 0
 			16 2 1 30>;
+		fsl,portid-mapping = <0x3c000000>;
 
 		pamu0: pamu@0 {
 			reg = <0 0x1000>;
diff --git a/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi
index fe1a2e6613b..1cc61e126e4 100644
--- a/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5020si-pre.dtsi
@@ -90,6 +90,7 @@
 			reg = <0>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_0>;
+			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -99,6 +100,7 @@
 			reg = <1>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
 				next-level-cache = <&cpc>;
 			};
diff --git a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
index 546a899efe2..67296fdd969 100644
--- a/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5040si-post.dtsi
@@ -233,7 +233,7 @@
 	};
 
 	corenet-cf@18000 {
-		compatible = "fsl,corenet-cf";
+		compatible = "fsl,corenet1-cf", "fsl,corenet-cf";
 		reg = <0x18000 0x1000>;
 		interrupts = <16 2 1 31>;
 		fsl,ccf-num-csdids = <32>;
@@ -248,6 +248,7 @@
 		#size-cells = <1>;
 		interrupts = <24 2 0 0
 			      16 2 1 30>;
+		fsl,portid-mapping = <0x0f800000>;
 
 		pamu0: pamu@0 {
 			reg = <0 0x1000>;
diff --git a/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi b/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi
index 3674686687c..b048a2be05a 100644
--- a/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5040si-pre.dtsi
@@ -83,6 +83,7 @@
 			reg = <0>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_0>;
+			fsl,portid-mapping = <0x80000000>;
 			L2_0: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -92,6 +93,7 @@
 			reg = <1>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x40000000>;
 			L2_1: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -101,6 +103,7 @@
 			reg = <2>;
 			clocks = <&mux2>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x20000000>;
 			L2_2: l2-cache {
 				next-level-cache = <&cpc>;
 			};
@@ -110,6 +113,7 @@
 			reg = <3>;
 			clocks = <&mux3>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x10000000>;
 			L2_3: l2-cache {
 				next-level-cache = <&cpc>;
 			};
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi
index f75b4f820c3..7d4a6a2354f 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi
@@ -32,7 +32,8 @@
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-	compatible = "fsl,sec-v6.0";
+	compatible = "fsl,sec-v6.0", "fsl,sec-v5.0",
+		     "fsl,sec-v4.0";
 	fsl,sec-era = <6>;
 	#address-cells = <1>;
 	#size-cells = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
new file mode 100644
index 00000000000..12e597eea3c
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -0,0 +1,430 @@
+/*
+ * T1040 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&ifc {
+	#address-cells = <2>;
+	#size-cells = <1>;
+	compatible = "fsl,ifc", "simple-bus";
+	interrupts = <25 2 0 0>;
+};
+
+&pci0 {
+	compatible = "fsl,t1040-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+	device_type = "pci";
+	#size-cells = <2>;
+	#address-cells = <3>;
+	bus-range = <0x0 0xff>;
+	interrupts = <20 2 0 0>;
+	fsl,iommu-parent = <&pamu0>;
+	pcie@0 {
+		reg = <0 0 0 0 0>;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		device_type = "pci";
+		interrupts = <20 2 0 0>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 40 1 0 0
+			0000 0 0 2 &mpic 1 1 0 0
+			0000 0 0 3 &mpic 2 1 0 0
+			0000 0 0 4 &mpic 3 1 0 0
+			>;
+	};
+};
+
+&pci1 {
+	compatible = "fsl,t1040-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+	device_type = "pci";
+	#size-cells = <2>;
+	#address-cells = <3>;
+	bus-range = <0 0xff>;
+	interrupts = <21 2 0 0>;
+	fsl,iommu-parent = <&pamu0>;
+	pcie@0 {
+		reg = <0 0 0 0 0>;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		device_type = "pci";
+		interrupts = <21 2 0 0>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 41 1 0 0
+			0000 0 0 2 &mpic 5 1 0 0
+			0000 0 0 3 &mpic 6 1 0 0
+			0000 0 0 4 &mpic 7 1 0 0
+			>;
+	};
+};
+
+&pci2 {
+	compatible = "fsl,t1040-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+	device_type = "pci";
+	#size-cells = <2>;
+	#address-cells = <3>;
+	bus-range = <0x0 0xff>;
+	interrupts = <22 2 0 0>;
+	fsl,iommu-parent = <&pamu0>;
+	pcie@0 {
+		reg = <0 0 0 0 0>;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		device_type = "pci";
+		interrupts = <22 2 0 0>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 42 1 0 0
+			0000 0 0 2 &mpic 9 1 0 0
+			0000 0 0 3 &mpic 10 1 0 0
+			0000 0 0 4 &mpic 11 1 0 0
+			>;
+	};
+};
+
+&pci3 {
+	compatible = "fsl,t1040-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+	device_type = "pci";
+	#size-cells = <2>;
+	#address-cells = <3>;
+	bus-range = <0x0 0xff>;
+	interrupts = <23 2 0 0>;
+	fsl,iommu-parent = <&pamu0>;
+	pcie@0 {
+		reg = <0 0 0 0 0>;
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		device_type = "pci";
+		interrupts = <23 2 0 0>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 43 1 0 0
+			0000 0 0 2 &mpic 0 1 0 0
+			0000 0 0 3 &mpic 4 1 0 0
+			0000 0 0 4 &mpic 8 1 0 0
+			>;
+	};
+};
+
+&dcsr {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "fsl,dcsr", "simple-bus";
+
+	dcsr-epu@0 {
+		compatible = "fsl,t1040-dcsr-epu", "fsl,dcsr-epu";
+		interrupts = <52 2 0 0
+			      84 2 0 0
+			      85 2 0 0>;
+		reg = <0x0 0x1000>;
+	};
+	dcsr-npc {
+		compatible = "fsl,t1040-dcsr-cnpc", "fsl,dcsr-cnpc";
+		reg = <0x1000 0x1000 0x1002000 0x10000>;
+	};
+	dcsr-nxc@2000 {
+		compatible = "fsl,dcsr-nxc";
+		reg = <0x2000 0x1000>;
+	};
+	dcsr-corenet {
+		compatible = "fsl,dcsr-corenet";
+		reg = <0x8000 0x1000 0x1A000 0x1000>;
+	};
+	dcsr-dpaa@9000 {
+		compatible = "fsl,t1040-dcsr-dpaa", "fsl,dcsr-dpaa";
+		reg = <0x9000 0x1000>;
+	};
+	dcsr-ocn@11000 {
+		compatible = "fsl,t1040-dcsr-ocn", "fsl,dcsr-ocn";
+		reg = <0x11000 0x1000>;
+	};
+	dcsr-ddr@12000 {
+		compatible = "fsl,dcsr-ddr";
+		dev-handle = <&ddr1>;
+		reg = <0x12000 0x1000>;
+	};
+	dcsr-nal@18000 {
+		compatible = "fsl,t1040-dcsr-nal", "fsl,dcsr-nal";
+		reg = <0x18000 0x1000>;
+	};
+	dcsr-rcpm@22000 {
+		compatible = "fsl,t1040-dcsr-rcpm", "fsl,dcsr-rcpm";
+		reg = <0x22000 0x1000>;
+	};
+	dcsr-snpc@30000 {
+		compatible = "fsl,t1040-dcsr-snpc", "fsl,dcsr-snpc";
+		reg = <0x30000 0x1000 0x1022000 0x10000>;
+	};
+	dcsr-snpc@31000 {
+		compatible = "fsl,t1040-dcsr-snpc", "fsl,dcsr-snpc";
+		reg = <0x31000 0x1000 0x1042000 0x10000>;
+	};
+	dcsr-cpu-sb-proxy@100000 {
+		compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+		cpu-handle = <&cpu0>;
+		reg = <0x100000 0x1000 0x101000 0x1000>;
+	};
+	dcsr-cpu-sb-proxy@108000 {
+		compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+		cpu-handle = <&cpu1>;
+		reg = <0x108000 0x1000 0x109000 0x1000>;
+	};
+	dcsr-cpu-sb-proxy@110000 {
+		compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+		cpu-handle = <&cpu2>;
+		reg = <0x110000 0x1000 0x111000 0x1000>;
+	};
+	dcsr-cpu-sb-proxy@118000 {
+		compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+		cpu-handle = <&cpu3>;
+		reg = <0x118000 0x1000 0x119000 0x1000>;
+	};
+};
+
+&soc {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	device_type = "soc";
+	compatible = "simple-bus";
+
+	soc-sram-error {
+		compatible = "fsl,soc-sram-error";
+		interrupts = <16 2 1 29>;
+	};
+
+	corenet-law@0 {
+		compatible = "fsl,corenet-law";
+		reg = <0x0 0x1000>;
+		fsl,num-laws = <16>;
+	};
+
+	ddr1: memory-controller@8000 {
+		compatible = "fsl,qoriq-memory-controller-v5.0",
+				"fsl,qoriq-memory-controller";
+		reg = <0x8000 0x1000>;
+		interrupts = <16 2 1 23>;
+	};
+
+	cpc: l3-cache-controller@10000 {
+		compatible = "fsl,t1040-l3-cache-controller", "cache";
+		reg = <0x10000 0x1000>;
+		interrupts = <16 2 1 27>;
+	};
+
+	corenet-cf@18000 {
+		compatible = "fsl,corenet2-cf", "fsl,corenet-cf";
+		reg = <0x18000 0x1000>;
+		interrupts = <16 2 1 31>;
+		fsl,ccf-num-csdids = <32>;
+		fsl,ccf-num-snoopids = <32>;
+	};
+
+	iommu@20000 {
+		compatible = "fsl,pamu-v1.0", "fsl,pamu";
+		reg = <0x20000 0x1000>;
+		ranges = <0 0x20000 0x1000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		interrupts = <
+			24 2 0 0
+			16 2 1 30>;
+		pamu0: pamu@0 {
+			reg = <0 0x1000>;
+			fsl,primary-cache-geometry = <128 1>;
+			fsl,secondary-cache-geometry = <16 2>;
+		};
+	};
+
+/include/ "qoriq-mpic.dtsi"
+
+	guts: global-utilities@e0000 {
+		compatible = "fsl,t1040-device-config", "fsl,qoriq-device-config-2.0";
+		reg = <0xe0000 0xe00>;
+		fsl,has-rstcr;
+		fsl,liodn-bits = <12>;
+	};
+
+	clockgen: global-utilities@e1000 {
+		compatible = "fsl,t1040-clockgen", "fsl,qoriq-clockgen-2.0";
+		ranges = <0x0 0xe1000 0x1000>;
+		reg = <0xe1000 0x1000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		sysclk: sysclk {
+			#clock-cells = <0>;
+			compatible = "fsl,qoriq-sysclk-2.0";
+			clock-output-names = "sysclk", "fixed-clock";
+		};
+
+
+		pll0: pll0@800 {
+			#clock-cells = <1>;
+			reg = <0x800 4>;
+			compatible = "fsl,qoriq-core-pll-2.0";
+			clocks = <&sysclk>;
+			clock-output-names = "pll0", "pll0-div2", "pll0-div4";
+		};
+
+		pll1: pll1@820 {
+			#clock-cells = <1>;
+			reg = <0x820 4>;
+			compatible = "fsl,qoriq-core-pll-2.0";
+			clocks = <&sysclk>;
+			clock-output-names = "pll1", "pll1-div2", "pll1-div4";
+		};
+
+		mux0: mux0@0 {
+			#clock-cells = <0>;
+			reg = <0x0 4>;
+			compatible = "fsl,qoriq-core-mux-2.0";
+			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
+			clock-names = "pll0", "pll0-div2", "pll1-div4",
+				"pll1", "pll1-div2", "pll1-div4";
+			clock-output-names = "cmux0";
+		};
+
+		mux1: mux1@20 {
+			#clock-cells = <0>;
+			reg = <0x20 4>;
+			compatible = "fsl,qoriq-core-mux-2.0";
+			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
+			clock-names = "pll0", "pll0-div2", "pll1-div4",
+				"pll1", "pll1-div2", "pll1-div4";
+			clock-output-names = "cmux1";
+		};
+
+		mux2: mux2@40 {
+			#clock-cells = <0>;
+			reg = <0x40 4>;
+			compatible = "fsl,qoriq-core-mux-2.0";
+			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
+			clock-names = "pll0", "pll0-div2", "pll1-div4",
+				"pll1", "pll1-div2", "pll1-div4";
+			clock-output-names = "cmux2";
+		};
+
+		mux3: mux3@60 {
+			#clock-cells = <0>;
+			reg = <0x60 4>;
+			compatible = "fsl,qoriq-core-mux-2.0";
+			clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+				 <&pll1 0>, <&pll1 1>, <&pll1 2>;
+			clock-names = "pll0_0", "pll0_1", "pll0_2",
+				"pll1_0", "pll1_1", "pll1_2";
+			clock-output-names = "cmux3";
+		};
+	};
+
+	rcpm: global-utilities@e2000 {
+		compatible = "fsl,t1040-rcpm", "fsl,qoriq-rcpm-2.0";
+		reg = <0xe2000 0x1000>;
+	};
+
+	sfp: sfp@e8000 {
+		compatible = "fsl,t1040-sfp";
+		reg	   = <0xe8000 0x1000>;
+	};
+
+	serdes: serdes@ea000 {
+		compatible = "fsl,t1040-serdes";
+		reg	   = <0xea000 0x4000>;
+	};
+
+/include/ "elo3-dma-0.dtsi"
+/include/ "elo3-dma-1.dtsi"
+/include/ "qoriq-espi-0.dtsi"
+	spi@110000 {
+		fsl,espi-num-chipselects = <4>;
+	};
+
+/include/ "qoriq-esdhc-0.dtsi"
+	sdhc@114000 {
+		compatible = "fsl,t1040-esdhc", "fsl,esdhc";
+		fsl,iommu-parent = <&pamu0>;
+		fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
+		sdhci,auto-cmd12;
+	};
+/include/ "qoriq-i2c-0.dtsi"
+/include/ "qoriq-i2c-1.dtsi"
+/include/ "qoriq-duart-0.dtsi"
+/include/ "qoriq-duart-1.dtsi"
+/include/ "qoriq-gpio-0.dtsi"
+/include/ "qoriq-gpio-1.dtsi"
+/include/ "qoriq-gpio-2.dtsi"
+/include/ "qoriq-gpio-3.dtsi"
+/include/ "qoriq-usb2-mph-0.dtsi"
+		usb0: usb@210000 {
+			compatible = "fsl-usb2-mph-v2.4", "fsl-usb2-mph";
+			fsl,iommu-parent = <&pamu0>;
+			fsl,liodn-reg = <&guts 0x520>; /* USB1LIODNR */
+			phy_type = "utmi";
+			port0;
+		};
+/include/ "qoriq-usb2-dr-0.dtsi"
+		usb1: usb@211000 {
+			compatible = "fsl-usb2-dr-v2.4", "fsl-usb2-dr";
+			fsl,iommu-parent = <&pamu0>;
+			fsl,liodn-reg = <&guts 0x524>; /* USB2LIODNR */
+			dr_mode = "host";
+			phy_type = "utmi";
+		};
+
+	display@180000 {
+		compatible = "fsl,t1040-diu", "fsl,diu";
+		reg = <0x180000 1000>;
+		interrupts = <74 2 0 0>;
+	};
+
+/include/ "qoriq-sata2-0.dtsi"
+	sata@220000 {
+		fsl,iommu-parent = <&pamu0>;
+		fsl,liodn-reg = <&guts 0x550>; /* SATA1LIODNR */
+	};
+/include/ "qoriq-sata2-1.dtsi"
+	sata@221000 {
+		fsl,iommu-parent = <&pamu0>;
+		fsl,liodn-reg = <&guts 0x554>; /* SATA2LIODNR */
+	};
+/include/ "qoriq-sec5.0-0.dtsi"
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi
new file mode 100644
index 00000000000..319b74f2972
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi
@@ -0,0 +1,37 @@
+/*
+ * T1042 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "t1040si-post.dtsi"
+
+/* Place holder for ethernet related device tree nodes */
diff --git a/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi
new file mode 100644
index 00000000000..bbb7025ca9c
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi
@@ -0,0 +1,104 @@
+/*
+ * T1040/T1042 Silicon/SoC Device Tree Source (pre include)
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/include/ "e5500_power_isa.dtsi"
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	aliases {
+		ccsr = &soc;
+		dcsr = &dcsr;
+
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		serial3 = &serial3;
+		pci0 = &pci0;
+		pci1 = &pci1;
+		pci2 = &pci2;
+		pci3 = &pci3;
+		usb0 = &usb0;
+		usb1 = &usb1;
+		sdhc = &sdhc;
+
+		crypto = &crypto;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: PowerPC,e5500@0 {
+			device_type = "cpu";
+			reg = <0>;
+			clocks = <&mux0>;
+			next-level-cache = <&L2_1>;
+			L2_1: l2-cache {
+				next-level-cache = <&cpc>;
+			};
+		};
+		cpu1: PowerPC,e5500@1 {
+			device_type = "cpu";
+			reg = <1>;
+			clocks = <&mux1>;
+			next-level-cache = <&L2_2>;
+			L2_2: l2-cache {
+				next-level-cache = <&cpc>;
+			};
+		};
+		cpu2: PowerPC,e5500@2 {
+			device_type = "cpu";
+			reg = <2>;
+			clocks = <&mux2>;
+			next-level-cache = <&L2_3>;
+			L2_3: l2-cache {
+				next-level-cache = <&cpc>;
+			};
+		};
+		cpu3: PowerPC,e5500@3 {
+			device_type = "cpu";
+			reg = <3>;
+			clocks = <&mux3>;
+			next-level-cache = <&L2_4>;
+			L2_4: l2-cache {
+				next-level-cache = <&cpc>;
+			};
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
index f99d74ff11b..793669baa13 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi
@@ -343,7 +343,7 @@
 	};
 
 	corenet-cf@18000 {
-		compatible = "fsl,corenet-cf";
+		compatible = "fsl,corenet2-cf", "fsl,corenet-cf";
 		reg = <0x18000 0x1000>;
 		interrupts = <16 2 1 31>;
 		fsl,ccf-num-csdids = <32>;
@@ -353,6 +353,7 @@
 	iommu@20000 {
 		compatible = "fsl,pamu-v1.0", "fsl,pamu";
 		reg = <0x20000 0x6000>;
+		fsl,portid-mapping = <0x8000>;
 		interrupts = <
 			24 2 0 0
 			16 2 1 30>;
diff --git a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
index 0b8ccc5b4a4..d2f157edbe8 100644
--- a/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t4240si-pre.dtsi
@@ -69,72 +69,84 @@
 			reg = <0 1>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu1: PowerPC,e6500@2 {
 			device_type = "cpu";
 			reg = <2 3>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu2: PowerPC,e6500@4 {
 			device_type = "cpu";
 			reg = <4 5>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu3: PowerPC,e6500@6 {
 			device_type = "cpu";
 			reg = <6 7>;
 			clocks = <&mux0>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu4: PowerPC,e6500@8 {
 			device_type = "cpu";
 			reg = <8 9>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu5: PowerPC,e6500@10 {
 			device_type = "cpu";
 			reg = <10 11>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu6: PowerPC,e6500@12 {
 			device_type = "cpu";
 			reg = <12 13>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu7: PowerPC,e6500@14 {
 			device_type = "cpu";
 			reg = <14 15>;
 			clocks = <&mux1>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu8: PowerPC,e6500@16 {
 			device_type = "cpu";
 			reg = <16 17>;
 			clocks = <&mux2>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x20000000>;
 		};
 		cpu9: PowerPC,e6500@18 {
 			device_type = "cpu";
 			reg = <18 19>;
 			clocks = <&mux2>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x20000000>;
 		};
 		cpu10: PowerPC,e6500@20 {
 			device_type = "cpu";
 			reg = <20 21>;
 			clocks = <&mux2>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x20000000>;
 		};
 		cpu11: PowerPC,e6500@22 {
 			device_type = "cpu";
 			reg = <22 23>;
 			clocks = <&mux2>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x20000000>;
 		};
 	};
 };
diff --git a/arch/powerpc/boot/dts/kmcoge4.dts b/arch/powerpc/boot/dts/kmcoge4.dts
new file mode 100644
index 00000000000..89b4119f3b1
--- /dev/null
+++ b/arch/powerpc/boot/dts/kmcoge4.dts
@@ -0,0 +1,152 @@
+/*
+ * Keymile kmcoge4 Device Tree Source, based on the P2041RDB DTS
+ *
+ * (C) Copyright 2014
+ * Valentin Longchamp, Keymile AG, valentin.longchamp@keymile.com
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/include/ "fsl/p2041si-pre.dtsi"
+
+/ {
+	model = "keymile,kmcoge4";
+	compatible = "keymile,kmcoge4", "keymile,kmp204x";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	memory {
+		device_type = "memory";
+	};
+
+	dcsr: dcsr@f00000000 {
+		ranges = <0x00000000 0xf 0x00000000 0x01008000>;
+	};
+
+	soc: soc@ffe000000 {
+		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+		reg = <0xf 0xfe000000 0 0x00001000>;
+		spi@110000 {
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "spansion,s25fl256s1";
+				reg = <0>;
+				spi-max-frequency = <20000000>; /* input clock */
+			};
+
+			network_clock@1 {
+				compatible = "zarlink,zl30343";
+				reg = <1>;
+				spi-max-frequency = <8000000>;
+			};
+
+			flash@2 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "micron,m25p32";
+				reg = <2>;
+				spi-max-frequency = <15000000>;
+			};
+		};
+
+		i2c@119000 {
+			status = "disabled";
+		};
+
+		i2c@119100 {
+			status = "disabled";
+		};
+
+		usb0: usb@210000 {
+			status = "disabled";
+		};
+
+		usb1: usb@211000 {
+			status = "disabled";
+		};
+
+		sata@220000 {
+			status = "disabled";
+		};
+
+		sata@221000 {
+			status = "disabled";
+		};
+	};
+
+	rio: rapidio@ffe0c0000 {
+		status = "disabled";
+	};
+
+	lbc: localbus@ffe124000 {
+		reg = <0xf 0xfe124000 0 0x1000>;
+		ranges = <0 0 0xf 0xffa00000 0x00040000		/* LB 0 */
+			  1 0 0xf 0xfb000000 0x00010000		/* LB 1 */
+			  2 0 0xf 0xd0000000 0x10000000		/* LB 2 */
+			  3 0 0xf 0xe0000000 0x10000000>;	/* LB 3 */
+
+		nand@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,elbc-fcm-nand";
+			reg = <0 0 0x40000>;
+		};
+
+		board-control@1,0 {
+			compatible = "keymile,qriox";
+			reg = <1 0 0x80>;
+		};
+
+		chassis-mgmt@3,0 {
+			compatible = "keymile,bfticu";
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			reg = <3 0 0x100>;
+			interrupt-parent = <&mpic>;
+			interrupts = <6 1 0 0>;
+		};
+	};
+
+	pci0: pcie@ffe200000 {
+		reg = <0xf 0xfe200000 0 0x1000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x20000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci1: pcie@ffe201000 {
+		status = "disabled";
+	};
+
+	pci2: pcie@ffe202000 {
+		reg = <0xf 0xfe202000 0 0x1000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x20000000
+			  0x01000000 0 0x00000000 0xf 0xf8010000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x20000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+};
+
+/include/ "fsl/p2041si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/mpc8308_p1m.dts b/arch/powerpc/boot/dts/mpc8308_p1m.dts
index 651e4f55acd..57f86cdf9f3 100644
--- a/arch/powerpc/boot/dts/mpc8308_p1m.dts
+++ b/arch/powerpc/boot/dts/mpc8308_p1m.dts
@@ -296,7 +296,7 @@
 		};
 
 		dma@2c000 {
-			compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma";
+			compatible = "fsl,mpc8308-dma";
 			reg = <0x2c000 0x1800>;
 			interrupts = <3 0x8
 					94 0x8>;
diff --git a/arch/powerpc/boot/dts/mpc8308rdb.dts b/arch/powerpc/boot/dts/mpc8308rdb.dts
index 9ce45f2efd3..d0211f0413c 100644
--- a/arch/powerpc/boot/dts/mpc8308rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8308rdb.dts
@@ -265,7 +265,7 @@
 		};
 
 		dma@2c000 {
-			compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma";
+			compatible = "fsl,mpc8308-dma";
 			reg = <0x2c000 0x1800>;
 			interrupts = <3 0x8
 					94 0x8>;
diff --git a/arch/powerpc/boot/dts/oca4080.dts b/arch/powerpc/boot/dts/oca4080.dts
new file mode 100644
index 00000000000..3d4c751d160
--- /dev/null
+++ b/arch/powerpc/boot/dts/oca4080.dts
@@ -0,0 +1,118 @@
+/*
+ * OCA4080 Device Tree Source
+ *
+ * Copyright 2014 Prodrive Technologies B.V.
+ *
+ * Based on:
+ * P4080DS Device Tree Source
+ * Copyright 2009-2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p4080si-pre.dtsi"
+
+/ {
+	model = "fsl,OCA4080";
+	compatible = "fsl,OCA4080";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	memory {
+		device_type = "memory";
+	};
+
+	dcsr: dcsr@f00000000 {
+		ranges = <0x00000000 0xf 0x00000000 0x01008000>;
+	};
+
+	soc: soc@ffe000000 {
+		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+		reg = <0xf 0xfe000000 0 0x00001000>;
+
+		i2c@118000 {
+			status = "disabled";
+		};
+
+		i2c@118100 {
+			status = "disabled";
+		};
+
+		i2c@119000 {
+			status = "disabled";
+		};
+
+		i2c@119100 {
+			status = "disabled";
+		};
+
+		usb0: usb@210000 {
+			status = "disabled";
+		};
+
+		usb1: usb@211000 {
+			status = "disabled";
+		};
+	};
+
+	rio: rapidio@ffe0c0000 {
+		reg = <0xf 0xfe0c0000 0 0x11000>;
+
+		port1 {
+			ranges = <0 0 0xc 0x20000000 0 0x10000000>;
+		};
+	};
+
+	lbc: localbus@ffe124000 {
+		reg = <0xf 0xfe124000 0 0x1000>;
+		ranges = <0 0 0xf 0xef800000 0x800000>;
+
+		flash@0,0 {
+			compatible = "cfi-flash";
+			reg = <0 0 0x00800000>;
+			bank-width = <2>;
+			device-width = <2>;
+		};
+	};
+
+	pci0: pcie@ffe200000 {
+		status = "disabled";
+	};
+
+	pci1: pcie@ffe201000 {
+		status = "disabled";
+	};
+
+	pci2: pcie@ffe202000 {
+		status = "disabled";
+	};
+};
+
+/include/ "fsl/p4080si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1023rds.dts b/arch/powerpc/boot/dts/p1023rds.dts
deleted file mode 100644
index beb6cb12e59..00000000000
--- a/arch/powerpc/boot/dts/p1023rds.dts
+++ /dev/null
@@ -1,219 +0,0 @@
-/*
- * P1023 RDS Device Tree Source
- *
- * Copyright 2010-2011 Freescale Semiconductor Inc.
- *
- * Author: Roy Zang <tie-fei.zang@freescale.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-/include/ "fsl/p1023si-pre.dtsi"
-
-/ {
-	model = "fsl,P1023";
-	compatible = "fsl,P1023RDS";
-	#address-cells = <2>;
-	#size-cells = <2>;
-	interrupt-parent = <&mpic>;
-
-	memory {
-		device_type = "memory";
-	};
-
-	soc: soc@ff600000 {
-		ranges = <0x0 0x0 0xff600000 0x200000>;
-
-		i2c@3000 {
-			rtc@68 {
-				compatible = "dallas,ds1374";
-				reg = <0x68>;
-			};
-		};
-
-		spi@7000 {
-			fsl_dataflash@0 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				compatible = "atmel,at45db081d";
-				reg = <0>;
-				spi-max-frequency = <40000000>; /* input clock */
-				partition@u-boot {
-					/* 512KB for u-boot Bootloader Image */
-					label = "u-boot-spi";
-					reg = <0x00000000 0x00080000>;
-					read-only;
-				};
-				partition@dtb {
-					/* 512KB for DTB Image */
-					label = "dtb-spi";
-					reg = <0x00080000 0x00080000>;
-					read-only;
-				};
-			};
-		};
-
-		usb@22000 {
-			dr_mode = "host";
-			phy_type = "ulpi";
-		};
-	};
-
-	lbc: localbus@ff605000 {
-		reg = <0 0xff605000 0 0x1000>;
-
-		/* NOR Flash, BCSR */
-		ranges = <0x0 0x0 0x0 0xee000000 0x02000000
-			  0x1 0x0 0x0 0xe0000000 0x00008000>;
-
-		nor@0,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "cfi-flash";
-			reg = <0x0 0x0 0x02000000>;
-			bank-width = <2>;
-			device-width = <1>;
-			partition@0 {
-				label = "ramdisk";
-				reg = <0x00000000 0x01c00000>;
-			};
-			partition@1c00000 {
-				label = "kernel";
-				reg = <0x01c00000 0x002e0000>;
-			};
-			partiton@1ee0000 {
-				label = "dtb";
-				reg = <0x01ee0000 0x00020000>;
-			};
-			partition@1f00000 {
-				label = "firmware";
-				reg = <0x01f00000 0x00080000>;
-				read-only;
-			};
-			partition@1f80000 {
-				label = "u-boot";
-				reg = <0x01f80000 0x00080000>;
-				read-only;
-			};
-		};
-
-		fpga@1,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,p1023rds-fpga";
-			reg = <1 0 0x8000>;
-			ranges = <0 1 0 0x8000>;
-
-			bcsr@20 {
-				compatible = "fsl,p1023rds-bcsr";
-				reg = <0x20 0x20>;
-			};
-		};
-	};
-
-	pci0: pcie@ff60a000 {
-		reg = <0 0xff60a000 0 0x1000>;
-		ranges = <0x2000000 0x0 0xc0000000 0 0xc0000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x10000>;
-		pcie@0 {
-			/* IRQ[0:3] are pulled up on board, set to active-low */
-			interrupt-map-mask = <0xf800 0 0 7>;
-			interrupt-map = <
-				/* IDSEL 0x0 */
-				0000 0 0 1 &mpic 0 1 0 0
-				0000 0 0 2 &mpic 1 1 0 0
-				0000 0 0 3 &mpic 2 1 0 0
-				0000 0 0 4 &mpic 3 1 0 0
-				>;
-			ranges = <0x2000000 0x0 0xc0000000
-				  0x2000000 0x0 0xc0000000
-				  0x0 0x20000000
-
-				  0x1000000 0x0 0x0
-				  0x1000000 0x0 0x0
-				  0x0 0x100000>;
-		};
-	};
-
-	board_pci1: pci1: pcie@ff609000 {
-		reg = <0 0xff609000 0 0x1000>;
-		ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
-		pcie@0 {
-			/*
-			 * IRQ[4:6] only for PCIe, set to active-high,
-			 * IRQ[7] is pulled up on board, set to active-low
-			 */
-			interrupt-map-mask = <0xf800 0 0 7>;
-			interrupt-map = <
-				/* IDSEL 0x0 */
-				0000 0 0 1 &mpic 4 2 0 0
-				0000 0 0 2 &mpic 5 2 0 0
-				0000 0 0 3 &mpic 6 2 0 0
-				0000 0 0 4 &mpic 7 1 0 0
-				>;
-			ranges = <0x2000000 0x0 0xa0000000
-				  0x2000000 0x0 0xa0000000
-				  0x0 0x20000000
-
-				  0x1000000 0x0 0x0
-				  0x1000000 0x0 0x0
-				  0x0 0x100000>;
-		};
-	};
-
-	pci2: pcie@ff60b000 {
-		reg = <0 0xff60b000 0 0x1000>;
-		ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000
-			  0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
-		pcie@0 {
-			/*
-			 * IRQ[8:10] are pulled up on board, set to active-low
-			 * IRQ[11] only for PCIe, set to active-high,
-			 */
-			interrupt-map-mask = <0xf800 0 0 7>;
-			interrupt-map = <
-				/* IDSEL 0x0 */
-				0000 0 0 1 &mpic 8 1 0 0
-				0000 0 0 2 &mpic 9 1 0 0
-				0000 0 0 3 &mpic 10 1 0 0
-				0000 0 0 4 &mpic 11 2 0 0
-				>;
-			ranges = <0x2000000 0x0 0x80000000
-				  0x2000000 0x0 0x80000000
-				  0x0 0x20000000
-
-				  0x1000000 0x0 0x0
-				  0x1000000 0x0 0x0
-				  0x0 0x100000>;
-		};
-	};
-};
-
-/include/ "fsl/p1023si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1040qds.dts b/arch/powerpc/boot/dts/t1040qds.dts
new file mode 100644
index 00000000000..973c29c2f56
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1040qds.dts
@@ -0,0 +1,46 @@
+/*
+ * T1040QDS Device Tree Source
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t104xsi-pre.dtsi"
+/include/ "t104xqds.dtsi"
+
+/ {
+	model = "fsl,T1040QDS";
+	compatible = "fsl,T1040QDS";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+};
+
+/include/ "fsl/t1040si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1042qds.dts b/arch/powerpc/boot/dts/t1042qds.dts
new file mode 100644
index 00000000000..45bd0375215
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1042qds.dts
@@ -0,0 +1,46 @@
+/*
+ * T1042QDS Device Tree Source
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t104xsi-pre.dtsi"
+/include/ "t104xqds.dtsi"
+
+/ {
+	model = "fsl,T1042QDS";
+	compatible = "fsl,T1042QDS";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+};
+
+/include/ "fsl/t1042si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t104xqds.dtsi b/arch/powerpc/boot/dts/t104xqds.dtsi
new file mode 100644
index 00000000000..234f4b596c5
--- /dev/null
+++ b/arch/powerpc/boot/dts/t104xqds.dtsi
@@ -0,0 +1,166 @@
+/*
+ * T104xQDS Device Tree Source
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *	 notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *	 notice, this list of conditions and the following disclaimer in the
+ *	 documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *	 names of its contributors may be used to endorse or promote products
+ *	 derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/ {
+	model = "fsl,T1040QDS";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&mpic>;
+
+	ifc: localbus@ffe124000 {
+		reg = <0xf 0xfe124000 0 0x2000>;
+		ranges = <0 0 0xf 0xe8000000 0x08000000
+			  2 0 0xf 0xff800000 0x00010000
+			  3 0 0xf 0xffdf0000 0x00008000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x8000000>;
+
+			bank-width = <2>;
+			device-width = <1>;
+		};
+
+		nand@2,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,ifc-nand";
+			reg = <0x2 0x0 0x10000>;
+		};
+
+		board-control@3,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,fpga-qixis";
+			reg = <3 0 0x300>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	dcsr: dcsr@f00000000 {
+		ranges = <0x00000000 0xf 0x00000000 0x01072000>;
+	};
+
+	soc: soc@ffe000000 {
+		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+		reg = <0xf 0xfe000000 0 0x00001000>;
+
+		spi@110000 {
+			flash@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "micron,n25q128a11";
+				reg = <0>;
+				spi-max-frequency = <10000000>; /* input clock */
+			};
+		};
+
+		i2c@118000 {
+			pca9547@77 {
+				compatible = "philips,pca9547";
+				reg = <0x77>;
+			};
+			rtc@68 {
+				compatible = "dallas,ds3232";
+				reg = <0x68>;
+				interrupts = <0x1 0x1 0 0>;
+			};
+		};
+	};
+
+	pci0: pcie@ffe240000 {
+		reg = <0xf 0xfe240000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci1: pcie@ffe250000 {
+		reg = <0xf 0xfe250000 0 0x10000>;
+		ranges = <0x02000000 0x0 0xe0000000 0xc 0x10000000 0x0 0x10000000
+			  0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci2: pcie@ffe260000 {
+		reg = <0xf 0xfe260000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x20000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci3: pcie@ffe270000 {
+		reg = <0xf 0xfe270000 0 0x10000>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x30000000 0 0x10000000
+			  0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>;
+		pcie@0 {
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x10000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/t4240emu.dts b/arch/powerpc/boot/dts/t4240emu.dts
index ee24ab33559..bc12127a03f 100644
--- a/arch/powerpc/boot/dts/t4240emu.dts
+++ b/arch/powerpc/boot/dts/t4240emu.dts
@@ -60,63 +60,75 @@
 			device_type = "cpu";
 			reg = <0 1>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu1: PowerPC,e6500@2 {
 			device_type = "cpu";
 			reg = <2 3>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu2: PowerPC,e6500@4 {
 			device_type = "cpu";
 			reg = <4 5>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 		cpu3: PowerPC,e6500@6 {
 			device_type = "cpu";
 			reg = <6 7>;
 			next-level-cache = <&L2_1>;
+			fsl,portid-mapping = <0x80000000>;
 		};
 
 		cpu4: PowerPC,e6500@8 {
 			device_type = "cpu";
 			reg = <8 9>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu5: PowerPC,e6500@10 {
 			device_type = "cpu";
 			reg = <10 11>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu6: PowerPC,e6500@12 {
 			device_type = "cpu";
 			reg = <12 13>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x40000000>;
 		};
 		cpu7: PowerPC,e6500@14 {
 			device_type = "cpu";
 			reg = <14 15>;
 			next-level-cache = <&L2_2>;
+			fsl,portid-mapping = <0x40000000>;
 		};
 
 		cpu8: PowerPC,e6500@16 {
 			device_type = "cpu";
 			reg = <16 17>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x20000000>;
 		};
 		cpu9: PowerPC,e6500@18 {
 			device_type = "cpu";
 			reg = <18 19>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x20000000>;
 		};
 		cpu10: PowerPC,e6500@20 {
 			device_type = "cpu";
 			reg = <20 21>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x20000000>;
 		};
 		cpu11: PowerPC,e6500@22 {
 			device_type = "cpu";
 			reg = <22 23>;
 			next-level-cache = <&L2_3>;
+			fsl,portid-mapping = <0x20000000>;
 		};
 	};
 };
@@ -213,7 +225,7 @@
 	};
 
 	corenet-cf@18000 {
-		compatible = "fsl,corenet-cf";
+		compatible = "fsl,corenet2-cf", "fsl,corenet-cf";
 		reg = <0x18000 0x1000>;
 		interrupts = <16 2 1 31>;
 		fsl,ccf-num-csdids = <32>;
@@ -223,6 +235,7 @@
 	iommu@20000 {
 		compatible = "fsl,pamu-v1.0", "fsl,pamu";
 		reg = <0x20000 0x6000>;
+		fsl,portid-mapping = <0x8000>;
 		interrupts = <
 			24 2 0 0
 			16 2 1 30>;
diff --git a/arch/powerpc/boot/elf_util.c b/arch/powerpc/boot/elf_util.c
index 1567a0c0f05..316552dea4d 100644
--- a/arch/powerpc/boot/elf_util.c
+++ b/arch/powerpc/boot/elf_util.c
@@ -26,7 +26,11 @@ int parse_elf64(void *hdr, struct elf_info *info)
 	      elf64->e_ident[EI_MAG2]  == ELFMAG2	&&
 	      elf64->e_ident[EI_MAG3]  == ELFMAG3	&&
 	      elf64->e_ident[EI_CLASS] == ELFCLASS64	&&
+#ifdef __LITTLE_ENDIAN__
+	      elf64->e_ident[EI_DATA]  == ELFDATA2LSB	&&
+#else
 	      elf64->e_ident[EI_DATA]  == ELFDATA2MSB	&&
+#endif
 	      (elf64->e_type            == ET_EXEC ||
 	       elf64->e_type            == ET_DYN)	&&
 	      elf64->e_machine         == EM_PPC64))
diff --git a/arch/powerpc/boot/of.c b/arch/powerpc/boot/of.c
index 62e2f43ec1d..7ca910cb2fc 100644
--- a/arch/powerpc/boot/of.c
+++ b/arch/powerpc/boot/of.c
@@ -40,8 +40,8 @@ static void *of_try_claim(unsigned long size)
 #ifdef DEBUG
 		printf("    trying: 0x%08lx\n\r", claim_base);
 #endif
-		addr = (unsigned long)of_claim(claim_base, size, 0);
-		if ((void *)addr != (void *)-1)
+		addr = (unsigned long) of_claim(claim_base, size, 0);
+		if (addr != PROM_ERROR)
 			break;
 	}
 	if (addr == 0)
diff --git a/arch/powerpc/boot/of.h b/arch/powerpc/boot/of.h
index e4c68f7391c..c8c1750aba0 100644
--- a/arch/powerpc/boot/of.h
+++ b/arch/powerpc/boot/of.h
@@ -1,12 +1,15 @@
 #ifndef _PPC_BOOT_OF_H_
 #define _PPC_BOOT_OF_H_
 
+#include "swab.h"
+
 typedef void *phandle;
-typedef void *ihandle;
+typedef u32 ihandle;
 
 void of_init(void *promptr);
 int of_call_prom(const char *service, int nargs, int nret, ...);
-void *of_claim(unsigned long virt, unsigned long size, unsigned long align);
+unsigned int of_claim(unsigned long virt, unsigned long size,
+	unsigned long align);
 void *of_vmlinux_alloc(unsigned long size);
 void of_exit(void);
 void *of_finddevice(const char *name);
@@ -18,4 +21,16 @@ int of_setprop(const void *phandle, const char *name, const void *buf,
 /* Console functions */
 void of_console_init(void);
 
+typedef u32			__be32;
+
+#ifdef __LITTLE_ENDIAN__
+#define cpu_to_be32(x) swab32(x)
+#define be32_to_cpu(x) swab32(x)
+#else
+#define cpu_to_be32(x) (x)
+#define be32_to_cpu(x) (x)
+#endif
+
+#define PROM_ERROR (-1u)
+
 #endif /* _PPC_BOOT_OF_H_ */
diff --git a/arch/powerpc/boot/ofconsole.c b/arch/powerpc/boot/ofconsole.c
index ce0e0242445..8b754702460 100644
--- a/arch/powerpc/boot/ofconsole.c
+++ b/arch/powerpc/boot/ofconsole.c
@@ -18,7 +18,7 @@
 
 #include "of.h"
 
-static void *of_stdout_handle;
+static unsigned int of_stdout_handle;
 
 static int of_console_open(void)
 {
@@ -27,8 +27,10 @@ static int of_console_open(void)
 	if (((devp = of_finddevice("/chosen")) != NULL)
 	    && (of_getprop(devp, "stdout", &of_stdout_handle,
 			   sizeof(of_stdout_handle))
-		== sizeof(of_stdout_handle)))
+		== sizeof(of_stdout_handle))) {
+		of_stdout_handle = be32_to_cpu(of_stdout_handle);
 		return 0;
+	}
 
 	return -1;
 }
diff --git a/arch/powerpc/boot/oflib.c b/arch/powerpc/boot/oflib.c
index b0ec9cf3eaa..46c98a47d94 100644
--- a/arch/powerpc/boot/oflib.c
+++ b/arch/powerpc/boot/oflib.c
@@ -16,74 +16,83 @@
 
 #include "of.h"
 
+typedef u32 prom_arg_t;
+
+/* The following structure is used to communicate with open firmware.
+ * All arguments in and out are in big endian format. */
+struct prom_args {
+	__be32 service;	/* Address of service name string. */
+	__be32 nargs;	/* Number of input arguments. */
+	__be32 nret;	/* Number of output arguments. */
+	__be32 args[10];	/* Input/output arguments. */
+};
+
+#ifdef __powerpc64__
+extern int prom(void *);
+#else
 static int (*prom) (void *);
+#endif
 
 void of_init(void *promptr)
 {
+#ifndef __powerpc64__
 	prom = (int (*)(void *))promptr;
+#endif
 }
 
+#define ADDR(x)		(u32)(unsigned long)(x)
+
 int of_call_prom(const char *service, int nargs, int nret, ...)
 {
 	int i;
-	struct prom_args {
-		const char *service;
-		int nargs;
-		int nret;
-		unsigned int args[12];
-	} args;
+	struct prom_args args;
 	va_list list;
 
-	args.service = service;
-	args.nargs = nargs;
-	args.nret = nret;
+	args.service = cpu_to_be32(ADDR(service));
+	args.nargs = cpu_to_be32(nargs);
+	args.nret = cpu_to_be32(nret);
 
 	va_start(list, nret);
 	for (i = 0; i < nargs; i++)
-		args.args[i] = va_arg(list, unsigned int);
+		args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t));
 	va_end(list);
 
 	for (i = 0; i < nret; i++)
 		args.args[nargs+i] = 0;
 
 	if (prom(&args) < 0)
-		return -1;
+		return PROM_ERROR;
 
-	return (nret > 0)? args.args[nargs]: 0;
+	return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0;
 }
 
 static int of_call_prom_ret(const char *service, int nargs, int nret,
-			    unsigned int *rets, ...)
+			    prom_arg_t *rets, ...)
 {
 	int i;
-	struct prom_args {
-		const char *service;
-		int nargs;
-		int nret;
-		unsigned int args[12];
-	} args;
+	struct prom_args args;
 	va_list list;
 
-	args.service = service;
-	args.nargs = nargs;
-	args.nret = nret;
+	args.service = cpu_to_be32(ADDR(service));
+	args.nargs = cpu_to_be32(nargs);
+	args.nret = cpu_to_be32(nret);
 
 	va_start(list, rets);
 	for (i = 0; i < nargs; i++)
-		args.args[i] = va_arg(list, unsigned int);
+		args.args[i] = cpu_to_be32(va_arg(list, prom_arg_t));
 	va_end(list);
 
 	for (i = 0; i < nret; i++)
 		args.args[nargs+i] = 0;
 
 	if (prom(&args) < 0)
-		return -1;
+		return PROM_ERROR;
 
-	if (rets != (void *) 0)
+	if (rets != NULL)
 		for (i = 1; i < nret; ++i)
-			rets[i-1] = args.args[nargs+i];
+			rets[i-1] = be32_to_cpu(args.args[nargs+i]);
 
-	return (nret > 0)? args.args[nargs]: 0;
+	return (nret > 0) ? be32_to_cpu(args.args[nargs]) : 0;
 }
 
 /* returns true if s2 is a prefix of s1 */
@@ -103,7 +112,7 @@ static int string_match(const char *s1, const char *s2)
  */
 static int need_map = -1;
 static ihandle chosen_mmu;
-static phandle memory;
+static ihandle memory;
 
 static int check_of_version(void)
 {
@@ -132,10 +141,10 @@ static int check_of_version(void)
 		printf("no mmu\n");
 		return 0;
 	}
-	memory = (ihandle) of_call_prom("open", 1, 1, "/memory");
-	if (memory == (ihandle) -1) {
-		memory = (ihandle) of_call_prom("open", 1, 1, "/memory@0");
-		if (memory == (ihandle) -1) {
+	memory = of_call_prom("open", 1, 1, "/memory");
+	if (memory == PROM_ERROR) {
+		memory = of_call_prom("open", 1, 1, "/memory@0");
+		if (memory == PROM_ERROR) {
 			printf("no memory node\n");
 			return 0;
 		}
@@ -144,40 +153,41 @@ static int check_of_version(void)
 	return 1;
 }
 
-void *of_claim(unsigned long virt, unsigned long size, unsigned long align)
+unsigned int of_claim(unsigned long virt, unsigned long size,
+		      unsigned long align)
 {
 	int ret;
-	unsigned int result;
+	prom_arg_t result;
 
 	if (need_map < 0)
 		need_map = check_of_version();
 	if (align || !need_map)
-		return (void *) of_call_prom("claim", 3, 1, virt, size, align);
+		return of_call_prom("claim", 3, 1, virt, size, align);
 
 	ret = of_call_prom_ret("call-method", 5, 2, &result, "claim", memory,
 			       align, size, virt);
 	if (ret != 0 || result == -1)
-		return (void *) -1;
+		return  -1;
 	ret = of_call_prom_ret("call-method", 5, 2, &result, "claim", chosen_mmu,
 			       align, size, virt);
 	/* 0x12 == coherent + read/write */
 	ret = of_call_prom("call-method", 6, 1, "map", chosen_mmu,
 			   0x12, size, virt, virt);
-	return (void *) virt;
+	return virt;
 }
 
 void *of_vmlinux_alloc(unsigned long size)
 {
 	unsigned long start = (unsigned long)_start, end = (unsigned long)_end;
-	void *addr;
+	unsigned long addr;
 	void *p;
 
 	/* With some older POWER4 firmware we need to claim the area the kernel
 	 * will reside in.  Newer firmwares don't need this so we just ignore
 	 * the return value.
 	 */
-	addr = of_claim(start, end - start, 0);
-	printf("Trying to claim from 0x%lx to 0x%lx (0x%lx) got %p\r\n",
+	addr = (unsigned long) of_claim(start, end - start, 0);
+	printf("Trying to claim from 0x%lx to 0x%lx (0x%lx) got %lx\r\n",
 	       start, end, end - start, addr);
 
 	p = malloc(size);
@@ -197,7 +207,7 @@ void of_exit(void)
  */
 void *of_finddevice(const char *name)
 {
-	return (phandle) of_call_prom("finddevice", 1, 1, name);
+	return (void *) (unsigned long) of_call_prom("finddevice", 1, 1, name);
 }
 
 int of_getprop(const void *phandle, const char *name, void *buf,
diff --git a/arch/powerpc/boot/ppc_asm.h b/arch/powerpc/boot/ppc_asm.h
index eb0e98be69e..35ea60c1f07 100644
--- a/arch/powerpc/boot/ppc_asm.h
+++ b/arch/powerpc/boot/ppc_asm.h
@@ -62,4 +62,16 @@
 #define SPRN_TBRL	268
 #define SPRN_TBRU	269
 
+#define FIXUP_ENDIAN						   \
+	tdi   0, 0, 0x48; /* Reverse endian of b . + 8		*/ \
+	b     $+36;	  /* Skip trampoline if endian is good	*/ \
+	.long 0x05009f42; /* bcl 20,31,$+4			*/ \
+	.long 0xa602487d; /* mflr r10				*/ \
+	.long 0x1c004a39; /* addi r10,r10,28			*/ \
+	.long 0xa600607d; /* mfmsr r11				*/ \
+	.long 0x01006b69; /* xori r11,r11,1			*/ \
+	.long 0xa6035a7d; /* mtsrr0 r10				*/ \
+	.long 0xa6037b7d; /* mtsrr1 r11				*/ \
+	.long 0x2400004c  /* rfid				*/
+
 #endif /* _PPC64_PPC_ASM_H */
diff --git a/arch/powerpc/boot/pseries-head.S b/arch/powerpc/boot/pseries-head.S
new file mode 100644
index 00000000000..6ef6e02e80f
--- /dev/null
+++ b/arch/powerpc/boot/pseries-head.S
@@ -0,0 +1,8 @@
+#include "ppc_asm.h"
+
+	.text
+
+	.globl _zimage_start
+_zimage_start:
+	FIXUP_ENDIAN
+	b _zimage_start_lib
diff --git a/arch/powerpc/boot/stdio.c b/arch/powerpc/boot/stdio.c
index 5b57800bbc6..a701261b178 100644
--- a/arch/powerpc/boot/stdio.c
+++ b/arch/powerpc/boot/stdio.c
@@ -21,6 +21,18 @@ size_t strnlen(const char * s, size_t count)
 	return sc - s;
 }
 
+#ifdef __powerpc64__
+
+# define do_div(n, base) ({						\
+	unsigned int __base = (base);					\
+	unsigned int __rem;						\
+	__rem = ((unsigned long long)(n)) % __base;			\
+	(n) = ((unsigned long long)(n)) / __base;			\
+	__rem;								\
+})
+
+#else
+
 extern unsigned int __div64_32(unsigned long long *dividend,
 			       unsigned int divisor);
 
@@ -39,6 +51,8 @@ extern unsigned int __div64_32(unsigned long long *dividend,
 	__rem;								\
  })
 
+#endif /* __powerpc64__ */
+
 static int skip_atoi(const char **s)
 {
 	int i, c;
diff --git a/arch/powerpc/boot/swab.h b/arch/powerpc/boot/swab.h
new file mode 100644
index 00000000000..d0e1431084c
--- /dev/null
+++ b/arch/powerpc/boot/swab.h
@@ -0,0 +1,29 @@
+#ifndef _PPC_BOOT_SWAB_H_
+#define _PPC_BOOT_SWAB_H_
+
+static inline u16 swab16(u16 x)
+{
+	return  ((x & (u16)0x00ffU) << 8) |
+		((x & (u16)0xff00U) >> 8);
+}
+
+static inline u32 swab32(u32 x)
+{
+	return  ((x & (u32)0x000000ffUL) << 24) |
+		((x & (u32)0x0000ff00UL) <<  8) |
+		((x & (u32)0x00ff0000UL) >>  8) |
+		((x & (u32)0xff000000UL) >> 24);
+}
+
+static inline u64 swab64(u64 x)
+{
+	return  (u64)((x & (u64)0x00000000000000ffULL) << 56) |
+		(u64)((x & (u64)0x000000000000ff00ULL) << 40) |
+		(u64)((x & (u64)0x0000000000ff0000ULL) << 24) |
+		(u64)((x & (u64)0x00000000ff000000ULL) <<  8) |
+		(u64)((x & (u64)0x000000ff00000000ULL) >>  8) |
+		(u64)((x & (u64)0x0000ff0000000000ULL) >> 24) |
+		(u64)((x & (u64)0x00ff000000000000ULL) >> 40) |
+		(u64)((x & (u64)0xff00000000000000ULL) >> 56);
+}
+#endif /* _PPC_BOOT_SWAB_H_ */
diff --git a/arch/powerpc/boot/treeboot-akebono.c b/arch/powerpc/boot/treeboot-akebono.c
new file mode 100644
index 00000000000..b73174c34fe
--- /dev/null
+++ b/arch/powerpc/boot/treeboot-akebono.c
@@ -0,0 +1,163 @@
+/*
+ * Copyright © 2013 Tony Breeds IBM Corporation
+ * Copyright © 2013 Alistair Popple IBM Corporation
+ *
+ * Based on earlier code:
+ *   Copyright (C) Paul Mackerras 1997.
+ *
+ *   Matt Porter <mporter@kernel.crashing.org>
+ *   Copyright 2002-2005 MontaVista Software Inc.
+ *
+ *   Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
+ *   Copyright (c) 2003, 2004 Zultys Technologies
+ *
+ *    Copyright 2007 David Gibson, IBM Corporation.
+ *    Copyright 2010 Ben. Herrenschmidt, IBM Corporation.
+ *    Copyright © 2011 David Kleikamp IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <stdarg.h>
+#include <stddef.h>
+#include "types.h"
+#include "elf.h"
+#include "string.h"
+#include "stdlib.h"
+#include "stdio.h"
+#include "page.h"
+#include "ops.h"
+#include "reg.h"
+#include "io.h"
+#include "dcr.h"
+#include "4xx.h"
+#include "44x.h"
+#include "libfdt.h"
+
+BSS_STACK(4096);
+
+#define SPRN_PIR	0x11E	/* Processor Indentification Register */
+#define USERDATA_LEN	256	/* Length of userdata passed in by PIBS */
+#define MAX_RANKS	0x4
+#define DDR3_MR0CF	0x80010011U
+#define CCTL0_MCO2	0x8000080FU
+#define CCTL0_MCO3	0x80000810U
+#define CCTL0_MCO4	0x80000811U
+#define CCTL0_MCO5	0x80000812U
+#define CCTL0_MCO6	0x80000813U
+
+static unsigned long long ibm_akebono_memsize;
+static long long unsigned mac_addr;
+
+static unsigned long long ibm_akebono_detect_memsize(void)
+{
+	u32 reg;
+	unsigned i;
+	unsigned long long memsize = 0;
+
+	for (i = 0; i < MAX_RANKS; i++) {
+		reg = mfdcrx(DDR3_MR0CF + i);
+
+		if (!(reg & 1))
+			continue;
+
+		reg &= 0x0000f000;
+		reg >>= 12;
+		memsize += (0x800000ULL << reg);
+	}
+
+	return memsize;
+}
+
+static void ibm_akebono_fixups(void)
+{
+	void *emac;
+	u32 reg;
+
+	dt_fixup_memory(0x0ULL,  ibm_akebono_memsize);
+
+	/* Fixup the SD timeout frequency */
+	mtdcrx(CCTL0_MCO4, 0x1);
+
+	/* Disable SD high-speed mode (which seems to be broken) */
+	reg = mfdcrx(CCTL0_MCO2) & ~0x2;
+	mtdcrx(CCTL0_MCO2, reg);
+
+	/* Set the MAC address */
+	emac = finddevice("/plb/opb/ethernet");
+	if (emac > 0) {
+		if (mac_addr)
+			setprop(emac, "local-mac-address",
+				((u8 *) &mac_addr) + 2 , 6);
+	}
+}
+
+void platform_init(char *userdata)
+{
+	unsigned long end_of_ram, avail_ram;
+	u32 pir_reg;
+	int node, size;
+	const u32 *timebase;
+	int len, i, userdata_len;
+	char *end;
+
+	userdata[USERDATA_LEN - 1] = '\0';
+	userdata_len = strlen(userdata);
+	for (i = 0; i < userdata_len - 15; i++) {
+		if (strncmp(&userdata[i], "local-mac-addr=", 15) == 0) {
+			if (i > 0 && userdata[i - 1] != ' ') {
+				/* We've only found a substring ending
+				 * with local-mac-addr so this isn't
+				 * our mac address. */
+				continue;
+			}
+
+			mac_addr = strtoull(&userdata[i + 15], &end, 16);
+
+			/* Remove the "local-mac-addr=<...>" from the kernel
+			 * command line, including the tailing space if
+			 * present. */
+			if (*end == ' ')
+				end++;
+
+			len = ((int) end) - ((int) &userdata[i]);
+			memmove(&userdata[i], end,
+				userdata_len - (len + i) + 1);
+			break;
+		}
+	}
+
+	loader_info.cmdline = userdata;
+	loader_info.cmdline_len = 256;
+
+	ibm_akebono_memsize = ibm_akebono_detect_memsize();
+	if (ibm_akebono_memsize >> 32)
+		end_of_ram = ~0UL;
+	else
+		end_of_ram = ibm_akebono_memsize;
+	avail_ram = end_of_ram - (unsigned long)_end;
+
+	simple_alloc_init(_end, avail_ram, 128, 64);
+	platform_ops.fixups = ibm_akebono_fixups;
+	platform_ops.exit = ibm44x_dbcr_reset;
+	pir_reg = mfspr(SPRN_PIR);
+
+	/* Make sure FDT blob is sane */
+	if (fdt_check_header(_dtb_start) != 0)
+		fatal("Invalid device tree blob\n");
+
+	node = fdt_node_offset_by_prop_value(_dtb_start, -1, "device_type",
+					     "cpu", sizeof("cpu"));
+	if (!node)
+		fatal("Cannot find cpu node\n");
+	timebase = fdt_getprop(_dtb_start, node, "timebase-frequency", &size);
+	if (timebase && (size == 4))
+		timebase_period_ns = 1000000000 / *timebase;
+
+	fdt_set_boot_cpuid_phys(_dtb_start, pir_reg);
+	fdt_init(_dtb_start);
+
+	serial_console_init();
+}
diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S
index 6636b1d7821..243b8497d58 100644
--- a/arch/powerpc/boot/util.S
+++ b/arch/powerpc/boot/util.S
@@ -45,7 +45,7 @@ udelay:
 	mfspr	r4,SPRN_PVR
 	srwi	r4,r4,16
 	cmpwi	0,r4,1		/* 601 ? */
-	bne	.udelay_not_601
+	bne	.Ludelay_not_601
 00:	li	r0,86	/* Instructions / microsecond? */
 	mtctr	r0
 10:	addi	r0,r0,0 /* NOP */
@@ -54,7 +54,7 @@ udelay:
 	bne	00b
 	blr
 
-.udelay_not_601:
+.Ludelay_not_601:
 	mulli	r4,r3,1000	/* nanoseconds */
 	/*  Change r4 to be the number of ticks using:
 	 *	(nanoseconds + (timebase_period_ns - 1 )) / timebase_period_ns
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index d27a25518b0..ae0f88ec4a3 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -40,6 +40,7 @@ cacheit=
 binary=
 gzip=.gz
 pie=
+format=
 
 # cross-compilation prefix
 CROSS=
@@ -136,6 +137,14 @@ if [ -z "$kernel" ]; then
     kernel=vmlinux
 fi
 
+elfformat="`${CROSS}objdump -p "$kernel" | grep 'file format' | awk '{print $4}'`"
+case "$elfformat" in
+    elf64-powerpcle)	format=elf64lppc	;;
+    elf64-powerpc)	format=elf32ppc	;;
+    elf32-powerpc)	format=elf32ppc	;;
+esac
+
+
 platformo=$object/"$platform".o
 lds=$object/zImage.lds
 ext=strip
@@ -152,8 +161,12 @@ of)
     make_space=n
     ;;
 pseries)
-    platformo="$object/of.o $object/epapr.o"
+    platformo="$object/pseries-head.o $object/of.o $object/epapr.o"
     link_address='0x4000000'
+    if [ "$format" != "elf32ppc" ]; then
+	link_address=
+	pie=-pie
+    fi
     make_space=n
     ;;
 maple)
@@ -257,6 +270,9 @@ gamecube|wii)
 treeboot-currituck)
     link_address='0x1000000'
     ;;
+treeboot-akebono)
+    link_address='0x1000000'
+    ;;
 treeboot-iss4xx-mpic)
     platformo="$object/treeboot-iss4xx.o"
     ;;
@@ -379,7 +395,7 @@ if [ "$platform" != "miboot" ]; then
     if [ -n "$link_address" ] ; then
         text_start="-Ttext $link_address"
     fi
-    ${CROSS}ld -m elf32ppc -T $lds $text_start $pie -o "$ofile" \
+    ${CROSS}ld -m $format -T $lds $text_start $pie -o "$ofile" \
 	$platformo $tmp $object/wrapper.a
     rm $tmp
 fi
diff --git a/arch/powerpc/boot/zImage.lds.S b/arch/powerpc/boot/zImage.lds.S
index 2bd8731f136..861e72109df 100644
--- a/arch/powerpc/boot/zImage.lds.S
+++ b/arch/powerpc/boot/zImage.lds.S
@@ -1,4 +1,10 @@
+#include <asm-generic/vmlinux.lds.h>
+
+#ifdef CONFIG_PPC64_BOOT_WRAPPER
+OUTPUT_ARCH(powerpc:common64)
+#else
 OUTPUT_ARCH(powerpc:common)
+#endif
 ENTRY(_zimage_start)
 EXTERN(_zimage_start)
 SECTIONS
@@ -16,7 +22,9 @@ SECTIONS
     *(.rodata*)
     *(.data*)
     *(.sdata*)
+#ifndef CONFIG_PPC64_BOOT_WRAPPER
     *(.got2)
+#endif
   }
   .dynsym : { *(.dynsym) }
   .dynstr : { *(.dynstr) }
@@ -27,7 +35,13 @@ SECTIONS
   }
   .hash : { *(.hash) }
   .interp : { *(.interp) }
-  .rela.dyn : { *(.rela*) }
+  .rela.dyn :
+  {
+#ifdef CONFIG_PPC64_BOOT_WRAPPER
+    __rela_dyn_start = .;
+#endif
+    *(.rela*)
+  }
 
   . = ALIGN(8);
   .kernel:dtb :
@@ -53,6 +67,15 @@ SECTIONS
     _initrd_end =  .;
   }
 
+#ifdef CONFIG_PPC64_BOOT_WRAPPER
+  .got :
+  {
+    __toc_start = .;
+    *(.got)
+    *(.toc)
+  }
+#endif
+
   . = ALIGN(4096);
   .bss       :
   {
diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig
new file mode 100644
index 00000000000..7e2530cd9d3
--- /dev/null
+++ b/arch/powerpc/configs/44x/akebono_defconfig
@@ -0,0 +1,148 @@
+CONFIG_44x=y
+CONFIG_SMP=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
+CONFIG_RD_XZ=y
+CONFIG_EXPERT=y
+CONFIG_KALLSYMS_ALL=y
+# CONFIG_SLUB_CPU_PARTIAL is not set
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_POWERNV_MSI is not set
+CONFIG_PPC_47x=y
+# CONFIG_EBONY is not set
+CONFIG_AKEBONO=y
+CONFIG_HIGHMEM=y
+CONFIG_HZ_100=y
+CONFIG_IRQ_ALL_CPUS=y
+# CONFIG_COMPACTION is not set
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE=""
+# CONFIG_SUSPEND is not set
+CONFIG_PCI_MSI=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_IPV6 is not set
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_CONNECTOR=y
+CONFIG_MTD=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_JEDECPROBE=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_PROC_DEVICETREE=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=35000
+# CONFIG_SCSI_PROC_FS is not set
+CONFIG_BLK_DEV_SD=y
+# CONFIG_SCSI_LOWLEVEL is not set
+# CONFIG_SATA_PMP is not set
+# CONFIG_ATA_SFF is not set
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ADAPTEC is not set
+# CONFIG_NET_VENDOR_ALTEON is not set
+# CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ATHEROS is not set
+# CONFIG_NET_CADENCE is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_BROCADE is not set
+# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_CISCO is not set
+# CONFIG_NET_VENDOR_DEC is not set
+# CONFIG_NET_VENDOR_DLINK is not set
+# CONFIG_NET_VENDOR_EMULEX is not set
+# CONFIG_NET_VENDOR_EXAR is not set
+# CONFIG_NET_VENDOR_HP is not set
+CONFIG_IBM_EMAC=y
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MELLANOX is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MYRI is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NVIDIA is not set
+# CONFIG_NET_VENDOR_OKI is not set
+# CONFIG_NET_VENDOR_QLOGIC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
+# CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SILAN is not set
+# CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_TEHUTI is not set
+# CONFIG_NET_VENDOR_TI is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_NET_VENDOR_XILINX is not set
+# CONFIG_KEYBOARD_ATKBD is not set
+# CONFIG_MOUSE_PS2 is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+CONFIG_SERIAL_8250=y
+# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C_CHARDEV=y
+# CONFIG_HWMON is not set
+CONFIG_THERMAL=y
+# CONFIG_USB_DEFAULT_PERSIST is not set
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_OHCI_HCD=y
+# CONFIG_USB_OHCI_HCD_PCI is not set
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_M41T80=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT3_FS_SECURITY=y
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY_USER is not set
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_CRAMFS=y
+# CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_NLS_DEFAULT="n"
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_XMON=y
+CONFIG_XMON_DEFAULT=y
+CONFIG_PPC_EARLY_DEBUG=y
+CONFIG_PPC_EARLY_DEBUG_44x_PHYSLOW=0x00010000
+CONFIG_PPC_EARLY_DEBUG_44x_PHYSHIGH=0x33f
+CONFIG_CRYPTO_PCBC=y
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_SHA1_PPC=y
+CONFIG_CRYPTO_DES=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+# CONFIG_CRYPTO_HW is not set
diff --git a/arch/powerpc/configs/85xx/kmp204x_defconfig b/arch/powerpc/configs/85xx/kmp204x_defconfig
new file mode 100644
index 00000000000..e9a81e5ba27
--- /dev/null
+++ b/arch/powerpc/configs/85xx/kmp204x_defconfig
@@ -0,0 +1,225 @@
+CONFIG_PPC_85xx=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_RELAY=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
+CONFIG_SLAB=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_MAC_PARTITION=y
+CONFIG_CORENET_GENERIC=y
+CONFIG_MPIC_MSGR=y
+CONFIG_HIGHMEM=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_BINFMT_MISC=m
+CONFIG_KEXEC=y
+CONFIG_FORCE_MAX_ZONEORDER=13
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+# CONFIG_PCIEASPM is not set
+CONFIG_PCI_MSI=y
+CONFIG_ADVANCED_OPTIONS=y
+CONFIG_LOWMEM_SIZE_BOOL=y
+CONFIG_LOWMEM_SIZE=0x20000000
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_XFRM_SUB_POLICY=y
+CONFIG_XFRM_STATISTICS=y
+CONFIG_NET_KEY=y
+CONFIG_NET_KEY_MIGRATE=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NET_IPIP=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_INET_AH=y
+CONFIG_INET_ESP=y
+CONFIG_INET_IPCOMP=y
+# CONFIG_INET_LRO is not set
+CONFIG_IPV6=y
+CONFIG_IP_SCTP=m
+CONFIG_TIPC=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_SCH_CBQ=y
+CONFIG_NET_SCH_HTB=y
+CONFIG_NET_SCH_HFSC=y
+CONFIG_NET_SCH_PRIO=y
+CONFIG_NET_SCH_MULTIQ=y
+CONFIG_NET_SCH_RED=y
+CONFIG_NET_SCH_SFQ=y
+CONFIG_NET_SCH_TEQL=y
+CONFIG_NET_SCH_TBF=y
+CONFIG_NET_SCH_GRED=y
+CONFIG_NET_CLS_BASIC=y
+CONFIG_NET_CLS_TCINDEX=y
+CONFIG_NET_CLS_U32=y
+CONFIG_CLS_U32_PERF=y
+CONFIG_CLS_U32_MARK=y
+CONFIG_NET_CLS_FLOW=y
+CONFIG_NET_CLS_CGROUP=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/mdev"
+CONFIG_DEVTMPFS=y
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_M25P80=y
+CONFIG_MTD_PHRAM=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_ECC_BCH=y
+CONFIG_MTD_NAND_FSL_ELBC=y
+CONFIG_MTD_UBI=y
+CONFIG_MTD_UBI_GLUEBI=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=2
+CONFIG_BLK_DEV_RAM_SIZE=2048
+CONFIG_EEPROM_AT24=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_ST=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_SCSI_MULTI_LUN=y
+CONFIG_SCSI_LOGGING=y
+CONFIG_SCSI_SYM53C8XX_2=y
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ADAPTEC is not set
+# CONFIG_NET_VENDOR_ALTEON is not set
+# CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_ATHEROS is not set
+# CONFIG_NET_CADENCE is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_BROCADE is not set
+# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_CISCO is not set
+# CONFIG_NET_VENDOR_DEC is not set
+# CONFIG_NET_VENDOR_DLINK is not set
+# CONFIG_NET_VENDOR_EMULEX is not set
+# CONFIG_NET_VENDOR_EXAR is not set
+CONFIG_FSL_PQ_MDIO=y
+CONFIG_FSL_XGMAC_MDIO=y
+# CONFIG_NET_VENDOR_HP is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MELLANOX is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROCHIP is not set
+# CONFIG_NET_VENDOR_MYRI is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NVIDIA is not set
+# CONFIG_NET_VENDOR_OKI is not set
+# CONFIG_NET_PACKET_ENGINE is not set
+# CONFIG_NET_VENDOR_QLOGIC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
+# CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SILAN is not set
+# CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_TEHUTI is not set
+# CONFIG_NET_VENDOR_TI is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_NET_VENDOR_XILINX is not set
+CONFIG_MARVELL_PHY=y
+CONFIG_VITESSE_PHY=y
+CONFIG_FIXED_PHY=y
+# CONFIG_WLAN is not set
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_SERIO_LIBPS2=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_PPC_EPAPR_HV_BYTECHAN=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_NVRAM=y
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_MUX=y
+CONFIG_I2C_MUX_PCA954x=y
+CONFIG_I2C_MPC=y
+CONFIG_SPI=y
+CONFIG_SPI_FSL_SPI=y
+CONFIG_SPI_FSL_ESPI=y
+CONFIG_SPI_SPIDEV=m
+CONFIG_PTP_1588_CLOCK=y
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_EDAC=y
+CONFIG_EDAC_MM_EDAC=y
+CONFIG_EDAC_MPC85XX=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_DS3232=y
+CONFIG_RTC_DRV_CMOS=y
+CONFIG_UIO=y
+CONFIG_STAGING=y
+# CONFIG_NET_VENDOR_SILICOM is not set
+CONFIG_CLK_PPC_CORENET=y
+CONFIG_EXT2_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_UBIFS_FS=y
+CONFIG_CRAMFS=y
+CONFIG_SQUASHFS=y
+CONFIG_SQUASHFS_XZ=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_UTF8=m
+CONFIG_CRC_ITU_T=m
+CONFIG_DEBUG_INFO=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_SCHEDSTATS=y
+CONFIG_RCU_TRACE=y
+CONFIG_UPROBE_EVENT=y
+CONFIG_CRYPTO_NULL=y
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_MD4=y
+CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_SHA512=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRYPTO_DEV_FSL_CAAM=y
diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig
deleted file mode 100644
index 4f35fc46238..00000000000
--- a/arch/powerpc/configs/chroma_defconfig
+++ /dev/null
@@ -1,307 +0,0 @@
-CONFIG_PPC64=y
-CONFIG_PPC_BOOK3E_64=y
-# CONFIG_VIRT_CPU_ACCOUNTING_NATIVE is not set
-CONFIG_SMP=y
-CONFIG_NR_CPUS=256
-CONFIG_EXPERIMENTAL=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_TASKSTATS=y
-CONFIG_TASK_DELAY_ACCT=y
-CONFIG_TASK_XACCT=y
-CONFIG_TASK_IO_ACCOUNTING=y
-CONFIG_AUDIT=y
-CONFIG_AUDITSYSCALL=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=19
-CONFIG_CGROUPS=y
-CONFIG_CGROUP_DEVICE=y
-CONFIG_CPUSETS=y
-CONFIG_CGROUP_CPUACCT=y
-CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEMCG=y
-CONFIG_CGROUP_MEMCG_SWAP=y
-CONFIG_NAMESPACES=y
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE=""
-CONFIG_RD_BZIP2=y
-CONFIG_RD_LZMA=y
-CONFIG_INITRAMFS_COMPRESSION_GZIP=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_EMBEDDED=y
-CONFIG_PERF_EVENTS=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=y
-CONFIG_KPROBES=y
-CONFIG_MODULES=y
-CONFIG_MODULE_FORCE_LOAD=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_SCOM_DEBUGFS=y
-CONFIG_PPC_A2_DD2=y
-CONFIG_KVM_GUEST=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_HZ_100=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_BINFMT_MISC=y
-CONFIG_NUMA=y
-# CONFIG_MIGRATION is not set
-CONFIG_PPC_64K_PAGES=y
-CONFIG_SCHED_SMT=y
-CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE=""
-# CONFIG_SECCOMP is not set
-CONFIG_PCIEPORTBUS=y
-# CONFIG_PCIEASPM is not set
-CONFIG_PCI_MSI=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_XFRM_SUB_POLICY=y
-CONFIG_XFRM_STATISTICS=y
-CONFIG_NET_KEY=m
-CONFIG_NET_KEY_MIGRATE=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_ADVANCED_ROUTER=y
-CONFIG_IP_ROUTE_MULTIPATH=y
-CONFIG_IP_ROUTE_VERBOSE=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_NET_IPIP=y
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_IPCOMP=m
-CONFIG_IPV6=y
-CONFIG_IPV6_PRIVACY=y
-CONFIG_IPV6_ROUTER_PREF=y
-CONFIG_IPV6_ROUTE_INFO=y
-CONFIG_IPV6_OPTIMISTIC_DAD=y
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_IPV6_MIP6=y
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=y
-CONFIG_IPV6_TUNNEL=y
-CONFIG_IPV6_MULTIPLE_TABLES=y
-CONFIG_IPV6_SUBTREES=y
-CONFIG_IPV6_MROUTE=y
-CONFIG_IPV6_PIMSM_V2=y
-CONFIG_NETFILTER=y
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_UDPLITE=m
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NF_CT_NETLINK=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFLOG=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
-CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
-CONFIG_NETFILTER_XT_MATCH_DSCP=m
-CONFIG_NETFILTER_XT_MATCH_ESP=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_HELPER=m
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
-CONFIG_NETFILTER_XT_MATCH_OWNER=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_QUOTA=m
-CONFIG_NETFILTER_XT_MATCH_RATEEST=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_SCTP=m
-CONFIG_NETFILTER_XT_MATCH_STATE=m
-CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_TIME=m
-CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_IP_NF_QUEUE=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_AH=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_TARGET_LOG=m
-CONFIG_IP_NF_TARGET_ULOG=m
-CONFIG_NF_NAT=m
-CONFIG_IP_NF_TARGET_MASQUERADE=m
-CONFIG_IP_NF_TARGET_NETMAP=m
-CONFIG_IP_NF_TARGET_REDIRECT=m
-CONFIG_NET_TCPPROBE=y
-# CONFIG_WIRELESS is not set
-CONFIG_NET_9P=y
-CONFIG_NET_9P_DEBUG=y
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_DEVTMPFS=y
-CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_BLOCK=y
-CONFIG_MTD_CFI=y
-CONFIG_MTD_CFI_ADV_OPTIONS=y
-CONFIG_MTD_CFI_LE_BYTE_SWAP=y
-CONFIG_MTD_CFI_INTELEXT=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_CFI_STAA=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_PROC_DEVICETREE=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=y
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=65536
-CONFIG_CDROM_PKTCDVD=y
-CONFIG_MISC_DEVICES=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_BLK_DEV_SR_VENDOR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_MULTI_LUN=y
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_SPI_ATTRS=y
-CONFIG_SCSI_FC_ATTRS=y
-CONFIG_SCSI_ISCSI_ATTRS=m
-CONFIG_SCSI_SAS_ATTRS=m
-CONFIG_SCSI_SRP_ATTRS=y
-CONFIG_ATA=y
-CONFIG_SATA_AHCI=y
-CONFIG_SATA_SIL24=y
-CONFIG_SATA_MV=y
-CONFIG_SATA_SIL=y
-CONFIG_PATA_CMD64X=y
-CONFIG_PATA_MARVELL=y
-CONFIG_PATA_SIL680=y
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=y
-CONFIG_BLK_DEV_DM=y
-CONFIG_DM_CRYPT=y
-CONFIG_DM_SNAPSHOT=y
-CONFIG_DM_MIRROR=y
-CONFIG_DM_ZERO=y
-CONFIG_DM_UEVENT=y
-CONFIG_NETDEVICES=y
-CONFIG_TUN=y
-CONFIG_E1000E=y
-CONFIG_TIGON3=y
-# CONFIG_WLAN is not set
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_HW_RANDOM=y
-CONFIG_RAW_DRIVER=y
-CONFIG_MAX_RAW_DEVS=1024
-# CONFIG_HWMON is not set
-# CONFIG_VGA_ARB is not set
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EDAC=y
-CONFIG_EDAC_MM_EDAC=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_DS1511=y
-CONFIG_RTC_DRV_DS1553=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
-CONFIG_EXT4_FS=y
-# CONFIG_DNOTIFY is not set
-CONFIG_FUSE_FS=y
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_ZISOFS=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_CONFIGFS_FS=m
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_NFS_V4_1=y
-CONFIG_ROOT_NFS=y
-CONFIG_CIFS=y
-CONFIG_CIFS_WEAK_PW_HASH=y
-CONFIG_CIFS_XATTR=y
-CONFIG_CIFS_POSIX=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_CRC_CCITT=m
-CONFIG_CRC_T10DIF=y
-CONFIG_LIBCRC32C=m
-CONFIG_PRINTK_TIME=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_STRIP_ASM_SYMS=y
-CONFIG_DETECT_HUNG_TASK=y
-# CONFIG_SCHED_DEBUG is not set
-CONFIG_DEBUG_INFO=y
-CONFIG_FTRACE_SYSCALLS=y
-CONFIG_PPC_EMULATED_STATS=y
-CONFIG_XMON=y
-CONFIG_XMON_DEFAULT=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
-CONFIG_PPC_EARLY_DEBUG=y
-CONFIG_KEYS_DEBUG_PROC_KEYS=y
-CONFIG_CRYPTO_NULL=m
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_CCM=m
-CONFIG_CRYPTO_GCM=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_SHA256=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_AES=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAST5=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_LZO=m
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_VIRTUALIZATION=y
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index bbd794deb6e..c19ff057d0f 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -72,6 +72,7 @@ CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_MTD_M25P80=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index 19f0fbe5ba4..55765c8cb08 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -32,7 +32,6 @@ CONFIG_P1010_RDB=y
 CONFIG_P1022_DS=y
 CONFIG_P1022_RDK=y
 CONFIG_P1023_RDB=y
-CONFIG_P1023_RDS=y
 CONFIG_SOCRATES=y
 CONFIG_KSI8560=y
 CONFIG_XES_MPC85xx=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index 062312e1fe1..5c6ecdc0f70 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -35,7 +35,6 @@ CONFIG_P1010_RDB=y
 CONFIG_P1022_DS=y
 CONFIG_P1022_RDK=y
 CONFIG_P1023_RDB=y
-CONFIG_P1023_RDS=y
 CONFIG_SOCRATES=y
 CONFIG_KSI8560=y
 CONFIG_XES_MPC85xx=y
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 97e02f985df..840a5509b3f 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -42,18 +42,61 @@ void __patch_exception(int exc, unsigned long addr);
 } while (0)
 #endif
 
+#define OP_RT_RA_MASK	0xffff0000UL
+#define LIS_R2		0x3c020000UL
+#define ADDIS_R2_R12	0x3c4c0000UL
+#define ADDI_R2_R2	0x38420000UL
+
 static inline unsigned long ppc_function_entry(void *func)
 {
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+	u32 *insn = func;
+
+	/*
+	 * A PPC64 ABIv2 function may have a local and a global entry
+	 * point. We need to use the local entry point when patching
+	 * functions, so identify and step over the global entry point
+	 * sequence.
+	 *
+	 * The global entry point sequence is always of the form:
+	 *
+	 * addis r2,r12,XXXX
+	 * addi  r2,r2,XXXX
+	 *
+	 * A linker optimisation may convert the addis to lis:
+	 *
+	 * lis   r2,XXXX
+	 * addi  r2,r2,XXXX
+	 */
+	if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) ||
+	     ((*insn & OP_RT_RA_MASK) == LIS_R2)) &&
+	    ((*(insn+1) & OP_RT_RA_MASK) == ADDI_R2_R2))
+		return (unsigned long)(insn + 2);
+	else
+		return (unsigned long)func;
+#else
 	/*
-	 * On PPC64 the function pointer actually points to the function's
-	 * descriptor. The first entry in the descriptor is the address
-	 * of the function text.
+	 * On PPC64 ABIv1 the function pointer actually points to the
+	 * function's descriptor. The first entry in the descriptor is the
+	 * address of the function text.
 	 */
 	return ((func_descr_t *)func)->entry;
+#endif
 #else
 	return (unsigned long)func;
 #endif
 }
 
+static inline unsigned long ppc_global_function_entry(void *func)
+{
+#if defined(CONFIG_PPC64) && defined(_CALL_ELF) && _CALL_ELF == 2
+	/* PPC64 ABIv2 the global entry point is at the address */
+	return (unsigned long)func;
+#else
+	/* All other cases there is no change vs ppc_function_entry() */
+	return ppc_function_entry(func);
+#endif
+}
+
 #endif /* _ASM_POWERPC_CODE_PATCHING_H */
diff --git a/arch/powerpc/include/asm/context_tracking.h b/arch/powerpc/include/asm/context_tracking.h
index b6f5a33b8ee..40014921fff 100644
--- a/arch/powerpc/include/asm/context_tracking.h
+++ b/arch/powerpc/include/asm/context_tracking.h
@@ -2,9 +2,9 @@
 #define _ASM_POWERPC_CONTEXT_TRACKING_H
 
 #ifdef CONFIG_CONTEXT_TRACKING
-#define SCHEDULE_USER bl	.schedule_user
+#define SCHEDULE_USER bl	schedule_user
 #else
-#define SCHEDULE_USER bl	.schedule
+#define SCHEDULE_USER bl	schedule
 #endif
 
 #endif
diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h
index f42e9baf3a4..7c8608b0969 100644
--- a/arch/powerpc/include/asm/cpm2.h
+++ b/arch/powerpc/include/asm/cpm2.h
@@ -489,7 +489,6 @@ typedef struct scc_trans {
 #define FCC_GFMR_TCI		((uint)0x20000000)
 #define FCC_GFMR_TRX		((uint)0x10000000)
 #define FCC_GFMR_TTX		((uint)0x08000000)
-#define FCC_GFMR_TTX		((uint)0x08000000)
 #define FCC_GFMR_CDP		((uint)0x04000000)
 #define FCC_GFMR_CTSP		((uint)0x02000000)
 #define FCC_GFMR_CDS		((uint)0x01000000)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index bc2347774f0..0fdd7eece6d 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -447,6 +447,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
 	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
 #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
+#define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index ac3eedb9b74..2bf8e9307be 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -18,10 +18,12 @@
 
 #ifdef CONFIG_SMP
 extern int threads_per_core;
+extern int threads_per_subcore;
 extern int threads_shift;
 extern cpumask_t threads_core_mask;
 #else
 #define threads_per_core	1
+#define threads_per_subcore	1
 #define threads_shift		0
 #define threads_core_mask	(CPU_MASK_CPU0)
 #endif
@@ -74,6 +76,11 @@ static inline int cpu_thread_in_core(int cpu)
 	return cpu & (threads_per_core - 1);
 }
 
+static inline int cpu_thread_in_subcore(int cpu)
+{
+	return cpu & (threads_per_subcore - 1);
+}
+
 static inline int cpu_first_thread_sibling(int cpu)
 {
 	return cpu & ~(threads_per_core - 1);
diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
index d2516308ed1..a954e497504 100644
--- a/arch/powerpc/include/asm/debug.h
+++ b/arch/powerpc/include/asm/debug.h
@@ -46,7 +46,8 @@ static inline int debugger_break_match(struct pt_regs *regs) { return 0; }
 static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; }
 #endif
 
-int set_breakpoint(struct arch_hw_breakpoint *brk);
+void set_breakpoint(struct arch_hw_breakpoint *brk);
+void __set_breakpoint(struct arch_hw_breakpoint *brk);
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 extern void do_send_trap(struct pt_regs *regs, unsigned long address,
 			 unsigned long error_code, int signal_code, int brkpt);
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index d4dd41fb951..fab7743c264 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -32,6 +32,22 @@ struct device_node;
 
 #ifdef CONFIG_EEH
 
+/* EEH subsystem flags */
+#define EEH_ENABLED		0x1	/* EEH enabled		*/
+#define EEH_FORCE_DISABLED	0x2	/* EEH disabled		*/
+#define EEH_PROBE_MODE_DEV	0x4	/* From PCI device	*/
+#define EEH_PROBE_MODE_DEVTREE	0x8	/* From device tree	*/
+
+/*
+ * Delay for PE reset, all in ms
+ *
+ * PCI specification has reset hold time of 100 milliseconds.
+ * We have 250 milliseconds here. The PCI bus settlement time
+ * is specified as 1.5 seconds and we have 1.8 seconds.
+ */
+#define EEH_PE_RST_HOLD_TIME		250
+#define EEH_PE_RST_SETTLE_TIME		1800
+
 /*
  * The struct is used to trace PE related EEH functionality.
  * In theory, there will have one instance of the struct to
@@ -53,7 +69,7 @@ struct device_node;
 
 #define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
-#define EEH_PE_PHB_DEAD		(1 << 2)	/* Dead PHB		*/
+#define EEH_PE_RESET		(1 << 2)	/* PE reset in progress	*/
 
 #define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
 
@@ -92,6 +108,7 @@ struct eeh_pe {
 
 #define EEH_DEV_NO_HANDLER	(1 << 8)	/* No error handler	*/
 #define EEH_DEV_SYSFS		(1 << 9)	/* Sysfs created	*/
+#define EEH_DEV_REMOVED		(1 << 10)	/* Removed permanently	*/
 
 struct eeh_dev {
 	int mode;			/* EEH mode			*/
@@ -99,7 +116,9 @@ struct eeh_dev {
 	int config_addr;		/* Config address		*/
 	int pe_config_addr;		/* PE config address		*/
 	u32 config_space[16];		/* Saved PCI config space	*/
-	u8 pcie_cap;			/* Saved PCIe capability	*/
+	int pcix_cap;			/* Saved PCIx capability	*/
+	int pcie_cap;			/* Saved PCIe capability	*/
+	int aer_cap;			/* Saved AER capability		*/
 	struct eeh_pe *pe;		/* Associated PE		*/
 	struct list_head list;		/* Form link list in the PE	*/
 	struct pci_controller *phb;	/* Associated PHB		*/
@@ -171,37 +190,40 @@ struct eeh_ops {
 	int (*restore_config)(struct device_node *dn);
 };
 
+extern int eeh_subsystem_flags;
 extern struct eeh_ops *eeh_ops;
-extern bool eeh_subsystem_enabled;
 extern raw_spinlock_t confirm_error_lock;
-extern int eeh_probe_mode;
 
 static inline bool eeh_enabled(void)
 {
-	return eeh_subsystem_enabled;
+	if ((eeh_subsystem_flags & EEH_FORCE_DISABLED) ||
+	    !(eeh_subsystem_flags & EEH_ENABLED))
+		return false;
+
+	return true;
 }
 
 static inline void eeh_set_enable(bool mode)
 {
-	eeh_subsystem_enabled = mode;
+	if (mode)
+		eeh_subsystem_flags |= EEH_ENABLED;
+	else
+		eeh_subsystem_flags &= ~EEH_ENABLED;
 }
 
-#define EEH_PROBE_MODE_DEV	(1<<0)	/* From PCI device	*/
-#define EEH_PROBE_MODE_DEVTREE	(1<<1)	/* From device tree	*/
-
 static inline void eeh_probe_mode_set(int flag)
 {
-	eeh_probe_mode = flag;
+	eeh_subsystem_flags |= flag;
 }
 
 static inline int eeh_probe_mode_devtree(void)
 {
-	return (eeh_probe_mode == EEH_PROBE_MODE_DEVTREE);
+	return (eeh_subsystem_flags & EEH_PROBE_MODE_DEVTREE);
 }
 
 static inline int eeh_probe_mode_dev(void)
 {
-	return (eeh_probe_mode == EEH_PROBE_MODE_DEV);
+	return (eeh_subsystem_flags & EEH_PROBE_MODE_DEV);
 }
 
 static inline void eeh_serialize_lock(unsigned long *flags)
@@ -232,6 +254,7 @@ void *eeh_pe_traverse(struct eeh_pe *root,
 void *eeh_pe_dev_traverse(struct eeh_pe *root,
 		eeh_traverse_func fn, void *flag);
 void eeh_pe_restore_bars(struct eeh_pe *pe);
+const char *eeh_pe_loc_get(struct eeh_pe *pe);
 struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
 
 void *eeh_dev_init(struct device_node *dn, void *data);
diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h
index 89d5670b2ee..1e551a2d6f8 100644
--- a/arch/powerpc/include/asm/eeh_event.h
+++ b/arch/powerpc/include/asm/eeh_event.h
@@ -33,7 +33,7 @@ struct eeh_event {
 
 int eeh_event_init(void);
 int eeh_send_failure_event(struct eeh_pe *pe);
-void eeh_remove_event(struct eeh_pe *pe);
+void eeh_remove_event(struct eeh_pe *pe, bool force);
 void eeh_handle_event(struct eeh_pe *pe);
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 935b5e7a143..888d8f3f252 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -90,6 +90,8 @@ typedef elf_vrregset_t elf_fpxregset_t;
 do {								\
 	if (((ex).e_flags & 0x3) == 2)				\
 		set_thread_flag(TIF_ELF2ABI);			\
+	else							\
+		clear_thread_flag(TIF_ELF2ABI);			\
 	if ((ex).e_ident[EI_CLASS] == ELFCLASS32)		\
 		set_thread_flag(TIF_32BIT);			\
 	else							\
diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h
index a563d9afd17..a8b52b61043 100644
--- a/arch/powerpc/include/asm/exception-64e.h
+++ b/arch/powerpc/include/asm/exception-64e.h
@@ -174,10 +174,10 @@ exc_##label##_book3e:
 	mtlr	r16;
 #define TLB_MISS_STATS_D(name)						    \
 	addi	r9,r13,MMSTAT_DSTATS+name;				    \
-	bl	.tlb_stat_inc;
+	bl	tlb_stat_inc;
 #define TLB_MISS_STATS_I(name)						    \
 	addi	r9,r13,MMSTAT_ISTATS+name;				    \
-	bl	.tlb_stat_inc;
+	bl	tlb_stat_inc;
 #define TLB_MISS_STATS_X(name)						    \
 	ld	r8,PACA_EXTLB+EX_TLB_ESR(r13);				    \
 	cmpdi	cr2,r8,-1;						    \
@@ -185,7 +185,7 @@ exc_##label##_book3e:
 	addi	r9,r13,MMSTAT_DSTATS+name;				    \
 	b	62f;							    \
 61:	addi	r9,r13,MMSTAT_ISTATS+name;				    \
-62:	bl	.tlb_stat_inc;
+62:	bl	tlb_stat_inc;
 #define TLB_MISS_STATS_SAVE_INFO					    \
 	std	r14,EX_TLB_ESR(r12);	/* save ESR */
 #define TLB_MISS_STATS_SAVE_INFO_BOLTED					    \
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index aeaa56cd9b5..8f35cd7d59c 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -517,7 +517,7 @@ label##_relon_hv:							\
 #define DISABLE_INTS	RECONCILE_IRQ_STATE(r10,r11)
 
 #define ADD_NVGPRS				\
-	bl	.save_nvgprs
+	bl	save_nvgprs
 
 #define RUNLATCH_ON				\
 BEGIN_FTR_SECTION				\
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 169d039ed40..e3661872fbe 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -61,6 +61,7 @@ struct dyn_arch_ftrace {
 #endif
 
 #if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64) && !defined(__ASSEMBLY__)
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
 static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
 {
@@ -72,6 +73,7 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name
 	 */
 	return !strcmp(sym + 4, name + 3);
 }
+#endif
 #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 && !__ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_FTRACE */
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index eb0f4ac75c4..ac6432d9be4 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -79,7 +79,7 @@ static inline void hw_breakpoint_disable(void)
 	brk.address = 0;
 	brk.type = 0;
 	brk.len = 0;
-	set_breakpoint(&brk);
+	__set_breakpoint(&brk);
 }
 extern void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs);
 
diff --git a/arch/powerpc/include/asm/irqflags.h b/arch/powerpc/include/asm/irqflags.h
index f51a5580bfd..e20eb95429a 100644
--- a/arch/powerpc/include/asm/irqflags.h
+++ b/arch/powerpc/include/asm/irqflags.h
@@ -20,9 +20,9 @@
  */
 #define TRACE_WITH_FRAME_BUFFER(func)		\
 	mflr	r0;				\
-	stdu	r1, -32(r1);			\
+	stdu	r1, -STACK_FRAME_OVERHEAD(r1);	\
 	std	r0, 16(r1);			\
-	stdu	r1, -32(r1);			\
+	stdu	r1, -STACK_FRAME_OVERHEAD(r1);	\
 	bl func;				\
 	ld	r1, 0(r1);			\
 	ld	r1, 0(r1);
@@ -36,8 +36,8 @@
  * have to call a C function so call a wrapper that saves all the
  * C-clobbered registers.
  */
-#define TRACE_ENABLE_INTS	TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_on)
-#define TRACE_DISABLE_INTS	TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_off)
+#define TRACE_ENABLE_INTS	TRACE_WITH_FRAME_BUFFER(trace_hardirqs_on)
+#define TRACE_DISABLE_INTS	TRACE_WITH_FRAME_BUFFER(trace_hardirqs_off)
 
 /*
  * This is used by assembly code to soft-disable interrupts first and
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 7b6feab6fd2..af15d4d8d60 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -30,6 +30,7 @@
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
 #include <asm/probes.h>
+#include <asm/code-patching.h>
 
 #define  __ARCH_WANT_KPROBES_INSN_SLOT
 
@@ -56,9 +57,9 @@ typedef ppc_opcode_t kprobe_opcode_t;
 		if ((colon = strchr(name, ':')) != NULL) {		\
 			colon++;					\
 			if (*colon != '\0' && *colon != '.')		\
-				addr = *(kprobe_opcode_t **)addr;	\
+				addr = (kprobe_opcode_t *)ppc_function_entry(addr); \
 		} else if (name[0] != '.')				\
-			addr = *(kprobe_opcode_t **)addr;		\
+			addr = (kprobe_opcode_t *)ppc_function_entry(addr); \
 	} else {							\
 		char dot_name[KSYM_NAME_LEN];				\
 		dot_name[0] = '.';					\
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index fddb72b48ce..d645428a65a 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -198,8 +198,10 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 	return rb;
 }
 
-static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l,
+					     bool is_base_size)
 {
+
 	int size, a_psize;
 	/* Look at the 8 bit LP value */
 	unsigned int lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1);
@@ -214,14 +216,27 @@ static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
 				continue;
 
 			a_psize = __hpte_actual_psize(lp, size);
-			if (a_psize != -1)
+			if (a_psize != -1) {
+				if (is_base_size)
+					return 1ul << mmu_psize_defs[size].shift;
 				return 1ul << mmu_psize_defs[a_psize].shift;
+			}
 		}
 
 	}
 	return 0;
 }
 
+static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 0);
+}
+
+static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 1);
+}
+
 static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize)
 {
 	return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 4a7cc453be0..9c89cdd067a 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -337,6 +337,10 @@ static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
 	vcpu->kvm->arch.kvm_ops->fast_vcpu_kick(vcpu);
 }
 
+extern void kvm_hv_vm_activated(void);
+extern void kvm_hv_vm_deactivated(void);
+extern bool kvm_hv_mode_active(void);
+
 #else
 static inline void __init kvm_cma_reserve(void)
 {}
@@ -356,6 +360,9 @@ static inline void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu)
 {
 	kvm_vcpu_kick(vcpu);
 }
+
+static inline bool kvm_hv_mode_active(void)		{ return false; }
+
 #endif
 
 #ifdef CONFIG_KVM_XICS
diff --git a/arch/powerpc/include/asm/linkage.h b/arch/powerpc/include/asm/linkage.h
index b36f650a13f..e3ad5c72724 100644
--- a/arch/powerpc/include/asm/linkage.h
+++ b/arch/powerpc/include/asm/linkage.h
@@ -2,6 +2,7 @@
 #define _ASM_POWERPC_LINKAGE_H
 
 #ifdef CONFIG_PPC64
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 #define cond_syscall(x) \
 	asm ("\t.weak " #x "\n\t.set " #x ", sys_ni_syscall\n"		\
 	     "\t.weak ." #x "\n\t.set ." #x ", .sys_ni_syscall\n")
@@ -9,5 +10,6 @@
 	asm ("\t.globl " #alias "\n\t.set " #alias ", " #name "\n"	\
 	     "\t.globl ." #alias "\n\t.set ." #alias ", ." #name)
 #endif
+#endif
 
 #endif	/* _ASM_POWERPC_LINKAGE_H */
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 5b6c03f1058..f92b0b54e92 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -98,6 +98,9 @@ struct machdep_calls {
 	void		(*iommu_save)(void);
 	void		(*iommu_restore)(void);
 #endif
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+	unsigned long	(*memory_block_size)(void);
+#endif
 #endif /* CONFIG_PPC64 */
 
 	void		(*pci_dma_dev_setup)(struct pci_dev *dev);
@@ -113,6 +116,8 @@ struct machdep_calls {
 	/* Optional, may be NULL. */
 	void		(*show_cpuinfo)(struct seq_file *m);
 	void		(*show_percpuinfo)(struct seq_file *m, int i);
+	/* Returns the current operating frequency of "cpu" in Hz */
+	unsigned long  	(*get_proc_freq)(unsigned int cpu);
 
 	void		(*init_IRQ)(void);
 
@@ -241,6 +246,9 @@ struct machdep_calls {
 	/* Called during PCI resource reassignment */
 	resource_size_t (*pcibios_window_alignment)(struct pci_bus *, unsigned long type);
 
+	/* Reset the secondary bus of bridge */
+	void  (*pcibios_reset_secondary_bus)(struct pci_dev *dev);
+
 	/* Called to shutdown machine specific hardware not already controlled
 	 * by other drivers.
 	 */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 901dac6b6cb..d0918e09557 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -223,10 +223,6 @@ typedef struct {
 	unsigned int	id;
 	unsigned int	active;
 	unsigned long	vdso_base;
-#ifdef CONFIG_PPC_ICSWX
-	struct spinlock *cop_lockp;	/* guard cop related stuff */
-	unsigned long acop;		/* mask of enabled coprocessor types */
-#endif /* CONFIG_PPC_ICSWX */
 #ifdef CONFIG_PPC_MM_SLICES
 	u64 low_slices_psize;   /* SLB page size encodings */
 	u64 high_slices_psize;  /* 4 bits per slice for now */
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 807014dde82..c2b4dcf23d0 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -22,6 +22,7 @@
  */
 #include <asm/pgtable-ppc64.h>
 #include <asm/bug.h>
+#include <asm/processor.h>
 
 /*
  * Segment table
@@ -496,7 +497,7 @@ extern void slb_set_size(u16 size);
  */
 struct subpage_prot_table {
 	unsigned long maxaddr;	/* only addresses < this are protected */
-	unsigned int **protptrs[2];
+	unsigned int **protptrs[(TASK_SIZE_USER64 >> 43)];
 	unsigned int *low_prot[4];
 };
 
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index f8d1d6dcf7d..e61f24ed4e6 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -19,8 +19,7 @@
 #define MMU_FTR_TYPE_40x		ASM_CONST(0x00000004)
 #define MMU_FTR_TYPE_44x		ASM_CONST(0x00000008)
 #define MMU_FTR_TYPE_FSL_E		ASM_CONST(0x00000010)
-#define MMU_FTR_TYPE_3E			ASM_CONST(0x00000020)
-#define MMU_FTR_TYPE_47x		ASM_CONST(0x00000040)
+#define MMU_FTR_TYPE_47x		ASM_CONST(0x00000020)
 
 /*
  * This is individual features
@@ -106,13 +105,6 @@
 				MMU_FTR_CI_LARGE_PAGE
 #define MMU_FTRS_PA6T		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
 				MMU_FTR_CI_LARGE_PAGE | MMU_FTR_NO_SLBIE_B
-#define MMU_FTRS_A2		MMU_FTR_TYPE_3E | MMU_FTR_USE_TLBILX | \
-				MMU_FTR_USE_TLBIVAX_BCAST | \
-				MMU_FTR_LOCK_BCAST_INVAL | \
-				MMU_FTR_USE_TLBRSRV | \
-				MMU_FTR_USE_PAIRED_MAS | \
-				MMU_FTR_TLBIEL | \
-				MMU_FTR_16M_PAGE
 #ifndef __ASSEMBLY__
 #include <asm/cputable.h>
 
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index 49fa55bfbac..dcfcad139bc 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -35,6 +35,7 @@ struct mod_arch_specific {
 #ifdef __powerpc64__
 	unsigned int stubs_section;	/* Index of stubs section in module */
 	unsigned int toc_section;	/* What section is the TOC? */
+	bool toc_fixed;			/* Have we fixed up .TOC.? */
 #ifdef CONFIG_DYNAMIC_FTRACE
 	unsigned long toc;
 	unsigned long tramp;
@@ -77,6 +78,9 @@ struct mod_arch_specific {
 #    endif	/* MODULE */
 #endif
 
+bool is_module_trampoline(u32 *insns);
+int module_trampoline_target(struct module *mod, u32 *trampoline,
+			     unsigned long *target);
 
 struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 66ad7a74116..0da1dbd42e0 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -12,27 +12,7 @@
 #ifndef __OPAL_H
 #define __OPAL_H
 
-/****** Takeover interface ********/
-
-/* PAPR H-Call used to querty the HAL existence and/or instanciate
- * it from within pHyp (tech preview only).
- *
- * This is exclusively used in prom_init.c
- */
-
 #ifndef __ASSEMBLY__
-
-struct opal_takeover_args {
-	u64	k_image;		/* r4 */
-	u64	k_size;			/* r5 */
-	u64	k_entry;		/* r6 */
-	u64	k_entry2;		/* r7 */
-	u64	hal_addr;		/* r8 */
-	u64	rd_image;		/* r9 */
-	u64	rd_size;		/* r10 */
-	u64	rd_loc;			/* r11 */
-};
-
 /*
  * SG entry
  *
@@ -55,15 +35,6 @@ struct opal_sg_list {
 /* We calculate number of sg entries based on PAGE_SIZE */
 #define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry))
 
-extern long opal_query_takeover(u64 *hal_size, u64 *hal_align);
-
-extern long opal_do_takeover(struct opal_takeover_args *args);
-
-struct rtas_args;
-extern int opal_enter_rtas(struct rtas_args *args,
-			   unsigned long data,
-			   unsigned long entry);
-
 #endif /* __ASSEMBLY__ */
 
 /****** OPAL APIs ******/
@@ -154,6 +125,7 @@ extern int opal_enter_rtas(struct rtas_args *args,
 #define OPAL_LPC_READ				67
 #define OPAL_LPC_WRITE				68
 #define OPAL_RETURN_CPU				69
+#define OPAL_REINIT_CPUS			70
 #define OPAL_ELOG_READ				71
 #define OPAL_ELOG_WRITE				72
 #define OPAL_ELOG_ACK				73
@@ -509,7 +481,7 @@ enum OpalMemErr_DynErrType {
 struct OpalMemoryErrorData {
 	enum OpalMemErr_Version	version:8;	/* 0x00 */
 	enum OpalMemErrType	type:8;		/* 0x01 */
-	uint16_t		flags;		/* 0x02 */
+	__be16			flags;		/* 0x02 */
 	uint8_t			reserved_1[4];	/* 0x04 */
 
 	union {
@@ -517,15 +489,15 @@ struct OpalMemoryErrorData {
 		struct {
 			enum OpalMemErr_ResilErrType resil_err_type:8;
 			uint8_t		reserved_1[7];
-			uint64_t	physical_address_start;
-			uint64_t	physical_address_end;
+			__be64		physical_address_start;
+			__be64		physical_address_end;
 		} resilience;
 		/* Dynamic memory deallocation error info */
 		struct {
 			enum OpalMemErr_DynErrType dyn_err_type:8;
 			uint8_t		reserved_1[7];
-			uint64_t	physical_address_start;
-			uint64_t	physical_address_end;
+			__be64		physical_address_start;
+			__be64		physical_address_end;
 		} dyn_dealloc;
 	} u;
 };
@@ -598,9 +570,9 @@ enum {
 };
 
 struct OpalIoPhbErrorCommon {
-	uint32_t version;
-	uint32_t ioType;
-	uint32_t len;
+	__be32 version;
+	__be32 ioType;
+	__be32 len;
 };
 
 struct OpalIoP7IOCPhbErrorData {
@@ -665,64 +637,69 @@ struct OpalIoP7IOCPhbErrorData {
 struct OpalIoPhb3ErrorData {
 	struct OpalIoPhbErrorCommon common;
 
-	uint32_t brdgCtl;
+	__be32 brdgCtl;
 
 	/* PHB3 UTL regs */
-	uint32_t portStatusReg;
-	uint32_t rootCmplxStatus;
-	uint32_t busAgentStatus;
+	__be32 portStatusReg;
+	__be32 rootCmplxStatus;
+	__be32 busAgentStatus;
 
 	/* PHB3 cfg regs */
-	uint32_t deviceStatus;
-	uint32_t slotStatus;
-	uint32_t linkStatus;
-	uint32_t devCmdStatus;
-	uint32_t devSecStatus;
+	__be32 deviceStatus;
+	__be32 slotStatus;
+	__be32 linkStatus;
+	__be32 devCmdStatus;
+	__be32 devSecStatus;
 
 	/* cfg AER regs */
-	uint32_t rootErrorStatus;
-	uint32_t uncorrErrorStatus;
-	uint32_t corrErrorStatus;
-	uint32_t tlpHdr1;
-	uint32_t tlpHdr2;
-	uint32_t tlpHdr3;
-	uint32_t tlpHdr4;
-	uint32_t sourceId;
+	__be32 rootErrorStatus;
+	__be32 uncorrErrorStatus;
+	__be32 corrErrorStatus;
+	__be32 tlpHdr1;
+	__be32 tlpHdr2;
+	__be32 tlpHdr3;
+	__be32 tlpHdr4;
+	__be32 sourceId;
 
-	uint32_t rsv3;
+	__be32 rsv3;
 
 	/* Record data about the call to allocate a buffer */
-	uint64_t errorClass;
-	uint64_t correlator;
+	__be64 errorClass;
+	__be64 correlator;
 
-	uint64_t nFir;			/* 000 */
-	uint64_t nFirMask;		/* 003 */
-	uint64_t nFirWOF;		/* 008 */
+	__be64 nFir;			/* 000 */
+	__be64 nFirMask;		/* 003 */
+	__be64 nFirWOF;		/* 008 */
 
 	/* PHB3 MMIO Error Regs */
-	uint64_t phbPlssr;		/* 120 */
-	uint64_t phbCsr;		/* 110 */
-	uint64_t lemFir;		/* C00 */
-	uint64_t lemErrorMask;		/* C18 */
-	uint64_t lemWOF;		/* C40 */
-	uint64_t phbErrorStatus;	/* C80 */
-	uint64_t phbFirstErrorStatus;	/* C88 */
-	uint64_t phbErrorLog0;		/* CC0 */
-	uint64_t phbErrorLog1;		/* CC8 */
-	uint64_t mmioErrorStatus;	/* D00 */
-	uint64_t mmioFirstErrorStatus;	/* D08 */
-	uint64_t mmioErrorLog0;		/* D40 */
-	uint64_t mmioErrorLog1;		/* D48 */
-	uint64_t dma0ErrorStatus;	/* D80 */
-	uint64_t dma0FirstErrorStatus;	/* D88 */
-	uint64_t dma0ErrorLog0;		/* DC0 */
-	uint64_t dma0ErrorLog1;		/* DC8 */
-	uint64_t dma1ErrorStatus;	/* E00 */
-	uint64_t dma1FirstErrorStatus;	/* E08 */
-	uint64_t dma1ErrorLog0;		/* E40 */
-	uint64_t dma1ErrorLog1;		/* E48 */
-	uint64_t pestA[OPAL_PHB3_NUM_PEST_REGS];
-	uint64_t pestB[OPAL_PHB3_NUM_PEST_REGS];
+	__be64 phbPlssr;		/* 120 */
+	__be64 phbCsr;		/* 110 */
+	__be64 lemFir;		/* C00 */
+	__be64 lemErrorMask;		/* C18 */
+	__be64 lemWOF;		/* C40 */
+	__be64 phbErrorStatus;	/* C80 */
+	__be64 phbFirstErrorStatus;	/* C88 */
+	__be64 phbErrorLog0;		/* CC0 */
+	__be64 phbErrorLog1;		/* CC8 */
+	__be64 mmioErrorStatus;	/* D00 */
+	__be64 mmioFirstErrorStatus;	/* D08 */
+	__be64 mmioErrorLog0;		/* D40 */
+	__be64 mmioErrorLog1;		/* D48 */
+	__be64 dma0ErrorStatus;	/* D80 */
+	__be64 dma0FirstErrorStatus;	/* D88 */
+	__be64 dma0ErrorLog0;		/* DC0 */
+	__be64 dma0ErrorLog1;		/* DC8 */
+	__be64 dma1ErrorStatus;	/* E00 */
+	__be64 dma1FirstErrorStatus;	/* E08 */
+	__be64 dma1ErrorLog0;		/* E40 */
+	__be64 dma1ErrorLog1;		/* E48 */
+	__be64 pestA[OPAL_PHB3_NUM_PEST_REGS];
+	__be64 pestB[OPAL_PHB3_NUM_PEST_REGS];
+};
+
+enum {
+	OPAL_REINIT_CPUS_HILE_BE	= (1 << 0),
+	OPAL_REINIT_CPUS_HILE_LE	= (1 << 1),
 };
 
 typedef struct oppanel_line {
@@ -845,10 +822,11 @@ int64_t opal_pci_mask_pe_error(uint64_t phb_id, uint16_t pe_number, uint8_t erro
 int64_t opal_set_slot_led_status(uint64_t phb_id, uint64_t slot_id, uint8_t led_type, uint8_t led_action);
 int64_t opal_get_epow_status(__be64 *status);
 int64_t opal_set_system_attention_led(uint8_t led_action);
-int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
-			    uint16_t *pci_error_type, uint16_t *severity);
+int64_t opal_pci_next_error(uint64_t phb_id, __be64 *first_frozen_pe,
+			    __be16 *pci_error_type, __be16 *severity);
 int64_t opal_pci_poll(uint64_t phb_id);
 int64_t opal_return_cpu(void);
+int64_t opal_reinit_cpus(uint64_t flags);
 
 int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
 int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val);
@@ -916,6 +894,7 @@ extern void opal_get_rtc_time(struct rtc_time *tm);
 extern unsigned long opal_get_boot_time(void);
 extern void opal_nvram_init(void);
 extern void opal_flash_init(void);
+extern void opal_flash_term_callback(void);
 extern int opal_elog_init(void);
 extern void opal_platform_dump_init(void);
 extern void opal_sys_param_init(void);
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 8e956a0b6e8..bb0bd25f20d 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -92,7 +92,10 @@ struct paca_struct {
 	struct slb_shadow *slb_shadow_ptr;
 	struct dtl_entry *dispatch_log;
 	struct dtl_entry *dispatch_log_end;
+#endif /* CONFIG_PPC_STD_MMU_64 */
+	u64 dscr_default;		/* per-CPU default DSCR */
 
+#ifdef CONFIG_PPC_STD_MMU_64
 	/*
 	 * Now, starting in cacheline 2, the exception save areas
 	 */
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 9ed737146db..b3e936027b2 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -61,8 +61,7 @@ struct power_pmu {
 #define PPMU_SIAR_VALID		0x00000010 /* Processor has SIAR Valid bit */
 #define PPMU_HAS_SSLOT		0x00000020 /* Has sampled slot in MMCRA */
 #define PPMU_HAS_SIER		0x00000040 /* Has SIER */
-#define PPMU_BHRB		0x00000080 /* has BHRB feature enabled */
-#define PPMU_EBB		0x00000100 /* supports event based branch */
+#define PPMU_ARCH_207S		0x00000080 /* PMC is architecture v2.07S */
 
 /*
  * Values for flags to get_alternatives()
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index ed57fa7920c..db1e2b8eff3 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -58,6 +58,7 @@ int rtas_write_config(struct pci_dn *, int where, int size, u32 val);
 int rtas_read_config(struct pci_dn *, int where, int size, u32 *val);
 void eeh_pe_state_mark(struct eeh_pe *pe, int state);
 void eeh_pe_state_clear(struct eeh_pe *pe, int state);
+void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode);
 
 void eeh_sysfs_add_device(struct pci_dev *pdev);
 void eeh_sysfs_remove_device(struct pci_dev *pdev);
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index cded7c1278e..7e461252854 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -57,7 +57,7 @@ BEGIN_FW_FTR_SECTION;							\
 	LDX_BE	r10,0,r10;		/* get log write index */	\
 	cmpd	cr1,r11,r10;						\
 	beq+	cr1,33f;						\
-	bl	.accumulate_stolen_time;				\
+	bl	accumulate_stolen_time;				\
 	ld	r12,_MSR(r1);						\
 	andi.	r10,r12,MSR_PR;		/* Restore cr0 (coming from user) */ \
 33:									\
@@ -189,57 +189,53 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define __STK_REG(i)   (112 + ((i)-14)*8)
 #define STK_REG(i)     __STK_REG(__REG_##i)
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define STK_GOT		24
+#define __STK_PARAM(i)	(32 + ((i)-3)*8)
+#else
+#define STK_GOT		40
 #define __STK_PARAM(i)	(48 + ((i)-3)*8)
+#endif
 #define STK_PARAM(i)	__STK_PARAM(__REG_##i)
 
-#define XGLUE(a,b) a##b
-#define GLUE(a,b) XGLUE(a,b)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
 
 #define _GLOBAL(name) \
 	.section ".text"; \
 	.align 2 ; \
+	.type name,@function; \
 	.globl name; \
-	.globl GLUE(.,name); \
-	.section ".opd","aw"; \
-name: \
-	.quad GLUE(.,name); \
-	.quad .TOC.@tocbase; \
-	.quad 0; \
-	.previous; \
-	.type GLUE(.,name),@function; \
-GLUE(.,name):
+name:
 
-#define _INIT_GLOBAL(name) \
-	__REF; \
+#define _GLOBAL_TOC(name) \
+	.section ".text"; \
 	.align 2 ; \
+	.type name,@function; \
 	.globl name; \
-	.globl GLUE(.,name); \
-	.section ".opd","aw"; \
 name: \
-	.quad GLUE(.,name); \
-	.quad .TOC.@tocbase; \
-	.quad 0; \
-	.previous; \
-	.type GLUE(.,name),@function; \
-GLUE(.,name):
+0:	addis r2,r12,(.TOC.-0b)@ha; \
+	addi r2,r2,(.TOC.-0b)@l; \
+	.localentry name,.-name
 
 #define _KPROBE(name) \
 	.section ".kprobes.text","a"; \
 	.align 2 ; \
+	.type name,@function; \
 	.globl name; \
-	.globl GLUE(.,name); \
-	.section ".opd","aw"; \
-name: \
-	.quad GLUE(.,name); \
-	.quad .TOC.@tocbase; \
-	.quad 0; \
-	.previous; \
-	.type GLUE(.,name),@function; \
-GLUE(.,name):
+name:
+
+#define DOTSYM(a)	a
+
+#else
+
+#define XGLUE(a,b) a##b
+#define GLUE(a,b) XGLUE(a,b)
 
-#define _STATIC(name) \
+#define _GLOBAL(name) \
 	.section ".text"; \
 	.align 2 ; \
+	.globl name; \
+	.globl GLUE(.,name); \
 	.section ".opd","aw"; \
 name: \
 	.quad GLUE(.,name); \
@@ -249,9 +245,13 @@ name: \
 	.type GLUE(.,name),@function; \
 GLUE(.,name):
 
-#define _INIT_STATIC(name) \
-	__REF; \
+#define _GLOBAL_TOC(name) _GLOBAL(name)
+
+#define _KPROBE(name) \
+	.section ".kprobes.text","a"; \
 	.align 2 ; \
+	.globl name; \
+	.globl GLUE(.,name); \
 	.section ".opd","aw"; \
 name: \
 	.quad GLUE(.,name); \
@@ -261,6 +261,10 @@ name: \
 	.type GLUE(.,name),@function; \
 GLUE(.,name):
 
+#define DOTSYM(a)	GLUE(.,a)
+
+#endif
+
 #else /* 32-bit */
 
 #define _ENTRY(n)	\
@@ -273,6 +277,8 @@ n:
 	.globl n;	\
 n:
 
+#define _GLOBAL_TOC(name) _GLOBAL(name)
+
 #define _KPROBE(n)	\
 	.section ".kprobes.text","a";	\
 	.globl	n;	\
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index d660dc36831..dda7ac4c80b 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -400,6 +400,8 @@ static inline unsigned long __pack_fe01(unsigned int fpmode)
 #define cpu_relax()	barrier()
 #endif
 
+#define cpu_relax_lowlatency() cpu_relax()
+
 /* Check that a certain kernel stack pointer is valid in task_struct p */
 int validate_sp(unsigned long sp, struct task_struct *p,
                        unsigned long nbytes);
@@ -449,7 +451,7 @@ extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
 
 extern int powersave_nap;	/* set if nap mode can be used in idle loop */
-extern void power7_nap(void);
+extern void power7_nap(int check_irq);
 extern void power7_sleep(void);
 extern void flush_instruction_cache(void);
 extern void hard_reset_now(void);
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 4852bcf270f..bffd89d2730 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -215,6 +215,7 @@
 #define SPRN_TEXASR	0x82	/* Transaction EXception & Summary */
 #define   TEXASR_FS	__MASK(63-36)	/* Transaction Failure Summary */
 #define SPRN_TEXASRU	0x83	/* ''	   ''	   ''	 Upper 32  */
+#define   TEXASR_FS     __MASK(63-36) /* TEXASR Failure Summary */
 #define SPRN_TFHAR	0x80	/* Transaction Failure Handler Addr */
 #define SPRN_CTRLF	0x088
 #define SPRN_CTRLT	0x098
@@ -224,6 +225,7 @@
 #define   CTRL_TE	0x00c00000	/* thread enable */
 #define   CTRL_RUNLATCH	0x1
 #define SPRN_DAWR	0xB4
+#define SPRN_RPR	0xBA	/* Relative Priority Register */
 #define SPRN_CIABR	0xBB
 #define   CIABR_PRIV		0x3
 #define   CIABR_PRIV_USER	1
@@ -272,8 +274,10 @@
 #define SPRN_HSRR1	0x13B	/* Hypervisor Save/Restore 1 */
 #define SPRN_IC		0x350	/* Virtual Instruction Count */
 #define SPRN_VTB	0x351	/* Virtual Time Base */
+#define SPRN_LDBAR	0x352	/* LD Base Address Register */
 #define SPRN_PMICR	0x354   /* Power Management Idle Control Reg */
 #define SPRN_PMSR	0x355   /* Power Management Status Reg */
+#define SPRN_PMMAR	0x356	/* Power Management Memory Activity Register */
 #define SPRN_PMCR	0x374	/* Power Management Control Register */
 
 /* HFSCR and FSCR bit numbers are the same */
@@ -433,6 +437,12 @@
 #define HID0_BTCD	(1<<1)		/* Branch target cache disable */
 #define HID0_NOPDST	(1<<1)		/* No-op dst, dstt, etc. instr. */
 #define HID0_NOPTI	(1<<0)		/* No-op dcbt and dcbst instr. */
+/* POWER8 HID0 bits */
+#define HID0_POWER8_4LPARMODE	__MASK(61)
+#define HID0_POWER8_2LPARMODE	__MASK(57)
+#define HID0_POWER8_1TO2LPAR	__MASK(52)
+#define HID0_POWER8_1TO4LPAR	__MASK(51)
+#define HID0_POWER8_DYNLPARDIS	__MASK(48)
 
 #define SPRN_HID1	0x3F1		/* Hardware Implementation Register 1 */
 #ifdef CONFIG_6xx
diff --git a/arch/powerpc/include/asm/reg_a2.h b/arch/powerpc/include/asm/reg_a2.h
index 3d52a1132f3..3ba9c6f096f 100644
--- a/arch/powerpc/include/asm/reg_a2.h
+++ b/arch/powerpc/include/asm/reg_a2.h
@@ -110,15 +110,6 @@
 #define TLB1_UR			ASM_CONST(0x0000000000000002)
 #define TLB1_SR			ASM_CONST(0x0000000000000001)
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
-#define WSP_UART_PHYS	0xffc000c000
-/* This needs to be careful chosen to hit a !0 congruence class
- * in the TLB since we bolt it in way 3, which is already occupied
- * by our linear mapping primary bolted entry in CC 0.
- */
-#define WSP_UART_VIRT	0xf000000000001000
-#endif
-
 /* A2 erativax attributes definitions */
 #define ERATIVAX_RS_IS_ALL		0x000
 #define ERATIVAX_RS_IS_TID		0x040
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 52179033067..a5e930aca80 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -50,6 +50,7 @@ static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end)
 #endif
 }
 
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
 #undef dereference_function_descriptor
 static inline void *dereference_function_descriptor(void *ptr)
 {
@@ -60,6 +61,7 @@ static inline void *dereference_function_descriptor(void *ptr)
 		ptr = p;
 	return ptr;
 }
+#endif
 
 #endif
 
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index ff51046b646..5a6614a7f0b 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -68,14 +68,6 @@ void generic_mach_cpu_die(void);
 void generic_set_cpu_dead(unsigned int cpu);
 void generic_set_cpu_up(unsigned int cpu);
 int generic_check_cpu_restart(unsigned int cpu);
-
-extern void inhibit_secondary_onlining(void);
-extern void uninhibit_secondary_onlining(void);
-
-#else /* HOTPLUG_CPU */
-static inline void inhibit_secondary_onlining(void) {}
-static inline void uninhibit_secondary_onlining(void) {}
-
 #endif
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 0dffad6bcc8..e40010abcaf 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -10,9 +10,7 @@
 #define __HAVE_ARCH_STRNCMP
 #define __HAVE_ARCH_STRCAT
 #define __HAVE_ARCH_MEMSET
-#ifdef __BIG_ENDIAN__
 #define __HAVE_ARCH_MEMCPY
-#endif
 #define __HAVE_ARCH_MEMMOVE
 #define __HAVE_ARCH_MEMCMP
 #define __HAVE_ARCH_MEMCHR
@@ -24,9 +22,7 @@ extern int strcmp(const char *,const char *);
 extern int strncmp(const char *, const char *, __kernel_size_t);
 extern char * strcat(char *, const char *);
 extern void * memset(void *,int,__kernel_size_t);
-#ifdef __BIG_ENDIAN__
 extern void * memcpy(void *,const void *,__kernel_size_t);
-#endif
 extern void * memmove(void *,const void *,__kernel_size_t);
 extern int memcmp(const void *,const void *,__kernel_size_t);
 extern void * memchr(const void *,int,__kernel_size_t);
diff --git a/arch/powerpc/include/asm/swab.h b/arch/powerpc/include/asm/swab.h
index b9bd1ca944d..96f59de6185 100644
--- a/arch/powerpc/include/asm/swab.h
+++ b/arch/powerpc/include/asm/swab.h
@@ -9,10 +9,6 @@
 
 #include <uapi/asm/swab.h>
 
-#ifdef __GNUC__
-#ifndef __powerpc64__
-#endif /* __powerpc64__ */
-
 static __inline__ __u16 ld_le16(const volatile __u16 *addr)
 {
 	__u16 val;
@@ -20,19 +16,12 @@ static __inline__ __u16 ld_le16(const volatile __u16 *addr)
 	__asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr));
 	return val;
 }
-#define __arch_swab16p ld_le16
 
 static __inline__ void st_le16(volatile __u16 *addr, const __u16 val)
 {
 	__asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr));
 }
 
-static inline void __arch_swab16s(__u16 *addr)
-{
-	st_le16(addr, *addr);
-}
-#define __arch_swab16s __arch_swab16s
-
 static __inline__ __u32 ld_le32(const volatile __u32 *addr)
 {
 	__u32 val;
@@ -40,42 +29,10 @@ static __inline__ __u32 ld_le32(const volatile __u32 *addr)
 	__asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr));
 	return val;
 }
-#define __arch_swab32p ld_le32
 
 static __inline__ void st_le32(volatile __u32 *addr, const __u32 val)
 {
 	__asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr));
 }
 
-static inline void __arch_swab32s(__u32 *addr)
-{
-	st_le32(addr, *addr);
-}
-#define __arch_swab32s __arch_swab32s
-
-static inline __attribute_const__ __u16 __arch_swab16(__u16 value)
-{
-	__u16 result;
-
-	__asm__("rlwimi %0,%1,8,16,23"
-	    : "=r" (result)
-	    : "r" (value), "0" (value >> 8));
-	return result;
-}
-#define __arch_swab16 __arch_swab16
-
-static inline __attribute_const__ __u32 __arch_swab32(__u32 value)
-{
-	__u32 result;
-
-	__asm__("rlwimi %0,%1,24,16,23\n\t"
-	    "rlwimi %0,%1,8,8,15\n\t"
-	    "rlwimi %0,%1,24,0,7"
-	    : "=r" (result)
-	    : "r" (value), "0" (value >> 24));
-	return result;
-}
-#define __arch_swab32 __arch_swab32
-
-#endif /* __GNUC__ */
 #endif /* _ASM_POWERPC_SWAB_H */
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 0e83e7d8c73..58abeda64cb 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -16,13 +16,15 @@ struct thread_struct;
 extern struct task_struct *_switch(struct thread_struct *prev,
 				   struct thread_struct *next);
 #ifdef CONFIG_PPC_BOOK3S_64
-static inline void save_tar(struct thread_struct *prev)
+static inline void save_early_sprs(struct thread_struct *prev)
 {
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		prev->tar = mfspr(SPRN_TAR);
+	if (cpu_has_feature(CPU_FTR_DSCR))
+		prev->dscr = mfspr(SPRN_DSCR);
 }
 #else
-static inline void save_tar(struct thread_struct *prev) {}
+static inline void save_early_sprs(struct thread_struct *prev) {}
 #endif
 
 extern void enable_kernel_fp(void);
@@ -84,6 +86,8 @@ static inline void clear_task_ebb(struct task_struct *t)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
     /* EBB perf events are not inherited, so clear all EBB state. */
+    t->thread.ebbrr = 0;
+    t->thread.ebbhr = 0;
     t->thread.bescr = 0;
     t->thread.mmcr2 = 0;
     t->thread.mmcr0 = 0;
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index ea4dc3a89c1..babbeca6850 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -62,7 +62,7 @@ COMPAT_SYS_SPU(fcntl)
 SYSCALL(ni_syscall)
 SYSCALL_SPU(setpgid)
 SYSCALL(ni_syscall)
-SYSX(sys_ni_syscall,sys_olduname, sys_olduname)
+SYSX(sys_ni_syscall,sys_olduname,sys_olduname)
 SYSCALL_SPU(umask)
 SYSCALL_SPU(chroot)
 COMPAT_SYS(ustat)
@@ -190,7 +190,7 @@ SYSCALL_SPU(getcwd)
 SYSCALL_SPU(capget)
 SYSCALL_SPU(capset)
 COMPAT_SYS(sigaltstack)
-COMPAT_SYS_SPU(sendfile)
+SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile)
 SYSCALL(ni_syscall)
 SYSCALL(ni_syscall)
 PPC_SYS(vfork)
@@ -258,7 +258,7 @@ SYSCALL_SPU(tgkill)
 COMPAT_SYS_SPU(utimes)
 COMPAT_SYS_SPU(statfs64)
 COMPAT_SYS_SPU(fstatfs64)
-SYSX(sys_ni_syscall, ppc_fadvise64_64, ppc_fadvise64_64)
+SYSX(sys_ni_syscall,ppc_fadvise64_64,ppc_fadvise64_64)
 PPC_SYS_SPU(rtas)
 OLDSYS(debug_setcontext)
 SYSCALL(ni_syscall)
@@ -295,7 +295,7 @@ SYSCALL_SPU(mkdirat)
 SYSCALL_SPU(mknodat)
 SYSCALL_SPU(fchownat)
 COMPAT_SYS_SPU(futimesat)
-SYSX_SPU(sys_newfstatat, sys_fstatat64, sys_fstatat64)
+SYSX_SPU(sys_newfstatat,sys_fstatat64,sys_fstatat64)
 SYSCALL_SPU(unlinkat)
 SYSCALL_SPU(renameat)
 SYSCALL_SPU(linkat)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 6c8a8c5a37a..5f1048eaa5b 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -16,19 +16,6 @@ struct device_node;
 
 #include <asm/mmzone.h>
 
-static inline int cpu_to_node(int cpu)
-{
-	int nid;
-
-	nid = numa_cpu_lookup_table[cpu];
-
-	/*
-	 * During early boot, the numa-cpu lookup table might not have been
-	 * setup for all CPUs yet. In such cases, default to node 0.
-	 */
-	return (nid < 0) ? 0 : nid;
-}
-
 #define parent_node(node)	(node)
 
 #define cpumask_of_node(node) ((node) == -1 ?				\
diff --git a/arch/powerpc/include/asm/wsp.h b/arch/powerpc/include/asm/wsp.h
deleted file mode 100644
index c7dc83088a3..00000000000
--- a/arch/powerpc/include/asm/wsp.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- *  Copyright 2011 Michael Ellerman, IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-#ifndef __ASM_POWERPC_WSP_H
-#define __ASM_POWERPC_WSP_H
-
-extern int wsp_get_chip_id(struct device_node *dn);
-
-#endif /* __ASM_POWERPC_WSP_H */
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index 48be855ef37..7a3f795ac21 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -15,7 +15,6 @@ header-y += ioctls.h
 header-y += ipcbuf.h
 header-y += kvm.h
 header-y += kvm_para.h
-header-y += linkage.h
 header-y += mman.h
 header-y += msgbuf.h
 header-y += nvram.h
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index 5b7657959fa..de2c0e4ee1a 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -41,5 +41,6 @@
 #define PPC_FEATURE2_EBB		0x10000000
 #define PPC_FEATURE2_ISEL		0x08000000
 #define PPC_FEATURE2_TAR		0x04000000
+#define PPC_FEATURE2_VEC_CRYPTO		0x02000000
 
 #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h
index 7e39c9146a7..59dad113897 100644
--- a/arch/powerpc/include/uapi/asm/elf.h
+++ b/arch/powerpc/include/uapi/asm/elf.h
@@ -291,9 +291,17 @@ do {									\
 #define R_PPC64_DTPREL16_HIGHERA 104 /* half16	(sym+add)@dtprel@highera */
 #define R_PPC64_DTPREL16_HIGHEST 105 /* half16	(sym+add)@dtprel@highest */
 #define R_PPC64_DTPREL16_HIGHESTA 106 /* half16	(sym+add)@dtprel@highesta */
+#define R_PPC64_TLSGD		107
+#define R_PPC64_TLSLD		108
+#define R_PPC64_TOCSAVE		109
+
+#define R_PPC64_REL16		249
+#define R_PPC64_REL16_LO	250
+#define R_PPC64_REL16_HI	251
+#define R_PPC64_REL16_HA	252
 
 /* Keep this the last entry.  */
-#define R_PPC64_NUM		107
+#define R_PPC64_NUM		253
 
 /* There's actually a third entry here, but it's unused */
 struct ppc64_opd_entry
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index fab19ec2559..670c312d914 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -43,7 +43,6 @@ obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
-obj-$(CONFIG_PPC_A2)		+= cpu_setup_a2.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 93e1465c849..f5995a91221 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -248,6 +248,7 @@ int main(void)
 #endif
 	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
 	DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
+	DEFINE(PACA_DSCR, offsetof(struct paca_struct, dscr_default));
 	DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
 	DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user));
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S
deleted file mode 100644
index 61f079e05b6..00000000000
--- a/arch/powerpc/kernel/cpu_setup_a2.S
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- *  A2 specific assembly support code
- *
- *  Copyright 2009 Ben Herrenschmidt, IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-
-#include <asm/asm-offsets.h>
-#include <asm/ppc_asm.h>
-#include <asm/ppc-opcode.h>
-#include <asm/processor.h>
-#include <asm/reg_a2.h>
-#include <asm/reg.h>
-#include <asm/thread_info.h>
-
-/*
- * Disable thdid and class fields in ERATs to bump PID to full 14 bits capacity.
- * This also prevents external LPID accesses but that isn't a problem when not a
- * guest. Under PV, this setting will be ignored and MMUCR will return the right
- * number of PID bits we can use.
- */
-#define MMUCR1_EXTEND_PID \
-	(MMUCR1_ICTID | MMUCR1_ITTID | MMUCR1_DCTID | \
-	 MMUCR1_DTTID | MMUCR1_DCCD)
-
-/*
- * Use extended PIDs if enabled.
- * Don't clear the ERATs on context sync events and enable I & D LRU.
- * Enable ERAT back invalidate when tlbwe overwrites an entry.
- */
-#define INITIAL_MMUCR1 \
-	(MMUCR1_EXTEND_PID | MMUCR1_CSINV_NEVER | MMUCR1_IRRE | \
-	 MMUCR1_DRRE | MMUCR1_TLBWE_BINV)
-
-_GLOBAL(__setup_cpu_a2)
-	/* Some of these are actually thread local and some are
-	 * core local but doing it always won't hurt
-	 */
-
-#ifdef CONFIG_PPC_ICSWX
-	/* Make sure ACOP starts out as zero */
-	li	r3,0
-	mtspr   SPRN_ACOP,r3
-
-	/* Skip the following if we are in Guest mode */
-	mfmsr	r3
-	andis.	r0,r3,MSR_GS@h
-	bne	_icswx_skip_guest
-
-	/* Enable icswx instruction */
-	mfspr   r3,SPRN_A2_CCR2
-	ori     r3,r3,A2_CCR2_ENABLE_ICSWX
-	mtspr   SPRN_A2_CCR2,r3
-
-	/* Unmask all CTs in HACOP */
-	li      r3,-1
-	mtspr   SPRN_HACOP,r3
-_icswx_skip_guest:
-#endif /* CONFIG_PPC_ICSWX */
-
-	/* Enable doorbell */
-	mfspr   r3,SPRN_A2_CCR2
-	oris     r3,r3,A2_CCR2_ENABLE_PC@h
-	mtspr   SPRN_A2_CCR2,r3
-	isync
-
-	/* Setup CCR0 to disable power saving for now as it's busted
-	 * in the current implementations. Setup CCR1 to wake on
-	 * interrupts normally (we write the default value but who
-	 * knows what FW may have clobbered...)
-	 */
-	li	r3,0
-	mtspr	SPRN_A2_CCR0, r3
-	LOAD_REG_IMMEDIATE(r3,0x0f0f0f0f)
-	mtspr	SPRN_A2_CCR1, r3
-
-	/* Initialise MMUCR1 */
-	lis	r3,INITIAL_MMUCR1@h
-	ori	r3,r3,INITIAL_MMUCR1@l
-	mtspr	SPRN_MMUCR1,r3
-
-	/* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */
-	LOAD_REG_IMMEDIATE(r3, 0x000a7531)
-	mtspr	SPRN_MMUCR2,r3
-
-	/* Set MMUCR3 to write all thids bit to the TLB */
-	LOAD_REG_IMMEDIATE(r3, 0x0000000f)
-	mtspr	SPRN_MMUCR3,r3
-
-	/* Don't do ERAT stuff if running guest mode */
-	mfmsr	r3
-	andis.	r0,r3,MSR_GS@h
-	bne	1f
-
-	/* Now set the I-ERAT watermark to 15 */
-	lis	r4,(MMUCR0_TLBSEL_I|MMUCR0_ECL)@h
-	mtspr	SPRN_MMUCR0, r4
-	li	r4,A2_IERAT_SIZE-1
-	PPC_ERATWE(R4,R4,3)
-
-	/* Now set the D-ERAT watermark to 31 */
-	lis	r4,(MMUCR0_TLBSEL_D|MMUCR0_ECL)@h
-	mtspr	SPRN_MMUCR0, r4
-	li	r4,A2_DERAT_SIZE-1
-	PPC_ERATWE(R4,R4,3)
-
-	/* And invalidate the beast just in case. That won't get rid of
-	 * a bolted entry though it will be in LRU and so will go away eventually
-	 * but let's not bother for now
-	 */
-	PPC_ERATILX(0,0,R0)
-1:
-	blr
-
-_GLOBAL(__restore_cpu_a2)
-	b	__setup_cpu_a2
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index cc2d8962e09..4f1393d2007 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -94,12 +94,12 @@ _GLOBAL(setup_altivec_idle)
 _GLOBAL(__setup_cpu_e6500)
 	mflr	r6
 #ifdef CONFIG_PPC64
-	bl	.setup_altivec_ivors
+	bl	setup_altivec_ivors
 	/* Touch IVOR42 only if the CPU supports E.HV category */
 	mfspr	r10,SPRN_MMUCFG
 	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
 	beq	1f
-	bl	.setup_lrat_ivor
+	bl	setup_lrat_ivor
 1:
 #endif
 	bl	setup_pw20_idle
@@ -164,15 +164,15 @@ _GLOBAL(__setup_cpu_e5500)
 #ifdef CONFIG_PPC_BOOK3E_64
 _GLOBAL(__restore_cpu_e6500)
 	mflr	r5
-	bl	.setup_altivec_ivors
+	bl	setup_altivec_ivors
 	/* Touch IVOR42 only if the CPU supports E.HV category */
 	mfspr	r10,SPRN_MMUCFG
 	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
 	beq	1f
-	bl	.setup_lrat_ivor
+	bl	setup_lrat_ivor
 1:
-	bl	.setup_pw20_idle
-	bl	.setup_altivec_idle
+	bl	setup_pw20_idle
+	bl	setup_altivec_idle
 	bl	__restore_cpu_e5500
 	mtlr	r5
 	blr
@@ -181,9 +181,9 @@ _GLOBAL(__restore_cpu_e5500)
 	mflr	r4
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup
-	bl	.__setup_base_ivors
-	bl	.setup_perfmon_ivor
-	bl	.setup_doorbell_ivors
+	bl	__setup_base_ivors
+	bl	setup_perfmon_ivor
+	bl	setup_doorbell_ivors
 	/*
 	 * We only want to touch IVOR38-41 if we're running on hardware
 	 * that supports category E.HV.  The architectural way to determine
@@ -192,7 +192,7 @@ _GLOBAL(__restore_cpu_e5500)
 	mfspr	r10,SPRN_MMUCFG
 	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
 	beq	1f
-	bl	.setup_ehv_ivors
+	bl	setup_ehv_ivors
 1:
 	mtlr	r4
 	blr
@@ -201,9 +201,9 @@ _GLOBAL(__setup_cpu_e5500)
 	mflr	r5
 	bl	__e500_icache_setup
 	bl	__e500_dcache_setup
-	bl	.__setup_base_ivors
-	bl	.setup_perfmon_ivor
-	bl	.setup_doorbell_ivors
+	bl	__setup_base_ivors
+	bl	setup_perfmon_ivor
+	bl	setup_doorbell_ivors
 	/*
 	 * We only want to touch IVOR38-41 if we're running on hardware
 	 * that supports category E.HV.  The architectural way to determine
@@ -212,7 +212,7 @@ _GLOBAL(__setup_cpu_e5500)
 	mfspr	r10,SPRN_MMUCFG
 	rlwinm.	r10,r10,0,MMUCFG_LPIDSIZE
 	beq	1f
-	bl	.setup_ehv_ivors
+	bl	setup_ehv_ivors
 	b	2f
 1:
 	ld	r10,CPU_SPEC_FEATURES(r4)
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 1557e7c2c7e..46733535cc0 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -56,6 +56,7 @@ _GLOBAL(__setup_cpu_power8)
 	li	r0,0
 	mtspr	SPRN_LPID,r0
 	mfspr	r3,SPRN_LPCR
+	ori	r3, r3, LPCR_PECEDH
 	bl	__init_LPCR
 	bl	__init_HFSCR
 	bl	__init_tlb_power8
@@ -74,6 +75,7 @@ _GLOBAL(__restore_cpu_power8)
 	li	r0,0
 	mtspr	SPRN_LPID,r0
 	mfspr   r3,SPRN_LPCR
+	ori	r3, r3, LPCR_PECEDH
 	bl	__init_LPCR
 	bl	__init_HFSCR
 	bl	__init_tlb_power8
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index c1faade6506..0c157642c2a 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -109,7 +109,8 @@ extern void __restore_cpu_e6500(void);
 				 PPC_FEATURE_PSERIES_PERFMON_COMPAT)
 #define COMMON_USER2_POWER8	(PPC_FEATURE2_ARCH_2_07 | \
 				 PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \
-				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR)
+				 PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
+				 PPC_FEATURE2_VEC_CRYPTO)
 #define COMMON_USER_PA6T	(COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
 				 PPC_FEATURE_TRUE_LE | \
 				 PPC_FEATURE_HAS_ALTIVEC_COMP)
@@ -526,6 +527,26 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
+	{	/* Power8 DD1: Does not support doorbell IPIs */
+		.pvr_mask		= 0xffffff00,
+		.pvr_value		= 0x004d0100,
+		.cpu_name		= "POWER8 (raw)",
+		.cpu_features		= CPU_FTRS_POWER8_DD1,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power8",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.flush_tlb		= __flush_tlb_power8,
+		.machine_check_early	= __machine_check_early_realmode_p8,
+		.platform		= "power8",
+	},
 	{	/* Power8 */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x004d0000,
@@ -2148,44 +2169,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 	}
 #endif /* CONFIG_PPC32 */
 #endif /* CONFIG_E500 */
-
-#ifdef CONFIG_PPC_A2
-	{	/* Standard A2 (>= DD2) + FPU core */
-		.pvr_mask		= 0xffff0000,
-		.pvr_value		= 0x00480000,
-		.cpu_name		= "A2 (>= DD2)",
-		.cpu_features		= CPU_FTRS_A2,
-		.cpu_user_features	= COMMON_USER_PPC64,
-		.mmu_features		= MMU_FTRS_A2,
-		.icache_bsize		= 64,
-		.dcache_bsize		= 64,
-		.num_pmcs		= 0,
-		.cpu_setup		= __setup_cpu_a2,
-		.cpu_restore		= __restore_cpu_a2,
-		.machine_check		= machine_check_generic,
-		.platform		= "ppca2",
-	},
-	{	/* This is a default entry to get going, to be replaced by
-		 * a real one at some stage
-		 */
-#define CPU_FTRS_BASE_BOOK3E	(CPU_FTR_USE_TB | \
-	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_SMT | \
-	    CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
-		.pvr_mask		= 0x00000000,
-		.pvr_value		= 0x00000000,
-		.cpu_name		= "Book3E",
-		.cpu_features		= CPU_FTRS_BASE_BOOK3E,
-		.cpu_user_features	= COMMON_USER_PPC64,
-		.mmu_features		= MMU_FTR_TYPE_3E | MMU_FTR_USE_TLBILX |
-					  MMU_FTR_USE_TLBIVAX_BCAST |
-					  MMU_FTR_LOCK_BCAST_INVAL,
-		.icache_bsize		= 64,
-		.dcache_bsize		= 64,
-		.num_pmcs		= 0,
-		.machine_check		= machine_check_generic,
-		.platform		= "power6",
-	},
-#endif /* CONFIG_PPC_A2 */
 };
 
 static struct cpu_spec the_cpu_spec;
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index e7b76a6bf15..86e25702aac 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/debugfs.h>
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/list.h>
@@ -35,6 +36,7 @@
 #include <linux/of.h>
 
 #include <linux/atomic.h>
+#include <asm/debug.h>
 #include <asm/eeh.h>
 #include <asm/eeh_event.h>
 #include <asm/io.h>
@@ -87,22 +89,21 @@
 /* Time to wait for a PCI slot to report status, in milliseconds */
 #define PCI_BUS_RESET_WAIT_MSEC (5*60*1000)
 
-/* Platform dependent EEH operations */
-struct eeh_ops *eeh_ops = NULL;
-
-bool eeh_subsystem_enabled = false;
-EXPORT_SYMBOL(eeh_subsystem_enabled);
-
 /*
- * EEH probe mode support. The intention is to support multiple
- * platforms for EEH. Some platforms like pSeries do PCI emunation
- * based on device tree. However, other platforms like powernv probe
- * PCI devices from hardware. The flag is used to distinguish that.
- * In addition, struct eeh_ops::probe would be invoked for particular
- * OF node or PCI device so that the corresponding PE would be created
- * there.
+ * EEH probe mode support, which is part of the flags,
+ * is to support multiple platforms for EEH. Some platforms
+ * like pSeries do PCI emunation based on device tree.
+ * However, other platforms like powernv probe PCI devices
+ * from hardware. The flag is used to distinguish that.
+ * In addition, struct eeh_ops::probe would be invoked for
+ * particular OF node or PCI device so that the corresponding
+ * PE would be created there.
  */
-int eeh_probe_mode;
+int eeh_subsystem_flags;
+EXPORT_SYMBOL(eeh_subsystem_flags);
+
+/* Platform dependent EEH operations */
+struct eeh_ops *eeh_ops = NULL;
 
 /* Lock to avoid races due to multiple reports of an error */
 DEFINE_RAW_SPINLOCK(confirm_error_lock);
@@ -133,6 +134,15 @@ static struct eeh_stats eeh_stats;
 
 #define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE)
 
+static int __init eeh_setup(char *str)
+{
+	if (!strcmp(str, "off"))
+		eeh_subsystem_flags |= EEH_FORCE_DISABLED;
+
+	return 1;
+}
+__setup("eeh=", eeh_setup);
+
 /**
  * eeh_gather_pci_data - Copy assorted PCI config space registers to buff
  * @edev: device to report data for
@@ -145,73 +155,67 @@ static struct eeh_stats eeh_stats;
 static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
 {
 	struct device_node *dn = eeh_dev_to_of_node(edev);
-	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
 	u32 cfg;
 	int cap, i;
 	int n = 0;
 
 	n += scnprintf(buf+n, len-n, "%s\n", dn->full_name);
-	printk(KERN_WARNING "EEH: of node=%s\n", dn->full_name);
+	pr_warn("EEH: of node=%s\n", dn->full_name);
 
 	eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg);
 	n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
-	printk(KERN_WARNING "EEH: PCI device/vendor: %08x\n", cfg);
+	pr_warn("EEH: PCI device/vendor: %08x\n", cfg);
 
 	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg);
 	n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
-	printk(KERN_WARNING "EEH: PCI cmd/status register: %08x\n", cfg);
-
-	if (!dev) {
-		printk(KERN_WARNING "EEH: no PCI device for this of node\n");
-		return n;
-	}
+	pr_warn("EEH: PCI cmd/status register: %08x\n", cfg);
 
 	/* Gather bridge-specific registers */
-	if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) {
+	if (edev->mode & EEH_DEV_BRIDGE) {
 		eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg);
 		n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
-		printk(KERN_WARNING "EEH: Bridge secondary status: %04x\n", cfg);
+		pr_warn("EEH: Bridge secondary status: %04x\n", cfg);
 
 		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg);
 		n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
-		printk(KERN_WARNING "EEH: Bridge control: %04x\n", cfg);
+		pr_warn("EEH: Bridge control: %04x\n", cfg);
 	}
 
 	/* Dump out the PCI-X command and status regs */
-	cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
+	cap = edev->pcix_cap;
 	if (cap) {
 		eeh_ops->read_config(dn, cap, 4, &cfg);
 		n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
-		printk(KERN_WARNING "EEH: PCI-X cmd: %08x\n", cfg);
+		pr_warn("EEH: PCI-X cmd: %08x\n", cfg);
 
 		eeh_ops->read_config(dn, cap+4, 4, &cfg);
 		n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
-		printk(KERN_WARNING "EEH: PCI-X status: %08x\n", cfg);
+		pr_warn("EEH: PCI-X status: %08x\n", cfg);
 	}
 
-	/* If PCI-E capable, dump PCI-E cap 10, and the AER */
-	if (pci_is_pcie(dev)) {
+	/* If PCI-E capable, dump PCI-E cap 10 */
+	cap = edev->pcie_cap;
+	if (cap) {
 		n += scnprintf(buf+n, len-n, "pci-e cap10:\n");
-		printk(KERN_WARNING
-		       "EEH: PCI-E capabilities and status follow:\n");
+		pr_warn("EEH: PCI-E capabilities and status follow:\n");
 
 		for (i=0; i<=8; i++) {
-			eeh_ops->read_config(dn, dev->pcie_cap+4*i, 4, &cfg);
+			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
 			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
-			printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg);
+			pr_warn("EEH: PCI-E %02x: %08x\n", i, cfg);
 		}
+	}
+
+	/* If AER capable, dump it */
+	cap = edev->aer_cap;
+	if (cap) {
+		n += scnprintf(buf+n, len-n, "pci-e AER:\n");
+		pr_warn("EEH: PCI-E AER capability register set follows:\n");
 
-		cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
-		if (cap) {
-			n += scnprintf(buf+n, len-n, "pci-e AER:\n");
-			printk(KERN_WARNING
-			       "EEH: PCI-E AER capability register set follows:\n");
-
-			for (i=0; i<14; i++) {
-				eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
-				n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
-				printk(KERN_WARNING "EEH: PCI-E AER %02x: %08x\n", i, cfg);
-			}
+		for (i=0; i<14; i++) {
+			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
+			pr_warn("EEH: PCI-E AER %02x: %08x\n", i, cfg);
 		}
 	}
 
@@ -232,21 +236,19 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 {
 	size_t loglen = 0;
 	struct eeh_dev *edev, *tmp;
-	bool valid_cfg_log = true;
 
 	/*
 	 * When the PHB is fenced or dead, it's pointless to collect
 	 * the data from PCI config space because it should return
 	 * 0xFF's. For ER, we still retrieve the data from the PCI
 	 * config space.
+	 *
+	 * For pHyp, we have to enable IO for log retrieval. Otherwise,
+	 * 0xFF's is always returned from PCI config space.
 	 */
-	if (eeh_probe_mode_dev() &&
-	    (pe->type & EEH_PE_PHB) &&
-	    (pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)))
-		valid_cfg_log = false;
-
-	if (valid_cfg_log) {
-		eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+	if (!(pe->type & EEH_PE_PHB)) {
+		if (eeh_probe_mode_devtree())
+			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 		eeh_ops->configure_bridge(pe);
 		eeh_pe_restore_bars(pe);
 
@@ -309,7 +311,7 @@ static int eeh_phb_check_failure(struct eeh_pe *pe)
 
 	/* If the PHB has been in problematic state */
 	eeh_serialize_lock(&flags);
-	if (phb_pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)) {
+	if (phb_pe->state & EEH_PE_ISOLATED) {
 		ret = 0;
 		goto out;
 	}
@@ -328,8 +330,8 @@ static int eeh_phb_check_failure(struct eeh_pe *pe)
 	eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
 	eeh_serialize_unlock(flags);
 
-	pr_err("EEH: PHB#%x failure detected\n",
-		phb_pe->phb->global_number);
+	pr_err("EEH: PHB#%x failure detected, location: %s\n",
+		phb_pe->phb->global_number, eeh_pe_loc_get(phb_pe));
 	dump_stack();
 	eeh_send_failure_event(phb_pe);
 
@@ -356,10 +358,11 @@ out:
 int eeh_dev_check_failure(struct eeh_dev *edev)
 {
 	int ret;
+	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	unsigned long flags;
 	struct device_node *dn;
 	struct pci_dev *dev;
-	struct eeh_pe *pe;
+	struct eeh_pe *pe, *parent_pe, *phb_pe;
 	int rc = 0;
 	const char *location;
 
@@ -437,14 +440,34 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	 */
 	if ((ret < 0) ||
 	    (ret == EEH_STATE_NOT_SUPPORT) ||
-	    (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
-	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
+	    ((ret & active_flags) == active_flags)) {
 		eeh_stats.false_positives++;
 		pe->false_positives++;
 		rc = 0;
 		goto dn_unlock;
 	}
 
+	/*
+	 * It should be corner case that the parent PE has been
+	 * put into frozen state as well. We should take care
+	 * that at first.
+	 */
+	parent_pe = pe->parent;
+	while (parent_pe) {
+		/* Hit the ceiling ? */
+		if (parent_pe->type & EEH_PE_PHB)
+			break;
+
+		/* Frozen parent PE ? */
+		ret = eeh_ops->get_state(parent_pe, NULL);
+		if (ret > 0 &&
+		    (ret & active_flags) != active_flags)
+			pe = parent_pe;
+
+		/* Next parent level */
+		parent_pe = parent_pe->parent;
+	}
+
 	eeh_stats.slot_resets++;
 
 	/* Avoid repeated reports of this failure, including problems
@@ -458,8 +481,11 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	 * a stack trace will help the device-driver authors figure
 	 * out what happened.  So print that out.
 	 */
-	pr_err("EEH: Frozen PE#%x detected on PHB#%x\n",
-		pe->addr, pe->phb->global_number);
+	phb_pe = eeh_phb_pe_get(pe->phb);
+	pr_err("EEH: Frozen PHB#%x-PE#%x detected\n",
+	       pe->phb->global_number, pe->addr);
+	pr_err("EEH: PE location: %s, PHB location: %s\n",
+	       eeh_pe_loc_get(pe), eeh_pe_loc_get(phb_pe));
 	dump_stack();
 
 	eeh_send_failure_event(pe);
@@ -515,16 +541,42 @@ EXPORT_SYMBOL(eeh_check_failure);
  */
 int eeh_pci_enable(struct eeh_pe *pe, int function)
 {
-	int rc;
+	int rc, flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+
+	/*
+	 * pHyp doesn't allow to enable IO or DMA on unfrozen PE.
+	 * Also, it's pointless to enable them on unfrozen PE. So
+	 * we have the check here.
+	 */
+	if (function == EEH_OPT_THAW_MMIO ||
+	    function == EEH_OPT_THAW_DMA) {
+		rc = eeh_ops->get_state(pe, NULL);
+		if (rc < 0)
+			return rc;
+
+		/* Needn't to enable or already enabled */
+		if ((rc == EEH_STATE_NOT_SUPPORT) ||
+		    ((rc & flags) == flags))
+			return 0;
+	}
 
 	rc = eeh_ops->set_option(pe, function);
 	if (rc)
-		pr_warning("%s: Unexpected state change %d on PHB#%d-PE#%x, err=%d\n",
-			__func__, function, pe->phb->global_number, pe->addr, rc);
+		pr_warn("%s: Unexpected state change %d on "
+			"PHB#%d-PE#%x, err=%d\n",
+			__func__, function, pe->phb->global_number,
+			pe->addr, rc);
 
 	rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-	if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) &&
-	   (function == EEH_OPT_THAW_MMIO))
+	if (rc <= 0)
+		return rc;
+
+	if ((function == EEH_OPT_THAW_MMIO) &&
+	    (rc & EEH_STATE_MMIO_ENABLED))
+		return 0;
+
+	if ((function == EEH_OPT_THAW_DMA) &&
+	    (rc & EEH_STATE_DMA_ENABLED))
 		return 0;
 
 	return rc;
@@ -612,26 +664,7 @@ static void eeh_reset_pe_once(struct eeh_pe *pe)
 	else
 		eeh_ops->reset(pe, EEH_RESET_HOT);
 
-	/* The PCI bus requires that the reset be held high for at least
-	 * a 100 milliseconds. We wait a bit longer 'just in case'.
-	 */
-#define PCI_BUS_RST_HOLD_TIME_MSEC 250
-	msleep(PCI_BUS_RST_HOLD_TIME_MSEC);
-
-	/* We might get hit with another EEH freeze as soon as the
-	 * pci slot reset line is dropped. Make sure we don't miss
-	 * these, and clear the flag now.
-	 */
-	eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
-
 	eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
-
-	/* After a PCI slot has been reset, the PCI Express spec requires
-	 * a 1.5 second idle time for the bus to stabilize, before starting
-	 * up traffic.
-	 */
-#define PCI_BUS_SETTLE_TIME_MSEC 1800
-	msleep(PCI_BUS_SETTLE_TIME_MSEC);
 }
 
 /**
@@ -651,6 +684,10 @@ int eeh_reset_pe(struct eeh_pe *pe)
 	for (i=0; i<3; i++) {
 		eeh_reset_pe_once(pe);
 
+		/*
+		 * EEH_PE_ISOLATED is expected to be removed after
+		 * BAR restore.
+		 */
 		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
 		if ((rc & flags) == flags)
 			return 0;
@@ -826,8 +863,8 @@ int eeh_init(void)
 			&hose_list, list_node)
 			pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL);
 	} else {
-		pr_warning("%s: Invalid probe mode %d\n",
-			   __func__, eeh_probe_mode);
+		pr_warn("%s: Invalid probe mode %x",
+			__func__, eeh_subsystem_flags);
 		return -EINVAL;
 	}
 
@@ -1102,10 +1139,45 @@ static const struct file_operations proc_eeh_operations = {
 	.release   = single_release,
 };
 
+#ifdef CONFIG_DEBUG_FS
+static int eeh_enable_dbgfs_set(void *data, u64 val)
+{
+	if (val)
+		eeh_subsystem_flags &= ~EEH_FORCE_DISABLED;
+	else
+		eeh_subsystem_flags |= EEH_FORCE_DISABLED;
+
+	/* Notify the backend */
+	if (eeh_ops->post_init)
+		eeh_ops->post_init();
+
+	return 0;
+}
+
+static int eeh_enable_dbgfs_get(void *data, u64 *val)
+{
+	if (eeh_enabled())
+		*val = 0x1ul;
+	else
+		*val = 0x0ul;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(eeh_enable_dbgfs_ops, eeh_enable_dbgfs_get,
+			eeh_enable_dbgfs_set, "0x%llx\n");
+#endif
+
 static int __init eeh_init_proc(void)
 {
-	if (machine_is(pseries) || machine_is(powernv))
+	if (machine_is(pseries) || machine_is(powernv)) {
 		proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
+#ifdef CONFIG_DEBUG_FS
+		debugfs_create_file("eeh_enable", 0600,
+                                    powerpc_debugfs_root, NULL,
+                                    &eeh_enable_dbgfs_ops);
+#endif
+	}
+
 	return 0;
 }
 __initcall(eeh_init_proc);
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index bb61ca58ca6..420da61d4ce 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -171,6 +171,15 @@ static void eeh_enable_irq(struct pci_dev *dev)
 	}
 }
 
+static bool eeh_dev_removed(struct eeh_dev *edev)
+{
+	/* EEH device removed ? */
+	if (!edev || (edev->mode & EEH_DEV_REMOVED))
+		return true;
+
+	return false;
+}
+
 /**
  * eeh_report_error - Report pci error to each device driver
  * @data: eeh device
@@ -187,10 +196,8 @@ static void *eeh_report_error(void *data, void *userdata)
 	enum pci_ers_result rc, *res = userdata;
 	struct pci_driver *driver;
 
-	/* We might not have the associated PCI device,
-	 * then we should continue for next one.
-	 */
-	if (!dev) return NULL;
+	if (!dev || eeh_dev_removed(edev))
+		return NULL;
 	dev->error_state = pci_channel_io_frozen;
 
 	driver = eeh_pcid_get(dev);
@@ -230,6 +237,9 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata)
 	enum pci_ers_result rc, *res = userdata;
 	struct pci_driver *driver;
 
+	if (!dev || eeh_dev_removed(edev))
+		return NULL;
+
 	driver = eeh_pcid_get(dev);
 	if (!driver) return NULL;
 
@@ -267,7 +277,8 @@ static void *eeh_report_reset(void *data, void *userdata)
 	enum pci_ers_result rc, *res = userdata;
 	struct pci_driver *driver;
 
-	if (!dev) return NULL;
+	if (!dev || eeh_dev_removed(edev))
+		return NULL;
 	dev->error_state = pci_channel_io_normal;
 
 	driver = eeh_pcid_get(dev);
@@ -307,7 +318,8 @@ static void *eeh_report_resume(void *data, void *userdata)
 	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
 	struct pci_driver *driver;
 
-	if (!dev) return NULL;
+	if (!dev || eeh_dev_removed(edev))
+		return NULL;
 	dev->error_state = pci_channel_io_normal;
 
 	driver = eeh_pcid_get(dev);
@@ -343,7 +355,8 @@ static void *eeh_report_failure(void *data, void *userdata)
 	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
 	struct pci_driver *driver;
 
-	if (!dev) return NULL;
+	if (!dev || eeh_dev_removed(edev))
+		return NULL;
 	dev->error_state = pci_channel_io_perm_failure;
 
 	driver = eeh_pcid_get(dev);
@@ -380,6 +393,16 @@ static void *eeh_rmv_device(void *data, void *userdata)
 	if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
 		return NULL;
 
+	/*
+	 * We rely on count-based pcibios_release_device() to
+	 * detach permanently offlined PEs. Unfortunately, that's
+	 * not reliable enough. We might have the permanently
+	 * offlined PEs attached, but we needn't take care of
+	 * them and their child devices.
+	 */
+	if (eeh_dev_removed(edev))
+		return NULL;
+
 	driver = eeh_pcid_get(dev);
 	if (driver) {
 		eeh_pcid_put(dev);
@@ -417,6 +440,48 @@ static void *eeh_pe_detach_dev(void *data, void *userdata)
 	return NULL;
 }
 
+/*
+ * Explicitly clear PE's frozen state for PowerNV where
+ * we have frozen PE until BAR restore is completed. It's
+ * harmless to clear it for pSeries. To be consistent with
+ * PE reset (for 3 times), we try to clear the frozen state
+ * for 3 times as well.
+ */
+static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
+{
+	struct eeh_pe *pe = (struct eeh_pe *)data;
+	int i, rc;
+
+	for (i = 0; i < 3; i++) {
+		rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+		if (rc)
+			continue;
+		rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
+		if (!rc)
+			break;
+	}
+
+	/* The PE has been isolated, clear it */
+	if (rc) {
+		pr_warn("%s: Can't clear frozen PHB#%x-PE#%x (%d)\n",
+			__func__, pe->phb->global_number, pe->addr, rc);
+		return (void *)pe;
+	}
+
+	return NULL;
+}
+
+static int eeh_clear_pe_frozen_state(struct eeh_pe *pe)
+{
+	void *rc;
+
+	rc = eeh_pe_traverse(pe, __eeh_clear_pe_frozen_state, NULL);
+	if (!rc)
+		eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+
+	return rc ? -EIO : 0;
+}
+
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
  * @pe: EEH PE
@@ -451,19 +516,33 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 		eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed);
 	}
 
-	/* Reset the pci controller. (Asserts RST#; resets config space).
+	/*
+	 * Reset the pci controller. (Asserts RST#; resets config space).
 	 * Reconfigure bridges and devices. Don't try to bring the system
 	 * up if the reset failed for some reason.
+	 *
+	 * During the reset, it's very dangerous to have uncontrolled PCI
+	 * config accesses. So we prefer to block them. However, controlled
+	 * PCI config accesses initiated from EEH itself are allowed.
 	 */
+	eeh_pe_state_mark(pe, EEH_PE_RESET);
 	rc = eeh_reset_pe(pe);
-	if (rc)
+	if (rc) {
+		eeh_pe_state_clear(pe, EEH_PE_RESET);
 		return rc;
+	}
 
 	pci_lock_rescan_remove();
 
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
+	eeh_pe_state_clear(pe, EEH_PE_RESET);
+
+	/* Clear frozen state */
+	rc = eeh_clear_pe_frozen_state(pe);
+	if (rc)
+		return rc;
 
 	/* Give the system 5 seconds to finish running the user-space
 	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes,
@@ -573,7 +652,6 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 			result = PCI_ERS_RESULT_NEED_RESET;
 		} else {
 			pr_info("EEH: Notify device drivers to resume I/O\n");
-			result = PCI_ERS_RESULT_NONE;
 			eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result);
 		}
 	}
@@ -585,10 +663,17 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 
 		if (rc < 0)
 			goto hard_fail;
-		if (rc)
+		if (rc) {
 			result = PCI_ERS_RESULT_NEED_RESET;
-		else
+		} else {
+			/*
+			 * We didn't do PE reset for the case. The PE
+			 * is still in frozen state. Clear it before
+			 * resuming the PE.
+			 */
+			eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
 			result = PCI_ERS_RESULT_RECOVERED;
+		}
 	}
 
 	/* If any device has a hard failure, then shut off everything. */
@@ -650,8 +735,17 @@ perm_error:
 	/* Notify all devices that they're about to go down. */
 	eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
 
-	/* Shut down the device drivers for good. */
+	/* Mark the PE to be removed permanently */
+	pe->freeze_count = EEH_MAX_ALLOWED_FREEZES + 1;
+
+	/*
+	 * Shut down the device drivers for good. We mark
+	 * all removed devices correctly to avoid access
+	 * the their PCI config any more.
+	 */
 	if (frozen_bus) {
+		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
+
 		pci_lock_rescan_remove();
 		pcibios_remove_pci_devices(frozen_bus);
 		pci_unlock_rescan_remove();
@@ -676,14 +770,13 @@ static void eeh_handle_special_event(void)
 			eeh_serialize_lock(&flags);
 
 			/* Purge all events */
-			eeh_remove_event(NULL);
+			eeh_remove_event(NULL, true);
 
 			list_for_each_entry(hose, &hose_list, list_node) {
 				phb_pe = eeh_phb_pe_get(hose);
 				if (!phb_pe) continue;
 
-				eeh_pe_state_mark(phb_pe,
-					EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
+				eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
 			}
 
 			eeh_serialize_unlock(flags);
@@ -696,11 +789,10 @@ static void eeh_handle_special_event(void)
 			eeh_serialize_lock(&flags);
 
 			/* Purge all events of the PHB */
-			eeh_remove_event(pe);
+			eeh_remove_event(pe, true);
 
 			if (rc == EEH_NEXT_ERR_DEAD_PHB)
-				eeh_pe_state_mark(pe,
-					EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
+				eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 			else
 				eeh_pe_state_mark(pe,
 					EEH_PE_ISOLATED | EEH_PE_RECOVERING);
@@ -724,12 +816,14 @@ static void eeh_handle_special_event(void)
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
 			eeh_handle_normal_event(pe);
+			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		} else {
 			pci_lock_rescan_remove();
 			list_for_each_entry(hose, &hose_list, list_node) {
 				phb_pe = eeh_phb_pe_get(hose);
 				if (!phb_pe ||
-				    !(phb_pe->state & EEH_PE_PHB_DEAD))
+				    !(phb_pe->state & EEH_PE_ISOLATED) ||
+				    (phb_pe->state & EEH_PE_RECOVERING))
 					continue;
 
 				/* Notify all devices to be down */
diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c
index 72d748b56c8..4eefb6e34db 100644
--- a/arch/powerpc/kernel/eeh_event.c
+++ b/arch/powerpc/kernel/eeh_event.c
@@ -152,24 +152,33 @@ int eeh_send_failure_event(struct eeh_pe *pe)
 /**
  * eeh_remove_event - Remove EEH event from the queue
  * @pe: Event binding to the PE
+ * @force: Event will be removed unconditionally
  *
  * On PowerNV platform, we might have subsequent coming events
  * is part of the former one. For that case, those subsequent
  * coming events are totally duplicated and unnecessary, thus
  * they should be removed.
  */
-void eeh_remove_event(struct eeh_pe *pe)
+void eeh_remove_event(struct eeh_pe *pe, bool force)
 {
 	unsigned long flags;
 	struct eeh_event *event, *tmp;
 
+	/*
+	 * If we have NULL PE passed in, we have dead IOC
+	 * or we're sure we can report all existing errors
+	 * by the caller.
+	 *
+	 * With "force", the event with associated PE that
+	 * have been isolated, the event won't be removed
+	 * to avoid event lost.
+	 */
 	spin_lock_irqsave(&eeh_eventlist_lock, flags);
 	list_for_each_entry_safe(event, tmp, &eeh_eventlist, list) {
-		/*
-		 * If we don't have valid PE passed in, that means
-		 * we already have event corresponding to dead IOC
-		 * and all events should be purged.
-		 */
+		if (!force && event->pe &&
+		    (event->pe->state & EEH_PE_ISOLATED))
+			continue;
+
 		if (!pe) {
 			list_del(&event->list);
 			kfree(event);
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index f0c353fa655..fbd01eba447 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -503,13 +503,17 @@ static void *__eeh_pe_state_mark(void *data, void *flag)
 	struct eeh_dev *edev, *tmp;
 	struct pci_dev *pdev;
 
-	/*
-	 * Mark the PE with the indicated state. Also,
-	 * the associated PCI device will be put into
-	 * I/O frozen state to avoid I/O accesses from
-	 * the PCI device driver.
-	 */
+	/* Keep the state of permanently removed PE intact */
+	if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
+	    (state & (EEH_PE_ISOLATED | EEH_PE_RECOVERING)))
+		return NULL;
+
 	pe->state |= state;
+
+	/* Offline PCI devices if applicable */
+	if (state != EEH_PE_ISOLATED)
+		return NULL;
+
 	eeh_pe_for_each_dev(pe, edev, tmp) {
 		pdev = eeh_dev_to_pci_dev(edev);
 		if (pdev)
@@ -532,6 +536,27 @@ void eeh_pe_state_mark(struct eeh_pe *pe, int state)
 	eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
 }
 
+static void *__eeh_pe_dev_mode_mark(void *data, void *flag)
+{
+	struct eeh_dev *edev = data;
+	int mode = *((int *)flag);
+
+	edev->mode |= mode;
+
+	return NULL;
+}
+
+/**
+ * eeh_pe_dev_state_mark - Mark state for all device under the PE
+ * @pe: EEH PE
+ *
+ * Mark specific state for all child devices of the PE.
+ */
+void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode)
+{
+	eeh_pe_dev_traverse(pe, __eeh_pe_dev_mode_mark, &mode);
+}
+
 /**
  * __eeh_pe_state_clear - Clear state for the PE
  * @data: EEH PE
@@ -546,8 +571,16 @@ static void *__eeh_pe_state_clear(void *data, void *flag)
 	struct eeh_pe *pe = (struct eeh_pe *)data;
 	int state = *((int *)flag);
 
+	/* Keep the state of permanently removed PE intact */
+	if ((pe->freeze_count > EEH_MAX_ALLOWED_FREEZES) &&
+	    (state & EEH_PE_ISOLATED))
+		return NULL;
+
 	pe->state &= ~state;
-	pe->check_count = 0;
+
+	/* Clear check count since last isolation */
+	if (state & EEH_PE_ISOLATED)
+		pe->check_count = 0;
 
 	return NULL;
 }
@@ -759,6 +792,66 @@ void eeh_pe_restore_bars(struct eeh_pe *pe)
 }
 
 /**
+ * eeh_pe_loc_get - Retrieve location code binding to the given PE
+ * @pe: EEH PE
+ *
+ * Retrieve the location code of the given PE. If the primary PE bus
+ * is root bus, we will grab location code from PHB device tree node
+ * or root port. Otherwise, the upstream bridge's device tree node
+ * of the primary PE bus will be checked for the location code.
+ */
+const char *eeh_pe_loc_get(struct eeh_pe *pe)
+{
+	struct pci_controller *hose;
+	struct pci_bus *bus = eeh_pe_bus_get(pe);
+	struct pci_dev *pdev;
+	struct device_node *dn;
+	const char *loc;
+
+	if (!bus)
+		return "N/A";
+
+	/* PHB PE or root PE ? */
+	if (pci_is_root_bus(bus)) {
+		hose = pci_bus_to_host(bus);
+		loc = of_get_property(hose->dn,
+				"ibm,loc-code", NULL);
+		if (loc)
+			return loc;
+		loc = of_get_property(hose->dn,
+				"ibm,io-base-loc-code", NULL);
+		if (loc)
+			return loc;
+
+		pdev = pci_get_slot(bus, 0x0);
+	} else {
+		pdev = bus->self;
+	}
+
+	if (!pdev) {
+		loc = "N/A";
+		goto out;
+	}
+
+	dn = pci_device_to_OF_node(pdev);
+	if (!dn) {
+		loc = "N/A";
+		goto out;
+	}
+
+	loc = of_get_property(dn, "ibm,loc-code", NULL);
+	if (!loc)
+		loc = of_get_property(dn, "ibm,slot-location-code", NULL);
+	if (!loc)
+		loc = "N/A";
+
+out:
+	if (pci_is_root_bus(bus) && pdev)
+		pci_dev_put(pdev);
+	return loc;
+}
+
+/**
  * eeh_pe_bus_get - Retrieve PCI bus according to the given PE
  * @pe: EEH PE
  *
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index 5d753d4f2c7..e2595ba4b72 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -59,6 +59,9 @@ void eeh_sysfs_add_device(struct pci_dev *pdev)
 	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
 	int rc=0;
 
+	if (!eeh_enabled())
+		return;
+
 	if (edev && (edev->mode & EEH_DEV_SYSFS))
 		return;
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 662c6dd9807..6528c5e2cc4 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -39,8 +39,8 @@
  * System calls.
  */
 	.section	".toc","aw"
-.SYS_CALL_TABLE:
-	.tc .sys_call_table[TC],.sys_call_table
+SYS_CALL_TABLE:
+	.tc sys_call_table[TC],sys_call_table
 
 /* This value is used to mark exception frames on the stack. */
 exception_marker:
@@ -106,7 +106,7 @@ BEGIN_FW_FTR_SECTION
 	LDX_BE	r10,0,r10		/* get log write index */
 	cmpd	cr1,r11,r10
 	beq+	cr1,33f
-	bl	.accumulate_stolen_time
+	bl	accumulate_stolen_time
 	REST_GPR(0,r1)
 	REST_4GPRS(3,r1)
 	REST_2GPRS(7,r1)
@@ -143,7 +143,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 	std	r10,SOFTE(r1)
 
 #ifdef SHOW_SYSCALLS
-	bl	.do_show_syscall
+	bl	do_show_syscall
 	REST_GPR(0,r1)
 	REST_4GPRS(3,r1)
 	REST_2GPRS(7,r1)
@@ -162,7 +162,7 @@ system_call:			/* label this so stack traces look sane */
  * Need to vector to 32 Bit or default sys_call_table here,
  * based on caller's run-mode / personality.
  */
-	ld	r11,.SYS_CALL_TABLE@toc(2)
+	ld	r11,SYS_CALL_TABLE@toc(2)
 	andi.	r10,r10,_TIF_32BIT
 	beq	15f
 	addi	r11,r11,8	/* use 32-bit syscall entries */
@@ -174,14 +174,14 @@ system_call:			/* label this so stack traces look sane */
 	clrldi	r8,r8,32
 15:
 	slwi	r0,r0,4
-	ldx	r10,r11,r0	/* Fetch system call handler [ptr] */
-	mtctr   r10
+	ldx	r12,r11,r0	/* Fetch system call handler [ptr] */
+	mtctr   r12
 	bctrl			/* Call handler */
 
 syscall_exit:
 	std	r3,RESULT(r1)
 #ifdef SHOW_SYSCALLS
-	bl	.do_show_syscall_exit
+	bl	do_show_syscall_exit
 	ld	r3,RESULT(r1)
 #endif
 	CURRENT_THREAD_INFO(r12, r1)
@@ -248,9 +248,9 @@ syscall_error:
 	
 /* Traced system call support */
 syscall_dotrace:
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_syscall_trace_enter
+	bl	do_syscall_trace_enter
 	/*
 	 * Restore argument registers possibly just changed.
 	 * We use the return value of do_syscall_trace_enter
@@ -308,7 +308,7 @@ syscall_exit_work:
 4:	/* Anything else left to do? */
 	SET_DEFAULT_THREAD_PPR(r3, r10)		/* Set thread.ppr = 3 */
 	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
-	beq	.ret_from_except_lite
+	beq	ret_from_except_lite
 
 	/* Re-enable interrupts */
 #ifdef CONFIG_PPC_BOOK3E
@@ -319,10 +319,10 @@ syscall_exit_work:
 	mtmsrd	r10,1
 #endif /* CONFIG_PPC_BOOK3E */
 
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_syscall_trace_leave
-	b	.ret_from_except
+	bl	do_syscall_trace_leave
+	b	ret_from_except
 
 /* Save non-volatile GPRs, if not already saved. */
 _GLOBAL(save_nvgprs)
@@ -345,52 +345,48 @@ _GLOBAL(save_nvgprs)
  */
 
 _GLOBAL(ppc_fork)
-	bl	.save_nvgprs
-	bl	.sys_fork
+	bl	save_nvgprs
+	bl	sys_fork
 	b	syscall_exit
 
 _GLOBAL(ppc_vfork)
-	bl	.save_nvgprs
-	bl	.sys_vfork
+	bl	save_nvgprs
+	bl	sys_vfork
 	b	syscall_exit
 
 _GLOBAL(ppc_clone)
-	bl	.save_nvgprs
-	bl	.sys_clone
+	bl	save_nvgprs
+	bl	sys_clone
 	b	syscall_exit
 
 _GLOBAL(ppc32_swapcontext)
-	bl	.save_nvgprs
-	bl	.compat_sys_swapcontext
+	bl	save_nvgprs
+	bl	compat_sys_swapcontext
 	b	syscall_exit
 
 _GLOBAL(ppc64_swapcontext)
-	bl	.save_nvgprs
-	bl	.sys_swapcontext
+	bl	save_nvgprs
+	bl	sys_swapcontext
 	b	syscall_exit
 
 _GLOBAL(ret_from_fork)
-	bl	.schedule_tail
+	bl	schedule_tail
 	REST_NVGPRS(r1)
 	li	r3,0
 	b	syscall_exit
 
 _GLOBAL(ret_from_kernel_thread)
-	bl	.schedule_tail
+	bl	schedule_tail
 	REST_NVGPRS(r1)
-	ld	r14, 0(r14)
 	mtlr	r14
 	mr	r3,r15
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+	mr	r12,r14
+#endif
 	blrl
 	li	r3,0
 	b	syscall_exit
 
-	.section	".toc","aw"
-DSCR_DEFAULT:
-	.tc dscr_default[TC],dscr_default
-
-	.section	".text"
-
 /*
  * This routine switches between two different tasks.  The process
  * state of one is saved on its kernel stack.  Then the state
@@ -432,12 +428,6 @@ BEGIN_FTR_SECTION
 	std	r24,THREAD_VRSAVE(r3)
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif /* CONFIG_ALTIVEC */
-#ifdef CONFIG_PPC64
-BEGIN_FTR_SECTION
-	mfspr	r25,SPRN_DSCR
-	std	r25,THREAD_DSCR(r3)
-END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
-#endif
 	and.	r0,r0,r22
 	beq+	1f
 	andc	r22,r22,r0
@@ -575,11 +565,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
 	lwz	r6,THREAD_DSCR_INHERIT(r4)
-	ld	r7,DSCR_DEFAULT@toc(2)
 	ld	r0,THREAD_DSCR(r4)
 	cmpwi	r6,0
 	bne	1f
-	ld	r0,0(r7)
+	ld	r0,PACA_DSCR(r13)
 1:
 BEGIN_FTR_SECTION_NESTED(70)
 	mfspr	r8, SPRN_FSCR
@@ -611,7 +600,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 _GLOBAL(ret_from_except)
 	ld	r11,_TRAP(r1)
 	andi.	r0,r11,1
-	bne	.ret_from_except_lite
+	bne	ret_from_except_lite
 	REST_NVGPRS(r1)
 
 _GLOBAL(ret_from_except_lite)
@@ -661,23 +650,23 @@ _GLOBAL(ret_from_except_lite)
 #endif
 1:	andi.	r0,r4,_TIF_NEED_RESCHED
 	beq	2f
-	bl	.restore_interrupts
+	bl	restore_interrupts
 	SCHEDULE_USER
-	b	.ret_from_except_lite
+	b	ret_from_except_lite
 2:
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	andi.	r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM
 	bne	3f		/* only restore TM if nothing else to do */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.restore_tm_state
+	bl	restore_tm_state
 	b	restore
 3:
 #endif
-	bl	.save_nvgprs
-	bl	.restore_interrupts
+	bl	save_nvgprs
+	bl	restore_interrupts
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_notify_resume
-	b	.ret_from_except
+	bl	do_notify_resume
+	b	ret_from_except
 
 resume_kernel:
 	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
@@ -730,7 +719,7 @@ resume_kernel:
 	 * sure we are soft-disabled first and reconcile irq state.
 	 */
 	RECONCILE_IRQ_STATE(r3,r4)
-1:	bl	.preempt_schedule_irq
+1:	bl	preempt_schedule_irq
 
 	/* Re-test flags and eventually loop */
 	CURRENT_THREAD_INFO(r9, r1)
@@ -792,7 +781,7 @@ restore_no_replay:
 	 */
 do_restore:
 #ifdef CONFIG_PPC_BOOK3E
-	b	.exception_return_book3e
+	b	exception_return_book3e
 #else
 	/*
 	 * Clear the reservation. If we know the CPU tracks the address of
@@ -907,7 +896,7 @@ restore_check_irq_replay:
 	 *
 	 * Still, this might be useful for things like hash_page
 	 */
-	bl	.__check_irq_replay
+	bl	__check_irq_replay
 	cmpwi	cr0,r3,0
  	beq	restore_no_replay
  
@@ -928,13 +917,13 @@ restore_check_irq_replay:
 	cmpwi	cr0,r3,0x500
 	bne	1f
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
- 	bl	.do_IRQ
-	b	.ret_from_except
+ 	bl	do_IRQ
+	b	ret_from_except
 1:	cmpwi	cr0,r3,0x900
 	bne	1f
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	.timer_interrupt
-	b	.ret_from_except
+	bl	timer_interrupt
+	b	ret_from_except
 #ifdef CONFIG_PPC_DOORBELL
 1:
 #ifdef CONFIG_PPC_BOOK3E
@@ -948,14 +937,14 @@ restore_check_irq_replay:
 #endif /* CONFIG_PPC_BOOK3E */
 	bne	1f
 	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	.doorbell_exception
-	b	.ret_from_except
+	bl	doorbell_exception
+	b	ret_from_except
 #endif /* CONFIG_PPC_DOORBELL */
-1:	b	.ret_from_except /* What else to do here ? */
+1:	b	ret_from_except /* What else to do here ? */
  
 unrecov_restore:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
+	bl	unrecoverable_exception
 	b	unrecov_restore
 
 #ifdef CONFIG_PPC_RTAS
@@ -1021,7 +1010,7 @@ _GLOBAL(enter_rtas)
         std	r6,PACASAVEDMSR(r13)
 
 	/* Setup our real return addr */	
-	LOAD_REG_ADDR(r4,.rtas_return_loc)
+	LOAD_REG_ADDR(r4,rtas_return_loc)
 	clrldi	r4,r4,2			/* convert to realmode address */
        	mtlr	r4
 
@@ -1045,7 +1034,7 @@ _GLOBAL(enter_rtas)
 	rfid
 	b	.	/* prevent speculative execution */
 
-_STATIC(rtas_return_loc)
+rtas_return_loc:
 	FIXUP_ENDIAN
 
 	/* relocation is off at this point */
@@ -1054,7 +1043,7 @@ _STATIC(rtas_return_loc)
 
 	bcl	20,31,$+4
 0:	mflr	r3
-	ld	r3,(1f-0b)(r3)		/* get &.rtas_restore_regs */
+	ld	r3,(1f-0b)(r3)		/* get &rtas_restore_regs */
 
 	mfmsr   r6
 	li	r0,MSR_RI
@@ -1071,9 +1060,9 @@ _STATIC(rtas_return_loc)
 	b	.	/* prevent speculative execution */
 
 	.align	3
-1:	.llong	.rtas_restore_regs
+1:	.llong	rtas_restore_regs
 
-_STATIC(rtas_restore_regs)
+rtas_restore_regs:
 	/* relocation is on at this point */
 	REST_GPR(2, r1)			/* Restore the TOC */
 	REST_GPR(13, r1)		/* Restore paca */
@@ -1173,7 +1162,7 @@ _GLOBAL(mcount)
 _GLOBAL(_mcount)
 	blr
 
-_GLOBAL(ftrace_caller)
+_GLOBAL_TOC(ftrace_caller)
 	/* Taken from output of objdump from lib64/glibc */
 	mflr	r3
 	ld	r11, 0(r1)
@@ -1197,10 +1186,7 @@ _GLOBAL(ftrace_graph_stub)
 _GLOBAL(ftrace_stub)
 	blr
 #else
-_GLOBAL(mcount)
-	blr
-
-_GLOBAL(_mcount)
+_GLOBAL_TOC(_mcount)
 	/* Taken from output of objdump from lib64/glibc */
 	mflr	r3
 	ld	r11, 0(r1)
@@ -1238,7 +1224,7 @@ _GLOBAL(ftrace_graph_caller)
 	ld	r11, 112(r1)
 	addi	r3, r11, 16
 
-	bl	.prepare_ftrace_return
+	bl	prepare_ftrace_return
 	nop
 
 	ld	r0, 128(r1)
@@ -1254,7 +1240,7 @@ _GLOBAL(return_to_handler)
 	mr	r31, r1
 	stdu	r1, -112(r1)
 
-	bl	.ftrace_return_to_handler
+	bl	ftrace_return_to_handler
 	nop
 
 	/* return value has real return address */
@@ -1284,7 +1270,7 @@ _GLOBAL(mod_return_to_handler)
 	 */
 	ld	r2, PACATOC(r13)
 
-	bl	.ftrace_return_to_handler
+	bl	ftrace_return_to_handler
 	nop
 
 	/* return value has real return address */
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
index 60d1a2259db..59e4ba74975 100644
--- a/arch/powerpc/kernel/epapr_paravirt.c
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -30,6 +30,7 @@ extern u32 epapr_ev_idle_start[];
 #endif
 
 bool epapr_paravirt_enabled;
+static bool __maybe_unused epapr_has_idle;
 
 static int __init early_init_dt_scan_epapr(unsigned long node,
 					   const char *uname,
@@ -56,7 +57,7 @@ static int __init early_init_dt_scan_epapr(unsigned long node,
 
 #if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
 	if (of_get_flat_dt_prop(node, "has-idle", NULL))
-		ppc_md.power_save = epapr_ev_idle;
+		epapr_has_idle = true;
 #endif
 
 	epapr_paravirt_enabled = true;
@@ -71,3 +72,14 @@ int __init epapr_paravirt_early_init(void)
 	return 0;
 }
 
+static int __init epapr_idle_init(void)
+{
+#if !defined(CONFIG_64BIT) || defined(CONFIG_PPC_BOOK3E_64)
+	if (epapr_has_idle)
+		ppc_md.power_save = epapr_ev_idle;
+#endif
+
+	return 0;
+}
+
+postcore_initcall(epapr_idle_init);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index c1bee3ce9d1..bb9cac6c805 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -499,7 +499,7 @@ exc_##n##_bad_stack:							    \
 	CHECK_NAPPING();						\
 	addi	r3,r1,STACK_FRAME_OVERHEAD;				\
 	bl	hdlr;							\
-	b	.ret_from_except_lite;
+	b	ret_from_except_lite;
 
 /* This value is used to mark exception frames on the stack. */
 	.section	".toc","aw"
@@ -550,11 +550,11 @@ interrupt_end_book3e:
 	CRIT_EXCEPTION_PROLOG(0x100, BOOKE_INTERRUPT_CRITICAL,
 			      PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_CRIT(0x100)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unknown_exception
+	bl	unknown_exception
 	b	ret_from_crit_except
 
 /* Machine Check Interrupt */
@@ -562,11 +562,11 @@ interrupt_end_book3e:
 	MC_EXCEPTION_PROLOG(0x000, BOOKE_INTERRUPT_MACHINE_CHECK,
 			    PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_MC(0x000)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.machine_check_exception
+	bl	machine_check_exception
 	b	ret_from_mc_except
 
 /* Data Storage Interrupt */
@@ -591,7 +591,7 @@ interrupt_end_book3e:
 
 /* External Input Interrupt */
 	MASKABLE_EXCEPTION(0x500, BOOKE_INTERRUPT_EXTERNAL,
-			   external_input, .do_IRQ, ACK_NONE)
+			   external_input, do_IRQ, ACK_NONE)
 
 /* Alignment */
 	START_EXCEPTION(alignment);
@@ -612,9 +612,9 @@ interrupt_end_book3e:
 	std	r14,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r14,PACA_EXGEN+EX_R14(r13)
-	bl	.save_nvgprs
-	bl	.program_check_exception
-	b	.ret_from_except
+	bl	save_nvgprs
+	bl	program_check_exception
+	b	ret_from_except
 
 /* Floating Point Unavailable Interrupt */
 	START_EXCEPTION(fp_unavailable);
@@ -625,13 +625,13 @@ interrupt_end_book3e:
 	ld	r12,_MSR(r1)
 	andi.	r0,r12,MSR_PR;
 	beq-	1f
-	bl	.load_up_fpu
+	bl	load_up_fpu
 	b	fast_exception_return
 1:	INTS_DISABLE
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.kernel_fp_unavailable_exception
-	b	.ret_from_except
+	bl	kernel_fp_unavailable_exception
+	b	ret_from_except
 
 /* Altivec Unavailable Interrupt */
 	START_EXCEPTION(altivec_unavailable);
@@ -644,16 +644,16 @@ BEGIN_FTR_SECTION
 	ld	r12,_MSR(r1)
 	andi.	r0,r12,MSR_PR;
 	beq-	1f
-	bl	.load_up_altivec
+	bl	load_up_altivec
 	b	fast_exception_return
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 	INTS_DISABLE
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.altivec_unavailable_exception
-	b	.ret_from_except
+	bl	altivec_unavailable_exception
+	b	ret_from_except
 
 /* AltiVec Assist */
 	START_EXCEPTION(altivec_assist);
@@ -662,39 +662,39 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 				PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0x220)
 	INTS_DISABLE
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
-	bl	.altivec_assist_exception
+	bl	altivec_assist_exception
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #else
-	bl	.unknown_exception
+	bl	unknown_exception
 #endif
-	b	.ret_from_except
+	b	ret_from_except
 
 
 /* Decrementer Interrupt */
 	MASKABLE_EXCEPTION(0x900, BOOKE_INTERRUPT_DECREMENTER,
-			   decrementer, .timer_interrupt, ACK_DEC)
+			   decrementer, timer_interrupt, ACK_DEC)
 
 /* Fixed Interval Timer Interrupt */
 	MASKABLE_EXCEPTION(0x980, BOOKE_INTERRUPT_FIT,
-			   fixed_interval, .unknown_exception, ACK_FIT)
+			   fixed_interval, unknown_exception, ACK_FIT)
 
 /* Watchdog Timer Interrupt */
 	START_EXCEPTION(watchdog);
 	CRIT_EXCEPTION_PROLOG(0x9f0, BOOKE_INTERRUPT_WATCHDOG,
 			      PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_CRIT(0x9f0)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_BOOKE_WDT
-	bl	.WatchdogException
+	bl	WatchdogException
 #else
-	bl	.unknown_exception
+	bl	unknown_exception
 #endif
 	b	ret_from_crit_except
 
@@ -712,10 +712,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 				PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0xf20)
 	INTS_DISABLE
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unknown_exception
-	b	.ret_from_except
+	bl	unknown_exception
+	b	ret_from_except
 
 /* Debug exception as a critical interrupt*/
 	START_EXCEPTION(debug_crit);
@@ -774,9 +774,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	mr	r4,r14
 	ld	r14,PACA_EXCRIT+EX_R14(r13)
 	ld	r15,PACA_EXCRIT+EX_R15(r13)
-	bl	.save_nvgprs
-	bl	.DebugException
-	b	.ret_from_except
+	bl	save_nvgprs
+	bl	DebugException
+	b	ret_from_except
 
 kernel_dbg_exc:
 	b	.	/* NYI */
@@ -839,9 +839,9 @@ kernel_dbg_exc:
 	mr	r4,r14
 	ld	r14,PACA_EXDBG+EX_R14(r13)
 	ld	r15,PACA_EXDBG+EX_R15(r13)
-	bl	.save_nvgprs
-	bl	.DebugException
-	b	.ret_from_except
+	bl	save_nvgprs
+	bl	DebugException
+	b	ret_from_except
 
 	START_EXCEPTION(perfmon);
 	NORMAL_EXCEPTION_PROLOG(0x260, BOOKE_INTERRUPT_PERFORMANCE_MONITOR,
@@ -850,23 +850,23 @@ kernel_dbg_exc:
 	INTS_DISABLE
 	CHECK_NAPPING()
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.performance_monitor_exception
-	b	.ret_from_except_lite
+	bl	performance_monitor_exception
+	b	ret_from_except_lite
 
 /* Doorbell interrupt */
 	MASKABLE_EXCEPTION(0x280, BOOKE_INTERRUPT_DOORBELL,
-			   doorbell, .doorbell_exception, ACK_NONE)
+			   doorbell, doorbell_exception, ACK_NONE)
 
 /* Doorbell critical Interrupt */
 	START_EXCEPTION(doorbell_crit);
 	CRIT_EXCEPTION_PROLOG(0x2a0, BOOKE_INTERRUPT_DOORBELL_CRITICAL,
 			      PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_CRIT(0x2a0)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unknown_exception
+	bl	unknown_exception
 	b	ret_from_crit_except
 
 /*
@@ -878,21 +878,21 @@ kernel_dbg_exc:
 			        PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0x2c0)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	INTS_RESTORE_HARD
-	bl	.unknown_exception
-	b	.ret_from_except
+	bl	unknown_exception
+	b	ret_from_except
 
 /* Guest Doorbell critical Interrupt */
 	START_EXCEPTION(guest_doorbell_crit);
 	CRIT_EXCEPTION_PROLOG(0x2e0, BOOKE_INTERRUPT_GUEST_DBELL_CRIT,
 			      PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON_CRIT(0x2e0)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	bl	special_reg_save
 	CHECK_NAPPING();
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unknown_exception
+	bl	unknown_exception
 	b	ret_from_crit_except
 
 /* Hypervisor call */
@@ -901,10 +901,10 @@ kernel_dbg_exc:
 			        PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0x310)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	INTS_RESTORE_HARD
-	bl	.unknown_exception
-	b	.ret_from_except
+	bl	unknown_exception
+	b	ret_from_except
 
 /* Embedded Hypervisor priviledged  */
 	START_EXCEPTION(ehpriv);
@@ -912,10 +912,10 @@ kernel_dbg_exc:
 			        PROLOG_ADDITION_NONE)
 	EXCEPTION_COMMON(0x320)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	INTS_RESTORE_HARD
-	bl	.unknown_exception
-	b	.ret_from_except
+	bl	unknown_exception
+	b	ret_from_except
 
 /* LRAT Error interrupt */
 	START_EXCEPTION(lrat_error);
@@ -1014,16 +1014,16 @@ storage_fault_common:
 	mr	r5,r15
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
-	bl	.do_page_fault
+	bl	do_page_fault
 	cmpdi	r3,0
 	bne-	1f
-	b	.ret_from_except_lite
-1:	bl	.save_nvgprs
+	b	ret_from_except_lite
+1:	bl	save_nvgprs
 	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r4,_DAR(r1)
-	bl	.bad_page_fault
-	b	.ret_from_except
+	bl	bad_page_fault
+	b	ret_from_except
 
 /*
  * Alignment exception doesn't fit entirely in the 0x100 bytes so it
@@ -1035,10 +1035,10 @@ alignment_more:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r14,PACA_EXGEN+EX_R14(r13)
 	ld	r15,PACA_EXGEN+EX_R15(r13)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	INTS_RESTORE_HARD
-	bl	.alignment_exception
-	b	.ret_from_except
+	bl	alignment_exception
+	b	ret_from_except
 
 /*
  * We branch here from entry_64.S for the last stage of the exception
@@ -1172,7 +1172,7 @@ bad_stack_book3e:
 	std	r12,0(r11)
 	ld	r2,PACATOC(r13)
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.kernel_bad_stack
+	bl	kernel_bad_stack
 	b	1b
 
 /*
@@ -1467,22 +1467,6 @@ a2_tlbinit_after_linear_map:
 	.globl  a2_tlbinit_after_iprot_flush
 a2_tlbinit_after_iprot_flush:
 
-#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
-	/* Now establish early debug mappings if applicable */
-	/* Restore the MAS0 we used for linear mapping load */
-	mtspr	SPRN_MAS0,r11
-
-	lis	r3,(MAS1_VALID | MAS1_IPROT)@h
-	ori	r3,r3,(BOOK3E_PAGESZ_4K << MAS1_TSIZE_SHIFT)
-	mtspr	SPRN_MAS1,r3
-	LOAD_REG_IMMEDIATE(r3, WSP_UART_VIRT | MAS2_I | MAS2_G)
-	mtspr	SPRN_MAS2,r3
-	LOAD_REG_IMMEDIATE(r3, WSP_UART_PHYS | MAS3_SR | MAS3_SW)
-	mtspr	SPRN_MAS7_MAS3,r3
-	/* re-use the MAS8 value from the linear mapping */
-	tlbwe
-#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */
-
 	PPC_TLBILX(0,0,R0)
 	sync
 	isync
@@ -1521,13 +1505,13 @@ _GLOBAL(start_initialization_book3e)
 	 * and always use AS 0, so we just set it up to match our link
 	 * address and never use 0 based addresses.
 	 */
-	bl	.initial_tlb_book3e
+	bl	initial_tlb_book3e
 
 	/* Init global core bits */
-	bl	.init_core_book3e
+	bl	init_core_book3e
 
 	/* Init per-thread bits */
-	bl	.init_thread_book3e
+	bl	init_thread_book3e
 
 	/* Return to common init code */
 	tovirt(r28,r28)
@@ -1548,7 +1532,7 @@ _GLOBAL(start_initialization_book3e)
  */
 _GLOBAL(book3e_secondary_core_init_tlb_set)
 	li	r4,1
-	b	.generic_secondary_smp_init
+	b	generic_secondary_smp_init
 
 _GLOBAL(book3e_secondary_core_init)
 	mflr	r28
@@ -1558,18 +1542,18 @@ _GLOBAL(book3e_secondary_core_init)
 	bne	2f
 
 	/* Setup TLB for this core */
-	bl	.initial_tlb_book3e
+	bl	initial_tlb_book3e
 
 	/* We can return from the above running at a different
 	 * address, so recalculate r2 (TOC)
 	 */
-	bl	.relative_toc
+	bl	relative_toc
 
 	/* Init global core bits */
-2:	bl	.init_core_book3e
+2:	bl	init_core_book3e
 
 	/* Init per-thread bits */
-3:	bl	.init_thread_book3e
+3:	bl	init_thread_book3e
 
 	/* Return to common init code at proper virtual address.
 	 *
@@ -1596,14 +1580,14 @@ _GLOBAL(book3e_secondary_thread_init)
 	mflr	r28
 	b	3b
 
-_STATIC(init_core_book3e)
+init_core_book3e:
 	/* Establish the interrupt vector base */
 	LOAD_REG_IMMEDIATE(r3, interrupt_base_book3e)
 	mtspr	SPRN_IVPR,r3
 	sync
 	blr
 
-_STATIC(init_thread_book3e)
+init_thread_book3e:
 	lis	r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h
 	mtspr	SPRN_EPCR,r3
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 3afd3915921..a7d36b19221 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -132,12 +132,12 @@ BEGIN_FTR_SECTION
 #endif
 
 	beq	cr1,2f
-	b	.power7_wakeup_noloss
-2:	b	.power7_wakeup_loss
+	b	power7_wakeup_noloss
+2:	b	power7_wakeup_loss
 
 	/* Fast Sleep wakeup on PowerNV */
 8:	GET_PACA(r13)
-	b 	.power7_wakeup_tb_loss
+	b 	power7_wakeup_tb_loss
 
 9:
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
@@ -211,16 +211,16 @@ data_access_slb_pSeries:
 #endif /* __DISABLED__ */
 	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
-	b	.slb_miss_realmode
+	b	slb_miss_realmode
 #else
 	/*
-	 * We can't just use a direct branch to .slb_miss_realmode
+	 * We can't just use a direct branch to slb_miss_realmode
 	 * because the distance from here to there depends on where
 	 * the kernel ends up being put.
 	 */
 	mfctr	r11
 	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, .slb_miss_realmode)
+	LOAD_HANDLER(r10, slb_miss_realmode)
 	mtctr	r10
 	bctr
 #endif
@@ -243,11 +243,11 @@ instruction_access_slb_pSeries:
 #endif /* __DISABLED__ */
 	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
-	b	.slb_miss_realmode
+	b	slb_miss_realmode
 #else
 	mfctr	r11
 	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, .slb_miss_realmode)
+	LOAD_HANDLER(r10, slb_miss_realmode)
 	mtctr	r10
 	bctr
 #endif
@@ -439,9 +439,9 @@ BEGIN_FTR_SECTION
 	 * R9		= CR
 	 * Original R9 to R13 is saved on PACA_EXMC
 	 *
-	 * Switch to mc_emergency stack and handle re-entrancy (though we
-	 * currently don't test for overflow). Save MCE registers srr1,
-	 * srr0, dar and dsisr and then set ME=1
+	 * Switch to mc_emergency stack and handle re-entrancy (we limit
+	 * the nested MCE upto level 4 to avoid stack overflow).
+	 * Save MCE registers srr1, srr0, dar and dsisr and then set ME=1
 	 *
 	 * We use paca->in_mce to check whether this is the first entry or
 	 * nested machine check. We increment paca->in_mce to track nested
@@ -464,6 +464,9 @@ BEGIN_FTR_SECTION
 0:	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame */
 	addi	r10,r10,1		/* increment paca->in_mce */
 	sth	r10,PACA_IN_MCE(r13)
+	/* Limit nested MCE to level 4 to avoid stack overflow */
+	cmpwi	r10,4
+	bgt	2f			/* Check if we hit limit of 4 */
 	std	r11,GPR1(r1)		/* Save r1 on the stack. */
 	std	r11,0(r1)		/* make stack chain pointer */
 	mfspr	r11,SPRN_SRR0		/* Save SRR0 */
@@ -482,10 +485,23 @@ BEGIN_FTR_SECTION
 	ori	r11,r11,MSR_RI		/* turn on RI bit */
 	ld	r12,PACAKBASE(r13)	/* get high part of &label */
 	LOAD_HANDLER(r12, machine_check_handle_early)
-	mtspr	SPRN_SRR0,r12
+1:	mtspr	SPRN_SRR0,r12
 	mtspr	SPRN_SRR1,r11
 	rfid
 	b	.	/* prevent speculative execution */
+2:
+	/* Stack overflow. Stay on emergency stack and panic.
+	 * Keep the ME bit off while panic-ing, so that if we hit
+	 * another machine check we checkstop.
+	 */
+	addi	r1,r1,INT_FRAME_SIZE	/* go back to previous stack frame */
+	ld	r11,PACAKMSR(r13)
+	ld	r12,PACAKBASE(r13)
+	LOAD_HANDLER(r12, unrecover_mce)
+	li	r10,MSR_ME
+	andc	r11,r11,r10		/* Turn off MSR_ME */
+	b	1b
+	b	.	/* prevent speculative execution */
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 
 machine_check_pSeries:
@@ -524,7 +540,7 @@ do_stab_bolted_pSeries:
 	std	r12,PACA_EXSLB+EX_R12(r13)
 	GET_SCRATCH0(r10)
 	std	r10,PACA_EXSLB+EX_R13(r13)
-	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
+	EXCEPTION_PROLOG_PSERIES_1(do_stab_bolted, EXC_STD)
 
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
 	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
@@ -769,38 +785,38 @@ kvmppc_skip_Hinterrupt:
 
 /*** Common interrupt handlers ***/
 
-	STD_EXCEPTION_COMMON(0x100, system_reset, .system_reset_exception)
+	STD_EXCEPTION_COMMON(0x100, system_reset, system_reset_exception)
 
 	STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
-	STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
-	STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt)
+	STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, timer_interrupt)
+	STD_EXCEPTION_COMMON(0x980, hdecrementer, hdec_interrupt)
 #ifdef CONFIG_PPC_DOORBELL
-	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .doorbell_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, doorbell_exception)
 #else
-	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, .unknown_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xa00, doorbell_super, unknown_exception)
 #endif
-	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
-	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
-	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
-	STD_EXCEPTION_COMMON(0xe40, emulation_assist, .emulation_assist_interrupt)
-	STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xb00, trap_0b, unknown_exception)
+	STD_EXCEPTION_COMMON(0xd00, single_step, single_step_exception)
+	STD_EXCEPTION_COMMON(0xe00, trap_0e, unknown_exception)
+	STD_EXCEPTION_COMMON(0xe40, emulation_assist, emulation_assist_interrupt)
+	STD_EXCEPTION_COMMON(0xe60, hmi_exception, unknown_exception)
 #ifdef CONFIG_PPC_DOORBELL
-	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .doorbell_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, doorbell_exception)
 #else
-	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .unknown_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, unknown_exception)
 #endif
-	STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, .performance_monitor_exception)
-	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
-	STD_EXCEPTION_COMMON(0x1502, denorm, .unknown_exception)
+	STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, performance_monitor_exception)
+	STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, instruction_breakpoint_exception)
+	STD_EXCEPTION_COMMON(0x1502, denorm, unknown_exception)
 #ifdef CONFIG_ALTIVEC
-	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, altivec_assist_exception)
 #else
-	STD_EXCEPTION_COMMON(0x1700, altivec_assist, .unknown_exception)
+	STD_EXCEPTION_COMMON(0x1700, altivec_assist, unknown_exception)
 #endif
 #ifdef CONFIG_CBE_RAS
-	STD_EXCEPTION_COMMON(0x1200, cbe_system_error, .cbe_system_error_exception)
-	STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, .cbe_maintenance_exception)
-	STD_EXCEPTION_COMMON(0x1800, cbe_thermal, .cbe_thermal_exception)
+	STD_EXCEPTION_COMMON(0x1200, cbe_system_error, cbe_system_error_exception)
+	STD_EXCEPTION_COMMON(0x1600, cbe_maintenance, cbe_maintenance_exception)
+	STD_EXCEPTION_COMMON(0x1800, cbe_thermal, cbe_thermal_exception)
 #endif /* CONFIG_CBE_RAS */
 
 	/*
@@ -829,16 +845,16 @@ data_access_slb_relon_pSeries:
 	mfspr	r3,SPRN_DAR
 	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
-	b	.slb_miss_realmode
+	b	slb_miss_realmode
 #else
 	/*
-	 * We can't just use a direct branch to .slb_miss_realmode
+	 * We can't just use a direct branch to slb_miss_realmode
 	 * because the distance from here to there depends on where
 	 * the kernel ends up being put.
 	 */
 	mfctr	r11
 	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, .slb_miss_realmode)
+	LOAD_HANDLER(r10, slb_miss_realmode)
 	mtctr	r10
 	bctr
 #endif
@@ -854,11 +870,11 @@ instruction_access_slb_relon_pSeries:
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
 	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
-	b	.slb_miss_realmode
+	b	slb_miss_realmode
 #else
 	mfctr	r11
 	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, .slb_miss_realmode)
+	LOAD_HANDLER(r10, slb_miss_realmode)
 	mtctr	r10
 	bctr
 #endif
@@ -966,7 +982,7 @@ system_call_entry:
 	b	system_call_common
 
 ppc64_runlatch_on_trampoline:
-	b	.__ppc64_runlatch_on
+	b	__ppc64_runlatch_on
 
 /*
  * Here we have detected that the kernel stack pointer is bad.
@@ -1025,7 +1041,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	std	r12,RESULT(r1)
 	std	r11,STACK_FRAME_OVERHEAD-16(r1)
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.kernel_bad_stack
+	bl	kernel_bad_stack
 	b	1b
 
 /*
@@ -1046,7 +1062,7 @@ data_access_common:
 	ld	r3,PACA_EXGEN+EX_DAR(r13)
 	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
 	li	r5,0x300
-	b	.do_hash_page		/* Try to handle as hpte fault */
+	b	do_hash_page		/* Try to handle as hpte fault */
 
 	.align  7
 	.globl  h_data_storage_common
@@ -1056,11 +1072,11 @@ h_data_storage_common:
 	mfspr   r10,SPRN_HDSISR
 	stw     r10,PACA_EXGEN+EX_DSISR(r13)
 	EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN)
-	bl      .save_nvgprs
+	bl      save_nvgprs
 	DISABLE_INTS
 	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl      .unknown_exception
-	b       .ret_from_except
+	bl      unknown_exception
+	b       ret_from_except
 
 	.align	7
 	.globl instruction_access_common
@@ -1071,9 +1087,9 @@ instruction_access_common:
 	ld	r3,_NIP(r1)
 	andis.	r4,r12,0x5820
 	li	r5,0x400
-	b	.do_hash_page		/* Try to handle as hpte fault */
+	b	do_hash_page		/* Try to handle as hpte fault */
 
-	STD_EXCEPTION_COMMON(0xe20, h_instr_storage, .unknown_exception)
+	STD_EXCEPTION_COMMON(0xe20, h_instr_storage, unknown_exception)
 
 /*
  * Here is the common SLB miss user that is used when going to virtual
@@ -1088,7 +1104,7 @@ slb_miss_user_common:
 	stw	r9,PACA_EXGEN+EX_CCR(r13)
 	std	r10,PACA_EXGEN+EX_LR(r13)
 	std	r11,PACA_EXGEN+EX_SRR0(r13)
-	bl	.slb_allocate_user
+	bl	slb_allocate_user
 
 	ld	r10,PACA_EXGEN+EX_LR(r13)
 	ld	r3,PACA_EXGEN+EX_R3(r13)
@@ -1131,9 +1147,9 @@ slb_miss_fault:
 unrecov_user_slb:
 	EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN)
 	DISABLE_INTS
-	bl	.save_nvgprs
+	bl	save_nvgprs
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
+	bl	unrecoverable_exception
 	b	1b
 
 #endif /* __DISABLED__ */
@@ -1158,10 +1174,10 @@ machine_check_common:
 	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.machine_check_exception
-	b	.ret_from_except
+	bl	machine_check_exception
+	b	ret_from_except
 
 	.align	7
 	.globl alignment_common
@@ -1175,31 +1191,31 @@ alignment_common:
 	lwz	r4,PACA_EXGEN+EX_DSISR(r13)
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.alignment_exception
-	b	.ret_from_except
+	bl	alignment_exception
+	b	ret_from_except
 
 	.align	7
 	.globl program_check_common
 program_check_common:
 	EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.program_check_exception
-	b	.ret_from_except
+	bl	program_check_exception
+	b	ret_from_except
 
 	.align	7
 	.globl fp_unavailable_common
 fp_unavailable_common:
 	EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN)
 	bne	1f			/* if from user, just load it up */
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.kernel_fp_unavailable_exception
+	bl	kernel_fp_unavailable_exception
 	BUG_OPCODE
 1:
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1211,15 +1227,15 @@ BEGIN_FTR_SECTION
 	bne-	2f
 END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
-	bl	.load_up_fpu
+	bl	load_up_fpu
 	b	fast_exception_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.fp_unavailable_tm
-	b	.ret_from_except
+	bl	fp_unavailable_tm
+	b	ret_from_except
 #endif
 	.align	7
 	.globl altivec_unavailable_common
@@ -1237,24 +1253,24 @@ BEGIN_FTR_SECTION
 	bne-	2f
   END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
 #endif
-	bl	.load_up_altivec
+	bl	load_up_altivec
 	b	fast_exception_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.altivec_unavailable_tm
-	b	.ret_from_except
+	bl	altivec_unavailable_tm
+	b	ret_from_except
 #endif
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.altivec_unavailable_exception
-	b	.ret_from_except
+	bl	altivec_unavailable_exception
+	b	ret_from_except
 
 	.align	7
 	.globl vsx_unavailable_common
@@ -1272,26 +1288,26 @@ BEGIN_FTR_SECTION
 	bne-	2f
   END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
 #endif
-	b	.load_up_vsx
+	b	load_up_vsx
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.vsx_unavailable_tm
-	b	.ret_from_except
+	bl	vsx_unavailable_tm
+	b	ret_from_except
 #endif
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	DISABLE_INTS
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.vsx_unavailable_exception
-	b	.ret_from_except
+	bl	vsx_unavailable_exception
+	b	ret_from_except
 
-	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception)
-	STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception)
+	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, facility_unavailable_exception)
+	STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, facility_unavailable_exception)
 
 	.align	7
 	.globl	__end_handlers
@@ -1386,9 +1402,10 @@ _GLOBAL(opal_mc_secondary_handler)
 machine_check_handle_early:
 	std	r0,GPR0(r1)	/* Save r0 */
 	EXCEPTION_PROLOG_COMMON_3(0x200)
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.machine_check_early
+	bl	machine_check_early
+	std	r3,RESULT(r1)	/* Save result */
 	ld	r12,_MSR(r1)
 #ifdef	CONFIG_PPC_P7_NAP
 	/*
@@ -1408,11 +1425,11 @@ machine_check_handle_early:
 	/* Supervisor state loss */
 	li	r0,1
 	stb	r0,PACA_NAPSTATELOST(r13)
-3:	bl	.machine_check_queue_event
+3:	bl	machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
 	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
-	b	.power7_enter_nap_mode
+	b	power7_enter_nap_mode
 4:
 #endif
 	/*
@@ -1443,16 +1460,38 @@ machine_check_handle_early:
 	 */
 	andi.	r11,r12,MSR_RI
 	bne	2f
-1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
-	b	1b
+1:	mfspr	r11,SPRN_SRR0
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10,unrecover_mce)
+	mtspr	SPRN_SRR0,r10
+	ld	r10,PACAKMSR(r13)
+	/*
+	 * We are going down. But there are chances that we might get hit by
+	 * another MCE during panic path and we may run into unstable state
+	 * with no way out. Hence, turn ME bit off while going down, so that
+	 * when another MCE is hit during panic path, system will checkstop
+	 * and hypervisor will get restarted cleanly by SP.
+	 */
+	li	r3,MSR_ME
+	andc	r10,r10,r3		/* Turn off MSR_ME */
+	mtspr	SPRN_SRR1,r10
+	rfid
+	b	.
 2:
 	/*
+	 * Check if we have successfully handled/recovered from error, if not
+	 * then stay on emergency stack and panic.
+	 */
+	ld	r3,RESULT(r1)	/* Load result */
+	cmpdi	r3,0		/* see if we handled MCE successfully */
+
+	beq	1b		/* if !handled then panic */
+	/*
 	 * Return from MC interrupt.
 	 * Queue up the MCE event so that we can log it later, while
 	 * returning from kernel or opal call.
 	 */
-	bl	.machine_check_queue_event
+	bl	machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
 	rfid
 9:
@@ -1460,6 +1499,17 @@ machine_check_handle_early:
 	MACHINE_CHECK_HANDLER_WINDUP
 	b	machine_check_pSeries
 
+unrecover_mce:
+	/* Invoke machine_check_exception to print MCE event and panic. */
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	machine_check_exception
+	/*
+	 * We will not reach here. Even if we did, there is no way out. Call
+	 * unrecoverable_exception and die.
+	 */
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	unrecoverable_exception
+	b	1b
 /*
  * r13 points to the PACA, r9 contains the saved CR,
  * r12 contain the saved SRR1, SRR0 is still ready for return
@@ -1468,7 +1518,7 @@ machine_check_handle_early:
  * r3 is saved in paca->slb_r3
  * We assume we aren't going to take any exceptions during this procedure.
  */
-_GLOBAL(slb_miss_realmode)
+slb_miss_realmode:
 	mflr	r10
 #ifdef CONFIG_RELOCATABLE
 	mtctr	r11
@@ -1477,7 +1527,7 @@ _GLOBAL(slb_miss_realmode)
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
 
-	bl	.slb_allocate_realmode
+	bl	slb_allocate_realmode
 
 	/* All done -- return from exception. */
 
@@ -1517,9 +1567,9 @@ _GLOBAL(slb_miss_realmode)
 unrecov_slb:
 	EXCEPTION_PROLOG_COMMON(0x4100, PACA_EXSLB)
 	DISABLE_INTS
-	bl	.save_nvgprs
+	bl	save_nvgprs
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.unrecoverable_exception
+	bl	unrecoverable_exception
 	b	1b
 
 
@@ -1536,7 +1586,7 @@ power4_fixup_nap:
  * Hash table stuff
  */
 	.align	7
-_STATIC(do_hash_page)
+do_hash_page:
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
 
@@ -1573,7 +1623,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 	 *
 	 * at return r3 = 0 for success, 1 for page fault, negative for error
 	 */
-	bl	.hash_page		/* build HPTE if possible */
+	bl	hash_page		/* build HPTE if possible */
 	cmpdi	r3,0			/* see if hash_page succeeded */
 
 	/* Success */
@@ -1587,35 +1637,35 @@ handle_page_fault:
 11:	ld	r4,_DAR(r1)
 	ld	r5,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_page_fault
+	bl	do_page_fault
 	cmpdi	r3,0
 	beq+	12f
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	lwz	r4,_DAR(r1)
-	bl	.bad_page_fault
-	b	.ret_from_except
+	bl	bad_page_fault
+	b	ret_from_except
 
 /* We have a data breakpoint exception - handle it */
 handle_dabr_fault:
-	bl	.save_nvgprs
+	bl	save_nvgprs
 	ld      r4,_DAR(r1)
 	ld      r5,_DSISR(r1)
 	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl      .do_break
-12:	b       .ret_from_except_lite
+	bl      do_break
+12:	b       ret_from_except_lite
 
 
 /* We have a page fault that hash_page could handle but HV refused
  * the PTE insertion
  */
-13:	bl	.save_nvgprs
+13:	bl	save_nvgprs
 	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r4,_DAR(r1)
-	bl	.low_hash_fault
-	b	.ret_from_except
+	bl	low_hash_fault
+	b	ret_from_except
 
 /*
  * We come here as a result of a DSI at a point where we don't want
@@ -1624,16 +1674,16 @@ handle_dabr_fault:
  * were soft-disabled.  We want to invoke the exception handler for
  * the access, or panic if there isn't a handler.
  */
-77:	bl	.save_nvgprs
+77:	bl	save_nvgprs
 	mr	r4,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	li	r5,SIGSEGV
-	bl	.bad_page_fault
-	b	.ret_from_except
+	bl	bad_page_fault
+	b	ret_from_except
 
 	/* here we have a segment miss */
 do_ste_alloc:
-	bl	.ste_allocate		/* try to insert stab entry */
+	bl	ste_allocate		/* try to insert stab entry */
 	cmpdi	r3,0
 	bne-	handle_page_fault
 	b	fast_exception_return
@@ -1646,7 +1696,7 @@ do_ste_alloc:
  * We assume (DAR >> 60) == 0xc.
  */
 	.align	7
-_GLOBAL(do_stab_bolted)
+do_stab_bolted:
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r11,PACA_EXSLB+EX_SRR0(r13)	/* save SRR0 in exc. frame */
 	mfspr	r11,SPRN_DAR			/* ea */
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 7213d930918..742694c1d85 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -69,7 +69,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
 	 */
 	token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
 	if (!token)
-		return 0;
+		return 1;
 
 	fw_dump.fadump_supported = 1;
 	fw_dump.ibm_configure_kernel_dump = *token;
@@ -92,7 +92,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
 					&size);
 
 	if (!sections)
-		return 0;
+		return 1;
 
 	num_sections = size / (3 * sizeof(u32));
 
@@ -110,6 +110,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
 			break;
 		}
 	}
+
 	return 1;
 }
 
@@ -645,7 +646,7 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
 		}
 		/* Lower 4 bytes of reg_value contains logical cpu id */
 		cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK;
-		if (!cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) {
+		if (fdh && !cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) {
 			SKIP_TO_NEXT_CPU(reg_entry);
 			continue;
 		}
@@ -662,9 +663,11 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
 	}
 	fadump_final_note(note_buf);
 
-	pr_debug("Updating elfcore header (%llx) with cpu notes\n",
+	if (fdh) {
+		pr_debug("Updating elfcore header (%llx) with cpu notes\n",
 							fdh->elfcorehdr_addr);
-	fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
+		fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
+	}
 	return 0;
 
 error_out:
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 6a014c763cc..390311c0f03 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) "ftrace-powerpc: " fmt
+
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
 #include <linux/uaccess.h>
@@ -105,11 +107,9 @@ __ftrace_make_nop(struct module *mod,
 		  struct dyn_ftrace *rec, unsigned long addr)
 {
 	unsigned int op;
-	unsigned int jmp[5];
-	unsigned long ptr;
+	unsigned long entry, ptr;
 	unsigned long ip = rec->ip;
-	unsigned long tramp;
-	int offset;
+	void *tramp;
 
 	/* read where this goes */
 	if (probe_kernel_read(&op, (void *)ip, sizeof(int)))
@@ -117,101 +117,46 @@ __ftrace_make_nop(struct module *mod,
 
 	/* Make sure that that this is still a 24bit jump */
 	if (!is_bl_op(op)) {
-		printk(KERN_ERR "Not expected bl: opcode is %x\n", op);
+		pr_err("Not expected bl: opcode is %x\n", op);
 		return -EINVAL;
 	}
 
 	/* lets find where the pointer goes */
-	tramp = find_bl_target(ip, op);
-
-	/*
-	 * On PPC64 the trampoline looks like:
-	 * 0x3d, 0x82, 0x00, 0x00,    addis   r12,r2, <high>
-	 * 0x39, 0x8c, 0x00, 0x00,    addi    r12,r12, <low>
-	 *   Where the bytes 2,3,6 and 7 make up the 32bit offset
-	 *   to the TOC that holds the pointer.
-	 *   to jump to.
-	 * 0xf8, 0x41, 0x00, 0x28,    std     r2,40(r1)
-	 * 0xe9, 0x6c, 0x00, 0x20,    ld      r11,32(r12)
-	 *   The actually address is 32 bytes from the offset
-	 *   into the TOC.
-	 * 0xe8, 0x4c, 0x00, 0x28,    ld      r2,40(r12)
-	 */
-
-	pr_devel("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
-
-	/* Find where the trampoline jumps to */
-	if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
-		printk(KERN_ERR "Failed to read %lx\n", tramp);
-		return -EFAULT;
-	}
+	tramp = (void *)find_bl_target(ip, op);
 
-	pr_devel(" %08x %08x", jmp[0], jmp[1]);
+	pr_devel("ip:%lx jumps to %p", ip, tramp);
 
-	/* verify that this is what we expect it to be */
-	if (((jmp[0] & 0xffff0000) != 0x3d820000) ||
-	    ((jmp[1] & 0xffff0000) != 0x398c0000) ||
-	    (jmp[2] != 0xf8410028) ||
-	    (jmp[3] != 0xe96c0020) ||
-	    (jmp[4] != 0xe84c0028)) {
-		printk(KERN_ERR "Not a trampoline\n");
+	if (!is_module_trampoline(tramp)) {
+		pr_err("Not a trampoline\n");
 		return -EINVAL;
 	}
 
-	/* The bottom half is signed extended */
-	offset = ((unsigned)((unsigned short)jmp[0]) << 16) +
-		(int)((short)jmp[1]);
-
-	pr_devel(" %x ", offset);
-
-	/* get the address this jumps too */
-	tramp = mod->arch.toc + offset + 32;
-	pr_devel("toc: %lx", tramp);
-
-	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
-		printk(KERN_ERR "Failed to read %lx\n", tramp);
+	if (module_trampoline_target(mod, tramp, &ptr)) {
+		pr_err("Failed to get trampoline target\n");
 		return -EFAULT;
 	}
 
-	pr_devel(" %08x %08x\n", jmp[0], jmp[1]);
-
-#ifdef __LITTLE_ENDIAN__
-	ptr = ((unsigned long)jmp[1] << 32) + jmp[0];
-#else
-	ptr = ((unsigned long)jmp[0] << 32) + jmp[1];
-#endif
+	pr_devel("trampoline target %lx", ptr);
 
+	entry = ppc_global_function_entry((void *)addr);
 	/* This should match what was called */
-	if (ptr != ppc_function_entry((void *)addr)) {
-		printk(KERN_ERR "addr does not match %lx\n", ptr);
-		return -EINVAL;
-	}
-
-	/*
-	 * We want to nop the line, but the next line is
-	 *  0xe8, 0x41, 0x00, 0x28   ld r2,40(r1)
-	 * This needs to be turned to a nop too.
-	 */
-	if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE))
-		return -EFAULT;
-
-	if (op != 0xe8410028) {
-		printk(KERN_ERR "Next line is not ld! (%08x)\n", op);
+	if (ptr != entry) {
+		pr_err("addr %lx does not match expected %lx\n", ptr, entry);
 		return -EINVAL;
 	}
 
 	/*
-	 * Milton Miller pointed out that we can not blindly do nops.
-	 * If a task was preempted when calling a trace function,
-	 * the nops will remove the way to restore the TOC in r2
-	 * and the r2 TOC will get corrupted.
-	 */
-
-	/*
-	 * Replace:
-	 *   bl <tramp>  <==== will be replaced with "b 1f"
-	 *   ld r2,40(r1)
-	 *  1:
+	 * Our original call site looks like:
+	 *
+	 * bl <tramp>
+	 * ld r2,XX(r1)
+	 *
+	 * Milton Miller pointed out that we can not simply nop the branch.
+	 * If a task was preempted when calling a trace function, the nops
+	 * will remove the way to restore the TOC in r2 and the r2 TOC will
+	 * get corrupted.
+	 *
+	 * Use a b +8 to jump over the load.
 	 */
 	op = 0x48000008;	/* b +8 */
 
@@ -236,7 +181,7 @@ __ftrace_make_nop(struct module *mod,
 
 	/* Make sure that that this is still a 24bit jump */
 	if (!is_bl_op(op)) {
-		printk(KERN_ERR "Not expected bl: opcode is %x\n", op);
+		pr_err("Not expected bl: opcode is %x\n", op);
 		return -EINVAL;
 	}
 
@@ -255,7 +200,7 @@ __ftrace_make_nop(struct module *mod,
 
 	/* Find where the trampoline jumps to */
 	if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
-		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		pr_err("Failed to read %lx\n", tramp);
 		return -EFAULT;
 	}
 
@@ -266,7 +211,7 @@ __ftrace_make_nop(struct module *mod,
 	    ((jmp[1] & 0xffff0000) != 0x398c0000) ||
 	    (jmp[2] != 0x7d8903a6) ||
 	    (jmp[3] != 0x4e800420)) {
-		printk(KERN_ERR "Not a trampoline\n");
+		pr_err("Not a trampoline\n");
 		return -EINVAL;
 	}
 
@@ -278,8 +223,7 @@ __ftrace_make_nop(struct module *mod,
 	pr_devel(" %lx ", tramp);
 
 	if (tramp != addr) {
-		printk(KERN_ERR
-		       "Trampoline location %08lx does not match addr\n",
+		pr_err("Trampoline location %08lx does not match addr\n",
 		       tramp);
 		return -EINVAL;
 	}
@@ -320,15 +264,13 @@ int ftrace_make_nop(struct module *mod,
 	 */
 	if (!rec->arch.mod) {
 		if (!mod) {
-			printk(KERN_ERR "No module loaded addr=%lx\n",
-			       addr);
+			pr_err("No module loaded addr=%lx\n", addr);
 			return -EFAULT;
 		}
 		rec->arch.mod = mod;
 	} else if (mod) {
 		if (mod != rec->arch.mod) {
-			printk(KERN_ERR
-			       "Record mod %p not equal to passed in mod %p\n",
+			pr_err("Record mod %p not equal to passed in mod %p\n",
 			       rec->arch.mod, mod);
 			return -EINVAL;
 		}
@@ -349,45 +291,42 @@ static int
 __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
 	unsigned int op[2];
-	unsigned long ip = rec->ip;
+	void *ip = (void *)rec->ip;
 
 	/* read where this goes */
-	if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2))
+	if (probe_kernel_read(op, ip, sizeof(op)))
 		return -EFAULT;
 
 	/*
-	 * It should be pointing to two nops or
-	 *  b +8; ld r2,40(r1)
+	 * We expect to see:
+	 *
+	 * b +8
+	 * ld r2,XX(r1)
+	 *
+	 * The load offset is different depending on the ABI. For simplicity
+	 * just mask it out when doing the compare.
 	 */
-	if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) &&
-	    ((op[0] != PPC_INST_NOP) || (op[1] != PPC_INST_NOP))) {
-		printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]);
+	if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) {
+		pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]);
 		return -EINVAL;
 	}
 
 	/* If we never set up a trampoline to ftrace_caller, then bail */
 	if (!rec->arch.mod->arch.tramp) {
-		printk(KERN_ERR "No ftrace trampoline\n");
+		pr_err("No ftrace trampoline\n");
 		return -EINVAL;
 	}
 
-	/* create the branch to the trampoline */
-	op[0] = create_branch((unsigned int *)ip,
-			      rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
-	if (!op[0]) {
-		printk(KERN_ERR "REL24 out of range!\n");
+	/* Ensure branch is within 24 bits */
+	if (!create_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) {
+		pr_err("Branch out of range\n");
 		return -EINVAL;
 	}
 
-	/* ld r2,40(r1) */
-	op[1] = 0xe8410028;
-
-	pr_devel("write to %lx\n", rec->ip);
-
-	if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2))
-		return -EPERM;
-
-	flush_icache_range(ip, ip + 8);
+	if (patch_branch(ip, rec->arch.mod->arch.tramp, BRANCH_SET_LINK)) {
+		pr_err("REL24 out of range!\n");
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -404,13 +343,13 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	/* It should be pointing to a nop */
 	if (op != PPC_INST_NOP) {
-		printk(KERN_ERR "Expected NOP but have %x\n", op);
+		pr_err("Expected NOP but have %x\n", op);
 		return -EINVAL;
 	}
 
 	/* If we never set up a trampoline to ftrace_caller, then bail */
 	if (!rec->arch.mod->arch.tramp) {
-		printk(KERN_ERR "No ftrace trampoline\n");
+		pr_err("No ftrace trampoline\n");
 		return -EINVAL;
 	}
 
@@ -418,7 +357,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	op = create_branch((unsigned int *)ip,
 			   rec->arch.mod->arch.tramp, BRANCH_SET_LINK);
 	if (!op) {
-		printk(KERN_ERR "REL24 out of range!\n");
+		pr_err("REL24 out of range!\n");
 		return -EINVAL;
 	}
 
@@ -456,7 +395,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	 * already have a module defined.
 	 */
 	if (!rec->arch.mod) {
-		printk(KERN_ERR "No module loaded\n");
+		pr_err("No module loaded\n");
 		return -EINVAL;
 	}
 
@@ -586,6 +525,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	struct ftrace_graph_ent trace;
 	unsigned long return_hooker = (unsigned long)&return_to_handler;
 
+	if (unlikely(ftrace_graph_is_dead()))
+		return;
+
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 67ee0d6c107..7d7d8635227 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -930,25 +930,6 @@ initial_mmu:
 	tlbwe	r4,r0,TLB_DATA		/* Load the data portion of the entry */
 	tlbwe	r3,r0,TLB_TAG		/* Load the tag portion of the entry */
 
-#if defined(CONFIG_SERIAL_TEXT_DEBUG) && defined(SERIAL_DEBUG_IO_BASE)
-
-	/* Load a TLB entry for the UART, so that ppc4xx_progress() can use
-	 * the UARTs nice and early.  We use a 4k real==virtual mapping. */
-
-	lis	r3,SERIAL_DEBUG_IO_BASE@h
-	ori	r3,r3,SERIAL_DEBUG_IO_BASE@l
-	mr	r4,r3
-	clrrwi	r4,r4,12
-	ori	r4,r4,(TLB_WR|TLB_I|TLB_M|TLB_G)
-
-	clrrwi	r3,r3,12
-	ori	r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_4K))
-
-	li	r0,0			/* TLB slot 0 */
-	tlbwe	r4,r0,TLB_DATA
-	tlbwe	r3,r0,TLB_TAG
-#endif /* CONFIG_SERIAL_DEBUG_TEXT && SERIAL_DEBUG_IO_BASE */
-
 	isync
 
 	/* Establish the exception vector base
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index b7363bd4245..a95145d7f61 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -70,16 +70,15 @@ _GLOBAL(__start)
 	/* NOP this out unconditionally */
 BEGIN_FTR_SECTION
 	FIXUP_ENDIAN
-	b	.__start_initialization_multiplatform
+	b	__start_initialization_multiplatform
 END_FTR_SECTION(0, 1)
 
 	/* Catch branch to 0 in real mode */
 	trap
 
-	/* Secondary processors spin on this value until it becomes nonzero.
-	 * When it does it contains the real address of the descriptor
-	 * of the function that the cpu should jump to to continue
-	 * initialization.
+	/* Secondary processors spin on this value until it becomes non-zero.
+	 * When non-zero, it contains the real address of the function the cpu
+	 * should jump to.
 	 */
 	.balign 8
 	.globl  __secondary_hold_spinloop
@@ -140,16 +139,15 @@ __secondary_hold:
 	tovirt(r26,r26)
 #endif
 	/* All secondary cpus wait here until told to start. */
-100:	ld	r4,__secondary_hold_spinloop-_stext(r26)
-	cmpdi	0,r4,0
+100:	ld	r12,__secondary_hold_spinloop-_stext(r26)
+	cmpdi	0,r12,0
 	beq	100b
 
 #if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
 #ifdef CONFIG_PPC_BOOK3E
-	tovirt(r4,r4)
+	tovirt(r12,r12)
 #endif
-	ld	r4,0(r4)		/* deref function descriptor */
-	mtctr	r4
+	mtctr	r12
 	mr	r3,r24
 	/*
 	 * it may be the case that other platforms have r4 right to
@@ -186,16 +184,16 @@ _GLOBAL(generic_secondary_thread_init)
 	mr	r24,r3
 
 	/* turn on 64-bit mode */
-	bl	.enable_64b_mode
+	bl	enable_64b_mode
 
 	/* get a valid TOC pointer, wherever we're mapped at */
-	bl	.relative_toc
+	bl	relative_toc
 	tovirt(r2,r2)
 
 #ifdef CONFIG_PPC_BOOK3E
 	/* Book3E initialization */
 	mr	r3,r24
-	bl	.book3e_secondary_thread_init
+	bl	book3e_secondary_thread_init
 #endif
 	b	generic_secondary_common_init
 
@@ -214,17 +212,17 @@ _GLOBAL(generic_secondary_smp_init)
 	mr	r25,r4
 
 	/* turn on 64-bit mode */
-	bl	.enable_64b_mode
+	bl	enable_64b_mode
 
 	/* get a valid TOC pointer, wherever we're mapped at */
-	bl	.relative_toc
+	bl	relative_toc
 	tovirt(r2,r2)
 
 #ifdef CONFIG_PPC_BOOK3E
 	/* Book3E initialization */
 	mr	r3,r24
 	mr	r4,r25
-	bl	.book3e_secondary_core_init
+	bl	book3e_secondary_core_init
 #endif
 
 generic_secondary_common_init:
@@ -236,7 +234,7 @@ generic_secondary_common_init:
 	ld	r13,0(r13)		/* Get base vaddr of paca array	 */
 #ifndef CONFIG_SMP
 	addi	r13,r13,PACA_SIZE	/* know r13 if used accidentally */
-	b	.kexec_wait		/* wait for next kernel if !SMP	 */
+	b	kexec_wait		/* wait for next kernel if !SMP	 */
 #else
 	LOAD_REG_ADDR(r7, nr_cpu_ids)	/* Load nr_cpu_ids address       */
 	lwz	r7,0(r7)		/* also the max paca allocated 	 */
@@ -250,7 +248,7 @@ generic_secondary_common_init:
 	blt	1b
 
 	mr	r3,r24			/* not found, copy phys to r3	 */
-	b	.kexec_wait		/* next kernel might do better	 */
+	b	kexec_wait		/* next kernel might do better	 */
 
 2:	SET_PACA(r13)
 #ifdef CONFIG_PPC_BOOK3E
@@ -264,11 +262,13 @@ generic_secondary_common_init:
 	/* See if we need to call a cpu state restore handler */
 	LOAD_REG_ADDR(r23, cur_cpu_spec)
 	ld	r23,0(r23)
-	ld	r23,CPU_SPEC_RESTORE(r23)
-	cmpdi	0,r23,0
+	ld	r12,CPU_SPEC_RESTORE(r23)
+	cmpdi	0,r12,0
 	beq	3f
-	ld	r23,0(r23)
-	mtctr	r23
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+	ld	r12,0(r12)
+#endif
+	mtctr	r12
 	bctrl
 
 3:	LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */
@@ -299,7 +299,7 @@ generic_secondary_common_init:
  * Assumes we're mapped EA == RA if the MMU is on.
  */
 #ifdef CONFIG_PPC_BOOK3S
-_STATIC(__mmu_off)
+__mmu_off:
 	mfmsr	r3
 	andi.	r0,r3,MSR_IR|MSR_DR
 	beqlr
@@ -324,12 +324,12 @@ _STATIC(__mmu_off)
  *                 DT block, r4 is a physical pointer to the kernel itself
  *
  */
-_GLOBAL(__start_initialization_multiplatform)
+__start_initialization_multiplatform:
 	/* Make sure we are running in 64 bits mode */
-	bl	.enable_64b_mode
+	bl	enable_64b_mode
 
 	/* Get TOC pointer (current runtime address) */
-	bl	.relative_toc
+	bl	relative_toc
 
 	/* find out where we are now */
 	bcl	20,31,$+4
@@ -342,7 +342,7 @@ _GLOBAL(__start_initialization_multiplatform)
 	 */
 	cmpldi	cr0,r5,0
 	beq	1f
-	b	.__boot_from_prom		/* yes -> prom */
+	b	__boot_from_prom		/* yes -> prom */
 1:
 	/* Save parameters */
 	mr	r31,r3
@@ -354,8 +354,8 @@ _GLOBAL(__start_initialization_multiplatform)
 #endif
 
 #ifdef CONFIG_PPC_BOOK3E
-	bl	.start_initialization_book3e
-	b	.__after_prom_start
+	bl	start_initialization_book3e
+	b	__after_prom_start
 #else
 	/* Setup some critical 970 SPRs before switching MMU off */
 	mfspr	r0,SPRN_PVR
@@ -368,15 +368,15 @@ _GLOBAL(__start_initialization_multiplatform)
 	beq	1f
 	cmpwi	r0,0x45		/* 970GX */
 	bne	2f
-1:	bl	.__cpu_preinit_ppc970
+1:	bl	__cpu_preinit_ppc970
 2:
 
 	/* Switch off MMU if not already off */
-	bl	.__mmu_off
-	b	.__after_prom_start
+	bl	__mmu_off
+	b	__after_prom_start
 #endif /* CONFIG_PPC_BOOK3E */
 
-_INIT_STATIC(__boot_from_prom)
+__boot_from_prom:
 #ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
 	/* Save parameters */
 	mr	r31,r3
@@ -395,7 +395,7 @@ _INIT_STATIC(__boot_from_prom)
 #ifdef CONFIG_RELOCATABLE
 	/* Relocate code for where we are now */
 	mr	r3,r26
-	bl	.relocate
+	bl	relocate
 #endif
 
 	/* Restore parameters */
@@ -407,14 +407,14 @@ _INIT_STATIC(__boot_from_prom)
 
 	/* Do all of the interaction with OF client interface */
 	mr	r8,r26
-	bl	.prom_init
+	bl	prom_init
 #endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */
 
 	/* We never return. We also hit that trap if trying to boot
 	 * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
 	trap
 
-_STATIC(__after_prom_start)
+__after_prom_start:
 #ifdef CONFIG_RELOCATABLE
 	/* process relocations for the final address of the kernel */
 	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
@@ -424,7 +424,7 @@ _STATIC(__after_prom_start)
 	bne	1f
 	add	r25,r25,r26
 1:	mr	r3,r25
-	bl	.relocate
+	bl	relocate
 #endif
 
 /*
@@ -464,12 +464,12 @@ _STATIC(__after_prom_start)
 	lis	r5,(copy_to_here - _stext)@ha
 	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
 
-	bl	.copy_and_flush		/* copy the first n bytes	 */
+	bl	copy_and_flush		/* copy the first n bytes	 */
 					/* this includes the code being	 */
 					/* executed here.		 */
 	addis	r8,r3,(4f - _stext)@ha	/* Jump to the copy of this code */
-	addi	r8,r8,(4f - _stext)@l	/* that we just made */
-	mtctr	r8
+	addi	r12,r8,(4f - _stext)@l	/* that we just made */
+	mtctr	r12
 	bctr
 
 .balign 8
@@ -478,9 +478,9 @@ p_end:	.llong	_end - _stext
 4:	/* Now copy the rest of the kernel up to _end */
 	addis	r5,r26,(p_end - _stext)@ha
 	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
-5:	bl	.copy_and_flush		/* copy the rest */
+5:	bl	copy_and_flush		/* copy the rest */
 
-9:	b	.start_here_multiplatform
+9:	b	start_here_multiplatform
 
 /*
  * Copy routine used to copy the kernel to start at physical address 0
@@ -544,7 +544,7 @@ __secondary_start_pmac_0:
 	
 _GLOBAL(pmac_secondary_start)
 	/* turn on 64-bit mode */
-	bl	.enable_64b_mode
+	bl	enable_64b_mode
 
 	li	r0,0
 	mfspr	r3,SPRN_HID4
@@ -556,11 +556,11 @@ _GLOBAL(pmac_secondary_start)
 	slbia
 
 	/* get TOC pointer (real address) */
-	bl	.relative_toc
+	bl	relative_toc
 	tovirt(r2,r2)
 
 	/* Copy some CPU settings from CPU 0 */
-	bl	.__restore_cpu_ppc970
+	bl	__restore_cpu_ppc970
 
 	/* pSeries do that early though I don't think we really need it */
 	mfmsr	r3
@@ -619,7 +619,7 @@ __secondary_start:
 	std	r14,PACAKSAVE(r13)
 
 	/* Do early setup for that CPU (stab, slb, hash table pointer) */
-	bl	.early_setup_secondary
+	bl	early_setup_secondary
 
 	/*
 	 * setup the new stack pointer, but *don't* use this until
@@ -639,7 +639,7 @@ __secondary_start:
 	stb	r0,PACAIRQHAPPENED(r13)
 
 	/* enable MMU and jump to start_secondary */
-	LOAD_REG_ADDR(r3, .start_secondary_prolog)
+	LOAD_REG_ADDR(r3, start_secondary_prolog)
 	LOAD_REG_IMMEDIATE(r4, MSR_KERNEL)
 
 	mtspr	SPRN_SRR0,r3
@@ -652,11 +652,11 @@ __secondary_start:
  * zero the stack back-chain pointer and get the TOC virtual address
  * before going into C code.
  */
-_GLOBAL(start_secondary_prolog)
+start_secondary_prolog:
 	ld	r2,PACATOC(r13)
 	li	r3,0
 	std	r3,0(r1)		/* Zero the stack frame pointer	*/
-	bl	.start_secondary
+	bl	start_secondary
 	b	.
 /*
  * Reset stack pointer and call start_secondary
@@ -667,14 +667,14 @@ _GLOBAL(start_secondary_resume)
 	ld	r1,PACAKSAVE(r13)	/* Reload kernel stack pointer */
 	li	r3,0
 	std	r3,0(r1)		/* Zero the stack frame pointer	*/
-	bl	.start_secondary
+	bl	start_secondary
 	b	.
 #endif
 
 /*
  * This subroutine clobbers r11 and r12
  */
-_GLOBAL(enable_64b_mode)
+enable_64b_mode:
 	mfmsr	r11			/* grab the current MSR */
 #ifdef CONFIG_PPC_BOOK3E
 	oris	r11,r11,0x8000		/* CM bit set, we'll set ICM later */
@@ -715,9 +715,9 @@ p_toc:	.llong	__toc_start + 0x8000 - 0b
 /*
  * This is where the main kernel code starts.
  */
-_INIT_STATIC(start_here_multiplatform)
+start_here_multiplatform:
 	/* set up the TOC */
-	bl      .relative_toc
+	bl      relative_toc
 	tovirt(r2,r2)
 
 	/* Clear out the BSS. It may have been done in prom_init,
@@ -776,9 +776,9 @@ _INIT_STATIC(start_here_multiplatform)
 
 	/* Restore parameters passed from prom_init/kexec */
 	mr	r3,r31
-	bl	.early_setup		/* also sets r13 and SPRG_PACA */
+	bl	early_setup		/* also sets r13 and SPRG_PACA */
 
-	LOAD_REG_ADDR(r3, .start_here_common)
+	LOAD_REG_ADDR(r3, start_here_common)
 	ld	r4,PACAKMSR(r13)
 	mtspr	SPRN_SRR0,r3
 	mtspr	SPRN_SRR1,r4
@@ -786,7 +786,8 @@ _INIT_STATIC(start_here_multiplatform)
 	b	.	/* prevent speculative execution */
 	
 	/* This is where all platforms converge execution */
-_INIT_GLOBAL(start_here_common)
+
+start_here_common:
 	/* relocation is on at this point */
 	std	r1,PACAKSAVE(r13)
 
@@ -794,7 +795,7 @@ _INIT_GLOBAL(start_here_common)
 	ld	r2,PACATOC(r13)
 
 	/* Do more system initializations in virtual mode */
-	bl	.setup_system
+	bl	setup_system
 
 	/* Mark interrupts soft and hard disabled (they might be enabled
 	 * in the PACA when doing hotplug)
@@ -805,7 +806,7 @@ _INIT_GLOBAL(start_here_common)
 	stb	r0,PACAIRQHAPPENED(r13)
 
 	/* Generic kernel entry */
-	bl	.start_kernel
+	bl	start_kernel
 
 	/* Not reached */
 	BUG_OPCODE
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index b0a1792279b..0bb5918faaa 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -72,7 +72,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 	 * If so, DABR will be populated in single_step_dabr_instruction().
 	 */
 	if (current->thread.last_hit_ubp != bp)
-		set_breakpoint(info);
+		__set_breakpoint(info);
 
 	return 0;
 }
@@ -198,7 +198,7 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
 
 	info = counter_arch_bp(tsk->thread.last_hit_ubp);
 	regs->msr &= ~MSR_SE;
-	set_breakpoint(info);
+	__set_breakpoint(info);
 	tsk->thread.last_hit_ubp = NULL;
 }
 
@@ -284,7 +284,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 	if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
 		perf_bp_event(bp, regs);
 
-	set_breakpoint(info);
+	__set_breakpoint(info);
 out:
 	rcu_read_unlock();
 	return rc;
@@ -316,7 +316,7 @@ int __kprobes single_step_dabr_instruction(struct die_args *args)
 	if (!(info->type & HW_BRK_TYPE_EXTRANEOUS_IRQ))
 		perf_bp_event(bp, regs);
 
-	set_breakpoint(info);
+	__set_breakpoint(info);
 	current->thread.last_hit_ubp = NULL;
 
 	/*
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index bfb73cc209c..48c21acef91 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -43,7 +43,7 @@ _GLOBAL(\name)
 	 */
 #ifdef CONFIG_TRACE_IRQFLAGS
 	stdu    r1,-128(r1)
-	bl	.trace_hardirqs_on
+	bl	trace_hardirqs_on
 	addi    r1,r1,128
 #endif
 	li	r0,1
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index e3edaa18991..f57a19348bd 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -46,7 +46,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
 	mflr	r0
 	std	r0,16(r1)
 	stdu    r1,-128(r1)
-	bl	.trace_hardirqs_on
+	bl	trace_hardirqs_on
 	addi    r1,r1,128
 	ld	r0,16(r1)
 	mtlr	r0
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index c3ab8697561..5cf3d367190 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -39,6 +39,10 @@
  * Pass requested state in r3:
  * 	0 - nap
  * 	1 - sleep
+ *
+ * To check IRQ_HAPPENED in r4
+ * 	0 - don't check
+ * 	1 - check
  */
 _GLOBAL(power7_powersave_common)
 	/* Use r3 to pass state nap/sleep/winkle */
@@ -58,7 +62,7 @@ _GLOBAL(power7_powersave_common)
 	/* Make sure FPU, VSX etc... are flushed as we may lose
 	 * state when going to nap mode
 	 */
-	bl	.discard_lazy_cpu_state
+	bl	discard_lazy_cpu_state
 #endif /* CONFIG_SMP */
 
 	/* Hard disable interrupts */
@@ -71,6 +75,8 @@ _GLOBAL(power7_powersave_common)
 	lbz	r0,PACAIRQHAPPENED(r13)
 	cmpwi	cr0,r0,0
 	beq	1f
+	cmpwi	cr0,r4,0
+	beq	1f
 	addi	r1,r1,INT_FRAME_SIZE
 	ld	r0,16(r1)
 	mtlr	r0
@@ -114,15 +120,18 @@ _GLOBAL(power7_idle)
 	lwz	r4,ADDROFF(powersave_nap)(r3)
 	cmpwi	0,r4,0
 	beqlr
+	li	r3, 1
 	/* fall through */
 
 _GLOBAL(power7_nap)
+	mr	r4,r3
 	li	r3,0
 	b	power7_powersave_common
 	/* No return */
 
 _GLOBAL(power7_sleep)
 	li	r3,1
+	li	r4,1
 	b	power7_powersave_common
 	/* No return */
 
@@ -168,7 +177,7 @@ _GLOBAL(power7_wakeup_loss)
 _GLOBAL(power7_wakeup_noloss)
 	lbz	r0,PACA_NAPSTATELOST(r13)
 	cmpwi	r0,0
-	bne	.power7_wakeup_loss
+	bne	power7_wakeup_loss
 	ld	r1,PACAR1(r13)
 	ld	r4,_MSR(r1)
 	ld	r5,_NIP(r1)
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index b82227e7e21..12e48d56f77 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -23,7 +23,7 @@ unsigned int ioread16(void __iomem *addr)
 }
 unsigned int ioread16be(void __iomem *addr)
 {
-	return in_be16(addr);
+	return readw_be(addr);
 }
 unsigned int ioread32(void __iomem *addr)
 {
@@ -31,7 +31,7 @@ unsigned int ioread32(void __iomem *addr)
 }
 unsigned int ioread32be(void __iomem *addr)
 {
-	return in_be32(addr);
+	return readl_be(addr);
 }
 EXPORT_SYMBOL(ioread8);
 EXPORT_SYMBOL(ioread16);
@@ -49,7 +49,7 @@ void iowrite16(u16 val, void __iomem *addr)
 }
 void iowrite16be(u16 val, void __iomem *addr)
 {
-	out_be16(addr, val);
+	writew_be(val, addr);
 }
 void iowrite32(u32 val, void __iomem *addr)
 {
@@ -57,7 +57,7 @@ void iowrite32(u32 val, void __iomem *addr)
 }
 void iowrite32be(u32 val, void __iomem *addr)
 {
-	out_be32(addr, val);
+	writel_be(val, addr);
 }
 EXPORT_SYMBOL(iowrite8);
 EXPORT_SYMBOL(iowrite16);
@@ -75,15 +75,15 @@ EXPORT_SYMBOL(iowrite32be);
  */
 void ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
 {
-	_insb((u8 __iomem *) addr, dst, count);
+	readsb(addr, dst, count);
 }
 void ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
 {
-	_insw_ns((u16 __iomem *) addr, dst, count);
+	readsw(addr, dst, count);
 }
 void ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
 {
-	_insl_ns((u32 __iomem *) addr, dst, count);
+	readsl(addr, dst, count);
 }
 EXPORT_SYMBOL(ioread8_rep);
 EXPORT_SYMBOL(ioread16_rep);
@@ -91,15 +91,15 @@ EXPORT_SYMBOL(ioread32_rep);
 
 void iowrite8_rep(void __iomem *addr, const void *src, unsigned long count)
 {
-	_outsb((u8 __iomem *) addr, src, count);
+	writesb(addr, src, count);
 }
 void iowrite16_rep(void __iomem *addr, const void *src, unsigned long count)
 {
-	_outsw_ns((u16 __iomem *) addr, src, count);
+	writesw(addr, src, count);
 }
 void iowrite32_rep(void __iomem *addr, const void *src, unsigned long count)
 {
-	_outsl_ns((u32 __iomem *) addr, src, count);
+	writesl(addr, src, count);
 }
 EXPORT_SYMBOL(iowrite8_rep);
 EXPORT_SYMBOL(iowrite16_rep);
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 90fab64d911..2f72af82513 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -32,6 +32,7 @@
 #include <linux/module.h>
 #include <linux/kdebug.h>
 #include <linux/slab.h>
+#include <asm/code-patching.h>
 #include <asm/cacheflush.h>
 #include <asm/sstep.h>
 #include <asm/uaccess.h>
@@ -491,12 +492,10 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-#ifdef CONFIG_PPC64
 unsigned long arch_deref_entry_point(void *entry)
 {
-	return ((func_descr_t *)entry)->entry;
+	return ppc_global_function_entry(entry);
 }
-#endif
 
 int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
@@ -508,8 +507,12 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	/* setup return addr to the jprobe handler routine */
 	regs->nip = arch_deref_entry_point(jp->entry);
 #ifdef CONFIG_PPC64
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+	regs->gpr[12] = (unsigned long)jp->entry;
+#else
 	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
 #endif
+#endif
 
 	return 1;
 }
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 40bd7bd4e19..936258881c9 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -48,6 +48,9 @@ static struct of_device_id legacy_serial_parents[] __initdata = {
 static unsigned int legacy_serial_count;
 static int legacy_serial_console = -1;
 
+static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
+	UPF_SHARE_IRQ | UPF_FIXED_PORT;
+
 static unsigned int tsi_serial_in(struct uart_port *p, int offset)
 {
 	unsigned int tmp;
@@ -71,8 +74,9 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
 				  phys_addr_t taddr, unsigned long irq,
 				  upf_t flags, int irq_check_parent)
 {
-	const __be32 *clk, *spd;
+	const __be32 *clk, *spd, *rs;
 	u32 clock = BASE_BAUD * 16;
+	u32 shift = 0;
 	int index;
 
 	/* get clock freq. if present */
@@ -83,6 +87,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
 	/* get default speed if present */
 	spd = of_get_property(np, "current-speed", NULL);
 
+	/* get register shift if present */
+	rs = of_get_property(np, "reg-shift", NULL);
+	if (rs && *rs)
+		shift = be32_to_cpup(rs);
+
 	/* If we have a location index, then try to use it */
 	if (want_index >= 0 && want_index < MAX_LEGACY_SERIAL_PORTS)
 		index = want_index;
@@ -126,6 +135,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
 	legacy_serial_ports[index].uartclk = clock;
 	legacy_serial_ports[index].irq = irq;
 	legacy_serial_ports[index].flags = flags;
+	legacy_serial_ports[index].regshift = shift;
 	legacy_serial_infos[index].taddr = taddr;
 	legacy_serial_infos[index].np = of_node_get(np);
 	legacy_serial_infos[index].clock = clock;
@@ -153,8 +163,6 @@ static int __init add_legacy_soc_port(struct device_node *np,
 {
 	u64 addr;
 	const __be32 *addrp;
-	upf_t flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_SHARE_IRQ
-		| UPF_FIXED_PORT;
 	struct device_node *tsi = of_get_parent(np);
 
 	/* We only support ports that have a clock frequency properly
@@ -163,9 +171,8 @@ static int __init add_legacy_soc_port(struct device_node *np,
 	if (of_get_property(np, "clock-frequency", NULL) == NULL)
 		return -1;
 
-	/* if reg-shift or offset, don't try to use it */
-	if ((of_get_property(np, "reg-shift", NULL) != NULL) ||
-		(of_get_property(np, "reg-offset", NULL) != NULL))
+	/* if reg-offset don't try to use it */
+	if ((of_get_property(np, "reg-offset", NULL) != NULL))
 		return -1;
 
 	/* if rtas uses this device, don't try to use it as well */
@@ -185,9 +192,11 @@ static int __init add_legacy_soc_port(struct device_node *np,
 	 * IO port value. It will be fixed up later along with the irq
 	 */
 	if (tsi && !strcmp(tsi->type, "tsi-bridge"))
-		return add_legacy_port(np, -1, UPIO_TSI, addr, addr, NO_IRQ, flags, 0);
+		return add_legacy_port(np, -1, UPIO_TSI, addr, addr,
+				       NO_IRQ, legacy_port_flags, 0);
 	else
-		return add_legacy_port(np, -1, UPIO_MEM, addr, addr, NO_IRQ, flags, 0);
+		return add_legacy_port(np, -1, UPIO_MEM, addr, addr,
+				       NO_IRQ, legacy_port_flags, 0);
 }
 
 static int __init add_legacy_isa_port(struct device_node *np,
@@ -233,7 +242,7 @@ static int __init add_legacy_isa_port(struct device_node *np,
 
 	/* Add port, irq will be dealt with later */
 	return add_legacy_port(np, index, UPIO_PORT, be32_to_cpu(reg[1]),
-			       taddr, NO_IRQ, UPF_BOOT_AUTOCONF, 0);
+			       taddr, NO_IRQ, legacy_port_flags, 0);
 
 }
 
@@ -306,7 +315,7 @@ static int __init add_legacy_pci_port(struct device_node *np,
 	 * IO port value. It will be fixed up later along with the irq
 	 */
 	return add_legacy_port(np, index, iotype, base, addr, NO_IRQ,
-			       UPF_BOOT_AUTOCONF, np != pci_dev);
+			       legacy_port_flags, np != pci_dev);
 }
 #endif
 
@@ -315,17 +324,20 @@ static void __init setup_legacy_serial_console(int console)
 	struct legacy_serial_info *info = &legacy_serial_infos[console];
 	struct plat_serial8250_port *port = &legacy_serial_ports[console];
 	void __iomem *addr;
+	unsigned int stride;
+
+	stride = 1 << port->regshift;
 
 	/* Check if a translated MMIO address has been found */
 	if (info->taddr) {
 		addr = ioremap(info->taddr, 0x1000);
 		if (addr == NULL)
 			return;
-		udbg_uart_init_mmio(addr, 1);
+		udbg_uart_init_mmio(addr, stride);
 	} else {
 		/* Check if it's PIO and we support untranslated PIO */
 		if (port->iotype == UPIO_PORT && isa_io_special)
-			udbg_uart_init_pio(port->iobase, 1);
+			udbg_uart_init_pio(port->iobase, stride);
 		else
 			return;
 	}
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 3d0249599d5..4e314b90c75 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -34,7 +34,7 @@ _GLOBAL(call_do_softirq)
 	std	r0,16(r1)
 	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
 	mr	r1,r3
-	bl	.__do_softirq
+	bl	__do_softirq
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
@@ -45,7 +45,7 @@ _GLOBAL(call_do_irq)
 	std	r0,16(r1)
 	stdu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
 	mr	r1,r4
-	bl	.__do_irq
+	bl	__do_irq
 	ld	r1,0(r1)
 	ld	r0,16(r1)
 	mtlr	r0
@@ -506,7 +506,7 @@ _GLOBAL(kexec_smp_wait)
 	stb	r4,PACAKEXECSTATE(r13)
 	SYNC
 
-	b	.kexec_wait
+	b	kexec_wait
 
 /*
  * switch to real mode (turn mmu off)
@@ -576,7 +576,7 @@ _GLOBAL(kexec_sequence)
 
 	/* copy dest pages, flush whole dest image */
 	mr	r3,r29
-	bl	.kexec_copy_flush	/* (image) */
+	bl	kexec_copy_flush	/* (image) */
 
 	/* turn off mmu */
 	bl	real_mode
@@ -586,7 +586,7 @@ _GLOBAL(kexec_sequence)
 	mr	r4,r30		/* start, aka phys mem offset */
 	li	r5,0x100
 	li	r6,0
-	bl	.copy_and_flush	/* (dest, src, copy limit, start offset) */
+	bl	copy_and_flush	/* (dest, src, copy limit, start offset) */
 1:	/* assume normal blr return */
 
 	/* release other cpus to the new kernel secondary start at 0x60 */
@@ -595,8 +595,12 @@ _GLOBAL(kexec_sequence)
 	stw	r6,kexec_flag-1b(5)
 
 	/* clear out hardware hash page table and tlb */
-	ld	r5,0(r27)		/* deref function descriptor */
-	mtctr	r5
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+	ld	r12,0(r27)		/* deref function descriptor */
+#else
+	mr	r12,r27
+#endif
+	mtctr	r12
 	bctrl				/* ppc_md.hpte_clear_all(void); */
 
 /*
@@ -630,3 +634,31 @@ _GLOBAL(kexec_sequence)
 	li	r5,0
 	blr	/* image->start(physid, image->start, 0); */
 #endif /* CONFIG_KEXEC */
+
+#ifdef CONFIG_MODULES
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+
+#ifdef CONFIG_MODVERSIONS
+.weak __crc_TOC.
+.section "___kcrctab+TOC.","a"
+.globl __kcrctab_TOC.
+__kcrctab_TOC.:
+	.llong	__crc_TOC.
+#endif
+
+/*
+ * Export a fake .TOC. since both modpost and depmod will complain otherwise.
+ * Both modpost and depmod strip the leading . so we do the same here.
+ */
+.section "__ksymtab_strings","a"
+__kstrtab_TOC.:
+	.asciz "TOC."
+
+.section "___ksymtab+TOC.","a"
+/* This symbol name is important: it's used by modpost to find exported syms */
+.globl __ksymtab_TOC.
+__ksymtab_TOC.:
+	.llong 0 /* .value */
+	.llong __kstrtab_TOC.
+#endif /* ELFv2 */
+#endif /* MODULES */
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 12664c130d7..d807ee626af 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/ftrace.h>
 #include <linux/bug.h>
+#include <linux/uaccess.h>
 #include <asm/module.h>
 #include <asm/firmware.h>
 #include <asm/code-patching.h>
@@ -41,46 +42,170 @@
 #define DEBUGP(fmt , ...)
 #endif
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define R2_STACK_OFFSET 24
+
+/* An address is simply the address of the function. */
+typedef unsigned long func_desc_t;
+
+static func_desc_t func_desc(unsigned long addr)
+{
+	return addr;
+}
+static unsigned long func_addr(unsigned long addr)
+{
+	return addr;
+}
+static unsigned long stub_func_addr(func_desc_t func)
+{
+	return func;
+}
+
+/* PowerPC64 specific values for the Elf64_Sym st_other field.  */
+#define STO_PPC64_LOCAL_BIT	5
+#define STO_PPC64_LOCAL_MASK	(7 << STO_PPC64_LOCAL_BIT)
+#define PPC64_LOCAL_ENTRY_OFFSET(other)					\
+ (((1 << (((other) & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT)) >> 2) << 2)
+
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+	/* sym->st_other indicates offset to local entry point
+	 * (otherwise it will assume r12 is the address of the start
+	 * of function and try to derive r2 from it). */
+	return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#else
+#define R2_STACK_OFFSET 40
+
+/* An address is address of the OPD entry, which contains address of fn. */
+typedef struct ppc64_opd_entry func_desc_t;
+
+static func_desc_t func_desc(unsigned long addr)
+{
+	return *(struct ppc64_opd_entry *)addr;
+}
+static unsigned long func_addr(unsigned long addr)
+{
+	return func_desc(addr).funcaddr;
+}
+static unsigned long stub_func_addr(func_desc_t func)
+{
+	return func.funcaddr;
+}
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+	return 0;
+}
+#endif
+
 /* Like PPC32, we need little trampolines to do > 24-bit jumps (into
    the kernel itself).  But on PPC64, these need to be used for every
    jump, actually, to reset r2 (TOC+0x8000). */
 struct ppc64_stub_entry
 {
-	/* 28 byte jump instruction sequence (7 instructions) */
-	unsigned char jump[28];
-	unsigned char unused[4];
+	/* 28 byte jump instruction sequence (7 instructions). We only
+	 * need 6 instructions on ABIv2 but we always allocate 7 so
+	 * so we don't have to modify the trampoline load instruction. */
+	u32 jump[7];
+	u32 unused;
 	/* Data for the above code */
-	struct ppc64_opd_entry opd;
+	func_desc_t funcdata;
 };
 
-/* We use a stub to fix up r2 (TOC ptr) and to jump to the (external)
-   function which may be more than 24-bits away.  We could simply
-   patch the new r2 value and function pointer into the stub, but it's
-   significantly shorter to put these values at the end of the stub
-   code, and patch the stub address (32-bits relative to the TOC ptr,
-   r2) into the stub. */
-static struct ppc64_stub_entry ppc64_stub =
-{ .jump = {
-#ifdef __LITTLE_ENDIAN__
-	0x00, 0x00, 0x82, 0x3d, /* addis   r12,r2, <high> */
-	0x00, 0x00, 0x8c, 0x39, /* addi    r12,r12, <low> */
+/*
+ * PPC64 uses 24 bit jumps, but we need to jump into other modules or
+ * the kernel which may be further.  So we jump to a stub.
+ *
+ * For ELFv1 we need to use this to set up the new r2 value (aka TOC
+ * pointer).  For ELFv2 it's the callee's responsibility to set up the
+ * new r2, but for both we need to save the old r2.
+ *
+ * We could simply patch the new r2 value and function pointer into
+ * the stub, but it's significantly shorter to put these values at the
+ * end of the stub code, and patch the stub address (32-bits relative
+ * to the TOC ptr, r2) into the stub.
+ */
+
+static u32 ppc64_stub_insns[] = {
+	0x3d620000,			/* addis   r11,r2, <high> */
+	0x396b0000,			/* addi    r11,r11, <low> */
 	/* Save current r2 value in magic place on the stack. */
-	0x28, 0x00, 0x41, 0xf8, /* std     r2,40(r1) */
-	0x20, 0x00, 0x6c, 0xe9, /* ld      r11,32(r12) */
-	0x28, 0x00, 0x4c, 0xe8, /* ld      r2,40(r12) */
-	0xa6, 0x03, 0x69, 0x7d, /* mtctr   r11 */
-	0x20, 0x04, 0x80, 0x4e  /* bctr */
-#else
-	0x3d, 0x82, 0x00, 0x00, /* addis   r12,r2, <high> */
-	0x39, 0x8c, 0x00, 0x00, /* addi    r12,r12, <low> */
-	/* Save current r2 value in magic place on the stack. */
-	0xf8, 0x41, 0x00, 0x28, /* std     r2,40(r1) */
-	0xe9, 0x6c, 0x00, 0x20, /* ld      r11,32(r12) */
-	0xe8, 0x4c, 0x00, 0x28, /* ld      r2,40(r12) */
-	0x7d, 0x69, 0x03, 0xa6, /* mtctr   r11 */
-	0x4e, 0x80, 0x04, 0x20  /* bctr */
+	0xf8410000|R2_STACK_OFFSET,	/* std     r2,R2_STACK_OFFSET(r1) */
+	0xe98b0020,			/* ld      r12,32(r11) */
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+	/* Set up new r2 from function descriptor */
+	0xe84b0028,			/* ld      r2,40(r11) */
+#endif
+	0x7d8903a6,			/* mtctr   r12 */
+	0x4e800420			/* bctr */
+};
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+static u32 ppc64_stub_mask[] = {
+	0xffff0000,
+	0xffff0000,
+	0xffffffff,
+	0xffffffff,
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+	0xffffffff,
+#endif
+	0xffffffff,
+	0xffffffff
+};
+
+bool is_module_trampoline(u32 *p)
+{
+	unsigned int i;
+	u32 insns[ARRAY_SIZE(ppc64_stub_insns)];
+
+	BUILD_BUG_ON(sizeof(ppc64_stub_insns) != sizeof(ppc64_stub_mask));
+
+	if (probe_kernel_read(insns, p, sizeof(insns)))
+		return -EFAULT;
+
+	for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) {
+		u32 insna = insns[i];
+		u32 insnb = ppc64_stub_insns[i];
+		u32 mask = ppc64_stub_mask[i];
+
+		if ((insna & mask) != (insnb & mask))
+			return false;
+	}
+
+	return true;
+}
+
+int module_trampoline_target(struct module *mod, u32 *trampoline,
+			     unsigned long *target)
+{
+	u32 buf[2];
+	u16 upper, lower;
+	long offset;
+	void *toc_entry;
+
+	if (probe_kernel_read(buf, trampoline, sizeof(buf)))
+		return -EFAULT;
+
+	upper = buf[0] & 0xffff;
+	lower = buf[1] & 0xffff;
+
+	/* perform the addis/addi, both signed */
+	offset = ((short)upper << 16) + (short)lower;
+
+	/*
+	 * Now get the address this trampoline jumps to. This
+	 * is always 32 bytes into our trampoline stub.
+	 */
+	toc_entry = (void *)mod->arch.toc + offset + 32;
+
+	if (probe_kernel_read(target, toc_entry, sizeof(*target)))
+		return -EFAULT;
+
+	return 0;
+}
+
 #endif
-} };
 
 /* Count how many different 24-bit relocations (different symbol,
    different addend) */
@@ -183,17 +308,27 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 	return relocs * sizeof(struct ppc64_stub_entry);
 }
 
+/* Still needed for ELFv2, for .TOC. */
 static void dedotify_versions(struct modversion_info *vers,
 			      unsigned long size)
 {
 	struct modversion_info *end;
 
 	for (end = (void *)vers + size; vers < end; vers++)
-		if (vers->name[0] == '.')
+		if (vers->name[0] == '.') {
 			memmove(vers->name, vers->name+1, strlen(vers->name));
+#ifdef ARCH_RELOCATES_KCRCTAB
+			/* The TOC symbol has no CRC computed. To avoid CRC
+			 * check failing, we must force it to the expected
+			 * value (see CRC check in module.c).
+			 */
+			if (!strcmp(vers->name, "TOC."))
+				vers->crc = -(unsigned long)reloc_start;
+#endif
+		}
 }
 
-/* Undefined symbols which refer to .funcname, hack to funcname */
+/* Undefined symbols which refer to .funcname, hack to funcname (or .TOC.) */
 static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 {
 	unsigned int i;
@@ -207,6 +342,24 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab)
 	}
 }
 
+static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs,
+			       const char *strtab,
+			       unsigned int symindex)
+{
+	unsigned int i, numsyms;
+	Elf64_Sym *syms;
+
+	syms = (Elf64_Sym *)sechdrs[symindex].sh_addr;
+	numsyms = sechdrs[symindex].sh_size / sizeof(Elf64_Sym);
+
+	for (i = 1; i < numsyms; i++) {
+		if (syms[i].st_shndx == SHN_UNDEF
+		    && strcmp(strtab + syms[i].st_name, "TOC.") == 0)
+			return &syms[i];
+	}
+	return NULL;
+}
+
 int module_frob_arch_sections(Elf64_Ehdr *hdr,
 			      Elf64_Shdr *sechdrs,
 			      char *secstrings,
@@ -271,21 +424,12 @@ static inline unsigned long my_r2(Elf64_Shdr *sechdrs, struct module *me)
 /* Patch stub to reference function and correct r2 value. */
 static inline int create_stub(Elf64_Shdr *sechdrs,
 			      struct ppc64_stub_entry *entry,
-			      struct ppc64_opd_entry *opd,
+			      unsigned long addr,
 			      struct module *me)
 {
-	Elf64_Half *loc1, *loc2;
 	long reladdr;
 
-	*entry = ppc64_stub;
-
-#ifdef __LITTLE_ENDIAN__
-	loc1 = (Elf64_Half *)&entry->jump[0];
-	loc2 = (Elf64_Half *)&entry->jump[4];
-#else
-	loc1 = (Elf64_Half *)&entry->jump[2];
-	loc2 = (Elf64_Half *)&entry->jump[6];
-#endif
+	memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns));
 
 	/* Stub uses address relative to r2. */
 	reladdr = (unsigned long)entry - my_r2(sechdrs, me);
@@ -296,35 +440,33 @@ static inline int create_stub(Elf64_Shdr *sechdrs,
 	}
 	DEBUGP("Stub %p get data from reladdr %li\n", entry, reladdr);
 
-	*loc1 = PPC_HA(reladdr);
-	*loc2 = PPC_LO(reladdr);
-	entry->opd.funcaddr = opd->funcaddr;
-	entry->opd.r2 = opd->r2;
+	entry->jump[0] |= PPC_HA(reladdr);
+	entry->jump[1] |= PPC_LO(reladdr);
+	entry->funcdata = func_desc(addr);
 	return 1;
 }
 
-/* Create stub to jump to function described in this OPD: we need the
+/* Create stub to jump to function described in this OPD/ptr: we need the
    stub to set up the TOC ptr (r2) for the function. */
 static unsigned long stub_for_addr(Elf64_Shdr *sechdrs,
-				   unsigned long opdaddr,
+				   unsigned long addr,
 				   struct module *me)
 {
 	struct ppc64_stub_entry *stubs;
-	struct ppc64_opd_entry *opd = (void *)opdaddr;
 	unsigned int i, num_stubs;
 
 	num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs);
 
 	/* Find this stub, or if that fails, the next avail. entry */
 	stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr;
-	for (i = 0; stubs[i].opd.funcaddr; i++) {
+	for (i = 0; stub_func_addr(stubs[i].funcdata); i++) {
 		BUG_ON(i >= num_stubs);
 
-		if (stubs[i].opd.funcaddr == opd->funcaddr)
+		if (stub_func_addr(stubs[i].funcdata) == func_addr(addr))
 			return (unsigned long)&stubs[i];
 	}
 
-	if (!create_stub(sechdrs, &stubs[i], opd, me))
+	if (!create_stub(sechdrs, &stubs[i], addr, me))
 		return 0;
 
 	return (unsigned long)&stubs[i];
@@ -339,7 +481,8 @@ static int restore_r2(u32 *instruction, struct module *me)
 		       me->name, *instruction);
 		return 0;
 	}
-	*instruction = 0xe8410028;	/* ld r2,40(r1) */
+	/* ld r2,R2_STACK_OFFSET(r1) */
+	*instruction = 0xe8410000 | R2_STACK_OFFSET;
 	return 1;
 }
 
@@ -357,6 +500,17 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 
 	DEBUGP("Applying ADD relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
+
+	/* First time we're called, we can fix up .TOC. */
+	if (!me->arch.toc_fixed) {
+		sym = find_dot_toc(sechdrs, strtab, symindex);
+		/* It's theoretically possible that a module doesn't want a
+		 * .TOC. so don't fail it just for that. */
+		if (sym)
+			sym->st_value = my_r2(sechdrs, me);
+		me->arch.toc_fixed = true;
+	}
+
 	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
 		/* This is where to make the change */
 		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
@@ -453,7 +607,8 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 					return -ENOENT;
 				if (!restore_r2((u32 *)location + 1, me))
 					return -ENOEXEC;
-			}
+			} else
+				value += local_entry_offset(sym);
 
 			/* Convert value to relative */
 			value -= (unsigned long)location;
@@ -474,6 +629,31 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			*location = value - (unsigned long)location;
 			break;
 
+		case R_PPC64_TOCSAVE:
+			/*
+			 * Marker reloc indicates we don't have to save r2.
+			 * That would only save us one instruction, so ignore
+			 * it.
+			 */
+			break;
+
+		case R_PPC64_REL16_HA:
+			/* Subtract location pointer */
+			value -= (unsigned long)location;
+			value = ((value + 0x8000) >> 16);
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+			break;
+
+		case R_PPC64_REL16_LO:
+			/* Subtract location pointer */
+			value -= (unsigned long)location;
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+			break;
+
 		default:
 			printk("%s: Unknown ADD relocation: %lu\n",
 			       me->name,
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 24d342e9179..b2814e23e1e 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
@@ -120,6 +121,16 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 	return 1;
 }
 
+void pcibios_reset_secondary_bus(struct pci_dev *dev)
+{
+	if (ppc_md.pcibios_reset_secondary_bus) {
+		ppc_md.pcibios_reset_secondary_bus(dev);
+		return;
+	}
+
+	pci_reset_secondary_bus(dev);
+}
+
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
@@ -646,60 +657,36 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 				  struct device_node *dev, int primary)
 {
-	const __be32 *ranges;
-	int rlen;
-	int pna = of_n_addr_cells(dev);
-	int np = pna + 5;
 	int memno = 0;
-	u32 pci_space;
-	unsigned long long pci_addr, cpu_addr, pci_next, cpu_next, size;
 	struct resource *res;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
 
 	printk(KERN_INFO "PCI host bridge %s %s ranges:\n",
 	       dev->full_name, primary ? "(primary)" : "");
 
-	/* Get ranges property */
-	ranges = of_get_property(dev, "ranges", &rlen);
-	if (ranges == NULL)
+	/* Check for ranges property */
+	if (of_pci_range_parser_init(&parser, dev))
 		return;
 
 	/* Parse it */
-	while ((rlen -= np * 4) >= 0) {
-		/* Read next ranges element */
-		pci_space = of_read_number(ranges, 1);
-		pci_addr = of_read_number(ranges + 1, 2);
-		cpu_addr = of_translate_address(dev, ranges + 3);
-		size = of_read_number(ranges + pna + 3, 2);
-		ranges += np;
-
+	for_each_of_pci_range(&parser, &range) {
 		/* If we failed translation or got a zero-sized region
 		 * (some FW try to feed us with non sensical zero sized regions
 		 * such as power3 which look like some kind of attempt at exposing
 		 * the VGA memory hole)
 		 */
-		if (cpu_addr == OF_BAD_ADDR || size == 0)
+		if (range.cpu_addr == OF_BAD_ADDR || range.size == 0)
 			continue;
 
-		/* Now consume following elements while they are contiguous */
-		for (; rlen >= np * sizeof(u32);
-		     ranges += np, rlen -= np * 4) {
-			if (of_read_number(ranges, 1) != pci_space)
-				break;
-			pci_next = of_read_number(ranges + 1, 2);
-			cpu_next = of_translate_address(dev, ranges + 3);
-			if (pci_next != pci_addr + size ||
-			    cpu_next != cpu_addr + size)
-				break;
-			size += of_read_number(ranges + pna + 3, 2);
-		}
-
 		/* Act based on address space type */
 		res = NULL;
-		switch ((pci_space >> 24) & 0x3) {
-		case 1:		/* PCI IO space */
+		switch (range.flags & IORESOURCE_TYPE_BITS) {
+		case IORESOURCE_IO:
 			printk(KERN_INFO
 			       "  IO 0x%016llx..0x%016llx -> 0x%016llx\n",
-			       cpu_addr, cpu_addr + size - 1, pci_addr);
+			       range.cpu_addr, range.cpu_addr + range.size - 1,
+			       range.pci_addr);
 
 			/* We support only one IO range */
 			if (hose->pci_io_size) {
@@ -709,11 +696,12 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			}
 #ifdef CONFIG_PPC32
 			/* On 32 bits, limit I/O space to 16MB */
-			if (size > 0x01000000)
-				size = 0x01000000;
+			if (range.size > 0x01000000)
+				range.size = 0x01000000;
 
 			/* 32 bits needs to map IOs here */
-			hose->io_base_virt = ioremap(cpu_addr, size);
+			hose->io_base_virt = ioremap(range.cpu_addr,
+						range.size);
 
 			/* Expect trouble if pci_addr is not 0 */
 			if (primary)
@@ -723,20 +711,20 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			/* pci_io_size and io_base_phys always represent IO
 			 * space starting at 0 so we factor in pci_addr
 			 */
-			hose->pci_io_size = pci_addr + size;
-			hose->io_base_phys = cpu_addr - pci_addr;
+			hose->pci_io_size = range.pci_addr + range.size;
+			hose->io_base_phys = range.cpu_addr - range.pci_addr;
 
 			/* Build resource */
 			res = &hose->io_resource;
-			res->flags = IORESOURCE_IO;
-			res->start = pci_addr;
+			range.cpu_addr = range.pci_addr;
 			break;
-		case 2:		/* PCI Memory space */
-		case 3:		/* PCI 64 bits Memory space */
+		case IORESOURCE_MEM:
 			printk(KERN_INFO
 			       " MEM 0x%016llx..0x%016llx -> 0x%016llx %s\n",
-			       cpu_addr, cpu_addr + size - 1, pci_addr,
-			       (pci_space & 0x40000000) ? "Prefetch" : "");
+			       range.cpu_addr, range.cpu_addr + range.size - 1,
+			       range.pci_addr,
+			       (range.pci_space & 0x40000000) ?
+			       "Prefetch" : "");
 
 			/* We support only 3 memory ranges */
 			if (memno >= 3) {
@@ -745,28 +733,21 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 				continue;
 			}
 			/* Handles ISA memory hole space here */
-			if (pci_addr == 0) {
+			if (range.pci_addr == 0) {
 				if (primary || isa_mem_base == 0)
-					isa_mem_base = cpu_addr;
-				hose->isa_mem_phys = cpu_addr;
-				hose->isa_mem_size = size;
+					isa_mem_base = range.cpu_addr;
+				hose->isa_mem_phys = range.cpu_addr;
+				hose->isa_mem_size = range.size;
 			}
 
 			/* Build resource */
-			hose->mem_offset[memno] = cpu_addr - pci_addr;
+			hose->mem_offset[memno] = range.cpu_addr -
+							range.pci_addr;
 			res = &hose->mem_resources[memno++];
-			res->flags = IORESOURCE_MEM;
-			if (pci_space & 0x40000000)
-				res->flags |= IORESOURCE_PREFETCH;
-			res->start = cpu_addr;
 			break;
 		}
 		if (res != NULL) {
-			res->name = dev->full_name;
-			res->end = res->start + size - 1;
-			res->parent = NULL;
-			res->sibling = NULL;
-			res->child = NULL;
+			of_pci_range_to_resource(&range, dev, res);
 		}
 	}
 }
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 059e244484f..44562aa97f1 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -304,6 +304,9 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus,
 	struct pci_dev *dev = NULL;
 	const __be32 *reg;
 	int reglen, devfn;
+#ifdef CONFIG_EEH
+	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+#endif
 
 	pr_debug("  * %s\n", dn->full_name);
 	if (!of_device_is_available(dn))
@@ -321,6 +324,12 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus,
 		return dev;
 	}
 
+	/* Device removed permanently ? */
+#ifdef CONFIG_EEH
+	if (edev && (edev->mode & EEH_DEV_REMOVED))
+		return NULL;
+#endif
+
 	/* create a new pci_dev for this device */
 	dev = of_create_pci_dev(dn, bus, devfn);
 	if (!dev)
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 450850a49dc..48d17d6fca5 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -155,9 +155,7 @@ EXPORT_SYMBOL(__cmpdi2);
 #endif
 long long __bswapdi2(long long);
 EXPORT_SYMBOL(__bswapdi2);
-#ifdef __BIG_ENDIAN__
 EXPORT_SYMBOL(memcpy);
-#endif
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memcmp);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 31d021506d2..be99774d3f4 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -54,6 +54,7 @@
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #endif
+#include <asm/code-patching.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
@@ -495,14 +496,21 @@ static inline int set_dawr(struct arch_hw_breakpoint *brk)
 	return 0;
 }
 
-int set_breakpoint(struct arch_hw_breakpoint *brk)
+void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
 	__get_cpu_var(current_brk) = *brk;
 
 	if (cpu_has_feature(CPU_FTR_DAWR))
-		return set_dawr(brk);
+		set_dawr(brk);
+	else
+		set_dabr(brk);
+}
 
-	return set_dabr(brk);
+void set_breakpoint(struct arch_hw_breakpoint *brk)
+{
+	preempt_disable();
+	__set_breakpoint(brk);
+	preempt_enable();
 }
 
 #ifdef CONFIG_PPC64
@@ -747,15 +755,15 @@ struct task_struct *__switch_to(struct task_struct *prev,
 
 	WARN_ON(!irqs_disabled());
 
-	/* Back up the TAR across context switches.
+	/* Back up the TAR and DSCR across context switches.
 	 * Note that the TAR is not available for use in the kernel.  (To
 	 * provide this, the TAR should be backed up/restored on exception
 	 * entry/exit instead, and be in pt_regs.  FIXME, this should be in
 	 * pt_regs anyway (for debug).)
-	 * Save the TAR here before we do treclaim/trecheckpoint as these
-	 * will change the TAR.
+	 * Save the TAR and DSCR here before we do treclaim/trecheckpoint as
+	 * these will change them.
 	 */
-	save_tar(&prev->thread);
+	save_early_sprs(&prev->thread);
 
 	__switch_to_tm(prev);
 
@@ -834,7 +842,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
  */
 #ifndef CONFIG_HAVE_HW_BREAKPOINT
 	if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk)))
-		set_breakpoint(&new->thread.hw_brk);
+		__set_breakpoint(&new->thread.hw_brk);
 #endif /* CONFIG_HAVE_HW_BREAKPOINT */
 #endif
 
@@ -1108,7 +1116,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		struct thread_info *ti = (void *)task_stack_page(p);
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gpr[1] = sp + sizeof(struct pt_regs);
-		childregs->gpr[14] = usp;	/* function */
+		/* function */
+		if (usp)
+			childregs->gpr[14] = ppc_function_entry((void *)usp);
 #ifdef CONFIG_PPC64
 		clear_tsk_thread_flag(p, TIF_32BIT);
 		childregs->softe = 1;
@@ -1187,17 +1197,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	if (cpu_has_feature(CPU_FTR_HAS_PPR))
 		p->thread.ppr = INIT_PPR;
 #endif
-	/*
-	 * The PPC64 ABI makes use of a TOC to contain function 
-	 * pointers.  The function (ret_from_except) is actually a pointer
-	 * to the TOC entry.  The first entry is a pointer to the actual
-	 * function.
-	 */
-#ifdef CONFIG_PPC64
-	kregs->nip = *((unsigned long *)f);
-#else
-	kregs->nip = (unsigned long)f;
-#endif
+	kregs->nip = ppc_function_entry(f);
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 613a860a203..b694b073097 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -662,13 +662,6 @@ void __init early_init_devtree(void *params)
 	of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
 #endif
 
-	/* Pre-initialize the cmd_line with the content of boot_commmand_line,
-	 * which will be empty except when the content of the variable has
-	 * been overriden by a bootloading mechanism. This happens typically
-	 * with HAL takeover
-	 */
-	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
-
 	/* Retrieve various informations from the /chosen node of the
 	 * device-tree, including the platform type, initrd location and
 	 * size, TCE reserve, and more ...
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 078145acf7f..1a85d8f9673 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1268,201 +1268,6 @@ static u64 __initdata prom_opal_base;
 static u64 __initdata prom_opal_entry;
 #endif
 
-#ifdef __BIG_ENDIAN__
-/* XXX Don't change this structure without updating opal-takeover.S */
-static struct opal_secondary_data {
-	s64				ack;	/*  0 */
-	u64				go;	/*  8 */
-	struct opal_takeover_args	args;	/* 16 */
-} opal_secondary_data;
-
-static u64 __initdata prom_opal_align;
-static u64 __initdata prom_opal_size;
-static int __initdata prom_rtas_start_cpu;
-static u64 __initdata prom_rtas_data;
-static u64 __initdata prom_rtas_entry;
-
-extern char opal_secondary_entry;
-
-static void __init prom_query_opal(void)
-{
-	long rc;
-
-	/* We must not query for OPAL presence on a machine that
-	 * supports TNK takeover (970 blades), as this uses the same
-	 * h-call with different arguments and will crash
-	 */
-	if (PHANDLE_VALID(call_prom("finddevice", 1, 1,
-				    ADDR("/tnk-memory-map")))) {
-		prom_printf("TNK takeover detected, skipping OPAL check\n");
-		return;
-	}
-
-	prom_printf("Querying for OPAL presence... ");
-
-	rc = opal_query_takeover(&prom_opal_size,
-				 &prom_opal_align);
-	prom_debug("(rc = %ld) ", rc);
-	if (rc != 0) {
-		prom_printf("not there.\n");
-		return;
-	}
-	of_platform = PLATFORM_OPAL;
-	prom_printf(" there !\n");
-	prom_debug("  opal_size  = 0x%lx\n", prom_opal_size);
-	prom_debug("  opal_align = 0x%lx\n", prom_opal_align);
-	if (prom_opal_align < 0x10000)
-		prom_opal_align = 0x10000;
-}
-
-static int __init prom_rtas_call(int token, int nargs, int nret,
-				 int *outputs, ...)
-{
-	struct rtas_args rtas_args;
-	va_list list;
-	int i;
-
-	rtas_args.token = token;
-	rtas_args.nargs = nargs;
-	rtas_args.nret  = nret;
-	rtas_args.rets  = (rtas_arg_t *)&(rtas_args.args[nargs]);
-	va_start(list, outputs);
-	for (i = 0; i < nargs; ++i)
-		rtas_args.args[i] = va_arg(list, rtas_arg_t);
-	va_end(list);
-
-	for (i = 0; i < nret; ++i)
-		rtas_args.rets[i] = 0;
-
-	opal_enter_rtas(&rtas_args, prom_rtas_data,
-			prom_rtas_entry);
-
-	if (nret > 1 && outputs != NULL)
-		for (i = 0; i < nret-1; ++i)
-			outputs[i] = rtas_args.rets[i+1];
-	return (nret > 0)? rtas_args.rets[0]: 0;
-}
-
-static void __init prom_opal_hold_cpus(void)
-{
-	int i, cnt, cpu, rc;
-	long j;
-	phandle node;
-	char type[64];
-	u32 servers[8];
-	void *entry = (unsigned long *)&opal_secondary_entry;
-	struct opal_secondary_data *data = &opal_secondary_data;
-
-	prom_debug("prom_opal_hold_cpus: start...\n");
-	prom_debug("    - entry       = 0x%x\n", entry);
-	prom_debug("    - data        = 0x%x\n", data);
-
-	data->ack = -1;
-	data->go = 0;
-
-	/* look for cpus */
-	for (node = 0; prom_next_node(&node); ) {
-		type[0] = 0;
-		prom_getprop(node, "device_type", type, sizeof(type));
-		if (strcmp(type, "cpu") != 0)
-			continue;
-
-		/* Skip non-configured cpus. */
-		if (prom_getprop(node, "status", type, sizeof(type)) > 0)
-			if (strcmp(type, "okay") != 0)
-				continue;
-
-		cnt = prom_getprop(node, "ibm,ppc-interrupt-server#s", servers,
-			     sizeof(servers));
-		if (cnt == PROM_ERROR)
-			break;
-		cnt >>= 2;
-		for (i = 0; i < cnt; i++) {
-			cpu = servers[i];
-			prom_debug("CPU %d ... ", cpu);
-			if (cpu == prom.cpu) {
-				prom_debug("booted !\n");
-				continue;
-			}
-			prom_debug("starting ... ");
-
-			/* Init the acknowledge var which will be reset by
-			 * the secondary cpu when it awakens from its OF
-			 * spinloop.
-			 */
-			data->ack = -1;
-			rc = prom_rtas_call(prom_rtas_start_cpu, 3, 1,
-					    NULL, cpu, entry, data);
-			prom_debug("rtas rc=%d ...", rc);
-
-			for (j = 0; j < 100000000 && data->ack == -1; j++) {
-				HMT_low();
-				mb();
-			}
-			HMT_medium();
-			if (data->ack != -1)
-				prom_debug("done, PIR=0x%x\n", data->ack);
-			else
-				prom_debug("timeout !\n");
-		}
-	}
-	prom_debug("prom_opal_hold_cpus: end...\n");
-}
-
-static void __init prom_opal_takeover(void)
-{
-	struct opal_secondary_data *data = &opal_secondary_data;
-	struct opal_takeover_args *args = &data->args;
-	u64 align = prom_opal_align;
-	u64 top_addr, opal_addr;
-
-	args->k_image	= (u64)_stext;
-	args->k_size	= _end - _stext;
-	args->k_entry	= 0;
-	args->k_entry2	= 0x60;
-
-	top_addr = _ALIGN_UP(args->k_size, align);
-
-	if (prom_initrd_start != 0) {
-		args->rd_image = prom_initrd_start;
-		args->rd_size = prom_initrd_end - args->rd_image;
-		args->rd_loc = top_addr;
-		top_addr = _ALIGN_UP(args->rd_loc + args->rd_size, align);
-	}
-
-	/* Pickup an address for the HAL. We want to go really high
-	 * up to avoid problem with future kexecs. On the other hand
-	 * we don't want to be all over the TCEs on P5IOC2 machines
-	 * which are going to be up there too. We assume the machine
-	 * has plenty of memory, and we ask for the HAL for now to
-	 * be just below the 1G point, or above the initrd
-	 */
-	opal_addr = _ALIGN_DOWN(0x40000000 - prom_opal_size, align);
-	if (opal_addr < top_addr)
-		opal_addr = top_addr;
-	args->hal_addr = opal_addr;
-
-	/* Copy the command line to the kernel image */
-	strlcpy(boot_command_line, prom_cmd_line,
-		COMMAND_LINE_SIZE);
-
-	prom_debug("  k_image    = 0x%lx\n", args->k_image);
-	prom_debug("  k_size     = 0x%lx\n", args->k_size);
-	prom_debug("  k_entry    = 0x%lx\n", args->k_entry);
-	prom_debug("  k_entry2   = 0x%lx\n", args->k_entry2);
-	prom_debug("  hal_addr   = 0x%lx\n", args->hal_addr);
-	prom_debug("  rd_image   = 0x%lx\n", args->rd_image);
-	prom_debug("  rd_size    = 0x%lx\n", args->rd_size);
-	prom_debug("  rd_loc     = 0x%lx\n", args->rd_loc);
-	prom_printf("Performing OPAL takeover,this can take a few minutes..\n");
-	prom_close_stdin();
-	mb();
-	data->go = 1;
-	for (;;)
-		opal_do_takeover(args);
-}
-#endif /* __BIG_ENDIAN__ */
-
 /*
  * Allocate room for and instantiate OPAL
  */
@@ -1597,12 +1402,6 @@ static void __init prom_instantiate_rtas(void)
 			 &val, sizeof(val)) != PROM_ERROR)
 		rtas_has_query_cpu_stopped = true;
 
-#if defined(CONFIG_PPC_POWERNV) && defined(__BIG_ENDIAN__)
-	/* PowerVN takeover hack */
-	prom_rtas_data = base;
-	prom_rtas_entry = entry;
-	prom_getprop(rtas_node, "start-cpu", &prom_rtas_start_cpu, 4);
-#endif
 	prom_debug("rtas base     = 0x%x\n", base);
 	prom_debug("rtas entry    = 0x%x\n", entry);
 	prom_debug("rtas size     = 0x%x\n", (long)size);
@@ -3027,16 +2826,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 		prom_instantiate_rtas();
 
 #ifdef CONFIG_PPC_POWERNV
-#ifdef __BIG_ENDIAN__
-	/* Detect HAL and try instanciating it & doing takeover */
-	if (of_platform == PLATFORM_PSERIES_LPAR) {
-		prom_query_opal();
-		if (of_platform == PLATFORM_OPAL) {
-			prom_opal_hold_cpus();
-			prom_opal_takeover();
-		}
-	} else
-#endif /* __BIG_ENDIAN__ */
 	if (of_platform == PLATFORM_OPAL)
 		prom_instantiate_opal();
 #endif /* CONFIG_PPC_POWERNV */
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index b0c263da219..fe8e54b9ef7 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -21,9 +21,7 @@ _end enter_prom memcpy memset reloc_offset __secondary_hold
 __secondary_hold_acknowledge __secondary_hold_spinloop __start
 strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
-opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry
-boot_command_line __prom_init_toc_start __prom_init_toc_end
-btext_setup_display"
+__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC."
 
 NM="$1"
 OBJ="$2"
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 658e89d2025..db2b482af65 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -611,17 +611,19 @@ static void rtas_flash_firmware(int reboot_type)
 	for (f = flist; f; f = next) {
 		/* Translate data addrs to absolute */
 		for (i = 0; i < f->num_blocks; i++) {
-			f->blocks[i].data = (char *)__pa(f->blocks[i].data);
+			f->blocks[i].data = (char *)cpu_to_be64(__pa(f->blocks[i].data));
 			image_size += f->blocks[i].length;
+			f->blocks[i].length = cpu_to_be64(f->blocks[i].length);
 		}
 		next = f->next;
 		/* Don't translate NULL pointer for last entry */
 		if (f->next)
-			f->next = (struct flash_block_list *)__pa(f->next);
+			f->next = (struct flash_block_list *)cpu_to_be64(__pa(f->next));
 		else
 			f->next = NULL;
 		/* make num_blocks into the version/length field */
 		f->num_blocks = (FLASH_BLOCK_LIST_VERSION << 56) | ((f->num_blocks+1)*16);
+		f->num_blocks = cpu_to_be64(f->num_blocks);
 	}
 
 	printk(KERN_ALERT "FLASH: flash image is %ld bytes\n", image_size);
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 7d4c7172f38..c168337aef9 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -80,10 +80,6 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
 	if (ret)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	if (returnval == EEH_IO_ERROR_VALUE(size) &&
-	    eeh_dev_check_failure(of_node_to_eeh_dev(pdn->node)))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
 	return PCIBIOS_SUCCESSFUL;
 }
 
@@ -92,18 +88,39 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 				int where, int size, u32 *val)
 {
 	struct device_node *busdn, *dn;
-
-	busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+	bool found = false;
+#ifdef CONFIG_EEH
+	struct eeh_dev *edev;
+#endif
+	int ret;
 
 	/* Search only direct children of the bus */
+	*val = 0xFFFFFFFF;
+	busdn = pci_bus_to_OF_node(bus);
 	for (dn = busdn->child; dn; dn = dn->sibling) {
-		struct pci_dn *pdn = PCI_DN(dn);
+		pdn = PCI_DN(dn);
 		if (pdn && pdn->devfn == devfn
-		    && of_device_is_available(dn))
-			return rtas_read_config(pdn, where, size, val);
+		    && of_device_is_available(dn)) {
+			found = true;
+			break;
+		}
 	}
 
-	return PCIBIOS_DEVICE_NOT_FOUND;
+	if (!found)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+#ifdef CONFIG_EEH
+	edev = of_node_to_eeh_dev(dn);
+	if (edev && edev->pe && edev->pe->state & EEH_PE_RESET)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+#endif
+
+	ret = rtas_read_config(pdn, where, size, val);
+	if (*val == EEH_IO_ERROR_VALUE(size) &&
+	    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	return ret;
 }
 
 int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
@@ -136,17 +153,34 @@ static int rtas_pci_write_config(struct pci_bus *bus,
 				 int where, int size, u32 val)
 {
 	struct device_node *busdn, *dn;
-
-	busdn = pci_bus_to_OF_node(bus);
+	struct pci_dn *pdn;
+	bool found = false;
+#ifdef CONFIG_EEH
+	struct eeh_dev *edev;
+#endif
+	int ret;
 
 	/* Search only direct children of the bus */
+	busdn = pci_bus_to_OF_node(bus);
 	for (dn = busdn->child; dn; dn = dn->sibling) {
-		struct pci_dn *pdn = PCI_DN(dn);
+		pdn = PCI_DN(dn);
 		if (pdn && pdn->devfn == devfn
-		    && of_device_is_available(dn))
-			return rtas_write_config(pdn, where, size, val);
+		    && of_device_is_available(dn)) {
+			found = true;
+			break;
+		}
 	}
-	return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (!found)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+#ifdef CONFIG_EEH
+	edev = of_node_to_eeh_dev(dn);
+	if (edev && edev->pe && (edev->pe->state & EEH_PE_RESET))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+#endif
+	ret = rtas_write_config(pdn, where, size, val);
+
+	return ret;
 }
 
 static struct pci_ops rtas_pci_ops = {
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 79b7612ac6f..e5b022c55cc 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -212,6 +212,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 {
 	unsigned long cpu_id = (unsigned long)v - 1;
 	unsigned int pvr;
+	unsigned long proc_freq;
 	unsigned short maj;
 	unsigned short min;
 
@@ -263,12 +264,19 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 #endif /* CONFIG_TAU */
 
 	/*
-	 * Assume here that all clock rates are the same in a
-	 * smp system.  -- Cort
+	 * Platforms that have variable clock rates, should implement
+	 * the method ppc_md.get_proc_freq() that reports the clock
+	 * rate of a given cpu. The rest can use ppc_proc_freq to
+	 * report the clock rate that is same across all cpus.
 	 */
-	if (ppc_proc_freq)
+	if (ppc_md.get_proc_freq)
+		proc_freq = ppc_md.get_proc_freq(cpu_id);
+	else
+		proc_freq = ppc_proc_freq;
+
+	if (proc_freq)
 		seq_printf(m, "clock\t\t: %lu.%06luMHz\n",
-			   ppc_proc_freq / 1000000, ppc_proc_freq % 1000000);
+			   proc_freq / 1000000, proc_freq % 1000000);
 
 	if (ppc_md.show_percpuinfo != NULL)
 		ppc_md.show_percpuinfo(m, cpu_id);
@@ -382,9 +390,10 @@ void __init check_for_initrd(void)
 
 #ifdef CONFIG_SMP
 
-int threads_per_core, threads_shift;
+int threads_per_core, threads_per_subcore, threads_shift;
 cpumask_t threads_core_mask;
 EXPORT_SYMBOL_GPL(threads_per_core);
+EXPORT_SYMBOL_GPL(threads_per_subcore);
 EXPORT_SYMBOL_GPL(threads_shift);
 EXPORT_SYMBOL_GPL(threads_core_mask);
 
@@ -393,6 +402,7 @@ static void __init cpu_init_thread_core_maps(int tpc)
 	int i;
 
 	threads_per_core = tpc;
+	threads_per_subcore = tpc;
 	cpumask_clear(&threads_core_mask);
 
 	/* This implementation only supports power of 2 number of threads
@@ -459,9 +469,17 @@ void __init smp_setup_cpu_maps(void)
 		}
 
 		for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
+			bool avail;
+
 			DBG("    thread %d -> cpu %d (hard id %d)\n",
 			    j, cpu, be32_to_cpu(intserv[j]));
-			set_cpu_present(cpu, true);
+
+			avail = of_device_is_available(dn);
+			if (!avail)
+				avail = !of_property_match_string(dn,
+						"enable-method", "spin-table");
+
+			set_cpu_present(cpu, avail);
 			set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j]));
 			set_cpu_possible(cpu, true);
 			cpu++;
@@ -718,33 +736,6 @@ static int powerpc_debugfs_init(void)
 arch_initcall(powerpc_debugfs_init);
 #endif
 
-#ifdef CONFIG_BOOKE_WDT
-extern u32 booke_wdt_enabled;
-extern u32 booke_wdt_period;
-
-/* Checks wdt=x and wdt_period=xx command-line option */
-notrace int __init early_parse_wdt(char *p)
-{
-	if (p && strncmp(p, "0", 1) != 0)
-		booke_wdt_enabled = 1;
-
-	return 0;
-}
-early_param("wdt", early_parse_wdt);
-
-int __init early_parse_wdt_period(char *p)
-{
-	unsigned long ret;
-	if (p) {
-		if (!kstrtol(p, 0, &ret))
-			booke_wdt_period = ret;
-	}
-
-	return 0;
-}
-early_param("wdt_period", early_parse_wdt_period);
-#endif	/* CONFIG_BOOKE_WDT */
-
 void ppc_printk_progress(char *s, unsigned short hex)
 {
 	pr_info("%s\n", s);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index fbe24377eda..ee082d77117 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -36,6 +36,7 @@
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
 #include <linux/hugetlb.h>
+#include <linux/memory.h>
 
 #include <asm/io.h>
 #include <asm/kdump.h>
@@ -341,7 +342,7 @@ void smp_release_cpus(void)
 
 	ptr  = (unsigned long *)((unsigned long)&__secondary_hold_spinloop
 			- PHYSICAL_START);
-	*ptr = __pa(generic_secondary_smp_init);
+	*ptr = ppc_function_entry(generic_secondary_smp_init);
 
 	/* And wait a bit for them to catch up */
 	for (i = 0; i < 100000; i++) {
@@ -780,6 +781,15 @@ void __init setup_per_cpu_areas(void)
 }
 #endif
 
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+unsigned long memory_block_size_bytes(void)
+{
+	if (ppc_md.memory_block_size)
+		return ppc_md.memory_block_size();
+
+	return MIN_MEMORY_BLOCK_SIZE;
+}
+#endif
 
 #if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
 struct ppc_pci_io ppc_pci_io;
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 8fc4177ed65..1c794cef288 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -134,7 +134,7 @@ static int do_signal(struct pt_regs *regs)
 	 */
 	if (current->thread.hw_brk.address &&
 		current->thread.hw_brk.type)
-		set_breakpoint(&current->thread.hw_brk);
+		__set_breakpoint(&current->thread.hw_brk);
 #endif
 	/* Re-enable the breakpoints for the signal stack */
 	thread_change_pc(current, regs);
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 4e47db686b5..1bc5a1755ed 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -54,7 +54,6 @@
 
 #include "signal.h"
 
-#undef DEBUG_SIG
 
 #ifdef CONFIG_PPC64
 #define sys_rt_sigreturn	compat_sys_rt_sigreturn
@@ -1063,10 +1062,6 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka,
 	return 1;
 
 badframe:
-#ifdef DEBUG_SIG
-	printk("badframe in handle_rt_signal, regs=%p frame=%p newsp=%lx\n",
-	       regs, frame, newsp);
-#endif
 	if (show_unhandled_signals)
 		printk_ratelimited(KERN_INFO
 				   "%s[%d]: bad frame in handle_rt_signal32: "
@@ -1484,10 +1479,6 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 	return 1;
 
 badframe:
-#ifdef DEBUG_SIG
-	printk("badframe in handle_signal, regs=%p frame=%p newsp=%lx\n",
-	       regs, frame, newsp);
-#endif
 	if (show_unhandled_signals)
 		printk_ratelimited(KERN_INFO
 				   "%s[%d]: bad frame in handle_signal32: "
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index d501dc4dc3e..97c1e4b683f 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -38,7 +38,6 @@
 
 #include "signal.h"
 
-#define DEBUG_SIG 0
 
 #define GP_REGS_SIZE	min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
 #define FP_REGS_SIZE	sizeof(elf_fpregset_t)
@@ -700,10 +699,6 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 	return 0;
 
 badframe:
-#if DEBUG_SIG
-	printk("badframe in sys_rt_sigreturn, regs=%p uc=%p &uc->uc_mcontext=%p\n",
-	       regs, uc, &uc->uc_mcontext);
-#endif
 	if (show_unhandled_signals)
 		printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32,
 				   current->comm, current->pid, "rt_sigreturn",
@@ -809,10 +804,6 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info,
 	return 1;
 
 badframe:
-#if DEBUG_SIG
-	printk("badframe in setup_rt_frame, regs=%p frame=%p newsp=%lx\n",
-	       regs, frame, newsp);
-#endif
 	if (show_unhandled_signals)
 		printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32,
 				   current->comm, current->pid, "setup_rt_frame",
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 10ffffef041..1007fb802e6 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -36,6 +36,7 @@
 #include <linux/atomic.h>
 #include <asm/irq.h>
 #include <asm/hw_irq.h>
+#include <asm/kvm_ppc.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/prom.h>
@@ -390,6 +391,7 @@ void smp_prepare_boot_cpu(void)
 #ifdef CONFIG_PPC64
 	paca[boot_cpuid].__current = current;
 #endif
+	set_numa_node(numa_cpu_lookup_table[boot_cpuid]);
 	current_set[boot_cpuid] = task_thread_info(current);
 }
 
@@ -457,38 +459,9 @@ int generic_check_cpu_restart(unsigned int cpu)
 	return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
 }
 
-static atomic_t secondary_inhibit_count;
-
-/*
- * Don't allow secondary CPU threads to come online
- */
-void inhibit_secondary_onlining(void)
+static bool secondaries_inhibited(void)
 {
-	/*
-	 * This makes secondary_inhibit_count stable during cpu
-	 * online/offline operations.
-	 */
-	get_online_cpus();
-
-	atomic_inc(&secondary_inhibit_count);
-	put_online_cpus();
-}
-EXPORT_SYMBOL_GPL(inhibit_secondary_onlining);
-
-/*
- * Allow secondary CPU threads to come online again
- */
-void uninhibit_secondary_onlining(void)
-{
-	get_online_cpus();
-	atomic_dec(&secondary_inhibit_count);
-	put_online_cpus();
-}
-EXPORT_SYMBOL_GPL(uninhibit_secondary_onlining);
-
-static int secondaries_inhibited(void)
-{
-	return atomic_read(&secondary_inhibit_count);
+	return kvm_hv_mode_active();
 }
 
 #else /* HOTPLUG_CPU */
@@ -517,7 +490,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	 * Don't allow secondary threads to come online if inhibited
 	 */
 	if (threads_per_core > 1 && secondaries_inhibited() &&
-	    cpu % threads_per_core != 0)
+	    cpu_thread_in_subcore(cpu))
 		return -EBUSY;
 
 	if (smp_ops == NULL ||
@@ -750,6 +723,12 @@ void start_secondary(void *unused)
 	}
 	traverse_core_siblings(cpu, true);
 
+	/*
+	 * numa_node_id() works after this.
+	 */
+	set_numa_node(numa_cpu_lookup_table[cpu]);
+	set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu]));
+
 	smp_wmb();
 	notify_cpu_starting(cpu);
 	set_cpu_online(cpu, true);
@@ -768,9 +747,9 @@ int setup_profiling_timer(unsigned int multiplier)
 
 #ifdef CONFIG_SCHED_SMT
 /* cpumask of CPUs with asymetric SMT dependancy */
-static const int powerpc_smt_flags(void)
+static int powerpc_smt_flags(void)
 {
-	int flags = SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES;
+	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
 
 	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
 		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index d90d4b7810d..67fd2fd2620 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -404,7 +404,7 @@ void ppc_enable_pmcs(void)
 }
 EXPORT_SYMBOL(ppc_enable_pmcs);
 
-#define __SYSFS_SPRSETUP(NAME, ADDRESS, EXTRA) \
+#define __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, EXTRA) \
 static void read_##NAME(void *val) \
 { \
 	*(unsigned long *)val = mfspr(ADDRESS);	\
@@ -413,7 +413,9 @@ static void write_##NAME(void *val) \
 { \
 	EXTRA; \
 	mtspr(ADDRESS, *(unsigned long *)val);	\
-} \
+}
+
+#define __SYSFS_SPRSETUP_SHOW_STORE(NAME) \
 static ssize_t show_##NAME(struct device *dev, \
 			struct device_attribute *attr, \
 			char *buf) \
@@ -436,10 +438,15 @@ static ssize_t __used \
 	return count; \
 }
 
-#define SYSFS_PMCSETUP(NAME, ADDRESS)	\
-	__SYSFS_SPRSETUP(NAME, ADDRESS, ppc_enable_pmcs())
-#define SYSFS_SPRSETUP(NAME, ADDRESS)	\
-	__SYSFS_SPRSETUP(NAME, ADDRESS, )
+#define SYSFS_PMCSETUP(NAME, ADDRESS) \
+	__SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ppc_enable_pmcs()) \
+	__SYSFS_SPRSETUP_SHOW_STORE(NAME)
+#define SYSFS_SPRSETUP(NAME, ADDRESS) \
+	__SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ) \
+	__SYSFS_SPRSETUP_SHOW_STORE(NAME)
+
+#define SYSFS_SPRSETUP_SHOW_STORE(NAME) \
+	__SYSFS_SPRSETUP_SHOW_STORE(NAME)
 
 /* Let's define all possible registers, we'll only hook up the ones
  * that are implemented on the current processor
@@ -477,7 +484,6 @@ SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
 SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
 SYSFS_SPRSETUP(purr, SPRN_PURR);
 SYSFS_SPRSETUP(spurr, SPRN_SPURR);
-SYSFS_SPRSETUP(dscr, SPRN_DSCR);
 SYSFS_SPRSETUP(pir, SPRN_PIR);
 
 /*
@@ -487,12 +493,27 @@ SYSFS_SPRSETUP(pir, SPRN_PIR);
 */
 static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
 static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
-static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
 static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
 static DEVICE_ATTR(pir, 0400, show_pir, NULL);
 
-unsigned long dscr_default = 0;
-EXPORT_SYMBOL(dscr_default);
+static unsigned long dscr_default;
+
+static void read_dscr(void *val)
+{
+	*(unsigned long *)val = get_paca()->dscr_default;
+}
+
+static void write_dscr(void *val)
+{
+	get_paca()->dscr_default = *(unsigned long *)val;
+	if (!current->thread.dscr_inherit) {
+		current->thread.dscr = *(unsigned long *)val;
+		mtspr(SPRN_DSCR, *(unsigned long *)val);
+	}
+}
+
+SYSFS_SPRSETUP_SHOW_STORE(dscr);
+static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
 
 static void add_write_permission_dev_attr(struct device_attribute *attr)
 {
@@ -505,14 +526,6 @@ static ssize_t show_dscr_default(struct device *dev,
 	return sprintf(buf, "%lx\n", dscr_default);
 }
 
-static void update_dscr(void *dummy)
-{
-	if (!current->thread.dscr_inherit) {
-		current->thread.dscr = dscr_default;
-		mtspr(SPRN_DSCR, dscr_default);
-	}
-}
-
 static ssize_t __used store_dscr_default(struct device *dev,
 		struct device_attribute *attr, const char *buf,
 		size_t count)
@@ -525,7 +538,7 @@ static ssize_t __used store_dscr_default(struct device *dev,
 		return -EINVAL;
 	dscr_default = val;
 
-	on_each_cpu(update_dscr, NULL, 1);
+	on_each_cpu(write_dscr, &val, 1);
 
 	return count;
 }
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index 93219c34af3..895c50ca943 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -17,12 +17,12 @@
 #include <asm/ppc_asm.h>
 
 #ifdef CONFIG_PPC64
-#define SYSCALL(func)		.llong	.sys_##func,.sys_##func
-#define COMPAT_SYS(func)	.llong	.sys_##func,.compat_sys_##func
-#define PPC_SYS(func)		.llong	.ppc_##func,.ppc_##func
-#define OLDSYS(func)		.llong	.sys_ni_syscall,.sys_ni_syscall
-#define SYS32ONLY(func)		.llong	.sys_ni_syscall,.compat_sys_##func
-#define SYSX(f, f3264, f32)	.llong	.f,.f3264
+#define SYSCALL(func)		.llong	DOTSYM(sys_##func),DOTSYM(sys_##func)
+#define COMPAT_SYS(func)	.llong	DOTSYM(sys_##func),DOTSYM(compat_sys_##func)
+#define PPC_SYS(func)		.llong	DOTSYM(ppc_##func),DOTSYM(ppc_##func)
+#define OLDSYS(func)		.llong	DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall)
+#define SYS32ONLY(func)		.llong	DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func)
+#define SYSX(f, f3264, f32)	.llong	DOTSYM(f),DOTSYM(f3264)
 #else
 #define SYSCALL(func)		.long	sys_##func
 #define COMPAT_SYS(func)	.long	sys_##func
@@ -36,6 +36,8 @@
 #define PPC_SYS_SPU(func)	PPC_SYS(func)
 #define SYSX_SPU(f, f3264, f32)	SYSX(f, f3264, f32)
 
+.section .rodata,"a"
+
 #ifdef CONFIG_PPC64
 #define sys_sigpending	sys_ni_syscall
 #define sys_old_getrlimit sys_ni_syscall
@@ -43,5 +45,7 @@
 	.p2align	3
 #endif
 
-_GLOBAL(sys_call_table)
+.globl sys_call_table
+sys_call_table:
+
 #include <asm/systbl.h>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 7e711bdcc6d..9fff9cdcc51 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -551,7 +551,7 @@ void timer_interrupt(struct pt_regs * regs)
 	may_hard_irq_enable();
 
 
-#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
+#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
 		do_IRQ(regs);
 #endif
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 03567c05950..2a324f4cb1b 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -10,6 +10,7 @@
 #include <asm/ppc-opcode.h>
 #include <asm/ptrace.h>
 #include <asm/reg.h>
+#include <asm/bug.h>
 
 #ifdef CONFIG_VSX
 /* See fpu.S, this is borrowed from there */
@@ -41,7 +42,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);		\
 /* Stack frame offsets for local variables. */
 #define TM_FRAME_L0	TM_FRAME_SIZE-16
 #define TM_FRAME_L1	TM_FRAME_SIZE-8
-#define STACK_PARAM(x)	(48+((x)*8))
 
 
 /* In order to access the TM SPRs, TM must be enabled.  So, do so: */
@@ -78,12 +78,6 @@ _GLOBAL(tm_abort)
 	TABORT(R3)
 	blr
 
-	.section	".toc","aw"
-DSCR_DEFAULT:
-	.tc dscr_default[TC],dscr_default
-
-	.section	".text"
-
 /* void tm_reclaim(struct thread_struct *thread,
  *                 unsigned long orig_msr,
  *		   uint8_t cause)
@@ -108,12 +102,12 @@ _GLOBAL(tm_reclaim)
 	mflr	r0
 	stw	r6, 8(r1)
 	std	r0, 16(r1)
-	std	r2, 40(r1)
+	std	r2, STK_GOT(r1)
 	stdu	r1, -TM_FRAME_SIZE(r1)
 
 	/* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD]. */
 
-	std	r3, STACK_PARAM(0)(r1)
+	std	r3, STK_PARAM(R3)(r1)
 	SAVE_NVGPRS(r1)
 
 	/* We need to setup MSR for VSX register save instructions.  Here we
@@ -175,6 +169,13 @@ dont_backup_vec:
 	stfd    fr0,FPSTATE_FPSCR(r7)
 
 dont_backup_fp:
+	/* Do sanity check on MSR to make sure we are suspended */
+	li	r7, (MSR_TS_S)@higher
+	srdi	r6, r14, 32
+	and	r6, r6, r7
+1:	tdeqi   r6, 0
+	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
+
 	/* The moment we treclaim, ALL of our GPRs will switch
 	 * to user register state.  (FPRs, CCR etc. also!)
 	 * Use an sprg and a tm_scratch in the PACA to shuffle.
@@ -202,7 +203,7 @@ dont_backup_fp:
 	/* Now get some more GPRS free */
 	std	r7, GPR7(r1)			/* Temporary stash */
 	std	r12, GPR12(r1)			/* ''   ''    ''   */
-	ld	r12, STACK_PARAM(0)(r1)		/* Param 0, thread_struct * */
+	ld	r12, STK_PARAM(R3)(r1)		/* Param 0, thread_struct * */
 
 	std	r11, THREAD_TM_PPR(r12)		/* Store PPR and free r11 */
 
@@ -289,11 +290,10 @@ dont_backup_fp:
 	ld	r0, 16(r1)
 	mtcr	r4
 	mtlr	r0
-	ld	r2, 40(r1)
+	ld	r2, STK_GOT(r1)
 
-	/* Load system default DSCR */
-	ld	r4, DSCR_DEFAULT@toc(r2)
-	ld	r0, 0(r4)
+	/* Load CPU's default DSCR */
+	ld	r0, PACA_DSCR(r13)
 	mtspr	SPRN_DSCR, r0
 
 	blr
@@ -312,7 +312,7 @@ _GLOBAL(__tm_recheckpoint)
 	mflr	r0
 	stw	r5, 8(r1)
 	std	r0, 16(r1)
-	std	r2, 40(r1)
+	std	r2, STK_GOT(r1)
 	stdu	r1, -TM_FRAME_SIZE(r1)
 
 	/* We've a struct pt_regs at [r1+STACK_FRAME_OVERHEAD].
@@ -320,8 +320,6 @@ _GLOBAL(__tm_recheckpoint)
 	 */
 	SAVE_NVGPRS(r1)
 
-	std	r1, PACAR1(r13)
-
 	/* Load complete register state from ts_ckpt* registers */
 
 	addi	r7, r3, PT_CKPT_REGS		/* Thread's ckpt_regs */
@@ -385,12 +383,10 @@ restore_gprs:
 	/* ******************** CR,LR,CCR,MSR ********** */
 	ld	r4, _CTR(r7)
 	ld	r5, _LINK(r7)
-	ld	r6, _CCR(r7)
 	ld	r8, _XER(r7)
 
 	mtctr	r4
 	mtlr	r5
-	mtcr	r6
 	mtxer	r8
 
 	/* ******************** TAR ******************** */
@@ -406,7 +402,8 @@ restore_gprs:
 	li	r4, 0
 	mtmsrd	r4, 1
 
-	REST_4GPRS(0, r7)			/* GPR0-3 */
+	REST_GPR(0, r7)				/* GPR0 */
+	REST_2GPRS(2, r7)			/* GPR2-3 */
 	REST_GPR(4, r7)				/* GPR4 */
 	REST_4GPRS(8, r7)			/* GPR8-11 */
 	REST_2GPRS(12, r7)			/* GPR12-13 */
@@ -418,6 +415,31 @@ restore_gprs:
 	mtspr	SPRN_DSCR, r5
 	mtspr	SPRN_PPR, r6
 
+	/* Do final sanity check on TEXASR to make sure FS is set.  Do this
+	 * here before we load up the userspace r1 so any bugs we hit will get
+	 * a call chain */
+	mfspr	r5, SPRN_TEXASR
+	srdi	r5, r5, 16
+	li	r6, (TEXASR_FS)@h
+	and	r6, r6, r5
+1:	tdeqi	r6, 0
+	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
+
+	/* Do final sanity check on MSR to make sure we are not transactional
+	 * or suspended
+	 */
+	mfmsr   r6
+	li	r5, (MSR_TS_MASK)@higher
+	srdi	r6, r6, 32
+	and	r6, r6, r5
+1:	tdnei   r6, 0
+	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0
+
+	/* Restore CR */
+	ld	r6, _CCR(r7)
+	mtcr    r6
+
+	REST_GPR(1, r7)				/* GPR1 */
 	REST_GPR(5, r7)				/* GPR5-7 */
 	REST_GPR(6, r7)
 	ld	r7, GPR7(r7)
@@ -448,11 +470,10 @@ restore_gprs:
 	ld	r0, 16(r1)
 	mtcr	r4
 	mtlr	r0
-	ld	r2, 40(r1)
+	ld	r2, STK_GOT(r1)
 
-	/* Load system default DSCR */
-	ld	r4, DSCR_DEFAULT@toc(r2)
-	ld	r0, 0(r4)
+	/* Load CPU's default DSCR */
+	ld	r0, PACA_DSCR(r13)
 	mtspr	SPRN_DSCR, r0
 
 	blr
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 1bd7ca298fa..239f1cde3ff 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -295,6 +295,8 @@ long machine_check_early(struct pt_regs *regs)
 {
 	long handled = 0;
 
+	__get_cpu_var(irq_stat).mce_exceptions++;
+
 	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
 		handled = cur_cpu_spec->machine_check_early(regs);
 	return handled;
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index a15837519dc..b7aa07279a6 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -62,8 +62,6 @@ void __init udbg_early_init(void)
 	udbg_init_cpm();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_USBGECKO)
 	udbg_init_usbgecko();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_WSP)
-	udbg_init_wsp();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_MEMCONS)
 	/* In memory console */
 	udbg_init_memcons();
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 75702e207b2..6e7c4923b5e 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -296,14 +296,3 @@ void __init udbg_init_40x_realmode(void)
 }
 
 #endif /* CONFIG_PPC_EARLY_DEBUG_40x */
-
-
-#ifdef CONFIG_PPC_EARLY_DEBUG_WSP
-
-void __init udbg_init_wsp(void)
-{
-	udbg_uart_init_mmio((void *)WSP_UART_VIRT, 1);
-	udbg_uart_setup(57600, 50000000);
-}
-
-#endif /* CONFIG_PPC_EARLY_DEBUG_WSP */
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 80561074078..68468d695f1 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1562,7 +1562,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 				goto out;
 			}
 			if (!rma_setup && is_vrma_hpte(v)) {
-				unsigned long psize = hpte_page_size(v, r);
+				unsigned long psize = hpte_base_page_size(v, r);
 				unsigned long senc = slb_pgsize_encoding(psize);
 				unsigned long lpcr;
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index aba05bbb3e7..7a12edbb61e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1236,7 +1236,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	int core;
 	struct kvmppc_vcore *vcore;
 
-	core = id / threads_per_core;
+	core = id / threads_per_subcore;
 	if (core >= KVM_MAX_VCORES)
 		goto out;
 
@@ -1286,7 +1286,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 			init_waitqueue_head(&vcore->wq);
 			vcore->preempt_tb = TB_NIL;
 			vcore->lpcr = kvm->arch.lpcr;
-			vcore->first_vcpuid = core * threads_per_core;
+			vcore->first_vcpuid = core * threads_per_subcore;
 			vcore->kvm = kvm;
 		}
 		kvm->arch.vcores[core] = vcore;
@@ -1476,16 +1476,19 @@ static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
 static int on_primary_thread(void)
 {
 	int cpu = smp_processor_id();
-	int thr = cpu_thread_in_core(cpu);
+	int thr;
 
-	if (thr)
+	/* Are we on a primary subcore? */
+	if (cpu_thread_in_subcore(cpu))
 		return 0;
-	while (++thr < threads_per_core)
+
+	thr = 0;
+	while (++thr < threads_per_subcore)
 		if (cpu_online(cpu + thr))
 			return 0;
 
 	/* Grab all hw threads so they can't go into the kernel */
-	for (thr = 1; thr < threads_per_core; ++thr) {
+	for (thr = 1; thr < threads_per_subcore; ++thr) {
 		if (kvmppc_grab_hwthread(cpu + thr)) {
 			/* Couldn't grab one; let the others go */
 			do {
@@ -1544,15 +1547,18 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	}
 
 	/*
-	 * Make sure we are running on thread 0, and that
-	 * secondary threads are offline.
+	 * Make sure we are running on primary threads, and that secondary
+	 * threads are offline.  Also check if the number of threads in this
+	 * guest are greater than the current system threads per guest.
 	 */
-	if (threads_per_core > 1 && !on_primary_thread()) {
+	if ((threads_per_core > 1) &&
+	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
 		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
 			vcpu->arch.ret = -EBUSY;
 		goto out;
 	}
 
+
 	vc->pcpu = smp_processor_id();
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		kvmppc_start_thread(vcpu);
@@ -1580,7 +1586,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	/* wait for secondary threads to finish writing their state to memory */
 	if (vc->nap_count < vc->n_woken)
 		kvmppc_wait_for_nap(vc);
-	for (i = 0; i < threads_per_core; ++i)
+	for (i = 0; i < threads_per_subcore; ++i)
 		kvmppc_release_hwthread(vc->pcpu + i);
 	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
 	vc->vcore_state = VCORE_EXITING;
@@ -2305,10 +2311,10 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 	spin_lock_init(&kvm->arch.slot_phys_lock);
 
 	/*
-	 * Don't allow secondary CPU threads to come online
-	 * while any KVM VMs exist.
+	 * Track that we now have a HV mode VM active. This blocks secondary
+	 * CPU threads from coming online.
 	 */
-	inhibit_secondary_onlining();
+	kvm_hv_vm_activated();
 
 	return 0;
 }
@@ -2324,7 +2330,7 @@ static void kvmppc_free_vcores(struct kvm *kvm)
 
 static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 {
-	uninhibit_secondary_onlining();
+	kvm_hv_vm_deactivated();
 
 	kvmppc_free_vcores(kvm);
 	if (kvm->arch.rma) {
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 8cd0daebb82..7cde8a66520 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/cpu.h>
 #include <linux/kvm_host.h>
 #include <linux/preempt.h>
 #include <linux/export.h>
@@ -181,3 +182,33 @@ void __init kvm_cma_reserve(void)
 		kvm_cma_declare_contiguous(selected_size, align_size);
 	}
 }
+
+/*
+ * When running HV mode KVM we need to block certain operations while KVM VMs
+ * exist in the system. We use a counter of VMs to track this.
+ *
+ * One of the operations we need to block is onlining of secondaries, so we
+ * protect hv_vm_count with get/put_online_cpus().
+ */
+static atomic_t hv_vm_count;
+
+void kvm_hv_vm_activated(void)
+{
+	get_online_cpus();
+	atomic_inc(&hv_vm_count);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(kvm_hv_vm_activated);
+
+void kvm_hv_vm_deactivated(void)
+{
+	get_online_cpus();
+	atomic_dec(&hv_vm_count);
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(kvm_hv_vm_deactivated);
+
+bool kvm_hv_mode_active(void)
+{
+	return atomic_read(&hv_vm_count) != 0;
+}
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index e18e3cfc32d..731be7478b2 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -127,11 +127,6 @@ BEGIN_FTR_SECTION
 	stw	r10, HSTATE_PMC + 24(r13)
 	stw	r11, HSTATE_PMC + 28(r13)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
-BEGIN_FTR_SECTION
-	mfspr	r9, SPRN_SIER
-	std	r8, HSTATE_MMCR + 40(r13)
-	std	r9, HSTATE_MMCR + 48(r13)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 31:
 
 	/*
@@ -171,7 +166,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 #endif /* CONFIG_SMP */
 
 	/* Jump to partition switch code */
-	bl	.kvmppc_hv_entry_trampoline
+	bl	kvmppc_hv_entry_trampoline
 	nop
 
 /*
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index 768a9f977c0..3a5c568b1e8 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -113,10 +113,8 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 	 * We assume that if the condition is recovered then linux host
 	 * will have generated an error log event that we will pick
 	 * up and log later.
-	 * Don't release mce event now. In case if condition is not
-	 * recovered we do guest exit and go back to linux host machine
-	 * check handler. Hence we need make sure that current mce event
-	 * is available for linux host to consume.
+	 * Don't release mce event now. We will queue up the event so that
+	 * we can log the MCE event info on host console.
 	 */
 	if (!get_mce_event(&mce_evt, MCE_EVENT_DONTRELEASE))
 		goto out;
@@ -128,11 +126,12 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 
 out:
 	/*
-	 * If we have handled the error, then release the mce event because
-	 * we will be delivering machine check to guest.
+	 * We are now going enter guest either through machine check
+	 * interrupt (for unhandled errors) or will continue from
+	 * current HSRR0 (for handled errors) in guest. Hence
+	 * queue up the event so that we can log it from host console later.
 	 */
-	if (handled)
-		release_mce_event();
+	machine_check_queue_event();
 
 	return handled;
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6e6224318c3..5a24d3c2b6b 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -814,13 +814,10 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 			r = hpte[i+1];
 
 			/*
-			 * Check the HPTE again, including large page size
-			 * Since we don't currently allow any MPSS (mixed
-			 * page-size segment) page sizes, it is sufficient
-			 * to check against the actual page size.
+			 * Check the HPTE again, including base page size
 			 */
 			if ((v & valid) && (v & mask) == val &&
-			    hpte_page_size(v, r) == (1ul << pshift))
+			    hpte_base_page_size(v, r) == (1ul << pshift))
 				/* Return with the HPTE still locked */
 				return (hash << 3) + (i >> 1);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 974793435a2..558a67df812 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -48,7 +48,7 @@
  *
  * LR = return address to continue at after eventually re-enabling MMU
  */
-_GLOBAL(kvmppc_hv_entry_trampoline)
+_GLOBAL_TOC(kvmppc_hv_entry_trampoline)
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
 	stdu	r1, -112(r1)
@@ -292,8 +292,7 @@ kvm_start_guest:
 	beq	kvm_no_guest
 
 	/* Set HSTATE_DSCR(r13) to something sensible */
-	LOAD_REG_ADDR(r6, dscr_default)
-	ld	r6, 0(r6)
+	ld	r6, PACA_DSCR(r13)
 	std	r6, HSTATE_DSCR(r13)
 
 	bl	kvmppc_hv_entry
@@ -1799,7 +1798,7 @@ kvmppc_hdsi:
 	/* Search the hash table. */
 	mr	r3, r9			/* vcpu pointer */
 	li	r7, 1			/* data fault */
-	bl	.kvmppc_hpte_hv_fault
+	bl	kvmppc_hpte_hv_fault
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	ld	r10, VCPU_PC(r9)
 	ld	r11, VCPU_MSR(r9)
@@ -1873,7 +1872,7 @@ kvmppc_hisi:
 	mr	r4, r10
 	mr	r6, r11
 	li	r7, 0			/* instruction fault */
-	bl	.kvmppc_hpte_hv_fault
+	bl	kvmppc_hpte_hv_fault
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	ld	r10, VCPU_PC(r9)
 	ld	r11, VCPU_MSR(r9)
@@ -1947,16 +1946,16 @@ hcall_real_fallback:
 	.globl	hcall_real_table
 hcall_real_table:
 	.long	0		/* 0 - unused */
-	.long	.kvmppc_h_remove - hcall_real_table
-	.long	.kvmppc_h_enter - hcall_real_table
-	.long	.kvmppc_h_read - hcall_real_table
+	.long	DOTSYM(kvmppc_h_remove) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_enter) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_read) - hcall_real_table
 	.long	0		/* 0x10 - H_CLEAR_MOD */
 	.long	0		/* 0x14 - H_CLEAR_REF */
-	.long	.kvmppc_h_protect - hcall_real_table
-	.long	.kvmppc_h_get_tce - hcall_real_table
-	.long	.kvmppc_h_put_tce - hcall_real_table
+	.long	DOTSYM(kvmppc_h_protect) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_get_tce) - hcall_real_table
+	.long	DOTSYM(kvmppc_h_put_tce) - hcall_real_table
 	.long	0		/* 0x24 - H_SET_SPRG0 */
-	.long	.kvmppc_h_set_dabr - hcall_real_table
+	.long	DOTSYM(kvmppc_h_set_dabr) - hcall_real_table
 	.long	0		/* 0x2c */
 	.long	0		/* 0x30 */
 	.long	0		/* 0x34 */
@@ -1972,11 +1971,11 @@ hcall_real_table:
 	.long	0		/* 0x5c */
 	.long	0		/* 0x60 */
 #ifdef CONFIG_KVM_XICS
-	.long	.kvmppc_rm_h_eoi - hcall_real_table
-	.long	.kvmppc_rm_h_cppr - hcall_real_table
-	.long	.kvmppc_rm_h_ipi - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table
 	.long	0		/* 0x70 - H_IPOLL */
-	.long	.kvmppc_rm_h_xirr - hcall_real_table
+	.long	DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table
 #else
 	.long	0		/* 0x64 - H_EOI */
 	.long	0		/* 0x68 - H_CPPR */
@@ -2010,7 +2009,7 @@ hcall_real_table:
 	.long	0		/* 0xd4 */
 	.long	0		/* 0xd8 */
 	.long	0		/* 0xdc */
-	.long	.kvmppc_h_cede - hcall_real_table
+	.long	DOTSYM(kvmppc_h_cede) - hcall_real_table
 	.long	0		/* 0xe4 */
 	.long	0		/* 0xe8 */
 	.long	0		/* 0xec */
@@ -2027,11 +2026,11 @@ hcall_real_table:
 	.long	0		/* 0x118 */
 	.long	0		/* 0x11c */
 	.long	0		/* 0x120 */
-	.long	.kvmppc_h_bulk_remove - hcall_real_table
+	.long	DOTSYM(kvmppc_h_bulk_remove) - hcall_real_table
 	.long	0		/* 0x128 */
 	.long	0		/* 0x12c */
 	.long	0		/* 0x130 */
-	.long	.kvmppc_h_set_xdabr - hcall_real_table
+	.long	DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
 hcall_real_table_end:
 
 ignore_hdec:
@@ -2256,17 +2255,30 @@ kvm_cede_exit:
 	/* Try to handle a machine check in real mode */
 machine_check_realmode:
 	mr	r3, r9		/* get vcpu pointer */
-	bl	.kvmppc_realmode_machine_check
+	bl	kvmppc_realmode_machine_check
 	nop
-	cmpdi	r3, 0		/* continue exiting from guest? */
+	cmpdi	r3, 0		/* Did we handle MCE ? */
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	li	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
-	beq	mc_cont
+	/*
+	 * Deliver unhandled/fatal (e.g. UE) MCE errors to guest through
+	 * machine check interrupt (set HSRR0 to 0x200). And for handled
+	 * errors (no-fatal), just go back to guest execution with current
+	 * HSRR0 instead of exiting guest. This new approach will inject
+	 * machine check to guest for fatal error causing guest to crash.
+	 *
+	 * The old code used to return to host for unhandled errors which
+	 * was causing guest to hang with soft lockups inside guest and
+	 * makes it difficult to recover guest instance.
+	 */
+	ld	r10, VCPU_PC(r9)
+	ld	r11, VCPU_MSR(r9)
+	bne	2f	/* Continue guest execution. */
 	/* If not, deliver a machine check.  SRR0/1 are already set */
 	li	r10, BOOK3S_INTERRUPT_MACHINE_CHECK
 	ld	r11, VCPU_MSR(r9)
 	bl	kvmppc_msr_interrupt
-	b	fast_interrupt_c_return
+2:	b	fast_interrupt_c_return
 
 /*
  * Check the reason we woke from nap, and take appropriate action.
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index e2c29e381dc..d044b8b7c69 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -25,7 +25,11 @@
 #include <asm/exception-64s.h>
 
 #if defined(CONFIG_PPC_BOOK3S_64)
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define FUNC(name) 		name
+#else
 #define FUNC(name) 		GLUE(.,name)
+#endif
 #define GET_SHADOW_VCPU(reg)    addi	reg, r13, PACA_SVCPU
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 9eec675220e..16c4d88ba27 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -36,7 +36,11 @@
 
 #if defined(CONFIG_PPC_BOOK3S_64)
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define FUNC(name) 		name
+#else
 #define FUNC(name) 		GLUE(.,name)
+#endif
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
@@ -146,7 +150,7 @@ kvmppc_handler_skip_ins:
  * On entry, r4 contains the guest shadow MSR
  * MSR.EE has to be 0 when calling this function
  */
-_GLOBAL(kvmppc_entry_trampoline)
+_GLOBAL_TOC(kvmppc_entry_trampoline)
 	mfmsr	r5
 	LOAD_REG_ADDR(r7, kvmppc_handler_trampoline_enter)
 	toreal(r7)
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index edb14ba992b..ef27fbd5d9c 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -23,20 +23,20 @@ static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq, server, priority;
 	int rc;
 
-	if (args->nargs != 3 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 3 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
-	server = args->args[1];
-	priority = args->args[2];
+	irq = be32_to_cpu(args->args[0]);
+	server = be32_to_cpu(args->args[1]);
+	priority = be32_to_cpu(args->args[2]);
 
 	rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -44,12 +44,12 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq, server, priority;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 3) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 3) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	server = priority = 0;
 	rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
@@ -58,10 +58,10 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
 		goto out;
 	}
 
-	args->rets[1] = server;
-	args->rets[2] = priority;
+	args->rets[1] = cpu_to_be32(server);
+	args->rets[2] = cpu_to_be32(priority);
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -69,18 +69,18 @@ static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	rc = kvmppc_xics_int_off(vcpu->kvm, irq);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 
 static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -88,18 +88,18 @@ static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
 	u32 irq;
 	int rc;
 
-	if (args->nargs != 1 || args->nret != 1) {
+	if (be32_to_cpu(args->nargs) != 1 || be32_to_cpu(args->nret) != 1) {
 		rc = -3;
 		goto out;
 	}
 
-	irq = args->args[0];
+	irq = be32_to_cpu(args->args[0]);
 
 	rc = kvmppc_xics_int_on(vcpu->kvm, irq);
 	if (rc)
 		rc = -3;
 out:
-	args->rets[0] = rc;
+	args->rets[0] = cpu_to_be32(rc);
 }
 #endif /* CONFIG_KVM_XICS */
 
@@ -205,32 +205,6 @@ int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp)
 	return rc;
 }
 
-static void kvmppc_rtas_swap_endian_in(struct rtas_args *args)
-{
-#ifdef __LITTLE_ENDIAN__
-	int i;
-
-	args->token = be32_to_cpu(args->token);
-	args->nargs = be32_to_cpu(args->nargs);
-	args->nret = be32_to_cpu(args->nret);
-	for (i = 0; i < args->nargs; i++)
-		args->args[i] = be32_to_cpu(args->args[i]);
-#endif
-}
-
-static void kvmppc_rtas_swap_endian_out(struct rtas_args *args)
-{
-#ifdef __LITTLE_ENDIAN__
-	int i;
-
-	for (i = 0; i < args->nret; i++)
-		args->args[i] = cpu_to_be32(args->args[i]);
-	args->token = cpu_to_be32(args->token);
-	args->nargs = cpu_to_be32(args->nargs);
-	args->nret = cpu_to_be32(args->nret);
-#endif
-}
-
 int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 {
 	struct rtas_token_definition *d;
@@ -249,8 +223,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	if (rc)
 		goto fail;
 
-	kvmppc_rtas_swap_endian_in(&args);
-
 	/*
 	 * args->rets is a pointer into args->args. Now that we've
 	 * copied args we need to fix it up to point into our copy,
@@ -258,13 +230,13 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 	 * value so we can restore it on the way out.
 	 */
 	orig_rets = args.rets;
-	args.rets = &args.args[args.nargs];
+	args.rets = &args.args[be32_to_cpu(args.nargs)];
 
 	mutex_lock(&vcpu->kvm->lock);
 
 	rc = -ENOENT;
 	list_for_each_entry(d, &vcpu->kvm->arch.rtas_tokens, list) {
-		if (d->token == args.token) {
+		if (d->token == be32_to_cpu(args.token)) {
 			d->handler->handler(vcpu, &args);
 			rc = 0;
 			break;
@@ -275,7 +247,6 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
 
 	if (rc == 0) {
 		args.rets = orig_rets;
-		kvmppc_rtas_swap_endian_out(&args);
 		rc = kvm_write_guest(vcpu->kvm, args_phys, &args, sizeof(args));
 		if (rc)
 			goto fail;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index dd2cc03f406..86903d3f5a0 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -473,7 +473,8 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		if (printk_ratelimit())
 			pr_err("%s: pte not present: gfn %lx, pfn %lx\n",
 				__func__, (long)gfn, pfn);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 	kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg);
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index bab20f41044..61c738ab128 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -426,7 +426,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_SMT:
 		if (hv_enabled)
-			r = threads_per_core;
+			r = threads_per_subcore;
 		else
 			r = 0;
 		break;
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 95a20e17dbf..59fa2de9546 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -23,9 +23,7 @@ obj-y			+= checksum_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_PPC64)	+= checksum_wrappers_64.o
 endif
 
-ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),)
 obj-$(CONFIG_PPC64)		+= memcpy_power7.o memcpy_64.o 
-endif
 
 obj-$(CONFIG_PPC_EMULATE_SSTEP)	+= sstep.o ldstfp.o
 
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
index 9f9434a8526..a3c4dc4defd 100644
--- a/arch/powerpc/lib/copypage_64.S
+++ b/arch/powerpc/lib/copypage_64.S
@@ -16,11 +16,11 @@ PPC64_CACHES:
         .tc             ppc64_caches[TC],ppc64_caches
         .section        ".text"
 
-_GLOBAL(copy_page)
+_GLOBAL_TOC(copy_page)
 BEGIN_FTR_SECTION
 	lis	r5,PAGE_SIZE@h
 FTR_SECTION_ELSE
-	b	.copypage_power7
+	b	copypage_power7
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
 	ori	r5,r5,PAGE_SIZE@l
 BEGIN_FTR_SECTION
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
index 395c594722a..d7dafb3777a 100644
--- a/arch/powerpc/lib/copypage_power7.S
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -56,15 +56,15 @@ _GLOBAL(copypage_power7)
 
 #ifdef CONFIG_ALTIVEC
 	mflr	r0
-	std	r3,48(r1)
-	std	r4,56(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	.enter_vmx_copy
+	bl	enter_vmx_copy
 	cmpwi	r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STACKFRAMESIZE+48(r1)
-	ld	r4,STACKFRAMESIZE+56(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
 	mtlr	r0
 
 	li	r0,(PAGE_SIZE/128)
@@ -103,7 +103,7 @@ _GLOBAL(copypage_power7)
 	addi	r3,r3,128
 	bdnz	1b
 
-	b	.exit_vmx_copy		/* tail call optimise */
+	b	exit_vmx_copy		/* tail call optimise */
 
 #else
 	li	r0,(PAGE_SIZE/128)
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 596a285c075..0860ee46013 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -18,7 +18,7 @@
 #endif
 
 	.align	7
-_GLOBAL(__copy_tofrom_user)
+_GLOBAL_TOC(__copy_tofrom_user)
 BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index e8e9c36dc78..c46c876ac96 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -66,7 +66,7 @@
 	ld	r15,STK_REG(R15)(r1)
 	ld	r14,STK_REG(R14)(r1)
 .Ldo_err3:
-	bl	.exit_vmx_usercopy
+	bl	exit_vmx_usercopy
 	ld	r0,STACKFRAMESIZE+16(r1)
 	mtlr	r0
 	b	.Lexit
@@ -85,9 +85,9 @@
 .Lexit:
 	addi	r1,r1,STACKFRAMESIZE
 .Ldo_err1:
-	ld	r3,48(r1)
-	ld	r4,56(r1)
-	ld	r5,64(r1)
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	ld	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	ld	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 	b	__copy_tofrom_user_base
 
 
@@ -96,18 +96,18 @@ _GLOBAL(__copy_tofrom_user_power7)
 	cmpldi	r5,16
 	cmpldi	cr1,r5,4096
 
-	std	r3,48(r1)
-	std	r4,56(r1)
-	std	r5,64(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 
 	blt	.Lshort_copy
 	bgt	cr1,.Lvmx_copy
 #else
 	cmpldi	r5,16
 
-	std	r3,48(r1)
-	std	r4,56(r1)
-	std	r5,64(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 
 	blt	.Lshort_copy
 #endif
@@ -295,12 +295,12 @@ err1;	stb	r0,0(r3)
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	.enter_vmx_usercopy
+	bl	enter_vmx_usercopy
 	cmpwi	cr1,r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STACKFRAMESIZE+48(r1)
-	ld	r4,STACKFRAMESIZE+56(r1)
-	ld	r5,STACKFRAMESIZE+64(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
+	ld	r5,STK_REG(R29)(r1)
 	mtlr	r0
 
 	/*
@@ -514,7 +514,7 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	.exit_vmx_usercopy	/* tail call optimise */
+	b	exit_vmx_usercopy	/* tail call optimise */
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -717,5 +717,5 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	.exit_vmx_usercopy	/* tail call optimise */
+	b	exit_vmx_usercopy	/* tail call optimise */
 #endif /* CONFiG_ALTIVEC */
diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S
index 9b96ff2ecd4..19e66001a4f 100644
--- a/arch/powerpc/lib/hweight_64.S
+++ b/arch/powerpc/lib/hweight_64.S
@@ -24,7 +24,7 @@
 
 _GLOBAL(__arch_hweight8)
 BEGIN_FTR_SECTION
-	b .__sw_hweight8
+	b __sw_hweight8
 	nop
 	nop
 FTR_SECTION_ELSE
@@ -35,7 +35,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
 
 _GLOBAL(__arch_hweight16)
 BEGIN_FTR_SECTION
-	b .__sw_hweight16
+	b __sw_hweight16
 	nop
 	nop
 	nop
@@ -57,7 +57,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
 
 _GLOBAL(__arch_hweight32)
 BEGIN_FTR_SECTION
-	b .__sw_hweight32
+	b __sw_hweight32
 	nop
 	nop
 	nop
@@ -82,7 +82,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
 
 _GLOBAL(__arch_hweight64)
 BEGIN_FTR_SECTION
-	b .__sw_hweight64
+	b __sw_hweight64
 	nop
 	nop
 	nop
diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S
index f4fcb0bc656..43435c6892f 100644
--- a/arch/powerpc/lib/mem_64.S
+++ b/arch/powerpc/lib/mem_64.S
@@ -77,10 +77,10 @@ _GLOBAL(memset)
 	stb	r4,0(r6)
 	blr
 
-_GLOBAL(memmove)
+_GLOBAL_TOC(memmove)
 	cmplw	0,r3,r4
-	bgt	.backwards_memcpy
-	b	.memcpy
+	bgt	backwards_memcpy
+	b	memcpy
 
 _GLOBAL(backwards_memcpy)
 	rlwinm.	r7,r5,32-3,3,31		/* r0 = r5 >> 3 */
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 72ad055168a..32a06ec395d 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -10,14 +10,29 @@
 #include <asm/ppc_asm.h>
 
 	.align	7
-_GLOBAL(memcpy)
+_GLOBAL_TOC(memcpy)
 BEGIN_FTR_SECTION
-	std	r3,48(r1)	/* save destination pointer for return value */
+#ifdef __LITTLE_ENDIAN__
+	cmpdi	cr7,r5,0
+#else
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* save destination pointer for return value */
+#endif
 FTR_SECTION_ELSE
 #ifndef SELFTEST
 	b	memcpy_power7
 #endif
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
+#ifdef __LITTLE_ENDIAN__
+	/* dumb little-endian memcpy that will get replaced at runtime */
+	addi r9,r3,-1
+	addi r4,r4,-1
+	beqlr cr7
+	mtctr r5
+1:	lbzu r10,1(r4)
+	stbu r10,1(r9)
+	bdnz 1b
+	blr
+#else
 	PPC_MTOCRF(0x01,r5)
 	cmpldi	cr1,r5,16
 	neg	r6,r3		# LS 3 bits = # bytes to 8-byte dest bdry
@@ -73,7 +88,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 2:	bf	cr7*4+3,3f
 	lbz	r9,8(r4)
 	stb	r9,0(r3)
-3:	ld	r3,48(r1)	/* return dest pointer */
+3:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* return dest pointer */
 	blr
 
 .Lsrc_unaligned:
@@ -156,7 +171,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 2:	bf	cr7*4+3,3f
 	rotldi	r9,r9,8
 	stb	r9,0(r3)
-3:	ld	r3,48(r1)	/* return dest pointer */
+3:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* return dest pointer */
 	blr
 
 .Ldst_unaligned:
@@ -201,5 +216,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 3:	bf	cr7*4+3,4f
 	lbz	r0,0(r4)
 	stb	r0,0(r3)
-4:	ld	r3,48(r1)	/* return dest pointer */
+4:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)	/* return dest pointer */
 	blr
+#endif
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index e4177dbea6b..2ff5c142f87 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -33,14 +33,14 @@ _GLOBAL(memcpy_power7)
 	cmpldi	r5,16
 	cmpldi	cr1,r5,4096
 
-	std	r3,48(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 
 	blt	.Lshort_copy
 	bgt	cr1,.Lvmx_copy
 #else
 	cmpldi	r5,16
 
-	std	r3,48(r1)
+	std	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 
 	blt	.Lshort_copy
 #endif
@@ -216,7 +216,7 @@ _GLOBAL(memcpy_power7)
 	lbz	r0,0(r4)
 	stb	r0,0(r3)
 
-15:	ld	r3,48(r1)
+15:	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
 	blr
 
 .Lunwind_stack_nonvmx_copy:
@@ -226,16 +226,16 @@ _GLOBAL(memcpy_power7)
 #ifdef CONFIG_ALTIVEC
 .Lvmx_copy:
 	mflr	r0
-	std	r4,56(r1)
-	std	r5,64(r1)
+	std	r4,-STACKFRAMESIZE+STK_REG(R30)(r1)
+	std	r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	.enter_vmx_copy
+	bl	enter_vmx_copy
 	cmpwi	cr1,r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
-	ld	r3,STACKFRAMESIZE+48(r1)
-	ld	r4,STACKFRAMESIZE+56(r1)
-	ld	r5,STACKFRAMESIZE+64(r1)
+	ld	r3,STK_REG(R31)(r1)
+	ld	r4,STK_REG(R30)(r1)
+	ld	r5,STK_REG(R29)(r1)
 	mtlr	r0
 
 	/*
@@ -447,8 +447,8 @@ _GLOBAL(memcpy_power7)
 	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	ld	r3,48(r1)
-	b	.exit_vmx_copy		/* tail call optimise */
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	b	exit_vmx_copy		/* tail call optimise */
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -651,6 +651,6 @@ _GLOBAL(memcpy_power7)
 	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	ld	r3,48(r1)
-	b	.exit_vmx_copy		/* tail call optimise */
+	ld	r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
+	b	exit_vmx_copy		/* tail call optimise */
 #endif /* CONFiG_ALTIVEC */
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index c0511c27a73..5c09f365c84 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1198,7 +1198,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = regs->gpr[rb] & 0x3f;
 			ival = (signed int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> (sh < 32 ? sh : 31);
-			if (ival < 0 && (sh >= 32 || (ival & ((1 << sh) - 1)) != 0))
+			if (ival < 0 && (sh >= 32 || (ival & ((1ul << sh) - 1)) != 0))
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1208,7 +1208,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = rb;
 			ival = (signed int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> sh;
-			if (ival < 0 && (ival & ((1 << sh) - 1)) != 0)
+			if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0)
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1216,7 +1216,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef __powerpc64__
 		case 27:	/* sld */
-			sh = regs->gpr[rd] & 0x7f;
+			sh = regs->gpr[rb] & 0x7f;
 			if (sh < 64)
 				regs->gpr[ra] = regs->gpr[rd] << sh;
 			else
@@ -1235,7 +1235,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = regs->gpr[rb] & 0x7f;
 			ival = (signed long int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> (sh < 64 ? sh : 63);
-			if (ival < 0 && (sh >= 64 || (ival & ((1 << sh) - 1)) != 0))
+			if (ival < 0 && (sh >= 64 || (ival & ((1ul << sh) - 1)) != 0))
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1246,7 +1246,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			sh = rb | ((instr & 2) << 4);
 			ival = (signed long int) regs->gpr[rd];
 			regs->gpr[ra] = ival >> sh;
-			if (ival < 0 && (ival & ((1 << sh) - 1)) != 0)
+			if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0)
 				regs->xer |= XER_CA;
 			else
 				regs->xer &= ~XER_CA;
@@ -1470,7 +1470,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 				regs->gpr[rd] = byterev_4(val);
 			goto ldst_done;
 
-#ifdef CONFIG_PPC_CPU
+#ifdef CONFIG_PPC_FPU
 		case 535:	/* lfsx */
 		case 567:	/* lfsux */
 			if (!(regs->msr & MSR_FP))
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
index 3b1e48049fa..7bd9549a90a 100644
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -77,7 +77,7 @@ err3;	stb	r0,0(r3)
 	mr	r3,r4
 	blr
 
-_GLOBAL(__clear_user)
+_GLOBAL_TOC(__clear_user)
 	cmpdi	r4,32
 	neg	r6,r3
 	li	r0,0
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 1136d26a95a..057cbbb4c57 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -159,7 +159,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 BEGIN_FTR_SECTION
 	mr	r4,r30
 	mr	r5,r7
-	bl	.hash_page_do_lazy_icache
+	bl	hash_page_do_lazy_icache
 END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 
 	/* At this point, r3 contains new PP bits, save them in
@@ -201,7 +201,8 @@ htab_insert_pte:
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge	htab_pte_insert_ok	/* Insertion successful */
@@ -225,7 +226,8 @@ _GLOBAL(htab_call_hpte_insert1)
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge+	htab_pte_insert_ok	/* Insertion successful */
@@ -242,7 +244,8 @@ _GLOBAL(htab_call_hpte_insert2)
 2:	and	r0,r5,r27
 	rldicr	r3,r0,3,63-3	/* r0 = (hash & mask) << 3 */	
 	/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
 	bl	.			/* Patched by htab_finish_init() */
 
 	/* Try all again */
@@ -296,7 +299,8 @@ htab_modify_pte:
 	li	r7,MMU_PAGE_4K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
 	bl	.			/* Patched by htab_finish_init() */
 
 	/* if we failed because typically the HPTE wasn't really here
@@ -471,7 +475,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 BEGIN_FTR_SECTION
 	mr	r4,r30
 	mr	r5,r7
-	bl	.hash_page_do_lazy_icache
+	bl	hash_page_do_lazy_icache
 END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 
 	/* At this point, r3 contains new PP bits, save them in
@@ -526,7 +530,8 @@ htab_special_pfn:
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert1)
+.globl htab_call_hpte_insert1
+htab_call_hpte_insert1:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge	htab_pte_insert_ok	/* Insertion successful */
@@ -554,7 +559,8 @@ _GLOBAL(htab_call_hpte_insert1)
 	li	r8,MMU_PAGE_4K		/* page size */
 	li	r9,MMU_PAGE_4K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(htab_call_hpte_insert2)
+.globl htab_call_hpte_insert2
+htab_call_hpte_insert2:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge+	htab_pte_insert_ok	/* Insertion successful */
@@ -571,7 +577,8 @@ _GLOBAL(htab_call_hpte_insert2)
 2:	and	r0,r5,r27
 	rldicr	r3,r0,3,63-3		/* r0 = (hash & mask) << 3 */
 	/* Call ppc_md.hpte_remove */
-_GLOBAL(htab_call_hpte_remove)
+.globl htab_call_hpte_remove
+htab_call_hpte_remove:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* Try all again */
@@ -588,7 +595,7 @@ htab_inval_old_hpte:
 	li	r6,MMU_PAGE_64K		/* psize */
 	ld	r7,STK_PARAM(R9)(r1)	/* ssize */
 	ld	r8,STK_PARAM(R8)(r1)	/* local */
-	bl	.flush_hash_page
+	bl	flush_hash_page
 	/* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */
 	lis	r0,_PAGE_HPTE_SUB@h
 	ori	r0,r0,_PAGE_HPTE_SUB@l
@@ -660,7 +667,8 @@ htab_modify_pte:
 	li	r7,MMU_PAGE_4K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
-_GLOBAL(htab_call_hpte_updatepp)
+.globl htab_call_hpte_updatepp
+htab_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* if we failed because typically the HPTE wasn't really here
@@ -812,7 +820,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 BEGIN_FTR_SECTION
 	mr	r4,r30
 	mr	r5,r7
-	bl	.hash_page_do_lazy_icache
+	bl	hash_page_do_lazy_icache
 END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 
 	/* At this point, r3 contains new PP bits, save them in
@@ -857,7 +865,8 @@ ht64_insert_pte:
 	li	r8,MMU_PAGE_64K
 	li	r9,MMU_PAGE_64K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(ht64_call_hpte_insert1)
+.globl ht64_call_hpte_insert1
+ht64_call_hpte_insert1:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge	ht64_pte_insert_ok	/* Insertion successful */
@@ -881,7 +890,8 @@ _GLOBAL(ht64_call_hpte_insert1)
 	li	r8,MMU_PAGE_64K
 	li	r9,MMU_PAGE_64K		/* actual page size */
 	ld	r10,STK_PARAM(R9)(r1)	/* segment size */
-_GLOBAL(ht64_call_hpte_insert2)
+.globl ht64_call_hpte_insert2
+ht64_call_hpte_insert2:
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
 	bge+	ht64_pte_insert_ok	/* Insertion successful */
@@ -898,7 +908,8 @@ _GLOBAL(ht64_call_hpte_insert2)
 2:	and	r0,r5,r27
 	rldicr	r3,r0,3,63-3	/* r0 = (hash & mask) << 3 */
 	/* Call ppc_md.hpte_remove */
-_GLOBAL(ht64_call_hpte_remove)
+.globl ht64_call_hpte_remove
+ht64_call_hpte_remove:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* Try all again */
@@ -952,7 +963,8 @@ ht64_modify_pte:
 	li	r7,MMU_PAGE_64K		/* actual page size */
 	ld	r8,STK_PARAM(R9)(r1)	/* segment size */
 	ld	r9,STK_PARAM(R8)(r1)	/* get "local" param */
-_GLOBAL(ht64_call_hpte_updatepp)
+.globl ht64_call_hpte_updatepp
+ht64_call_hpte_updatepp:
 	bl	.			/* patched by htab_finish_init() */
 
 	/* if we failed because typically the HPTE wasn't really here
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 350aa58a6f9..88fdd9d2507 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -449,6 +449,24 @@ static void mmu_psize_set_default_penc(void)
 			mmu_psize_defs[bpsize].penc[apsize] = -1;
 }
 
+#ifdef CONFIG_PPC_64K_PAGES
+
+static bool might_have_hea(void)
+{
+	/*
+	 * The HEA ethernet adapter requires awareness of the
+	 * GX bus. Without that awareness we can easily assume
+	 * we will never see an HEA ethernet device.
+	 */
+#ifdef CONFIG_IBMEBUS
+	return !cpu_has_feature(CPU_FTR_ARCH_207S);
+#else
+	return false;
+#endif
+}
+
+#endif /* #ifdef CONFIG_PPC_64K_PAGES */
+
 static void __init htab_init_page_sizes(void)
 {
 	int rc;
@@ -503,10 +521,11 @@ static void __init htab_init_page_sizes(void)
 			mmu_linear_psize = MMU_PAGE_64K;
 		if (mmu_has_feature(MMU_FTR_CI_LARGE_PAGE)) {
 			/*
-			 * Don't use 64k pages for ioremap on pSeries, since
-			 * that would stop us accessing the HEA ethernet.
+			 * When running on pSeries using 64k pages for ioremap
+			 * would stop us accessing the HEA ethernet. So if we
+			 * have the chance of ever seeing one, stay at 4k.
 			 */
-			if (!machine_is(pseries))
+			if (!might_have_hea() || !machine_is(pseries))
 				mmu_io_psize = MMU_PAGE_64K;
 		} else
 			mmu_ci_restrictions = 1;
@@ -607,47 +626,43 @@ int remove_section_mapping(unsigned long start, unsigned long end)
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-#define FUNCTION_TEXT(A)	((*(unsigned long *)(A)))
+extern u32 htab_call_hpte_insert1[];
+extern u32 htab_call_hpte_insert2[];
+extern u32 htab_call_hpte_remove[];
+extern u32 htab_call_hpte_updatepp[];
+extern u32 ht64_call_hpte_insert1[];
+extern u32 ht64_call_hpte_insert2[];
+extern u32 ht64_call_hpte_remove[];
+extern u32 ht64_call_hpte_updatepp[];
 
 static void __init htab_finish_init(void)
 {
-	extern unsigned int *htab_call_hpte_insert1;
-	extern unsigned int *htab_call_hpte_insert2;
-	extern unsigned int *htab_call_hpte_remove;
-	extern unsigned int *htab_call_hpte_updatepp;
-
 #ifdef CONFIG_PPC_HAS_HASH_64K
-	extern unsigned int *ht64_call_hpte_insert1;
-	extern unsigned int *ht64_call_hpte_insert2;
-	extern unsigned int *ht64_call_hpte_remove;
-	extern unsigned int *ht64_call_hpte_updatepp;
-
 	patch_branch(ht64_call_hpte_insert1,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(ht64_call_hpte_insert2,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(ht64_call_hpte_remove,
-		FUNCTION_TEXT(ppc_md.hpte_remove),
+		ppc_function_entry(ppc_md.hpte_remove),
 		BRANCH_SET_LINK);
 	patch_branch(ht64_call_hpte_updatepp,
-		FUNCTION_TEXT(ppc_md.hpte_updatepp),
+		ppc_function_entry(ppc_md.hpte_updatepp),
 		BRANCH_SET_LINK);
-
 #endif /* CONFIG_PPC_HAS_HASH_64K */
 
 	patch_branch(htab_call_hpte_insert1,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(htab_call_hpte_insert2,
-		FUNCTION_TEXT(ppc_md.hpte_insert),
+		ppc_function_entry(ppc_md.hpte_insert),
 		BRANCH_SET_LINK);
 	patch_branch(htab_call_hpte_remove,
-		FUNCTION_TEXT(ppc_md.hpte_remove),
+		ppc_function_entry(ppc_md.hpte_remove),
 		BRANCH_SET_LINK);
 	patch_branch(htab_call_hpte_updatepp,
-		FUNCTION_TEXT(ppc_md.hpte_updatepp),
+		ppc_function_entry(ppc_md.hpte_updatepp),
 		BRANCH_SET_LINK);
 }
 
@@ -964,6 +979,22 @@ void hash_failure_debug(unsigned long ea, unsigned long access,
 		trap, vsid, ssize, psize, lpsize, pte);
 }
 
+static void check_paca_psize(unsigned long ea, struct mm_struct *mm,
+			     int psize, bool user_region)
+{
+	if (user_region) {
+		if (psize != get_paca_psize(ea)) {
+			get_paca()->context = mm->context;
+			slb_flush_and_rebolt();
+		}
+	} else if (get_paca()->vmalloc_sllp !=
+		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
+		get_paca()->vmalloc_sllp =
+			mmu_psize_defs[mmu_vmalloc_psize].sllp;
+		slb_vmalloc_update();
+	}
+}
+
 /* Result code is:
  *  0 - handled
  *  1 - normal page fault
@@ -1085,6 +1116,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 			WARN_ON(1);
 		}
 #endif
+		check_paca_psize(ea, mm, psize, user_region);
+
 		goto bail;
 	}
 
@@ -1125,17 +1158,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 #endif
 		}
 	}
-	if (user_region) {
-		if (psize != get_paca_psize(ea)) {
-			get_paca()->context = mm->context;
-			slb_flush_and_rebolt();
-		}
-	} else if (get_paca()->vmalloc_sllp !=
-		   mmu_psize_defs[mmu_vmalloc_psize].sllp) {
-		get_paca()->vmalloc_sllp =
-			mmu_psize_defs[mmu_vmalloc_psize].sllp;
-		slb_vmalloc_update();
-	}
+
+	check_paca_psize(ea, mm, psize, user_region);
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #ifdef CONFIG_PPC_HAS_HASH_64K
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index af3d78e1930..928ebe79668 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -410,17 +410,7 @@ void __init mmu_context_init(void)
 	} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
 		first_context = 1;
 		last_context = 65535;
-	} else
-#ifdef CONFIG_PPC_BOOK3E_MMU
-	if (mmu_has_feature(MMU_FTR_TYPE_3E)) {
-		u32 mmucfg = mfspr(SPRN_MMUCFG);
-		u32 pid_bits = (mmucfg & MMUCFG_PIDSIZE_MASK)
-				>> MMUCFG_PIDSIZE_SHIFT;
-		first_context = 1;
-		last_context = (1UL << (pid_bits + 1)) - 1;
-	} else
-#endif
-	{
+	} else {
 		first_context = 1;
 		last_context = 255;
 	}
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 964a5f61488..0399a670295 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -256,10 +256,14 @@ static inline void patch_slb_encoding(unsigned int *insn_addr,
 	patch_instruction(insn_addr, insn);
 }
 
+extern u32 slb_compare_rr_to_size[];
+extern u32 slb_miss_kernel_load_linear[];
+extern u32 slb_miss_kernel_load_io[];
+extern u32 slb_compare_rr_to_size[];
+extern u32 slb_miss_kernel_load_vmemmap[];
+
 void slb_set_size(u16 size)
 {
-	extern unsigned int *slb_compare_rr_to_size;
-
 	if (mmu_slb_size == size)
 		return;
 
@@ -272,11 +276,7 @@ void slb_initialize(void)
 	unsigned long linear_llp, vmalloc_llp, io_llp;
 	unsigned long lflags, vflags;
 	static int slb_encoding_inited;
-	extern unsigned int *slb_miss_kernel_load_linear;
-	extern unsigned int *slb_miss_kernel_load_io;
-	extern unsigned int *slb_compare_rr_to_size;
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-	extern unsigned int *slb_miss_kernel_load_vmemmap;
 	unsigned long vmemmap_llp;
 #endif
 
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 17aa6dfceb3..736d18b3cef 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -35,7 +35,7 @@ _GLOBAL(slb_allocate_realmode)
 	 * check for bad kernel/user address
 	 * (ea & ~REGION_MASK) >= PGTABLE_RANGE
 	 */
-	rldicr. r9,r3,4,(63 - 46 - 4)
+	rldicr. r9,r3,4,(63 - PGTABLE_EADDR_SIZE - 4)
 	bne-	8f
 
 	srdi	r9,r3,60		/* get region */
@@ -59,7 +59,8 @@ _GLOBAL(slb_allocate_realmode)
 	/* Linear mapping encoding bits, the "li" instruction below will
 	 * be patched by the kernel at boot
 	 */
-_GLOBAL(slb_miss_kernel_load_linear)
+.globl slb_miss_kernel_load_linear
+slb_miss_kernel_load_linear:
 	li	r11,0
 	/*
 	 * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
@@ -79,7 +80,8 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 	/* Check virtual memmap region. To be patches at kernel boot */
 	cmpldi	cr0,r9,0xf
 	bne	1f
-_GLOBAL(slb_miss_kernel_load_vmemmap)
+.globl slb_miss_kernel_load_vmemmap
+slb_miss_kernel_load_vmemmap:
 	li	r11,0
 	b	6f
 1:
@@ -95,7 +97,8 @@ _GLOBAL(slb_miss_kernel_load_vmemmap)
 	b	6f
 5:
 	/* IO mapping */
-	_GLOBAL(slb_miss_kernel_load_io)
+.globl slb_miss_kernel_load_io
+slb_miss_kernel_load_io:
 	li	r11,0
 6:
 	/*
@@ -250,7 +253,8 @@ slb_finish_load:
 7:	ld	r10,PACASTABRR(r13)
 	addi	r10,r10,1
 	/* This gets soft patched on boot. */
-_GLOBAL(slb_compare_rr_to_size)
+.globl slb_compare_rr_to_size
+slb_compare_rr_to_size:
 	cmpldi	r10,0
 
 	blt+	4f
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index ae3d5b799b9..92cb18d52ea 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -596,8 +596,13 @@ static void __early_init_mmu(int boot_cpu)
 	/* XXX This should be decided at runtime based on supported
 	 * page sizes in the TLB, but for now let's assume 16M is
 	 * always there and a good fit (which it probably is)
+	 *
+	 * Freescale booke only supports 4K pages in TLB0, so use that.
 	 */
-	mmu_vmemmap_psize = MMU_PAGE_16M;
+	if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
+		mmu_vmemmap_psize = MMU_PAGE_4K;
+	else
+		mmu_vmemmap_psize = MMU_PAGE_16M;
 
 	/* XXX This code only checks for TLB 0 capabilities and doesn't
 	 *     check what page size combos are supported by the HW. It
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index e76eba74d9d..8f87d921712 100644
--- a/arch/powerpc/net/bpf_jit_64.S
+++ b/arch/powerpc/net/bpf_jit_64.S
@@ -78,7 +78,7 @@ sk_load_byte_positive_offset:
 	blr
 
 /*
- * BPF_S_LDX_B_MSH: ldxb  4*([offset]&0xf)
+ * BPF_LDX | BPF_B | BPF_MSH: ldxb  4*([offset]&0xf)
  * r_addr is the offset value
  */
 	.globl sk_load_byte_msh
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 808ce1cae21..82e82cadcde 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -79,19 +79,11 @@ static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image,
 	}
 
 	switch (filter[0].code) {
-	case BPF_S_RET_K:
-	case BPF_S_LD_W_LEN:
-	case BPF_S_ANC_PROTOCOL:
-	case BPF_S_ANC_IFINDEX:
-	case BPF_S_ANC_MARK:
-	case BPF_S_ANC_RXHASH:
-	case BPF_S_ANC_VLAN_TAG:
-	case BPF_S_ANC_VLAN_TAG_PRESENT:
-	case BPF_S_ANC_CPU:
-	case BPF_S_ANC_QUEUE:
-	case BPF_S_LD_W_ABS:
-	case BPF_S_LD_H_ABS:
-	case BPF_S_LD_B_ABS:
+	case BPF_RET | BPF_K:
+	case BPF_LD | BPF_W | BPF_LEN:
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
 		/* first instruction sets A register (or is RET 'constant') */
 		break;
 	default:
@@ -144,6 +136,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 
 	for (i = 0; i < flen; i++) {
 		unsigned int K = filter[i].k;
+		u16 code = bpf_anc_helper(&filter[i]);
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -151,35 +144,35 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 		 */
 		addrs[i] = ctx->idx * 4;
 
-		switch (filter[i].code) {
+		switch (code) {
 			/*** ALU ops ***/
-		case BPF_S_ALU_ADD_X: /* A += X; */
+		case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_ADD(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_ADD_K: /* A += K; */
+		case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */
 			if (!K)
 				break;
 			PPC_ADDI(r_A, r_A, IMM_L(K));
 			if (K >= 32768)
 				PPC_ADDIS(r_A, r_A, IMM_HA(K));
 			break;
-		case BPF_S_ALU_SUB_X: /* A -= X; */
+		case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_SUB(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_SUB_K: /* A -= K */
+		case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */
 			if (!K)
 				break;
 			PPC_ADDI(r_A, r_A, IMM_L(-K));
 			if (K >= 32768)
 				PPC_ADDIS(r_A, r_A, IMM_HA(-K));
 			break;
-		case BPF_S_ALU_MUL_X: /* A *= X; */
+		case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_MUL(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_MUL_K: /* A *= K */
+		case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */
 			if (K < 32768)
 				PPC_MULI(r_A, r_A, K);
 			else {
@@ -187,7 +180,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 				PPC_MUL(r_A, r_A, r_scratch1);
 			}
 			break;
-		case BPF_S_ALU_MOD_X: /* A %= X; */
+		case BPF_ALU | BPF_MOD | BPF_X: /* A %= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_CMPWI(r_X, 0);
 			if (ctx->pc_ret0 != -1) {
@@ -201,13 +194,13 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			PPC_MUL(r_scratch1, r_X, r_scratch1);
 			PPC_SUB(r_A, r_A, r_scratch1);
 			break;
-		case BPF_S_ALU_MOD_K: /* A %= K; */
+		case BPF_ALU | BPF_MOD | BPF_K: /* A %= K; */
 			PPC_LI32(r_scratch2, K);
 			PPC_DIVWU(r_scratch1, r_A, r_scratch2);
 			PPC_MUL(r_scratch1, r_scratch2, r_scratch1);
 			PPC_SUB(r_A, r_A, r_scratch1);
 			break;
-		case BPF_S_ALU_DIV_X: /* A /= X; */
+		case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_CMPWI(r_X, 0);
 			if (ctx->pc_ret0 != -1) {
@@ -223,17 +216,17 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			}
 			PPC_DIVWU(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_DIV_K: /* A /= K */
+		case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */
 			if (K == 1)
 				break;
 			PPC_LI32(r_scratch1, K);
 			PPC_DIVWU(r_A, r_A, r_scratch1);
 			break;
-		case BPF_S_ALU_AND_X:
+		case BPF_ALU | BPF_AND | BPF_X:
 			ctx->seen |= SEEN_XREG;
 			PPC_AND(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_AND_K:
+		case BPF_ALU | BPF_AND | BPF_K:
 			if (!IMM_H(K))
 				PPC_ANDI(r_A, r_A, K);
 			else {
@@ -241,51 +234,51 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 				PPC_AND(r_A, r_A, r_scratch1);
 			}
 			break;
-		case BPF_S_ALU_OR_X:
+		case BPF_ALU | BPF_OR | BPF_X:
 			ctx->seen |= SEEN_XREG;
 			PPC_OR(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_OR_K:
+		case BPF_ALU | BPF_OR | BPF_K:
 			if (IMM_L(K))
 				PPC_ORI(r_A, r_A, IMM_L(K));
 			if (K >= 65536)
 				PPC_ORIS(r_A, r_A, IMM_H(K));
 			break;
-		case BPF_S_ANC_ALU_XOR_X:
-		case BPF_S_ALU_XOR_X: /* A ^= X */
+		case BPF_ANC | SKF_AD_ALU_XOR_X:
+		case BPF_ALU | BPF_XOR | BPF_X: /* A ^= X */
 			ctx->seen |= SEEN_XREG;
 			PPC_XOR(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_XOR_K: /* A ^= K */
+		case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */
 			if (IMM_L(K))
 				PPC_XORI(r_A, r_A, IMM_L(K));
 			if (K >= 65536)
 				PPC_XORIS(r_A, r_A, IMM_H(K));
 			break;
-		case BPF_S_ALU_LSH_X: /* A <<= X; */
+		case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_SLW(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_LSH_K:
+		case BPF_ALU | BPF_LSH | BPF_K:
 			if (K == 0)
 				break;
 			else
 				PPC_SLWI(r_A, r_A, K);
 			break;
-		case BPF_S_ALU_RSH_X: /* A >>= X; */
+		case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */
 			ctx->seen |= SEEN_XREG;
 			PPC_SRW(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_RSH_K: /* A >>= K; */
+		case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */
 			if (K == 0)
 				break;
 			else
 				PPC_SRWI(r_A, r_A, K);
 			break;
-		case BPF_S_ALU_NEG:
+		case BPF_ALU | BPF_NEG:
 			PPC_NEG(r_A, r_A);
 			break;
-		case BPF_S_RET_K:
+		case BPF_RET | BPF_K:
 			PPC_LI32(r_ret, K);
 			if (!K) {
 				if (ctx->pc_ret0 == -1)
@@ -312,7 +305,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 					PPC_BLR();
 			}
 			break;
-		case BPF_S_RET_A:
+		case BPF_RET | BPF_A:
 			PPC_MR(r_ret, r_A);
 			if (i != flen - 1) {
 				if (ctx->seen)
@@ -321,53 +314,53 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 					PPC_BLR();
 			}
 			break;
-		case BPF_S_MISC_TAX: /* X = A */
+		case BPF_MISC | BPF_TAX: /* X = A */
 			PPC_MR(r_X, r_A);
 			break;
-		case BPF_S_MISC_TXA: /* A = X */
+		case BPF_MISC | BPF_TXA: /* A = X */
 			ctx->seen |= SEEN_XREG;
 			PPC_MR(r_A, r_X);
 			break;
 
 			/*** Constant loads/M[] access ***/
-		case BPF_S_LD_IMM: /* A = K */
+		case BPF_LD | BPF_IMM: /* A = K */
 			PPC_LI32(r_A, K);
 			break;
-		case BPF_S_LDX_IMM: /* X = K */
+		case BPF_LDX | BPF_IMM: /* X = K */
 			PPC_LI32(r_X, K);
 			break;
-		case BPF_S_LD_MEM: /* A = mem[K] */
+		case BPF_LD | BPF_MEM: /* A = mem[K] */
 			PPC_MR(r_A, r_M + (K & 0xf));
 			ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
 			break;
-		case BPF_S_LDX_MEM: /* X = mem[K] */
+		case BPF_LDX | BPF_MEM: /* X = mem[K] */
 			PPC_MR(r_X, r_M + (K & 0xf));
 			ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
 			break;
-		case BPF_S_ST: /* mem[K] = A */
+		case BPF_ST: /* mem[K] = A */
 			PPC_MR(r_M + (K & 0xf), r_A);
 			ctx->seen |= SEEN_MEM | (1<<(K & 0xf));
 			break;
-		case BPF_S_STX: /* mem[K] = X */
+		case BPF_STX: /* mem[K] = X */
 			PPC_MR(r_M + (K & 0xf), r_X);
 			ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf));
 			break;
-		case BPF_S_LD_W_LEN: /*	A = skb->len; */
+		case BPF_LD | BPF_W | BPF_LEN: /*	A = skb->len; */
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
 			PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len));
 			break;
-		case BPF_S_LDX_W_LEN: /* X = skb->len; */
+		case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */
 			PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len));
 			break;
 
 			/*** Ancillary info loads ***/
-		case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */
+		case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
 						  protocol) != 2);
 			PPC_NTOHS_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							    protocol));
 			break;
-		case BPF_S_ANC_IFINDEX:
+		case BPF_ANC | SKF_AD_IFINDEX:
 			PPC_LD_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff,
 								dev));
 			PPC_CMPDI(r_scratch1, 0);
@@ -384,33 +377,37 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			PPC_LWZ_OFFS(r_A, r_scratch1,
 				     offsetof(struct net_device, ifindex));
 			break;
-		case BPF_S_ANC_MARK:
+		case BPF_ANC | SKF_AD_MARK:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
 			PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  mark));
 			break;
-		case BPF_S_ANC_RXHASH:
+		case BPF_ANC | SKF_AD_RXHASH:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
 			PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  hash));
 			break;
-		case BPF_S_ANC_VLAN_TAG:
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
+		case BPF_ANC | SKF_AD_VLAN_TAG:
+		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+			BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+
 			PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  vlan_tci));
-			if (filter[i].code == BPF_S_ANC_VLAN_TAG)
-				PPC_ANDI(r_A, r_A, VLAN_VID_MASK);
-			else
+			if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
+				PPC_ANDI(r_A, r_A, ~VLAN_TAG_PRESENT);
+			} else {
 				PPC_ANDI(r_A, r_A, VLAN_TAG_PRESENT);
+				PPC_SRWI(r_A, r_A, 12);
+			}
 			break;
-		case BPF_S_ANC_QUEUE:
+		case BPF_ANC | SKF_AD_QUEUE:
 			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
 						  queue_mapping) != 2);
 			PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
 							  queue_mapping));
 			break;
-		case BPF_S_ANC_CPU:
+		case BPF_ANC | SKF_AD_CPU:
 #ifdef CONFIG_SMP
 			/*
 			 * PACA ptr is r13:
@@ -426,13 +423,13 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			break;
 
 			/*** Absolute loads from packet header/data ***/
-		case BPF_S_LD_W_ABS:
+		case BPF_LD | BPF_W | BPF_ABS:
 			func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 			goto common_load;
-		case BPF_S_LD_H_ABS:
+		case BPF_LD | BPF_H | BPF_ABS:
 			func = CHOOSE_LOAD_FUNC(K, sk_load_half);
 			goto common_load;
-		case BPF_S_LD_B_ABS:
+		case BPF_LD | BPF_B | BPF_ABS:
 			func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
 		common_load:
 			/* Load from [K]. */
@@ -449,13 +446,13 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			break;
 
 			/*** Indirect loads from packet header/data ***/
-		case BPF_S_LD_W_IND:
+		case BPF_LD | BPF_W | BPF_IND:
 			func = sk_load_word;
 			goto common_load_ind;
-		case BPF_S_LD_H_IND:
+		case BPF_LD | BPF_H | BPF_IND:
 			func = sk_load_half;
 			goto common_load_ind;
-		case BPF_S_LD_B_IND:
+		case BPF_LD | BPF_B | BPF_IND:
 			func = sk_load_byte;
 		common_load_ind:
 			/*
@@ -473,31 +470,31 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			PPC_BCC(COND_LT, exit_addr);
 			break;
 
-		case BPF_S_LDX_B_MSH:
+		case BPF_LDX | BPF_B | BPF_MSH:
 			func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
 			goto common_load;
 			break;
 
 			/*** Jump and branches ***/
-		case BPF_S_JMP_JA:
+		case BPF_JMP | BPF_JA:
 			if (K != 0)
 				PPC_JMP(addrs[i + 1 + K]);
 			break;
 
-		case BPF_S_JMP_JGT_K:
-		case BPF_S_JMP_JGT_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
 			true_cond = COND_GT;
 			goto cond_branch;
-		case BPF_S_JMP_JGE_K:
-		case BPF_S_JMP_JGE_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
 			true_cond = COND_GE;
 			goto cond_branch;
-		case BPF_S_JMP_JEQ_K:
-		case BPF_S_JMP_JEQ_X:
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
 			true_cond = COND_EQ;
 			goto cond_branch;
-		case BPF_S_JMP_JSET_K:
-		case BPF_S_JMP_JSET_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
 			true_cond = COND_NE;
 			/* Fall through */
 		cond_branch:
@@ -508,20 +505,20 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 				break;
 			}
 
-			switch (filter[i].code) {
-			case BPF_S_JMP_JGT_X:
-			case BPF_S_JMP_JGE_X:
-			case BPF_S_JMP_JEQ_X:
+			switch (code) {
+			case BPF_JMP | BPF_JGT | BPF_X:
+			case BPF_JMP | BPF_JGE | BPF_X:
+			case BPF_JMP | BPF_JEQ | BPF_X:
 				ctx->seen |= SEEN_XREG;
 				PPC_CMPLW(r_A, r_X);
 				break;
-			case BPF_S_JMP_JSET_X:
+			case BPF_JMP | BPF_JSET | BPF_X:
 				ctx->seen |= SEEN_XREG;
 				PPC_AND_DOT(r_scratch1, r_A, r_X);
 				break;
-			case BPF_S_JMP_JEQ_K:
-			case BPF_S_JMP_JGT_K:
-			case BPF_S_JMP_JGE_K:
+			case BPF_JMP | BPF_JEQ | BPF_K:
+			case BPF_JMP | BPF_JGT | BPF_K:
+			case BPF_JMP | BPF_JGE | BPF_K:
 				if (K < 32768)
 					PPC_CMPLWI(r_A, K);
 				else {
@@ -529,7 +526,7 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 					PPC_CMPLW(r_A, r_scratch1);
 				}
 				break;
-			case BPF_S_JMP_JSET_K:
+			case BPF_JMP | BPF_JSET | BPF_K:
 				if (K < 32768)
 					/* PPC_ANDI is /only/ dot-form */
 					PPC_ANDI(r_scratch1, r_A, K);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 4520c9356b5..fe52db2eea6 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -485,7 +485,7 @@ static bool is_ebb_event(struct perf_event *event)
 	 * check that the PMU supports EBB, meaning those that don't can still
 	 * use bit 63 of the event code for something else if they wish.
 	 */
-	return (ppmu->flags & PPMU_EBB) &&
+	return (ppmu->flags & PPMU_ARCH_207S) &&
 	       ((event->attr.config >> PERF_EVENT_CONFIG_EBB_SHIFT) & 1);
 }
 
@@ -777,7 +777,7 @@ void perf_event_print_debug(void)
 	if (ppmu->flags & PPMU_HAS_SIER)
 		sier = mfspr(SPRN_SIER);
 
-	if (ppmu->flags & PPMU_EBB) {
+	if (ppmu->flags & PPMU_ARCH_207S) {
 		pr_info("MMCR2: %016lx EBBHR: %016lx\n",
 			mfspr(SPRN_MMCR2), mfspr(SPRN_EBBHR));
 		pr_info("EBBRR: %016lx BESCR: %016lx\n",
@@ -996,7 +996,22 @@ static void power_pmu_read(struct perf_event *event)
 	} while (local64_cmpxchg(&event->hw.prev_count, prev, val) != prev);
 
 	local64_add(delta, &event->count);
-	local64_sub(delta, &event->hw.period_left);
+
+	/*
+	 * A number of places program the PMC with (0x80000000 - period_left).
+	 * We never want period_left to be less than 1 because we will program
+	 * the PMC with a value >= 0x800000000 and an edge detected PMC will
+	 * roll around to 0 before taking an exception. We have seen this
+	 * on POWER8.
+	 *
+	 * To fix this, clamp the minimum value of period_left to 1.
+	 */
+	do {
+		prev = local64_read(&event->hw.period_left);
+		val = prev - delta;
+		if (val < 1)
+			val = 1;
+	} while (local64_cmpxchg(&event->hw.period_left, prev, val) != prev);
 }
 
 /*
@@ -1292,6 +1307,9 @@ static void power_pmu_enable(struct pmu *pmu)
  out_enable:
 	pmao_restore_workaround(ebb);
 
+	if (ppmu->flags & PPMU_ARCH_207S)
+		mtspr(SPRN_MMCR2, 0);
+
 	mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]);
 
 	mb();
@@ -1696,7 +1714,7 @@ static int power_pmu_event_init(struct perf_event *event)
 
 	if (has_branch_stack(event)) {
 	        /* PMU has BHRB enabled */
-		if (!(ppmu->flags & PPMU_BHRB))
+		if (!(ppmu->flags & PPMU_ARCH_207S))
 			return -EOPNOTSUPP;
 	}
 
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index e0766b82e16..66d0f179650 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -387,8 +387,7 @@ static int h_24x7_event_init(struct perf_event *event)
 	    event->attr.exclude_hv     ||
 	    event->attr.exclude_idle   ||
 	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    is_sampling_event(event)) /* no sampling */
+	    event->attr.exclude_guest)
 		return -EINVAL;
 
 	/* no branch sampling */
@@ -513,6 +512,9 @@ static int hv_24x7_init(void)
 	if (!hv_page_cache)
 		return -ENOMEM;
 
+	/* sampling not supported */
+	h_24x7_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1);
 	if (r)
 		return r;
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index c9d399a2df8..15fc76c9302 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -210,8 +210,7 @@ static int h_gpci_event_init(struct perf_event *event)
 	    event->attr.exclude_hv     ||
 	    event->attr.exclude_idle   ||
 	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    is_sampling_event(event)) /* no sampling */
+	    event->attr.exclude_guest)
 		return -EINVAL;
 
 	/* no branch sampling */
@@ -284,6 +283,9 @@ static int hv_gpci_init(void)
 		return -ENODEV;
 	}
 
+	/* sampling not supported */
+	h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	r = perf_pmu_register(&h_gpci_pmu, h_gpci_pmu.name, -1);
 	if (r)
 		return r;
diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c
index fe2763b6e03..639cd915658 100644
--- a/arch/powerpc/perf/power8-pmu.c
+++ b/arch/powerpc/perf/power8-pmu.c
@@ -792,7 +792,7 @@ static struct power_pmu power8_pmu = {
 	.get_constraint		= power8_get_constraint,
 	.get_alternatives	= power8_get_alternatives,
 	.disable_pmc		= power8_disable_pmc,
-	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB,
+	.flags			= PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_ARCH_207S,
 	.n_generic		= ARRAY_SIZE(power8_generic_events),
 	.generic_events		= power8_generic_events,
 	.cache_events		= &power8_cache_events,
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index dc1a264ec6e..4d88f6a1905 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -199,6 +199,34 @@ config CURRITUCK
 	help
 	  This option enables support for the IBM Currituck (476fpe) evaluation board
 
+config AKEBONO
+	bool "IBM Akebono (476gtr) Support"
+	depends on PPC_47x
+	default n
+	select SWIOTLB
+	select 476FPE
+	select PPC4xx_PCI_EXPRESS
+	select PCI_MSI
+	select PPC4xx_HSTA_MSI
+	select I2C
+	select I2C_IBM_IIC
+	select NETDEVICES
+	select ETHERNET
+	select NET_VENDOR_IBM
+	select IBM_EMAC_EMAC4
+	select IBM_EMAC_RGMII_WOL
+	select USB
+	select USB_OHCI_HCD_PLATFORM
+	select USB_EHCI_HCD_PLATFORM
+	select MMC_SDHCI
+	select MMC_SDHCI_PLTFM
+	select MMC_SDHCI_OF_476GTR
+	select ATA
+	select SATA_AHCI_PLATFORM
+	help
+	  This option enables support for the IBM Akebono (476gtr) evaluation board
+
+
 config ICON
 	bool "Icon"
 	depends on 44x
@@ -323,6 +351,20 @@ config APM821xx
 	select IBM_EMAC_EMAC4
 	select IBM_EMAC_TAH
 
+config 476FPE_ERR46
+	depends on 476FPE
+	bool "Enable linker work around for PPC476FPE errata #46"
+	help
+	  This option enables a work around for an icache bug on 476
+	  that can cause execution of stale instructions when falling
+	  through pages (IBM errata #46). It requires a recent version
+	  of binutils which supports the --ppc476-workaround option.
+
+	  The work around enables the appropriate linker options and
+	  ensures that all module output sections are aligned to 4K
+	  page boundaries. The work around is only required when
+	  building modules.
+
 # 44x errata/workaround config symbols, selected by the CPU models above
 config IBM440EP_ERR42
 	bool
diff --git a/arch/powerpc/platforms/44x/Makefile b/arch/powerpc/platforms/44x/Makefile
index d03833abec0..26d35b5941f 100644
--- a/arch/powerpc/platforms/44x/Makefile
+++ b/arch/powerpc/platforms/44x/Makefile
@@ -10,4 +10,5 @@ obj-$(CONFIG_XILINX_VIRTEX_5_FXT) += virtex.o
 obj-$(CONFIG_XILINX_ML510) += virtex_ml510.o
 obj-$(CONFIG_ISS4xx)	+= iss4xx.o
 obj-$(CONFIG_CANYONLANDS)+= canyonlands.o
-obj-$(CONFIG_CURRITUCK)	+= currituck.o
+obj-$(CONFIG_CURRITUCK)	+= ppc476.o
+obj-$(CONFIG_AKEBONO)	+= ppc476.o
diff --git a/arch/powerpc/platforms/44x/currituck.c b/arch/powerpc/platforms/44x/ppc476.c
index 7f1b71a01c6..33986c1a05d 100644
--- a/arch/powerpc/platforms/44x/currituck.c
+++ b/arch/powerpc/platforms/44x/ppc476.c
@@ -1,7 +1,8 @@
 /*
- * Currituck board specific routines
+ * PowerPC 476FPE board specific routines
  *
- * Copyright © 2011 Tony Breeds IBM Corporation
+ * Copyright © 2013 Tony Breeds IBM Corporation
+ * Copyright © 2013 Alistair Popple IBM Corporation
  *
  * Based on earlier code:
  *    Matt Porter <mporter@kernel.crashing.org>
@@ -35,8 +36,9 @@
 #include <asm/mmu.h>
 
 #include <linux/pci.h>
+#include <linux/i2c.h>
 
-static __initdata struct of_device_id ppc47x_of_bus[] = {
+static struct of_device_id ppc47x_of_bus[] __initdata = {
 	{ .compatible = "ibm,plb4", },
 	{ .compatible = "ibm,plb6", },
 	{ .compatible = "ibm,opb", },
@@ -55,15 +57,69 @@ static void quirk_ppc_currituck_usb_fixup(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(0x1033, 0x0035, quirk_ppc_currituck_usb_fixup);
 
+/* Akebono has an AVR microcontroller attached to the I2C bus
+ * which is used to power off/reset the system. */
+
+/* AVR I2C Commands */
+#define AVR_PWRCTL_CMD (0x26)
+
+/* Flags for the power control I2C commands */
+#define AVR_PWRCTL_PWROFF (0x01)
+#define AVR_PWRCTL_RESET (0x02)
+
+static struct i2c_client *avr_i2c_client;
+static void avr_halt_system(int pwrctl_flags)
+{
+	/* Request the AVR to reset the system */
+	i2c_smbus_write_byte_data(avr_i2c_client,
+				  AVR_PWRCTL_CMD, pwrctl_flags);
+
+	/* Wait for system to be reset */
+	while (1)
+		;
+}
+
+static void avr_power_off_system(void)
+{
+	avr_halt_system(AVR_PWRCTL_PWROFF);
+}
+
+static void avr_reset_system(char *cmd)
+{
+	avr_halt_system(AVR_PWRCTL_RESET);
+}
+
+static int avr_probe(struct i2c_client *client,
+			    const struct i2c_device_id *id)
+{
+	avr_i2c_client = client;
+	ppc_md.restart = avr_reset_system;
+	ppc_md.power_off = avr_power_off_system;
+	return 0;
+}
+
+static const struct i2c_device_id avr_id[] = {
+	{ "akebono-avr", 0 },
+	{ }
+};
+
+static struct i2c_driver avr_driver = {
+	.driver = {
+		.name = "akebono-avr",
+	},
+	.probe = avr_probe,
+	.id_table = avr_id,
+};
+
 static int __init ppc47x_device_probe(void)
 {
+	i2c_add_driver(&avr_driver);
 	of_platform_bus_probe(NULL, ppc47x_of_bus, NULL);
 
 	return 0;
 }
 machine_device_initcall(ppc47x, ppc47x_device_probe);
 
-/* We can have either UICs or MPICs */
 static void __init ppc47x_init_irq(void)
 {
 	struct device_node *np;
@@ -157,43 +213,36 @@ static void __init ppc47x_setup_arch(void)
 {
 
 	/* No need to check the DMA config as we /know/ our windows are all of
- 	 * RAM.  Lets hope that doesn't change */
+	 * RAM.  Lets hope that doesn't change */
 	swiotlb_detect_4g();
 
 	ppc47x_smp_init();
 }
 
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-static int __init ppc47x_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "ibm,currituck"))
-		return 0;
-
-	return 1;
-}
-
 static int board_rev = -1;
 static int __init ppc47x_get_board_rev(void)
 {
-	u8 fpga_reg0;
-	void *fpga;
-	struct device_node *np;
+	int reg;
+	u8 *fpga;
+	struct device_node *np = NULL;
+
+	if (of_machine_is_compatible("ibm,currituck")) {
+		np = of_find_compatible_node(NULL, NULL, "ibm,currituck-fpga");
+		reg = 0;
+	} else if (of_machine_is_compatible("ibm,akebono")) {
+		np = of_find_compatible_node(NULL, NULL, "ibm,akebono-fpga");
+		reg = 2;
+	}
 
-	np = of_find_compatible_node(NULL, NULL, "ibm,currituck-fpga");
 	if (!np)
 		goto fail;
 
-	fpga = of_iomap(np, 0);
+	fpga = (u8 *) of_iomap(np, 0);
 	of_node_put(np);
 	if (!fpga)
 		goto fail;
 
-	fpga_reg0 = ioread8(fpga);
-	board_rev = fpga_reg0 & 0x03;
+	board_rev = ioread8(fpga + reg) & 0x03;
 	pr_info("%s: Found board revision %d\n", __func__, board_rev);
 	iounmap(fpga);
 	return 0;
@@ -208,7 +257,7 @@ machine_arch_initcall(ppc47x, ppc47x_get_board_rev);
 static void ppc47x_pci_irq_fixup(struct pci_dev *dev)
 {
 	if (dev->vendor == 0x1033 && (dev->device == 0x0035 ||
-	                              dev->device == 0x00e0)) {
+				      dev->device == 0x00e0)) {
 		if (board_rev == 0) {
 			dev->irq = irq_create_mapping(NULL, 47);
 			pr_info("%s: Mapping irq %d\n", __func__, dev->irq);
@@ -221,13 +270,30 @@ static void ppc47x_pci_irq_fixup(struct pci_dev *dev)
 	}
 }
 
+/*
+ * Called very early, MMU is off, device-tree isn't unflattened
+ */
+static int __init ppc47x_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	if (of_flat_dt_is_compatible(root, "ibm,akebono"))
+		return 1;
+
+	if (of_flat_dt_is_compatible(root, "ibm,currituck")) {
+		ppc_md.pci_irq_fixup = ppc47x_pci_irq_fixup;
+		return 1;
+	}
+
+	return 0;
+}
+
 define_machine(ppc47x) {
 	.name			= "PowerPC 47x",
 	.probe			= ppc47x_probe,
 	.progress		= udbg_progress,
 	.init_IRQ		= ppc47x_init_irq,
 	.setup_arch		= ppc47x_setup_arch,
-	.pci_irq_fixup		= ppc47x_pci_irq_fixup,
 	.restart		= ppc4xx_reset_system,
 	.calibrate_decr		= generic_calibrate_decr,
 };
diff --git a/arch/powerpc/platforms/44x/ppc476_modules.lds b/arch/powerpc/platforms/44x/ppc476_modules.lds
new file mode 100644
index 00000000000..9fec5d34ba8
--- /dev/null
+++ b/arch/powerpc/platforms/44x/ppc476_modules.lds
@@ -0,0 +1,15 @@
+SECTIONS
+{
+	.text : ALIGN(4096)
+	{
+		*(.text .text.* .fixup)
+	}
+	.init.text : ALIGN(4096)
+	{
+		*(.init.text .init.text.*)
+	}
+	.exit.text : ALIGN(4096)
+	{
+		*(.exit.text .exit.text.*)
+	}
+}
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index c17aae80e7f..f442120e003 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -38,6 +38,15 @@ config C293_PCIE
 	  help
 	  This option enables support for the C293PCIE board
 
+config BSC9132_QDS
+	bool "Freescale BSC9132QDS"
+	select DEFAULT_UIMAGE
+	help
+	  This option enables support for the Freescale BSC9132 QDS board.
+	  BSC9132 is a heterogeneous SoC containing dual e500v2 powerpc cores
+	  and dual StarCore SC3850 DSP cores.
+	  Manufacturer : Freescale Semiconductor, Inc
+
 config MPC8540_ADS
 	bool "Freescale MPC8540 ADS"
 	select DEFAULT_UIMAGE
@@ -117,11 +126,11 @@ config P1022_RDK
 	  This option enables support for the Freescale / iVeia P1022RDK
 	  reference board.
 
-config P1023_RDS
-	bool "Freescale P1023 RDS/RDB"
+config P1023_RDB
+	bool "Freescale P1023 RDB"
 	select DEFAULT_UIMAGE
 	help
-	  This option enables support for the P1023 RDS and RDB boards
+	  This option enables support for the P1023 RDB board.
 
 config TWR_P102x
 	bool "Freescale TWR-P102x"
@@ -263,11 +272,11 @@ config CORENET_GENERIC
 	help
 	  This option enables support for the FSL CoreNet based boards.
 	  For 32bit kernel, the following boards are supported:
-	    P2041 RDB, P3041 DS and P4080 DS
+	    P2041 RDB, P3041 DS, P4080 DS, kmcoge4, and OCA4080
 	  For 64bit kernel, the following boards are supported:
 	    T4240 QDS and B4 QDS
 	  The following boards are supported for both 32bit and 64bit kernel:
-	    P5020 DS and P5040 DS
+	    P5020 DS, P5040 DS and T104xQDS
 
 endif # FSL_SOC_BOOKE
 
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index 25cebe74ac4..73032604662 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_SMP) += smp.o
 obj-y += common.o
 
 obj-$(CONFIG_BSC9131_RDB) += bsc913x_rdb.o
+obj-$(CONFIG_BSC9132_QDS) += bsc913x_qds.o
 obj-$(CONFIG_C293_PCIE)   += c293pcie.o
 obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o
 obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o
@@ -17,7 +18,7 @@ obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o
 obj-$(CONFIG_P1010_RDB)   += p1010rdb.o
 obj-$(CONFIG_P1022_DS)    += p1022_ds.o
 obj-$(CONFIG_P1022_RDK)   += p1022_rdk.o
-obj-$(CONFIG_P1023_RDS)   += p1023_rds.o
+obj-$(CONFIG_P1023_RDB)   += p1023_rdb.o
 obj-$(CONFIG_TWR_P102x)   += twr_p102x.o
 obj-$(CONFIG_CORENET_GENERIC)   += corenet_generic.o
 obj-$(CONFIG_STX_GP3)	  += stx_gp3.o
diff --git a/arch/powerpc/platforms/85xx/bsc913x_qds.c b/arch/powerpc/platforms/85xx/bsc913x_qds.c
new file mode 100644
index 00000000000..f0927e58af2
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/bsc913x_qds.c
@@ -0,0 +1,74 @@
+/*
+ * BSC913xQDS Board Setup
+ *
+ * Author:
+ *   Harninder Rai <harninder.rai@freescale.com>
+ *   Priyanka Jain <Priyanka.Jain@freescale.com>
+ *
+ * Copyright 2014 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <asm/mpic.h>
+#include <sysdev/fsl_soc.h>
+#include <asm/udbg.h>
+
+#include "mpc85xx.h"
+#include "smp.h"
+
+void __init bsc913x_qds_pic_init(void)
+{
+	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+	  MPIC_SINGLE_DEST_CPU,
+	  0, 256, " OpenPIC  ");
+
+	if (!mpic)
+		pr_err("bsc913x: Failed to allocate MPIC structure\n");
+	else
+		mpic_init(mpic);
+}
+
+/*
+ * Setup the architecture
+ */
+static void __init bsc913x_qds_setup_arch(void)
+{
+	if (ppc_md.progress)
+		ppc_md.progress("bsc913x_qds_setup_arch()", 0);
+
+#if defined(CONFIG_SMP)
+	mpc85xx_smp_init();
+#endif
+
+	pr_info("bsc913x board from Freescale Semiconductor\n");
+}
+
+machine_device_initcall(bsc9132_qds, mpc85xx_common_publish_devices);
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+
+static int __init bsc9132_qds_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return of_flat_dt_is_compatible(root, "fsl,bsc9132qds");
+}
+
+define_machine(bsc9132_qds) {
+	.name			= "BSC9132 QDS",
+	.probe			= bsc9132_qds_probe,
+	.setup_arch		= bsc913x_qds_setup_arch,
+	.init_IRQ		= bsc913x_qds_pic_init,
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c
index 8e4b1e1a491..5db1e117fdd 100644
--- a/arch/powerpc/platforms/85xx/corenet_generic.c
+++ b/arch/powerpc/platforms/85xx/corenet_generic.c
@@ -67,7 +67,7 @@ void __init corenet_gen_setup_arch(void)
 
 	swiotlb_detect_4g();
 
-	pr_info("%s board from Freescale Semiconductor\n", ppc_md.name);
+	pr_info("%s board\n", ppc_md.name);
 
 	mpc85xx_qe_init();
 }
@@ -115,6 +115,7 @@ int __init corenet_gen_publish_devices(void)
 static const char * const boards[] __initconst = {
 	"fsl,P2041RDB",
 	"fsl,P3041DS",
+	"fsl,OCA4080",
 	"fsl,P4080DS",
 	"fsl,P5020DS",
 	"fsl,P5040DS",
@@ -122,12 +123,16 @@ static const char * const boards[] __initconst = {
 	"fsl,B4860QDS",
 	"fsl,B4420QDS",
 	"fsl,B4220QDS",
+	"fsl,T1040QDS",
+	"fsl,T1042QDS",
+	"keymile,kmcoge4",
 	NULL
 };
 
 static const char * const hv_boards[] __initconst = {
 	"fsl,P2041RDB-hv",
 	"fsl,P3041DS-hv",
+	"fsl,OCA4080-hv",
 	"fsl,P4080DS-hv",
 	"fsl,P5020DS-hv",
 	"fsl,P5040DS-hv",
@@ -135,6 +140,8 @@ static const char * const hv_boards[] __initconst = {
 	"fsl,B4860QDS-hv",
 	"fsl,B4420QDS-hv",
 	"fsl,B4220QDS-hv",
+	"fsl,T1040QDS-hv",
+	"fsl,T1042QDS-hv",
 	NULL
 };
 
diff --git a/arch/powerpc/platforms/85xx/p1023_rds.c b/arch/powerpc/platforms/85xx/p1023_rdb.c
index 0e614007acf..d5b7509825d 100644
--- a/arch/powerpc/platforms/85xx/p1023_rds.c
+++ b/arch/powerpc/platforms/85xx/p1023_rdb.c
@@ -4,7 +4,7 @@
  * Author: Roy Zang <tie-fei.zang@freescale.com>
  *
  * Description:
- * P1023 RDS Board Setup
+ * P1023 RDB Board Setup
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -41,12 +41,12 @@
  * Setup the architecture
  *
  */
-static void __init mpc85xx_rds_setup_arch(void)
+static void __init mpc85xx_rdb_setup_arch(void)
 {
 	struct device_node *np;
 
 	if (ppc_md.progress)
-		ppc_md.progress("p1023_rds_setup_arch()", 0);
+		ppc_md.progress("p1023_rdb_setup_arch()", 0);
 
 	/* Map BCSR area */
 	np = of_find_node_by_name(NULL, "bcsr");
@@ -85,10 +85,9 @@ static void __init mpc85xx_rds_setup_arch(void)
 	fsl_pci_assign_primary();
 }
 
-machine_arch_initcall(p1023_rds, mpc85xx_common_publish_devices);
 machine_arch_initcall(p1023_rdb, mpc85xx_common_publish_devices);
 
-static void __init mpc85xx_rds_pic_init(void)
+static void __init mpc85xx_rdb_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 		MPIC_SINGLE_DEST_CPU,
@@ -99,14 +98,6 @@ static void __init mpc85xx_rds_pic_init(void)
 	mpic_init(mpic);
 }
 
-static int __init p1023_rds_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	return of_flat_dt_is_compatible(root, "fsl,P1023RDS");
-
-}
-
 static int __init p1023_rdb_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
@@ -115,26 +106,11 @@ static int __init p1023_rdb_probe(void)
 
 }
 
-define_machine(p1023_rds) {
-	.name			= "P1023 RDS",
-	.probe			= p1023_rds_probe,
-	.setup_arch		= mpc85xx_rds_setup_arch,
-	.init_IRQ		= mpc85xx_rds_pic_init,
-	.get_irq		= mpic_get_irq,
-	.restart		= fsl_rstcr_restart,
-	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= udbg_progress,
-#ifdef CONFIG_PCI
-	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
-	.pcibios_fixup_phb      = fsl_pcibios_fixup_phb,
-#endif
-};
-
 define_machine(p1023_rdb) {
 	.name			= "P1023 RDB",
 	.probe			= p1023_rdb_probe,
-	.setup_arch		= mpc85xx_rds_setup_arch,
-	.init_IRQ		= mpc85xx_rds_pic_init,
+	.setup_arch		= mpc85xx_rdb_setup_arch,
+	.init_IRQ		= mpc85xx_rdb_pic_init,
 	.get_irq		= mpic_get_irq,
 	.restart		= fsl_rstcr_restart,
 	.calibrate_decr		= generic_calibrate_decr,
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 6382098d6f8..ba093f55367 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -27,6 +27,7 @@
 #include <asm/cacheflush.h>
 #include <asm/dbell.h>
 #include <asm/fsl_guts.h>
+#include <asm/code-patching.h>
 
 #include <sysdev/fsl_soc.h>
 #include <sysdev/mpic.h>
@@ -267,7 +268,7 @@ out:
 	flush_spin_table(spin_table);
 	out_be32(&spin_table->pir, hw_cpu);
 	out_be64((u64 *)(&spin_table->addr_h),
-	  __pa((u64)*((unsigned long long *)generic_secondary_smp_init)));
+		__pa(ppc_function_entry(generic_secondary_smp_init)));
 	flush_spin_table(spin_table);
 #endif
 
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index bf9c6d4cd26..391b3f6b54a 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -19,7 +19,6 @@ source "arch/powerpc/platforms/embedded6xx/Kconfig"
 source "arch/powerpc/platforms/44x/Kconfig"
 source "arch/powerpc/platforms/40x/Kconfig"
 source "arch/powerpc/platforms/amigaone/Kconfig"
-source "arch/powerpc/platforms/wsp/Kconfig"
 
 config KVM_GUEST
 	bool "KVM Guest support"
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index d9e2b19b7c8..a41bd023647 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -148,10 +148,6 @@ config POWER4
 	depends on PPC64 && PPC_BOOK3S
 	def_bool y
 
-config PPC_A2
-	bool
-	depends on PPC_BOOK3E_64
-
 config TUNE_CELL
 	bool "Optimize for Cell Broadband Engine"
 	depends on PPC64 && PPC_BOOK3S
@@ -280,7 +276,7 @@ config VSX
 
 config PPC_ICSWX
 	bool "Support for PowerPC icswx coprocessor instruction"
-	depends on POWER4 || PPC_A2
+	depends on POWER4
 	default n
 	---help---
 
@@ -422,6 +418,7 @@ config CPU_BIG_ENDIAN
 
 config CPU_LITTLE_ENDIAN
 	bool "Build little endian kernel"
+	select PPC64_BOOT_WRAPPER
 	help
 	  Build a little endian kernel.
 
@@ -430,3 +427,7 @@ config CPU_LITTLE_ENDIAN
 	  little endian powerpc.
 
 endchoice
+
+config PPC64_BOOT_WRAPPER
+	def_bool n
+	depends on CPU_LITTLE_ENDIAN
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index 879b4a44849..469ef170d21 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -22,4 +22,3 @@ obj-$(CONFIG_PPC_CELL)		+= cell/
 obj-$(CONFIG_PPC_PS3)		+= ps3/
 obj-$(CONFIG_EMBEDDED6xx)	+= embedded6xx/
 obj-$(CONFIG_AMIGAONE)		+= amigaone/
-obj-$(CONFIG_PPC_WSP)		+= wsp/
diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c
index 94560db788b..2c15ff09448 100644
--- a/arch/powerpc/platforms/cell/cbe_thermal.c
+++ b/arch/powerpc/platforms/cell/cbe_thermal.c
@@ -125,7 +125,7 @@ static ssize_t show_throttle(struct cbe_pmd_regs __iomem *pmd_regs, char *buf, i
 static ssize_t store_throttle(struct cbe_pmd_regs __iomem *pmd_regs, const char *buf, size_t size, int pos)
 {
 	u64 reg_value;
-	int temp;
+	unsigned int temp;
 	u64 new_value;
 	int ret;
 
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index 90745eaa45f..c8017a7bcab 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -40,6 +40,7 @@
 #include <asm/firmware.h>
 #include <asm/rtas.h>
 #include <asm/cputhreads.h>
+#include <asm/code-patching.h>
 
 #include "interrupt.h"
 #include <asm/udbg.h>
@@ -70,8 +71,8 @@ static cpumask_t of_spin_map;
 static inline int smp_startup_cpu(unsigned int lcpu)
 {
 	int status;
-	unsigned long start_here = __pa((u32)*((unsigned long *)
-					       generic_secondary_smp_init));
+	unsigned long start_here =
+			__pa(ppc_function_entry(generic_secondary_smp_init));
 	unsigned int pcpu;
 	int start_cpu;
 
diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c
index 38e0a1a5cec..5e6e0bad6db 100644
--- a/arch/powerpc/platforms/cell/spu_syscalls.c
+++ b/arch/powerpc/platforms/cell/spu_syscalls.c
@@ -111,6 +111,7 @@ asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus)
 	return ret;
 }
 
+#ifdef CONFIG_COREDUMP
 int elf_coredump_extra_notes_size(void)
 {
 	struct spufs_calls *calls;
@@ -142,6 +143,7 @@ int elf_coredump_extra_notes_write(struct coredump_params *cprm)
 
 	return ret;
 }
+#endif
 
 void notify_spus_active(void)
 {
diff --git a/arch/powerpc/platforms/cell/spufs/Makefile b/arch/powerpc/platforms/cell/spufs/Makefile
index b9d5d678aa4..52a7d2596d3 100644
--- a/arch/powerpc/platforms/cell/spufs/Makefile
+++ b/arch/powerpc/platforms/cell/spufs/Makefile
@@ -1,8 +1,9 @@
 
 obj-$(CONFIG_SPU_FS) += spufs.o
-spufs-y += inode.o file.o context.o syscalls.o coredump.o
+spufs-y += inode.o file.o context.o syscalls.o
 spufs-y += sched.o backing_ops.o hw_ops.o run.o gang.o
 spufs-y += switch.o fault.o lscsa_alloc.o
+spufs-$(CONFIG_COREDUMP) += coredump.o
 
 # magic for the trace events
 CFLAGS_sched.o := -I$(src)
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 0ba3c959835..bcfd6f063ef 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -35,7 +35,6 @@
 #define SPUFS_PS_MAP_SIZE	0x20000
 #define SPUFS_MFC_MAP_SIZE	0x1000
 #define SPUFS_CNTL_MAP_SIZE	0x1000
-#define SPUFS_CNTL_MAP_SIZE	0x1000
 #define SPUFS_SIGNAL_MAP_SIZE	PAGE_SIZE
 #define SPUFS_MSS_MAP_SIZE	0x1000
 
diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index b045fdda484..a87200a535f 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -79,8 +79,10 @@ static long do_spu_create(const char __user *pathname, unsigned int flags,
 struct spufs_calls spufs_calls = {
 	.create_thread = do_spu_create,
 	.spu_run = do_spu_run,
-	.coredump_extra_notes_size = spufs_coredump_extra_notes_size,
-	.coredump_extra_notes_write = spufs_coredump_extra_notes_write,
 	.notify_spus_active = do_notify_spus_active,
 	.owner = THIS_MODULE,
+#ifdef CONFIG_COREDUMP
+	.coredump_extra_notes_size = spufs_coredump_extra_notes_size,
+	.coredump_extra_notes_write = spufs_coredump_extra_notes_write,
+#endif
 };
diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig
index 2a7024d8d8b..a25f496c2ef 100644
--- a/arch/powerpc/platforms/embedded6xx/Kconfig
+++ b/arch/powerpc/platforms/embedded6xx/Kconfig
@@ -65,6 +65,7 @@ config MVME5100
 	select PPC_INDIRECT_PCI
 	select PPC_I8259
 	select PPC_NATIVE
+	select PPC_UDBG_16550
 	help
 	  This option enables support for the Motorola (now Emerson) MVME5100
 	  board.
diff --git a/arch/powerpc/platforms/pasemi/powersave.S b/arch/powerpc/platforms/pasemi/powersave.S
index 56f45adcd08..81ab555aa49 100644
--- a/arch/powerpc/platforms/pasemi/powersave.S
+++ b/arch/powerpc/platforms/pasemi/powersave.S
@@ -66,7 +66,7 @@ sleep_common:
 	std	r3, 48(r1)
 
 	/* Only do power savings when in astate 0 */
-	bl	.check_astate
+	bl	check_astate
 	cmpwi	r3,0
 	bne	1f
 
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index c252ee95bdd..45a8ed0585c 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -17,6 +17,7 @@ config PPC_POWERNV
 	select CPU_FREQ_GOV_USERSPACE
 	select CPU_FREQ_GOV_ONDEMAND
 	select CPU_FREQ_GOV_CONSERVATIVE
+	select PPC_DOORBELL
 	default y
 
 config PPC_POWERNV_RTAS
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 63cebb9b4d4..4ad227d04c1 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -1,9 +1,9 @@
-obj-y			+= setup.o opal-takeover.o opal-wrappers.o opal.o opal-async.o
+obj-y			+= setup.o opal-wrappers.o opal.o opal-async.o
 obj-y			+= opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y			+= rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
 obj-y			+= opal-msglog.o
 
-obj-$(CONFIG_SMP)	+= smp.o
+obj-$(CONFIG_SMP)	+= smp.o subcore.o subcore-asm.o
 obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o pci-ioda.o
 obj-$(CONFIG_EEH)	+= eeh-ioda.o eeh-powernv.o
 obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 5b51079f3e3..8ad0c5b891f 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -42,11 +42,19 @@ static int ioda_eeh_event(struct notifier_block *nb,
 {
 	uint64_t changed_evts = (uint64_t)change;
 
-	/* We simply send special EEH event */
-	if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
-	    (events & OPAL_EVENT_PCI_ERROR) &&
-	    eeh_enabled())
+	/*
+	 * We simply send special EEH event if EEH has
+	 * been enabled, or clear pending events in
+	 * case that we enable EEH soon
+	 */
+	if (!(changed_evts & OPAL_EVENT_PCI_ERROR) ||
+	    !(events & OPAL_EVENT_PCI_ERROR))
+		return 0;
+
+	if (eeh_enabled())
 		eeh_send_failure_event(NULL);
+	else
+		opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
 
 	return 0;
 }
@@ -141,7 +149,9 @@ static int ioda_eeh_post_init(struct pci_controller *hose)
 	}
 
 #ifdef CONFIG_DEBUG_FS
-	if (phb->dbgfs) {
+	if (!phb->has_dbgfs && phb->dbgfs) {
+		phb->has_dbgfs = 1;
+
 		debugfs_create_file("err_injct_outbound", 0600,
 				    phb->dbgfs, hose,
 				    &ioda_eeh_outb_dbgfs_ops);
@@ -154,7 +164,14 @@ static int ioda_eeh_post_init(struct pci_controller *hose)
 	}
 #endif
 
-	phb->eeh_state |= PNV_EEH_STATE_ENABLED;
+	/* If EEH is enabled, we're going to rely on that.
+	 * Otherwise, we restore to conventional mechanism
+	 * to clear frozen PE during PCI config access.
+	 */
+	if (eeh_enabled())
+		phb->flags |= PNV_PHB_FLAG_EEH;
+	else
+		phb->flags &= ~PNV_PHB_FLAG_EEH;
 
 	return 0;
 }
@@ -250,7 +267,7 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
 {
 	s64 ret = 0;
 	u8 fstate;
-	u16 pcierr;
+	__be16 pcierr;
 	u32 pe_no;
 	int result;
 	struct pci_controller *hose = pe->phb;
@@ -268,6 +285,21 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
 		return EEH_STATE_NOT_SUPPORT;
 	}
 
+	/*
+	 * If we're in middle of PE reset, return normal
+	 * state to keep EEH core going. For PHB reset, we
+	 * still expect to have fenced PHB cleared with
+	 * PHB reset.
+	 */
+	if (!(pe->type & EEH_PE_PHB) &&
+	    (pe->state & EEH_PE_RESET)) {
+		result = (EEH_STATE_MMIO_ACTIVE |
+			  EEH_STATE_DMA_ACTIVE |
+			  EEH_STATE_MMIO_ENABLED |
+			  EEH_STATE_DMA_ENABLED);
+		return result;
+	}
+
 	/* Retrieve PE status through OPAL */
 	pe_no = pe->addr;
 	ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no,
@@ -284,7 +316,7 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
 		result = 0;
 		result &= ~EEH_STATE_RESET_ACTIVE;
 
-		if (pcierr != OPAL_EEH_PHB_ERROR) {
+		if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) {
 			result |= EEH_STATE_MMIO_ACTIVE;
 			result |= EEH_STATE_DMA_ACTIVE;
 			result |= EEH_STATE_MMIO_ENABLED;
@@ -347,52 +379,6 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
 	return result;
 }
 
-static int ioda_eeh_pe_clear(struct eeh_pe *pe)
-{
-	struct pci_controller *hose;
-	struct pnv_phb *phb;
-	u32 pe_no;
-	u8 fstate;
-	u16 pcierr;
-	s64 ret;
-
-	pe_no = pe->addr;
-	hose = pe->phb;
-	phb = pe->phb->private_data;
-
-	/* Clear the EEH error on the PE */
-	ret = opal_pci_eeh_freeze_clear(phb->opal_id,
-			pe_no, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
-	if (ret) {
-		pr_err("%s: Failed to clear EEH error for "
-		       "PHB#%x-PE#%x, err=%lld\n",
-		       __func__, hose->global_number, pe_no, ret);
-		return -EIO;
-	}
-
-	/*
-	 * Read the PE state back and verify that the frozen
-	 * state has been removed.
-	 */
-	ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no,
-			&fstate, &pcierr, NULL);
-	if (ret) {
-		pr_err("%s: Failed to get EEH status on "
-		       "PHB#%x-PE#%x\n, err=%lld\n",
-		       __func__, hose->global_number, pe_no, ret);
-		return -EIO;
-	}
-
-	if (fstate != OPAL_EEH_STOPPED_NOT_FROZEN) {
-		pr_err("%s: Frozen state not cleared on "
-		       "PHB#%x-PE#%x, sts=%x\n",
-		       __func__, hose->global_number, pe_no, fstate);
-		return -EIO;
-	}
-
-	return 0;
-}
-
 static s64 ioda_eeh_phb_poll(struct pnv_phb *phb)
 {
 	s64 rc = OPAL_HARDWARE;
@@ -402,13 +388,16 @@ static s64 ioda_eeh_phb_poll(struct pnv_phb *phb)
 		if (rc <= 0)
 			break;
 
-		msleep(rc);
+		if (system_state < SYSTEM_RUNNING)
+			udelay(1000 * rc);
+		else
+			msleep(rc);
 	}
 
 	return rc;
 }
 
-static int ioda_eeh_phb_reset(struct pci_controller *hose, int option)
+int ioda_eeh_phb_reset(struct pci_controller *hose, int option)
 {
 	struct pnv_phb *phb = hose->private_data;
 	s64 rc = OPAL_HARDWARE;
@@ -431,9 +420,17 @@ static int ioda_eeh_phb_reset(struct pci_controller *hose, int option)
 
 	/*
 	 * Poll state of the PHB until the request is done
-	 * successfully.
+	 * successfully. The PHB reset is usually PHB complete
+	 * reset followed by hot reset on root bus. So we also
+	 * need the PCI bus settlement delay.
 	 */
 	rc = ioda_eeh_phb_poll(phb);
+	if (option == EEH_RESET_DEACTIVATE) {
+		if (system_state < SYSTEM_RUNNING)
+			udelay(1000 * EEH_PE_RST_SETTLE_TIME);
+		else
+			msleep(EEH_PE_RST_SETTLE_TIME);
+	}
 out:
 	if (rc != OPAL_SUCCESS)
 		return -EIO;
@@ -471,6 +468,8 @@ static int ioda_eeh_root_reset(struct pci_controller *hose, int option)
 
 	/* Poll state of the PHB until the request is done */
 	rc = ioda_eeh_phb_poll(phb);
+	if (option == EEH_RESET_DEACTIVATE)
+		msleep(EEH_PE_RST_SETTLE_TIME);
 out:
 	if (rc != OPAL_SUCCESS)
 		return -EIO;
@@ -478,32 +477,71 @@ out:
 	return 0;
 }
 
-static int ioda_eeh_bridge_reset(struct pci_controller *hose,
-		struct pci_dev *dev, int option)
+static int ioda_eeh_bridge_reset(struct pci_dev *dev, int option)
+
 {
-	u16 ctrl;
+	struct device_node *dn = pci_device_to_OF_node(dev);
+	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	int aer = edev ? edev->aer_cap : 0;
+	u32 ctrl;
 
-	pr_debug("%s: Reset device %04x:%02x:%02x.%01x with option %d\n",
-		 __func__, hose->global_number, dev->bus->number,
-		 PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn), option);
+	pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n",
+		 __func__, pci_domain_nr(dev->bus),
+		 dev->bus->number, option);
 
 	switch (option) {
 	case EEH_RESET_FUNDAMENTAL:
 	case EEH_RESET_HOT:
-		pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl);
+		/* Don't report linkDown event */
+		if (aer) {
+			eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK,
+					     4, &ctrl);
+			ctrl |= PCI_ERR_UNC_SURPDN;
+                        eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK,
+					      4, ctrl);
+                }
+
+		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl);
 		ctrl |= PCI_BRIDGE_CTL_BUS_RESET;
-		pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl);
+		eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl);
+		msleep(EEH_PE_RST_HOLD_TIME);
+
 		break;
 	case EEH_RESET_DEACTIVATE:
-		pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl);
+		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl);
 		ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
-		pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl);
+		eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl);
+		msleep(EEH_PE_RST_SETTLE_TIME);
+
+		/* Continue reporting linkDown event */
+		if (aer) {
+			eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK,
+					     4, &ctrl);
+			ctrl &= ~PCI_ERR_UNC_SURPDN;
+			eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK,
+					      4, ctrl);
+		}
+
 		break;
 	}
 
 	return 0;
 }
 
+void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
+{
+	struct pci_controller *hose;
+
+	if (pci_is_root_bus(dev->bus)) {
+		hose = pci_bus_to_host(dev->bus);
+		ioda_eeh_root_reset(hose, EEH_RESET_HOT);
+		ioda_eeh_root_reset(hose, EEH_RESET_DEACTIVATE);
+	} else {
+		ioda_eeh_bridge_reset(dev, EEH_RESET_HOT);
+		ioda_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE);
+	}
+}
+
 /**
  * ioda_eeh_reset - Reset the indicated PE
  * @pe: EEH PE
@@ -523,27 +561,18 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 	int ret;
 
 	/*
-	 * Anyway, we have to clear the problematic state for the
-	 * corresponding PE. However, we needn't do it if the PE
-	 * is PHB associated. That means the PHB is having fatal
-	 * errors and it needs reset. Further more, the AIB interface
-	 * isn't reliable any more.
-	 */
-	if (!(pe->type & EEH_PE_PHB) &&
-	    (option == EEH_RESET_HOT ||
-	    option == EEH_RESET_FUNDAMENTAL)) {
-		ret = ioda_eeh_pe_clear(pe);
-		if (ret)
-			return -EIO;
-	}
-
-	/*
-	 * The rules applied to reset, either fundamental or hot reset:
+	 * For PHB reset, we always have complete reset. For those PEs whose
+	 * primary bus derived from root complex (root bus) or root port
+	 * (usually bus#1), we apply hot or fundamental reset on the root port.
+	 * For other PEs, we always have hot reset on the PE primary bus.
 	 *
-	 * We always reset the direct upstream bridge of the PE. If the
-	 * direct upstream bridge isn't root bridge, we always take hot
-	 * reset no matter what option (fundamental or hot) is. Otherwise,
-	 * we should do the reset according to the required option.
+	 * Here, we have different design to pHyp, which always clear the
+	 * frozen state during PE reset. However, the good idea here from
+	 * benh is to keep frozen state before we get PE reset done completely
+	 * (until BAR restore). With the frozen state, HW drops illegal IO
+	 * or MMIO access, which can incur recrusive frozen PE during PE
+	 * reset. The side effect is that EEH core has to clear the frozen
+	 * state explicitly after BAR restore.
 	 */
 	if (pe->type & EEH_PE_PHB) {
 		ret = ioda_eeh_phb_reset(hose, option);
@@ -553,7 +582,7 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 		    pci_is_root_bus(bus->parent))
 			ret = ioda_eeh_root_reset(hose, option);
 		else
-			ret = ioda_eeh_bridge_reset(hose, bus->self, option);
+			ret = ioda_eeh_bridge_reset(bus->self, option);
 	}
 
 	return ret;
@@ -640,22 +669,6 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose)
 	}
 }
 
-static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
-			       struct eeh_pe **pe)
-{
-	struct eeh_pe *phb_pe;
-
-	phb_pe = eeh_phb_pe_get(hose);
-	if (!phb_pe) {
-		pr_warning("%s Can't find PE for PHB#%d\n",
-			   __func__, hose->global_number);
-		return -EEXIST;
-	}
-
-	*pe = phb_pe;
-	return 0;
-}
-
 static int ioda_eeh_get_pe(struct pci_controller *hose,
 			   u16 pe_no, struct eeh_pe **pe)
 {
@@ -663,7 +676,8 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
 	struct eeh_dev dev;
 
 	/* Find the PHB PE */
-	if (ioda_eeh_get_phb_pe(hose, &phb_pe))
+	phb_pe = eeh_phb_pe_get(hose);
+	if (!phb_pe)
 		return -EEXIST;
 
 	/* Find the PE according to PE# */
@@ -691,26 +705,30 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
-	u64 frozen_pe_no;
-	u16 err_type, severity;
+	struct eeh_pe *phb_pe, *parent_pe;
+	__be64 frozen_pe_no;
+	__be16 err_type, severity;
+	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	long rc;
-	int ret = EEH_NEXT_ERR_NONE;
+	int state, ret = EEH_NEXT_ERR_NONE;
 
 	/*
 	 * While running here, it's safe to purge the event queue.
 	 * And we should keep the cached OPAL notifier event sychronized
 	 * between the kernel and firmware.
 	 */
-	eeh_remove_event(NULL);
+	eeh_remove_event(NULL, false);
 	opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
 
 	list_for_each_entry(hose, &hose_list, list_node) {
 		/*
 		 * If the subordinate PCI buses of the PHB has been
-		 * removed, we needn't take care of it any more.
+		 * removed or is exactly under error recovery, we
+		 * needn't take care of it any more.
 		 */
 		phb = hose->private_data;
-		if (phb->eeh_state & PNV_EEH_STATE_REMOVED)
+		phb_pe = eeh_phb_pe_get(hose);
+		if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED))
 			continue;
 
 		rc = opal_pci_next_error(phb->opal_id,
@@ -725,8 +743,8 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		}
 
 		/* If the PHB doesn't have error, stop processing */
-		if (err_type == OPAL_EEH_NO_ERROR ||
-		    severity == OPAL_EEH_SEV_NO_ERROR) {
+		if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR ||
+		    be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) {
 			pr_devel("%s: No error found on PHB#%x\n",
 				 __func__, hose->global_number);
 			continue;
@@ -738,20 +756,14 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		 * specific PHB.
 		 */
 		pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n",
-			 __func__, err_type, severity,
-			 frozen_pe_no, hose->global_number);
-		switch (err_type) {
+			 __func__, be16_to_cpu(err_type), be16_to_cpu(severity),
+			 be64_to_cpu(frozen_pe_no), hose->global_number);
+		switch (be16_to_cpu(err_type)) {
 		case OPAL_EEH_IOC_ERROR:
-			if (severity == OPAL_EEH_SEV_IOC_DEAD) {
-				list_for_each_entry(hose, &hose_list,
-						    list_node) {
-					phb = hose->private_data;
-					phb->eeh_state |= PNV_EEH_STATE_REMOVED;
-				}
-
+			if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) {
 				pr_err("EEH: dead IOC detected\n");
 				ret = EEH_NEXT_ERR_DEAD_IOC;
-			} else if (severity == OPAL_EEH_SEV_INF) {
+			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
 				pr_info("EEH: IOC informative error "
 					"detected\n");
 				ioda_eeh_hub_diag(hose);
@@ -760,25 +772,26 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 
 			break;
 		case OPAL_EEH_PHB_ERROR:
-			if (severity == OPAL_EEH_SEV_PHB_DEAD) {
-				if (ioda_eeh_get_phb_pe(hose, pe))
-					break;
-
-				pr_err("EEH: dead PHB#%x detected\n",
-					hose->global_number);
-				phb->eeh_state |= PNV_EEH_STATE_REMOVED;
+			if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) {
+				*pe = phb_pe;
+				pr_err("EEH: dead PHB#%x detected, "
+				       "location: %s\n",
+				       hose->global_number,
+				       eeh_pe_loc_get(phb_pe));
 				ret = EEH_NEXT_ERR_DEAD_PHB;
-			} else if (severity == OPAL_EEH_SEV_PHB_FENCED) {
-				if (ioda_eeh_get_phb_pe(hose, pe))
-					break;
-
-				pr_err("EEH: fenced PHB#%x detected\n",
-					hose->global_number);
+			} else if (be16_to_cpu(severity) ==
+						OPAL_EEH_SEV_PHB_FENCED) {
+				*pe = phb_pe;
+				pr_err("EEH: Fenced PHB#%x detected, "
+				       "location: %s\n",
+				       hose->global_number,
+				       eeh_pe_loc_get(phb_pe));
 				ret = EEH_NEXT_ERR_FENCED_PHB;
-			} else if (severity == OPAL_EEH_SEV_INF) {
+			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
 				pr_info("EEH: PHB#%x informative error "
-					"detected\n",
-					hose->global_number);
+					"detected, location: %s\n",
+					hose->global_number,
+					eeh_pe_loc_get(phb_pe));
 				ioda_eeh_phb_diag(hose);
 				ret = EEH_NEXT_ERR_NONE;
 			}
@@ -786,30 +799,33 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 			break;
 		case OPAL_EEH_PE_ERROR:
 			/*
-			 * If we can't find the corresponding PE, the
-			 * PEEV / PEST would be messy. So we force an
-			 * fenced PHB so that it can be recovered.
+			 * If we can't find the corresponding PE, we
+			 * just try to unfreeze.
 			 */
-			if (ioda_eeh_get_pe(hose, frozen_pe_no, pe)) {
-				if (!ioda_eeh_get_phb_pe(hose, pe)) {
-					pr_err("EEH: Escalated fenced PHB#%x "
-					       "detected for PE#%llx\n",
-						hose->global_number,
-						frozen_pe_no);
-					ret = EEH_NEXT_ERR_FENCED_PHB;
-				} else {
-					ret = EEH_NEXT_ERR_NONE;
-				}
+			if (ioda_eeh_get_pe(hose,
+					    be64_to_cpu(frozen_pe_no), pe)) {
+				/* Try best to clear it */
+				pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n",
+					hose->global_number, frozen_pe_no);
+				pr_info("EEH: PHB location: %s\n",
+					eeh_pe_loc_get(phb_pe));
+				opal_pci_eeh_freeze_clear(phb->opal_id, frozen_pe_no,
+					OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+				ret = EEH_NEXT_ERR_NONE;
+			} else if ((*pe)->state & EEH_PE_ISOLATED) {
+				ret = EEH_NEXT_ERR_NONE;
 			} else {
 				pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
 					(*pe)->addr, (*pe)->phb->global_number);
+				pr_err("EEH: PE location: %s, PHB location: %s\n",
+					eeh_pe_loc_get(*pe), eeh_pe_loc_get(phb_pe));
 				ret = EEH_NEXT_ERR_FROZEN_PE;
 			}
 
 			break;
 		default:
 			pr_warn("%s: Unexpected error type %d\n",
-				__func__, err_type);
+				__func__, be16_to_cpu(err_type));
 		}
 
 		/*
@@ -827,6 +843,31 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		}
 
 		/*
+		 * We probably have the frozen parent PE out there and
+		 * we need have to handle frozen parent PE firstly.
+		 */
+		if (ret == EEH_NEXT_ERR_FROZEN_PE) {
+			parent_pe = (*pe)->parent;
+			while (parent_pe) {
+				/* Hit the ceiling ? */
+				if (parent_pe->type & EEH_PE_PHB)
+					break;
+
+				/* Frozen parent PE ? */
+				state = ioda_eeh_get_state(parent_pe);
+				if (state > 0 &&
+				    (state & active_flags) != active_flags)
+					*pe = parent_pe;
+
+				/* Next parent level */
+				parent_pe = parent_pe->parent;
+			}
+
+			/* We possibly migrate to another PE */
+			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+		}
+
+		/*
 		 * If we have no errors on the specific PHB or only
 		 * informative error there, we continue poking it.
 		 * Otherwise, we need actions to be taken by upper
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index a59788e83b8..56a206f32f7 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -126,6 +126,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	edev->mode	&= 0xFFFFFF00;
 	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
 		edev->mode |= EEH_DEV_BRIDGE;
+	edev->pcix_cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
 	if (pci_is_pcie(dev)) {
 		edev->pcie_cap = pci_pcie_cap(dev);
 
@@ -133,6 +134,9 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 			edev->mode |= EEH_DEV_ROOT_PORT;
 		else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM)
 			edev->mode |= EEH_DEV_DS_PORT;
+
+		edev->aer_cap = pci_find_ext_capability(dev,
+							PCI_EXT_CAP_ID_ERR);
 	}
 
 	edev->config_addr	= ((dev->bus->number << 8) | dev->devfn);
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 10268c41d83..0ad533b617f 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -249,7 +249,7 @@ static void elog_work_fn(struct work_struct *work)
 
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
-		pr_err("ELOG: Opal log read failed\n");
+		pr_err("ELOG: OPAL log info read failed\n");
 		return;
 	}
 
@@ -257,7 +257,7 @@ static void elog_work_fn(struct work_struct *work)
 	log_id = be64_to_cpu(id);
 	elog_type = be64_to_cpu(type);
 
-	BUG_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
+	WARN_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
 
 	if (elog_size >= OPAL_MAX_ERRLOG_SIZE)
 		elog_size  =  OPAL_MAX_ERRLOG_SIZE;
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index dc487ff0470..5c21d9c07f4 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
+#include <linux/delay.h>
 
 #include <asm/opal.h>
 
@@ -130,7 +131,8 @@ static inline void opal_flash_validate(void)
 {
 	long ret;
 	void *buf = validate_flash_data.buf;
-	__be32 size, result;
+	__be32 size = cpu_to_be32(validate_flash_data.buf_size);
+	__be32 result;
 
 	ret = opal_validate_flash(__pa(buf), &size, &result);
 
@@ -290,11 +292,6 @@ static int opal_flash_update(int op)
 	/* First entry address */
 	addr = __pa(list);
 
-	pr_alert("FLASH: Image is %u bytes\n", image_data.size);
-	pr_alert("FLASH: Image update requested\n");
-	pr_alert("FLASH: Image will be updated during system reboot\n");
-	pr_alert("FLASH: This will take several minutes. Do not power off!\n");
-
 flash:
 	rc = opal_update_flash(addr);
 
@@ -302,6 +299,47 @@ invalid_img:
 	return rc;
 }
 
+/* Return CPUs to OPAL before starting FW update */
+static void flash_return_cpu(void *info)
+{
+	int cpu = smp_processor_id();
+
+	if (!cpu_online(cpu))
+		return;
+
+	/* Disable IRQ */
+	hard_irq_disable();
+
+	/* Return the CPU to OPAL */
+	opal_return_cpu();
+}
+
+/* This gets called just before system reboots */
+void opal_flash_term_callback(void)
+{
+	struct cpumask mask;
+
+	if (update_flash_data.status != FLASH_IMG_READY)
+		return;
+
+	pr_alert("FLASH: Flashing new firmware\n");
+	pr_alert("FLASH: Image is %u bytes\n", image_data.size);
+	pr_alert("FLASH: Performing flash and reboot/shutdown\n");
+	pr_alert("FLASH: This will take several minutes. Do not power off!\n");
+
+	/* Small delay to help getting the above message out */
+	msleep(500);
+
+	/* Return secondary CPUs to firmware */
+	cpumask_copy(&mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+	if (!cpumask_empty(&mask))
+		smp_call_function_many(&mask,
+				       flash_return_cpu, NULL, false);
+	/* Hard disable interrupts */
+	hard_irq_disable();
+}
+
 /*
  * Show candidate image status
  */
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index 79d83cad3d6..f04b4d8aca5 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -12,12 +12,17 @@
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/bug.h>
+#include <linux/debugfs.h>
+#include <linux/io.h>
+#include <linux/slab.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/xics.h>
 #include <asm/opal.h>
 #include <asm/prom.h>
+#include <asm/uaccess.h>
+#include <asm/debug.h>
 
 static int opal_lpc_chip_id = -1;
 
@@ -176,6 +181,152 @@ static const struct ppc_pci_io opal_lpc_io = {
 	.outsl	= opal_lpc_outsl,
 };
 
+#ifdef CONFIG_DEBUG_FS
+struct lpc_debugfs_entry {
+	enum OpalLPCAddressType lpc_type;
+};
+
+static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf,
+			      size_t count, loff_t *ppos)
+{
+	struct lpc_debugfs_entry *lpc = filp->private_data;
+	u32 data, pos, len, todo;
+	int rc;
+
+	if (!access_ok(VERIFY_WRITE, ubuf, count))
+		return -EFAULT;
+
+	todo = count;
+	while (todo) {
+		pos = *ppos;
+
+		/*
+		 * Select access size based on count and alignment and
+		 * access type. IO and MEM only support byte acceses,
+		 * FW supports all 3.
+		 */
+		len = 1;
+		if (lpc->lpc_type == OPAL_LPC_FW) {
+			if (todo > 3 && (pos & 3) == 0)
+				len = 4;
+			else if (todo > 1 && (pos & 1) == 0)
+				len = 2;
+		}
+		rc = opal_lpc_read(opal_lpc_chip_id, lpc->lpc_type, pos,
+				   &data, len);
+		if (rc)
+			return -ENXIO;
+		switch(len) {
+		case 4:
+			rc = __put_user((u32)data, (u32 __user *)ubuf);
+			break;
+		case 2:
+			rc = __put_user((u16)data, (u16 __user *)ubuf);
+			break;
+		default:
+			rc = __put_user((u8)data, (u8 __user *)ubuf);
+			break;
+		}
+		if (rc)
+			return -EFAULT;
+		*ppos += len;
+		ubuf += len;
+		todo -= len;
+	}
+
+	return count;
+}
+
+static ssize_t lpc_debug_write(struct file *filp, const char __user *ubuf,
+			       size_t count, loff_t *ppos)
+{
+	struct lpc_debugfs_entry *lpc = filp->private_data;
+	u32 data, pos, len, todo;
+	int rc;
+
+	if (!access_ok(VERIFY_READ, ubuf, count))
+		return -EFAULT;
+
+	todo = count;
+	while (todo) {
+		pos = *ppos;
+
+		/*
+		 * Select access size based on count and alignment and
+		 * access type. IO and MEM only support byte acceses,
+		 * FW supports all 3.
+		 */
+		len = 1;
+		if (lpc->lpc_type == OPAL_LPC_FW) {
+			if (todo > 3 && (pos & 3) == 0)
+				len = 4;
+			else if (todo > 1 && (pos & 1) == 0)
+				len = 2;
+		}
+		switch(len) {
+		case 4:
+			rc = __get_user(data, (u32 __user *)ubuf);
+			break;
+		case 2:
+			rc = __get_user(data, (u16 __user *)ubuf);
+			break;
+		default:
+			rc = __get_user(data, (u8 __user *)ubuf);
+			break;
+		}
+		if (rc)
+			return -EFAULT;
+
+		rc = opal_lpc_write(opal_lpc_chip_id, lpc->lpc_type, pos,
+				    data, len);
+		if (rc)
+			return -ENXIO;
+		*ppos += len;
+		ubuf += len;
+		todo -= len;
+	}
+
+	return count;
+}
+
+static const struct file_operations lpc_fops = {
+	.read =		lpc_debug_read,
+	.write =	lpc_debug_write,
+	.open =		simple_open,
+	.llseek =	default_llseek,
+};
+
+static int opal_lpc_debugfs_create_type(struct dentry *folder,
+					const char *fname,
+					enum OpalLPCAddressType type)
+{
+	struct lpc_debugfs_entry *entry;
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+	entry->lpc_type = type;
+	debugfs_create_file(fname, 0600, folder, entry, &lpc_fops);
+	return 0;
+}
+
+static int opal_lpc_init_debugfs(void)
+{
+	struct dentry *root;
+	int rc = 0;
+
+	if (opal_lpc_chip_id < 0)
+		return -ENODEV;
+
+	root = debugfs_create_dir("lpc", powerpc_debugfs_root);
+
+	rc |= opal_lpc_debugfs_create_type(root, "io", OPAL_LPC_IO);
+	rc |= opal_lpc_debugfs_create_type(root, "mem", OPAL_LPC_MEM);
+	rc |= opal_lpc_debugfs_create_type(root, "fw", OPAL_LPC_FW);
+	return rc;
+}
+device_initcall(opal_lpc_init_debugfs);
+#endif  /* CONFIG_DEBUG_FS */
+
 void opal_lpc_init(void)
 {
 	struct device_node *np;
diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c
index ec4132239cd..b17a34b695e 100644
--- a/arch/powerpc/platforms/powernv/opal-memory-errors.c
+++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c
@@ -47,12 +47,12 @@ static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt)
 		  __func__, merr_evt->type);
 	switch (merr_evt->type) {
 	case OPAL_MEM_ERR_TYPE_RESILIENCE:
-		paddr_start = merr_evt->u.resilience.physical_address_start;
-		paddr_end = merr_evt->u.resilience.physical_address_end;
+		paddr_start = be64_to_cpu(merr_evt->u.resilience.physical_address_start);
+		paddr_end = be64_to_cpu(merr_evt->u.resilience.physical_address_end);
 		break;
 	case OPAL_MEM_ERR_TYPE_DYN_DALLOC:
-		paddr_start = merr_evt->u.dyn_dealloc.physical_address_start;
-		paddr_end = merr_evt->u.dyn_dealloc.physical_address_end;
+		paddr_start = be64_to_cpu(merr_evt->u.dyn_dealloc.physical_address_start);
+		paddr_end = be64_to_cpu(merr_evt->u.dyn_dealloc.physical_address_end);
 		break;
 	default:
 		return;
diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c
index 1bb25b95250..44ed78af1a0 100644
--- a/arch/powerpc/platforms/powernv/opal-msglog.c
+++ b/arch/powerpc/platforms/powernv/opal-msglog.c
@@ -37,7 +37,8 @@ static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj,
 {
 	struct memcons *mc = bin_attr->private;
 	const char *conbuf;
-	size_t ret, first_read = 0;
+	ssize_t ret;
+	size_t first_read = 0;
 	uint32_t out_pos, avail;
 
 	if (!mc)
@@ -69,6 +70,9 @@ static ssize_t opal_msglog_read(struct file *file, struct kobject *kobj,
 		to += first_read;
 		count -= first_read;
 		pos -= avail;
+
+		if (count <= 0)
+			goto out;
 	}
 
 	/* Sanity check. The firmware should not do this to us. */
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index d202f9bc368..9d1acf22a09 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -260,10 +260,10 @@ void __init opal_sys_param_init(void)
 			attr[i].kobj_attr.attr.mode = S_IRUGO;
 			break;
 		case OPAL_SYSPARAM_WRITE:
-			attr[i].kobj_attr.attr.mode = S_IWUGO;
+			attr[i].kobj_attr.attr.mode = S_IWUSR;
 			break;
 		case OPAL_SYSPARAM_RW:
-			attr[i].kobj_attr.attr.mode = S_IRUGO | S_IWUGO;
+			attr[i].kobj_attr.attr.mode = S_IRUGO | S_IWUSR;
 			break;
 		default:
 			break;
diff --git a/arch/powerpc/platforms/powernv/opal-takeover.S b/arch/powerpc/platforms/powernv/opal-takeover.S
deleted file mode 100644
index 3cd262897c2..00000000000
--- a/arch/powerpc/platforms/powernv/opal-takeover.S
+++ /dev/null
@@ -1,138 +0,0 @@
-/*
- * PowerNV OPAL takeover assembly code, for use by prom_init.c
- *
- * Copyright 2011 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <asm/ppc_asm.h>
-#include <asm/hvcall.h>
-#include <asm/asm-offsets.h>
-#include <asm/opal.h>
-
-#define H_HAL_TAKEOVER			0x5124
-#define H_HAL_TAKEOVER_QUERY_MAGIC	-1
-
-	.text
-_GLOBAL(opal_query_takeover)
-	mfcr	r0
-	stw	r0,8(r1)
-	std	r3,STK_PARAM(R3)(r1)
-	std	r4,STK_PARAM(R4)(r1)
-	li	r3,H_HAL_TAKEOVER
-	li	r4,H_HAL_TAKEOVER_QUERY_MAGIC
-	HVSC
-	ld	r10,STK_PARAM(R3)(r1)
-	std	r4,0(r10)
-	ld	r10,STK_PARAM(R4)(r1)
-	std	r5,0(r10)
-	lwz	r0,8(r1)
-	mtcrf	0xff,r0
-	blr
-
-_GLOBAL(opal_do_takeover)
-	mfcr	r0
-	stw	r0,8(r1)
-	mflr	r0
-	std	r0,16(r1)
-	bl	__opal_do_takeover
-	ld	r0,16(r1)
-	mtlr	r0
-	lwz	r0,8(r1)
-	mtcrf	0xff,r0
-	blr
-
-__opal_do_takeover:
-	ld	r4,0(r3)
-	ld	r5,0x8(r3)
-	ld	r6,0x10(r3)
-	ld	r7,0x18(r3)
-	ld	r8,0x20(r3)
-	ld	r9,0x28(r3)
-	ld	r10,0x30(r3)
-	ld	r11,0x38(r3)
-	li	r3,H_HAL_TAKEOVER
-	HVSC
-	blr
-
-	.globl opal_secondary_entry
-opal_secondary_entry:
-	mr	r31,r3
-	mfmsr	r11
-	li	r12,(MSR_SF | MSR_ISF)@highest
-	sldi	r12,r12,48
-	or	r11,r11,r12
-	mtmsrd	r11
-	isync
-	mfspr	r4,SPRN_PIR
-	std	r4,0(r3)
-1:	HMT_LOW
-	ld	r4,8(r3)
-	cmpli	cr0,r4,0
-	beq	1b
-	HMT_MEDIUM
-1:	addi	r3,r31,16
-	bl	__opal_do_takeover
-	b	1b
-
-_GLOBAL(opal_enter_rtas)
-	mflr	r0
-	std	r0,16(r1)
-        stdu	r1,-PROM_FRAME_SIZE(r1)	/* Save SP and create stack space */
-
-	/* Because PROM is running in 32b mode, it clobbers the high order half
-	 * of all registers that it saves.  We therefore save those registers
-	 * PROM might touch to the stack.  (r0, r3-r13 are caller saved)
-	*/
-	SAVE_GPR(2, r1)
-	SAVE_GPR(13, r1)
-	SAVE_8GPRS(14, r1)
-	SAVE_10GPRS(22, r1)
-	mfcr	r10
-	mfmsr	r11
-	std	r10,_CCR(r1)
-	std	r11,_MSR(r1)
-
-	/* Get the PROM entrypoint */
-	mtlr	r5
-
-	/* Switch MSR to 32 bits mode
-	 */
-        li      r12,1
-        rldicr  r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
-        andc    r11,r11,r12
-        li      r12,1
-        rldicr  r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
-        andc    r11,r11,r12
-        mtmsrd  r11
-        isync
-
-	/* Enter RTAS here... */
-	blrl
-
-	/* Just make sure that r1 top 32 bits didn't get
-	 * corrupt by OF
-	 */
-	rldicl	r1,r1,0,32
-
-	/* Restore the MSR (back to 64 bits) */
-	ld	r0,_MSR(r1)
-	MTMSRD(r0)
-        isync
-
-	/* Restore other registers */
-	REST_GPR(2, r1)
-	REST_GPR(13, r1)
-	REST_8GPRS(14, r1)
-	REST_10GPRS(22, r1)
-	ld	r4,_CCR(r1)
-	mtcr	r4
-
-        addi	r1,r1,PROM_FRAME_SIZE
-	ld	r0,16(r1)
-	mtlr    r0
-	blr
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index f531ffe35b3..4abbff22a61 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -32,7 +32,7 @@
 	std	r12,PACASAVEDMSR(r13);	\
 	andc	r12,r12,r0;		\
 	mtmsrd	r12,1;			\
-	LOAD_REG_ADDR(r0,.opal_return);	\
+	LOAD_REG_ADDR(r0,opal_return);	\
 	mtlr	r0;			\
 	li	r0,MSR_DR|MSR_IR|MSR_LE;\
 	andc	r12,r12,r0;		\
@@ -44,7 +44,7 @@
 	mtspr	SPRN_HSRR0,r12;		\
 	hrfid
 
-_STATIC(opal_return)
+opal_return:
 	/*
 	 * Fixup endian on OPAL return... we should be able to simplify
 	 * this by instead converting the below trampoline to a set of
@@ -124,6 +124,7 @@ OPAL_CALL(opal_xscom_write,			OPAL_XSCOM_WRITE);
 OPAL_CALL(opal_lpc_read,			OPAL_LPC_READ);
 OPAL_CALL(opal_lpc_write,			OPAL_LPC_WRITE);
 OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
+OPAL_CALL(opal_reinit_cpus,			OPAL_REINIT_CPUS);
 OPAL_CALL(opal_read_elog,			OPAL_ELOG_READ);
 OPAL_CALL(opal_send_ack_elog,			OPAL_ELOG_ACK);
 OPAL_CALL(opal_get_elog_size,			OPAL_ELOG_SIZE);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index f343183add0..199975613fe 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -57,6 +57,21 @@ static DEFINE_SPINLOCK(opal_notifier_lock);
 static uint64_t last_notified_mask = 0x0ul;
 static atomic_t opal_notifier_hold = ATOMIC_INIT(0);
 
+static void opal_reinit_cores(void)
+{
+	/* Do the actual re-init, This will clobber all FPRs, VRs, etc...
+	 *
+	 * It will preserve non volatile GPRs and HSPRG0/1. It will
+	 * also restore HIDs and other SPRs to their original value
+	 * but it might clobber a bunch.
+	 */
+#ifdef __BIG_ENDIAN__
+	opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_BE);
+#else
+	opal_reinit_cpus(OPAL_REINIT_CPUS_HILE_LE);
+#endif
+}
+
 int __init early_init_dt_scan_opal(unsigned long node,
 				   const char *uname, int depth, void *data)
 {
@@ -96,6 +111,13 @@ int __init early_init_dt_scan_opal(unsigned long node,
 		printk("OPAL V1 detected !\n");
 	}
 
+	/* Reinit all cores with the right endian */
+	opal_reinit_cores();
+
+	/* Restore some bits */
+	if (cur_cpu_spec->cpu_restore)
+		cur_cpu_spec->cpu_restore();
+
 	return 1;
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 98824aa9917..de19edeaa7a 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -13,6 +13,7 @@
 
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/crash_dump.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/string.h>
@@ -663,15 +664,15 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 		 * errors, and on the first pass the data will be a relative
 		 * bus number, print that out instead.
 		 */
-		tbl->it_busno = 0;
 		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
 		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
 				8);
-		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE |
-			       TCE_PCI_SWINV_PAIR;
+		tbl->it_type |= (TCE_PCI_SWINV_CREATE |
+				 TCE_PCI_SWINV_FREE   |
+				 TCE_PCI_SWINV_PAIR);
 	}
 	iommu_init_table(tbl, phb->hose->node);
-	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
+	iommu_register_group(tbl, phb->hose->global_number, pe->pe_number);
 
 	if (pe->pdev)
 		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
@@ -793,14 +794,13 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 		 * errors, and on the first pass the data will be a relative
 		 * bus number, print that out instead.
 		 */
-		tbl->it_busno = 0;
 		pe->tce_inval_reg_phys = be64_to_cpup(swinvp);
 		tbl->it_index = (unsigned long)ioremap(pe->tce_inval_reg_phys,
 				8);
-		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
+		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
 	}
 	iommu_init_table(tbl, phb->hose->node);
-	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
+	iommu_register_group(tbl, phb->hose->global_number, pe->pe_number);
 
 	if (pe->pdev)
 		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
@@ -1386,12 +1386,24 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
 	ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
 	ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
+	ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus;
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
 	rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET);
 	if (rc)
 		pr_warning("  OPAL Error %ld performing IODA table reset !\n", rc);
+
+	/* If we're running in kdump kerenl, the previous kerenl never
+	 * shutdown PCI devices correctly. We already got IODA table
+	 * cleaned out. So we have to issue PHB reset to stop all PCI
+	 * transactions from previous kerenl.
+	 */
+	if (is_kdump_kernel()) {
+		pr_info("  Issue PHB reset ...\n");
+		ioda_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL);
+		ioda_eeh_phb_reset(hose, OPAL_DEASSERT_RESET);
+	}
 }
 
 void __init pnv_pci_init_ioda2_phb(struct device_node *np)
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 8518817dcdf..f91a4e5d872 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -131,65 +131,60 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
 	int i;
 
 	data = (struct OpalIoP7IOCPhbErrorData *)common;
-	pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
+	pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n",
 		hose->global_number, common->version);
 
 	if (data->brdgCtl)
-		pr_info("  brdgCtl:     %08x\n",
+		pr_info("brdgCtl:     %08x\n",
 			data->brdgCtl);
 	if (data->portStatusReg || data->rootCmplxStatus ||
 	    data->busAgentStatus)
-		pr_info("  UtlSts:      %08x %08x %08x\n",
+		pr_info("UtlSts:      %08x %08x %08x\n",
 			data->portStatusReg, data->rootCmplxStatus,
 			data->busAgentStatus);
 	if (data->deviceStatus || data->slotStatus   ||
 	    data->linkStatus   || data->devCmdStatus ||
 	    data->devSecStatus)
-		pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
+		pr_info("RootSts:     %08x %08x %08x %08x %08x\n",
 			data->deviceStatus, data->slotStatus,
 			data->linkStatus, data->devCmdStatus,
 			data->devSecStatus);
 	if (data->rootErrorStatus   || data->uncorrErrorStatus ||
 	    data->corrErrorStatus)
-		pr_info("  RootErrSts:  %08x %08x %08x\n",
+		pr_info("RootErrSts:  %08x %08x %08x\n",
 			data->rootErrorStatus, data->uncorrErrorStatus,
 			data->corrErrorStatus);
 	if (data->tlpHdr1 || data->tlpHdr2 ||
 	    data->tlpHdr3 || data->tlpHdr4)
-		pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
+		pr_info("RootErrLog:  %08x %08x %08x %08x\n",
 			data->tlpHdr1, data->tlpHdr2,
 			data->tlpHdr3, data->tlpHdr4);
 	if (data->sourceId || data->errorClass ||
 	    data->correlator)
-		pr_info("  RootErrLog1: %08x %016llx %016llx\n",
+		pr_info("RootErrLog1: %08x %016llx %016llx\n",
 			data->sourceId, data->errorClass,
 			data->correlator);
 	if (data->p7iocPlssr || data->p7iocCsr)
-		pr_info("  PhbSts:      %016llx %016llx\n",
+		pr_info("PhbSts:      %016llx %016llx\n",
 			data->p7iocPlssr, data->p7iocCsr);
-	if (data->lemFir || data->lemErrorMask ||
-	    data->lemWOF)
-		pr_info("  Lem:         %016llx %016llx %016llx\n",
+	if (data->lemFir)
+		pr_info("Lem:         %016llx %016llx %016llx\n",
 			data->lemFir, data->lemErrorMask,
 			data->lemWOF);
-	if (data->phbErrorStatus || data->phbFirstErrorStatus ||
-	    data->phbErrorLog0   || data->phbErrorLog1)
-		pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
+	if (data->phbErrorStatus)
+		pr_info("PhbErr:      %016llx %016llx %016llx %016llx\n",
 			data->phbErrorStatus, data->phbFirstErrorStatus,
 			data->phbErrorLog0, data->phbErrorLog1);
-	if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
-	    data->mmioErrorLog0   || data->mmioErrorLog1)
-		pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
+	if (data->mmioErrorStatus)
+		pr_info("OutErr:      %016llx %016llx %016llx %016llx\n",
 			data->mmioErrorStatus, data->mmioFirstErrorStatus,
 			data->mmioErrorLog0, data->mmioErrorLog1);
-	if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
-	    data->dma0ErrorLog0   || data->dma0ErrorLog1)
-		pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
+	if (data->dma0ErrorStatus)
+		pr_info("InAErr:      %016llx %016llx %016llx %016llx\n",
 			data->dma0ErrorStatus, data->dma0FirstErrorStatus,
 			data->dma0ErrorLog0, data->dma0ErrorLog1);
-	if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
-	    data->dma1ErrorLog0   || data->dma1ErrorLog1)
-		pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
+	if (data->dma1ErrorStatus)
+		pr_info("InBErr:      %016llx %016llx %016llx %016llx\n",
 			data->dma1ErrorStatus, data->dma1FirstErrorStatus,
 			data->dma1ErrorLog0, data->dma1ErrorLog1);
 
@@ -198,7 +193,7 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
 		    (data->pestB[i] >> 63) == 0)
 			continue;
 
-		pr_info("  PE[%3d] A/B: %016llx %016llx\n",
+		pr_info("PE[%3d] A/B: %016llx %016llx\n",
 			i, data->pestA[i], data->pestB[i]);
 	}
 }
@@ -210,79 +205,92 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose,
 	int i;
 
 	data = (struct OpalIoPhb3ErrorData*)common;
-	pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
-		hose->global_number, common->version);
+	pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n",
+		hose->global_number, be32_to_cpu(common->version));
 	if (data->brdgCtl)
-		pr_info("  brdgCtl:     %08x\n",
-			data->brdgCtl);
+		pr_info("brdgCtl:     %08x\n",
+			be32_to_cpu(data->brdgCtl));
 	if (data->portStatusReg || data->rootCmplxStatus ||
 	    data->busAgentStatus)
-		pr_info("  UtlSts:      %08x %08x %08x\n",
-			data->portStatusReg, data->rootCmplxStatus,
-			data->busAgentStatus);
+		pr_info("UtlSts:      %08x %08x %08x\n",
+			be32_to_cpu(data->portStatusReg),
+			be32_to_cpu(data->rootCmplxStatus),
+			be32_to_cpu(data->busAgentStatus));
 	if (data->deviceStatus || data->slotStatus   ||
 	    data->linkStatus   || data->devCmdStatus ||
 	    data->devSecStatus)
-		pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
-			data->deviceStatus, data->slotStatus,
-			data->linkStatus, data->devCmdStatus,
-			data->devSecStatus);
+		pr_info("RootSts:     %08x %08x %08x %08x %08x\n",
+			be32_to_cpu(data->deviceStatus),
+			be32_to_cpu(data->slotStatus),
+			be32_to_cpu(data->linkStatus),
+			be32_to_cpu(data->devCmdStatus),
+			be32_to_cpu(data->devSecStatus));
 	if (data->rootErrorStatus || data->uncorrErrorStatus ||
 	    data->corrErrorStatus)
-		pr_info("  RootErrSts:  %08x %08x %08x\n",
-			data->rootErrorStatus, data->uncorrErrorStatus,
-			data->corrErrorStatus);
+		pr_info("RootErrSts:  %08x %08x %08x\n",
+			be32_to_cpu(data->rootErrorStatus),
+			be32_to_cpu(data->uncorrErrorStatus),
+			be32_to_cpu(data->corrErrorStatus));
 	if (data->tlpHdr1 || data->tlpHdr2 ||
 	    data->tlpHdr3 || data->tlpHdr4)
-		pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
-			data->tlpHdr1, data->tlpHdr2,
-			data->tlpHdr3, data->tlpHdr4);
+		pr_info("RootErrLog:  %08x %08x %08x %08x\n",
+			be32_to_cpu(data->tlpHdr1),
+			be32_to_cpu(data->tlpHdr2),
+			be32_to_cpu(data->tlpHdr3),
+			be32_to_cpu(data->tlpHdr4));
 	if (data->sourceId || data->errorClass ||
 	    data->correlator)
-		pr_info("  RootErrLog1: %08x %016llx %016llx\n",
-			data->sourceId, data->errorClass,
-			data->correlator);
-	if (data->nFir || data->nFirMask ||
-	    data->nFirWOF)
-		pr_info("  nFir:        %016llx %016llx %016llx\n",
-			data->nFir, data->nFirMask,
-			data->nFirWOF);
+		pr_info("RootErrLog1: %08x %016llx %016llx\n",
+			be32_to_cpu(data->sourceId),
+			be64_to_cpu(data->errorClass),
+			be64_to_cpu(data->correlator));
+	if (data->nFir)
+		pr_info("nFir:        %016llx %016llx %016llx\n",
+			be64_to_cpu(data->nFir),
+			be64_to_cpu(data->nFirMask),
+			be64_to_cpu(data->nFirWOF));
 	if (data->phbPlssr || data->phbCsr)
-		pr_info("  PhbSts:      %016llx %016llx\n",
-			data->phbPlssr, data->phbCsr);
-	if (data->lemFir || data->lemErrorMask ||
-	    data->lemWOF)
-		pr_info("  Lem:         %016llx %016llx %016llx\n",
-			data->lemFir, data->lemErrorMask,
-			data->lemWOF);
-	if (data->phbErrorStatus || data->phbFirstErrorStatus ||
-	    data->phbErrorLog0   || data->phbErrorLog1)
-		pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
-			data->phbErrorStatus, data->phbFirstErrorStatus,
-			data->phbErrorLog0, data->phbErrorLog1);
-	if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
-	    data->mmioErrorLog0   || data->mmioErrorLog1)
-		pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
-			data->mmioErrorStatus, data->mmioFirstErrorStatus,
-			data->mmioErrorLog0, data->mmioErrorLog1);
-	if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
-	    data->dma0ErrorLog0   || data->dma0ErrorLog1)
-		pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
-			data->dma0ErrorStatus, data->dma0FirstErrorStatus,
-			data->dma0ErrorLog0, data->dma0ErrorLog1);
-	if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
-	    data->dma1ErrorLog0   || data->dma1ErrorLog1)
-		pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
-			data->dma1ErrorStatus, data->dma1FirstErrorStatus,
-			data->dma1ErrorLog0, data->dma1ErrorLog1);
+		pr_info("PhbSts:      %016llx %016llx\n",
+			be64_to_cpu(data->phbPlssr),
+			be64_to_cpu(data->phbCsr));
+	if (data->lemFir)
+		pr_info("Lem:         %016llx %016llx %016llx\n",
+			be64_to_cpu(data->lemFir),
+			be64_to_cpu(data->lemErrorMask),
+			be64_to_cpu(data->lemWOF));
+	if (data->phbErrorStatus)
+		pr_info("PhbErr:      %016llx %016llx %016llx %016llx\n",
+			be64_to_cpu(data->phbErrorStatus),
+			be64_to_cpu(data->phbFirstErrorStatus),
+			be64_to_cpu(data->phbErrorLog0),
+			be64_to_cpu(data->phbErrorLog1));
+	if (data->mmioErrorStatus)
+		pr_info("OutErr:      %016llx %016llx %016llx %016llx\n",
+			be64_to_cpu(data->mmioErrorStatus),
+			be64_to_cpu(data->mmioFirstErrorStatus),
+			be64_to_cpu(data->mmioErrorLog0),
+			be64_to_cpu(data->mmioErrorLog1));
+	if (data->dma0ErrorStatus)
+		pr_info("InAErr:      %016llx %016llx %016llx %016llx\n",
+			be64_to_cpu(data->dma0ErrorStatus),
+			be64_to_cpu(data->dma0FirstErrorStatus),
+			be64_to_cpu(data->dma0ErrorLog0),
+			be64_to_cpu(data->dma0ErrorLog1));
+	if (data->dma1ErrorStatus)
+		pr_info("InBErr:      %016llx %016llx %016llx %016llx\n",
+			be64_to_cpu(data->dma1ErrorStatus),
+			be64_to_cpu(data->dma1FirstErrorStatus),
+			be64_to_cpu(data->dma1ErrorLog0),
+			be64_to_cpu(data->dma1ErrorLog1));
 
 	for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
-		if ((data->pestA[i] >> 63) == 0 &&
-		    (data->pestB[i] >> 63) == 0)
+		if ((be64_to_cpu(data->pestA[i]) >> 63) == 0 &&
+		    (be64_to_cpu(data->pestB[i]) >> 63) == 0)
 			continue;
 
-		pr_info("  PE[%3d] A/B: %016llx %016llx\n",
-			i, data->pestA[i], data->pestB[i]);
+		pr_info("PE[%3d] A/B: %016llx %016llx\n",
+				i, be64_to_cpu(data->pestA[i]),
+				be64_to_cpu(data->pestB[i]));
 	}
 }
 
@@ -295,7 +303,7 @@ void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
 		return;
 
 	common = (struct OpalIoPhbErrorCommon *)log_buff;
-	switch (common->ioType) {
+	switch (be32_to_cpu(common->ioType)) {
 	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
 		pnv_pci_dump_p7ioc_diag_data(hose, common);
 		break;
@@ -304,7 +312,7 @@ void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
 		break;
 	default:
 		pr_warn("%s: Unrecognized ioType %d\n",
-			__func__, common->ioType);
+			__func__, be32_to_cpu(common->ioType));
 	}
 }
 
@@ -384,9 +392,6 @@ int pnv_pci_cfg_read(struct device_node *dn,
 	struct pci_dn *pdn = PCI_DN(dn);
 	struct pnv_phb *phb = pdn->phb->private_data;
 	u32 bdfn = (pdn->busno << 8) | pdn->devfn;
-#ifdef CONFIG_EEH
-	struct eeh_pe *phb_pe = NULL;
-#endif
 	s64 rc;
 
 	switch (size) {
@@ -412,31 +417,9 @@ int pnv_pci_cfg_read(struct device_node *dn,
 	default:
 		return PCIBIOS_FUNC_NOT_SUPPORTED;
 	}
+
 	cfg_dbg("%s: bus: %x devfn: %x +%x/%x -> %08x\n",
 		__func__, pdn->busno, pdn->devfn, where, size, *val);
-
-	/*
-	 * Check if the specified PE has been put into frozen
-	 * state. On the other hand, we needn't do that while
-	 * the PHB has been put into frozen state because of
-	 * PHB-fatal errors.
-	 */
-#ifdef CONFIG_EEH
-	phb_pe = eeh_phb_pe_get(pdn->phb);
-	if (phb_pe && (phb_pe->state & EEH_PE_ISOLATED))
-		return PCIBIOS_SUCCESSFUL;
-
-	if (phb->eeh_state & PNV_EEH_STATE_ENABLED) {
-		if (*val == EEH_IO_ERROR_VALUE(size) &&
-		    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
-			return PCIBIOS_DEVICE_NOT_FOUND;
-	} else {
-		pnv_pci_config_check_eeh(phb, dn);
-	}
-#else
-	pnv_pci_config_check_eeh(phb, dn);
-#endif
-
 	return PCIBIOS_SUCCESSFUL;
 }
 
@@ -463,33 +446,74 @@ int pnv_pci_cfg_write(struct device_node *dn,
 		return PCIBIOS_FUNC_NOT_SUPPORTED;
 	}
 
-	/* Check if the PHB got frozen due to an error (no response) */
-#ifdef CONFIG_EEH
-	if (!(phb->eeh_state & PNV_EEH_STATE_ENABLED))
-		pnv_pci_config_check_eeh(phb, dn);
-#else
-	pnv_pci_config_check_eeh(phb, dn);
-#endif
-
 	return PCIBIOS_SUCCESSFUL;
 }
 
+#if CONFIG_EEH
+static bool pnv_pci_cfg_check(struct pci_controller *hose,
+			      struct device_node *dn)
+{
+	struct eeh_dev *edev = NULL;
+	struct pnv_phb *phb = hose->private_data;
+
+	/* EEH not enabled ? */
+	if (!(phb->flags & PNV_PHB_FLAG_EEH))
+		return true;
+
+	/* PE reset or device removed ? */
+	edev = of_node_to_eeh_dev(dn);
+	if (edev) {
+		if (edev->pe &&
+		    (edev->pe->state & EEH_PE_RESET))
+			return false;
+
+		if (edev->mode & EEH_DEV_REMOVED)
+			return false;
+	}
+
+	return true;
+}
+#else
+static inline pnv_pci_cfg_check(struct pci_controller *hose,
+				struct device_node *dn)
+{
+	return true;
+}
+#endif /* CONFIG_EEH */
+
 static int pnv_pci_read_config(struct pci_bus *bus,
 			       unsigned int devfn,
 			       int where, int size, u32 *val)
 {
 	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
 	struct pci_dn *pdn;
+	struct pnv_phb *phb;
+	bool found = false;
+	int ret;
 
+	*val = 0xFFFFFFFF;
 	for (dn = busdn->child; dn; dn = dn->sibling) {
 		pdn = PCI_DN(dn);
-		if (pdn && pdn->devfn == devfn)
-			return pnv_pci_cfg_read(dn, where, size, val);
+		if (pdn && pdn->devfn == devfn) {
+			phb = pdn->phb->private_data;
+			found = true;
+			break;
+		}
 	}
 
-	*val = 0xFFFFFFFF;
-	return PCIBIOS_DEVICE_NOT_FOUND;
+	if (!found || !pnv_pci_cfg_check(pdn->phb, dn))
+		return PCIBIOS_DEVICE_NOT_FOUND;
 
+	ret = pnv_pci_cfg_read(dn, where, size, val);
+	if (phb->flags & PNV_PHB_FLAG_EEH) {
+		if (*val == EEH_IO_ERROR_VALUE(size) &&
+		    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+                        return PCIBIOS_DEVICE_NOT_FOUND;
+	} else {
+		pnv_pci_config_check_eeh(phb, dn);
+	}
+
+	return ret;
 }
 
 static int pnv_pci_write_config(struct pci_bus *bus,
@@ -498,14 +522,27 @@ static int pnv_pci_write_config(struct pci_bus *bus,
 {
 	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
 	struct pci_dn *pdn;
+	struct pnv_phb *phb;
+	bool found = false;
+	int ret;
 
 	for (dn = busdn->child; dn; dn = dn->sibling) {
 		pdn = PCI_DN(dn);
-		if (pdn && pdn->devfn == devfn)
-			return pnv_pci_cfg_write(dn, where, size, val);
+		if (pdn && pdn->devfn == devfn) {
+			phb = pdn->phb->private_data;
+			found = true;
+			break;
+		}
 	}
 
-	return PCIBIOS_DEVICE_NOT_FOUND;
+	if (!found || !pnv_pci_cfg_check(pdn->phb, dn))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	ret = pnv_pci_cfg_write(dn, where, size, val);
+	if (!(phb->flags & PNV_PHB_FLAG_EEH))
+		pnv_pci_config_check_eeh(phb, dn);
+
+	return ret;
 }
 
 struct pci_ops pnv_pci_ops = {
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index cde16944277..676232c3432 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -81,28 +81,27 @@ struct pnv_eeh_ops {
 	int (*configure_bridge)(struct eeh_pe *pe);
 	int (*next_error)(struct eeh_pe **pe);
 };
-
-#define PNV_EEH_STATE_ENABLED	(1 << 0)	/* EEH enabled	*/
-#define PNV_EEH_STATE_REMOVED	(1 << 1)	/* PHB removed	*/
-
 #endif /* CONFIG_EEH */
 
+#define PNV_PHB_FLAG_EEH	(1 << 0)
+
 struct pnv_phb {
 	struct pci_controller	*hose;
 	enum pnv_phb_type	type;
 	enum pnv_phb_model	model;
 	u64			hub_id;
 	u64			opal_id;
+	int			flags;
 	void __iomem		*regs;
 	int			initialized;
 	spinlock_t		lock;
 
 #ifdef CONFIG_EEH
 	struct pnv_eeh_ops	*eeh_ops;
-	int			eeh_state;
 #endif
 
 #ifdef CONFIG_DEBUG_FS
+	int			has_dbgfs;
 	struct dentry		*dbgfs;
 #endif
 
@@ -205,5 +204,7 @@ extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
 					__be64 *startp, __be64 *endp, bool rm);
+extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
+extern int ioda_eeh_phb_reset(struct pci_controller *hose, int option);
 
 #endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 0051e108ef0..75501bfede7 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -25,4 +25,6 @@ static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 
 extern void pnv_lpc_init(void);
 
+bool cpu_core_split_required(void);
+
 #endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 8723d32632f..d9b88fa7c5a 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -27,6 +27,7 @@
 #include <linux/interrupt.h>
 #include <linux/bug.h>
 #include <linux/pci.h>
+#include <linux/cpufreq.h>
 
 #include <asm/machdep.h>
 #include <asm/firmware.h>
@@ -34,11 +35,14 @@
 #include <asm/rtas.h>
 #include <asm/opal.h>
 #include <asm/kexec.h>
+#include <asm/smp.h>
 
 #include "powernv.h"
 
 static void __init pnv_setup_arch(void)
 {
+	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
+
 	/* Initialize SMP */
 	pnv_smp_init();
 
@@ -98,11 +102,32 @@ static void pnv_show_cpuinfo(struct seq_file *m)
 	of_node_put(root);
 }
 
+static void pnv_prepare_going_down(void)
+{
+	/*
+	 * Disable all notifiers from OPAL, we can't
+	 * service interrupts anymore anyway
+	 */
+	opal_notifier_disable();
+
+	/* Soft disable interrupts */
+	local_irq_disable();
+
+	/*
+	 * Return secondary CPUs to firwmare if a flash update
+	 * is pending otherwise we will get all sort of error
+	 * messages about CPU being stuck etc.. This will also
+	 * have the side effect of hard disabling interrupts so
+	 * past this point, the kernel is effectively dead.
+	 */
+	opal_flash_term_callback();
+}
+
 static void  __noreturn pnv_restart(char *cmd)
 {
 	long rc = OPAL_BUSY;
 
-	opal_notifier_disable();
+	pnv_prepare_going_down();
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_cec_reboot();
@@ -119,7 +144,7 @@ static void __noreturn pnv_power_off(void)
 {
 	long rc = OPAL_BUSY;
 
-	opal_notifier_disable();
+	pnv_prepare_going_down();
 
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_cec_power_down(0);
@@ -222,6 +247,13 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 }
 #endif /* CONFIG_KEXEC */
 
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+static unsigned long pnv_memory_block_size(void)
+{
+	return 256UL * 1024 * 1024;
+}
+#endif
+
 static void __init pnv_setup_machdep_opal(void)
 {
 	ppc_md.get_boot_time = opal_get_boot_time;
@@ -269,6 +301,25 @@ static int __init pnv_probe(void)
 	return 1;
 }
 
+/*
+ * Returns the cpu frequency for 'cpu' in Hz. This is used by
+ * /proc/cpuinfo
+ */
+unsigned long pnv_get_proc_freq(unsigned int cpu)
+{
+	unsigned long ret_freq;
+
+	ret_freq = cpufreq_quick_get(cpu) * 1000ul;
+
+	/*
+	 * If the backend cpufreq driver does not exist,
+         * then fallback to old way of reporting the clockrate.
+	 */
+	if (!ret_freq)
+		ret_freq = ppc_proc_freq;
+	return ret_freq;
+}
+
 define_machine(powernv) {
 	.name			= "PowerNV",
 	.probe			= pnv_probe,
@@ -276,6 +327,7 @@ define_machine(powernv) {
 	.setup_arch		= pnv_setup_arch,
 	.init_IRQ		= pnv_init_IRQ,
 	.show_cpuinfo		= pnv_show_cpuinfo,
+	.get_proc_freq          = pnv_get_proc_freq,
 	.progress		= pnv_progress,
 	.machine_shutdown	= pnv_shutdown,
 	.power_save             = power7_idle,
@@ -284,4 +336,7 @@ define_machine(powernv) {
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+	.memory_block_size	= pnv_memory_block_size,
+#endif
 };
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index bf5fcd45216..5fcfcf44e3a 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -31,6 +31,8 @@
 #include <asm/xics.h>
 #include <asm/opal.h>
 #include <asm/runlatch.h>
+#include <asm/code-patching.h>
+#include <asm/dbell.h>
 
 #include "powernv.h"
 
@@ -45,13 +47,18 @@ static void pnv_smp_setup_cpu(int cpu)
 {
 	if (cpu != boot_cpuid)
 		xics_setup_cpu();
+
+#ifdef CONFIG_PPC_DOORBELL
+	if (cpu_has_feature(CPU_FTR_DBELL))
+		doorbell_setup_this_cpu();
+#endif
 }
 
 int pnv_smp_kick_cpu(int nr)
 {
 	unsigned int pcpu = get_hard_smp_processor_id(nr);
-	unsigned long start_here = __pa(*((unsigned long *)
-					  generic_secondary_smp_init));
+	unsigned long start_here =
+			__pa(ppc_function_entry(generic_secondary_smp_init));
 	long rc;
 
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
@@ -158,17 +165,19 @@ static void pnv_smp_cpu_kill_self(void)
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
 		ppc64_runlatch_off();
-		power7_nap();
+		power7_nap(1);
 		ppc64_runlatch_on();
-		if (!generic_check_cpu_restart(cpu)) {
+
+		/* Reenable IRQs briefly to clear the IPI that woke us */
+		local_irq_enable();
+		local_irq_disable();
+		mb();
+
+		if (cpu_core_split_required())
+			continue;
+
+		if (!generic_check_cpu_restart(cpu))
 			DBG("CPU%d Unexpected exit while offline !\n", cpu);
-			/* We may be getting an IPI, so we re-enable
-			 * interrupts to process it, it will be ignored
-			 * since we aren't online (hopefully)
-			 */
-			local_irq_enable();
-			local_irq_disable();
-		}
 	}
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1);
 	DBG("CPU%d coming online...\n", cpu);
diff --git a/arch/powerpc/platforms/powernv/subcore-asm.S b/arch/powerpc/platforms/powernv/subcore-asm.S
new file mode 100644
index 00000000000..39bb24aa8f3
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/subcore-asm.S
@@ -0,0 +1,95 @@
+/*
+ * Copyright 2013, Michael (Ellerman|Neuling), IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
+#include <asm/reg.h>
+
+#include "subcore.h"
+
+
+_GLOBAL(split_core_secondary_loop)
+	/*
+	 * r3 = u8 *state, used throughout the routine
+	 * r4 = temp
+	 * r5 = temp
+	 * ..
+	 * r12 = MSR
+	 */
+	mfmsr	r12
+
+	/* Disable interrupts so SRR0/1 don't get trashed */
+	li	r4,0
+	ori	r4,r4,MSR_EE|MSR_SE|MSR_BE|MSR_RI
+	andc	r4,r12,r4
+	sync
+	mtmsrd	r4
+
+	/* Switch to real mode and leave interrupts off */
+	li	r5, MSR_IR|MSR_DR
+	andc	r5, r4, r5
+
+	LOAD_REG_ADDR(r4, real_mode)
+
+	mtspr	SPRN_SRR0,r4
+	mtspr	SPRN_SRR1,r5
+	rfid
+	b	.	/* prevent speculative execution */
+
+real_mode:
+	/* Grab values from unsplit SPRs */
+	mfspr	r6,  SPRN_LDBAR
+	mfspr	r7,  SPRN_PMMAR
+	mfspr	r8,  SPRN_PMCR
+	mfspr	r9,  SPRN_RPR
+	mfspr	r10, SPRN_SDR1
+
+	/* Order reading the SPRs vs telling the primary we are ready to split */
+	sync
+
+	/* Tell thread 0 we are in real mode */
+	li	r4, SYNC_STEP_REAL_MODE
+	stb	r4, 0(r3)
+
+	li	r5, (HID0_POWER8_4LPARMODE | HID0_POWER8_2LPARMODE)@highest
+	sldi	r5, r5, 48
+
+	/* Loop until we see the split happen in HID0 */
+1:	mfspr	r4, SPRN_HID0
+	and.	r4, r4, r5
+	beq	1b
+
+	/*
+	 * We only need to initialise the below regs once for each subcore,
+	 * but it's simpler and harmless to do it on each thread.
+	 */
+
+	/* Make sure various SPRS have sane values */
+	li	r4, 0
+	mtspr	SPRN_LPID, r4
+	mtspr	SPRN_PCR, r4
+	mtspr	SPRN_HDEC, r4
+
+	/* Restore SPR values now we are split */
+	mtspr	SPRN_LDBAR, r6
+	mtspr	SPRN_PMMAR, r7
+	mtspr	SPRN_PMCR, r8
+	mtspr	SPRN_RPR, r9
+	mtspr	SPRN_SDR1, r10
+
+	LOAD_REG_ADDR(r5, virtual_mode)
+
+	/* Get out of real mode */
+	mtspr	SPRN_SRR0,r5
+	mtspr	SPRN_SRR1,r12
+	rfid
+	b	.	/* prevent speculative execution */
+
+virtual_mode:
+	blr
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
new file mode 100644
index 00000000000..894ecb3eb59
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -0,0 +1,392 @@
+/*
+ * Copyright 2013, Michael (Ellerman|Neuling), IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt)	"powernv: " fmt
+
+#include <linux/kernel.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/gfp.h>
+#include <linux/smp.h>
+#include <linux/stop_machine.h>
+
+#include <asm/cputhreads.h>
+#include <asm/kvm_ppc.h>
+#include <asm/machdep.h>
+#include <asm/opal.h>
+#include <asm/smp.h>
+
+#include "subcore.h"
+
+
+/*
+ * Split/unsplit procedure:
+ *
+ * A core can be in one of three states, unsplit, 2-way split, and 4-way split.
+ *
+ * The mapping to subcores_per_core is simple:
+ *
+ *  State       | subcores_per_core
+ *  ------------|------------------
+ *  Unsplit     |        1
+ *  2-way split |        2
+ *  4-way split |        4
+ *
+ * The core is split along thread boundaries, the mapping between subcores and
+ * threads is as follows:
+ *
+ *  Unsplit:
+ *          ----------------------------
+ *  Subcore |            0             |
+ *          ----------------------------
+ *  Thread  |  0  1  2  3  4  5  6  7  |
+ *          ----------------------------
+ *
+ *  2-way split:
+ *          -------------------------------------
+ *  Subcore |        0        |        1        |
+ *          -------------------------------------
+ *  Thread  |  0   1   2   3  |  4   5   6   7  |
+ *          -------------------------------------
+ *
+ *  4-way split:
+ *          -----------------------------------------
+ *  Subcore |    0    |    1    |    2    |    3    |
+ *          -----------------------------------------
+ *  Thread  |  0   1  |  2   3  |  4   5  |  6   7  |
+ *          -----------------------------------------
+ *
+ *
+ * Transitions
+ * -----------
+ *
+ * It is not possible to transition between either of the split states, the
+ * core must first be unsplit. The legal transitions are:
+ *
+ *  -----------          ---------------
+ *  |         |  <---->  | 2-way split |
+ *  |         |          ---------------
+ *  | Unsplit |
+ *  |         |          ---------------
+ *  |         |  <---->  | 4-way split |
+ *  -----------          ---------------
+ *
+ * Unsplitting
+ * -----------
+ *
+ * Unsplitting is the simpler procedure. It requires thread 0 to request the
+ * unsplit while all other threads NAP.
+ *
+ * Thread 0 clears HID0_POWER8_DYNLPARDIS (Dynamic LPAR Disable). This tells
+ * the hardware that if all threads except 0 are napping, the hardware should
+ * unsplit the core.
+ *
+ * Non-zero threads are sent to a NAP loop, they don't exit the loop until they
+ * see the core unsplit.
+ *
+ * Core 0 spins waiting for the hardware to see all the other threads napping
+ * and perform the unsplit.
+ *
+ * Once thread 0 sees the unsplit, it IPIs the secondary threads to wake them
+ * out of NAP. They will then see the core unsplit and exit the NAP loop.
+ *
+ * Splitting
+ * ---------
+ *
+ * The basic splitting procedure is fairly straight forward. However it is
+ * complicated by the fact that after the split occurs, the newly created
+ * subcores are not in a fully initialised state.
+ *
+ * Most notably the subcores do not have the correct value for SDR1, which
+ * means they must not be running in virtual mode when the split occurs. The
+ * subcores have separate timebases SPRs but these are pre-synchronised by
+ * opal.
+ *
+ * To begin with secondary threads are sent to an assembly routine. There they
+ * switch to real mode, so they are immune to the uninitialised SDR1 value.
+ * Once in real mode they indicate that they are in real mode, and spin waiting
+ * to see the core split.
+ *
+ * Thread 0 waits to see that all secondaries are in real mode, and then begins
+ * the splitting procedure. It firstly sets HID0_POWER8_DYNLPARDIS, which
+ * prevents the hardware from unsplitting. Then it sets the appropriate HID bit
+ * to request the split, and spins waiting to see that the split has happened.
+ *
+ * Concurrently the secondaries will notice the split. When they do they set up
+ * their SPRs, notably SDR1, and then they can return to virtual mode and exit
+ * the procedure.
+ */
+
+/* Initialised at boot by subcore_init() */
+static int subcores_per_core;
+
+/*
+ * Used to communicate to offline cpus that we want them to pop out of the
+ * offline loop and do a split or unsplit.
+ *
+ * 0 - no split happening
+ * 1 - unsplit in progress
+ * 2 - split to 2 in progress
+ * 4 - split to 4 in progress
+ */
+static int new_split_mode;
+
+static cpumask_var_t cpu_offline_mask;
+
+struct split_state {
+	u8 step;
+	u8 master;
+};
+
+static DEFINE_PER_CPU(struct split_state, split_state);
+
+static void wait_for_sync_step(int step)
+{
+	int i, cpu = smp_processor_id();
+
+	for (i = cpu + 1; i < cpu + threads_per_core; i++)
+		while(per_cpu(split_state, i).step < step)
+			barrier();
+
+	/* Order the wait loop vs any subsequent loads/stores. */
+	mb();
+}
+
+static void unsplit_core(void)
+{
+	u64 hid0, mask;
+	int i, cpu;
+
+	mask = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE;
+
+	cpu = smp_processor_id();
+	if (cpu_thread_in_core(cpu) != 0) {
+		while (mfspr(SPRN_HID0) & mask)
+			power7_nap(0);
+
+		per_cpu(split_state, cpu).step = SYNC_STEP_UNSPLIT;
+		return;
+	}
+
+	hid0 = mfspr(SPRN_HID0);
+	hid0 &= ~HID0_POWER8_DYNLPARDIS;
+	mtspr(SPRN_HID0, hid0);
+
+	while (mfspr(SPRN_HID0) & mask)
+		cpu_relax();
+
+	/* Wake secondaries out of NAP */
+	for (i = cpu + 1; i < cpu + threads_per_core; i++)
+		smp_send_reschedule(i);
+
+	wait_for_sync_step(SYNC_STEP_UNSPLIT);
+}
+
+static void split_core(int new_mode)
+{
+	struct {  u64 value; u64 mask; } split_parms[2] = {
+		{ HID0_POWER8_1TO2LPAR, HID0_POWER8_2LPARMODE },
+		{ HID0_POWER8_1TO4LPAR, HID0_POWER8_4LPARMODE }
+	};
+	int i, cpu;
+	u64 hid0;
+
+	/* Convert new_mode (2 or 4) into an index into our parms array */
+	i = (new_mode >> 1) - 1;
+	BUG_ON(i < 0 || i > 1);
+
+	cpu = smp_processor_id();
+	if (cpu_thread_in_core(cpu) != 0) {
+		split_core_secondary_loop(&per_cpu(split_state, cpu).step);
+		return;
+	}
+
+	wait_for_sync_step(SYNC_STEP_REAL_MODE);
+
+	/* Write new mode */
+	hid0  = mfspr(SPRN_HID0);
+	hid0 |= HID0_POWER8_DYNLPARDIS | split_parms[i].value;
+	mtspr(SPRN_HID0, hid0);
+
+	/* Wait for it to happen */
+	while (!(mfspr(SPRN_HID0) & split_parms[i].mask))
+		cpu_relax();
+}
+
+static void cpu_do_split(int new_mode)
+{
+	/*
+	 * At boot subcores_per_core will be 0, so we will always unsplit at
+	 * boot. In the usual case where the core is already unsplit it's a
+	 * nop, and this just ensures the kernel's notion of the mode is
+	 * consistent with the hardware.
+	 */
+	if (subcores_per_core != 1)
+		unsplit_core();
+
+	if (new_mode != 1)
+		split_core(new_mode);
+
+	mb();
+	per_cpu(split_state, smp_processor_id()).step = SYNC_STEP_FINISHED;
+}
+
+bool cpu_core_split_required(void)
+{
+	smp_rmb();
+
+	if (!new_split_mode)
+		return false;
+
+	cpu_do_split(new_split_mode);
+
+	return true;
+}
+
+static int cpu_update_split_mode(void *data)
+{
+	int cpu, new_mode = *(int *)data;
+
+	if (this_cpu_ptr(&split_state)->master) {
+		new_split_mode = new_mode;
+		smp_wmb();
+
+		cpumask_andnot(cpu_offline_mask, cpu_present_mask,
+			       cpu_online_mask);
+
+		/* This should work even though the cpu is offline */
+		for_each_cpu(cpu, cpu_offline_mask)
+			smp_send_reschedule(cpu);
+	}
+
+	cpu_do_split(new_mode);
+
+	if (this_cpu_ptr(&split_state)->master) {
+		/* Wait for all cpus to finish before we touch subcores_per_core */
+		for_each_present_cpu(cpu) {
+			if (cpu >= setup_max_cpus)
+				break;
+
+			while(per_cpu(split_state, cpu).step < SYNC_STEP_FINISHED)
+				barrier();
+		}
+
+		new_split_mode = 0;
+
+		/* Make the new mode public */
+		subcores_per_core = new_mode;
+		threads_per_subcore = threads_per_core / subcores_per_core;
+
+		/* Make sure the new mode is written before we exit */
+		mb();
+	}
+
+	return 0;
+}
+
+static int set_subcores_per_core(int new_mode)
+{
+	struct split_state *state;
+	int cpu;
+
+	if (kvm_hv_mode_active()) {
+		pr_err("Unable to change split core mode while KVM active.\n");
+		return -EBUSY;
+	}
+
+	/*
+	 * We are only called at boot, or from the sysfs write. If that ever
+	 * changes we'll need a lock here.
+	 */
+	BUG_ON(new_mode < 1 || new_mode > 4 || new_mode == 3);
+
+	for_each_present_cpu(cpu) {
+		state = &per_cpu(split_state, cpu);
+		state->step = SYNC_STEP_INITIAL;
+		state->master = 0;
+	}
+
+	get_online_cpus();
+
+	/* This cpu will update the globals before exiting stop machine */
+	this_cpu_ptr(&split_state)->master = 1;
+
+	/* Ensure state is consistent before we call the other cpus */
+	mb();
+
+	stop_machine(cpu_update_split_mode, &new_mode, cpu_online_mask);
+
+	put_online_cpus();
+
+	return 0;
+}
+
+static ssize_t __used store_subcores_per_core(struct device *dev,
+		struct device_attribute *attr, const char *buf,
+		size_t count)
+{
+	unsigned long val;
+	int rc;
+
+	/* We are serialised by the attribute lock */
+
+	rc = sscanf(buf, "%lx", &val);
+	if (rc != 1)
+		return -EINVAL;
+
+	switch (val) {
+	case 1:
+	case 2:
+	case 4:
+		if (subcores_per_core == val)
+			/* Nothing to do */
+			goto out;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rc = set_subcores_per_core(val);
+	if (rc)
+		return rc;
+
+out:
+	return count;
+}
+
+static ssize_t show_subcores_per_core(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%x\n", subcores_per_core);
+}
+
+static DEVICE_ATTR(subcores_per_core, 0644,
+		show_subcores_per_core, store_subcores_per_core);
+
+static int subcore_init(void)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return 0;
+
+	/*
+	 * We need all threads in a core to be present to split/unsplit so
+         * continue only if max_cpus are aligned to threads_per_core.
+	 */
+	if (setup_max_cpus % threads_per_core)
+		return 0;
+
+	BUG_ON(!alloc_cpumask_var(&cpu_offline_mask, GFP_KERNEL));
+
+	set_subcores_per_core(1);
+
+	return device_create_file(cpu_subsys.dev_root,
+				  &dev_attr_subcores_per_core);
+}
+machine_device_initcall(powernv, subcore_init);
diff --git a/arch/powerpc/platforms/powernv/subcore.h b/arch/powerpc/platforms/powernv/subcore.h
new file mode 100644
index 00000000000..148abc91deb
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/subcore.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright 2013, Michael Ellerman, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/* These are ordered and tested with <= */
+#define SYNC_STEP_INITIAL	0
+#define SYNC_STEP_UNSPLIT	1	/* Set by secondary when it sees unsplit */
+#define SYNC_STEP_REAL_MODE	2	/* Set by secondary when in real mode  */
+#define SYNC_STEP_FINISHED	3	/* Set by secondary when split/unsplit is done */
+
+#ifndef __ASSEMBLY__
+void split_core_secondary_loop(u8 *state);
+#endif
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 2cb8b776c84..756b482f819 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -21,6 +21,7 @@ config PPC_PSERIES
 	select HAVE_CONTEXT_TRACKING
 	select HOTPLUG_CPU if SMP
 	select ARCH_RANDOM
+	select PPC_DOORBELL
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 022b38e6a80..2d0b4d68a40 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -86,6 +86,7 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa,
 	}
 
 	of_node_set_flag(dn, OF_DYNAMIC);
+	of_node_init(dn);
 
 	return dn;
 }
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 8a8f0472d98..0bec0c02c5e 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -175,6 +175,36 @@ static int pseries_eeh_find_cap(struct device_node *dn, int cap)
 	return 0;
 }
 
+static int pseries_eeh_find_ecap(struct device_node *dn, int cap)
+{
+	struct pci_dn *pdn = PCI_DN(dn);
+	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	u32 header;
+	int pos = 256;
+	int ttl = (4096 - 256) / 8;
+
+	if (!edev || !edev->pcie_cap)
+		return 0;
+	if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+		return 0;
+	else if (!header)
+		return 0;
+
+	while (ttl-- > 0) {
+		if (PCI_EXT_CAP_ID(header) == cap && pos)
+			return pos;
+
+		pos = PCI_EXT_CAP_NEXT(header);
+		if (pos < 256)
+			break;
+
+		if (rtas_read_config(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+			break;
+	}
+
+	return 0;
+}
+
 /**
  * pseries_eeh_of_probe - EEH probe on the given device
  * @dn: OF node
@@ -220,7 +250,9 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 	 * or PCIe switch downstream port.
 	 */
 	edev->class_code = class_code;
+	edev->pcix_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_PCIX);
 	edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP);
+	edev->aer_cap = pseries_eeh_find_ecap(dn, PCI_EXT_CAP_ID_ERR);
 	edev->mode &= 0xFFFFFF00;
 	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
@@ -464,6 +496,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *state)
 			} else {
 				result = EEH_STATE_NOT_SUPPORT;
 			}
+			break;
 		default:
 			result = EEH_STATE_NOT_SUPPORT;
 		}
@@ -499,11 +532,19 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option)
 	/* If fundamental-reset not supported, try hot-reset */
 	if (option == EEH_RESET_FUNDAMENTAL &&
 	    ret == -8) {
+		option = EEH_RESET_HOT;
 		ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
 				config_addr, BUID_HI(pe->phb->buid),
-				BUID_LO(pe->phb->buid), EEH_RESET_HOT);
+				BUID_LO(pe->phb->buid), option);
 	}
 
+	/* We need reset hold or settlement delay */
+	if (option == EEH_RESET_FUNDAMENTAL ||
+	    option == EEH_RESET_HOT)
+		msleep(EEH_PE_RST_HOLD_TIME);
+	else
+		msleep(EEH_PE_RST_SETTLE_TIME);
+
 	return ret;
 }
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 7f75c94af82..7995135170a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -21,7 +21,7 @@
 #include <asm/prom.h>
 #include <asm/sparsemem.h>
 
-static unsigned long get_memblock_size(void)
+unsigned long pseries_memory_block_size(void)
 {
 	struct device_node *np;
 	unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE;
@@ -64,17 +64,6 @@ static unsigned long get_memblock_size(void)
 	return memblock_size;
 }
 
-/* WARNING: This is going to override the generic definition whenever
- * pseries is built-in regardless of what platform is active at boot
- * time. This is fine for now as this is the only "option" and it
- * should work everywhere. If not, we'll have to turn this into a
- * ppc_md. callback
- */
-unsigned long memory_block_size_bytes(void)
-{
-	return get_memblock_size();
-}
-
 #ifdef CONFIG_MEMORY_HOTREMOVE
 static int pseries_remove_memory(u64 start, u64 size)
 {
@@ -105,7 +94,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz
 	if (!pfn_valid(start_pfn))
 		goto out;
 
-	block_sz = memory_block_size_bytes();
+	block_sz = pseries_memory_block_size();
 	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
 	nid = memory_add_physaddr_to_nid(base);
 
@@ -201,7 +190,7 @@ static int pseries_update_drconf_memory(struct of_prop_reconfig *pr)
 	u32 *p;
 	int i, rc = -EINVAL;
 
-	memblock_size = get_memblock_size();
+	memblock_size = pseries_memory_block_size();
 	if (!memblock_size)
 		return -EINVAL;
 
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index 444fe7759e5..99ecf0a5a92 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -49,7 +49,7 @@ END_FTR_SECTION(0, 1);						\
 	std	r0,16(r1);					\
 	addi	r4,r1,STK_PARAM(FIRST_REG);			\
 	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
-	bl	.__trace_hcall_entry;				\
+	bl	__trace_hcall_entry;				\
 	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
 	ld	r0,16(r1);					\
 	ld	r3,STK_PARAM(R3)(r1);				\
@@ -83,7 +83,7 @@ END_FTR_SECTION(0, 1);						\
 	mr	r3,r6;						\
 	std	r0,16(r1);					\
 	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
-	bl	.__trace_hcall_exit;				\
+	bl	__trace_hcall_exit;				\
 	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
 	ld	r0,16(r1);					\
 	ld	r3,STK_PARAM(R3)(r1);				\
@@ -106,7 +106,7 @@ END_FTR_SECTION(0, 1);						\
 
 	.text
 
-_GLOBAL(plpar_hcall_norets)
+_GLOBAL_TOC(plpar_hcall_norets)
 	HMT_MEDIUM
 
 	mfcr	r0
@@ -122,7 +122,7 @@ _GLOBAL(plpar_hcall_norets)
 	mtcrf	0xff,r0
 	blr				/* return r3 = status */
 
-_GLOBAL(plpar_hcall)
+_GLOBAL_TOC(plpar_hcall)
 	HMT_MEDIUM
 
 	mfcr	r0
@@ -188,7 +188,7 @@ _GLOBAL(plpar_hcall_raw)
 
 	blr				/* return r3 = status */
 
-_GLOBAL(plpar_hcall9)
+_GLOBAL_TOC(plpar_hcall9)
 	HMT_MEDIUM
 
 	mfcr	r0
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 99219530ea4..361add62abf 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -64,4 +64,6 @@ extern int dlpar_detach_node(struct device_node *);
 struct pci_host_bridge;
 int pseries_root_bridge_prepare(struct pci_host_bridge *bridge);
 
+unsigned long pseries_memory_block_size(void);
+
 #endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 0435bb65d0a..1c0a60d9886 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -69,6 +69,7 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist
 
 	np->properties = proplist;
 	of_node_set_flag(np, OF_DYNAMIC);
+	of_node_init(np);
 
 	np->parent = derive_parent(path);
 	if (IS_ERR(np->parent)) {
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 099d2df976a..f2f40e64658 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -510,7 +510,11 @@ static void __init pSeries_setup_arch(void)
 static int __init pSeries_init_panel(void)
 {
 	/* Manually leave the kernel version on the panel. */
+#ifdef __BIG_ENDIAN__
 	ppc_md.progress("Linux ppc64\n", 0);
+#else
+	ppc_md.progress("Linux ppc64le\n", 0);
+#endif
 	ppc_md.progress(init_utsname()->version, 0);
 
 	return 0;
@@ -806,4 +810,7 @@ define_machine(pseries) {
 #ifdef CONFIG_KEXEC
 	.machine_kexec          = pSeries_machine_kexec,
 #endif
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+	.memory_block_size	= pseries_memory_block_size,
+#endif
 };
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 24f58cb0a54..a3555b10c1a 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -44,6 +44,7 @@
 #include <asm/xics.h>
 #include <asm/dbell.h>
 #include <asm/plpar_wrappers.h>
+#include <asm/code-patching.h>
 
 #include "pseries.h"
 #include "offline_states.h"
@@ -96,8 +97,8 @@ int smp_query_cpu_stopped(unsigned int pcpu)
 static inline int smp_startup_cpu(unsigned int lcpu)
 {
 	int status;
-	unsigned long start_here = __pa((u32)*((unsigned long *)
-					       generic_secondary_smp_init));
+	unsigned long start_here =
+			__pa(ppc_function_entry(generic_secondary_smp_init));
 	unsigned int pcpu;
 	int start_cpu;
 
diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig
deleted file mode 100644
index 422a175b10e..00000000000
--- a/arch/powerpc/platforms/wsp/Kconfig
+++ /dev/null
@@ -1,30 +0,0 @@
-config PPC_WSP
-	bool
-	select PPC_A2
-	select GENERIC_TBSYNC
-	select PPC_ICSWX
-	select PPC_SCOM
-	select PPC_XICS
-	select PPC_ICP_NATIVE
-	select PCI
-	select PPC_IO_WORKAROUNDS if PCI
-	select PPC_INDIRECT_PIO if PCI
-	default n
-
-menu "WSP platform selection"
-	depends on PPC_BOOK3E_64
-
-config PPC_PSR2
-	bool "PowerEN System Reference Platform 2"
-	select EPAPR_BOOT
-	select PPC_WSP
-	default y
-
-config PPC_CHROMA
-	bool "PowerEN PCIe Chroma Card"
-	select EPAPR_BOOT
-	select PPC_WSP
-	select OF_DYNAMIC
-	default y
-
-endmenu
diff --git a/arch/powerpc/platforms/wsp/Makefile b/arch/powerpc/platforms/wsp/Makefile
deleted file mode 100644
index 162fc60125a..00000000000
--- a/arch/powerpc/platforms/wsp/Makefile
+++ /dev/null
@@ -1,10 +0,0 @@
-ccflags-y			+= $(NO_MINIMAL_TOC)
-
-obj-y				+= setup.o ics.o wsp.o
-obj-$(CONFIG_PPC_PSR2)		+= psr2.o
-obj-$(CONFIG_PPC_CHROMA)	+= chroma.o h8.o
-obj-$(CONFIG_PPC_WSP)		+= opb_pic.o
-obj-$(CONFIG_PPC_WSP)		+= scom_wsp.o
-obj-$(CONFIG_SMP)		+= smp.o scom_smp.o
-obj-$(CONFIG_PCI)		+= wsp_pci.o
-obj-$(CONFIG_PCI_MSI)		+= msi.o
diff --git a/arch/powerpc/platforms/wsp/chroma.c b/arch/powerpc/platforms/wsp/chroma.c
deleted file mode 100644
index aaa46b35371..00000000000
--- a/arch/powerpc/platforms/wsp/chroma.c
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * Copyright 2008-2011, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/of.h>
-#include <linux/smp.h>
-#include <linux/time.h>
-#include <linux/of_fdt.h>
-
-#include <asm/machdep.h>
-#include <asm/udbg.h>
-
-#include "ics.h"
-#include "wsp.h"
-
-void __init chroma_setup_arch(void)
-{
-	wsp_setup_arch();
-	wsp_setup_h8();
-
-}
-
-static int __init chroma_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if (!of_flat_dt_is_compatible(root, "ibm,wsp-chroma"))
-		return 0;
-
-	return 1;
-}
-
-define_machine(chroma_md) {
-	.name			= "Chroma PCIe",
-	.probe			= chroma_probe,
-	.setup_arch		= chroma_setup_arch,
-	.restart		= wsp_h8_restart,
-	.power_off		= wsp_h8_power_off,
-	.halt			= wsp_halt,
-	.calibrate_decr		= generic_calibrate_decr,
-	.init_IRQ		= wsp_setup_irq,
-	.progress		= udbg_progress,
-	.power_save		= book3e_idle,
-};
-
-machine_arch_initcall(chroma_md, wsp_probe_devices);
diff --git a/arch/powerpc/platforms/wsp/h8.c b/arch/powerpc/platforms/wsp/h8.c
deleted file mode 100644
index a3c87f39575..00000000000
--- a/arch/powerpc/platforms/wsp/h8.c
+++ /dev/null
@@ -1,135 +0,0 @@
-/*
- * Copyright 2008-2011, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/io.h>
-#include <linux/of_address.h>
-
-#include "wsp.h"
-
-/*
- * The UART connection to the H8 is over ttyS1 which is just a 16550.
- * We assume that FW has it setup right and no one messes with it.
- */
-
-
-static u8 __iomem *h8;
-
-#define RBR 0		/* Receiver Buffer Register */
-#define THR 0		/* Transmitter Holding Register */
-#define LSR 5		/* Line Status Register */
-#define LSR_DR 0x01	/* LSR value for Data-Ready */
-#define LSR_THRE 0x20	/* LSR value for Transmitter-Holding-Register-Empty */
-static void wsp_h8_putc(int c)
-{
-	u8 lsr;
-
-	do {
-		lsr = readb(h8 + LSR);
-	} while ((lsr & LSR_THRE) != LSR_THRE);
-	writeb(c, h8 + THR);
-}
-
-static int wsp_h8_getc(void)
-{
-	u8 lsr;
-
-	do {
-		lsr = readb(h8 + LSR);
-	} while ((lsr & LSR_DR) != LSR_DR);
-
-	return readb(h8 + RBR);
-}
-
-static void wsp_h8_puts(const char *s, int sz)
-{
-	int i;
-
-	for (i = 0; i < sz; i++) {
-		wsp_h8_putc(s[i]);
-
-		/* no flow control so wait for echo */
-		wsp_h8_getc();
-	}
-	wsp_h8_putc('\r');
-	wsp_h8_putc('\n');
-}
-
-static void wsp_h8_terminal_cmd(const char *cmd, int sz)
-{
-	hard_irq_disable();
-	wsp_h8_puts(cmd, sz);
-	/* should never return, but just in case */
-	for (;;)
-		continue;
-}
-
-
-void wsp_h8_restart(char *cmd)
-{
-	static const char restart[] = "warm-reset";
-
-	(void)cmd;
-	wsp_h8_terminal_cmd(restart, sizeof(restart) - 1);
-}
-
-void wsp_h8_power_off(void)
-{
-	static const char off[] = "power-off";
-
-	wsp_h8_terminal_cmd(off, sizeof(off) - 1);
-}
-
-static void __iomem *wsp_h8_getaddr(void)
-{
-	struct device_node *aliases;
-	struct device_node *uart;
-	struct property *path;
-	void __iomem *va = NULL;
-
-	/*
-	 * there is nothing in the devtree to tell us which is mapped
-	 * to the H8, but se know it is the second serial port.
-	 */
-
-	aliases = of_find_node_by_path("/aliases");
-	if (aliases == NULL)
-		return NULL;
-
-	path = of_find_property(aliases, "serial1", NULL);
-	if (path == NULL)
-		goto out;
-
-	uart = of_find_node_by_path(path->value);
-	if (uart == NULL)
-		goto out;
-
-	va = of_iomap(uart, 0);
-
-	/* remove it so no one messes with it */
-	of_detach_node(uart);
-	of_node_put(uart);
-
-out:
-	of_node_put(aliases);
-
-	return va;
-}
-
-void __init wsp_setup_h8(void)
-{
-	h8 = wsp_h8_getaddr();
-
-	/* Devtree change? lets hard map it anyway */
-	if (h8 == NULL) {
-		pr_warn("UART to H8 could not be found");
-		h8 = ioremap(0xffc0008000ULL, 0x100);
-	}
-}
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
deleted file mode 100644
index 9cd92e64502..00000000000
--- a/arch/powerpc/platforms/wsp/ics.c
+++ /dev/null
@@ -1,762 +0,0 @@
-/*
- * Copyright 2008-2011 IBM Corporation.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-
-#include <linux/cpu.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/msi.h>
-#include <linux/of.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/xics.h>
-
-#include "wsp.h"
-#include "ics.h"
-
-
-/* WSP ICS */
-
-struct wsp_ics {
-	struct ics ics;
-	struct device_node *dn;
-	void __iomem *regs;
-	spinlock_t lock;
-	unsigned long *bitmap;
-	u32 chip_id;
-	u32 lsi_base;
-	u32 lsi_count;
-	u64 hwirq_start;
-	u64 count;
-#ifdef CONFIG_SMP
-	int *hwirq_cpu_map;
-#endif
-};
-
-#define to_wsp_ics(ics)	container_of(ics, struct wsp_ics, ics)
-
-#define INT_SRC_LAYER_BUID_REG(base)	((base) + 0x00)
-#define IODA_TBL_ADDR_REG(base)		((base) + 0x18)
-#define IODA_TBL_DATA_REG(base)		((base) + 0x20)
-#define XIVE_UPDATE_REG(base)		((base) + 0x28)
-#define ICS_INT_CAPS_REG(base)		((base) + 0x30)
-
-#define TBL_AUTO_INCREMENT	((1UL << 63) | (1UL << 15))
-#define TBL_SELECT_XIST		(1UL << 48)
-#define TBL_SELECT_XIVT		(1UL << 49)
-
-#define IODA_IRQ(irq)		((irq) & (0x7FFULL))	/* HRM 5.1.3.4 */
-
-#define XIST_REQUIRED		0x8
-#define XIST_REJECTED		0x4
-#define XIST_PRESENTED		0x2
-#define XIST_PENDING		0x1
-
-#define XIVE_SERVER_SHIFT	42
-#define XIVE_SERVER_MASK	0xFFFFULL
-#define XIVE_PRIORITY_MASK	0xFFULL
-#define XIVE_PRIORITY_SHIFT	32
-#define XIVE_WRITE_ENABLE	(1ULL << 63)
-
-/*
- * The docs refer to a 6 bit field called ChipID, which consists of a
- * 3 bit NodeID and a 3 bit ChipID. On WSP the ChipID is always zero
- * so we ignore it, and every where we use "chip id" in this code we
- * mean the NodeID.
- */
-#define WSP_ICS_CHIP_SHIFT		17
-
-
-static struct wsp_ics *ics_list;
-static int num_ics;
-
-/* ICS Source controller accessors */
-
-static u64 wsp_ics_get_xive(struct wsp_ics *ics, unsigned int irq)
-{
-	unsigned long flags;
-	u64 xive;
-
-	spin_lock_irqsave(&ics->lock, flags);
-	out_be64(IODA_TBL_ADDR_REG(ics->regs), TBL_SELECT_XIVT | IODA_IRQ(irq));
-	xive = in_be64(IODA_TBL_DATA_REG(ics->regs));
-	spin_unlock_irqrestore(&ics->lock, flags);
-
-	return xive;
-}
-
-static void wsp_ics_set_xive(struct wsp_ics *ics, unsigned int irq, u64 xive)
-{
-	xive &= ~XIVE_ADDR_MASK;
-	xive |= (irq & XIVE_ADDR_MASK);
-	xive |= XIVE_WRITE_ENABLE;
-
-	out_be64(XIVE_UPDATE_REG(ics->regs), xive);
-}
-
-static u64 xive_set_server(u64 xive, unsigned int server)
-{
-	u64 mask = ~(XIVE_SERVER_MASK << XIVE_SERVER_SHIFT);
-
-	xive &= mask;
-	xive |= (server & XIVE_SERVER_MASK) << XIVE_SERVER_SHIFT;
-
-	return xive;
-}
-
-static u64 xive_set_priority(u64 xive, unsigned int priority)
-{
-	u64 mask = ~(XIVE_PRIORITY_MASK << XIVE_PRIORITY_SHIFT);
-
-	xive &= mask;
-	xive |= (priority & XIVE_PRIORITY_MASK) << XIVE_PRIORITY_SHIFT;
-
-	return xive;
-}
-
-
-#ifdef CONFIG_SMP
-/* Find logical CPUs within mask on a given chip and store result in ret */
-void cpus_on_chip(int chip_id, cpumask_t *mask, cpumask_t *ret)
-{
-	int cpu, chip;
-	struct device_node *cpu_dn, *dn;
-	const u32 *prop;
-
-	cpumask_clear(ret);
-	for_each_cpu(cpu, mask) {
-		cpu_dn = of_get_cpu_node(cpu, NULL);
-		if (!cpu_dn)
-			continue;
-
-		prop = of_get_property(cpu_dn, "at-node", NULL);
-		if (!prop) {
-			of_node_put(cpu_dn);
-			continue;
-		}
-
-		dn = of_find_node_by_phandle(*prop);
-		of_node_put(cpu_dn);
-
-		chip = wsp_get_chip_id(dn);
-		if (chip == chip_id)
-			cpumask_set_cpu(cpu, ret);
-
-		of_node_put(dn);
-	}
-}
-
-/* Store a suitable CPU to handle a hwirq in the ics->hwirq_cpu_map cache */
-static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq,
-			   const cpumask_t *affinity)
-{
-	cpumask_var_t avail, newmask;
-	int ret = -ENOMEM, cpu, cpu_rover = 0, target;
-	int index = hwirq - ics->hwirq_start;
-	unsigned int nodeid;
-
-	BUG_ON(index < 0 || index >= ics->count);
-
-	if (!ics->hwirq_cpu_map)
-		return -ENOMEM;
-
-	if (!distribute_irqs) {
-		ics->hwirq_cpu_map[hwirq - ics->hwirq_start] = xics_default_server;
-		return 0;
-	}
-
-	/* Allocate needed CPU masks */
-	if (!alloc_cpumask_var(&avail, GFP_KERNEL))
-		goto ret;
-	if (!alloc_cpumask_var(&newmask, GFP_KERNEL))
-		goto freeavail;
-
-	/* Find PBus attached to the source of this IRQ */
-	nodeid = (hwirq >> WSP_ICS_CHIP_SHIFT) & 0x3; /* 12:14 */
-
-	/* Find CPUs that could handle this IRQ */
-	if (affinity)
-		cpumask_and(avail, cpu_online_mask, affinity);
-	else
-		cpumask_copy(avail, cpu_online_mask);
-
-	/* Narrow selection down to logical CPUs on the same chip */
-	cpus_on_chip(nodeid, avail, newmask);
-
-	/* Ensure we haven't narrowed it down to 0 */
-	if (unlikely(cpumask_empty(newmask))) {
-		if (unlikely(cpumask_empty(avail))) {
-			ret = -1;
-			goto out;
-		}
-		cpumask_copy(newmask, avail);
-	}
-
-	/* Choose a CPU out of those we narrowed it down to in round robin */
-	target = hwirq % cpumask_weight(newmask);
-	for_each_cpu(cpu, newmask) {
-		if (cpu_rover++ >= target) {
-			ics->hwirq_cpu_map[index] = get_hard_smp_processor_id(cpu);
-			ret = 0;
-			goto out;
-		}
-	}
-
-	/* Shouldn't happen */
-	WARN_ON(1);
-
-out:
-	free_cpumask_var(newmask);
-freeavail:
-	free_cpumask_var(avail);
-ret:
-	if (ret < 0) {
-		ics->hwirq_cpu_map[index] = cpumask_first(cpu_online_mask);
-		pr_warning("Error, falling hwirq 0x%x routing back to CPU %i\n",
-			   hwirq, ics->hwirq_cpu_map[index]);
-	}
-	return ret;
-}
-
-static void alloc_irq_map(struct wsp_ics *ics)
-{
-	int i;
-
-	ics->hwirq_cpu_map = kmalloc(sizeof(int) * ics->count, GFP_KERNEL);
-	if (!ics->hwirq_cpu_map) {
-		pr_warning("Allocate hwirq_cpu_map failed, "
-			   "IRQ balancing disabled\n");
-		return;
-	}
-
-	for (i=0; i < ics->count; i++)
-		ics->hwirq_cpu_map[i] = xics_default_server;
-}
-
-static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq)
-{
-	int index = hwirq - ics->hwirq_start;
-
-	BUG_ON(index < 0 || index >= ics->count);
-
-	if (!ics->hwirq_cpu_map)
-		return xics_default_server;
-
-	return ics->hwirq_cpu_map[index];
-}
-#else /* !CONFIG_SMP */
-static int cache_hwirq_map(struct wsp_ics *ics, unsigned int hwirq,
-			   const cpumask_t *affinity)
-{
-	return 0;
-}
-
-static int get_irq_server(struct wsp_ics *ics, unsigned int hwirq)
-{
-	return xics_default_server;
-}
-
-static void alloc_irq_map(struct wsp_ics *ics) { }
-#endif
-
-static void wsp_chip_unmask_irq(struct irq_data *d)
-{
-	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
-	struct wsp_ics *ics;
-	int server;
-	u64 xive;
-
-	if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
-		return;
-
-	ics = d->chip_data;
-	if (WARN_ON(!ics))
-		return;
-
-	server = get_irq_server(ics, hw_irq);
-
-	xive = wsp_ics_get_xive(ics, hw_irq);
-	xive = xive_set_server(xive, server);
-	xive = xive_set_priority(xive, DEFAULT_PRIORITY);
-	wsp_ics_set_xive(ics, hw_irq, xive);
-}
-
-static unsigned int wsp_chip_startup(struct irq_data *d)
-{
-	/* unmask it */
-	wsp_chip_unmask_irq(d);
-	return 0;
-}
-
-static void wsp_mask_real_irq(unsigned int hw_irq, struct wsp_ics *ics)
-{
-	u64 xive;
-
-	if (hw_irq == XICS_IPI)
-		return;
-
-	if (WARN_ON(!ics))
-		return;
-	xive = wsp_ics_get_xive(ics, hw_irq);
-	xive = xive_set_server(xive, xics_default_server);
-	xive = xive_set_priority(xive, LOWEST_PRIORITY);
-	wsp_ics_set_xive(ics, hw_irq, xive);
-}
-
-static void wsp_chip_mask_irq(struct irq_data *d)
-{
-	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
-	struct wsp_ics *ics = d->chip_data;
-
-	if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
-		return;
-
-	wsp_mask_real_irq(hw_irq, ics);
-}
-
-static int wsp_chip_set_affinity(struct irq_data *d,
-				 const struct cpumask *cpumask, bool force)
-{
-	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
-	struct wsp_ics *ics;
-	int ret;
-	u64 xive;
-
-	if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
-		return -1;
-
-	ics = d->chip_data;
-	if (WARN_ON(!ics))
-		return -1;
-	xive = wsp_ics_get_xive(ics, hw_irq);
-
-	/*
-	 * For the moment only implement delivery to all cpus or one cpu.
-	 * Get current irq_server for the given irq
-	 */
-	ret = cache_hwirq_map(ics, hw_irq, cpumask);
-	if (ret == -1) {
-		char cpulist[128];
-		cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask);
-		pr_warning("%s: No online cpus in the mask %s for irq %d\n",
-			   __func__, cpulist, d->irq);
-		return -1;
-	} else if (ret == -ENOMEM) {
-		pr_warning("%s: Out of memory\n", __func__);
-		return -1;
-	}
-
-	xive = xive_set_server(xive, get_irq_server(ics, hw_irq));
-	wsp_ics_set_xive(ics, hw_irq, xive);
-
-	return IRQ_SET_MASK_OK;
-}
-
-static struct irq_chip wsp_irq_chip = {
-	.name = "WSP ICS",
-	.irq_startup		= wsp_chip_startup,
-	.irq_mask		= wsp_chip_mask_irq,
-	.irq_unmask		= wsp_chip_unmask_irq,
-	.irq_set_affinity	= wsp_chip_set_affinity
-};
-
-static int wsp_ics_host_match(struct ics *ics, struct device_node *dn)
-{
-	/* All ICSs in the system implement a global irq number space,
-	 * so match against them all. */
-	return of_device_is_compatible(dn, "ibm,ppc-xics");
-}
-
-static int wsp_ics_match_hwirq(struct wsp_ics *wsp_ics, unsigned int hwirq)
-{
-	if (hwirq >= wsp_ics->hwirq_start &&
-	    hwirq <  wsp_ics->hwirq_start + wsp_ics->count)
-		return 1;
-
-	return 0;
-}
-
-static int wsp_ics_map(struct ics *ics, unsigned int virq)
-{
-	struct wsp_ics *wsp_ics = to_wsp_ics(ics);
-	unsigned int hw_irq = virq_to_hw(virq);
-	unsigned long flags;
-
-	if (!wsp_ics_match_hwirq(wsp_ics, hw_irq))
-		return -ENOENT;
-
-	irq_set_chip_and_handler(virq, &wsp_irq_chip, handle_fasteoi_irq);
-
-	irq_set_chip_data(virq, wsp_ics);
-
-	spin_lock_irqsave(&wsp_ics->lock, flags);
-	bitmap_allocate_region(wsp_ics->bitmap, hw_irq - wsp_ics->hwirq_start, 0);
-	spin_unlock_irqrestore(&wsp_ics->lock, flags);
-
-	return 0;
-}
-
-static void wsp_ics_mask_unknown(struct ics *ics, unsigned long hw_irq)
-{
-	struct wsp_ics *wsp_ics = to_wsp_ics(ics);
-
-	if (!wsp_ics_match_hwirq(wsp_ics, hw_irq))
-		return;
-
-	pr_err("%s: IRQ %lu (real) is invalid, disabling it.\n", __func__, hw_irq);
-	wsp_mask_real_irq(hw_irq, wsp_ics);
-}
-
-static long wsp_ics_get_server(struct ics *ics, unsigned long hw_irq)
-{
-	struct wsp_ics *wsp_ics = to_wsp_ics(ics);
-
-	if (!wsp_ics_match_hwirq(wsp_ics, hw_irq))
-		return -ENOENT;
-
-	return get_irq_server(wsp_ics, hw_irq);
-}
-
-/* HW Number allocation API */
-
-static struct wsp_ics *wsp_ics_find_dn_ics(struct device_node *dn)
-{
-	struct device_node *iparent;
-	int i;
-
-	iparent = of_irq_find_parent(dn);
-	if (!iparent) {
-		pr_err("wsp_ics: Failed to find interrupt parent!\n");
-		return NULL;
-	}
-
-	for(i = 0; i < num_ics; i++) {
-		if(ics_list[i].dn == iparent)
-			break;
-	}
-
-	if (i >= num_ics) {
-		pr_err("wsp_ics: Unable to find parent bitmap!\n");
-		return NULL;
-	}
-
-	return &ics_list[i];
-}
-
-int wsp_ics_alloc_irq(struct device_node *dn, int num)
-{
-	struct wsp_ics *ics;
-	int order, offset;
-
-	ics = wsp_ics_find_dn_ics(dn);
-	if (!ics)
-		return -ENODEV;
-
-	/* Fast, but overly strict if num isn't a power of two */
-	order = get_count_order(num);
-
-	spin_lock_irq(&ics->lock);
-	offset = bitmap_find_free_region(ics->bitmap, ics->count, order);
-	spin_unlock_irq(&ics->lock);
-
-	if (offset < 0)
-		return offset;
-
-	return offset + ics->hwirq_start;
-}
-
-void wsp_ics_free_irq(struct device_node *dn, unsigned int irq)
-{
-	struct wsp_ics *ics;
-
-	ics = wsp_ics_find_dn_ics(dn);
-	if (WARN_ON(!ics))
-		return;
-
-	spin_lock_irq(&ics->lock);
-	bitmap_release_region(ics->bitmap, irq, 0);
-	spin_unlock_irq(&ics->lock);
-}
-
-/* Initialisation */
-
-static int __init wsp_ics_bitmap_setup(struct wsp_ics *ics,
-				      struct device_node *dn)
-{
-	int len, i, j, size;
-	u32 start, count;
-	const u32 *p;
-
-	size = BITS_TO_LONGS(ics->count) * sizeof(long);
-	ics->bitmap = kzalloc(size, GFP_KERNEL);
-	if (!ics->bitmap) {
-		pr_err("wsp_ics: ENOMEM allocating IRQ bitmap!\n");
-		return -ENOMEM;
-	}
-
-	spin_lock_init(&ics->lock);
-
-	p = of_get_property(dn, "available-ranges", &len);
-	if (!p || !len) {
-		/* FIXME this should be a WARN() once mambo is updated */
-		pr_err("wsp_ics: No available-ranges defined for %s\n",
-			dn->full_name);
-		return 0;
-	}
-
-	if (len % (2 * sizeof(u32)) != 0) {
-		/* FIXME this should be a WARN() once mambo is updated */
-		pr_err("wsp_ics: Invalid available-ranges for %s\n",
-			dn->full_name);
-		return 0;
-	}
-
-	bitmap_fill(ics->bitmap, ics->count);
-
-	for (i = 0; i < len / sizeof(u32); i += 2) {
-		start = of_read_number(p + i, 1);
-		count = of_read_number(p + i + 1, 1);
-
-		pr_devel("%s: start: %d count: %d\n", __func__, start, count);
-
-		if ((start + count) > (ics->hwirq_start + ics->count) ||
-		     start < ics->hwirq_start) {
-			pr_err("wsp_ics: Invalid range! -> %d to %d\n",
-					start, start + count);
-			break;
-		}
-
-		for (j = 0; j < count; j++)
-			bitmap_release_region(ics->bitmap,
-				(start + j) - ics->hwirq_start, 0);
-	}
-
-	/* Ensure LSIs are not available for allocation */
-	bitmap_allocate_region(ics->bitmap, ics->lsi_base,
-			       get_count_order(ics->lsi_count));
-
-	return 0;
-}
-
-static int __init wsp_ics_setup(struct wsp_ics *ics, struct device_node *dn)
-{
-	u32 lsi_buid, msi_buid, msi_base, msi_count;
-	void __iomem *regs;
-	const u32 *p;
-	int rc, len, i;
-	u64 caps, buid;
-
-	p = of_get_property(dn, "interrupt-ranges", &len);
-	if (!p || len < (2 * sizeof(u32))) {
-		pr_err("wsp_ics: No/bad interrupt-ranges found on %s\n",
-			dn->full_name);
-		return -ENOENT;
-	}
-
-	if (len > (2 * sizeof(u32))) {
-		pr_err("wsp_ics: Multiple ics ranges not supported.\n");
-		return -EINVAL;
-	}
-
-	regs = of_iomap(dn, 0);
-	if (!regs) {
-		pr_err("wsp_ics: of_iomap(%s) failed\n", dn->full_name);
-		return -ENXIO;
-	}
-
-	ics->hwirq_start = of_read_number(p, 1);
-	ics->count = of_read_number(p + 1, 1);
-	ics->regs = regs;
-
-	ics->chip_id = wsp_get_chip_id(dn);
-	if (WARN_ON(ics->chip_id < 0))
-		ics->chip_id = 0;
-
-	/* Get some informations about the critter */
-	caps = in_be64(ICS_INT_CAPS_REG(ics->regs));
-	buid = in_be64(INT_SRC_LAYER_BUID_REG(ics->regs));
-	ics->lsi_count = caps >> 56;
-	msi_count = (caps >> 44) & 0x7ff;
-
-	/* Note: LSI BUID is 9 bits, but really only 3 are BUID and the
-	 * rest is mixed in the interrupt number. We store the whole
-	 * thing though
-	 */
-	lsi_buid = (buid >> 48) & 0x1ff;
-	ics->lsi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | lsi_buid << 5;
-	msi_buid = (buid >> 37) & 0x7;
-	msi_base = (ics->chip_id << WSP_ICS_CHIP_SHIFT) | msi_buid << 11;
-
-	pr_info("wsp_ics: Found %s\n", dn->full_name);
-	pr_info("wsp_ics:    irq range : 0x%06llx..0x%06llx\n",
-		ics->hwirq_start, ics->hwirq_start + ics->count - 1);
-	pr_info("wsp_ics:    %4d LSIs : 0x%06x..0x%06x\n",
-		ics->lsi_count, ics->lsi_base,
-		ics->lsi_base + ics->lsi_count - 1);
-	pr_info("wsp_ics:    %4d MSIs : 0x%06x..0x%06x\n",
-		msi_count, msi_base,
-		msi_base + msi_count - 1);
-
-	/* Let's check the HW config is sane */
-	if (ics->lsi_base < ics->hwirq_start ||
-	    (ics->lsi_base + ics->lsi_count) > (ics->hwirq_start + ics->count))
-		pr_warning("wsp_ics: WARNING ! LSIs out of interrupt-ranges !\n");
-	if (msi_base < ics->hwirq_start ||
-	    (msi_base + msi_count) > (ics->hwirq_start + ics->count))
-		pr_warning("wsp_ics: WARNING ! MSIs out of interrupt-ranges !\n");
-
-	/* We don't check for overlap between LSI and MSI, which will happen
-	 * if we use the same BUID, I'm not sure yet how legit that is.
-	 */
-
-	rc = wsp_ics_bitmap_setup(ics, dn);
-	if (rc) {
-		iounmap(regs);
-		return rc;
-	}
-
-	ics->dn = of_node_get(dn);
-	alloc_irq_map(ics);
-
-	for(i = 0; i < ics->count; i++)
-		wsp_mask_real_irq(ics->hwirq_start + i, ics);
-
-	ics->ics.map = wsp_ics_map;
-	ics->ics.mask_unknown = wsp_ics_mask_unknown;
-	ics->ics.get_server = wsp_ics_get_server;
-	ics->ics.host_match = wsp_ics_host_match;
-
-	xics_register_ics(&ics->ics);
-
-	return 0;
-}
-
-static void __init wsp_ics_set_default_server(void)
-{
-	struct device_node *np;
-	u32 hwid;
-
-	/* Find the server number for the boot cpu. */
-	np = of_get_cpu_node(boot_cpuid, NULL);
-	BUG_ON(!np);
-
-	hwid = get_hard_smp_processor_id(boot_cpuid);
-
-	pr_info("wsp_ics: default server is %#x, CPU %s\n", hwid, np->full_name);
-	xics_default_server = hwid;
-
-	of_node_put(np);
-}
-
-static int __init wsp_ics_init(void)
-{
-	struct device_node *dn;
-	struct wsp_ics *ics;
-	int rc, found;
-
-	wsp_ics_set_default_server();
-
-	found = 0;
-	for_each_compatible_node(dn, NULL, "ibm,ppc-xics")
-		found++;
-
-	if (found == 0) {
-		pr_err("wsp_ics: No ICS's found!\n");
-		return -ENODEV;
-	}
-
-	ics_list = kmalloc(sizeof(*ics) * found, GFP_KERNEL);
-	if (!ics_list) {
-		pr_err("wsp_ics: No memory for structs.\n");
-		return -ENOMEM;
-	}
-
-	num_ics = 0;
-	ics = ics_list;
-	for_each_compatible_node(dn, NULL, "ibm,wsp-xics") {
-		rc = wsp_ics_setup(ics, dn);
-		if (rc == 0) {
-			ics++;
-			num_ics++;
-		}
-	}
-
-	if (found != num_ics) {
-		pr_err("wsp_ics: Failed setting up %d ICS's\n",
-			found - num_ics);
-		return -1;
-	}
-
-	return 0;
-}
-
-void __init wsp_init_irq(void)
-{
-	wsp_ics_init();
-	xics_init();
-
-	/* We need to patch our irq chip's EOI to point to the right ICP */
-	wsp_irq_chip.irq_eoi = icp_ops->eoi;
-}
-
-#ifdef CONFIG_PCI_MSI
-static void wsp_ics_msi_unmask_irq(struct irq_data *d)
-{
-	wsp_chip_unmask_irq(d);
-	unmask_msi_irq(d);
-}
-
-static unsigned int wsp_ics_msi_startup(struct irq_data *d)
-{
-	wsp_ics_msi_unmask_irq(d);
-	return 0;
-}
-
-static void wsp_ics_msi_mask_irq(struct irq_data *d)
-{
-	mask_msi_irq(d);
-	wsp_chip_mask_irq(d);
-}
-
-/*
- * we do it this way because we reassinge default EOI handling in
- * irq_init() above
- */
-static void wsp_ics_eoi(struct irq_data *data)
-{
-	wsp_irq_chip.irq_eoi(data);
-}
-
-static struct irq_chip wsp_ics_msi = {
-	.name = "WSP ICS MSI",
-	.irq_startup = wsp_ics_msi_startup,
-	.irq_mask = wsp_ics_msi_mask_irq,
-	.irq_unmask = wsp_ics_msi_unmask_irq,
-	.irq_eoi = wsp_ics_eoi,
-	.irq_set_affinity = wsp_chip_set_affinity
-};
-
-void wsp_ics_set_msi_chip(unsigned int irq)
-{
-	irq_set_chip(irq, &wsp_ics_msi);
-}
-
-void wsp_ics_set_std_chip(unsigned int irq)
-{
-	irq_set_chip(irq, &wsp_irq_chip);
-}
-#endif /* CONFIG_PCI_MSI */
diff --git a/arch/powerpc/platforms/wsp/ics.h b/arch/powerpc/platforms/wsp/ics.h
deleted file mode 100644
index 07b644e0cf9..00000000000
--- a/arch/powerpc/platforms/wsp/ics.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * Copyright 2009 IBM Corporation.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-
-#ifndef __ICS_H
-#define __ICS_H
-
-#define XIVE_ADDR_MASK		0x7FFULL
-
-extern void wsp_init_irq(void);
-
-extern int wsp_ics_alloc_irq(struct device_node *dn, int num);
-extern void wsp_ics_free_irq(struct device_node *dn, unsigned int irq);
-
-#ifdef CONFIG_PCI_MSI
-extern void wsp_ics_set_msi_chip(unsigned int irq);
-extern void wsp_ics_set_std_chip(unsigned int irq);
-#endif /* CONFIG_PCI_MSI */
-
-#endif /* __ICS_H */
diff --git a/arch/powerpc/platforms/wsp/msi.c b/arch/powerpc/platforms/wsp/msi.c
deleted file mode 100644
index 380882f27ad..00000000000
--- a/arch/powerpc/platforms/wsp/msi.c
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * Copyright 2011 Michael Ellerman, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/msi.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
-
-#include "msi.h"
-#include "ics.h"
-#include "wsp_pci.h"
-
-/* Magic addresses for 32 & 64-bit MSIs with hardcoded MVE 0 */
-#define MSI_ADDR_32		0xFFFF0000ul
-#define MSI_ADDR_64		0x1000000000000000ul
-
-int wsp_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	struct pci_controller *phb;
-	struct msi_desc *entry;
-	struct msi_msg msg;
-	unsigned int virq;
-	int hwirq;
-
-	phb = pci_bus_to_host(dev->bus);
-	if (!phb)
-		return -ENOENT;
-
-	entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
-	if (entry->msi_attrib.is_64) {
-		msg.address_lo = 0;
-		msg.address_hi = MSI_ADDR_64 >> 32;
-	} else {
-		msg.address_lo = MSI_ADDR_32;
-		msg.address_hi = 0;
-	}
-
-	list_for_each_entry(entry, &dev->msi_list, list) {
-		hwirq = wsp_ics_alloc_irq(phb->dn, 1);
-		if (hwirq < 0) {
-			dev_warn(&dev->dev, "wsp_msi: hwirq alloc failed!\n");
-			return hwirq;
-		}
-
-		virq = irq_create_mapping(NULL, hwirq);
-		if (virq == NO_IRQ) {
-			dev_warn(&dev->dev, "wsp_msi: virq alloc failed!\n");
-			return -1;
-		}
-
-		dev_dbg(&dev->dev, "wsp_msi: allocated irq %#x/%#x\n",
-			hwirq, virq);
-
-		wsp_ics_set_msi_chip(virq);
-		irq_set_msi_desc(virq, entry);
-		msg.data = hwirq & XIVE_ADDR_MASK;
-		write_msi_msg(virq, &msg);
-	}
-
-	return 0;
-}
-
-void wsp_teardown_msi_irqs(struct pci_dev *dev)
-{
-	struct pci_controller *phb;
-	struct msi_desc *entry;
-	int hwirq;
-
-	phb = pci_bus_to_host(dev->bus);
-
-	dev_dbg(&dev->dev, "wsp_msi: tearing down msi irqs\n");
-
-	list_for_each_entry(entry, &dev->msi_list, list) {
-		if (entry->irq == NO_IRQ)
-			continue;
-
-		irq_set_msi_desc(entry->irq, NULL);
-		wsp_ics_set_std_chip(entry->irq);
-
-		hwirq = virq_to_hw(entry->irq);
-		/* In this order to avoid racing with irq_create_mapping() */
-		irq_dispose_mapping(entry->irq);
-		wsp_ics_free_irq(phb->dn, hwirq);
-	}
-}
-
-void wsp_setup_phb_msi(struct pci_controller *phb)
-{
-	/* Create a single MVE at offset 0 that matches everything */
-	out_be64(phb->cfg_data + PCIE_REG_IODA_ADDR, PCIE_REG_IODA_AD_TBL_MVT);
-	out_be64(phb->cfg_data + PCIE_REG_IODA_DATA0, 1ull << 63);
-
-	ppc_md.setup_msi_irqs = wsp_setup_msi_irqs;
-	ppc_md.teardown_msi_irqs = wsp_teardown_msi_irqs;
-}
diff --git a/arch/powerpc/platforms/wsp/msi.h b/arch/powerpc/platforms/wsp/msi.h
deleted file mode 100644
index 0ab27b71b24..00000000000
--- a/arch/powerpc/platforms/wsp/msi.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * Copyright 2011 Michael Ellerman, IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-
-#ifndef __WSP_MSI_H
-#define __WSP_MSI_H
-
-#ifdef CONFIG_PCI_MSI
-extern void wsp_setup_phb_msi(struct pci_controller *phb);
-#else
-static inline void wsp_setup_phb_msi(struct pci_controller *phb) { }
-#endif
-
-#endif /* __WSP_MSI_H */
diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c
deleted file mode 100644
index 3f672980793..00000000000
--- a/arch/powerpc/platforms/wsp/opb_pic.c
+++ /dev/null
@@ -1,321 +0,0 @@
-/*
- * IBM Onboard Peripheral Bus Interrupt Controller
- *
- * Copyright 2010 Jack Miller, IBM Corporation.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/of.h>
-#include <linux/slab.h>
-#include <linux/time.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-
-#include <asm/reg_a2.h>
-#include <asm/irq.h>
-
-#define OPB_NR_IRQS 32
-
-#define OPB_MLSASIER	0x04    /* MLS Accumulated Status IER */
-#define OPB_MLSIR	0x50	/* MLS Interrupt Register */
-#define OPB_MLSIER	0x54	/* MLS Interrupt Enable Register */
-#define OPB_MLSIPR	0x58	/* MLS Interrupt Polarity Register */
-#define OPB_MLSIIR	0x5c	/* MLS Interrupt Inputs Register */
-
-static int opb_index = 0;
-
-struct opb_pic {
-	struct irq_domain *host;
-	void *regs;
-	int index;
-	spinlock_t lock;
-};
-
-static u32 opb_in(struct opb_pic *opb, int offset)
-{
-	return in_be32(opb->regs + offset);
-}
-
-static void opb_out(struct opb_pic *opb, int offset, u32 val)
-{
-	out_be32(opb->regs + offset, val);
-}
-
-static void opb_unmask_irq(struct irq_data *d)
-{
-	struct opb_pic *opb;
-	unsigned long flags;
-	u32 ier, bitset;
-
-	opb = d->chip_data;
-	bitset = (1 << (31 - irqd_to_hwirq(d)));
-
-	spin_lock_irqsave(&opb->lock, flags);
-
-	ier = opb_in(opb, OPB_MLSIER);
-	opb_out(opb, OPB_MLSIER, ier | bitset);
-	ier = opb_in(opb, OPB_MLSIER);
-
-	spin_unlock_irqrestore(&opb->lock, flags);
-}
-
-static void opb_mask_irq(struct irq_data *d)
-{
-	struct opb_pic *opb;
-	unsigned long flags;
-	u32 ier, mask;
-
-	opb = d->chip_data;
-	mask = ~(1 << (31 - irqd_to_hwirq(d)));
-
-	spin_lock_irqsave(&opb->lock, flags);
-
-	ier = opb_in(opb, OPB_MLSIER);
-	opb_out(opb, OPB_MLSIER, ier & mask);
-	ier = opb_in(opb, OPB_MLSIER); // Flush posted writes
-
-	spin_unlock_irqrestore(&opb->lock, flags);
-}
-
-static void opb_ack_irq(struct irq_data *d)
-{
-	struct opb_pic *opb;
-	unsigned long flags;
-	u32 bitset;
-
-	opb = d->chip_data;
-	bitset = (1 << (31 - irqd_to_hwirq(d)));
-
-	spin_lock_irqsave(&opb->lock, flags);
-
-	opb_out(opb, OPB_MLSIR, bitset);
-	opb_in(opb, OPB_MLSIR); // Flush posted writes
-
-	spin_unlock_irqrestore(&opb->lock, flags);
-}
-
-static void opb_mask_ack_irq(struct irq_data *d)
-{
-	struct opb_pic *opb;
-	unsigned long flags;
-	u32 bitset;
-	u32 ier, ir;
-
-	opb = d->chip_data;
-	bitset = (1 << (31 - irqd_to_hwirq(d)));
-
-	spin_lock_irqsave(&opb->lock, flags);
-
-	ier = opb_in(opb, OPB_MLSIER);
-	opb_out(opb, OPB_MLSIER, ier & ~bitset);
-	ier = opb_in(opb, OPB_MLSIER); // Flush posted writes
-
-	opb_out(opb, OPB_MLSIR, bitset);
-	ir = opb_in(opb, OPB_MLSIR); // Flush posted writes
-
-	spin_unlock_irqrestore(&opb->lock, flags);
-}
-
-static int opb_set_irq_type(struct irq_data *d, unsigned int flow)
-{
-	struct opb_pic *opb;
-	unsigned long flags;
-	int invert, ipr, mask, bit;
-
-	opb = d->chip_data;
-
-	/* The only information we're interested in in the type is whether it's
-	 * a high or low trigger. For high triggered interrupts, the polarity
-	 * set for it in the MLS Interrupt Polarity Register is 0, for low
-	 * interrupts it's 1 so that the proper input in the MLS Interrupt Input
-	 * Register is interrupted as asserting the interrupt. */
-
-	switch (flow) {
-		case IRQ_TYPE_NONE:
-			opb_mask_irq(d);
-			return 0;
-
-		case IRQ_TYPE_LEVEL_HIGH:
-			invert = 0;
-			break;
-
-		case IRQ_TYPE_LEVEL_LOW:
-			invert = 1;
-			break;
-
-		default:
-			return -EINVAL;
-	}
-
-	bit = (1 << (31 - irqd_to_hwirq(d)));
-	mask = ~bit;
-
-	spin_lock_irqsave(&opb->lock, flags);
-
-	ipr = opb_in(opb, OPB_MLSIPR);
-	ipr = (ipr & mask) | (invert ? bit : 0);
-	opb_out(opb, OPB_MLSIPR, ipr);
-	ipr = opb_in(opb, OPB_MLSIPR);  // Flush posted writes
-
-	spin_unlock_irqrestore(&opb->lock, flags);
-
-	/* Record the type in the interrupt descriptor */
-	irqd_set_trigger_type(d, flow);
-
-	return 0;
-}
-
-static struct irq_chip opb_irq_chip = {
-	.name		= "OPB",
-	.irq_mask	= opb_mask_irq,
-	.irq_unmask	= opb_unmask_irq,
-	.irq_mask_ack	= opb_mask_ack_irq,
-	.irq_ack	= opb_ack_irq,
-	.irq_set_type	= opb_set_irq_type
-};
-
-static int opb_host_map(struct irq_domain *host, unsigned int virq,
-		irq_hw_number_t hwirq)
-{
-	struct opb_pic *opb;
-
-	opb = host->host_data;
-
-	/* Most of the important stuff is handled by the generic host code, like
-	 * the lookup, so just attach some info to the virtual irq */
-
-	irq_set_chip_data(virq, opb);
-	irq_set_chip_and_handler(virq, &opb_irq_chip, handle_level_irq);
-	irq_set_irq_type(virq, IRQ_TYPE_NONE);
-
-	return 0;
-}
-
-static const struct irq_domain_ops opb_host_ops = {
-	.map = opb_host_map,
-	.xlate = irq_domain_xlate_twocell,
-};
-
-irqreturn_t opb_irq_handler(int irq, void *private)
-{
-	struct opb_pic *opb;
-	u32 ir, src, subvirq;
-
-	opb = (struct opb_pic *) private;
-
-	/* Read the OPB MLS Interrupt Register for
-	 * asserted interrupts */
-	ir = opb_in(opb, OPB_MLSIR);
-	if (!ir)
-		return IRQ_NONE;
-
-	do {
-		/* Get 1 - 32 source, *NOT* bit */
-		src = 32 - ffs(ir);
-
-		/* Translate from the OPB's conception of interrupt number to
-		 * Linux's virtual IRQ */
-
-		subvirq = irq_linear_revmap(opb->host, src);
-
-		generic_handle_irq(subvirq);
-	} while ((ir = opb_in(opb, OPB_MLSIR)));
-
-	return IRQ_HANDLED;
-}
-
-struct opb_pic *opb_pic_init_one(struct device_node *dn)
-{
-	struct opb_pic *opb;
-	struct resource res;
-
-	if (of_address_to_resource(dn, 0, &res)) {
-		printk(KERN_ERR "opb: Couldn't translate resource\n");
-		return  NULL;
-	}
-
-	opb = kzalloc(sizeof(struct opb_pic), GFP_KERNEL);
-	if (!opb) {
-		printk(KERN_ERR "opb: Failed to allocate opb struct!\n");
-		return NULL;
-	}
-
-	/* Get access to the OPB MMIO registers */
-	opb->regs = ioremap(res.start + 0x10000, 0x1000);
-	if (!opb->regs) {
-		printk(KERN_ERR "opb: Failed to allocate register space!\n");
-		goto free_opb;
-	}
-
-	/* Allocate an irq domain so that Linux knows that despite only
-	 * having one interrupt to issue, we're the controller for multiple
-	 * hardware IRQs, so later we can lookup their virtual IRQs. */
-
-	opb->host = irq_domain_add_linear(dn, OPB_NR_IRQS, &opb_host_ops, opb);
-	if (!opb->host) {
-		printk(KERN_ERR "opb: Failed to allocate IRQ host!\n");
-		goto free_regs;
-	}
-
-	opb->index = opb_index++;
-	spin_lock_init(&opb->lock);
-
-	/* Disable all interrupts by default */
-	opb_out(opb, OPB_MLSASIER, 0);
-	opb_out(opb, OPB_MLSIER, 0);
-
-	/* ACK any interrupts left by FW */
-	opb_out(opb, OPB_MLSIR, 0xFFFFFFFF);
-
-	return opb;
-
-free_regs:
-	iounmap(opb->regs);
-free_opb:
-	kfree(opb);
-	return NULL;
-}
-
-void __init opb_pic_init(void)
-{
-	struct device_node *dn;
-	struct opb_pic *opb;
-	int virq;
-	int rc;
-
-	/* Call init_one for each OPB device */
-	for_each_compatible_node(dn, NULL, "ibm,opb") {
-
-		/* Fill in an OPB struct */
-		opb = opb_pic_init_one(dn);
-		if (!opb) {
-			printk(KERN_WARNING "opb: Failed to init node, skipped!\n");
-			continue;
-		}
-
-		/* Map / get opb's hardware virtual irq */
-		virq = irq_of_parse_and_map(dn, 0);
-		if (virq <= 0) {
-			printk("opb: irq_op_parse_and_map failed!\n");
-			continue;
-		}
-
-		/* Attach opb interrupt handler to new virtual IRQ */
-		rc = request_irq(virq, opb_irq_handler, IRQF_NO_THREAD,
-				 "OPB LS Cascade", opb);
-		if (rc) {
-			printk("opb: request_irq failed: %d\n", rc);
-			continue;
-		}
-
-		printk("OPB%d init with %d IRQs at %p\n", opb->index,
-				OPB_NR_IRQS, opb->regs);
-	}
-}
diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c
deleted file mode 100644
index a87b414c766..00000000000
--- a/arch/powerpc/platforms/wsp/psr2.c
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * Copyright 2008-2011, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/of.h>
-#include <linux/smp.h>
-#include <linux/time.h>
-#include <linux/of_fdt.h>
-
-#include <asm/machdep.h>
-#include <asm/udbg.h>
-
-#include "ics.h"
-#include "wsp.h"
-
-
-static void psr2_spin(void)
-{
-	hard_irq_disable();
-	for (;;)
-		continue;
-}
-
-static void psr2_restart(char *cmd)
-{
-	psr2_spin();
-}
-
-static int __init psr2_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-
-	if (of_flat_dt_is_compatible(root, "ibm,wsp-chroma")) {
-		/* chroma systems also claim they are psr2s */
-		return 0;
-	}
-
-	if (!of_flat_dt_is_compatible(root, "ibm,psr2"))
-		return 0;
-
-	return 1;
-}
-
-define_machine(psr2_md) {
-	.name			= "PSR2 A2",
-	.probe			= psr2_probe,
-	.setup_arch		= wsp_setup_arch,
-	.restart		= psr2_restart,
-	.power_off		= psr2_spin,
-	.halt			= psr2_spin,
-	.calibrate_decr		= generic_calibrate_decr,
-	.init_IRQ		= wsp_setup_irq,
-	.progress		= udbg_progress,
-	.power_save		= book3e_idle,
-};
-
-machine_arch_initcall(psr2_md, wsp_probe_devices);
diff --git a/arch/powerpc/platforms/wsp/scom_smp.c b/arch/powerpc/platforms/wsp/scom_smp.c
deleted file mode 100644
index 268bc899c1f..00000000000
--- a/arch/powerpc/platforms/wsp/scom_smp.c
+++ /dev/null
@@ -1,434 +0,0 @@
-/*
- * SCOM support for A2 platforms
- *
- * Copyright 2007-2011 Benjamin Herrenschmidt, David Gibson,
- *		       Michael Ellerman, IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/cpumask.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-
-#include <asm/cputhreads.h>
-#include <asm/reg_a2.h>
-#include <asm/scom.h>
-#include <asm/udbg.h>
-
-#include "wsp.h"
-
-#define SCOM_RAMC		0x2a		/* Ram Command */
-#define SCOM_RAMC_TGT1_EXT	0x80000000
-#define SCOM_RAMC_SRC1_EXT	0x40000000
-#define SCOM_RAMC_SRC2_EXT	0x20000000
-#define SCOM_RAMC_SRC3_EXT	0x10000000
-#define SCOM_RAMC_ENABLE	0x00080000
-#define SCOM_RAMC_THREADSEL	0x00060000
-#define SCOM_RAMC_EXECUTE	0x00010000
-#define SCOM_RAMC_MSR_OVERRIDE	0x00008000
-#define SCOM_RAMC_MSR_PR	0x00004000
-#define SCOM_RAMC_MSR_GS	0x00002000
-#define SCOM_RAMC_FORCE		0x00001000
-#define SCOM_RAMC_FLUSH		0x00000800
-#define SCOM_RAMC_INTERRUPT	0x00000004
-#define SCOM_RAMC_ERROR		0x00000002
-#define SCOM_RAMC_DONE		0x00000001
-#define SCOM_RAMI		0x29		/* Ram Instruction */
-#define SCOM_RAMIC		0x28		/* Ram Instruction and Command */
-#define SCOM_RAMIC_INSN		0xffffffff00000000
-#define SCOM_RAMD		0x2d		/* Ram Data */
-#define SCOM_RAMDH		0x2e		/* Ram Data High */
-#define SCOM_RAMDL		0x2f		/* Ram Data Low */
-#define SCOM_PCCR0		0x33		/* PC Configuration Register 0 */
-#define SCOM_PCCR0_ENABLE_DEBUG	0x80000000
-#define SCOM_PCCR0_ENABLE_RAM	0x40000000
-#define SCOM_THRCTL		0x30		/* Thread Control and Status */
-#define SCOM_THRCTL_T0_STOP	0x80000000
-#define SCOM_THRCTL_T1_STOP	0x40000000
-#define SCOM_THRCTL_T2_STOP	0x20000000
-#define SCOM_THRCTL_T3_STOP	0x10000000
-#define SCOM_THRCTL_T0_STEP	0x08000000
-#define SCOM_THRCTL_T1_STEP	0x04000000
-#define SCOM_THRCTL_T2_STEP	0x02000000
-#define SCOM_THRCTL_T3_STEP	0x01000000
-#define SCOM_THRCTL_T0_RUN	0x00800000
-#define SCOM_THRCTL_T1_RUN	0x00400000
-#define SCOM_THRCTL_T2_RUN	0x00200000
-#define SCOM_THRCTL_T3_RUN	0x00100000
-#define SCOM_THRCTL_T0_PM	0x00080000
-#define SCOM_THRCTL_T1_PM	0x00040000
-#define SCOM_THRCTL_T2_PM	0x00020000
-#define SCOM_THRCTL_T3_PM	0x00010000
-#define SCOM_THRCTL_T0_UDE	0x00008000
-#define SCOM_THRCTL_T1_UDE	0x00004000
-#define SCOM_THRCTL_T2_UDE	0x00002000
-#define SCOM_THRCTL_T3_UDE	0x00001000
-#define SCOM_THRCTL_ASYNC_DIS	0x00000800
-#define SCOM_THRCTL_TB_DIS	0x00000400
-#define SCOM_THRCTL_DEC_DIS	0x00000200
-#define SCOM_THRCTL_AND		0x31		/* Thread Control and Status */
-#define SCOM_THRCTL_OR		0x32		/* Thread Control and Status */
-
-
-static DEFINE_PER_CPU(scom_map_t, scom_ptrs);
-
-static scom_map_t get_scom(int cpu, struct device_node *np, int *first_thread)
-{
-	scom_map_t scom = per_cpu(scom_ptrs, cpu);
-	int tcpu;
-
-	if (scom_map_ok(scom)) {
-		*first_thread = 0;
-		return scom;
-	}
-
-	*first_thread = 1;
-
-	scom = scom_map_device(np, 0);
-
-	for (tcpu = cpu_first_thread_sibling(cpu);
-	     tcpu <= cpu_last_thread_sibling(cpu); tcpu++)
-		per_cpu(scom_ptrs, tcpu) = scom;
-
-	/* Hack: for the boot core, this will actually get called on
-	 * the second thread up, not the first so our test above will
-	 * set first_thread incorrectly. */
-	if (cpu_first_thread_sibling(cpu) == 0)
-		*first_thread = 0;
-
-	return scom;
-}
-
-static int a2_scom_ram(scom_map_t scom, int thread, u32 insn, int extmask)
-{
-	u64 cmd, mask, val;
-	int n = 0;
-
-	cmd = ((u64)insn << 32) | (((u64)extmask & 0xf) << 28)
-		| ((u64)thread << 17) | SCOM_RAMC_ENABLE | SCOM_RAMC_EXECUTE;
-	mask = SCOM_RAMC_DONE | SCOM_RAMC_INTERRUPT | SCOM_RAMC_ERROR;
-
-	scom_write(scom, SCOM_RAMIC, cmd);
-
-	for (;;) {
-		if (scom_read(scom, SCOM_RAMC, &val) != 0) {
-			pr_err("SCOM error on instruction 0x%08x, thread %d\n",
-			       insn, thread);
-			return -1;
-		}
-		if (val & mask)
-			break;
-		pr_devel("Waiting on RAMC = 0x%llx\n", val);
-		if (++n == 3) {
-			pr_err("RAMC timeout on instruction 0x%08x, thread %d\n",
-			       insn, thread);
-			return -1;
-		}
-	}
-
-	if (val & SCOM_RAMC_INTERRUPT) {
-		pr_err("RAMC interrupt on instruction 0x%08x, thread %d\n",
-		       insn, thread);
-		return -SCOM_RAMC_INTERRUPT;
-	}
-
-	if (val & SCOM_RAMC_ERROR) {
-		pr_err("RAMC error on instruction 0x%08x, thread %d\n",
-		       insn, thread);
-		return -SCOM_RAMC_ERROR;
-	}
-
-	return 0;
-}
-
-static int a2_scom_getgpr(scom_map_t scom, int thread, int gpr, int alt,
-			  u64 *out_gpr)
-{
-	int rc;
-
-	/* or rN, rN, rN */
-	u32 insn = 0x7c000378 | (gpr << 21) | (gpr << 16) | (gpr << 11);
-	rc = a2_scom_ram(scom, thread, insn, alt ? 0xf : 0x0);
-	if (rc)
-		return rc;
-
-	return scom_read(scom, SCOM_RAMD, out_gpr);
-}
-
-static int a2_scom_getspr(scom_map_t scom, int thread, int spr, u64 *out_spr)
-{
-	int rc, sprhi, sprlo;
-	u32 insn;
-
-	sprhi = spr >> 5;
-	sprlo = spr & 0x1f;
-	insn = 0x7c2002a6 | (sprlo << 16) | (sprhi << 11); /* mfspr r1,spr */
-
-	if (spr == 0x0ff0)
-		insn = 0x7c2000a6; /* mfmsr r1 */
-
-	rc = a2_scom_ram(scom, thread, insn, 0xf);
-	if (rc)
-		return rc;
-	return a2_scom_getgpr(scom, thread, 1, 1, out_spr);
-}
-
-static int a2_scom_setgpr(scom_map_t scom, int thread, int gpr,
-			  int alt, u64 val)
-{
-	u32 lis = 0x3c000000 | (gpr << 21);
-	u32 li = 0x38000000 | (gpr << 21);
-	u32 oris = 0x64000000 | (gpr << 21) | (gpr << 16);
-	u32 ori = 0x60000000 | (gpr << 21) | (gpr << 16);
-	u32 rldicr32 = 0x780007c6 | (gpr << 21) | (gpr << 16);
-	u32 highest = val >> 48;
-	u32 higher = (val >> 32) & 0xffff;
-	u32 high = (val >> 16) & 0xffff;
-	u32 low = val & 0xffff;
-	int lext = alt ? 0x8 : 0x0;
-	int oext = alt ? 0xf : 0x0;
-	int rc = 0;
-
-	if (highest)
-		rc |= a2_scom_ram(scom, thread, lis | highest, lext);
-
-	if (higher) {
-		if (highest)
-			rc |= a2_scom_ram(scom, thread, oris | higher, oext);
-		else
-			rc |= a2_scom_ram(scom, thread, li | higher, lext);
-	}
-
-	if (highest || higher)
-		rc |= a2_scom_ram(scom, thread, rldicr32, oext);
-
-	if (high) {
-		if (highest || higher)
-			rc |= a2_scom_ram(scom, thread, oris | high, oext);
-		else
-			rc |= a2_scom_ram(scom, thread, lis | high, lext);
-	}
-
-	if (highest || higher || high)
-		rc |= a2_scom_ram(scom, thread, ori | low, oext);
-	else
-		rc |= a2_scom_ram(scom, thread, li | low, lext);
-
-	return rc;
-}
-
-static int a2_scom_setspr(scom_map_t scom, int thread, int spr, u64 val)
-{
-	int sprhi = spr >> 5;
-	int sprlo = spr & 0x1f;
-	/* mtspr spr, r1 */
-	u32 insn = 0x7c2003a6 | (sprlo << 16) | (sprhi << 11);
-
-	if (spr == 0x0ff0)
-		insn = 0x7c200124; /* mtmsr r1 */
-
-	if (a2_scom_setgpr(scom, thread, 1, 1, val))
-		return -1;
-
-	return a2_scom_ram(scom, thread, insn, 0xf);
-}
-
-static int a2_scom_initial_tlb(scom_map_t scom, int thread)
-{
-	extern u32 a2_tlbinit_code_start[], a2_tlbinit_code_end[];
-	extern u32 a2_tlbinit_after_iprot_flush[];
-	extern u32 a2_tlbinit_after_linear_map[];
-	u32 assoc, entries, i;
-	u64 epn, tlbcfg;
-	u32 *p;
-	int rc;
-
-	/* Invalidate all entries (including iprot) */
-
-	rc = a2_scom_getspr(scom, thread, SPRN_TLB0CFG, &tlbcfg);
-	if (rc)
-		goto scom_fail;
-	entries = tlbcfg & TLBnCFG_N_ENTRY;
-	assoc = (tlbcfg & TLBnCFG_ASSOC) >> 24;
-	epn = 0;
-
-	/* Set MMUCR2 to enable 4K, 64K, 1M, 16M and 1G pages */
-	a2_scom_setspr(scom, thread, SPRN_MMUCR2, 0x000a7531);
-	/* Set MMUCR3 to write all thids bit to the TLB */
-	a2_scom_setspr(scom, thread, SPRN_MMUCR3, 0x0000000f);
-
-	/* Set MAS1 for 1G page size, and MAS2 to our initial EPN */
-	a2_scom_setspr(scom, thread, SPRN_MAS1, MAS1_TSIZE(BOOK3E_PAGESZ_1GB));
-	a2_scom_setspr(scom, thread, SPRN_MAS2, epn);
-	for (i = 0; i < entries; i++) {
-
-		a2_scom_setspr(scom, thread, SPRN_MAS0, MAS0_ESEL(i % assoc));
-
-		/* tlbwe */
-		rc = a2_scom_ram(scom, thread, 0x7c0007a4, 0);
-		if (rc)
-			goto scom_fail;
-
-		/* Next entry is new address? */
-		if((i + 1) % assoc == 0) {
-			epn += (1 << 30);
-			a2_scom_setspr(scom, thread, SPRN_MAS2, epn);
-		}
-	}
-
-	/* Setup args for linear mapping */
-	rc = a2_scom_setgpr(scom, thread, 3, 0, MAS0_TLBSEL(0));
-	if (rc)
-		goto scom_fail;
-
-	/* Linear mapping */
-	for (p = a2_tlbinit_code_start; p < a2_tlbinit_after_linear_map; p++) {
-		rc = a2_scom_ram(scom, thread, *p, 0);
-		if (rc)
-			goto scom_fail;
-	}
-
-	/*
-	 * For the boot thread, between the linear mapping and the debug
-	 * mappings there is a loop to flush iprot mappings. Ramming doesn't do
-	 * branches, but the secondary threads don't need to be nearly as smart
-	 * (i.e. we don't need to worry about invalidating the mapping we're
-	 * standing on).
-	 */
-
-	/* Debug mappings. Expects r11 = MAS0 from linear map (set above) */
-	for (p = a2_tlbinit_after_iprot_flush; p < a2_tlbinit_code_end; p++) {
-		rc = a2_scom_ram(scom, thread, *p, 0);
-		if (rc)
-			goto scom_fail;
-	}
-
-scom_fail:
-	if (rc)
-		pr_err("Setting up initial TLB failed, err %d\n", rc);
-
-	if (rc == -SCOM_RAMC_INTERRUPT) {
-		/* Interrupt, dump some status */
-		int rc[10];
-		u64 iar, srr0, srr1, esr, mas0, mas1, mas2, mas7_3, mas8, ccr2;
-		rc[0] = a2_scom_getspr(scom, thread, SPRN_IAR, &iar);
-		rc[1] = a2_scom_getspr(scom, thread, SPRN_SRR0, &srr0);
-		rc[2] = a2_scom_getspr(scom, thread, SPRN_SRR1, &srr1);
-		rc[3] = a2_scom_getspr(scom, thread, SPRN_ESR, &esr);
-		rc[4] = a2_scom_getspr(scom, thread, SPRN_MAS0, &mas0);
-		rc[5] = a2_scom_getspr(scom, thread, SPRN_MAS1, &mas1);
-		rc[6] = a2_scom_getspr(scom, thread, SPRN_MAS2, &mas2);
-		rc[7] = a2_scom_getspr(scom, thread, SPRN_MAS7_MAS3, &mas7_3);
-		rc[8] = a2_scom_getspr(scom, thread, SPRN_MAS8, &mas8);
-		rc[9] = a2_scom_getspr(scom, thread, SPRN_A2_CCR2, &ccr2);
-		pr_err(" -> retreived IAR =0x%llx (err %d)\n", iar, rc[0]);
-		pr_err("    retreived SRR0=0x%llx (err %d)\n", srr0, rc[1]);
-		pr_err("    retreived SRR1=0x%llx (err %d)\n", srr1, rc[2]);
-		pr_err("    retreived ESR =0x%llx (err %d)\n", esr, rc[3]);
-		pr_err("    retreived MAS0=0x%llx (err %d)\n", mas0, rc[4]);
-		pr_err("    retreived MAS1=0x%llx (err %d)\n", mas1, rc[5]);
-		pr_err("    retreived MAS2=0x%llx (err %d)\n", mas2, rc[6]);
-		pr_err("    retreived MS73=0x%llx (err %d)\n", mas7_3, rc[7]);
-		pr_err("    retreived MAS8=0x%llx (err %d)\n", mas8, rc[8]);
-		pr_err("    retreived CCR2=0x%llx (err %d)\n", ccr2, rc[9]);
-	}
-
-	return rc;
-}
-
-int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx, struct device_node *np)
-{
-	u64 init_iar, init_msr, init_ccr2;
-	unsigned long start_here;
-	int rc, core_setup;
-	scom_map_t scom;
-	u64 pccr0;
-
-	scom = get_scom(lcpu, np, &core_setup);
-	if (!scom) {
-		printk(KERN_ERR "Couldn't map SCOM for CPU%d\n", lcpu);
-		return -1;
-	}
-
-	pr_devel("Bringing up CPU%d using SCOM...\n", lcpu);
-
-	if (scom_read(scom, SCOM_PCCR0, &pccr0) != 0) {
-		printk(KERN_ERR "XSCOM failure readng PCCR0 on CPU%d\n", lcpu);
-		return -1;
-	}
-	scom_write(scom, SCOM_PCCR0, pccr0 | SCOM_PCCR0_ENABLE_DEBUG |
-				     SCOM_PCCR0_ENABLE_RAM);
-
-	/* Stop the thead with THRCTL. If we are setting up the TLB we stop all
-	 * threads. We also disable asynchronous interrupts while RAMing.
-	 */
-	if (core_setup)
-		scom_write(scom, SCOM_THRCTL_OR,
-			      SCOM_THRCTL_T0_STOP |
-			      SCOM_THRCTL_T1_STOP |
-			      SCOM_THRCTL_T2_STOP |
-			      SCOM_THRCTL_T3_STOP |
-			      SCOM_THRCTL_ASYNC_DIS);
-	else
-		scom_write(scom, SCOM_THRCTL_OR, SCOM_THRCTL_T0_STOP >> thr_idx);
-
-	/* Flush its pipeline just in case */
-	scom_write(scom, SCOM_RAMC, ((u64)thr_idx << 17) |
-		      SCOM_RAMC_FLUSH | SCOM_RAMC_ENABLE);
-
-	a2_scom_getspr(scom, thr_idx, SPRN_IAR, &init_iar);
-	a2_scom_getspr(scom, thr_idx, 0x0ff0, &init_msr);
-	a2_scom_getspr(scom, thr_idx, SPRN_A2_CCR2, &init_ccr2);
-
-	/* Set MSR to MSR_CM (0x0ff0 is magic value for MSR_CM) */
-	rc = a2_scom_setspr(scom, thr_idx, 0x0ff0, MSR_CM);
-	if (rc) {
-		pr_err("Failed to set MSR ! err %d\n", rc);
-		return rc;
-	}
-
-	/* RAM in an sync/isync for the sake of it */
-	a2_scom_ram(scom, thr_idx, 0x7c0004ac, 0);
-	a2_scom_ram(scom, thr_idx, 0x4c00012c, 0);
-
-	if (core_setup) {
-		pr_devel("CPU%d is first thread in core, initializing TLB...\n",
-			 lcpu);
-		rc = a2_scom_initial_tlb(scom, thr_idx);
-		if (rc)
-			goto fail;
-	}
-
-	start_here = *(unsigned long *)(core_setup ? generic_secondary_smp_init
-					: generic_secondary_thread_init);
-	pr_devel("CPU%d entry point at 0x%lx...\n", lcpu, start_here);
-
-	rc |= a2_scom_setspr(scom, thr_idx, SPRN_IAR, start_here);
-	rc |= a2_scom_setgpr(scom, thr_idx, 3, 0,
-			     get_hard_smp_processor_id(lcpu));
-	/*
-	 * Tell book3e_secondary_core_init not to set up the TLB, we've
-	 * already done that.
-	 */
-	rc |= a2_scom_setgpr(scom, thr_idx, 4, 0, 1);
-
-	rc |= a2_scom_setspr(scom, thr_idx, SPRN_TENS, 0x1 << thr_idx);
-
-	scom_write(scom, SCOM_RAMC, 0);
-	scom_write(scom, SCOM_THRCTL_AND, ~(SCOM_THRCTL_T0_STOP >> thr_idx));
-	scom_write(scom, SCOM_PCCR0, pccr0);
-fail:
-	pr_devel("  SCOM initialization %s\n", rc ? "failed" : "succeeded");
-	if (rc) {
-		pr_err("Old IAR=0x%08llx MSR=0x%08llx CCR2=0x%08llx\n",
-		       init_iar, init_msr, init_ccr2);
-	}
-
-	return rc;
-}
diff --git a/arch/powerpc/platforms/wsp/scom_wsp.c b/arch/powerpc/platforms/wsp/scom_wsp.c
deleted file mode 100644
index 6538b4de34f..00000000000
--- a/arch/powerpc/platforms/wsp/scom_wsp.c
+++ /dev/null
@@ -1,82 +0,0 @@
-/*
- *  SCOM backend for WSP
- *
- *  Copyright 2010 Benjamin Herrenschmidt, IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-
-#include <linux/cpumask.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-#include <linux/of_address.h>
-
-#include <asm/cputhreads.h>
-#include <asm/reg_a2.h>
-#include <asm/scom.h>
-#include <asm/udbg.h>
-
-#include "wsp.h"
-
-
-static scom_map_t wsp_scom_map(struct device_node *dev, u64 reg, u64 count)
-{
-	struct resource r;
-	u64 xscom_addr;
-
-	if (!of_get_property(dev, "scom-controller", NULL)) {
-		pr_err("%s: device %s is not a SCOM controller\n",
-			__func__, dev->full_name);
-		return SCOM_MAP_INVALID;
-	}
-
-	if (of_address_to_resource(dev, 0, &r)) {
-		pr_debug("Failed to find SCOM controller address\n");
-		return 0;
-	}
-
-	/* Transform the SCOM address into an XSCOM offset */
-	xscom_addr = ((reg & 0x7f000000) >> 1) | ((reg & 0xfffff) << 3);
-
-	return (scom_map_t)ioremap(r.start + xscom_addr, count << 3);
-}
-
-static void wsp_scom_unmap(scom_map_t map)
-{
-	iounmap((void *)map);
-}
-
-static int wsp_scom_read(scom_map_t map, u64 reg, u64 *value)
-{
-	u64 __iomem *addr = (u64 __iomem *)map;
-
-	*value = in_be64(addr + reg);
-
-	return 0;
-}
-
-static int wsp_scom_write(scom_map_t map, u64 reg, u64 value)
-{
-	u64 __iomem *addr = (u64 __iomem *)map;
-
-	out_be64(addr + reg, value);
-
-	return 0;
-}
-
-static const struct scom_controller wsp_scom_controller = {
-	.map	= wsp_scom_map,
-	.unmap	= wsp_scom_unmap,
-	.read	= wsp_scom_read,
-	.write	= wsp_scom_write
-};
-
-void scom_init_wsp(void)
-{
-	scom_init(&wsp_scom_controller);
-}
diff --git a/arch/powerpc/platforms/wsp/setup.c b/arch/powerpc/platforms/wsp/setup.c
deleted file mode 100644
index 11ac2f05e01..00000000000
--- a/arch/powerpc/platforms/wsp/setup.c
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * Copyright 2010 Michael Ellerman, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/of_platform.h>
-
-#include "wsp.h"
-
-/*
- * Find chip-id by walking up device tree looking for ibm,wsp-chip-id property.
- * Won't work for nodes that are not a descendant of a wsp node.
- */
-int wsp_get_chip_id(struct device_node *dn)
-{
-	const u32 *p;
-	int rc;
-
-	/* Start looking at the specified node, not its parent */
-	dn = of_node_get(dn);
-	while (dn && !(p = of_get_property(dn, "ibm,wsp-chip-id", NULL)))
-		dn = of_get_next_parent(dn);
-
-	if (!dn)
-		return -1;
-
-	rc = *p;
-	of_node_put(dn);
-
-	return rc;
-}
diff --git a/arch/powerpc/platforms/wsp/smp.c b/arch/powerpc/platforms/wsp/smp.c
deleted file mode 100644
index 332a18b8140..00000000000
--- a/arch/powerpc/platforms/wsp/smp.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- *  SMP Support for A2 platforms
- *
- *  Copyright 2007 Benjamin Herrenschmidt, IBM Corp.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
- */
-
-#include <linux/cpumask.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/smp.h>
-
-#include <asm/dbell.h>
-#include <asm/machdep.h>
-#include <asm/xics.h>
-
-#include "ics.h"
-#include "wsp.h"
-
-static void smp_a2_setup_cpu(int cpu)
-{
-	doorbell_setup_this_cpu();
-
-	if (cpu != boot_cpuid)
-		xics_setup_cpu();
-}
-
-int smp_a2_kick_cpu(int nr)
-{
-	const char *enable_method;
-	struct device_node *np;
-	int thr_idx;
-
-	if (nr < 0 || nr >= NR_CPUS)
-		return -ENOENT;
-
-	np = of_get_cpu_node(nr, &thr_idx);
-	if (!np)
-		return -ENODEV;
-
-	enable_method = of_get_property(np, "enable-method", NULL);
-	pr_devel("CPU%d has enable-method: \"%s\"\n", nr, enable_method);
-
-	if (!enable_method) {
-                printk(KERN_ERR "CPU%d has no enable-method\n", nr);
-		return -ENOENT;
-	} else if (strcmp(enable_method, "ibm,a2-scom") == 0) {
-		if (a2_scom_startup_cpu(nr, thr_idx, np))
-			return -1;
-	} else {
-		printk(KERN_ERR "CPU%d: Don't understand enable-method \"%s\"\n",
-                       nr, enable_method);
-		return -EINVAL;
-	}
-
-	/*
-	 * The processor is currently spinning, waiting for the
-	 * cpu_start field to become non-zero After we set cpu_start,
-	 * the processor will continue on to secondary_start
-	 */
-	paca[nr].cpu_start = 1;
-
-	return 0;
-}
-
-static int __init smp_a2_probe(void)
-{
-	return num_possible_cpus();
-}
-
-static struct smp_ops_t a2_smp_ops = {
-	.message_pass	= NULL,	/* Use smp_muxed_ipi_message_pass */
-	.cause_ipi	= doorbell_cause_ipi,
-	.probe		= smp_a2_probe,
-	.kick_cpu	= smp_a2_kick_cpu,
-	.setup_cpu	= smp_a2_setup_cpu,
-};
-
-void __init a2_setup_smp(void)
-{
-	smp_ops = &a2_smp_ops;
-}
diff --git a/arch/powerpc/platforms/wsp/wsp.c b/arch/powerpc/platforms/wsp/wsp.c
deleted file mode 100644
index 58cd1f00e1e..00000000000
--- a/arch/powerpc/platforms/wsp/wsp.c
+++ /dev/null
@@ -1,117 +0,0 @@
-/*
- * Copyright 2008-2011, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/smp.h>
-#include <linux/delay.h>
-#include <linux/time.h>
-#include <linux/of_address.h>
-
-#include <asm/scom.h>
-
-#include "wsp.h"
-#include "ics.h"
-
-#define WSP_SOC_COMPATIBLE	"ibm,wsp-soc"
-#define PBIC_COMPATIBLE		"ibm,wsp-pbic"
-#define COPRO_COMPATIBLE	"ibm,wsp-coprocessor"
-
-static int __init wsp_probe_buses(void)
-{
-	static __initdata struct of_device_id bus_ids[] = {
-		/*
-		 * every node in between needs to be here or you won't
-		 * find it
-		 */
-		{ .compatible = WSP_SOC_COMPATIBLE, },
-		{ .compatible = PBIC_COMPATIBLE, },
-		{ .compatible = COPRO_COMPATIBLE, },
-		{},
-	};
-	of_platform_bus_probe(NULL, bus_ids, NULL);
-
-	return 0;
-}
-
-void __init wsp_setup_arch(void)
-{
-	/* init to some ~sane value until calibrate_delay() runs */
-	loops_per_jiffy = 50000000;
-
-	scom_init_wsp();
-
-	/* Setup SMP callback */
-#ifdef CONFIG_SMP
-	a2_setup_smp();
-#endif
-#ifdef CONFIG_PCI
-	wsp_setup_pci();
-#endif
-}
-
-void __init wsp_setup_irq(void)
-{
-	wsp_init_irq();
-	opb_pic_init();
-}
-
-
-int __init wsp_probe_devices(void)
-{
-	struct device_node *np;
-
-	/* Our RTC is a ds1500. It seems to be programatically compatible
-	 * with the ds1511 for which we have a driver so let's use that
-	 */
-	np = of_find_compatible_node(NULL, NULL, "dallas,ds1500");
-	if (np != NULL) {
-		struct resource res;
-		if (of_address_to_resource(np, 0, &res) == 0)
-			platform_device_register_simple("ds1511", 0, &res, 1);
-	}
-
-	wsp_probe_buses();
-
-	return 0;
-}
-
-void wsp_halt(void)
-{
-	u64 val;
-	scom_map_t m;
-	struct device_node *dn;
-	struct device_node *mine;
-	struct device_node *me;
-	int rc;
-
-	me = of_get_cpu_node(smp_processor_id(), NULL);
-	mine = scom_find_parent(me);
-
-	/* This will halt all the A2s but not power off the chip */
-	for_each_node_with_property(dn, "scom-controller") {
-		if (dn == mine)
-			continue;
-		m = scom_map(dn, 0, 1);
-
-		/* read-modify-write it so the HW probe does not get
-		 * confused */
-		rc = scom_read(m, 0, &val);
-		if (rc == 0)
-			scom_write(m, 0, val | 1);
-		scom_unmap(m);
-	}
-	m = scom_map(mine, 0, 1);
-	rc = scom_read(m, 0, &val);
-	if (rc == 0)
-		scom_write(m, 0, val | 1);
-	/* should never return */
-	scom_unmap(m);
-}
diff --git a/arch/powerpc/platforms/wsp/wsp.h b/arch/powerpc/platforms/wsp/wsp.h
deleted file mode 100644
index a563a8aaf81..00000000000
--- a/arch/powerpc/platforms/wsp/wsp.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __WSP_H
-#define __WSP_H
-
-#include <asm/wsp.h>
-
-/* Devtree compatible strings for major devices */
-#define PCIE_COMPATIBLE     "ibm,wsp-pciex"
-
-extern void wsp_setup_arch(void);
-extern void wsp_setup_irq(void);
-extern int wsp_probe_devices(void);
-extern void wsp_halt(void);
-
-extern void wsp_setup_pci(void);
-extern void scom_init_wsp(void);
-
-extern void a2_setup_smp(void);
-extern int a2_scom_startup_cpu(unsigned int lcpu, int thr_idx,
-			       struct device_node *np);
-extern int smp_a2_kick_cpu(int nr);
-
-extern void opb_pic_init(void);
-
-/* chroma specific managment */
-extern void wsp_h8_restart(char *cmd);
-extern void wsp_h8_power_off(void);
-extern void __init wsp_setup_h8(void);
-
-#endif /*  __WSP_H */
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c
deleted file mode 100644
index 9a15e5b39bb..00000000000
--- a/arch/powerpc/platforms/wsp/wsp_pci.c
+++ /dev/null
@@ -1,1134 +0,0 @@
-/*
- * Copyright 2010 Ben Herrenschmidt, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#define DEBUG
-
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/delay.h>
-#include <linux/string.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
-#include <linux/debugfs.h>
-
-#include <asm/sections.h>
-#include <asm/io.h>
-#include <asm/prom.h>
-#include <asm/pci-bridge.h>
-#include <asm/machdep.h>
-#include <asm/ppc-pci.h>
-#include <asm/iommu.h>
-#include <asm/io-workarounds.h>
-#include <asm/debug.h>
-
-#include "wsp.h"
-#include "wsp_pci.h"
-#include "msi.h"
-
-
-/* Max number of TVTs for one table. Only 32-bit tables can use
- * multiple TVTs and so the max currently supported is thus 8
- * since only 2G of DMA space is supported
- */
-#define MAX_TABLE_TVT_COUNT		8
-
-struct wsp_dma_table {
-	struct list_head	link;
-	struct iommu_table	table;
-	struct wsp_phb	*phb;
-	struct page		*tces[MAX_TABLE_TVT_COUNT];
-};
-
-/* We support DMA regions from 0...2G in 32bit space (no support for
- * 64-bit DMA just yet). Each device gets a separate TCE table (TVT
- * entry) with validation enabled (though not supported by SimiCS
- * just yet).
- *
- * To simplify things, we divide this 2G space into N regions based
- * on the constant below which could be turned into a tunable eventually
- *
- * We then assign dynamically those regions to devices as they show up.
- *
- * We use a bitmap as an allocator for these.
- *
- * Tables are allocated/created dynamically as devices are discovered,
- * multiple TVT entries are used if needed
- *
- * When 64-bit DMA support is added we should simply use a separate set
- * of larger regions (the HW supports 64 TVT entries). We can
- * additionally create a bypass region in 64-bit space for performances
- * though that would have a cost in term of security.
- *
- * If you set NUM_DMA32_REGIONS to 1, then a single table is shared
- * for all devices and bus/dev/fn validation is disabled
- *
- * Note that a DMA32 region cannot be smaller than 256M so the max
- * supported here for now is 8. We don't yet support sharing regions
- * between multiple devices so the max number of devices supported
- * is MAX_TABLE_TVT_COUNT.
- */
-#define NUM_DMA32_REGIONS	1
-
-struct wsp_phb {
-	struct pci_controller	*hose;
-
-	/* Lock controlling access to the list of dma tables.
-	 * It does -not- protect against dma_* operations on
-	 * those tables, those should be stopped before an entry
-	 * is removed from the list.
-	 *
-	 * The lock is also used for error handling operations
-	 */
-	spinlock_t		lock;
-	struct list_head	dma_tables;
-	unsigned long		dma32_map;
-	unsigned long		dma32_base;
-	unsigned int		dma32_num_regions;
-	unsigned long		dma32_region_size;
-
-	/* Debugfs stuff */
-	struct dentry		*ddir;
-
-	struct list_head	all;
-};
-static LIST_HEAD(wsp_phbs);
-
-//#define cfg_debug(fmt...)	pr_debug(fmt)
-#define cfg_debug(fmt...)
-
-
-static int wsp_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
-				  int offset, int len, u32 *val)
-{
-	struct pci_controller *hose;
-	int suboff;
-	u64 addr;
-
-	hose = pci_bus_to_host(bus);
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	if (offset >= 0x1000)
-		return  PCIBIOS_BAD_REGISTER_NUMBER;
-	addr = PCIE_REG_CA_ENABLE |
-		((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT |
-		((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT |
-		((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT;
-	suboff = offset & 3;
-
-	/*
-	 * Note: the caller has already checked that offset is
-	 * suitably aligned and that len is 1, 2 or 4.
-	 */
-
-	switch (len) {
-	case 1:
-		addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT;
-		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
-		*val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA)
-			>> (suboff << 3)) & 0xff;
-		cfg_debug("read 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n",
-			  bus->number, devfn >> 3, devfn & 7,
-			  offset, suboff, addr, *val);
-		break;
-	case 2:
-		addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT;
-		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
-		*val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA)
-			>> (suboff << 3)) & 0xffff;
-		cfg_debug("read 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n",
-			  bus->number, devfn >> 3, devfn & 7,
-			  offset, suboff, addr, *val);
-		break;
-	default:
-		addr |= 0xful << PCIE_REG_CA_BE_SHIFT;
-		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
-		*val = in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA);
-		cfg_debug("read 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n",
-			  bus->number, devfn >> 3, devfn & 7,
-			  offset, suboff, addr, *val);
-		break;
-	}
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static int wsp_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
-				   int offset, int len, u32 val)
-{
-	struct pci_controller *hose;
-	int suboff;
-	u64 addr;
-
-	hose = pci_bus_to_host(bus);
-	if (hose == NULL)
-		return PCIBIOS_DEVICE_NOT_FOUND;
-	if (offset >= 0x1000)
-		return  PCIBIOS_BAD_REGISTER_NUMBER;
-	addr = PCIE_REG_CA_ENABLE |
-		((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT |
-		((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT |
-		((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT;
-	suboff = offset & 3;
-
-	/*
-	 * Note: the caller has already checked that offset is
-	 * suitably aligned and that len is 1, 2 or 4.
-	 */
-	switch (len) {
-	case 1:
-		addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT;
-		val <<= suboff << 3;
-		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
-		out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
-		cfg_debug("write 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n",
-			  bus->number, devfn >> 3, devfn & 7,
-			  offset, suboff, addr, val);
-		break;
-	case 2:
-		addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT;
-		val <<= suboff << 3;
-		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
-		out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
-		cfg_debug("write 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n",
-			  bus->number, devfn >> 3, devfn & 7,
-			  offset, suboff, addr, val);
-		break;
-	default:
-		addr |= 0xful << PCIE_REG_CA_BE_SHIFT;
-		out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
-		out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
-		cfg_debug("write 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n",
-			  bus->number, devfn >> 3, devfn & 7,
-			  offset, suboff, addr, val);
-		break;
-	}
-	return PCIBIOS_SUCCESSFUL;
-}
-
-static struct pci_ops wsp_pcie_pci_ops =
-{
-	.read = wsp_pcie_read_config,
-	.write = wsp_pcie_write_config,
-};
-
-#define TCE_SHIFT		12
-#define TCE_PAGE_SIZE		(1 << TCE_SHIFT)
-#define TCE_PCI_WRITE		0x2		 /* write from PCI allowed */
-#define TCE_PCI_READ		0x1	 	 /* read from PCI allowed */
-#define TCE_RPN_MASK		0x3fffffffffful  /* 42-bit RPN (4K pages) */
-#define TCE_RPN_SHIFT		12
-
-//#define dma_debug(fmt...)	pr_debug(fmt)
-#define dma_debug(fmt...)
-
-static int tce_build_wsp(struct iommu_table *tbl, long index, long npages,
-			   unsigned long uaddr, enum dma_data_direction direction,
-			   struct dma_attrs *attrs)
-{
-	struct wsp_dma_table *ptbl = container_of(tbl,
-						    struct wsp_dma_table,
-						    table);
-	u64 proto_tce;
-	u64 *tcep;
-	u64 rpn;
-
-	proto_tce = TCE_PCI_READ;
-#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
-	proto_tce |= TCE_PCI_WRITE;
-#else
-	if (direction != DMA_TO_DEVICE)
-		proto_tce |= TCE_PCI_WRITE;
-#endif
-
-	/* XXX Make this faster by factoring out the page address for
-	 * within a TCE table
-	 */
-	while (npages--) {
-		/* We don't use it->base as the table can be scattered */
-		tcep = (u64 *)page_address(ptbl->tces[index >> 16]);
-		tcep += (index & 0xffff);
-
-		/* can't move this out since we might cross LMB boundary */
-		rpn = __pa(uaddr) >> TCE_SHIFT;
-		*tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
-
-		dma_debug("[DMA] TCE %p set to 0x%016llx (dma addr: 0x%lx)\n",
-			  tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT_4K);
-
-		uaddr += TCE_PAGE_SIZE;
-		index++;
-	}
-	return 0;
-}
-
-static void tce_free_wsp(struct iommu_table *tbl, long index, long npages)
-{
-	struct wsp_dma_table *ptbl = container_of(tbl,
-						    struct wsp_dma_table,
-						    table);
-#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
-	struct pci_controller *hose = ptbl->phb->hose;
-#endif
-	u64 *tcep;
-
-	/* XXX Make this faster by factoring out the page address for
-	 * within a TCE table. Also use line-kill option to kill multiple
-	 * TCEs at once
-	 */
-	while (npages--) {
-		/* We don't use it->base as the table can be scattered */
-		tcep = (u64 *)page_address(ptbl->tces[index >> 16]);
-		tcep += (index & 0xffff);
-		dma_debug("[DMA] TCE %p cleared\n", tcep);
-		*tcep = 0;
-#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
-		/* Don't write there since it would pollute other MMIO accesses */
-		out_be64(hose->cfg_data + PCIE_REG_TCE_KILL,
-			 PCIE_REG_TCEKILL_SINGLE | PCIE_REG_TCEKILL_PS_4K |
-			 (__pa(tcep) & PCIE_REG_TCEKILL_ADDR_MASK));
-#endif
-		index++;
-	}
-}
-
-static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb,
-							    unsigned int region,
-							    struct pci_dev *validate)
-{
-	struct pci_controller *hose = phb->hose;
-	unsigned long size = phb->dma32_region_size;
-	unsigned long addr = phb->dma32_region_size * region + phb->dma32_base;
-	struct wsp_dma_table *tbl;
-	int tvts_per_table, i, tvt, nid;
-	unsigned long flags;
-
-	nid = of_node_to_nid(phb->hose->dn);
-
-	/* Calculate how many TVTs are needed */
-	tvts_per_table = size / 0x10000000;
-	if (tvts_per_table == 0)
-		tvts_per_table = 1;
-
-	/* Calculate the base TVT index. We know all tables have the same
-	 * size so we just do a simple multiply here
-	 */
-	tvt = region * tvts_per_table;
-
-	pr_debug("         Region : %d\n", region);
-	pr_debug("      DMA range : 0x%08lx..0x%08lx\n", addr, addr + size - 1);
-	pr_debug(" Number of TVTs : %d\n", tvts_per_table);
-	pr_debug("       Base TVT : %d\n", tvt);
-	pr_debug("         Node   : %d\n", nid);
-
-	tbl = kzalloc_node(sizeof(struct wsp_dma_table), GFP_KERNEL, nid);
-	if (!tbl)
-		return ERR_PTR(-ENOMEM);
-	tbl->phb = phb;
-
-	/* Create as many TVTs as needed, each represents 256M at most */
-	for (i = 0; i < tvts_per_table; i++) {
-		u64 tvt_data1, tvt_data0;
-
-		/* Allocate table. We use a 4K TCE size for now always so
-		 * one table is always 8 * (258M / 4K) == 512K
-		 */
-		tbl->tces[i] = alloc_pages_node(nid, GFP_KERNEL, get_order(0x80000));
-		if (tbl->tces[i] == NULL)
-			goto fail;
-		memset(page_address(tbl->tces[i]), 0, 0x80000);
-
-		pr_debug(" TCE table %d at : %p\n", i, page_address(tbl->tces[i]));
-
-		/* Table size. We currently set it to be the whole 256M region */
-		tvt_data0 = 2ull << IODA_TVT0_TCE_TABLE_SIZE_SHIFT;
-		/* IO page size set to 4K */
-		tvt_data1 = 1ull << IODA_TVT1_IO_PAGE_SIZE_SHIFT;
-		/* Shift in the address */
-		tvt_data0 |= __pa(page_address(tbl->tces[i])) << IODA_TVT0_TTA_SHIFT;
-
-		/* Validation stuff. We only validate fully bus/dev/fn for now
-		 * one day maybe we can group devices but that isn't the case
-		 * at the moment
-		 */
-		if (validate) {
-			tvt_data0 |= IODA_TVT0_BUSNUM_VALID_MASK;
-			tvt_data0 |= validate->bus->number;
-			tvt_data1 |= IODA_TVT1_DEVNUM_VALID;
-			tvt_data1 |= ((u64)PCI_SLOT(validate->devfn))
-				<< IODA_TVT1_DEVNUM_VALUE_SHIFT;
-			tvt_data1 |= IODA_TVT1_FUNCNUM_VALID;
-			tvt_data1 |= ((u64)PCI_FUNC(validate->devfn))
-				<< IODA_TVT1_FUNCNUM_VALUE_SHIFT;
-		}
-
-		/* XX PE number is always 0 for now */
-
-		/* Program the values using the PHB lock */
-		spin_lock_irqsave(&phb->lock, flags);
-		out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR,
-			 (tvt + i) | PCIE_REG_IODA_AD_TBL_TVT);
-		out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, tvt_data1);
-		out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, tvt_data0);
-		spin_unlock_irqrestore(&phb->lock, flags);
-	}
-
-	/* Init bits and pieces */
-	tbl->table.it_blocksize = 16;
-	tbl->table.it_page_shift = IOMMU_PAGE_SHIFT_4K;
-	tbl->table.it_offset = addr >> tbl->table.it_page_shift;
-	tbl->table.it_size = size >> tbl->table.it_page_shift;
-
-	/*
-	 * It's already blank but we clear it anyway.
-	 * Consider an aditiona interface that makes cleaing optional
-	 */
-	iommu_init_table(&tbl->table, nid);
-
-	list_add(&tbl->link, &phb->dma_tables);
-	return tbl;
-
- fail:
-	pr_debug("  Failed to allocate a 256M TCE table !\n");
-	for (i = 0; i < tvts_per_table; i++)
-		if (tbl->tces[i])
-			__free_pages(tbl->tces[i], get_order(0x80000));
-	kfree(tbl);
-	return ERR_PTR(-ENOMEM);
-}
-
-static void wsp_pci_dma_dev_setup(struct pci_dev *pdev)
-{
-	struct dev_archdata *archdata = &pdev->dev.archdata;
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct wsp_phb *phb = hose->private_data;
-	struct wsp_dma_table *table = NULL;
-	unsigned long flags;
-	int i;
-
-	/* Don't assign an iommu table to a bridge */
-	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
-		return;
-
-	pr_debug("%s: Setting up DMA...\n", pci_name(pdev));
-
-	spin_lock_irqsave(&phb->lock, flags);
-
-	/* If only one region, check if it already exist */
-	if (phb->dma32_num_regions == 1) {
-		spin_unlock_irqrestore(&phb->lock, flags);
-		if (list_empty(&phb->dma_tables))
-			table = wsp_pci_create_dma32_table(phb, 0, NULL);
-		else
-			table = list_first_entry(&phb->dma_tables,
-						 struct wsp_dma_table,
-						 link);
-	} else {
-		/* else find a free region */
-		for (i = 0; i < phb->dma32_num_regions && !table; i++) {
-			if (__test_and_set_bit(i, &phb->dma32_map))
-				continue;
-			spin_unlock_irqrestore(&phb->lock, flags);
-			table = wsp_pci_create_dma32_table(phb, i, pdev);
-		}
-	}
-
-	/* Check if we got an error */
-	if (IS_ERR(table)) {
-		pr_err("%s: Failed to create DMA table, err %ld !\n",
-		       pci_name(pdev), PTR_ERR(table));
-		return;
-	}
-
-	/* Or a valid table */
-	if (table) {
-		pr_info("%s: Setup iommu: 32-bit DMA region 0x%08lx..0x%08lx\n",
-			pci_name(pdev),
-			table->table.it_offset << IOMMU_PAGE_SHIFT_4K,
-			(table->table.it_offset << IOMMU_PAGE_SHIFT_4K)
-			+ phb->dma32_region_size - 1);
-		archdata->dma_data.iommu_table_base = &table->table;
-		return;
-	}
-
-	/* Or no room */
-	spin_unlock_irqrestore(&phb->lock, flags);
-	pr_err("%s: Out of DMA space !\n", pci_name(pdev));
-}
-
-static void __init wsp_pcie_configure_hw(struct pci_controller *hose)
-{
-	u64 val;
-	int i;
-
-#define DUMP_REG(x) \
-	pr_debug("%-30s : 0x%016llx\n", #x, in_be64(hose->cfg_data + x))
-
-	/*
-	 * Some WSP variants  has a bogus class code by default in the PCI-E
-	 * root complex's built-in P2P bridge
-	 */
-	val = in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1);
-	pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", val);
-	out_be64(hose->cfg_data + PCIE_REG_SYS_CFG1,
-		 (val & ~PCIE_REG_SYS_CFG1_CLASS_CODE) | (PCI_CLASS_BRIDGE_PCI << 8));
-	pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1));
-
-#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
-	/* XXX Disable TCE caching, it doesn't work on DD1 */
-	out_be64(hose->cfg_data + 0xe50,
-		 in_be64(hose->cfg_data + 0xe50) | (3ull << 62));
-	printk("PCI-E DEBUG CONTROL 5 = 0x%llx\n", in_be64(hose->cfg_data + 0xe50));
-#endif
-
-	/* Configure M32A and IO. IO is hard wired to be 1M for now */
-	out_be64(hose->cfg_data + PCIE_REG_IO_BASE_ADDR, hose->io_base_phys);
-	out_be64(hose->cfg_data + PCIE_REG_IO_BASE_MASK,
-		 (~(hose->io_resource.end - hose->io_resource.start)) &
-		 0x3fffffff000ul);
-	out_be64(hose->cfg_data + PCIE_REG_IO_START_ADDR, 0 | 1);
-
-	out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_ADDR,
-		 hose->mem_resources[0].start);
-	printk("Want to write to M32A_BASE_MASK : 0x%llx\n",
-		 (~(hose->mem_resources[0].end -
-		    hose->mem_resources[0].start)) & 0x3ffffff0000ul);
-	out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_MASK,
-		 (~(hose->mem_resources[0].end -
-		    hose->mem_resources[0].start)) & 0x3ffffff0000ul);
-	out_be64(hose->cfg_data + PCIE_REG_M32A_START_ADDR,
-		 (hose->mem_resources[0].start - hose->mem_offset[0]) | 1);
-
-	/* Clear all TVT entries
-	 *
-	 * XX Might get TVT count from device-tree
-	 */
-	for (i = 0; i < IODA_TVT_COUNT; i++) {
-		out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR,
-			 PCIE_REG_IODA_AD_TBL_TVT | i);
-		out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, 0);
-		out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, 0);
-	}
-
-	/* Kill the TCE cache */
-	out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG,
-		 in_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG) |
-		 PCIE_REG_PHBC_64B_TCE_EN);
-
-	/* Enable 32 & 64-bit MSIs, IO space and M32A */
-	val = PCIE_REG_PHBC_32BIT_MSI_EN |
-	      PCIE_REG_PHBC_IO_EN |
-	      PCIE_REG_PHBC_64BIT_MSI_EN |
-	      PCIE_REG_PHBC_M32A_EN;
-	if (iommu_is_off)
-		val |= PCIE_REG_PHBC_DMA_XLATE_BYPASS;
-	pr_debug("Will write config: 0x%llx\n", val);
-	out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG, val);
-
-	/* Enable error reporting */
-	out_be64(hose->cfg_data + 0xe00,
-		 in_be64(hose->cfg_data + 0xe00) | 0x0008000000000000ull);
-
-	/* Mask an error that's generated when doing config space probe
-	 *
-	 * XXX Maybe we should only mask it around config space cycles... that or
-	 * ignore it when we know we had a config space cycle recently ?
-	 */
-	out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS_MASK, 0x8000000000000000ull);
-	out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS_MASK, 0x8000000000000000ull);
-
-	/* Enable UTL errors, for now, all of them got to UTL irq 1
-	 *
-	 * We similarily mask one UTL error caused apparently during normal
-	 * probing. We also mask the link up error
-	 */
-	out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_ERR_SEV, 0);
-	out_be64(hose->cfg_data + PCIE_UTL_RC_ERR_SEVERITY, 0);
-	out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_ERROR_SEV, 0);
-	out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_IRQ_EN, 0xffffffff00000000ull);
-	out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_IRQ_EN, 0xff5fffff00000000ull);
-	out_be64(hose->cfg_data + PCIE_UTL_EP_ERR_IRQ_EN, 0xffffffff00000000ull);
-
-	DUMP_REG(PCIE_REG_IO_BASE_ADDR);
-	DUMP_REG(PCIE_REG_IO_BASE_MASK);
-	DUMP_REG(PCIE_REG_IO_START_ADDR);
-	DUMP_REG(PCIE_REG_M32A_BASE_ADDR);
-	DUMP_REG(PCIE_REG_M32A_BASE_MASK);
-	DUMP_REG(PCIE_REG_M32A_START_ADDR);
-	DUMP_REG(PCIE_REG_M32B_BASE_ADDR);
-	DUMP_REG(PCIE_REG_M32B_BASE_MASK);
-	DUMP_REG(PCIE_REG_M32B_START_ADDR);
-	DUMP_REG(PCIE_REG_M64_BASE_ADDR);
-	DUMP_REG(PCIE_REG_M64_BASE_MASK);
-	DUMP_REG(PCIE_REG_M64_START_ADDR);
-	DUMP_REG(PCIE_REG_PHB_CONFIG);
-}
-
-static void wsp_pci_wait_io_idle(struct wsp_phb *phb, unsigned long port)
-{
-	u64 val;
-	int i;
-
-	for (i = 0; i < 10000; i++) {
-		val = in_be64(phb->hose->cfg_data + 0xe08);
-		if ((val & 0x1900000000000000ull) == 0x0100000000000000ull)
-			return;
-		udelay(1);
-	}
-	pr_warning("PCI IO timeout on domain %d port 0x%lx\n",
-		   phb->hose->global_number, port);
-}
-
-#define DEF_PCI_AC_RET_pio(name, ret, at, al, aa)		\
-static ret wsp_pci_##name at					\
-{								\
-	struct iowa_bus *bus;					\
-	struct wsp_phb *phb;					\
-	unsigned long flags;					\
-	ret rval;						\
-	bus = iowa_pio_find_bus(aa);				\
-	WARN_ON(!bus);						\
-	phb = bus->private;					\
-	spin_lock_irqsave(&phb->lock, flags);			\
-	wsp_pci_wait_io_idle(phb, aa);				\
-	rval = __do_##name al;					\
-	spin_unlock_irqrestore(&phb->lock, flags);		\
-	return rval;						\
-}
-
-#define DEF_PCI_AC_NORET_pio(name, at, al, aa)			\
-static void wsp_pci_##name at					\
-{								\
-	struct iowa_bus *bus;					\
-	struct wsp_phb *phb;					\
-	unsigned long flags;					\
-	bus = iowa_pio_find_bus(aa);				\
-	WARN_ON(!bus);						\
-	phb = bus->private;					\
-	spin_lock_irqsave(&phb->lock, flags);			\
-	wsp_pci_wait_io_idle(phb, aa);				\
-	__do_##name al;						\
-	spin_unlock_irqrestore(&phb->lock, flags);		\
-}
-
-#define DEF_PCI_AC_RET_mem(name, ret, at, al, aa)
-#define DEF_PCI_AC_NORET_mem(name, at, al, aa)
-
-#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)		\
-	DEF_PCI_AC_RET_##space(name, ret, at, al, aa)
-
-#define DEF_PCI_AC_NORET(name, at, al, space, aa)		\
-	DEF_PCI_AC_NORET_##space(name, at, al, aa)		\
-
-
-#include <asm/io-defs.h>
-
-#undef DEF_PCI_AC_RET
-#undef DEF_PCI_AC_NORET
-
-static struct ppc_pci_io wsp_pci_iops = {
-	.inb = wsp_pci_inb,
-	.inw = wsp_pci_inw,
-	.inl = wsp_pci_inl,
-	.outb = wsp_pci_outb,
-	.outw = wsp_pci_outw,
-	.outl = wsp_pci_outl,
-	.insb = wsp_pci_insb,
-	.insw = wsp_pci_insw,
-	.insl = wsp_pci_insl,
-	.outsb = wsp_pci_outsb,
-	.outsw = wsp_pci_outsw,
-	.outsl = wsp_pci_outsl,
-};
-
-static int __init wsp_setup_one_phb(struct device_node *np)
-{
-	struct pci_controller *hose;
-	struct wsp_phb *phb;
-
-	pr_info("PCI: Setting up PCIe host bridge 0x%s\n", np->full_name);
-
-	phb = zalloc_maybe_bootmem(sizeof(struct wsp_phb), GFP_KERNEL);
-	if (!phb)
-		return -ENOMEM;
-	hose = pcibios_alloc_controller(np);
-	if (!hose) {
-		/* Can't really free the phb */
-		return -ENOMEM;
-	}
-	hose->private_data = phb;
-	phb->hose = hose;
-
-	INIT_LIST_HEAD(&phb->dma_tables);
-	spin_lock_init(&phb->lock);
-
-	/* XXX Use bus-range property ? */
-	hose->first_busno = 0;
-	hose->last_busno = 0xff;
-
-	/* We use cfg_data as the address for the whole bridge MMIO space
-	 */
-	hose->cfg_data = of_iomap(hose->dn, 0);
-
-	pr_debug("PCIe registers mapped at 0x%p\n", hose->cfg_data);
-
-	/* Get the ranges of the device-tree */
-	pci_process_bridge_OF_ranges(hose, np, 0);
-
-	/* XXX Force re-assigning of everything for now */
-	pci_add_flags(PCI_REASSIGN_ALL_BUS | PCI_REASSIGN_ALL_RSRC |
-		      PCI_ENABLE_PROC_DOMAINS);
-
-	/* Calculate how the TCE space is divided */
-	phb->dma32_base		= 0;
-	phb->dma32_num_regions	= NUM_DMA32_REGIONS;
-	if (phb->dma32_num_regions > MAX_TABLE_TVT_COUNT) {
-		pr_warning("IOMMU: Clamped to %d DMA32 regions\n",
-			   MAX_TABLE_TVT_COUNT);
-		phb->dma32_num_regions = MAX_TABLE_TVT_COUNT;
-	}
-	phb->dma32_region_size	= 0x80000000 / phb->dma32_num_regions;
-
-	BUG_ON(!is_power_of_2(phb->dma32_region_size));
-
-	/* Setup config ops */
-	hose->ops = &wsp_pcie_pci_ops;
-
-	/* Configure the HW */
-	wsp_pcie_configure_hw(hose);
-
-	/* Instanciate IO workarounds */
-	iowa_register_bus(hose, &wsp_pci_iops, NULL, phb);
-#ifdef CONFIG_PCI_MSI
-	wsp_setup_phb_msi(hose);
-#endif
-
-	/* Add to global list */
-	list_add(&phb->all, &wsp_phbs);
-
-	return 0;
-}
-
-void __init wsp_setup_pci(void)
-{
-	struct device_node *np;
-	int rc;
-
-	/* Find host bridges */
-	for_each_compatible_node(np, "pciex", PCIE_COMPATIBLE) {
-		rc = wsp_setup_one_phb(np);
-		if (rc)
-			pr_err("Failed to setup PCIe bridge %s, rc=%d\n",
-			       np->full_name, rc);
-	}
-
-	/* Establish device-tree linkage */
-	pci_devs_phb_init();
-
-	/* Set DMA ops to use TCEs */
-	if (iommu_is_off) {
-		pr_info("PCI-E: Disabled TCEs, using direct DMA\n");
-		set_pci_dma_ops(&dma_direct_ops);
-	} else {
-		ppc_md.pci_dma_dev_setup = wsp_pci_dma_dev_setup;
-		ppc_md.tce_build = tce_build_wsp;
-		ppc_md.tce_free = tce_free_wsp;
-		set_pci_dma_ops(&dma_iommu_ops);
-	}
-}
-
-#define err_debug(fmt...)	pr_debug(fmt)
-//#define err_debug(fmt...)
-
-static int __init wsp_pci_get_err_irq_no_dt(struct device_node *np)
-{
-	const u32 *prop;
-	int hw_irq;
-
-	/* Ok, no interrupts property, let's try to find our child P2P */
-	np = of_get_next_child(np, NULL);
-	if (np == NULL)
-		return 0;
-
-	/* Grab it's interrupt map */
-	prop = of_get_property(np, "interrupt-map", NULL);
-	if (prop == NULL)
-		return 0;
-
-	/* Grab one of the interrupts in there, keep the low 4 bits */
-	hw_irq = prop[5] & 0xf;
-
-	/* 0..4 for PHB 0 and 5..9 for PHB 1 */
-	if (hw_irq < 5)
-		hw_irq = 4;
-	else
-		hw_irq = 9;
-	hw_irq |= prop[5] & ~0xf;
-
-	err_debug("PCI: Using 0x%x as error IRQ for %s\n",
-		  hw_irq, np->parent->full_name);
-	return irq_create_mapping(NULL, hw_irq);
-}
-
-static const struct {
-	u32 offset;
-	const char *name;
-} wsp_pci_regs[] = {
-#define DREG(x) { PCIE_REG_##x, #x }
-#define DUTL(x) { PCIE_UTL_##x, "UTL_" #x }
-	/* Architected registers except CONFIG_ and IODA
-         * to avoid side effects
-	 */
-	DREG(DMA_CHAN_STATUS),
-	DREG(CPU_LOADSTORE_STATUS),
-	DREG(LOCK0),
-	DREG(LOCK1),
-	DREG(PHB_CONFIG),
-	DREG(IO_BASE_ADDR),
-	DREG(IO_BASE_MASK),
-	DREG(IO_START_ADDR),
-	DREG(M32A_BASE_ADDR),
-	DREG(M32A_BASE_MASK),
-	DREG(M32A_START_ADDR),
-	DREG(M32B_BASE_ADDR),
-	DREG(M32B_BASE_MASK),
-	DREG(M32B_START_ADDR),
-	DREG(M64_BASE_ADDR),
-	DREG(M64_BASE_MASK),
-	DREG(M64_START_ADDR),
-	DREG(TCE_KILL),
-	DREG(LOCK2),
-	DREG(PHB_GEN_CAP),
-	DREG(PHB_TCE_CAP),
-	DREG(PHB_IRQ_CAP),
-	DREG(PHB_EEH_CAP),
-	DREG(PAPR_ERR_INJ_CONTROL),
-	DREG(PAPR_ERR_INJ_ADDR),
-	DREG(PAPR_ERR_INJ_MASK),
-
-	/* UTL core regs */
-	DUTL(SYS_BUS_CONTROL),
-	DUTL(STATUS),
-	DUTL(SYS_BUS_AGENT_STATUS),
-	DUTL(SYS_BUS_AGENT_ERR_SEV),
-	DUTL(SYS_BUS_AGENT_IRQ_EN),
-	DUTL(SYS_BUS_BURST_SZ_CONF),
-	DUTL(REVISION_ID),
-	DUTL(OUT_POST_HDR_BUF_ALLOC),
-	DUTL(OUT_POST_DAT_BUF_ALLOC),
-	DUTL(IN_POST_HDR_BUF_ALLOC),
-	DUTL(IN_POST_DAT_BUF_ALLOC),
-	DUTL(OUT_NP_BUF_ALLOC),
-	DUTL(IN_NP_BUF_ALLOC),
-	DUTL(PCIE_TAGS_ALLOC),
-	DUTL(GBIF_READ_TAGS_ALLOC),
-
-	DUTL(PCIE_PORT_CONTROL),
-	DUTL(PCIE_PORT_STATUS),
-	DUTL(PCIE_PORT_ERROR_SEV),
-	DUTL(PCIE_PORT_IRQ_EN),
-	DUTL(RC_STATUS),
-	DUTL(RC_ERR_SEVERITY),
-	DUTL(RC_IRQ_EN),
-	DUTL(EP_STATUS),
-	DUTL(EP_ERR_SEVERITY),
-	DUTL(EP_ERR_IRQ_EN),
-	DUTL(PCI_PM_CTRL1),
-	DUTL(PCI_PM_CTRL2),
-
-	/* PCIe stack regs */
-	DREG(SYSTEM_CONFIG1),
-	DREG(SYSTEM_CONFIG2),
-	DREG(EP_SYSTEM_CONFIG),
-	DREG(EP_FLR),
-	DREG(EP_BAR_CONFIG),
-	DREG(LINK_CONFIG),
-	DREG(PM_CONFIG),
-	DREG(DLP_CONTROL),
-	DREG(DLP_STATUS),
-	DREG(ERR_REPORT_CONTROL),
-	DREG(SLOT_CONTROL1),
-	DREG(SLOT_CONTROL2),
-	DREG(UTL_CONFIG),
-	DREG(BUFFERS_CONFIG),
-	DREG(ERROR_INJECT),
-	DREG(SRIOV_CONFIG),
-	DREG(PF0_SRIOV_STATUS),
-	DREG(PF1_SRIOV_STATUS),
-	DREG(PORT_NUMBER),
-	DREG(POR_SYSTEM_CONFIG),
-
-	/* Internal logic regs */
-	DREG(PHB_VERSION),
-	DREG(RESET),
-	DREG(PHB_CONTROL),
-	DREG(PHB_TIMEOUT_CONTROL1),
-	DREG(PHB_QUIESCE_DMA),
-	DREG(PHB_DMA_READ_TAG_ACTV),
-	DREG(PHB_TCE_READ_TAG_ACTV),
-
-	/* FIR registers */
-	DREG(LEM_FIR_ACCUM),
-	DREG(LEM_FIR_AND_MASK),
-	DREG(LEM_FIR_OR_MASK),
-	DREG(LEM_ACTION0),
-	DREG(LEM_ACTION1),
-	DREG(LEM_ERROR_MASK),
-	DREG(LEM_ERROR_AND_MASK),
-	DREG(LEM_ERROR_OR_MASK),
-
-	/* Error traps registers */
-	DREG(PHB_ERR_STATUS),
-	DREG(PHB_ERR_STATUS),
-	DREG(PHB_ERR1_STATUS),
-	DREG(PHB_ERR_INJECT),
-	DREG(PHB_ERR_LEM_ENABLE),
-	DREG(PHB_ERR_IRQ_ENABLE),
-	DREG(PHB_ERR_FREEZE_ENABLE),
-	DREG(PHB_ERR_SIDE_ENABLE),
-	DREG(PHB_ERR_LOG_0),
-	DREG(PHB_ERR_LOG_1),
-	DREG(PHB_ERR_STATUS_MASK),
-	DREG(PHB_ERR1_STATUS_MASK),
-	DREG(MMIO_ERR_STATUS),
-	DREG(MMIO_ERR1_STATUS),
-	DREG(MMIO_ERR_INJECT),
-	DREG(MMIO_ERR_LEM_ENABLE),
-	DREG(MMIO_ERR_IRQ_ENABLE),
-	DREG(MMIO_ERR_FREEZE_ENABLE),
-	DREG(MMIO_ERR_SIDE_ENABLE),
-	DREG(MMIO_ERR_LOG_0),
-	DREG(MMIO_ERR_LOG_1),
-	DREG(MMIO_ERR_STATUS_MASK),
-	DREG(MMIO_ERR1_STATUS_MASK),
-	DREG(DMA_ERR_STATUS),
-	DREG(DMA_ERR1_STATUS),
-	DREG(DMA_ERR_INJECT),
-	DREG(DMA_ERR_LEM_ENABLE),
-	DREG(DMA_ERR_IRQ_ENABLE),
-	DREG(DMA_ERR_FREEZE_ENABLE),
-	DREG(DMA_ERR_SIDE_ENABLE),
-	DREG(DMA_ERR_LOG_0),
-	DREG(DMA_ERR_LOG_1),
-	DREG(DMA_ERR_STATUS_MASK),
-	DREG(DMA_ERR1_STATUS_MASK),
-
-	/* Debug and Trace registers */
-	DREG(PHB_DEBUG_CONTROL0),
-	DREG(PHB_DEBUG_STATUS0),
-	DREG(PHB_DEBUG_CONTROL1),
-	DREG(PHB_DEBUG_STATUS1),
-	DREG(PHB_DEBUG_CONTROL2),
-	DREG(PHB_DEBUG_STATUS2),
-	DREG(PHB_DEBUG_CONTROL3),
-	DREG(PHB_DEBUG_STATUS3),
-	DREG(PHB_DEBUG_CONTROL4),
-	DREG(PHB_DEBUG_STATUS4),
-	DREG(PHB_DEBUG_CONTROL5),
-	DREG(PHB_DEBUG_STATUS5),
-
-	/* Don't seem to exist ...
-	DREG(PHB_DEBUG_CONTROL6),
-	DREG(PHB_DEBUG_STATUS6),
-	*/
-};
-
-static int wsp_pci_regs_show(struct seq_file *m, void *private)
-{
-	struct wsp_phb *phb = m->private;
-	struct pci_controller *hose = phb->hose;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) {
-		/* Skip write-only regs */
-		if (wsp_pci_regs[i].offset == 0xc08 ||
-		    wsp_pci_regs[i].offset == 0xc10 ||
-		    wsp_pci_regs[i].offset == 0xc38 ||
-		    wsp_pci_regs[i].offset == 0xc40)
-			continue;
-		seq_printf(m, "0x%03x: 0x%016llx %s\n",
-			   wsp_pci_regs[i].offset,
-			   in_be64(hose->cfg_data + wsp_pci_regs[i].offset),
-			   wsp_pci_regs[i].name);
-	}
-	return 0;
-}
-
-static int wsp_pci_regs_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, wsp_pci_regs_show, inode->i_private);
-}
-
-static const struct file_operations wsp_pci_regs_fops = {
-	.open = wsp_pci_regs_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static int wsp_pci_reg_set(void *data, u64 val)
-{
-	out_be64((void __iomem *)data, val);
-	return 0;
-}
-
-static int wsp_pci_reg_get(void *data, u64 *val)
-{
-	*val = in_be64((void __iomem *)data);
-	return 0;
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(wsp_pci_reg_fops, wsp_pci_reg_get, wsp_pci_reg_set, "0x%llx\n");
-
-static irqreturn_t wsp_pci_err_irq(int irq, void *dev_id)
-{
-	struct wsp_phb *phb = dev_id;
-	struct pci_controller *hose = phb->hose;
-	irqreturn_t handled = IRQ_NONE;
-	struct wsp_pcie_err_log_data ed;
-
-	pr_err("PCI: Error interrupt on %s (PHB %d)\n",
-	       hose->dn->full_name, hose->global_number);
- again:
-	memset(&ed, 0, sizeof(ed));
-
-	/* Read and clear UTL errors */
-	ed.utl_sys_err = in_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS);
-	if (ed.utl_sys_err)
-		out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS, ed.utl_sys_err);
-	ed.utl_port_err = in_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS);
-	if (ed.utl_port_err)
-		out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS, ed.utl_port_err);
-	ed.utl_rc_err = in_be64(hose->cfg_data + PCIE_UTL_RC_STATUS);
-	if (ed.utl_rc_err)
-		out_be64(hose->cfg_data + PCIE_UTL_RC_STATUS, ed.utl_rc_err);
-
-	/* Read and clear main trap errors */
-	ed.phb_err = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS);
-	if (ed.phb_err) {
-		ed.phb_err1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS);
-		ed.phb_log0 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_0);
-		ed.phb_log1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_1);
-		out_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS, 0);
-		out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS, 0);
-	}
-	ed.mmio_err = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS);
-	if (ed.mmio_err) {
-		ed.mmio_err1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS);
-		ed.mmio_log0 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_0);
-		ed.mmio_log1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_1);
-		out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS, 0);
-		out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS, 0);
-	}
-	ed.dma_err = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS);
-	if (ed.dma_err) {
-		ed.dma_err1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS);
-		ed.dma_log0 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_0);
-		ed.dma_log1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_1);
-		out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS, 0);
-		out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS, 0);
-	}
-
-	/* Now print things out */
-	if (ed.phb_err) {
-		pr_err("   PHB Error Status      : 0x%016llx\n", ed.phb_err);
-		pr_err("   PHB First Error Status: 0x%016llx\n", ed.phb_err1);
-		pr_err("   PHB Error Log 0       : 0x%016llx\n", ed.phb_log0);
-		pr_err("   PHB Error Log 1       : 0x%016llx\n", ed.phb_log1);
-	}
-	if (ed.mmio_err) {
-		pr_err("  MMIO Error Status      : 0x%016llx\n", ed.mmio_err);
-		pr_err("  MMIO First Error Status: 0x%016llx\n", ed.mmio_err1);
-		pr_err("  MMIO Error Log 0       : 0x%016llx\n", ed.mmio_log0);
-		pr_err("  MMIO Error Log 1       : 0x%016llx\n", ed.mmio_log1);
-	}
-	if (ed.dma_err) {
-		pr_err("   DMA Error Status      : 0x%016llx\n", ed.dma_err);
-		pr_err("   DMA First Error Status: 0x%016llx\n", ed.dma_err1);
-		pr_err("   DMA Error Log 0       : 0x%016llx\n", ed.dma_log0);
-		pr_err("   DMA Error Log 1       : 0x%016llx\n", ed.dma_log1);
-	}
-	if (ed.utl_sys_err)
-		pr_err("   UTL Sys Error Status  : 0x%016llx\n", ed.utl_sys_err);
-	if (ed.utl_port_err)
-		pr_err("   UTL Port Error Status : 0x%016llx\n", ed.utl_port_err);
-	if (ed.utl_rc_err)
-		pr_err("   UTL RC Error Status   : 0x%016llx\n", ed.utl_rc_err);
-
-	/* Interrupts are caused by the error traps. If we had any error there
-	 * we loop again in case the UTL buffered some new stuff between
-	 * going there and going to the traps
-	 */
-	if (ed.dma_err || ed.mmio_err || ed.phb_err) {
-		handled = IRQ_HANDLED;
-		goto again;
-	}
-	return handled;
-}
-
-static void __init wsp_setup_pci_err_reporting(struct wsp_phb *phb)
-{
-	struct pci_controller *hose = phb->hose;
-	int err_irq, i, rc;
-	char fname[16];
-
-	/* Create a debugfs file for that PHB */
-	sprintf(fname, "phb%d", phb->hose->global_number);
-	phb->ddir = debugfs_create_dir(fname, powerpc_debugfs_root);
-
-	/* Some useful debug output */
-	if (phb->ddir) {
-		struct dentry *d = debugfs_create_dir("regs", phb->ddir);
-		char tmp[64];
-
-		for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) {
-			sprintf(tmp, "%03x_%s", wsp_pci_regs[i].offset,
-				wsp_pci_regs[i].name);
-			debugfs_create_file(tmp, 0600, d,
-					    hose->cfg_data + wsp_pci_regs[i].offset,
-					    &wsp_pci_reg_fops);
-		}
-		debugfs_create_file("all_regs", 0600, phb->ddir, phb, &wsp_pci_regs_fops);
-	}
-
-	/* Find the IRQ number for that PHB */
-	err_irq = irq_of_parse_and_map(hose->dn, 0);
-	if (err_irq == 0)
-		/* XXX Error IRQ lacking from device-tree */
-		err_irq = wsp_pci_get_err_irq_no_dt(hose->dn);
-	if (err_irq == 0) {
-		pr_err("PCI: Failed to fetch error interrupt for %s\n",
-		       hose->dn->full_name);
-		return;
-	}
-	/* Request it */
-	rc = request_irq(err_irq, wsp_pci_err_irq, 0, "wsp_pci error", phb);
-	if (rc) {
-		pr_err("PCI: Failed to request interrupt for %s\n",
-		       hose->dn->full_name);
-	}
-	/* Enable interrupts for all errors for now */
-	out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
-	out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
-	out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
-}
-
-/*
- * This is called later to hookup with the error interrupt
- */
-static int __init wsp_setup_pci_late(void)
-{
-	struct wsp_phb *phb;
-
-	list_for_each_entry(phb, &wsp_phbs, all)
-		wsp_setup_pci_err_reporting(phb);
-
-	return 0;
-}
-arch_initcall(wsp_setup_pci_late);
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.h b/arch/powerpc/platforms/wsp/wsp_pci.h
deleted file mode 100644
index 52e9bd95250..00000000000
--- a/arch/powerpc/platforms/wsp/wsp_pci.h
+++ /dev/null
@@ -1,268 +0,0 @@
-/*
- * Copyright 2010 Ben Herrenschmidt, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifndef __WSP_PCI_H
-#define __WSP_PCI_H
-
-/* Architected registers */
-#define PCIE_REG_DMA_CHAN_STATUS	0x110
-#define PCIE_REG_CPU_LOADSTORE_STATUS	0x120
-
-#define PCIE_REG_CONFIG_DATA		0x130
-#define PCIE_REG_LOCK0			0x138
-#define PCIE_REG_CONFIG_ADDRESS		0x140
-#define   PCIE_REG_CA_ENABLE			0x8000000000000000ull
-#define	  PCIE_REG_CA_BUS_MASK			0x0ff0000000000000ull
-#define   PCIE_REG_CA_BUS_SHIFT			(20+32)
-#define   PCIE_REG_CA_DEV_MASK			0x000f800000000000ull
-#define   PCIE_REG_CA_DEV_SHIFT			(15+32)
-#define   PCIE_REG_CA_FUNC_MASK			0x0000700000000000ull
-#define   PCIE_REG_CA_FUNC_SHIFT		(12+32)
-#define   PCIE_REG_CA_REG_MASK			0x00000fff00000000ull
-#define   PCIE_REG_CA_REG_SHIFT			( 0+32)
-#define   PCIE_REG_CA_BE_MASK			0x00000000f0000000ull
-#define   PCIE_REG_CA_BE_SHIFT			(   28)
-#define PCIE_REG_LOCK1			0x148
-
-#define PCIE_REG_PHB_CONFIG		0x160
-#define   PCIE_REG_PHBC_64B_TCE_EN		0x2000000000000000ull
-#define   PCIE_REG_PHBC_MMIO_DMA_FREEZE_EN	0x1000000000000000ull
-#define   PCIE_REG_PHBC_32BIT_MSI_EN		0x0080000000000000ull
-#define   PCIE_REG_PHBC_M64_EN			0x0040000000000000ull
-#define   PCIE_REG_PHBC_IO_EN			0x0008000000000000ull
-#define   PCIE_REG_PHBC_64BIT_MSI_EN		0x0002000000000000ull
-#define   PCIE_REG_PHBC_M32A_EN			0x0000800000000000ull
-#define   PCIE_REG_PHBC_M32B_EN			0x0000400000000000ull
-#define   PCIE_REG_PHBC_MSI_PE_VALIDATE		0x0000200000000000ull
-#define   PCIE_REG_PHBC_DMA_XLATE_BYPASS	0x0000100000000000ull
-
-#define PCIE_REG_IO_BASE_ADDR		0x170
-#define PCIE_REG_IO_BASE_MASK		0x178
-#define PCIE_REG_IO_START_ADDR		0x180
-
-#define PCIE_REG_M32A_BASE_ADDR		0x190
-#define PCIE_REG_M32A_BASE_MASK		0x198
-#define PCIE_REG_M32A_START_ADDR	0x1a0
-
-#define PCIE_REG_M32B_BASE_ADDR		0x1b0
-#define PCIE_REG_M32B_BASE_MASK		0x1b8
-#define PCIE_REG_M32B_START_ADDR	0x1c0
-
-#define PCIE_REG_M64_BASE_ADDR		0x1e0
-#define PCIE_REG_M64_BASE_MASK		0x1e8
-#define PCIE_REG_M64_START_ADDR		0x1f0
-
-#define PCIE_REG_TCE_KILL		0x210
-#define   PCIE_REG_TCEKILL_SINGLE	0x8000000000000000ull
-#define   PCIE_REG_TCEKILL_ADDR_MASK	0x000003fffffffff8ull
-#define   PCIE_REG_TCEKILL_PS_4K	0
-#define   PCIE_REG_TCEKILL_PS_64K	1
-#define   PCIE_REG_TCEKILL_PS_16M	2
-#define   PCIE_REG_TCEKILL_PS_16G	3
-
-#define PCIE_REG_IODA_ADDR		0x220
-#define   PCIE_REG_IODA_AD_AUTOINC	0x8000000000000000ull
-#define   PCIE_REG_IODA_AD_TBL_MVT	0x0005000000000000ull
-#define   PCIE_REG_IODA_AD_TBL_PELT	0x0006000000000000ull
-#define   PCIE_REG_IODA_AD_TBL_PESTA	0x0007000000000000ull
-#define   PCIE_REG_IODA_AD_TBL_PESTB	0x0008000000000000ull
-#define   PCIE_REG_IODA_AD_TBL_TVT	0x0009000000000000ull
-#define   PCIE_REG_IODA_AD_TBL_TCE	0x000a000000000000ull
-#define PCIE_REG_IODA_DATA0		0x228
-#define PCIE_REG_IODA_DATA1		0x230
-
-#define PCIE_REG_LOCK2			0x240
-
-#define PCIE_REG_PHB_GEN_CAP		0x250
-#define PCIE_REG_PHB_TCE_CAP		0x258
-#define PCIE_REG_PHB_IRQ_CAP		0x260
-#define PCIE_REG_PHB_EEH_CAP		0x268
-
-#define PCIE_REG_PAPR_ERR_INJ_CONTROL	0x2b0
-#define PCIE_REG_PAPR_ERR_INJ_ADDR	0x2b8
-#define PCIE_REG_PAPR_ERR_INJ_MASK	0x2c0
-
-
-#define PCIE_REG_SYS_CFG1		0x600
-#define   PCIE_REG_SYS_CFG1_CLASS_CODE	0x0000000000ffffffull
-
-#define IODA_TVT0_TTA_MASK		0x000fffffffff0000ull
-#define IODA_TVT0_TTA_SHIFT		4
-#define IODA_TVT0_BUSNUM_VALID_MASK	0x000000000000e000ull
-#define IODA_TVT0_TCE_TABLE_SIZE_MASK	0x0000000000001f00ull
-#define IODA_TVT0_TCE_TABLE_SIZE_SHIFT	8
-#define IODA_TVT0_BUSNUM_VALUE_MASK	0x00000000000000ffull
-#define IODA_TVT0_BUSNUM_VALID_SHIFT	0
-#define IODA_TVT1_DEVNUM_VALID		0x2000000000000000ull
-#define IODA_TVT1_DEVNUM_VALUE_MASK	0x1f00000000000000ull
-#define IODA_TVT1_DEVNUM_VALUE_SHIFT	56
-#define IODA_TVT1_FUNCNUM_VALID		0x0008000000000000ull
-#define IODA_TVT1_FUNCNUM_VALUE_MASK	0x0007000000000000ull
-#define IODA_TVT1_FUNCNUM_VALUE_SHIFT	48
-#define IODA_TVT1_IO_PAGE_SIZE_MASK	0x00001f0000000000ull
-#define IODA_TVT1_IO_PAGE_SIZE_SHIFT	40
-#define IODA_TVT1_PE_NUMBER_MASK	0x000000000000003full
-#define IODA_TVT1_PE_NUMBER_SHIFT	0
-
-#define IODA_TVT_COUNT			64
-
-/* UTL Core registers */
-#define PCIE_UTL_SYS_BUS_CONTROL	0x400
-#define PCIE_UTL_STATUS			0x408
-#define PCIE_UTL_SYS_BUS_AGENT_STATUS	0x410
-#define PCIE_UTL_SYS_BUS_AGENT_ERR_SEV	0x418
-#define PCIE_UTL_SYS_BUS_AGENT_IRQ_EN	0x420
-#define PCIE_UTL_SYS_BUS_BURST_SZ_CONF	0x440
-#define PCIE_UTL_REVISION_ID		0x448
-
-#define PCIE_UTL_OUT_POST_HDR_BUF_ALLOC	0x4c0
-#define PCIE_UTL_OUT_POST_DAT_BUF_ALLOC	0x4d0
-#define PCIE_UTL_IN_POST_HDR_BUF_ALLOC	0x4e0
-#define PCIE_UTL_IN_POST_DAT_BUF_ALLOC	0x4f0
-#define PCIE_UTL_OUT_NP_BUF_ALLOC	0x500
-#define PCIE_UTL_IN_NP_BUF_ALLOC	0x510
-#define PCIE_UTL_PCIE_TAGS_ALLOC	0x520
-#define PCIE_UTL_GBIF_READ_TAGS_ALLOC	0x530
-
-#define PCIE_UTL_PCIE_PORT_CONTROL	0x540
-#define PCIE_UTL_PCIE_PORT_STATUS	0x548
-#define PCIE_UTL_PCIE_PORT_ERROR_SEV	0x550
-#define PCIE_UTL_PCIE_PORT_IRQ_EN	0x558
-#define PCIE_UTL_RC_STATUS		0x560
-#define PCIE_UTL_RC_ERR_SEVERITY	0x568
-#define PCIE_UTL_RC_IRQ_EN		0x570
-#define PCIE_UTL_EP_STATUS		0x578
-#define PCIE_UTL_EP_ERR_SEVERITY	0x580
-#define PCIE_UTL_EP_ERR_IRQ_EN		0x588
-
-#define PCIE_UTL_PCI_PM_CTRL1		0x590
-#define PCIE_UTL_PCI_PM_CTRL2		0x598
-
-/* PCIe stack registers */
-#define PCIE_REG_SYSTEM_CONFIG1		0x600
-#define PCIE_REG_SYSTEM_CONFIG2		0x608
-#define PCIE_REG_EP_SYSTEM_CONFIG	0x618
-#define PCIE_REG_EP_FLR			0x620
-#define PCIE_REG_EP_BAR_CONFIG		0x628
-#define PCIE_REG_LINK_CONFIG		0x630
-#define PCIE_REG_PM_CONFIG		0x640
-#define PCIE_REG_DLP_CONTROL		0x650
-#define PCIE_REG_DLP_STATUS		0x658
-#define PCIE_REG_ERR_REPORT_CONTROL	0x660
-#define PCIE_REG_SLOT_CONTROL1		0x670
-#define PCIE_REG_SLOT_CONTROL2		0x678
-#define PCIE_REG_UTL_CONFIG		0x680
-#define PCIE_REG_BUFFERS_CONFIG		0x690
-#define PCIE_REG_ERROR_INJECT		0x698
-#define PCIE_REG_SRIOV_CONFIG		0x6a0
-#define PCIE_REG_PF0_SRIOV_STATUS	0x6a8
-#define PCIE_REG_PF1_SRIOV_STATUS	0x6b0
-#define PCIE_REG_PORT_NUMBER		0x700
-#define PCIE_REG_POR_SYSTEM_CONFIG	0x708
-
-/* PHB internal logic registers */
-#define PCIE_REG_PHB_VERSION		0x800
-#define PCIE_REG_RESET			0x808
-#define PCIE_REG_PHB_CONTROL		0x810
-#define PCIE_REG_PHB_TIMEOUT_CONTROL1	0x878
-#define PCIE_REG_PHB_QUIESCE_DMA	0x888
-#define PCIE_REG_PHB_DMA_READ_TAG_ACTV	0x900
-#define PCIE_REG_PHB_TCE_READ_TAG_ACTV	0x908
-
-/* FIR registers */
-#define PCIE_REG_LEM_FIR_ACCUM		0xc00
-#define PCIE_REG_LEM_FIR_AND_MASK	0xc08
-#define PCIE_REG_LEM_FIR_OR_MASK	0xc10
-#define PCIE_REG_LEM_ACTION0		0xc18
-#define PCIE_REG_LEM_ACTION1		0xc20
-#define PCIE_REG_LEM_ERROR_MASK		0xc30
-#define PCIE_REG_LEM_ERROR_AND_MASK	0xc38
-#define PCIE_REG_LEM_ERROR_OR_MASK	0xc40
-
-/* PHB Error registers */
-#define PCIE_REG_PHB_ERR_STATUS		0xc80
-#define PCIE_REG_PHB_ERR1_STATUS	0xc88
-#define PCIE_REG_PHB_ERR_INJECT		0xc90
-#define PCIE_REG_PHB_ERR_LEM_ENABLE	0xc98
-#define PCIE_REG_PHB_ERR_IRQ_ENABLE	0xca0
-#define PCIE_REG_PHB_ERR_FREEZE_ENABLE	0xca8
-#define PCIE_REG_PHB_ERR_SIDE_ENABLE	0xcb8
-#define PCIE_REG_PHB_ERR_LOG_0		0xcc0
-#define PCIE_REG_PHB_ERR_LOG_1		0xcc8
-#define PCIE_REG_PHB_ERR_STATUS_MASK	0xcd0
-#define PCIE_REG_PHB_ERR1_STATUS_MASK	0xcd8
-
-#define PCIE_REG_MMIO_ERR_STATUS	0xd00
-#define PCIE_REG_MMIO_ERR1_STATUS	0xd08
-#define PCIE_REG_MMIO_ERR_INJECT	0xd10
-#define PCIE_REG_MMIO_ERR_LEM_ENABLE	0xd18
-#define PCIE_REG_MMIO_ERR_IRQ_ENABLE	0xd20
-#define PCIE_REG_MMIO_ERR_FREEZE_ENABLE	0xd28
-#define PCIE_REG_MMIO_ERR_SIDE_ENABLE	0xd38
-#define PCIE_REG_MMIO_ERR_LOG_0		0xd40
-#define PCIE_REG_MMIO_ERR_LOG_1		0xd48
-#define PCIE_REG_MMIO_ERR_STATUS_MASK	0xd50
-#define PCIE_REG_MMIO_ERR1_STATUS_MASK	0xd58
-
-#define PCIE_REG_DMA_ERR_STATUS		0xd80
-#define PCIE_REG_DMA_ERR1_STATUS	0xd88
-#define PCIE_REG_DMA_ERR_INJECT		0xd90
-#define PCIE_REG_DMA_ERR_LEM_ENABLE	0xd98
-#define PCIE_REG_DMA_ERR_IRQ_ENABLE	0xda0
-#define PCIE_REG_DMA_ERR_FREEZE_ENABLE	0xda8
-#define PCIE_REG_DMA_ERR_SIDE_ENABLE	0xdb8
-#define PCIE_REG_DMA_ERR_LOG_0		0xdc0
-#define PCIE_REG_DMA_ERR_LOG_1		0xdc8
-#define PCIE_REG_DMA_ERR_STATUS_MASK	0xdd0
-#define PCIE_REG_DMA_ERR1_STATUS_MASK	0xdd8
-
-/* Shortcuts for access to the above using the PHB definitions
- * with an offset
- */
-#define PCIE_REG_ERR_PHB_OFFSET		0x0
-#define PCIE_REG_ERR_MMIO_OFFSET	0x80
-#define PCIE_REG_ERR_DMA_OFFSET		0x100
-
-/* Debug and Trace registers */
-#define PCIE_REG_PHB_DEBUG_CONTROL0	0xe00
-#define PCIE_REG_PHB_DEBUG_STATUS0	0xe08
-#define PCIE_REG_PHB_DEBUG_CONTROL1	0xe10
-#define PCIE_REG_PHB_DEBUG_STATUS1	0xe18
-#define PCIE_REG_PHB_DEBUG_CONTROL2	0xe20
-#define PCIE_REG_PHB_DEBUG_STATUS2	0xe28
-#define PCIE_REG_PHB_DEBUG_CONTROL3	0xe30
-#define PCIE_REG_PHB_DEBUG_STATUS3	0xe38
-#define PCIE_REG_PHB_DEBUG_CONTROL4	0xe40
-#define PCIE_REG_PHB_DEBUG_STATUS4	0xe48
-#define PCIE_REG_PHB_DEBUG_CONTROL5	0xe50
-#define PCIE_REG_PHB_DEBUG_STATUS5	0xe58
-#define PCIE_REG_PHB_DEBUG_CONTROL6	0xe60
-#define PCIE_REG_PHB_DEBUG_STATUS6	0xe68
-
-/* Definition for PCIe errors */
-struct wsp_pcie_err_log_data {
-	__u64	phb_err;
-	__u64	phb_err1;
-	__u64	phb_log0;
-	__u64	phb_log1;
-	__u64	mmio_err;
-	__u64	mmio_err1;
-	__u64	mmio_log0;
-	__u64	mmio_log1;
-	__u64	dma_err;
-	__u64	dma_err1;
-	__u64	dma_log0;
-	__u64	dma_log1;
-	__u64	utl_sys_err;
-	__u64	utl_port_err;
-	__u64	utl_rc_err;
-	__u64	unused;
-};
-
-#endif /* __WSP_PCI_H */
diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig
index 7baa70d6dc0..a19332a3871 100644
--- a/arch/powerpc/sysdev/Kconfig
+++ b/arch/powerpc/sysdev/Kconfig
@@ -7,6 +7,12 @@ config PPC4xx_PCI_EXPRESS
 	depends on PCI && 4xx
 	default n
 
+config PPC4xx_HSTA_MSI
+	bool
+	depends on PCI_MSI
+	depends on PCI && 4xx
+	default n
+
 config PPC4xx_MSI
 	bool
 	depends on PCI_MSI
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index afbcc37aa09..f7cb2a1b01f 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -45,6 +45,7 @@ obj-$(CONFIG_OF_RTC)		+= of_rtc.o
 ifeq ($(CONFIG_PCI),y)
 obj-$(CONFIG_4xx)		+= ppc4xx_pci.o
 endif
+obj-$(CONFIG_PPC4xx_HSTA_MSI)	+= ppc4xx_hsta_msi.o
 obj-$(CONFIG_PPC4xx_MSI)	+= ppc4xx_msi.o
 obj-$(CONFIG_PPC4xx_CPM)	+= ppc4xx_cpm.o
 obj-$(CONFIG_PPC4xx_GPIO)	+= ppc4xx_gpio.o
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 62c47bb7651..9e5353ff6d1 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -476,6 +476,11 @@ void __init alloc_dart_table(void)
 	 */
 	dart_tablebase = (unsigned long)
 		__va(memblock_alloc_base(1UL<<24, 1UL<<24, 0x80000000L));
+	/*
+	 * The DART space is later unmapped from the kernel linear mapping and
+	 * accessing dart_tablebase during kmemleak scanning will fault.
+	 */
+	kmemleak_no_scan((void *)dart_tablebase);
 
 	printk(KERN_INFO "DART table allocated at: %lx\n", dart_tablebase);
 }
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 3f415e252ea..4bd091a0558 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1150,8 +1150,7 @@ static int fsl_pci_pme_probe(struct pci_controller *hose)
 	pci = hose->private_data;
 
 	/* Enable PTOD, ENL23D & EXL23D */
-	out_be32(&pci->pex_pme_mes_disr, 0);
-	setbits32(&pci->pex_pme_mes_disr,
+	clrbits32(&pci->pex_pme_mes_disr,
 		  PME_DISR_EN_PTOD | PME_DISR_EN_ENL23D | PME_DISR_EN_EXL23D);
 
 	out_be32(&pci->pex_pme_mes_ier, 0);
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index cf2b0840a67..c04b718307c 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -391,8 +391,10 @@ int fsl_rio_setup(struct platform_device *dev)
 	ops->get_inb_message = fsl_get_inb_message;
 
 	rmu_node = of_parse_phandle(dev->dev.of_node, "fsl,srio-rmu-handle", 0);
-	if (!rmu_node)
+	if (!rmu_node) {
+		dev_err(&dev->dev, "No valid fsl,srio-rmu-handle property\n");
 		goto err_rmu;
+	}
 	rc = of_address_to_resource(rmu_node, 0, &rmu_regs);
 	if (rc) {
 		dev_err(&dev->dev, "Can't get %s property 'reg'\n",
@@ -413,6 +415,7 @@ int fsl_rio_setup(struct platform_device *dev)
 	/*set up doobell node*/
 	np = of_find_compatible_node(NULL, NULL, "fsl,srio-dbell-unit");
 	if (!np) {
+		dev_err(&dev->dev, "No fsl,srio-dbell-unit node\n");
 		rc = -ENODEV;
 		goto err_dbell;
 	}
@@ -441,6 +444,7 @@ int fsl_rio_setup(struct platform_device *dev)
 	/*set up port write node*/
 	np = of_find_compatible_node(NULL, NULL, "fsl,srio-port-write-unit");
 	if (!np) {
+		dev_err(&dev->dev, "No fsl,srio-port-write-unit node\n");
 		rc = -ENODEV;
 		goto err_pw;
 	}
@@ -633,14 +637,18 @@ int fsl_rio_setup(struct platform_device *dev)
 	return 0;
 err:
 	kfree(pw);
+	pw = NULL;
 err_pw:
 	kfree(dbell);
+	dbell = NULL;
 err_dbell:
 	iounmap(rmu_regs_win);
+	rmu_regs_win = NULL;
 err_rmu:
 	kfree(ops);
 err_ops:
 	iounmap(rio_regs_win);
+	rio_regs_win = NULL;
 err_rio_regs:
 	return rc;
 }
diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c
index 00e224a1048..b48197ae44d 100644
--- a/arch/powerpc/sysdev/fsl_rmu.c
+++ b/arch/powerpc/sysdev/fsl_rmu.c
@@ -881,9 +881,9 @@ fsl_open_inb_mbox(struct rio_mport *mport, void *dev_id, int mbox, int entries)
 	rc = request_irq(IRQ_RIO_RX(mport), fsl_rio_rx_handler, 0,
 			 "msg_rx", (void *)mport);
 	if (rc < 0) {
-		dma_free_coherent(priv->dev, RIO_MSG_BUFFER_SIZE,
-			rmu->msg_tx_ring.virt_buffer[i],
-			rmu->msg_tx_ring.phys_buffer[i]);
+		dma_free_coherent(priv->dev,
+			rmu->msg_rx_ring.size * RIO_MAX_MSG_SIZE,
+			rmu->msg_rx_ring.virt, rmu->msg_rx_ring.phys);
 		goto out;
 	}
 
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index 228cf91b91c..ffd1169ebaa 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -25,7 +25,6 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/phy.h>
-#include <linux/phy_fixed.h>
 #include <linux/spi/spi.h>
 #include <linux/fsl_devices.h>
 #include <linux/fs_enet_pd.h>
@@ -178,37 +177,6 @@ u32 get_baudrate(void)
 EXPORT_SYMBOL(get_baudrate);
 #endif /* CONFIG_CPM2 */
 
-#ifdef CONFIG_FIXED_PHY
-static int __init of_add_fixed_phys(void)
-{
-	int ret;
-	struct device_node *np;
-	u32 *fixed_link;
-	struct fixed_phy_status status = {};
-
-	for_each_node_by_name(np, "ethernet") {
-		fixed_link  = (u32 *)of_get_property(np, "fixed-link", NULL);
-		if (!fixed_link)
-			continue;
-
-		status.link = 1;
-		status.duplex = fixed_link[1];
-		status.speed = fixed_link[2];
-		status.pause = fixed_link[3];
-		status.asym_pause = fixed_link[4];
-
-		ret = fixed_phy_add(PHY_POLL, fixed_link[0], &status);
-		if (ret) {
-			of_node_put(np);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-arch_initcall(of_add_fixed_phys);
-#endif /* CONFIG_FIXED_PHY */
-
 #if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
 static __be32 __iomem *rstcr;
 
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 8209744b282..be33c9768ea 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1588,10 +1588,6 @@ void __init mpic_init(struct mpic *mpic)
 			num_timers = 8;
 	}
 
-	/* FSL mpic error interrupt intialization */
-	if (mpic->flags & MPIC_FSL_HAS_EIMR)
-		mpic_err_int_init(mpic, MPIC_FSL_ERR_INT);
-
 	/* Initialize timers to our reserved vectors and mask them for now */
 	for (i = 0; i < num_timers; i++) {
 		unsigned int offset = mpic_tm_offset(mpic, i);
@@ -1675,6 +1671,10 @@ void __init mpic_init(struct mpic *mpic)
 			irq_set_chained_handler(virq, &mpic_cascade);
 		}
 	}
+
+	/* FSL mpic error interrupt intialization */
+	if (mpic->flags & MPIC_FSL_HAS_EIMR)
+		mpic_err_int_init(mpic, MPIC_FSL_ERR_INT);
 }
 
 void __init mpic_set_clk_ratio(struct mpic *mpic, u32 clock_ratio)
diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
new file mode 100644
index 00000000000..11c888416f0
--- /dev/null
+++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
@@ -0,0 +1,215 @@
+/*
+ * MSI support for PPC4xx SoCs using High Speed Transfer Assist (HSTA) for
+ * generation of the interrupt.
+ *
+ * Copyright © 2013 Alistair Popple <alistair@popple.id.au> IBM Corporation
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <linux/semaphore.h>
+#include <asm/msi_bitmap.h>
+
+struct ppc4xx_hsta_msi {
+	struct device *dev;
+
+	/* The ioremapped HSTA MSI IO space */
+	u32 __iomem *data;
+
+	/* Physical address of HSTA MSI IO space */
+	u64 address;
+	struct msi_bitmap bmp;
+
+	/* An array mapping offsets to hardware IRQs */
+	int *irq_map;
+
+	/* Number of hwirqs supported */
+	int irq_count;
+};
+static struct ppc4xx_hsta_msi ppc4xx_hsta_msi;
+
+static int hsta_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct msi_msg msg;
+	struct msi_desc *entry;
+	int irq, hwirq;
+	u64 addr;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		irq = msi_bitmap_alloc_hwirqs(&ppc4xx_hsta_msi.bmp, 1);
+		if (irq < 0) {
+			pr_debug("%s: Failed to allocate msi interrupt\n",
+				 __func__);
+			return irq;
+		}
+
+		hwirq = ppc4xx_hsta_msi.irq_map[irq];
+		if (hwirq == NO_IRQ) {
+			pr_err("%s: Failed mapping irq %d\n", __func__, irq);
+			return -EINVAL;
+		}
+
+		/*
+		 * HSTA generates interrupts on writes to 128-bit aligned
+		 * addresses.
+		 */
+		addr = ppc4xx_hsta_msi.address + irq*0x10;
+		msg.address_hi = upper_32_bits(addr);
+		msg.address_lo = lower_32_bits(addr);
+
+		/* Data is not used by the HSTA. */
+		msg.data = 0;
+
+		pr_debug("%s: Setup irq %d (0x%0llx)\n", __func__, hwirq,
+			 (((u64) msg.address_hi) << 32) | msg.address_lo);
+
+		if (irq_set_msi_desc(hwirq, entry)) {
+			pr_err(
+			"%s: Invalid hwirq %d specified in device tree\n",
+			__func__, hwirq);
+			msi_bitmap_free_hwirqs(&ppc4xx_hsta_msi.bmp, irq, 1);
+			return -EINVAL;
+		}
+		write_msi_msg(hwirq, &msg);
+	}
+
+	return 0;
+}
+
+static int hsta_find_hwirq_offset(int hwirq)
+{
+	int irq;
+
+	/* Find the offset given the hwirq */
+	for (irq = 0; irq < ppc4xx_hsta_msi.irq_count; irq++)
+		if (ppc4xx_hsta_msi.irq_map[irq] == hwirq)
+			return irq;
+
+	return -EINVAL;
+}
+
+static void hsta_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct msi_desc *entry;
+	int irq;
+
+	list_for_each_entry(entry, &dev->msi_list, list) {
+		if (entry->irq == NO_IRQ)
+			continue;
+
+		irq = hsta_find_hwirq_offset(entry->irq);
+
+		/* entry->irq should always be in irq_map */
+		BUG_ON(irq < 0);
+		irq_set_msi_desc(entry->irq, NULL);
+		msi_bitmap_free_hwirqs(&ppc4xx_hsta_msi.bmp, irq, 1);
+		pr_debug("%s: Teardown IRQ %u (index %u)\n", __func__,
+			 entry->irq, irq);
+	}
+}
+
+static int hsta_msi_check_device(struct pci_dev *pdev, int nvec, int type)
+{
+	/* We don't support MSI-X */
+	if (type == PCI_CAP_ID_MSIX) {
+		pr_debug("%s: MSI-X not supported.\n", __func__);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hsta_msi_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *mem;
+	int irq, ret, irq_count;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (IS_ERR(mem)) {
+		dev_err(dev, "Unable to get mmio space\n");
+		return -EINVAL;
+	}
+
+	irq_count = of_irq_count(dev->of_node);
+	if (!irq_count) {
+		dev_err(dev, "Unable to find IRQ range\n");
+		return -EINVAL;
+	}
+
+	ppc4xx_hsta_msi.dev = dev;
+	ppc4xx_hsta_msi.address = mem->start;
+	ppc4xx_hsta_msi.data = ioremap(mem->start, resource_size(mem));
+	ppc4xx_hsta_msi.irq_count = irq_count;
+	if (IS_ERR(ppc4xx_hsta_msi.data)) {
+		dev_err(dev, "Unable to map memory\n");
+		return -ENOMEM;
+	}
+
+	ret = msi_bitmap_alloc(&ppc4xx_hsta_msi.bmp, irq_count, dev->of_node);
+	if (ret)
+		goto out;
+
+	ppc4xx_hsta_msi.irq_map = kmalloc(sizeof(int) * irq_count, GFP_KERNEL);
+	if (IS_ERR(ppc4xx_hsta_msi.irq_map)) {
+		ret = -ENOMEM;
+		goto out1;
+	}
+
+	/* Setup a mapping from irq offsets to hardware irq numbers */
+	for (irq = 0; irq < irq_count; irq++) {
+		ppc4xx_hsta_msi.irq_map[irq] =
+			irq_of_parse_and_map(dev->of_node, irq);
+		if (ppc4xx_hsta_msi.irq_map[irq] == NO_IRQ) {
+			dev_err(dev, "Unable to map IRQ\n");
+			ret = -EINVAL;
+			goto out2;
+		}
+	}
+
+	ppc_md.setup_msi_irqs = hsta_setup_msi_irqs;
+	ppc_md.teardown_msi_irqs = hsta_teardown_msi_irqs;
+	ppc_md.msi_check_device = hsta_msi_check_device;
+	return 0;
+
+out2:
+	kfree(ppc4xx_hsta_msi.irq_map);
+
+out1:
+	msi_bitmap_free(&ppc4xx_hsta_msi.bmp);
+
+out:
+	iounmap(ppc4xx_hsta_msi.data);
+	return ret;
+}
+
+static const struct of_device_id hsta_msi_ids[] = {
+	{
+		.compatible = "ibm,hsta-msi",
+	},
+	{}
+};
+
+static struct platform_driver hsta_msi_driver = {
+	.probe = hsta_msi_probe,
+	.driver = {
+		.name = "hsta-msi",
+		.owner = THIS_MODULE,
+		.of_match_table = hsta_msi_ids,
+	},
+};
+
+static int hsta_msi_init(void)
+{
+	return platform_driver_register(&hsta_msi_driver);
+}
+subsys_initcall(hsta_msi_init);
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c
index 4914fd3f41e..df6e2fc4ff9 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.c
+++ b/arch/powerpc/sysdev/ppc4xx_pci.c
@@ -176,8 +176,12 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose,
 		return -ENXIO;
 	}
 
-	/* Check that we are fully contained within 32 bits space */
-	if (res->end > 0xffffffff) {
+	/* Check that we are fully contained within 32 bits space if we are not
+	 * running on a 460sx or 476fpe which have 64 bit bus addresses.
+	 */
+	if (res->end > 0xffffffff &&
+	    !(of_device_is_compatible(hose->dn, "ibm,plb-pciex-460sx")
+	      || of_device_is_compatible(hose->dn, "ibm,plb-pciex-476fpe"))) {
 		printk(KERN_ERR "%s: dma-ranges outside of 32 bits space\n",
 		       hose->dn->full_name);
 		return -ENXIO;
@@ -1440,7 +1444,8 @@ static int __init ppc4xx_pciex_check_core_init(struct device_node *np)
 		ppc4xx_pciex_hwops = &ppc405ex_pcie_hwops;
 #endif
 #ifdef CONFIG_476FPE
-	if (of_device_is_compatible(np, "ibm,plb-pciex-476fpe"))
+	if (of_device_is_compatible(np, "ibm,plb-pciex-476fpe")
+		|| of_device_is_compatible(np, "ibm,plb-pciex-476gtr"))
 		ppc4xx_pciex_hwops = &ppc_476fpe_pcie_hwops;
 #endif
 	if (ppc4xx_pciex_hwops == NULL) {
@@ -1751,7 +1756,10 @@ static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port	*port,
 			dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL,
 				sa | DCRO_PEGPL_460SX_OMR1MSKL_UOT
 					| DCRO_PEGPL_OMRxMSKL_VAL);
-		else if (of_device_is_compatible(port->node, "ibm,plb-pciex-476fpe"))
+		else if (of_device_is_compatible(
+				port->node, "ibm,plb-pciex-476fpe") ||
+			of_device_is_compatible(
+				port->node, "ibm,plb-pciex-476gtr"))
 			dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL,
 				sa | DCRO_PEGPL_476FPE_OMR1MSKL_UOT
 					| DCRO_PEGPL_OMRxMSKL_VAL);
@@ -1881,7 +1889,10 @@ static void __init ppc4xx_configure_pciex_PIMs(struct ppc4xx_pciex_port *port,
 			sa |= PCI_BASE_ADDRESS_MEM_PREFETCH;
 
 		if (of_device_is_compatible(port->node, "ibm,plb-pciex-460sx") ||
-		    of_device_is_compatible(port->node, "ibm,plb-pciex-476fpe"))
+		    of_device_is_compatible(
+			    port->node, "ibm,plb-pciex-476fpe") ||
+		    of_device_is_compatible(
+			    port->node, "ibm,plb-pciex-476gtr"))
 			sa |= PCI_BASE_ADDRESS_MEM_TYPE_64;
 
 		out_le32(mbase + PECFG_BAR0HMPA, RES_TO_U32_HIGH(sa));
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 9dee47071af..de8d9483bbe 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -26,6 +26,7 @@
 #include <asm/errno.h>
 #include <asm/xics.h>
 #include <asm/kvm_ppc.h>
+#include <asm/dbell.h>
 
 struct icp_ipl {
 	union {
@@ -145,7 +146,13 @@ static unsigned int icp_native_get_irq(void)
 static void icp_native_cause_ipi(int cpu, unsigned long data)
 {
 	kvmppc_set_host_ipi(cpu, 1);
-	icp_native_set_qirr(cpu, IPI_PRIORITY);
+#ifdef CONFIG_PPC_DOORBELL
+	if (cpu_has_feature(CPU_FTR_DBELL) &&
+	    (cpumask_test_cpu(cpu, cpu_sibling_mask(smp_processor_id()))))
+		doorbell_cause_ipi(cpu, data);
+	else
+#endif
+		icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
 void xics_wake_cpu(int cpu)
diff --git a/arch/powerpc/xmon/nonstdio.c b/arch/powerpc/xmon/nonstdio.c
index bce3dcfe505..c9874861789 100644
--- a/arch/powerpc/xmon/nonstdio.c
+++ b/arch/powerpc/xmon/nonstdio.c
@@ -122,7 +122,7 @@ void xmon_printf(const char *format, ...)
 
 	if (n && rc == 0) {
 		/* No udbg hooks, fallback to printk() - dangerous */
-		printk(xmon_outbuf);
+		printk("%s", xmon_outbuf);
 	}
 }
 
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 08504e75b2c..d199bfa2f1f 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -419,7 +419,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 		get_output_lock();
 		excprint(regs);
 		if (bp) {
-			printf("cpu 0x%x stopped at breakpoint 0x%x (",
+			printf("cpu 0x%x stopped at breakpoint 0x%lx (",
 			       cpu, BP_NUM(bp));
 			xmon_print_symbol(regs->nip, " ", ")\n");
 		}
@@ -513,7 +513,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 		excprint(regs);
 		bp = at_breakpoint(regs->nip);
 		if (bp) {
-			printf("Stopped at breakpoint %x (", BP_NUM(bp));
+			printf("Stopped at breakpoint %lx (", BP_NUM(bp));
 			xmon_print_symbol(regs->nip, " ", ")\n");
 		}
 		if (unrecoverable_excp(regs))
@@ -759,7 +759,7 @@ static void insert_cpu_bpts(void)
 		brk.address = dabr.address;
 		brk.type = (dabr.enabled & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL;
 		brk.len = 8;
-		set_breakpoint(&brk);
+		__set_breakpoint(&brk);
 	}
 	if (iabr && cpu_has_feature(CPU_FTR_IABR))
 		mtspr(SPRN_IABR, iabr->address
@@ -997,14 +997,14 @@ static int cpu_cmd(void)
 					last_cpu = cpu;
 				} else {
 					if (last_cpu != first_cpu)
-						printf("-%lx", last_cpu);
+						printf("-0x%lx", last_cpu);
 					last_cpu = first_cpu = cpu;
-					printf(" %lx", cpu);
+					printf(" 0x%lx", cpu);
 				}
 			}
 		}
 		if (last_cpu != first_cpu)
-			printf("-%lx", last_cpu);
+			printf("-0x%lx", last_cpu);
 		printf("\n");
 		return 0;
 	}
@@ -1024,7 +1024,7 @@ static int cpu_cmd(void)
 			/* take control back */
 			mb();
 			xmon_owner = smp_processor_id();
-			printf("cpu %u didn't take control\n", cpu);
+			printf("cpu 0x%x didn't take control\n", cpu);
 			return 0;
 		}
 		barrier();
@@ -1086,7 +1086,7 @@ csum(void)
 	fcs = 0xffff;
 	for (i = 0; i < ncsum; ++i) {
 		if (mread(adrs+i, &v, 1) == 0) {
-			printf("csum stopped at %x\n", adrs+i);
+			printf("csum stopped at "REG"\n", adrs+i);
 			break;
 		}
 		fcs = FCS(fcs, v);
@@ -1202,12 +1202,12 @@ bpt_cmds(void)
 			/* assume a breakpoint address */
 			bp = at_breakpoint(a);
 			if (bp == NULL) {
-				printf("No breakpoint at %x\n", a);
+				printf("No breakpoint at %lx\n", a);
 				break;
 			}
 		}
 
-		printf("Cleared breakpoint %x (", BP_NUM(bp));
+		printf("Cleared breakpoint %lx (", BP_NUM(bp));
 		xmon_print_symbol(bp->address, " ", ")\n");
 		bp->enabled = 0;
 		break;
@@ -1746,7 +1746,7 @@ mwrite(unsigned long adrs, void *buf, int size)
 		__delay(200);
 		n = size;
 	} else {
-		printf("*** Error writing address %x\n", adrs + n);
+		printf("*** Error writing address "REG"\n", adrs + n);
 	}
 	catch_memory_errors = 0;
 	return n;
@@ -2435,7 +2435,7 @@ static void proccall(void)
 		ret = func(args[0], args[1], args[2], args[3],
 			   args[4], args[5], args[6], args[7]);
 		sync();
-		printf("return value is %x\n", ret);
+		printf("return value is 0x%lx\n", ret);
 	} else {
 		printf("*** %x exception occurred\n", fault_except);
 	}
@@ -2700,7 +2700,7 @@ static void dump_slb(void)
 	unsigned long esid,vsid,valid;
 	unsigned long llp;
 
-	printf("SLB contents of cpu %x\n", smp_processor_id());
+	printf("SLB contents of cpu 0x%x\n", smp_processor_id());
 
 	for (i = 0; i < mmu_slb_size; i++) {
 		asm volatile("slbmfee  %0,%1" : "=r" (esid) : "r" (i));
@@ -2732,7 +2732,7 @@ static void dump_stab(void)
 	int i;
 	unsigned long *tmp = (unsigned long *)local_paca->stab_addr;
 
-	printf("Segment table contents of cpu %x\n", smp_processor_id());
+	printf("Segment table contents of cpu 0x%x\n", smp_processor_id());
 
 	for (i = 0; i < PAGE_SIZE/16; i++) {
 		unsigned long a, b;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index bb63499fc5d..f5af5f6ef0f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -116,7 +116,6 @@ config S390
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 8df022c43af..fd09a10a2b5 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -45,7 +45,8 @@ CONFIG_SOLARIS_X86_PARTITION=y
 CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z9_109=y
+CONFIG_MARCH_Z196=y
+CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=256
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
@@ -240,7 +241,6 @@ CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
 CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -456,6 +456,7 @@ CONFIG_TN3270_FS=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
+CONFIG_DIAG288_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index c81a74e3e25..b061180d354 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -45,7 +45,8 @@ CONFIG_SOLARIS_X86_PARTITION=y
 CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z9_109=y
+CONFIG_MARCH_Z196=y
+CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
@@ -238,7 +239,6 @@ CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
 CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -453,6 +453,7 @@ CONFIG_TN3270_FS=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
+CONFIG_DIAG288_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index b5ba8fe1cc6..d279baa0801 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -43,7 +43,8 @@ CONFIG_SOLARIS_X86_PARTITION=y
 CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z9_109=y
+CONFIG_MARCH_Z196=y
+CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
@@ -236,7 +237,6 @@ CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
 CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -451,6 +451,7 @@ CONFIG_TN3270_FS=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
+CONFIG_DIAG288_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index cef073ca1f0..948e0e057a2 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -8,7 +8,8 @@ CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_MARCH_Z9_109=y
+CONFIG_MARCH_Z196=y
+CONFIG_TUNE_ZEC12=y
 # CONFIG_COMPAT is not set
 CONFIG_NR_CPUS=2
 # CONFIG_HOTPLUG_CPU is not set
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 4557cb7ffdd..2e56498a40d 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -135,8 +135,8 @@ CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
+CONFIG_DEBUG_PI_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_PROVE_RCU=y
@@ -199,4 +199,10 @@ CONFIG_CRYPTO_SHA512_S390=m
 CONFIG_CRYPTO_DES_S390=m
 CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRC7=m
+# CONFIG_XZ_DEC_X86 is not set
+# CONFIG_XZ_DEC_POWERPC is not set
+# CONFIG_XZ_DEC_IA64 is not set
+# CONFIG_XZ_DEC_ARM is not set
+# CONFIG_XZ_DEC_ARMTHUMB is not set
+# CONFIG_XZ_DEC_SPARC is not set
 CONFIG_CMM=m
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 4181d7baabb..773bef7614d 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -305,7 +305,6 @@ struct kvm_s390_local_interrupt {
 	struct list_head list;
 	atomic_t active;
 	struct kvm_s390_float_interrupt *float_int;
-	int timer_due; /* event indicator for waitqueue below */
 	wait_queue_head_t *wq;
 	atomic_t *cpuflags;
 	unsigned int action_bits;
@@ -367,7 +366,6 @@ struct kvm_vcpu_arch {
 	s390_fp_regs      guest_fpregs;
 	struct kvm_s390_local_interrupt local_int;
 	struct hrtimer    ckc_timer;
-	struct tasklet_struct tasklet;
 	struct kvm_s390_pgm_info pgm;
 	union  {
 		struct cpuid	cpu_id;
@@ -418,6 +416,7 @@ struct kvm_arch{
 	int css_support;
 	int use_irqchip;
 	int use_cmma;
+	int user_cpu_state_ctrl;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 	wait_queue_head_t ipte_wq;
 	spinlock_t start_stop_lock;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index c28f32a45af..3815bfea1b2 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -33,10 +33,9 @@ static inline int init_new_context(struct task_struct *tsk,
 
 static inline void set_user_asce(struct mm_struct *mm)
 {
-	pgd_t *pgd = mm->pgd;
-
-	S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd);
-	set_fs(current->thread.mm_segment);
+	S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd);
+	if (current->thread.mm_segment.ar4)
+		__ctl_load(S390_lowcore.user_asce, 7, 7);
 	set_cpu_flag(CIF_ASCE);
 }
 
@@ -70,12 +69,11 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	/* Clear old ASCE by loading the kernel ASCE. */
 	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
 	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
-	/* Delay loading of the new ASCE to control registers CR1 & CR7 */
-	set_cpu_flag(CIF_ASCE);
 	atomic_inc(&next->context.attach_count);
 	atomic_dec(&prev->context.attach_count);
 	if (MACHINE_HAS_TLB_LC)
 		cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
+	S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd);
 }
 
 #define finish_arch_post_lock_switch finish_arch_post_lock_switch
@@ -84,17 +82,18 @@ static inline void finish_arch_post_lock_switch(void)
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
 
-	if (!mm)
-		return;
-	preempt_disable();
-	while (atomic_read(&mm->context.attach_count) >> 16)
-		cpu_relax();
-
-	cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-	set_user_asce(mm);
-	if (mm->context.flush_mm)
-		__tlb_flush_mm(mm);
-	preempt_enable();
+	load_kernel_asce();
+	if (mm) {
+		preempt_disable();
+		while (atomic_read(&mm->context.attach_count) >> 16)
+			cpu_relax();
+
+		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+		if (mm->context.flush_mm)
+			__tlb_flush_mm(mm);
+		preempt_enable();
+	}
+	set_fs(current->thread.mm_segment);
 }
 
 #define enter_lazy_tlb(mm,tsk)	do { } while (0)
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 6f02d452bbe..e568fc8a725 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -217,7 +217,7 @@ static inline void cpu_relax(void)
 	barrier();
 }
 
-#define arch_mutex_cpu_relax()  barrier()
+#define cpu_relax_lowlatency()  barrier()
 
 static inline void psw_set_key(unsigned int key)
 {
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 29c81f82705..18ea9e3f814 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -51,8 +51,8 @@ static inline int restore_fp_ctl(u32 *fpc)
 		return 0;
 
 	asm volatile(
-		"0:	lfpc    %1\n"
-		"	la	%0,0\n"
+		"	lfpc    %1\n"
+		"0:	la	%0,0\n"
 		"1:\n"
 		EX_TABLE(0b,1b)
 		: "=d" (rc) : "Q" (*fpc), "0" (-EINVAL));
@@ -134,8 +134,4 @@ static inline void restore_access_regs(unsigned int *acrs)
 	prev = __switch_to(prev,next);					\
 } while (0)
 
-#define finish_arch_switch(prev) do {					     \
-	set_fs(current->thread.mm_segment);				     \
-} while (0)
-
 #endif /* __ASM_SWITCH_TO_H */
diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild
index 6a9a9eb645f..08fe6dad902 100644
--- a/arch/s390/include/uapi/asm/Kbuild
+++ b/arch/s390/include/uapi/asm/Kbuild
@@ -16,6 +16,7 @@ header-y += ioctls.h
 header-y += ipcbuf.h
 header-y += kvm.h
 header-y += kvm_para.h
+header-y += kvm_perf.h
 header-y += kvm_virtio.h
 header-y += mman.h
 header-y += monwriter.h
@@ -36,6 +37,7 @@ header-y += signal.h
 header-y += socket.h
 header-y += sockios.h
 header-y += sclp_ctl.h
+header-y += sie.h
 header-y += stat.h
 header-y += statfs.h
 header-y += swab.h
diff --git a/arch/s390/include/uapi/asm/kvm_perf.h b/arch/s390/include/uapi/asm/kvm_perf.h
new file mode 100644
index 00000000000..397282727e2
--- /dev/null
+++ b/arch/s390/include/uapi/asm/kvm_perf.h
@@ -0,0 +1,25 @@
+/*
+ * Definitions for perf-kvm on s390
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_KVM_PERF_S390_H
+#define __LINUX_KVM_PERF_S390_H
+
+#include <asm/sie.h>
+
+#define DECODE_STR_LEN 40
+
+#define VCPU_ID "id"
+
+#define KVM_ENTRY_TRACE "kvm:kvm_s390_sie_enter"
+#define KVM_EXIT_TRACE "kvm:kvm_s390_sie_exit"
+#define KVM_EXIT_REASON "icptcode"
+
+#endif
diff --git a/arch/s390/include/uapi/asm/sie.h b/arch/s390/include/uapi/asm/sie.h
index 3d97f610198..d4096fdfc6a 100644
--- a/arch/s390/include/uapi/asm/sie.h
+++ b/arch/s390/include/uapi/asm/sie.h
@@ -1,8 +1,6 @@
 #ifndef _UAPI_ASM_S390_SIE_H
 #define _UAPI_ASM_S390_SIE_H
 
-#include <asm/sigp.h>
-
 #define diagnose_codes						\
 	{ 0x10, "DIAG (0x10) release pages" },			\
 	{ 0x44, "DIAG (0x44) time slice end" },			\
@@ -13,18 +11,18 @@
 	{ 0x500, "DIAG (0x500) KVM virtio functions" },		\
 	{ 0x501, "DIAG (0x501) KVM breakpoint" }
 
-#define sigp_order_codes						\
-	{ SIGP_SENSE, "SIGP sense" },					\
-	{ SIGP_EXTERNAL_CALL, "SIGP external call" },			\
-	{ SIGP_EMERGENCY_SIGNAL, "SIGP emergency signal" },		\
-	{ SIGP_STOP, "SIGP stop" },					\
-	{ SIGP_STOP_AND_STORE_STATUS, "SIGP stop and store status" },	\
-	{ SIGP_SET_ARCHITECTURE, "SIGP set architecture" },		\
-	{ SIGP_SET_PREFIX, "SIGP set prefix" },				\
-	{ SIGP_SENSE_RUNNING, "SIGP sense running" },			\
-	{ SIGP_RESTART, "SIGP restart" },				\
-	{ SIGP_INITIAL_CPU_RESET, "SIGP initial cpu reset" },		\
-	{ SIGP_STORE_STATUS_AT_ADDRESS, "SIGP store status at address" }
+#define sigp_order_codes					\
+	{ 0x01, "SIGP sense" },					\
+	{ 0x02, "SIGP external call" },				\
+	{ 0x03, "SIGP emergency signal" },			\
+	{ 0x05, "SIGP stop" },					\
+	{ 0x06, "SIGP restart" },				\
+	{ 0x09, "SIGP stop and store status" },			\
+	{ 0x0b, "SIGP initial cpu reset" },			\
+	{ 0x0d, "SIGP set prefix" },				\
+	{ 0x0e, "SIGP store status at address" },		\
+	{ 0x12, "SIGP set architecture" },			\
+	{ 0x15, "SIGP sense running" }
 
 #define icpt_prog_codes						\
 	{ 0x0001, "Prog Operation" },				\
@@ -110,6 +108,7 @@
 	exit_code_ipa0(0xB2, 0x17, "STETR"),	\
 	exit_code_ipa0(0xB2, 0x18, "PC"),	\
 	exit_code_ipa0(0xB2, 0x20, "SERVC"),	\
+	exit_code_ipa0(0xB2, 0x21, "IPTE"),	\
 	exit_code_ipa0(0xB2, 0x28, "PT"),	\
 	exit_code_ipa0(0xB2, 0x29, "ISKE"),	\
 	exit_code_ipa0(0xB2, 0x2a, "RRBE"),	\
diff --git a/arch/s390/include/uapi/asm/ucontext.h b/arch/s390/include/uapi/asm/ucontext.h
index 200e06325c6..3e077b2a470 100644
--- a/arch/s390/include/uapi/asm/ucontext.h
+++ b/arch/s390/include/uapi/asm/ucontext.h
@@ -16,7 +16,9 @@ struct ucontext_extended {
 	struct ucontext  *uc_link;
 	stack_t		  uc_stack;
 	_sigregs	  uc_mcontext;
-	unsigned long	  uc_sigmask[2];
+	sigset_t	  uc_sigmask;
+	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
+	unsigned char	  __unused[128 - sizeof(sigset_t)];
 	unsigned long	  uc_gprs_high[16];
 };
 
@@ -27,7 +29,9 @@ struct ucontext {
 	struct ucontext  *uc_link;
 	stack_t		  uc_stack;
 	_sigregs          uc_mcontext;
-	sigset_t	  uc_sigmask;	/* mask last for extensibility */
+	sigset_t	  uc_sigmask;
+	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
+	unsigned char	  __unused[128 - sizeof(sigset_t)];
 };
 
 #endif /* !_ASM_S390_UCONTEXT_H */
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index 39ddfdb40ae..70d4b7c4bea 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -69,7 +69,9 @@ struct ucontext32 {
 	__u32			uc_link;	/* pointer */	
 	compat_stack_t		uc_stack;
 	_sigregs32		uc_mcontext;
-	compat_sigset_t		uc_sigmask;	/* mask last for extensibility */
+	compat_sigset_t		uc_sigmask;
+	/* Allow for uc_sigmask growth.  Glibc uses a 1024-bit sigset_t.  */
+	unsigned char		__unused[128 - sizeof(compat_sigset_t)];
 };
 
 struct stat64_emu31;
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 7ba7d678451..e88d35d7495 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -437,11 +437,11 @@ ENTRY(startup_kdump)
 
 #if defined(CONFIG_64BIT)
 #if defined(CONFIG_MARCH_ZEC12)
-	.long 3, 0xc100efea, 0xf46ce800, 0x00400000
+	.long 3, 0xc100eff2, 0xf46ce800, 0x00400000
 #elif defined(CONFIG_MARCH_Z196)
-	.long 2, 0xc100efea, 0xf46c0000
+	.long 2, 0xc100eff2, 0xf46c0000
 #elif defined(CONFIG_MARCH_Z10)
-	.long 2, 0xc100efea, 0xf0680000
+	.long 2, 0xc100eff2, 0xf0680000
 #elif defined(CONFIG_MARCH_Z9_109)
 	.long 1, 0xc100efc2
 #elif defined(CONFIG_MARCH_Z990)
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 08dcf21cb8d..433c6dbfa44 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -21,13 +21,9 @@ ENTRY(_mcount)
 ENTRY(ftrace_caller)
 #endif
 	stm	%r2,%r5,16(%r15)
-	bras	%r1,2f
+	bras	%r1,1f
 0:	.long	ftrace_trace_function
-1:	.long	function_trace_stop
-2:	l	%r2,1b-0b(%r1)
-	icm	%r2,0xf,0(%r2)
-	jnz	3f
-	st	%r14,56(%r15)
+1:	st	%r14,56(%r15)
 	lr	%r0,%r15
 	ahi	%r15,-96
 	l	%r3,100(%r15)
@@ -50,7 +46,7 @@ ENTRY(ftrace_graph_caller)
 #endif
 	ahi	%r15,96
 	l	%r14,56(%r15)
-3:	lm	%r2,%r5,16(%r15)
+	lm	%r2,%r5,16(%r15)
 	br	%r14
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S
index 1c52eae3396..c67a8bf0fd9 100644
--- a/arch/s390/kernel/mcount64.S
+++ b/arch/s390/kernel/mcount64.S
@@ -20,9 +20,6 @@ ENTRY(_mcount)
 
 ENTRY(ftrace_caller)
 #endif
-	larl	%r1,function_trace_stop
-	icm	%r1,0xf,0(%r1)
-	bnzr	%r14
 	stmg	%r2,%r5,32(%r15)
 	stg	%r14,112(%r15)
 	lgr	%r1,%r15
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index ea75d011a6f..d3194de7ae1 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -411,12 +411,6 @@ static int cpumf_pmu_event_init(struct perf_event *event)
 	case PERF_TYPE_HARDWARE:
 	case PERF_TYPE_HW_CACHE:
 	case PERF_TYPE_RAW:
-		/* The CPU measurement counter facility does not have overflow
-		 * interrupts to do sampling.  Sampling must be provided by
-		 * external means, for example, by timers.
-		 */
-		if (is_sampling_event(event))
-			return -ENOENT;
 		err = __hw_perf_event_init(event);
 		break;
 	default:
@@ -681,6 +675,12 @@ static int __init cpumf_pmu_init(void)
 		goto out;
 	}
 
+	/* The CPU measurement counter facility does not have overflow
+	 * interrupts to do sampling.  Sampling must be provided by
+	 * external means, for example, by timers.
+	 */
+	cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	cpumf_pmu.attr_groups = cpumf_cf_event_group();
 	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
 	if (rc) {
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 2d716734b5b..5dc7ad9e2fb 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -334,9 +334,14 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 			unsigned long mask = PSW_MASK_USER;
 
 			mask |= is_ri_task(child) ? PSW_MASK_RI : 0;
-			if ((data & ~mask) != PSW_USER_BITS)
+			if ((data ^ PSW_USER_BITS) & ~mask)
+				/* Invalid psw mask. */
+				return -EINVAL;
+			if ((data & PSW_MASK_ASC) == PSW_ASC_HOME)
+				/* Invalid address-space-control bits */
 				return -EINVAL;
 			if ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))
+				/* Invalid addressing mode bits */
 				return -EINVAL;
 		}
 		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
@@ -672,9 +677,12 @@ static int __poke_user_compat(struct task_struct *child,
 
 			mask |= is_ri_task(child) ? PSW32_MASK_RI : 0;
 			/* Build a 64 bit psw mask from 31 bit mask. */
-			if ((tmp & ~mask) != PSW32_USER_BITS)
+			if ((tmp ^ PSW32_USER_BITS) & ~mask)
 				/* Invalid psw mask. */
 				return -EINVAL;
+			if ((data & PSW32_MASK_ASC) == PSW32_ASC_HOME)
+				/* Invalid address-space-control bits */
+				return -EINVAL;
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
 				(regs->psw.mask & PSW_MASK_BA) |
 				(__u64)(tmp & mask) << 32;
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 0161675878a..59bd8f991b9 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -176,7 +176,8 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP;
 	}
 
-	kvm_s390_vcpu_stop(vcpu);
+	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+		kvm_s390_vcpu_stop(vcpu);
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index a0b586c1913..eaf46291d36 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -56,32 +56,26 @@ static int handle_noop(struct kvm_vcpu *vcpu)
 static int handle_stop(struct kvm_vcpu *vcpu)
 {
 	int rc = 0;
+	unsigned int action_bits;
 
 	vcpu->stat.exit_stop_request++;
-	spin_lock_bh(&vcpu->arch.local_int.lock);
-
 	trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits);
 
-	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
-		kvm_s390_vcpu_stop(vcpu);
-		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
-		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
-		rc = -EOPNOTSUPP;
-	}
+	action_bits = vcpu->arch.local_int.action_bits;
 
-	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
-		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
-		/* store status must be called unlocked. Since local_int.lock
-		 * only protects local_int.* and not guest memory we can give
-		 * up the lock here */
-		spin_unlock_bh(&vcpu->arch.local_int.lock);
+	if (!(action_bits & ACTION_STOP_ON_STOP))
+		return 0;
+
+	if (action_bits & ACTION_STORE_ON_STOP) {
 		rc = kvm_s390_vcpu_store_status(vcpu,
 						KVM_S390_STORE_STATUS_NOADDR);
-		if (rc >= 0)
-			rc = -EOPNOTSUPP;
-	} else
-		spin_unlock_bh(&vcpu->arch.local_int.lock);
-	return rc;
+		if (rc)
+			return rc;
+	}
+
+	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+		kvm_s390_vcpu_stop(vcpu);
+	return -EOPNOTSUPP;
 }
 
 static int handle_validity(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 90c8de22a2a..92528a0bdda 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -158,6 +158,9 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 					       LCTL_CR10 | LCTL_CR11);
 		vcpu->arch.sie_block->ictl |= (ICTL_STCTL | ICTL_PINT);
 	}
+
+	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP)
+		atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
 }
 
 static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
@@ -544,13 +547,13 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
 	int rc = 0;
 
 	if (atomic_read(&li->active)) {
-		spin_lock_bh(&li->lock);
+		spin_lock(&li->lock);
 		list_for_each_entry(inti, &li->list, list)
 			if (__interrupt_is_deliverable(vcpu, inti)) {
 				rc = 1;
 				break;
 			}
-		spin_unlock_bh(&li->lock);
+		spin_unlock(&li->lock);
 	}
 
 	if ((!rc) && atomic_read(&fi->active)) {
@@ -585,88 +588,56 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 {
 	u64 now, sltime;
-	DECLARE_WAITQUEUE(wait, current);
 
 	vcpu->stat.exit_wait_state++;
-	if (kvm_cpu_has_interrupt(vcpu))
-		return 0;
 
-	__set_cpu_idle(vcpu);
-	spin_lock_bh(&vcpu->arch.local_int.lock);
-	vcpu->arch.local_int.timer_due = 0;
-	spin_unlock_bh(&vcpu->arch.local_int.lock);
+	/* fast path */
+	if (kvm_cpu_has_pending_timer(vcpu) || kvm_arch_vcpu_runnable(vcpu))
+		return 0;
 
 	if (psw_interrupts_disabled(vcpu)) {
 		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
-		__unset_cpu_idle(vcpu);
 		return -EOPNOTSUPP; /* disabled wait */
 	}
 
+	__set_cpu_idle(vcpu);
 	if (!ckc_interrupts_enabled(vcpu)) {
 		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
 		goto no_timer;
 	}
 
 	now = get_tod_clock_fast() + vcpu->arch.sie_block->epoch;
-	if (vcpu->arch.sie_block->ckc < now) {
-		__unset_cpu_idle(vcpu);
-		return 0;
-	}
-
 	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
-
 	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
 	VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);
 no_timer:
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-	spin_lock(&vcpu->arch.local_int.float_int->lock);
-	spin_lock_bh(&vcpu->arch.local_int.lock);
-	add_wait_queue(&vcpu->wq, &wait);
-	while (list_empty(&vcpu->arch.local_int.list) &&
-		list_empty(&vcpu->arch.local_int.float_int->list) &&
-		(!vcpu->arch.local_int.timer_due) &&
-		!signal_pending(current) &&
-		!kvm_s390_si_ext_call_pending(vcpu)) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		spin_unlock_bh(&vcpu->arch.local_int.lock);
-		spin_unlock(&vcpu->arch.local_int.float_int->lock);
-		schedule();
-		spin_lock(&vcpu->arch.local_int.float_int->lock);
-		spin_lock_bh(&vcpu->arch.local_int.lock);
-	}
+	kvm_vcpu_block(vcpu);
 	__unset_cpu_idle(vcpu);
-	__set_current_state(TASK_RUNNING);
-	remove_wait_queue(&vcpu->wq, &wait);
-	spin_unlock_bh(&vcpu->arch.local_int.lock);
-	spin_unlock(&vcpu->arch.local_int.float_int->lock);
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
 	return 0;
 }
 
-void kvm_s390_tasklet(unsigned long parm)
+void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm;
-
-	spin_lock(&vcpu->arch.local_int.lock);
-	vcpu->arch.local_int.timer_due = 1;
-	if (waitqueue_active(&vcpu->wq))
+	if (waitqueue_active(&vcpu->wq)) {
+		/*
+		 * The vcpu gave up the cpu voluntarily, mark it as a good
+		 * yield-candidate.
+		 */
+		vcpu->preempted = true;
 		wake_up_interruptible(&vcpu->wq);
-	spin_unlock(&vcpu->arch.local_int.lock);
+	}
 }
 
-/*
- * low level hrtimer wake routine. Because this runs in hardirq context
- * we schedule a tasklet to do the real work.
- */
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
 
 	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
-	vcpu->preempted = true;
-	tasklet_schedule(&vcpu->arch.tasklet);
+	kvm_s390_vcpu_wakeup(vcpu);
 
 	return HRTIMER_NORESTART;
 }
@@ -676,13 +647,13 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
 	struct kvm_s390_interrupt_info  *n, *inti = NULL;
 
-	spin_lock_bh(&li->lock);
+	spin_lock(&li->lock);
 	list_for_each_entry_safe(inti, n, &li->list, list) {
 		list_del(&inti->list);
 		kfree(inti);
 	}
 	atomic_set(&li->active, 0);
-	spin_unlock_bh(&li->lock);
+	spin_unlock(&li->lock);
 
 	/* clear pending external calls set by sigp interpretation facility */
 	atomic_clear_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
@@ -701,7 +672,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 	if (atomic_read(&li->active)) {
 		do {
 			deliver = 0;
-			spin_lock_bh(&li->lock);
+			spin_lock(&li->lock);
 			list_for_each_entry_safe(inti, n, &li->list, list) {
 				if (__interrupt_is_deliverable(vcpu, inti)) {
 					list_del(&inti->list);
@@ -712,7 +683,7 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 			}
 			if (list_empty(&li->list))
 				atomic_set(&li->active, 0);
-			spin_unlock_bh(&li->lock);
+			spin_unlock(&li->lock);
 			if (deliver) {
 				__do_deliver_interrupt(vcpu, inti);
 				kfree(inti);
@@ -758,7 +729,7 @@ void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
 	if (atomic_read(&li->active)) {
 		do {
 			deliver = 0;
-			spin_lock_bh(&li->lock);
+			spin_lock(&li->lock);
 			list_for_each_entry_safe(inti, n, &li->list, list) {
 				if ((inti->type == KVM_S390_MCHK) &&
 				    __interrupt_is_deliverable(vcpu, inti)) {
@@ -770,7 +741,7 @@ void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
 			}
 			if (list_empty(&li->list))
 				atomic_set(&li->active, 0);
-			spin_unlock_bh(&li->lock);
+			spin_unlock(&li->lock);
 			if (deliver) {
 				__do_deliver_interrupt(vcpu, inti);
 				kfree(inti);
@@ -817,11 +788,11 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 
 	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, inti->type, code, 0, 1);
-	spin_lock_bh(&li->lock);
+	spin_lock(&li->lock);
 	list_add(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
 	BUG_ON(waitqueue_active(li->wq));
-	spin_unlock_bh(&li->lock);
+	spin_unlock(&li->lock);
 	return 0;
 }
 
@@ -842,11 +813,11 @@ int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu,
 
 	inti->type = KVM_S390_PROGRAM_INT;
 	memcpy(&inti->pgm, pgm_info, sizeof(inti->pgm));
-	spin_lock_bh(&li->lock);
+	spin_lock(&li->lock);
 	list_add(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
 	BUG_ON(waitqueue_active(li->wq));
-	spin_unlock_bh(&li->lock);
+	spin_unlock(&li->lock);
 	return 0;
 }
 
@@ -934,12 +905,10 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	}
 	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
 	li = &dst_vcpu->arch.local_int;
-	spin_lock_bh(&li->lock);
+	spin_lock(&li->lock);
 	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-	if (waitqueue_active(li->wq))
-		wake_up_interruptible(li->wq);
-	kvm_get_vcpu(kvm, sigcpu)->preempted = true;
-	spin_unlock_bh(&li->lock);
+	spin_unlock(&li->lock);
+	kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu));
 unlock_fi:
 	spin_unlock(&fi->lock);
 	mutex_unlock(&kvm->lock);
@@ -1081,7 +1050,7 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 
 	mutex_lock(&vcpu->kvm->lock);
 	li = &vcpu->arch.local_int;
-	spin_lock_bh(&li->lock);
+	spin_lock(&li->lock);
 	if (inti->type == KVM_S390_PROGRAM_INT)
 		list_add(&inti->list, &li->list);
 	else
@@ -1090,11 +1059,9 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 	if (inti->type == KVM_S390_SIGP_STOP)
 		li->action_bits |= ACTION_STOP_ON_STOP;
 	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
-	vcpu->preempted = true;
-	spin_unlock_bh(&li->lock);
+	spin_unlock(&li->lock);
 	mutex_unlock(&vcpu->kvm->lock);
+	kvm_s390_vcpu_wakeup(vcpu);
 	return 0;
 }
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2f3e14fe91a..339b34a02fb 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -166,7 +166,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:
+	case KVM_CAP_S390_IRQCHIP:
 	case KVM_CAP_VM_ATTRIBUTES:
+	case KVM_CAP_MP_STATE:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -595,7 +597,8 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
-	kvm_s390_vcpu_stop(vcpu);
+	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+		kvm_s390_vcpu_stop(vcpu);
 	kvm_s390_clear_local_irqs(vcpu);
 }
 
@@ -647,8 +650,6 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 			return rc;
 	}
 	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
-		     (unsigned long) vcpu);
 	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
 	get_cpu_id(&vcpu->arch.cpu_id);
 	vcpu->arch.cpu_id.version = 0xff;
@@ -926,7 +927,7 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
 {
 	int rc = 0;
 
-	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
+	if (!is_vcpu_stopped(vcpu))
 		rc = -EBUSY;
 	else {
 		vcpu->run->psw_mask = psw.mask;
@@ -980,13 +981,34 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	return -EINVAL; /* not implemented yet */
+	/* CHECK_STOP and LOAD are not supported yet */
+	return is_vcpu_stopped(vcpu) ? KVM_MP_STATE_STOPPED :
+				       KVM_MP_STATE_OPERATING;
 }
 
 int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	return -EINVAL; /* not implemented yet */
+	int rc = 0;
+
+	/* user space knows about this interface - let it control the state */
+	vcpu->kvm->arch.user_cpu_state_ctrl = 1;
+
+	switch (mp_state->mp_state) {
+	case KVM_MP_STATE_STOPPED:
+		kvm_s390_vcpu_stop(vcpu);
+		break;
+	case KVM_MP_STATE_OPERATING:
+		kvm_s390_vcpu_start(vcpu);
+		break;
+	case KVM_MP_STATE_LOAD:
+	case KVM_MP_STATE_CHECK_STOP:
+		/* fall through - CHECK_STOP and LOAD are not supported yet */
+	default:
+		rc = -ENXIO;
+	}
+
+	return rc;
 }
 
 bool kvm_s390_cmma_enabled(struct kvm *kvm)
@@ -1045,6 +1067,9 @@ retry:
 		goto retry;
 	}
 
+	/* nothing to do, just clear the request */
+	clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
+
 	return 0;
 }
 
@@ -1284,7 +1309,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
-	kvm_s390_vcpu_start(vcpu);
+	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
+		kvm_s390_vcpu_start(vcpu);
+	} else if (is_vcpu_stopped(vcpu)) {
+		pr_err_ratelimited("kvm-s390: can't run stopped vcpu %d\n",
+				   vcpu->vcpu_id);
+		return -EINVAL;
+	}
 
 	switch (kvm_run->exit_reason) {
 	case KVM_EXIT_S390_SIEIC:
@@ -1413,11 +1444,6 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	return kvm_s390_store_status_unloaded(vcpu, addr);
 }
 
-static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
-{
-	return atomic_read(&(vcpu)->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
-}
-
 static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 {
 	kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu);
@@ -1451,7 +1477,7 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 
 	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
 	/* Only one cpu at a time may enter/leave the STOPPED state. */
-	spin_lock_bh(&vcpu->kvm->arch.start_stop_lock);
+	spin_lock(&vcpu->kvm->arch.start_stop_lock);
 	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);
 
 	for (i = 0; i < online_vcpus; i++) {
@@ -1477,7 +1503,7 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 	 * Let's play safe and flush the VCPU at startup.
 	 */
 	vcpu->arch.sie_block->ihcpu  = 0xffff;
-	spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock);
+	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
 	return;
 }
 
@@ -1491,10 +1517,18 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 
 	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
 	/* Only one cpu at a time may enter/leave the STOPPED state. */
-	spin_lock_bh(&vcpu->kvm->arch.start_stop_lock);
+	spin_lock(&vcpu->kvm->arch.start_stop_lock);
 	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);
 
+	/* Need to lock access to action_bits to avoid a SIGP race condition */
+	spin_lock(&vcpu->arch.local_int.lock);
 	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+
+	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
+	vcpu->arch.local_int.action_bits &=
+				 ~(ACTION_STOP_ON_STOP | ACTION_STORE_ON_STOP);
+	spin_unlock(&vcpu->arch.local_int.lock);
+
 	__disable_ibs_on_vcpu(vcpu);
 
 	for (i = 0; i < online_vcpus; i++) {
@@ -1512,7 +1546,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 		__enable_ibs_on_vcpu(started_vcpu);
 	}
 
-	spin_unlock_bh(&vcpu->kvm->arch.start_stop_lock);
+	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
 	return;
 }
 
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index a8655ed3161..3862fa2cefe 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -45,9 +45,9 @@ do { \
 	  d_args); \
 } while (0)
 
-static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
+static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
 {
-	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
+	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
 }
 
 static inline int kvm_is_ucontrol(struct kvm *kvm)
@@ -129,9 +129,15 @@ static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc)
 	vcpu->arch.sie_block->gpsw.mask |= cc << 44;
 }
 
+/* are cpu states controlled by user space */
+static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm)
+{
+	return kvm->arch.user_cpu_state_ctrl != 0;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
+void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
-void kvm_s390_tasklet(unsigned long parm);
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
 void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu);
 void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 43079a48cc9..cf243ba3d50 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -125,8 +125,9 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
 	return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED;
 }
 
-static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
+static int __inject_sigp_stop(struct kvm_vcpu *dst_vcpu, int action)
 {
+	struct kvm_s390_local_interrupt *li = &dst_vcpu->arch.local_int;
 	struct kvm_s390_interrupt_info *inti;
 	int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 
@@ -135,7 +136,13 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 		return -ENOMEM;
 	inti->type = KVM_S390_SIGP_STOP;
 
-	spin_lock_bh(&li->lock);
+	spin_lock(&li->lock);
+	if (li->action_bits & ACTION_STOP_ON_STOP) {
+		/* another SIGP STOP is pending */
+		kfree(inti);
+		rc = SIGP_CC_BUSY;
+		goto out;
+	}
 	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
 		kfree(inti);
 		if ((action & ACTION_STORE_ON_STOP) != 0)
@@ -144,19 +151,17 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 	}
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
-	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
 	li->action_bits |= action;
-	if (waitqueue_active(li->wq))
-		wake_up_interruptible(li->wq);
+	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+	kvm_s390_vcpu_wakeup(dst_vcpu);
 out:
-	spin_unlock_bh(&li->lock);
+	spin_unlock(&li->lock);
 
 	return rc;
 }
 
 static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action)
 {
-	struct kvm_s390_local_interrupt *li;
 	struct kvm_vcpu *dst_vcpu = NULL;
 	int rc;
 
@@ -166,9 +171,8 @@ static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action)
 	dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
-	li = &dst_vcpu->arch.local_int;
 
-	rc = __inject_sigp_stop(li, action);
+	rc = __inject_sigp_stop(dst_vcpu, action);
 
 	VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr);
 
@@ -238,7 +242,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 	if (!inti)
 		return SIGP_CC_BUSY;
 
-	spin_lock_bh(&li->lock);
+	spin_lock(&li->lock);
 	/* cpu must be in stopped state */
 	if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
 		*reg &= 0xffffffff00000000UL;
@@ -253,13 +257,12 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
-	if (waitqueue_active(li->wq))
-		wake_up_interruptible(li->wq);
+	kvm_s390_vcpu_wakeup(dst_vcpu);
 	rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 
 	VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address);
 out_li:
-	spin_unlock_bh(&li->lock);
+	spin_unlock(&li->lock);
 	return rc;
 }
 
@@ -275,9 +278,9 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, u16 cpu_id,
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
 
-	spin_lock_bh(&dst_vcpu->arch.local_int.lock);
+	spin_lock(&dst_vcpu->arch.local_int.lock);
 	flags = atomic_read(dst_vcpu->arch.local_int.cpuflags);
-	spin_unlock_bh(&dst_vcpu->arch.local_int.lock);
+	spin_unlock(&dst_vcpu->arch.local_int.lock);
 	if (!(flags & CPUSTAT_STOPPED)) {
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INCORRECT_STATE;
@@ -338,10 +341,10 @@ static int sigp_check_callable(struct kvm_vcpu *vcpu, u16 cpu_addr)
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
 	li = &dst_vcpu->arch.local_int;
-	spin_lock_bh(&li->lock);
+	spin_lock(&li->lock);
 	if (li->action_bits & ACTION_STOP_ON_STOP)
 		rc = SIGP_CC_BUSY;
-	spin_unlock_bh(&li->lock);
+	spin_unlock(&li->lock);
 
 	return rc;
 }
@@ -461,12 +464,7 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu)
 		dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
 		BUG_ON(dest_vcpu == NULL);
 
-		spin_lock_bh(&dest_vcpu->arch.local_int.lock);
-		if (waitqueue_active(&dest_vcpu->wq))
-			wake_up_interruptible(&dest_vcpu->wq);
-		dest_vcpu->preempted = true;
-		spin_unlock_bh(&dest_vcpu->arch.local_int.lock);
-
+		kvm_s390_vcpu_wakeup(dest_vcpu);
 		kvm_s390_set_psw_cc(vcpu, SIGP_CC_ORDER_CODE_ACCEPTED);
 		return 0;
 	}
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index e9f8fa9337f..a2cbd875543 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -269,27 +269,17 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter)
 		EMIT4(0xa7c80000);
 	/* Clear A if the first register does not set it. */
 	switch (filter[0].code) {
-	case BPF_S_LD_W_ABS:
-	case BPF_S_LD_H_ABS:
-	case BPF_S_LD_B_ABS:
-	case BPF_S_LD_W_LEN:
-	case BPF_S_LD_W_IND:
-	case BPF_S_LD_H_IND:
-	case BPF_S_LD_B_IND:
-	case BPF_S_LD_IMM:
-	case BPF_S_LD_MEM:
-	case BPF_S_MISC_TXA:
-	case BPF_S_ANC_PROTOCOL:
-	case BPF_S_ANC_PKTTYPE:
-	case BPF_S_ANC_IFINDEX:
-	case BPF_S_ANC_MARK:
-	case BPF_S_ANC_QUEUE:
-	case BPF_S_ANC_HATYPE:
-	case BPF_S_ANC_RXHASH:
-	case BPF_S_ANC_CPU:
-	case BPF_S_ANC_VLAN_TAG:
-	case BPF_S_ANC_VLAN_TAG_PRESENT:
-	case BPF_S_RET_K:
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
+	case BPF_LD | BPF_W | BPF_LEN:
+	case BPF_LD | BPF_W | BPF_IND:
+	case BPF_LD | BPF_H | BPF_IND:
+	case BPF_LD | BPF_B | BPF_IND:
+	case BPF_LD | BPF_IMM:
+	case BPF_LD | BPF_MEM:
+	case BPF_MISC | BPF_TXA:
+	case BPF_RET | BPF_K:
 		/* first instruction sets A register */
 		break;
 	default: /* A = 0 */
@@ -304,15 +294,18 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 	unsigned int K;
 	int offset;
 	unsigned int mask;
+	u16 code;
 
 	K = filter->k;
-	switch (filter->code) {
-	case BPF_S_ALU_ADD_X: /* A += X */
+	code = bpf_anc_helper(filter);
+
+	switch (code) {
+	case BPF_ALU | BPF_ADD | BPF_X: /* A += X */
 		jit->seen |= SEEN_XREG;
 		/* ar %r5,%r12 */
 		EMIT2(0x1a5c);
 		break;
-	case BPF_S_ALU_ADD_K: /* A += K */
+	case BPF_ALU | BPF_ADD | BPF_K: /* A += K */
 		if (!K)
 			break;
 		if (K <= 16383)
@@ -325,12 +318,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* a %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5a50d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_SUB_X: /* A -= X */
+	case BPF_ALU | BPF_SUB | BPF_X: /* A -= X */
 		jit->seen |= SEEN_XREG;
 		/* sr %r5,%r12 */
 		EMIT2(0x1b5c);
 		break;
-	case BPF_S_ALU_SUB_K: /* A -= K */
+	case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */
 		if (!K)
 			break;
 		if (K <= 16384)
@@ -343,12 +336,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* s %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5b50d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_MUL_X: /* A *= X */
+	case BPF_ALU | BPF_MUL | BPF_X: /* A *= X */
 		jit->seen |= SEEN_XREG;
 		/* msr %r5,%r12 */
 		EMIT4(0xb252005c);
 		break;
-	case BPF_S_ALU_MUL_K: /* A *= K */
+	case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */
 		if (K <= 16383)
 			/* mhi %r5,K */
 			EMIT4_IMM(0xa75c0000, K);
@@ -359,7 +352,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* ms %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x7150d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_DIV_X: /* A /= X */
+	case BPF_ALU | BPF_DIV | BPF_X: /* A /= X */
 		jit->seen |= SEEN_XREG | SEEN_RET0;
 		/* ltr %r12,%r12 */
 		EMIT2(0x12cc);
@@ -370,7 +363,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* dlr %r4,%r12 */
 		EMIT4(0xb997004c);
 		break;
-	case BPF_S_ALU_DIV_K: /* A /= K */
+	case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */
 		if (K == 1)
 			break;
 		/* lhi %r4,0 */
@@ -378,7 +371,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* dl %r4,<d(K)>(%r13) */
 		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_MOD_X: /* A %= X */
+	case BPF_ALU | BPF_MOD | BPF_X: /* A %= X */
 		jit->seen |= SEEN_XREG | SEEN_RET0;
 		/* ltr %r12,%r12 */
 		EMIT2(0x12cc);
@@ -391,7 +384,7 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
-	case BPF_S_ALU_MOD_K: /* A %= K */
+	case BPF_ALU | BPF_MOD | BPF_K: /* A %= K */
 		if (K == 1) {
 			/* lhi %r5,0 */
 			EMIT4(0xa7580000);
@@ -404,12 +397,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
-	case BPF_S_ALU_AND_X: /* A &= X */
+	case BPF_ALU | BPF_AND | BPF_X: /* A &= X */
 		jit->seen |= SEEN_XREG;
 		/* nr %r5,%r12 */
 		EMIT2(0x145c);
 		break;
-	case BPF_S_ALU_AND_K: /* A &= K */
+	case BPF_ALU | BPF_AND | BPF_K: /* A &= K */
 		if (test_facility(21))
 			/* nilf %r5,<K> */
 			EMIT6_IMM(0xc05b0000, K);
@@ -417,12 +410,12 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* n %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5450d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_OR_X: /* A |= X */
+	case BPF_ALU | BPF_OR | BPF_X: /* A |= X */
 		jit->seen |= SEEN_XREG;
 		/* or %r5,%r12 */
 		EMIT2(0x165c);
 		break;
-	case BPF_S_ALU_OR_K: /* A |= K */
+	case BPF_ALU | BPF_OR | BPF_K: /* A |= K */
 		if (test_facility(21))
 			/* oilf %r5,<K> */
 			EMIT6_IMM(0xc05d0000, K);
@@ -430,55 +423,55 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 			/* o %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5650d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */
-	case BPF_S_ALU_XOR_X:
+	case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */
+	case BPF_ALU | BPF_XOR | BPF_X:
 		jit->seen |= SEEN_XREG;
 		/* xr %r5,%r12 */
 		EMIT2(0x175c);
 		break;
-	case BPF_S_ALU_XOR_K: /* A ^= K */
+	case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */
 		if (!K)
 			break;
 		/* x %r5,<d(K)>(%r13) */
 		EMIT4_DISP(0x5750d000, EMIT_CONST(K));
 		break;
-	case BPF_S_ALU_LSH_X: /* A <<= X; */
+	case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */
 		jit->seen |= SEEN_XREG;
 		/* sll %r5,0(%r12) */
 		EMIT4(0x8950c000);
 		break;
-	case BPF_S_ALU_LSH_K: /* A <<= K */
+	case BPF_ALU | BPF_LSH | BPF_K: /* A <<= K */
 		if (K == 0)
 			break;
 		/* sll %r5,K */
 		EMIT4_DISP(0x89500000, K);
 		break;
-	case BPF_S_ALU_RSH_X: /* A >>= X; */
+	case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */
 		jit->seen |= SEEN_XREG;
 		/* srl %r5,0(%r12) */
 		EMIT4(0x8850c000);
 		break;
-	case BPF_S_ALU_RSH_K: /* A >>= K; */
+	case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */
 		if (K == 0)
 			break;
 		/* srl %r5,K */
 		EMIT4_DISP(0x88500000, K);
 		break;
-	case BPF_S_ALU_NEG: /* A = -A */
+	case BPF_ALU | BPF_NEG: /* A = -A */
 		/* lnr %r5,%r5 */
 		EMIT2(0x1155);
 		break;
-	case BPF_S_JMP_JA: /* ip += K */
+	case BPF_JMP | BPF_JA: /* ip += K */
 		offset = addrs[i + K] + jit->start - jit->prg;
 		EMIT4_PCREL(0xa7f40000, offset);
 		break;
-	case BPF_S_JMP_JGT_K: /* ip += (A > K) ? jt : jf */
+	case BPF_JMP | BPF_JGT | BPF_K: /* ip += (A > K) ? jt : jf */
 		mask = 0x200000; /* jh */
 		goto kbranch;
-	case BPF_S_JMP_JGE_K: /* ip += (A >= K) ? jt : jf */
+	case BPF_JMP | BPF_JGE | BPF_K: /* ip += (A >= K) ? jt : jf */
 		mask = 0xa00000; /* jhe */
 		goto kbranch;
-	case BPF_S_JMP_JEQ_K: /* ip += (A == K) ? jt : jf */
+	case BPF_JMP | BPF_JEQ | BPF_K: /* ip += (A == K) ? jt : jf */
 		mask = 0x800000; /* je */
 kbranch:	/* Emit compare if the branch targets are different */
 		if (filter->jt != filter->jf) {
@@ -511,7 +504,7 @@ branch:		if (filter->jt == filter->jf) {
 			EMIT4_PCREL(0xa7040000 | (mask ^ 0xf00000), offset);
 		}
 		break;
-	case BPF_S_JMP_JSET_K: /* ip += (A & K) ? jt : jf */
+	case BPF_JMP | BPF_JSET | BPF_K: /* ip += (A & K) ? jt : jf */
 		mask = 0x700000; /* jnz */
 		/* Emit test if the branch targets are different */
 		if (filter->jt != filter->jf) {
@@ -525,13 +518,13 @@ branch:		if (filter->jt == filter->jf) {
 				EMIT4_IMM(0xa7510000, K);
 		}
 		goto branch;
-	case BPF_S_JMP_JGT_X: /* ip += (A > X) ? jt : jf */
+	case BPF_JMP | BPF_JGT | BPF_X: /* ip += (A > X) ? jt : jf */
 		mask = 0x200000; /* jh */
 		goto xbranch;
-	case BPF_S_JMP_JGE_X: /* ip += (A >= X) ? jt : jf */
+	case BPF_JMP | BPF_JGE | BPF_X: /* ip += (A >= X) ? jt : jf */
 		mask = 0xa00000; /* jhe */
 		goto xbranch;
-	case BPF_S_JMP_JEQ_X: /* ip += (A == X) ? jt : jf */
+	case BPF_JMP | BPF_JEQ | BPF_X: /* ip += (A == X) ? jt : jf */
 		mask = 0x800000; /* je */
 xbranch:	/* Emit compare if the branch targets are different */
 		if (filter->jt != filter->jf) {
@@ -540,7 +533,7 @@ xbranch:	/* Emit compare if the branch targets are different */
 			EMIT2(0x195c);
 		}
 		goto branch;
-	case BPF_S_JMP_JSET_X: /* ip += (A & X) ? jt : jf */
+	case BPF_JMP | BPF_JSET | BPF_X: /* ip += (A & X) ? jt : jf */
 		mask = 0x700000; /* jnz */
 		/* Emit test if the branch targets are different */
 		if (filter->jt != filter->jf) {
@@ -551,15 +544,15 @@ xbranch:	/* Emit compare if the branch targets are different */
 			EMIT2(0x144c);
 		}
 		goto branch;
-	case BPF_S_LD_W_ABS: /* A = *(u32 *) (skb->data+K) */
+	case BPF_LD | BPF_W | BPF_ABS: /* A = *(u32 *) (skb->data+K) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_WORD;
 		offset = jit->off_load_word;
 		goto load_abs;
-	case BPF_S_LD_H_ABS: /* A = *(u16 *) (skb->data+K) */
+	case BPF_LD | BPF_H | BPF_ABS: /* A = *(u16 *) (skb->data+K) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_HALF;
 		offset = jit->off_load_half;
 		goto load_abs;
-	case BPF_S_LD_B_ABS: /* A = *(u8 *) (skb->data+K) */
+	case BPF_LD | BPF_B | BPF_ABS: /* A = *(u8 *) (skb->data+K) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_BYTE;
 		offset = jit->off_load_byte;
 load_abs:	if ((int) K < 0)
@@ -573,19 +566,19 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		/* jnz <ret0> */
 		EMIT4_PCREL(0xa7740000, (jit->ret0_ip - jit->prg));
 		break;
-	case BPF_S_LD_W_IND: /* A = *(u32 *) (skb->data+K+X) */
+	case BPF_LD | BPF_W | BPF_IND: /* A = *(u32 *) (skb->data+K+X) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IWORD;
 		offset = jit->off_load_iword;
 		goto call_fn;
-	case BPF_S_LD_H_IND: /* A = *(u16 *) (skb->data+K+X) */
+	case BPF_LD | BPF_H | BPF_IND: /* A = *(u16 *) (skb->data+K+X) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IHALF;
 		offset = jit->off_load_ihalf;
 		goto call_fn;
-	case BPF_S_LD_B_IND: /* A = *(u8 *) (skb->data+K+X) */
+	case BPF_LD | BPF_B | BPF_IND: /* A = *(u8 *) (skb->data+K+X) */
 		jit->seen |= SEEN_DATAREF | SEEN_RET0 | SEEN_LOAD_IBYTE;
 		offset = jit->off_load_ibyte;
 		goto call_fn;
-	case BPF_S_LDX_B_MSH:
+	case BPF_LDX | BPF_B | BPF_MSH:
 		/* X = (*(u8 *)(skb->data+K) & 0xf) << 2 */
 		jit->seen |= SEEN_RET0;
 		if ((int) K < 0) {
@@ -596,17 +589,17 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		jit->seen |= SEEN_DATAREF | SEEN_LOAD_BMSH;
 		offset = jit->off_load_bmsh;
 		goto call_fn;
-	case BPF_S_LD_W_LEN: /*	A = skb->len; */
+	case BPF_LD | BPF_W | BPF_LEN: /*	A = skb->len; */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
 		/* l %r5,<d(len)>(%r2) */
 		EMIT4_DISP(0x58502000, offsetof(struct sk_buff, len));
 		break;
-	case BPF_S_LDX_W_LEN: /* X = skb->len; */
+	case BPF_LDX | BPF_W | BPF_LEN: /* X = skb->len; */
 		jit->seen |= SEEN_XREG;
 		/* l %r12,<d(len)>(%r2) */
 		EMIT4_DISP(0x58c02000, offsetof(struct sk_buff, len));
 		break;
-	case BPF_S_LD_IMM: /* A = K */
+	case BPF_LD | BPF_IMM: /* A = K */
 		if (K <= 16383)
 			/* lhi %r5,K */
 			EMIT4_IMM(0xa7580000, K);
@@ -617,7 +610,7 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 			/* l %r5,<d(K)>(%r13) */
 			EMIT4_DISP(0x5850d000, EMIT_CONST(K));
 		break;
-	case BPF_S_LDX_IMM: /* X = K */
+	case BPF_LDX | BPF_IMM: /* X = K */
 		jit->seen |= SEEN_XREG;
 		if (K <= 16383)
 			/* lhi %r12,<K> */
@@ -629,29 +622,29 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 			/* l %r12,<d(K)>(%r13) */
 			EMIT4_DISP(0x58c0d000, EMIT_CONST(K));
 		break;
-	case BPF_S_LD_MEM: /* A = mem[K] */
+	case BPF_LD | BPF_MEM: /* A = mem[K] */
 		jit->seen |= SEEN_MEM;
 		/* l %r5,<K>(%r15) */
 		EMIT4_DISP(0x5850f000,
 			   (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4);
 		break;
-	case BPF_S_LDX_MEM: /* X = mem[K] */
+	case BPF_LDX | BPF_MEM: /* X = mem[K] */
 		jit->seen |= SEEN_XREG | SEEN_MEM;
 		/* l %r12,<K>(%r15) */
 		EMIT4_DISP(0x58c0f000,
 			   (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4);
 		break;
-	case BPF_S_MISC_TAX: /* X = A */
+	case BPF_MISC | BPF_TAX: /* X = A */
 		jit->seen |= SEEN_XREG;
 		/* lr %r12,%r5 */
 		EMIT2(0x18c5);
 		break;
-	case BPF_S_MISC_TXA: /* A = X */
+	case BPF_MISC | BPF_TXA: /* A = X */
 		jit->seen |= SEEN_XREG;
 		/* lr %r5,%r12 */
 		EMIT2(0x185c);
 		break;
-	case BPF_S_RET_K:
+	case BPF_RET | BPF_K:
 		if (K == 0) {
 			jit->seen |= SEEN_RET0;
 			if (last)
@@ -671,33 +664,33 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 			EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg);
 		}
 		break;
-	case BPF_S_RET_A:
+	case BPF_RET | BPF_A:
 		/* llgfr %r2,%r5 */
 		EMIT4(0xb9160025);
 		/* j <exit> */
 		EMIT4_PCREL(0xa7f40000, jit->exit_ip - jit->prg);
 		break;
-	case BPF_S_ST: /* mem[K] = A */
+	case BPF_ST: /* mem[K] = A */
 		jit->seen |= SEEN_MEM;
 		/* st %r5,<K>(%r15) */
 		EMIT4_DISP(0x5050f000,
 			   (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4);
 		break;
-	case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */
+	case BPF_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */
 		jit->seen |= SEEN_XREG | SEEN_MEM;
 		/* st %r12,<K>(%r15) */
 		EMIT4_DISP(0x50c0f000,
 			   (jit->seen & SEEN_DATAREF) ? 160 + K*4 : K*4);
 		break;
-	case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */
+	case BPF_ANC | SKF_AD_PROTOCOL: /* A = ntohs(skb->protocol); */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
 		/* lhi %r5,0 */
 		EMIT4(0xa7580000);
 		/* icm	%r5,3,<d(protocol)>(%r2) */
 		EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, protocol));
 		break;
-	case BPF_S_ANC_IFINDEX:	/* if (!skb->dev) return 0;
-				 * A = skb->dev->ifindex */
+	case BPF_ANC | SKF_AD_IFINDEX:	/* if (!skb->dev) return 0;
+					 * A = skb->dev->ifindex */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
 		jit->seen |= SEEN_RET0;
 		/* lg %r1,<d(dev)>(%r2) */
@@ -709,20 +702,20 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		/* l %r5,<d(ifindex)>(%r1) */
 		EMIT4_DISP(0x58501000, offsetof(struct net_device, ifindex));
 		break;
-	case BPF_S_ANC_MARK: /* A = skb->mark */
+	case BPF_ANC | SKF_AD_MARK: /* A = skb->mark */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
 		/* l %r5,<d(mark)>(%r2) */
 		EMIT4_DISP(0x58502000, offsetof(struct sk_buff, mark));
 		break;
-	case BPF_S_ANC_QUEUE: /* A = skb->queue_mapping */
+	case BPF_ANC | SKF_AD_QUEUE: /* A = skb->queue_mapping */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
 		/* lhi %r5,0 */
 		EMIT4(0xa7580000);
 		/* icm	%r5,3,<d(queue_mapping)>(%r2) */
 		EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, queue_mapping));
 		break;
-	case BPF_S_ANC_HATYPE:	/* if (!skb->dev) return 0;
-				 * A = skb->dev->type */
+	case BPF_ANC | SKF_AD_HATYPE:	/* if (!skb->dev) return 0;
+					 * A = skb->dev->type */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2);
 		jit->seen |= SEEN_RET0;
 		/* lg %r1,<d(dev)>(%r2) */
@@ -736,20 +729,20 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		/* icm	%r5,3,<d(type)>(%r1) */
 		EMIT4_DISP(0xbf531000, offsetof(struct net_device, type));
 		break;
-	case BPF_S_ANC_RXHASH: /* A = skb->hash */
+	case BPF_ANC | SKF_AD_RXHASH: /* A = skb->hash */
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
 		/* l %r5,<d(hash)>(%r2) */
 		EMIT4_DISP(0x58502000, offsetof(struct sk_buff, hash));
 		break;
-	case BPF_S_ANC_VLAN_TAG:
-	case BPF_S_ANC_VLAN_TAG_PRESENT:
+	case BPF_ANC | SKF_AD_VLAN_TAG:
+	case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
 		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
 		/* lhi %r5,0 */
 		EMIT4(0xa7580000);
 		/* icm	%r5,3,<d(vlan_tci)>(%r2) */
 		EMIT4_DISP(0xbf532000, offsetof(struct sk_buff, vlan_tci));
-		if (filter->code == BPF_S_ANC_VLAN_TAG) {
+		if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
 			/* nill %r5,0xefff */
 			EMIT4_IMM(0xa5570000, ~VLAN_TAG_PRESENT);
 		} else {
@@ -759,7 +752,7 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 			EMIT4_DISP(0x88500000, 12);
 		}
 		break;
-	case BPF_S_ANC_PKTTYPE:
+	case BPF_ANC | SKF_AD_PKTTYPE:
 		if (pkt_type_offset < 0)
 			goto out;
 		/* lhi %r5,0 */
@@ -769,7 +762,7 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		/* srl %r5,5 */
 		EMIT4_DISP(0x88500000, 5);
 		break;
-	case BPF_S_ANC_CPU: /* A = smp_processor_id() */
+	case BPF_ANC | SKF_AD_CPU: /* A = smp_processor_id() */
 #ifdef CONFIG_SMP
 		/* l %r5,<d(cpu_nr)> */
 		EMIT4_DISP(0x58500000, offsetof(struct _lowcore, cpu_nr));
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 9ddc51eeb8d..30de42730b2 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -48,13 +48,10 @@
 static LIST_HEAD(zpci_list);
 static DEFINE_SPINLOCK(zpci_list_lock);
 
-static void zpci_enable_irq(struct irq_data *data);
-static void zpci_disable_irq(struct irq_data *data);
-
 static struct irq_chip zpci_irq_chip = {
 	.name = "zPCI",
-	.irq_unmask = zpci_enable_irq,
-	.irq_mask = zpci_disable_irq,
+	.irq_unmask = unmask_msi_irq,
+	.irq_mask = mask_msi_irq,
 };
 
 static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
@@ -244,43 +241,6 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 	return rc;
 }
 
-static int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag)
-{
-	int offset, pos;
-	u32 mask_bits;
-
-	if (msi->msi_attrib.is_msix) {
-		offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
-			PCI_MSIX_ENTRY_VECTOR_CTRL;
-		msi->masked = readl(msi->mask_base + offset);
-		writel(flag, msi->mask_base + offset);
-	} else if (msi->msi_attrib.maskbit) {
-		pos = (long) msi->mask_base;
-		pci_read_config_dword(msi->dev, pos, &mask_bits);
-		mask_bits &= ~(mask);
-		mask_bits |= flag & mask;
-		pci_write_config_dword(msi->dev, pos, mask_bits);
-	} else
-		return 0;
-
-	msi->msi_attrib.maskbit = !!flag;
-	return 1;
-}
-
-static void zpci_enable_irq(struct irq_data *data)
-{
-	struct msi_desc *msi = irq_get_msi_desc(data->irq);
-
-	zpci_msi_set_mask_bits(msi, 1, 0);
-}
-
-static void zpci_disable_irq(struct irq_data *data)
-{
-	struct msi_desc *msi = irq_get_msi_desc(data->irq);
-
-	zpci_msi_set_mask_bits(msi, 1, 1);
-}
-
 void pcibios_fixup_bus(struct pci_bus *bus)
 {
 }
@@ -487,7 +447,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
 
 	/* Release MSI interrupts */
 	list_for_each_entry(msi, &pdev->msi_list, list) {
-		zpci_msi_set_mask_bits(msi, 1, 1);
+		if (msi->msi_attrib.is_msix)
+			default_msix_mask_irq(msi, 1);
+		else
+			default_msi_mask_irq(msi, 1, 1);
 		irq_set_msi_desc(msi->irq, NULL);
 		irq_free_desc(msi->irq);
 		msi->msg.address_lo = 0;
diff --git a/arch/score/include/asm/processor.h b/arch/score/include/asm/processor.h
index d9a922d8711..851f441991d 100644
--- a/arch/score/include/asm/processor.h
+++ b/arch/score/include/asm/processor.h
@@ -24,6 +24,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define current_text_addr() ({ __label__ _l; _l: &&_l; })
 
 #define cpu_relax()		barrier()
+#define cpu_relax_lowlatency()        cpu_relax()
 #define release_thread(thread)	do {} while (0)
 
 /*
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 834b67c4db5..aa2df3eaeb2 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -57,7 +57,6 @@ config SUPERH32
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_FUNCTION_GRAPH_TRACER
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index d4d16e4be07..bf5b3f5f496 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -32,7 +32,8 @@ endif
 
 cflags-$(CONFIG_CPU_SH2)		:= $(call cc-option,-m2,)
 cflags-$(CONFIG_CPU_SH2A)		+= $(call cc-option,-m2a,) \
-					   $(call cc-option,-m2a-nofpu,)
+					   $(call cc-option,-m2a-nofpu,) \
+					   $(call cc-option,-m4-nofpu,)
 cflags-$(CONFIG_CPU_SH3)		:= $(call cc-option,-m3,)
 cflags-$(CONFIG_CPU_SH4)		:= $(call cc-option,-m4,) \
 	$(call cc-option,-mno-implicit-fp,-m4-nofpu)
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index 5448f9bbf4a..1506897648a 100644
--- a/arch/sh/include/asm/processor.h
+++ b/arch/sh/include/asm/processor.h
@@ -97,6 +97,7 @@ extern struct sh_cpuinfo cpu_data[];
 
 #define cpu_sleep()	__asm__ __volatile__ ("sleep" : : : "memory")
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 void default_idle(void);
 void stop_this_cpu(void *);
diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index 3c74f53db6d..079d70e6d74 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -344,6 +344,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 	struct ftrace_graph_ent trace;
 	unsigned long return_hooker = (unsigned long)&return_to_handler;
 
+	if (unlikely(ftrace_graph_is_dead()))
+		return;
+
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 02331672b6d..7cfd7f15396 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -129,14 +129,6 @@ static int __hw_perf_event_init(struct perf_event *event)
 		return -ENODEV;
 
 	/*
-	 * All of the on-chip counters are "limited", in that they have
-	 * no interrupts, and are therefore unable to do sampling without
-	 * further work and timer assistance.
-	 */
-	if (hwc->sample_period)
-		return -EINVAL;
-
-	/*
 	 * See if we need to reserve the counter.
 	 *
 	 * If no events are currently in use, then we have to take a
@@ -392,6 +384,13 @@ int register_sh_pmu(struct sh_pmu *_pmu)
 
 	pr_info("Performance Events: %s support registered\n", _pmu->name);
 
+	/*
+	 * All of the on-chip counters are "limited", in that they have
+	 * no interrupts, and are therefore unable to do sampling without
+	 * further work and timer assistance.
+	 */
+	pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 	WARN_ON(_pmu->num_events > MAX_HWEVENTS);
 
 	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
diff --git a/arch/sh/lib/mcount.S b/arch/sh/lib/mcount.S
index 52aa2011d75..7a8572f9d58 100644
--- a/arch/sh/lib/mcount.S
+++ b/arch/sh/lib/mcount.S
@@ -92,13 +92,6 @@ mcount:
 	rts
 	 nop
 #else
-#ifndef CONFIG_DYNAMIC_FTRACE
-	mov.l	.Lfunction_trace_stop, r0
-	mov.l	@r0, r0
-	tst	r0, r0
-	bf	ftrace_stub
-#endif
-
 	MCOUNT_ENTER()
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -174,11 +167,6 @@ ftrace_graph_call:
 
 	.globl ftrace_caller
 ftrace_caller:
-	mov.l	.Lfunction_trace_stop, r0
-	mov.l	@r0, r0
-	tst	r0, r0
-	bf	ftrace_stub
-
 	MCOUNT_ENTER()
 
 	.globl ftrace_call
@@ -196,8 +184,6 @@ ftrace_call:
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 	.align 2
-.Lfunction_trace_stop:
-	.long	function_trace_stop
 
 /*
  * NOTE: From here on the locations of the .Lftrace_stub label and
@@ -217,12 +203,7 @@ ftrace_stub:
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	.globl	ftrace_graph_caller
 ftrace_graph_caller:
-	mov.l	2f, r0
-	mov.l	@r0, r0
-	tst	r0, r0
-	bt	1f
-
-	mov.l	3f, r1
+	mov.l	2f, r1
 	jmp	@r1
 	 nop
 1:
@@ -242,8 +223,7 @@ ftrace_graph_caller:
 	MCOUNT_LEAVE()
 
 	.align 2
-2:	.long	function_trace_stop
-3:	.long	skip_trace
+2:	.long	skip_trace
 .Lprepare_ftrace_return:
 	.long	prepare_ftrace_return
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 29f2e988c56..4692c90936f 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -55,7 +55,6 @@ config SPARC64
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_FP_TEST
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_RCU_TABLE_FREE if SMP
@@ -78,6 +77,7 @@ config SPARC64
 	select HAVE_C_RECORDMCOUNT
 	select NO_BOOTMEM
 	select HAVE_ARCH_AUDITSYSCALL
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/sparc/crypto/aes_glue.c b/arch/sparc/crypto/aes_glue.c
index 503e6d96ad4..df922f52d76 100644
--- a/arch/sparc/crypto/aes_glue.c
+++ b/arch/sparc/crypto/aes_glue.c
@@ -124,7 +124,7 @@ extern void aes_sparc64_ctr_crypt_256(const u64 *key, const u64 *input,
 				      u64 *output, unsigned int len,
 				      u64 *iv);
 
-struct aes_ops aes128_ops = {
+static struct aes_ops aes128_ops = {
 	.encrypt		= aes_sparc64_encrypt_128,
 	.decrypt		= aes_sparc64_decrypt_128,
 	.load_encrypt_keys	= aes_sparc64_load_encrypt_keys_128,
@@ -136,7 +136,7 @@ struct aes_ops aes128_ops = {
 	.ctr_crypt		= aes_sparc64_ctr_crypt_128,
 };
 
-struct aes_ops aes192_ops = {
+static struct aes_ops aes192_ops = {
 	.encrypt		= aes_sparc64_encrypt_192,
 	.decrypt		= aes_sparc64_decrypt_192,
 	.load_encrypt_keys	= aes_sparc64_load_encrypt_keys_192,
@@ -148,7 +148,7 @@ struct aes_ops aes192_ops = {
 	.ctr_crypt		= aes_sparc64_ctr_crypt_192,
 };
 
-struct aes_ops aes256_ops = {
+static struct aes_ops aes256_ops = {
 	.encrypt		= aes_sparc64_encrypt_256,
 	.decrypt		= aes_sparc64_decrypt_256,
 	.load_encrypt_keys	= aes_sparc64_load_encrypt_keys_256,
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index f08fe51b264..7aed2be45b4 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -20,11 +20,11 @@
 
 #define ATOMIC_INIT(i)  { (i) }
 
-extern int __atomic_add_return(int, atomic_t *);
-extern int atomic_cmpxchg(atomic_t *, int, int);
+int __atomic_add_return(int, atomic_t *);
+int atomic_cmpxchg(atomic_t *, int, int);
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-extern int __atomic_add_unless(atomic_t *, int, int);
-extern void atomic_set(atomic_t *, int);
+int __atomic_add_unless(atomic_t *, int, int);
+void atomic_set(atomic_t *, int);
 
 #define atomic_read(v)          (*(volatile int *)&(v)->counter)
 
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 8b2f1bde288..bb894c8bec5 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -20,15 +20,15 @@
 #define atomic_set(v, i)	(((v)->counter) = i)
 #define atomic64_set(v, i)	(((v)->counter) = i)
 
-extern void atomic_add(int, atomic_t *);
-extern void atomic64_add(long, atomic64_t *);
-extern void atomic_sub(int, atomic_t *);
-extern void atomic64_sub(long, atomic64_t *);
+void atomic_add(int, atomic_t *);
+void atomic64_add(long, atomic64_t *);
+void atomic_sub(int, atomic_t *);
+void atomic64_sub(long, atomic64_t *);
 
-extern int atomic_add_ret(int, atomic_t *);
-extern long atomic64_add_ret(long, atomic64_t *);
-extern int atomic_sub_ret(int, atomic_t *);
-extern long atomic64_sub_ret(long, atomic64_t *);
+int atomic_add_ret(int, atomic_t *);
+long atomic64_add_ret(long, atomic64_t *);
+int atomic_sub_ret(int, atomic_t *);
+long atomic64_sub_ret(long, atomic64_t *);
 
 #define atomic_dec_return(v) atomic_sub_ret(1, v)
 #define atomic64_dec_return(v) atomic64_sub_ret(1, v)
@@ -107,6 +107,6 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 
 #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
 
-extern long atomic64_dec_if_positive(atomic64_t *v);
+long atomic64_dec_if_positive(atomic64_t *v);
 
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/sparc/include/asm/auxio.h b/arch/sparc/include/asm/auxio.h
index 13dc67f0301..3e09a07b77e 100644
--- a/arch/sparc/include/asm/auxio.h
+++ b/arch/sparc/include/asm/auxio.h
@@ -1,5 +1,12 @@
 #ifndef ___ASM_SPARC_AUXIO_H
 #define ___ASM_SPARC_AUXIO_H
+
+#ifndef __ASSEMBLY__
+
+extern void __iomem *auxio_register;
+
+#endif /* ifndef __ASSEMBLY__ */
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/auxio_64.h>
 #else
diff --git a/arch/sparc/include/asm/auxio_32.h b/arch/sparc/include/asm/auxio_32.h
index 3a319775ae3..5d685df427b 100644
--- a/arch/sparc/include/asm/auxio_32.h
+++ b/arch/sparc/include/asm/auxio_32.h
@@ -34,8 +34,8 @@
  * NOTE: these routines are implementation dependent--
  * understand the hardware you are querying!
  */
-extern void set_auxio(unsigned char bits_on, unsigned char bits_off);
-extern unsigned char get_auxio(void); /* .../asm/floppy.h */
+void set_auxio(unsigned char bits_on, unsigned char bits_off);
+unsigned char get_auxio(void); /* .../asm/floppy.h */
 
 /*
  * The following routines are provided for driver-compatibility
@@ -78,7 +78,7 @@ do { \
 
 
 /* AUXIO2 (Power Off Control) */
-extern __volatile__ unsigned char * auxio_power_register;
+extern volatile u8 __iomem *auxio_power_register;
 
 #define	AUXIO_POWER_DETECT_FAILURE	32
 #define	AUXIO_POWER_CLEAR_FAILURE	2
diff --git a/arch/sparc/include/asm/auxio_64.h b/arch/sparc/include/asm/auxio_64.h
index f61cd1e3e39..6079e59a7ad 100644
--- a/arch/sparc/include/asm/auxio_64.h
+++ b/arch/sparc/include/asm/auxio_64.h
@@ -75,8 +75,6 @@
 
 #ifndef __ASSEMBLY__
 
-extern void __iomem *auxio_register;
-
 #define AUXIO_LTE_ON	1
 #define AUXIO_LTE_OFF	0
 
@@ -84,7 +82,7 @@ extern void __iomem *auxio_register;
  *
  * on - AUXIO_LTE_ON or AUXIO_LTE_OFF
  */
-extern void auxio_set_lte(int on);
+void auxio_set_lte(int on);
 
 #define AUXIO_LED_ON	1
 #define AUXIO_LED_OFF	0
@@ -93,7 +91,7 @@ extern void auxio_set_lte(int on);
  *
  * on - AUXIO_LED_ON or AUXIO_LED_OFF
  */
-extern void auxio_set_led(int on);
+void auxio_set_led(int on);
 
 #endif /* ifndef __ASSEMBLY__ */
 
diff --git a/arch/sparc/include/asm/bitext.h b/arch/sparc/include/asm/bitext.h
index 297b2f2fcb4..9c988bf3adb 100644
--- a/arch/sparc/include/asm/bitext.h
+++ b/arch/sparc/include/asm/bitext.h
@@ -20,8 +20,8 @@ struct bit_map {
 	int num_colors;
 };
 
-extern int bit_map_string_get(struct bit_map *t, int len, int align);
-extern void bit_map_clear(struct bit_map *t, int offset, int len);
-extern void bit_map_init(struct bit_map *t, unsigned long *map, int size);
+int bit_map_string_get(struct bit_map *t, int len, int align);
+void bit_map_clear(struct bit_map *t, int offset, int len);
+void bit_map_init(struct bit_map *t, unsigned long *map, int size);
 
 #endif /* defined(_SPARC_BITEXT_H) */
diff --git a/arch/sparc/include/asm/bitops_32.h b/arch/sparc/include/asm/bitops_32.h
index 88c9a962502..600ed1d9c8c 100644
--- a/arch/sparc/include/asm/bitops_32.h
+++ b/arch/sparc/include/asm/bitops_32.h
@@ -18,9 +18,9 @@
 #error only <linux/bitops.h> can be included directly
 #endif
 
-extern unsigned long ___set_bit(unsigned long *addr, unsigned long mask);
-extern unsigned long ___clear_bit(unsigned long *addr, unsigned long mask);
-extern unsigned long ___change_bit(unsigned long *addr, unsigned long mask);
+unsigned long ___set_bit(unsigned long *addr, unsigned long mask);
+unsigned long ___clear_bit(unsigned long *addr, unsigned long mask);
+unsigned long ___change_bit(unsigned long *addr, unsigned long mask);
 
 /*
  * Set bit 'nr' in 32-bit quantity at address 'addr' where bit '0'
diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h
index f1a051ca301..2d522402a93 100644
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -15,12 +15,12 @@
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 
-extern int test_and_set_bit(unsigned long nr, volatile unsigned long *addr);
-extern int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr);
-extern int test_and_change_bit(unsigned long nr, volatile unsigned long *addr);
-extern void set_bit(unsigned long nr, volatile unsigned long *addr);
-extern void clear_bit(unsigned long nr, volatile unsigned long *addr);
-extern void change_bit(unsigned long nr, volatile unsigned long *addr);
+int test_and_set_bit(unsigned long nr, volatile unsigned long *addr);
+int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr);
+int test_and_change_bit(unsigned long nr, volatile unsigned long *addr);
+void set_bit(unsigned long nr, volatile unsigned long *addr);
+void clear_bit(unsigned long nr, volatile unsigned long *addr);
+void change_bit(unsigned long nr, volatile unsigned long *addr);
 
 #include <asm-generic/bitops/non-atomic.h>
 
@@ -30,8 +30,8 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr);
 
 #ifdef __KERNEL__
 
-extern int ffs(int x);
-extern unsigned long __ffs(unsigned long);
+int ffs(int x);
+unsigned long __ffs(unsigned long);
 
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/sched.h>
@@ -41,10 +41,10 @@ extern unsigned long __ffs(unsigned long);
  * of bits set) of a N-bit word
  */
 
-extern unsigned long __arch_hweight64(__u64 w);
-extern unsigned int __arch_hweight32(unsigned int w);
-extern unsigned int __arch_hweight16(unsigned int w);
-extern unsigned int __arch_hweight8(unsigned int w);
+unsigned long __arch_hweight64(__u64 w);
+unsigned int __arch_hweight32(unsigned int w);
+unsigned int __arch_hweight16(unsigned int w);
+unsigned int __arch_hweight8(unsigned int w);
 
 #include <asm-generic/bitops/const_hweight.h>
 #include <asm-generic/bitops/lock.h>
diff --git a/arch/sparc/include/asm/btext.h b/arch/sparc/include/asm/btext.h
index 9b2bc6b6ed0..75a32b109e1 100644
--- a/arch/sparc/include/asm/btext.h
+++ b/arch/sparc/include/asm/btext.h
@@ -1,6 +1,6 @@
 #ifndef _SPARC_BTEXT_H
 #define _SPARC_BTEXT_H
 
-extern int btext_find_display(void);
+int btext_find_display(void);
 
 #endif /* _SPARC_BTEXT_H */
diff --git a/arch/sparc/include/asm/bug.h b/arch/sparc/include/asm/bug.h
index 6bd9f43cb5a..eaa8f8d3812 100644
--- a/arch/sparc/include/asm/bug.h
+++ b/arch/sparc/include/asm/bug.h
@@ -5,7 +5,7 @@
 #include <linux/compiler.h>
 
 #ifdef CONFIG_DEBUG_BUGVERBOSE
-extern void do_BUG(const char *file, int line);
+void do_BUG(const char *file, int line);
 #define BUG() do {					\
 	do_BUG(__FILE__, __LINE__);			\
 	__builtin_trap();				\
@@ -20,6 +20,6 @@ extern void do_BUG(const char *file, int line);
 #include <asm-generic/bug.h>
 
 struct pt_regs;
-extern void die_if_kernel(char *str, struct pt_regs *regs) __attribute__ ((noreturn));
+void __noreturn die_if_kernel(char *str, struct pt_regs *regs);
 
 #endif
diff --git a/arch/sparc/include/asm/cacheflush_32.h b/arch/sparc/include/asm/cacheflush_32.h
index bb014c24f31..12164006181 100644
--- a/arch/sparc/include/asm/cacheflush_32.h
+++ b/arch/sparc/include/asm/cacheflush_32.h
@@ -36,7 +36,7 @@
 #define flush_page_for_dma(addr) \
 	sparc32_cachetlb_ops->page_for_dma(addr)
 
-extern void sparc_flush_page_to_ram(struct page *page);
+void sparc_flush_page_to_ram(struct page *page);
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 #define flush_dcache_page(page)			sparc_flush_page_to_ram(page)
@@ -51,8 +51,8 @@ extern void sparc_flush_page_to_ram(struct page *page);
  * way the windows are all clean for the next process and the stack
  * frames are up to date.
  */
-extern void flush_user_windows(void);
-extern void kill_user_windows(void);
-extern void flushw_all(void);
+void flush_user_windows(void);
+void kill_user_windows(void);
+void flushw_all(void);
 
 #endif /* _SPARC_CACHEFLUSH_H */
diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h
index 301736d9e7a..38965379e35 100644
--- a/arch/sparc/include/asm/cacheflush_64.h
+++ b/arch/sparc/include/asm/cacheflush_64.h
@@ -10,7 +10,7 @@
 /* Cache flush operations. */
 #define flushw_all()	__asm__ __volatile__("flushw")
 
-extern void __flushw_user(void);
+void __flushw_user(void);
 #define flushw_user() __flushw_user()
 
 #define flush_user_windows flushw_user
@@ -30,29 +30,29 @@ extern void __flushw_user(void);
  * use block commit stores (which invalidate icache lines) during
  * module load, so we need this.
  */
-extern void flush_icache_range(unsigned long start, unsigned long end);
-extern void __flush_icache_page(unsigned long);
+void flush_icache_range(unsigned long start, unsigned long end);
+void __flush_icache_page(unsigned long);
 
-extern void __flush_dcache_page(void *addr, int flush_icache);
-extern void flush_dcache_page_impl(struct page *page);
+void __flush_dcache_page(void *addr, int flush_icache);
+void flush_dcache_page_impl(struct page *page);
 #ifdef CONFIG_SMP
-extern void smp_flush_dcache_page_impl(struct page *page, int cpu);
-extern void flush_dcache_page_all(struct mm_struct *mm, struct page *page);
+void smp_flush_dcache_page_impl(struct page *page, int cpu);
+void flush_dcache_page_all(struct mm_struct *mm, struct page *page);
 #else
 #define smp_flush_dcache_page_impl(page,cpu) flush_dcache_page_impl(page)
 #define flush_dcache_page_all(mm,page) flush_dcache_page_impl(page)
 #endif
 
-extern void __flush_dcache_range(unsigned long start, unsigned long end);
+void __flush_dcache_range(unsigned long start, unsigned long end);
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
 
 #define flush_icache_page(vma, pg)	do { } while(0)
 #define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
 
-extern void flush_ptrace_access(struct vm_area_struct *, struct page *,
-				unsigned long uaddr, void *kaddr,
-				unsigned long len, int write);
+void flush_ptrace_access(struct vm_area_struct *, struct page *,
+			 unsigned long uaddr, void *kaddr,
+			 unsigned long len, int write);
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len)		\
 	do {								\
diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h
index bdbda1453aa..426b2389a1c 100644
--- a/arch/sparc/include/asm/checksum_32.h
+++ b/arch/sparc/include/asm/checksum_32.h
@@ -29,7 +29,7 @@
  *
  * it's best to have buff aligned on a 32-bit boundary
  */
-extern __wsum csum_partial(const void *buff, int len, __wsum sum);
+__wsum csum_partial(const void *buff, int len, __wsum sum);
 
 /* the same as csum_partial, but copies from fs:src while it
  * checksums
@@ -38,7 +38,7 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum);
  * better 64-bit) boundary
  */
 
-extern unsigned int __csum_partial_copy_sparc_generic (const unsigned char *, unsigned char *);
+unsigned int __csum_partial_copy_sparc_generic (const unsigned char *, unsigned char *);
 
 static inline __wsum
 csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
@@ -238,4 +238,16 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 	return csum_fold(csum_partial(buff, len, 0));
 }
 
+#define HAVE_ARCH_CSUM_ADD
+static inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+	__asm__ __volatile__(
+		"addcc   %0, %1, %0\n"
+		"addx    %0, %%g0, %0"
+		: "=r" (csum)
+		: "r" (addend), "0" (csum));
+
+	return csum;
+}
+
 #endif /* !(__SPARC_CHECKSUM_H) */
diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h
index 019b9615e43..b8779a6a591 100644
--- a/arch/sparc/include/asm/checksum_64.h
+++ b/arch/sparc/include/asm/checksum_64.h
@@ -29,7 +29,7 @@
  *
  * it's best to have buff aligned on a 32-bit boundary
  */
-extern __wsum csum_partial(const void * buff, int len, __wsum sum);
+__wsum csum_partial(const void * buff, int len, __wsum sum);
 
 /* the same as csum_partial, but copies from user space while it
  * checksums
@@ -37,12 +37,12 @@ extern __wsum csum_partial(const void * buff, int len, __wsum sum);
  * here even more important to align src and dst on a 32-bit (or even
  * better 64-bit) boundary
  */
-extern __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					      int len, __wsum sum);
+__wsum csum_partial_copy_nocheck(const void *src, void *dst,
+				 int len, __wsum sum);
 
-extern long __csum_partial_copy_from_user(const void __user *src,
-					  void *dst, int len,
-					  __wsum sum);
+long __csum_partial_copy_from_user(const void __user *src,
+				   void *dst, int len,
+				   __wsum sum);
 
 static inline __wsum
 csum_partial_copy_from_user(const void __user *src,
@@ -59,9 +59,9 @@ csum_partial_copy_from_user(const void __user *src,
  *	Copy and checksum to user
  */
 #define HAVE_CSUM_COPY_USER
-extern long __csum_partial_copy_to_user(const void *src,
-					void __user *dst, int len,
-					  __wsum sum);
+long __csum_partial_copy_to_user(const void *src,
+				 void __user *dst, int len,
+				 __wsum sum);
 
 static inline __wsum
 csum_and_copy_to_user(const void *src,
@@ -77,7 +77,7 @@ csum_and_copy_to_user(const void *src,
 /* ihl is always 5 or greater, almost always is 5, and iph is word aligned
  * the majority of the time.
  */
-extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
+__sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 
 /* Fold a partial checksum without adding pseudo headers. */
 static inline __sum16 csum_fold(__wsum sum)
@@ -96,9 +96,9 @@ static inline __sum16 csum_fold(__wsum sum)
 }
 
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					       unsigned int len,
-					       unsigned short proto,
-					       __wsum sum)
+					unsigned int len,
+					unsigned short proto,
+					__wsum sum)
 {
 	__asm__ __volatile__(
 "	addcc		%1, %0, %0\n"
@@ -116,9 +116,9 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  * returns a 16-bit checksum, already complemented
  */
 static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
+					unsigned short len,
+					unsigned short proto,
+					__wsum sum)
 {
 	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
 }
@@ -164,4 +164,16 @@ static inline __sum16 ip_compute_csum(const void *buff, int len)
 	return csum_fold(csum_partial(buff, len, 0));
 }
 
+#define HAVE_ARCH_CSUM_ADD
+static inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+	__asm__ __volatile__(
+		"addcc   %0, %1, %0\n"
+		"addx    %0, %%g0, %0"
+		: "=r" (csum)
+		: "r" (addend), "0" (csum));
+
+	return csum;
+}
+
 #endif /* !(__SPARC64_CHECKSUM_H) */
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index 1fae1a02e3c..32c29a133f9 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -20,7 +20,7 @@ static inline unsigned long xchg_u32(__volatile__ unsigned long *m, unsigned lon
 	return val;
 }
 
-extern void __xchg_called_with_bad_pointer(void);
+void __xchg_called_with_bad_pointer(void);
 
 static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int size)
 {
@@ -45,9 +45,9 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int
 #define __HAVE_ARCH_CMPXCHG	1
 
 /* bug catcher for when unsupported size is used - won't link */
-extern void __cmpxchg_called_with_bad_pointer(void);
+void __cmpxchg_called_with_bad_pointer(void);
 /* we only need to support cmpxchg of a u32 on sparc */
-extern unsigned long __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
+unsigned long __cmpxchg_u32(volatile u32 *m, u32 old, u32 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
index 4adefe8e288..0e1ed6cfbf6 100644
--- a/arch/sparc/include/asm/cmpxchg_64.h
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -42,7 +42,7 @@ static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long
 
 #define xchg(ptr,x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
 
-extern void __xchg_called_with_bad_pointer(void);
+void __xchg_called_with_bad_pointer(void);
 
 static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
 				       int size)
@@ -91,7 +91,7 @@ __cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new)
 
 /* This function doesn't exist, so you'll get a linker error
    if something tries to do an invalid cmpxchg().  */
-extern void __cmpxchg_called_with_bad_pointer(void);
+void __cmpxchg_called_with_bad_pointer(void);
 
 static inline unsigned long
 __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
diff --git a/arch/sparc/include/asm/cpudata.h b/arch/sparc/include/asm/cpudata.h
index b5976de7cac..128b56b0867 100644
--- a/arch/sparc/include/asm/cpudata.h
+++ b/arch/sparc/include/asm/cpudata.h
@@ -1,5 +1,15 @@
 #ifndef ___ASM_SPARC_CPUDATA_H
 #define ___ASM_SPARC_CPUDATA_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/threads.h>
+#include <linux/percpu.h>
+
+extern const struct seq_operations cpuinfo_op;
+
+#endif /* !(__ASSEMBLY__) */
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/cpudata_64.h>
 #else
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index 050ef35b9dc..0e594076912 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -8,9 +8,6 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/percpu.h>
-#include <linux/threads.h>
-
 typedef struct {
 	/* Dcache line 1 */
 	unsigned int	__softirq_pending; /* must be 1st, see rtrap.S */
@@ -35,8 +32,6 @@ DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
 #define cpu_data(__cpu)		per_cpu(__cpu_data, (__cpu))
 #define local_cpu_data()	__get_cpu_var(__cpu_data)
 
-extern const struct seq_operations cpuinfo_op;
-
 #endif /* !(__ASSEMBLY__) */
 
 #include <asm/trap_block.h>
diff --git a/arch/sparc/include/asm/delay_32.h b/arch/sparc/include/asm/delay_32.h
index bc9aba2bead..3fb8ca144b4 100644
--- a/arch/sparc/include/asm/delay_32.h
+++ b/arch/sparc/include/asm/delay_32.h
@@ -20,8 +20,8 @@ static inline void __delay(unsigned long loops)
 }
 
 /* This is too messy with inline asm on the Sparc. */
-extern void __udelay(unsigned long usecs, unsigned long lpj);
-extern void __ndelay(unsigned long nsecs, unsigned long lpj);
+void __udelay(unsigned long usecs, unsigned long lpj);
+void __ndelay(unsigned long nsecs, unsigned long lpj);
 
 #ifdef CONFIG_SMP
 #define __udelay_val	cpu_data(smp_processor_id()).udelay_val
diff --git a/arch/sparc/include/asm/delay_64.h b/arch/sparc/include/asm/delay_64.h
index a77aa622d76..0ba5424856d 100644
--- a/arch/sparc/include/asm/delay_64.h
+++ b/arch/sparc/include/asm/delay_64.h
@@ -8,8 +8,8 @@
 
 #ifndef __ASSEMBLY__
 
-extern void __delay(unsigned long loops);
-extern void udelay(unsigned long usecs);
+void __delay(unsigned long loops);
+void udelay(unsigned long usecs);
 #define mdelay(n)	udelay((n) * 1000)
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/sparc/include/asm/device.h b/arch/sparc/include/asm/device.h
index daa6a8a5e9c..bb3f0b0c675 100644
--- a/arch/sparc/include/asm/device.h
+++ b/arch/sparc/include/asm/device.h
@@ -19,7 +19,7 @@ struct dev_archdata {
 	int			numa_node;
 };
 
-extern void of_propagate_archdata(struct platform_device *bus);
+void of_propagate_archdata(struct platform_device *bus);
 
 struct pdev_archdata {
 	struct resource		resource[PROMREG_MAX];
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 05fe53f5346..1ee02710b2d 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -7,7 +7,7 @@
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
 
-extern int dma_supported(struct device *dev, u64 mask);
+int dma_supported(struct device *dev, u64 mask);
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
diff --git a/arch/sparc/include/asm/ebus_dma.h b/arch/sparc/include/asm/ebus_dma.h
index f07a5b541c9..fcfb4948147 100644
--- a/arch/sparc/include/asm/ebus_dma.h
+++ b/arch/sparc/include/asm/ebus_dma.h
@@ -22,14 +22,14 @@ struct ebus_dma_info {
 	unsigned char	name[64];
 };
 
-extern int ebus_dma_register(struct ebus_dma_info *p);
-extern int ebus_dma_irq_enable(struct ebus_dma_info *p, int on);
-extern void ebus_dma_unregister(struct ebus_dma_info *p);
-extern int ebus_dma_request(struct ebus_dma_info *p, dma_addr_t bus_addr,
+int ebus_dma_register(struct ebus_dma_info *p);
+int ebus_dma_irq_enable(struct ebus_dma_info *p, int on);
+void ebus_dma_unregister(struct ebus_dma_info *p);
+int ebus_dma_request(struct ebus_dma_info *p, dma_addr_t bus_addr,
 			    size_t len);
-extern void ebus_dma_prepare(struct ebus_dma_info *p, int write);
-extern unsigned int ebus_dma_residue(struct ebus_dma_info *p);
-extern unsigned int ebus_dma_addr(struct ebus_dma_info *p);
-extern void ebus_dma_enable(struct ebus_dma_info *p, int on);
+void ebus_dma_prepare(struct ebus_dma_info *p, int write);
+unsigned int ebus_dma_residue(struct ebus_dma_info *p);
+unsigned int ebus_dma_addr(struct ebus_dma_info *p);
+void ebus_dma_enable(struct ebus_dma_info *p, int on);
 
 #endif /* __ASM_SPARC_EBUS_DMA_H */
diff --git a/arch/sparc/include/asm/floppy_32.h b/arch/sparc/include/asm/floppy_32.h
index fb3f16954c6..071b83e52f1 100644
--- a/arch/sparc/include/asm/floppy_32.h
+++ b/arch/sparc/include/asm/floppy_32.h
@@ -9,11 +9,12 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 
-#include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/idprom.h>
 #include <asm/oplib.h>
 #include <asm/auxio.h>
+#include <asm/setup.h>
+#include <asm/page.h>
 #include <asm/irq.h>
 
 /* We don't need no stinkin' I/O port allocation crap. */
@@ -49,7 +50,6 @@ struct sun_flpy_controller {
 
 /* You'll only ever find one controller on a SparcStation anyways. */
 static struct sun_flpy_controller *sun_fdc = NULL;
-extern volatile unsigned char *fdc_status;
 
 struct sun_floppy_ops {
 	unsigned char (*fd_inb)(int port);
@@ -212,13 +212,6 @@ static void sun_82077_fd_outb(unsigned char value, int port)
  * underruns.  If non-zero, doing_pdma encodes the direction of
  * the transfer for debugging.  1=read 2=write
  */
-extern char *pdma_vaddr;
-extern unsigned long pdma_size;
-extern volatile int doing_pdma;
-
-/* This is software state */
-extern char *pdma_base;
-extern unsigned long pdma_areasize;
 
 /* Common routines to all controller types on the Sparc. */
 static inline void virtual_dma_init(void)
@@ -263,8 +256,7 @@ static inline void sun_fd_enable_dma(void)
 	pdma_areasize = pdma_size;
 }
 
-extern int sparc_floppy_request_irq(unsigned int irq,
-                                    irq_handler_t irq_handler);
+int sparc_floppy_request_irq(unsigned int irq, irq_handler_t irq_handler);
 
 static int sun_fd_request_irq(void)
 {
diff --git a/arch/sparc/include/asm/floppy_64.h b/arch/sparc/include/asm/floppy_64.h
index 7c90c50c200..625756406a7 100644
--- a/arch/sparc/include/asm/floppy_64.h
+++ b/arch/sparc/include/asm/floppy_64.h
@@ -296,7 +296,7 @@ struct sun_pci_dma_op {
 static struct sun_pci_dma_op sun_pci_dma_current = { -1U, 0, 0, NULL};
 static struct sun_pci_dma_op sun_pci_dma_pending = { -1U, 0, 0, NULL};
 
-extern irqreturn_t floppy_interrupt(int irq, void *dev_id);
+irqreturn_t floppy_interrupt(int irq, void *dev_id);
 
 static unsigned char sun_pci_fd_inb(unsigned long port)
 {
diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h
index b0f18e9893d..9ec94ad116f 100644
--- a/arch/sparc/include/asm/ftrace.h
+++ b/arch/sparc/include/asm/ftrace.h
@@ -6,7 +6,7 @@
 #define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
 
 #ifndef __ASSEMBLY__
-extern void _mcount(void);
+void _mcount(void);
 #endif
 
 #endif
@@ -22,4 +22,8 @@ struct dyn_arch_ftrace {
 };
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 
+unsigned long prepare_ftrace_return(unsigned long parent,
+				    unsigned long self_addr,
+				    unsigned long frame_pointer);
+
 #endif /* _ASM_SPARC64_FTRACE */
diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h
index 4f9e15c757e..92ded294a4e 100644
--- a/arch/sparc/include/asm/highmem.h
+++ b/arch/sparc/include/asm/highmem.h
@@ -31,7 +31,7 @@ extern unsigned long highstart_pfn, highend_pfn;
 extern pgprot_t kmap_prot;
 extern pte_t *pkmap_page_table;
 
-extern void kmap_init(void) __init;
+void kmap_init(void) __init;
 
 /*
  * Right now we initialize only a single pte table. It can be extended
@@ -49,8 +49,8 @@ extern void kmap_init(void) __init;
 
 #define PKMAP_END (PKMAP_ADDR(LAST_PKMAP))
 
-extern void *kmap_high(struct page *page);
-extern void kunmap_high(struct page *page);
+void *kmap_high(struct page *page);
+void kunmap_high(struct page *page);
 
 static inline void *kmap(struct page *page)
 {
@@ -68,8 +68,8 @@ static inline void kunmap(struct page *page)
 	kunmap_high(page);
 }
 
-extern void *kmap_atomic(struct page *page);
-extern void __kunmap_atomic(void *kvaddr);
+void *kmap_atomic(struct page *page);
+void __kunmap_atomic(void *kvaddr);
 
 #define flush_cache_kmaps()	flush_cache_all()
 
diff --git a/arch/sparc/include/asm/hvtramp.h b/arch/sparc/include/asm/hvtramp.h
index b2b9b947b3a..04b56f862bb 100644
--- a/arch/sparc/include/asm/hvtramp.h
+++ b/arch/sparc/include/asm/hvtramp.h
@@ -19,7 +19,7 @@ struct hvtramp_descr {
 	struct hvtramp_mapping	maps[1];
 };
 
-extern void hv_cpu_startup(unsigned long hvdescr_pa);
+void hv_cpu_startup(unsigned long hvdescr_pa);
 
 #endif
 
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index ca121f0fa3e..94b39caea3e 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -98,7 +98,7 @@
 #define HV_FAST_MACH_EXIT		0x00
 
 #ifndef __ASSEMBLY__
-extern void sun4v_mach_exit(unsigned long exit_code);
+void sun4v_mach_exit(unsigned long exit_code);
 #endif
 
 /* Domain services.  */
@@ -127,9 +127,9 @@ extern void sun4v_mach_exit(unsigned long exit_code);
 #define HV_FAST_MACH_DESC		0x01
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mach_desc(unsigned long buffer_pa,
-				     unsigned long buf_len,
-				     unsigned long *real_buf_len);
+unsigned long sun4v_mach_desc(unsigned long buffer_pa,
+			      unsigned long buf_len,
+			      unsigned long *real_buf_len);
 #endif
 
 /* mach_sir()
@@ -148,7 +148,7 @@ extern unsigned long sun4v_mach_desc(unsigned long buffer_pa,
 #define HV_FAST_MACH_SIR		0x02
 
 #ifndef __ASSEMBLY__
-extern void sun4v_mach_sir(void);
+void sun4v_mach_sir(void);
 #endif
 
 /* mach_set_watchdog()
@@ -204,8 +204,8 @@ extern void sun4v_mach_sir(void);
 #define HV_FAST_MACH_SET_WATCHDOG	0x05
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mach_set_watchdog(unsigned long timeout,
-					     unsigned long *orig_timeout);
+unsigned long sun4v_mach_set_watchdog(unsigned long timeout,
+				      unsigned long *orig_timeout);
 #endif
 
 /* CPU services.
@@ -250,10 +250,10 @@ extern unsigned long sun4v_mach_set_watchdog(unsigned long timeout,
 #define HV_FAST_CPU_START		0x10
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_start(unsigned long cpuid,
-				     unsigned long pc,
-				     unsigned long rtba,
-				     unsigned long arg0);
+unsigned long sun4v_cpu_start(unsigned long cpuid,
+			      unsigned long pc,
+			      unsigned long rtba,
+			      unsigned long arg0);
 #endif
 
 /* cpu_stop()
@@ -278,7 +278,7 @@ extern unsigned long sun4v_cpu_start(unsigned long cpuid,
 #define HV_FAST_CPU_STOP		0x11
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_stop(unsigned long cpuid);
+unsigned long sun4v_cpu_stop(unsigned long cpuid);
 #endif
 
 /* cpu_yield()
@@ -295,7 +295,7 @@ extern unsigned long sun4v_cpu_stop(unsigned long cpuid);
 #define HV_FAST_CPU_YIELD		0x12
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_yield(void);
+unsigned long sun4v_cpu_yield(void);
 #endif
 
 /* cpu_qconf()
@@ -341,9 +341,9 @@ extern unsigned long sun4v_cpu_yield(void);
 #define  HV_CPU_QUEUE_NONRES_ERROR	 0x3f
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_qconf(unsigned long type,
-				     unsigned long queue_paddr,
-				     unsigned long num_queue_entries);
+unsigned long sun4v_cpu_qconf(unsigned long type,
+			      unsigned long queue_paddr,
+			      unsigned long num_queue_entries);
 #endif
 
 /* cpu_qinfo()
@@ -394,7 +394,9 @@ extern unsigned long sun4v_cpu_qconf(unsigned long type,
 #define HV_FAST_CPU_MONDO_SEND		0x42
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_cpu_mondo_send(unsigned long cpu_count, unsigned long cpu_list_pa, unsigned long mondo_block_pa);
+unsigned long sun4v_cpu_mondo_send(unsigned long cpu_count,
+				   unsigned long cpu_list_pa,
+				   unsigned long mondo_block_pa);
 #endif
 
 /* cpu_myid()
@@ -425,7 +427,7 @@ extern unsigned long sun4v_cpu_mondo_send(unsigned long cpu_count, unsigned long
 #define  HV_CPU_STATE_ERROR		 0x03
 
 #ifndef __ASSEMBLY__
-extern long sun4v_cpu_state(unsigned long cpuid);
+long sun4v_cpu_state(unsigned long cpuid);
 #endif
 
 /* cpu_set_rtba()
@@ -625,8 +627,8 @@ struct hv_fault_status {
 #define HV_FAST_MMU_TSB_CTX0		0x20
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mmu_tsb_ctx0(unsigned long num_descriptions,
-					unsigned long tsb_desc_ra);
+unsigned long sun4v_mmu_tsb_ctx0(unsigned long num_descriptions,
+				 unsigned long tsb_desc_ra);
 #endif
 
 /* mmu_tsb_ctxnon0()
@@ -710,7 +712,7 @@ extern unsigned long sun4v_mmu_tsb_ctx0(unsigned long num_descriptions,
 #define HV_FAST_MMU_DEMAP_ALL		0x24
 
 #ifndef __ASSEMBLY__
-extern void sun4v_mmu_demap_all(void);
+void sun4v_mmu_demap_all(void);
 #endif
 
 /* mmu_map_perm_addr()
@@ -740,10 +742,10 @@ extern void sun4v_mmu_demap_all(void);
 #define HV_FAST_MMU_MAP_PERM_ADDR	0x25
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mmu_map_perm_addr(unsigned long vaddr,
-					     unsigned long set_to_zero,
-					     unsigned long tte,
-					     unsigned long flags);
+unsigned long sun4v_mmu_map_perm_addr(unsigned long vaddr,
+				      unsigned long set_to_zero,
+				      unsigned long tte,
+				      unsigned long flags);
 #endif
 
 /* mmu_fault_area_conf()
@@ -945,7 +947,7 @@ extern unsigned long sun4v_mmu_map_perm_addr(unsigned long vaddr,
 #define HV_FAST_TOD_GET			0x50
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_tod_get(unsigned long *time);
+unsigned long sun4v_tod_get(unsigned long *time);
 #endif
 
 /* tod_set()
@@ -962,7 +964,7 @@ extern unsigned long sun4v_tod_get(unsigned long *time);
 #define HV_FAST_TOD_SET			0x51
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_tod_set(unsigned long time);
+unsigned long sun4v_tod_set(unsigned long time);
 #endif
 
 /* Console services */
@@ -1038,14 +1040,14 @@ extern unsigned long sun4v_tod_set(unsigned long time);
 #define HV_FAST_CONS_WRITE		0x63
 
 #ifndef __ASSEMBLY__
-extern long sun4v_con_getchar(long *status);
-extern long sun4v_con_putchar(long c);
-extern long sun4v_con_read(unsigned long buffer,
-			   unsigned long size,
-			   unsigned long *bytes_read);
-extern unsigned long sun4v_con_write(unsigned long buffer,
-				     unsigned long size,
-				     unsigned long *bytes_written);
+long sun4v_con_getchar(long *status);
+long sun4v_con_putchar(long c);
+long sun4v_con_read(unsigned long buffer,
+		    unsigned long size,
+		    unsigned long *bytes_read);
+unsigned long sun4v_con_write(unsigned long buffer,
+			      unsigned long size,
+			      unsigned long *bytes_written);
 #endif
 
 /* mach_set_soft_state()
@@ -1080,8 +1082,8 @@ extern unsigned long sun4v_con_write(unsigned long buffer,
 #define  HV_SOFT_STATE_TRANSITION	 0x02
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mach_set_soft_state(unsigned long soft_state,
-					       unsigned long msg_string_ra);
+unsigned long sun4v_mach_set_soft_state(unsigned long soft_state,
+				        unsigned long msg_string_ra);
 #endif
 
 /* mach_get_soft_state()
@@ -1159,20 +1161,20 @@ extern unsigned long sun4v_mach_set_soft_state(unsigned long soft_state,
 #define HV_FAST_SVC_CLRSTATUS		0x84
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_svc_send(unsigned long svc_id,
-				    unsigned long buffer,
-				    unsigned long buffer_size,
-				    unsigned long *sent_bytes);
-extern unsigned long sun4v_svc_recv(unsigned long svc_id,
-				    unsigned long buffer,
-				    unsigned long buffer_size,
-				    unsigned long *recv_bytes);
-extern unsigned long sun4v_svc_getstatus(unsigned long svc_id,
-					 unsigned long *status_bits);
-extern unsigned long sun4v_svc_setstatus(unsigned long svc_id,
-					 unsigned long status_bits);
-extern unsigned long sun4v_svc_clrstatus(unsigned long svc_id,
-					 unsigned long status_bits);
+unsigned long sun4v_svc_send(unsigned long svc_id,
+			     unsigned long buffer,
+			     unsigned long buffer_size,
+			     unsigned long *sent_bytes);
+unsigned long sun4v_svc_recv(unsigned long svc_id,
+			     unsigned long buffer,
+			     unsigned long buffer_size,
+			     unsigned long *recv_bytes);
+unsigned long sun4v_svc_getstatus(unsigned long svc_id,
+				  unsigned long *status_bits);
+unsigned long sun4v_svc_setstatus(unsigned long svc_id,
+				  unsigned long status_bits);
+unsigned long sun4v_svc_clrstatus(unsigned long svc_id,
+				  unsigned long status_bits);
 #endif
 
 /* Trap trace services.
@@ -1458,8 +1460,8 @@ struct hv_trap_trace_entry {
 #define HV_FAST_INTR_DEVINO2SYSINO	0xa0
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_devino_to_sysino(unsigned long devhandle,
-					    unsigned long devino);
+unsigned long sun4v_devino_to_sysino(unsigned long devhandle,
+				     unsigned long devino);
 #endif
 
 /* intr_getenabled()
@@ -1476,7 +1478,7 @@ extern unsigned long sun4v_devino_to_sysino(unsigned long devhandle,
 #define HV_FAST_INTR_GETENABLED		0xa1
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_getenabled(unsigned long sysino);
+unsigned long sun4v_intr_getenabled(unsigned long sysino);
 #endif
 
 /* intr_setenabled()
@@ -1492,7 +1494,8 @@ extern unsigned long sun4v_intr_getenabled(unsigned long sysino);
 #define HV_FAST_INTR_SETENABLED		0xa2
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_setenabled(unsigned long sysino, unsigned long intr_enabled);
+unsigned long sun4v_intr_setenabled(unsigned long sysino,
+				    unsigned long intr_enabled);
 #endif
 
 /* intr_getstate()
@@ -1508,7 +1511,7 @@ extern unsigned long sun4v_intr_setenabled(unsigned long sysino, unsigned long i
 #define HV_FAST_INTR_GETSTATE		0xa3
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_getstate(unsigned long sysino);
+unsigned long sun4v_intr_getstate(unsigned long sysino);
 #endif
 
 /* intr_setstate()
@@ -1528,7 +1531,7 @@ extern unsigned long sun4v_intr_getstate(unsigned long sysino);
 #define HV_FAST_INTR_SETSTATE		0xa4
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_setstate(unsigned long sysino, unsigned long intr_state);
+unsigned long sun4v_intr_setstate(unsigned long sysino, unsigned long intr_state);
 #endif
 
 /* intr_gettarget()
@@ -1546,7 +1549,7 @@ extern unsigned long sun4v_intr_setstate(unsigned long sysino, unsigned long int
 #define HV_FAST_INTR_GETTARGET		0xa5
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_gettarget(unsigned long sysino);
+unsigned long sun4v_intr_gettarget(unsigned long sysino);
 #endif
 
 /* intr_settarget()
@@ -1563,7 +1566,7 @@ extern unsigned long sun4v_intr_gettarget(unsigned long sysino);
 #define HV_FAST_INTR_SETTARGET		0xa6
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_intr_settarget(unsigned long sysino, unsigned long cpuid);
+unsigned long sun4v_intr_settarget(unsigned long sysino, unsigned long cpuid);
 #endif
 
 /* vintr_get_cookie()
@@ -1647,30 +1650,30 @@ extern unsigned long sun4v_intr_settarget(unsigned long sysino, unsigned long cp
 #define HV_FAST_VINTR_SET_TARGET	0xae
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_vintr_get_cookie(unsigned long dev_handle,
-					    unsigned long dev_ino,
-					    unsigned long *cookie);
-extern unsigned long sun4v_vintr_set_cookie(unsigned long dev_handle,
-					    unsigned long dev_ino,
-					    unsigned long cookie);
-extern unsigned long sun4v_vintr_get_valid(unsigned long dev_handle,
-					   unsigned long dev_ino,
-					   unsigned long *valid);
-extern unsigned long sun4v_vintr_set_valid(unsigned long dev_handle,
-					   unsigned long dev_ino,
-					   unsigned long valid);
-extern unsigned long sun4v_vintr_get_state(unsigned long dev_handle,
-					   unsigned long dev_ino,
-					   unsigned long *state);
-extern unsigned long sun4v_vintr_set_state(unsigned long dev_handle,
-					   unsigned long dev_ino,
-					   unsigned long state);
-extern unsigned long sun4v_vintr_get_target(unsigned long dev_handle,
-					    unsigned long dev_ino,
-					    unsigned long *cpuid);
-extern unsigned long sun4v_vintr_set_target(unsigned long dev_handle,
-					    unsigned long dev_ino,
-					    unsigned long cpuid);
+unsigned long sun4v_vintr_get_cookie(unsigned long dev_handle,
+				     unsigned long dev_ino,
+				     unsigned long *cookie);
+unsigned long sun4v_vintr_set_cookie(unsigned long dev_handle,
+				     unsigned long dev_ino,
+				     unsigned long cookie);
+unsigned long sun4v_vintr_get_valid(unsigned long dev_handle,
+				    unsigned long dev_ino,
+				    unsigned long *valid);
+unsigned long sun4v_vintr_set_valid(unsigned long dev_handle,
+				    unsigned long dev_ino,
+				    unsigned long valid);
+unsigned long sun4v_vintr_get_state(unsigned long dev_handle,
+				    unsigned long dev_ino,
+				    unsigned long *state);
+unsigned long sun4v_vintr_set_state(unsigned long dev_handle,
+				    unsigned long dev_ino,
+				    unsigned long state);
+unsigned long sun4v_vintr_get_target(unsigned long dev_handle,
+				     unsigned long dev_ino,
+				     unsigned long *cpuid);
+unsigned long sun4v_vintr_set_target(unsigned long dev_handle,
+				     unsigned long dev_ino,
+				     unsigned long cpuid);
 #endif
 
 /* PCI IO services.
@@ -2627,50 +2630,50 @@ struct ldc_mtable_entry {
 #define HV_FAST_LDC_REVOKE		0xef
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_ldc_tx_qconf(unsigned long channel,
-					unsigned long ra,
-					unsigned long num_entries);
-extern unsigned long sun4v_ldc_tx_qinfo(unsigned long channel,
-					unsigned long *ra,
-					unsigned long *num_entries);
-extern unsigned long sun4v_ldc_tx_get_state(unsigned long channel,
-					    unsigned long *head_off,
-					    unsigned long *tail_off,
-					    unsigned long *chan_state);
-extern unsigned long sun4v_ldc_tx_set_qtail(unsigned long channel,
-					    unsigned long tail_off);
-extern unsigned long sun4v_ldc_rx_qconf(unsigned long channel,
-					unsigned long ra,
-					unsigned long num_entries);
-extern unsigned long sun4v_ldc_rx_qinfo(unsigned long channel,
-					unsigned long *ra,
-					unsigned long *num_entries);
-extern unsigned long sun4v_ldc_rx_get_state(unsigned long channel,
-					    unsigned long *head_off,
-					    unsigned long *tail_off,
-					    unsigned long *chan_state);
-extern unsigned long sun4v_ldc_rx_set_qhead(unsigned long channel,
-					    unsigned long head_off);
-extern unsigned long sun4v_ldc_set_map_table(unsigned long channel,
-					     unsigned long ra,
-					     unsigned long num_entries);
-extern unsigned long sun4v_ldc_get_map_table(unsigned long channel,
-					     unsigned long *ra,
-					     unsigned long *num_entries);
-extern unsigned long sun4v_ldc_copy(unsigned long channel,
-				    unsigned long dir_code,
-				    unsigned long tgt_raddr,
-				    unsigned long lcl_raddr,
-				    unsigned long len,
-				    unsigned long *actual_len);
-extern unsigned long sun4v_ldc_mapin(unsigned long channel,
-				     unsigned long cookie,
-				     unsigned long *ra,
-				     unsigned long *perm);
-extern unsigned long sun4v_ldc_unmap(unsigned long ra);
-extern unsigned long sun4v_ldc_revoke(unsigned long channel,
-				      unsigned long cookie,
-				      unsigned long mte_cookie);
+unsigned long sun4v_ldc_tx_qconf(unsigned long channel,
+				 unsigned long ra,
+				 unsigned long num_entries);
+unsigned long sun4v_ldc_tx_qinfo(unsigned long channel,
+				 unsigned long *ra,
+				 unsigned long *num_entries);
+unsigned long sun4v_ldc_tx_get_state(unsigned long channel,
+				     unsigned long *head_off,
+				     unsigned long *tail_off,
+				     unsigned long *chan_state);
+unsigned long sun4v_ldc_tx_set_qtail(unsigned long channel,
+				     unsigned long tail_off);
+unsigned long sun4v_ldc_rx_qconf(unsigned long channel,
+				 unsigned long ra,
+				 unsigned long num_entries);
+unsigned long sun4v_ldc_rx_qinfo(unsigned long channel,
+				 unsigned long *ra,
+				 unsigned long *num_entries);
+unsigned long sun4v_ldc_rx_get_state(unsigned long channel,
+				     unsigned long *head_off,
+				     unsigned long *tail_off,
+				     unsigned long *chan_state);
+unsigned long sun4v_ldc_rx_set_qhead(unsigned long channel,
+				     unsigned long head_off);
+unsigned long sun4v_ldc_set_map_table(unsigned long channel,
+				      unsigned long ra,
+				      unsigned long num_entries);
+unsigned long sun4v_ldc_get_map_table(unsigned long channel,
+				      unsigned long *ra,
+				      unsigned long *num_entries);
+unsigned long sun4v_ldc_copy(unsigned long channel,
+			     unsigned long dir_code,
+			     unsigned long tgt_raddr,
+			     unsigned long lcl_raddr,
+			     unsigned long len,
+			     unsigned long *actual_len);
+unsigned long sun4v_ldc_mapin(unsigned long channel,
+			      unsigned long cookie,
+			      unsigned long *ra,
+			      unsigned long *perm);
+unsigned long sun4v_ldc_unmap(unsigned long ra);
+unsigned long sun4v_ldc_revoke(unsigned long channel,
+			       unsigned long cookie,
+			       unsigned long mte_cookie);
 #endif
 
 /* Performance counter services.  */
@@ -2727,14 +2730,14 @@ extern unsigned long sun4v_ldc_revoke(unsigned long channel,
 #define HV_FAST_N2_SET_PERFREG		0x105
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_niagara_getperf(unsigned long reg,
-					   unsigned long *val);
-extern unsigned long sun4v_niagara_setperf(unsigned long reg,
-					   unsigned long val);
-extern unsigned long sun4v_niagara2_getperf(unsigned long reg,
-					    unsigned long *val);
-extern unsigned long sun4v_niagara2_setperf(unsigned long reg,
-					    unsigned long val);
+unsigned long sun4v_niagara_getperf(unsigned long reg,
+				    unsigned long *val);
+unsigned long sun4v_niagara_setperf(unsigned long reg,
+				    unsigned long val);
+unsigned long sun4v_niagara2_getperf(unsigned long reg,
+				     unsigned long *val);
+unsigned long sun4v_niagara2_setperf(unsigned long reg,
+				     unsigned long val);
 #endif
 
 /* MMU statistics services.
@@ -2829,8 +2832,8 @@ struct hv_mmu_statistics {
 #define HV_FAST_MMUSTAT_INFO		0x103
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_mmustat_conf(unsigned long ra, unsigned long *orig_ra);
-extern unsigned long sun4v_mmustat_info(unsigned long *ra);
+unsigned long sun4v_mmustat_conf(unsigned long ra, unsigned long *orig_ra);
+unsigned long sun4v_mmustat_info(unsigned long *ra);
 #endif
 
 /* NCS crypto services  */
@@ -2919,9 +2922,9 @@ struct hv_ncs_qtail_update_arg {
 #define HV_FAST_NCS_REQUEST		0x110
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_ncs_request(unsigned long request,
-				       unsigned long arg_ra,
-				       unsigned long arg_size);
+unsigned long sun4v_ncs_request(unsigned long request,
+			        unsigned long arg_ra,
+			        unsigned long arg_size);
 #endif
 
 #define HV_FAST_FIRE_GET_PERFREG	0x120
@@ -2930,18 +2933,18 @@ extern unsigned long sun4v_ncs_request(unsigned long request,
 #define HV_FAST_REBOOT_DATA_SET		0x172
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_reboot_data_set(unsigned long ra,
-					   unsigned long len);
+unsigned long sun4v_reboot_data_set(unsigned long ra,
+				    unsigned long len);
 #endif
 
 #define HV_FAST_VT_GET_PERFREG		0x184
 #define HV_FAST_VT_SET_PERFREG		0x185
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_vt_get_perfreg(unsigned long reg_num,
-					  unsigned long *reg_val);
-extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
-					  unsigned long reg_val);
+unsigned long sun4v_vt_get_perfreg(unsigned long reg_num,
+				   unsigned long *reg_val);
+unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
+				   unsigned long reg_val);
 #endif
 
 /* Function numbers for HV_CORE_TRAP.  */
@@ -2978,21 +2981,21 @@ extern unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
 #define HV_GRP_DIAG			0x0300
 
 #ifndef __ASSEMBLY__
-extern unsigned long sun4v_get_version(unsigned long group,
-				       unsigned long *major,
-				       unsigned long *minor);
-extern unsigned long sun4v_set_version(unsigned long group,
-				       unsigned long major,
-				       unsigned long minor,
-				       unsigned long *actual_minor);
-
-extern int sun4v_hvapi_register(unsigned long group, unsigned long major,
-				unsigned long *minor);
-extern void sun4v_hvapi_unregister(unsigned long group);
-extern int sun4v_hvapi_get(unsigned long group,
-			   unsigned long *major,
-			   unsigned long *minor);
-extern void sun4v_hvapi_init(void);
+unsigned long sun4v_get_version(unsigned long group,
+			        unsigned long *major,
+			        unsigned long *minor);
+unsigned long sun4v_set_version(unsigned long group,
+			        unsigned long major,
+			        unsigned long minor,
+			        unsigned long *actual_minor);
+
+int sun4v_hvapi_register(unsigned long group, unsigned long major,
+			 unsigned long *minor);
+void sun4v_hvapi_unregister(unsigned long group);
+int sun4v_hvapi_get(unsigned long group,
+		    unsigned long *major,
+		    unsigned long *minor);
+void sun4v_hvapi_init(void);
 #endif
 
 #endif /* !(_SPARC64_HYPERVISOR_H) */
diff --git a/arch/sparc/include/asm/idprom.h b/arch/sparc/include/asm/idprom.h
index 6976aa2439c..3793f7f91c4 100644
--- a/arch/sparc/include/asm/idprom.h
+++ b/arch/sparc/include/asm/idprom.h
@@ -20,6 +20,6 @@ struct idprom {
 };
 
 extern struct idprom *idprom;
-extern void idprom_init(void);
+void idprom_init(void);
 
 #endif /* !(_SPARC_IDPROM_H) */
diff --git a/arch/sparc/include/asm/io-unit.h b/arch/sparc/include/asm/io-unit.h
index 01ab2f613e9..04a9701e720 100644
--- a/arch/sparc/include/asm/io-unit.h
+++ b/arch/sparc/include/asm/io-unit.h
@@ -43,7 +43,7 @@
 struct iounit_struct {
 	unsigned long		bmap[(IOUNIT_DMA_SIZE >> (PAGE_SHIFT + 3)) / sizeof(unsigned long)];
 	spinlock_t		lock;
-	iopte_t			*page_table;
+	iopte_t __iomem		*page_table;
 	unsigned long		rotor[3];
 	unsigned long		limit[4];
 };
diff --git a/arch/sparc/include/asm/io_32.h b/arch/sparc/include/asm/io_32.h
index c1acbd891cb..9f532902627 100644
--- a/arch/sparc/include/asm/io_32.h
+++ b/arch/sparc/include/asm/io_32.h
@@ -2,191 +2,94 @@
 #define __SPARC_IO_H
 
 #include <linux/kernel.h>
-#include <linux/types.h>
 #include <linux/ioport.h>  /* struct resource */
 
-#include <asm/page.h>      /* IO address mapping routines need this */
-#include <asm-generic/pci_iomap.h>
-
-#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
-
-static inline u32 flip_dword (u32 l)
-{
-	return ((l&0xff)<<24) | (((l>>8)&0xff)<<16) | (((l>>16)&0xff)<<8)| ((l>>24)&0xff);
-}
-
-static inline u16 flip_word (u16 w)
-{
-	return ((w&0xff) << 8) | ((w>>8)&0xff);
-}
-
-#define mmiowb()
-
-/*
- * Memory mapped I/O to PCI
- */
-
-static inline u8 __raw_readb(const volatile void __iomem *addr)
-{
-	return *(__force volatile u8 *)addr;
-}
-
-static inline u16 __raw_readw(const volatile void __iomem *addr)
-{
-	return *(__force volatile u16 *)addr;
-}
-
-static inline u32 __raw_readl(const volatile void __iomem *addr)
-{
-	return *(__force volatile u32 *)addr;
-}
+#define readb_relaxed(__addr)	readb(__addr)
+#define readw_relaxed(__addr)	readw(__addr)
+#define readl_relaxed(__addr)	readl(__addr)
 
-static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
-{
-	*(__force volatile u8 *)addr = b;
-}
+#define IO_SPACE_LIMIT 0xffffffff
 
-static inline void __raw_writew(u16 w, volatile void __iomem *addr)
-{
-	*(__force volatile u16 *)addr = w;
-}
+#define memset_io(d,c,sz)     _memset_io(d,c,sz)
+#define memcpy_fromio(d,s,sz) _memcpy_fromio(d,s,sz)
+#define memcpy_toio(d,s,sz)   _memcpy_toio(d,s,sz)
 
-static inline void __raw_writel(u32 l, volatile void __iomem *addr)
-{
-	*(__force volatile u32 *)addr = l;
-}
+#include <asm-generic/io.h>
 
-static inline u8 __readb(const volatile void __iomem *addr)
+static inline void _memset_io(volatile void __iomem *dst,
+                              int c, __kernel_size_t n)
 {
-	return *(__force volatile u8 *)addr;
-}
+	volatile void __iomem *d = dst;
 
-static inline u16 __readw(const volatile void __iomem *addr)
-{
-	return flip_word(*(__force volatile u16 *)addr);
+	while (n--) {
+		writeb(c, d);
+		d++;
+	}
 }
 
-static inline u32 __readl(const volatile void __iomem *addr)
+static inline void _memcpy_fromio(void *dst, const volatile void __iomem *src,
+                                  __kernel_size_t n)
 {
-	return flip_dword(*(__force volatile u32 *)addr);
-}
+	char *d = dst;
 
-static inline void __writeb(u8 b, volatile void __iomem *addr)
-{
-	*(__force volatile u8 *)addr = b;
+	while (n--) {
+		char tmp = readb(src);
+		*d++ = tmp;
+		src++;
+	}
 }
 
-static inline void __writew(u16 w, volatile void __iomem *addr)
+static inline void _memcpy_toio(volatile void __iomem *dst, const void *src,
+                                __kernel_size_t n)
 {
-	*(__force volatile u16 *)addr = flip_word(w);
-}
+	const char *s = src;
+	volatile void __iomem *d = dst;
 
-static inline void __writel(u32 l, volatile void __iomem *addr)
-{
-	*(__force volatile u32 *)addr = flip_dword(l);
+	while (n--) {
+		char tmp = *s++;
+		writeb(tmp, d);
+		d++;
+	}
 }
 
-#define readb(__addr)		__readb(__addr)
-#define readw(__addr)		__readw(__addr)
-#define readl(__addr)		__readl(__addr)
-#define readb_relaxed(__addr)	readb(__addr)
-#define readw_relaxed(__addr)	readw(__addr)
-#define readl_relaxed(__addr)	readl(__addr)
-
-#define writeb(__b, __addr)	__writeb((__b),(__addr))
-#define writew(__w, __addr)	__writew((__w),(__addr))
-#define writel(__l, __addr)	__writel((__l),(__addr))
-
-/*
- * I/O space operations
- *
- * Arrangement on a Sun is somewhat complicated.
- *
- * First of all, we want to use standard Linux drivers
- * for keyboard, PC serial, etc. These drivers think
- * they access I/O space and use inb/outb.
- * On the other hand, EBus bridge accepts PCI *memory*
- * cycles and converts them into ISA *I/O* cycles.
- * Ergo, we want inb & outb to generate PCI memory cycles.
- *
- * If we want to issue PCI *I/O* cycles, we do this
- * with a low 64K fixed window in PCIC. This window gets
- * mapped somewhere into virtual kernel space and we
- * can use inb/outb again.
- */
-#define inb_local(__addr)	__readb((void __iomem *)(unsigned long)(__addr))
-#define inb(__addr)		__readb((void __iomem *)(unsigned long)(__addr))
-#define inw(__addr)		__readw((void __iomem *)(unsigned long)(__addr))
-#define inl(__addr)		__readl((void __iomem *)(unsigned long)(__addr))
-
-#define outb_local(__b, __addr)	__writeb(__b, (void __iomem *)(unsigned long)(__addr))
-#define outb(__b, __addr)	__writeb(__b, (void __iomem *)(unsigned long)(__addr))
-#define outw(__w, __addr)	__writew(__w, (void __iomem *)(unsigned long)(__addr))
-#define outl(__l, __addr)	__writel(__l, (void __iomem *)(unsigned long)(__addr))
-
-#define inb_p(__addr)		inb(__addr)
-#define outb_p(__b, __addr)	outb(__b, __addr)
-#define inw_p(__addr)		inw(__addr)
-#define outw_p(__w, __addr)	outw(__w, __addr)
-#define inl_p(__addr)		inl(__addr)
-#define outl_p(__l, __addr)	outl(__l, __addr)
-
-void outsb(unsigned long addr, const void *src, unsigned long cnt);
-void outsw(unsigned long addr, const void *src, unsigned long cnt);
-void outsl(unsigned long addr, const void *src, unsigned long cnt);
-void insb(unsigned long addr, void *dst, unsigned long count);
-void insw(unsigned long addr, void *dst, unsigned long count);
-void insl(unsigned long addr, void *dst, unsigned long count);
-
-#define IO_SPACE_LIMIT 0xffffffff
-
 /*
  * SBus accessors.
  *
  * SBus has only one, memory mapped, I/O space.
  * We do not need to flip bytes for SBus of course.
  */
-static inline u8 _sbus_readb(const volatile void __iomem *addr)
+static inline u8 sbus_readb(const volatile void __iomem *addr)
 {
 	return *(__force volatile u8 *)addr;
 }
 
-static inline u16 _sbus_readw(const volatile void __iomem *addr)
+static inline u16 sbus_readw(const volatile void __iomem *addr)
 {
 	return *(__force volatile u16 *)addr;
 }
 
-static inline u32 _sbus_readl(const volatile void __iomem *addr)
+static inline u32 sbus_readl(const volatile void __iomem *addr)
 {
 	return *(__force volatile u32 *)addr;
 }
 
-static inline void _sbus_writeb(u8 b, volatile void __iomem *addr)
+static inline void sbus_writeb(u8 b, volatile void __iomem *addr)
 {
 	*(__force volatile u8 *)addr = b;
 }
 
-static inline void _sbus_writew(u16 w, volatile void __iomem *addr)
+static inline void sbus_writew(u16 w, volatile void __iomem *addr)
 {
 	*(__force volatile u16 *)addr = w;
 }
 
-static inline void _sbus_writel(u32 l, volatile void __iomem *addr)
+static inline void sbus_writel(u32 l, volatile void __iomem *addr)
 {
 	*(__force volatile u32 *)addr = l;
 }
 
-/*
- * The only reason for #define's is to hide casts to unsigned long.
- */
-#define sbus_readb(__addr)		_sbus_readb(__addr)
-#define sbus_readw(__addr)		_sbus_readw(__addr)
-#define sbus_readl(__addr)		_sbus_readl(__addr)
-#define sbus_writeb(__b, __addr)	_sbus_writeb(__b, __addr)
-#define sbus_writew(__w, __addr)	_sbus_writew(__w, __addr)
-#define sbus_writel(__l, __addr)	_sbus_writel(__l, __addr)
-
-static inline void sbus_memset_io(volatile void __iomem *__dst, int c, __kernel_size_t n)
+static inline void sbus_memset_io(volatile void __iomem *__dst, int c,
+                                  __kernel_size_t n)
 {
 	while(n--) {
 		sbus_writeb(c, __dst);
@@ -194,22 +97,9 @@ static inline void sbus_memset_io(volatile void __iomem *__dst, int c, __kernel_
 	}
 }
 
-static inline void
-_memset_io(volatile void __iomem *dst, int c, __kernel_size_t n)
-{
-	volatile void __iomem *d = dst;
-
-	while (n--) {
-		writeb(c, d);
-		d++;
-	}
-}
-
-#define memset_io(d,c,sz)	_memset_io(d,c,sz)
-
-static inline void
-_sbus_memcpy_fromio(void *dst, const volatile void __iomem *src,
-		    __kernel_size_t n)
+static inline void sbus_memcpy_fromio(void *dst,
+                                      const volatile void __iomem *src,
+                                      __kernel_size_t n)
 {
 	char *d = dst;
 
@@ -220,25 +110,9 @@ _sbus_memcpy_fromio(void *dst, const volatile void __iomem *src,
 	}
 }
 
-#define sbus_memcpy_fromio(d, s, sz)	_sbus_memcpy_fromio(d, s, sz)
-
-static inline void
-_memcpy_fromio(void *dst, const volatile void __iomem *src, __kernel_size_t n)
-{
-	char *d = dst;
-
-	while (n--) {
-		char tmp = readb(src);
-		*d++ = tmp;
-		src++;
-	}
-}
-
-#define memcpy_fromio(d,s,sz)	_memcpy_fromio(d,s,sz)
-
-static inline void
-_sbus_memcpy_toio(volatile void __iomem *dst, const void *src,
-		  __kernel_size_t n)
+static inline void sbus_memcpy_toio(volatile void __iomem *dst,
+                                    const void *src,
+                                    __kernel_size_t n)
 {
 	const char *s = src;
 	volatile void __iomem *d = dst;
@@ -250,81 +124,26 @@ _sbus_memcpy_toio(volatile void __iomem *dst, const void *src,
 	}
 }
 
-#define sbus_memcpy_toio(d, s, sz)	_sbus_memcpy_toio(d, s, sz)
-
-static inline void
-_memcpy_toio(volatile void __iomem *dst, const void *src, __kernel_size_t n)
-{
-	const char *s = src;
-	volatile void __iomem *d = dst;
-
-	while (n--) {
-		char tmp = *s++;
-		writeb(tmp, d);
-		d++;
-	}
-}
-
-#define memcpy_toio(d,s,sz)	_memcpy_toio(d,s,sz)
-
 #ifdef __KERNEL__
 
 /*
  * Bus number may be embedded in the higher bits of the physical address.
  * This is why we have no bus number argument to ioremap().
  */
-extern void __iomem *ioremap(unsigned long offset, unsigned long size);
+void __iomem *ioremap(unsigned long offset, unsigned long size);
 #define ioremap_nocache(X,Y)	ioremap((X),(Y))
 #define ioremap_wc(X,Y)		ioremap((X),(Y))
-extern void iounmap(volatile void __iomem *addr);
-
-#define ioread8(X)			readb(X)
-#define ioread16(X)			readw(X)
-#define ioread16be(X)			__raw_readw(X)
-#define ioread32(X)			readl(X)
-#define ioread32be(X)			__raw_readl(X)
-#define iowrite8(val,X)			writeb(val,X)
-#define iowrite16(val,X)		writew(val,X)
-#define iowrite16be(val,X)		__raw_writew(val,X)
-#define iowrite32(val,X)		writel(val,X)
-#define iowrite32be(val,X)		__raw_writel(val,X)
-
-static inline void ioread8_rep(void __iomem *port, void *buf, unsigned long count)
-{
-	insb((unsigned long __force)port, buf, count);
-}
-static inline void ioread16_rep(void __iomem *port, void *buf, unsigned long count)
-{
-	insw((unsigned long __force)port, buf, count);
-}
-
-static inline void ioread32_rep(void __iomem *port, void *buf, unsigned long count)
-{
-	insl((unsigned long __force)port, buf, count);
-}
-
-static inline void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count)
-{
-	outsb((unsigned long __force)port, buf, count);
-}
-
-static inline void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count)
-{
-	outsw((unsigned long __force)port, buf, count);
-}
-
-static inline void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count)
-{
-	outsl((unsigned long __force)port, buf, count);
-}
+void iounmap(volatile void __iomem *addr);
 
 /* Create a virtual mapping cookie for an IO port range */
-extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
-extern void ioport_unmap(void __iomem *);
+void __iomem *ioport_map(unsigned long port, unsigned int nr);
+void ioport_unmap(void __iomem *);
 
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 struct pci_dev;
-extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
+void pci_iounmap(struct pci_dev *dev, void __iomem *);
+
+
 
 /*
  * At the moment, we do not use CMOS_READ anywhere outside of rtc.c,
@@ -343,21 +162,11 @@ static inline int sbus_can_burst64(void)
 	return 0; /* actually, sparc_cpu_model==sun4d */
 }
 struct device;
-extern void sbus_set_sbus64(struct device *, int);
+void sbus_set_sbus64(struct device *, int);
 
 #endif
 
 #define __ARCH_HAS_NO_PAGE_ZERO_MAPPED		1
 
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
 
 #endif /* !(__SPARC_IO_H) */
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 09b0b88aeb2..05381c3a422 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -15,7 +15,6 @@
 
 /* BIO layer definitions. */
 extern unsigned long kern_base, kern_size;
-#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
 
 static inline u8 _inb(unsigned long addr)
 {
@@ -91,12 +90,12 @@ static inline void _outl(u32 l, unsigned long addr)
 #define inl_p(__addr)		inl(__addr)
 #define outl_p(__l, __addr)	outl(__l, __addr)
 
-extern void outsb(unsigned long, const void *, unsigned long);
-extern void outsw(unsigned long, const void *, unsigned long);
-extern void outsl(unsigned long, const void *, unsigned long);
-extern void insb(unsigned long, void *, unsigned long);
-extern void insw(unsigned long, void *, unsigned long);
-extern void insl(unsigned long, void *, unsigned long);
+void outsb(unsigned long, const void *, unsigned long);
+void outsw(unsigned long, const void *, unsigned long);
+void outsl(unsigned long, const void *, unsigned long);
+void insb(unsigned long, void *, unsigned long);
+void insw(unsigned long, void *, unsigned long);
+void insl(unsigned long, void *, unsigned long);
 
 static inline void ioread8_rep(void __iomem *port, void *buf, unsigned long count)
 {
@@ -509,12 +508,12 @@ static inline void iounmap(volatile void __iomem *addr)
 #define iowrite32be(val,X)		__raw_writel(val,X)
 
 /* Create a virtual mapping cookie for an IO port range */
-extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
-extern void ioport_unmap(void __iomem *);
+void __iomem *ioport_map(unsigned long port, unsigned int nr);
+void ioport_unmap(void __iomem *);
 
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 struct pci_dev;
-extern void pci_iounmap(struct pci_dev *dev, void __iomem *);
+void pci_iounmap(struct pci_dev *dev, void __iomem *);
 
 static inline int sbus_can_dma_64bit(void)
 {
@@ -525,7 +524,7 @@ static inline int sbus_can_burst64(void)
 	return 1;
 }
 struct device;
-extern void sbus_set_sbus64(struct device *, int);
+void sbus_set_sbus64(struct device *, int);
 
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/arch/sparc/include/asm/iommu_32.h b/arch/sparc/include/asm/iommu_32.h
index 70c589c05a1..f6c066b52fd 100644
--- a/arch/sparc/include/asm/iommu_32.h
+++ b/arch/sparc/include/asm/iommu_32.h
@@ -99,7 +99,7 @@ struct iommu_regs {
 #define IOPTE_WAZ           0x00000001 /* Write as zeros */
 
 struct iommu_struct {
-	struct iommu_regs *regs;
+	struct iommu_regs __iomem *regs;
 	iopte_t *page_table;
 	/* For convenience */
 	unsigned long start; /* First managed virtual address */
@@ -108,14 +108,14 @@ struct iommu_struct {
 	struct bit_map usemap;
 };
 
-static inline void iommu_invalidate(struct iommu_regs *regs)
+static inline void iommu_invalidate(struct iommu_regs __iomem *regs)
 {
-	regs->tlbflush = 0;
+	sbus_writel(0, &regs->tlbflush);
 }
 
-static inline void iommu_invalidate_page(struct iommu_regs *regs, unsigned long ba)
+static inline void iommu_invalidate_page(struct iommu_regs __iomem *regs, unsigned long ba)
 {
-	regs->pageflush = (ba & PAGE_MASK);
+	sbus_writel(ba & PAGE_MASK, &regs->pageflush);
 }
 
 #endif /* !(_SPARC_IOMMU_H) */
diff --git a/arch/sparc/include/asm/iommu_64.h b/arch/sparc/include/asm/iommu_64.h
index caf798b5619..2b9321ab064 100644
--- a/arch/sparc/include/asm/iommu_64.h
+++ b/arch/sparc/include/asm/iommu_64.h
@@ -58,8 +58,8 @@ struct strbuf {
 	volatile unsigned long	__flushflag_buf[(64+(64-1)) / sizeof(long)];
 };
 
-extern int iommu_table_init(struct iommu *iommu, int tsbsize,
-			    u32 dma_offset, u32 dma_addr_mask,
-			    int numa_node);
+int iommu_table_init(struct iommu *iommu, int tsbsize,
+		     u32 dma_offset, u32 dma_addr_mask,
+		     int numa_node);
 
 #endif /* !(_SPARC64_IOMMU_H) */
diff --git a/arch/sparc/include/asm/irq_32.h b/arch/sparc/include/asm/irq_32.h
index 2ae3acaeb1b..eecd3d8442c 100644
--- a/arch/sparc/include/asm/irq_32.h
+++ b/arch/sparc/include/asm/irq_32.h
@@ -16,7 +16,8 @@
 
 #define irq_canonicalize(irq)	(irq)
 
-extern void __init init_IRQ(void);
+void __init init_IRQ(void);
+void __init sun4d_init_sbi_irq(void);
 
 #define NO_IRQ		0xffffffff
 
diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h
index abf6afe82ca..91d21938130 100644
--- a/arch/sparc/include/asm/irq_64.h
+++ b/arch/sparc/include/asm/irq_64.h
@@ -39,32 +39,32 @@
  */
 #define NR_IRQS    255
 
-extern void irq_install_pre_handler(int irq,
-				    void (*func)(unsigned int, void *, void *),
-				    void *arg1, void *arg2);
+void irq_install_pre_handler(int irq,
+			     void (*func)(unsigned int, void *, void *),
+			     void *arg1, void *arg2);
 #define irq_canonicalize(irq)	(irq)
-extern unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap);
-extern unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino);
-extern unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino);
-extern unsigned int sun4v_build_msi(u32 devhandle, unsigned int *irq_p,
-				    unsigned int msi_devino_start,
-				    unsigned int msi_devino_end);
-extern void sun4v_destroy_msi(unsigned int irq);
-extern unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p,
-				    unsigned int msi_devino_start,
-				    unsigned int msi_devino_end,
-				    unsigned long imap_base,
-				    unsigned long iclr_base);
-extern void sun4u_destroy_msi(unsigned int irq);
-
-extern unsigned char irq_alloc(unsigned int dev_handle,
-				    unsigned int dev_ino);
+unsigned int build_irq(int inofixup, unsigned long iclr, unsigned long imap);
+unsigned int sun4v_build_irq(u32 devhandle, unsigned int devino);
+unsigned int sun4v_build_virq(u32 devhandle, unsigned int devino);
+unsigned int sun4v_build_msi(u32 devhandle, unsigned int *irq_p,
+			     unsigned int msi_devino_start,
+			     unsigned int msi_devino_end);
+void sun4v_destroy_msi(unsigned int irq);
+unsigned int sun4u_build_msi(u32 portid, unsigned int *irq_p,
+			     unsigned int msi_devino_start,
+			     unsigned int msi_devino_end,
+			     unsigned long imap_base,
+			     unsigned long iclr_base);
+void sun4u_destroy_msi(unsigned int irq);
+
+unsigned char irq_alloc(unsigned int dev_handle,
+			unsigned int dev_ino);
 #ifdef CONFIG_PCI_MSI
-extern void irq_free(unsigned int irq);
+void irq_free(unsigned int irq);
 #endif
 
-extern void __init init_IRQ(void);
-extern void fixup_irqs(void);
+void __init init_IRQ(void);
+void fixup_irqs(void);
 
 static inline void set_softint(unsigned long bits)
 {
@@ -89,7 +89,7 @@ static inline unsigned long get_softint(void)
 	return retval;
 }
 
-void arch_trigger_all_cpu_backtrace(void);
+void arch_trigger_all_cpu_backtrace(bool);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 
 extern void *hardirq_stack[NR_CPUS];
diff --git a/arch/sparc/include/asm/irqflags_32.h b/arch/sparc/include/asm/irqflags_32.h
index e414c06615c..71cc284f55c 100644
--- a/arch/sparc/include/asm/irqflags_32.h
+++ b/arch/sparc/include/asm/irqflags_32.h
@@ -15,9 +15,9 @@
 #include <linux/types.h>
 #include <asm/psr.h>
 
-extern void arch_local_irq_restore(unsigned long);
-extern unsigned long arch_local_irq_save(void);
-extern void arch_local_irq_enable(void);
+void arch_local_irq_restore(unsigned long);
+unsigned long arch_local_irq_save(void);
+void arch_local_irq_enable(void);
 
 static inline notrace unsigned long arch_local_save_flags(void)
 {
diff --git a/arch/sparc/include/asm/kdebug_64.h b/arch/sparc/include/asm/kdebug_64.h
index feb3578e12c..04465de8f3b 100644
--- a/arch/sparc/include/asm/kdebug_64.h
+++ b/arch/sparc/include/asm/kdebug_64.h
@@ -3,7 +3,7 @@
 
 struct pt_regs;
 
-extern void bad_trap(struct pt_regs *, long);
+void bad_trap(struct pt_regs *, long);
 
 /* Grossly misnamed. */
 enum die_val {
diff --git a/arch/sparc/include/asm/kgdb.h b/arch/sparc/include/asm/kgdb.h
index b6ef301d05b..47366af7a58 100644
--- a/arch/sparc/include/asm/kgdb.h
+++ b/arch/sparc/include/asm/kgdb.h
@@ -28,9 +28,12 @@ enum regnames {
 #define NUMREGBYTES		((GDB_CSR + 1) * 4)
 #else
 #define NUMREGBYTES		((GDB_Y + 1) * 8)
+
+struct pt_regs;
+asmlinkage void kgdb_trap(unsigned long trap_level, struct pt_regs *regs);
 #endif
 
-extern void arch_kgdb_breakpoint(void);
+void arch_kgdb_breakpoint(void);
 
 #define BREAK_INSTR_SIZE	4
 #define CACHE_FLUSH_IS_SAFE	1
diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h
index 5879d71afda..a145d798e11 100644
--- a/arch/sparc/include/asm/kprobes.h
+++ b/arch/sparc/include/asm/kprobes.h
@@ -43,7 +43,9 @@ struct kprobe_ctlblk {
 	struct prev_kprobe prev_kprobe;
 };
 
-extern int kprobe_exceptions_notify(struct notifier_block *self,
-				    unsigned long val, void *data);
-extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
+int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data);
+int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
+asmlinkage void __kprobes kprobe_trap(unsigned long trap_level,
+				      struct pt_regs *regs);
 #endif /* _SPARC64_KPROBES_H */
diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h
index bdb524a7b81..c8c67f621f4 100644
--- a/arch/sparc/include/asm/ldc.h
+++ b/arch/sparc/include/asm/ldc.h
@@ -4,9 +4,9 @@
 #include <asm/hypervisor.h>
 
 extern int ldom_domaining_enabled;
-extern void ldom_set_var(const char *var, const char *value);
-extern void ldom_reboot(const char *boot_command);
-extern void ldom_power_off(void);
+void ldom_set_var(const char *var, const char *value);
+void ldom_reboot(const char *boot_command);
+void ldom_power_off(void);
 
 /* The event handler will be evoked when link state changes
  * or data becomes available on the receive side.
@@ -51,30 +51,30 @@ struct ldc_channel_config {
 struct ldc_channel;
 
 /* Allocate state for a channel.  */
-extern struct ldc_channel *ldc_alloc(unsigned long id,
-				     const struct ldc_channel_config *cfgp,
-				     void *event_arg);
+struct ldc_channel *ldc_alloc(unsigned long id,
+			      const struct ldc_channel_config *cfgp,
+			      void *event_arg);
 
 /* Shut down and free state for a channel.  */
-extern void ldc_free(struct ldc_channel *lp);
+void ldc_free(struct ldc_channel *lp);
 
 /* Register TX and RX queues of the link with the hypervisor.  */
-extern int ldc_bind(struct ldc_channel *lp, const char *name);
+int ldc_bind(struct ldc_channel *lp, const char *name);
 
 /* For non-RAW protocols we need to complete a handshake before
  * communication can proceed.  ldc_connect() does that, if the
  * handshake completes successfully, an LDC_EVENT_UP event will
  * be sent up to the driver.
  */
-extern int ldc_connect(struct ldc_channel *lp);
-extern int ldc_disconnect(struct ldc_channel *lp);
+int ldc_connect(struct ldc_channel *lp);
+int ldc_disconnect(struct ldc_channel *lp);
 
-extern int ldc_state(struct ldc_channel *lp);
+int ldc_state(struct ldc_channel *lp);
 
 /* Read and write operations.  Only valid when the link is up.  */
-extern int ldc_write(struct ldc_channel *lp, const void *buf,
-		     unsigned int size);
-extern int ldc_read(struct ldc_channel *lp, void *buf, unsigned int size);
+int ldc_write(struct ldc_channel *lp, const void *buf,
+	      unsigned int size);
+int ldc_read(struct ldc_channel *lp, void *buf, unsigned int size);
 
 #define LDC_MAP_SHADOW	0x01
 #define LDC_MAP_DIRECT	0x02
@@ -92,22 +92,22 @@ struct ldc_trans_cookie {
 };
 
 struct scatterlist;
-extern int ldc_map_sg(struct ldc_channel *lp,
-		      struct scatterlist *sg, int num_sg,
-		      struct ldc_trans_cookie *cookies, int ncookies,
-		      unsigned int map_perm);
+int ldc_map_sg(struct ldc_channel *lp,
+	       struct scatterlist *sg, int num_sg,
+	       struct ldc_trans_cookie *cookies, int ncookies,
+	       unsigned int map_perm);
 
-extern int ldc_map_single(struct ldc_channel *lp,
-			  void *buf, unsigned int len,
-			  struct ldc_trans_cookie *cookies, int ncookies,
-			  unsigned int map_perm);
+int ldc_map_single(struct ldc_channel *lp,
+		   void *buf, unsigned int len,
+		   struct ldc_trans_cookie *cookies, int ncookies,
+		   unsigned int map_perm);
 
-extern void ldc_unmap(struct ldc_channel *lp, struct ldc_trans_cookie *cookies,
-		      int ncookies);
+void ldc_unmap(struct ldc_channel *lp, struct ldc_trans_cookie *cookies,
+	       int ncookies);
 
-extern int ldc_copy(struct ldc_channel *lp, int copy_dir,
-		    void *buf, unsigned int len, unsigned long offset,
-		    struct ldc_trans_cookie *cookies, int ncookies);
+int ldc_copy(struct ldc_channel *lp, int copy_dir,
+	     void *buf, unsigned int len, unsigned long offset,
+	     struct ldc_trans_cookie *cookies, int ncookies);
 
 static inline int ldc_get_dring_entry(struct ldc_channel *lp,
 				      void *buf, unsigned int len,
@@ -127,12 +127,12 @@ static inline int ldc_put_dring_entry(struct ldc_channel *lp,
 	return ldc_copy(lp, LDC_COPY_OUT, buf, len, offset, cookies, ncookies);
 }
 
-extern void *ldc_alloc_exp_dring(struct ldc_channel *lp, unsigned int len,
-				 struct ldc_trans_cookie *cookies,
-				 int *ncookies, unsigned int map_perm);
+void *ldc_alloc_exp_dring(struct ldc_channel *lp, unsigned int len,
+			  struct ldc_trans_cookie *cookies,
+			  int *ncookies, unsigned int map_perm);
 
-extern void ldc_free_exp_dring(struct ldc_channel *lp, void *buf,
-			       unsigned int len,
-			       struct ldc_trans_cookie *cookies, int ncookies);
+void ldc_free_exp_dring(struct ldc_channel *lp, void *buf,
+		        unsigned int len,
+		        struct ldc_trans_cookie *cookies, int ncookies);
 
 #endif /* _SPARC64_LDC_H */
diff --git a/arch/sparc/include/asm/leon.h b/arch/sparc/include/asm/leon.h
index c2f6ff6d7a3..204771cd74a 100644
--- a/arch/sparc/include/asm/leon.h
+++ b/arch/sparc/include/asm/leon.h
@@ -82,8 +82,8 @@ static inline unsigned long leon_load_reg(unsigned long paddr)
 #define LEON_BYPASS_LOAD_PA(x)      leon_load_reg((unsigned long)(x))
 #define LEON_BYPASS_STORE_PA(x, v)  leon_store_reg((unsigned long)(x), (unsigned long)(v))
 
-extern void leon_switch_mm(void);
-extern void leon_init_IRQ(void);
+void leon_switch_mm(void);
+void leon_init_IRQ(void);
 
 static inline unsigned long sparc_leon3_get_dcachecfg(void)
 {
@@ -196,14 +196,14 @@ static inline int sparc_leon3_cpuid(void)
 #ifndef __ASSEMBLY__
 struct vm_area_struct;
 
-extern unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr);
-extern void leon_flush_icache_all(void);
-extern void leon_flush_dcache_all(void);
-extern void leon_flush_cache_all(void);
-extern void leon_flush_tlb_all(void);
+unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr);
+void leon_flush_icache_all(void);
+void leon_flush_dcache_all(void);
+void leon_flush_cache_all(void);
+void leon_flush_tlb_all(void);
 extern int leon_flush_during_switch;
-extern int leon_flush_needed(void);
-extern void leon_flush_pcache_all(struct vm_area_struct *vma, unsigned long page);
+int leon_flush_needed(void);
+void leon_flush_pcache_all(struct vm_area_struct *vma, unsigned long page);
 
 /* struct that hold LEON3 cache configuration registers */
 struct leon3_cacheregs {
@@ -217,29 +217,29 @@ struct leon3_cacheregs {
 
 struct device_node;
 struct task_struct;
-extern unsigned int leon_build_device_irq(unsigned int real_irq,
-					   irq_flow_handler_t flow_handler,
-					   const char *name, int do_ack);
-extern void leon_update_virq_handling(unsigned int virq,
-			      irq_flow_handler_t flow_handler,
-			      const char *name, int do_ack);
-extern void leon_init_timers(void);
-extern void leon_trans_init(struct device_node *dp);
-extern void leon_node_init(struct device_node *dp, struct device_node ***nextp);
-extern void init_leon(void);
-extern void poke_leonsparc(void);
-extern void leon3_getCacheRegs(struct leon3_cacheregs *regs);
+unsigned int leon_build_device_irq(unsigned int real_irq,
+				   irq_flow_handler_t flow_handler,
+				   const char *name, int do_ack);
+void leon_update_virq_handling(unsigned int virq,
+			       irq_flow_handler_t flow_handler,
+			       const char *name, int do_ack);
+void leon_init_timers(void);
+void leon_trans_init(struct device_node *dp);
+void leon_node_init(struct device_node *dp, struct device_node ***nextp);
+void init_leon(void);
+void poke_leonsparc(void);
+void leon3_getCacheRegs(struct leon3_cacheregs *regs);
 extern int leon3_ticker_irq;
 
 #ifdef CONFIG_SMP
-extern int leon_smp_nrcpus(void);
-extern void leon_clear_profile_irq(int cpu);
-extern void leon_smp_done(void);
-extern void leon_boot_cpus(void);
-extern int leon_boot_one_cpu(int i, struct task_struct *);
+int leon_smp_nrcpus(void);
+void leon_clear_profile_irq(int cpu);
+void leon_smp_done(void);
+void leon_boot_cpus(void);
+int leon_boot_one_cpu(int i, struct task_struct *);
 void leon_init_smp(void);
 void leon_enable_irq_cpu(unsigned int irq_nr, unsigned int cpu);
-extern irqreturn_t leon_percpu_timer_interrupt(int irq, void *unused);
+irqreturn_t leon_percpu_timer_interrupt(int irq, void *unused);
 
 extern unsigned int smpleon_ipi[];
 extern unsigned int linux_trap_ipi15_leon[];
diff --git a/arch/sparc/include/asm/leon_pci.h b/arch/sparc/include/asm/leon_pci.h
index bfd3ab3092b..049d067ed8b 100644
--- a/arch/sparc/include/asm/leon_pci.h
+++ b/arch/sparc/include/asm/leon_pci.h
@@ -16,7 +16,7 @@ struct leon_pci_info {
 	int (*map_irq)(const struct pci_dev *dev, u8 slot, u8 pin);
 };
 
-extern void leon_pci_init(struct platform_device *ofdev,
-				struct leon_pci_info *info);
+void leon_pci_init(struct platform_device *ofdev,
+		   struct leon_pci_info *info);
 
 #endif /* _ASM_LEON_PCI_H_ */
diff --git a/arch/sparc/include/asm/mc146818rtc.h b/arch/sparc/include/asm/mc146818rtc.h
index 67ed9e3a023..d8e72f37dc4 100644
--- a/arch/sparc/include/asm/mc146818rtc.h
+++ b/arch/sparc/include/asm/mc146818rtc.h
@@ -1,5 +1,10 @@
 #ifndef ___ASM_SPARC_MC146818RTC_H
 #define ___ASM_SPARC_MC146818RTC_H
+
+#include <linux/spinlock.h>
+
+extern spinlock_t rtc_lock;
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/mc146818rtc_64.h>
 #else
diff --git a/arch/sparc/include/asm/mdesc.h b/arch/sparc/include/asm/mdesc.h
index 139097f3a67..aebeb88f70d 100644
--- a/arch/sparc/include/asm/mdesc.h
+++ b/arch/sparc/include/asm/mdesc.h
@@ -12,13 +12,13 @@ struct mdesc_handle;
  * the first argument to all of the operational calls that work
  * on mdescs.
  */
-extern struct mdesc_handle *mdesc_grab(void);
-extern void mdesc_release(struct mdesc_handle *);
+struct mdesc_handle *mdesc_grab(void);
+void mdesc_release(struct mdesc_handle *);
 
 #define MDESC_NODE_NULL		(~(u64)0)
 
-extern u64 mdesc_node_by_name(struct mdesc_handle *handle,
-			      u64 from_node, const char *name);
+u64 mdesc_node_by_name(struct mdesc_handle *handle,
+		       u64 from_node, const char *name);
 #define mdesc_for_each_node_by_name(__hdl, __node, __name) \
 	for (__node = mdesc_node_by_name(__hdl, MDESC_NODE_NULL, __name); \
 	     (__node) != MDESC_NODE_NULL; \
@@ -34,9 +34,9 @@ extern u64 mdesc_node_by_name(struct mdesc_handle *handle,
  *
  * These same rules apply to mdesc_node_name().
  */
-extern const void *mdesc_get_property(struct mdesc_handle *handle,
-				      u64 node, const char *name, int *lenp);
-extern const char *mdesc_node_name(struct mdesc_handle *hp, u64 node);
+const void *mdesc_get_property(struct mdesc_handle *handle,
+			       u64 node, const char *name, int *lenp);
+const char *mdesc_node_name(struct mdesc_handle *hp, u64 node);
 
 /* MD arc iteration, the standard sequence is:
  *
@@ -50,16 +50,16 @@ extern const char *mdesc_node_name(struct mdesc_handle *hp, u64 node);
 #define MDESC_ARC_TYPE_FWD	"fwd"
 #define MDESC_ARC_TYPE_BACK	"back"
 
-extern u64 mdesc_next_arc(struct mdesc_handle *handle, u64 from,
-			  const char *arc_type);
+u64 mdesc_next_arc(struct mdesc_handle *handle, u64 from,
+		   const char *arc_type);
 #define mdesc_for_each_arc(__arc, __hdl, __node, __type) \
 	for (__arc = mdesc_next_arc(__hdl, __node, __type); \
 	     (__arc) != MDESC_NODE_NULL; \
 	     __arc = mdesc_next_arc(__hdl, __arc, __type))
 
-extern u64 mdesc_arc_target(struct mdesc_handle *hp, u64 arc);
+u64 mdesc_arc_target(struct mdesc_handle *hp, u64 arc);
 
-extern void mdesc_update(void);
+void mdesc_update(void);
 
 struct mdesc_notifier_client {
 	void (*add)(struct mdesc_handle *handle, u64 node);
@@ -69,12 +69,12 @@ struct mdesc_notifier_client {
 	struct mdesc_notifier_client	*next;
 };
 
-extern void mdesc_register_notifier(struct mdesc_notifier_client *client);
+void mdesc_register_notifier(struct mdesc_notifier_client *client);
 
-extern void mdesc_fill_in_cpu_data(cpumask_t *mask);
-extern void mdesc_populate_present_mask(cpumask_t *mask);
-extern void mdesc_get_page_sizes(cpumask_t *mask, unsigned long *pgsz_mask);
+void mdesc_fill_in_cpu_data(cpumask_t *mask);
+void mdesc_populate_present_mask(cpumask_t *mask);
+void mdesc_get_page_sizes(cpumask_t *mask, unsigned long *pgsz_mask);
 
-extern void sun4v_mdesc_init(void);
+void sun4v_mdesc_init(void);
 
 #endif
diff --git a/arch/sparc/include/asm/mmu_64.h b/arch/sparc/include/asm/mmu_64.h
index f668797ae23..70067ce184b 100644
--- a/arch/sparc/include/asm/mmu_64.h
+++ b/arch/sparc/include/asm/mmu_64.h
@@ -67,9 +67,9 @@ struct tsb {
 	unsigned long pte;
 } __attribute__((aligned(TSB_ENTRY_ALIGNMENT)));
 
-extern void __tsb_insert(unsigned long ent, unsigned long tag, unsigned long pte);
-extern void tsb_flush(unsigned long ent, unsigned long tag);
-extern void tsb_init(struct tsb *tsb, unsigned long size);
+void __tsb_insert(unsigned long ent, unsigned long tag, unsigned long pte);
+void tsb_flush(unsigned long ent, unsigned long tag);
+void tsb_init(struct tsb *tsb, unsigned long size);
 
 struct tsb_config {
 	struct tsb		*tsb;
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index 3d528f06e4b..b84be675e50 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -17,20 +17,20 @@ extern spinlock_t ctx_alloc_lock;
 extern unsigned long tlb_context_cache;
 extern unsigned long mmu_context_bmap[];
 
-extern void get_new_mmu_context(struct mm_struct *mm);
+void get_new_mmu_context(struct mm_struct *mm);
 #ifdef CONFIG_SMP
-extern void smp_new_mmu_context_version(void);
+void smp_new_mmu_context_version(void);
 #else
 #define smp_new_mmu_context_version() do { } while (0)
 #endif
 
-extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-extern void destroy_context(struct mm_struct *mm);
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context(struct mm_struct *mm);
 
-extern void __tsb_context_switch(unsigned long pgd_pa,
-				 struct tsb_config *tsb_base,
-				 struct tsb_config *tsb_huge,
-				 unsigned long tsb_descr_pa);
+void __tsb_context_switch(unsigned long pgd_pa,
+			  struct tsb_config *tsb_base,
+			  struct tsb_config *tsb_huge,
+			  unsigned long tsb_descr_pa);
 
 static inline void tsb_context_switch(struct mm_struct *mm)
 {
@@ -46,9 +46,11 @@ static inline void tsb_context_switch(struct mm_struct *mm)
 			     , __pa(&mm->context.tsb_descr[0]));
 }
 
-extern void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long mm_rss);
+void tsb_grow(struct mm_struct *mm,
+	      unsigned long tsb_index,
+	      unsigned long mm_rss);
 #ifdef CONFIG_SMP
-extern void smp_tsb_sync(struct mm_struct *mm);
+void smp_tsb_sync(struct mm_struct *mm);
 #else
 #define smp_tsb_sync(__mm) do { } while (0)
 #endif
@@ -66,7 +68,7 @@ extern void smp_tsb_sync(struct mm_struct *mm);
 	: "r" (CTX_HWBITS((__mm)->context)), \
 	  "r" (SECONDARY_CONTEXT), "i" (ASI_DMMU), "i" (ASI_MMU))
 
-extern void __flush_tlb_mm(unsigned long, unsigned long);
+void __flush_tlb_mm(unsigned long, unsigned long);
 
 /* Switch the current MM context. */
 static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h
index 72e6500e7ab..26ad2b2607c 100644
--- a/arch/sparc/include/asm/nmi.h
+++ b/arch/sparc/include/asm/nmi.h
@@ -1,13 +1,13 @@
 #ifndef __NMI_H
 #define __NMI_H
 
-extern int __init nmi_init(void);
-extern void perfctr_irq(int irq, struct pt_regs *regs);
-extern void nmi_adjust_hz(unsigned int new_hz);
+int __init nmi_init(void);
+void perfctr_irq(int irq, struct pt_regs *regs);
+void nmi_adjust_hz(unsigned int new_hz);
 
 extern atomic_t nmi_active;
 
-extern void start_nmi_watchdog(void *unused);
-extern void stop_nmi_watchdog(void *unused);
+void start_nmi_watchdog(void *unused);
+void stop_nmi_watchdog(void *unused);
 
 #endif /* __NMI_H */
diff --git a/arch/sparc/include/asm/oplib_32.h b/arch/sparc/include/asm/oplib_32.h
index c72f3045820..56a09b9d7b1 100644
--- a/arch/sparc/include/asm/oplib_32.h
+++ b/arch/sparc/include/asm/oplib_32.h
@@ -43,28 +43,28 @@ extern struct linux_nodeops *prom_nodeops;
 /* You must call prom_init() before using any of the library services,
  * preferably as early as possible.  Pass it the romvec pointer.
  */
-extern void prom_init(struct linux_romvec *rom_ptr);
+void prom_init(struct linux_romvec *rom_ptr);
 
 /* Boot argument acquisition, returns the boot command line string. */
-extern char *prom_getbootargs(void);
+char *prom_getbootargs(void);
 
 /* Miscellaneous routines, don't really fit in any category per se. */
 
 /* Reboot the machine with the command line passed. */
-extern void prom_reboot(char *boot_command);
+void prom_reboot(char *boot_command);
 
 /* Evaluate the forth string passed. */
-extern void prom_feval(char *forth_string);
+void prom_feval(char *forth_string);
 
 /* Enter the prom, with possibility of continuation with the 'go'
  * command in newer proms.
  */
-extern void prom_cmdline(void);
+void prom_cmdline(void);
 
 /* Enter the prom, with no chance of continuation for the stand-alone
  * which calls this.
  */
-extern void __noreturn prom_halt(void);
+void __noreturn prom_halt(void);
 
 /* Set the PROM 'sync' callback function to the passed function pointer.
  * When the user gives the 'sync' command at the prom prompt while the
@@ -73,37 +73,37 @@ extern void __noreturn prom_halt(void);
  * XXX The arguments are different on V0 vs. V2->higher proms, grrr! XXX
  */
 typedef void (*sync_func_t)(void);
-extern void prom_setsync(sync_func_t func_ptr);
+void prom_setsync(sync_func_t func_ptr);
 
 /* Acquire the IDPROM of the root node in the prom device tree.  This
  * gets passed a buffer where you would like it stuffed.  The return value
  * is the format type of this idprom or 0xff on error.
  */
-extern unsigned char prom_get_idprom(char *idp_buffer, int idpbuf_size);
+unsigned char prom_get_idprom(char *idp_buffer, int idpbuf_size);
 
 /* Get the prom major version. */
-extern int prom_version(void);
+int prom_version(void);
 
 /* Get the prom plugin revision. */
-extern int prom_getrev(void);
+int prom_getrev(void);
 
 /* Get the prom firmware revision. */
-extern int prom_getprev(void);
+int prom_getprev(void);
 
 /* Write a buffer of characters to the console. */
-extern void prom_console_write_buf(const char *buf, int len);
+void prom_console_write_buf(const char *buf, int len);
 
 /* Prom's internal routines, don't use in kernel/boot code. */
-extern __printf(1, 2) void prom_printf(const char *fmt, ...);
-extern void prom_write(const char *buf, unsigned int len);
+__printf(1, 2) void prom_printf(const char *fmt, ...);
+void prom_write(const char *buf, unsigned int len);
 
 /* Multiprocessor operations... */
 
 /* Start the CPU with the given device tree node, context table, and context
  * at the passed program counter.
  */
-extern int prom_startcpu(int cpunode, struct linux_prom_registers *context_table,
-			 int context, char *program_counter);
+int prom_startcpu(int cpunode, struct linux_prom_registers *context_table,
+		  int context, char *program_counter);
 
 /* Initialize the memory lists based upon the prom version. */
 void prom_meminit(void);
@@ -111,65 +111,65 @@ void prom_meminit(void);
 /* PROM device tree traversal functions... */
 
 /* Get the child node of the given node, or zero if no child exists. */
-extern phandle prom_getchild(phandle parent_node);
+phandle prom_getchild(phandle parent_node);
 
 /* Get the next sibling node of the given node, or zero if no further
  * siblings exist.
  */
-extern phandle prom_getsibling(phandle node);
+phandle prom_getsibling(phandle node);
 
 /* Get the length, at the passed node, of the given property type.
  * Returns -1 on error (ie. no such property at this node).
  */
-extern int prom_getproplen(phandle thisnode, const char *property);
+int prom_getproplen(phandle thisnode, const char *property);
 
 /* Fetch the requested property using the given buffer.  Returns
  * the number of bytes the prom put into your buffer or -1 on error.
  */
-extern int __must_check prom_getproperty(phandle thisnode, const char *property,
-					 char *prop_buffer, int propbuf_size);
+int __must_check prom_getproperty(phandle thisnode, const char *property,
+				  char *prop_buffer, int propbuf_size);
 
 /* Acquire an integer property. */
-extern int prom_getint(phandle node, char *property);
+int prom_getint(phandle node, char *property);
 
 /* Acquire an integer property, with a default value. */
-extern int prom_getintdefault(phandle node, char *property, int defval);
+int prom_getintdefault(phandle node, char *property, int defval);
 
 /* Acquire a boolean property, 0=FALSE 1=TRUE. */
-extern int prom_getbool(phandle node, char *prop);
+int prom_getbool(phandle node, char *prop);
 
 /* Acquire a string property, null string on error. */
-extern void prom_getstring(phandle node, char *prop, char *buf, int bufsize);
+void prom_getstring(phandle node, char *prop, char *buf, int bufsize);
 
 /* Search all siblings starting at the passed node for "name" matching
  * the given string.  Returns the node on success, zero on failure.
  */
-extern phandle prom_searchsiblings(phandle node_start, char *name);
+phandle prom_searchsiblings(phandle node_start, char *name);
 
 /* Returns the next property after the passed property for the given
  * node.  Returns null string on failure.
  */
-extern char *prom_nextprop(phandle node, char *prev_property, char *buffer);
+char *prom_nextprop(phandle node, char *prev_property, char *buffer);
 
 /* Returns phandle of the path specified */
-extern phandle prom_finddevice(char *name);
+phandle prom_finddevice(char *name);
 
 /* Set the indicated property at the given node with the passed value.
  * Returns the number of bytes of your value that the prom took.
  */
-extern int prom_setprop(phandle node, const char *prop_name, char *prop_value,
-			int value_size);
+int prom_setprop(phandle node, const char *prop_name, char *prop_value,
+		 int value_size);
 
-extern phandle prom_inst2pkg(int);
+phandle prom_inst2pkg(int);
 
 /* Dorking with Bus ranges... */
 
 /* Apply promlib probes OBIO ranges to registers. */
-extern void prom_apply_obio_ranges(struct linux_prom_registers *obioregs, int nregs);
+void prom_apply_obio_ranges(struct linux_prom_registers *obioregs, int nregs);
 
 /* Apply ranges of any prom node (and optionally parent node as well) to registers. */
-extern void prom_apply_generic_ranges(phandle node, phandle parent,
-				      struct linux_prom_registers *sbusregs, int nregs);
+void prom_apply_generic_ranges(phandle node, phandle parent,
+			       struct linux_prom_registers *sbusregs, int nregs);
 
 void prom_ranges_init(void);
 
diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h
index a12dbe3b776..f34682430fc 100644
--- a/arch/sparc/include/asm/oplib_64.h
+++ b/arch/sparc/include/asm/oplib_64.h
@@ -62,100 +62,100 @@ struct linux_mem_p1275 {
 /* You must call prom_init() before using any of the library services,
  * preferably as early as possible.  Pass it the romvec pointer.
  */
-extern void prom_init(void *cif_handler, void *cif_stack);
+void prom_init(void *cif_handler, void *cif_stack);
 
 /* Boot argument acquisition, returns the boot command line string. */
-extern char *prom_getbootargs(void);
+char *prom_getbootargs(void);
 
 /* Miscellaneous routines, don't really fit in any category per se. */
 
 /* Reboot the machine with the command line passed. */
-extern void prom_reboot(const char *boot_command);
+void prom_reboot(const char *boot_command);
 
 /* Evaluate the forth string passed. */
-extern void prom_feval(const char *forth_string);
+void prom_feval(const char *forth_string);
 
 /* Enter the prom, with possibility of continuation with the 'go'
  * command in newer proms.
  */
-extern void prom_cmdline(void);
+void prom_cmdline(void);
 
 /* Enter the prom, with no chance of continuation for the stand-alone
  * which calls this.
  */
-extern void prom_halt(void) __attribute__ ((noreturn));
+void prom_halt(void) __attribute__ ((noreturn));
 
 /* Halt and power-off the machine. */
-extern void prom_halt_power_off(void) __attribute__ ((noreturn));
+void prom_halt_power_off(void) __attribute__ ((noreturn));
 
 /* Acquire the IDPROM of the root node in the prom device tree.  This
  * gets passed a buffer where you would like it stuffed.  The return value
  * is the format type of this idprom or 0xff on error.
  */
-extern unsigned char prom_get_idprom(char *idp_buffer, int idpbuf_size);
+unsigned char prom_get_idprom(char *idp_buffer, int idpbuf_size);
 
 /* Write a buffer of characters to the console. */
-extern void prom_console_write_buf(const char *buf, int len);
+void prom_console_write_buf(const char *buf, int len);
 
 /* Prom's internal routines, don't use in kernel/boot code. */
-extern __printf(1, 2) void prom_printf(const char *fmt, ...);
-extern void prom_write(const char *buf, unsigned int len);
+__printf(1, 2) void prom_printf(const char *fmt, ...);
+void prom_write(const char *buf, unsigned int len);
 
 /* Multiprocessor operations... */
 #ifdef CONFIG_SMP
 /* Start the CPU with the given device tree node at the passed program
  * counter with the given arg passed in via register %o0.
  */
-extern void prom_startcpu(int cpunode, unsigned long pc, unsigned long arg);
+void prom_startcpu(int cpunode, unsigned long pc, unsigned long arg);
 
 /* Start the CPU with the given cpu ID at the passed program
  * counter with the given arg passed in via register %o0.
  */
-extern void prom_startcpu_cpuid(int cpuid, unsigned long pc, unsigned long arg);
+void prom_startcpu_cpuid(int cpuid, unsigned long pc, unsigned long arg);
 
 /* Stop the CPU with the given cpu ID.  */
-extern void prom_stopcpu_cpuid(int cpuid);
+void prom_stopcpu_cpuid(int cpuid);
 
 /* Stop the current CPU. */
-extern void prom_stopself(void);
+void prom_stopself(void);
 
 /* Idle the current CPU. */
-extern void prom_idleself(void);
+void prom_idleself(void);
 
 /* Resume the CPU with the passed device tree node. */
-extern void prom_resumecpu(int cpunode);
+void prom_resumecpu(int cpunode);
 #endif
 
 /* Power management interfaces. */
 
 /* Put the current CPU to sleep. */
-extern void prom_sleepself(void);
+void prom_sleepself(void);
 
 /* Put the entire system to sleep. */
-extern int prom_sleepsystem(void);
+int prom_sleepsystem(void);
 
 /* Initiate a wakeup event. */
-extern int prom_wakeupsystem(void);
+int prom_wakeupsystem(void);
 
 /* MMU and memory related OBP interfaces. */
 
 /* Get unique string identifying SIMM at given physical address. */
-extern int prom_getunumber(int syndrome_code,
-			   unsigned long phys_addr,
-			   char *buf, int buflen);
+int prom_getunumber(int syndrome_code,
+		    unsigned long phys_addr,
+		    char *buf, int buflen);
 
 /* Retain physical memory to the caller across soft resets. */
-extern int prom_retain(const char *name, unsigned long size,
-		       unsigned long align, unsigned long *paddr);
+int prom_retain(const char *name, unsigned long size,
+		unsigned long align, unsigned long *paddr);
 
 /* Load explicit I/D TLB entries into the calling processor. */
-extern long prom_itlb_load(unsigned long index,
-			   unsigned long tte_data,
-			   unsigned long vaddr);
+long prom_itlb_load(unsigned long index,
+		    unsigned long tte_data,
+		    unsigned long vaddr);
 
-extern long prom_dtlb_load(unsigned long index,
-			   unsigned long tte_data,
-			   unsigned long vaddr);
+long prom_dtlb_load(unsigned long index,
+		    unsigned long tte_data,
+		    unsigned long vaddr);
 
 /* Map/Unmap client program address ranges.  First the format of
  * the mapping mode argument.
@@ -170,81 +170,81 @@ extern long prom_dtlb_load(unsigned long index,
 #define PROM_MAP_IE	0x0100 /* Invert-Endianness */
 #define PROM_MAP_DEFAULT (PROM_MAP_WRITE | PROM_MAP_READ | PROM_MAP_EXEC | PROM_MAP_CACHED)
 
-extern int prom_map(int mode, unsigned long size,
-		    unsigned long vaddr, unsigned long paddr);
-extern void prom_unmap(unsigned long size, unsigned long vaddr);
+int prom_map(int mode, unsigned long size,
+	     unsigned long vaddr, unsigned long paddr);
+void prom_unmap(unsigned long size, unsigned long vaddr);
 
 
 /* PROM device tree traversal functions... */
 
 /* Get the child node of the given node, or zero if no child exists. */
-extern phandle prom_getchild(phandle parent_node);
+phandle prom_getchild(phandle parent_node);
 
 /* Get the next sibling node of the given node, or zero if no further
  * siblings exist.
  */
-extern phandle prom_getsibling(phandle node);
+phandle prom_getsibling(phandle node);
 
 /* Get the length, at the passed node, of the given property type.
  * Returns -1 on error (ie. no such property at this node).
  */
-extern int prom_getproplen(phandle thisnode, const char *property);
+int prom_getproplen(phandle thisnode, const char *property);
 
 /* Fetch the requested property using the given buffer.  Returns
  * the number of bytes the prom put into your buffer or -1 on error.
  */
-extern int prom_getproperty(phandle thisnode, const char *property,
-			    char *prop_buffer, int propbuf_size);
+int prom_getproperty(phandle thisnode, const char *property,
+		     char *prop_buffer, int propbuf_size);
 
 /* Acquire an integer property. */
-extern int prom_getint(phandle node, const char *property);
+int prom_getint(phandle node, const char *property);
 
 /* Acquire an integer property, with a default value. */
-extern int prom_getintdefault(phandle node, const char *property, int defval);
+int prom_getintdefault(phandle node, const char *property, int defval);
 
 /* Acquire a boolean property, 0=FALSE 1=TRUE. */
-extern int prom_getbool(phandle node, const char *prop);
+int prom_getbool(phandle node, const char *prop);
 
 /* Acquire a string property, null string on error. */
-extern void prom_getstring(phandle node, const char *prop, char *buf,
-			   int bufsize);
+void prom_getstring(phandle node, const char *prop, char *buf,
+		    int bufsize);
 
 /* Does the passed node have the given "name"? YES=1 NO=0 */
-extern int prom_nodematch(phandle thisnode, const char *name);
+int prom_nodematch(phandle thisnode, const char *name);
 
 /* Search all siblings starting at the passed node for "name" matching
  * the given string.  Returns the node on success, zero on failure.
  */
-extern phandle prom_searchsiblings(phandle node_start, const char *name);
+phandle prom_searchsiblings(phandle node_start, const char *name);
 
 /* Return the first property type, as a string, for the given node.
  * Returns a null string on error. Buffer should be at least 32B long.
  */
-extern char *prom_firstprop(phandle node, char *buffer);
+char *prom_firstprop(phandle node, char *buffer);
 
 /* Returns the next property after the passed property for the given
  * node.  Returns null string on failure. Buffer should be at least 32B long.
  */
-extern char *prom_nextprop(phandle node, const char *prev_property, char *buf);
+char *prom_nextprop(phandle node, const char *prev_property, char *buf);
 
 /* Returns 1 if the specified node has given property. */
-extern int prom_node_has_property(phandle node, const char *property);
+int prom_node_has_property(phandle node, const char *property);
 
 /* Returns phandle of the path specified */
-extern phandle prom_finddevice(const char *name);
+phandle prom_finddevice(const char *name);
 
 /* Set the indicated property at the given node with the passed value.
  * Returns the number of bytes of your value that the prom took.
  */
-extern int prom_setprop(phandle node, const char *prop_name, char *prop_value,
-			int value_size);
+int prom_setprop(phandle node, const char *prop_name, char *prop_value,
+		 int value_size);
 
-extern phandle prom_inst2pkg(int);
-extern void prom_sun4v_guest_soft_state(void);
+phandle prom_inst2pkg(int);
+void prom_sun4v_guest_soft_state(void);
 
-extern int prom_ihandle2path(int handle, char *buffer, int bufsize);
+int prom_ihandle2path(int handle, char *buffer, int bufsize);
 
 /* Client interface level routines. */
-extern void p1275_cmd_direct(unsigned long *);
+void p1275_cmd_direct(unsigned long *);
 
 #endif /* !(__SPARC64_OPLIB_H) */
diff --git a/arch/sparc/include/asm/page.h b/arch/sparc/include/asm/page.h
index f21de034902..1be2fdec626 100644
--- a/arch/sparc/include/asm/page.h
+++ b/arch/sparc/include/asm/page.h
@@ -1,5 +1,8 @@
 #ifndef ___ASM_SPARC_PAGE_H
 #define ___ASM_SPARC_PAGE_H
+
+#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
+
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/page_64.h>
 #else
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index aac53fcea80..bf109984a03 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -31,17 +31,17 @@
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
 struct pt_regs;
-extern void hugetlb_setup(struct pt_regs *regs);
+void hugetlb_setup(struct pt_regs *regs);
 #endif
 
 #define WANT_PAGE_VIRTUAL
 
-extern void _clear_page(void *page);
+void _clear_page(void *page);
 #define clear_page(X)	_clear_page((void *)(X))
 struct page;
-extern void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
+void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
 #define copy_page(X,Y)	memcpy((void *)(X), (void *)(Y), PAGE_SIZE)
-extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage);
+void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage);
 
 /* Unlike sparc32, sparc64's parameter passing API is more
  * sane in that structures which as small enough are passed
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index c6c7396e762..bd00a622616 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -52,7 +52,7 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 
 /* Return the index of the PCI controller for device PDEV. */
 
-extern int pci_domain_nr(struct pci_bus *bus);
+int pci_domain_nr(struct pci_bus *bus);
 static inline int pci_proc_domain(struct pci_bus *bus)
 {
 	return 1;
@@ -64,9 +64,9 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 #define HAVE_ARCH_PCI_GET_UNMAPPED_AREA
 #define get_pci_unmapped_area get_fb_unmapped_area
 
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-			       enum pci_mmap_state mmap_state,
-			       int write_combine);
+int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+			enum pci_mmap_state mmap_state,
+			int write_combine);
 
 static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 {
@@ -74,9 +74,9 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 }
 
 #define HAVE_ARCH_PCI_RESOURCE_TO_USER
-extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
-				 const struct resource *rsrc,
-				 resource_size_t *start, resource_size_t *end);
+void pci_resource_to_user(const struct pci_dev *dev, int bar,
+			  const struct resource *rsrc,
+			  resource_size_t *start, resource_size_t *end);
 #endif /* __KERNEL__ */
 
 #endif /* __SPARC64_PCI_H */
diff --git a/arch/sparc/include/asm/pcic.h b/arch/sparc/include/asm/pcic.h
index 6676cbcc8b6..f4170679259 100644
--- a/arch/sparc/include/asm/pcic.h
+++ b/arch/sparc/include/asm/pcic.h
@@ -30,10 +30,10 @@ struct linux_pcic {
 };
 
 #ifdef CONFIG_PCIC_PCI
-extern int pcic_present(void);
-extern int pcic_probe(void);
-extern void pci_time_init(void);
-extern void sun4m_pci_init_IRQ(void);
+int pcic_present(void);
+int pcic_probe(void);
+void pci_time_init(void);
+void sun4m_pci_init_IRQ(void);
 #else
 static inline int pcic_present(void) { return 0; }
 static inline int pcic_probe(void) { return 0; }
diff --git a/arch/sparc/include/asm/pcr.h b/arch/sparc/include/asm/pcr.h
index 942bb17f60c..cdf800c3326 100644
--- a/arch/sparc/include/asm/pcr.h
+++ b/arch/sparc/include/asm/pcr.h
@@ -12,8 +12,8 @@ struct pcr_ops {
 };
 extern const struct pcr_ops *pcr_ops;
 
-extern void deferred_pcr_work_irq(int irq, struct pt_regs *regs);
-extern void schedule_deferred_pcr_work(void);
+void deferred_pcr_work_irq(int irq, struct pt_regs *regs);
+void schedule_deferred_pcr_work(void);
 
 #define PCR_PIC_PRIV		0x00000001 /* PIC access is privileged */
 #define PCR_STRACE		0x00000002 /* Trace supervisor events  */
@@ -45,6 +45,6 @@ extern void schedule_deferred_pcr_work(void);
 #define PCR_N4_PICNHT		0x00020000 /* PIC non-hypervisor trap  */
 #define PCR_N4_NTC		0x00040000 /* Next-To-Commit wrap      */
 
-extern int pcr_arch_init(void);
+int pcr_arch_init(void);
 
 #endif /* __PCR_H */
diff --git a/arch/sparc/include/asm/pgalloc_32.h b/arch/sparc/include/asm/pgalloc_32.h
index 9b1c36de0f1..a3890da9442 100644
--- a/arch/sparc/include/asm/pgalloc_32.h
+++ b/arch/sparc/include/asm/pgalloc_32.h
@@ -14,6 +14,8 @@ struct page;
 void *srmmu_get_nocache(int size, int align);
 void srmmu_free_nocache(void *addr, int size);
 
+extern struct resource sparc_iomap;
+
 #define check_pgt_cache()	do { } while (0)
 
 pgd_t *get_pgd_fast(void);
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index bcfe063bce2..39a7ac49b00 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -38,12 +38,12 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 	kmem_cache_free(pgtable_cache, pmd);
 }
 
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
-				   unsigned long address);
-extern pgtable_t pte_alloc_one(struct mm_struct *mm,
-			       unsigned long address);
-extern void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
-extern void pte_free(struct mm_struct *mm, pgtable_t ptepage);
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
+			    unsigned long address);
+pgtable_t pte_alloc_one(struct mm_struct *mm,
+			unsigned long address);
+void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
+void pte_free(struct mm_struct *mm, pgtable_t ptepage);
 
 #define pmd_populate_kernel(MM, PMD, PTE)	pmd_set(MM, PMD, PTE)
 #define pmd_populate(MM, PMD, PTE)		pmd_set(MM, PMD, PTE)
@@ -51,12 +51,12 @@ extern void pte_free(struct mm_struct *mm, pgtable_t ptepage);
 
 #define check_pgt_cache()	do { } while (0)
 
-extern void pgtable_free(void *table, bool is_page);
+void pgtable_free(void *table, bool is_page);
 
 #ifdef CONFIG_SMP
 
 struct mmu_gather;
-extern void tlb_remove_table(struct mmu_gather *, void *);
+void tlb_remove_table(struct mmu_gather *, void *);
 
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, bool is_page)
 {
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 502f632f6cc..b9b91ae19fe 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -25,8 +25,9 @@
 struct vm_area_struct;
 struct page;
 
-extern void load_mmu(void);
-extern unsigned long calc_highpages(void);
+void load_mmu(void);
+unsigned long calc_highpages(void);
+unsigned long __init bootmem_init(unsigned long *pages_avail);
 
 #define pte_ERROR(e)   __builtin_trap()
 #define pmd_ERROR(e)   __builtin_trap()
@@ -56,7 +57,7 @@ extern unsigned long calc_highpages(void);
  * srmmu.c will assign the real one (which is dynamically sized) */
 #define swapper_pg_dir NULL
 
-extern void paging_init(void);
+void paging_init(void);
 
 extern unsigned long ptr_in_current_pgd;
 
@@ -428,8 +429,8 @@ extern unsigned long *sparc_valid_addr_bitmap;
 #define GET_IOSPACE(pfn)		(pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)			(pfn & 0x0fffffffUL)
 
-extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
-			   unsigned long, pgprot_t);
+int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+		    unsigned long, pgprot_t);
 
 static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 				     unsigned long from, unsigned long pfn,
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 1a49ffdf9da..3770bf5c6e1 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -210,9 +210,9 @@ static inline bool kern_addr_valid(unsigned long addr)
 
 #ifndef __ASSEMBLY__
 
-extern pte_t mk_pte_io(unsigned long, pgprot_t, int, unsigned long);
+pte_t mk_pte_io(unsigned long, pgprot_t, int, unsigned long);
 
-extern unsigned long pte_sz_bits(unsigned long size);
+unsigned long pte_sz_bits(unsigned long size);
 
 extern pgprot_t PAGE_KERNEL;
 extern pgprot_t PAGE_KERNEL_LOCKED;
@@ -780,8 +780,8 @@ static inline int pmd_present(pmd_t pmd)
 					 !__kern_addr_valid(pud_val(pud)))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern void set_pmd_at(struct mm_struct *mm, unsigned long addr,
-		       pmd_t *pmdp, pmd_t pmd);
+void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmdp, pmd_t pmd);
 #else
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t pmd)
@@ -840,8 +840,8 @@ static inline unsigned long __pmd_page(pmd_t pmd)
 #define pte_unmap(pte)			do { } while (0)
 
 /* Actual page table PTE updates.  */
-extern void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
-			  pte_t *ptep, pte_t orig, int fullmm);
+void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
+		   pte_t *ptep, pte_t orig, int fullmm);
 
 #define __HAVE_ARCH_PMDP_GET_AND_CLEAR
 static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
@@ -900,28 +900,28 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pmd_t swapper_low_pmd_dir[PTRS_PER_PMD];
 
-extern void paging_init(void);
-extern unsigned long find_ecache_flush_span(unsigned long size);
+void paging_init(void);
+unsigned long find_ecache_flush_span(unsigned long size);
 
 struct seq_file;
-extern void mmu_info(struct seq_file *);
+void mmu_info(struct seq_file *);
 
 struct vm_area_struct;
-extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
+void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
-				 pmd_t *pmd);
+void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
+			  pmd_t *pmd);
 
 #define __HAVE_ARCH_PMDP_INVALIDATE
 extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 			    pmd_t *pmdp);
 
 #define __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				       pgtable_t pgtable);
+void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pgtable);
 
 #define __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #endif
 
 /* Encode and de-code a swap entry */
@@ -937,12 +937,12 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
 /* File offset in PTE support. */
-extern unsigned long pte_file(pte_t);
+unsigned long pte_file(pte_t);
 #define pte_to_pgoff(pte)	(pte_val(pte) >> PAGE_SHIFT)
-extern pte_t pgoff_to_pte(unsigned long);
+pte_t pgoff_to_pte(unsigned long);
 #define PTE_FILE_MAX_BITS	(64UL - PAGE_SHIFT - 1UL)
 
-extern int page_in_phys_avail(unsigned long paddr);
+int page_in_phys_avail(unsigned long paddr);
 
 /*
  * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
@@ -952,8 +952,8 @@ extern int page_in_phys_avail(unsigned long paddr);
 #define GET_IOSPACE(pfn)		(pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)			(pfn & 0x0fffffffffffffffUL)
 
-extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
-			   unsigned long, pgprot_t);
+int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+		    unsigned long, pgprot_t);
 
 static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 				     unsigned long from, unsigned long pfn,
@@ -981,20 +981,20 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
 /* We provide a special get_unmapped_area for framebuffer mmaps to try and use
  * the largest alignment possible such that larget PTEs can be used.
  */
-extern unsigned long get_fb_unmapped_area(struct file *filp, unsigned long,
-					  unsigned long, unsigned long,
-					  unsigned long);
+unsigned long get_fb_unmapped_area(struct file *filp, unsigned long,
+				   unsigned long, unsigned long,
+				   unsigned long);
 #define HAVE_ARCH_FB_UNMAPPED_AREA
 
-extern void pgtable_cache_init(void);
-extern void sun4v_register_fault_status(void);
-extern void sun4v_ktsb_register(void);
-extern void __init cheetah_ecache_flush_init(void);
-extern void sun4v_patch_tlb_handlers(void);
+void pgtable_cache_init(void);
+void sun4v_register_fault_status(void);
+void sun4v_ktsb_register(void);
+void __init cheetah_ecache_flush_init(void);
+void sun4v_patch_tlb_handlers(void);
 
 extern unsigned long cmdline_memory_size;
 
-extern asmlinkage void do_sparc64_fault(struct pt_regs *regs);
+asmlinkage void do_sparc64_fault(struct pt_regs *regs);
 
 #endif /* !(__ASSEMBLY__) */
 
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index 2c7baa4c450..812fd08f3e6 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -74,7 +74,7 @@ struct thread_struct {
 }
 
 /* Return saved PC of a blocked thread. */
-extern unsigned long thread_saved_pc(struct task_struct *t);
+unsigned long thread_saved_pc(struct task_struct *t);
 
 /* Do necessary setup to start up a newly executed thread. */
 static inline void start_thread(struct pt_regs * regs, unsigned long pc,
@@ -107,7 +107,7 @@ static inline void start_thread(struct pt_regs * regs, unsigned long pc,
 /* Free all resources held by a thread. */
 #define release_thread(tsk)		do { } while(0)
 
-extern unsigned long get_wchan(struct task_struct *);
+unsigned long get_wchan(struct task_struct *);
 
 #define task_pt_regs(tsk) ((tsk)->thread.kregs)
 #define KSTK_EIP(tsk)  ((tsk)->thread.kregs->pc)
@@ -116,8 +116,11 @@ extern unsigned long get_wchan(struct task_struct *);
 #ifdef __KERNEL__
 
 extern struct task_struct *last_task_used_math;
+int do_mathemu(struct pt_regs *regs, struct task_struct *fpt);
 
 #define cpu_relax()	barrier()
+#define cpu_relax_lowlatency() cpu_relax()
+
 extern void (*sparc_idle)(void);
 
 #endif
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 4c3f7f01c70..6924bdefe14 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -95,7 +95,7 @@ struct thread_struct {
 
 /* Return saved PC of a blocked thread. */
 struct task_struct;
-extern unsigned long thread_saved_pc(struct task_struct *);
+unsigned long thread_saved_pc(struct task_struct *);
 
 /* On Uniprocessor, even in RMO processes see TSO semantics */
 #ifdef CONFIG_SMP
@@ -194,7 +194,7 @@ do { \
 /* Free all resources held by a thread. */
 #define release_thread(tsk)		do { } while (0)
 
-extern unsigned long get_wchan(struct task_struct *task);
+unsigned long get_wchan(struct task_struct *task);
 
 #define task_pt_regs(tsk) (task_thread_info(tsk)->kregs)
 #define KSTK_EIP(tsk)  (task_pt_regs(tsk)->tpc)
@@ -216,6 +216,7 @@ extern unsigned long get_wchan(struct task_struct *task);
 				     "nop\n\t"				\
 				     ".previous"			\
 				     ::: "memory")
+#define cpu_relax_lowlatency() cpu_relax()
 
 /* Prefetch support.  This is tuned for UltraSPARC-III and later.
  * UltraSPARC-I will treat these as nops, and UltraSPARC-II has
@@ -253,6 +254,8 @@ static inline void prefetchw(const void *x)
 
 #define HAVE_ARCH_PICK_MMAP_LAYOUT
 
+int do_mathemu(struct pt_regs *regs, struct fpustate *f, bool illegal_insn_trap);
+
 #endif /* !(__ASSEMBLY__) */
 
 #endif /* !(__ASM_SPARC64_PROCESSOR_H) */
diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h
index 11ebd659e7b..d955c8df62d 100644
--- a/arch/sparc/include/asm/prom.h
+++ b/arch/sparc/include/asm/prom.h
@@ -36,28 +36,28 @@ struct of_irq_controller {
 	void		*data;
 };
 
-extern struct device_node *of_find_node_by_cpuid(int cpuid);
-extern int of_set_property(struct device_node *node, const char *name, void *val, int len);
+struct device_node *of_find_node_by_cpuid(int cpuid);
+int of_set_property(struct device_node *node, const char *name, void *val, int len);
 extern struct mutex of_set_property_mutex;
-extern int of_getintprop_default(struct device_node *np,
-				 const char *name,
+int of_getintprop_default(struct device_node *np,
+			  const char *name,
 				 int def);
-extern int of_find_in_proplist(const char *list, const char *match, int len);
+int of_find_in_proplist(const char *list, const char *match, int len);
 
-extern void prom_build_devicetree(void);
-extern void of_populate_present_mask(void);
-extern void of_fill_in_cpu_data(void);
+void prom_build_devicetree(void);
+void of_populate_present_mask(void);
+void of_fill_in_cpu_data(void);
 
 struct resource;
-extern void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name);
-extern void of_iounmap(struct resource *res, void __iomem *base, unsigned long size);
+void __iomem *of_ioremap(struct resource *res, unsigned long offset, unsigned long size, char *name);
+void of_iounmap(struct resource *res, void __iomem *base, unsigned long size);
 
 extern struct device_node *of_console_device;
 extern char *of_console_path;
 extern char *of_console_options;
 
-extern void irq_trans_init(struct device_node *dp);
-extern char *build_path_component(struct device_node *dp);
+void irq_trans_init(struct device_node *dp);
+char *build_path_component(struct device_node *dp);
 
 #endif /* __KERNEL__ */
 #endif /* _SPARC_PROM_H */
diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h
index bdfafd7af46..bac6a946ee0 100644
--- a/arch/sparc/include/asm/ptrace.h
+++ b/arch/sparc/include/asm/ptrace.h
@@ -73,7 +73,7 @@ static inline long regs_return_value(struct pt_regs *regs)
 	return regs->u_regs[UREG_I0];
 }
 #ifdef CONFIG_SMP
-extern unsigned long profile_pc(struct pt_regs *);
+unsigned long profile_pc(struct pt_regs *);
 #else
 #define profile_pc(regs) instruction_pointer(regs)
 #endif
diff --git a/arch/sparc/include/asm/setup.h b/arch/sparc/include/asm/setup.h
index 5e35e051731..f5fffd84d0d 100644
--- a/arch/sparc/include/asm/setup.h
+++ b/arch/sparc/include/asm/setup.h
@@ -4,8 +4,9 @@
 #ifndef _SPARC_SETUP_H
 #define _SPARC_SETUP_H
 
-#include <uapi/asm/setup.h>
+#include <linux/interrupt.h>
 
+#include <uapi/asm/setup.h>
 
 extern char reboot_command[];
 
@@ -22,9 +23,43 @@ static inline int con_is_present(void)
 {
 	return serial_console ? 0 : 1;
 }
+
+/* from irq_32.c */
+extern volatile unsigned char *fdc_status;
+extern char *pdma_vaddr;
+extern unsigned long pdma_size;
+extern volatile int doing_pdma;
+
+/* This is software state */
+extern char *pdma_base;
+extern unsigned long pdma_areasize;
+
+int sparc_floppy_request_irq(unsigned int irq, irq_handler_t irq_handler);
+
+/* setup_32.c */
+extern unsigned long cmdline_memory_size;
+
+/* devices.c */
+void __init device_scan(void);
+
+/* unaligned_32.c */
+unsigned long safe_compute_effective_address(struct pt_regs *, unsigned int);
+
+#endif
+
+#ifdef CONFIG_SPARC64
+/* unaligned_64.c */
+int handle_ldf_stq(u32 insn, struct pt_regs *regs);
+void handle_ld_nf(u32 insn, struct pt_regs *regs);
+
+/* init_64.c */
+extern atomic_t dcpage_flushes;
+extern atomic_t dcpage_flushes_xcall;
+
+extern int sysctl_tsb_ratio;
 #endif
 
-extern void sun_do_break(void);
+void sun_do_break(void);
 extern int stop_a_enabled;
 extern int scons_pwroff;
 
diff --git a/arch/sparc/include/asm/sfp-machine_32.h b/arch/sparc/include/asm/sfp-machine_32.h
index 01d9c3b5a73..838c9d58f3b 100644
--- a/arch/sparc/include/asm/sfp-machine_32.h
+++ b/arch/sparc/include/asm/sfp-machine_32.h
@@ -79,9 +79,9 @@
   __asm__ ("addcc %r7,%8,%2\n\t"					\
 	   "addxcc %r5,%6,%1\n\t"					\
 	   "addx %r3,%4,%0\n"						\
-	   : "=r" ((USItype)(r2)),					\
-	     "=&r" ((USItype)(r1)),					\
-	     "=&r" ((USItype)(r0))					\
+	   : "=r" (r2),							\
+	     "=&r" (r1),						\
+	     "=&r" (r0)							\
 	   : "%rJ" ((USItype)(x2)),					\
 	     "rI" ((USItype)(y2)),					\
 	     "%rJ" ((USItype)(x1)),					\
@@ -94,9 +94,9 @@
   __asm__ ("subcc %r7,%8,%2\n\t"					\
 	    "subxcc %r5,%6,%1\n\t"					\
 	    "subx %r3,%4,%0\n"						\
-	   : "=r" ((USItype)(r2)),					\
-	     "=&r" ((USItype)(r1)),					\
-	     "=&r" ((USItype)(r0))					\
+	   : "=r" (r2),							\
+	     "=&r" (r1),						\
+	     "=&r" (r0)							\
 	   : "%rJ" ((USItype)(x2)),					\
 	     "rI" ((USItype)(y2)),					\
 	     "%rJ" ((USItype)(x1)),					\
@@ -115,8 +115,8 @@
 	    "addxcc %r6,%7,%0\n\t"					\
 	    "addxcc %r4,%5,%%g2\n\t"					\
 	    "addx %r2,%3,%%g1\n\t"					\
-	   : "=&r" ((USItype)(r1)),					\
-	     "=&r" ((USItype)(r0))					\
+	   : "=&r" (r1),						\
+	     "=&r" (r0)							\
 	   : "%rJ" ((USItype)(x3)),					\
 	     "rI" ((USItype)(y3)),					\
 	     "%rJ" ((USItype)(x2)),					\
@@ -140,8 +140,8 @@
 	    "subxcc %r6,%7,%0\n\t"					\
 	    "subxcc %r4,%5,%%g2\n\t"					\
 	    "subx %r2,%3,%%g1\n\t"					\
-	   : "=&r" ((USItype)(r1)),					\
-	     "=&r" ((USItype)(r0))					\
+	   : "=&r" (r1),						\
+	     "=&r" (r0)							\
 	   : "%rJ" ((USItype)(x3)),					\
 	     "rI" ((USItype)(y3)),					\
 	     "%rJ" ((USItype)(x2)),					\
@@ -164,10 +164,10 @@
 	   "addxcc %2,%%g0,%2\n\t"					\
 	   "addxcc %1,%%g0,%1\n\t"					\
 	   "addx %0,%%g0,%0\n\t"					\
-	   : "=&r" ((USItype)(x3)),					\
-	     "=&r" ((USItype)(x2)),					\
-	     "=&r" ((USItype)(x1)),					\
-	     "=&r" ((USItype)(x0))					\
+	   : "=&r" (x3),						\
+	     "=&r" (x2),						\
+	     "=&r" (x1),						\
+	     "=&r" (x0)							\
 	   : "rI" ((USItype)(i)),					\
 	     "0" ((USItype)(x3)),					\
 	     "1" ((USItype)(x2)),					\
diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h
index 3c8917f054d..7c24e08a88d 100644
--- a/arch/sparc/include/asm/smp_32.h
+++ b/arch/sparc/include/asm/smp_32.h
@@ -93,15 +93,15 @@ static inline void xc4(smpfunc_t func, unsigned long arg1, unsigned long arg2,
 				    arg1, arg2, arg3, arg4);
 }
 
-extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+void arch_send_call_function_single_ipi(int cpu);
+void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 static inline int cpu_logical_map(int cpu)
 {
 	return cpu;
 }
 
-extern int hard_smp_processor_id(void);
+int hard_smp_processor_id(void);
 
 #define raw_smp_processor_id()		(current_thread_info()->cpu)
 
diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h
index 05710393959..26d9e772686 100644
--- a/arch/sparc/include/asm/smp_64.h
+++ b/arch/sparc/include/asm/smp_64.h
@@ -33,29 +33,35 @@
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 extern cpumask_t cpu_core_map[NR_CPUS];
 
-extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+void arch_send_call_function_single_ipi(int cpu);
+void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 /*
  *	General functions that each host system must provide.
  */
 
-extern int hard_smp_processor_id(void);
+int hard_smp_processor_id(void);
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
-extern void smp_fill_in_sib_core_maps(void);
-extern void cpu_play_dead(void);
+void smp_fill_in_sib_core_maps(void);
+void cpu_play_dead(void);
 
-extern void smp_fetch_global_regs(void);
-extern void smp_fetch_global_pmu(void);
+void smp_fetch_global_regs(void);
+void smp_fetch_global_pmu(void);
 
 struct seq_file;
 void smp_bogo(struct seq_file *);
 void smp_info(struct seq_file *);
 
+void smp_callin(void);
+void cpu_panic(void);
+void smp_synchronize_tick_client(void);
+void smp_capture(void);
+void smp_release(void);
+
 #ifdef CONFIG_HOTPLUG_CPU
-extern int __cpu_disable(void);
-extern void __cpu_die(unsigned int cpu);
+int __cpu_disable(void);
+void __cpu_die(unsigned int cpu);
 #endif
 
 #endif /* !(__ASSEMBLY__) */
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index 6b67e50fb9b..3fc58691dbd 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -62,7 +62,7 @@ extern enum ultra_tlb_layout tlb_type;
 extern int sun4v_chip_type;
 
 extern int cheetah_pcache_forced_on;
-extern void cheetah_enable_pcache(void);
+void cheetah_enable_pcache(void);
 
 #define sparc64_highest_locked_tlbent()	\
 	(tlb_type == spitfire ? \
diff --git a/arch/sparc/include/asm/stacktrace.h b/arch/sparc/include/asm/stacktrace.h
index 6cee39adf6d..c30d066f304 100644
--- a/arch/sparc/include/asm/stacktrace.h
+++ b/arch/sparc/include/asm/stacktrace.h
@@ -1,6 +1,6 @@
 #ifndef _SPARC64_STACKTRACE_H
 #define _SPARC64_STACKTRACE_H
 
-extern void stack_trace_flush(void);
+void stack_trace_flush(void);
 
 #endif /* _SPARC64_STACKTRACE_H */
diff --git a/arch/sparc/include/asm/starfire.h b/arch/sparc/include/asm/starfire.h
index d56ce60a599..c100dc27a0a 100644
--- a/arch/sparc/include/asm/starfire.h
+++ b/arch/sparc/include/asm/starfire.h
@@ -11,10 +11,10 @@
 
 extern int this_is_starfire;
 
-extern void check_if_starfire(void);
-extern int starfire_hard_smp_processor_id(void);
-extern void starfire_hookup(int);
-extern unsigned int starfire_translate(unsigned long imap, unsigned int upaid);
+void check_if_starfire(void);
+int starfire_hard_smp_processor_id(void);
+void starfire_hookup(int);
+unsigned int starfire_translate(unsigned long imap, unsigned int upaid);
 
 #endif
 #endif
diff --git a/arch/sparc/include/asm/string_32.h b/arch/sparc/include/asm/string_32.h
index 12f67857152..69974e92461 100644
--- a/arch/sparc/include/asm/string_32.h
+++ b/arch/sparc/include/asm/string_32.h
@@ -15,7 +15,7 @@
 
 #ifdef __KERNEL__
 
-extern void __memmove(void *,const void *,__kernel_size_t);
+void __memmove(void *,const void *,__kernel_size_t);
 
 #ifndef EXPORT_SYMTAB_STROPS
 
@@ -40,8 +40,8 @@ extern void __memmove(void *,const void *,__kernel_size_t);
 #undef memscan
 #define memscan(__arg0, __char, __arg2)						\
 ({										\
-	extern void *__memscan_zero(void *, size_t);				\
-	extern void *__memscan_generic(void *, int, size_t);			\
+	void *__memscan_zero(void *, size_t);					\
+	void *__memscan_generic(void *, int, size_t);				\
 	void *__retval, *__addr = (__arg0);					\
 	size_t __size = (__arg2);						\
 										\
@@ -54,14 +54,14 @@ extern void __memmove(void *,const void *,__kernel_size_t);
 })
 
 #define __HAVE_ARCH_MEMCMP
-extern int memcmp(const void *,const void *,__kernel_size_t);
+int memcmp(const void *,const void *,__kernel_size_t);
 
 /* Now the str*() stuff... */
 #define __HAVE_ARCH_STRLEN
-extern __kernel_size_t strlen(const char *);
+__kernel_size_t strlen(const char *);
 
 #define __HAVE_ARCH_STRNCMP
-extern int strncmp(const char *, const char *, __kernel_size_t);
+int strncmp(const char *, const char *, __kernel_size_t);
 
 #endif /* !EXPORT_SYMTAB_STROPS */
 
diff --git a/arch/sparc/include/asm/string_64.h b/arch/sparc/include/asm/string_64.h
index 9623bc21315..5936b8ff3c0 100644
--- a/arch/sparc/include/asm/string_64.h
+++ b/arch/sparc/include/asm/string_64.h
@@ -19,7 +19,7 @@
 
 /* First the mem*() things. */
 #define __HAVE_ARCH_MEMMOVE
-extern void *memmove(void *, const void *, __kernel_size_t);
+void *memmove(void *, const void *, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMCPY
 #define memcpy(t, f, n) __builtin_memcpy(t, f, n)
@@ -32,8 +32,8 @@ extern void *memmove(void *, const void *, __kernel_size_t);
 #undef memscan
 #define memscan(__arg0, __char, __arg2)					\
 ({									\
-	extern void *__memscan_zero(void *, size_t);			\
-	extern void *__memscan_generic(void *, int, size_t);		\
+	void *__memscan_zero(void *, size_t);				\
+	void *__memscan_generic(void *, int, size_t);			\
 	void *__retval, *__addr = (__arg0);				\
 	size_t __size = (__arg2);					\
 									\
@@ -46,14 +46,14 @@ extern void *memmove(void *, const void *, __kernel_size_t);
 })
 
 #define __HAVE_ARCH_MEMCMP
-extern int memcmp(const void *,const void *,__kernel_size_t);
+int memcmp(const void *,const void *,__kernel_size_t);
 
 /* Now the str*() stuff... */
 #define __HAVE_ARCH_STRLEN
-extern __kernel_size_t strlen(const char *);
+__kernel_size_t strlen(const char *);
 
 #define __HAVE_ARCH_STRNCMP
-extern int strncmp(const char *, const char *, __kernel_size_t);
+int strncmp(const char *, const char *, __kernel_size_t);
 
 #endif /* !EXPORT_SYMTAB_STROPS */
 
diff --git a/arch/sparc/include/asm/switch_to_32.h b/arch/sparc/include/asm/switch_to_32.h
index e32e82b76ee..16f10374feb 100644
--- a/arch/sparc/include/asm/switch_to_32.h
+++ b/arch/sparc/include/asm/switch_to_32.h
@@ -99,8 +99,8 @@ extern struct thread_info *current_set[NR_CPUS];
 	  "o0", "o1", "o2", "o3",                   "o7");	\
 	} while(0)
 
-extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
-		   void *fpqueue, unsigned long *fpqdepth);
-extern void synchronize_user_stack(void);
+void fpsave(unsigned long *fpregs, unsigned long *fsr,
+	    void *fpqueue, unsigned long *fpqdepth);
+void synchronize_user_stack(void);
 
 #endif /* __SPARC_SWITCH_TO_H */
diff --git a/arch/sparc/include/asm/switch_to_64.h b/arch/sparc/include/asm/switch_to_64.h
index 8d284801f23..10e76332dc9 100644
--- a/arch/sparc/include/asm/switch_to_64.h
+++ b/arch/sparc/include/asm/switch_to_64.h
@@ -65,7 +65,7 @@ do {	save_and_clear_fpu();						\
 	  "o0", "o1", "o2", "o3", "o4", "o5",       "o7");		\
 } while(0)
 
-extern void synchronize_user_stack(void);
-extern void fault_in_user_windows(void);
+void synchronize_user_stack(void);
+void fault_in_user_windows(void);
 
 #endif /* __SPARC64_SWITCH_TO_64_H */
diff --git a/arch/sparc/include/asm/syscalls.h b/arch/sparc/include/asm/syscalls.h
index bf8972adea1..b0a0db8ea61 100644
--- a/arch/sparc/include/asm/syscalls.h
+++ b/arch/sparc/include/asm/syscalls.h
@@ -3,9 +3,9 @@
 
 struct pt_regs;
 
-extern asmlinkage long sparc_do_fork(unsigned long clone_flags,
-				     unsigned long stack_start,
-				     struct pt_regs *regs,
-				     unsigned long stack_size);
+asmlinkage long sparc_do_fork(unsigned long clone_flags,
+			      unsigned long stack_start,
+			      struct pt_regs *regs,
+			      unsigned long stack_size);
 
 #endif /* _SPARC64_SYSCALLS_H */
diff --git a/arch/sparc/include/asm/timer_32.h b/arch/sparc/include/asm/timer_32.h
index 72f40a546de..f8e708a0aa5 100644
--- a/arch/sparc/include/asm/timer_32.h
+++ b/arch/sparc/include/asm/timer_32.h
@@ -32,13 +32,13 @@ static inline unsigned int timer_value(unsigned int value)
 	return (value + 1) << TIMER_VALUE_SHIFT;
 }
 
-extern __volatile__ unsigned int *master_l10_counter;
+extern volatile u32 __iomem *master_l10_counter;
 
-extern irqreturn_t notrace timer_interrupt(int dummy, void *dev_id);
+irqreturn_t notrace timer_interrupt(int dummy, void *dev_id);
 
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU(struct clock_event_device, sparc32_clockevent);
-extern void register_percpu_ce(int cpu);
+void register_percpu_ce(int cpu);
 #endif
 
 #endif /* !(_SPARC_TIMER_H) */
diff --git a/arch/sparc/include/asm/timer_64.h b/arch/sparc/include/asm/timer_64.h
index 01197d8215c..fce41503400 100644
--- a/arch/sparc/include/asm/timer_64.h
+++ b/arch/sparc/include/asm/timer_64.h
@@ -23,8 +23,8 @@ struct sparc64_tick_ops {
 
 extern struct sparc64_tick_ops *tick_ops;
 
-extern unsigned long sparc64_get_clock_tick(unsigned int cpu);
-extern void setup_sparc64_timer(void);
-extern void __init time_init(void);
+unsigned long sparc64_get_clock_tick(unsigned int cpu);
+void setup_sparc64_timer(void);
+void __init time_init(void);
 
 #endif /* _SPARC64_TIMER_H */
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index 190e18913cc..4cb392f75d2 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -8,19 +8,19 @@
 #include <asm/mmu_context.h>
 
 #ifdef CONFIG_SMP
-extern void smp_flush_tlb_pending(struct mm_struct *,
+void smp_flush_tlb_pending(struct mm_struct *,
 				  unsigned long, unsigned long *);
 #endif
 
 #ifdef CONFIG_SMP
-extern void smp_flush_tlb_mm(struct mm_struct *mm);
+void smp_flush_tlb_mm(struct mm_struct *mm);
 #define do_flush_tlb_mm(mm) smp_flush_tlb_mm(mm)
 #else
 #define do_flush_tlb_mm(mm) __flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT)
 #endif
 
-extern void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
-extern void flush_tlb_pending(void);
+void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
+void flush_tlb_pending(void);
 
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h
index 3c3c89f5264..816d8202fa0 100644
--- a/arch/sparc/include/asm/tlbflush_64.h
+++ b/arch/sparc/include/asm/tlbflush_64.h
@@ -14,9 +14,9 @@ struct tlb_batch {
 	unsigned long vaddrs[TLB_BATCH_NR];
 };
 
-extern void flush_tsb_kernel_range(unsigned long start, unsigned long end);
-extern void flush_tsb_user(struct tlb_batch *tb);
-extern void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
+void flush_tsb_kernel_range(unsigned long start, unsigned long end);
+void flush_tsb_user(struct tlb_batch *tb);
+void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr);
 
 /* TLB flush operations. */
 
@@ -36,15 +36,15 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 
 #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
 
-extern void flush_tlb_pending(void);
-extern void arch_enter_lazy_mmu_mode(void);
-extern void arch_leave_lazy_mmu_mode(void);
+void flush_tlb_pending(void);
+void arch_enter_lazy_mmu_mode(void);
+void arch_leave_lazy_mmu_mode(void);
 #define arch_flush_lazy_mmu_mode()      do {} while (0)
 
 /* Local cpu only.  */
-extern void __flush_tlb_all(void);
-extern void __flush_tlb_page(unsigned long context, unsigned long vaddr);
-extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void __flush_tlb_all(void);
+void __flush_tlb_page(unsigned long context, unsigned long vaddr);
+void __flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #ifndef CONFIG_SMP
 
@@ -60,8 +60,8 @@ static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vad
 
 #else /* CONFIG_SMP */
 
-extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
-extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
+void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr);
 
 #define flush_tlb_kernel_range(start, end) \
 do {	flush_tsb_kernel_range(start,end); \
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index a2d10fc64fa..ed8f071132e 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -18,7 +18,7 @@ static inline int cpu_to_node(int cpu)
 
 struct pci_bus;
 #ifdef CONFIG_PCI
-extern int pcibus_to_node(struct pci_bus *pbus);
+int pcibus_to_node(struct pci_bus *pbus);
 #else
 static inline int pcibus_to_node(struct pci_bus *pbus)
 {
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index 7e26b2db621..6fd4436d32f 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -51,11 +51,11 @@ struct trap_per_cpu {
 	unsigned long		__per_cpu_base;
 } __attribute__((aligned(64)));
 extern struct trap_per_cpu trap_block[NR_CPUS];
-extern void init_cur_cpu_trap(struct thread_info *);
-extern void setup_tba(void);
+void init_cur_cpu_trap(struct thread_info *);
+void setup_tba(void);
 extern int ncpus_probed;
 
-extern unsigned long real_hard_smp_processor_id(void);
+unsigned long real_hard_smp_processor_id(void);
 
 struct cpuid_patch_entry {
 	unsigned int	addr;
diff --git a/arch/sparc/include/asm/uaccess.h b/arch/sparc/include/asm/uaccess.h
index 0167d26d0d1..bd56c28fff9 100644
--- a/arch/sparc/include/asm/uaccess.h
+++ b/arch/sparc/include/asm/uaccess.h
@@ -9,6 +9,6 @@
 #define user_addr_max() \
 	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
 
-extern long strncpy_from_user(char *dest, const char __user *src, long count);
+long strncpy_from_user(char *dest, const char __user *src, long count);
 
 #endif
diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h
index 53a28dd59f5..9634d086fc5 100644
--- a/arch/sparc/include/asm/uaccess_32.h
+++ b/arch/sparc/include/asm/uaccess_32.h
@@ -78,9 +78,9 @@ struct exception_table_entry
 };
 
 /* Returns 0 if exception not found and fixup otherwise.  */
-extern unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
+unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
 
-extern void __ret_efault(void);
+void __ret_efault(void);
 
 /* Uh, these should become the main single-value transfer routines..
  * They automatically use the right size if we just have the right
@@ -152,7 +152,7 @@ __asm__ __volatile__(							\
        : "=&r" (ret) : "r" (x), "m" (*__m(addr)),			\
 	 "i" (-EFAULT))
 
-extern int __put_user_bad(void);
+int __put_user_bad(void);
 
 #define __get_user_check(x,addr,size,type) ({ \
 register int __gu_ret; \
@@ -244,9 +244,9 @@ __asm__ __volatile__(							\
 	".previous\n\t"							\
        : "=&r" (x) : "m" (*__m(addr)), "i" (retval))
 
-extern int __get_user_bad(void);
+int __get_user_bad(void);
 
-extern unsigned long __copy_user(void __user *to, const void __user *from, unsigned long size);
+unsigned long __copy_user(void __user *to, const void __user *from, unsigned long size);
 
 static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
 {
@@ -306,8 +306,8 @@ static inline unsigned long clear_user(void __user *addr, unsigned long n)
 		return n;
 }
 
-extern __must_check long strlen_user(const char __user *str);
-extern __must_check long strnlen_user(const char __user *str, long n);
+__must_check long strlen_user(const char __user *str);
+__must_check long strnlen_user(const char __user *str, long n);
 
 #endif  /* __ASSEMBLY__ */
 
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index ad7e178337f..c990a5e577f 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -76,8 +76,8 @@ struct exception_table_entry {
         unsigned int insn, fixup;
 };
 
-extern void __ret_efault(void);
-extern void __retl_efault(void);
+void __ret_efault(void);
+void __retl_efault(void);
 
 /* Uh, these should become the main single-value transfer routines..
  * They automatically use the right size if we just have the right
@@ -134,7 +134,7 @@ __asm__ __volatile__(							\
        : "=r" (ret) : "r" (x), "r" (__m(addr)),				\
 	 "i" (-EFAULT))
 
-extern int __put_user_bad(void);
+int __put_user_bad(void);
 
 #define __get_user_nocheck(data,addr,size,type) ({ \
 register int __gu_ret; \
@@ -204,13 +204,13 @@ __asm__ __volatile__(							\
 	".previous\n\t"							\
        : "=r" (x) : "r" (__m(addr)), "i" (retval))
 
-extern int __get_user_bad(void);
+int __get_user_bad(void);
 
-extern unsigned long __must_check ___copy_from_user(void *to,
-						    const void __user *from,
-						    unsigned long size);
-extern unsigned long copy_from_user_fixup(void *to, const void __user *from,
-					  unsigned long size);
+unsigned long __must_check ___copy_from_user(void *to,
+					     const void __user *from,
+					     unsigned long size);
+unsigned long copy_from_user_fixup(void *to, const void __user *from,
+				   unsigned long size);
 static inline unsigned long __must_check
 copy_from_user(void *to, const void __user *from, unsigned long size)
 {
@@ -223,11 +223,11 @@ copy_from_user(void *to, const void __user *from, unsigned long size)
 }
 #define __copy_from_user copy_from_user
 
-extern unsigned long __must_check ___copy_to_user(void __user *to,
-						  const void *from,
-						  unsigned long size);
-extern unsigned long copy_to_user_fixup(void __user *to, const void *from,
-					unsigned long size);
+unsigned long __must_check ___copy_to_user(void __user *to,
+					   const void *from,
+					   unsigned long size);
+unsigned long copy_to_user_fixup(void __user *to, const void *from,
+				 unsigned long size);
 static inline unsigned long __must_check
 copy_to_user(void __user *to, const void *from, unsigned long size)
 {
@@ -239,11 +239,11 @@ copy_to_user(void __user *to, const void *from, unsigned long size)
 }
 #define __copy_to_user copy_to_user
 
-extern unsigned long __must_check ___copy_in_user(void __user *to,
-						  const void __user *from,
-						  unsigned long size);
-extern unsigned long copy_in_user_fixup(void __user *to, void __user *from,
-					unsigned long size);
+unsigned long __must_check ___copy_in_user(void __user *to,
+					   const void __user *from,
+					   unsigned long size);
+unsigned long copy_in_user_fixup(void __user *to, void __user *from,
+				 unsigned long size);
 static inline unsigned long __must_check
 copy_in_user(void __user *to, void __user *from, unsigned long size)
 {
@@ -255,20 +255,20 @@ copy_in_user(void __user *to, void __user *from, unsigned long size)
 }
 #define __copy_in_user copy_in_user
 
-extern unsigned long __must_check __clear_user(void __user *, unsigned long);
+unsigned long __must_check __clear_user(void __user *, unsigned long);
 
 #define clear_user __clear_user
 
-extern __must_check long strlen_user(const char __user *str);
-extern __must_check long strnlen_user(const char __user *str, long n);
+__must_check long strlen_user(const char __user *str);
+__must_check long strnlen_user(const char __user *str, long n);
 
 #define __copy_to_user_inatomic __copy_to_user
 #define __copy_from_user_inatomic __copy_from_user
 
 struct pt_regs;
-extern unsigned long compute_effective_address(struct pt_regs *,
-					       unsigned int insn,
-					       unsigned int rd);
+unsigned long compute_effective_address(struct pt_regs *,
+					unsigned int insn,
+					unsigned int rd);
 
 #endif  /* __ASSEMBLY__ */
 
diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 432afa83886..e0f6c399f1d 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -372,14 +372,14 @@ do {	if (vio->debug & VIO_DEBUG_##TYPE) \
 		       vio->vdev->channel_id, ## a); \
 } while (0)
 
-extern int __vio_register_driver(struct vio_driver *drv, struct module *owner,
+int __vio_register_driver(struct vio_driver *drv, struct module *owner,
 				 const char *mod_name);
 /*
  * vio_register_driver must be a macro so that KBUILD_MODNAME can be expanded
  */
 #define vio_register_driver(driver)		\
 	__vio_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)
-extern void vio_unregister_driver(struct vio_driver *drv);
+void vio_unregister_driver(struct vio_driver *drv);
 
 static inline struct vio_driver *to_vio_driver(struct device_driver *drv)
 {
@@ -391,21 +391,21 @@ static inline struct vio_dev *to_vio_dev(struct device *dev)
 	return container_of(dev, struct vio_dev, dev);
 }
 
-extern int vio_ldc_send(struct vio_driver_state *vio, void *data, int len);
-extern void vio_link_state_change(struct vio_driver_state *vio, int event);
-extern void vio_conn_reset(struct vio_driver_state *vio);
-extern int vio_control_pkt_engine(struct vio_driver_state *vio, void *pkt);
-extern int vio_validate_sid(struct vio_driver_state *vio,
-			    struct vio_msg_tag *tp);
-extern u32 vio_send_sid(struct vio_driver_state *vio);
-extern int vio_ldc_alloc(struct vio_driver_state *vio,
-			 struct ldc_channel_config *base_cfg, void *event_arg);
-extern void vio_ldc_free(struct vio_driver_state *vio);
-extern int vio_driver_init(struct vio_driver_state *vio, struct vio_dev *vdev,
-			   u8 dev_class, struct vio_version *ver_table,
-			   int ver_table_size, struct vio_driver_ops *ops,
-			   char *name);
-
-extern void vio_port_up(struct vio_driver_state *vio);
+int vio_ldc_send(struct vio_driver_state *vio, void *data, int len);
+void vio_link_state_change(struct vio_driver_state *vio, int event);
+void vio_conn_reset(struct vio_driver_state *vio);
+int vio_control_pkt_engine(struct vio_driver_state *vio, void *pkt);
+int vio_validate_sid(struct vio_driver_state *vio,
+		     struct vio_msg_tag *tp);
+u32 vio_send_sid(struct vio_driver_state *vio);
+int vio_ldc_alloc(struct vio_driver_state *vio,
+		  struct ldc_channel_config *base_cfg, void *event_arg);
+void vio_ldc_free(struct vio_driver_state *vio);
+int vio_driver_init(struct vio_driver_state *vio, struct vio_dev *vdev,
+		    u8 dev_class, struct vio_version *ver_table,
+		    int ver_table_size, struct vio_driver_ops *ops,
+		    char *name);
+
+void vio_port_up(struct vio_driver_state *vio);
 
 #endif /* _SPARC64_VIO_H */
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 39ca301920d..b2667375928 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -57,7 +57,8 @@ static inline void save_and_clear_fpu(void) {
 "		" : : "i" (FPRS_FEF|FPRS_DU) :
 		"o5", "g1", "g2", "g3", "g7", "cc");
 }
-extern int vis_emul(struct pt_regs *, unsigned int);
+
+int vis_emul(struct pt_regs *, unsigned int);
 #endif
 
 #endif /* _SPARC64_ASI_H */
diff --git a/arch/sparc/include/asm/xor_64.h b/arch/sparc/include/asm/xor_64.h
index ee8edc68423..50c88285603 100644
--- a/arch/sparc/include/asm/xor_64.h
+++ b/arch/sparc/include/asm/xor_64.h
@@ -20,13 +20,13 @@
 
 #include <asm/spitfire.h>
 
-extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
-extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
-		      unsigned long *);
-extern void xor_vis_4(unsigned long, unsigned long *, unsigned long *,
-		      unsigned long *, unsigned long *);
-extern void xor_vis_5(unsigned long, unsigned long *, unsigned long *,
-		      unsigned long *, unsigned long *, unsigned long *);
+void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
+void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
+	       unsigned long *);
+void xor_vis_4(unsigned long, unsigned long *, unsigned long *,
+	       unsigned long *, unsigned long *);
+void xor_vis_5(unsigned long, unsigned long *, unsigned long *,
+	       unsigned long *, unsigned long *, unsigned long *);
 
 /* XXX Ugh, write cheetah versions... -DaveM */
 
@@ -38,13 +38,13 @@ static struct xor_block_template xor_block_VIS = {
         .do_5	= xor_vis_5,
 };
 
-extern void xor_niagara_2(unsigned long, unsigned long *, unsigned long *);
-extern void xor_niagara_3(unsigned long, unsigned long *, unsigned long *,
-			  unsigned long *);
-extern void xor_niagara_4(unsigned long, unsigned long *, unsigned long *,
-			  unsigned long *, unsigned long *);
-extern void xor_niagara_5(unsigned long, unsigned long *, unsigned long *,
-			  unsigned long *, unsigned long *, unsigned long *);
+void xor_niagara_2(unsigned long, unsigned long *, unsigned long *);
+void xor_niagara_3(unsigned long, unsigned long *, unsigned long *,
+		   unsigned long *);
+void xor_niagara_4(unsigned long, unsigned long *, unsigned long *,
+		   unsigned long *, unsigned long *);
+void xor_niagara_5(unsigned long, unsigned long *, unsigned long *,
+		   unsigned long *, unsigned long *, unsigned long *);
 
 static struct xor_block_template xor_block_niagara = {
         .name	= "Niagara",
diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h
index b73274fb961..42f2bca1d33 100644
--- a/arch/sparc/include/uapi/asm/unistd.h
+++ b/arch/sparc/include/uapi/asm/unistd.h
@@ -410,8 +410,9 @@
 #define __NR_finit_module	342
 #define __NR_sched_setattr	343
 #define __NR_sched_getattr	344
+#define __NR_renameat2		345
 
-#define NR_syscalls		345
+#define NR_syscalls		346
 
 /* Bitmask values returned from kern_features system call.  */
 #define KERN_FEATURE_MIXED_MODE_STACK	0x00000001
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index d15cc1794b0..7cf9c6ea3f1 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -42,7 +42,6 @@ obj-y                   += time_$(BITS).o
 obj-$(CONFIG_SPARC32)   += windows.o
 obj-y                   += cpu.o
 obj-$(CONFIG_SPARC32)   += devices.o
-obj-$(CONFIG_SPARC32)   += tadpole.o
 obj-y                   += ptrace_$(BITS).o
 obj-y                   += unaligned_$(BITS).o
 obj-y                   += una_asm_$(BITS).o
diff --git a/arch/sparc/kernel/audit.c b/arch/sparc/kernel/audit.c
index 8fff0ac63d5..24361b494a9 100644
--- a/arch/sparc/kernel/audit.c
+++ b/arch/sparc/kernel/audit.c
@@ -3,6 +3,8 @@
 #include <linux/audit.h>
 #include <asm/unistd.h>
 
+#include "kernel.h"
+
 static unsigned dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
 ~0U
@@ -40,7 +42,6 @@ int audit_classify_arch(int arch)
 int audit_classify_syscall(int abi, unsigned syscall)
 {
 #ifdef CONFIG_COMPAT
-	extern int sparc32_classify_syscall(unsigned);
 	if (abi == AUDIT_ARCH_SPARC)
 		return sparc32_classify_syscall(syscall);
 #endif
@@ -61,11 +62,6 @@ int audit_classify_syscall(int abi, unsigned syscall)
 static int __init audit_classes_init(void)
 {
 #ifdef CONFIG_COMPAT
-	extern __u32 sparc32_dir_class[];
-	extern __u32 sparc32_write_class[];
-	extern __u32 sparc32_read_class[];
-	extern __u32 sparc32_chattr_class[];
-	extern __u32 sparc32_signal_class[];
 	audit_register_class(AUDIT_CLASS_WRITE_32, sparc32_write_class);
 	audit_register_class(AUDIT_CLASS_READ_32, sparc32_read_class);
 	audit_register_class(AUDIT_CLASS_DIR_WRITE_32, sparc32_dir_class);
diff --git a/arch/sparc/kernel/auxio_32.c b/arch/sparc/kernel/auxio_32.c
index e20cc55fb76..ae88c223e4d 100644
--- a/arch/sparc/kernel/auxio_32.c
+++ b/arch/sparc/kernel/auxio_32.c
@@ -9,12 +9,15 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/export.h>
+
 #include <asm/oplib.h>
 #include <asm/io.h>
 #include <asm/auxio.h>
 #include <asm/string.h>		/* memset(), Linux has no bzero() */
 #include <asm/cpu_type.h>
 
+#include "kernel.h"
+
 /* Probe and map in the Auxiliary I/O register */
 
 /* auxio_register is not static because it is referenced 
@@ -103,7 +106,7 @@ EXPORT_SYMBOL(set_auxio);
 
 /* sun4m power control register (AUXIO2) */
 
-volatile unsigned char * auxio_power_register = NULL;
+volatile u8 __iomem *auxio_power_register = NULL;
 
 void __init auxio_power_probe(void)
 {
@@ -127,8 +130,8 @@ void __init auxio_power_probe(void)
 	r.flags = regs.which_io & 0xF;
 	r.start = regs.phys_addr;
 	r.end = regs.phys_addr + regs.reg_size - 1;
-	auxio_power_register = (unsigned char *) of_ioremap(&r, 0,
-	    regs.reg_size, "auxpower");
+	auxio_power_register =
+		(u8 __iomem *)of_ioremap(&r, 0, regs.reg_size, "auxpower");
 
 	/* Display a quick message on the console. */
 	if (auxio_power_register)
diff --git a/arch/sparc/kernel/btext.c b/arch/sparc/kernel/btext.c
index 57073e56ba9..987f7ec497c 100644
--- a/arch/sparc/kernel/btext.c
+++ b/arch/sparc/kernel/btext.c
@@ -137,7 +137,7 @@ static void scrollscreen(void)
 }
 #endif /* ndef NO_SCROLL */
 
-void btext_drawchar(char c)
+static void btext_drawchar(char c)
 {
 	int cline = 0;
 #ifdef NO_SCROLL
diff --git a/arch/sparc/kernel/compat_audit.c b/arch/sparc/kernel/compat_audit.c
index d865575b25b..7062263d09c 100644
--- a/arch/sparc/kernel/compat_audit.c
+++ b/arch/sparc/kernel/compat_audit.c
@@ -1,5 +1,6 @@
 #define __32bit_syscall_numbers__
 #include <asm/unistd.h>
+#include "kernel.h"
 
 unsigned sparc32_dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 5c5125895db..82a3a71c451 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -22,6 +22,7 @@
 #include <asm/cpudata.h>
 
 #include "kernel.h"
+#include "entry.h"
 
 DEFINE_PER_CPU(cpuinfo_sparc, __cpu_data) = { 0 };
 EXPORT_PER_CPU_SYMBOL(__cpu_data);
diff --git a/arch/sparc/kernel/cpumap.h b/arch/sparc/kernel/cpumap.h
index e639880ab86..9dac398c434 100644
--- a/arch/sparc/kernel/cpumap.h
+++ b/arch/sparc/kernel/cpumap.h
@@ -2,8 +2,8 @@
 #define _CPUMAP_H
 
 #ifdef CONFIG_SMP
-extern void cpu_map_rebuild(void);
-extern int  map_to_cpu(unsigned int index);
+void cpu_map_rebuild(void);
+int map_to_cpu(unsigned int index);
 #define cpu_map_init() cpu_map_rebuild()
 #else
 #define cpu_map_init() do {} while (0)
diff --git a/arch/sparc/kernel/devices.c b/arch/sparc/kernel/devices.c
index 3d465e87f7e..8d5d09f09ca 100644
--- a/arch/sparc/kernel/devices.c
+++ b/arch/sparc/kernel/devices.c
@@ -19,8 +19,9 @@
 #include <asm/smp.h>
 #include <asm/cpudata.h>
 #include <asm/cpu_type.h>
+#include <asm/setup.h>
 
-extern void clock_stop_probe(void); /* tadpole.c */
+#include "kernel.h"
 
 static char *cpu_mid_prop(void)
 {
@@ -131,11 +132,6 @@ void __init device_scan(void)
 	}
 #endif /* !CONFIG_SMP */
 
-	{
-		extern void auxio_probe(void);
-		extern void auxio_power_probe(void);
-		auxio_probe();
-		auxio_power_probe();
-	}
-	clock_stop_probe();
+	auxio_probe();
+	auxio_power_probe();
 }
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index 140966fbd30..ebaba6167dd 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -6,40 +6,39 @@
 #include <linux/init.h>
 
 /* irq */
-extern void handler_irq(int irq, struct pt_regs *regs);
+void handler_irq(int irq, struct pt_regs *regs);
 
 #ifdef CONFIG_SPARC32
 /* traps */
-extern void do_hw_interrupt(struct pt_regs *regs, unsigned long type);
-extern void do_illegal_instruction(struct pt_regs *regs, unsigned long pc,
-                                   unsigned long npc, unsigned long psr);
-
-extern void do_priv_instruction(struct pt_regs *regs, unsigned long pc,
-                                unsigned long npc, unsigned long psr);
-extern void do_memaccess_unaligned(struct pt_regs *regs, unsigned long pc,
-                                   unsigned long npc,
-                                   unsigned long psr);
-extern void do_fpd_trap(struct pt_regs *regs, unsigned long pc,
+void do_hw_interrupt(struct pt_regs *regs, unsigned long type);
+void do_illegal_instruction(struct pt_regs *regs, unsigned long pc,
+                            unsigned long npc, unsigned long psr);
+
+void do_priv_instruction(struct pt_regs *regs, unsigned long pc,
+                         unsigned long npc, unsigned long psr);
+void do_memaccess_unaligned(struct pt_regs *regs, unsigned long pc,
+                            unsigned long npc, unsigned long psr);
+void do_fpd_trap(struct pt_regs *regs, unsigned long pc,
+                 unsigned long npc, unsigned long psr);
+void do_fpe_trap(struct pt_regs *regs, unsigned long pc,
+                 unsigned long npc, unsigned long psr);
+void handle_tag_overflow(struct pt_regs *regs, unsigned long pc,
+                         unsigned long npc, unsigned long psr);
+void handle_watchpoint(struct pt_regs *regs, unsigned long pc,
+                       unsigned long npc, unsigned long psr);
+void handle_reg_access(struct pt_regs *regs, unsigned long pc,
+                       unsigned long npc, unsigned long psr);
+void handle_cp_disabled(struct pt_regs *regs, unsigned long pc,
                         unsigned long npc, unsigned long psr);
-extern void do_fpe_trap(struct pt_regs *regs, unsigned long pc,
-                        unsigned long npc, unsigned long psr);
-extern void handle_tag_overflow(struct pt_regs *regs, unsigned long pc,
-                                unsigned long npc, unsigned long psr);
-extern void handle_watchpoint(struct pt_regs *regs, unsigned long pc,
-                              unsigned long npc, unsigned long psr);
-extern void handle_reg_access(struct pt_regs *regs, unsigned long pc,
-                              unsigned long npc, unsigned long psr);
-extern void handle_cp_disabled(struct pt_regs *regs, unsigned long pc,
-                               unsigned long npc, unsigned long psr);
-extern void handle_cp_exception(struct pt_regs *regs, unsigned long pc,
-                                unsigned long npc, unsigned long psr);
+void handle_cp_exception(struct pt_regs *regs, unsigned long pc,
+                         unsigned long npc, unsigned long psr);
 
 
 
 /* entry.S */
-extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
-                   void *fpqueue, unsigned long *fpqdepth);
-extern void fpload(unsigned long *fpregs, unsigned long *fsr);
+void fpsave(unsigned long *fpregs, unsigned long *fsr,
+            void *fpqueue, unsigned long *fpqdepth);
+void fpload(unsigned long *fpregs, unsigned long *fsr);
 
 #else /* CONFIG_SPARC32 */
 
@@ -66,123 +65,123 @@ struct pause_patch_entry {
 extern struct pause_patch_entry __pause_3insn_patch,
 	__pause_3insn_patch_end;
 
-extern void __init per_cpu_patch(void);
-extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
-				    struct sun4v_1insn_patch_entry *);
-extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
-				    struct sun4v_2insn_patch_entry *);
-extern void __init sun4v_patch(void);
-extern void __init boot_cpu_id_too_large(int cpu);
+void __init per_cpu_patch(void);
+void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
+			     struct sun4v_1insn_patch_entry *);
+void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+			     struct sun4v_2insn_patch_entry *);
+void __init sun4v_patch(void);
+void __init boot_cpu_id_too_large(int cpu);
 extern unsigned int dcache_parity_tl1_occurred;
 extern unsigned int icache_parity_tl1_occurred;
 
-extern asmlinkage void sparc_breakpoint(struct pt_regs *regs);
-extern void timer_interrupt(int irq, struct pt_regs *regs);
-
-extern void do_notify_resume(struct pt_regs *regs,
-			     unsigned long orig_i0,
-			     unsigned long thread_info_flags);
-
-extern asmlinkage int syscall_trace_enter(struct pt_regs *regs);
-extern asmlinkage void syscall_trace_leave(struct pt_regs *regs);
-
-extern void bad_trap_tl1(struct pt_regs *regs, long lvl);
-
-extern void do_fpieee(struct pt_regs *regs);
-extern void do_fpother(struct pt_regs *regs);
-extern void do_tof(struct pt_regs *regs);
-extern void do_div0(struct pt_regs *regs);
-extern void do_illegal_instruction(struct pt_regs *regs);
-extern void mem_address_unaligned(struct pt_regs *regs,
-				  unsigned long sfar,
-				  unsigned long sfsr);
-extern void sun4v_do_mna(struct pt_regs *regs,
-			 unsigned long addr,
-			 unsigned long type_ctx);
-extern void do_privop(struct pt_regs *regs);
-extern void do_privact(struct pt_regs *regs);
-extern void do_cee(struct pt_regs *regs);
-extern void do_cee_tl1(struct pt_regs *regs);
-extern void do_dae_tl1(struct pt_regs *regs);
-extern void do_iae_tl1(struct pt_regs *regs);
-extern void do_div0_tl1(struct pt_regs *regs);
-extern void do_fpdis_tl1(struct pt_regs *regs);
-extern void do_fpieee_tl1(struct pt_regs *regs);
-extern void do_fpother_tl1(struct pt_regs *regs);
-extern void do_ill_tl1(struct pt_regs *regs);
-extern void do_irq_tl1(struct pt_regs *regs);
-extern void do_lddfmna_tl1(struct pt_regs *regs);
-extern void do_stdfmna_tl1(struct pt_regs *regs);
-extern void do_paw(struct pt_regs *regs);
-extern void do_paw_tl1(struct pt_regs *regs);
-extern void do_vaw(struct pt_regs *regs);
-extern void do_vaw_tl1(struct pt_regs *regs);
-extern void do_tof_tl1(struct pt_regs *regs);
-extern void do_getpsr(struct pt_regs *regs);
-
-extern void spitfire_insn_access_exception(struct pt_regs *regs,
-					   unsigned long sfsr,
-					   unsigned long sfar);
-extern void spitfire_insn_access_exception_tl1(struct pt_regs *regs,
-					       unsigned long sfsr,
-					       unsigned long sfar);
-extern void spitfire_data_access_exception(struct pt_regs *regs,
-					   unsigned long sfsr,
-					   unsigned long sfar);
-extern void spitfire_data_access_exception_tl1(struct pt_regs *regs,
-					       unsigned long sfsr,
-					       unsigned long sfar);
-extern void spitfire_access_error(struct pt_regs *regs,
-				  unsigned long status_encoded,
-				  unsigned long afar);
-
-extern void cheetah_fecc_handler(struct pt_regs *regs,
-				 unsigned long afsr,
-				 unsigned long afar);
-extern void cheetah_cee_handler(struct pt_regs *regs,
-				unsigned long afsr,
-				unsigned long afar);
-extern void cheetah_deferred_handler(struct pt_regs *regs,
-				     unsigned long afsr,
-				     unsigned long afar);
-extern void cheetah_plus_parity_error(int type, struct pt_regs *regs);
-
-extern void sun4v_insn_access_exception(struct pt_regs *regs,
-					unsigned long addr,
-					unsigned long type_ctx);
-extern void sun4v_insn_access_exception_tl1(struct pt_regs *regs,
-					    unsigned long addr,
-					    unsigned long type_ctx);
-extern void sun4v_data_access_exception(struct pt_regs *regs,
-					unsigned long addr,
-					unsigned long type_ctx);
-extern void sun4v_data_access_exception_tl1(struct pt_regs *regs,
-					    unsigned long addr,
-					    unsigned long type_ctx);
-extern void sun4v_resum_error(struct pt_regs *regs,
-			      unsigned long offset);
-extern void sun4v_resum_overflow(struct pt_regs *regs);
-extern void sun4v_nonresum_error(struct pt_regs *regs,
-				 unsigned long offset);
-extern void sun4v_nonresum_overflow(struct pt_regs *regs);
+asmlinkage void sparc_breakpoint(struct pt_regs *regs);
+void timer_interrupt(int irq, struct pt_regs *regs);
+
+void do_notify_resume(struct pt_regs *regs,
+		      unsigned long orig_i0,
+		      unsigned long thread_info_flags);
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs);
+asmlinkage void syscall_trace_leave(struct pt_regs *regs);
+
+void bad_trap_tl1(struct pt_regs *regs, long lvl);
+
+void do_fpieee(struct pt_regs *regs);
+void do_fpother(struct pt_regs *regs);
+void do_tof(struct pt_regs *regs);
+void do_div0(struct pt_regs *regs);
+void do_illegal_instruction(struct pt_regs *regs);
+void mem_address_unaligned(struct pt_regs *regs,
+			   unsigned long sfar,
+			   unsigned long sfsr);
+void sun4v_do_mna(struct pt_regs *regs,
+		  unsigned long addr,
+		  unsigned long type_ctx);
+void do_privop(struct pt_regs *regs);
+void do_privact(struct pt_regs *regs);
+void do_cee(struct pt_regs *regs);
+void do_cee_tl1(struct pt_regs *regs);
+void do_dae_tl1(struct pt_regs *regs);
+void do_iae_tl1(struct pt_regs *regs);
+void do_div0_tl1(struct pt_regs *regs);
+void do_fpdis_tl1(struct pt_regs *regs);
+void do_fpieee_tl1(struct pt_regs *regs);
+void do_fpother_tl1(struct pt_regs *regs);
+void do_ill_tl1(struct pt_regs *regs);
+void do_irq_tl1(struct pt_regs *regs);
+void do_lddfmna_tl1(struct pt_regs *regs);
+void do_stdfmna_tl1(struct pt_regs *regs);
+void do_paw(struct pt_regs *regs);
+void do_paw_tl1(struct pt_regs *regs);
+void do_vaw(struct pt_regs *regs);
+void do_vaw_tl1(struct pt_regs *regs);
+void do_tof_tl1(struct pt_regs *regs);
+void do_getpsr(struct pt_regs *regs);
+
+void spitfire_insn_access_exception(struct pt_regs *regs,
+				    unsigned long sfsr,
+				    unsigned long sfar);
+void spitfire_insn_access_exception_tl1(struct pt_regs *regs,
+				        unsigned long sfsr,
+				        unsigned long sfar);
+void spitfire_data_access_exception(struct pt_regs *regs,
+				    unsigned long sfsr,
+				    unsigned long sfar);
+void spitfire_data_access_exception_tl1(struct pt_regs *regs,
+				        unsigned long sfsr,
+				        unsigned long sfar);
+void spitfire_access_error(struct pt_regs *regs,
+			   unsigned long status_encoded,
+			   unsigned long afar);
+
+void cheetah_fecc_handler(struct pt_regs *regs,
+			  unsigned long afsr,
+			  unsigned long afar);
+void cheetah_cee_handler(struct pt_regs *regs,
+			 unsigned long afsr,
+			 unsigned long afar);
+void cheetah_deferred_handler(struct pt_regs *regs,
+			      unsigned long afsr,
+			      unsigned long afar);
+void cheetah_plus_parity_error(int type, struct pt_regs *regs);
+
+void sun4v_insn_access_exception(struct pt_regs *regs,
+				 unsigned long addr,
+				 unsigned long type_ctx);
+void sun4v_insn_access_exception_tl1(struct pt_regs *regs,
+				     unsigned long addr,
+				     unsigned long type_ctx);
+void sun4v_data_access_exception(struct pt_regs *regs,
+				 unsigned long addr,
+				 unsigned long type_ctx);
+void sun4v_data_access_exception_tl1(struct pt_regs *regs,
+				     unsigned long addr,
+				     unsigned long type_ctx);
+void sun4v_resum_error(struct pt_regs *regs,
+		       unsigned long offset);
+void sun4v_resum_overflow(struct pt_regs *regs);
+void sun4v_nonresum_error(struct pt_regs *regs,
+			  unsigned long offset);
+void sun4v_nonresum_overflow(struct pt_regs *regs);
 
 extern unsigned long sun4v_err_itlb_vaddr;
 extern unsigned long sun4v_err_itlb_ctx;
 extern unsigned long sun4v_err_itlb_pte;
 extern unsigned long sun4v_err_itlb_error;
 
-extern void sun4v_itlb_error_report(struct pt_regs *regs, int tl);
+void sun4v_itlb_error_report(struct pt_regs *regs, int tl);
 
 extern unsigned long sun4v_err_dtlb_vaddr;
 extern unsigned long sun4v_err_dtlb_ctx;
 extern unsigned long sun4v_err_dtlb_pte;
 extern unsigned long sun4v_err_dtlb_error;
 
-extern void sun4v_dtlb_error_report(struct pt_regs *regs, int tl);
-extern void hypervisor_tlbop_error(unsigned long err,
-				   unsigned long op);
-extern void hypervisor_tlbop_error_xcall(unsigned long err,
-					 unsigned long op);
+void sun4v_dtlb_error_report(struct pt_regs *regs, int tl);
+void hypervisor_tlbop_error(unsigned long err,
+			    unsigned long op);
+void hypervisor_tlbop_error_xcall(unsigned long err,
+				  unsigned long op);
 
 /* WARNING: The error trap handlers in assembly know the precise
  *	    layout of the following structure.
@@ -248,8 +247,8 @@ struct ino_bucket {
 extern struct ino_bucket *ivector_table;
 extern unsigned long ivector_table_pa;
 
-extern void init_irqwork_curcpu(void);
-extern void sun4v_register_mondo_queues(int this_cpu);
+void init_irqwork_curcpu(void);
+void sun4v_register_mondo_queues(int this_cpu);
 
 #endif /* CONFIG_SPARC32 */
 #endif /* _ENTRY_H */
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 76663b019eb..bfa4d0c2df4 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -21,6 +21,7 @@
 #include <asm/iommu.h>
 
 #include "iommu_common.h"
+#include "kernel.h"
 
 #define STC_CTXMATCH_ADDR(STC, CTX)	\
 	((STC)->strbuf_ctxmatch_base + ((CTX) << 3))
@@ -840,8 +841,6 @@ static struct dma_map_ops sun4u_dma_ops = {
 struct dma_map_ops *dma_ops = &sun4u_dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-extern int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask);
-
 int dma_supported(struct device *dev, u64 device_mask)
 {
 	struct iommu *iommu = dev->archdata.iommu;
diff --git a/arch/sparc/kernel/iommu_common.h b/arch/sparc/kernel/iommu_common.h
index 591f5879039..1ec0de4156e 100644
--- a/arch/sparc/kernel/iommu_common.h
+++ b/arch/sparc/kernel/iommu_common.h
@@ -48,12 +48,12 @@ static inline int is_span_boundary(unsigned long entry,
 	return iommu_is_span_boundary(entry, nr, shift, boundary_size);
 }
 
-extern unsigned long iommu_range_alloc(struct device *dev,
-				       struct iommu *iommu,
-				       unsigned long npages,
-				       unsigned long *handle);
-extern void iommu_range_free(struct iommu *iommu,
-			     dma_addr_t dma_addr,
-			     unsigned long npages);
+unsigned long iommu_range_alloc(struct device *dev,
+				struct iommu *iommu,
+				unsigned long npages,
+				unsigned long *handle);
+void iommu_range_free(struct iommu *iommu,
+		      dma_addr_t dma_addr,
+		      unsigned long npages);
 
 #endif /* _IOMMU_COMMON_H */
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index e7e215dfa86..7f08ec8a7c6 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -186,7 +186,7 @@ static void __iomem *_sparc_alloc_io(unsigned int busno, unsigned long phys,
 
 	if (name == NULL) name = "???";
 
-	if ((xres = xres_alloc()) != 0) {
+	if ((xres = xres_alloc()) != NULL) {
 		tack = xres->xname;
 		res = &xres->xres;
 	} else {
@@ -400,7 +400,7 @@ static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	BUG();
 }
 
-struct dma_map_ops sbus_dma_ops = {
+static struct dma_map_ops sbus_dma_ops = {
 	.alloc			= sbus_alloc_coherent,
 	.free			= sbus_free_coherent,
 	.map_page		= sbus_map_page,
@@ -681,7 +681,7 @@ static int sparc_io_proc_show(struct seq_file *m, void *v)
 	const char *nm;
 
 	for (r = root->child; r != NULL; r = r->sibling) {
-		if ((nm = r->name) == 0) nm = "???";
+		if ((nm = r->name) == NULL) nm = "???";
 		seq_printf(m, "%016llx-%016llx: %s\n",
 				(unsigned long long)r->start,
 				(unsigned long long)r->end, nm);
diff --git a/arch/sparc/kernel/irq.h b/arch/sparc/kernel/irq.h
index b66b6aad1d6..70a0b8ddd0b 100644
--- a/arch/sparc/kernel/irq.h
+++ b/arch/sparc/kernel/irq.h
@@ -82,11 +82,20 @@ void handler_irq(unsigned int pil, struct pt_regs *regs);
 
 unsigned long leon_get_irqmask(unsigned int irq);
 
+/* irq_32.c */
+void sparc_floppy_irq(int irq, void *dev_id, struct pt_regs *regs);
+
+/* sun4m_irq.c */
+void sun4m_nmi(struct pt_regs *regs);
+
+/* sun4d_irq.c */
+void sun4d_handler_irq(unsigned int pil, struct pt_regs *regs);
+
 #ifdef CONFIG_SMP
 
 /* All SUN4D IPIs are sent on this IRQ, may be shared with hard IRQs */
 #define SUN4D_IPI_IRQ 13
 
-extern void sun4d_ipi_interrupt(void);
+void sun4d_ipi_interrupt(void);
 
 #endif
diff --git a/arch/sparc/kernel/irq_32.c b/arch/sparc/kernel/irq_32.c
index c145f6fd123..a979e99f875 100644
--- a/arch/sparc/kernel/irq_32.c
+++ b/arch/sparc/kernel/irq_32.c
@@ -17,6 +17,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/cpudata.h>
+#include <asm/setup.h>
 #include <asm/pcic.h>
 #include <asm/leon.h>
 
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
index a702d9ab019..e7f652be9e6 100644
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -2,6 +2,7 @@
 #define __SPARC_KERNEL_H
 
 #include <linux/interrupt.h>
+#include <linux/ftrace.h>
 
 #include <asm/traps.h>
 #include <asm/head.h>
@@ -15,62 +16,111 @@ extern int ncpus_probed;
 #ifdef CONFIG_SPARC64
 /* setup_64.c */
 struct seq_file;
-extern void cpucap_info(struct seq_file *);
+void cpucap_info(struct seq_file *);
 
-static inline unsigned long kimage_addr_to_ra(const char *p)
+static inline unsigned long kimage_addr_to_ra(const void *p)
 {
 	unsigned long val = (unsigned long) p;
 
 	return kern_base + (val - KERNBASE);
 }
+
+/* sys_sparc_64.c */
+asmlinkage long sys_kern_features(void);
+
+/* unaligned_64.c */
+asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn);
+int handle_popc(u32 insn, struct pt_regs *regs);
+void handle_lddfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr);
+void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr);
+
+/* smp_64.c */
+void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
+void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
+void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
+void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
+void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);
+
+/* kgdb_64.c */
+void __irq_entry smp_kgdb_capture_client(int irq, struct pt_regs *regs);
+
+/* pci.c */
+int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask);
+
+/* signal32.c */
+void do_sigreturn32(struct pt_regs *regs);
+asmlinkage void do_rt_sigreturn32(struct pt_regs *regs);
+void do_signal32(struct pt_regs * regs);
+asmlinkage int do_sys32_sigstack(u32 u_ssptr, u32 u_ossptr, unsigned long sp);
+
+/* compat_audit.c */
+extern unsigned sparc32_dir_class[];
+extern unsigned sparc32_chattr_class[];
+extern unsigned sparc32_write_class[];
+extern unsigned sparc32_read_class[];
+extern unsigned sparc32_signal_class[];
+int sparc32_classify_syscall(unsigned syscall);
 #endif
 
 #ifdef CONFIG_SPARC32
 /* setup_32.c */
+struct linux_romvec;
 void sparc32_start_kernel(struct linux_romvec *rp);
 
 /* cpu.c */
-extern void cpu_probe(void);
+void cpu_probe(void);
 
 /* traps_32.c */
-extern void handle_hw_divzero(struct pt_regs *regs, unsigned long pc,
-                              unsigned long npc, unsigned long psr);
+void handle_hw_divzero(struct pt_regs *regs, unsigned long pc,
+                       unsigned long npc, unsigned long psr);
 /* irq_32.c */
 extern struct irqaction static_irqaction[];
 extern int static_irq_count;
 extern spinlock_t irq_action_lock;
 
-extern void unexpected_irq(int irq, void *dev_id, struct pt_regs * regs);
-extern void init_IRQ(void);
+void unexpected_irq(int irq, void *dev_id, struct pt_regs * regs);
+void init_IRQ(void);
 
 /* sun4m_irq.c */
-extern void sun4m_init_IRQ(void);
-extern void sun4m_unmask_profile_irq(void);
-extern void sun4m_clear_profile_irq(int cpu);
+void sun4m_init_IRQ(void);
+void sun4m_unmask_profile_irq(void);
+void sun4m_clear_profile_irq(int cpu);
 
 /* sun4m_smp.c */
 void sun4m_cpu_pre_starting(void *arg);
 void sun4m_cpu_pre_online(void *arg);
+void __init smp4m_boot_cpus(void);
+int smp4m_boot_one_cpu(int i, struct task_struct *idle);
+void __init smp4m_smp_done(void);
+void smp4m_cross_call_irq(void);
+void smp4m_percpu_timer_interrupt(struct pt_regs *regs);
 
 /* sun4d_irq.c */
 extern spinlock_t sun4d_imsk_lock;
 
-extern void sun4d_init_IRQ(void);
-extern int sun4d_request_irq(unsigned int irq,
-                             irq_handler_t handler,
-                             unsigned long irqflags,
-                             const char *devname, void *dev_id);
-extern int show_sun4d_interrupts(struct seq_file *, void *);
-extern void sun4d_distribute_irqs(void);
-extern void sun4d_free_irq(unsigned int irq, void *dev_id);
+void sun4d_init_IRQ(void);
+int sun4d_request_irq(unsigned int irq,
+                      irq_handler_t handler,
+                      unsigned long irqflags,
+                      const char *devname, void *dev_id);
+int show_sun4d_interrupts(struct seq_file *, void *);
+void sun4d_distribute_irqs(void);
+void sun4d_free_irq(unsigned int irq, void *dev_id);
 
 /* sun4d_smp.c */
 void sun4d_cpu_pre_starting(void *arg);
 void sun4d_cpu_pre_online(void *arg);
+void __init smp4d_boot_cpus(void);
+int smp4d_boot_one_cpu(int i, struct task_struct *idle);
+void __init smp4d_smp_done(void);
+void smp4d_cross_call_irq(void);
+void smp4d_percpu_timer_interrupt(struct pt_regs *regs);
 
 /* leon_smp.c */
 void leon_cpu_pre_starting(void *arg);
 void leon_cpu_pre_online(void *arg);
+void leonsmp_ipi_interrupt(void);
+void leon_cross_call_irq(void);
 
 /* head_32.S */
 extern unsigned int t_nmi[];
@@ -89,12 +139,48 @@ extern unsigned int real_irq_entry[];
 extern unsigned int smp4d_ticker[];
 extern unsigned int patchme_maybe_smp_msg[];
 
-extern void floppy_hardint(void);
+void floppy_hardint(void);
 
 /* trampoline_32.S */
 extern unsigned long sun4m_cpu_startup;
 extern unsigned long sun4d_cpu_startup;
 
+/* process_32.c */
+asmlinkage int sparc_do_fork(unsigned long clone_flags,
+                             unsigned long stack_start,
+                             struct pt_regs *regs,
+                             unsigned long stack_size);
+
+/* signal_32.c */
+asmlinkage void do_sigreturn(struct pt_regs *regs);
+asmlinkage void do_rt_sigreturn(struct pt_regs *regs);
+void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0,
+                      unsigned long thread_info_flags);
+asmlinkage int do_sys_sigstack(struct sigstack __user *ssptr,
+                               struct sigstack __user *ossptr,
+                               unsigned long sp);
+
+/* ptrace_32.c */
+asmlinkage int syscall_trace(struct pt_regs *regs, int syscall_exit_p);
+
+/* unaligned_32.c */
+asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn);
+asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn);
+
+/* windows.c */
+void try_to_clear_window_buffer(struct pt_regs *regs, int who);
+
+/* auxio_32.c */
+void __init auxio_probe(void);
+void __init auxio_power_probe(void);
+
+/* pcic.c */
+extern void __iomem *pcic_regs;
+void pcic_nmi(unsigned int pend, struct pt_regs *regs);
+
+/* time_32.c */
+void __init time_init(void);
+
 #else /* CONFIG_SPARC32 */
 #endif /* CONFIG_SPARC32 */
 #endif /* !(__SPARC_KERNEL_H) */
diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c
index b45fe3fb4d2..cbf21d0870e 100644
--- a/arch/sparc/kernel/kgdb_64.c
+++ b/arch/sparc/kernel/kgdb_64.c
@@ -13,6 +13,8 @@
 #include <asm/ptrace.h>
 #include <asm/irq.h>
 
+#include "kernel.h"
+
 void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs)
 {
 	struct reg_window *win;
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index 1b097350319..98d71284341 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -512,7 +512,8 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 /*
  * Called when the probe at kretprobe trampoline is hit
  */
-int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+static int __kprobes trampoline_probe_handler(struct kprobe *p,
+					      struct pt_regs *regs)
 {
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
@@ -576,7 +577,7 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 	return 1;
 }
 
-void kretprobe_trampoline_holder(void)
+static void __used kretprobe_trampoline_holder(void)
 {
 	asm volatile(".global kretprobe_trampoline\n"
 		     "kretprobe_trampoline:\n"
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index b7c68976cbc..683c4af999d 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -32,12 +32,12 @@ struct leon3_gptimer_regs_map *leon3_gptimer_regs; /* timer controller base addr
 
 int leondebug_irq_disable;
 int leon_debug_irqout;
-static int dummy_master_l10_counter;
+static volatile u32 dummy_master_l10_counter;
 unsigned long amba_system_id;
 static DEFINE_SPINLOCK(leon_irq_lock);
 
+static unsigned long leon3_gptimer_idx; /* Timer Index (0..6) within Timer Core */
 unsigned long leon3_gptimer_irq; /* interrupt controller irq number */
-unsigned long leon3_gptimer_idx; /* Timer Index (0..6) within Timer Core */
 unsigned int sparc_leon_eirq;
 #define LEON_IMASK(cpu) (&leon3_irqctrl_regs->mask[cpu])
 #define LEON_IACK (&leon3_irqctrl_regs->iclear)
@@ -65,7 +65,7 @@ static void leon_handle_ext_irq(unsigned int irq, struct irq_desc *desc)
 }
 
 /* The extended IRQ controller has been found, this function registers it */
-void leon_eirq_setup(unsigned int eirq)
+static void leon_eirq_setup(unsigned int eirq)
 {
 	unsigned long mask, oldmask;
 	unsigned int veirq;
@@ -270,7 +270,7 @@ static u32 leon_cycles_offset(void)
 #ifdef CONFIG_SMP
 
 /* smp clockevent irq */
-irqreturn_t leon_percpu_timer_ce_interrupt(int irq, void *unused)
+static irqreturn_t leon_percpu_timer_ce_interrupt(int irq, void *unused)
 {
 	struct clock_event_device *ce;
 	int cpu = smp_processor_id();
@@ -313,7 +313,7 @@ void __init leon_init_timers(void)
 
 	leondebug_irq_disable = 0;
 	leon_debug_irqout = 0;
-	master_l10_counter = (unsigned int *)&dummy_master_l10_counter;
+	master_l10_counter = (u32 __iomem *)&dummy_master_l10_counter;
 	dummy_master_l10_counter = 0;
 
 	rootnp = of_find_node_by_path("/ambapp0");
diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c
index e16c4157e1a..899b7203a4e 100644
--- a/arch/sparc/kernel/leon_pci.c
+++ b/arch/sparc/kernel/leon_pci.c
@@ -98,82 +98,3 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 {
 	return res->start;
 }
-
-/* in/out routines taken from pcic.c
- *
- * This probably belongs here rather than ioport.c because
- * we do not want this crud linked into SBus kernels.
- * Also, think for a moment about likes of floppy.c that
- * include architecture specific parts. They may want to redefine ins/outs.
- *
- * We do not use horrible macros here because we want to
- * advance pointer by sizeof(size).
- */
-void outsb(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 1;
-		outb(*(const char *)src, addr);
-		src += 1;
-		/* addr += 1; */
-	}
-}
-EXPORT_SYMBOL(outsb);
-
-void outsw(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 2;
-		outw(*(const short *)src, addr);
-		src += 2;
-		/* addr += 2; */
-	}
-}
-EXPORT_SYMBOL(outsw);
-
-void outsl(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 4;
-		outl(*(const long *)src, addr);
-		src += 4;
-		/* addr += 4; */
-	}
-}
-EXPORT_SYMBOL(outsl);
-
-void insb(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 1;
-		*(unsigned char *)dst = inb(addr);
-		dst += 1;
-		/* addr += 1; */
-	}
-}
-EXPORT_SYMBOL(insb);
-
-void insw(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 2;
-		*(unsigned short *)dst = inw(addr);
-		dst += 2;
-		/* addr += 2; */
-	}
-}
-EXPORT_SYMBOL(insw);
-
-void insl(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 4;
-		/*
-		 * XXX I am sure we are in for an unaligned trap here.
-		 */
-		*(unsigned long *)dst = inl(addr);
-		dst += 4;
-		/* addr += 4; */
-	}
-}
-EXPORT_SYMBOL(insl);
diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c
index 6df26e37f87..c8bf26edfa7 100644
--- a/arch/sparc/kernel/leon_pci_grpci1.c
+++ b/arch/sparc/kernel/leon_pci_grpci1.c
@@ -80,7 +80,7 @@ struct grpci1_regs {
 
 struct grpci1_priv {
 	struct leon_pci_info	info; /* must be on top of this structure */
-	struct grpci1_regs	*regs;		/* GRPCI register map */
+	struct grpci1_regs __iomem *regs;		/* GRPCI register map */
 	struct device		*dev;
 	int			pci_err_mask;	/* STATUS register error mask */
 	int			irq;		/* LEON irqctrl GRPCI IRQ */
@@ -101,7 +101,7 @@ static struct grpci1_priv *grpci1priv;
 static int grpci1_cfg_w32(struct grpci1_priv *priv, unsigned int bus,
 				unsigned int devfn, int where, u32 val);
 
-int grpci1_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int grpci1_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	struct grpci1_priv *priv = dev->bus->sysdata;
 	int irq_group;
@@ -144,7 +144,7 @@ static int grpci1_cfg_r32(struct grpci1_priv *priv, unsigned int bus,
 		grpci1_cfg_w32(priv, TGT, 0, PCI_COMMAND, tmp);
 	} else {
 		/* Bus always little endian (unaffected by byte-swapping) */
-		*val = flip_dword(tmp);
+		*val = swab32(tmp);
 	}
 
 	return 0;
@@ -197,7 +197,7 @@ static int grpci1_cfg_w32(struct grpci1_priv *priv, unsigned int bus,
 
 	pci_conf = (unsigned int *) (priv->pci_conf |
 						(devfn << 8) | (where & 0xfc));
-	LEON3_BYPASS_STORE_PA(pci_conf, flip_dword(val));
+	LEON3_BYPASS_STORE_PA(pci_conf, swab32(val));
 
 	return 0;
 }
@@ -417,10 +417,10 @@ out:
  *  BAR1: peripheral DMA to host's memory (size at least 256MByte)
  *  BAR2..BAR5: not implemented in hardware
  */
-void grpci1_hw_init(struct grpci1_priv *priv)
+static void grpci1_hw_init(struct grpci1_priv *priv)
 {
 	u32 ahbadr, bar_sz, data, pciadr;
-	struct grpci1_regs *regs = priv->regs;
+	struct grpci1_regs __iomem *regs = priv->regs;
 
 	/* set 1:1 mapping between AHB -> PCI memory space */
 	REGSTORE(regs->cfg_stat, priv->pci_area & 0xf0000000);
@@ -509,7 +509,7 @@ static irqreturn_t grpci1_err_interrupt(int irq, void *arg)
 
 static int grpci1_of_probe(struct platform_device *ofdev)
 {
-	struct grpci1_regs *regs;
+	struct grpci1_regs __iomem *regs;
 	struct grpci1_priv *priv;
 	int err, len;
 	const int *tmp;
@@ -690,7 +690,7 @@ err3:
 err2:
 	release_resource(&priv->info.mem_space);
 err1:
-	iounmap((void *)priv->pci_io_va);
+	iounmap((void __iomem *)priv->pci_io_va);
 	grpci1priv = NULL;
 	return err;
 }
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index 24d6a444634..e433a4d69fe 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -191,7 +191,7 @@ struct grpci2_cap_first {
 
 struct grpci2_priv {
 	struct leon_pci_info	info; /* must be on top of this structure */
-	struct grpci2_regs	*regs;
+	struct grpci2_regs __iomem *regs;
 	char			irq;
 	char			irq_mode; /* IRQ Mode from CAPSTS REG */
 	char			bt_enabled;
@@ -215,10 +215,10 @@ struct grpci2_priv {
 	struct grpci2_barcfg	tgtbars[6];
 };
 
-DEFINE_SPINLOCK(grpci2_dev_lock);
-struct grpci2_priv *grpci2priv;
+static DEFINE_SPINLOCK(grpci2_dev_lock);
+static struct grpci2_priv *grpci2priv;
 
-int grpci2_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int grpci2_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	struct grpci2_priv *priv = dev->bus->sysdata;
 	int irq_group;
@@ -270,7 +270,7 @@ static int grpci2_cfg_r32(struct grpci2_priv *priv, unsigned int bus,
 		*val = 0xffffffff;
 	} else {
 		/* Bus always little endian (unaffected by byte-swapping) */
-		*val = flip_dword(tmp);
+		*val = swab32(tmp);
 	}
 
 	return 0;
@@ -328,7 +328,7 @@ static int grpci2_cfg_w32(struct grpci2_priv *priv, unsigned int bus,
 
 	pci_conf = (unsigned int *) (priv->pci_conf |
 						(devfn << 8) | (where & 0xfc));
-	LEON3_BYPASS_STORE_PA(pci_conf, flip_dword(val));
+	LEON3_BYPASS_STORE_PA(pci_conf, swab32(val));
 
 	/* Wait until GRPCI2 signals that CFG access is done, it should be
 	 * done instantaneously unless a DMA operation is ongoing...
@@ -561,10 +561,10 @@ out:
 	return virq;
 }
 
-void grpci2_hw_init(struct grpci2_priv *priv)
+static void grpci2_hw_init(struct grpci2_priv *priv)
 {
 	u32 ahbadr, pciadr, bar_sz, capptr, io_map, data;
-	struct grpci2_regs *regs = priv->regs;
+	struct grpci2_regs __iomem *regs = priv->regs;
 	int i;
 	struct grpci2_barcfg *barcfg = priv->tgtbars;
 
@@ -655,7 +655,7 @@ static irqreturn_t grpci2_jump_interrupt(int irq, void *arg)
 static irqreturn_t grpci2_err_interrupt(int irq, void *arg)
 {
 	struct grpci2_priv *priv = arg;
-	struct grpci2_regs *regs = priv->regs;
+	struct grpci2_regs __iomem *regs = priv->regs;
 	unsigned int status;
 
 	status = REGLOAD(regs->sts_cap);
@@ -682,7 +682,7 @@ static irqreturn_t grpci2_err_interrupt(int irq, void *arg)
 
 static int grpci2_of_probe(struct platform_device *ofdev)
 {
-	struct grpci2_regs *regs;
+	struct grpci2_regs __iomem *regs;
 	struct grpci2_priv *priv;
 	int err, i, len;
 	const int *tmp;
@@ -878,7 +878,7 @@ err4:
 	release_resource(&priv->info.mem_space);
 err3:
 	err = -ENOMEM;
-	iounmap((void *)priv->pci_io_va);
+	iounmap((void __iomem *)priv->pci_io_va);
 err2:
 	kfree(priv);
 err1:
diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c
index b0b3967a2dd..ddcf950282e 100644
--- a/arch/sparc/kernel/leon_pmc.c
+++ b/arch/sparc/kernel/leon_pmc.c
@@ -12,14 +12,14 @@
 #include <asm/processor.h>
 
 /* List of Systems that need fixup instructions around power-down instruction */
-unsigned int pmc_leon_fixup_ids[] = {
+static unsigned int pmc_leon_fixup_ids[] = {
 	AEROFLEX_UT699,
 	GAISLER_GR712RC,
 	LEON4_NEXTREME1,
 	0
 };
 
-int pmc_leon_need_fixup(void)
+static int pmc_leon_need_fixup(void)
 {
 	unsigned int systemid = amba_system_id >> 16;
 	unsigned int *id;
@@ -38,7 +38,7 @@ int pmc_leon_need_fixup(void)
  * CPU idle callback function for systems that need some extra handling
  * See .../arch/sparc/kernel/process.c
  */
-void pmc_leon_idle_fixup(void)
+static void pmc_leon_idle_fixup(void)
 {
 	/* Prepare an address to a non-cachable region. APB is always
 	 * none-cachable. One instruction is executed after the Sleep
@@ -62,7 +62,7 @@ void pmc_leon_idle_fixup(void)
  * CPU idle callback function
  * See .../arch/sparc/kernel/process.c
  */
-void pmc_leon_idle(void)
+static void pmc_leon_idle(void)
 {
 	/* Interrupts need to be enabled to not hang the CPU */
 	local_irq_enable();
diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c
index 6edf955f987..018ef11f57d 100644
--- a/arch/sparc/kernel/leon_smp.c
+++ b/arch/sparc/kernel/leon_smp.c
@@ -130,7 +130,7 @@ void leon_configure_cache_smp(void)
 	local_ops->tlb_all();
 }
 
-void leon_smp_setbroadcast(unsigned int mask)
+static void leon_smp_setbroadcast(unsigned int mask)
 {
 	int broadcast =
 	    ((LEON3_BYPASS_LOAD_PA(&(leon3_irqctrl_regs->mpstatus)) >>
@@ -148,13 +148,6 @@ void leon_smp_setbroadcast(unsigned int mask)
 	LEON_BYPASS_STORE_PA(&(leon3_irqctrl_regs->mpbroadcast), mask);
 }
 
-unsigned int leon_smp_getbroadcast(void)
-{
-	unsigned int mask;
-	mask = LEON_BYPASS_LOAD_PA(&(leon3_irqctrl_regs->mpbroadcast));
-	return mask;
-}
-
 int leon_smp_nrcpus(void)
 {
 	int nrcpu =
@@ -266,10 +259,6 @@ void __init leon_smp_done(void)
 
 }
 
-void leon_irq_rotate(int cpu)
-{
-}
-
 struct leon_ipi_work {
 	int single;
 	int msk;
diff --git a/arch/sparc/kernel/of_device_common.c b/arch/sparc/kernel/of_device_common.c
index 3241f56331c..de0ee3971f0 100644
--- a/arch/sparc/kernel/of_device_common.c
+++ b/arch/sparc/kernel/of_device_common.c
@@ -5,8 +5,10 @@
 #include <linux/mod_devicetable.h>
 #include <linux/errno.h>
 #include <linux/irq.h>
-#include <linux/of_device.h>
 #include <linux/of_platform.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
 
 #include "of_device_common.h"
 
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 857ad77df9c..539babf00bb 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -28,6 +28,7 @@
 #include <asm/apb.h>
 
 #include "pci_impl.h"
+#include "kernel.h"
 
 /* List of all PCI controllers found in the system. */
 struct pci_pbm_info *pci_pbm_root = NULL;
diff --git a/arch/sparc/kernel/pci_impl.h b/arch/sparc/kernel/pci_impl.h
index 5f688531f48..75803c780af 100644
--- a/arch/sparc/kernel/pci_impl.h
+++ b/arch/sparc/kernel/pci_impl.h
@@ -48,8 +48,8 @@ struct sparc64_msiq_ops {
 			      unsigned long devino);
 };
 
-extern void sparc64_pbm_msi_init(struct pci_pbm_info *pbm,
-				 const struct sparc64_msiq_ops *ops);
+void sparc64_pbm_msi_init(struct pci_pbm_info *pbm,
+			  const struct sparc64_msiq_ops *ops);
 
 struct sparc64_msiq_cookie {
 	struct pci_pbm_info *pbm;
@@ -158,23 +158,23 @@ extern struct pci_pbm_info *pci_pbm_root;
 extern int pci_num_pbms;
 
 /* PCI bus scanning and fixup support. */
-extern void pci_get_pbm_props(struct pci_pbm_info *pbm);
-extern struct pci_bus *pci_scan_one_pbm(struct pci_pbm_info *pbm,
-					struct device *parent);
-extern void pci_determine_mem_io_space(struct pci_pbm_info *pbm);
+void pci_get_pbm_props(struct pci_pbm_info *pbm);
+struct pci_bus *pci_scan_one_pbm(struct pci_pbm_info *pbm,
+				 struct device *parent);
+void pci_determine_mem_io_space(struct pci_pbm_info *pbm);
 
 /* Error reporting support. */
-extern void pci_scan_for_target_abort(struct pci_pbm_info *, struct pci_bus *);
-extern void pci_scan_for_master_abort(struct pci_pbm_info *, struct pci_bus *);
-extern void pci_scan_for_parity_error(struct pci_pbm_info *, struct pci_bus *);
+void pci_scan_for_target_abort(struct pci_pbm_info *, struct pci_bus *);
+void pci_scan_for_master_abort(struct pci_pbm_info *, struct pci_bus *);
+void pci_scan_for_parity_error(struct pci_pbm_info *, struct pci_bus *);
 
 /* Configuration space access. */
-extern void pci_config_read8(u8 *addr, u8 *ret);
-extern void pci_config_read16(u16 *addr, u16 *ret);
-extern void pci_config_read32(u32 *addr, u32 *ret);
-extern void pci_config_write8(u8 *addr, u8 val);
-extern void pci_config_write16(u16 *addr, u16 val);
-extern void pci_config_write32(u32 *addr, u32 val);
+void pci_config_read8(u8 *addr, u8 *ret);
+void pci_config_read16(u16 *addr, u16 *ret);
+void pci_config_read32(u32 *addr, u32 *ret);
+void pci_config_write8(u8 *addr, u8 val);
+void pci_config_write16(u16 *addr, u16 val);
+void pci_config_write32(u32 *addr, u32 val);
 
 extern struct pci_ops sun4u_pci_ops;
 extern struct pci_ops sun4v_pci_ops;
diff --git a/arch/sparc/kernel/pci_sun4v.h b/arch/sparc/kernel/pci_sun4v.h
index 8e9fc3a5b4f..5642212390b 100644
--- a/arch/sparc/kernel/pci_sun4v.h
+++ b/arch/sparc/kernel/pci_sun4v.h
@@ -6,87 +6,87 @@
 #ifndef _PCI_SUN4V_H
 #define _PCI_SUN4V_H
 
-extern long pci_sun4v_iommu_map(unsigned long devhandle,
-				unsigned long tsbid,
-				unsigned long num_ttes,
-				unsigned long io_attributes,
-				unsigned long io_page_list_pa);
-extern unsigned long pci_sun4v_iommu_demap(unsigned long devhandle,
-					   unsigned long tsbid,
-					   unsigned long num_ttes);
-extern unsigned long pci_sun4v_iommu_getmap(unsigned long devhandle,
-					    unsigned long tsbid,
-					    unsigned long *io_attributes,
-					    unsigned long *real_address);
-extern unsigned long pci_sun4v_config_get(unsigned long devhandle,
-					  unsigned long pci_device,
-					  unsigned long config_offset,
-					  unsigned long size);
-extern int pci_sun4v_config_put(unsigned long devhandle,
-				unsigned long pci_device,
-				unsigned long config_offset,
-				unsigned long size,
-				unsigned long data);
+long pci_sun4v_iommu_map(unsigned long devhandle,
+			 unsigned long tsbid,
+			 unsigned long num_ttes,
+			 unsigned long io_attributes,
+			 unsigned long io_page_list_pa);
+unsigned long pci_sun4v_iommu_demap(unsigned long devhandle,
+				    unsigned long tsbid,
+				    unsigned long num_ttes);
+unsigned long pci_sun4v_iommu_getmap(unsigned long devhandle,
+				     unsigned long tsbid,
+				     unsigned long *io_attributes,
+				     unsigned long *real_address);
+unsigned long pci_sun4v_config_get(unsigned long devhandle,
+				   unsigned long pci_device,
+				   unsigned long config_offset,
+				   unsigned long size);
+int pci_sun4v_config_put(unsigned long devhandle,
+			 unsigned long pci_device,
+			 unsigned long config_offset,
+			 unsigned long size,
+			 unsigned long data);
 
-extern unsigned long pci_sun4v_msiq_conf(unsigned long devhandle,
+unsigned long pci_sun4v_msiq_conf(unsigned long devhandle,
 					 unsigned long msiqid,
 					 unsigned long msiq_paddr,
 					 unsigned long num_entries);
-extern unsigned long pci_sun4v_msiq_info(unsigned long devhandle,
-					 unsigned long msiqid,
-					 unsigned long *msiq_paddr,
-					 unsigned long *num_entries);
-extern unsigned long pci_sun4v_msiq_getvalid(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long *valid);
-extern unsigned long pci_sun4v_msiq_setvalid(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long valid);
-extern unsigned long pci_sun4v_msiq_getstate(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long *state);
-extern unsigned long pci_sun4v_msiq_setstate(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long state);
-extern unsigned long pci_sun4v_msiq_gethead(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long *head);
-extern unsigned long pci_sun4v_msiq_sethead(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long head);
-extern unsigned long pci_sun4v_msiq_gettail(unsigned long devhandle,
-					     unsigned long msiqid,
-					     unsigned long *head);
-extern unsigned long pci_sun4v_msi_getvalid(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long *valid);
-extern unsigned long pci_sun4v_msi_setvalid(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long valid);
-extern unsigned long pci_sun4v_msi_getmsiq(unsigned long devhandle,
-					   unsigned long msinum,
-					   unsigned long *msiq);
-extern unsigned long pci_sun4v_msi_setmsiq(unsigned long devhandle,
-					   unsigned long msinum,
-					   unsigned long msiq,
-					   unsigned long msitype);
-extern unsigned long pci_sun4v_msi_getstate(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long *state);
-extern unsigned long pci_sun4v_msi_setstate(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long state);
-extern unsigned long pci_sun4v_msg_getmsiq(unsigned long devhandle,
-					   unsigned long msinum,
-					   unsigned long *msiq);
-extern unsigned long pci_sun4v_msg_setmsiq(unsigned long devhandle,
-					   unsigned long msinum,
-					   unsigned long msiq);
-extern unsigned long pci_sun4v_msg_getvalid(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long *valid);
-extern unsigned long pci_sun4v_msg_setvalid(unsigned long devhandle,
-					    unsigned long msinum,
-					    unsigned long valid);
+unsigned long pci_sun4v_msiq_info(unsigned long devhandle,
+				  unsigned long msiqid,
+				  unsigned long *msiq_paddr,
+				  unsigned long *num_entries);
+unsigned long pci_sun4v_msiq_getvalid(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long *valid);
+unsigned long pci_sun4v_msiq_setvalid(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long valid);
+unsigned long pci_sun4v_msiq_getstate(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long *state);
+unsigned long pci_sun4v_msiq_setstate(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long state);
+unsigned long pci_sun4v_msiq_gethead(unsigned long devhandle,
+				     unsigned long msiqid,
+				     unsigned long *head);
+unsigned long pci_sun4v_msiq_sethead(unsigned long devhandle,
+				     unsigned long msiqid,
+				     unsigned long head);
+unsigned long pci_sun4v_msiq_gettail(unsigned long devhandle,
+				      unsigned long msiqid,
+				      unsigned long *head);
+unsigned long pci_sun4v_msi_getvalid(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long *valid);
+unsigned long pci_sun4v_msi_setvalid(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long valid);
+unsigned long pci_sun4v_msi_getmsiq(unsigned long devhandle,
+				    unsigned long msinum,
+				    unsigned long *msiq);
+unsigned long pci_sun4v_msi_setmsiq(unsigned long devhandle,
+				    unsigned long msinum,
+				    unsigned long msiq,
+				    unsigned long msitype);
+unsigned long pci_sun4v_msi_getstate(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long *state);
+unsigned long pci_sun4v_msi_setstate(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long state);
+unsigned long pci_sun4v_msg_getmsiq(unsigned long devhandle,
+				    unsigned long msinum,
+				    unsigned long *msiq);
+unsigned long pci_sun4v_msg_setmsiq(unsigned long devhandle,
+				    unsigned long msinum,
+				    unsigned long msiq);
+unsigned long pci_sun4v_msg_getvalid(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long *valid);
+unsigned long pci_sun4v_msg_setvalid(unsigned long devhandle,
+				     unsigned long msinum,
+				     unsigned long valid);
 
 #endif /* !(_PCI_SUN4V_H) */
diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
index 09f4fdd8d80..6cc78c213c0 100644
--- a/arch/sparc/kernel/pcic.c
+++ b/arch/sparc/kernel/pcic.c
@@ -36,6 +36,7 @@
 #include <asm/uaccess.h>
 #include <asm/irq_regs.h>
 
+#include "kernel.h"
 #include "irq.h"
 
 /*
@@ -162,8 +163,8 @@ static int pcic0_up;
 static struct linux_pcic pcic0;
 
 void __iomem *pcic_regs;
-volatile int pcic_speculative;
-volatile int pcic_trapped;
+static volatile int pcic_speculative;
+static volatile int pcic_trapped;
 
 /* forward */
 unsigned int pcic_build_device_irq(struct platform_device *op,
@@ -329,7 +330,7 @@ int __init pcic_probe(void)
 
 	pcic->pcic_res_cfg_addr.name = "pcic_cfg_addr";
 	if ((pcic->pcic_config_space_addr =
-	    ioremap(regs[2].phys_addr, regs[2].reg_size * 2)) == 0) {
+	    ioremap(regs[2].phys_addr, regs[2].reg_size * 2)) == NULL) {
 		prom_printf("PCIC: Error, cannot map "
 			    "PCI Configuration Space Address.\n");
 		prom_halt();
@@ -341,7 +342,7 @@ int __init pcic_probe(void)
 	 */
 	pcic->pcic_res_cfg_data.name = "pcic_cfg_data";
 	if ((pcic->pcic_config_space_data =
-	    ioremap(regs[3].phys_addr, regs[3].reg_size * 2)) == 0) {
+	    ioremap(regs[3].phys_addr, regs[3].reg_size * 2)) == NULL) {
 		prom_printf("PCIC: Error, cannot map "
 			    "PCI Configuration Space Data.\n");
 		prom_halt();
@@ -353,7 +354,6 @@ int __init pcic_probe(void)
 	strcpy(pbm->prom_name, namebuf);
 
 	{
-		extern volatile int t_nmi[4];
 		extern int pcic_nmi_trap_patch[4];
 
 		t_nmi[0] = pcic_nmi_trap_patch[0];
@@ -536,7 +536,7 @@ pcic_fill_irq(struct linux_pcic *pcic, struct pci_dev *dev, int node)
 		prom_getstring(node, "name", namebuf, sizeof(namebuf));
 	}
 
-	if ((p = pcic->pcic_imap) == 0) {
+	if ((p = pcic->pcic_imap) == NULL) {
 		dev->irq = 0;
 		return;
 	}
@@ -670,30 +670,6 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 	}
 }
 
-/*
- * pcic_pin_to_irq() is exported to bus probing code
- */
-unsigned int
-pcic_pin_to_irq(unsigned int pin, const char *name)
-{
-	struct linux_pcic *pcic = &pcic0;
-	unsigned int irq;
-	unsigned int ivec;
-
-	if (pin < 4) {
-		ivec = readw(pcic->pcic_regs+PCI_INT_SELECT_LO);
-		irq = ivec >> (pin << 2) & 0xF;
-	} else if (pin < 8) {
-		ivec = readw(pcic->pcic_regs+PCI_INT_SELECT_HI);
-		irq = ivec >> ((pin-4) << 2) & 0xF;
-	} else {					/* Corrupted map */
-		printk("PCIC: BAD PIN %d FOR %s\n", pin, name);
-		for (;;) {}	/* XXX Cannot panic properly in case of PROLL */
-	}
-/* P3 */ /* printk("PCIC: dev %s pin %d ivec 0x%x irq %x\n", name, pin, ivec, irq); */
-	return irq;
-}
-
 /* Makes compiler happy */
 static volatile int pcic_timer_dummy;
 
@@ -783,7 +759,7 @@ int pcibios_enable_device(struct pci_dev *pdev, int mask)
 void pcic_nmi(unsigned int pend, struct pt_regs *regs)
 {
 
-	pend = flip_dword(pend);
+	pend = swab32(pend);
 
 	if (!pcic_speculative || (pend & PCI_SYS_INT_PENDING_PIO) == 0) {
 		/*
@@ -875,82 +851,4 @@ void __init sun4m_pci_init_IRQ(void)
 	sparc_config.load_profile_irq = pcic_load_profile_irq;
 }
 
-/*
- * This probably belongs here rather than ioport.c because
- * we do not want this crud linked into SBus kernels.
- * Also, think for a moment about likes of floppy.c that
- * include architecture specific parts. They may want to redefine ins/outs.
- *
- * We do not use horrible macros here because we want to
- * advance pointer by sizeof(size).
- */
-void outsb(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 1;
-		outb(*(const char *)src, addr);
-		src += 1;
-		/* addr += 1; */
-	}
-}
-EXPORT_SYMBOL(outsb);
-
-void outsw(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 2;
-		outw(*(const short *)src, addr);
-		src += 2;
-		/* addr += 2; */
-	}
-}
-EXPORT_SYMBOL(outsw);
-
-void outsl(unsigned long addr, const void *src, unsigned long count)
-{
-	while (count) {
-		count -= 4;
-		outl(*(const long *)src, addr);
-		src += 4;
-		/* addr += 4; */
-	}
-}
-EXPORT_SYMBOL(outsl);
-
-void insb(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 1;
-		*(unsigned char *)dst = inb(addr);
-		dst += 1;
-		/* addr += 1; */
-	}
-}
-EXPORT_SYMBOL(insb);
-
-void insw(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 2;
-		*(unsigned short *)dst = inw(addr);
-		dst += 2;
-		/* addr += 2; */
-	}
-}
-EXPORT_SYMBOL(insw);
-
-void insl(unsigned long addr, void *dst, unsigned long count)
-{
-	while (count) {
-		count -= 4;
-		/*
-		 * XXX I am sure we are in for an unaligned trap here.
-		 */
-		*(unsigned long *)dst = inl(addr);
-		dst += 4;
-		/* addr += 4; */
-	}
-}
-EXPORT_SYMBOL(insl);
-
 subsys_initcall(pcic_init);
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b5c38faa4ea..8efd33753ad 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -110,7 +110,7 @@ struct cpu_hw_events {
 
 	unsigned int		group_flag;
 };
-DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, };
+static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { .enabled = 1, };
 
 /* An event map describes the characteristics of a performance
  * counter event.  In particular it gives the encoding as well as
@@ -1153,7 +1153,7 @@ static void perf_stop_nmi_watchdog(void *unused)
 		cpuc->pcr[i] = pcr_ops->read_pcr(i);
 }
 
-void perf_event_grab_pmc(void)
+static void perf_event_grab_pmc(void)
 {
 	if (atomic_inc_not_zero(&active_events))
 		return;
@@ -1169,7 +1169,7 @@ void perf_event_grab_pmc(void)
 	mutex_unlock(&pmc_grab_mutex);
 }
 
-void perf_event_release_pmc(void)
+static void perf_event_release_pmc(void)
 {
 	if (atomic_dec_and_mutex_lock(&active_events, &pmc_grab_mutex)) {
 		if (atomic_read(&nmi_active) == 0)
@@ -1669,7 +1669,7 @@ static bool __init supported_pmu(void)
 	return false;
 }
 
-int __init init_hw_perf_events(void)
+static int __init init_hw_perf_events(void)
 {
 	pr_info("Performance events: ");
 
@@ -1742,10 +1742,11 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 
 	ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
 	do {
-		struct sparc_stackf *usf, sf;
+		struct sparc_stackf __user *usf;
+		struct sparc_stackf sf;
 		unsigned long pc;
 
-		usf = (struct sparc_stackf *) ufp;
+		usf = (struct sparc_stackf __user *)ufp;
 		if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
 			break;
 
@@ -1765,17 +1766,19 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 		unsigned long pc;
 
 		if (thread32_stack_is_64bit(ufp)) {
-			struct sparc_stackf *usf, sf;
+			struct sparc_stackf __user *usf;
+			struct sparc_stackf sf;
 
 			ufp += STACK_BIAS;
-			usf = (struct sparc_stackf *) ufp;
+			usf = (struct sparc_stackf __user *)ufp;
 			if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
 				break;
 			pc = sf.callers_pc & 0xffffffff;
 			ufp = ((unsigned long) sf.fp) & 0xffffffff;
 		} else {
-			struct sparc_stackf32 *usf, sf;
-			usf = (struct sparc_stackf32 *) ufp;
+			struct sparc_stackf32 __user *usf;
+			struct sparc_stackf32 sf;
+			usf = (struct sparc_stackf32 __user *)ufp;
 			if (__copy_from_user_inatomic(&sf, usf, sizeof(sf)))
 				break;
 			pc = sf.callers_pc;
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 510baec1b69..50e7b626afe 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -10,6 +10,7 @@
 
 #include <stdarg.h>
 
+#include <linux/elfcore.h>
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
@@ -23,6 +24,7 @@
 #include <linux/delay.h>
 #include <linux/pm.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 
 #include <asm/auxio.h>
 #include <asm/oplib.h>
@@ -38,6 +40,8 @@
 #include <asm/unistd.h>
 #include <asm/setup.h>
 
+#include "kernel.h"
+
 /* 
  * Power management idle function 
  * Set in pm platform drivers (apc.c and pmc.c)
@@ -102,8 +106,12 @@ void machine_restart(char * cmd)
 void machine_power_off(void)
 {
 	if (auxio_power_register &&
-	    (strcmp(of_console_device->type, "serial") || scons_pwroff))
-		*auxio_power_register |= AUXIO_POWER_OFF;
+	    (strcmp(of_console_device->type, "serial") || scons_pwroff)) {
+		u8 power_register = sbus_readb(auxio_power_register);
+		power_register |= AUXIO_POWER_OFF;
+		sbus_writeb(power_register, auxio_power_register);
+	}
+
 	machine_halt();
 }
 
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index d7b4967f8fa..027e0998619 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -88,7 +88,7 @@ void arch_cpu_idle(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-void arch_cpu_idle_dead()
+void arch_cpu_idle_dead(void)
 {
 	sched_preempt_enable_no_resched();
 	cpu_play_dead();
@@ -239,7 +239,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp)
 	}
 }
 
-void arch_trigger_all_cpu_backtrace(void)
+void arch_trigger_all_cpu_backtrace(bool include_self)
 {
 	struct thread_info *tp = current_thread_info();
 	struct pt_regs *regs = get_irq_regs();
@@ -251,16 +251,22 @@ void arch_trigger_all_cpu_backtrace(void)
 
 	spin_lock_irqsave(&global_cpu_snapshot_lock, flags);
 
-	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
-
 	this_cpu = raw_smp_processor_id();
 
-	__global_reg_self(tp, regs, this_cpu);
+	memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
+
+	if (include_self)
+		__global_reg_self(tp, regs, this_cpu);
 
 	smp_fetch_global_regs();
 
 	for_each_online_cpu(cpu) {
-		struct global_reg_snapshot *gp = &global_cpu_snapshot[cpu].reg;
+		struct global_reg_snapshot *gp;
+
+		if (!include_self && cpu == this_cpu)
+			continue;
+
+		gp = &global_cpu_snapshot[cpu].reg;
 
 		__global_reg_poll(gp);
 
@@ -292,7 +298,7 @@ void arch_trigger_all_cpu_backtrace(void)
 
 static void sysrq_handle_globreg(int key)
 {
-	arch_trigger_all_cpu_backtrace();
+	arch_trigger_all_cpu_backtrace(true);
 }
 
 static struct sysrq_key_op sparc_globalreg_op = {
diff --git a/arch/sparc/kernel/prom.h b/arch/sparc/kernel/prom.h
index cf5fe1c0b02..890281b12b2 100644
--- a/arch/sparc/kernel/prom.h
+++ b/arch/sparc/kernel/prom.h
@@ -4,7 +4,7 @@
 #include <linux/spinlock.h>
 #include <asm/prom.h>
 
-extern void of_console_init(void);
+void of_console_init(void);
 
 extern unsigned int prom_early_allocated;
 
diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c
index 9a690d39c01..20cc5d80a47 100644
--- a/arch/sparc/kernel/prom_64.c
+++ b/arch/sparc/kernel/prom_64.c
@@ -15,11 +15,12 @@
  *      2 of the License, or (at your option) any later version.
  */
 
+#include <linux/memblock.h>
 #include <linux/kernel.h>
-#include <linux/types.h>
 #include <linux/string.h>
+#include <linux/types.h>
+#include <linux/cpu.h>
 #include <linux/mm.h>
-#include <linux/memblock.h>
 #include <linux/of.h>
 
 #include <asm/prom.h>
diff --git a/arch/sparc/kernel/psycho_common.h b/arch/sparc/kernel/psycho_common.h
index 590b4ed8ab5..05a6e30a928 100644
--- a/arch/sparc/kernel/psycho_common.h
+++ b/arch/sparc/kernel/psycho_common.h
@@ -30,19 +30,19 @@ enum psycho_error_type {
 	UE_ERR, CE_ERR, PCI_ERR
 };
 
-extern void psycho_check_iommu_error(struct pci_pbm_info *pbm,
-				     unsigned long afsr,
-				     unsigned long afar,
-				     enum psycho_error_type type);
+void psycho_check_iommu_error(struct pci_pbm_info *pbm,
+			      unsigned long afsr,
+			      unsigned long afar,
+			      enum psycho_error_type type);
 
-extern irqreturn_t psycho_pcierr_intr(int irq, void *dev_id);
+irqreturn_t psycho_pcierr_intr(int irq, void *dev_id);
 
-extern int psycho_iommu_init(struct pci_pbm_info *pbm, int tsbsize,
-			     u32 dvma_offset, u32 dma_mask,
-			     unsigned long write_complete_offset);
+int psycho_iommu_init(struct pci_pbm_info *pbm, int tsbsize,
+		      u32 dvma_offset, u32 dma_mask,
+		      unsigned long write_complete_offset);
 
-extern void psycho_pbm_init_common(struct pci_pbm_info *pbm,
-				   struct platform_device *op,
-				   const char *chip_name, int chip_type);
+void psycho_pbm_init_common(struct pci_pbm_info *pbm,
+			    struct platform_device *op,
+			    const char *chip_name, int chip_type);
 
 #endif /* _PSYCHO_COMMON_H */
diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c
index 896ba7c5cd8..a331fdc11a2 100644
--- a/arch/sparc/kernel/ptrace_32.c
+++ b/arch/sparc/kernel/ptrace_32.c
@@ -26,6 +26,8 @@
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 
+#include "kernel.h"
+
 /* #define ALLOW_INIT_TRACING */
 
 /*
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 1434526970a..baef495c06b 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -267,7 +267,7 @@ static __init void leon_patch(void)
 }
 
 struct tt_entry *sparc_ttable;
-struct pt_regs fake_swapper_regs;
+static struct pt_regs fake_swapper_regs;
 
 /* Called from head_32.S - before we have setup anything
  * in the kernel. Be very careful with what you do here.
@@ -365,7 +365,7 @@ void __init setup_arch(char **cmdline_p)
 
 	prom_setsync(prom_sync_me);
 
-	if((boot_flags&BOOTME_DEBUG) && (linux_dbvec!=0) && 
+	if((boot_flags & BOOTME_DEBUG) && (linux_dbvec != NULL) &&
 	   ((*(short *)linux_dbvec) != -1)) {
 		printk("Booted under KADB. Syncing trap table.\n");
 		(*(linux_dbvec->teach_debugger))();
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index ee789d2ef05..62deba7be1a 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -31,6 +31,7 @@
 #include <asm/switch_to.h>
 
 #include "sigutil.h"
+#include "kernel.h"
 
 /* This magic should be in g_upper[0] for all upper parts
  * to be valid.
@@ -145,7 +146,7 @@ void do_sigreturn32(struct pt_regs *regs)
 	unsigned int psr;
 	unsigned pc, npc;
 	sigset_t set;
-	unsigned seta[_COMPAT_NSIG_WORDS];
+	compat_sigset_t seta;
 	int err, i;
 	
 	/* Always make any pending restarted system calls return -EINTR */
@@ -209,17 +210,13 @@ void do_sigreturn32(struct pt_regs *regs)
 		if (restore_rwin_state(compat_ptr(rwin_save)))
 			goto segv;
 	}
-	err |= __get_user(seta[0], &sf->info.si_mask);
-	err |= copy_from_user(seta+1, &sf->extramask,
+	err |= __get_user(seta.sig[0], &sf->info.si_mask);
+	err |= copy_from_user(&seta.sig[1], &sf->extramask,
 			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
 	if (err)
 	    	goto segv;
-	switch (_NSIG_WORDS) {
-		case 4: set.sig[3] = seta[6] + (((long)seta[7]) << 32);
-		case 3: set.sig[2] = seta[4] + (((long)seta[5]) << 32);
-		case 2: set.sig[1] = seta[2] + (((long)seta[3]) << 32);
-		case 1: set.sig[0] = seta[0] + (((long)seta[1]) << 32);
-	}
+
+	set.sig[0] = seta.sig[0] + (((long)seta.sig[1]) << 32);
 	set_current_blocked(&set);
 	return;
 
@@ -303,12 +300,7 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs)
 			goto segv;
 	}
 
-	switch (_NSIG_WORDS) {
-		case 4: set.sig[3] = seta.sig[6] + (((long)seta.sig[7]) << 32);
-		case 3: set.sig[2] = seta.sig[4] + (((long)seta.sig[5]) << 32);
-		case 2: set.sig[1] = seta.sig[2] + (((long)seta.sig[3]) << 32);
-		case 1: set.sig[0] = seta.sig[0] + (((long)seta.sig[1]) << 32);
-	}
+	set.sig[0] = seta.sig[0] + (((long)seta.sig[1]) << 32);
 	set_current_blocked(&set);
 	return;
 segv:
@@ -417,7 +409,7 @@ static int setup_frame32(struct ksignal *ksig, struct pt_regs *regs,
 	void __user *tail;
 	int sigframe_size;
 	u32 psr;
-	unsigned int seta[_COMPAT_NSIG_WORDS];
+	compat_sigset_t seta;
 
 	/* 1. Make sure everything is clean */
 	synchronize_user_stack();
@@ -481,18 +473,14 @@ static int setup_frame32(struct ksignal *ksig, struct pt_regs *regs,
 		err |= __put_user(0, &sf->rwin_save);
 	}
 
-	switch (_NSIG_WORDS) {
-	case 4: seta[7] = (oldset->sig[3] >> 32);
-	        seta[6] = oldset->sig[3];
-	case 3: seta[5] = (oldset->sig[2] >> 32);
-	        seta[4] = oldset->sig[2];
-	case 2: seta[3] = (oldset->sig[1] >> 32);
-	        seta[2] = oldset->sig[1];
-	case 1: seta[1] = (oldset->sig[0] >> 32);
-	        seta[0] = oldset->sig[0];
-	}
-	err |= __put_user(seta[0], &sf->info.si_mask);
-	err |= __copy_to_user(sf->extramask, seta + 1,
+	/* If these change we need to know - assignments to seta relies on these sizes */
+	BUILD_BUG_ON(_NSIG_WORDS != 1);
+	BUILD_BUG_ON(_COMPAT_NSIG_WORDS != 2);
+	seta.sig[1] = (oldset->sig[0] >> 32);
+	seta.sig[0] = oldset->sig[0];
+
+	err |= __put_user(seta.sig[0], &sf->info.si_mask);
+	err |= __copy_to_user(sf->extramask, &seta.sig[1],
 			      (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int));
 
 	if (!wsaved) {
@@ -622,16 +610,8 @@ static int setup_rt_frame32(struct ksignal *ksig, struct pt_regs *regs,
 	/* Setup sigaltstack */
 	err |= __compat_save_altstack(&sf->stack, regs->u_regs[UREG_FP]);
 
-	switch (_NSIG_WORDS) {
-	case 4: seta.sig[7] = (oldset->sig[3] >> 32);
-		seta.sig[6] = oldset->sig[3];
-	case 3: seta.sig[5] = (oldset->sig[2] >> 32);
-		seta.sig[4] = oldset->sig[2];
-	case 2: seta.sig[3] = (oldset->sig[1] >> 32);
-		seta.sig[2] = oldset->sig[1];
-	case 1: seta.sig[1] = (oldset->sig[0] >> 32);
-		seta.sig[0] = oldset->sig[0];
-	}
+	seta.sig[1] = (oldset->sig[0] >> 32);
+	seta.sig[0] = oldset->sig[0];
 	err |= __copy_to_user(&sf->mask, &seta, sizeof(compat_sigset_t));
 
 	if (!wsaved) {
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 7d5d8e1f841..9ee72fc8e0e 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -28,6 +28,7 @@
 #include <asm/switch_to.h>
 
 #include "sigutil.h"
+#include "kernel.h"
 
 extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 		   void *fpqueue, unsigned long *fpqdepth);
@@ -341,7 +342,7 @@ static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs,
 	err |= __put_user(0, &sf->extra_size);
 
 	if (psr & PSR_EF) {
-		__siginfo_fpu_t *fp = tail;
+		__siginfo_fpu_t __user *fp = tail;
 		tail += sizeof(*fp);
 		err |= save_fpu_state(regs, fp);
 		err |= __put_user(fp, &sf->fpu_save);
@@ -349,7 +350,7 @@ static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs,
 		err |= __put_user(0, &sf->fpu_save);
 	}
 	if (wsaved) {
-		__siginfo_rwin_t *rwp = tail;
+		__siginfo_rwin_t __user *rwp = tail;
 		tail += sizeof(*rwp);
 		err |= save_rwin_state(wsaved, rwp);
 		err |= __put_user(rwp, &sf->rwin_save);
@@ -517,9 +518,9 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0,
 	}
 }
 
-asmlinkage int
-do_sys_sigstack(struct sigstack __user *ssptr, struct sigstack __user *ossptr,
-		unsigned long sp)
+asmlinkage int do_sys_sigstack(struct sigstack __user *ssptr,
+                               struct sigstack __user *ossptr,
+                               unsigned long sp)
 {
 	int ret = -EFAULT;
 
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index cd91d010e6d..1a699986803 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -35,9 +35,10 @@
 #include <asm/switch_to.h>
 #include <asm/cacheflush.h>
 
-#include "entry.h"
-#include "systbls.h"
 #include "sigutil.h"
+#include "systbls.h"
+#include "kernel.h"
+#include "entry.h"
 
 /* {set, get}context() needed for 64-bit SparcLinux userland. */
 asmlinkage void sparc64_set_context(struct pt_regs *regs)
@@ -492,7 +493,6 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 
 #ifdef CONFIG_COMPAT
 	if (test_thread_flag(TIF_32BIT)) {
-		extern void do_signal32(struct pt_regs *);
 		do_signal32(regs);
 		return;
 	}
diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c
index a102bfba6ea..7958242d63c 100644
--- a/arch/sparc/kernel/smp_32.c
+++ b/arch/sparc/kernel/smp_32.c
@@ -20,6 +20,7 @@
 #include <linux/seq_file.h>
 #include <linux/cache.h>
 #include <linux/delay.h>
+#include <linux/profile.h>
 #include <linux/cpu.h>
 
 #include <asm/ptrace.h>
@@ -75,8 +76,6 @@ void smp_store_cpu_info(int id)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	extern void smp4m_smp_done(void);
-	extern void smp4d_smp_done(void);
 	unsigned long bogosum = 0;
 	int cpu, num = 0;
 
@@ -183,8 +182,6 @@ int setup_profiling_timer(unsigned int multiplier)
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	extern void __init smp4m_boot_cpus(void);
-	extern void __init smp4d_boot_cpus(void);
 	int i, cpuid, extra;
 
 	printk("Entering SMP Mode...\n");
@@ -261,8 +258,6 @@ void __init smp_prepare_boot_cpu(void)
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
-	extern int smp4m_boot_one_cpu(int, struct task_struct *);
-	extern int smp4d_boot_one_cpu(int, struct task_struct *);
 	int ret=0;
 
 	switch(sparc_cpu_model) {
@@ -297,7 +292,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	return ret;
 }
 
-void arch_cpu_pre_starting(void *arg)
+static void arch_cpu_pre_starting(void *arg)
 {
 	local_ops->cache_all();
 	local_ops->tlb_all();
@@ -317,7 +312,7 @@ void arch_cpu_pre_starting(void *arg)
 	}
 }
 
-void arch_cpu_pre_online(void *arg)
+static void arch_cpu_pre_online(void *arg)
 {
 	unsigned int cpuid = hard_smp_processor_id();
 
@@ -344,7 +339,7 @@ void arch_cpu_pre_online(void *arg)
 	}
 }
 
-void sparc_start_secondary(void *arg)
+static void sparc_start_secondary(void *arg)
 {
 	unsigned int cpu;
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 745a3633ce1..41aa2478f3c 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -25,6 +25,7 @@
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
 #include <linux/slab.h>
+#include <linux/kgdb.h>
 
 #include <asm/head.h>
 #include <asm/ptrace.h>
@@ -35,6 +36,7 @@
 #include <asm/hvtramp.h>
 #include <asm/io.h>
 #include <asm/timer.h>
+#include <asm/setup.h>
 
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
@@ -52,6 +54,7 @@
 #include <asm/pcr.h>
 
 #include "cpumap.h"
+#include "kernel.h"
 
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
@@ -272,14 +275,6 @@ static void smp_synchronize_one_tick(int cpu)
 }
 
 #if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU)
-/* XXX Put this in some common place. XXX */
-static unsigned long kimage_addr_to_ra(void *p)
-{
-	unsigned long val = (unsigned long) p;
-
-	return kern_base + (val - KERNBASE);
-}
-
 static void ldom_startcpu_cpuid(unsigned int cpu, unsigned long thread_reg,
 				void **descrp)
 {
@@ -867,11 +862,6 @@ extern unsigned long xcall_flush_dcache_page_cheetah;
 #endif
 extern unsigned long xcall_flush_dcache_page_spitfire;
 
-#ifdef CONFIG_DEBUG_DCFLUSH
-extern atomic_t dcpage_flushes;
-extern atomic_t dcpage_flushes_xcall;
-#endif
-
 static inline void __local_flush_dcache_page(struct page *page)
 {
 #ifdef DCACHE_ALIASING_POSSIBLE
diff --git a/arch/sparc/kernel/sun4d_irq.c b/arch/sparc/kernel/sun4d_irq.c
index f8933be3ca8..a1bb2675b28 100644
--- a/arch/sparc/kernel/sun4d_irq.c
+++ b/arch/sparc/kernel/sun4d_irq.c
@@ -143,7 +143,7 @@ static void sun4d_sbus_handler_irq(int sbusl)
 	}
 }
 
-void sun4d_handler_irq(int pil, struct pt_regs *regs)
+void sun4d_handler_irq(unsigned int pil, struct pt_regs *regs)
 {
 	struct pt_regs *old_regs;
 	/* SBUS IRQ level (1 - 7) */
@@ -236,7 +236,7 @@ static void sun4d_shutdown_irq(struct irq_data *data)
 	irq_unlink(data->irq);
 }
 
-struct irq_chip sun4d_irq = {
+static struct irq_chip sun4d_irq = {
 	.name		= "sun4d",
 	.irq_startup	= sun4d_startup_irq,
 	.irq_shutdown	= sun4d_shutdown_irq,
@@ -285,9 +285,9 @@ static void __init sun4d_load_profile_irqs(void)
 	}
 }
 
-unsigned int _sun4d_build_device_irq(unsigned int real_irq,
-                                     unsigned int pil,
-                                     unsigned int board)
+static unsigned int _sun4d_build_device_irq(unsigned int real_irq,
+                                            unsigned int pil,
+                                            unsigned int board)
 {
 	struct sun4d_handler_data *handler_data;
 	unsigned int irq;
@@ -320,8 +320,8 @@ err_out:
 
 
 
-unsigned int sun4d_build_device_irq(struct platform_device *op,
-                                    unsigned int real_irq)
+static unsigned int sun4d_build_device_irq(struct platform_device *op,
+                                           unsigned int real_irq)
 {
 	struct device_node *dp = op->dev.of_node;
 	struct device_node *board_parent, *bus = dp->parent;
@@ -383,7 +383,8 @@ err_out:
 	return irq;
 }
 
-unsigned int sun4d_build_timer_irq(unsigned int board, unsigned int real_irq)
+static unsigned int sun4d_build_timer_irq(unsigned int board,
+                                          unsigned int real_irq)
 {
 	return _sun4d_build_device_irq(real_irq, real_irq, board);
 }
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index d066eb18650..f834224208e 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -48,6 +48,7 @@ SIGN1(sys32_futex, compat_sys_futex, %o1)
 SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
 SIGN1(sys32_recvmsg, compat_sys_recvmsg, %o0)
 SIGN1(sys32_sendmsg, compat_sys_sendmsg, %o0)
+SIGN2(sys32_renameat2, sys_renameat2, %o0, %o2)
 
 	.globl		sys32_mmap2
 sys32_mmap2:
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index 71368850dfc..022c30c72eb 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -49,6 +49,8 @@
 #include <asm/mmu_context.h>
 #include <asm/compat_signal.h>
 
+#include "systbls.h"
+
 asmlinkage long sys32_truncate64(const char __user * path, unsigned long high, unsigned long low)
 {
 	if ((int)high < 0)
diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index 3a8d1844402..646988d4c1a 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -24,6 +24,8 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 
+#include "systbls.h"
+
 /* #define DEBUG_UNIMP_SYSCALL */
 
 /* XXX Make this per-binary type, this way we can detect the type of
@@ -68,7 +70,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
  * sys_pipe() is the normal C calling standard for creating
  * a pipe. It's not the way unix traditionally does this, though.
  */
-asmlinkage int sparc_pipe(struct pt_regs *regs)
+asmlinkage long sparc_pipe(struct pt_regs *regs)
 {
 	int fd[2];
 	int error;
@@ -93,7 +95,7 @@ int sparc_mmap_check(unsigned long addr, unsigned long len)
 
 /* Linux version of mmap */
 
-asmlinkage unsigned long sys_mmap2(unsigned long addr, unsigned long len,
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
 	unsigned long prot, unsigned long flags, unsigned long fd,
 	unsigned long pgoff)
 {
@@ -103,7 +105,7 @@ asmlinkage unsigned long sys_mmap2(unsigned long addr, unsigned long len,
 			      pgoff >> (PAGE_SHIFT - 12));
 }
 
-asmlinkage unsigned long sys_mmap(unsigned long addr, unsigned long len,
+asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
 	unsigned long prot, unsigned long flags, unsigned long fd,
 	unsigned long off)
 {
@@ -197,7 +199,7 @@ SYSCALL_DEFINE5(rt_sigaction, int, sig,
 	return ret;
 }
 
-asmlinkage int sys_getdomainname(char __user *name, int len)
+asmlinkage long sys_getdomainname(char __user *name, int len)
 {
  	int nlen, err;
  	
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index beb0b5a5f21..c85403d0496 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -31,6 +31,7 @@
 #include <asm/unistd.h>
 
 #include "entry.h"
+#include "kernel.h"
 #include "systbls.h"
 
 /* #define DEBUG_UNIMP_SYSCALL */
diff --git a/arch/sparc/kernel/systbls.h b/arch/sparc/kernel/systbls.h
index 26e6dd72e92..2dab8236d49 100644
--- a/arch/sparc/kernel/systbls.h
+++ b/arch/sparc/kernel/systbls.h
@@ -1,41 +1,103 @@
 #ifndef _SYSTBLS_H
 #define _SYSTBLS_H
 
+#include <linux/signal.h>
 #include <linux/kernel.h>
+#include <linux/compat.h>
 #include <linux/types.h>
-#include <linux/signal.h>
+
 #include <asm/utrap.h>
 
-extern asmlinkage unsigned long sys_getpagesize(void);
-extern asmlinkage long sparc_pipe(struct pt_regs *regs);
-extern asmlinkage long sys_sparc_ipc(unsigned int call, int first,
-			       unsigned long second,
-			       unsigned long third,
-			       void __user *ptr, long fifth);
-extern asmlinkage long sparc64_personality(unsigned long personality);
-extern asmlinkage long sys64_munmap(unsigned long addr, size_t len);
-extern asmlinkage unsigned long sys64_mremap(unsigned long addr,
-					     unsigned long old_len,
-					     unsigned long new_len,
-					     unsigned long flags,
-					     unsigned long new_addr);
-extern asmlinkage unsigned long c_sys_nis_syscall(struct pt_regs *regs);
-extern asmlinkage long sys_getdomainname(char __user *name, int len);
-extern asmlinkage long sys_utrap_install(utrap_entry_t type,
-					 utrap_handler_t new_p,
-					 utrap_handler_t new_d,
-					 utrap_handler_t __user *old_p,
-					 utrap_handler_t __user *old_d);
-extern asmlinkage long sparc_memory_ordering(unsigned long model,
-					     struct pt_regs *regs);
-extern asmlinkage long sys_rt_sigaction(int sig,
-					const struct sigaction __user *act,
-					struct sigaction __user *oact,
-					void __user *restorer,
-					size_t sigsetsize);
+asmlinkage unsigned long sys_getpagesize(void);
+asmlinkage long sparc_pipe(struct pt_regs *regs);
+asmlinkage unsigned long c_sys_nis_syscall(struct pt_regs *regs);
+asmlinkage long sys_getdomainname(char __user *name, int len);
+void do_rt_sigreturn(struct pt_regs *regs);
+asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
+			 unsigned long prot, unsigned long flags,
+			 unsigned long fd, unsigned long off);
+asmlinkage void sparc_breakpoint(struct pt_regs *regs);
+
+#ifdef CONFIG_SPARC32
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
+			  unsigned long prot, unsigned long flags,
+			  unsigned long fd, unsigned long pgoff);
+long sparc_remap_file_pages(unsigned long start, unsigned long size,
+			    unsigned long prot, unsigned long pgoff,
+			    unsigned long flags);
 
-extern asmlinkage void sparc64_set_context(struct pt_regs *regs);
-extern asmlinkage void sparc64_get_context(struct pt_regs *regs);
-extern void do_rt_sigreturn(struct pt_regs *regs);
+#endif /* CONFIG_SPARC32 */
 
+#ifdef CONFIG_SPARC64
+asmlinkage long sys_sparc_ipc(unsigned int call, int first,
+			      unsigned long second,
+			      unsigned long third,
+			      void __user *ptr, long fifth);
+asmlinkage long sparc64_personality(unsigned long personality);
+asmlinkage long sys64_munmap(unsigned long addr, size_t len);
+asmlinkage unsigned long sys64_mremap(unsigned long addr,
+				      unsigned long old_len,
+				      unsigned long new_len,
+				      unsigned long flags,
+				      unsigned long new_addr);
+asmlinkage long sys_utrap_install(utrap_entry_t type,
+				  utrap_handler_t new_p,
+				  utrap_handler_t new_d,
+				  utrap_handler_t __user *old_p,
+				  utrap_handler_t __user *old_d);
+asmlinkage long sparc_memory_ordering(unsigned long model,
+				      struct pt_regs *regs);
+asmlinkage void sparc64_set_context(struct pt_regs *regs);
+asmlinkage void sparc64_get_context(struct pt_regs *regs);
+asmlinkage long sys32_truncate64(const char __user * path,
+				 unsigned long high,
+				 unsigned long low);
+asmlinkage long sys32_ftruncate64(unsigned int fd,
+				  unsigned long high,
+				  unsigned long low);
+struct compat_stat64;
+asmlinkage long compat_sys_stat64(const char __user * filename,
+				  struct compat_stat64 __user *statbuf);
+asmlinkage long compat_sys_lstat64(const char __user * filename,
+				   struct compat_stat64 __user *statbuf);
+asmlinkage long compat_sys_fstat64(unsigned int fd,
+				   struct compat_stat64 __user * statbuf);
+asmlinkage long compat_sys_fstatat64(unsigned int dfd,
+				     const char __user *filename,
+				     struct compat_stat64 __user * statbuf, int flag);
+asmlinkage compat_ssize_t sys32_pread64(unsigned int fd,
+					char __user *ubuf,
+					compat_size_t count,
+					unsigned long poshi,
+					unsigned long poslo);
+asmlinkage compat_ssize_t sys32_pwrite64(unsigned int fd,
+					 char __user *ubuf,
+					 compat_size_t count,
+					 unsigned long poshi,
+					 unsigned long poslo);
+asmlinkage long compat_sys_readahead(int fd,
+				     unsigned long offhi,
+				     unsigned long offlo,
+				     compat_size_t count);
+long compat_sys_fadvise64(int fd,
+			  unsigned long offhi,
+			  unsigned long offlo,
+			  compat_size_t len, int advice);
+long compat_sys_fadvise64_64(int fd,
+			     unsigned long offhi, unsigned long offlo,
+			     unsigned long lenhi, unsigned long lenlo,
+			     int advice);
+long sys32_sync_file_range(unsigned int fd,
+			   unsigned long off_high, unsigned long off_low,
+			   unsigned long nb_high, unsigned long nb_low,
+			   unsigned int flags);
+asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo,
+				     u32 lenhi, u32 lenlo);
+asmlinkage long compat_sys_fstat64(unsigned int fd,
+				   struct compat_stat64 __user * statbuf);
+asmlinkage long compat_sys_fstatat64(unsigned int dfd,
+				     const char __user *filename,
+				     struct compat_stat64 __user * statbuf,
+				     int flag);
+#endif /* CONFIG_SPARC64 */
 #endif /* _SYSTBLS_H */
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index 151ace8766c..85fe9b1087c 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -86,3 +86,4 @@ sys_call_table:
 /*330*/	.long sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
 /*335*/	.long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
+/*345*/	.long sys_renameat2
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index 4bd4e2bb26c..33ecba2826e 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -87,6 +87,7 @@ sys_call_table32:
 /*330*/	.word compat_sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, compat_sys_open_by_handle_at, compat_sys_clock_adjtime
 	.word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
+	.word sys32_renameat2
 
 #endif /* CONFIG_COMPAT */
 
@@ -165,3 +166,4 @@ sys_call_table:
 /*330*/	.word sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime
 	.word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
 /*340*/	.word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
+	.word sys_renameat2
diff --git a/arch/sparc/kernel/tadpole.c b/arch/sparc/kernel/tadpole.c
deleted file mode 100644
index 9aba8bd5a78..00000000000
--- a/arch/sparc/kernel/tadpole.c
+++ /dev/null
@@ -1,126 +0,0 @@
-/* tadpole.c: Probing for the tadpole clock stopping h/w at boot time.
- *
- * Copyright (C) 1996 David Redman (djhr@tadpole.co.uk)
- */
-
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-
-#include <asm/asi.h>
-#include <asm/oplib.h>
-#include <asm/io.h>
-
-#define MACIO_SCSI_CSR_ADDR	0x78400000
-#define MACIO_EN_DMA		0x00000200
-#define CLOCK_INIT_DONE		1
-
-static int clk_state;
-static volatile unsigned char *clk_ctrl;
-void (*cpu_pwr_save)(void);
-
-static inline unsigned int ldphys(unsigned int addr)
-{
-	unsigned long data;
-    
-	__asm__ __volatile__("\n\tlda [%1] %2, %0\n\t" : 
-			     "=r" (data) :
-			     "r" (addr), "i" (ASI_M_BYPASS));
-	return data;
-}
-
-static void clk_init(void)
-{
-	__asm__ __volatile__("mov 0x6c, %%g1\n\t"
-			     "mov 0x4c, %%g2\n\t"
-			     "mov 0xdf, %%g3\n\t"
-			     "stb %%g1, [%0+3]\n\t"
-			     "stb %%g2, [%0+3]\n\t"
-			     "stb %%g3, [%0+3]\n\t" : :
-			     "r" (clk_ctrl) :
-			     "g1", "g2", "g3");
-}
-
-static void clk_slow(void)
-{
-	__asm__ __volatile__("mov 0xcc, %%g2\n\t"
-			     "mov 0x4c, %%g3\n\t"
-			     "mov 0xcf, %%g4\n\t"
-			     "mov 0xdf, %%g5\n\t"
-			     "stb %%g2, [%0+3]\n\t"
-			     "stb %%g3, [%0+3]\n\t"
-			     "stb %%g4, [%0+3]\n\t"
-			     "stb %%g5, [%0+3]\n\t" : :
-			     "r" (clk_ctrl) :
-			     "g2", "g3", "g4", "g5");
-}
-
-/*
- * Tadpole is guaranteed to be UP, using local_irq_save.
- */
-static void tsu_clockstop(void)
-{
-	unsigned int mcsr;
-	unsigned long flags;
-
-	if (!clk_ctrl)
-		return;
-	if (!(clk_state & CLOCK_INIT_DONE)) {
-		local_irq_save(flags);
-		clk_init();
-		clk_state |= CLOCK_INIT_DONE;       /* all done */
-		local_irq_restore(flags);
-		return;
-	}
-	if (!(clk_ctrl[2] & 1))
-		return;               /* no speed up yet */
-
-	local_irq_save(flags);
-
-	/* if SCSI DMA in progress, don't slow clock */
-	mcsr = ldphys(MACIO_SCSI_CSR_ADDR);
-	if ((mcsr&MACIO_EN_DMA) != 0) {
-		local_irq_restore(flags);
-		return;
-	}
-	/* TODO... the minimum clock setting ought to increase the
-	 * memory refresh interval..
-	 */
-	clk_slow();
-	local_irq_restore(flags);
-}
-
-static void swift_clockstop(void)
-{
-	if (!clk_ctrl)
-		return;
-	clk_ctrl[0] = 0;
-}
-
-void __init clock_stop_probe(void)
-{
-	phandle node, clk_nd;
-	char name[20];
-    
-	prom_getstring(prom_root_node, "name", name, sizeof(name));
-	if (strncmp(name, "Tadpole", 7))
-		return;
-	node = prom_getchild(prom_root_node);
-	node = prom_searchsiblings(node, "obio");
-	node = prom_getchild(node);
-	clk_nd = prom_searchsiblings(node, "clk-ctrl");
-	if (!clk_nd)
-		return;
-	printk("Clock Stopping h/w detected... ");
-	clk_ctrl = (char *) prom_getint(clk_nd, "address");
-	clk_state = 0;
-	if (name[10] == '\0') {
-		cpu_pwr_save = tsu_clockstop;
-		printk("enabled (S3)\n");
-	} else if ((name[10] == 'X') || (name[10] == 'G')) {
-		cpu_pwr_save = swift_clockstop;
-		printk("enabled (%s)\n",name+7);
-	} else
-		printk("disabled %s\n",name+7);
-}
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index c4c27b0f906..5923d1e4e7c 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -36,6 +36,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 
+#include <asm/mc146818rtc.h>
 #include <asm/oplib.h>
 #include <asm/timex.h>
 #include <asm/timer.h>
@@ -47,6 +48,7 @@
 #include <asm/irq_regs.h>
 #include <asm/setup.h>
 
+#include "kernel.h"
 #include "irq.h"
 
 static __cacheline_aligned_in_smp DEFINE_SEQLOCK(timer_cs_lock);
@@ -83,7 +85,7 @@ unsigned long profile_pc(struct pt_regs *regs)
 
 EXPORT_SYMBOL(profile_pc);
 
-__volatile__ unsigned int *master_l10_counter;
+volatile u32 __iomem *master_l10_counter;
 
 int update_persistent_clock(struct timespec now)
 {
@@ -143,9 +145,9 @@ static __init void setup_timer_ce(void)
 
 static unsigned int sbus_cycles_offset(void)
 {
-	unsigned int val, offset;
+	u32 val, offset;
 
-	val = *master_l10_counter;
+	val = sbus_readl(master_l10_counter);
 	offset = (val >> TIMER_VALUE_SHIFT) & TIMER_VALUE_MASK;
 
 	/* Limit hit? */
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index 662982946a8..6fd386c5232 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -44,7 +44,7 @@ static void instruction_dump(unsigned long *pc)
 #define __SAVE __asm__ __volatile__("save %sp, -0x40, %sp\n\t")
 #define __RESTORE __asm__ __volatile__("restore %g0, %g0, %g0\n\t")
 
-void die_if_kernel(char *str, struct pt_regs *regs)
+void __noreturn die_if_kernel(char *str, struct pt_regs *regs)
 {
 	static int die_counter;
 	int count = 0;
@@ -219,8 +219,6 @@ static unsigned long fake_fsr;
 static unsigned long fake_queue[32] __attribute__ ((aligned (8)));
 static unsigned long fake_depth;
 
-extern int do_mathemu(struct pt_regs *, struct task_struct *);
-
 void do_fpe_trap(struct pt_regs *regs, unsigned long pc, unsigned long npc,
 		 unsigned long psr)
 {
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 4ced92f0535..fb6640ec855 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -43,8 +43,10 @@
 #include <asm/prom.h>
 #include <asm/memctrl.h>
 #include <asm/cacheflush.h>
+#include <asm/setup.h>
 
 #include "entry.h"
+#include "kernel.h"
 #include "kstack.h"
 
 /* When an irrecoverable trap occurs at tl > 0, the trap entry
@@ -2209,8 +2211,6 @@ out:
 	exception_exit(prev_state);
 }
 
-extern int do_mathemu(struct pt_regs *, struct fpustate *, bool);
-
 void do_fpother(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -2383,7 +2383,7 @@ static inline struct reg_window *kernel_stack_up(struct reg_window *rw)
 	return (struct reg_window *) (fp + STACK_BIAS);
 }
 
-void die_if_kernel(char *str, struct pt_regs *regs)
+void __noreturn die_if_kernel(char *str, struct pt_regs *regs)
 {
 	static int die_counter;
 	int count = 0;
@@ -2433,9 +2433,6 @@ EXPORT_SYMBOL(die_if_kernel);
 #define VIS_OPCODE_MASK	((0x3 << 30) | (0x3f << 19))
 #define VIS_OPCODE_VAL	((0x2 << 30) | (0x36 << 19))
 
-extern int handle_popc(u32 insn, struct pt_regs *regs);
-extern int handle_ldf_stq(u32 insn, struct pt_regs *regs);
-
 void do_illegal_instruction(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -2486,8 +2483,6 @@ out:
 	exception_exit(prev_state);
 }
 
-extern void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn);
-
 void mem_address_unaligned(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr)
 {
 	enum ctx_state prev_state = exception_enter();
diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c
index c0ec8978619..c5c61b3c6b5 100644
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@@ -16,6 +16,10 @@
 #include <linux/smp.h>
 #include <linux/perf_event.h>
 
+#include <asm/setup.h>
+
+#include "kernel.h"
+
 enum direction {
 	load,    /* ld, ldd, ldh, ldsh */
 	store,   /* st, std, sth, stsh */
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index 35ab8b60d25..62098a89bbb 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -24,8 +24,10 @@
 #include <linux/context_tracking.h>
 #include <asm/fpumacro.h>
 #include <asm/cacheflush.h>
+#include <asm/setup.h>
 
 #include "entry.h"
+#include "kernel.h"
 
 enum direction {
 	load,    /* ld, ldd, ldh, ldsh */
diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c
index 3107381e576..87bab0a3857 100644
--- a/arch/sparc/kernel/windows.c
+++ b/arch/sparc/kernel/windows.c
@@ -10,8 +10,11 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 
+#include <asm/cacheflush.h>
 #include <asm/uaccess.h>
 
+#include "kernel.h"
+
 /* Do save's until all user register windows are out of the cpu. */
 void flush_user_windows(void)
 {
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index dbe119b63b4..3269b023409 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -41,7 +41,7 @@ lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
 lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
 lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o
 
-obj-y                 += iomap.o
+obj-$(CONFIG_SPARC64) += iomap.o
 obj-$(CONFIG_SPARC32) += atomic32.o ucmpdi2.o
 obj-y                 += ksyms.o
 obj-$(CONFIG_SPARC64) += PeeCeeI.o
diff --git a/arch/sparc/lib/mcount.S b/arch/sparc/lib/mcount.S
index 3ad6cbdc216..0b0ed4d3421 100644
--- a/arch/sparc/lib/mcount.S
+++ b/arch/sparc/lib/mcount.S
@@ -24,10 +24,7 @@ mcount:
 #ifdef CONFIG_DYNAMIC_FTRACE
 	/* Do nothing, the retl/nop below is all we need.  */
 #else
-	sethi		%hi(function_trace_stop), %g1
-	lduw		[%g1 + %lo(function_trace_stop)], %g2
-	brnz,pn		%g2, 2f
-	 sethi		%hi(ftrace_trace_function), %g1
+	sethi		%hi(ftrace_trace_function), %g1
 	sethi		%hi(ftrace_stub), %g2
 	ldx		[%g1 + %lo(ftrace_trace_function)], %g1
 	or		%g2, %lo(ftrace_stub), %g2
@@ -80,11 +77,8 @@ ftrace_stub:
 	.globl		ftrace_caller
 	.type		ftrace_caller,#function
 ftrace_caller:
-	sethi		%hi(function_trace_stop), %g1
 	mov		%i7, %g2
-	lduw		[%g1 + %lo(function_trace_stop)], %g1
-	brnz,pn		%g1, ftrace_stub
-	 mov		%fp, %g3
+	mov		%fp, %g3
 	save		%sp, -176, %sp
 	mov		%g2, %o1
 	mov		%g2, %l0
diff --git a/arch/sparc/math-emu/sfp-util_32.h b/arch/sparc/math-emu/sfp-util_32.h
index d1b2aff3c25..bb587d5f3d9 100644
--- a/arch/sparc/math-emu/sfp-util_32.h
+++ b/arch/sparc/math-emu/sfp-util_32.h
@@ -4,20 +4,20 @@
 #include <asm/byteorder.h>
 
 #define add_ssaaaa(sh, sl, ah, al, bh, bl) 				\
-  __asm__ ("addcc %r4,%5,%1\n\t"						\
+  __asm__ ("addcc %r4,%5,%1\n\t"					\
 	   "addx %r2,%3,%0\n"						\
-	   : "=r" ((USItype)(sh)),					\
-	     "=&r" ((USItype)(sl))					\
+	   : "=r" (sh),							\
+	     "=&r" (sl)							\
 	   : "%rJ" ((USItype)(ah)),					\
 	     "rI" ((USItype)(bh)),					\
 	     "%rJ" ((USItype)(al)),					\
 	     "rI" ((USItype)(bl))					\
 	   : "cc")
 #define sub_ddmmss(sh, sl, ah, al, bh, bl) 				\
-  __asm__ ("subcc %r4,%5,%1\n\t"						\
+  __asm__ ("subcc %r4,%5,%1\n\t"					\
 	   "subx %r2,%3,%0\n"						\
-	   : "=r" ((USItype)(sh)),					\
-	     "=&r" ((USItype)(sl))					\
+	   : "=r" (sh),							\
+	     "=&r" (sl)							\
 	   : "rJ" ((USItype)(ah)),					\
 	     "rI" ((USItype)(bh)),					\
 	     "rJ" ((USItype)(al)),					\
@@ -65,8 +65,8 @@
 	"mulscc	%%g1,0,%%g1\n\t" 					\
 	"add	%%g1,%%g2,%0\n\t" 					\
 	"rd	%%y,%1\n"						\
-	   : "=r" ((USItype)(w1)),					\
-	     "=r" ((USItype)(w0))					\
+	   : "=r" (w1),							\
+	     "=r" (w0)							\
 	   : "%rI" ((USItype)(u)),					\
 	     "r" ((USItype)(v))						\
 	   : "%g1", "%g2", "cc")
@@ -98,8 +98,8 @@
 	   "sub	%1,%2,%1\n\t"						\
 	   "3:	xnor	%0,0,%0\n\t"					\
 	   "! End of inline udiv_qrnnd\n"				\
-	   : "=&r" ((USItype)(q)),					\
-	     "=&r" ((USItype)(r))					\
+	   : "=&r" (q),							\
+	     "=&r" (r)							\
 	   : "r" ((USItype)(d)),					\
 	     "1" ((USItype)(n1)),					\
 	     "0" ((USItype)(n0)) : "%g1", "cc")
diff --git a/arch/sparc/math-emu/sfp-util_64.h b/arch/sparc/math-emu/sfp-util_64.h
index 425d3cf01af..51320a861cc 100644
--- a/arch/sparc/math-emu/sfp-util_64.h
+++ b/arch/sparc/math-emu/sfp-util_64.h
@@ -17,8 +17,8 @@
   	   "bcs,a,pn %%xcc, 1f\n\t"		\
   	   "add %0, 1, %0\n"			\
   	   "1:"					\
-	   : "=r" ((UDItype)(sh)),		\
-	     "=&r" ((UDItype)(sl))		\
+	   : "=r" (sh),				\
+	     "=&r" (sl)				\
 	   : "r" ((UDItype)(ah)),		\
 	     "r" ((UDItype)(bh)),		\
 	     "r" ((UDItype)(al)),		\
@@ -31,8 +31,8 @@
   	   "bcs,a,pn %%xcc, 1f\n\t"		\
   	   "sub %0, 1, %0\n"			\
   	   "1:"					\
-	   : "=r" ((UDItype)(sh)),		\
-	     "=&r" ((UDItype)(sl))		\
+	   : "=r" (sh),				\
+	     "=&r" (sl)				\
 	   : "r" ((UDItype)(ah)),		\
 	     "r" ((UDItype)(bh)),		\
 	     "r" ((UDItype)(al)),		\
@@ -64,8 +64,8 @@
 		   "sllx %3,32,%3\n\t"			\
 		   "add %1,%3,%1\n\t"			\
 		   "add %5,%2,%0"			\
-	   : "=r" ((UDItype)(wh)),			\
-	     "=&r" ((UDItype)(wl)),			\
+	   : "=r" (wh),					\
+	     "=&r" (wl),				\
 	     "=&r" (tmp1), "=&r" (tmp2), "=&r" (tmp3), "=&r" (tmp4) \
 	   : "r" ((UDItype)(u)),			\
 	     "r" ((UDItype)(v))				\
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 59dbd464572..908e8c17c90 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -26,14 +26,14 @@
 #include <asm/pgtable.h>
 #include <asm/openprom.h>
 #include <asm/oplib.h>
+#include <asm/setup.h>
 #include <asm/smp.h>
 #include <asm/traps.h>
 #include <asm/uaccess.h>
 
-int show_unhandled_signals = 1;
+#include "mm_32.h"
 
-static void unhandled_fault(unsigned long, struct task_struct *,
-		struct pt_regs *) __attribute__ ((noreturn));
+int show_unhandled_signals = 1;
 
 static void __noreturn unhandled_fault(unsigned long address,
 				       struct task_struct *tsk,
@@ -141,9 +141,6 @@ static void __do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 	force_sig_info (sig, &info, current);
 }
 
-extern unsigned long safe_compute_effective_address(struct pt_regs *,
-						    unsigned int);
-
 static unsigned long compute_si_addr(struct pt_regs *regs, int text_fault)
 {
 	unsigned int insn;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 4ced3fc6613..587cd056512 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -32,6 +32,7 @@
 #include <asm/lsu.h>
 #include <asm/sections.h>
 #include <asm/mmu_context.h>
+#include <asm/setup.h>
 
 int show_unhandled_signals = 1;
 
@@ -196,9 +197,6 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 	force_sig_info(sig, &info, current);
 }
 
-extern int handle_ldf_stq(u32, struct pt_regs *);
-extern int handle_ld_nf(u32, struct pt_regs *);
-
 static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn)
 {
 	if (!insn) {
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index db698708280..eb828715527 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -31,10 +31,13 @@
 #include <asm/pgtable.h>
 #include <asm/vaddrs.h>
 #include <asm/pgalloc.h>	/* bug in asm-generic/tlb.h: check_pgt_cache */
+#include <asm/setup.h>
 #include <asm/tlb.h>
 #include <asm/prom.h>
 #include <asm/leon.h>
 
+#include "mm_32.h"
+
 unsigned long *sparc_valid_addr_bitmap;
 EXPORT_SYMBOL(sparc_valid_addr_bitmap);
 
@@ -63,7 +66,6 @@ void show_mem(unsigned int filter)
 }
 
 
-extern unsigned long cmdline_memory_size;
 unsigned long last_valid_pfn;
 
 unsigned long calc_highpages(void)
@@ -246,9 +248,6 @@ unsigned long __init bootmem_init(unsigned long *pages_avail)
  * init routine based upon the Sun model type on the Sparc.
  *
  */
-extern void srmmu_paging_init(void);
-extern void device_scan(void);
-
 void __init paging_init(void)
 {
 	srmmu_paging_init();
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index ed3c969a5f4..16b58ff11e6 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -47,6 +47,7 @@
 #include <asm/prom.h>
 #include <asm/mdesc.h>
 #include <asm/cpudata.h>
+#include <asm/setup.h>
 #include <asm/irq.h>
 
 #include "init_64.h"
@@ -794,11 +795,11 @@ struct node_mem_mask {
 static struct node_mem_mask node_masks[MAX_NUMNODES];
 static int num_node_masks;
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+
 int numa_cpu_lookup_table[NR_CPUS];
 cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES];
 
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-
 struct mdesc_mblock {
 	u64	base;
 	u64	size;
@@ -887,17 +888,21 @@ static void __init allocate_node_data(int nid)
 
 static void init_node_masks_nonnuma(void)
 {
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	int i;
+#endif
 
 	numadbg("Initializing tables for non-numa.\n");
 
 	node_masks[0].mask = node_masks[0].val = 0;
 	num_node_masks = 1;
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 	for (i = 0; i < NR_CPUS; i++)
 		numa_cpu_lookup_table[i] = 0;
 
 	cpumask_setall(&numa_cpumask_lookup_table[0]);
+#endif
 }
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h
index 5d3782deb40..0668b364f44 100644
--- a/arch/sparc/mm/init_64.h
+++ b/arch/sparc/mm/init_64.h
@@ -21,7 +21,7 @@ extern unsigned int sparc64_highest_unlocked_tlb_ent;
 extern unsigned long sparc64_kern_pri_context;
 extern unsigned long sparc64_kern_pri_nuc_bits;
 extern unsigned long sparc64_kern_sec_context;
-extern void mmu_info(struct seq_file *m);
+void mmu_info(struct seq_file *m);
 
 struct linux_prom_translation {
 	unsigned long virt;
@@ -36,7 +36,7 @@ extern unsigned int prom_trans_ents;
 /* Exported for SMP bootup purposes. */
 extern unsigned long kern_locked_tte_data;
 
-extern void prom_world(int enter);
+void prom_world(int enter);
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 #define VMEMMAP_CHUNK_SHIFT	22
diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index eb99862e965..f311bf21901 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -25,6 +25,8 @@
 #include <asm/dma.h>
 #include <asm/oplib.h>
 
+#include "mm_32.h"
+
 /* #define IOUNIT_DEBUG */
 #ifdef IOUNIT_DEBUG
 #define IOD(x) printk(x)
@@ -38,7 +40,8 @@
 static void __init iounit_iommu_init(struct platform_device *op)
 {
 	struct iounit_struct *iounit;
-	iopte_t *xpt, *xptend;
+	iopte_t __iomem *xpt;
+	iopte_t __iomem *xptend;
 
 	iounit = kzalloc(sizeof(struct iounit_struct), GFP_ATOMIC);
 	if (!iounit) {
@@ -62,10 +65,10 @@ static void __init iounit_iommu_init(struct platform_device *op)
 	op->dev.archdata.iommu = iounit;
 	iounit->page_table = xpt;
 	spin_lock_init(&iounit->lock);
-	
-	for (xptend = iounit->page_table + (16 * PAGE_SIZE) / sizeof(iopte_t);
-	     xpt < xptend;)
-	     	iopte_val(*xpt++) = 0;
+
+	xptend = iounit->page_table + (16 * PAGE_SIZE) / sizeof(iopte_t);
+	for (; xpt < xptend; xpt++)
+		sbus_writel(0, xpt);
 }
 
 static int __init iounit_init(void)
@@ -130,7 +133,7 @@ nexti:	scan = find_next_zero_bit(iounit->bmap, limit, scan);
 	vaddr = IOUNIT_DMA_BASE + (scan << PAGE_SHIFT) + (vaddr & ~PAGE_MASK);
 	for (k = 0; k < npages; k++, iopte = __iopte(iopte_val(iopte) + 0x100), scan++) {
 		set_bit(scan, iounit->bmap);
-		iounit->page_table[scan] = iopte;
+		sbus_writel(iopte, &iounit->page_table[scan]);
 	}
 	IOD(("%08lx\n", vaddr));
 	return vaddr;
@@ -202,7 +205,7 @@ static int iounit_map_dma_area(struct device *dev, dma_addr_t *pba, unsigned lon
 	struct iounit_struct *iounit = dev->archdata.iommu;
 	unsigned long page, end;
 	pgprot_t dvma_prot;
-	iopte_t *iopte;
+	iopte_t __iomem *iopte;
 
 	*pba = addr;
 
@@ -224,8 +227,8 @@ static int iounit_map_dma_area(struct device *dev, dma_addr_t *pba, unsigned lon
 			
 			i = ((addr - IOUNIT_DMA_BASE) >> PAGE_SHIFT);
 
-			iopte = (iopte_t *)(iounit->page_table + i);
-			*iopte = MKIOPTE(__pa(page));
+			iopte = iounit->page_table + i;
+			sbus_writel(MKIOPTE(__pa(page)), iopte);
 		}
 		addr += PAGE_SIZE;
 		va += PAGE_SIZE;
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 28f96f27c76..491511d37e3 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -27,6 +27,8 @@
 #include <asm/iommu.h>
 #include <asm/dma.h>
 
+#include "mm_32.h"
+
 /*
  * This can be sized dynamically, but we will do this
  * only when we have a guidance about actual I/O pressures.
@@ -37,9 +39,6 @@
 #define IOMMU_NPTES	(IOMMU_WINSIZE/PAGE_SIZE)	/* 64K PTEs, 256KB */
 #define IOMMU_ORDER	6				/* 4096 * (1<<6) */
 
-/* srmmu.c */
-extern int viking_mxcc_present;
-extern int flush_page_for_dma_global;
 static int viking_flush;
 /* viking.S */
 extern void viking_flush_page(unsigned long page);
@@ -59,6 +58,8 @@ static void __init sbus_iommu_init(struct platform_device *op)
 	struct iommu_struct *iommu;
 	unsigned int impl, vers;
 	unsigned long *bitmap;
+	unsigned long control;
+	unsigned long base;
 	unsigned long tmp;
 
 	iommu = kmalloc(sizeof(struct iommu_struct), GFP_KERNEL);
@@ -73,12 +74,14 @@ static void __init sbus_iommu_init(struct platform_device *op)
 		prom_printf("Cannot map IOMMU registers\n");
 		prom_halt();
 	}
-	impl = (iommu->regs->control & IOMMU_CTRL_IMPL) >> 28;
-	vers = (iommu->regs->control & IOMMU_CTRL_VERS) >> 24;
-	tmp = iommu->regs->control;
-	tmp &= ~(IOMMU_CTRL_RNGE);
-	tmp |= (IOMMU_RNGE_256MB | IOMMU_CTRL_ENAB);
-	iommu->regs->control = tmp;
+
+	control = sbus_readl(&iommu->regs->control);
+	impl = (control & IOMMU_CTRL_IMPL) >> 28;
+	vers = (control & IOMMU_CTRL_VERS) >> 24;
+	control &= ~(IOMMU_CTRL_RNGE);
+	control |= (IOMMU_RNGE_256MB | IOMMU_CTRL_ENAB);
+	sbus_writel(control, &iommu->regs->control);
+
 	iommu_invalidate(iommu->regs);
 	iommu->start = IOMMU_START;
 	iommu->end = 0xffffffff;
@@ -100,7 +103,9 @@ static void __init sbus_iommu_init(struct platform_device *op)
 	memset(iommu->page_table, 0, IOMMU_NPTES*sizeof(iopte_t));
 	flush_cache_all();
 	flush_tlb_all();
-	iommu->regs->base = __pa((unsigned long) iommu->page_table) >> 4;
+
+	base = __pa((unsigned long)iommu->page_table) >> 4;
+	sbus_writel(base, &iommu->regs->base);
 	iommu_invalidate(iommu->regs);
 
 	bitmap = kmalloc(IOMMU_NPTES>>3, GFP_KERNEL);
diff --git a/arch/sparc/mm/leon_mm.c b/arch/sparc/mm/leon_mm.c
index 5bed085a2c1..3b17b6f7895 100644
--- a/arch/sparc/mm/leon_mm.c
+++ b/arch/sparc/mm/leon_mm.c
@@ -15,10 +15,10 @@
 #include <asm/leon.h>
 #include <asm/tlbflush.h>
 
-#include "srmmu.h"
+#include "mm_32.h"
 
 int leon_flush_during_switch = 1;
-int srmmu_swprobe_trace;
+static int srmmu_swprobe_trace;
 
 static inline unsigned long leon_get_ctable_ptr(void)
 {
diff --git a/arch/sparc/mm/mm_32.h b/arch/sparc/mm/mm_32.h
new file mode 100644
index 00000000000..a6c27ca9a72
--- /dev/null
+++ b/arch/sparc/mm/mm_32.h
@@ -0,0 +1,24 @@
+/* fault_32.c - visible as they are called from assembler */
+asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc,
+                            unsigned long address);
+asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
+                               unsigned long address);
+
+void window_overflow_fault(void);
+void window_underflow_fault(unsigned long sp);
+void window_ret_fault(struct pt_regs *regs);
+
+/* srmmu.c */
+extern char *srmmu_name;
+extern int viking_mxcc_present;
+extern int flush_page_for_dma_global;
+
+extern void (*poke_srmmu)(void);
+
+void __init srmmu_paging_init(void);
+
+/* iommu.c */
+void ld_mmu_iommu(void);
+
+/* io-unit.c */
+void ld_mmu_iounit(void);
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index cfbe53c17b0..be65f035d18 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -49,7 +49,7 @@
 #include <asm/mxcc.h>
 #include <asm/ross.h>
 
-#include "srmmu.h"
+#include "mm_32.h"
 
 enum mbus_module srmmu_modtype;
 static unsigned int hwbug_bitmask;
@@ -100,7 +100,6 @@ static unsigned long srmmu_nocache_end;
 #define SRMMU_NOCACHE_ALIGN_MAX (sizeof(ctxd_t)*SRMMU_MAX_CONTEXTS)
 
 void *srmmu_nocache_pool;
-void *srmmu_nocache_bitmap;
 static struct bit_map srmmu_nocache_map;
 
 static inline int srmmu_pmd_none(pmd_t pmd)
@@ -173,7 +172,7 @@ static void *__srmmu_get_nocache(int size, int align)
 		printk(KERN_ERR "srmmu: out of nocache %d: %d/%d\n",
 		       size, (int) srmmu_nocache_size,
 		       srmmu_nocache_map.used << SRMMU_NOCACHE_BITMAP_SHIFT);
-		return 0;
+		return NULL;
 	}
 
 	addr = SRMMU_NOCACHE_VADDR + (offset << SRMMU_NOCACHE_BITMAP_SHIFT);
@@ -269,6 +268,7 @@ static void __init srmmu_nocache_calcsize(void)
 
 static void __init srmmu_nocache_init(void)
 {
+	void *srmmu_nocache_bitmap;
 	unsigned int bitmap_bits;
 	pgd_t *pgd;
 	pmd_t *pmd;
@@ -728,7 +728,7 @@ static inline unsigned long srmmu_probe(unsigned long vaddr)
 				     "=r" (retval) :
 				     "r" (vaddr | 0x400), "i" (ASI_M_FLUSH_PROBE));
 	} else {
-		retval = leon_swprobe(vaddr, 0);
+		retval = leon_swprobe(vaddr, NULL);
 	}
 	return retval;
 }
@@ -865,8 +865,6 @@ static void __init map_kernel(void)
 
 void (*poke_srmmu)(void) = NULL;
 
-extern unsigned long bootmem_init(unsigned long *pages_avail);
-
 void __init srmmu_paging_init(void)
 {
 	int i;
@@ -1771,9 +1769,6 @@ static struct sparc32_cachetlb_ops smp_cachetlb_ops = {
 /* Load up routines and constants for sun4m and sun4d mmu */
 void __init load_mmu(void)
 {
-	extern void ld_mmu_iommu(void);
-	extern void ld_mmu_iounit(void);
-
 	/* Functions */
 	get_srmmu_type();
 
diff --git a/arch/sparc/mm/srmmu.h b/arch/sparc/mm/srmmu.h
deleted file mode 100644
index 5703274ccf8..00000000000
--- a/arch/sparc/mm/srmmu.h
+++ /dev/null
@@ -1,4 +0,0 @@
-/* srmmu.c */
-extern char *srmmu_name;
-
-extern void (*poke_srmmu)(void);
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index fe19b81acc0..a06576683c3 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -9,6 +9,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
+#include <asm/setup.h>
 #include <asm/tsb.h>
 #include <asm/tlb.h>
 #include <asm/oplib.h>
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index a82c6b2a978..892a102671a 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -83,9 +83,9 @@ static void bpf_flush_icache(void *start_, void *end_)
 #define BNE		(F2(0, 2) | CONDNE)
 
 #ifdef CONFIG_SPARC64
-#define BNE_PTR		(F2(0, 1) | CONDNE | (2 << 20))
+#define BE_PTR		(F2(0, 1) | CONDE | (2 << 20))
 #else
-#define BNE_PTR		BNE
+#define BE_PTR		BE
 #endif
 
 #define SETHI(K, REG)	\
@@ -415,20 +415,11 @@ void bpf_jit_compile(struct sk_filter *fp)
 		emit_reg_move(O7, r_saved_O7);
 
 		switch (filter[0].code) {
-		case BPF_S_RET_K:
-		case BPF_S_LD_W_LEN:
-		case BPF_S_ANC_PROTOCOL:
-		case BPF_S_ANC_PKTTYPE:
-		case BPF_S_ANC_IFINDEX:
-		case BPF_S_ANC_MARK:
-		case BPF_S_ANC_RXHASH:
-		case BPF_S_ANC_VLAN_TAG:
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
-		case BPF_S_ANC_CPU:
-		case BPF_S_ANC_QUEUE:
-		case BPF_S_LD_W_ABS:
-		case BPF_S_LD_H_ABS:
-		case BPF_S_LD_B_ABS:
+		case BPF_RET | BPF_K:
+		case BPF_LD | BPF_W | BPF_LEN:
+		case BPF_LD | BPF_W | BPF_ABS:
+		case BPF_LD | BPF_H | BPF_ABS:
+		case BPF_LD | BPF_B | BPF_ABS:
 			/* The first instruction sets the A register (or is
 			 * a "RET 'constant'")
 			 */
@@ -445,59 +436,60 @@ void bpf_jit_compile(struct sk_filter *fp)
 			unsigned int t_offset;
 			unsigned int f_offset;
 			u32 t_op, f_op;
+			u16 code = bpf_anc_helper(&filter[i]);
 			int ilen;
 
-			switch (filter[i].code) {
-			case BPF_S_ALU_ADD_X:	/* A += X; */
+			switch (code) {
+			case BPF_ALU | BPF_ADD | BPF_X:	/* A += X; */
 				emit_alu_X(ADD);
 				break;
-			case BPF_S_ALU_ADD_K:	/* A += K; */
+			case BPF_ALU | BPF_ADD | BPF_K:	/* A += K; */
 				emit_alu_K(ADD, K);
 				break;
-			case BPF_S_ALU_SUB_X:	/* A -= X; */
+			case BPF_ALU | BPF_SUB | BPF_X:	/* A -= X; */
 				emit_alu_X(SUB);
 				break;
-			case BPF_S_ALU_SUB_K:	/* A -= K */
+			case BPF_ALU | BPF_SUB | BPF_K:	/* A -= K */
 				emit_alu_K(SUB, K);
 				break;
-			case BPF_S_ALU_AND_X:	/* A &= X */
+			case BPF_ALU | BPF_AND | BPF_X:	/* A &= X */
 				emit_alu_X(AND);
 				break;
-			case BPF_S_ALU_AND_K:	/* A &= K */
+			case BPF_ALU | BPF_AND | BPF_K:	/* A &= K */
 				emit_alu_K(AND, K);
 				break;
-			case BPF_S_ALU_OR_X:	/* A |= X */
+			case BPF_ALU | BPF_OR | BPF_X:	/* A |= X */
 				emit_alu_X(OR);
 				break;
-			case BPF_S_ALU_OR_K:	/* A |= K */
+			case BPF_ALU | BPF_OR | BPF_K:	/* A |= K */
 				emit_alu_K(OR, K);
 				break;
-			case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */
-			case BPF_S_ALU_XOR_X:
+			case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */
+			case BPF_ALU | BPF_XOR | BPF_X:
 				emit_alu_X(XOR);
 				break;
-			case BPF_S_ALU_XOR_K:	/* A ^= K */
+			case BPF_ALU | BPF_XOR | BPF_K:	/* A ^= K */
 				emit_alu_K(XOR, K);
 				break;
-			case BPF_S_ALU_LSH_X:	/* A <<= X */
+			case BPF_ALU | BPF_LSH | BPF_X:	/* A <<= X */
 				emit_alu_X(SLL);
 				break;
-			case BPF_S_ALU_LSH_K:	/* A <<= K */
+			case BPF_ALU | BPF_LSH | BPF_K:	/* A <<= K */
 				emit_alu_K(SLL, K);
 				break;
-			case BPF_S_ALU_RSH_X:	/* A >>= X */
+			case BPF_ALU | BPF_RSH | BPF_X:	/* A >>= X */
 				emit_alu_X(SRL);
 				break;
-			case BPF_S_ALU_RSH_K:	/* A >>= K */
+			case BPF_ALU | BPF_RSH | BPF_K:	/* A >>= K */
 				emit_alu_K(SRL, K);
 				break;
-			case BPF_S_ALU_MUL_X:	/* A *= X; */
+			case BPF_ALU | BPF_MUL | BPF_X:	/* A *= X; */
 				emit_alu_X(MUL);
 				break;
-			case BPF_S_ALU_MUL_K:	/* A *= K */
+			case BPF_ALU | BPF_MUL | BPF_K:	/* A *= K */
 				emit_alu_K(MUL, K);
 				break;
-			case BPF_S_ALU_DIV_K:	/* A /= K with K != 0*/
+			case BPF_ALU | BPF_DIV | BPF_K:	/* A /= K with K != 0*/
 				if (K == 1)
 					break;
 				emit_write_y(G0);
@@ -512,7 +504,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 #endif
 				emit_alu_K(DIV, K);
 				break;
-			case BPF_S_ALU_DIV_X:	/* A /= X; */
+			case BPF_ALU | BPF_DIV | BPF_X:	/* A /= X; */
 				emit_cmpi(r_X, 0);
 				if (pc_ret0 > 0) {
 					t_offset = addrs[pc_ret0 - 1];
@@ -544,10 +536,10 @@ void bpf_jit_compile(struct sk_filter *fp)
 #endif
 				emit_alu_X(DIV);
 				break;
-			case BPF_S_ALU_NEG:
+			case BPF_ALU | BPF_NEG:
 				emit_neg();
 				break;
-			case BPF_S_RET_K:
+			case BPF_RET | BPF_K:
 				if (!K) {
 					if (pc_ret0 == -1)
 						pc_ret0 = i;
@@ -556,7 +548,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 					emit_loadimm(K, r_A);
 				}
 				/* Fallthrough */
-			case BPF_S_RET_A:
+			case BPF_RET | BPF_A:
 				if (seen_or_pass0) {
 					if (i != flen - 1) {
 						emit_jump(cleanup_addr);
@@ -573,18 +565,18 @@ void bpf_jit_compile(struct sk_filter *fp)
 				emit_jmpl(r_saved_O7, 8, G0);
 				emit_reg_move(r_A, O0); /* delay slot */
 				break;
-			case BPF_S_MISC_TAX:
+			case BPF_MISC | BPF_TAX:
 				seen |= SEEN_XREG;
 				emit_reg_move(r_A, r_X);
 				break;
-			case BPF_S_MISC_TXA:
+			case BPF_MISC | BPF_TXA:
 				seen |= SEEN_XREG;
 				emit_reg_move(r_X, r_A);
 				break;
-			case BPF_S_ANC_CPU:
+			case BPF_ANC | SKF_AD_CPU:
 				emit_load_cpu(r_A);
 				break;
-			case BPF_S_ANC_PROTOCOL:
+			case BPF_ANC | SKF_AD_PROTOCOL:
 				emit_skb_load16(protocol, r_A);
 				break;
 #if 0
@@ -592,38 +584,38 @@ void bpf_jit_compile(struct sk_filter *fp)
 				 * a bit field even though we very much
 				 * know what we are doing here.
 				 */
-			case BPF_S_ANC_PKTTYPE:
+			case BPF_ANC | SKF_AD_PKTTYPE:
 				__emit_skb_load8(pkt_type, r_A);
 				emit_alu_K(SRL, 5);
 				break;
 #endif
-			case BPF_S_ANC_IFINDEX:
+			case BPF_ANC | SKF_AD_IFINDEX:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load32(r_A, struct net_device, ifindex, r_A);
 				break;
-			case BPF_S_ANC_MARK:
+			case BPF_ANC | SKF_AD_MARK:
 				emit_skb_load32(mark, r_A);
 				break;
-			case BPF_S_ANC_QUEUE:
+			case BPF_ANC | SKF_AD_QUEUE:
 				emit_skb_load16(queue_mapping, r_A);
 				break;
-			case BPF_S_ANC_HATYPE:
+			case BPF_ANC | SKF_AD_HATYPE:
 				emit_skb_loadptr(dev, r_A);
 				emit_cmpi(r_A, 0);
-				emit_branch(BNE_PTR, cleanup_addr + 4);
+				emit_branch(BE_PTR, cleanup_addr + 4);
 				emit_nop();
 				emit_load16(r_A, struct net_device, type, r_A);
 				break;
-			case BPF_S_ANC_RXHASH:
+			case BPF_ANC | SKF_AD_RXHASH:
 				emit_skb_load32(hash, r_A);
 				break;
-			case BPF_S_ANC_VLAN_TAG:
-			case BPF_S_ANC_VLAN_TAG_PRESENT:
+			case BPF_ANC | SKF_AD_VLAN_TAG:
+			case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
 				emit_skb_load16(vlan_tci, r_A);
-				if (filter[i].code == BPF_S_ANC_VLAN_TAG) {
+				if (code == (BPF_ANC | SKF_AD_VLAN_TAG)) {
 					emit_andi(r_A, VLAN_VID_MASK, r_A);
 				} else {
 					emit_loadimm(VLAN_TAG_PRESENT, r_TMP);
@@ -631,44 +623,44 @@ void bpf_jit_compile(struct sk_filter *fp)
 				}
 				break;
 
-			case BPF_S_LD_IMM:
+			case BPF_LD | BPF_IMM:
 				emit_loadimm(K, r_A);
 				break;
-			case BPF_S_LDX_IMM:
+			case BPF_LDX | BPF_IMM:
 				emit_loadimm(K, r_X);
 				break;
-			case BPF_S_LD_MEM:
+			case BPF_LD | BPF_MEM:
 				emit_ldmem(K * 4, r_A);
 				break;
-			case BPF_S_LDX_MEM:
+			case BPF_LDX | BPF_MEM:
 				emit_ldmem(K * 4, r_X);
 				break;
-			case BPF_S_ST:
+			case BPF_ST:
 				emit_stmem(K * 4, r_A);
 				break;
-			case BPF_S_STX:
+			case BPF_STX:
 				emit_stmem(K * 4, r_X);
 				break;
 
 #define CHOOSE_LOAD_FUNC(K, func) \
 	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
-			case BPF_S_LD_W_ABS:
+			case BPF_LD | BPF_W | BPF_ABS:
 				func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_word);
 common_load:			seen |= SEEN_DATAREF;
 				emit_loadimm(K, r_OFF);
 				emit_call(func);
 				break;
-			case BPF_S_LD_H_ABS:
+			case BPF_LD | BPF_H | BPF_ABS:
 				func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_half);
 				goto common_load;
-			case BPF_S_LD_B_ABS:
+			case BPF_LD | BPF_B | BPF_ABS:
 				func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte);
 				goto common_load;
-			case BPF_S_LDX_B_MSH:
+			case BPF_LDX | BPF_B | BPF_MSH:
 				func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte_msh);
 				goto common_load;
-			case BPF_S_LD_W_IND:
+			case BPF_LD | BPF_W | BPF_IND:
 				func = bpf_jit_load_word;
 common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 				if (K) {
@@ -683,13 +675,13 @@ common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 				}
 				emit_call(func);
 				break;
-			case BPF_S_LD_H_IND:
+			case BPF_LD | BPF_H | BPF_IND:
 				func = bpf_jit_load_half;
 				goto common_load_ind;
-			case BPF_S_LD_B_IND:
+			case BPF_LD | BPF_B | BPF_IND:
 				func = bpf_jit_load_byte;
 				goto common_load_ind;
-			case BPF_S_JMP_JA:
+			case BPF_JMP | BPF_JA:
 				emit_jump(addrs[i + K]);
 				emit_nop();
 				break;
@@ -700,14 +692,14 @@ common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 		f_op = FOP;		\
 		goto cond_branch
 
-			COND_SEL(BPF_S_JMP_JGT_K, BGU, BLEU);
-			COND_SEL(BPF_S_JMP_JGE_K, BGEU, BLU);
-			COND_SEL(BPF_S_JMP_JEQ_K, BE, BNE);
-			COND_SEL(BPF_S_JMP_JSET_K, BNE, BE);
-			COND_SEL(BPF_S_JMP_JGT_X, BGU, BLEU);
-			COND_SEL(BPF_S_JMP_JGE_X, BGEU, BLU);
-			COND_SEL(BPF_S_JMP_JEQ_X, BE, BNE);
-			COND_SEL(BPF_S_JMP_JSET_X, BNE, BE);
+			COND_SEL(BPF_JMP | BPF_JGT | BPF_K, BGU, BLEU);
+			COND_SEL(BPF_JMP | BPF_JGE | BPF_K, BGEU, BLU);
+			COND_SEL(BPF_JMP | BPF_JEQ | BPF_K, BE, BNE);
+			COND_SEL(BPF_JMP | BPF_JSET | BPF_K, BNE, BE);
+			COND_SEL(BPF_JMP | BPF_JGT | BPF_X, BGU, BLEU);
+			COND_SEL(BPF_JMP | BPF_JGE | BPF_X, BGEU, BLU);
+			COND_SEL(BPF_JMP | BPF_JEQ | BPF_X, BE, BNE);
+			COND_SEL(BPF_JMP | BPF_JSET | BPF_X, BNE, BE);
 
 cond_branch:			f_offset = addrs[i + filter[i].jf];
 				t_offset = addrs[i + filter[i].jt];
@@ -719,20 +711,20 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 					break;
 				}
 
-				switch (filter[i].code) {
-				case BPF_S_JMP_JGT_X:
-				case BPF_S_JMP_JGE_X:
-				case BPF_S_JMP_JEQ_X:
+				switch (code) {
+				case BPF_JMP | BPF_JGT | BPF_X:
+				case BPF_JMP | BPF_JGE | BPF_X:
+				case BPF_JMP | BPF_JEQ | BPF_X:
 					seen |= SEEN_XREG;
 					emit_cmp(r_A, r_X);
 					break;
-				case BPF_S_JMP_JSET_X:
+				case BPF_JMP | BPF_JSET | BPF_X:
 					seen |= SEEN_XREG;
 					emit_btst(r_A, r_X);
 					break;
-				case BPF_S_JMP_JEQ_K:
-				case BPF_S_JMP_JGT_K:
-				case BPF_S_JMP_JGE_K:
+				case BPF_JMP | BPF_JEQ | BPF_K:
+				case BPF_JMP | BPF_JGT | BPF_K:
+				case BPF_JMP | BPF_JGE | BPF_K:
 					if (is_simm13(K)) {
 						emit_cmpi(r_A, K);
 					} else {
@@ -740,7 +732,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 						emit_cmp(r_A, r_TMP);
 					}
 					break;
-				case BPF_S_JMP_JSET_K:
+				case BPF_JMP | BPF_JSET | BPF_K:
 					if (is_simm13(K)) {
 						emit_btsti(r_A, K);
 					} else {
diff --git a/arch/sparc/prom/misc_64.c b/arch/sparc/prom/misc_64.c
index f178b9dcc7b..53a696d3eb3 100644
--- a/arch/sparc/prom/misc_64.c
+++ b/arch/sparc/prom/misc_64.c
@@ -81,11 +81,6 @@ void prom_feval(const char *fstring)
 }
 EXPORT_SYMBOL(prom_feval);
 
-#ifdef CONFIG_SMP
-extern void smp_capture(void);
-extern void smp_release(void);
-#endif
-
 /* Drop into the prom, with the chance to continue with the 'go'
  * prom command.
  */
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 4f3006b600e..7fcd492adbf 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -128,7 +128,6 @@ config TILEGX
 	select SPARSE_IRQ
 	select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
 	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h
index 42323636c45..dd4f9f17e30 100644
--- a/arch/tile/include/asm/processor.h
+++ b/arch/tile/include/asm/processor.h
@@ -266,6 +266,8 @@ static inline void cpu_relax(void)
 	barrier();
 }
 
+#define cpu_relax_lowlatency() cpu_relax()
+
 /* Info on this processor (see fs/proc/cpuinfo.c) */
 struct seq_operations;
 extern const struct seq_operations cpuinfo_op;
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index d767ff9f59b..48e4fd0f38e 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -94,7 +94,7 @@ register unsigned long stack_pointer __asm__("sp");
 /* Sit on a nap instruction until interrupted. */
 extern void smp_nap(void);
 
-/* Enable interrupts racelessly and nap forever: helper for cpu_idle(). */
+/* Enable interrupts racelessly and nap forever: helper for arch_cpu_idle(). */
 extern void _cpu_idle(void);
 
 #else /* __ASSEMBLY__ */
diff --git a/arch/tile/kernel/mcount_64.S b/arch/tile/kernel/mcount_64.S
index 70d7bb0c4d8..3c2b8d5e1d1 100644
--- a/arch/tile/kernel/mcount_64.S
+++ b/arch/tile/kernel/mcount_64.S
@@ -77,15 +77,6 @@ STD_ENDPROC(__mcount)
 
 	.align	64
 STD_ENTRY(ftrace_caller)
-	moveli	r11, hw2_last(function_trace_stop)
-	{ shl16insli	r11, r11, hw1(function_trace_stop); move r12, lr }
-	{ shl16insli	r11, r11, hw0(function_trace_stop); move lr, r10 }
-	ld	r11, r11
-	beqz	r11, 1f
-	jrp	r12
-
-1:
-	{ move	r10, lr; move	lr, r12 }
 	MCOUNT_SAVE_REGS
 
 	/* arg1: self return address */
@@ -119,15 +110,6 @@ STD_ENDPROC(ftrace_caller)
 
 	.align	64
 STD_ENTRY(__mcount)
-	moveli	r11, hw2_last(function_trace_stop)
-	{ shl16insli	r11, r11, hw1(function_trace_stop); move r12, lr }
-	{ shl16insli	r11, r11, hw0(function_trace_stop); move lr, r10 }
-	ld	r11, r11
-	beqz	r11, 1f
-	jrp	r12
-
-1:
-	{ move	r10, lr; move	lr, r12 }
 	{
 	 moveli	r11, hw2_last(ftrace_trace_function)
 	 moveli	r13, hw2_last(ftrace_stub)
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 74c91729a62..112ababa9e5 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -228,13 +228,10 @@ early_param("isolnodes", setup_isolnodes);
 #if defined(CONFIG_PCI) && !defined(__tilegx__)
 static int __init setup_pci_reserve(char* str)
 {
-	unsigned long mb;
-
-	if (str == NULL || strict_strtoul(str, 0, &mb) != 0 ||
-	    mb > 3 * 1024)
+	if (str == NULL || kstrtouint(str, 0, &pci_reserve_mb) != 0 ||
+	    pci_reserve_mb > 3 * 1024)
 		return -EINVAL;
 
-	pci_reserve_mb = mb;
 	pr_info("Reserving %dMB for PCIE root complex mappings\n",
 		pci_reserve_mb);
 	return 0;
@@ -691,7 +688,7 @@ static void __init setup_bootmem_allocator(void)
 	/* Reserve any memory excluded by "memmap" arguments. */
 	for (i = 0; i < memmap_nr; ++i) {
 		struct memmap_entry *m = &memmap_map[i];
-		reserve_bootmem(m->addr, m->size, 0);
+		reserve_bootmem(m->addr, m->size, BOOTMEM_DEFAULT);
 	}
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -715,7 +712,8 @@ static void __init setup_bootmem_allocator(void)
 
 #ifdef CONFIG_KEXEC
 	if (crashk_res.start != crashk_res.end)
-		reserve_bootmem(crashk_res.start, resource_size(&crashk_res), 0);
+		reserve_bootmem(crashk_res.start, resource_size(&crashk_res),
+				BOOTMEM_DEFAULT);
 #endif
 }
 
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index 2d1dbf38a9a..d1d026f0126 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -321,14 +321,13 @@ int show_unhandled_signals = 1;
 
 static int __init crashinfo(char *str)
 {
-	unsigned long val;
 	const char *word;
 
 	if (*str == '\0')
-		val = 2;
-	else if (*str != '=' || strict_strtoul(++str, 0, &val) != 0)
+		show_unhandled_signals = 2;
+	else if (*str != '=' || kstrtoint(++str, 0, &show_unhandled_signals) != 0)
 		return 0;
-	show_unhandled_signals = val;
+
 	switch (show_unhandled_signals) {
 	case 0:
 		word = "No";
diff --git a/arch/tile/kernel/traps.c b/arch/tile/kernel/traps.c
index 6b603d556ca..f3ceb6308e4 100644
--- a/arch/tile/kernel/traps.c
+++ b/arch/tile/kernel/traps.c
@@ -42,10 +42,9 @@ static int __init setup_unaligned_fixup(char *str)
 	 * will still parse the instruction, then fire a SIGBUS with
 	 * the correct address from inside the single_step code.
 	 */
-	long val;
-	if (strict_strtol(str, 0, &val) != 0)
+	if (kstrtoint(str, 0, &unaligned_fixup) != 0)
 		return 0;
-	unaligned_fixup = val;
+
 	pr_info("Fixups for unaligned data accesses are %s\n",
 	       unaligned_fixup >= 0 ?
 	       (unaligned_fixup ? "enabled" : "disabled") :
diff --git a/arch/tile/kernel/unaligned.c b/arch/tile/kernel/unaligned.c
index b030b4e7884..c02ea2a45f6 100644
--- a/arch/tile/kernel/unaligned.c
+++ b/arch/tile/kernel/unaligned.c
@@ -182,18 +182,7 @@ static void find_regs(tilegx_bundle_bits bundle, uint64_t *rd, uint64_t *ra,
 	int i;
 	uint64_t reg;
 	uint64_t reg_map = 0, alias_reg_map = 0, map;
-	bool alias;
-
-	*ra = -1;
-	*rb = -1;
-
-	if (rd)
-		*rd = -1;
-
-	*clob1 = -1;
-	*clob2 = -1;
-	*clob3 = -1;
-	alias = false;
+	bool alias = false;
 
 	/*
 	 * Parse fault bundle, find potential used registers and mark
@@ -569,7 +558,7 @@ void jit_bundle_gen(struct pt_regs *regs, tilegx_bundle_bits bundle,
 	tilegx_bundle_bits bundle_2 = 0;
 	/* If bundle_2_enable = false, bundle_2 is fnop/nop operation. */
 	bool     bundle_2_enable = true;
-	uint64_t ra, rb, rd = -1, clob1, clob2, clob3;
+	uint64_t ra = -1, rb = -1, rd = -1, clob1 = -1, clob2 = -1, clob3 = -1;
 	/*
 	 * Indicate if the unalign access
 	 * instruction's registers hit with
diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index 0fa1acfac79..bfb3127b4df 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -273,9 +273,9 @@ static pgprot_t __init init_pgprot(ulong address)
 	/*
 	 * Otherwise we just hand out consecutive cpus.  To avoid
 	 * requiring this function to hold state, we just walk forward from
-	 * _sdata by PAGE_SIZE, skipping the readonly and init data, to reach
-	 * the requested address, while walking cpu home around kdata_mask.
-	 * This is typically no more than a dozen or so iterations.
+	 * __end_rodata by PAGE_SIZE, skipping the readonly and init data, to
+	 * reach the requested address, while walking cpu home around
+	 * kdata_mask. This is typically no more than a dozen or so iterations.
 	 */
 	page = (((ulong)__end_rodata) + PAGE_SIZE - 1) & PAGE_MASK;
 	BUG_ON(address < page || address >= (ulong)_end);
@@ -912,7 +912,7 @@ static long __write_once initfree = 1;
 static int __init set_initfree(char *str)
 {
 	long val;
-	if (strict_strtol(str, 0, &val) == 0) {
+	if (kstrtol(str, 0, &val) == 0) {
 		initfree = val;
 		pr_info("initfree: %s free init pages\n",
 			initfree ? "will" : "won't");
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 36e658a4291..e4b1a9639c4 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -111,8 +111,7 @@ endef
 KBUILD_KCONFIG := $(HOST_DIR)/um/Kconfig
 
 archheaders:
-	$(Q)$(MAKE) -C '$(srctree)' KBUILD_SRC= \
-		ARCH=$(HEADER_ARCH) O='$(objtree)' archheaders
+	$(Q)$(MAKE) KBUILD_SRC= ARCH=$(HEADER_ARCH) archheaders
 
 archprepare: include/generated/user_constants.h
 
diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c
index 9472079471b..f1b3eb14b85 100644
--- a/arch/um/kernel/tlb.c
+++ b/arch/um/kernel/tlb.c
@@ -12,6 +12,7 @@
 #include <mem_user.h>
 #include <os.h>
 #include <skas.h>
+#include <kern_util.h>
 
 struct host_vm_change {
 	struct host_vm_op {
@@ -124,6 +125,9 @@ static int add_munmap(unsigned long addr, unsigned long len,
 	struct host_vm_op *last;
 	int ret = 0;
 
+	if ((addr >= STUB_START) && (addr < STUB_END))
+		return -EINVAL;
+
 	if (hvc->index != 0) {
 		last = &hvc->ops[hvc->index - 1];
 		if ((last->type == MUNMAP) &&
@@ -283,8 +287,11 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 	/* This is not an else because ret is modified above */
 	if (ret) {
 		printk(KERN_ERR "fix_range_common: failed, killing current "
-		       "process\n");
+		       "process: %d\n", task_tgid_vnr(current));
+		/* We are under mmap_sem, release it such that current can terminate */
+		up_write(&current->mm->mmap_sem);
 		force_sig(SIGKILL, current);
+		do_signal();
 	}
 }
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index 974b87474a9..5678c3571e7 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -206,7 +206,7 @@ unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
 	int is_write = FAULT_WRITE(fi);
 	unsigned long address = FAULT_ADDRESS(fi);
 
-	if (regs)
+	if (!is_user && regs)
 		current->thread.segv_regs = container_of(regs, struct pt_regs, regs);
 
 	if (!is_user && (address >= start_vm) && (address < end_vm)) {
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index d531879a461..908579f2b0a 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -54,7 +54,7 @@ static int ptrace_dump_regs(int pid)
 
 void wait_stub_done(int pid)
 {
-	int n, status, err, bad_stop = 0;
+	int n, status, err;
 
 	while (1) {
 		CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED | __WALL));
@@ -74,8 +74,6 @@ void wait_stub_done(int pid)
 
 	if (((1 << WSTOPSIG(status)) & STUB_DONE_MASK) != 0)
 		return;
-	else
-		bad_stop = 1;
 
 bad_wait:
 	err = ptrace_dump_regs(pid);
@@ -85,10 +83,7 @@ bad_wait:
 	printk(UM_KERN_ERR "wait_stub_done : failed to wait for SIGTRAP, "
 	       "pid = %d, n = %d, errno = %d, status = 0x%x\n", pid, n, errno,
 	       status);
-	if (bad_stop)
-		kill(pid, SIGKILL);
-	else
-		fatal_sigsegv();
+	fatal_sigsegv();
 }
 
 extern unsigned long current_stub_stack(void);
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index aafad6fa166..928237a7b9c 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -51,9 +51,6 @@ config ARCH_HAS_ILOG2_U32
 config ARCH_HAS_ILOG2_U64
 	bool
 
-config ARCH_HAS_CPUFREQ
-	bool
-
 config GENERIC_HWEIGHT
 	def_bool y
 
@@ -87,7 +84,6 @@ config ARCH_PUV3
 	select GENERIC_CLOCKEVENTS
 	select HAVE_CLK
 	select ARCH_REQUIRE_GPIOLIB
-	select ARCH_HAS_CPUFREQ
 
 # CONFIGs for ARCH_PUV3
 
@@ -198,9 +194,7 @@ menu "Power management options"
 
 source "kernel/power/Kconfig"
 
-if ARCH_HAS_CPUFREQ
 source "drivers/cpufreq/Kconfig"
-endif
 
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y if !ARCH_FPGA
diff --git a/arch/unicore32/include/asm/io.h b/arch/unicore32/include/asm/io.h
index 39decb6e6f5..cb1d8fd2b16 100644
--- a/arch/unicore32/include/asm/io.h
+++ b/arch/unicore32/include/asm/io.h
@@ -39,10 +39,37 @@ extern void __uc32_iounmap(volatile void __iomem *addr);
 #define ioremap_nocache(cookie, size)	__uc32_ioremap(cookie, size)
 #define iounmap(cookie)			__uc32_iounmap(cookie)
 
+#define readb_relaxed readb
+#define readw_relaxed readw
+#define readl_relaxed readl
+
 #define HAVE_ARCH_PIO_SIZE
 #define PIO_OFFSET		(unsigned int)(PCI_IOBASE)
 #define PIO_MASK		(unsigned int)(IO_SPACE_LIMIT)
 #define PIO_RESERVED		(PIO_OFFSET + PIO_MASK + 1)
 
+#ifdef CONFIG_STRICT_DEVMEM
+
+#include <linux/ioport.h>
+#include <linux/mm.h>
+
+/*
+ * devmem_is_allowed() checks to see if /dev/mem access to a certain
+ * address is valid. The argument is a physical page number.
+ * We mimic x86 here by disallowing access to system RAM as well as
+ * device-exclusive MMIO regions. This effectively disable read()/write()
+ * on /dev/mem.
+ */
+static inline int devmem_is_allowed(unsigned long pfn)
+{
+	if (iomem_is_exclusive(pfn << PAGE_SHIFT))
+		return 0;
+	if (!page_is_ram(pfn))
+		return 1;
+	return 0;
+}
+
+#endif /* CONFIG_STRICT_DEVMEM */
+
 #endif	/* __KERNEL__ */
 #endif	/* __UNICORE_IO_H__ */
diff --git a/arch/unicore32/include/asm/pgtable.h b/arch/unicore32/include/asm/pgtable.h
index 233c25880df..ed6f7d000fb 100644
--- a/arch/unicore32/include/asm/pgtable.h
+++ b/arch/unicore32/include/asm/pgtable.h
@@ -87,16 +87,16 @@ extern pgprot_t pgprot_kernel;
 
 #define PAGE_NONE		pgprot_user
 #define PAGE_SHARED		__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_WRITE)
+								| PTE_WRITE))
 #define PAGE_SHARED_EXEC	__pgprot(pgprot_val(pgprot_user | PTE_READ \
 								| PTE_WRITE \
-								| PTE_EXEC)
+								| PTE_EXEC))
 #define PAGE_COPY		__pgprot(pgprot_val(pgprot_user | PTE_READ)
 #define PAGE_COPY_EXEC		__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_EXEC)
-#define PAGE_READONLY		__pgprot(pgprot_val(pgprot_user | PTE_READ)
+								| PTE_EXEC))
+#define PAGE_READONLY		__pgprot(pgprot_val(pgprot_user | PTE_READ))
 #define PAGE_READONLY_EXEC	__pgprot(pgprot_val(pgprot_user | PTE_READ \
-								| PTE_EXEC)
+								| PTE_EXEC))
 #define PAGE_KERNEL		pgprot_kernel
 #define PAGE_KERNEL_EXEC	__pgprot(pgprot_val(pgprot_kernel | PTE_EXEC))
 
diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h
index 4eaa4216766..8d21b7adf26 100644
--- a/arch/unicore32/include/asm/processor.h
+++ b/arch/unicore32/include/asm/processor.h
@@ -71,6 +71,7 @@ extern void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
 #define cpu_relax()			barrier()
+#define cpu_relax_lowlatency()                cpu_relax()
 
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
diff --git a/arch/unicore32/include/asm/ptrace.h b/arch/unicore32/include/asm/ptrace.h
index 9df53d991c7..02bf5a415bf 100644
--- a/arch/unicore32/include/asm/ptrace.h
+++ b/arch/unicore32/include/asm/ptrace.h
@@ -55,6 +55,7 @@ static inline int valid_user_regs(struct pt_regs *regs)
 
 #define instruction_pointer(regs)	((regs)->UCreg_pc)
 #define user_stack_pointer(regs)	((regs)->UCreg_sp)
+#define profile_pc(regs)		instruction_pointer(regs)
 
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/unicore32/kernel/clock.c b/arch/unicore32/kernel/clock.c
index 18d4563e6fa..b1ca775f6f6 100644
--- a/arch/unicore32/kernel/clock.c
+++ b/arch/unicore32/kernel/clock.c
@@ -179,7 +179,7 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 	}
 #ifdef CONFIG_CPU_FREQ
 	if (clk == &clk_mclk_clk) {
-		u32 pll_rate, divstatus = PM_DIVSTATUS;
+		u32 pll_rate, divstatus = readl(PM_DIVSTATUS);
 		int ret, i;
 
 		/* lookup mclk_clk_table */
@@ -201,10 +201,10 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 				/ (((divstatus & 0x0000f000) >> 12) + 1);
 
 		/* set pll sys cfg reg. */
-		PM_PLLSYSCFG = pll_rate;
+		writel(pll_rate, PM_PLLSYSCFG);
 
-		PM_PMCR = PM_PMCR_CFBSYS;
-		while ((PM_PLLDFCDONE & PM_PLLDFCDONE_SYSDFC)
+		writel(PM_PMCR_CFBSYS, PM_PMCR);
+		while ((readl(PM_PLLDFCDONE) & PM_PLLDFCDONE_SYSDFC)
 				!= PM_PLLDFCDONE_SYSDFC)
 			udelay(100);
 			/* about 1ms */
diff --git a/arch/unicore32/kernel/ksyms.c b/arch/unicore32/kernel/ksyms.c
index d285d71cbe3..0323528a80f 100644
--- a/arch/unicore32/kernel/ksyms.c
+++ b/arch/unicore32/kernel/ksyms.c
@@ -23,41 +23,15 @@
 
 #include "ksyms.h"
 
+EXPORT_SYMBOL(find_first_bit);
+EXPORT_SYMBOL(find_first_zero_bit);
 EXPORT_SYMBOL(find_next_zero_bit);
 EXPORT_SYMBOL(find_next_bit);
 
-EXPORT_SYMBOL(__backtrace);
-
 	/* platform dependent support */
 EXPORT_SYMBOL(__udelay);
 EXPORT_SYMBOL(__const_udelay);
 
-	/* networking */
-EXPORT_SYMBOL(csum_partial);
-EXPORT_SYMBOL(csum_partial_copy_from_user);
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
-EXPORT_SYMBOL(__csum_ipv6_magic);
-
-	/* io */
-#ifndef __raw_readsb
-EXPORT_SYMBOL(__raw_readsb);
-#endif
-#ifndef __raw_readsw
-EXPORT_SYMBOL(__raw_readsw);
-#endif
-#ifndef __raw_readsl
-EXPORT_SYMBOL(__raw_readsl);
-#endif
-#ifndef __raw_writesb
-EXPORT_SYMBOL(__raw_writesb);
-#endif
-#ifndef __raw_writesw
-EXPORT_SYMBOL(__raw_writesw);
-#endif
-#ifndef __raw_writesl
-EXPORT_SYMBOL(__raw_writesl);
-#endif
-
 	/* string / mem functions */
 EXPORT_SYMBOL(strchr);
 EXPORT_SYMBOL(strrchr);
@@ -76,23 +50,12 @@ EXPORT_SYMBOL(__copy_from_user);
 EXPORT_SYMBOL(__copy_to_user);
 EXPORT_SYMBOL(__clear_user);
 
-EXPORT_SYMBOL(__get_user_1);
-EXPORT_SYMBOL(__get_user_2);
-EXPORT_SYMBOL(__get_user_4);
-
-EXPORT_SYMBOL(__put_user_1);
-EXPORT_SYMBOL(__put_user_2);
-EXPORT_SYMBOL(__put_user_4);
-EXPORT_SYMBOL(__put_user_8);
-
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__ashrdi3);
 EXPORT_SYMBOL(__divsi3);
 EXPORT_SYMBOL(__lshrdi3);
 EXPORT_SYMBOL(__modsi3);
-EXPORT_SYMBOL(__muldi3);
 EXPORT_SYMBOL(__ucmpdi2);
 EXPORT_SYMBOL(__udivsi3);
 EXPORT_SYMBOL(__umodsi3);
-EXPORT_SYMBOL(__bswapsi2);
 
diff --git a/arch/unicore32/kernel/ksyms.h b/arch/unicore32/kernel/ksyms.h
index 185cdc712d0..31472ad9467 100644
--- a/arch/unicore32/kernel/ksyms.h
+++ b/arch/unicore32/kernel/ksyms.h
@@ -8,8 +8,6 @@ extern void __ashrdi3(void);
 extern void __divsi3(void);
 extern void __lshrdi3(void);
 extern void __modsi3(void);
-extern void __muldi3(void);
 extern void __ucmpdi2(void);
 extern void __udivsi3(void);
 extern void __umodsi3(void);
-extern void __bswapsi2(void);
diff --git a/arch/unicore32/kernel/module.c b/arch/unicore32/kernel/module.c
index 16bd1495b93..dc41f6dfedb 100644
--- a/arch/unicore32/kernel/module.c
+++ b/arch/unicore32/kernel/module.c
@@ -24,14 +24,9 @@
 
 void *module_alloc(unsigned long size)
 {
-	struct vm_struct *area;
-
-	size = PAGE_ALIGN(size);
-	area = __get_vm_area(size, VM_ALLOC, MODULES_VADDR, MODULES_END);
-	if (!area)
-		return NULL;
-
-	return __vmalloc_area(area, GFP_KERNEL, PAGE_KERNEL_EXEC);
+	return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+				GFP_KERNEL, PAGE_KERNEL_EXEC, NUMA_NO_NODE,
+				__builtin_return_address(0));
 }
 
 int
diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c
index 778ebba8082..b008e996146 100644
--- a/arch/unicore32/kernel/process.c
+++ b/arch/unicore32/kernel/process.c
@@ -60,6 +60,7 @@ void machine_halt(void)
  * Function pointers to optional machine specific functions
  */
 void (*pm_power_off)(void) = NULL;
+EXPORT_SYMBOL(pm_power_off);
 
 void machine_power_off(void)
 {
diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c
index 87adbf5ebfe..3fa317f9612 100644
--- a/arch/unicore32/kernel/setup.c
+++ b/arch/unicore32/kernel/setup.c
@@ -53,6 +53,10 @@ struct stack {
 
 static struct stack stacks[NR_CPUS];
 
+#ifdef CONFIG_VGA_CONSOLE
+struct screen_info screen_info;
+#endif
+
 char elf_platform[ELF_PLATFORM_SIZE];
 EXPORT_SYMBOL(elf_platform);
 
diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c
index de7dc5fdd58..24e836023e6 100644
--- a/arch/unicore32/mm/alignment.c
+++ b/arch/unicore32/mm/alignment.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 
+#include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/unaligned.h>
 
diff --git a/arch/unicore32/mm/proc-syms.c b/arch/unicore32/mm/proc-syms.c
index f30071e3665..21c00fc85c9 100644
--- a/arch/unicore32/mm/proc-syms.c
+++ b/arch/unicore32/mm/proc-syms.c
@@ -19,5 +19,7 @@
 EXPORT_SYMBOL(cpu_dcache_clean_area);
 EXPORT_SYMBOL(cpu_set_pte);
 
+EXPORT_SYMBOL(__cpuc_coherent_kern_range);
+
 EXPORT_SYMBOL(__cpuc_dma_flush_range);
 EXPORT_SYMBOL(__cpuc_dma_clean_range);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b660088c220..3fc7d724d0a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -54,7 +54,6 @@ config X86
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_FP_TEST
-	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_SYSCALL_TRACEPOINTS
 	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_KVM
@@ -121,6 +120,7 @@ config X86
 	select MODULES_USE_ELF_RELA if X86_64
 	select CLONE_BACKWARDS if X86_32
 	select ARCH_USE_BUILTIN_BSWAP
+	select ARCH_USE_QUEUE_RWLOCK
 	select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
 	select OLD_SIGACTION if X86_32
 	select COMPAT_OLD_SIGACTION if IA32_EMULATION
@@ -130,6 +130,7 @@ config X86
 	select HAVE_CC_STACKPROTECTOR
 	select GENERIC_CPU_AUTOPROBE
 	select HAVE_ARCH_AUDITSYSCALL
+	select ARCH_SUPPORTS_ATOMIC_RMW
 
 config INSTRUCTION_DECODER
 	def_bool y
@@ -1521,6 +1522,7 @@ config EFI
 	bool "EFI runtime service support"
 	depends on ACPI
 	select UCS2_STRING
+	select EFI_RUNTIME_WRAPPERS
 	---help---
 	  This enables the kernel to use EFI runtime services that are
 	  available (such as the EFI variable services).
@@ -1671,7 +1673,6 @@ config RELOCATABLE
 config RANDOMIZE_BASE
 	bool "Randomize the address of the kernel image"
 	depends on RELOCATABLE
-	depends on !HIBERNATION
 	default n
 	---help---
 	   Randomizes the physical and virtual address at which the
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 33f71b01fd2..c65fd965046 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -15,12 +15,9 @@ endif
 # that way we can complain to the user if the CPU is insufficient.
 #
 # The -m16 option is supported by GCC >= 4.9 and clang >= 3.5. For
-# older versions of GCC, we need to play evil and unreliable tricks to
-# attempt to ensure that our asm(".code16gcc") is first in the asm
-# output.
-CODE16GCC_CFLAGS := -m32 -include $(srctree)/arch/x86/boot/code16gcc.h \
-		    $(call cc-option, -fno-toplevel-reorder,\
-		      $(call cc-option, -fno-unit-at-a-time))
+# older versions of GCC, include an *assembly* header to make sure that
+# gcc doesn't play any games behind our back.
+CODE16GCC_CFLAGS := -m32 -Wa,$(srctree)/arch/x86/boot/code16gcc.h
 M16_CFLAGS	 := $(call cc-option, -m16, $(CODE16GCC_CFLAGS))
 
 REALMODE_CFLAGS	:= $(M16_CFLAGS) -g -Os -D__KERNEL__ \
diff --git a/arch/x86/boot/code16gcc.h b/arch/x86/boot/code16gcc.h
index d93e48010b6..5ff42653539 100644
--- a/arch/x86/boot/code16gcc.h
+++ b/arch/x86/boot/code16gcc.h
@@ -1,15 +1,11 @@
-/*
- * code16gcc.h
- *
- * This file is -include'd when compiling 16-bit C code.
- * Note: this asm() needs to be emitted before gcc emits any code.
- * Depending on gcc version, this requires -fno-unit-at-a-time or
- * -fno-toplevel-reorder.
- *
- * Hopefully gcc will eventually have a real -m16 option so we can
- * drop this hack long term.
- */
+#
+# code16gcc.h
+#
+# This file is added to the assembler via -Wa when compiling 16-bit C code.
+# This is done this way instead via asm() to make sure gcc does not reorder
+# things around us.
+#
+# gcc 4.9+ has a real -m16 option so we can drop this hack long term.
+#
 
-#ifndef __ASSEMBLY__
-asm(".code16gcc");
-#endif
+	.code16gcc
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 0fcd9133790..7a801a310e3 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -33,7 +33,8 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
 ifeq ($(CONFIG_EFI_STUB), y)
-	VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
+	VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \
+				$(objtree)/drivers/firmware/efi/libstub/lib.a
 endif
 
 $(obj)/vmlinux: $(VMLINUX_OBJS) FORCE
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 4dbf967da50..fc6091abedb 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -289,10 +289,17 @@ unsigned char *choose_kernel_location(unsigned char *input,
 	unsigned long choice = (unsigned long)output;
 	unsigned long random;
 
+#ifdef CONFIG_HIBERNATION
+	if (!cmdline_find_option_bool("kaslr")) {
+		debug_putstr("KASLR disabled by default...\n");
+		goto out;
+	}
+#else
 	if (cmdline_find_option_bool("nokaslr")) {
-		debug_putstr("KASLR disabled...\n");
+		debug_putstr("KASLR disabled by cmdline...\n");
 		goto out;
 	}
+#endif
 
 	/* Record the various known unsafe memory ranges. */
 	mem_avoid_init((unsigned long)input, input_size,
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 0331d765c2b..f277184e2ac 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -19,10 +19,7 @@
 
 static efi_system_table_t *sys_table;
 
-static struct efi_config *efi_early;
-
-#define efi_call_early(f, ...)						\
-	efi_early->call(efi_early->f, __VA_ARGS__);
+struct efi_config *efi_early;
 
 #define BOOT_SERVICES(bits)						\
 static void setup_boot_services##bits(struct efi_config *c)		\
@@ -48,8 +45,7 @@ static void setup_boot_services##bits(struct efi_config *c)		\
 BOOT_SERVICES(32);
 BOOT_SERVICES(64);
 
-static void efi_printk(efi_system_table_t *, char *);
-static void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
+void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
 static efi_status_t
 __file_size32(void *__fh, efi_char16_t *filename_16,
@@ -156,7 +152,7 @@ grow:
 
 	return status;
 }
-static efi_status_t
+efi_status_t
 efi_file_size(efi_system_table_t *sys_table, void *__fh,
 	      efi_char16_t *filename_16, void **handle, u64 *file_sz)
 {
@@ -166,7 +162,7 @@ efi_file_size(efi_system_table_t *sys_table, void *__fh,
 	return __file_size32(__fh, filename_16, handle, file_sz);
 }
 
-static inline efi_status_t
+efi_status_t
 efi_file_read(void *handle, unsigned long *size, void *addr)
 {
 	unsigned long func;
@@ -184,7 +180,7 @@ efi_file_read(void *handle, unsigned long *size, void *addr)
 	}
 }
 
-static inline efi_status_t efi_file_close(void *handle)
+efi_status_t efi_file_close(void *handle)
 {
 	if (efi_early->is64) {
 		efi_file_handle_64_t *fh = handle;
@@ -249,7 +245,7 @@ static inline efi_status_t __open_volume64(void *__image, void **__fh)
 	return status;
 }
 
-static inline efi_status_t
+efi_status_t
 efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
 {
 	if (efi_early->is64)
@@ -258,7 +254,7 @@ efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
 	return __open_volume32(__image, __fh);
 }
 
-static void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
+void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 {
 	unsigned long output_string;
 	size_t offset;
@@ -284,8 +280,6 @@ static void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 	}
 }
 
-#include "../../../../drivers/firmware/efi/efi-stub-helper.c"
-
 static void find_bits(unsigned long mask, u8 *pos, u8 *size)
 {
 	u8 first, len;
@@ -1038,6 +1032,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	int i;
 	unsigned long ramdisk_addr;
 	unsigned long ramdisk_size;
+	unsigned long initrd_addr_max;
 
 	efi_early = c;
 	sys_table = (efi_system_table_t *)(unsigned long)efi_early->table;
@@ -1100,14 +1095,21 @@ struct boot_params *make_boot_params(struct efi_config *c)
 
 	memset(sdt, 0, sizeof(*sdt));
 
+	if (hdr->xloadflags & XLF_CAN_BE_LOADED_ABOVE_4G)
+		initrd_addr_max = -1UL;
+	else
+		initrd_addr_max = hdr->initrd_addr_max;
+
 	status = handle_cmdline_files(sys_table, image,
 				      (char *)(unsigned long)hdr->cmd_line_ptr,
-				      "initrd=", hdr->initrd_addr_max,
+				      "initrd=", initrd_addr_max,
 				      &ramdisk_addr, &ramdisk_size);
 	if (status != EFI_SUCCESS)
 		goto fail2;
-	hdr->ramdisk_image = ramdisk_addr;
-	hdr->ramdisk_size = ramdisk_size;
+	hdr->ramdisk_image = ramdisk_addr & 0xffffffff;
+	hdr->ramdisk_size  = ramdisk_size & 0xffffffff;
+	boot_params->ext_ramdisk_image = (u64)ramdisk_addr >> 32;
+	boot_params->ext_ramdisk_size  = (u64)ramdisk_size >> 32;
 
 	return boot_params;
 fail2:
@@ -1374,7 +1376,10 @@ struct boot_params *efi_main(struct efi_config *c,
 
 	setup_graphics(boot_params);
 
-	setup_efi_pci(boot_params);
+	status = setup_efi_pci(boot_params);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table, "setup_efi_pci() failed!\n");
+	}
 
 	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
 				sizeof(*gdt), (void **)&gdt);
@@ -1401,16 +1406,20 @@ struct boot_params *efi_main(struct efi_config *c,
 					     hdr->init_size, hdr->init_size,
 					     hdr->pref_address,
 					     hdr->kernel_alignment);
-		if (status != EFI_SUCCESS)
+		if (status != EFI_SUCCESS) {
+			efi_printk(sys_table, "efi_relocate_kernel() failed!\n");
 			goto fail;
+		}
 
 		hdr->pref_address = hdr->code32_start;
 		hdr->code32_start = bzimage_addr;
 	}
 
 	status = exit_boot(boot_params, handle, is64);
-	if (status != EFI_SUCCESS)
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table, "exit_boot() failed!\n");
 		goto fail;
+	}
 
 	memset((char *)gdt->address, 0x0, gdt->size);
 	desc = (struct desc_struct *)gdt->address;
@@ -1470,5 +1479,6 @@ struct boot_params *efi_main(struct efi_config *c,
 
 	return boot_params;
 fail:
+	efi_printk(sys_table, "efi_main() failed!\n");
 	return NULL;
 }
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index c88c31ecad1..d487e727f1e 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -103,20 +103,4 @@ struct efi_uga_draw_protocol {
 	void *blt;
 };
 
-struct efi_config {
-	u64 image_handle;
-	u64 table;
-	u64 allocate_pool;
-	u64 allocate_pages;
-	u64 get_memory_map;
-	u64 free_pool;
-	u64 free_pages;
-	u64 locate_handle;
-	u64 handle_protocol;
-	u64 exit_boot_services;
-	u64 text_output;
-	efi_status_t (*call)(unsigned long, ...);
-	bool is64;
-} __packed;
-
 #endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 84c223479e3..16ef02596db 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -91,10 +91,9 @@ bs_die:
 
 	.section ".bsdata", "a"
 bugger_off_msg:
-	.ascii	"Direct floppy boot is not supported. "
-	.ascii	"Use a boot loader program instead.\r\n"
+	.ascii	"Use a boot loader.\r\n"
 	.ascii	"\n"
-	.ascii	"Remove disk and press any key to reboot ...\r\n"
+	.ascii	"Remove disk and press any key to reboot...\r\n"
 	.byte	0
 
 #ifdef CONFIG_EFI_STUB
@@ -108,7 +107,7 @@ coff_header:
 #else
 	.word	0x8664				# x86-64
 #endif
-	.word	3				# nr_sections
+	.word	4				# nr_sections
 	.long	0 				# TimeDateStamp
 	.long	0				# PointerToSymbolTable
 	.long	1				# NumberOfSymbols
@@ -155,7 +154,7 @@ extra_header_fields:
 #else
 	.quad	0				# ImageBase
 #endif
-	.long	0x20				# SectionAlignment
+	.long	CONFIG_PHYSICAL_ALIGN		# SectionAlignment
 	.long	0x20				# FileAlignment
 	.word	0				# MajorOperatingSystemVersion
 	.word	0				# MinorOperatingSystemVersion
@@ -250,6 +249,25 @@ section_table:
 	.word	0				# NumberOfLineNumbers
 	.long	0x60500020			# Characteristics (section flags)
 
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".bss"
+	.byte	0
+	.byte	0
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0x0
+	.long	0				# Size of initialized data
+						# on disk
+	.long	0x0
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0xc8000080			# Characteristics (section flags)
+
 #endif /* CONFIG_EFI_STUB */
 
 	# Kernel attributes; used by setup.  This is part 1 of the
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 1a2f2121cad..a7661c430cd 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -143,7 +143,7 @@ static void usage(void)
 
 #ifdef CONFIG_EFI_STUB
 
-static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
 {
 	unsigned int pe_header;
 	unsigned short num_sections;
@@ -164,10 +164,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
 			put_unaligned_le32(size, section + 0x8);
 
 			/* section header vma field */
-			put_unaligned_le32(offset, section + 0xc);
+			put_unaligned_le32(vma, section + 0xc);
 
 			/* section header 'size of initialised data' field */
-			put_unaligned_le32(size, section + 0x10);
+			put_unaligned_le32(datasz, section + 0x10);
 
 			/* section header 'file offset' field */
 			put_unaligned_le32(offset, section + 0x14);
@@ -179,6 +179,11 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz
 	}
 }
 
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+	update_pecoff_section_header_fields(section_name, offset, size, size, offset);
+}
+
 static void update_pecoff_setup_and_reloc(unsigned int size)
 {
 	u32 setup_offset = 0x200;
@@ -203,9 +208,6 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
 
 	pe_header = get_unaligned_le32(&buf[0x3c]);
 
-	/* Size of image */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
 	/*
 	 * Size of code: Subtract the size of the first sector (512 bytes)
 	 * which includes the header.
@@ -220,6 +222,22 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
 	update_pecoff_section_header(".text", text_start, text_sz);
 }
 
+static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz)
+{
+	unsigned int pe_header;
+	unsigned int bss_sz = init_sz - file_sz;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+
+	/* Size of uninitialized data */
+	put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]);
+
+	/* Size of image */
+	put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
+
+	update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0);
+}
+
 static int reserve_pecoff_reloc_section(int c)
 {
 	/* Reserve 0x20 bytes for .reloc section */
@@ -259,6 +277,8 @@ static void efi_stub_entry_update(void)
 static inline void update_pecoff_setup_and_reloc(unsigned int size) {}
 static inline void update_pecoff_text(unsigned int text_start,
 				      unsigned int file_sz) {}
+static inline void update_pecoff_bss(unsigned int file_sz,
+				     unsigned int init_sz) {}
 static inline void efi_stub_defaults(void) {}
 static inline void efi_stub_entry_update(void) {}
 
@@ -310,7 +330,7 @@ static void parse_zoffset(char *fname)
 
 int main(int argc, char ** argv)
 {
-	unsigned int i, sz, setup_sectors;
+	unsigned int i, sz, setup_sectors, init_sz;
 	int c;
 	u32 sys_size;
 	struct stat sb;
@@ -376,7 +396,9 @@ int main(int argc, char ** argv)
 	buf[0x1f1] = setup_sectors-1;
 	put_unaligned_le32(sys_size, &buf[0x1f4]);
 
-	update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+	update_pecoff_text(setup_sectors * 512, i + (sys_size * 16));
+	init_sz = get_unaligned_le32(&buf[0x260]);
+	update_pecoff_bss(i + (sys_size * 16), init_sz);
 
 	efi_stub_entry_update();
 
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 61d6e281898..d551165a315 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
 obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
 
 obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
+obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o
 obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
@@ -52,6 +53,7 @@ salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
 serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
 
 aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
+des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o
 camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
 blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
 twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
@@ -76,7 +78,7 @@ ifeq ($(avx2_supported),yes)
 endif
 
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
-aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o
+aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
 ifeq ($(avx2_supported),yes)
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
new file mode 100644
index 00000000000..f091f122ed2
--- /dev/null
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -0,0 +1,546 @@
+/*
+ *	Implement AES CTR mode by8 optimization with AVX instructions. (x86_64)
+ *
+ * This is AES128/192/256 CTR mode optimization implementation. It requires
+ * the support of Intel(R) AESNI and AVX instructions.
+ *
+ * This work was inspired by the AES CTR mode optimization published
+ * in Intel Optimized IPSEC Cryptograhpic library.
+ * Additional information on it can be found at:
+ *    http://downloadcenter.intel.com/Detail_Desc.aspx?agr=Y&DwnldID=22972
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * James Guilford <james.guilford@intel.com>
+ * Sean Gulley <sean.m.gulley@intel.com>
+ * Chandramouli Narayanan <mouli@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/inst.h>
+
+#define CONCAT(a,b)	a##b
+#define VMOVDQ		vmovdqu
+
+#define xdata0		%xmm0
+#define xdata1		%xmm1
+#define xdata2		%xmm2
+#define xdata3		%xmm3
+#define xdata4		%xmm4
+#define xdata5		%xmm5
+#define xdata6		%xmm6
+#define xdata7		%xmm7
+#define xcounter	%xmm8
+#define xbyteswap	%xmm9
+#define xkey0		%xmm10
+#define xkey3		%xmm11
+#define xkey6		%xmm12
+#define xkey9		%xmm13
+#define xkey4		%xmm11
+#define xkey8		%xmm12
+#define xkey12		%xmm13
+#define xkeyA		%xmm14
+#define xkeyB		%xmm15
+
+#define p_in		%rdi
+#define p_iv		%rsi
+#define p_keys		%rdx
+#define p_out		%rcx
+#define num_bytes	%r8
+
+#define tmp		%r10
+#define	DDQ(i)		CONCAT(ddq_add_,i)
+#define	XMM(i)		CONCAT(%xmm, i)
+#define	DDQ_DATA	0
+#define	XDATA		1
+#define KEY_128		1
+#define KEY_192		2
+#define KEY_256		3
+
+.section .rodata
+.align 16
+
+byteswap_const:
+	.octa 0x000102030405060708090A0B0C0D0E0F
+ddq_add_1:
+	.octa 0x00000000000000000000000000000001
+ddq_add_2:
+	.octa 0x00000000000000000000000000000002
+ddq_add_3:
+	.octa 0x00000000000000000000000000000003
+ddq_add_4:
+	.octa 0x00000000000000000000000000000004
+ddq_add_5:
+	.octa 0x00000000000000000000000000000005
+ddq_add_6:
+	.octa 0x00000000000000000000000000000006
+ddq_add_7:
+	.octa 0x00000000000000000000000000000007
+ddq_add_8:
+	.octa 0x00000000000000000000000000000008
+
+.text
+
+/* generate a unique variable for ddq_add_x */
+
+.macro setddq n
+	var_ddq_add = DDQ(\n)
+.endm
+
+/* generate a unique variable for xmm register */
+.macro setxdata n
+	var_xdata = XMM(\n)
+.endm
+
+/* club the numeric 'id' to the symbol 'name' */
+
+.macro club name, id
+.altmacro
+	.if \name == DDQ_DATA
+		setddq %\id
+	.elseif \name == XDATA
+		setxdata %\id
+	.endif
+.noaltmacro
+.endm
+
+/*
+ * do_aes num_in_par load_keys key_len
+ * This increments p_in, but not p_out
+ */
+.macro do_aes b, k, key_len
+	.set by, \b
+	.set load_keys, \k
+	.set klen, \key_len
+
+	.if (load_keys)
+		vmovdqa	0*16(p_keys), xkey0
+	.endif
+
+	vpshufb	xbyteswap, xcounter, xdata0
+
+	.set i, 1
+	.rept (by - 1)
+		club DDQ_DATA, i
+		club XDATA, i
+		vpaddd	var_ddq_add(%rip), xcounter, var_xdata
+		vpshufb	xbyteswap, var_xdata, var_xdata
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	1*16(p_keys), xkeyA
+
+	vpxor	xkey0, xdata0, xdata0
+	club DDQ_DATA, by
+	vpaddd	var_ddq_add(%rip), xcounter, xcounter
+
+	.set i, 1
+	.rept (by - 1)
+		club XDATA, i
+		vpxor	xkey0, var_xdata, var_xdata
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	2*16(p_keys), xkeyB
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyA, var_xdata, var_xdata		/* key 1 */
+		.set i, (i +1)
+	.endr
+
+	.if (klen == KEY_128)
+		.if (load_keys)
+			vmovdqa	3*16(p_keys), xkeyA
+		.endif
+	.else
+		vmovdqa	3*16(p_keys), xkeyA
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyB, var_xdata, var_xdata		/* key 2 */
+		.set i, (i +1)
+	.endr
+
+	add	$(16*by), p_in
+
+	.if (klen == KEY_128)
+		vmovdqa	4*16(p_keys), xkey4
+	.else
+		.if (load_keys)
+			vmovdqa	4*16(p_keys), xkey4
+		.endif
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyA, var_xdata, var_xdata		/* key 3 */
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	5*16(p_keys), xkeyA
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkey4, var_xdata, var_xdata		/* key 4 */
+		.set i, (i +1)
+	.endr
+
+	.if (klen == KEY_128)
+		.if (load_keys)
+			vmovdqa	6*16(p_keys), xkeyB
+		.endif
+	.else
+		vmovdqa	6*16(p_keys), xkeyB
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyA, var_xdata, var_xdata		/* key 5 */
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	7*16(p_keys), xkeyA
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyB, var_xdata, var_xdata		/* key 6 */
+		.set i, (i +1)
+	.endr
+
+	.if (klen == KEY_128)
+		vmovdqa	8*16(p_keys), xkey8
+	.else
+		.if (load_keys)
+			vmovdqa	8*16(p_keys), xkey8
+		.endif
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyA, var_xdata, var_xdata		/* key 7 */
+		.set i, (i +1)
+	.endr
+
+	.if (klen == KEY_128)
+		.if (load_keys)
+			vmovdqa	9*16(p_keys), xkeyA
+		.endif
+	.else
+		vmovdqa	9*16(p_keys), xkeyA
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkey8, var_xdata, var_xdata		/* key 8 */
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	10*16(p_keys), xkeyB
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyA, var_xdata, var_xdata		/* key 9 */
+		.set i, (i +1)
+	.endr
+
+	.if (klen != KEY_128)
+		vmovdqa	11*16(p_keys), xkeyA
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		/* key 10 */
+		.if (klen == KEY_128)
+			vaesenclast	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.endif
+		.set i, (i +1)
+	.endr
+
+	.if (klen != KEY_128)
+		.if (load_keys)
+			vmovdqa	12*16(p_keys), xkey12
+		.endif
+
+		.set i, 0
+		.rept by
+			club XDATA, i
+			vaesenc	xkeyA, var_xdata, var_xdata	/* key 11 */
+			.set i, (i +1)
+		.endr
+
+		.if (klen == KEY_256)
+			vmovdqa	13*16(p_keys), xkeyA
+		.endif
+
+		.set i, 0
+		.rept by
+			club XDATA, i
+			.if (klen == KEY_256)
+				/* key 12 */
+				vaesenc	xkey12, var_xdata, var_xdata
+			.else
+				vaesenclast xkey12, var_xdata, var_xdata
+			.endif
+			.set i, (i +1)
+		.endr
+
+		.if (klen == KEY_256)
+			vmovdqa	14*16(p_keys), xkeyB
+
+			.set i, 0
+			.rept by
+				club XDATA, i
+				/* key 13 */
+				vaesenc	xkeyA, var_xdata, var_xdata
+				.set i, (i +1)
+			.endr
+
+			.set i, 0
+			.rept by
+				club XDATA, i
+				/* key 14 */
+				vaesenclast	xkeyB, var_xdata, var_xdata
+				.set i, (i +1)
+			.endr
+		.endif
+	.endif
+
+	.set i, 0
+	.rept (by / 2)
+		.set j, (i+1)
+		VMOVDQ	(i*16 - 16*by)(p_in), xkeyA
+		VMOVDQ	(j*16 - 16*by)(p_in), xkeyB
+		club XDATA, i
+		vpxor	xkeyA, var_xdata, var_xdata
+		club XDATA, j
+		vpxor	xkeyB, var_xdata, var_xdata
+		.set i, (i+2)
+	.endr
+
+	.if (i < by)
+		VMOVDQ	(i*16 - 16*by)(p_in), xkeyA
+		club XDATA, i
+		vpxor	xkeyA, var_xdata, var_xdata
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		VMOVDQ	var_xdata, i*16(p_out)
+		.set i, (i+1)
+	.endr
+.endm
+
+.macro do_aes_load val, key_len
+	do_aes \val, 1, \key_len
+.endm
+
+.macro do_aes_noload val, key_len
+	do_aes \val, 0, \key_len
+.endm
+
+/* main body of aes ctr load */
+
+.macro do_aes_ctrmain key_len
+
+	cmp	$16, num_bytes
+	jb	.Ldo_return2\key_len
+
+	vmovdqa	byteswap_const(%rip), xbyteswap
+	vmovdqu	(p_iv), xcounter
+	vpshufb	xbyteswap, xcounter, xcounter
+
+	mov	num_bytes, tmp
+	and	$(7*16), tmp
+	jz	.Lmult_of_8_blks\key_len
+
+	/* 1 <= tmp <= 7 */
+	cmp	$(4*16), tmp
+	jg	.Lgt4\key_len
+	je	.Leq4\key_len
+
+.Llt4\key_len:
+	cmp	$(2*16), tmp
+	jg	.Leq3\key_len
+	je	.Leq2\key_len
+
+.Leq1\key_len:
+	do_aes_load	1, \key_len
+	add	$(1*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Leq2\key_len:
+	do_aes_load	2, \key_len
+	add	$(2*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+
+.Leq3\key_len:
+	do_aes_load	3, \key_len
+	add	$(3*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Leq4\key_len:
+	do_aes_load	4, \key_len
+	add	$(4*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Lgt4\key_len:
+	cmp	$(6*16), tmp
+	jg	.Leq7\key_len
+	je	.Leq6\key_len
+
+.Leq5\key_len:
+	do_aes_load	5, \key_len
+	add	$(5*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Leq6\key_len:
+	do_aes_load	6, \key_len
+	add	$(6*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Leq7\key_len:
+	do_aes_load	7, \key_len
+	add	$(7*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Lmult_of_8_blks\key_len:
+	.if (\key_len != KEY_128)
+		vmovdqa	0*16(p_keys), xkey0
+		vmovdqa	4*16(p_keys), xkey4
+		vmovdqa	8*16(p_keys), xkey8
+		vmovdqa	12*16(p_keys), xkey12
+	.else
+		vmovdqa	0*16(p_keys), xkey0
+		vmovdqa	3*16(p_keys), xkey4
+		vmovdqa	6*16(p_keys), xkey8
+		vmovdqa	9*16(p_keys), xkey12
+	.endif
+.align 16
+.Lmain_loop2\key_len:
+	/* num_bytes is a multiple of 8 and >0 */
+	do_aes_noload	8, \key_len
+	add	$(8*16), p_out
+	sub	$(8*16), num_bytes
+	jne	.Lmain_loop2\key_len
+
+.Ldo_return2\key_len:
+	/* return updated IV */
+	vpshufb	xbyteswap, xcounter, xcounter
+	vmovdqu	xcounter, (p_iv)
+	ret
+.endm
+
+/*
+ * routine to do AES128 CTR enc/decrypt "by8"
+ * XMM registers are clobbered.
+ * Saving/restoring must be done at a higher level
+ * aes_ctr_enc_128_avx_by8(void *in, void *iv, void *keys, void *out,
+ *			unsigned int num_bytes)
+ */
+ENTRY(aes_ctr_enc_128_avx_by8)
+	/* call the aes main loop */
+	do_aes_ctrmain KEY_128
+
+ENDPROC(aes_ctr_enc_128_avx_by8)
+
+/*
+ * routine to do AES192 CTR enc/decrypt "by8"
+ * XMM registers are clobbered.
+ * Saving/restoring must be done at a higher level
+ * aes_ctr_enc_192_avx_by8(void *in, void *iv, void *keys, void *out,
+ *			unsigned int num_bytes)
+ */
+ENTRY(aes_ctr_enc_192_avx_by8)
+	/* call the aes main loop */
+	do_aes_ctrmain KEY_192
+
+ENDPROC(aes_ctr_enc_192_avx_by8)
+
+/*
+ * routine to do AES256 CTR enc/decrypt "by8"
+ * XMM registers are clobbered.
+ * Saving/restoring must be done at a higher level
+ * aes_ctr_enc_256_avx_by8(void *in, void *iv, void *keys, void *out,
+ *			unsigned int num_bytes)
+ */
+ENTRY(aes_ctr_enc_256_avx_by8)
+	/* call the aes main loop */
+	do_aes_ctrmain KEY_256
+
+ENDPROC(aes_ctr_enc_256_avx_by8)
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 948ad0e7774..888950f29fd 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -105,6 +105,9 @@ void crypto_fpu_exit(void);
 #define AVX_GEN4_OPTSIZE 4096
 
 #ifdef CONFIG_X86_64
+
+static void (*aesni_ctr_enc_tfm)(struct crypto_aes_ctx *ctx, u8 *out,
+			      const u8 *in, unsigned int len, u8 *iv);
 asmlinkage void aesni_ctr_enc(struct crypto_aes_ctx *ctx, u8 *out,
 			      const u8 *in, unsigned int len, u8 *iv);
 
@@ -155,6 +158,12 @@ asmlinkage void aesni_gcm_dec(void *ctx, u8 *out,
 
 
 #ifdef CONFIG_AS_AVX
+asmlinkage void aes_ctr_enc_128_avx_by8(const u8 *in, u8 *iv,
+		void *keys, u8 *out, unsigned int num_bytes);
+asmlinkage void aes_ctr_enc_192_avx_by8(const u8 *in, u8 *iv,
+		void *keys, u8 *out, unsigned int num_bytes);
+asmlinkage void aes_ctr_enc_256_avx_by8(const u8 *in, u8 *iv,
+		void *keys, u8 *out, unsigned int num_bytes);
 /*
  * asmlinkage void aesni_gcm_precomp_avx_gen2()
  * gcm_data *my_ctx_data, context data
@@ -472,6 +481,25 @@ static void ctr_crypt_final(struct crypto_aes_ctx *ctx,
 	crypto_inc(ctrblk, AES_BLOCK_SIZE);
 }
 
+#ifdef CONFIG_AS_AVX
+static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out,
+			      const u8 *in, unsigned int len, u8 *iv)
+{
+	/*
+	 * based on key length, override with the by8 version
+	 * of ctr mode encryption/decryption for improved performance
+	 * aes_set_key_common() ensures that key length is one of
+	 * {128,192,256}
+	 */
+	if (ctx->key_length == AES_KEYSIZE_128)
+		aes_ctr_enc_128_avx_by8(in, iv, (void *)ctx, out, len);
+	else if (ctx->key_length == AES_KEYSIZE_192)
+		aes_ctr_enc_192_avx_by8(in, iv, (void *)ctx, out, len);
+	else
+		aes_ctr_enc_256_avx_by8(in, iv, (void *)ctx, out, len);
+}
+#endif
+
 static int ctr_crypt(struct blkcipher_desc *desc,
 		     struct scatterlist *dst, struct scatterlist *src,
 		     unsigned int nbytes)
@@ -486,8 +514,8 @@ static int ctr_crypt(struct blkcipher_desc *desc,
 
 	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
-		aesni_ctr_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
-			      nbytes & AES_BLOCK_MASK, walk.iv);
+		aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr,
+				  nbytes & AES_BLOCK_MASK, walk.iv);
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
@@ -1493,6 +1521,14 @@ static int __init aesni_init(void)
 		aesni_gcm_enc_tfm = aesni_gcm_enc;
 		aesni_gcm_dec_tfm = aesni_gcm_dec;
 	}
+	aesni_ctr_enc_tfm = aesni_ctr_enc;
+#ifdef CONFIG_AS_AVX
+	if (cpu_has_avx) {
+		/* optimize performance of ctr mode encryption transform */
+		aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm;
+		pr_info("AES CTR mode by8 optimization enabled\n");
+	}
+#endif
 #endif
 
 	err = crypto_fpu_init();
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index dbc4339b541..26d49ebae04 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -72,6 +72,7 @@
 
 # unsigned int crc_pcl(u8 *buffer, int len, unsigned int crc_init);
 
+.text
 ENTRY(crc_pcl)
 #define    bufp		%rdi
 #define    bufp_dw	%edi
@@ -216,15 +217,11 @@ LABEL crc_ %i
 	## 4) Combine three results:
 	################################################################
 
-	lea	(K_table-16)(%rip), bufp	# first entry is for idx 1
+	lea	(K_table-8)(%rip), bufp		# first entry is for idx 1
 	shlq    $3, %rax			# rax *= 8
-	subq    %rax, tmp			# tmp -= rax*8
-	shlq    $1, %rax
-	subq    %rax, tmp			# tmp -= rax*16
-						# (total tmp -= rax*24)
-	addq    %rax, bufp
-
-	movdqa  (bufp), %xmm0			# 2 consts: K1:K2
+	pmovzxdq (bufp,%rax), %xmm0		# 2 consts: K1:K2
+	leal	(%eax,%eax,2), %eax		# rax *= 3 (total *24)
+	subq    %rax, tmp			# tmp -= rax*24
 
 	movq    crc_init, %xmm1			# CRC for block 1
 	PCLMULQDQ 0x00,%xmm0,%xmm1		# Multiply by K2
@@ -238,9 +235,9 @@ LABEL crc_ %i
 	mov     crc2, crc_init
 	crc32   %rax, crc_init
 
-################################################################
-## 5) Check for end:
-################################################################
+	################################################################
+	## 5) Check for end:
+	################################################################
 
 LABEL crc_ 0
 	mov     tmp, len
@@ -331,136 +328,136 @@ ENDPROC(crc_pcl)
 
 	################################################################
 	## PCLMULQDQ tables
-	## Table is 128 entries x 2 quad words each
+	## Table is 128 entries x 2 words (8 bytes) each
 	################################################################
-.data
-.align 64
+.section	.rotata, "a", %progbits
+.align 8
 K_table:
-        .quad 0x14cd00bd6,0x105ec76f0
-        .quad 0x0ba4fc28e,0x14cd00bd6
-        .quad 0x1d82c63da,0x0f20c0dfe
-        .quad 0x09e4addf8,0x0ba4fc28e
-        .quad 0x039d3b296,0x1384aa63a
-        .quad 0x102f9b8a2,0x1d82c63da
-        .quad 0x14237f5e6,0x01c291d04
-        .quad 0x00d3b6092,0x09e4addf8
-        .quad 0x0c96cfdc0,0x0740eef02
-        .quad 0x18266e456,0x039d3b296
-        .quad 0x0daece73e,0x0083a6eec
-        .quad 0x0ab7aff2a,0x102f9b8a2
-        .quad 0x1248ea574,0x1c1733996
-        .quad 0x083348832,0x14237f5e6
-        .quad 0x12c743124,0x02ad91c30
-        .quad 0x0b9e02b86,0x00d3b6092
-        .quad 0x018b33a4e,0x06992cea2
-        .quad 0x1b331e26a,0x0c96cfdc0
-        .quad 0x17d35ba46,0x07e908048
-        .quad 0x1bf2e8b8a,0x18266e456
-        .quad 0x1a3e0968a,0x11ed1f9d8
-        .quad 0x0ce7f39f4,0x0daece73e
-        .quad 0x061d82e56,0x0f1d0f55e
-        .quad 0x0d270f1a2,0x0ab7aff2a
-        .quad 0x1c3f5f66c,0x0a87ab8a8
-        .quad 0x12ed0daac,0x1248ea574
-        .quad 0x065863b64,0x08462d800
-        .quad 0x11eef4f8e,0x083348832
-        .quad 0x1ee54f54c,0x071d111a8
-        .quad 0x0b3e32c28,0x12c743124
-        .quad 0x0064f7f26,0x0ffd852c6
-        .quad 0x0dd7e3b0c,0x0b9e02b86
-        .quad 0x0f285651c,0x0dcb17aa4
-        .quad 0x010746f3c,0x018b33a4e
-        .quad 0x1c24afea4,0x0f37c5aee
-        .quad 0x0271d9844,0x1b331e26a
-        .quad 0x08e766a0c,0x06051d5a2
-        .quad 0x093a5f730,0x17d35ba46
-        .quad 0x06cb08e5c,0x11d5ca20e
-        .quad 0x06b749fb2,0x1bf2e8b8a
-        .quad 0x1167f94f2,0x021f3d99c
-        .quad 0x0cec3662e,0x1a3e0968a
-        .quad 0x19329634a,0x08f158014
-        .quad 0x0e6fc4e6a,0x0ce7f39f4
-        .quad 0x08227bb8a,0x1a5e82106
-        .quad 0x0b0cd4768,0x061d82e56
-        .quad 0x13c2b89c4,0x188815ab2
-        .quad 0x0d7a4825c,0x0d270f1a2
-        .quad 0x10f5ff2ba,0x105405f3e
-        .quad 0x00167d312,0x1c3f5f66c
-        .quad 0x0f6076544,0x0e9adf796
-        .quad 0x026f6a60a,0x12ed0daac
-        .quad 0x1a2adb74e,0x096638b34
-        .quad 0x19d34af3a,0x065863b64
-        .quad 0x049c3cc9c,0x1e50585a0
-        .quad 0x068bce87a,0x11eef4f8e
-        .quad 0x1524fa6c6,0x19f1c69dc
-        .quad 0x16cba8aca,0x1ee54f54c
-        .quad 0x042d98888,0x12913343e
-        .quad 0x1329d9f7e,0x0b3e32c28
-        .quad 0x1b1c69528,0x088f25a3a
-        .quad 0x02178513a,0x0064f7f26
-        .quad 0x0e0ac139e,0x04e36f0b0
-        .quad 0x0170076fa,0x0dd7e3b0c
-        .quad 0x141a1a2e2,0x0bd6f81f8
-        .quad 0x16ad828b4,0x0f285651c
-        .quad 0x041d17b64,0x19425cbba
-        .quad 0x1fae1cc66,0x010746f3c
-        .quad 0x1a75b4b00,0x18db37e8a
-        .quad 0x0f872e54c,0x1c24afea4
-        .quad 0x01e41e9fc,0x04c144932
-        .quad 0x086d8e4d2,0x0271d9844
-        .quad 0x160f7af7a,0x052148f02
-        .quad 0x05bb8f1bc,0x08e766a0c
-        .quad 0x0a90fd27a,0x0a3c6f37a
-        .quad 0x0b3af077a,0x093a5f730
-        .quad 0x04984d782,0x1d22c238e
-        .quad 0x0ca6ef3ac,0x06cb08e5c
-        .quad 0x0234e0b26,0x063ded06a
-        .quad 0x1d88abd4a,0x06b749fb2
-        .quad 0x04597456a,0x04d56973c
-        .quad 0x0e9e28eb4,0x1167f94f2
-        .quad 0x07b3ff57a,0x19385bf2e
-        .quad 0x0c9c8b782,0x0cec3662e
-        .quad 0x13a9cba9e,0x0e417f38a
-        .quad 0x093e106a4,0x19329634a
-        .quad 0x167001a9c,0x14e727980
-        .quad 0x1ddffc5d4,0x0e6fc4e6a
-        .quad 0x00df04680,0x0d104b8fc
-        .quad 0x02342001e,0x08227bb8a
-        .quad 0x00a2a8d7e,0x05b397730
-        .quad 0x168763fa6,0x0b0cd4768
-        .quad 0x1ed5a407a,0x0e78eb416
-        .quad 0x0d2c3ed1a,0x13c2b89c4
-        .quad 0x0995a5724,0x1641378f0
-        .quad 0x19b1afbc4,0x0d7a4825c
-        .quad 0x109ffedc0,0x08d96551c
-        .quad 0x0f2271e60,0x10f5ff2ba
-        .quad 0x00b0bf8ca,0x00bf80dd2
-        .quad 0x123888b7a,0x00167d312
-        .quad 0x1e888f7dc,0x18dcddd1c
-        .quad 0x002ee03b2,0x0f6076544
-        .quad 0x183e8d8fe,0x06a45d2b2
-        .quad 0x133d7a042,0x026f6a60a
-        .quad 0x116b0f50c,0x1dd3e10e8
-        .quad 0x05fabe670,0x1a2adb74e
-        .quad 0x130004488,0x0de87806c
-        .quad 0x000bcf5f6,0x19d34af3a
-        .quad 0x18f0c7078,0x014338754
-        .quad 0x017f27698,0x049c3cc9c
-        .quad 0x058ca5f00,0x15e3e77ee
-        .quad 0x1af900c24,0x068bce87a
-        .quad 0x0b5cfca28,0x0dd07448e
-        .quad 0x0ded288f8,0x1524fa6c6
-        .quad 0x059f229bc,0x1d8048348
-        .quad 0x06d390dec,0x16cba8aca
-        .quad 0x037170390,0x0a3e3e02c
-        .quad 0x06353c1cc,0x042d98888
-        .quad 0x0c4584f5c,0x0d73c7bea
-        .quad 0x1f16a3418,0x1329d9f7e
-        .quad 0x0531377e2,0x185137662
-        .quad 0x1d8d9ca7c,0x1b1c69528
-        .quad 0x0b25b29f2,0x18a08b5bc
-        .quad 0x19fb2a8b0,0x02178513a
-        .quad 0x1a08fe6ac,0x1da758ae0
-        .quad 0x045cddf4e,0x0e0ac139e
-        .quad 0x1a91647f2,0x169cf9eb0
-        .quad 0x1a0f717c4,0x0170076fa
+	.long 0x493c7d27, 0x00000001
+	.long 0xba4fc28e, 0x493c7d27
+	.long 0xddc0152b, 0xf20c0dfe
+	.long 0x9e4addf8, 0xba4fc28e
+	.long 0x39d3b296, 0x3da6d0cb
+	.long 0x0715ce53, 0xddc0152b
+	.long 0x47db8317, 0x1c291d04
+	.long 0x0d3b6092, 0x9e4addf8
+	.long 0xc96cfdc0, 0x740eef02
+	.long 0x878a92a7, 0x39d3b296
+	.long 0xdaece73e, 0x083a6eec
+	.long 0xab7aff2a, 0x0715ce53
+	.long 0x2162d385, 0xc49f4f67
+	.long 0x83348832, 0x47db8317
+	.long 0x299847d5, 0x2ad91c30
+	.long 0xb9e02b86, 0x0d3b6092
+	.long 0x18b33a4e, 0x6992cea2
+	.long 0xb6dd949b, 0xc96cfdc0
+	.long 0x78d9ccb7, 0x7e908048
+	.long 0xbac2fd7b, 0x878a92a7
+	.long 0xa60ce07b, 0x1b3d8f29
+	.long 0xce7f39f4, 0xdaece73e
+	.long 0x61d82e56, 0xf1d0f55e
+	.long 0xd270f1a2, 0xab7aff2a
+	.long 0xc619809d, 0xa87ab8a8
+	.long 0x2b3cac5d, 0x2162d385
+	.long 0x65863b64, 0x8462d800
+	.long 0x1b03397f, 0x83348832
+	.long 0xebb883bd, 0x71d111a8
+	.long 0xb3e32c28, 0x299847d5
+	.long 0x064f7f26, 0xffd852c6
+	.long 0xdd7e3b0c, 0xb9e02b86
+	.long 0xf285651c, 0xdcb17aa4
+	.long 0x10746f3c, 0x18b33a4e
+	.long 0xc7a68855, 0xf37c5aee
+	.long 0x271d9844, 0xb6dd949b
+	.long 0x8e766a0c, 0x6051d5a2
+	.long 0x93a5f730, 0x78d9ccb7
+	.long 0x6cb08e5c, 0x18b0d4ff
+	.long 0x6b749fb2, 0xbac2fd7b
+	.long 0x1393e203, 0x21f3d99c
+	.long 0xcec3662e, 0xa60ce07b
+	.long 0x96c515bb, 0x8f158014
+	.long 0xe6fc4e6a, 0xce7f39f4
+	.long 0x8227bb8a, 0xa00457f7
+	.long 0xb0cd4768, 0x61d82e56
+	.long 0x39c7ff35, 0x8d6d2c43
+	.long 0xd7a4825c, 0xd270f1a2
+	.long 0x0ab3844b, 0x00ac29cf
+	.long 0x0167d312, 0xc619809d
+	.long 0xf6076544, 0xe9adf796
+	.long 0x26f6a60a, 0x2b3cac5d
+	.long 0xa741c1bf, 0x96638b34
+	.long 0x98d8d9cb, 0x65863b64
+	.long 0x49c3cc9c, 0xe0e9f351
+	.long 0x68bce87a, 0x1b03397f
+	.long 0x57a3d037, 0x9af01f2d
+	.long 0x6956fc3b, 0xebb883bd
+	.long 0x42d98888, 0x2cff42cf
+	.long 0x3771e98f, 0xb3e32c28
+	.long 0xb42ae3d9, 0x88f25a3a
+	.long 0x2178513a, 0x064f7f26
+	.long 0xe0ac139e, 0x4e36f0b0
+	.long 0x170076fa, 0xdd7e3b0c
+	.long 0x444dd413, 0xbd6f81f8
+	.long 0x6f345e45, 0xf285651c
+	.long 0x41d17b64, 0x91c9bd4b
+	.long 0xff0dba97, 0x10746f3c
+	.long 0xa2b73df1, 0x885f087b
+	.long 0xf872e54c, 0xc7a68855
+	.long 0x1e41e9fc, 0x4c144932
+	.long 0x86d8e4d2, 0x271d9844
+	.long 0x651bd98b, 0x52148f02
+	.long 0x5bb8f1bc, 0x8e766a0c
+	.long 0xa90fd27a, 0xa3c6f37a
+	.long 0xb3af077a, 0x93a5f730
+	.long 0x4984d782, 0xd7c0557f
+	.long 0xca6ef3ac, 0x6cb08e5c
+	.long 0x234e0b26, 0x63ded06a
+	.long 0xdd66cbbb, 0x6b749fb2
+	.long 0x4597456a, 0x4d56973c
+	.long 0xe9e28eb4, 0x1393e203
+	.long 0x7b3ff57a, 0x9669c9df
+	.long 0xc9c8b782, 0xcec3662e
+	.long 0x3f70cc6f, 0xe417f38a
+	.long 0x93e106a4, 0x96c515bb
+	.long 0x62ec6c6d, 0x4b9e0f71
+	.long 0xd813b325, 0xe6fc4e6a
+	.long 0x0df04680, 0xd104b8fc
+	.long 0x2342001e, 0x8227bb8a
+	.long 0x0a2a8d7e, 0x5b397730
+	.long 0x6d9a4957, 0xb0cd4768
+	.long 0xe8b6368b, 0xe78eb416
+	.long 0xd2c3ed1a, 0x39c7ff35
+	.long 0x995a5724, 0x61ff0e01
+	.long 0x9ef68d35, 0xd7a4825c
+	.long 0x0c139b31, 0x8d96551c
+	.long 0xf2271e60, 0x0ab3844b
+	.long 0x0b0bf8ca, 0x0bf80dd2
+	.long 0x2664fd8b, 0x0167d312
+	.long 0xed64812d, 0x8821abed
+	.long 0x02ee03b2, 0xf6076544
+	.long 0x8604ae0f, 0x6a45d2b2
+	.long 0x363bd6b3, 0x26f6a60a
+	.long 0x135c83fd, 0xd8d26619
+	.long 0x5fabe670, 0xa741c1bf
+	.long 0x35ec3279, 0xde87806c
+	.long 0x00bcf5f6, 0x98d8d9cb
+	.long 0x8ae00689, 0x14338754
+	.long 0x17f27698, 0x49c3cc9c
+	.long 0x58ca5f00, 0x5bd2011f
+	.long 0xaa7c7ad5, 0x68bce87a
+	.long 0xb5cfca28, 0xdd07448e
+	.long 0xded288f8, 0x57a3d037
+	.long 0x59f229bc, 0xdde8f5b9
+	.long 0x6d390dec, 0x6956fc3b
+	.long 0x37170390, 0xa3e3e02c
+	.long 0x6353c1cc, 0x42d98888
+	.long 0xc4584f5c, 0xd73c7bea
+	.long 0xf48642e9, 0x3771e98f
+	.long 0x531377e2, 0x80ff0093
+	.long 0xdd35bc8d, 0xb42ae3d9
+	.long 0xb25b29f2, 0x8fe4c34d
+	.long 0x9a5ede41, 0x2178513a
+	.long 0xa563905d, 0xdf99fc11
+	.long 0x45cddf4e, 0xe0ac139e
+	.long 0xacfa3103, 0x6c23e841
+	.long 0xa51b6135, 0x170076fa
diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S
new file mode 100644
index 00000000000..038f6ae87c5
--- /dev/null
+++ b/arch/x86/crypto/des3_ede-asm_64.S
@@ -0,0 +1,805 @@
+/*
+ * des3_ede-asm_64.S  -  x86-64 assembly implementation of 3DES cipher
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+
+.file "des3_ede-asm_64.S"
+.text
+
+#define s1 .L_s1
+#define s2 ((s1) + (64*8))
+#define s3 ((s2) + (64*8))
+#define s4 ((s3) + (64*8))
+#define s5 ((s4) + (64*8))
+#define s6 ((s5) + (64*8))
+#define s7 ((s6) + (64*8))
+#define s8 ((s7) + (64*8))
+
+/* register macros */
+#define CTX %rdi
+
+#define RL0 %r8
+#define RL1 %r9
+#define RL2 %r10
+
+#define RL0d %r8d
+#define RL1d %r9d
+#define RL2d %r10d
+
+#define RR0 %r11
+#define RR1 %r12
+#define RR2 %r13
+
+#define RR0d %r11d
+#define RR1d %r12d
+#define RR2d %r13d
+
+#define RW0 %rax
+#define RW1 %rbx
+#define RW2 %rcx
+
+#define RW0d %eax
+#define RW1d %ebx
+#define RW2d %ecx
+
+#define RW0bl %al
+#define RW1bl %bl
+#define RW2bl %cl
+
+#define RW0bh %ah
+#define RW1bh %bh
+#define RW2bh %ch
+
+#define RT0 %r15
+#define RT1 %rbp
+#define RT2 %r14
+#define RT3 %rdx
+
+#define RT0d %r15d
+#define RT1d %ebp
+#define RT2d %r14d
+#define RT3d %edx
+
+/***********************************************************************
+ * 1-way 3DES
+ ***********************************************************************/
+#define do_permutation(a, b, offset, mask) \
+	movl a, RT0d; \
+	shrl $(offset), RT0d; \
+	xorl b, RT0d; \
+	andl $(mask), RT0d; \
+	xorl RT0d, b; \
+	shll $(offset), RT0d; \
+	xorl RT0d, a;
+
+#define expand_to_64bits(val, mask) \
+	movl val##d, RT0d; \
+	rorl $4, RT0d; \
+	shlq $32, RT0; \
+	orq RT0, val; \
+	andq mask, val;
+
+#define compress_to_64bits(val) \
+	movq val, RT0; \
+	shrq $32, RT0; \
+	roll $4, RT0d; \
+	orl RT0d, val##d;
+
+#define initial_permutation(left, right) \
+	do_permutation(left##d, right##d,  4, 0x0f0f0f0f); \
+	do_permutation(left##d, right##d, 16, 0x0000ffff); \
+	do_permutation(right##d, left##d,  2, 0x33333333); \
+	do_permutation(right##d, left##d,  8, 0x00ff00ff); \
+	movabs $0x3f3f3f3f3f3f3f3f, RT3; \
+	movl left##d, RW0d; \
+	roll $1, right##d; \
+	xorl right##d, RW0d; \
+	andl $0xaaaaaaaa, RW0d; \
+	xorl RW0d, left##d; \
+	xorl RW0d, right##d; \
+	roll $1, left##d; \
+	expand_to_64bits(right, RT3); \
+	expand_to_64bits(left, RT3);
+
+#define final_permutation(left, right) \
+	compress_to_64bits(right); \
+	compress_to_64bits(left); \
+	movl right##d, RW0d; \
+	rorl $1, left##d; \
+	xorl left##d, RW0d; \
+	andl $0xaaaaaaaa, RW0d; \
+	xorl RW0d, right##d; \
+	xorl RW0d, left##d; \
+	rorl $1, right##d; \
+	do_permutation(right##d, left##d,  8, 0x00ff00ff); \
+	do_permutation(right##d, left##d,  2, 0x33333333); \
+	do_permutation(left##d, right##d, 16, 0x0000ffff); \
+	do_permutation(left##d, right##d,  4, 0x0f0f0f0f);
+
+#define round1(n, from, to, load_next_key) \
+	xorq from, RW0; \
+	\
+	movzbl RW0bl, RT0d; \
+	movzbl RW0bh, RT1d; \
+	shrq $16, RW0; \
+	movzbl RW0bl, RT2d; \
+	movzbl RW0bh, RT3d; \
+	shrq $16, RW0; \
+	movq s8(, RT0, 8), RT0; \
+	xorq s6(, RT1, 8), to; \
+	movzbl RW0bl, RL1d; \
+	movzbl RW0bh, RT1d; \
+	shrl $16, RW0d; \
+	xorq s4(, RT2, 8), RT0; \
+	xorq s2(, RT3, 8), to; \
+	movzbl RW0bl, RT2d; \
+	movzbl RW0bh, RT3d; \
+	xorq s7(, RL1, 8), RT0; \
+	xorq s5(, RT1, 8), to; \
+	xorq s3(, RT2, 8), RT0; \
+	load_next_key(n, RW0); \
+	xorq RT0, to; \
+	xorq s1(, RT3, 8), to; \
+
+#define load_next_key(n, RWx) \
+	movq (((n) + 1) * 8)(CTX), RWx;
+
+#define dummy2(a, b) /*_*/
+
+#define read_block(io, left, right) \
+	movl    (io), left##d; \
+	movl   4(io), right##d; \
+	bswapl left##d; \
+	bswapl right##d;
+
+#define write_block(io, left, right) \
+	bswapl left##d; \
+	bswapl right##d; \
+	movl   left##d,   (io); \
+	movl   right##d, 4(io);
+
+ENTRY(des3_ede_x86_64_crypt_blk)
+	/* input:
+	 *	%rdi: round keys, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+	pushq %rbp;
+	pushq %rbx;
+	pushq %r12;
+	pushq %r13;
+	pushq %r14;
+	pushq %r15;
+
+	read_block(%rdx, RL0, RR0);
+	initial_permutation(RL0, RR0);
+
+	movq (CTX), RW0;
+
+	round1(0, RR0, RL0, load_next_key);
+	round1(1, RL0, RR0, load_next_key);
+	round1(2, RR0, RL0, load_next_key);
+	round1(3, RL0, RR0, load_next_key);
+	round1(4, RR0, RL0, load_next_key);
+	round1(5, RL0, RR0, load_next_key);
+	round1(6, RR0, RL0, load_next_key);
+	round1(7, RL0, RR0, load_next_key);
+	round1(8, RR0, RL0, load_next_key);
+	round1(9, RL0, RR0, load_next_key);
+	round1(10, RR0, RL0, load_next_key);
+	round1(11, RL0, RR0, load_next_key);
+	round1(12, RR0, RL0, load_next_key);
+	round1(13, RL0, RR0, load_next_key);
+	round1(14, RR0, RL0, load_next_key);
+	round1(15, RL0, RR0, load_next_key);
+
+	round1(16+0, RL0, RR0, load_next_key);
+	round1(16+1, RR0, RL0, load_next_key);
+	round1(16+2, RL0, RR0, load_next_key);
+	round1(16+3, RR0, RL0, load_next_key);
+	round1(16+4, RL0, RR0, load_next_key);
+	round1(16+5, RR0, RL0, load_next_key);
+	round1(16+6, RL0, RR0, load_next_key);
+	round1(16+7, RR0, RL0, load_next_key);
+	round1(16+8, RL0, RR0, load_next_key);
+	round1(16+9, RR0, RL0, load_next_key);
+	round1(16+10, RL0, RR0, load_next_key);
+	round1(16+11, RR0, RL0, load_next_key);
+	round1(16+12, RL0, RR0, load_next_key);
+	round1(16+13, RR0, RL0, load_next_key);
+	round1(16+14, RL0, RR0, load_next_key);
+	round1(16+15, RR0, RL0, load_next_key);
+
+	round1(32+0, RR0, RL0, load_next_key);
+	round1(32+1, RL0, RR0, load_next_key);
+	round1(32+2, RR0, RL0, load_next_key);
+	round1(32+3, RL0, RR0, load_next_key);
+	round1(32+4, RR0, RL0, load_next_key);
+	round1(32+5, RL0, RR0, load_next_key);
+	round1(32+6, RR0, RL0, load_next_key);
+	round1(32+7, RL0, RR0, load_next_key);
+	round1(32+8, RR0, RL0, load_next_key);
+	round1(32+9, RL0, RR0, load_next_key);
+	round1(32+10, RR0, RL0, load_next_key);
+	round1(32+11, RL0, RR0, load_next_key);
+	round1(32+12, RR0, RL0, load_next_key);
+	round1(32+13, RL0, RR0, load_next_key);
+	round1(32+14, RR0, RL0, load_next_key);
+	round1(32+15, RL0, RR0, dummy2);
+
+	final_permutation(RR0, RL0);
+	write_block(%rsi, RR0, RL0);
+
+	popq %r15;
+	popq %r14;
+	popq %r13;
+	popq %r12;
+	popq %rbx;
+	popq %rbp;
+
+	ret;
+ENDPROC(des3_ede_x86_64_crypt_blk)
+
+/***********************************************************************
+ * 3-way 3DES
+ ***********************************************************************/
+#define expand_to_64bits(val, mask) \
+	movl val##d, RT0d; \
+	rorl $4, RT0d; \
+	shlq $32, RT0; \
+	orq RT0, val; \
+	andq mask, val;
+
+#define compress_to_64bits(val) \
+	movq val, RT0; \
+	shrq $32, RT0; \
+	roll $4, RT0d; \
+	orl RT0d, val##d;
+
+#define initial_permutation3(left, right) \
+	do_permutation(left##0d, right##0d,  4, 0x0f0f0f0f); \
+	do_permutation(left##0d, right##0d, 16, 0x0000ffff); \
+	  do_permutation(left##1d, right##1d,  4, 0x0f0f0f0f); \
+	  do_permutation(left##1d, right##1d, 16, 0x0000ffff); \
+	    do_permutation(left##2d, right##2d,  4, 0x0f0f0f0f); \
+	    do_permutation(left##2d, right##2d, 16, 0x0000ffff); \
+	    \
+	do_permutation(right##0d, left##0d,  2, 0x33333333); \
+	do_permutation(right##0d, left##0d,  8, 0x00ff00ff); \
+	  do_permutation(right##1d, left##1d,  2, 0x33333333); \
+	  do_permutation(right##1d, left##1d,  8, 0x00ff00ff); \
+	    do_permutation(right##2d, left##2d,  2, 0x33333333); \
+	    do_permutation(right##2d, left##2d,  8, 0x00ff00ff); \
+	    \
+	movabs $0x3f3f3f3f3f3f3f3f, RT3; \
+	    \
+	movl left##0d, RW0d; \
+	roll $1, right##0d; \
+	xorl right##0d, RW0d; \
+	andl $0xaaaaaaaa, RW0d; \
+	xorl RW0d, left##0d; \
+	xorl RW0d, right##0d; \
+	roll $1, left##0d; \
+	expand_to_64bits(right##0, RT3); \
+	expand_to_64bits(left##0, RT3); \
+	  movl left##1d, RW1d; \
+	  roll $1, right##1d; \
+	  xorl right##1d, RW1d; \
+	  andl $0xaaaaaaaa, RW1d; \
+	  xorl RW1d, left##1d; \
+	  xorl RW1d, right##1d; \
+	  roll $1, left##1d; \
+	  expand_to_64bits(right##1, RT3); \
+	  expand_to_64bits(left##1, RT3); \
+	    movl left##2d, RW2d; \
+	    roll $1, right##2d; \
+	    xorl right##2d, RW2d; \
+	    andl $0xaaaaaaaa, RW2d; \
+	    xorl RW2d, left##2d; \
+	    xorl RW2d, right##2d; \
+	    roll $1, left##2d; \
+	    expand_to_64bits(right##2, RT3); \
+	    expand_to_64bits(left##2, RT3);
+
+#define final_permutation3(left, right) \
+	compress_to_64bits(right##0); \
+	compress_to_64bits(left##0); \
+	movl right##0d, RW0d; \
+	rorl $1, left##0d; \
+	xorl left##0d, RW0d; \
+	andl $0xaaaaaaaa, RW0d; \
+	xorl RW0d, right##0d; \
+	xorl RW0d, left##0d; \
+	rorl $1, right##0d; \
+	  compress_to_64bits(right##1); \
+	  compress_to_64bits(left##1); \
+	  movl right##1d, RW1d; \
+	  rorl $1, left##1d; \
+	  xorl left##1d, RW1d; \
+	  andl $0xaaaaaaaa, RW1d; \
+	  xorl RW1d, right##1d; \
+	  xorl RW1d, left##1d; \
+	  rorl $1, right##1d; \
+	    compress_to_64bits(right##2); \
+	    compress_to_64bits(left##2); \
+	    movl right##2d, RW2d; \
+	    rorl $1, left##2d; \
+	    xorl left##2d, RW2d; \
+	    andl $0xaaaaaaaa, RW2d; \
+	    xorl RW2d, right##2d; \
+	    xorl RW2d, left##2d; \
+	    rorl $1, right##2d; \
+	    \
+	do_permutation(right##0d, left##0d,  8, 0x00ff00ff); \
+	do_permutation(right##0d, left##0d,  2, 0x33333333); \
+	  do_permutation(right##1d, left##1d,  8, 0x00ff00ff); \
+	  do_permutation(right##1d, left##1d,  2, 0x33333333); \
+	    do_permutation(right##2d, left##2d,  8, 0x00ff00ff); \
+	    do_permutation(right##2d, left##2d,  2, 0x33333333); \
+	    \
+	do_permutation(left##0d, right##0d, 16, 0x0000ffff); \
+	do_permutation(left##0d, right##0d,  4, 0x0f0f0f0f); \
+	  do_permutation(left##1d, right##1d, 16, 0x0000ffff); \
+	  do_permutation(left##1d, right##1d,  4, 0x0f0f0f0f); \
+	    do_permutation(left##2d, right##2d, 16, 0x0000ffff); \
+	    do_permutation(left##2d, right##2d,  4, 0x0f0f0f0f);
+
+#define round3(n, from, to, load_next_key, do_movq) \
+	xorq from##0, RW0; \
+	movzbl RW0bl, RT3d; \
+	movzbl RW0bh, RT1d; \
+	shrq $16, RW0; \
+	xorq s8(, RT3, 8), to##0; \
+	xorq s6(, RT1, 8), to##0; \
+	movzbl RW0bl, RT3d; \
+	movzbl RW0bh, RT1d; \
+	shrq $16, RW0; \
+	xorq s4(, RT3, 8), to##0; \
+	xorq s2(, RT1, 8), to##0; \
+	movzbl RW0bl, RT3d; \
+	movzbl RW0bh, RT1d; \
+	shrl $16, RW0d; \
+	xorq s7(, RT3, 8), to##0; \
+	xorq s5(, RT1, 8), to##0; \
+	movzbl RW0bl, RT3d; \
+	movzbl RW0bh, RT1d; \
+	load_next_key(n, RW0); \
+	xorq s3(, RT3, 8), to##0; \
+	xorq s1(, RT1, 8), to##0; \
+		xorq from##1, RW1; \
+		movzbl RW1bl, RT3d; \
+		movzbl RW1bh, RT1d; \
+		shrq $16, RW1; \
+		xorq s8(, RT3, 8), to##1; \
+		xorq s6(, RT1, 8), to##1; \
+		movzbl RW1bl, RT3d; \
+		movzbl RW1bh, RT1d; \
+		shrq $16, RW1; \
+		xorq s4(, RT3, 8), to##1; \
+		xorq s2(, RT1, 8), to##1; \
+		movzbl RW1bl, RT3d; \
+		movzbl RW1bh, RT1d; \
+		shrl $16, RW1d; \
+		xorq s7(, RT3, 8), to##1; \
+		xorq s5(, RT1, 8), to##1; \
+		movzbl RW1bl, RT3d; \
+		movzbl RW1bh, RT1d; \
+		do_movq(RW0, RW1); \
+		xorq s3(, RT3, 8), to##1; \
+		xorq s1(, RT1, 8), to##1; \
+			xorq from##2, RW2; \
+			movzbl RW2bl, RT3d; \
+			movzbl RW2bh, RT1d; \
+			shrq $16, RW2; \
+			xorq s8(, RT3, 8), to##2; \
+			xorq s6(, RT1, 8), to##2; \
+			movzbl RW2bl, RT3d; \
+			movzbl RW2bh, RT1d; \
+			shrq $16, RW2; \
+			xorq s4(, RT3, 8), to##2; \
+			xorq s2(, RT1, 8), to##2; \
+			movzbl RW2bl, RT3d; \
+			movzbl RW2bh, RT1d; \
+			shrl $16, RW2d; \
+			xorq s7(, RT3, 8), to##2; \
+			xorq s5(, RT1, 8), to##2; \
+			movzbl RW2bl, RT3d; \
+			movzbl RW2bh, RT1d; \
+			do_movq(RW0, RW2); \
+			xorq s3(, RT3, 8), to##2; \
+			xorq s1(, RT1, 8), to##2;
+
+#define __movq(src, dst) \
+	movq src, dst;
+
+ENTRY(des3_ede_x86_64_crypt_blk_3way)
+	/* input:
+	 *	%rdi: ctx, round keys
+	 *	%rsi: dst (3 blocks)
+	 *	%rdx: src (3 blocks)
+	 */
+
+	pushq %rbp;
+	pushq %rbx;
+	pushq %r12;
+	pushq %r13;
+	pushq %r14;
+	pushq %r15;
+
+	/* load input */
+	movl 0 * 4(%rdx), RL0d;
+	movl 1 * 4(%rdx), RR0d;
+	movl 2 * 4(%rdx), RL1d;
+	movl 3 * 4(%rdx), RR1d;
+	movl 4 * 4(%rdx), RL2d;
+	movl 5 * 4(%rdx), RR2d;
+
+	bswapl RL0d;
+	bswapl RR0d;
+	bswapl RL1d;
+	bswapl RR1d;
+	bswapl RL2d;
+	bswapl RR2d;
+
+	initial_permutation3(RL, RR);
+
+	movq 0(CTX), RW0;
+	movq RW0, RW1;
+	movq RW0, RW2;
+
+	round3(0, RR, RL, load_next_key, __movq);
+	round3(1, RL, RR, load_next_key, __movq);
+	round3(2, RR, RL, load_next_key, __movq);
+	round3(3, RL, RR, load_next_key, __movq);
+	round3(4, RR, RL, load_next_key, __movq);
+	round3(5, RL, RR, load_next_key, __movq);
+	round3(6, RR, RL, load_next_key, __movq);
+	round3(7, RL, RR, load_next_key, __movq);
+	round3(8, RR, RL, load_next_key, __movq);
+	round3(9, RL, RR, load_next_key, __movq);
+	round3(10, RR, RL, load_next_key, __movq);
+	round3(11, RL, RR, load_next_key, __movq);
+	round3(12, RR, RL, load_next_key, __movq);
+	round3(13, RL, RR, load_next_key, __movq);
+	round3(14, RR, RL, load_next_key, __movq);
+	round3(15, RL, RR, load_next_key, __movq);
+
+	round3(16+0, RL, RR, load_next_key, __movq);
+	round3(16+1, RR, RL, load_next_key, __movq);
+	round3(16+2, RL, RR, load_next_key, __movq);
+	round3(16+3, RR, RL, load_next_key, __movq);
+	round3(16+4, RL, RR, load_next_key, __movq);
+	round3(16+5, RR, RL, load_next_key, __movq);
+	round3(16+6, RL, RR, load_next_key, __movq);
+	round3(16+7, RR, RL, load_next_key, __movq);
+	round3(16+8, RL, RR, load_next_key, __movq);
+	round3(16+9, RR, RL, load_next_key, __movq);
+	round3(16+10, RL, RR, load_next_key, __movq);
+	round3(16+11, RR, RL, load_next_key, __movq);
+	round3(16+12, RL, RR, load_next_key, __movq);
+	round3(16+13, RR, RL, load_next_key, __movq);
+	round3(16+14, RL, RR, load_next_key, __movq);
+	round3(16+15, RR, RL, load_next_key, __movq);
+
+	round3(32+0, RR, RL, load_next_key, __movq);
+	round3(32+1, RL, RR, load_next_key, __movq);
+	round3(32+2, RR, RL, load_next_key, __movq);
+	round3(32+3, RL, RR, load_next_key, __movq);
+	round3(32+4, RR, RL, load_next_key, __movq);
+	round3(32+5, RL, RR, load_next_key, __movq);
+	round3(32+6, RR, RL, load_next_key, __movq);
+	round3(32+7, RL, RR, load_next_key, __movq);
+	round3(32+8, RR, RL, load_next_key, __movq);
+	round3(32+9, RL, RR, load_next_key, __movq);
+	round3(32+10, RR, RL, load_next_key, __movq);
+	round3(32+11, RL, RR, load_next_key, __movq);
+	round3(32+12, RR, RL, load_next_key, __movq);
+	round3(32+13, RL, RR, load_next_key, __movq);
+	round3(32+14, RR, RL, load_next_key, __movq);
+	round3(32+15, RL, RR, dummy2, dummy2);
+
+	final_permutation3(RR, RL);
+
+	bswapl RR0d;
+	bswapl RL0d;
+	bswapl RR1d;
+	bswapl RL1d;
+	bswapl RR2d;
+	bswapl RL2d;
+
+	movl RR0d, 0 * 4(%rsi);
+	movl RL0d, 1 * 4(%rsi);
+	movl RR1d, 2 * 4(%rsi);
+	movl RL1d, 3 * 4(%rsi);
+	movl RR2d, 4 * 4(%rsi);
+	movl RL2d, 5 * 4(%rsi);
+
+	popq %r15;
+	popq %r14;
+	popq %r13;
+	popq %r12;
+	popq %rbx;
+	popq %rbp;
+
+	ret;
+ENDPROC(des3_ede_x86_64_crypt_blk_3way)
+
+.data
+.align 16
+.L_s1:
+	.quad 0x0010100001010400, 0x0000000000000000
+	.quad 0x0000100000010000, 0x0010100001010404
+	.quad 0x0010100001010004, 0x0000100000010404
+	.quad 0x0000000000000004, 0x0000100000010000
+	.quad 0x0000000000000400, 0x0010100001010400
+	.quad 0x0010100001010404, 0x0000000000000400
+	.quad 0x0010000001000404, 0x0010100001010004
+	.quad 0x0010000001000000, 0x0000000000000004
+	.quad 0x0000000000000404, 0x0010000001000400
+	.quad 0x0010000001000400, 0x0000100000010400
+	.quad 0x0000100000010400, 0x0010100001010000
+	.quad 0x0010100001010000, 0x0010000001000404
+	.quad 0x0000100000010004, 0x0010000001000004
+	.quad 0x0010000001000004, 0x0000100000010004
+	.quad 0x0000000000000000, 0x0000000000000404
+	.quad 0x0000100000010404, 0x0010000001000000
+	.quad 0x0000100000010000, 0x0010100001010404
+	.quad 0x0000000000000004, 0x0010100001010000
+	.quad 0x0010100001010400, 0x0010000001000000
+	.quad 0x0010000001000000, 0x0000000000000400
+	.quad 0x0010100001010004, 0x0000100000010000
+	.quad 0x0000100000010400, 0x0010000001000004
+	.quad 0x0000000000000400, 0x0000000000000004
+	.quad 0x0010000001000404, 0x0000100000010404
+	.quad 0x0010100001010404, 0x0000100000010004
+	.quad 0x0010100001010000, 0x0010000001000404
+	.quad 0x0010000001000004, 0x0000000000000404
+	.quad 0x0000100000010404, 0x0010100001010400
+	.quad 0x0000000000000404, 0x0010000001000400
+	.quad 0x0010000001000400, 0x0000000000000000
+	.quad 0x0000100000010004, 0x0000100000010400
+	.quad 0x0000000000000000, 0x0010100001010004
+.L_s2:
+	.quad 0x0801080200100020, 0x0800080000000000
+	.quad 0x0000080000000000, 0x0001080200100020
+	.quad 0x0001000000100000, 0x0000000200000020
+	.quad 0x0801000200100020, 0x0800080200000020
+	.quad 0x0800000200000020, 0x0801080200100020
+	.quad 0x0801080000100000, 0x0800000000000000
+	.quad 0x0800080000000000, 0x0001000000100000
+	.quad 0x0000000200000020, 0x0801000200100020
+	.quad 0x0001080000100000, 0x0001000200100020
+	.quad 0x0800080200000020, 0x0000000000000000
+	.quad 0x0800000000000000, 0x0000080000000000
+	.quad 0x0001080200100020, 0x0801000000100000
+	.quad 0x0001000200100020, 0x0800000200000020
+	.quad 0x0000000000000000, 0x0001080000100000
+	.quad 0x0000080200000020, 0x0801080000100000
+	.quad 0x0801000000100000, 0x0000080200000020
+	.quad 0x0000000000000000, 0x0001080200100020
+	.quad 0x0801000200100020, 0x0001000000100000
+	.quad 0x0800080200000020, 0x0801000000100000
+	.quad 0x0801080000100000, 0x0000080000000000
+	.quad 0x0801000000100000, 0x0800080000000000
+	.quad 0x0000000200000020, 0x0801080200100020
+	.quad 0x0001080200100020, 0x0000000200000020
+	.quad 0x0000080000000000, 0x0800000000000000
+	.quad 0x0000080200000020, 0x0801080000100000
+	.quad 0x0001000000100000, 0x0800000200000020
+	.quad 0x0001000200100020, 0x0800080200000020
+	.quad 0x0800000200000020, 0x0001000200100020
+	.quad 0x0001080000100000, 0x0000000000000000
+	.quad 0x0800080000000000, 0x0000080200000020
+	.quad 0x0800000000000000, 0x0801000200100020
+	.quad 0x0801080200100020, 0x0001080000100000
+.L_s3:
+	.quad 0x0000002000000208, 0x0000202008020200
+	.quad 0x0000000000000000, 0x0000200008020008
+	.quad 0x0000002008000200, 0x0000000000000000
+	.quad 0x0000202000020208, 0x0000002008000200
+	.quad 0x0000200000020008, 0x0000000008000008
+	.quad 0x0000000008000008, 0x0000200000020000
+	.quad 0x0000202008020208, 0x0000200000020008
+	.quad 0x0000200008020000, 0x0000002000000208
+	.quad 0x0000000008000000, 0x0000000000000008
+	.quad 0x0000202008020200, 0x0000002000000200
+	.quad 0x0000202000020200, 0x0000200008020000
+	.quad 0x0000200008020008, 0x0000202000020208
+	.quad 0x0000002008000208, 0x0000202000020200
+	.quad 0x0000200000020000, 0x0000002008000208
+	.quad 0x0000000000000008, 0x0000202008020208
+	.quad 0x0000002000000200, 0x0000000008000000
+	.quad 0x0000202008020200, 0x0000000008000000
+	.quad 0x0000200000020008, 0x0000002000000208
+	.quad 0x0000200000020000, 0x0000202008020200
+	.quad 0x0000002008000200, 0x0000000000000000
+	.quad 0x0000002000000200, 0x0000200000020008
+	.quad 0x0000202008020208, 0x0000002008000200
+	.quad 0x0000000008000008, 0x0000002000000200
+	.quad 0x0000000000000000, 0x0000200008020008
+	.quad 0x0000002008000208, 0x0000200000020000
+	.quad 0x0000000008000000, 0x0000202008020208
+	.quad 0x0000000000000008, 0x0000202000020208
+	.quad 0x0000202000020200, 0x0000000008000008
+	.quad 0x0000200008020000, 0x0000002008000208
+	.quad 0x0000002000000208, 0x0000200008020000
+	.quad 0x0000202000020208, 0x0000000000000008
+	.quad 0x0000200008020008, 0x0000202000020200
+.L_s4:
+	.quad 0x1008020000002001, 0x1000020800002001
+	.quad 0x1000020800002001, 0x0000000800000000
+	.quad 0x0008020800002000, 0x1008000800000001
+	.quad 0x1008000000000001, 0x1000020000002001
+	.quad 0x0000000000000000, 0x0008020000002000
+	.quad 0x0008020000002000, 0x1008020800002001
+	.quad 0x1000000800000001, 0x0000000000000000
+	.quad 0x0008000800000000, 0x1008000000000001
+	.quad 0x1000000000000001, 0x0000020000002000
+	.quad 0x0008000000000000, 0x1008020000002001
+	.quad 0x0000000800000000, 0x0008000000000000
+	.quad 0x1000020000002001, 0x0000020800002000
+	.quad 0x1008000800000001, 0x1000000000000001
+	.quad 0x0000020800002000, 0x0008000800000000
+	.quad 0x0000020000002000, 0x0008020800002000
+	.quad 0x1008020800002001, 0x1000000800000001
+	.quad 0x0008000800000000, 0x1008000000000001
+	.quad 0x0008020000002000, 0x1008020800002001
+	.quad 0x1000000800000001, 0x0000000000000000
+	.quad 0x0000000000000000, 0x0008020000002000
+	.quad 0x0000020800002000, 0x0008000800000000
+	.quad 0x1008000800000001, 0x1000000000000001
+	.quad 0x1008020000002001, 0x1000020800002001
+	.quad 0x1000020800002001, 0x0000000800000000
+	.quad 0x1008020800002001, 0x1000000800000001
+	.quad 0x1000000000000001, 0x0000020000002000
+	.quad 0x1008000000000001, 0x1000020000002001
+	.quad 0x0008020800002000, 0x1008000800000001
+	.quad 0x1000020000002001, 0x0000020800002000
+	.quad 0x0008000000000000, 0x1008020000002001
+	.quad 0x0000000800000000, 0x0008000000000000
+	.quad 0x0000020000002000, 0x0008020800002000
+.L_s5:
+	.quad 0x0000001000000100, 0x0020001002080100
+	.quad 0x0020000002080000, 0x0420001002000100
+	.quad 0x0000000000080000, 0x0000001000000100
+	.quad 0x0400000000000000, 0x0020000002080000
+	.quad 0x0400001000080100, 0x0000000000080000
+	.quad 0x0020001002000100, 0x0400001000080100
+	.quad 0x0420001002000100, 0x0420000002080000
+	.quad 0x0000001000080100, 0x0400000000000000
+	.quad 0x0020000002000000, 0x0400000000080000
+	.quad 0x0400000000080000, 0x0000000000000000
+	.quad 0x0400001000000100, 0x0420001002080100
+	.quad 0x0420001002080100, 0x0020001002000100
+	.quad 0x0420000002080000, 0x0400001000000100
+	.quad 0x0000000000000000, 0x0420000002000000
+	.quad 0x0020001002080100, 0x0020000002000000
+	.quad 0x0420000002000000, 0x0000001000080100
+	.quad 0x0000000000080000, 0x0420001002000100
+	.quad 0x0000001000000100, 0x0020000002000000
+	.quad 0x0400000000000000, 0x0020000002080000
+	.quad 0x0420001002000100, 0x0400001000080100
+	.quad 0x0020001002000100, 0x0400000000000000
+	.quad 0x0420000002080000, 0x0020001002080100
+	.quad 0x0400001000080100, 0x0000001000000100
+	.quad 0x0020000002000000, 0x0420000002080000
+	.quad 0x0420001002080100, 0x0000001000080100
+	.quad 0x0420000002000000, 0x0420001002080100
+	.quad 0x0020000002080000, 0x0000000000000000
+	.quad 0x0400000000080000, 0x0420000002000000
+	.quad 0x0000001000080100, 0x0020001002000100
+	.quad 0x0400001000000100, 0x0000000000080000
+	.quad 0x0000000000000000, 0x0400000000080000
+	.quad 0x0020001002080100, 0x0400001000000100
+.L_s6:
+	.quad 0x0200000120000010, 0x0204000020000000
+	.quad 0x0000040000000000, 0x0204040120000010
+	.quad 0x0204000020000000, 0x0000000100000010
+	.quad 0x0204040120000010, 0x0004000000000000
+	.quad 0x0200040020000000, 0x0004040100000010
+	.quad 0x0004000000000000, 0x0200000120000010
+	.quad 0x0004000100000010, 0x0200040020000000
+	.quad 0x0200000020000000, 0x0000040100000010
+	.quad 0x0000000000000000, 0x0004000100000010
+	.quad 0x0200040120000010, 0x0000040000000000
+	.quad 0x0004040000000000, 0x0200040120000010
+	.quad 0x0000000100000010, 0x0204000120000010
+	.quad 0x0204000120000010, 0x0000000000000000
+	.quad 0x0004040100000010, 0x0204040020000000
+	.quad 0x0000040100000010, 0x0004040000000000
+	.quad 0x0204040020000000, 0x0200000020000000
+	.quad 0x0200040020000000, 0x0000000100000010
+	.quad 0x0204000120000010, 0x0004040000000000
+	.quad 0x0204040120000010, 0x0004000000000000
+	.quad 0x0000040100000010, 0x0200000120000010
+	.quad 0x0004000000000000, 0x0200040020000000
+	.quad 0x0200000020000000, 0x0000040100000010
+	.quad 0x0200000120000010, 0x0204040120000010
+	.quad 0x0004040000000000, 0x0204000020000000
+	.quad 0x0004040100000010, 0x0204040020000000
+	.quad 0x0000000000000000, 0x0204000120000010
+	.quad 0x0000000100000010, 0x0000040000000000
+	.quad 0x0204000020000000, 0x0004040100000010
+	.quad 0x0000040000000000, 0x0004000100000010
+	.quad 0x0200040120000010, 0x0000000000000000
+	.quad 0x0204040020000000, 0x0200000020000000
+	.quad 0x0004000100000010, 0x0200040120000010
+.L_s7:
+	.quad 0x0002000000200000, 0x2002000004200002
+	.quad 0x2000000004000802, 0x0000000000000000
+	.quad 0x0000000000000800, 0x2000000004000802
+	.quad 0x2002000000200802, 0x0002000004200800
+	.quad 0x2002000004200802, 0x0002000000200000
+	.quad 0x0000000000000000, 0x2000000004000002
+	.quad 0x2000000000000002, 0x0000000004000000
+	.quad 0x2002000004200002, 0x2000000000000802
+	.quad 0x0000000004000800, 0x2002000000200802
+	.quad 0x2002000000200002, 0x0000000004000800
+	.quad 0x2000000004000002, 0x0002000004200000
+	.quad 0x0002000004200800, 0x2002000000200002
+	.quad 0x0002000004200000, 0x0000000000000800
+	.quad 0x2000000000000802, 0x2002000004200802
+	.quad 0x0002000000200800, 0x2000000000000002
+	.quad 0x0000000004000000, 0x0002000000200800
+	.quad 0x0000000004000000, 0x0002000000200800
+	.quad 0x0002000000200000, 0x2000000004000802
+	.quad 0x2000000004000802, 0x2002000004200002
+	.quad 0x2002000004200002, 0x2000000000000002
+	.quad 0x2002000000200002, 0x0000000004000000
+	.quad 0x0000000004000800, 0x0002000000200000
+	.quad 0x0002000004200800, 0x2000000000000802
+	.quad 0x2002000000200802, 0x0002000004200800
+	.quad 0x2000000000000802, 0x2000000004000002
+	.quad 0x2002000004200802, 0x0002000004200000
+	.quad 0x0002000000200800, 0x0000000000000000
+	.quad 0x2000000000000002, 0x2002000004200802
+	.quad 0x0000000000000000, 0x2002000000200802
+	.quad 0x0002000004200000, 0x0000000000000800
+	.quad 0x2000000004000002, 0x0000000004000800
+	.quad 0x0000000000000800, 0x2002000000200002
+.L_s8:
+	.quad 0x0100010410001000, 0x0000010000001000
+	.quad 0x0000000000040000, 0x0100010410041000
+	.quad 0x0100000010000000, 0x0100010410001000
+	.quad 0x0000000400000000, 0x0100000010000000
+	.quad 0x0000000400040000, 0x0100000010040000
+	.quad 0x0100010410041000, 0x0000010000041000
+	.quad 0x0100010010041000, 0x0000010400041000
+	.quad 0x0000010000001000, 0x0000000400000000
+	.quad 0x0100000010040000, 0x0100000410000000
+	.quad 0x0100010010001000, 0x0000010400001000
+	.quad 0x0000010000041000, 0x0000000400040000
+	.quad 0x0100000410040000, 0x0100010010041000
+	.quad 0x0000010400001000, 0x0000000000000000
+	.quad 0x0000000000000000, 0x0100000410040000
+	.quad 0x0100000410000000, 0x0100010010001000
+	.quad 0x0000010400041000, 0x0000000000040000
+	.quad 0x0000010400041000, 0x0000000000040000
+	.quad 0x0100010010041000, 0x0000010000001000
+	.quad 0x0000000400000000, 0x0100000410040000
+	.quad 0x0000010000001000, 0x0000010400041000
+	.quad 0x0100010010001000, 0x0000000400000000
+	.quad 0x0100000410000000, 0x0100000010040000
+	.quad 0x0100000410040000, 0x0100000010000000
+	.quad 0x0000000000040000, 0x0100010410001000
+	.quad 0x0000000000000000, 0x0100010410041000
+	.quad 0x0000000400040000, 0x0100000410000000
+	.quad 0x0100000010040000, 0x0100010010001000
+	.quad 0x0100010410001000, 0x0000000000000000
+	.quad 0x0100010410041000, 0x0000010000041000
+	.quad 0x0000010000041000, 0x0000010400001000
+	.quad 0x0000010400001000, 0x0000000400040000
+	.quad 0x0100000010000000, 0x0100010010041000
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
new file mode 100644
index 00000000000..0e9c0668fe4
--- /dev/null
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -0,0 +1,509 @@
+/*
+ * Glue Code for assembler optimized version of 3DES
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
+ *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
+ * CTR part based on code (crypto/ctr.c) by:
+ *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <asm/processor.h>
+#include <crypto/des.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <crypto/algapi.h>
+
+struct des3_ede_x86_ctx {
+	u32 enc_expkey[DES3_EDE_EXPKEY_WORDS];
+	u32 dec_expkey[DES3_EDE_EXPKEY_WORDS];
+};
+
+/* regular block cipher functions */
+asmlinkage void des3_ede_x86_64_crypt_blk(const u32 *expkey, u8 *dst,
+					  const u8 *src);
+
+/* 3-way parallel cipher functions */
+asmlinkage void des3_ede_x86_64_crypt_blk_3way(const u32 *expkey, u8 *dst,
+					       const u8 *src);
+
+static inline void des3_ede_enc_blk(struct des3_ede_x86_ctx *ctx, u8 *dst,
+				    const u8 *src)
+{
+	u32 *enc_ctx = ctx->enc_expkey;
+
+	des3_ede_x86_64_crypt_blk(enc_ctx, dst, src);
+}
+
+static inline void des3_ede_dec_blk(struct des3_ede_x86_ctx *ctx, u8 *dst,
+				    const u8 *src)
+{
+	u32 *dec_ctx = ctx->dec_expkey;
+
+	des3_ede_x86_64_crypt_blk(dec_ctx, dst, src);
+}
+
+static inline void des3_ede_enc_blk_3way(struct des3_ede_x86_ctx *ctx, u8 *dst,
+					 const u8 *src)
+{
+	u32 *enc_ctx = ctx->enc_expkey;
+
+	des3_ede_x86_64_crypt_blk_3way(enc_ctx, dst, src);
+}
+
+static inline void des3_ede_dec_blk_3way(struct des3_ede_x86_ctx *ctx, u8 *dst,
+					 const u8 *src)
+{
+	u32 *dec_ctx = ctx->dec_expkey;
+
+	des3_ede_x86_64_crypt_blk_3way(dec_ctx, dst, src);
+}
+
+static void des3_ede_x86_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	des3_ede_enc_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static void des3_ede_x86_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	des3_ede_dec_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
+		     const u32 *expkey)
+{
+	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	unsigned int nbytes;
+	int err;
+
+	err = blkcipher_walk_virt(desc, walk);
+
+	while ((nbytes = walk->nbytes)) {
+		u8 *wsrc = walk->src.virt.addr;
+		u8 *wdst = walk->dst.virt.addr;
+
+		/* Process four block batch */
+		if (nbytes >= bsize * 3) {
+			do {
+				des3_ede_x86_64_crypt_blk_3way(expkey, wdst,
+							       wsrc);
+
+				wsrc += bsize * 3;
+				wdst += bsize * 3;
+				nbytes -= bsize * 3;
+			} while (nbytes >= bsize * 3);
+
+			if (nbytes < bsize)
+				goto done;
+		}
+
+		/* Handle leftovers */
+		do {
+			des3_ede_x86_64_crypt_blk(expkey, wdst, wsrc);
+
+			wsrc += bsize;
+			wdst += bsize;
+			nbytes -= bsize;
+		} while (nbytes >= bsize);
+
+done:
+		err = blkcipher_walk_done(desc, walk, nbytes);
+	}
+
+	return err;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_crypt(desc, &walk, ctx->enc_expkey);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_crypt(desc, &walk, ctx->dec_expkey);
+}
+
+static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
+				  struct blkcipher_walk *walk)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+	u64 *iv = (u64 *)walk->iv;
+
+	do {
+		*dst = *src ^ *iv;
+		des3_ede_enc_blk(ctx, (u8 *)dst, (u8 *)dst);
+		iv = dst;
+
+		src += 1;
+		dst += 1;
+		nbytes -= bsize;
+	} while (nbytes >= bsize);
+
+	*(u64 *)walk->iv = *iv;
+	return nbytes;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while ((nbytes = walk.nbytes)) {
+		nbytes = __cbc_encrypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	return err;
+}
+
+static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
+				  struct blkcipher_walk *walk)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+	u64 ivs[3 - 1];
+	u64 last_iv;
+
+	/* Start of the last block. */
+	src += nbytes / bsize - 1;
+	dst += nbytes / bsize - 1;
+
+	last_iv = *src;
+
+	/* Process four block batch */
+	if (nbytes >= bsize * 3) {
+		do {
+			nbytes -= bsize * 3 - bsize;
+			src -= 3 - 1;
+			dst -= 3 - 1;
+
+			ivs[0] = src[0];
+			ivs[1] = src[1];
+
+			des3_ede_dec_blk_3way(ctx, (u8 *)dst, (u8 *)src);
+
+			dst[1] ^= ivs[0];
+			dst[2] ^= ivs[1];
+
+			nbytes -= bsize;
+			if (nbytes < bsize)
+				goto done;
+
+			*dst ^= *(src - 1);
+			src -= 1;
+			dst -= 1;
+		} while (nbytes >= bsize * 3);
+	}
+
+	/* Handle leftovers */
+	for (;;) {
+		des3_ede_dec_blk(ctx, (u8 *)dst, (u8 *)src);
+
+		nbytes -= bsize;
+		if (nbytes < bsize)
+			break;
+
+		*dst ^= *(src - 1);
+		src -= 1;
+		dst -= 1;
+	}
+
+done:
+	*dst ^= *(u64 *)walk->iv;
+	*(u64 *)walk->iv = last_iv;
+
+	return nbytes;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while ((nbytes = walk.nbytes)) {
+		nbytes = __cbc_decrypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	return err;
+}
+
+static void ctr_crypt_final(struct des3_ede_x86_ctx *ctx,
+			    struct blkcipher_walk *walk)
+{
+	u8 *ctrblk = walk->iv;
+	u8 keystream[DES3_EDE_BLOCK_SIZE];
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+
+	des3_ede_enc_blk(ctx, keystream, ctrblk);
+	crypto_xor(keystream, src, nbytes);
+	memcpy(dst, keystream, nbytes);
+
+	crypto_inc(ctrblk, DES3_EDE_BLOCK_SIZE);
+}
+
+static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
+				struct blkcipher_walk *walk)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	__be64 *src = (__be64 *)walk->src.virt.addr;
+	__be64 *dst = (__be64 *)walk->dst.virt.addr;
+	u64 ctrblk = be64_to_cpu(*(__be64 *)walk->iv);
+	__be64 ctrblocks[3];
+
+	/* Process four block batch */
+	if (nbytes >= bsize * 3) {
+		do {
+			/* create ctrblks for parallel encrypt */
+			ctrblocks[0] = cpu_to_be64(ctrblk++);
+			ctrblocks[1] = cpu_to_be64(ctrblk++);
+			ctrblocks[2] = cpu_to_be64(ctrblk++);
+
+			des3_ede_enc_blk_3way(ctx, (u8 *)ctrblocks,
+					      (u8 *)ctrblocks);
+
+			dst[0] = src[0] ^ ctrblocks[0];
+			dst[1] = src[1] ^ ctrblocks[1];
+			dst[2] = src[2] ^ ctrblocks[2];
+
+			src += 3;
+			dst += 3;
+		} while ((nbytes -= bsize * 3) >= bsize * 3);
+
+		if (nbytes < bsize)
+			goto done;
+	}
+
+	/* Handle leftovers */
+	do {
+		ctrblocks[0] = cpu_to_be64(ctrblk++);
+
+		des3_ede_enc_blk(ctx, (u8 *)ctrblocks, (u8 *)ctrblocks);
+
+		dst[0] = src[0] ^ ctrblocks[0];
+
+		src += 1;
+		dst += 1;
+	} while ((nbytes -= bsize) >= bsize);
+
+done:
+	*(__be64 *)walk->iv = cpu_to_be64(ctrblk);
+	return nbytes;
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, DES3_EDE_BLOCK_SIZE);
+
+	while ((nbytes = walk.nbytes) >= DES3_EDE_BLOCK_SIZE) {
+		nbytes = __ctr_crypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	if (walk.nbytes) {
+		ctr_crypt_final(crypto_blkcipher_ctx(desc->tfm), &walk);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	return err;
+}
+
+static int des3_ede_x86_setkey(struct crypto_tfm *tfm, const u8 *key,
+			       unsigned int keylen)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 i, j, tmp;
+	int err;
+
+	/* Generate encryption context using generic implementation. */
+	err = __des3_ede_setkey(ctx->enc_expkey, &tfm->crt_flags, key, keylen);
+	if (err < 0)
+		return err;
+
+	/* Fix encryption context for this implementation and form decryption
+	 * context. */
+	j = DES3_EDE_EXPKEY_WORDS - 2;
+	for (i = 0; i < DES3_EDE_EXPKEY_WORDS; i += 2, j -= 2) {
+		tmp = ror32(ctx->enc_expkey[i + 1], 4);
+		ctx->enc_expkey[i + 1] = tmp;
+
+		ctx->dec_expkey[j + 0] = ctx->enc_expkey[i + 0];
+		ctx->dec_expkey[j + 1] = tmp;
+	}
+
+	return 0;
+}
+
+static struct crypto_alg des3_ede_algs[4] = { {
+	.cra_name		= "des3_ede",
+	.cra_driver_name	= "des3_ede-asm",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
+	.cra_alignmask		= 0,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.cipher = {
+			.cia_min_keysize	= DES3_EDE_KEY_SIZE,
+			.cia_max_keysize	= DES3_EDE_KEY_SIZE,
+			.cia_setkey		= des3_ede_x86_setkey,
+			.cia_encrypt		= des3_ede_x86_encrypt,
+			.cia_decrypt		= des3_ede_x86_decrypt,
+		}
+	}
+}, {
+	.cra_name		= "ecb(des3_ede)",
+	.cra_driver_name	= "ecb-des3_ede-asm",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= DES3_EDE_KEY_SIZE,
+			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.setkey		= des3_ede_x86_setkey,
+			.encrypt	= ecb_encrypt,
+			.decrypt	= ecb_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "cbc(des3_ede)",
+	.cra_driver_name	= "cbc-des3_ede-asm",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= DES3_EDE_KEY_SIZE,
+			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.ivsize		= DES3_EDE_BLOCK_SIZE,
+			.setkey		= des3_ede_x86_setkey,
+			.encrypt	= cbc_encrypt,
+			.decrypt	= cbc_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ctr(des3_ede)",
+	.cra_driver_name	= "ctr-des3_ede-asm",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= DES3_EDE_KEY_SIZE,
+			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.ivsize		= DES3_EDE_BLOCK_SIZE,
+			.setkey		= des3_ede_x86_setkey,
+			.encrypt	= ctr_crypt,
+			.decrypt	= ctr_crypt,
+		},
+	},
+} };
+
+static bool is_blacklisted_cpu(void)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return false;
+
+	if (boot_cpu_data.x86 == 0x0f) {
+		/*
+		 * On Pentium 4, des3_ede-x86_64 is slower than generic C
+		 * implementation because use of 64bit rotates (which are really
+		 * slow on P4). Therefore blacklist P4s.
+		 */
+		return true;
+	}
+
+	return false;
+}
+
+static int force;
+module_param(force, int, 0);
+MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
+
+static int __init des3_ede_x86_init(void)
+{
+	if (!force && is_blacklisted_cpu()) {
+		pr_info("des3_ede-x86_64: performance on this CPU would be suboptimal: disabling des3_ede-x86_64.\n");
+		return -ENODEV;
+	}
+
+	return crypto_register_algs(des3_ede_algs, ARRAY_SIZE(des3_ede_algs));
+}
+
+static void __exit des3_ede_x86_fini(void)
+{
+	crypto_unregister_algs(des3_ede_algs, ARRAY_SIZE(des3_ede_algs));
+}
+
+module_init(des3_ede_x86_init);
+module_exit(des3_ede_x86_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Triple DES EDE Cipher Algorithm, asm optimized");
+MODULE_ALIAS("des3_ede");
+MODULE_ALIAS("des3_ede-asm");
+MODULE_ALIAS("des");
+MODULE_ALIAS("des-asm");
+MODULE_AUTHOR("Jussi Kivilinna <jussi.kivilinna@iki.fi>");
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index f30cd10293f..8626b03e83b 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -141,7 +141,7 @@ static int sha512_ssse3_final(struct shash_desc *desc, u8 *out)
 
 	/* save number of bits */
 	bits[1] = cpu_to_be64(sctx->count[0] << 3);
-	bits[0] = cpu_to_be64(sctx->count[1] << 3) | sctx->count[0] >> 61;
+	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
 
 	/* Pad out to 112 mod 128 and append length */
 	index = sctx->count[0] & 0x7f;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 19b0ebafcd3..79752f2bdec 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -99,7 +99,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
 {
 	volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
 
-	alternative_io("movl %0, %1", "xchgl %0, %1", X86_FEATURE_11AP,
+	alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP,
 		       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
 		       ASM_OUTPUT2("0" (v), "m" (*addr)));
 }
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 4582e8e1cd1..7730c1c5c83 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -57,6 +57,12 @@
 	.long (from) - . ;					\
 	.long (to) - . + 0x7ffffff0 ;				\
 	.popsection
+
+# define _ASM_NOKPROBE(entry)					\
+	.pushsection "_kprobe_blacklist","aw" ;			\
+	_ASM_ALIGN ;						\
+	_ASM_PTR (entry);					\
+	.popsection
 #else
 # define _ASM_EXTABLE(from,to)					\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
@@ -71,6 +77,7 @@
 	" .long (" #from ") - .\n"				\
 	" .long (" #to ") - . + 0x7ffffff0\n"			\
 	" .popsection\n"
+/* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif
 
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 5c7198cca5e..0f4460b5636 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -99,7 +99,7 @@
 #if defined(CONFIG_X86_PPRO_FENCE)
 
 /*
- * For either of these options x86 doesn't have a strong TSO memory
+ * For this option x86 doesn't have a strong TSO memory
  * model and we should fall back to full barriers.
  */
 
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index e6fd8a026c7..cd00e177449 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -184,8 +184,15 @@ static inline unsigned add32_with_carry(unsigned a, unsigned b)
 	asm("addl %2,%0\n\t"
 	    "adcl $0,%0"
 	    : "=r" (a)
-	    : "0" (a), "r" (b));
+	    : "0" (a), "rm" (b));
 	return a;
 }
 
+#define HAVE_ARCH_CSUM_ADD
+static inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+	return (__force __wsum)add32_with_carry((__force unsigned)csum,
+						(__force unsigned)addend);
+}
+
 #endif /* _ASM_X86_CHECKSUM_64_H */
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index d47786acb01..99c105d78b7 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -4,6 +4,8 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
+#define __HAVE_ARCH_CMPXCHG 1
+
 /*
  * Non-existant functions to indicate usage errors at link time
  * (or compile-time if the compiler implements __compiletime_error().
@@ -143,7 +145,6 @@ extern void __add_wrong_size(void)
 # include <asm/cmpxchg_64.h>
 #endif
 
-#ifdef __HAVE_ARCH_CMPXCHG
 #define cmpxchg(ptr, old, new)						\
 	__cmpxchg(ptr, old, new, sizeof(*(ptr)))
 
@@ -152,7 +153,6 @@ extern void __add_wrong_size(void)
 
 #define cmpxchg_local(ptr, old, new)					\
 	__cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
-#endif
 
 /*
  * xadd() adds "inc" to "*ptr" and atomically returns the previous
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index f8bf2eecab8..f7e14292648 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -34,8 +34,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 value)
 		     : "memory");
 }
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #ifdef CONFIG_X86_CMPXCHG64
 #define cmpxchg64(ptr, o, n)						\
 	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 614be87f1a9..1af94697aae 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -6,8 +6,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 	*ptr = val;
 }
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define cmpxchg64(ptr, o, n)						\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e265ff95d16..bb9b258d60e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -8,7 +8,7 @@
 #include <asm/required-features.h>
 #endif
 
-#define NCAPINTS	10	/* N 32-bit words worth of info */
+#define NCAPINTS	11	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -18,213 +18,218 @@
  */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		(0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		(0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		(0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		(0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		(0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		(0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		(0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8		(0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	(0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		(0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	(0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		(0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		(0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	(0*32+15) /* CMOV instructions */
+#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
 					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		(0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	(0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		(0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH	(0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS		(0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	(0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		(0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	(0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		(0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	(0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	(0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		(0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		(0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	(0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		(0*32+31) /* Pending Break Enable */
+#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	(1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		(1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		(1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	(1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	(1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	(1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		(1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	(1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	(1*32+31) /* 3DNow! */
+#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
 
 /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	(2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	(2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	(2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
 
 /* Other features, Linux-defined mapping, word 3 */
 /* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	(3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	(3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	(3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	(3*32+ 3) /* Centaur MCRs (= MTRRs) */
+#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
 /* cpu types for specific tunings: */
-#define X86_FEATURE_K8		(3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		(3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		(3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		(3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		(3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
-#define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	(3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		(3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	(3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	(3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	(3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_11AP	(3*32+19) /* "" Bad local APIC aka 11AP */
-#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS	(3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY	(3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
-#define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     (3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF	(3*32+28) /* APERFMPERF */
-#define X86_FEATURE_EAGER_FPU	(3*32+29) /* "eagerfpu" Non lazy FPU restore */
-#define X86_FEATURE_NONSTOP_TSC_S3 (3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
+/* free, was #define X86_FEATURE_FXSAVE_LEAK ( 3*32+10) * "" FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
+/* free, was #define X86_FEATURE_11AP	( 3*32+19) * "" Bad local APIC aka 11AP */
+#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
+/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
+#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
+#define X86_FEATURE_EAGER_FPU	( 3*32+29) /* "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	(4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	(4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	(4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	(4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		(4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		(4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		(4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		(4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	(4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		(4*32+10) /* Context ID */
-#define X86_FEATURE_FMA		(4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	(4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	(4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	(4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID	(4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA		(4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	(4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	(4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	(4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE	(4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      (4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER	(4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES		(4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		(4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C	(4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND	(4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR	(4*32+31) /* Running on a hypervisor */
+#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
+#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
+#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
+#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
+#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	(5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	(5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	(5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	(5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	(5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	(5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		(5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	(5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		(5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	(5*32+13) /* PMM enabled */
+#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
 
 /* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	(6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	(6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		(6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	(6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	(6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		(6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	(6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE (6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	(6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		(6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP		(6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP		(6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4	(6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE		(6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM		(6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT	(6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB  (6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_PERFCTR_L2	(6*32+28) /* L2 performance counter extensions */
+#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
+#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_PERFCTR_L2	( 6*32+28) /* L2 performance counter extensions */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
  * CPUID levels like 0x6, 0xA etc, word 7
  */
-#define X86_FEATURE_IDA		(7*32+ 0) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	(7*32+ 1) /* Always Running APIC Timer */
-#define X86_FEATURE_CPB		(7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB		(7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_XSAVEOPT	(7*32+ 4) /* Optimized Xsave */
-#define X86_FEATURE_PLN		(7*32+ 5) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		(7*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_DTHERM	(7*32+ 7) /* Digital Thermal Sensor */
-#define X86_FEATURE_HW_PSTATE	(7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK (7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_IDA		( 7*32+ 0) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT	( 7*32+ 1) /* Always Running APIC Timer */
+#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_PLN		( 7*32+ 5) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS		( 7*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_DTHERM	( 7*32+ 7) /* Digital Thermal Sensor */
+#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 
 /* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        (8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         (8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        (8*32+ 4) /* Intel Virtual Processor ID */
-#define X86_FEATURE_NPT		(8*32+ 5) /* AMD Nested Page Table support */
-#define X86_FEATURE_LBRV	(8*32+ 6) /* AMD LBR Virtualization support */
-#define X86_FEATURE_SVML	(8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
-#define X86_FEATURE_NRIPS	(8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */
+#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_NPT		( 8*32+ 5) /* AMD Nested Page Table support */
+#define X86_FEATURE_LBRV	( 8*32+ 6) /* AMD LBR Virtualization support */
+#define X86_FEATURE_SVML	( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
+#define X86_FEATURE_NRIPS	( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
 
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST	(9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1	(9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE		(9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2	(9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP	(9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2	(9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID	(9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM		(9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_MPX		(9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_AVX512F	(9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_RDSEED	(9*32+18) /* The RDSEED instruction */
-#define X86_FEATURE_ADX		(9*32+19) /* The ADCX and ADOX instructions */
-#define X86_FEATURE_SMAP	(9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_CLFLUSHOPT	(9*32+23) /* CLFLUSHOPT instruction */
-#define X86_FEATURE_AVX512PF	(9*32+26) /* AVX-512 Prefetch */
-#define X86_FEATURE_AVX512ER	(9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD	(9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
+#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
+#define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
+
+/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
+#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
+#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
+#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
+#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
 
 /*
  * BUG word(s)
@@ -234,8 +239,11 @@
 #define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
 #define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
 #define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
-#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* AMD Erratum 383 */
-#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* AMD Erratum 400 */
+#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
@@ -245,6 +253,12 @@
 extern const char * const x86_cap_flags[NCAPINTS*32];
 extern const char * const x86_power_flags[32];
 
+/*
+ * In order to save room, we index into this array by doing
+ * X86_BUG_<name> - NCAPINTS*32.
+ */
+extern const char * const x86_bug_flags[NBUGINTS*32];
+
 #define test_cpu_cap(c, bit)						\
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
@@ -301,7 +315,6 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_avx		boot_cpu_has(X86_FEATURE_AVX)
 #define cpu_has_avx2		boot_cpu_has(X86_FEATURE_AVX2)
 #define cpu_has_ht		boot_cpu_has(X86_FEATURE_HT)
-#define cpu_has_mp		boot_cpu_has(X86_FEATURE_MP)
 #define cpu_has_nx		boot_cpu_has(X86_FEATURE_NX)
 #define cpu_has_k6_mtrr		boot_cpu_has(X86_FEATURE_K6_MTRR)
 #define cpu_has_cyrix_arr	boot_cpu_has(X86_FEATURE_CYRIX_ARR)
@@ -328,6 +341,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
 #define cpu_has_xsaveopt	boot_cpu_has(X86_FEATURE_XSAVEOPT)
+#define cpu_has_xsaves		boot_cpu_has(X86_FEATURE_XSAVES)
 #define cpu_has_osxsave		boot_cpu_has(X86_FEATURE_OSXSAVE)
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
@@ -347,9 +361,6 @@ extern const char * const x86_power_flags[32];
 #undef  cpu_has_pae
 #define cpu_has_pae		___BUG___
 
-#undef  cpu_has_mp
-#define cpu_has_mp		1
-
 #undef  cpu_has_k6_mtrr
 #define cpu_has_k6_mtrr		0
 
@@ -539,20 +550,20 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 #define static_cpu_has_safe(bit)	boot_cpu_has(bit)
 #endif
 
-#define cpu_has_bug(c, bit)	cpu_has(c, (bit))
-#define set_cpu_bug(c, bit)	set_cpu_cap(c, (bit))
-#define clear_cpu_bug(c, bit)	clear_cpu_cap(c, (bit));
+#define cpu_has_bug(c, bit)		cpu_has(c, (bit))
+#define set_cpu_bug(c, bit)		set_cpu_cap(c, (bit))
+#define clear_cpu_bug(c, bit)		clear_cpu_cap(c, (bit))
 
-#define static_cpu_has_bug(bit)	static_cpu_has((bit))
-#define boot_cpu_has_bug(bit)	cpu_has_bug(&boot_cpu_data, (bit))
+#define static_cpu_has_bug(bit)		static_cpu_has((bit))
+#define static_cpu_has_bug_safe(bit)	static_cpu_has_safe((bit))
+#define boot_cpu_has_bug(bit)		cpu_has_bug(&boot_cpu_data, (bit))
 
-#define MAX_CPU_FEATURES	(NCAPINTS * 32)
-#define cpu_have_feature	boot_cpu_has
+#define MAX_CPU_FEATURES		(NCAPINTS * 32)
+#define cpu_have_feature		boot_cpu_has
 
-#define CPU_FEATURE_TYPEFMT	"x86,ven%04Xfam%04Xmod%04X"
-#define CPU_FEATURE_TYPEVAL	boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
-				boot_cpu_data.x86_model
+#define CPU_FEATURE_TYPEFMT		"x86,ven%04Xfam%04Xmod%04X"
+#define CPU_FEATURE_TYPEVAL		boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
+					boot_cpu_data.x86_model
 
 #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
-
 #endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 1eb5f6433ad..044a2fd3c5f 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -104,6 +104,8 @@ extern void __init runtime_code_page_mkexec(void);
 extern void __init efi_runtime_mkexec(void);
 extern void __init efi_dump_pagetable(void);
 extern void __init efi_apply_memmap_quirks(void);
+extern int __init efi_reuse_config(u64 tables, int nr_tables);
+extern void efi_delete_dummy_variable(void);
 
 struct efi_setup_data {
 	u64 fw_vendor;
@@ -156,6 +158,33 @@ static inline efi_status_t efi_thunk_set_virtual_address_map(
 	return EFI_SUCCESS;
 }
 #endif /* CONFIG_EFI_MIXED */
+
+
+/* arch specific definitions used by the stub code */
+
+struct efi_config {
+	u64 image_handle;
+	u64 table;
+	u64 allocate_pool;
+	u64 allocate_pages;
+	u64 get_memory_map;
+	u64 free_pool;
+	u64 free_pages;
+	u64 locate_handle;
+	u64 handle_protocol;
+	u64 exit_boot_services;
+	u64 text_output;
+	efi_status_t (*call)(unsigned long, ...);
+	bool is64;
+} __packed;
+
+extern struct efi_config *efi_early;
+
+#define efi_call_early(f, ...)						\
+	efi_early->call(efi_early->f, __VA_ARGS__);
+
+extern bool efi_reboot_required(void);
+
 #else
 /*
  * IF EFI is not configured, have the EFI calls return -ENOSYS.
@@ -168,6 +197,10 @@ static inline efi_status_t efi_thunk_set_virtual_address_map(
 #define efi_call5(_f, _a1, _a2, _a3, _a4, _a5)		(-ENOSYS)
 #define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6)	(-ENOSYS)
 static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
+static inline bool efi_reboot_required(void)
+{
+	return false;
+}
 #endif /* CONFIG_EFI */
 
 #endif /* _ASM_X86_EFI_H */
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 115e3689cd5..e3b85422cf1 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -293,7 +293,7 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
 	   values. "m" is a random variable that should be in L1 */
-	if (unlikely(static_cpu_has_safe(X86_FEATURE_FXSAVE_LEAK))) {
+	if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) {
 		asm volatile(
 			"fnclex\n\t"
 			"emms\n\t"
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 0525a8bdf65..e1f7fecaa7d 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -68,6 +68,8 @@ struct dyn_arch_ftrace {
 
 int ftrace_int3_handler(struct pt_regs *regs);
 
+#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
+
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index cb6cfcd034c..a80cbb88ea9 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -43,7 +43,7 @@ extern int vector_used_by_percpu_irq(unsigned int vector);
 extern void init_ISA_irqs(void);
 
 #ifdef CONFIG_X86_LOCAL_APIC
-void arch_trigger_all_cpu_backtrace(void);
+void arch_trigger_all_cpu_backtrace(bool);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 #endif
 
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index bba3cf88e62..0a8b519226b 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void)
 
 #define PARAVIRT_ADJUST_EXCEPTION_FRAME	/*  */
 
-#define INTERRUPT_RETURN	iretq
+#define INTERRUPT_RETURN	jmp native_iret
 #define USERGS_SYSRET64				\
 	swapgs;					\
 	sysretq;
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 9454c167629..53cdfb2857a 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -116,4 +116,6 @@ struct kprobe_ctlblk {
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_exceptions_notify(struct notifier_block *self,
 				    unsigned long val, void *data);
+extern int kprobe_int3_handler(struct pt_regs *regs);
+extern int kprobe_debug_handler(struct pt_regs *regs);
 #endif /* _ASM_X86_KPROBES_H */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index a04fe4eb237..eb181178fe0 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -37,6 +37,7 @@ struct x86_instruction_info {
 	u8  modrm_reg;          /* index of register used               */
 	u8  modrm_rm;		/* rm part of modrm			*/
 	u64 src_val;            /* value of source operand              */
+	u64 dst_val;            /* value of destination operand         */
 	u8  src_bytes;          /* size of source operand               */
 	u8  dst_bytes;          /* size of destination operand          */
 	u8  ad_bytes;           /* size of src/dst address              */
@@ -194,6 +195,7 @@ struct x86_emulate_ops {
 	int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
 	int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
 	int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
+	int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc);
 	int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata);
 	void (*halt)(struct x86_emulate_ctxt *ctxt);
 	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
@@ -231,7 +233,7 @@ struct operand {
 	union {
 		unsigned long val;
 		u64 val64;
-		char valptr[sizeof(unsigned long) + 2];
+		char valptr[sizeof(sse128_t)];
 		sse128_t vec_val;
 		u64 mm_val;
 		void *data;
@@ -240,8 +242,8 @@ struct operand {
 
 struct fetch_cache {
 	u8 data[15];
-	unsigned long start;
-	unsigned long end;
+	u8 *ptr;
+	u8 *end;
 };
 
 struct read_cache {
@@ -286,30 +288,36 @@ struct x86_emulate_ctxt {
 	u8 opcode_len;
 	u8 b;
 	u8 intercept;
-	u8 lock_prefix;
-	u8 rep_prefix;
 	u8 op_bytes;
 	u8 ad_bytes;
-	u8 rex_prefix;
 	struct operand src;
 	struct operand src2;
 	struct operand dst;
-	bool has_seg_override;
-	u8 seg_override;
-	u64 d;
 	int (*execute)(struct x86_emulate_ctxt *ctxt);
 	int (*check_perm)(struct x86_emulate_ctxt *ctxt);
+	/*
+	 * The following six fields are cleared together,
+	 * the rest are initialized unconditionally in x86_decode_insn
+	 * or elsewhere
+	 */
+	bool rip_relative;
+	u8 rex_prefix;
+	u8 lock_prefix;
+	u8 rep_prefix;
+	/* bitmaps of registers in _regs[] that can be read */
+	u32 regs_valid;
+	/* bitmaps of registers in _regs[] that have been written */
+	u32 regs_dirty;
 	/* modrm */
 	u8 modrm;
 	u8 modrm_mod;
 	u8 modrm_reg;
 	u8 modrm_rm;
 	u8 modrm_seg;
-	bool rip_relative;
+	u8 seg_override;
+	u64 d;
 	unsigned long _eip;
 	struct operand memop;
-	u32 regs_valid;  /* bitmaps of registers in _regs[] that can be read */
-	u32 regs_dirty;  /* bitmaps of registers in _regs[] that have been written */
 	/* Fields above regs are cleared together. */
 	unsigned long _regs[NR_VCPU_REGS];
 	struct operand *memopp;
@@ -407,6 +415,7 @@ bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
 #define EMULATION_OK 0
 #define EMULATION_RESTART 1
 #define EMULATION_INTERCEPTED 2
+void init_decode_cache(struct x86_emulate_ctxt *ctxt);
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt);
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 			 u16 tss_selector, int idt_index, int reason,
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 49314155b66..572460175ba 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -95,7 +95,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 80
 #define KVM_NR_FIXED_MTRR_REGION 88
-#define KVM_NR_VAR_MTRR 8
+#define KVM_NR_VAR_MTRR 10
 
 #define ASYNC_PF_PER_VCPU 64
 
@@ -152,14 +152,16 @@ enum {
 
 #define DR6_BD		(1 << 13)
 #define DR6_BS		(1 << 14)
-#define DR6_FIXED_1	0xffff0ff0
-#define DR6_VOLATILE	0x0000e00f
+#define DR6_RTM		(1 << 16)
+#define DR6_FIXED_1	0xfffe0ff0
+#define DR6_INIT	0xffff0ff0
+#define DR6_VOLATILE	0x0001e00f
 
 #define DR7_BP_EN_MASK	0x000000ff
 #define DR7_GE		(1 << 9)
 #define DR7_GD		(1 << 13)
 #define DR7_FIXED_1	0x00000400
-#define DR7_VOLATILE	0xffff23ff
+#define DR7_VOLATILE	0xffff2bff
 
 /* apic attention bits */
 #define KVM_APIC_CHECK_VAPIC	0
@@ -448,7 +450,7 @@ struct kvm_vcpu_arch {
 	u64 tsc_offset_adjustment;
 	u64 this_tsc_nsec;
 	u64 this_tsc_write;
-	u8  this_tsc_generation;
+	u64 this_tsc_generation;
 	bool tsc_catchup;
 	bool tsc_always_catchup;
 	s8 virtual_tsc_shift;
@@ -461,7 +463,7 @@ struct kvm_vcpu_arch {
 	bool nmi_injected;    /* Trying to inject an NMI this entry */
 
 	struct mtrr_state_type mtrr_state;
-	u32 pat;
+	u64 pat;
 
 	unsigned switch_db_regs;
 	unsigned long db[KVM_NR_DB_REGS];
@@ -591,7 +593,7 @@ struct kvm_arch {
 	u64 cur_tsc_nsec;
 	u64 cur_tsc_write;
 	u64 cur_tsc_offset;
-	u8  cur_tsc_generation;
+	u64 cur_tsc_generation;
 	int nr_vcpus_matched_tsc;
 
 	spinlock_t pvclock_gtod_sync_lock;
@@ -717,7 +719,7 @@ struct kvm_x86_ops {
 	int (*handle_exit)(struct kvm_vcpu *vcpu);
 	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
 	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
-	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
+	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
 	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
 				unsigned char *hypercall_addr);
 	void (*set_irq)(struct kvm_vcpu *vcpu);
@@ -1070,6 +1072,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu);
 bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr);
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc);
 int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
 void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
 void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index a55c7efcc4e..0f555cc3198 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -13,7 +13,7 @@
 #define RTC_ALWAYS_BCD	1	/* RTC operates in binary mode */
 #endif
 
-#if defined(CONFIG_X86_32) && defined(__HAVE_ARCH_CMPXCHG)
+#if defined(CONFIG_X86_32)
 /*
  * This lock provides nmi access to the CMOS/RTC registers.  It has some
  * special properties.  It is owned by a CPU and stores the index register
diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h
index 0208c3c2cbc..85e6cda45a0 100644
--- a/arch/x86/include/asm/mutex_32.h
+++ b/arch/x86/include/asm/mutex_32.h
@@ -100,23 +100,11 @@ do {								\
 static inline int __mutex_fastpath_trylock(atomic_t *count,
 					   int (*fail_fn)(atomic_t *))
 {
-	/*
-	 * We have two variants here. The cmpxchg based one is the best one
-	 * because it never induce a false contention state.  It is included
-	 * here because architectures using the inc/dec algorithms over the
-	 * xchg ones are much more likely to support cmpxchg natively.
-	 *
-	 * If not we fall back to the spinlock based variant - that is
-	 * just as efficient (and simpler) as a 'destructive' probing of
-	 * the mutex state would be.
-	 */
-#ifdef __HAVE_ARCH_CMPXCHG
+	/* cmpxchg because it never induces a false contention state. */
 	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
 		return 1;
+
 	return 0;
-#else
-	return fail_fn(count);
-#endif
 }
 
 #endif /* _ASM_X86_MUTEX_32_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 1da25a5f96f..a1410db38a1 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -43,7 +43,7 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 {
 	if (!current_set_polling_and_test()) {
-		if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) {
+		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
 			mb();
 			clflush((void *)&current_thread_info()->flags);
 			mb();
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 851bcdc5db0..fd472181a1d 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -52,10 +52,9 @@
  * Compared to the generic __my_cpu_offset version, the following
  * saves one instruction and avoids clobbering a temp register.
  */
-#define raw_cpu_ptr(ptr)				\
+#define arch_raw_cpu_ptr(ptr)				\
 ({							\
 	unsigned long tcp_ptr__;			\
-	__verify_pcpu_ptr(ptr);				\
 	asm volatile("add " __percpu_arg(1) ", %0"	\
 		     : "=r" (tcp_ptr__)			\
 		     : "m" (this_cpu_off), "0" (ptr));	\
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 43d61daea96..ee30b9f0b91 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -695,6 +695,8 @@ static inline void cpu_relax(void)
 	rep_nop();
 }
 
+#define cpu_relax_lowlatency() cpu_relax()
+
 /* Stop speculative execution and prefetching of modified code. */
 static inline void sync_core(void)
 {
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 14fd6fd75a1..6205f0c434d 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -231,6 +231,22 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 
 #define ARCH_HAS_USER_SINGLE_STEP_INFO
 
+/*
+ * When hitting ptrace_stop(), we cannot return using SYSRET because
+ * that does not restore the full CPU state, only a minimal set.  The
+ * ptracer can change arbitrary register values, which is usually okay
+ * because the usual ptrace stops run off the signal delivery path which
+ * forces IRET; however, ptrace_event() stops happen in arbitrary places
+ * in the kernel and don't force IRET path.
+ *
+ * So force IRET path after a ptrace stop.
+ */
+#define arch_ptrace_stop_needed(code, info)				\
+({									\
+	set_thread_flag(TIF_NOTIFY_RESUME);				\
+	false;								\
+})
+
 struct user_desc;
 extern int do_get_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info);
diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h
new file mode 100644
index 00000000000..ae0e241e228
--- /dev/null
+++ b/arch/x86/include/asm/qrwlock.h
@@ -0,0 +1,17 @@
+#ifndef _ASM_X86_QRWLOCK_H
+#define _ASM_X86_QRWLOCK_H
+
+#include <asm-generic/qrwlock_types.h>
+
+#ifndef CONFIG_X86_PPRO_FENCE
+#define queue_write_unlock queue_write_unlock
+static inline void queue_write_unlock(struct qrwlock *lock)
+{
+        barrier();
+        ACCESS_ONCE(*(u8 *)&lock->cnts) = 0;
+}
+#endif
+
+#include <asm-generic/qrwlock.h>
+
+#endif /* _ASM_X86_QRWLOCK_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 0f62f5482d9..54f1c8068c0 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -187,6 +187,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 		cpu_relax();
 }
 
+#ifndef CONFIG_QUEUE_RWLOCK
 /*
  * Read-write spinlocks, allowing multiple readers
  * but only one writer.
@@ -269,6 +270,9 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 	asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0"
 		     : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory");
 }
+#else
+#include <asm/qrwlock.h>
+#endif /* CONFIG_QUEUE_RWLOCK */
 
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 4f1bea19945..73c4c007200 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -34,6 +34,10 @@ typedef struct arch_spinlock {
 
 #define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
 
+#ifdef CONFIG_QUEUE_RWLOCK
+#include <asm-generic/qrwlock_types.h>
+#else
 #include <asm/rwlock.h>
+#endif
 
 #endif /* _ASM_X86_SPINLOCK_TYPES_H */
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 8ba18842c48..bc8352e7010 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -68,7 +68,7 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long);
 dotraplinkage void do_stack_segment(struct pt_regs *, long);
 #ifdef CONFIG_X86_64
 dotraplinkage void do_double_fault(struct pt_regs *, long);
-asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *);
+asmlinkage struct pt_regs *sync_regs(struct pt_regs *);
 #endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
@@ -103,7 +103,6 @@ static inline int get_si_code(unsigned long condition)
 
 extern int panic_on_unrecovered_nmi;
 
-void math_error(struct pt_regs *, int, int);
 void math_emulate(struct math_emu_info *);
 #ifndef CONFIG_X86_32
 asmlinkage void smp_thermal_interrupt(void);
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 93bee7b9385..74f4c2ff642 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -41,18 +41,18 @@ struct arch_uprobe {
 		u8			ixol[MAX_UINSN_BYTES];
 	};
 
-	u16				fixups;
 	const struct uprobe_xol_ops	*ops;
 
 	union {
-#ifdef CONFIG_X86_64
-		unsigned long			rip_rela_target_address;
-#endif
 		struct {
 			s32	offs;
 			u8	ilen;
 			u8	opc1;
-		}				branch;
+		}			branch;
+		struct {
+			u8	fixups;
+			u8	ilen;
+		} 			defparam;
 	};
 };
 
diff --git a/arch/x86/include/asm/vga.h b/arch/x86/include/asm/vga.h
index 44282fbf7bf..c4b9dc2f67c 100644
--- a/arch/x86/include/asm/vga.h
+++ b/arch/x86/include/asm/vga.h
@@ -17,10 +17,4 @@
 #define vga_readb(x) (*(x))
 #define vga_writeb(x, y) (*(y) = (x))
 
-#ifdef CONFIG_FB_EFI
-#define __ARCH_HAS_VGA_DEFAULT_DEVICE
-extern struct pci_dev *vga_default_device(void);
-extern void vga_set_default_device(struct pci_dev *pdev);
-#endif
-
 #endif /* _ASM_X86_VGA_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 7004d21e621..bcbfade26d8 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -51,6 +51,9 @@
 #define CPU_BASED_MONITOR_EXITING               0x20000000
 #define CPU_BASED_PAUSE_EXITING                 0x40000000
 #define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS   0x80000000
+
+#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x0401e172
+
 /*
  * Definitions of Secondary Processor-Based VM-Execution Controls.
  */
@@ -76,7 +79,7 @@
 
 #define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR	0x00000016
 
-#define VM_EXIT_SAVE_DEBUG_CONTROLS             0x00000002
+#define VM_EXIT_SAVE_DEBUG_CONTROLS             0x00000004
 #define VM_EXIT_HOST_ADDR_SPACE_SIZE            0x00000200
 #define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL      0x00001000
 #define VM_EXIT_ACK_INTR_ON_EXIT                0x00008000
@@ -89,7 +92,7 @@
 
 #define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR	0x00036dff
 
-#define VM_ENTRY_LOAD_DEBUG_CONTROLS            0x00000002
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS            0x00000004
 #define VM_ENTRY_IA32E_MODE                     0x00000200
 #define VM_ENTRY_SMM                            0x00000400
 #define VM_ENTRY_DEACT_DUAL_MONITOR             0x00000800
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index 09409c44f9a..3dec769cadf 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -22,6 +22,7 @@ header-y += ipcbuf.h
 header-y += ist.h
 header-y += kvm.h
 header-y += kvm_para.h
+header-y += kvm_perf.h
 header-y += ldt.h
 header-y += mce.h
 header-y += mman.h
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index d3a87780c70..d7dcef58aef 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -23,7 +23,10 @@
 #define GP_VECTOR 13
 #define PF_VECTOR 14
 #define MF_VECTOR 16
+#define AC_VECTOR 17
 #define MC_VECTOR 18
+#define XM_VECTOR 19
+#define VE_VECTOR 20
 
 /* Select x86 specific features in <linux/kvm.h> */
 #define __KVM_HAVE_PIT
diff --git a/arch/x86/include/uapi/asm/kvm_perf.h b/arch/x86/include/uapi/asm/kvm_perf.h
new file mode 100644
index 00000000000..3bb964f88aa
--- /dev/null
+++ b/arch/x86/include/uapi/asm/kvm_perf.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_KVM_PERF_H
+#define _ASM_X86_KVM_PERF_H
+
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
+
+#define DECODE_STR_LEN 20
+
+#define VCPU_ID "vcpu_id"
+
+#define KVM_ENTRY_TRACE "kvm:kvm_entry"
+#define KVM_EXIT_TRACE "kvm:kvm_exit"
+#define KVM_EXIT_REASON "exit_reason"
+
+#endif /* _ASM_X86_KVM_PERF_H */
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index fcf2b3ae1bf..eac9e92fe18 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -297,6 +297,8 @@
 #define MSR_IA32_TSC_ADJUST             0x0000003b
 #define MSR_IA32_BNDCFGS		0x00000d90
 
+#define MSR_IA32_XSS			0x00000da0
+
 #define FEATURE_CONTROL_LOCKED				(1<<0)
 #define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX	(1<<1)
 #define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX	(1<<2)
@@ -558,6 +560,7 @@
 
 /* VMX_BASIC bits and bitmasks */
 #define VMX_BASIC_VMCS_SIZE_SHIFT	32
+#define VMX_BASIC_TRUE_CTLS		(1ULL << 55)
 #define VMX_BASIC_64		0x0001000000000000LLU
 #define VMX_BASIC_MEM_TYPE_SHIFT	50
 #define VMX_BASIC_MEM_TYPE_MASK	0x003c000000000000LLU
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 491ef3e5985..047f9ff2e36 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
 obj-$(CONFIG_X86_32)	+= i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
+obj-$(CONFIG_X86_64)	+= mcount_64.o
 obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 86281ffb96d..a531f6564ed 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -74,10 +74,6 @@ int acpi_fix_pin2_polarity __initdata;
 static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 #endif
 
-#ifndef __HAVE_ARCH_CMPXCHG
-#warning ACPI uses CMPXCHG, i486 and later hardware
-#endif
-
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
    -------------------------------------------------------------------------- */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index df94598ad05..703130f469e 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -5,7 +5,6 @@
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/stringify.h>
-#include <linux/kprobes.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
@@ -551,7 +550,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
  *
  * Note: Must be called under text_mutex.
  */
-void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
+void *text_poke(void *addr, const void *opcode, size_t len)
 {
 	unsigned long flags;
 	char *vaddr;
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index eab67047dec..6a1e71bde32 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -33,34 +33,44 @@ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
 /* "in progress" flag of arch_trigger_all_cpu_backtrace */
 static unsigned long backtrace_flag;
 
-void arch_trigger_all_cpu_backtrace(void)
+void arch_trigger_all_cpu_backtrace(bool include_self)
 {
 	int i;
+	int cpu = get_cpu();
 
-	if (test_and_set_bit(0, &backtrace_flag))
+	if (test_and_set_bit(0, &backtrace_flag)) {
 		/*
 		 * If there is already a trigger_all_cpu_backtrace() in progress
 		 * (backtrace_flag == 1), don't output double cpu dump infos.
 		 */
+		put_cpu();
 		return;
+	}
 
 	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
+	if (!include_self)
+		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 
-	printk(KERN_INFO "sending NMI to all CPUs:\n");
-	apic->send_IPI_all(NMI_VECTOR);
+	if (!cpumask_empty(to_cpumask(backtrace_mask))) {
+		pr_info("sending NMI to %s CPUs:\n",
+			(include_self ? "all" : "other"));
+		apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR);
+	}
 
 	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
 	for (i = 0; i < 10 * 1000; i++) {
 		if (cpumask_empty(to_cpumask(backtrace_mask)))
 			break;
 		mdelay(1);
+		touch_softlockup_watchdog();
 	}
 
 	clear_bit(0, &backtrace_flag);
 	smp_mb__after_atomic();
+	put_cpu();
 }
 
-static int __kprobes
+static int
 arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
 {
 	int cpu;
@@ -80,6 +90,7 @@ arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
 
 	return NMI_DONE;
 }
+NOKPROBE_SYMBOL(arch_trigger_all_cpu_backtrace_handler);
 
 static int __init register_trigger_all_cpu_backtrace(void)
 {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 9d0a9795a0f..81e08eff05e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2297,7 +2297,7 @@ int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	int err;
 
 	if (!config_enabled(CONFIG_SMP))
-		return -1;
+		return -EPERM;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
 		return -EINVAL;
@@ -2328,7 +2328,7 @@ int native_ioapic_set_affinity(struct irq_data *data,
 	int ret;
 
 	if (!config_enabled(CONFIG_SMP))
-		return -1;
+		return -EPERM;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	ret = __ioapic_set_affinity(data, mask, &dest);
@@ -3001,9 +3001,11 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 	struct irq_cfg *cfg = data->chip_data;
 	struct msi_msg msg;
 	unsigned int dest;
+	int ret;
 
-	if (__ioapic_set_affinity(data, mask, &dest))
-		return -1;
+	ret = __ioapic_set_affinity(data, mask, &dest);
+	if (ret)
+		return ret;
 
 	__get_cached_msi_msg(data->msi_desc, &msg);
 
@@ -3100,9 +3102,11 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	struct irq_cfg *cfg = data->chip_data;
 	unsigned int dest, irq = data->irq;
 	struct msi_msg msg;
+	int ret;
 
-	if (__ioapic_set_affinity(data, mask, &dest))
-		return -1;
+	ret = __ioapic_set_affinity(data, mask, &dest);
+	if (ret)
+		return ret;
 
 	dmar_msi_read(irq, &msg);
 
@@ -3149,9 +3153,11 @@ static int hpet_msi_set_affinity(struct irq_data *data,
 	struct irq_cfg *cfg = data->chip_data;
 	struct msi_msg msg;
 	unsigned int dest;
+	int ret;
 
-	if (__ioapic_set_affinity(data, mask, &dest))
-		return -1;
+	ret = __ioapic_set_affinity(data, mask, &dest);
+	if (ret)
+		return ret;
 
 	hpet_msi_read(data->handler_data, &msg);
 
@@ -3218,9 +3224,11 @@ ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
 	struct irq_cfg *cfg = data->chip_data;
 	unsigned int dest;
+	int ret;
 
-	if (__ioapic_set_affinity(data, mask, &dest))
-		return -1;
+	ret = __ioapic_set_affinity(data, mask, &dest);
+	if (ret)
+		return ret;
 
 	target_ht_irq(data->irq, dest, cfg->vector);
 	return IRQ_SET_MASK_OK_NOCOPY;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index f3a1f04ed4c..58487445141 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -841,7 +841,6 @@ static int apm_do_idle(void)
 	u32 eax;
 	u8 ret = 0;
 	int idled = 0;
-	int polling;
 	int err = 0;
 
 	if (!need_resched()) {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a1a53d09498..60e5497681f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -8,6 +8,7 @@
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cpu.h>
+#include <asm/smp.h>
 #include <asm/pci-direct.h>
 
 #ifdef CONFIG_X86_64
@@ -50,7 +51,6 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
 	return wrmsr_safe_regs(gprs);
 }
 
-#ifdef CONFIG_X86_32
 /*
  *	B step AMD K6 before B 9730xxxx have hardware bugs that can cause
  *	misexecution of code under Linux. Owners of such processors should
@@ -70,6 +70,7 @@ __asm__(".globl vide\n\t.align 4\nvide: ret");
 
 static void init_amd_k5(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_32
 /*
  * General Systems BIOSen alias the cpu frequency registers
  * of the Elan at 0x000df000. Unfortuantly, one of the Linux
@@ -83,11 +84,12 @@ static void init_amd_k5(struct cpuinfo_x86 *c)
 		if (inl(CBAR) & CBAR_ENB)
 			outl(0 | CBAR_KEY, CBAR);
 	}
+#endif
 }
 
-
 static void init_amd_k6(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_32
 	u32 l, h;
 	int mbytes = get_num_physpages() >> (20-PAGE_SHIFT);
 
@@ -176,10 +178,44 @@ static void init_amd_k6(struct cpuinfo_x86 *c)
 		/* placeholder for any needed mods */
 		return;
 	}
+#endif
 }
 
-static void amd_k7_smp_check(struct cpuinfo_x86 *c)
+static void init_amd_k7(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_32
+	u32 l, h;
+
+	/*
+	 * Bit 15 of Athlon specific MSR 15, needs to be 0
+	 * to enable SSE on Palomino/Morgan/Barton CPU's.
+	 * If the BIOS didn't enable it already, enable it here.
+	 */
+	if (c->x86_model >= 6 && c->x86_model <= 10) {
+		if (!cpu_has(c, X86_FEATURE_XMM)) {
+			printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
+			msr_clear_bit(MSR_K7_HWCR, 15);
+			set_cpu_cap(c, X86_FEATURE_XMM);
+		}
+	}
+
+	/*
+	 * It's been determined by AMD that Athlons since model 8 stepping 1
+	 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
+	 * As per AMD technical note 27212 0.2
+	 */
+	if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
+		rdmsr(MSR_K7_CLK_CTL, l, h);
+		if ((l & 0xfff00000) != 0x20000000) {
+			printk(KERN_INFO
+			    "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n",
+					l, ((l & 0x000fffff)|0x20000000));
+			wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
+		}
+	}
+
+	set_cpu_cap(c, X86_FEATURE_K7);
+
 	/* calling is from identify_secondary_cpu() ? */
 	if (!c->cpu_index)
 		return;
@@ -207,7 +243,7 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c)
 	if (((c->x86_model == 6) && (c->x86_mask >= 2)) ||
 	    ((c->x86_model == 7) && (c->x86_mask >= 1)) ||
 	     (c->x86_model > 7))
-		if (cpu_has_mp)
+		if (cpu_has(c, X86_FEATURE_MP))
 			return;
 
 	/* If we get here, not a certified SMP capable AMD system. */
@@ -219,45 +255,8 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c)
 	WARN_ONCE(1, "WARNING: This combination of AMD"
 		" processors is not suitable for SMP.\n");
 	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
-}
-
-static void init_amd_k7(struct cpuinfo_x86 *c)
-{
-	u32 l, h;
-
-	/*
-	 * Bit 15 of Athlon specific MSR 15, needs to be 0
-	 * to enable SSE on Palomino/Morgan/Barton CPU's.
-	 * If the BIOS didn't enable it already, enable it here.
-	 */
-	if (c->x86_model >= 6 && c->x86_model <= 10) {
-		if (!cpu_has(c, X86_FEATURE_XMM)) {
-			printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
-			msr_clear_bit(MSR_K7_HWCR, 15);
-			set_cpu_cap(c, X86_FEATURE_XMM);
-		}
-	}
-
-	/*
-	 * It's been determined by AMD that Athlons since model 8 stepping 1
-	 * are more robust with CLK_CTL set to 200xxxxx instead of 600xxxxx
-	 * As per AMD technical note 27212 0.2
-	 */
-	if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) {
-		rdmsr(MSR_K7_CLK_CTL, l, h);
-		if ((l & 0xfff00000) != 0x20000000) {
-			printk(KERN_INFO
-			    "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n",
-					l, ((l & 0x000fffff)|0x20000000));
-			wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h);
-		}
-	}
-
-	set_cpu_cap(c, X86_FEATURE_K7);
-
-	amd_k7_smp_check(c);
-}
 #endif
+}
 
 #ifdef CONFIG_NUMA
 /*
@@ -446,6 +445,26 @@ static void early_init_amd_mc(struct cpuinfo_x86 *c)
 
 static void bsp_init_amd(struct cpuinfo_x86 *c)
 {
+
+#ifdef CONFIG_X86_64
+	if (c->x86 >= 0xf) {
+		unsigned long long tseg;
+
+		/*
+		 * Split up direct mapping around the TSEG SMM area.
+		 * Don't do it for gbpages because there seems very little
+		 * benefit in doing so.
+		 */
+		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+			unsigned long pfn = tseg >> PAGE_SHIFT;
+
+			printk(KERN_DEBUG "tseg: %010llx\n", tseg);
+			if (pfn_range_is_mapped(pfn, pfn + 1))
+				set_memory_4k((unsigned long)__va(tseg), 1);
+		}
+	}
+#endif
+
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
 
 		if (c->x86 > 0x10 ||
@@ -515,101 +534,74 @@ static const int amd_erratum_383[];
 static const int amd_erratum_400[];
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
 
-static void init_amd(struct cpuinfo_x86 *c)
+static void init_amd_k8(struct cpuinfo_x86 *c)
 {
-	u32 dummy;
-	unsigned long long value;
-
-#ifdef CONFIG_SMP
-	/*
-	 * Disable TLB flush filter by setting HWCR.FFDIS on K8
-	 * bit 6 of msr C001_0015
-	 *
-	 * Errata 63 for SH-B3 steppings
-	 * Errata 122 for all steppings (F+ have it disabled by default)
-	 */
-	if (c->x86 == 0xf)
-		msr_set_bit(MSR_K7_HWCR, 6);
-#endif
+	u32 level;
+	u64 value;
 
-	early_init_amd(c);
+	/* On C+ stepping K8 rep microcode works well for copy/memset */
+	level = cpuid_eax(1);
+	if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 
 	/*
-	 * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
-	 * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
+	 * Some BIOSes incorrectly force this feature, but only K8 revision D
+	 * (model = 0x14) and later actually support it.
+	 * (AMD Erratum #110, docId: 25759).
 	 */
-	clear_cpu_cap(c, 0*32+31);
-
-#ifdef CONFIG_X86_64
-	/* On C+ stepping K8 rep microcode works well for copy/memset */
-	if (c->x86 == 0xf) {
-		u32 level;
-
-		level = cpuid_eax(1);
-		if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)
-			set_cpu_cap(c, X86_FEATURE_REP_GOOD);
-
-		/*
-		 * Some BIOSes incorrectly force this feature, but only K8
-		 * revision D (model = 0x14) and later actually support it.
-		 * (AMD Erratum #110, docId: 25759).
-		 */
-		if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
-			clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
-			if (!rdmsrl_amd_safe(0xc001100d, &value)) {
-				value &= ~(1ULL << 32);
-				wrmsrl_amd_safe(0xc001100d, value);
-			}
+	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
+		clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
+		if (!rdmsrl_amd_safe(0xc001100d, &value)) {
+			value &= ~BIT_64(32);
+			wrmsrl_amd_safe(0xc001100d, value);
 		}
-
 	}
-	if (c->x86 >= 0x10)
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 
-	/* get apicid instead of initial apic id from cpuid */
-	c->apicid = hard_smp_processor_id();
-#else
+	if (!c->x86_model_id[0])
+		strcpy(c->x86_model_id, "Hammer");
+}
+
+static void init_amd_gh(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
+	/* do this for boot cpu */
+	if (c == &boot_cpu_data)
+		check_enable_amd_mmconf_dmi();
+
+	fam10h_check_enable_mmcfg();
+#endif
 
 	/*
-	 *	FIXME: We should handle the K5 here. Set up the write
-	 *	range and also turn on MSR 83 bits 4 and 31 (write alloc,
-	 *	no bus pipeline)
+	 * Disable GART TLB Walk Errors on Fam10h. We do this here because this
+	 * is always needed when GART is enabled, even in a kernel which has no
+	 * MCE support built in. BIOS should disable GartTlbWlk Errors already.
+	 * If it doesn't, we do it here as suggested by the BKDG.
+	 *
+	 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
 	 */
+	msr_set_bit(MSR_AMD64_MCx_MASK(4), 10);
 
-	switch (c->x86) {
-	case 4:
-		init_amd_k5(c);
-		break;
-	case 5:
-		init_amd_k6(c);
-		break;
-	case 6: /* An Athlon/Duron */
-		init_amd_k7(c);
-		break;
-	}
+	/*
+	 * On family 10h BIOS may not have properly enabled WC+ support, causing
+	 * it to be converted to CD memtype. This may result in performance
+	 * degradation for certain nested-paging guests. Prevent this conversion
+	 * by clearing bit 24 in MSR_AMD64_BU_CFG2.
+	 *
+	 * NOTE: we want to use the _safe accessors so as not to #GP kvm
+	 * guests on older kvm hosts.
+	 */
+	msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
 
-	/* K6s reports MCEs but don't actually have all the MSRs */
-	if (c->x86 < 6)
-		clear_cpu_cap(c, X86_FEATURE_MCE);
-#endif
+	if (cpu_has_amd_erratum(c, amd_erratum_383))
+		set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
+}
 
-	/* Enable workaround for FXSAVE leak */
-	if (c->x86 >= 6)
-		set_cpu_cap(c, X86_FEATURE_FXSAVE_LEAK);
-
-	if (!c->x86_model_id[0]) {
-		switch (c->x86) {
-		case 0xf:
-			/* Should distinguish Models here, but this is only
-			   a fallback anyways. */
-			strcpy(c->x86_model_id, "Hammer");
-			break;
-		}
-	}
+static void init_amd_bd(struct cpuinfo_x86 *c)
+{
+	u64 value;
 
 	/* re-enable TopologyExtensions if switched off by BIOS */
-	if ((c->x86 == 0x15) &&
-	    (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+	if ((c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
 	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
 
 		if (msr_set_bit(0xc0011005, 54) > 0) {
@@ -625,14 +617,60 @@ static void init_amd(struct cpuinfo_x86 *c)
 	 * The way access filter has a performance penalty on some workloads.
 	 * Disable it on the affected CPUs.
 	 */
-	if ((c->x86 == 0x15) &&
-	    (c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
-
+	if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
 		if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) {
 			value |= 0x1E;
 			wrmsrl_safe(0xc0011021, value);
 		}
 	}
+}
+
+static void init_amd(struct cpuinfo_x86 *c)
+{
+	u32 dummy;
+
+#ifdef CONFIG_SMP
+	/*
+	 * Disable TLB flush filter by setting HWCR.FFDIS on K8
+	 * bit 6 of msr C001_0015
+	 *
+	 * Errata 63 for SH-B3 steppings
+	 * Errata 122 for all steppings (F+ have it disabled by default)
+	 */
+	if (c->x86 == 0xf)
+		msr_set_bit(MSR_K7_HWCR, 6);
+#endif
+
+	early_init_amd(c);
+
+	/*
+	 * Bit 31 in normal CPUID used for nonstandard 3DNow ID;
+	 * 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway
+	 */
+	clear_cpu_cap(c, 0*32+31);
+
+	if (c->x86 >= 0x10)
+		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+	/* get apicid instead of initial apic id from cpuid */
+	c->apicid = hard_smp_processor_id();
+
+	/* K6s reports MCEs but don't actually have all the MSRs */
+	if (c->x86 < 6)
+		clear_cpu_cap(c, X86_FEATURE_MCE);
+
+	switch (c->x86) {
+	case 4:    init_amd_k5(c); break;
+	case 5:    init_amd_k6(c); break;
+	case 6:	   init_amd_k7(c); break;
+	case 0xf:  init_amd_k8(c); break;
+	case 0x10: init_amd_gh(c); break;
+	case 0x15: init_amd_bd(c); break;
+	}
+
+	/* Enable workaround for FXSAVE leak */
+	if (c->x86 >= 6)
+		set_cpu_bug(c, X86_BUG_FXSAVE_LEAK);
 
 	cpu_detect_cache_sizes(c);
 
@@ -656,33 +694,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
 	}
 
-#ifdef CONFIG_X86_64
-	if (c->x86 == 0x10) {
-		/* do this for boot cpu */
-		if (c == &boot_cpu_data)
-			check_enable_amd_mmconf_dmi();
-
-		fam10h_check_enable_mmcfg();
-	}
-
-	if (c == &boot_cpu_data && c->x86 >= 0xf) {
-		unsigned long long tseg;
-
-		/*
-		 * Split up direct mapping around the TSEG SMM area.
-		 * Don't do it for gbpages because there seems very little
-		 * benefit in doing so.
-		 */
-		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
-			unsigned long pfn = tseg >> PAGE_SHIFT;
-
-			printk(KERN_DEBUG "tseg: %010llx\n", tseg);
-			if (pfn_range_is_mapped(pfn, pfn + 1))
-				set_memory_4k((unsigned long)__va(tseg), 1);
-		}
-	}
-#endif
-
 	/*
 	 * Family 0x12 and above processors have APIC timer
 	 * running in deep C states.
@@ -690,34 +701,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 > 0x11)
 		set_cpu_cap(c, X86_FEATURE_ARAT);
 
-	if (c->x86 == 0x10) {
-		/*
-		 * Disable GART TLB Walk Errors on Fam10h. We do this here
-		 * because this is always needed when GART is enabled, even in a
-		 * kernel which has no MCE support built in.
-		 * BIOS should disable GartTlbWlk Errors already. If
-		 * it doesn't, do it here as suggested by the BKDG.
-		 *
-		 * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
-		 */
-		msr_set_bit(MSR_AMD64_MCx_MASK(4), 10);
-
-		/*
-		 * On family 10h BIOS may not have properly enabled WC+ support,
-		 * causing it to be converted to CD memtype. This may result in
-		 * performance degradation for certain nested-paging guests.
-		 * Prevent this conversion by clearing bit 24 in
-		 * MSR_AMD64_BU_CFG2.
-		 *
-		 * NOTE: we want to use the _safe accessors so as not to #GP kvm
-		 * guests on older kvm hosts.
-		 */
-		msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
-
-		if (cpu_has_amd_erratum(c, amd_erratum_383))
-			set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
-	}
-
 	if (cpu_has_amd_erratum(c, amd_erratum_400))
 		set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2c178208512..333fd520933 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -8,6 +8,7 @@
 #include <linux/delay.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/kprobes.h>
 #include <linux/kgdb.h>
 #include <linux/smp.h>
 #include <linux/io.h>
@@ -624,6 +625,15 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[9] = ebx;
 	}
 
+	/* Extended state features: level 0x0000000d */
+	if (c->cpuid_level >= 0x0000000d) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx);
+
+		c->x86_capability[10] = eax;
+	}
+
 	/* AMD-defined flags: level 0x80000001 */
 	xlvl = cpuid_eax(0x80000000);
 	c->extended_cpuid_level = xlvl;
@@ -1184,6 +1194,7 @@ int is_debug_stack(unsigned long addr)
 		(addr <= __get_cpu_var(debug_stack_addr) &&
 		 addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
 }
+NOKPROBE_SYMBOL(is_debug_stack);
 
 DEFINE_PER_CPU(u32, debug_idt_ctr);
 
@@ -1192,6 +1203,7 @@ void debug_stack_set_zero(void)
 	this_cpu_inc(debug_idt_ctr);
 	load_current_idt();
 }
+NOKPROBE_SYMBOL(debug_stack_set_zero);
 
 void debug_stack_reset(void)
 {
@@ -1200,6 +1212,7 @@ void debug_stack_reset(void)
 	if (this_cpu_dec_return(debug_idt_ctr) == 0)
 		load_current_idt();
 }
+NOKPROBE_SYMBOL(debug_stack_reset);
 
 #else	/* CONFIG_X86_64 */
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index cd61755de49..74e804ddc5c 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -253,7 +253,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 */
 	if (cpu_has_apic && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
 	    (c->x86_mask < 0x6 || c->x86_mask == 0xb))
-		set_cpu_cap(c, X86_FEATURE_11AP);
+		set_cpu_bug(c, X86_BUG_11AP);
 
 
 #ifdef CONFIG_X86_INTEL_USERCOPY
@@ -370,6 +370,17 @@ static void init_intel(struct cpuinfo_x86 *c)
 	 */
 	detect_extended_topology(c);
 
+	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
+		/*
+		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
+		 * detection.
+		 */
+		c->x86_max_cores = intel_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+		detect_ht(c);
+#endif
+	}
+
 	l2 = init_intel_cacheinfo(c);
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
@@ -391,7 +402,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 
 	if (c->x86 == 6 && cpu_has_clflush &&
 	    (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
-		set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
+		set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
 
 #ifdef CONFIG_X86_64
 	if (c->x86 == 15)
@@ -438,17 +449,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_P3);
 #endif
 
-	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
-		/*
-		 * let's use the legacy cpuid vector 0x1 and 0x4 for topology
-		 * detection.
-		 */
-		c->x86_max_cores = intel_num_cpu_cores(c);
-#ifdef CONFIG_X86_32
-		detect_ht(c);
-#endif
-	}
-
 	/* Work around errata */
 	srat_detect_node(c);
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index a952e9c85b6..9c8f7394c61 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -730,6 +730,18 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
 #endif
 	}
 
+#ifdef CONFIG_X86_HT
+	/*
+	 * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
+	 * turns means that the only possibility is SMT (as indicated in
+	 * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
+	 * that SMT shares all caches, we can unconditionally set cpu_llc_id to
+	 * c->phys_proc_id.
+	 */
+	if (per_cpu(cpu_llc_id, cpu) == BAD_APICID)
+		per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+#endif
+
 	c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
 
 	return l2;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index bb92f38153b..9a79c8dbd8e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2451,6 +2451,12 @@ static __init int mcheck_init_device(void)
 	for_each_online_cpu(i) {
 		err = mce_device_create(i);
 		if (err) {
+			/*
+			 * Register notifier anyway (and do not unreg it) so
+			 * that we don't leave undeleted timers, see notifier
+			 * callback above.
+			 */
+			__register_hotcpu_notifier(&mce_cpu_notifier);
 			cpu_notifier_register_done();
 			goto err_device_create;
 		}
@@ -2471,10 +2477,6 @@ static __init int mcheck_init_device(void)
 err_register:
 	unregister_syscore_ops(&mce_syscore_ops);
 
-	cpu_notifier_register_begin();
-	__unregister_hotcpu_notifier(&mce_cpu_notifier);
-	cpu_notifier_register_done();
-
 err_device_create:
 	/*
 	 * We didn't keep track of which devices were created above, but
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index 2bf61650549..e2b22df964c 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -1,23 +1,25 @@
 #!/bin/sh
 #
-# Generate the x86_cap_flags[] array from include/asm/cpufeature.h
+# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeature.h
 #
 
 IN=$1
 OUT=$2
 
-TABS="$(printf '\t\t\t\t\t')"
-trap 'rm "$OUT"' EXIT
+function dump_array()
+{
+	ARRAY=$1
+	SIZE=$2
+	PFX=$3
+	POSTFIX=$4
 
-(
-	echo "#ifndef _ASM_X86_CPUFEATURE_H"
-	echo "#include <asm/cpufeature.h>"
-	echo "#endif"
-	echo ""
-	echo "const char * const x86_cap_flags[NCAPINTS*32] = {"
+	PFX_SZ=$(echo $PFX | wc -c)
+	TABS="$(printf '\t\t\t\t\t')"
+
+	echo "const char * const $ARRAY[$SIZE] = {"
 
-	# Iterate through any input lines starting with #define X86_FEATURE_
-	sed -n -e 's/\t/ /g' -e 's/^ *# *define *X86_FEATURE_//p' $IN |
+	# Iterate through any input lines starting with #define $PFX
+	sed -n -e 's/\t/ /g' -e "s/^ *# *define *$PFX//p" $IN |
 	while read i
 	do
 		# Name is everything up to the first whitespace
@@ -31,11 +33,32 @@ trap 'rm "$OUT"' EXIT
 		# Name is uppercase, VALUE is all lowercase
 		VALUE="$(echo "$VALUE" | tr A-Z a-z)"
 
-		TABCOUNT=$(( ( 5*8 - 14 - $(echo "$NAME" | wc -c) ) / 8 ))
-		printf "\t[%s]%.*s = %s,\n" \
-			"X86_FEATURE_$NAME" "$TABCOUNT" "$TABS" "$VALUE"
+        if [ -n "$POSTFIX" ]; then
+            T=$(( $PFX_SZ + $(echo $POSTFIX | wc -c) + 2 ))
+	        TABS="$(printf '\t\t\t\t\t\t')"
+		    TABCOUNT=$(( ( 6*8 - ($T + 1) - $(echo "$NAME" | wc -c) ) / 8 ))
+		    printf "\t[%s - %s]%.*s = %s,\n" "$PFX$NAME" "$POSTFIX" "$TABCOUNT" "$TABS" "$VALUE"
+        else
+		    TABCOUNT=$(( ( 5*8 - ($PFX_SZ + 1) - $(echo "$NAME" | wc -c) ) / 8 ))
+            printf "\t[%s]%.*s = %s,\n" "$PFX$NAME" "$TABCOUNT" "$TABS" "$VALUE"
+        fi
 	done
 	echo "};"
+}
+
+trap 'rm "$OUT"' EXIT
+
+(
+	echo "#ifndef _ASM_X86_CPUFEATURE_H"
+	echo "#include <asm/cpufeature.h>"
+	echo "#endif"
+	echo ""
+
+	dump_array "x86_cap_flags" "NCAPINTS*32" "X86_FEATURE_" ""
+	echo ""
+
+	dump_array "x86_bug_flags" "NBUGINTS*32" "X86_BUG_" "NCAPINTS*32"
+
 ) > $OUT
 
 trap - EXIT
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 76f98fe5b35..a450373e8e9 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -132,15 +132,6 @@ static void __init ms_hyperv_init_platform(void)
 		lapic_timer_frequency = hv_lapic_frequency;
 		printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n",
 				lapic_timer_frequency);
-
-		/*
-		 * On Hyper-V, when we are booting off an EFI firmware stack,
-		 * we do not have many legacy devices including PIC, PIT etc.
-		 */
-		if (efi_enabled(EFI_BOOT)) {
-			printk(KERN_INFO "HyperV: Using null_legacy_pic\n");
-			legacy_pic = &null_legacy_pic;
-		}
 	}
 #endif
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 89f3b7c1af2..2879ecdaac4 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
 			return -EINVAL;
+		/* Check if the extra msrs can be safely accessed*/
+		if (!er->extra_msr_access)
+			return -ENXIO;
 
 		reg->idx = er->idx;
 		reg->config = event->attr.config1;
@@ -303,15 +306,6 @@ int x86_setup_perfctr(struct perf_event *event)
 		hwc->sample_period = x86_pmu.max_period;
 		hwc->last_period = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
-	} else {
-		/*
-		 * If we have a PMU initialized but no APIC
-		 * interrupts, we cannot sample hardware
-		 * events (user-space has to fall back and
-		 * sample via a hrtimer based software event):
-		 */
-		if (!x86_pmu.apic)
-			return -EOPNOTSUPP;
 	}
 
 	if (attr->type == PERF_TYPE_RAW)
@@ -1293,7 +1287,7 @@ void perf_events_lapic_init(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
-static int __kprobes
+static int
 perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
 	u64 start_clock;
@@ -1311,6 +1305,7 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 
 	return ret;
 }
+NOKPROBE_SYMBOL(perf_event_nmi_handler);
 
 struct event_constraint emptyconstraint;
 struct event_constraint unconstrained;
@@ -1366,6 +1361,15 @@ static void __init pmu_check_apic(void)
 	x86_pmu.apic = 0;
 	pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n");
 	pr_info("no hardware sampling interrupt available.\n");
+
+	/*
+	 * If we have a PMU initialized but no APIC
+	 * interrupts, we cannot sample hardware
+	 * events (user-space has to fall back and
+	 * sample via a hrtimer based software event):
+	 */
+	pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
 }
 
 static struct attribute_group x86_pmu_format_group = {
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 3b2f9bdd974..8ade93111e0 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -295,14 +295,16 @@ struct extra_reg {
 	u64			config_mask;
 	u64			valid_mask;
 	int			idx;  /* per_xxx->regs[] reg index */
+	bool			extra_msr_access;
 };
 
 #define EVENT_EXTRA_REG(e, ms, m, vm, i) {	\
-	.event = (e),		\
-	.msr = (ms),		\
-	.config_mask = (m),	\
-	.valid_mask = (vm),	\
-	.idx = EXTRA_REG_##i,	\
+	.event = (e),			\
+	.msr = (ms),			\
+	.config_mask = (m),		\
+	.valid_mask = (vm),		\
+	.idx = EXTRA_REG_##i,		\
+	.extra_msr_access = true,	\
 	}
 
 #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx)	\
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 4c36bbe3173..cbb1be3ed9e 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -593,7 +593,7 @@ out:
 	return 1;
 }
 
-static int __kprobes
+static int
 perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
 	int handled = 0;
@@ -606,6 +606,7 @@ perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 
 	return handled;
 }
+NOKPROBE_SYMBOL(perf_ibs_nmi_handler);
 
 static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
 {
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 3bbdf4cd38b..30790d798e6 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -294,31 +294,41 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
 			cpu_to_node(cpu));
 }
 
-static void amd_uncore_cpu_up_prepare(unsigned int cpu)
+static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 {
-	struct amd_uncore *uncore;
+	struct amd_uncore *uncore_nb = NULL, *uncore_l2;
 
 	if (amd_uncore_nb) {
-		uncore = amd_uncore_alloc(cpu);
-		uncore->cpu = cpu;
-		uncore->num_counters = NUM_COUNTERS_NB;
-		uncore->rdpmc_base = RDPMC_BASE_NB;
-		uncore->msr_base = MSR_F15H_NB_PERF_CTL;
-		uncore->active_mask = &amd_nb_active_mask;
-		uncore->pmu = &amd_nb_pmu;
-		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
+		uncore_nb = amd_uncore_alloc(cpu);
+		if (!uncore_nb)
+			goto fail;
+		uncore_nb->cpu = cpu;
+		uncore_nb->num_counters = NUM_COUNTERS_NB;
+		uncore_nb->rdpmc_base = RDPMC_BASE_NB;
+		uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
+		uncore_nb->active_mask = &amd_nb_active_mask;
+		uncore_nb->pmu = &amd_nb_pmu;
+		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
 	}
 
 	if (amd_uncore_l2) {
-		uncore = amd_uncore_alloc(cpu);
-		uncore->cpu = cpu;
-		uncore->num_counters = NUM_COUNTERS_L2;
-		uncore->rdpmc_base = RDPMC_BASE_L2;
-		uncore->msr_base = MSR_F16H_L2I_PERF_CTL;
-		uncore->active_mask = &amd_l2_active_mask;
-		uncore->pmu = &amd_l2_pmu;
-		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+		uncore_l2 = amd_uncore_alloc(cpu);
+		if (!uncore_l2)
+			goto fail;
+		uncore_l2->cpu = cpu;
+		uncore_l2->num_counters = NUM_COUNTERS_L2;
+		uncore_l2->rdpmc_base = RDPMC_BASE_L2;
+		uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
+		uncore_l2->active_mask = &amd_l2_active_mask;
+		uncore_l2->pmu = &amd_l2_pmu;
+		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
 	}
+
+	return 0;
+
+fail:
+	kfree(uncore_nb);
+	return -ENOMEM;
 }
 
 static struct amd_uncore *
@@ -441,7 +451,7 @@ static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores)
 
 	if (!--uncore->refcnt)
 		kfree(uncore);
-	*per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
+	*per_cpu_ptr(uncores, cpu) = NULL;
 }
 
 static void amd_uncore_cpu_dead(unsigned int cpu)
@@ -461,7 +471,8 @@ amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
-		amd_uncore_cpu_up_prepare(cpu);
+		if (amd_uncore_cpu_up_prepare(cpu))
+			return notifier_from_errno(-ENOMEM);
 		break;
 
 	case CPU_STARTING:
@@ -501,20 +512,33 @@ static void __init init_cpu_already_online(void *dummy)
 	amd_uncore_cpu_online(cpu);
 }
 
+static void cleanup_cpu_online(void *dummy)
+{
+	unsigned int cpu = smp_processor_id();
+
+	amd_uncore_cpu_dead(cpu);
+}
+
 static int __init amd_uncore_init(void)
 {
-	unsigned int cpu;
+	unsigned int cpu, cpu2;
 	int ret = -ENODEV;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
-		return -ENODEV;
+		goto fail_nodev;
 
 	if (!cpu_has_topoext)
-		return -ENODEV;
+		goto fail_nodev;
 
 	if (cpu_has_perfctr_nb) {
 		amd_uncore_nb = alloc_percpu(struct amd_uncore *);
-		perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
+		if (!amd_uncore_nb) {
+			ret = -ENOMEM;
+			goto fail_nb;
+		}
+		ret = perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
+		if (ret)
+			goto fail_nb;
 
 		printk(KERN_INFO "perf: AMD NB counters detected\n");
 		ret = 0;
@@ -522,20 +546,28 @@ static int __init amd_uncore_init(void)
 
 	if (cpu_has_perfctr_l2) {
 		amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
-		perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+		if (!amd_uncore_l2) {
+			ret = -ENOMEM;
+			goto fail_l2;
+		}
+		ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+		if (ret)
+			goto fail_l2;
 
 		printk(KERN_INFO "perf: AMD L2I counters detected\n");
 		ret = 0;
 	}
 
 	if (ret)
-		return -ENODEV;
+		goto fail_nodev;
 
 	cpu_notifier_register_begin();
 
 	/* init cpus already online before registering for hotplug notifier */
 	for_each_online_cpu(cpu) {
-		amd_uncore_cpu_up_prepare(cpu);
+		ret = amd_uncore_cpu_up_prepare(cpu);
+		if (ret)
+			goto fail_online;
 		smp_call_function_single(cpu, init_cpu_already_online, NULL, 1);
 	}
 
@@ -543,5 +575,30 @@ static int __init amd_uncore_init(void)
 	cpu_notifier_register_done();
 
 	return 0;
+
+
+fail_online:
+	for_each_online_cpu(cpu2) {
+		if (cpu2 == cpu)
+			break;
+		smp_call_function_single(cpu, cleanup_cpu_online, NULL, 1);
+	}
+	cpu_notifier_register_done();
+
+	/* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */
+	amd_uncore_nb = amd_uncore_l2 = NULL;
+	if (cpu_has_perfctr_l2)
+		perf_pmu_unregister(&amd_l2_pmu);
+fail_l2:
+	if (cpu_has_perfctr_nb)
+		perf_pmu_unregister(&amd_nb_pmu);
+	if (amd_uncore_l2)
+		free_percpu(amd_uncore_l2);
+fail_nb:
+	if (amd_uncore_nb)
+		free_percpu(amd_uncore_nb);
+
+fail_nodev:
+	return ret;
 }
 device_initcall(amd_uncore_init);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index adb02aa62af..2502d0d9d24 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1382,6 +1382,15 @@ again:
 	intel_pmu_lbr_read();
 
 	/*
+	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
+	 * and clear the bit.
+	 */
+	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+		if (!status)
+			goto done;
+	}
+
+	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
 	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
@@ -2173,6 +2182,41 @@ static void intel_snb_check_microcode(void)
 	}
 }
 
+/*
+ * Under certain circumstances, access certain MSR may cause #GP.
+ * The function tests if the input MSR can be safely accessed.
+ */
+static bool check_msr(unsigned long msr, u64 mask)
+{
+	u64 val_old, val_new, val_tmp;
+
+	/*
+	 * Read the current value, change it and read it back to see if it
+	 * matches, this is needed to detect certain hardware emulators
+	 * (qemu/kvm) that don't trap on the MSR access and always return 0s.
+	 */
+	if (rdmsrl_safe(msr, &val_old))
+		return false;
+
+	/*
+	 * Only change the bits which can be updated by wrmsrl.
+	 */
+	val_tmp = val_old ^ mask;
+	if (wrmsrl_safe(msr, val_tmp) ||
+	    rdmsrl_safe(msr, &val_new))
+		return false;
+
+	if (val_new != val_tmp)
+		return false;
+
+	/* Here it's sure that the MSR can be safely accessed.
+	 * Restore the old value and return.
+	 */
+	wrmsrl(msr, val_old);
+
+	return true;
+}
+
 static __init void intel_sandybridge_quirk(void)
 {
 	x86_pmu.check_microcode = intel_snb_check_microcode;
@@ -2262,7 +2306,8 @@ __init int intel_pmu_init(void)
 	union cpuid10_ebx ebx;
 	struct event_constraint *c;
 	unsigned int unused;
-	int version;
+	struct extra_reg *er;
+	int version, i;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
 		switch (boot_cpu_data.x86) {
@@ -2465,6 +2510,9 @@ __init int intel_pmu_init(void)
 	case 62: /* IvyBridge EP */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		/* dTLB-load-misses on IVB is different than SNB */
+		hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */
+
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
 		       sizeof(hw_cache_extra_regs));
 
@@ -2565,6 +2613,34 @@ __init int intel_pmu_init(void)
 		}
 	}
 
+	/*
+	 * Access LBR MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support LBR MSR
+	 * Check all LBT MSR here.
+	 * Disable LBR access if any LBR MSRs can not be accessed.
+	 */
+	if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL))
+		x86_pmu.lbr_nr = 0;
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) &&
+		      check_msr(x86_pmu.lbr_to + i, 0xffffUL)))
+			x86_pmu.lbr_nr = 0;
+	}
+
+	/*
+	 * Access extra MSR may cause #GP under certain circumstances.
+	 * E.g. KVM doesn't support offcore event
+	 * Check all extra_regs here.
+	 */
+	if (x86_pmu.extra_regs) {
+		for (er = x86_pmu.extra_regs; er->msr; er++) {
+			er->extra_msr_access = check_msr(er->msr, 0x1ffUL);
+			/* Disable LBR select mapping */
+			if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access)
+				x86_pmu.lbr_sel_map = NULL;
+		}
+	}
+
 	/* Support full width counters using alternative MSR range */
 	if (x86_pmu.intel_cap.full_width_write) {
 		x86_pmu.max_period = x86_pmu.cntval_mask;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 980970cb744..696ade311de 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -311,9 +311,11 @@ static int alloc_bts_buffer(int cpu)
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node);
-	if (unlikely(!buffer))
+	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	if (unlikely(!buffer)) {
+		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
+	}
 
 	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
 	thresh = max / 16;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index d82d155aca8..9dd2459a4c7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -384,6 +384,9 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 	if (br_type & PERF_SAMPLE_BRANCH_NO_TX)
 		mask |= X86_BR_NO_TX;
 
+	if (br_type & PERF_SAMPLE_BRANCH_COND)
+		mask |= X86_BR_JCC;
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
@@ -678,6 +681,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
 	 * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
 	 */
 	[PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
+	[PERF_SAMPLE_BRANCH_COND]     = LBR_JCC,
 };
 
 static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
@@ -689,6 +693,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
 	[PERF_SAMPLE_BRANCH_ANY_CALL]	= LBR_REL_CALL | LBR_IND_CALL
 					| LBR_FAR,
 	[PERF_SAMPLE_BRANCH_IND_CALL]	= LBR_IND_CALL,
+	[PERF_SAMPLE_BRANCH_COND]       = LBR_JCC,
 };
 
 /* core */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 65bbbea38b9..cfc6f9dfcd9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -550,16 +550,16 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
@@ -1222,6 +1222,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
 				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+
 	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
@@ -1245,7 +1246,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
@@ -2946,10 +2947,7 @@ again:
 		 * extra registers. If we failed to take an extra
 		 * register, try the alternative.
 		 */
-		if (idx % 2)
-			idx--;
-		else
-			idx++;
+		idx ^= 1;
 		if (idx != reg1->idx % 6) {
 			if (idx == 2)
 				config1 >>= 8;
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 06fe3ed8b85..5433658e598 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -97,6 +97,14 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		if (cpu_has(c, i) && x86_cap_flags[i] != NULL)
 			seq_printf(m, " %s", x86_cap_flags[i]);
 
+	seq_printf(m, "\nbugs\t\t:");
+	for (i = 0; i < 32*NBUGINTS; i++) {
+		unsigned int bug_bit = 32*NCAPINTS + i;
+
+		if (cpu_has_bug(c, bug_bit) && x86_bug_flags[i])
+			seq_printf(m, " %s", x86_bug_flags[i]);
+	}
+
 	seq_printf(m, "\nbogomips\t: %lu.%02lu\n",
 		   c->loops_per_jiffy/(500000/HZ),
 		   (c->loops_per_jiffy/(5000/HZ)) % 100);
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index b6f794aa169..4a8013d5594 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -38,7 +38,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		{ X86_FEATURE_PTS,		CR_EAX, 6, 0x00000006, 0 },
 		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006, 0 },
 		{ X86_FEATURE_EPB,		CR_ECX, 3, 0x00000006, 0 },
-		{ X86_FEATURE_XSAVEOPT,		CR_EAX,	0, 0x0000000d, 1 },
 		{ X86_FEATURE_HW_PSTATE,	CR_EDX, 7, 0x80000007, 0 },
 		{ X86_FEATURE_CPB,		CR_EDX, 9, 0x80000007, 0 },
 		{ X86_FEATURE_PROC_FEEDBACK,	CR_EDX,11, 0x80000007, 0 },
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index d9c12d3022a..b74ebc7c440 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -200,7 +200,7 @@ static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED;
 static int die_owner = -1;
 static unsigned int die_nest_count;
 
-unsigned __kprobes long oops_begin(void)
+unsigned long oops_begin(void)
 {
 	int cpu;
 	unsigned long flags;
@@ -223,8 +223,9 @@ unsigned __kprobes long oops_begin(void)
 	return flags;
 }
 EXPORT_SYMBOL_GPL(oops_begin);
+NOKPROBE_SYMBOL(oops_begin);
 
-void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
+void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 {
 	if (regs && kexec_should_crash(current))
 		crash_kexec(regs);
@@ -247,8 +248,9 @@ void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
 		panic("Fatal exception");
 	do_exit(signr);
 }
+NOKPROBE_SYMBOL(oops_end);
 
-int __kprobes __die(const char *str, struct pt_regs *regs, long err)
+int __die(const char *str, struct pt_regs *regs, long err)
 {
 #ifdef CONFIG_X86_32
 	unsigned short ss;
@@ -291,6 +293,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
 #endif
 	return 0;
 }
+NOKPROBE_SYMBOL(__die);
 
 /*
  * This is gone through when something in the kernel has done something bad
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 6cda0baeac9..2e1a6853e00 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -419,7 +419,7 @@ static size_t __init gen6_stolen_size(int num, int slot, int func)
 	return gmch_ctrl << 25; /* 32 MB units */
 }
 
-static size_t gen8_stolen_size(int num, int slot, int func)
+static size_t __init gen8_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
 
@@ -429,48 +429,73 @@ static size_t gen8_stolen_size(int num, int slot, int func)
 	return gmch_ctrl << 25; /* 32 MB units */
 }
 
+static size_t __init chv_stolen_size(int num, int slot, int func)
+{
+	u16 gmch_ctrl;
+
+	gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
+	gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
+	gmch_ctrl &= SNB_GMCH_GMS_MASK;
+
+	/*
+	 * 0x0  to 0x10: 32MB increments starting at 0MB
+	 * 0x11 to 0x16: 4MB increments starting at 8MB
+	 * 0x17 to 0x1d: 4MB increments start at 36MB
+	 */
+	if (gmch_ctrl < 0x11)
+		return gmch_ctrl << 25;
+	else if (gmch_ctrl < 0x17)
+		return (gmch_ctrl - 0x11 + 2) << 22;
+	else
+		return (gmch_ctrl - 0x17 + 9) << 22;
+}
 
 struct intel_stolen_funcs {
 	size_t (*size)(int num, int slot, int func);
 	u32 (*base)(int num, int slot, int func, size_t size);
 };
 
-static const struct intel_stolen_funcs i830_stolen_funcs = {
+static const struct intel_stolen_funcs i830_stolen_funcs __initconst = {
 	.base = i830_stolen_base,
 	.size = i830_stolen_size,
 };
 
-static const struct intel_stolen_funcs i845_stolen_funcs = {
+static const struct intel_stolen_funcs i845_stolen_funcs __initconst = {
 	.base = i845_stolen_base,
 	.size = i830_stolen_size,
 };
 
-static const struct intel_stolen_funcs i85x_stolen_funcs = {
+static const struct intel_stolen_funcs i85x_stolen_funcs __initconst = {
 	.base = i85x_stolen_base,
 	.size = gen3_stolen_size,
 };
 
-static const struct intel_stolen_funcs i865_stolen_funcs = {
+static const struct intel_stolen_funcs i865_stolen_funcs __initconst = {
 	.base = i865_stolen_base,
 	.size = gen3_stolen_size,
 };
 
-static const struct intel_stolen_funcs gen3_stolen_funcs = {
+static const struct intel_stolen_funcs gen3_stolen_funcs __initconst = {
 	.base = intel_stolen_base,
 	.size = gen3_stolen_size,
 };
 
-static const struct intel_stolen_funcs gen6_stolen_funcs = {
+static const struct intel_stolen_funcs gen6_stolen_funcs __initconst = {
 	.base = intel_stolen_base,
 	.size = gen6_stolen_size,
 };
 
-static const struct intel_stolen_funcs gen8_stolen_funcs = {
+static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = {
 	.base = intel_stolen_base,
 	.size = gen8_stolen_size,
 };
 
-static struct pci_device_id intel_stolen_ids[] __initdata = {
+static const struct intel_stolen_funcs chv_stolen_funcs __initconst = {
+	.base = intel_stolen_base,
+	.size = chv_stolen_size,
+};
+
+static const struct pci_device_id intel_stolen_ids[] __initconst = {
 	INTEL_I830_IDS(&i830_stolen_funcs),
 	INTEL_I845G_IDS(&i845_stolen_funcs),
 	INTEL_I85X_IDS(&i85x_stolen_funcs),
@@ -496,7 +521,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = {
 	INTEL_HSW_D_IDS(&gen6_stolen_funcs),
 	INTEL_HSW_M_IDS(&gen6_stolen_funcs),
 	INTEL_BDW_M_IDS(&gen8_stolen_funcs),
-	INTEL_BDW_D_IDS(&gen8_stolen_funcs)
+	INTEL_BDW_D_IDS(&gen8_stolen_funcs),
+	INTEL_CHV_IDS(&chv_stolen_funcs),
 };
 
 static void __init intel_graphics_stolen(int num, int slot, int func)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 98313ffaae6..47c410d99f5 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -315,10 +315,6 @@ ENTRY(ret_from_kernel_thread)
 ENDPROC(ret_from_kernel_thread)
 
 /*
- * Interrupt exit functions should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
-/*
  * Return to user mode is not as complex as all this looks,
  * but we want the default path for a system call return to
  * go as quickly as possible which is why some of this is
@@ -372,10 +368,6 @@ need_resched:
 END(resume_kernel)
 #endif
 	CFI_ENDPROC
-/*
- * End of kprobes section
- */
-	.popsection
 
 /* SYSENTER_RETURN points to after the "sysenter" instruction in
    the vsyscall page.  See vsyscall-sysentry.S, which defines the symbol.  */
@@ -431,8 +423,9 @@ sysenter_past_esp:
 	jnz sysenter_audit
 sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
-	jae syscall_badsys
+	jae sysenter_badsys
 	call *sys_call_table(,%eax,4)
+sysenter_after_call:
 	movl %eax,PT_EAX(%esp)
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
@@ -495,10 +488,6 @@ sysexit_audit:
 	PTGS_TO_GS_EX
 ENDPROC(ia32_sysenter_target)
 
-/*
- * syscall stub including irq exit should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
 	# system call handler stub
 ENTRY(system_call)
 	RING0_INT_FRAME			# can't unwind into user space anyway
@@ -513,6 +502,7 @@ ENTRY(system_call)
 	jae syscall_badsys
 syscall_call:
 	call *sys_call_table(,%eax,4)
+syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
 syscall_exit:
 	LOCKDEP_SYS_EXIT
@@ -686,14 +676,15 @@ syscall_fault:
 END(syscall_fault)
 
 syscall_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
-	jmp resume_userspace
+	movl $-ENOSYS,%eax
+	jmp syscall_after_call
+END(syscall_badsys)
+
+sysenter_badsys:
+	movl $-ENOSYS,%eax
+	jmp sysenter_after_call
 END(syscall_badsys)
 	CFI_ENDPROC
-/*
- * End of kprobes section
- */
-	.popsection
 
 .macro FIXUP_ESPFIX_STACK
 /*
@@ -784,10 +775,6 @@ common_interrupt:
 ENDPROC(common_interrupt)
 	CFI_ENDPROC
 
-/*
- *  Irq entries should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
 #define BUILD_INTERRUPT3(name, nr, fn)	\
 ENTRY(name)				\
 	RING0_INT_FRAME;		\
@@ -964,10 +951,6 @@ ENTRY(spurious_interrupt_bug)
 	jmp error_code
 	CFI_ENDPROC
 END(spurious_interrupt_bug)
-/*
- * End of kprobes section
- */
-	.popsection
 
 #ifdef CONFIG_XEN
 /* Xen doesn't set %esp to be precisely what the normal sysenter
@@ -1076,9 +1059,6 @@ ENTRY(mcount)
 END(mcount)
 
 ENTRY(ftrace_caller)
-	cmpl $0, function_trace_stop
-	jne  ftrace_stub
-
 	pushl %eax
 	pushl %ecx
 	pushl %edx
@@ -1110,8 +1090,6 @@ END(ftrace_caller)
 
 ENTRY(ftrace_regs_caller)
 	pushf	/* push flags before compare (in cs location) */
-	cmpl $0, function_trace_stop
-	jne ftrace_restore_flags
 
 	/*
 	 * i386 does not save SS and ESP when coming from kernel.
@@ -1170,7 +1148,6 @@ GLOBAL(ftrace_regs_call)
 	popf			/* Pop flags at end (no addl to corrupt flags) */
 	jmp ftrace_ret
 
-ftrace_restore_flags:
 	popf
 	jmp  ftrace_stub
 #else /* ! CONFIG_DYNAMIC_FTRACE */
@@ -1179,9 +1156,6 @@ ENTRY(mcount)
 	cmpl $__PAGE_OFFSET, %esp
 	jb ftrace_stub		/* Paging not enabled yet? */
 
-	cmpl $0, function_trace_stop
-	jne  ftrace_stub
-
 	cmpl $ftrace_stub, ftrace_trace_function
 	jnz trace
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -1242,11 +1216,6 @@ return_to_handler:
 	jmp *%ecx
 #endif
 
-/*
- * Some functions should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
-
 #ifdef CONFIG_TRACING
 ENTRY(trace_page_fault)
 	RING0_EC_FRAME
@@ -1460,7 +1429,3 @@ ENTRY(async_page_fault)
 END(async_page_fault)
 #endif
 
-/*
- * End of kprobes section
- */
-	.popsection
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 96987987c5d..2fac1343a90 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -53,7 +53,6 @@
 #include <asm/page_types.h>
 #include <asm/irqflags.h>
 #include <asm/paravirt.h>
-#include <asm/ftrace.h>
 #include <asm/percpu.h>
 #include <asm/asm.h>
 #include <asm/context_tracking.h>
@@ -70,209 +69,6 @@
 	.code64
 	.section .entry.text, "ax"
 
-#ifdef CONFIG_FUNCTION_TRACER
-
-#ifdef CC_USING_FENTRY
-# define function_hook	__fentry__
-#else
-# define function_hook	mcount
-#endif
-
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(function_hook)
-	retq
-END(function_hook)
-
-/* skip is set if stack has been adjusted */
-.macro ftrace_caller_setup skip=0
-	MCOUNT_SAVE_FRAME \skip
-
-	/* Load the ftrace_ops into the 3rd parameter */
-	movq function_trace_op(%rip), %rdx
-
-	/* Load ip into the first parameter */
-	movq RIP(%rsp), %rdi
-	subq $MCOUNT_INSN_SIZE, %rdi
-	/* Load the parent_ip into the second parameter */
-#ifdef CC_USING_FENTRY
-	movq SS+16(%rsp), %rsi
-#else
-	movq 8(%rbp), %rsi
-#endif
-.endm
-
-ENTRY(ftrace_caller)
-	/* Check if tracing was disabled (quick check) */
-	cmpl $0, function_trace_stop
-	jne  ftrace_stub
-
-	ftrace_caller_setup
-	/* regs go into 4th parameter (but make it NULL) */
-	movq $0, %rcx
-
-GLOBAL(ftrace_call)
-	call ftrace_stub
-
-	MCOUNT_RESTORE_FRAME
-ftrace_return:
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-GLOBAL(ftrace_graph_call)
-	jmp ftrace_stub
-#endif
-
-GLOBAL(ftrace_stub)
-	retq
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
-	/* Save the current flags before compare (in SS location)*/
-	pushfq
-
-	/* Check if tracing was disabled (quick check) */
-	cmpl $0, function_trace_stop
-	jne  ftrace_restore_flags
-
-	/* skip=8 to skip flags saved in SS */
-	ftrace_caller_setup 8
-
-	/* Save the rest of pt_regs */
-	movq %r15, R15(%rsp)
-	movq %r14, R14(%rsp)
-	movq %r13, R13(%rsp)
-	movq %r12, R12(%rsp)
-	movq %r11, R11(%rsp)
-	movq %r10, R10(%rsp)
-	movq %rbp, RBP(%rsp)
-	movq %rbx, RBX(%rsp)
-	/* Copy saved flags */
-	movq SS(%rsp), %rcx
-	movq %rcx, EFLAGS(%rsp)
-	/* Kernel segments */
-	movq $__KERNEL_DS, %rcx
-	movq %rcx, SS(%rsp)
-	movq $__KERNEL_CS, %rcx
-	movq %rcx, CS(%rsp)
-	/* Stack - skipping return address */
-	leaq SS+16(%rsp), %rcx
-	movq %rcx, RSP(%rsp)
-
-	/* regs go into 4th parameter */
-	leaq (%rsp), %rcx
-
-GLOBAL(ftrace_regs_call)
-	call ftrace_stub
-
-	/* Copy flags back to SS, to restore them */
-	movq EFLAGS(%rsp), %rax
-	movq %rax, SS(%rsp)
-
-	/* Handlers can change the RIP */
-	movq RIP(%rsp), %rax
-	movq %rax, SS+8(%rsp)
-
-	/* restore the rest of pt_regs */
-	movq R15(%rsp), %r15
-	movq R14(%rsp), %r14
-	movq R13(%rsp), %r13
-	movq R12(%rsp), %r12
-	movq R10(%rsp), %r10
-	movq RBP(%rsp), %rbp
-	movq RBX(%rsp), %rbx
-
-	/* skip=8 to skip flags saved in SS */
-	MCOUNT_RESTORE_FRAME 8
-
-	/* Restore flags */
-	popfq
-
-	jmp ftrace_return
-ftrace_restore_flags:
-	popfq
-	jmp  ftrace_stub
-
-END(ftrace_regs_caller)
-
-
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(function_hook)
-	cmpl $0, function_trace_stop
-	jne  ftrace_stub
-
-	cmpq $ftrace_stub, ftrace_trace_function
-	jnz trace
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	cmpq $ftrace_stub, ftrace_graph_return
-	jnz ftrace_graph_caller
-
-	cmpq $ftrace_graph_entry_stub, ftrace_graph_entry
-	jnz ftrace_graph_caller
-#endif
-
-GLOBAL(ftrace_stub)
-	retq
-
-trace:
-	MCOUNT_SAVE_FRAME
-
-	movq RIP(%rsp), %rdi
-#ifdef CC_USING_FENTRY
-	movq SS+16(%rsp), %rsi
-#else
-	movq 8(%rbp), %rsi
-#endif
-	subq $MCOUNT_INSN_SIZE, %rdi
-
-	call   *ftrace_trace_function
-
-	MCOUNT_RESTORE_FRAME
-
-	jmp ftrace_stub
-END(function_hook)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
-	MCOUNT_SAVE_FRAME
-
-#ifdef CC_USING_FENTRY
-	leaq SS+16(%rsp), %rdi
-	movq $0, %rdx	/* No framepointers needed */
-#else
-	leaq 8(%rbp), %rdi
-	movq (%rbp), %rdx
-#endif
-	movq RIP(%rsp), %rsi
-	subq $MCOUNT_INSN_SIZE, %rsi
-
-	call	prepare_ftrace_return
-
-	MCOUNT_RESTORE_FRAME
-
-	retq
-END(ftrace_graph_caller)
-
-GLOBAL(return_to_handler)
-	subq  $24, %rsp
-
-	/* Save the return values */
-	movq %rax, (%rsp)
-	movq %rdx, 8(%rsp)
-	movq %rbp, %rdi
-
-	call ftrace_return_to_handler
-
-	movq %rax, %rdi
-	movq 8(%rsp), %rdx
-	movq (%rsp), %rax
-	addq $24, %rsp
-	jmp *%rdi
-#endif
-
 
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
@@ -411,7 +207,6 @@ ENDPROC(native_usergs_sysret64)
  */
 	.macro XCPT_FRAME start=1 offset=0
 	INTR_FRAME \start, RIP+\offset-ORIG_RAX
-	/*CFI_REL_OFFSET orig_rax, ORIG_RAX-ORIG_RAX*/
 	.endm
 
 /*
@@ -488,26 +283,24 @@ ENDPROC(native_usergs_sysret64)
 	TRACE_IRQS_OFF
 	.endm
 
-/* save complete stack frame */
-	.pushsection .kprobes.text, "ax"
 ENTRY(save_paranoid)
 	XCPT_FRAME 1 RDI+8
 	cld
-	movq_cfi rdi, RDI+8
-	movq_cfi rsi, RSI+8
+	movq %rdi, RDI+8(%rsp)
+	movq %rsi, RSI+8(%rsp)
 	movq_cfi rdx, RDX+8
 	movq_cfi rcx, RCX+8
 	movq_cfi rax, RAX+8
-	movq_cfi r8, R8+8
-	movq_cfi r9, R9+8
-	movq_cfi r10, R10+8
-	movq_cfi r11, R11+8
+	movq %r8, R8+8(%rsp)
+	movq %r9, R9+8(%rsp)
+	movq %r10, R10+8(%rsp)
+	movq %r11, R11+8(%rsp)
 	movq_cfi rbx, RBX+8
-	movq_cfi rbp, RBP+8
-	movq_cfi r12, R12+8
-	movq_cfi r13, R13+8
-	movq_cfi r14, R14+8
-	movq_cfi r15, R15+8
+	movq %rbp, RBP+8(%rsp)
+	movq %r12, R12+8(%rsp)
+	movq %r13, R13+8(%rsp)
+	movq %r14, R14+8(%rsp)
+	movq %r15, R15+8(%rsp)
 	movl $1,%ebx
 	movl $MSR_GS_BASE,%ecx
 	rdmsr
@@ -518,7 +311,6 @@ ENTRY(save_paranoid)
 1:	ret
 	CFI_ENDPROC
 END(save_paranoid)
-	.popsection
 
 /*
  * A newly forked process directly context switches into this address.
@@ -976,10 +768,6 @@ END(interrupt)
 	call \func
 	.endm
 
-/*
- * Interrupt entry/exit should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
 	/*
 	 * The interrupt stubs push (~vector+0x80) onto the stack and
 	 * then jump to common_interrupt.
@@ -1041,27 +829,24 @@ restore_args:
 	RESTORE_ARGS 1,8,1
 
 irq_return:
+	INTERRUPT_RETURN
+
+ENTRY(native_iret)
 	/*
 	 * Are we returning to a stack segment from the LDT?  Note: in
 	 * 64-bit mode SS:RSP on the exception stack is always valid.
 	 */
 #ifdef CONFIG_X86_ESPFIX64
 	testb $4,(SS-RIP)(%rsp)
-	jnz irq_return_ldt
+	jnz native_irq_return_ldt
 #endif
 
-irq_return_iret:
-	INTERRUPT_RETURN
-	_ASM_EXTABLE(irq_return_iret, bad_iret)
-
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_iret)
+native_irq_return_iret:
 	iretq
-	_ASM_EXTABLE(native_iret, bad_iret)
-#endif
+	_ASM_EXTABLE(native_irq_return_iret, bad_iret)
 
 #ifdef CONFIG_X86_ESPFIX64
-irq_return_ldt:
+native_irq_return_ldt:
 	pushq_cfi %rax
 	pushq_cfi %rdi
 	SWAPGS
@@ -1083,7 +868,7 @@ irq_return_ldt:
 	SWAPGS
 	movq %rax,%rsp
 	popq_cfi %rax
-	jmp irq_return_iret
+	jmp native_irq_return_iret
 #endif
 
 	.section .fixup,"ax"
@@ -1167,13 +952,8 @@ __do_double_fault:
 	cmpl $__KERNEL_CS,CS(%rdi)
 	jne do_double_fault
 	movq RIP(%rdi),%rax
-	cmpq $irq_return_iret,%rax
-#ifdef CONFIG_PARAVIRT
-	je 1f
-	cmpq $native_iret,%rax
-#endif
+	cmpq $native_irq_return_iret,%rax
 	jne do_double_fault		/* This shouldn't happen... */
-1:
 	movq PER_CPU_VAR(kernel_stack),%rax
 	subq $(6*8-KERNEL_STACK_OFFSET),%rax	/* Reset to original stack */
 	movq %rax,RSP(%rdi)
@@ -1187,11 +967,6 @@ END(__do_double_fault)
 #endif
 
 /*
- * End of kprobes section
- */
-       .popsection
-
-/*
  * APIC interrupts.
  */
 .macro apicinterrupt3 num sym do_sym
@@ -1525,11 +1300,6 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
 	hyperv_callback_vector hyperv_vector_handler
 #endif /* CONFIG_HYPERV */
 
-/*
- * Some functions should be protected against kprobes
- */
-	.pushsection .kprobes.text, "ax"
-
 idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
 idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
 idtentry stack_segment do_stack_segment has_error_code=1 paranoid=1
@@ -1616,21 +1386,21 @@ ENTRY(error_entry)
 	CFI_ADJUST_CFA_OFFSET 15*8
 	/* oldrax contains error code */
 	cld
-	movq_cfi rdi, RDI+8
-	movq_cfi rsi, RSI+8
-	movq_cfi rdx, RDX+8
-	movq_cfi rcx, RCX+8
-	movq_cfi rax, RAX+8
-	movq_cfi  r8,  R8+8
-	movq_cfi  r9,  R9+8
-	movq_cfi r10, R10+8
-	movq_cfi r11, R11+8
+	movq %rdi, RDI+8(%rsp)
+	movq %rsi, RSI+8(%rsp)
+	movq %rdx, RDX+8(%rsp)
+	movq %rcx, RCX+8(%rsp)
+	movq %rax, RAX+8(%rsp)
+	movq  %r8,  R8+8(%rsp)
+	movq  %r9,  R9+8(%rsp)
+	movq %r10, R10+8(%rsp)
+	movq %r11, R11+8(%rsp)
 	movq_cfi rbx, RBX+8
-	movq_cfi rbp, RBP+8
-	movq_cfi r12, R12+8
-	movq_cfi r13, R13+8
-	movq_cfi r14, R14+8
-	movq_cfi r15, R15+8
+	movq %rbp, RBP+8(%rsp)
+	movq %r12, R12+8(%rsp)
+	movq %r13, R13+8(%rsp)
+	movq %r14, R14+8(%rsp)
+	movq %r15, R15+8(%rsp)
 	xorl %ebx,%ebx
 	testl $3,CS+8(%rsp)
 	je error_kernelspace
@@ -1648,8 +1418,9 @@ error_sti:
  * compat mode. Check for these here too.
  */
 error_kernelspace:
+	CFI_REL_OFFSET rcx, RCX+8
 	incl %ebx
-	leaq irq_return_iret(%rip),%rcx
+	leaq native_irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
 	je error_swapgs
 	movl %ecx,%eax	/* zero extend */
@@ -1946,7 +1717,3 @@ ENTRY(ignore_sysret)
 	CFI_ENDPROC
 END(ignore_sysret)
 
-/*
- * End of kprobes section
- */
-	.popsection
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 6afbb16e9b7..94d857fb103 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -175,7 +175,7 @@ void init_espfix_ap(void)
 	if (!pud_present(pud)) {
 		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
 		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
 			set_pud(&pud_p[n], pud);
 	}
@@ -185,7 +185,7 @@ void init_espfix_ap(void)
 	if (!pmd_present(pmd)) {
 		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
 		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
-		paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
 			set_pmd(&pmd_p[n], pmd);
 	}
@@ -193,7 +193,6 @@ void init_espfix_ap(void)
 	pte_p = pte_offset_kernel(&pmd, addr);
 	stack_page = (void *)__get_free_page(GFP_KERNEL);
 	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
-	paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT);
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 52819e816f8..3386dc9aa33 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -297,16 +297,7 @@ int ftrace_int3_handler(struct pt_regs *regs)
 
 static int ftrace_write(unsigned long ip, const char *val, int size)
 {
-	/*
-	 * On x86_64, kernel text mappings are mapped read-only with
-	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
-	 * of the kernel text mapping to modify the kernel text.
-	 *
-	 * For 32bit kernels, these mappings are same and we can use
-	 * kernel identity mapping to modify code.
-	 */
-	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
-		ip = (unsigned long)__va(__pa_symbol(ip));
+	ip = text_ip_addr(ip);
 
 	if (probe_kernel_write((void *)ip, val, size))
 		return -EPERM;
@@ -349,40 +340,14 @@ static int add_brk_on_nop(struct dyn_ftrace *rec)
 	return add_break(rec->ip, old);
 }
 
-/*
- * If the record has the FTRACE_FL_REGS set, that means that it
- * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
- * is not not set, then it wants to convert to the normal callback.
- */
-static unsigned long get_ftrace_addr(struct dyn_ftrace *rec)
-{
-	if (rec->flags & FTRACE_FL_REGS)
-		return (unsigned long)FTRACE_REGS_ADDR;
-	else
-		return (unsigned long)FTRACE_ADDR;
-}
-
-/*
- * The FTRACE_FL_REGS_EN is set when the record already points to
- * a function that saves all the regs. Basically the '_EN' version
- * represents the current state of the function.
- */
-static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec)
-{
-	if (rec->flags & FTRACE_FL_REGS_EN)
-		return (unsigned long)FTRACE_REGS_ADDR;
-	else
-		return (unsigned long)FTRACE_ADDR;
-}
-
 static int add_breakpoints(struct dyn_ftrace *rec, int enable)
 {
 	unsigned long ftrace_addr;
 	int ret;
 
-	ret = ftrace_test_record(rec, enable);
+	ftrace_addr = ftrace_get_addr_curr(rec);
 
-	ftrace_addr = get_ftrace_addr(rec);
+	ret = ftrace_test_record(rec, enable);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
@@ -392,10 +357,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
 		/* converting nop to call */
 		return add_brk_on_nop(rec);
 
-	case FTRACE_UPDATE_MODIFY_CALL_REGS:
 	case FTRACE_UPDATE_MODIFY_CALL:
-		ftrace_addr = get_ftrace_old_addr(rec);
-		/* fall through */
 	case FTRACE_UPDATE_MAKE_NOP:
 		/* converting a call to a nop */
 		return add_brk_on_call(rec, ftrace_addr);
@@ -440,14 +402,14 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
 		 * If not, don't touch the breakpoint, we make just create
 		 * a disaster.
 		 */
-		ftrace_addr = get_ftrace_addr(rec);
+		ftrace_addr = ftrace_get_addr_new(rec);
 		nop = ftrace_call_replace(ip, ftrace_addr);
 
 		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
 			goto update;
 
 		/* Check both ftrace_addr and ftrace_old_addr */
-		ftrace_addr = get_ftrace_old_addr(rec);
+		ftrace_addr = ftrace_get_addr_curr(rec);
 		nop = ftrace_call_replace(ip, ftrace_addr);
 
 		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
@@ -491,13 +453,12 @@ static int add_update(struct dyn_ftrace *rec, int enable)
 
 	ret = ftrace_test_record(rec, enable);
 
-	ftrace_addr  = get_ftrace_addr(rec);
+	ftrace_addr  = ftrace_get_addr_new(rec);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
 		return 0;
 
-	case FTRACE_UPDATE_MODIFY_CALL_REGS:
 	case FTRACE_UPDATE_MODIFY_CALL:
 	case FTRACE_UPDATE_MAKE_CALL:
 		/* converting nop to call */
@@ -538,13 +499,12 @@ static int finish_update(struct dyn_ftrace *rec, int enable)
 
 	ret = ftrace_update_record(rec, enable);
 
-	ftrace_addr = get_ftrace_addr(rec);
+	ftrace_addr = ftrace_get_addr_new(rec);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
 		return 0;
 
-	case FTRACE_UPDATE_MODIFY_CALL_REGS:
 	case FTRACE_UPDATE_MODIFY_CALL:
 	case FTRACE_UPDATE_MAKE_CALL:
 		/* converting nop to call */
@@ -621,8 +581,8 @@ void ftrace_replace_code(int enable)
 	return;
 
  remove_breakpoints:
+	pr_warn("Failed on %s (%d):\n", report, count);
 	ftrace_bug(ret, rec ? rec->ip : 0);
-	printk(KERN_WARNING "Failed on %s (%d):\n", report, count);
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
 		/*
@@ -743,6 +703,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
+	if (unlikely(ftrace_graph_is_dead()))
+		return;
+
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index a67b47c3131..5f9cf20cdb6 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -32,7 +32,6 @@
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/kallsyms.h>
-#include <linux/kprobes.h>
 #include <linux/percpu.h>
 #include <linux/kdebug.h>
 #include <linux/kernel.h>
@@ -424,7 +423,7 @@ EXPORT_SYMBOL_GPL(hw_breakpoint_restore);
  * NOTIFY_STOP returned for all other cases
  *
  */
-static int __kprobes hw_breakpoint_handler(struct die_args *args)
+static int hw_breakpoint_handler(struct die_args *args)
 {
 	int i, cpu, rc = NOTIFY_STOP;
 	struct perf_event *bp;
@@ -511,7 +510,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 /*
  * Handle debug exception notifications.
  */
-int __kprobes hw_breakpoint_exceptions_notify(
+int hw_breakpoint_exceptions_notify(
 		struct notifier_block *unused, unsigned long val, void *data)
 {
 	if (val != DIE_DEBUG)
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 2e977b5d61d..8af817105e2 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -299,13 +299,31 @@ static void unmask_8259A(void)
 static void init_8259A(int auto_eoi)
 {
 	unsigned long flags;
+	unsigned char probe_val = ~(1 << PIC_CASCADE_IR);
+	unsigned char new_val;
 
 	i8259A_auto_eoi = auto_eoi;
 
 	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
-	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
+	/*
+	 * Check to see if we have a PIC.
+	 * Mask all except the cascade and read
+	 * back the value we just wrote. If we don't
+	 * have a PIC, we will read 0xff as opposed to the
+	 * value we wrote.
+	 */
 	outb(0xff, PIC_SLAVE_IMR);	/* mask all of 8259A-2 */
+	outb(probe_val, PIC_MASTER_IMR);
+	new_val = inb(PIC_MASTER_IMR);
+	if (new_val != probe_val) {
+		printk(KERN_INFO "Using NULL legacy PIC\n");
+		legacy_pic = &null_legacy_pic;
+		raw_spin_unlock_irqrestore(&i8259A_lock, flags);
+		return;
+	}
+
+	outb(0xff, PIC_MASTER_IMR);	/* mask all of 8259A-1 */
 
 	/*
 	 * outb_pic - this has to work on a wide range of PC hardware.
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 11ccfb0a63e..922d2858102 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -365,6 +365,7 @@ void fixup_irqs(void)
 	struct irq_desc *desc;
 	struct irq_data *data;
 	struct irq_chip *chip;
+	int ret;
 
 	for_each_irq_desc(irq, desc) {
 		int break_affinity = 0;
@@ -403,10 +404,14 @@ void fixup_irqs(void)
 		if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
 			chip->irq_mask(data);
 
-		if (chip->irq_set_affinity)
-			chip->irq_set_affinity(data, affinity, true);
-		else if (!(warned++))
-			set_affinity = 0;
+		if (chip->irq_set_affinity) {
+			ret = chip->irq_set_affinity(data, affinity, true);
+			if (ret == -ENOSPC)
+				pr_crit("IRQ %d set affinity failed because there are no available vectors.  The device assigned to this IRQ is unstable.\n", irq);
+		} else {
+			if (!(warned++))
+				set_affinity = 0;
+		}
 
 		/*
 		 * We unmask if the irq was not marked masked by the
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 61b17dc2c27..67e6d19ef1b 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -112,7 +112,8 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = {
 
 const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);
 
-static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
+static nokprobe_inline void
+__synthesize_relative_insn(void *from, void *to, u8 op)
 {
 	struct __arch_relative_insn {
 		u8 op;
@@ -125,21 +126,23 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op)
 }
 
 /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
-void __kprobes synthesize_reljump(void *from, void *to)
+void synthesize_reljump(void *from, void *to)
 {
 	__synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE);
 }
+NOKPROBE_SYMBOL(synthesize_reljump);
 
 /* Insert a call instruction at address 'from', which calls address 'to'.*/
-void __kprobes synthesize_relcall(void *from, void *to)
+void synthesize_relcall(void *from, void *to)
 {
 	__synthesize_relative_insn(from, to, RELATIVECALL_OPCODE);
 }
+NOKPROBE_SYMBOL(synthesize_relcall);
 
 /*
  * Skip the prefixes of the instruction.
  */
-static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
+static kprobe_opcode_t *skip_prefixes(kprobe_opcode_t *insn)
 {
 	insn_attr_t attr;
 
@@ -154,12 +157,13 @@ static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn)
 #endif
 	return insn;
 }
+NOKPROBE_SYMBOL(skip_prefixes);
 
 /*
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-int __kprobes can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
@@ -260,7 +264,7 @@ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long add
 }
 
 /* Check if paddr is at an instruction boundary */
-static int __kprobes can_probe(unsigned long paddr)
+static int can_probe(unsigned long paddr)
 {
 	unsigned long addr, __addr, offset = 0;
 	struct insn insn;
@@ -299,7 +303,7 @@ static int __kprobes can_probe(unsigned long paddr)
 /*
  * Returns non-zero if opcode modifies the interrupt flag.
  */
-static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
+static int is_IF_modifier(kprobe_opcode_t *insn)
 {
 	/* Skip prefixes */
 	insn = skip_prefixes(insn);
@@ -322,7 +326,7 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn)
  * If not, return null.
  * Only applicable to 64-bit x86.
  */
-int __kprobes __copy_instruction(u8 *dest, u8 *src)
+int __copy_instruction(u8 *dest, u8 *src)
 {
 	struct insn insn;
 	kprobe_opcode_t buf[MAX_INSN_SIZE];
@@ -365,7 +369,7 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src)
 	return insn.length;
 }
 
-static int __kprobes arch_copy_kprobe(struct kprobe *p)
+static int arch_copy_kprobe(struct kprobe *p)
 {
 	int ret;
 
@@ -392,7 +396,7 @@ static int __kprobes arch_copy_kprobe(struct kprobe *p)
 	return 0;
 }
 
-int __kprobes arch_prepare_kprobe(struct kprobe *p)
+int arch_prepare_kprobe(struct kprobe *p)
 {
 	if (alternatives_text_reserved(p->addr, p->addr))
 		return -EINVAL;
@@ -407,17 +411,17 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	return arch_copy_kprobe(p);
 }
 
-void __kprobes arch_arm_kprobe(struct kprobe *p)
+void arch_arm_kprobe(struct kprobe *p)
 {
 	text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1);
 }
 
-void __kprobes arch_disarm_kprobe(struct kprobe *p)
+void arch_disarm_kprobe(struct kprobe *p)
 {
 	text_poke(p->addr, &p->opcode, 1);
 }
 
-void __kprobes arch_remove_kprobe(struct kprobe *p)
+void arch_remove_kprobe(struct kprobe *p)
 {
 	if (p->ainsn.insn) {
 		free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
@@ -425,7 +429,8 @@ void __kprobes arch_remove_kprobe(struct kprobe *p)
 	}
 }
 
-static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
+static nokprobe_inline void
+save_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	kcb->prev_kprobe.kp = kprobe_running();
 	kcb->prev_kprobe.status = kcb->kprobe_status;
@@ -433,7 +438,8 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 	kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags;
 }
 
-static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+static nokprobe_inline void
+restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
 	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
@@ -441,8 +447,9 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 	kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags;
 }
 
-static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
-				struct kprobe_ctlblk *kcb)
+static nokprobe_inline void
+set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
+		   struct kprobe_ctlblk *kcb)
 {
 	__this_cpu_write(current_kprobe, p);
 	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
@@ -451,7 +458,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
 		kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
 }
 
-static void __kprobes clear_btf(void)
+static nokprobe_inline void clear_btf(void)
 {
 	if (test_thread_flag(TIF_BLOCKSTEP)) {
 		unsigned long debugctl = get_debugctlmsr();
@@ -461,7 +468,7 @@ static void __kprobes clear_btf(void)
 	}
 }
 
-static void __kprobes restore_btf(void)
+static nokprobe_inline void restore_btf(void)
 {
 	if (test_thread_flag(TIF_BLOCKSTEP)) {
 		unsigned long debugctl = get_debugctlmsr();
@@ -471,8 +478,7 @@ static void __kprobes restore_btf(void)
 	}
 }
 
-void __kprobes
-arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
+void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	unsigned long *sara = stack_addr(regs);
 
@@ -481,9 +487,10 @@ arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 	/* Replace the return addr with trampoline addr */
 	*sara = (unsigned long) &kretprobe_trampoline;
 }
+NOKPROBE_SYMBOL(arch_prepare_kretprobe);
 
-static void __kprobes
-setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter)
+static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
+			     struct kprobe_ctlblk *kcb, int reenter)
 {
 	if (setup_detour_execution(p, regs, reenter))
 		return;
@@ -519,22 +526,24 @@ setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *k
 	else
 		regs->ip = (unsigned long)p->ainsn.insn;
 }
+NOKPROBE_SYMBOL(setup_singlestep);
 
 /*
  * We have reentered the kprobe_handler(), since another probe was hit while
  * within the handler. We save the original kprobes variables and just single
  * step on the instruction of the new probe without calling any user handlers.
  */
-static int __kprobes
-reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
+static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
+			  struct kprobe_ctlblk *kcb)
 {
 	switch (kcb->kprobe_status) {
 	case KPROBE_HIT_SSDONE:
 	case KPROBE_HIT_ACTIVE:
+	case KPROBE_HIT_SS:
 		kprobes_inc_nmissed_count(p);
 		setup_singlestep(p, regs, kcb, 1);
 		break;
-	case KPROBE_HIT_SS:
+	case KPROBE_REENTER:
 		/* A probe has been hit in the codepath leading up to, or just
 		 * after, single-stepping of a probed instruction. This entire
 		 * codepath should strictly reside in .kprobes.text section.
@@ -553,17 +562,21 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb
 
 	return 1;
 }
+NOKPROBE_SYMBOL(reenter_kprobe);
 
 /*
  * Interrupts are disabled on entry as trap3 is an interrupt gate and they
  * remain disabled throughout this function.
  */
-static int __kprobes kprobe_handler(struct pt_regs *regs)
+int kprobe_int3_handler(struct pt_regs *regs)
 {
 	kprobe_opcode_t *addr;
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
+	if (user_mode_vm(regs))
+		return 0;
+
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
 	/*
 	 * We don't want to be preempted for the entire
@@ -621,12 +634,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	preempt_enable_no_resched();
 	return 0;
 }
+NOKPROBE_SYMBOL(kprobe_int3_handler);
 
 /*
  * When a retprobed function returns, this code saves registers and
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
  */
-static void __used __kprobes kretprobe_trampoline_holder(void)
+static void __used kretprobe_trampoline_holder(void)
 {
 	asm volatile (
 			".global kretprobe_trampoline\n"
@@ -657,11 +671,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
 #endif
 			"	ret\n");
 }
+NOKPROBE_SYMBOL(kretprobe_trampoline_holder);
+NOKPROBE_SYMBOL(kretprobe_trampoline);
 
 /*
  * Called from kretprobe_trampoline
  */
-__visible __used __kprobes void *trampoline_handler(struct pt_regs *regs)
+__visible __used void *trampoline_handler(struct pt_regs *regs)
 {
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
@@ -747,6 +763,7 @@ __visible __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	}
 	return (void *)orig_ret_address;
 }
+NOKPROBE_SYMBOL(trampoline_handler);
 
 /*
  * Called after single-stepping.  p->addr is the address of the
@@ -775,8 +792,8 @@ __visible __used __kprobes void *trampoline_handler(struct pt_regs *regs)
  * jump instruction after the copied instruction, that jumps to the next
  * instruction after the probepoint.
  */
-static void __kprobes
-resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
+static void resume_execution(struct kprobe *p, struct pt_regs *regs,
+			     struct kprobe_ctlblk *kcb)
 {
 	unsigned long *tos = stack_addr(regs);
 	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
@@ -851,12 +868,13 @@ resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *k
 no_change:
 	restore_btf();
 }
+NOKPROBE_SYMBOL(resume_execution);
 
 /*
  * Interrupts are disabled on entry as trap1 is an interrupt gate and they
  * remain disabled throughout this function.
  */
-static int __kprobes post_kprobe_handler(struct pt_regs *regs)
+int kprobe_debug_handler(struct pt_regs *regs)
 {
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -891,8 +909,9 @@ out:
 
 	return 1;
 }
+NOKPROBE_SYMBOL(kprobe_debug_handler);
 
-int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -949,12 +968,13 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 
 	return 0;
 }
+NOKPROBE_SYMBOL(kprobe_fault_handler);
 
 /*
  * Wrapper routine for handling exceptions.
  */
-int __kprobes
-kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data)
+int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
+			     void *data)
 {
 	struct die_args *args = data;
 	int ret = NOTIFY_DONE;
@@ -962,22 +982,7 @@ kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *d
 	if (args->regs && user_mode_vm(args->regs))
 		return ret;
 
-	switch (val) {
-	case DIE_INT3:
-		if (kprobe_handler(args->regs))
-			ret = NOTIFY_STOP;
-		break;
-	case DIE_DEBUG:
-		if (post_kprobe_handler(args->regs)) {
-			/*
-			 * Reset the BS bit in dr6 (pointed by args->err) to
-			 * denote completion of processing
-			 */
-			(*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP;
-			ret = NOTIFY_STOP;
-		}
-		break;
-	case DIE_GPF:
+	if (val == DIE_GPF) {
 		/*
 		 * To be potentially processing a kprobe fault and to
 		 * trust the result from kprobe_running(), we have
@@ -986,14 +991,12 @@ kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *d
 		if (!preemptible() && kprobe_running() &&
 		    kprobe_fault_handler(args->regs, args->trapnr))
 			ret = NOTIFY_STOP;
-		break;
-	default:
-		break;
 	}
 	return ret;
 }
+NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
+int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
 	unsigned long addr;
@@ -1017,8 +1020,9 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->ip = (unsigned long)(jp->entry);
 	return 1;
 }
+NOKPROBE_SYMBOL(setjmp_pre_handler);
 
-void __kprobes jprobe_return(void)
+void jprobe_return(void)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
@@ -1034,8 +1038,10 @@ void __kprobes jprobe_return(void)
 			"       nop			\n"::"b"
 			(kcb->jprobe_saved_sp):"memory");
 }
+NOKPROBE_SYMBOL(jprobe_return);
+NOKPROBE_SYMBOL(jprobe_return_end);
 
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
+int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	u8 *addr = (u8 *) (regs->ip - 1);
@@ -1063,13 +1069,22 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	}
 	return 0;
 }
+NOKPROBE_SYMBOL(longjmp_break_handler);
+
+bool arch_within_kprobe_blacklist(unsigned long addr)
+{
+	return  (addr >= (unsigned long)__kprobes_text_start &&
+		 addr < (unsigned long)__kprobes_text_end) ||
+		(addr >= (unsigned long)__entry_text_start &&
+		 addr < (unsigned long)__entry_text_end);
+}
 
 int __init arch_init_kprobes(void)
 {
 	return 0;
 }
 
-int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+int arch_trampoline_kprobe(struct kprobe *p)
 {
 	return 0;
 }
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 23ef5c556f0..717b02a22e6 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -25,8 +25,9 @@
 
 #include "common.h"
 
-static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			     struct kprobe_ctlblk *kcb)
+static nokprobe_inline
+int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+		      struct kprobe_ctlblk *kcb)
 {
 	/*
 	 * Emulate singlestep (and also recover regs->ip)
@@ -41,18 +42,19 @@ static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
 	return 1;
 }
 
-int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			      struct kprobe_ctlblk *kcb)
+int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+		    struct kprobe_ctlblk *kcb)
 {
 	if (kprobe_ftrace(p))
 		return __skip_singlestep(p, regs, kcb);
 	else
 		return 0;
 }
+NOKPROBE_SYMBOL(skip_singlestep);
 
 /* Ftrace callback handler for kprobes */
-void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
-				     struct ftrace_ops *ops, struct pt_regs *regs)
+void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+			   struct ftrace_ops *ops, struct pt_regs *regs)
 {
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
@@ -84,8 +86,9 @@ void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 end:
 	local_irq_restore(flags);
 }
+NOKPROBE_SYMBOL(kprobe_ftrace_handler);
 
-int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
+int arch_prepare_kprobe_ftrace(struct kprobe *p)
 {
 	p->ainsn.insn = NULL;
 	p->ainsn.boostable = -1;
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 898160b42e4..f304773285a 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -77,7 +77,7 @@ found:
 }
 
 /* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */
-static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
+static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val)
 {
 #ifdef CONFIG_X86_64
 	*addr++ = 0x48;
@@ -138,7 +138,8 @@ asm (
 #define INT3_SIZE sizeof(kprobe_opcode_t)
 
 /* Optimized kprobe call back function: called from optinsn */
-static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
+static void
+optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	unsigned long flags;
@@ -168,8 +169,9 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_
 	}
 	local_irq_restore(flags);
 }
+NOKPROBE_SYMBOL(optimized_callback);
 
-static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
+static int copy_optimized_instructions(u8 *dest, u8 *src)
 {
 	int len = 0, ret;
 
@@ -189,7 +191,7 @@ static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
 }
 
 /* Check whether insn is indirect jump */
-static int __kprobes insn_is_indirect_jump(struct insn *insn)
+static int insn_is_indirect_jump(struct insn *insn)
 {
 	return ((insn->opcode.bytes[0] == 0xff &&
 		(X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */
@@ -224,7 +226,7 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len)
 }
 
 /* Decode whole function to ensure any instructions don't jump into target */
-static int __kprobes can_optimize(unsigned long paddr)
+static int can_optimize(unsigned long paddr)
 {
 	unsigned long addr, size = 0, offset = 0;
 	struct insn insn;
@@ -275,7 +277,7 @@ static int __kprobes can_optimize(unsigned long paddr)
 }
 
 /* Check optimized_kprobe can actually be optimized. */
-int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
+int arch_check_optimized_kprobe(struct optimized_kprobe *op)
 {
 	int i;
 	struct kprobe *p;
@@ -290,15 +292,15 @@ int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op)
 }
 
 /* Check the addr is within the optimized instructions. */
-int __kprobes
-arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr)
+int arch_within_optimized_kprobe(struct optimized_kprobe *op,
+				 unsigned long addr)
 {
 	return ((unsigned long)op->kp.addr <= addr &&
 		(unsigned long)op->kp.addr + op->optinsn.size > addr);
 }
 
 /* Free optimized instruction slot */
-static __kprobes
+static
 void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 {
 	if (op->optinsn.insn) {
@@ -308,7 +310,7 @@ void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 	}
 }
 
-void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
+void arch_remove_optimized_kprobe(struct optimized_kprobe *op)
 {
 	__arch_remove_optimized_kprobe(op, 1);
 }
@@ -318,7 +320,7 @@ void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op)
  * Target instructions MUST be relocatable (checked inside)
  * This is called when new aggr(opt)probe is allocated or reused.
  */
-int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
+int arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
 {
 	u8 *buf;
 	int ret;
@@ -372,7 +374,7 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
  * Replace breakpoints (int3) with relative jumps.
  * Caller must call with locking kprobe_mutex and text_mutex.
  */
-void __kprobes arch_optimize_kprobes(struct list_head *oplist)
+void arch_optimize_kprobes(struct list_head *oplist)
 {
 	struct optimized_kprobe *op, *tmp;
 	u8 insn_buf[RELATIVEJUMP_SIZE];
@@ -398,7 +400,7 @@ void __kprobes arch_optimize_kprobes(struct list_head *oplist)
 }
 
 /* Replace a relative jump with a breakpoint (int3).  */
-void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
+void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
 	u8 insn_buf[RELATIVEJUMP_SIZE];
 
@@ -424,8 +426,7 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist,
 	}
 }
 
-int  __kprobes
-setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
+int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 {
 	struct optimized_kprobe *op;
 
@@ -441,3 +442,4 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 	}
 	return 0;
 }
+NOKPROBE_SYMBOL(setup_detour_execution);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7e97371387f..3dd8e2c4d74 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -251,8 +251,9 @@ u32 kvm_read_and_reset_pf_reason(void)
 	return reason;
 }
 EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason);
+NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason);
 
-dotraplinkage void __kprobes
+dotraplinkage void
 do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
 	enum ctx_state prev_state;
@@ -276,6 +277,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 		break;
 	}
 }
+NOKPROBE_SYMBOL(do_async_page_fault);
 
 static void __init paravirt_ops_setup(void)
 {
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
new file mode 100644
index 00000000000..c73aecf10d3
--- /dev/null
+++ b/arch/x86/kernel/mcount_64.S
@@ -0,0 +1,206 @@
+/*
+ *  linux/arch/x86_64/mcount_64.S
+ *
+ *  Copyright (C) 2014  Steven Rostedt, Red Hat Inc
+ */
+
+#include <linux/linkage.h>
+#include <asm/ptrace.h>
+#include <asm/ftrace.h>
+
+
+	.code64
+	.section .entry.text, "ax"
+
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+#ifdef CC_USING_FENTRY
+# define function_hook	__fentry__
+#else
+# define function_hook	mcount
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(function_hook)
+	retq
+END(function_hook)
+
+/* skip is set if stack has been adjusted */
+.macro ftrace_caller_setup skip=0
+	MCOUNT_SAVE_FRAME \skip
+
+	/* Load the ftrace_ops into the 3rd parameter */
+	movq function_trace_op(%rip), %rdx
+
+	/* Load ip into the first parameter */
+	movq RIP(%rsp), %rdi
+	subq $MCOUNT_INSN_SIZE, %rdi
+	/* Load the parent_ip into the second parameter */
+#ifdef CC_USING_FENTRY
+	movq SS+16(%rsp), %rsi
+#else
+	movq 8(%rbp), %rsi
+#endif
+.endm
+
+ENTRY(ftrace_caller)
+	ftrace_caller_setup
+	/* regs go into 4th parameter (but make it NULL) */
+	movq $0, %rcx
+
+GLOBAL(ftrace_call)
+	call ftrace_stub
+
+	MCOUNT_RESTORE_FRAME
+ftrace_return:
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+GLOBAL(ftrace_graph_call)
+	jmp ftrace_stub
+#endif
+
+GLOBAL(ftrace_stub)
+	retq
+END(ftrace_caller)
+
+ENTRY(ftrace_regs_caller)
+	/* Save the current flags before compare (in SS location)*/
+	pushfq
+
+	/* skip=8 to skip flags saved in SS */
+	ftrace_caller_setup 8
+
+	/* Save the rest of pt_regs */
+	movq %r15, R15(%rsp)
+	movq %r14, R14(%rsp)
+	movq %r13, R13(%rsp)
+	movq %r12, R12(%rsp)
+	movq %r11, R11(%rsp)
+	movq %r10, R10(%rsp)
+	movq %rbp, RBP(%rsp)
+	movq %rbx, RBX(%rsp)
+	/* Copy saved flags */
+	movq SS(%rsp), %rcx
+	movq %rcx, EFLAGS(%rsp)
+	/* Kernel segments */
+	movq $__KERNEL_DS, %rcx
+	movq %rcx, SS(%rsp)
+	movq $__KERNEL_CS, %rcx
+	movq %rcx, CS(%rsp)
+	/* Stack - skipping return address */
+	leaq SS+16(%rsp), %rcx
+	movq %rcx, RSP(%rsp)
+
+	/* regs go into 4th parameter */
+	leaq (%rsp), %rcx
+
+GLOBAL(ftrace_regs_call)
+	call ftrace_stub
+
+	/* Copy flags back to SS, to restore them */
+	movq EFLAGS(%rsp), %rax
+	movq %rax, SS(%rsp)
+
+	/* Handlers can change the RIP */
+	movq RIP(%rsp), %rax
+	movq %rax, SS+8(%rsp)
+
+	/* restore the rest of pt_regs */
+	movq R15(%rsp), %r15
+	movq R14(%rsp), %r14
+	movq R13(%rsp), %r13
+	movq R12(%rsp), %r12
+	movq R10(%rsp), %r10
+	movq RBP(%rsp), %rbp
+	movq RBX(%rsp), %rbx
+
+	/* skip=8 to skip flags saved in SS */
+	MCOUNT_RESTORE_FRAME 8
+
+	/* Restore flags */
+	popfq
+
+	jmp ftrace_return
+
+	popfq
+	jmp  ftrace_stub
+
+END(ftrace_regs_caller)
+
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(function_hook)
+	cmpq $ftrace_stub, ftrace_trace_function
+	jnz trace
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	cmpq $ftrace_stub, ftrace_graph_return
+	jnz ftrace_graph_caller
+
+	cmpq $ftrace_graph_entry_stub, ftrace_graph_entry
+	jnz ftrace_graph_caller
+#endif
+
+GLOBAL(ftrace_stub)
+	retq
+
+trace:
+	MCOUNT_SAVE_FRAME
+
+	movq RIP(%rsp), %rdi
+#ifdef CC_USING_FENTRY
+	movq SS+16(%rsp), %rsi
+#else
+	movq 8(%rbp), %rsi
+#endif
+	subq $MCOUNT_INSN_SIZE, %rdi
+
+	call   *ftrace_trace_function
+
+	MCOUNT_RESTORE_FRAME
+
+	jmp ftrace_stub
+END(function_hook)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+	MCOUNT_SAVE_FRAME
+
+#ifdef CC_USING_FENTRY
+	leaq SS+16(%rsp), %rdi
+	movq $0, %rdx	/* No framepointers needed */
+#else
+	leaq 8(%rbp), %rdi
+	movq (%rbp), %rdx
+#endif
+	movq RIP(%rsp), %rsi
+	subq $MCOUNT_INSN_SIZE, %rsi
+
+	call	prepare_ftrace_return
+
+	MCOUNT_RESTORE_FRAME
+
+	retq
+END(ftrace_graph_caller)
+
+GLOBAL(return_to_handler)
+	subq  $24, %rsp
+
+	/* Save the return values */
+	movq %rax, (%rsp)
+	movq %rdx, 8(%rsp)
+	movq %rbp, %rdi
+
+	call ftrace_return_to_handler
+
+	movq %rax, %rdi
+	movq 8(%rsp), %rdx
+	movq (%rsp), %rax
+	addq $24, %rsp
+	jmp *%rdi
+#endif
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index b4872b999a7..c3e985d1751 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -110,7 +110,7 @@ static void nmi_max_handler(struct irq_work *w)
 		a->handler, whole_msecs, decimal_msecs);
 }
 
-static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
+static int nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
 	struct nmiaction *a;
@@ -146,6 +146,7 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
 	/* return total number of NMI events handled */
 	return handled;
 }
+NOKPROBE_SYMBOL(nmi_handle);
 
 int __register_nmi_handler(unsigned int type, struct nmiaction *action)
 {
@@ -208,7 +209,7 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 }
 EXPORT_SYMBOL_GPL(unregister_nmi_handler);
 
-static __kprobes void
+static void
 pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
 	/* check to see if anyone registered against these types of errors */
@@ -238,8 +239,9 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
 	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
 	outb(reason, NMI_REASON_PORT);
 }
+NOKPROBE_SYMBOL(pci_serr_error);
 
-static __kprobes void
+static void
 io_check_error(unsigned char reason, struct pt_regs *regs)
 {
 	unsigned long i;
@@ -269,8 +271,9 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 	reason &= ~NMI_REASON_CLEAR_IOCHK;
 	outb(reason, NMI_REASON_PORT);
 }
+NOKPROBE_SYMBOL(io_check_error);
 
-static __kprobes void
+static void
 unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 {
 	int handled;
@@ -298,11 +301,12 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 
 	pr_emerg("Dazed and confused, but trying to continue\n");
 }
+NOKPROBE_SYMBOL(unknown_nmi_error);
 
 static DEFINE_PER_CPU(bool, swallow_nmi);
 static DEFINE_PER_CPU(unsigned long, last_nmi_rip);
 
-static __kprobes void default_do_nmi(struct pt_regs *regs)
+static void default_do_nmi(struct pt_regs *regs)
 {
 	unsigned char reason = 0;
 	int handled;
@@ -401,6 +405,7 @@ static __kprobes void default_do_nmi(struct pt_regs *regs)
 	else
 		unknown_nmi_error(reason, regs);
 }
+NOKPROBE_SYMBOL(default_do_nmi);
 
 /*
  * NMIs can hit breakpoints which will cause it to lose its
@@ -520,7 +525,7 @@ static inline void nmi_nesting_postprocess(void)
 }
 #endif
 
-dotraplinkage notrace __kprobes void
+dotraplinkage notrace void
 do_nmi(struct pt_regs *regs, long error_code)
 {
 	nmi_nesting_preprocess(regs);
@@ -537,6 +542,7 @@ do_nmi(struct pt_regs *regs, long error_code)
 	/* On i386, may loop back to preprocess */
 	nmi_nesting_postprocess();
 }
+NOKPROBE_SYMBOL(do_nmi);
 
 void stop_nmi(void)
 {
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1b10af835c3..548d25f00c9 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -23,6 +23,7 @@
 #include <linux/efi.h>
 #include <linux/bcd.h>
 #include <linux/highmem.h>
+#include <linux/kprobes.h>
 
 #include <asm/bug.h>
 #include <asm/paravirt.h>
@@ -389,6 +390,11 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
 	.end_context_switch = paravirt_nop,
 };
 
+/* At this point, native_get/set_debugreg has real function entries */
+NOKPROBE_SYMBOL(native_get_debugreg);
+NOKPROBE_SYMBOL(native_set_debugreg);
+NOKPROBE_SYMBOL(native_load_idt);
+
 struct pv_apic_ops pv_apic_ops = {
 #ifdef CONFIG_X86_LOCAL_APIC
 	.startup_ipi_hook = paravirt_nop,
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34f93e..a1da6737ba5 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
 DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
 DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
 DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_irq_ops, save_fl);
 		PATCH_SITE(pv_irq_ops, irq_enable);
 		PATCH_SITE(pv_irq_ops, irq_disable);
-		PATCH_SITE(pv_cpu_ops, iret);
 		PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret32);
 		PATCH_SITE(pv_cpu_ops, usergs_sysret64);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 898d077617a..ca5b02d405c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -413,12 +413,11 @@ void set_personality_ia32(bool x32)
 	set_thread_flag(TIF_ADDR32);
 
 	/* Mark the associated mm as containing 32-bit tasks. */
-	if (current->mm)
-		current->mm->context.ia32_compat = 1;
-
 	if (x32) {
 		clear_thread_flag(TIF_IA32);
 		set_thread_flag(TIF_X32);
+		if (current->mm)
+			current->mm->context.ia32_compat = TIF_X32;
 		current->personality &= ~READ_IMPLIES_EXEC;
 		/* is_compat_task() uses the presence of the x32
 		   syscall bit flag to determine compat status */
@@ -426,6 +425,8 @@ void set_personality_ia32(bool x32)
 	} else {
 		set_thread_flag(TIF_IA32);
 		clear_thread_flag(TIF_X32);
+		if (current->mm)
+			current->mm->context.ia32_compat = TIF_IA32;
 		current->personality |= force_personality32;
 		/* Prepare the first "return" to user space */
 		current_thread_info()->status |= TS_COMPAT;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 52b1157c53e..17962e667a9 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -28,6 +28,7 @@
 #include <linux/mc146818rtc.h>
 #include <asm/realmode.h>
 #include <asm/x86_init.h>
+#include <asm/efi.h>
 
 /*
  * Power off function, if any
@@ -401,12 +402,25 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 
 static int __init reboot_init(void)
 {
+	int rv;
+
 	/*
 	 * Only do the DMI check if reboot_type hasn't been overridden
 	 * on the command line
 	 */
-	if (reboot_default)
-		dmi_check_system(reboot_dmi_table);
+	if (!reboot_default)
+		return 0;
+
+	/*
+	 * The DMI quirks table takes precedence. If no quirks entry
+	 * matches and the ACPI Hardware Reduced bit is set, force EFI
+	 * reboot.
+	 */
+	rv = dmi_check_system(reboot_dmi_table);
+
+	if (!rv && efi_reboot_required())
+		reboot_type = BOOT_EFI;
+
 	return 0;
 }
 core_initcall(reboot_init);
@@ -528,11 +542,7 @@ static void native_machine_emergency_restart(void)
 			break;
 
 		case BOOT_EFI:
-			if (efi_enabled(EFI_RUNTIME_SERVICES))
-				efi.reset_system(reboot_mode == REBOOT_WARM ?
-						 EFI_RESET_WARM :
-						 EFI_RESET_COLD,
-						 EFI_SUCCESS, 0, NULL);
+			efi_reboot(reboot_mode, NULL);
 			reboot_type = BOOT_BIOS;
 			break;
 
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 2a26819bb6a..80eab01c1a6 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail)
 
 void arch_remove_reservations(struct resource *avail)
 {
-	/* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+	/*
+	 * Trim out BIOS area (high 2MB) and E820 regions. We do not remove
+	 * the low 1MB unconditionally, as this area is needed for some ISA
+	 * cards requiring a memory range, e.g. the i82365 PCMCIA controller.
+	 */
 	if (avail->flags & IORESOURCE_MEM) {
-		if (avail->start < BIOS_END)
-			avail->start = BIOS_END;
 		resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
 
 		remove_e820_regions(avail);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 78a0e629892..41ead8d3bc0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -924,10 +924,10 @@ void __init setup_arch(char **cmdline_p)
 #endif
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
-		     "EL32", 4)) {
+		     EFI32_LOADER_SIGNATURE, 4)) {
 		set_bit(EFI_BOOT, &efi.flags);
 	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
-		     "EL64", 4)) {
+		     EFI64_LOADER_SIGNATURE, 4)) {
 		set_bit(EFI_BOOT, &efi.flags);
 		set_bit(EFI_64BIT, &efi.flags);
 	}
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index a0da58db43a..2851d63c120 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -363,7 +363,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 		/* Set up to return from userspace.  */
 		restorer = current->mm->context.vdso +
-			selected_vdso32->sym___kernel_sigreturn;
+			selected_vdso32->sym___kernel_rt_sigreturn;
 		if (ksig->ka.sa.sa_flags & SA_RESTORER)
 			restorer = ksig->ka.sa.sa_restorer;
 		put_user_ex(restorer, &frame->pretcode);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index f73b5d435bd..0d0e922fafc 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
+#include <linux/uprobes.h>
 #include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
@@ -106,7 +107,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 	preempt_count_dec();
 }
 
-static int __kprobes
+static nokprobe_inline int
 do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 		  struct pt_regs *regs,	long error_code)
 {
@@ -136,7 +137,38 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 	return -1;
 }
 
-static void __kprobes
+static siginfo_t *fill_trap_info(struct pt_regs *regs, int signr, int trapnr,
+				siginfo_t *info)
+{
+	unsigned long siaddr;
+	int sicode;
+
+	switch (trapnr) {
+	default:
+		return SEND_SIG_PRIV;
+
+	case X86_TRAP_DE:
+		sicode = FPE_INTDIV;
+		siaddr = uprobe_get_trap_addr(regs);
+		break;
+	case X86_TRAP_UD:
+		sicode = ILL_ILLOPN;
+		siaddr = uprobe_get_trap_addr(regs);
+		break;
+	case X86_TRAP_AC:
+		sicode = BUS_ADRALN;
+		siaddr = 0;
+		break;
+	}
+
+	info->si_signo = signr;
+	info->si_errno = 0;
+	info->si_code = sicode;
+	info->si_addr = (void __user *)siaddr;
+	return info;
+}
+
+static void
 do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 	long error_code, siginfo_t *info)
 {
@@ -168,60 +200,43 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 	}
 #endif
 
-	if (info)
-		force_sig_info(signr, info, tsk);
-	else
-		force_sig(signr, tsk);
+	force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk);
 }
+NOKPROBE_SYMBOL(do_trap);
 
-#define DO_ERROR(trapnr, signr, str, name)				\
-dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
-{									\
-	enum ctx_state prev_state;					\
-									\
-	prev_state = exception_enter();					\
-	if (notify_die(DIE_TRAP, str, regs, error_code,			\
-			trapnr, signr) == NOTIFY_STOP) {		\
-		exception_exit(prev_state);				\
-		return;							\
-	}								\
-	conditional_sti(regs);						\
-	do_trap(trapnr, signr, str, regs, error_code, NULL);		\
-	exception_exit(prev_state);					\
+static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
+			  unsigned long trapnr, int signr)
+{
+	enum ctx_state prev_state = exception_enter();
+	siginfo_t info;
+
+	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
+			NOTIFY_STOP) {
+		conditional_sti(regs);
+		do_trap(trapnr, signr, str, regs, error_code,
+			fill_trap_info(regs, signr, trapnr, &info));
+	}
+
+	exception_exit(prev_state);
 }
 
-#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr)		\
+#define DO_ERROR(trapnr, signr, str, name)				\
 dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 {									\
-	siginfo_t info;							\
-	enum ctx_state prev_state;					\
-									\
-	info.si_signo = signr;						\
-	info.si_errno = 0;						\
-	info.si_code = sicode;						\
-	info.si_addr = (void __user *)siaddr;				\
-	prev_state = exception_enter();					\
-	if (notify_die(DIE_TRAP, str, regs, error_code,			\
-			trapnr, signr) == NOTIFY_STOP) {		\
-		exception_exit(prev_state);				\
-		return;							\
-	}								\
-	conditional_sti(regs);						\
-	do_trap(trapnr, signr, str, regs, error_code, &info);		\
-	exception_exit(prev_state);					\
+	do_error_trap(regs, error_code, str, trapnr, signr);		\
 }
 
-DO_ERROR_INFO(X86_TRAP_DE,     SIGFPE,  "divide error",			divide_error,		     FPE_INTDIV, regs->ip )
-DO_ERROR     (X86_TRAP_OF,     SIGSEGV, "overflow",			overflow					  )
-DO_ERROR     (X86_TRAP_BR,     SIGSEGV, "bounds",			bounds						  )
-DO_ERROR_INFO(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op,		     ILL_ILLOPN, regs->ip )
-DO_ERROR     (X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",	coprocessor_segment_overrun			  )
-DO_ERROR     (X86_TRAP_TS,     SIGSEGV, "invalid TSS",			invalid_TSS					  )
-DO_ERROR     (X86_TRAP_NP,     SIGBUS,  "segment not present",		segment_not_present				  )
+DO_ERROR(X86_TRAP_DE,     SIGFPE,  "divide error",		divide_error)
+DO_ERROR(X86_TRAP_OF,     SIGSEGV, "overflow",			overflow)
+DO_ERROR(X86_TRAP_BR,     SIGSEGV, "bounds",			bounds)
+DO_ERROR(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op)
+DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",coprocessor_segment_overrun)
+DO_ERROR(X86_TRAP_TS,     SIGSEGV, "invalid TSS",		invalid_TSS)
+DO_ERROR(X86_TRAP_NP,     SIGBUS,  "segment not present",	segment_not_present)
 #ifdef CONFIG_X86_32
-DO_ERROR     (X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment					  )
+DO_ERROR(X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment)
 #endif
-DO_ERROR_INFO(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check,	     BUS_ADRALN, 0	  )
+DO_ERROR(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check)
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
@@ -263,7 +278,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 }
 #endif
 
-dotraplinkage void __kprobes
+dotraplinkage void
 do_general_protection(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk;
@@ -305,13 +320,14 @@ do_general_protection(struct pt_regs *regs, long error_code)
 		pr_cont("\n");
 	}
 
-	force_sig(SIGSEGV, tsk);
+	force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
 exit:
 	exception_exit(prev_state);
 }
+NOKPROBE_SYMBOL(do_general_protection);
 
 /* May run on IST stack. */
-dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
+dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 {
 	enum ctx_state prev_state;
 
@@ -334,6 +350,11 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
 		goto exit;
 #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
 
+#ifdef CONFIG_KPROBES
+	if (kprobe_int3_handler(regs))
+		goto exit;
+#endif
+
 	if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 			SIGTRAP) == NOTIFY_STOP)
 		goto exit;
@@ -350,6 +371,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
 exit:
 	exception_exit(prev_state);
 }
+NOKPROBE_SYMBOL(do_int3);
 
 #ifdef CONFIG_X86_64
 /*
@@ -357,7 +379,7 @@ exit:
  * for scheduling or signal handling. The actual stack switch is done in
  * entry.S
  */
-asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
+asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
 	struct pt_regs *regs = eregs;
 	/* Did already sync */
@@ -376,6 +398,7 @@ asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 		*regs = *eregs;
 	return regs;
 }
+NOKPROBE_SYMBOL(sync_regs);
 #endif
 
 /*
@@ -402,7 +425,7 @@ asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
  *
  * May run on IST stack.
  */
-dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
+dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
 	enum ctx_state prev_state;
@@ -440,6 +463,11 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	/* Store the virtualized DR6 value */
 	tsk->thread.debugreg6 = dr6;
 
+#ifdef CONFIG_KPROBES
+	if (kprobe_debug_handler(regs))
+		goto exit;
+#endif
+
 	if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code,
 							SIGTRAP) == NOTIFY_STOP)
 		goto exit;
@@ -482,13 +510,14 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 exit:
 	exception_exit(prev_state);
 }
+NOKPROBE_SYMBOL(do_debug);
 
 /*
  * Note that we play around with the 'TS' bit in an attempt to get
  * the correct behaviour even in the presence of the asynchronous
  * IRQ13 behaviour
  */
-void math_error(struct pt_regs *regs, int error_code, int trapnr)
+static void math_error(struct pt_regs *regs, int error_code, int trapnr)
 {
 	struct task_struct *task = current;
 	siginfo_t info;
@@ -518,7 +547,7 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
 	task->thread.error_code = error_code;
 	info.si_signo = SIGFPE;
 	info.si_errno = 0;
-	info.si_addr = (void __user *)regs->ip;
+	info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
 	if (trapnr == X86_TRAP_MF) {
 		unsigned short cwd, swd;
 		/*
@@ -645,7 +674,7 @@ void math_state_restore(void)
 	 */
 	if (unlikely(restore_fpu_checking(tsk))) {
 		drop_init_fpu(tsk);
-		force_sig(SIGSEGV, tsk);
+		force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
 		return;
 	}
 
@@ -653,7 +682,7 @@ void math_state_restore(void)
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 
-dotraplinkage void __kprobes
+dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
 	enum ctx_state prev_state;
@@ -679,6 +708,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 #endif
 	exception_exit(prev_state);
 }
+NOKPROBE_SYMBOL(do_device_not_available);
 
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 57e5ce126d5..56b0c338061 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -234,9 +234,6 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 	return ns;
 }
 
-/* XXX surely we already have this someplace in the kernel?! */
-#define DIV_ROUND(n, d) (((n) + ((d) / 2)) / (d))
-
 static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 {
 	unsigned long long tsc_now, ns_now;
@@ -259,7 +256,9 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 	 * time function is continuous; see the comment near struct
 	 * cyc2ns_data.
 	 */
-	data->cyc2ns_mul = DIV_ROUND(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, cpu_khz);
+	data->cyc2ns_mul =
+		DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR,
+				  cpu_khz);
 	data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
 	data->cyc2ns_offset = ns_now -
 		mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
@@ -920,9 +919,9 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
 			mark_tsc_unstable("cpufreq changes");
-	}
 
-	set_cyc2ns_scale(tsc_khz, freq->cpu);
+		set_cyc2ns_scale(tsc_khz, freq->cpu);
+	}
 
 	return 0;
 }
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index ace22916ade..5d1cbfe4ae5 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -32,20 +32,20 @@
 
 /* Post-execution fixups. */
 
-/* No fixup needed */
-#define UPROBE_FIX_NONE		0x0
-
 /* Adjust IP back to vicinity of actual insn */
-#define UPROBE_FIX_IP		0x1
+#define UPROBE_FIX_IP		0x01
 
 /* Adjust the return address of a call insn */
-#define UPROBE_FIX_CALL	0x2
+#define UPROBE_FIX_CALL		0x02
 
 /* Instruction will modify TF, don't change it */
-#define UPROBE_FIX_SETF	0x4
+#define UPROBE_FIX_SETF		0x04
 
-#define UPROBE_FIX_RIP_AX	0x8000
-#define UPROBE_FIX_RIP_CX	0x4000
+#define UPROBE_FIX_RIP_SI	0x08
+#define UPROBE_FIX_RIP_DI	0x10
+#define UPROBE_FIX_RIP_BX	0x20
+#define UPROBE_FIX_RIP_MASK	\
+	(UPROBE_FIX_RIP_SI | UPROBE_FIX_RIP_DI | UPROBE_FIX_RIP_BX)
 
 #define	UPROBE_TRAP_NR		UINT_MAX
 
@@ -67,6 +67,7 @@
  * to keep gcc from statically optimizing it out, as variable_test_bit makes
  * some versions of gcc to think only *(unsigned long*) is used.
  */
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 static volatile u32 good_insns_32[256 / 32] = {
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 	/*      ----------------------------------------------         */
@@ -89,33 +90,12 @@ static volatile u32 good_insns_32[256 / 32] = {
 	/*      ----------------------------------------------         */
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 };
+#else
+#define good_insns_32	NULL
+#endif
 
-/* Using this for both 64-bit and 32-bit apps */
-static volatile u32 good_2byte_insns[256 / 32] = {
-	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
-	/*      ----------------------------------------------         */
-	W(0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1) | /* 00 */
-	W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* 10 */
-	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */
-	W(0x30, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
-	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
-	W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
-	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 60 */
-	W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */
-	W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
-	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
-	W(0xa0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1) | /* a0 */
-	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
-	W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */
-	W(0xd0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
-	W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* e0 */
-	W(0xf0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0)   /* f0 */
-	/*      ----------------------------------------------         */
-	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
-};
-
-#ifdef CONFIG_X86_64
 /* Good-instruction tables for 64-bit apps */
+#if defined(CONFIG_X86_64)
 static volatile u32 good_insns_64[256 / 32] = {
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 	/*      ----------------------------------------------         */
@@ -138,7 +118,33 @@ static volatile u32 good_insns_64[256 / 32] = {
 	/*      ----------------------------------------------         */
 	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
 };
+#else
+#define good_insns_64	NULL
 #endif
+
+/* Using this for both 64-bit and 32-bit apps */
+static volatile u32 good_2byte_insns[256 / 32] = {
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
+	/*      ----------------------------------------------         */
+	W(0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1) | /* 00 */
+	W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* 10 */
+	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */
+	W(0x30, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
+	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
+	W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
+	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 60 */
+	W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */
+	W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
+	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
+	W(0xa0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1) | /* a0 */
+	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
+	W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */
+	W(0xd0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
+	W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* e0 */
+	W(0xf0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0)   /* f0 */
+	/*      ----------------------------------------------         */
+	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f         */
+};
 #undef W
 
 /*
@@ -209,16 +215,25 @@ static bool is_prefix_bad(struct insn *insn)
 	return false;
 }
 
-static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn)
+static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool x86_64)
 {
-	insn_init(insn, auprobe->insn, false);
+	u32 volatile *good_insns;
+
+	insn_init(insn, auprobe->insn, x86_64);
+	/* has the side-effect of processing the entire instruction */
+	insn_get_length(insn);
+	if (WARN_ON_ONCE(!insn_complete(insn)))
+		return -ENOEXEC;
 
-	/* Skip good instruction prefixes; reject "bad" ones. */
-	insn_get_opcode(insn);
 	if (is_prefix_bad(insn))
 		return -ENOTSUPP;
 
-	if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_32))
+	if (x86_64)
+		good_insns = good_insns_64;
+	else
+		good_insns = good_insns_32;
+
+	if (test_bit(OPCODE1(insn), (unsigned long *)good_insns))
 		return 0;
 
 	if (insn->opcode.nbytes == 2) {
@@ -230,14 +245,18 @@ static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn)
 }
 
 #ifdef CONFIG_X86_64
+static inline bool is_64bit_mm(struct mm_struct *mm)
+{
+	return	!config_enabled(CONFIG_IA32_EMULATION) ||
+		!(mm->context.ia32_compat == TIF_IA32);
+}
 /*
  * If arch_uprobe->insn doesn't use rip-relative addressing, return
  * immediately.  Otherwise, rewrite the instruction so that it accesses
  * its memory operand indirectly through a scratch register.  Set
- * arch_uprobe->fixups and arch_uprobe->rip_rela_target_address
- * accordingly.  (The contents of the scratch register will be saved
- * before we single-step the modified instruction, and restored
- * afterward.)
+ * defparam->fixups accordingly. (The contents of the scratch register
+ * will be saved before we single-step the modified instruction,
+ * and restored afterward).
  *
  * We do this because a rip-relative instruction can access only a
  * relatively small area (+/- 2 GB from the instruction), and the XOL
@@ -248,164 +267,192 @@ static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn)
  *
  * Some useful facts about rip-relative instructions:
  *
- *  - There's always a modrm byte.
+ *  - There's always a modrm byte with bit layout "00 reg 101".
  *  - There's never a SIB byte.
  *  - The displacement is always 4 bytes.
+ *  - REX.B=1 bit in REX prefix, which normally extends r/m field,
+ *    has no effect on rip-relative mode. It doesn't make modrm byte
+ *    with r/m=101 refer to register 1101 = R13.
  */
-static void
-handle_riprel_insn(struct arch_uprobe *auprobe, struct insn *insn)
+static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
 {
 	u8 *cursor;
 	u8 reg;
+	u8 reg2;
 
 	if (!insn_rip_relative(insn))
 		return;
 
 	/*
-	 * insn_rip_relative() would have decoded rex_prefix, modrm.
+	 * insn_rip_relative() would have decoded rex_prefix, vex_prefix, modrm.
 	 * Clear REX.b bit (extension of MODRM.rm field):
-	 * we want to encode rax/rcx, not r8/r9.
+	 * we want to encode low numbered reg, not r8+.
 	 */
 	if (insn->rex_prefix.nbytes) {
 		cursor = auprobe->insn + insn_offset_rex_prefix(insn);
-		*cursor &= 0xfe;	/* Clearing REX.B bit */
+		/* REX byte has 0100wrxb layout, clearing REX.b bit */
+		*cursor &= 0xfe;
+	}
+	/*
+	 * Similar treatment for VEX3 prefix.
+	 * TODO: add XOP/EVEX treatment when insn decoder supports them
+	 */
+	if (insn->vex_prefix.nbytes == 3) {
+		/*
+		 * vex2:     c5    rvvvvLpp   (has no b bit)
+		 * vex3/xop: c4/8f rxbmmmmm wvvvvLpp
+		 * evex:     62    rxbR00mm wvvvv1pp zllBVaaa
+		 *   (evex will need setting of both b and x since
+		 *   in non-sib encoding evex.x is 4th bit of MODRM.rm)
+		 * Setting VEX3.b (setting because it has inverted meaning):
+		 */
+		cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1;
+		*cursor |= 0x20;
 	}
 
 	/*
+	 * Convert from rip-relative addressing to register-relative addressing
+	 * via a scratch register.
+	 *
+	 * This is tricky since there are insns with modrm byte
+	 * which also use registers not encoded in modrm byte:
+	 * [i]div/[i]mul: implicitly use dx:ax
+	 * shift ops: implicitly use cx
+	 * cmpxchg: implicitly uses ax
+	 * cmpxchg8/16b: implicitly uses dx:ax and bx:cx
+	 *   Encoding: 0f c7/1 modrm
+	 *   The code below thinks that reg=1 (cx), chooses si as scratch.
+	 * mulx: implicitly uses dx: mulx r/m,r1,r2 does r1:r2 = dx * r/m.
+	 *   First appeared in Haswell (BMI2 insn). It is vex-encoded.
+	 *   Example where none of bx,cx,dx can be used as scratch reg:
+	 *   c4 e2 63 f6 0d disp32   mulx disp32(%rip),%ebx,%ecx
+	 * [v]pcmpistri: implicitly uses cx, xmm0
+	 * [v]pcmpistrm: implicitly uses xmm0
+	 * [v]pcmpestri: implicitly uses ax, dx, cx, xmm0
+	 * [v]pcmpestrm: implicitly uses ax, dx, xmm0
+	 *   Evil SSE4.2 string comparison ops from hell.
+	 * maskmovq/[v]maskmovdqu: implicitly uses (ds:rdi) as destination.
+	 *   Encoding: 0f f7 modrm, 66 0f f7 modrm, vex-encoded: c5 f9 f7 modrm.
+	 *   Store op1, byte-masked by op2 msb's in each byte, to (ds:rdi).
+	 *   AMD says it has no 3-operand form (vex.vvvv must be 1111)
+	 *   and that it can have only register operands, not mem
+	 *   (its modrm byte must have mode=11).
+	 *   If these restrictions will ever be lifted,
+	 *   we'll need code to prevent selection of di as scratch reg!
+	 *
+	 * Summary: I don't know any insns with modrm byte which
+	 * use SI register implicitly. DI register is used only
+	 * by one insn (maskmovq) and BX register is used
+	 * only by one too (cmpxchg8b).
+	 * BP is stack-segment based (may be a problem?).
+	 * AX, DX, CX are off-limits (many implicit users).
+	 * SP is unusable (it's stack pointer - think about "pop mem";
+	 * also, rsp+disp32 needs sib encoding -> insn length change).
+	 */
+
+	reg = MODRM_REG(insn);	/* Fetch modrm.reg */
+	reg2 = 0xff;		/* Fetch vex.vvvv */
+	if (insn->vex_prefix.nbytes == 2)
+		reg2 = insn->vex_prefix.bytes[1];
+	else if (insn->vex_prefix.nbytes == 3)
+		reg2 = insn->vex_prefix.bytes[2];
+	/*
+	 * TODO: add XOP, EXEV vvvv reading.
+	 *
+	 * vex.vvvv field is in bits 6-3, bits are inverted.
+	 * But in 32-bit mode, high-order bit may be ignored.
+	 * Therefore, let's consider only 3 low-order bits.
+	 */
+	reg2 = ((reg2 >> 3) & 0x7) ^ 0x7;
+	/*
+	 * Register numbering is ax,cx,dx,bx, sp,bp,si,di, r8..r15.
+	 *
+	 * Choose scratch reg. Order is important: must not select bx
+	 * if we can use si (cmpxchg8b case!)
+	 */
+	if (reg != 6 && reg2 != 6) {
+		reg2 = 6;
+		auprobe->defparam.fixups |= UPROBE_FIX_RIP_SI;
+	} else if (reg != 7 && reg2 != 7) {
+		reg2 = 7;
+		auprobe->defparam.fixups |= UPROBE_FIX_RIP_DI;
+		/* TODO (paranoia): force maskmovq to not use di */
+	} else {
+		reg2 = 3;
+		auprobe->defparam.fixups |= UPROBE_FIX_RIP_BX;
+	}
+	/*
 	 * Point cursor at the modrm byte.  The next 4 bytes are the
 	 * displacement.  Beyond the displacement, for some instructions,
 	 * is the immediate operand.
 	 */
 	cursor = auprobe->insn + insn_offset_modrm(insn);
-	insn_get_length(insn);
-
 	/*
-	 * Convert from rip-relative addressing to indirect addressing
-	 * via a scratch register.  Change the r/m field from 0x5 (%rip)
-	 * to 0x0 (%rax) or 0x1 (%rcx), and squeeze out the offset field.
+	 * Change modrm from "00 reg 101" to "10 reg reg2". Example:
+	 * 89 05 disp32  mov %eax,disp32(%rip) becomes
+	 * 89 86 disp32  mov %eax,disp32(%rsi)
 	 */
-	reg = MODRM_REG(insn);
-	if (reg == 0) {
-		/*
-		 * The register operand (if any) is either the A register
-		 * (%rax, %eax, etc.) or (if the 0x4 bit is set in the
-		 * REX prefix) %r8.  In any case, we know the C register
-		 * is NOT the register operand, so we use %rcx (register
-		 * #1) for the scratch register.
-		 */
-		auprobe->fixups = UPROBE_FIX_RIP_CX;
-		/* Change modrm from 00 000 101 to 00 000 001. */
-		*cursor = 0x1;
-	} else {
-		/* Use %rax (register #0) for the scratch register. */
-		auprobe->fixups = UPROBE_FIX_RIP_AX;
-		/* Change modrm from 00 xxx 101 to 00 xxx 000 */
-		*cursor = (reg << 3);
-	}
-
-	/* Target address = address of next instruction + (signed) offset */
-	auprobe->rip_rela_target_address = (long)insn->length + insn->displacement.value;
+	*cursor = 0x80 | (reg << 3) | reg2;
+}
 
-	/* Displacement field is gone; slide immediate field (if any) over. */
-	if (insn->immediate.nbytes) {
-		cursor++;
-		memmove(cursor, cursor + insn->displacement.nbytes, insn->immediate.nbytes);
-	}
+static inline unsigned long *
+scratch_reg(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	if (auprobe->defparam.fixups & UPROBE_FIX_RIP_SI)
+		return &regs->si;
+	if (auprobe->defparam.fixups & UPROBE_FIX_RIP_DI)
+		return &regs->di;
+	return &regs->bx;
 }
 
 /*
  * If we're emulating a rip-relative instruction, save the contents
  * of the scratch register and store the target address in that register.
  */
-static void
-pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs,
-				struct arch_uprobe_task *autask)
-{
-	if (auprobe->fixups & UPROBE_FIX_RIP_AX) {
-		autask->saved_scratch_register = regs->ax;
-		regs->ax = current->utask->vaddr;
-		regs->ax += auprobe->rip_rela_target_address;
-	} else if (auprobe->fixups & UPROBE_FIX_RIP_CX) {
-		autask->saved_scratch_register = regs->cx;
-		regs->cx = current->utask->vaddr;
-		regs->cx += auprobe->rip_rela_target_address;
-	}
-}
-
-static void
-handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs, long *correction)
+static void riprel_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
-	if (auprobe->fixups & (UPROBE_FIX_RIP_AX | UPROBE_FIX_RIP_CX)) {
-		struct arch_uprobe_task *autask;
-
-		autask = &current->utask->autask;
-		if (auprobe->fixups & UPROBE_FIX_RIP_AX)
-			regs->ax = autask->saved_scratch_register;
-		else
-			regs->cx = autask->saved_scratch_register;
+	if (auprobe->defparam.fixups & UPROBE_FIX_RIP_MASK) {
+		struct uprobe_task *utask = current->utask;
+		unsigned long *sr = scratch_reg(auprobe, regs);
 
-		/*
-		 * The original instruction includes a displacement, and so
-		 * is 4 bytes longer than what we've just single-stepped.
-		 * Caller may need to apply other fixups to handle stuff
-		 * like "jmpq *...(%rip)" and "callq *...(%rip)".
-		 */
-		if (correction)
-			*correction += 4;
+		utask->autask.saved_scratch_register = *sr;
+		*sr = utask->vaddr + auprobe->defparam.ilen;
 	}
 }
 
-static int validate_insn_64bits(struct arch_uprobe *auprobe, struct insn *insn)
+static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
-	insn_init(insn, auprobe->insn, true);
-
-	/* Skip good instruction prefixes; reject "bad" ones. */
-	insn_get_opcode(insn);
-	if (is_prefix_bad(insn))
-		return -ENOTSUPP;
+	if (auprobe->defparam.fixups & UPROBE_FIX_RIP_MASK) {
+		struct uprobe_task *utask = current->utask;
+		unsigned long *sr = scratch_reg(auprobe, regs);
 
-	if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_64))
-		return 0;
-
-	if (insn->opcode.nbytes == 2) {
-		if (test_bit(OPCODE2(insn), (unsigned long *)good_2byte_insns))
-			return 0;
+		*sr = utask->autask.saved_scratch_register;
 	}
-	return -ENOTSUPP;
 }
-
-static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn)
+#else /* 32-bit: */
+static inline bool is_64bit_mm(struct mm_struct *mm)
 {
-	if (mm->context.ia32_compat)
-		return validate_insn_32bits(auprobe, insn);
-	return validate_insn_64bits(auprobe, insn);
+	return false;
 }
-#else /* 32-bit: */
 /*
  * No RIP-relative addressing on 32-bit
  */
-static void handle_riprel_insn(struct arch_uprobe *auprobe, struct insn *insn)
+static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn)
 {
 }
-static void pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs,
-				struct arch_uprobe_task *autask)
+static void riprel_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 }
-static void handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs,
-					long *correction)
+static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 }
-
-static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm,  struct insn *insn)
-{
-	return validate_insn_32bits(auprobe, insn);
-}
 #endif /* CONFIG_X86_64 */
 
 struct uprobe_xol_ops {
 	bool	(*emulate)(struct arch_uprobe *, struct pt_regs *);
 	int	(*pre_xol)(struct arch_uprobe *, struct pt_regs *);
 	int	(*post_xol)(struct arch_uprobe *, struct pt_regs *);
+	void	(*abort)(struct arch_uprobe *, struct pt_regs *);
 };
 
 static inline int sizeof_long(void)
@@ -415,50 +462,67 @@ static inline int sizeof_long(void)
 
 static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
-	pre_xol_rip_insn(auprobe, regs, &current->utask->autask);
+	riprel_pre_xol(auprobe, regs);
 	return 0;
 }
 
-/*
- * Adjust the return address pushed by a call insn executed out of line.
- */
-static int adjust_ret_addr(unsigned long sp, long correction)
+static int push_ret_address(struct pt_regs *regs, unsigned long ip)
 {
-	int rasize = sizeof_long();
-	long ra;
-
-	if (copy_from_user(&ra, (void __user *)sp, rasize))
-		return -EFAULT;
+	unsigned long new_sp = regs->sp - sizeof_long();
 
-	ra += correction;
-	if (copy_to_user((void __user *)sp, &ra, rasize))
+	if (copy_to_user((void __user *)new_sp, &ip, sizeof_long()))
 		return -EFAULT;
 
+	regs->sp = new_sp;
 	return 0;
 }
 
+/*
+ * We have to fix things up as follows:
+ *
+ * Typically, the new ip is relative to the copied instruction.  We need
+ * to make it relative to the original instruction (FIX_IP).  Exceptions
+ * are return instructions and absolute or indirect jump or call instructions.
+ *
+ * If the single-stepped instruction was a call, the return address that
+ * is atop the stack is the address following the copied instruction.  We
+ * need to make it the address following the original instruction (FIX_CALL).
+ *
+ * If the original instruction was a rip-relative instruction such as
+ * "movl %edx,0xnnnn(%rip)", we have instead executed an equivalent
+ * instruction using a scratch register -- e.g., "movl %edx,0xnnnn(%rsi)".
+ * We need to restore the contents of the scratch register
+ * (FIX_RIP_reg).
+ */
 static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	struct uprobe_task *utask = current->utask;
-	long correction = (long)(utask->vaddr - utask->xol_vaddr);
 
-	handle_riprel_post_xol(auprobe, regs, &correction);
-	if (auprobe->fixups & UPROBE_FIX_IP)
+	riprel_post_xol(auprobe, regs);
+	if (auprobe->defparam.fixups & UPROBE_FIX_IP) {
+		long correction = utask->vaddr - utask->xol_vaddr;
 		regs->ip += correction;
-
-	if (auprobe->fixups & UPROBE_FIX_CALL) {
-		if (adjust_ret_addr(regs->sp, correction)) {
-			regs->sp += sizeof_long();
+	} else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) {
+		regs->sp += sizeof_long(); /* Pop incorrect return address */
+		if (push_ret_address(regs, utask->vaddr + auprobe->defparam.ilen))
 			return -ERESTART;
-		}
 	}
+	/* popf; tell the caller to not touch TF */
+	if (auprobe->defparam.fixups & UPROBE_FIX_SETF)
+		utask->autask.saved_tf = true;
 
 	return 0;
 }
 
+static void default_abort_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	riprel_post_xol(auprobe, regs);
+}
+
 static struct uprobe_xol_ops default_xol_ops = {
 	.pre_xol  = default_pre_xol_op,
 	.post_xol = default_post_xol_op,
+	.abort	  = default_abort_op,
 };
 
 static bool branch_is_call(struct arch_uprobe *auprobe)
@@ -520,7 +584,6 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	unsigned long offs = (long)auprobe->branch.offs;
 
 	if (branch_is_call(auprobe)) {
-		unsigned long new_sp = regs->sp - sizeof_long();
 		/*
 		 * If it fails we execute this (mangled, see the comment in
 		 * branch_clear_offset) insn out-of-line. In the likely case
@@ -530,9 +593,8 @@ static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		 *
 		 * But there is corner case, see the comment in ->post_xol().
 		 */
-		if (copy_to_user((void __user *)new_sp, &new_ip, sizeof_long()))
+		if (push_ret_address(regs, new_ip))
 			return false;
-		regs->sp = new_sp;
 	} else if (!check_jmp_cond(auprobe, regs)) {
 		offs = 0;
 	}
@@ -583,11 +645,7 @@ static struct uprobe_xol_ops branch_xol_ops = {
 static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 {
 	u8 opc1 = OPCODE1(insn);
-
-	/* has the side-effect of processing the entire instruction */
-	insn_get_length(insn);
-	if (WARN_ON_ONCE(!insn_complete(insn)))
-		return -ENOEXEC;
+	int i;
 
 	switch (opc1) {
 	case 0xeb:	/* jmp 8 */
@@ -612,6 +670,16 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 			return -ENOSYS;
 	}
 
+	/*
+	 * 16-bit overrides such as CALLW (66 e8 nn nn) are not supported.
+	 * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix.
+	 * No one uses these insns, reject any branch insns with such prefix.
+	 */
+	for (i = 0; i < insn->prefixes.nbytes; i++) {
+		if (insn->prefixes.bytes[i] == 0x66)
+			return -ENOTSUPP;
+	}
+
 	auprobe->branch.opc1 = opc1;
 	auprobe->branch.ilen = insn->length;
 	auprobe->branch.offs = insn->immediate.value;
@@ -630,10 +698,10 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr)
 {
 	struct insn insn;
-	bool fix_ip = true, fix_call = false;
+	u8 fix_ip_or_call = UPROBE_FIX_IP;
 	int ret;
 
-	ret = validate_insn_bits(auprobe, mm, &insn);
+	ret = uprobe_init_insn(auprobe, &insn, is_64bit_mm(mm));
 	if (ret)
 		return ret;
 
@@ -642,44 +710,39 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
 		return ret;
 
 	/*
-	 * Figure out which fixups arch_uprobe_post_xol() will need to perform,
-	 * and annotate arch_uprobe->fixups accordingly. To start with, ->fixups
-	 * is either zero or it reflects rip-related fixups.
+	 * Figure out which fixups default_post_xol_op() will need to perform,
+	 * and annotate defparam->fixups accordingly.
 	 */
 	switch (OPCODE1(&insn)) {
 	case 0x9d:		/* popf */
-		auprobe->fixups |= UPROBE_FIX_SETF;
+		auprobe->defparam.fixups |= UPROBE_FIX_SETF;
 		break;
 	case 0xc3:		/* ret or lret -- ip is correct */
 	case 0xcb:
 	case 0xc2:
 	case 0xca:
-		fix_ip = false;
+	case 0xea:		/* jmp absolute -- ip is correct */
+		fix_ip_or_call = 0;
 		break;
 	case 0x9a:		/* call absolute - Fix return addr, not ip */
-		fix_call = true;
-		fix_ip = false;
-		break;
-	case 0xea:		/* jmp absolute -- ip is correct */
-		fix_ip = false;
+		fix_ip_or_call = UPROBE_FIX_CALL;
 		break;
 	case 0xff:
-		insn_get_modrm(&insn);
 		switch (MODRM_REG(&insn)) {
 		case 2: case 3:			/* call or lcall, indirect */
-			fix_call = true;
+			fix_ip_or_call = UPROBE_FIX_CALL;
+			break;
 		case 4: case 5:			/* jmp or ljmp, indirect */
-			fix_ip = false;
+			fix_ip_or_call = 0;
+			break;
 		}
 		/* fall through */
 	default:
-		handle_riprel_insn(auprobe, &insn);
+		riprel_analyze(auprobe, &insn);
 	}
 
-	if (fix_ip)
-		auprobe->fixups |= UPROBE_FIX_IP;
-	if (fix_call)
-		auprobe->fixups |= UPROBE_FIX_CALL;
+	auprobe->defparam.ilen = insn.length;
+	auprobe->defparam.fixups |= fix_ip_or_call;
 
 	auprobe->ops = &default_xol_ops;
 	return 0;
@@ -694,6 +757,12 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	struct uprobe_task *utask = current->utask;
 
+	if (auprobe->ops->pre_xol) {
+		int err = auprobe->ops->pre_xol(auprobe, regs);
+		if (err)
+			return err;
+	}
+
 	regs->ip = utask->xol_vaddr;
 	utask->autask.saved_trap_nr = current->thread.trap_nr;
 	current->thread.trap_nr = UPROBE_TRAP_NR;
@@ -703,8 +772,6 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	if (test_tsk_thread_flag(current, TIF_BLOCKSTEP))
 		set_task_blockstep(current, false);
 
-	if (auprobe->ops->pre_xol)
-		return auprobe->ops->pre_xol(auprobe, regs);
 	return 0;
 }
 
@@ -732,56 +799,42 @@ bool arch_uprobe_xol_was_trapped(struct task_struct *t)
  * single-step, we single-stepped a copy of the instruction.
  *
  * This function prepares to resume execution after the single-step.
- * We have to fix things up as follows:
- *
- * Typically, the new ip is relative to the copied instruction.  We need
- * to make it relative to the original instruction (FIX_IP).  Exceptions
- * are return instructions and absolute or indirect jump or call instructions.
- *
- * If the single-stepped instruction was a call, the return address that
- * is atop the stack is the address following the copied instruction.  We
- * need to make it the address following the original instruction (FIX_CALL).
- *
- * If the original instruction was a rip-relative instruction such as
- * "movl %edx,0xnnnn(%rip)", we have instead executed an equivalent
- * instruction using a scratch register -- e.g., "movl %edx,(%rax)".
- * We need to restore the contents of the scratch register and adjust
- * the ip, keeping in mind that the instruction we executed is 4 bytes
- * shorter than the original instruction (since we squeezed out the offset
- * field).  (FIX_RIP_AX or FIX_RIP_CX)
  */
 int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	struct uprobe_task *utask = current->utask;
+	bool send_sigtrap = utask->autask.saved_tf;
+	int err = 0;
 
 	WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR);
+	current->thread.trap_nr = utask->autask.saved_trap_nr;
 
 	if (auprobe->ops->post_xol) {
-		int err = auprobe->ops->post_xol(auprobe, regs);
+		err = auprobe->ops->post_xol(auprobe, regs);
 		if (err) {
-			arch_uprobe_abort_xol(auprobe, regs);
 			/*
-			 * Restart the probed insn. ->post_xol() must ensure
-			 * this is really possible if it returns -ERESTART.
+			 * Restore ->ip for restart or post mortem analysis.
+			 * ->post_xol() must not return -ERESTART unless this
+			 * is really possible.
 			 */
+			regs->ip = utask->vaddr;
 			if (err == -ERESTART)
-				return 0;
-			return err;
+				err = 0;
+			send_sigtrap = false;
 		}
 	}
-
-	current->thread.trap_nr = utask->autask.saved_trap_nr;
 	/*
 	 * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP
 	 * so we can get an extra SIGTRAP if we do not clear TF. We need
 	 * to examine the opcode to make it right.
 	 */
-	if (utask->autask.saved_tf)
+	if (send_sigtrap)
 		send_sig(SIGTRAP, current, 0);
-	else if (!(auprobe->fixups & UPROBE_FIX_SETF))
+
+	if (!utask->autask.saved_tf)
 		regs->flags &= ~X86_EFLAGS_TF;
 
-	return 0;
+	return err;
 }
 
 /* callback routine for handling exceptions. */
@@ -815,18 +868,18 @@ int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val,
 
 /*
  * This function gets called when XOL instruction either gets trapped or
- * the thread has a fatal signal, or if arch_uprobe_post_xol() failed.
- * Reset the instruction pointer to its probed address for the potential
- * restart or for post mortem analysis.
+ * the thread has a fatal signal. Reset the instruction pointer to its
+ * probed address for the potential restart or for post mortem analysis.
  */
 void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
 	struct uprobe_task *utask = current->utask;
 
-	current->thread.trap_nr = utask->autask.saved_trap_nr;
-	handle_riprel_post_xol(auprobe, regs, NULL);
-	instruction_pointer_set(regs, utask->vaddr);
+	if (auprobe->ops->abort)
+		auprobe->ops->abort(auprobe, regs);
 
+	current->thread.trap_nr = utask->autask.saved_trap_nr;
+	regs->ip = utask->vaddr;
 	/* clear TF if it was set by us in arch_uprobe_pre_xol() */
 	if (!utask->autask.saved_tf)
 		regs->flags &= ~X86_EFLAGS_TF;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index f9087315e0c..a5380590ab0 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -95,4 +95,12 @@ static inline bool guest_cpuid_has_gbpages(struct kvm_vcpu *vcpu)
 	best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
 	return best && (best->edx & bit(X86_FEATURE_GBPAGES));
 }
+
+static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ebx & bit(X86_FEATURE_RTM));
+}
 #endif
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e4e833d3d7d..56657b0bb3b 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -162,6 +162,10 @@
 #define NoWrite     ((u64)1 << 45)  /* No writeback */
 #define SrcWrite    ((u64)1 << 46)  /* Write back src operand */
 #define NoMod	    ((u64)1 << 47)  /* Mod field is ignored */
+#define Intercept   ((u64)1 << 48)  /* Has valid intercept field */
+#define CheckPerm   ((u64)1 << 49)  /* Has valid check_perm field */
+#define NoBigReal   ((u64)1 << 50)  /* No big real mode */
+#define PrivUD      ((u64)1 << 51)  /* #UD instead of #GP on CPL > 0 */
 
 #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)
 
@@ -426,6 +430,7 @@ static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt,
 		.modrm_reg  = ctxt->modrm_reg,
 		.modrm_rm   = ctxt->modrm_rm,
 		.src_val    = ctxt->src.val64,
+		.dst_val    = ctxt->dst.val64,
 		.src_bytes  = ctxt->src.bytes,
 		.dst_bytes  = ctxt->dst.bytes,
 		.ad_bytes   = ctxt->ad_bytes,
@@ -511,12 +516,6 @@ static u32 desc_limit_scaled(struct desc_struct *desc)
 	return desc->g ? (limit << 12) | 0xfff : limit;
 }
 
-static void set_seg_override(struct x86_emulate_ctxt *ctxt, int seg)
-{
-	ctxt->has_seg_override = true;
-	ctxt->seg_override = seg;
-}
-
 static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, int seg)
 {
 	if (ctxt->mode == X86EMUL_MODE_PROT64 && seg < VCPU_SREG_FS)
@@ -525,14 +524,6 @@ static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, int seg)
 	return ctxt->ops->get_cached_segment_base(ctxt, seg);
 }
 
-static unsigned seg_override(struct x86_emulate_ctxt *ctxt)
-{
-	if (!ctxt->has_seg_override)
-		return 0;
-
-	return ctxt->seg_override;
-}
-
 static int emulate_exception(struct x86_emulate_ctxt *ctxt, int vec,
 			     u32 error, bool valid)
 {
@@ -651,7 +642,12 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
 		if (!fetch && (desc.type & 8) && !(desc.type & 2))
 			goto bad;
 		lim = desc_limit_scaled(&desc);
-		if ((desc.type & 8) || !(desc.type & 4)) {
+		if ((ctxt->mode == X86EMUL_MODE_REAL) && !fetch &&
+		    (ctxt->d & NoBigReal)) {
+			/* la is between zero and 0xffff */
+			if (la > 0xffff || (u32)(la + size - 1) > 0xffff)
+				goto bad;
+		} else if ((desc.type & 8) || !(desc.type & 4)) {
 			/* expand-up segment */
 			if (addr.ea > lim || (u32)(addr.ea + size - 1) > lim)
 				goto bad;
@@ -716,68 +712,71 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
 }
 
 /*
- * Fetch the next byte of the instruction being emulated which is pointed to
- * by ctxt->_eip, then increment ctxt->_eip.
- *
- * Also prefetch the remaining bytes of the instruction without crossing page
+ * Prefetch the remaining bytes of the instruction without crossing page
  * boundary if they are not in fetch_cache yet.
  */
-static int do_insn_fetch_byte(struct x86_emulate_ctxt *ctxt, u8 *dest)
+static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size)
 {
-	struct fetch_cache *fc = &ctxt->fetch;
 	int rc;
-	int size, cur_size;
-
-	if (ctxt->_eip == fc->end) {
-		unsigned long linear;
-		struct segmented_address addr = { .seg = VCPU_SREG_CS,
-						  .ea  = ctxt->_eip };
-		cur_size = fc->end - fc->start;
-		size = min(15UL - cur_size,
-			   PAGE_SIZE - offset_in_page(ctxt->_eip));
-		rc = __linearize(ctxt, addr, size, false, true, &linear);
-		if (unlikely(rc != X86EMUL_CONTINUE))
-			return rc;
-		rc = ctxt->ops->fetch(ctxt, linear, fc->data + cur_size,
-				      size, &ctxt->exception);
-		if (unlikely(rc != X86EMUL_CONTINUE))
-			return rc;
-		fc->end += size;
-	}
-	*dest = fc->data[ctxt->_eip - fc->start];
-	ctxt->_eip++;
-	return X86EMUL_CONTINUE;
-}
+	unsigned size;
+	unsigned long linear;
+	int cur_size = ctxt->fetch.end - ctxt->fetch.data;
+	struct segmented_address addr = { .seg = VCPU_SREG_CS,
+					   .ea = ctxt->eip + cur_size };
+
+	size = 15UL ^ cur_size;
+	rc = __linearize(ctxt, addr, size, false, true, &linear);
+	if (unlikely(rc != X86EMUL_CONTINUE))
+		return rc;
 
-static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
-			 void *dest, unsigned size)
-{
-	int rc;
+	size = min_t(unsigned, size, PAGE_SIZE - offset_in_page(linear));
 
-	/* x86 instructions are limited to 15 bytes. */
-	if (unlikely(ctxt->_eip + size - ctxt->eip > 15))
+	/*
+	 * One instruction can only straddle two pages,
+	 * and one has been loaded at the beginning of
+	 * x86_decode_insn.  So, if not enough bytes
+	 * still, we must have hit the 15-byte boundary.
+	 */
+	if (unlikely(size < op_size))
 		return X86EMUL_UNHANDLEABLE;
-	while (size--) {
-		rc = do_insn_fetch_byte(ctxt, dest++);
-		if (rc != X86EMUL_CONTINUE)
-			return rc;
-	}
+	rc = ctxt->ops->fetch(ctxt, linear, ctxt->fetch.end,
+			      size, &ctxt->exception);
+	if (unlikely(rc != X86EMUL_CONTINUE))
+		return rc;
+	ctxt->fetch.end += size;
 	return X86EMUL_CONTINUE;
 }
 
+static __always_inline int do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt,
+					       unsigned size)
+{
+	if (unlikely(ctxt->fetch.end - ctxt->fetch.ptr < size))
+		return __do_insn_fetch_bytes(ctxt, size);
+	else
+		return X86EMUL_CONTINUE;
+}
+
 /* Fetch next part of the instruction being emulated. */
 #define insn_fetch(_type, _ctxt)					\
-({	unsigned long _x;						\
-	rc = do_insn_fetch(_ctxt, &_x, sizeof(_type));			\
+({	_type _x;							\
+									\
+	rc = do_insn_fetch_bytes(_ctxt, sizeof(_type));			\
 	if (rc != X86EMUL_CONTINUE)					\
 		goto done;						\
-	(_type)_x;							\
+	ctxt->_eip += sizeof(_type);					\
+	_x = *(_type __aligned(1) *) ctxt->fetch.ptr;			\
+	ctxt->fetch.ptr += sizeof(_type);				\
+	_x;								\
 })
 
 #define insn_fetch_arr(_arr, _size, _ctxt)				\
-({	rc = do_insn_fetch(_ctxt, _arr, (_size));			\
+({									\
+	rc = do_insn_fetch_bytes(_ctxt, _size);				\
 	if (rc != X86EMUL_CONTINUE)					\
 		goto done;						\
+	ctxt->_eip += (_size);						\
+	memcpy(_arr, ctxt->fetch.ptr, _size);				\
+	ctxt->fetch.ptr += (_size);					\
 })
 
 /*
@@ -1063,19 +1062,17 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 			struct operand *op)
 {
 	u8 sib;
-	int index_reg = 0, base_reg = 0, scale;
+	int index_reg, base_reg, scale;
 	int rc = X86EMUL_CONTINUE;
 	ulong modrm_ea = 0;
 
-	if (ctxt->rex_prefix) {
-		ctxt->modrm_reg = (ctxt->rex_prefix & 4) << 1;	/* REX.R */
-		index_reg = (ctxt->rex_prefix & 2) << 2; /* REX.X */
-		ctxt->modrm_rm = base_reg = (ctxt->rex_prefix & 1) << 3; /* REG.B */
-	}
+	ctxt->modrm_reg = ((ctxt->rex_prefix << 1) & 8); /* REX.R */
+	index_reg = (ctxt->rex_prefix << 2) & 8; /* REX.X */
+	base_reg = (ctxt->rex_prefix << 3) & 8; /* REX.B */
 
-	ctxt->modrm_mod |= (ctxt->modrm & 0xc0) >> 6;
+	ctxt->modrm_mod = (ctxt->modrm & 0xc0) >> 6;
 	ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3;
-	ctxt->modrm_rm |= (ctxt->modrm & 0x07);
+	ctxt->modrm_rm = base_reg | (ctxt->modrm & 0x07);
 	ctxt->modrm_seg = VCPU_SREG_DS;
 
 	if (ctxt->modrm_mod == 3 || (ctxt->d & NoMod)) {
@@ -1093,7 +1090,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 		if (ctxt->d & Mmx) {
 			op->type = OP_MM;
 			op->bytes = 8;
-			op->addr.xmm = ctxt->modrm_rm & 7;
+			op->addr.mm = ctxt->modrm_rm & 7;
 			return rc;
 		}
 		fetch_register_operand(op);
@@ -1190,6 +1187,9 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 		}
 	}
 	op->addr.mem.ea = modrm_ea;
+	if (ctxt->ad_bytes != 8)
+		ctxt->memop.addr.mem.ea = (u32)ctxt->memop.addr.mem.ea;
+
 done:
 	return rc;
 }
@@ -1220,12 +1220,14 @@ static void fetch_bit_operand(struct x86_emulate_ctxt *ctxt)
 	long sv = 0, mask;
 
 	if (ctxt->dst.type == OP_MEM && ctxt->src.type == OP_REG) {
-		mask = ~(ctxt->dst.bytes * 8 - 1);
+		mask = ~((long)ctxt->dst.bytes * 8 - 1);
 
 		if (ctxt->src.bytes == 2)
 			sv = (s16)ctxt->src.val & (s16)mask;
 		else if (ctxt->src.bytes == 4)
 			sv = (s32)ctxt->src.val & (s32)mask;
+		else
+			sv = (s64)ctxt->src.val & (s64)mask;
 
 		ctxt->dst.addr.mem.ea += (sv >> 3);
 	}
@@ -1315,8 +1317,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
 		in_page = (ctxt->eflags & EFLG_DF) ?
 			offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)) :
 			PAGE_SIZE - offset_in_page(reg_read(ctxt, VCPU_REGS_RDI));
-		n = min(min(in_page, (unsigned int)sizeof(rc->data)) / size,
-			count);
+		n = min3(in_page, (unsigned int)sizeof(rc->data) / size, count);
 		if (n == 0)
 			n = 1;
 		rc->pos = rc->end = 0;
@@ -1358,17 +1359,19 @@ static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt,
 				     u16 selector, struct desc_ptr *dt)
 {
 	const struct x86_emulate_ops *ops = ctxt->ops;
+	u32 base3 = 0;
 
 	if (selector & 1 << 2) {
 		struct desc_struct desc;
 		u16 sel;
 
 		memset (dt, 0, sizeof *dt);
-		if (!ops->get_segment(ctxt, &sel, &desc, NULL, VCPU_SREG_LDTR))
+		if (!ops->get_segment(ctxt, &sel, &desc, &base3,
+				      VCPU_SREG_LDTR))
 			return;
 
 		dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */
-		dt->address = get_desc_base(&desc);
+		dt->address = get_desc_base(&desc) | ((u64)base3 << 32);
 	} else
 		ops->get_gdt(ctxt, dt);
 }
@@ -1422,6 +1425,7 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	ulong desc_addr;
 	int ret;
 	u16 dummy;
+	u32 base3 = 0;
 
 	memset(&seg_desc, 0, sizeof seg_desc);
 
@@ -1538,9 +1542,14 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 		ret = write_segment_descriptor(ctxt, selector, &seg_desc);
 		if (ret != X86EMUL_CONTINUE)
 			return ret;
+	} else if (ctxt->mode == X86EMUL_MODE_PROT64) {
+		ret = ctxt->ops->read_std(ctxt, desc_addr+8, &base3,
+				sizeof(base3), &ctxt->exception);
+		if (ret != X86EMUL_CONTINUE)
+			return ret;
 	}
 load:
-	ctxt->ops->set_segment(ctxt, selector, &seg_desc, 0, seg);
+	ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg);
 	return X86EMUL_CONTINUE;
 exception:
 	emulate_exception(ctxt, err_vec, err_code, true);
@@ -1575,34 +1584,28 @@ static void write_register_operand(struct operand *op)
 
 static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op)
 {
-	int rc;
-
 	switch (op->type) {
 	case OP_REG:
 		write_register_operand(op);
 		break;
 	case OP_MEM:
 		if (ctxt->lock_prefix)
-			rc = segmented_cmpxchg(ctxt,
+			return segmented_cmpxchg(ctxt,
+						 op->addr.mem,
+						 &op->orig_val,
+						 &op->val,
+						 op->bytes);
+		else
+			return segmented_write(ctxt,
 					       op->addr.mem,
-					       &op->orig_val,
 					       &op->val,
 					       op->bytes);
-		else
-			rc = segmented_write(ctxt,
-					     op->addr.mem,
-					     &op->val,
-					     op->bytes);
-		if (rc != X86EMUL_CONTINUE)
-			return rc;
 		break;
 	case OP_MEM_STR:
-		rc = segmented_write(ctxt,
-				op->addr.mem,
-				op->data,
-				op->bytes * op->count);
-		if (rc != X86EMUL_CONTINUE)
-			return rc;
+		return segmented_write(ctxt,
+				       op->addr.mem,
+				       op->data,
+				       op->bytes * op->count);
 		break;
 	case OP_XMM:
 		write_sse_reg(ctxt, &op->vec_val, op->addr.xmm);
@@ -1671,7 +1674,7 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt,
 		return rc;
 
 	change_mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_OF
-		| EFLG_TF | EFLG_DF | EFLG_NT | EFLG_RF | EFLG_AC | EFLG_ID;
+		| EFLG_TF | EFLG_DF | EFLG_NT | EFLG_AC | EFLG_ID;
 
 	switch(ctxt->mode) {
 	case X86EMUL_MODE_PROT64:
@@ -1754,6 +1757,9 @@ static int em_pop_sreg(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
+	if (ctxt->modrm_reg == VCPU_SREG_SS)
+		ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS;
+
 	rc = load_segment_descriptor(ctxt, (u16)selector, seg);
 	return rc;
 }
@@ -1991,6 +1997,9 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt)
 {
 	u64 old = ctxt->dst.orig_val64;
 
+	if (ctxt->dst.bytes == 16)
+		return X86EMUL_UNHANDLEABLE;
+
 	if (((u32) (old >> 0) != (u32) reg_read(ctxt, VCPU_REGS_RAX)) ||
 	    ((u32) (old >> 32) != (u32) reg_read(ctxt, VCPU_REGS_RDX))) {
 		*reg_write(ctxt, VCPU_REGS_RAX) = (u32) (old >> 0);
@@ -2017,6 +2026,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	unsigned long cs;
+	int cpl = ctxt->ops->cpl(ctxt);
 
 	rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
@@ -2026,6 +2036,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
+	/* Outer-privilege level return is not implemented */
+	if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
+		return X86EMUL_UNHANDLEABLE;
 	rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS);
 	return rc;
 }
@@ -2044,8 +2057,10 @@ static int em_ret_far_imm(struct x86_emulate_ctxt *ctxt)
 static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
 {
 	/* Save real source value, then compare EAX against destination. */
+	ctxt->dst.orig_val = ctxt->dst.val;
+	ctxt->dst.val = reg_read(ctxt, VCPU_REGS_RAX);
 	ctxt->src.orig_val = ctxt->src.val;
-	ctxt->src.val = reg_read(ctxt, VCPU_REGS_RAX);
+	ctxt->src.val = ctxt->dst.orig_val;
 	fastop(ctxt, em_cmp);
 
 	if (ctxt->eflags & EFLG_ZF) {
@@ -2055,6 +2070,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
 		/* Failure: write the value we saw to EAX. */
 		ctxt->dst.type = OP_REG;
 		ctxt->dst.addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX);
+		ctxt->dst.val = ctxt->dst.orig_val;
 	}
 	return X86EMUL_CONTINUE;
 }
@@ -2194,7 +2210,7 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 	*reg_write(ctxt, VCPU_REGS_RCX) = ctxt->_eip;
 	if (efer & EFER_LMA) {
 #ifdef CONFIG_X86_64
-		*reg_write(ctxt, VCPU_REGS_R11) = ctxt->eflags & ~EFLG_RF;
+		*reg_write(ctxt, VCPU_REGS_R11) = ctxt->eflags;
 
 		ops->get_msr(ctxt,
 			     ctxt->mode == X86EMUL_MODE_PROT64 ?
@@ -2202,14 +2218,14 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 		ctxt->_eip = msr_data;
 
 		ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data);
-		ctxt->eflags &= ~(msr_data | EFLG_RF);
+		ctxt->eflags &= ~msr_data;
 #endif
 	} else {
 		/* legacy mode */
 		ops->get_msr(ctxt, MSR_STAR, &msr_data);
 		ctxt->_eip = (u32)msr_data;
 
-		ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF);
+		ctxt->eflags &= ~(EFLG_VM | EFLG_IF);
 	}
 
 	return X86EMUL_CONTINUE;
@@ -2258,7 +2274,7 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
 		break;
 	}
 
-	ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF);
+	ctxt->eflags &= ~(EFLG_VM | EFLG_IF);
 	cs_sel = (u16)msr_data;
 	cs_sel &= ~SELECTOR_RPL_MASK;
 	ss_sel = cs_sel + 8;
@@ -2964,7 +2980,7 @@ static int em_rdpmc(struct x86_emulate_ctxt *ctxt)
 
 static int em_mov(struct x86_emulate_ctxt *ctxt)
 {
-	memcpy(ctxt->dst.valptr, ctxt->src.valptr, ctxt->op_bytes);
+	memcpy(ctxt->dst.valptr, ctxt->src.valptr, sizeof(ctxt->src.valptr));
 	return X86EMUL_CONTINUE;
 }
 
@@ -3221,7 +3237,8 @@ static int em_lidt(struct x86_emulate_ctxt *ctxt)
 
 static int em_smsw(struct x86_emulate_ctxt *ctxt)
 {
-	ctxt->dst.bytes = 2;
+	if (ctxt->dst.type == OP_MEM)
+		ctxt->dst.bytes = 2;
 	ctxt->dst.val = ctxt->ops->get_cr(ctxt, 0);
 	return X86EMUL_CONTINUE;
 }
@@ -3496,7 +3513,7 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt)
 	u64 rcx = reg_read(ctxt, VCPU_REGS_RCX);
 
 	if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) ||
-	    (rcx > 3))
+	    ctxt->ops->check_pmc(ctxt, rcx))
 		return emulate_gp(ctxt, 0);
 
 	return X86EMUL_CONTINUE;
@@ -3521,9 +3538,9 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 }
 
 #define D(_y) { .flags = (_y) }
-#define DI(_y, _i) { .flags = (_y), .intercept = x86_intercept_##_i }
-#define DIP(_y, _i, _p) { .flags = (_y), .intercept = x86_intercept_##_i, \
-		      .check_perm = (_p) }
+#define DI(_y, _i) { .flags = (_y)|Intercept, .intercept = x86_intercept_##_i }
+#define DIP(_y, _i, _p) { .flags = (_y)|Intercept|CheckPerm, \
+		      .intercept = x86_intercept_##_i, .check_perm = (_p) }
 #define N    D(NotImpl)
 #define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) }
 #define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) }
@@ -3532,10 +3549,10 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
 #define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
 #define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) }
 #define II(_f, _e, _i) \
-	{ .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i }
+	{ .flags = (_f)|Intercept, .u.execute = (_e), .intercept = x86_intercept_##_i }
 #define IIP(_f, _e, _i, _p) \
-	{ .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i, \
-	  .check_perm = (_p) }
+	{ .flags = (_f)|Intercept|CheckPerm, .u.execute = (_e), \
+	  .intercept = x86_intercept_##_i, .check_perm = (_p) }
 #define GP(_f, _g) { .flags = ((_f) | Prefix), .u.gprefix = (_g) }
 
 #define D2bv(_f)      D((_f) | ByteOp), D(_f)
@@ -3634,8 +3651,8 @@ static const struct opcode group6[] = {
 };
 
 static const struct group_dual group7 = { {
-	II(Mov | DstMem | Priv,			em_sgdt, sgdt),
-	II(Mov | DstMem | Priv,			em_sidt, sidt),
+	II(Mov | DstMem,			em_sgdt, sgdt),
+	II(Mov | DstMem,			em_sidt, sidt),
 	II(SrcMem | Priv,			em_lgdt, lgdt),
 	II(SrcMem | Priv,			em_lidt, lidt),
 	II(SrcNone | DstMem | Mov,		em_smsw, smsw), N,
@@ -3899,7 +3916,7 @@ static const struct opcode twobyte_table[256] = {
 	N, N,
 	N, N, N, N, N, N, N, N,
 	/* 0x40 - 0x4F */
-	X16(D(DstReg | SrcMem | ModRM | Mov)),
+	X16(D(DstReg | SrcMem | ModRM)),
 	/* 0x50 - 0x5F */
 	N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N,
 	/* 0x60 - 0x6F */
@@ -4061,12 +4078,12 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 	mem_common:
 		*op = ctxt->memop;
 		ctxt->memopp = op;
-		if ((ctxt->d & BitOp) && op == &ctxt->dst)
+		if (ctxt->d & BitOp)
 			fetch_bit_operand(ctxt);
 		op->orig_val = op->val;
 		break;
 	case OpMem64:
-		ctxt->memop.bytes = 8;
+		ctxt->memop.bytes = (ctxt->op_bytes == 8) ? 16 : 8;
 		goto mem_common;
 	case OpAcc:
 		op->type = OP_REG;
@@ -4150,7 +4167,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 		op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
 		op->addr.mem.ea =
 			register_address(ctxt, reg_read(ctxt, VCPU_REGS_RSI));
-		op->addr.mem.seg = seg_override(ctxt);
+		op->addr.mem.seg = ctxt->seg_override;
 		op->val = 0;
 		op->count = 1;
 		break;
@@ -4161,7 +4178,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 			register_address(ctxt,
 				reg_read(ctxt, VCPU_REGS_RBX) +
 				(reg_read(ctxt, VCPU_REGS_RAX) & 0xff));
-		op->addr.mem.seg = seg_override(ctxt);
+		op->addr.mem.seg = ctxt->seg_override;
 		op->val = 0;
 		break;
 	case OpImmFAddr:
@@ -4208,16 +4225,22 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	int mode = ctxt->mode;
 	int def_op_bytes, def_ad_bytes, goffset, simd_prefix;
 	bool op_prefix = false;
+	bool has_seg_override = false;
 	struct opcode opcode;
 
 	ctxt->memop.type = OP_NONE;
 	ctxt->memopp = NULL;
 	ctxt->_eip = ctxt->eip;
-	ctxt->fetch.start = ctxt->_eip;
-	ctxt->fetch.end = ctxt->fetch.start + insn_len;
+	ctxt->fetch.ptr = ctxt->fetch.data;
+	ctxt->fetch.end = ctxt->fetch.data + insn_len;
 	ctxt->opcode_len = 1;
 	if (insn_len > 0)
 		memcpy(ctxt->fetch.data, insn, insn_len);
+	else {
+		rc = __do_insn_fetch_bytes(ctxt, 1);
+		if (rc != X86EMUL_CONTINUE)
+			return rc;
+	}
 
 	switch (mode) {
 	case X86EMUL_MODE_REAL:
@@ -4261,11 +4284,13 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 		case 0x2e:	/* CS override */
 		case 0x36:	/* SS override */
 		case 0x3e:	/* DS override */
-			set_seg_override(ctxt, (ctxt->b >> 3) & 3);
+			has_seg_override = true;
+			ctxt->seg_override = (ctxt->b >> 3) & 3;
 			break;
 		case 0x64:	/* FS override */
 		case 0x65:	/* GS override */
-			set_seg_override(ctxt, ctxt->b & 7);
+			has_seg_override = true;
+			ctxt->seg_override = ctxt->b & 7;
 			break;
 		case 0x40 ... 0x4f: /* REX */
 			if (mode != X86EMUL_MODE_PROT64)
@@ -4314,6 +4339,13 @@ done_prefixes:
 	if (ctxt->d & ModRM)
 		ctxt->modrm = insn_fetch(u8, ctxt);
 
+	/* vex-prefix instructions are not implemented */
+	if (ctxt->opcode_len == 1 && (ctxt->b == 0xc5 || ctxt->b == 0xc4) &&
+	    (mode == X86EMUL_MODE_PROT64 ||
+	    (mode >= X86EMUL_MODE_PROT16 && (ctxt->modrm & 0x80)))) {
+		ctxt->d = NotImpl;
+	}
+
 	while (ctxt->d & GroupMask) {
 		switch (ctxt->d & GroupMask) {
 		case Group:
@@ -4356,49 +4388,59 @@ done_prefixes:
 		ctxt->d |= opcode.flags;
 	}
 
-	ctxt->execute = opcode.u.execute;
-	ctxt->check_perm = opcode.check_perm;
-	ctxt->intercept = opcode.intercept;
-
 	/* Unrecognised? */
-	if (ctxt->d == 0 || (ctxt->d & NotImpl))
+	if (ctxt->d == 0)
 		return EMULATION_FAILED;
 
-	if (!(ctxt->d & EmulateOnUD) && ctxt->ud)
-		return EMULATION_FAILED;
+	ctxt->execute = opcode.u.execute;
 
-	if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
-		ctxt->op_bytes = 8;
+	if (unlikely(ctxt->d &
+		     (NotImpl|EmulateOnUD|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) {
+		/*
+		 * These are copied unconditionally here, and checked unconditionally
+		 * in x86_emulate_insn.
+		 */
+		ctxt->check_perm = opcode.check_perm;
+		ctxt->intercept = opcode.intercept;
+
+		if (ctxt->d & NotImpl)
+			return EMULATION_FAILED;
+
+		if (!(ctxt->d & EmulateOnUD) && ctxt->ud)
+			return EMULATION_FAILED;
 
-	if (ctxt->d & Op3264) {
-		if (mode == X86EMUL_MODE_PROT64)
+		if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
 			ctxt->op_bytes = 8;
-		else
-			ctxt->op_bytes = 4;
-	}
 
-	if (ctxt->d & Sse)
-		ctxt->op_bytes = 16;
-	else if (ctxt->d & Mmx)
-		ctxt->op_bytes = 8;
+		if (ctxt->d & Op3264) {
+			if (mode == X86EMUL_MODE_PROT64)
+				ctxt->op_bytes = 8;
+			else
+				ctxt->op_bytes = 4;
+		}
+
+		if (ctxt->d & Sse)
+			ctxt->op_bytes = 16;
+		else if (ctxt->d & Mmx)
+			ctxt->op_bytes = 8;
+	}
 
 	/* ModRM and SIB bytes. */
 	if (ctxt->d & ModRM) {
 		rc = decode_modrm(ctxt, &ctxt->memop);
-		if (!ctxt->has_seg_override)
-			set_seg_override(ctxt, ctxt->modrm_seg);
+		if (!has_seg_override) {
+			has_seg_override = true;
+			ctxt->seg_override = ctxt->modrm_seg;
+		}
 	} else if (ctxt->d & MemAbs)
 		rc = decode_abs(ctxt, &ctxt->memop);
 	if (rc != X86EMUL_CONTINUE)
 		goto done;
 
-	if (!ctxt->has_seg_override)
-		set_seg_override(ctxt, VCPU_SREG_DS);
-
-	ctxt->memop.addr.mem.seg = seg_override(ctxt);
+	if (!has_seg_override)
+		ctxt->seg_override = VCPU_SREG_DS;
 
-	if (ctxt->memop.type == OP_MEM && ctxt->ad_bytes != 8)
-		ctxt->memop.addr.mem.ea = (u32)ctxt->memop.addr.mem.ea;
+	ctxt->memop.addr.mem.seg = ctxt->seg_override;
 
 	/*
 	 * Decode and fetch the source operand: register, memory
@@ -4420,7 +4462,7 @@ done_prefixes:
 	rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
 
 done:
-	if (ctxt->memopp && ctxt->memopp->type == OP_MEM && ctxt->rip_relative)
+	if (ctxt->rip_relative)
 		ctxt->memopp->addr.mem.ea += ctxt->_eip;
 
 	return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK;
@@ -4495,6 +4537,16 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
 	return X86EMUL_CONTINUE;
 }
 
+void init_decode_cache(struct x86_emulate_ctxt *ctxt)
+{
+	memset(&ctxt->rip_relative, 0,
+	       (void *)&ctxt->modrm - (void *)&ctxt->rip_relative);
+
+	ctxt->io_read.pos = 0;
+	ctxt->io_read.end = 0;
+	ctxt->mem_read.end = 0;
+}
+
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 {
 	const struct x86_emulate_ops *ops = ctxt->ops;
@@ -4503,12 +4555,6 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 
 	ctxt->mem_read.pos = 0;
 
-	if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) ||
-			(ctxt->d & Undefined)) {
-		rc = emulate_ud(ctxt);
-		goto done;
-	}
-
 	/* LOCK prefix is allowed only with some instructions */
 	if (ctxt->lock_prefix && (!(ctxt->d & Lock) || ctxt->dst.type != OP_MEM)) {
 		rc = emulate_ud(ctxt);
@@ -4520,69 +4566,82 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 		goto done;
 	}
 
-	if (((ctxt->d & (Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM)))
-	    || ((ctxt->d & Sse) && !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) {
-		rc = emulate_ud(ctxt);
-		goto done;
-	}
-
-	if ((ctxt->d & (Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) {
-		rc = emulate_nm(ctxt);
-		goto done;
-	}
+	if (unlikely(ctxt->d &
+		     (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) {
+		if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) ||
+				(ctxt->d & Undefined)) {
+			rc = emulate_ud(ctxt);
+			goto done;
+		}
 
-	if (ctxt->d & Mmx) {
-		rc = flush_pending_x87_faults(ctxt);
-		if (rc != X86EMUL_CONTINUE)
+		if (((ctxt->d & (Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM)))
+		    || ((ctxt->d & Sse) && !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) {
+			rc = emulate_ud(ctxt);
 			goto done;
-		/*
-		 * Now that we know the fpu is exception safe, we can fetch
-		 * operands from it.
-		 */
-		fetch_possible_mmx_operand(ctxt, &ctxt->src);
-		fetch_possible_mmx_operand(ctxt, &ctxt->src2);
-		if (!(ctxt->d & Mov))
-			fetch_possible_mmx_operand(ctxt, &ctxt->dst);
-	}
+		}
 
-	if (unlikely(ctxt->guest_mode) && ctxt->intercept) {
-		rc = emulator_check_intercept(ctxt, ctxt->intercept,
-					      X86_ICPT_PRE_EXCEPT);
-		if (rc != X86EMUL_CONTINUE)
+		if ((ctxt->d & (Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) {
+			rc = emulate_nm(ctxt);
 			goto done;
-	}
+		}
 
-	/* Privileged instruction can be executed only in CPL=0 */
-	if ((ctxt->d & Priv) && ops->cpl(ctxt)) {
-		rc = emulate_gp(ctxt, 0);
-		goto done;
-	}
+		if (ctxt->d & Mmx) {
+			rc = flush_pending_x87_faults(ctxt);
+			if (rc != X86EMUL_CONTINUE)
+				goto done;
+			/*
+			 * Now that we know the fpu is exception safe, we can fetch
+			 * operands from it.
+			 */
+			fetch_possible_mmx_operand(ctxt, &ctxt->src);
+			fetch_possible_mmx_operand(ctxt, &ctxt->src2);
+			if (!(ctxt->d & Mov))
+				fetch_possible_mmx_operand(ctxt, &ctxt->dst);
+		}
 
-	/* Instruction can only be executed in protected mode */
-	if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) {
-		rc = emulate_ud(ctxt);
-		goto done;
-	}
+		if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) {
+			rc = emulator_check_intercept(ctxt, ctxt->intercept,
+						      X86_ICPT_PRE_EXCEPT);
+			if (rc != X86EMUL_CONTINUE)
+				goto done;
+		}
 
-	/* Do instruction specific permission checks */
-	if (ctxt->check_perm) {
-		rc = ctxt->check_perm(ctxt);
-		if (rc != X86EMUL_CONTINUE)
+		/* Privileged instruction can be executed only in CPL=0 */
+		if ((ctxt->d & Priv) && ops->cpl(ctxt)) {
+			if (ctxt->d & PrivUD)
+				rc = emulate_ud(ctxt);
+			else
+				rc = emulate_gp(ctxt, 0);
 			goto done;
-	}
+		}
 
-	if (unlikely(ctxt->guest_mode) && ctxt->intercept) {
-		rc = emulator_check_intercept(ctxt, ctxt->intercept,
-					      X86_ICPT_POST_EXCEPT);
-		if (rc != X86EMUL_CONTINUE)
+		/* Instruction can only be executed in protected mode */
+		if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) {
+			rc = emulate_ud(ctxt);
 			goto done;
-	}
+		}
 
-	if (ctxt->rep_prefix && (ctxt->d & String)) {
-		/* All REP prefixes have the same first termination condition */
-		if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) {
-			ctxt->eip = ctxt->_eip;
-			goto done;
+		/* Do instruction specific permission checks */
+		if (ctxt->d & CheckPerm) {
+			rc = ctxt->check_perm(ctxt);
+			if (rc != X86EMUL_CONTINUE)
+				goto done;
+		}
+
+		if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) {
+			rc = emulator_check_intercept(ctxt, ctxt->intercept,
+						      X86_ICPT_POST_EXCEPT);
+			if (rc != X86EMUL_CONTINUE)
+				goto done;
+		}
+
+		if (ctxt->rep_prefix && (ctxt->d & String)) {
+			/* All REP prefixes have the same first termination condition */
+			if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) {
+				ctxt->eip = ctxt->_eip;
+				ctxt->eflags &= ~EFLG_RF;
+				goto done;
+			}
 		}
 	}
 
@@ -4616,13 +4675,18 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 
 special_insn:
 
-	if (unlikely(ctxt->guest_mode) && ctxt->intercept) {
+	if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) {
 		rc = emulator_check_intercept(ctxt, ctxt->intercept,
 					      X86_ICPT_POST_MEMACCESS);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
 	}
 
+	if (ctxt->rep_prefix && (ctxt->d & String))
+		ctxt->eflags |= EFLG_RF;
+	else
+		ctxt->eflags &= ~EFLG_RF;
+
 	if (ctxt->execute) {
 		if (ctxt->d & Fastop) {
 			void (*fop)(struct fastop *) = (void *)ctxt->execute;
@@ -4657,8 +4721,9 @@ special_insn:
 		break;
 	case 0x90 ... 0x97: /* nop / xchg reg, rax */
 		if (ctxt->dst.addr.reg == reg_rmw(ctxt, VCPU_REGS_RAX))
-			break;
-		rc = em_xchg(ctxt);
+			ctxt->dst.type = OP_NONE;
+		else
+			rc = em_xchg(ctxt);
 		break;
 	case 0x98: /* cbw/cwde/cdqe */
 		switch (ctxt->op_bytes) {
@@ -4709,17 +4774,17 @@ special_insn:
 		goto done;
 
 writeback:
-	if (!(ctxt->d & NoWrite)) {
-		rc = writeback(ctxt, &ctxt->dst);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
-	}
 	if (ctxt->d & SrcWrite) {
 		BUG_ON(ctxt->src.type == OP_MEM || ctxt->src.type == OP_MEM_STR);
 		rc = writeback(ctxt, &ctxt->src);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
 	}
+	if (!(ctxt->d & NoWrite)) {
+		rc = writeback(ctxt, &ctxt->dst);
+		if (rc != X86EMUL_CONTINUE)
+			goto done;
+	}
 
 	/*
 	 * restore dst type in case the decoding will be reused
@@ -4761,6 +4826,7 @@ writeback:
 			}
 			goto done; /* skip rip writeback */
 		}
+		ctxt->eflags &= ~EFLG_RF;
 	}
 
 	ctxt->eip = ctxt->_eip;
@@ -4793,8 +4859,10 @@ twobyte_insn:
 		ops->get_dr(ctxt, ctxt->modrm_reg, &ctxt->dst.val);
 		break;
 	case 0x40 ... 0x4f:	/* cmov */
-		ctxt->dst.val = ctxt->dst.orig_val = ctxt->src.val;
-		if (!test_cc(ctxt->b, ctxt->eflags))
+		if (test_cc(ctxt->b, ctxt->eflags))
+			ctxt->dst.val = ctxt->src.val;
+		else if (ctxt->mode != X86EMUL_MODE_PROT64 ||
+			 ctxt->op_bytes != 4)
 			ctxt->dst.type = OP_NONE; /* no writeback */
 		break;
 	case 0x80 ... 0x8f: /* jnz rel, etc*/
@@ -4818,8 +4886,8 @@ twobyte_insn:
 		break;
 	case 0xc3:		/* movnti */
 		ctxt->dst.bytes = ctxt->op_bytes;
-		ctxt->dst.val = (ctxt->op_bytes == 4) ? (u32) ctxt->src.val :
-							(u64) ctxt->src.val;
+		ctxt->dst.val = (ctxt->op_bytes == 8) ? (u64) ctxt->src.val :
+							(u32) ctxt->src.val;
 		break;
 	default:
 		goto cannot_emulate;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 00691185817..3855103f71f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1451,7 +1451,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.apic_arb_prio = 0;
 	vcpu->arch.apic_attention = 0;
 
-	apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr="
+	apic_debug("%s: vcpu=%p, id=%d, base_msr="
 		   "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
 		   vcpu, kvm_apic_id(apic),
 		   vcpu->arch.apic_base, apic->base_address);
@@ -1895,7 +1895,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 		/* evaluate pending_events before reading the vector */
 		smp_rmb();
 		sipi_vector = apic->sipi_vector;
-		pr_debug("vcpu %d received sipi with vector # %x\n",
+		apic_debug("vcpu %d received sipi with vector # %x\n",
 			 vcpu->vcpu_id, sipi_vector);
 		kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector);
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 9d2e0ffcb19..5aaf3564176 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -22,7 +22,7 @@
 	__entry->unsync = sp->unsync;
 
 #define KVM_MMU_PAGE_PRINTK() ({				        \
-	const char *ret = p->buffer + p->len;				\
+	const u32 saved_len = p->len;					\
 	static const char *access_str[] = {			        \
 		"---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux"  \
 	};							        \
@@ -41,7 +41,7 @@
 			 role.nxe ? "" : "!",				\
 			 __entry->root_count,				\
 			 __entry->unsync ? "unsync" : "sync", 0);	\
-	ret;								\
+	p->buffer + saved_len;						\
 		})
 
 #define kvm_mmu_trace_pferr_flags       \
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index cbecaa90399..3dd6accb64e 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -428,6 +428,15 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	return 1;
 }
 
+int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc)
+{
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	bool fixed = pmc & (1u << 30);
+	pmc &= ~(3u << 30);
+	return (!fixed && pmc >= pmu->nr_arch_gp_counters) ||
+		(fixed && pmc >= pmu->nr_arch_fixed_counters);
+}
+
 int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data)
 {
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ec8366c5cfe..ddf742768ec 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -486,14 +486,14 @@ static int is_external_interrupt(u32 info)
 	return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR);
 }
 
-static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
+static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 ret = 0;
 
 	if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
-		ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
-	return ret & mask;
+		ret = KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
+	return ret;
 }
 
 static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
@@ -1415,7 +1415,16 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 	var->avl = (s->attrib >> SVM_SELECTOR_AVL_SHIFT) & 1;
 	var->l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1;
 	var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
-	var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1;
+
+	/*
+	 * AMD CPUs circa 2014 track the G bit for all segments except CS.
+	 * However, the SVM spec states that the G bit is not observed by the
+	 * CPU, and some VMware virtual CPUs drop the G bit for all segments.
+	 * So let's synthesize a legal G bit for all segments, this helps
+	 * running KVM nested. It also helps cross-vendor migration, because
+	 * Intel's vmentry has a check on the 'G' bit.
+	 */
+	var->g = s->limit > 0xfffff;
 
 	/*
 	 * AMD's VMCB does not have an explicit unusable field, so emulate it
@@ -1424,14 +1433,6 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 	var->unusable = !var->present || (var->type == 0);
 
 	switch (seg) {
-	case VCPU_SREG_CS:
-		/*
-		 * SVM always stores 0 for the 'G' bit in the CS selector in
-		 * the VMCB on a VMEXIT. This hurts cross-vendor migration:
-		 * Intel's VMENTRY has a check on the 'G' bit.
-		 */
-		var->g = s->limit > 0xfffff;
-		break;
 	case VCPU_SREG_TR:
 		/*
 		 * Work around a bug where the busy flag in the tr selector
@@ -1462,6 +1463,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 		 */
 		if (var->unusable)
 			var->db = 0;
+		var->dpl = to_svm(vcpu)->vmcb->save.cpl;
 		break;
 	}
 }
@@ -2115,22 +2117,27 @@ static void nested_svm_unmap(struct page *page)
 
 static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
 {
-	unsigned port;
-	u8 val, bit;
+	unsigned port, size, iopm_len;
+	u16 val, mask;
+	u8 start_bit;
 	u64 gpa;
 
 	if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT)))
 		return NESTED_EXIT_HOST;
 
 	port = svm->vmcb->control.exit_info_1 >> 16;
+	size = (svm->vmcb->control.exit_info_1 & SVM_IOIO_SIZE_MASK) >>
+		SVM_IOIO_SIZE_SHIFT;
 	gpa  = svm->nested.vmcb_iopm + (port / 8);
-	bit  = port % 8;
-	val  = 0;
+	start_bit = port % 8;
+	iopm_len = (start_bit + size > 8) ? 2 : 1;
+	mask = (0xf >> (4 - size)) << start_bit;
+	val = 0;
 
-	if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, 1))
-		val &= (1 << bit);
+	if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, iopm_len))
+		return NESTED_EXIT_DONE;
 
-	return val ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
+	return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
 }
 
 static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
@@ -4204,7 +4211,8 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 		if (info->intercept == x86_intercept_cr_write)
 			icpt_info.exit_code += info->modrm_reg;
 
-		if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0)
+		if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0 ||
+		    info->intercept == x86_intercept_clts)
 			break;
 
 		intercept = svm->nested.intercept;
@@ -4249,14 +4257,14 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 		u64 exit_info;
 		u32 bytes;
 
-		exit_info = (vcpu->arch.regs[VCPU_REGS_RDX] & 0xffff) << 16;
-
 		if (info->intercept == x86_intercept_in ||
 		    info->intercept == x86_intercept_ins) {
-			exit_info |= SVM_IOIO_TYPE_MASK;
-			bytes = info->src_bytes;
-		} else {
+			exit_info = ((info->src_val & 0xffff) << 16) |
+				SVM_IOIO_TYPE_MASK;
 			bytes = info->dst_bytes;
+		} else {
+			exit_info = (info->dst_val & 0xffff) << 16;
+			bytes = info->src_bytes;
 		}
 
 		if (info->intercept == x86_intercept_outs ||
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 33574c95220..e850a7d332b 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -721,10 +721,10 @@ TRACE_EVENT(kvm_emulate_insn,
 		),
 
 	TP_fast_assign(
-		__entry->rip = vcpu->arch.emulate_ctxt.fetch.start;
 		__entry->csbase = kvm_x86_ops->get_segment_base(vcpu, VCPU_SREG_CS);
-		__entry->len = vcpu->arch.emulate_ctxt._eip
-			       - vcpu->arch.emulate_ctxt.fetch.start;
+		__entry->len = vcpu->arch.emulate_ctxt.fetch.ptr
+			       - vcpu->arch.emulate_ctxt.fetch.data;
+		__entry->rip = vcpu->arch.emulate_ctxt._eip - __entry->len;
 		memcpy(__entry->insn,
 		       vcpu->arch.emulate_ctxt.fetch.data,
 		       15);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 801332edefc..e618f34bde2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -383,6 +383,9 @@ struct nested_vmx {
 
 	struct hrtimer preemption_timer;
 	bool preemption_timer_expired;
+
+	/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
+	u64 vmcs01_debugctl;
 };
 
 #define POSTED_INTR_ON  0
@@ -740,7 +743,6 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var);
 static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
 static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
-static bool vmx_mpx_supported(void);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -820,7 +822,6 @@ static const u32 vmx_msr_index[] = {
 #endif
 	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
 };
-#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
 
 static inline bool is_page_fault(u32 intr_info)
 {
@@ -1940,7 +1941,7 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	vmcs_writel(GUEST_RFLAGS, rflags);
 }
 
-static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
+static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
 	int ret = 0;
@@ -1950,7 +1951,7 @@ static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 	if (interruptibility & GUEST_INTR_STATE_MOV_SS)
 		ret |= KVM_X86_SHADOW_INT_MOV_SS;
 
-	return ret & mask;
+	return ret;
 }
 
 static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
@@ -2239,10 +2240,13 @@ static inline bool nested_vmx_allowed(struct kvm_vcpu *vcpu)
  * or other means.
  */
 static u32 nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high;
+static u32 nested_vmx_true_procbased_ctls_low;
 static u32 nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high;
 static u32 nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high;
 static u32 nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high;
+static u32 nested_vmx_true_exit_ctls_low;
 static u32 nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high;
+static u32 nested_vmx_true_entry_ctls_low;
 static u32 nested_vmx_misc_low, nested_vmx_misc_high;
 static u32 nested_vmx_ept_caps;
 static __init void nested_vmx_setup_ctls_msrs(void)
@@ -2265,21 +2269,13 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	/* pin-based controls */
 	rdmsr(MSR_IA32_VMX_PINBASED_CTLS,
 	      nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high);
-	/*
-	 * According to the Intel spec, if bit 55 of VMX_BASIC is off (as it is
-	 * in our case), bits 1, 2 and 4 (i.e., 0x16) must be 1 in this MSR.
-	 */
 	nested_vmx_pinbased_ctls_low |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
 	nested_vmx_pinbased_ctls_high &= PIN_BASED_EXT_INTR_MASK |
 		PIN_BASED_NMI_EXITING | PIN_BASED_VIRTUAL_NMIS;
 	nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
 		PIN_BASED_VMX_PREEMPTION_TIMER;
 
-	/*
-	 * Exit controls
-	 * If bit 55 of VMX_BASIC is off, bits 0-8 and 10, 11, 13, 14, 16 and
-	 * 17 must be 1.
-	 */
+	/* exit controls */
 	rdmsr(MSR_IA32_VMX_EXIT_CTLS,
 		nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high);
 	nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
@@ -2296,10 +2292,13 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	if (vmx_mpx_supported())
 		nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
 
+	/* We support free control of debug control saving. */
+	nested_vmx_true_exit_ctls_low = nested_vmx_exit_ctls_low &
+		~VM_EXIT_SAVE_DEBUG_CONTROLS;
+
 	/* entry controls */
 	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
 		nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high);
-	/* If bit 55 of VMX_BASIC is off, bits 0-8 and 12 must be 1. */
 	nested_vmx_entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
 	nested_vmx_entry_ctls_high &=
 #ifdef CONFIG_X86_64
@@ -2311,10 +2310,14 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	if (vmx_mpx_supported())
 		nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
 
+	/* We support free control of debug control loading. */
+	nested_vmx_true_entry_ctls_low = nested_vmx_entry_ctls_low &
+		~VM_ENTRY_LOAD_DEBUG_CONTROLS;
+
 	/* cpu-based controls */
 	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
 		nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high);
-	nested_vmx_procbased_ctls_low = 0;
+	nested_vmx_procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
 	nested_vmx_procbased_ctls_high &=
 		CPU_BASED_VIRTUAL_INTR_PENDING |
 		CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING |
@@ -2335,7 +2338,12 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	 * can use it to avoid exits to L1 - even when L0 runs L2
 	 * without MSR bitmaps.
 	 */
-	nested_vmx_procbased_ctls_high |= CPU_BASED_USE_MSR_BITMAPS;
+	nested_vmx_procbased_ctls_high |= CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
+		CPU_BASED_USE_MSR_BITMAPS;
+
+	/* We support free control of CR3 access interception. */
+	nested_vmx_true_procbased_ctls_low = nested_vmx_procbased_ctls_low &
+		~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING);
 
 	/* secondary cpu-based controls */
 	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
@@ -2394,7 +2402,7 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 		 * guest, and the VMCS structure we give it - not about the
 		 * VMX support of the underlying hardware.
 		 */
-		*pdata = VMCS12_REVISION |
+		*pdata = VMCS12_REVISION | VMX_BASIC_TRUE_CTLS |
 			   ((u64)VMCS12_SIZE << VMX_BASIC_VMCS_SIZE_SHIFT) |
 			   (VMX_BASIC_MEM_TYPE_WB << VMX_BASIC_MEM_TYPE_SHIFT);
 		break;
@@ -2404,16 +2412,25 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 					nested_vmx_pinbased_ctls_high);
 		break;
 	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
+		*pdata = vmx_control_msr(nested_vmx_true_procbased_ctls_low,
+					nested_vmx_procbased_ctls_high);
+		break;
 	case MSR_IA32_VMX_PROCBASED_CTLS:
 		*pdata = vmx_control_msr(nested_vmx_procbased_ctls_low,
 					nested_vmx_procbased_ctls_high);
 		break;
 	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
+		*pdata = vmx_control_msr(nested_vmx_true_exit_ctls_low,
+					nested_vmx_exit_ctls_high);
+		break;
 	case MSR_IA32_VMX_EXIT_CTLS:
 		*pdata = vmx_control_msr(nested_vmx_exit_ctls_low,
 					nested_vmx_exit_ctls_high);
 		break;
 	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
+		*pdata = vmx_control_msr(nested_vmx_true_entry_ctls_low,
+					nested_vmx_entry_ctls_high);
+		break;
 	case MSR_IA32_VMX_ENTRY_CTLS:
 		*pdata = vmx_control_msr(nested_vmx_entry_ctls_low,
 					nested_vmx_entry_ctls_high);
@@ -2442,7 +2459,7 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 		*pdata = -1ULL;
 		break;
 	case MSR_IA32_VMX_VMCS_ENUM:
-		*pdata = 0x1f;
+		*pdata = 0x2e; /* highest index: VMX_PREEMPTION_TIMER_VALUE */
 		break;
 	case MSR_IA32_VMX_PROCBASED_CTLS2:
 		*pdata = vmx_control_msr(nested_vmx_secondary_ctls_low,
@@ -3653,7 +3670,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var));
 
 out:
-	vmx->emulation_required |= emulation_required(vcpu);
+	vmx->emulation_required = emulation_required(vcpu);
 }
 
 static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
@@ -4422,7 +4439,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		vmx->vcpu.arch.pat = host_pat;
 	}
 
-	for (i = 0; i < NR_VMX_MSR; ++i) {
+	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
 		u32 index = vmx_msr_index[i];
 		u32 data_low, data_high;
 		int j = vmx->nmsrs;
@@ -4873,7 +4890,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		if (!(vcpu->guest_debug &
 		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
 			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= dr6;
+			vcpu->arch.dr6 |= dr6 | DR6_RTM;
 			if (!(dr6 & ~DR6_RESERVED)) /* icebp */
 				skip_emulated_instruction(vcpu);
 
@@ -5039,7 +5056,7 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 	reg = (exit_qualification >> 8) & 15;
 	switch ((exit_qualification >> 4) & 3) {
 	case 0: /* mov to cr */
-		val = kvm_register_read(vcpu, reg);
+		val = kvm_register_readl(vcpu, reg);
 		trace_kvm_cr_write(cr, val);
 		switch (cr) {
 		case 0:
@@ -5056,7 +5073,7 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 			return 1;
 		case 8: {
 				u8 cr8_prev = kvm_get_cr8(vcpu);
-				u8 cr8 = kvm_register_read(vcpu, reg);
+				u8 cr8 = (u8)val;
 				err = kvm_set_cr8(vcpu, cr8);
 				kvm_complete_insn_gp(vcpu, err);
 				if (irqchip_in_kernel(vcpu->kvm))
@@ -5132,7 +5149,7 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 			return 0;
 		} else {
 			vcpu->arch.dr7 &= ~DR7_GD;
-			vcpu->arch.dr6 |= DR6_BD;
+			vcpu->arch.dr6 |= DR6_BD | DR6_RTM;
 			vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
 			kvm_queue_exception(vcpu, DB_VECTOR);
 			return 1;
@@ -5165,7 +5182,7 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 			return 1;
 		kvm_register_write(vcpu, reg, val);
 	} else
-		if (kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)))
+		if (kvm_set_dr(vcpu, dr, kvm_register_readl(vcpu, reg)))
 			return 1;
 
 	skip_emulated_instruction(vcpu);
@@ -5621,7 +5638,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 	cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
 	intr_window_requested = cpu_exec_ctrl & CPU_BASED_VIRTUAL_INTR_PENDING;
 
-	while (!guest_state_valid(vcpu) && count-- != 0) {
+	while (vmx->emulation_required && count-- != 0) {
 		if (intr_window_requested && vmx_interrupt_allowed(vcpu))
 			return handle_interrupt_window(&vmx->vcpu);
 
@@ -5655,7 +5672,6 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 			schedule();
 	}
 
-	vmx->emulation_required = emulation_required(vcpu);
 out:
 	return ret;
 }
@@ -5754,22 +5770,27 @@ static void nested_free_vmcs02(struct vcpu_vmx *vmx, gpa_t vmptr)
 
 /*
  * Free all VMCSs saved for this vcpu, except the one pointed by
- * vmx->loaded_vmcs. These include the VMCSs in vmcs02_pool (except the one
- * currently used, if running L2), and vmcs01 when running L2.
+ * vmx->loaded_vmcs. We must be running L1, so vmx->loaded_vmcs
+ * must be &vmx->vmcs01.
  */
 static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
 {
 	struct vmcs02_list *item, *n;
+
+	WARN_ON(vmx->loaded_vmcs != &vmx->vmcs01);
 	list_for_each_entry_safe(item, n, &vmx->nested.vmcs02_pool, list) {
-		if (vmx->loaded_vmcs != &item->vmcs02)
-			free_loaded_vmcs(&item->vmcs02);
+		/*
+		 * Something will leak if the above WARN triggers.  Better than
+		 * a use-after-free.
+		 */
+		if (vmx->loaded_vmcs == &item->vmcs02)
+			continue;
+
+		free_loaded_vmcs(&item->vmcs02);
 		list_del(&item->list);
 		kfree(item);
+		vmx->nested.vmcs02_num--;
 	}
-	vmx->nested.vmcs02_num = 0;
-
-	if (vmx->loaded_vmcs != &vmx->vmcs01)
-		free_loaded_vmcs(&vmx->vmcs01);
 }
 
 /*
@@ -5918,7 +5939,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 		 * which replaces physical address width with 32
 		 *
 		 */
-		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
 			nested_vmx_failInvalid(vcpu);
 			skip_emulated_instruction(vcpu);
 			return 1;
@@ -5936,7 +5957,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 		vmx->nested.vmxon_ptr = vmptr;
 		break;
 	case EXIT_REASON_VMCLEAR:
-		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
 			nested_vmx_failValid(vcpu,
 					     VMXERR_VMCLEAR_INVALID_ADDRESS);
 			skip_emulated_instruction(vcpu);
@@ -5951,7 +5972,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
 		}
 		break;
 	case EXIT_REASON_VMPTRLD:
-		if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) {
+		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
 			nested_vmx_failValid(vcpu,
 					     VMXERR_VMPTRLD_INVALID_ADDRESS);
 			skip_emulated_instruction(vcpu);
@@ -6086,20 +6107,27 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
 static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
 {
 	u32 exec_control;
+	if (vmx->nested.current_vmptr == -1ull)
+		return;
+
+	/* current_vmptr and current_vmcs12 are always set/reset together */
+	if (WARN_ON(vmx->nested.current_vmcs12 == NULL))
+		return;
+
 	if (enable_shadow_vmcs) {
-		if (vmx->nested.current_vmcs12 != NULL) {
-			/* copy to memory all shadowed fields in case
-			   they were modified */
-			copy_shadow_to_vmcs12(vmx);
-			vmx->nested.sync_shadow_vmcs = false;
-			exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
-			exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
-			vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
-			vmcs_write64(VMCS_LINK_POINTER, -1ull);
-		}
+		/* copy to memory all shadowed fields in case
+		   they were modified */
+		copy_shadow_to_vmcs12(vmx);
+		vmx->nested.sync_shadow_vmcs = false;
+		exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+		exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS;
+		vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
+		vmcs_write64(VMCS_LINK_POINTER, -1ull);
 	}
 	kunmap(vmx->nested.current_vmcs12_page);
 	nested_release_page(vmx->nested.current_vmcs12_page);
+	vmx->nested.current_vmptr = -1ull;
+	vmx->nested.current_vmcs12 = NULL;
 }
 
 /*
@@ -6110,12 +6138,9 @@ static void free_nested(struct vcpu_vmx *vmx)
 {
 	if (!vmx->nested.vmxon)
 		return;
+
 	vmx->nested.vmxon = false;
-	if (vmx->nested.current_vmptr != -1ull) {
-		nested_release_vmcs12(vmx);
-		vmx->nested.current_vmptr = -1ull;
-		vmx->nested.current_vmcs12 = NULL;
-	}
+	nested_release_vmcs12(vmx);
 	if (enable_shadow_vmcs)
 		free_vmcs(vmx->nested.current_shadow_vmcs);
 	/* Unpin physical memory we referred to in current vmcs02 */
@@ -6152,11 +6177,8 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr))
 		return 1;
 
-	if (vmptr == vmx->nested.current_vmptr) {
+	if (vmptr == vmx->nested.current_vmptr)
 		nested_release_vmcs12(vmx);
-		vmx->nested.current_vmptr = -1ull;
-		vmx->nested.current_vmcs12 = NULL;
-	}
 
 	page = nested_get_page(vcpu, vmptr);
 	if (page == NULL) {
@@ -6384,7 +6406,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 		return 1;
 
 	/* Decode instruction info and find the field to read */
-	field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
 	/* Read the field, zero-extended to a u64 field_value */
 	if (!vmcs12_read_any(vcpu, field, &field_value)) {
 		nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
@@ -6397,7 +6419,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 	 * on the guest's mode (32 or 64 bit), not on the given field's length.
 	 */
 	if (vmx_instruction_info & (1u << 10)) {
-		kvm_register_write(vcpu, (((vmx_instruction_info) >> 3) & 0xf),
+		kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf),
 			field_value);
 	} else {
 		if (get_vmx_mem_address(vcpu, exit_qualification,
@@ -6434,21 +6456,21 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 		return 1;
 
 	if (vmx_instruction_info & (1u << 10))
-		field_value = kvm_register_read(vcpu,
+		field_value = kvm_register_readl(vcpu,
 			(((vmx_instruction_info) >> 3) & 0xf));
 	else {
 		if (get_vmx_mem_address(vcpu, exit_qualification,
 				vmx_instruction_info, &gva))
 			return 1;
 		if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva,
-			   &field_value, (is_long_mode(vcpu) ? 8 : 4), &e)) {
+			   &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
 			kvm_inject_page_fault(vcpu, &e);
 			return 1;
 		}
 	}
 
 
-	field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
 	if (vmcs_field_readonly(field)) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
@@ -6498,9 +6520,8 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 			skip_emulated_instruction(vcpu);
 			return 1;
 		}
-		if (vmx->nested.current_vmptr != -1ull)
-			nested_release_vmcs12(vmx);
 
+		nested_release_vmcs12(vmx);
 		vmx->nested.current_vmptr = vmptr;
 		vmx->nested.current_vmcs12 = new_vmcs12;
 		vmx->nested.current_vmcs12_page = page;
@@ -6571,7 +6592,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	}
 
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
+	type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf);
 
 	types = (nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
 
@@ -6751,7 +6772,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	int cr = exit_qualification & 15;
 	int reg = (exit_qualification >> 8) & 15;
-	unsigned long val = kvm_register_read(vcpu, reg);
+	unsigned long val = kvm_register_readl(vcpu, reg);
 
 	switch ((exit_qualification >> 4) & 3) {
 	case 0: /* mov to cr */
@@ -7112,7 +7133,26 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
 	if (max_irr == -1)
 		return;
 
-	vmx_set_rvi(max_irr);
+	/*
+	 * If a vmexit is needed, vmx_check_nested_events handles it.
+	 */
+	if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
+		return;
+
+	if (!is_guest_mode(vcpu)) {
+		vmx_set_rvi(max_irr);
+		return;
+	}
+
+	/*
+	 * Fall back to pre-APICv interrupt injection since L2
+	 * is run without virtual interrupt delivery.
+	 */
+	if (!kvm_event_needs_reinjection(vcpu) &&
+	    vmx_interrupt_allowed(vcpu)) {
+		kvm_queue_interrupt(vcpu, max_irr, false);
+		vmx_inject_irq(vcpu);
+	}
 }
 
 static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
@@ -7520,13 +7560,31 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx_complete_interrupts(vmx);
 }
 
+static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int cpu;
+
+	if (vmx->loaded_vmcs == &vmx->vmcs01)
+		return;
+
+	cpu = get_cpu();
+	vmx->loaded_vmcs = &vmx->vmcs01;
+	vmx_vcpu_put(vcpu);
+	vmx_vcpu_load(vcpu, cpu);
+	vcpu->cpu = cpu;
+	put_cpu();
+}
+
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
 	free_vpid(vmx);
-	free_loaded_vmcs(vmx->loaded_vmcs);
+	leave_guest_mode(vcpu);
+	vmx_load_vmcs01(vcpu);
 	free_nested(vmx);
+	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vmx);
@@ -7548,6 +7606,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 		goto free_vcpu;
 
 	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) * sizeof(vmx->guest_msrs[0])
+		     > PAGE_SIZE);
+
 	err = -ENOMEM;
 	if (!vmx->guest_msrs) {
 		goto uninit_vcpu;
@@ -7836,7 +7897,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
 	vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
 
-	vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) {
+		kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+	} else {
+		kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
+		vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
+	}
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
 		vmcs12->vm_entry_intr_info_field);
 	vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
@@ -7846,7 +7913,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
 		vmcs12->guest_interruptibility_info);
 	vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
-	kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
 	vmx_set_rflags(vcpu, vmcs12->guest_rflags);
 	vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
 		vmcs12->guest_pending_dbg_exceptions);
@@ -8113,14 +8179,14 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	}
 
 	if ((vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_MSR_BITMAPS) &&
-			!IS_ALIGNED(vmcs12->msr_bitmap, PAGE_SIZE)) {
+			!PAGE_ALIGNED(vmcs12->msr_bitmap)) {
 		/*TODO: Also verify bits beyond physical address width are 0*/
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 		return 1;
 	}
 
 	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
-			!IS_ALIGNED(vmcs12->apic_access_addr, PAGE_SIZE)) {
+			!PAGE_ALIGNED(vmcs12->apic_access_addr)) {
 		/*TODO: Also verify bits beyond physical address width are 0*/
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 		return 1;
@@ -8136,15 +8202,18 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	}
 
 	if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
-	      nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high) ||
+				nested_vmx_true_procbased_ctls_low,
+				nested_vmx_procbased_ctls_high) ||
 	    !vmx_control_verify(vmcs12->secondary_vm_exec_control,
 	      nested_vmx_secondary_ctls_low, nested_vmx_secondary_ctls_high) ||
 	    !vmx_control_verify(vmcs12->pin_based_vm_exec_control,
 	      nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high) ||
 	    !vmx_control_verify(vmcs12->vm_exit_controls,
-	      nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high) ||
+				nested_vmx_true_exit_ctls_low,
+				nested_vmx_exit_ctls_high) ||
 	    !vmx_control_verify(vmcs12->vm_entry_controls,
-	      nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high))
+				nested_vmx_true_entry_ctls_low,
+				nested_vmx_entry_ctls_high))
 	{
 		nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 		return 1;
@@ -8221,6 +8290,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 
 	vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET);
 
+	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
+		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+
 	cpu = get_cpu();
 	vmx->loaded_vmcs = vmcs02;
 	vmx_vcpu_put(vcpu);
@@ -8398,7 +8470,6 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12);
 	vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12);
 
-	kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7);
 	vmcs12->guest_rsp = kvm_register_read(vcpu, VCPU_REGS_RSP);
 	vmcs12->guest_rip = kvm_register_read(vcpu, VCPU_REGS_RIP);
 	vmcs12->guest_rflags = vmcs_readl(GUEST_RFLAGS);
@@ -8477,9 +8548,13 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
 		(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
 
+	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) {
+		kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7);
+		vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+	}
+
 	/* TODO: These cannot have changed unless we have MSR bitmaps and
 	 * the relevant bit asks not to trap the change */
-	vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
 	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT)
 		vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT);
 	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER)
@@ -8670,7 +8745,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 			      unsigned long exit_qualification)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int cpu;
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
 	/* trying to cancel vmlaunch/vmresume is a bug */
@@ -8695,12 +8769,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 				       vmcs12->vm_exit_intr_error_code,
 				       KVM_ISA_VMX);
 
-	cpu = get_cpu();
-	vmx->loaded_vmcs = &vmx->vmcs01;
-	vmx_vcpu_put(vcpu);
-	vmx_vcpu_load(vcpu, cpu);
-	vcpu->cpu = cpu;
-	put_cpu();
+	vmx_load_vmcs01(vcpu);
 
 	vm_entry_controls_init(vmx, vmcs_read32(VM_ENTRY_CONTROLS));
 	vm_exit_controls_init(vmx, vmcs_read32(VM_EXIT_CONTROLS));
@@ -8890,7 +8959,7 @@ static int __init vmx_init(void)
 
 	rdmsrl_safe(MSR_EFER, &host_efer);
 
-	for (i = 0; i < NR_VMX_MSR; ++i)
+	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)
 		kvm_define_shared_msr(i, vmx_msr_index[i]);
 
 	vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f32a02578c0..b86d329b953 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -87,6 +87,7 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
+static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 
 struct kvm_x86_ops *kvm_x86_ops;
 EXPORT_SYMBOL_GPL(kvm_x86_ops);
@@ -211,6 +212,7 @@ static void shared_msr_update(unsigned slot, u32 msr)
 
 void kvm_define_shared_msr(unsigned slot, u32 msr)
 {
+	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
 	if (slot >= shared_msrs_global.nr)
 		shared_msrs_global.nr = slot + 1;
 	shared_msrs_global.msrs[slot] = msr;
@@ -310,6 +312,31 @@ static int exception_class(int vector)
 	return EXCPT_BENIGN;
 }
 
+#define EXCPT_FAULT		0
+#define EXCPT_TRAP		1
+#define EXCPT_ABORT		2
+#define EXCPT_INTERRUPT		3
+
+static int exception_type(int vector)
+{
+	unsigned int mask;
+
+	if (WARN_ON(vector > 31 || vector == NMI_VECTOR))
+		return EXCPT_INTERRUPT;
+
+	mask = 1 << vector;
+
+	/* #DB is trap, as instruction watchpoints are handled elsewhere */
+	if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR)))
+		return EXCPT_TRAP;
+
+	if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR)))
+		return EXCPT_ABORT;
+
+	/* Reserved exceptions will result in fault */
+	return EXCPT_FAULT;
+}
+
 static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 		unsigned nr, bool has_error, u32 error_code,
 		bool reinject)
@@ -758,6 +785,15 @@ static void kvm_update_dr7(struct kvm_vcpu *vcpu)
 		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED;
 }
 
+static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
+{
+	u64 fixed = DR6_FIXED_1;
+
+	if (!guest_cpuid_has_rtm(vcpu))
+		fixed |= DR6_RTM;
+	return fixed;
+}
+
 static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 {
 	switch (dr) {
@@ -773,7 +809,7 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 	case 6:
 		if (val & 0xffffffff00000000ULL)
 			return -1; /* #GP */
-		vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
+		vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu);
 		kvm_update_dr6(vcpu);
 		break;
 	case 5:
@@ -1215,6 +1251,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	unsigned long flags;
 	s64 usdiff;
 	bool matched;
+	bool already_matched;
 	u64 data = msr->data;
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
@@ -1279,6 +1316,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
 		}
 		matched = true;
+		already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation);
 	} else {
 		/*
 		 * We split periods of matched TSC writes into generations.
@@ -1294,7 +1332,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		kvm->arch.cur_tsc_write = data;
 		kvm->arch.cur_tsc_offset = offset;
 		matched = false;
-		pr_debug("kvm: new tsc generation %u, clock %llu\n",
+		pr_debug("kvm: new tsc generation %llu, clock %llu\n",
 			 kvm->arch.cur_tsc_generation, data);
 	}
 
@@ -1319,10 +1357,11 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
 	spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
-	if (matched)
-		kvm->arch.nr_vcpus_matched_tsc++;
-	else
+	if (!matched) {
 		kvm->arch.nr_vcpus_matched_tsc = 0;
+	} else if (!already_matched) {
+		kvm->arch.nr_vcpus_matched_tsc++;
+	}
 
 	kvm_track_tsc_matching(vcpu);
 	spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
@@ -1898,7 +1937,7 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
 			break;
 		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
-		if (kvm_write_guest(kvm, data,
+		if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
 			&tsc_ref, sizeof(tsc_ref)))
 			return 1;
 		mark_page_dirty(kvm, gfn);
@@ -2032,6 +2071,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		data &= ~(u64)0x40;	/* ignore flush filter disable */
 		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
 		data &= ~(u64)0x8;	/* ignore TLB cache disable */
+		data &= ~(u64)0x40000;  /* ignore Mc status write enable */
 		if (data != 0) {
 			vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
 				    data);
@@ -2974,9 +3014,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 		vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft;
 	events->interrupt.nr = vcpu->arch.interrupt.nr;
 	events->interrupt.soft = 0;
-	events->interrupt.shadow =
-		kvm_x86_ops->get_interrupt_shadow(vcpu,
-			KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI);
+	events->interrupt.shadow = kvm_x86_ops->get_interrupt_shadow(vcpu);
 
 	events->nmi.injected = vcpu->arch.nmi_injected;
 	events->nmi.pending = vcpu->arch.nmi_pending != 0;
@@ -4082,7 +4120,8 @@ static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
 
 		if (gpa == UNMAPPED_GVA)
 			return X86EMUL_PROPAGATE_FAULT;
-		ret = kvm_read_guest(vcpu->kvm, gpa, data, toread);
+		ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, data,
+					  offset, toread);
 		if (ret < 0) {
 			r = X86EMUL_IO_NEEDED;
 			goto out;
@@ -4103,10 +4142,24 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+	unsigned offset;
+	int ret;
 
-	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu,
-					  access | PFERR_FETCH_MASK,
-					  exception);
+	/* Inline kvm_read_guest_virt_helper for speed.  */
+	gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access|PFERR_FETCH_MASK,
+						    exception);
+	if (unlikely(gpa == UNMAPPED_GVA))
+		return X86EMUL_PROPAGATE_FAULT;
+
+	offset = addr & (PAGE_SIZE-1);
+	if (WARN_ON(offset + bytes > PAGE_SIZE))
+		bytes = (unsigned)PAGE_SIZE - offset;
+	ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, val,
+				  offset, bytes);
+	if (unlikely(ret < 0))
+		return X86EMUL_IO_NEEDED;
+
+	return X86EMUL_CONTINUE;
 }
 
 int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt,
@@ -4730,7 +4783,6 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector,
 	if (desc->g)
 		var.limit = (var.limit << 12) | 0xfff;
 	var.type = desc->type;
-	var.present = desc->p;
 	var.dpl = desc->dpl;
 	var.db = desc->d;
 	var.s = desc->s;
@@ -4762,6 +4814,12 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
 	return kvm_set_msr(emul_to_vcpu(ctxt), &msr);
 }
 
+static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
+			      u32 pmc)
+{
+	return kvm_pmu_check_pmc(emul_to_vcpu(ctxt), pmc);
+}
+
 static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
 			     u32 pmc, u64 *pdata)
 {
@@ -4838,6 +4896,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.set_dr              = emulator_set_dr,
 	.set_msr             = emulator_set_msr,
 	.get_msr             = emulator_get_msr,
+	.check_pmc	     = emulator_check_pmc,
 	.read_pmc            = emulator_read_pmc,
 	.halt                = emulator_halt,
 	.wbinvd              = emulator_wbinvd,
@@ -4850,7 +4909,7 @@ static const struct x86_emulate_ops emulate_ops = {
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
 {
-	u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu, mask);
+	u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu);
 	/*
 	 * an sti; sti; sequence only disable interrupts for the first
 	 * instruction. So, if the last instruction, be it emulated or
@@ -4858,8 +4917,13 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
 	 * means that the last instruction is an sti. We should not
 	 * leave the flag on in this case. The same goes for mov ss
 	 */
-	if (!(int_shadow & mask))
+	if (int_shadow & mask)
+		mask = 0;
+	if (unlikely(int_shadow || mask)) {
 		kvm_x86_ops->set_interrupt_shadow(vcpu, mask);
+		if (!mask)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
+	}
 }
 
 static void inject_emulated_exception(struct kvm_vcpu *vcpu)
@@ -4874,19 +4938,6 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu)
 		kvm_queue_exception(vcpu, ctxt->exception.vector);
 }
 
-static void init_decode_cache(struct x86_emulate_ctxt *ctxt)
-{
-	memset(&ctxt->opcode_len, 0,
-	       (void *)&ctxt->_regs - (void *)&ctxt->opcode_len);
-
-	ctxt->fetch.start = 0;
-	ctxt->fetch.end = 0;
-	ctxt->io_read.pos = 0;
-	ctxt->io_read.end = 0;
-	ctxt->mem_read.pos = 0;
-	ctxt->mem_read.end = 0;
-}
-
 static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 {
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
@@ -5085,23 +5136,22 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 	return dr6;
 }
 
-static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r)
+static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
 	/*
-	 * Use the "raw" value to see if TF was passed to the processor.
-	 * Note that the new value of the flags has not been saved yet.
+	 * rflags is the old, "raw" value of the flags.  The new value has
+	 * not been saved yet.
 	 *
 	 * This is correct even for TF set by the guest, because "the
 	 * processor will not generate this exception after the instruction
 	 * that sets the TF flag".
 	 */
-	unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
-
 	if (unlikely(rflags & X86_EFLAGS_TF)) {
 		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-			kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1;
+			kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 |
+						  DR6_RTM;
 			kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
 			kvm_run->debug.arch.exception = DB_VECTOR;
 			kvm_run->exit_reason = KVM_EXIT_DEBUG;
@@ -5114,7 +5164,7 @@ static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r)
 			 * cleared by the processor".
 			 */
 			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= DR6_BS;
+			vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
 			kvm_queue_exception(vcpu, DB_VECTOR);
 		}
 	}
@@ -5133,7 +5183,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
 					   vcpu->arch.eff_db);
 
 		if (dr6 != 0) {
-			kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
+			kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM;
 			kvm_run->debug.arch.pc = kvm_rip_read(vcpu) +
 				get_segment_base(vcpu, VCPU_SREG_CS);
 
@@ -5144,14 +5194,15 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
 		}
 	}
 
-	if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK)) {
+	if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) &&
+	    !(kvm_get_rflags(vcpu) & X86_EFLAGS_RF)) {
 		dr6 = kvm_vcpu_check_hw_bp(eip, 0,
 					   vcpu->arch.dr7,
 					   vcpu->arch.db);
 
 		if (dr6 != 0) {
 			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= dr6;
+			vcpu->arch.dr6 |= dr6 | DR6_RTM;
 			kvm_queue_exception(vcpu, DB_VECTOR);
 			*r = EMULATE_DONE;
 			return true;
@@ -5215,6 +5266,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 	if (emulation_type & EMULTYPE_SKIP) {
 		kvm_rip_write(vcpu, ctxt->_eip);
+		if (ctxt->eflags & X86_EFLAGS_RF)
+			kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF);
 		return EMULATE_DONE;
 	}
 
@@ -5265,13 +5318,22 @@ restart:
 		r = EMULATE_DONE;
 
 	if (writeback) {
+		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
-		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
 		if (r == EMULATE_DONE)
-			kvm_vcpu_check_singlestep(vcpu, &r);
-		kvm_set_rflags(vcpu, ctxt->eflags);
+			kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+		__kvm_set_rflags(vcpu, ctxt->eflags);
+
+		/*
+		 * For STI, interrupts are shadowed; so KVM_REQ_EVENT will
+		 * do nothing, and it will be requested again as soon as
+		 * the shadow expires.  But we still need to check here,
+		 * because POPF has no interrupt shadow.
+		 */
+		if (unlikely((ctxt->eflags & ~rflags) & X86_EFLAGS_IF))
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 	} else
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = true;
 
@@ -5662,7 +5724,6 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	u64 param, ingpa, outgpa, ret;
 	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
 	bool fast, longmode;
-	int cs_db, cs_l;
 
 	/*
 	 * hypercall generates UD from non zero cpl and real mode
@@ -5673,8 +5734,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
-	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
-	longmode = is_long_mode(vcpu) && cs_l == 1;
+	longmode = is_64_bit_mode(vcpu);
 
 	if (!longmode) {
 		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
@@ -5739,7 +5799,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
-	int r = 1;
+	int op_64_bit, r = 1;
 
 	if (kvm_hv_hypercall_enabled(vcpu->kvm))
 		return kvm_hv_hypercall(vcpu);
@@ -5752,7 +5812,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 
 	trace_kvm_hypercall(nr, a0, a1, a2, a3);
 
-	if (!is_long_mode(vcpu)) {
+	op_64_bit = is_64_bit_mode(vcpu);
+	if (!op_64_bit) {
 		nr &= 0xFFFFFFFF;
 		a0 &= 0xFFFFFFFF;
 		a1 &= 0xFFFFFFFF;
@@ -5778,6 +5839,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		break;
 	}
 out:
+	if (!op_64_bit)
+		ret = (u32)ret;
 	kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
 	++vcpu->stat.hypercalls;
 	return r;
@@ -5856,6 +5919,11 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 		trace_kvm_inj_exception(vcpu->arch.exception.nr,
 					vcpu->arch.exception.has_error_code,
 					vcpu->arch.exception.error_code);
+
+		if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT)
+			__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
+					     X86_EFLAGS_RF);
+
 		kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
 					  vcpu->arch.exception.has_error_code,
 					  vcpu->arch.exception.error_code,
@@ -5887,6 +5955,18 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 			kvm_x86_ops->set_nmi(vcpu);
 		}
 	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
+		/*
+		 * Because interrupts can be injected asynchronously, we are
+		 * calling check_nested_events again here to avoid a race condition.
+		 * See https://lkml.org/lkml/2014/7/2/60 for discussion about this
+		 * proposal and current concerns.  Perhaps we should be setting
+		 * KVM_REQ_EVENT only on certain events and not unconditionally?
+		 */
+		if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+			r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+			if (r != 0)
+				return r;
+		}
 		if (kvm_x86_ops->interrupt_allowed(vcpu)) {
 			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
 					    false);
@@ -6835,9 +6915,11 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
 	atomic_set(&vcpu->arch.nmi_queued, 0);
 	vcpu->arch.nmi_pending = 0;
 	vcpu->arch.nmi_injected = false;
+	kvm_clear_interrupt_queue(vcpu);
+	kvm_clear_exception_queue(vcpu);
 
 	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
-	vcpu->arch.dr6 = DR6_FIXED_1;
+	vcpu->arch.dr6 = DR6_INIT;
 	kvm_update_dr6(vcpu);
 	vcpu->arch.dr7 = DR7_FIXED_1;
 	kvm_update_dr7(vcpu);
@@ -7393,12 +7475,17 @@ unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_get_rflags);
 
-void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP &&
 	    kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip))
 		rflags |= X86_EFLAGS_TF;
 	kvm_x86_ops->set_rflags(vcpu, rflags);
+}
+
+void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+{
+	__kvm_set_rflags(vcpu, rflags);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_set_rflags);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 8c97bac9a89..306a1b77581 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -47,6 +47,16 @@ static inline int is_long_mode(struct kvm_vcpu *vcpu)
 #endif
 }
 
+static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu)
+{
+	int cs_db, cs_l;
+
+	if (!is_long_mode(vcpu))
+		return false;
+	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
+	return cs_l;
+}
+
 static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
@@ -108,6 +118,23 @@ static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
 	return false;
 }
 
+static inline unsigned long kvm_register_readl(struct kvm_vcpu *vcpu,
+					       enum kvm_reg reg)
+{
+	unsigned long val = kvm_register_read(vcpu, reg);
+
+	return is_64_bit_mode(vcpu) ? val : (u32)val;
+}
+
+static inline void kvm_register_writel(struct kvm_vcpu *vcpu,
+				       enum kvm_reg reg,
+				       unsigned long val)
+{
+	if (!is_64_bit_mode(vcpu))
+		val = (u32)val;
+	return kvm_register_write(vcpu, reg, val);
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
index 2930ae05d77..28f85c91671 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/lib/thunk_32.S
@@ -4,8 +4,8 @@
  *  (inspired by Andi Kleen's thunk_64.S)
  * Subject to the GNU public license, v.2. No warranty of any kind.
  */
-
 	#include <linux/linkage.h>
+	#include <asm/asm.h>
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/* put return address in eax (arg1) */
@@ -22,6 +22,7 @@
 	popl %ecx
 	popl %eax
 	ret
+	_ASM_NOKPROBE(\name)
 	.endm
 
 	thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index a63efd6bb6a..92d9feaff42 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -8,6 +8,7 @@
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/calling.h>
+#include <asm/asm.h>
 
 	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 	.macro THUNK name, func, put_ret_addr_in_rdi=0
@@ -25,6 +26,7 @@
 	call \func
 	jmp  restore
 	CFI_ENDPROC
+	_ASM_NOKPROBE(\name)
 	.endm
 
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -43,3 +45,4 @@ restore:
 	RESTORE_ARGS
 	ret
 	CFI_ENDPROC
+	_ASM_NOKPROBE(restore)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9de4cdbf124..1dbade870f9 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -8,7 +8,7 @@
 #include <linux/kdebug.h>		/* oops_begin/end, ...		*/
 #include <linux/module.h>		/* search_exception_table	*/
 #include <linux/bootmem.h>		/* max_low_pfn			*/
-#include <linux/kprobes.h>		/* __kprobes, ...		*/
+#include <linux/kprobes.h>		/* NOKPROBE_SYMBOL, ...		*/
 #include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
 #include <linux/perf_event.h>		/* perf_sw_event		*/
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
@@ -46,7 +46,7 @@ enum x86_pf_error_code {
  * Returns 0 if mmiotrace is disabled, or if the fault is not
  * handled by mmiotrace:
  */
-static inline int __kprobes
+static nokprobe_inline int
 kmmio_fault(struct pt_regs *regs, unsigned long addr)
 {
 	if (unlikely(is_kmmio_active()))
@@ -55,7 +55,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
 	return 0;
 }
 
-static inline int __kprobes kprobes_fault(struct pt_regs *regs)
+static nokprobe_inline int kprobes_fault(struct pt_regs *regs)
 {
 	int ret = 0;
 
@@ -262,7 +262,7 @@ void vmalloc_sync_all(void)
  *
  *   Handle a fault on the vmalloc or module mapping area
  */
-static noinline __kprobes int vmalloc_fault(unsigned long address)
+static noinline int vmalloc_fault(unsigned long address)
 {
 	unsigned long pgd_paddr;
 	pmd_t *pmd_k;
@@ -292,6 +292,7 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 
 	return 0;
 }
+NOKPROBE_SYMBOL(vmalloc_fault);
 
 /*
  * Did it hit the DOS screen memory VA from vm86 mode?
@@ -359,7 +360,7 @@ void vmalloc_sync_all(void)
  *
  * This assumes no large pages in there.
  */
-static noinline __kprobes int vmalloc_fault(unsigned long address)
+static noinline int vmalloc_fault(unsigned long address)
 {
 	pgd_t *pgd, *pgd_ref;
 	pud_t *pud, *pud_ref;
@@ -426,6 +427,7 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 
 	return 0;
 }
+NOKPROBE_SYMBOL(vmalloc_fault);
 
 #ifdef CONFIG_CPU_SUP_AMD
 static const char errata93_warning[] =
@@ -934,7 +936,7 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte)
  * There are no security implications to leaving a stale TLB when
  * increasing the permissions on a page.
  */
-static noinline __kprobes int
+static noinline int
 spurious_fault(unsigned long error_code, unsigned long address)
 {
 	pgd_t *pgd;
@@ -982,6 +984,7 @@ spurious_fault(unsigned long error_code, unsigned long address)
 
 	return ret;
 }
+NOKPROBE_SYMBOL(spurious_fault);
 
 int show_unhandled_signals = 1;
 
@@ -1037,7 +1040,7 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs)
  * {,trace_}do_page_fault() have notrace on. Having this an actual function
  * guarantees there's a function trace entry.
  */
-static void __kprobes noinline
+static noinline void
 __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		unsigned long address)
 {
@@ -1260,8 +1263,9 @@ good_area:
 
 	up_read(&mm->mmap_sem);
 }
+NOKPROBE_SYMBOL(__do_page_fault);
 
-dotraplinkage void __kprobes notrace
+dotraplinkage void notrace
 do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
 	unsigned long address = read_cr2(); /* Get the faulting address */
@@ -1279,10 +1283,12 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
+NOKPROBE_SYMBOL(do_page_fault);
 
 #ifdef CONFIG_TRACING
-static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
-				     unsigned long error_code)
+static nokprobe_inline void
+trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
+			 unsigned long error_code)
 {
 	if (user_mode(regs))
 		trace_page_fault_user(address, regs, error_code);
@@ -1290,7 +1296,7 @@ static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs
 		trace_page_fault_kernel(address, regs, error_code);
 }
 
-dotraplinkage void __kprobes notrace
+dotraplinkage void notrace
 trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
 	/*
@@ -1307,4 +1313,5 @@ trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	__do_page_fault(regs, error_code, address);
 	exception_exit(prev_state);
 }
+NOKPROBE_SYMBOL(trace_do_page_fault);
 #endif /* CONFIG_TRACING */
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 01495755701..6440221ced0 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -12,13 +12,16 @@
 
 /*
  * Calling convention :
- * rdi : skb pointer
+ * rbx : skb pointer (callee saved)
  * esi : offset of byte(s) to fetch in skb (can be scratched)
- * r8  : copy of skb->data
+ * r10 : copy of skb->data
  * r9d : hlen = skb->len - skb->data_len
  */
-#define SKBDATA	%r8
+#define SKBDATA	%r10
 #define SKF_MAX_NEG_OFF    $(-0x200000) /* SKF_LL_OFF from filter.h */
+#define MAX_BPF_STACK (512 /* from filter.h */ + \
+	32 /* space for rbx,r13,r14,r15 */ + \
+	8 /* space for skb_copy_bits */)
 
 sk_load_word:
 	.globl	sk_load_word
@@ -68,53 +71,31 @@ sk_load_byte_positive_offset:
 	movzbl	(SKBDATA,%rsi),%eax
 	ret
 
-/**
- * sk_load_byte_msh - BPF_S_LDX_B_MSH helper
- *
- * Implements BPF_S_LDX_B_MSH : ldxb  4*([offset]&0xf)
- * Must preserve A accumulator (%eax)
- * Inputs : %esi is the offset value
- */
-sk_load_byte_msh:
-	.globl	sk_load_byte_msh
-	test	%esi,%esi
-	js	bpf_slow_path_byte_msh_neg
-
-sk_load_byte_msh_positive_offset:
-	.globl	sk_load_byte_msh_positive_offset
-	cmp	%esi,%r9d      /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
-	jle	bpf_slow_path_byte_msh
-	movzbl	(SKBDATA,%rsi),%ebx
-	and	$15,%bl
-	shl	$2,%bl
-	ret
-
 /* rsi contains offset and can be scratched */
 #define bpf_slow_path_common(LEN)		\
-	push	%rdi;    /* save skb */		\
+	mov	%rbx, %rdi; /* arg1 == skb */	\
 	push	%r9;				\
 	push	SKBDATA;			\
 /* rsi already has offset */			\
 	mov	$LEN,%ecx;	/* len */	\
-	lea	-12(%rbp),%rdx;			\
+	lea	- MAX_BPF_STACK + 32(%rbp),%rdx;			\
 	call	skb_copy_bits;			\
 	test    %eax,%eax;			\
 	pop	SKBDATA;			\
-	pop	%r9;				\
-	pop	%rdi
+	pop	%r9;
 
 
 bpf_slow_path_word:
 	bpf_slow_path_common(4)
 	js	bpf_error
-	mov	-12(%rbp),%eax
+	mov	- MAX_BPF_STACK + 32(%rbp),%eax
 	bswap	%eax
 	ret
 
 bpf_slow_path_half:
 	bpf_slow_path_common(2)
 	js	bpf_error
-	mov	-12(%rbp),%ax
+	mov	- MAX_BPF_STACK + 32(%rbp),%ax
 	rol	$8,%ax
 	movzwl	%ax,%eax
 	ret
@@ -122,21 +103,11 @@ bpf_slow_path_half:
 bpf_slow_path_byte:
 	bpf_slow_path_common(1)
 	js	bpf_error
-	movzbl	-12(%rbp),%eax
-	ret
-
-bpf_slow_path_byte_msh:
-	xchg	%eax,%ebx /* dont lose A , X is about to be scratched */
-	bpf_slow_path_common(1)
-	js	bpf_error
-	movzbl	-12(%rbp),%eax
-	and	$15,%al
-	shl	$2,%al
-	xchg	%eax,%ebx
+	movzbl	- MAX_BPF_STACK + 32(%rbp),%eax
 	ret
 
 #define sk_negative_common(SIZE)				\
-	push	%rdi;	/* save skb */				\
+	mov	%rbx, %rdi; /* arg1 == skb */			\
 	push	%r9;						\
 	push	SKBDATA;					\
 /* rsi already has offset */					\
@@ -145,10 +116,8 @@ bpf_slow_path_byte_msh:
 	test	%rax,%rax;					\
 	pop	SKBDATA;					\
 	pop	%r9;						\
-	pop	%rdi;						\
 	jz	bpf_error
 
-
 bpf_slow_path_word_neg:
 	cmp	SKF_MAX_NEG_OFF, %esi	/* test range */
 	jl	bpf_error	/* offset lower -> error  */
@@ -179,22 +148,12 @@ sk_load_byte_negative_offset:
 	movzbl	(%rax), %eax
 	ret
 
-bpf_slow_path_byte_msh_neg:
-	cmp	SKF_MAX_NEG_OFF, %esi
-	jl	bpf_error
-sk_load_byte_msh_negative_offset:
-	.globl	sk_load_byte_msh_negative_offset
-	xchg	%eax,%ebx /* dont lose A , X is about to be scratched */
-	sk_negative_common(1)
-	movzbl	(%rax),%eax
-	and	$15,%al
-	shl	$2,%al
-	xchg	%eax,%ebx
-	ret
-
 bpf_error:
 # force a return 0 from jit handler
-	xor		%eax,%eax
-	mov		-8(%rbp),%rbx
+	xor	%eax,%eax
+	mov	- MAX_BPF_STACK(%rbp),%rbx
+	mov	- MAX_BPF_STACK + 8(%rbp),%r13
+	mov	- MAX_BPF_STACK + 16(%rbp),%r14
+	mov	- MAX_BPF_STACK + 24(%rbp),%r15
 	leaveq
 	ret
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 6d5663a599a..99bef86ed6d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1,6 +1,7 @@
 /* bpf_jit_comp.c : BPF JIT compiler
  *
  * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com)
+ * Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -14,28 +15,16 @@
 #include <linux/if_vlan.h>
 #include <linux/random.h>
 
-/*
- * Conventions :
- *  EAX : BPF A accumulator
- *  EBX : BPF X accumulator
- *  RDI : pointer to skb   (first argument given to JIT function)
- *  RBP : frame pointer (even if CONFIG_FRAME_POINTER=n)
- *  ECX,EDX,ESI : scratch registers
- *  r9d : skb->len - skb->data_len (headlen)
- *  r8  : skb->data
- * -8(RBP) : saved RBX value
- * -16(RBP)..-80(RBP) : BPF_MEMWORDS values
- */
 int bpf_jit_enable __read_mostly;
 
 /*
  * assembly code in arch/x86/net/bpf_jit.S
  */
-extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
+extern u8 sk_load_word[], sk_load_half[], sk_load_byte[];
 extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
-extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_byte_positive_offset[];
 extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
-extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
+extern u8 sk_load_byte_negative_offset[];
 
 static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -56,30 +45,44 @@ static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT2(b1, b2)		EMIT((b1) + ((b2) << 8), 2)
 #define EMIT3(b1, b2, b3)	EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3)
 #define EMIT4(b1, b2, b3, b4)   EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4)
-#define EMIT1_off32(b1, off)	do { EMIT1(b1); EMIT(off, 4);} while (0)
-
-#define CLEAR_A() EMIT2(0x31, 0xc0) /* xor %eax,%eax */
-#define CLEAR_X() EMIT2(0x31, 0xdb) /* xor %ebx,%ebx */
+#define EMIT1_off32(b1, off) \
+	do {EMIT1(b1); EMIT(off, 4); } while (0)
+#define EMIT2_off32(b1, b2, off) \
+	do {EMIT2(b1, b2); EMIT(off, 4); } while (0)
+#define EMIT3_off32(b1, b2, b3, off) \
+	do {EMIT3(b1, b2, b3); EMIT(off, 4); } while (0)
+#define EMIT4_off32(b1, b2, b3, b4, off) \
+	do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
 
 static inline bool is_imm8(int value)
 {
 	return value <= 127 && value >= -128;
 }
 
-static inline bool is_near(int offset)
+static inline bool is_simm32(s64 value)
 {
-	return offset <= 127 && offset >= -128;
+	return value == (s64) (s32) value;
 }
 
-#define EMIT_JMP(offset)						\
-do {									\
-	if (offset) {							\
-		if (is_near(offset))					\
-			EMIT2(0xeb, offset); /* jmp .+off8 */		\
-		else							\
-			EMIT1_off32(0xe9, offset); /* jmp .+off32 */	\
-	}								\
-} while (0)
+/* mov dst, src */
+#define EMIT_mov(DST, SRC) \
+	do {if (DST != SRC) \
+		EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \
+	} while (0)
+
+static int bpf_size_to_x86_bytes(int bpf_size)
+{
+	if (bpf_size == BPF_W)
+		return 4;
+	else if (bpf_size == BPF_H)
+		return 2;
+	else if (bpf_size == BPF_B)
+		return 1;
+	else if (bpf_size == BPF_DW)
+		return 4; /* imm32 */
+	else
+		return 0;
+}
 
 /* list of x86 cond jumps opcodes (. + s8)
  * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32)
@@ -90,27 +93,8 @@ do {									\
 #define X86_JNE 0x75
 #define X86_JBE 0x76
 #define X86_JA  0x77
-
-#define EMIT_COND_JMP(op, offset)				\
-do {								\
-	if (is_near(offset))					\
-		EMIT2(op, offset); /* jxx .+off8 */		\
-	else {							\
-		EMIT2(0x0f, op + 0x10);				\
-		EMIT(offset, 4); /* jxx .+off32 */		\
-	}							\
-} while (0)
-
-#define COND_SEL(CODE, TOP, FOP)	\
-	case CODE:			\
-		t_op = TOP;		\
-		f_op = FOP;		\
-		goto cond_branch
-
-
-#define SEEN_DATAREF 1 /* might call external helpers */
-#define SEEN_XREG    2 /* ebx is used */
-#define SEEN_MEM     4 /* use mem[] for temporary storage */
+#define X86_JGE 0x7D
+#define X86_JG  0x7F
 
 static inline void bpf_flush_icache(void *start, void *end)
 {
@@ -125,26 +109,6 @@ static inline void bpf_flush_icache(void *start, void *end)
 #define CHOOSE_LOAD_FUNC(K, func) \
 	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
-/* Helper to find the offset of pkt_type in sk_buff
- * We want to make sure its still a 3bit field starting at a byte boundary.
- */
-#define PKT_TYPE_MAX 7
-static int pkt_type_offset(void)
-{
-	struct sk_buff skb_probe = {
-		.pkt_type = ~0,
-	};
-	char *ct = (char *)&skb_probe;
-	unsigned int off;
-
-	for (off = 0; off < sizeof(struct sk_buff); off++) {
-		if (ct[off] == PKT_TYPE_MAX)
-			return off;
-	}
-	pr_err_once("Please fix pkt_type_offset(), as pkt_type couldn't be found\n");
-	return -1;
-}
-
 struct bpf_binary_header {
 	unsigned int	pages;
 	/* Note : for security reasons, bpf code will follow a randomly
@@ -178,583 +142,771 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen,
 	return header;
 }
 
-void bpf_jit_compile(struct sk_filter *fp)
+/* pick a register outside of BPF range for JIT internal work */
+#define AUX_REG (MAX_BPF_REG + 1)
+
+/* the following table maps BPF registers to x64 registers.
+ * x64 register r12 is unused, since if used as base address register
+ * in load/store instructions, it always needs an extra byte of encoding
+ */
+static const int reg2hex[] = {
+	[BPF_REG_0] = 0,  /* rax */
+	[BPF_REG_1] = 7,  /* rdi */
+	[BPF_REG_2] = 6,  /* rsi */
+	[BPF_REG_3] = 2,  /* rdx */
+	[BPF_REG_4] = 1,  /* rcx */
+	[BPF_REG_5] = 0,  /* r8 */
+	[BPF_REG_6] = 3,  /* rbx callee saved */
+	[BPF_REG_7] = 5,  /* r13 callee saved */
+	[BPF_REG_8] = 6,  /* r14 callee saved */
+	[BPF_REG_9] = 7,  /* r15 callee saved */
+	[BPF_REG_FP] = 5, /* rbp readonly */
+	[AUX_REG] = 3,    /* r11 temp register */
+};
+
+/* is_ereg() == true if BPF register 'reg' maps to x64 r8..r15
+ * which need extra byte of encoding.
+ * rax,rcx,...,rbp have simpler encoding
+ */
+static inline bool is_ereg(u32 reg)
 {
-	u8 temp[64];
-	u8 *prog;
-	unsigned int proglen, oldproglen = 0;
-	int ilen, i;
-	int t_offset, f_offset;
-	u8 t_op, f_op, seen = 0, pass;
-	u8 *image = NULL;
-	struct bpf_binary_header *header = NULL;
-	u8 *func;
-	int pc_ret0 = -1; /* bpf index of first RET #0 instruction (if any) */
-	unsigned int cleanup_addr; /* epilogue code offset */
-	unsigned int *addrs;
-	const struct sock_filter *filter = fp->insns;
-	int flen = fp->len;
+	if (reg == BPF_REG_5 || reg == AUX_REG ||
+	    (reg >= BPF_REG_7 && reg <= BPF_REG_9))
+		return true;
+	else
+		return false;
+}
 
-	if (!bpf_jit_enable)
-		return;
+/* add modifiers if 'reg' maps to x64 registers r8..r15 */
+static inline u8 add_1mod(u8 byte, u32 reg)
+{
+	if (is_ereg(reg))
+		byte |= 1;
+	return byte;
+}
 
-	addrs = kmalloc(flen * sizeof(*addrs), GFP_KERNEL);
-	if (addrs == NULL)
-		return;
+static inline u8 add_2mod(u8 byte, u32 r1, u32 r2)
+{
+	if (is_ereg(r1))
+		byte |= 1;
+	if (is_ereg(r2))
+		byte |= 4;
+	return byte;
+}
 
-	/* Before first pass, make a rough estimation of addrs[]
-	 * each bpf instruction is translated to less than 64 bytes
+/* encode 'dst_reg' register into x64 opcode 'byte' */
+static inline u8 add_1reg(u8 byte, u32 dst_reg)
+{
+	return byte + reg2hex[dst_reg];
+}
+
+/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */
+static inline u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
+{
+	return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
+}
+
+struct jit_context {
+	unsigned int cleanup_addr; /* epilogue code offset */
+	bool seen_ld_abs;
+};
+
+static int do_jit(struct sk_filter *bpf_prog, int *addrs, u8 *image,
+		  int oldproglen, struct jit_context *ctx)
+{
+	struct sock_filter_int *insn = bpf_prog->insnsi;
+	int insn_cnt = bpf_prog->len;
+	u8 temp[64];
+	int i;
+	int proglen = 0;
+	u8 *prog = temp;
+	int stacksize = MAX_BPF_STACK +
+		32 /* space for rbx, r13, r14, r15 */ +
+		8 /* space for skb_copy_bits() buffer */;
+
+	EMIT1(0x55); /* push rbp */
+	EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */
+
+	/* sub rsp, stacksize */
+	EMIT3_off32(0x48, 0x81, 0xEC, stacksize);
+
+	/* all classic BPF filters use R6(rbx) save it */
+
+	/* mov qword ptr [rbp-X],rbx */
+	EMIT3_off32(0x48, 0x89, 0x9D, -stacksize);
+
+	/* sk_convert_filter() maps classic BPF register X to R7 and uses R8
+	 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and
+	 * R8(r14). R9(r15) spill could be made conditional, but there is only
+	 * one 'bpf_error' return path out of helper functions inside bpf_jit.S
+	 * The overhead of extra spill is negligible for any filter other
+	 * than synthetic ones. Therefore not worth adding complexity.
 	 */
-	for (proglen = 0, i = 0; i < flen; i++) {
-		proglen += 64;
-		addrs[i] = proglen;
+
+	/* mov qword ptr [rbp-X],r13 */
+	EMIT3_off32(0x4C, 0x89, 0xAD, -stacksize + 8);
+	/* mov qword ptr [rbp-X],r14 */
+	EMIT3_off32(0x4C, 0x89, 0xB5, -stacksize + 16);
+	/* mov qword ptr [rbp-X],r15 */
+	EMIT3_off32(0x4C, 0x89, 0xBD, -stacksize + 24);
+
+	/* clear A and X registers */
+	EMIT2(0x31, 0xc0); /* xor eax, eax */
+	EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */
+
+	if (ctx->seen_ld_abs) {
+		/* r9d : skb->len - skb->data_len (headlen)
+		 * r10 : skb->data
+		 */
+		if (is_imm8(offsetof(struct sk_buff, len)))
+			/* mov %r9d, off8(%rdi) */
+			EMIT4(0x44, 0x8b, 0x4f,
+			      offsetof(struct sk_buff, len));
+		else
+			/* mov %r9d, off32(%rdi) */
+			EMIT3_off32(0x44, 0x8b, 0x8f,
+				    offsetof(struct sk_buff, len));
+
+		if (is_imm8(offsetof(struct sk_buff, data_len)))
+			/* sub %r9d, off8(%rdi) */
+			EMIT4(0x44, 0x2b, 0x4f,
+			      offsetof(struct sk_buff, data_len));
+		else
+			EMIT3_off32(0x44, 0x2b, 0x8f,
+				    offsetof(struct sk_buff, data_len));
+
+		if (is_imm8(offsetof(struct sk_buff, data)))
+			/* mov %r10, off8(%rdi) */
+			EMIT4(0x4c, 0x8b, 0x57,
+			      offsetof(struct sk_buff, data));
+		else
+			/* mov %r10, off32(%rdi) */
+			EMIT3_off32(0x4c, 0x8b, 0x97,
+				    offsetof(struct sk_buff, data));
 	}
-	cleanup_addr = proglen; /* epilogue address */
 
-	for (pass = 0; pass < 10; pass++) {
-		u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
-		/* no prologue/epilogue for trivial filters (RET something) */
-		proglen = 0;
-		prog = temp;
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		const s32 imm32 = insn->imm;
+		u32 dst_reg = insn->dst_reg;
+		u32 src_reg = insn->src_reg;
+		u8 b1 = 0, b2 = 0, b3 = 0;
+		s64 jmp_offset;
+		u8 jmp_cond;
+		int ilen;
+		u8 *func;
+
+		switch (insn->code) {
+			/* ALU */
+		case BPF_ALU | BPF_ADD | BPF_X:
+		case BPF_ALU | BPF_SUB | BPF_X:
+		case BPF_ALU | BPF_AND | BPF_X:
+		case BPF_ALU | BPF_OR | BPF_X:
+		case BPF_ALU | BPF_XOR | BPF_X:
+		case BPF_ALU64 | BPF_ADD | BPF_X:
+		case BPF_ALU64 | BPF_SUB | BPF_X:
+		case BPF_ALU64 | BPF_AND | BPF_X:
+		case BPF_ALU64 | BPF_OR | BPF_X:
+		case BPF_ALU64 | BPF_XOR | BPF_X:
+			switch (BPF_OP(insn->code)) {
+			case BPF_ADD: b2 = 0x01; break;
+			case BPF_SUB: b2 = 0x29; break;
+			case BPF_AND: b2 = 0x21; break;
+			case BPF_OR: b2 = 0x09; break;
+			case BPF_XOR: b2 = 0x31; break;
+			}
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_2mod(0x48, dst_reg, src_reg));
+			else if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
+			break;
 
-		if (seen_or_pass0) {
-			EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */
-			EMIT4(0x48, 0x83, 0xec, 96);	/* subq  $96,%rsp	*/
-			/* note : must save %rbx in case bpf_error is hit */
-			if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF))
-				EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */
-			if (seen_or_pass0 & SEEN_XREG)
-				CLEAR_X(); /* make sure we dont leek kernel memory */
-
-			/*
-			 * If this filter needs to access skb data,
-			 * loads r9 and r8 with :
-			 *  r9 = skb->len - skb->data_len
-			 *  r8 = skb->data
+			/* mov dst, src */
+		case BPF_ALU64 | BPF_MOV | BPF_X:
+			EMIT_mov(dst_reg, src_reg);
+			break;
+
+			/* mov32 dst, src */
+		case BPF_ALU | BPF_MOV | BPF_X:
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT1(add_2mod(0x40, dst_reg, src_reg));
+			EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
+			break;
+
+			/* neg dst */
+		case BPF_ALU | BPF_NEG:
+		case BPF_ALU64 | BPF_NEG:
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_1mod(0x48, dst_reg));
+			else if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
+			EMIT2(0xF7, add_1reg(0xD8, dst_reg));
+			break;
+
+		case BPF_ALU | BPF_ADD | BPF_K:
+		case BPF_ALU | BPF_SUB | BPF_K:
+		case BPF_ALU | BPF_AND | BPF_K:
+		case BPF_ALU | BPF_OR | BPF_K:
+		case BPF_ALU | BPF_XOR | BPF_K:
+		case BPF_ALU64 | BPF_ADD | BPF_K:
+		case BPF_ALU64 | BPF_SUB | BPF_K:
+		case BPF_ALU64 | BPF_AND | BPF_K:
+		case BPF_ALU64 | BPF_OR | BPF_K:
+		case BPF_ALU64 | BPF_XOR | BPF_K:
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_1mod(0x48, dst_reg));
+			else if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
+
+			switch (BPF_OP(insn->code)) {
+			case BPF_ADD: b3 = 0xC0; break;
+			case BPF_SUB: b3 = 0xE8; break;
+			case BPF_AND: b3 = 0xE0; break;
+			case BPF_OR: b3 = 0xC8; break;
+			case BPF_XOR: b3 = 0xF0; break;
+			}
+
+			if (is_imm8(imm32))
+				EMIT3(0x83, add_1reg(b3, dst_reg), imm32);
+			else
+				EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32);
+			break;
+
+		case BPF_ALU64 | BPF_MOV | BPF_K:
+			/* optimization: if imm32 is positive,
+			 * use 'mov eax, imm32' (which zero-extends imm32)
+			 * to save 2 bytes
 			 */
-			if (seen_or_pass0 & SEEN_DATAREF) {
-				if (offsetof(struct sk_buff, len) <= 127)
-					/* mov    off8(%rdi),%r9d */
-					EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len));
-				else {
-					/* mov    off32(%rdi),%r9d */
-					EMIT3(0x44, 0x8b, 0x8f);
-					EMIT(offsetof(struct sk_buff, len), 4);
-				}
-				if (is_imm8(offsetof(struct sk_buff, data_len)))
-					/* sub    off8(%rdi),%r9d */
-					EMIT4(0x44, 0x2b, 0x4f, offsetof(struct sk_buff, data_len));
-				else {
-					EMIT3(0x44, 0x2b, 0x8f);
-					EMIT(offsetof(struct sk_buff, data_len), 4);
-				}
+			if (imm32 < 0) {
+				/* 'mov rax, imm32' sign extends imm32 */
+				b1 = add_1mod(0x48, dst_reg);
+				b2 = 0xC7;
+				b3 = 0xC0;
+				EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
+				break;
+			}
 
-				if (is_imm8(offsetof(struct sk_buff, data)))
-					/* mov off8(%rdi),%r8 */
-					EMIT4(0x4c, 0x8b, 0x47, offsetof(struct sk_buff, data));
-				else {
-					/* mov off32(%rdi),%r8 */
-					EMIT3(0x4c, 0x8b, 0x87);
-					EMIT(offsetof(struct sk_buff, data), 4);
-				}
+		case BPF_ALU | BPF_MOV | BPF_K:
+			/* mov %eax, imm32 */
+			if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
+			EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
+			break;
+
+			/* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */
+		case BPF_ALU | BPF_MOD | BPF_X:
+		case BPF_ALU | BPF_DIV | BPF_X:
+		case BPF_ALU | BPF_MOD | BPF_K:
+		case BPF_ALU | BPF_DIV | BPF_K:
+		case BPF_ALU64 | BPF_MOD | BPF_X:
+		case BPF_ALU64 | BPF_DIV | BPF_X:
+		case BPF_ALU64 | BPF_MOD | BPF_K:
+		case BPF_ALU64 | BPF_DIV | BPF_K:
+			EMIT1(0x50); /* push rax */
+			EMIT1(0x52); /* push rdx */
+
+			if (BPF_SRC(insn->code) == BPF_X)
+				/* mov r11, src_reg */
+				EMIT_mov(AUX_REG, src_reg);
+			else
+				/* mov r11, imm32 */
+				EMIT3_off32(0x49, 0xC7, 0xC3, imm32);
+
+			/* mov rax, dst_reg */
+			EMIT_mov(BPF_REG_0, dst_reg);
+
+			/* xor edx, edx
+			 * equivalent to 'xor rdx, rdx', but one byte less
+			 */
+			EMIT2(0x31, 0xd2);
+
+			if (BPF_SRC(insn->code) == BPF_X) {
+				/* if (src_reg == 0) return 0 */
+
+				/* cmp r11, 0 */
+				EMIT4(0x49, 0x83, 0xFB, 0x00);
+
+				/* jne .+9 (skip over pop, pop, xor and jmp) */
+				EMIT2(X86_JNE, 1 + 1 + 2 + 5);
+				EMIT1(0x5A); /* pop rdx */
+				EMIT1(0x58); /* pop rax */
+				EMIT2(0x31, 0xc0); /* xor eax, eax */
+
+				/* jmp cleanup_addr
+				 * addrs[i] - 11, because there are 11 bytes
+				 * after this insn: div, mov, pop, pop, mov
+				 */
+				jmp_offset = ctx->cleanup_addr - (addrs[i] - 11);
+				EMIT1_off32(0xE9, jmp_offset);
 			}
-		}
 
-		switch (filter[0].code) {
-		case BPF_S_RET_K:
-		case BPF_S_LD_W_LEN:
-		case BPF_S_ANC_PROTOCOL:
-		case BPF_S_ANC_IFINDEX:
-		case BPF_S_ANC_MARK:
-		case BPF_S_ANC_RXHASH:
-		case BPF_S_ANC_CPU:
-		case BPF_S_ANC_VLAN_TAG:
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
-		case BPF_S_ANC_QUEUE:
-		case BPF_S_ANC_PKTTYPE:
-		case BPF_S_LD_W_ABS:
-		case BPF_S_LD_H_ABS:
-		case BPF_S_LD_B_ABS:
-			/* first instruction sets A register (or is RET 'constant') */
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				/* div r11 */
+				EMIT3(0x49, 0xF7, 0xF3);
+			else
+				/* div r11d */
+				EMIT3(0x41, 0xF7, 0xF3);
+
+			if (BPF_OP(insn->code) == BPF_MOD)
+				/* mov r11, rdx */
+				EMIT3(0x49, 0x89, 0xD3);
+			else
+				/* mov r11, rax */
+				EMIT3(0x49, 0x89, 0xC3);
+
+			EMIT1(0x5A); /* pop rdx */
+			EMIT1(0x58); /* pop rax */
+
+			/* mov dst_reg, r11 */
+			EMIT_mov(dst_reg, AUX_REG);
 			break;
-		default:
-			/* make sure we dont leak kernel information to user */
-			CLEAR_A(); /* A = 0 */
-		}
 
-		for (i = 0; i < flen; i++) {
-			unsigned int K = filter[i].k;
+		case BPF_ALU | BPF_MUL | BPF_K:
+		case BPF_ALU | BPF_MUL | BPF_X:
+		case BPF_ALU64 | BPF_MUL | BPF_K:
+		case BPF_ALU64 | BPF_MUL | BPF_X:
+			EMIT1(0x50); /* push rax */
+			EMIT1(0x52); /* push rdx */
+
+			/* mov r11, dst_reg */
+			EMIT_mov(AUX_REG, dst_reg);
+
+			if (BPF_SRC(insn->code) == BPF_X)
+				/* mov rax, src_reg */
+				EMIT_mov(BPF_REG_0, src_reg);
+			else
+				/* mov rax, imm32 */
+				EMIT3_off32(0x48, 0xC7, 0xC0, imm32);
+
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_1mod(0x48, AUX_REG));
+			else if (is_ereg(AUX_REG))
+				EMIT1(add_1mod(0x40, AUX_REG));
+			/* mul(q) r11 */
+			EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
+
+			/* mov r11, rax */
+			EMIT_mov(AUX_REG, BPF_REG_0);
+
+			EMIT1(0x5A); /* pop rdx */
+			EMIT1(0x58); /* pop rax */
+
+			/* mov dst_reg, r11 */
+			EMIT_mov(dst_reg, AUX_REG);
+			break;
 
-			switch (filter[i].code) {
-			case BPF_S_ALU_ADD_X: /* A += X; */
-				seen |= SEEN_XREG;
-				EMIT2(0x01, 0xd8);		/* add %ebx,%eax */
-				break;
-			case BPF_S_ALU_ADD_K: /* A += K; */
-				if (!K)
-					break;
-				if (is_imm8(K))
-					EMIT3(0x83, 0xc0, K);	/* add imm8,%eax */
-				else
-					EMIT1_off32(0x05, K);	/* add imm32,%eax */
-				break;
-			case BPF_S_ALU_SUB_X: /* A -= X; */
-				seen |= SEEN_XREG;
-				EMIT2(0x29, 0xd8);		/* sub    %ebx,%eax */
-				break;
-			case BPF_S_ALU_SUB_K: /* A -= K */
-				if (!K)
-					break;
-				if (is_imm8(K))
-					EMIT3(0x83, 0xe8, K); /* sub imm8,%eax */
-				else
-					EMIT1_off32(0x2d, K); /* sub imm32,%eax */
-				break;
-			case BPF_S_ALU_MUL_X: /* A *= X; */
-				seen |= SEEN_XREG;
-				EMIT3(0x0f, 0xaf, 0xc3);	/* imul %ebx,%eax */
-				break;
-			case BPF_S_ALU_MUL_K: /* A *= K */
-				if (is_imm8(K))
-					EMIT3(0x6b, 0xc0, K); /* imul imm8,%eax,%eax */
-				else {
-					EMIT2(0x69, 0xc0);		/* imul imm32,%eax */
-					EMIT(K, 4);
-				}
-				break;
-			case BPF_S_ALU_DIV_X: /* A /= X; */
-				seen |= SEEN_XREG;
-				EMIT2(0x85, 0xdb);	/* test %ebx,%ebx */
-				if (pc_ret0 > 0) {
-					/* addrs[pc_ret0 - 1] is start address of target
-					 * (addrs[i] - 4) is the address following this jmp
-					 * ("xor %edx,%edx; div %ebx" being 4 bytes long)
-					 */
-					EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] -
-								(addrs[i] - 4));
-				} else {
-					EMIT_COND_JMP(X86_JNE, 2 + 5);
-					CLEAR_A();
-					EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */
-				}
-				EMIT4(0x31, 0xd2, 0xf7, 0xf3); /* xor %edx,%edx; div %ebx */
-				break;
-			case BPF_S_ALU_MOD_X: /* A %= X; */
-				seen |= SEEN_XREG;
-				EMIT2(0x85, 0xdb);	/* test %ebx,%ebx */
-				if (pc_ret0 > 0) {
-					/* addrs[pc_ret0 - 1] is start address of target
-					 * (addrs[i] - 6) is the address following this jmp
-					 * ("xor %edx,%edx; div %ebx;mov %edx,%eax" being 6 bytes long)
-					 */
-					EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] -
-								(addrs[i] - 6));
-				} else {
-					EMIT_COND_JMP(X86_JNE, 2 + 5);
-					CLEAR_A();
-					EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 6)); /* jmp .+off32 */
-				}
-				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
-				EMIT2(0xf7, 0xf3);	/* div %ebx */
-				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
-				break;
-			case BPF_S_ALU_MOD_K: /* A %= K; */
-				if (K == 1) {
-					CLEAR_A();
-					break;
-				}
-				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
-				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
-				EMIT2(0xf7, 0xf1);	/* div %ecx */
-				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
-				break;
-			case BPF_S_ALU_DIV_K: /* A /= K */
-				if (K == 1)
-					break;
-				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
-				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
-				EMIT2(0xf7, 0xf1);	/* div %ecx */
-				break;
-			case BPF_S_ALU_AND_X:
-				seen |= SEEN_XREG;
-				EMIT2(0x21, 0xd8);		/* and %ebx,%eax */
-				break;
-			case BPF_S_ALU_AND_K:
-				if (K >= 0xFFFFFF00) {
-					EMIT2(0x24, K & 0xFF); /* and imm8,%al */
-				} else if (K >= 0xFFFF0000) {
-					EMIT2(0x66, 0x25);	/* and imm16,%ax */
-					EMIT(K, 2);
-				} else {
-					EMIT1_off32(0x25, K);	/* and imm32,%eax */
-				}
-				break;
-			case BPF_S_ALU_OR_X:
-				seen |= SEEN_XREG;
-				EMIT2(0x09, 0xd8);		/* or %ebx,%eax */
-				break;
-			case BPF_S_ALU_OR_K:
-				if (is_imm8(K))
-					EMIT3(0x83, 0xc8, K); /* or imm8,%eax */
-				else
-					EMIT1_off32(0x0d, K);	/* or imm32,%eax */
-				break;
-			case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */
-			case BPF_S_ALU_XOR_X:
-				seen |= SEEN_XREG;
-				EMIT2(0x31, 0xd8);		/* xor %ebx,%eax */
-				break;
-			case BPF_S_ALU_XOR_K: /* A ^= K; */
-				if (K == 0)
-					break;
-				if (is_imm8(K))
-					EMIT3(0x83, 0xf0, K);	/* xor imm8,%eax */
-				else
-					EMIT1_off32(0x35, K);	/* xor imm32,%eax */
-				break;
-			case BPF_S_ALU_LSH_X: /* A <<= X; */
-				seen |= SEEN_XREG;
-				EMIT4(0x89, 0xd9, 0xd3, 0xe0);	/* mov %ebx,%ecx; shl %cl,%eax */
-				break;
-			case BPF_S_ALU_LSH_K:
-				if (K == 0)
-					break;
-				else if (K == 1)
-					EMIT2(0xd1, 0xe0); /* shl %eax */
-				else
-					EMIT3(0xc1, 0xe0, K);
-				break;
-			case BPF_S_ALU_RSH_X: /* A >>= X; */
-				seen |= SEEN_XREG;
-				EMIT4(0x89, 0xd9, 0xd3, 0xe8);	/* mov %ebx,%ecx; shr %cl,%eax */
-				break;
-			case BPF_S_ALU_RSH_K: /* A >>= K; */
-				if (K == 0)
-					break;
-				else if (K == 1)
-					EMIT2(0xd1, 0xe8); /* shr %eax */
-				else
-					EMIT3(0xc1, 0xe8, K);
-				break;
-			case BPF_S_ALU_NEG:
-				EMIT2(0xf7, 0xd8);		/* neg %eax */
-				break;
-			case BPF_S_RET_K:
-				if (!K) {
-					if (pc_ret0 == -1)
-						pc_ret0 = i;
-					CLEAR_A();
-				} else {
-					EMIT1_off32(0xb8, K);	/* mov $imm32,%eax */
-				}
-				/* fallinto */
-			case BPF_S_RET_A:
-				if (seen_or_pass0) {
-					if (i != flen - 1) {
-						EMIT_JMP(cleanup_addr - addrs[i]);
-						break;
-					}
-					if (seen_or_pass0 & SEEN_XREG)
-						EMIT4(0x48, 0x8b, 0x5d, 0xf8);  /* mov  -8(%rbp),%rbx */
-					EMIT1(0xc9);		/* leaveq */
-				}
-				EMIT1(0xc3);		/* ret */
-				break;
-			case BPF_S_MISC_TAX: /* X = A */
-				seen |= SEEN_XREG;
-				EMIT2(0x89, 0xc3);	/* mov    %eax,%ebx */
-				break;
-			case BPF_S_MISC_TXA: /* A = X */
-				seen |= SEEN_XREG;
-				EMIT2(0x89, 0xd8);	/* mov    %ebx,%eax */
-				break;
-			case BPF_S_LD_IMM: /* A = K */
-				if (!K)
-					CLEAR_A();
-				else
-					EMIT1_off32(0xb8, K); /* mov $imm32,%eax */
-				break;
-			case BPF_S_LDX_IMM: /* X = K */
-				seen |= SEEN_XREG;
-				if (!K)
-					CLEAR_X();
+			/* shifts */
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_K:
+		case BPF_ALU | BPF_ARSH | BPF_K:
+		case BPF_ALU64 | BPF_LSH | BPF_K:
+		case BPF_ALU64 | BPF_RSH | BPF_K:
+		case BPF_ALU64 | BPF_ARSH | BPF_K:
+			if (BPF_CLASS(insn->code) == BPF_ALU64)
+				EMIT1(add_1mod(0x48, dst_reg));
+			else if (is_ereg(dst_reg))
+				EMIT1(add_1mod(0x40, dst_reg));
+
+			switch (BPF_OP(insn->code)) {
+			case BPF_LSH: b3 = 0xE0; break;
+			case BPF_RSH: b3 = 0xE8; break;
+			case BPF_ARSH: b3 = 0xF8; break;
+			}
+			EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
+			break;
+
+		case BPF_ALU | BPF_END | BPF_FROM_BE:
+			switch (imm32) {
+			case 16:
+				/* emit 'ror %ax, 8' to swap lower 2 bytes */
+				EMIT1(0x66);
+				if (is_ereg(dst_reg))
+					EMIT1(0x41);
+				EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8);
+				break;
+			case 32:
+				/* emit 'bswap eax' to swap lower 4 bytes */
+				if (is_ereg(dst_reg))
+					EMIT2(0x41, 0x0F);
 				else
-					EMIT1_off32(0xbb, K); /* mov $imm32,%ebx */
-				break;
-			case BPF_S_LD_MEM: /* A = mem[K] : mov off8(%rbp),%eax */
-				seen |= SEEN_MEM;
-				EMIT3(0x8b, 0x45, 0xf0 - K*4);
-				break;
-			case BPF_S_LDX_MEM: /* X = mem[K] : mov off8(%rbp),%ebx */
-				seen |= SEEN_XREG | SEEN_MEM;
-				EMIT3(0x8b, 0x5d, 0xf0 - K*4);
-				break;
-			case BPF_S_ST: /* mem[K] = A : mov %eax,off8(%rbp) */
-				seen |= SEEN_MEM;
-				EMIT3(0x89, 0x45, 0xf0 - K*4);
-				break;
-			case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */
-				seen |= SEEN_XREG | SEEN_MEM;
-				EMIT3(0x89, 0x5d, 0xf0 - K*4);
-				break;
-			case BPF_S_LD_W_LEN: /*	A = skb->len; */
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4);
-				if (is_imm8(offsetof(struct sk_buff, len)))
-					/* mov    off8(%rdi),%eax */
-					EMIT3(0x8b, 0x47, offsetof(struct sk_buff, len));
-				else {
-					EMIT2(0x8b, 0x87);
-					EMIT(offsetof(struct sk_buff, len), 4);
-				}
-				break;
-			case BPF_S_LDX_W_LEN: /* X = skb->len; */
-				seen |= SEEN_XREG;
-				if (is_imm8(offsetof(struct sk_buff, len)))
-					/* mov off8(%rdi),%ebx */
-					EMIT3(0x8b, 0x5f, offsetof(struct sk_buff, len));
-				else {
-					EMIT2(0x8b, 0x9f);
-					EMIT(offsetof(struct sk_buff, len), 4);
-				}
-				break;
-			case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
-				if (is_imm8(offsetof(struct sk_buff, protocol))) {
-					/* movzwl off8(%rdi),%eax */
-					EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, protocol));
-				} else {
-					EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
-					EMIT(offsetof(struct sk_buff, protocol), 4);
-				}
-				EMIT2(0x86, 0xc4); /* ntohs() : xchg   %al,%ah */
-				break;
-			case BPF_S_ANC_IFINDEX:
-				if (is_imm8(offsetof(struct sk_buff, dev))) {
-					/* movq off8(%rdi),%rax */
-					EMIT4(0x48, 0x8b, 0x47, offsetof(struct sk_buff, dev));
-				} else {
-					EMIT3(0x48, 0x8b, 0x87); /* movq off32(%rdi),%rax */
-					EMIT(offsetof(struct sk_buff, dev), 4);
-				}
-				EMIT3(0x48, 0x85, 0xc0);	/* test %rax,%rax */
-				EMIT_COND_JMP(X86_JE, cleanup_addr - (addrs[i] - 6));
-				BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
-				EMIT2(0x8b, 0x80);	/* mov off32(%rax),%eax */
-				EMIT(offsetof(struct net_device, ifindex), 4);
-				break;
-			case BPF_S_ANC_MARK:
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
-				if (is_imm8(offsetof(struct sk_buff, mark))) {
-					/* mov off8(%rdi),%eax */
-					EMIT3(0x8b, 0x47, offsetof(struct sk_buff, mark));
-				} else {
-					EMIT2(0x8b, 0x87);
-					EMIT(offsetof(struct sk_buff, mark), 4);
-				}
-				break;
-			case BPF_S_ANC_RXHASH:
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
-				if (is_imm8(offsetof(struct sk_buff, hash))) {
-					/* mov off8(%rdi),%eax */
-					EMIT3(0x8b, 0x47, offsetof(struct sk_buff, hash));
-				} else {
-					EMIT2(0x8b, 0x87);
-					EMIT(offsetof(struct sk_buff, hash), 4);
-				}
-				break;
-			case BPF_S_ANC_QUEUE:
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
-				if (is_imm8(offsetof(struct sk_buff, queue_mapping))) {
-					/* movzwl off8(%rdi),%eax */
-					EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, queue_mapping));
-				} else {
-					EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
-					EMIT(offsetof(struct sk_buff, queue_mapping), 4);
-				}
-				break;
-			case BPF_S_ANC_CPU:
-#ifdef CONFIG_SMP
-				EMIT4(0x65, 0x8b, 0x04, 0x25); /* mov %gs:off32,%eax */
-				EMIT((u32)(unsigned long)&cpu_number, 4); /* A = smp_processor_id(); */
-#else
-				CLEAR_A();
-#endif
+					EMIT1(0x0F);
+				EMIT1(add_1reg(0xC8, dst_reg));
 				break;
-			case BPF_S_ANC_VLAN_TAG:
-			case BPF_S_ANC_VLAN_TAG_PRESENT:
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
-				if (is_imm8(offsetof(struct sk_buff, vlan_tci))) {
-					/* movzwl off8(%rdi),%eax */
-					EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, vlan_tci));
-				} else {
-					EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */
-					EMIT(offsetof(struct sk_buff, vlan_tci), 4);
-				}
-				BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
-				if (filter[i].code == BPF_S_ANC_VLAN_TAG) {
-					EMIT3(0x80, 0xe4, 0xef); /* and    $0xef,%ah */
-				} else {
-					EMIT3(0xc1, 0xe8, 0x0c); /* shr    $0xc,%eax */
-					EMIT3(0x83, 0xe0, 0x01); /* and    $0x1,%eax */
-				}
-				break;
-			case BPF_S_ANC_PKTTYPE:
-			{
-				int off = pkt_type_offset();
-
-				if (off < 0)
-					goto out;
-				if (is_imm8(off)) {
-					/* movzbl off8(%rdi),%eax */
-					EMIT4(0x0f, 0xb6, 0x47, off);
-				} else {
-					/* movbl off32(%rdi),%eax */
-					EMIT3(0x0f, 0xb6, 0x87);
-					EMIT(off, 4);
-				}
-				EMIT3(0x83, 0xe0, PKT_TYPE_MAX); /* and    $0x7,%eax */
+			case 64:
+				/* emit 'bswap rax' to swap 8 bytes */
+				EMIT3(add_1mod(0x48, dst_reg), 0x0F,
+				      add_1reg(0xC8, dst_reg));
 				break;
 			}
-			case BPF_S_LD_W_ABS:
-				func = CHOOSE_LOAD_FUNC(K, sk_load_word);
-common_load:			seen |= SEEN_DATAREF;
-				t_offset = func - (image + addrs[i]);
-				EMIT1_off32(0xbe, K); /* mov imm32,%esi */
-				EMIT1_off32(0xe8, t_offset); /* call */
-				break;
-			case BPF_S_LD_H_ABS:
-				func = CHOOSE_LOAD_FUNC(K, sk_load_half);
-				goto common_load;
-			case BPF_S_LD_B_ABS:
-				func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
-				goto common_load;
-			case BPF_S_LDX_B_MSH:
-				func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
-				seen |= SEEN_DATAREF | SEEN_XREG;
-				t_offset = func - (image + addrs[i]);
-				EMIT1_off32(0xbe, K);	/* mov imm32,%esi */
-				EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
-				break;
-			case BPF_S_LD_W_IND:
-				func = sk_load_word;
-common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
-				t_offset = func - (image + addrs[i]);
-				if (K) {
-					if (is_imm8(K)) {
-						EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */
-					} else {
-						EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */
-						EMIT(K, 4);
-					}
-				} else {
-					EMIT2(0x89,0xde); /* mov %ebx,%esi */
-				}
-				EMIT1_off32(0xe8, t_offset);	/* call sk_load_xxx_ind */
-				break;
-			case BPF_S_LD_H_IND:
-				func = sk_load_half;
-				goto common_load_ind;
-			case BPF_S_LD_B_IND:
-				func = sk_load_byte;
-				goto common_load_ind;
-			case BPF_S_JMP_JA:
-				t_offset = addrs[i + K] - addrs[i];
-				EMIT_JMP(t_offset);
-				break;
-			COND_SEL(BPF_S_JMP_JGT_K, X86_JA, X86_JBE);
-			COND_SEL(BPF_S_JMP_JGE_K, X86_JAE, X86_JB);
-			COND_SEL(BPF_S_JMP_JEQ_K, X86_JE, X86_JNE);
-			COND_SEL(BPF_S_JMP_JSET_K,X86_JNE, X86_JE);
-			COND_SEL(BPF_S_JMP_JGT_X, X86_JA, X86_JBE);
-			COND_SEL(BPF_S_JMP_JGE_X, X86_JAE, X86_JB);
-			COND_SEL(BPF_S_JMP_JEQ_X, X86_JE, X86_JNE);
-			COND_SEL(BPF_S_JMP_JSET_X,X86_JNE, X86_JE);
-
-cond_branch:			f_offset = addrs[i + filter[i].jf] - addrs[i];
-				t_offset = addrs[i + filter[i].jt] - addrs[i];
-
-				/* same targets, can avoid doing the test :) */
-				if (filter[i].jt == filter[i].jf) {
-					EMIT_JMP(t_offset);
-					break;
-				}
+			break;
+
+		case BPF_ALU | BPF_END | BPF_FROM_LE:
+			break;
+
+			/* ST: *(u8*)(dst_reg + off) = imm */
+		case BPF_ST | BPF_MEM | BPF_B:
+			if (is_ereg(dst_reg))
+				EMIT2(0x41, 0xC6);
+			else
+				EMIT1(0xC6);
+			goto st;
+		case BPF_ST | BPF_MEM | BPF_H:
+			if (is_ereg(dst_reg))
+				EMIT3(0x66, 0x41, 0xC7);
+			else
+				EMIT2(0x66, 0xC7);
+			goto st;
+		case BPF_ST | BPF_MEM | BPF_W:
+			if (is_ereg(dst_reg))
+				EMIT2(0x41, 0xC7);
+			else
+				EMIT1(0xC7);
+			goto st;
+		case BPF_ST | BPF_MEM | BPF_DW:
+			EMIT2(add_1mod(0x48, dst_reg), 0xC7);
+
+st:			if (is_imm8(insn->off))
+				EMIT2(add_1reg(0x40, dst_reg), insn->off);
+			else
+				EMIT1_off32(add_1reg(0x80, dst_reg), insn->off);
+
+			EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(insn->code)));
+			break;
+
+			/* STX: *(u8*)(dst_reg + off) = src_reg */
+		case BPF_STX | BPF_MEM | BPF_B:
+			/* emit 'mov byte ptr [rax + off], al' */
+			if (is_ereg(dst_reg) || is_ereg(src_reg) ||
+			    /* have to add extra byte for x86 SIL, DIL regs */
+			    src_reg == BPF_REG_1 || src_reg == BPF_REG_2)
+				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88);
+			else
+				EMIT1(0x88);
+			goto stx;
+		case BPF_STX | BPF_MEM | BPF_H:
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89);
+			else
+				EMIT2(0x66, 0x89);
+			goto stx;
+		case BPF_STX | BPF_MEM | BPF_W:
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89);
+			else
+				EMIT1(0x89);
+			goto stx;
+		case BPF_STX | BPF_MEM | BPF_DW:
+			EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89);
+stx:			if (is_imm8(insn->off))
+				EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
+			else
+				EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
+					    insn->off);
+			break;
+
+			/* LDX: dst_reg = *(u8*)(src_reg + off) */
+		case BPF_LDX | BPF_MEM | BPF_B:
+			/* emit 'movzx rax, byte ptr [rax + off]' */
+			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6);
+			goto ldx;
+		case BPF_LDX | BPF_MEM | BPF_H:
+			/* emit 'movzx rax, word ptr [rax + off]' */
+			EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7);
+			goto ldx;
+		case BPF_LDX | BPF_MEM | BPF_W:
+			/* emit 'mov eax, dword ptr [rax+0x14]' */
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B);
+			else
+				EMIT1(0x8B);
+			goto ldx;
+		case BPF_LDX | BPF_MEM | BPF_DW:
+			/* emit 'mov rax, qword ptr [rax+0x14]' */
+			EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B);
+ldx:			/* if insn->off == 0 we can save one extra byte, but
+			 * special case of x86 r13 which always needs an offset
+			 * is not worth the hassle
+			 */
+			if (is_imm8(insn->off))
+				EMIT2(add_2reg(0x40, src_reg, dst_reg), insn->off);
+			else
+				EMIT1_off32(add_2reg(0x80, src_reg, dst_reg),
+					    insn->off);
+			break;
+
+			/* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */
+		case BPF_STX | BPF_XADD | BPF_W:
+			/* emit 'lock add dword ptr [rax + off], eax' */
+			if (is_ereg(dst_reg) || is_ereg(src_reg))
+				EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01);
+			else
+				EMIT2(0xF0, 0x01);
+			goto xadd;
+		case BPF_STX | BPF_XADD | BPF_DW:
+			EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01);
+xadd:			if (is_imm8(insn->off))
+				EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off);
+			else
+				EMIT1_off32(add_2reg(0x80, dst_reg, src_reg),
+					    insn->off);
+			break;
+
+			/* call */
+		case BPF_JMP | BPF_CALL:
+			func = (u8 *) __bpf_call_base + imm32;
+			jmp_offset = func - (image + addrs[i]);
+			if (ctx->seen_ld_abs) {
+				EMIT2(0x41, 0x52); /* push %r10 */
+				EMIT2(0x41, 0x51); /* push %r9 */
+				/* need to adjust jmp offset, since
+				 * pop %r9, pop %r10 take 4 bytes after call insn
+				 */
+				jmp_offset += 4;
+			}
+			if (!imm32 || !is_simm32(jmp_offset)) {
+				pr_err("unsupported bpf func %d addr %p image %p\n",
+				       imm32, func, image);
+				return -EINVAL;
+			}
+			EMIT1_off32(0xE8, jmp_offset);
+			if (ctx->seen_ld_abs) {
+				EMIT2(0x41, 0x59); /* pop %r9 */
+				EMIT2(0x41, 0x5A); /* pop %r10 */
+			}
+			break;
+
+			/* cond jump */
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JNE | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JSGT | BPF_X:
+		case BPF_JMP | BPF_JSGE | BPF_X:
+			/* cmp dst_reg, src_reg */
+			EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x39,
+			      add_2reg(0xC0, dst_reg, src_reg));
+			goto emit_cond_jmp;
+
+		case BPF_JMP | BPF_JSET | BPF_X:
+			/* test dst_reg, src_reg */
+			EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x85,
+			      add_2reg(0xC0, dst_reg, src_reg));
+			goto emit_cond_jmp;
+
+		case BPF_JMP | BPF_JSET | BPF_K:
+			/* test dst_reg, imm32 */
+			EMIT1(add_1mod(0x48, dst_reg));
+			EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32);
+			goto emit_cond_jmp;
+
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JNE | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JSGT | BPF_K:
+		case BPF_JMP | BPF_JSGE | BPF_K:
+			/* cmp dst_reg, imm8/32 */
+			EMIT1(add_1mod(0x48, dst_reg));
+
+			if (is_imm8(imm32))
+				EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32);
+			else
+				EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32);
+
+emit_cond_jmp:		/* convert BPF opcode to x86 */
+			switch (BPF_OP(insn->code)) {
+			case BPF_JEQ:
+				jmp_cond = X86_JE;
+				break;
+			case BPF_JSET:
+			case BPF_JNE:
+				jmp_cond = X86_JNE;
+				break;
+			case BPF_JGT:
+				/* GT is unsigned '>', JA in x86 */
+				jmp_cond = X86_JA;
+				break;
+			case BPF_JGE:
+				/* GE is unsigned '>=', JAE in x86 */
+				jmp_cond = X86_JAE;
+				break;
+			case BPF_JSGT:
+				/* signed '>', GT in x86 */
+				jmp_cond = X86_JG;
+				break;
+			case BPF_JSGE:
+				/* signed '>=', GE in x86 */
+				jmp_cond = X86_JGE;
+				break;
+			default: /* to silence gcc warning */
+				return -EFAULT;
+			}
+			jmp_offset = addrs[i + insn->off] - addrs[i];
+			if (is_imm8(jmp_offset)) {
+				EMIT2(jmp_cond, jmp_offset);
+			} else if (is_simm32(jmp_offset)) {
+				EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset);
+			} else {
+				pr_err("cond_jmp gen bug %llx\n", jmp_offset);
+				return -EFAULT;
+			}
+
+			break;
 
-				switch (filter[i].code) {
-				case BPF_S_JMP_JGT_X:
-				case BPF_S_JMP_JGE_X:
-				case BPF_S_JMP_JEQ_X:
-					seen |= SEEN_XREG;
-					EMIT2(0x39, 0xd8); /* cmp %ebx,%eax */
-					break;
-				case BPF_S_JMP_JSET_X:
-					seen |= SEEN_XREG;
-					EMIT2(0x85, 0xd8); /* test %ebx,%eax */
-					break;
-				case BPF_S_JMP_JEQ_K:
-					if (K == 0) {
-						EMIT2(0x85, 0xc0); /* test   %eax,%eax */
-						break;
-					}
-				case BPF_S_JMP_JGT_K:
-				case BPF_S_JMP_JGE_K:
-					if (K <= 127)
-						EMIT3(0x83, 0xf8, K); /* cmp imm8,%eax */
+		case BPF_JMP | BPF_JA:
+			jmp_offset = addrs[i + insn->off] - addrs[i];
+			if (!jmp_offset)
+				/* optimize out nop jumps */
+				break;
+emit_jmp:
+			if (is_imm8(jmp_offset)) {
+				EMIT2(0xEB, jmp_offset);
+			} else if (is_simm32(jmp_offset)) {
+				EMIT1_off32(0xE9, jmp_offset);
+			} else {
+				pr_err("jmp gen bug %llx\n", jmp_offset);
+				return -EFAULT;
+			}
+			break;
+
+		case BPF_LD | BPF_IND | BPF_W:
+			func = sk_load_word;
+			goto common_load;
+		case BPF_LD | BPF_ABS | BPF_W:
+			func = CHOOSE_LOAD_FUNC(imm32, sk_load_word);
+common_load:		ctx->seen_ld_abs = true;
+			jmp_offset = func - (image + addrs[i]);
+			if (!func || !is_simm32(jmp_offset)) {
+				pr_err("unsupported bpf func %d addr %p image %p\n",
+				       imm32, func, image);
+				return -EINVAL;
+			}
+			if (BPF_MODE(insn->code) == BPF_ABS) {
+				/* mov %esi, imm32 */
+				EMIT1_off32(0xBE, imm32);
+			} else {
+				/* mov %rsi, src_reg */
+				EMIT_mov(BPF_REG_2, src_reg);
+				if (imm32) {
+					if (is_imm8(imm32))
+						/* add %esi, imm8 */
+						EMIT3(0x83, 0xC6, imm32);
 					else
-						EMIT1_off32(0x3d, K); /* cmp imm32,%eax */
-					break;
-				case BPF_S_JMP_JSET_K:
-					if (K <= 0xFF)
-						EMIT2(0xa8, K); /* test imm8,%al */
-					else if (!(K & 0xFFFF00FF))
-						EMIT3(0xf6, 0xc4, K >> 8); /* test imm8,%ah */
-					else if (K <= 0xFFFF) {
-						EMIT2(0x66, 0xa9); /* test imm16,%ax */
-						EMIT(K, 2);
-					} else {
-						EMIT1_off32(0xa9, K); /* test imm32,%eax */
-					}
-					break;
+						/* add %esi, imm32 */
+						EMIT2_off32(0x81, 0xC6, imm32);
 				}
-				if (filter[i].jt != 0) {
-					if (filter[i].jf && f_offset)
-						t_offset += is_near(f_offset) ? 2 : 5;
-					EMIT_COND_JMP(t_op, t_offset);
-					if (filter[i].jf)
-						EMIT_JMP(f_offset);
-					break;
-				}
-				EMIT_COND_JMP(f_op, f_offset);
-				break;
-			default:
-				/* hmm, too complex filter, give up with jit compiler */
-				goto out;
 			}
-			ilen = prog - temp;
-			if (image) {
-				if (unlikely(proglen + ilen > oldproglen)) {
-					pr_err("bpb_jit_compile fatal error\n");
-					kfree(addrs);
-					module_free(NULL, header);
-					return;
-				}
-				memcpy(image + proglen, temp, ilen);
+			/* skb pointer is in R6 (%rbx), it will be copied into
+			 * %rdi if skb_copy_bits() call is necessary.
+			 * sk_load_* helpers also use %r10 and %r9d.
+			 * See bpf_jit.S
+			 */
+			EMIT1_off32(0xE8, jmp_offset); /* call */
+			break;
+
+		case BPF_LD | BPF_IND | BPF_H:
+			func = sk_load_half;
+			goto common_load;
+		case BPF_LD | BPF_ABS | BPF_H:
+			func = CHOOSE_LOAD_FUNC(imm32, sk_load_half);
+			goto common_load;
+		case BPF_LD | BPF_IND | BPF_B:
+			func = sk_load_byte;
+			goto common_load;
+		case BPF_LD | BPF_ABS | BPF_B:
+			func = CHOOSE_LOAD_FUNC(imm32, sk_load_byte);
+			goto common_load;
+
+		case BPF_JMP | BPF_EXIT:
+			if (i != insn_cnt - 1) {
+				jmp_offset = ctx->cleanup_addr - addrs[i];
+				goto emit_jmp;
 			}
-			proglen += ilen;
-			addrs[i] = proglen;
-			prog = temp;
+			/* update cleanup_addr */
+			ctx->cleanup_addr = proglen;
+			/* mov rbx, qword ptr [rbp-X] */
+			EMIT3_off32(0x48, 0x8B, 0x9D, -stacksize);
+			/* mov r13, qword ptr [rbp-X] */
+			EMIT3_off32(0x4C, 0x8B, 0xAD, -stacksize + 8);
+			/* mov r14, qword ptr [rbp-X] */
+			EMIT3_off32(0x4C, 0x8B, 0xB5, -stacksize + 16);
+			/* mov r15, qword ptr [rbp-X] */
+			EMIT3_off32(0x4C, 0x8B, 0xBD, -stacksize + 24);
+
+			EMIT1(0xC9); /* leave */
+			EMIT1(0xC3); /* ret */
+			break;
+
+		default:
+			/* By design x64 JIT should support all BPF instructions
+			 * This error will be seen if new instruction was added
+			 * to interpreter, but not to JIT
+			 * or if there is junk in sk_filter
+			 */
+			pr_err("bpf_jit: unknown opcode %02x\n", insn->code);
+			return -EINVAL;
 		}
-		/* last bpf instruction is always a RET :
-		 * use it to give the cleanup instruction(s) addr
-		 */
-		cleanup_addr = proglen - 1; /* ret */
-		if (seen_or_pass0)
-			cleanup_addr -= 1; /* leaveq */
-		if (seen_or_pass0 & SEEN_XREG)
-			cleanup_addr -= 4; /* mov  -8(%rbp),%rbx */
 
+		ilen = prog - temp;
+		if (image) {
+			if (unlikely(proglen + ilen > oldproglen)) {
+				pr_err("bpf_jit_compile fatal error\n");
+				return -EFAULT;
+			}
+			memcpy(image + proglen, temp, ilen);
+		}
+		proglen += ilen;
+		addrs[i] = proglen;
+		prog = temp;
+	}
+	return proglen;
+}
+
+void bpf_jit_compile(struct sk_filter *prog)
+{
+}
+
+void bpf_int_jit_compile(struct sk_filter *prog)
+{
+	struct bpf_binary_header *header = NULL;
+	int proglen, oldproglen = 0;
+	struct jit_context ctx = {};
+	u8 *image = NULL;
+	int *addrs;
+	int pass;
+	int i;
+
+	if (!bpf_jit_enable)
+		return;
+
+	if (!prog || !prog->len)
+		return;
+
+	addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL);
+	if (!addrs)
+		return;
+
+	/* Before first pass, make a rough estimation of addrs[]
+	 * each bpf instruction is translated to less than 64 bytes
+	 */
+	for (proglen = 0, i = 0; i < prog->len; i++) {
+		proglen += 64;
+		addrs[i] = proglen;
+	}
+	ctx.cleanup_addr = proglen;
+
+	for (pass = 0; pass < 10; pass++) {
+		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
+		if (proglen <= 0) {
+			image = NULL;
+			if (header)
+				module_free(NULL, header);
+			goto out;
+		}
 		if (image) {
 			if (proglen != oldproglen)
-				pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen);
+				pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
+				       proglen, oldproglen);
 			break;
 		}
 		if (proglen == oldproglen) {
@@ -766,17 +918,16 @@ cond_branch:			f_offset = addrs[i + filter[i].jf] - addrs[i];
 	}
 
 	if (bpf_jit_enable > 1)
-		bpf_jit_dump(flen, proglen, pass, image);
+		bpf_jit_dump(prog->len, proglen, 0, image);
 
 	if (image) {
 		bpf_flush_icache(header, image + proglen);
 		set_memory_ro((unsigned long)header, header->pages);
-		fp->bpf_func = (void *)image;
-		fp->jited = 1;
+		prog->bpf_func = (void *)image;
+		prog->jited = 1;
 	}
 out:
 	kfree(addrs);
-	return;
 }
 
 static void bpf_jit_free_deferred(struct work_struct *work)
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index b5e60268d93..c61ea57d1ba 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -326,6 +326,27 @@ static void pci_fixup_video(struct pci_dev *pdev)
 	struct pci_bus *bus;
 	u16 config;
 
+	if (!vga_default_device()) {
+		resource_size_t start, end;
+		int i;
+
+		/* Does firmware framebuffer belong to us? */
+		for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+			if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM))
+				continue;
+
+			start = pci_resource_start(pdev, i);
+			end  = pci_resource_end(pdev, i);
+
+			if (!start || !end)
+				continue;
+
+			if (screen_info.lfb_base >= start &&
+			    (screen_info.lfb_base + screen_info.lfb_size) < end)
+				vga_set_default_device(pdev);
+		}
+	}
+
 	/* Is VGA routed to us? */
 	bus = pdev->bus;
 	while (bus) {
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index a19ed92e74e..2ae525e0d8b 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -162,6 +162,10 @@ pcibios_align_resource(void *data, const struct resource *res,
 			return start;
 		if (start & 0x300)
 			start = (start + 0x3ff) & ~0x3ff;
+	} else if (res->flags & IORESOURCE_MEM) {
+		/* The low 1MB range is reserved for ISA cards */
+		if (start < BIOS_END)
+			start = BIOS_END;
 	}
 	return start;
 }
diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile
index d51045afcaa..2846aaab510 100644
--- a/arch/x86/platform/efi/Makefile
+++ b/arch/x86/platform/efi/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_EFI) 		+= efi.o efi_$(BITS).o efi_stub_$(BITS).o
+obj-$(CONFIG_EFI) 		+= quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o
 obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
 obj-$(CONFIG_EARLY_PRINTK_EFI)	+= early_printk.o
 obj-$(CONFIG_EFI_MIXED)		+= efi_thunk_$(BITS).o
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 87fc96bcc13..850da94fef3 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -56,13 +56,6 @@
 
 #define EFI_DEBUG
 
-#define EFI_MIN_RESERVE 5120
-
-#define EFI_DUMMY_GUID \
-	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
-
-static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
-
 struct efi_memory_map memmap;
 
 static struct efi efi_phys __initdata;
@@ -95,139 +88,6 @@ static int __init setup_add_efi_memmap(char *arg)
 }
 early_param("add_efi_memmap", setup_add_efi_memmap);
 
-static bool efi_no_storage_paranoia;
-
-static int __init setup_storage_paranoia(char *arg)
-{
-	efi_no_storage_paranoia = true;
-	return 0;
-}
-early_param("efi_no_storage_paranoia", setup_storage_paranoia);
-
-static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
-{
-	unsigned long flags;
-	efi_status_t status;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	status = efi_call_virt(get_time, tm, tc);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return status;
-}
-
-static efi_status_t virt_efi_set_time(efi_time_t *tm)
-{
-	unsigned long flags;
-	efi_status_t status;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	status = efi_call_virt(set_time, tm);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return status;
-}
-
-static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
-					     efi_bool_t *pending,
-					     efi_time_t *tm)
-{
-	unsigned long flags;
-	efi_status_t status;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return status;
-}
-
-static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
-{
-	unsigned long flags;
-	efi_status_t status;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	status = efi_call_virt(set_wakeup_time, enabled, tm);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return status;
-}
-
-static efi_status_t virt_efi_get_variable(efi_char16_t *name,
-					  efi_guid_t *vendor,
-					  u32 *attr,
-					  unsigned long *data_size,
-					  void *data)
-{
-	return efi_call_virt(get_variable,
-			     name, vendor, attr,
-			     data_size, data);
-}
-
-static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
-					       efi_char16_t *name,
-					       efi_guid_t *vendor)
-{
-	return efi_call_virt(get_next_variable,
-			     name_size, name, vendor);
-}
-
-static efi_status_t virt_efi_set_variable(efi_char16_t *name,
-					  efi_guid_t *vendor,
-					  u32 attr,
-					  unsigned long data_size,
-					  void *data)
-{
-	return efi_call_virt(set_variable,
-			     name, vendor, attr,
-			     data_size, data);
-}
-
-static efi_status_t virt_efi_query_variable_info(u32 attr,
-						 u64 *storage_space,
-						 u64 *remaining_space,
-						 u64 *max_variable_size)
-{
-	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
-		return EFI_UNSUPPORTED;
-
-	return efi_call_virt(query_variable_info, attr, storage_space,
-			     remaining_space, max_variable_size);
-}
-
-static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
-{
-	return efi_call_virt(get_next_high_mono_count, count);
-}
-
-static void virt_efi_reset_system(int reset_type,
-				  efi_status_t status,
-				  unsigned long data_size,
-				  efi_char16_t *data)
-{
-	__efi_call_virt(reset_system, reset_type, status,
-			data_size, data);
-}
-
-static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
-					    unsigned long count,
-					    unsigned long sg_list)
-{
-	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
-		return EFI_UNSUPPORTED;
-
-	return efi_call_virt(update_capsule, capsules, count, sg_list);
-}
-
-static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
-						unsigned long count,
-						u64 *max_size,
-						int *reset_type)
-{
-	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
-		return EFI_UNSUPPORTED;
-
-	return efi_call_virt(query_capsule_caps, capsules, count, max_size,
-			     reset_type);
-}
-
 static efi_status_t __init phys_efi_set_virtual_address_map(
 	unsigned long memory_map_size,
 	unsigned long descriptor_size,
@@ -244,42 +104,6 @@ static efi_status_t __init phys_efi_set_virtual_address_map(
 	return status;
 }
 
-int efi_set_rtc_mmss(const struct timespec *now)
-{
-	unsigned long nowtime = now->tv_sec;
-	efi_status_t	status;
-	efi_time_t	eft;
-	efi_time_cap_t	cap;
-	struct rtc_time	tm;
-
-	status = efi.get_time(&eft, &cap);
-	if (status != EFI_SUCCESS) {
-		pr_err("Oops: efitime: can't read time!\n");
-		return -1;
-	}
-
-	rtc_time_to_tm(nowtime, &tm);
-	if (!rtc_valid_tm(&tm)) {
-		eft.year = tm.tm_year + 1900;
-		eft.month = tm.tm_mon + 1;
-		eft.day = tm.tm_mday;
-		eft.minute = tm.tm_min;
-		eft.second = tm.tm_sec;
-		eft.nanosecond = 0;
-	} else {
-		pr_err("%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n",
-		       __func__, nowtime);
-		return -1;
-	}
-
-	status = efi.set_time(&eft);
-	if (status != EFI_SUCCESS) {
-		pr_err("Oops: efitime: can't write time!\n");
-		return -1;
-	}
-	return 0;
-}
-
 void efi_get_time(struct timespec *now)
 {
 	efi_status_t status;
@@ -350,6 +174,9 @@ int __init efi_memblock_x86_reserve_range(void)
 	struct efi_info *e = &boot_params.efi_info;
 	unsigned long pmap;
 
+	if (efi_enabled(EFI_PARAVIRT))
+		return 0;
+
 #ifdef CONFIG_X86_32
 	/* Can't handle data above 4GB at this time */
 	if (e->efi_memmap_hi) {
@@ -392,69 +219,15 @@ static void __init print_efi_memmap(void)
 #endif  /*  EFI_DEBUG  */
 }
 
-void __init efi_reserve_boot_services(void)
-{
-	void *p;
-
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
-		u64 start = md->phys_addr;
-		u64 size = md->num_pages << EFI_PAGE_SHIFT;
-
-		if (md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
-		/* Only reserve where possible:
-		 * - Not within any already allocated areas
-		 * - Not over any memory area (really needed, if above?)
-		 * - Not within any part of the kernel
-		 * - Not the bios reserved area
-		*/
-		if ((start + size > __pa_symbol(_text)
-				&& start <= __pa_symbol(_end)) ||
-			!e820_all_mapped(start, start+size, E820_RAM) ||
-			memblock_is_region_reserved(start, size)) {
-			/* Could not reserve, skip it */
-			md->num_pages = 0;
-			memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n",
-				     start, start+size-1);
-		} else
-			memblock_reserve(start, size);
-	}
-}
-
 void __init efi_unmap_memmap(void)
 {
 	clear_bit(EFI_MEMMAP, &efi.flags);
 	if (memmap.map) {
-		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
+		early_memunmap(memmap.map, memmap.nr_map * memmap.desc_size);
 		memmap.map = NULL;
 	}
 }
 
-void __init efi_free_boot_services(void)
-{
-	void *p;
-
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-		efi_memory_desc_t *md = p;
-		unsigned long long start = md->phys_addr;
-		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
-
-		if (md->type != EFI_BOOT_SERVICES_CODE &&
-		    md->type != EFI_BOOT_SERVICES_DATA)
-			continue;
-
-		/* Could not reserve boot area */
-		if (!size)
-			continue;
-
-		free_bootmem_late(start, size);
-	}
-
-	efi_unmap_memmap();
-}
-
 static int __init efi_systab_init(void *phys)
 {
 	if (efi_enabled(EFI_64BIT)) {
@@ -467,12 +240,12 @@ static int __init efi_systab_init(void *phys)
 			if (!data)
 				return -ENOMEM;
 		}
-		systab64 = early_ioremap((unsigned long)phys,
+		systab64 = early_memremap((unsigned long)phys,
 					 sizeof(*systab64));
 		if (systab64 == NULL) {
 			pr_err("Couldn't map the system table!\n");
 			if (data)
-				early_iounmap(data, sizeof(*data));
+				early_memunmap(data, sizeof(*data));
 			return -ENOMEM;
 		}
 
@@ -504,9 +277,9 @@ static int __init efi_systab_init(void *phys)
 					   systab64->tables;
 		tmp |= data ? data->tables : systab64->tables;
 
-		early_iounmap(systab64, sizeof(*systab64));
+		early_memunmap(systab64, sizeof(*systab64));
 		if (data)
-			early_iounmap(data, sizeof(*data));
+			early_memunmap(data, sizeof(*data));
 #ifdef CONFIG_X86_32
 		if (tmp >> 32) {
 			pr_err("EFI data located above 4GB, disabling EFI.\n");
@@ -516,7 +289,7 @@ static int __init efi_systab_init(void *phys)
 	} else {
 		efi_system_table_32_t *systab32;
 
-		systab32 = early_ioremap((unsigned long)phys,
+		systab32 = early_memremap((unsigned long)phys,
 					 sizeof(*systab32));
 		if (systab32 == NULL) {
 			pr_err("Couldn't map the system table!\n");
@@ -537,7 +310,7 @@ static int __init efi_systab_init(void *phys)
 		efi_systab.nr_tables = systab32->nr_tables;
 		efi_systab.tables = systab32->tables;
 
-		early_iounmap(systab32, sizeof(*systab32));
+		early_memunmap(systab32, sizeof(*systab32));
 	}
 
 	efi.systab = &efi_systab;
@@ -563,7 +336,7 @@ static int __init efi_runtime_init32(void)
 {
 	efi_runtime_services_32_t *runtime;
 
-	runtime = early_ioremap((unsigned long)efi.systab->runtime,
+	runtime = early_memremap((unsigned long)efi.systab->runtime,
 			sizeof(efi_runtime_services_32_t));
 	if (!runtime) {
 		pr_err("Could not map the runtime service table!\n");
@@ -578,7 +351,7 @@ static int __init efi_runtime_init32(void)
 	efi_phys.set_virtual_address_map =
 			(efi_set_virtual_address_map_t *)
 			(unsigned long)runtime->set_virtual_address_map;
-	early_iounmap(runtime, sizeof(efi_runtime_services_32_t));
+	early_memunmap(runtime, sizeof(efi_runtime_services_32_t));
 
 	return 0;
 }
@@ -587,7 +360,7 @@ static int __init efi_runtime_init64(void)
 {
 	efi_runtime_services_64_t *runtime;
 
-	runtime = early_ioremap((unsigned long)efi.systab->runtime,
+	runtime = early_memremap((unsigned long)efi.systab->runtime,
 			sizeof(efi_runtime_services_64_t));
 	if (!runtime) {
 		pr_err("Could not map the runtime service table!\n");
@@ -602,7 +375,7 @@ static int __init efi_runtime_init64(void)
 	efi_phys.set_virtual_address_map =
 			(efi_set_virtual_address_map_t *)
 			(unsigned long)runtime->set_virtual_address_map;
-	early_iounmap(runtime, sizeof(efi_runtime_services_64_t));
+	early_memunmap(runtime, sizeof(efi_runtime_services_64_t));
 
 	return 0;
 }
@@ -616,14 +389,24 @@ static int __init efi_runtime_init(void)
 	 * the runtime services table so that we can grab the physical
 	 * address of several of the EFI runtime functions, needed to
 	 * set the firmware into virtual mode.
+	 *
+	 * When EFI_PARAVIRT is in force then we could not map runtime
+	 * service memory region because we do not have direct access to it.
+	 * However, runtime services are available through proxy functions
+	 * (e.g. in case of Xen dom0 EFI implementation they call special
+	 * hypercall which executes relevant EFI functions) and that is why
+	 * they are always enabled.
 	 */
-	if (efi_enabled(EFI_64BIT))
-		rv = efi_runtime_init64();
-	else
-		rv = efi_runtime_init32();
 
-	if (rv)
-		return rv;
+	if (!efi_enabled(EFI_PARAVIRT)) {
+		if (efi_enabled(EFI_64BIT))
+			rv = efi_runtime_init64();
+		else
+			rv = efi_runtime_init32();
+
+		if (rv)
+			return rv;
+	}
 
 	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 
@@ -632,8 +415,11 @@ static int __init efi_runtime_init(void)
 
 static int __init efi_memmap_init(void)
 {
+	if (efi_enabled(EFI_PARAVIRT))
+		return 0;
+
 	/* Map the EFI memory map */
-	memmap.map = early_ioremap((unsigned long)memmap.phys_map,
+	memmap.map = early_memremap((unsigned long)memmap.phys_map,
 				   memmap.nr_map * memmap.desc_size);
 	if (memmap.map == NULL) {
 		pr_err("Could not map the memory map!\n");
@@ -649,62 +435,6 @@ static int __init efi_memmap_init(void)
 	return 0;
 }
 
-/*
- * A number of config table entries get remapped to virtual addresses
- * after entering EFI virtual mode. However, the kexec kernel requires
- * their physical addresses therefore we pass them via setup_data and
- * correct those entries to their respective physical addresses here.
- *
- * Currently only handles smbios which is necessary for some firmware
- * implementation.
- */
-static int __init efi_reuse_config(u64 tables, int nr_tables)
-{
-	int i, sz, ret = 0;
-	void *p, *tablep;
-	struct efi_setup_data *data;
-
-	if (!efi_setup)
-		return 0;
-
-	if (!efi_enabled(EFI_64BIT))
-		return 0;
-
-	data = early_memremap(efi_setup, sizeof(*data));
-	if (!data) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	if (!data->smbios)
-		goto out_memremap;
-
-	sz = sizeof(efi_config_table_64_t);
-
-	p = tablep = early_memremap(tables, nr_tables * sz);
-	if (!p) {
-		pr_err("Could not map Configuration table!\n");
-		ret = -ENOMEM;
-		goto out_memremap;
-	}
-
-	for (i = 0; i < efi.systab->nr_tables; i++) {
-		efi_guid_t guid;
-
-		guid = ((efi_config_table_64_t *)p)->guid;
-
-		if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
-			((efi_config_table_64_t *)p)->table = data->smbios;
-		p += sz;
-	}
-	early_iounmap(tablep, nr_tables * sz);
-
-out_memremap:
-	early_iounmap(data, sizeof(*data));
-out:
-	return ret;
-}
-
 void __init efi_init(void)
 {
 	efi_char16_t *c16;
@@ -728,8 +458,6 @@ void __init efi_init(void)
 	if (efi_systab_init(efi_phys.systab))
 		return;
 
-	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
-
 	efi.config_table = (unsigned long)efi.systab->tables;
 	efi.fw_vendor	 = (unsigned long)efi.systab->fw_vendor;
 	efi.runtime	 = (unsigned long)efi.systab->runtime;
@@ -737,14 +465,14 @@ void __init efi_init(void)
 	/*
 	 * Show what we know for posterity
 	 */
-	c16 = tmp = early_ioremap(efi.systab->fw_vendor, 2);
+	c16 = tmp = early_memremap(efi.systab->fw_vendor, 2);
 	if (c16) {
 		for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i)
 			vendor[i] = *c16++;
 		vendor[i] = '\0';
 	} else
 		pr_err("Could not map the firmware vendor!\n");
-	early_iounmap(tmp, 2);
+	early_memunmap(tmp, 2);
 
 	pr_info("EFI v%u.%.02u by %s\n",
 		efi.systab->hdr.revision >> 16,
@@ -770,8 +498,6 @@ void __init efi_init(void)
 	if (efi_memmap_init())
 		return;
 
-	set_bit(EFI_MEMMAP, &efi.flags);
-
 	print_efi_memmap();
 }
 
@@ -847,22 +573,6 @@ void __init old_map_region(efi_memory_desc_t *md)
 		       (unsigned long long)md->phys_addr);
 }
 
-static void native_runtime_setup(void)
-{
-	efi.get_time = virt_efi_get_time;
-	efi.set_time = virt_efi_set_time;
-	efi.get_wakeup_time = virt_efi_get_wakeup_time;
-	efi.set_wakeup_time = virt_efi_set_wakeup_time;
-	efi.get_variable = virt_efi_get_variable;
-	efi.get_next_variable = virt_efi_get_next_variable;
-	efi.set_variable = virt_efi_set_variable;
-	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
-	efi.reset_system = virt_efi_reset_system;
-	efi.query_variable_info = virt_efi_query_variable_info;
-	efi.update_capsule = virt_efi_update_capsule;
-	efi.query_capsule_caps = virt_efi_query_capsule_caps;
-}
-
 /* Merge contiguous regions of the same type and attribute */
 static void __init efi_merge_regions(void)
 {
@@ -1049,7 +759,7 @@ static void __init kexec_enter_virtual_mode(void)
 	 */
 	efi.runtime_version = efi_systab.hdr.revision;
 
-	native_runtime_setup();
+	efi_native_runtime_setup();
 
 	efi.set_virtual_address_map = NULL;
 
@@ -1057,11 +767,7 @@ static void __init kexec_enter_virtual_mode(void)
 		runtime_code_page_mkexec();
 
 	/* clean DUMMY object */
-	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
-			 EFI_VARIABLE_NON_VOLATILE |
-			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
-			 EFI_VARIABLE_RUNTIME_ACCESS,
-			 0, NULL);
+	efi_delete_dummy_variable();
 #endif
 }
 
@@ -1142,7 +848,7 @@ static void __init __efi_enter_virtual_mode(void)
 	efi.runtime_version = efi_systab.hdr.revision;
 
 	if (efi_is_native())
-		native_runtime_setup();
+		efi_native_runtime_setup();
 	else
 		efi_thunk_runtime_setup();
 
@@ -1179,15 +885,14 @@ static void __init __efi_enter_virtual_mode(void)
 	free_pages((unsigned long)new_memmap, pg_shift);
 
 	/* clean DUMMY object */
-	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
-			 EFI_VARIABLE_NON_VOLATILE |
-			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
-			 EFI_VARIABLE_RUNTIME_ACCESS,
-			 0, NULL);
+	efi_delete_dummy_variable();
 }
 
 void __init efi_enter_virtual_mode(void)
 {
+	if (efi_enabled(EFI_PARAVIRT))
+		return;
+
 	if (efi_setup)
 		kexec_enter_virtual_mode();
 	else
@@ -1220,6 +925,9 @@ u64 efi_mem_attributes(unsigned long phys_addr)
 	efi_memory_desc_t *md;
 	void *p;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return 0;
+
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
 		if ((md->phys_addr <= phys_addr) &&
@@ -1230,86 +938,6 @@ u64 efi_mem_attributes(unsigned long phys_addr)
 	return 0;
 }
 
-/*
- * Some firmware implementations refuse to boot if there's insufficient space
- * in the variable store. Ensure that we never use more than a safe limit.
- *
- * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
- * store.
- */
-efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
-{
-	efi_status_t status;
-	u64 storage_size, remaining_size, max_size;
-
-	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
-		return 0;
-
-	status = efi.query_variable_info(attributes, &storage_size,
-					 &remaining_size, &max_size);
-	if (status != EFI_SUCCESS)
-		return status;
-
-	/*
-	 * We account for that by refusing the write if permitting it would
-	 * reduce the available space to under 5KB. This figure was provided by
-	 * Samsung, so should be safe.
-	 */
-	if ((remaining_size - size < EFI_MIN_RESERVE) &&
-		!efi_no_storage_paranoia) {
-
-		/*
-		 * Triggering garbage collection may require that the firmware
-		 * generate a real EFI_OUT_OF_RESOURCES error. We can force
-		 * that by attempting to use more space than is available.
-		 */
-		unsigned long dummy_size = remaining_size + 1024;
-		void *dummy = kzalloc(dummy_size, GFP_ATOMIC);
-
-		if (!dummy)
-			return EFI_OUT_OF_RESOURCES;
-
-		status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
-					  EFI_VARIABLE_NON_VOLATILE |
-					  EFI_VARIABLE_BOOTSERVICE_ACCESS |
-					  EFI_VARIABLE_RUNTIME_ACCESS,
-					  dummy_size, dummy);
-
-		if (status == EFI_SUCCESS) {
-			/*
-			 * This should have failed, so if it didn't make sure
-			 * that we delete it...
-			 */
-			efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
-					 EFI_VARIABLE_NON_VOLATILE |
-					 EFI_VARIABLE_BOOTSERVICE_ACCESS |
-					 EFI_VARIABLE_RUNTIME_ACCESS,
-					 0, dummy);
-		}
-
-		kfree(dummy);
-
-		/*
-		 * The runtime code may now have triggered a garbage collection
-		 * run, so check the variable info again
-		 */
-		status = efi.query_variable_info(attributes, &storage_size,
-						 &remaining_size, &max_size);
-
-		if (status != EFI_SUCCESS)
-			return status;
-
-		/*
-		 * There still isn't enough room, so return an error
-		 */
-		if (remaining_size - size < EFI_MIN_RESERVE)
-			return EFI_OUT_OF_RESOURCES;
-	}
-
-	return EFI_SUCCESS;
-}
-EXPORT_SYMBOL_GPL(efi_query_variable_store);
-
 static int __init parse_efi_cmdline(char *str)
 {
 	if (*str == '=')
@@ -1321,22 +949,3 @@ static int __init parse_efi_cmdline(char *str)
 	return 0;
 }
 early_param("efi", parse_efi_cmdline);
-
-void __init efi_apply_memmap_quirks(void)
-{
-	/*
-	 * Once setup is done earlier, unmap the EFI memory map on mismatched
-	 * firmware/kernel architectures since there is no support for runtime
-	 * services.
-	 */
-	if (!efi_runtime_supported()) {
-		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
-		efi_unmap_memmap();
-	}
-
-	/*
-	 * UV doesn't support the new EFI pagetable mapping yet.
-	 */
-	if (is_uv_system())
-		set_bit(EFI_OLD_MEMMAP, &efi.flags);
-}
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
new file mode 100644
index 00000000000..1c7380da65f
--- /dev/null
+++ b/arch/x86/platform/efi/quirks.c
@@ -0,0 +1,290 @@
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/time.h>
+#include <linux/types.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/acpi.h>
+#include <asm/efi.h>
+#include <asm/uv/uv.h>
+
+#define EFI_MIN_RESERVE 5120
+
+#define EFI_DUMMY_GUID \
+	EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9)
+
+static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
+
+static bool efi_no_storage_paranoia;
+
+/*
+ * Some firmware implementations refuse to boot if there's insufficient
+ * space in the variable store. The implementation of garbage collection
+ * in some FW versions causes stale (deleted) variables to take up space
+ * longer than intended and space is only freed once the store becomes
+ * almost completely full.
+ *
+ * Enabling this option disables the space checks in
+ * efi_query_variable_store() and forces garbage collection.
+ *
+ * Only enable this option if deleting EFI variables does not free up
+ * space in your variable store, e.g. if despite deleting variables
+ * you're unable to create new ones.
+ */
+static int __init setup_storage_paranoia(char *arg)
+{
+	efi_no_storage_paranoia = true;
+	return 0;
+}
+early_param("efi_no_storage_paranoia", setup_storage_paranoia);
+
+/*
+ * Deleting the dummy variable which kicks off garbage collection
+*/
+void efi_delete_dummy_variable(void)
+{
+	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+			 EFI_VARIABLE_NON_VOLATILE |
+			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
+			 EFI_VARIABLE_RUNTIME_ACCESS,
+			 0, NULL);
+}
+
+/*
+ * Some firmware implementations refuse to boot if there's insufficient space
+ * in the variable store. Ensure that we never use more than a safe limit.
+ *
+ * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
+ * store.
+ */
+efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
+{
+	efi_status_t status;
+	u64 storage_size, remaining_size, max_size;
+
+	if (!(attributes & EFI_VARIABLE_NON_VOLATILE))
+		return 0;
+
+	status = efi.query_variable_info(attributes, &storage_size,
+					 &remaining_size, &max_size);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	/*
+	 * We account for that by refusing the write if permitting it would
+	 * reduce the available space to under 5KB. This figure was provided by
+	 * Samsung, so should be safe.
+	 */
+	if ((remaining_size - size < EFI_MIN_RESERVE) &&
+		!efi_no_storage_paranoia) {
+
+		/*
+		 * Triggering garbage collection may require that the firmware
+		 * generate a real EFI_OUT_OF_RESOURCES error. We can force
+		 * that by attempting to use more space than is available.
+		 */
+		unsigned long dummy_size = remaining_size + 1024;
+		void *dummy = kzalloc(dummy_size, GFP_ATOMIC);
+
+		if (!dummy)
+			return EFI_OUT_OF_RESOURCES;
+
+		status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+					  EFI_VARIABLE_NON_VOLATILE |
+					  EFI_VARIABLE_BOOTSERVICE_ACCESS |
+					  EFI_VARIABLE_RUNTIME_ACCESS,
+					  dummy_size, dummy);
+
+		if (status == EFI_SUCCESS) {
+			/*
+			 * This should have failed, so if it didn't make sure
+			 * that we delete it...
+			 */
+			efi_delete_dummy_variable();
+		}
+
+		kfree(dummy);
+
+		/*
+		 * The runtime code may now have triggered a garbage collection
+		 * run, so check the variable info again
+		 */
+		status = efi.query_variable_info(attributes, &storage_size,
+						 &remaining_size, &max_size);
+
+		if (status != EFI_SUCCESS)
+			return status;
+
+		/*
+		 * There still isn't enough room, so return an error
+		 */
+		if (remaining_size - size < EFI_MIN_RESERVE)
+			return EFI_OUT_OF_RESOURCES;
+	}
+
+	return EFI_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(efi_query_variable_store);
+
+/*
+ * The UEFI specification makes it clear that the operating system is free to do
+ * whatever it wants with boot services code after ExitBootServices() has been
+ * called. Ignoring this recommendation a significant bunch of EFI implementations 
+ * continue calling into boot services code (SetVirtualAddressMap). In order to 
+ * work around such buggy implementations we reserve boot services region during 
+ * EFI init and make sure it stays executable. Then, after SetVirtualAddressMap(), it
+* is discarded.
+*/
+void __init efi_reserve_boot_services(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		u64 start = md->phys_addr;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+		/* Only reserve where possible:
+		 * - Not within any already allocated areas
+		 * - Not over any memory area (really needed, if above?)
+		 * - Not within any part of the kernel
+		 * - Not the bios reserved area
+		*/
+		if ((start + size > __pa_symbol(_text)
+				&& start <= __pa_symbol(_end)) ||
+			!e820_all_mapped(start, start+size, E820_RAM) ||
+			memblock_is_region_reserved(start, size)) {
+			/* Could not reserve, skip it */
+			md->num_pages = 0;
+			memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n",
+				     start, start+size-1);
+		} else
+			memblock_reserve(start, size);
+	}
+}
+
+void __init efi_free_boot_services(void)
+{
+	void *p;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		efi_memory_desc_t *md = p;
+		unsigned long long start = md->phys_addr;
+		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+
+		if (md->type != EFI_BOOT_SERVICES_CODE &&
+		    md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+
+		/* Could not reserve boot area */
+		if (!size)
+			continue;
+
+		free_bootmem_late(start, size);
+	}
+
+	efi_unmap_memmap();
+}
+
+/*
+ * A number of config table entries get remapped to virtual addresses
+ * after entering EFI virtual mode. However, the kexec kernel requires
+ * their physical addresses therefore we pass them via setup_data and
+ * correct those entries to their respective physical addresses here.
+ *
+ * Currently only handles smbios which is necessary for some firmware
+ * implementation.
+ */
+int __init efi_reuse_config(u64 tables, int nr_tables)
+{
+	int i, sz, ret = 0;
+	void *p, *tablep;
+	struct efi_setup_data *data;
+
+	if (!efi_setup)
+		return 0;
+
+	if (!efi_enabled(EFI_64BIT))
+		return 0;
+
+	data = early_memremap(efi_setup, sizeof(*data));
+	if (!data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (!data->smbios)
+		goto out_memremap;
+
+	sz = sizeof(efi_config_table_64_t);
+
+	p = tablep = early_memremap(tables, nr_tables * sz);
+	if (!p) {
+		pr_err("Could not map Configuration table!\n");
+		ret = -ENOMEM;
+		goto out_memremap;
+	}
+
+	for (i = 0; i < efi.systab->nr_tables; i++) {
+		efi_guid_t guid;
+
+		guid = ((efi_config_table_64_t *)p)->guid;
+
+		if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
+			((efi_config_table_64_t *)p)->table = data->smbios;
+		p += sz;
+	}
+	early_memunmap(tablep, nr_tables * sz);
+
+out_memremap:
+	early_memunmap(data, sizeof(*data));
+out:
+	return ret;
+}
+
+void __init efi_apply_memmap_quirks(void)
+{
+	/*
+	 * Once setup is done earlier, unmap the EFI memory map on mismatched
+	 * firmware/kernel architectures since there is no support for runtime
+	 * services.
+	 */
+	if (!efi_runtime_supported()) {
+		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+		efi_unmap_memmap();
+	}
+
+	/*
+	 * UV doesn't support the new EFI pagetable mapping yet.
+	 */
+	if (is_uv_system())
+		set_bit(EFI_OLD_MEMMAP, &efi.flags);
+}
+
+/*
+ * For most modern platforms the preferred method of powering off is via
+ * ACPI. However, there are some that are known to require the use of
+ * EFI runtime services and for which ACPI does not work at all.
+ *
+ * Using EFI is a last resort, to be used only if no other option
+ * exists.
+ */
+bool efi_reboot_required(void)
+{
+	if (!acpi_gbl_reduced_hardware)
+		return false;
+
+	efi_reboot_quirk_mode = EFI_RESET_WARM;
+	return true;
+}
+
+bool efi_poweroff_required(void)
+{
+	return !!acpi_gbl_reduced_hardware;
+}
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index 097e7a7940d..af9307f2cc2 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -20,3 +20,4 @@ obj-$(subst m,y,$(CONFIG_DRM_MEDFIELD)) += platform_tc35876x.o
 obj-$(subst m,y,$(CONFIG_SERIAL_MRST_MAX3110)) += platform_max3111.o
 # MISC Devices
 obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
new file mode 100644
index 00000000000..973cf3bfa9f
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c
@@ -0,0 +1,72 @@
+/*
+ * platform_wdt.c: Watchdog platform library file
+ *
+ * (C) Copyright 2014 Intel Corporation
+ * Author: David Cohen <david.a.cohen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/intel-mid_wdt.h>
+#include <asm/intel-mid.h>
+#include <asm/io_apic.h>
+
+#define TANGIER_EXT_TIMER0_MSI 15
+
+static struct platform_device wdt_dev = {
+	.name = "intel_mid_wdt",
+	.id = -1,
+};
+
+static int tangier_probe(struct platform_device *pdev)
+{
+	int ioapic;
+	int irq;
+	struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
+	struct io_apic_irq_attr irq_attr = { 0 };
+
+	if (!pdata)
+		return -EINVAL;
+
+	irq = pdata->irq;
+	ioapic = mp_find_ioapic(irq);
+	if (ioapic >= 0) {
+		int ret;
+		irq_attr.ioapic = ioapic;
+		irq_attr.ioapic_pin = irq;
+		irq_attr.trigger = 1;
+		/* irq_attr.polarity = 0; -> Active high */
+		ret = io_apic_set_pci_routing(NULL, irq, &irq_attr);
+		if (ret)
+			return ret;
+	} else {
+		dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n",
+			 irq);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct intel_mid_wdt_pdata tangier_pdata = {
+	.irq = TANGIER_EXT_TIMER0_MSI,
+	.probe = tangier_probe,
+};
+
+static int __init register_mid_wdt(void)
+{
+	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) {
+		wdt_dev.dev.platform_data = &tangier_pdata;
+		return platform_device_register(&wdt_dev);
+	}
+
+	return -ENODEV;
+}
+
+rootfs_initcall(register_mid_wdt);
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 424f4c97a44..6ec7910f59b 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -165,7 +165,7 @@ static void fix_processor_context(void)
  *		by __save_processor_state()
  *	@ctxt - structure to load the registers contents from
  */
-static void __restore_processor_state(struct saved_context *ctxt)
+static void notrace __restore_processor_state(struct saved_context *ctxt)
 {
 	if (ctxt->misc_enable_saved)
 		wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
@@ -239,7 +239,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
 }
 
 /* Needed by apm.c */
-void restore_processor_state(void)
+void notrace restore_processor_state(void)
 {
 	__restore_processor_state(&saved_context);
 }
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 04f82e020f2..2a206d2b14a 100644
--- a/arch/x86/um/asm/processor.h
+++ b/arch/x86/um/asm/processor.h
@@ -25,7 +25,8 @@ static inline void rep_nop(void)
 	__asm__ __volatile__("rep;nop": : :"memory");
 }
 
-#define cpu_relax()	rep_nop()
+#define cpu_relax()		rep_nop()
+#define cpu_relax_lowlatency()	cpu_relax()
 
 #include <asm/processor-generic.h>
 
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index 9769df09403..61b04fe36e6 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -9,18 +9,8 @@ VDSOX32-$(CONFIG_X86_X32_ABI)	:= y
 VDSO32-$(CONFIG_X86_32)		:= y
 VDSO32-$(CONFIG_COMPAT)		:= y
 
-vdso-install-$(VDSO64-y)	+= vdso.so
-vdso-install-$(VDSOX32-y)	+= vdsox32.so
-vdso-install-$(VDSO32-y)	+= $(vdso32-images)
-
-
 # files to link into the vdso
-vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
-
-vobjs-$(VDSOX32-y) += $(vobjx32s-compat)
-
-# Filter out x32 objects.
-vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y))
+vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vdso-fakesections.o
 
 # files to link into kernel
 obj-y				+= vma.o
@@ -34,7 +24,7 @@ vdso_img-$(VDSO32-y)		+= 32-sysenter
 
 obj-$(VDSO32-y)			+= vdso32-setup.o
 
-vobjs := $(foreach F,$(vobj64s),$(obj)/$F)
+vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
 
 $(obj)/vdso.o: $(obj)/vdso.so
 
@@ -76,7 +66,8 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso2c FORCE
 #
 CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
        $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
-       -fno-omit-frame-pointer -foptimize-sibling-calls
+       -fno-omit-frame-pointer -foptimize-sibling-calls \
+       -DDISABLE_BRANCH_PROFILING
 
 $(vobjs): KBUILD_CFLAGS += $(CFL)
 
@@ -104,7 +95,13 @@ VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
 			   -Wl,-z,max-page-size=4096 \
 			   -Wl,-z,common-page-size=4096
 
-vobjx32s-y := $(vobj64s:.o=-x32.o)
+# 64-bit objects to re-brand as x32
+vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y))
+
+# x32-rebranded versions
+vobjx32s-y := $(vobjs64-for-x32:.o=-x32.o)
+
+# same thing, but in the output directory
 vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
 
 # Convert 64bit object file to x32 for x32 vDSO.
@@ -137,7 +134,7 @@ override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
 
 targets += vdso32/vdso32.lds
 targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o)
-targets += vdso32/vclock_gettime.o
+targets += vdso32/vclock_gettime.o vdso32/vdso-fakesections.o
 
 $(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%)
 
@@ -153,11 +150,13 @@ KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
 KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
+KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
 $(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
 
 $(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
 				 $(obj)/vdso32/vdso32.lds \
 				 $(obj)/vdso32/vclock_gettime.o \
+				 $(obj)/vdso32/vdso-fakesections.o \
 				 $(obj)/vdso32/note.o \
 				 $(obj)/vdso32/%.o
 	$(call if_changed,vdso)
@@ -172,19 +171,34 @@ quiet_cmd_vdso = VDSO    $@
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
 VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
-	-Wl,-Bsymbolic $(LTO_CFLAGS)
+	$(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS)
 GCOV_PROFILE := n
 
 #
-# Install the unstripped copy of vdso*.so listed in $(vdso-install-y).
+# Install the unstripped copies of vdso*.so.  If our toolchain supports
+# build-id, install .build-id links as well.
 #
-quiet_cmd_vdso_install = INSTALL $@
-      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
-$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE
+quiet_cmd_vdso_install = INSTALL $(@:install_%=%)
+define cmd_vdso_install
+	cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \
+	if readelf -n $< |grep -q 'Build ID'; then \
+	  buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \
+	  first=`echo $$buildid | cut -b-2`; \
+	  last=`echo $$buildid | cut -b3-`; \
+	  mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \
+	  ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \
+	fi
+endef
+
+vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%)
+
+$(MODLIB)/vdso: FORCE
 	@mkdir -p $(MODLIB)/vdso
+
+$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE
 	$(call cmd,vdso_install)
 
-PHONY += vdso_install $(vdso-install-y)
-vdso_install: $(vdso-install-y)
+PHONY += vdso_install $(vdso_img_insttargets)
+vdso_install: $(vdso_img_insttargets) FORCE
 
 clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80*
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index b2e4f493e5b..9793322751e 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -11,9 +11,6 @@
  * Check with readelf after changing.
  */
 
-/* Disable profiling for userspace code: */
-#define DISABLE_BRANCH_PROFILING
-
 #include <uapi/linux/time.h>
 #include <asm/vgtod.h>
 #include <asm/hpet.h>
diff --git a/arch/x86/vdso/vdso-fakesections.c b/arch/x86/vdso/vdso-fakesections.c
new file mode 100644
index 00000000000..aa5fbfab20a
--- /dev/null
+++ b/arch/x86/vdso/vdso-fakesections.c
@@ -0,0 +1,21 @@
+/*
+ * Copyright 2014 Andy Lutomirski
+ * Subject to the GNU Public License, v.2
+ *
+ * String table for loadable section headers.  See vdso2c.h for why
+ * this exists.
+ */
+
+const char fake_shstrtab[] __attribute__((section(".fake_shstrtab"))) =
+	".hash\0"
+	".dynsym\0"
+	".dynstr\0"
+	".gnu.version\0"
+	".gnu.version_d\0"
+	".dynamic\0"
+	".rodata\0"
+	".fake_shstrtab\0"  /* Yay, self-referential code. */
+	".note\0"
+	".eh_frame_hdr\0"
+	".eh_frame\0"
+	".text";
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S
index 2ec72f651eb..9197544eea9 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/vdso/vdso-layout.lds.S
@@ -6,6 +6,16 @@
  * This script controls its layout.
  */
 
+#if defined(BUILD_VDSO64)
+# define SHDR_SIZE 64
+#elif defined(BUILD_VDSO32) || defined(BUILD_VDSOX32)
+# define SHDR_SIZE 40
+#else
+# error unknown VDSO target
+#endif
+
+#define NUM_FAKE_SHDRS 13
+
 SECTIONS
 {
 	. = SIZEOF_HEADERS;
@@ -18,36 +28,53 @@ SECTIONS
 	.gnu.version_d	: { *(.gnu.version_d) }
 	.gnu.version_r	: { *(.gnu.version_r) }
 
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.rodata		: {
+		*(.rodata*)
+		*(.data*)
+		*(.sdata*)
+		*(.got.plt) *(.got)
+		*(.gnu.linkonce.d.*)
+		*(.bss*)
+		*(.dynbss*)
+		*(.gnu.linkonce.b.*)
+
+		/*
+		 * Ideally this would live in a C file, but that won't
+		 * work cleanly for x32 until we start building the x32
+		 * C code using an x32 toolchain.
+		 */
+		VDSO_FAKE_SECTION_TABLE_START = .;
+		. = . + NUM_FAKE_SHDRS * SHDR_SIZE;
+		VDSO_FAKE_SECTION_TABLE_END = .;
+	}						:text
+
+	.fake_shstrtab	: { *(.fake_shstrtab) }		:text
+
+
 	.note		: { *(.note.*) }		:text	:note
 
 	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
 	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
 
-	.dynamic	: { *(.dynamic) }		:text	:dynamic
-
-	.rodata		: { *(.rodata*) }		:text
-	.data		: {
-	      *(.data*)
-	      *(.sdata*)
-	      *(.got.plt) *(.got)
-	      *(.gnu.linkonce.d.*)
-	      *(.bss*)
-	      *(.dynbss*)
-	      *(.gnu.linkonce.b.*)
-	}
-
-	.altinstructions	: { *(.altinstructions) }
-	.altinstr_replacement	: { *(.altinstr_replacement) }
 
 	/*
-	 * Align the actual code well away from the non-instruction data.
-	 * This is the best thing for the I-cache.
+	 * Text is well-separated from actual data: there's plenty of
+	 * stuff that isn't used at runtime in between.
 	 */
-	. = ALIGN(0x100);
 
 	.text		: { *(.text*) }			:text	=0x90909090,
 
 	/*
+	 * At the end so that eu-elflint stays happy when vdso2c strips
+	 * these.  A better implementation would avoid allocating space
+	 * for these.
+	 */
+	.altinstructions	: { *(.altinstructions) }	:text
+	.altinstr_replacement	: { *(.altinstr_replacement) }	:text
+
+	/*
 	 * The remainder of the vDSO consists of special pages that are
 	 * shared between the kernel and userspace.  It needs to be at the
 	 * end so that it doesn't overlap the mapping of the actual
@@ -75,6 +102,7 @@ SECTIONS
 	/DISCARD/ : {
 		*(.discard)
 		*(.discard.*)
+		*(__bug_table)
 	}
 }
 
diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/vdso/vdso.lds.S
index 75e3404c83b..6807932643c 100644
--- a/arch/x86/vdso/vdso.lds.S
+++ b/arch/x86/vdso/vdso.lds.S
@@ -6,6 +6,8 @@
  * the DSO.
  */
 
+#define BUILD_VDSO64
+
 #include "vdso-layout.lds.S"
 
 /*
diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/vdso/vdso2c.c
index 450ac6eaf61..238dbe82776 100644
--- a/arch/x86/vdso/vdso2c.c
+++ b/arch/x86/vdso/vdso2c.c
@@ -23,6 +23,8 @@ enum {
 	sym_vvar_page,
 	sym_hpet_page,
 	sym_end_mapping,
+	sym_VDSO_FAKE_SECTION_TABLE_START,
+	sym_VDSO_FAKE_SECTION_TABLE_END,
 };
 
 const int special_pages[] = {
@@ -30,15 +32,26 @@ const int special_pages[] = {
 	sym_hpet_page,
 };
 
-char const * const required_syms[] = {
-	[sym_vvar_page] = "vvar_page",
-	[sym_hpet_page] = "hpet_page",
-	[sym_end_mapping] = "end_mapping",
-	"VDSO32_NOTE_MASK",
-	"VDSO32_SYSENTER_RETURN",
-	"__kernel_vsyscall",
-	"__kernel_sigreturn",
-	"__kernel_rt_sigreturn",
+struct vdso_sym {
+	const char *name;
+	bool export;
+};
+
+struct vdso_sym required_syms[] = {
+	[sym_vvar_page] = {"vvar_page", true},
+	[sym_hpet_page] = {"hpet_page", true},
+	[sym_end_mapping] = {"end_mapping", true},
+	[sym_VDSO_FAKE_SECTION_TABLE_START] = {
+		"VDSO_FAKE_SECTION_TABLE_START", false
+	},
+	[sym_VDSO_FAKE_SECTION_TABLE_END] = {
+		"VDSO_FAKE_SECTION_TABLE_END", false
+	},
+	{"VDSO32_NOTE_MASK", true},
+	{"VDSO32_SYSENTER_RETURN", true},
+	{"__kernel_vsyscall", true},
+	{"__kernel_sigreturn", true},
+	{"__kernel_rt_sigreturn", true},
 };
 
 __attribute__((format(printf, 1, 2))) __attribute__((noreturn))
@@ -54,7 +67,7 @@ static void fail(const char *format, ...)
 }
 
 /*
- * Evil macros to do a little-endian read.
+ * Evil macros for little-endian reads and writes
  */
 #define GLE(x, bits, ifnot)						\
 	__builtin_choose_expr(						\
@@ -62,45 +75,42 @@ static void fail(const char *format, ...)
 		(__typeof__(*(x)))get_unaligned_le##bits(x), ifnot)
 
 extern void bad_get_le(void);
-#define LAST_LE(x)							\
+#define LAST_GLE(x)							\
 	__builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le())
 
 #define GET_LE(x)							\
-	GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_LE(x))))
+	GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_GLE(x))))
+
+#define PLE(x, val, bits, ifnot)					\
+	__builtin_choose_expr(						\
+		(sizeof(*(x)) == bits/8),				\
+		put_unaligned_le##bits((val), (x)), ifnot)
+
+extern void bad_put_le(void);
+#define LAST_PLE(x, val)						\
+	__builtin_choose_expr(sizeof(*(x)) == 1, *(x) = (val), bad_put_le())
+
+#define PUT_LE(x, val)					\
+	PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val))))
+
 
 #define NSYMS (sizeof(required_syms) / sizeof(required_syms[0]))
 
-#define BITS 64
-#define GOFUNC go64
-#define Elf_Ehdr Elf64_Ehdr
-#define Elf_Shdr Elf64_Shdr
-#define Elf_Phdr Elf64_Phdr
-#define Elf_Sym Elf64_Sym
-#define Elf_Dyn Elf64_Dyn
+#define BITSFUNC3(name, bits) name##bits
+#define BITSFUNC2(name, bits) BITSFUNC3(name, bits)
+#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS)
+
+#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x
+#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
+#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x)
+
+#define ELF_BITS 64
 #include "vdso2c.h"
-#undef BITS
-#undef GOFUNC
-#undef Elf_Ehdr
-#undef Elf_Shdr
-#undef Elf_Phdr
-#undef Elf_Sym
-#undef Elf_Dyn
-
-#define BITS 32
-#define GOFUNC go32
-#define Elf_Ehdr Elf32_Ehdr
-#define Elf_Shdr Elf32_Shdr
-#define Elf_Phdr Elf32_Phdr
-#define Elf_Sym Elf32_Sym
-#define Elf_Dyn Elf32_Dyn
+#undef ELF_BITS
+
+#define ELF_BITS 32
 #include "vdso2c.h"
-#undef BITS
-#undef GOFUNC
-#undef Elf_Ehdr
-#undef Elf_Shdr
-#undef Elf_Phdr
-#undef Elf_Sym
-#undef Elf_Dyn
+#undef ELF_BITS
 
 static void go(void *addr, size_t len, FILE *outfile, const char *name)
 {
diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h
index 8a074637a57..11b65d4f941 100644
--- a/arch/x86/vdso/vdso2c.h
+++ b/arch/x86/vdso/vdso2c.h
@@ -4,21 +4,139 @@
  * are built for 32-bit userspace.
  */
 
-static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
+/*
+ * We're writing a section table for a few reasons:
+ *
+ * The Go runtime had a couple of bugs: it would read the section
+ * table to try to figure out how many dynamic symbols there were (it
+ * shouldn't have looked at the section table at all) and, if there
+ * were no SHT_SYNDYM section table entry, it would use an
+ * uninitialized value for the number of symbols.  An empty DYNSYM
+ * table would work, but I see no reason not to write a valid one (and
+ * keep full performance for old Go programs).  This hack is only
+ * needed on x86_64.
+ *
+ * The bug was introduced on 2012-08-31 by:
+ * https://code.google.com/p/go/source/detail?r=56ea40aac72b
+ * and was fixed on 2014-06-13 by:
+ * https://code.google.com/p/go/source/detail?r=fc1cd5e12595
+ *
+ * Binutils has issues debugging the vDSO: it reads the section table to
+ * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which
+ * would break build-id if we removed the section table.  Binutils
+ * also requires that shstrndx != 0.  See:
+ * https://sourceware.org/bugzilla/show_bug.cgi?id=17064
+ *
+ * elfutils might not look for PT_NOTE if there is a section table at
+ * all.  I don't know whether this matters for any practical purpose.
+ *
+ * For simplicity, rather than hacking up a partial section table, we
+ * just write a mostly complete one.  We omit non-dynamic symbols,
+ * though, since they're rather large.
+ *
+ * Once binutils gets fixed, we might be able to drop this for all but
+ * the 64-bit vdso, since build-id only works in kernel RPMs, and
+ * systems that update to new enough kernel RPMs will likely update
+ * binutils in sync.  build-id has never worked for home-built kernel
+ * RPMs without manual symlinking, and I suspect that no one ever does
+ * that.
+ */
+struct BITSFUNC(fake_sections)
+{
+	ELF(Shdr) *table;
+	unsigned long table_offset;
+	int count, max_count;
+
+	int in_shstrndx;
+	unsigned long shstr_offset;
+	const char *shstrtab;
+	size_t shstrtab_len;
+
+	int out_shstrndx;
+};
+
+static unsigned int BITSFUNC(find_shname)(struct BITSFUNC(fake_sections) *out,
+					  const char *name)
+{
+	const char *outname = out->shstrtab;
+	while (outname - out->shstrtab < out->shstrtab_len) {
+		if (!strcmp(name, outname))
+			return (outname - out->shstrtab) + out->shstr_offset;
+		outname += strlen(outname) + 1;
+	}
+
+	if (*name)
+		printf("Warning: could not find output name \"%s\"\n", name);
+	return out->shstr_offset + out->shstrtab_len - 1;  /* Use a null. */
+}
+
+static void BITSFUNC(init_sections)(struct BITSFUNC(fake_sections) *out)
+{
+	if (!out->in_shstrndx)
+		fail("didn't find the fake shstrndx\n");
+
+	memset(out->table, 0, out->max_count * sizeof(ELF(Shdr)));
+
+	if (out->max_count < 1)
+		fail("we need at least two fake output sections\n");
+
+	PUT_LE(&out->table[0].sh_type, SHT_NULL);
+	PUT_LE(&out->table[0].sh_name, BITSFUNC(find_shname)(out, ""));
+
+	out->count = 1;
+}
+
+static void BITSFUNC(copy_section)(struct BITSFUNC(fake_sections) *out,
+				   int in_idx, const ELF(Shdr) *in,
+				   const char *name)
+{
+	uint64_t flags = GET_LE(&in->sh_flags);
+
+	bool copy = flags & SHF_ALLOC &&
+		(GET_LE(&in->sh_size) ||
+		 (GET_LE(&in->sh_type) != SHT_RELA &&
+		  GET_LE(&in->sh_type) != SHT_REL)) &&
+		strcmp(name, ".altinstructions") &&
+		strcmp(name, ".altinstr_replacement");
+
+	if (!copy)
+		return;
+
+	if (out->count >= out->max_count)
+		fail("too many copied sections (max = %d)\n", out->max_count);
+
+	if (in_idx == out->in_shstrndx)
+		out->out_shstrndx = out->count;
+
+	out->table[out->count] = *in;
+	PUT_LE(&out->table[out->count].sh_name,
+	       BITSFUNC(find_shname)(out, name));
+
+	/* elfutils requires that a strtab have the correct type. */
+	if (!strcmp(name, ".fake_shstrtab"))
+		PUT_LE(&out->table[out->count].sh_type, SHT_STRTAB);
+
+	out->count++;
+}
+
+static void BITSFUNC(go)(void *addr, size_t len,
+			 FILE *outfile, const char *name)
 {
 	int found_load = 0;
 	unsigned long load_size = -1;  /* Work around bogus warning */
 	unsigned long data_size;
-	Elf_Ehdr *hdr = (Elf_Ehdr *)addr;
+	ELF(Ehdr) *hdr = (ELF(Ehdr) *)addr;
 	int i;
 	unsigned long j;
-	Elf_Shdr *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr,
+	ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr,
 		*alt_sec = NULL;
-	Elf_Dyn *dyn = 0, *dyn_end = 0;
+	ELF(Dyn) *dyn = 0, *dyn_end = 0;
 	const char *secstrings;
 	uint64_t syms[NSYMS] = {};
 
-	Elf_Phdr *pt = (Elf_Phdr *)(addr + GET_LE(&hdr->e_phoff));
+	struct BITSFUNC(fake_sections) fake_sections = {};
+
+	ELF(Phdr) *pt = (ELF(Phdr) *)(addr + GET_LE(&hdr->e_phoff));
 
 	/* Walk the segment table. */
 	for (i = 0; i < GET_LE(&hdr->e_phnum); i++) {
@@ -49,7 +167,7 @@ static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 	for (i = 0; dyn + i < dyn_end &&
 		     GET_LE(&dyn[i].d_tag) != DT_NULL; i++) {
 		typeof(dyn[i].d_tag) tag = GET_LE(&dyn[i].d_tag);
-		if (tag == DT_REL || tag == DT_RELSZ ||
+		if (tag == DT_REL || tag == DT_RELSZ || tag == DT_RELA ||
 		    tag == DT_RELENT || tag == DT_TEXTREL)
 			fail("vdso image contains dynamic relocations\n");
 	}
@@ -59,7 +177,7 @@ static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 		GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx);
 	secstrings = addr + GET_LE(&secstrings_hdr->sh_offset);
 	for (i = 0; i < GET_LE(&hdr->e_shnum); i++) {
-		Elf_Shdr *sh = addr + GET_LE(&hdr->e_shoff) +
+		ELF(Shdr) *sh = addr + GET_LE(&hdr->e_shoff) +
 			GET_LE(&hdr->e_shentsize) * i;
 		if (GET_LE(&sh->sh_type) == SHT_SYMTAB)
 			symtab_hdr = sh;
@@ -80,20 +198,62 @@ static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 	     i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize);
 	     i++) {
 		int k;
-		Elf_Sym *sym = addr + GET_LE(&symtab_hdr->sh_offset) +
+		ELF(Sym) *sym = addr + GET_LE(&symtab_hdr->sh_offset) +
 			GET_LE(&symtab_hdr->sh_entsize) * i;
 		const char *name = addr + GET_LE(&strtab_hdr->sh_offset) +
 			GET_LE(&sym->st_name);
+
 		for (k = 0; k < NSYMS; k++) {
-			if (!strcmp(name, required_syms[k])) {
+			if (!strcmp(name, required_syms[k].name)) {
 				if (syms[k]) {
 					fail("duplicate symbol %s\n",
-					     required_syms[k]);
+					     required_syms[k].name);
 				}
 				syms[k] = GET_LE(&sym->st_value);
 			}
 		}
+
+		if (!strcmp(name, "fake_shstrtab")) {
+			ELF(Shdr) *sh;
+
+			fake_sections.in_shstrndx = GET_LE(&sym->st_shndx);
+			fake_sections.shstrtab = addr + GET_LE(&sym->st_value);
+			fake_sections.shstrtab_len = GET_LE(&sym->st_size);
+			sh = addr + GET_LE(&hdr->e_shoff) +
+				GET_LE(&hdr->e_shentsize) *
+				fake_sections.in_shstrndx;
+			fake_sections.shstr_offset = GET_LE(&sym->st_value) -
+				GET_LE(&sh->sh_addr);
+		}
+	}
+
+	/* Build the output section table. */
+	if (!syms[sym_VDSO_FAKE_SECTION_TABLE_START] ||
+	    !syms[sym_VDSO_FAKE_SECTION_TABLE_END])
+		fail("couldn't find fake section table\n");
+	if ((syms[sym_VDSO_FAKE_SECTION_TABLE_END] -
+	     syms[sym_VDSO_FAKE_SECTION_TABLE_START]) % sizeof(ELF(Shdr)))
+		fail("fake section table size isn't a multiple of sizeof(Shdr)\n");
+	fake_sections.table = addr + syms[sym_VDSO_FAKE_SECTION_TABLE_START];
+	fake_sections.table_offset = syms[sym_VDSO_FAKE_SECTION_TABLE_START];
+	fake_sections.max_count = (syms[sym_VDSO_FAKE_SECTION_TABLE_END] -
+				   syms[sym_VDSO_FAKE_SECTION_TABLE_START]) /
+		sizeof(ELF(Shdr));
+
+	BITSFUNC(init_sections)(&fake_sections);
+	for (i = 0; i < GET_LE(&hdr->e_shnum); i++) {
+		ELF(Shdr) *sh = addr + GET_LE(&hdr->e_shoff) +
+			GET_LE(&hdr->e_shentsize) * i;
+		BITSFUNC(copy_section)(&fake_sections, i, sh,
+				       secstrings + GET_LE(&sh->sh_name));
 	}
+	if (!fake_sections.out_shstrndx)
+		fail("didn't generate shstrndx?!?\n");
+
+	PUT_LE(&hdr->e_shoff, fake_sections.table_offset);
+	PUT_LE(&hdr->e_shentsize, sizeof(ELF(Shdr)));
+	PUT_LE(&hdr->e_shnum, fake_sections.count);
+	PUT_LE(&hdr->e_shstrndx, fake_sections.out_shstrndx);
 
 	/* Validate mapping addresses. */
 	for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
@@ -102,22 +262,17 @@ static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 
 		if (syms[i] % 4096)
 			fail("%s must be a multiple of 4096\n",
-			     required_syms[i]);
+			     required_syms[i].name);
 		if (syms[i] < data_size)
 			fail("%s must be after the text mapping\n",
-			     required_syms[i]);
+			     required_syms[i].name);
 		if (syms[sym_end_mapping] < syms[i] + 4096)
-			fail("%s overruns end_mapping\n", required_syms[i]);
+			fail("%s overruns end_mapping\n",
+			     required_syms[i].name);
 	}
 	if (syms[sym_end_mapping] % 4096)
 		fail("end_mapping must be a multiple of 4096\n");
 
-	/* Remove sections. */
-	hdr->e_shoff = 0;
-	hdr->e_shentsize = 0;
-	hdr->e_shnum = 0;
-	hdr->e_shstrndx = htole16(SHN_UNDEF);
-
 	if (!name) {
 		fwrite(addr, load_size, 1, outfile);
 		return;
@@ -155,9 +310,9 @@ static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name)
 			(unsigned long)GET_LE(&alt_sec->sh_size));
 	}
 	for (i = 0; i < NSYMS; i++) {
-		if (syms[i])
+		if (required_syms[i].export && syms[i])
 			fprintf(outfile, "\t.sym_%s = 0x%" PRIx64 ",\n",
-				required_syms[i], syms[i]);
+				required_syms[i].name, syms[i]);
 	}
 	fprintf(outfile, "};\n");
 }
diff --git a/arch/x86/vdso/vdso32/vdso-fakesections.c b/arch/x86/vdso/vdso32/vdso-fakesections.c
new file mode 100644
index 00000000000..541468e2526
--- /dev/null
+++ b/arch/x86/vdso/vdso32/vdso-fakesections.c
@@ -0,0 +1 @@
+#include "../vdso-fakesections.c"
diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/vdso/vdsox32.lds.S
index 46b991b578a..697c11ece90 100644
--- a/arch/x86/vdso/vdsox32.lds.S
+++ b/arch/x86/vdso/vdsox32.lds.S
@@ -6,6 +6,8 @@
  * the DSO.
  */
 
+#define BUILD_VDSOX32
+
 #include "vdso-layout.lds.S"
 
 /*
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index e1513c47872..5a5176de8d0 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -62,6 +62,9 @@ struct linux_binprm;
    Only used for the 64-bit and x32 vdsos. */
 static unsigned long vdso_addr(unsigned long start, unsigned len)
 {
+#ifdef CONFIG_X86_32
+	return 0;
+#else
 	unsigned long addr, end;
 	unsigned offset;
 	end = (start + PMD_SIZE - 1) & PMD_MASK;
@@ -83,6 +86,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 	addr = align_vdso_addr(addr);
 
 	return addr;
+#endif
 }
 
 static int map_vdso(const struct vdso_image *image, bool calculate_addr)
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 96ab2c09cb6..7322755f337 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -22,3 +22,4 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 obj-$(CONFIG_XEN_DOM0)		+= apic.o vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
+obj-$(CONFIG_XEN_EFI)		+= efi.o
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
new file mode 100644
index 00000000000..a02e09e18f5
--- /dev/null
+++ b/arch/x86/xen/efi.c
@@ -0,0 +1,43 @@
+/*
+ * Copyright (c) 2014 Oracle Co., Daniel Kiper
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/string.h>
+
+#include <xen/xen-ops.h>
+
+#include <asm/setup.h>
+
+void __init xen_efi_init(void)
+{
+	efi_system_table_t *efi_systab_xen;
+
+	efi_systab_xen = xen_efi_probe();
+
+	if (efi_systab_xen == NULL)
+		return;
+
+	strncpy((char *)&boot_params.efi_info.efi_loader_signature, "Xen",
+			sizeof(boot_params.efi_info.efi_loader_signature));
+	boot_params.efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
+	boot_params.efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);
+
+	set_bit(EFI_BOOT, &efi.flags);
+	set_bit(EFI_PARAVIRT, &efi.flags);
+	set_bit(EFI_64BIT, &efi.flags);
+}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index f17b29210ac..94813515fdd 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1537,7 +1537,10 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	if (!xen_pvh_domain())
 		pv_cpu_ops = xen_cpu_ops;
 
-	x86_init.resources.memory_setup = xen_memory_setup;
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		x86_init.resources.memory_setup = xen_auto_xlated_memory_setup;
+	else
+		x86_init.resources.memory_setup = xen_memory_setup;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
 
@@ -1715,6 +1718,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	xen_setup_runstate_info(0);
 
+	xen_efi_init();
+
 	/* Start the world */
 #ifdef CONFIG_X86_32
 	i386_start_kernel();
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index c9858358858..ebfa9b2c871 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -36,99 +36,133 @@
 
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 
 #include <xen/interface/xen.h>
 #include <xen/page.h>
 #include <xen/grant_table.h>
+#include <xen/xen.h>
 
 #include <asm/pgtable.h>
 
-static int map_pte_fn(pte_t *pte, struct page *pmd_page,
-		      unsigned long addr, void *data)
+static struct gnttab_vm_area {
+	struct vm_struct *area;
+	pte_t **ptes;
+} gnttab_shared_vm_area, gnttab_status_vm_area;
+
+int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   void **__shared)
 {
-	unsigned long **frames = (unsigned long **)data;
+	void *shared = *__shared;
+	unsigned long addr;
+	unsigned long i;
 
-	set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
-	(*frames)++;
-	return 0;
-}
+	if (shared == NULL)
+		*__shared = shared = gnttab_shared_vm_area.area->addr;
 
-/*
- * This function is used to map shared frames to store grant status. It is
- * different from map_pte_fn above, the frames type here is uint64_t.
- */
-static int map_pte_fn_status(pte_t *pte, struct page *pmd_page,
-			     unsigned long addr, void *data)
-{
-	uint64_t **frames = (uint64_t **)data;
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i],
+			   mfn_pte(frames[i], PAGE_KERNEL));
+		addr += PAGE_SIZE;
+	}
 
-	set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL));
-	(*frames)++;
 	return 0;
 }
 
-static int unmap_pte_fn(pte_t *pte, struct page *pmd_page,
-			unsigned long addr, void *data)
+int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
+			   unsigned long max_nr_gframes,
+			   grant_status_t **__shared)
 {
+	grant_status_t *shared = *__shared;
+	unsigned long addr;
+	unsigned long i;
+
+	if (shared == NULL)
+		*__shared = shared = gnttab_status_vm_area.area->addr;
+
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, gnttab_status_vm_area.ptes[i],
+			   mfn_pte(frames[i], PAGE_KERNEL));
+		addr += PAGE_SIZE;
+	}
 
-	set_pte_at(&init_mm, addr, pte, __pte(0));
 	return 0;
 }
 
-int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
-			   unsigned long max_nr_gframes,
-			   void **__shared)
+void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
 {
-	int rc;
-	void *shared = *__shared;
+	pte_t **ptes;
+	unsigned long addr;
+	unsigned long i;
 
-	if (shared == NULL) {
-		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
-		BUG_ON(area == NULL);
-		shared = area->addr;
-		*__shared = shared;
-	}
+	if (shared == gnttab_status_vm_area.area->addr)
+		ptes = gnttab_status_vm_area.ptes;
+	else
+		ptes = gnttab_shared_vm_area.ptes;
 
-	rc = apply_to_page_range(&init_mm, (unsigned long)shared,
-				 PAGE_SIZE * nr_gframes,
-				 map_pte_fn, &frames);
-	return rc;
+	addr = (unsigned long)shared;
+
+	for (i = 0; i < nr_gframes; i++) {
+		set_pte_at(&init_mm, addr, ptes[i], __pte(0));
+		addr += PAGE_SIZE;
+	}
 }
 
-int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes,
-			   unsigned long max_nr_gframes,
-			   grant_status_t **__shared)
+static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
 {
-	int rc;
-	grant_status_t *shared = *__shared;
+	area->ptes = kmalloc(sizeof(pte_t *) * nr_frames, GFP_KERNEL);
+	if (area->ptes == NULL)
+		return -ENOMEM;
 
-	if (shared == NULL) {
-		/* No need to pass in PTE as we are going to do it
-		 * in apply_to_page_range anyhow. */
-		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
-		BUG_ON(area == NULL);
-		shared = area->addr;
-		*__shared = shared;
+	area->area = alloc_vm_area(PAGE_SIZE * nr_frames, area->ptes);
+	if (area->area == NULL) {
+		kfree(area->ptes);
+		return -ENOMEM;
 	}
 
-	rc = apply_to_page_range(&init_mm, (unsigned long)shared,
-				 PAGE_SIZE * nr_gframes,
-				 map_pte_fn_status, &frames);
-	return rc;
+	return 0;
 }
 
-void arch_gnttab_unmap(void *shared, unsigned long nr_gframes)
+static void arch_gnttab_vfree(struct gnttab_vm_area *area)
+{
+	free_vm_area(area->area);
+	kfree(area->ptes);
+}
+
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status)
 {
-	apply_to_page_range(&init_mm, (unsigned long)shared,
-			    PAGE_SIZE * nr_gframes, unmap_pte_fn, NULL);
+	int ret;
+
+	if (!xen_pv_domain())
+		return 0;
+
+	ret = arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Always allocate the space for the status frames in case
+	 * we're migrated to a host with V2 support.
+	 */
+	ret = arch_gnttab_valloc(&gnttab_status_vm_area, nr_status);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+  err:
+	arch_gnttab_vfree(&gnttab_shared_vm_area);
+	return -ENOMEM;
 }
+
 #ifdef CONFIG_XEN_PVH
 #include <xen/balloon.h>
 #include <xen/events.h>
-#include <xen/xen.h>
 #include <linux/slab.h>
 static int __init xlated_setup_gnttab_pages(void)
 {
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 821a11ada59..2e555163c2f 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -27,7 +27,6 @@
 #include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
 #include <xen/features.h>
-#include "mmu.h"
 #include "xen-ops.h"
 #include "vdso.h"
 
@@ -82,9 +81,6 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
 
 	memblock_reserve(start, size);
 
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return;
-
 	xen_max_p2m_pfn = PFN_DOWN(start + size);
 	for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
 		unsigned long mfn = pfn_to_mfn(pfn);
@@ -107,7 +103,6 @@ static unsigned long __init xen_do_chunk(unsigned long start,
 		.domid        = DOMID_SELF
 	};
 	unsigned long len = 0;
-	int xlated_phys = xen_feature(XENFEAT_auto_translated_physmap);
 	unsigned long pfn;
 	int ret;
 
@@ -121,7 +116,7 @@ static unsigned long __init xen_do_chunk(unsigned long start,
 				continue;
 			frame = mfn;
 		} else {
-			if (!xlated_phys && mfn != INVALID_P2M_ENTRY)
+			if (mfn != INVALID_P2M_ENTRY)
 				continue;
 			frame = pfn;
 		}
@@ -159,13 +154,6 @@ static unsigned long __init xen_do_chunk(unsigned long start,
 static unsigned long __init xen_release_chunk(unsigned long start,
 					      unsigned long end)
 {
-	/*
-	 * Xen already ballooned out the E820 non RAM regions for us
-	 * and set them up properly in EPT.
-	 */
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return end - start;
-
 	return xen_do_chunk(start, end, true);
 }
 
@@ -234,13 +222,7 @@ static void __init xen_set_identity_and_release_chunk(
 	 * (except for the ISA region which must be 1:1 mapped) to
 	 * release the refcounts (in Xen) on the original frames.
 	 */
-
-	/*
-	 * PVH E820 matches the hypervisor's P2M which means we need to
-	 * account for the proper values of *release and *identity.
-	 */
-	for (pfn = start_pfn; !xen_feature(XENFEAT_auto_translated_physmap) &&
-	     pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
+	for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
 		pte_t pte = __pte_ma(0);
 
 		if (pfn < PFN_UP(ISA_END_ADDRESS))
@@ -518,6 +500,35 @@ char * __init xen_memory_setup(void)
 }
 
 /*
+ * Machine specific memory setup for auto-translated guests.
+ */
+char * __init xen_auto_xlated_memory_setup(void)
+{
+	static struct e820entry map[E820MAX] __initdata;
+
+	struct xen_memory_map memmap;
+	int i;
+	int rc;
+
+	memmap.nr_entries = E820MAX;
+	set_xen_guest_handle(memmap.buffer, map);
+
+	rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap);
+	if (rc < 0)
+		panic("No memory map (%d)\n", rc);
+
+	sanitize_e820_map(map, ARRAY_SIZE(map), &memmap.nr_entries);
+
+	for (i = 0; i < memmap.nr_entries; i++)
+		e820_add_region(map[i].addr, map[i].size, map[i].type);
+
+	memblock_reserve(__pa(xen_start_info->mfn_list),
+			 xen_start_info->pt_base - xen_start_info->mfn_list);
+
+	return "Xen";
+}
+
+/*
  * Set the bit indicating "nosegneg" library variants should be used.
  * We only need to bother in pure 32-bit mode; compat 32-bit processes
  * can have un-truncated segments, so wrapping around is allowed.
@@ -590,13 +601,7 @@ void xen_enable_syscall(void)
 	}
 #endif /* CONFIG_X86_64 */
 }
-void xen_enable_nmi(void)
-{
-#ifdef CONFIG_X86_64
-	if (register_callback(CALLBACKTYPE_nmi, (char *)nmi))
-		BUG();
-#endif
-}
+
 void __init xen_pvmmu_arch_setup(void)
 {
 	HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
@@ -611,7 +616,6 @@ void __init xen_pvmmu_arch_setup(void)
 
 	xen_enable_sysenter();
 	xen_enable_syscall();
-	xen_enable_nmi();
 }
 
 /* This function is not called for HVM domains */
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index c834d4b231f..28c7e0be56e 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -36,6 +36,7 @@ void xen_mm_unpin_all(void);
 void xen_set_pat(u64);
 
 char * __init xen_memory_setup(void);
+char * xen_auto_xlated_memory_setup(void);
 void __init xen_arch_setup(void);
 void xen_enable_sysenter(void);
 void xen_enable_syscall(void);
@@ -104,6 +105,14 @@ static inline void __init xen_init_apic(void)
 }
 #endif
 
+#ifdef CONFIG_XEN_EFI
+extern void xen_efi_init(void);
+#else
+static inline void __init xen_efi_init(void)
+{
+}
+#endif
+
 /* Declare an asm function, along with symbols needed to make it
    inlineable */
 #define DECL_ASM(ret, name, ...)		\
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index abb59708a3b..b61bdf0eea2 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -182,6 +182,7 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)		(task_pt_regs(tsk)->areg[1])
 
 #define cpu_relax()  barrier()
+#define cpu_relax_lowlatency() cpu_relax()
 
 /* Special register access. */
 
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index f9e1ec346e3..8453e6e3989 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -376,38 +376,42 @@ _DoubleExceptionVector_WindowOverflow:
 	beqz	a2, 1f		# if at start of vector, don't restore
 
 	addi	a0, a0, -128
-	bbsi	a0, 8, 1f	# don't restore except for overflow 8 and 12
-	bbsi	a0, 7, 2f
+	bbsi.l	a0, 8, 1f	# don't restore except for overflow 8 and 12
+
+	/*
+	 * This fixup handler is for the extremely unlikely case where the
+	 * overflow handler's reference thru a0 gets a hardware TLB refill
+	 * that bumps out the (distinct, aliasing) TLB entry that mapped its
+	 * prior references thru a9/a13, and where our reference now thru
+	 * a9/a13 gets a 2nd-level miss exception (not hardware TLB refill).
+	 */
+	movi	a2, window_overflow_restore_a0_fixup
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+
+	bbsi.l	a0, 7, 2f
 
 	/*
 	 * Restore a0 as saved by _WindowOverflow8().
-	 *
-	 * FIXME:  we really need a fixup handler for this L32E,
-	 * for the extremely unlikely case where the overflow handler's
-	 * reference thru a0 gets a hardware TLB refill that bumps out
-	 * the (distinct, aliasing) TLB entry that mapped its prior
-	 * references thru a9, and where our reference now thru a9
-	 * gets a 2nd-level miss exception (not hardware TLB refill).
 	 */
 
-	l32e	a2, a9, -16
-	wsr	a2, depc	# replace the saved a0
-	j	1f
+	l32e	a0, a9, -16
+	wsr	a0, depc	# replace the saved a0
+	j	3f
 
 2:
 	/*
 	 * Restore a0 as saved by _WindowOverflow12().
-	 *
-	 * FIXME:  we really need a fixup handler for this L32E,
-	 * for the extremely unlikely case where the overflow handler's
-	 * reference thru a0 gets a hardware TLB refill that bumps out
-	 * the (distinct, aliasing) TLB entry that mapped its prior
-	 * references thru a13, and where our reference now thru a13
-	 * gets a 2nd-level miss exception (not hardware TLB refill).
 	 */
 
-	l32e	a2, a13, -16
-	wsr	a2, depc	# replace the saved a0
+	l32e	a0, a13, -16
+	wsr	a0, depc	# replace the saved a0
+3:
+	xsr	a3, excsave1
+	movi	a0, 0
+	s32i	a0, a3, EXC_TABLE_FIXUP
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
 1:
 	/*
 	 * Restore WindowBase while leaving all address registers restored.
@@ -449,6 +453,7 @@ _DoubleExceptionVector_WindowOverflow:
 
 	s32i	a0, a2, PT_DEPC
 
+_DoubleExceptionVector_handle_exception:
 	addx4	a0, a0, a3
 	l32i	a0, a0, EXC_TABLE_FAST_USER
 	xsr	a3, excsave1
@@ -464,11 +469,120 @@ _DoubleExceptionVector_WindowOverflow:
 	rotw	-3
 	j	1b
 
-	.end literal_prefix
 
 ENDPROC(_DoubleExceptionVector)
 
 /*
+ * Fixup handler for TLB miss in double exception handler for window owerflow.
+ * We get here with windowbase set to the window that was being spilled and
+ * a0 trashed. a0 bit 7 determines if this is a call8 (bit clear) or call12
+ * (bit set) window.
+ *
+ * We do the following here:
+ * - go to the original window retaining a0 value;
+ * - set up exception stack to return back to appropriate a0 restore code
+ *   (we'll need to rotate window back and there's no place to save this
+ *    information, use different return address for that);
+ * - handle the exception;
+ * - go to the window that was being spilled;
+ * - set up window_overflow_restore_a0_fixup as a fixup routine;
+ * - reload a0;
+ * - restore the original window;
+ * - reset the default fixup routine;
+ * - return to user. By the time we get to this fixup handler all information
+ *   about the conditions of the original double exception that happened in
+ *   the window overflow handler is lost, so we just return to userspace to
+ *   retry overflow from start.
+ *
+ * a0: value of depc, original value in depc
+ * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
+ * a3: exctable, original value in excsave1
+ */
+
+ENTRY(window_overflow_restore_a0_fixup)
+
+	rsr	a0, ps
+	extui	a0, a0, PS_OWB_SHIFT, PS_OWB_WIDTH
+	rsr	a2, windowbase
+	sub	a0, a2, a0
+	extui	a0, a0, 0, 3
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+
+	_beqi	a0, 1, .Lhandle_1
+	_beqi	a0, 3, .Lhandle_3
+
+	.macro	overflow_fixup_handle_exception_pane n
+
+	rsr	a0, depc
+	rotw	-\n
+
+	xsr	a3, excsave1
+	wsr	a2, depc
+	l32i	a2, a3, EXC_TABLE_KSTK
+	s32i	a0, a2, PT_AREG0
+
+	movi	a0, .Lrestore_\n
+	s32i	a0, a2, PT_DEPC
+	rsr	a0, exccause
+	j	_DoubleExceptionVector_handle_exception
+
+	.endm
+
+	overflow_fixup_handle_exception_pane 2
+.Lhandle_1:
+	overflow_fixup_handle_exception_pane 1
+.Lhandle_3:
+	overflow_fixup_handle_exception_pane 3
+
+	.macro	overflow_fixup_restore_a0_pane n
+
+	rotw	\n
+	/* Need to preserve a0 value here to be able to handle exception
+	 * that may occur on a0 reload from stack. It may occur because
+	 * TLB miss handler may not be atomic and pointer to page table
+	 * may be lost before we get here. There are no free registers,
+	 * so we need to use EXC_TABLE_DOUBLE_SAVE area.
+	 */
+	xsr	a3, excsave1
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	movi	a2, window_overflow_restore_a0_fixup
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+	bbsi.l	a0, 7, 1f
+	l32e	a0, a9, -16
+	j	2f
+1:
+	l32e	a0, a13, -16
+2:
+	rotw	-\n
+
+	.endm
+
+.Lrestore_2:
+	overflow_fixup_restore_a0_pane 2
+
+.Lset_default_fixup:
+	xsr	a3, excsave1
+	s32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	movi	a2, 0
+	s32i	a2, a3, EXC_TABLE_FIXUP
+	l32i	a2, a3, EXC_TABLE_DOUBLE_SAVE
+	xsr	a3, excsave1
+	rfe
+
+.Lrestore_1:
+	overflow_fixup_restore_a0_pane 1
+	j	.Lset_default_fixup
+.Lrestore_3:
+	overflow_fixup_restore_a0_pane 3
+	j	.Lset_default_fixup
+
+ENDPROC(window_overflow_restore_a0_fixup)
+
+	.end literal_prefix
+/*
  * Debug interrupt vector
  *
  * There is not much space here, so simply jump to another handler.
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index ee32c0085df..d16db6df86f 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -269,13 +269,13 @@ SECTIONS
 		  .UserExceptionVector.literal)
   SECTION_VECTOR (_DoubleExceptionVector_literal,
 		  .DoubleExceptionVector.literal,
-		  DOUBLEEXC_VECTOR_VADDR - 16,
+		  DOUBLEEXC_VECTOR_VADDR - 40,
 		  SIZEOF(.UserExceptionVector.text),
 		  .UserExceptionVector.text)
   SECTION_VECTOR (_DoubleExceptionVector_text,
 		  .DoubleExceptionVector.text,
 		  DOUBLEEXC_VECTOR_VADDR,
-		  32,
+		  40,
 		  .DoubleExceptionVector.literal)
 
   . = (LOADADDR( .DoubleExceptionVector.text ) + SIZEOF( .DoubleExceptionVector.text ) + 3) & ~ 3;
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 4224256bb21..77ed20209ca 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -191,7 +191,7 @@ int __init mem_reserve(unsigned long start, unsigned long end, int must_exist)
 		return -EINVAL;
 	}
 
-	if (it && start - it->start < bank_sz) {
+	if (it && start - it->start <= bank_sz) {
 		if (start == it->start) {
 			if (end - it->start < bank_sz) {
 				it->start = end;
diff --git a/block/bio.c b/block/bio.c
index 96d28eee8a1..0ec61c9e536 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -746,6 +746,14 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 
 			goto done;
 		}
+
+		/*
+		 * If the queue doesn't support SG gaps and adding this
+		 * offset would create a gap, disallow it.
+		 */
+		if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) &&
+		    bvec_gap_to_prev(prev, offset))
+			return 0;
 	}
 
 	if (bio->bi_vcnt >= bio->bi_max_vecs)
@@ -849,7 +857,13 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
 		 unsigned int offset)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q));
+	unsigned int max_sectors;
+
+	max_sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
+	if ((max_sectors < (len >> 9)) && !bio->bi_iter.bi_size)
+		max_sectors = len >> 9;
+
+	return __bio_add_page(q, bio, page, len, offset, max_sectors);
 }
 EXPORT_SYMBOL(bio_add_page);
 
@@ -1971,7 +1985,7 @@ int bio_associate_current(struct bio *bio)
 	/* associate blkcg if exists */
 	rcu_read_lock();
 	css = task_css(current, blkio_cgrp_id);
-	if (css && css_tryget(css))
+	if (css && css_tryget_online(css))
 		bio->bi_css = css;
 	rcu_read_unlock();
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1039fb9ff5f..e17da947f6b 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -80,7 +80,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	blkg->q = q;
 	INIT_LIST_HEAD(&blkg->q_node);
 	blkg->blkcg = blkcg;
-	blkg->refcnt = 1;
+	atomic_set(&blkg->refcnt, 1);
 
 	/* root blkg uses @q->root_rl, init rl only for !root blkgs */
 	if (blkcg != &blkcg_root) {
@@ -185,7 +185,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 	lockdep_assert_held(q->queue_lock);
 
 	/* blkg holds a reference to blkcg */
-	if (!css_tryget(&blkcg->css)) {
+	if (!css_tryget_online(&blkcg->css)) {
 		ret = -EINVAL;
 		goto err_free_blkg;
 	}
@@ -399,11 +399,8 @@ void __blkg_release_rcu(struct rcu_head *rcu_head)
 
 	/* release the blkcg and parent blkg refs this blkg has been holding */
 	css_put(&blkg->blkcg->css);
-	if (blkg->parent) {
-		spin_lock_irq(blkg->q->queue_lock);
+	if (blkg->parent)
 		blkg_put(blkg->parent);
-		spin_unlock_irq(blkg->q->queue_lock);
-	}
 
 	blkg_free(blkg);
 }
@@ -875,6 +872,13 @@ void blkcg_drain_queue(struct request_queue *q)
 {
 	lockdep_assert_held(q->queue_lock);
 
+	/*
+	 * @q could be exiting and already have destroyed all blkgs as
+	 * indicated by NULL root_blkg.  If so, don't confuse policies.
+	 */
+	if (!q->root_blkg)
+		return;
+
 	blk_throtl_drain(q);
 }
 
@@ -924,7 +928,15 @@ struct cgroup_subsys blkio_cgrp_subsys = {
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
-	.base_cftypes = blkcg_files,
+	.legacy_cftypes = blkcg_files,
+#ifdef CONFIG_MEMCG
+	/*
+	 * This ensures that, if available, memcg is automatically enabled
+	 * together on the default hierarchy so that the owner cgroup can
+	 * be retrieved from writeback pages.
+	 */
+	.depends_on = 1 << memory_cgrp_id,
+#endif
 };
 EXPORT_SYMBOL_GPL(blkio_cgrp_subsys);
 
@@ -1116,7 +1128,8 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 
 	/* everything is in place, add intf files for the new policy */
 	if (pol->cftypes)
-		WARN_ON(cgroup_add_cftypes(&blkio_cgrp_subsys, pol->cftypes));
+		WARN_ON(cgroup_add_legacy_cftypes(&blkio_cgrp_subsys,
+						  pol->cftypes));
 	ret = 0;
 out_unlock:
 	mutex_unlock(&blkcg_pol_mutex);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 371fe8e92ab..d3fd7aa3d2a 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -18,6 +18,7 @@
 #include <linux/seq_file.h>
 #include <linux/radix-tree.h>
 #include <linux/blkdev.h>
+#include <linux/atomic.h>
 
 /* Max limits for throttle policy */
 #define THROTL_IOPS_MAX		UINT_MAX
@@ -104,7 +105,7 @@ struct blkcg_gq {
 	struct request_list		rl;
 
 	/* reference count */
-	int				refcnt;
+	atomic_t			refcnt;
 
 	/* is this blkg online? protected by both blkcg and q locks */
 	bool				online;
@@ -204,7 +205,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
  */
 static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
 {
-	return css_to_blkcg(css_parent(&blkcg->css));
+	return css_to_blkcg(blkcg->css.parent);
 }
 
 /**
@@ -257,13 +258,12 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
  * blkg_get - get a blkg reference
  * @blkg: blkg to get
  *
- * The caller should be holding queue_lock and an existing reference.
+ * The caller should be holding an existing reference.
  */
 static inline void blkg_get(struct blkcg_gq *blkg)
 {
-	lockdep_assert_held(blkg->q->queue_lock);
-	WARN_ON_ONCE(!blkg->refcnt);
-	blkg->refcnt++;
+	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
+	atomic_inc(&blkg->refcnt);
 }
 
 void __blkg_release_rcu(struct rcu_head *rcu);
@@ -271,14 +271,11 @@ void __blkg_release_rcu(struct rcu_head *rcu);
 /**
  * blkg_put - put a blkg reference
  * @blkg: blkg to put
- *
- * The caller should be holding queue_lock.
  */
 static inline void blkg_put(struct blkcg_gq *blkg)
 {
-	lockdep_assert_held(blkg->q->queue_lock);
-	WARN_ON_ONCE(blkg->refcnt <= 0);
-	if (!--blkg->refcnt)
+	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
+	if (atomic_dec_and_test(&blkg->refcnt))
 		call_rcu(&blkg->rcu_head, __blkg_release_rcu);
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 40d654861c3..6f8dba161bf 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -43,6 +43,7 @@
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_split);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
 
 DEFINE_IDA(blk_queue_ida);
@@ -1218,6 +1219,8 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 	if (unlikely(!rq))
 		return ERR_PTR(-ENOMEM);
 
+	blk_rq_set_block_pc(rq);
+
 	for_each_bio(bio) {
 		struct bio *bounce_bio = bio;
 		int ret;
@@ -1235,6 +1238,22 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 EXPORT_SYMBOL(blk_make_request);
 
 /**
+ * blk_rq_set_block_pc - initialize a requeest to type BLOCK_PC
+ * @rq:		request to be initialized
+ *
+ */
+void blk_rq_set_block_pc(struct request *rq)
+{
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
+	memset(rq->__cmd, 0, sizeof(rq->__cmd));
+	rq->cmd = rq->__cmd;
+}
+EXPORT_SYMBOL(blk_rq_set_block_pc);
+
+/**
  * blk_requeue_request - put a request back on queue
  * @q:		request queue where request should be inserted
  * @rq:		request to be inserted
@@ -3293,8 +3312,7 @@ int __init blk_dev_init(void)
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
-					    WQ_MEM_RECLAIM | WQ_HIGHPRI |
-					    WQ_POWER_EFFICIENT, 0);
+					    WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
 	if (!kblockd_workqueue)
 		panic("Failed to create kblockd\n");
 
diff --git a/block/blk-exec.c b/block/blk-exec.c
index dbf4502b1d6..f4d27b12c90 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -132,6 +132,11 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 	if (rq->errors)
 		err = -EIO;
 
+	if (rq->sense == sense)	{
+		rq->sense = NULL;
+		rq->sense_len = 0;
+	}
+
 	return err;
 }
 EXPORT_SYMBOL(blk_execute_rq);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 8ffee4b5f93..3cb5e9e7108 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -422,44 +422,6 @@ void blk_insert_flush(struct request *rq)
 }
 
 /**
- * blk_abort_flushes - @q is being aborted, abort flush requests
- * @q: request_queue being aborted
- *
- * To be called from elv_abort_queue().  @q is being aborted.  Prepare all
- * FLUSH/FUA requests for abortion.
- *
- * CONTEXT:
- * spin_lock_irq(q->queue_lock)
- */
-void blk_abort_flushes(struct request_queue *q)
-{
-	struct request *rq, *n;
-	int i;
-
-	/*
-	 * Requests in flight for data are already owned by the dispatch
-	 * queue or the device driver.  Just restore for normal completion.
-	 */
-	list_for_each_entry_safe(rq, n, &q->flush_data_in_flight, flush.list) {
-		list_del_init(&rq->flush.list);
-		blk_flush_restore_request(rq);
-	}
-
-	/*
-	 * We need to give away requests on flush queues.  Restore for
-	 * normal completion and put them on the dispatch queue.
-	 */
-	for (i = 0; i < ARRAY_SIZE(q->flush_queue); i++) {
-		list_for_each_entry_safe(rq, n, &q->flush_queue[i],
-					 flush.list) {
-			list_del_init(&rq->flush.list);
-			blk_flush_restore_request(rq);
-			list_add_tail(&rq->queuelist, &q->queue_head);
-		}
-	}
-}
-
-/**
  * blkdev_issue_flush - queue a flush
  * @bdev:	blockdev to issue flush for
  * @gfp_mask:	memory allocation flags (for bio_alloc)
diff --git a/block/blk-merge.c b/block/blk-merge.c
index b3bf0df0f4c..54535831f1e 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -568,6 +568,8 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 {
+	struct request_queue *q = rq->q;
+
 	if (!rq_mergeable(rq) || !bio_mergeable(bio))
 		return false;
 
@@ -591,6 +593,14 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	    !blk_write_same_mergeable(rq->bio, bio))
 		return false;
 
+	if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) {
+		struct bio_vec *bprev;
+
+		bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1];
+		if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset))
+			return false;
+	}
+
 	return true;
 }
 
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 1aab39f71d9..c1b92426c95 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -43,9 +43,16 @@ bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
 	return bt_has_free_tags(&tags->bitmap_tags);
 }
 
-static inline void bt_index_inc(unsigned int *index)
+static inline int bt_index_inc(int index)
 {
-	*index = (*index + 1) & (BT_WAIT_QUEUES - 1);
+	return (index + 1) & (BT_WAIT_QUEUES - 1);
+}
+
+static inline void bt_index_atomic_inc(atomic_t *index)
+{
+	int old = atomic_read(index);
+	int new = bt_index_inc(old);
+	atomic_cmpxchg(index, old, new);
 }
 
 /*
@@ -69,14 +76,14 @@ static void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags)
 	int i, wake_index;
 
 	bt = &tags->bitmap_tags;
-	wake_index = bt->wake_index;
+	wake_index = atomic_read(&bt->wake_index);
 	for (i = 0; i < BT_WAIT_QUEUES; i++) {
 		struct bt_wait_state *bs = &bt->bs[wake_index];
 
 		if (waitqueue_active(&bs->wait))
 			wake_up(&bs->wait);
 
-		bt_index_inc(&wake_index);
+		wake_index = bt_index_inc(wake_index);
 	}
 }
 
@@ -212,12 +219,14 @@ static struct bt_wait_state *bt_wait_ptr(struct blk_mq_bitmap_tags *bt,
 					 struct blk_mq_hw_ctx *hctx)
 {
 	struct bt_wait_state *bs;
+	int wait_index;
 
 	if (!hctx)
 		return &bt->bs[0];
 
-	bs = &bt->bs[hctx->wait_index];
-	bt_index_inc(&hctx->wait_index);
+	wait_index = atomic_read(&hctx->wait_index);
+	bs = &bt->bs[wait_index];
+	bt_index_atomic_inc(&hctx->wait_index);
 	return bs;
 }
 
@@ -239,18 +248,12 @@ static int bt_get(struct blk_mq_alloc_data *data,
 
 	bs = bt_wait_ptr(bt, hctx);
 	do {
-		bool was_empty;
-
-		was_empty = list_empty(&wait.task_list);
 		prepare_to_wait(&bs->wait, &wait, TASK_UNINTERRUPTIBLE);
 
 		tag = __bt_get(hctx, bt, last_tag);
 		if (tag != -1)
 			break;
 
-		if (was_empty)
-			atomic_set(&bs->wait_cnt, bt->wake_cnt);
-
 		blk_mq_put_ctx(data->ctx);
 
 		io_schedule();
@@ -313,18 +316,19 @@ static struct bt_wait_state *bt_wake_ptr(struct blk_mq_bitmap_tags *bt)
 {
 	int i, wake_index;
 
-	wake_index = bt->wake_index;
+	wake_index = atomic_read(&bt->wake_index);
 	for (i = 0; i < BT_WAIT_QUEUES; i++) {
 		struct bt_wait_state *bs = &bt->bs[wake_index];
 
 		if (waitqueue_active(&bs->wait)) {
-			if (wake_index != bt->wake_index)
-				bt->wake_index = wake_index;
+			int o = atomic_read(&bt->wake_index);
+			if (wake_index != o)
+				atomic_cmpxchg(&bt->wake_index, o, wake_index);
 
 			return bs;
 		}
 
-		bt_index_inc(&wake_index);
+		wake_index = bt_index_inc(wake_index);
 	}
 
 	return NULL;
@@ -334,6 +338,7 @@ static void bt_clear_tag(struct blk_mq_bitmap_tags *bt, unsigned int tag)
 {
 	const int index = TAG_TO_INDEX(bt, tag);
 	struct bt_wait_state *bs;
+	int wait_cnt;
 
 	/*
 	 * The unlock memory barrier need to order access to req in free
@@ -342,10 +347,19 @@ static void bt_clear_tag(struct blk_mq_bitmap_tags *bt, unsigned int tag)
 	clear_bit_unlock(TAG_TO_BIT(bt, tag), &bt->map[index].word);
 
 	bs = bt_wake_ptr(bt);
-	if (bs && atomic_dec_and_test(&bs->wait_cnt)) {
-		atomic_set(&bs->wait_cnt, bt->wake_cnt);
-		bt_index_inc(&bt->wake_index);
+	if (!bs)
+		return;
+
+	wait_cnt = atomic_dec_return(&bs->wait_cnt);
+	if (wait_cnt == 0) {
+wake:
+		atomic_add(bt->wake_cnt, &bs->wait_cnt);
+		bt_index_atomic_inc(&bt->wake_index);
 		wake_up(&bs->wait);
+	} else if (wait_cnt < 0) {
+		wait_cnt = atomic_inc_return(&bs->wait_cnt);
+		if (!wait_cnt)
+			goto wake;
 	}
 }
 
@@ -499,10 +513,13 @@ static int bt_alloc(struct blk_mq_bitmap_tags *bt, unsigned int depth,
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < BT_WAIT_QUEUES; i++)
+	bt_update_count(bt, depth);
+
+	for (i = 0; i < BT_WAIT_QUEUES; i++) {
 		init_waitqueue_head(&bt->bs[i].wait);
+		atomic_set(&bt->bs[i].wait_cnt, bt->wake_cnt);
+	}
 
-	bt_update_count(bt, depth);
 	return 0;
 }
 
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 98696a65d4d..6206ed17ef7 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -24,7 +24,7 @@ struct blk_mq_bitmap_tags {
 	unsigned int map_nr;
 	struct blk_align_bitmap *map;
 
-	unsigned int wake_index;
+	atomic_t wake_index;
 	struct bt_wait_state *bs;
 };
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4e4cd620805..ad69ef657e8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -82,8 +82,10 @@ static int blk_mq_queue_enter(struct request_queue *q)
 
 	__percpu_counter_add(&q->mq_usage_counter, 1, 1000000);
 	smp_wmb();
-	/* we have problems to freeze the queue if it's initializing */
-	if (!blk_queue_bypass(q) || !blk_queue_init_done(q))
+
+	/* we have problems freezing the queue if it's initializing */
+	if (!blk_queue_dying(q) &&
+	    (!blk_queue_bypass(q) || !blk_queue_init_done(q)))
 		return 0;
 
 	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);
@@ -107,7 +109,7 @@ static void blk_mq_queue_exit(struct request_queue *q)
 	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);
 }
 
-static void __blk_mq_drain_queue(struct request_queue *q)
+void blk_mq_drain_queue(struct request_queue *q)
 {
 	while (true) {
 		s64 count;
@@ -118,7 +120,7 @@ static void __blk_mq_drain_queue(struct request_queue *q)
 
 		if (count == 0)
 			break;
-		blk_mq_run_queues(q, false);
+		blk_mq_start_hw_queues(q);
 		msleep(10);
 	}
 }
@@ -137,12 +139,7 @@ static void blk_mq_freeze_queue(struct request_queue *q)
 	spin_unlock_irq(q->queue_lock);
 
 	if (drain)
-		__blk_mq_drain_queue(q);
-}
-
-void blk_mq_drain_queue(struct request_queue *q)
-{
-	__blk_mq_drain_queue(q);
+		blk_mq_drain_queue(q);
 }
 
 static void blk_mq_unfreeze_queue(struct request_queue *q)
@@ -183,6 +180,7 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->rq_disk = NULL;
 	rq->part = NULL;
+	rq->start_time = jiffies;
 #ifdef CONFIG_BLK_CGROUP
 	rq->rl = NULL;
 	set_start_time_ns(rq);
@@ -202,6 +200,8 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->sense = NULL;
 
 	INIT_LIST_HEAD(&rq->timeout_list);
+	rq->timeout = 0;
+
 	rq->end_io = NULL;
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
@@ -406,16 +406,7 @@ static void blk_mq_start_request(struct request *rq, bool last)
 	if (unlikely(blk_bidi_rq(rq)))
 		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
 
-	/*
-	 * Just mark start time and set the started bit. Due to memory
-	 * ordering, we know we'll see the correct deadline as long as
-	 * REQ_ATOMIC_STARTED is seen. Use the default queue timeout,
-	 * unless one has been set in the request.
-	 */
-	if (!rq->timeout)
-		rq->deadline = jiffies + q->rq_timeout;
-	else
-		rq->deadline = jiffies + rq->timeout;
+	blk_add_timer(rq);
 
 	/*
 	 * Mark us as started and clear complete. Complete might have been
@@ -887,7 +878,7 @@ void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx)
 	clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
 
 	preempt_disable();
-	__blk_mq_run_hw_queue(hctx);
+	blk_mq_run_hw_queue(hctx, false);
 	preempt_enable();
 }
 EXPORT_SYMBOL(blk_mq_start_hw_queue);
@@ -967,11 +958,6 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 		list_add_tail(&rq->queuelist, &ctx->rq_list);
 
 	blk_mq_hctx_mark_pending(hctx, ctx);
-
-	/*
-	 * We do this early, to ensure we are on the right CPU.
-	 */
-	blk_add_timer(rq);
 }
 
 void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
@@ -1100,10 +1086,8 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
 {
 	init_request_from_bio(rq, bio);
 
-	if (blk_do_io_stat(rq)) {
-		rq->start_time = jiffies;
+	if (blk_do_io_stat(rq))
 		blk_account_io_start(rq, 1);
-	}
 }
 
 static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
@@ -1216,7 +1200,6 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_start_request(rq, true);
-		blk_add_timer(rq);
 
 		/*
 		 * For OK queue, we are done. For error, kill it. Any other
@@ -1967,13 +1950,19 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+/*
+ * Alloc a tag set to be associated with one or more request queues.
+ * May fail with EINVAL for various error conditions. May adjust the
+ * requested depth down, if if it too large. In that case, the set
+ * value will be stored in set->queue_depth.
+ */
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 {
 	int i;
 
 	if (!set->nr_hw_queues)
 		return -EINVAL;
-	if (!set->queue_depth || set->queue_depth > BLK_MQ_MAX_DEPTH)
+	if (!set->queue_depth)
 		return -EINVAL;
 	if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN)
 		return -EINVAL;
@@ -1981,6 +1970,11 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (!set->nr_hw_queues || !set->ops->queue_rq || !set->ops->map_queue)
 		return -EINVAL;
 
+	if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
+		pr_info("blk-mq: reduced tag depth to %u\n",
+			BLK_MQ_MAX_DEPTH);
+		set->queue_depth = BLK_MQ_MAX_DEPTH;
+	}
 
 	set->tags = kmalloc_node(set->nr_hw_queues *
 				 sizeof(struct blk_mq_tags *),
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5d21239bc85..f1a1795a568 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -113,6 +113,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
 	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
 	lim->discard_granularity = 0;
@@ -277,6 +278,26 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
 /**
+ * blk_queue_chunk_sectors - set size of the chunk for this queue
+ * @q:  the request queue for the device
+ * @chunk_sectors:  chunk sectors in the usual 512b unit
+ *
+ * Description:
+ *    If a driver doesn't want IOs to cross a given chunk size, it can set
+ *    this limit and prevent merging across chunks. Note that the chunk size
+ *    must currently be a power-of-2 in sectors. Also note that the block
+ *    layer must accept a page worth of data at any offset. So if the
+ *    crossing of chunks is a hard limitation in the driver, it must still be
+ *    prepared to split single page bios.
+ **/
+void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
+{
+	BUG_ON(!is_power_of_2(chunk_sectors));
+	q->limits.chunk_sectors = chunk_sectors;
+}
+EXPORT_SYMBOL(blk_queue_chunk_sectors);
+
+/**
  * blk_queue_max_discard_sectors - set max sectors for a single discard
  * @q:  the request queue for the device
  * @max_discard_sectors: maximum number of sectors to discard
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 3f33d867226..a185b86741e 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag)
 EXPORT_SYMBOL(blk_queue_find_tag);
 
 /**
- * __blk_free_tags - release a given set of tag maintenance info
+ * blk_free_tags - release a given set of tag maintenance info
  * @bqt:	the tag map to free
  *
- * Tries to free the specified @bqt.  Returns true if it was
- * actually freed and false if there are still references using it
+ * Drop the reference count on @bqt and frees it when the last reference
+ * is dropped.
  */
-static int __blk_free_tags(struct blk_queue_tag *bqt)
+void blk_free_tags(struct blk_queue_tag *bqt)
 {
-	int retval;
-
-	retval = atomic_dec_and_test(&bqt->refcnt);
-	if (retval) {
+	if (atomic_dec_and_test(&bqt->refcnt)) {
 		BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
 							bqt->max_depth);
 
@@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt)
 
 		kfree(bqt);
 	}
-
-	return retval;
 }
+EXPORT_SYMBOL(blk_free_tags);
 
 /**
  * __blk_queue_free_tags - release tag maintenance info
@@ -69,28 +65,13 @@ void __blk_queue_free_tags(struct request_queue *q)
 	if (!bqt)
 		return;
 
-	__blk_free_tags(bqt);
+	blk_free_tags(bqt);
 
 	q->queue_tags = NULL;
 	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
 }
 
 /**
- * blk_free_tags - release a given set of tag maintenance info
- * @bqt:	the tag map to free
- *
- * For externally managed @bqt frees the map.  Callers of this
- * function must guarantee to have released all the queues that
- * might have been using this tag map.
- */
-void blk_free_tags(struct blk_queue_tag *bqt)
-{
-	if (unlikely(!__blk_free_tags(bqt)))
-		BUG();
-}
-EXPORT_SYMBOL(blk_free_tags);
-
-/**
  * blk_queue_free_tags - release tag maintenance info
  * @q:  the request queue for the device
  *
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 9353b468335..9273d0969eb 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -412,13 +412,13 @@ static void throtl_pd_init(struct blkcg_gq *blkg)
 	int rw;
 
 	/*
-	 * If sane_hierarchy is enabled, we switch to properly hierarchical
+	 * If on the default hierarchy, we switch to properly hierarchical
 	 * behavior where limits on a given throtl_grp are applied to the
 	 * whole subtree rather than just the group itself.  e.g. If 16M
 	 * read_bps limit is set on the root group, the whole system can't
 	 * exceed 16M for the device.
 	 *
-	 * If sane_hierarchy is not enabled, the broken flat hierarchy
+	 * If not on the default hierarchy, the broken flat hierarchy
 	 * behavior is retained where all throtl_grps are treated as if
 	 * they're all separate root groups right below throtl_data.
 	 * Limits of a group don't interact with limits of other groups
@@ -426,7 +426,7 @@ static void throtl_pd_init(struct blkcg_gq *blkg)
 	 */
 	parent_sq = &td->service_queue;
 
-	if (cgroup_sane_behavior(blkg->blkcg->css.cgroup) && blkg->parent)
+	if (cgroup_on_dfl(blkg->blkcg->css.cgroup) && blkg->parent)
 		parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
 
 	throtl_service_queue_init(&tg->service_queue, parent_sq);
@@ -1346,10 +1346,10 @@ static int tg_print_conf_uint(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
-		       const char *buf, bool is_u64)
+static ssize_t tg_set_conf(struct kernfs_open_file *of,
+			   char *buf, size_t nbytes, loff_t off, bool is_u64)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct throtl_grp *tg;
 	struct throtl_service_queue *sq;
@@ -1368,9 +1368,9 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 		ctx.v = -1;
 
 	if (is_u64)
-		*(u64 *)((void *)tg + cft->private) = ctx.v;
+		*(u64 *)((void *)tg + of_cft(of)->private) = ctx.v;
 	else
-		*(unsigned int *)((void *)tg + cft->private) = ctx.v;
+		*(unsigned int *)((void *)tg + of_cft(of)->private) = ctx.v;
 
 	throtl_log(&tg->service_queue,
 		   "limit change rbps=%llu wbps=%llu riops=%u wiops=%u",
@@ -1404,19 +1404,19 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 	}
 
 	blkg_conf_finish(&ctx);
-	return 0;
+	return nbytes;
 }
 
-static int tg_set_conf_u64(struct cgroup_subsys_state *css, struct cftype *cft,
-			   char *buf)
+static ssize_t tg_set_conf_u64(struct kernfs_open_file *of,
+			       char *buf, size_t nbytes, loff_t off)
 {
-	return tg_set_conf(css, cft, buf, true);
+	return tg_set_conf(of, buf, nbytes, off, true);
 }
 
-static int tg_set_conf_uint(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buf)
+static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
-	return tg_set_conf(css, cft, buf, false);
+	return tg_set_conf(of, buf, nbytes, off, false);
 }
 
 static struct cftype throtl_files[] = {
@@ -1424,25 +1424,25 @@ static struct cftype throtl_files[] = {
 		.name = "throttle.read_bps_device",
 		.private = offsetof(struct throtl_grp, bps[READ]),
 		.seq_show = tg_print_conf_u64,
-		.write_string = tg_set_conf_u64,
+		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.write_bps_device",
 		.private = offsetof(struct throtl_grp, bps[WRITE]),
 		.seq_show = tg_print_conf_u64,
-		.write_string = tg_set_conf_u64,
+		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.read_iops_device",
 		.private = offsetof(struct throtl_grp, iops[READ]),
 		.seq_show = tg_print_conf_uint,
-		.write_string = tg_set_conf_uint,
+		.write = tg_set_conf_uint,
 	},
 	{
 		.name = "throttle.write_iops_device",
 		.private = offsetof(struct throtl_grp, iops[WRITE]),
 		.seq_show = tg_print_conf_uint,
-		.write_string = tg_set_conf_uint,
+		.write = tg_set_conf_uint,
 	},
 	{
 		.name = "throttle.io_service_bytes",
diff --git a/block/blk.h b/block/blk.h
index 45385e9abf6..6748c4f8d7a 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -84,7 +84,6 @@ static inline void blk_clear_rq_complete(struct request *rq)
 #define ELV_ON_HASH(rq) ((rq)->cmd_flags & REQ_HASHED)
 
 void blk_insert_flush(struct request *rq);
-void blk_abort_flushes(struct request_queue *q);
 
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
diff --git a/block/bsg.c b/block/bsg.c
index e5214c14809..ff46addde5d 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -196,7 +196,6 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 	 * fill in request structure
 	 */
 	rq->cmd_len = hdr->request_len;
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -273,6 +272,8 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 	rq = blk_get_request(q, rw, GFP_KERNEL);
 	if (!rq)
 		return ERR_PTR(-ENOMEM);
+	blk_rq_set_block_pc(rq);
+
 	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
 	if (ret)
 		goto out;
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 22dffebc7c7..cadc3784174 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1670,11 +1670,11 @@ static int cfq_print_leaf_weight(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
-				    struct cftype *cft, const char *buf,
-				    bool is_leaf_weight)
+static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of,
+					char *buf, size_t nbytes, loff_t off,
+					bool is_leaf_weight)
 {
-	struct blkcg *blkcg = css_to_blkcg(css);
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct cfq_group *cfqg;
 	int ret;
@@ -1697,19 +1697,19 @@ static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
 	}
 
 	blkg_conf_finish(&ctx);
-	return ret;
+	return ret ?: nbytes;
 }
 
-static int cfqg_set_weight_device(struct cgroup_subsys_state *css,
-				  struct cftype *cft, char *buf)
+static ssize_t cfqg_set_weight_device(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
 {
-	return __cfqg_set_weight_device(css, cft, buf, false);
+	return __cfqg_set_weight_device(of, buf, nbytes, off, false);
 }
 
-static int cfqg_set_leaf_weight_device(struct cgroup_subsys_state *css,
-				       struct cftype *cft, char *buf)
+static ssize_t cfqg_set_leaf_weight_device(struct kernfs_open_file *of,
+					   char *buf, size_t nbytes, loff_t off)
 {
-	return __cfqg_set_weight_device(css, cft, buf, true);
+	return __cfqg_set_weight_device(of, buf, nbytes, off, true);
 }
 
 static int __cfq_set_weight(struct cgroup_subsys_state *css, struct cftype *cft,
@@ -1837,7 +1837,7 @@ static struct cftype cfq_blkcg_files[] = {
 		.name = "weight_device",
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cfqg_print_leaf_weight_device,
-		.write_string = cfqg_set_leaf_weight_device,
+		.write = cfqg_set_leaf_weight_device,
 	},
 	{
 		.name = "weight",
@@ -1851,7 +1851,7 @@ static struct cftype cfq_blkcg_files[] = {
 		.name = "weight_device",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cfqg_print_weight_device,
-		.write_string = cfqg_set_weight_device,
+		.write = cfqg_set_weight_device,
 	},
 	{
 		.name = "weight",
@@ -1863,7 +1863,7 @@ static struct cftype cfq_blkcg_files[] = {
 	{
 		.name = "leaf_weight_device",
 		.seq_show = cfqg_print_leaf_weight_device,
-		.write_string = cfqg_set_leaf_weight_device,
+		.write = cfqg_set_leaf_weight_device,
 	},
 	{
 		.name = "leaf_weight",
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index fbd5a67cb77..a0926a6094b 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -690,6 +690,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKROSET:
 	case BLKDISCARD:
 	case BLKSECDISCARD:
+	case BLKZEROOUT:
 	/*
 	 * the ones below are implemented in blkdev_locked_ioctl,
 	 * but we call blkdev_ioctl, which gets the lock for us
diff --git a/block/elevator.c b/block/elevator.c
index 1e01b66a0b9..24c28b659bb 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -729,26 +729,6 @@ int elv_may_queue(struct request_queue *q, int rw)
 	return ELV_MQUEUE_MAY;
 }
 
-void elv_abort_queue(struct request_queue *q)
-{
-	struct request *rq;
-
-	blk_abort_flushes(q);
-
-	while (!list_empty(&q->queue_head)) {
-		rq = list_entry_rq(q->queue_head.next);
-		rq->cmd_flags |= REQ_QUIET;
-		trace_block_rq_abort(q, rq);
-		/*
-		 * Mark this request as started so we don't trigger
-		 * any debug logic in the end I/O path.
-		 */
-		blk_start_request(rq);
-		__blk_end_request_all(rq, -EIO);
-	}
-}
-EXPORT_SYMBOL(elv_abort_queue);
-
 void elv_completed_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 9c28a5b3804..14695c6221c 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -229,7 +229,6 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 	 * fill in request structure
 	 */
 	rq->cmd_len = hdr->cmd_len;
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -311,6 +310,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
 	if (!rq)
 		return -ENOMEM;
+	blk_rq_set_block_pc(rq);
 
 	if (blk_fill_sghdr_rq(q, rq, hdr, mode)) {
 		blk_put_request(rq);
@@ -491,7 +491,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	memset(sense, 0, sizeof(sense));
 	rq->sense = sense;
 	rq->sense_len = 0;
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	blk_rq_set_block_pc(rq);
 
 	blk_execute_rq(q, disk, rq, 0);
 
@@ -524,7 +524,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	int err;
 
 	rq = blk_get_request(q, WRITE, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	blk_rq_set_block_pc(rq);
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
 	rq->cmd[0] = cmd;
 	rq->cmd[4] = data;
diff --git a/crypto/Kconfig b/crypto/Kconfig
index ce4012a5878..6345c470650 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -23,7 +23,8 @@ comment "Crypto core or helper"
 
 config CRYPTO_FIPS
 	bool "FIPS 200 compliance"
-	depends on CRYPTO_ANSI_CPRNG && !CRYPTO_MANAGER_DISABLE_TESTS
+	depends on (CRYPTO_ANSI_CPRNG || CRYPTO_DRBG) && !CRYPTO_MANAGER_DISABLE_TESTS
+	depends on MODULE_SIG
 	help
 	  This options enables the fips boot option which is
 	  required if you want to system to operate in a FIPS 200
@@ -1019,6 +1020,19 @@ config CRYPTO_DES_SPARC64
 	  DES cipher algorithm (FIPS 46-2), and Triple DES EDE (FIPS 46-3),
 	  optimized using SPARC64 crypto opcodes.
 
+config CRYPTO_DES3_EDE_X86_64
+	tristate "Triple DES EDE cipher algorithm (x86-64)"
+	depends on X86 && 64BIT
+	select CRYPTO_ALGAPI
+	select CRYPTO_DES
+	help
+	  Triple DES EDE (FIPS 46-3) algorithm.
+
+	  This module provides implementation of the Triple DES EDE cipher
+	  algorithm that is optimized for x86-64 processors. Two versions of
+	  algorithm are provided; regular processing one input block and
+	  one that processes three blocks parallel.
+
 config CRYPTO_FCRYPT
 	tristate "FCrypt cipher algorithm"
 	select CRYPTO_ALGAPI
@@ -1380,6 +1394,40 @@ config CRYPTO_ANSI_CPRNG
 	  ANSI X9.31 A.2.4. Note that this option must be enabled if
 	  CRYPTO_FIPS is selected
 
+menuconfig CRYPTO_DRBG_MENU
+	tristate "NIST SP800-90A DRBG"
+	help
+	  NIST SP800-90A compliant DRBG. In the following submenu, one or
+	  more of the DRBG types must be selected.
+
+if CRYPTO_DRBG_MENU
+
+config CRYPTO_DRBG_HMAC
+	bool "Enable HMAC DRBG"
+	default y
+	select CRYPTO_HMAC
+	help
+	  Enable the HMAC DRBG variant as defined in NIST SP800-90A.
+
+config CRYPTO_DRBG_HASH
+	bool "Enable Hash DRBG"
+	select CRYPTO_HASH
+	help
+	  Enable the Hash DRBG variant as defined in NIST SP800-90A.
+
+config CRYPTO_DRBG_CTR
+	bool "Enable CTR DRBG"
+	select CRYPTO_AES
+	help
+	  Enable the CTR DRBG variant as defined in NIST SP800-90A.
+
+config CRYPTO_DRBG
+	tristate
+	default CRYPTO_DRBG_MENU if (CRYPTO_DRBG_HMAC || CRYPTO_DRBG_HASH || CRYPTO_DRBG_CTR)
+	select CRYPTO_RNG
+
+endif	# if CRYPTO_DRBG_MENU
+
 config CRYPTO_USER_API
 	tristate
 
diff --git a/crypto/Makefile b/crypto/Makefile
index 38e64231dcd..cfa57b3f5a4 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -92,6 +92,7 @@ obj-$(CONFIG_CRYPTO_842) += 842.o
 obj-$(CONFIG_CRYPTO_RNG2) += rng.o
 obj-$(CONFIG_CRYPTO_RNG2) += krng.o
 obj-$(CONFIG_CRYPTO_ANSI_CPRNG) += ansi_cprng.o
+obj-$(CONFIG_CRYPTO_DRBG) += drbg.o
 obj-$(CONFIG_CRYPTO_TEST) += tcrypt.o
 obj-$(CONFIG_CRYPTO_GHASH) += ghash-generic.o
 obj-$(CONFIG_CRYPTO_USER_API) += af_alg.o
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 966f893711b..6a3ad801158 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/net.h>
 #include <linux/rwsem.h>
+#include <linux/security.h>
 
 struct alg_type_list {
 	const struct af_alg_type *type;
@@ -243,6 +244,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 
 	sock_init_data(newsock, sk2);
 	sock_graft(sk2, newsock);
+	security_sk_clone(sk, sk2);
 
 	err = type->accept(ask->private, sk2);
 	if (err) {
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 7a1ae87f168..e8d3a7dca8c 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -41,8 +41,20 @@ static inline int crypto_set_driver_name(struct crypto_alg *alg)
 	return 0;
 }
 
+static inline void crypto_check_module_sig(struct module *mod)
+{
+#ifdef CONFIG_CRYPTO_FIPS
+	if (fips_enabled && mod && !mod->sig_ok)
+		panic("Module %s signature verification failed in FIPS mode\n",
+		      mod->name);
+#endif
+	return;
+}
+
 static int crypto_check_alg(struct crypto_alg *alg)
 {
+	crypto_check_module_sig(alg->cra_module);
+
 	if (alg->cra_alignmask & (alg->cra_alignmask + 1))
 		return -EINVAL;
 
@@ -430,6 +442,8 @@ int crypto_register_template(struct crypto_template *tmpl)
 
 	down_write(&crypto_alg_sem);
 
+	crypto_check_module_sig(tmpl->module);
+
 	list_for_each_entry(q, &crypto_template_list, list) {
 		if (q == tmpl)
 			goto out;
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 7bdd61b867c..e592c90abeb 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -233,7 +233,7 @@ static void cryptd_blkcipher_decrypt(struct crypto_async_request *req, int err)
 }
 
 static int cryptd_blkcipher_enqueue(struct ablkcipher_request *req,
-				    crypto_completion_t complete)
+				    crypto_completion_t compl)
 {
 	struct cryptd_blkcipher_request_ctx *rctx = ablkcipher_request_ctx(req);
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
@@ -241,7 +241,7 @@ static int cryptd_blkcipher_enqueue(struct ablkcipher_request *req,
 
 	queue = cryptd_get_queue(crypto_ablkcipher_tfm(tfm));
 	rctx->complete = req->base.complete;
-	req->base.complete = complete;
+	req->base.complete = compl;
 
 	return cryptd_enqueue_request(queue, &req->base);
 }
@@ -414,7 +414,7 @@ static int cryptd_hash_setkey(struct crypto_ahash *parent,
 }
 
 static int cryptd_hash_enqueue(struct ahash_request *req,
-				crypto_completion_t complete)
+				crypto_completion_t compl)
 {
 	struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
@@ -422,7 +422,7 @@ static int cryptd_hash_enqueue(struct ahash_request *req,
 		cryptd_get_queue(crypto_ahash_tfm(tfm));
 
 	rctx->complete = req->base.complete;
-	req->base.complete = complete;
+	req->base.complete = compl;
 
 	return cryptd_enqueue_request(queue, &req->base);
 }
@@ -667,14 +667,14 @@ static void cryptd_aead_decrypt(struct crypto_async_request *areq, int err)
 }
 
 static int cryptd_aead_enqueue(struct aead_request *req,
-				    crypto_completion_t complete)
+				    crypto_completion_t compl)
 {
 	struct cryptd_aead_request_ctx *rctx = aead_request_ctx(req);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct cryptd_queue *queue = cryptd_get_queue(crypto_aead_tfm(tfm));
 
 	rctx->complete = req->base.complete;
-	req->base.complete = complete;
+	req->base.complete = compl;
 	return cryptd_enqueue_request(queue, &req->base);
 }
 
diff --git a/crypto/des_generic.c b/crypto/des_generic.c
index f6cf63f8846..298d464ab7d 100644
--- a/crypto/des_generic.c
+++ b/crypto/des_generic.c
@@ -859,13 +859,10 @@ static void des_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
  *   property.
  *
  */
-static int des3_ede_setkey(struct crypto_tfm *tfm, const u8 *key,
-			   unsigned int keylen)
+int __des3_ede_setkey(u32 *expkey, u32 *flags, const u8 *key,
+		      unsigned int keylen)
 {
 	const u32 *K = (const u32 *)key;
-	struct des3_ede_ctx *dctx = crypto_tfm_ctx(tfm);
-	u32 *expkey = dctx->expkey;
-	u32 *flags = &tfm->crt_flags;
 
 	if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
 		     !((K[2] ^ K[4]) | (K[3] ^ K[5]))) &&
@@ -880,6 +877,17 @@ static int des3_ede_setkey(struct crypto_tfm *tfm, const u8 *key,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__des3_ede_setkey);
+
+static int des3_ede_setkey(struct crypto_tfm *tfm, const u8 *key,
+			   unsigned int keylen)
+{
+	struct des3_ede_ctx *dctx = crypto_tfm_ctx(tfm);
+	u32 *flags = &tfm->crt_flags;
+	u32 *expkey = dctx->expkey;
+
+	return __des3_ede_setkey(expkey, flags, key, keylen);
+}
 
 static void des3_ede_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
@@ -945,6 +953,8 @@ static void des3_ede_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 
 static struct crypto_alg des_algs[2] = { {
 	.cra_name		=	"des",
+	.cra_driver_name	=	"des-generic",
+	.cra_priority		=	100,
 	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		=	DES_BLOCK_SIZE,
 	.cra_ctxsize		=	sizeof(struct des_ctx),
@@ -958,6 +968,8 @@ static struct crypto_alg des_algs[2] = { {
 	.cia_decrypt		=	des_decrypt } }
 }, {
 	.cra_name		=	"des3_ede",
+	.cra_driver_name	=	"des3_ede-generic",
+	.cra_priority		=	100,
 	.cra_flags		=	CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		=	DES3_EDE_BLOCK_SIZE,
 	.cra_ctxsize		=	sizeof(struct des3_ede_ctx),
diff --git a/crypto/drbg.c b/crypto/drbg.c
new file mode 100644
index 00000000000..7894db9ca90
--- /dev/null
+++ b/crypto/drbg.c
@@ -0,0 +1,2044 @@
+/*
+ * DRBG: Deterministic Random Bits Generator
+ *       Based on NIST Recommended DRBG from NIST SP800-90A with the following
+ *       properties:
+ *		* CTR DRBG with DF with AES-128, AES-192, AES-256 cores
+ *		* Hash DRBG with DF with SHA-1, SHA-256, SHA-384, SHA-512 cores
+ *		* HMAC DRBG with DF with SHA-1, SHA-256, SHA-384, SHA-512 cores
+ *		* with and without prediction resistance
+ *
+ * Copyright Stephan Mueller <smueller@chronox.de>, 2014
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, and the entire permission notice in its entirety,
+ *    including the disclaimer of warranties.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. The name of the author may not be used to endorse or promote
+ *    products derived from this software without specific prior
+ *    written permission.
+ *
+ * ALTERNATIVELY, this product may be distributed under the terms of
+ * the GNU General Public License, in which case the provisions of the GPL are
+ * required INSTEAD OF the above restrictions.  (This clause is
+ * necessary due to a potential bad interaction between the GPL and
+ * the restrictions contained in a BSD-style copyright.)
+ *
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF
+ * WHICH ARE HEREBY DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
+ * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OF THIS SOFTWARE, EVEN IF NOT ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ *
+ * DRBG Usage
+ * ==========
+ * The SP 800-90A DRBG allows the user to specify a personalization string
+ * for initialization as well as an additional information string for each
+ * random number request. The following code fragments show how a caller
+ * uses the kernel crypto API to use the full functionality of the DRBG.
+ *
+ * Usage without any additional data
+ * ---------------------------------
+ * struct crypto_rng *drng;
+ * int err;
+ * char data[DATALEN];
+ *
+ * drng = crypto_alloc_rng(drng_name, 0, 0);
+ * err = crypto_rng_get_bytes(drng, &data, DATALEN);
+ * crypto_free_rng(drng);
+ *
+ *
+ * Usage with personalization string during initialization
+ * -------------------------------------------------------
+ * struct crypto_rng *drng;
+ * int err;
+ * char data[DATALEN];
+ * struct drbg_string pers;
+ * char personalization[11] = "some-string";
+ *
+ * drbg_string_fill(&pers, personalization, strlen(personalization));
+ * drng = crypto_alloc_rng(drng_name, 0, 0);
+ * // The reset completely re-initializes the DRBG with the provided
+ * // personalization string
+ * err = crypto_rng_reset(drng, &personalization, strlen(personalization));
+ * err = crypto_rng_get_bytes(drng, &data, DATALEN);
+ * crypto_free_rng(drng);
+ *
+ *
+ * Usage with additional information string during random number request
+ * ---------------------------------------------------------------------
+ * struct crypto_rng *drng;
+ * int err;
+ * char data[DATALEN];
+ * char addtl_string[11] = "some-string";
+ * string drbg_string addtl;
+ *
+ * drbg_string_fill(&addtl, addtl_string, strlen(addtl_string));
+ * drng = crypto_alloc_rng(drng_name, 0, 0);
+ * // The following call is a wrapper to crypto_rng_get_bytes() and returns
+ * // the same error codes.
+ * err = crypto_drbg_get_bytes_addtl(drng, &data, DATALEN, &addtl);
+ * crypto_free_rng(drng);
+ *
+ *
+ * Usage with personalization and additional information strings
+ * -------------------------------------------------------------
+ * Just mix both scenarios above.
+ */
+
+#include <crypto/drbg.h>
+
+/***************************************************************
+ * Backend cipher definitions available to DRBG
+ ***************************************************************/
+
+/*
+ * The order of the DRBG definitions here matter: every DRBG is registered
+ * as stdrng. Each DRBG receives an increasing cra_priority values the later
+ * they are defined in this array (see drbg_fill_array).
+ *
+ * HMAC DRBGs are favored over Hash DRBGs over CTR DRBGs, and
+ * the SHA256 / AES 256 over other ciphers. Thus, the favored
+ * DRBGs are the latest entries in this array.
+ */
+static const struct drbg_core drbg_cores[] = {
+#ifdef CONFIG_CRYPTO_DRBG_CTR
+	{
+		.flags = DRBG_CTR | DRBG_STRENGTH128,
+		.statelen = 32, /* 256 bits as defined in 10.2.1 */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 16,
+		.cra_name = "ctr_aes128",
+		.backend_cra_name = "ecb(aes)",
+	}, {
+		.flags = DRBG_CTR | DRBG_STRENGTH192,
+		.statelen = 40, /* 320 bits as defined in 10.2.1 */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 16,
+		.cra_name = "ctr_aes192",
+		.backend_cra_name = "ecb(aes)",
+	}, {
+		.flags = DRBG_CTR | DRBG_STRENGTH256,
+		.statelen = 48, /* 384 bits as defined in 10.2.1 */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 16,
+		.cra_name = "ctr_aes256",
+		.backend_cra_name = "ecb(aes)",
+	},
+#endif /* CONFIG_CRYPTO_DRBG_CTR */
+#ifdef CONFIG_CRYPTO_DRBG_HASH
+	{
+		.flags = DRBG_HASH | DRBG_STRENGTH128,
+		.statelen = 55, /* 440 bits */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 20,
+		.cra_name = "sha1",
+		.backend_cra_name = "sha1",
+	}, {
+		.flags = DRBG_HASH | DRBG_STRENGTH256,
+		.statelen = 111, /* 888 bits */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 48,
+		.cra_name = "sha384",
+		.backend_cra_name = "sha384",
+	}, {
+		.flags = DRBG_HASH | DRBG_STRENGTH256,
+		.statelen = 111, /* 888 bits */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 64,
+		.cra_name = "sha512",
+		.backend_cra_name = "sha512",
+	}, {
+		.flags = DRBG_HASH | DRBG_STRENGTH256,
+		.statelen = 55, /* 440 bits */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 32,
+		.cra_name = "sha256",
+		.backend_cra_name = "sha256",
+	},
+#endif /* CONFIG_CRYPTO_DRBG_HASH */
+#ifdef CONFIG_CRYPTO_DRBG_HMAC
+	{
+		.flags = DRBG_HMAC | DRBG_STRENGTH128,
+		.statelen = 20, /* block length of cipher */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 20,
+		.cra_name = "hmac_sha1",
+		.backend_cra_name = "hmac(sha1)",
+	}, {
+		.flags = DRBG_HMAC | DRBG_STRENGTH256,
+		.statelen = 48, /* block length of cipher */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 48,
+		.cra_name = "hmac_sha384",
+		.backend_cra_name = "hmac(sha384)",
+	}, {
+		.flags = DRBG_HMAC | DRBG_STRENGTH256,
+		.statelen = 64, /* block length of cipher */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 64,
+		.cra_name = "hmac_sha512",
+		.backend_cra_name = "hmac(sha512)",
+	}, {
+		.flags = DRBG_HMAC | DRBG_STRENGTH256,
+		.statelen = 32, /* block length of cipher */
+		.max_addtllen = 35,
+		.max_bits = 19,
+		.max_req = 48,
+		.blocklen_bytes = 32,
+		.cra_name = "hmac_sha256",
+		.backend_cra_name = "hmac(sha256)",
+	},
+#endif /* CONFIG_CRYPTO_DRBG_HMAC */
+};
+
+/******************************************************************
+ * Generic helper functions
+ ******************************************************************/
+
+/*
+ * Return strength of DRBG according to SP800-90A section 8.4
+ *
+ * @flags DRBG flags reference
+ *
+ * Return: normalized strength in *bytes* value or 32 as default
+ *	   to counter programming errors
+ */
+static inline unsigned short drbg_sec_strength(drbg_flag_t flags)
+{
+	switch (flags & DRBG_STRENGTH_MASK) {
+	case DRBG_STRENGTH128:
+		return 16;
+	case DRBG_STRENGTH192:
+		return 24;
+	case DRBG_STRENGTH256:
+		return 32;
+	default:
+		return 32;
+	}
+}
+
+/*
+ * FIPS 140-2 continuous self test
+ * The test is performed on the result of one round of the output
+ * function. Thus, the function implicitly knows the size of the
+ * buffer.
+ *
+ * The FIPS test can be called in an endless loop until it returns
+ * true. Although the code looks like a potential for a deadlock, it
+ * is not the case, because returning a false cannot mathematically
+ * occur (except once when a reseed took place and the updated state
+ * would is now set up such that the generation of new value returns
+ * an identical one -- this is most unlikely and would happen only once).
+ * Thus, if this function repeatedly returns false and thus would cause
+ * a deadlock, the integrity of the entire kernel is lost.
+ *
+ * @drbg DRBG handle
+ * @buf output buffer of random data to be checked
+ *
+ * return:
+ *	true on success
+ *	false on error
+ */
+static bool drbg_fips_continuous_test(struct drbg_state *drbg,
+				      const unsigned char *buf)
+{
+#ifdef CONFIG_CRYPTO_FIPS
+	int ret = 0;
+	/* skip test if we test the overall system */
+	if (drbg->test_data)
+		return true;
+	/* only perform test in FIPS mode */
+	if (0 == fips_enabled)
+		return true;
+	if (!drbg->fips_primed) {
+		/* Priming of FIPS test */
+		memcpy(drbg->prev, buf, drbg_blocklen(drbg));
+		drbg->fips_primed = true;
+		/* return false due to priming, i.e. another round is needed */
+		return false;
+	}
+	ret = memcmp(drbg->prev, buf, drbg_blocklen(drbg));
+	memcpy(drbg->prev, buf, drbg_blocklen(drbg));
+	/* the test shall pass when the two compared values are not equal */
+	return ret != 0;
+#else
+	return true;
+#endif /* CONFIG_CRYPTO_FIPS */
+}
+
+/*
+ * Convert an integer into a byte representation of this integer.
+ * The byte representation is big-endian
+ *
+ * @buf buffer holding the converted integer
+ * @val value to be converted
+ * @buflen length of buffer
+ */
+#if (defined(CONFIG_CRYPTO_DRBG_HASH) || defined(CONFIG_CRYPTO_DRBG_CTR))
+static inline void drbg_int2byte(unsigned char *buf, uint64_t val,
+				 size_t buflen)
+{
+	unsigned char *byte;
+	uint64_t i;
+
+	byte = buf + (buflen - 1);
+	for (i = 0; i < buflen; i++)
+		*(byte--) = val >> (i * 8) & 0xff;
+}
+
+/*
+ * Increment buffer
+ *
+ * @dst buffer to increment
+ * @add value to add
+ */
+static inline void drbg_add_buf(unsigned char *dst, size_t dstlen,
+				const unsigned char *add, size_t addlen)
+{
+	/* implied: dstlen > addlen */
+	unsigned char *dstptr;
+	const unsigned char *addptr;
+	unsigned int remainder = 0;
+	size_t len = addlen;
+
+	dstptr = dst + (dstlen-1);
+	addptr = add + (addlen-1);
+	while (len) {
+		remainder += *dstptr + *addptr;
+		*dstptr = remainder & 0xff;
+		remainder >>= 8;
+		len--; dstptr--; addptr--;
+	}
+	len = dstlen - addlen;
+	while (len && remainder > 0) {
+		remainder = *dstptr + 1;
+		*dstptr = remainder & 0xff;
+		remainder >>= 8;
+		len--; dstptr--;
+	}
+}
+#endif /* defined(CONFIG_CRYPTO_DRBG_HASH) || defined(CONFIG_CRYPTO_DRBG_CTR) */
+
+/******************************************************************
+ * CTR DRBG callback functions
+ ******************************************************************/
+
+#ifdef CONFIG_CRYPTO_DRBG_CTR
+#define CRYPTO_DRBG_CTR_STRING "CTR "
+static int drbg_kcapi_sym(struct drbg_state *drbg, const unsigned char *key,
+			  unsigned char *outval, const struct drbg_string *in);
+static int drbg_init_sym_kernel(struct drbg_state *drbg);
+static int drbg_fini_sym_kernel(struct drbg_state *drbg);
+
+/* BCC function for CTR DRBG as defined in 10.4.3 */
+static int drbg_ctr_bcc(struct drbg_state *drbg,
+			unsigned char *out, const unsigned char *key,
+			struct list_head *in)
+{
+	int ret = 0;
+	struct drbg_string *curr = NULL;
+	struct drbg_string data;
+	short cnt = 0;
+
+	drbg_string_fill(&data, out, drbg_blocklen(drbg));
+
+	/* 10.4.3 step 1 */
+	memset(out, 0, drbg_blocklen(drbg));
+
+	/* 10.4.3 step 2 / 4 */
+	list_for_each_entry(curr, in, list) {
+		const unsigned char *pos = curr->buf;
+		size_t len = curr->len;
+		/* 10.4.3 step 4.1 */
+		while (len) {
+			/* 10.4.3 step 4.2 */
+			if (drbg_blocklen(drbg) == cnt) {
+				cnt = 0;
+				ret = drbg_kcapi_sym(drbg, key, out, &data);
+				if (ret)
+					return ret;
+			}
+			out[cnt] ^= *pos;
+			pos++;
+			cnt++;
+			len--;
+		}
+	}
+	/* 10.4.3 step 4.2 for last block */
+	if (cnt)
+		ret = drbg_kcapi_sym(drbg, key, out, &data);
+
+	return ret;
+}
+
+/*
+ * scratchpad usage: drbg_ctr_update is interlinked with drbg_ctr_df
+ * (and drbg_ctr_bcc, but this function does not need any temporary buffers),
+ * the scratchpad is used as follows:
+ * drbg_ctr_update:
+ *	temp
+ *		start: drbg->scratchpad
+ *		length: drbg_statelen(drbg) + drbg_blocklen(drbg)
+ *			note: the cipher writing into this variable works
+ *			blocklen-wise. Now, when the statelen is not a multiple
+ *			of blocklen, the generateion loop below "spills over"
+ *			by at most blocklen. Thus, we need to give sufficient
+ *			memory.
+ *	df_data
+ *		start: drbg->scratchpad +
+ *				drbg_statelen(drbg) + drbg_blocklen(drbg)
+ *		length: drbg_statelen(drbg)
+ *
+ * drbg_ctr_df:
+ *	pad
+ *		start: df_data + drbg_statelen(drbg)
+ *		length: drbg_blocklen(drbg)
+ *	iv
+ *		start: pad + drbg_blocklen(drbg)
+ *		length: drbg_blocklen(drbg)
+ *	temp
+ *		start: iv + drbg_blocklen(drbg)
+ *		length: drbg_satelen(drbg) + drbg_blocklen(drbg)
+ *			note: temp is the buffer that the BCC function operates
+ *			on. BCC operates blockwise. drbg_statelen(drbg)
+ *			is sufficient when the DRBG state length is a multiple
+ *			of the block size. For AES192 (and maybe other ciphers)
+ *			this is not correct and the length for temp is
+ *			insufficient (yes, that also means for such ciphers,
+ *			the final output of all BCC rounds are truncated).
+ *			Therefore, add drbg_blocklen(drbg) to cover all
+ *			possibilities.
+ */
+
+/* Derivation Function for CTR DRBG as defined in 10.4.2 */
+static int drbg_ctr_df(struct drbg_state *drbg,
+		       unsigned char *df_data, size_t bytes_to_return,
+		       struct list_head *seedlist)
+{
+	int ret = -EFAULT;
+	unsigned char L_N[8];
+	/* S3 is input */
+	struct drbg_string S1, S2, S4, cipherin;
+	LIST_HEAD(bcc_list);
+	unsigned char *pad = df_data + drbg_statelen(drbg);
+	unsigned char *iv = pad + drbg_blocklen(drbg);
+	unsigned char *temp = iv + drbg_blocklen(drbg);
+	size_t padlen = 0;
+	unsigned int templen = 0;
+	/* 10.4.2 step 7 */
+	unsigned int i = 0;
+	/* 10.4.2 step 8 */
+	const unsigned char *K = (unsigned char *)
+			   "\x00\x01\x02\x03\x04\x05\x06\x07"
+			   "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"
+			   "\x10\x11\x12\x13\x14\x15\x16\x17"
+			   "\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f";
+	unsigned char *X;
+	size_t generated_len = 0;
+	size_t inputlen = 0;
+	struct drbg_string *seed = NULL;
+
+	memset(pad, 0, drbg_blocklen(drbg));
+	memset(iv, 0, drbg_blocklen(drbg));
+	memset(temp, 0, drbg_statelen(drbg));
+
+	/* 10.4.2 step 1 is implicit as we work byte-wise */
+
+	/* 10.4.2 step 2 */
+	if ((512/8) < bytes_to_return)
+		return -EINVAL;
+
+	/* 10.4.2 step 2 -- calculate the entire length of all input data */
+	list_for_each_entry(seed, seedlist, list)
+		inputlen += seed->len;
+	drbg_int2byte(&L_N[0], inputlen, 4);
+
+	/* 10.4.2 step 3 */
+	drbg_int2byte(&L_N[4], bytes_to_return, 4);
+
+	/* 10.4.2 step 5: length is L_N, input_string, one byte, padding */
+	padlen = (inputlen + sizeof(L_N) + 1) % (drbg_blocklen(drbg));
+	/* wrap the padlen appropriately */
+	if (padlen)
+		padlen = drbg_blocklen(drbg) - padlen;
+	/*
+	 * pad / padlen contains the 0x80 byte and the following zero bytes.
+	 * As the calculated padlen value only covers the number of zero
+	 * bytes, this value has to be incremented by one for the 0x80 byte.
+	 */
+	padlen++;
+	pad[0] = 0x80;
+
+	/* 10.4.2 step 4 -- first fill the linked list and then order it */
+	drbg_string_fill(&S1, iv, drbg_blocklen(drbg));
+	list_add_tail(&S1.list, &bcc_list);
+	drbg_string_fill(&S2, L_N, sizeof(L_N));
+	list_add_tail(&S2.list, &bcc_list);
+	list_splice_tail(seedlist, &bcc_list);
+	drbg_string_fill(&S4, pad, padlen);
+	list_add_tail(&S4.list, &bcc_list);
+
+	/* 10.4.2 step 9 */
+	while (templen < (drbg_keylen(drbg) + (drbg_blocklen(drbg)))) {
+		/*
+		 * 10.4.2 step 9.1 - the padding is implicit as the buffer
+		 * holds zeros after allocation -- even the increment of i
+		 * is irrelevant as the increment remains within length of i
+		 */
+		drbg_int2byte(iv, i, 4);
+		/* 10.4.2 step 9.2 -- BCC and concatenation with temp */
+		ret = drbg_ctr_bcc(drbg, temp + templen, K, &bcc_list);
+		if (ret)
+			goto out;
+		/* 10.4.2 step 9.3 */
+		i++;
+		templen += drbg_blocklen(drbg);
+	}
+
+	/* 10.4.2 step 11 */
+	X = temp + (drbg_keylen(drbg));
+	drbg_string_fill(&cipherin, X, drbg_blocklen(drbg));
+
+	/* 10.4.2 step 12: overwriting of outval is implemented in next step */
+
+	/* 10.4.2 step 13 */
+	while (generated_len < bytes_to_return) {
+		short blocklen = 0;
+		/*
+		 * 10.4.2 step 13.1: the truncation of the key length is
+		 * implicit as the key is only drbg_blocklen in size based on
+		 * the implementation of the cipher function callback
+		 */
+		ret = drbg_kcapi_sym(drbg, temp, X, &cipherin);
+		if (ret)
+			goto out;
+		blocklen = (drbg_blocklen(drbg) <
+				(bytes_to_return - generated_len)) ?
+			    drbg_blocklen(drbg) :
+				(bytes_to_return - generated_len);
+		/* 10.4.2 step 13.2 and 14 */
+		memcpy(df_data + generated_len, X, blocklen);
+		generated_len += blocklen;
+	}
+
+	ret = 0;
+
+out:
+	memset(iv, 0, drbg_blocklen(drbg));
+	memset(temp, 0, drbg_statelen(drbg));
+	memset(pad, 0, drbg_blocklen(drbg));
+	return ret;
+}
+
+/*
+ * update function of CTR DRBG as defined in 10.2.1.2
+ *
+ * The reseed variable has an enhanced meaning compared to the update
+ * functions of the other DRBGs as follows:
+ * 0 => initial seed from initialization
+ * 1 => reseed via drbg_seed
+ * 2 => first invocation from drbg_ctr_update when addtl is present. In
+ *      this case, the df_data scratchpad is not deleted so that it is
+ *      available for another calls to prevent calling the DF function
+ *      again.
+ * 3 => second invocation from drbg_ctr_update. When the update function
+ *      was called with addtl, the df_data memory already contains the
+ *      DFed addtl information and we do not need to call DF again.
+ */
+static int drbg_ctr_update(struct drbg_state *drbg, struct list_head *seed,
+			   int reseed)
+{
+	int ret = -EFAULT;
+	/* 10.2.1.2 step 1 */
+	unsigned char *temp = drbg->scratchpad;
+	unsigned char *df_data = drbg->scratchpad + drbg_statelen(drbg) +
+				 drbg_blocklen(drbg);
+	unsigned char *temp_p, *df_data_p; /* pointer to iterate over buffers */
+	unsigned int len = 0;
+	struct drbg_string cipherin;
+	unsigned char prefix = DRBG_PREFIX1;
+
+	memset(temp, 0, drbg_statelen(drbg) + drbg_blocklen(drbg));
+	if (3 > reseed)
+		memset(df_data, 0, drbg_statelen(drbg));
+
+	/* 10.2.1.3.2 step 2 and 10.2.1.4.2 step 2 */
+	if (seed) {
+		ret = drbg_ctr_df(drbg, df_data, drbg_statelen(drbg), seed);
+		if (ret)
+			goto out;
+	}
+
+	drbg_string_fill(&cipherin, drbg->V, drbg_blocklen(drbg));
+	/*
+	 * 10.2.1.3.2 steps 2 and 3 are already covered as the allocation
+	 * zeroizes all memory during initialization
+	 */
+	while (len < (drbg_statelen(drbg))) {
+		/* 10.2.1.2 step 2.1 */
+		drbg_add_buf(drbg->V, drbg_blocklen(drbg), &prefix, 1);
+		/*
+		 * 10.2.1.2 step 2.2 */
+		ret = drbg_kcapi_sym(drbg, drbg->C, temp + len, &cipherin);
+		if (ret)
+			goto out;
+		/* 10.2.1.2 step 2.3 and 3 */
+		len += drbg_blocklen(drbg);
+	}
+
+	/* 10.2.1.2 step 4 */
+	temp_p = temp;
+	df_data_p = df_data;
+	for (len = 0; len < drbg_statelen(drbg); len++) {
+		*temp_p ^= *df_data_p;
+		df_data_p++; temp_p++;
+	}
+
+	/* 10.2.1.2 step 5 */
+	memcpy(drbg->C, temp, drbg_keylen(drbg));
+	/* 10.2.1.2 step 6 */
+	memcpy(drbg->V, temp + drbg_keylen(drbg), drbg_blocklen(drbg));
+	ret = 0;
+
+out:
+	memset(temp, 0, drbg_statelen(drbg) + drbg_blocklen(drbg));
+	if (2 != reseed)
+		memset(df_data, 0, drbg_statelen(drbg));
+	return ret;
+}
+
+/*
+ * scratchpad use: drbg_ctr_update is called independently from
+ * drbg_ctr_extract_bytes. Therefore, the scratchpad is reused
+ */
+/* Generate function of CTR DRBG as defined in 10.2.1.5.2 */
+static int drbg_ctr_generate(struct drbg_state *drbg,
+			     unsigned char *buf, unsigned int buflen,
+			     struct list_head *addtl)
+{
+	int len = 0;
+	int ret = 0;
+	struct drbg_string data;
+	unsigned char prefix = DRBG_PREFIX1;
+
+	memset(drbg->scratchpad, 0, drbg_blocklen(drbg));
+
+	/* 10.2.1.5.2 step 2 */
+	if (addtl && !list_empty(addtl)) {
+		ret = drbg_ctr_update(drbg, addtl, 2);
+		if (ret)
+			return 0;
+	}
+
+	/* 10.2.1.5.2 step 4.1 */
+	drbg_add_buf(drbg->V, drbg_blocklen(drbg), &prefix, 1);
+	drbg_string_fill(&data, drbg->V, drbg_blocklen(drbg));
+	while (len < buflen) {
+		int outlen = 0;
+		/* 10.2.1.5.2 step 4.2 */
+		ret = drbg_kcapi_sym(drbg, drbg->C, drbg->scratchpad, &data);
+		if (ret) {
+			len = ret;
+			goto out;
+		}
+		outlen = (drbg_blocklen(drbg) < (buflen - len)) ?
+			  drbg_blocklen(drbg) : (buflen - len);
+		if (!drbg_fips_continuous_test(drbg, drbg->scratchpad)) {
+			/* 10.2.1.5.2 step 6 */
+			drbg_add_buf(drbg->V, drbg_blocklen(drbg), &prefix, 1);
+			continue;
+		}
+		/* 10.2.1.5.2 step 4.3 */
+		memcpy(buf + len, drbg->scratchpad, outlen);
+		len += outlen;
+		/* 10.2.1.5.2 step 6 */
+		if (len < buflen)
+			drbg_add_buf(drbg->V, drbg_blocklen(drbg), &prefix, 1);
+	}
+
+	/* 10.2.1.5.2 step 6 */
+	ret = drbg_ctr_update(drbg, NULL, 3);
+	if (ret)
+		len = ret;
+
+out:
+	memset(drbg->scratchpad, 0, drbg_blocklen(drbg));
+	return len;
+}
+
+static struct drbg_state_ops drbg_ctr_ops = {
+	.update		= drbg_ctr_update,
+	.generate	= drbg_ctr_generate,
+	.crypto_init	= drbg_init_sym_kernel,
+	.crypto_fini	= drbg_fini_sym_kernel,
+};
+#endif /* CONFIG_CRYPTO_DRBG_CTR */
+
+/******************************************************************
+ * HMAC DRBG callback functions
+ ******************************************************************/
+
+#if defined(CONFIG_CRYPTO_DRBG_HASH) || defined(CONFIG_CRYPTO_DRBG_HMAC)
+static int drbg_kcapi_hash(struct drbg_state *drbg, const unsigned char *key,
+			   unsigned char *outval, const struct list_head *in);
+static int drbg_init_hash_kernel(struct drbg_state *drbg);
+static int drbg_fini_hash_kernel(struct drbg_state *drbg);
+#endif /* (CONFIG_CRYPTO_DRBG_HASH || CONFIG_CRYPTO_DRBG_HMAC) */
+
+#ifdef CONFIG_CRYPTO_DRBG_HMAC
+#define CRYPTO_DRBG_HMAC_STRING "HMAC "
+/* update function of HMAC DRBG as defined in 10.1.2.2 */
+static int drbg_hmac_update(struct drbg_state *drbg, struct list_head *seed,
+			    int reseed)
+{
+	int ret = -EFAULT;
+	int i = 0;
+	struct drbg_string seed1, seed2, vdata;
+	LIST_HEAD(seedlist);
+	LIST_HEAD(vdatalist);
+
+	if (!reseed) {
+		/* 10.1.2.3 step 2 */
+		memset(drbg->C, 0, drbg_statelen(drbg));
+		memset(drbg->V, 1, drbg_statelen(drbg));
+	}
+
+	drbg_string_fill(&seed1, drbg->V, drbg_statelen(drbg));
+	list_add_tail(&seed1.list, &seedlist);
+	/* buffer of seed2 will be filled in for loop below with one byte */
+	drbg_string_fill(&seed2, NULL, 1);
+	list_add_tail(&seed2.list, &seedlist);
+	/* input data of seed is allowed to be NULL at this point */
+	if (seed)
+		list_splice_tail(seed, &seedlist);
+
+	drbg_string_fill(&vdata, drbg->V, drbg_statelen(drbg));
+	list_add_tail(&vdata.list, &vdatalist);
+	for (i = 2; 0 < i; i--) {
+		/* first round uses 0x0, second 0x1 */
+		unsigned char prefix = DRBG_PREFIX0;
+		if (1 == i)
+			prefix = DRBG_PREFIX1;
+		/* 10.1.2.2 step 1 and 4 -- concatenation and HMAC for key */
+		seed2.buf = &prefix;
+		ret = drbg_kcapi_hash(drbg, drbg->C, drbg->C, &seedlist);
+		if (ret)
+			return ret;
+
+		/* 10.1.2.2 step 2 and 5 -- HMAC for V */
+		ret = drbg_kcapi_hash(drbg, drbg->C, drbg->V, &vdatalist);
+		if (ret)
+			return ret;
+
+		/* 10.1.2.2 step 3 */
+		if (!seed)
+			return ret;
+	}
+
+	return 0;
+}
+
+/* generate function of HMAC DRBG as defined in 10.1.2.5 */
+static int drbg_hmac_generate(struct drbg_state *drbg,
+			      unsigned char *buf,
+			      unsigned int buflen,
+			      struct list_head *addtl)
+{
+	int len = 0;
+	int ret = 0;
+	struct drbg_string data;
+	LIST_HEAD(datalist);
+
+	/* 10.1.2.5 step 2 */
+	if (addtl && !list_empty(addtl)) {
+		ret = drbg_hmac_update(drbg, addtl, 1);
+		if (ret)
+			return ret;
+	}
+
+	drbg_string_fill(&data, drbg->V, drbg_statelen(drbg));
+	list_add_tail(&data.list, &datalist);
+	while (len < buflen) {
+		unsigned int outlen = 0;
+		/* 10.1.2.5 step 4.1 */
+		ret = drbg_kcapi_hash(drbg, drbg->C, drbg->V, &datalist);
+		if (ret)
+			return ret;
+		outlen = (drbg_blocklen(drbg) < (buflen - len)) ?
+			  drbg_blocklen(drbg) : (buflen - len);
+		if (!drbg_fips_continuous_test(drbg, drbg->V))
+			continue;
+
+		/* 10.1.2.5 step 4.2 */
+		memcpy(buf + len, drbg->V, outlen);
+		len += outlen;
+	}
+
+	/* 10.1.2.5 step 6 */
+	if (addtl && !list_empty(addtl))
+		ret = drbg_hmac_update(drbg, addtl, 1);
+	else
+		ret = drbg_hmac_update(drbg, NULL, 1);
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+static struct drbg_state_ops drbg_hmac_ops = {
+	.update		= drbg_hmac_update,
+	.generate	= drbg_hmac_generate,
+	.crypto_init	= drbg_init_hash_kernel,
+	.crypto_fini	= drbg_fini_hash_kernel,
+
+};
+#endif /* CONFIG_CRYPTO_DRBG_HMAC */
+
+/******************************************************************
+ * Hash DRBG callback functions
+ ******************************************************************/
+
+#ifdef CONFIG_CRYPTO_DRBG_HASH
+#define CRYPTO_DRBG_HASH_STRING "HASH "
+/*
+ * scratchpad usage: as drbg_hash_update and drbg_hash_df are used
+ * interlinked, the scratchpad is used as follows:
+ * drbg_hash_update
+ *	start: drbg->scratchpad
+ *	length: drbg_statelen(drbg)
+ * drbg_hash_df:
+ *	start: drbg->scratchpad + drbg_statelen(drbg)
+ *	length: drbg_blocklen(drbg)
+ *
+ * drbg_hash_process_addtl uses the scratchpad, but fully completes
+ * before either of the functions mentioned before are invoked. Therefore,
+ * drbg_hash_process_addtl does not need to be specifically considered.
+ */
+
+/* Derivation Function for Hash DRBG as defined in 10.4.1 */
+static int drbg_hash_df(struct drbg_state *drbg,
+			unsigned char *outval, size_t outlen,
+			struct list_head *entropylist)
+{
+	int ret = 0;
+	size_t len = 0;
+	unsigned char input[5];
+	unsigned char *tmp = drbg->scratchpad + drbg_statelen(drbg);
+	struct drbg_string data;
+
+	memset(tmp, 0, drbg_blocklen(drbg));
+
+	/* 10.4.1 step 3 */
+	input[0] = 1;
+	drbg_int2byte(&input[1], (outlen * 8), 4);
+
+	/* 10.4.1 step 4.1 -- concatenation of data for input into hash */
+	drbg_string_fill(&data, input, 5);
+	list_add(&data.list, entropylist);
+
+	/* 10.4.1 step 4 */
+	while (len < outlen) {
+		short blocklen = 0;
+		/* 10.4.1 step 4.1 */
+		ret = drbg_kcapi_hash(drbg, NULL, tmp, entropylist);
+		if (ret)
+			goto out;
+		/* 10.4.1 step 4.2 */
+		input[0]++;
+		blocklen = (drbg_blocklen(drbg) < (outlen - len)) ?
+			    drbg_blocklen(drbg) : (outlen - len);
+		memcpy(outval + len, tmp, blocklen);
+		len += blocklen;
+	}
+
+out:
+	memset(tmp, 0, drbg_blocklen(drbg));
+	return ret;
+}
+
+/* update function for Hash DRBG as defined in 10.1.1.2 / 10.1.1.3 */
+static int drbg_hash_update(struct drbg_state *drbg, struct list_head *seed,
+			    int reseed)
+{
+	int ret = 0;
+	struct drbg_string data1, data2;
+	LIST_HEAD(datalist);
+	LIST_HEAD(datalist2);
+	unsigned char *V = drbg->scratchpad;
+	unsigned char prefix = DRBG_PREFIX1;
+
+	memset(drbg->scratchpad, 0, drbg_statelen(drbg));
+	if (!seed)
+		return -EINVAL;
+
+	if (reseed) {
+		/* 10.1.1.3 step 1 */
+		memcpy(V, drbg->V, drbg_statelen(drbg));
+		drbg_string_fill(&data1, &prefix, 1);
+		list_add_tail(&data1.list, &datalist);
+		drbg_string_fill(&data2, V, drbg_statelen(drbg));
+		list_add_tail(&data2.list, &datalist);
+	}
+	list_splice_tail(seed, &datalist);
+
+	/* 10.1.1.2 / 10.1.1.3 step 2 and 3 */
+	ret = drbg_hash_df(drbg, drbg->V, drbg_statelen(drbg), &datalist);
+	if (ret)
+		goto out;
+
+	/* 10.1.1.2 / 10.1.1.3 step 4  */
+	prefix = DRBG_PREFIX0;
+	drbg_string_fill(&data1, &prefix, 1);
+	list_add_tail(&data1.list, &datalist2);
+	drbg_string_fill(&data2, drbg->V, drbg_statelen(drbg));
+	list_add_tail(&data2.list, &datalist2);
+	/* 10.1.1.2 / 10.1.1.3 step 4 */
+	ret = drbg_hash_df(drbg, drbg->C, drbg_statelen(drbg), &datalist2);
+
+out:
+	memset(drbg->scratchpad, 0, drbg_statelen(drbg));
+	return ret;
+}
+
+/* processing of additional information string for Hash DRBG */
+static int drbg_hash_process_addtl(struct drbg_state *drbg,
+				   struct list_head *addtl)
+{
+	int ret = 0;
+	struct drbg_string data1, data2;
+	LIST_HEAD(datalist);
+	unsigned char prefix = DRBG_PREFIX2;
+
+	/* this is value w as per documentation */
+	memset(drbg->scratchpad, 0, drbg_blocklen(drbg));
+
+	/* 10.1.1.4 step 2 */
+	if (!addtl || list_empty(addtl))
+		return 0;
+
+	/* 10.1.1.4 step 2a */
+	drbg_string_fill(&data1, &prefix, 1);
+	drbg_string_fill(&data2, drbg->V, drbg_statelen(drbg));
+	list_add_tail(&data1.list, &datalist);
+	list_add_tail(&data2.list, &datalist);
+	list_splice_tail(addtl, &datalist);
+	ret = drbg_kcapi_hash(drbg, NULL, drbg->scratchpad, &datalist);
+	if (ret)
+		goto out;
+
+	/* 10.1.1.4 step 2b */
+	drbg_add_buf(drbg->V, drbg_statelen(drbg),
+		     drbg->scratchpad, drbg_blocklen(drbg));
+
+out:
+	memset(drbg->scratchpad, 0, drbg_blocklen(drbg));
+	return ret;
+}
+
+/* Hashgen defined in 10.1.1.4 */
+static int drbg_hash_hashgen(struct drbg_state *drbg,
+			     unsigned char *buf,
+			     unsigned int buflen)
+{
+	int len = 0;
+	int ret = 0;
+	unsigned char *src = drbg->scratchpad;
+	unsigned char *dst = drbg->scratchpad + drbg_statelen(drbg);
+	struct drbg_string data;
+	LIST_HEAD(datalist);
+	unsigned char prefix = DRBG_PREFIX1;
+
+	memset(src, 0, drbg_statelen(drbg));
+	memset(dst, 0, drbg_blocklen(drbg));
+
+	/* 10.1.1.4 step hashgen 2 */
+	memcpy(src, drbg->V, drbg_statelen(drbg));
+
+	drbg_string_fill(&data, src, drbg_statelen(drbg));
+	list_add_tail(&data.list, &datalist);
+	while (len < buflen) {
+		unsigned int outlen = 0;
+		/* 10.1.1.4 step hashgen 4.1 */
+		ret = drbg_kcapi_hash(drbg, NULL, dst, &datalist);
+		if (ret) {
+			len = ret;
+			goto out;
+		}
+		outlen = (drbg_blocklen(drbg) < (buflen - len)) ?
+			  drbg_blocklen(drbg) : (buflen - len);
+		if (!drbg_fips_continuous_test(drbg, dst)) {
+			drbg_add_buf(src, drbg_statelen(drbg), &prefix, 1);
+			continue;
+		}
+		/* 10.1.1.4 step hashgen 4.2 */
+		memcpy(buf + len, dst, outlen);
+		len += outlen;
+		/* 10.1.1.4 hashgen step 4.3 */
+		if (len < buflen)
+			drbg_add_buf(src, drbg_statelen(drbg), &prefix, 1);
+	}
+
+out:
+	memset(drbg->scratchpad, 0,
+	       (drbg_statelen(drbg) + drbg_blocklen(drbg)));
+	return len;
+}
+
+/* generate function for Hash DRBG as defined in  10.1.1.4 */
+static int drbg_hash_generate(struct drbg_state *drbg,
+			      unsigned char *buf, unsigned int buflen,
+			      struct list_head *addtl)
+{
+	int len = 0;
+	int ret = 0;
+	unsigned char req[8];
+	unsigned char prefix = DRBG_PREFIX3;
+	struct drbg_string data1, data2;
+	LIST_HEAD(datalist);
+
+	/* 10.1.1.4 step 2 */
+	ret = drbg_hash_process_addtl(drbg, addtl);
+	if (ret)
+		return ret;
+	/* 10.1.1.4 step 3 */
+	len = drbg_hash_hashgen(drbg, buf, buflen);
+
+	/* this is the value H as documented in 10.1.1.4 */
+	memset(drbg->scratchpad, 0, drbg_blocklen(drbg));
+	/* 10.1.1.4 step 4 */
+	drbg_string_fill(&data1, &prefix, 1);
+	list_add_tail(&data1.list, &datalist);
+	drbg_string_fill(&data2, drbg->V, drbg_statelen(drbg));
+	list_add_tail(&data2.list, &datalist);
+	ret = drbg_kcapi_hash(drbg, NULL, drbg->scratchpad, &datalist);
+	if (ret) {
+		len = ret;
+		goto out;
+	}
+
+	/* 10.1.1.4 step 5 */
+	drbg_add_buf(drbg->V, drbg_statelen(drbg),
+		     drbg->scratchpad, drbg_blocklen(drbg));
+	drbg_add_buf(drbg->V, drbg_statelen(drbg),
+		     drbg->C, drbg_statelen(drbg));
+	drbg_int2byte(req, drbg->reseed_ctr, sizeof(req));
+	drbg_add_buf(drbg->V, drbg_statelen(drbg), req, 8);
+
+out:
+	memset(drbg->scratchpad, 0, drbg_blocklen(drbg));
+	return len;
+}
+
+/*
+ * scratchpad usage: as update and generate are used isolated, both
+ * can use the scratchpad
+ */
+static struct drbg_state_ops drbg_hash_ops = {
+	.update		= drbg_hash_update,
+	.generate	= drbg_hash_generate,
+	.crypto_init	= drbg_init_hash_kernel,
+	.crypto_fini	= drbg_fini_hash_kernel,
+};
+#endif /* CONFIG_CRYPTO_DRBG_HASH */
+
+/******************************************************************
+ * Functions common for DRBG implementations
+ ******************************************************************/
+
+/*
+ * Seeding or reseeding of the DRBG
+ *
+ * @drbg: DRBG state struct
+ * @pers: personalization / additional information buffer
+ * @reseed: 0 for initial seed process, 1 for reseeding
+ *
+ * return:
+ *	0 on success
+ *	error value otherwise
+ */
+static int drbg_seed(struct drbg_state *drbg, struct drbg_string *pers,
+		     bool reseed)
+{
+	int ret = 0;
+	unsigned char *entropy = NULL;
+	size_t entropylen = 0;
+	struct drbg_string data1;
+	LIST_HEAD(seedlist);
+
+	/* 9.1 / 9.2 / 9.3.1 step 3 */
+	if (pers && pers->len > (drbg_max_addtl(drbg))) {
+		pr_devel("DRBG: personalization string too long %zu\n",
+			 pers->len);
+		return -EINVAL;
+	}
+
+	if (drbg->test_data && drbg->test_data->testentropy) {
+		drbg_string_fill(&data1, drbg->test_data->testentropy->buf,
+				 drbg->test_data->testentropy->len);
+		pr_devel("DRBG: using test entropy\n");
+	} else {
+		/*
+		 * Gather entropy equal to the security strength of the DRBG.
+		 * With a derivation function, a nonce is required in addition
+		 * to the entropy. A nonce must be at least 1/2 of the security
+		 * strength of the DRBG in size. Thus, entropy * nonce is 3/2
+		 * of the strength. The consideration of a nonce is only
+		 * applicable during initial seeding.
+		 */
+		entropylen = drbg_sec_strength(drbg->core->flags);
+		if (!entropylen)
+			return -EFAULT;
+		if (!reseed)
+			entropylen = ((entropylen + 1) / 2) * 3;
+		pr_devel("DRBG: (re)seeding with %zu bytes of entropy\n",
+			 entropylen);
+		entropy = kzalloc(entropylen, GFP_KERNEL);
+		if (!entropy)
+			return -ENOMEM;
+		get_random_bytes(entropy, entropylen);
+		drbg_string_fill(&data1, entropy, entropylen);
+	}
+	list_add_tail(&data1.list, &seedlist);
+
+	/*
+	 * concatenation of entropy with personalization str / addtl input)
+	 * the variable pers is directly handed in by the caller, so check its
+	 * contents whether it is appropriate
+	 */
+	if (pers && pers->buf && 0 < pers->len) {
+		list_add_tail(&pers->list, &seedlist);
+		pr_devel("DRBG: using personalization string\n");
+	}
+
+	ret = drbg->d_ops->update(drbg, &seedlist, reseed);
+	if (ret)
+		goto out;
+
+	drbg->seeded = true;
+	/* 10.1.1.2 / 10.1.1.3 step 5 */
+	drbg->reseed_ctr = 1;
+
+out:
+	if (entropy)
+		kzfree(entropy);
+	return ret;
+}
+
+/* Free all substructures in a DRBG state without the DRBG state structure */
+static inline void drbg_dealloc_state(struct drbg_state *drbg)
+{
+	if (!drbg)
+		return;
+	if (drbg->V)
+		kzfree(drbg->V);
+	drbg->V = NULL;
+	if (drbg->C)
+		kzfree(drbg->C);
+	drbg->C = NULL;
+	if (drbg->scratchpad)
+		kzfree(drbg->scratchpad);
+	drbg->scratchpad = NULL;
+	drbg->reseed_ctr = 0;
+#ifdef CONFIG_CRYPTO_FIPS
+	if (drbg->prev)
+		kzfree(drbg->prev);
+	drbg->prev = NULL;
+	drbg->fips_primed = false;
+#endif
+}
+
+/*
+ * Allocate all sub-structures for a DRBG state.
+ * The DRBG state structure must already be allocated.
+ */
+static inline int drbg_alloc_state(struct drbg_state *drbg)
+{
+	int ret = -ENOMEM;
+	unsigned int sb_size = 0;
+
+	if (!drbg)
+		return -EINVAL;
+
+	drbg->V = kzalloc(drbg_statelen(drbg), GFP_KERNEL);
+	if (!drbg->V)
+		goto err;
+	drbg->C = kzalloc(drbg_statelen(drbg), GFP_KERNEL);
+	if (!drbg->C)
+		goto err;
+#ifdef CONFIG_CRYPTO_FIPS
+	drbg->prev = kzalloc(drbg_blocklen(drbg), GFP_KERNEL);
+	if (!drbg->prev)
+		goto err;
+	drbg->fips_primed = false;
+#endif
+	/* scratchpad is only generated for CTR and Hash */
+	if (drbg->core->flags & DRBG_HMAC)
+		sb_size = 0;
+	else if (drbg->core->flags & DRBG_CTR)
+		sb_size = drbg_statelen(drbg) + drbg_blocklen(drbg) + /* temp */
+			  drbg_statelen(drbg) +	/* df_data */
+			  drbg_blocklen(drbg) +	/* pad */
+			  drbg_blocklen(drbg) +	/* iv */
+			  drbg_statelen(drbg) + drbg_blocklen(drbg); /* temp */
+	else
+		sb_size = drbg_statelen(drbg) + drbg_blocklen(drbg);
+
+	if (0 < sb_size) {
+		drbg->scratchpad = kzalloc(sb_size, GFP_KERNEL);
+		if (!drbg->scratchpad)
+			goto err;
+	}
+	spin_lock_init(&drbg->drbg_lock);
+	return 0;
+
+err:
+	drbg_dealloc_state(drbg);
+	return ret;
+}
+
+/*
+ * Strategy to avoid holding long term locks: generate a shadow copy of DRBG
+ * and perform all operations on this shadow copy. After finishing, restore
+ * the updated state of the shadow copy into original drbg state. This way,
+ * only the read and write operations of the original drbg state must be
+ * locked
+ */
+static inline void drbg_copy_drbg(struct drbg_state *src,
+				  struct drbg_state *dst)
+{
+	if (!src || !dst)
+		return;
+	memcpy(dst->V, src->V, drbg_statelen(src));
+	memcpy(dst->C, src->C, drbg_statelen(src));
+	dst->reseed_ctr = src->reseed_ctr;
+	dst->seeded = src->seeded;
+	dst->pr = src->pr;
+#ifdef CONFIG_CRYPTO_FIPS
+	dst->fips_primed = src->fips_primed;
+	memcpy(dst->prev, src->prev, drbg_blocklen(src));
+#endif
+	/*
+	 * Not copied:
+	 * scratchpad is initialized drbg_alloc_state;
+	 * priv_data is initialized with call to crypto_init;
+	 * d_ops and core are set outside, as these parameters are const;
+	 * test_data is set outside to prevent it being copied back.
+	 */
+}
+
+static int drbg_make_shadow(struct drbg_state *drbg, struct drbg_state **shadow)
+{
+	int ret = -ENOMEM;
+	struct drbg_state *tmp = NULL;
+
+	if (!drbg || !drbg->core || !drbg->V || !drbg->C) {
+		pr_devel("DRBG: attempt to generate shadow copy for "
+			 "uninitialized DRBG state rejected\n");
+		return -EINVAL;
+	}
+	/* HMAC does not have a scratchpad */
+	if (!(drbg->core->flags & DRBG_HMAC) && NULL == drbg->scratchpad)
+		return -EINVAL;
+
+	tmp = kzalloc(sizeof(struct drbg_state), GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	/* read-only data as they are defined as const, no lock needed */
+	tmp->core = drbg->core;
+	tmp->d_ops = drbg->d_ops;
+
+	ret = drbg_alloc_state(tmp);
+	if (ret)
+		goto err;
+
+	spin_lock_bh(&drbg->drbg_lock);
+	drbg_copy_drbg(drbg, tmp);
+	/* only make a link to the test buffer, as we only read that data */
+	tmp->test_data = drbg->test_data;
+	spin_unlock_bh(&drbg->drbg_lock);
+	*shadow = tmp;
+	return 0;
+
+err:
+	if (tmp)
+		kzfree(tmp);
+	return ret;
+}
+
+static void drbg_restore_shadow(struct drbg_state *drbg,
+				struct drbg_state **shadow)
+{
+	struct drbg_state *tmp = *shadow;
+
+	spin_lock_bh(&drbg->drbg_lock);
+	drbg_copy_drbg(tmp, drbg);
+	spin_unlock_bh(&drbg->drbg_lock);
+	drbg_dealloc_state(tmp);
+	kzfree(tmp);
+	*shadow = NULL;
+}
+
+/*************************************************************************
+ * DRBG interface functions
+ *************************************************************************/
+
+/*
+ * DRBG generate function as required by SP800-90A - this function
+ * generates random numbers
+ *
+ * @drbg DRBG state handle
+ * @buf Buffer where to store the random numbers -- the buffer must already
+ *      be pre-allocated by caller
+ * @buflen Length of output buffer - this value defines the number of random
+ *	   bytes pulled from DRBG
+ * @addtl Additional input that is mixed into state, may be NULL -- note
+ *	  the entropy is pulled by the DRBG internally unconditionally
+ *	  as defined in SP800-90A. The additional input is mixed into
+ *	  the state in addition to the pulled entropy.
+ *
+ * return: generated number of bytes
+ */
+static int drbg_generate(struct drbg_state *drbg,
+			 unsigned char *buf, unsigned int buflen,
+			 struct drbg_string *addtl)
+{
+	int len = 0;
+	struct drbg_state *shadow = NULL;
+	LIST_HEAD(addtllist);
+	struct drbg_string timestamp;
+	union {
+		cycles_t cycles;
+		unsigned char char_cycles[sizeof(cycles_t)];
+	} now;
+
+	if (0 == buflen || !buf) {
+		pr_devel("DRBG: no output buffer provided\n");
+		return -EINVAL;
+	}
+	if (addtl && NULL == addtl->buf && 0 < addtl->len) {
+		pr_devel("DRBG: wrong format of additional information\n");
+		return -EINVAL;
+	}
+
+	len = drbg_make_shadow(drbg, &shadow);
+	if (len) {
+		pr_devel("DRBG: shadow copy cannot be generated\n");
+		return len;
+	}
+
+	/* 9.3.1 step 2 */
+	len = -EINVAL;
+	if (buflen > (drbg_max_request_bytes(shadow))) {
+		pr_devel("DRBG: requested random numbers too large %u\n",
+			 buflen);
+		goto err;
+	}
+
+	/* 9.3.1 step 3 is implicit with the chosen DRBG */
+
+	/* 9.3.1 step 4 */
+	if (addtl && addtl->len > (drbg_max_addtl(shadow))) {
+		pr_devel("DRBG: additional information string too long %zu\n",
+			 addtl->len);
+		goto err;
+	}
+	/* 9.3.1 step 5 is implicit with the chosen DRBG */
+
+	/*
+	 * 9.3.1 step 6 and 9 supplemented by 9.3.2 step c is implemented
+	 * here. The spec is a bit convoluted here, we make it simpler.
+	 */
+	if ((drbg_max_requests(shadow)) < shadow->reseed_ctr)
+		shadow->seeded = false;
+
+	/* allocate cipher handle */
+	if (shadow->d_ops->crypto_init) {
+		len = shadow->d_ops->crypto_init(shadow);
+		if (len)
+			goto err;
+	}
+
+	if (shadow->pr || !shadow->seeded) {
+		pr_devel("DRBG: reseeding before generation (prediction "
+			 "resistance: %s, state %s)\n",
+			 drbg->pr ? "true" : "false",
+			 drbg->seeded ? "seeded" : "unseeded");
+		/* 9.3.1 steps 7.1 through 7.3 */
+		len = drbg_seed(shadow, addtl, true);
+		if (len)
+			goto err;
+		/* 9.3.1 step 7.4 */
+		addtl = NULL;
+	}
+
+	/*
+	 * Mix the time stamp into the DRBG state if the DRBG is not in
+	 * test mode. If there are two callers invoking the DRBG at the same
+	 * time, i.e. before the first caller merges its shadow state back,
+	 * both callers would obtain the same random number stream without
+	 * changing the state here.
+	 */
+	if (!drbg->test_data) {
+		now.cycles = random_get_entropy();
+		drbg_string_fill(&timestamp, now.char_cycles, sizeof(cycles_t));
+		list_add_tail(&timestamp.list, &addtllist);
+	}
+	if (addtl && 0 < addtl->len)
+		list_add_tail(&addtl->list, &addtllist);
+	/* 9.3.1 step 8 and 10 */
+	len = shadow->d_ops->generate(shadow, buf, buflen, &addtllist);
+
+	/* 10.1.1.4 step 6, 10.1.2.5 step 7, 10.2.1.5.2 step 7 */
+	shadow->reseed_ctr++;
+	if (0 >= len)
+		goto err;
+
+	/*
+	 * Section 11.3.3 requires to re-perform self tests after some
+	 * generated random numbers. The chosen value after which self
+	 * test is performed is arbitrary, but it should be reasonable.
+	 * However, we do not perform the self tests because of the following
+	 * reasons: it is mathematically impossible that the initial self tests
+	 * were successfully and the following are not. If the initial would
+	 * pass and the following would not, the kernel integrity is violated.
+	 * In this case, the entire kernel operation is questionable and it
+	 * is unlikely that the integrity violation only affects the
+	 * correct operation of the DRBG.
+	 *
+	 * Albeit the following code is commented out, it is provided in
+	 * case somebody has a need to implement the test of 11.3.3.
+	 */
+#if 0
+	if (shadow->reseed_ctr && !(shadow->reseed_ctr % 4096)) {
+		int err = 0;
+		pr_devel("DRBG: start to perform self test\n");
+		if (drbg->core->flags & DRBG_HMAC)
+			err = alg_test("drbg_pr_hmac_sha256",
+				       "drbg_pr_hmac_sha256", 0, 0);
+		else if (drbg->core->flags & DRBG_CTR)
+			err = alg_test("drbg_pr_ctr_aes128",
+				       "drbg_pr_ctr_aes128", 0, 0);
+		else
+			err = alg_test("drbg_pr_sha256",
+				       "drbg_pr_sha256", 0, 0);
+		if (err) {
+			pr_err("DRBG: periodical self test failed\n");
+			/*
+			 * uninstantiate implies that from now on, only errors
+			 * are returned when reusing this DRBG cipher handle
+			 */
+			drbg_uninstantiate(drbg);
+			drbg_dealloc_state(shadow);
+			kzfree(shadow);
+			return 0;
+		} else {
+			pr_devel("DRBG: self test successful\n");
+		}
+	}
+#endif
+
+err:
+	if (shadow->d_ops->crypto_fini)
+		shadow->d_ops->crypto_fini(shadow);
+	drbg_restore_shadow(drbg, &shadow);
+	return len;
+}
+
+/*
+ * Wrapper around drbg_generate which can pull arbitrary long strings
+ * from the DRBG without hitting the maximum request limitation.
+ *
+ * Parameters: see drbg_generate
+ * Return codes: see drbg_generate -- if one drbg_generate request fails,
+ *		 the entire drbg_generate_long request fails
+ */
+static int drbg_generate_long(struct drbg_state *drbg,
+			      unsigned char *buf, unsigned int buflen,
+			      struct drbg_string *addtl)
+{
+	int len = 0;
+	unsigned int slice = 0;
+	do {
+		int tmplen = 0;
+		unsigned int chunk = 0;
+		slice = ((buflen - len) / drbg_max_request_bytes(drbg));
+		chunk = slice ? drbg_max_request_bytes(drbg) : (buflen - len);
+		tmplen = drbg_generate(drbg, buf + len, chunk, addtl);
+		if (0 >= tmplen)
+			return tmplen;
+		len += tmplen;
+	} while (slice > 0 && (len < buflen));
+	return len;
+}
+
+/*
+ * DRBG instantiation function as required by SP800-90A - this function
+ * sets up the DRBG handle, performs the initial seeding and all sanity
+ * checks required by SP800-90A
+ *
+ * @drbg memory of state -- if NULL, new memory is allocated
+ * @pers Personalization string that is mixed into state, may be NULL -- note
+ *	 the entropy is pulled by the DRBG internally unconditionally
+ *	 as defined in SP800-90A. The additional input is mixed into
+ *	 the state in addition to the pulled entropy.
+ * @coreref reference to core
+ * @pr prediction resistance enabled
+ *
+ * return
+ *	0 on success
+ *	error value otherwise
+ */
+static int drbg_instantiate(struct drbg_state *drbg, struct drbg_string *pers,
+			    int coreref, bool pr)
+{
+	int ret = -ENOMEM;
+
+	pr_devel("DRBG: Initializing DRBG core %d with prediction resistance "
+		 "%s\n", coreref, pr ? "enabled" : "disabled");
+	drbg->core = &drbg_cores[coreref];
+	drbg->pr = pr;
+	drbg->seeded = false;
+	switch (drbg->core->flags & DRBG_TYPE_MASK) {
+#ifdef CONFIG_CRYPTO_DRBG_HMAC
+	case DRBG_HMAC:
+		drbg->d_ops = &drbg_hmac_ops;
+		break;
+#endif /* CONFIG_CRYPTO_DRBG_HMAC */
+#ifdef CONFIG_CRYPTO_DRBG_HASH
+	case DRBG_HASH:
+		drbg->d_ops = &drbg_hash_ops;
+		break;
+#endif /* CONFIG_CRYPTO_DRBG_HASH */
+#ifdef CONFIG_CRYPTO_DRBG_CTR
+	case DRBG_CTR:
+		drbg->d_ops = &drbg_ctr_ops;
+		break;
+#endif /* CONFIG_CRYPTO_DRBG_CTR */
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* 9.1 step 1 is implicit with the selected DRBG type */
+
+	/*
+	 * 9.1 step 2 is implicit as caller can select prediction resistance
+	 * and the flag is copied into drbg->flags --
+	 * all DRBG types support prediction resistance
+	 */
+
+	/* 9.1 step 4 is implicit in  drbg_sec_strength */
+
+	ret = drbg_alloc_state(drbg);
+	if (ret)
+		return ret;
+
+	ret = -EFAULT;
+	if (drbg->d_ops->crypto_init && drbg->d_ops->crypto_init(drbg))
+		goto err;
+	ret = drbg_seed(drbg, pers, false);
+	if (drbg->d_ops->crypto_fini)
+		drbg->d_ops->crypto_fini(drbg);
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	drbg_dealloc_state(drbg);
+	return ret;
+}
+
+/*
+ * DRBG uninstantiate function as required by SP800-90A - this function
+ * frees all buffers and the DRBG handle
+ *
+ * @drbg DRBG state handle
+ *
+ * return
+ *	0 on success
+ */
+static int drbg_uninstantiate(struct drbg_state *drbg)
+{
+	spin_lock_bh(&drbg->drbg_lock);
+	drbg_dealloc_state(drbg);
+	/* no scrubbing of test_data -- this shall survive an uninstantiate */
+	spin_unlock_bh(&drbg->drbg_lock);
+	return 0;
+}
+
+/*
+ * Helper function for setting the test data in the DRBG
+ *
+ * @drbg DRBG state handle
+ * @test_data test data to sets
+ */
+static inline void drbg_set_testdata(struct drbg_state *drbg,
+				     struct drbg_test_data *test_data)
+{
+	if (!test_data || !test_data->testentropy)
+		return;
+	spin_lock_bh(&drbg->drbg_lock);
+	drbg->test_data = test_data;
+	spin_unlock_bh(&drbg->drbg_lock);
+}
+
+/***************************************************************
+ * Kernel crypto API cipher invocations requested by DRBG
+ ***************************************************************/
+
+#if defined(CONFIG_CRYPTO_DRBG_HASH) || defined(CONFIG_CRYPTO_DRBG_HMAC)
+struct sdesc {
+	struct shash_desc shash;
+	char ctx[];
+};
+
+static int drbg_init_hash_kernel(struct drbg_state *drbg)
+{
+	struct sdesc *sdesc;
+	struct crypto_shash *tfm;
+
+	tfm = crypto_alloc_shash(drbg->core->backend_cra_name, 0, 0);
+	if (IS_ERR(tfm)) {
+		pr_info("DRBG: could not allocate digest TFM handle\n");
+		return PTR_ERR(tfm);
+	}
+	BUG_ON(drbg_blocklen(drbg) != crypto_shash_digestsize(tfm));
+	sdesc = kzalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
+			GFP_KERNEL);
+	if (!sdesc) {
+		crypto_free_shash(tfm);
+		return -ENOMEM;
+	}
+
+	sdesc->shash.tfm = tfm;
+	sdesc->shash.flags = 0;
+	drbg->priv_data = sdesc;
+	return 0;
+}
+
+static int drbg_fini_hash_kernel(struct drbg_state *drbg)
+{
+	struct sdesc *sdesc = (struct sdesc *)drbg->priv_data;
+	if (sdesc) {
+		crypto_free_shash(sdesc->shash.tfm);
+		kzfree(sdesc);
+	}
+	drbg->priv_data = NULL;
+	return 0;
+}
+
+static int drbg_kcapi_hash(struct drbg_state *drbg, const unsigned char *key,
+			   unsigned char *outval, const struct list_head *in)
+{
+	struct sdesc *sdesc = (struct sdesc *)drbg->priv_data;
+	struct drbg_string *input = NULL;
+
+	if (key)
+		crypto_shash_setkey(sdesc->shash.tfm, key, drbg_statelen(drbg));
+	crypto_shash_init(&sdesc->shash);
+	list_for_each_entry(input, in, list)
+		crypto_shash_update(&sdesc->shash, input->buf, input->len);
+	return crypto_shash_final(&sdesc->shash, outval);
+}
+#endif /* (CONFIG_CRYPTO_DRBG_HASH || CONFIG_CRYPTO_DRBG_HMAC) */
+
+#ifdef CONFIG_CRYPTO_DRBG_CTR
+static int drbg_init_sym_kernel(struct drbg_state *drbg)
+{
+	int ret = 0;
+	struct crypto_blkcipher *tfm;
+
+	tfm = crypto_alloc_blkcipher(drbg->core->backend_cra_name, 0, 0);
+	if (IS_ERR(tfm)) {
+		pr_info("DRBG: could not allocate cipher TFM handle\n");
+		return PTR_ERR(tfm);
+	}
+	BUG_ON(drbg_blocklen(drbg) != crypto_blkcipher_blocksize(tfm));
+	drbg->priv_data = tfm;
+	return ret;
+}
+
+static int drbg_fini_sym_kernel(struct drbg_state *drbg)
+{
+	struct crypto_blkcipher *tfm =
+		(struct crypto_blkcipher *)drbg->priv_data;
+	if (tfm)
+		crypto_free_blkcipher(tfm);
+	drbg->priv_data = NULL;
+	return 0;
+}
+
+static int drbg_kcapi_sym(struct drbg_state *drbg, const unsigned char *key,
+			  unsigned char *outval, const struct drbg_string *in)
+{
+	int ret = 0;
+	struct scatterlist sg_in, sg_out;
+	struct blkcipher_desc desc;
+	struct crypto_blkcipher *tfm =
+		(struct crypto_blkcipher *)drbg->priv_data;
+
+	desc.tfm = tfm;
+	desc.flags = 0;
+	crypto_blkcipher_setkey(tfm, key, (drbg_keylen(drbg)));
+	/* there is only component in *in */
+	sg_init_one(&sg_in, in->buf, in->len);
+	sg_init_one(&sg_out, outval, drbg_blocklen(drbg));
+	ret = crypto_blkcipher_encrypt(&desc, &sg_out, &sg_in, in->len);
+
+	return ret;
+}
+#endif /* CONFIG_CRYPTO_DRBG_CTR */
+
+/***************************************************************
+ * Kernel crypto API interface to register DRBG
+ ***************************************************************/
+
+/*
+ * Look up the DRBG flags by given kernel crypto API cra_name
+ * The code uses the drbg_cores definition to do this
+ *
+ * @cra_name kernel crypto API cra_name
+ * @coreref reference to integer which is filled with the pointer to
+ *  the applicable core
+ * @pr reference for setting prediction resistance
+ *
+ * return: flags
+ */
+static inline void drbg_convert_tfm_core(const char *cra_driver_name,
+					 int *coreref, bool *pr)
+{
+	int i = 0;
+	size_t start = 0;
+	int len = 0;
+
+	*pr = true;
+	/* disassemble the names */
+	if (!memcmp(cra_driver_name, "drbg_nopr_", 10)) {
+		start = 10;
+		*pr = false;
+	} else if (!memcmp(cra_driver_name, "drbg_pr_", 8)) {
+		start = 8;
+	} else {
+		return;
+	}
+
+	/* remove the first part */
+	len = strlen(cra_driver_name) - start;
+	for (i = 0; ARRAY_SIZE(drbg_cores) > i; i++) {
+		if (!memcmp(cra_driver_name + start, drbg_cores[i].cra_name,
+			    len)) {
+			*coreref = i;
+			return;
+		}
+	}
+}
+
+static int drbg_kcapi_init(struct crypto_tfm *tfm)
+{
+	struct drbg_state *drbg = crypto_tfm_ctx(tfm);
+	bool pr = false;
+	int coreref = 0;
+
+	drbg_convert_tfm_core(crypto_tfm_alg_driver_name(tfm), &coreref, &pr);
+	/*
+	 * when personalization string is needed, the caller must call reset
+	 * and provide the personalization string as seed information
+	 */
+	return drbg_instantiate(drbg, NULL, coreref, pr);
+}
+
+static void drbg_kcapi_cleanup(struct crypto_tfm *tfm)
+{
+	drbg_uninstantiate(crypto_tfm_ctx(tfm));
+}
+
+/*
+ * Generate random numbers invoked by the kernel crypto API:
+ * The API of the kernel crypto API is extended as follows:
+ *
+ * If dlen is larger than zero, rdata is interpreted as the output buffer
+ * where random data is to be stored.
+ *
+ * If dlen is zero, rdata is interpreted as a pointer to a struct drbg_gen
+ * which holds the additional information string that is used for the
+ * DRBG generation process. The output buffer that is to be used to store
+ * data is also pointed to by struct drbg_gen.
+ */
+static int drbg_kcapi_random(struct crypto_rng *tfm, u8 *rdata,
+			     unsigned int dlen)
+{
+	struct drbg_state *drbg = crypto_rng_ctx(tfm);
+	if (0 < dlen) {
+		return drbg_generate_long(drbg, rdata, dlen, NULL);
+	} else {
+		struct drbg_gen *data = (struct drbg_gen *)rdata;
+		struct drbg_string addtl;
+		/* catch NULL pointer */
+		if (!data)
+			return 0;
+		drbg_set_testdata(drbg, data->test_data);
+		/* linked list variable is now local to allow modification */
+		drbg_string_fill(&addtl, data->addtl->buf, data->addtl->len);
+		return drbg_generate_long(drbg, data->outbuf, data->outlen,
+					  &addtl);
+	}
+}
+
+/*
+ * Reset the DRBG invoked by the kernel crypto API
+ * The reset implies a full re-initialization of the DRBG. Similar to the
+ * generate function of drbg_kcapi_random, this function extends the
+ * kernel crypto API interface with struct drbg_gen
+ */
+static int drbg_kcapi_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
+{
+	struct drbg_state *drbg = crypto_rng_ctx(tfm);
+	struct crypto_tfm *tfm_base = crypto_rng_tfm(tfm);
+	bool pr = false;
+	struct drbg_string seed_string;
+	int coreref = 0;
+
+	drbg_uninstantiate(drbg);
+	drbg_convert_tfm_core(crypto_tfm_alg_driver_name(tfm_base), &coreref,
+			      &pr);
+	if (0 < slen) {
+		drbg_string_fill(&seed_string, seed, slen);
+		return drbg_instantiate(drbg, &seed_string, coreref, pr);
+	} else {
+		struct drbg_gen *data = (struct drbg_gen *)seed;
+		/* allow invocation of API call with NULL, 0 */
+		if (!data)
+			return drbg_instantiate(drbg, NULL, coreref, pr);
+		drbg_set_testdata(drbg, data->test_data);
+		/* linked list variable is now local to allow modification */
+		drbg_string_fill(&seed_string, data->addtl->buf,
+				 data->addtl->len);
+		return drbg_instantiate(drbg, &seed_string, coreref, pr);
+	}
+}
+
+/***************************************************************
+ * Kernel module: code to load the module
+ ***************************************************************/
+
+/*
+ * Tests as defined in 11.3.2 in addition to the cipher tests: testing
+ * of the error handling.
+ *
+ * Note: testing of failing seed source as defined in 11.3.2 is not applicable
+ * as seed source of get_random_bytes does not fail.
+ *
+ * Note 2: There is no sensible way of testing the reseed counter
+ * enforcement, so skip it.
+ */
+static inline int __init drbg_healthcheck_sanity(void)
+{
+#ifdef CONFIG_CRYPTO_FIPS
+	int len = 0;
+#define OUTBUFLEN 16
+	unsigned char buf[OUTBUFLEN];
+	struct drbg_state *drbg = NULL;
+	int ret = -EFAULT;
+	int rc = -EFAULT;
+	bool pr = false;
+	int coreref = 0;
+	struct drbg_string addtl;
+	size_t max_addtllen, max_request_bytes;
+
+	/* only perform test in FIPS mode */
+	if (!fips_enabled)
+		return 0;
+
+#ifdef CONFIG_CRYPTO_DRBG_CTR
+	drbg_convert_tfm_core("drbg_nopr_ctr_aes128", &coreref, &pr);
+#elif defined CONFIG_CRYPTO_DRBG_HASH
+	drbg_convert_tfm_core("drbg_nopr_sha256", &coreref, &pr);
+#else
+	drbg_convert_tfm_core("drbg_nopr_hmac_sha256", &coreref, &pr);
+#endif
+
+	drbg = kzalloc(sizeof(struct drbg_state), GFP_KERNEL);
+	if (!drbg)
+		return -ENOMEM;
+
+	/*
+	 * if the following tests fail, it is likely that there is a buffer
+	 * overflow as buf is much smaller than the requested or provided
+	 * string lengths -- in case the error handling does not succeed
+	 * we may get an OOPS. And we want to get an OOPS as this is a
+	 * grave bug.
+	 */
+
+	/* get a valid instance of DRBG for following tests */
+	ret = drbg_instantiate(drbg, NULL, coreref, pr);
+	if (ret) {
+		rc = ret;
+		goto outbuf;
+	}
+	max_addtllen = drbg_max_addtl(drbg);
+	max_request_bytes = drbg_max_request_bytes(drbg);
+	drbg_string_fill(&addtl, buf, max_addtllen + 1);
+	/* overflow addtllen with additonal info string */
+	len = drbg_generate(drbg, buf, OUTBUFLEN, &addtl);
+	BUG_ON(0 < len);
+	/* overflow max_bits */
+	len = drbg_generate(drbg, buf, (max_request_bytes + 1), NULL);
+	BUG_ON(0 < len);
+	drbg_uninstantiate(drbg);
+
+	/* overflow max addtllen with personalization string */
+	ret = drbg_instantiate(drbg, &addtl, coreref, pr);
+	BUG_ON(0 == ret);
+	/* test uninstantated DRBG */
+	len = drbg_generate(drbg, buf, (max_request_bytes + 1), NULL);
+	BUG_ON(0 < len);
+	/* all tests passed */
+	rc = 0;
+
+	pr_devel("DRBG: Sanity tests for failure code paths successfully "
+		 "completed\n");
+
+	drbg_uninstantiate(drbg);
+outbuf:
+	kzfree(drbg);
+	return rc;
+#else /* CONFIG_CRYPTO_FIPS */
+	return 0;
+#endif /* CONFIG_CRYPTO_FIPS */
+}
+
+static struct crypto_alg drbg_algs[22];
+
+/*
+ * Fill the array drbg_algs used to register the different DRBGs
+ * with the kernel crypto API. To fill the array, the information
+ * from drbg_cores[] is used.
+ */
+static inline void __init drbg_fill_array(struct crypto_alg *alg,
+					  const struct drbg_core *core, int pr)
+{
+	int pos = 0;
+	static int priority = 100;
+
+	memset(alg, 0, sizeof(struct crypto_alg));
+	memcpy(alg->cra_name, "stdrng", 6);
+	if (pr) {
+		memcpy(alg->cra_driver_name, "drbg_pr_", 8);
+		pos = 8;
+	} else {
+		memcpy(alg->cra_driver_name, "drbg_nopr_", 10);
+		pos = 10;
+	}
+	memcpy(alg->cra_driver_name + pos, core->cra_name,
+	       strlen(core->cra_name));
+
+	alg->cra_priority = priority;
+	priority++;
+	/*
+	 * If FIPS mode enabled, the selected DRBG shall have the
+	 * highest cra_priority over other stdrng instances to ensure
+	 * it is selected.
+	 */
+	if (fips_enabled)
+		alg->cra_priority += 200;
+
+	alg->cra_flags		= CRYPTO_ALG_TYPE_RNG;
+	alg->cra_ctxsize 	= sizeof(struct drbg_state);
+	alg->cra_type		= &crypto_rng_type;
+	alg->cra_module		= THIS_MODULE;
+	alg->cra_init		= drbg_kcapi_init;
+	alg->cra_exit		= drbg_kcapi_cleanup;
+	alg->cra_u.rng.rng_make_random	= drbg_kcapi_random;
+	alg->cra_u.rng.rng_reset	= drbg_kcapi_reset;
+	alg->cra_u.rng.seedsize	= 0;
+}
+
+static int __init drbg_init(void)
+{
+	unsigned int i = 0; /* pointer to drbg_algs */
+	unsigned int j = 0; /* pointer to drbg_cores */
+	int ret = -EFAULT;
+
+	ret = drbg_healthcheck_sanity();
+	if (ret)
+		return ret;
+
+	if (ARRAY_SIZE(drbg_cores) * 2 > ARRAY_SIZE(drbg_algs)) {
+		pr_info("DRBG: Cannot register all DRBG types"
+			"(slots needed: %zu, slots available: %zu)\n",
+			ARRAY_SIZE(drbg_cores) * 2, ARRAY_SIZE(drbg_algs));
+		return ret;
+	}
+
+	/*
+	 * each DRBG definition can be used with PR and without PR, thus
+	 * we instantiate each DRBG in drbg_cores[] twice.
+	 *
+	 * As the order of placing them into the drbg_algs array matters
+	 * (the later DRBGs receive a higher cra_priority) we register the
+	 * prediction resistance DRBGs first as the should not be too
+	 * interesting.
+	 */
+	for (j = 0; ARRAY_SIZE(drbg_cores) > j; j++, i++)
+		drbg_fill_array(&drbg_algs[i], &drbg_cores[j], 1);
+	for (j = 0; ARRAY_SIZE(drbg_cores) > j; j++, i++)
+		drbg_fill_array(&drbg_algs[i], &drbg_cores[j], 0);
+	return crypto_register_algs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
+}
+
+static void __exit drbg_exit(void)
+{
+	crypto_unregister_algs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
+}
+
+module_init(drbg_init);
+module_exit(drbg_exit);
+#ifndef CRYPTO_DRBG_HASH_STRING
+#define CRYPTO_DRBG_HASH_STRING ""
+#endif
+#ifndef CRYPTO_DRBG_HMAC_STRING
+#define CRYPTO_DRBG_HMAC_STRING ""
+#endif
+#ifndef CRYPTO_DRBG_CTR_STRING
+#define CRYPTO_DRBG_CTR_STRING ""
+#endif
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Stephan Mueller <smueller@chronox.de>");
+MODULE_DESCRIPTION("NIST SP800-90A Deterministic Random Bit Generator (DRBG) "
+		   "using following cores: "
+		   CRYPTO_DRBG_HASH_STRING
+		   CRYPTO_DRBG_HMAC_STRING
+		   CRYPTO_DRBG_CTR_STRING);
diff --git a/crypto/eseqiv.c b/crypto/eseqiv.c
index 42ce9f570ae..bf7ab4a8949 100644
--- a/crypto/eseqiv.c
+++ b/crypto/eseqiv.c
@@ -68,7 +68,7 @@ static int eseqiv_givencrypt(struct skcipher_givcrypt_request *req)
 	struct eseqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
 	struct eseqiv_request_ctx *reqctx = skcipher_givcrypt_reqctx(req);
 	struct ablkcipher_request *subreq;
-	crypto_completion_t complete;
+	crypto_completion_t compl;
 	void *data;
 	struct scatterlist *osrc, *odst;
 	struct scatterlist *dst;
@@ -86,7 +86,7 @@ static int eseqiv_givencrypt(struct skcipher_givcrypt_request *req)
 	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
 
 	giv = req->giv;
-	complete = req->creq.base.complete;
+	compl = req->creq.base.complete;
 	data = req->creq.base.data;
 
 	osrc = req->creq.src;
@@ -101,11 +101,11 @@ static int eseqiv_givencrypt(struct skcipher_givcrypt_request *req)
 	if (vsrc != giv + ivsize && vdst != giv + ivsize) {
 		giv = PTR_ALIGN((u8 *)reqctx->tail,
 				crypto_ablkcipher_alignmask(geniv) + 1);
-		complete = eseqiv_complete;
+		compl = eseqiv_complete;
 		data = req;
 	}
 
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags, complete,
+	ablkcipher_request_set_callback(subreq, req->creq.base.flags, compl,
 					data);
 
 	sg_init_table(reqctx->src, 2);
diff --git a/crypto/gcm.c b/crypto/gcm.c
index b4f01793900..276cdac567b 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -228,14 +228,14 @@ static void gcm_hash_final_done(struct crypto_async_request *areq, int err);
 
 static int gcm_hash_update(struct aead_request *req,
 			   struct crypto_gcm_req_priv_ctx *pctx,
-			   crypto_completion_t complete,
+			   crypto_completion_t compl,
 			   struct scatterlist *src,
 			   unsigned int len)
 {
 	struct ahash_request *ahreq = &pctx->u.ahreq;
 
 	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   complete, req);
+				   compl, req);
 	ahash_request_set_crypt(ahreq, src, NULL, len);
 
 	return crypto_ahash_update(ahreq);
@@ -244,12 +244,12 @@ static int gcm_hash_update(struct aead_request *req,
 static int gcm_hash_remain(struct aead_request *req,
 			   struct crypto_gcm_req_priv_ctx *pctx,
 			   unsigned int remain,
-			   crypto_completion_t complete)
+			   crypto_completion_t compl)
 {
 	struct ahash_request *ahreq = &pctx->u.ahreq;
 
 	ahash_request_set_callback(ahreq, aead_request_flags(req),
-				   complete, req);
+				   compl, req);
 	sg_init_one(pctx->src, gcm_zeroes, remain);
 	ahash_request_set_crypt(ahreq, pctx->src, NULL, remain);
 
@@ -375,14 +375,14 @@ static void __gcm_hash_assoc_remain_done(struct aead_request *req, int err)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
-	crypto_completion_t complete;
+	crypto_completion_t compl;
 	unsigned int remain = 0;
 
 	if (!err && gctx->cryptlen) {
 		remain = gcm_remain(gctx->cryptlen);
-		complete = remain ? gcm_hash_crypt_done :
+		compl = remain ? gcm_hash_crypt_done :
 			gcm_hash_crypt_remain_done;
-		err = gcm_hash_update(req, pctx, complete,
+		err = gcm_hash_update(req, pctx, compl,
 				      gctx->src, gctx->cryptlen);
 		if (err == -EINPROGRESS || err == -EBUSY)
 			return;
@@ -429,14 +429,14 @@ static void gcm_hash_assoc_done(struct crypto_async_request *areq, int err)
 static void __gcm_hash_init_done(struct aead_request *req, int err)
 {
 	struct crypto_gcm_req_priv_ctx *pctx = crypto_gcm_reqctx(req);
-	crypto_completion_t complete;
+	crypto_completion_t compl;
 	unsigned int remain = 0;
 
 	if (!err && req->assoclen) {
 		remain = gcm_remain(req->assoclen);
-		complete = remain ? gcm_hash_assoc_done :
+		compl = remain ? gcm_hash_assoc_done :
 			gcm_hash_assoc_remain_done;
-		err = gcm_hash_update(req, pctx, complete,
+		err = gcm_hash_update(req, pctx, compl,
 				      req->assoc, req->assoclen);
 		if (err == -EINPROGRESS || err == -EBUSY)
 			return;
@@ -462,7 +462,7 @@ static int gcm_hash(struct aead_request *req,
 	struct crypto_gcm_ghash_ctx *gctx = &pctx->ghash_ctx;
 	struct crypto_gcm_ctx *ctx = crypto_tfm_ctx(req->base.tfm);
 	unsigned int remain;
-	crypto_completion_t complete;
+	crypto_completion_t compl;
 	int err;
 
 	ahash_request_set_tfm(ahreq, ctx->ghash);
@@ -473,8 +473,8 @@ static int gcm_hash(struct aead_request *req,
 	if (err)
 		return err;
 	remain = gcm_remain(req->assoclen);
-	complete = remain ? gcm_hash_assoc_done : gcm_hash_assoc_remain_done;
-	err = gcm_hash_update(req, pctx, complete, req->assoc, req->assoclen);
+	compl = remain ? gcm_hash_assoc_done : gcm_hash_assoc_remain_done;
+	err = gcm_hash_update(req, pctx, compl, req->assoc, req->assoclen);
 	if (err)
 		return err;
 	if (remain) {
@@ -484,8 +484,8 @@ static int gcm_hash(struct aead_request *req,
 			return err;
 	}
 	remain = gcm_remain(gctx->cryptlen);
-	complete = remain ? gcm_hash_crypt_done : gcm_hash_crypt_remain_done;
-	err = gcm_hash_update(req, pctx, complete, gctx->src, gctx->cryptlen);
+	compl = remain ? gcm_hash_crypt_done : gcm_hash_crypt_remain_done;
+	err = gcm_hash_update(req, pctx, compl, gctx->src, gctx->cryptlen);
 	if (err)
 		return err;
 	if (remain) {
diff --git a/crypto/lzo.c b/crypto/lzo.c
index 1c2aa69c54b..a8ff2f778dc 100644
--- a/crypto/lzo.c
+++ b/crypto/lzo.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/crypto.h>
 #include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <linux/lzo.h>
 
 struct lzo_ctx {
@@ -30,7 +31,10 @@ static int lzo_init(struct crypto_tfm *tfm)
 {
 	struct lzo_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	ctx->lzo_comp_mem = vmalloc(LZO1X_MEM_COMPRESS);
+	ctx->lzo_comp_mem = kmalloc(LZO1X_MEM_COMPRESS,
+				    GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	if (!ctx->lzo_comp_mem)
+		ctx->lzo_comp_mem = vmalloc(LZO1X_MEM_COMPRESS);
 	if (!ctx->lzo_comp_mem)
 		return -ENOMEM;
 
@@ -41,7 +45,7 @@ static void lzo_exit(struct crypto_tfm *tfm)
 {
 	struct lzo_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	vfree(ctx->lzo_comp_mem);
+	kvfree(ctx->lzo_comp_mem);
 }
 
 static int lzo_compress(struct crypto_tfm *tfm, const u8 *src,
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index f2cba4ed6f2..ee190fcedcd 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -100,7 +100,7 @@ static int seqiv_givencrypt(struct skcipher_givcrypt_request *req)
 	struct crypto_ablkcipher *geniv = skcipher_givcrypt_reqtfm(req);
 	struct seqiv_ctx *ctx = crypto_ablkcipher_ctx(geniv);
 	struct ablkcipher_request *subreq = skcipher_givcrypt_reqctx(req);
-	crypto_completion_t complete;
+	crypto_completion_t compl;
 	void *data;
 	u8 *info;
 	unsigned int ivsize;
@@ -108,7 +108,7 @@ static int seqiv_givencrypt(struct skcipher_givcrypt_request *req)
 
 	ablkcipher_request_set_tfm(subreq, skcipher_geniv_cipher(geniv));
 
-	complete = req->creq.base.complete;
+	compl = req->creq.base.complete;
 	data = req->creq.base.data;
 	info = req->creq.info;
 
@@ -122,11 +122,11 @@ static int seqiv_givencrypt(struct skcipher_givcrypt_request *req)
 		if (!info)
 			return -ENOMEM;
 
-		complete = seqiv_complete;
+		compl = seqiv_complete;
 		data = req;
 	}
 
-	ablkcipher_request_set_callback(subreq, req->creq.base.flags, complete,
+	ablkcipher_request_set_callback(subreq, req->creq.base.flags, compl,
 					data);
 	ablkcipher_request_set_crypt(subreq, req->creq.src, req->creq.dst,
 				     req->creq.nbytes, info);
@@ -146,7 +146,7 @@ static int seqiv_aead_givencrypt(struct aead_givcrypt_request *req)
 	struct seqiv_ctx *ctx = crypto_aead_ctx(geniv);
 	struct aead_request *areq = &req->areq;
 	struct aead_request *subreq = aead_givcrypt_reqctx(req);
-	crypto_completion_t complete;
+	crypto_completion_t compl;
 	void *data;
 	u8 *info;
 	unsigned int ivsize;
@@ -154,7 +154,7 @@ static int seqiv_aead_givencrypt(struct aead_givcrypt_request *req)
 
 	aead_request_set_tfm(subreq, aead_geniv_base(geniv));
 
-	complete = areq->base.complete;
+	compl = areq->base.complete;
 	data = areq->base.data;
 	info = areq->iv;
 
@@ -168,11 +168,11 @@ static int seqiv_aead_givencrypt(struct aead_givcrypt_request *req)
 		if (!info)
 			return -ENOMEM;
 
-		complete = seqiv_aead_complete;
+		compl = seqiv_aead_complete;
 		data = req;
 	}
 
-	aead_request_set_callback(subreq, areq->base.flags, complete, data);
+	aead_request_set_callback(subreq, areq->base.flags, compl, data);
 	aead_request_set_crypt(subreq, areq->src, areq->dst, areq->cryptlen,
 			       info);
 	aead_request_set_assoc(subreq, areq->assoc, areq->assoclen);
diff --git a/crypto/shash.c b/crypto/shash.c
index 929058a6856..47c713954bf 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -67,7 +67,8 @@ EXPORT_SYMBOL_GPL(crypto_shash_setkey);
 static inline unsigned int shash_align_buffer_size(unsigned len,
 						   unsigned long mask)
 {
-	return len + (mask & ~(__alignof__(u8 __attribute__ ((aligned))) - 1));
+	typedef u8 __attribute__ ((aligned)) u8_aligned;
+	return len + (mask & ~(__alignof__(u8_aligned) - 1));
 }
 
 static int shash_update_unaligned(struct shash_desc *desc, const u8 *data,
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index ba247cf3085..890449e6e7e 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -48,6 +48,11 @@
 #define DECRYPT 0
 
 /*
+ * return a string with the driver name
+ */
+#define get_driver_name(tfm_type, tfm) crypto_tfm_alg_driver_name(tfm_type ## _tfm(tfm))
+
+/*
  * Used by test_cipher_speed()
  */
 static unsigned int sec;
@@ -68,13 +73,13 @@ static char *check[] = {
 };
 
 static int test_cipher_jiffies(struct blkcipher_desc *desc, int enc,
-			       struct scatterlist *sg, int blen, int sec)
+			       struct scatterlist *sg, int blen, int secs)
 {
 	unsigned long start, end;
 	int bcount;
 	int ret;
 
-	for (start = jiffies, end = start + sec * HZ, bcount = 0;
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
 		if (enc)
 			ret = crypto_blkcipher_encrypt(desc, sg, sg, blen);
@@ -86,7 +91,7 @@ static int test_cipher_jiffies(struct blkcipher_desc *desc, int enc,
 	}
 
 	printk("%d operations in %d seconds (%ld bytes)\n",
-	       bcount, sec, (long)bcount * blen);
+	       bcount, secs, (long)bcount * blen);
 	return 0;
 }
 
@@ -138,13 +143,13 @@ out:
 }
 
 static int test_aead_jiffies(struct aead_request *req, int enc,
-				int blen, int sec)
+				int blen, int secs)
 {
 	unsigned long start, end;
 	int bcount;
 	int ret;
 
-	for (start = jiffies, end = start + sec * HZ, bcount = 0;
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
 		if (enc)
 			ret = crypto_aead_encrypt(req);
@@ -156,7 +161,7 @@ static int test_aead_jiffies(struct aead_request *req, int enc,
 	}
 
 	printk("%d operations in %d seconds (%ld bytes)\n",
-	       bcount, sec, (long)bcount * blen);
+	       bcount, secs, (long)bcount * blen);
 	return 0;
 }
 
@@ -260,7 +265,7 @@ static void sg_init_aead(struct scatterlist *sg, char *xbuf[XBUFSIZE],
 	}
 }
 
-static void test_aead_speed(const char *algo, int enc, unsigned int sec,
+static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 			    struct aead_speed_template *template,
 			    unsigned int tcount, u8 authsize,
 			    unsigned int aad_size, u8 *keysize)
@@ -305,9 +310,6 @@ static void test_aead_speed(const char *algo, int enc, unsigned int sec,
 	asg = &sg[8];
 	sgout = &asg[8];
 
-
-	printk(KERN_INFO "\ntesting speed of %s %s\n", algo, e);
-
 	tfm = crypto_alloc_aead(algo, 0, 0);
 
 	if (IS_ERR(tfm)) {
@@ -316,6 +318,9 @@ static void test_aead_speed(const char *algo, int enc, unsigned int sec,
 		goto out_notfm;
 	}
 
+	printk(KERN_INFO "\ntesting speed of %s (%s) %s\n", algo,
+			get_driver_name(crypto_aead, tfm), e);
+
 	req = aead_request_alloc(tfm, GFP_KERNEL);
 	if (!req) {
 		pr_err("alg: aead: Failed to allocate request for %s\n",
@@ -374,8 +379,9 @@ static void test_aead_speed(const char *algo, int enc, unsigned int sec,
 			aead_request_set_crypt(req, sg, sgout, *b_size, iv);
 			aead_request_set_assoc(req, asg, aad_size);
 
-			if (sec)
-				ret = test_aead_jiffies(req, enc, *b_size, sec);
+			if (secs)
+				ret = test_aead_jiffies(req, enc, *b_size,
+							secs);
 			else
 				ret = test_aead_cycles(req, enc, *b_size);
 
@@ -405,7 +411,7 @@ out_noxbuf:
 	return;
 }
 
-static void test_cipher_speed(const char *algo, int enc, unsigned int sec,
+static void test_cipher_speed(const char *algo, int enc, unsigned int secs,
 			      struct cipher_speed_template *template,
 			      unsigned int tcount, u8 *keysize)
 {
@@ -422,8 +428,6 @@ static void test_cipher_speed(const char *algo, int enc, unsigned int sec,
 	else
 		e = "decryption";
 
-	printk("\ntesting speed of %s %s\n", algo, e);
-
 	tfm = crypto_alloc_blkcipher(algo, 0, CRYPTO_ALG_ASYNC);
 
 	if (IS_ERR(tfm)) {
@@ -434,6 +438,9 @@ static void test_cipher_speed(const char *algo, int enc, unsigned int sec,
 	desc.tfm = tfm;
 	desc.flags = 0;
 
+	printk(KERN_INFO "\ntesting speed of %s (%s) %s\n", algo,
+			get_driver_name(crypto_blkcipher, tfm), e);
+
 	i = 0;
 	do {
 
@@ -483,9 +490,9 @@ static void test_cipher_speed(const char *algo, int enc, unsigned int sec,
 				crypto_blkcipher_set_iv(tfm, iv, iv_len);
 			}
 
-			if (sec)
+			if (secs)
 				ret = test_cipher_jiffies(&desc, enc, sg,
-							  *b_size, sec);
+							  *b_size, secs);
 			else
 				ret = test_cipher_cycles(&desc, enc, sg,
 							 *b_size);
@@ -506,13 +513,13 @@ out:
 
 static int test_hash_jiffies_digest(struct hash_desc *desc,
 				    struct scatterlist *sg, int blen,
-				    char *out, int sec)
+				    char *out, int secs)
 {
 	unsigned long start, end;
 	int bcount;
 	int ret;
 
-	for (start = jiffies, end = start + sec * HZ, bcount = 0;
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
 		ret = crypto_hash_digest(desc, sg, blen, out);
 		if (ret)
@@ -520,22 +527,22 @@ static int test_hash_jiffies_digest(struct hash_desc *desc,
 	}
 
 	printk("%6u opers/sec, %9lu bytes/sec\n",
-	       bcount / sec, ((long)bcount * blen) / sec);
+	       bcount / secs, ((long)bcount * blen) / secs);
 
 	return 0;
 }
 
 static int test_hash_jiffies(struct hash_desc *desc, struct scatterlist *sg,
-			     int blen, int plen, char *out, int sec)
+			     int blen, int plen, char *out, int secs)
 {
 	unsigned long start, end;
 	int bcount, pcount;
 	int ret;
 
 	if (plen == blen)
-		return test_hash_jiffies_digest(desc, sg, blen, out, sec);
+		return test_hash_jiffies_digest(desc, sg, blen, out, secs);
 
-	for (start = jiffies, end = start + sec * HZ, bcount = 0;
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
 		ret = crypto_hash_init(desc);
 		if (ret)
@@ -552,7 +559,7 @@ static int test_hash_jiffies(struct hash_desc *desc, struct scatterlist *sg,
 	}
 
 	printk("%6u opers/sec, %9lu bytes/sec\n",
-	       bcount / sec, ((long)bcount * blen) / sec);
+	       bcount / secs, ((long)bcount * blen) / secs);
 
 	return 0;
 }
@@ -673,7 +680,7 @@ static void test_hash_sg_init(struct scatterlist *sg)
 	}
 }
 
-static void test_hash_speed(const char *algo, unsigned int sec,
+static void test_hash_speed(const char *algo, unsigned int secs,
 			    struct hash_speed *speed)
 {
 	struct scatterlist sg[TVMEMSIZE];
@@ -683,8 +690,6 @@ static void test_hash_speed(const char *algo, unsigned int sec,
 	int i;
 	int ret;
 
-	printk(KERN_INFO "\ntesting speed of %s\n", algo);
-
 	tfm = crypto_alloc_hash(algo, 0, CRYPTO_ALG_ASYNC);
 
 	if (IS_ERR(tfm)) {
@@ -693,6 +698,9 @@ static void test_hash_speed(const char *algo, unsigned int sec,
 		return;
 	}
 
+	printk(KERN_INFO "\ntesting speed of %s (%s)\n", algo,
+			get_driver_name(crypto_hash, tfm));
+
 	desc.tfm = tfm;
 	desc.flags = 0;
 
@@ -718,9 +726,9 @@ static void test_hash_speed(const char *algo, unsigned int sec,
 		       "(%5u byte blocks,%5u bytes per update,%4u updates): ",
 		       i, speed[i].blen, speed[i].plen, speed[i].blen / speed[i].plen);
 
-		if (sec)
+		if (secs)
 			ret = test_hash_jiffies(&desc, sg, speed[i].blen,
-						speed[i].plen, output, sec);
+						speed[i].plen, output, secs);
 		else
 			ret = test_hash_cycles(&desc, sg, speed[i].blen,
 					       speed[i].plen, output);
@@ -765,13 +773,13 @@ static inline int do_one_ahash_op(struct ahash_request *req, int ret)
 }
 
 static int test_ahash_jiffies_digest(struct ahash_request *req, int blen,
-				     char *out, int sec)
+				     char *out, int secs)
 {
 	unsigned long start, end;
 	int bcount;
 	int ret;
 
-	for (start = jiffies, end = start + sec * HZ, bcount = 0;
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
 		ret = do_one_ahash_op(req, crypto_ahash_digest(req));
 		if (ret)
@@ -779,22 +787,22 @@ static int test_ahash_jiffies_digest(struct ahash_request *req, int blen,
 	}
 
 	printk("%6u opers/sec, %9lu bytes/sec\n",
-	       bcount / sec, ((long)bcount * blen) / sec);
+	       bcount / secs, ((long)bcount * blen) / secs);
 
 	return 0;
 }
 
 static int test_ahash_jiffies(struct ahash_request *req, int blen,
-			      int plen, char *out, int sec)
+			      int plen, char *out, int secs)
 {
 	unsigned long start, end;
 	int bcount, pcount;
 	int ret;
 
 	if (plen == blen)
-		return test_ahash_jiffies_digest(req, blen, out, sec);
+		return test_ahash_jiffies_digest(req, blen, out, secs);
 
-	for (start = jiffies, end = start + sec * HZ, bcount = 0;
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
 		ret = crypto_ahash_init(req);
 		if (ret)
@@ -811,7 +819,7 @@ static int test_ahash_jiffies(struct ahash_request *req, int blen,
 	}
 
 	pr_cont("%6u opers/sec, %9lu bytes/sec\n",
-		bcount / sec, ((long)bcount * blen) / sec);
+		bcount / secs, ((long)bcount * blen) / secs);
 
 	return 0;
 }
@@ -911,7 +919,7 @@ out:
 	return 0;
 }
 
-static void test_ahash_speed(const char *algo, unsigned int sec,
+static void test_ahash_speed(const char *algo, unsigned int secs,
 			     struct hash_speed *speed)
 {
 	struct scatterlist sg[TVMEMSIZE];
@@ -921,8 +929,6 @@ static void test_ahash_speed(const char *algo, unsigned int sec,
 	static char output[1024];
 	int i, ret;
 
-	printk(KERN_INFO "\ntesting speed of async %s\n", algo);
-
 	tfm = crypto_alloc_ahash(algo, 0, 0);
 	if (IS_ERR(tfm)) {
 		pr_err("failed to load transform for %s: %ld\n",
@@ -930,6 +936,9 @@ static void test_ahash_speed(const char *algo, unsigned int sec,
 		return;
 	}
 
+	printk(KERN_INFO "\ntesting speed of async %s (%s)\n", algo,
+			get_driver_name(crypto_ahash, tfm));
+
 	if (crypto_ahash_digestsize(tfm) > sizeof(output)) {
 		pr_err("digestsize(%u) > outputbuffer(%zu)\n",
 		       crypto_ahash_digestsize(tfm), sizeof(output));
@@ -960,9 +969,9 @@ static void test_ahash_speed(const char *algo, unsigned int sec,
 
 		ahash_request_set_crypt(req, sg, output, speed[i].plen);
 
-		if (sec)
+		if (secs)
 			ret = test_ahash_jiffies(req, speed[i].blen,
-						 speed[i].plen, output, sec);
+						 speed[i].plen, output, secs);
 		else
 			ret = test_ahash_cycles(req, speed[i].blen,
 						speed[i].plen, output);
@@ -994,13 +1003,13 @@ static inline int do_one_acipher_op(struct ablkcipher_request *req, int ret)
 }
 
 static int test_acipher_jiffies(struct ablkcipher_request *req, int enc,
-				int blen, int sec)
+				int blen, int secs)
 {
 	unsigned long start, end;
 	int bcount;
 	int ret;
 
-	for (start = jiffies, end = start + sec * HZ, bcount = 0;
+	for (start = jiffies, end = start + secs * HZ, bcount = 0;
 	     time_before(jiffies, end); bcount++) {
 		if (enc)
 			ret = do_one_acipher_op(req,
@@ -1014,7 +1023,7 @@ static int test_acipher_jiffies(struct ablkcipher_request *req, int enc,
 	}
 
 	pr_cont("%d operations in %d seconds (%ld bytes)\n",
-		bcount, sec, (long)bcount * blen);
+		bcount, secs, (long)bcount * blen);
 	return 0;
 }
 
@@ -1065,7 +1074,7 @@ out:
 	return ret;
 }
 
-static void test_acipher_speed(const char *algo, int enc, unsigned int sec,
+static void test_acipher_speed(const char *algo, int enc, unsigned int secs,
 			       struct cipher_speed_template *template,
 			       unsigned int tcount, u8 *keysize)
 {
@@ -1083,8 +1092,6 @@ static void test_acipher_speed(const char *algo, int enc, unsigned int sec,
 	else
 		e = "decryption";
 
-	pr_info("\ntesting speed of async %s %s\n", algo, e);
-
 	init_completion(&tresult.completion);
 
 	tfm = crypto_alloc_ablkcipher(algo, 0, 0);
@@ -1095,6 +1102,9 @@ static void test_acipher_speed(const char *algo, int enc, unsigned int sec,
 		return;
 	}
 
+	pr_info("\ntesting speed of async %s (%s) %s\n", algo,
+			get_driver_name(crypto_ablkcipher, tfm), e);
+
 	req = ablkcipher_request_alloc(tfm, GFP_KERNEL);
 	if (!req) {
 		pr_err("tcrypt: skcipher: Failed to allocate request for %s\n",
@@ -1168,9 +1178,9 @@ static void test_acipher_speed(const char *algo, int enc, unsigned int sec,
 
 			ablkcipher_request_set_crypt(req, sg, sg, *b_size, iv);
 
-			if (sec)
+			if (secs)
 				ret = test_acipher_jiffies(req, enc,
-							   *b_size, sec);
+							   *b_size, secs);
 			else
 				ret = test_acipher_cycles(req, enc,
 							  *b_size);
@@ -1585,6 +1595,12 @@ static int do_test(int m)
 		test_cipher_speed("cbc(des3_ede)", DECRYPT, sec,
 				des3_speed_template, DES3_SPEED_VECTORS,
 				speed_template_24);
+		test_cipher_speed("ctr(des3_ede)", ENCRYPT, sec,
+				des3_speed_template, DES3_SPEED_VECTORS,
+				speed_template_24);
+		test_cipher_speed("ctr(des3_ede)", DECRYPT, sec,
+				des3_speed_template, DES3_SPEED_VECTORS,
+				speed_template_24);
 		break;
 
 	case 202:
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 498649ac195..ac2b63105af 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -27,6 +27,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <crypto/rng.h>
+#include <crypto/drbg.h>
 
 #include "internal.h"
 
@@ -108,6 +109,11 @@ struct cprng_test_suite {
 	unsigned int count;
 };
 
+struct drbg_test_suite {
+	struct drbg_testvec *vecs;
+	unsigned int count;
+};
+
 struct alg_test_desc {
 	const char *alg;
 	int (*test)(const struct alg_test_desc *desc, const char *driver,
@@ -121,6 +127,7 @@ struct alg_test_desc {
 		struct pcomp_test_suite pcomp;
 		struct hash_test_suite hash;
 		struct cprng_test_suite cprng;
+		struct drbg_test_suite drbg;
 	} suite;
 };
 
@@ -191,13 +198,20 @@ static int __test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
 	const char *algo = crypto_tfm_alg_driver_name(crypto_ahash_tfm(tfm));
 	unsigned int i, j, k, temp;
 	struct scatterlist sg[8];
-	char result[64];
+	char *result;
+	char *key;
 	struct ahash_request *req;
 	struct tcrypt_result tresult;
 	void *hash_buff;
 	char *xbuf[XBUFSIZE];
 	int ret = -ENOMEM;
 
+	result = kmalloc(MAX_DIGEST_SIZE, GFP_KERNEL);
+	if (!result)
+		return ret;
+	key = kmalloc(MAX_KEYLEN, GFP_KERNEL);
+	if (!key)
+		goto out_nobuf;
 	if (testmgr_alloc_buf(xbuf))
 		goto out_nobuf;
 
@@ -222,7 +236,7 @@ static int __test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
 			goto out;
 
 		j++;
-		memset(result, 0, 64);
+		memset(result, 0, MAX_DIGEST_SIZE);
 
 		hash_buff = xbuf[0];
 		hash_buff += align_offset;
@@ -232,8 +246,14 @@ static int __test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
 
 		if (template[i].ksize) {
 			crypto_ahash_clear_flags(tfm, ~0);
-			ret = crypto_ahash_setkey(tfm, template[i].key,
-						  template[i].ksize);
+			if (template[i].ksize > MAX_KEYLEN) {
+				pr_err("alg: hash: setkey failed on test %d for %s: key size %d > %d\n",
+				       j, algo, template[i].ksize, MAX_KEYLEN);
+				ret = -EINVAL;
+				goto out;
+			}
+			memcpy(key, template[i].key, template[i].ksize);
+			ret = crypto_ahash_setkey(tfm, key, template[i].ksize);
 			if (ret) {
 				printk(KERN_ERR "alg: hash: setkey failed on "
 				       "test %d for %s: ret=%d\n", j, algo,
@@ -293,7 +313,7 @@ static int __test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
 
 		if (template[i].np) {
 			j++;
-			memset(result, 0, 64);
+			memset(result, 0, MAX_DIGEST_SIZE);
 
 			temp = 0;
 			sg_init_table(sg, template[i].np);
@@ -312,8 +332,16 @@ static int __test_hash(struct crypto_ahash *tfm, struct hash_testvec *template,
 			}
 
 			if (template[i].ksize) {
+				if (template[i].ksize > MAX_KEYLEN) {
+					pr_err("alg: hash: setkey failed on test %d for %s: key size %d > %d\n",
+					       j, algo, template[i].ksize,
+					       MAX_KEYLEN);
+					ret = -EINVAL;
+					goto out;
+				}
 				crypto_ahash_clear_flags(tfm, ~0);
-				ret = crypto_ahash_setkey(tfm, template[i].key,
+				memcpy(key, template[i].key, template[i].ksize);
+				ret = crypto_ahash_setkey(tfm, key,
 							  template[i].ksize);
 
 				if (ret) {
@@ -365,6 +393,8 @@ out:
 out_noreq:
 	testmgr_free_buf(xbuf);
 out_nobuf:
+	kfree(key);
+	kfree(result);
 	return ret;
 }
 
@@ -422,6 +452,9 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 	iv = kzalloc(MAX_IVLEN, GFP_KERNEL);
 	if (!iv)
 		return ret;
+	key = kmalloc(MAX_KEYLEN, GFP_KERNEL);
+	if (!key)
+		goto out_noxbuf;
 	if (testmgr_alloc_buf(xbuf))
 		goto out_noxbuf;
 	if (testmgr_alloc_buf(axbuf))
@@ -486,7 +519,14 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 				crypto_aead_set_flags(
 					tfm, CRYPTO_TFM_REQ_WEAK_KEY);
 
-			key = template[i].key;
+			if (template[i].klen > MAX_KEYLEN) {
+				pr_err("alg: aead%s: setkey failed on test %d for %s: key size %d > %d\n",
+				       d, j, algo, template[i].klen,
+				       MAX_KEYLEN);
+				ret = -EINVAL;
+				goto out;
+			}
+			memcpy(key, template[i].key, template[i].klen);
 
 			ret = crypto_aead_setkey(tfm, key,
 						 template[i].klen);
@@ -587,7 +627,14 @@ static int __test_aead(struct crypto_aead *tfm, int enc,
 			if (template[i].wk)
 				crypto_aead_set_flags(
 					tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-			key = template[i].key;
+			if (template[i].klen > MAX_KEYLEN) {
+				pr_err("alg: aead%s: setkey failed on test %d for %s: key size %d > %d\n",
+				       d, j, algo, template[i].klen,
+				       MAX_KEYLEN);
+				ret = -EINVAL;
+				goto out;
+			}
+			memcpy(key, template[i].key, template[i].klen);
 
 			ret = crypto_aead_setkey(tfm, key, template[i].klen);
 			if (!ret == template[i].fail) {
@@ -769,6 +816,7 @@ out_nooutbuf:
 out_noaxbuf:
 	testmgr_free_buf(xbuf);
 out_noxbuf:
+	kfree(key);
 	kfree(iv);
 	return ret;
 }
@@ -1715,6 +1763,100 @@ static int alg_test_cprng(const struct alg_test_desc *desc, const char *driver,
 	return err;
 }
 
+
+static int drbg_cavs_test(struct drbg_testvec *test, int pr,
+			  const char *driver, u32 type, u32 mask)
+{
+	int ret = -EAGAIN;
+	struct crypto_rng *drng;
+	struct drbg_test_data test_data;
+	struct drbg_string addtl, pers, testentropy;
+	unsigned char *buf = kzalloc(test->expectedlen, GFP_KERNEL);
+
+	if (!buf)
+		return -ENOMEM;
+
+	drng = crypto_alloc_rng(driver, type, mask);
+	if (IS_ERR(drng)) {
+		printk(KERN_ERR "alg: drbg: could not allocate DRNG handle for "
+		       "%s\n", driver);
+		kzfree(buf);
+		return -ENOMEM;
+	}
+
+	test_data.testentropy = &testentropy;
+	drbg_string_fill(&testentropy, test->entropy, test->entropylen);
+	drbg_string_fill(&pers, test->pers, test->perslen);
+	ret = crypto_drbg_reset_test(drng, &pers, &test_data);
+	if (ret) {
+		printk(KERN_ERR "alg: drbg: Failed to reset rng\n");
+		goto outbuf;
+	}
+
+	drbg_string_fill(&addtl, test->addtla, test->addtllen);
+	if (pr) {
+		drbg_string_fill(&testentropy, test->entpra, test->entprlen);
+		ret = crypto_drbg_get_bytes_addtl_test(drng,
+			buf, test->expectedlen, &addtl,	&test_data);
+	} else {
+		ret = crypto_drbg_get_bytes_addtl(drng,
+			buf, test->expectedlen, &addtl);
+	}
+	if (ret <= 0) {
+		printk(KERN_ERR "alg: drbg: could not obtain random data for "
+		       "driver %s\n", driver);
+		goto outbuf;
+	}
+
+	drbg_string_fill(&addtl, test->addtlb, test->addtllen);
+	if (pr) {
+		drbg_string_fill(&testentropy, test->entprb, test->entprlen);
+		ret = crypto_drbg_get_bytes_addtl_test(drng,
+			buf, test->expectedlen, &addtl, &test_data);
+	} else {
+		ret = crypto_drbg_get_bytes_addtl(drng,
+			buf, test->expectedlen, &addtl);
+	}
+	if (ret <= 0) {
+		printk(KERN_ERR "alg: drbg: could not obtain random data for "
+		       "driver %s\n", driver);
+		goto outbuf;
+	}
+
+	ret = memcmp(test->expected, buf, test->expectedlen);
+
+outbuf:
+	crypto_free_rng(drng);
+	kzfree(buf);
+	return ret;
+}
+
+
+static int alg_test_drbg(const struct alg_test_desc *desc, const char *driver,
+			 u32 type, u32 mask)
+{
+	int err = 0;
+	int pr = 0;
+	int i = 0;
+	struct drbg_testvec *template = desc->suite.drbg.vecs;
+	unsigned int tcount = desc->suite.drbg.count;
+
+	if (0 == memcmp(driver, "drbg_pr_", 8))
+		pr = 1;
+
+	for (i = 0; i < tcount; i++) {
+		err = drbg_cavs_test(&template[i], pr, driver, type, mask);
+		if (err) {
+			printk(KERN_ERR "alg: drbg: Test %d failed for %s\n",
+			       i, driver);
+			err = -EINVAL;
+			break;
+		}
+	}
+	return err;
+
+}
+
 static int alg_test_null(const struct alg_test_desc *desc,
 			     const char *driver, u32 type, u32 mask)
 {
@@ -2458,6 +2600,152 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.alg = "digest_null",
 		.test = alg_test_null,
 	}, {
+		.alg = "drbg_nopr_ctr_aes128",
+		.test = alg_test_drbg,
+		.fips_allowed = 1,
+		.suite = {
+			.drbg = {
+				.vecs = drbg_nopr_ctr_aes128_tv_template,
+				.count = ARRAY_SIZE(drbg_nopr_ctr_aes128_tv_template)
+			}
+		}
+	}, {
+		.alg = "drbg_nopr_ctr_aes192",
+		.test = alg_test_drbg,
+		.fips_allowed = 1,
+		.suite = {
+			.drbg = {
+				.vecs = drbg_nopr_ctr_aes192_tv_template,
+				.count = ARRAY_SIZE(drbg_nopr_ctr_aes192_tv_template)
+			}
+		}
+	}, {
+		.alg = "drbg_nopr_ctr_aes256",
+		.test = alg_test_drbg,
+		.fips_allowed = 1,
+		.suite = {
+			.drbg = {
+				.vecs = drbg_nopr_ctr_aes256_tv_template,
+				.count = ARRAY_SIZE(drbg_nopr_ctr_aes256_tv_template)
+			}
+		}
+	}, {
+		/*
+		 * There is no need to specifically test the DRBG with every
+		 * backend cipher -- covered by drbg_nopr_hmac_sha256 test
+		 */
+		.alg = "drbg_nopr_hmac_sha1",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_nopr_hmac_sha256",
+		.test = alg_test_drbg,
+		.fips_allowed = 1,
+		.suite = {
+			.drbg = {
+				.vecs = drbg_nopr_hmac_sha256_tv_template,
+				.count =
+				ARRAY_SIZE(drbg_nopr_hmac_sha256_tv_template)
+			}
+		}
+	}, {
+		/* covered by drbg_nopr_hmac_sha256 test */
+		.alg = "drbg_nopr_hmac_sha384",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_nopr_hmac_sha512",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
+		.alg = "drbg_nopr_sha1",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_nopr_sha256",
+		.test = alg_test_drbg,
+		.fips_allowed = 1,
+		.suite = {
+			.drbg = {
+				.vecs = drbg_nopr_sha256_tv_template,
+				.count = ARRAY_SIZE(drbg_nopr_sha256_tv_template)
+			}
+		}
+	}, {
+		/* covered by drbg_nopr_sha256 test */
+		.alg = "drbg_nopr_sha384",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_nopr_sha512",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_pr_ctr_aes128",
+		.test = alg_test_drbg,
+		.fips_allowed = 1,
+		.suite = {
+			.drbg = {
+				.vecs = drbg_pr_ctr_aes128_tv_template,
+				.count = ARRAY_SIZE(drbg_pr_ctr_aes128_tv_template)
+			}
+		}
+	}, {
+		/* covered by drbg_pr_ctr_aes128 test */
+		.alg = "drbg_pr_ctr_aes192",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_pr_ctr_aes256",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_pr_hmac_sha1",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_pr_hmac_sha256",
+		.test = alg_test_drbg,
+		.fips_allowed = 1,
+		.suite = {
+			.drbg = {
+				.vecs = drbg_pr_hmac_sha256_tv_template,
+				.count = ARRAY_SIZE(drbg_pr_hmac_sha256_tv_template)
+			}
+		}
+	}, {
+		/* covered by drbg_pr_hmac_sha256 test */
+		.alg = "drbg_pr_hmac_sha384",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_pr_hmac_sha512",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
+		.alg = "drbg_pr_sha1",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_pr_sha256",
+		.test = alg_test_drbg,
+		.fips_allowed = 1,
+		.suite = {
+			.drbg = {
+				.vecs = drbg_pr_sha256_tv_template,
+				.count = ARRAY_SIZE(drbg_pr_sha256_tv_template)
+			}
+		}
+	}, {
+		/* covered by drbg_pr_sha256 test */
+		.alg = "drbg_pr_sha384",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
+		.alg = "drbg_pr_sha512",
+		.fips_allowed = 1,
+		.test = alg_test_null,
+	}, {
 		.alg = "ecb(__aes-aesni)",
 		.test = alg_test_null,
 		.fips_allowed = 1,
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 69d0dd8ef27..6597203eccf 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -32,7 +32,7 @@
 #define MAX_DIGEST_SIZE		64
 #define MAX_TAP			8
 
-#define MAX_KEYLEN		56
+#define MAX_KEYLEN		160
 #define MAX_IVLEN		32
 
 struct hash_testvec {
@@ -92,6 +92,21 @@ struct cprng_testvec {
 	unsigned short loops;
 };
 
+struct drbg_testvec {
+	unsigned char *entropy;
+	size_t entropylen;
+	unsigned char *entpra;
+	unsigned char *entprb;
+	size_t entprlen;
+	unsigned char *addtla;
+	unsigned char *addtlb;
+	size_t addtllen;
+	unsigned char *pers;
+	size_t perslen;
+	unsigned char *expected;
+	size_t expectedlen;
+};
+
 static char zeroed_string[48];
 
 /*
@@ -1807,18 +1822,59 @@ static struct hash_testvec tgr128_tv_template[] = {
 	},
 };
 
-#define GHASH_TEST_VECTORS 1
+#define GHASH_TEST_VECTORS 5
 
 static struct hash_testvec ghash_tv_template[] =
 {
 	{
-
-		.key	= "\xdf\xa6\xbf\x4d\xed\x81\xdb\x03\xff\xca\xff\x95\xf8\x30\xf0\x61",
+		.key	= "\xdf\xa6\xbf\x4d\xed\x81\xdb\x03"
+			  "\xff\xca\xff\x95\xf8\x30\xf0\x61",
 		.ksize	= 16,
-		.plaintext = "\x95\x2b\x2a\x56\xa5\x60\x04a\xc0\xb3\x2b\x66\x56\xa0\x5b\x40\xb6",
+		.plaintext = "\x95\x2b\x2a\x56\xa5\x60\x04a\xc0"
+			     "\xb3\x2b\x66\x56\xa0\x5b\x40\xb6",
 		.psize	= 16,
 		.digest	= "\xda\x53\xeb\x0a\xd2\xc5\x5b\xb6"
 			  "\x4f\xc4\x80\x2c\xc3\xfe\xda\x60",
+	}, {
+		.key	= "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b"
+			  "\x0b\x0b\x0b\x0b\x0b\x0b\x0b\x0b",
+		.ksize	= 16,
+		.plaintext = "what do ya want for nothing?",
+		.psize	= 28,
+		.digest	= "\x3e\x1f\x5c\x4d\x65\xf0\xef\xce"
+			  "\x0d\x61\x06\x27\x66\x51\xd5\xe2",
+		.np	= 2,
+		.tap	= {14, 14}
+	}, {
+		.key	= "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa"
+			  "\xaa\xaa\xaa\xaa\xaa\xaa\xaa\xaa",
+		.ksize	= 16,
+		.plaintext = "\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd"
+			"\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd"
+			"\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd"
+			"\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd\xdd",
+		.psize	= 50,
+		.digest	= "\xfb\x49\x8a\x36\xe1\x96\xe1\x96"
+			  "\xe1\x96\xe1\x96\xe1\x96\xe1\x96",
+	}, {
+		.key	= "\xda\x53\xeb\x0a\xd2\xc5\x5b\xb6"
+			  "\x4f\xc4\x80\x2c\xc3\xfe\xda\x60",
+		.ksize	= 16,
+		.plaintext = "\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd"
+			"\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd"
+			"\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd"
+			"\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd",
+		.psize	= 50,
+		.digest	= "\x2b\x5c\x0c\x7f\x52\xd1\x60\xc2"
+			  "\x49\xed\x6e\x32\x7a\xa9\xbe\x08",
+	}, {
+		.key	= "\x95\x2b\x2a\x56\xa5\x60\x04a\xc0"
+			  "\xb3\x2b\x66\x56\xa0\x5b\x40\xb6",
+		.ksize	= 16,
+		.plaintext = "Test With Truncation",
+		.psize	= 20,
+		.digest	= "\xf8\x94\x87\x2a\x4b\x63\x99\x28"
+			  "\x23\xf7\x93\xf7\x19\xf5\x96\xd9",
 	},
 };
 
@@ -3097,8 +3153,8 @@ static struct cipher_testvec des_enc_tv_template[] = {
 			  "\x5F\x62\xC7\x72\xD9\xFC\xCB\x9A",
 		.rlen	= 248,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 248 - 8, 8 },
+		.np	= 3,
+		.tap	= { 248 - 10, 2, 8 },
 	},
 };
 
@@ -3207,8 +3263,8 @@ static struct cipher_testvec des_dec_tv_template[] = {
 			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB",
 		.rlen	= 248,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 248 - 8, 8 },
+		.np	= 3,
+		.tap	= { 248 - 10, 2, 8 },
 	},
 };
 
@@ -3333,8 +3389,8 @@ static struct cipher_testvec des_cbc_enc_tv_template[] = {
 			  "\xC6\x4A\xF3\x55\xC7\x29\x2E\x63",
 		.rlen	= 248,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 248 - 8, 8 },
+		.np	= 3,
+		.tap	= { 248 - 10, 2, 8 },
 	},
 };
 
@@ -3442,8 +3498,8 @@ static struct cipher_testvec des_cbc_dec_tv_template[] = {
 			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB",
 		.rlen	= 248,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 248 - 8, 8 },
+		.np	= 3,
+		.tap	= { 248 - 10, 2, 8 },
 	},
 };
 
@@ -3517,8 +3573,8 @@ static struct cipher_testvec des_ctr_enc_tv_template[] = {
 			  "\x69\x74\xA1\x06\x46\x0F\x4E\x75",
 		.rlen	= 248,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 248 - 8, 8 },
+		.np	= 3,
+		.tap	= { 248 - 10, 2, 8 },
 	}, { /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
 		.klen	= 8,
@@ -3663,8 +3719,8 @@ static struct cipher_testvec des_ctr_dec_tv_template[] = {
 			  "\xC6\x2F\xBB\x24\x8D\x19\x82\xEB",
 		.rlen	= 248,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 248 - 8, 8 },
+		.np	= 3,
+		.tap	= { 248 - 10, 2, 8 },
 	}, { /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55",
 		.klen	= 8,
@@ -3899,8 +3955,8 @@ static struct cipher_testvec des3_ede_enc_tv_template[] = {
 			  "\xD8\x45\xFF\x33\xBA\xBB\x2B\x63",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -4064,8 +4120,8 @@ static struct cipher_testvec des3_ede_dec_tv_template[] = {
 			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -4244,8 +4300,8 @@ static struct cipher_testvec des3_ede_cbc_enc_tv_template[] = {
 			  "\x95\x63\x73\xA2\x44\xAC\xF8\xA5",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -4424,8 +4480,8 @@ static struct cipher_testvec des3_ede_cbc_dec_tv_template[] = {
 			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -4564,8 +4620,8 @@ static struct cipher_testvec des3_ede_ctr_enc_tv_template[] = {
 			  "\x5C\xEE\xFC\xCF\xC4\x70\x00\x34",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	}, { /* Generated with Crypto++ */
 		.key	= "\x9C\xD6\xF3\x9C\xB9\x5A\x67\x00"
 			  "\x5A\x67\x00\x2D\xCE\xEB\x2D\xCE"
@@ -4842,8 +4898,8 @@ static struct cipher_testvec des3_ede_ctr_dec_tv_template[] = {
 			  "\xB8\x03\xEA\x7D\xE1\x48\xD3\x47",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	}, { /* Generated with Crypto++ */
 		.key	= "\x9C\xD6\xF3\x9C\xB9\x5A\x67\x00"
 			  "\x5A\x67\x00\x2D\xCE\xEB\x2D\xCE"
@@ -5182,8 +5238,8 @@ static struct cipher_testvec bf_enc_tv_template[] = {
 			  "\xC9\x1A\xFB\x5D\xDE\xBB\x43\xF4",
 		.rlen	= 504,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 504 - 8, 8 },
+		.np	= 3,
+		.tap	= { 504 - 10, 2, 8 },
 	},
 };
 
@@ -5374,8 +5430,8 @@ static struct cipher_testvec bf_dec_tv_template[] = {
 			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
 		.rlen	= 504,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 504 - 8, 8 },
+		.np	= 3,
+		.tap	= { 504 - 10, 2, 8 },
 	},
 };
 
@@ -5531,8 +5587,8 @@ static struct cipher_testvec bf_cbc_enc_tv_template[] = {
 			  "\xB4\x98\xD8\x6B\x74\xE7\x65\xF4",
 		.rlen	= 504,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 504 - 8, 8 },
+		.np	= 3,
+		.tap	= { 504 - 10, 2, 8 },
 	},
 };
 
@@ -5688,8 +5744,8 @@ static struct cipher_testvec bf_cbc_dec_tv_template[] = {
 			  "\x2B\xC2\x59\xF0\x64\xFB\x92\x06",
 		.rlen	= 504,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 504 - 8, 8 },
+		.np	= 3,
+		.tap	= { 504 - 10, 2, 8 },
 	},
 };
 
@@ -6694,8 +6750,8 @@ static struct cipher_testvec tf_enc_tv_template[] = {
 			  "\x2C\x75\x64\xC4\xCA\xC1\x7E\xD5",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -6862,8 +6918,8 @@ static struct cipher_testvec tf_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -7045,8 +7101,8 @@ static struct cipher_testvec tf_cbc_enc_tv_template[] = {
 			  "\x0A\xA3\x30\x10\x26\x25\x41\x2C",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -7228,8 +7284,8 @@ static struct cipher_testvec tf_cbc_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -8302,8 +8358,8 @@ static struct cipher_testvec tf_lrw_enc_tv_template[] = {
 			  "\x11\xd7\xb8\x6e\xea\xe1\x80\x30",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -8555,8 +8611,8 @@ static struct cipher_testvec tf_lrw_dec_tv_template[] = {
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -8897,8 +8953,8 @@ static struct cipher_testvec tf_xts_enc_tv_template[] = {
 			  "\x37\x30\xe1\x91\x8d\xb3\x2a\xff",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -9240,8 +9296,8 @@ static struct cipher_testvec tf_xts_dec_tv_template[] = {
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -9438,8 +9494,8 @@ static struct cipher_testvec serpent_enc_tv_template[] = {
 			  "\xF4\x46\x2E\xEB\xAC\xF3\xD2\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -9664,8 +9720,8 @@ static struct cipher_testvec serpent_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -9846,8 +9902,8 @@ static struct cipher_testvec serpent_cbc_enc_tv_template[] = {
 			  "\xBC\x08\x3A\xA2\x29\xB3\xDF\xD1",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -9987,8 +10043,8 @@ static struct cipher_testvec serpent_cbc_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -11061,8 +11117,8 @@ static struct cipher_testvec serpent_lrw_enc_tv_template[] = {
 			  "\xd9\x51\x0f\xd7\x94\x2f\xc5\xa7",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -11314,8 +11370,8 @@ static struct cipher_testvec serpent_lrw_dec_tv_template[] = {
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -11656,8 +11712,8 @@ static struct cipher_testvec serpent_xts_enc_tv_template[] = {
 			  "\xd4\xa0\x91\x98\x11\x5f\x4d\xb1",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -11999,8 +12055,8 @@ static struct cipher_testvec serpent_xts_dec_tv_template[] = {
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -12182,8 +12238,8 @@ static struct cipher_testvec cast6_enc_tv_template[] = {
 			  "\x11\x74\x93\x57\xB4\x7E\xC6\x00",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -12353,8 +12409,8 @@ static struct cipher_testvec cast6_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -12494,8 +12550,8 @@ static struct cipher_testvec cast6_cbc_enc_tv_template[] = {
 			  "\x22\x46\x89\x2D\x0F\x2B\x08\x24",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -12635,8 +12691,8 @@ static struct cipher_testvec cast6_cbc_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -12792,8 +12848,8 @@ static struct cipher_testvec cast6_ctr_enc_tv_template[] = {
 			  "\xF9\xC5\xDD\x27\xB3\x39\xCB\xCB",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -12949,8 +13005,8 @@ static struct cipher_testvec cast6_ctr_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -13096,8 +13152,8 @@ static struct cipher_testvec cast6_lrw_enc_tv_template[] = {
 			  "\xC4\xF5\x99\x61\xBC\xBB\x5B\x46",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -13243,8 +13299,8 @@ static struct cipher_testvec cast6_lrw_dec_tv_template[] = {
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -13392,8 +13448,8 @@ static struct cipher_testvec cast6_xts_enc_tv_template[] = {
 			  "\x22\x60\x4E\xE8\xA4\x5D\x85\xB9",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -13541,8 +13597,8 @@ static struct cipher_testvec cast6_xts_dec_tv_template[] = {
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -13749,8 +13805,8 @@ static struct cipher_testvec aes_enc_tv_template[] = {
 			  "\x17\xBB\xC0\x6B\x62\x3F\x56\xE9",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -13921,8 +13977,8 @@ static struct cipher_testvec aes_dec_tv_template[] = {
 			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -14140,8 +14196,8 @@ static struct cipher_testvec aes_cbc_enc_tv_template[] = {
 			  "\xA3\xAA\x13\xCC\x50\xFF\x7B\x02",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -14359,8 +14415,8 @@ static struct cipher_testvec aes_cbc_dec_tv_template[] = {
 			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -16265,8 +16321,8 @@ static struct cipher_testvec aes_lrw_enc_tv_template[] = {
 			  "\x74\x3f\x7d\x58\x88\x75\xde\x3e",
 		.rlen   = 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	}
 };
 
@@ -16519,8 +16575,8 @@ static struct cipher_testvec aes_lrw_dec_tv_template[] = {
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
 		.rlen   = 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	}
 };
 
@@ -16861,8 +16917,8 @@ static struct cipher_testvec aes_xts_enc_tv_template[] = {
 			  "\xb9\xc6\xe6\x93\xe1\x48\xc1\x51",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	}
 };
 
@@ -17203,8 +17259,8 @@ static struct cipher_testvec aes_xts_dec_tv_template[] = {
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	}
 };
 
@@ -17420,8 +17476,8 @@ static struct cipher_testvec aes_ctr_enc_tv_template[] = {
 			  "\xF1\x4C\xE5\xB2\x91\x64\x0C\x51",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	}, { /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55"
 			  "\x0F\x32\x55\x78\x9B\xBE\x78\x9B"
@@ -17775,8 +17831,8 @@ static struct cipher_testvec aes_ctr_dec_tv_template[] = {
 			  "\xED\x56\xBF\x28\xB4\x1D\x86\x12",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	}, { /* Generated with Crypto++ */
 		.key	= "\xC9\x83\xA6\xC9\xEC\x0F\x32\x55"
 			  "\x0F\x32\x55\x78\x9B\xBE\x78\x9B"
@@ -20743,6 +20799,834 @@ static struct cprng_testvec ansi_cprng_aes_tv_template[] = {
 	},
 };
 
+/*
+ * SP800-90A DRBG Test vectors from
+ * http://csrc.nist.gov/groups/STM/cavp/documents/drbg/drbgtestvectors.zip
+ *
+ * Test vectors for DRBG with prediction resistance. All types of DRBGs
+ * (Hash, HMAC, CTR) are tested with all permutations of use cases (w/ and
+ * w/o personalization string, w/ and w/o additional input string).
+ */
+static struct drbg_testvec drbg_pr_sha256_tv_template[] = {
+	{
+		.entropy = (unsigned char *)
+			"\x72\x88\x4c\xcd\x6c\x85\x57\x70\xf7\x0b\x8b\x86"
+			"\xc1\xeb\xd2\x4e\x36\x14\xab\x18\xc4\x9c\xc9\xcf"
+			"\x1a\xe8\xf7\x7b\x02\x49\x73\xd7\xf1\x42\x7d\xc6"
+			"\x3f\x29\x2d\xec\xd3\x66\x51\x3f\x1d\x8d\x5b\x4e",
+		.entropylen = 48,
+		.entpra = (unsigned char *)
+			"\x38\x9c\x91\xfa\xc2\xa3\x46\x89\x56\x08\x3f\x62"
+			"\x73\xd5\x22\xa9\x29\x63\x3a\x1d\xe5\x5d\x5e\x4f"
+			"\x67\xb0\x67\x7a\x5e\x9e\x0c\x62",
+		.entprb = (unsigned char *)
+			"\xb2\x8f\x36\xb2\xf6\x8d\x39\x13\xfa\x6c\x66\xcf"
+			"\x62\x8a\x7e\x8c\x12\x33\x71\x9c\x69\xe4\xa5\xf0"
+			"\x8c\xee\xeb\x9c\xf5\x31\x98\x31",
+		.entprlen = 32,
+		.expected = (unsigned char *)
+			"\x52\x7b\xa3\xad\x71\x77\xa4\x49\x42\x04\x61\xc7"
+			"\xf0\xaf\xa5\xfd\xd3\xb3\x0d\x6a\x61\xba\x35\x49"
+			"\xbb\xaa\xaf\xe4\x25\x7d\xb5\x48\xaf\x5c\x18\x3d"
+			"\x33\x8d\x9d\x45\xdf\x98\xd5\x94\xa8\xda\x92\xfe"
+			"\xc4\x3c\x94\x2a\xcf\x7f\x7b\xf2\xeb\x28\xa9\xf1"
+			"\xe0\x86\x30\xa8\xfe\xf2\x48\x90\x91\x0c\x75\xb5"
+			"\x3c\x00\xf0\x4d\x09\x4f\x40\xa7\xa2\x8c\x52\xdf"
+			"\x52\xef\x17\xbf\x3d\xd1\xa2\x31\xb4\xb8\xdc\xe6"
+			"\x5b\x0d\x1f\x78\x36\xb4\xe6\x4b\xa7\x11\x25\xd5"
+			"\x94\xc6\x97\x36\xab\xf0\xe5\x31\x28\x6a\xbb\xce"
+			"\x30\x81\xa6\x8f\x27\x14\xf8\x1c",
+		.expectedlen = 128,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\x5d\xf2\x14\xbc\xf6\xb5\x4e\x0b\xf0\x0d\x6f\x2d"
+			"\xe2\x01\x66\x7b\xd0\xa4\x73\xa4\x21\xdd\xb0\xc0"
+			"\x51\x79\x09\xf4\xea\xa9\x08\xfa\xa6\x67\xe0\xe1"
+			"\xd1\x88\xa8\xad\xee\x69\x74\xb3\x55\x06\x9b\xf6",
+		.entropylen = 48,
+		.entpra = (unsigned char *)
+			"\xef\x48\x06\xa2\xc2\x45\xf1\x44\xfa\x34\x2c\xeb"
+			"\x8d\x78\x3c\x09\x8f\x34\x72\x20\xf2\xe7\xfd\x13"
+			"\x76\x0a\xf6\xdc\x3c\xf5\xc0\x15",
+		.entprb = (unsigned char *)
+			"\x4b\xbe\xe5\x24\xed\x6a\x2d\x0c\xdb\x73\x5e\x09"
+			"\xf9\xad\x67\x7c\x51\x47\x8b\x6b\x30\x2a\xc6\xde"
+			"\x76\xaa\x55\x04\x8b\x0a\x72\x95",
+		.entprlen = 32,
+		.expected = (unsigned char *)
+			"\x3b\x14\x71\x99\xa1\xda\xa0\x42\xe6\xc8\x85\x32"
+			"\x70\x20\x32\x53\x9a\xbe\xd1\x1e\x15\xef\xfb\x4c"
+			"\x25\x6e\x19\x3a\xf0\xb9\xcb\xde\xf0\x3b\xc6\x18"
+			"\x4d\x85\x5a\x9b\xf1\xe3\xc2\x23\x03\x93\x08\xdb"
+			"\xa7\x07\x4b\x33\x78\x40\x4d\xeb\x24\xf5\x6e\x81"
+			"\x4a\x1b\x6e\xa3\x94\x52\x43\xb0\xaf\x2e\x21\xf4"
+			"\x42\x46\x8e\x90\xed\x34\x21\x75\xea\xda\x67\xb6"
+			"\xe4\xf6\xff\xc6\x31\x6c\x9a\x5a\xdb\xb3\x97\x13"
+			"\x09\xd3\x20\x98\x33\x2d\x6d\xd7\xb5\x6a\xa8\xa9"
+			"\x9a\x5b\xd6\x87\x52\xa1\x89\x2b\x4b\x9c\x64\x60"
+			"\x50\x47\xa3\x63\x81\x16\xaf\x19",
+		.expectedlen = 128,
+		.addtla = (unsigned char *)
+			"\xbe\x13\xdb\x2a\xe9\xa8\xfe\x09\x97\xe1\xce\x5d"
+			"\xe8\xbb\xc0\x7c\x4f\xcb\x62\x19\x3f\x0f\xd2\xad"
+			"\xa9\xd0\x1d\x59\x02\xc4\xff\x70",
+		.addtlb = (unsigned char *)
+			"\x6f\x96\x13\xe2\xa7\xf5\x6c\xfe\xdf\x66\xe3\x31"
+			"\x63\x76\xbf\x20\x27\x06\x49\xf1\xf3\x01\x77\x41"
+			"\x9f\xeb\xe4\x38\xfe\x67\x00\xcd",
+		.addtllen = 32,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\xc6\x1c\xaf\x83\xa2\x56\x38\xf9\xb0\xbc\xd9\x85"
+			"\xf5\x2e\xc4\x46\x9c\xe1\xb9\x40\x98\x70\x10\x72"
+			"\xd7\x7d\x15\x85\xa1\x83\x5a\x97\xdf\xc8\xa8\xe8"
+			"\x03\x4c\xcb\x70\x35\x8b\x90\x94\x46\x8a\x6e\xa1",
+		.entropylen = 48,
+		.entpra = (unsigned char *)
+			"\xc9\x05\xa4\xcf\x28\x80\x4b\x93\x0f\x8b\xc6\xf9"
+			"\x09\x41\x58\x74\xe9\xec\x28\xc7\x53\x0a\x73\x60"
+			"\xba\x0a\xde\x57\x5b\x4b\x9f\x29",
+		.entprb = (unsigned char *)
+			"\x4f\x31\xd2\xeb\xac\xfa\xa8\xe2\x01\x7d\xf3\xbd"
+			"\x42\xbd\x20\xa0\x30\x65\x74\xd5\x5d\xd2\xad\xa4"
+			"\xa9\xeb\x1f\x4d\xf6\xfd\xb8\x26",
+		.entprlen = 32,
+		.expected = (unsigned char *)
+			"\xf6\x13\x05\xcb\x83\x60\x16\x42\x49\x1d\xc6\x25"
+			"\x3b\x8c\x31\xa3\xbe\x8b\xbd\x1c\xe2\xec\x1d\xde"
+			"\xbb\xbf\xa1\xac\xa8\x9f\x50\xce\x69\xce\xef\xd5"
+			"\xd6\xf2\xef\x6a\xf7\x81\x38\xdf\xbc\xa7\x5a\xb9"
+			"\xb2\x42\x65\xab\xe4\x86\x8d\x2d\x9d\x59\x99\x2c"
+			"\x5a\x0d\x71\x55\x98\xa4\x45\xc2\x8d\xdb\x05\x5e"
+			"\x50\x21\xf7\xcd\xe8\x98\x43\xce\x57\x74\x63\x4c"
+			"\xf3\xb1\xa5\x14\x1e\x9e\x01\xeb\x54\xd9\x56\xae"
+			"\xbd\xb6\x6f\x1a\x47\x6b\x3b\x44\xe4\xa2\xe9\x3c"
+			"\x6c\x83\x12\x30\xb8\x78\x7f\x8e\x54\x82\xd4\xfe"
+			"\x90\x35\x0d\x4c\x4d\x85\xe7\x13",
+		.expectedlen = 128,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = (unsigned char *)
+			"\xa5\xbf\xac\x4f\x71\xa1\xbb\x67\x94\xc6\x50\xc7"
+			"\x2a\x45\x9e\x10\xa8\xed\xf7\x52\x4f\xfe\x21\x90"
+			"\xa4\x1b\xe1\xe2\x53\xcc\x61\x47",
+		.perslen = 32,
+	}, {
+		.entropy = (unsigned char *)
+			"\xb6\xc1\x8d\xdf\x99\x54\xbe\x95\x10\x48\xd9\xf6"
+			"\xd7\x48\xa8\x73\x2d\x74\xde\x1e\xde\x57\x7e\xf4"
+			"\x7b\x7b\x64\xef\x88\x7a\xa8\x10\x4b\xe1\xc1\x87"
+			"\xbb\x0b\xe1\x39\x39\x50\xaf\x68\x9c\xa2\xbf\x5e",
+		.entropylen = 48,
+		.entpra = (unsigned char *)
+			"\xdc\x81\x0a\x01\x58\xa7\x2e\xce\xee\x48\x8c\x7c"
+			"\x77\x9e\x3c\xf1\x17\x24\x7a\xbb\xab\x9f\xca\x12"
+			"\x19\xaf\x97\x2d\x5f\xf9\xff\xfc",
+		.entprb = (unsigned char *)
+			"\xaf\xfc\x4f\x98\x8b\x93\x95\xc1\xb5\x8b\x7f\x73"
+			"\x6d\xa6\xbe\x6d\x33\xeb\x2c\x82\xb1\xaf\xc1\xb6"
+			"\xb6\x05\xe2\x44\xaa\xfd\xe7\xdb",
+		.entprlen = 32,
+		.expected = (unsigned char *)
+			"\x51\x79\xde\x1c\x0f\x58\xf3\xf4\xc9\x57\x2e\x31"
+			"\xa7\x09\xa1\x53\x64\x63\xa2\xc5\x1d\x84\x88\x65"
+			"\x01\x1b\xc6\x16\x3c\x49\x5b\x42\x8e\x53\xf5\x18"
+			"\xad\x94\x12\x0d\x4f\x55\xcc\x45\x5c\x98\x0f\x42"
+			"\x28\x2f\x47\x11\xf9\xc4\x01\x97\x6b\xa0\x94\x50"
+			"\xa9\xd1\x5e\x06\x54\x3f\xdf\xbb\xc4\x98\xee\x8b"
+			"\xba\xa9\xfa\x49\xee\x1d\xdc\xfb\x50\xf6\x51\x9f"
+			"\x6c\x4a\x9a\x6f\x63\xa2\x7d\xad\xaf\x3a\x24\xa0"
+			"\xd9\x9f\x07\xeb\x15\xee\x26\xe0\xd5\x63\x39\xda"
+			"\x3c\x59\xd6\x33\x6c\x02\xe8\x05\x71\x46\x68\x44"
+			"\x63\x4a\x68\x72\xe9\xf5\x55\xfe",
+		.expectedlen = 128,
+		.addtla = (unsigned char *)
+			"\x15\x20\x2f\xf6\x98\x28\x63\xa2\xc4\x4e\xbb\x6c"
+			"\xb2\x25\x92\x61\x79\xc9\x22\xc4\x61\x54\x96\xff"
+			"\x4a\x85\xca\x80\xfe\x0d\x1c\xd0",
+		.addtlb = (unsigned char *)
+			"\xde\x29\x8e\x03\x42\x61\xa3\x28\x5e\xc8\x80\xc2"
+			"\x6d\xbf\xad\x13\xe1\x8d\x2a\xc7\xe8\xc7\x18\x89"
+			"\x42\x58\x9e\xd6\xcc\xad\x7b\x1e",
+		.addtllen = 32,
+		.pers = (unsigned char *)
+			"\x84\xc3\x73\x9e\xce\xb3\xbc\x89\xf7\x62\xb3\xe1"
+			"\xd7\x48\x45\x8a\xa9\xcc\xe9\xed\xd5\x81\x84\x52"
+			"\x82\x4c\xdc\x19\xb8\xf8\x92\x5c",
+		.perslen = 32,
+	},
+};
+
+static struct drbg_testvec drbg_pr_hmac_sha256_tv_template[] = {
+	{
+		.entropy = (unsigned char *)
+			"\x99\x69\xe5\x4b\x47\x03\xff\x31\x78\x5b\x87\x9a"
+			"\x7e\x5c\x0e\xae\x0d\x3e\x30\x95\x59\xe9\xfe\x96"
+			"\xb0\x67\x6d\x49\xd5\x91\xea\x4d\x07\xd2\x0d\x46"
+			"\xd0\x64\x75\x7d\x30\x23\xca\xc2\x37\x61\x27\xab",
+		.entropylen = 48,
+		.entpra = (unsigned char *)
+			"\xc6\x0f\x29\x99\x10\x0f\x73\x8c\x10\xf7\x47\x92"
+			"\x67\x6a\x3f\xc4\xa2\x62\xd1\x37\x21\x79\x80\x46"
+			"\xe2\x9a\x29\x51\x81\x56\x9f\x54",
+		.entprb = (unsigned char *)
+			"\xc1\x1d\x45\x24\xc9\x07\x1b\xd3\x09\x60\x15\xfc"
+			"\xf7\xbc\x24\xa6\x07\xf2\x2f\xa0\x65\xc9\x37\x65"
+			"\x8a\x2a\x77\xa8\x69\x90\x89\xf4",
+		.entprlen = 32,
+		.expected = (unsigned char *)
+			"\xab\xc0\x15\x85\x60\x94\x80\x3a\x93\x8d\xff\xd2"
+			"\x0d\xa9\x48\x43\x87\x0e\xf9\x35\xb8\x2c\xfe\xc1"
+			"\x77\x06\xb8\xf5\x51\xb8\x38\x50\x44\x23\x5d\xd4"
+			"\x4b\x59\x9f\x94\xb3\x9b\xe7\x8d\xd4\x76\xe0\xcf"
+			"\x11\x30\x9c\x99\x5a\x73\x34\xe0\xa7\x8b\x37\xbc"
+			"\x95\x86\x23\x50\x86\xfa\x3b\x63\x7b\xa9\x1c\xf8"
+			"\xfb\x65\xef\xa2\x2a\x58\x9c\x13\x75\x31\xaa\x7b"
+			"\x2d\x4e\x26\x07\xaa\xc2\x72\x92\xb0\x1c\x69\x8e"
+			"\x6e\x01\xae\x67\x9e\xb8\x7c\x01\xa8\x9c\x74\x22"
+			"\xd4\x37\x2d\x6d\x75\x4a\xba\xbb\x4b\xf8\x96\xfc"
+			"\xb1\xcd\x09\xd6\x92\xd0\x28\x3f",
+		.expectedlen = 128,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\xb9\x1f\xe9\xef\xdd\x9b\x7d\x20\xb6\xec\xe0\x2f"
+			"\xdb\x76\x24\xce\x41\xc8\x3a\x4a\x12\x7f\x3e\x2f"
+			"\xae\x05\x99\xea\xb5\x06\x71\x0d\x0c\x4c\xb4\x05"
+			"\x26\xc6\xbd\xf5\x7f\x2a\x3d\xf2\xb5\x49\x7b\xda",
+		.entropylen = 48,
+		.entpra = (unsigned char *)
+			"\xef\x67\x50\x9c\xa7\x7d\xdf\xb7\x2d\x81\x01\xa4"
+			"\x62\x81\x6a\x69\x5b\xb3\x37\x45\xa7\x34\x8e\x26"
+			"\x46\xd9\x26\xa2\x19\xd4\x94\x43",
+		.entprb = (unsigned char *)
+			"\x97\x75\x53\x53\xba\xb4\xa6\xb2\x91\x60\x71\x79"
+			"\xd1\x6b\x4a\x24\x9a\x34\x66\xcc\x33\xab\x07\x98"
+			"\x51\x78\x72\xb2\x79\xfd\x2c\xff",
+		.entprlen = 32,
+		.expected = (unsigned char *)
+			"\x9c\xdc\x63\x8a\x19\x23\x22\x66\x0c\xc5\xb9\xd7"
+			"\xfb\x2a\xb0\x31\xe3\x8a\x36\xa8\x5a\xa8\x14\xda"
+			"\x1e\xa9\xcc\xfe\xb8\x26\x44\x83\x9f\xf6\xff\xaa"
+			"\xc8\x98\xb8\x30\x35\x3b\x3d\x36\xd2\x49\xd4\x40"
+			"\x62\x0a\x65\x10\x76\x55\xef\xc0\x95\x9c\xa7\xda"
+			"\x3f\xcf\xb7\x7b\xc6\xe1\x28\x52\xfc\x0c\xe2\x37"
+			"\x0d\x83\xa7\x51\x4b\x31\x47\x3c\xe1\x3c\xae\x70"
+			"\x01\xc8\xa3\xd3\xc2\xac\x77\x9c\xd1\x68\x77\x9b"
+			"\x58\x27\x3b\xa5\x0f\xc2\x7a\x8b\x04\x65\x62\xd5"
+			"\xe8\xd6\xfe\x2a\xaf\xd3\xd3\xfe\xbd\x18\xfb\xcd"
+			"\xcd\x66\xb5\x01\x69\x66\xa0\x3c",
+		.expectedlen = 128,
+		.addtla = (unsigned char *)
+			"\x17\xc1\x56\xcb\xcc\x50\xd6\x03\x7d\x45\x76\xa3"
+			"\x75\x76\xc1\x4a\x66\x1b\x2e\xdf\xb0\x2e\x7d\x56"
+			"\x6d\x99\x3b\xc6\x58\xda\x03\xf6",
+		.addtlb = (unsigned char *)
+			"\x7c\x7b\x4a\x4b\x32\x5e\x6f\x67\x34\xf5\x21\x4c"
+			"\xf9\x96\xf9\xbf\x1c\x8c\x81\xd3\x9b\x60\x6a\x44"
+			"\xc6\x03\xa2\xfb\x13\x20\x19\xb7",
+		.addtllen = 32,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\x13\x54\x96\xfc\x1b\x7d\x28\xf3\x18\xc9\xa7\x89"
+			"\xb6\xb3\xc8\x72\xac\x00\xd4\x59\x36\x25\x05\xaf"
+			"\xa5\xdb\x96\xcb\x3c\x58\x46\x87\xa5\xaa\xbf\x20"
+			"\x3b\xfe\x23\x0e\xd1\xc7\x41\x0f\x3f\xc9\xb3\x67",
+		.entropylen = 48,
+		.entpra = (unsigned char *)
+			"\xe2\xbd\xb7\x48\x08\x06\xf3\xe1\x93\x3c\xac\x79"
+			"\xa7\x2b\x11\xda\xe3\x2e\xe1\x91\xa5\x02\x19\x57"
+			"\x20\x28\xad\xf2\x60\xd7\xcd\x45",
+		.entprb = (unsigned char *)
+			"\x8b\xd4\x69\xfc\xff\x59\x95\x95\xc6\x51\xde\x71"
+			"\x68\x5f\xfc\xf9\x4a\xab\xec\x5a\xcb\xbe\xd3\x66"
+			"\x1f\xfa\x74\xd3\xac\xa6\x74\x60",
+		.entprlen = 32,
+		.expected = (unsigned char *)
+			"\x1f\x9e\xaf\xe4\xd2\x46\xb7\x47\x41\x4c\x65\x99"
+			"\x01\xe9\x3b\xbb\x83\x0c\x0a\xb0\xc1\x3a\xe2\xb3"
+			"\x31\x4e\xeb\x93\x73\xee\x0b\x26\xc2\x63\xa5\x75"
+			"\x45\x99\xd4\x5c\x9f\xa1\xd4\x45\x87\x6b\x20\x61"
+			"\x40\xea\x78\xa5\x32\xdf\x9e\x66\x17\xaf\xb1\x88"
+			"\x9e\x2e\x23\xdd\xc1\xda\x13\x97\x88\xa5\xb6\x5e"
+			"\x90\x14\x4e\xef\x13\xab\x5c\xd9\x2c\x97\x9e\x7c"
+			"\xd7\xf8\xce\xea\x81\xf5\xcd\x71\x15\x49\x44\xce"
+			"\x83\xb6\x05\xfb\x7d\x30\xb5\x57\x2c\x31\x4f\xfc"
+			"\xfe\x80\xb6\xc0\x13\x0c\x5b\x9b\x2e\x8f\x3d\xfc"
+			"\xc2\xa3\x0c\x11\x1b\x80\x5f\xf3",
+		.expectedlen = 128,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = (unsigned char *)
+			"\x64\xb6\xfc\x60\xbc\x61\x76\x23\x6d\x3f\x4a\x0f"
+			"\xe1\xb4\xd5\x20\x9e\x70\xdd\x03\x53\x6d\xbf\xce"
+			"\xcd\x56\x80\xbc\xb8\x15\xc8\xaa",
+		.perslen = 32,
+	}, {
+		.entropy = (unsigned char *)
+			"\xc7\xcc\xbc\x67\x7e\x21\x66\x1e\x27\x2b\x63\xdd"
+			"\x3a\x78\xdc\xdf\x66\x6d\x3f\x24\xae\xcf\x37\x01"
+			"\xa9\x0d\x89\x8a\xa7\xdc\x81\x58\xae\xb2\x10\x15"
+			"\x7e\x18\x44\x6d\x13\xea\xdf\x37\x85\xfe\x81\xfb",
+		.entropylen = 48,
+		.entpra = (unsigned char *)
+			"\x7b\xa1\x91\x5b\x3c\x04\xc4\x1b\x1d\x19\x2f\x1a"
+			"\x18\x81\x60\x3c\x6c\x62\x91\xb7\xe9\xf5\xcb\x96"
+			"\xbb\x81\x6a\xcc\xb5\xae\x55\xb6",
+		.entprb = (unsigned char *)
+			"\x99\x2c\xc7\x78\x7e\x3b\x88\x12\xef\xbe\xd3\xd2"
+			"\x7d\x2a\xa5\x86\xda\x8d\x58\x73\x4a\x0a\xb2\x2e"
+			"\xbb\x4c\x7e\xe3\x9a\xb6\x81\xc1",
+		.entprlen = 32,
+		.expected = (unsigned char *)
+			"\x95\x6f\x95\xfc\x3b\xb7\xfe\x3e\xd0\x4e\x1a\x14"
+			"\x6c\x34\x7f\x7b\x1d\x0d\x63\x5e\x48\x9c\x69\xe6"
+			"\x46\x07\xd2\x87\xf3\x86\x52\x3d\x98\x27\x5e\xd7"
+			"\x54\xe7\x75\x50\x4f\xfb\x4d\xfd\xac\x2f\x4b\x77"
+			"\xcf\x9e\x8e\xcc\x16\xa2\x24\xcd\x53\xde\x3e\xc5"
+			"\x55\x5d\xd5\x26\x3f\x89\xdf\xca\x8b\x4e\x1e\xb6"
+			"\x88\x78\x63\x5c\xa2\x63\x98\x4e\x6f\x25\x59\xb1"
+			"\x5f\x2b\x23\xb0\x4b\xa5\x18\x5d\xc2\x15\x74\x40"
+			"\x59\x4c\xb4\x1e\xcf\x9a\x36\xfd\x43\xe2\x03\xb8"
+			"\x59\x91\x30\x89\x2a\xc8\x5a\x43\x23\x7c\x73\x72"
+			"\xda\x3f\xad\x2b\xba\x00\x6b\xd1",
+		.expectedlen = 128,
+		.addtla = (unsigned char *)
+			"\x18\xe8\x17\xff\xef\x39\xc7\x41\x5c\x73\x03\x03"
+			"\xf6\x3d\xe8\x5f\xc8\xab\xe4\xab\x0f\xad\xe8\xd6"
+			"\x86\x88\x55\x28\xc1\x69\xdd\x76",
+		.addtlb = (unsigned char *)
+			"\xac\x07\xfc\xbe\x87\x0e\xd3\xea\x1f\x7e\xb8\xe7"
+			"\x9d\xec\xe8\xe7\xbc\xf3\x18\x25\x77\x35\x4a\xaa"
+			"\x00\x99\x2a\xdd\x0a\x00\x50\x82",
+		.addtllen = 32,
+		.pers = (unsigned char *)
+			"\xbc\x55\xab\x3c\xf6\x52\xb0\x11\x3d\x7b\x90\xb8"
+			"\x24\xc9\x26\x4e\x5a\x1e\x77\x0d\x3d\x58\x4a\xda"
+			"\xd1\x81\xe9\xf8\xeb\x30\x8f\x6f",
+		.perslen = 32,
+	},
+};
+
+static struct drbg_testvec drbg_pr_ctr_aes128_tv_template[] = {
+	{
+		.entropy = (unsigned char *)
+			"\xd1\x44\xc6\x61\x81\x6d\xca\x9d\x15\x28\x8a\x42"
+			"\x94\xd7\x28\x9c\x43\x77\x19\x29\x1a\x6d\xc3\xa2",
+		.entropylen = 24,
+		.entpra = (unsigned char *)
+			"\x96\xd8\x9e\x45\x32\xc9\xd2\x08\x7a\x6d\x97\x15"
+			"\xb4\xec\x80\xb1",
+		.entprb = (unsigned char *)
+			"\x8b\xb6\x72\xb5\x24\x0b\x98\x65\x95\x95\xe9\xc9"
+			"\x28\x07\xeb\xc2",
+		.entprlen = 16,
+		.expected = (unsigned char *)
+			"\x70\x19\xd0\x4c\x45\x78\xd6\x68\xa9\x9a\xaa\xfe"
+			"\xc1\xdf\x27\x9a\x1c\x0d\x0d\xf7\x24\x75\x46\xcc"
+			"\x77\x6b\xdf\x89\xc6\x94\xdc\x74\x50\x10\x70\x18"
+			"\x9b\xdc\x96\xb4\x89\x23\x40\x1a\xce\x09\x87\xce"
+			"\xd2\xf3\xd5\xe4\x51\x67\x74\x11\x5a\xcc\x8b\x3b"
+			"\x8a\xf1\x23\xa8",
+		.expectedlen = 64,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\x8e\x83\xe0\xeb\x37\xea\x3e\x53\x5e\x17\x6e\x77"
+			"\xbd\xb1\x53\x90\xfc\xdc\xc1\x3c\x9a\x88\x22\x94",
+		.entropylen = 24,
+		.entpra = (unsigned char *)
+			"\x6a\x85\xe7\x37\xc8\xf1\x04\x31\x98\x4f\xc8\x73"
+			"\x67\xd1\x08\xf8",
+		.entprb = (unsigned char *)
+			"\xd7\xa4\x68\xe2\x12\x74\xc3\xd9\xf1\xb7\x05\xbc"
+			"\xd4\xba\x04\x58",
+		.entprlen = 16,
+		.expected = (unsigned char *)
+			"\x78\xd6\xa6\x70\xff\xd1\x82\xf5\xa2\x88\x7f\x6d"
+			"\x3d\x8c\x39\xb1\xa8\xcb\x2c\x91\xab\x14\x7e\xbc"
+			"\x95\x45\x9f\x24\xb8\x20\xac\x21\x23\xdb\x72\xd7"
+			"\x12\x8d\x48\x95\xf3\x19\x0c\x43\xc6\x19\x45\xfc"
+			"\x8b\xac\x40\x29\x73\x00\x03\x45\x5e\x12\xff\x0c"
+			"\xc1\x02\x41\x82",
+		.expectedlen = 64,
+		.addtla = (unsigned char *)
+			"\xa2\xd9\x38\xcf\x8b\x29\x67\x5b\x65\x62\x6f\xe8"
+			"\xeb\xb3\x01\x76",
+		.addtlb = (unsigned char *)
+			"\x59\x63\x1e\x81\x8a\x14\xa8\xbb\xa1\xb8\x41\x25"
+			"\xd0\x7f\xcc\x43",
+		.addtllen = 16,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\x04\xd9\x49\xa6\xdc\xe8\x6e\xbb\xf1\x08\x77\x2b"
+			"\x9e\x08\xca\x92\x65\x16\xda\x99\xa2\x59\xf3\xe8",
+		.entropylen = 24,
+		.entpra = (unsigned char *)
+			"\x38\x7e\x3f\x6b\x51\x70\x7b\x20\xec\x53\xd0\x66"
+			"\xc3\x0f\xe3\xb0",
+		.entprb = (unsigned char *)
+			"\xe0\x86\xa6\xaa\x5f\x72\x2f\xad\xf7\xef\x06\xb8"
+			"\xd6\x9c\x9d\xe8",
+		.entprlen = 16,
+		.expected = (unsigned char *)
+			"\xc9\x0a\xaf\x85\x89\x71\x44\x66\x4f\x25\x0b\x2b"
+			"\xde\xd8\xfa\xff\x52\x5a\x1b\x32\x5e\x41\x7a\x10"
+			"\x1f\xef\x1e\x62\x23\xe9\x20\x30\xc9\x0d\xad\x69"
+			"\xb4\x9c\x5b\xf4\x87\x42\xd5\xae\x5e\x5e\x43\xcc"
+			"\xd9\xfd\x0b\x93\x4a\xe3\xd4\x06\x37\x36\x0f\x3f"
+			"\x72\x82\x0c\xcf",
+		.expectedlen = 64,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = (unsigned char *)
+			"\xbf\xa4\x9a\x8f\x7b\xd8\xb1\x7a\x9d\xfa\x45\xed"
+			"\x21\x52\xb3\xad",
+		.perslen = 16,
+	}, {
+		.entropy = (unsigned char *)
+			"\x92\x89\x8f\x31\xfa\x1c\xff\x6d\x18\x2f\x26\x06"
+			"\x43\xdf\xf8\x18\xc2\xa4\xd9\x72\xc3\xb9\xb6\x97",
+		.entropylen = 24,
+		.entpra = (unsigned char *)
+			"\x20\x72\x8a\x06\xf8\x6f\x8d\xd4\x41\xe2\x72\xb7"
+			"\xc4\x2c\xe8\x10",
+		.entprb = (unsigned char *)
+			"\x3d\xb0\xf0\x94\xf3\x05\x50\x33\x17\x86\x3e\x22"
+			"\x08\xf7\xa5\x01",
+		.entprlen = 16,
+		.expected = (unsigned char *)
+			"\x5a\x35\x39\x87\x0f\x4d\x22\xa4\x09\x24\xee\x71"
+			"\xc9\x6f\xac\x72\x0a\xd6\xf0\x88\x82\xd0\x83\x28"
+			"\x73\xec\x3f\x93\xd8\xab\x45\x23\xf0\x7e\xac\x45"
+			"\x14\x5e\x93\x9f\xb1\xd6\x76\x43\x3d\xb6\xe8\x08"
+			"\x88\xf6\xda\x89\x08\x77\x42\xfe\x1a\xf4\x3f\xc4"
+			"\x23\xc5\x1f\x68",
+		.expectedlen = 64,
+		.addtla = (unsigned char *)
+			"\x1a\x40\xfa\xe3\xcc\x6c\x7c\xa0\xf8\xda\xba\x59"
+			"\x23\x6d\xad\x1d",
+		.addtlb = (unsigned char *)
+			"\x9f\x72\x76\x6c\xc7\x46\xe5\xed\x2e\x53\x20\x12"
+			"\xbc\x59\x31\x8c",
+		.addtllen = 16,
+		.pers = (unsigned char *)
+			"\xea\x65\xee\x60\x26\x4e\x7e\xb6\x0e\x82\x68\xc4"
+			"\x37\x3c\x5c\x0b",
+		.perslen = 16,
+	},
+};
+
+/*
+ * SP800-90A DRBG Test vectors from
+ * http://csrc.nist.gov/groups/STM/cavp/documents/drbg/drbgtestvectors.zip
+ *
+ * Test vectors for DRBG without prediction resistance. All types of DRBGs
+ * (Hash, HMAC, CTR) are tested with all permutations of use cases (w/ and
+ * w/o personalization string, w/ and w/o additional input string).
+ */
+static struct drbg_testvec drbg_nopr_sha256_tv_template[] = {
+	{
+		.entropy = (unsigned char *)
+			"\xa6\x5a\xd0\xf3\x45\xdb\x4e\x0e\xff\xe8\x75\xc3"
+			"\xa2\xe7\x1f\x42\xc7\x12\x9d\x62\x0f\xf5\xc1\x19"
+			"\xa9\xef\x55\xf0\x51\x85\xe0\xfb\x85\x81\xf9\x31"
+			"\x75\x17\x27\x6e\x06\xe9\x60\x7d\xdb\xcb\xcc\x2e",
+		.entropylen = 48,
+		.expected = (unsigned char *)
+			"\xd3\xe1\x60\xc3\x5b\x99\xf3\x40\xb2\x62\x82\x64"
+			"\xd1\x75\x10\x60\xe0\x04\x5d\xa3\x83\xff\x57\xa5"
+			"\x7d\x73\xa6\x73\xd2\xb8\xd8\x0d\xaa\xf6\xa6\xc3"
+			"\x5a\x91\xbb\x45\x79\xd7\x3f\xd0\xc8\xfe\xd1\x11"
+			"\xb0\x39\x13\x06\x82\x8a\xdf\xed\x52\x8f\x01\x81"
+			"\x21\xb3\xfe\xbd\xc3\x43\xe7\x97\xb8\x7d\xbb\x63"
+			"\xdb\x13\x33\xde\xd9\xd1\xec\xe1\x77\xcf\xa6\xb7"
+			"\x1f\xe8\xab\x1d\xa4\x66\x24\xed\x64\x15\xe5\x1c"
+			"\xcd\xe2\xc7\xca\x86\xe2\x83\x99\x0e\xea\xeb\x91"
+			"\x12\x04\x15\x52\x8b\x22\x95\x91\x02\x81\xb0\x2d"
+			"\xd4\x31\xf4\xc9\xf7\x04\x27\xdf",
+		.expectedlen = 128,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\x73\xd3\xfb\xa3\x94\x5f\x2b\x5f\xb9\x8f\xf6\x9c"
+			"\x8a\x93\x17\xae\x19\xc3\x4c\xc3\xd6\xca\xa3\x2d"
+			"\x16\xfc\x42\xd2\x2d\xd5\x6f\x56\xcc\x1d\x30\xff"
+			"\x9e\x06\x3e\x09\xce\x58\xe6\x9a\x35\xb3\xa6\x56",
+		.entropylen = 48,
+		.expected = (unsigned char *)
+			"\x71\x7b\x93\x46\x1a\x40\xaa\x35\xa4\xaa\xc5\xe7"
+			"\x6d\x5b\x5b\x8a\xa0\xdf\x39\x7d\xae\x71\x58\x5b"
+			"\x3c\x7c\xb4\xf0\x89\xfa\x4a\x8c\xa9\x5c\x54\xc0"
+			"\x40\xdf\xbc\xce\x26\x81\x34\xf8\xba\x7d\x1c\xe8"
+			"\xad\x21\xe0\x74\xcf\x48\x84\x30\x1f\xa1\xd5\x4f"
+			"\x81\x42\x2f\xf4\xdb\x0b\x23\xf8\x73\x27\xb8\x1d"
+			"\x42\xf8\x44\x58\xd8\x5b\x29\x27\x0a\xf8\x69\x59"
+			"\xb5\x78\x44\xeb\x9e\xe0\x68\x6f\x42\x9a\xb0\x5b"
+			"\xe0\x4e\xcb\x6a\xaa\xe2\xd2\xd5\x33\x25\x3e\xe0"
+			"\x6c\xc7\x6a\x07\xa5\x03\x83\x9f\xe2\x8b\xd1\x1c"
+			"\x70\xa8\x07\x59\x97\xeb\xf6\xbe",
+		.expectedlen = 128,
+		.addtla = (unsigned char *)
+			"\xf4\xd5\x98\x3d\xa8\xfc\xfa\x37\xb7\x54\x67\x73"
+			"\xc7\xc3\xdd\x47\x34\x71\x02\x5d\xc1\xa0\xd3\x10"
+			"\xc1\x8b\xbd\xf5\x66\x34\x6f\xdd",
+		.addtlb = (unsigned char *)
+			"\xf7\x9e\x6a\x56\x0e\x73\xe9\xd9\x7a\xd1\x69\xe0"
+			"\x6f\x8c\x55\x1c\x44\xd1\xce\x6f\x28\xcc\xa4\x4d"
+			"\xa8\xc0\x85\xd1\x5a\x0c\x59\x40",
+		.addtllen = 32,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\x2a\x85\xa9\x8b\xd0\xda\x83\xd6\xad\xab\x9f\xbb"
+			"\x54\x31\x15\x95\x1c\x4d\x49\x9f\x6a\x15\xf6\xe4"
+			"\x15\x50\x88\x06\x29\x0d\xed\x8d\xb9\x6f\x96\xe1"
+			"\x83\x9f\xf7\x88\xda\x84\xbf\x44\x28\xd9\x1d\xaa",
+		.entropylen = 48,
+		.expected = (unsigned char *)
+			"\x2d\x55\xde\xc9\xed\x05\x47\x07\x3d\x04\xfc\x28"
+			"\x0f\x92\xf0\x4d\xd8\x00\x32\x47\x0a\x1b\x1c\x4b"
+			"\xef\xd9\x97\xa1\x17\x67\xda\x26\x6c\xfe\x76\x46"
+			"\x6f\xbc\x6d\x82\x4e\x83\x8a\x98\x66\x6c\x01\xb6"
+			"\xe6\x64\xe0\x08\x10\x6f\xd3\x5d\x90\xe7\x0d\x72"
+			"\xa6\xa7\xe3\xbb\x98\x11\x12\x56\x23\xc2\x6d\xd1"
+			"\xc8\xa8\x7a\x39\xf3\x34\xe3\xb8\xf8\x66\x00\x77"
+			"\x7d\xcf\x3c\x3e\xfa\xc9\x0f\xaf\xe0\x24\xfa\xe9"
+			"\x84\xf9\x6a\x01\xf6\x35\xdb\x5c\xab\x2a\xef\x4e"
+			"\xac\xab\x55\xb8\x9b\xef\x98\x68\xaf\x51\xd8\x16"
+			"\xa5\x5e\xae\xf9\x1e\xd2\xdb\xe6",
+		.expectedlen = 128,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = (unsigned char *)
+			"\xa8\x80\xec\x98\x30\x98\x15\xd2\xc6\xc4\x68\xf1"
+			"\x3a\x1c\xbf\xce\x6a\x40\x14\xeb\x36\x99\x53\xda"
+			"\x57\x6b\xce\xa4\x1c\x66\x3d\xbc",
+		.perslen = 32,
+	}, {
+		.entropy = (unsigned char *)
+			"\x69\xed\x82\xa9\xc5\x7b\xbf\xe5\x1d\x2f\xcb\x7a"
+			"\xd3\x50\x7d\x96\xb4\xb9\x2b\x50\x77\x51\x27\x74"
+			"\x33\x74\xba\xf1\x30\xdf\x8e\xdf\x87\x1d\x87\xbc"
+			"\x96\xb2\xc3\xa7\xed\x60\x5e\x61\x4e\x51\x29\x1a",
+		.entropylen = 48,
+		.expected = (unsigned char *)
+			"\xa5\x71\x24\x31\x11\xfe\x13\xe1\xa8\x24\x12\xfb"
+			"\x37\xa1\x27\xa5\xab\x77\xa1\x9f\xae\x8f\xaf\x13"
+			"\x93\xf7\x53\x85\x91\xb6\x1b\xab\xd4\x6b\xea\xb6"
+			"\xef\xda\x4c\x90\x6e\xef\x5f\xde\xe1\xc7\x10\x36"
+			"\xd5\x67\xbd\x14\xb6\x89\x21\x0c\xc9\x92\x65\x64"
+			"\xd0\xf3\x23\xe0\x7f\xd1\xe8\x75\xc2\x85\x06\xea"
+			"\xca\xc0\xcb\x79\x2d\x29\x82\xfc\xaa\x9a\xc6\x95"
+			"\x7e\xdc\x88\x65\xba\xec\x0e\x16\x87\xec\xa3\x9e"
+			"\xd8\x8c\x80\xab\x3a\x64\xe0\xcb\x0e\x45\x98\xdd"
+			"\x7c\x6c\x6c\x26\x11\x13\xc8\xce\xa9\x47\xa6\x06"
+			"\x57\xa2\x66\xbb\x2d\x7f\xf3\xc1",
+		.expectedlen = 128,
+		.addtla = (unsigned char *)
+			"\x74\xd3\x6d\xda\xe8\xd6\x86\x5f\x63\x01\xfd\xf2"
+			"\x7d\x06\x29\x6d\x94\xd1\x66\xf0\xd2\x72\x67\x4e"
+			"\x77\xc5\x3d\x9e\x03\xe3\xa5\x78",
+		.addtlb = (unsigned char *)
+			"\xf6\xb6\x3d\xf0\x7c\x26\x04\xc5\x8b\xcd\x3e\x6a"
+			"\x9f\x9c\x3a\x2e\xdb\x47\x87\xe5\x8e\x00\x5e\x2b"
+			"\x74\x7f\xa6\xf6\x80\xcd\x9b\x21",
+		.addtllen = 32,
+		.pers = (unsigned char *)
+			"\x74\xa6\xe0\x08\xf9\x27\xee\x1d\x6e\x3c\x28\x20"
+			"\x87\xdd\xd7\x54\x31\x47\x78\x4b\xe5\x6d\xa3\x73"
+			"\xa9\x65\xb1\x10\xc1\xdc\x77\x7c",
+		.perslen = 32,
+	},
+};
+
+static struct drbg_testvec drbg_nopr_hmac_sha256_tv_template[] = {
+	{
+		.entropy = (unsigned char *)
+			"\xca\x85\x19\x11\x34\x93\x84\xbf\xfe\x89\xde\x1c"
+			"\xbd\xc4\x6e\x68\x31\xe4\x4d\x34\xa4\xfb\x93\x5e"
+			"\xe2\x85\xdd\x14\xb7\x1a\x74\x88\x65\x9b\xa9\x6c"
+			"\x60\x1d\xc6\x9f\xc9\x02\x94\x08\x05\xec\x0c\xa8",
+		.entropylen = 48,
+		.expected = (unsigned char *)
+			"\xe5\x28\xe9\xab\xf2\xde\xce\x54\xd4\x7c\x7e\x75"
+			"\xe5\xfe\x30\x21\x49\xf8\x17\xea\x9f\xb4\xbe\xe6"
+			"\xf4\x19\x96\x97\xd0\x4d\x5b\x89\xd5\x4f\xbb\x97"
+			"\x8a\x15\xb5\xc4\x43\xc9\xec\x21\x03\x6d\x24\x60"
+			"\xb6\xf7\x3e\xba\xd0\xdc\x2a\xba\x6e\x62\x4a\xbf"
+			"\x07\x74\x5b\xc1\x07\x69\x4b\xb7\x54\x7b\xb0\x99"
+			"\x5f\x70\xde\x25\xd6\xb2\x9e\x2d\x30\x11\xbb\x19"
+			"\xd2\x76\x76\xc0\x71\x62\xc8\xb5\xcc\xde\x06\x68"
+			"\x96\x1d\xf8\x68\x03\x48\x2c\xb3\x7e\xd6\xd5\xc0"
+			"\xbb\x8d\x50\xcf\x1f\x50\xd4\x76\xaa\x04\x58\xbd"
+			"\xab\xa8\x06\xf4\x8b\xe9\xdc\xb8",
+		.expectedlen = 128,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\xf9\x7a\x3c\xfd\x91\xfa\xa0\x46\xb9\xe6\x1b\x94"
+			"\x93\xd4\x36\xc4\x93\x1f\x60\x4b\x22\xf1\x08\x15"
+			"\x21\xb3\x41\x91\x51\xe8\xff\x06\x11\xf3\xa7\xd4"
+			"\x35\x95\x35\x7d\x58\x12\x0b\xd1\xe2\xdd\x8a\xed",
+		.entropylen = 48,
+		.expected = (unsigned char *)
+			"\xc6\x87\x1c\xff\x08\x24\xfe\x55\xea\x76\x89\xa5"
+			"\x22\x29\x88\x67\x30\x45\x0e\x5d\x36\x2d\xa5\xbf"
+			"\x59\x0d\xcf\x9a\xcd\x67\xfe\xd4\xcb\x32\x10\x7d"
+			"\xf5\xd0\x39\x69\xa6\x6b\x1f\x64\x94\xfd\xf5\xd6"
+			"\x3d\x5b\x4d\x0d\x34\xea\x73\x99\xa0\x7d\x01\x16"
+			"\x12\x6d\x0d\x51\x8c\x7c\x55\xba\x46\xe1\x2f\x62"
+			"\xef\xc8\xfe\x28\xa5\x1c\x9d\x42\x8e\x6d\x37\x1d"
+			"\x73\x97\xab\x31\x9f\xc7\x3d\xed\x47\x22\xe5\xb4"
+			"\xf3\x00\x04\x03\x2a\x61\x28\xdf\x5e\x74\x97\xec"
+			"\xf8\x2c\xa7\xb0\xa5\x0e\x86\x7e\xf6\x72\x8a\x4f"
+			"\x50\x9a\x8c\x85\x90\x87\x03\x9c",
+		.expectedlen = 128,
+		.addtla = (unsigned char *)
+			"\x51\x72\x89\xaf\xe4\x44\xa0\xfe\x5e\xd1\xa4\x1d"
+			"\xbb\xb5\xeb\x17\x15\x00\x79\xbd\xd3\x1e\x29\xcf"
+			"\x2f\xf3\x00\x34\xd8\x26\x8e\x3b",
+		.addtlb = (unsigned char *)
+			"\x88\x02\x8d\x29\xef\x80\xb4\xe6\xf0\xfe\x12\xf9"
+			"\x1d\x74\x49\xfe\x75\x06\x26\x82\xe8\x9c\x57\x14"
+			"\x40\xc0\xc9\xb5\x2c\x42\xa6\xe0",
+		.addtllen = 32,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\x8d\xf0\x13\xb4\xd1\x03\x52\x30\x73\x91\x7d\xdf"
+			"\x6a\x86\x97\x93\x05\x9e\x99\x43\xfc\x86\x54\x54"
+			"\x9e\x7a\xb2\x2f\x7c\x29\xf1\x22\xda\x26\x25\xaf"
+			"\x2d\xdd\x4a\xbc\xce\x3c\xf4\xfa\x46\x59\xd8\x4e",
+		.entropylen = 48,
+		.expected = (unsigned char *)
+			"\xb9\x1c\xba\x4c\xc8\x4f\xa2\x5d\xf8\x61\x0b\x81"
+			"\xb6\x41\x40\x27\x68\xa2\x09\x72\x34\x93\x2e\x37"
+			"\xd5\x90\xb1\x15\x4c\xbd\x23\xf9\x74\x52\xe3\x10"
+			"\xe2\x91\xc4\x51\x46\x14\x7f\x0d\xa2\xd8\x17\x61"
+			"\xfe\x90\xfb\xa6\x4f\x94\x41\x9c\x0f\x66\x2b\x28"
+			"\xc1\xed\x94\xda\x48\x7b\xb7\xe7\x3e\xec\x79\x8f"
+			"\xbc\xf9\x81\xb7\x91\xd1\xbe\x4f\x17\x7a\x89\x07"
+			"\xaa\x3c\x40\x16\x43\xa5\xb6\x2b\x87\xb8\x9d\x66"
+			"\xb3\xa6\x0e\x40\xd4\xa8\xe4\xe9\xd8\x2a\xf6\xd2"
+			"\x70\x0e\x6f\x53\x5c\xdb\x51\xf7\x5c\x32\x17\x29"
+			"\x10\x37\x41\x03\x0c\xcc\x3a\x56",
+		.expectedlen = 128,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = (unsigned char *)
+			"\xb5\x71\xe6\x6d\x7c\x33\x8b\xc0\x7b\x76\xad\x37"
+			"\x57\xbb\x2f\x94\x52\xbf\x7e\x07\x43\x7a\xe8\x58"
+			"\x1c\xe7\xbc\x7c\x3a\xc6\x51\xa9",
+		.perslen = 32,
+	}, {
+		.entropy = (unsigned char *)
+			"\xc2\xa5\x66\xa9\xa1\x81\x7b\x15\xc5\xc3\xb7\x78"
+			"\x17\x7a\xc8\x7c\x24\xe7\x97\xbe\x0a\x84\x5f\x11"
+			"\xc2\xfe\x39\x9d\xd3\x77\x32\xf2\xcb\x18\x94\xeb"
+			"\x2b\x97\xb3\xc5\x6e\x62\x83\x29\x51\x6f\x86\xec",
+		.entropylen = 48,
+		.expected = (unsigned char *)
+			"\xb3\xa3\x69\x8d\x77\x76\x99\xa0\xdd\x9f\xa3\xf0"
+			"\xa9\xfa\x57\x83\x2d\x3c\xef\xac\x5d\xf2\x44\x37"
+			"\xc6\xd7\x3a\x0f\xe4\x10\x40\xf1\x72\x90\x38\xae"
+			"\xf1\xe9\x26\x35\x2e\xa5\x9d\xe1\x20\xbf\xb7\xb0"
+			"\x73\x18\x3a\x34\x10\x6e\xfe\xd6\x27\x8f\xf8\xad"
+			"\x84\x4b\xa0\x44\x81\x15\xdf\xdd\xf3\x31\x9a\x82"
+			"\xde\x6b\xb1\x1d\x80\xbd\x87\x1a\x9a\xcd\x35\xc7"
+			"\x36\x45\xe1\x27\x0f\xb9\xfe\x4f\xa8\x8e\xc0\xe4"
+			"\x65\x40\x9e\xa0\xcb\xa8\x09\xfe\x2f\x45\xe0\x49"
+			"\x43\xa2\xe3\x96\xbb\xb7\xdd\x2f\x4e\x07\x95\x30"
+			"\x35\x24\xcc\x9c\xc5\xea\x54\xa1",
+		.expectedlen = 128,
+		.addtla = (unsigned char *)
+			"\x41\x3d\xd8\x3f\xe5\x68\x35\xab\xd4\x78\xcb\x96"
+			"\x93\xd6\x76\x35\x90\x1c\x40\x23\x9a\x26\x64\x62"
+			"\xd3\x13\x3b\x83\xe4\x9c\x82\x0b",
+		.addtlb = (unsigned char *)
+			"\xd5\xc4\xa7\x1f\x9d\x6d\x95\xa1\xbe\xdf\x0b\xd2"
+			"\x24\x7c\x27\x7d\x1f\x84\xa4\xe5\x7a\x4a\x88\x25"
+			"\xb8\x2a\x2d\x09\x7d\xe6\x3e\xf1",
+		.addtllen = 32,
+		.pers = (unsigned char *)
+			"\x13\xce\x4d\x8d\xd2\xdb\x97\x96\xf9\x41\x56\xc8"
+			"\xe8\xf0\x76\x9b\x0a\xa1\xc8\x2c\x13\x23\xb6\x15"
+			"\x36\x60\x3b\xca\x37\xc9\xee\x29",
+		.perslen = 32,
+	},
+};
+
+static struct drbg_testvec drbg_nopr_ctr_aes192_tv_template[] = {
+	{
+		.entropy = (unsigned char *)
+			"\xc3\x5c\x2f\xa2\xa8\x9d\x52\xa1\x1f\xa3\x2a\xa9"
+			"\x6c\x95\xb8\xf1\xc9\xa8\xf9\xcb\x24\x5a\x8b\x40"
+			"\xf3\xa6\xe5\xa7\xfb\xd9\xd3\xc6\x8e\x27\x7b\xa9"
+			"\xac\x9b\xbb\x00",
+		.entropylen = 40,
+		.expected = (unsigned char *)
+			"\x8c\x2e\x72\xab\xfd\x9b\xb8\x28\x4d\xb7\x9e\x17"
+			"\xa4\x3a\x31\x46\xcd\x76\x94\xe3\x52\x49\xfc\x33"
+			"\x83\x91\x4a\x71\x17\xf4\x13\x68\xe6\xd4\xf1\x48"
+			"\xff\x49\xbf\x29\x07\x6b\x50\x15\xc5\x9f\x45\x79"
+			"\x45\x66\x2e\x3d\x35\x03\x84\x3f\x4a\xa5\xa3\xdf"
+			"\x9a\x9d\xf1\x0d",
+		.expectedlen = 64,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = NULL,
+		.perslen = 0,
+	},
+};
+
+static struct drbg_testvec drbg_nopr_ctr_aes256_tv_template[] = {
+	{
+		.entropy = (unsigned char *)
+			"\x36\x40\x19\x40\xfa\x8b\x1f\xba\x91\xa1\x66\x1f"
+			"\x21\x1d\x78\xa0\xb9\x38\x9a\x74\xe5\xbc\xcf\xec"
+			"\xe8\xd7\x66\xaf\x1a\x6d\x3b\x14\x49\x6f\x25\xb0"
+			"\xf1\x30\x1b\x4f\x50\x1b\xe3\x03\x80\xa1\x37\xeb",
+		.entropylen = 48,
+		.expected = (unsigned char *)
+			"\x58\x62\xeb\x38\xbd\x55\x8d\xd9\x78\xa6\x96\xe6"
+			"\xdf\x16\x47\x82\xdd\xd8\x87\xe7\xe9\xa6\xc9\xf3"
+			"\xf1\xfb\xaf\xb7\x89\x41\xb5\x35\xa6\x49\x12\xdf"
+			"\xd2\x24\xc6\xdc\x74\x54\xe5\x25\x0b\x3d\x97\x16"
+			"\x5e\x16\x26\x0c\x2f\xaf\x1c\xc7\x73\x5c\xb7\x5f"
+			"\xb4\xf0\x7e\x1d",
+		.expectedlen = 64,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = NULL,
+		.perslen = 0,
+	},
+};
+
+static struct drbg_testvec drbg_nopr_ctr_aes128_tv_template[] = {
+	{
+		.entropy = (unsigned char *)
+			"\x87\xe1\xc5\x32\x99\x7f\x57\xa3\x5c\x28\x6d\xe8"
+			"\x64\xbf\xf2\x64\xa3\x9e\x98\xdb\x6c\x10\x78\x7f",
+		.entropylen = 24,
+		.expected = (unsigned char *)
+			"\x2c\x14\x7e\x24\x11\x9a\xd8\xd4\xb2\xed\x61\xc1"
+			"\x53\xd0\x50\xc9\x24\xff\x59\x75\x15\xf1\x17\x3a"
+			"\x3d\xf4\x4b\x2c\x84\x28\xef\x89\x0e\xb9\xde\xf3"
+			"\xe4\x78\x04\xb2\xfd\x9b\x35\x7f\xe1\x3f\x8a\x3e"
+			"\x10\xc8\x67\x0a\xf9\xdf\x2d\x6c\x96\xfb\xb2\xb8"
+			"\xcb\x2d\xd6\xb0",
+		.expectedlen = 64,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\x71\xbd\xce\x35\x42\x7d\x20\xbf\x58\xcf\x17\x74"
+			"\xce\x72\xd8\x33\x34\x50\x2d\x8f\x5b\x14\xc4\xdd",
+		.entropylen = 24,
+		.expected = (unsigned char *)
+			"\x97\x33\xe8\x20\x12\xe2\x7b\xa1\x46\x8f\xf2\x34"
+			"\xb3\xc9\xb6\x6b\x20\xb2\x4f\xee\x27\xd8\x0b\x21"
+			"\x8c\xff\x63\x73\x69\x29\xfb\xf3\x85\xcd\x88\x8e"
+			"\x43\x2c\x71\x8b\xa2\x55\xd2\x0f\x1d\x7f\xe3\xe1"
+			"\x2a\xa3\xe9\x2c\x25\x89\xc7\x14\x52\x99\x56\xcc"
+			"\xc3\xdf\xb3\x81",
+		.expectedlen = 64,
+		.addtla = (unsigned char *)
+			"\x66\xef\x42\xd6\x9a\x8c\x3d\x6d\x4a\x9e\x95\xa6"
+			"\x91\x4d\x81\x56",
+		.addtlb = (unsigned char *)
+			"\xe3\x18\x83\xd9\x4b\x5e\xc4\xcc\xaa\x61\x2f\xbb"
+			"\x4a\x55\xd1\xc6",
+		.addtllen = 16,
+		.pers = NULL,
+		.perslen = 0,
+	}, {
+		.entropy = (unsigned char *)
+			"\xca\x4b\x1e\xfa\x75\xbd\x69\x36\x38\x73\xb8\xf9"
+			"\xdb\x4d\x35\x0e\x47\xbf\x6c\x37\x72\xfd\xf7\xa9",
+		.entropylen = 24,
+		.expected = (unsigned char *)
+			"\x59\xc3\x19\x79\x1b\xb1\xf3\x0e\xe9\x34\xae\x6e"
+			"\x8b\x1f\xad\x1f\x74\xca\x25\x45\x68\xb8\x7f\x75"
+			"\x12\xf8\xf2\xab\x4c\x23\x01\x03\x05\xe1\x70\xee"
+			"\x75\xd8\xcb\xeb\x23\x4c\x7a\x23\x6e\x12\x27\xdb"
+			"\x6f\x7a\xac\x3c\x44\xb7\x87\x4b\x65\x56\x74\x45"
+			"\x34\x30\x0c\x3d",
+		.expectedlen = 64,
+		.addtla = NULL,
+		.addtlb = NULL,
+		.addtllen = 0,
+		.pers = (unsigned char *)
+			"\xeb\xaa\x60\x2c\x4d\xbe\x33\xff\x1b\xef\xbf\x0a"
+			"\x0b\xc6\x97\x54",
+		.perslen = 16,
+	}, {
+		.entropy = (unsigned char *)
+			"\xc0\x70\x1f\x92\x50\x75\x8f\xcd\xf2\xbe\x73\x98"
+			"\x80\xdb\x66\xeb\x14\x68\xb4\xa5\x87\x9c\x2d\xa6",
+		.entropylen = 24,
+		.expected = (unsigned char *)
+			"\x97\xc0\xc0\xe5\xa0\xcc\xf2\x4f\x33\x63\x48\x8a"
+			"\xdb\x13\x0a\x35\x89\xbf\x80\x65\x62\xee\x13\x95"
+			"\x7c\x33\xd3\x7d\xf4\x07\x77\x7a\x2b\x65\x0b\x5f"
+			"\x45\x5c\x13\xf1\x90\x77\x7f\xc5\x04\x3f\xcc\x1a"
+			"\x38\xf8\xcd\x1b\xbb\xd5\x57\xd1\x4a\x4c\x2e\x8a"
+			"\x2b\x49\x1e\x5c",
+		.expectedlen = 64,
+		.addtla = (unsigned char *)
+			"\xf9\x01\xf8\x16\x7a\x1d\xff\xde\x8e\x3c\x83\xe2"
+			"\x44\x85\xe7\xfe",
+		.addtlb = (unsigned char *)
+			"\x17\x1c\x09\x38\xc2\x38\x9f\x97\x87\x60\x55\xb4"
+			"\x82\x16\x62\x7f",
+		.addtllen = 16,
+		.pers = (unsigned char *)
+			"\x80\x08\xae\xe8\xe9\x69\x40\xc5\x08\x73\xc7\x9f"
+			"\x8e\xcf\xe0\x02",
+		.perslen = 16,
+	},
+};
+
 /* Cast5 test vectors from RFC 2144 */
 #define CAST5_ENC_TEST_VECTORS		4
 #define CAST5_DEC_TEST_VECTORS		4
@@ -20907,8 +21791,8 @@ static struct cipher_testvec cast5_enc_tv_template[] = {
 			  "\xF5\xBC\x25\xD6\x02\x56\x57\x1C",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -21068,8 +21952,8 @@ static struct cipher_testvec cast5_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -21206,8 +22090,8 @@ static struct cipher_testvec cast5_cbc_enc_tv_template[] = {
 			  "\x1D\x18\x66\x44\x5B\x8F\x14\xEB",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -21344,8 +22228,8 @@ static struct cipher_testvec cast5_cbc_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -21495,8 +22379,8 @@ static struct cipher_testvec cast5_ctr_enc_tv_template[] = {
 			  "\xC0\x0D\x96\xAA\x23\xF8\xFE\x13",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -21646,8 +22530,8 @@ static struct cipher_testvec cast5_ctr_dec_tv_template[] = {
 			  "\xDC\x50\xE7\x7E\x15\x89\x20\xB7",
 		.rlen	= 496,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 496 - 16, 16 },
+		.np	= 3,
+		.tap	= { 496 - 20, 4, 16 },
 	},
 };
 
@@ -22805,8 +23689,8 @@ static struct cipher_testvec camellia_enc_tv_template[] = {
 			  "\x33\x1A\xBB\xD3\xA2\x7E\x97\x66",
 		.rlen	= 1008,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 1008 - 16, 16 },
+		.np	= 3,
+		.tap	= { 1008 - 20, 4, 16 },
 	},
 };
 
@@ -23105,8 +23989,8 @@ static struct cipher_testvec camellia_dec_tv_template[] = {
 			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D",
 		.rlen	= 1008,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 1008 - 16, 16 },
+		.np	= 3,
+		.tap	= { 1008 - 20, 4, 16 },
 	},
 };
 
@@ -23401,8 +24285,8 @@ static struct cipher_testvec camellia_cbc_enc_tv_template[] = {
 			  "\x70\xC5\xB9\x0B\x3B\x7A\x6E\x6C",
 		.rlen	= 1008,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 1008 - 16, 16 },
+		.np	= 3,
+		.tap	= { 1008 - 20, 4, 16 },
 	},
 };
 
@@ -23697,8 +24581,8 @@ static struct cipher_testvec camellia_cbc_dec_tv_template[] = {
 			  "\x72\x09\xA0\x14\xAB\x42\xD9\x4D",
 		.rlen	= 1008,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 1008 - 16, 16 },
+		.np	= 3,
+		.tap	= { 1008 - 20, 4, 16 },
 	},
 };
 
@@ -25283,8 +26167,8 @@ static struct cipher_testvec camellia_lrw_enc_tv_template[] = {
 			  "\x5a\xa8\x92\x7f\xba\xe6\x0c\x95",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -25536,8 +26420,8 @@ static struct cipher_testvec camellia_lrw_dec_tv_template[] = {
 			  "\x21\xc4\xc2\x75\x67\x89\x37\x0a",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -25878,8 +26762,8 @@ static struct cipher_testvec camellia_xts_enc_tv_template[] = {
 			  "\xd5\xc6\x99\xcc\x4e\x6c\x94\x95",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
@@ -26221,8 +27105,8 @@ static struct cipher_testvec camellia_xts_dec_tv_template[] = {
 			  "\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
 		.rlen	= 512,
 		.also_non_np = 1,
-		.np	= 2,
-		.tap	= { 512 - 16, 16 },
+		.np	= 3,
+		.tap	= { 512 - 20, 4, 16 },
 	},
 };
 
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index c67f6f5ad61..36b0e61f9c0 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -30,6 +30,10 @@
 #include <linux/types.h>
 #include <linux/dmi.h>
 #include <linux/delay.h>
+#ifdef CONFIG_ACPI_PROCFS_POWER
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#endif
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
 #include <linux/acpi.h>
@@ -52,6 +56,7 @@ MODULE_AUTHOR("Paul Diefenbaugh");
 MODULE_DESCRIPTION("ACPI AC Adapter Driver");
 MODULE_LICENSE("GPL");
 
+
 static int acpi_ac_add(struct acpi_device *device);
 static int acpi_ac_remove(struct acpi_device *device);
 static void acpi_ac_notify(struct acpi_device *device, u32 event);
@@ -67,6 +72,13 @@ static int acpi_ac_resume(struct device *dev);
 #endif
 static SIMPLE_DEV_PM_OPS(acpi_ac_pm, NULL, acpi_ac_resume);
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+extern struct proc_dir_entry *acpi_lock_ac_dir(void);
+extern void *acpi_unlock_ac_dir(struct proc_dir_entry *acpi_ac_dir);
+static int acpi_ac_open_fs(struct inode *inode, struct file *file);
+#endif
+
+
 static int ac_sleep_before_get_state_ms;
 
 static struct acpi_driver acpi_ac_driver = {
@@ -91,6 +103,16 @@ struct acpi_ac {
 
 #define to_acpi_ac(x) container_of(x, struct acpi_ac, charger)
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+static const struct file_operations acpi_ac_fops = {
+	.owner = THIS_MODULE,
+	.open = acpi_ac_open_fs,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+#endif
+
 /* --------------------------------------------------------------------------
                                AC Adapter Management
    -------------------------------------------------------------------------- */
@@ -143,6 +165,83 @@ static enum power_supply_property ac_props[] = {
 	POWER_SUPPLY_PROP_ONLINE,
 };
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+/* --------------------------------------------------------------------------
+                              FS Interface (/proc)
+   -------------------------------------------------------------------------- */
+
+static struct proc_dir_entry *acpi_ac_dir;
+
+static int acpi_ac_seq_show(struct seq_file *seq, void *offset)
+{
+	struct acpi_ac *ac = seq->private;
+
+
+	if (!ac)
+		return 0;
+
+	if (acpi_ac_get_state(ac)) {
+		seq_puts(seq, "ERROR: Unable to read AC Adapter state\n");
+		return 0;
+	}
+
+	seq_puts(seq, "state:                   ");
+	switch (ac->state) {
+	case ACPI_AC_STATUS_OFFLINE:
+		seq_puts(seq, "off-line\n");
+		break;
+	case ACPI_AC_STATUS_ONLINE:
+		seq_puts(seq, "on-line\n");
+		break;
+	default:
+		seq_puts(seq, "unknown\n");
+		break;
+	}
+
+	return 0;
+}
+
+static int acpi_ac_open_fs(struct inode *inode, struct file *file)
+{
+	return single_open(file, acpi_ac_seq_show, PDE_DATA(inode));
+}
+
+static int acpi_ac_add_fs(struct acpi_ac *ac)
+{
+	struct proc_dir_entry *entry = NULL;
+
+	printk(KERN_WARNING PREFIX "Deprecated procfs I/F for AC is loaded,"
+			" please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
+	if (!acpi_device_dir(ac->device)) {
+		acpi_device_dir(ac->device) =
+			proc_mkdir(acpi_device_bid(ac->device), acpi_ac_dir);
+		if (!acpi_device_dir(ac->device))
+			return -ENODEV;
+	}
+
+	/* 'state' [R] */
+	entry = proc_create_data(ACPI_AC_FILE_STATE,
+				 S_IRUGO, acpi_device_dir(ac->device),
+				 &acpi_ac_fops, ac);
+	if (!entry)
+		return -ENODEV;
+	return 0;
+}
+
+static int acpi_ac_remove_fs(struct acpi_ac *ac)
+{
+
+	if (acpi_device_dir(ac->device)) {
+		remove_proc_entry(ACPI_AC_FILE_STATE,
+				  acpi_device_dir(ac->device));
+		remove_proc_entry(acpi_device_bid(ac->device), acpi_ac_dir);
+		acpi_device_dir(ac->device) = NULL;
+	}
+
+	return 0;
+}
+#endif
+
 /* --------------------------------------------------------------------------
                                    Driver Model
    -------------------------------------------------------------------------- */
@@ -243,6 +342,11 @@ static int acpi_ac_add(struct acpi_device *device)
 		goto end;
 
 	ac->charger.name = acpi_device_bid(device);
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	result = acpi_ac_add_fs(ac);
+	if (result)
+		goto end;
+#endif
 	ac->charger.type = POWER_SUPPLY_TYPE_MAINS;
 	ac->charger.properties = ac_props;
 	ac->charger.num_properties = ARRAY_SIZE(ac_props);
@@ -258,8 +362,12 @@ static int acpi_ac_add(struct acpi_device *device)
 	ac->battery_nb.notifier_call = acpi_ac_battery_notify;
 	register_acpi_notifier(&ac->battery_nb);
 end:
-	if (result)
+	if (result) {
+#ifdef CONFIG_ACPI_PROCFS_POWER
+		acpi_ac_remove_fs(ac);
+#endif
 		kfree(ac);
+	}
 
 	dmi_check_system(ac_dmi_table);
 	return result;
@@ -303,6 +411,10 @@ static int acpi_ac_remove(struct acpi_device *device)
 		power_supply_unregister(&ac->charger);
 	unregister_acpi_notifier(&ac->battery_nb);
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_ac_remove_fs(ac);
+#endif
+
 	kfree(ac);
 
 	return 0;
@@ -315,9 +427,20 @@ static int __init acpi_ac_init(void)
 	if (acpi_disabled)
 		return -ENODEV;
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_ac_dir = acpi_lock_ac_dir();
+	if (!acpi_ac_dir)
+		return -ENODEV;
+#endif
+
+
 	result = acpi_bus_register_driver(&acpi_ac_driver);
-	if (result < 0)
+	if (result < 0) {
+#ifdef CONFIG_ACPI_PROCFS_POWER
+		acpi_unlock_ac_dir(acpi_ac_dir);
+#endif
 		return -ENODEV;
+	}
 
 	return 0;
 }
@@ -325,6 +448,9 @@ static int __init acpi_ac_init(void)
 static void __exit acpi_ac_exit(void)
 {
 	acpi_bus_unregister_driver(&acpi_ac_driver);
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_unlock_ac_dir(acpi_ac_dir);
+#endif
 }
 module_init(acpi_ac_init);
 module_exit(acpi_ac_exit);
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 63407d26488..9cb65b0e759 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -34,6 +34,9 @@ ACPI_MODULE_NAME("acpi_lpss");
 
 /* Offsets relative to LPSS_PRIVATE_OFFSET */
 #define LPSS_CLK_DIVIDER_DEF_MASK	(BIT(1) | BIT(16))
+#define LPSS_RESETS			0x04
+#define LPSS_RESETS_RESET_FUNC		BIT(0)
+#define LPSS_RESETS_RESET_APB		BIT(1)
 #define LPSS_GENERAL			0x08
 #define LPSS_GENERAL_LTR_MODE_SW	BIT(2)
 #define LPSS_GENERAL_UART_RTS_OVRD	BIT(3)
@@ -99,6 +102,17 @@ static void lpss_uart_setup(struct lpss_private_data *pdata)
 	writel(reg | LPSS_GENERAL_UART_RTS_OVRD, pdata->mmio_base + offset);
 }
 
+static void lpss_i2c_setup(struct lpss_private_data *pdata)
+{
+	unsigned int offset;
+	u32 val;
+
+	offset = pdata->dev_desc->prv_offset + LPSS_RESETS;
+	val = readl(pdata->mmio_base + offset);
+	val |= LPSS_RESETS_RESET_APB | LPSS_RESETS_RESET_FUNC;
+	writel(val, pdata->mmio_base + offset);
+}
+
 static struct lpss_device_desc lpt_dev_desc = {
 	.clk_required = true,
 	.prv_offset = 0x800,
@@ -171,6 +185,7 @@ static struct lpss_device_desc byt_i2c_dev_desc = {
 	.prv_offset = 0x800,
 	.save_ctx = true,
 	.shared_clock = &i2c_clock,
+	.setup = lpss_i2c_setup,
 };
 
 #else
diff --git a/drivers/acpi/acpi_pnp.c b/drivers/acpi/acpi_pnp.c
index 6703c1fd993..4ddb0dca56f 100644
--- a/drivers/acpi/acpi_pnp.c
+++ b/drivers/acpi/acpi_pnp.c
@@ -14,6 +14,8 @@
 #include <linux/module.h>
 
 static const struct acpi_device_id acpi_pnp_device_ids[] = {
+	/* soc_button_array */
+	{"PNP0C40"},
 	/* pata_isapnp */
 	{"PNP0600"},		/* Generic ESDI/IDE/ATA compatible hard disk controller */
 	/* floppy */
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index e48fc98e71c..130f513e08c 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -32,8 +32,10 @@
 #include <linux/jiffies.h>
 #include <linux/async.h>
 #include <linux/dmi.h>
+#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/delay.h>
 #include <asm/unaligned.h>
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
@@ -70,6 +72,7 @@ MODULE_DESCRIPTION("ACPI Battery Driver");
 MODULE_LICENSE("GPL");
 
 static int battery_bix_broken_package;
+static int battery_notification_delay_ms;
 static unsigned int cache_time = 1000;
 module_param(cache_time, uint, 0644);
 MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
@@ -532,6 +535,20 @@ static int acpi_battery_get_state(struct acpi_battery *battery)
 			" invalid.\n");
 	}
 
+	/*
+	 * When fully charged, some batteries wrongly report
+	 * capacity_now = design_capacity instead of = full_charge_capacity
+	 */
+	if (battery->capacity_now > battery->full_charge_capacity
+	    && battery->full_charge_capacity != ACPI_BATTERY_VALUE_UNKNOWN) {
+		battery->capacity_now = battery->full_charge_capacity;
+		if (battery->capacity_now != battery->design_capacity)
+			printk_once(KERN_WARNING FW_BUG
+				"battery: reported current charge level (%d) "
+				"is higher than reported maximum charge level (%d).\n",
+				battery->capacity_now, battery->full_charge_capacity);
+	}
+
 	if (test_bit(ACPI_BATTERY_QUIRK_PERCENTAGE_CAPACITY, &battery->flags)
 	    && battery->capacity_now >= 0 && battery->capacity_now <= 100)
 		battery->capacity_now = (battery->capacity_now *
@@ -930,7 +947,10 @@ static ssize_t acpi_battery_write_alarm(struct file *file,
 		goto end;
 	}
 	alarm_string[count] = '\0';
-	battery->alarm = simple_strtol(alarm_string, NULL, 0);
+	if (kstrtoint(alarm_string, 0, &battery->alarm)) {
+		result = -EINVAL;
+		goto end;
+	}
 	result = acpi_battery_set_alarm(battery);
       end:
 	if (!result)
@@ -1062,6 +1082,14 @@ static void acpi_battery_notify(struct acpi_device *device, u32 event)
 	if (!battery)
 		return;
 	old = battery->bat.dev;
+	/*
+	* On Acer Aspire V5-573G notifications are sometimes triggered too
+	* early. For example, when AC is unplugged and notification is
+	* triggered, battery state is still reported as "Full", and changes to
+	* "Discharging" only after short delay, without any notification.
+	*/
+	if (battery_notification_delay_ms > 0)
+		msleep(battery_notification_delay_ms);
 	if (event == ACPI_BATTERY_NOTIFY_INFO)
 		acpi_battery_refresh(battery);
 	acpi_battery_update(battery, false);
@@ -1106,17 +1134,60 @@ static int battery_notify(struct notifier_block *nb,
 	return 0;
 }
 
+static int battery_bix_broken_package_quirk(const struct dmi_system_id *d)
+{
+	battery_bix_broken_package = 1;
+	return 0;
+}
+
+static int battery_notification_delay_quirk(const struct dmi_system_id *d)
+{
+	battery_notification_delay_ms = 1000;
+	return 0;
+}
+
 static struct dmi_system_id bat_dmi_table[] = {
 	{
+		.callback = battery_bix_broken_package_quirk,
 		.ident = "NEC LZ750/LS",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "PC-LZ750LS"),
 		},
 	},
+	{
+		.callback = battery_notification_delay_quirk,
+		.ident = "Acer Aspire V5-573G",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-573G"),
+		},
+	},
 	{},
 };
 
+/*
+ * Some machines'(E,G Lenovo Z480) ECs are not stable
+ * during boot up and this causes battery driver fails to be
+ * probed due to failure of getting battery information
+ * from EC sometimes. After several retries, the operation
+ * may work. So add retry code here and 20ms sleep between
+ * every retries.
+ */
+static int acpi_battery_update_retry(struct acpi_battery *battery)
+{
+	int retry, ret;
+
+	for (retry = 5; retry; retry--) {
+		ret = acpi_battery_update(battery, false);
+		if (!ret)
+			break;
+
+		msleep(20);
+	}
+	return ret;
+}
+
 static int acpi_battery_add(struct acpi_device *device)
 {
 	int result = 0;
@@ -1135,9 +1206,11 @@ static int acpi_battery_add(struct acpi_device *device)
 	mutex_init(&battery->sysfs_lock);
 	if (acpi_has_method(battery->device->handle, "_BIX"))
 		set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags);
-	result = acpi_battery_update(battery, false);
+
+	result = acpi_battery_update_retry(battery);
 	if (result)
 		goto fail;
+
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	result = acpi_battery_add_fs(device);
 #endif
@@ -1227,8 +1300,7 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
 	if (acpi_disabled)
 		return;
 
-	if (dmi_check_system(bat_dmi_table))
-		battery_bix_broken_package = 1;
+	dmi_check_system(bat_dmi_table);
 	
 #ifdef CONFIG_ACPI_PROCFS_POWER
 	acpi_battery_dir = acpi_lock_battery_dir();
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index ad11ba4a412..a66ab658abb 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1,11 +1,14 @@
 /*
- *  ec.c - ACPI Embedded Controller Driver (v2.1)
+ *  ec.c - ACPI Embedded Controller Driver (v2.2)
  *
- *  Copyright (C) 2006-2008 Alexey Starikovskiy <astarikovskiy@suse.de>
- *  Copyright (C) 2006 Denis Sadykov <denis.m.sadykov@intel.com>
- *  Copyright (C) 2004 Luming Yu <luming.yu@intel.com>
- *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
- *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *  Copyright (C) 2001-2014 Intel Corporation
+ *    Author: 2014       Lv Zheng <lv.zheng@intel.com>
+ *            2006, 2007 Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>
+ *            2006       Denis Sadykov <denis.m.sadykov@intel.com>
+ *            2004       Luming Yu <luming.yu@intel.com>
+ *            2001, 2002 Andy Grover <andrew.grover@intel.com>
+ *            2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *  Copyright (C) 2008      Alexey Starikovskiy <astarikovskiy@suse.de>
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  *
@@ -52,6 +55,7 @@
 /* EC status register */
 #define ACPI_EC_FLAG_OBF	0x01	/* Output buffer full */
 #define ACPI_EC_FLAG_IBF	0x02	/* Input buffer full */
+#define ACPI_EC_FLAG_CMD	0x08	/* Input buffer contains a command */
 #define ACPI_EC_FLAG_BURST	0x10	/* burst mode */
 #define ACPI_EC_FLAG_SCI	0x20	/* EC-SCI occurred */
 
@@ -78,6 +82,9 @@ enum {
 	EC_FLAGS_BLOCKED,		/* Transactions are blocked */
 };
 
+#define ACPI_EC_COMMAND_POLL		0x01 /* Available for command byte */
+#define ACPI_EC_COMMAND_COMPLETE	0x02 /* Completed last byte */
+
 /* ec.c is compiled in acpi namespace so this shows up as acpi.ec_delay param */
 static unsigned int ec_delay __read_mostly = ACPI_EC_DELAY;
 module_param(ec_delay, uint, 0644);
@@ -109,7 +116,7 @@ struct transaction {
 	u8 ri;
 	u8 wlen;
 	u8 rlen;
-	bool done;
+	u8 flags;
 };
 
 struct acpi_ec *boot_ec, *first_ec;
@@ -127,83 +134,104 @@ static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */
 static inline u8 acpi_ec_read_status(struct acpi_ec *ec)
 {
 	u8 x = inb(ec->command_addr);
-	pr_debug("---> status = 0x%2.2x\n", x);
+	pr_debug("EC_SC(R) = 0x%2.2x "
+		 "SCI_EVT=%d BURST=%d CMD=%d IBF=%d OBF=%d\n",
+		 x,
+		 !!(x & ACPI_EC_FLAG_SCI),
+		 !!(x & ACPI_EC_FLAG_BURST),
+		 !!(x & ACPI_EC_FLAG_CMD),
+		 !!(x & ACPI_EC_FLAG_IBF),
+		 !!(x & ACPI_EC_FLAG_OBF));
 	return x;
 }
 
 static inline u8 acpi_ec_read_data(struct acpi_ec *ec)
 {
 	u8 x = inb(ec->data_addr);
-	pr_debug("---> data = 0x%2.2x\n", x);
+	pr_debug("EC_DATA(R) = 0x%2.2x\n", x);
 	return x;
 }
 
 static inline void acpi_ec_write_cmd(struct acpi_ec *ec, u8 command)
 {
-	pr_debug("<--- command = 0x%2.2x\n", command);
+	pr_debug("EC_SC(W) = 0x%2.2x\n", command);
 	outb(command, ec->command_addr);
 }
 
 static inline void acpi_ec_write_data(struct acpi_ec *ec, u8 data)
 {
-	pr_debug("<--- data = 0x%2.2x\n", data);
+	pr_debug("EC_DATA(W) = 0x%2.2x\n", data);
 	outb(data, ec->data_addr);
 }
 
-static int ec_transaction_done(struct acpi_ec *ec)
+static int ec_transaction_completed(struct acpi_ec *ec)
 {
 	unsigned long flags;
 	int ret = 0;
 	spin_lock_irqsave(&ec->lock, flags);
-	if (!ec->curr || ec->curr->done)
+	if (ec->curr && (ec->curr->flags & ACPI_EC_COMMAND_COMPLETE))
 		ret = 1;
 	spin_unlock_irqrestore(&ec->lock, flags);
 	return ret;
 }
 
-static void start_transaction(struct acpi_ec *ec)
+static bool advance_transaction(struct acpi_ec *ec)
 {
-	ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0;
-	ec->curr->done = false;
-	acpi_ec_write_cmd(ec, ec->curr->command);
-}
-
-static void advance_transaction(struct acpi_ec *ec, u8 status)
-{
-	unsigned long flags;
 	struct transaction *t;
+	u8 status;
+	bool wakeup = false;
 
-	spin_lock_irqsave(&ec->lock, flags);
+	pr_debug("===== %s =====\n", in_interrupt() ? "IRQ" : "TASK");
+	status = acpi_ec_read_status(ec);
 	t = ec->curr;
 	if (!t)
-		goto unlock;
-	if (t->wlen > t->wi) {
-		if ((status & ACPI_EC_FLAG_IBF) == 0)
-			acpi_ec_write_data(ec,
-				t->wdata[t->wi++]);
-		else
-			goto err;
-	} else if (t->rlen > t->ri) {
-		if ((status & ACPI_EC_FLAG_OBF) == 1) {
-			t->rdata[t->ri++] = acpi_ec_read_data(ec);
-			if (t->rlen == t->ri)
-				t->done = true;
+		goto err;
+	if (t->flags & ACPI_EC_COMMAND_POLL) {
+		if (t->wlen > t->wi) {
+			if ((status & ACPI_EC_FLAG_IBF) == 0)
+				acpi_ec_write_data(ec, t->wdata[t->wi++]);
+			else
+				goto err;
+		} else if (t->rlen > t->ri) {
+			if ((status & ACPI_EC_FLAG_OBF) == 1) {
+				t->rdata[t->ri++] = acpi_ec_read_data(ec);
+				if (t->rlen == t->ri) {
+					t->flags |= ACPI_EC_COMMAND_COMPLETE;
+					wakeup = true;
+				}
+			} else
+				goto err;
+		} else if (t->wlen == t->wi &&
+			   (status & ACPI_EC_FLAG_IBF) == 0) {
+			t->flags |= ACPI_EC_COMMAND_COMPLETE;
+			wakeup = true;
+		}
+		return wakeup;
+	} else {
+		if ((status & ACPI_EC_FLAG_IBF) == 0) {
+			acpi_ec_write_cmd(ec, t->command);
+			t->flags |= ACPI_EC_COMMAND_POLL;
 		} else
 			goto err;
-	} else if (t->wlen == t->wi &&
-		   (status & ACPI_EC_FLAG_IBF) == 0)
-		t->done = true;
-	goto unlock;
+		return wakeup;
+	}
 err:
 	/*
 	 * If SCI bit is set, then don't think it's a false IRQ
 	 * otherwise will take a not handled IRQ as a false one.
 	 */
-	if (in_interrupt() && !(status & ACPI_EC_FLAG_SCI))
-		++t->irq_count;
+	if (!(status & ACPI_EC_FLAG_SCI)) {
+		if (in_interrupt() && t)
+			++t->irq_count;
+	}
+	return wakeup;
+}
 
-unlock:
-	spin_unlock_irqrestore(&ec->lock, flags);
+static void start_transaction(struct acpi_ec *ec)
+{
+	ec->curr->irq_count = ec->curr->wi = ec->curr->ri = 0;
+	ec->curr->flags = 0;
+	(void)advance_transaction(ec);
 }
 
 static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data);
@@ -228,15 +256,17 @@ static int ec_poll(struct acpi_ec *ec)
 			/* don't sleep with disabled interrupts */
 			if (EC_FLAGS_MSI || irqs_disabled()) {
 				udelay(ACPI_EC_MSI_UDELAY);
-				if (ec_transaction_done(ec))
+				if (ec_transaction_completed(ec))
 					return 0;
 			} else {
 				if (wait_event_timeout(ec->wait,
-						ec_transaction_done(ec),
+						ec_transaction_completed(ec),
 						msecs_to_jiffies(1)))
 					return 0;
 			}
-			advance_transaction(ec, acpi_ec_read_status(ec));
+			spin_lock_irqsave(&ec->lock, flags);
+			(void)advance_transaction(ec);
+			spin_unlock_irqrestore(&ec->lock, flags);
 		} while (time_before(jiffies, delay));
 		pr_debug("controller reset, restart transaction\n");
 		spin_lock_irqsave(&ec->lock, flags);
@@ -268,23 +298,6 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	return ret;
 }
 
-static int ec_check_ibf0(struct acpi_ec *ec)
-{
-	u8 status = acpi_ec_read_status(ec);
-	return (status & ACPI_EC_FLAG_IBF) == 0;
-}
-
-static int ec_wait_ibf0(struct acpi_ec *ec)
-{
-	unsigned long delay = jiffies + msecs_to_jiffies(ec_delay);
-	/* interrupt wait manually if GPE mode is not active */
-	while (time_before(jiffies, delay))
-		if (wait_event_timeout(ec->wait, ec_check_ibf0(ec),
-					msecs_to_jiffies(1)))
-			return 0;
-	return -ETIME;
-}
-
 static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 {
 	int status;
@@ -305,12 +318,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 			goto unlock;
 		}
 	}
-	if (ec_wait_ibf0(ec)) {
-		pr_err("input buffer is not empty, "
-				"aborting transaction\n");
-		status = -ETIME;
-		goto end;
-	}
 	pr_debug("transaction start (cmd=0x%02x, addr=0x%02x)\n",
 			t->command, t->wdata ? t->wdata[0] : 0);
 	/* disable GPE during transaction if storm is detected */
@@ -334,7 +341,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 		set_bit(EC_FLAGS_GPE_STORM, &ec->flags);
 	}
 	pr_debug("transaction end\n");
-end:
 	if (ec->global_lock)
 		acpi_release_global_lock(glk);
 unlock:
@@ -634,17 +640,14 @@ static int ec_check_sci(struct acpi_ec *ec, u8 state)
 static u32 acpi_ec_gpe_handler(acpi_handle gpe_device,
 	u32 gpe_number, void *data)
 {
+	unsigned long flags;
 	struct acpi_ec *ec = data;
-	u8 status = acpi_ec_read_status(ec);
 
-	pr_debug("~~~> interrupt, status:0x%02x\n", status);
-
-	advance_transaction(ec, status);
-	if (ec_transaction_done(ec) &&
-	    (acpi_ec_read_status(ec) & ACPI_EC_FLAG_IBF) == 0) {
+	spin_lock_irqsave(&ec->lock, flags);
+	if (advance_transaction(ec))
 		wake_up(&ec->wait);
-		ec_check_sci(ec, acpi_ec_read_status(ec));
-	}
+	spin_unlock_irqrestore(&ec->lock, flags);
+	ec_check_sci(ec, acpi_ec_read_status(ec));
 	return ACPI_INTERRUPT_HANDLED | ACPI_REENABLE_GPE;
 }
 
@@ -1066,8 +1069,10 @@ int __init acpi_ec_ecdt_probe(void)
 	/* fall through */
 	}
 
-	if (EC_FLAGS_SKIP_DSDT_SCAN)
+	if (EC_FLAGS_SKIP_DSDT_SCAN) {
+		kfree(saved_ec);
 		return -ENODEV;
+	}
 
 	/* This workaround is needed only on some broken machines,
 	 * which require early EC, but fail to provide ECDT */
@@ -1105,6 +1110,7 @@ install:
 	}
 error:
 	kfree(boot_ec);
+	kfree(saved_ec);
 	boot_ec = NULL;
 	return -ENODEV;
 }
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 147bc1b91b4..bad25b070fe 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -235,7 +235,8 @@ void acpi_os_vprintf(const char *fmt, va_list args)
 static unsigned long acpi_rsdp;
 static int __init setup_acpi_rsdp(char *arg)
 {
-	acpi_rsdp = simple_strtoul(arg, NULL, 16);
+	if (kstrtoul(arg, 16, &acpi_rsdp))
+		return -EINVAL;
 	return 0;
 }
 early_param("acpi_rsdp", setup_acpi_rsdp);
@@ -1810,6 +1811,16 @@ acpi_status __init acpi_os_initialize(void)
 	acpi_os_map_generic_address(&acpi_gbl_FADT.xpm1b_event_block);
 	acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe0_block);
 	acpi_os_map_generic_address(&acpi_gbl_FADT.xgpe1_block);
+	if (acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER) {
+		/*
+		 * Use acpi_os_map_generic_address to pre-map the reset
+		 * register if it's in system memory.
+		 */
+		int rv;
+
+		rv = acpi_os_map_generic_address(&acpi_gbl_FADT.reset_register);
+		pr_debug(PREFIX "%s: map reset_reg status %d\n", __func__, rv);
+	}
 
 	return AE_OK;
 }
@@ -1838,6 +1849,8 @@ acpi_status acpi_os_terminate(void)
 	acpi_os_unmap_generic_address(&acpi_gbl_FADT.xgpe0_block);
 	acpi_os_unmap_generic_address(&acpi_gbl_FADT.xpm1b_event_block);
 	acpi_os_unmap_generic_address(&acpi_gbl_FADT.xpm1a_event_block);
+	if (acpi_gbl_FADT.flags & ACPI_FADT_RESET_REGISTER)
+		acpi_os_unmap_generic_address(&acpi_gbl_FADT.reset_register);
 
 	destroy_workqueue(kacpid_wq);
 	destroy_workqueue(kacpi_notify_wq);
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 0bdacc5e26a..2ba8f02ced3 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -77,7 +77,7 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res)
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_MEMORY24:
 		memory24 = &ares->data.memory24;
-		if (!memory24->address_length)
+		if (!memory24->minimum && !memory24->address_length)
 			return false;
 		acpi_dev_get_memresource(res, memory24->minimum,
 					 memory24->address_length,
@@ -85,7 +85,7 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res)
 		break;
 	case ACPI_RESOURCE_TYPE_MEMORY32:
 		memory32 = &ares->data.memory32;
-		if (!memory32->address_length)
+		if (!memory32->minimum && !memory32->address_length)
 			return false;
 		acpi_dev_get_memresource(res, memory32->minimum,
 					 memory32->address_length,
@@ -93,7 +93,7 @@ bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res)
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
 		fixed_memory32 = &ares->data.fixed_memory32;
-		if (!fixed_memory32->address_length)
+		if (!fixed_memory32->address && !fixed_memory32->address_length)
 			return false;
 		acpi_dev_get_memresource(res, fixed_memory32->address,
 					 fixed_memory32->address_length,
@@ -150,7 +150,7 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res)
 	switch (ares->type) {
 	case ACPI_RESOURCE_TYPE_IO:
 		io = &ares->data.io;
-		if (!io->address_length)
+		if (!io->minimum && !io->address_length)
 			return false;
 		acpi_dev_get_ioresource(res, io->minimum,
 					io->address_length,
@@ -158,7 +158,7 @@ bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res)
 		break;
 	case ACPI_RESOURCE_TYPE_FIXED_IO:
 		fixed_io = &ares->data.fixed_io;
-		if (!fixed_io->address_length)
+		if (!fixed_io->address && !fixed_io->address_length)
 			return false;
 		acpi_dev_get_ioresource(res, fixed_io->address,
 					fixed_io->address_length,
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index c11e3795431..b3e3cc73ba7 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -19,6 +19,7 @@
 #include <linux/acpi.h>
 #include <linux/module.h>
 #include <asm/io.h>
+#include <trace/events/power.h>
 
 #include "internal.h"
 #include "sleep.h"
@@ -501,6 +502,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state)
 
 	ACPI_FLUSH_CPU_CACHE();
 
+	trace_suspend_resume(TPS("acpi_suspend"), acpi_state, true);
 	switch (acpi_state) {
 	case ACPI_STATE_S1:
 		barrier();
@@ -516,6 +518,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state)
 		pr_info(PREFIX "Low-level resume complete\n");
 		break;
 	}
+	trace_suspend_resume(TPS("acpi_suspend"), acpi_state, false);
 
 	/* This violates the spec but is required for bug compatibility. */
 	acpi_write_bit_register(ACPI_BITREG_SCI_ENABLE, 1);
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 05550ba44d3..6d5a6cda073 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -360,7 +360,8 @@ static int __init acpi_parse_apic_instance(char *str)
 	if (!str)
 		return -EINVAL;
 
-	acpi_apic_instance = simple_strtoul(str, NULL, 0);
+	if (kstrtoint(str, 0, &acpi_apic_instance))
+		return -EINVAL;
 
 	pr_notice("Shall use APIC/MADT table %d\n", acpi_apic_instance);
 
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 101fb090dcb..350d52a8f78 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -68,7 +68,7 @@ MODULE_AUTHOR("Bruno Ducrot");
 MODULE_DESCRIPTION("ACPI Video Driver");
 MODULE_LICENSE("GPL");
 
-static bool brightness_switch_enabled;
+static bool brightness_switch_enabled = 1;
 module_param(brightness_switch_enabled, bool, 0644);
 
 /*
@@ -82,7 +82,7 @@ module_param(allow_duplicates, bool, 0644);
  * For Windows 8 systems: used to decide if video module
  * should skip registering backlight interface of its own.
  */
-static int use_native_backlight_param = -1;
+static int use_native_backlight_param = 1;
 module_param_named(use_native_backlight, use_native_backlight_param, int, 0444);
 static bool use_native_backlight_dmi = false;
 
@@ -241,13 +241,14 @@ static bool acpi_video_use_native_backlight(void)
 		return use_native_backlight_dmi;
 }
 
-static bool acpi_video_verify_backlight_support(void)
+bool acpi_video_verify_backlight_support(void)
 {
 	if (acpi_osi_is_win8() && acpi_video_use_native_backlight() &&
 	    backlight_device_registered(BACKLIGHT_RAW))
 		return false;
 	return acpi_video_backlight_support();
 }
+EXPORT_SYMBOL_GPL(acpi_video_verify_backlight_support);
 
 /* backlight device sysfs support */
 static int acpi_video_get_brightness(struct backlight_device *bd)
@@ -563,6 +564,14 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 		},
 	},
 	{
+	 .callback = video_set_use_native_backlight,
+	 .ident = "Acer TravelMate B113",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate B113"),
+		},
+	},
+	{
 	.callback = video_set_use_native_backlight,
 	.ident = "HP ProBook 4340s",
 	.matches = {
@@ -572,6 +581,14 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 	},
 	{
 	.callback = video_set_use_native_backlight,
+	.ident = "HP ProBook 4540s",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "HP ProBook 4540s"),
+		},
+	},
+	{
+	.callback = video_set_use_native_backlight,
 	.ident = "HP ProBook 2013 models",
 	.matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 33e3db548a2..c42feb2bacd 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -166,6 +166,14 @@ static struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"),
 		},
 	},
+	{
+	.callback = video_detect_force_vendor,
+	.ident = "Dell Inspiron 5737",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5737"),
+		},
+	},
 	{ },
 };
 
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 0033fafc470..e65d400efd4 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -123,6 +123,15 @@ config AHCI_IMX
 
 	  If unsure, say N.
 
+config AHCI_MVEBU
+	tristate "Marvell EBU AHCI SATA support"
+	depends on ARCH_MVEBU
+	help
+	  This option enables support for the Marvebu EBU SoC's
+	  onboard AHCI SATA.
+
+	  If unsure, say N.
+
 config AHCI_SUNXI
 	tristate "Allwinner sunxi AHCI SATA support"
 	depends on ARCH_SUNXI
@@ -132,6 +141,15 @@ config AHCI_SUNXI
 
 	  If unsure, say N.
 
+config AHCI_TEGRA
+	tristate "NVIDIA Tegra124 AHCI SATA support"
+	depends on ARCH_TEGRA
+	help
+	  This option enables support for the NVIDIA Tegra124 SoC's
+	  onboard AHCI SATA.
+
+	  If unsure, say N.
+
 config AHCI_XGENE
 	tristate "APM X-Gene 6.0Gbps AHCI SATA host controller support"
 	depends on PHY_XGENE
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index 44c8016e565..ae41107afc1 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -12,8 +12,10 @@ obj-$(CONFIG_SATA_DWC)		+= sata_dwc_460ex.o
 obj-$(CONFIG_SATA_HIGHBANK)	+= sata_highbank.o libahci.o
 obj-$(CONFIG_AHCI_DA850)	+= ahci_da850.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_IMX)		+= ahci_imx.o libahci.o libahci_platform.o
+obj-$(CONFIG_AHCI_MVEBU)	+= ahci_mvebu.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_SUNXI)	+= ahci_sunxi.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_ST)		+= ahci_st.o libahci.o libahci_platform.o
+obj-$(CONFIG_AHCI_TEGRA)	+= ahci_tegra.o libahci.o libahci_platform.o
 obj-$(CONFIG_AHCI_XGENE)	+= ahci_xgene.o libahci.o libahci_platform.o
 
 # SFF w/ custom DMA
diff --git a/drivers/ata/acard-ahci.c b/drivers/ata/acard-ahci.c
index b51605ac597..25d0ac32e72 100644
--- a/drivers/ata/acard-ahci.c
+++ b/drivers/ata/acard-ahci.c
@@ -77,7 +77,7 @@ static bool acard_ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int acard_ahci_port_start(struct ata_port *ap);
 static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int acard_ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg);
 static int acard_ahci_pci_device_resume(struct pci_dev *pdev);
 #endif
@@ -118,13 +118,13 @@ static struct pci_driver acard_ahci_pci_driver = {
 	.id_table		= acard_ahci_pci_tbl,
 	.probe			= acard_ahci_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= acard_ahci_pci_device_suspend,
 	.resume			= acard_ahci_pci_device_resume,
 #endif
 };
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int acard_ahci_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -441,7 +441,7 @@ static int acard_ahci_init_one(struct pci_dev *pdev, const struct pci_device_id
 	hpriv->mmio = pcim_iomap_table(pdev)[AHCI_PCI_BAR];
 
 	/* save initial config */
-	ahci_save_initial_config(&pdev->dev, hpriv, 0, 0);
+	ahci_save_initial_config(&pdev->dev, hpriv);
 
 	/* prepare host */
 	if (hpriv->cap & HOST_CAP_NCQ)
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 60707814a84..a29f8012fb0 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -445,13 +445,18 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9192),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 on some Gigabyte */
+	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0),
+	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x91a3),
 	  .driver_data = board_ahci_yes_fbs },
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9230),
 	  .driver_data = board_ahci_yes_fbs },
+	{ PCI_DEVICE(PCI_VENDOR_ID_TTI, 0x0642),
+	  .driver_data = board_ahci_yes_fbs },
 
 	/* Promise */
 	{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci },	/* PDC42819 */
+	{ PCI_VDEVICE(PROMISE, 0x3781), board_ahci },   /* FastTrak TX8660 ahci-mode */
 
 	/* Asmedia */
 	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */
@@ -521,8 +526,7 @@ static void ahci_pci_save_initial_config(struct pci_dev *pdev,
 			  "Disabling your PATA port. Use the boot option 'ahci.marvell_enable=0' to avoid this.\n");
 	}
 
-	ahci_save_initial_config(&pdev->dev, hpriv, force_port_map,
-				 mask_port_map);
+	ahci_save_initial_config(&pdev->dev, hpriv);
 }
 
 static int ahci_pci_reset_controller(struct ata_host *host)
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index af63c75c200..59ae0ee0014 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -53,7 +53,7 @@
 
 enum {
 	AHCI_MAX_PORTS		= 32,
-	AHCI_MAX_CLKS		= 3,
+	AHCI_MAX_CLKS		= 4,
 	AHCI_MAX_SG		= 168, /* hardware max is 64K */
 	AHCI_DMA_BOUNDARY	= 0xffffffff,
 	AHCI_MAX_CMDS		= 32,
@@ -237,6 +237,7 @@ enum {
 						        error-handling stage) */
 	AHCI_HFLAG_MULTI_MSI		= (1 << 16), /* multiple PCI MSIs */
 	AHCI_HFLAG_NO_DEVSLP		= (1 << 17), /* no device sleep */
+	AHCI_HFLAG_NO_FBS		= (1 << 18), /* no FBS */
 
 	/* ap->flags bits */
 
@@ -315,8 +316,12 @@ struct ahci_port_priv {
 };
 
 struct ahci_host_priv {
-	void __iomem *		mmio;		/* bus-independent mem map */
+	/* Input fields */
 	unsigned int		flags;		/* AHCI_HFLAG_* */
+	u32			force_port_map;	/* force port map */
+	u32			mask_port_map;	/* mask out particular bits */
+
+	void __iomem *		mmio;		/* bus-independent mem map */
 	u32			cap;		/* cap to use */
 	u32			cap2;		/* cap2 to use */
 	u32			port_map;	/* port map to use */
@@ -329,7 +334,12 @@ struct ahci_host_priv {
 	bool			got_runtime_pm; /* Did we do pm_runtime_get? */
 	struct clk		*clks[AHCI_MAX_CLKS]; /* Optional */
 	struct regulator	*target_pwr;	/* Optional */
-	struct phy		*phy;		/* If platform uses phy */
+	/*
+	 * If platform uses PHYs. There is a 1:1 relation between the port number and
+	 * the PHY position in this array.
+	 */
+	struct phy		**phys;
+	unsigned		nports;		/* Number of ports */
 	void			*plat_data;	/* Other platform data */
 	/*
 	 * Optional ahci_start_engine override, if not set this gets set to the
@@ -360,9 +370,7 @@ unsigned int ahci_dev_classify(struct ata_port *ap);
 void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag,
 			u32 opts);
 void ahci_save_initial_config(struct device *dev,
-			      struct ahci_host_priv *hpriv,
-			      unsigned int force_port_map,
-			      unsigned int mask_port_map);
+			      struct ahci_host_priv *hpriv);
 void ahci_init_controller(struct ata_host *host);
 int ahci_reset_controller(struct ata_host *host);
 
@@ -370,7 +378,9 @@ int ahci_do_softreset(struct ata_link *link, unsigned int *class,
 		      int pmp, unsigned long deadline,
 		      int (*check_ready)(struct ata_link *link));
 
+unsigned int ahci_qc_issue(struct ata_queued_cmd *qc);
 int ahci_stop_engine(struct ata_port *ap);
+void ahci_start_fis_rx(struct ata_port *ap);
 void ahci_start_engine(struct ata_port *ap);
 int ahci_check_ready(struct ata_link *link);
 int ahci_kick_engine(struct ata_port *ap);
diff --git a/drivers/ata/ahci_da850.c b/drivers/ata/ahci_da850.c
index 2c83613ce2d..ad1e71ec10c 100644
--- a/drivers/ata/ahci_da850.c
+++ b/drivers/ata/ahci_da850.c
@@ -85,7 +85,7 @@ static int ahci_da850_probe(struct platform_device *pdev)
 
 	da850_sata_init(dev, pwrdn_reg, hpriv->mmio);
 
-	rc = ahci_platform_init_host(pdev, hpriv, &ahci_da850_port_info, 0, 0);
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_da850_port_info);
 	if (rc)
 		goto disable_resources;
 
diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
index 8befeb69eeb..f3970b4ed88 100644
--- a/drivers/ata/ahci_imx.c
+++ b/drivers/ata/ahci_imx.c
@@ -58,10 +58,13 @@ enum ahci_imx_type {
 struct imx_ahci_priv {
 	struct platform_device *ahci_pdev;
 	enum ahci_imx_type type;
+	struct clk *sata_clk;
+	struct clk *sata_ref_clk;
 	struct clk *ahb_clk;
 	struct regmap *gpr;
 	bool no_device;
 	bool first_time;
+	u32 phy_params;
 };
 
 static int ahci_imx_hotplug;
@@ -224,7 +227,7 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv)
 			return ret;
 	}
 
-	ret = ahci_platform_enable_clks(hpriv);
+	ret = clk_prepare_enable(imxpriv->sata_ref_clk);
 	if (ret < 0)
 		goto disable_regulator;
 
@@ -246,14 +249,7 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv)
 				   IMX6Q_GPR13_SATA_TX_LVL_MASK |
 				   IMX6Q_GPR13_SATA_MPLL_CLK_EN |
 				   IMX6Q_GPR13_SATA_TX_EDGE_RATE,
-				   IMX6Q_GPR13_SATA_RX_EQ_VAL_3_0_DB |
-				   IMX6Q_GPR13_SATA_RX_LOS_LVL_SATA2M |
-				   IMX6Q_GPR13_SATA_RX_DPLL_MODE_2P_4F |
-				   IMX6Q_GPR13_SATA_SPD_MODE_3P0G |
-				   IMX6Q_GPR13_SATA_MPLL_SS_EN |
-				   IMX6Q_GPR13_SATA_TX_ATTEN_9_16 |
-				   IMX6Q_GPR13_SATA_TX_BOOST_3_33_DB |
-				   IMX6Q_GPR13_SATA_TX_LVL_1_025_V);
+				   imxpriv->phy_params);
 		regmap_update_bits(imxpriv->gpr, IOMUXC_GPR13,
 				   IMX6Q_GPR13_SATA_MPLL_CLK_EN,
 				   IMX6Q_GPR13_SATA_MPLL_CLK_EN);
@@ -263,7 +259,7 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv)
 		ret = imx_sata_phy_reset(hpriv);
 		if (ret) {
 			dev_err(dev, "failed to reset phy: %d\n", ret);
-			goto disable_regulator;
+			goto disable_clk;
 		}
 	}
 
@@ -271,6 +267,8 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv)
 
 	return 0;
 
+disable_clk:
+	clk_disable_unprepare(imxpriv->sata_ref_clk);
 disable_regulator:
 	if (hpriv->target_pwr)
 		regulator_disable(hpriv->target_pwr);
@@ -291,7 +289,7 @@ static void imx_sata_disable(struct ahci_host_priv *hpriv)
 				   !IMX6Q_GPR13_SATA_MPLL_CLK_EN);
 	}
 
-	ahci_platform_disable_clks(hpriv);
+	clk_disable_unprepare(imxpriv->sata_ref_clk);
 
 	if (hpriv->target_pwr)
 		regulator_disable(hpriv->target_pwr);
@@ -324,6 +322,9 @@ static void ahci_imx_error_handler(struct ata_port *ap)
 	writel(reg_val | IMX_P0PHYCR_TEST_PDDQ, mmio + IMX_P0PHYCR);
 	imx_sata_disable(hpriv);
 	imxpriv->no_device = true;
+
+	dev_info(ap->dev, "no device found, disabling link.\n");
+	dev_info(ap->dev, "pass " MODULE_PARAM_PREFIX ".hotplug=1 to enable hotplug\n");
 }
 
 static int ahci_imx_softreset(struct ata_link *link, unsigned int *class,
@@ -364,6 +365,165 @@ static const struct of_device_id imx_ahci_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, imx_ahci_of_match);
 
+struct reg_value {
+	u32 of_value;
+	u32 reg_value;
+};
+
+struct reg_property {
+	const char *name;
+	const struct reg_value *values;
+	size_t num_values;
+	u32 def_value;
+	u32 set_value;
+};
+
+static const struct reg_value gpr13_tx_level[] = {
+	{  937, IMX6Q_GPR13_SATA_TX_LVL_0_937_V },
+	{  947, IMX6Q_GPR13_SATA_TX_LVL_0_947_V },
+	{  957, IMX6Q_GPR13_SATA_TX_LVL_0_957_V },
+	{  966, IMX6Q_GPR13_SATA_TX_LVL_0_966_V },
+	{  976, IMX6Q_GPR13_SATA_TX_LVL_0_976_V },
+	{  986, IMX6Q_GPR13_SATA_TX_LVL_0_986_V },
+	{  996, IMX6Q_GPR13_SATA_TX_LVL_0_996_V },
+	{ 1005, IMX6Q_GPR13_SATA_TX_LVL_1_005_V },
+	{ 1015, IMX6Q_GPR13_SATA_TX_LVL_1_015_V },
+	{ 1025, IMX6Q_GPR13_SATA_TX_LVL_1_025_V },
+	{ 1035, IMX6Q_GPR13_SATA_TX_LVL_1_035_V },
+	{ 1045, IMX6Q_GPR13_SATA_TX_LVL_1_045_V },
+	{ 1054, IMX6Q_GPR13_SATA_TX_LVL_1_054_V },
+	{ 1064, IMX6Q_GPR13_SATA_TX_LVL_1_064_V },
+	{ 1074, IMX6Q_GPR13_SATA_TX_LVL_1_074_V },
+	{ 1084, IMX6Q_GPR13_SATA_TX_LVL_1_084_V },
+	{ 1094, IMX6Q_GPR13_SATA_TX_LVL_1_094_V },
+	{ 1104, IMX6Q_GPR13_SATA_TX_LVL_1_104_V },
+	{ 1113, IMX6Q_GPR13_SATA_TX_LVL_1_113_V },
+	{ 1123, IMX6Q_GPR13_SATA_TX_LVL_1_123_V },
+	{ 1133, IMX6Q_GPR13_SATA_TX_LVL_1_133_V },
+	{ 1143, IMX6Q_GPR13_SATA_TX_LVL_1_143_V },
+	{ 1152, IMX6Q_GPR13_SATA_TX_LVL_1_152_V },
+	{ 1162, IMX6Q_GPR13_SATA_TX_LVL_1_162_V },
+	{ 1172, IMX6Q_GPR13_SATA_TX_LVL_1_172_V },
+	{ 1182, IMX6Q_GPR13_SATA_TX_LVL_1_182_V },
+	{ 1191, IMX6Q_GPR13_SATA_TX_LVL_1_191_V },
+	{ 1201, IMX6Q_GPR13_SATA_TX_LVL_1_201_V },
+	{ 1211, IMX6Q_GPR13_SATA_TX_LVL_1_211_V },
+	{ 1221, IMX6Q_GPR13_SATA_TX_LVL_1_221_V },
+	{ 1230, IMX6Q_GPR13_SATA_TX_LVL_1_230_V },
+	{ 1240, IMX6Q_GPR13_SATA_TX_LVL_1_240_V }
+};
+
+static const struct reg_value gpr13_tx_boost[] = {
+	{    0, IMX6Q_GPR13_SATA_TX_BOOST_0_00_DB },
+	{  370, IMX6Q_GPR13_SATA_TX_BOOST_0_37_DB },
+	{  740, IMX6Q_GPR13_SATA_TX_BOOST_0_74_DB },
+	{ 1110, IMX6Q_GPR13_SATA_TX_BOOST_1_11_DB },
+	{ 1480, IMX6Q_GPR13_SATA_TX_BOOST_1_48_DB },
+	{ 1850, IMX6Q_GPR13_SATA_TX_BOOST_1_85_DB },
+	{ 2220, IMX6Q_GPR13_SATA_TX_BOOST_2_22_DB },
+	{ 2590, IMX6Q_GPR13_SATA_TX_BOOST_2_59_DB },
+	{ 2960, IMX6Q_GPR13_SATA_TX_BOOST_2_96_DB },
+	{ 3330, IMX6Q_GPR13_SATA_TX_BOOST_3_33_DB },
+	{ 3700, IMX6Q_GPR13_SATA_TX_BOOST_3_70_DB },
+	{ 4070, IMX6Q_GPR13_SATA_TX_BOOST_4_07_DB },
+	{ 4440, IMX6Q_GPR13_SATA_TX_BOOST_4_44_DB },
+	{ 4810, IMX6Q_GPR13_SATA_TX_BOOST_4_81_DB },
+	{ 5280, IMX6Q_GPR13_SATA_TX_BOOST_5_28_DB },
+	{ 5750, IMX6Q_GPR13_SATA_TX_BOOST_5_75_DB }
+};
+
+static const struct reg_value gpr13_tx_atten[] = {
+	{  8, IMX6Q_GPR13_SATA_TX_ATTEN_8_16 },
+	{  9, IMX6Q_GPR13_SATA_TX_ATTEN_9_16 },
+	{ 10, IMX6Q_GPR13_SATA_TX_ATTEN_10_16 },
+	{ 12, IMX6Q_GPR13_SATA_TX_ATTEN_12_16 },
+	{ 14, IMX6Q_GPR13_SATA_TX_ATTEN_14_16 },
+	{ 16, IMX6Q_GPR13_SATA_TX_ATTEN_16_16 },
+};
+
+static const struct reg_value gpr13_rx_eq[] = {
+	{  500, IMX6Q_GPR13_SATA_RX_EQ_VAL_0_5_DB },
+	{ 1000, IMX6Q_GPR13_SATA_RX_EQ_VAL_1_0_DB },
+	{ 1500, IMX6Q_GPR13_SATA_RX_EQ_VAL_1_5_DB },
+	{ 2000, IMX6Q_GPR13_SATA_RX_EQ_VAL_2_0_DB },
+	{ 2500, IMX6Q_GPR13_SATA_RX_EQ_VAL_2_5_DB },
+	{ 3000, IMX6Q_GPR13_SATA_RX_EQ_VAL_3_0_DB },
+	{ 3500, IMX6Q_GPR13_SATA_RX_EQ_VAL_3_5_DB },
+	{ 4000, IMX6Q_GPR13_SATA_RX_EQ_VAL_4_0_DB },
+};
+
+static const struct reg_property gpr13_props[] = {
+	{
+		.name = "fsl,transmit-level-mV",
+		.values = gpr13_tx_level,
+		.num_values = ARRAY_SIZE(gpr13_tx_level),
+		.def_value = IMX6Q_GPR13_SATA_TX_LVL_1_025_V,
+	}, {
+		.name = "fsl,transmit-boost-mdB",
+		.values = gpr13_tx_boost,
+		.num_values = ARRAY_SIZE(gpr13_tx_boost),
+		.def_value = IMX6Q_GPR13_SATA_TX_BOOST_3_33_DB,
+	}, {
+		.name = "fsl,transmit-atten-16ths",
+		.values = gpr13_tx_atten,
+		.num_values = ARRAY_SIZE(gpr13_tx_atten),
+		.def_value = IMX6Q_GPR13_SATA_TX_ATTEN_9_16,
+	}, {
+		.name = "fsl,receive-eq-mdB",
+		.values = gpr13_rx_eq,
+		.num_values = ARRAY_SIZE(gpr13_rx_eq),
+		.def_value = IMX6Q_GPR13_SATA_RX_EQ_VAL_3_0_DB,
+	}, {
+		.name = "fsl,no-spread-spectrum",
+		.def_value = IMX6Q_GPR13_SATA_MPLL_SS_EN,
+		.set_value = 0,
+	},
+};
+
+static u32 imx_ahci_parse_props(struct device *dev,
+				const struct reg_property *prop, size_t num)
+{
+	struct device_node *np = dev->of_node;
+	u32 reg_value = 0;
+	int i, j;
+
+	for (i = 0; i < num; i++, prop++) {
+		u32 of_val;
+
+		if (prop->num_values == 0) {
+			if (of_property_read_bool(np, prop->name))
+				reg_value |= prop->set_value;
+			else
+				reg_value |= prop->def_value;
+			continue;
+		}
+
+		if (of_property_read_u32(np, prop->name, &of_val)) {
+			dev_info(dev, "%s not specified, using %08x\n",
+				prop->name, prop->def_value);
+			reg_value |= prop->def_value;
+			continue;
+		}
+
+		for (j = 0; j < prop->num_values; j++) {
+			if (prop->values[j].of_value == of_val) {
+				dev_info(dev, "%s value %u, using %08x\n",
+					prop->name, of_val, prop->values[j].reg_value);
+				reg_value |= prop->values[j].reg_value;
+				break;
+			}
+		}
+
+		if (j == prop->num_values) {
+			dev_err(dev, "DT property %s is not a valid value\n",
+				prop->name);
+			reg_value |= prop->def_value;
+		}
+	}
+
+	return reg_value;
+}
+
 static int imx_ahci_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -385,6 +545,19 @@ static int imx_ahci_probe(struct platform_device *pdev)
 	imxpriv->no_device = false;
 	imxpriv->first_time = true;
 	imxpriv->type = (enum ahci_imx_type)of_id->data;
+
+	imxpriv->sata_clk = devm_clk_get(dev, "sata");
+	if (IS_ERR(imxpriv->sata_clk)) {
+		dev_err(dev, "can't get sata clock.\n");
+		return PTR_ERR(imxpriv->sata_clk);
+	}
+
+	imxpriv->sata_ref_clk = devm_clk_get(dev, "sata_ref");
+	if (IS_ERR(imxpriv->sata_ref_clk)) {
+		dev_err(dev, "can't get sata_ref clock.\n");
+		return PTR_ERR(imxpriv->sata_ref_clk);
+	}
+
 	imxpriv->ahb_clk = devm_clk_get(dev, "ahb");
 	if (IS_ERR(imxpriv->ahb_clk)) {
 		dev_err(dev, "can't get ahb clock.\n");
@@ -392,6 +565,8 @@ static int imx_ahci_probe(struct platform_device *pdev)
 	}
 
 	if (imxpriv->type == AHCI_IMX6Q) {
+		u32 reg_value;
+
 		imxpriv->gpr = syscon_regmap_lookup_by_compatible(
 							"fsl,imx6q-iomuxc-gpr");
 		if (IS_ERR(imxpriv->gpr)) {
@@ -399,6 +574,15 @@ static int imx_ahci_probe(struct platform_device *pdev)
 				"failed to find fsl,imx6q-iomux-gpr regmap\n");
 			return PTR_ERR(imxpriv->gpr);
 		}
+
+		reg_value = imx_ahci_parse_props(dev, gpr13_props,
+						 ARRAY_SIZE(gpr13_props));
+
+		imxpriv->phy_params =
+				   IMX6Q_GPR13_SATA_RX_LOS_LVL_SATA2M |
+				   IMX6Q_GPR13_SATA_RX_DPLL_MODE_2P_4F |
+				   IMX6Q_GPR13_SATA_SPD_MODE_3P0G |
+				   reg_value;
 	}
 
 	hpriv = ahci_platform_get_resources(pdev);
@@ -407,10 +591,14 @@ static int imx_ahci_probe(struct platform_device *pdev)
 
 	hpriv->plat_data = imxpriv;
 
-	ret = imx_sata_enable(hpriv);
+	ret = clk_prepare_enable(imxpriv->sata_clk);
 	if (ret)
 		return ret;
 
+	ret = imx_sata_enable(hpriv);
+	if (ret)
+		goto disable_clk;
+
 	/*
 	 * Configure the HWINIT bits of the HOST_CAP and HOST_PORTS_IMPL,
 	 * and IP vendor specific register IMX_TIMER1MS.
@@ -432,18 +620,26 @@ static int imx_ahci_probe(struct platform_device *pdev)
 	reg_val = clk_get_rate(imxpriv->ahb_clk) / 1000;
 	writel(reg_val, hpriv->mmio + IMX_TIMER1MS);
 
-	ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info, 0, 0);
+	ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info);
 	if (ret)
-		imx_sata_disable(hpriv);
+		goto disable_sata;
+
+	return 0;
 
+disable_sata:
+	imx_sata_disable(hpriv);
+disable_clk:
+	clk_disable_unprepare(imxpriv->sata_clk);
 	return ret;
 }
 
 static void ahci_imx_host_stop(struct ata_host *host)
 {
 	struct ahci_host_priv *hpriv = host->private_data;
+	struct imx_ahci_priv *imxpriv = hpriv->plat_data;
 
 	imx_sata_disable(hpriv);
+	clk_disable_unprepare(imxpriv->sata_clk);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
new file mode 100644
index 00000000000..68672d2692e
--- /dev/null
+++ b/drivers/ata/ahci_mvebu.c
@@ -0,0 +1,127 @@
+/*
+ * AHCI glue platform driver for Marvell EBU SOCs
+ *
+ * Copyright (C) 2014 Marvell
+ *
+ * Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+ * Marcin Wojtas <mw@semihalf.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/ahci_platform.h>
+#include <linux/kernel.h>
+#include <linux/mbus.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include "ahci.h"
+
+#define AHCI_VENDOR_SPECIFIC_0_ADDR  0xa0
+#define AHCI_VENDOR_SPECIFIC_0_DATA  0xa4
+
+#define AHCI_WINDOW_CTRL(win)	(0x60 + ((win) << 4))
+#define AHCI_WINDOW_BASE(win)	(0x64 + ((win) << 4))
+#define AHCI_WINDOW_SIZE(win)	(0x68 + ((win) << 4))
+
+static void ahci_mvebu_mbus_config(struct ahci_host_priv *hpriv,
+				   const struct mbus_dram_target_info *dram)
+{
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		writel(0, hpriv->mmio + AHCI_WINDOW_CTRL(i));
+		writel(0, hpriv->mmio + AHCI_WINDOW_BASE(i));
+		writel(0, hpriv->mmio + AHCI_WINDOW_SIZE(i));
+	}
+
+	for (i = 0; i < dram->num_cs; i++) {
+		const struct mbus_dram_window *cs = dram->cs + i;
+
+		writel((cs->mbus_attr << 8) |
+		       (dram->mbus_dram_target_id << 4) | 1,
+		       hpriv->mmio + AHCI_WINDOW_CTRL(i));
+		writel(cs->base, hpriv->mmio + AHCI_WINDOW_BASE(i));
+		writel(((cs->size - 1) & 0xffff0000),
+		       hpriv->mmio + AHCI_WINDOW_SIZE(i));
+	}
+}
+
+static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv)
+{
+	/*
+	 * Enable the regret bit to allow the SATA unit to regret a
+	 * request that didn't receive an acknowlegde and avoid a
+	 * deadlock
+	 */
+	writel(0x4, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_ADDR);
+	writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA);
+}
+
+static const struct ata_port_info ahci_mvebu_port_info = {
+	.flags	   = AHCI_FLAG_COMMON,
+	.pio_mask  = ATA_PIO4,
+	.udma_mask = ATA_UDMA6,
+	.port_ops  = &ahci_platform_ops,
+};
+
+static int ahci_mvebu_probe(struct platform_device *pdev)
+{
+	struct ahci_host_priv *hpriv;
+	const struct mbus_dram_target_info *dram;
+	int rc;
+
+	hpriv = ahci_platform_get_resources(pdev);
+	if (IS_ERR(hpriv))
+		return PTR_ERR(hpriv);
+
+	rc = ahci_platform_enable_resources(hpriv);
+	if (rc)
+		return rc;
+
+	dram = mv_mbus_dram_info();
+	if (!dram)
+		return -ENODEV;
+
+	ahci_mvebu_mbus_config(hpriv, dram);
+	ahci_mvebu_regret_option(hpriv);
+
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_mvebu_port_info);
+	if (rc)
+		goto disable_resources;
+
+	return 0;
+
+disable_resources:
+	ahci_platform_disable_resources(hpriv);
+	return rc;
+}
+
+static const struct of_device_id ahci_mvebu_of_match[] = {
+	{ .compatible = "marvell,armada-380-ahci", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, ahci_mvebu_of_match);
+
+/*
+ * We currently don't provide power management related operations,
+ * since there is no suspend/resume support at the platform level for
+ * Armada 38x for the moment.
+ */
+static struct platform_driver ahci_mvebu_driver = {
+	.probe = ahci_mvebu_probe,
+	.remove = ata_platform_remove_one,
+	.driver = {
+		.name = "ahci-mvebu",
+		.owner = THIS_MODULE,
+		.of_match_table = ahci_mvebu_of_match,
+	},
+};
+module_platform_driver(ahci_mvebu_driver);
+
+MODULE_DESCRIPTION("Marvell EBU AHCI SATA driver");
+MODULE_AUTHOR("Thomas Petazzoni <thomas.petazzoni@free-electrons.com>, Marcin Wojtas <mw@semihalf.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:ahci_mvebu");
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index ef67e79944f..f61ddb9146d 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/device.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/libata.h>
 #include <linux/ahci_platform.h>
@@ -55,7 +56,10 @@ static int ahci_probe(struct platform_device *pdev)
 			goto disable_resources;
 	}
 
-	rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info, 0, 0);
+	if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci"))
+		hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ;
+
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_port_info);
 	if (rc)
 		goto pdata_exit;
 
@@ -72,10 +76,13 @@ static SIMPLE_DEV_PM_OPS(ahci_pm_ops, ahci_platform_suspend,
 			 ahci_platform_resume);
 
 static const struct of_device_id ahci_of_match[] = {
+	{ .compatible = "generic-ahci", },
+	/* Keep the following compatibles for device tree compatibility */
 	{ .compatible = "snps,spear-ahci", },
 	{ .compatible = "snps,exynos5440-ahci", },
 	{ .compatible = "ibm,476gtr-ahci", },
 	{ .compatible = "snps,dwc-ahci", },
+	{ .compatible = "hisilicon,hisi-ahci", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, ahci_of_match);
diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c
index 633222226c1..835d6eea84f 100644
--- a/drivers/ata/ahci_st.c
+++ b/drivers/ata/ahci_st.c
@@ -166,7 +166,7 @@ static int st_ahci_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info, 0, 0);
+	err = ahci_platform_init_host(pdev, hpriv, &st_ahci_port_info);
 	if (err) {
 		ahci_platform_disable_resources(hpriv);
 		return err;
@@ -221,7 +221,7 @@ static int st_ahci_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(st_ahci_pm_ops, st_ahci_suspend, st_ahci_resume);
 
-static struct of_device_id st_ahci_match[] = {
+static const struct of_device_id st_ahci_match[] = {
 	{ .compatible = "st,ahci", },
 	{},
 };
diff --git a/drivers/ata/ahci_sunxi.c b/drivers/ata/ahci_sunxi.c
index 42d3f64e74b..e44d675a30e 100644
--- a/drivers/ata/ahci_sunxi.c
+++ b/drivers/ata/ahci_sunxi.c
@@ -157,8 +157,6 @@ static void ahci_sunxi_start_engine(struct ata_port *ap)
 }
 
 static const struct ata_port_info ahci_sunxi_port_info = {
-	AHCI_HFLAGS(AHCI_HFLAG_32BIT_ONLY | AHCI_HFLAG_NO_MSI |
-			  AHCI_HFLAG_NO_PMP | AHCI_HFLAG_YES_NCQ),
 	.flags		= AHCI_FLAG_COMMON | ATA_FLAG_NCQ,
 	.pio_mask	= ATA_PIO4,
 	.udma_mask	= ATA_UDMA6,
@@ -185,7 +183,10 @@ static int ahci_sunxi_probe(struct platform_device *pdev)
 	if (rc)
 		goto disable_resources;
 
-	rc = ahci_platform_init_host(pdev, hpriv, &ahci_sunxi_port_info, 0, 0);
+	hpriv->flags = AHCI_HFLAG_32BIT_ONLY | AHCI_HFLAG_NO_MSI |
+		       AHCI_HFLAG_NO_PMP | AHCI_HFLAG_YES_NCQ;
+
+	rc = ahci_platform_init_host(pdev, hpriv, &ahci_sunxi_port_info);
 	if (rc)
 		goto disable_resources;
 
diff --git a/drivers/ata/ahci_tegra.c b/drivers/ata/ahci_tegra.c
new file mode 100644
index 00000000000..fc3df47fca3
--- /dev/null
+++ b/drivers/ata/ahci_tegra.c
@@ -0,0 +1,376 @@
+/*
+ * drivers/ata/ahci_tegra.c
+ *
+ * Copyright (c) 2014, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * Author:
+ *	Mikko Perttunen <mperttunen@nvidia.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/ahci_platform.h>
+#include <linux/reset.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/tegra-powergate.h>
+#include <linux/regulator/consumer.h>
+#include "ahci.h"
+
+#define SATA_CONFIGURATION_0				0x180
+#define SATA_CONFIGURATION_EN_FPCI			BIT(0)
+
+#define SCFG_OFFSET					0x1000
+
+#define T_SATA0_CFG_1					0x04
+#define T_SATA0_CFG_1_IO_SPACE				BIT(0)
+#define T_SATA0_CFG_1_MEMORY_SPACE			BIT(1)
+#define T_SATA0_CFG_1_BUS_MASTER			BIT(2)
+#define T_SATA0_CFG_1_SERR				BIT(8)
+
+#define T_SATA0_CFG_9					0x24
+#define T_SATA0_CFG_9_BASE_ADDRESS_SHIFT		13
+
+#define SATA_FPCI_BAR5					0x94
+#define SATA_FPCI_BAR5_START_SHIFT			4
+
+#define SATA_INTR_MASK					0x188
+#define SATA_INTR_MASK_IP_INT_MASK			BIT(16)
+
+#define T_SATA0_AHCI_HBA_CAP_BKDR			0x300
+
+#define T_SATA0_BKDOOR_CC				0x4a4
+
+#define T_SATA0_CFG_SATA				0x54c
+#define T_SATA0_CFG_SATA_BACKDOOR_PROG_IF_EN		BIT(12)
+
+#define T_SATA0_CFG_MISC				0x550
+
+#define T_SATA0_INDEX					0x680
+
+#define T_SATA0_CHX_PHY_CTRL1_GEN1			0x690
+#define T_SATA0_CHX_PHY_CTRL1_GEN1_TX_AMP_MASK		0xff
+#define T_SATA0_CHX_PHY_CTRL1_GEN1_TX_AMP_SHIFT		0
+#define T_SATA0_CHX_PHY_CTRL1_GEN1_TX_PEAK_MASK		(0xff << 8)
+#define T_SATA0_CHX_PHY_CTRL1_GEN1_TX_PEAK_SHIFT	8
+
+#define T_SATA0_CHX_PHY_CTRL1_GEN2			0x694
+#define T_SATA0_CHX_PHY_CTRL1_GEN2_TX_AMP_MASK		0xff
+#define T_SATA0_CHX_PHY_CTRL1_GEN2_TX_AMP_SHIFT		0
+#define T_SATA0_CHX_PHY_CTRL1_GEN2_TX_PEAK_MASK		(0xff << 12)
+#define T_SATA0_CHX_PHY_CTRL1_GEN2_TX_PEAK_SHIFT	12
+
+#define T_SATA0_CHX_PHY_CTRL2				0x69c
+#define T_SATA0_CHX_PHY_CTRL2_CDR_CNTL_GEN1		0x23
+
+#define T_SATA0_CHX_PHY_CTRL11				0x6d0
+#define T_SATA0_CHX_PHY_CTRL11_GEN2_RX_EQ		(0x2800 << 16)
+
+#define FUSE_SATA_CALIB					0x124
+#define FUSE_SATA_CALIB_MASK				0x3
+
+struct sata_pad_calibration {
+	u8 gen1_tx_amp;
+	u8 gen1_tx_peak;
+	u8 gen2_tx_amp;
+	u8 gen2_tx_peak;
+};
+
+static const struct sata_pad_calibration tegra124_pad_calibration[] = {
+	{0x18, 0x04, 0x18, 0x0a},
+	{0x0e, 0x04, 0x14, 0x0a},
+	{0x0e, 0x07, 0x1a, 0x0e},
+	{0x14, 0x0e, 0x1a, 0x0e},
+};
+
+struct tegra_ahci_priv {
+	struct platform_device	   *pdev;
+	void __iomem		   *sata_regs;
+	struct reset_control	   *sata_rst;
+	struct reset_control	   *sata_oob_rst;
+	struct reset_control	   *sata_cold_rst;
+	/* Needs special handling, cannot use ahci_platform */
+	struct clk		   *sata_clk;
+	struct regulator_bulk_data supplies[5];
+};
+
+static int tegra_ahci_power_on(struct ahci_host_priv *hpriv)
+{
+	struct tegra_ahci_priv *tegra = hpriv->plat_data;
+	int ret;
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(tegra->supplies),
+				    tegra->supplies);
+	if (ret)
+		return ret;
+
+	ret = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_SATA,
+						tegra->sata_clk,
+						tegra->sata_rst);
+	if (ret)
+		goto disable_regulators;
+
+	reset_control_assert(tegra->sata_oob_rst);
+	reset_control_assert(tegra->sata_cold_rst);
+
+	ret = ahci_platform_enable_resources(hpriv);
+	if (ret)
+		goto disable_power;
+
+	reset_control_deassert(tegra->sata_cold_rst);
+	reset_control_deassert(tegra->sata_oob_rst);
+
+	return 0;
+
+disable_power:
+	clk_disable_unprepare(tegra->sata_clk);
+
+	tegra_powergate_power_off(TEGRA_POWERGATE_SATA);
+
+disable_regulators:
+	regulator_bulk_disable(ARRAY_SIZE(tegra->supplies), tegra->supplies);
+
+	return ret;
+}
+
+static void tegra_ahci_power_off(struct ahci_host_priv *hpriv)
+{
+	struct tegra_ahci_priv *tegra = hpriv->plat_data;
+
+	ahci_platform_disable_resources(hpriv);
+
+	reset_control_assert(tegra->sata_rst);
+	reset_control_assert(tegra->sata_oob_rst);
+	reset_control_assert(tegra->sata_cold_rst);
+
+	clk_disable_unprepare(tegra->sata_clk);
+	tegra_powergate_power_off(TEGRA_POWERGATE_SATA);
+
+	regulator_bulk_disable(ARRAY_SIZE(tegra->supplies), tegra->supplies);
+}
+
+static int tegra_ahci_controller_init(struct ahci_host_priv *hpriv)
+{
+	struct tegra_ahci_priv *tegra = hpriv->plat_data;
+	int ret;
+	unsigned int val;
+	struct sata_pad_calibration calib;
+
+	ret = tegra_ahci_power_on(hpriv);
+	if (ret) {
+		dev_err(&tegra->pdev->dev,
+			"failed to power on AHCI controller: %d\n", ret);
+		return ret;
+	}
+
+	val = readl(tegra->sata_regs + SATA_CONFIGURATION_0);
+	val |= SATA_CONFIGURATION_EN_FPCI;
+	writel(val, tegra->sata_regs + SATA_CONFIGURATION_0);
+
+	/* Pad calibration */
+
+	/* FIXME Always use calibration 0. Change this to read the calibration
+	 * fuse once the fuse driver has landed. */
+	val = 0;
+
+	calib = tegra124_pad_calibration[val & FUSE_SATA_CALIB_MASK];
+
+	writel(BIT(0), tegra->sata_regs + SCFG_OFFSET + T_SATA0_INDEX);
+
+	val = readl(tegra->sata_regs +
+		SCFG_OFFSET + T_SATA0_CHX_PHY_CTRL1_GEN1);
+	val &= ~T_SATA0_CHX_PHY_CTRL1_GEN1_TX_AMP_MASK;
+	val &= ~T_SATA0_CHX_PHY_CTRL1_GEN1_TX_PEAK_MASK;
+	val |= calib.gen1_tx_amp <<
+			T_SATA0_CHX_PHY_CTRL1_GEN1_TX_AMP_SHIFT;
+	val |= calib.gen1_tx_peak <<
+			T_SATA0_CHX_PHY_CTRL1_GEN1_TX_PEAK_SHIFT;
+	writel(val, tegra->sata_regs + SCFG_OFFSET +
+		T_SATA0_CHX_PHY_CTRL1_GEN1);
+
+	val = readl(tegra->sata_regs +
+			SCFG_OFFSET + T_SATA0_CHX_PHY_CTRL1_GEN2);
+	val &= ~T_SATA0_CHX_PHY_CTRL1_GEN2_TX_AMP_MASK;
+	val &= ~T_SATA0_CHX_PHY_CTRL1_GEN2_TX_PEAK_MASK;
+	val |= calib.gen2_tx_amp <<
+			T_SATA0_CHX_PHY_CTRL1_GEN1_TX_AMP_SHIFT;
+	val |= calib.gen2_tx_peak <<
+			T_SATA0_CHX_PHY_CTRL1_GEN1_TX_PEAK_SHIFT;
+	writel(val, tegra->sata_regs + SCFG_OFFSET +
+		T_SATA0_CHX_PHY_CTRL1_GEN2);
+
+	writel(T_SATA0_CHX_PHY_CTRL11_GEN2_RX_EQ,
+		tegra->sata_regs + SCFG_OFFSET + T_SATA0_CHX_PHY_CTRL11);
+	writel(T_SATA0_CHX_PHY_CTRL2_CDR_CNTL_GEN1,
+		tegra->sata_regs + SCFG_OFFSET + T_SATA0_CHX_PHY_CTRL2);
+
+	writel(0, tegra->sata_regs + SCFG_OFFSET + T_SATA0_INDEX);
+
+	/* Program controller device ID */
+
+	val = readl(tegra->sata_regs + SCFG_OFFSET + T_SATA0_CFG_SATA);
+	val |= T_SATA0_CFG_SATA_BACKDOOR_PROG_IF_EN;
+	writel(val, tegra->sata_regs + SCFG_OFFSET + T_SATA0_CFG_SATA);
+
+	writel(0x01060100, tegra->sata_regs + SCFG_OFFSET + T_SATA0_BKDOOR_CC);
+
+	val = readl(tegra->sata_regs + SCFG_OFFSET + T_SATA0_CFG_SATA);
+	val &= ~T_SATA0_CFG_SATA_BACKDOOR_PROG_IF_EN;
+	writel(val, tegra->sata_regs + SCFG_OFFSET + T_SATA0_CFG_SATA);
+
+	/* Enable IO & memory access, bus master mode */
+
+	val = readl(tegra->sata_regs + SCFG_OFFSET + T_SATA0_CFG_1);
+	val |= T_SATA0_CFG_1_IO_SPACE | T_SATA0_CFG_1_MEMORY_SPACE |
+		T_SATA0_CFG_1_BUS_MASTER | T_SATA0_CFG_1_SERR;
+	writel(val, tegra->sata_regs + SCFG_OFFSET + T_SATA0_CFG_1);
+
+	/* Program SATA MMIO */
+
+	writel(0x10000 << SATA_FPCI_BAR5_START_SHIFT,
+	       tegra->sata_regs + SATA_FPCI_BAR5);
+
+	writel(0x08000 << T_SATA0_CFG_9_BASE_ADDRESS_SHIFT,
+	       tegra->sata_regs + SCFG_OFFSET + T_SATA0_CFG_9);
+
+	/* Unmask SATA interrupts */
+
+	val = readl(tegra->sata_regs + SATA_INTR_MASK);
+	val |= SATA_INTR_MASK_IP_INT_MASK;
+	writel(val, tegra->sata_regs + SATA_INTR_MASK);
+
+	return 0;
+}
+
+static void tegra_ahci_controller_deinit(struct ahci_host_priv *hpriv)
+{
+	tegra_ahci_power_off(hpriv);
+}
+
+static void tegra_ahci_host_stop(struct ata_host *host)
+{
+	struct ahci_host_priv *hpriv = host->private_data;
+
+	tegra_ahci_controller_deinit(hpriv);
+}
+
+static struct ata_port_operations ahci_tegra_port_ops = {
+	.inherits	= &ahci_ops,
+	.host_stop	= tegra_ahci_host_stop,
+};
+
+static const struct ata_port_info ahci_tegra_port_info = {
+	.flags		= AHCI_FLAG_COMMON,
+	.pio_mask	= ATA_PIO4,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &ahci_tegra_port_ops,
+};
+
+static const struct of_device_id tegra_ahci_of_match[] = {
+	{ .compatible = "nvidia,tegra124-ahci" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, tegra_ahci_of_match);
+
+static int tegra_ahci_probe(struct platform_device *pdev)
+{
+	struct ahci_host_priv *hpriv;
+	struct tegra_ahci_priv *tegra;
+	struct resource *res;
+	int ret;
+
+	hpriv = ahci_platform_get_resources(pdev);
+	if (IS_ERR(hpriv))
+		return PTR_ERR(hpriv);
+
+	tegra = devm_kzalloc(&pdev->dev, sizeof(*tegra), GFP_KERNEL);
+	if (!tegra)
+		return -ENOMEM;
+
+	hpriv->plat_data = tegra;
+
+	tegra->pdev = pdev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	tegra->sata_regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(tegra->sata_regs))
+		return PTR_ERR(tegra->sata_regs);
+
+	tegra->sata_rst = devm_reset_control_get(&pdev->dev, "sata");
+	if (IS_ERR(tegra->sata_rst)) {
+		dev_err(&pdev->dev, "Failed to get sata reset\n");
+		return PTR_ERR(tegra->sata_rst);
+	}
+
+	tegra->sata_oob_rst = devm_reset_control_get(&pdev->dev, "sata-oob");
+	if (IS_ERR(tegra->sata_oob_rst)) {
+		dev_err(&pdev->dev, "Failed to get sata-oob reset\n");
+		return PTR_ERR(tegra->sata_oob_rst);
+	}
+
+	tegra->sata_cold_rst = devm_reset_control_get(&pdev->dev, "sata-cold");
+	if (IS_ERR(tegra->sata_cold_rst)) {
+		dev_err(&pdev->dev, "Failed to get sata-cold reset\n");
+		return PTR_ERR(tegra->sata_cold_rst);
+	}
+
+	tegra->sata_clk = devm_clk_get(&pdev->dev, "sata");
+	if (IS_ERR(tegra->sata_clk)) {
+		dev_err(&pdev->dev, "Failed to get sata clock\n");
+		return PTR_ERR(tegra->sata_clk);
+	}
+
+	tegra->supplies[0].supply = "avdd";
+	tegra->supplies[1].supply = "hvdd";
+	tegra->supplies[2].supply = "vddio";
+	tegra->supplies[3].supply = "target-5v";
+	tegra->supplies[4].supply = "target-12v";
+
+	ret = devm_regulator_bulk_get(&pdev->dev, ARRAY_SIZE(tegra->supplies),
+				      tegra->supplies);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to get regulators\n");
+		return ret;
+	}
+
+	ret = tegra_ahci_controller_init(hpriv);
+	if (ret)
+		return ret;
+
+	ret = ahci_platform_init_host(pdev, hpriv, &ahci_tegra_port_info);
+	if (ret)
+		goto deinit_controller;
+
+	return 0;
+
+deinit_controller:
+	tegra_ahci_controller_deinit(hpriv);
+
+	return ret;
+};
+
+static struct platform_driver tegra_ahci_driver = {
+	.probe = tegra_ahci_probe,
+	.remove = ata_platform_remove_one,
+	.driver = {
+		.name = "tegra-ahci",
+		.of_match_table = tegra_ahci_of_match,
+	},
+	/* LP0 suspend support not implemented */
+};
+module_platform_driver(tegra_ahci_driver);
+
+MODULE_AUTHOR("Mikko Perttunen <mperttunen@nvidia.com>");
+MODULE_DESCRIPTION("Tegra124 AHCI SATA driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index 77c89bf171f..bc281115490 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -67,6 +67,9 @@
 #define PORTAXICFG			0x000000bc
 #define PORTAXICFG_OUTTRANS_SET(dst, src) \
 		(((dst) & ~0x00f00000) | (((u32)(src) << 0x14) & 0x00f00000))
+#define PORTRANSCFG			0x000000c8
+#define PORTRANSCFG_RXWM_SET(dst, src)		\
+		(((dst) & ~0x0000007f) | (((u32)(src)) & 0x0000007f))
 
 /* SATA host controller AXI CSR */
 #define INT_SLV_TMOMASK			0x00000010
@@ -78,6 +81,7 @@
 struct xgene_ahci_context {
 	struct ahci_host_priv *hpriv;
 	struct device *dev;
+	u8 last_cmd[MAX_AHCI_CHN_PERCTR]; /* tracking the last command issued*/
 	void __iomem *csr_core;		/* Core CSR address of IP */
 	void __iomem *csr_diag;		/* Diag CSR address of IP */
 	void __iomem *csr_axi;		/* AXI CSR address of IP */
@@ -98,20 +102,62 @@ static int xgene_ahci_init_memram(struct xgene_ahci_context *ctx)
 }
 
 /**
+ * xgene_ahci_restart_engine - Restart the dma engine.
+ * @ap : ATA port of interest
+ *
+ * Restarts the dma engine inside the controller.
+ */
+static int xgene_ahci_restart_engine(struct ata_port *ap)
+{
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+
+	ahci_stop_engine(ap);
+	ahci_start_fis_rx(ap);
+	hpriv->start_engine(ap);
+
+	return 0;
+}
+
+/**
+ * xgene_ahci_qc_issue - Issue commands to the device
+ * @qc: Command to issue
+ *
+ * Due to Hardware errata for IDENTIFY DEVICE command, the controller cannot
+ * clear the BSY bit after receiving the PIO setup FIS. This results in the dma
+ * state machine goes into the CMFatalErrorUpdate state and locks up. By
+ * restarting the dma engine, it removes the controller out of lock up state.
+ */
+static unsigned int xgene_ahci_qc_issue(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	struct ahci_host_priv *hpriv = ap->host->private_data;
+	struct xgene_ahci_context *ctx = hpriv->plat_data;
+	int rc = 0;
+
+	if (unlikely(ctx->last_cmd[ap->port_no] == ATA_CMD_ID_ATA))
+		xgene_ahci_restart_engine(ap);
+
+	rc = ahci_qc_issue(qc);
+
+	/* Save the last command issued */
+	ctx->last_cmd[ap->port_no] = qc->tf.command;
+
+	return rc;
+}
+
+/**
  * xgene_ahci_read_id - Read ID data from the specified device
  * @dev: device
  * @tf: proposed taskfile
  * @id: data buffer
  *
  * This custom read ID function is required due to the fact that the HW
- * does not support DEVSLP and the controller state machine may get stuck
- * after processing the ID query command.
+ * does not support DEVSLP.
  */
 static unsigned int xgene_ahci_read_id(struct ata_device *dev,
 				       struct ata_taskfile *tf, u16 *id)
 {
 	u32 err_mask;
-	void __iomem *port_mmio = ahci_port_base(dev->link->ap);
 
 	err_mask = ata_do_dev_read_id(dev, tf, id);
 	if (err_mask)
@@ -133,16 +179,6 @@ static unsigned int xgene_ahci_read_id(struct ata_device *dev,
 	 */
 	id[ATA_ID_FEATURE_SUPP] &= ~(1 << 8);
 
-	/*
-	 * Due to HW errata, restart the port if no other command active.
-	 * Otherwise the controller may get stuck.
-	 */
-	if (!readl(port_mmio + PORT_CMD_ISSUE)) {
-		writel(PORT_CMD_FIS_RX, port_mmio + PORT_CMD);
-		readl(port_mmio + PORT_CMD);	/* Force a barrier */
-		writel(PORT_CMD_FIS_RX | PORT_CMD_START, port_mmio + PORT_CMD);
-		readl(port_mmio + PORT_CMD);	/* Force a barrier */
-	}
 	return 0;
 }
 
@@ -160,11 +196,11 @@ static void xgene_ahci_set_phy_cfg(struct xgene_ahci_context *ctx, int channel)
 	/* Disable fix rate */
 	writel(0x0001fffe, mmio + PORTPHY1CFG);
 	readl(mmio + PORTPHY1CFG); /* Force a barrier */
-	writel(0x5018461c, mmio + PORTPHY2CFG);
+	writel(0x28183219, mmio + PORTPHY2CFG);
 	readl(mmio + PORTPHY2CFG); /* Force a barrier */
-	writel(0x1c081907, mmio + PORTPHY3CFG);
+	writel(0x13081008, mmio + PORTPHY3CFG);
 	readl(mmio + PORTPHY3CFG); /* Force a barrier */
-	writel(0x1c080815, mmio + PORTPHY4CFG);
+	writel(0x00480815, mmio + PORTPHY4CFG);
 	readl(mmio + PORTPHY4CFG); /* Force a barrier */
 	/* Set window negotiation */
 	val = readl(mmio + PORTPHY5CFG);
@@ -176,6 +212,10 @@ static void xgene_ahci_set_phy_cfg(struct xgene_ahci_context *ctx, int channel)
 	val = PORTAXICFG_OUTTRANS_SET(val, 0xe); /* Set outstanding */
 	writel(val, mmio + PORTAXICFG);
 	readl(mmio + PORTAXICFG); /* Force a barrier */
+	/* Set the watermark threshold of the receive FIFO */
+	val = readl(mmio + PORTRANSCFG);
+	val = PORTRANSCFG_RXWM_SET(val, 0x30);
+	writel(val, mmio + PORTRANSCFG);
 }
 
 /**
@@ -300,10 +340,10 @@ static struct ata_port_operations xgene_ahci_ops = {
 	.host_stop = xgene_ahci_host_stop,
 	.hardreset = xgene_ahci_hardreset,
 	.read_id = xgene_ahci_read_id,
+	.qc_issue = xgene_ahci_qc_issue,
 };
 
 static const struct ata_port_info xgene_ahci_port_info = {
-	AHCI_HFLAGS(AHCI_HFLAG_NO_PMP | AHCI_HFLAG_YES_NCQ),
 	.flags = AHCI_FLAG_COMMON | ATA_FLAG_NCQ,
 	.pio_mask = ATA_PIO4,
 	.udma_mask = ATA_UDMA6,
@@ -440,17 +480,9 @@ static int xgene_ahci_probe(struct platform_device *pdev)
 	/* Configure the host controller */
 	xgene_ahci_hw_init(hpriv);
 
-	/*
-	 * Setup DMA mask. This is preliminary until the DMA range is sorted
-	 * out.
-	 */
-	rc = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
-	if (rc) {
-		dev_err(dev, "Unable to set dma mask\n");
-		goto disable_resources;
-	}
+	hpriv->flags = AHCI_HFLAG_NO_PMP | AHCI_HFLAG_YES_NCQ;
 
-	rc = ahci_platform_init_host(pdev, hpriv, &xgene_ahci_port_info, 0, 0);
+	rc = ahci_platform_init_host(pdev, hpriv, &xgene_ahci_port_info);
 	if (rc)
 		goto disable_resources;
 
diff --git a/drivers/ata/ata_generic.c b/drivers/ata/ata_generic.c
index 9498a7d3846..9ff545ce8da 100644
--- a/drivers/ata/ata_generic.c
+++ b/drivers/ata/ata_generic.c
@@ -241,7 +241,7 @@ static struct pci_driver ata_generic_pci_driver = {
 	.id_table	= ata_generic,
 	.probe 		= ata_generic_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 6334c8d7c3f..893e30e9a9e 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -830,7 +830,7 @@ static bool piix_irq_check(struct ata_port *ap)
 	return ap->ops->bmdma_status(ap) & ATA_DMA_INTR;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int piix_broken_suspend(void)
 {
 	static const struct dmi_system_id sysids[] = {
@@ -1767,7 +1767,7 @@ static struct pci_driver piix_pci_driver = {
 	.id_table		= piix_pci_tbl,
 	.probe			= piix_init_one,
 	.remove			= piix_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= piix_pci_device_suspend,
 	.resume			= piix_pci_device_resume,
 #endif
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index b9861453fc8..b784e9de426 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -68,7 +68,6 @@ static ssize_t ahci_transmit_led_message(struct ata_port *ap, u32 state,
 
 static int ahci_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val);
 static int ahci_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
-static unsigned int ahci_qc_issue(struct ata_queued_cmd *qc);
 static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc);
 static int ahci_port_start(struct ata_port *ap);
 static void ahci_port_stop(struct ata_port *ap);
@@ -383,8 +382,6 @@ static ssize_t ahci_show_em_supported(struct device *dev,
  *	ahci_save_initial_config - Save and fixup initial config values
  *	@dev: target AHCI device
  *	@hpriv: host private area to store config values
- *	@force_port_map: force port map to a specified value
- *	@mask_port_map: mask out particular bits from port map
  *
  *	Some registers containing configuration info might be setup by
  *	BIOS and might be cleared on reset.  This function saves the
@@ -399,10 +396,7 @@ static ssize_t ahci_show_em_supported(struct device *dev,
  *	LOCKING:
  *	None.
  */
-void ahci_save_initial_config(struct device *dev,
-			      struct ahci_host_priv *hpriv,
-			      unsigned int force_port_map,
-			      unsigned int mask_port_map)
+void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 {
 	void __iomem *mmio = hpriv->mmio;
 	u32 cap, cap2, vers, port_map;
@@ -464,17 +458,22 @@ void ahci_save_initial_config(struct device *dev,
 		cap |= HOST_CAP_FBS;
 	}
 
-	if (force_port_map && port_map != force_port_map) {
+	if ((cap & HOST_CAP_FBS) && (hpriv->flags & AHCI_HFLAG_NO_FBS)) {
+		dev_info(dev, "controller can't do FBS, turning off CAP_FBS\n");
+		cap &= ~HOST_CAP_FBS;
+	}
+
+	if (hpriv->force_port_map && port_map != hpriv->force_port_map) {
 		dev_info(dev, "forcing port_map 0x%x -> 0x%x\n",
-			 port_map, force_port_map);
-		port_map = force_port_map;
+			 port_map, hpriv->force_port_map);
+		port_map = hpriv->force_port_map;
 	}
 
-	if (mask_port_map) {
+	if (hpriv->mask_port_map) {
 		dev_warn(dev, "masking port_map 0x%x -> 0x%x\n",
 			port_map,
-			port_map & mask_port_map);
-		port_map &= mask_port_map;
+			port_map & hpriv->mask_port_map);
+		port_map &= hpriv->mask_port_map;
 	}
 
 	/* cross check port_map and cap.n_ports */
@@ -615,7 +614,7 @@ int ahci_stop_engine(struct ata_port *ap)
 }
 EXPORT_SYMBOL_GPL(ahci_stop_engine);
 
-static void ahci_start_fis_rx(struct ata_port *ap)
+void ahci_start_fis_rx(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
 	struct ahci_host_priv *hpriv = ap->host->private_data;
@@ -641,6 +640,7 @@ static void ahci_start_fis_rx(struct ata_port *ap)
 	/* flush */
 	readl(port_mmio + PORT_CMD);
 }
+EXPORT_SYMBOL_GPL(ahci_start_fis_rx);
 
 static int ahci_stop_fis_rx(struct ata_port *ap)
 {
@@ -1940,7 +1940,7 @@ irqreturn_t ahci_interrupt(int irq, void *dev_instance)
 }
 EXPORT_SYMBOL_GPL(ahci_interrupt);
 
-static unsigned int ahci_qc_issue(struct ata_queued_cmd *qc)
+unsigned int ahci_qc_issue(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
 	void __iomem *port_mmio = ahci_port_base(ap);
@@ -1969,6 +1969,7 @@ static unsigned int ahci_qc_issue(struct ata_queued_cmd *qc)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ahci_qc_issue);
 
 static bool ahci_qc_fill_rtf(struct ata_queued_cmd *qc)
 {
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 7cb3a85719c..5b92c290e6c 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -39,6 +39,67 @@ static struct scsi_host_template ahci_platform_sht = {
 };
 
 /**
+ * ahci_platform_enable_phys - Enable PHYs
+ * @hpriv: host private area to store config values
+ *
+ * This function enables all the PHYs found in hpriv->phys, if any.
+ * If a PHY fails to be enabled, it disables all the PHYs already
+ * enabled in reverse order and returns an error.
+ *
+ * RETURNS:
+ * 0 on success otherwise a negative error code
+ */
+int ahci_platform_enable_phys(struct ahci_host_priv *hpriv)
+{
+	int rc, i;
+
+	for (i = 0; i < hpriv->nports; i++) {
+		if (!hpriv->phys[i])
+			continue;
+
+		rc = phy_init(hpriv->phys[i]);
+		if (rc)
+			goto disable_phys;
+
+		rc = phy_power_on(hpriv->phys[i]);
+		if (rc) {
+			phy_exit(hpriv->phys[i]);
+			goto disable_phys;
+		}
+	}
+
+	return 0;
+
+disable_phys:
+	while (--i >= 0) {
+		phy_power_off(hpriv->phys[i]);
+		phy_exit(hpriv->phys[i]);
+	}
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ahci_platform_enable_phys);
+
+/**
+ * ahci_platform_disable_phys - Disable PHYs
+ * @hpriv: host private area to store config values
+ *
+ * This function disables all PHYs found in hpriv->phys.
+ */
+void ahci_platform_disable_phys(struct ahci_host_priv *hpriv)
+{
+	int i;
+
+	for (i = 0; i < hpriv->nports; i++) {
+		if (!hpriv->phys[i])
+			continue;
+
+		phy_power_off(hpriv->phys[i]);
+		phy_exit(hpriv->phys[i]);
+	}
+}
+EXPORT_SYMBOL_GPL(ahci_platform_disable_phys);
+
+/**
  * ahci_platform_enable_clks - Enable platform clocks
  * @hpriv: host private area to store config values
  *
@@ -92,7 +153,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_disable_clks);
  * following order:
  * 1) Regulator
  * 2) Clocks (through ahci_platform_enable_clks)
- * 3) Phy
+ * 3) Phys
  *
  * If resource enabling fails at any point the previous enabled resources
  * are disabled in reverse order.
@@ -114,17 +175,9 @@ int ahci_platform_enable_resources(struct ahci_host_priv *hpriv)
 	if (rc)
 		goto disable_regulator;
 
-	if (hpriv->phy) {
-		rc = phy_init(hpriv->phy);
-		if (rc)
-			goto disable_clks;
-
-		rc = phy_power_on(hpriv->phy);
-		if (rc) {
-			phy_exit(hpriv->phy);
-			goto disable_clks;
-		}
-	}
+	rc = ahci_platform_enable_phys(hpriv);
+	if (rc)
+		goto disable_clks;
 
 	return 0;
 
@@ -144,16 +197,13 @@ EXPORT_SYMBOL_GPL(ahci_platform_enable_resources);
  *
  * This function disables all ahci_platform managed resources in the
  * following order:
- * 1) Phy
+ * 1) Phys
  * 2) Clocks (through ahci_platform_disable_clks)
  * 3) Regulator
  */
 void ahci_platform_disable_resources(struct ahci_host_priv *hpriv)
 {
-	if (hpriv->phy) {
-		phy_power_off(hpriv->phy);
-		phy_exit(hpriv->phy);
-	}
+	ahci_platform_disable_phys(hpriv);
 
 	ahci_platform_disable_clks(hpriv);
 
@@ -187,7 +237,7 @@ static void ahci_platform_put_resources(struct device *dev, void *res)
  * 2) regulator for controlling the targets power (optional)
  * 3) 0 - AHCI_MAX_CLKS clocks, as specified in the devs devicetree node,
  *    or for non devicetree enabled platforms a single clock
- *	4) phy (optional)
+ *	4) phys (optional)
  *
  * RETURNS:
  * The allocated ahci_host_priv on success, otherwise an ERR_PTR value
@@ -197,7 +247,9 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct ahci_host_priv *hpriv;
 	struct clk *clk;
-	int i, rc = -ENOMEM;
+	struct device_node *child;
+	int i, enabled_ports = 0, rc = -ENOMEM;
+	u32 mask_port_map = 0;
 
 	if (!devres_open_group(dev, NULL, GFP_KERNEL))
 		return ERR_PTR(-ENOMEM);
@@ -246,23 +298,89 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev)
 		hpriv->clks[i] = clk;
 	}
 
-	hpriv->phy = devm_phy_get(dev, "sata-phy");
-	if (IS_ERR(hpriv->phy)) {
-		rc = PTR_ERR(hpriv->phy);
-		switch (rc) {
-		case -ENODEV:
-		case -ENOSYS:
-			/* continue normally */
-			hpriv->phy = NULL;
-			break;
+	hpriv->nports = of_get_child_count(dev->of_node);
 
-		case -EPROBE_DEFER:
+	if (hpriv->nports) {
+		hpriv->phys = devm_kzalloc(dev,
+					   hpriv->nports * sizeof(*hpriv->phys),
+					   GFP_KERNEL);
+		if (!hpriv->phys) {
+			rc = -ENOMEM;
 			goto err_out;
+		}
+
+		for_each_child_of_node(dev->of_node, child) {
+			u32 port;
+
+			if (!of_device_is_available(child))
+				continue;
+
+			if (of_property_read_u32(child, "reg", &port)) {
+				rc = -EINVAL;
+				goto err_out;
+			}
 
-		default:
-			dev_err(dev, "couldn't get sata-phy\n");
+			if (port >= hpriv->nports) {
+				dev_warn(dev, "invalid port number %d\n", port);
+				continue;
+			}
+
+			mask_port_map |= BIT(port);
+
+			hpriv->phys[port] = devm_of_phy_get(dev, child, NULL);
+			if (IS_ERR(hpriv->phys[port])) {
+				rc = PTR_ERR(hpriv->phys[port]);
+				dev_err(dev,
+					"couldn't get PHY in node %s: %d\n",
+					child->name, rc);
+				goto err_out;
+			}
+
+			enabled_ports++;
+		}
+		if (!enabled_ports) {
+			dev_warn(dev, "No port enabled\n");
+			rc = -ENODEV;
 			goto err_out;
 		}
+
+		if (!hpriv->mask_port_map)
+			hpriv->mask_port_map = mask_port_map;
+	} else {
+		/*
+		 * If no sub-node was found, keep this for device tree
+		 * compatibility
+		 */
+		struct phy *phy = devm_phy_get(dev, "sata-phy");
+		if (!IS_ERR(phy)) {
+			hpriv->phys = devm_kzalloc(dev, sizeof(*hpriv->phys),
+						   GFP_KERNEL);
+			if (!hpriv->phys) {
+				rc = -ENOMEM;
+				goto err_out;
+			}
+
+			hpriv->phys[0] = phy;
+			hpriv->nports = 1;
+		} else {
+			rc = PTR_ERR(phy);
+			switch (rc) {
+				case -ENOSYS:
+					/* No PHY support. Check if PHY is required. */
+					if (of_find_property(dev->of_node, "phys", NULL)) {
+						dev_err(dev, "couldn't get sata-phy: ENOSYS\n");
+						goto err_out;
+					}
+				case -ENODEV:
+					/* continue normally */
+					hpriv->phys = NULL;
+					break;
+
+				default:
+					goto err_out;
+
+			}
+		}
 	}
 
 	pm_runtime_enable(dev);
@@ -283,11 +401,9 @@ EXPORT_SYMBOL_GPL(ahci_platform_get_resources);
  * @pdev: platform device pointer for the host
  * @hpriv: ahci-host private data for the host
  * @pi_template: template for the ata_port_info to use
- * @force_port_map: param passed to ahci_save_initial_config
- * @mask_port_map: param passed to ahci_save_initial_config
  *
  * This function does all the usual steps needed to bring up an
- * ahci-platform host, note any necessary resources (ie clks, phy, etc.)
+ * ahci-platform host, note any necessary resources (ie clks, phys, etc.)
  * must be initialized / enabled before calling this.
  *
  * RETURNS:
@@ -295,9 +411,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_get_resources);
  */
 int ahci_platform_init_host(struct platform_device *pdev,
 			    struct ahci_host_priv *hpriv,
-			    const struct ata_port_info *pi_template,
-			    unsigned int force_port_map,
-			    unsigned int mask_port_map)
+			    const struct ata_port_info *pi_template)
 {
 	struct device *dev = &pdev->dev;
 	struct ata_port_info pi = *pi_template;
@@ -312,9 +426,9 @@ int ahci_platform_init_host(struct platform_device *pdev,
 	}
 
 	/* prepare host */
-	hpriv->flags |= (unsigned long)pi.private_data;
+	pi.private_data = (void *)(unsigned long)hpriv->flags;
 
-	ahci_save_initial_config(dev, hpriv, force_port_map, mask_port_map);
+	ahci_save_initial_config(dev, hpriv);
 
 	if (hpriv->cap & HOST_CAP_NCQ)
 		pi.flags |= ATA_FLAG_NCQ;
@@ -361,6 +475,19 @@ int ahci_platform_init_host(struct platform_device *pdev,
 			ap->ops = &ata_dummy_port_ops;
 	}
 
+	if (hpriv->cap & HOST_CAP_64) {
+		rc = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
+		if (rc) {
+			rc = dma_coerce_mask_and_coherent(dev,
+							  DMA_BIT_MASK(32));
+			if (rc) {
+				dev_err(dev, "Failed to enable 64-bit DMA.\n");
+				return rc;
+			}
+			dev_warn(dev, "Enable 32-bit DMA instead of 64-bit.\n");
+		}
+	}
+
 	rc = ahci_reset_controller(host);
 	if (rc)
 		return rc;
@@ -391,7 +518,7 @@ static void ahci_host_stop(struct ata_host *host)
  * @dev: device pointer for the host
  *
  * This function does all the usual steps needed to suspend an
- * ahci-platform host, note any necessary resources (ie clks, phy, etc.)
+ * ahci-platform host, note any necessary resources (ie clks, phys, etc.)
  * must be disabled after calling this.
  *
  * RETURNS:
@@ -428,7 +555,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_suspend_host);
  * @dev: device pointer for the host
  *
  * This function does all the usual steps needed to resume an ahci-platform
- * host, note any necessary resources (ie clks, phy, etc.)  must be
+ * host, note any necessary resources (ie clks, phys, etc.)  must be
  * initialized / enabled before calling this.
  *
  * RETURNS:
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 18d97d5c7d9..677c0c1b03b 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4787,6 +4787,10 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
  *	ata_qc_new - Request an available ATA command, for queueing
  *	@ap: target port
  *
+ *	Some ATA host controllers may implement a queue depth which is less
+ *	than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond
+ *	the hardware limitation.
+ *
  *	LOCKING:
  *	None.
  */
@@ -4794,14 +4798,15 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
 {
 	struct ata_queued_cmd *qc = NULL;
+	unsigned int max_queue = ap->host->n_tags;
 	unsigned int i, tag;
 
 	/* no command while frozen */
 	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
 		return NULL;
 
-	for (i = 0; i < ATA_MAX_QUEUE; i++) {
-		tag = (i + ap->last_tag + 1) % ATA_MAX_QUEUE;
+	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
+		tag = tag < max_queue ? tag : 0;
 
 		/* the last tag is reserved for internal command. */
 		if (tag == ATA_TAG_INTERNAL)
@@ -6088,6 +6093,7 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 {
 	spin_lock_init(&host->lock);
 	mutex_init(&host->eh_mutex);
+	host->n_tags = ATA_MAX_QUEUE - 1;
 	host->dev = dev;
 	host->ops = ops;
 }
@@ -6169,6 +6175,8 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 {
 	int i, rc;
 
+	host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE - 1);
+
 	/* host must have been started */
 	if (!(host->flags & ATA_HOST_STARTED)) {
 		dev_err(host->dev, "BUG: trying to register unstarted host\n");
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 6760fc4e85b..dad83df555c 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1811,7 +1811,7 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc,
 	case ATA_DEV_ATA:
 		if (err & ATA_ICRC)
 			qc->err_mask |= AC_ERR_ATA_BUS;
-		if (err & ATA_UNC)
+		if (err & (ATA_UNC | ATA_AMNF))
 			qc->err_mask |= AC_ERR_MEDIA;
 		if (err & ATA_IDNF)
 			qc->err_mask |= AC_ERR_INVALID;
@@ -2556,11 +2556,12 @@ static void ata_eh_link_report(struct ata_link *link)
 		}
 
 		if (cmd->command != ATA_CMD_PACKET &&
-		    (res->feature & (ATA_ICRC | ATA_UNC | ATA_IDNF |
-				     ATA_ABORTED)))
-			ata_dev_err(qc->dev, "error: { %s%s%s%s}\n",
+		    (res->feature & (ATA_ICRC | ATA_UNC | ATA_AMNF |
+				     ATA_IDNF | ATA_ABORTED)))
+			ata_dev_err(qc->dev, "error: { %s%s%s%s%s}\n",
 			  res->feature & ATA_ICRC ? "ICRC " : "",
 			  res->feature & ATA_UNC ? "UNC " : "",
+			  res->feature & ATA_AMNF ? "AMNF " : "",
 			  res->feature & ATA_IDNF ? "IDNF " : "",
 			  res->feature & ATA_ABORTED ? "ABRT " : "");
 #endif
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index ef8567de6a7..72691fd9394 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1993,7 +1993,11 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
 	memcpy(rbuf, hdr, sizeof(hdr));
 	memcpy(&rbuf[8], "ATA     ", 8);
 	ata_id_string(args->id, &rbuf[16], ATA_ID_PROD, 16);
-	ata_id_string(args->id, &rbuf[32], ATA_ID_FW_REV, 4);
+
+	/* From SAT, use last 2 words from fw rev unless they are spaces */
+	ata_id_string(args->id, &rbuf[32], ATA_ID_FW_REV + 2, 4);
+	if (strncmp(&rbuf[32], "    ", 4) == 0)
+		ata_id_string(args->id, &rbuf[32], ATA_ID_FW_REV, 4);
 
 	if (rbuf[32] == 0 || rbuf[32] == ' ')
 		memcpy(&rbuf[32], "n/a ", 4);
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index b603720b877..1121153f1ec 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2433,15 +2433,6 @@ int ata_pci_sff_activate_host(struct ata_host *host,
 		mask = (1 << 2) | (1 << 0);
 		if ((tmp8 & mask) != mask)
 			legacy_mode = 1;
-#if defined(CONFIG_NO_ATA_LEGACY)
-		/* Some platforms with PCI limits cannot address compat
-		   port space. In that case we punt if their firmware has
-		   left a device in compatibility mode */
-		if (legacy_mode) {
-			printk(KERN_ERR "ata: Compatibility mode ATA is not supported on this platform, skipping.\n");
-			return -EOPNOTSUPP;
-		}
-#endif
 	}
 
 	if (!devres_open_group(dev, NULL, GFP_KERNEL))
diff --git a/drivers/ata/pata_acpi.c b/drivers/ata/pata_acpi.c
index 5108b8744dc..b70fce2a38e 100644
--- a/drivers/ata/pata_acpi.c
+++ b/drivers/ata/pata_acpi.c
@@ -265,7 +265,7 @@ static struct pci_driver pacpi_pci_driver = {
 	.id_table		= pacpi_pci_tbl,
 	.probe			= pacpi_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_ali.c b/drivers/ata/pata_ali.c
index 1b7b2ccabcf..d19cd88ed2d 100644
--- a/drivers/ata/pata_ali.c
+++ b/drivers/ata/pata_ali.c
@@ -589,7 +589,7 @@ static int ali_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ata_pci_bmdma_init_one(pdev, ppi, &ali_sht, NULL, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int ali_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -616,7 +616,7 @@ static struct pci_driver ali_pci_driver = {
 	.id_table	= ali,
 	.probe 		= ali_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ali_reinit_one,
 #endif
diff --git a/drivers/ata/pata_amd.c b/drivers/ata/pata_amd.c
index 1206fa6b62c..8d4d959a821 100644
--- a/drivers/ata/pata_amd.c
+++ b/drivers/ata/pata_amd.c
@@ -574,7 +574,7 @@ static int amd_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_bmdma_init_one(pdev, ppi, &amd_sht, hpriv, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int amd_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -625,7 +625,7 @@ static struct pci_driver amd_pci_driver = {
 	.id_table	= amd,
 	.probe 		= amd_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= amd_reinit_one,
 #endif
diff --git a/drivers/ata/pata_artop.c b/drivers/ata/pata_artop.c
index 3aa4e655e3c..96c05c9494f 100644
--- a/drivers/ata/pata_artop.c
+++ b/drivers/ata/pata_artop.c
@@ -422,7 +422,7 @@ static const struct pci_device_id artop_pci_tbl[] = {
 	{ }	/* terminate list */
 };
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int atp8xx_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -444,7 +444,7 @@ static struct pci_driver artop_pci_driver = {
 	.id_table		= artop_pci_tbl,
 	.probe			= artop_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= atp8xx_reinit_one,
 #endif
diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c
index 30fa4ca4cef..970f7767e5f 100644
--- a/drivers/ata/pata_atiixp.c
+++ b/drivers/ata/pata_atiixp.c
@@ -298,7 +298,7 @@ static struct pci_driver atiixp_pci_driver = {
 	.id_table	= atiixp,
 	.probe 		= atiixp_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.resume		= ata_pci_device_resume,
 	.suspend	= ata_pci_device_suspend,
 #endif
diff --git a/drivers/ata/pata_atp867x.c b/drivers/ata/pata_atp867x.c
index 7e73a0f1e32..a705cfca90f 100644
--- a/drivers/ata/pata_atp867x.c
+++ b/drivers/ata/pata_atp867x.c
@@ -530,7 +530,7 @@ err_out:
 	return rc;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int atp867x_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -558,7 +558,7 @@ static struct pci_driver atp867x_driver = {
 	.id_table 	= atp867x_pci_tbl,
 	.probe 		= atp867x_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= atp867x_reinit_one,
 #endif
diff --git a/drivers/ata/pata_bf54x.c b/drivers/ata/pata_bf54x.c
index ba0d8a29dc2..03f2f2bc83b 100644
--- a/drivers/ata/pata_bf54x.c
+++ b/drivers/ata/pata_bf54x.c
@@ -1619,7 +1619,7 @@ static int bfin_atapi_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int bfin_atapi_suspend(struct platform_device *pdev, pm_message_t state)
 {
 	struct ata_host *host = platform_get_drvdata(pdev);
diff --git a/drivers/ata/pata_cmd640.c b/drivers/ata/pata_cmd640.c
index 57f1be64dbf..c47caa807fa 100644
--- a/drivers/ata/pata_cmd640.c
+++ b/drivers/ata/pata_cmd640.c
@@ -231,7 +231,7 @@ static int cmd640_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_sff_init_one(pdev, ppi, &cmd640_sht, NULL, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int cmd640_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -256,7 +256,7 @@ static struct pci_driver cmd640_pci_driver = {
 	.id_table	= cmd640,
 	.probe 		= cmd640_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= cmd640_reinit_one,
 #endif
diff --git a/drivers/ata/pata_cmd64x.c b/drivers/ata/pata_cmd64x.c
index 6bca3505b9e..13ca5883285 100644
--- a/drivers/ata/pata_cmd64x.c
+++ b/drivers/ata/pata_cmd64x.c
@@ -487,7 +487,7 @@ static int cmd64x_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_bmdma_init_one(pdev, ppi, &cmd64x_sht, NULL, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int cmd64x_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -518,7 +518,7 @@ static struct pci_driver cmd64x_pci_driver = {
 	.id_table	= cmd64x,
 	.probe 		= cmd64x_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= cmd64x_reinit_one,
 #endif
diff --git a/drivers/ata/pata_cs5520.c b/drivers/ata/pata_cs5520.c
index bcde4b78680..d65cb9d2fa8 100644
--- a/drivers/ata/pata_cs5520.c
+++ b/drivers/ata/pata_cs5520.c
@@ -229,7 +229,7 @@ static int cs5520_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_host_register(host, &cs5520_sht);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 /**
  *	cs5520_reinit_one	-	device resume
  *	@pdev: PCI device
@@ -278,7 +278,7 @@ static int cs5520_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg)
 	pci_save_state(pdev);
 	return 0;
 }
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 /* For now keep DMA off. We can set it for all but A rev CS5510 once the
    core ATA code can handle it */
@@ -295,7 +295,7 @@ static struct pci_driver cs5520_pci_driver = {
 	.id_table	= pata_cs5520,
 	.probe 		= cs5520_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= cs5520_pci_device_suspend,
 	.resume		= cs5520_reinit_one,
 #endif
diff --git a/drivers/ata/pata_cs5530.c b/drivers/ata/pata_cs5530.c
index 8afe854a5a5..48ae4b43447 100644
--- a/drivers/ata/pata_cs5530.c
+++ b/drivers/ata/pata_cs5530.c
@@ -326,7 +326,7 @@ static int cs5530_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_bmdma_init_one(pdev, ppi, &cs5530_sht, NULL, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int cs5530_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -343,7 +343,7 @@ static int cs5530_reinit_one(struct pci_dev *pdev)
 	ata_host_resume(host);
 	return 0;
 }
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 static const struct pci_device_id cs5530[] = {
 	{ PCI_VDEVICE(CYRIX, PCI_DEVICE_ID_CYRIX_5530_IDE), },
@@ -356,7 +356,7 @@ static struct pci_driver cs5530_pci_driver = {
 	.id_table	= cs5530,
 	.probe 		= cs5530_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= cs5530_reinit_one,
 #endif
diff --git a/drivers/ata/pata_cs5535.c b/drivers/ata/pata_cs5535.c
index 2c0986fa4bb..97584e8456d 100644
--- a/drivers/ata/pata_cs5535.c
+++ b/drivers/ata/pata_cs5535.c
@@ -200,7 +200,7 @@ static struct pci_driver cs5535_pci_driver = {
 	.id_table	= cs5535,
 	.probe 		= cs5535_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_cs5536.c b/drivers/ata/pata_cs5536.c
index 32ddcae5a36..6c15a554efb 100644
--- a/drivers/ata/pata_cs5536.c
+++ b/drivers/ata/pata_cs5536.c
@@ -297,7 +297,7 @@ static struct pci_driver cs5536_pci_driver = {
 	.id_table	= cs5536,
 	.probe		= cs5536_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_cypress.c b/drivers/ata/pata_cypress.c
index 3435bd6a5cc..793018460d8 100644
--- a/drivers/ata/pata_cypress.c
+++ b/drivers/ata/pata_cypress.c
@@ -151,7 +151,7 @@ static struct pci_driver cy82c693_pci_driver = {
 	.id_table	= cy82c693,
 	.probe 		= cy82c693_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_efar.c b/drivers/ata/pata_efar.c
index f440892225f..4a57a6f032d 100644
--- a/drivers/ata/pata_efar.c
+++ b/drivers/ata/pata_efar.c
@@ -288,7 +288,7 @@ static struct pci_driver efar_pci_driver = {
 	.id_table		= efar_pci_tbl,
 	.probe			= efar_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c
index cad9d45749c..4d37c5415fc 100644
--- a/drivers/ata/pata_ep93xx.c
+++ b/drivers/ata/pata_ep93xx.c
@@ -708,8 +708,8 @@ static void ep93xx_pata_dma_start(struct ata_queued_cmd *qc)
 	struct dma_chan *channel = qc->dma_dir == DMA_TO_DEVICE
 		? drv_data->dma_tx_channel : drv_data->dma_rx_channel;
 
-	txd = channel->device->device_prep_slave_sg(channel, qc->sg,
-		 qc->n_elem, qc->dma_dir, DMA_CTRL_ACK, NULL);
+	txd = dmaengine_prep_slave_sg(channel, qc->sg, qc->n_elem, qc->dma_dir,
+		DMA_CTRL_ACK);
 	if (!txd) {
 		dev_err(qc->ap->dev, "failed to prepare slave for sg dma\n");
 		return;
@@ -915,7 +915,7 @@ static int ep93xx_pata_probe(struct platform_device *pdev)
 	struct ep93xx_pata_data *drv_data;
 	struct ata_host *host;
 	struct ata_port *ap;
-	unsigned int irq;
+	int irq;
 	struct resource *mem_res;
 	void __iomem *ide_base;
 	int err;
diff --git a/drivers/ata/pata_hpt366.c b/drivers/ata/pata_hpt366.c
index 8e76f79689d..cbc3de793d1 100644
--- a/drivers/ata/pata_hpt366.c
+++ b/drivers/ata/pata_hpt366.c
@@ -386,7 +386,7 @@ static int hpt36x_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 	return ata_pci_bmdma_init_one(dev, ppi, &hpt36x_sht, hpriv, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int hpt36x_reinit_one(struct pci_dev *dev)
 {
 	struct ata_host *host = pci_get_drvdata(dev);
@@ -411,7 +411,7 @@ static struct pci_driver hpt36x_pci_driver = {
 	.id_table	= hpt36x,
 	.probe		= hpt36x_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= hpt36x_reinit_one,
 #endif
diff --git a/drivers/ata/pata_hpt3x3.c b/drivers/ata/pata_hpt3x3.c
index 255c5aaff3a..d019cdd5bc9 100644
--- a/drivers/ata/pata_hpt3x3.c
+++ b/drivers/ata/pata_hpt3x3.c
@@ -249,7 +249,7 @@ static int hpt3x3_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 				 IRQF_SHARED, &hpt3x3_sht);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int hpt3x3_reinit_one(struct pci_dev *dev)
 {
 	struct ata_host *host = pci_get_drvdata(dev);
@@ -277,7 +277,7 @@ static struct pci_driver hpt3x3_pci_driver = {
 	.id_table	= hpt3x3,
 	.probe 		= hpt3x3_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= hpt3x3_reinit_one,
 #endif
diff --git a/drivers/ata/pata_imx.c b/drivers/ata/pata_imx.c
index e0872db913d..af424573c2f 100644
--- a/drivers/ata/pata_imx.c
+++ b/drivers/ata/pata_imx.c
@@ -185,7 +185,7 @@ static int pata_imx_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int pata_imx_suspend(struct device *dev)
 {
 	struct ata_host *host = dev_get_drvdata(dev);
@@ -244,7 +244,7 @@ static struct platform_driver pata_imx_driver = {
 		.name		= DRV_NAME,
 		.of_match_table	= imx_pata_dt_ids,
 		.owner		= THIS_MODULE,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 		.pm		= &pata_imx_pm_ops,
 #endif
 	},
diff --git a/drivers/ata/pata_it8213.c b/drivers/ata/pata_it8213.c
index 81369d187a5..4f97d1e52f8 100644
--- a/drivers/ata/pata_it8213.c
+++ b/drivers/ata/pata_it8213.c
@@ -283,7 +283,7 @@ static struct pci_driver it8213_pci_driver = {
 	.id_table		= it8213_pci_tbl,
 	.probe			= it8213_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c
index dc3d7877f29..a5088ecb349 100644
--- a/drivers/ata/pata_it821x.c
+++ b/drivers/ata/pata_it821x.c
@@ -935,7 +935,7 @@ static int it821x_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_bmdma_init_one(pdev, ppi, &it821x_sht, NULL, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int it821x_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -965,7 +965,7 @@ static struct pci_driver it821x_pci_driver = {
 	.id_table	= it821x,
 	.probe 		= it821x_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= it821x_reinit_one,
 #endif
diff --git a/drivers/ata/pata_jmicron.c b/drivers/ata/pata_jmicron.c
index b1cfa0258fd..4d1a5d2c428 100644
--- a/drivers/ata/pata_jmicron.c
+++ b/drivers/ata/pata_jmicron.c
@@ -157,7 +157,7 @@ static struct pci_driver jmicron_pci_driver = {
 	.id_table		= jmicron_pci_tbl,
 	.probe			= jmicron_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index c28d0645e85..a02f76fdcfc 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -845,8 +845,7 @@ static int pata_macio_slave_config(struct scsi_device *sdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-
+#ifdef CONFIG_PM_SLEEP
 static int pata_macio_do_suspend(struct pata_macio_priv *priv, pm_message_t mesg)
 {
 	int rc;
@@ -907,8 +906,7 @@ static int pata_macio_do_resume(struct pata_macio_priv *priv)
 
 	return 0;
 }
-
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 static struct scsi_host_template pata_macio_sht = {
 	ATA_BASE_SHT(DRV_NAME),
@@ -1208,8 +1206,7 @@ static int pata_macio_detach(struct macio_dev *mdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-
+#ifdef CONFIG_PM_SLEEP
 static int pata_macio_suspend(struct macio_dev *mdev, pm_message_t mesg)
 {
 	struct ata_host *host = macio_get_drvdata(mdev);
@@ -1223,8 +1220,7 @@ static int pata_macio_resume(struct macio_dev *mdev)
 
 	return pata_macio_do_resume(host->private_data);
 }
-
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PMAC_MEDIABAY
 static void pata_macio_mb_event(struct macio_dev* mdev, int mb_state)
@@ -1316,8 +1312,7 @@ static void pata_macio_pci_detach(struct pci_dev *pdev)
 	ata_host_detach(host);
 }
 
-#ifdef CONFIG_PM
-
+#ifdef CONFIG_PM_SLEEP
 static int pata_macio_pci_suspend(struct pci_dev *pdev, pm_message_t mesg)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -1331,8 +1326,7 @@ static int pata_macio_pci_resume(struct pci_dev *pdev)
 
 	return pata_macio_do_resume(host->private_data);
 }
-
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 static struct of_device_id pata_macio_match[] =
 {
@@ -1360,7 +1354,7 @@ static struct macio_driver pata_macio_driver =
 	},
 	.probe		= pata_macio_attach,
 	.remove		= pata_macio_detach,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= pata_macio_suspend,
 	.resume		= pata_macio_resume,
 #endif
@@ -1383,7 +1377,7 @@ static struct pci_driver pata_macio_pci_driver = {
 	.id_table	= pata_macio_pci_match,
 	.probe		= pata_macio_pci_attach,
 	.remove		= pata_macio_pci_detach,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= pata_macio_pci_suspend,
 	.resume		= pata_macio_pci_resume,
 #endif
diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c
index 6bad3df3a13..ae9feb1ba8f 100644
--- a/drivers/ata/pata_marvell.c
+++ b/drivers/ata/pata_marvell.c
@@ -171,7 +171,7 @@ static struct pci_driver marvell_pci_driver = {
 	.id_table		= marvell_pci_tbl,
 	.probe			= marvell_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_mpc52xx.c b/drivers/ata/pata_mpc52xx.c
index 0024ced3e20..ccd1c83a05c 100644
--- a/drivers/ata/pata_mpc52xx.c
+++ b/drivers/ata/pata_mpc52xx.c
@@ -819,9 +819,7 @@ mpc52xx_ata_remove(struct platform_device *op)
 	return 0;
 }
 
-
-#ifdef CONFIG_PM
-
+#ifdef CONFIG_PM_SLEEP
 static int
 mpc52xx_ata_suspend(struct platform_device *op, pm_message_t state)
 {
@@ -847,10 +845,8 @@ mpc52xx_ata_resume(struct platform_device *op)
 
 	return 0;
 }
-
 #endif
 
-
 static struct of_device_id mpc52xx_ata_of_match[] = {
 	{ .compatible = "fsl,mpc5200-ata", },
 	{ .compatible = "mpc5200-ata", },
@@ -861,7 +857,7 @@ static struct of_device_id mpc52xx_ata_of_match[] = {
 static struct platform_driver mpc52xx_ata_of_platform_driver = {
 	.probe		= mpc52xx_ata_probe,
 	.remove		= mpc52xx_ata_remove,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= mpc52xx_ata_suspend,
 	.resume		= mpc52xx_ata_resume,
 #endif
diff --git a/drivers/ata/pata_mpiix.c b/drivers/ata/pata_mpiix.c
index f39a5379e81..202b4d60139 100644
--- a/drivers/ata/pata_mpiix.c
+++ b/drivers/ata/pata_mpiix.c
@@ -223,7 +223,7 @@ static struct pci_driver mpiix_pci_driver = {
 	.id_table	= mpiix,
 	.probe 		= mpiix_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_netcell.c b/drivers/ata/pata_netcell.c
index e3b97093ef9..0ea18331d46 100644
--- a/drivers/ata/pata_netcell.c
+++ b/drivers/ata/pata_netcell.c
@@ -92,7 +92,7 @@ static struct pci_driver netcell_pci_driver = {
 	.id_table		= netcell_pci_tbl,
 	.probe			= netcell_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_ninja32.c b/drivers/ata/pata_ninja32.c
index 56201a69af1..efb272da856 100644
--- a/drivers/ata/pata_ninja32.c
+++ b/drivers/ata/pata_ninja32.c
@@ -152,8 +152,7 @@ static int ninja32_init_one(struct pci_dev *dev, const struct pci_device_id *id)
 				 IRQF_SHARED, &ninja32_sht);
 }
 
-#ifdef CONFIG_PM
-
+#ifdef CONFIG_PM_SLEEP
 static int ninja32_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -183,7 +182,7 @@ static struct pci_driver ninja32_pci_driver = {
 	.id_table	= ninja32,
 	.probe 		= ninja32_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ninja32_reinit_one,
 #endif
diff --git a/drivers/ata/pata_ns87410.c b/drivers/ata/pata_ns87410.c
index 6154c3ee11a..200e1eb23a2 100644
--- a/drivers/ata/pata_ns87410.c
+++ b/drivers/ata/pata_ns87410.c
@@ -161,7 +161,7 @@ static struct pci_driver ns87410_pci_driver = {
 	.id_table	= ns87410,
 	.probe 		= ns87410_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_ns87415.c b/drivers/ata/pata_ns87415.c
index d44df7ccfe4..84c6b225b56 100644
--- a/drivers/ata/pata_ns87415.c
+++ b/drivers/ata/pata_ns87415.c
@@ -385,7 +385,7 @@ static const struct pci_device_id ns87415_pci_tbl[] = {
 	{ }	/* terminate list */
 };
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int ns87415_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -407,7 +407,7 @@ static struct pci_driver ns87415_pci_driver = {
 	.id_table		= ns87415_pci_tbl,
 	.probe			= ns87415_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ns87415_reinit_one,
 #endif
diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index 83c4ddb1bc7..2a97d3a531e 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -865,7 +865,7 @@ static int octeon_cf_probe(struct platform_device *pdev)
 	if (node == NULL)
 		return -EINVAL;
 
-	cf_port = kzalloc(sizeof(*cf_port), GFP_KERNEL);
+	cf_port = devm_kzalloc(&pdev->dev, sizeof(*cf_port), GFP_KERNEL);
 	if (!cf_port)
 		return -ENOMEM;
 
@@ -881,10 +881,9 @@ static int octeon_cf_probe(struct platform_device *pdev)
 	n_size = of_n_size_cells(node);
 
 	reg_prop = of_find_property(node, "reg", &reg_len);
-	if (!reg_prop || reg_len < sizeof(__be32)) {
-		rv = -EINVAL;
-		goto free_cf_port;
-	}
+	if (!reg_prop || reg_len < sizeof(__be32))
+		return -EINVAL;
+
 	cs_num = reg_prop->value;
 	cf_port->cs0 = be32_to_cpup(cs_num);
 
@@ -901,16 +900,13 @@ static int octeon_cf_probe(struct platform_device *pdev)
 				res_dma = platform_get_resource(dma_dev, IORESOURCE_MEM, 0);
 				if (!res_dma) {
 					of_node_put(dma_node);
-					rv = -EINVAL;
-					goto free_cf_port;
+					return -EINVAL;
 				}
 				cf_port->dma_base = (u64)devm_ioremap_nocache(&pdev->dev, res_dma->start,
 									 resource_size(res_dma));
-
 				if (!cf_port->dma_base) {
 					of_node_put(dma_node);
-					rv = -EINVAL;
-					goto free_cf_port;
+					return -EINVAL;
 				}
 
 				irq_handler = octeon_cf_interrupt;
@@ -921,41 +917,34 @@ static int octeon_cf_probe(struct platform_device *pdev)
 			of_node_put(dma_node);
 		}
 		res_cs1 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-		if (!res_cs1) {
-			rv = -EINVAL;
-			goto free_cf_port;
-		}
+		if (!res_cs1)
+			return -EINVAL;
+
 		cs1 = devm_ioremap_nocache(&pdev->dev, res_cs1->start,
 					   resource_size(res_cs1));
-
 		if (!cs1)
-			goto free_cf_port;
+			return rv;
+
+		if (reg_len < (n_addr + n_size + 1) * sizeof(__be32))
+			return -EINVAL;
 
-		if (reg_len < (n_addr + n_size + 1) * sizeof(__be32)) {
-			rv = -EINVAL;
-			goto free_cf_port;
-		}
 		cs_num += n_addr + n_size;
 		cf_port->cs1 = be32_to_cpup(cs_num);
 	}
 
 	res_cs0 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-
-	if (!res_cs0) {
-		rv = -EINVAL;
-		goto free_cf_port;
-	}
+	if (!res_cs0)
+		return -EINVAL;
 
 	cs0 = devm_ioremap_nocache(&pdev->dev, res_cs0->start,
 				   resource_size(res_cs0));
-
 	if (!cs0)
-		goto free_cf_port;
+		return rv;
 
 	/* allocate host */
 	host = ata_host_alloc(&pdev->dev, 1);
 	if (!host)
-		goto free_cf_port;
+		return rv;
 
 	ap = host->ports[0];
 	ap->private_data = cf_port;
@@ -1020,17 +1009,12 @@ static int octeon_cf_probe(struct platform_device *pdev)
 
 	ata_port_desc(ap, "cmd %p ctl %p", base, ap->ioaddr.ctl_addr);
 
-
 	dev_info(&pdev->dev, "version " DRV_VERSION" %d bit%s.\n",
 		 is_16bit ? 16 : 8,
 		 cf_port->is_true_ide ? ", True IDE" : "");
 
 	return ata_host_activate(host, irq, irq_handler,
 				 IRQF_SHARED, &octeon_cf_sht);
-
-free_cf_port:
-	kfree(cf_port);
-	return rv;
 }
 
 static void octeon_cf_shutdown(struct device *dev)
diff --git a/drivers/ata/pata_oldpiix.c b/drivers/ata/pata_oldpiix.c
index 319b64491b7..b9bf78b7d48 100644
--- a/drivers/ata/pata_oldpiix.c
+++ b/drivers/ata/pata_oldpiix.c
@@ -258,7 +258,7 @@ static struct pci_driver oldpiix_pci_driver = {
 	.id_table		= oldpiix_pci_tbl,
 	.probe			= oldpiix_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_opti.c b/drivers/ata/pata_opti.c
index fb042e0519d..3a944a02926 100644
--- a/drivers/ata/pata_opti.c
+++ b/drivers/ata/pata_opti.c
@@ -184,7 +184,7 @@ static struct pci_driver opti_pci_driver = {
 	.id_table	= opti,
 	.probe 		= opti_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_optidma.c b/drivers/ata/pata_optidma.c
index bb71ea214b9..bdec7efa464 100644
--- a/drivers/ata/pata_optidma.c
+++ b/drivers/ata/pata_optidma.c
@@ -440,7 +440,7 @@ static struct pci_driver optidma_pci_driver = {
 	.id_table	= optidma,
 	.probe 		= optidma_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index 1151f23177b..4d06a5cda98 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -62,7 +62,7 @@ enum {
 };
 
 static int pdc2027x_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int pdc2027x_reinit_one(struct pci_dev *pdev);
 #endif
 static int pdc2027x_prereset(struct ata_link *link, unsigned long deadline);
@@ -128,7 +128,7 @@ static struct pci_driver pdc2027x_pci_driver = {
 	.id_table		= pdc2027x_pci_tbl,
 	.probe			= pdc2027x_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= pdc2027x_reinit_one,
 #endif
@@ -761,7 +761,7 @@ static int pdc2027x_init_one(struct pci_dev *pdev,
 				 IRQF_SHARED, &pdc2027x_sht);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int pdc2027x_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
diff --git a/drivers/ata/pata_pdc202xx_old.c b/drivers/ata/pata_pdc202xx_old.c
index defa050e178..9001991d283 100644
--- a/drivers/ata/pata_pdc202xx_old.c
+++ b/drivers/ata/pata_pdc202xx_old.c
@@ -377,7 +377,7 @@ static struct pci_driver pdc202xx_pci_driver = {
 	.id_table	= pdc202xx,
 	.probe 		= pdc202xx_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_piccolo.c b/drivers/ata/pata_piccolo.c
index 0b46be11705..35cb0e26323 100644
--- a/drivers/ata/pata_piccolo.c
+++ b/drivers/ata/pata_piccolo.c
@@ -110,7 +110,7 @@ static struct pci_driver ata_tosh_pci_driver = {
 	.id_table	= ata_tosh,
 	.probe 		= ata_tosh_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_radisys.c b/drivers/ata/pata_radisys.c
index be3f10240dc..a3f1123d17a 100644
--- a/drivers/ata/pata_radisys.c
+++ b/drivers/ata/pata_radisys.c
@@ -237,7 +237,7 @@ static struct pci_driver radisys_pci_driver = {
 	.id_table		= radisys_pci_tbl,
 	.probe			= radisys_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_rdc.c b/drivers/ata/pata_rdc.c
index 521b2137ea3..9ce5952216b 100644
--- a/drivers/ata/pata_rdc.c
+++ b/drivers/ata/pata_rdc.c
@@ -382,7 +382,7 @@ static struct pci_driver rdc_pci_driver = {
 	.id_table		= rdc_pci_tbl,
 	.probe			= rdc_init_one,
 	.remove			= rdc_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_rz1000.c b/drivers/ata/pata_rz1000.c
index caedc90855b..b3ec18c6bcc 100644
--- a/drivers/ata/pata_rz1000.c
+++ b/drivers/ata/pata_rz1000.c
@@ -101,7 +101,7 @@ static int rz1000_init_one (struct pci_dev *pdev, const struct pci_device_id *en
 	return -ENODEV;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int rz1000_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -133,7 +133,7 @@ static struct pci_driver rz1000_pci_driver = {
 	.id_table	= pata_rz1000,
 	.probe 		= rz1000_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= rz1000_reinit_one,
 #endif
diff --git a/drivers/ata/pata_samsung_cf.c b/drivers/ata/pata_samsung_cf.c
index 0610e78c8a2..2578fc16960 100644
--- a/drivers/ata/pata_samsung_cf.c
+++ b/drivers/ata/pata_samsung_cf.c
@@ -54,7 +54,6 @@
 
 enum s3c_cpu_type {
 	TYPE_S3C64XX,
-	TYPE_S5PC100,
 	TYPE_S5PV210,
 };
 
@@ -476,10 +475,6 @@ static void pata_s3c_hwinit(struct s3c_ide_info *info,
 		writel(0x1b, info->ide_addr + S3C_ATA_IRQ_MSK);
 		break;
 
-	case TYPE_S5PC100:
-		pata_s3c_cfg_mode(info->sfr_addr);
-		/* FALLTHROUGH */
-
 	case TYPE_S5PV210:
 		/* Configure as little endian */
 		pata_s3c_set_endian(info->ide_addr, 0);
@@ -549,11 +544,6 @@ static int __init pata_s3c_probe(struct platform_device *pdev)
 		info->sfr_addr = info->ide_addr + 0x1800;
 		info->ide_addr += 0x1900;
 		info->fifo_status_reg = 0x94;
-	} else if (cpu_type == TYPE_S5PC100) {
-		ap->ops = &pata_s5p_port_ops;
-		info->sfr_addr = info->ide_addr + 0x1800;
-		info->ide_addr += 0x1900;
-		info->fifo_status_reg = 0x84;
 	} else {
 		ap->ops = &pata_s5p_port_ops;
 		info->fifo_status_reg = 0x84;
@@ -619,7 +609,7 @@ static int __exit pata_s3c_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int pata_s3c_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -653,9 +643,6 @@ static struct platform_device_id pata_s3c_driver_ids[] = {
 		.name		= "s3c64xx-pata",
 		.driver_data	= TYPE_S3C64XX,
 	}, {
-		.name		= "s5pc100-pata",
-		.driver_data	= TYPE_S5PC100,
-	}, {
 		.name		= "s5pv210-pata",
 		.driver_data	= TYPE_S5PV210,
 	},
@@ -670,7 +657,7 @@ static struct platform_driver pata_s3c_driver = {
 	.driver		= {
 		.name	= DRV_NAME,
 		.owner	= THIS_MODULE,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 		.pm	= &pata_s3c_pm_ops,
 #endif
 	},
diff --git a/drivers/ata/pata_sc1200.c b/drivers/ata/pata_sc1200.c
index 96a232fffae..c71de5d680d 100644
--- a/drivers/ata/pata_sc1200.c
+++ b/drivers/ata/pata_sc1200.c
@@ -254,7 +254,7 @@ static struct pci_driver sc1200_pci_driver = {
 	.id_table	= sc1200,
 	.probe 		= sc1200_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
index f1f5b5ae338..4e006d74bef 100644
--- a/drivers/ata/pata_scc.c
+++ b/drivers/ata/pata_scc.c
@@ -1096,7 +1096,7 @@ static struct pci_driver scc_pci_driver = {
 	.id_table		= scc_pci_tbl,
 	.probe			= scc_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_sch.c b/drivers/ata/pata_sch.c
index 5a1cde0ea36..b920c3407f8 100644
--- a/drivers/ata/pata_sch.c
+++ b/drivers/ata/pata_sch.c
@@ -64,7 +64,7 @@ static struct pci_driver sch_pci_driver = {
 	.id_table		= sch_pci_tbl,
 	.probe			= sch_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index e27f31fe1b6..fc5f31d4828 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -436,7 +436,7 @@ static int serverworks_init_one(struct pci_dev *pdev, const struct pci_device_id
 	return ata_pci_bmdma_init_one(pdev, ppi, &serverworks_sht, NULL, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int serverworks_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -468,7 +468,7 @@ static struct pci_driver serverworks_pci_driver = {
 	.id_table	= serverworks,
 	.probe 		= serverworks_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= serverworks_reinit_one,
 #endif
diff --git a/drivers/ata/pata_sil680.c b/drivers/ata/pata_sil680.c
index 73fe362d971..f597edccede 100644
--- a/drivers/ata/pata_sil680.c
+++ b/drivers/ata/pata_sil680.c
@@ -403,7 +403,7 @@ use_ioports:
 	return ata_pci_bmdma_init_one(pdev, ppi, &sil680_sht, NULL, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int sil680_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -429,7 +429,7 @@ static struct pci_driver sil680_pci_driver = {
 	.id_table	= sil680,
 	.probe 		= sil680_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= sil680_reinit_one,
 #endif
diff --git a/drivers/ata/pata_sis.c b/drivers/ata/pata_sis.c
index 78d913aa93c..626f989d5c6 100644
--- a/drivers/ata/pata_sis.c
+++ b/drivers/ata/pata_sis.c
@@ -869,7 +869,7 @@ static int sis_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
 	return ata_pci_bmdma_init_one(pdev, ppi, &sis_sht, chipset, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int sis_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -899,7 +899,7 @@ static struct pci_driver sis_pci_driver = {
 	.id_table		= sis_pci_tbl,
 	.probe			= sis_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= sis_reinit_one,
 #endif
diff --git a/drivers/ata/pata_sl82c105.c b/drivers/ata/pata_sl82c105.c
index 900f0e4a1fa..4935f61f629 100644
--- a/drivers/ata/pata_sl82c105.c
+++ b/drivers/ata/pata_sl82c105.c
@@ -337,7 +337,7 @@ static int sl82c105_init_one(struct pci_dev *dev, const struct pci_device_id *id
 	return ata_pci_bmdma_init_one(dev, ppi, &sl82c105_sht, NULL, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int sl82c105_reinit_one(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -365,7 +365,7 @@ static struct pci_driver sl82c105_pci_driver = {
 	.id_table	= sl82c105,
 	.probe 		= sl82c105_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= sl82c105_reinit_one,
 #endif
diff --git a/drivers/ata/pata_triflex.c b/drivers/ata/pata_triflex.c
index 7bc78e264f9..d9364af8eb6 100644
--- a/drivers/ata/pata_triflex.c
+++ b/drivers/ata/pata_triflex.c
@@ -207,7 +207,7 @@ static const struct pci_device_id triflex[] = {
 	{ },
 };
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int triflex_ata_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -233,7 +233,7 @@ static struct pci_driver triflex_pci_driver = {
 	.id_table	= triflex,
 	.probe 		= triflex_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= triflex_ata_pci_device_suspend,
 	.resume		= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index f6c9632bdff..1ca6bcab369 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -659,7 +659,7 @@ static int via_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	return ata_pci_bmdma_init_one(pdev, ppi, &via_sht, (void *)config, 0);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 /**
  *	via_reinit_one		-	reinit after resume
  *	@pdev; PCI device
@@ -704,7 +704,7 @@ static struct pci_driver via_pci_driver = {
 	.id_table	= via,
 	.probe 		= via_init_one,
 	.remove		= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= via_reinit_one,
 #endif
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index fb0b40a191c..07bc7e4dbd0 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -734,13 +734,12 @@ static int sata_fsl_port_start(struct ata_port *ap)
 	if (!pp)
 		return -ENOMEM;
 
-	mem = dma_alloc_coherent(dev, SATA_FSL_PORT_PRIV_DMA_SZ, &mem_dma,
-				 GFP_KERNEL);
+	mem = dma_zalloc_coherent(dev, SATA_FSL_PORT_PRIV_DMA_SZ, &mem_dma,
+				  GFP_KERNEL);
 	if (!mem) {
 		kfree(pp);
 		return -ENOMEM;
 	}
-	memset(mem, 0, SATA_FSL_PORT_PRIV_DMA_SZ);
 
 	pp->cmdslot = mem;
 	pp->cmdslot_paddr = mem_dma;
@@ -774,20 +773,6 @@ static int sata_fsl_port_start(struct ata_port *ap)
 	VPRINTK("HControl = 0x%x\n", ioread32(hcr_base + HCONTROL));
 	VPRINTK("CHBA  = 0x%x\n", ioread32(hcr_base + CHBA));
 
-#ifdef CONFIG_MPC8315_DS
-	/*
-	 * Workaround for 8315DS board 3gbps link-up issue,
-	 * currently limit SATA port to GEN1 speed
-	 */
-	sata_fsl_scr_read(&ap->link, SCR_CONTROL, &temp);
-	temp &= ~(0xF << 4);
-	temp |= (0x1 << 4);
-	sata_fsl_scr_write(&ap->link, SCR_CONTROL, temp);
-
-	sata_fsl_scr_read(&ap->link, SCR_CONTROL, &temp);
-	dev_warn(dev, "scr_control, speed limited to %x\n", temp);
-#endif
-
 	return 0;
 }
 
@@ -1588,7 +1573,7 @@ static int sata_fsl_remove(struct platform_device *ofdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int sata_fsl_suspend(struct platform_device *op, pm_message_t state)
 {
 	struct ata_host *host = platform_get_drvdata(op);
@@ -1644,7 +1629,7 @@ static struct platform_driver fsl_sata_driver = {
 	},
 	.probe		= sata_fsl_probe,
 	.remove		= sata_fsl_remove,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= sata_fsl_suspend,
 	.resume		= sata_fsl_resume,
 #endif
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index 65965cf5af0..da3bc2709c6 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -512,7 +512,7 @@ static int ahci_highbank_probe(struct platform_device *pdev)
 		return rc;
 
 
-	ahci_save_initial_config(dev, hpriv, 0, 0);
+	ahci_save_initial_config(dev, hpriv);
 
 	/* prepare host */
 	if (hpriv->cap & HOST_CAP_NCQ)
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index 5c54d957370..069827826b2 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -785,7 +785,7 @@ static int init_controller(void __iomem *mmio_base, u16 hctl)
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int inic_pci_device_resume(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -898,7 +898,7 @@ static const struct pci_device_id inic_pci_tbl[] = {
 static struct pci_driver inic_pci_driver = {
 	.name 		= DRV_NAME,
 	.id_table	= inic_pci_tbl,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend	= ata_pci_device_suspend,
 	.resume		= inic_pci_device_resume,
 #endif
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 05c8a44adf8..391cfda1e83 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -4222,7 +4222,7 @@ static int mv_platform_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int mv_platform_suspend(struct platform_device *pdev, pm_message_t state)
 {
 	struct ata_host *host = platform_get_drvdata(pdev);
@@ -4289,7 +4289,7 @@ static struct platform_driver mv_platform_driver = {
 #ifdef CONFIG_PCI
 static int mv_pci_init_one(struct pci_dev *pdev,
 			   const struct pci_device_id *ent);
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int mv_pci_device_resume(struct pci_dev *pdev);
 #endif
 
@@ -4299,7 +4299,7 @@ static struct pci_driver mv_pci_driver = {
 	.id_table		= mv_pci_tbl,
 	.probe			= mv_pci_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= mv_pci_device_resume,
 #endif
@@ -4457,7 +4457,7 @@ static int mv_pci_init_one(struct pci_dev *pdev,
 				 IS_GEN_I(hpriv) ? &mv5_sht : &mv6_sht);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int mv_pci_device_resume(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index ba5f2712033..cdf99fac139 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -295,7 +295,7 @@ struct nv_swncq_port_priv {
 #define NV_ADMA_CHECK_INTR(GCTL, PORT) ((GCTL) & (1 << (19 + (12 * (PORT)))))
 
 static int nv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int nv_pci_device_resume(struct pci_dev *pdev);
 #endif
 static void nv_ck804_host_stop(struct ata_host *host);
@@ -379,7 +379,7 @@ static struct pci_driver nv_pci_driver = {
 	.name			= DRV_NAME,
 	.id_table		= nv_pci_tbl,
 	.probe			= nv_init_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= nv_pci_device_resume,
 #endif
@@ -2431,7 +2431,7 @@ static int nv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return ata_pci_sff_activate_host(host, ipriv->irq_handler, ipriv->sht);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int nv_pci_device_resume(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 2b25bd83fc9..61eb6d77dac 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -937,7 +937,7 @@ static int sata_rcar_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int sata_rcar_suspend(struct device *dev)
 {
 	struct ata_host *host = dev_get_drvdata(dev);
@@ -991,7 +991,7 @@ static struct platform_driver sata_rcar_driver = {
 		.name		= DRV_NAME,
 		.owner		= THIS_MODULE,
 		.of_match_table	= sata_rcar_match,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 		.pm		= &sata_rcar_pm_ops,
 #endif
 	},
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 3062f8605b2..40b76b2d18c 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -112,7 +112,7 @@ enum {
 };
 
 static int sil_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int sil_pci_device_resume(struct pci_dev *pdev);
 #endif
 static void sil_dev_config(struct ata_device *dev);
@@ -166,7 +166,7 @@ static struct pci_driver sil_pci_driver = {
 	.id_table		= sil_pci_tbl,
 	.probe			= sil_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= sil_pci_device_resume,
 #endif
@@ -802,7 +802,7 @@ static int sil_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 				 &sil_sht);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int sil_pci_device_resume(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index aa1051ba6d1..d81b20ddb52 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -353,8 +353,10 @@ static void sil24_error_handler(struct ata_port *ap);
 static void sil24_post_internal_cmd(struct ata_queued_cmd *qc);
 static int sil24_port_start(struct ata_port *ap);
 static int sil24_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int sil24_pci_device_resume(struct pci_dev *pdev);
+#endif
+#ifdef CONFIG_PM
 static int sil24_port_resume(struct ata_port *ap);
 #endif
 
@@ -375,7 +377,7 @@ static struct pci_driver sil24_pci_driver = {
 	.id_table		= sil24_pci_tbl,
 	.probe			= sil24_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= sil24_pci_device_resume,
 #endif
@@ -1152,8 +1154,8 @@ static irqreturn_t sil24_interrupt(int irq, void *dev_instance)
 	status = readl(host_base + HOST_IRQ_STAT);
 
 	if (status == 0xffffffff) {
-		printk(KERN_ERR DRV_NAME ": IRQ status == 0xffffffff, "
-		       "PCI fault or device removal?\n");
+		dev_err(host->dev, "IRQ status == 0xffffffff, "
+			"PCI fault or device removal?\n");
 		goto out;
 	}
 
@@ -1350,7 +1352,7 @@ static int sil24_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 				 &sil24_sht);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int sil24_pci_device_resume(struct pci_dev *pdev)
 {
 	struct ata_host *host = pci_get_drvdata(pdev);
@@ -1370,7 +1372,9 @@ static int sil24_pci_device_resume(struct pci_dev *pdev)
 
 	return 0;
 }
+#endif
 
+#ifdef CONFIG_PM
 static int sil24_port_resume(struct ata_port *ap)
 {
 	sil24_config_pmp(ap, ap->nr_pmp_links);
diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c
index b513428171b..d1637ac40a7 100644
--- a/drivers/ata/sata_sis.c
+++ b/drivers/ata/sata_sis.c
@@ -82,7 +82,7 @@ static struct pci_driver sis_pci_driver = {
 	.id_table		= sis_pci_tbl,
 	.probe			= sis_init_one,
 	.remove			= ata_pci_remove_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c
index f72e84228c5..47bf89464ce 100644
--- a/drivers/ata/sata_via.c
+++ b/drivers/ata/sata_via.c
@@ -103,7 +103,7 @@ static struct pci_driver svia_pci_driver = {
 	.name			= DRV_NAME,
 	.id_table		= svia_pci_tbl,
 	.probe			= svia_init_one,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.suspend		= ata_pci_device_suspend,
 	.resume			= ata_pci_device_resume,
 #endif
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c
index 204814e88e4..d4725fc0395 100644
--- a/drivers/atm/fore200e.c
+++ b/drivers/atm/fore200e.c
@@ -2780,7 +2780,7 @@ static struct pci_driver fore200e_pca_driver = {
 
 static int __init fore200e_module_init(void)
 {
-	int err;
+	int err = 0;
 
 	printk(FORE200E "FORE Systems 200E-series ATM driver - version " FORE200E_VERSION "\n");
 
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 1bdf104e90b..b621f56a36b 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -2551,12 +2551,12 @@ done:
 		timeout = 5 * 1000;
 		while (atomic_read(&vc->scq->used) > 0) {
 			timeout = msleep_interruptible(timeout);
-			if (!timeout)
+			if (!timeout) {
+				pr_warn("%s: SCQ drain timeout: %u used\n",
+					card->name, atomic_read(&vc->scq->used));
 				break;
+			}
 		}
-		if (!timeout)
-			printk("%s: SCQ drain timeout: %u used\n",
-			       card->name, atomic_read(&vc->scq->used));
 
 		writel(TCMDQ_HALT | vc->index, SAR_REG_TCMDQ);
 		clear_scd(card, vc->scq, vc->class);
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 83969f8c572..6467c919c50 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -176,14 +176,24 @@ static int __init cma_activate_area(struct cma *cma)
 		base_pfn = pfn;
 		for (j = pageblock_nr_pages; j; --j, pfn++) {
 			WARN_ON_ONCE(!pfn_valid(pfn));
+			/*
+			 * alloc_contig_range requires the pfn range
+			 * specified to be in the same zone. Make this
+			 * simple by forcing the entire CMA resv range
+			 * to be in the same zone.
+			 */
 			if (page_zone(pfn_to_page(pfn)) != zone)
-				return -EINVAL;
+				goto err;
 		}
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
 
 	mutex_init(&cma->lock);
 	return 0;
+
+err:
+	kfree(cma->bitmap);
+	return -EINVAL;
 }
 
 static struct cma cma_areas[MAX_CMA_AREAS];
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 9e9227e1762..00f2208949d 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -23,6 +23,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/idr.h>
 #include <linux/acpi.h>
+#include <linux/clk/clk-conf.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -89,8 +90,13 @@ int platform_get_irq(struct platform_device *dev, unsigned int num)
 	return dev->archdata.irqs[num];
 #else
 	struct resource *r;
-	if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node)
-		return of_irq_get(dev->dev.of_node, num);
+	if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) {
+		int ret;
+
+		ret = of_irq_get(dev->dev.of_node, num);
+		if (ret >= 0 || ret == -EPROBE_DEFER)
+			return ret;
+	}
 
 	r = platform_get_resource(dev, IORESOURCE_IRQ, num);
 
@@ -133,8 +139,13 @@ int platform_get_irq_byname(struct platform_device *dev, const char *name)
 {
 	struct resource *r;
 
-	if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node)
-		return of_irq_get_byname(dev->dev.of_node, name);
+	if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node) {
+		int ret;
+
+		ret = of_irq_get_byname(dev->dev.of_node, name);
+		if (ret >= 0 || ret == -EPROBE_DEFER)
+			return ret;
+	}
 
 	r = platform_get_resource_byname(dev, IORESOURCE_IRQ, name);
 	return r ? r->start : -ENXIO;
@@ -489,6 +500,10 @@ static int platform_drv_probe(struct device *_dev)
 	struct platform_device *dev = to_platform_device(_dev);
 	int ret;
 
+	ret = of_clk_set_defaults(_dev->of_node, false);
+	if (ret < 0)
+		return ret;
+
 	acpi_dev_pm_attach(_dev, true);
 
 	ret = drv->probe(dev);
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 343ffad5937..bf412961a93 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -214,9 +214,6 @@ static void initcall_debug_report(struct device *dev, ktime_t calltime,
 		pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev),
 			error, (unsigned long long)nsecs >> 10);
 	}
-
-	trace_device_pm_report_time(dev, info, nsecs, pm_verb(state.event),
-				    error);
 }
 
 /**
@@ -387,7 +384,9 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev,
 	calltime = initcall_debug_start(dev);
 
 	pm_dev_dbg(dev, state, info);
+	trace_device_pm_callback_start(dev, info, state.event);
 	error = cb(dev);
+	trace_device_pm_callback_end(dev, error);
 	suspend_report_result(cb, error);
 
 	initcall_debug_report(dev, calltime, error, state, info);
@@ -545,6 +544,7 @@ static void dpm_resume_noirq(pm_message_t state)
 	struct device *dev;
 	ktime_t starttime = ktime_get();
 
+	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, true);
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
@@ -587,6 +587,7 @@ static void dpm_resume_noirq(pm_message_t state)
 	dpm_show_time(starttime, state, "noirq");
 	resume_device_irqs();
 	cpuidle_resume();
+	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false);
 }
 
 /**
@@ -664,6 +665,7 @@ static void dpm_resume_early(pm_message_t state)
 	struct device *dev;
 	ktime_t starttime = ktime_get();
 
+	trace_suspend_resume(TPS("dpm_resume_early"), state.event, true);
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 
@@ -703,6 +705,7 @@ static void dpm_resume_early(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
 	dpm_show_time(starttime, state, "early");
+	trace_suspend_resume(TPS("dpm_resume_early"), state.event, false);
 }
 
 /**
@@ -834,6 +837,7 @@ void dpm_resume(pm_message_t state)
 	struct device *dev;
 	ktime_t starttime = ktime_get();
 
+	trace_suspend_resume(TPS("dpm_resume"), state.event, true);
 	might_sleep();
 
 	mutex_lock(&dpm_list_mtx);
@@ -875,6 +879,7 @@ void dpm_resume(pm_message_t state)
 	dpm_show_time(starttime, state, NULL);
 
 	cpufreq_resume();
+	trace_suspend_resume(TPS("dpm_resume"), state.event, false);
 }
 
 /**
@@ -913,7 +918,9 @@ static void device_complete(struct device *dev, pm_message_t state)
 
 	if (callback) {
 		pm_dev_dbg(dev, state, info);
+		trace_device_pm_callback_start(dev, info, state.event);
 		callback(dev);
+		trace_device_pm_callback_end(dev, 0);
 	}
 
 	device_unlock(dev);
@@ -932,6 +939,7 @@ void dpm_complete(pm_message_t state)
 {
 	struct list_head list;
 
+	trace_suspend_resume(TPS("dpm_complete"), state.event, true);
 	might_sleep();
 
 	INIT_LIST_HEAD(&list);
@@ -951,6 +959,7 @@ void dpm_complete(pm_message_t state)
 	}
 	list_splice(&list, &dpm_list);
 	mutex_unlock(&dpm_list_mtx);
+	trace_suspend_resume(TPS("dpm_complete"), state.event, false);
 }
 
 /**
@@ -1086,6 +1095,7 @@ static int dpm_suspend_noirq(pm_message_t state)
 	ktime_t starttime = ktime_get();
 	int error = 0;
 
+	trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, true);
 	cpuidle_pause();
 	suspend_device_irqs();
 	mutex_lock(&dpm_list_mtx);
@@ -1126,6 +1136,7 @@ static int dpm_suspend_noirq(pm_message_t state)
 	} else {
 		dpm_show_time(starttime, state, "noirq");
 	}
+	trace_suspend_resume(TPS("dpm_suspend_noirq"), state.event, false);
 	return error;
 }
 
@@ -1222,6 +1233,7 @@ static int dpm_suspend_late(pm_message_t state)
 	ktime_t starttime = ktime_get();
 	int error = 0;
 
+	trace_suspend_resume(TPS("dpm_suspend_late"), state.event, true);
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 	async_error = 0;
@@ -1257,6 +1269,7 @@ static int dpm_suspend_late(pm_message_t state)
 	} else {
 		dpm_show_time(starttime, state, "late");
 	}
+	trace_suspend_resume(TPS("dpm_suspend_late"), state.event, false);
 	return error;
 }
 
@@ -1295,7 +1308,9 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
 
 	calltime = initcall_debug_start(dev);
 
+	trace_device_pm_callback_start(dev, info, state.event);
 	error = cb(dev, state);
+	trace_device_pm_callback_end(dev, error);
 	suspend_report_result(cb, error);
 
 	initcall_debug_report(dev, calltime, error, state, info);
@@ -1461,6 +1476,7 @@ int dpm_suspend(pm_message_t state)
 	ktime_t starttime = ktime_get();
 	int error = 0;
 
+	trace_suspend_resume(TPS("dpm_suspend"), state.event, true);
 	might_sleep();
 
 	cpufreq_suspend();
@@ -1498,6 +1514,7 @@ int dpm_suspend(pm_message_t state)
 		dpm_save_failed_step(SUSPEND_SUSPEND);
 	} else
 		dpm_show_time(starttime, state, NULL);
+	trace_suspend_resume(TPS("dpm_suspend"), state.event, false);
 	return error;
 }
 
@@ -1549,8 +1566,11 @@ static int device_prepare(struct device *dev, pm_message_t state)
 		callback = dev->driver->pm->prepare;
 	}
 
-	if (callback)
+	if (callback) {
+		trace_device_pm_callback_start(dev, info, state.event);
 		ret = callback(dev);
+		trace_device_pm_callback_end(dev, ret);
+	}
 
 	device_unlock(dev);
 
@@ -1582,6 +1602,7 @@ int dpm_prepare(pm_message_t state)
 {
 	int error = 0;
 
+	trace_suspend_resume(TPS("dpm_prepare"), state.event, true);
 	might_sleep();
 
 	mutex_lock(&dpm_list_mtx);
@@ -1612,6 +1633,7 @@ int dpm_prepare(pm_message_t state)
 		put_device(dev);
 	}
 	mutex_unlock(&dpm_list_mtx);
+	trace_suspend_resume(TPS("dpm_prepare"), state.event, false);
 	return error;
 }
 
diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c
index e8d11b6630e..dbb8350ea8d 100644
--- a/drivers/base/syscore.c
+++ b/drivers/base/syscore.c
@@ -10,6 +10,7 @@
 #include <linux/mutex.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <trace/events/power.h>
 
 static LIST_HEAD(syscore_ops_list);
 static DEFINE_MUTEX(syscore_ops_lock);
@@ -49,6 +50,7 @@ int syscore_suspend(void)
 	struct syscore_ops *ops;
 	int ret = 0;
 
+	trace_suspend_resume(TPS("syscore_suspend"), 0, true);
 	pr_debug("Checking wakeup interrupts\n");
 
 	/* Return error code if there are any wakeup interrupts pending. */
@@ -70,6 +72,7 @@ int syscore_suspend(void)
 				"Interrupts enabled after %pF\n", ops->suspend);
 		}
 
+	trace_suspend_resume(TPS("syscore_suspend"), 0, false);
 	return 0;
 
  err_out:
@@ -92,6 +95,7 @@ void syscore_resume(void)
 {
 	struct syscore_ops *ops;
 
+	trace_suspend_resume(TPS("syscore_resume"), 0, true);
 	WARN_ONCE(!irqs_disabled(),
 		"Interrupts enabled before system core resume.\n");
 
@@ -103,6 +107,7 @@ void syscore_resume(void)
 			WARN_ONCE(!irqs_disabled(),
 				"Interrupts enabled after %pF\n", ops->resume);
 		}
+	trace_suspend_resume(TPS("syscore_resume"), 0, false);
 }
 EXPORT_SYMBOL_GPL(syscore_resume);
 #endif /* CONFIG_PM_SLEEP */
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 1b35c45c92b..3f2e1673808 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -544,6 +544,12 @@ void conn_try_outdate_peer_async(struct drbd_connection *connection)
 	struct task_struct *opa;
 
 	kref_get(&connection->kref);
+	/* We may just have force_sig()'ed this thread
+	 * to get it out of some blocking network function.
+	 * Clear signals; otherwise kthread_run(), which internally uses
+	 * wait_on_completion_killable(), will mistake our pending signal
+	 * for a new fatal signal and fail. */
+	flush_signals(current);
 	opa = kthread_run(_try_outdate_peer_async, connection, "drbd_async_h");
 	if (IS_ERR(opa)) {
 		drbd_err(connection, "out of mem, failed to invoke fence-peer helper\n");
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index b6c8aaf4931..5b17ec88ea0 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1337,8 +1337,11 @@ int drbd_submit_peer_request(struct drbd_device *device,
 		return 0;
 	}
 
+	/* Discards don't have any payload.
+	 * But the scsi layer still expects a bio_vec it can use internally,
+	 * see sd_setup_discard_cmnd() and blk_add_request_payload(). */
 	if (peer_req->flags & EE_IS_TRIM)
-		nr_pages = 0; /* discards don't have any payload. */
+		nr_pages = 1;
 
 	/* In most cases, we will only need one bio.  But in case the lower
 	 * level restrictions happen to be different at this offset on this
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 677db049f55..56d46ffb08e 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3777,7 +3777,7 @@ static void floppy_rb0_cb(struct bio *bio, int err)
 	int drive = cbdata->drive;
 
 	if (err) {
-		pr_info("floppy: error %d while reading block 0", err);
+		pr_info("floppy: error %d while reading block 0\n", err);
 		set_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
 	}
 	complete(&cbdata->complete);
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 74abd49fabd..295f3afbbef 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -39,6 +39,7 @@
 #include <../drivers/ata/ahci.h>
 #include <linux/export.h>
 #include <linux/debugfs.h>
+#include <linux/prefetch.h>
 #include "mtip32xx.h"
 
 #define HW_CMD_SLOT_SZ		(MTIP_MAX_COMMAND_SLOTS * 32)
@@ -2380,6 +2381,8 @@ static void mtip_hw_submit_io(struct driver_data *dd, struct request *rq,
 	/* Map the scatter list for DMA access */
 	nents = dma_map_sg(&dd->pdev->dev, command->sg, nents, dma_dir);
 
+	prefetch(&port->flags);
+
 	command->scatter_ents = nents;
 
 	/*
@@ -2392,7 +2395,7 @@ static void mtip_hw_submit_io(struct driver_data *dd, struct request *rq,
 	fis = command->command;
 	fis->type        = 0x27;
 	fis->opts        = 1 << 7;
-	if (rq_data_dir(rq) == READ)
+	if (dma_dir == DMA_FROM_DEVICE)
 		fis->command = ATA_CMD_FPDMA_READ;
 	else
 		fis->command = ATA_CMD_FPDMA_WRITE;
@@ -2412,7 +2415,7 @@ static void mtip_hw_submit_io(struct driver_data *dd, struct request *rq,
 	fis->res3        = 0;
 	fill_command_sg(dd, command, nents);
 
-	if (command->unaligned)
+	if (unlikely(command->unaligned))
 		fis->device |= 1 << 7;
 
 	/* Populate the command header */
@@ -2433,7 +2436,7 @@ static void mtip_hw_submit_io(struct driver_data *dd, struct request *rq,
 	 * To prevent this command from being issued
 	 * if an internal command is in progress or error handling is active.
 	 */
-	if (port->flags & MTIP_PF_PAUSE_IO) {
+	if (unlikely(port->flags & MTIP_PF_PAUSE_IO)) {
 		set_bit(rq->tag, port->cmds_to_issue);
 		set_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags);
 		return;
@@ -3754,7 +3757,7 @@ static bool mtip_check_unal_depth(struct blk_mq_hw_ctx *hctx,
 	struct driver_data *dd = hctx->queue->queuedata;
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
-	if (!dd->unal_qdepth || rq_data_dir(rq) == READ)
+	if (rq_data_dir(rq) == READ || !dd->unal_qdepth)
 		return false;
 
 	/*
@@ -3776,11 +3779,11 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
 	int ret;
 
-	if (mtip_check_unal_depth(hctx, rq))
+	if (unlikely(mtip_check_unal_depth(hctx, rq)))
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
 	ret = mtip_submit_request(hctx, rq);
-	if (!ret)
+	if (likely(!ret))
 		return BLK_MQ_RQ_QUEUE_OK;
 
 	rq->errors = ret;
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index 4b9b554234b..ba1b31ee22e 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -493,19 +493,19 @@ struct driver_data {
 
 	struct workqueue_struct *isr_workq;
 
-	struct mtip_work work[MTIP_MAX_SLOT_GROUPS];
-
 	atomic_t irq_workers_active;
 
+	struct mtip_work work[MTIP_MAX_SLOT_GROUPS];
+
 	int isr_binding;
 
 	struct block_device *bdev;
 
-	int unal_qdepth; /* qdepth of unaligned IO queue */
-
 	struct list_head online_list; /* linkage for online list */
 
 	struct list_head remove_list; /* linkage for removing list */
+
+	int unal_qdepth; /* qdepth of unaligned IO queue */
 };
 
 #endif
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 77087a29b12..a3b042c4d44 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -79,7 +79,7 @@ MODULE_PARM_DESC(home_node, "Home node for the device");
 
 static int queue_mode = NULL_Q_MQ;
 module_param(queue_mode, int, S_IRUGO);
-MODULE_PARM_DESC(use_mq, "Use blk-mq interface (0=bio,1=rq,2=multiqueue)");
+MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");
 
 static int gb = 250;
 module_param(gb, int, S_IRUGO);
@@ -227,7 +227,10 @@ static void null_cmd_end_timer(struct nullb_cmd *cmd)
 
 static void null_softirq_done_fn(struct request *rq)
 {
-	end_cmd(blk_mq_rq_to_pdu(rq));
+	if (queue_mode == NULL_Q_MQ)
+		end_cmd(blk_mq_rq_to_pdu(rq));
+	else
+		end_cmd(rq->special);
 }
 
 static inline void null_handle_cmd(struct nullb_cmd *cmd)
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index a842c71dcc2..02351e21716 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -10,10 +10,6 @@
  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #include <linux/nvme.h>
@@ -46,16 +42,26 @@
 #include <scsi/sg.h>
 #include <asm-generic/io-64-nonatomic-lo-hi.h>
 
-#define NVME_Q_DEPTH 1024
+#include <trace/events/block.h>
+
+#define NVME_Q_DEPTH		1024
 #define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
-#define ADMIN_TIMEOUT	(60 * HZ)
-#define IOD_TIMEOUT	(4 * NVME_IO_TIMEOUT)
+#define ADMIN_TIMEOUT		(admin_timeout * HZ)
+#define IOD_TIMEOUT		(retry_time * HZ)
+
+static unsigned char admin_timeout = 60;
+module_param(admin_timeout, byte, 0644);
+MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands");
 
-unsigned char io_timeout = 30;
-module_param(io_timeout, byte, 0644);
+unsigned char nvme_io_timeout = 30;
+module_param_named(io_timeout, nvme_io_timeout, byte, 0644);
 MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
 
+static unsigned char retry_time = 30;
+module_param(retry_time, byte, 0644);
+MODULE_PARM_DESC(retry_time, "time in seconds to retry failed I/O");
+
 static int nvme_major;
 module_param(nvme_major, int, 0);
 
@@ -67,6 +73,7 @@ static LIST_HEAD(dev_list);
 static struct task_struct *nvme_thread;
 static struct workqueue_struct *nvme_workq;
 static wait_queue_head_t nvme_kthread_wait;
+static struct notifier_block nvme_nb;
 
 static void nvme_reset_failed_dev(struct work_struct *ws);
 
@@ -199,16 +206,13 @@ static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
 #define CMD_CTX_CANCELLED	(0x30C + CMD_CTX_BASE)
 #define CMD_CTX_COMPLETED	(0x310 + CMD_CTX_BASE)
 #define CMD_CTX_INVALID		(0x314 + CMD_CTX_BASE)
-#define CMD_CTX_FLUSH		(0x318 + CMD_CTX_BASE)
-#define CMD_CTX_ABORT		(0x31C + CMD_CTX_BASE)
+#define CMD_CTX_ABORT		(0x318 + CMD_CTX_BASE)
 
 static void special_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	if (ctx == CMD_CTX_CANCELLED)
 		return;
-	if (ctx == CMD_CTX_FLUSH)
-		return;
 	if (ctx == CMD_CTX_ABORT) {
 		++nvmeq->dev->abort_limit;
 		return;
@@ -247,8 +251,9 @@ static void *free_cmdid(struct nvme_queue *nvmeq, int cmdid,
 	void *ctx;
 	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
 
-	if (cmdid >= nvmeq->q_depth) {
-		*fn = special_completion;
+	if (cmdid >= nvmeq->q_depth || !info[cmdid].fn) {
+		if (fn)
+			*fn = special_completion;
 		return CMD_CTX_INVALID;
 	}
 	if (fn)
@@ -281,9 +286,17 @@ static struct nvme_queue *raw_nvmeq(struct nvme_dev *dev, int qid)
 
 static struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU)
 {
+	struct nvme_queue *nvmeq;
 	unsigned queue_id = get_cpu_var(*dev->io_queue);
+
 	rcu_read_lock();
-	return rcu_dereference(dev->queues[queue_id]);
+	nvmeq = rcu_dereference(dev->queues[queue_id]);
+	if (nvmeq)
+		return nvmeq;
+
+	rcu_read_unlock();
+	put_cpu_var(*dev->io_queue);
+	return NULL;
 }
 
 static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
@@ -295,8 +308,15 @@ static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
 static struct nvme_queue *lock_nvmeq(struct nvme_dev *dev, int q_idx)
 							__acquires(RCU)
 {
+	struct nvme_queue *nvmeq;
+
 	rcu_read_lock();
-	return rcu_dereference(dev->queues[q_idx]);
+	nvmeq = rcu_dereference(dev->queues[q_idx]);
+	if (nvmeq)
+		return nvmeq;
+
+	rcu_read_unlock();
+	return NULL;
 }
 
 static void unlock_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
@@ -387,25 +407,30 @@ void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
 static void nvme_start_io_acct(struct bio *bio)
 {
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	const int rw = bio_data_dir(bio);
-	int cpu = part_stat_lock();
-	part_round_stats(cpu, &disk->part0);
-	part_stat_inc(cpu, &disk->part0, ios[rw]);
-	part_stat_add(cpu, &disk->part0, sectors[rw], bio_sectors(bio));
-	part_inc_in_flight(&disk->part0, rw);
-	part_stat_unlock();
+	if (blk_queue_io_stat(disk->queue)) {
+		const int rw = bio_data_dir(bio);
+		int cpu = part_stat_lock();
+		part_round_stats(cpu, &disk->part0);
+		part_stat_inc(cpu, &disk->part0, ios[rw]);
+		part_stat_add(cpu, &disk->part0, sectors[rw],
+							bio_sectors(bio));
+		part_inc_in_flight(&disk->part0, rw);
+		part_stat_unlock();
+	}
 }
 
 static void nvme_end_io_acct(struct bio *bio, unsigned long start_time)
 {
 	struct gendisk *disk = bio->bi_bdev->bd_disk;
-	const int rw = bio_data_dir(bio);
-	unsigned long duration = jiffies - start_time;
-	int cpu = part_stat_lock();
-	part_stat_add(cpu, &disk->part0, ticks[rw], duration);
-	part_round_stats(cpu, &disk->part0);
-	part_dec_in_flight(&disk->part0, rw);
-	part_stat_unlock();
+	if (blk_queue_io_stat(disk->queue)) {
+		const int rw = bio_data_dir(bio);
+		unsigned long duration = jiffies - start_time;
+		int cpu = part_stat_lock();
+		part_stat_add(cpu, &disk->part0, ticks[rw], duration);
+		part_round_stats(cpu, &disk->part0);
+		part_dec_in_flight(&disk->part0, rw);
+		part_stat_unlock();
+	}
 }
 
 static void bio_completion(struct nvme_queue *nvmeq, void *ctx,
@@ -414,6 +439,7 @@ static void bio_completion(struct nvme_queue *nvmeq, void *ctx,
 	struct nvme_iod *iod = ctx;
 	struct bio *bio = iod->private;
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
+	int error = 0;
 
 	if (unlikely(status)) {
 		if (!(status & NVME_SC_DNR ||
@@ -426,6 +452,7 @@ static void bio_completion(struct nvme_queue *nvmeq, void *ctx,
 			wake_up(&nvmeq->sq_full);
 			return;
 		}
+		error = -EIO;
 	}
 	if (iod->nents) {
 		dma_unmap_sg(nvmeq->q_dmadev, iod->sg, iod->nents,
@@ -433,10 +460,9 @@ static void bio_completion(struct nvme_queue *nvmeq, void *ctx,
 		nvme_end_io_acct(bio, iod->start_time);
 	}
 	nvme_free_iod(nvmeq->dev, iod);
-	if (status)
-		bio_endio(bio, -EIO);
-	else
-		bio_endio(bio, 0);
+
+	trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio, error);
+	bio_endio(bio, error);
 }
 
 /* length is in bytes.  gfp flags indicates whether we may sleep. */
@@ -525,6 +551,8 @@ static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq,
 	if (!split)
 		return -ENOMEM;
 
+	trace_block_split(bdev_get_queue(bio->bi_bdev), bio,
+					split->bi_iter.bi_sector);
 	bio_chain(split, bio);
 
 	if (!waitqueue_active(&nvmeq->sq_full))
@@ -627,16 +655,6 @@ static int nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	return 0;
 }
 
-int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns)
-{
-	int cmdid = alloc_cmdid(nvmeq, (void *)CMD_CTX_FLUSH,
-					special_completion, NVME_IO_TIMEOUT);
-	if (unlikely(cmdid < 0))
-		return cmdid;
-
-	return nvme_submit_flush(nvmeq, ns, cmdid);
-}
-
 static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
 {
 	struct bio *bio = iod->private;
@@ -652,7 +670,7 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
 
 	if (bio->bi_rw & REQ_DISCARD)
 		return nvme_submit_discard(nvmeq, ns, bio, iod, cmdid);
-	if ((bio->bi_rw & REQ_FLUSH) && !iod->nents)
+	if (bio->bi_rw & REQ_FLUSH)
 		return nvme_submit_flush(nvmeq, ns, cmdid);
 
 	control = 0;
@@ -686,6 +704,26 @@ static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
 	return 0;
 }
 
+static int nvme_split_flush_data(struct nvme_queue *nvmeq, struct bio *bio)
+{
+	struct bio *split = bio_clone(bio, GFP_ATOMIC);
+	if (!split)
+		return -ENOMEM;
+
+	split->bi_iter.bi_size = 0;
+	split->bi_phys_segments = 0;
+	bio->bi_rw &= ~REQ_FLUSH;
+	bio_chain(split, bio);
+
+	if (!waitqueue_active(&nvmeq->sq_full))
+		add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
+	bio_list_add(&nvmeq->sq_cong, split);
+	bio_list_add(&nvmeq->sq_cong, bio);
+	wake_up_process(nvme_thread);
+
+	return 0;
+}
+
 /*
  * Called with local interrupts disabled and the q_lock held.  May not sleep.
  */
@@ -696,11 +734,8 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 	int psegs = bio_phys_segments(ns->queue, bio);
 	int result;
 
-	if ((bio->bi_rw & REQ_FLUSH) && psegs) {
-		result = nvme_submit_flush_data(nvmeq, ns);
-		if (result)
-			return result;
-	}
+	if ((bio->bi_rw & REQ_FLUSH) && psegs)
+		return nvme_split_flush_data(nvmeq, bio);
 
 	iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC);
 	if (!iod)
@@ -795,7 +830,6 @@ static void nvme_make_request(struct request_queue *q, struct bio *bio)
 	int result = -EBUSY;
 
 	if (!nvmeq) {
-		put_nvmeq(NULL);
 		bio_endio(bio, -EIO);
 		return;
 	}
@@ -870,10 +904,8 @@ static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx,
 	struct nvme_queue *nvmeq;
 
 	nvmeq = lock_nvmeq(dev, q_idx);
-	if (!nvmeq) {
-		unlock_nvmeq(nvmeq);
+	if (!nvmeq)
 		return -ENODEV;
-	}
 
 	cmdinfo.task = current;
 	cmdinfo.status = -EINTR;
@@ -898,9 +930,10 @@ static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx,
 
 	if (cmdinfo.status == -EINTR) {
 		nvmeq = lock_nvmeq(dev, q_idx);
-		if (nvmeq)
+		if (nvmeq) {
 			nvme_abort_command(nvmeq, cmdid);
-		unlock_nvmeq(nvmeq);
+			unlock_nvmeq(nvmeq);
+		}
 		return -EINTR;
 	}
 
@@ -1358,7 +1391,8 @@ static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled)
 			return -EINTR;
 		if (time_after(jiffies, timeout)) {
 			dev_err(&dev->pci_dev->dev,
-				"Device not ready; aborting initialisation\n");
+				"Device not ready; aborting %s\n", enabled ?
+						"initialisation" : "reset");
 			return -ENODEV;
 		}
 	}
@@ -1481,7 +1515,11 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 		goto put_pages;
 	}
 
+	err = -ENOMEM;
 	iod = nvme_alloc_iod(count, length, GFP_KERNEL);
+	if (!iod)
+		goto put_pages;
+
 	sg = iod->sg;
 	sg_init_table(sg, count);
 	for (i = 0; i < count; i++) {
@@ -1494,7 +1532,6 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 	sg_mark_end(&sg[i - 1]);
 	iod->nents = count;
 
-	err = -ENOMEM;
 	nents = dma_map_sg(&dev->pci_dev->dev, sg, count,
 				write ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 	if (!nents)
@@ -1894,6 +1931,8 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 	blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
 	if (dev->max_hw_sectors)
 		blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
+	if (dev->vwc & NVME_CTRL_VWC_PRESENT)
+		blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
 
 	disk->major = nvme_major;
 	disk->first_minor = 0;
@@ -2062,8 +2101,13 @@ static int set_queue_count(struct nvme_dev *dev, int count)
 
 	status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, q_count, 0,
 								&result);
-	if (status)
-		return status < 0 ? -EIO : -EBUSY;
+	if (status < 0)
+		return status;
+	if (status > 0) {
+		dev_err(&dev->pci_dev->dev, "Could not set queue count (%d)\n",
+									status);
+		return -EBUSY;
+	}
 	return min(result & 0xffff, result >> 16) + 1;
 }
 
@@ -2072,14 +2116,25 @@ static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
 	return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
 }
 
+static void nvme_cpu_workfn(struct work_struct *work)
+{
+	struct nvme_dev *dev = container_of(work, struct nvme_dev, cpu_work);
+	if (dev->initialized)
+		nvme_assign_io_queues(dev);
+}
+
 static int nvme_cpu_notify(struct notifier_block *self,
 				unsigned long action, void *hcpu)
 {
-	struct nvme_dev *dev = container_of(self, struct nvme_dev, nb);
+	struct nvme_dev *dev;
+
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_DEAD:
-		nvme_assign_io_queues(dev);
+		spin_lock(&dev_list_lock);
+		list_for_each_entry(dev, &dev_list, node)
+			schedule_work(&dev->cpu_work);
+		spin_unlock(&dev_list_lock);
 		break;
 	}
 	return NOTIFY_OK;
@@ -2148,11 +2203,6 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	nvme_free_queues(dev, nr_io_queues + 1);
 	nvme_assign_io_queues(dev);
 
-	dev->nb.notifier_call = &nvme_cpu_notify;
-	result = register_hotcpu_notifier(&dev->nb);
-	if (result)
-		goto free_queues;
-
 	return 0;
 
  free_queues:
@@ -2184,6 +2234,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 
 	res = nvme_identify(dev, 0, 1, dma_addr);
 	if (res) {
+		dev_err(&pdev->dev, "Identify Controller failed (%d)\n", res);
 		res = -EIO;
 		goto out;
 	}
@@ -2192,6 +2243,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	nn = le32_to_cpup(&ctrl->nn);
 	dev->oncs = le16_to_cpup(&ctrl->oncs);
 	dev->abort_limit = ctrl->acl + 1;
+	dev->vwc = ctrl->vwc;
 	memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
 	memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
 	memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
@@ -2450,8 +2502,6 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 	int i;
 
 	dev->initialized = 0;
-	unregister_hotcpu_notifier(&dev->nb);
-
 	nvme_dev_list_remove(dev);
 
 	if (!dev->bar || (dev->bar && readl(&dev->bar->csts) == -1)) {
@@ -2722,6 +2772,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&dev->namespaces);
 	dev->reset_workfn = nvme_reset_failed_dev;
 	INIT_WORK(&dev->reset_work, nvme_reset_workfn);
+	INIT_WORK(&dev->cpu_work, nvme_cpu_workfn);
 	dev->pci_dev = pdev;
 	pci_set_drvdata(pdev, dev);
 	result = nvme_set_instance(dev);
@@ -2801,6 +2852,7 @@ static void nvme_remove(struct pci_dev *pdev)
 
 	pci_set_drvdata(pdev, NULL);
 	flush_work(&dev->reset_work);
+	flush_work(&dev->cpu_work);
 	misc_deregister(&dev->miscdev);
 	nvme_dev_remove(dev);
 	nvme_dev_shutdown(dev);
@@ -2889,11 +2941,18 @@ static int __init nvme_init(void)
 	else if (result > 0)
 		nvme_major = result;
 
-	result = pci_register_driver(&nvme_driver);
+	nvme_nb.notifier_call = &nvme_cpu_notify;
+	result = register_hotcpu_notifier(&nvme_nb);
 	if (result)
 		goto unregister_blkdev;
+
+	result = pci_register_driver(&nvme_driver);
+	if (result)
+		goto unregister_hotcpu;
 	return 0;
 
+ unregister_hotcpu:
+	unregister_hotcpu_notifier(&nvme_nb);
  unregister_blkdev:
 	unregister_blkdev(nvme_major, "nvme");
  kill_workq:
@@ -2904,9 +2963,11 @@ static int __init nvme_init(void)
 static void __exit nvme_exit(void)
 {
 	pci_unregister_driver(&nvme_driver);
+	unregister_hotcpu_notifier(&nvme_nb);
 	unregister_blkdev(nvme_major, "nvme");
 	destroy_workqueue(nvme_workq);
 	BUG_ON(nvme_thread && !IS_ERR(nvme_thread));
+	_nvme_check_size();
 }
 
 MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 2c3f5be06da..a4cd6d691c6 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -1,6 +1,6 @@
 /*
  * NVM Express device driver
- * Copyright (c) 2011, Intel Corporation.
+ * Copyright (c) 2011-2014, Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -10,10 +10,6 @@
  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 /*
@@ -243,8 +239,6 @@ static int sg_version_num = 30534;	/* 2 digits for each component */
 #define READ_CAP_16_RESP_SIZE				32
 
 /* NVMe Namespace and Command Defines */
-#define NVME_GET_SMART_LOG_PAGE				0x02
-#define NVME_GET_FEAT_TEMP_THRESH			0x04
 #define BYTES_TO_DWORDS					4
 #define NVME_MAX_FIRMWARE_SLOT				7
 
@@ -686,6 +680,7 @@ static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns,
 	u8 resp_data_format = 0x02;
 	u8 protect;
 	u8 cmdque = 0x01 << 1;
+	u8 fw_offset = sizeof(dev->firmware_rev);
 
 	mem = dma_alloc_coherent(&dev->pci_dev->dev, sizeof(struct nvme_id_ns),
 				&dma_addr, GFP_KERNEL);
@@ -721,7 +716,11 @@ static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns,
 	inq_response[7] = cmdque;	/* wbus16=0 | sync=0 | vs=0 */
 	strncpy(&inq_response[8], "NVMe    ", 8);
 	strncpy(&inq_response[16], dev->model, 16);
-	strncpy(&inq_response[32], dev->firmware_rev, 4);
+
+	while (dev->firmware_rev[fw_offset - 1] == ' ' && fw_offset > 4)
+		fw_offset--;
+	fw_offset -= 4;
+	strncpy(&inq_response[32], dev->firmware_rev + fw_offset, 4);
 
 	xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
 	res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
@@ -1018,8 +1017,8 @@ static int nvme_trans_log_info_exceptions(struct nvme_ns *ns,
 	c.common.opcode = nvme_admin_get_log_page;
 	c.common.nsid = cpu_to_le32(0xFFFFFFFF);
 	c.common.prp1 = cpu_to_le64(dma_addr);
-	c.common.cdw10[0] = cpu_to_le32(((sizeof(struct nvme_smart_log) /
-			BYTES_TO_DWORDS) << 16) | NVME_GET_SMART_LOG_PAGE);
+	c.common.cdw10[0] = cpu_to_le32((((sizeof(struct nvme_smart_log) /
+			BYTES_TO_DWORDS) - 1) << 16) | NVME_LOG_SMART);
 	res = nvme_submit_admin_cmd(dev, &c, NULL);
 	if (res != NVME_SC_SUCCESS) {
 		temp_c = LOG_TEMP_UNKNOWN;
@@ -1086,8 +1085,8 @@ static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	c.common.opcode = nvme_admin_get_log_page;
 	c.common.nsid = cpu_to_le32(0xFFFFFFFF);
 	c.common.prp1 = cpu_to_le64(dma_addr);
-	c.common.cdw10[0] = cpu_to_le32(((sizeof(struct nvme_smart_log) /
-			BYTES_TO_DWORDS) << 16) | NVME_GET_SMART_LOG_PAGE);
+	c.common.cdw10[0] = cpu_to_le32((((sizeof(struct nvme_smart_log) /
+			BYTES_TO_DWORDS) - 1) << 16) | NVME_LOG_SMART);
 	res = nvme_submit_admin_cmd(dev, &c, NULL);
 	if (res != NVME_SC_SUCCESS) {
 		temp_c_cur = LOG_TEMP_UNKNOWN;
@@ -1477,7 +1476,7 @@ static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		goto out_dma;
 	}
 	id_ctrl = mem;
-	lowest_pow_st = id_ctrl->npss - 1;
+	lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1));
 
 	switch (pc) {
 	case NVME_POWER_STATE_START_VALID:
@@ -1494,20 +1493,19 @@ static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 		break;
 	case NVME_POWER_STATE_IDLE:
 		/* Action unspecified if POWER CONDITION MODIFIER != [0,1,2] */
-		/* min of desired state and (lps-1) because lps is STOP */
 		if (pcmod == 0x0)
-			ps_desired = min(POWER_STATE_1, (lowest_pow_st - 1));
+			ps_desired = POWER_STATE_1;
 		else if (pcmod == 0x1)
-			ps_desired = min(POWER_STATE_2, (lowest_pow_st - 1));
+			ps_desired = POWER_STATE_2;
 		else if (pcmod == 0x2)
-			ps_desired = min(POWER_STATE_3, (lowest_pow_st - 1));
+			ps_desired = POWER_STATE_3;
 		break;
 	case NVME_POWER_STATE_STANDBY:
 		/* Action unspecified if POWER CONDITION MODIFIER != [0,1] */
 		if (pcmod == 0x0)
-			ps_desired = max(0, (lowest_pow_st - 2));
+			ps_desired = max(POWER_STATE_0, (lowest_pow_st - 2));
 		else if (pcmod == 0x1)
-			ps_desired = max(0, (lowest_pow_st - 1));
+			ps_desired = max(POWER_STATE_0, (lowest_pow_st - 1));
 		break;
 	case NVME_POWER_STATE_LU_CONTROL:
 	default:
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index ef166ad2dba..758ac442c5b 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -704,6 +704,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 
 	rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
 			     WRITE : READ, __GFP_WAIT);
+	blk_rq_set_block_pc(rq);
 
 	if (cgc->buflen) {
 		ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
@@ -716,7 +717,6 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 	memcpy(rq->cmd, cgc->cmd, CDROM_PACKET_SIZE);
 
 	rq->timeout = 60*HZ;
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	if (cgc->quiet)
 		rq->cmd_flags |= REQ_QUIET;
 
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 4c95b503b09..b2c98c1bc03 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -541,7 +541,6 @@ static int rbd_open(struct block_device *bdev, fmode_t mode)
 		return -ENOENT;
 
 	(void) get_device(&rbd_dev->dev);
-	set_device_ro(bdev, rbd_dev->mapping.read_only);
 
 	return 0;
 }
@@ -559,10 +558,76 @@ static void rbd_release(struct gendisk *disk, fmode_t mode)
 	put_device(&rbd_dev->dev);
 }
 
+static int rbd_ioctl_set_ro(struct rbd_device *rbd_dev, unsigned long arg)
+{
+	int ret = 0;
+	int val;
+	bool ro;
+	bool ro_changed = false;
+
+	/* get_user() may sleep, so call it before taking rbd_dev->lock */
+	if (get_user(val, (int __user *)(arg)))
+		return -EFAULT;
+
+	ro = val ? true : false;
+	/* Snapshot doesn't allow to write*/
+	if (rbd_dev->spec->snap_id != CEPH_NOSNAP && !ro)
+		return -EROFS;
+
+	spin_lock_irq(&rbd_dev->lock);
+	/* prevent others open this device */
+	if (rbd_dev->open_count > 1) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (rbd_dev->mapping.read_only != ro) {
+		rbd_dev->mapping.read_only = ro;
+		ro_changed = true;
+	}
+
+out:
+	spin_unlock_irq(&rbd_dev->lock);
+	/* set_disk_ro() may sleep, so call it after releasing rbd_dev->lock */
+	if (ret == 0 && ro_changed)
+		set_disk_ro(rbd_dev->disk, ro ? 1 : 0);
+
+	return ret;
+}
+
+static int rbd_ioctl(struct block_device *bdev, fmode_t mode,
+			unsigned int cmd, unsigned long arg)
+{
+	struct rbd_device *rbd_dev = bdev->bd_disk->private_data;
+	int ret = 0;
+
+	switch (cmd) {
+	case BLKROSET:
+		ret = rbd_ioctl_set_ro(rbd_dev, arg);
+		break;
+	default:
+		ret = -ENOTTY;
+	}
+
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static int rbd_compat_ioctl(struct block_device *bdev, fmode_t mode,
+				unsigned int cmd, unsigned long arg)
+{
+	return rbd_ioctl(bdev, mode, cmd, arg);
+}
+#endif /* CONFIG_COMPAT */
+
 static const struct block_device_operations rbd_bd_ops = {
 	.owner			= THIS_MODULE,
 	.open			= rbd_open,
 	.release		= rbd_release,
+	.ioctl			= rbd_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= rbd_compat_ioctl,
+#endif
 };
 
 /*
@@ -1366,6 +1431,14 @@ static bool obj_request_exists_test(struct rbd_obj_request *obj_request)
 	return test_bit(OBJ_REQ_EXISTS, &obj_request->flags) != 0;
 }
 
+static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request)
+{
+	struct rbd_device *rbd_dev = obj_request->img_request->rbd_dev;
+
+	return obj_request->img_offset <
+	    round_up(rbd_dev->parent_overlap, rbd_obj_bytes(&rbd_dev->header));
+}
+
 static void rbd_obj_request_get(struct rbd_obj_request *obj_request)
 {
 	dout("%s: obj %p (was %d)\n", __func__, obj_request,
@@ -1382,6 +1455,13 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request)
 	kref_put(&obj_request->kref, rbd_obj_request_destroy);
 }
 
+static void rbd_img_request_get(struct rbd_img_request *img_request)
+{
+	dout("%s: img %p (was %d)\n", __func__, img_request,
+	     atomic_read(&img_request->kref.refcount));
+	kref_get(&img_request->kref);
+}
+
 static bool img_request_child_test(struct rbd_img_request *img_request);
 static void rbd_parent_request_destroy(struct kref *kref);
 static void rbd_img_request_destroy(struct kref *kref);
@@ -2142,6 +2222,7 @@ static void rbd_img_obj_callback(struct rbd_obj_request *obj_request)
 	img_request->next_completion = which;
 out:
 	spin_unlock_irq(&img_request->completion_lock);
+	rbd_img_request_put(img_request);
 
 	if (!more)
 		rbd_img_request_complete(img_request);
@@ -2242,6 +2323,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
 			goto out_unwind;
 		obj_request->osd_req = osd_req;
 		obj_request->callback = rbd_img_obj_callback;
+		rbd_img_request_get(img_request);
 
 		if (write_request) {
 			osd_req_op_alloc_hint_init(osd_req, which,
@@ -2674,7 +2756,7 @@ static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request)
 	 */
 	if (!img_request_write_test(img_request) ||
 		!img_request_layered_test(img_request) ||
-		rbd_dev->parent_overlap <= obj_request->img_offset ||
+		!obj_request_overlaps_parent(obj_request) ||
 		((known = obj_request_known_test(obj_request)) &&
 			obj_request_exists_test(obj_request))) {
 
@@ -2872,56 +2954,55 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data)
 }
 
 /*
- * Request sync osd watch/unwatch.  The value of "start" determines
- * whether a watch request is being initiated or torn down.
+ * Initiate a watch request, synchronously.
  */
-static int __rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, bool start)
+static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev)
 {
 	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
 	struct rbd_obj_request *obj_request;
 	int ret;
 
-	rbd_assert(start ^ !!rbd_dev->watch_event);
-	rbd_assert(start ^ !!rbd_dev->watch_request);
+	rbd_assert(!rbd_dev->watch_event);
+	rbd_assert(!rbd_dev->watch_request);
 
-	if (start) {
-		ret = ceph_osdc_create_event(osdc, rbd_watch_cb, rbd_dev,
-						&rbd_dev->watch_event);
-		if (ret < 0)
-			return ret;
-		rbd_assert(rbd_dev->watch_event != NULL);
-	}
+	ret = ceph_osdc_create_event(osdc, rbd_watch_cb, rbd_dev,
+				     &rbd_dev->watch_event);
+	if (ret < 0)
+		return ret;
+
+	rbd_assert(rbd_dev->watch_event);
 
-	ret = -ENOMEM;
 	obj_request = rbd_obj_request_create(rbd_dev->header_name, 0, 0,
-							OBJ_REQUEST_NODATA);
-	if (!obj_request)
+					     OBJ_REQUEST_NODATA);
+	if (!obj_request) {
+		ret = -ENOMEM;
 		goto out_cancel;
+	}
 
 	obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, 1,
 						  obj_request);
-	if (!obj_request->osd_req)
-		goto out_cancel;
+	if (!obj_request->osd_req) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
 
-	if (start)
-		ceph_osdc_set_request_linger(osdc, obj_request->osd_req);
-	else
-		ceph_osdc_unregister_linger_request(osdc,
-					rbd_dev->watch_request->osd_req);
+	ceph_osdc_set_request_linger(osdc, obj_request->osd_req);
 
 	osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_WATCH,
-				rbd_dev->watch_event->cookie, 0, start ? 1 : 0);
+			      rbd_dev->watch_event->cookie, 0, 1);
 	rbd_osd_req_format_write(obj_request);
 
 	ret = rbd_obj_request_submit(osdc, obj_request);
 	if (ret)
-		goto out_cancel;
+		goto out_linger;
+
 	ret = rbd_obj_request_wait(obj_request);
 	if (ret)
-		goto out_cancel;
+		goto out_linger;
+
 	ret = obj_request->result;
 	if (ret)
-		goto out_cancel;
+		goto out_linger;
 
 	/*
 	 * A watch request is set to linger, so the underlying osd
@@ -2931,36 +3012,84 @@ static int __rbd_dev_header_watch_sync(struct rbd_device *rbd_dev, bool start)
 	 * it.  We'll drop that reference (below) after we've
 	 * unregistered it.
 	 */
-	if (start) {
-		rbd_dev->watch_request = obj_request;
+	rbd_dev->watch_request = obj_request;
 
-		return 0;
+	return 0;
+
+out_linger:
+	ceph_osdc_unregister_linger_request(osdc, obj_request->osd_req);
+out_put:
+	rbd_obj_request_put(obj_request);
+out_cancel:
+	ceph_osdc_cancel_event(rbd_dev->watch_event);
+	rbd_dev->watch_event = NULL;
+
+	return ret;
+}
+
+/*
+ * Tear down a watch request, synchronously.
+ */
+static int __rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev)
+{
+	struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
+	struct rbd_obj_request *obj_request;
+	int ret;
+
+	rbd_assert(rbd_dev->watch_event);
+	rbd_assert(rbd_dev->watch_request);
+
+	obj_request = rbd_obj_request_create(rbd_dev->header_name, 0, 0,
+					     OBJ_REQUEST_NODATA);
+	if (!obj_request) {
+		ret = -ENOMEM;
+		goto out_cancel;
+	}
+
+	obj_request->osd_req = rbd_osd_req_create(rbd_dev, true, 1,
+						  obj_request);
+	if (!obj_request->osd_req) {
+		ret = -ENOMEM;
+		goto out_put;
 	}
 
+	osd_req_op_watch_init(obj_request->osd_req, 0, CEPH_OSD_OP_WATCH,
+			      rbd_dev->watch_event->cookie, 0, 0);
+	rbd_osd_req_format_write(obj_request);
+
+	ret = rbd_obj_request_submit(osdc, obj_request);
+	if (ret)
+		goto out_put;
+
+	ret = rbd_obj_request_wait(obj_request);
+	if (ret)
+		goto out_put;
+
+	ret = obj_request->result;
+	if (ret)
+		goto out_put;
+
 	/* We have successfully torn down the watch request */
 
+	ceph_osdc_unregister_linger_request(osdc,
+					    rbd_dev->watch_request->osd_req);
 	rbd_obj_request_put(rbd_dev->watch_request);
 	rbd_dev->watch_request = NULL;
+
+out_put:
+	rbd_obj_request_put(obj_request);
 out_cancel:
-	/* Cancel the event if we're tearing down, or on error */
 	ceph_osdc_cancel_event(rbd_dev->watch_event);
 	rbd_dev->watch_event = NULL;
-	if (obj_request)
-		rbd_obj_request_put(obj_request);
 
 	return ret;
 }
 
-static int rbd_dev_header_watch_sync(struct rbd_device *rbd_dev)
-{
-	return __rbd_dev_header_watch_sync(rbd_dev, true);
-}
-
 static void rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev)
 {
 	int ret;
 
-	ret = __rbd_dev_header_watch_sync(rbd_dev, false);
+	ret = __rbd_dev_header_unwatch_sync(rbd_dev);
 	if (ret) {
 		rbd_warn(rbd_dev, "unable to tear down watch request: %d\n",
 			 ret);
@@ -3058,7 +3187,6 @@ static void rbd_request_fn(struct request_queue *q)
 		__releases(q->queue_lock) __acquires(q->queue_lock)
 {
 	struct rbd_device *rbd_dev = q->queuedata;
-	bool read_only = rbd_dev->mapping.read_only;
 	struct request *rq;
 	int result;
 
@@ -3094,7 +3222,7 @@ static void rbd_request_fn(struct request_queue *q)
 
 		if (write_request) {
 			result = -EROFS;
-			if (read_only)
+			if (rbd_dev->mapping.read_only)
 				goto end_request;
 			rbd_assert(rbd_dev->spec->snap_id == CEPH_NOSNAP);
 		}
@@ -4683,6 +4811,38 @@ out_err:
 }
 
 /*
+ * Return pool id (>= 0) or a negative error code.
+ */
+static int rbd_add_get_pool_id(struct rbd_client *rbdc, const char *pool_name)
+{
+	u64 newest_epoch;
+	unsigned long timeout = rbdc->client->options->mount_timeout * HZ;
+	int tries = 0;
+	int ret;
+
+again:
+	ret = ceph_pg_poolid_by_name(rbdc->client->osdc.osdmap, pool_name);
+	if (ret == -ENOENT && tries++ < 1) {
+		ret = ceph_monc_do_get_version(&rbdc->client->monc, "osdmap",
+					       &newest_epoch);
+		if (ret < 0)
+			return ret;
+
+		if (rbdc->client->osdc.osdmap->epoch < newest_epoch) {
+			ceph_monc_request_next_osdmap(&rbdc->client->monc);
+			(void) ceph_monc_wait_osdmap(&rbdc->client->monc,
+						     newest_epoch, timeout);
+			goto again;
+		} else {
+			/* the osdmap we have is new enough */
+			return -ENOENT;
+		}
+	}
+
+	return ret;
+}
+
+/*
  * An rbd format 2 image has a unique identifier, distinct from the
  * name given to it by the user.  Internally, that identifier is
  * what's used to specify the names of objects related to the image.
@@ -4752,7 +4912,7 @@ static int rbd_dev_image_id(struct rbd_device *rbd_dev)
 
 		image_id = ceph_extract_encoded_string(&p, p + ret,
 						NULL, GFP_NOIO);
-		ret = IS_ERR(image_id) ? PTR_ERR(image_id) : 0;
+		ret = PTR_ERR_OR_ZERO(image_id);
 		if (!ret)
 			rbd_dev->image_format = 2;
 	} else {
@@ -4907,6 +5067,7 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
 	if (ret)
 		goto err_out_disk;
 	set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
+	set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only);
 
 	ret = rbd_bus_add_dev(rbd_dev);
 	if (ret)
@@ -5053,7 +5214,6 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	struct rbd_options *rbd_opts = NULL;
 	struct rbd_spec *spec = NULL;
 	struct rbd_client *rbdc;
-	struct ceph_osd_client *osdc;
 	bool read_only;
 	int rc = -ENOMEM;
 
@@ -5075,8 +5235,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
 	}
 
 	/* pick the pool */
-	osdc = &rbdc->client->osdc;
-	rc = ceph_pg_poolid_by_name(osdc->osdmap, spec->pool_name);
+	rc = rbd_add_get_pool_id(rbdc, spec->pool_name);
 	if (rc < 0)
 		goto err_out_client;
 	spec->pool_id = (u64)rc;
@@ -5387,6 +5546,7 @@ err_out_slab:
 
 static void __exit rbd_exit(void)
 {
+	ida_destroy(&rbd_dev_id_ida);
 	rbd_sysfs_cleanup();
 	if (single_major)
 		unregister_blkdev(rbd_major, RBD_DRV_NAME);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 48eccb35018..36e54be402d 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -624,7 +624,16 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 	zram->disksize = 0;
 	if (reset_capacity)
 		set_capacity(zram->disk, 0);
+
 	up_write(&zram->init_lock);
+
+	/*
+	 * Revalidate disk out of the init_lock to avoid lockdep splat.
+	 * It's okay because disk's capacity is protected by init_lock
+	 * so that revalidate_disk always sees up-to-date capacity.
+	 */
+	if (reset_capacity)
+		revalidate_disk(zram->disk);
 }
 
 static ssize_t disksize_store(struct device *dev,
@@ -665,6 +674,14 @@ static ssize_t disksize_store(struct device *dev,
 	zram->disksize = disksize;
 	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);
 	up_write(&zram->init_lock);
+
+	/*
+	 * Revalidate disk out of the init_lock to avoid lockdep splat.
+	 * It's okay because disk's capacity is protected by init_lock
+	 * so that revalidate_disk always sees up-to-date capacity.
+	 */
+	revalidate_disk(zram->disk);
+
 	return len;
 
 out_destroy_comp:
diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index a83b57e57b6..f50dffc0374 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -90,7 +90,6 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x0b05, 0x17d0) },
 	{ USB_DEVICE(0x0CF3, 0x0036) },
 	{ USB_DEVICE(0x0CF3, 0x3004) },
-	{ USB_DEVICE(0x0CF3, 0x3005) },
 	{ USB_DEVICE(0x0CF3, 0x3008) },
 	{ USB_DEVICE(0x0CF3, 0x311D) },
 	{ USB_DEVICE(0x0CF3, 0x311E) },
@@ -140,7 +139,6 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0CF3, 0x0036), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 },
-	{ USB_DEVICE(0x0cf3, 0x3005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x311D), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x311E), .driver_info = BTUSB_ATH3012 },
@@ -193,9 +191,10 @@ static int ath3k_load_firmware(struct usb_device *udev,
 	sent += 20;
 	count -= 20;
 
+	pipe = usb_sndbulkpipe(udev, 0x02);
+
 	while (count) {
 		size = min_t(uint, count, BULK_SIZE);
-		pipe = usb_sndbulkpipe(udev, 0x02);
 		memcpy(send_buf, firmware->data + sent, size);
 
 		err = usb_bulk_msg(udev, pipe, send_buf, size,
diff --git a/drivers/bluetooth/btmrvl_drv.h b/drivers/bluetooth/btmrvl_drv.h
index 7399303d7d9..dc79f88f871 100644
--- a/drivers/bluetooth/btmrvl_drv.h
+++ b/drivers/bluetooth/btmrvl_drv.h
@@ -59,6 +59,8 @@ struct btmrvl_device {
 };
 
 struct btmrvl_adapter {
+	void *hw_regs_buf;
+	u8 *hw_regs;
 	u32 int_count;
 	struct sk_buff_head tx_queue;
 	u8 psmode;
@@ -140,7 +142,7 @@ void btmrvl_interrupt(struct btmrvl_private *priv);
 bool btmrvl_check_evtpkt(struct btmrvl_private *priv, struct sk_buff *skb);
 int btmrvl_process_event(struct btmrvl_private *priv, struct sk_buff *skb);
 
-int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, int subcmd);
+int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, u8 subcmd);
 int btmrvl_send_hscfg_cmd(struct btmrvl_private *priv);
 int btmrvl_enable_ps(struct btmrvl_private *priv);
 int btmrvl_prepare_command(struct btmrvl_private *priv);
diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c
index 2c4997ce248..e9dbddb0b8f 100644
--- a/drivers/bluetooth/btmrvl_main.c
+++ b/drivers/bluetooth/btmrvl_main.c
@@ -24,6 +24,7 @@
 #include <net/bluetooth/hci_core.h>
 
 #include "btmrvl_drv.h"
+#include "btmrvl_sdio.h"
 
 #define VERSION "1.0"
 
@@ -201,7 +202,7 @@ static int btmrvl_send_sync_cmd(struct btmrvl_private *priv, u16 opcode,
 	return 0;
 }
 
-int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, int subcmd)
+int btmrvl_send_module_cfg_cmd(struct btmrvl_private *priv, u8 subcmd)
 {
 	int ret;
 
@@ -337,10 +338,25 @@ static int btmrvl_tx_pkt(struct btmrvl_private *priv, struct sk_buff *skb)
 
 static void btmrvl_init_adapter(struct btmrvl_private *priv)
 {
+	int buf_size;
+
 	skb_queue_head_init(&priv->adapter->tx_queue);
 
 	priv->adapter->ps_state = PS_AWAKE;
 
+	buf_size = ALIGN_SZ(SDIO_BLOCK_SIZE, BTSDIO_DMA_ALIGN);
+	priv->adapter->hw_regs_buf = kzalloc(buf_size, GFP_KERNEL);
+	if (!priv->adapter->hw_regs_buf) {
+		priv->adapter->hw_regs = NULL;
+		BT_ERR("Unable to allocate buffer for hw_regs.");
+	} else {
+		priv->adapter->hw_regs =
+			(u8 *)ALIGN_ADDR(priv->adapter->hw_regs_buf,
+					 BTSDIO_DMA_ALIGN);
+		BT_DBG("hw_regs_buf=%p hw_regs=%p",
+		       priv->adapter->hw_regs_buf, priv->adapter->hw_regs);
+	}
+
 	init_waitqueue_head(&priv->adapter->cmd_wait_q);
 }
 
@@ -348,6 +364,7 @@ static void btmrvl_free_adapter(struct btmrvl_private *priv)
 {
 	skb_queue_purge(&priv->adapter->tx_queue);
 
+	kfree(priv->adapter->hw_regs_buf);
 	kfree(priv->adapter);
 
 	priv->adapter = NULL;
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 1b52c9f5230..9dedca516ff 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -64,6 +64,7 @@ static const struct btmrvl_sdio_card_reg btmrvl_reg_8688 = {
 	.io_port_0 = 0x00,
 	.io_port_1 = 0x01,
 	.io_port_2 = 0x02,
+	.int_read_to_clear = false,
 };
 static const struct btmrvl_sdio_card_reg btmrvl_reg_87xx = {
 	.cfg = 0x00,
@@ -80,6 +81,7 @@ static const struct btmrvl_sdio_card_reg btmrvl_reg_87xx = {
 	.io_port_0 = 0x78,
 	.io_port_1 = 0x79,
 	.io_port_2 = 0x7a,
+	.int_read_to_clear = false,
 };
 
 static const struct btmrvl_sdio_card_reg btmrvl_reg_88xx = {
@@ -97,6 +99,9 @@ static const struct btmrvl_sdio_card_reg btmrvl_reg_88xx = {
 	.io_port_0 = 0xd8,
 	.io_port_1 = 0xd9,
 	.io_port_2 = 0xda,
+	.int_read_to_clear = true,
+	.host_int_rsr = 0x01,
+	.card_misc_cfg = 0xcc,
 };
 
 static const struct btmrvl_sdio_device btmrvl_sdio_sd8688 = {
@@ -667,46 +672,78 @@ static int btmrvl_sdio_process_int_status(struct btmrvl_private *priv)
 	return 0;
 }
 
-static void btmrvl_sdio_interrupt(struct sdio_func *func)
+static int btmrvl_sdio_read_to_clear(struct btmrvl_sdio_card *card, u8 *ireg)
 {
-	struct btmrvl_private *priv;
-	struct btmrvl_sdio_card *card;
-	ulong flags;
-	u8 ireg = 0;
+	struct btmrvl_adapter *adapter = card->priv->adapter;
 	int ret;
 
-	card = sdio_get_drvdata(func);
-	if (!card || !card->priv) {
-		BT_ERR("sbi_interrupt(%p) card or priv is "
-				"NULL, card=%p\n", func, card);
-		return;
+	ret = sdio_readsb(card->func, adapter->hw_regs, 0, SDIO_BLOCK_SIZE);
+	if (ret) {
+		BT_ERR("sdio_readsb: read int hw_regs failed: %d", ret);
+		return ret;
 	}
 
-	priv = card->priv;
+	*ireg = adapter->hw_regs[card->reg->host_intstatus];
+	BT_DBG("hw_regs[%#x]=%#x", card->reg->host_intstatus, *ireg);
+
+	return 0;
+}
 
-	ireg = sdio_readb(card->func, card->reg->host_intstatus, &ret);
+static int btmrvl_sdio_write_to_clear(struct btmrvl_sdio_card *card, u8 *ireg)
+{
+	int ret;
+
+	*ireg = sdio_readb(card->func, card->reg->host_intstatus, &ret);
 	if (ret) {
-		BT_ERR("sdio_readb: read int status register failed");
-		return;
+		BT_ERR("sdio_readb: read int status failed: %d", ret);
+		return ret;
 	}
 
-	if (ireg != 0) {
+	if (*ireg) {
 		/*
 		 * DN_LD_HOST_INT_STATUS and/or UP_LD_HOST_INT_STATUS
 		 * Clear the interrupt status register and re-enable the
 		 * interrupt.
 		 */
-		BT_DBG("ireg = 0x%x", ireg);
+		BT_DBG("int_status = 0x%x", *ireg);
 
-		sdio_writeb(card->func, ~(ireg) & (DN_LD_HOST_INT_STATUS |
-					UP_LD_HOST_INT_STATUS),
-				card->reg->host_intstatus, &ret);
+		sdio_writeb(card->func, ~(*ireg) & (DN_LD_HOST_INT_STATUS |
+						    UP_LD_HOST_INT_STATUS),
+			    card->reg->host_intstatus, &ret);
 		if (ret) {
-			BT_ERR("sdio_writeb: clear int status register failed");
-			return;
+			BT_ERR("sdio_writeb: clear int status failed: %d", ret);
+			return ret;
 		}
 	}
 
+	return 0;
+}
+
+static void btmrvl_sdio_interrupt(struct sdio_func *func)
+{
+	struct btmrvl_private *priv;
+	struct btmrvl_sdio_card *card;
+	ulong flags;
+	u8 ireg = 0;
+	int ret;
+
+	card = sdio_get_drvdata(func);
+	if (!card || !card->priv) {
+		BT_ERR("sbi_interrupt(%p) card or priv is "
+				"NULL, card=%p\n", func, card);
+		return;
+	}
+
+	priv = card->priv;
+
+	if (card->reg->int_read_to_clear)
+		ret = btmrvl_sdio_read_to_clear(card, &ireg);
+	else
+		ret = btmrvl_sdio_write_to_clear(card, &ireg);
+
+	if (ret)
+		return;
+
 	spin_lock_irqsave(&priv->driver_lock, flags);
 	sdio_ireg |= ireg;
 	spin_unlock_irqrestore(&priv->driver_lock, flags);
@@ -777,6 +814,30 @@ static int btmrvl_sdio_register_dev(struct btmrvl_sdio_card *card)
 
 	BT_DBG("SDIO FUNC%d IO port: 0x%x", func->num, card->ioport);
 
+	if (card->reg->int_read_to_clear) {
+		reg = sdio_readb(func, card->reg->host_int_rsr, &ret);
+		if (ret < 0) {
+			ret = -EIO;
+			goto release_irq;
+		}
+		sdio_writeb(func, reg | 0x3f, card->reg->host_int_rsr, &ret);
+		if (ret < 0) {
+			ret = -EIO;
+			goto release_irq;
+		}
+
+		reg = sdio_readb(func, card->reg->card_misc_cfg, &ret);
+		if (ret < 0) {
+			ret = -EIO;
+			goto release_irq;
+		}
+		sdio_writeb(func, reg | 0x10, card->reg->card_misc_cfg, &ret);
+		if (ret < 0) {
+			ret = -EIO;
+			goto release_irq;
+		}
+	}
+
 	sdio_set_drvdata(func, card);
 
 	sdio_release_host(func);
diff --git a/drivers/bluetooth/btmrvl_sdio.h b/drivers/bluetooth/btmrvl_sdio.h
index 43d35a609ca..d4dd3b0fa53 100644
--- a/drivers/bluetooth/btmrvl_sdio.h
+++ b/drivers/bluetooth/btmrvl_sdio.h
@@ -78,6 +78,9 @@ struct btmrvl_sdio_card_reg {
 	u8 io_port_0;
 	u8 io_port_1;
 	u8 io_port_2;
+	bool int_read_to_clear;
+	u8 host_int_rsr;
+	u8 card_misc_cfg;
 };
 
 struct btmrvl_sdio_card {
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index a7dfbf9a3af..6250fc2fb93 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -49,6 +49,7 @@ static struct usb_driver btusb_driver;
 #define BTUSB_WRONG_SCO_MTU	0x40
 #define BTUSB_ATH3012		0x80
 #define BTUSB_INTEL		0x100
+#define BTUSB_BCM_PATCHRAM	0x200
 
 static const struct usb_device_id btusb_table[] = {
 	/* Generic Bluetooth USB device */
@@ -111,7 +112,8 @@ static const struct usb_device_id btusb_table[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0489, 0xff, 0x01, 0x01) },
 
 	/* Broadcom devices with vendor specific id */
-	{ USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01) },
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x0a5c, 0xff, 0x01, 0x01),
+	  .driver_info = BTUSB_BCM_PATCHRAM },
 
 	/* Belkin F8065bf - Broadcom based */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x050d, 0xff, 0x01, 0x01) },
@@ -160,7 +162,6 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x0036), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 },
-	{ USB_DEVICE(0x0cf3, 0x3005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 },
@@ -1381,6 +1382,154 @@ exit_mfg_deactivate:
 	return 0;
 }
 
+static int btusb_setup_bcm_patchram(struct hci_dev *hdev)
+{
+	struct btusb_data *data = hci_get_drvdata(hdev);
+	struct usb_device *udev = data->udev;
+	char fw_name[64];
+	const struct firmware *fw;
+	const u8 *fw_ptr;
+	size_t fw_size;
+	const struct hci_command_hdr *cmd;
+	const u8 *cmd_param;
+	u16 opcode;
+	struct sk_buff *skb;
+	struct hci_rp_read_local_version *ver;
+	long ret;
+
+	snprintf(fw_name, sizeof(fw_name), "brcm/%s-%04x-%04x.hcd",
+		 udev->product ? udev->product : "BCM",
+		 le16_to_cpu(udev->descriptor.idVendor),
+		 le16_to_cpu(udev->descriptor.idProduct));
+
+	ret = request_firmware(&fw, fw_name, &hdev->dev);
+	if (ret < 0) {
+		BT_INFO("%s: BCM: patch %s not found", hdev->name,
+			fw_name);
+		return 0;
+	}
+
+	/* Reset */
+	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		BT_ERR("%s: HCI_OP_RESET failed (%ld)", hdev->name, ret);
+		goto done;
+	}
+	kfree_skb(skb);
+
+	/* Read Local Version Info */
+	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
+			     HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)",
+			hdev->name, ret);
+		goto done;
+	}
+
+	if (skb->len != sizeof(*ver)) {
+		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch",
+			hdev->name);
+		kfree_skb(skb);
+		ret = -EIO;
+		goto done;
+	}
+
+	ver = (struct hci_rp_read_local_version *) skb->data;
+	BT_INFO("%s: BCM: patching hci_ver=%02x hci_rev=%04x lmp_ver=%02x "
+		"lmp_subver=%04x", hdev->name, ver->hci_ver, ver->hci_rev,
+		ver->lmp_ver, ver->lmp_subver);
+	kfree_skb(skb);
+
+	/* Start Download */
+	skb = __hci_cmd_sync(hdev, 0xfc2e, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		BT_ERR("%s: BCM: Download Minidrv command failed (%ld)",
+			hdev->name, ret);
+		goto reset_fw;
+	}
+	kfree_skb(skb);
+
+	/* 50 msec delay after Download Minidrv completes */
+	msleep(50);
+
+	fw_ptr = fw->data;
+	fw_size = fw->size;
+
+	while (fw_size >= sizeof(*cmd)) {
+		cmd = (struct hci_command_hdr *) fw_ptr;
+		fw_ptr += sizeof(*cmd);
+		fw_size -= sizeof(*cmd);
+
+		if (fw_size < cmd->plen) {
+			BT_ERR("%s: BCM: patch %s is corrupted",
+				hdev->name, fw_name);
+			ret = -EINVAL;
+			goto reset_fw;
+		}
+
+		cmd_param = fw_ptr;
+		fw_ptr += cmd->plen;
+		fw_size -= cmd->plen;
+
+		opcode = le16_to_cpu(cmd->opcode);
+
+		skb = __hci_cmd_sync(hdev, opcode, cmd->plen, cmd_param,
+				     HCI_INIT_TIMEOUT);
+		if (IS_ERR(skb)) {
+			ret = PTR_ERR(skb);
+			BT_ERR("%s: BCM: patch command %04x failed (%ld)",
+				hdev->name, opcode, ret);
+			goto reset_fw;
+		}
+		kfree_skb(skb);
+	}
+
+	/* 250 msec delay after Launch Ram completes */
+	msleep(250);
+
+reset_fw:
+	/* Reset */
+	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		BT_ERR("%s: HCI_OP_RESET failed (%ld)", hdev->name, ret);
+		goto done;
+	}
+	kfree_skb(skb);
+
+	/* Read Local Version Info */
+	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
+			     HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)",
+			hdev->name, ret);
+		goto done;
+	}
+
+	if (skb->len != sizeof(*ver)) {
+		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch",
+			hdev->name);
+		kfree_skb(skb);
+		ret = -EIO;
+		goto done;
+	}
+
+	ver = (struct hci_rp_read_local_version *) skb->data;
+	BT_INFO("%s: BCM: firmware hci_ver=%02x hci_rev=%04x lmp_ver=%02x "
+		"lmp_subver=%04x", hdev->name, ver->hci_ver, ver->hci_rev,
+		ver->lmp_ver, ver->lmp_subver);
+	kfree_skb(skb);
+
+done:
+	release_firmware(fw);
+
+	return ret;
+}
+
 static int btusb_probe(struct usb_interface *intf,
 				const struct usb_device_id *id)
 {
@@ -1486,6 +1635,9 @@ static int btusb_probe(struct usb_interface *intf,
 	if (id->driver_info & BTUSB_BCM92035)
 		hdev->setup = btusb_setup_bcm92035;
 
+	if (id->driver_info & BTUSB_BCM_PATCHRAM)
+		hdev->setup = btusb_setup_bcm_patchram;
+
 	if (id->driver_info & BTUSB_INTEL)
 		hdev->setup = btusb_setup_intel;
 
diff --git a/drivers/bluetooth/hci_h4.c b/drivers/bluetooth/hci_h4.c
index 7048a583fe5..66db9a80337 100644
--- a/drivers/bluetooth/hci_h4.c
+++ b/drivers/bluetooth/hci_h4.c
@@ -55,13 +55,6 @@ struct h4_struct {
 	struct sk_buff_head txq;
 };
 
-/* H4 receiver States */
-#define H4_W4_PACKET_TYPE	0
-#define H4_W4_EVENT_HDR		1
-#define H4_W4_ACL_HDR		2
-#define H4_W4_SCO_HDR		3
-#define H4_W4_DATA		4
-
 /* Initialize protocol */
 static int h4_open(struct hci_uart *hu)
 {
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index 04680ead927..fede8ca7147 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -406,6 +406,7 @@ static int h5_rx_3wire_hdr(struct hci_uart *hu, unsigned char c)
 	    H5_HDR_PKT_TYPE(hdr) != HCI_3WIRE_LINK_PKT) {
 		BT_ERR("Non-link packet received in non-active state");
 		h5_reset_rx(h5);
+		return 0;
 	}
 
 	h5->rx_func = h5_rx_payload;
diff --git a/drivers/bus/Kconfig b/drivers/bus/Kconfig
index a118ec1650f..1f37d9870e7 100644
--- a/drivers/bus/Kconfig
+++ b/drivers/bus/Kconfig
@@ -45,7 +45,7 @@ config OMAP_INTERCONNECT
 
 config ARM_CCI
 	bool "ARM CCI driver support"
-	depends on ARM
+	depends on ARM && OF && CPU_V7
 	help
 	  Driver supporting the CCI cache coherent interconnect for ARM
 	  platforms.
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 2a44767891f..898b84bba28 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2184,6 +2184,7 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 			ret = -ENOMEM;
 			break;
 		}
+		blk_rq_set_block_pc(rq);
 
 		ret = blk_rq_map_user(q, rq, NULL, ubuf, len, GFP_KERNEL);
 		if (ret) {
@@ -2203,7 +2204,6 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		rq->cmd[9] = 0xf8;
 
 		rq->cmd_len = 12;
-		rq->cmd_type = REQ_TYPE_BLOCK_PC;
 		rq->timeout = 60 * HZ;
 		bio = rq->bio;
 
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 334601cc81c..c4419ea1ab0 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -55,16 +55,41 @@ static DEFINE_MUTEX(rng_mutex);
 static int data_avail;
 static u8 *rng_buffer;
 
+static inline int rng_get_data(struct hwrng *rng, u8 *buffer, size_t size,
+			       int wait);
+
 static size_t rng_buffer_size(void)
 {
 	return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES;
 }
 
+static void add_early_randomness(struct hwrng *rng)
+{
+	unsigned char bytes[16];
+	int bytes_read;
+
+	/*
+	 * Currently only virtio-rng cannot return data during device
+	 * probe, and that's handled in virtio-rng.c itself.  If there
+	 * are more such devices, this call to rng_get_data can be
+	 * made conditional here instead of doing it per-device.
+	 */
+	bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1);
+	if (bytes_read > 0)
+		add_device_randomness(bytes, bytes_read);
+}
+
 static inline int hwrng_init(struct hwrng *rng)
 {
-	if (!rng->init)
-		return 0;
-	return rng->init(rng);
+	if (rng->init) {
+		int ret;
+
+		ret =  rng->init(rng);
+		if (ret)
+			return ret;
+	}
+	add_early_randomness(rng);
+	return 0;
 }
 
 static inline void hwrng_cleanup(struct hwrng *rng)
@@ -304,8 +329,6 @@ int hwrng_register(struct hwrng *rng)
 {
 	int err = -EINVAL;
 	struct hwrng *old_rng, *tmp;
-	unsigned char bytes[16];
-	int bytes_read;
 
 	if (rng->name == NULL ||
 	    (rng->data_read == NULL && rng->read == NULL))
@@ -347,9 +370,17 @@ int hwrng_register(struct hwrng *rng)
 	INIT_LIST_HEAD(&rng->list);
 	list_add_tail(&rng->list, &rng_list);
 
-	bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1);
-	if (bytes_read > 0)
-		add_device_randomness(bytes, bytes_read);
+	if (old_rng && !rng->init) {
+		/*
+		 * Use a new device's input to add some randomness to
+		 * the system.  If this rng device isn't going to be
+		 * used right away, its init function hasn't been
+		 * called yet; so only use the randomness from devices
+		 * that don't need an init callback.
+		 */
+		add_early_randomness(rng);
+	}
+
 out_unlock:
 	mutex_unlock(&rng_mutex);
 out:
diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c
index 2ce0e225e58..e9b15bc18b4 100644
--- a/drivers/char/hw_random/virtio-rng.c
+++ b/drivers/char/hw_random/virtio-rng.c
@@ -25,101 +25,140 @@
 #include <linux/virtio_rng.h>
 #include <linux/module.h>
 
-static struct virtqueue *vq;
-static unsigned int data_avail;
-static DECLARE_COMPLETION(have_data);
-static bool busy;
+static DEFINE_IDA(rng_index_ida);
+
+struct virtrng_info {
+	struct virtio_device *vdev;
+	struct hwrng hwrng;
+	struct virtqueue *vq;
+	unsigned int data_avail;
+	struct completion have_data;
+	bool busy;
+	char name[25];
+	int index;
+};
+
+static bool probe_done;
 
 static void random_recv_done(struct virtqueue *vq)
 {
+	struct virtrng_info *vi = vq->vdev->priv;
+
 	/* We can get spurious callbacks, e.g. shared IRQs + virtio_pci. */
-	if (!virtqueue_get_buf(vq, &data_avail))
+	if (!virtqueue_get_buf(vi->vq, &vi->data_avail))
 		return;
 
-	complete(&have_data);
+	complete(&vi->have_data);
 }
 
 /* The host will fill any buffer we give it with sweet, sweet randomness. */
-static void register_buffer(u8 *buf, size_t size)
+static void register_buffer(struct virtrng_info *vi, u8 *buf, size_t size)
 {
 	struct scatterlist sg;
 
 	sg_init_one(&sg, buf, size);
 
 	/* There should always be room for one buffer. */
-	virtqueue_add_inbuf(vq, &sg, 1, buf, GFP_KERNEL);
+	virtqueue_add_inbuf(vi->vq, &sg, 1, buf, GFP_KERNEL);
 
-	virtqueue_kick(vq);
+	virtqueue_kick(vi->vq);
 }
 
 static int virtio_read(struct hwrng *rng, void *buf, size_t size, bool wait)
 {
 	int ret;
+	struct virtrng_info *vi = (struct virtrng_info *)rng->priv;
 
-	if (!busy) {
-		busy = true;
-		init_completion(&have_data);
-		register_buffer(buf, size);
+	/*
+	 * Don't ask host for data till we're setup.  This call can
+	 * happen during hwrng_register(), after commit d9e7972619.
+	 */
+	if (unlikely(!probe_done))
+		return 0;
+
+	if (!vi->busy) {
+		vi->busy = true;
+		init_completion(&vi->have_data);
+		register_buffer(vi, buf, size);
 	}
 
 	if (!wait)
 		return 0;
 
-	ret = wait_for_completion_killable(&have_data);
+	ret = wait_for_completion_killable(&vi->have_data);
 	if (ret < 0)
 		return ret;
 
-	busy = false;
+	vi->busy = false;
 
-	return data_avail;
+	return vi->data_avail;
 }
 
 static void virtio_cleanup(struct hwrng *rng)
 {
-	if (busy)
-		wait_for_completion(&have_data);
-}
+	struct virtrng_info *vi = (struct virtrng_info *)rng->priv;
 
-
-static struct hwrng virtio_hwrng = {
-	.name		= "virtio",
-	.cleanup	= virtio_cleanup,
-	.read		= virtio_read,
-};
+	if (vi->busy)
+		wait_for_completion(&vi->have_data);
+}
 
 static int probe_common(struct virtio_device *vdev)
 {
-	int err;
+	int err, index;
+	struct virtrng_info *vi = NULL;
 
-	if (vq) {
-		/* We only support one device for now */
-		return -EBUSY;
+	vi = kzalloc(sizeof(struct virtrng_info), GFP_KERNEL);
+	if (!vi)
+		return -ENOMEM;
+
+	vi->index = index = ida_simple_get(&rng_index_ida, 0, 0, GFP_KERNEL);
+	if (index < 0) {
+		kfree(vi);
+		return index;
 	}
+	sprintf(vi->name, "virtio_rng.%d", index);
+	init_completion(&vi->have_data);
+
+	vi->hwrng = (struct hwrng) {
+		.read = virtio_read,
+		.cleanup = virtio_cleanup,
+		.priv = (unsigned long)vi,
+		.name = vi->name,
+	};
+	vdev->priv = vi;
+
 	/* We expect a single virtqueue. */
-	vq = virtio_find_single_vq(vdev, random_recv_done, "input");
-	if (IS_ERR(vq)) {
-		err = PTR_ERR(vq);
-		vq = NULL;
+	vi->vq = virtio_find_single_vq(vdev, random_recv_done, "input");
+	if (IS_ERR(vi->vq)) {
+		err = PTR_ERR(vi->vq);
+		vi->vq = NULL;
+		kfree(vi);
+		ida_simple_remove(&rng_index_ida, index);
 		return err;
 	}
 
-	err = hwrng_register(&virtio_hwrng);
+	err = hwrng_register(&vi->hwrng);
 	if (err) {
 		vdev->config->del_vqs(vdev);
-		vq = NULL;
+		vi->vq = NULL;
+		kfree(vi);
+		ida_simple_remove(&rng_index_ida, index);
 		return err;
 	}
 
+	probe_done = true;
 	return 0;
 }
 
 static void remove_common(struct virtio_device *vdev)
 {
+	struct virtrng_info *vi = vdev->priv;
 	vdev->config->reset(vdev);
-	busy = false;
-	hwrng_unregister(&virtio_hwrng);
+	vi->busy = false;
+	hwrng_unregister(&vi->hwrng);
 	vdev->config->del_vqs(vdev);
-	vq = NULL;
+	ida_simple_remove(&rng_index_ida, vi->index);
+	kfree(vi);
 }
 
 static int virtrng_probe(struct virtio_device *vdev)
diff --git a/drivers/char/i8k.c b/drivers/char/i8k.c
index d915707d2ba..93dcad0c1cb 100644
--- a/drivers/char/i8k.c
+++ b/drivers/char/i8k.c
@@ -138,7 +138,9 @@ static int i8k_smm(struct smm_regs *regs)
 	if (!alloc_cpumask_var(&old_mask, GFP_KERNEL))
 		return -ENOMEM;
 	cpumask_copy(old_mask, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current, cpumask_of(0));
+	rc = set_cpus_allowed_ptr(current, cpumask_of(0));
+	if (rc)
+		goto out;
 	if (smp_processor_id() != 0) {
 		rc = -EBUSY;
 		goto out;
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 4ad71ef2cd5..71529e196b8 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -641,7 +641,7 @@ retry:
 		} while (unlikely(entropy_count < pool_size-2 && pnfrac));
 	}
 
-	if (entropy_count < 0) {
+	if (unlikely(entropy_count < 0)) {
 		pr_warn("random: negative entropy/overflow: pool %s count %d\n",
 			r->name, entropy_count);
 		WARN_ON(1);
@@ -980,26 +980,37 @@ static void push_to_pool(struct work_struct *work)
 static size_t account(struct entropy_store *r, size_t nbytes, int min,
 		      int reserved)
 {
-	int have_bytes;
 	int entropy_count, orig;
-	size_t ibytes;
+	size_t ibytes, nfrac;
 
 	BUG_ON(r->entropy_count > r->poolinfo->poolfracbits);
 
 	/* Can we pull enough? */
 retry:
 	entropy_count = orig = ACCESS_ONCE(r->entropy_count);
-	have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
 	ibytes = nbytes;
 	/* If limited, never pull more than available */
-	if (r->limit)
-		ibytes = min_t(size_t, ibytes, have_bytes - reserved);
+	if (r->limit) {
+		int have_bytes = entropy_count >> (ENTROPY_SHIFT + 3);
+
+		if ((have_bytes -= reserved) < 0)
+			have_bytes = 0;
+		ibytes = min_t(size_t, ibytes, have_bytes);
+	}
 	if (ibytes < min)
 		ibytes = 0;
-	if (have_bytes >= ibytes + reserved)
-		entropy_count -= ibytes << (ENTROPY_SHIFT + 3);
+
+	if (unlikely(entropy_count < 0)) {
+		pr_warn("random: negative entropy count: pool %s count %d\n",
+			r->name, entropy_count);
+		WARN_ON(1);
+		entropy_count = 0;
+	}
+	nfrac = ibytes << (ENTROPY_SHIFT + 3);
+	if ((size_t) entropy_count > nfrac)
+		entropy_count -= nfrac;
 	else
-		entropy_count = reserved << (ENTROPY_SHIFT + 3);
+		entropy_count = 0;
 
 	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
 		goto retry;
@@ -1375,6 +1386,7 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 			    "with %d bits of entropy available\n",
 			    current->comm, nonblocking_pool.entropy_total);
 
+	nbytes = min_t(size_t, nbytes, INT_MAX >> (ENTROPY_SHIFT + 3));
 	ret = extract_entropy_user(&nonblocking_pool, buf, nbytes);
 
 	trace_urandom_read(8 * nbytes, ENTROPY_BITS(&nonblocking_pool),
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index 6e8d65e9b1d..0102dc78860 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -284,10 +284,10 @@ static long raw_ctl_compat_ioctl(struct file *file, unsigned int cmd,
 #endif
 
 static const struct file_operations raw_fops = {
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= blkdev_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= blkdev_write_iter,
 	.fsync		= blkdev_fsync,
 	.open		= raw_open,
 	.release	= raw_release,
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 9f9c5ae5359..cfd3af7b2cb 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -102,6 +102,13 @@ config COMMON_CLK_KEYSTONE
           Supports clock drivers for Keystone based SOCs. These SOCs have local
 	  a power sleep control module that gate the clock to the IPs and PLLs.
 
+config COMMON_CLK_PALMAS
+	tristate "Clock driver for TI Palmas devices"
+	depends on MFD_PALMAS
+	---help---
+	  This driver supports TI Palmas devices 32KHz output KG and KG_AUDIO
+	  using common clock framework.
+
 source "drivers/clk/qcom/Kconfig"
 
 endmenu
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 567f1025902..f537a0b1f79 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -9,12 +9,16 @@ obj-$(CONFIG_COMMON_CLK)	+= clk-gate.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-mux.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-composite.o
 obj-$(CONFIG_COMMON_CLK)	+= clk-fractional-divider.o
+ifeq ($(CONFIG_OF), y)
+obj-$(CONFIG_COMMON_CLK)	+= clk-conf.o
+endif
 
 # hardware specific clock types
 # please keep this section sorted lexicographically by file/directory path name
 obj-$(CONFIG_COMMON_CLK_AXI_CLKGEN)	+= clk-axi-clkgen.o
 obj-$(CONFIG_ARCH_AXXIA)		+= clk-axm5516.o
 obj-$(CONFIG_ARCH_BCM2835)		+= clk-bcm2835.o
+obj-$(CONFIG_ARCH_CLPS711X)		+= clk-clps711x.o
 obj-$(CONFIG_ARCH_EFM32)		+= clk-efm32gg.o
 obj-$(CONFIG_ARCH_HIGHBANK)		+= clk-highbank.o
 obj-$(CONFIG_MACH_LOONGSON1)		+= clk-ls1x.o
@@ -22,6 +26,7 @@ obj-$(CONFIG_COMMON_CLK_MAX77686)	+= clk-max77686.o
 obj-$(CONFIG_ARCH_MOXART)		+= clk-moxart.o
 obj-$(CONFIG_ARCH_NOMADIK)		+= clk-nomadik.o
 obj-$(CONFIG_ARCH_NSPIRE)		+= clk-nspire.o
+obj-$(CONFIG_COMMON_CLK_PALMAS)		+= clk-palmas.o
 obj-$(CONFIG_CLK_PPC_CORENET)		+= clk-ppc-corenet.o
 obj-$(CONFIG_COMMON_CLK_S2MPS11)	+= clk-s2mps11.o
 obj-$(CONFIG_COMMON_CLK_SI5351)		+= clk-si5351.o
diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
index 733306131b9..59fa3cc96c9 100644
--- a/drivers/clk/at91/clk-main.c
+++ b/drivers/clk/at91/clk-main.c
@@ -388,6 +388,7 @@ static unsigned long clk_main_recalc_rate(struct at91_pmc *pmc,
 	if (parent_rate)
 		return parent_rate;
 
+	pr_warn("Main crystal frequency not set, using approximate value\n");
 	tmp = pmc_read(pmc, AT91_CKGR_MCFR);
 	if (!(tmp & AT91_PMC_MAINRDY))
 		return 0;
diff --git a/drivers/clk/clk-clps711x.c b/drivers/clk/clk-clps711x.c
new file mode 100644
index 00000000000..715eec1a990
--- /dev/null
+++ b/drivers/clk/clk-clps711x.c
@@ -0,0 +1,192 @@
+/*
+ *  Cirrus Logic CLPS711X CLK driver
+ *
+ *  Copyright (C) 2014 Alexander Shiyan <shc_work@mail.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/mfd/syscon/clps711x.h>
+
+#include <dt-bindings/clock/clps711x-clock.h>
+
+#define CLPS711X_SYSCON1	(0x0100)
+#define CLPS711X_SYSCON2	(0x1100)
+#define CLPS711X_SYSFLG2	(CLPS711X_SYSCON2 + SYSFLG_OFFSET)
+#define CLPS711X_PLLR		(0xa5a8)
+
+#define CLPS711X_EXT_FREQ	(13000000)
+#define CLPS711X_OSC_FREQ	(3686400)
+
+static const struct clk_div_table spi_div_table[] = {
+	{ .val = 0, .div = 32, },
+	{ .val = 1, .div = 8, },
+	{ .val = 2, .div = 2, },
+	{ .val = 3, .div = 1, },
+};
+
+static const struct clk_div_table timer_div_table[] = {
+	{ .val = 0, .div = 256, },
+	{ .val = 1, .div = 1, },
+};
+
+struct clps711x_clk {
+	struct clk_onecell_data	clk_data;
+	spinlock_t		lock;
+	struct clk		*clks[CLPS711X_CLK_MAX];
+};
+
+static struct clps711x_clk * __init _clps711x_clk_init(void __iomem *base,
+						       u32 fref)
+{
+	u32 tmp, f_cpu, f_pll, f_bus, f_tim, f_pwm, f_spi;
+	struct clps711x_clk *clps711x_clk;
+	unsigned i;
+
+	if (!base)
+		return ERR_PTR(-ENOMEM);
+
+	clps711x_clk = kzalloc(sizeof(*clps711x_clk), GFP_KERNEL);
+	if (!clps711x_clk)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&clps711x_clk->lock);
+
+	/* Read PLL multiplier value and sanity check */
+	tmp = readl(base + CLPS711X_PLLR) >> 24;
+	if (((tmp >= 10) && (tmp <= 50)) || !fref)
+		f_pll = DIV_ROUND_UP(CLPS711X_OSC_FREQ * tmp, 2);
+	else
+		f_pll = fref;
+
+	tmp = readl(base + CLPS711X_SYSFLG2);
+	if (tmp & SYSFLG2_CKMODE) {
+		f_cpu = CLPS711X_EXT_FREQ;
+		f_bus = CLPS711X_EXT_FREQ;
+		f_spi = DIV_ROUND_CLOSEST(CLPS711X_EXT_FREQ, 96);
+		f_pll = 0;
+		f_pwm = DIV_ROUND_CLOSEST(CLPS711X_EXT_FREQ, 128);
+	} else {
+		f_cpu = f_pll;
+		if (f_cpu > 36864000)
+			f_bus = DIV_ROUND_UP(f_cpu, 2);
+		else
+			f_bus = 36864000 / 2;
+		f_spi = DIV_ROUND_CLOSEST(f_cpu, 576);
+		f_pwm = DIV_ROUND_CLOSEST(f_cpu, 768);
+	}
+
+	if (tmp & SYSFLG2_CKMODE) {
+		if (readl(base + CLPS711X_SYSCON2) & SYSCON2_OSTB)
+			f_tim = DIV_ROUND_CLOSEST(CLPS711X_EXT_FREQ, 26);
+		else
+			f_tim = DIV_ROUND_CLOSEST(CLPS711X_EXT_FREQ, 24);
+	} else
+		f_tim = DIV_ROUND_CLOSEST(f_cpu, 144);
+
+	tmp = readl(base + CLPS711X_SYSCON1);
+	/* Timer1 in free running mode.
+	 * Counter will wrap around to 0xffff when it underflows
+	 * and will continue to count down.
+	 */
+	tmp &= ~(SYSCON1_TC1M | SYSCON1_TC1S);
+	/* Timer2 in prescale mode.
+	 * Value writen is automatically re-loaded when
+	 * the counter underflows.
+	 */
+	tmp |= SYSCON1_TC2M | SYSCON1_TC2S;
+	writel(tmp, base + CLPS711X_SYSCON1);
+
+	clps711x_clk->clks[CLPS711X_CLK_DUMMY] =
+		clk_register_fixed_rate(NULL, "dummy", NULL, CLK_IS_ROOT, 0);
+	clps711x_clk->clks[CLPS711X_CLK_CPU] =
+		clk_register_fixed_rate(NULL, "cpu", NULL, CLK_IS_ROOT, f_cpu);
+	clps711x_clk->clks[CLPS711X_CLK_BUS] =
+		clk_register_fixed_rate(NULL, "bus", NULL, CLK_IS_ROOT, f_bus);
+	clps711x_clk->clks[CLPS711X_CLK_PLL] =
+		clk_register_fixed_rate(NULL, "pll", NULL, CLK_IS_ROOT, f_pll);
+	clps711x_clk->clks[CLPS711X_CLK_TIMERREF] =
+		clk_register_fixed_rate(NULL, "timer_ref", NULL, CLK_IS_ROOT,
+					f_tim);
+	clps711x_clk->clks[CLPS711X_CLK_TIMER1] =
+		clk_register_divider_table(NULL, "timer1", "timer_ref", 0,
+					   base + CLPS711X_SYSCON1, 5, 1, 0,
+					   timer_div_table, &clps711x_clk->lock);
+	clps711x_clk->clks[CLPS711X_CLK_TIMER2] =
+		clk_register_divider_table(NULL, "timer2", "timer_ref", 0,
+					   base + CLPS711X_SYSCON1, 7, 1, 0,
+					   timer_div_table, &clps711x_clk->lock);
+	clps711x_clk->clks[CLPS711X_CLK_PWM] =
+		clk_register_fixed_rate(NULL, "pwm", NULL, CLK_IS_ROOT, f_pwm);
+	clps711x_clk->clks[CLPS711X_CLK_SPIREF] =
+		clk_register_fixed_rate(NULL, "spi_ref", NULL, CLK_IS_ROOT,
+					f_spi);
+	clps711x_clk->clks[CLPS711X_CLK_SPI] =
+		clk_register_divider_table(NULL, "spi", "spi_ref", 0,
+					   base + CLPS711X_SYSCON1, 16, 2, 0,
+					   spi_div_table, &clps711x_clk->lock);
+	clps711x_clk->clks[CLPS711X_CLK_UART] =
+		clk_register_fixed_factor(NULL, "uart", "bus", 0, 1, 10);
+	clps711x_clk->clks[CLPS711X_CLK_TICK] =
+		clk_register_fixed_rate(NULL, "tick", NULL, CLK_IS_ROOT, 64);
+
+	for (i = 0; i < CLPS711X_CLK_MAX; i++)
+		if (IS_ERR(clps711x_clk->clks[i]))
+			pr_err("clk %i: register failed with %ld\n",
+			       i, PTR_ERR(clps711x_clk->clks[i]));
+
+	return clps711x_clk;
+}
+
+void __init clps711x_clk_init(void __iomem *base)
+{
+	struct clps711x_clk *clps711x_clk;
+
+	clps711x_clk = _clps711x_clk_init(base, 73728000);
+
+	BUG_ON(IS_ERR(clps711x_clk));
+
+	/* Clocksource */
+	clk_register_clkdev(clps711x_clk->clks[CLPS711X_CLK_TIMER1],
+			    NULL, "clps711x-timer.0");
+	clk_register_clkdev(clps711x_clk->clks[CLPS711X_CLK_TIMER2],
+			    NULL, "clps711x-timer.1");
+
+	/* Drivers */
+	clk_register_clkdev(clps711x_clk->clks[CLPS711X_CLK_PWM],
+			    NULL, "clps711x-pwm");
+	clk_register_clkdev(clps711x_clk->clks[CLPS711X_CLK_UART],
+			    NULL, "clps711x-uart.0");
+	clk_register_clkdev(clps711x_clk->clks[CLPS711X_CLK_UART],
+			    NULL, "clps711x-uart.1");
+}
+
+#ifdef CONFIG_OF
+static void __init clps711x_clk_init_dt(struct device_node *np)
+{
+	void __iomem *base = of_iomap(np, 0);
+	struct clps711x_clk *clps711x_clk;
+	u32 fref = 0;
+
+	WARN_ON(of_property_read_u32(np, "startup-frequency", &fref));
+
+	clps711x_clk = _clps711x_clk_init(base, fref);
+	BUG_ON(IS_ERR(clps711x_clk));
+
+	clps711x_clk->clk_data.clks = clps711x_clk->clks;
+	clps711x_clk->clk_data.clk_num = CLPS711X_CLK_MAX;
+	of_clk_add_provider(np, of_clk_src_onecell_get,
+			    &clps711x_clk->clk_data);
+}
+CLK_OF_DECLARE(clps711x, "cirrus,clps711x-clk", clps711x_clk_init_dt);
+#endif
diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index 57a078e06ef..b9355daf806 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -64,11 +64,56 @@ static long clk_composite_determine_rate(struct clk_hw *hw, unsigned long rate,
 	const struct clk_ops *mux_ops = composite->mux_ops;
 	struct clk_hw *rate_hw = composite->rate_hw;
 	struct clk_hw *mux_hw = composite->mux_hw;
+	struct clk *parent;
+	unsigned long parent_rate;
+	long tmp_rate, best_rate = 0;
+	unsigned long rate_diff;
+	unsigned long best_rate_diff = ULONG_MAX;
+	int i;
 
 	if (rate_hw && rate_ops && rate_ops->determine_rate) {
 		rate_hw->clk = hw->clk;
 		return rate_ops->determine_rate(rate_hw, rate, best_parent_rate,
 						best_parent_p);
+	} else if (rate_hw && rate_ops && rate_ops->round_rate &&
+		   mux_hw && mux_ops && mux_ops->set_parent) {
+		*best_parent_p = NULL;
+
+		if (__clk_get_flags(hw->clk) & CLK_SET_RATE_NO_REPARENT) {
+			*best_parent_p = clk_get_parent(mux_hw->clk);
+			*best_parent_rate = __clk_get_rate(*best_parent_p);
+
+			return rate_ops->round_rate(rate_hw, rate,
+						    best_parent_rate);
+		}
+
+		for (i = 0; i < __clk_get_num_parents(mux_hw->clk); i++) {
+			parent = clk_get_parent_by_index(mux_hw->clk, i);
+			if (!parent)
+				continue;
+
+			parent_rate = __clk_get_rate(parent);
+
+			tmp_rate = rate_ops->round_rate(rate_hw, rate,
+							&parent_rate);
+			if (tmp_rate < 0)
+				continue;
+
+			rate_diff = abs(rate - tmp_rate);
+
+			if (!rate_diff || !*best_parent_p
+				       || best_rate_diff > rate_diff) {
+				*best_parent_p = parent;
+				*best_parent_rate = parent_rate;
+				best_rate_diff = rate_diff;
+				best_rate = tmp_rate;
+			}
+
+			if (!rate_diff)
+				return rate;
+		}
+
+		return best_rate;
 	} else if (mux_hw && mux_ops && mux_ops->determine_rate) {
 		mux_hw->clk = hw->clk;
 		return mux_ops->determine_rate(mux_hw, rate, best_parent_rate,
@@ -162,7 +207,7 @@ struct clk *clk_register_composite(struct device *dev, const char *name,
 	clk_composite_ops = &composite->ops;
 
 	if (mux_hw && mux_ops) {
-		if (!mux_ops->get_parent || !mux_ops->set_parent) {
+		if (!mux_ops->get_parent) {
 			clk = ERR_PTR(-EINVAL);
 			goto err;
 		}
@@ -170,7 +215,8 @@ struct clk *clk_register_composite(struct device *dev, const char *name,
 		composite->mux_hw = mux_hw;
 		composite->mux_ops = mux_ops;
 		clk_composite_ops->get_parent = clk_composite_get_parent;
-		clk_composite_ops->set_parent = clk_composite_set_parent;
+		if (mux_ops->set_parent)
+			clk_composite_ops->set_parent = clk_composite_set_parent;
 		if (mux_ops->determine_rate)
 			clk_composite_ops->determine_rate = clk_composite_determine_rate;
 	}
@@ -180,24 +226,27 @@ struct clk *clk_register_composite(struct device *dev, const char *name,
 			clk = ERR_PTR(-EINVAL);
 			goto err;
 		}
+		clk_composite_ops->recalc_rate = clk_composite_recalc_rate;
 
-		/* .round_rate is a prerequisite for .set_rate */
-		if (rate_ops->round_rate) {
-			clk_composite_ops->round_rate = clk_composite_round_rate;
-			if (rate_ops->set_rate) {
-				clk_composite_ops->set_rate = clk_composite_set_rate;
-			}
-		} else {
-			WARN(rate_ops->set_rate,
-				"%s: missing round_rate op is required\n",
-				__func__);
+		if (rate_ops->determine_rate)
+			clk_composite_ops->determine_rate =
+				clk_composite_determine_rate;
+		else if (rate_ops->round_rate)
+			clk_composite_ops->round_rate =
+				clk_composite_round_rate;
+
+		/* .set_rate requires either .round_rate or .determine_rate */
+		if (rate_ops->set_rate) {
+			if (rate_ops->determine_rate || rate_ops->round_rate)
+				clk_composite_ops->set_rate =
+						clk_composite_set_rate;
+			else
+				WARN(1, "%s: missing round_rate op is required\n",
+						__func__);
 		}
 
 		composite->rate_hw = rate_hw;
 		composite->rate_ops = rate_ops;
-		clk_composite_ops->recalc_rate = clk_composite_recalc_rate;
-		if (rate_ops->determine_rate)
-			clk_composite_ops->determine_rate = clk_composite_determine_rate;
 	}
 
 	if (gate_hw && gate_ops) {
diff --git a/drivers/clk/clk-conf.c b/drivers/clk/clk-conf.c
new file mode 100644
index 00000000000..aad4796aa3e
--- /dev/null
+++ b/drivers/clk/clk-conf.c
@@ -0,0 +1,144 @@
+/*
+ * Copyright (C) 2014 Samsung Electronics Co., Ltd.
+ * Sylwester Nawrocki <s.nawrocki@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/clk/clk-conf.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/printk.h>
+#include "clk.h"
+
+static int __set_clk_parents(struct device_node *node, bool clk_supplier)
+{
+	struct of_phandle_args clkspec;
+	int index, rc, num_parents;
+	struct clk *clk, *pclk;
+
+	num_parents = of_count_phandle_with_args(node, "assigned-clock-parents",
+						 "#clock-cells");
+	if (num_parents == -EINVAL)
+		pr_err("clk: invalid value of clock-parents property at %s\n",
+		       node->full_name);
+
+	for (index = 0; index < num_parents; index++) {
+		rc = of_parse_phandle_with_args(node, "assigned-clock-parents",
+					"#clock-cells",	index, &clkspec);
+		if (rc < 0) {
+			/* skip empty (null) phandles */
+			if (rc == -ENOENT)
+				continue;
+			else
+				return rc;
+		}
+		if (clkspec.np == node && !clk_supplier)
+			return 0;
+		pclk = of_clk_get_by_clkspec(&clkspec);
+		if (IS_ERR(pclk)) {
+			pr_warn("clk: couldn't get parent clock %d for %s\n",
+				index, node->full_name);
+			return PTR_ERR(pclk);
+		}
+
+		rc = of_parse_phandle_with_args(node, "assigned-clocks",
+					"#clock-cells", index, &clkspec);
+		if (rc < 0)
+			goto err;
+		if (clkspec.np == node && !clk_supplier) {
+			rc = 0;
+			goto err;
+		}
+		clk = of_clk_get_by_clkspec(&clkspec);
+		if (IS_ERR(clk)) {
+			pr_warn("clk: couldn't get parent clock %d for %s\n",
+				index, node->full_name);
+			rc = PTR_ERR(clk);
+			goto err;
+		}
+
+		rc = clk_set_parent(clk, pclk);
+		if (rc < 0)
+			pr_err("clk: failed to reparent %s to %s: %d\n",
+			       __clk_get_name(clk), __clk_get_name(pclk), rc);
+		clk_put(clk);
+		clk_put(pclk);
+	}
+	return 0;
+err:
+	clk_put(pclk);
+	return rc;
+}
+
+static int __set_clk_rates(struct device_node *node, bool clk_supplier)
+{
+	struct of_phandle_args clkspec;
+	struct property	*prop;
+	const __be32 *cur;
+	int rc, index = 0;
+	struct clk *clk;
+	u32 rate;
+
+	of_property_for_each_u32(node, "assigned-clock-rates", prop, cur, rate) {
+		if (rate) {
+			rc = of_parse_phandle_with_args(node, "assigned-clocks",
+					"#clock-cells",	index, &clkspec);
+			if (rc < 0) {
+				/* skip empty (null) phandles */
+				if (rc == -ENOENT)
+					continue;
+				else
+					return rc;
+			}
+			if (clkspec.np == node && !clk_supplier)
+				return 0;
+
+			clk = of_clk_get_by_clkspec(&clkspec);
+			if (IS_ERR(clk)) {
+				pr_warn("clk: couldn't get clock %d for %s\n",
+					index, node->full_name);
+				return PTR_ERR(clk);
+			}
+
+			rc = clk_set_rate(clk, rate);
+			if (rc < 0)
+				pr_err("clk: couldn't set %s clock rate: %d\n",
+				       __clk_get_name(clk), rc);
+			clk_put(clk);
+		}
+		index++;
+	}
+	return 0;
+}
+
+/**
+ * of_clk_set_defaults() - parse and set assigned clocks configuration
+ * @node: device node to apply clock settings for
+ * @clk_supplier: true if clocks supplied by @node should also be considered
+ *
+ * This function parses 'assigned-{clocks/clock-parents/clock-rates}' properties
+ * and sets any specified clock parents and rates. The @clk_supplier argument
+ * should be set to true if @node may be also a clock supplier of any clock
+ * listed in its 'assigned-clocks' or 'assigned-clock-parents' properties.
+ * If @clk_supplier is false the function exits returnning 0 as soon as it
+ * determines the @node is also a supplier of any of the clocks.
+ */
+int of_clk_set_defaults(struct device_node *node, bool clk_supplier)
+{
+	int rc;
+
+	if (!node)
+		return 0;
+
+	rc = __set_clk_parents(node, clk_supplier);
+	if (rc < 0)
+		return rc;
+
+	return __set_clk_rates(node, clk_supplier);
+}
+EXPORT_SYMBOL_GPL(of_clk_set_defaults);
diff --git a/drivers/clk/clk-palmas.c b/drivers/clk/clk-palmas.c
new file mode 100644
index 00000000000..781630e1372
--- /dev/null
+++ b/drivers/clk/clk-palmas.c
@@ -0,0 +1,307 @@
+/*
+ * Clock driver for Palmas device.
+ *
+ * Copyright (c) 2013, NVIDIA Corporation.
+ * Copyright (c) 2013-2014 Texas Instruments, Inc.
+ *
+ * Author:	Laxman Dewangan <ldewangan@nvidia.com>
+ *		Peter Ujfalusi <peter.ujfalusi@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
+ * whether express or implied; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/mfd/palmas.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#define PALMAS_CLOCK_DT_EXT_CONTROL_ENABLE1	1
+#define PALMAS_CLOCK_DT_EXT_CONTROL_ENABLE2	2
+#define PALMAS_CLOCK_DT_EXT_CONTROL_NSLEEP	3
+
+struct palmas_clk32k_desc {
+	const char *clk_name;
+	unsigned int control_reg;
+	unsigned int enable_mask;
+	unsigned int sleep_mask;
+	unsigned int sleep_reqstr_id;
+	int delay;
+};
+
+struct palmas_clock_info {
+	struct device *dev;
+	struct clk *clk;
+	struct clk_hw hw;
+	struct palmas *palmas;
+	struct palmas_clk32k_desc *clk_desc;
+	int ext_control_pin;
+};
+
+static inline struct palmas_clock_info *to_palmas_clks_info(struct clk_hw *hw)
+{
+	return container_of(hw, struct palmas_clock_info, hw);
+}
+
+static unsigned long palmas_clks_recalc_rate(struct clk_hw *hw,
+					     unsigned long parent_rate)
+{
+	return 32768;
+}
+
+static int palmas_clks_prepare(struct clk_hw *hw)
+{
+	struct palmas_clock_info *cinfo = to_palmas_clks_info(hw);
+	int ret;
+
+	ret = palmas_update_bits(cinfo->palmas, PALMAS_RESOURCE_BASE,
+				 cinfo->clk_desc->control_reg,
+				 cinfo->clk_desc->enable_mask,
+				 cinfo->clk_desc->enable_mask);
+	if (ret < 0)
+		dev_err(cinfo->dev, "Reg 0x%02x update failed, %d\n",
+			cinfo->clk_desc->control_reg, ret);
+	else if (cinfo->clk_desc->delay)
+		udelay(cinfo->clk_desc->delay);
+
+	return ret;
+}
+
+static void palmas_clks_unprepare(struct clk_hw *hw)
+{
+	struct palmas_clock_info *cinfo = to_palmas_clks_info(hw);
+	int ret;
+
+	/*
+	 * Clock can be disabled through external pin if it is externally
+	 * controlled.
+	 */
+	if (cinfo->ext_control_pin)
+		return;
+
+	ret = palmas_update_bits(cinfo->palmas, PALMAS_RESOURCE_BASE,
+				 cinfo->clk_desc->control_reg,
+				 cinfo->clk_desc->enable_mask, 0);
+	if (ret < 0)
+		dev_err(cinfo->dev, "Reg 0x%02x update failed, %d\n",
+			cinfo->clk_desc->control_reg, ret);
+}
+
+static int palmas_clks_is_prepared(struct clk_hw *hw)
+{
+	struct palmas_clock_info *cinfo = to_palmas_clks_info(hw);
+	int ret;
+	u32 val;
+
+	if (cinfo->ext_control_pin)
+		return 1;
+
+	ret = palmas_read(cinfo->palmas, PALMAS_RESOURCE_BASE,
+			  cinfo->clk_desc->control_reg, &val);
+	if (ret < 0) {
+		dev_err(cinfo->dev, "Reg 0x%02x read failed, %d\n",
+			cinfo->clk_desc->control_reg, ret);
+		return ret;
+	}
+	return !!(val & cinfo->clk_desc->enable_mask);
+}
+
+static struct clk_ops palmas_clks_ops = {
+	.prepare	= palmas_clks_prepare,
+	.unprepare	= palmas_clks_unprepare,
+	.is_prepared	= palmas_clks_is_prepared,
+	.recalc_rate	= palmas_clks_recalc_rate,
+};
+
+struct palmas_clks_of_match_data {
+	struct clk_init_data init;
+	struct palmas_clk32k_desc desc;
+};
+
+static struct palmas_clks_of_match_data palmas_of_clk32kg = {
+	.init = {
+		.name = "clk32kg",
+		.ops = &palmas_clks_ops,
+		.flags = CLK_IS_ROOT | CLK_IGNORE_UNUSED,
+	},
+	.desc = {
+		.clk_name = "clk32kg",
+		.control_reg = PALMAS_CLK32KG_CTRL,
+		.enable_mask = PALMAS_CLK32KG_CTRL_MODE_ACTIVE,
+		.sleep_mask = PALMAS_CLK32KG_CTRL_MODE_SLEEP,
+		.sleep_reqstr_id = PALMAS_EXTERNAL_REQSTR_ID_CLK32KG,
+		.delay = 200,
+	},
+};
+
+static struct palmas_clks_of_match_data palmas_of_clk32kgaudio = {
+	.init = {
+		.name = "clk32kgaudio",
+		.ops = &palmas_clks_ops,
+		.flags = CLK_IS_ROOT | CLK_IGNORE_UNUSED,
+	},
+	.desc = {
+		.clk_name = "clk32kgaudio",
+		.control_reg = PALMAS_CLK32KGAUDIO_CTRL,
+		.enable_mask = PALMAS_CLK32KG_CTRL_MODE_ACTIVE,
+		.sleep_mask = PALMAS_CLK32KG_CTRL_MODE_SLEEP,
+		.sleep_reqstr_id = PALMAS_EXTERNAL_REQSTR_ID_CLK32KGAUDIO,
+		.delay = 200,
+	},
+};
+
+static struct of_device_id palmas_clks_of_match[] = {
+	{
+		.compatible = "ti,palmas-clk32kg",
+		.data = &palmas_of_clk32kg,
+	},
+	{
+		.compatible = "ti,palmas-clk32kgaudio",
+		.data = &palmas_of_clk32kgaudio,
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, palmas_clks_of_match);
+
+static void palmas_clks_get_clk_data(struct platform_device *pdev,
+				     struct palmas_clock_info *cinfo)
+{
+	struct device_node *node = pdev->dev.of_node;
+	unsigned int prop;
+	int ret;
+
+	ret = of_property_read_u32(node, "ti,external-sleep-control",
+				   &prop);
+	if (ret)
+		return;
+
+	switch (prop) {
+	case PALMAS_CLOCK_DT_EXT_CONTROL_ENABLE1:
+		prop = PALMAS_EXT_CONTROL_ENABLE1;
+		break;
+	case PALMAS_CLOCK_DT_EXT_CONTROL_ENABLE2:
+		prop = PALMAS_EXT_CONTROL_ENABLE2;
+		break;
+	case PALMAS_CLOCK_DT_EXT_CONTROL_NSLEEP:
+		prop = PALMAS_EXT_CONTROL_NSLEEP;
+		break;
+	default:
+		dev_warn(&pdev->dev, "%s: Invalid ext control option: %u\n",
+			 node->name, prop);
+		prop = 0;
+		break;
+	}
+	cinfo->ext_control_pin = prop;
+}
+
+static int palmas_clks_init_configure(struct palmas_clock_info *cinfo)
+{
+	int ret;
+
+	ret = palmas_update_bits(cinfo->palmas, PALMAS_RESOURCE_BASE,
+				 cinfo->clk_desc->control_reg,
+				 cinfo->clk_desc->sleep_mask, 0);
+	if (ret < 0) {
+		dev_err(cinfo->dev, "Reg 0x%02x update failed, %d\n",
+			cinfo->clk_desc->control_reg, ret);
+		return ret;
+	}
+
+	if (cinfo->ext_control_pin) {
+		ret = clk_prepare(cinfo->clk);
+		if (ret < 0) {
+			dev_err(cinfo->dev, "Clock prep failed, %d\n", ret);
+			return ret;
+		}
+
+		ret = palmas_ext_control_req_config(cinfo->palmas,
+					cinfo->clk_desc->sleep_reqstr_id,
+					cinfo->ext_control_pin, true);
+		if (ret < 0) {
+			dev_err(cinfo->dev, "Ext config for %s failed, %d\n",
+				cinfo->clk_desc->clk_name, ret);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+static int palmas_clks_probe(struct platform_device *pdev)
+{
+	struct palmas *palmas = dev_get_drvdata(pdev->dev.parent);
+	struct device_node *node = pdev->dev.of_node;
+	struct palmas_clks_of_match_data *match_data;
+	const struct of_device_id *match;
+	struct palmas_clock_info *cinfo;
+	struct clk *clk;
+	int ret;
+
+	match = of_match_device(palmas_clks_of_match, &pdev->dev);
+	match_data = (struct palmas_clks_of_match_data *)match->data;
+
+	cinfo = devm_kzalloc(&pdev->dev, sizeof(*cinfo), GFP_KERNEL);
+	if (!cinfo)
+		return -ENOMEM;
+
+	palmas_clks_get_clk_data(pdev, cinfo);
+	platform_set_drvdata(pdev, cinfo);
+
+	cinfo->dev = &pdev->dev;
+	cinfo->palmas = palmas;
+
+	cinfo->clk_desc = &match_data->desc;
+	cinfo->hw.init = &match_data->init;
+	clk = devm_clk_register(&pdev->dev, &cinfo->hw);
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		dev_err(&pdev->dev, "Fail to register clock %s, %d\n",
+			match_data->desc.clk_name, ret);
+		return ret;
+	}
+
+	cinfo->clk = clk;
+	ret = palmas_clks_init_configure(cinfo);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Clock config failed, %d\n", ret);
+		return ret;
+	}
+
+	ret = of_clk_add_provider(node, of_clk_src_simple_get, cinfo->clk);
+	if (ret < 0)
+		dev_err(&pdev->dev, "Fail to add clock driver, %d\n", ret);
+	return ret;
+}
+
+static int palmas_clks_remove(struct platform_device *pdev)
+{
+	of_clk_del_provider(pdev->dev.of_node);
+	return 0;
+}
+
+static struct platform_driver palmas_clks_driver = {
+	.driver = {
+		.name = "palmas-clk",
+		.owner = THIS_MODULE,
+		.of_match_table = palmas_clks_of_match,
+	},
+	.probe = palmas_clks_probe,
+	.remove = palmas_clks_remove,
+};
+
+module_platform_driver(palmas_clks_driver);
+
+MODULE_DESCRIPTION("Clock driver for Palmas Series Devices");
+MODULE_ALIAS("platform:palmas-clk");
+MODULE_AUTHOR("Peter Ujfalusi <peter.ujfalusi@ti.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/clk-ppc-corenet.c b/drivers/clk/clk-ppc-corenet.c
index 8b284be4efa..8e58edfeeb3 100644
--- a/drivers/clk/clk-ppc-corenet.c
+++ b/drivers/clk/clk-ppc-corenet.c
@@ -291,7 +291,7 @@ static const struct of_device_id ppc_clk_ids[] __initconst = {
 	{}
 };
 
-static struct platform_driver ppc_corenet_clk_driver = {
+static struct platform_driver ppc_corenet_clk_driver __initdata = {
 	.driver = {
 		.name = "ppc_corenet_clock",
 		.owner = THIS_MODULE,
diff --git a/drivers/clk/clk-s2mps11.c b/drivers/clk/clk-s2mps11.c
index 9b7b5859a42..b7797fb12e1 100644
--- a/drivers/clk/clk-s2mps11.c
+++ b/drivers/clk/clk-s2mps11.c
@@ -46,7 +46,6 @@ struct s2mps11_clk {
 	struct clk *clk;
 	struct clk_lookup *lookup;
 	u32 mask;
-	bool enabled;
 	unsigned int reg;
 };
 
@@ -63,8 +62,6 @@ static int s2mps11_clk_prepare(struct clk_hw *hw)
 	ret = regmap_update_bits(s2mps11->iodev->regmap_pmic,
 				 s2mps11->reg,
 				 s2mps11->mask, s2mps11->mask);
-	if (!ret)
-		s2mps11->enabled = true;
 
 	return ret;
 }
@@ -76,32 +73,32 @@ static void s2mps11_clk_unprepare(struct clk_hw *hw)
 
 	ret = regmap_update_bits(s2mps11->iodev->regmap_pmic, s2mps11->reg,
 			   s2mps11->mask, ~s2mps11->mask);
-
-	if (!ret)
-		s2mps11->enabled = false;
 }
 
-static int s2mps11_clk_is_enabled(struct clk_hw *hw)
+static int s2mps11_clk_is_prepared(struct clk_hw *hw)
 {
+	int ret;
+	u32 val;
 	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
 
-	return s2mps11->enabled;
+	ret = regmap_read(s2mps11->iodev->regmap_pmic,
+				s2mps11->reg, &val);
+	if (ret < 0)
+		return -EINVAL;
+
+	return val & s2mps11->mask;
 }
 
 static unsigned long s2mps11_clk_recalc_rate(struct clk_hw *hw,
 					     unsigned long parent_rate)
 {
-	struct s2mps11_clk *s2mps11 = to_s2mps11_clk(hw);
-	if (s2mps11->enabled)
-		return 32768;
-	else
-		return 0;
+	return 32768;
 }
 
 static struct clk_ops s2mps11_clk_ops = {
 	.prepare	= s2mps11_clk_prepare,
 	.unprepare	= s2mps11_clk_unprepare,
-	.is_enabled	= s2mps11_clk_is_enabled,
+	.is_prepared	= s2mps11_clk_is_prepared,
 	.recalc_rate	= s2mps11_clk_recalc_rate,
 };
 
@@ -169,7 +166,6 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 	unsigned int s2mps11_reg;
 	struct clk_init_data *clks_init;
 	int i, ret = 0;
-	u32 val;
 
 	s2mps11_clks = devm_kzalloc(&pdev->dev, sizeof(*s2mps11_clk) *
 					S2MPS11_CLKS_NUM, GFP_KERNEL);
@@ -214,13 +210,6 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 		s2mps11_clk->mask = 1 << i;
 		s2mps11_clk->reg = s2mps11_reg;
 
-		ret = regmap_read(s2mps11_clk->iodev->regmap_pmic,
-				  s2mps11_clk->reg, &val);
-		if (ret < 0)
-			goto err_reg;
-
-		s2mps11_clk->enabled = val & s2mps11_clk->mask;
-
 		s2mps11_clk->clk = devm_clk_register(&pdev->dev,
 							&s2mps11_clk->hw);
 		if (IS_ERR(s2mps11_clk->clk)) {
@@ -230,16 +219,13 @@ static int s2mps11_clk_probe(struct platform_device *pdev)
 			goto err_reg;
 		}
 
-		s2mps11_clk->lookup = devm_kzalloc(&pdev->dev,
-					sizeof(struct clk_lookup), GFP_KERNEL);
+		s2mps11_clk->lookup = clkdev_alloc(s2mps11_clk->clk,
+					s2mps11_name(s2mps11_clk), NULL);
 		if (!s2mps11_clk->lookup) {
 			ret = -ENOMEM;
 			goto err_lup;
 		}
 
-		s2mps11_clk->lookup->con_id = s2mps11_name(s2mps11_clk);
-		s2mps11_clk->lookup->clk = s2mps11_clk->clk;
-
 		clkdev_add(s2mps11_clk->lookup);
 	}
 
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 8b73edef151..b76fa69b44c 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/clk-private.h>
+#include <linux/clk/clk-conf.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
@@ -98,9 +99,19 @@ static void clk_enable_unlock(unsigned long flags)
 #include <linux/debugfs.h>
 
 static struct dentry *rootdir;
-static struct dentry *orphandir;
 static int inited = 0;
 
+static struct hlist_head *all_lists[] = {
+	&clk_root_list,
+	&clk_orphan_list,
+	NULL,
+};
+
+static struct hlist_head *orphan_list[] = {
+	&clk_orphan_list,
+	NULL,
+};
+
 static void clk_summary_show_one(struct seq_file *s, struct clk *c, int level)
 {
 	if (!c)
@@ -130,17 +141,16 @@ static void clk_summary_show_subtree(struct seq_file *s, struct clk *c,
 static int clk_summary_show(struct seq_file *s, void *data)
 {
 	struct clk *c;
+	struct hlist_head **lists = (struct hlist_head **)s->private;
 
 	seq_puts(s, "   clock                         enable_cnt  prepare_cnt        rate   accuracy\n");
 	seq_puts(s, "--------------------------------------------------------------------------------\n");
 
 	clk_prepare_lock();
 
-	hlist_for_each_entry(c, &clk_root_list, child_node)
-		clk_summary_show_subtree(s, c, 0);
-
-	hlist_for_each_entry(c, &clk_orphan_list, child_node)
-		clk_summary_show_subtree(s, c, 0);
+	for (; *lists; lists++)
+		hlist_for_each_entry(c, *lists, child_node)
+			clk_summary_show_subtree(s, c, 0);
 
 	clk_prepare_unlock();
 
@@ -193,21 +203,19 @@ static int clk_dump(struct seq_file *s, void *data)
 {
 	struct clk *c;
 	bool first_node = true;
+	struct hlist_head **lists = (struct hlist_head **)s->private;
 
 	seq_printf(s, "{");
 
 	clk_prepare_lock();
 
-	hlist_for_each_entry(c, &clk_root_list, child_node) {
-		if (!first_node)
-			seq_printf(s, ",");
-		first_node = false;
-		clk_dump_subtree(s, c, 0);
-	}
-
-	hlist_for_each_entry(c, &clk_orphan_list, child_node) {
-		seq_printf(s, ",");
-		clk_dump_subtree(s, c, 0);
+	for (; *lists; lists++) {
+		hlist_for_each_entry(c, *lists, child_node) {
+			if (!first_node)
+				seq_puts(s, ",");
+			first_node = false;
+			clk_dump_subtree(s, c, 0);
+		}
 	}
 
 	clk_prepare_unlock();
@@ -276,9 +284,11 @@ static int clk_debug_create_one(struct clk *clk, struct dentry *pdentry)
 	if (!d)
 		goto err_out;
 
-	if (clk->ops->debug_init)
-		if (clk->ops->debug_init(clk->hw, clk->dentry))
+	if (clk->ops->debug_init) {
+		ret = clk->ops->debug_init(clk->hw, clk->dentry);
+		if (ret)
 			goto err_out;
+	}
 
 	ret = 0;
 	goto out;
@@ -305,7 +315,7 @@ static int clk_debug_create_subtree(struct clk *clk, struct dentry *pdentry)
 		goto out;
 
 	hlist_for_each_entry(child, &clk->children, child_node)
-		clk_debug_create_subtree(child, clk->dentry);
+		clk_debug_create_subtree(child, pdentry);
 
 	ret = 0;
 out:
@@ -325,31 +335,12 @@ out:
  */
 static int clk_debug_register(struct clk *clk)
 {
-	struct clk *parent;
-	struct dentry *pdentry;
 	int ret = 0;
 
 	if (!inited)
 		goto out;
 
-	parent = clk->parent;
-
-	/*
-	 * Check to see if a clk is a root clk.  Also check that it is
-	 * safe to add this clk to debugfs
-	 */
-	if (!parent)
-		if (clk->flags & CLK_IS_ROOT)
-			pdentry = rootdir;
-		else
-			pdentry = orphandir;
-	else
-		if (parent->dentry)
-			pdentry = parent->dentry;
-		else
-			goto out;
-
-	ret = clk_debug_create_subtree(clk, pdentry);
+	ret = clk_debug_create_subtree(clk, rootdir);
 
 out:
 	return ret;
@@ -370,38 +361,17 @@ static void clk_debug_unregister(struct clk *clk)
 	debugfs_remove_recursive(clk->dentry);
 }
 
-/**
- * clk_debug_reparent - reparent clk node in the debugfs clk tree
- * @clk: the clk being reparented
- * @new_parent: the new clk parent, may be NULL
- *
- * Rename clk entry in the debugfs clk tree if debugfs has been
- * initialized.  Otherwise it bails out early since the debugfs clk tree
- * will be created lazily by clk_debug_init as part of a late_initcall.
- *
- * Caller must hold prepare_lock.
- */
-static void clk_debug_reparent(struct clk *clk, struct clk *new_parent)
+struct dentry *clk_debugfs_add_file(struct clk *clk, char *name, umode_t mode,
+				void *data, const struct file_operations *fops)
 {
-	struct dentry *d;
-	struct dentry *new_parent_d;
-
-	if (!inited)
-		return;
+	struct dentry *d = NULL;
 
-	if (new_parent)
-		new_parent_d = new_parent->dentry;
-	else
-		new_parent_d = orphandir;
+	if (clk->dentry)
+		d = debugfs_create_file(name, mode, clk->dentry, data, fops);
 
-	d = debugfs_rename(clk->dentry->d_parent, clk->dentry,
-			new_parent_d, clk->name);
-	if (d)
-		clk->dentry = d;
-	else
-		pr_debug("%s: failed to rename debugfs entry for %s\n",
-				__func__, clk->name);
+	return d;
 }
+EXPORT_SYMBOL_GPL(clk_debugfs_add_file);
 
 /**
  * clk_debug_init - lazily create the debugfs clk tree visualization
@@ -425,19 +395,24 @@ static int __init clk_debug_init(void)
 	if (!rootdir)
 		return -ENOMEM;
 
-	d = debugfs_create_file("clk_summary", S_IRUGO, rootdir, NULL,
+	d = debugfs_create_file("clk_summary", S_IRUGO, rootdir, &all_lists,
 				&clk_summary_fops);
 	if (!d)
 		return -ENOMEM;
 
-	d = debugfs_create_file("clk_dump", S_IRUGO, rootdir, NULL,
+	d = debugfs_create_file("clk_dump", S_IRUGO, rootdir, &all_lists,
 				&clk_dump_fops);
 	if (!d)
 		return -ENOMEM;
 
-	orphandir = debugfs_create_dir("orphans", rootdir);
+	d = debugfs_create_file("clk_orphan_summary", S_IRUGO, rootdir,
+				&orphan_list, &clk_summary_fops);
+	if (!d)
+		return -ENOMEM;
 
-	if (!orphandir)
+	d = debugfs_create_file("clk_orphan_dump", S_IRUGO, rootdir,
+				&orphan_list, &clk_dump_fops);
+	if (!d)
 		return -ENOMEM;
 
 	clk_prepare_lock();
@@ -446,7 +421,7 @@ static int __init clk_debug_init(void)
 		clk_debug_create_subtree(clk, rootdir);
 
 	hlist_for_each_entry(clk, &clk_orphan_list, child_node)
-		clk_debug_create_subtree(clk, orphandir);
+		clk_debug_create_subtree(clk, rootdir);
 
 	inited = 1;
 
@@ -1284,9 +1259,6 @@ static void __clk_set_parent_after(struct clk *clk, struct clk *parent,
 		clk_disable(old_parent);
 		__clk_unprepare(old_parent);
 	}
-
-	/* update debugfs with new clk tree topology */
-	clk_debug_reparent(clk, parent);
 }
 
 static int __clk_set_parent(struct clk *clk, struct clk *parent, u8 p_index)
@@ -1683,7 +1655,6 @@ out:
 void __clk_reparent(struct clk *clk, struct clk *new_parent)
 {
 	clk_reparent(clk, new_parent);
-	clk_debug_reparent(clk, new_parent);
 	__clk_recalc_accuracies(clk);
 	__clk_recalc_rates(clk, POST_RATE_CHANGE);
 }
@@ -2414,6 +2385,7 @@ int of_clk_add_provider(struct device_node *np,
 			void *data)
 {
 	struct of_clk_provider *cp;
+	int ret;
 
 	cp = kzalloc(sizeof(struct of_clk_provider), GFP_KERNEL);
 	if (!cp)
@@ -2428,7 +2400,11 @@ int of_clk_add_provider(struct device_node *np,
 	mutex_unlock(&of_clk_mutex);
 	pr_debug("Added clock from %s\n", np->full_name);
 
-	return 0;
+	ret = of_clk_set_defaults(np, true);
+	if (ret < 0)
+		of_clk_del_provider(np);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(of_clk_add_provider);
 
@@ -2605,7 +2581,10 @@ void __init of_clk_init(const struct of_device_id *matches)
 		list_for_each_entry_safe(clk_provider, next,
 					&clk_provider_list, node) {
 			if (force || parent_ready(clk_provider->np)) {
+
 				clk_provider->clk_init_cb(clk_provider->np);
+				of_clk_set_defaults(clk_provider->np, true);
+
 				list_del(&clk_provider->node);
 				kfree(clk_provider);
 				is_init_done = true;
@@ -2620,7 +2599,6 @@ void __init of_clk_init(const struct of_device_id *matches)
 		 */
 		if (!is_init_done)
 			force = true;
-
 	}
 }
 #endif
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index f890b901c6b..da4bda8b7fc 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -101,8 +101,9 @@ struct clk *of_clk_get_by_name(struct device_node *np, const char *name)
 		if (!IS_ERR(clk))
 			break;
 		else if (name && index >= 0) {
-			pr_err("ERROR: could not get clock %s:%s(%i)\n",
-				np->full_name, name ? name : "", index);
+			if (PTR_ERR(clk) != -EPROBE_DEFER)
+				pr_err("ERROR: could not get clock %s:%s(%i)\n",
+					np->full_name, name ? name : "", index);
 			return clk;
 		}
 
diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 7f696b7d442..1107351ed34 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -4,6 +4,31 @@ config COMMON_CLK_QCOM
 	select REGMAP_MMIO
 	select RESET_CONTROLLER
 
+config APQ_GCC_8084
+	tristate "APQ8084 Global Clock Controller"
+	depends on COMMON_CLK_QCOM
+	help
+	  Support for the global clock controller on apq8084 devices.
+	  Say Y if you want to use peripheral devices such as UART, SPI,
+	  i2c, USB, SD/eMMC, SATA, PCIe, etc.
+
+config APQ_MMCC_8084
+	tristate "APQ8084 Multimedia Clock Controller"
+	select APQ_GCC_8084
+	depends on COMMON_CLK_QCOM
+	help
+	  Support for the multimedia clock controller on apq8084 devices.
+	  Say Y if you want to support multimedia devices such as display,
+	  graphics, video encode/decode, camera, etc.
+
+config IPQ_GCC_806X
+	tristate "IPQ806x Global Clock Controller"
+	depends on COMMON_CLK_QCOM
+	help
+	  Support for the global clock controller on ipq806x devices.
+	  Say Y if you want to use peripheral devices such as UART, SPI,
+	  i2c, USB, SD/eMMC, etc.
+
 config MSM_GCC_8660
 	tristate "MSM8660 Global Clock Controller"
 	depends on COMMON_CLK_QCOM
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index 689e05bf4f9..783cfb24faa 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -8,6 +8,9 @@ clk-qcom-y += clk-rcg2.o
 clk-qcom-y += clk-branch.o
 clk-qcom-y += reset.o
 
+obj-$(CONFIG_APQ_GCC_8084) += gcc-apq8084.o
+obj-$(CONFIG_APQ_MMCC_8084) += mmcc-apq8084.o
+obj-$(CONFIG_IPQ_GCC_806X) += gcc-ipq806x.o
 obj-$(CONFIG_MSM_GCC_8660) += gcc-msm8660.o
 obj-$(CONFIG_MSM_GCC_8960) += gcc-msm8960.o
 obj-$(CONFIG_MSM_GCC_8974) += gcc-msm8974.o
diff --git a/drivers/clk/qcom/clk-pll.c b/drivers/clk/qcom/clk-pll.c
index 0f927c53861..9db03d3b165 100644
--- a/drivers/clk/qcom/clk-pll.c
+++ b/drivers/clk/qcom/clk-pll.c
@@ -166,7 +166,7 @@ const struct clk_ops clk_pll_vote_ops = {
 EXPORT_SYMBOL_GPL(clk_pll_vote_ops);
 
 static void
-clk_pll_set_fsm_mode(struct clk_pll *pll, struct regmap *regmap)
+clk_pll_set_fsm_mode(struct clk_pll *pll, struct regmap *regmap, u8 lock_count)
 {
 	u32 val;
 	u32 mask;
@@ -175,7 +175,7 @@ clk_pll_set_fsm_mode(struct clk_pll *pll, struct regmap *regmap)
 	regmap_update_bits(regmap, pll->mode_reg, PLL_VOTE_FSM_RESET, 0);
 
 	/* Program bias count and lock count */
-	val = 1 << PLL_BIAS_COUNT_SHIFT;
+	val = 1 << PLL_BIAS_COUNT_SHIFT | lock_count << PLL_LOCK_COUNT_SHIFT;
 	mask = PLL_BIAS_COUNT_MASK << PLL_BIAS_COUNT_SHIFT;
 	mask |= PLL_LOCK_COUNT_MASK << PLL_LOCK_COUNT_SHIFT;
 	regmap_update_bits(regmap, pll->mode_reg, mask, val);
@@ -212,11 +212,20 @@ static void clk_pll_configure(struct clk_pll *pll, struct regmap *regmap,
 	regmap_update_bits(regmap, pll->config_reg, mask, val);
 }
 
+void clk_pll_configure_sr(struct clk_pll *pll, struct regmap *regmap,
+		const struct pll_config *config, bool fsm_mode)
+{
+	clk_pll_configure(pll, regmap, config);
+	if (fsm_mode)
+		clk_pll_set_fsm_mode(pll, regmap, 8);
+}
+EXPORT_SYMBOL_GPL(clk_pll_configure_sr);
+
 void clk_pll_configure_sr_hpm_lp(struct clk_pll *pll, struct regmap *regmap,
 		const struct pll_config *config, bool fsm_mode)
 {
 	clk_pll_configure(pll, regmap, config);
 	if (fsm_mode)
-		clk_pll_set_fsm_mode(pll, regmap);
+		clk_pll_set_fsm_mode(pll, regmap, 0);
 }
 EXPORT_SYMBOL_GPL(clk_pll_configure_sr_hpm_lp);
diff --git a/drivers/clk/qcom/clk-pll.h b/drivers/clk/qcom/clk-pll.h
index 0775a99ca76..3003e996247 100644
--- a/drivers/clk/qcom/clk-pll.h
+++ b/drivers/clk/qcom/clk-pll.h
@@ -60,6 +60,8 @@ struct pll_config {
 	u32 aux_output_mask;
 };
 
+void clk_pll_configure_sr(struct clk_pll *pll, struct regmap *regmap,
+		const struct pll_config *config, bool fsm_mode);
 void clk_pll_configure_sr_hpm_lp(struct clk_pll *pll, struct regmap *regmap,
 		const struct pll_config *config, bool fsm_mode);
 
diff --git a/drivers/clk/qcom/clk-rcg.c b/drivers/clk/qcom/clk-rcg.c
index abfc2b675ae..b638c5846db 100644
--- a/drivers/clk/qcom/clk-rcg.c
+++ b/drivers/clk/qcom/clk-rcg.c
@@ -417,20 +417,25 @@ static long clk_dyn_rcg_determine_rate(struct clk_hw *hw, unsigned long rate,
 	return _freq_tbl_determine_rate(hw, rcg->freq_tbl, rate, p_rate, p);
 }
 
-static int clk_rcg_set_rate(struct clk_hw *hw, unsigned long rate,
-			    unsigned long parent_rate)
+static long clk_rcg_bypass_determine_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long *p_rate, struct clk **p)
 {
 	struct clk_rcg *rcg = to_clk_rcg(hw);
-	const struct freq_tbl *f;
+	const struct freq_tbl *f = rcg->freq_tbl;
+
+	*p = clk_get_parent_by_index(hw->clk, f->src);
+	*p_rate = __clk_round_rate(*p, rate);
+
+	return *p_rate;
+}
+
+static int __clk_rcg_set_rate(struct clk_rcg *rcg, const struct freq_tbl *f)
+{
 	u32 ns, md, ctl;
 	struct mn *mn = &rcg->mn;
 	u32 mask = 0;
 	unsigned int reset_reg;
 
-	f = find_freq(rcg->freq_tbl, rate);
-	if (!f)
-		return -EINVAL;
-
 	if (rcg->mn.reset_in_cc)
 		reset_reg = rcg->clkr.enable_reg;
 	else
@@ -466,6 +471,27 @@ static int clk_rcg_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
+static int clk_rcg_set_rate(struct clk_hw *hw, unsigned long rate,
+			    unsigned long parent_rate)
+{
+	struct clk_rcg *rcg = to_clk_rcg(hw);
+	const struct freq_tbl *f;
+
+	f = find_freq(rcg->freq_tbl, rate);
+	if (!f)
+		return -EINVAL;
+
+	return __clk_rcg_set_rate(rcg, f);
+}
+
+static int clk_rcg_bypass_set_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long parent_rate)
+{
+	struct clk_rcg *rcg = to_clk_rcg(hw);
+
+	return __clk_rcg_set_rate(rcg, rcg->freq_tbl);
+}
+
 static int __clk_dyn_rcg_set_rate(struct clk_hw *hw, unsigned long rate)
 {
 	struct clk_dyn_rcg *rcg = to_clk_dyn_rcg(hw);
@@ -503,6 +529,17 @@ const struct clk_ops clk_rcg_ops = {
 };
 EXPORT_SYMBOL_GPL(clk_rcg_ops);
 
+const struct clk_ops clk_rcg_bypass_ops = {
+	.enable = clk_enable_regmap,
+	.disable = clk_disable_regmap,
+	.get_parent = clk_rcg_get_parent,
+	.set_parent = clk_rcg_set_parent,
+	.recalc_rate = clk_rcg_recalc_rate,
+	.determine_rate = clk_rcg_bypass_determine_rate,
+	.set_rate = clk_rcg_bypass_set_rate,
+};
+EXPORT_SYMBOL_GPL(clk_rcg_bypass_ops);
+
 const struct clk_ops clk_dyn_rcg_ops = {
 	.enable = clk_enable_regmap,
 	.is_enabled = clk_is_enabled_regmap,
diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h
index b9ec11dfd1b..ba0523cefd2 100644
--- a/drivers/clk/qcom/clk-rcg.h
+++ b/drivers/clk/qcom/clk-rcg.h
@@ -95,6 +95,7 @@ struct clk_rcg {
 };
 
 extern const struct clk_ops clk_rcg_ops;
+extern const struct clk_ops clk_rcg_bypass_ops;
 
 #define to_clk_rcg(_hw) container_of(to_clk_regmap(_hw), struct clk_rcg, clkr)
 
diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c
index 9b5a1cfc6b9..eeb3eea01f4 100644
--- a/drivers/clk/qcom/common.c
+++ b/drivers/clk/qcom/common.c
@@ -27,30 +27,35 @@ struct qcom_cc {
 	struct clk *clks[];
 };
 
-int qcom_cc_probe(struct platform_device *pdev, const struct qcom_cc_desc *desc)
+struct regmap *
+qcom_cc_map(struct platform_device *pdev, const struct qcom_cc_desc *desc)
 {
 	void __iomem *base;
 	struct resource *res;
+	struct device *dev = &pdev->dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return ERR_CAST(base);
+
+	return devm_regmap_init_mmio(dev, base, desc->config);
+}
+EXPORT_SYMBOL_GPL(qcom_cc_map);
+
+int qcom_cc_really_probe(struct platform_device *pdev,
+			 const struct qcom_cc_desc *desc, struct regmap *regmap)
+{
 	int i, ret;
 	struct device *dev = &pdev->dev;
 	struct clk *clk;
 	struct clk_onecell_data *data;
 	struct clk **clks;
-	struct regmap *regmap;
 	struct qcom_reset_controller *reset;
 	struct qcom_cc *cc;
 	size_t num_clks = desc->num_clks;
 	struct clk_regmap **rclks = desc->clks;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(base))
-		return PTR_ERR(base);
-
-	regmap = devm_regmap_init_mmio(dev, base, desc->config);
-	if (IS_ERR(regmap))
-		return PTR_ERR(regmap);
-
 	cc = devm_kzalloc(dev, sizeof(*cc) + sizeof(*clks) * num_clks,
 			  GFP_KERNEL);
 	if (!cc)
@@ -91,6 +96,18 @@ int qcom_cc_probe(struct platform_device *pdev, const struct qcom_cc_desc *desc)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(qcom_cc_really_probe);
+
+int qcom_cc_probe(struct platform_device *pdev, const struct qcom_cc_desc *desc)
+{
+	struct regmap *regmap;
+
+	regmap = qcom_cc_map(pdev, desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	return qcom_cc_really_probe(pdev, desc, regmap);
+}
 EXPORT_SYMBOL_GPL(qcom_cc_probe);
 
 void qcom_cc_remove(struct platform_device *pdev)
diff --git a/drivers/clk/qcom/common.h b/drivers/clk/qcom/common.h
index 2c3cfc86034..2765e9d3da9 100644
--- a/drivers/clk/qcom/common.h
+++ b/drivers/clk/qcom/common.h
@@ -17,6 +17,7 @@ struct platform_device;
 struct regmap_config;
 struct clk_regmap;
 struct qcom_reset_map;
+struct regmap;
 
 struct qcom_cc_desc {
 	const struct regmap_config *config;
@@ -26,6 +27,11 @@ struct qcom_cc_desc {
 	size_t num_resets;
 };
 
+extern struct regmap *qcom_cc_map(struct platform_device *pdev,
+				  const struct qcom_cc_desc *desc);
+extern int qcom_cc_really_probe(struct platform_device *pdev,
+				const struct qcom_cc_desc *desc,
+				struct regmap *regmap);
 extern int qcom_cc_probe(struct platform_device *pdev,
 			 const struct qcom_cc_desc *desc);
 
diff --git a/drivers/clk/qcom/gcc-apq8084.c b/drivers/clk/qcom/gcc-apq8084.c
new file mode 100644
index 00000000000..ee52eb1c838
--- /dev/null
+++ b/drivers/clk/qcom/gcc-apq8084.c
@@ -0,0 +1,3611 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/clk-provider.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+
+#include <dt-bindings/clock/qcom,gcc-apq8084.h>
+#include <dt-bindings/reset/qcom,gcc-apq8084.h>
+
+#include "common.h"
+#include "clk-regmap.h"
+#include "clk-pll.h"
+#include "clk-rcg.h"
+#include "clk-branch.h"
+#include "reset.h"
+
+#define P_XO	0
+#define P_GPLL0	1
+#define P_GPLL1	1
+#define P_GPLL4	2
+#define P_PCIE_0_1_PIPE_CLK 1
+#define P_SATA_ASIC0_CLK 1
+#define P_SATA_RX_CLK 1
+#define P_SLEEP_CLK 1
+
+static const u8 gcc_xo_gpll0_map[] = {
+	[P_XO]		= 0,
+	[P_GPLL0]	= 1,
+};
+
+static const char *gcc_xo_gpll0[] = {
+	"xo",
+	"gpll0_vote",
+};
+
+static const u8 gcc_xo_gpll0_gpll4_map[] = {
+	[P_XO]		= 0,
+	[P_GPLL0]	= 1,
+	[P_GPLL4]	= 5,
+};
+
+static const char *gcc_xo_gpll0_gpll4[] = {
+	"xo",
+	"gpll0_vote",
+	"gpll4_vote",
+};
+
+static const u8 gcc_xo_sata_asic0_map[] = {
+	[P_XO]			= 0,
+	[P_SATA_ASIC0_CLK]	= 2,
+};
+
+static const char *gcc_xo_sata_asic0[] = {
+	"xo",
+	"sata_asic0_clk",
+};
+
+static const u8 gcc_xo_sata_rx_map[] = {
+	[P_XO]			= 0,
+	[P_SATA_RX_CLK]		= 2,
+};
+
+static const char *gcc_xo_sata_rx[] = {
+	"xo",
+	"sata_rx_clk",
+};
+
+static const u8 gcc_xo_pcie_map[] = {
+	[P_XO]			= 0,
+	[P_PCIE_0_1_PIPE_CLK]	= 2,
+};
+
+static const char *gcc_xo_pcie[] = {
+	"xo",
+	"pcie_pipe",
+};
+
+static const u8 gcc_xo_pcie_sleep_map[] = {
+	[P_XO]			= 0,
+	[P_SLEEP_CLK]		= 6,
+};
+
+static const char *gcc_xo_pcie_sleep[] = {
+	"xo",
+	"sleep_clk_src",
+};
+
+#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
+
+static struct clk_pll gpll0 = {
+	.l_reg = 0x0004,
+	.m_reg = 0x0008,
+	.n_reg = 0x000c,
+	.config_reg = 0x0014,
+	.mode_reg = 0x0000,
+	.status_reg = 0x001c,
+	.status_bit = 17,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll0",
+		.parent_names = (const char *[]){ "xo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_regmap gpll0_vote = {
+	.enable_reg = 0x1480,
+	.enable_mask = BIT(0),
+	.hw.init = &(struct clk_init_data){
+		.name = "gpll0_vote",
+		.parent_names = (const char *[]){ "gpll0" },
+		.num_parents = 1,
+		.ops = &clk_pll_vote_ops,
+	},
+};
+
+static struct clk_rcg2 config_noc_clk_src = {
+	.cmd_rcgr = 0x0150,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "config_noc_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 periph_noc_clk_src = {
+	.cmd_rcgr = 0x0190,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "periph_noc_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 system_noc_clk_src = {
+	.cmd_rcgr = 0x0120,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "system_noc_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_pll gpll1 = {
+	.l_reg = 0x0044,
+	.m_reg = 0x0048,
+	.n_reg = 0x004c,
+	.config_reg = 0x0054,
+	.mode_reg = 0x0040,
+	.status_reg = 0x005c,
+	.status_bit = 17,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll1",
+		.parent_names = (const char *[]){ "xo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_regmap gpll1_vote = {
+	.enable_reg = 0x1480,
+	.enable_mask = BIT(1),
+	.hw.init = &(struct clk_init_data){
+		.name = "gpll1_vote",
+		.parent_names = (const char *[]){ "gpll1" },
+		.num_parents = 1,
+		.ops = &clk_pll_vote_ops,
+	},
+};
+
+static struct clk_pll gpll4 = {
+	.l_reg = 0x1dc4,
+	.m_reg = 0x1dc8,
+	.n_reg = 0x1dcc,
+	.config_reg = 0x1dd4,
+	.mode_reg = 0x1dc0,
+	.status_reg = 0x1ddc,
+	.status_bit = 17,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll4",
+		.parent_names = (const char *[]){ "xo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_regmap gpll4_vote = {
+	.enable_reg = 0x1480,
+	.enable_mask = BIT(4),
+	.hw.init = &(struct clk_init_data){
+		.name = "gpll4_vote",
+		.parent_names = (const char *[]){ "gpll4" },
+		.num_parents = 1,
+		.ops = &clk_pll_vote_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_ufs_axi_clk[] = {
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(240000000, P_GPLL0, 2.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 ufs_axi_clk_src = {
+	.cmd_rcgr = 0x1d64,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_ufs_axi_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ufs_axi_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb30_master_clk[] = {
+	F(125000000, P_GPLL0, 1, 5, 24),
+	{ }
+};
+
+static struct clk_rcg2 usb30_master_clk_src = {
+	.cmd_rcgr = 0x03d4,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_usb30_master_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb30_master_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb30_sec_master_clk[] = {
+	F(125000000, P_GPLL0, 1, 5, 24),
+	{ }
+};
+
+static struct clk_rcg2 usb30_sec_master_clk_src = {
+	.cmd_rcgr = 0x1bd4,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_usb30_sec_master_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb30_sec_master_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_usb30_sec_mock_utmi_clk = {
+	.halt_reg = 0x1bd0,
+	.clkr = {
+		.enable_reg = 0x1bd0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_sec_mock_utmi_clk",
+			.parent_names = (const char *[]){
+				"usb30_sec_mock_utmi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_sec_sleep_clk = {
+	.halt_reg = 0x1bcc,
+	.clkr = {
+		.enable_reg = 0x1bcc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_sec_sleep_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(50000000, P_GPLL0, 12, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 blsp1_qup1_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x0660,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup1_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk[] = {
+	F(960000, P_XO, 10, 1, 2),
+	F(4800000, P_XO, 4, 0, 0),
+	F(9600000, P_XO, 2, 0, 0),
+	F(15000000, P_GPLL0, 10, 1, 4),
+	F(19200000, P_XO, 1, 0, 0),
+	F(25000000, P_GPLL0, 12, 1, 2),
+	F(50000000, P_GPLL0, 12, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 blsp1_qup1_spi_apps_clk_src = {
+	.cmd_rcgr = 0x064c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup1_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup2_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x06e0,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup2_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup2_spi_apps_clk_src = {
+	.cmd_rcgr = 0x06cc,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup2_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup3_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x0760,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup3_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup3_spi_apps_clk_src = {
+	.cmd_rcgr = 0x074c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup3_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup4_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x07e0,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup4_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup4_spi_apps_clk_src = {
+	.cmd_rcgr = 0x07cc,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup4_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup5_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x0860,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup5_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup5_spi_apps_clk_src = {
+	.cmd_rcgr = 0x084c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup5_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup6_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x08e0,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup6_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup6_spi_apps_clk_src = {
+	.cmd_rcgr = 0x08cc,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup6_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_blsp1_2_uart1_6_apps_clk[] = {
+	F(3686400, P_GPLL0, 1, 96, 15625),
+	F(7372800, P_GPLL0, 1, 192, 15625),
+	F(14745600, P_GPLL0, 1, 384, 15625),
+	F(16000000, P_GPLL0, 5, 2, 15),
+	F(19200000, P_XO, 1, 0, 0),
+	F(24000000, P_GPLL0, 5, 1, 5),
+	F(32000000, P_GPLL0, 1, 4, 75),
+	F(40000000, P_GPLL0, 15, 0, 0),
+	F(46400000, P_GPLL0, 1, 29, 375),
+	F(48000000, P_GPLL0, 12.5, 0, 0),
+	F(51200000, P_GPLL0, 1, 32, 375),
+	F(56000000, P_GPLL0, 1, 7, 75),
+	F(58982400, P_GPLL0, 1, 1536, 15625),
+	F(60000000, P_GPLL0, 10, 0, 0),
+	F(63160000, P_GPLL0, 9.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 blsp1_uart1_apps_clk_src = {
+	.cmd_rcgr = 0x068c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart1_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart2_apps_clk_src = {
+	.cmd_rcgr = 0x070c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart2_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart3_apps_clk_src = {
+	.cmd_rcgr = 0x078c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart3_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart4_apps_clk_src = {
+	.cmd_rcgr = 0x080c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart4_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart5_apps_clk_src = {
+	.cmd_rcgr = 0x088c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart5_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart6_apps_clk_src = {
+	.cmd_rcgr = 0x090c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart6_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup1_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x09a0,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup1_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup1_spi_apps_clk_src = {
+	.cmd_rcgr = 0x098c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup1_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup2_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x0a20,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup2_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup2_spi_apps_clk_src = {
+	.cmd_rcgr = 0x0a0c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup2_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup3_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x0aa0,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup3_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup3_spi_apps_clk_src = {
+	.cmd_rcgr = 0x0a8c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup3_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup4_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x0b20,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup4_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup4_spi_apps_clk_src = {
+	.cmd_rcgr = 0x0b0c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup4_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup5_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x0ba0,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup5_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup5_spi_apps_clk_src = {
+	.cmd_rcgr = 0x0b8c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup5_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup6_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x0c20,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_i2c_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup6_i2c_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_qup6_spi_apps_clk_src = {
+	.cmd_rcgr = 0x0c0c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_qup1_6_spi_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_qup6_spi_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_uart1_apps_clk_src = {
+	.cmd_rcgr = 0x09cc,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_uart1_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_uart2_apps_clk_src = {
+	.cmd_rcgr = 0x0a4c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_uart2_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_uart3_apps_clk_src = {
+	.cmd_rcgr = 0x0acc,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_uart3_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_uart4_apps_clk_src = {
+	.cmd_rcgr = 0x0b4c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_uart4_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_uart5_apps_clk_src = {
+	.cmd_rcgr = 0x0bcc,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_uart5_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp2_uart6_apps_clk_src = {
+	.cmd_rcgr = 0x0c4c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_blsp1_2_uart1_6_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp2_uart6_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_ce1_clk[] = {
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(85710000, P_GPLL0, 7, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(171430000, P_GPLL0, 3.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 ce1_clk_src = {
+	.cmd_rcgr = 0x1050,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_ce1_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ce1_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_ce2_clk[] = {
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(85710000, P_GPLL0, 7, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(171430000, P_GPLL0, 3.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 ce2_clk_src = {
+	.cmd_rcgr = 0x1090,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_ce2_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ce2_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_ce3_clk[] = {
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(85710000, P_GPLL0, 7, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(171430000, P_GPLL0, 3.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 ce3_clk_src = {
+	.cmd_rcgr = 0x1d10,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_ce3_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ce3_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_gp_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(200000000, P_GPLL0, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gp1_clk_src = {
+	.cmd_rcgr = 0x1904,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_gp_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gp1_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gp2_clk_src = {
+	.cmd_rcgr = 0x1944,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_gp_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gp2_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gp3_clk_src = {
+	.cmd_rcgr = 0x1984,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_gp_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gp3_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_pcie_0_1_aux_clk[] = {
+	F(1010000, P_XO, 1, 1, 19),
+	{ }
+};
+
+static struct clk_rcg2 pcie_0_aux_clk_src = {
+	.cmd_rcgr = 0x1b2c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_pcie_sleep_map,
+	.freq_tbl = ftbl_gcc_pcie_0_1_aux_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie_0_aux_clk_src",
+		.parent_names = gcc_xo_pcie_sleep,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 pcie_1_aux_clk_src = {
+	.cmd_rcgr = 0x1bac,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_pcie_sleep_map,
+	.freq_tbl = ftbl_gcc_pcie_0_1_aux_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie_1_aux_clk_src",
+		.parent_names = gcc_xo_pcie_sleep,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_pcie_0_1_pipe_clk[] = {
+	F(125000000, P_PCIE_0_1_PIPE_CLK, 1, 0, 0),
+	F(250000000, P_PCIE_0_1_PIPE_CLK, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 pcie_0_pipe_clk_src = {
+	.cmd_rcgr = 0x1b18,
+	.hid_width = 5,
+	.parent_map = gcc_xo_pcie_map,
+	.freq_tbl = ftbl_gcc_pcie_0_1_pipe_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie_0_pipe_clk_src",
+		.parent_names = gcc_xo_pcie,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 pcie_1_pipe_clk_src = {
+	.cmd_rcgr = 0x1b98,
+	.hid_width = 5,
+	.parent_map = gcc_xo_pcie_map,
+	.freq_tbl = ftbl_gcc_pcie_0_1_pipe_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie_1_pipe_clk_src",
+		.parent_names = gcc_xo_pcie,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_pdm2_clk[] = {
+	F(60000000, P_GPLL0, 10, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 pdm2_clk_src = {
+	.cmd_rcgr = 0x0cd0,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_pdm2_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pdm2_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_sata_asic0_clk[] = {
+	F(75000000, P_SATA_ASIC0_CLK, 1, 0, 0),
+	F(150000000, P_SATA_ASIC0_CLK, 1, 0, 0),
+	F(300000000, P_SATA_ASIC0_CLK, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 sata_asic0_clk_src = {
+	.cmd_rcgr = 0x1c94,
+	.hid_width = 5,
+	.parent_map = gcc_xo_sata_asic0_map,
+	.freq_tbl = ftbl_gcc_sata_asic0_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sata_asic0_clk_src",
+		.parent_names = gcc_xo_sata_asic0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_sata_pmalive_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 sata_pmalive_clk_src = {
+	.cmd_rcgr = 0x1c80,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_sata_pmalive_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sata_pmalive_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_sata_rx_clk[] = {
+	F(75000000, P_SATA_RX_CLK, 1, 0, 0),
+	F(150000000, P_SATA_RX_CLK, 1, 0, 0),
+	F(300000000, P_SATA_RX_CLK, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 sata_rx_clk_src = {
+	.cmd_rcgr = 0x1ca8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_sata_rx_map,
+	.freq_tbl = ftbl_gcc_sata_rx_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sata_rx_clk_src",
+		.parent_names = gcc_xo_sata_rx,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_sata_rx_oob_clk[] = {
+	F(100000000, P_GPLL0, 6, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 sata_rx_oob_clk_src = {
+	.cmd_rcgr = 0x1c5c,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_sata_rx_oob_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sata_rx_oob_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_sdcc1_4_apps_clk[] = {
+	F(144000, P_XO, 16, 3, 25),
+	F(400000, P_XO, 12, 1, 4),
+	F(20000000, P_GPLL0, 15, 1, 2),
+	F(25000000, P_GPLL0, 12, 1, 2),
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(192000000, P_GPLL4, 4, 0, 0),
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(384000000, P_GPLL4, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 sdcc1_apps_clk_src = {
+	.cmd_rcgr = 0x04d0,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll4_map,
+	.freq_tbl = ftbl_gcc_sdcc1_4_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sdcc1_apps_clk_src",
+		.parent_names = gcc_xo_gpll0_gpll4,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 sdcc2_apps_clk_src = {
+	.cmd_rcgr = 0x0510,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_sdcc1_4_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sdcc2_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 sdcc3_apps_clk_src = {
+	.cmd_rcgr = 0x0550,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_sdcc1_4_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sdcc3_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 sdcc4_apps_clk_src = {
+	.cmd_rcgr = 0x0590,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_sdcc1_4_apps_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sdcc4_apps_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_tsif_ref_clk[] = {
+	F(105000, P_XO, 2, 1, 91),
+	{ }
+};
+
+static struct clk_rcg2 tsif_ref_clk_src = {
+	.cmd_rcgr = 0x0d90,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_tsif_ref_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "tsif_ref_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb30_mock_utmi_clk[] = {
+	F(60000000, P_GPLL0, 10, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 usb30_mock_utmi_clk_src = {
+	.cmd_rcgr = 0x03e8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_usb30_mock_utmi_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb30_mock_utmi_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb30_sec_mock_utmi_clk[] = {
+	F(125000000, P_GPLL0, 1, 5, 24),
+	{ }
+};
+
+static struct clk_rcg2 usb30_sec_mock_utmi_clk_src = {
+	.cmd_rcgr = 0x1be8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_usb30_sec_mock_utmi_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb30_sec_mock_utmi_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb_hs_system_clk[] = {
+	F(75000000, P_GPLL0, 8, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 usb_hs_system_clk_src = {
+	.cmd_rcgr = 0x0490,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_usb_hs_system_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb_hs_system_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb_hsic_clk[] = {
+	F(480000000, P_GPLL1, 1, 0, 0),
+	{ }
+};
+
+static u8 usb_hsic_clk_src_map[] = {
+	[P_XO]		= 0,
+	[P_GPLL1]	= 4,
+};
+
+static struct clk_rcg2 usb_hsic_clk_src = {
+	.cmd_rcgr = 0x0440,
+	.hid_width = 5,
+	.parent_map = usb_hsic_clk_src_map,
+	.freq_tbl = ftbl_gcc_usb_hsic_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb_hsic_clk_src",
+		.parent_names = (const char *[]){
+			"xo",
+			"gpll1_vote",
+		},
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb_hsic_ahb_clk_src[] = {
+	F(60000000, P_GPLL1, 8, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 usb_hsic_ahb_clk_src = {
+	.cmd_rcgr = 0x046c,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = usb_hsic_clk_src_map,
+	.freq_tbl = ftbl_gcc_usb_hsic_ahb_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb_hsic_ahb_clk_src",
+		.parent_names = (const char *[]){
+			"xo",
+			"gpll1_vote",
+		},
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb_hsic_io_cal_clk[] = {
+	F(9600000, P_XO, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 usb_hsic_io_cal_clk_src = {
+	.cmd_rcgr = 0x0458,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_usb_hsic_io_cal_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb_hsic_io_cal_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 1,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_usb_hsic_mock_utmi_clk = {
+	.halt_reg = 0x1f14,
+	.clkr = {
+		.enable_reg = 0x1f14,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_hsic_mock_utmi_clk",
+			.parent_names = (const char *[]){
+				"usb_hsic_mock_utmi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb_hsic_mock_utmi_clk[] = {
+	F(60000000, P_GPLL0, 10, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 usb_hsic_mock_utmi_clk_src = {
+	.cmd_rcgr = 0x1f00,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_usb_hsic_mock_utmi_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb_hsic_mock_utmi_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 1,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gcc_usb_hsic_system_clk[] = {
+	F(75000000, P_GPLL0, 8, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 usb_hsic_system_clk_src = {
+	.cmd_rcgr = 0x041c,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.freq_tbl = ftbl_gcc_usb_hsic_system_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb_hsic_system_clk_src",
+		.parent_names = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_bam_dma_ahb_clk = {
+	.halt_reg = 0x0d44,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(12),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_bam_dma_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_ahb_clk = {
+	.halt_reg = 0x05c4,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(17),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup1_i2c_apps_clk = {
+	.halt_reg = 0x0648,
+	.clkr = {
+		.enable_reg = 0x0648,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup1_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup1_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup1_spi_apps_clk = {
+	.halt_reg = 0x0644,
+	.clkr = {
+		.enable_reg = 0x0644,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup1_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup1_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup2_i2c_apps_clk = {
+	.halt_reg = 0x06c8,
+	.clkr = {
+		.enable_reg = 0x06c8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup2_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup2_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup2_spi_apps_clk = {
+	.halt_reg = 0x06c4,
+	.clkr = {
+		.enable_reg = 0x06c4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup2_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup2_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup3_i2c_apps_clk = {
+	.halt_reg = 0x0748,
+	.clkr = {
+		.enable_reg = 0x0748,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup3_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup3_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup3_spi_apps_clk = {
+	.halt_reg = 0x0744,
+	.clkr = {
+		.enable_reg = 0x0744,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup3_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup3_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup4_i2c_apps_clk = {
+	.halt_reg = 0x07c8,
+	.clkr = {
+		.enable_reg = 0x07c8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup4_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup4_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup4_spi_apps_clk = {
+	.halt_reg = 0x07c4,
+	.clkr = {
+		.enable_reg = 0x07c4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup4_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup4_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup5_i2c_apps_clk = {
+	.halt_reg = 0x0848,
+	.clkr = {
+		.enable_reg = 0x0848,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup5_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup5_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup5_spi_apps_clk = {
+	.halt_reg = 0x0844,
+	.clkr = {
+		.enable_reg = 0x0844,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup5_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup5_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup6_i2c_apps_clk = {
+	.halt_reg = 0x08c8,
+	.clkr = {
+		.enable_reg = 0x08c8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup6_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup6_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup6_spi_apps_clk = {
+	.halt_reg = 0x08c4,
+	.clkr = {
+		.enable_reg = 0x08c4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup6_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_qup6_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart1_apps_clk = {
+	.halt_reg = 0x0684,
+	.clkr = {
+		.enable_reg = 0x0684,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart1_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_uart1_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart2_apps_clk = {
+	.halt_reg = 0x0704,
+	.clkr = {
+		.enable_reg = 0x0704,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart2_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_uart2_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart3_apps_clk = {
+	.halt_reg = 0x0784,
+	.clkr = {
+		.enable_reg = 0x0784,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart3_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_uart3_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart4_apps_clk = {
+	.halt_reg = 0x0804,
+	.clkr = {
+		.enable_reg = 0x0804,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart4_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_uart4_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart5_apps_clk = {
+	.halt_reg = 0x0884,
+	.clkr = {
+		.enable_reg = 0x0884,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart5_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_uart5_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart6_apps_clk = {
+	.halt_reg = 0x0904,
+	.clkr = {
+		.enable_reg = 0x0904,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart6_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp1_uart6_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_ahb_clk = {
+	.halt_reg = 0x0944,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(15),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup1_i2c_apps_clk = {
+	.halt_reg = 0x0988,
+	.clkr = {
+		.enable_reg = 0x0988,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup1_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup1_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup1_spi_apps_clk = {
+	.halt_reg = 0x0984,
+	.clkr = {
+		.enable_reg = 0x0984,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup1_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup1_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup2_i2c_apps_clk = {
+	.halt_reg = 0x0a08,
+	.clkr = {
+		.enable_reg = 0x0a08,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup2_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup2_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup2_spi_apps_clk = {
+	.halt_reg = 0x0a04,
+	.clkr = {
+		.enable_reg = 0x0a04,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup2_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup2_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup3_i2c_apps_clk = {
+	.halt_reg = 0x0a88,
+	.clkr = {
+		.enable_reg = 0x0a88,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup3_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup3_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup3_spi_apps_clk = {
+	.halt_reg = 0x0a84,
+	.clkr = {
+		.enable_reg = 0x0a84,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup3_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup3_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup4_i2c_apps_clk = {
+	.halt_reg = 0x0b08,
+	.clkr = {
+		.enable_reg = 0x0b08,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup4_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup4_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup4_spi_apps_clk = {
+	.halt_reg = 0x0b04,
+	.clkr = {
+		.enable_reg = 0x0b04,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup4_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup4_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup5_i2c_apps_clk = {
+	.halt_reg = 0x0b88,
+	.clkr = {
+		.enable_reg = 0x0b88,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup5_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup5_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup5_spi_apps_clk = {
+	.halt_reg = 0x0b84,
+	.clkr = {
+		.enable_reg = 0x0b84,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup5_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup5_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup6_i2c_apps_clk = {
+	.halt_reg = 0x0c08,
+	.clkr = {
+		.enable_reg = 0x0c08,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup6_i2c_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup6_i2c_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_qup6_spi_apps_clk = {
+	.halt_reg = 0x0c04,
+	.clkr = {
+		.enable_reg = 0x0c04,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_qup6_spi_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_qup6_spi_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_uart1_apps_clk = {
+	.halt_reg = 0x09c4,
+	.clkr = {
+		.enable_reg = 0x09c4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_uart1_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_uart1_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_uart2_apps_clk = {
+	.halt_reg = 0x0a44,
+	.clkr = {
+		.enable_reg = 0x0a44,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_uart2_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_uart2_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_uart3_apps_clk = {
+	.halt_reg = 0x0ac4,
+	.clkr = {
+		.enable_reg = 0x0ac4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_uart3_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_uart3_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_uart4_apps_clk = {
+	.halt_reg = 0x0b44,
+	.clkr = {
+		.enable_reg = 0x0b44,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_uart4_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_uart4_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_uart5_apps_clk = {
+	.halt_reg = 0x0bc4,
+	.clkr = {
+		.enable_reg = 0x0bc4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_uart5_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_uart5_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp2_uart6_apps_clk = {
+	.halt_reg = 0x0c44,
+	.clkr = {
+		.enable_reg = 0x0c44,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp2_uart6_apps_clk",
+			.parent_names = (const char *[]){
+				"blsp2_uart6_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_boot_rom_ahb_clk = {
+	.halt_reg = 0x0e04,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(10),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_boot_rom_ahb_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce1_ahb_clk = {
+	.halt_reg = 0x104c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(3),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce1_ahb_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce1_axi_clk = {
+	.halt_reg = 0x1048,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce1_axi_clk",
+			.parent_names = (const char *[]){
+				"system_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce1_clk = {
+	.halt_reg = 0x1050,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(5),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce1_clk",
+			.parent_names = (const char *[]){
+				"ce1_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce2_ahb_clk = {
+	.halt_reg = 0x108c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce2_ahb_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce2_axi_clk = {
+	.halt_reg = 0x1088,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce2_axi_clk",
+			.parent_names = (const char *[]){
+				"system_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce2_clk = {
+	.halt_reg = 0x1090,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(2),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce2_clk",
+			.parent_names = (const char *[]){
+				"ce2_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce3_ahb_clk = {
+	.halt_reg = 0x1d0c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1d0c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce3_ahb_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce3_axi_clk = {
+	.halt_reg = 0x1088,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1d08,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce3_axi_clk",
+			.parent_names = (const char *[]){
+				"system_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ce3_clk = {
+	.halt_reg = 0x1090,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1d04,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ce3_clk",
+			.parent_names = (const char *[]){
+				"ce3_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp1_clk = {
+	.halt_reg = 0x1900,
+	.clkr = {
+		.enable_reg = 0x1900,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp1_clk",
+			.parent_names = (const char *[]){
+				"gp1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp2_clk = {
+	.halt_reg = 0x1940,
+	.clkr = {
+		.enable_reg = 0x1940,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp2_clk",
+			.parent_names = (const char *[]){
+				"gp2_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp3_clk = {
+	.halt_reg = 0x1980,
+	.clkr = {
+		.enable_reg = 0x1980,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp3_clk",
+			.parent_names = (const char *[]){
+				"gp3_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ocmem_noc_cfg_ahb_clk = {
+	.halt_reg = 0x0248,
+	.clkr = {
+		.enable_reg = 0x0248,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ocmem_noc_cfg_ahb_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_0_aux_clk = {
+	.halt_reg = 0x1b10,
+	.clkr = {
+		.enable_reg = 0x1b10,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_0_aux_clk",
+			.parent_names = (const char *[]){
+				"pcie_0_aux_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_0_cfg_ahb_clk = {
+	.halt_reg = 0x1b0c,
+	.clkr = {
+		.enable_reg = 0x1b0c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_0_cfg_ahb_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_0_mstr_axi_clk = {
+	.halt_reg = 0x1b08,
+	.clkr = {
+		.enable_reg = 0x1b08,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_0_mstr_axi_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_0_pipe_clk = {
+	.halt_reg = 0x1b14,
+	.clkr = {
+		.enable_reg = 0x1b14,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_0_pipe_clk",
+			.parent_names = (const char *[]){
+				"pcie_0_pipe_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_0_slv_axi_clk = {
+	.halt_reg = 0x1b04,
+	.clkr = {
+		.enable_reg = 0x1b04,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_0_slv_axi_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_1_aux_clk = {
+	.halt_reg = 0x1b90,
+	.clkr = {
+		.enable_reg = 0x1b90,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_1_aux_clk",
+			.parent_names = (const char *[]){
+				"pcie_1_aux_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_1_cfg_ahb_clk = {
+	.halt_reg = 0x1b8c,
+	.clkr = {
+		.enable_reg = 0x1b8c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_1_cfg_ahb_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_1_mstr_axi_clk = {
+	.halt_reg = 0x1b88,
+	.clkr = {
+		.enable_reg = 0x1b88,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_1_mstr_axi_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_1_pipe_clk = {
+	.halt_reg = 0x1b94,
+	.clkr = {
+		.enable_reg = 0x1b94,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_1_pipe_clk",
+			.parent_names = (const char *[]){
+				"pcie_1_pipe_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie_1_slv_axi_clk = {
+	.halt_reg = 0x1b84,
+	.clkr = {
+		.enable_reg = 0x1b84,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie_1_slv_axi_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pdm2_clk = {
+	.halt_reg = 0x0ccc,
+	.clkr = {
+		.enable_reg = 0x0ccc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pdm2_clk",
+			.parent_names = (const char *[]){
+				"pdm2_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pdm_ahb_clk = {
+	.halt_reg = 0x0cc4,
+	.clkr = {
+		.enable_reg = 0x0cc4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pdm_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_periph_noc_usb_hsic_ahb_clk = {
+	.halt_reg = 0x01a4,
+	.clkr = {
+		.enable_reg = 0x01a4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_periph_noc_usb_hsic_ahb_clk",
+			.parent_names = (const char *[]){
+				"usb_hsic_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_prng_ahb_clk = {
+	.halt_reg = 0x0d04,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x1484,
+		.enable_mask = BIT(13),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_prng_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sata_asic0_clk = {
+	.halt_reg = 0x1c54,
+	.clkr = {
+		.enable_reg = 0x1c54,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sata_asic0_clk",
+			.parent_names = (const char *[]){
+				"sata_asic0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sata_axi_clk = {
+	.halt_reg = 0x1c44,
+	.clkr = {
+		.enable_reg = 0x1c44,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sata_axi_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sata_cfg_ahb_clk = {
+	.halt_reg = 0x1c48,
+	.clkr = {
+		.enable_reg = 0x1c48,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sata_cfg_ahb_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sata_pmalive_clk = {
+	.halt_reg = 0x1c50,
+	.clkr = {
+		.enable_reg = 0x1c50,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sata_pmalive_clk",
+			.parent_names = (const char *[]){
+				"sata_pmalive_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sata_rx_clk = {
+	.halt_reg = 0x1c58,
+	.clkr = {
+		.enable_reg = 0x1c58,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sata_rx_clk",
+			.parent_names = (const char *[]){
+				"sata_rx_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sata_rx_oob_clk = {
+	.halt_reg = 0x1c4c,
+	.clkr = {
+		.enable_reg = 0x1c4c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sata_rx_oob_clk",
+			.parent_names = (const char *[]){
+				"sata_rx_oob_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_ahb_clk = {
+	.halt_reg = 0x04c8,
+	.clkr = {
+		.enable_reg = 0x04c8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_apps_clk = {
+	.halt_reg = 0x04c4,
+	.clkr = {
+		.enable_reg = 0x04c4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_apps_clk",
+			.parent_names = (const char *[]){
+				"sdcc1_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_cdccal_ff_clk = {
+	.halt_reg = 0x04e8,
+	.clkr = {
+		.enable_reg = 0x04e8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_cdccal_ff_clk",
+			.parent_names = (const char *[]){
+				"xo"
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_cdccal_sleep_clk = {
+	.halt_reg = 0x04e4,
+	.clkr = {
+		.enable_reg = 0x04e4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_cdccal_sleep_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src"
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc2_ahb_clk = {
+	.halt_reg = 0x0508,
+	.clkr = {
+		.enable_reg = 0x0508,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc2_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc2_apps_clk = {
+	.halt_reg = 0x0504,
+	.clkr = {
+		.enable_reg = 0x0504,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc2_apps_clk",
+			.parent_names = (const char *[]){
+				"sdcc2_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc3_ahb_clk = {
+	.halt_reg = 0x0548,
+	.clkr = {
+		.enable_reg = 0x0548,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc3_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc3_apps_clk = {
+	.halt_reg = 0x0544,
+	.clkr = {
+		.enable_reg = 0x0544,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc3_apps_clk",
+			.parent_names = (const char *[]){
+				"sdcc3_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc4_ahb_clk = {
+	.halt_reg = 0x0588,
+	.clkr = {
+		.enable_reg = 0x0588,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc4_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc4_apps_clk = {
+	.halt_reg = 0x0584,
+	.clkr = {
+		.enable_reg = 0x0584,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc4_apps_clk",
+			.parent_names = (const char *[]){
+				"sdcc4_apps_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sys_noc_ufs_axi_clk = {
+	.halt_reg = 0x013c,
+	.clkr = {
+		.enable_reg = 0x013c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sys_noc_ufs_axi_clk",
+			.parent_names = (const char *[]){
+				"ufs_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sys_noc_usb3_axi_clk = {
+	.halt_reg = 0x0108,
+	.clkr = {
+		.enable_reg = 0x0108,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sys_noc_usb3_axi_clk",
+			.parent_names = (const char *[]){
+				"usb30_master_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sys_noc_usb3_sec_axi_clk = {
+	.halt_reg = 0x0138,
+	.clkr = {
+		.enable_reg = 0x0138,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sys_noc_usb3_sec_axi_clk",
+			.parent_names = (const char *[]){
+				"usb30_sec_master_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_tsif_ahb_clk = {
+	.halt_reg = 0x0d84,
+	.clkr = {
+		.enable_reg = 0x0d84,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_tsif_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_tsif_inactivity_timers_clk = {
+	.halt_reg = 0x0d8c,
+	.clkr = {
+		.enable_reg = 0x0d8c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_tsif_inactivity_timers_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_tsif_ref_clk = {
+	.halt_reg = 0x0d88,
+	.clkr = {
+		.enable_reg = 0x0d88,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_tsif_ref_clk",
+			.parent_names = (const char *[]){
+				"tsif_ref_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_ahb_clk = {
+	.halt_reg = 0x1d48,
+	.clkr = {
+		.enable_reg = 0x1d48,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ufs_ahb_clk",
+			.parent_names = (const char *[]){
+				"config_noc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_axi_clk = {
+	.halt_reg = 0x1d44,
+	.clkr = {
+		.enable_reg = 0x1d44,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ufs_axi_clk",
+			.parent_names = (const char *[]){
+				"ufs_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_rx_cfg_clk = {
+	.halt_reg = 0x1d50,
+	.clkr = {
+		.enable_reg = 0x1d50,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ufs_rx_cfg_clk",
+			.parent_names = (const char *[]){
+				"ufs_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_rx_symbol_0_clk = {
+	.halt_reg = 0x1d5c,
+	.clkr = {
+		.enable_reg = 0x1d5c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ufs_rx_symbol_0_clk",
+			.parent_names = (const char *[]){
+				"ufs_rx_symbol_0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_rx_symbol_1_clk = {
+	.halt_reg = 0x1d60,
+	.clkr = {
+		.enable_reg = 0x1d60,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ufs_rx_symbol_1_clk",
+			.parent_names = (const char *[]){
+				"ufs_rx_symbol_1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_tx_cfg_clk = {
+	.halt_reg = 0x1d4c,
+	.clkr = {
+		.enable_reg = 0x1d4c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ufs_tx_cfg_clk",
+			.parent_names = (const char *[]){
+				"ufs_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_tx_symbol_0_clk = {
+	.halt_reg = 0x1d54,
+	.clkr = {
+		.enable_reg = 0x1d54,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ufs_tx_symbol_0_clk",
+			.parent_names = (const char *[]){
+				"ufs_tx_symbol_0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ufs_tx_symbol_1_clk = {
+	.halt_reg = 0x1d58,
+	.clkr = {
+		.enable_reg = 0x1d58,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ufs_tx_symbol_1_clk",
+			.parent_names = (const char *[]){
+				"ufs_tx_symbol_1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb2a_phy_sleep_clk = {
+	.halt_reg = 0x04ac,
+	.clkr = {
+		.enable_reg = 0x04ac,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb2a_phy_sleep_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb2b_phy_sleep_clk = {
+	.halt_reg = 0x04b4,
+	.clkr = {
+		.enable_reg = 0x04b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb2b_phy_sleep_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_master_clk = {
+	.halt_reg = 0x03c8,
+	.clkr = {
+		.enable_reg = 0x03c8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_master_clk",
+			.parent_names = (const char *[]){
+				"usb30_master_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_sec_master_clk = {
+	.halt_reg = 0x1bc8,
+	.clkr = {
+		.enable_reg = 0x1bc8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_sec_master_clk",
+			.parent_names = (const char *[]){
+				"usb30_sec_master_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_mock_utmi_clk = {
+	.halt_reg = 0x03d0,
+	.clkr = {
+		.enable_reg = 0x03d0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_mock_utmi_clk",
+			.parent_names = (const char *[]){
+				"usb30_mock_utmi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb30_sleep_clk = {
+	.halt_reg = 0x03cc,
+	.clkr = {
+		.enable_reg = 0x03cc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb30_sleep_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb_hs_ahb_clk = {
+	.halt_reg = 0x0488,
+	.clkr = {
+		.enable_reg = 0x0488,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_hs_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb_hs_inactivity_timers_clk = {
+	.halt_reg = 0x048c,
+	.clkr = {
+		.enable_reg = 0x048c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_hs_inactivity_timers_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb_hs_system_clk = {
+	.halt_reg = 0x0484,
+	.clkr = {
+		.enable_reg = 0x0484,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_hs_system_clk",
+			.parent_names = (const char *[]){
+				"usb_hs_system_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb_hsic_ahb_clk = {
+	.halt_reg = 0x0408,
+	.clkr = {
+		.enable_reg = 0x0408,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_hsic_ahb_clk",
+			.parent_names = (const char *[]){
+				"periph_noc_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb_hsic_clk = {
+	.halt_reg = 0x0410,
+	.clkr = {
+		.enable_reg = 0x0410,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_hsic_clk",
+			.parent_names = (const char *[]){
+				"usb_hsic_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb_hsic_io_cal_clk = {
+	.halt_reg = 0x0414,
+	.clkr = {
+		.enable_reg = 0x0414,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_hsic_io_cal_clk",
+			.parent_names = (const char *[]){
+				"usb_hsic_io_cal_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb_hsic_io_cal_sleep_clk = {
+	.halt_reg = 0x0418,
+	.clkr = {
+		.enable_reg = 0x0418,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_hsic_io_cal_sleep_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb_hsic_system_clk = {
+	.halt_reg = 0x040c,
+	.clkr = {
+		.enable_reg = 0x040c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb_hsic_system_clk",
+			.parent_names = (const char *[]){
+				"usb_hsic_system_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_regmap *gcc_apq8084_clocks[] = {
+	[GPLL0] = &gpll0.clkr,
+	[GPLL0_VOTE] = &gpll0_vote,
+	[GPLL1] = &gpll1.clkr,
+	[GPLL1_VOTE] = &gpll1_vote,
+	[GPLL4] = &gpll4.clkr,
+	[GPLL4_VOTE] = &gpll4_vote,
+	[CONFIG_NOC_CLK_SRC] = &config_noc_clk_src.clkr,
+	[PERIPH_NOC_CLK_SRC] = &periph_noc_clk_src.clkr,
+	[SYSTEM_NOC_CLK_SRC] = &system_noc_clk_src.clkr,
+	[UFS_AXI_CLK_SRC] = &ufs_axi_clk_src.clkr,
+	[USB30_MASTER_CLK_SRC] = &usb30_master_clk_src.clkr,
+	[USB30_SEC_MASTER_CLK_SRC] = &usb30_sec_master_clk_src.clkr,
+	[USB_HSIC_AHB_CLK_SRC] = &usb_hsic_ahb_clk_src.clkr,
+	[BLSP1_QUP1_I2C_APPS_CLK_SRC] = &blsp1_qup1_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP1_SPI_APPS_CLK_SRC] = &blsp1_qup1_spi_apps_clk_src.clkr,
+	[BLSP1_QUP2_I2C_APPS_CLK_SRC] = &blsp1_qup2_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP2_SPI_APPS_CLK_SRC] = &blsp1_qup2_spi_apps_clk_src.clkr,
+	[BLSP1_QUP3_I2C_APPS_CLK_SRC] = &blsp1_qup3_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP3_SPI_APPS_CLK_SRC] = &blsp1_qup3_spi_apps_clk_src.clkr,
+	[BLSP1_QUP4_I2C_APPS_CLK_SRC] = &blsp1_qup4_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP4_SPI_APPS_CLK_SRC] = &blsp1_qup4_spi_apps_clk_src.clkr,
+	[BLSP1_QUP5_I2C_APPS_CLK_SRC] = &blsp1_qup5_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP5_SPI_APPS_CLK_SRC] = &blsp1_qup5_spi_apps_clk_src.clkr,
+	[BLSP1_QUP6_I2C_APPS_CLK_SRC] = &blsp1_qup6_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP6_SPI_APPS_CLK_SRC] = &blsp1_qup6_spi_apps_clk_src.clkr,
+	[BLSP1_UART1_APPS_CLK_SRC] = &blsp1_uart1_apps_clk_src.clkr,
+	[BLSP1_UART2_APPS_CLK_SRC] = &blsp1_uart2_apps_clk_src.clkr,
+	[BLSP1_UART3_APPS_CLK_SRC] = &blsp1_uart3_apps_clk_src.clkr,
+	[BLSP1_UART4_APPS_CLK_SRC] = &blsp1_uart4_apps_clk_src.clkr,
+	[BLSP1_UART5_APPS_CLK_SRC] = &blsp1_uart5_apps_clk_src.clkr,
+	[BLSP1_UART6_APPS_CLK_SRC] = &blsp1_uart6_apps_clk_src.clkr,
+	[BLSP2_QUP1_I2C_APPS_CLK_SRC] = &blsp2_qup1_i2c_apps_clk_src.clkr,
+	[BLSP2_QUP1_SPI_APPS_CLK_SRC] = &blsp2_qup1_spi_apps_clk_src.clkr,
+	[BLSP2_QUP2_I2C_APPS_CLK_SRC] = &blsp2_qup2_i2c_apps_clk_src.clkr,
+	[BLSP2_QUP2_SPI_APPS_CLK_SRC] = &blsp2_qup2_spi_apps_clk_src.clkr,
+	[BLSP2_QUP3_I2C_APPS_CLK_SRC] = &blsp2_qup3_i2c_apps_clk_src.clkr,
+	[BLSP2_QUP3_SPI_APPS_CLK_SRC] = &blsp2_qup3_spi_apps_clk_src.clkr,
+	[BLSP2_QUP4_I2C_APPS_CLK_SRC] = &blsp2_qup4_i2c_apps_clk_src.clkr,
+	[BLSP2_QUP4_SPI_APPS_CLK_SRC] = &blsp2_qup4_spi_apps_clk_src.clkr,
+	[BLSP2_QUP5_I2C_APPS_CLK_SRC] = &blsp2_qup5_i2c_apps_clk_src.clkr,
+	[BLSP2_QUP5_SPI_APPS_CLK_SRC] = &blsp2_qup5_spi_apps_clk_src.clkr,
+	[BLSP2_QUP6_I2C_APPS_CLK_SRC] = &blsp2_qup6_i2c_apps_clk_src.clkr,
+	[BLSP2_QUP6_SPI_APPS_CLK_SRC] = &blsp2_qup6_spi_apps_clk_src.clkr,
+	[BLSP2_UART1_APPS_CLK_SRC] = &blsp2_uart1_apps_clk_src.clkr,
+	[BLSP2_UART2_APPS_CLK_SRC] = &blsp2_uart2_apps_clk_src.clkr,
+	[BLSP2_UART3_APPS_CLK_SRC] = &blsp2_uart3_apps_clk_src.clkr,
+	[BLSP2_UART4_APPS_CLK_SRC] = &blsp2_uart4_apps_clk_src.clkr,
+	[BLSP2_UART5_APPS_CLK_SRC] = &blsp2_uart5_apps_clk_src.clkr,
+	[BLSP2_UART6_APPS_CLK_SRC] = &blsp2_uart6_apps_clk_src.clkr,
+	[CE1_CLK_SRC] = &ce1_clk_src.clkr,
+	[CE2_CLK_SRC] = &ce2_clk_src.clkr,
+	[CE3_CLK_SRC] = &ce3_clk_src.clkr,
+	[GP1_CLK_SRC] = &gp1_clk_src.clkr,
+	[GP2_CLK_SRC] = &gp2_clk_src.clkr,
+	[GP3_CLK_SRC] = &gp3_clk_src.clkr,
+	[PCIE_0_AUX_CLK_SRC] = &pcie_0_aux_clk_src.clkr,
+	[PCIE_0_PIPE_CLK_SRC] = &pcie_0_pipe_clk_src.clkr,
+	[PCIE_1_AUX_CLK_SRC] = &pcie_1_aux_clk_src.clkr,
+	[PCIE_1_PIPE_CLK_SRC] = &pcie_1_pipe_clk_src.clkr,
+	[PDM2_CLK_SRC] = &pdm2_clk_src.clkr,
+	[SATA_ASIC0_CLK_SRC] = &sata_asic0_clk_src.clkr,
+	[SATA_PMALIVE_CLK_SRC] = &sata_pmalive_clk_src.clkr,
+	[SATA_RX_CLK_SRC] = &sata_rx_clk_src.clkr,
+	[SATA_RX_OOB_CLK_SRC] = &sata_rx_oob_clk_src.clkr,
+	[SDCC1_APPS_CLK_SRC] = &sdcc1_apps_clk_src.clkr,
+	[SDCC2_APPS_CLK_SRC] = &sdcc2_apps_clk_src.clkr,
+	[SDCC3_APPS_CLK_SRC] = &sdcc3_apps_clk_src.clkr,
+	[SDCC4_APPS_CLK_SRC] = &sdcc4_apps_clk_src.clkr,
+	[TSIF_REF_CLK_SRC] = &tsif_ref_clk_src.clkr,
+	[USB30_MOCK_UTMI_CLK_SRC] = &usb30_mock_utmi_clk_src.clkr,
+	[USB30_SEC_MOCK_UTMI_CLK_SRC] = &usb30_sec_mock_utmi_clk_src.clkr,
+	[USB_HS_SYSTEM_CLK_SRC] = &usb_hs_system_clk_src.clkr,
+	[USB_HSIC_CLK_SRC] = &usb_hsic_clk_src.clkr,
+	[USB_HSIC_IO_CAL_CLK_SRC] = &usb_hsic_io_cal_clk_src.clkr,
+	[USB_HSIC_MOCK_UTMI_CLK_SRC] = &usb_hsic_mock_utmi_clk_src.clkr,
+	[USB_HSIC_SYSTEM_CLK_SRC] = &usb_hsic_system_clk_src.clkr,
+	[GCC_BAM_DMA_AHB_CLK] = &gcc_bam_dma_ahb_clk.clkr,
+	[GCC_BLSP1_AHB_CLK] = &gcc_blsp1_ahb_clk.clkr,
+	[GCC_BLSP1_QUP1_I2C_APPS_CLK] = &gcc_blsp1_qup1_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP1_SPI_APPS_CLK] = &gcc_blsp1_qup1_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP2_I2C_APPS_CLK] = &gcc_blsp1_qup2_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP2_SPI_APPS_CLK] = &gcc_blsp1_qup2_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP3_I2C_APPS_CLK] = &gcc_blsp1_qup3_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP3_SPI_APPS_CLK] = &gcc_blsp1_qup3_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP4_I2C_APPS_CLK] = &gcc_blsp1_qup4_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP4_SPI_APPS_CLK] = &gcc_blsp1_qup4_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP5_I2C_APPS_CLK] = &gcc_blsp1_qup5_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP5_SPI_APPS_CLK] = &gcc_blsp1_qup5_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP6_I2C_APPS_CLK] = &gcc_blsp1_qup6_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP6_SPI_APPS_CLK] = &gcc_blsp1_qup6_spi_apps_clk.clkr,
+	[GCC_BLSP1_UART1_APPS_CLK] = &gcc_blsp1_uart1_apps_clk.clkr,
+	[GCC_BLSP1_UART2_APPS_CLK] = &gcc_blsp1_uart2_apps_clk.clkr,
+	[GCC_BLSP1_UART3_APPS_CLK] = &gcc_blsp1_uart3_apps_clk.clkr,
+	[GCC_BLSP1_UART4_APPS_CLK] = &gcc_blsp1_uart4_apps_clk.clkr,
+	[GCC_BLSP1_UART5_APPS_CLK] = &gcc_blsp1_uart5_apps_clk.clkr,
+	[GCC_BLSP1_UART6_APPS_CLK] = &gcc_blsp1_uart6_apps_clk.clkr,
+	[GCC_BLSP2_AHB_CLK] = &gcc_blsp2_ahb_clk.clkr,
+	[GCC_BLSP2_QUP1_I2C_APPS_CLK] = &gcc_blsp2_qup1_i2c_apps_clk.clkr,
+	[GCC_BLSP2_QUP1_SPI_APPS_CLK] = &gcc_blsp2_qup1_spi_apps_clk.clkr,
+	[GCC_BLSP2_QUP2_I2C_APPS_CLK] = &gcc_blsp2_qup2_i2c_apps_clk.clkr,
+	[GCC_BLSP2_QUP2_SPI_APPS_CLK] = &gcc_blsp2_qup2_spi_apps_clk.clkr,
+	[GCC_BLSP2_QUP3_I2C_APPS_CLK] = &gcc_blsp2_qup3_i2c_apps_clk.clkr,
+	[GCC_BLSP2_QUP3_SPI_APPS_CLK] = &gcc_blsp2_qup3_spi_apps_clk.clkr,
+	[GCC_BLSP2_QUP4_I2C_APPS_CLK] = &gcc_blsp2_qup4_i2c_apps_clk.clkr,
+	[GCC_BLSP2_QUP4_SPI_APPS_CLK] = &gcc_blsp2_qup4_spi_apps_clk.clkr,
+	[GCC_BLSP2_QUP5_I2C_APPS_CLK] = &gcc_blsp2_qup5_i2c_apps_clk.clkr,
+	[GCC_BLSP2_QUP5_SPI_APPS_CLK] = &gcc_blsp2_qup5_spi_apps_clk.clkr,
+	[GCC_BLSP2_QUP6_I2C_APPS_CLK] = &gcc_blsp2_qup6_i2c_apps_clk.clkr,
+	[GCC_BLSP2_QUP6_SPI_APPS_CLK] = &gcc_blsp2_qup6_spi_apps_clk.clkr,
+	[GCC_BLSP2_UART1_APPS_CLK] = &gcc_blsp2_uart1_apps_clk.clkr,
+	[GCC_BLSP2_UART2_APPS_CLK] = &gcc_blsp2_uart2_apps_clk.clkr,
+	[GCC_BLSP2_UART3_APPS_CLK] = &gcc_blsp2_uart3_apps_clk.clkr,
+	[GCC_BLSP2_UART4_APPS_CLK] = &gcc_blsp2_uart4_apps_clk.clkr,
+	[GCC_BLSP2_UART5_APPS_CLK] = &gcc_blsp2_uart5_apps_clk.clkr,
+	[GCC_BLSP2_UART6_APPS_CLK] = &gcc_blsp2_uart6_apps_clk.clkr,
+	[GCC_BOOT_ROM_AHB_CLK] = &gcc_boot_rom_ahb_clk.clkr,
+	[GCC_CE1_AHB_CLK] = &gcc_ce1_ahb_clk.clkr,
+	[GCC_CE1_AXI_CLK] = &gcc_ce1_axi_clk.clkr,
+	[GCC_CE1_CLK] = &gcc_ce1_clk.clkr,
+	[GCC_CE2_AHB_CLK] = &gcc_ce2_ahb_clk.clkr,
+	[GCC_CE2_AXI_CLK] = &gcc_ce2_axi_clk.clkr,
+	[GCC_CE2_CLK] = &gcc_ce2_clk.clkr,
+	[GCC_CE3_AHB_CLK] = &gcc_ce3_ahb_clk.clkr,
+	[GCC_CE3_AXI_CLK] = &gcc_ce3_axi_clk.clkr,
+	[GCC_CE3_CLK] = &gcc_ce3_clk.clkr,
+	[GCC_GP1_CLK] = &gcc_gp1_clk.clkr,
+	[GCC_GP2_CLK] = &gcc_gp2_clk.clkr,
+	[GCC_GP3_CLK] = &gcc_gp3_clk.clkr,
+	[GCC_OCMEM_NOC_CFG_AHB_CLK] = &gcc_ocmem_noc_cfg_ahb_clk.clkr,
+	[GCC_PCIE_0_AUX_CLK] = &gcc_pcie_0_aux_clk.clkr,
+	[GCC_PCIE_0_CFG_AHB_CLK] = &gcc_pcie_0_cfg_ahb_clk.clkr,
+	[GCC_PCIE_0_MSTR_AXI_CLK] = &gcc_pcie_0_mstr_axi_clk.clkr,
+	[GCC_PCIE_0_PIPE_CLK] = &gcc_pcie_0_pipe_clk.clkr,
+	[GCC_PCIE_0_SLV_AXI_CLK] = &gcc_pcie_0_slv_axi_clk.clkr,
+	[GCC_PCIE_1_AUX_CLK] = &gcc_pcie_1_aux_clk.clkr,
+	[GCC_PCIE_1_CFG_AHB_CLK] = &gcc_pcie_1_cfg_ahb_clk.clkr,
+	[GCC_PCIE_1_MSTR_AXI_CLK] = &gcc_pcie_1_mstr_axi_clk.clkr,
+	[GCC_PCIE_1_PIPE_CLK] = &gcc_pcie_1_pipe_clk.clkr,
+	[GCC_PCIE_1_SLV_AXI_CLK] = &gcc_pcie_1_slv_axi_clk.clkr,
+	[GCC_PDM2_CLK] = &gcc_pdm2_clk.clkr,
+	[GCC_PDM_AHB_CLK] = &gcc_pdm_ahb_clk.clkr,
+	[GCC_PERIPH_NOC_USB_HSIC_AHB_CLK] = &gcc_periph_noc_usb_hsic_ahb_clk.clkr,
+	[GCC_PRNG_AHB_CLK] = &gcc_prng_ahb_clk.clkr,
+	[GCC_SATA_ASIC0_CLK] = &gcc_sata_asic0_clk.clkr,
+	[GCC_SATA_AXI_CLK] = &gcc_sata_axi_clk.clkr,
+	[GCC_SATA_CFG_AHB_CLK] = &gcc_sata_cfg_ahb_clk.clkr,
+	[GCC_SATA_PMALIVE_CLK] = &gcc_sata_pmalive_clk.clkr,
+	[GCC_SATA_RX_CLK] = &gcc_sata_rx_clk.clkr,
+	[GCC_SATA_RX_OOB_CLK] = &gcc_sata_rx_oob_clk.clkr,
+	[GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr,
+	[GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr,
+	[GCC_SDCC1_CDCCAL_FF_CLK] = &gcc_sdcc1_cdccal_ff_clk.clkr,
+	[GCC_SDCC1_CDCCAL_SLEEP_CLK] = &gcc_sdcc1_cdccal_sleep_clk.clkr,
+	[GCC_SDCC2_AHB_CLK] = &gcc_sdcc2_ahb_clk.clkr,
+	[GCC_SDCC2_APPS_CLK] = &gcc_sdcc2_apps_clk.clkr,
+	[GCC_SDCC3_AHB_CLK] = &gcc_sdcc3_ahb_clk.clkr,
+	[GCC_SDCC3_APPS_CLK] = &gcc_sdcc3_apps_clk.clkr,
+	[GCC_SDCC4_AHB_CLK] = &gcc_sdcc4_ahb_clk.clkr,
+	[GCC_SDCC4_APPS_CLK] = &gcc_sdcc4_apps_clk.clkr,
+	[GCC_SYS_NOC_UFS_AXI_CLK] = &gcc_sys_noc_ufs_axi_clk.clkr,
+	[GCC_SYS_NOC_USB3_AXI_CLK] = &gcc_sys_noc_usb3_axi_clk.clkr,
+	[GCC_SYS_NOC_USB3_SEC_AXI_CLK] = &gcc_sys_noc_usb3_sec_axi_clk.clkr,
+	[GCC_TSIF_AHB_CLK] = &gcc_tsif_ahb_clk.clkr,
+	[GCC_TSIF_INACTIVITY_TIMERS_CLK] = &gcc_tsif_inactivity_timers_clk.clkr,
+	[GCC_TSIF_REF_CLK] = &gcc_tsif_ref_clk.clkr,
+	[GCC_UFS_AHB_CLK] = &gcc_ufs_ahb_clk.clkr,
+	[GCC_UFS_AXI_CLK] = &gcc_ufs_axi_clk.clkr,
+	[GCC_UFS_RX_CFG_CLK] = &gcc_ufs_rx_cfg_clk.clkr,
+	[GCC_UFS_RX_SYMBOL_0_CLK] = &gcc_ufs_rx_symbol_0_clk.clkr,
+	[GCC_UFS_RX_SYMBOL_1_CLK] = &gcc_ufs_rx_symbol_1_clk.clkr,
+	[GCC_UFS_TX_CFG_CLK] = &gcc_ufs_tx_cfg_clk.clkr,
+	[GCC_UFS_TX_SYMBOL_0_CLK] = &gcc_ufs_tx_symbol_0_clk.clkr,
+	[GCC_UFS_TX_SYMBOL_1_CLK] = &gcc_ufs_tx_symbol_1_clk.clkr,
+	[GCC_USB2A_PHY_SLEEP_CLK] = &gcc_usb2a_phy_sleep_clk.clkr,
+	[GCC_USB2B_PHY_SLEEP_CLK] = &gcc_usb2b_phy_sleep_clk.clkr,
+	[GCC_USB30_MASTER_CLK] = &gcc_usb30_master_clk.clkr,
+	[GCC_USB30_MOCK_UTMI_CLK] = &gcc_usb30_mock_utmi_clk.clkr,
+	[GCC_USB30_SLEEP_CLK] = &gcc_usb30_sleep_clk.clkr,
+	[GCC_USB30_SEC_MASTER_CLK] = &gcc_usb30_sec_master_clk.clkr,
+	[GCC_USB30_SEC_MOCK_UTMI_CLK] = &gcc_usb30_sec_mock_utmi_clk.clkr,
+	[GCC_USB30_SEC_SLEEP_CLK] = &gcc_usb30_sec_sleep_clk.clkr,
+	[GCC_USB_HS_AHB_CLK] = &gcc_usb_hs_ahb_clk.clkr,
+	[GCC_USB_HS_INACTIVITY_TIMERS_CLK] = &gcc_usb_hs_inactivity_timers_clk.clkr,
+	[GCC_USB_HS_SYSTEM_CLK] = &gcc_usb_hs_system_clk.clkr,
+	[GCC_USB_HSIC_AHB_CLK] = &gcc_usb_hsic_ahb_clk.clkr,
+	[GCC_USB_HSIC_CLK] = &gcc_usb_hsic_clk.clkr,
+	[GCC_USB_HSIC_IO_CAL_CLK] = &gcc_usb_hsic_io_cal_clk.clkr,
+	[GCC_USB_HSIC_IO_CAL_SLEEP_CLK] = &gcc_usb_hsic_io_cal_sleep_clk.clkr,
+	[GCC_USB_HSIC_MOCK_UTMI_CLK] = &gcc_usb_hsic_mock_utmi_clk.clkr,
+	[GCC_USB_HSIC_SYSTEM_CLK] = &gcc_usb_hsic_system_clk.clkr,
+};
+
+static const struct qcom_reset_map gcc_apq8084_resets[] = {
+	[GCC_SYSTEM_NOC_BCR] = { 0x0100 },
+	[GCC_CONFIG_NOC_BCR] = { 0x0140 },
+	[GCC_PERIPH_NOC_BCR] = { 0x0180 },
+	[GCC_IMEM_BCR] = { 0x0200 },
+	[GCC_MMSS_BCR] = { 0x0240 },
+	[GCC_QDSS_BCR] = { 0x0300 },
+	[GCC_USB_30_BCR] = { 0x03c0 },
+	[GCC_USB3_PHY_BCR] = { 0x03fc },
+	[GCC_USB_HS_HSIC_BCR] = { 0x0400 },
+	[GCC_USB_HS_BCR] = { 0x0480 },
+	[GCC_USB2A_PHY_BCR] = { 0x04a8 },
+	[GCC_USB2B_PHY_BCR] = { 0x04b0 },
+	[GCC_SDCC1_BCR] = { 0x04c0 },
+	[GCC_SDCC2_BCR] = { 0x0500 },
+	[GCC_SDCC3_BCR] = { 0x0540 },
+	[GCC_SDCC4_BCR] = { 0x0580 },
+	[GCC_BLSP1_BCR] = { 0x05c0 },
+	[GCC_BLSP1_QUP1_BCR] = { 0x0640 },
+	[GCC_BLSP1_UART1_BCR] = { 0x0680 },
+	[GCC_BLSP1_QUP2_BCR] = { 0x06c0 },
+	[GCC_BLSP1_UART2_BCR] = { 0x0700 },
+	[GCC_BLSP1_QUP3_BCR] = { 0x0740 },
+	[GCC_BLSP1_UART3_BCR] = { 0x0780 },
+	[GCC_BLSP1_QUP4_BCR] = { 0x07c0 },
+	[GCC_BLSP1_UART4_BCR] = { 0x0800 },
+	[GCC_BLSP1_QUP5_BCR] = { 0x0840 },
+	[GCC_BLSP1_UART5_BCR] = { 0x0880 },
+	[GCC_BLSP1_QUP6_BCR] = { 0x08c0 },
+	[GCC_BLSP1_UART6_BCR] = { 0x0900 },
+	[GCC_BLSP2_BCR] = { 0x0940 },
+	[GCC_BLSP2_QUP1_BCR] = { 0x0980 },
+	[GCC_BLSP2_UART1_BCR] = { 0x09c0 },
+	[GCC_BLSP2_QUP2_BCR] = { 0x0a00 },
+	[GCC_BLSP2_UART2_BCR] = { 0x0a40 },
+	[GCC_BLSP2_QUP3_BCR] = { 0x0a80 },
+	[GCC_BLSP2_UART3_BCR] = { 0x0ac0 },
+	[GCC_BLSP2_QUP4_BCR] = { 0x0b00 },
+	[GCC_BLSP2_UART4_BCR] = { 0x0b40 },
+	[GCC_BLSP2_QUP5_BCR] = { 0x0b80 },
+	[GCC_BLSP2_UART5_BCR] = { 0x0bc0 },
+	[GCC_BLSP2_QUP6_BCR] = { 0x0c00 },
+	[GCC_BLSP2_UART6_BCR] = { 0x0c40 },
+	[GCC_PDM_BCR] = { 0x0cc0 },
+	[GCC_PRNG_BCR] = { 0x0d00 },
+	[GCC_BAM_DMA_BCR] = { 0x0d40 },
+	[GCC_TSIF_BCR] = { 0x0d80 },
+	[GCC_TCSR_BCR] = { 0x0dc0 },
+	[GCC_BOOT_ROM_BCR] = { 0x0e00 },
+	[GCC_MSG_RAM_BCR] = { 0x0e40 },
+	[GCC_TLMM_BCR] = { 0x0e80 },
+	[GCC_MPM_BCR] = { 0x0ec0 },
+	[GCC_MPM_AHB_RESET] = { 0x0ec4, 1 },
+	[GCC_MPM_NON_AHB_RESET] = { 0x0ec4, 2 },
+	[GCC_SEC_CTRL_BCR] = { 0x0f40 },
+	[GCC_SPMI_BCR] = { 0x0fc0 },
+	[GCC_SPDM_BCR] = { 0x1000 },
+	[GCC_CE1_BCR] = { 0x1040 },
+	[GCC_CE2_BCR] = { 0x1080 },
+	[GCC_BIMC_BCR] = { 0x1100 },
+	[GCC_SNOC_BUS_TIMEOUT0_BCR] = { 0x1240 },
+	[GCC_SNOC_BUS_TIMEOUT2_BCR] = { 0x1248 },
+	[GCC_PNOC_BUS_TIMEOUT0_BCR] = { 0x1280 },
+	[GCC_PNOC_BUS_TIMEOUT1_BCR] = { 0x1288 },
+	[GCC_PNOC_BUS_TIMEOUT2_BCR] = { 0x1290 },
+	[GCC_PNOC_BUS_TIMEOUT3_BCR] = { 0x1298 },
+	[GCC_PNOC_BUS_TIMEOUT4_BCR] = { 0x12a0 },
+	[GCC_CNOC_BUS_TIMEOUT0_BCR] = { 0x12c0 },
+	[GCC_CNOC_BUS_TIMEOUT1_BCR] = { 0x12c8 },
+	[GCC_CNOC_BUS_TIMEOUT2_BCR] = { 0x12d0 },
+	[GCC_CNOC_BUS_TIMEOUT3_BCR] = { 0x12d8 },
+	[GCC_CNOC_BUS_TIMEOUT4_BCR] = { 0x12e0 },
+	[GCC_CNOC_BUS_TIMEOUT5_BCR] = { 0x12e8 },
+	[GCC_CNOC_BUS_TIMEOUT6_BCR] = { 0x12f0 },
+	[GCC_DEHR_BCR] = { 0x1300 },
+	[GCC_RBCPR_BCR] = { 0x1380 },
+	[GCC_MSS_RESTART] = { 0x1680 },
+	[GCC_LPASS_RESTART] = { 0x16c0 },
+	[GCC_WCSS_RESTART] = { 0x1700 },
+	[GCC_VENUS_RESTART] = { 0x1740 },
+	[GCC_COPSS_SMMU_BCR] = { 0x1a40 },
+	[GCC_SPSS_BCR] = { 0x1a80 },
+	[GCC_PCIE_0_BCR] = { 0x1ac0 },
+	[GCC_PCIE_0_PHY_BCR] = { 0x1b00 },
+	[GCC_PCIE_1_BCR] = { 0x1b40 },
+	[GCC_PCIE_1_PHY_BCR] = { 0x1b80 },
+	[GCC_USB_30_SEC_BCR] = { 0x1bc0 },
+	[GCC_USB3_SEC_PHY_BCR] = { 0x1bfc },
+	[GCC_SATA_BCR] = { 0x1c40 },
+	[GCC_CE3_BCR] = { 0x1d00 },
+	[GCC_UFS_BCR] = { 0x1d40 },
+	[GCC_USB30_PHY_COM_BCR] = { 0x1e80 },
+};
+
+static const struct regmap_config gcc_apq8084_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x1fc0,
+	.fast_io	= true,
+};
+
+static const struct qcom_cc_desc gcc_apq8084_desc = {
+	.config = &gcc_apq8084_regmap_config,
+	.clks = gcc_apq8084_clocks,
+	.num_clks = ARRAY_SIZE(gcc_apq8084_clocks),
+	.resets = gcc_apq8084_resets,
+	.num_resets = ARRAY_SIZE(gcc_apq8084_resets),
+};
+
+static const struct of_device_id gcc_apq8084_match_table[] = {
+	{ .compatible = "qcom,gcc-apq8084" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, gcc_apq8084_match_table);
+
+static int gcc_apq8084_probe(struct platform_device *pdev)
+{
+	struct clk *clk;
+	struct device *dev = &pdev->dev;
+
+	/* Temporary until RPM clocks supported */
+	clk = clk_register_fixed_rate(dev, "xo", NULL, CLK_IS_ROOT, 19200000);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	clk = clk_register_fixed_rate(dev, "sleep_clk_src", NULL,
+				      CLK_IS_ROOT, 32768);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	return qcom_cc_probe(pdev, &gcc_apq8084_desc);
+}
+
+static int gcc_apq8084_remove(struct platform_device *pdev)
+{
+	qcom_cc_remove(pdev);
+	return 0;
+}
+
+static struct platform_driver gcc_apq8084_driver = {
+	.probe		= gcc_apq8084_probe,
+	.remove		= gcc_apq8084_remove,
+	.driver		= {
+		.name	= "gcc-apq8084",
+		.owner	= THIS_MODULE,
+		.of_match_table = gcc_apq8084_match_table,
+	},
+};
+
+static int __init gcc_apq8084_init(void)
+{
+	return platform_driver_register(&gcc_apq8084_driver);
+}
+core_initcall(gcc_apq8084_init);
+
+static void __exit gcc_apq8084_exit(void)
+{
+	platform_driver_unregister(&gcc_apq8084_driver);
+}
+module_exit(gcc_apq8084_exit);
+
+MODULE_DESCRIPTION("QCOM GCC APQ8084 Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:gcc-apq8084");
diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c
new file mode 100644
index 00000000000..4032e510d9a
--- /dev/null
+++ b/drivers/clk/qcom/gcc-ipq806x.c
@@ -0,0 +1,2424 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/clk-provider.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+
+#include <dt-bindings/clock/qcom,gcc-ipq806x.h>
+#include <dt-bindings/reset/qcom,gcc-ipq806x.h>
+
+#include "common.h"
+#include "clk-regmap.h"
+#include "clk-pll.h"
+#include "clk-rcg.h"
+#include "clk-branch.h"
+#include "reset.h"
+
+static struct clk_pll pll3 = {
+	.l_reg = 0x3164,
+	.m_reg = 0x3168,
+	.n_reg = 0x316c,
+	.config_reg = 0x3174,
+	.mode_reg = 0x3160,
+	.status_reg = 0x3178,
+	.status_bit = 16,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pll3",
+		.parent_names = (const char *[]){ "pxo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_pll pll8 = {
+	.l_reg = 0x3144,
+	.m_reg = 0x3148,
+	.n_reg = 0x314c,
+	.config_reg = 0x3154,
+	.mode_reg = 0x3140,
+	.status_reg = 0x3158,
+	.status_bit = 16,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pll8",
+		.parent_names = (const char *[]){ "pxo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_regmap pll8_vote = {
+	.enable_reg = 0x34c0,
+	.enable_mask = BIT(8),
+	.hw.init = &(struct clk_init_data){
+		.name = "pll8_vote",
+		.parent_names = (const char *[]){ "pll8" },
+		.num_parents = 1,
+		.ops = &clk_pll_vote_ops,
+	},
+};
+
+static struct clk_pll pll14 = {
+	.l_reg = 0x31c4,
+	.m_reg = 0x31c8,
+	.n_reg = 0x31cc,
+	.config_reg = 0x31d4,
+	.mode_reg = 0x31c0,
+	.status_reg = 0x31d8,
+	.status_bit = 16,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pll14",
+		.parent_names = (const char *[]){ "pxo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_regmap pll14_vote = {
+	.enable_reg = 0x34c0,
+	.enable_mask = BIT(14),
+	.hw.init = &(struct clk_init_data){
+		.name = "pll14_vote",
+		.parent_names = (const char *[]){ "pll14" },
+		.num_parents = 1,
+		.ops = &clk_pll_vote_ops,
+	},
+};
+
+#define P_PXO	0
+#define P_PLL8	1
+#define P_PLL3	1
+#define P_PLL0	2
+#define P_CXO	2
+
+static const u8 gcc_pxo_pll8_map[] = {
+	[P_PXO]		= 0,
+	[P_PLL8]	= 3,
+};
+
+static const char *gcc_pxo_pll8[] = {
+	"pxo",
+	"pll8_vote",
+};
+
+static const u8 gcc_pxo_pll8_cxo_map[] = {
+	[P_PXO]		= 0,
+	[P_PLL8]	= 3,
+	[P_CXO]		= 5,
+};
+
+static const char *gcc_pxo_pll8_cxo[] = {
+	"pxo",
+	"pll8_vote",
+	"cxo",
+};
+
+static const u8 gcc_pxo_pll3_map[] = {
+	[P_PXO]		= 0,
+	[P_PLL3]	= 1,
+};
+
+static const u8 gcc_pxo_pll3_sata_map[] = {
+	[P_PXO]		= 0,
+	[P_PLL3]	= 6,
+};
+
+static const char *gcc_pxo_pll3[] = {
+	"pxo",
+	"pll3",
+};
+
+static const u8 gcc_pxo_pll8_pll0[] = {
+	[P_PXO]		= 0,
+	[P_PLL8]	= 3,
+	[P_PLL0]	= 2,
+};
+
+static const char *gcc_pxo_pll8_pll0_map[] = {
+	"pxo",
+	"pll8_vote",
+	"pll0",
+};
+
+static struct freq_tbl clk_tbl_gsbi_uart[] = {
+	{  1843200, P_PLL8, 2,  6, 625 },
+	{  3686400, P_PLL8, 2, 12, 625 },
+	{  7372800, P_PLL8, 2, 24, 625 },
+	{ 14745600, P_PLL8, 2, 48, 625 },
+	{ 16000000, P_PLL8, 4,  1,   6 },
+	{ 24000000, P_PLL8, 4,  1,   4 },
+	{ 32000000, P_PLL8, 4,  1,   3 },
+	{ 40000000, P_PLL8, 1,  5,  48 },
+	{ 46400000, P_PLL8, 1, 29, 240 },
+	{ 48000000, P_PLL8, 4,  1,   2 },
+	{ 51200000, P_PLL8, 1,  2,  15 },
+	{ 56000000, P_PLL8, 1,  7,  48 },
+	{ 58982400, P_PLL8, 1, 96, 625 },
+	{ 64000000, P_PLL8, 2,  1,   3 },
+	{ }
+};
+
+static struct clk_rcg gsbi1_uart_src = {
+	.ns_reg = 0x29d4,
+	.md_reg = 0x29d0,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 16,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_uart,
+	.clkr = {
+		.enable_reg = 0x29d4,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi1_uart_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi1_uart_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 12,
+	.clkr = {
+		.enable_reg = 0x29d4,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi1_uart_clk",
+			.parent_names = (const char *[]){
+				"gsbi1_uart_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi2_uart_src = {
+	.ns_reg = 0x29f4,
+	.md_reg = 0x29f0,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 16,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_uart,
+	.clkr = {
+		.enable_reg = 0x29f4,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi2_uart_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi2_uart_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 8,
+	.clkr = {
+		.enable_reg = 0x29f4,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi2_uart_clk",
+			.parent_names = (const char *[]){
+				"gsbi2_uart_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi4_uart_src = {
+	.ns_reg = 0x2a34,
+	.md_reg = 0x2a30,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 16,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_uart,
+	.clkr = {
+		.enable_reg = 0x2a34,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi4_uart_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi4_uart_clk = {
+	.halt_reg = 0x2fd0,
+	.halt_bit = 26,
+	.clkr = {
+		.enable_reg = 0x2a34,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi4_uart_clk",
+			.parent_names = (const char *[]){
+				"gsbi4_uart_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi5_uart_src = {
+	.ns_reg = 0x2a54,
+	.md_reg = 0x2a50,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 16,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_uart,
+	.clkr = {
+		.enable_reg = 0x2a54,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi5_uart_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi5_uart_clk = {
+	.halt_reg = 0x2fd0,
+	.halt_bit = 22,
+	.clkr = {
+		.enable_reg = 0x2a54,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi5_uart_clk",
+			.parent_names = (const char *[]){
+				"gsbi5_uart_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi6_uart_src = {
+	.ns_reg = 0x2a74,
+	.md_reg = 0x2a70,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 16,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_uart,
+	.clkr = {
+		.enable_reg = 0x2a74,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi6_uart_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi6_uart_clk = {
+	.halt_reg = 0x2fd0,
+	.halt_bit = 18,
+	.clkr = {
+		.enable_reg = 0x2a74,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi6_uart_clk",
+			.parent_names = (const char *[]){
+				"gsbi6_uart_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi7_uart_src = {
+	.ns_reg = 0x2a94,
+	.md_reg = 0x2a90,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 16,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_uart,
+	.clkr = {
+		.enable_reg = 0x2a94,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi7_uart_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi7_uart_clk = {
+	.halt_reg = 0x2fd0,
+	.halt_bit = 14,
+	.clkr = {
+		.enable_reg = 0x2a94,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi7_uart_clk",
+			.parent_names = (const char *[]){
+				"gsbi7_uart_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct freq_tbl clk_tbl_gsbi_qup[] = {
+	{  1100000, P_PXO,  1, 2, 49 },
+	{  5400000, P_PXO,  1, 1,  5 },
+	{ 10800000, P_PXO,  1, 2,  5 },
+	{ 15060000, P_PLL8, 1, 2, 51 },
+	{ 24000000, P_PLL8, 4, 1,  4 },
+	{ 25600000, P_PLL8, 1, 1, 15 },
+	{ 27000000, P_PXO,  1, 0,  0 },
+	{ 48000000, P_PLL8, 4, 1,  2 },
+	{ 51200000, P_PLL8, 1, 2, 15 },
+	{ }
+};
+
+static struct clk_rcg gsbi1_qup_src = {
+	.ns_reg = 0x29cc,
+	.md_reg = 0x29c8,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_qup,
+	.clkr = {
+		.enable_reg = 0x29cc,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi1_qup_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi1_qup_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 11,
+	.clkr = {
+		.enable_reg = 0x29cc,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi1_qup_clk",
+			.parent_names = (const char *[]){ "gsbi1_qup_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi2_qup_src = {
+	.ns_reg = 0x29ec,
+	.md_reg = 0x29e8,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_qup,
+	.clkr = {
+		.enable_reg = 0x29ec,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi2_qup_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi2_qup_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 6,
+	.clkr = {
+		.enable_reg = 0x29ec,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi2_qup_clk",
+			.parent_names = (const char *[]){ "gsbi2_qup_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi4_qup_src = {
+	.ns_reg = 0x2a2c,
+	.md_reg = 0x2a28,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_qup,
+	.clkr = {
+		.enable_reg = 0x2a2c,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi4_qup_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi4_qup_clk = {
+	.halt_reg = 0x2fd0,
+	.halt_bit = 24,
+	.clkr = {
+		.enable_reg = 0x2a2c,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi4_qup_clk",
+			.parent_names = (const char *[]){ "gsbi4_qup_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi5_qup_src = {
+	.ns_reg = 0x2a4c,
+	.md_reg = 0x2a48,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_qup,
+	.clkr = {
+		.enable_reg = 0x2a4c,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi5_qup_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi5_qup_clk = {
+	.halt_reg = 0x2fd0,
+	.halt_bit = 20,
+	.clkr = {
+		.enable_reg = 0x2a4c,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi5_qup_clk",
+			.parent_names = (const char *[]){ "gsbi5_qup_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi6_qup_src = {
+	.ns_reg = 0x2a6c,
+	.md_reg = 0x2a68,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_qup,
+	.clkr = {
+		.enable_reg = 0x2a6c,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi6_qup_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi6_qup_clk = {
+	.halt_reg = 0x2fd0,
+	.halt_bit = 16,
+	.clkr = {
+		.enable_reg = 0x2a6c,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi6_qup_clk",
+			.parent_names = (const char *[]){ "gsbi6_qup_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gsbi7_qup_src = {
+	.ns_reg = 0x2a8c,
+	.md_reg = 0x2a88,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_gsbi_qup,
+	.clkr = {
+		.enable_reg = 0x2a8c,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi7_qup_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	},
+};
+
+static struct clk_branch gsbi7_qup_clk = {
+	.halt_reg = 0x2fd0,
+	.halt_bit = 12,
+	.clkr = {
+		.enable_reg = 0x2a8c,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi7_qup_clk",
+			.parent_names = (const char *[]){ "gsbi7_qup_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch gsbi1_h_clk = {
+	.hwcg_reg = 0x29c0,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fcc,
+	.halt_bit = 13,
+	.clkr = {
+		.enable_reg = 0x29c0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi1_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch gsbi2_h_clk = {
+	.hwcg_reg = 0x29e0,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fcc,
+	.halt_bit = 9,
+	.clkr = {
+		.enable_reg = 0x29e0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi2_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch gsbi4_h_clk = {
+	.hwcg_reg = 0x2a20,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fd0,
+	.halt_bit = 27,
+	.clkr = {
+		.enable_reg = 0x2a20,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi4_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch gsbi5_h_clk = {
+	.hwcg_reg = 0x2a40,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fd0,
+	.halt_bit = 23,
+	.clkr = {
+		.enable_reg = 0x2a40,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi5_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch gsbi6_h_clk = {
+	.hwcg_reg = 0x2a60,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fd0,
+	.halt_bit = 19,
+	.clkr = {
+		.enable_reg = 0x2a60,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi6_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch gsbi7_h_clk = {
+	.hwcg_reg = 0x2a80,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fd0,
+	.halt_bit = 15,
+	.clkr = {
+		.enable_reg = 0x2a80,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "gsbi7_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_gp[] = {
+	{ 12500000, P_PXO,  2, 0, 0 },
+	{ 25000000, P_PXO,  1, 0, 0 },
+	{ 64000000, P_PLL8, 2, 1, 3 },
+	{ 76800000, P_PLL8, 1, 1, 5 },
+	{ 96000000, P_PLL8, 4, 0, 0 },
+	{ 128000000, P_PLL8, 3, 0, 0 },
+	{ 192000000, P_PLL8, 2, 0, 0 },
+	{ }
+};
+
+static struct clk_rcg gp0_src = {
+	.ns_reg = 0x2d24,
+	.md_reg = 0x2d00,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_cxo_map,
+	},
+	.freq_tbl = clk_tbl_gp,
+	.clkr = {
+		.enable_reg = 0x2d24,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gp0_src",
+			.parent_names = gcc_pxo_pll8_cxo,
+			.num_parents = 3,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_PARENT_GATE,
+		},
+	}
+};
+
+static struct clk_branch gp0_clk = {
+	.halt_reg = 0x2fd8,
+	.halt_bit = 7,
+	.clkr = {
+		.enable_reg = 0x2d24,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gp0_clk",
+			.parent_names = (const char *[]){ "gp0_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gp1_src = {
+	.ns_reg = 0x2d44,
+	.md_reg = 0x2d40,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_cxo_map,
+	},
+	.freq_tbl = clk_tbl_gp,
+	.clkr = {
+		.enable_reg = 0x2d44,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gp1_src",
+			.parent_names = gcc_pxo_pll8_cxo,
+			.num_parents = 3,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	}
+};
+
+static struct clk_branch gp1_clk = {
+	.halt_reg = 0x2fd8,
+	.halt_bit = 6,
+	.clkr = {
+		.enable_reg = 0x2d44,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gp1_clk",
+			.parent_names = (const char *[]){ "gp1_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg gp2_src = {
+	.ns_reg = 0x2d64,
+	.md_reg = 0x2d60,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_cxo_map,
+	},
+	.freq_tbl = clk_tbl_gp,
+	.clkr = {
+		.enable_reg = 0x2d64,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "gp2_src",
+			.parent_names = gcc_pxo_pll8_cxo,
+			.num_parents = 3,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	}
+};
+
+static struct clk_branch gp2_clk = {
+	.halt_reg = 0x2fd8,
+	.halt_bit = 5,
+	.clkr = {
+		.enable_reg = 0x2d64,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "gp2_clk",
+			.parent_names = (const char *[]){ "gp2_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch pmem_clk = {
+	.hwcg_reg = 0x25a0,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fc8,
+	.halt_bit = 20,
+	.clkr = {
+		.enable_reg = 0x25a0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pmem_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_rcg prng_src = {
+	.ns_reg = 0x2e80,
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 4,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "prng_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+		},
+	},
+};
+
+static struct clk_branch prng_clk = {
+	.halt_reg = 0x2fd8,
+	.halt_check = BRANCH_HALT_VOTED,
+	.halt_bit = 10,
+	.clkr = {
+		.enable_reg = 0x3080,
+		.enable_mask = BIT(10),
+		.hw.init = &(struct clk_init_data){
+			.name = "prng_clk",
+			.parent_names = (const char *[]){ "prng_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_sdc[] = {
+	{    144000, P_PXO,   5, 18,625 },
+	{    400000, P_PLL8,  4, 1, 240 },
+	{  16000000, P_PLL8,  4, 1,   6 },
+	{  17070000, P_PLL8,  1, 2,  45 },
+	{  20210000, P_PLL8,  1, 1,  19 },
+	{  24000000, P_PLL8,  4, 1,   4 },
+	{  48000000, P_PLL8,  4, 1,   2 },
+	{  64000000, P_PLL8,  3, 1,   2 },
+	{  96000000, P_PLL8,  4, 0,   0 },
+	{ 192000000, P_PLL8,  2, 0,   0 },
+	{ }
+};
+
+static struct clk_rcg sdc1_src = {
+	.ns_reg = 0x282c,
+	.md_reg = 0x2828,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_sdc,
+	.clkr = {
+		.enable_reg = 0x282c,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "sdc1_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	}
+};
+
+static struct clk_branch sdc1_clk = {
+	.halt_reg = 0x2fc8,
+	.halt_bit = 6,
+	.clkr = {
+		.enable_reg = 0x282c,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "sdc1_clk",
+			.parent_names = (const char *[]){ "sdc1_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg sdc3_src = {
+	.ns_reg = 0x286c,
+	.md_reg = 0x2868,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_sdc,
+	.clkr = {
+		.enable_reg = 0x286c,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "sdc3_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	}
+};
+
+static struct clk_branch sdc3_clk = {
+	.halt_reg = 0x2fc8,
+	.halt_bit = 4,
+	.clkr = {
+		.enable_reg = 0x286c,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "sdc3_clk",
+			.parent_names = (const char *[]){ "sdc3_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch sdc1_h_clk = {
+	.hwcg_reg = 0x2820,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fc8,
+	.halt_bit = 11,
+	.clkr = {
+		.enable_reg = 0x2820,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sdc1_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch sdc3_h_clk = {
+	.hwcg_reg = 0x2860,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fc8,
+	.halt_bit = 9,
+	.clkr = {
+		.enable_reg = 0x2860,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sdc3_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_tsif_ref[] = {
+	{ 105000, P_PXO,  1, 1, 256 },
+	{ }
+};
+
+static struct clk_rcg tsif_ref_src = {
+	.ns_reg = 0x2710,
+	.md_reg = 0x270c,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 16,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_tsif_ref,
+	.clkr = {
+		.enable_reg = 0x2710,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "tsif_ref_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	}
+};
+
+static struct clk_branch tsif_ref_clk = {
+	.halt_reg = 0x2fd4,
+	.halt_bit = 5,
+	.clkr = {
+		.enable_reg = 0x2710,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "tsif_ref_clk",
+			.parent_names = (const char *[]){ "tsif_ref_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch tsif_h_clk = {
+	.hwcg_reg = 0x2700,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fd4,
+	.halt_bit = 7,
+	.clkr = {
+		.enable_reg = 0x2700,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "tsif_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch dma_bam_h_clk = {
+	.hwcg_reg = 0x25c0,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fc8,
+	.halt_bit = 12,
+	.clkr = {
+		.enable_reg = 0x25c0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "dma_bam_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch adm0_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_check = BRANCH_HALT_VOTED,
+	.halt_bit = 12,
+	.clkr = {
+		.enable_reg = 0x3080,
+		.enable_mask = BIT(2),
+		.hw.init = &(struct clk_init_data){
+			.name = "adm0_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch adm0_pbus_clk = {
+	.hwcg_reg = 0x2208,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fdc,
+	.halt_check = BRANCH_HALT_VOTED,
+	.halt_bit = 11,
+	.clkr = {
+		.enable_reg = 0x3080,
+		.enable_mask = BIT(3),
+		.hw.init = &(struct clk_init_data){
+			.name = "adm0_pbus_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pmic_arb0_h_clk = {
+	.halt_reg = 0x2fd8,
+	.halt_check = BRANCH_HALT_VOTED,
+	.halt_bit = 22,
+	.clkr = {
+		.enable_reg = 0x3080,
+		.enable_mask = BIT(8),
+		.hw.init = &(struct clk_init_data){
+			.name = "pmic_arb0_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pmic_arb1_h_clk = {
+	.halt_reg = 0x2fd8,
+	.halt_check = BRANCH_HALT_VOTED,
+	.halt_bit = 21,
+	.clkr = {
+		.enable_reg = 0x3080,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "pmic_arb1_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pmic_ssbi2_clk = {
+	.halt_reg = 0x2fd8,
+	.halt_check = BRANCH_HALT_VOTED,
+	.halt_bit = 23,
+	.clkr = {
+		.enable_reg = 0x3080,
+		.enable_mask = BIT(7),
+		.hw.init = &(struct clk_init_data){
+			.name = "pmic_ssbi2_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch rpm_msg_ram_h_clk = {
+	.hwcg_reg = 0x27e0,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fd8,
+	.halt_check = BRANCH_HALT_VOTED,
+	.halt_bit = 12,
+	.clkr = {
+		.enable_reg = 0x3080,
+		.enable_mask = BIT(6),
+		.hw.init = &(struct clk_init_data){
+			.name = "rpm_msg_ram_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_pcie_ref[] = {
+	{ 100000000, P_PLL3,  12, 0, 0 },
+	{ }
+};
+
+static struct clk_rcg pcie_ref_src = {
+	.ns_reg = 0x3860,
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 4,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll3_map,
+	},
+	.freq_tbl = clk_tbl_pcie_ref,
+	.clkr = {
+		.enable_reg = 0x3860,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie_ref_src",
+			.parent_names = gcc_pxo_pll3,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch pcie_ref_src_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 30,
+	.clkr = {
+		.enable_reg = 0x3860,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie_ref_src_clk",
+			.parent_names = (const char *[]){ "pcie_ref_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch pcie_a_clk = {
+	.halt_reg = 0x2fc0,
+	.halt_bit = 13,
+	.clkr = {
+		.enable_reg = 0x22c0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie_a_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie_aux_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 31,
+	.clkr = {
+		.enable_reg = 0x22c8,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie_aux_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie_h_clk = {
+	.halt_reg = 0x2fd4,
+	.halt_bit = 8,
+	.clkr = {
+		.enable_reg = 0x22cc,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie_phy_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 29,
+	.clkr = {
+		.enable_reg = 0x22d0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie_phy_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_rcg pcie1_ref_src = {
+	.ns_reg = 0x3aa0,
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 4,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll3_map,
+	},
+	.freq_tbl = clk_tbl_pcie_ref,
+	.clkr = {
+		.enable_reg = 0x3aa0,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie1_ref_src",
+			.parent_names = gcc_pxo_pll3,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch pcie1_ref_src_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 27,
+	.clkr = {
+		.enable_reg = 0x3aa0,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie1_ref_src_clk",
+			.parent_names = (const char *[]){ "pcie1_ref_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch pcie1_a_clk = {
+	.halt_reg = 0x2fc0,
+	.halt_bit = 10,
+	.clkr = {
+		.enable_reg = 0x3a80,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie1_a_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie1_aux_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 28,
+	.clkr = {
+		.enable_reg = 0x3a88,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie1_aux_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie1_h_clk = {
+	.halt_reg = 0x2fd4,
+	.halt_bit = 9,
+	.clkr = {
+		.enable_reg = 0x3a8c,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie1_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie1_phy_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 26,
+	.clkr = {
+		.enable_reg = 0x3a90,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie1_phy_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_rcg pcie2_ref_src = {
+	.ns_reg = 0x3ae0,
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 4,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll3_map,
+	},
+	.freq_tbl = clk_tbl_pcie_ref,
+	.clkr = {
+		.enable_reg = 0x3ae0,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie2_ref_src",
+			.parent_names = gcc_pxo_pll3,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch pcie2_ref_src_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 24,
+	.clkr = {
+		.enable_reg = 0x3ae0,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie2_ref_src_clk",
+			.parent_names = (const char *[]){ "pcie2_ref_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch pcie2_a_clk = {
+	.halt_reg = 0x2fc0,
+	.halt_bit = 9,
+	.clkr = {
+		.enable_reg = 0x3ac0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie2_a_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie2_aux_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 25,
+	.clkr = {
+		.enable_reg = 0x3ac8,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie2_aux_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie2_h_clk = {
+	.halt_reg = 0x2fd4,
+	.halt_bit = 10,
+	.clkr = {
+		.enable_reg = 0x3acc,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie2_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie2_phy_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 23,
+	.clkr = {
+		.enable_reg = 0x3ad0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie2_phy_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_sata_ref[] = {
+	{ 100000000, P_PLL3,  12, 0, 0 },
+	{ }
+};
+
+static struct clk_rcg sata_ref_src = {
+	.ns_reg = 0x2c08,
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 4,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll3_sata_map,
+	},
+	.freq_tbl = clk_tbl_sata_ref,
+	.clkr = {
+		.enable_reg = 0x2c08,
+		.enable_mask = BIT(7),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_ref_src",
+			.parent_names = gcc_pxo_pll3,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch sata_rxoob_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 20,
+	.clkr = {
+		.enable_reg = 0x2c0c,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_rxoob_clk",
+			.parent_names = (const char *[]){ "sata_ref_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch sata_pmalive_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 19,
+	.clkr = {
+		.enable_reg = 0x2c10,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_pmalive_clk",
+			.parent_names = (const char *[]){ "sata_ref_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch sata_phy_ref_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 18,
+	.clkr = {
+		.enable_reg = 0x2c14,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_phy_ref_clk",
+			.parent_names = (const char *[]){ "pxo" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+		},
+	},
+};
+
+static struct clk_branch sata_a_clk = {
+	.halt_reg = 0x2fc0,
+	.halt_bit = 12,
+	.clkr = {
+		.enable_reg = 0x2c20,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_a_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch sata_h_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 21,
+	.clkr = {
+		.enable_reg = 0x2c00,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch sfab_sata_s_h_clk = {
+	.halt_reg = 0x2fc4,
+	.halt_bit = 14,
+	.clkr = {
+		.enable_reg = 0x2480,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sfab_sata_s_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch sata_phy_cfg_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 14,
+	.clkr = {
+		.enable_reg = 0x2c40,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_phy_cfg_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_usb30_master[] = {
+	{ 125000000, P_PLL0,  1, 5, 32 },
+	{ }
+};
+
+static struct clk_rcg usb30_master_clk_src = {
+	.ns_reg = 0x3b2c,
+	.md_reg = 0x3b28,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll0,
+	},
+	.freq_tbl = clk_tbl_usb30_master,
+	.clkr = {
+		.enable_reg = 0x3b2c,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb30_master_ref_src",
+			.parent_names = gcc_pxo_pll8_pll0_map,
+			.num_parents = 3,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch usb30_0_branch_clk = {
+	.halt_reg = 0x2fc4,
+	.halt_bit = 22,
+	.clkr = {
+		.enable_reg = 0x3b24,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb30_0_branch_clk",
+			.parent_names = (const char *[]){ "usb30_master_ref_src", },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch usb30_1_branch_clk = {
+	.halt_reg = 0x2fc4,
+	.halt_bit = 17,
+	.clkr = {
+		.enable_reg = 0x3b34,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb30_1_branch_clk",
+			.parent_names = (const char *[]){ "usb30_master_ref_src", },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_usb30_utmi[] = {
+	{ 60000000, P_PLL8,  1, 5, 32 },
+	{ }
+};
+
+static struct clk_rcg usb30_utmi_clk = {
+	.ns_reg = 0x3b44,
+	.md_reg = 0x3b40,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll0,
+	},
+	.freq_tbl = clk_tbl_usb30_utmi,
+	.clkr = {
+		.enable_reg = 0x3b44,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb30_utmi_clk",
+			.parent_names = gcc_pxo_pll8_pll0_map,
+			.num_parents = 3,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch usb30_0_utmi_clk_ctl = {
+	.halt_reg = 0x2fc4,
+	.halt_bit = 21,
+	.clkr = {
+		.enable_reg = 0x3b48,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb30_0_utmi_clk_ctl",
+			.parent_names = (const char *[]){ "usb30_utmi_clk", },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch usb30_1_utmi_clk_ctl = {
+	.halt_reg = 0x2fc4,
+	.halt_bit = 15,
+	.clkr = {
+		.enable_reg = 0x3b4c,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb30_1_utmi_clk_ctl",
+			.parent_names = (const char *[]){ "usb30_utmi_clk", },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_usb[] = {
+	{ 60000000, P_PLL8,  1, 5, 32 },
+	{ }
+};
+
+static struct clk_rcg usb_hs1_xcvr_clk_src = {
+	.ns_reg = 0x290C,
+	.md_reg = 0x2908,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll0,
+	},
+	.freq_tbl = clk_tbl_usb,
+	.clkr = {
+		.enable_reg = 0x2968,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_hs1_xcvr_src",
+			.parent_names = gcc_pxo_pll8_pll0_map,
+			.num_parents = 3,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch usb_hs1_xcvr_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 17,
+	.clkr = {
+		.enable_reg = 0x290c,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_hs1_xcvr_clk",
+			.parent_names = (const char *[]){ "usb_hs1_xcvr_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch usb_hs1_h_clk = {
+	.hwcg_reg = 0x2900,
+	.hwcg_bit = 6,
+	.halt_reg = 0x2fc8,
+	.halt_bit = 1,
+	.clkr = {
+		.enable_reg = 0x2900,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_hs1_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_rcg usb_fs1_xcvr_clk_src = {
+	.ns_reg = 0x2968,
+	.md_reg = 0x2964,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll0,
+	},
+	.freq_tbl = clk_tbl_usb,
+	.clkr = {
+		.enable_reg = 0x2968,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_fs1_xcvr_src",
+			.parent_names = gcc_pxo_pll8_pll0_map,
+			.num_parents = 3,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch usb_fs1_xcvr_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 17,
+	.clkr = {
+		.enable_reg = 0x2968,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_fs1_xcvr_clk",
+			.parent_names = (const char *[]){ "usb_fs1_xcvr_src", },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch usb_fs1_sys_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 18,
+	.clkr = {
+		.enable_reg = 0x296c,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_fs1_sys_clk",
+			.parent_names = (const char *[]){ "usb_fs1_xcvr_src", },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch usb_fs1_h_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 19,
+	.clkr = {
+		.enable_reg = 0x2960,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_fs1_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_regmap *gcc_ipq806x_clks[] = {
+	[PLL3] = &pll3.clkr,
+	[PLL8] = &pll8.clkr,
+	[PLL8_VOTE] = &pll8_vote,
+	[PLL14] = &pll14.clkr,
+	[PLL14_VOTE] = &pll14_vote,
+	[GSBI1_UART_SRC] = &gsbi1_uart_src.clkr,
+	[GSBI1_UART_CLK] = &gsbi1_uart_clk.clkr,
+	[GSBI2_UART_SRC] = &gsbi2_uart_src.clkr,
+	[GSBI2_UART_CLK] = &gsbi2_uart_clk.clkr,
+	[GSBI4_UART_SRC] = &gsbi4_uart_src.clkr,
+	[GSBI4_UART_CLK] = &gsbi4_uart_clk.clkr,
+	[GSBI5_UART_SRC] = &gsbi5_uart_src.clkr,
+	[GSBI5_UART_CLK] = &gsbi5_uart_clk.clkr,
+	[GSBI6_UART_SRC] = &gsbi6_uart_src.clkr,
+	[GSBI6_UART_CLK] = &gsbi6_uart_clk.clkr,
+	[GSBI7_UART_SRC] = &gsbi7_uart_src.clkr,
+	[GSBI7_UART_CLK] = &gsbi7_uart_clk.clkr,
+	[GSBI1_QUP_SRC] = &gsbi1_qup_src.clkr,
+	[GSBI1_QUP_CLK] = &gsbi1_qup_clk.clkr,
+	[GSBI2_QUP_SRC] = &gsbi2_qup_src.clkr,
+	[GSBI2_QUP_CLK] = &gsbi2_qup_clk.clkr,
+	[GSBI4_QUP_SRC] = &gsbi4_qup_src.clkr,
+	[GSBI4_QUP_CLK] = &gsbi4_qup_clk.clkr,
+	[GSBI5_QUP_SRC] = &gsbi5_qup_src.clkr,
+	[GSBI5_QUP_CLK] = &gsbi5_qup_clk.clkr,
+	[GSBI6_QUP_SRC] = &gsbi6_qup_src.clkr,
+	[GSBI6_QUP_CLK] = &gsbi6_qup_clk.clkr,
+	[GSBI7_QUP_SRC] = &gsbi7_qup_src.clkr,
+	[GSBI7_QUP_CLK] = &gsbi7_qup_clk.clkr,
+	[GP0_SRC] = &gp0_src.clkr,
+	[GP0_CLK] = &gp0_clk.clkr,
+	[GP1_SRC] = &gp1_src.clkr,
+	[GP1_CLK] = &gp1_clk.clkr,
+	[GP2_SRC] = &gp2_src.clkr,
+	[GP2_CLK] = &gp2_clk.clkr,
+	[PMEM_A_CLK] = &pmem_clk.clkr,
+	[PRNG_SRC] = &prng_src.clkr,
+	[PRNG_CLK] = &prng_clk.clkr,
+	[SDC1_SRC] = &sdc1_src.clkr,
+	[SDC1_CLK] = &sdc1_clk.clkr,
+	[SDC3_SRC] = &sdc3_src.clkr,
+	[SDC3_CLK] = &sdc3_clk.clkr,
+	[TSIF_REF_SRC] = &tsif_ref_src.clkr,
+	[TSIF_REF_CLK] = &tsif_ref_clk.clkr,
+	[DMA_BAM_H_CLK] = &dma_bam_h_clk.clkr,
+	[GSBI1_H_CLK] = &gsbi1_h_clk.clkr,
+	[GSBI2_H_CLK] = &gsbi2_h_clk.clkr,
+	[GSBI4_H_CLK] = &gsbi4_h_clk.clkr,
+	[GSBI5_H_CLK] = &gsbi5_h_clk.clkr,
+	[GSBI6_H_CLK] = &gsbi6_h_clk.clkr,
+	[GSBI7_H_CLK] = &gsbi7_h_clk.clkr,
+	[TSIF_H_CLK] = &tsif_h_clk.clkr,
+	[SDC1_H_CLK] = &sdc1_h_clk.clkr,
+	[SDC3_H_CLK] = &sdc3_h_clk.clkr,
+	[ADM0_CLK] = &adm0_clk.clkr,
+	[ADM0_PBUS_CLK] = &adm0_pbus_clk.clkr,
+	[PCIE_A_CLK] = &pcie_a_clk.clkr,
+	[PCIE_AUX_CLK] = &pcie_aux_clk.clkr,
+	[PCIE_H_CLK] = &pcie_h_clk.clkr,
+	[PCIE_PHY_CLK] = &pcie_phy_clk.clkr,
+	[SFAB_SATA_S_H_CLK] = &sfab_sata_s_h_clk.clkr,
+	[PMIC_ARB0_H_CLK] = &pmic_arb0_h_clk.clkr,
+	[PMIC_ARB1_H_CLK] = &pmic_arb1_h_clk.clkr,
+	[PMIC_SSBI2_CLK] = &pmic_ssbi2_clk.clkr,
+	[RPM_MSG_RAM_H_CLK] = &rpm_msg_ram_h_clk.clkr,
+	[SATA_H_CLK] = &sata_h_clk.clkr,
+	[SATA_CLK_SRC] = &sata_ref_src.clkr,
+	[SATA_RXOOB_CLK] = &sata_rxoob_clk.clkr,
+	[SATA_PMALIVE_CLK] = &sata_pmalive_clk.clkr,
+	[SATA_PHY_REF_CLK] = &sata_phy_ref_clk.clkr,
+	[SATA_A_CLK] = &sata_a_clk.clkr,
+	[SATA_PHY_CFG_CLK] = &sata_phy_cfg_clk.clkr,
+	[PCIE_ALT_REF_SRC] = &pcie_ref_src.clkr,
+	[PCIE_ALT_REF_CLK] = &pcie_ref_src_clk.clkr,
+	[PCIE_1_A_CLK] = &pcie1_a_clk.clkr,
+	[PCIE_1_AUX_CLK] = &pcie1_aux_clk.clkr,
+	[PCIE_1_H_CLK] = &pcie1_h_clk.clkr,
+	[PCIE_1_PHY_CLK] = &pcie1_phy_clk.clkr,
+	[PCIE_1_ALT_REF_SRC] = &pcie1_ref_src.clkr,
+	[PCIE_1_ALT_REF_CLK] = &pcie1_ref_src_clk.clkr,
+	[PCIE_2_A_CLK] = &pcie2_a_clk.clkr,
+	[PCIE_2_AUX_CLK] = &pcie2_aux_clk.clkr,
+	[PCIE_2_H_CLK] = &pcie2_h_clk.clkr,
+	[PCIE_2_PHY_CLK] = &pcie2_phy_clk.clkr,
+	[PCIE_2_ALT_REF_SRC] = &pcie2_ref_src.clkr,
+	[PCIE_2_ALT_REF_CLK] = &pcie2_ref_src_clk.clkr,
+	[USB30_MASTER_SRC] = &usb30_master_clk_src.clkr,
+	[USB30_0_MASTER_CLK] = &usb30_0_branch_clk.clkr,
+	[USB30_1_MASTER_CLK] = &usb30_1_branch_clk.clkr,
+	[USB30_UTMI_SRC] = &usb30_utmi_clk.clkr,
+	[USB30_0_UTMI_CLK] = &usb30_0_utmi_clk_ctl.clkr,
+	[USB30_1_UTMI_CLK] = &usb30_1_utmi_clk_ctl.clkr,
+	[USB_HS1_H_CLK] = &usb_hs1_h_clk.clkr,
+	[USB_HS1_XCVR_SRC] = &usb_hs1_xcvr_clk_src.clkr,
+	[USB_HS1_XCVR_CLK] = &usb_hs1_xcvr_clk.clkr,
+	[USB_FS1_H_CLK] = &usb_fs1_h_clk.clkr,
+	[USB_FS1_XCVR_SRC] = &usb_fs1_xcvr_clk_src.clkr,
+	[USB_FS1_XCVR_CLK] = &usb_fs1_xcvr_clk.clkr,
+	[USB_FS1_SYSTEM_CLK] = &usb_fs1_sys_clk.clkr,
+};
+
+static const struct qcom_reset_map gcc_ipq806x_resets[] = {
+	[QDSS_STM_RESET] = { 0x2060, 6 },
+	[AFAB_SMPSS_S_RESET] = { 0x20b8, 2 },
+	[AFAB_SMPSS_M1_RESET] = { 0x20b8, 1 },
+	[AFAB_SMPSS_M0_RESET] = { 0x20b8, 0 },
+	[AFAB_EBI1_CH0_RESET] = { 0x20c0, 7 },
+	[AFAB_EBI1_CH1_RESET] = { 0x20c4, 7 },
+	[SFAB_ADM0_M0_RESET] = { 0x21e0, 7 },
+	[SFAB_ADM0_M1_RESET] = { 0x21e4, 7 },
+	[SFAB_ADM0_M2_RESET] = { 0x21e8, 7 },
+	[ADM0_C2_RESET] = { 0x220c, 4 },
+	[ADM0_C1_RESET] = { 0x220c, 3 },
+	[ADM0_C0_RESET] = { 0x220c, 2 },
+	[ADM0_PBUS_RESET] = { 0x220c, 1 },
+	[ADM0_RESET] = { 0x220c, 0 },
+	[QDSS_CLKS_SW_RESET] = { 0x2260, 5 },
+	[QDSS_POR_RESET] = { 0x2260, 4 },
+	[QDSS_TSCTR_RESET] = { 0x2260, 3 },
+	[QDSS_HRESET_RESET] = { 0x2260, 2 },
+	[QDSS_AXI_RESET] = { 0x2260, 1 },
+	[QDSS_DBG_RESET] = { 0x2260, 0 },
+	[SFAB_PCIE_M_RESET] = { 0x22d8, 1 },
+	[SFAB_PCIE_S_RESET] = { 0x22d8, 0 },
+	[PCIE_EXT_RESET] = { 0x22dc, 6 },
+	[PCIE_PHY_RESET] = { 0x22dc, 5 },
+	[PCIE_PCI_RESET] = { 0x22dc, 4 },
+	[PCIE_POR_RESET] = { 0x22dc, 3 },
+	[PCIE_HCLK_RESET] = { 0x22dc, 2 },
+	[PCIE_ACLK_RESET] = { 0x22dc, 0 },
+	[SFAB_LPASS_RESET] = { 0x23a0, 7 },
+	[SFAB_AFAB_M_RESET] = { 0x23e0, 7 },
+	[AFAB_SFAB_M0_RESET] = { 0x2420, 7 },
+	[AFAB_SFAB_M1_RESET] = { 0x2424, 7 },
+	[SFAB_SATA_S_RESET] = { 0x2480, 7 },
+	[SFAB_DFAB_M_RESET] = { 0x2500, 7 },
+	[DFAB_SFAB_M_RESET] = { 0x2520, 7 },
+	[DFAB_SWAY0_RESET] = { 0x2540, 7 },
+	[DFAB_SWAY1_RESET] = { 0x2544, 7 },
+	[DFAB_ARB0_RESET] = { 0x2560, 7 },
+	[DFAB_ARB1_RESET] = { 0x2564, 7 },
+	[PPSS_PROC_RESET] = { 0x2594, 1 },
+	[PPSS_RESET] = { 0x2594, 0 },
+	[DMA_BAM_RESET] = { 0x25c0, 7 },
+	[SPS_TIC_H_RESET] = { 0x2600, 7 },
+	[SFAB_CFPB_M_RESET] = { 0x2680, 7 },
+	[SFAB_CFPB_S_RESET] = { 0x26c0, 7 },
+	[TSIF_H_RESET] = { 0x2700, 7 },
+	[CE1_H_RESET] = { 0x2720, 7 },
+	[CE1_CORE_RESET] = { 0x2724, 7 },
+	[CE1_SLEEP_RESET] = { 0x2728, 7 },
+	[CE2_H_RESET] = { 0x2740, 7 },
+	[CE2_CORE_RESET] = { 0x2744, 7 },
+	[SFAB_SFPB_M_RESET] = { 0x2780, 7 },
+	[SFAB_SFPB_S_RESET] = { 0x27a0, 7 },
+	[RPM_PROC_RESET] = { 0x27c0, 7 },
+	[PMIC_SSBI2_RESET] = { 0x280c, 12 },
+	[SDC1_RESET] = { 0x2830, 0 },
+	[SDC2_RESET] = { 0x2850, 0 },
+	[SDC3_RESET] = { 0x2870, 0 },
+	[SDC4_RESET] = { 0x2890, 0 },
+	[USB_HS1_RESET] = { 0x2910, 0 },
+	[USB_HSIC_RESET] = { 0x2934, 0 },
+	[USB_FS1_XCVR_RESET] = { 0x2974, 1 },
+	[USB_FS1_RESET] = { 0x2974, 0 },
+	[GSBI1_RESET] = { 0x29dc, 0 },
+	[GSBI2_RESET] = { 0x29fc, 0 },
+	[GSBI3_RESET] = { 0x2a1c, 0 },
+	[GSBI4_RESET] = { 0x2a3c, 0 },
+	[GSBI5_RESET] = { 0x2a5c, 0 },
+	[GSBI6_RESET] = { 0x2a7c, 0 },
+	[GSBI7_RESET] = { 0x2a9c, 0 },
+	[SPDM_RESET] = { 0x2b6c, 0 },
+	[SEC_CTRL_RESET] = { 0x2b80, 7 },
+	[TLMM_H_RESET] = { 0x2ba0, 7 },
+	[SFAB_SATA_M_RESET] = { 0x2c18, 0 },
+	[SATA_RESET] = { 0x2c1c, 0 },
+	[TSSC_RESET] = { 0x2ca0, 7 },
+	[PDM_RESET] = { 0x2cc0, 12 },
+	[MPM_H_RESET] = { 0x2da0, 7 },
+	[MPM_RESET] = { 0x2da4, 0 },
+	[SFAB_SMPSS_S_RESET] = { 0x2e00, 7 },
+	[PRNG_RESET] = { 0x2e80, 12 },
+	[SFAB_CE3_M_RESET] = { 0x36c8, 1 },
+	[SFAB_CE3_S_RESET] = { 0x36c8, 0 },
+	[CE3_SLEEP_RESET] = { 0x36d0, 7 },
+	[PCIE_1_M_RESET] = { 0x3a98, 1 },
+	[PCIE_1_S_RESET] = { 0x3a98, 0 },
+	[PCIE_1_EXT_RESET] = { 0x3a9c, 6 },
+	[PCIE_1_PHY_RESET] = { 0x3a9c, 5 },
+	[PCIE_1_PCI_RESET] = { 0x3a9c, 4 },
+	[PCIE_1_POR_RESET] = { 0x3a9c, 3 },
+	[PCIE_1_HCLK_RESET] = { 0x3a9c, 2 },
+	[PCIE_1_ACLK_RESET] = { 0x3a9c, 0 },
+	[PCIE_2_M_RESET] = { 0x3ad8, 1 },
+	[PCIE_2_S_RESET] = { 0x3ad8, 0 },
+	[PCIE_2_EXT_RESET] = { 0x3adc, 6 },
+	[PCIE_2_PHY_RESET] = { 0x3adc, 5 },
+	[PCIE_2_PCI_RESET] = { 0x3adc, 4 },
+	[PCIE_2_POR_RESET] = { 0x3adc, 3 },
+	[PCIE_2_HCLK_RESET] = { 0x3adc, 2 },
+	[PCIE_2_ACLK_RESET] = { 0x3adc, 0 },
+	[SFAB_USB30_S_RESET] = { 0x3b54, 1 },
+	[SFAB_USB30_M_RESET] = { 0x3b54, 0 },
+	[USB30_0_PORT2_HS_PHY_RESET] = { 0x3b50, 5 },
+	[USB30_0_MASTER_RESET] = { 0x3b50, 4 },
+	[USB30_0_SLEEP_RESET] = { 0x3b50, 3 },
+	[USB30_0_UTMI_PHY_RESET] = { 0x3b50, 2 },
+	[USB30_0_POWERON_RESET] = { 0x3b50, 1 },
+	[USB30_0_PHY_RESET] = { 0x3b50, 0 },
+	[USB30_1_MASTER_RESET] = { 0x3b58, 4 },
+	[USB30_1_SLEEP_RESET] = { 0x3b58, 3 },
+	[USB30_1_UTMI_PHY_RESET] = { 0x3b58, 2 },
+	[USB30_1_POWERON_RESET] = { 0x3b58, 1 },
+	[USB30_1_PHY_RESET] = { 0x3b58, 0 },
+	[NSSFB0_RESET] = { 0x3b60, 6 },
+	[NSSFB1_RESET] = { 0x3b60, 7 },
+};
+
+static const struct regmap_config gcc_ipq806x_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x3e40,
+	.fast_io	= true,
+};
+
+static const struct qcom_cc_desc gcc_ipq806x_desc = {
+	.config = &gcc_ipq806x_regmap_config,
+	.clks = gcc_ipq806x_clks,
+	.num_clks = ARRAY_SIZE(gcc_ipq806x_clks),
+	.resets = gcc_ipq806x_resets,
+	.num_resets = ARRAY_SIZE(gcc_ipq806x_resets),
+};
+
+static const struct of_device_id gcc_ipq806x_match_table[] = {
+	{ .compatible = "qcom,gcc-ipq8064" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, gcc_ipq806x_match_table);
+
+static int gcc_ipq806x_probe(struct platform_device *pdev)
+{
+	struct clk *clk;
+	struct device *dev = &pdev->dev;
+
+	/* Temporary until RPM clocks supported */
+	clk = clk_register_fixed_rate(dev, "cxo", NULL, CLK_IS_ROOT, 25000000);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	clk = clk_register_fixed_rate(dev, "pxo", NULL, CLK_IS_ROOT, 25000000);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	return qcom_cc_probe(pdev, &gcc_ipq806x_desc);
+}
+
+static int gcc_ipq806x_remove(struct platform_device *pdev)
+{
+	qcom_cc_remove(pdev);
+	return 0;
+}
+
+static struct platform_driver gcc_ipq806x_driver = {
+	.probe		= gcc_ipq806x_probe,
+	.remove		= gcc_ipq806x_remove,
+	.driver		= {
+		.name	= "gcc-ipq806x",
+		.owner	= THIS_MODULE,
+		.of_match_table = gcc_ipq806x_match_table,
+	},
+};
+
+static int __init gcc_ipq806x_init(void)
+{
+	return platform_driver_register(&gcc_ipq806x_driver);
+}
+core_initcall(gcc_ipq806x_init);
+
+static void __exit gcc_ipq806x_exit(void)
+{
+	platform_driver_unregister(&gcc_ipq806x_driver);
+}
+module_exit(gcc_ipq806x_exit);
+
+MODULE_DESCRIPTION("QCOM GCC IPQ806x Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:gcc-ipq806x");
diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index f4ffd91901f..007534f7a2d 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -104,6 +104,7 @@ static struct clk_regmap pll14_vote = {
 
 #define P_PXO	0
 #define P_PLL8	1
+#define P_PLL3	2
 #define P_CXO	2
 
 static const u8 gcc_pxo_pll8_map[] = {
@@ -128,6 +129,18 @@ static const char *gcc_pxo_pll8_cxo[] = {
 	"cxo",
 };
 
+static const u8 gcc_pxo_pll8_pll3_map[] = {
+	[P_PXO]		= 0,
+	[P_PLL8]	= 3,
+	[P_PLL3]	= 6,
+};
+
+static const char *gcc_pxo_pll8_pll3[] = {
+	"pxo",
+	"pll8_vote",
+	"pll3",
+};
+
 static struct freq_tbl clk_tbl_gsbi_uart[] = {
 	{  1843200, P_PLL8, 2,  6, 625 },
 	{  3686400, P_PLL8, 2, 12, 625 },
@@ -1928,6 +1941,104 @@ static struct clk_branch usb_hs1_xcvr_clk = {
 	},
 };
 
+static struct clk_rcg usb_hs3_xcvr_src = {
+	.ns_reg = 0x370c,
+	.md_reg = 0x3708,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_usb,
+	.clkr = {
+		.enable_reg = 0x370c,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_hs3_xcvr_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	}
+};
+
+static struct clk_branch usb_hs3_xcvr_clk = {
+	.halt_reg = 0x2fc8,
+	.halt_bit = 30,
+	.clkr = {
+		.enable_reg = 0x370c,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_hs3_xcvr_clk",
+			.parent_names = (const char *[]){ "usb_hs3_xcvr_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_rcg usb_hs4_xcvr_src = {
+	.ns_reg = 0x372c,
+	.md_reg = 0x3728,
+	.mn = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 7,
+		.mnctr_mode_shift = 5,
+		.n_val_shift = 16,
+		.m_val_shift = 16,
+		.width = 8,
+	},
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 2,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_map,
+	},
+	.freq_tbl = clk_tbl_usb,
+	.clkr = {
+		.enable_reg = 0x372c,
+		.enable_mask = BIT(11),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_hs4_xcvr_src",
+			.parent_names = gcc_pxo_pll8,
+			.num_parents = 2,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	}
+};
+
+static struct clk_branch usb_hs4_xcvr_clk = {
+	.halt_reg = 0x2fc8,
+	.halt_bit = 2,
+	.clkr = {
+		.enable_reg = 0x372c,
+		.enable_mask = BIT(9),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_hs4_xcvr_clk",
+			.parent_names = (const char *[]){ "usb_hs4_xcvr_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
 static struct clk_rcg usb_hsic_xcvr_fs_src = {
 	.ns_reg = 0x2928,
 	.md_reg = 0x2924,
@@ -2456,6 +2567,34 @@ static struct clk_branch usb_hs1_h_clk = {
 	},
 };
 
+static struct clk_branch usb_hs3_h_clk = {
+	.halt_reg = 0x2fc8,
+	.halt_bit = 31,
+	.clkr = {
+		.enable_reg = 0x3700,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_hs3_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch usb_hs4_h_clk = {
+	.halt_reg = 0x2fc8,
+	.halt_bit = 7,
+	.clkr = {
+		.enable_reg = 0x3720,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "usb_hs4_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
 static struct clk_branch usb_hsic_h_clk = {
 	.halt_reg = 0x2fcc,
 	.halt_bit = 28,
@@ -2582,6 +2721,244 @@ static struct clk_branch adm0_pbus_clk = {
 	},
 };
 
+static struct freq_tbl clk_tbl_ce3[] = {
+	{ 48000000, P_PLL8, 8 },
+	{ 100000000, P_PLL3, 12 },
+	{ 120000000, P_PLL3, 10 },
+	{ }
+};
+
+static struct clk_rcg ce3_src = {
+	.ns_reg = 0x36c0,
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 4,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll3_map,
+	},
+	.freq_tbl = clk_tbl_ce3,
+	.clkr = {
+		.enable_reg = 0x2c08,
+		.enable_mask = BIT(7),
+		.hw.init = &(struct clk_init_data){
+			.name = "ce3_src",
+			.parent_names = gcc_pxo_pll8_pll3,
+			.num_parents = 3,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch ce3_core_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 5,
+	.clkr = {
+		.enable_reg = 0x36c4,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "ce3_core_clk",
+			.parent_names = (const char *[]){ "ce3_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch ce3_h_clk = {
+	.halt_reg = 0x2fc4,
+	.halt_bit = 16,
+	.clkr = {
+		.enable_reg = 0x36c4,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "ce3_h_clk",
+			.parent_names = (const char *[]){ "ce3_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl clk_tbl_sata_ref[] = {
+	{ 48000000, P_PLL8, 8, 0, 0 },
+	{ 100000000, P_PLL3, 12, 0, 0 },
+	{ }
+};
+
+static struct clk_rcg sata_clk_src = {
+	.ns_reg = 0x2c08,
+	.p = {
+		.pre_div_shift = 3,
+		.pre_div_width = 4,
+	},
+	.s = {
+		.src_sel_shift = 0,
+		.parent_map = gcc_pxo_pll8_pll3_map,
+	},
+	.freq_tbl = clk_tbl_sata_ref,
+	.clkr = {
+		.enable_reg = 0x2c08,
+		.enable_mask = BIT(7),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_clk_src",
+			.parent_names = gcc_pxo_pll8_pll3,
+			.num_parents = 3,
+			.ops = &clk_rcg_ops,
+			.flags = CLK_SET_RATE_GATE,
+		},
+	},
+};
+
+static struct clk_branch sata_rxoob_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 26,
+	.clkr = {
+		.enable_reg = 0x2c0c,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_rxoob_clk",
+			.parent_names = (const char *[]){ "sata_clk_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch sata_pmalive_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 25,
+	.clkr = {
+		.enable_reg = 0x2c10,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_pmalive_clk",
+			.parent_names = (const char *[]){ "sata_clk_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch sata_phy_ref_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 24,
+	.clkr = {
+		.enable_reg = 0x2c14,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_phy_ref_clk",
+			.parent_names = (const char *[]){ "pxo" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+		},
+	},
+};
+
+static struct clk_branch sata_a_clk = {
+	.halt_reg = 0x2fc0,
+	.halt_bit = 12,
+	.clkr = {
+		.enable_reg = 0x2c20,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_a_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch sata_h_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 27,
+	.clkr = {
+		.enable_reg = 0x2c00,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch sfab_sata_s_h_clk = {
+	.halt_reg = 0x2fc4,
+	.halt_bit = 14,
+	.clkr = {
+		.enable_reg = 0x2480,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sfab_sata_s_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch sata_phy_cfg_clk = {
+	.halt_reg = 0x2fcc,
+	.halt_bit = 12,
+	.clkr = {
+		.enable_reg = 0x2c40,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "sata_phy_cfg_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie_phy_ref_clk = {
+	.halt_reg = 0x2fdc,
+	.halt_bit = 29,
+	.clkr = {
+		.enable_reg = 0x22d0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie_phy_ref_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie_h_clk = {
+	.halt_reg = 0x2fd4,
+	.halt_bit = 8,
+	.clkr = {
+		.enable_reg = 0x22cc,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie_h_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
+static struct clk_branch pcie_a_clk = {
+	.halt_reg = 0x2fc0,
+	.halt_bit = 13,
+	.clkr = {
+		.enable_reg = 0x22c0,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie_a_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
 static struct clk_branch pmic_arb0_h_clk = {
 	.halt_reg = 0x2fd8,
 	.halt_check = BRANCH_HALT_VOTED,
@@ -2869,13 +3246,205 @@ static const struct qcom_reset_map gcc_msm8960_resets[] = {
 };
 
 static struct clk_regmap *gcc_apq8064_clks[] = {
+	[PLL3] = &pll3.clkr,
 	[PLL8] = &pll8.clkr,
 	[PLL8_VOTE] = &pll8_vote,
+	[PLL14] = &pll14.clkr,
+	[PLL14_VOTE] = &pll14_vote,
+	[GSBI1_UART_SRC] = &gsbi1_uart_src.clkr,
+	[GSBI1_UART_CLK] = &gsbi1_uart_clk.clkr,
+	[GSBI2_UART_SRC] = &gsbi2_uart_src.clkr,
+	[GSBI2_UART_CLK] = &gsbi2_uart_clk.clkr,
+	[GSBI3_UART_SRC] = &gsbi3_uart_src.clkr,
+	[GSBI3_UART_CLK] = &gsbi3_uart_clk.clkr,
+	[GSBI4_UART_SRC] = &gsbi4_uart_src.clkr,
+	[GSBI4_UART_CLK] = &gsbi4_uart_clk.clkr,
+	[GSBI5_UART_SRC] = &gsbi5_uart_src.clkr,
+	[GSBI5_UART_CLK] = &gsbi5_uart_clk.clkr,
+	[GSBI6_UART_SRC] = &gsbi6_uart_src.clkr,
+	[GSBI6_UART_CLK] = &gsbi6_uart_clk.clkr,
 	[GSBI7_UART_SRC] = &gsbi7_uart_src.clkr,
 	[GSBI7_UART_CLK] = &gsbi7_uart_clk.clkr,
+	[GSBI1_QUP_SRC] = &gsbi1_qup_src.clkr,
+	[GSBI1_QUP_CLK] = &gsbi1_qup_clk.clkr,
+	[GSBI2_QUP_SRC] = &gsbi2_qup_src.clkr,
+	[GSBI2_QUP_CLK] = &gsbi2_qup_clk.clkr,
+	[GSBI3_QUP_SRC] = &gsbi3_qup_src.clkr,
+	[GSBI3_QUP_CLK] = &gsbi3_qup_clk.clkr,
+	[GSBI4_QUP_SRC] = &gsbi4_qup_src.clkr,
+	[GSBI4_QUP_CLK] = &gsbi4_qup_clk.clkr,
+	[GSBI5_QUP_SRC] = &gsbi5_qup_src.clkr,
+	[GSBI5_QUP_CLK] = &gsbi5_qup_clk.clkr,
+	[GSBI6_QUP_SRC] = &gsbi6_qup_src.clkr,
+	[GSBI6_QUP_CLK] = &gsbi6_qup_clk.clkr,
 	[GSBI7_QUP_SRC] = &gsbi7_qup_src.clkr,
 	[GSBI7_QUP_CLK] = &gsbi7_qup_clk.clkr,
+	[GP0_SRC] = &gp0_src.clkr,
+	[GP0_CLK] = &gp0_clk.clkr,
+	[GP1_SRC] = &gp1_src.clkr,
+	[GP1_CLK] = &gp1_clk.clkr,
+	[GP2_SRC] = &gp2_src.clkr,
+	[GP2_CLK] = &gp2_clk.clkr,
+	[PMEM_A_CLK] = &pmem_clk.clkr,
+	[PRNG_SRC] = &prng_src.clkr,
+	[PRNG_CLK] = &prng_clk.clkr,
+	[SDC1_SRC] = &sdc1_src.clkr,
+	[SDC1_CLK] = &sdc1_clk.clkr,
+	[SDC2_SRC] = &sdc2_src.clkr,
+	[SDC2_CLK] = &sdc2_clk.clkr,
+	[SDC3_SRC] = &sdc3_src.clkr,
+	[SDC3_CLK] = &sdc3_clk.clkr,
+	[SDC4_SRC] = &sdc4_src.clkr,
+	[SDC4_CLK] = &sdc4_clk.clkr,
+	[TSIF_REF_SRC] = &tsif_ref_src.clkr,
+	[TSIF_REF_CLK] = &tsif_ref_clk.clkr,
+	[USB_HS1_XCVR_SRC] = &usb_hs1_xcvr_src.clkr,
+	[USB_HS1_XCVR_CLK] = &usb_hs1_xcvr_clk.clkr,
+	[USB_HS3_XCVR_SRC] = &usb_hs3_xcvr_src.clkr,
+	[USB_HS3_XCVR_CLK] = &usb_hs3_xcvr_clk.clkr,
+	[USB_HS4_XCVR_SRC] = &usb_hs4_xcvr_src.clkr,
+	[USB_HS4_XCVR_CLK] = &usb_hs4_xcvr_clk.clkr,
+	[USB_HSIC_XCVR_FS_SRC] = &usb_hsic_xcvr_fs_src.clkr,
+	[USB_HSIC_XCVR_FS_CLK] = &usb_hsic_xcvr_fs_clk.clkr,
+	[USB_HSIC_SYSTEM_CLK] = &usb_hsic_system_clk.clkr,
+	[USB_HSIC_HSIC_CLK] = &usb_hsic_hsic_clk.clkr,
+	[USB_HSIC_HSIO_CAL_CLK] = &usb_hsic_hsio_cal_clk.clkr,
+	[USB_FS1_XCVR_FS_SRC] = &usb_fs1_xcvr_fs_src.clkr,
+	[USB_FS1_XCVR_FS_CLK] = &usb_fs1_xcvr_fs_clk.clkr,
+	[USB_FS1_SYSTEM_CLK] = &usb_fs1_system_clk.clkr,
+	[SATA_H_CLK] = &sata_h_clk.clkr,
+	[SATA_CLK_SRC] = &sata_clk_src.clkr,
+	[SATA_RXOOB_CLK] = &sata_rxoob_clk.clkr,
+	[SATA_PMALIVE_CLK] = &sata_pmalive_clk.clkr,
+	[SATA_PHY_REF_CLK] = &sata_phy_ref_clk.clkr,
+	[SATA_PHY_CFG_CLK] = &sata_phy_cfg_clk.clkr,
+	[SATA_A_CLK] = &sata_a_clk.clkr,
+	[SFAB_SATA_S_H_CLK] = &sfab_sata_s_h_clk.clkr,
+	[CE3_SRC] = &ce3_src.clkr,
+	[CE3_CORE_CLK] = &ce3_core_clk.clkr,
+	[CE3_H_CLK] = &ce3_h_clk.clkr,
+	[DMA_BAM_H_CLK] = &dma_bam_h_clk.clkr,
+	[GSBI1_H_CLK] = &gsbi1_h_clk.clkr,
+	[GSBI2_H_CLK] = &gsbi2_h_clk.clkr,
+	[GSBI3_H_CLK] = &gsbi3_h_clk.clkr,
+	[GSBI4_H_CLK] = &gsbi4_h_clk.clkr,
+	[GSBI5_H_CLK] = &gsbi5_h_clk.clkr,
+	[GSBI6_H_CLK] = &gsbi6_h_clk.clkr,
 	[GSBI7_H_CLK] = &gsbi7_h_clk.clkr,
+	[TSIF_H_CLK] = &tsif_h_clk.clkr,
+	[USB_FS1_H_CLK] = &usb_fs1_h_clk.clkr,
+	[USB_HS1_H_CLK] = &usb_hs1_h_clk.clkr,
+	[USB_HSIC_H_CLK] = &usb_hsic_h_clk.clkr,
+	[USB_HS3_H_CLK] = &usb_hs3_h_clk.clkr,
+	[USB_HS4_H_CLK] = &usb_hs4_h_clk.clkr,
+	[SDC1_H_CLK] = &sdc1_h_clk.clkr,
+	[SDC2_H_CLK] = &sdc2_h_clk.clkr,
+	[SDC3_H_CLK] = &sdc3_h_clk.clkr,
+	[SDC4_H_CLK] = &sdc4_h_clk.clkr,
+	[ADM0_CLK] = &adm0_clk.clkr,
+	[ADM0_PBUS_CLK] = &adm0_pbus_clk.clkr,
+	[PCIE_A_CLK] = &pcie_a_clk.clkr,
+	[PCIE_PHY_REF_CLK] = &pcie_phy_ref_clk.clkr,
+	[PCIE_H_CLK] = &pcie_h_clk.clkr,
+	[PMIC_ARB0_H_CLK] = &pmic_arb0_h_clk.clkr,
+	[PMIC_ARB1_H_CLK] = &pmic_arb1_h_clk.clkr,
+	[PMIC_SSBI2_CLK] = &pmic_ssbi2_clk.clkr,
+	[RPM_MSG_RAM_H_CLK] = &rpm_msg_ram_h_clk.clkr,
+};
+
+static const struct qcom_reset_map gcc_apq8064_resets[] = {
+	[QDSS_STM_RESET] = { 0x2060, 6 },
+	[AFAB_SMPSS_S_RESET] = { 0x20b8, 2 },
+	[AFAB_SMPSS_M1_RESET] = { 0x20b8, 1 },
+	[AFAB_SMPSS_M0_RESET] = { 0x20b8 },
+	[AFAB_EBI1_CH0_RESET] = { 0x20c0, 7 },
+	[AFAB_EBI1_CH1_RESET] = { 0x20c4, 7},
+	[SFAB_ADM0_M0_RESET] = { 0x21e0, 7 },
+	[SFAB_ADM0_M1_RESET] = { 0x21e4, 7 },
+	[SFAB_ADM0_M2_RESET] = { 0x21e8, 7 },
+	[ADM0_C2_RESET] = { 0x220c, 4},
+	[ADM0_C1_RESET] = { 0x220c, 3},
+	[ADM0_C0_RESET] = { 0x220c, 2},
+	[ADM0_PBUS_RESET] = { 0x220c, 1 },
+	[ADM0_RESET] = { 0x220c },
+	[QDSS_CLKS_SW_RESET] = { 0x2260, 5 },
+	[QDSS_POR_RESET] = { 0x2260, 4 },
+	[QDSS_TSCTR_RESET] = { 0x2260, 3 },
+	[QDSS_HRESET_RESET] = { 0x2260, 2 },
+	[QDSS_AXI_RESET] = { 0x2260, 1 },
+	[QDSS_DBG_RESET] = { 0x2260 },
+	[SFAB_PCIE_M_RESET] = { 0x22d8, 1 },
+	[SFAB_PCIE_S_RESET] = { 0x22d8 },
+	[PCIE_EXT_PCI_RESET] = { 0x22dc, 6 },
+	[PCIE_PHY_RESET] = { 0x22dc, 5 },
+	[PCIE_PCI_RESET] = { 0x22dc, 4 },
+	[PCIE_POR_RESET] = { 0x22dc, 3 },
+	[PCIE_HCLK_RESET] = { 0x22dc, 2 },
+	[PCIE_ACLK_RESET] = { 0x22dc },
+	[SFAB_USB3_M_RESET] = { 0x2360, 7 },
+	[SFAB_RIVA_M_RESET] = { 0x2380, 7 },
+	[SFAB_LPASS_RESET] = { 0x23a0, 7 },
+	[SFAB_AFAB_M_RESET] = { 0x23e0, 7 },
+	[AFAB_SFAB_M0_RESET] = { 0x2420, 7 },
+	[AFAB_SFAB_M1_RESET] = { 0x2424, 7 },
+	[SFAB_SATA_S_RESET] = { 0x2480, 7 },
+	[SFAB_DFAB_M_RESET] = { 0x2500, 7 },
+	[DFAB_SFAB_M_RESET] = { 0x2520, 7 },
+	[DFAB_SWAY0_RESET] = { 0x2540, 7 },
+	[DFAB_SWAY1_RESET] = { 0x2544, 7 },
+	[DFAB_ARB0_RESET] = { 0x2560, 7 },
+	[DFAB_ARB1_RESET] = { 0x2564, 7 },
+	[PPSS_PROC_RESET] = { 0x2594, 1 },
+	[PPSS_RESET] = { 0x2594},
+	[DMA_BAM_RESET] = { 0x25c0, 7 },
+	[SPS_TIC_H_RESET] = { 0x2600, 7 },
+	[SFAB_CFPB_M_RESET] = { 0x2680, 7 },
+	[SFAB_CFPB_S_RESET] = { 0x26c0, 7 },
+	[TSIF_H_RESET] = { 0x2700, 7 },
+	[CE1_H_RESET] = { 0x2720, 7 },
+	[CE1_CORE_RESET] = { 0x2724, 7 },
+	[CE1_SLEEP_RESET] = { 0x2728, 7 },
+	[CE2_H_RESET] = { 0x2740, 7 },
+	[CE2_CORE_RESET] = { 0x2744, 7 },
+	[SFAB_SFPB_M_RESET] = { 0x2780, 7 },
+	[SFAB_SFPB_S_RESET] = { 0x27a0, 7 },
+	[RPM_PROC_RESET] = { 0x27c0, 7 },
+	[PMIC_SSBI2_RESET] = { 0x280c, 12 },
+	[SDC1_RESET] = { 0x2830 },
+	[SDC2_RESET] = { 0x2850 },
+	[SDC3_RESET] = { 0x2870 },
+	[SDC4_RESET] = { 0x2890 },
+	[USB_HS1_RESET] = { 0x2910 },
+	[USB_HSIC_RESET] = { 0x2934 },
+	[USB_FS1_XCVR_RESET] = { 0x2974, 1 },
+	[USB_FS1_RESET] = { 0x2974 },
+	[GSBI1_RESET] = { 0x29dc },
+	[GSBI2_RESET] = { 0x29fc },
+	[GSBI3_RESET] = { 0x2a1c },
+	[GSBI4_RESET] = { 0x2a3c },
+	[GSBI5_RESET] = { 0x2a5c },
+	[GSBI6_RESET] = { 0x2a7c },
+	[GSBI7_RESET] = { 0x2a9c },
+	[SPDM_RESET] = { 0x2b6c },
+	[TLMM_H_RESET] = { 0x2ba0, 7 },
+	[SATA_SFAB_M_RESET] = { 0x2c18 },
+	[SATA_RESET] = { 0x2c1c },
+	[GSS_SLP_RESET] = { 0x2c60, 7 },
+	[GSS_RESET] = { 0x2c64 },
+	[TSSC_RESET] = { 0x2ca0, 7 },
+	[PDM_RESET] = { 0x2cc0, 12 },
+	[MPM_H_RESET] = { 0x2da0, 7 },
+	[MPM_RESET] = { 0x2da4 },
+	[SFAB_SMPSS_S_RESET] = { 0x2e00, 7 },
+	[PRNG_RESET] = { 0x2e80, 12 },
+	[RIVA_RESET] = { 0x35e0 },
+	[CE3_H_RESET] = { 0x36c4, 7 },
+	[SFAB_CE3_M_RESET] = { 0x36c8, 1 },
+	[SFAB_CE3_S_RESET] = { 0x36c8 },
+	[CE3_RESET] = { 0x36cc, 7 },
+	[CE3_SLEEP_RESET] = { 0x36d0, 7 },
+	[USB_HS3_RESET] = { 0x3710 },
+	[USB_HS4_RESET] = { 0x3730 },
 };
 
 static const struct regmap_config gcc_msm8960_regmap_config = {
@@ -2886,6 +3455,14 @@ static const struct regmap_config gcc_msm8960_regmap_config = {
 	.fast_io	= true,
 };
 
+static const struct regmap_config gcc_apq8064_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x3880,
+	.fast_io	= true,
+};
+
 static const struct qcom_cc_desc gcc_msm8960_desc = {
 	.config = &gcc_msm8960_regmap_config,
 	.clks = gcc_msm8960_clks,
@@ -2895,11 +3472,11 @@ static const struct qcom_cc_desc gcc_msm8960_desc = {
 };
 
 static const struct qcom_cc_desc gcc_apq8064_desc = {
-	.config = &gcc_msm8960_regmap_config,
+	.config = &gcc_apq8064_regmap_config,
 	.clks = gcc_apq8064_clks,
 	.num_clks = ARRAY_SIZE(gcc_apq8064_clks),
-	.resets = gcc_msm8960_resets,
-	.num_resets = ARRAY_SIZE(gcc_msm8960_resets),
+	.resets = gcc_apq8064_resets,
+	.num_resets = ARRAY_SIZE(gcc_apq8064_resets),
 };
 
 static const struct of_device_id gcc_msm8960_match_table[] = {
diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c
new file mode 100644
index 00000000000..751eea376a2
--- /dev/null
+++ b/drivers/clk/qcom/mmcc-apq8084.c
@@ -0,0 +1,3352 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+
+#include <dt-bindings/clock/qcom,mmcc-apq8084.h>
+#include <dt-bindings/reset/qcom,mmcc-apq8084.h>
+
+#include "common.h"
+#include "clk-regmap.h"
+#include "clk-pll.h"
+#include "clk-rcg.h"
+#include "clk-branch.h"
+#include "reset.h"
+
+#define P_XO		0
+#define P_MMPLL0	1
+#define P_EDPLINK	1
+#define P_MMPLL1	2
+#define P_HDMIPLL	2
+#define P_GPLL0		3
+#define P_EDPVCO	3
+#define P_MMPLL4	4
+#define P_DSI0PLL	4
+#define P_DSI0PLL_BYTE	4
+#define P_MMPLL2	4
+#define P_MMPLL3	4
+#define P_GPLL1		5
+#define P_DSI1PLL	5
+#define P_DSI1PLL_BYTE	5
+#define P_MMSLEEP	6
+
+static const u8 mmcc_xo_mmpll0_mmpll1_gpll0_map[] = {
+	[P_XO]		= 0,
+	[P_MMPLL0]	= 1,
+	[P_MMPLL1]	= 2,
+	[P_GPLL0]	= 5,
+};
+
+static const char *mmcc_xo_mmpll0_mmpll1_gpll0[] = {
+	"xo",
+	"mmpll0_vote",
+	"mmpll1_vote",
+	"mmss_gpll0_vote",
+};
+
+static const u8 mmcc_xo_mmpll0_dsi_hdmi_gpll0_map[] = {
+	[P_XO]		= 0,
+	[P_MMPLL0]	= 1,
+	[P_HDMIPLL]	= 4,
+	[P_GPLL0]	= 5,
+	[P_DSI0PLL]	= 2,
+	[P_DSI1PLL]	= 3,
+};
+
+static const char *mmcc_xo_mmpll0_dsi_hdmi_gpll0[] = {
+	"xo",
+	"mmpll0_vote",
+	"hdmipll",
+	"mmss_gpll0_vote",
+	"dsi0pll",
+	"dsi1pll",
+};
+
+static const u8 mmcc_xo_mmpll0_1_2_gpll0_map[] = {
+	[P_XO]		= 0,
+	[P_MMPLL0]	= 1,
+	[P_MMPLL1]	= 2,
+	[P_GPLL0]	= 5,
+	[P_MMPLL2]	= 3,
+};
+
+static const char *mmcc_xo_mmpll0_1_2_gpll0[] = {
+	"xo",
+	"mmpll0_vote",
+	"mmpll1_vote",
+	"mmss_gpll0_vote",
+	"mmpll2",
+};
+
+static const u8 mmcc_xo_mmpll0_1_3_gpll0_map[] = {
+	[P_XO]		= 0,
+	[P_MMPLL0]	= 1,
+	[P_MMPLL1]	= 2,
+	[P_GPLL0]	= 5,
+	[P_MMPLL3]	= 3,
+};
+
+static const char *mmcc_xo_mmpll0_1_3_gpll0[] = {
+	"xo",
+	"mmpll0_vote",
+	"mmpll1_vote",
+	"mmss_gpll0_vote",
+	"mmpll3",
+};
+
+static const u8 mmcc_xo_dsi_hdmi_edp_map[] = {
+	[P_XO]		= 0,
+	[P_EDPLINK]	= 4,
+	[P_HDMIPLL]	= 3,
+	[P_EDPVCO]	= 5,
+	[P_DSI0PLL]	= 1,
+	[P_DSI1PLL]	= 2,
+};
+
+static const char *mmcc_xo_dsi_hdmi_edp[] = {
+	"xo",
+	"edp_link_clk",
+	"hdmipll",
+	"edp_vco_div",
+	"dsi0pll",
+	"dsi1pll",
+};
+
+static const u8 mmcc_xo_dsi_hdmi_edp_gpll0_map[] = {
+	[P_XO]		= 0,
+	[P_EDPLINK]	= 4,
+	[P_HDMIPLL]	= 3,
+	[P_GPLL0]	= 5,
+	[P_DSI0PLL]	= 1,
+	[P_DSI1PLL]	= 2,
+};
+
+static const char *mmcc_xo_dsi_hdmi_edp_gpll0[] = {
+	"xo",
+	"edp_link_clk",
+	"hdmipll",
+	"gpll0_vote",
+	"dsi0pll",
+	"dsi1pll",
+};
+
+static const u8 mmcc_xo_dsibyte_hdmi_edp_gpll0_map[] = {
+	[P_XO]			= 0,
+	[P_EDPLINK]		= 4,
+	[P_HDMIPLL]		= 3,
+	[P_GPLL0]		= 5,
+	[P_DSI0PLL_BYTE]	= 1,
+	[P_DSI1PLL_BYTE]	= 2,
+};
+
+static const char *mmcc_xo_dsibyte_hdmi_edp_gpll0[] = {
+	"xo",
+	"edp_link_clk",
+	"hdmipll",
+	"gpll0_vote",
+	"dsi0pllbyte",
+	"dsi1pllbyte",
+};
+
+static const u8 mmcc_xo_mmpll0_1_4_gpll0_map[] = {
+	[P_XO]		= 0,
+	[P_MMPLL0]	= 1,
+	[P_MMPLL1]	= 2,
+	[P_GPLL0]	= 5,
+	[P_MMPLL4]	= 3,
+};
+
+static const char *mmcc_xo_mmpll0_1_4_gpll0[] = {
+	"xo",
+	"mmpll0",
+	"mmpll1",
+	"mmpll4",
+	"gpll0",
+};
+
+static const u8 mmcc_xo_mmpll0_1_4_gpll1_0_map[] = {
+	[P_XO]		= 0,
+	[P_MMPLL0]	= 1,
+	[P_MMPLL1]	= 2,
+	[P_MMPLL4]	= 3,
+	[P_GPLL0]	= 5,
+	[P_GPLL1]	= 4,
+};
+
+static const char *mmcc_xo_mmpll0_1_4_gpll1_0[] = {
+	"xo",
+	"mmpll0",
+	"mmpll1",
+	"mmpll4",
+	"gpll1",
+	"gpll0",
+};
+
+static const u8 mmcc_xo_mmpll0_1_4_gpll1_0_sleep_map[] = {
+	[P_XO]		= 0,
+	[P_MMPLL0]	= 1,
+	[P_MMPLL1]	= 2,
+	[P_MMPLL4]	= 3,
+	[P_GPLL0]	= 5,
+	[P_GPLL1]	= 4,
+	[P_MMSLEEP]	= 6,
+};
+
+static const char *mmcc_xo_mmpll0_1_4_gpll1_0_sleep[] = {
+	"xo",
+	"mmpll0",
+	"mmpll1",
+	"mmpll4",
+	"gpll1",
+	"gpll0",
+	"sleep_clk_src",
+};
+
+#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
+
+static struct clk_pll mmpll0 = {
+	.l_reg = 0x0004,
+	.m_reg = 0x0008,
+	.n_reg = 0x000c,
+	.config_reg = 0x0014,
+	.mode_reg = 0x0000,
+	.status_reg = 0x001c,
+	.status_bit = 17,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll0",
+		.parent_names = (const char *[]){ "xo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_regmap mmpll0_vote = {
+	.enable_reg = 0x0100,
+	.enable_mask = BIT(0),
+	.hw.init = &(struct clk_init_data){
+		.name = "mmpll0_vote",
+		.parent_names = (const char *[]){ "mmpll0" },
+		.num_parents = 1,
+		.ops = &clk_pll_vote_ops,
+	},
+};
+
+static struct clk_pll mmpll1 = {
+	.l_reg = 0x0044,
+	.m_reg = 0x0048,
+	.n_reg = 0x004c,
+	.config_reg = 0x0050,
+	.mode_reg = 0x0040,
+	.status_reg = 0x005c,
+	.status_bit = 17,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll1",
+		.parent_names = (const char *[]){ "xo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_regmap mmpll1_vote = {
+	.enable_reg = 0x0100,
+	.enable_mask = BIT(1),
+	.hw.init = &(struct clk_init_data){
+		.name = "mmpll1_vote",
+		.parent_names = (const char *[]){ "mmpll1" },
+		.num_parents = 1,
+		.ops = &clk_pll_vote_ops,
+	},
+};
+
+static struct clk_pll mmpll2 = {
+	.l_reg = 0x4104,
+	.m_reg = 0x4108,
+	.n_reg = 0x410c,
+	.config_reg = 0x4110,
+	.mode_reg = 0x4100,
+	.status_reg = 0x411c,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll2",
+		.parent_names = (const char *[]){ "xo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_pll mmpll3 = {
+	.l_reg = 0x0084,
+	.m_reg = 0x0088,
+	.n_reg = 0x008c,
+	.config_reg = 0x0090,
+	.mode_reg = 0x0080,
+	.status_reg = 0x009c,
+	.status_bit = 17,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll3",
+		.parent_names = (const char *[]){ "xo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_pll mmpll4 = {
+	.l_reg = 0x00a4,
+	.m_reg = 0x00a8,
+	.n_reg = 0x00ac,
+	.config_reg = 0x00b0,
+	.mode_reg = 0x0080,
+	.status_reg = 0x00bc,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll4",
+		.parent_names = (const char *[]){ "xo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static struct clk_rcg2 mmss_ahb_clk_src = {
+	.cmd_rcgr = 0x5000,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmss_ahb_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_mmss_axi_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(37500000, P_GPLL0, 16, 0, 0),
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(75000000, P_GPLL0, 8, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(150000000, P_GPLL0, 4, 0, 0),
+	F(333430000, P_MMPLL1, 3.5, 0, 0),
+	F(400000000, P_MMPLL0, 2, 0, 0),
+	F(466800000, P_MMPLL1, 2.5, 0, 0),
+};
+
+static struct clk_rcg2 mmss_axi_clk_src = {
+	.cmd_rcgr = 0x5040,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_mmss_axi_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmss_axi_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_ocmemnoc_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(37500000, P_GPLL0, 16, 0, 0),
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(75000000, P_GPLL0, 8, 0, 0),
+	F(109090000, P_GPLL0, 5.5, 0, 0),
+	F(150000000, P_GPLL0, 4, 0, 0),
+	F(228570000, P_MMPLL0, 3.5, 0, 0),
+	F(320000000, P_MMPLL0, 2.5, 0, 0),
+};
+
+static struct clk_rcg2 ocmemnoc_clk_src = {
+	.cmd_rcgr = 0x5090,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_ocmemnoc_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ocmemnoc_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_camss_csi0_3_clk[] = {
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(200000000, P_MMPLL0, 4, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 csi0_clk_src = {
+	.cmd_rcgr = 0x3090,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_csi0_3_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi0_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi1_clk_src = {
+	.cmd_rcgr = 0x3100,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_csi0_3_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi1_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi2_clk_src = {
+	.cmd_rcgr = 0x3160,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_csi0_3_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi2_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi3_clk_src = {
+	.cmd_rcgr = 0x31c0,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_csi0_3_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi3_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_camss_vfe_vfe0_1_clk[] = {
+	F(37500000, P_GPLL0, 16, 0, 0),
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(60000000, P_GPLL0, 10, 0, 0),
+	F(80000000, P_GPLL0, 7.5, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(109090000, P_GPLL0, 5.5, 0, 0),
+	F(133330000, P_GPLL0, 4.5, 0, 0),
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(228570000, P_MMPLL0, 3.5, 0, 0),
+	F(266670000, P_MMPLL0, 3, 0, 0),
+	F(320000000, P_MMPLL0, 2.5, 0, 0),
+	F(465000000, P_MMPLL4, 2, 0, 0),
+	F(600000000, P_GPLL0, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 vfe0_clk_src = {
+	.cmd_rcgr = 0x3600,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_vfe_vfe0_1_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vfe0_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 vfe1_clk_src = {
+	.cmd_rcgr = 0x3620,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_vfe_vfe0_1_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vfe1_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_mdss_mdp_clk[] = {
+	F(37500000, P_GPLL0, 16, 0, 0),
+	F(60000000, P_GPLL0, 10, 0, 0),
+	F(75000000, P_GPLL0, 8, 0, 0),
+	F(85710000, P_GPLL0, 7, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(150000000, P_GPLL0, 4, 0, 0),
+	F(160000000, P_MMPLL0, 5, 0, 0),
+	F(200000000, P_MMPLL0, 4, 0, 0),
+	F(228570000, P_MMPLL0, 3.5, 0, 0),
+	F(300000000, P_GPLL0, 2, 0, 0),
+	F(320000000, P_MMPLL0, 2.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 mdp_clk_src = {
+	.cmd_rcgr = 0x2040,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_dsi_hdmi_gpll0_map,
+	.freq_tbl = ftbl_mdss_mdp_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mdp_clk_src",
+		.parent_names = mmcc_xo_mmpll0_dsi_hdmi_gpll0,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gfx3d_clk_src = {
+	.cmd_rcgr = 0x4000,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_2_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gfx3d_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_2_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_camss_jpeg_jpeg0_2_clk[] = {
+	F(75000000, P_GPLL0, 8, 0, 0),
+	F(133330000, P_GPLL0, 4.5, 0, 0),
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(228570000, P_MMPLL0, 3.5, 0, 0),
+	F(266670000, P_MMPLL0, 3, 0, 0),
+	F(320000000, P_MMPLL0, 2.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 jpeg0_clk_src = {
+	.cmd_rcgr = 0x3500,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_jpeg_jpeg0_2_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "jpeg0_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 jpeg1_clk_src = {
+	.cmd_rcgr = 0x3520,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_jpeg_jpeg0_2_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "jpeg1_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 jpeg2_clk_src = {
+	.cmd_rcgr = 0x3540,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_jpeg_jpeg0_2_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "jpeg2_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl pixel_freq_tbl[] = {
+	{ .src = P_DSI0PLL },
+	{ }
+};
+
+static struct clk_rcg2 pclk0_clk_src = {
+	.cmd_rcgr = 0x2000,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_dsi_hdmi_edp_gpll0_map,
+	.freq_tbl = pixel_freq_tbl,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pclk0_clk_src",
+		.parent_names = mmcc_xo_dsi_hdmi_edp_gpll0,
+		.num_parents = 6,
+		.ops = &clk_pixel_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_rcg2 pclk1_clk_src = {
+	.cmd_rcgr = 0x2020,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_dsi_hdmi_edp_gpll0_map,
+	.freq_tbl = pixel_freq_tbl,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pclk1_clk_src",
+		.parent_names = mmcc_xo_dsi_hdmi_edp_gpll0,
+		.num_parents = 6,
+		.ops = &clk_pixel_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct freq_tbl ftbl_venus0_vcodec0_clk[] = {
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(133330000, P_GPLL0, 4.5, 0, 0),
+	F(200000000, P_MMPLL0, 4, 0, 0),
+	F(266670000, P_MMPLL0, 3, 0, 0),
+	F(465000000, P_MMPLL3, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 vcodec0_clk_src = {
+	.cmd_rcgr = 0x1000,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_3_gpll0_map,
+	.freq_tbl = ftbl_venus0_vcodec0_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vcodec0_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_3_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_avsync_vp_clk[] = {
+	F(150000000, P_GPLL0, 4, 0, 0),
+	F(320000000, P_MMPLL0, 2.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 vp_clk_src = {
+	.cmd_rcgr = 0x2430,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_avsync_vp_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vp_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_camss_cci_cci_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cci_clk_src = {
+	.cmd_rcgr = 0x3300,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll1_0_map,
+	.freq_tbl = ftbl_camss_cci_cci_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cci_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll1_0,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_camss_gp0_1_clk[] = {
+	F(10000, P_XO, 16, 1, 120),
+	F(24000, P_XO, 16, 1, 50),
+	F(6000000, P_GPLL0, 10, 1, 10),
+	F(12000000, P_GPLL0, 10, 1, 5),
+	F(13000000, P_GPLL0, 4, 13, 150),
+	F(24000000, P_GPLL0, 5, 1, 5),
+	{ }
+};
+
+static struct clk_rcg2 camss_gp0_clk_src = {
+	.cmd_rcgr = 0x3420,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll1_0_sleep_map,
+	.freq_tbl = ftbl_camss_gp0_1_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "camss_gp0_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll1_0_sleep,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 camss_gp1_clk_src = {
+	.cmd_rcgr = 0x3450,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll1_0_sleep_map,
+	.freq_tbl = ftbl_camss_gp0_1_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "camss_gp1_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll1_0_sleep,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_camss_mclk0_3_clk[] = {
+	F(4800000, P_XO, 4, 0, 0),
+	F(6000000, P_GPLL0, 10, 1, 10),
+	F(8000000, P_GPLL0, 15, 1, 5),
+	F(9600000, P_XO, 2, 0, 0),
+	F(16000000, P_MMPLL0, 10, 1, 5),
+	F(19200000, P_XO, 1, 0, 0),
+	F(24000000, P_GPLL0, 5, 1, 5),
+	F(32000000, P_MMPLL0, 5, 1, 5),
+	F(48000000, P_GPLL0, 12.5, 0, 0),
+	F(64000000, P_MMPLL0, 12.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 mclk0_clk_src = {
+	.cmd_rcgr = 0x3360,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll1_0_map,
+	.freq_tbl = ftbl_camss_mclk0_3_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mclk0_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll1_0,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 mclk1_clk_src = {
+	.cmd_rcgr = 0x3390,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll1_0_map,
+	.freq_tbl = ftbl_camss_mclk0_3_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mclk1_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll1_0,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 mclk2_clk_src = {
+	.cmd_rcgr = 0x33c0,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll1_0_map,
+	.freq_tbl = ftbl_camss_mclk0_3_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mclk2_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll1_0,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 mclk3_clk_src = {
+	.cmd_rcgr = 0x33f0,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll1_0_map,
+	.freq_tbl = ftbl_camss_mclk0_3_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mclk3_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll1_0,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_camss_phy0_2_csi0_2phytimer_clk[] = {
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(200000000, P_MMPLL0, 4, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 csi0phytimer_clk_src = {
+	.cmd_rcgr = 0x3000,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_phy0_2_csi0_2phytimer_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi0phytimer_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi1phytimer_clk_src = {
+	.cmd_rcgr = 0x3030,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_phy0_2_csi0_2phytimer_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi1phytimer_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi2phytimer_clk_src = {
+	.cmd_rcgr = 0x3060,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_phy0_2_csi0_2phytimer_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi2phytimer_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_camss_vfe_cpp_clk[] = {
+	F(133330000, P_GPLL0, 4.5, 0, 0),
+	F(266670000, P_MMPLL0, 3, 0, 0),
+	F(320000000, P_MMPLL0, 2.5, 0, 0),
+	F(372000000, P_MMPLL4, 2.5, 0, 0),
+	F(465000000, P_MMPLL4, 2, 0, 0),
+	F(600000000, P_GPLL0, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cpp_clk_src = {
+	.cmd_rcgr = 0x3640,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_1_4_gpll0_map,
+	.freq_tbl = ftbl_camss_vfe_cpp_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cpp_clk_src",
+		.parent_names = mmcc_xo_mmpll0_1_4_gpll0,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl byte_freq_tbl[] = {
+	{ .src = P_DSI0PLL_BYTE },
+	{ }
+};
+
+static struct clk_rcg2 byte0_clk_src = {
+	.cmd_rcgr = 0x2120,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_dsibyte_hdmi_edp_gpll0_map,
+	.freq_tbl = byte_freq_tbl,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "byte0_clk_src",
+		.parent_names = mmcc_xo_dsibyte_hdmi_edp_gpll0,
+		.num_parents = 6,
+		.ops = &clk_byte_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_rcg2 byte1_clk_src = {
+	.cmd_rcgr = 0x2140,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_dsibyte_hdmi_edp_gpll0_map,
+	.freq_tbl = byte_freq_tbl,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "byte1_clk_src",
+		.parent_names = mmcc_xo_dsibyte_hdmi_edp_gpll0,
+		.num_parents = 6,
+		.ops = &clk_byte_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct freq_tbl ftbl_mdss_edpaux_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 edpaux_clk_src = {
+	.cmd_rcgr = 0x20e0,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_mdss_edpaux_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "edpaux_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_mdss_edplink_clk[] = {
+	F(135000000, P_EDPLINK, 2, 0, 0),
+	F(270000000, P_EDPLINK, 11, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 edplink_clk_src = {
+	.cmd_rcgr = 0x20c0,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_dsi_hdmi_edp_gpll0_map,
+	.freq_tbl = ftbl_mdss_edplink_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "edplink_clk_src",
+		.parent_names = mmcc_xo_dsi_hdmi_edp_gpll0,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct freq_tbl edp_pixel_freq_tbl[] = {
+	{ .src = P_EDPVCO },
+	{ }
+};
+
+static struct clk_rcg2 edppixel_clk_src = {
+	.cmd_rcgr = 0x20a0,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_dsi_hdmi_edp_map,
+	.freq_tbl = edp_pixel_freq_tbl,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "edppixel_clk_src",
+		.parent_names = mmcc_xo_dsi_hdmi_edp,
+		.num_parents = 6,
+		.ops = &clk_edp_pixel_ops,
+	},
+};
+
+static struct freq_tbl ftbl_mdss_esc0_1_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 esc0_clk_src = {
+	.cmd_rcgr = 0x2160,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_dsibyte_hdmi_edp_gpll0_map,
+	.freq_tbl = ftbl_mdss_esc0_1_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "esc0_clk_src",
+		.parent_names = mmcc_xo_dsibyte_hdmi_edp_gpll0,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 esc1_clk_src = {
+	.cmd_rcgr = 0x2180,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_dsibyte_hdmi_edp_gpll0_map,
+	.freq_tbl = ftbl_mdss_esc0_1_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "esc1_clk_src",
+		.parent_names = mmcc_xo_dsibyte_hdmi_edp_gpll0,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl extpclk_freq_tbl[] = {
+	{ .src = P_HDMIPLL },
+	{ }
+};
+
+static struct clk_rcg2 extpclk_clk_src = {
+	.cmd_rcgr = 0x2060,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_dsi_hdmi_edp_gpll0_map,
+	.freq_tbl = extpclk_freq_tbl,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "extpclk_clk_src",
+		.parent_names = mmcc_xo_dsi_hdmi_edp_gpll0,
+		.num_parents = 6,
+		.ops = &clk_byte_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct freq_tbl ftbl_mdss_hdmi_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 hdmi_clk_src = {
+	.cmd_rcgr = 0x2100,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_mdss_hdmi_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "hdmi_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_mdss_vsync_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 vsync_clk_src = {
+	.cmd_rcgr = 0x2080,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_mdss_vsync_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vsync_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_mmss_rbcpr_clk[] = {
+	F(50000000, P_GPLL0, 12, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 rbcpr_clk_src = {
+	.cmd_rcgr = 0x4060,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_mmss_rbcpr_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "rbcpr_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_oxili_rbbmtimer_clk[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 rbbmtimer_clk_src = {
+	.cmd_rcgr = 0x4090,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_oxili_rbbmtimer_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "rbbmtimer_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_vpu_maple_clk[] = {
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(133330000, P_GPLL0, 4.5, 0, 0),
+	F(200000000, P_MMPLL0, 4, 0, 0),
+	F(266670000, P_MMPLL0, 3, 0, 0),
+	F(465000000, P_MMPLL3, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 maple_clk_src = {
+	.cmd_rcgr = 0x1320,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_vpu_maple_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "maple_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_vpu_vdp_clk[] = {
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(200000000, P_MMPLL0, 4, 0, 0),
+	F(320000000, P_MMPLL0, 2.5, 0, 0),
+	F(400000000, P_MMPLL0, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 vdp_clk_src = {
+	.cmd_rcgr = 0x1300,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_vpu_vdp_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vdp_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_vpu_bus_clk[] = {
+	F(40000000, P_GPLL0, 15, 0, 0),
+	F(80000000, P_MMPLL0, 10, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 vpu_bus_clk_src = {
+	.cmd_rcgr = 0x1340,
+	.hid_width = 5,
+	.parent_map = mmcc_xo_mmpll0_mmpll1_gpll0_map,
+	.freq_tbl = ftbl_vpu_bus_clk,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vpu_bus_clk_src",
+		.parent_names = mmcc_xo_mmpll0_mmpll1_gpll0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch mmss_cxo_clk = {
+	.halt_reg = 0x5104,
+	.clkr = {
+		.enable_reg = 0x5104,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_cxo_clk",
+			.parent_names = (const char *[]){ "xo" },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_sleepclk_clk = {
+	.halt_reg = 0x5100,
+	.clkr = {
+		.enable_reg = 0x5100,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_sleepclk_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch avsync_ahb_clk = {
+	.halt_reg = 0x2414,
+	.clkr = {
+		.enable_reg = 0x2414,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "avsync_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch avsync_edppixel_clk = {
+	.halt_reg = 0x2418,
+	.clkr = {
+		.enable_reg = 0x2418,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "avsync_edppixel_clk",
+			.parent_names = (const char *[]){
+				"edppixel_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch avsync_extpclk_clk = {
+	.halt_reg = 0x2410,
+	.clkr = {
+		.enable_reg = 0x2410,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "avsync_extpclk_clk",
+			.parent_names = (const char *[]){
+				"extpclk_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch avsync_pclk0_clk = {
+	.halt_reg = 0x241c,
+	.clkr = {
+		.enable_reg = 0x241c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "avsync_pclk0_clk",
+			.parent_names = (const char *[]){
+				"pclk0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch avsync_pclk1_clk = {
+	.halt_reg = 0x2420,
+	.clkr = {
+		.enable_reg = 0x2420,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "avsync_pclk1_clk",
+			.parent_names = (const char *[]){
+				"pclk1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch avsync_vp_clk = {
+	.halt_reg = 0x2404,
+	.clkr = {
+		.enable_reg = 0x2404,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "avsync_vp_clk",
+			.parent_names = (const char *[]){
+				"vp_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_ahb_clk = {
+	.halt_reg = 0x348c,
+	.clkr = {
+		.enable_reg = 0x348c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_cci_cci_ahb_clk = {
+	.halt_reg = 0x3348,
+	.clkr = {
+		.enable_reg = 0x3348,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cci_cci_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_cci_cci_clk = {
+	.halt_reg = 0x3344,
+	.clkr = {
+		.enable_reg = 0x3344,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cci_cci_clk",
+			.parent_names = (const char *[]){
+				"cci_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0_ahb_clk = {
+	.halt_reg = 0x30bc,
+	.clkr = {
+		.enable_reg = 0x30bc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0_clk = {
+	.halt_reg = 0x30b4,
+	.clkr = {
+		.enable_reg = 0x30b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0_clk",
+			.parent_names = (const char *[]){
+				"csi0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0phy_clk = {
+	.halt_reg = 0x30c4,
+	.clkr = {
+		.enable_reg = 0x30c4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0phy_clk",
+			.parent_names = (const char *[]){
+				"csi0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0pix_clk = {
+	.halt_reg = 0x30e4,
+	.clkr = {
+		.enable_reg = 0x30e4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0pix_clk",
+			.parent_names = (const char *[]){
+				"csi0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0rdi_clk = {
+	.halt_reg = 0x30d4,
+	.clkr = {
+		.enable_reg = 0x30d4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0rdi_clk",
+			.parent_names = (const char *[]){
+				"csi0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1_ahb_clk = {
+	.halt_reg = 0x3128,
+	.clkr = {
+		.enable_reg = 0x3128,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1_clk = {
+	.halt_reg = 0x3124,
+	.clkr = {
+		.enable_reg = 0x3124,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1_clk",
+			.parent_names = (const char *[]){
+				"csi1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1phy_clk = {
+	.halt_reg = 0x3134,
+	.clkr = {
+		.enable_reg = 0x3134,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1phy_clk",
+			.parent_names = (const char *[]){
+				"csi1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1pix_clk = {
+	.halt_reg = 0x3154,
+	.clkr = {
+		.enable_reg = 0x3154,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1pix_clk",
+			.parent_names = (const char *[]){
+				"csi1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1rdi_clk = {
+	.halt_reg = 0x3144,
+	.clkr = {
+		.enable_reg = 0x3144,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1rdi_clk",
+			.parent_names = (const char *[]){
+				"csi1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2_ahb_clk = {
+	.halt_reg = 0x3188,
+	.clkr = {
+		.enable_reg = 0x3188,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2_clk = {
+	.halt_reg = 0x3184,
+	.clkr = {
+		.enable_reg = 0x3184,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2_clk",
+			.parent_names = (const char *[]){
+				"csi2_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2phy_clk = {
+	.halt_reg = 0x3194,
+	.clkr = {
+		.enable_reg = 0x3194,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2phy_clk",
+			.parent_names = (const char *[]){
+				"csi2_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2pix_clk = {
+	.halt_reg = 0x31b4,
+	.clkr = {
+		.enable_reg = 0x31b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2pix_clk",
+			.parent_names = (const char *[]){
+				"csi2_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2rdi_clk = {
+	.halt_reg = 0x31a4,
+	.clkr = {
+		.enable_reg = 0x31a4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2rdi_clk",
+			.parent_names = (const char *[]){
+				"csi2_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi3_ahb_clk = {
+	.halt_reg = 0x31e8,
+	.clkr = {
+		.enable_reg = 0x31e8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi3_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi3_clk = {
+	.halt_reg = 0x31e4,
+	.clkr = {
+		.enable_reg = 0x31e4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi3_clk",
+			.parent_names = (const char *[]){
+				"csi3_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi3phy_clk = {
+	.halt_reg = 0x31f4,
+	.clkr = {
+		.enable_reg = 0x31f4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi3phy_clk",
+			.parent_names = (const char *[]){
+				"csi3_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi3pix_clk = {
+	.halt_reg = 0x3214,
+	.clkr = {
+		.enable_reg = 0x3214,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi3pix_clk",
+			.parent_names = (const char *[]){
+				"csi3_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi3rdi_clk = {
+	.halt_reg = 0x3204,
+	.clkr = {
+		.enable_reg = 0x3204,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi3rdi_clk",
+			.parent_names = (const char *[]){
+				"csi3_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi_vfe0_clk = {
+	.halt_reg = 0x3704,
+	.clkr = {
+		.enable_reg = 0x3704,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi_vfe0_clk",
+			.parent_names = (const char *[]){
+				"vfe0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_csi_vfe1_clk = {
+	.halt_reg = 0x3714,
+	.clkr = {
+		.enable_reg = 0x3714,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi_vfe1_clk",
+			.parent_names = (const char *[]){
+				"vfe1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_gp0_clk = {
+	.halt_reg = 0x3444,
+	.clkr = {
+		.enable_reg = 0x3444,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_gp0_clk",
+			.parent_names = (const char *[]){
+				"camss_gp0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_gp1_clk = {
+	.halt_reg = 0x3474,
+	.clkr = {
+		.enable_reg = 0x3474,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_gp1_clk",
+			.parent_names = (const char *[]){
+				"camss_gp1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_ispif_ahb_clk = {
+	.halt_reg = 0x3224,
+	.clkr = {
+		.enable_reg = 0x3224,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_ispif_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_jpeg_jpeg0_clk = {
+	.halt_reg = 0x35a8,
+	.clkr = {
+		.enable_reg = 0x35a8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_jpeg_jpeg0_clk",
+			.parent_names = (const char *[]){
+				"jpeg0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_jpeg_jpeg1_clk = {
+	.halt_reg = 0x35ac,
+	.clkr = {
+		.enable_reg = 0x35ac,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_jpeg_jpeg1_clk",
+			.parent_names = (const char *[]){
+				"jpeg1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_jpeg_jpeg2_clk = {
+	.halt_reg = 0x35b0,
+	.clkr = {
+		.enable_reg = 0x35b0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_jpeg_jpeg2_clk",
+			.parent_names = (const char *[]){
+				"jpeg2_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_jpeg_jpeg_ahb_clk = {
+	.halt_reg = 0x35b4,
+	.clkr = {
+		.enable_reg = 0x35b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_jpeg_jpeg_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_jpeg_jpeg_axi_clk = {
+	.halt_reg = 0x35b8,
+	.clkr = {
+		.enable_reg = 0x35b8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_jpeg_jpeg_axi_clk",
+			.parent_names = (const char *[]){
+				"mmss_axi_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_mclk0_clk = {
+	.halt_reg = 0x3384,
+	.clkr = {
+		.enable_reg = 0x3384,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_mclk0_clk",
+			.parent_names = (const char *[]){
+				"mclk0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_mclk1_clk = {
+	.halt_reg = 0x33b4,
+	.clkr = {
+		.enable_reg = 0x33b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_mclk1_clk",
+			.parent_names = (const char *[]){
+				"mclk1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_mclk2_clk = {
+	.halt_reg = 0x33e4,
+	.clkr = {
+		.enable_reg = 0x33e4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_mclk2_clk",
+			.parent_names = (const char *[]){
+				"mclk2_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_mclk3_clk = {
+	.halt_reg = 0x3414,
+	.clkr = {
+		.enable_reg = 0x3414,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_mclk3_clk",
+			.parent_names = (const char *[]){
+				"mclk3_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_micro_ahb_clk = {
+	.halt_reg = 0x3494,
+	.clkr = {
+		.enable_reg = 0x3494,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_micro_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_phy0_csi0phytimer_clk = {
+	.halt_reg = 0x3024,
+	.clkr = {
+		.enable_reg = 0x3024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_phy0_csi0phytimer_clk",
+			.parent_names = (const char *[]){
+				"csi0phytimer_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_phy1_csi1phytimer_clk = {
+	.halt_reg = 0x3054,
+	.clkr = {
+		.enable_reg = 0x3054,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_phy1_csi1phytimer_clk",
+			.parent_names = (const char *[]){
+				"csi1phytimer_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_phy2_csi2phytimer_clk = {
+	.halt_reg = 0x3084,
+	.clkr = {
+		.enable_reg = 0x3084,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_phy2_csi2phytimer_clk",
+			.parent_names = (const char *[]){
+				"csi2phytimer_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_top_ahb_clk = {
+	.halt_reg = 0x3484,
+	.clkr = {
+		.enable_reg = 0x3484,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_top_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe_cpp_ahb_clk = {
+	.halt_reg = 0x36b4,
+	.clkr = {
+		.enable_reg = 0x36b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe_cpp_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe_cpp_clk = {
+	.halt_reg = 0x36b0,
+	.clkr = {
+		.enable_reg = 0x36b0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe_cpp_clk",
+			.parent_names = (const char *[]){
+				"cpp_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe_vfe0_clk = {
+	.halt_reg = 0x36a8,
+	.clkr = {
+		.enable_reg = 0x36a8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe_vfe0_clk",
+			.parent_names = (const char *[]){
+				"vfe0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe_vfe1_clk = {
+	.halt_reg = 0x36ac,
+	.clkr = {
+		.enable_reg = 0x36ac,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe_vfe1_clk",
+			.parent_names = (const char *[]){
+				"vfe1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe_vfe_ahb_clk = {
+	.halt_reg = 0x36b8,
+	.clkr = {
+		.enable_reg = 0x36b8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe_vfe_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe_vfe_axi_clk = {
+	.halt_reg = 0x36bc,
+	.clkr = {
+		.enable_reg = 0x36bc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe_vfe_axi_clk",
+			.parent_names = (const char *[]){
+				"mmss_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_ahb_clk = {
+	.halt_reg = 0x2308,
+	.clkr = {
+		.enable_reg = 0x2308,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_axi_clk = {
+	.halt_reg = 0x2310,
+	.clkr = {
+		.enable_reg = 0x2310,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_axi_clk",
+			.parent_names = (const char *[]){
+				"mmss_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_byte0_clk = {
+	.halt_reg = 0x233c,
+	.clkr = {
+		.enable_reg = 0x233c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_byte0_clk",
+			.parent_names = (const char *[]){
+				"byte0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_byte1_clk = {
+	.halt_reg = 0x2340,
+	.clkr = {
+		.enable_reg = 0x2340,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_byte1_clk",
+			.parent_names = (const char *[]){
+				"byte1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_edpaux_clk = {
+	.halt_reg = 0x2334,
+	.clkr = {
+		.enable_reg = 0x2334,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_edpaux_clk",
+			.parent_names = (const char *[]){
+				"edpaux_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_edplink_clk = {
+	.halt_reg = 0x2330,
+	.clkr = {
+		.enable_reg = 0x2330,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_edplink_clk",
+			.parent_names = (const char *[]){
+				"edplink_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_edppixel_clk = {
+	.halt_reg = 0x232c,
+	.clkr = {
+		.enable_reg = 0x232c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_edppixel_clk",
+			.parent_names = (const char *[]){
+				"edppixel_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_esc0_clk = {
+	.halt_reg = 0x2344,
+	.clkr = {
+		.enable_reg = 0x2344,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_esc0_clk",
+			.parent_names = (const char *[]){
+				"esc0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_esc1_clk = {
+	.halt_reg = 0x2348,
+	.clkr = {
+		.enable_reg = 0x2348,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_esc1_clk",
+			.parent_names = (const char *[]){
+				"esc1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_extpclk_clk = {
+	.halt_reg = 0x2324,
+	.clkr = {
+		.enable_reg = 0x2324,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_extpclk_clk",
+			.parent_names = (const char *[]){
+				"extpclk_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_hdmi_ahb_clk = {
+	.halt_reg = 0x230c,
+	.clkr = {
+		.enable_reg = 0x230c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_hdmi_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_hdmi_clk = {
+	.halt_reg = 0x2338,
+	.clkr = {
+		.enable_reg = 0x2338,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_hdmi_clk",
+			.parent_names = (const char *[]){
+				"hdmi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_mdp_clk = {
+	.halt_reg = 0x231c,
+	.clkr = {
+		.enable_reg = 0x231c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_mdp_clk",
+			.parent_names = (const char *[]){
+				"mdp_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_mdp_lut_clk = {
+	.halt_reg = 0x2320,
+	.clkr = {
+		.enable_reg = 0x2320,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_mdp_lut_clk",
+			.parent_names = (const char *[]){
+				"mdp_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_pclk0_clk = {
+	.halt_reg = 0x2314,
+	.clkr = {
+		.enable_reg = 0x2314,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_pclk0_clk",
+			.parent_names = (const char *[]){
+				"pclk0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_pclk1_clk = {
+	.halt_reg = 0x2318,
+	.clkr = {
+		.enable_reg = 0x2318,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_pclk1_clk",
+			.parent_names = (const char *[]){
+				"pclk1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_vsync_clk = {
+	.halt_reg = 0x2328,
+	.clkr = {
+		.enable_reg = 0x2328,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_vsync_clk",
+			.parent_names = (const char *[]){
+				"vsync_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_rbcpr_ahb_clk = {
+	.halt_reg = 0x4088,
+	.clkr = {
+		.enable_reg = 0x4088,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_rbcpr_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_rbcpr_clk = {
+	.halt_reg = 0x4084,
+	.clkr = {
+		.enable_reg = 0x4084,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_rbcpr_clk",
+			.parent_names = (const char *[]){
+				"rbcpr_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_ahb_clk = {
+	.halt_reg = 0x0230,
+	.clkr = {
+		.enable_reg = 0x0230,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_ahb_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_axi_clk = {
+	.halt_reg = 0x0210,
+	.clkr = {
+		.enable_reg = 0x0210,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_axi_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_axi_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_csi0_clk = {
+	.halt_reg = 0x023c,
+	.clkr = {
+		.enable_reg = 0x023c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_csi0_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_csi0_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_gfx3d_clk = {
+	.halt_reg = 0x022c,
+	.clkr = {
+		.enable_reg = 0x022c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_gfx3d_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_gfx3d_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_jpeg0_clk = {
+	.halt_reg = 0x0204,
+	.clkr = {
+		.enable_reg = 0x0204,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_jpeg0_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_jpeg0_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_jpeg1_clk = {
+	.halt_reg = 0x0208,
+	.clkr = {
+		.enable_reg = 0x0208,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_jpeg1_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_jpeg1_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_jpeg2_clk = {
+	.halt_reg = 0x0224,
+	.clkr = {
+		.enable_reg = 0x0224,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_jpeg2_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_jpeg2_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_mdp_clk = {
+	.halt_reg = 0x020c,
+	.clkr = {
+		.enable_reg = 0x020c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_mdp_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_mdp_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_pclk0_clk = {
+	.halt_reg = 0x0234,
+	.clkr = {
+		.enable_reg = 0x0234,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_pclk0_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_pclk0_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_pclk1_clk = {
+	.halt_reg = 0x0228,
+	.clkr = {
+		.enable_reg = 0x0228,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_pclk1_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_pclk1_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_vcodec0_clk = {
+	.halt_reg = 0x0214,
+	.clkr = {
+		.enable_reg = 0x0214,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_vcodec0_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_vcodec0_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_vfe0_clk = {
+	.halt_reg = 0x0218,
+	.clkr = {
+		.enable_reg = 0x0218,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_vfe0_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_vfe0_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_vfe1_clk = {
+	.halt_reg = 0x021c,
+	.clkr = {
+		.enable_reg = 0x021c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_vfe1_clk",
+			.parent_names = (const char *[]){
+				"mmss_spdm_vfe1_div_clk",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_rm_axi_clk = {
+	.halt_reg = 0x0304,
+	.clkr = {
+		.enable_reg = 0x0304,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_rm_axi_clk",
+			.parent_names = (const char *[]){
+				"mmss_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_spdm_rm_ocmemnoc_clk = {
+	.halt_reg = 0x0308,
+	.clkr = {
+		.enable_reg = 0x0308,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_spdm_rm_ocmemnoc_clk",
+			.parent_names = (const char *[]){
+				"ocmemnoc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+
+static struct clk_branch mmss_misc_ahb_clk = {
+	.halt_reg = 0x502c,
+	.clkr = {
+		.enable_reg = 0x502c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_misc_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_mmssnoc_ahb_clk = {
+	.halt_reg = 0x5024,
+	.clkr = {
+		.enable_reg = 0x5024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_mmssnoc_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+		},
+	},
+};
+
+static struct clk_branch mmss_mmssnoc_bto_ahb_clk = {
+	.halt_reg = 0x5028,
+	.clkr = {
+		.enable_reg = 0x5028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_mmssnoc_bto_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+		},
+	},
+};
+
+static struct clk_branch mmss_mmssnoc_axi_clk = {
+	.halt_reg = 0x506c,
+	.clkr = {
+		.enable_reg = 0x506c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_mmssnoc_axi_clk",
+			.parent_names = (const char *[]){
+				"mmss_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mmss_s0_axi_clk = {
+	.halt_reg = 0x5064,
+	.clkr = {
+		.enable_reg = 0x5064,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmss_s0_axi_clk",
+			.parent_names = (const char *[]){
+				"mmss_axi_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT | CLK_IGNORE_UNUSED,
+		},
+	},
+};
+
+static struct clk_branch ocmemcx_ahb_clk = {
+	.halt_reg = 0x405c,
+	.clkr = {
+		.enable_reg = 0x405c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "ocmemcx_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch ocmemcx_ocmemnoc_clk = {
+	.halt_reg = 0x4058,
+	.clkr = {
+		.enable_reg = 0x4058,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "ocmemcx_ocmemnoc_clk",
+			.parent_names = (const char *[]){
+				"ocmemnoc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch oxili_ocmemgx_clk = {
+	.halt_reg = 0x402c,
+	.clkr = {
+		.enable_reg = 0x402c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "oxili_ocmemgx_clk",
+			.parent_names = (const char *[]){
+				"gfx3d_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch oxili_gfx3d_clk = {
+	.halt_reg = 0x4028,
+	.clkr = {
+		.enable_reg = 0x4028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "oxili_gfx3d_clk",
+			.parent_names = (const char *[]){
+				"gfx3d_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch oxili_rbbmtimer_clk = {
+	.halt_reg = 0x40b0,
+	.clkr = {
+		.enable_reg = 0x40b0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "oxili_rbbmtimer_clk",
+			.parent_names = (const char *[]){
+				"rbbmtimer_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch oxilicx_ahb_clk = {
+	.halt_reg = 0x403c,
+	.clkr = {
+		.enable_reg = 0x403c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "oxilicx_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch venus0_ahb_clk = {
+	.halt_reg = 0x1030,
+	.clkr = {
+		.enable_reg = 0x1030,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "venus0_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch venus0_axi_clk = {
+	.halt_reg = 0x1034,
+	.clkr = {
+		.enable_reg = 0x1034,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "venus0_axi_clk",
+			.parent_names = (const char *[]){
+				"mmss_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch venus0_core0_vcodec_clk = {
+	.halt_reg = 0x1048,
+	.clkr = {
+		.enable_reg = 0x1048,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "venus0_core0_vcodec_clk",
+			.parent_names = (const char *[]){
+				"vcodec0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch venus0_core1_vcodec_clk = {
+	.halt_reg = 0x104c,
+	.clkr = {
+		.enable_reg = 0x104c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "venus0_core1_vcodec_clk",
+			.parent_names = (const char *[]){
+				"vcodec0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch venus0_ocmemnoc_clk = {
+	.halt_reg = 0x1038,
+	.clkr = {
+		.enable_reg = 0x1038,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "venus0_ocmemnoc_clk",
+			.parent_names = (const char *[]){
+				"ocmemnoc_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch venus0_vcodec0_clk = {
+	.halt_reg = 0x1028,
+	.clkr = {
+		.enable_reg = 0x1028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "venus0_vcodec0_clk",
+			.parent_names = (const char *[]){
+				"vcodec0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch vpu_ahb_clk = {
+	.halt_reg = 0x1430,
+	.clkr = {
+		.enable_reg = 0x1430,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vpu_ahb_clk",
+			.parent_names = (const char *[]){
+				"mmss_ahb_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch vpu_axi_clk = {
+	.halt_reg = 0x143c,
+	.clkr = {
+		.enable_reg = 0x143c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vpu_axi_clk",
+			.parent_names = (const char *[]){
+				"mmss_axi_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch vpu_bus_clk = {
+	.halt_reg = 0x1440,
+	.clkr = {
+		.enable_reg = 0x1440,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vpu_bus_clk",
+			.parent_names = (const char *[]){
+				"vpu_bus_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch vpu_cxo_clk = {
+	.halt_reg = 0x1434,
+	.clkr = {
+		.enable_reg = 0x1434,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vpu_cxo_clk",
+			.parent_names = (const char *[]){ "xo" },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch vpu_maple_clk = {
+	.halt_reg = 0x142c,
+	.clkr = {
+		.enable_reg = 0x142c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vpu_maple_clk",
+			.parent_names = (const char *[]){
+				"maple_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch vpu_sleep_clk = {
+	.halt_reg = 0x1438,
+	.clkr = {
+		.enable_reg = 0x1438,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vpu_sleep_clk",
+			.parent_names = (const char *[]){
+				"sleep_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch vpu_vdp_clk = {
+	.halt_reg = 0x1428,
+	.clkr = {
+		.enable_reg = 0x1428,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vpu_vdp_clk",
+			.parent_names = (const char *[]){
+				"vdp_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static const struct pll_config mmpll1_config = {
+	.l = 60,
+	.m = 25,
+	.n = 32,
+	.vco_val = 0x0,
+	.vco_mask = 0x3 << 20,
+	.pre_div_val = 0x0,
+	.pre_div_mask = 0x7 << 12,
+	.post_div_val = 0x0,
+	.post_div_mask = 0x3 << 8,
+	.mn_ena_mask = BIT(24),
+	.main_output_mask = BIT(0),
+};
+
+static const struct pll_config mmpll3_config = {
+	.l = 48,
+	.m = 7,
+	.n = 16,
+	.vco_val = 0x0,
+	.vco_mask = 0x3 << 20,
+	.pre_div_val = 0x0,
+	.pre_div_mask = 0x7 << 12,
+	.post_div_val = 0x0,
+	.post_div_mask = 0x3 << 8,
+	.mn_ena_mask = BIT(24),
+	.main_output_mask = BIT(0),
+	.aux_output_mask = BIT(1),
+};
+
+static struct clk_regmap *mmcc_apq8084_clocks[] = {
+	[MMSS_AHB_CLK_SRC] = &mmss_ahb_clk_src.clkr,
+	[MMSS_AXI_CLK_SRC] = &mmss_axi_clk_src.clkr,
+	[MMPLL0] = &mmpll0.clkr,
+	[MMPLL0_VOTE] = &mmpll0_vote,
+	[MMPLL1] = &mmpll1.clkr,
+	[MMPLL1_VOTE] = &mmpll1_vote,
+	[MMPLL2] = &mmpll2.clkr,
+	[MMPLL3] = &mmpll3.clkr,
+	[MMPLL4] = &mmpll4.clkr,
+	[CSI0_CLK_SRC] = &csi0_clk_src.clkr,
+	[CSI1_CLK_SRC] = &csi1_clk_src.clkr,
+	[CSI2_CLK_SRC] = &csi2_clk_src.clkr,
+	[CSI3_CLK_SRC] = &csi3_clk_src.clkr,
+	[VCODEC0_CLK_SRC] = &vcodec0_clk_src.clkr,
+	[VFE0_CLK_SRC] = &vfe0_clk_src.clkr,
+	[VFE1_CLK_SRC] = &vfe1_clk_src.clkr,
+	[MDP_CLK_SRC] = &mdp_clk_src.clkr,
+	[PCLK0_CLK_SRC] = &pclk0_clk_src.clkr,
+	[PCLK1_CLK_SRC] = &pclk1_clk_src.clkr,
+	[OCMEMNOC_CLK_SRC] = &ocmemnoc_clk_src.clkr,
+	[GFX3D_CLK_SRC] = &gfx3d_clk_src.clkr,
+	[JPEG0_CLK_SRC] = &jpeg0_clk_src.clkr,
+	[JPEG1_CLK_SRC] = &jpeg1_clk_src.clkr,
+	[JPEG2_CLK_SRC] = &jpeg2_clk_src.clkr,
+	[EDPPIXEL_CLK_SRC] = &edppixel_clk_src.clkr,
+	[EXTPCLK_CLK_SRC] = &extpclk_clk_src.clkr,
+	[VP_CLK_SRC] = &vp_clk_src.clkr,
+	[CCI_CLK_SRC] = &cci_clk_src.clkr,
+	[CAMSS_GP0_CLK_SRC] = &camss_gp0_clk_src.clkr,
+	[CAMSS_GP1_CLK_SRC] = &camss_gp1_clk_src.clkr,
+	[MCLK0_CLK_SRC] = &mclk0_clk_src.clkr,
+	[MCLK1_CLK_SRC] = &mclk1_clk_src.clkr,
+	[MCLK2_CLK_SRC] = &mclk2_clk_src.clkr,
+	[MCLK3_CLK_SRC] = &mclk3_clk_src.clkr,
+	[CSI0PHYTIMER_CLK_SRC] = &csi0phytimer_clk_src.clkr,
+	[CSI1PHYTIMER_CLK_SRC] = &csi1phytimer_clk_src.clkr,
+	[CSI2PHYTIMER_CLK_SRC] = &csi2phytimer_clk_src.clkr,
+	[CPP_CLK_SRC] = &cpp_clk_src.clkr,
+	[BYTE0_CLK_SRC] = &byte0_clk_src.clkr,
+	[BYTE1_CLK_SRC] = &byte1_clk_src.clkr,
+	[EDPAUX_CLK_SRC] = &edpaux_clk_src.clkr,
+	[EDPLINK_CLK_SRC] = &edplink_clk_src.clkr,
+	[ESC0_CLK_SRC] = &esc0_clk_src.clkr,
+	[ESC1_CLK_SRC] = &esc1_clk_src.clkr,
+	[HDMI_CLK_SRC] = &hdmi_clk_src.clkr,
+	[VSYNC_CLK_SRC] = &vsync_clk_src.clkr,
+	[RBCPR_CLK_SRC] = &rbcpr_clk_src.clkr,
+	[RBBMTIMER_CLK_SRC] = &rbbmtimer_clk_src.clkr,
+	[MAPLE_CLK_SRC] = &maple_clk_src.clkr,
+	[VDP_CLK_SRC] = &vdp_clk_src.clkr,
+	[VPU_BUS_CLK_SRC] = &vpu_bus_clk_src.clkr,
+	[MMSS_CXO_CLK] = &mmss_cxo_clk.clkr,
+	[MMSS_SLEEPCLK_CLK] = &mmss_sleepclk_clk.clkr,
+	[AVSYNC_AHB_CLK] = &avsync_ahb_clk.clkr,
+	[AVSYNC_EDPPIXEL_CLK] = &avsync_edppixel_clk.clkr,
+	[AVSYNC_EXTPCLK_CLK] = &avsync_extpclk_clk.clkr,
+	[AVSYNC_PCLK0_CLK] = &avsync_pclk0_clk.clkr,
+	[AVSYNC_PCLK1_CLK] = &avsync_pclk1_clk.clkr,
+	[AVSYNC_VP_CLK] = &avsync_vp_clk.clkr,
+	[CAMSS_AHB_CLK] = &camss_ahb_clk.clkr,
+	[CAMSS_CCI_CCI_AHB_CLK] = &camss_cci_cci_ahb_clk.clkr,
+	[CAMSS_CCI_CCI_CLK] = &camss_cci_cci_clk.clkr,
+	[CAMSS_CSI0_AHB_CLK] = &camss_csi0_ahb_clk.clkr,
+	[CAMSS_CSI0_CLK] = &camss_csi0_clk.clkr,
+	[CAMSS_CSI0PHY_CLK] = &camss_csi0phy_clk.clkr,
+	[CAMSS_CSI0PIX_CLK] = &camss_csi0pix_clk.clkr,
+	[CAMSS_CSI0RDI_CLK] = &camss_csi0rdi_clk.clkr,
+	[CAMSS_CSI1_AHB_CLK] = &camss_csi1_ahb_clk.clkr,
+	[CAMSS_CSI1_CLK] = &camss_csi1_clk.clkr,
+	[CAMSS_CSI1PHY_CLK] = &camss_csi1phy_clk.clkr,
+	[CAMSS_CSI1PIX_CLK] = &camss_csi1pix_clk.clkr,
+	[CAMSS_CSI1RDI_CLK] = &camss_csi1rdi_clk.clkr,
+	[CAMSS_CSI2_AHB_CLK] = &camss_csi2_ahb_clk.clkr,
+	[CAMSS_CSI2_CLK] = &camss_csi2_clk.clkr,
+	[CAMSS_CSI2PHY_CLK] = &camss_csi2phy_clk.clkr,
+	[CAMSS_CSI2PIX_CLK] = &camss_csi2pix_clk.clkr,
+	[CAMSS_CSI2RDI_CLK] = &camss_csi2rdi_clk.clkr,
+	[CAMSS_CSI3_AHB_CLK] = &camss_csi3_ahb_clk.clkr,
+	[CAMSS_CSI3_CLK] = &camss_csi3_clk.clkr,
+	[CAMSS_CSI3PHY_CLK] = &camss_csi3phy_clk.clkr,
+	[CAMSS_CSI3PIX_CLK] = &camss_csi3pix_clk.clkr,
+	[CAMSS_CSI3RDI_CLK] = &camss_csi3rdi_clk.clkr,
+	[CAMSS_CSI_VFE0_CLK] = &camss_csi_vfe0_clk.clkr,
+	[CAMSS_CSI_VFE1_CLK] = &camss_csi_vfe1_clk.clkr,
+	[CAMSS_GP0_CLK] = &camss_gp0_clk.clkr,
+	[CAMSS_GP1_CLK] = &camss_gp1_clk.clkr,
+	[CAMSS_ISPIF_AHB_CLK] = &camss_ispif_ahb_clk.clkr,
+	[CAMSS_JPEG_JPEG0_CLK] = &camss_jpeg_jpeg0_clk.clkr,
+	[CAMSS_JPEG_JPEG1_CLK] = &camss_jpeg_jpeg1_clk.clkr,
+	[CAMSS_JPEG_JPEG2_CLK] = &camss_jpeg_jpeg2_clk.clkr,
+	[CAMSS_JPEG_JPEG_AHB_CLK] = &camss_jpeg_jpeg_ahb_clk.clkr,
+	[CAMSS_JPEG_JPEG_AXI_CLK] = &camss_jpeg_jpeg_axi_clk.clkr,
+	[CAMSS_MCLK0_CLK] = &camss_mclk0_clk.clkr,
+	[CAMSS_MCLK1_CLK] = &camss_mclk1_clk.clkr,
+	[CAMSS_MCLK2_CLK] = &camss_mclk2_clk.clkr,
+	[CAMSS_MCLK3_CLK] = &camss_mclk3_clk.clkr,
+	[CAMSS_MICRO_AHB_CLK] = &camss_micro_ahb_clk.clkr,
+	[CAMSS_PHY0_CSI0PHYTIMER_CLK] = &camss_phy0_csi0phytimer_clk.clkr,
+	[CAMSS_PHY1_CSI1PHYTIMER_CLK] = &camss_phy1_csi1phytimer_clk.clkr,
+	[CAMSS_PHY2_CSI2PHYTIMER_CLK] = &camss_phy2_csi2phytimer_clk.clkr,
+	[CAMSS_TOP_AHB_CLK] = &camss_top_ahb_clk.clkr,
+	[CAMSS_VFE_CPP_AHB_CLK] = &camss_vfe_cpp_ahb_clk.clkr,
+	[CAMSS_VFE_CPP_CLK] = &camss_vfe_cpp_clk.clkr,
+	[CAMSS_VFE_VFE0_CLK] = &camss_vfe_vfe0_clk.clkr,
+	[CAMSS_VFE_VFE1_CLK] = &camss_vfe_vfe1_clk.clkr,
+	[CAMSS_VFE_VFE_AHB_CLK] = &camss_vfe_vfe_ahb_clk.clkr,
+	[CAMSS_VFE_VFE_AXI_CLK] = &camss_vfe_vfe_axi_clk.clkr,
+	[MDSS_AHB_CLK] = &mdss_ahb_clk.clkr,
+	[MDSS_AXI_CLK] = &mdss_axi_clk.clkr,
+	[MDSS_BYTE0_CLK] = &mdss_byte0_clk.clkr,
+	[MDSS_BYTE1_CLK] = &mdss_byte1_clk.clkr,
+	[MDSS_EDPAUX_CLK] = &mdss_edpaux_clk.clkr,
+	[MDSS_EDPLINK_CLK] = &mdss_edplink_clk.clkr,
+	[MDSS_EDPPIXEL_CLK] = &mdss_edppixel_clk.clkr,
+	[MDSS_ESC0_CLK] = &mdss_esc0_clk.clkr,
+	[MDSS_ESC1_CLK] = &mdss_esc1_clk.clkr,
+	[MDSS_EXTPCLK_CLK] = &mdss_extpclk_clk.clkr,
+	[MDSS_HDMI_AHB_CLK] = &mdss_hdmi_ahb_clk.clkr,
+	[MDSS_HDMI_CLK] = &mdss_hdmi_clk.clkr,
+	[MDSS_MDP_CLK] = &mdss_mdp_clk.clkr,
+	[MDSS_MDP_LUT_CLK] = &mdss_mdp_lut_clk.clkr,
+	[MDSS_PCLK0_CLK] = &mdss_pclk0_clk.clkr,
+	[MDSS_PCLK1_CLK] = &mdss_pclk1_clk.clkr,
+	[MDSS_VSYNC_CLK] = &mdss_vsync_clk.clkr,
+	[MMSS_RBCPR_AHB_CLK] = &mmss_rbcpr_ahb_clk.clkr,
+	[MMSS_RBCPR_CLK] = &mmss_rbcpr_clk.clkr,
+	[MMSS_SPDM_AHB_CLK] = &mmss_spdm_ahb_clk.clkr,
+	[MMSS_SPDM_AXI_CLK] = &mmss_spdm_axi_clk.clkr,
+	[MMSS_SPDM_CSI0_CLK] = &mmss_spdm_csi0_clk.clkr,
+	[MMSS_SPDM_GFX3D_CLK] = &mmss_spdm_gfx3d_clk.clkr,
+	[MMSS_SPDM_JPEG0_CLK] = &mmss_spdm_jpeg0_clk.clkr,
+	[MMSS_SPDM_JPEG1_CLK] = &mmss_spdm_jpeg1_clk.clkr,
+	[MMSS_SPDM_JPEG2_CLK] = &mmss_spdm_jpeg2_clk.clkr,
+	[MMSS_SPDM_MDP_CLK] = &mmss_spdm_mdp_clk.clkr,
+	[MMSS_SPDM_PCLK0_CLK] = &mmss_spdm_pclk0_clk.clkr,
+	[MMSS_SPDM_PCLK1_CLK] = &mmss_spdm_pclk1_clk.clkr,
+	[MMSS_SPDM_VCODEC0_CLK] = &mmss_spdm_vcodec0_clk.clkr,
+	[MMSS_SPDM_VFE0_CLK] = &mmss_spdm_vfe0_clk.clkr,
+	[MMSS_SPDM_VFE1_CLK] = &mmss_spdm_vfe1_clk.clkr,
+	[MMSS_SPDM_RM_AXI_CLK] = &mmss_spdm_rm_axi_clk.clkr,
+	[MMSS_SPDM_RM_OCMEMNOC_CLK] = &mmss_spdm_rm_ocmemnoc_clk.clkr,
+	[MMSS_MISC_AHB_CLK] = &mmss_misc_ahb_clk.clkr,
+	[MMSS_MMSSNOC_AHB_CLK] = &mmss_mmssnoc_ahb_clk.clkr,
+	[MMSS_MMSSNOC_BTO_AHB_CLK] = &mmss_mmssnoc_bto_ahb_clk.clkr,
+	[MMSS_MMSSNOC_AXI_CLK] = &mmss_mmssnoc_axi_clk.clkr,
+	[MMSS_S0_AXI_CLK] = &mmss_s0_axi_clk.clkr,
+	[OCMEMCX_AHB_CLK] = &ocmemcx_ahb_clk.clkr,
+	[OCMEMCX_OCMEMNOC_CLK] = &ocmemcx_ocmemnoc_clk.clkr,
+	[OXILI_OCMEMGX_CLK] = &oxili_ocmemgx_clk.clkr,
+	[OXILI_GFX3D_CLK] = &oxili_gfx3d_clk.clkr,
+	[OXILI_RBBMTIMER_CLK] = &oxili_rbbmtimer_clk.clkr,
+	[OXILICX_AHB_CLK] = &oxilicx_ahb_clk.clkr,
+	[VENUS0_AHB_CLK] = &venus0_ahb_clk.clkr,
+	[VENUS0_AXI_CLK] = &venus0_axi_clk.clkr,
+	[VENUS0_CORE0_VCODEC_CLK] = &venus0_core0_vcodec_clk.clkr,
+	[VENUS0_CORE1_VCODEC_CLK] = &venus0_core1_vcodec_clk.clkr,
+	[VENUS0_OCMEMNOC_CLK] = &venus0_ocmemnoc_clk.clkr,
+	[VENUS0_VCODEC0_CLK] = &venus0_vcodec0_clk.clkr,
+	[VPU_AHB_CLK] = &vpu_ahb_clk.clkr,
+	[VPU_AXI_CLK] = &vpu_axi_clk.clkr,
+	[VPU_BUS_CLK] = &vpu_bus_clk.clkr,
+	[VPU_CXO_CLK] = &vpu_cxo_clk.clkr,
+	[VPU_MAPLE_CLK] = &vpu_maple_clk.clkr,
+	[VPU_SLEEP_CLK] = &vpu_sleep_clk.clkr,
+	[VPU_VDP_CLK] = &vpu_vdp_clk.clkr,
+};
+
+static const struct qcom_reset_map mmcc_apq8084_resets[] = {
+	[MMSS_SPDM_RESET] = { 0x0200 },
+	[MMSS_SPDM_RM_RESET] = { 0x0300 },
+	[VENUS0_RESET] = { 0x1020 },
+	[VPU_RESET] = { 0x1400 },
+	[MDSS_RESET] = { 0x2300 },
+	[AVSYNC_RESET] = { 0x2400 },
+	[CAMSS_PHY0_RESET] = { 0x3020 },
+	[CAMSS_PHY1_RESET] = { 0x3050 },
+	[CAMSS_PHY2_RESET] = { 0x3080 },
+	[CAMSS_CSI0_RESET] = { 0x30b0 },
+	[CAMSS_CSI0PHY_RESET] = { 0x30c0 },
+	[CAMSS_CSI0RDI_RESET] = { 0x30d0 },
+	[CAMSS_CSI0PIX_RESET] = { 0x30e0 },
+	[CAMSS_CSI1_RESET] = { 0x3120 },
+	[CAMSS_CSI1PHY_RESET] = { 0x3130 },
+	[CAMSS_CSI1RDI_RESET] = { 0x3140 },
+	[CAMSS_CSI1PIX_RESET] = { 0x3150 },
+	[CAMSS_CSI2_RESET] = { 0x3180 },
+	[CAMSS_CSI2PHY_RESET] = { 0x3190 },
+	[CAMSS_CSI2RDI_RESET] = { 0x31a0 },
+	[CAMSS_CSI2PIX_RESET] = { 0x31b0 },
+	[CAMSS_CSI3_RESET] = { 0x31e0 },
+	[CAMSS_CSI3PHY_RESET] = { 0x31f0 },
+	[CAMSS_CSI3RDI_RESET] = { 0x3200 },
+	[CAMSS_CSI3PIX_RESET] = { 0x3210 },
+	[CAMSS_ISPIF_RESET] = { 0x3220 },
+	[CAMSS_CCI_RESET] = { 0x3340 },
+	[CAMSS_MCLK0_RESET] = { 0x3380 },
+	[CAMSS_MCLK1_RESET] = { 0x33b0 },
+	[CAMSS_MCLK2_RESET] = { 0x33e0 },
+	[CAMSS_MCLK3_RESET] = { 0x3410 },
+	[CAMSS_GP0_RESET] = { 0x3440 },
+	[CAMSS_GP1_RESET] = { 0x3470 },
+	[CAMSS_TOP_RESET] = { 0x3480 },
+	[CAMSS_AHB_RESET] = { 0x3488 },
+	[CAMSS_MICRO_RESET] = { 0x3490 },
+	[CAMSS_JPEG_RESET] = { 0x35a0 },
+	[CAMSS_VFE_RESET] = { 0x36a0 },
+	[CAMSS_CSI_VFE0_RESET] = { 0x3700 },
+	[CAMSS_CSI_VFE1_RESET] = { 0x3710 },
+	[OXILI_RESET] = { 0x4020 },
+	[OXILICX_RESET] = { 0x4030 },
+	[OCMEMCX_RESET] = { 0x4050 },
+	[MMSS_RBCRP_RESET] = { 0x4080 },
+	[MMSSNOCAHB_RESET] = { 0x5020 },
+	[MMSSNOCAXI_RESET] = { 0x5060 },
+};
+
+static const struct regmap_config mmcc_apq8084_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x5104,
+	.fast_io	= true,
+};
+
+static const struct qcom_cc_desc mmcc_apq8084_desc = {
+	.config = &mmcc_apq8084_regmap_config,
+	.clks = mmcc_apq8084_clocks,
+	.num_clks = ARRAY_SIZE(mmcc_apq8084_clocks),
+	.resets = mmcc_apq8084_resets,
+	.num_resets = ARRAY_SIZE(mmcc_apq8084_resets),
+};
+
+static const struct of_device_id mmcc_apq8084_match_table[] = {
+	{ .compatible = "qcom,mmcc-apq8084" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mmcc_apq8084_match_table);
+
+static int mmcc_apq8084_probe(struct platform_device *pdev)
+{
+	int ret;
+	struct regmap *regmap;
+
+	ret = qcom_cc_probe(pdev, &mmcc_apq8084_desc);
+	if (ret)
+		return ret;
+
+	regmap = dev_get_regmap(&pdev->dev, NULL);
+	clk_pll_configure_sr_hpm_lp(&mmpll1, regmap, &mmpll1_config, true);
+	clk_pll_configure_sr_hpm_lp(&mmpll3, regmap, &mmpll3_config, false);
+
+	return 0;
+}
+
+static int mmcc_apq8084_remove(struct platform_device *pdev)
+{
+	qcom_cc_remove(pdev);
+	return 0;
+}
+
+static struct platform_driver mmcc_apq8084_driver = {
+	.probe		= mmcc_apq8084_probe,
+	.remove		= mmcc_apq8084_remove,
+	.driver		= {
+		.name	= "mmcc-apq8084",
+		.owner	= THIS_MODULE,
+		.of_match_table = mmcc_apq8084_match_table,
+	},
+};
+module_platform_driver(mmcc_apq8084_driver);
+
+MODULE_DESCRIPTION("QCOM MMCC APQ8084 Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:mmcc-apq8084");
diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c
index 12f3c0b64fc..2e80a219b8e 100644
--- a/drivers/clk/qcom/mmcc-msm8960.c
+++ b/drivers/clk/qcom/mmcc-msm8960.c
@@ -37,6 +37,9 @@
 #define P_PLL8	1
 #define P_PLL2	2
 #define P_PLL3	3
+#define P_PLL15	3
+
+#define F_MN(f, s, _m, _n) { .freq = f, .src = s, .m = _m, .n = _n }
 
 static u8 mmcc_pxo_pll8_pll2_map[] = {
 	[P_PXO]		= 0,
@@ -57,10 +60,24 @@ static u8 mmcc_pxo_pll8_pll2_pll3_map[] = {
 	[P_PLL3]	= 3,
 };
 
-static const char *mmcc_pxo_pll8_pll2_pll3[] = {
+static const char *mmcc_pxo_pll8_pll2_pll15[] = {
 	"pxo",
+	"pll8_vote",
 	"pll2",
+	"pll15",
+};
+
+static u8 mmcc_pxo_pll8_pll2_pll15_map[] = {
+	[P_PXO]		= 0,
+	[P_PLL8]	= 2,
+	[P_PLL2]	= 1,
+	[P_PLL15]	= 3,
+};
+
+static const char *mmcc_pxo_pll8_pll2_pll3[] = {
+	"pxo",
 	"pll8_vote",
+	"pll2",
 	"pll3",
 };
 
@@ -80,6 +97,36 @@ static struct clk_pll pll2 = {
 	},
 };
 
+static struct clk_pll pll15 = {
+	.l_reg = 0x33c,
+	.m_reg = 0x340,
+	.n_reg = 0x344,
+	.config_reg = 0x348,
+	.mode_reg = 0x338,
+	.status_reg = 0x350,
+	.status_bit = 16,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pll15",
+		.parent_names = (const char *[]){ "pxo" },
+		.num_parents = 1,
+		.ops = &clk_pll_ops,
+	},
+};
+
+static const struct pll_config pll15_config = {
+	.l = 33,
+	.m = 1,
+	.n = 3,
+	.vco_val = 0x2 << 16,
+	.vco_mask = 0x3 << 16,
+	.pre_div_val = 0x0,
+	.pre_div_mask = BIT(19),
+	.post_div_val = 0x0,
+	.post_div_mask = 0x3 << 20,
+	.mn_ena_mask = BIT(22),
+	.main_output_mask = BIT(23),
+};
+
 static struct freq_tbl clk_tbl_cam[] = {
 	{   6000000, P_PLL8, 4, 1, 16 },
 	{   8000000, P_PLL8, 4, 1, 12 },
@@ -710,18 +757,18 @@ static struct clk_branch csiphy2_timer_clk = {
 };
 
 static struct freq_tbl clk_tbl_gfx2d[] = {
-	{  27000000, P_PXO,  1,  0 },
-	{  48000000, P_PLL8, 1,  8 },
-	{  54857000, P_PLL8, 1,  7 },
-	{  64000000, P_PLL8, 1,  6 },
-	{  76800000, P_PLL8, 1,  5 },
-	{  96000000, P_PLL8, 1,  4 },
-	{ 128000000, P_PLL8, 1,  3 },
-	{ 145455000, P_PLL2, 2, 11 },
-	{ 160000000, P_PLL2, 1,  5 },
-	{ 177778000, P_PLL2, 2,  9 },
-	{ 200000000, P_PLL2, 1,  4 },
-	{ 228571000, P_PLL2, 2,  7 },
+	F_MN( 27000000, P_PXO,  1,  0),
+	F_MN( 48000000, P_PLL8, 1,  8),
+	F_MN( 54857000, P_PLL8, 1,  7),
+	F_MN( 64000000, P_PLL8, 1,  6),
+	F_MN( 76800000, P_PLL8, 1,  5),
+	F_MN( 96000000, P_PLL8, 1,  4),
+	F_MN(128000000, P_PLL8, 1,  3),
+	F_MN(145455000, P_PLL2, 2, 11),
+	F_MN(160000000, P_PLL2, 1,  5),
+	F_MN(177778000, P_PLL2, 2,  9),
+	F_MN(200000000, P_PLL2, 1,  4),
+	F_MN(228571000, P_PLL2, 2,  7),
 	{ }
 };
 
@@ -842,22 +889,43 @@ static struct clk_branch gfx2d1_clk = {
 };
 
 static struct freq_tbl clk_tbl_gfx3d[] = {
-	{  27000000, P_PXO,  1,  0 },
-	{  48000000, P_PLL8, 1,  8 },
-	{  54857000, P_PLL8, 1,  7 },
-	{  64000000, P_PLL8, 1,  6 },
-	{  76800000, P_PLL8, 1,  5 },
-	{  96000000, P_PLL8, 1,  4 },
-	{ 128000000, P_PLL8, 1,  3 },
-	{ 145455000, P_PLL2, 2, 11 },
-	{ 160000000, P_PLL2, 1,  5 },
-	{ 177778000, P_PLL2, 2,  9 },
-	{ 200000000, P_PLL2, 1,  4 },
-	{ 228571000, P_PLL2, 2,  7 },
-	{ 266667000, P_PLL2, 1,  3 },
-	{ 300000000, P_PLL3, 1,  4 },
-	{ 320000000, P_PLL2, 2,  5 },
-	{ 400000000, P_PLL2, 1,  2 },
+	F_MN( 27000000, P_PXO,  1,  0),
+	F_MN( 48000000, P_PLL8, 1,  8),
+	F_MN( 54857000, P_PLL8, 1,  7),
+	F_MN( 64000000, P_PLL8, 1,  6),
+	F_MN( 76800000, P_PLL8, 1,  5),
+	F_MN( 96000000, P_PLL8, 1,  4),
+	F_MN(128000000, P_PLL8, 1,  3),
+	F_MN(145455000, P_PLL2, 2, 11),
+	F_MN(160000000, P_PLL2, 1,  5),
+	F_MN(177778000, P_PLL2, 2,  9),
+	F_MN(200000000, P_PLL2, 1,  4),
+	F_MN(228571000, P_PLL2, 2,  7),
+	F_MN(266667000, P_PLL2, 1,  3),
+	F_MN(300000000, P_PLL3, 1,  4),
+	F_MN(320000000, P_PLL2, 2,  5),
+	F_MN(400000000, P_PLL2, 1,  2),
+	{ }
+};
+
+static struct freq_tbl clk_tbl_gfx3d_8064[] = {
+	F_MN( 27000000, P_PXO,   0,  0),
+	F_MN( 48000000, P_PLL8,  1,  8),
+	F_MN( 54857000, P_PLL8,  1,  7),
+	F_MN( 64000000, P_PLL8,  1,  6),
+	F_MN( 76800000, P_PLL8,  1,  5),
+	F_MN( 96000000, P_PLL8,  1,  4),
+	F_MN(128000000, P_PLL8,  1,  3),
+	F_MN(145455000, P_PLL2,  2, 11),
+	F_MN(160000000, P_PLL2,  1,  5),
+	F_MN(177778000, P_PLL2,  2,  9),
+	F_MN(192000000, P_PLL8,  1,  2),
+	F_MN(200000000, P_PLL2,  1,  4),
+	F_MN(228571000, P_PLL2,  2,  7),
+	F_MN(266667000, P_PLL2,  1,  3),
+	F_MN(320000000, P_PLL2,  2,  5),
+	F_MN(400000000, P_PLL2,  1,  2),
+	F_MN(450000000, P_PLL15, 1,  2),
 	{ }
 };
 
@@ -897,12 +965,19 @@ static struct clk_dyn_rcg gfx3d_src = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gfx3d_src",
 			.parent_names = mmcc_pxo_pll8_pll2_pll3,
-			.num_parents = 3,
+			.num_parents = 4,
 			.ops = &clk_dyn_rcg_ops,
 		},
 	},
 };
 
+static const struct clk_init_data gfx3d_8064_init = {
+	.name = "gfx3d_src",
+	.parent_names = mmcc_pxo_pll8_pll2_pll15,
+	.num_parents = 4,
+	.ops = &clk_dyn_rcg_ops,
+};
+
 static struct clk_branch gfx3d_clk = {
 	.halt_reg = 0x01c8,
 	.halt_bit = 4,
@@ -919,6 +994,91 @@ static struct clk_branch gfx3d_clk = {
 	},
 };
 
+static struct freq_tbl clk_tbl_vcap[] = {
+	F_MN( 27000000, P_PXO,  0,  0),
+	F_MN( 54860000, P_PLL8, 1,  7),
+	F_MN( 64000000, P_PLL8, 1,  6),
+	F_MN( 76800000, P_PLL8, 1,  5),
+	F_MN(128000000, P_PLL8, 1,  3),
+	F_MN(160000000, P_PLL2, 1,  5),
+	F_MN(200000000, P_PLL2, 1,  4),
+	{ }
+};
+
+static struct clk_dyn_rcg vcap_src = {
+	.ns_reg = 0x021c,
+	.md_reg[0] = 0x01ec,
+	.md_reg[1] = 0x0218,
+	.mn[0] = {
+		.mnctr_en_bit = 8,
+		.mnctr_reset_bit = 23,
+		.mnctr_mode_shift = 9,
+		.n_val_shift = 18,
+		.m_val_shift = 4,
+		.width = 4,
+	},
+	.mn[1] = {
+		.mnctr_en_bit = 5,
+		.mnctr_reset_bit = 22,
+		.mnctr_mode_shift = 6,
+		.n_val_shift = 14,
+		.m_val_shift = 4,
+		.width = 4,
+	},
+	.s[0] = {
+		.src_sel_shift = 3,
+		.parent_map = mmcc_pxo_pll8_pll2_map,
+	},
+	.s[1] = {
+		.src_sel_shift = 0,
+		.parent_map = mmcc_pxo_pll8_pll2_map,
+	},
+	.mux_sel_bit = 11,
+	.freq_tbl = clk_tbl_vcap,
+	.clkr = {
+		.enable_reg = 0x0178,
+		.enable_mask = BIT(2),
+		.hw.init = &(struct clk_init_data){
+			.name = "vcap_src",
+			.parent_names = mmcc_pxo_pll8_pll2,
+			.num_parents = 3,
+			.ops = &clk_dyn_rcg_ops,
+		},
+	},
+};
+
+static struct clk_branch vcap_clk = {
+	.halt_reg = 0x0240,
+	.halt_bit = 15,
+	.clkr = {
+		.enable_reg = 0x0178,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vcap_clk",
+			.parent_names = (const char *[]){ "vcap_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch vcap_npl_clk = {
+	.halt_reg = 0x0240,
+	.halt_bit = 25,
+	.clkr = {
+		.enable_reg = 0x0178,
+		.enable_mask = BIT(13),
+		.hw.init = &(struct clk_init_data){
+			.name = "vcap_npl_clk",
+			.parent_names = (const char *[]){ "vcap_src" },
+			.num_parents = 1,
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
 static struct freq_tbl clk_tbl_ijpeg[] = {
 	{  27000000, P_PXO,  1, 0,  0 },
 	{  36570000, P_PLL8, 1, 2, 21 },
@@ -995,7 +1155,7 @@ static struct clk_rcg jpegd_src = {
 	.ns_reg = 0x00ac,
 	.p = {
 		.pre_div_shift = 12,
-		.pre_div_width = 2,
+		.pre_div_width = 4,
 	},
 	.s = {
 		.src_sel_shift = 0,
@@ -1115,7 +1275,7 @@ static struct clk_branch mdp_lut_clk = {
 		.enable_reg = 0x016c,
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
-			.parent_names = (const char *[]){ "mdp_clk" },
+			.parent_names = (const char *[]){ "mdp_src" },
 			.num_parents = 1,
 			.name = "mdp_lut_clk",
 			.ops = &clk_branch_ops,
@@ -1209,7 +1369,7 @@ static struct clk_branch rot_clk = {
 
 static u8 mmcc_pxo_hdmi_map[] = {
 	[P_PXO]		= 0,
-	[P_HDMI_PLL]	= 2,
+	[P_HDMI_PLL]	= 3,
 };
 
 static const char *mmcc_pxo_hdmi[] = {
@@ -1218,12 +1378,7 @@ static const char *mmcc_pxo_hdmi[] = {
 };
 
 static struct freq_tbl clk_tbl_tv[] = {
-	{  25200000, P_HDMI_PLL, 1, 0, 0 },
-	{  27000000, P_HDMI_PLL, 1, 0, 0 },
-	{  27030000, P_HDMI_PLL, 1, 0, 0 },
-	{  74250000, P_HDMI_PLL, 1, 0, 0 },
-	{ 108000000, P_HDMI_PLL, 1, 0, 0 },
-	{ 148500000, P_HDMI_PLL, 1, 0, 0 },
+	{  .src = P_HDMI_PLL, .pre_div = 1 },
 	{ }
 };
 
@@ -1254,7 +1409,7 @@ static struct clk_rcg tv_src = {
 			.name = "tv_src",
 			.parent_names = mmcc_pxo_hdmi,
 			.num_parents = 2,
-			.ops = &clk_rcg_ops,
+			.ops = &clk_rcg_bypass_ops,
 			.flags = CLK_SET_RATE_PARENT,
 		},
 	},
@@ -1326,6 +1481,38 @@ static struct clk_branch hdmi_tv_clk = {
 	},
 };
 
+static struct clk_branch rgb_tv_clk = {
+	.halt_reg = 0x0240,
+	.halt_bit = 27,
+	.clkr = {
+		.enable_reg = 0x0124,
+		.enable_mask = BIT(14),
+		.hw.init = &(struct clk_init_data){
+			.parent_names = tv_src_name,
+			.num_parents = 1,
+			.name = "rgb_tv_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch npl_tv_clk = {
+	.halt_reg = 0x0240,
+	.halt_bit = 26,
+	.clkr = {
+		.enable_reg = 0x0124,
+		.enable_mask = BIT(16),
+		.hw.init = &(struct clk_init_data){
+			.parent_names = tv_src_name,
+			.num_parents = 1,
+			.name = "npl_tv_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
 static struct clk_branch hdmi_app_clk = {
 	.halt_reg = 0x01cc,
 	.halt_bit = 25,
@@ -1342,15 +1529,15 @@ static struct clk_branch hdmi_app_clk = {
 };
 
 static struct freq_tbl clk_tbl_vcodec[] = {
-	{  27000000, P_PXO,  1,  0 },
-	{  32000000, P_PLL8, 1, 12 },
-	{  48000000, P_PLL8, 1,  8 },
-	{  54860000, P_PLL8, 1,  7 },
-	{  96000000, P_PLL8, 1,  4 },
-	{ 133330000, P_PLL2, 1,  6 },
-	{ 200000000, P_PLL2, 1,  4 },
-	{ 228570000, P_PLL2, 2,  7 },
-	{ 266670000, P_PLL2, 1,  3 },
+	F_MN( 27000000, P_PXO,  1,  0),
+	F_MN( 32000000, P_PLL8, 1, 12),
+	F_MN( 48000000, P_PLL8, 1,  8),
+	F_MN( 54860000, P_PLL8, 1,  7),
+	F_MN( 96000000, P_PLL8, 1,  4),
+	F_MN(133330000, P_PLL2, 1,  6),
+	F_MN(200000000, P_PLL2, 1,  4),
+	F_MN(228570000, P_PLL2, 2,  7),
+	F_MN(266670000, P_PLL2, 1,  3),
 	{ }
 };
 
@@ -1701,6 +1888,22 @@ static struct clk_branch rot_axi_clk = {
 	},
 };
 
+static struct clk_branch vcap_axi_clk = {
+	.halt_reg = 0x0240,
+	.halt_bit = 20,
+	.hwcg_reg = 0x0244,
+	.hwcg_bit = 11,
+	.clkr = {
+		.enable_reg = 0x0244,
+		.enable_mask = BIT(12),
+		.hw.init = &(struct clk_init_data){
+			.name = "vcap_axi_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
 static struct clk_branch vpe_axi_clk = {
 	.hwcg_reg = 0x0020,
 	.hwcg_bit = 27,
@@ -2003,6 +2206,20 @@ static struct clk_branch tv_enc_ahb_clk = {
 	},
 };
 
+static struct clk_branch vcap_ahb_clk = {
+	.halt_reg = 0x0240,
+	.halt_bit = 23,
+	.clkr = {
+		.enable_reg = 0x0248,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "vcap_ahb_clk",
+			.ops = &clk_branch_ops,
+			.flags = CLK_IS_ROOT,
+		},
+	},
+};
+
 static struct clk_branch vcodec_ahb_clk = {
 	.hwcg_reg = 0x0038,
 	.hwcg_bit = 26,
@@ -2215,6 +2432,175 @@ static const struct qcom_reset_map mmcc_msm8960_resets[] = {
 	[CSI_RDI2_RESET] = { 0x0214 },
 };
 
+static struct clk_regmap *mmcc_apq8064_clks[] = {
+	[AMP_AHB_CLK] = &amp_ahb_clk.clkr,
+	[DSI2_S_AHB_CLK] = &dsi2_s_ahb_clk.clkr,
+	[JPEGD_AHB_CLK] = &jpegd_ahb_clk.clkr,
+	[DSI_S_AHB_CLK] = &dsi_s_ahb_clk.clkr,
+	[DSI2_M_AHB_CLK] = &dsi2_m_ahb_clk.clkr,
+	[VPE_AHB_CLK] = &vpe_ahb_clk.clkr,
+	[SMMU_AHB_CLK] = &smmu_ahb_clk.clkr,
+	[HDMI_M_AHB_CLK] = &hdmi_m_ahb_clk.clkr,
+	[VFE_AHB_CLK] = &vfe_ahb_clk.clkr,
+	[ROT_AHB_CLK] = &rot_ahb_clk.clkr,
+	[VCODEC_AHB_CLK] = &vcodec_ahb_clk.clkr,
+	[MDP_AHB_CLK] = &mdp_ahb_clk.clkr,
+	[DSI_M_AHB_CLK] = &dsi_m_ahb_clk.clkr,
+	[CSI_AHB_CLK] = &csi_ahb_clk.clkr,
+	[MMSS_IMEM_AHB_CLK] = &mmss_imem_ahb_clk.clkr,
+	[IJPEG_AHB_CLK] = &ijpeg_ahb_clk.clkr,
+	[HDMI_S_AHB_CLK] = &hdmi_s_ahb_clk.clkr,
+	[GFX3D_AHB_CLK] = &gfx3d_ahb_clk.clkr,
+	[JPEGD_AXI_CLK] = &jpegd_axi_clk.clkr,
+	[GMEM_AXI_CLK] = &gmem_axi_clk.clkr,
+	[MDP_AXI_CLK] = &mdp_axi_clk.clkr,
+	[MMSS_IMEM_AXI_CLK] = &mmss_imem_axi_clk.clkr,
+	[IJPEG_AXI_CLK] = &ijpeg_axi_clk.clkr,
+	[GFX3D_AXI_CLK] = &gfx3d_axi_clk.clkr,
+	[VCODEC_AXI_CLK] = &vcodec_axi_clk.clkr,
+	[VFE_AXI_CLK] = &vfe_axi_clk.clkr,
+	[VPE_AXI_CLK] = &vpe_axi_clk.clkr,
+	[ROT_AXI_CLK] = &rot_axi_clk.clkr,
+	[VCODEC_AXI_A_CLK] = &vcodec_axi_a_clk.clkr,
+	[VCODEC_AXI_B_CLK] = &vcodec_axi_b_clk.clkr,
+	[CSI0_SRC] = &csi0_src.clkr,
+	[CSI0_CLK] = &csi0_clk.clkr,
+	[CSI0_PHY_CLK] = &csi0_phy_clk.clkr,
+	[CSI1_SRC] = &csi1_src.clkr,
+	[CSI1_CLK] = &csi1_clk.clkr,
+	[CSI1_PHY_CLK] = &csi1_phy_clk.clkr,
+	[CSI2_SRC] = &csi2_src.clkr,
+	[CSI2_CLK] = &csi2_clk.clkr,
+	[CSI2_PHY_CLK] = &csi2_phy_clk.clkr,
+	[CSI_PIX_CLK] = &csi_pix_clk.clkr,
+	[CSI_RDI_CLK] = &csi_rdi_clk.clkr,
+	[MDP_VSYNC_CLK] = &mdp_vsync_clk.clkr,
+	[HDMI_APP_CLK] = &hdmi_app_clk.clkr,
+	[CSI_PIX1_CLK] = &csi_pix1_clk.clkr,
+	[CSI_RDI2_CLK] = &csi_rdi2_clk.clkr,
+	[CSI_RDI1_CLK] = &csi_rdi1_clk.clkr,
+	[GFX3D_SRC] = &gfx3d_src.clkr,
+	[GFX3D_CLK] = &gfx3d_clk.clkr,
+	[IJPEG_SRC] = &ijpeg_src.clkr,
+	[IJPEG_CLK] = &ijpeg_clk.clkr,
+	[JPEGD_SRC] = &jpegd_src.clkr,
+	[JPEGD_CLK] = &jpegd_clk.clkr,
+	[MDP_SRC] = &mdp_src.clkr,
+	[MDP_CLK] = &mdp_clk.clkr,
+	[MDP_LUT_CLK] = &mdp_lut_clk.clkr,
+	[ROT_SRC] = &rot_src.clkr,
+	[ROT_CLK] = &rot_clk.clkr,
+	[TV_DAC_CLK] = &tv_dac_clk.clkr,
+	[HDMI_TV_CLK] = &hdmi_tv_clk.clkr,
+	[MDP_TV_CLK] = &mdp_tv_clk.clkr,
+	[TV_SRC] = &tv_src.clkr,
+	[VCODEC_SRC] = &vcodec_src.clkr,
+	[VCODEC_CLK] = &vcodec_clk.clkr,
+	[VFE_SRC] = &vfe_src.clkr,
+	[VFE_CLK] = &vfe_clk.clkr,
+	[VFE_CSI_CLK] = &vfe_csi_clk.clkr,
+	[VPE_SRC] = &vpe_src.clkr,
+	[VPE_CLK] = &vpe_clk.clkr,
+	[CAMCLK0_SRC] = &camclk0_src.clkr,
+	[CAMCLK0_CLK] = &camclk0_clk.clkr,
+	[CAMCLK1_SRC] = &camclk1_src.clkr,
+	[CAMCLK1_CLK] = &camclk1_clk.clkr,
+	[CAMCLK2_SRC] = &camclk2_src.clkr,
+	[CAMCLK2_CLK] = &camclk2_clk.clkr,
+	[CSIPHYTIMER_SRC] = &csiphytimer_src.clkr,
+	[CSIPHY2_TIMER_CLK] = &csiphy2_timer_clk.clkr,
+	[CSIPHY1_TIMER_CLK] = &csiphy1_timer_clk.clkr,
+	[CSIPHY0_TIMER_CLK] = &csiphy0_timer_clk.clkr,
+	[PLL2] = &pll2.clkr,
+	[RGB_TV_CLK] = &rgb_tv_clk.clkr,
+	[NPL_TV_CLK] = &npl_tv_clk.clkr,
+	[VCAP_AHB_CLK] = &vcap_ahb_clk.clkr,
+	[VCAP_AXI_CLK] = &vcap_axi_clk.clkr,
+	[VCAP_SRC] = &vcap_src.clkr,
+	[VCAP_CLK] = &vcap_clk.clkr,
+	[VCAP_NPL_CLK] = &vcap_npl_clk.clkr,
+	[PLL15] = &pll15.clkr,
+};
+
+static const struct qcom_reset_map mmcc_apq8064_resets[] = {
+	[GFX3D_AXI_RESET] = { 0x0208, 17 },
+	[VCAP_AXI_RESET] = { 0x0208, 16 },
+	[VPE_AXI_RESET] = { 0x0208, 15 },
+	[IJPEG_AXI_RESET] = { 0x0208, 14 },
+	[MPD_AXI_RESET] = { 0x0208, 13 },
+	[VFE_AXI_RESET] = { 0x0208, 9 },
+	[SP_AXI_RESET] = { 0x0208, 8 },
+	[VCODEC_AXI_RESET] = { 0x0208, 7 },
+	[ROT_AXI_RESET] = { 0x0208, 6 },
+	[VCODEC_AXI_A_RESET] = { 0x0208, 5 },
+	[VCODEC_AXI_B_RESET] = { 0x0208, 4 },
+	[FAB_S3_AXI_RESET] = { 0x0208, 3 },
+	[FAB_S2_AXI_RESET] = { 0x0208, 2 },
+	[FAB_S1_AXI_RESET] = { 0x0208, 1 },
+	[FAB_S0_AXI_RESET] = { 0x0208 },
+	[SMMU_GFX3D_ABH_RESET] = { 0x020c, 31 },
+	[SMMU_VPE_AHB_RESET] = { 0x020c, 30 },
+	[SMMU_VFE_AHB_RESET] = { 0x020c, 29 },
+	[SMMU_ROT_AHB_RESET] = { 0x020c, 28 },
+	[SMMU_VCODEC_B_AHB_RESET] = { 0x020c, 27 },
+	[SMMU_VCODEC_A_AHB_RESET] = { 0x020c, 26 },
+	[SMMU_MDP1_AHB_RESET] = { 0x020c, 25 },
+	[SMMU_MDP0_AHB_RESET] = { 0x020c, 24 },
+	[SMMU_JPEGD_AHB_RESET] = { 0x020c, 23 },
+	[SMMU_IJPEG_AHB_RESET] = { 0x020c, 22 },
+	[APU_AHB_RESET] = { 0x020c, 18 },
+	[CSI_AHB_RESET] = { 0x020c, 17 },
+	[TV_ENC_AHB_RESET] = { 0x020c, 15 },
+	[VPE_AHB_RESET] = { 0x020c, 14 },
+	[FABRIC_AHB_RESET] = { 0x020c, 13 },
+	[GFX3D_AHB_RESET] = { 0x020c, 10 },
+	[HDMI_AHB_RESET] = { 0x020c, 9 },
+	[MSSS_IMEM_AHB_RESET] = { 0x020c, 8 },
+	[IJPEG_AHB_RESET] = { 0x020c, 7 },
+	[DSI_M_AHB_RESET] = { 0x020c, 6 },
+	[DSI_S_AHB_RESET] = { 0x020c, 5 },
+	[JPEGD_AHB_RESET] = { 0x020c, 4 },
+	[MDP_AHB_RESET] = { 0x020c, 3 },
+	[ROT_AHB_RESET] = { 0x020c, 2 },
+	[VCODEC_AHB_RESET] = { 0x020c, 1 },
+	[VFE_AHB_RESET] = { 0x020c, 0 },
+	[SMMU_VCAP_AHB_RESET] = { 0x0200, 3 },
+	[VCAP_AHB_RESET] = { 0x0200, 2 },
+	[DSI2_M_AHB_RESET] = { 0x0200, 1 },
+	[DSI2_S_AHB_RESET] = { 0x0200, 0 },
+	[CSIPHY2_RESET] = { 0x0210, 31 },
+	[CSI_PIX1_RESET] = { 0x0210, 30 },
+	[CSIPHY0_RESET] = { 0x0210, 29 },
+	[CSIPHY1_RESET] = { 0x0210, 28 },
+	[CSI_RDI_RESET] = { 0x0210, 27 },
+	[CSI_PIX_RESET] = { 0x0210, 26 },
+	[DSI2_RESET] = { 0x0210, 25 },
+	[VFE_CSI_RESET] = { 0x0210, 24 },
+	[MDP_RESET] = { 0x0210, 21 },
+	[AMP_RESET] = { 0x0210, 20 },
+	[JPEGD_RESET] = { 0x0210, 19 },
+	[CSI1_RESET] = { 0x0210, 18 },
+	[VPE_RESET] = { 0x0210, 17 },
+	[MMSS_FABRIC_RESET] = { 0x0210, 16 },
+	[VFE_RESET] = { 0x0210, 15 },
+	[GFX3D_RESET] = { 0x0210, 12 },
+	[HDMI_RESET] = { 0x0210, 11 },
+	[MMSS_IMEM_RESET] = { 0x0210, 10 },
+	[IJPEG_RESET] = { 0x0210, 9 },
+	[CSI0_RESET] = { 0x0210, 8 },
+	[DSI_RESET] = { 0x0210, 7 },
+	[VCODEC_RESET] = { 0x0210, 6 },
+	[MDP_TV_RESET] = { 0x0210, 4 },
+	[MDP_VSYNC_RESET] = { 0x0210, 3 },
+	[ROT_RESET] = { 0x0210, 2 },
+	[TV_HDMI_RESET] = { 0x0210, 1 },
+	[VCAP_NPL_RESET] = { 0x0214, 4 },
+	[VCAP_RESET] = { 0x0214, 3 },
+	[CSI2_RESET] = { 0x0214, 2 },
+	[CSI_RDI1_RESET] = { 0x0214, 1 },
+	[CSI_RDI2_RESET] = { 0x0214 },
+};
+
 static const struct regmap_config mmcc_msm8960_regmap_config = {
 	.reg_bits	= 32,
 	.reg_stride	= 4,
@@ -2223,6 +2609,14 @@ static const struct regmap_config mmcc_msm8960_regmap_config = {
 	.fast_io	= true,
 };
 
+static const struct regmap_config mmcc_apq8064_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x350,
+	.fast_io	= true,
+};
+
 static const struct qcom_cc_desc mmcc_msm8960_desc = {
 	.config = &mmcc_msm8960_regmap_config,
 	.clks = mmcc_msm8960_clks,
@@ -2231,15 +2625,47 @@ static const struct qcom_cc_desc mmcc_msm8960_desc = {
 	.num_resets = ARRAY_SIZE(mmcc_msm8960_resets),
 };
 
+static const struct qcom_cc_desc mmcc_apq8064_desc = {
+	.config = &mmcc_apq8064_regmap_config,
+	.clks = mmcc_apq8064_clks,
+	.num_clks = ARRAY_SIZE(mmcc_apq8064_clks),
+	.resets = mmcc_apq8064_resets,
+	.num_resets = ARRAY_SIZE(mmcc_apq8064_resets),
+};
+
 static const struct of_device_id mmcc_msm8960_match_table[] = {
-	{ .compatible = "qcom,mmcc-msm8960" },
+	{ .compatible = "qcom,mmcc-msm8960", .data = &mmcc_msm8960_desc },
+	{ .compatible = "qcom,mmcc-apq8064", .data = &mmcc_apq8064_desc },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, mmcc_msm8960_match_table);
 
 static int mmcc_msm8960_probe(struct platform_device *pdev)
 {
-	return qcom_cc_probe(pdev, &mmcc_msm8960_desc);
+	const struct of_device_id *match;
+	struct regmap *regmap;
+	bool is_8064;
+	struct device *dev = &pdev->dev;
+
+	match = of_match_device(mmcc_msm8960_match_table, dev);
+	if (!match)
+		return -EINVAL;
+
+	is_8064 = of_device_is_compatible(dev->of_node, "qcom,mmcc-apq8064");
+	if (is_8064) {
+		gfx3d_src.freq_tbl = clk_tbl_gfx3d_8064;
+		gfx3d_src.clkr.hw.init = &gfx3d_8064_init;
+		gfx3d_src.s[0].parent_map = mmcc_pxo_pll8_pll2_pll15_map;
+		gfx3d_src.s[1].parent_map = mmcc_pxo_pll8_pll2_pll15_map;
+	}
+
+	regmap = qcom_cc_map(pdev, match->data);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	clk_pll_configure_sr(&pll15, regmap, &pll15_config, false);
+
+	return qcom_cc_really_probe(pdev, match->data, regmap);
 }
 
 static int mmcc_msm8960_remove(struct platform_device *pdev)
diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c
index c65b9051587..bc8f519c47a 100644
--- a/drivers/clk/qcom/mmcc-msm8974.c
+++ b/drivers/clk/qcom/mmcc-msm8974.c
@@ -2547,18 +2547,16 @@ MODULE_DEVICE_TABLE(of, mmcc_msm8974_match_table);
 
 static int mmcc_msm8974_probe(struct platform_device *pdev)
 {
-	int ret;
 	struct regmap *regmap;
 
-	ret = qcom_cc_probe(pdev, &mmcc_msm8974_desc);
-	if (ret)
-		return ret;
+	regmap = qcom_cc_map(pdev, &mmcc_msm8974_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
 
-	regmap = dev_get_regmap(&pdev->dev, NULL);
 	clk_pll_configure_sr_hpm_lp(&mmpll1, regmap, &mmpll1_config, true);
 	clk_pll_configure_sr_hpm_lp(&mmpll3, regmap, &mmpll3_config, false);
 
-	return 0;
+	return qcom_cc_really_probe(pdev, &mmcc_msm8974_desc, regmap);
 }
 
 static int mmcc_msm8974_remove(struct platform_device *pdev)
diff --git a/drivers/clk/rockchip/Makefile b/drivers/clk/rockchip/Makefile
index 8d3aefad2e7..ee6b077381e 100644
--- a/drivers/clk/rockchip/Makefile
+++ b/drivers/clk/rockchip/Makefile
@@ -3,3 +3,9 @@
 #
 
 obj-y	+= clk-rockchip.o
+obj-y	+= clk.o
+obj-y	+= clk-pll.o
+obj-$(CONFIG_RESET_CONTROLLER)	+= softrst.o
+
+obj-y	+= clk-rk3188.o
+obj-y	+= clk-rk3288.o
diff --git a/drivers/clk/rockchip/clk-pll.c b/drivers/clk/rockchip/clk-pll.c
new file mode 100644
index 00000000000..f2a1c7abf4d
--- /dev/null
+++ b/drivers/clk/rockchip/clk-pll.c
@@ -0,0 +1,431 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <asm/div64.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/regmap.h>
+#include "clk.h"
+
+#define PLL_MODE_MASK		0x3
+#define PLL_MODE_SLOW		0x0
+#define PLL_MODE_NORM		0x1
+#define PLL_MODE_DEEP		0x2
+
+struct rockchip_clk_pll {
+	struct clk_hw		hw;
+
+	struct clk_mux		pll_mux;
+	const struct clk_ops	*pll_mux_ops;
+
+	struct notifier_block	clk_nb;
+	bool			rate_change_remuxed;
+
+	void __iomem		*reg_base;
+	int			lock_offset;
+	unsigned int		lock_shift;
+	enum rockchip_pll_type	type;
+	const struct rockchip_pll_rate_table *rate_table;
+	unsigned int		rate_count;
+	spinlock_t		*lock;
+};
+
+#define to_rockchip_clk_pll(_hw) container_of(_hw, struct rockchip_clk_pll, hw)
+#define to_rockchip_clk_pll_nb(nb) \
+			container_of(nb, struct rockchip_clk_pll, clk_nb)
+
+static const struct rockchip_pll_rate_table *rockchip_get_pll_settings(
+			    struct rockchip_clk_pll *pll, unsigned long rate)
+{
+	const struct rockchip_pll_rate_table  *rate_table = pll->rate_table;
+	int i;
+
+	for (i = 0; i < pll->rate_count; i++) {
+		if (rate == rate_table[i].rate)
+			return &rate_table[i];
+	}
+
+	return NULL;
+}
+
+static long rockchip_pll_round_rate(struct clk_hw *hw,
+			    unsigned long drate, unsigned long *prate)
+{
+	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
+	const struct rockchip_pll_rate_table *rate_table = pll->rate_table;
+	int i;
+
+	/* Assumming rate_table is in descending order */
+	for (i = 0; i < pll->rate_count; i++) {
+		if (drate >= rate_table[i].rate)
+			return rate_table[i].rate;
+	}
+
+	/* return minimum supported value */
+	return rate_table[i - 1].rate;
+}
+
+/*
+ * Wait for the pll to reach the locked state.
+ * The calling set_rate function is responsible for making sure the
+ * grf regmap is available.
+ */
+static int rockchip_pll_wait_lock(struct rockchip_clk_pll *pll)
+{
+	struct regmap *grf = rockchip_clk_get_grf();
+	unsigned int val;
+	int delay = 24000000, ret;
+
+	while (delay > 0) {
+		ret = regmap_read(grf, pll->lock_offset, &val);
+		if (ret) {
+			pr_err("%s: failed to read pll lock status: %d\n",
+			       __func__, ret);
+			return ret;
+		}
+
+		if (val & BIT(pll->lock_shift))
+			return 0;
+		delay--;
+	}
+
+	pr_err("%s: timeout waiting for pll to lock\n", __func__);
+	return -ETIMEDOUT;
+}
+
+/**
+ * Set pll mux when changing the pll rate.
+ * This makes sure to move the pll mux away from the actual pll before
+ * changing its rate and back to the original parent after the change.
+ */
+static int rockchip_pll_notifier_cb(struct notifier_block *nb,
+					unsigned long event, void *data)
+{
+	struct rockchip_clk_pll *pll = to_rockchip_clk_pll_nb(nb);
+	struct clk_mux *pll_mux = &pll->pll_mux;
+	const struct clk_ops *pll_mux_ops = pll->pll_mux_ops;
+	int cur_parent;
+
+	switch (event) {
+	case PRE_RATE_CHANGE:
+		cur_parent = pll_mux_ops->get_parent(&pll_mux->hw);
+		if (cur_parent == PLL_MODE_NORM) {
+			pll_mux_ops->set_parent(&pll_mux->hw, PLL_MODE_SLOW);
+			pll->rate_change_remuxed = 1;
+		}
+		break;
+	case POST_RATE_CHANGE:
+		if (pll->rate_change_remuxed) {
+			pll_mux_ops->set_parent(&pll_mux->hw, PLL_MODE_NORM);
+			pll->rate_change_remuxed = 0;
+		}
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+/**
+ * PLL used in RK3066, RK3188 and RK3288
+ */
+
+#define RK3066_PLL_RESET_DELAY(nr)	((nr * 500) / 24 + 1)
+
+#define RK3066_PLLCON(i)		(i * 0x4)
+#define RK3066_PLLCON0_OD_MASK		0xf
+#define RK3066_PLLCON0_OD_SHIFT		0
+#define RK3066_PLLCON0_NR_MASK		0x3f
+#define RK3066_PLLCON0_NR_SHIFT		8
+#define RK3066_PLLCON1_NF_MASK		0x1fff
+#define RK3066_PLLCON1_NF_SHIFT		0
+#define RK3066_PLLCON2_BWADJ_MASK	0xfff
+#define RK3066_PLLCON2_BWADJ_SHIFT	0
+#define RK3066_PLLCON3_RESET		(1 << 5)
+#define RK3066_PLLCON3_PWRDOWN		(1 << 1)
+#define RK3066_PLLCON3_BYPASS		(1 << 0)
+
+static unsigned long rockchip_rk3066_pll_recalc_rate(struct clk_hw *hw,
+						     unsigned long prate)
+{
+	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
+	u64 nf, nr, no, rate64 = prate;
+	u32 pllcon;
+
+	pllcon = readl_relaxed(pll->reg_base + RK3066_PLLCON(3));
+	if (pllcon & RK3066_PLLCON3_BYPASS) {
+		pr_debug("%s: pll %s is bypassed\n", __func__,
+			__clk_get_name(hw->clk));
+		return prate;
+	}
+
+	pllcon = readl_relaxed(pll->reg_base + RK3066_PLLCON(1));
+	nf = (pllcon >> RK3066_PLLCON1_NF_SHIFT) & RK3066_PLLCON1_NF_MASK;
+
+	pllcon = readl_relaxed(pll->reg_base + RK3066_PLLCON(0));
+	nr = (pllcon >> RK3066_PLLCON0_NR_SHIFT) & RK3066_PLLCON0_NR_MASK;
+	no = (pllcon >> RK3066_PLLCON0_OD_SHIFT) & RK3066_PLLCON0_OD_MASK;
+
+	rate64 *= (nf + 1);
+	do_div(rate64, nr + 1);
+	do_div(rate64, no + 1);
+
+	return (unsigned long)rate64;
+}
+
+static int rockchip_rk3066_pll_set_rate(struct clk_hw *hw, unsigned long drate,
+					unsigned long prate)
+{
+	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
+	const struct rockchip_pll_rate_table *rate;
+	unsigned long old_rate = rockchip_rk3066_pll_recalc_rate(hw, prate);
+	struct regmap *grf = rockchip_clk_get_grf();
+	int ret;
+
+	if (IS_ERR(grf)) {
+		pr_debug("%s: grf regmap not available, aborting rate change\n",
+			 __func__);
+		return PTR_ERR(grf);
+	}
+
+	pr_debug("%s: changing %s from %lu to %lu with a parent rate of %lu\n",
+		 __func__, __clk_get_name(hw->clk), old_rate, drate, prate);
+
+	/* Get required rate settings from table */
+	rate = rockchip_get_pll_settings(pll, drate);
+	if (!rate) {
+		pr_err("%s: Invalid rate : %lu for pll clk %s\n", __func__,
+			drate, __clk_get_name(hw->clk));
+		return -EINVAL;
+	}
+
+	pr_debug("%s: rate settings for %lu (nr, no, nf): (%d, %d, %d)\n",
+		 __func__, rate->rate, rate->nr, rate->no, rate->nf);
+
+	/* enter reset mode */
+	writel(HIWORD_UPDATE(RK3066_PLLCON3_RESET, RK3066_PLLCON3_RESET, 0),
+	       pll->reg_base + RK3066_PLLCON(3));
+
+	/* update pll values */
+	writel(HIWORD_UPDATE(rate->nr - 1, RK3066_PLLCON0_NR_MASK,
+					   RK3066_PLLCON0_NR_SHIFT) |
+	       HIWORD_UPDATE(rate->no - 1, RK3066_PLLCON0_OD_MASK,
+					   RK3066_PLLCON0_OD_SHIFT),
+	       pll->reg_base + RK3066_PLLCON(0));
+
+	writel_relaxed(HIWORD_UPDATE(rate->nf - 1, RK3066_PLLCON1_NF_MASK,
+						   RK3066_PLLCON1_NF_SHIFT),
+		       pll->reg_base + RK3066_PLLCON(1));
+	writel_relaxed(HIWORD_UPDATE(rate->bwadj, RK3066_PLLCON2_BWADJ_MASK,
+						  RK3066_PLLCON2_BWADJ_SHIFT),
+		       pll->reg_base + RK3066_PLLCON(2));
+
+	/* leave reset and wait the reset_delay */
+	writel(HIWORD_UPDATE(0, RK3066_PLLCON3_RESET, 0),
+	       pll->reg_base + RK3066_PLLCON(3));
+	udelay(RK3066_PLL_RESET_DELAY(rate->nr));
+
+	/* wait for the pll to lock */
+	ret = rockchip_pll_wait_lock(pll);
+	if (ret) {
+		pr_warn("%s: pll did not lock, trying to restore old rate %lu\n",
+			__func__, old_rate);
+		rockchip_rk3066_pll_set_rate(hw, old_rate, prate);
+	}
+
+	return ret;
+}
+
+static int rockchip_rk3066_pll_enable(struct clk_hw *hw)
+{
+	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
+
+	writel(HIWORD_UPDATE(0, RK3066_PLLCON3_PWRDOWN, 0),
+	       pll->reg_base + RK3066_PLLCON(3));
+
+	return 0;
+}
+
+static void rockchip_rk3066_pll_disable(struct clk_hw *hw)
+{
+	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
+
+	writel(HIWORD_UPDATE(RK3066_PLLCON3_PWRDOWN,
+			     RK3066_PLLCON3_PWRDOWN, 0),
+	       pll->reg_base + RK3066_PLLCON(3));
+}
+
+static int rockchip_rk3066_pll_is_enabled(struct clk_hw *hw)
+{
+	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
+	u32 pllcon = readl(pll->reg_base + RK3066_PLLCON(3));
+
+	return !(pllcon & RK3066_PLLCON3_PWRDOWN);
+}
+
+static const struct clk_ops rockchip_rk3066_pll_clk_norate_ops = {
+	.recalc_rate = rockchip_rk3066_pll_recalc_rate,
+	.enable = rockchip_rk3066_pll_enable,
+	.disable = rockchip_rk3066_pll_disable,
+	.is_enabled = rockchip_rk3066_pll_is_enabled,
+};
+
+static const struct clk_ops rockchip_rk3066_pll_clk_ops = {
+	.recalc_rate = rockchip_rk3066_pll_recalc_rate,
+	.round_rate = rockchip_pll_round_rate,
+	.set_rate = rockchip_rk3066_pll_set_rate,
+	.enable = rockchip_rk3066_pll_enable,
+	.disable = rockchip_rk3066_pll_disable,
+	.is_enabled = rockchip_rk3066_pll_is_enabled,
+};
+
+/*
+ * Common registering of pll clocks
+ */
+
+struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
+		const char *name, const char **parent_names, u8 num_parents,
+		void __iomem *base, int con_offset, int grf_lock_offset,
+		int lock_shift, int mode_offset, int mode_shift,
+		struct rockchip_pll_rate_table *rate_table,
+		spinlock_t *lock)
+{
+	const char *pll_parents[3];
+	struct clk_init_data init;
+	struct rockchip_clk_pll *pll;
+	struct clk_mux *pll_mux;
+	struct clk *pll_clk, *mux_clk;
+	char pll_name[20];
+	int ret;
+
+	if (num_parents != 2) {
+		pr_err("%s: needs two parent clocks\n", __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* name the actual pll */
+	snprintf(pll_name, sizeof(pll_name), "pll_%s", name);
+
+	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
+	if (!pll)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = pll_name;
+
+	/* keep all plls untouched for now */
+	init.flags = CLK_IGNORE_UNUSED;
+
+	init.parent_names = &parent_names[0];
+	init.num_parents = 1;
+
+	if (rate_table) {
+		int len;
+
+		/* find count of rates in rate_table */
+		for (len = 0; rate_table[len].rate != 0; )
+			len++;
+
+		pll->rate_count = len;
+		pll->rate_table = kmemdup(rate_table,
+					pll->rate_count *
+					sizeof(struct rockchip_pll_rate_table),
+					GFP_KERNEL);
+		WARN(!pll->rate_table,
+			"%s: could not allocate rate table for %s\n",
+			__func__, name);
+	}
+
+	switch (pll_type) {
+	case pll_rk3066:
+		if (!pll->rate_table)
+			init.ops = &rockchip_rk3066_pll_clk_norate_ops;
+		else
+			init.ops = &rockchip_rk3066_pll_clk_ops;
+		break;
+	default:
+		pr_warn("%s: Unknown pll type for pll clk %s\n",
+			__func__, name);
+	}
+
+	pll->hw.init = &init;
+	pll->type = pll_type;
+	pll->reg_base = base + con_offset;
+	pll->lock_offset = grf_lock_offset;
+	pll->lock_shift = lock_shift;
+	pll->lock = lock;
+	pll->clk_nb.notifier_call = rockchip_pll_notifier_cb;
+
+	pll_clk = clk_register(NULL, &pll->hw);
+	if (IS_ERR(pll_clk)) {
+		pr_err("%s: failed to register pll clock %s : %ld\n",
+			__func__, name, PTR_ERR(pll_clk));
+		mux_clk = pll_clk;
+		goto err_pll;
+	}
+
+	ret = clk_notifier_register(pll_clk, &pll->clk_nb);
+	if (ret) {
+		pr_err("%s: failed to register clock notifier for %s : %d\n",
+				__func__, name, ret);
+		mux_clk = ERR_PTR(ret);
+		goto err_pll_notifier;
+	}
+
+	/* create the mux on top of the real pll */
+	pll->pll_mux_ops = &clk_mux_ops;
+	pll_mux = &pll->pll_mux;
+
+	/* the actual muxing is xin24m, pll-output, xin32k */
+	pll_parents[0] = parent_names[0];
+	pll_parents[1] = pll_name;
+	pll_parents[2] = parent_names[1];
+
+	init.name = name;
+	init.flags = CLK_SET_RATE_PARENT;
+	init.ops = pll->pll_mux_ops;
+	init.parent_names = pll_parents;
+	init.num_parents = ARRAY_SIZE(pll_parents);
+
+	pll_mux->reg = base + mode_offset;
+	pll_mux->shift = mode_shift;
+	pll_mux->mask = PLL_MODE_MASK;
+	pll_mux->flags = 0;
+	pll_mux->lock = lock;
+	pll_mux->hw.init = &init;
+
+	if (pll_type == pll_rk3066)
+		pll_mux->flags |= CLK_MUX_HIWORD_MASK;
+
+	mux_clk = clk_register(NULL, &pll_mux->hw);
+	if (IS_ERR(mux_clk))
+		goto err_mux;
+
+	return mux_clk;
+
+err_mux:
+	ret = clk_notifier_unregister(pll_clk, &pll->clk_nb);
+	if (ret) {
+		pr_err("%s: could not unregister clock notifier in error path : %d\n",
+		       __func__, ret);
+		return mux_clk;
+	}
+err_pll_notifier:
+	clk_unregister(pll_clk);
+err_pll:
+	kfree(pll);
+	return mux_clk;
+}
diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c
new file mode 100644
index 00000000000..a83a6d8d0fb
--- /dev/null
+++ b/drivers/clk/rockchip/clk-rk3188.c
@@ -0,0 +1,672 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <dt-bindings/clock/rk3188-cru-common.h>
+#include "clk.h"
+
+#define RK3188_GRF_SOC_STATUS	0xac
+
+enum rk3188_plls {
+	apll, cpll, dpll, gpll,
+};
+
+struct rockchip_pll_rate_table rk3188_pll_rates[] = {
+	RK3066_PLL_RATE(2208000000, 1, 92, 1),
+	RK3066_PLL_RATE(2184000000, 1, 91, 1),
+	RK3066_PLL_RATE(2160000000, 1, 90, 1),
+	RK3066_PLL_RATE(2136000000, 1, 89, 1),
+	RK3066_PLL_RATE(2112000000, 1, 88, 1),
+	RK3066_PLL_RATE(2088000000, 1, 87, 1),
+	RK3066_PLL_RATE(2064000000, 1, 86, 1),
+	RK3066_PLL_RATE(2040000000, 1, 85, 1),
+	RK3066_PLL_RATE(2016000000, 1, 84, 1),
+	RK3066_PLL_RATE(1992000000, 1, 83, 1),
+	RK3066_PLL_RATE(1968000000, 1, 82, 1),
+	RK3066_PLL_RATE(1944000000, 1, 81, 1),
+	RK3066_PLL_RATE(1920000000, 1, 80, 1),
+	RK3066_PLL_RATE(1896000000, 1, 79, 1),
+	RK3066_PLL_RATE(1872000000, 1, 78, 1),
+	RK3066_PLL_RATE(1848000000, 1, 77, 1),
+	RK3066_PLL_RATE(1824000000, 1, 76, 1),
+	RK3066_PLL_RATE(1800000000, 1, 75, 1),
+	RK3066_PLL_RATE(1776000000, 1, 74, 1),
+	RK3066_PLL_RATE(1752000000, 1, 73, 1),
+	RK3066_PLL_RATE(1728000000, 1, 72, 1),
+	RK3066_PLL_RATE(1704000000, 1, 71, 1),
+	RK3066_PLL_RATE(1680000000, 1, 70, 1),
+	RK3066_PLL_RATE(1656000000, 1, 69, 1),
+	RK3066_PLL_RATE(1632000000, 1, 68, 1),
+	RK3066_PLL_RATE(1608000000, 1, 67, 1),
+	RK3066_PLL_RATE(1560000000, 1, 65, 1),
+	RK3066_PLL_RATE(1512000000, 1, 63, 1),
+	RK3066_PLL_RATE(1488000000, 1, 62, 1),
+	RK3066_PLL_RATE(1464000000, 1, 61, 1),
+	RK3066_PLL_RATE(1440000000, 1, 60, 1),
+	RK3066_PLL_RATE(1416000000, 1, 59, 1),
+	RK3066_PLL_RATE(1392000000, 1, 58, 1),
+	RK3066_PLL_RATE(1368000000, 1, 57, 1),
+	RK3066_PLL_RATE(1344000000, 1, 56, 1),
+	RK3066_PLL_RATE(1320000000, 1, 55, 1),
+	RK3066_PLL_RATE(1296000000, 1, 54, 1),
+	RK3066_PLL_RATE(1272000000, 1, 53, 1),
+	RK3066_PLL_RATE(1248000000, 1, 52, 1),
+	RK3066_PLL_RATE(1224000000, 1, 51, 1),
+	RK3066_PLL_RATE(1200000000, 1, 50, 1),
+	RK3066_PLL_RATE(1188000000, 2, 99, 1),
+	RK3066_PLL_RATE(1176000000, 1, 49, 1),
+	RK3066_PLL_RATE(1128000000, 1, 47, 1),
+	RK3066_PLL_RATE(1104000000, 1, 46, 1),
+	RK3066_PLL_RATE(1008000000, 1, 84, 2),
+	RK3066_PLL_RATE( 912000000, 1, 76, 2),
+	RK3066_PLL_RATE( 891000000, 8, 594, 2),
+	RK3066_PLL_RATE( 888000000, 1, 74, 2),
+	RK3066_PLL_RATE( 816000000, 1, 68, 2),
+	RK3066_PLL_RATE( 798000000, 2, 133, 2),
+	RK3066_PLL_RATE( 792000000, 1, 66, 2),
+	RK3066_PLL_RATE( 768000000, 1, 64, 2),
+	RK3066_PLL_RATE( 742500000, 8, 495, 2),
+	RK3066_PLL_RATE( 696000000, 1, 58, 2),
+	RK3066_PLL_RATE( 600000000, 1, 50, 2),
+	RK3066_PLL_RATE( 594000000, 2, 198, 4),
+	RK3066_PLL_RATE( 552000000, 1, 46, 2),
+	RK3066_PLL_RATE( 504000000, 1, 84, 4),
+	RK3066_PLL_RATE( 456000000, 1, 76, 4),
+	RK3066_PLL_RATE( 408000000, 1, 68, 4),
+	RK3066_PLL_RATE( 384000000, 2, 128, 4),
+	RK3066_PLL_RATE( 360000000, 1, 60, 4),
+	RK3066_PLL_RATE( 312000000, 1, 52, 4),
+	RK3066_PLL_RATE( 300000000, 1, 50, 4),
+	RK3066_PLL_RATE( 297000000, 2, 198, 8),
+	RK3066_PLL_RATE( 252000000, 1, 84, 8),
+	RK3066_PLL_RATE( 216000000, 1, 72, 8),
+	RK3066_PLL_RATE( 148500000, 2, 99, 8),
+	RK3066_PLL_RATE( 126000000, 1, 84, 16),
+	RK3066_PLL_RATE(  48000000, 1, 64, 32),
+	{ /* sentinel */ },
+};
+
+PNAME(mux_pll_p)		= { "xin24m", "xin32k" };
+PNAME(mux_armclk_p)		= { "apll", "gpll_armclk" };
+PNAME(mux_ddrphy_p)		= { "dpll", "gpll_ddr" };
+PNAME(mux_pll_src_gpll_cpll_p)	= { "gpll", "cpll" };
+PNAME(mux_pll_src_cpll_gpll_p)	= { "cpll", "gpll" };
+PNAME(mux_aclk_cpu_p)		= { "apll", "gpll" };
+PNAME(mux_sclk_cif0_p)		= { "cif0_pre", "xin24m" };
+PNAME(mux_sclk_i2s0_p)		= { "i2s0_pre", "i2s0_frac", "xin12m" };
+PNAME(mux_sclk_spdif_p)		= { "spdif_src", "spdif_frac", "xin12m" };
+PNAME(mux_sclk_uart0_p)		= { "uart0_pre", "uart0_frac", "xin24m" };
+PNAME(mux_sclk_uart1_p)		= { "uart1_pre", "uart1_frac", "xin24m" };
+PNAME(mux_sclk_uart2_p)		= { "uart2_pre", "uart2_frac", "xin24m" };
+PNAME(mux_sclk_uart3_p)		= { "uart3_pre", "uart3_frac", "xin24m" };
+PNAME(mux_sclk_hsadc_p)		= { "hsadc_src", "hsadc_frac", "ext_hsadc" };
+PNAME(mux_mac_p)		= { "gpll", "dpll" };
+PNAME(mux_sclk_macref_p)	= { "mac_src", "ext_rmii" };
+
+static struct rockchip_pll_clock rk3188_pll_clks[] __initdata = {
+	[apll] = PLL(pll_rk3066, PLL_APLL, "apll", mux_pll_p, 0, RK2928_PLL_CON(0),
+		     RK2928_MODE_CON, 0, 6, rk3188_pll_rates),
+	[dpll] = PLL(pll_rk3066, PLL_DPLL, "dpll", mux_pll_p, 0, RK2928_PLL_CON(4),
+		     RK2928_MODE_CON, 4, 5, NULL),
+	[cpll] = PLL(pll_rk3066, PLL_CPLL, "cpll", mux_pll_p, 0, RK2928_PLL_CON(8),
+		     RK2928_MODE_CON, 8, 7, rk3188_pll_rates),
+	[gpll] = PLL(pll_rk3066, PLL_GPLL, "gpll", mux_pll_p, 0, RK2928_PLL_CON(12),
+		     RK2928_MODE_CON, 12, 8, rk3188_pll_rates),
+};
+
+#define MFLAGS CLK_MUX_HIWORD_MASK
+#define DFLAGS CLK_DIVIDER_HIWORD_MASK
+#define GFLAGS (CLK_GATE_HIWORD_MASK | CLK_GATE_SET_TO_DISABLE)
+
+/* 2 ^ (val + 1) */
+static struct clk_div_table div_core_peri_t[] = {
+	{ .val = 0, .div = 2 },
+	{ .val = 1, .div = 4 },
+	{ .val = 2, .div = 8 },
+	{ .val = 3, .div = 16 },
+	{ /* sentinel */ },
+};
+
+static struct rockchip_clk_branch common_clk_branches[] __initdata = {
+	/*
+	 * Clock-Architecture Diagram 2
+	 */
+
+	GATE(0, "gpll_armclk", "gpll", 0, RK2928_CLKGATE_CON(0), 1, GFLAGS),
+
+	/* these two are set by the cpuclk and should not be changed */
+	COMPOSITE_NOMUX_DIVTBL(CORE_PERI, "core_peri", "armclk", 0,
+			RK2928_CLKSEL_CON(0), 6, 2, DFLAGS | CLK_DIVIDER_READ_ONLY,
+			div_core_peri_t, RK2928_CLKGATE_CON(0), 0, GFLAGS),
+
+	COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(32), 7, 1, MFLAGS, 0, 5, DFLAGS,
+			RK2928_CLKGATE_CON(3), 9, GFLAGS),
+	GATE(0, "hclk_vepu", "aclk_vepu", 0,
+			RK2928_CLKGATE_CON(3), 10, GFLAGS),
+	COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(32), 15, 1, MFLAGS, 8, 5, DFLAGS,
+			RK2928_CLKGATE_CON(3), 11, GFLAGS),
+	GATE(0, "hclk_vdpu", "aclk_vdpu", 0,
+			RK2928_CLKGATE_CON(3), 12, GFLAGS),
+
+	GATE(0, "gpll_ddr", "gpll", 0,
+			RK2928_CLKGATE_CON(1), 7, GFLAGS),
+	COMPOSITE(0, "ddrphy", mux_ddrphy_p, 0,
+			RK2928_CLKSEL_CON(26), 8, 1, MFLAGS, 0, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
+			RK2928_CLKGATE_CON(0), 2, GFLAGS),
+
+	GATE(0, "aclk_cpu", "aclk_cpu_pre", 0,
+			RK2928_CLKGATE_CON(0), 3, GFLAGS),
+
+	DIV(0, "pclk_cpu_pre", "aclk_cpu_pre", 0,
+			RK2928_CLKSEL_CON(1), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO),
+	GATE(0, "atclk_cpu", "pclk_cpu_pre", 0,
+			RK2928_CLKGATE_CON(0), 6, GFLAGS),
+	GATE(0, "pclk_cpu", "pclk_cpu_pre", 0,
+			RK2928_CLKGATE_CON(0), 5, GFLAGS),
+	DIV(0, "hclk_cpu_pre", "aclk_cpu_pre", 0,
+			RK2928_CLKSEL_CON(1), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO),
+	COMPOSITE_NOMUX(0, "hclk_ahb2apb", "hclk_cpu_pre", 0,
+			RK2928_CLKSEL_CON(1), 14, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
+			RK2928_CLKGATE_CON(4), 9, GFLAGS),
+	GATE(0, "hclk_cpu", "hclk_cpu_pre", 0,
+			RK2928_CLKGATE_CON(0), 4, GFLAGS),
+
+	COMPOSITE(0, "aclk_lcdc0_pre", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(31), 7, 1, MFLAGS, 0, 5, DFLAGS,
+			RK2928_CLKGATE_CON(3), 0, GFLAGS),
+	COMPOSITE(0, "aclk_lcdc1_pre", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(31), 15, 1, MFLAGS, 8, 5, DFLAGS,
+			RK2928_CLKGATE_CON(1), 4, GFLAGS),
+
+	GATE(0, "aclk_peri", "aclk_peri_pre", 0,
+			RK2928_CLKGATE_CON(2), 1, GFLAGS),
+	COMPOSITE_NOMUX(0, "hclk_peri", "aclk_peri_pre", 0,
+			RK2928_CLKSEL_CON(10), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
+			RK2928_CLKGATE_CON(2), 2, GFLAGS),
+	COMPOSITE_NOMUX(0, "pclk_peri", "aclk_peri_pre", 0,
+			RK2928_CLKSEL_CON(10), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
+			RK2928_CLKGATE_CON(2), 3, GFLAGS),
+
+	MUX(0, "cif_src", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(29), 0, 1, MFLAGS),
+	COMPOSITE_NOMUX(0, "cif0_pre", "cif_src", 0,
+			RK2928_CLKSEL_CON(29), 1, 5, DFLAGS,
+			RK2928_CLKGATE_CON(3), 7, GFLAGS),
+	MUX(SCLK_CIF0, "sclk_cif0", mux_sclk_cif0_p, 0,
+			RK2928_CLKSEL_CON(29), 7, 1, MFLAGS),
+
+	GATE(0, "pclkin_cif0", "ext_cif0", 0,
+			RK2928_CLKGATE_CON(3), 3, GFLAGS),
+
+	/*
+	 * the 480m are generated inside the usb block from these clocks,
+	 * but they are also a source for the hsicphy clock.
+	 */
+	GATE(SCLK_OTGPHY0, "sclk_otgphy0", "usb480m", 0,
+			RK2928_CLKGATE_CON(1), 5, GFLAGS),
+	GATE(SCLK_OTGPHY1, "sclk_otgphy1", "usb480m", 0,
+			RK2928_CLKGATE_CON(1), 6, GFLAGS),
+
+	COMPOSITE(0, "mac_src", mux_mac_p, 0,
+			RK2928_CLKSEL_CON(21), 0, 1, MFLAGS, 8, 5, DFLAGS,
+			RK2928_CLKGATE_CON(2), 5, GFLAGS),
+	MUX(SCLK_MAC, "sclk_macref", mux_sclk_macref_p, CLK_SET_RATE_PARENT,
+			RK2928_CLKSEL_CON(21), 4, 1, MFLAGS),
+	GATE(0, "sclk_mac_lbtest", "sclk_macref",
+			RK2928_CLKGATE_CON(2), 12, 0, GFLAGS),
+
+	COMPOSITE(0, "hsadc_src", mux_pll_src_gpll_cpll_p, 0,
+			RK2928_CLKSEL_CON(22), 0, 1, MFLAGS, 8, 8, DFLAGS,
+			RK2928_CLKGATE_CON(2), 6, GFLAGS),
+	COMPOSITE_FRAC(0, "hsadc_frac", "hsadc_src",
+			RK2928_CLKSEL_CON(23), 0,
+			RK2928_CLKGATE_CON(2), 7, 0, GFLAGS),
+	MUX(SCLK_HSADC, "sclk_hsadc", mux_sclk_hsadc_p, 0,
+			RK2928_CLKSEL_CON(22), 4, 2, MFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_SARADC, "sclk_saradc", "xin24m", 0,
+			RK2928_CLKSEL_CON(24), 8, 8, DFLAGS,
+			RK2928_CLKGATE_CON(2), 8, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 4
+	 */
+
+	GATE(SCLK_SMC, "sclk_smc", "hclk_peri",
+			RK2928_CLKGATE_CON(2), 4, 0, GFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_SPI0, "sclk_spi0", "pclk_peri", 0,
+			RK2928_CLKSEL_CON(25), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(2), 9, GFLAGS),
+	COMPOSITE_NOMUX(SCLK_SPI1, "sclk_spi1", "pclk_peri", 0,
+			RK2928_CLKSEL_CON(25), 8, 7, DFLAGS,
+			RK2928_CLKGATE_CON(2), 10, GFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_SDMMC, "sclk_sdmmc", "hclk_peri", 0,
+			RK2928_CLKSEL_CON(11), 0, 6, DFLAGS,
+			RK2928_CLKGATE_CON(2), 11, GFLAGS),
+	COMPOSITE_NOMUX(SCLK_SDIO, "sclk_sdio", "hclk_peri", 0,
+			RK2928_CLKSEL_CON(12), 0, 6, DFLAGS,
+			RK2928_CLKGATE_CON(2), 13, GFLAGS),
+	COMPOSITE_NOMUX(SCLK_EMMC, "sclk_emmc", "hclk_peri", 0,
+			RK2928_CLKSEL_CON(12), 8, 6, DFLAGS,
+			RK2928_CLKGATE_CON(2), 14, GFLAGS),
+
+	MUX(0, "uart_src", mux_pll_src_gpll_cpll_p, 0,
+			RK2928_CLKSEL_CON(12), 15, 1, MFLAGS),
+	COMPOSITE_NOMUX(0, "uart0_pre", "uart_src", 0,
+			RK2928_CLKSEL_CON(13), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(1), 8, GFLAGS),
+	COMPOSITE_FRAC(0, "uart0_frac", "uart0_pre", 0,
+			RK2928_CLKSEL_CON(17), 0,
+			RK2928_CLKGATE_CON(1), 9, GFLAGS),
+	MUX(SCLK_UART0, "sclk_uart0", mux_sclk_uart0_p, 0,
+			RK2928_CLKSEL_CON(13), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "uart1_pre", "uart_src", 0,
+			RK2928_CLKSEL_CON(14), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(1), 10, GFLAGS),
+	COMPOSITE_FRAC(0, "uart1_frac", "uart1_pre", 0,
+			RK2928_CLKSEL_CON(18), 0,
+			RK2928_CLKGATE_CON(1), 11, GFLAGS),
+	MUX(SCLK_UART1, "sclk_uart1", mux_sclk_uart1_p, 0,
+			RK2928_CLKSEL_CON(14), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "uart2_pre", "uart_src", 0,
+			RK2928_CLKSEL_CON(15), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(1), 12, GFLAGS),
+	COMPOSITE_FRAC(0, "uart2_frac", "uart2_pre", 0,
+			RK2928_CLKSEL_CON(19), 0,
+			RK2928_CLKGATE_CON(1), 13, GFLAGS),
+	MUX(SCLK_UART2, "sclk_uart2", mux_sclk_uart2_p, 0,
+			RK2928_CLKSEL_CON(15), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "uart3_pre", "uart_src", 0,
+			RK2928_CLKSEL_CON(16), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(1), 14, GFLAGS),
+	COMPOSITE_FRAC(0, "uart3_frac", "uart3_pre", 0,
+			RK2928_CLKSEL_CON(20), 0,
+			RK2928_CLKGATE_CON(1), 15, GFLAGS),
+	MUX(SCLK_UART3, "sclk_uart3", mux_sclk_uart3_p, 0,
+			RK2928_CLKSEL_CON(16), 8, 2, MFLAGS),
+
+	GATE(SCLK_JTAG, "jtag", "ext_jtag", 0, RK2928_CLKGATE_CON(1), 3, GFLAGS),
+
+	GATE(SCLK_TIMER0, "timer0", "xin24m", 0, RK2928_CLKGATE_CON(1), 0, GFLAGS),
+	GATE(SCLK_TIMER1, "timer1", "xin24m", 0, RK2928_CLKGATE_CON(1), 1, GFLAGS),
+
+	/* clk_core_pre gates */
+	GATE(0, "core_dbg", "armclk", 0, RK2928_CLKGATE_CON(9), 0, GFLAGS),
+
+	/* aclk_cpu gates */
+	GATE(ACLK_DMA1, "aclk_dma1", "aclk_cpu", 0, RK2928_CLKGATE_CON(5), 0, GFLAGS),
+	GATE(0, "aclk_intmem", "aclk_cpu", 0, RK2928_CLKGATE_CON(4), 12, GFLAGS),
+	GATE(0, "aclk_strc_sys", "aclk_cpu", 0, RK2928_CLKGATE_CON(4), 10, GFLAGS),
+
+	/* hclk_cpu gates */
+	GATE(HCLK_ROM, "hclk_rom", "hclk_cpu", 0, RK2928_CLKGATE_CON(5), 6, GFLAGS),
+	GATE(HCLK_I2S0, "hclk_i2s0", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 2, GFLAGS),
+	GATE(HCLK_SPDIF, "hclk_spdif", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 1, GFLAGS),
+	GATE(0, "hclk_cpubus", "hclk_cpu", 0, RK2928_CLKGATE_CON(4), 8, GFLAGS),
+	/* hclk_ahb2apb is part of a clk branch */
+	GATE(0, "hclk_vio_bus", "hclk_cpu", 0, RK2928_CLKGATE_CON(6), 12, GFLAGS),
+	GATE(HCLK_LCDC0, "hclk_lcdc0", "hclk_cpu", 0, RK2928_CLKGATE_CON(6), 1, GFLAGS),
+	GATE(HCLK_LCDC1, "hclk_lcdc1", "aclk_cpu", 0, RK2928_CLKGATE_CON(6), 2, GFLAGS),
+	GATE(HCLK_CIF0, "hclk_cif0", "hclk_cpu", 0, RK2928_CLKGATE_CON(6), 4, GFLAGS),
+	GATE(HCLK_IPP, "hclk_ipp", "hclk_cpu", 0, RK2928_CLKGATE_CON(6), 9, GFLAGS),
+	GATE(HCLK_RGA, "hclk_rga", "hclk_cpu", 0, RK2928_CLKGATE_CON(6), 10, GFLAGS),
+
+	/* hclk_peri gates */
+	GATE(0, "hclk_peri_axi_matrix", "hclk_peri", 0, RK2928_CLKGATE_CON(4), 0, GFLAGS),
+	GATE(0, "hclk_peri_ahb_arbi", "hclk_peri", 0, RK2928_CLKGATE_CON(4), 6, GFLAGS),
+	GATE(0, "hclk_emem_peri", "hclk_peri", 0, RK2928_CLKGATE_CON(4), 7, GFLAGS),
+	GATE(HCLK_EMAC, "hclk_emac", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 0, GFLAGS),
+	GATE(HCLK_NANDC0, "hclk_nandc0", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 9, GFLAGS),
+	GATE(0, "hclk_usb_peri", "hclk_peri", 0, RK2928_CLKGATE_CON(4), 5, GFLAGS),
+	GATE(HCLK_OTG0, "hclk_usbotg0", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 13, GFLAGS),
+	GATE(HCLK_HSADC, "hclk_hsadc", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 5, GFLAGS),
+	GATE(HCLK_PIDF, "hclk_pidfilter", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 6, GFLAGS),
+	GATE(HCLK_SDMMC, "hclk_sdmmc", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 10, GFLAGS),
+	GATE(HCLK_SDIO, "hclk_sdio", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 11, GFLAGS),
+	GATE(HCLK_EMMC, "hclk_emmc", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 12, GFLAGS),
+
+	/* aclk_lcdc0_pre gates */
+	GATE(0, "aclk_vio0", "aclk_lcdc0_pre", 0, RK2928_CLKGATE_CON(6), 13, GFLAGS),
+	GATE(ACLK_LCDC0, "aclk_lcdc0", "aclk_vio0", 0, RK2928_CLKGATE_CON(6), 0, GFLAGS),
+	GATE(ACLK_CIF0, "aclk_cif0", "aclk_vio0", 0, RK2928_CLKGATE_CON(6), 5, GFLAGS),
+	GATE(ACLK_IPP, "aclk_ipp", "aclk_vio0", 0, RK2928_CLKGATE_CON(6), 8, GFLAGS),
+
+	/* aclk_lcdc1_pre gates */
+	GATE(0, "aclk_vio1", "aclk_lcdc1_pre", 0, RK2928_CLKGATE_CON(9), 5, GFLAGS),
+	GATE(ACLK_LCDC1, "aclk_lcdc1", "aclk_vio1", 0, RK2928_CLKGATE_CON(6), 3, GFLAGS),
+	GATE(ACLK_RGA, "aclk_rga", "aclk_vio1", 0, RK2928_CLKGATE_CON(6), 11, GFLAGS),
+
+	/* atclk_cpu gates */
+	GATE(0, "atclk", "atclk_cpu", 0, RK2928_CLKGATE_CON(9), 3, GFLAGS),
+	GATE(0, "trace", "atclk_cpu", 0, RK2928_CLKGATE_CON(9), 2, GFLAGS),
+
+	/* pclk_cpu gates */
+	GATE(PCLK_PWM01, "pclk_pwm01", "pclk_cpu", 0, RK2928_CLKGATE_CON(7), 10, GFLAGS),
+	GATE(PCLK_TIMER0, "pclk_timer0", "pclk_cpu", 0, RK2928_CLKGATE_CON(7), 7, GFLAGS),
+	GATE(PCLK_I2C0, "pclk_i2c0", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 4, GFLAGS),
+	GATE(PCLK_I2C1, "pclk_i2c1", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 5, GFLAGS),
+	GATE(PCLK_GPIO0, "pclk_gpio0", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 9, GFLAGS),
+	GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 10, GFLAGS),
+	GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 11, GFLAGS),
+	GATE(PCLK_EFUSE, "pclk_efuse", "pclk_cpu", 0, RK2928_CLKGATE_CON(5), 2, GFLAGS),
+	GATE(PCLK_TZPC, "pclk_tzpc", "pclk_cpu", 0, RK2928_CLKGATE_CON(5), 3, GFLAGS),
+	GATE(0, "pclk_ddrupctl", "pclk_cpu", 0, RK2928_CLKGATE_CON(5), 7, GFLAGS),
+	GATE(0, "pclk_ddrpubl", "pclk_cpu", 0, RK2928_CLKGATE_CON(9), 6, GFLAGS),
+	GATE(0, "pclk_dbg", "pclk_cpu", 0, RK2928_CLKGATE_CON(9), 1, GFLAGS),
+	GATE(PCLK_GRF, "pclk_grf", "pclk_cpu", 0, RK2928_CLKGATE_CON(5), 4, GFLAGS),
+	GATE(PCLK_PMU, "pclk_pmu", "pclk_cpu", 0, RK2928_CLKGATE_CON(5), 5, GFLAGS),
+
+	/* aclk_peri */
+	GATE(ACLK_DMA2, "aclk_dma2", "aclk_peri", 0, RK2928_CLKGATE_CON(5), 1, GFLAGS),
+	GATE(ACLK_SMC, "aclk_smc", "aclk_peri", 0, RK2928_CLKGATE_CON(5), 8, GFLAGS),
+	GATE(0, "aclk_peri_niu", "aclk_peri", 0, RK2928_CLKGATE_CON(4), 4, GFLAGS),
+	GATE(0, "aclk_cpu_peri", "aclk_peri", 0, RK2928_CLKGATE_CON(4), 2, GFLAGS),
+	GATE(0, "aclk_peri_axi_matrix", "aclk_peri", 0, RK2928_CLKGATE_CON(4), 3, GFLAGS),
+
+	/* pclk_peri gates */
+	GATE(0, "pclk_peri_axi_matrix", "pclk_peri", 0, RK2928_CLKGATE_CON(4), 1, GFLAGS),
+	GATE(PCLK_PWM23, "pclk_pwm23", "pclk_peri", 0, RK2928_CLKGATE_CON(7), 11, GFLAGS),
+	GATE(PCLK_WDT, "pclk_wdt", "pclk_peri", 0, RK2928_CLKGATE_CON(7), 15, GFLAGS),
+	GATE(PCLK_SPI0, "pclk_spi0", "pclk_peri", 0, RK2928_CLKGATE_CON(7), 12, GFLAGS),
+	GATE(PCLK_SPI1, "pclk_spi1", "pclk_peri", 0, RK2928_CLKGATE_CON(7), 13, GFLAGS),
+	GATE(PCLK_UART2, "pclk_uart2", "pclk_peri", 0, RK2928_CLKGATE_CON(8), 2, GFLAGS),
+	GATE(PCLK_UART3, "pclk_uart3", "pclk_peri", 0, RK2928_CLKGATE_CON(8), 3, GFLAGS),
+	GATE(PCLK_I2C2, "pclk_i2c2", "pclk_peri", 0, RK2928_CLKGATE_CON(8), 6, GFLAGS),
+	GATE(PCLK_I2C3, "pclk_i2c3", "pclk_peri", 0, RK2928_CLKGATE_CON(8), 7, GFLAGS),
+	GATE(PCLK_I2C4, "pclk_i2c4", "pclk_peri", 0, RK2928_CLKGATE_CON(8), 8, GFLAGS),
+	GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_peri", 0, RK2928_CLKGATE_CON(8), 12, GFLAGS),
+	GATE(PCLK_SARADC, "pclk_saradc", "pclk_peri", 0, RK2928_CLKGATE_CON(7), 14, GFLAGS),
+};
+
+PNAME(mux_rk3066_lcdc0_p)	= { "dclk_lcdc0_src", "xin27m" };
+PNAME(mux_rk3066_lcdc1_p)	= { "dclk_lcdc1_src", "xin27m" };
+PNAME(mux_sclk_cif1_p)		= { "cif1_pre", "xin24m" };
+PNAME(mux_sclk_i2s1_p)		= { "i2s1_pre", "i2s1_frac", "xin12m" };
+PNAME(mux_sclk_i2s2_p)		= { "i2s2_pre", "i2s2_frac", "xin12m" };
+
+static struct clk_div_table div_aclk_cpu_t[] = {
+	{ .val = 0, .div = 1 },
+	{ .val = 1, .div = 2 },
+	{ .val = 2, .div = 3 },
+	{ .val = 3, .div = 4 },
+	{ .val = 4, .div = 8 },
+	{ /* sentinel */ },
+};
+
+static struct rockchip_clk_branch rk3066a_clk_branches[] __initdata = {
+	COMPOSITE_NOGATE(0, "armclk", mux_armclk_p, 0,
+			RK2928_CLKSEL_CON(0), 8, 1, MFLAGS, 0, 5, DFLAGS),
+	DIVTBL(0, "aclk_cpu_pre", "armclk", 0,
+			RK2928_CLKSEL_CON(1), 0, 3, DFLAGS, div_aclk_cpu_t),
+
+	GATE(CORE_L2C, "core_l2c", "aclk_cpu", 0,
+			RK2928_CLKGATE_CON(9), 4, GFLAGS),
+
+	COMPOSITE(0, "aclk_peri_pre", mux_pll_src_gpll_cpll_p, 0,
+			RK2928_CLKSEL_CON(10), 15, 1, MFLAGS, 0, 5, DFLAGS,
+			RK2928_CLKGATE_CON(2), 0, GFLAGS),
+
+	COMPOSITE(0, "dclk_lcdc0_src", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(27), 0, 1, MFLAGS, 8, 8, DFLAGS,
+			RK2928_CLKGATE_CON(3), 1, GFLAGS),
+	MUX(DCLK_LCDC0, "dclk_lcdc0", mux_rk3066_lcdc0_p, 0,
+			RK2928_CLKSEL_CON(27), 4, 1, MFLAGS),
+	COMPOSITE(0, "dclk_lcdc1_src", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(28), 0, 1, MFLAGS, 8, 8, DFLAGS,
+			RK2928_CLKGATE_CON(3), 2, GFLAGS),
+	MUX(DCLK_LCDC1, "dclk_lcdc1", mux_rk3066_lcdc1_p, 0,
+			RK2928_CLKSEL_CON(28), 4, 1, MFLAGS),
+
+	COMPOSITE_NOMUX(0, "cif1_pre", "cif_src", 0,
+			RK2928_CLKSEL_CON(29), 8, 5, DFLAGS,
+			RK2928_CLKGATE_CON(3), 8, GFLAGS),
+	MUX(SCLK_CIF1, "sclk_cif1", mux_sclk_cif1_p, 0,
+			RK2928_CLKSEL_CON(29), 15, 1, MFLAGS),
+
+	GATE(0, "pclkin_cif1", "ext_cif1", 0,
+			RK2928_CLKGATE_CON(3), 4, GFLAGS),
+
+	COMPOSITE(0, "aclk_gpu_src", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(33), 8, 1, MFLAGS, 0, 5, DFLAGS,
+			RK2928_CLKGATE_CON(3), 13, GFLAGS),
+	GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_src", 0,
+			RK2928_CLKGATE_CON(5), 15, GFLAGS),
+
+	GATE(SCLK_TIMER2, "timer2", "xin24m", 0,
+			RK2928_CLKGATE_CON(3), 2, GFLAGS),
+
+	COMPOSITE_NOMUX(0, "sclk_tsadc", "xin24m", 0,
+			RK2928_CLKSEL_CON(34), 0, 16, DFLAGS,
+			RK2928_CLKGATE_CON(2), 15, GFLAGS),
+
+	MUX(0, "i2s_src", mux_pll_src_gpll_cpll_p, 0,
+			RK2928_CLKSEL_CON(2), 15, 1, MFLAGS),
+	COMPOSITE_NOMUX(0, "i2s0_pre", "i2s_src", 0,
+			RK2928_CLKSEL_CON(2), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(0), 7, GFLAGS),
+	COMPOSITE_FRAC(0, "i2s0_frac", "i2s0_pre", 0,
+			RK2928_CLKSEL_CON(6), 0,
+			RK2928_CLKGATE_CON(0), 8, GFLAGS),
+	MUX(SCLK_I2S0, "sclk_i2s0", mux_sclk_i2s0_p, 0,
+			RK2928_CLKSEL_CON(2), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "i2s1_pre", "i2s_src", 0,
+			RK2928_CLKSEL_CON(3), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(0), 9, GFLAGS),
+	COMPOSITE_FRAC(0, "i2s1_frac", "i2s1_pre", 0,
+			RK2928_CLKSEL_CON(7), 0,
+			RK2928_CLKGATE_CON(0), 10, GFLAGS),
+	MUX(SCLK_I2S1, "sclk_i2s1", mux_sclk_i2s1_p, 0,
+			RK2928_CLKSEL_CON(3), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "i2s2_pre", "i2s_src", 0,
+			RK2928_CLKSEL_CON(4), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(0), 11, GFLAGS),
+	COMPOSITE_FRAC(0, "i2s2_frac", "i2s2_pre", 0,
+			RK2928_CLKSEL_CON(8), 0,
+			RK2928_CLKGATE_CON(0), 12, GFLAGS),
+	MUX(SCLK_I2S2, "sclk_i2s2", mux_sclk_i2s2_p, 0,
+			RK2928_CLKSEL_CON(4), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "spdif_pre", "i2s_src", 0,
+			RK2928_CLKSEL_CON(5), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(0), 13, GFLAGS),
+	COMPOSITE_FRAC(0, "spdif_frac", "spdif_pll", 0,
+			RK2928_CLKSEL_CON(9), 0,
+			RK2928_CLKGATE_CON(0), 14, GFLAGS),
+	MUX(SCLK_SPDIF, "sclk_spdif", mux_sclk_spdif_p, 0,
+			RK2928_CLKSEL_CON(5), 8, 2, MFLAGS),
+
+	GATE(HCLK_I2S1, "hclk_i2s1", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS),
+	GATE(HCLK_I2S2, "hclk_i2s2", "hclk_cpu", 0, RK2928_CLKGATE_CON(7), 4, GFLAGS),
+	GATE(0, "hclk_cif1", "hclk_cpu", 0, RK2928_CLKGATE_CON(6), 6, GFLAGS),
+	GATE(0, "hclk_hdmi", "hclk_cpu", 0, RK2928_CLKGATE_CON(4), 14, GFLAGS),
+
+	GATE(HCLK_OTG1, "hclk_usbotg1", "hclk_peri", 0, RK2928_CLKGATE_CON(5), 14, GFLAGS),
+
+	GATE(0, "aclk_cif1", "aclk_vio1", 0, RK2928_CLKGATE_CON(6), 7, GFLAGS),
+
+	GATE(PCLK_TIMER1, "pclk_timer1", "pclk_cpu", 0, RK2928_CLKGATE_CON(7), 8, GFLAGS),
+	GATE(PCLK_TIMER2, "pclk_timer2", "pclk_cpu", 0, RK2928_CLKGATE_CON(7), 9, GFLAGS),
+	GATE(PCLK_GPIO6, "pclk_gpio6", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 15, GFLAGS),
+	GATE(PCLK_UART0, "pclk_uart0", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 0, GFLAGS),
+	GATE(PCLK_UART1, "pclk_uart1", "pclk_cpu", 0, RK2928_CLKGATE_CON(8), 1, GFLAGS),
+
+	GATE(PCLK_GPIO4, "pclk_gpio4", "pclk_peri", 0, RK2928_CLKGATE_CON(8), 13, GFLAGS),
+	GATE(PCLK_TSADC, "pclk_tsadc", "pclk_peri", 0, RK2928_CLKGATE_CON(4), 13, GFLAGS),
+};
+
+static struct clk_div_table div_rk3188_aclk_core_t[] = {
+	{ .val = 0, .div = 1 },
+	{ .val = 1, .div = 2 },
+	{ .val = 2, .div = 3 },
+	{ .val = 3, .div = 4 },
+	{ .val = 4, .div = 8 },
+	{ /* sentinel */ },
+};
+
+PNAME(mux_hsicphy_p)		= { "sclk_otgphy0", "sclk_otgphy1",
+				    "gpll", "cpll" };
+
+static struct rockchip_clk_branch rk3188_clk_branches[] __initdata = {
+	COMPOSITE_NOGATE(0, "armclk", mux_armclk_p, 0,
+			RK2928_CLKSEL_CON(0), 8, 1, MFLAGS, 9, 5, DFLAGS),
+	COMPOSITE_NOMUX_DIVTBL(0, "aclk_core", "armclk", 0,
+			RK2928_CLKSEL_CON(1), 3, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
+			div_rk3188_aclk_core_t, RK2928_CLKGATE_CON(0), 7, GFLAGS),
+
+	/* do not source aclk_cpu_pre from the apll, to keep complexity down */
+	COMPOSITE_NOGATE(0, "aclk_cpu_pre", mux_aclk_cpu_p, CLK_SET_RATE_NO_REPARENT,
+			RK2928_CLKSEL_CON(0), 5, 1, MFLAGS, 0, 5, DFLAGS),
+
+	GATE(CORE_L2C, "core_l2c", "armclk", 0,
+			RK2928_CLKGATE_CON(9), 4, GFLAGS),
+
+	COMPOSITE(0, "aclk_peri_pre", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(10), 15, 1, MFLAGS, 0, 5, DFLAGS,
+			RK2928_CLKGATE_CON(2), 0, GFLAGS),
+
+	COMPOSITE(DCLK_LCDC0, "dclk_lcdc0", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(27), 0, 1, MFLAGS, 8, 8, DFLAGS,
+			RK2928_CLKGATE_CON(3), 1, GFLAGS),
+	COMPOSITE(DCLK_LCDC1, "dclk_lcdc1", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(28), 0, 1, MFLAGS, 8, 8, DFLAGS,
+			RK2928_CLKGATE_CON(3), 2, GFLAGS),
+
+	COMPOSITE(0, "aclk_gpu_src", mux_pll_src_cpll_gpll_p, 0,
+			RK2928_CLKSEL_CON(34), 7, 1, MFLAGS, 0, 5, DFLAGS,
+			RK2928_CLKGATE_CON(3), 15, GFLAGS),
+	GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_src", 0,
+			RK2928_CLKGATE_CON(9), 7, GFLAGS),
+
+	GATE(SCLK_TIMER2, "timer2", "xin24m", 0, RK2928_CLKGATE_CON(3), 4, GFLAGS),
+	GATE(SCLK_TIMER3, "timer3", "xin24m", 0, RK2928_CLKGATE_CON(1), 2, GFLAGS),
+	GATE(SCLK_TIMER4, "timer4", "xin24m", 0, RK2928_CLKGATE_CON(3), 5, GFLAGS),
+	GATE(SCLK_TIMER5, "timer5", "xin24m", 0, RK2928_CLKGATE_CON(3), 8, GFLAGS),
+	GATE(SCLK_TIMER6, "timer6", "xin24m", 0, RK2928_CLKGATE_CON(3), 14, GFLAGS),
+
+	COMPOSITE_NODIV(0, "sclk_hsicphy_480m", mux_hsicphy_p, 0,
+			RK2928_CLKSEL_CON(30), 0, 2, DFLAGS,
+			RK2928_CLKGATE_CON(3), 6, GFLAGS),
+	DIV(0, "sclk_hsicphy_12m", "sclk_hsicphy_480m", 0,
+			RK2928_CLKGATE_CON(11), 8, 6, DFLAGS),
+
+	MUX(0, "i2s_src", mux_pll_src_gpll_cpll_p, 0,
+			RK2928_CLKSEL_CON(2), 15, 1, MFLAGS),
+	COMPOSITE_NOMUX(0, "i2s0_pre", "i2s_src", 0,
+			RK2928_CLKSEL_CON(3), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(0), 9, GFLAGS),
+	COMPOSITE_FRAC(0, "i2s0_frac", "i2s0_pre", 0,
+			RK2928_CLKSEL_CON(7), 0,
+			RK2928_CLKGATE_CON(0), 10, GFLAGS),
+	MUX(SCLK_I2S0, "sclk_i2s0", mux_sclk_i2s0_p, 0,
+			RK2928_CLKSEL_CON(3), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "spdif_pre", "i2s_src", 0,
+			RK2928_CLKSEL_CON(5), 0, 7, DFLAGS,
+			RK2928_CLKGATE_CON(13), 13, GFLAGS),
+	COMPOSITE_FRAC(0, "spdif_frac", "spdif_pll", 0,
+			RK2928_CLKSEL_CON(9), 0,
+			RK2928_CLKGATE_CON(0), 14, GFLAGS),
+	MUX(SCLK_SPDIF, "sclk_spdif", mux_sclk_spdif_p, 0,
+			RK2928_CLKSEL_CON(5), 8, 2, MFLAGS),
+
+	GATE(0, "hclk_imem0", "hclk_cpu", 0, RK2928_CLKGATE_CON(4), 14, GFLAGS),
+	GATE(0, "hclk_imem1", "hclk_cpu", 0, RK2928_CLKGATE_CON(4), 15, GFLAGS),
+
+	GATE(HCLK_OTG1, "hclk_usbotg1", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 3, GFLAGS),
+	GATE(HCLK_HSIC, "hclk_hsic", "hclk_peri", 0, RK2928_CLKGATE_CON(7), 4, GFLAGS),
+
+	GATE(PCLK_TIMER3, "pclk_timer3", "pclk_cpu", 0, RK2928_CLKGATE_CON(7), 9, GFLAGS),
+
+	GATE(PCLK_UART0, "pclk_uart0", "hclk_ahb2apb", 0, RK2928_CLKGATE_CON(8), 0, GFLAGS),
+	GATE(PCLK_UART1, "pclk_uart1", "hclk_ahb2apb", 0, RK2928_CLKGATE_CON(8), 1, GFLAGS),
+
+	GATE(ACLK_GPS, "aclk_gps", "aclk_peri", 0, RK2928_CLKGATE_CON(8), 13, GFLAGS),
+};
+
+static void __init rk3188_common_clk_init(struct device_node *np)
+{
+	void __iomem *reg_base;
+	struct clk *clk;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		pr_err("%s: could not map cru region\n", __func__);
+		return;
+	}
+
+	rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
+
+	/* xin12m is created by an cru-internal divider */
+	clk = clk_register_fixed_factor(NULL, "xin12m", "xin24m", 0, 1, 2);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock xin12m: %ld\n",
+			__func__, PTR_ERR(clk));
+
+	clk = clk_register_fixed_factor(NULL, "usb480m", "xin24m", 0, 20, 1);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock usb480m: %ld\n",
+			__func__, PTR_ERR(clk));
+
+	rockchip_clk_register_plls(rk3188_pll_clks,
+				   ARRAY_SIZE(rk3188_pll_clks),
+				   RK3188_GRF_SOC_STATUS);
+	rockchip_clk_register_branches(common_clk_branches,
+				  ARRAY_SIZE(common_clk_branches));
+
+	rockchip_register_softrst(np, 9, reg_base + RK2928_SOFTRST_CON(0),
+				  ROCKCHIP_SOFTRST_HIWORD_MASK);
+}
+
+static void __init rk3066a_clk_init(struct device_node *np)
+{
+	rk3188_common_clk_init(np);
+	rockchip_clk_register_branches(rk3066a_clk_branches,
+				  ARRAY_SIZE(rk3066a_clk_branches));
+}
+CLK_OF_DECLARE(rk3066a_cru, "rockchip,rk3066a-cru", rk3066a_clk_init);
+
+static void __init rk3188a_clk_init(struct device_node *np)
+{
+	rk3188_common_clk_init(np);
+	rockchip_clk_register_branches(rk3188_clk_branches,
+				  ARRAY_SIZE(rk3188_clk_branches));
+}
+CLK_OF_DECLARE(rk3188a_cru, "rockchip,rk3188a-cru", rk3188a_clk_init);
+
+static void __init rk3188_clk_init(struct device_node *np)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(rk3188_pll_clks); i++) {
+		struct rockchip_pll_clock *pll = &rk3188_pll_clks[i];
+		struct rockchip_pll_rate_table *rate;
+
+		if (!pll->rate_table)
+			continue;
+
+		rate = pll->rate_table;
+		while (rate->rate > 0) {
+			rate->bwadj = 0;
+			rate++;
+		}
+	}
+
+	rk3188a_clk_init(np);
+}
+CLK_OF_DECLARE(rk3188_cru, "rockchip,rk3188-cru", rk3188_clk_init);
diff --git a/drivers/clk/rockchip/clk-rk3288.c b/drivers/clk/rockchip/clk-rk3288.c
new file mode 100644
index 00000000000..0d8c6c59a75
--- /dev/null
+++ b/drivers/clk/rockchip/clk-rk3288.c
@@ -0,0 +1,717 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <dt-bindings/clock/rk3288-cru.h>
+#include "clk.h"
+
+#define RK3288_GRF_SOC_CON(x)	(0x244 + x * 4)
+#define RK3288_GRF_SOC_STATUS	0x280
+
+enum rk3288_plls {
+	apll, dpll, cpll, gpll, npll,
+};
+
+struct rockchip_pll_rate_table rk3288_pll_rates[] = {
+	RK3066_PLL_RATE(2208000000, 1, 92, 1),
+	RK3066_PLL_RATE(2184000000, 1, 91, 1),
+	RK3066_PLL_RATE(2160000000, 1, 90, 1),
+	RK3066_PLL_RATE(2136000000, 1, 89, 1),
+	RK3066_PLL_RATE(2112000000, 1, 88, 1),
+	RK3066_PLL_RATE(2088000000, 1, 87, 1),
+	RK3066_PLL_RATE(2064000000, 1, 86, 1),
+	RK3066_PLL_RATE(2040000000, 1, 85, 1),
+	RK3066_PLL_RATE(2016000000, 1, 84, 1),
+	RK3066_PLL_RATE(1992000000, 1, 83, 1),
+	RK3066_PLL_RATE(1968000000, 1, 82, 1),
+	RK3066_PLL_RATE(1944000000, 1, 81, 1),
+	RK3066_PLL_RATE(1920000000, 1, 80, 1),
+	RK3066_PLL_RATE(1896000000, 1, 79, 1),
+	RK3066_PLL_RATE(1872000000, 1, 78, 1),
+	RK3066_PLL_RATE(1848000000, 1, 77, 1),
+	RK3066_PLL_RATE(1824000000, 1, 76, 1),
+	RK3066_PLL_RATE(1800000000, 1, 75, 1),
+	RK3066_PLL_RATE(1776000000, 1, 74, 1),
+	RK3066_PLL_RATE(1752000000, 1, 73, 1),
+	RK3066_PLL_RATE(1728000000, 1, 72, 1),
+	RK3066_PLL_RATE(1704000000, 1, 71, 1),
+	RK3066_PLL_RATE(1680000000, 1, 70, 1),
+	RK3066_PLL_RATE(1656000000, 1, 69, 1),
+	RK3066_PLL_RATE(1632000000, 1, 68, 1),
+	RK3066_PLL_RATE(1608000000, 1, 67, 1),
+	RK3066_PLL_RATE(1560000000, 1, 65, 1),
+	RK3066_PLL_RATE(1512000000, 1, 63, 1),
+	RK3066_PLL_RATE(1488000000, 1, 62, 1),
+	RK3066_PLL_RATE(1464000000, 1, 61, 1),
+	RK3066_PLL_RATE(1440000000, 1, 60, 1),
+	RK3066_PLL_RATE(1416000000, 1, 59, 1),
+	RK3066_PLL_RATE(1392000000, 1, 58, 1),
+	RK3066_PLL_RATE(1368000000, 1, 57, 1),
+	RK3066_PLL_RATE(1344000000, 1, 56, 1),
+	RK3066_PLL_RATE(1320000000, 1, 55, 1),
+	RK3066_PLL_RATE(1296000000, 1, 54, 1),
+	RK3066_PLL_RATE(1272000000, 1, 53, 1),
+	RK3066_PLL_RATE(1248000000, 1, 52, 1),
+	RK3066_PLL_RATE(1224000000, 1, 51, 1),
+	RK3066_PLL_RATE(1200000000, 1, 50, 1),
+	RK3066_PLL_RATE(1188000000, 2, 99, 1),
+	RK3066_PLL_RATE(1176000000, 1, 49, 1),
+	RK3066_PLL_RATE(1128000000, 1, 47, 1),
+	RK3066_PLL_RATE(1104000000, 1, 46, 1),
+	RK3066_PLL_RATE(1008000000, 1, 84, 2),
+	RK3066_PLL_RATE( 912000000, 1, 76, 2),
+	RK3066_PLL_RATE( 891000000, 8, 594, 2),
+	RK3066_PLL_RATE( 888000000, 1, 74, 2),
+	RK3066_PLL_RATE( 816000000, 1, 68, 2),
+	RK3066_PLL_RATE( 798000000, 2, 133, 2),
+	RK3066_PLL_RATE( 792000000, 1, 66, 2),
+	RK3066_PLL_RATE( 768000000, 1, 64, 2),
+	RK3066_PLL_RATE( 742500000, 8, 495, 2),
+	RK3066_PLL_RATE( 696000000, 1, 58, 2),
+	RK3066_PLL_RATE( 600000000, 1, 50, 2),
+	RK3066_PLL_RATE( 594000000, 2, 198, 4),
+	RK3066_PLL_RATE( 552000000, 1, 46, 2),
+	RK3066_PLL_RATE( 504000000, 1, 84, 4),
+	RK3066_PLL_RATE( 456000000, 1, 76, 4),
+	RK3066_PLL_RATE( 408000000, 1, 68, 4),
+	RK3066_PLL_RATE( 384000000, 2, 128, 4),
+	RK3066_PLL_RATE( 360000000, 1, 60, 4),
+	RK3066_PLL_RATE( 312000000, 1, 52, 4),
+	RK3066_PLL_RATE( 300000000, 1, 50, 4),
+	RK3066_PLL_RATE( 297000000, 2, 198, 8),
+	RK3066_PLL_RATE( 252000000, 1, 84, 8),
+	RK3066_PLL_RATE( 216000000, 1, 72, 8),
+	RK3066_PLL_RATE( 148500000, 2, 99, 8),
+	RK3066_PLL_RATE( 126000000, 1, 84, 16),
+	RK3066_PLL_RATE(  48000000, 1, 64, 32),
+	{ /* sentinel */ },
+};
+
+PNAME(mux_pll_p)		= { "xin24m", "xin32k" };
+PNAME(mux_armclk_p)		= { "apll_core", "gpll_core" };
+PNAME(mux_ddrphy_p)		= { "dpll_ddr", "gpll_ddr" };
+PNAME(mux_aclk_cpu_src_p)	= { "cpll_aclk_cpu", "gpll_aclk_cpu" };
+
+PNAME(mux_pll_src_cpll_gpll_p)		= { "cpll", "gpll" };
+PNAME(mux_pll_src_npll_cpll_gpll_p)	= { "npll", "cpll", "gpll" };
+PNAME(mux_pll_src_cpll_gpll_npll_p)	= { "cpll", "gpll", "npll" };
+PNAME(mux_pll_src_cpll_gpll_usb480m_p)	= { "cpll", "gpll", "usb480m" };
+
+PNAME(mux_mmc_src_p)	= { "cpll", "gpll", "xin24m", "xin24m" };
+PNAME(mux_i2s_pre_p)	= { "i2s_src", "i2s_frac", "ext_i2s", "xin12m" };
+PNAME(mux_i2s_clkout_p)	= { "i2s_pre", "xin12m" };
+PNAME(mux_spdif_p)	= { "spdif_pre", "spdif_frac", "xin12m" };
+PNAME(mux_spdif_8ch_p)	= { "spdif_8ch_pre", "spdif_8ch_frac", "xin12m" };
+PNAME(mux_uart0_pll_p)	= { "cpll", "gpll", "usbphy_480m_src", "npll" };
+PNAME(mux_uart0_p)	= { "uart0_src", "uart0_frac", "xin24m" };
+PNAME(mux_uart1_p)	= { "uart1_src", "uart1_frac", "xin24m" };
+PNAME(mux_uart2_p)	= { "uart2_src", "uart2_frac", "xin24m" };
+PNAME(mux_uart3_p)	= { "uart3_src", "uart3_frac", "xin24m" };
+PNAME(mux_uart4_p)	= { "uart4_src", "uart4_frac", "xin24m" };
+PNAME(mux_cif_out_p)	= { "cif_src", "xin24m" };
+PNAME(mux_macref_p)	= { "mac_src", "ext_gmac" };
+PNAME(mux_hsadcout_p)	= { "hsadc_src", "ext_hsadc" };
+PNAME(mux_edp_24m_p)	= { "ext_edp_24m", "xin24m" };
+PNAME(mux_tspout_p)	= { "cpll", "gpll", "npll", "xin27m" };
+
+PNAME(mux_usbphy480m_p)		= { "sclk_otgphy0", "sclk_otgphy1",
+				    "sclk_otgphy2" };
+PNAME(mux_hsicphy480m_p)	= { "cpll", "gpll", "usbphy480m_src" };
+PNAME(mux_hsicphy12m_p)		= { "hsicphy12m_xin12m", "hsicphy12m_usbphy" };
+
+static struct rockchip_pll_clock rk3288_pll_clks[] __initdata = {
+	[apll] = PLL(pll_rk3066, PLL_APLL, "apll", mux_pll_p, 0, RK3288_PLL_CON(0),
+		     RK3288_MODE_CON, 0, 6, rk3288_pll_rates),
+	[dpll] = PLL(pll_rk3066, PLL_DPLL, "dpll", mux_pll_p, 0, RK3288_PLL_CON(4),
+		     RK3288_MODE_CON, 4, 5, NULL),
+	[cpll] = PLL(pll_rk3066, PLL_CPLL, "cpll", mux_pll_p, 0, RK3288_PLL_CON(8),
+		     RK3288_MODE_CON, 8, 7, rk3288_pll_rates),
+	[gpll] = PLL(pll_rk3066, PLL_GPLL, "gpll", mux_pll_p, 0, RK3288_PLL_CON(12),
+		     RK3288_MODE_CON, 12, 8, rk3288_pll_rates),
+	[npll] = PLL(pll_rk3066, PLL_NPLL, "npll",  mux_pll_p, 0, RK3288_PLL_CON(16),
+		     RK3288_MODE_CON, 14, 9, NULL),
+};
+
+static struct clk_div_table div_hclk_cpu_t[] = {
+	{ .val = 0, .div = 1 },
+	{ .val = 1, .div = 2 },
+	{ .val = 3, .div = 4 },
+	{ /* sentinel */},
+};
+
+#define MFLAGS CLK_MUX_HIWORD_MASK
+#define DFLAGS CLK_DIVIDER_HIWORD_MASK
+#define GFLAGS (CLK_GATE_HIWORD_MASK | CLK_GATE_SET_TO_DISABLE)
+
+static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
+	/*
+	 * Clock-Architecture Diagram 1
+	 */
+
+	GATE(0, "apll_core", "apll", 0,
+			RK3288_CLKGATE_CON(0), 1, GFLAGS),
+	GATE(0, "gpll_core", "gpll", 0,
+			RK3288_CLKGATE_CON(0), 2, GFLAGS),
+	COMPOSITE_NOGATE(0, "armclk", mux_armclk_p, 0,
+			RK3288_CLKSEL_CON(0), 15, 1, MFLAGS, 8, 5, DFLAGS),
+
+	COMPOSITE_NOMUX(0, "armcore0", "armclk", 0,
+			RK3288_CLKSEL_CON(36), 0, 3, DFLAGS,
+			RK3288_CLKGATE_CON(12), 0, GFLAGS),
+	COMPOSITE_NOMUX(0, "armcore1", "armclk", 0,
+			RK3288_CLKSEL_CON(36), 4, 3, DFLAGS,
+			RK3288_CLKGATE_CON(12), 1, GFLAGS),
+	COMPOSITE_NOMUX(0, "armcore2", "armclk", 0,
+			RK3288_CLKSEL_CON(36), 8, 3, DFLAGS,
+			RK3288_CLKGATE_CON(12), 2, GFLAGS),
+	COMPOSITE_NOMUX(0, "armcore3", "armclk", 0,
+			RK3288_CLKSEL_CON(36), 12, 3, DFLAGS,
+			RK3288_CLKGATE_CON(12), 3, GFLAGS),
+	COMPOSITE_NOMUX(0, "l2ram", "armclk", 0,
+			RK3288_CLKSEL_CON(37), 0, 3, DFLAGS,
+			RK3288_CLKGATE_CON(12), 4, GFLAGS),
+	COMPOSITE_NOMUX(0, "aclk_core_m0", "armclk", 0,
+			RK3288_CLKSEL_CON(0), 0, 4, DFLAGS,
+			RK3288_CLKGATE_CON(12), 5, GFLAGS),
+	COMPOSITE_NOMUX(0, "aclk_core_mp", "armclk", 0,
+			RK3288_CLKSEL_CON(0), 4, 4, DFLAGS,
+			RK3288_CLKGATE_CON(12), 6, GFLAGS),
+	COMPOSITE_NOMUX(0, "atclk", "armclk", 0,
+			RK3288_CLKSEL_CON(37), 4, 5, DFLAGS,
+			RK3288_CLKGATE_CON(12), 7, GFLAGS),
+	COMPOSITE_NOMUX(0, "pclk_dbg_pre", "armclk", 0,
+			RK3288_CLKSEL_CON(37), 9, 5, DFLAGS,
+			RK3288_CLKGATE_CON(12), 8, GFLAGS),
+	GATE(0, "pclk_dbg", "pclk_dbg_pre", 0,
+			RK3288_CLKGATE_CON(12), 9, GFLAGS),
+	GATE(0, "cs_dbg", "pclk_dbg_pre", 0,
+			RK3288_CLKGATE_CON(12), 10, GFLAGS),
+	GATE(0, "pclk_core_niu", "pclk_dbg_pre", 0,
+			RK3288_CLKGATE_CON(12), 11, GFLAGS),
+
+	GATE(0, "dpll_ddr", "dpll", 0,
+			RK3288_CLKGATE_CON(0), 8, GFLAGS),
+	GATE(0, "gpll_ddr", "gpll", 0,
+			RK3288_CLKGATE_CON(0), 9, GFLAGS),
+	COMPOSITE_NOGATE(0, "ddrphy", mux_ddrphy_p, 0,
+			RK3288_CLKSEL_CON(26), 2, 1, MFLAGS, 0, 2,
+					DFLAGS | CLK_DIVIDER_POWER_OF_TWO),
+
+	GATE(0, "gpll_aclk_cpu", "gpll", 0,
+			RK3288_CLKGATE_CON(0), 10, GFLAGS),
+	GATE(0, "cpll_aclk_cpu", "cpll", 0,
+			RK3288_CLKGATE_CON(0), 11, GFLAGS),
+	COMPOSITE_NOGATE(0, "aclk_cpu_src", mux_aclk_cpu_src_p, 0,
+			RK3288_CLKSEL_CON(1), 15, 1, MFLAGS, 3, 5, DFLAGS),
+	DIV(0, "aclk_cpu_pre", "aclk_cpu_src", 0,
+			RK3288_CLKSEL_CON(1), 0, 3, DFLAGS),
+	GATE(0, "aclk_cpu", "aclk_cpu_pre", 0,
+			RK3288_CLKGATE_CON(0), 3, GFLAGS),
+	COMPOSITE_NOMUX(0, "pclk_cpu", "aclk_cpu_pre", 0,
+			RK3288_CLKSEL_CON(1), 12, 3, DFLAGS,
+			RK3288_CLKGATE_CON(0), 5, GFLAGS),
+	COMPOSITE_NOMUX_DIVTBL(0, "hclk_cpu", "aclk_cpu_pre", 0,
+			RK3288_CLKSEL_CON(1), 8, 2, DFLAGS, div_hclk_cpu_t,
+			RK3288_CLKGATE_CON(0), 4, GFLAGS),
+	GATE(0, "c2c_host", "aclk_cpu_src", 0,
+			RK3288_CLKGATE_CON(13), 8, GFLAGS),
+	COMPOSITE_NOMUX(0, "crypto", "aclk_cpu_pre", 0,
+			RK3288_CLKSEL_CON(26), 6, 2, DFLAGS,
+			RK3288_CLKGATE_CON(5), 4, GFLAGS),
+	GATE(0, "aclk_bus_2pmu", "aclk_cpu_pre", 0,
+			RK3288_CLKGATE_CON(0), 7, GFLAGS),
+
+	COMPOSITE(0, "i2s_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(4), 15, 1, MFLAGS, 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(4), 1, GFLAGS),
+	COMPOSITE_FRAC(0, "i2s_frac", "i2s_src", 0,
+			RK3288_CLKSEL_CON(8), 0,
+			RK3288_CLKGATE_CON(4), 2, GFLAGS),
+	MUX(0, "i2s_pre", mux_i2s_pre_p, 0,
+			RK3288_CLKSEL_CON(4), 8, 2, MFLAGS),
+	COMPOSITE_NODIV(0, "i2s0_clkout", mux_i2s_clkout_p, 0,
+			RK3288_CLKSEL_CON(4), 12, 1, MFLAGS,
+			RK3288_CLKGATE_CON(4), 0, GFLAGS),
+	GATE(SCLK_I2S0, "sclk_i2s0", "i2s_pre", 0,
+			RK3288_CLKGATE_CON(4), 3, GFLAGS),
+
+	MUX(0, "spdif_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(5), 15, 1, MFLAGS),
+	COMPOSITE_NOMUX(0, "spdif_pre", "spdif_src", 0,
+			RK3288_CLKSEL_CON(5), 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(4), 4, GFLAGS),
+	COMPOSITE_FRAC(0, "spdif_frac", "spdif_src", 0,
+			RK3288_CLKSEL_CON(9), 0,
+			RK3288_CLKGATE_CON(4), 5, GFLAGS),
+	COMPOSITE_NODIV(SCLK_SPDIF, "sclk_spdif", mux_spdif_p, 0,
+			RK3288_CLKSEL_CON(5), 8, 2, MFLAGS,
+			RK3288_CLKGATE_CON(4), 6, GFLAGS),
+	COMPOSITE_NOMUX(0, "spdif_8ch_pre", "spdif_src", 0,
+			RK3288_CLKSEL_CON(40), 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(4), 7, GFLAGS),
+	COMPOSITE_FRAC(0, "spdif_8ch_frac", "spdif_8ch_src", 0,
+			RK3288_CLKSEL_CON(41), 0,
+			RK3288_CLKGATE_CON(4), 8, GFLAGS),
+	COMPOSITE_NODIV(SCLK_SPDIF8CH, "sclk_spdif_8ch", mux_spdif_8ch_p, 0,
+			RK3288_CLKSEL_CON(40), 8, 2, MFLAGS,
+			RK3288_CLKGATE_CON(4), 9, GFLAGS),
+
+	GATE(0, "sclk_acc_efuse", "xin24m", 0,
+			RK3288_CLKGATE_CON(0), 12, GFLAGS),
+
+	GATE(SCLK_TIMER0, "sclk_timer0", "xin24m", 0,
+			RK3288_CLKGATE_CON(1), 0, GFLAGS),
+	GATE(SCLK_TIMER1, "sclk_timer1", "xin24m", 0,
+			RK3288_CLKGATE_CON(1), 1, GFLAGS),
+	GATE(SCLK_TIMER2, "sclk_timer2", "xin24m", 0,
+			RK3288_CLKGATE_CON(1), 2, GFLAGS),
+	GATE(SCLK_TIMER3, "sclk_timer3", "xin24m", 0,
+			RK3288_CLKGATE_CON(1), 3, GFLAGS),
+	GATE(SCLK_TIMER4, "sclk_timer4", "xin24m", 0,
+			RK3288_CLKGATE_CON(1), 4, GFLAGS),
+	GATE(SCLK_TIMER5, "sclk_timer5", "xin24m", 0,
+			RK3288_CLKGATE_CON(1), 5, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 2
+	 */
+
+	COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_usb480m_p, 0,
+			RK3288_CLKSEL_CON(32), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3288_CLKGATE_CON(3), 9, GFLAGS),
+	COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_usb480m_p, 0,
+			RK3288_CLKSEL_CON(32), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3288_CLKGATE_CON(3), 11, GFLAGS),
+
+	COMPOSITE(0, "aclk_vio0", mux_pll_src_cpll_gpll_usb480m_p, 0,
+			RK3288_CLKSEL_CON(31), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3288_CLKGATE_CON(3), 0, GFLAGS),
+	DIV(0, "hclk_vio", "aclk_vio0", 0,
+			RK3288_CLKSEL_CON(28), 8, 5, DFLAGS),
+	COMPOSITE(0, "aclk_vio1", mux_pll_src_cpll_gpll_usb480m_p, 0,
+			RK3288_CLKSEL_CON(31), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3288_CLKGATE_CON(3), 2, GFLAGS),
+
+	COMPOSITE(0, "aclk_rga_pre", mux_pll_src_cpll_gpll_usb480m_p, 0,
+			RK3288_CLKSEL_CON(30), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3288_CLKGATE_CON(3), 5, GFLAGS),
+	COMPOSITE(0, "sclk_rga", mux_pll_src_cpll_gpll_usb480m_p, 0,
+			RK3288_CLKSEL_CON(30), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3288_CLKGATE_CON(3), 4, GFLAGS),
+
+	COMPOSITE(DCLK_VOP0, "dclk_vop0", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3288_CLKSEL_CON(27), 0, 2, MFLAGS, 8, 8, DFLAGS,
+			RK3288_CLKGATE_CON(3), 1, GFLAGS),
+	COMPOSITE(DCLK_VOP1, "dclk_vop1", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3288_CLKSEL_CON(29), 6, 2, MFLAGS, 8, 8, DFLAGS,
+			RK3288_CLKGATE_CON(3), 3, GFLAGS),
+
+	COMPOSITE_NODIV(0, "sclk_edp_24m", mux_edp_24m_p, 0,
+			RK3288_CLKSEL_CON(28), 15, 1, MFLAGS,
+			RK3288_CLKGATE_CON(3), 12, GFLAGS),
+	COMPOSITE(0, "sclk_edp", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3288_CLKSEL_CON(28), 6, 2, MFLAGS, 0, 6, DFLAGS,
+			RK3288_CLKGATE_CON(3), 13, GFLAGS),
+
+	COMPOSITE(0, "sclk_isp", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3288_CLKSEL_CON(6), 6, 2, MFLAGS, 0, 6, DFLAGS,
+			RK3288_CLKGATE_CON(3), 14, GFLAGS),
+	COMPOSITE(0, "sclk_isp_jpe", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3288_CLKSEL_CON(6), 14, 2, MFLAGS, 8, 6, DFLAGS,
+			RK3288_CLKGATE_CON(3), 15, GFLAGS),
+
+	GATE(0, "sclk_hdmi_hdcp", "xin24m", 0,
+			RK3288_CLKGATE_CON(5), 12, GFLAGS),
+	GATE(0, "sclk_hdmi_cec", "xin32k", 0,
+			RK3288_CLKGATE_CON(5), 11, GFLAGS),
+
+	COMPOSITE(0, "aclk_hevc", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3288_CLKSEL_CON(39), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3288_CLKGATE_CON(13), 13, GFLAGS),
+	DIV(0, "hclk_hevc", "aclk_hevc", 0,
+			RK3288_CLKSEL_CON(40), 12, 2, DFLAGS),
+
+	COMPOSITE(0, "sclk_hevc_cabac", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3288_CLKSEL_CON(42), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3288_CLKGATE_CON(13), 14, GFLAGS),
+	COMPOSITE(0, "sclk_hevc_core", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3288_CLKSEL_CON(42), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3288_CLKGATE_CON(13), 15, GFLAGS),
+
+	COMPOSITE_NODIV(0, "vip_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(26), 8, 1, MFLAGS,
+			RK3288_CLKGATE_CON(3), 7, GFLAGS),
+	COMPOSITE_NOGATE(0, "sclk_vip_out", mux_cif_out_p, 0,
+			RK3288_CLKSEL_CON(26), 15, 1, MFLAGS, 9, 5, DFLAGS),
+
+	DIV(0, "pclk_pd_alive", "gpll", 0,
+			RK3288_CLKSEL_CON(33), 8, 5, DFLAGS),
+	COMPOSITE_NOMUX(0, "pclk_pd_pmu", "gpll", 0,
+			RK3288_CLKSEL_CON(33), 0, 5, DFLAGS,
+			RK3288_CLKGATE_CON(5), 8, GFLAGS),
+
+	COMPOSITE(SCLK_GPU, "sclk_gpu", mux_pll_src_cpll_gpll_usb480m_p, 0,
+			RK3288_CLKSEL_CON(34), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3288_CLKGATE_CON(5), 7, GFLAGS),
+
+	COMPOSITE(0, "aclk_peri_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(10), 15, 1, MFLAGS, 0, 5, DFLAGS,
+			RK3288_CLKGATE_CON(2), 0, GFLAGS),
+	COMPOSITE_NOMUX(0, "pclk_peri", "aclk_peri_src", 0,
+			RK3288_CLKSEL_CON(10), 12, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
+			RK3288_CLKGATE_CON(2), 3, GFLAGS),
+	COMPOSITE_NOMUX(0, "hclk_peri", "aclk_peri_src", 0,
+			RK3288_CLKSEL_CON(10), 8, 2, DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
+			RK3288_CLKGATE_CON(2), 2, GFLAGS),
+	GATE(0, "aclk_peri", "aclk_peri_src", 0,
+			RK3288_CLKGATE_CON(2), 1, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 3
+	 */
+
+	COMPOSITE(SCLK_SPI0, "sclk_spi0", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(25), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(2), 9, GFLAGS),
+	COMPOSITE(SCLK_SPI1, "sclk_spi1", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(25), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			RK3288_CLKGATE_CON(2), 10, GFLAGS),
+	COMPOSITE(SCLK_SPI2, "sclk_spi2", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(39), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(2), 11, GFLAGS),
+
+	COMPOSITE(SCLK_SDMMC, "sclk_sdmmc", mux_mmc_src_p, 0,
+			RK3288_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS,
+			RK3288_CLKGATE_CON(13), 0, GFLAGS),
+	COMPOSITE(SCLK_SDIO0, "sclk_sdio0", mux_mmc_src_p, 0,
+			RK3288_CLKSEL_CON(12), 6, 2, MFLAGS, 0, 6, DFLAGS,
+			RK3288_CLKGATE_CON(13), 1, GFLAGS),
+	COMPOSITE(SCLK_SDIO1, "sclk_sdio1", mux_mmc_src_p, 0,
+			RK3288_CLKSEL_CON(34), 14, 2, MFLAGS, 8, 6, DFLAGS,
+			RK3288_CLKGATE_CON(13), 2, GFLAGS),
+	COMPOSITE(SCLK_EMMC, "sclk_emmc", mux_mmc_src_p, 0,
+			RK3288_CLKSEL_CON(12), 14, 2, MFLAGS, 8, 6, DFLAGS,
+			RK3288_CLKGATE_CON(13), 3, GFLAGS),
+
+	COMPOSITE(0, "sclk_tspout", mux_tspout_p, 0,
+			RK3288_CLKSEL_CON(35), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3288_CLKGATE_CON(4), 11, GFLAGS),
+	COMPOSITE(0, "sclk_tsp", mux_pll_src_cpll_gpll_npll_p, 0,
+			RK3288_CLKSEL_CON(35), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			RK3288_CLKGATE_CON(4), 10, GFLAGS),
+
+	GATE(SCLK_OTGPHY0, "sclk_otgphy0", "usb480m", 0,
+			RK3288_CLKGATE_CON(13), 4, GFLAGS),
+	GATE(SCLK_OTGPHY1, "sclk_otgphy1", "usb480m", 0,
+			RK3288_CLKGATE_CON(13), 5, GFLAGS),
+	GATE(SCLK_OTGPHY2, "sclk_otgphy2", "usb480m", 0,
+			RK3288_CLKGATE_CON(13), 6, GFLAGS),
+	GATE(SCLK_OTG_ADP, "sclk_otg_adp", "xin32k", 0,
+			RK3288_CLKGATE_CON(13), 7, GFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_TSADC, "sclk_tsadc", "xin32k", 0,
+			RK3288_CLKSEL_CON(2), 0, 6, DFLAGS,
+			RK3288_CLKGATE_CON(2), 7, GFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_SARADC, "sclk_saradc", "xin24m", 0,
+			RK3288_CLKSEL_CON(24), 8, 8, DFLAGS,
+			RK3288_CLKGATE_CON(2), 8, GFLAGS),
+
+	GATE(SCLK_PS2C, "sclk_ps2c", "xin24m", 0,
+			RK3288_CLKGATE_CON(5), 13, GFLAGS),
+
+	COMPOSITE(SCLK_NANDC0, "sclk_nandc0", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(38), 7, 1, MFLAGS, 0, 5, DFLAGS,
+			RK3288_CLKGATE_CON(5), 5, GFLAGS),
+	COMPOSITE(SCLK_NANDC1, "sclk_nandc1", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(38), 15, 1, MFLAGS, 8, 5, DFLAGS,
+			RK3288_CLKGATE_CON(5), 6, GFLAGS),
+
+	COMPOSITE(0, "uart0_src", mux_uart0_pll_p, 0,
+			RK3288_CLKSEL_CON(13), 13, 2, MFLAGS, 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(1), 8, GFLAGS),
+	COMPOSITE_FRAC(0, "uart0_frac", "uart0_src", 0,
+			RK3288_CLKSEL_CON(17), 0,
+			RK3288_CLKGATE_CON(1), 9, GFLAGS),
+	MUX(SCLK_UART0, "sclk_uart0", mux_uart0_p, 0,
+			RK3288_CLKSEL_CON(13), 8, 2, MFLAGS),
+	MUX(0, "uart_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(13), 15, 1, MFLAGS),
+	COMPOSITE_NOMUX(0, "uart1_src", "uart_src", 0,
+			RK3288_CLKSEL_CON(14), 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(1), 10, GFLAGS),
+	COMPOSITE_FRAC(0, "uart1_frac", "uart1_src", 0,
+			RK3288_CLKSEL_CON(18), 0,
+			RK3288_CLKGATE_CON(1), 11, GFLAGS),
+	MUX(SCLK_UART1, "sclk_uart1", mux_uart1_p, 0,
+			RK3288_CLKSEL_CON(14), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "uart2_src", "uart_src", 0,
+			RK3288_CLKSEL_CON(15), 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(1), 12, GFLAGS),
+	COMPOSITE_FRAC(0, "uart2_frac", "uart2_src", 0,
+			RK3288_CLKSEL_CON(19), 0,
+			RK3288_CLKGATE_CON(1), 13, GFLAGS),
+	MUX(SCLK_UART2, "sclk_uart2", mux_uart2_p, 0,
+			RK3288_CLKSEL_CON(15), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "uart3_src", "uart_src", 0,
+			RK3288_CLKSEL_CON(16), 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(1), 14, GFLAGS),
+	COMPOSITE_FRAC(0, "uart3_frac", "uart3_src", 0,
+			RK3288_CLKSEL_CON(20), 0,
+			RK3288_CLKGATE_CON(1), 15, GFLAGS),
+	MUX(SCLK_UART3, "sclk_uart3", mux_uart3_p, 0,
+			RK3288_CLKSEL_CON(16), 8, 2, MFLAGS),
+	COMPOSITE_NOMUX(0, "uart4_src", "uart_src", 0,
+			RK3288_CLKSEL_CON(3), 0, 7, DFLAGS,
+			RK3288_CLKGATE_CON(2), 12, GFLAGS),
+	COMPOSITE_FRAC(0, "uart4_frac", "uart4_src", 0,
+			RK3288_CLKSEL_CON(7), 0,
+			RK3288_CLKGATE_CON(2), 13, GFLAGS),
+	MUX(SCLK_UART4, "sclk_uart4", mux_uart4_p, 0,
+			RK3288_CLKSEL_CON(3), 8, 2, MFLAGS),
+
+	COMPOSITE(0, "mac_src", mux_pll_src_npll_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(21), 0, 2, MFLAGS, 8, 5, DFLAGS,
+			RK3288_CLKGATE_CON(2), 5, GFLAGS),
+	MUX(0, "macref", mux_macref_p, 0,
+			RK3288_CLKSEL_CON(21), 4, 1, MFLAGS),
+	GATE(0, "sclk_macref_out", "macref", 0,
+			RK3288_CLKGATE_CON(5), 3, GFLAGS),
+	GATE(SCLK_MACREF, "sclk_macref", "macref", 0,
+			RK3288_CLKGATE_CON(5), 2, GFLAGS),
+	GATE(SCLK_MAC_RX, "sclk_mac_rx", "macref", 0,
+			RK3288_CLKGATE_CON(5), 0, GFLAGS),
+	GATE(SCLK_MAC_TX, "sclk_mac_tx", "macref", 0,
+			RK3288_CLKGATE_CON(5), 1, GFLAGS),
+
+	COMPOSITE(0, "hsadc_src", mux_pll_src_cpll_gpll_p, 0,
+			RK3288_CLKSEL_CON(22), 0, 1, MFLAGS, 8, 8, DFLAGS,
+			RK3288_CLKGATE_CON(2), 6, GFLAGS),
+	MUX(SCLK_HSADC, "sclk_hsadc_out", mux_hsadcout_p, 0,
+			RK3288_CLKSEL_CON(22), 4, 1, MFLAGS),
+
+	GATE(0, "jtag", "ext_jtag", 0,
+			RK3288_CLKGATE_CON(4), 14, GFLAGS),
+
+	COMPOSITE_NODIV(0, "usbphy480m_src", mux_usbphy480m_p, 0,
+			RK3288_CLKSEL_CON(13), 11, 2, MFLAGS,
+			RK3288_CLKGATE_CON(5), 15, GFLAGS),
+	COMPOSITE_NODIV(SCLK_HSICPHY480M, "sclk_hsicphy480m", mux_hsicphy480m_p, 0,
+			RK3288_CLKSEL_CON(29), 0, 2, MFLAGS,
+			RK3288_CLKGATE_CON(3), 6, GFLAGS),
+	GATE(0, "hsicphy12m_xin12m", "xin12m", 0,
+			RK3288_CLKGATE_CON(13), 9, GFLAGS),
+	DIV(0, "hsicphy12m_usbphy", "sclk_hsicphy480m", 0,
+			RK3288_CLKSEL_CON(11), 8, 6, DFLAGS),
+	MUX(SCLK_HSICPHY12M, "sclk_hsicphy12m", mux_hsicphy12m_p, 0,
+			RK3288_CLKSEL_CON(22), 4, 1, MFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 4
+	 */
+
+	/* aclk_cpu gates */
+	GATE(0, "sclk_intmem0", "aclk_cpu", 0, RK3288_CLKGATE_CON(10), 5, GFLAGS),
+	GATE(0, "sclk_intmem1", "aclk_cpu", 0, RK3288_CLKGATE_CON(10), 6, GFLAGS),
+	GATE(0, "sclk_intmem2", "aclk_cpu", 0, RK3288_CLKGATE_CON(10), 7, GFLAGS),
+	GATE(ACLK_DMAC1, "aclk_dmac1", "aclk_cpu", 0, RK3288_CLKGATE_CON(10), 12, GFLAGS),
+	GATE(0, "aclk_strc_sys", "aclk_cpu", 0, RK3288_CLKGATE_CON(10), 13, GFLAGS),
+	GATE(0, "aclk_intmem", "aclk_cpu", 0, RK3288_CLKGATE_CON(10), 4, GFLAGS),
+	GATE(ACLK_CRYPTO, "aclk_crypto", "aclk_cpu", 0, RK3288_CLKGATE_CON(11), 6, GFLAGS),
+	GATE(0, "aclk_ccp", "aclk_cpu", 0, RK3288_CLKGATE_CON(11), 8, GFLAGS),
+
+	/* hclk_cpu gates */
+	GATE(HCLK_CRYPTO, "hclk_crypto", "hclk_cpu", 0, RK3288_CLKGATE_CON(11), 7, GFLAGS),
+	GATE(HCLK_I2S0, "hclk_i2s0", "hclk_cpu", 0, RK3288_CLKGATE_CON(10), 8, GFLAGS),
+	GATE(HCLK_ROM, "hclk_rom", "hclk_cpu", 0, RK3288_CLKGATE_CON(10), 9, GFLAGS),
+	GATE(HCLK_SPDIF, "hclk_spdif", "hclk_cpu", 0, RK3288_CLKGATE_CON(10), 10, GFLAGS),
+	GATE(HCLK_SPDIF8CH, "hclk_spdif_8ch", "hclk_cpu", 0, RK3288_CLKGATE_CON(10), 11, GFLAGS),
+
+	/* pclk_cpu gates */
+	GATE(PCLK_PWM, "pclk_pwm", "pclk_cpu", 0, RK3288_CLKGATE_CON(10), 0, GFLAGS),
+	GATE(PCLK_TIMER, "pclk_timer", "pclk_cpu", 0, RK3288_CLKGATE_CON(10), 1, GFLAGS),
+	GATE(PCLK_I2C0, "pclk_i2c0", "pclk_cpu", 0, RK3288_CLKGATE_CON(10), 2, GFLAGS),
+	GATE(PCLK_I2C1, "pclk_i2c1", "pclk_cpu", 0, RK3288_CLKGATE_CON(10), 3, GFLAGS),
+	GATE(0, "pclk_ddrupctl0", "pclk_cpu", 0, RK3288_CLKGATE_CON(10), 14, GFLAGS),
+	GATE(0, "pclk_publ0", "pclk_cpu", 0, RK3288_CLKGATE_CON(10), 15, GFLAGS),
+	GATE(0, "pclk_ddrupctl1", "pclk_cpu", 0, RK3288_CLKGATE_CON(11), 0, GFLAGS),
+	GATE(0, "pclk_publ1", "pclk_cpu", 0, RK3288_CLKGATE_CON(11), 1, GFLAGS),
+	GATE(0, "pclk_efuse_1024", "pclk_cpu", 0, RK3288_CLKGATE_CON(11), 2, GFLAGS),
+	GATE(PCLK_TZPC, "pclk_tzpc", "pclk_cpu", 0, RK3288_CLKGATE_CON(11), 3, GFLAGS),
+	GATE(PCLK_UART2, "pclk_uart2", "pclk_cpu", 0, RK3288_CLKGATE_CON(11), 9, GFLAGS),
+	GATE(0, "pclk_efuse_256", "pclk_cpu", 0, RK3288_CLKGATE_CON(11), 10, GFLAGS),
+	GATE(PCLK_RKPWM, "pclk_rkpwm", "pclk_cpu", 0, RK3288_CLKGATE_CON(11), 11, GFLAGS),
+
+	/* ddrctrl [DDR Controller PHY clock] gates */
+	GATE(0, "nclk_ddrupctl0", "ddrphy", 0, RK3288_CLKGATE_CON(11), 4, GFLAGS),
+	GATE(0, "nclk_ddrupctl1", "ddrphy", 0, RK3288_CLKGATE_CON(11), 5, GFLAGS),
+
+	/* ddrphy gates */
+	GATE(0, "sclk_ddrphy0", "ddrphy", 0, RK3288_CLKGATE_CON(4), 12, GFLAGS),
+	GATE(0, "sclk_ddrphy1", "ddrphy", 0, RK3288_CLKGATE_CON(4), 13, GFLAGS),
+
+	/* aclk_peri gates */
+	GATE(0, "aclk_peri_axi_matrix", "aclk_peri", 0, RK3288_CLKGATE_CON(6), 2, GFLAGS),
+	GATE(ACLK_DMAC2, "aclk_dmac2", "aclk_peri", 0, RK3288_CLKGATE_CON(6), 3, GFLAGS),
+	GATE(0, "aclk_peri_niu", "aclk_peri", 0, RK3288_CLKGATE_CON(7), 11, GFLAGS),
+	GATE(ACLK_MMU, "aclk_mmu", "aclk_peri", 0, RK3288_CLKGATE_CON(8), 12, GFLAGS),
+	GATE(ACLK_GMAC, "aclk_gmac", "aclk_peri", 0, RK3288_CLKGATE_CON(8), 0, GFLAGS),
+	GATE(HCLK_GPS, "hclk_gps", "aclk_peri", 0, RK3288_CLKGATE_CON(8), 2, GFLAGS),
+
+	/* hclk_peri gates */
+	GATE(0, "hclk_peri_matrix", "hclk_peri", 0, RK3288_CLKGATE_CON(6), 0, GFLAGS),
+	GATE(HCLK_OTG0, "hclk_otg0", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 4, GFLAGS),
+	GATE(HCLK_USBHOST0, "hclk_host0", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 6, GFLAGS),
+	GATE(HCLK_USBHOST1, "hclk_host1", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 7, GFLAGS),
+	GATE(HCLK_HSIC, "hclk_hsic", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 8, GFLAGS),
+	GATE(0, "hclk_usb_peri", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 9, GFLAGS),
+	GATE(0, "hclk_peri_ahb_arbi", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 10, GFLAGS),
+	GATE(0, "hclk_emem", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 12, GFLAGS),
+	GATE(0, "hclk_mem", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 13, GFLAGS),
+	GATE(HCLK_NANDC0, "hclk_nandc0", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 14, GFLAGS),
+	GATE(HCLK_NANDC1, "hclk_nandc1", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 15, GFLAGS),
+	GATE(HCLK_TSP, "hclk_tsp", "hclk_peri", 0, RK3288_CLKGATE_CON(8), 8, GFLAGS),
+	GATE(HCLK_SDMMC, "hclk_sdmmc", "hclk_peri", 0, RK3288_CLKGATE_CON(8), 3, GFLAGS),
+	GATE(HCLK_SDIO0, "hclk_sdio0", "hclk_peri", 0, RK3288_CLKGATE_CON(8), 4, GFLAGS),
+	GATE(HCLK_SDIO1, "hclk_sdio1", "hclk_peri", 0, RK3288_CLKGATE_CON(8), 5, GFLAGS),
+	GATE(HCLK_EMMC, "hclk_emmc", "hclk_peri", 0, RK3288_CLKGATE_CON(8), 6, GFLAGS),
+	GATE(HCLK_HSADC, "hclk_hsadc", "hclk_peri", 0, RK3288_CLKGATE_CON(8), 7, GFLAGS),
+	GATE(0, "pmu_hclk_otg0", "hclk_peri", 0, RK3288_CLKGATE_CON(7), 5, GFLAGS),
+
+	/* pclk_peri gates */
+	GATE(0, "pclk_peri_matrix", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 1, GFLAGS),
+	GATE(PCLK_SPI0, "pclk_spi0", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 4, GFLAGS),
+	GATE(PCLK_SPI1, "pclk_spi1", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 5, GFLAGS),
+	GATE(PCLK_SPI2, "pclk_spi2", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 6, GFLAGS),
+	GATE(PCLK_PS2C, "pclk_ps2c", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 7, GFLAGS),
+	GATE(PCLK_UART0, "pclk_uart0", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 8, GFLAGS),
+	GATE(PCLK_UART1, "pclk_uart1", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 9, GFLAGS),
+	GATE(PCLK_I2C4, "pclk_i2c4", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 15, GFLAGS),
+	GATE(PCLK_UART3, "pclk_uart3", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 11, GFLAGS),
+	GATE(PCLK_UART4, "pclk_uart4", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 12, GFLAGS),
+	GATE(PCLK_I2C2, "pclk_i2c2", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 13, GFLAGS),
+	GATE(PCLK_I2C3, "pclk_i2c3", "pclk_peri", 0, RK3288_CLKGATE_CON(6), 14, GFLAGS),
+	GATE(PCLK_SARADC, "pclk_saradc", "pclk_peri", 0, RK3288_CLKGATE_CON(7), 1, GFLAGS),
+	GATE(PCLK_TSADC, "pclk_tsadc", "pclk_peri", 0, RK3288_CLKGATE_CON(7), 2, GFLAGS),
+	GATE(PCLK_SIM, "pclk_sim", "pclk_peri", 0, RK3288_CLKGATE_CON(7), 3, GFLAGS),
+	GATE(PCLK_I2C5, "pclk_i2c5", "pclk_peri", 0, RK3288_CLKGATE_CON(7), 0, GFLAGS),
+	GATE(PCLK_GMAC, "pclk_gmac", "pclk_peri", 0, RK3288_CLKGATE_CON(8), 1, GFLAGS),
+
+	GATE(SCLK_LCDC_PWM0, "sclk_lcdc_pwm0", "xin24m", 0, RK3288_CLKGATE_CON(13), 10, GFLAGS),
+	GATE(SCLK_LCDC_PWM1, "sclk_lcdc_pwm1", "xin24m", 0, RK3288_CLKGATE_CON(13), 11, GFLAGS),
+	GATE(0, "sclk_pvtm_core", "xin24m", 0, RK3288_CLKGATE_CON(5), 9, GFLAGS),
+	GATE(0, "sclk_pvtm_gpu", "xin24m", 0, RK3288_CLKGATE_CON(5), 10, GFLAGS),
+	GATE(0, "sclk_mipidsi_24m", "xin24m", 0, RK3288_CLKGATE_CON(5), 15, GFLAGS),
+
+	/* sclk_gpu gates */
+	GATE(ACLK_GPU, "aclk_gpu", "sclk_gpu", 0, RK3288_CLKGATE_CON(18), 0, GFLAGS),
+
+	/* pclk_pd_alive gates */
+	GATE(PCLK_GPIO8, "pclk_gpio8", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 8, GFLAGS),
+	GATE(PCLK_GPIO7, "pclk_gpio7", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 7, GFLAGS),
+	GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 1, GFLAGS),
+	GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 2, GFLAGS),
+	GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 3, GFLAGS),
+	GATE(PCLK_GPIO4, "pclk_gpio4", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 4, GFLAGS),
+	GATE(PCLK_GPIO5, "pclk_gpio5", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 5, GFLAGS),
+	GATE(PCLK_GPIO6, "pclk_gpio6", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 6, GFLAGS),
+	GATE(PCLK_GRF, "pclk_grf", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 11, GFLAGS),
+	GATE(0, "pclk_alive_niu", "pclk_pd_alive", 0, RK3288_CLKGATE_CON(14), 12, GFLAGS),
+
+	/* pclk_pd_pmu gates */
+	GATE(PCLK_PMU, "pclk_pmu", "pclk_pd_pmu", 0, RK3288_CLKGATE_CON(17), 0, GFLAGS),
+	GATE(0, "pclk_intmem1", "pclk_pd_pmu", 0, RK3288_CLKGATE_CON(17), 1, GFLAGS),
+	GATE(0, "pclk_pmu_niu", "pclk_pd_pmu", 0, RK3288_CLKGATE_CON(17), 2, GFLAGS),
+	GATE(PCLK_SGRF, "pclk_sgrf", "pclk_pd_pmu", 0, RK3288_CLKGATE_CON(17), 3, GFLAGS),
+	GATE(PCLK_GPIO0, "pclk_gpio0", "pclk_pd_pmu", 0, RK3288_CLKGATE_CON(17), 4, GFLAGS),
+
+	/* hclk_vio gates */
+	GATE(HCLK_RGA, "hclk_rga", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 1, GFLAGS),
+	GATE(HCLK_VOP0, "hclk_vop0", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 6, GFLAGS),
+	GATE(HCLK_VOP1, "hclk_vop1", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 8, GFLAGS),
+	GATE(0, "hclk_vio_ahb_arbi", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 9, GFLAGS),
+	GATE(0, "hclk_vio_niu", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 10, GFLAGS),
+	GATE(0, "hclk_vip", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 15, GFLAGS),
+	GATE(HCLK_IEP, "hclk_iep", "hclk_vio", 0, RK3288_CLKGATE_CON(15), 3, GFLAGS),
+	GATE(HCLK_ISP, "hclk_isp", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 1, GFLAGS),
+	GATE(0, "hclk_vio2_h2p", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 10, GFLAGS),
+	GATE(0, "pclk_mipi_dsi0", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 4, GFLAGS),
+	GATE(0, "pclk_mipi_dsi1", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 5, GFLAGS),
+	GATE(0, "pclk_mipi_csi", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 6, GFLAGS),
+	GATE(0, "pclk_lvds_phy", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 7, GFLAGS),
+	GATE(0, "pclk_edp_ctrl", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 8, GFLAGS),
+	GATE(0, "pclk_hdmi_ctrl", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 9, GFLAGS),
+	GATE(0, "pclk_vio2_h2p", "hclk_vio", 0, RK3288_CLKGATE_CON(16), 11, GFLAGS),
+
+	/* aclk_vio0 gates */
+	GATE(ACLK_VOP0, "aclk_vop0", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 5, GFLAGS),
+	GATE(0, "aclk_iep", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 2, GFLAGS),
+	GATE(0, "aclk_vio0_niu", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 11, GFLAGS),
+	GATE(0, "aclk_vip", "aclk_vio0", 0, RK3288_CLKGATE_CON(15), 14, GFLAGS),
+
+	/* aclk_vio1 gates */
+	GATE(ACLK_VOP1, "aclk_vop1", "aclk_vio1", 0, RK3288_CLKGATE_CON(15), 7, GFLAGS),
+	GATE(0, "aclk_isp", "aclk_vio1", 0, RK3288_CLKGATE_CON(16), 2, GFLAGS),
+	GATE(0, "aclk_vio1_niu", "aclk_vio1", 0, RK3288_CLKGATE_CON(15), 12, GFLAGS),
+
+	/* aclk_rga_pre gates */
+	GATE(ACLK_RGA, "aclk_rga", "aclk_rga_pre", 0, RK3288_CLKGATE_CON(15), 0, GFLAGS),
+	GATE(0, "aclk_rga_niu", "aclk_rga_pre", 0, RK3288_CLKGATE_CON(15), 13, GFLAGS),
+
+	/*
+	 * Other ungrouped clocks.
+	 */
+
+	GATE(0, "pclk_vip_in", "ext_vip", 0, RK3288_CLKGATE_CON(16), 0, GFLAGS),
+	GATE(0, "pclk_isp_in", "ext_isp", 0, RK3288_CLKGATE_CON(16), 3, GFLAGS),
+};
+
+static void __init rk3288_clk_init(struct device_node *np)
+{
+	void __iomem *reg_base;
+	struct clk *clk;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		pr_err("%s: could not map cru region\n", __func__);
+		return;
+	}
+
+	rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
+
+	/* xin12m is created by an cru-internal divider */
+	clk = clk_register_fixed_factor(NULL, "xin12m", "xin24m", 0, 1, 2);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock xin12m: %ld\n",
+			__func__, PTR_ERR(clk));
+
+
+	clk = clk_register_fixed_factor(NULL, "usb480m", "xin24m", 0, 20, 1);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock usb480m: %ld\n",
+			__func__, PTR_ERR(clk));
+
+	rockchip_clk_register_plls(rk3288_pll_clks,
+				   ARRAY_SIZE(rk3288_pll_clks),
+				   RK3288_GRF_SOC_STATUS);
+	rockchip_clk_register_branches(rk3288_clk_branches,
+				  ARRAY_SIZE(rk3288_clk_branches));
+
+	rockchip_register_softrst(np, 9, reg_base + RK3288_SOFTRST_CON(0),
+				  ROCKCHIP_SOFTRST_HIWORD_MASK);
+}
+CLK_OF_DECLARE(rk3288_cru, "rockchip,rk3288-cru", rk3288_clk_init);
diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
new file mode 100644
index 00000000000..278cf9dd1e2
--- /dev/null
+++ b/drivers/clk/rockchip/clk.c
@@ -0,0 +1,244 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * based on
+ *
+ * samsung/clk.c
+ * Copyright (c) 2013 Samsung Electronics Co., Ltd.
+ * Copyright (c) 2013 Linaro Ltd.
+ * Author: Thomas Abraham <thomas.ab@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/slab.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include "clk.h"
+
+/**
+ * Register a clock branch.
+ * Most clock branches have a form like
+ *
+ * src1 --|--\
+ *        |M |--[GATE]-[DIV]-
+ * src2 --|--/
+ *
+ * sometimes without one of those components.
+ */
+struct clk *rockchip_clk_register_branch(const char *name,
+		const char **parent_names, u8 num_parents, void __iomem *base,
+		int muxdiv_offset, u8 mux_shift, u8 mux_width, u8 mux_flags,
+		u8 div_shift, u8 div_width, u8 div_flags,
+		struct clk_div_table *div_table, int gate_offset,
+		u8 gate_shift, u8 gate_flags, unsigned long flags,
+		spinlock_t *lock)
+{
+	struct clk *clk;
+	struct clk_mux *mux = NULL;
+	struct clk_gate *gate = NULL;
+	struct clk_divider *div = NULL;
+	const struct clk_ops *mux_ops = NULL, *div_ops = NULL,
+			     *gate_ops = NULL;
+
+	if (num_parents > 1) {
+		mux = kzalloc(sizeof(*mux), GFP_KERNEL);
+		if (!mux)
+			return ERR_PTR(-ENOMEM);
+
+		mux->reg = base + muxdiv_offset;
+		mux->shift = mux_shift;
+		mux->mask = BIT(mux_width) - 1;
+		mux->flags = mux_flags;
+		mux->lock = lock;
+		mux_ops = (mux_flags & CLK_MUX_READ_ONLY) ? &clk_mux_ro_ops
+							: &clk_mux_ops;
+	}
+
+	if (gate_offset >= 0) {
+		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+		if (!gate)
+			return ERR_PTR(-ENOMEM);
+
+		gate->flags = gate_flags;
+		gate->reg = base + gate_offset;
+		gate->bit_idx = gate_shift;
+		gate->lock = lock;
+		gate_ops = &clk_gate_ops;
+	}
+
+	if (div_width > 0) {
+		div = kzalloc(sizeof(*div), GFP_KERNEL);
+		if (!div)
+			return ERR_PTR(-ENOMEM);
+
+		div->flags = div_flags;
+		div->reg = base + muxdiv_offset;
+		div->shift = div_shift;
+		div->width = div_width;
+		div->lock = lock;
+		div->table = div_table;
+		div_ops = (div_flags & CLK_DIVIDER_READ_ONLY)
+						? &clk_divider_ro_ops
+						: &clk_divider_ops;
+	}
+
+	clk = clk_register_composite(NULL, name, parent_names, num_parents,
+				     mux ? &mux->hw : NULL, mux_ops,
+				     div ? &div->hw : NULL, div_ops,
+				     gate ? &gate->hw : NULL, gate_ops,
+				     flags);
+
+	return clk;
+}
+
+static DEFINE_SPINLOCK(clk_lock);
+static struct clk **clk_table;
+static void __iomem *reg_base;
+static struct clk_onecell_data clk_data;
+static struct device_node *cru_node;
+static struct regmap *grf;
+
+void __init rockchip_clk_init(struct device_node *np, void __iomem *base,
+			      unsigned long nr_clks)
+{
+	reg_base = base;
+	cru_node = np;
+	grf = ERR_PTR(-EPROBE_DEFER);
+
+	clk_table = kcalloc(nr_clks, sizeof(struct clk *), GFP_KERNEL);
+	if (!clk_table)
+		pr_err("%s: could not allocate clock lookup table\n", __func__);
+
+	clk_data.clks = clk_table;
+	clk_data.clk_num = nr_clks;
+	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+}
+
+struct regmap *rockchip_clk_get_grf(void)
+{
+	if (IS_ERR(grf))
+		grf = syscon_regmap_lookup_by_phandle(cru_node, "rockchip,grf");
+	return grf;
+}
+
+void rockchip_clk_add_lookup(struct clk *clk, unsigned int id)
+{
+	if (clk_table && id)
+		clk_table[id] = clk;
+}
+
+void __init rockchip_clk_register_plls(struct rockchip_pll_clock *list,
+				unsigned int nr_pll, int grf_lock_offset)
+{
+	struct clk *clk;
+	int idx;
+
+	for (idx = 0; idx < nr_pll; idx++, list++) {
+		clk = rockchip_clk_register_pll(list->type, list->name,
+				list->parent_names, list->num_parents,
+				reg_base, list->con_offset, grf_lock_offset,
+				list->lock_shift, list->mode_offset,
+				list->mode_shift, list->rate_table, &clk_lock);
+		if (IS_ERR(clk)) {
+			pr_err("%s: failed to register clock %s\n", __func__,
+				list->name);
+			continue;
+		}
+
+		rockchip_clk_add_lookup(clk, list->id);
+	}
+}
+
+void __init rockchip_clk_register_branches(
+				      struct rockchip_clk_branch *list,
+				      unsigned int nr_clk)
+{
+	struct clk *clk = NULL;
+	unsigned int idx;
+	unsigned long flags;
+
+	for (idx = 0; idx < nr_clk; idx++, list++) {
+		flags = list->flags;
+
+		/* catch simple muxes */
+		switch (list->branch_type) {
+		case branch_mux:
+			clk = clk_register_mux(NULL, list->name,
+				list->parent_names, list->num_parents,
+				flags, reg_base + list->muxdiv_offset,
+				list->mux_shift, list->mux_width,
+				list->mux_flags, &clk_lock);
+			break;
+		case branch_divider:
+			if (list->div_table)
+				clk = clk_register_divider_table(NULL,
+					list->name, list->parent_names[0],
+					flags, reg_base + list->muxdiv_offset,
+					list->div_shift, list->div_width,
+					list->div_flags, list->div_table,
+					&clk_lock);
+			else
+				clk = clk_register_divider(NULL, list->name,
+					list->parent_names[0], flags,
+					reg_base + list->muxdiv_offset,
+					list->div_shift, list->div_width,
+					list->div_flags, &clk_lock);
+			break;
+		case branch_fraction_divider:
+			/* unimplemented */
+			continue;
+			break;
+		case branch_gate:
+			flags |= CLK_SET_RATE_PARENT;
+
+			/* keep all gates untouched for now */
+			flags |= CLK_IGNORE_UNUSED;
+
+			clk = clk_register_gate(NULL, list->name,
+				list->parent_names[0], flags,
+				reg_base + list->gate_offset,
+				list->gate_shift, list->gate_flags, &clk_lock);
+			break;
+		case branch_composite:
+			/* keep all gates untouched for now */
+			flags |= CLK_IGNORE_UNUSED;
+
+			clk = rockchip_clk_register_branch(list->name,
+				list->parent_names, list->num_parents,
+				reg_base, list->muxdiv_offset, list->mux_shift,
+				list->mux_width, list->mux_flags,
+				list->div_shift, list->div_width,
+				list->div_flags, list->div_table,
+				list->gate_offset, list->gate_shift,
+				list->gate_flags, flags, &clk_lock);
+			break;
+		}
+
+		/* none of the cases above matched */
+		if (!clk) {
+			pr_err("%s: unknown clock type %d\n",
+			       __func__, list->branch_type);
+			continue;
+		}
+
+		if (IS_ERR(clk)) {
+			pr_err("%s: failed to register clock %s: %ld\n",
+			       __func__, list->name, PTR_ERR(clk));
+			continue;
+		}
+
+		rockchip_clk_add_lookup(clk, list->id);
+	}
+}
diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h
new file mode 100644
index 00000000000..887cbdeca2a
--- /dev/null
+++ b/drivers/clk/rockchip/clk.h
@@ -0,0 +1,347 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * based on
+ *
+ * samsung/clk.h
+ * Copyright (c) 2013 Samsung Electronics Co., Ltd.
+ * Copyright (c) 2013 Linaro Ltd.
+ * Author: Thomas Abraham <thomas.ab@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef CLK_ROCKCHIP_CLK_H
+#define CLK_ROCKCHIP_CLK_H
+
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+
+#define HIWORD_UPDATE(val, mask, shift) \
+		((val) << (shift) | (mask) << ((shift) + 16))
+
+/* register positions shared by RK2928, RK3066 and RK3188 */
+#define RK2928_PLL_CON(x)		(x * 0x4)
+#define RK2928_MODE_CON		0x40
+#define RK2928_CLKSEL_CON(x)	(x * 0x4 + 0x44)
+#define RK2928_CLKGATE_CON(x)	(x * 0x4 + 0xd0)
+#define RK2928_GLB_SRST_FST		0x100
+#define RK2928_GLB_SRST_SND		0x104
+#define RK2928_SOFTRST_CON(x)	(x * 0x4 + 0x110)
+#define RK2928_MISC_CON		0x134
+
+#define RK3288_PLL_CON(x)		RK2928_PLL_CON(x)
+#define RK3288_MODE_CON			0x50
+#define RK3288_CLKSEL_CON(x)		(x * 0x4 + 0x60)
+#define RK3288_CLKGATE_CON(x)		(x * 0x4 + 0x160)
+#define RK3288_GLB_SRST_FST		0x1b0
+#define RK3288_GLB_SRST_SND		0x1b4
+#define RK3288_SOFTRST_CON(x)		(x * 0x4 + 0x1b8)
+#define RK3288_MISC_CON			0x1e8
+
+enum rockchip_pll_type {
+	pll_rk3066,
+};
+
+#define RK3066_PLL_RATE(_rate, _nr, _nf, _no)	\
+{						\
+	.rate	= _rate##U,			\
+	.nr = _nr,				\
+	.nf = _nf,				\
+	.no = _no,				\
+	.bwadj = (_nf >> 1),			\
+}
+
+struct rockchip_pll_rate_table {
+	unsigned long rate;
+	unsigned int nr;
+	unsigned int nf;
+	unsigned int no;
+	unsigned int bwadj;
+};
+
+/**
+ * struct rockchip_pll_clock: information about pll clock
+ * @id: platform specific id of the clock.
+ * @name: name of this pll clock.
+ * @parent_name: name of the parent clock.
+ * @flags: optional flags for basic clock.
+ * @con_offset: offset of the register for configuring the PLL.
+ * @mode_offset: offset of the register for configuring the PLL-mode.
+ * @mode_shift: offset inside the mode-register for the mode of this pll.
+ * @lock_shift: offset inside the lock register for the lock status.
+ * @type: Type of PLL to be registered.
+ * @rate_table: Table of usable pll rates
+ */
+struct rockchip_pll_clock {
+	unsigned int		id;
+	const char		*name;
+	const char		**parent_names;
+	u8			num_parents;
+	unsigned long		flags;
+	int			con_offset;
+	int			mode_offset;
+	int			mode_shift;
+	int			lock_shift;
+	enum rockchip_pll_type	type;
+	struct rockchip_pll_rate_table *rate_table;
+};
+
+#define PLL(_type, _id, _name, _pnames, _flags, _con, _mode, _mshift,	\
+		_lshift, _rtable)					\
+	{								\
+		.id		= _id,					\
+		.type		= _type,				\
+		.name		= _name,				\
+		.parent_names	= _pnames,				\
+		.num_parents	= ARRAY_SIZE(_pnames),			\
+		.flags		= CLK_GET_RATE_NOCACHE | _flags,	\
+		.con_offset	= _con,					\
+		.mode_offset	= _mode,				\
+		.mode_shift	= _mshift,				\
+		.lock_shift	= _lshift,				\
+		.rate_table	= _rtable,				\
+	}
+
+struct clk *rockchip_clk_register_pll(enum rockchip_pll_type pll_type,
+		const char *name, const char **parent_names, u8 num_parents,
+		void __iomem *base, int con_offset, int grf_lock_offset,
+		int lock_shift, int reg_mode, int mode_shift,
+		struct rockchip_pll_rate_table *rate_table,
+		spinlock_t *lock);
+
+#define PNAME(x) static const char *x[] __initconst
+
+enum rockchip_clk_branch_type {
+	branch_composite,
+	branch_mux,
+	branch_divider,
+	branch_fraction_divider,
+	branch_gate,
+};
+
+struct rockchip_clk_branch {
+	unsigned int			id;
+	enum rockchip_clk_branch_type	branch_type;
+	const char			*name;
+	const char			**parent_names;
+	u8				num_parents;
+	unsigned long			flags;
+	int				muxdiv_offset;
+	u8				mux_shift;
+	u8				mux_width;
+	u8				mux_flags;
+	u8				div_shift;
+	u8				div_width;
+	u8				div_flags;
+	struct clk_div_table		*div_table;
+	int				gate_offset;
+	u8				gate_shift;
+	u8				gate_flags;
+};
+
+#define COMPOSITE(_id, cname, pnames, f, mo, ms, mw, mf, ds, dw,\
+		  df, go, gs, gf)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_composite,		\
+		.name		= cname,			\
+		.parent_names	= pnames,			\
+		.num_parents	= ARRAY_SIZE(pnames),		\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.mux_shift	= ms,				\
+		.mux_width	= mw,				\
+		.mux_flags	= mf,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.gate_offset	= go,				\
+		.gate_shift	= gs,				\
+		.gate_flags	= gf,				\
+	}
+
+#define COMPOSITE_NOMUX(_id, cname, pname, f, mo, ds, dw, df,	\
+			go, gs, gf)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_composite,		\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.gate_offset	= go,				\
+		.gate_shift	= gs,				\
+		.gate_flags	= gf,				\
+	}
+
+#define COMPOSITE_NOMUX_DIVTBL(_id, cname, pname, f, mo, ds, dw,\
+			       df, dt, go, gs, gf)		\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_composite,		\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.div_table	= dt,				\
+		.gate_offset	= go,				\
+		.gate_shift	= gs,				\
+		.gate_flags	= gf,				\
+	}
+
+#define COMPOSITE_NODIV(_id, cname, pnames, f, mo, ms, mw, mf,	\
+			go, gs, gf)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_composite,		\
+		.name		= cname,			\
+		.parent_names	= pnames,			\
+		.num_parents	= ARRAY_SIZE(pnames),		\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.mux_shift	= ms,				\
+		.mux_width	= mw,				\
+		.mux_flags	= mf,				\
+		.gate_offset	= go,				\
+		.gate_shift	= gs,				\
+		.gate_flags	= gf,				\
+	}
+
+#define COMPOSITE_NOGATE(_id, cname, pnames, f, mo, ms, mw, mf,	\
+			 ds, dw, df)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_composite,		\
+		.name		= cname,			\
+		.parent_names	= pnames,			\
+		.num_parents	= ARRAY_SIZE(pnames),		\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.mux_shift	= ms,				\
+		.mux_width	= mw,				\
+		.mux_flags	= mf,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.gate_offset	= -1,				\
+	}
+
+#define COMPOSITE_FRAC(_id, cname, pname, f, mo, df, go, gs, gf)\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_fraction_divider,	\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.div_shift	= 16,				\
+		.div_width	= 16,				\
+		.div_flags	= df,				\
+		.gate_offset	= go,				\
+		.gate_shift	= gs,				\
+		.gate_flags	= gf,				\
+	}
+
+#define MUX(_id, cname, pnames, f, o, s, w, mf)			\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_mux,			\
+		.name		= cname,			\
+		.parent_names	= pnames,			\
+		.num_parents	= ARRAY_SIZE(pnames),		\
+		.flags		= f,				\
+		.muxdiv_offset	= o,				\
+		.mux_shift	= s,				\
+		.mux_width	= w,				\
+		.mux_flags	= mf,				\
+		.gate_offset	= -1,				\
+	}
+
+#define DIV(_id, cname, pname, f, o, s, w, df)			\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_divider,		\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= o,				\
+		.div_shift	= s,				\
+		.div_width	= w,				\
+		.div_flags	= df,				\
+		.gate_offset	= -1,				\
+	}
+
+#define DIVTBL(_id, cname, pname, f, o, s, w, df, dt)		\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_divider,		\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= o,				\
+		.div_shift	= s,				\
+		.div_width	= w,				\
+		.div_flags	= df,				\
+		.div_table	= dt,				\
+	}
+
+#define GATE(_id, cname, pname, f, o, b, gf)			\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_gate,			\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.gate_offset	= o,				\
+		.gate_shift	= b,				\
+		.gate_flags	= gf,				\
+	}
+
+
+void rockchip_clk_init(struct device_node *np, void __iomem *base,
+		       unsigned long nr_clks);
+struct regmap *rockchip_clk_get_grf(void);
+void rockchip_clk_add_lookup(struct clk *clk, unsigned int id);
+void rockchip_clk_register_branches(struct rockchip_clk_branch *clk_list,
+				    unsigned int nr_clk);
+void rockchip_clk_register_plls(struct rockchip_pll_clock *pll_list,
+				unsigned int nr_pll, int grf_lock_offset);
+
+#define ROCKCHIP_SOFTRST_HIWORD_MASK	BIT(0)
+
+#ifdef CONFIG_RESET_CONTROLLER
+void rockchip_register_softrst(struct device_node *np,
+			       unsigned int num_regs,
+			       void __iomem *base, u8 flags);
+#else
+static inline void rockchip_register_softrst(struct device_node *np,
+			       unsigned int num_regs,
+			       void __iomem *base, u8 flags)
+{
+}
+#endif
+
+#endif
diff --git a/drivers/clk/rockchip/softrst.c b/drivers/clk/rockchip/softrst.c
new file mode 100644
index 00000000000..552f7bb15bc
--- /dev/null
+++ b/drivers/clk/rockchip/softrst.c
@@ -0,0 +1,118 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/reset-controller.h>
+#include <linux/spinlock.h>
+#include "clk.h"
+
+struct rockchip_softrst {
+	struct reset_controller_dev	rcdev;
+	void __iomem			*reg_base;
+	int				num_regs;
+	int				num_per_reg;
+	u8				flags;
+	spinlock_t			lock;
+};
+
+static int rockchip_softrst_assert(struct reset_controller_dev *rcdev,
+			      unsigned long id)
+{
+	struct rockchip_softrst *softrst = container_of(rcdev,
+						     struct rockchip_softrst,
+						     rcdev);
+	int bank = id / softrst->num_per_reg;
+	int offset = id % softrst->num_per_reg;
+
+	if (softrst->flags & ROCKCHIP_SOFTRST_HIWORD_MASK) {
+		writel(BIT(offset) | (BIT(offset) << 16),
+		       softrst->reg_base + (bank * 4));
+	} else {
+		unsigned long flags;
+		u32 reg;
+
+		spin_lock_irqsave(&softrst->lock, flags);
+
+		reg = readl(softrst->reg_base + (bank * 4));
+		writel(reg | BIT(offset), softrst->reg_base + (bank * 4));
+
+		spin_unlock_irqrestore(&softrst->lock, flags);
+	}
+
+	return 0;
+}
+
+static int rockchip_softrst_deassert(struct reset_controller_dev *rcdev,
+				unsigned long id)
+{
+	struct rockchip_softrst *softrst = container_of(rcdev,
+						     struct rockchip_softrst,
+						     rcdev);
+	int bank = id / softrst->num_per_reg;
+	int offset = id % softrst->num_per_reg;
+
+	if (softrst->flags & ROCKCHIP_SOFTRST_HIWORD_MASK) {
+		writel((BIT(offset) << 16), softrst->reg_base + (bank * 4));
+	} else {
+		unsigned long flags;
+		u32 reg;
+
+		spin_lock_irqsave(&softrst->lock, flags);
+
+		reg = readl(softrst->reg_base + (bank * 4));
+		writel(reg & ~BIT(offset), softrst->reg_base + (bank * 4));
+
+		spin_unlock_irqrestore(&softrst->lock, flags);
+	}
+
+	return 0;
+}
+
+static struct reset_control_ops rockchip_softrst_ops = {
+	.assert		= rockchip_softrst_assert,
+	.deassert	= rockchip_softrst_deassert,
+};
+
+void __init rockchip_register_softrst(struct device_node *np,
+				      unsigned int num_regs,
+				      void __iomem *base, u8 flags)
+{
+	struct rockchip_softrst *softrst;
+	int ret;
+
+	softrst = kzalloc(sizeof(*softrst), GFP_KERNEL);
+	if (!softrst)
+		return;
+
+	spin_lock_init(&softrst->lock);
+
+	softrst->reg_base = base;
+	softrst->flags = flags;
+	softrst->num_regs = num_regs;
+	softrst->num_per_reg = (flags & ROCKCHIP_SOFTRST_HIWORD_MASK) ? 16
+								      : 32;
+
+	softrst->rcdev.owner = THIS_MODULE;
+	softrst->rcdev.nr_resets =  num_regs * softrst->num_per_reg;
+	softrst->rcdev.ops = &rockchip_softrst_ops;
+	softrst->rcdev.of_node = np;
+	ret = reset_controller_register(&softrst->rcdev);
+	if (ret) {
+		pr_err("%s: could not register reset controller, %d\n",
+		       __func__, ret);
+		kfree(softrst);
+	}
+};
diff --git a/drivers/clk/samsung/Makefile b/drivers/clk/samsung/Makefile
index 69e81773164..2949a556af8 100644
--- a/drivers/clk/samsung/Makefile
+++ b/drivers/clk/samsung/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_SOC_EXYNOS5410)	+= clk-exynos5410.o
 obj-$(CONFIG_SOC_EXYNOS5420)	+= clk-exynos5420.o
 obj-$(CONFIG_SOC_EXYNOS5440)	+= clk-exynos5440.o
 obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-audss.o
+obj-$(CONFIG_ARCH_EXYNOS)	+= clk-exynos-clkout.o
 obj-$(CONFIG_S3C2410_COMMON_CLK)+= clk-s3c2410.o
 obj-$(CONFIG_S3C2410_COMMON_DCLK)+= clk-s3c2410-dclk.o
 obj-$(CONFIG_S3C2412_COMMON_CLK)+= clk-s3c2412.o
diff --git a/drivers/clk/samsung/clk-exynos-clkout.c b/drivers/clk/samsung/clk-exynos-clkout.c
new file mode 100644
index 00000000000..3a7cb250673
--- /dev/null
+++ b/drivers/clk/samsung/clk-exynos-clkout.c
@@ -0,0 +1,153 @@
+/*
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd.
+ * Author: Tomasz Figa <t.figa@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Clock driver for Exynos clock output
+ */
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/syscore_ops.h>
+
+#define EXYNOS_CLKOUT_NR_CLKS		1
+#define EXYNOS_CLKOUT_PARENTS		32
+
+#define EXYNOS_PMU_DEBUG_REG		0xa00
+#define EXYNOS_CLKOUT_DISABLE_SHIFT	0
+#define EXYNOS_CLKOUT_MUX_SHIFT		8
+#define EXYNOS4_CLKOUT_MUX_MASK		0xf
+#define EXYNOS5_CLKOUT_MUX_MASK		0x1f
+
+struct exynos_clkout {
+	struct clk_gate gate;
+	struct clk_mux mux;
+	spinlock_t slock;
+	struct clk_onecell_data data;
+	struct clk *clk_table[EXYNOS_CLKOUT_NR_CLKS];
+	void __iomem *reg;
+	u32 pmu_debug_save;
+};
+
+static struct exynos_clkout *clkout;
+
+static int exynos_clkout_suspend(void)
+{
+	clkout->pmu_debug_save = readl(clkout->reg + EXYNOS_PMU_DEBUG_REG);
+
+	return 0;
+}
+
+static void exynos_clkout_resume(void)
+{
+	writel(clkout->pmu_debug_save, clkout->reg + EXYNOS_PMU_DEBUG_REG);
+}
+
+static struct syscore_ops exynos_clkout_syscore_ops = {
+	.suspend = exynos_clkout_suspend,
+	.resume = exynos_clkout_resume,
+};
+
+static void __init exynos_clkout_init(struct device_node *node, u32 mux_mask)
+{
+	const char *parent_names[EXYNOS_CLKOUT_PARENTS];
+	struct clk *parents[EXYNOS_CLKOUT_PARENTS];
+	int parent_count;
+	int ret;
+	int i;
+
+	clkout = kzalloc(sizeof(*clkout), GFP_KERNEL);
+	if (!clkout)
+		return;
+
+	spin_lock_init(&clkout->slock);
+
+	parent_count = 0;
+	for (i = 0; i < EXYNOS_CLKOUT_PARENTS; ++i) {
+		char name[] = "clkoutXX";
+
+		snprintf(name, sizeof(name), "clkout%d", i);
+		parents[i] = of_clk_get_by_name(node, name);
+		if (IS_ERR(parents[i])) {
+			parent_names[i] = "none";
+			continue;
+		}
+
+		parent_names[i] = __clk_get_name(parents[i]);
+		parent_count = i + 1;
+	}
+
+	if (!parent_count)
+		goto free_clkout;
+
+	clkout->reg = of_iomap(node, 0);
+	if (!clkout->reg)
+		goto clks_put;
+
+	clkout->gate.reg = clkout->reg + EXYNOS_PMU_DEBUG_REG;
+	clkout->gate.bit_idx = EXYNOS_CLKOUT_DISABLE_SHIFT;
+	clkout->gate.flags = CLK_GATE_SET_TO_DISABLE;
+	clkout->gate.lock = &clkout->slock;
+
+	clkout->mux.reg = clkout->reg + EXYNOS_PMU_DEBUG_REG;
+	clkout->mux.mask = mux_mask;
+	clkout->mux.shift = EXYNOS_CLKOUT_MUX_SHIFT;
+	clkout->mux.lock = &clkout->slock;
+
+	clkout->clk_table[0] = clk_register_composite(NULL, "clkout",
+				parent_names, parent_count, &clkout->mux.hw,
+				&clk_mux_ops, NULL, NULL, &clkout->gate.hw,
+				&clk_gate_ops, CLK_SET_RATE_PARENT
+				| CLK_SET_RATE_NO_REPARENT);
+	if (IS_ERR(clkout->clk_table[0]))
+		goto err_unmap;
+
+	clkout->data.clks = clkout->clk_table;
+	clkout->data.clk_num = EXYNOS_CLKOUT_NR_CLKS;
+	ret = of_clk_add_provider(node, of_clk_src_onecell_get, &clkout->data);
+	if (ret)
+		goto err_clk_unreg;
+
+	register_syscore_ops(&exynos_clkout_syscore_ops);
+
+	return;
+
+err_clk_unreg:
+	clk_unregister(clkout->clk_table[0]);
+err_unmap:
+	iounmap(clkout->reg);
+clks_put:
+	for (i = 0; i < EXYNOS_CLKOUT_PARENTS; ++i)
+		if (!IS_ERR(parents[i]))
+			clk_put(parents[i]);
+free_clkout:
+	kfree(clkout);
+
+	pr_err("%s: failed to register clkout clock\n", __func__);
+}
+
+static void __init exynos4_clkout_init(struct device_node *node)
+{
+	exynos_clkout_init(node, EXYNOS4_CLKOUT_MUX_MASK);
+}
+CLK_OF_DECLARE(exynos4210_clkout, "samsung,exynos4210-pmu",
+		exynos4_clkout_init);
+CLK_OF_DECLARE(exynos4212_clkout, "samsung,exynos4212-pmu",
+		exynos4_clkout_init);
+CLK_OF_DECLARE(exynos4412_clkout, "samsung,exynos4412-pmu",
+		exynos4_clkout_init);
+
+static void __init exynos5_clkout_init(struct device_node *node)
+{
+	exynos_clkout_init(node, EXYNOS5_CLKOUT_MUX_MASK);
+}
+CLK_OF_DECLARE(exynos5250_clkout, "samsung,exynos5250-pmu",
+		exynos5_clkout_init);
+CLK_OF_DECLARE(exynos5420_clkout, "samsung,exynos5420-pmu",
+		exynos5_clkout_init);
diff --git a/drivers/clk/samsung/clk-exynos3250.c b/drivers/clk/samsung/clk-exynos3250.c
index 7a17bd40d1d..dc85f8e7a2d 100644
--- a/drivers/clk/samsung/clk-exynos3250.c
+++ b/drivers/clk/samsung/clk-exynos3250.c
@@ -87,6 +87,22 @@
 #define SRC_CPU			0x14200
 #define DIV_CPU0		0x14500
 #define DIV_CPU1		0x14504
+#define PWR_CTRL1		0x15020
+#define PWR_CTRL2		0x15024
+
+/* Below definitions are used for PWR_CTRL settings */
+#define PWR_CTRL1_CORE2_DOWN_RATIO(x)		(((x) & 0x7) << 28)
+#define PWR_CTRL1_CORE1_DOWN_RATIO(x)		(((x) & 0x7) << 16)
+#define PWR_CTRL1_DIV2_DOWN_EN			(1 << 9)
+#define PWR_CTRL1_DIV1_DOWN_EN			(1 << 8)
+#define PWR_CTRL1_USE_CORE3_WFE			(1 << 7)
+#define PWR_CTRL1_USE_CORE2_WFE			(1 << 6)
+#define PWR_CTRL1_USE_CORE1_WFE			(1 << 5)
+#define PWR_CTRL1_USE_CORE0_WFE			(1 << 4)
+#define PWR_CTRL1_USE_CORE3_WFI			(1 << 3)
+#define PWR_CTRL1_USE_CORE2_WFI			(1 << 2)
+#define PWR_CTRL1_USE_CORE1_WFI			(1 << 1)
+#define PWR_CTRL1_USE_CORE0_WFI			(1 << 0)
 
 /* list of PLLs to be registered */
 enum exynos3250_plls {
@@ -168,6 +184,8 @@ static unsigned long exynos3250_cmu_clk_regs[] __initdata = {
 	SRC_CPU,
 	DIV_CPU0,
 	DIV_CPU1,
+	PWR_CTRL1,
+	PWR_CTRL2,
 };
 
 static int exynos3250_clk_suspend(void)
@@ -748,6 +766,27 @@ static struct samsung_pll_clock exynos3250_plls[nr_plls] __initdata = {
 			UPLL_LOCK, UPLL_CON0, NULL),
 };
 
+static void __init exynos3_core_down_clock(void)
+{
+	unsigned int tmp;
+
+	/*
+	 * Enable arm clock down (in idle) and set arm divider
+	 * ratios in WFI/WFE state.
+	 */
+	tmp = (PWR_CTRL1_CORE2_DOWN_RATIO(7) | PWR_CTRL1_CORE1_DOWN_RATIO(7) |
+		PWR_CTRL1_DIV2_DOWN_EN | PWR_CTRL1_DIV1_DOWN_EN |
+		PWR_CTRL1_USE_CORE1_WFE | PWR_CTRL1_USE_CORE0_WFE |
+		PWR_CTRL1_USE_CORE1_WFI | PWR_CTRL1_USE_CORE0_WFI);
+	__raw_writel(tmp, reg_base + PWR_CTRL1);
+
+	/*
+	 * Disable the clock up feature on Exynos4x12, in case it was
+	 * enabled by bootloader.
+	 */
+	__raw_writel(0x0, reg_base + PWR_CTRL2);
+}
+
 static void __init exynos3250_cmu_init(struct device_node *np)
 {
 	struct samsung_clk_provider *ctx;
@@ -775,6 +814,10 @@ static void __init exynos3250_cmu_init(struct device_node *np)
 	samsung_clk_register_div(ctx, div_clks, ARRAY_SIZE(div_clks));
 	samsung_clk_register_gate(ctx, gate_clks, ARRAY_SIZE(gate_clks));
 
+	exynos3_core_down_clock();
+
 	exynos3250_clk_sleep_init();
+
+	samsung_clk_of_add_provider(np, ctx);
 }
 CLK_OF_DECLARE(exynos3250_cmu, "samsung,exynos3250-cmu", exynos3250_cmu_init);
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index 4f150c9dd38..ac163d7f5bc 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -25,10 +25,12 @@
 #define DIV_LEFTBUS		0x4500
 #define GATE_IP_LEFTBUS		0x4800
 #define E4X12_GATE_IP_IMAGE	0x4930
+#define CLKOUT_CMU_LEFTBUS	0x4a00
 #define SRC_RIGHTBUS		0x8200
 #define DIV_RIGHTBUS		0x8500
 #define GATE_IP_RIGHTBUS	0x8800
 #define E4X12_GATE_IP_PERIR	0x8960
+#define CLKOUT_CMU_RIGHTBUS	0x8a00
 #define EPLL_LOCK		0xc010
 #define VPLL_LOCK		0xc020
 #define EPLL_CON0		0xc110
@@ -98,6 +100,7 @@
 #define GATE_IP_PERIL		0xc950
 #define E4210_GATE_IP_PERIR	0xc960
 #define GATE_BLOCK		0xc970
+#define CLKOUT_CMU_TOP		0xca00
 #define E4X12_MPLL_LOCK		0x10008
 #define E4X12_MPLL_CON0		0x10108
 #define SRC_DMC			0x10200
@@ -105,6 +108,7 @@
 #define DIV_DMC0		0x10500
 #define DIV_DMC1		0x10504
 #define GATE_IP_DMC		0x10900
+#define CLKOUT_CMU_DMC		0x10a00
 #define APLL_LOCK		0x14000
 #define E4210_MPLL_LOCK		0x14008
 #define APLL_CON0		0x14100
@@ -114,11 +118,28 @@
 #define DIV_CPU1		0x14504
 #define GATE_SCLK_CPU		0x14800
 #define GATE_IP_CPU		0x14900
+#define CLKOUT_CMU_CPU		0x14a00
+#define PWR_CTRL1		0x15020
+#define E4X12_PWR_CTRL2		0x15024
 #define E4X12_DIV_ISP0		0x18300
 #define E4X12_DIV_ISP1		0x18304
 #define E4X12_GATE_ISP0		0x18800
 #define E4X12_GATE_ISP1		0x18804
 
+/* Below definitions are used for PWR_CTRL settings */
+#define PWR_CTRL1_CORE2_DOWN_RATIO(x)		(((x) & 0x7) << 28)
+#define PWR_CTRL1_CORE1_DOWN_RATIO(x)		(((x) & 0x7) << 16)
+#define PWR_CTRL1_DIV2_DOWN_EN			(1 << 9)
+#define PWR_CTRL1_DIV1_DOWN_EN			(1 << 8)
+#define PWR_CTRL1_USE_CORE3_WFE			(1 << 7)
+#define PWR_CTRL1_USE_CORE2_WFE			(1 << 6)
+#define PWR_CTRL1_USE_CORE1_WFE			(1 << 5)
+#define PWR_CTRL1_USE_CORE0_WFE			(1 << 4)
+#define PWR_CTRL1_USE_CORE3_WFI			(1 << 3)
+#define PWR_CTRL1_USE_CORE2_WFI			(1 << 2)
+#define PWR_CTRL1_USE_CORE1_WFI			(1 << 1)
+#define PWR_CTRL1_USE_CORE0_WFI			(1 << 0)
+
 /* the exynos4 soc type */
 enum exynos4_soc {
 	EXYNOS4210,
@@ -155,6 +176,7 @@ static unsigned long exynos4210_clk_save[] __initdata = {
 	E4210_GATE_IP_LCD1,
 	E4210_GATE_IP_PERIR,
 	E4210_MPLL_CON0,
+	PWR_CTRL1,
 };
 
 static unsigned long exynos4x12_clk_save[] __initdata = {
@@ -164,6 +186,8 @@ static unsigned long exynos4x12_clk_save[] __initdata = {
 	E4X12_DIV_ISP,
 	E4X12_DIV_CAM1,
 	E4X12_MPLL_CON0,
+	PWR_CTRL1,
+	E4X12_PWR_CTRL2,
 };
 
 static unsigned long exynos4_clk_pll_regs[] __initdata = {
@@ -242,6 +266,11 @@ static unsigned long exynos4_clk_regs[] __initdata = {
 	DIV_CPU1,
 	GATE_SCLK_CPU,
 	GATE_IP_CPU,
+	CLKOUT_CMU_LEFTBUS,
+	CLKOUT_CMU_RIGHTBUS,
+	CLKOUT_CMU_TOP,
+	CLKOUT_CMU_DMC,
+	CLKOUT_CMU_CPU,
 };
 
 static const struct samsung_clk_reg_dump src_mask_suspend[] = {
@@ -397,10 +426,32 @@ PNAME(mout_audio2_p4210) = { "cdclk2", "none", "sclk_hdmi24m",
 				"sclk_epll", "sclk_vpll", };
 PNAME(mout_mixer_p4210)	= { "sclk_dac", "sclk_hdmi", };
 PNAME(mout_dac_p4210)	= { "sclk_vpll", "sclk_hdmiphy", };
+PNAME(mout_pwi_p4210) = { "xxti", "xusbxti", "sclk_hdmi24m", "sclk_usbphy0",
+				"sclk_usbphy1", "sclk_hdmiphy", "none",
+				"sclk_epll", "sclk_vpll" };
+PNAME(clkout_left_p4210) = { "sclk_mpll_div_2", "sclk_apll_div_2",
+				"div_gdl", "div_gpl" };
+PNAME(clkout_right_p4210) = { "sclk_mpll_div_2", "sclk_apll_div_2",
+				"div_gdr", "div_gpr" };
+PNAME(clkout_top_p4210) = { "fout_epll", "fout_vpll", "sclk_hdmi24m",
+				"sclk_usbphy0", "sclk_usbphy1", "sclk_hdmiphy",
+				"cdclk0", "cdclk1", "cdclk2", "spdif_extclk",
+				"aclk160", "aclk133", "aclk200", "aclk100",
+				"sclk_mfc", "sclk_g3d", "sclk_g2d",
+				"cam_a_pclk", "cam_b_pclk", "s_rxbyteclkhs0_2l",
+				"s_rxbyteclkhs0_4l" };
+PNAME(clkout_dmc_p4210) = { "div_dmcd", "div_dmcp", "div_acp_pclk", "div_dmc",
+				"div_dphy", "none", "div_pwi" };
+PNAME(clkout_cpu_p4210) = { "fout_apll_div_2", "none", "fout_mpll_div_2",
+				"none", "arm_clk_div_2", "div_corem0",
+				"div_corem1", "div_corem0", "div_atb",
+				"div_periph", "div_pclk_dbg", "div_hpm" };
 
 /* Exynos 4x12-specific parent groups */
 PNAME(mout_mpll_user_p4x12) = { "fin_pll", "sclk_mpll", };
 PNAME(mout_core_p4x12)	= { "mout_apll", "mout_mpll_user_c", };
+PNAME(mout_gdl_p4x12)	= { "mout_mpll_user_l", "sclk_apll", };
+PNAME(mout_gdr_p4x12)	= { "mout_mpll_user_r", "sclk_apll", };
 PNAME(sclk_ampll_p4x12)	= { "mout_mpll_user_t", "sclk_apll", };
 PNAME(group1_p4x12)	= { "xxti", "xusbxti", "sclk_hdmi24m", "sclk_usbphy0",
 				"none",	"sclk_hdmiphy", "mout_mpll_user_t",
@@ -418,6 +469,32 @@ PNAME(aclk_p4412)	= { "mout_mpll_user_t", "sclk_apll", };
 PNAME(mout_user_aclk400_mcuisp_p4x12) = {"fin_pll", "div_aclk400_mcuisp", };
 PNAME(mout_user_aclk200_p4x12) = {"fin_pll", "div_aclk200", };
 PNAME(mout_user_aclk266_gps_p4x12) = {"fin_pll", "div_aclk266_gps", };
+PNAME(mout_pwi_p4x12) = { "xxti", "xusbxti", "sclk_hdmi24m", "sclk_usbphy0",
+				"none", "sclk_hdmiphy", "sclk_mpll",
+				"sclk_epll", "sclk_vpll" };
+PNAME(clkout_left_p4x12) = { "sclk_mpll_user_l_div_2", "sclk_apll_div_2",
+				"div_gdl", "div_gpl" };
+PNAME(clkout_right_p4x12) = { "sclk_mpll_user_r_div_2", "sclk_apll_div_2",
+				"div_gdr", "div_gpr" };
+PNAME(clkout_top_p4x12) = { "fout_epll", "fout_vpll", "sclk_hdmi24m",
+				"sclk_usbphy0", "none", "sclk_hdmiphy",
+				"cdclk0", "cdclk1", "cdclk2", "spdif_extclk",
+				"aclk160", "aclk133", "aclk200", "aclk100",
+				"sclk_mfc", "sclk_g3d", "aclk400_mcuisp",
+				"cam_a_pclk", "cam_b_pclk", "s_rxbyteclkhs0_2l",
+				"s_rxbyteclkhs0_4l", "rx_half_byte_clk_csis0",
+				"rx_half_byte_clk_csis1", "div_jpeg",
+				"sclk_pwm_isp", "sclk_spi0_isp",
+				"sclk_spi1_isp", "sclk_uart_isp",
+				"sclk_mipihsi", "sclk_hdmi", "sclk_fimd0",
+				"sclk_pcm0" };
+PNAME(clkout_dmc_p4x12) = { "div_dmcd", "div_dmcp", "aclk_acp", "div_acp_pclk",
+				"div_dmc", "div_dphy", "fout_mpll_div_2",
+				"div_pwi", "none", "div_c2c", "div_c2c_aclk" };
+PNAME(clkout_cpu_p4x12) = { "fout_apll_div_2", "none", "none", "none",
+				"arm_clk_div_2", "div_corem0", "div_corem1",
+				"div_cores", "div_atb", "div_periph",
+				"div_pclk_dbg", "div_hpm" };
 
 /* fixed rate clocks generated outside the soc */
 static struct samsung_fixed_rate_clock exynos4_fixed_rate_ext_clks[] __initdata = {
@@ -436,6 +513,24 @@ static struct samsung_fixed_rate_clock exynos4210_fixed_rate_clks[] __initdata =
 	FRATE(0, "sclk_usbphy1", NULL, CLK_IS_ROOT, 48000000),
 };
 
+static struct samsung_fixed_factor_clock exynos4_fixed_factor_clks[] __initdata = {
+	FFACTOR(0, "sclk_apll_div_2", "sclk_apll", 1, 2, 0),
+	FFACTOR(0, "fout_mpll_div_2", "fout_mpll", 1, 2, 0),
+	FFACTOR(0, "fout_apll_div_2", "fout_apll", 1, 2, 0),
+	FFACTOR(0, "arm_clk_div_2", "arm_clk", 1, 2, 0),
+};
+
+static struct samsung_fixed_factor_clock exynos4210_fixed_factor_clks[] __initdata = {
+	FFACTOR(0, "sclk_mpll_div_2", "sclk_mpll", 1, 2, 0),
+};
+
+static struct samsung_fixed_factor_clock exynos4x12_fixed_factor_clks[] __initdata = {
+	FFACTOR(0, "sclk_mpll_user_l_div_2", "mout_mpll_user_l", 1, 2, 0),
+	FFACTOR(0, "sclk_mpll_user_r_div_2", "mout_mpll_user_r", 1, 2, 0),
+	FFACTOR(0, "sclk_mpll_user_t_div_2", "mout_mpll_user_t", 1, 2, 0),
+	FFACTOR(0, "sclk_mpll_user_c_div_2", "mout_mpll_user_c", 1, 2, 0),
+};
+
 /* list of mux clocks supported in all exynos4 soc's */
 static struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
 	MUX_FA(CLK_MOUT_APLL, "mout_apll", mout_apll_p, SRC_CPU, 0, 1,
@@ -451,6 +546,9 @@ static struct samsung_mux_clock exynos4_mux_clks[] __initdata = {
 	MUX(0, "mout_onenand1", mout_onenand1_p, SRC_TOP0, 0, 1),
 	MUX(CLK_SCLK_EPLL, "sclk_epll", mout_epll_p, SRC_TOP0, 4, 1),
 	MUX(0, "mout_onenand", mout_onenand_p, SRC_TOP0, 28, 1),
+
+	MUX(0, "mout_dmc_bus", sclk_ampll_p4210, SRC_DMC, 4, 1),
+	MUX(0, "mout_dphy", sclk_ampll_p4210, SRC_DMC, 8, 1),
 };
 
 /* list of mux clocks supported in exynos4210 soc */
@@ -459,6 +557,14 @@ static struct samsung_mux_clock exynos4210_mux_early[] __initdata = {
 };
 
 static struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
+	MUX(0, "mout_gdl", sclk_ampll_p4210, SRC_LEFTBUS, 0, 1),
+	MUX(0, "mout_clkout_leftbus", clkout_left_p4210,
+			CLKOUT_CMU_LEFTBUS, 0, 5),
+
+	MUX(0, "mout_gdr", sclk_ampll_p4210, SRC_RIGHTBUS, 0, 1),
+	MUX(0, "mout_clkout_rightbus", clkout_right_p4210,
+			CLKOUT_CMU_RIGHTBUS, 0, 5),
+
 	MUX(0, "mout_aclk200", sclk_ampll_p4210, SRC_TOP0, 12, 1),
 	MUX(0, "mout_aclk100", sclk_ampll_p4210, SRC_TOP0, 16, 1),
 	MUX(0, "mout_aclk160", sclk_ampll_p4210, SRC_TOP0, 20, 1),
@@ -472,6 +578,7 @@ static struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
 	MUX(0, "mout_mipi1", group1_p4210, E4210_SRC_LCD1, 12, 4),
 	MUX(CLK_SCLK_MPLL, "sclk_mpll", mout_mpll_p, SRC_CPU, 8, 1),
 	MUX(CLK_MOUT_CORE, "mout_core", mout_core_p4210, SRC_CPU, 16, 1),
+	MUX(0, "mout_hpm", mout_core_p4210, SRC_CPU, 20, 1),
 	MUX(CLK_SCLK_VPLL, "sclk_vpll", sclk_vpll_p4210, SRC_TOP0, 8, 1),
 	MUX(CLK_MOUT_FIMC0, "mout_fimc0", group1_p4210, SRC_CAM, 0, 4),
 	MUX(CLK_MOUT_FIMC1, "mout_fimc1", group1_p4210, SRC_CAM, 4, 4),
@@ -503,12 +610,30 @@ static struct samsung_mux_clock exynos4210_mux_clks[] __initdata = {
 	MUX(0, "mout_spi0", group1_p4210, SRC_PERIL1, 16, 4),
 	MUX(0, "mout_spi1", group1_p4210, SRC_PERIL1, 20, 4),
 	MUX(0, "mout_spi2", group1_p4210, SRC_PERIL1, 24, 4),
+	MUX(0, "mout_clkout_top", clkout_top_p4210, CLKOUT_CMU_TOP, 0, 5),
+
+	MUX(0, "mout_pwi", mout_pwi_p4210, SRC_DMC, 16, 4),
+	MUX(0, "mout_clkout_dmc", clkout_dmc_p4210, CLKOUT_CMU_DMC, 0, 5),
+
+	MUX(0, "mout_clkout_cpu", clkout_cpu_p4210, CLKOUT_CMU_CPU, 0, 5),
 };
 
 /* list of mux clocks supported in exynos4x12 soc */
 static struct samsung_mux_clock exynos4x12_mux_clks[] __initdata = {
+	MUX(0, "mout_mpll_user_l", mout_mpll_p, SRC_LEFTBUS, 4, 1),
+	MUX(0, "mout_gdl", mout_gdl_p4x12, SRC_LEFTBUS, 0, 1),
+	MUX(0, "mout_clkout_leftbus", clkout_left_p4x12,
+			CLKOUT_CMU_LEFTBUS, 0, 5),
+
+	MUX(0, "mout_mpll_user_r", mout_mpll_p, SRC_RIGHTBUS, 4, 1),
+	MUX(0, "mout_gdr", mout_gdr_p4x12, SRC_RIGHTBUS, 0, 1),
+	MUX(0, "mout_clkout_rightbus", clkout_right_p4x12,
+			CLKOUT_CMU_RIGHTBUS, 0, 5),
+
 	MUX(CLK_MOUT_MPLL_USER_C, "mout_mpll_user_c", mout_mpll_user_p4x12,
 			SRC_CPU, 24, 1),
+	MUX(0, "mout_clkout_cpu", clkout_cpu_p4x12, CLKOUT_CMU_CPU, 0, 5),
+
 	MUX(0, "mout_aclk266_gps", aclk_p4412, SRC_TOP1, 4, 1),
 	MUX(0, "mout_aclk400_mcuisp", aclk_p4412, SRC_TOP1, 8, 1),
 	MUX(CLK_MOUT_MPLL_USER_T, "mout_mpll_user_t", mout_mpll_user_p4x12,
@@ -531,6 +656,7 @@ static struct samsung_mux_clock exynos4x12_mux_clks[] __initdata = {
 	MUX(CLK_SCLK_MPLL, "sclk_mpll", mout_mpll_p, SRC_DMC, 12, 1),
 	MUX(CLK_SCLK_VPLL, "sclk_vpll", mout_vpll_p, SRC_TOP0, 8, 1),
 	MUX(CLK_MOUT_CORE, "mout_core", mout_core_p4x12, SRC_CPU, 16, 1),
+	MUX(0, "mout_hpm", mout_core_p4x12, SRC_CPU, 20, 1),
 	MUX(CLK_MOUT_FIMC0, "mout_fimc0", group1_p4x12, SRC_CAM, 0, 4),
 	MUX(CLK_MOUT_FIMC1, "mout_fimc1", group1_p4x12, SRC_CAM, 4, 4),
 	MUX(CLK_MOUT_FIMC2, "mout_fimc2", group1_p4x12, SRC_CAM, 8, 4),
@@ -565,15 +691,39 @@ static struct samsung_mux_clock exynos4x12_mux_clks[] __initdata = {
 	MUX(0, "mout_spi0_isp", group1_p4x12, E4X12_SRC_ISP, 4, 4),
 	MUX(0, "mout_spi1_isp", group1_p4x12, E4X12_SRC_ISP, 8, 4),
 	MUX(0, "mout_uart_isp", group1_p4x12, E4X12_SRC_ISP, 12, 4),
+	MUX(0, "mout_clkout_top", clkout_top_p4x12, CLKOUT_CMU_TOP, 0, 5),
+
+	MUX(0, "mout_c2c", sclk_ampll_p4210, SRC_DMC, 0, 1),
+	MUX(0, "mout_pwi", mout_pwi_p4x12, SRC_DMC, 16, 4),
 	MUX(0, "mout_g2d0", sclk_ampll_p4210, SRC_DMC, 20, 1),
 	MUX(0, "mout_g2d1", sclk_evpll_p, SRC_DMC, 24, 1),
 	MUX(0, "mout_g2d", mout_g2d_p, SRC_DMC, 28, 1),
+	MUX(0, "mout_clkout_dmc", clkout_dmc_p4x12, CLKOUT_CMU_DMC, 0, 5),
 };
 
 /* list of divider clocks supported in all exynos4 soc's */
 static struct samsung_div_clock exynos4_div_clks[] __initdata = {
+	DIV(0, "div_gdl", "mout_gdl", DIV_LEFTBUS, 0, 3),
+	DIV(0, "div_gpl", "div_gdl", DIV_LEFTBUS, 4, 3),
+	DIV(0, "div_clkout_leftbus", "mout_clkout_leftbus",
+			CLKOUT_CMU_LEFTBUS, 8, 6),
+
+	DIV(0, "div_gdr", "mout_gdr", DIV_RIGHTBUS, 0, 3),
+	DIV(0, "div_gpr", "div_gdr", DIV_RIGHTBUS, 4, 3),
+	DIV(0, "div_clkout_rightbus", "mout_clkout_rightbus",
+			CLKOUT_CMU_RIGHTBUS, 8, 6),
+
 	DIV(0, "div_core", "mout_core", DIV_CPU0, 0, 3),
+	DIV(0, "div_corem0", "div_core2", DIV_CPU0, 4, 3),
+	DIV(0, "div_corem1", "div_core2", DIV_CPU0, 8, 3),
+	DIV(0, "div_periph", "div_core2", DIV_CPU0, 12, 3),
+	DIV(0, "div_atb", "mout_core", DIV_CPU0, 16, 3),
+	DIV(0, "div_pclk_dbg", "div_atb", DIV_CPU0, 20, 3),
 	DIV(0, "div_core2", "div_core", DIV_CPU0, 28, 3),
+	DIV(0, "div_copy", "mout_hpm", DIV_CPU1, 0, 3),
+	DIV(0, "div_hpm", "div_copy", DIV_CPU1, 4, 3),
+	DIV(0, "div_clkout_cpu", "mout_clkout_cpu", CLKOUT_CMU_CPU, 8, 6),
+
 	DIV(0, "div_fimc0", "mout_fimc0", DIV_CAM, 0, 4),
 	DIV(0, "div_fimc1", "mout_fimc1", DIV_CAM, 4, 4),
 	DIV(0, "div_fimc2", "mout_fimc2", DIV_CAM, 8, 4),
@@ -631,6 +781,16 @@ static struct samsung_div_clock exynos4_div_clks[] __initdata = {
 			CLK_SET_RATE_PARENT, 0),
 	DIV_F(0, "div_mmc_pre3", "div_mmc3", DIV_FSYS2, 24, 8,
 			CLK_SET_RATE_PARENT, 0),
+	DIV(0, "div_clkout_top", "mout_clkout_top", CLKOUT_CMU_TOP, 8, 6),
+
+	DIV(0, "div_acp", "mout_dmc_bus", DIV_DMC0, 0, 3),
+	DIV(0, "div_acp_pclk", "div_acp", DIV_DMC0, 4, 3),
+	DIV(0, "div_dphy", "mout_dphy", DIV_DMC0, 8, 3),
+	DIV(0, "div_dmc", "mout_dmc_bus", DIV_DMC0, 12, 3),
+	DIV(0, "div_dmcd", "div_dmc", DIV_DMC0, 16, 3),
+	DIV(0, "div_dmcp", "div_dmcd", DIV_DMC0, 20, 3),
+	DIV(0, "div_pwi", "mout_pwi", DIV_DMC1, 8, 4),
+	DIV(0, "div_clkout_dmc", "mout_clkout_dmc", CLKOUT_CMU_DMC, 8, 6),
 };
 
 /* list of divider clocks supported in exynos4210 soc */
@@ -671,6 +831,8 @@ static struct samsung_div_clock exynos4x12_div_clks[] __initdata = {
 	DIV_F(CLK_DIV_MCUISP1, "div_mcuisp1", "div_mcuisp0", E4X12_DIV_ISP1,
 						8, 3, CLK_GET_RATE_NOCACHE, 0),
 	DIV(CLK_SCLK_FIMG2D, "sclk_fimg2d", "mout_g2d", DIV_DMC1, 0, 4),
+	DIV(0, "div_c2c", "mout_c2c", DIV_DMC1, 4, 3),
+	DIV(0, "div_c2c_aclk", "div_c2c", DIV_DMC1, 12, 3),
 };
 
 /* list of gate clocks supported in all exynos4 soc's */
@@ -680,6 +842,8 @@ static struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
 	 * the device name and clock alias names specified below for some
 	 * of the clocks can be removed.
 	 */
+	GATE(CLK_PPMULEFT, "ppmuleft", "aclk200", GATE_IP_LEFTBUS, 1, 0, 0),
+	GATE(CLK_PPMURIGHT, "ppmuright", "aclk200", GATE_IP_RIGHTBUS, 1, 0, 0),
 	GATE(CLK_SCLK_HDMI, "sclk_hdmi", "mout_hdmi", SRC_MASK_TV, 0, 0, 0),
 	GATE(CLK_SCLK_SPDIF, "sclk_spdif", "mout_spdif", SRC_MASK_PERIL1, 8, 0,
 		0),
@@ -695,11 +859,13 @@ static struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
 	GATE(CLK_SROMC, "sromc", "aclk133", GATE_IP_FSYS, 11, 0, 0),
 	GATE(CLK_SCLK_G3D, "sclk_g3d", "div_g3d", GATE_IP_G3D, 0,
 			CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_PPMUG3D, "ppmug3d", "aclk200", GATE_IP_G3D, 1, 0, 0),
 	GATE(CLK_USB_DEVICE, "usb_device", "aclk133", GATE_IP_FSYS, 13, 0, 0),
 	GATE(CLK_ONENAND, "onenand", "aclk133", GATE_IP_FSYS, 15, 0, 0),
 	GATE(CLK_NFCON, "nfcon", "aclk133", GATE_IP_FSYS, 16, 0, 0),
 	GATE(CLK_GPS, "gps", "aclk133", GATE_IP_GPS, 0, 0, 0),
 	GATE(CLK_SMMU_GPS, "smmu_gps", "aclk133", GATE_IP_GPS, 1, 0, 0),
+	GATE(CLK_PPMUGPS, "ppmugps", "aclk200", GATE_IP_GPS, 2, 0, 0),
 	GATE(CLK_SLIMBUS, "slimbus", "aclk100", GATE_IP_PERIL, 25, 0, 0),
 	GATE(CLK_SCLK_CAM0, "sclk_cam0", "div_cam0", GATE_SCLK_CAM, 4,
 			CLK_SET_RATE_PARENT, 0),
@@ -781,19 +947,24 @@ static struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
 			0, 0),
 	GATE(CLK_SMMU_JPEG, "smmu_jpeg", "aclk160", GATE_IP_CAM, 11,
 			0, 0),
+	GATE(CLK_PPMUCAMIF, "ppmucamif", "aclk160", GATE_IP_CAM, 16, 0, 0),
 	GATE(CLK_PIXELASYNCM0, "pxl_async0", "aclk160", GATE_IP_CAM, 17, 0, 0),
 	GATE(CLK_PIXELASYNCM1, "pxl_async1", "aclk160", GATE_IP_CAM, 18, 0, 0),
 	GATE(CLK_SMMU_TV, "smmu_tv", "aclk160", GATE_IP_TV, 4,
 			0, 0),
+	GATE(CLK_PPMUTV, "ppmutv", "aclk160", GATE_IP_TV, 5, 0, 0),
 	GATE(CLK_MFC, "mfc", "aclk100", GATE_IP_MFC, 0, 0, 0),
 	GATE(CLK_SMMU_MFCL, "smmu_mfcl", "aclk100", GATE_IP_MFC, 1,
 			0, 0),
 	GATE(CLK_SMMU_MFCR, "smmu_mfcr", "aclk100", GATE_IP_MFC, 2,
 			0, 0),
+	GATE(CLK_PPMUMFC_L, "ppmumfc_l", "aclk100", GATE_IP_MFC, 3, 0, 0),
+	GATE(CLK_PPMUMFC_R, "ppmumfc_r", "aclk100", GATE_IP_MFC, 4, 0, 0),
 	GATE(CLK_FIMD0, "fimd0", "aclk160", GATE_IP_LCD0, 0,
 			0, 0),
 	GATE(CLK_SMMU_FIMD0, "smmu_fimd0", "aclk160", GATE_IP_LCD0, 4,
 			0, 0),
+	GATE(CLK_PPMULCD0, "ppmulcd0", "aclk160", GATE_IP_LCD0, 5, 0, 0),
 	GATE(CLK_PDMA0, "pdma0", "aclk133", GATE_IP_FSYS, 0,
 			0, 0),
 	GATE(CLK_PDMA1, "pdma1", "aclk133", GATE_IP_FSYS, 1,
@@ -806,6 +977,7 @@ static struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
 			0, 0),
 	GATE(CLK_SDMMC3, "sdmmc3", "aclk133", GATE_IP_FSYS, 8,
 			0, 0),
+	GATE(CLK_PPMUFILE, "ppmufile", "aclk133", GATE_IP_FSYS, 17, 0, 0),
 	GATE(CLK_UART0, "uart0", "aclk100", GATE_IP_PERIL, 0,
 			0, 0),
 	GATE(CLK_UART1, "uart1", "aclk100", GATE_IP_PERIL, 1,
@@ -852,6 +1024,21 @@ static struct samsung_gate_clock exynos4_gate_clks[] __initdata = {
 			0, 0),
 	GATE(CLK_AC97, "ac97", "aclk100", GATE_IP_PERIL, 27,
 			0, 0),
+	GATE(CLK_PPMUDMC0, "ppmudmc0", "aclk133", GATE_IP_DMC, 8, 0, 0),
+	GATE(CLK_PPMUDMC1, "ppmudmc1", "aclk133", GATE_IP_DMC, 9, 0, 0),
+	GATE(CLK_PPMUCPU, "ppmucpu", "aclk133", GATE_IP_DMC, 10, 0, 0),
+	GATE(CLK_PPMUACP, "ppmuacp", "aclk133", GATE_IP_DMC, 16, 0, 0),
+
+	GATE(CLK_OUT_LEFTBUS, "clkout_leftbus", "div_clkout_leftbus",
+			CLKOUT_CMU_LEFTBUS, 16, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_OUT_RIGHTBUS, "clkout_rightbus", "div_clkout_rightbus",
+			CLKOUT_CMU_RIGHTBUS, 16, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_OUT_TOP, "clkout_top", "div_clkout_top",
+			CLKOUT_CMU_TOP, 16, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_OUT_DMC, "clkout_dmc", "div_clkout_dmc",
+			CLKOUT_CMU_DMC, 16, CLK_SET_RATE_PARENT, 0),
+	GATE(CLK_OUT_CPU, "clkout_cpu", "div_clkout_cpu",
+			CLKOUT_CMU_CPU, 16, CLK_SET_RATE_PARENT, 0),
 };
 
 /* list of gate clocks supported in exynos4210 soc */
@@ -863,6 +1050,9 @@ static struct samsung_gate_clock exynos4210_gate_clks[] __initdata = {
 	GATE(CLK_SMMU_G2D, "smmu_g2d", "aclk200", E4210_GATE_IP_IMAGE, 3, 0, 0),
 	GATE(CLK_SMMU_MDMA, "smmu_mdma", "aclk200", E4210_GATE_IP_IMAGE, 5, 0,
 		0),
+	GATE(CLK_PPMUIMAGE, "ppmuimage", "aclk200", E4210_GATE_IP_IMAGE, 9, 0,
+		0),
+	GATE(CLK_PPMULCD1, "ppmulcd1", "aclk160", E4210_GATE_IP_LCD1, 5, 0, 0),
 	GATE(CLK_PCIE_PHY, "pcie_phy", "aclk133", GATE_IP_FSYS, 2, 0, 0),
 	GATE(CLK_SATA_PHY, "sata_phy", "aclk133", GATE_IP_FSYS, 3, 0, 0),
 	GATE(CLK_SATA, "sata", "aclk133", GATE_IP_FSYS, 10, 0, 0),
@@ -906,6 +1096,8 @@ static struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 	GATE(CLK_MDMA, "mdma", "aclk200", E4X12_GATE_IP_IMAGE, 2, 0, 0),
 	GATE(CLK_SMMU_MDMA, "smmu_mdma", "aclk200", E4X12_GATE_IP_IMAGE, 5, 0,
 		0),
+	GATE(CLK_PPMUIMAGE, "ppmuimage", "aclk200", E4X12_GATE_IP_IMAGE, 9, 0,
+		0),
 	GATE(CLK_MIPI_HSI, "mipi_hsi", "aclk133", GATE_IP_FSYS, 10, 0, 0),
 	GATE(CLK_CHIPID, "chipid", "aclk100", E4X12_GATE_IP_PERIR, 0, 0, 0),
 	GATE(CLK_SYSREG, "sysreg", "aclk100", E4X12_GATE_IP_PERIR, 1,
@@ -925,21 +1117,13 @@ static struct samsung_gate_clock exynos4x12_gate_clks[] __initdata = {
 	GATE(CLK_RTC, "rtc", "aclk100", E4X12_GATE_IP_PERIR, 15,
 			0, 0),
 	GATE(CLK_KEYIF, "keyif", "aclk100", E4X12_GATE_IP_PERIR, 16, 0, 0),
-	GATE(CLK_SCLK_PWM_ISP, "sclk_pwm_isp", "div_pwm_isp",
-			E4X12_SRC_MASK_ISP, 0, CLK_SET_RATE_PARENT, 0),
-	GATE(CLK_SCLK_SPI0_ISP, "sclk_spi0_isp", "div_spi0_isp_pre",
-			E4X12_SRC_MASK_ISP, 4, CLK_SET_RATE_PARENT, 0),
-	GATE(CLK_SCLK_SPI1_ISP, "sclk_spi1_isp", "div_spi1_isp_pre",
-			E4X12_SRC_MASK_ISP, 8, CLK_SET_RATE_PARENT, 0),
-	GATE(CLK_SCLK_UART_ISP, "sclk_uart_isp", "div_uart_isp",
-			E4X12_SRC_MASK_ISP, 12, CLK_SET_RATE_PARENT, 0),
-	GATE(CLK_PWM_ISP_SCLK, "pwm_isp_sclk", "sclk_pwm_isp",
+	GATE(CLK_PWM_ISP_SCLK, "pwm_isp_sclk", "div_pwm_isp",
 			E4X12_GATE_IP_ISP, 0, 0, 0),
-	GATE(CLK_SPI0_ISP_SCLK, "spi0_isp_sclk", "sclk_spi0_isp",
+	GATE(CLK_SPI0_ISP_SCLK, "spi0_isp_sclk", "div_spi0_isp_pre",
 			E4X12_GATE_IP_ISP, 1, 0, 0),
-	GATE(CLK_SPI1_ISP_SCLK, "spi1_isp_sclk", "sclk_spi1_isp",
+	GATE(CLK_SPI1_ISP_SCLK, "spi1_isp_sclk", "div_spi1_isp_pre",
 			E4X12_GATE_IP_ISP, 2, 0, 0),
-	GATE(CLK_UART_ISP_SCLK, "uart_isp_sclk", "sclk_uart_isp",
+	GATE(CLK_UART_ISP_SCLK, "uart_isp_sclk", "div_uart_isp",
 			E4X12_GATE_IP_ISP, 3, 0, 0),
 	GATE(CLK_WDT, "watchdog", "aclk100", E4X12_GATE_IP_PERIR, 14, 0, 0),
 	GATE(CLK_PCM0, "pcm0", "aclk100", E4X12_GATE_IP_MAUDIO, 2,
@@ -1070,7 +1254,7 @@ static void __init exynos4_clk_register_finpll(struct samsung_clk_provider *ctx)
 
 }
 
-static struct of_device_id ext_clk_match[] __initdata = {
+static const struct of_device_id ext_clk_match[] __initconst = {
 	{ .compatible = "samsung,clock-xxti", .data = (void *)0, },
 	{ .compatible = "samsung,clock-xusbxti", .data = (void *)1, },
 	{},
@@ -1172,6 +1356,32 @@ static struct samsung_pll_clock exynos4x12_plls[nr_plls] __initdata = {
 			VPLL_LOCK, VPLL_CON0, NULL),
 };
 
+static void __init exynos4_core_down_clock(enum exynos4_soc soc)
+{
+	unsigned int tmp;
+
+	/*
+	 * Enable arm clock down (in idle) and set arm divider
+	 * ratios in WFI/WFE state.
+	 */
+	tmp = (PWR_CTRL1_CORE2_DOWN_RATIO(7) | PWR_CTRL1_CORE1_DOWN_RATIO(7) |
+		PWR_CTRL1_DIV2_DOWN_EN | PWR_CTRL1_DIV1_DOWN_EN |
+		PWR_CTRL1_USE_CORE1_WFE | PWR_CTRL1_USE_CORE0_WFE |
+		PWR_CTRL1_USE_CORE1_WFI | PWR_CTRL1_USE_CORE0_WFI);
+	/* On Exynos4412 enable it also on core 2 and 3 */
+	if (num_possible_cpus() == 4)
+		tmp |= PWR_CTRL1_USE_CORE3_WFE | PWR_CTRL1_USE_CORE2_WFE |
+		       PWR_CTRL1_USE_CORE3_WFI | PWR_CTRL1_USE_CORE2_WFI;
+	__raw_writel(tmp, reg_base + PWR_CTRL1);
+
+	/*
+	 * Disable the clock up feature on Exynos4x12, in case it was
+	 * enabled by bootloader.
+	 */
+	if (exynos4_soc == EXYNOS4X12)
+		__raw_writel(0x0, reg_base + E4X12_PWR_CTRL2);
+}
+
 /* register exynos4 clocks */
 static void __init exynos4_clk_init(struct device_node *np,
 				    enum exynos4_soc soc)
@@ -1232,6 +1442,8 @@ static void __init exynos4_clk_init(struct device_node *np,
 			ARRAY_SIZE(exynos4_div_clks));
 	samsung_clk_register_gate(ctx, exynos4_gate_clks,
 			ARRAY_SIZE(exynos4_gate_clks));
+	samsung_clk_register_fixed_factor(ctx, exynos4_fixed_factor_clks,
+			ARRAY_SIZE(exynos4_fixed_factor_clks));
 
 	if (exynos4_soc == EXYNOS4210) {
 		samsung_clk_register_fixed_rate(ctx, exynos4210_fixed_rate_clks,
@@ -1244,6 +1456,9 @@ static void __init exynos4_clk_init(struct device_node *np,
 			ARRAY_SIZE(exynos4210_gate_clks));
 		samsung_clk_register_alias(ctx, exynos4210_aliases,
 			ARRAY_SIZE(exynos4210_aliases));
+		samsung_clk_register_fixed_factor(ctx,
+			exynos4210_fixed_factor_clks,
+			ARRAY_SIZE(exynos4210_fixed_factor_clks));
 	} else {
 		samsung_clk_register_mux(ctx, exynos4x12_mux_clks,
 			ARRAY_SIZE(exynos4x12_mux_clks));
@@ -1253,13 +1468,19 @@ static void __init exynos4_clk_init(struct device_node *np,
 			ARRAY_SIZE(exynos4x12_gate_clks));
 		samsung_clk_register_alias(ctx, exynos4x12_aliases,
 			ARRAY_SIZE(exynos4x12_aliases));
+		samsung_clk_register_fixed_factor(ctx,
+			exynos4x12_fixed_factor_clks,
+			ARRAY_SIZE(exynos4x12_fixed_factor_clks));
 	}
 
 	samsung_clk_register_alias(ctx, exynos4_aliases,
 			ARRAY_SIZE(exynos4_aliases));
 
+	exynos4_core_down_clock(soc);
 	exynos4_clk_sleep_init();
 
+	samsung_clk_of_add_provider(np, ctx);
+
 	pr_info("%s clocks: sclk_apll = %ld, sclk_mpll = %ld\n"
 		"\tsclk_epll = %ld, sclk_vpll = %ld, arm_clk = %ld\n",
 		exynos4_soc == EXYNOS4210 ? "Exynos4210" : "Exynos4x12",
diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index 1fad4c5e3f5..70ec3d2608a 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -661,7 +661,7 @@ static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
 	GATE(CLK_RTC, "rtc", "div_aclk66", GATE_IP_PERIS, 20, 0, 0),
 	GATE(CLK_TMU, "tmu", "div_aclk66", GATE_IP_PERIS, 21, 0, 0),
 	GATE(CLK_SMMU_TV, "smmu_tv", "mout_aclk200_disp1_sub",
-			GATE_IP_DISP1, 2, 0, 0),
+			GATE_IP_DISP1, 9, 0, 0),
 	GATE(CLK_SMMU_FIMD1, "smmu_fimd1", "mout_aclk200_disp1_sub",
 			GATE_IP_DISP1, 8, 0, 0),
 	GATE(CLK_SMMU_2D, "smmu_2d", "div_aclk200", GATE_IP_ACP, 7, 0, 0),
@@ -748,7 +748,7 @@ static struct samsung_pll_clock exynos5250_plls[nr_plls] __initdata = {
 		VPLL_LOCK, VPLL_CON0, NULL),
 };
 
-static struct of_device_id ext_clk_match[] __initdata = {
+static const struct of_device_id ext_clk_match[] __initconst = {
 	{ .compatible = "samsung,clock-xxti", .data = (void *)0, },
 	{ },
 };
@@ -820,6 +820,8 @@ static void __init exynos5250_clk_init(struct device_node *np)
 
 	exynos5250_clk_sleep_init();
 
+	samsung_clk_of_add_provider(np, ctx);
+
 	pr_info("Exynos5250: clock setup completed, armclk=%ld\n",
 			_get_rate("div_arm2"));
 }
diff --git a/drivers/clk/samsung/clk-exynos5260.c b/drivers/clk/samsung/clk-exynos5260.c
index 64596ba58df..ce3de97e5f1 100644
--- a/drivers/clk/samsung/clk-exynos5260.c
+++ b/drivers/clk/samsung/clk-exynos5260.c
@@ -206,6 +206,8 @@ void __init exynos5260_cmu_register_one(struct device_node *np,
 	if (cmu->clk_regs)
 		exynos5260_clk_sleep_init(reg_base, cmu->clk_regs,
 			cmu->nr_clk_regs);
+
+	samsung_clk_of_add_provider(np, ctx);
 }
 
 
diff --git a/drivers/clk/samsung/clk-exynos5410.c b/drivers/clk/samsung/clk-exynos5410.c
index c9505ab9ee7..231475bc2b9 100644
--- a/drivers/clk/samsung/clk-exynos5410.c
+++ b/drivers/clk/samsung/clk-exynos5410.c
@@ -204,6 +204,8 @@ static void __init exynos5410_clk_init(struct device_node *np)
 	samsung_clk_register_gate(ctx, exynos5410_gate_clks,
 			ARRAY_SIZE(exynos5410_gate_clks));
 
+	samsung_clk_of_add_provider(np, ctx);
+
 	pr_debug("Exynos5410: clock setup completed.\n");
 }
 CLK_OF_DECLARE(exynos5410_clk, "samsung,exynos5410-clock", exynos5410_clk_init);
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index 9d7d7eed03f..848d602efc0 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -28,6 +28,7 @@
 #define GATE_BUS_CPU		0x700
 #define GATE_SCLK_CPU		0x800
 #define CLKOUT_CMU_CPU		0xa00
+#define SRC_MASK_CPERI		0x4300
 #define GATE_IP_G2D		0x8800
 #define CPLL_LOCK		0x10020
 #define DPLL_LOCK		0x10030
@@ -70,6 +71,8 @@
 #define SRC_TOP11		0x10284
 #define SRC_TOP12		0x10288
 #define SRC_TOP13		0x1028c /* 5800 specific */
+#define SRC_MASK_TOP0		0x10300
+#define SRC_MASK_TOP1		0x10304
 #define SRC_MASK_TOP2		0x10308
 #define SRC_MASK_TOP7		0x1031c
 #define SRC_MASK_DISP10		0x1032c
@@ -77,6 +80,7 @@
 #define SRC_MASK_FSYS		0x10340
 #define SRC_MASK_PERIC0		0x10350
 #define SRC_MASK_PERIC1		0x10354
+#define SRC_MASK_ISP		0x10370
 #define DIV_TOP0		0x10500
 #define DIV_TOP1		0x10504
 #define DIV_TOP2		0x10508
@@ -98,6 +102,7 @@
 #define DIV2_RATIO0		0x10590
 #define DIV4_RATIO		0x105a0
 #define GATE_BUS_TOP		0x10700
+#define GATE_BUS_DISP1		0x10728
 #define GATE_BUS_GEN		0x1073c
 #define GATE_BUS_FSYS0		0x10740
 #define GATE_BUS_FSYS2		0x10748
@@ -190,6 +195,10 @@ static unsigned long exynos5x_clk_regs[] __initdata = {
 	SRC_MASK_FSYS,
 	SRC_MASK_PERIC0,
 	SRC_MASK_PERIC1,
+	SRC_MASK_TOP0,
+	SRC_MASK_TOP1,
+	SRC_MASK_MAU,
+	SRC_MASK_ISP,
 	SRC_ISP,
 	DIV_TOP0,
 	DIV_TOP1,
@@ -208,6 +217,7 @@ static unsigned long exynos5x_clk_regs[] __initdata = {
 	SCLK_DIV_ISP1,
 	DIV2_RATIO0,
 	DIV4_RATIO,
+	GATE_BUS_DISP1,
 	GATE_BUS_TOP,
 	GATE_BUS_GEN,
 	GATE_BUS_FSYS0,
@@ -249,6 +259,22 @@ static unsigned long exynos5800_clk_regs[] __initdata = {
 	GATE_IP_CAM,
 };
 
+static const struct samsung_clk_reg_dump exynos5420_set_clksrc[] = {
+	{ .offset = SRC_MASK_CPERI,		.value = 0xffffffff, },
+	{ .offset = SRC_MASK_TOP0,		.value = 0x11111111, },
+	{ .offset = SRC_MASK_TOP1,		.value = 0x11101111, },
+	{ .offset = SRC_MASK_TOP2,		.value = 0x11111110, },
+	{ .offset = SRC_MASK_TOP7,		.value = 0x00111100, },
+	{ .offset = SRC_MASK_DISP10,		.value = 0x11111110, },
+	{ .offset = SRC_MASK_MAU,		.value = 0x10000000, },
+	{ .offset = SRC_MASK_FSYS,		.value = 0x11111110, },
+	{ .offset = SRC_MASK_PERIC0,		.value = 0x11111110, },
+	{ .offset = SRC_MASK_PERIC1,		.value = 0x11111100, },
+	{ .offset = SRC_MASK_ISP,		.value = 0x11111000, },
+	{ .offset = GATE_BUS_DISP1,		.value = 0xffffffff, },
+	{ .offset = GATE_IP_PERIC,		.value = 0xffffffff, },
+};
+
 static int exynos5420_clk_suspend(void)
 {
 	samsung_clk_save(reg_base, exynos5x_save,
@@ -258,6 +284,9 @@ static int exynos5420_clk_suspend(void)
 		samsung_clk_save(reg_base, exynos5800_save,
 				ARRAY_SIZE(exynos5800_clk_regs));
 
+	samsung_clk_restore(reg_base, exynos5420_set_clksrc,
+				ARRAY_SIZE(exynos5420_set_clksrc));
+
 	return 0;
 }
 
@@ -631,7 +660,8 @@ static struct samsung_mux_clock exynos5x_mux_clks[] __initdata = {
 			SRC_TOP4, 16, 1),
 	MUX(0, "mout_user_aclk266", mout_user_aclk266_p, SRC_TOP4, 20, 1),
 	MUX(0, "mout_user_aclk166", mout_user_aclk166_p, SRC_TOP4, 24, 1),
-	MUX(0, "mout_user_aclk333", mout_user_aclk333_p, SRC_TOP4, 28, 1),
+	MUX(CLK_MOUT_USER_ACLK333, "mout_user_aclk333", mout_user_aclk333_p,
+			SRC_TOP4, 28, 1),
 
 	MUX(0, "mout_user_aclk400_disp1", mout_user_aclk400_disp1_p,
 			SRC_TOP5, 0, 1),
@@ -684,7 +714,8 @@ static struct samsung_mux_clock exynos5x_mux_clks[] __initdata = {
 			SRC_TOP11, 12, 1),
 	MUX(0, "mout_sw_aclk266", mout_sw_aclk266_p, SRC_TOP11, 20, 1),
 	MUX(0, "mout_sw_aclk166", mout_sw_aclk166_p, SRC_TOP11, 24, 1),
-	MUX(0, "mout_sw_aclk333", mout_sw_aclk333_p, SRC_TOP11, 28, 1),
+	MUX(CLK_MOUT_SW_ACLK333, "mout_sw_aclk333", mout_sw_aclk333_p,
+			SRC_TOP11, 28, 1),
 
 	MUX(0, "mout_sw_aclk400_disp1", mout_sw_aclk400_disp1_p,
 			SRC_TOP12, 4, 1),
@@ -890,8 +921,6 @@ static struct samsung_gate_clock exynos5x_gate_clks[] __initdata = {
 			GATE_BUS_TOP, 9, CLK_IGNORE_UNUSED, 0),
 	GATE(0, "aclk66_psgen", "mout_user_aclk66_psgen",
 			GATE_BUS_TOP, 10, CLK_IGNORE_UNUSED, 0),
-	GATE(CLK_ACLK66_PERIC, "aclk66_peric", "mout_user_aclk66_peric",
-			GATE_BUS_TOP, 11, CLK_IGNORE_UNUSED, 0),
 	GATE(0, "aclk266_isp", "mout_user_aclk266_isp",
 			GATE_BUS_TOP, 13, 0, 0),
 	GATE(0, "aclk166", "mout_user_aclk166",
@@ -994,34 +1023,61 @@ static struct samsung_gate_clock exynos5x_gate_clks[] __initdata = {
 			SRC_MASK_FSYS, 24, CLK_SET_RATE_PARENT, 0),
 
 	/* PERIC Block */
-	GATE(CLK_UART0, "uart0", "aclk66_peric", GATE_IP_PERIC, 0, 0, 0),
-	GATE(CLK_UART1, "uart1", "aclk66_peric", GATE_IP_PERIC, 1, 0, 0),
-	GATE(CLK_UART2, "uart2", "aclk66_peric", GATE_IP_PERIC, 2, 0, 0),
-	GATE(CLK_UART3, "uart3", "aclk66_peric", GATE_IP_PERIC, 3, 0, 0),
-	GATE(CLK_I2C0, "i2c0", "aclk66_peric", GATE_IP_PERIC, 6, 0, 0),
-	GATE(CLK_I2C1, "i2c1", "aclk66_peric", GATE_IP_PERIC, 7, 0, 0),
-	GATE(CLK_I2C2, "i2c2", "aclk66_peric", GATE_IP_PERIC, 8, 0, 0),
-	GATE(CLK_I2C3, "i2c3", "aclk66_peric", GATE_IP_PERIC, 9, 0, 0),
-	GATE(CLK_USI0, "usi0", "aclk66_peric", GATE_IP_PERIC, 10, 0, 0),
-	GATE(CLK_USI1, "usi1", "aclk66_peric", GATE_IP_PERIC, 11, 0, 0),
-	GATE(CLK_USI2, "usi2", "aclk66_peric", GATE_IP_PERIC, 12, 0, 0),
-	GATE(CLK_USI3, "usi3", "aclk66_peric", GATE_IP_PERIC, 13, 0, 0),
-	GATE(CLK_I2C_HDMI, "i2c_hdmi", "aclk66_peric", GATE_IP_PERIC, 14, 0, 0),
-	GATE(CLK_TSADC, "tsadc", "aclk66_peric", GATE_IP_PERIC, 15, 0, 0),
-	GATE(CLK_SPI0, "spi0", "aclk66_peric", GATE_IP_PERIC, 16, 0, 0),
-	GATE(CLK_SPI1, "spi1", "aclk66_peric", GATE_IP_PERIC, 17, 0, 0),
-	GATE(CLK_SPI2, "spi2", "aclk66_peric", GATE_IP_PERIC, 18, 0, 0),
-	GATE(CLK_I2S1, "i2s1", "aclk66_peric", GATE_IP_PERIC, 20, 0, 0),
-	GATE(CLK_I2S2, "i2s2", "aclk66_peric", GATE_IP_PERIC, 21, 0, 0),
-	GATE(CLK_PCM1, "pcm1", "aclk66_peric", GATE_IP_PERIC, 22, 0, 0),
-	GATE(CLK_PCM2, "pcm2", "aclk66_peric", GATE_IP_PERIC, 23, 0, 0),
-	GATE(CLK_PWM, "pwm", "aclk66_peric", GATE_IP_PERIC, 24, 0, 0),
-	GATE(CLK_SPDIF, "spdif", "aclk66_peric", GATE_IP_PERIC, 26, 0, 0),
-	GATE(CLK_USI4, "usi4", "aclk66_peric", GATE_IP_PERIC, 28, 0, 0),
-	GATE(CLK_USI5, "usi5", "aclk66_peric", GATE_IP_PERIC, 30, 0, 0),
-	GATE(CLK_USI6, "usi6", "aclk66_peric", GATE_IP_PERIC, 31, 0, 0),
-
-	GATE(CLK_KEYIF, "keyif", "aclk66_peric", GATE_BUS_PERIC, 22, 0, 0),
+	GATE(CLK_UART0, "uart0", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 0, 0, 0),
+	GATE(CLK_UART1, "uart1", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 1, 0, 0),
+	GATE(CLK_UART2, "uart2", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 2, 0, 0),
+	GATE(CLK_UART3, "uart3", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 3, 0, 0),
+	GATE(CLK_I2C0, "i2c0", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 6, 0, 0),
+	GATE(CLK_I2C1, "i2c1", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 7, 0, 0),
+	GATE(CLK_I2C2, "i2c2", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 8, 0, 0),
+	GATE(CLK_I2C3, "i2c3", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 9, 0, 0),
+	GATE(CLK_USI0, "usi0", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 10, 0, 0),
+	GATE(CLK_USI1, "usi1", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 11, 0, 0),
+	GATE(CLK_USI2, "usi2", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 12, 0, 0),
+	GATE(CLK_USI3, "usi3", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 13, 0, 0),
+	GATE(CLK_I2C_HDMI, "i2c_hdmi", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 14, 0, 0),
+	GATE(CLK_TSADC, "tsadc", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 15, 0, 0),
+	GATE(CLK_SPI0, "spi0", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 16, 0, 0),
+	GATE(CLK_SPI1, "spi1", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 17, 0, 0),
+	GATE(CLK_SPI2, "spi2", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 18, 0, 0),
+	GATE(CLK_I2S1, "i2s1", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 20, 0, 0),
+	GATE(CLK_I2S2, "i2s2", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 21, 0, 0),
+	GATE(CLK_PCM1, "pcm1", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 22, 0, 0),
+	GATE(CLK_PCM2, "pcm2", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 23, 0, 0),
+	GATE(CLK_PWM, "pwm", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 24, 0, 0),
+	GATE(CLK_SPDIF, "spdif", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 26, 0, 0),
+	GATE(CLK_USI4, "usi4", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 28, 0, 0),
+	GATE(CLK_USI5, "usi5", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 30, 0, 0),
+	GATE(CLK_USI6, "usi6", "mout_user_aclk66_peric",
+			GATE_IP_PERIC, 31, 0, 0),
+
+	GATE(CLK_KEYIF, "keyif", "mout_user_aclk66_peric",
+			GATE_BUS_PERIC, 22, 0, 0),
 
 	/* PERIS Block */
 	GATE(CLK_CHIPID, "chipid", "aclk66_psgen",
@@ -1142,6 +1198,28 @@ static struct samsung_gate_clock exynos5x_gate_clks[] __initdata = {
 	GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0),
 };
 
+static const struct samsung_pll_rate_table exynos5420_pll2550x_24mhz_tbl[] = {
+	PLL_35XX_RATE(2000000000, 250, 3, 0),
+	PLL_35XX_RATE(1900000000, 475, 6, 0),
+	PLL_35XX_RATE(1800000000, 225, 3, 0),
+	PLL_35XX_RATE(1700000000, 425, 6, 0),
+	PLL_35XX_RATE(1600000000, 200, 3, 0),
+	PLL_35XX_RATE(1500000000, 250, 4, 0),
+	PLL_35XX_RATE(1400000000, 175, 3, 0),
+	PLL_35XX_RATE(1300000000, 325, 6, 0),
+	PLL_35XX_RATE(1200000000, 200, 2, 1),
+	PLL_35XX_RATE(1100000000, 275, 3, 1),
+	PLL_35XX_RATE(1000000000, 250, 3, 1),
+	PLL_35XX_RATE(900000000,  150, 2, 1),
+	PLL_35XX_RATE(800000000,  200, 3, 1),
+	PLL_35XX_RATE(700000000,  175, 3, 1),
+	PLL_35XX_RATE(600000000,  200, 2, 2),
+	PLL_35XX_RATE(500000000,  250, 3, 2),
+	PLL_35XX_RATE(400000000,  200, 3, 2),
+	PLL_35XX_RATE(300000000,  200, 2, 3),
+	PLL_35XX_RATE(200000000,  200, 3, 3),
+};
+
 static struct samsung_pll_clock exynos5x_plls[nr_plls] __initdata = {
 	[apll] = PLL(pll_2550, CLK_FOUT_APLL, "fout_apll", "fin_pll", APLL_LOCK,
 		APLL_CON0, NULL),
@@ -1167,7 +1245,7 @@ static struct samsung_pll_clock exynos5x_plls[nr_plls] __initdata = {
 		KPLL_CON0, NULL),
 };
 
-static struct of_device_id ext_clk_match[] __initdata = {
+static const struct of_device_id ext_clk_match[] __initconst = {
 	{ .compatible = "samsung,exynos5420-oscclk", .data = (void *)0, },
 	{ },
 };
@@ -1195,6 +1273,12 @@ static void __init exynos5x_clk_init(struct device_node *np,
 	samsung_clk_of_register_fixed_ext(ctx, exynos5x_fixed_rate_ext_clks,
 			ARRAY_SIZE(exynos5x_fixed_rate_ext_clks),
 			ext_clk_match);
+
+	if (_get_rate("fin_pll") == 24 * MHZ) {
+		exynos5x_plls[apll].rate_table = exynos5420_pll2550x_24mhz_tbl;
+		exynos5x_plls[kpll].rate_table = exynos5420_pll2550x_24mhz_tbl;
+	}
+
 	samsung_clk_register_pll(ctx, exynos5x_plls, ARRAY_SIZE(exynos5x_plls),
 					reg_base);
 	samsung_clk_register_fixed_rate(ctx, exynos5x_fixed_rate_clks,
@@ -1226,6 +1310,8 @@ static void __init exynos5x_clk_init(struct device_node *np,
 	}
 
 	exynos5420_clk_sleep_init();
+
+	samsung_clk_of_add_provider(np, ctx);
 }
 
 static void __init exynos5420_clk_init(struct device_node *np)
diff --git a/drivers/clk/samsung/clk-exynos5440.c b/drivers/clk/samsung/clk-exynos5440.c
index 647f1440aa6..00d1d00a41d 100644
--- a/drivers/clk/samsung/clk-exynos5440.c
+++ b/drivers/clk/samsung/clk-exynos5440.c
@@ -84,7 +84,7 @@ static struct samsung_gate_clock exynos5440_gate_clks[] __initdata = {
 	GATE(CLK_CS250_O, "cs250_o", "cs250", CLKEN_OV_VAL, 19, 0, 0),
 };
 
-static struct of_device_id ext_clk_match[] __initdata = {
+static const struct of_device_id ext_clk_match[] __initconst = {
 	{ .compatible = "samsung,clock-xtal", .data = (void *)0, },
 	{},
 };
@@ -123,6 +123,8 @@ static void __init exynos5440_clk_init(struct device_node *np)
 	samsung_clk_register_gate(ctx, exynos5440_gate_clks,
 			ARRAY_SIZE(exynos5440_gate_clks));
 
+	samsung_clk_of_add_provider(np, ctx);
+
 	pr_info("Exynos5440: arm_clk = %ldHz\n", _get_rate("arm_clk"));
 	pr_info("exynos5440 clock initialization complete\n");
 }
diff --git a/drivers/clk/samsung/clk-s3c2410.c b/drivers/clk/samsung/clk-s3c2410.c
index ba0716801db..5d2f03461bc 100644
--- a/drivers/clk/samsung/clk-s3c2410.c
+++ b/drivers/clk/samsung/clk-s3c2410.c
@@ -152,6 +152,11 @@ struct samsung_clock_alias s3c2410_common_aliases[] __initdata = {
 	ALIAS(HCLK, NULL, "hclk"),
 	ALIAS(MPLL, NULL, "mpll"),
 	ALIAS(FCLK, NULL, "fclk"),
+	ALIAS(PCLK, NULL, "watchdog"),
+	ALIAS(PCLK_SDI, NULL, "sdi"),
+	ALIAS(HCLK_NAND, NULL, "nand"),
+	ALIAS(PCLK_I2S, NULL, "iis"),
+	ALIAS(PCLK_I2C, NULL, "i2c"),
 };
 
 /* S3C2410 specific clocks */
@@ -378,7 +383,7 @@ void __init s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f,
 	if (!np)
 		s3c2410_common_clk_register_fixed_ext(ctx, xti_f);
 
-	if (current_soc == 2410) {
+	if (current_soc == S3C2410) {
 		if (_get_rate("xti") == 12 * MHZ) {
 			s3c2410_plls[mpll].rate_table = pll_s3c2410_12mhz_tbl;
 			s3c2410_plls[upll].rate_table = pll_s3c2410_12mhz_tbl;
@@ -432,7 +437,7 @@ void __init s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f,
 		samsung_clk_register_fixed_factor(ctx, s3c2410_ffactor,
 				ARRAY_SIZE(s3c2410_ffactor));
 		samsung_clk_register_alias(ctx, s3c2410_aliases,
-			ARRAY_SIZE(s3c2410_common_aliases));
+			ARRAY_SIZE(s3c2410_aliases));
 		break;
 	case S3C2440:
 		samsung_clk_register_mux(ctx, s3c2440_muxes,
@@ -461,6 +466,8 @@ void __init s3c2410_common_clk_init(struct device_node *np, unsigned long xti_f,
 	}
 
 	s3c2410_clk_sleep_init();
+
+	samsung_clk_of_add_provider(np, ctx);
 }
 
 static void __init s3c2410_clk_init(struct device_node *np)
diff --git a/drivers/clk/samsung/clk-s3c2412.c b/drivers/clk/samsung/clk-s3c2412.c
index 23e4313f625..34af09f6a15 100644
--- a/drivers/clk/samsung/clk-s3c2412.c
+++ b/drivers/clk/samsung/clk-s3c2412.c
@@ -265,6 +265,8 @@ void __init s3c2412_common_clk_init(struct device_node *np, unsigned long xti_f,
 				   ARRAY_SIZE(s3c2412_aliases));
 
 	s3c2412_clk_sleep_init();
+
+	samsung_clk_of_add_provider(np, ctx);
 }
 
 static void __init s3c2412_clk_init(struct device_node *np)
diff --git a/drivers/clk/samsung/clk-s3c2443.c b/drivers/clk/samsung/clk-s3c2443.c
index c4bbdabebaa..c92f853fca9 100644
--- a/drivers/clk/samsung/clk-s3c2443.c
+++ b/drivers/clk/samsung/clk-s3c2443.c
@@ -445,6 +445,8 @@ void __init s3c2443_common_clk_init(struct device_node *np, unsigned long xti_f,
 	}
 
 	s3c2443_clk_sleep_init();
+
+	samsung_clk_of_add_provider(np, ctx);
 }
 
 static void __init s3c2416_clk_init(struct device_node *np)
diff --git a/drivers/clk/samsung/clk-s3c64xx.c b/drivers/clk/samsung/clk-s3c64xx.c
index efa16ee592c..0f590e5550c 100644
--- a/drivers/clk/samsung/clk-s3c64xx.c
+++ b/drivers/clk/samsung/clk-s3c64xx.c
@@ -418,8 +418,10 @@ static struct samsung_clock_alias s3c64xx_clock_aliases[] = {
 	ALIAS(SCLK_MMC2, "s3c-sdhci.2", "mmc_busclk.2"),
 	ALIAS(SCLK_MMC1, "s3c-sdhci.1", "mmc_busclk.2"),
 	ALIAS(SCLK_MMC0, "s3c-sdhci.0", "mmc_busclk.2"),
-	ALIAS(SCLK_SPI1, "s3c6410-spi.1", "spi-bus"),
-	ALIAS(SCLK_SPI0, "s3c6410-spi.0", "spi-bus"),
+	ALIAS(PCLK_SPI1, "s3c6410-spi.1", "spi_busclk0"),
+	ALIAS(SCLK_SPI1, "s3c6410-spi.1", "spi_busclk2"),
+	ALIAS(PCLK_SPI0, "s3c6410-spi.0", "spi_busclk0"),
+	ALIAS(SCLK_SPI0, "s3c6410-spi.0", "spi_busclk2"),
 	ALIAS(SCLK_AUDIO1, "samsung-pcm.1", "audio-bus"),
 	ALIAS(SCLK_AUDIO1, "samsung-i2s.1", "audio-bus"),
 	ALIAS(SCLK_AUDIO0, "samsung-pcm.0", "audio-bus"),
@@ -516,6 +518,8 @@ void __init s3c64xx_clk_init(struct device_node *np, unsigned long xtal_f,
 					ARRAY_SIZE(s3c64xx_clock_aliases));
 	s3c64xx_clk_sleep_init();
 
+	samsung_clk_of_add_provider(np, ctx);
+
 	pr_info("%s clocks: apll = %lu, mpll = %lu\n"
 		"\tepll = %lu, arm_clk = %lu\n",
 		is_s3c6400 ? "S3C6400" : "S3C6410",
diff --git a/drivers/clk/samsung/clk.c b/drivers/clk/samsung/clk.c
index 49629c71c9e..deab84d9f37 100644
--- a/drivers/clk/samsung/clk.c
+++ b/drivers/clk/samsung/clk.c
@@ -53,7 +53,6 @@ struct samsung_clk_provider *__init samsung_clk_init(struct device_node *np,
 {
 	struct samsung_clk_provider *ctx;
 	struct clk **clk_table;
-	int ret;
 	int i;
 
 	ctx = kzalloc(sizeof(struct samsung_clk_provider), GFP_KERNEL);
@@ -72,17 +71,19 @@ struct samsung_clk_provider *__init samsung_clk_init(struct device_node *np,
 	ctx->clk_data.clk_num = nr_clks;
 	spin_lock_init(&ctx->lock);
 
-	if (!np)
-		return ctx;
-
-	ret = of_clk_add_provider(np, of_clk_src_onecell_get,
-			&ctx->clk_data);
-	if (ret)
-		panic("could not register clock provide\n");
-
 	return ctx;
 }
 
+void __init samsung_clk_of_add_provider(struct device_node *np,
+				struct samsung_clk_provider *ctx)
+{
+	if (np) {
+		if (of_clk_add_provider(np, of_clk_src_onecell_get,
+					&ctx->clk_data))
+			panic("could not register clk provider\n");
+	}
+}
+
 /* add a clock instance to the clock lookup table used for dt based lookup */
 void samsung_clk_add_lookup(struct samsung_clk_provider *ctx, struct clk *clk,
 				unsigned int id)
@@ -284,7 +285,7 @@ void __init samsung_clk_register_gate(struct samsung_clk_provider *ctx,
 void __init samsung_clk_of_register_fixed_ext(struct samsung_clk_provider *ctx,
 			struct samsung_fixed_rate_clock *fixed_rate_clk,
 			unsigned int nr_fixed_rate_clk,
-			struct of_device_id *clk_matches)
+			const struct of_device_id *clk_matches)
 {
 	const struct of_device_id *match;
 	struct device_node *clk_np;
diff --git a/drivers/clk/samsung/clk.h b/drivers/clk/samsung/clk.h
index 9693b80d924..66ab36b5cef 100644
--- a/drivers/clk/samsung/clk.h
+++ b/drivers/clk/samsung/clk.h
@@ -327,11 +327,13 @@ struct samsung_pll_clock {
 extern struct samsung_clk_provider *__init samsung_clk_init(
 			struct device_node *np, void __iomem *base,
 			unsigned long nr_clks);
+extern void __init samsung_clk_of_add_provider(struct device_node *np,
+			struct samsung_clk_provider *ctx);
 extern void __init samsung_clk_of_register_fixed_ext(
 			struct samsung_clk_provider *ctx,
 			struct samsung_fixed_rate_clock *fixed_rate_clk,
 			unsigned int nr_fixed_rate_clk,
-			struct of_device_id *clk_matches);
+			const struct of_device_id *clk_matches);
 
 extern void samsung_clk_add_lookup(struct samsung_clk_provider *ctx,
 			struct clk *clk, unsigned int id);
diff --git a/drivers/clk/spear/spear1310_clock.c b/drivers/clk/spear/spear1310_clock.c
index 65894f7687e..4daa5977793 100644
--- a/drivers/clk/spear/spear1310_clock.c
+++ b/drivers/clk/spear/spear1310_clock.c
@@ -742,19 +742,19 @@ void __init spear1310_clk_init(void __iomem *misc_base, void __iomem *ras_base)
 	clk = clk_register_gate(NULL, "pcie_sata_0_clk", "ahb_clk", 0,
 			SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_PCIE_SATA_0_CLK_ENB,
 			0, &_lock);
-	clk_register_clkdev(clk, NULL, "dw_pcie.0");
+	clk_register_clkdev(clk, NULL, "b1000000.pcie");
 	clk_register_clkdev(clk, NULL, "b1000000.ahci");
 
 	clk = clk_register_gate(NULL, "pcie_sata_1_clk", "ahb_clk", 0,
 			SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_PCIE_SATA_1_CLK_ENB,
 			0, &_lock);
-	clk_register_clkdev(clk, NULL, "dw_pcie.1");
+	clk_register_clkdev(clk, NULL, "b1800000.pcie");
 	clk_register_clkdev(clk, NULL, "b1800000.ahci");
 
 	clk = clk_register_gate(NULL, "pcie_sata_2_clk", "ahb_clk", 0,
 			SPEAR1310_PERIP1_CLK_ENB, SPEAR1310_PCIE_SATA_2_CLK_ENB,
 			0, &_lock);
-	clk_register_clkdev(clk, NULL, "dw_pcie.2");
+	clk_register_clkdev(clk, NULL, "b4000000.pcie");
 	clk_register_clkdev(clk, NULL, "b4000000.ahci");
 
 	clk = clk_register_gate(NULL, "sysram0_clk", "ahb_clk", 0,
diff --git a/drivers/clk/spear/spear1340_clock.c b/drivers/clk/spear/spear1340_clock.c
index fe835c1845f..5a5c6648308 100644
--- a/drivers/clk/spear/spear1340_clock.c
+++ b/drivers/clk/spear/spear1340_clock.c
@@ -839,7 +839,7 @@ void __init spear1340_clk_init(void __iomem *misc_base)
 	clk = clk_register_gate(NULL, "pcie_sata_clk", "ahb_clk", 0,
 			SPEAR1340_PERIP1_CLK_ENB, SPEAR1340_PCIE_SATA_CLK_ENB,
 			0, &_lock);
-	clk_register_clkdev(clk, NULL, "dw_pcie");
+	clk_register_clkdev(clk, NULL, "b1000000.pcie");
 	clk_register_clkdev(clk, NULL, "b1000000.ahci");
 
 	clk = clk_register_gate(NULL, "sysram0_clk", "ahb_clk", 0,
diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c
index c2d20431554..bb5f387774e 100644
--- a/drivers/clk/spear/spear3xx_clock.c
+++ b/drivers/clk/spear/spear3xx_clock.c
@@ -211,7 +211,7 @@ static inline void spear310_clk_init(void) { }
 /* array of all spear 320 clock lookups */
 #ifdef CONFIG_MACH_SPEAR320
 
-#define SPEAR320_CONTROL_REG		(soc_config_base + 0x0000)
+#define SPEAR320_CONTROL_REG		(soc_config_base + 0x0010)
 #define SPEAR320_EXT_CTRL_REG		(soc_config_base + 0x0018)
 
 	#define SPEAR320_UARTX_PCLK_MASK		0x1
@@ -245,7 +245,8 @@ static const char *smii0_parents[] = { "smii_125m_pad", "ras_pll2_clk",
 	"ras_syn0_gclk", };
 static const char *uartx_parents[] = { "ras_syn1_gclk", "ras_apb_clk", };
 
-static void __init spear320_clk_init(void __iomem *soc_config_base)
+static void __init spear320_clk_init(void __iomem *soc_config_base,
+				     struct clk *ras_apb_clk)
 {
 	struct clk *clk;
 
@@ -342,6 +343,8 @@ static void __init spear320_clk_init(void __iomem *soc_config_base)
 			SPEAR320_CONTROL_REG, UART1_PCLK_SHIFT, UART1_PCLK_MASK,
 			0, &_lock);
 	clk_register_clkdev(clk, NULL, "a3000000.serial");
+	/* Enforce ras_apb_clk */
+	clk_set_parent(clk, ras_apb_clk);
 
 	clk = clk_register_mux(NULL, "uart2_clk", uartx_parents,
 			ARRAY_SIZE(uartx_parents),
@@ -349,6 +352,8 @@ static void __init spear320_clk_init(void __iomem *soc_config_base)
 			SPEAR320_EXT_CTRL_REG, SPEAR320_UART2_PCLK_SHIFT,
 			SPEAR320_UARTX_PCLK_MASK, 0, &_lock);
 	clk_register_clkdev(clk, NULL, "a4000000.serial");
+	/* Enforce ras_apb_clk */
+	clk_set_parent(clk, ras_apb_clk);
 
 	clk = clk_register_mux(NULL, "uart3_clk", uartx_parents,
 			ARRAY_SIZE(uartx_parents),
@@ -379,12 +384,12 @@ static void __init spear320_clk_init(void __iomem *soc_config_base)
 	clk_register_clkdev(clk, NULL, "60100000.serial");
 }
 #else
-static inline void spear320_clk_init(void __iomem *soc_config_base) { }
+static inline void spear320_clk_init(void __iomem *sb, struct clk *rc) { }
 #endif
 
 void __init spear3xx_clk_init(void __iomem *misc_base, void __iomem *soc_config_base)
 {
-	struct clk *clk, *clk1;
+	struct clk *clk, *clk1, *ras_apb_clk;
 
 	clk = clk_register_fixed_rate(NULL, "osc_32k_clk", NULL, CLK_IS_ROOT,
 			32000);
@@ -613,6 +618,7 @@ void __init spear3xx_clk_init(void __iomem *misc_base, void __iomem *soc_config_
 	clk = clk_register_gate(NULL, "ras_apb_clk", "apb_clk", 0, RAS_CLK_ENB,
 			RAS_APB_CLK_ENB, 0, &_lock);
 	clk_register_clkdev(clk, "ras_apb_clk", NULL);
+	ras_apb_clk = clk;
 
 	clk = clk_register_gate(NULL, "ras_32k_clk", "osc_32k_clk", 0,
 			RAS_CLK_ENB, RAS_32K_CLK_ENB, 0, &_lock);
@@ -659,5 +665,5 @@ void __init spear3xx_clk_init(void __iomem *misc_base, void __iomem *soc_config_
 	else if (of_machine_is_compatible("st,spear310"))
 		spear310_clk_init();
 	else if (of_machine_is_compatible("st,spear320"))
-		spear320_clk_init(soc_config_base);
+		spear320_clk_init(soc_config_base, ras_apb_clk);
 }
diff --git a/drivers/clk/st/Makefile b/drivers/clk/st/Makefile
index c7455ffdbdf..ede7b2f1309 100644
--- a/drivers/clk/st/Makefile
+++ b/drivers/clk/st/Makefile
@@ -1 +1 @@
-obj-y += clkgen-mux.o clkgen-pll.o clkgen-fsyn.o
+obj-y += clkgen-mux.o clkgen-pll.o clkgen-fsyn.o clk-flexgen.o
diff --git a/drivers/clk/st/clk-flexgen.c b/drivers/clk/st/clk-flexgen.c
new file mode 100644
index 00000000000..2282cef9f2f
--- /dev/null
+++ b/drivers/clk/st/clk-flexgen.c
@@ -0,0 +1,331 @@
+/*
+ * clk-flexgen.c
+ *
+ * Copyright (C) ST-Microelectronics SA 2013
+ * Author:  Maxime Coquelin <maxime.coquelin@st.com> for ST-Microelectronics.
+ * License terms:  GNU General Public License (GPL), version 2  */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+struct flexgen {
+	struct clk_hw hw;
+
+	/* Crossbar */
+	struct clk_mux mux;
+	/* Pre-divisor's gate */
+	struct clk_gate pgate;
+	/* Pre-divisor */
+	struct clk_divider pdiv;
+	/* Final divisor's gate */
+	struct clk_gate fgate;
+	/* Final divisor */
+	struct clk_divider fdiv;
+};
+
+#define to_flexgen(_hw) container_of(_hw, struct flexgen, hw)
+
+static int flexgen_enable(struct clk_hw *hw)
+{
+	struct flexgen *flexgen = to_flexgen(hw);
+	struct clk_hw *pgate_hw = &flexgen->pgate.hw;
+	struct clk_hw *fgate_hw = &flexgen->fgate.hw;
+
+	pgate_hw->clk = hw->clk;
+	fgate_hw->clk = hw->clk;
+
+	clk_gate_ops.enable(pgate_hw);
+
+	clk_gate_ops.enable(fgate_hw);
+
+	pr_debug("%s: flexgen output enabled\n", __clk_get_name(hw->clk));
+	return 0;
+}
+
+static void flexgen_disable(struct clk_hw *hw)
+{
+	struct flexgen *flexgen = to_flexgen(hw);
+	struct clk_hw *fgate_hw = &flexgen->fgate.hw;
+
+	/* disable only the final gate */
+	fgate_hw->clk = hw->clk;
+
+	clk_gate_ops.disable(fgate_hw);
+
+	pr_debug("%s: flexgen output disabled\n", __clk_get_name(hw->clk));
+}
+
+static int flexgen_is_enabled(struct clk_hw *hw)
+{
+	struct flexgen *flexgen = to_flexgen(hw);
+	struct clk_hw *fgate_hw = &flexgen->fgate.hw;
+
+	fgate_hw->clk = hw->clk;
+
+	if (!clk_gate_ops.is_enabled(fgate_hw))
+		return 0;
+
+	return 1;
+}
+
+static u8 flexgen_get_parent(struct clk_hw *hw)
+{
+	struct flexgen *flexgen = to_flexgen(hw);
+	struct clk_hw *mux_hw = &flexgen->mux.hw;
+
+	mux_hw->clk = hw->clk;
+
+	return clk_mux_ops.get_parent(mux_hw);
+}
+
+static int flexgen_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct flexgen *flexgen = to_flexgen(hw);
+	struct clk_hw *mux_hw = &flexgen->mux.hw;
+
+	mux_hw->clk = hw->clk;
+
+	return clk_mux_ops.set_parent(mux_hw, index);
+}
+
+static inline unsigned long
+clk_best_div(unsigned long parent_rate, unsigned long rate)
+{
+	return parent_rate / rate + ((rate > (2*(parent_rate % rate))) ? 0 : 1);
+}
+
+static long flexgen_round_rate(struct clk_hw *hw, unsigned long rate,
+				   unsigned long *prate)
+{
+	unsigned long div;
+
+	/* Round div according to exact prate and wished rate */
+	div = clk_best_div(*prate, rate);
+
+	if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+		*prate = rate * div;
+		return rate;
+	}
+
+	return *prate / div;
+}
+
+unsigned long flexgen_recalc_rate(struct clk_hw *hw,
+		unsigned long parent_rate)
+{
+	struct flexgen *flexgen = to_flexgen(hw);
+	struct clk_hw *pdiv_hw = &flexgen->pdiv.hw;
+	struct clk_hw *fdiv_hw = &flexgen->fdiv.hw;
+	unsigned long mid_rate;
+
+	pdiv_hw->clk = hw->clk;
+	fdiv_hw->clk = hw->clk;
+
+	mid_rate = clk_divider_ops.recalc_rate(pdiv_hw, parent_rate);
+
+	return clk_divider_ops.recalc_rate(fdiv_hw, mid_rate);
+}
+
+static int flexgen_set_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long parent_rate)
+{
+	struct flexgen *flexgen = to_flexgen(hw);
+	struct clk_hw *pdiv_hw = &flexgen->pdiv.hw;
+	struct clk_hw *fdiv_hw = &flexgen->fdiv.hw;
+	unsigned long primary_div = 0;
+	int ret = 0;
+
+	pdiv_hw->clk = hw->clk;
+	fdiv_hw->clk = hw->clk;
+
+	primary_div = clk_best_div(parent_rate, rate);
+
+	clk_divider_ops.set_rate(fdiv_hw, parent_rate, parent_rate);
+	ret = clk_divider_ops.set_rate(pdiv_hw, rate, rate * primary_div);
+
+	return ret;
+}
+
+static const struct clk_ops flexgen_ops = {
+	.enable = flexgen_enable,
+	.disable = flexgen_disable,
+	.is_enabled = flexgen_is_enabled,
+	.get_parent = flexgen_get_parent,
+	.set_parent = flexgen_set_parent,
+	.round_rate = flexgen_round_rate,
+	.recalc_rate = flexgen_recalc_rate,
+	.set_rate = flexgen_set_rate,
+};
+
+struct clk *clk_register_flexgen(const char *name,
+				const char **parent_names, u8 num_parents,
+				void __iomem *reg, spinlock_t *lock, u32 idx,
+				unsigned long flexgen_flags) {
+	struct flexgen *fgxbar;
+	struct clk *clk;
+	struct clk_init_data init;
+	u32  xbar_shift;
+	void __iomem *xbar_reg, *fdiv_reg;
+
+	fgxbar = kzalloc(sizeof(struct flexgen), GFP_KERNEL);
+	if (!fgxbar)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &flexgen_ops;
+	init.flags = CLK_IS_BASIC | flexgen_flags;
+	init.parent_names = parent_names;
+	init.num_parents = num_parents;
+
+	xbar_reg = reg + 0x18 + (idx & ~0x3);
+	xbar_shift = (idx % 4) * 0x8;
+	fdiv_reg = reg + 0x164 + idx * 4;
+
+	/* Crossbar element config */
+	fgxbar->mux.lock = lock;
+	fgxbar->mux.mask = BIT(6) - 1;
+	fgxbar->mux.reg = xbar_reg;
+	fgxbar->mux.shift = xbar_shift;
+	fgxbar->mux.table = NULL;
+
+
+	/* Pre-divider's gate config (in xbar register)*/
+	fgxbar->pgate.lock = lock;
+	fgxbar->pgate.reg = xbar_reg;
+	fgxbar->pgate.bit_idx = xbar_shift + 6;
+
+	/* Pre-divider config */
+	fgxbar->pdiv.lock = lock;
+	fgxbar->pdiv.reg = reg + 0x58 + idx * 4;
+	fgxbar->pdiv.width = 10;
+
+	/* Final divider's gate config */
+	fgxbar->fgate.lock = lock;
+	fgxbar->fgate.reg = fdiv_reg;
+	fgxbar->fgate.bit_idx = 6;
+
+	/* Final divider config */
+	fgxbar->fdiv.lock = lock;
+	fgxbar->fdiv.reg = fdiv_reg;
+	fgxbar->fdiv.width = 6;
+
+	fgxbar->hw.init = &init;
+
+	clk = clk_register(NULL, &fgxbar->hw);
+	if (IS_ERR(clk))
+		kfree(fgxbar);
+	else
+		pr_debug("%s: parent %s rate %u\n",
+			__clk_get_name(clk),
+			__clk_get_name(clk_get_parent(clk)),
+			(unsigned int)clk_get_rate(clk));
+	return clk;
+}
+
+static const char ** __init flexgen_get_parents(struct device_node *np,
+						       int *num_parents)
+{
+	const char **parents;
+	int nparents, i;
+
+	nparents = of_count_phandle_with_args(np, "clocks", "#clock-cells");
+	if (WARN_ON(nparents <= 0))
+		return NULL;
+
+	parents = kcalloc(nparents, sizeof(const char *), GFP_KERNEL);
+	if (!parents)
+		return NULL;
+
+	for (i = 0; i < nparents; i++)
+		parents[i] = of_clk_get_parent_name(np, i);
+
+	*num_parents = nparents;
+	return parents;
+}
+
+void __init st_of_flexgen_setup(struct device_node *np)
+{
+	struct device_node *pnode;
+	void __iomem *reg;
+	struct clk_onecell_data *clk_data;
+	const char **parents;
+	int num_parents, i;
+	spinlock_t *rlock = NULL;
+	unsigned long flex_flags = 0;
+
+	pnode = of_get_parent(np);
+	if (!pnode)
+		return;
+
+	reg = of_iomap(pnode, 0);
+	if (!reg)
+		return;
+
+	parents = flexgen_get_parents(np, &num_parents);
+	if (!parents)
+		return;
+
+	clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL);
+	if (!clk_data)
+		goto err;
+
+	clk_data->clk_num = of_property_count_strings(np ,
+			"clock-output-names");
+	if (clk_data->clk_num <= 0) {
+		pr_err("%s: Failed to get number of output clocks (%d)",
+				__func__, clk_data->clk_num);
+		goto err;
+	}
+
+	clk_data->clks = kcalloc(clk_data->clk_num, sizeof(struct clk *),
+			GFP_KERNEL);
+	if (!clk_data->clks)
+		goto err;
+
+	rlock = kzalloc(sizeof(spinlock_t), GFP_KERNEL);
+	if (!rlock)
+		goto err;
+
+	for (i = 0; i < clk_data->clk_num; i++) {
+		struct clk *clk;
+		const char *clk_name;
+
+		if (of_property_read_string_index(np, "clock-output-names",
+						  i, &clk_name)) {
+			break;
+		}
+
+		/*
+		 * If we read an empty clock name then the output is unused
+		 */
+		if (*clk_name == '\0')
+			continue;
+
+		clk = clk_register_flexgen(clk_name, parents, num_parents,
+					   reg, rlock, i, flex_flags);
+
+		if (IS_ERR(clk))
+			goto err;
+
+		clk_data->clks[i] = clk;
+	}
+
+	kfree(parents);
+	of_clk_add_provider(np, of_clk_src_onecell_get, clk_data);
+
+	return;
+
+err:
+	if (clk_data)
+		kfree(clk_data->clks);
+	kfree(clk_data);
+	kfree(parents);
+	kfree(rlock);
+}
+CLK_OF_DECLARE(flexgen, "st,flexgen", st_of_flexgen_setup);
diff --git a/drivers/clk/st/clkgen-fsyn.c b/drivers/clk/st/clkgen-fsyn.c
index 4f53ee0778d..af94ed82cfc 100644
--- a/drivers/clk/st/clkgen-fsyn.c
+++ b/drivers/clk/st/clkgen-fsyn.c
@@ -41,7 +41,7 @@ struct stm_fs {
 	unsigned long nsdiv;
 };
 
-static struct stm_fs fs216c65_rtbl[] = {
+static const struct stm_fs fs216c65_rtbl[] = {
 	{ .mdiv = 0x1f, .pe = 0x0,	.sdiv = 0x7,	.nsdiv = 0 },	/* 312.5 Khz */
 	{ .mdiv = 0x17, .pe = 0x25ed,	.sdiv = 0x1,	.nsdiv = 0 },	/* 27    MHz */
 	{ .mdiv = 0x1a, .pe = 0x7b36,	.sdiv = 0x2,	.nsdiv = 1 },	/* 36.87 MHz */
@@ -49,31 +49,86 @@ static struct stm_fs fs216c65_rtbl[] = {
 	{ .mdiv = 0x11, .pe = 0x1c72,	.sdiv = 0x1,	.nsdiv = 1 },	/* 108   MHz */
 };
 
-static struct stm_fs fs432c65_rtbl[] = {
-	{ .mdiv = 0x1f, .pe = 0x0,	.sdiv = 0x7,	.nsdiv = 0 },	/* 625   Khz */
-	{ .mdiv = 0x11, .pe = 0x1c72,	.sdiv = 0x2,	.nsdiv = 1 },	/* 108   MHz */
-	{ .mdiv = 0x19, .pe = 0x121a,	.sdiv = 0x0,	.nsdiv = 1 },	/* 297   MHz */
+static const struct stm_fs fs432c65_rtbl[] = {
+	{ .mdiv = 0x1f, .pe = 0x0,	.sdiv = 0x7,	.nsdiv = 0 },	/* 625     Khz */
+	{ .mdiv = 0x13, .pe = 0x777c,	.sdiv = 0x4,	.nsdiv = 1 },	/* 25.175  MHz */
+	{ .mdiv = 0x19, .pe = 0x4d35,	.sdiv = 0x2,	.nsdiv = 0 },	/* 25.200  MHz */
+	{ .mdiv = 0x11, .pe = 0x1c72,	.sdiv = 0x4,	.nsdiv = 1 },	/* 27.000  MHz */
+	{ .mdiv = 0x17, .pe = 0x28f5,	.sdiv = 0x2,	.nsdiv = 0 },	/* 27.027  MHz */
+	{ .mdiv = 0x16, .pe = 0x3359,	.sdiv = 0x2,	.nsdiv = 0 },	/* 28.320  MHz */
+	{ .mdiv = 0x1f, .pe = 0x2083,	.sdiv = 0x3,	.nsdiv = 1 },	/* 30.240  MHz */
+	{ .mdiv = 0x1e, .pe = 0x430d,	.sdiv = 0x3,	.nsdiv = 1 },	/* 31.500  MHz */
+	{ .mdiv = 0x17, .pe = 0x0,	.sdiv = 0x3,	.nsdiv = 1 },	/* 40.000  MHz */
+	{ .mdiv = 0x19, .pe = 0x121a,	.sdiv = 0x1,	.nsdiv = 0 },	/* 49.500  MHz */
+	{ .mdiv = 0x13, .pe = 0x6667,	.sdiv = 0x3,	.nsdiv = 1 },	/* 50.000  MHz */
+	{ .mdiv = 0x10, .pe = 0x1ee6,	.sdiv = 0x3,	.nsdiv = 1 },	/* 57.284  MHz */
+	{ .mdiv = 0x1d, .pe = 0x3b14,	.sdiv = 0x2,	.nsdiv = 1 },	/* 65.000  MHz */
+	{ .mdiv = 0x12, .pe = 0x7c65,	.sdiv = 0x1,	.nsdiv = 0 },	/* 71.000  MHz */
+	{ .mdiv = 0x19, .pe = 0xecd,	.sdiv = 0x2,	.nsdiv = 1 },	/* 74.176  MHz */
+	{ .mdiv = 0x19, .pe = 0x121a,	.sdiv = 0x2,	.nsdiv = 1 },	/* 74.250  MHz */
+	{ .mdiv = 0x19, .pe = 0x3334,	.sdiv = 0x2,	.nsdiv = 1 },	/* 75.000  MHz */
+	{ .mdiv = 0x18, .pe = 0x5138,	.sdiv = 0x2,	.nsdiv = 1 },	/* 78.800  MHz */
+	{ .mdiv = 0x1d, .pe = 0x77d,	.sdiv = 0x0,	.nsdiv = 0 },	/* 85.500  MHz */
+	{ .mdiv = 0x1c, .pe = 0x13d5,	.sdiv = 0x0,	.nsdiv = 0 },	/* 88.750  MHz */
+	{ .mdiv = 0x11, .pe = 0x1c72,	.sdiv = 0x2,	.nsdiv = 1 },	/* 108.000 MHz */
+	{ .mdiv = 0x17, .pe = 0x28f5,	.sdiv = 0x0,	.nsdiv = 0 },	/* 108.108 MHz */
+	{ .mdiv = 0x10, .pe = 0x6e26,	.sdiv = 0x2,	.nsdiv = 1 },	/* 118.963 MHz */
+	{ .mdiv = 0x15, .pe = 0x3e63,	.sdiv = 0x0,	.nsdiv = 0 },	/* 119.000 MHz */
+	{ .mdiv = 0x1c, .pe = 0x471d,	.sdiv = 0x1,	.nsdiv = 1 },	/* 135.000 MHz */
+	{ .mdiv = 0x19, .pe = 0xecd,	.sdiv = 0x1,	.nsdiv = 1 },	/* 148.352 MHz */
+	{ .mdiv = 0x19, .pe = 0x121a,	.sdiv = 0x1,	.nsdiv = 1 },	/* 148.500 MHz */
+	{ .mdiv = 0x19, .pe = 0x121a,	.sdiv = 0x0,	.nsdiv = 1 },	/* 297     MHz */
 };
 
-static struct stm_fs fs660c32_rtbl[] = {
-	{ .mdiv = 0x01, .pe = 0x2aaa,	.sdiv = 0x8,	.nsdiv = 0 },	/* 600   KHz */
-	{ .mdiv = 0x02, .pe = 0x3d33,	.sdiv = 0x0,	.nsdiv = 0 },	/* 148.5 Mhz */
-	{ .mdiv = 0x13, .pe = 0x5bcc,	.sdiv = 0x0,	.nsdiv = 1 },	/* 297   Mhz */
-	{ .mdiv = 0x0e, .pe = 0x1025,	.sdiv = 0x0,	.nsdiv = 1 },	/* 333   Mhz */
-	{ .mdiv = 0x0b, .pe = 0x715f,	.sdiv = 0x0,	.nsdiv = 1 },	/* 350   Mhz */
+static const struct stm_fs fs660c32_rtbl[] = {
+	{ .mdiv = 0x14, .pe = 0x376b,	.sdiv = 0x4,	.nsdiv = 1 },	/* 25.175  MHz */
+	{ .mdiv = 0x14, .pe = 0x30c3,	.sdiv = 0x4,	.nsdiv = 1 },	/* 25.200  MHz */
+	{ .mdiv = 0x10, .pe = 0x71c7,	.sdiv = 0x4,	.nsdiv = 1 },	/* 27.000  MHz */
+	{ .mdiv = 0x00, .pe = 0x47af,	.sdiv = 0x3,	.nsdiv = 0 },	/* 27.027  MHz */
+	{ .mdiv = 0x0e, .pe = 0x4e1a,	.sdiv = 0x4,	.nsdiv = 1 },	/* 28.320  MHz */
+	{ .mdiv = 0x0b, .pe = 0x534d,	.sdiv = 0x4,	.nsdiv = 1 },	/* 30.240  MHz */
+	{ .mdiv = 0x17, .pe = 0x6fbf,	.sdiv = 0x2,	.nsdiv = 0 },	/* 31.500  MHz */
+	{ .mdiv = 0x01, .pe = 0x0,	.sdiv = 0x4,	.nsdiv = 1 },	/* 40.000  MHz */
+	{ .mdiv = 0x15, .pe = 0x2aab,	.sdiv = 0x3,	.nsdiv = 1 },	/* 49.500  MHz */
+	{ .mdiv = 0x14, .pe = 0x6666,	.sdiv = 0x3,	.nsdiv = 1 },	/* 50.000  MHz */
+	{ .mdiv = 0x1d, .pe = 0x395f,	.sdiv = 0x1,	.nsdiv = 0 },	/* 57.284  MHz */
+	{ .mdiv = 0x08, .pe = 0x4ec5,	.sdiv = 0x3,	.nsdiv = 1 },	/* 65.000  MHz */
+	{ .mdiv = 0x05, .pe = 0x1770,	.sdiv = 0x3,	.nsdiv = 1 },	/* 71.000  MHz */
+	{ .mdiv = 0x03, .pe = 0x4ba7,	.sdiv = 0x3,	.nsdiv = 1 },	/* 74.176  MHz */
+	{ .mdiv = 0x0f, .pe = 0x3426,	.sdiv = 0x1,	.nsdiv = 0 },	/* 74.250  MHz */
+	{ .mdiv = 0x0e, .pe = 0x7777,	.sdiv = 0x1,	.nsdiv = 0 },	/* 75.000  MHz */
+	{ .mdiv = 0x01, .pe = 0x4053,	.sdiv = 0x3,	.nsdiv = 1 },	/* 78.800  MHz */
+	{ .mdiv = 0x09, .pe = 0x15b5,	.sdiv = 0x1,	.nsdiv = 0 },	/* 85.500  MHz */
+	{ .mdiv = 0x1b, .pe = 0x3f19,	.sdiv = 0x2,	.nsdiv = 1 },	/* 88.750  MHz */
+	{ .mdiv = 0x10, .pe = 0x71c7,	.sdiv = 0x2,	.nsdiv = 1 },	/* 108.000 MHz */
+	{ .mdiv = 0x00, .pe = 0x47af,	.sdiv = 0x1,	.nsdiv = 0 },	/* 108.108 MHz */
+	{ .mdiv = 0x0c, .pe = 0x3118,	.sdiv = 0x2,	.nsdiv = 1 },	/* 118.963 MHz */
+	{ .mdiv = 0x0c, .pe = 0x2f54,	.sdiv = 0x2,	.nsdiv = 1 },	/* 119.000 MHz */
+	{ .mdiv = 0x07, .pe = 0xe39,	.sdiv = 0x2,	.nsdiv = 1 },	/* 135.000 MHz */
+	{ .mdiv = 0x03, .pe = 0x4ba7,	.sdiv = 0x2,	.nsdiv = 1 },	/* 148.352 MHz */
+	{ .mdiv = 0x0f, .pe = 0x3426,	.sdiv = 0x0,	.nsdiv = 0 },	/* 148.500 MHz */
+	{ .mdiv = 0x03, .pe = 0x4ba7,	.sdiv = 0x1,	.nsdiv = 1 },	/* 296.704 MHz */
+	{ .mdiv = 0x03, .pe = 0x471c,	.sdiv = 0x1,	.nsdiv = 1 },	/* 297.000 MHz */
+	{ .mdiv = 0x00, .pe = 0x295f,	.sdiv = 0x1,	.nsdiv = 1 },	/* 326.700 MHz */
+	{ .mdiv = 0x1f, .pe = 0x3633,	.sdiv = 0x0,	.nsdiv = 1 },	/* 333.000 MHz */
+	{ .mdiv = 0x1c, .pe = 0x0,	.sdiv = 0x0,	.nsdiv = 1 },	/* 352.000 Mhz */
 };
 
 struct clkgen_quadfs_data {
 	bool reset_present;
 	bool bwfilter_present;
 	bool lockstatus_present;
+	bool powerup_polarity;
+	bool standby_polarity;
 	bool nsdiv_present;
+	bool nrst_present;
 	struct clkgen_field ndiv;
 	struct clkgen_field ref_bw;
 	struct clkgen_field nreset;
 	struct clkgen_field npda;
 	struct clkgen_field lock_status;
 
+	struct clkgen_field nrst[QUADFS_MAX_CHAN];
 	struct clkgen_field nsb[QUADFS_MAX_CHAN];
 	struct clkgen_field en[QUADFS_MAX_CHAN];
 	struct clkgen_field mdiv[QUADFS_MAX_CHAN];
@@ -82,9 +137,9 @@ struct clkgen_quadfs_data {
 	struct clkgen_field nsdiv[QUADFS_MAX_CHAN];
 
 	const struct clk_ops *pll_ops;
-	struct stm_fs *rtbl;
+	const struct stm_fs *rtbl;
 	u8 rtbl_cnt;
-	int  (*get_rate)(unsigned long , struct stm_fs *,
+	int  (*get_rate)(unsigned long , const struct stm_fs *,
 			unsigned long *);
 };
 
@@ -94,11 +149,11 @@ static const struct clk_ops st_quadfs_fs216c65_ops;
 static const struct clk_ops st_quadfs_fs432c65_ops;
 static const struct clk_ops st_quadfs_fs660c32_ops;
 
-static int clk_fs216c65_get_rate(unsigned long, struct stm_fs *,
+static int clk_fs216c65_get_rate(unsigned long, const struct stm_fs *,
 		unsigned long *);
-static int clk_fs432c65_get_rate(unsigned long, struct stm_fs *,
+static int clk_fs432c65_get_rate(unsigned long, const struct stm_fs *,
 		unsigned long *);
-static int clk_fs660c32_dig_get_rate(unsigned long, struct stm_fs *,
+static int clk_fs660c32_dig_get_rate(unsigned long, const struct stm_fs *,
 		unsigned long *);
 /*
  * Values for all of the standalone instances of this clock
@@ -106,7 +161,7 @@ static int clk_fs660c32_dig_get_rate(unsigned long, struct stm_fs *,
  * that the individual channel standby control bits (nsb) are in the
  * first register along with the PLL control bits.
  */
-static struct clkgen_quadfs_data st_fs216c65_416 = {
+static const struct clkgen_quadfs_data st_fs216c65_416 = {
 	/* 416 specific */
 	.npda	= CLKGEN_FIELD(0x0, 0x1, 14),
 	.nsb	= { CLKGEN_FIELD(0x0, 0x1, 10),
@@ -143,7 +198,7 @@ static struct clkgen_quadfs_data st_fs216c65_416 = {
 	.get_rate	= clk_fs216c65_get_rate,
 };
 
-static struct clkgen_quadfs_data st_fs432c65_416 = {
+static const struct clkgen_quadfs_data st_fs432c65_416 = {
 	.npda	= CLKGEN_FIELD(0x0, 0x1, 14),
 	.nsb	= { CLKGEN_FIELD(0x0, 0x1, 10),
 		    CLKGEN_FIELD(0x0, 0x1, 11),
@@ -179,7 +234,7 @@ static struct clkgen_quadfs_data st_fs432c65_416 = {
 	.get_rate	= clk_fs432c65_get_rate,
 };
 
-static struct clkgen_quadfs_data st_fs660c32_E_416 = {
+static const struct clkgen_quadfs_data st_fs660c32_E_416 = {
 	.npda	= CLKGEN_FIELD(0x0, 0x1, 14),
 	.nsb	= { CLKGEN_FIELD(0x0, 0x1, 10),
 		    CLKGEN_FIELD(0x0, 0x1, 11),
@@ -215,7 +270,7 @@ static struct clkgen_quadfs_data st_fs660c32_E_416 = {
 	.get_rate	= clk_fs660c32_dig_get_rate,
 };
 
-static struct clkgen_quadfs_data st_fs660c32_F_416 = {
+static const struct clkgen_quadfs_data st_fs660c32_F_416 = {
 	.npda	= CLKGEN_FIELD(0x0, 0x1, 14),
 	.nsb	= { CLKGEN_FIELD(0x0, 0x1, 10),
 		    CLKGEN_FIELD(0x0, 0x1, 11),
@@ -251,6 +306,91 @@ static struct clkgen_quadfs_data st_fs660c32_F_416 = {
 	.get_rate	= clk_fs660c32_dig_get_rate,
 };
 
+static const struct clkgen_quadfs_data st_fs660c32_C_407 = {
+	.nrst_present = true,
+	.nrst	= { CLKGEN_FIELD(0x2f0, 0x1, 0),
+		    CLKGEN_FIELD(0x2f0, 0x1, 1),
+		    CLKGEN_FIELD(0x2f0, 0x1, 2),
+		    CLKGEN_FIELD(0x2f0, 0x1, 3) },
+	.npda	= CLKGEN_FIELD(0x2f0, 0x1, 12),
+	.nsb	= { CLKGEN_FIELD(0x2f0, 0x1, 8),
+		    CLKGEN_FIELD(0x2f0, 0x1, 9),
+		    CLKGEN_FIELD(0x2f0, 0x1, 10),
+		    CLKGEN_FIELD(0x2f0, 0x1, 11) },
+	.nsdiv_present = true,
+	.nsdiv	= { CLKGEN_FIELD(0x304, 0x1, 24),
+		    CLKGEN_FIELD(0x308, 0x1, 24),
+		    CLKGEN_FIELD(0x30c, 0x1, 24),
+		    CLKGEN_FIELD(0x310, 0x1, 24) },
+	.mdiv	= { CLKGEN_FIELD(0x304, 0x1f, 15),
+		    CLKGEN_FIELD(0x308, 0x1f, 15),
+		    CLKGEN_FIELD(0x30c, 0x1f, 15),
+		    CLKGEN_FIELD(0x310, 0x1f, 15) },
+	.en	= { CLKGEN_FIELD(0x2fc, 0x1, 0),
+		    CLKGEN_FIELD(0x2fc, 0x1, 1),
+		    CLKGEN_FIELD(0x2fc, 0x1, 2),
+		    CLKGEN_FIELD(0x2fc, 0x1, 3) },
+	.ndiv	= CLKGEN_FIELD(0x2f4, 0x7, 16),
+	.pe	= { CLKGEN_FIELD(0x304, 0x7fff, 0),
+		    CLKGEN_FIELD(0x308, 0x7fff, 0),
+		    CLKGEN_FIELD(0x30c, 0x7fff, 0),
+		    CLKGEN_FIELD(0x310, 0x7fff, 0) },
+	.sdiv	= { CLKGEN_FIELD(0x304, 0xf, 20),
+		    CLKGEN_FIELD(0x308, 0xf, 20),
+		    CLKGEN_FIELD(0x30c, 0xf, 20),
+		    CLKGEN_FIELD(0x310, 0xf, 20) },
+	.lockstatus_present = true,
+	.lock_status = CLKGEN_FIELD(0x2A0, 0x1, 24),
+	.powerup_polarity = 1,
+	.standby_polarity = 1,
+	.pll_ops	= &st_quadfs_pll_c32_ops,
+	.rtbl		= fs660c32_rtbl,
+	.rtbl_cnt	= ARRAY_SIZE(fs660c32_rtbl),
+	.get_rate	= clk_fs660c32_dig_get_rate,
+};
+
+static const struct clkgen_quadfs_data st_fs660c32_D_407 = {
+	.nrst_present = true,
+	.nrst	= { CLKGEN_FIELD(0x2a0, 0x1, 0),
+		    CLKGEN_FIELD(0x2a0, 0x1, 1),
+		    CLKGEN_FIELD(0x2a0, 0x1, 2),
+		    CLKGEN_FIELD(0x2a0, 0x1, 3) },
+	.ndiv	= CLKGEN_FIELD(0x2a4, 0x7, 16),
+	.pe	= { CLKGEN_FIELD(0x2b4, 0x7fff, 0),
+		    CLKGEN_FIELD(0x2b8, 0x7fff, 0),
+		    CLKGEN_FIELD(0x2bc, 0x7fff, 0),
+		    CLKGEN_FIELD(0x2c0, 0x7fff, 0) },
+	.sdiv	= { CLKGEN_FIELD(0x2b4, 0xf, 20),
+		    CLKGEN_FIELD(0x2b8, 0xf, 20),
+		    CLKGEN_FIELD(0x2bc, 0xf, 20),
+		    CLKGEN_FIELD(0x2c0, 0xf, 20) },
+	.npda	= CLKGEN_FIELD(0x2a0, 0x1, 12),
+	.nsb	= { CLKGEN_FIELD(0x2a0, 0x1, 8),
+		    CLKGEN_FIELD(0x2a0, 0x1, 9),
+		    CLKGEN_FIELD(0x2a0, 0x1, 10),
+		    CLKGEN_FIELD(0x2a0, 0x1, 11) },
+	.nsdiv_present = true,
+	.nsdiv	= { CLKGEN_FIELD(0x2b4, 0x1, 24),
+		    CLKGEN_FIELD(0x2b8, 0x1, 24),
+		    CLKGEN_FIELD(0x2bc, 0x1, 24),
+		    CLKGEN_FIELD(0x2c0, 0x1, 24) },
+	.mdiv	= { CLKGEN_FIELD(0x2b4, 0x1f, 15),
+		    CLKGEN_FIELD(0x2b8, 0x1f, 15),
+		    CLKGEN_FIELD(0x2bc, 0x1f, 15),
+		    CLKGEN_FIELD(0x2c0, 0x1f, 15) },
+	.en	= { CLKGEN_FIELD(0x2ac, 0x1, 0),
+		    CLKGEN_FIELD(0x2ac, 0x1, 1),
+		    CLKGEN_FIELD(0x2ac, 0x1, 2),
+		    CLKGEN_FIELD(0x2ac, 0x1, 3) },
+	.lockstatus_present = true,
+	.lock_status = CLKGEN_FIELD(0x2A0, 0x1, 24),
+	.powerup_polarity = 1,
+	.standby_polarity = 1,
+	.pll_ops	= &st_quadfs_pll_c32_ops,
+	.rtbl		= fs660c32_rtbl,
+	.rtbl_cnt	= ARRAY_SIZE(fs660c32_rtbl),
+	.get_rate	= clk_fs660c32_dig_get_rate,};
+
 /**
  * DOC: A Frequency Synthesizer that multiples its input clock by a fixed factor
  *
@@ -308,7 +448,7 @@ static int quadfs_pll_enable(struct clk_hw *hw)
 	/*
 	 * Power up the PLL
 	 */
-	CLKGEN_WRITE(pll, npda, 1);
+	CLKGEN_WRITE(pll, npda, !pll->data->powerup_polarity);
 
 	if (pll->lock)
 		spin_unlock_irqrestore(pll->lock, flags);
@@ -335,7 +475,7 @@ static void quadfs_pll_disable(struct clk_hw *hw)
 	 * Powerdown the PLL and then put block into soft reset if we have
 	 * reset control.
 	 */
-	CLKGEN_WRITE(pll, npda, 0);
+	CLKGEN_WRITE(pll, npda, pll->data->powerup_polarity);
 
 	if (pll->data->reset_present)
 		CLKGEN_WRITE(pll, nreset, 0);
@@ -611,7 +751,10 @@ static int quadfs_fsynth_enable(struct clk_hw *hw)
 	if (fs->lock)
 		spin_lock_irqsave(fs->lock, flags);
 
-	CLKGEN_WRITE(fs, nsb[fs->chan], 1);
+	CLKGEN_WRITE(fs, nsb[fs->chan], !fs->data->standby_polarity);
+
+	if (fs->data->nrst_present)
+		CLKGEN_WRITE(fs, nrst[fs->chan], 0);
 
 	if (fs->lock)
 		spin_unlock_irqrestore(fs->lock, flags);
@@ -631,7 +774,7 @@ static void quadfs_fsynth_disable(struct clk_hw *hw)
 	if (fs->lock)
 		spin_lock_irqsave(fs->lock, flags);
 
-	CLKGEN_WRITE(fs, nsb[fs->chan], 0);
+	CLKGEN_WRITE(fs, nsb[fs->chan], !fs->data->standby_polarity);
 
 	if (fs->lock)
 		spin_unlock_irqrestore(fs->lock, flags);
@@ -645,12 +788,12 @@ static int quadfs_fsynth_is_enabled(struct clk_hw *hw)
 	pr_debug("%s: %s enable bit = 0x%x\n",
 		 __func__, __clk_get_name(hw->clk), nsb);
 
-	return !!nsb;
+	return fs->data->standby_polarity ? !nsb : !!nsb;
 }
 
 #define P15			(uint64_t)(1 << 15)
 
-static int clk_fs216c65_get_rate(unsigned long input, struct stm_fs *fs,
+static int clk_fs216c65_get_rate(unsigned long input, const struct stm_fs *fs,
 		unsigned long *rate)
 {
 	uint64_t res;
@@ -670,7 +813,7 @@ static int clk_fs216c65_get_rate(unsigned long input, struct stm_fs *fs,
 	return 0;
 }
 
-static int clk_fs432c65_get_rate(unsigned long input, struct stm_fs *fs,
+static int clk_fs432c65_get_rate(unsigned long input, const struct stm_fs *fs,
 		unsigned long *rate)
 {
 	uint64_t res;
@@ -693,7 +836,7 @@ static int clk_fs432c65_get_rate(unsigned long input, struct stm_fs *fs,
 #define P20		(uint64_t)(1 << 20)
 
 static int clk_fs660c32_dig_get_rate(unsigned long input,
-				struct stm_fs *fs, unsigned long *rate)
+				const struct stm_fs *fs, unsigned long *rate)
 {
 	unsigned long s = (1 << fs->sdiv);
 	unsigned long ns;
@@ -749,7 +892,7 @@ static long quadfs_find_best_rate(struct clk_hw *hw, unsigned long drate,
 {
 	struct st_clk_quadfs_fsynth *fs = to_quadfs_fsynth(hw);
 	int (*clk_fs_get_rate)(unsigned long ,
-				struct stm_fs *, unsigned long *);
+				const struct stm_fs *, unsigned long *);
 	struct stm_fs prev_params;
 	unsigned long prev_rate, rate = 0;
 	unsigned long diff_rate, prev_diff_rate = ~0;
@@ -793,7 +936,7 @@ static unsigned long quadfs_recalc_rate(struct clk_hw *hw,
 	unsigned long rate = 0;
 	struct stm_fs params;
 	int (*clk_fs_get_rate)(unsigned long ,
-				struct stm_fs *, unsigned long *);
+				const struct stm_fs *, unsigned long *);
 
 	clk_fs_get_rate = fs->data->get_rate;
 
@@ -917,19 +1060,31 @@ static struct clk * __init st_clk_register_quadfs_fsynth(
 static struct of_device_id quadfs_of_match[] = {
 	{
 		.compatible = "st,stih416-quadfs216",
-		.data = (void *)&st_fs216c65_416
+		.data = &st_fs216c65_416
 	},
 	{
 		.compatible = "st,stih416-quadfs432",
-		.data = (void *)&st_fs432c65_416
+		.data = &st_fs432c65_416
 	},
 	{
 		.compatible = "st,stih416-quadfs660-E",
-		.data = (void *)&st_fs660c32_E_416
+		.data = &st_fs660c32_E_416
 	},
 	{
 		.compatible = "st,stih416-quadfs660-F",
-		.data = (void *)&st_fs660c32_F_416
+		.data = &st_fs660c32_F_416
+	},
+	{
+		.compatible = "st,stih407-quadfs660-C",
+		.data = &st_fs660c32_C_407
+	},
+	{
+		.compatible = "st,stih407-quadfs660-D",
+		.data = &st_fs660c32_D_407
+	},
+	{
+		.compatible = "st,stih407-quadfs660-D",
+		.data = (void *)&st_fs660c32_D_407
 	},
 	{}
 };
diff --git a/drivers/clk/st/clkgen-mux.c b/drivers/clk/st/clkgen-mux.c
index a329906d1e8..79dc40b5cc6 100644
--- a/drivers/clk/st/clkgen-mux.c
+++ b/drivers/clk/st/clkgen-mux.c
@@ -580,6 +580,11 @@ static struct clkgen_mux_data stih416_a9_mux_data = {
 	.shift = 0,
 	.width = 2,
 };
+static struct clkgen_mux_data stih407_a9_mux_data = {
+	.offset = 0x1a4,
+	.shift = 1,
+	.width = 2,
+};
 
 static struct of_device_id mux_of_match[] = {
 	{
@@ -610,6 +615,10 @@ static struct of_device_id mux_of_match[] = {
 		.compatible = "st,stih416-clkgen-a9-mux",
 		.data = &stih416_a9_mux_data,
 	},
+	{
+		.compatible = "st,stih407-clkgen-a9-mux",
+		.data = &stih407_a9_mux_data,
+	},
 	{}
 };
 
@@ -765,7 +774,8 @@ void __init st_of_clkgen_vcc_setup(struct device_node *np)
 		div->reg = reg + VCC_DIV_OFFSET;
 		div->shift = 2 * i;
 		div->width = 2;
-		div->flags = CLK_DIVIDER_POWER_OF_TWO;
+		div->flags = CLK_DIVIDER_POWER_OF_TWO |
+			CLK_DIVIDER_ROUND_CLOSEST;
 
 		mux->reg = reg + VCC_MUX_OFFSET;
 		mux->shift = 2 * i;
diff --git a/drivers/clk/st/clkgen-pll.c b/drivers/clk/st/clkgen-pll.c
index d8b9b1a2aed..29769d79e30 100644
--- a/drivers/clk/st/clkgen-pll.c
+++ b/drivers/clk/st/clkgen-pll.c
@@ -59,7 +59,7 @@ static const struct clk_ops st_pll800c65_ops;
 static const struct clk_ops stm_pll3200c32_ops;
 static const struct clk_ops st_pll1200c32_ops;
 
-static struct clkgen_pll_data st_pll1600c65_ax = {
+static const struct clkgen_pll_data st_pll1600c65_ax = {
 	.pdn_status	= CLKGEN_FIELD(0x0, 0x1,			19),
 	.locked_status	= CLKGEN_FIELD(0x0, 0x1,			31),
 	.mdiv		= CLKGEN_FIELD(0x0, C65_MDIV_PLL1600_MASK,	0),
@@ -67,7 +67,7 @@ static struct clkgen_pll_data st_pll1600c65_ax = {
 	.ops		= &st_pll1600c65_ops
 };
 
-static struct clkgen_pll_data st_pll800c65_ax = {
+static const struct clkgen_pll_data st_pll800c65_ax = {
 	.pdn_status	= CLKGEN_FIELD(0x0,	0x1,			19),
 	.locked_status	= CLKGEN_FIELD(0x0,	0x1,			31),
 	.mdiv		= CLKGEN_FIELD(0x0,	C65_MDIV_PLL800_MASK,	0),
@@ -76,7 +76,7 @@ static struct clkgen_pll_data st_pll800c65_ax = {
 	.ops		= &st_pll800c65_ops
 };
 
-static struct clkgen_pll_data st_pll3200c32_a1x_0 = {
+static const struct clkgen_pll_data st_pll3200c32_a1x_0 = {
 	.pdn_status	= CLKGEN_FIELD(0x0,	0x1,			31),
 	.locked_status	= CLKGEN_FIELD(0x4,	0x1,			31),
 	.ndiv		= CLKGEN_FIELD(0x0,	C32_NDIV_MASK,		0x0),
@@ -93,7 +93,7 @@ static struct clkgen_pll_data st_pll3200c32_a1x_0 = {
 	.ops		= &stm_pll3200c32_ops,
 };
 
-static struct clkgen_pll_data st_pll3200c32_a1x_1 = {
+static const struct clkgen_pll_data st_pll3200c32_a1x_1 = {
 	.pdn_status	= CLKGEN_FIELD(0xC,	0x1,			31),
 	.locked_status	= CLKGEN_FIELD(0x10,	0x1,			31),
 	.ndiv		= CLKGEN_FIELD(0xC,	C32_NDIV_MASK,		0x0),
@@ -111,7 +111,7 @@ static struct clkgen_pll_data st_pll3200c32_a1x_1 = {
 };
 
 /* 415 specific */
-static struct clkgen_pll_data st_pll3200c32_a9_415 = {
+static const struct clkgen_pll_data st_pll3200c32_a9_415 = {
 	.pdn_status	= CLKGEN_FIELD(0x0,	0x1,			0),
 	.locked_status	= CLKGEN_FIELD(0x6C,	0x1,			0),
 	.ndiv		= CLKGEN_FIELD(0x0,	C32_NDIV_MASK,		9),
@@ -122,7 +122,7 @@ static struct clkgen_pll_data st_pll3200c32_a9_415 = {
 	.ops		= &stm_pll3200c32_ops,
 };
 
-static struct clkgen_pll_data st_pll3200c32_ddr_415 = {
+static const struct clkgen_pll_data st_pll3200c32_ddr_415 = {
 	.pdn_status	= CLKGEN_FIELD(0x0,	0x1,			0),
 	.locked_status	= CLKGEN_FIELD(0x100,	0x1,			0),
 	.ndiv		= CLKGEN_FIELD(0x8,	C32_NDIV_MASK,		0),
@@ -135,7 +135,7 @@ static struct clkgen_pll_data st_pll3200c32_ddr_415 = {
 	.ops		= &stm_pll3200c32_ops,
 };
 
-static struct clkgen_pll_data st_pll1200c32_gpu_415 = {
+static const struct clkgen_pll_data st_pll1200c32_gpu_415 = {
 	.pdn_status	= CLKGEN_FIELD(0x144,	0x1,			3),
 	.locked_status	= CLKGEN_FIELD(0x168,	0x1,			0),
 	.ldf		= CLKGEN_FIELD(0x0,	C32_LDF_MASK,		3),
@@ -146,7 +146,7 @@ static struct clkgen_pll_data st_pll1200c32_gpu_415 = {
 };
 
 /* 416 specific */
-static struct clkgen_pll_data st_pll3200c32_a9_416 = {
+static const struct clkgen_pll_data st_pll3200c32_a9_416 = {
 	.pdn_status	= CLKGEN_FIELD(0x0,	0x1,			0),
 	.locked_status	= CLKGEN_FIELD(0x6C,	0x1,			0),
 	.ndiv		= CLKGEN_FIELD(0x8,	C32_NDIV_MASK,		0),
@@ -157,7 +157,7 @@ static struct clkgen_pll_data st_pll3200c32_a9_416 = {
 	.ops		= &stm_pll3200c32_ops,
 };
 
-static struct clkgen_pll_data st_pll3200c32_ddr_416 = {
+static const struct clkgen_pll_data st_pll3200c32_ddr_416 = {
 	.pdn_status	= CLKGEN_FIELD(0x0,	0x1,			0),
 	.locked_status	= CLKGEN_FIELD(0x10C,	0x1,			0),
 	.ndiv		= CLKGEN_FIELD(0x8,	C32_NDIV_MASK,		0),
@@ -170,7 +170,7 @@ static struct clkgen_pll_data st_pll3200c32_ddr_416 = {
 	.ops		= &stm_pll3200c32_ops,
 };
 
-static struct clkgen_pll_data st_pll1200c32_gpu_416 = {
+static const struct clkgen_pll_data st_pll1200c32_gpu_416 = {
 	.pdn_status	= CLKGEN_FIELD(0x8E4,	0x1,			3),
 	.locked_status	= CLKGEN_FIELD(0x90C,	0x1,			0),
 	.ldf		= CLKGEN_FIELD(0x0,	C32_LDF_MASK,		3),
@@ -180,6 +180,54 @@ static struct clkgen_pll_data st_pll1200c32_gpu_416 = {
 	.ops		= &st_pll1200c32_ops,
 };
 
+static const struct clkgen_pll_data st_pll3200c32_407_a0 = {
+	/* 407 A0 */
+	.pdn_status	= CLKGEN_FIELD(0x2a0,	0x1,			8),
+	.locked_status	= CLKGEN_FIELD(0x2a0,	0x1,			24),
+	.ndiv		= CLKGEN_FIELD(0x2a4,	C32_NDIV_MASK,		16),
+	.idf		= CLKGEN_FIELD(0x2a4,	C32_IDF_MASK,		0x0),
+	.num_odfs = 1,
+	.odf		= { CLKGEN_FIELD(0x2b4, C32_ODF_MASK,		0) },
+	.odf_gate	= { CLKGEN_FIELD(0x2b4,	0x1,			6) },
+	.ops		= &stm_pll3200c32_ops,
+};
+
+static const struct clkgen_pll_data st_pll3200c32_407_c0_0 = {
+	/* 407 C0 PLL0 */
+	.pdn_status	= CLKGEN_FIELD(0x2a0,	0x1,			8),
+	.locked_status	= CLKGEN_FIELD(0x2a0,	0x1,			24),
+	.ndiv		= CLKGEN_FIELD(0x2a4,	C32_NDIV_MASK,		16),
+	.idf		= CLKGEN_FIELD(0x2a4,	C32_IDF_MASK,		0x0),
+	.num_odfs = 1,
+	.odf		= { CLKGEN_FIELD(0x2b4, C32_ODF_MASK,		0) },
+	.odf_gate	= { CLKGEN_FIELD(0x2b4, 0x1,			6) },
+	.ops		= &stm_pll3200c32_ops,
+};
+
+static const struct clkgen_pll_data st_pll3200c32_407_c0_1 = {
+	/* 407 C0 PLL1 */
+	.pdn_status	= CLKGEN_FIELD(0x2c8,	0x1,			8),
+	.locked_status	= CLKGEN_FIELD(0x2c8,	0x1,			24),
+	.ndiv		= CLKGEN_FIELD(0x2cc,	C32_NDIV_MASK,		16),
+	.idf		= CLKGEN_FIELD(0x2cc,	C32_IDF_MASK,		0x0),
+	.num_odfs = 1,
+	.odf		= { CLKGEN_FIELD(0x2dc, C32_ODF_MASK,		0) },
+	.odf_gate	= { CLKGEN_FIELD(0x2dc, 0x1,			6) },
+	.ops		= &stm_pll3200c32_ops,
+};
+
+static const struct clkgen_pll_data st_pll3200c32_407_a9 = {
+	/* 407 A9 */
+	.pdn_status	= CLKGEN_FIELD(0x1a8,	0x1,			0),
+	.locked_status	= CLKGEN_FIELD(0x87c,	0x1,			0),
+	.ndiv		= CLKGEN_FIELD(0x1b0,	C32_NDIV_MASK,		0),
+	.idf		= CLKGEN_FIELD(0x1a8,	C32_IDF_MASK,		25),
+	.num_odfs = 1,
+	.odf		= { CLKGEN_FIELD(0x1b0, C32_ODF_MASK,		8) },
+	.odf_gate	= { CLKGEN_FIELD(0x1ac, 0x1,			28) },
+	.ops		= &stm_pll3200c32_ops,
+};
+
 /**
  * DOC: Clock Generated by PLL, rate set and enabled by bootloader
  *
@@ -450,9 +498,8 @@ static void __init clkgena_c65_pll_setup(struct device_node *np)
 	 * PLL0 HS (high speed) output
 	 */
 	clk_data->clks[0] = clkgen_pll_register(parent_name,
-						&st_pll1600c65_ax,
-						reg + CLKGENAx_PLL0_OFFSET,
-						clk_name);
+			(struct clkgen_pll_data *) &st_pll1600c65_ax,
+			reg + CLKGENAx_PLL0_OFFSET, clk_name);
 
 	if (IS_ERR(clk_data->clks[0]))
 		goto err;
@@ -480,9 +527,8 @@ static void __init clkgena_c65_pll_setup(struct device_node *np)
 	 * PLL1 output
 	 */
 	clk_data->clks[2] = clkgen_pll_register(parent_name,
-						&st_pll800c65_ax,
-						reg + CLKGENAx_PLL1_OFFSET,
-						clk_name);
+			(struct clkgen_pll_data *) &st_pll800c65_ax,
+			reg + CLKGENAx_PLL1_OFFSET, clk_name);
 
 	if (IS_ERR(clk_data->clks[2]))
 		goto err;
@@ -572,6 +618,22 @@ static struct of_device_id c32_pll_of_match[] = {
 		.compatible = "st,stih416-plls-c32-ddr",
 		.data = &st_pll3200c32_ddr_416,
 	},
+	{
+		.compatible = "st,stih407-plls-c32-a0",
+		.data = &st_pll3200c32_407_a0,
+	},
+	{
+		.compatible = "st,stih407-plls-c32-c0_0",
+		.data = &st_pll3200c32_407_c0_0,
+	},
+	{
+		.compatible = "st,stih407-plls-c32-c0_1",
+		.data = &st_pll3200c32_407_c0_1,
+	},
+	{
+		.compatible = "st,stih407-plls-c32-a9",
+		.data = &st_pll3200c32_407_a9,
+	},
 	{}
 };
 
diff --git a/drivers/clk/sunxi/Makefile b/drivers/clk/sunxi/Makefile
index b5bac917612..6850cba3587 100644
--- a/drivers/clk/sunxi/Makefile
+++ b/drivers/clk/sunxi/Makefile
@@ -3,3 +3,9 @@
 #
 
 obj-y += clk-sunxi.o clk-factors.o
+obj-y += clk-a10-hosc.o
+obj-y += clk-a20-gmac.o
+
+obj-$(CONFIG_MFD_SUN6I_PRCM) += \
+	clk-sun6i-ar100.o clk-sun6i-apb0.o clk-sun6i-apb0-gates.o \
+	clk-sun8i-apb0.o
diff --git a/drivers/clk/sunxi/clk-a10-hosc.c b/drivers/clk/sunxi/clk-a10-hosc.c
new file mode 100644
index 00000000000..0481d5d673d
--- /dev/null
+++ b/drivers/clk/sunxi/clk-a10-hosc.c
@@ -0,0 +1,73 @@
+/*
+ * Copyright 2013 Emilio López
+ *
+ * Emilio López <emilio@elopez.com.ar>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#define SUNXI_OSC24M_GATE	0
+
+static DEFINE_SPINLOCK(hosc_lock);
+
+static void __init sun4i_osc_clk_setup(struct device_node *node)
+{
+	struct clk *clk;
+	struct clk_fixed_rate *fixed;
+	struct clk_gate *gate;
+	const char *clk_name = node->name;
+	u32 rate;
+
+	if (of_property_read_u32(node, "clock-frequency", &rate))
+		return;
+
+	/* allocate fixed-rate and gate clock structs */
+	fixed = kzalloc(sizeof(struct clk_fixed_rate), GFP_KERNEL);
+	if (!fixed)
+		return;
+	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
+	if (!gate)
+		goto err_free_fixed;
+
+	of_property_read_string(node, "clock-output-names", &clk_name);
+
+	/* set up gate and fixed rate properties */
+	gate->reg = of_iomap(node, 0);
+	gate->bit_idx = SUNXI_OSC24M_GATE;
+	gate->lock = &hosc_lock;
+	fixed->fixed_rate = rate;
+
+	clk = clk_register_composite(NULL, clk_name,
+			NULL, 0,
+			NULL, NULL,
+			&fixed->hw, &clk_fixed_rate_ops,
+			&gate->hw, &clk_gate_ops,
+			CLK_IS_ROOT);
+
+	if (IS_ERR(clk))
+		goto err_free_gate;
+
+	of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	clk_register_clkdev(clk, clk_name, NULL);
+
+	return;
+
+err_free_gate:
+	kfree(gate);
+err_free_fixed:
+	kfree(fixed);
+}
+CLK_OF_DECLARE(sun4i_osc, "allwinner,sun4i-a10-osc-clk", sun4i_osc_clk_setup);
diff --git a/drivers/clk/sunxi/clk-a20-gmac.c b/drivers/clk/sunxi/clk-a20-gmac.c
new file mode 100644
index 00000000000..5296fd6dd7b
--- /dev/null
+++ b/drivers/clk/sunxi/clk-a20-gmac.c
@@ -0,0 +1,119 @@
+/*
+ * Copyright 2013 Emilio López
+ * Emilio López <emilio@elopez.com.ar>
+ *
+ * Copyright 2013 Chen-Yu Tsai
+ * Chen-Yu Tsai <wens@csie.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+
+static DEFINE_SPINLOCK(gmac_lock);
+
+/**
+ * sun7i_a20_gmac_clk_setup - Setup function for A20/A31 GMAC clock module
+ *
+ * This clock looks something like this
+ *                               ________________________
+ *  MII TX clock from PHY >-----|___________    _________|----> to GMAC core
+ *  GMAC Int. RGMII TX clk >----|___________\__/__gate---|----> to PHY
+ *  Ext. 125MHz RGMII TX clk >--|__divider__/            |
+ *                              |________________________|
+ *
+ * The external 125 MHz reference is optional, i.e. GMAC can use its
+ * internal TX clock just fine. The A31 GMAC clock module does not have
+ * the divider controls for the external reference.
+ *
+ * To keep it simple, let the GMAC use either the MII TX clock for MII mode,
+ * and its internal TX clock for GMII and RGMII modes. The GMAC driver should
+ * select the appropriate source and gate/ungate the output to the PHY.
+ *
+ * Only the GMAC should use this clock. Altering the clock so that it doesn't
+ * match the GMAC's operation parameters will result in the GMAC not being
+ * able to send traffic out. The GMAC driver should set the clock rate and
+ * enable/disable this clock to configure the required state. The clock
+ * driver then responds by auto-reparenting the clock.
+ */
+
+#define SUN7I_A20_GMAC_GPIT	2
+#define SUN7I_A20_GMAC_MASK	0x3
+#define SUN7I_A20_GMAC_PARENTS	2
+
+static void __init sun7i_a20_gmac_clk_setup(struct device_node *node)
+{
+	struct clk *clk;
+	struct clk_mux *mux;
+	struct clk_gate *gate;
+	const char *clk_name = node->name;
+	const char *parents[SUN7I_A20_GMAC_PARENTS];
+	void __iomem *reg;
+
+	if (of_property_read_string(node, "clock-output-names", &clk_name))
+		return;
+
+	/* allocate mux and gate clock structs */
+	mux = kzalloc(sizeof(struct clk_mux), GFP_KERNEL);
+	if (!mux)
+		return;
+
+	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
+	if (!gate)
+		goto free_mux;
+
+	/* gmac clock requires exactly 2 parents */
+	parents[0] = of_clk_get_parent_name(node, 0);
+	parents[1] = of_clk_get_parent_name(node, 1);
+	if (!parents[0] || !parents[1])
+		goto free_gate;
+
+	reg = of_iomap(node, 0);
+	if (!reg)
+		goto free_gate;
+
+	/* set up gate and fixed rate properties */
+	gate->reg = reg;
+	gate->bit_idx = SUN7I_A20_GMAC_GPIT;
+	gate->lock = &gmac_lock;
+	mux->reg = reg;
+	mux->mask = SUN7I_A20_GMAC_MASK;
+	mux->flags = CLK_MUX_INDEX_BIT;
+	mux->lock = &gmac_lock;
+
+	clk = clk_register_composite(NULL, clk_name,
+			parents, SUN7I_A20_GMAC_PARENTS,
+			&mux->hw, &clk_mux_ops,
+			NULL, NULL,
+			&gate->hw, &clk_gate_ops,
+			0);
+
+	if (IS_ERR(clk))
+		goto iounmap_reg;
+
+	of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	clk_register_clkdev(clk, clk_name, NULL);
+
+	return;
+
+iounmap_reg:
+	iounmap(reg);
+free_gate:
+	kfree(gate);
+free_mux:
+	kfree(mux);
+}
+CLK_OF_DECLARE(sun7i_a20_gmac, "allwinner,sun7i-a20-gmac-clk",
+		sun7i_a20_gmac_clk_setup);
diff --git a/drivers/clk/sunxi/clk-factors.c b/drivers/clk/sunxi/clk-factors.c
index 3806d97e529..2057c8ac648 100644
--- a/drivers/clk/sunxi/clk-factors.c
+++ b/drivers/clk/sunxi/clk-factors.c
@@ -62,7 +62,7 @@ static unsigned long clk_factors_recalc_rate(struct clk_hw *hw,
 		p = FACTOR_GET(config->pshift, config->pwidth, reg);
 
 	/* Calculate the rate */
-	rate = (parent_rate * n * (k + 1) >> p) / (m + 1);
+	rate = (parent_rate * (n + config->n_start) * (k + 1) >> p) / (m + 1);
 
 	return rate;
 }
diff --git a/drivers/clk/sunxi/clk-factors.h b/drivers/clk/sunxi/clk-factors.h
index 02e1a43ebac..d2d0efa3937 100644
--- a/drivers/clk/sunxi/clk-factors.h
+++ b/drivers/clk/sunxi/clk-factors.h
@@ -15,6 +15,7 @@ struct clk_factors_config {
 	u8 mwidth;
 	u8 pshift;
 	u8 pwidth;
+	u8 n_start;
 };
 
 struct clk_factors {
diff --git a/drivers/clk/sunxi/clk-sun6i-apb0-gates.c b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
new file mode 100644
index 00000000000..e10d0521ec7
--- /dev/null
+++ b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright (C) 2014 Free Electrons
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * Allwinner A31 APB0 clock gates driver
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+
+#define SUN6I_APB0_GATES_MAX_SIZE	32
+
+struct gates_data {
+	DECLARE_BITMAP(mask, SUN6I_APB0_GATES_MAX_SIZE);
+};
+
+static const struct gates_data sun6i_a31_apb0_gates __initconst = {
+	.mask = {0x7F},
+};
+
+static const struct gates_data sun8i_a23_apb0_gates __initconst = {
+	.mask = {0x5D},
+};
+
+static const struct of_device_id sun6i_a31_apb0_gates_clk_dt_ids[] = {
+	{ .compatible = "allwinner,sun6i-a31-apb0-gates-clk", .data = &sun6i_a31_apb0_gates },
+	{ .compatible = "allwinner,sun8i-a23-apb0-gates-clk", .data = &sun8i_a23_apb0_gates },
+	{ /* sentinel */ }
+};
+
+static int sun6i_a31_apb0_gates_clk_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct clk_onecell_data *clk_data;
+	const struct of_device_id *device;
+	const struct gates_data *data;
+	const char *clk_parent;
+	const char *clk_name;
+	struct resource *r;
+	void __iomem *reg;
+	int ngates;
+	int i;
+	int j = 0;
+
+	if (!np)
+		return -ENODEV;
+
+	device = of_match_device(sun6i_a31_apb0_gates_clk_dt_ids, &pdev->dev);
+	if (!device)
+		return -ENODEV;
+	data = device->data;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	reg = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	clk_parent = of_clk_get_parent_name(np, 0);
+	if (!clk_parent)
+		return -EINVAL;
+
+	clk_data = devm_kzalloc(&pdev->dev, sizeof(struct clk_onecell_data),
+				GFP_KERNEL);
+	if (!clk_data)
+		return -ENOMEM;
+
+	/* Worst-case size approximation and memory allocation */
+	ngates = find_last_bit(data->mask, SUN6I_APB0_GATES_MAX_SIZE);
+	clk_data->clks = devm_kcalloc(&pdev->dev, (ngates + 1),
+				      sizeof(struct clk *), GFP_KERNEL);
+	if (!clk_data->clks)
+		return -ENOMEM;
+
+	for_each_set_bit(i, data->mask, SUN6I_APB0_GATES_MAX_SIZE) {
+		of_property_read_string_index(np, "clock-output-names",
+					      j, &clk_name);
+
+		clk_data->clks[i] = clk_register_gate(&pdev->dev, clk_name,
+						      clk_parent, 0, reg, i,
+						      0, NULL);
+		WARN_ON(IS_ERR(clk_data->clks[i]));
+		clk_register_clkdev(clk_data->clks[i], clk_name, NULL);
+
+		j++;
+	}
+
+	clk_data->clk_num = ngates + 1;
+
+	return of_clk_add_provider(np, of_clk_src_onecell_get, clk_data);
+}
+
+static struct platform_driver sun6i_a31_apb0_gates_clk_driver = {
+	.driver = {
+		.name = "sun6i-a31-apb0-gates-clk",
+		.owner = THIS_MODULE,
+		.of_match_table = sun6i_a31_apb0_gates_clk_dt_ids,
+	},
+	.probe = sun6i_a31_apb0_gates_clk_probe,
+};
+module_platform_driver(sun6i_a31_apb0_gates_clk_driver);
+
+MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A31 APB0 gate clocks driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/sunxi/clk-sun6i-apb0.c b/drivers/clk/sunxi/clk-sun6i-apb0.c
new file mode 100644
index 00000000000..1fa23371c8c
--- /dev/null
+++ b/drivers/clk/sunxi/clk-sun6i-apb0.c
@@ -0,0 +1,77 @@
+/*
+ * Copyright (C) 2014 Free Electrons
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * Allwinner A31 APB0 clock driver
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+/*
+ * The APB0 clk has a configurable divisor.
+ *
+ * We must use a clk_div_table and not a regular power of 2
+ * divisor here, because the first 2 values divide the clock
+ * by 2.
+ */
+static const struct clk_div_table sun6i_a31_apb0_divs[] = {
+	{ .val = 0, .div = 2, },
+	{ .val = 1, .div = 2, },
+	{ .val = 2, .div = 4, },
+	{ .val = 3, .div = 8, },
+	{ /* sentinel */ },
+};
+
+static int sun6i_a31_apb0_clk_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const char *clk_name = np->name;
+	const char *clk_parent;
+	struct resource *r;
+	void __iomem *reg;
+	struct clk *clk;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	reg = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	clk_parent = of_clk_get_parent_name(np, 0);
+	if (!clk_parent)
+		return -EINVAL;
+
+	of_property_read_string(np, "clock-output-names", &clk_name);
+
+	clk = clk_register_divider_table(&pdev->dev, clk_name, clk_parent,
+					 0, reg, 0, 2, 0, sun6i_a31_apb0_divs,
+					 NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	return of_clk_add_provider(np, of_clk_src_simple_get, clk);
+}
+
+static const struct of_device_id sun6i_a31_apb0_clk_dt_ids[] = {
+	{ .compatible = "allwinner,sun6i-a31-apb0-clk" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver sun6i_a31_apb0_clk_driver = {
+	.driver = {
+		.name = "sun6i-a31-apb0-clk",
+		.owner = THIS_MODULE,
+		.of_match_table = sun6i_a31_apb0_clk_dt_ids,
+	},
+	.probe = sun6i_a31_apb0_clk_probe,
+};
+module_platform_driver(sun6i_a31_apb0_clk_driver);
+
+MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A31 APB0 clock Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/sunxi/clk-sun6i-ar100.c b/drivers/clk/sunxi/clk-sun6i-ar100.c
new file mode 100644
index 00000000000..eca8ca025b6
--- /dev/null
+++ b/drivers/clk/sunxi/clk-sun6i-ar100.c
@@ -0,0 +1,233 @@
+/*
+ * Copyright (C) 2014 Free Electrons
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * Allwinner A31 AR100 clock driver
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#define SUN6I_AR100_MAX_PARENTS		4
+#define SUN6I_AR100_SHIFT_MASK		0x3
+#define SUN6I_AR100_SHIFT_MAX		SUN6I_AR100_SHIFT_MASK
+#define SUN6I_AR100_SHIFT_SHIFT		4
+#define SUN6I_AR100_DIV_MASK		0x1f
+#define SUN6I_AR100_DIV_MAX		(SUN6I_AR100_DIV_MASK + 1)
+#define SUN6I_AR100_DIV_SHIFT		8
+#define SUN6I_AR100_MUX_MASK		0x3
+#define SUN6I_AR100_MUX_SHIFT		16
+
+struct ar100_clk {
+	struct clk_hw hw;
+	void __iomem *reg;
+};
+
+static inline struct ar100_clk *to_ar100_clk(struct clk_hw *hw)
+{
+	return container_of(hw, struct ar100_clk, hw);
+}
+
+static unsigned long ar100_recalc_rate(struct clk_hw *hw,
+				       unsigned long parent_rate)
+{
+	struct ar100_clk *clk = to_ar100_clk(hw);
+	u32 val = readl(clk->reg);
+	int shift = (val >> SUN6I_AR100_SHIFT_SHIFT) & SUN6I_AR100_SHIFT_MASK;
+	int div = (val >> SUN6I_AR100_DIV_SHIFT) & SUN6I_AR100_DIV_MASK;
+
+	return (parent_rate >> shift) / (div + 1);
+}
+
+static long ar100_determine_rate(struct clk_hw *hw, unsigned long rate,
+				 unsigned long *best_parent_rate,
+				 struct clk **best_parent_clk)
+{
+	int nparents = __clk_get_num_parents(hw->clk);
+	long best_rate = -EINVAL;
+	int i;
+
+	*best_parent_clk = NULL;
+
+	for (i = 0; i < nparents; i++) {
+		unsigned long parent_rate;
+		unsigned long tmp_rate;
+		struct clk *parent;
+		unsigned long div;
+		int shift;
+
+		parent = clk_get_parent_by_index(hw->clk, i);
+		parent_rate = __clk_get_rate(parent);
+		div = DIV_ROUND_UP(parent_rate, rate);
+
+		/*
+		 * The AR100 clk contains 2 divisors:
+		 * - one power of 2 divisor
+		 * - one regular divisor
+		 *
+		 * First check if we can safely shift (or divide by a power
+		 * of 2) without losing precision on the requested rate.
+		 */
+		shift = ffs(div) - 1;
+		if (shift > SUN6I_AR100_SHIFT_MAX)
+			shift = SUN6I_AR100_SHIFT_MAX;
+
+		div >>= shift;
+
+		/*
+		 * Then if the divisor is still bigger than what the HW
+		 * actually supports, use a bigger shift (or power of 2
+		 * divider) value and accept to lose some precision.
+		 */
+		while (div > SUN6I_AR100_DIV_MAX) {
+			shift++;
+			div >>= 1;
+			if (shift > SUN6I_AR100_SHIFT_MAX)
+				break;
+		}
+
+		/*
+		 * If the shift value (or power of 2 divider) is bigger
+		 * than what the HW actually support, skip this parent.
+		 */
+		if (shift > SUN6I_AR100_SHIFT_MAX)
+			continue;
+
+		tmp_rate = (parent_rate >> shift) / div;
+		if (!*best_parent_clk || tmp_rate > best_rate) {
+			*best_parent_clk = parent;
+			*best_parent_rate = parent_rate;
+			best_rate = tmp_rate;
+		}
+	}
+
+	return best_rate;
+}
+
+static int ar100_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct ar100_clk *clk = to_ar100_clk(hw);
+	u32 val = readl(clk->reg);
+
+	if (index >= SUN6I_AR100_MAX_PARENTS)
+		return -EINVAL;
+
+	val &= ~(SUN6I_AR100_MUX_MASK << SUN6I_AR100_MUX_SHIFT);
+	val |= (index << SUN6I_AR100_MUX_SHIFT);
+	writel(val, clk->reg);
+
+	return 0;
+}
+
+static u8 ar100_get_parent(struct clk_hw *hw)
+{
+	struct ar100_clk *clk = to_ar100_clk(hw);
+	return (readl(clk->reg) >> SUN6I_AR100_MUX_SHIFT) &
+	       SUN6I_AR100_MUX_MASK;
+}
+
+static int ar100_set_rate(struct clk_hw *hw, unsigned long rate,
+			  unsigned long parent_rate)
+{
+	unsigned long div = parent_rate / rate;
+	struct ar100_clk *clk = to_ar100_clk(hw);
+	u32 val = readl(clk->reg);
+	int shift;
+
+	if (parent_rate % rate)
+		return -EINVAL;
+
+	shift = ffs(div) - 1;
+	if (shift > SUN6I_AR100_SHIFT_MAX)
+		shift = SUN6I_AR100_SHIFT_MAX;
+
+	div >>= shift;
+
+	if (div > SUN6I_AR100_DIV_MAX)
+		return -EINVAL;
+
+	val &= ~((SUN6I_AR100_SHIFT_MASK << SUN6I_AR100_SHIFT_SHIFT) |
+		 (SUN6I_AR100_DIV_MASK << SUN6I_AR100_DIV_SHIFT));
+	val |= (shift << SUN6I_AR100_SHIFT_SHIFT) |
+	       (div << SUN6I_AR100_DIV_SHIFT);
+	writel(val, clk->reg);
+
+	return 0;
+}
+
+static struct clk_ops ar100_ops = {
+	.recalc_rate = ar100_recalc_rate,
+	.determine_rate = ar100_determine_rate,
+	.set_parent = ar100_set_parent,
+	.get_parent = ar100_get_parent,
+	.set_rate = ar100_set_rate,
+};
+
+static int sun6i_a31_ar100_clk_probe(struct platform_device *pdev)
+{
+	const char *parents[SUN6I_AR100_MAX_PARENTS];
+	struct device_node *np = pdev->dev.of_node;
+	const char *clk_name = np->name;
+	struct clk_init_data init;
+	struct ar100_clk *ar100;
+	struct resource *r;
+	struct clk *clk;
+	int nparents;
+	int i;
+
+	ar100 = devm_kzalloc(&pdev->dev, sizeof(*ar100), GFP_KERNEL);
+	if (!ar100)
+		return -ENOMEM;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ar100->reg = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(ar100->reg))
+		return PTR_ERR(ar100->reg);
+
+	nparents = of_clk_get_parent_count(np);
+	if (nparents > SUN6I_AR100_MAX_PARENTS)
+		nparents = SUN6I_AR100_MAX_PARENTS;
+
+	for (i = 0; i < nparents; i++)
+		parents[i] = of_clk_get_parent_name(np, i);
+
+	of_property_read_string(np, "clock-output-names", &clk_name);
+
+	init.name = clk_name;
+	init.ops = &ar100_ops;
+	init.parent_names = parents;
+	init.num_parents = nparents;
+	init.flags = 0;
+
+	ar100->hw.init = &init;
+
+	clk = clk_register(&pdev->dev, &ar100->hw);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	return of_clk_add_provider(np, of_clk_src_simple_get, clk);
+}
+
+static const struct of_device_id sun6i_a31_ar100_clk_dt_ids[] = {
+	{ .compatible = "allwinner,sun6i-a31-ar100-clk" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver sun6i_a31_ar100_clk_driver = {
+	.driver = {
+		.name = "sun6i-a31-ar100-clk",
+		.owner = THIS_MODULE,
+		.of_match_table = sun6i_a31_ar100_clk_dt_ids,
+	},
+	.probe = sun6i_a31_ar100_clk_probe,
+};
+module_platform_driver(sun6i_a31_ar100_clk_driver);
+
+MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A31 AR100 clock Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/sunxi/clk-sun8i-apb0.c b/drivers/clk/sunxi/clk-sun8i-apb0.c
new file mode 100644
index 00000000000..1f5ba9b4b8c
--- /dev/null
+++ b/drivers/clk/sunxi/clk-sun8i-apb0.c
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2014 Chen-Yu Tsai
+ * Author: Chen-Yu Tsai <wens@csie.org>
+ *
+ * Allwinner A23 APB0 clock driver
+ *
+ * License Terms: GNU General Public License v2
+ *
+ * Based on clk-sun6i-apb0.c
+ * Allwinner A31 APB0 clock driver
+ *
+ * Copyright (C) 2014 Free Electrons
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+static int sun8i_a23_apb0_clk_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const char *clk_name = np->name;
+	const char *clk_parent;
+	struct resource *r;
+	void __iomem *reg;
+	struct clk *clk;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	reg = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	clk_parent = of_clk_get_parent_name(np, 0);
+	if (!clk_parent)
+		return -EINVAL;
+
+	of_property_read_string(np, "clock-output-names", &clk_name);
+
+	/* The A23 APB0 clock is a standard 2 bit wide divider clock */
+	clk = clk_register_divider(&pdev->dev, clk_name, clk_parent, 0, reg,
+				   0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	return of_clk_add_provider(np, of_clk_src_simple_get, clk);
+}
+
+static const struct of_device_id sun8i_a23_apb0_clk_dt_ids[] = {
+	{ .compatible = "allwinner,sun8i-a23-apb0-clk" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver sun8i_a23_apb0_clk_driver = {
+	.driver = {
+		.name = "sun8i-a23-apb0-clk",
+		.owner = THIS_MODULE,
+		.of_match_table = sun8i_a23_apb0_clk_dt_ids,
+	},
+	.probe = sun8i_a23_apb0_clk_probe,
+};
+module_platform_driver(sun8i_a23_apb0_clk_driver);
+
+MODULE_AUTHOR("Chen-Yu Tsai <wens@csie.org>");
+MODULE_DESCRIPTION("Allwinner A23 APB0 clock Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 426483422d3..b654b7b1d13 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -28,63 +28,6 @@ static DEFINE_SPINLOCK(clk_lock);
 #define SUNXI_MAX_PARENTS	5
 
 /**
- * sun4i_osc_clk_setup() - Setup function for gatable oscillator
- */
-
-#define SUNXI_OSC24M_GATE	0
-
-static void __init sun4i_osc_clk_setup(struct device_node *node)
-{
-	struct clk *clk;
-	struct clk_fixed_rate *fixed;
-	struct clk_gate *gate;
-	const char *clk_name = node->name;
-	u32 rate;
-
-	if (of_property_read_u32(node, "clock-frequency", &rate))
-		return;
-
-	/* allocate fixed-rate and gate clock structs */
-	fixed = kzalloc(sizeof(struct clk_fixed_rate), GFP_KERNEL);
-	if (!fixed)
-		return;
-	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
-	if (!gate)
-		goto err_free_fixed;
-
-	of_property_read_string(node, "clock-output-names", &clk_name);
-
-	/* set up gate and fixed rate properties */
-	gate->reg = of_iomap(node, 0);
-	gate->bit_idx = SUNXI_OSC24M_GATE;
-	gate->lock = &clk_lock;
-	fixed->fixed_rate = rate;
-
-	clk = clk_register_composite(NULL, clk_name,
-			NULL, 0,
-			NULL, NULL,
-			&fixed->hw, &clk_fixed_rate_ops,
-			&gate->hw, &clk_gate_ops,
-			CLK_IS_ROOT);
-
-	if (IS_ERR(clk))
-		goto err_free_gate;
-
-	of_clk_add_provider(node, of_clk_src_simple_get, clk);
-	clk_register_clkdev(clk, clk_name, NULL);
-
-	return;
-
-err_free_gate:
-	kfree(gate);
-err_free_fixed:
-	kfree(fixed);
-}
-CLK_OF_DECLARE(sun4i_osc, "allwinner,sun4i-a10-osc-clk", sun4i_osc_clk_setup);
-
-
-
-/**
  * sun4i_get_pll1_factors() - calculates n, k, m, p factors for PLL1
  * PLL1 rate is calculated as follows
  * rate = (parent_rate * n * (k + 1) >> p) / (m + 1);
@@ -221,6 +164,54 @@ static void sun6i_a31_get_pll1_factors(u32 *freq, u32 parent_rate,
 }
 
 /**
+ * sun8i_a23_get_pll1_factors() - calculates n, k, m, p factors for PLL1
+ * PLL1 rate is calculated as follows
+ * rate = (parent_rate * (n + 1) * (k + 1) >> p) / (m + 1);
+ * parent_rate is always 24Mhz
+ */
+
+static void sun8i_a23_get_pll1_factors(u32 *freq, u32 parent_rate,
+				   u8 *n, u8 *k, u8 *m, u8 *p)
+{
+	u8 div;
+
+	/* Normalize value to a 6M multiple */
+	div = *freq / 6000000;
+	*freq = 6000000 * div;
+
+	/* we were called to round the frequency, we can now return */
+	if (n == NULL)
+		return;
+
+	/* m is always zero for pll1 */
+	*m = 0;
+
+	/* k is 1 only on these cases */
+	if (*freq >= 768000000 || *freq == 42000000 || *freq == 54000000)
+		*k = 1;
+	else
+		*k = 0;
+
+	/* p will be 2 for divs under 20 and odd divs under 32 */
+	if (div < 20 || (div < 32 && (div & 1)))
+		*p = 2;
+
+	/* p will be 1 for even divs under 32, divs under 40 and odd pairs
+	 * of divs between 40-62 */
+	else if (div < 40 || (div < 64 && (div & 2)))
+		*p = 1;
+
+	/* any other entries have p = 0 */
+	else
+		*p = 0;
+
+	/* calculate a suitable n based on k and p */
+	div <<= *p;
+	div /= (*k + 1);
+	*n = div / 4 - 1;
+}
+
+/**
  * sun4i_get_pll5_factors() - calculates n, k factors for PLL5
  * PLL5 rate is calculated as follows
  * rate = parent_rate * n * (k + 1)
@@ -408,104 +399,6 @@ static void sun7i_a20_get_out_factors(u32 *freq, u32 parent_rate,
 	*p = calcp;
 }
 
-
-
-/**
- * sun7i_a20_gmac_clk_setup - Setup function for A20/A31 GMAC clock module
- *
- * This clock looks something like this
- *                               ________________________
- *  MII TX clock from PHY >-----|___________    _________|----> to GMAC core
- *  GMAC Int. RGMII TX clk >----|___________\__/__gate---|----> to PHY
- *  Ext. 125MHz RGMII TX clk >--|__divider__/            |
- *                              |________________________|
- *
- * The external 125 MHz reference is optional, i.e. GMAC can use its
- * internal TX clock just fine. The A31 GMAC clock module does not have
- * the divider controls for the external reference.
- *
- * To keep it simple, let the GMAC use either the MII TX clock for MII mode,
- * and its internal TX clock for GMII and RGMII modes. The GMAC driver should
- * select the appropriate source and gate/ungate the output to the PHY.
- *
- * Only the GMAC should use this clock. Altering the clock so that it doesn't
- * match the GMAC's operation parameters will result in the GMAC not being
- * able to send traffic out. The GMAC driver should set the clock rate and
- * enable/disable this clock to configure the required state. The clock
- * driver then responds by auto-reparenting the clock.
- */
-
-#define SUN7I_A20_GMAC_GPIT	2
-#define SUN7I_A20_GMAC_MASK	0x3
-#define SUN7I_A20_GMAC_PARENTS	2
-
-static void __init sun7i_a20_gmac_clk_setup(struct device_node *node)
-{
-	struct clk *clk;
-	struct clk_mux *mux;
-	struct clk_gate *gate;
-	const char *clk_name = node->name;
-	const char *parents[SUN7I_A20_GMAC_PARENTS];
-	void *reg;
-
-	if (of_property_read_string(node, "clock-output-names", &clk_name))
-		return;
-
-	/* allocate mux and gate clock structs */
-	mux = kzalloc(sizeof(struct clk_mux), GFP_KERNEL);
-	if (!mux)
-		return;
-
-	gate = kzalloc(sizeof(struct clk_gate), GFP_KERNEL);
-	if (!gate)
-		goto free_mux;
-
-	/* gmac clock requires exactly 2 parents */
-	parents[0] = of_clk_get_parent_name(node, 0);
-	parents[1] = of_clk_get_parent_name(node, 1);
-	if (!parents[0] || !parents[1])
-		goto free_gate;
-
-	reg = of_iomap(node, 0);
-	if (!reg)
-		goto free_gate;
-
-	/* set up gate and fixed rate properties */
-	gate->reg = reg;
-	gate->bit_idx = SUN7I_A20_GMAC_GPIT;
-	gate->lock = &clk_lock;
-	mux->reg = reg;
-	mux->mask = SUN7I_A20_GMAC_MASK;
-	mux->flags = CLK_MUX_INDEX_BIT;
-	mux->lock = &clk_lock;
-
-	clk = clk_register_composite(NULL, clk_name,
-			parents, SUN7I_A20_GMAC_PARENTS,
-			&mux->hw, &clk_mux_ops,
-			NULL, NULL,
-			&gate->hw, &clk_gate_ops,
-			0);
-
-	if (IS_ERR(clk))
-		goto iounmap_reg;
-
-	of_clk_add_provider(node, of_clk_src_simple_get, clk);
-	clk_register_clkdev(clk, clk_name, NULL);
-
-	return;
-
-iounmap_reg:
-	iounmap(reg);
-free_gate:
-	kfree(gate);
-free_mux:
-	kfree(mux);
-}
-CLK_OF_DECLARE(sun7i_a20_gmac, "allwinner,sun7i-a20-gmac-clk",
-		sun7i_a20_gmac_clk_setup);
-
-
-
 /**
  * clk_sunxi_mmc_phase_control() - configures MMC clock phase control
  */
@@ -577,6 +470,18 @@ static struct clk_factors_config sun6i_a31_pll1_config = {
 	.mwidth = 2,
 };
 
+static struct clk_factors_config sun8i_a23_pll1_config = {
+	.nshift = 8,
+	.nwidth = 5,
+	.kshift = 4,
+	.kwidth = 2,
+	.mshift = 0,
+	.mwidth = 2,
+	.pshift = 16,
+	.pwidth = 2,
+	.n_start = 1,
+};
+
 static struct clk_factors_config sun4i_pll5_config = {
 	.nshift = 8,
 	.nwidth = 5,
@@ -626,6 +531,12 @@ static const struct factors_data sun6i_a31_pll1_data __initconst = {
 	.getter = sun6i_a31_get_pll1_factors,
 };
 
+static const struct factors_data sun8i_a23_pll1_data __initconst = {
+	.enable = 31,
+	.table = &sun8i_a23_pll1_config,
+	.getter = sun8i_a23_get_pll1_factors,
+};
+
 static const struct factors_data sun7i_a20_pll4_data __initconst = {
 	.enable = 31,
 	.table = &sun4i_pll5_config,
@@ -682,7 +593,7 @@ static struct clk * __init sunxi_factors_clk_setup(struct device_node *node,
 	struct clk_hw *mux_hw = NULL;
 	const char *clk_name = node->name;
 	const char *parents[SUNXI_MAX_PARENTS];
-	void *reg;
+	void __iomem *reg;
 	int i = 0;
 
 	reg = of_iomap(node, 0);
@@ -787,7 +698,7 @@ static void __init sunxi_mux_clk_setup(struct device_node *node,
 	struct clk *clk;
 	const char *clk_name = node->name;
 	const char *parents[SUNXI_MAX_PARENTS];
-	void *reg;
+	void __iomem *reg;
 	int i = 0;
 
 	reg = of_iomap(node, 0);
@@ -819,6 +730,7 @@ struct div_data {
 	u8	shift;
 	u8	pow;
 	u8	width;
+	const struct clk_div_table *table;
 };
 
 static const struct div_data sun4i_axi_data __initconst = {
@@ -827,6 +739,23 @@ static const struct div_data sun4i_axi_data __initconst = {
 	.width	= 2,
 };
 
+static const struct clk_div_table sun8i_a23_axi_table[] __initconst = {
+	{ .val = 0, .div = 1 },
+	{ .val = 1, .div = 2 },
+	{ .val = 2, .div = 3 },
+	{ .val = 3, .div = 4 },
+	{ .val = 4, .div = 4 },
+	{ .val = 5, .div = 4 },
+	{ .val = 6, .div = 4 },
+	{ .val = 7, .div = 4 },
+	{ } /* sentinel */
+};
+
+static const struct div_data sun8i_a23_axi_data __initconst = {
+	.width	= 3,
+	.table	= sun8i_a23_axi_table,
+};
+
 static const struct div_data sun4i_ahb_data __initconst = {
 	.shift	= 4,
 	.pow	= 1,
@@ -851,7 +780,7 @@ static void __init sunxi_divider_clk_setup(struct device_node *node,
 	struct clk *clk;
 	const char *clk_name = node->name;
 	const char *clk_parent;
-	void *reg;
+	void __iomem *reg;
 
 	reg = of_iomap(node, 0);
 
@@ -859,10 +788,10 @@ static void __init sunxi_divider_clk_setup(struct device_node *node,
 
 	of_property_read_string(node, "clock-output-names", &clk_name);
 
-	clk = clk_register_divider(NULL, clk_name, clk_parent, 0,
-				   reg, data->shift, data->width,
-				   data->pow ? CLK_DIVIDER_POWER_OF_TWO : 0,
-				   &clk_lock);
+	clk = clk_register_divider_table(NULL, clk_name, clk_parent, 0,
+					 reg, data->shift, data->width,
+					 data->pow ? CLK_DIVIDER_POWER_OF_TWO : 0,
+					 data->table, &clk_lock);
 	if (clk) {
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
 		clk_register_clkdev(clk, clk_name, NULL);
@@ -959,6 +888,10 @@ static const struct gates_data sun7i_a20_ahb_gates_data __initconst = {
 	.mask = { 0x12f77fff, 0x16ff3f },
 };
 
+static const struct gates_data sun8i_a23_ahb1_gates_data __initconst = {
+	.mask = {0x25386742, 0x2505111},
+};
+
 static const struct gates_data sun4i_apb0_gates_data __initconst = {
 	.mask = {0x4EF},
 };
@@ -991,6 +924,10 @@ static const struct gates_data sun6i_a31_apb1_gates_data __initconst = {
 	.mask = {0x3031},
 };
 
+static const struct gates_data sun8i_a23_apb1_gates_data __initconst = {
+	.mask = {0x3021},
+};
+
 static const struct gates_data sun6i_a31_apb2_gates_data __initconst = {
 	.mask = {0x3F000F},
 };
@@ -999,6 +936,10 @@ static const struct gates_data sun7i_a20_apb1_gates_data __initconst = {
 	.mask = { 0xff80ff },
 };
 
+static const struct gates_data sun8i_a23_apb2_gates_data __initconst = {
+	.mask = {0x1F0007},
+};
+
 static const struct gates_data sun4i_a10_usb_gates_data __initconst = {
 	.mask = {0x1C0},
 	.reset_mask = 0x07,
@@ -1009,6 +950,11 @@ static const struct gates_data sun5i_a13_usb_gates_data __initconst = {
 	.reset_mask = 0x03,
 };
 
+static const struct gates_data sun6i_a31_usb_gates_data __initconst = {
+	.mask = { BIT(18) | BIT(17) | BIT(16) | BIT(10) | BIT(9) | BIT(8) },
+	.reset_mask = BIT(2) | BIT(1) | BIT(0),
+};
+
 static void __init sunxi_gates_clk_setup(struct device_node *node,
 					 struct gates_data *data)
 {
@@ -1016,11 +962,10 @@ static void __init sunxi_gates_clk_setup(struct device_node *node,
 	struct gates_reset_data *reset_data;
 	const char *clk_parent;
 	const char *clk_name;
-	void *reg;
+	void __iomem *reg;
 	int qty;
 	int i = 0;
 	int j = 0;
-	int ignore;
 
 	reg = of_iomap(node, 0);
 
@@ -1041,14 +986,12 @@ static void __init sunxi_gates_clk_setup(struct device_node *node,
 		of_property_read_string_index(node, "clock-output-names",
 					      j, &clk_name);
 
-		/* No driver claims this clock, but it should remain gated */
-		ignore = !strcmp("ahb_sdram", clk_name) ? CLK_IGNORE_UNUSED : 0;
-
 		clk_data->clks[i] = clk_register_gate(NULL, clk_name,
-						      clk_parent, ignore,
+						      clk_parent, 0,
 						      reg + 4 * (i/32), i % 32,
 						      0, &clk_lock);
 		WARN_ON(IS_ERR(clk_data->clks[i]));
+		clk_register_clkdev(clk_data->clks[i], clk_name, NULL);
 
 		j++;
 	}
@@ -1141,7 +1084,7 @@ static void __init sunxi_divs_clk_setup(struct device_node *node,
 	struct clk_gate *gate = NULL;
 	struct clk_fixed_factor *fix_factor;
 	struct clk_divider *divider;
-	void *reg;
+	void __iomem *reg;
 	int i = 0;
 	int flags, clkflags;
 
@@ -1252,6 +1195,7 @@ free_clkdata:
 static const struct of_device_id clk_factors_match[] __initconst = {
 	{.compatible = "allwinner,sun4i-a10-pll1-clk", .data = &sun4i_pll1_data,},
 	{.compatible = "allwinner,sun6i-a31-pll1-clk", .data = &sun6i_a31_pll1_data,},
+	{.compatible = "allwinner,sun8i-a23-pll1-clk", .data = &sun8i_a23_pll1_data,},
 	{.compatible = "allwinner,sun7i-a20-pll4-clk", .data = &sun7i_a20_pll4_data,},
 	{.compatible = "allwinner,sun6i-a31-pll6-clk", .data = &sun6i_a31_pll6_data,},
 	{.compatible = "allwinner,sun4i-a10-apb1-clk", .data = &sun4i_apb1_data,},
@@ -1263,6 +1207,7 @@ static const struct of_device_id clk_factors_match[] __initconst = {
 /* Matches for divider clocks */
 static const struct of_device_id clk_div_match[] __initconst = {
 	{.compatible = "allwinner,sun4i-a10-axi-clk", .data = &sun4i_axi_data,},
+	{.compatible = "allwinner,sun8i-a23-axi-clk", .data = &sun8i_a23_axi_data,},
 	{.compatible = "allwinner,sun4i-a10-ahb-clk", .data = &sun4i_ahb_data,},
 	{.compatible = "allwinner,sun4i-a10-apb0-clk", .data = &sun4i_apb0_data,},
 	{.compatible = "allwinner,sun6i-a31-apb2-div-clk", .data = &sun6i_a31_apb2_div_data,},
@@ -1292,6 +1237,7 @@ static const struct of_device_id clk_gates_match[] __initconst = {
 	{.compatible = "allwinner,sun5i-a13-ahb-gates-clk", .data = &sun5i_a13_ahb_gates_data,},
 	{.compatible = "allwinner,sun6i-a31-ahb1-gates-clk", .data = &sun6i_a31_ahb1_gates_data,},
 	{.compatible = "allwinner,sun7i-a20-ahb-gates-clk", .data = &sun7i_a20_ahb_gates_data,},
+	{.compatible = "allwinner,sun8i-a23-ahb1-gates-clk", .data = &sun8i_a23_ahb1_gates_data,},
 	{.compatible = "allwinner,sun4i-a10-apb0-gates-clk", .data = &sun4i_apb0_gates_data,},
 	{.compatible = "allwinner,sun5i-a10s-apb0-gates-clk", .data = &sun5i_a10s_apb0_gates_data,},
 	{.compatible = "allwinner,sun5i-a13-apb0-gates-clk", .data = &sun5i_a13_apb0_gates_data,},
@@ -1301,9 +1247,12 @@ static const struct of_device_id clk_gates_match[] __initconst = {
 	{.compatible = "allwinner,sun5i-a13-apb1-gates-clk", .data = &sun5i_a13_apb1_gates_data,},
 	{.compatible = "allwinner,sun6i-a31-apb1-gates-clk", .data = &sun6i_a31_apb1_gates_data,},
 	{.compatible = "allwinner,sun7i-a20-apb1-gates-clk", .data = &sun7i_a20_apb1_gates_data,},
+	{.compatible = "allwinner,sun8i-a23-apb1-gates-clk", .data = &sun8i_a23_apb1_gates_data,},
 	{.compatible = "allwinner,sun6i-a31-apb2-gates-clk", .data = &sun6i_a31_apb2_gates_data,},
+	{.compatible = "allwinner,sun8i-a23-apb2-gates-clk", .data = &sun8i_a23_apb2_gates_data,},
 	{.compatible = "allwinner,sun4i-a10-usb-clk", .data = &sun4i_a10_usb_gates_data,},
 	{.compatible = "allwinner,sun5i-a13-usb-clk", .data = &sun5i_a13_usb_gates_data,},
+	{.compatible = "allwinner,sun6i-a31-usb-clk", .data = &sun6i_a31_usb_gates_data,},
 	{}
 };
 
@@ -1321,33 +1270,10 @@ static void __init of_sunxi_table_clock_setup(const struct of_device_id *clk_mat
 	}
 }
 
-/**
- * System clock protection
- *
- * By enabling these critical clocks, we prevent their accidental gating
- * by the framework
- */
-static void __init sunxi_clock_protect(void)
+static void __init sunxi_init_clocks(const char *clocks[], int nclocks)
 {
-	struct clk *clk;
-
-	/* memory bus clock - sun5i+ */
-	clk = clk_get(NULL, "mbus");
-	if (!IS_ERR(clk)) {
-		clk_prepare_enable(clk);
-		clk_put(clk);
-	}
+	unsigned int i;
 
-	/* DDR clock - sun4i+ */
-	clk = clk_get(NULL, "pll5_ddr");
-	if (!IS_ERR(clk)) {
-		clk_prepare_enable(clk);
-		clk_put(clk);
-	}
-}
-
-static void __init sunxi_init_clocks(struct device_node *np)
-{
 	/* Register factor clocks */
 	of_sunxi_table_clock_setup(clk_factors_match, sunxi_factors_clk_setup);
 
@@ -1363,11 +1289,51 @@ static void __init sunxi_init_clocks(struct device_node *np)
 	/* Register gate clocks */
 	of_sunxi_table_clock_setup(clk_gates_match, sunxi_gates_clk_setup);
 
-	/* Enable core system clocks */
-	sunxi_clock_protect();
+	/* Protect the clocks that needs to stay on */
+	for (i = 0; i < nclocks; i++) {
+		struct clk *clk = clk_get(NULL, clocks[i]);
+
+		if (!IS_ERR(clk))
+			clk_prepare_enable(clk);
+	}
+}
+
+static const char *sun4i_a10_critical_clocks[] __initdata = {
+	"pll5_ddr",
+	"ahb_sdram",
+};
+
+static void __init sun4i_a10_init_clocks(struct device_node *node)
+{
+	sunxi_init_clocks(sun4i_a10_critical_clocks,
+			  ARRAY_SIZE(sun4i_a10_critical_clocks));
+}
+CLK_OF_DECLARE(sun4i_a10_clk_init, "allwinner,sun4i-a10", sun4i_a10_init_clocks);
+
+static const char *sun5i_critical_clocks[] __initdata = {
+	"mbus",
+	"pll5_ddr",
+	"ahb_sdram",
+};
+
+static void __init sun5i_init_clocks(struct device_node *node)
+{
+	sunxi_init_clocks(sun5i_critical_clocks,
+			  ARRAY_SIZE(sun5i_critical_clocks));
+}
+CLK_OF_DECLARE(sun5i_a10s_clk_init, "allwinner,sun5i-a10s", sun5i_init_clocks);
+CLK_OF_DECLARE(sun5i_a13_clk_init, "allwinner,sun5i-a13", sun5i_init_clocks);
+CLK_OF_DECLARE(sun7i_a20_clk_init, "allwinner,sun7i-a20", sun5i_init_clocks);
+
+static const char *sun6i_critical_clocks[] __initdata = {
+	"cpu",
+	"ahb1_sdram",
+};
+
+static void __init sun6i_init_clocks(struct device_node *node)
+{
+	sunxi_init_clocks(sun6i_critical_clocks,
+			  ARRAY_SIZE(sun6i_critical_clocks));
 }
-CLK_OF_DECLARE(sun4i_a10_clk_init, "allwinner,sun4i-a10", sunxi_init_clocks);
-CLK_OF_DECLARE(sun5i_a10s_clk_init, "allwinner,sun5i-a10s", sunxi_init_clocks);
-CLK_OF_DECLARE(sun5i_a13_clk_init, "allwinner,sun5i-a13", sunxi_init_clocks);
-CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sunxi_init_clocks);
-CLK_OF_DECLARE(sun7i_a20_clk_init, "allwinner,sun7i-a20", sunxi_init_clocks);
+CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sun6i_init_clocks);
+CLK_OF_DECLARE(sun8i_a23_clk_init, "allwinner,sun8i-a23", sun6i_init_clocks);
diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c
index 637b62ccc91..c7c6d8fb32f 100644
--- a/drivers/clk/tegra/clk-pll.c
+++ b/drivers/clk/tegra/clk-pll.c
@@ -110,6 +110,12 @@
 #define XUSBIO_PLL_CFG0_SEQ_ENABLE		BIT(24)
 #define XUSBIO_PLL_CFG0_SEQ_START_STATE		BIT(25)
 
+#define SATA_PLL_CFG0		0x490
+#define SATA_PLL_CFG0_PADPLL_RESET_SWCTL	BIT(0)
+#define SATA_PLL_CFG0_PADPLL_USE_LOCKDET	BIT(2)
+#define SATA_PLL_CFG0_SEQ_ENABLE		BIT(24)
+#define SATA_PLL_CFG0_SEQ_START_STATE		BIT(25)
+
 #define PLLE_MISC_PLLE_PTS	BIT(8)
 #define PLLE_MISC_IDDQ_SW_VALUE	BIT(13)
 #define PLLE_MISC_IDDQ_SW_CTRL	BIT(14)
@@ -1361,6 +1367,19 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw)
 	val |= XUSBIO_PLL_CFG0_SEQ_ENABLE;
 	pll_writel(val, XUSBIO_PLL_CFG0, pll);
 
+	/* Enable hw control of SATA pll */
+	val = pll_readl(SATA_PLL_CFG0, pll);
+	val &= ~SATA_PLL_CFG0_PADPLL_RESET_SWCTL;
+	val |= SATA_PLL_CFG0_PADPLL_USE_LOCKDET;
+	val |= SATA_PLL_CFG0_SEQ_START_STATE;
+	pll_writel(val, SATA_PLL_CFG0, pll);
+
+	udelay(1);
+
+	val = pll_readl(SATA_PLL_CFG0, pll);
+	val |= SATA_PLL_CFG0_SEQ_ENABLE;
+	pll_writel(val, SATA_PLL_CFG0, pll);
+
 out:
 	if (pll->lock)
 		spin_unlock_irqrestore(pll->lock, flags);
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index adf6b814b5b..37f32c49674 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -469,7 +469,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	MUX("sata", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_SATA, 124, TEGRA_PERIPH_ON_APB, tegra_clk_sata),
 	MUX("adx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_ADX1, 180, TEGRA_PERIPH_ON_APB, tegra_clk_adx1),
 	MUX("amx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_AMX1, 185, TEGRA_PERIPH_ON_APB, tegra_clk_amx1),
-	MUX("vi_sensor2", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR2, 20, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor2),
+	MUX("vi_sensor2", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR2, 165, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor2),
 	MUX8("sdmmc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC1, 14, 0, tegra_clk_sdmmc1_8),
 	MUX8("sdmmc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC2, 9, 0, tegra_clk_sdmmc2_8),
 	MUX8("sdmmc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC3, 69, 0, tegra_clk_sdmmc3_8),
@@ -487,7 +487,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	MUX8("extern2", mux_plla_clk32_pllp_clkm_plle, CLK_SOURCE_EXTERN2, 121, 0, tegra_clk_extern2),
 	MUX8("extern3", mux_plla_clk32_pllp_clkm_plle, CLK_SOURCE_EXTERN3, 122, 0, tegra_clk_extern3),
 	MUX8("soc_therm", mux_pllm_pllc_pllp_plla, CLK_SOURCE_SOC_THERM, 78, TEGRA_PERIPH_ON_APB, tegra_clk_soc_therm),
-	MUX8("vi_sensor", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR, 20, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor_8),
+	MUX8("vi_sensor", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR, 164, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor_8),
 	MUX8("isp", mux_pllm_pllc_pllp_plla_clkm_pllc4, CLK_SOURCE_ISP, 23, TEGRA_PERIPH_ON_APB, tegra_clk_isp_8),
 	MUX8("entropy", mux_pllp_clkm1, CLK_SOURCE_ENTROPY, 149,  0, tegra_clk_entropy),
 	MUX8("hdmi_audio", mux_pllp3_pllc_clkm, CLK_SOURCE_HDMI_AUDIO, 176, TEGRA_PERIPH_NO_RESET, tegra_clk_hdmi_audio),
diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c
index b9c8ba258ef..f760f31d05c 100644
--- a/drivers/clk/tegra/clk-tegra114.c
+++ b/drivers/clk/tegra/clk-tegra114.c
@@ -151,6 +151,13 @@
 /* Tegra CPU clock and reset control regs */
 #define CLK_RST_CONTROLLER_CPU_CMPLX_STATUS	0x470
 
+#define MUX8(_name, _parents, _offset, \
+			     _clk_num, _gate_flags, _clk_id)	\
+	TEGRA_INIT_DATA_TABLE(_name, NULL, NULL, _parents, _offset,\
+			29, MASK(3), 0, 0, 8, 1, TEGRA_DIVIDER_ROUND_UP,\
+			_clk_num, _gate_flags, _clk_id, _parents##_idx, 0,\
+			NULL)
+
 #ifdef CONFIG_PM_SLEEP
 static struct cpu_clk_suspend_context {
 	u32 clk_csite_src;
@@ -777,7 +784,6 @@ static struct tegra_clk tegra114_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_spdif_in] = { .dt_id = TEGRA114_CLK_SPDIF_IN, .present = true },
 	[tegra_clk_spdif_out] = { .dt_id = TEGRA114_CLK_SPDIF_OUT, .present = true },
 	[tegra_clk_vi_8] = { .dt_id = TEGRA114_CLK_VI, .present = true },
-	[tegra_clk_vi_sensor_8] = { .dt_id = TEGRA114_CLK_VI_SENSOR, .present = true },
 	[tegra_clk_fuse] = { .dt_id = TEGRA114_CLK_FUSE, .present = true },
 	[tegra_clk_fuse_burn] = { .dt_id = TEGRA114_CLK_FUSE_BURN, .present = true },
 	[tegra_clk_clk_32k] = { .dt_id = TEGRA114_CLK_CLK_32K, .present = true },
@@ -923,6 +929,13 @@ static struct tegra_devclk devclks[] __initdata = {
 	{ .dev_id = "timer", .dt_id = TEGRA114_CLK_TIMER },
 };
 
+static const char *mux_pllm_pllc2_c_c3_pllp_plla[] = {
+	"pll_m", "pll_c2", "pll_c", "pll_c3", "pll_p", "pll_a_out0"
+};
+static u32 mux_pllm_pllc2_c_c3_pllp_plla_idx[] = {
+	[0] = 0, [1] = 1, [2] = 2, [3] = 3, [4] = 4, [5] = 6,
+};
+
 static struct clk **clks;
 
 static unsigned long osc_freq;
@@ -1178,10 +1191,18 @@ static void __init tegra114_pll_init(void __iomem *clk_base,
 	clks[TEGRA114_CLK_PLL_E_OUT0] = clk;
 }
 
+#define CLK_SOURCE_VI_SENSOR 0x1a8
+
+static struct tegra_periph_init_data tegra_periph_clk_list[] = {
+	MUX8("vi_sensor", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR, 20, TEGRA_PERIPH_NO_RESET, TEGRA114_CLK_VI_SENSOR),
+};
+
 static __init void tegra114_periph_clk_init(void __iomem *clk_base,
 					    void __iomem *pmc_base)
 {
 	struct clk *clk;
+	struct tegra_periph_init_data *data;
+	int i;
 
 	/* xusb_ss_div2 */
 	clk = clk_register_fixed_factor(NULL, "xusb_ss_div2", "xusb_ss_src", 0,
@@ -1209,6 +1230,14 @@ static __init void tegra114_periph_clk_init(void __iomem *clk_base,
 			       clk_base + CLK_SOURCE_EMC,
 			       29, 3, 0, NULL);
 
+	for (i = 0; i < ARRAY_SIZE(tegra_periph_clk_list); i++) {
+		data = &tegra_periph_clk_list[i];
+		clk = tegra_clk_register_periph(data->name,
+			data->p.parent_names, data->num_parents,
+			&data->periph, clk_base, data->offset, data->flags);
+		clks[data->clk_id] = clk;
+	}
+
 	tegra_periph_clk_init(clk_base, pmc_base, tegra114_clks,
 				&pll_p_params);
 }
diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index 80efe51fdcd..9525c684d14 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -869,7 +869,7 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_spdif_in] = { .dt_id = TEGRA124_CLK_SPDIF_IN, .present = true },
 	[tegra_clk_spdif_out] = { .dt_id = TEGRA124_CLK_SPDIF_OUT, .present = true },
 	[tegra_clk_vi_9] = { .dt_id = TEGRA124_CLK_VI, .present = true },
-	[tegra_clk_vi_sensor] = { .dt_id = TEGRA124_CLK_VI_SENSOR, .present = true },
+	[tegra_clk_vi_sensor_8] = { .dt_id = TEGRA124_CLK_VI_SENSOR, .present = true },
 	[tegra_clk_fuse] = { .dt_id = TEGRA124_CLK_FUSE, .present = true },
 	[tegra_clk_fuse_burn] = { .dt_id = TEGRA124_CLK_FUSE_BURN, .present = true },
 	[tegra_clk_clk_32k] = { .dt_id = TEGRA124_CLK_CLK_32K, .present = true },
@@ -1369,6 +1369,14 @@ static struct tegra_clk_init_table init_table[] __initdata = {
 	{TEGRA124_CLK_XUSB_HS_SRC, TEGRA124_CLK_PLL_U_60M, 60000000, 0},
 	{TEGRA124_CLK_XUSB_FALCON_SRC, TEGRA124_CLK_PLL_RE_OUT, 224000000, 0},
 	{TEGRA124_CLK_XUSB_HOST_SRC, TEGRA124_CLK_PLL_RE_OUT, 112000000, 0},
+	{TEGRA124_CLK_SATA, TEGRA124_CLK_PLL_P, 104000000, 0},
+	{TEGRA124_CLK_SATA_OOB, TEGRA124_CLK_PLL_P, 204000000, 0},
+	{TEGRA124_CLK_EMC, TEGRA124_CLK_CLK_MAX, 0, 1},
+	{TEGRA124_CLK_CCLK_G, TEGRA124_CLK_CLK_MAX, 0, 1},
+	{TEGRA124_CLK_MSELECT, TEGRA124_CLK_CLK_MAX, 0, 1},
+	{TEGRA124_CLK_CSITE, TEGRA124_CLK_CLK_MAX, 0, 1},
+	{TEGRA124_CLK_TSENSOR, TEGRA124_CLK_CLK_M, 400000, 0},
+	{TEGRA124_CLK_SOC_THERM, TEGRA124_CLK_PLL_P, 51000000, 0},
 	/* This MUST be the last entry. */
 	{TEGRA124_CLK_CLK_MAX, TEGRA124_CLK_CLK_MAX, 0, 0},
 };
diff --git a/drivers/clk/tegra/clk.c b/drivers/clk/tegra/clk.c
index c0a7d772351..bf452b62beb 100644
--- a/drivers/clk/tegra/clk.c
+++ b/drivers/clk/tegra/clk.c
@@ -277,6 +277,12 @@ void __init tegra_register_devclks(struct tegra_devclk *dev_clks, int num)
 	for (i = 0; i < num; i++, dev_clks++)
 		clk_register_clkdev(clks[dev_clks->dt_id], dev_clks->con_id,
 				dev_clks->dev_id);
+
+	for (i = 0; i < clk_num; i++) {
+		if (!IS_ERR_OR_NULL(clks[i]))
+			clk_register_clkdev(clks[i], __clk_get_name(clks[i]),
+				"tegra-clk-debug");
+	}
 }
 
 struct clk ** __init tegra_lookup_dt_id(int clk_id,
diff --git a/drivers/clk/ti/Makefile b/drivers/clk/ti/Makefile
index 4319d4031aa..ed4d0aaf891 100644
--- a/drivers/clk/ti/Makefile
+++ b/drivers/clk/ti/Makefile
@@ -3,9 +3,11 @@ obj-y					+= clk.o autoidle.o clockdomain.o
 clk-common				= dpll.o composite.o divider.o gate.o \
 					  fixed-factor.o mux.o apll.o
 obj-$(CONFIG_SOC_AM33XX)		+= $(clk-common) clk-33xx.o
+obj-$(CONFIG_ARCH_OMAP2)		+= $(clk-common) interface.o clk-2xxx.o
 obj-$(CONFIG_ARCH_OMAP3)		+= $(clk-common) interface.o clk-3xxx.o
 obj-$(CONFIG_ARCH_OMAP4)		+= $(clk-common) clk-44xx.o
 obj-$(CONFIG_SOC_OMAP5)			+= $(clk-common) clk-54xx.o
-obj-$(CONFIG_SOC_DRA7XX)		+= $(clk-common) clk-7xx.o
+obj-$(CONFIG_SOC_DRA7XX)		+= $(clk-common) clk-7xx.o \
+					   clk-dra7-atl.o
 obj-$(CONFIG_SOC_AM43XX)		+= $(clk-common) clk-43xx.o
 endif
diff --git a/drivers/clk/ti/apll.c b/drivers/clk/ti/apll.c
index b986f61f5a7..72d97279eae 100644
--- a/drivers/clk/ti/apll.c
+++ b/drivers/clk/ti/apll.c
@@ -77,13 +77,11 @@ static int dra7_apll_enable(struct clk_hw *hw)
 	if (i == MAX_APLL_WAIT_TRIES) {
 		pr_warn("clock: %s failed transition to '%s'\n",
 			clk_name, (state) ? "locked" : "bypassed");
-	} else {
+		r = -EBUSY;
+	} else
 		pr_debug("clock: %s transition to '%s' in %d loops\n",
 			 clk_name, (state) ? "locked" : "bypassed", i);
 
-		r = 0;
-	}
-
 	return r;
 }
 
@@ -221,3 +219,184 @@ cleanup:
 	kfree(init);
 }
 CLK_OF_DECLARE(dra7_apll_clock, "ti,dra7-apll-clock", of_dra7_apll_setup);
+
+#define OMAP2_EN_APLL_LOCKED	0x3
+#define OMAP2_EN_APLL_STOPPED	0x0
+
+static int omap2_apll_is_enabled(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *ad = clk->dpll_data;
+	u32 v;
+
+	v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+	v &= ad->enable_mask;
+
+	v >>= __ffs(ad->enable_mask);
+
+	return v == OMAP2_EN_APLL_LOCKED ? 1 : 0;
+}
+
+static unsigned long omap2_apll_recalc(struct clk_hw *hw,
+				       unsigned long parent_rate)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+
+	if (omap2_apll_is_enabled(hw))
+		return clk->fixed_rate;
+
+	return 0;
+}
+
+static int omap2_apll_enable(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *ad = clk->dpll_data;
+	u32 v;
+	int i = 0;
+
+	v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+	v &= ~ad->enable_mask;
+	v |= OMAP2_EN_APLL_LOCKED << __ffs(ad->enable_mask);
+	ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+
+	while (1) {
+		v = ti_clk_ll_ops->clk_readl(ad->idlest_reg);
+		if (v & ad->idlest_mask)
+			break;
+		if (i > MAX_APLL_WAIT_TRIES)
+			break;
+		i++;
+		udelay(1);
+	}
+
+	if (i == MAX_APLL_WAIT_TRIES) {
+		pr_warn("%s failed to transition to locked\n",
+			__clk_get_name(clk->hw.clk));
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void omap2_apll_disable(struct clk_hw *hw)
+{
+	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+	struct dpll_data *ad = clk->dpll_data;
+	u32 v;
+
+	v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+	v &= ~ad->enable_mask;
+	v |= OMAP2_EN_APLL_STOPPED << __ffs(ad->enable_mask);
+	ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+}
+
+static struct clk_ops omap2_apll_ops = {
+	.enable		= &omap2_apll_enable,
+	.disable	= &omap2_apll_disable,
+	.is_enabled	= &omap2_apll_is_enabled,
+	.recalc_rate	= &omap2_apll_recalc,
+};
+
+static void omap2_apll_set_autoidle(struct clk_hw_omap *clk, u32 val)
+{
+	struct dpll_data *ad = clk->dpll_data;
+	u32 v;
+
+	v = ti_clk_ll_ops->clk_readl(ad->autoidle_reg);
+	v &= ~ad->autoidle_mask;
+	v |= val << __ffs(ad->autoidle_mask);
+	ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+}
+
+#define OMAP2_APLL_AUTOIDLE_LOW_POWER_STOP	0x3
+#define OMAP2_APLL_AUTOIDLE_DISABLE		0x0
+
+static void omap2_apll_allow_idle(struct clk_hw_omap *clk)
+{
+	omap2_apll_set_autoidle(clk, OMAP2_APLL_AUTOIDLE_LOW_POWER_STOP);
+}
+
+static void omap2_apll_deny_idle(struct clk_hw_omap *clk)
+{
+	omap2_apll_set_autoidle(clk, OMAP2_APLL_AUTOIDLE_DISABLE);
+}
+
+static struct clk_hw_omap_ops omap2_apll_hwops = {
+	.allow_idle	= &omap2_apll_allow_idle,
+	.deny_idle	= &omap2_apll_deny_idle,
+};
+
+static void __init of_omap2_apll_setup(struct device_node *node)
+{
+	struct dpll_data *ad = NULL;
+	struct clk_hw_omap *clk_hw = NULL;
+	struct clk_init_data *init = NULL;
+	struct clk *clk;
+	const char *parent_name;
+	u32 val;
+
+	ad = kzalloc(sizeof(*ad), GFP_KERNEL);
+	clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
+	init = kzalloc(sizeof(*init), GFP_KERNEL);
+
+	if (!ad || !clk_hw || !init)
+		goto cleanup;
+
+	clk_hw->dpll_data = ad;
+	clk_hw->hw.init = init;
+	init->ops = &omap2_apll_ops;
+	init->name = node->name;
+	clk_hw->ops = &omap2_apll_hwops;
+
+	init->num_parents = of_clk_get_parent_count(node);
+	if (init->num_parents != 1) {
+		pr_err("%s must have one parent\n", node->name);
+		goto cleanup;
+	}
+
+	parent_name = of_clk_get_parent_name(node, 0);
+	init->parent_names = &parent_name;
+
+	if (of_property_read_u32(node, "ti,clock-frequency", &val)) {
+		pr_err("%s missing clock-frequency\n", node->name);
+		goto cleanup;
+	}
+	clk_hw->fixed_rate = val;
+
+	if (of_property_read_u32(node, "ti,bit-shift", &val)) {
+		pr_err("%s missing bit-shift\n", node->name);
+		goto cleanup;
+	}
+
+	clk_hw->enable_bit = val;
+	ad->enable_mask = 0x3 << val;
+	ad->autoidle_mask = 0x3 << val;
+
+	if (of_property_read_u32(node, "ti,idlest-shift", &val)) {
+		pr_err("%s missing idlest-shift\n", node->name);
+		goto cleanup;
+	}
+
+	ad->idlest_mask = 1 << val;
+
+	ad->control_reg = ti_clk_get_reg_addr(node, 0);
+	ad->autoidle_reg = ti_clk_get_reg_addr(node, 1);
+	ad->idlest_reg = ti_clk_get_reg_addr(node, 2);
+
+	if (!ad->control_reg || !ad->autoidle_reg || !ad->idlest_reg)
+		goto cleanup;
+
+	clk = clk_register(NULL, &clk_hw->hw);
+	if (!IS_ERR(clk)) {
+		of_clk_add_provider(node, of_clk_src_simple_get, clk);
+		kfree(init);
+		return;
+	}
+cleanup:
+	kfree(ad);
+	kfree(clk_hw);
+	kfree(init);
+}
+CLK_OF_DECLARE(omap2_apll_clock, "ti,omap2-apll-clock",
+	       of_omap2_apll_setup);
diff --git a/drivers/clk/ti/clk-2xxx.c b/drivers/clk/ti/clk-2xxx.c
new file mode 100644
index 00000000000..c808ab3d2bb
--- /dev/null
+++ b/drivers/clk/ti/clk-2xxx.c
@@ -0,0 +1,256 @@
+/*
+ * OMAP2 Clock init
+ *
+ * Copyright (C) 2013 Texas Instruments, Inc
+ *     Tero Kristo (t-kristo@ti.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/clk-provider.h>
+#include <linux/clk/ti.h>
+
+static struct ti_dt_clk omap2xxx_clks[] = {
+	DT_CLK(NULL, "func_32k_ck", "func_32k_ck"),
+	DT_CLK(NULL, "secure_32k_ck", "secure_32k_ck"),
+	DT_CLK(NULL, "virt_12m_ck", "virt_12m_ck"),
+	DT_CLK(NULL, "virt_13m_ck", "virt_13m_ck"),
+	DT_CLK(NULL, "virt_19200000_ck", "virt_19200000_ck"),
+	DT_CLK(NULL, "virt_26m_ck", "virt_26m_ck"),
+	DT_CLK(NULL, "aplls_clkin_ck", "aplls_clkin_ck"),
+	DT_CLK(NULL, "aplls_clkin_x2_ck", "aplls_clkin_x2_ck"),
+	DT_CLK(NULL, "osc_ck", "osc_ck"),
+	DT_CLK(NULL, "sys_ck", "sys_ck"),
+	DT_CLK(NULL, "alt_ck", "alt_ck"),
+	DT_CLK(NULL, "mcbsp_clks", "mcbsp_clks"),
+	DT_CLK(NULL, "dpll_ck", "dpll_ck"),
+	DT_CLK(NULL, "apll96_ck", "apll96_ck"),
+	DT_CLK(NULL, "apll54_ck", "apll54_ck"),
+	DT_CLK(NULL, "func_54m_ck", "func_54m_ck"),
+	DT_CLK(NULL, "core_ck", "core_ck"),
+	DT_CLK(NULL, "func_96m_ck", "func_96m_ck"),
+	DT_CLK(NULL, "func_48m_ck", "func_48m_ck"),
+	DT_CLK(NULL, "func_12m_ck", "func_12m_ck"),
+	DT_CLK(NULL, "sys_clkout_src", "sys_clkout_src"),
+	DT_CLK(NULL, "sys_clkout", "sys_clkout"),
+	DT_CLK(NULL, "emul_ck", "emul_ck"),
+	DT_CLK(NULL, "mpu_ck", "mpu_ck"),
+	DT_CLK(NULL, "dsp_fck", "dsp_fck"),
+	DT_CLK(NULL, "gfx_3d_fck", "gfx_3d_fck"),
+	DT_CLK(NULL, "gfx_2d_fck", "gfx_2d_fck"),
+	DT_CLK(NULL, "gfx_ick", "gfx_ick"),
+	DT_CLK("omapdss_dss", "ick", "dss_ick"),
+	DT_CLK(NULL, "dss_ick", "dss_ick"),
+	DT_CLK(NULL, "dss1_fck", "dss1_fck"),
+	DT_CLK(NULL, "dss2_fck", "dss2_fck"),
+	DT_CLK(NULL, "dss_54m_fck", "dss_54m_fck"),
+	DT_CLK(NULL, "core_l3_ck", "core_l3_ck"),
+	DT_CLK(NULL, "ssi_fck", "ssi_ssr_sst_fck"),
+	DT_CLK(NULL, "usb_l4_ick", "usb_l4_ick"),
+	DT_CLK(NULL, "l4_ck", "l4_ck"),
+	DT_CLK(NULL, "ssi_l4_ick", "ssi_l4_ick"),
+	DT_CLK(NULL, "gpt1_ick", "gpt1_ick"),
+	DT_CLK(NULL, "gpt1_fck", "gpt1_fck"),
+	DT_CLK(NULL, "gpt2_ick", "gpt2_ick"),
+	DT_CLK(NULL, "gpt2_fck", "gpt2_fck"),
+	DT_CLK(NULL, "gpt3_ick", "gpt3_ick"),
+	DT_CLK(NULL, "gpt3_fck", "gpt3_fck"),
+	DT_CLK(NULL, "gpt4_ick", "gpt4_ick"),
+	DT_CLK(NULL, "gpt4_fck", "gpt4_fck"),
+	DT_CLK(NULL, "gpt5_ick", "gpt5_ick"),
+	DT_CLK(NULL, "gpt5_fck", "gpt5_fck"),
+	DT_CLK(NULL, "gpt6_ick", "gpt6_ick"),
+	DT_CLK(NULL, "gpt6_fck", "gpt6_fck"),
+	DT_CLK(NULL, "gpt7_ick", "gpt7_ick"),
+	DT_CLK(NULL, "gpt7_fck", "gpt7_fck"),
+	DT_CLK(NULL, "gpt8_ick", "gpt8_ick"),
+	DT_CLK(NULL, "gpt8_fck", "gpt8_fck"),
+	DT_CLK(NULL, "gpt9_ick", "gpt9_ick"),
+	DT_CLK(NULL, "gpt9_fck", "gpt9_fck"),
+	DT_CLK(NULL, "gpt10_ick", "gpt10_ick"),
+	DT_CLK(NULL, "gpt10_fck", "gpt10_fck"),
+	DT_CLK(NULL, "gpt11_ick", "gpt11_ick"),
+	DT_CLK(NULL, "gpt11_fck", "gpt11_fck"),
+	DT_CLK(NULL, "gpt12_ick", "gpt12_ick"),
+	DT_CLK(NULL, "gpt12_fck", "gpt12_fck"),
+	DT_CLK("omap-mcbsp.1", "ick", "mcbsp1_ick"),
+	DT_CLK(NULL, "mcbsp1_ick", "mcbsp1_ick"),
+	DT_CLK(NULL, "mcbsp1_fck", "mcbsp1_fck"),
+	DT_CLK("omap-mcbsp.2", "ick", "mcbsp2_ick"),
+	DT_CLK(NULL, "mcbsp2_ick", "mcbsp2_ick"),
+	DT_CLK(NULL, "mcbsp2_fck", "mcbsp2_fck"),
+	DT_CLK("omap2_mcspi.1", "ick", "mcspi1_ick"),
+	DT_CLK(NULL, "mcspi1_ick", "mcspi1_ick"),
+	DT_CLK(NULL, "mcspi1_fck", "mcspi1_fck"),
+	DT_CLK("omap2_mcspi.2", "ick", "mcspi2_ick"),
+	DT_CLK(NULL, "mcspi2_ick", "mcspi2_ick"),
+	DT_CLK(NULL, "mcspi2_fck", "mcspi2_fck"),
+	DT_CLK(NULL, "uart1_ick", "uart1_ick"),
+	DT_CLK(NULL, "uart1_fck", "uart1_fck"),
+	DT_CLK(NULL, "uart2_ick", "uart2_ick"),
+	DT_CLK(NULL, "uart2_fck", "uart2_fck"),
+	DT_CLK(NULL, "uart3_ick", "uart3_ick"),
+	DT_CLK(NULL, "uart3_fck", "uart3_fck"),
+	DT_CLK(NULL, "gpios_ick", "gpios_ick"),
+	DT_CLK(NULL, "gpios_fck", "gpios_fck"),
+	DT_CLK("omap_wdt", "ick", "mpu_wdt_ick"),
+	DT_CLK(NULL, "mpu_wdt_ick", "mpu_wdt_ick"),
+	DT_CLK(NULL, "mpu_wdt_fck", "mpu_wdt_fck"),
+	DT_CLK(NULL, "sync_32k_ick", "sync_32k_ick"),
+	DT_CLK(NULL, "wdt1_ick", "wdt1_ick"),
+	DT_CLK(NULL, "omapctrl_ick", "omapctrl_ick"),
+	DT_CLK("omap24xxcam", "fck", "cam_fck"),
+	DT_CLK(NULL, "cam_fck", "cam_fck"),
+	DT_CLK("omap24xxcam", "ick", "cam_ick"),
+	DT_CLK(NULL, "cam_ick", "cam_ick"),
+	DT_CLK(NULL, "mailboxes_ick", "mailboxes_ick"),
+	DT_CLK(NULL, "wdt4_ick", "wdt4_ick"),
+	DT_CLK(NULL, "wdt4_fck", "wdt4_fck"),
+	DT_CLK(NULL, "mspro_ick", "mspro_ick"),
+	DT_CLK(NULL, "mspro_fck", "mspro_fck"),
+	DT_CLK(NULL, "fac_ick", "fac_ick"),
+	DT_CLK(NULL, "fac_fck", "fac_fck"),
+	DT_CLK("omap_hdq.0", "ick", "hdq_ick"),
+	DT_CLK(NULL, "hdq_ick", "hdq_ick"),
+	DT_CLK("omap_hdq.0", "fck", "hdq_fck"),
+	DT_CLK(NULL, "hdq_fck", "hdq_fck"),
+	DT_CLK("omap_i2c.1", "ick", "i2c1_ick"),
+	DT_CLK(NULL, "i2c1_ick", "i2c1_ick"),
+	DT_CLK("omap_i2c.2", "ick", "i2c2_ick"),
+	DT_CLK(NULL, "i2c2_ick", "i2c2_ick"),
+	DT_CLK(NULL, "gpmc_fck", "gpmc_fck"),
+	DT_CLK(NULL, "sdma_fck", "sdma_fck"),
+	DT_CLK(NULL, "sdma_ick", "sdma_ick"),
+	DT_CLK(NULL, "sdrc_ick", "sdrc_ick"),
+	DT_CLK(NULL, "des_ick", "des_ick"),
+	DT_CLK("omap-sham", "ick", "sha_ick"),
+	DT_CLK(NULL, "sha_ick", "sha_ick"),
+	DT_CLK("omap_rng", "ick", "rng_ick"),
+	DT_CLK(NULL, "rng_ick", "rng_ick"),
+	DT_CLK("omap-aes", "ick", "aes_ick"),
+	DT_CLK(NULL, "aes_ick", "aes_ick"),
+	DT_CLK(NULL, "pka_ick", "pka_ick"),
+	DT_CLK(NULL, "usb_fck", "usb_fck"),
+	DT_CLK(NULL, "timer_32k_ck", "func_32k_ck"),
+	DT_CLK(NULL, "timer_sys_ck", "sys_ck"),
+	DT_CLK(NULL, "timer_ext_ck", "alt_ck"),
+	{ .node_name = NULL },
+};
+
+static struct ti_dt_clk omap2420_clks[] = {
+	DT_CLK(NULL, "sys_clkout2_src", "sys_clkout2_src"),
+	DT_CLK(NULL, "sys_clkout2", "sys_clkout2"),
+	DT_CLK(NULL, "dsp_ick", "dsp_ick"),
+	DT_CLK(NULL, "iva1_ifck", "iva1_ifck"),
+	DT_CLK(NULL, "iva1_mpu_int_ifck", "iva1_mpu_int_ifck"),
+	DT_CLK(NULL, "wdt3_ick", "wdt3_ick"),
+	DT_CLK(NULL, "wdt3_fck", "wdt3_fck"),
+	DT_CLK("mmci-omap.0", "ick", "mmc_ick"),
+	DT_CLK(NULL, "mmc_ick", "mmc_ick"),
+	DT_CLK("mmci-omap.0", "fck", "mmc_fck"),
+	DT_CLK(NULL, "mmc_fck", "mmc_fck"),
+	DT_CLK(NULL, "eac_ick", "eac_ick"),
+	DT_CLK(NULL, "eac_fck", "eac_fck"),
+	DT_CLK(NULL, "i2c1_fck", "i2c1_fck"),
+	DT_CLK(NULL, "i2c2_fck", "i2c2_fck"),
+	DT_CLK(NULL, "vlynq_ick", "vlynq_ick"),
+	DT_CLK(NULL, "vlynq_fck", "vlynq_fck"),
+	DT_CLK("musb-hdrc", "fck", "osc_ck"),
+	{ .node_name = NULL },
+};
+
+static struct ti_dt_clk omap2430_clks[] = {
+	DT_CLK("twl", "fck", "osc_ck"),
+	DT_CLK(NULL, "iva2_1_ick", "iva2_1_ick"),
+	DT_CLK(NULL, "mdm_ick", "mdm_ick"),
+	DT_CLK(NULL, "mdm_osc_ck", "mdm_osc_ck"),
+	DT_CLK("omap-mcbsp.3", "ick", "mcbsp3_ick"),
+	DT_CLK(NULL, "mcbsp3_ick", "mcbsp3_ick"),
+	DT_CLK(NULL, "mcbsp3_fck", "mcbsp3_fck"),
+	DT_CLK("omap-mcbsp.4", "ick", "mcbsp4_ick"),
+	DT_CLK(NULL, "mcbsp4_ick", "mcbsp4_ick"),
+	DT_CLK(NULL, "mcbsp4_fck", "mcbsp4_fck"),
+	DT_CLK("omap-mcbsp.5", "ick", "mcbsp5_ick"),
+	DT_CLK(NULL, "mcbsp5_ick", "mcbsp5_ick"),
+	DT_CLK(NULL, "mcbsp5_fck", "mcbsp5_fck"),
+	DT_CLK("omap2_mcspi.3", "ick", "mcspi3_ick"),
+	DT_CLK(NULL, "mcspi3_ick", "mcspi3_ick"),
+	DT_CLK(NULL, "mcspi3_fck", "mcspi3_fck"),
+	DT_CLK(NULL, "icr_ick", "icr_ick"),
+	DT_CLK(NULL, "i2chs1_fck", "i2chs1_fck"),
+	DT_CLK(NULL, "i2chs2_fck", "i2chs2_fck"),
+	DT_CLK("musb-omap2430", "ick", "usbhs_ick"),
+	DT_CLK(NULL, "usbhs_ick", "usbhs_ick"),
+	DT_CLK("omap_hsmmc.0", "ick", "mmchs1_ick"),
+	DT_CLK(NULL, "mmchs1_ick", "mmchs1_ick"),
+	DT_CLK(NULL, "mmchs1_fck", "mmchs1_fck"),
+	DT_CLK("omap_hsmmc.1", "ick", "mmchs2_ick"),
+	DT_CLK(NULL, "mmchs2_ick", "mmchs2_ick"),
+	DT_CLK(NULL, "mmchs2_fck", "mmchs2_fck"),
+	DT_CLK(NULL, "gpio5_ick", "gpio5_ick"),
+	DT_CLK(NULL, "gpio5_fck", "gpio5_fck"),
+	DT_CLK(NULL, "mdm_intc_ick", "mdm_intc_ick"),
+	DT_CLK("omap_hsmmc.0", "mmchsdb_fck", "mmchsdb1_fck"),
+	DT_CLK(NULL, "mmchsdb1_fck", "mmchsdb1_fck"),
+	DT_CLK("omap_hsmmc.1", "mmchsdb_fck", "mmchsdb2_fck"),
+	DT_CLK(NULL, "mmchsdb2_fck", "mmchsdb2_fck"),
+	{ .node_name = NULL },
+};
+
+static const char *enable_init_clks[] = {
+	"apll96_ck",
+	"apll54_ck",
+	"sync_32k_ick",
+	"omapctrl_ick",
+	"gpmc_fck",
+	"sdrc_ick",
+};
+
+enum {
+	OMAP2_SOC_OMAP2420,
+	OMAP2_SOC_OMAP2430,
+};
+
+static int __init omap2xxx_dt_clk_init(int soc_type)
+{
+	ti_dt_clocks_register(omap2xxx_clks);
+
+	if (soc_type == OMAP2_SOC_OMAP2420)
+		ti_dt_clocks_register(omap2420_clks);
+	else
+		ti_dt_clocks_register(omap2430_clks);
+
+	omap2xxx_clkt_vps_init();
+
+	omap2_clk_disable_autoidle_all();
+
+	omap2_clk_enable_init_clocks(enable_init_clks,
+				     ARRAY_SIZE(enable_init_clks));
+
+	pr_info("Clocking rate (Crystal/DPLL/MPU): %ld.%01ld/%ld/%ld MHz\n",
+		(clk_get_rate(clk_get_sys(NULL, "sys_ck")) / 1000000),
+		(clk_get_rate(clk_get_sys(NULL, "sys_ck")) / 100000) % 10,
+		(clk_get_rate(clk_get_sys(NULL, "dpll_ck")) / 1000000),
+		(clk_get_rate(clk_get_sys(NULL, "mpu_ck")) / 1000000));
+
+	return 0;
+}
+
+int __init omap2420_dt_clk_init(void)
+{
+	return omap2xxx_dt_clk_init(OMAP2_SOC_OMAP2420);
+}
+
+int __init omap2430_dt_clk_init(void)
+{
+	return omap2xxx_dt_clk_init(OMAP2_SOC_OMAP2430);
+}
diff --git a/drivers/clk/ti/clk-43xx.c b/drivers/clk/ti/clk-43xx.c
index 527a43da3d3..3795fce8a83 100644
--- a/drivers/clk/ti/clk-43xx.c
+++ b/drivers/clk/ti/clk-43xx.c
@@ -116,9 +116,25 @@ static struct ti_dt_clk am43xx_clks[] = {
 
 int __init am43xx_dt_clk_init(void)
 {
+	struct clk *clk1, *clk2;
+
 	ti_dt_clocks_register(am43xx_clks);
 
 	omap2_clk_disable_autoidle_all();
 
+	/*
+	 * cpsw_cpts_rft_clk  has got the choice of 3 clocksources
+	 * dpll_core_m4_ck, dpll_core_m5_ck and dpll_disp_m2_ck.
+	 * By default dpll_core_m4_ck is selected, witn this as clock
+	 * source the CPTS doesnot work properly. It gives clockcheck errors
+	 * while running PTP.
+	 * clockcheck: clock jumped backward or running slower than expected!
+	 * By selecting dpll_core_m5_ck as the clocksource fixes this issue.
+	 * In AM335x dpll_core_m5_ck is the default clocksource.
+	 */
+	clk1 = clk_get_sys(NULL, "cpsw_cpts_rft_clk");
+	clk2 = clk_get_sys(NULL, "dpll_core_m5_ck");
+	clk_set_parent(clk1, clk2);
+
 	return 0;
 }
diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c
index 08f3d1b915b..5e183993e3e 100644
--- a/drivers/clk/ti/clk-54xx.c
+++ b/drivers/clk/ti/clk-54xx.c
@@ -240,6 +240,12 @@ int __init omap5xxx_dt_clk_init(void)
 	if (rc)
 		pr_err("%s: failed to configure ABE DPLL!\n", __func__);
 
+	abe_dpll = clk_get_sys(NULL, "dpll_abe_m2x2_ck");
+	if (!rc)
+		rc = clk_set_rate(abe_dpll, OMAP5_DPLL_ABE_DEFFREQ * 2);
+	if (rc)
+		pr_err("%s: failed to configure ABE m2x2 DPLL!\n", __func__);
+
 	usb_dpll = clk_get_sys(NULL, "dpll_usb_ck");
 	rc = clk_set_rate(usb_dpll, OMAP5_DPLL_USB_DEFFREQ);
 	if (rc)
diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index f7e40734c81..62ac8f6e480 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -16,15 +16,16 @@
 #include <linux/clkdev.h>
 #include <linux/clk/ti.h>
 
-#define DRA7_DPLL_ABE_DEFFREQ				361267200
+#define DRA7_DPLL_ABE_DEFFREQ				180633600
 #define DRA7_DPLL_GMAC_DEFFREQ				1000000000
+#define DRA7_DPLL_USB_DEFFREQ				960000000
 
 
 static struct ti_dt_clk dra7xx_clks[] = {
 	DT_CLK(NULL, "atl_clkin0_ck", "atl_clkin0_ck"),
 	DT_CLK(NULL, "atl_clkin1_ck", "atl_clkin1_ck"),
 	DT_CLK(NULL, "atl_clkin2_ck", "atl_clkin2_ck"),
-	DT_CLK(NULL, "atlclkin3_ck", "atlclkin3_ck"),
+	DT_CLK(NULL, "atl_clkin3_ck", "atl_clkin3_ck"),
 	DT_CLK(NULL, "hdmi_clkin_ck", "hdmi_clkin_ck"),
 	DT_CLK(NULL, "mlb_clkin_ck", "mlb_clkin_ck"),
 	DT_CLK(NULL, "mlbp_clkin_ck", "mlbp_clkin_ck"),
@@ -322,10 +323,25 @@ int __init dra7xx_dt_clk_init(void)
 	if (rc)
 		pr_err("%s: failed to configure ABE DPLL!\n", __func__);
 
+	dpll_ck = clk_get_sys(NULL, "dpll_abe_m2x2_ck");
+	rc = clk_set_rate(dpll_ck, DRA7_DPLL_ABE_DEFFREQ * 2);
+	if (rc)
+		pr_err("%s: failed to configure ABE DPLL m2x2!\n", __func__);
+
 	dpll_ck = clk_get_sys(NULL, "dpll_gmac_ck");
 	rc = clk_set_rate(dpll_ck, DRA7_DPLL_GMAC_DEFFREQ);
 	if (rc)
 		pr_err("%s: failed to configure GMAC DPLL!\n", __func__);
 
+	dpll_ck = clk_get_sys(NULL, "dpll_usb_ck");
+	rc = clk_set_rate(dpll_ck, DRA7_DPLL_USB_DEFFREQ);
+	if (rc)
+		pr_err("%s: failed to configure USB DPLL!\n", __func__);
+
+	dpll_ck = clk_get_sys(NULL, "dpll_usb_m2_ck");
+	rc = clk_set_rate(dpll_ck, DRA7_DPLL_USB_DEFFREQ/2);
+	if (rc)
+		pr_err("%s: failed to set USB_DPLL M2 OUT\n", __func__);
+
 	return rc;
 }
diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c
new file mode 100644
index 00000000000..4a65b410e4d
--- /dev/null
+++ b/drivers/clk/ti/clk-dra7-atl.c
@@ -0,0 +1,312 @@
+/*
+ * DRA7 ATL (Audio Tracking Logic) clock driver
+ *
+ * Copyright (C) 2013 Texas Instruments, Inc.
+ *
+ * Peter Ujfalusi <peter.ujfalusi@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/clk-provider.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#define DRA7_ATL_INSTANCES	4
+
+#define DRA7_ATL_PPMR_REG(id)		(0x200 + (id * 0x80))
+#define DRA7_ATL_BBSR_REG(id)		(0x204 + (id * 0x80))
+#define DRA7_ATL_ATLCR_REG(id)		(0x208 + (id * 0x80))
+#define DRA7_ATL_SWEN_REG(id)		(0x210 + (id * 0x80))
+#define DRA7_ATL_BWSMUX_REG(id)		(0x214 + (id * 0x80))
+#define DRA7_ATL_AWSMUX_REG(id)		(0x218 + (id * 0x80))
+#define DRA7_ATL_PCLKMUX_REG(id)	(0x21c + (id * 0x80))
+
+#define DRA7_ATL_SWEN			BIT(0)
+#define DRA7_ATL_DIVIDER_MASK		(0x1f)
+#define DRA7_ATL_PCLKMUX		BIT(0)
+struct dra7_atl_clock_info;
+
+struct dra7_atl_desc {
+	struct clk *clk;
+	struct clk_hw hw;
+	struct dra7_atl_clock_info *cinfo;
+	int id;
+
+	bool probed;		/* the driver for the IP has been loaded */
+	bool valid;		/* configured */
+	bool enabled;
+	u32 bws;		/* Baseband Word Select Mux */
+	u32 aws;		/* Audio Word Select Mux */
+	u32 divider;		/* Cached divider value */
+};
+
+struct dra7_atl_clock_info {
+	struct device *dev;
+	void __iomem *iobase;
+
+	struct dra7_atl_desc *cdesc;
+};
+
+#define to_atl_desc(_hw)	container_of(_hw, struct dra7_atl_desc, hw)
+
+static inline void atl_write(struct dra7_atl_clock_info *cinfo, u32 reg,
+			     u32 val)
+{
+	__raw_writel(val, cinfo->iobase + reg);
+}
+
+static inline int atl_read(struct dra7_atl_clock_info *cinfo, u32 reg)
+{
+	return __raw_readl(cinfo->iobase + reg);
+}
+
+static int atl_clk_enable(struct clk_hw *hw)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+
+	if (!cdesc->probed)
+		goto out;
+
+	if (unlikely(!cdesc->valid))
+		dev_warn(cdesc->cinfo->dev, "atl%d has not been configured\n",
+			 cdesc->id);
+	pm_runtime_get_sync(cdesc->cinfo->dev);
+
+	atl_write(cdesc->cinfo, DRA7_ATL_ATLCR_REG(cdesc->id),
+		  cdesc->divider - 1);
+	atl_write(cdesc->cinfo, DRA7_ATL_SWEN_REG(cdesc->id), DRA7_ATL_SWEN);
+
+out:
+	cdesc->enabled = true;
+
+	return 0;
+}
+
+static void atl_clk_disable(struct clk_hw *hw)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+
+	if (!cdesc->probed)
+		goto out;
+
+	atl_write(cdesc->cinfo, DRA7_ATL_SWEN_REG(cdesc->id), 0);
+	pm_runtime_put_sync(cdesc->cinfo->dev);
+
+out:
+	cdesc->enabled = false;
+}
+
+static int atl_clk_is_enabled(struct clk_hw *hw)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+
+	return cdesc->enabled;
+}
+
+static unsigned long atl_clk_recalc_rate(struct clk_hw *hw,
+					 unsigned long parent_rate)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+
+	return parent_rate / cdesc->divider;
+}
+
+static long atl_clk_round_rate(struct clk_hw *hw, unsigned long rate,
+			       unsigned long *parent_rate)
+{
+	unsigned divider;
+
+	divider = (*parent_rate + rate / 2) / rate;
+	if (divider > DRA7_ATL_DIVIDER_MASK + 1)
+		divider = DRA7_ATL_DIVIDER_MASK + 1;
+
+	return *parent_rate / divider;
+}
+
+static int atl_clk_set_rate(struct clk_hw *hw, unsigned long rate,
+			    unsigned long parent_rate)
+{
+	struct dra7_atl_desc *cdesc = to_atl_desc(hw);
+	u32 divider;
+
+	divider = ((parent_rate + rate / 2) / rate) - 1;
+	if (divider > DRA7_ATL_DIVIDER_MASK)
+		divider = DRA7_ATL_DIVIDER_MASK;
+
+	cdesc->divider = divider + 1;
+
+	return 0;
+}
+
+const struct clk_ops atl_clk_ops = {
+	.enable		= atl_clk_enable,
+	.disable	= atl_clk_disable,
+	.is_enabled	= atl_clk_is_enabled,
+	.recalc_rate	= atl_clk_recalc_rate,
+	.round_rate	= atl_clk_round_rate,
+	.set_rate	= atl_clk_set_rate,
+};
+
+static void __init of_dra7_atl_clock_setup(struct device_node *node)
+{
+	struct dra7_atl_desc *clk_hw = NULL;
+	struct clk_init_data init = { 0 };
+	const char **parent_names = NULL;
+	struct clk *clk;
+
+	clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
+	if (!clk_hw) {
+		pr_err("%s: could not allocate dra7_atl_desc\n", __func__);
+		return;
+	}
+
+	clk_hw->hw.init = &init;
+	clk_hw->divider = 1;
+	init.name = node->name;
+	init.ops = &atl_clk_ops;
+	init.flags = CLK_IGNORE_UNUSED;
+	init.num_parents = of_clk_get_parent_count(node);
+
+	if (init.num_parents != 1) {
+		pr_err("%s: atl clock %s must have 1 parent\n", __func__,
+		       node->name);
+		goto cleanup;
+	}
+
+	parent_names = kzalloc(sizeof(char *), GFP_KERNEL);
+
+	if (!parent_names)
+		goto cleanup;
+
+	parent_names[0] = of_clk_get_parent_name(node, 0);
+
+	init.parent_names = parent_names;
+
+	clk = clk_register(NULL, &clk_hw->hw);
+
+	if (!IS_ERR(clk)) {
+		of_clk_add_provider(node, of_clk_src_simple_get, clk);
+		return;
+	}
+cleanup:
+	kfree(parent_names);
+	kfree(clk_hw);
+}
+CLK_OF_DECLARE(dra7_atl_clock, "ti,dra7-atl-clock", of_dra7_atl_clock_setup);
+
+static int of_dra7_atl_clk_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct dra7_atl_clock_info *cinfo;
+	int i;
+	int ret = 0;
+
+	if (!node)
+		return -ENODEV;
+
+	cinfo = devm_kzalloc(&pdev->dev, sizeof(*cinfo), GFP_KERNEL);
+	if (!cinfo)
+		return -ENOMEM;
+
+	cinfo->iobase = of_iomap(node, 0);
+	cinfo->dev = &pdev->dev;
+	pm_runtime_enable(cinfo->dev);
+
+	pm_runtime_get_sync(cinfo->dev);
+	atl_write(cinfo, DRA7_ATL_PCLKMUX_REG(0), DRA7_ATL_PCLKMUX);
+
+	for (i = 0; i < DRA7_ATL_INSTANCES; i++) {
+		struct device_node *cfg_node;
+		char prop[5];
+		struct dra7_atl_desc *cdesc;
+		struct of_phandle_args clkspec;
+		struct clk *clk;
+		int rc;
+
+		rc = of_parse_phandle_with_args(node, "ti,provided-clocks",
+						NULL, i, &clkspec);
+
+		if (rc) {
+			pr_err("%s: failed to lookup atl clock %d\n", __func__,
+			       i);
+			return -EINVAL;
+		}
+
+		clk = of_clk_get_from_provider(&clkspec);
+
+		cdesc = to_atl_desc(__clk_get_hw(clk));
+		cdesc->cinfo = cinfo;
+		cdesc->id = i;
+
+		/* Get configuration for the ATL instances */
+		snprintf(prop, sizeof(prop), "atl%u", i);
+		cfg_node = of_find_node_by_name(node, prop);
+		if (cfg_node) {
+			ret = of_property_read_u32(cfg_node, "bws",
+						   &cdesc->bws);
+			ret |= of_property_read_u32(cfg_node, "aws",
+						    &cdesc->aws);
+			if (!ret) {
+				cdesc->valid = true;
+				atl_write(cinfo, DRA7_ATL_BWSMUX_REG(i),
+					  cdesc->bws);
+				atl_write(cinfo, DRA7_ATL_AWSMUX_REG(i),
+					  cdesc->aws);
+			}
+		}
+
+		cdesc->probed = true;
+		/*
+		 * Enable the clock if it has been asked prior to loading the
+		 * hw driver
+		 */
+		if (cdesc->enabled)
+			atl_clk_enable(__clk_get_hw(clk));
+	}
+	pm_runtime_put_sync(cinfo->dev);
+
+	return ret;
+}
+
+static int of_dra7_atl_clk_remove(struct platform_device *pdev)
+{
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static struct of_device_id of_dra7_atl_clk_match_tbl[] = {
+	{ .compatible = "ti,dra7-atl", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_dra7_atl_clk_match_tbl);
+
+static struct platform_driver dra7_atl_clk_driver = {
+	.driver = {
+		.name = "dra7-atl",
+		.owner = THIS_MODULE,
+		.of_match_table = of_dra7_atl_clk_match_tbl,
+	},
+	.probe = of_dra7_atl_clk_probe,
+	.remove = of_dra7_atl_clk_remove,
+};
+
+module_platform_driver(dra7_atl_clk_driver);
+
+MODULE_DESCRIPTION("Clock driver for DRA7 Audio Tracking Logic");
+MODULE_ALIAS("platform:dra7-atl-clock");
+MODULE_AUTHOR("Peter Ujfalusi <peter.ujfalusi@ti.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/ti/dpll.c b/drivers/clk/ti/dpll.c
index 7e498a44f97..79791e1bf28 100644
--- a/drivers/clk/ti/dpll.c
+++ b/drivers/clk/ti/dpll.c
@@ -25,8 +25,6 @@
 #undef pr_fmt
 #define pr_fmt(fmt) "%s: " fmt, __func__
 
-#define DPLL_HAS_AUTOIDLE	0x1
-
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \
 	defined(CONFIG_SOC_DRA7XX)
 static const struct clk_ops dpll_m4xen_ck_ops = {
@@ -37,21 +35,18 @@ static const struct clk_ops dpll_m4xen_ck_ops = {
 	.set_rate	= &omap3_noncore_dpll_set_rate,
 	.get_parent	= &omap2_init_dpll_parent,
 };
+#else
+static const struct clk_ops dpll_m4xen_ck_ops = {};
 #endif
 
+#if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_ARCH_OMAP4) || \
+	defined(CONFIG_SOC_OMAP5) || defined(CONFIG_SOC_DRA7XX) || \
+	defined(CONFIG_SOC_AM33XX) || defined(CONFIG_SOC_AM43XX)
 static const struct clk_ops dpll_core_ck_ops = {
 	.recalc_rate	= &omap3_dpll_recalc,
 	.get_parent	= &omap2_init_dpll_parent,
 };
 
-#ifdef CONFIG_ARCH_OMAP3
-static const struct clk_ops omap3_dpll_core_ck_ops = {
-	.get_parent	= &omap2_init_dpll_parent,
-	.recalc_rate	= &omap3_dpll_recalc,
-	.round_rate	= &omap2_dpll_round_rate,
-};
-#endif
-
 static const struct clk_ops dpll_ck_ops = {
 	.enable		= &omap3_noncore_dpll_enable,
 	.disable	= &omap3_noncore_dpll_disable,
@@ -67,6 +62,33 @@ static const struct clk_ops dpll_no_gate_ck_ops = {
 	.round_rate	= &omap2_dpll_round_rate,
 	.set_rate	= &omap3_noncore_dpll_set_rate,
 };
+#else
+static const struct clk_ops dpll_core_ck_ops = {};
+static const struct clk_ops dpll_ck_ops = {};
+static const struct clk_ops dpll_no_gate_ck_ops = {};
+const struct clk_hw_omap_ops clkhwops_omap3_dpll = {};
+#endif
+
+#ifdef CONFIG_ARCH_OMAP2
+static const struct clk_ops omap2_dpll_core_ck_ops = {
+	.get_parent	= &omap2_init_dpll_parent,
+	.recalc_rate	= &omap2_dpllcore_recalc,
+	.round_rate	= &omap2_dpll_round_rate,
+	.set_rate	= &omap2_reprogram_dpllcore,
+};
+#else
+static const struct clk_ops omap2_dpll_core_ck_ops = {};
+#endif
+
+#ifdef CONFIG_ARCH_OMAP3
+static const struct clk_ops omap3_dpll_core_ck_ops = {
+	.get_parent	= &omap2_init_dpll_parent,
+	.recalc_rate	= &omap3_dpll_recalc,
+	.round_rate	= &omap2_dpll_round_rate,
+};
+#else
+static const struct clk_ops omap3_dpll_core_ck_ops = {};
+#endif
 
 #ifdef CONFIG_ARCH_OMAP3
 static const struct clk_ops omap3_dpll_ck_ops = {
@@ -139,7 +161,8 @@ cleanup:
 }
 
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \
-	defined(CONFIG_SOC_DRA7XX) || defined(CONFIG_SOC_AM33XX)
+	defined(CONFIG_SOC_DRA7XX) || defined(CONFIG_SOC_AM33XX) || \
+	defined(CONFIG_SOC_AM43XX)
 /**
  * ti_clk_register_dpll_x2 - Registers a DPLLx2 clock
  * @node: device node for this clock
@@ -193,14 +216,12 @@ static void ti_clk_register_dpll_x2(struct device_node *node,
  * @node: device node containing the DPLL info
  * @ops: ops for the DPLL
  * @ddt: DPLL data template to use
- * @init_flags: flags for controlling init types
  *
  * Initializes a DPLL clock from device tree data.
  */
 static void __init of_ti_dpll_setup(struct device_node *node,
 				    const struct clk_ops *ops,
-				    const struct dpll_data *ddt,
-				    u8 init_flags)
+				    const struct dpll_data *ddt)
 {
 	struct clk_hw_omap *clk_hw = NULL;
 	struct clk_init_data *init = NULL;
@@ -241,13 +262,30 @@ static void __init of_ti_dpll_setup(struct device_node *node,
 	init->parent_names = parent_names;
 
 	dd->control_reg = ti_clk_get_reg_addr(node, 0);
-	dd->idlest_reg = ti_clk_get_reg_addr(node, 1);
-	dd->mult_div1_reg = ti_clk_get_reg_addr(node, 2);
 
-	if (!dd->control_reg || !dd->idlest_reg || !dd->mult_div1_reg)
+	/*
+	 * Special case for OMAP2 DPLL, register order is different due to
+	 * missing idlest_reg, also clkhwops is different. Detected from
+	 * missing idlest_mask.
+	 */
+	if (!dd->idlest_mask) {
+		dd->mult_div1_reg = ti_clk_get_reg_addr(node, 1);
+#ifdef CONFIG_ARCH_OMAP2
+		clk_hw->ops = &clkhwops_omap2xxx_dpll;
+		omap2xxx_clkt_dpllcore_init(&clk_hw->hw);
+#endif
+	} else {
+		dd->idlest_reg = ti_clk_get_reg_addr(node, 1);
+		if (!dd->idlest_reg)
+			goto cleanup;
+
+		dd->mult_div1_reg = ti_clk_get_reg_addr(node, 2);
+	}
+
+	if (!dd->control_reg || !dd->mult_div1_reg)
 		goto cleanup;
 
-	if (init_flags & DPLL_HAS_AUTOIDLE) {
+	if (dd->autoidle_mask) {
 		dd->autoidle_reg = ti_clk_get_reg_addr(node, 3);
 		if (!dd->autoidle_reg)
 			goto cleanup;
@@ -285,7 +323,7 @@ CLK_OF_DECLARE(ti_omap4_dpll_x2_clock, "ti,omap4-dpll-x2-clock",
 	       of_ti_omap4_dpll_x2_setup);
 #endif
 
-#ifdef CONFIG_SOC_AM33XX
+#if defined(CONFIG_SOC_AM33XX) || defined(CONFIG_SOC_AM43XX)
 static void __init of_ti_am3_dpll_x2_setup(struct device_node *node)
 {
 	ti_clk_register_dpll_x2(node, &dpll_x2_ck_ops, NULL);
@@ -310,7 +348,7 @@ static void __init of_ti_omap3_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &omap3_dpll_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &omap3_dpll_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap3_dpll_clock, "ti,omap3-dpll-clock",
 	       of_ti_omap3_dpll_setup);
@@ -329,7 +367,7 @@ static void __init of_ti_omap3_core_dpll_setup(struct device_node *node)
 		.freqsel_mask = 0xf0,
 	};
 
-	of_ti_dpll_setup(node, &omap3_dpll_core_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &omap3_dpll_core_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap3_core_dpll_clock, "ti,omap3-dpll-core-clock",
 	       of_ti_omap3_core_dpll_setup);
@@ -349,7 +387,7 @@ static void __init of_ti_omap3_per_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_STOP) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap3_per_dpll_clock, "ti,omap3-dpll-per-clock",
 	       of_ti_omap3_per_dpll_setup);
@@ -371,7 +409,7 @@ static void __init of_ti_omap3_per_jtype_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_STOP) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &omap3_dpll_per_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap3_per_jtype_dpll_clock, "ti,omap3-dpll-per-j-type-clock",
 	       of_ti_omap3_per_jtype_dpll_setup);
@@ -391,11 +429,32 @@ static void __init of_ti_omap4_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &dpll_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap4_dpll_clock, "ti,omap4-dpll-clock",
 	       of_ti_omap4_dpll_setup);
 
+static void __init of_ti_omap5_mpu_dpll_setup(struct device_node *node)
+{
+	const struct dpll_data dd = {
+		.idlest_mask = 0x1,
+		.enable_mask = 0x7,
+		.autoidle_mask = 0x7,
+		.mult_mask = 0x7ff << 8,
+		.div1_mask = 0x7f,
+		.max_multiplier = 2047,
+		.max_divider = 128,
+		.dcc_mask = BIT(22),
+		.dcc_rate = 1400000000, /* DCC beyond 1.4GHz */
+		.min_divider = 1,
+		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
+	};
+
+	of_ti_dpll_setup(node, &dpll_ck_ops, &dd);
+}
+CLK_OF_DECLARE(of_ti_omap5_mpu_dpll_clock, "ti,omap5-mpu-dpll-clock",
+	       of_ti_omap5_mpu_dpll_setup);
+
 static void __init of_ti_omap4_core_dpll_setup(struct device_node *node)
 {
 	const struct dpll_data dd = {
@@ -410,7 +469,7 @@ static void __init of_ti_omap4_core_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap4_core_dpll_clock, "ti,omap4-dpll-core-clock",
 	       of_ti_omap4_core_dpll_setup);
@@ -433,7 +492,7 @@ static void __init of_ti_omap4_m4xen_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap4_m4xen_dpll_clock, "ti,omap4-dpll-m4xen-clock",
 	       of_ti_omap4_m4xen_dpll_setup);
@@ -454,7 +513,7 @@ static void __init of_ti_omap4_jtype_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd, DPLL_HAS_AUTOIDLE);
+	of_ti_dpll_setup(node, &dpll_m4xen_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_omap4_jtype_dpll_clock, "ti,omap4-dpll-j-type-clock",
 	       of_ti_omap4_jtype_dpll_setup);
@@ -465,7 +524,6 @@ static void __init of_ti_am3_no_gate_dpll_setup(struct device_node *node)
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 2047,
@@ -474,7 +532,7 @@ static void __init of_ti_am3_no_gate_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_no_gate_dpll_clock, "ti,am3-dpll-no-gate-clock",
 	       of_ti_am3_no_gate_dpll_setup);
@@ -484,7 +542,6 @@ static void __init of_ti_am3_jtype_dpll_setup(struct device_node *node)
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 4095,
@@ -494,7 +551,7 @@ static void __init of_ti_am3_jtype_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_jtype_dpll_clock, "ti,am3-dpll-j-type-clock",
 	       of_ti_am3_jtype_dpll_setup);
@@ -504,7 +561,6 @@ static void __init of_ti_am3_no_gate_jtype_dpll_setup(struct device_node *node)
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 2047,
@@ -514,7 +570,7 @@ static void __init of_ti_am3_no_gate_jtype_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_no_gate_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_no_gate_jtype_dpll_clock,
 	       "ti,am3-dpll-no-gate-j-type-clock",
@@ -525,7 +581,6 @@ static void __init of_ti_am3_dpll_setup(struct device_node *node)
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 2047,
@@ -534,7 +589,7 @@ static void __init of_ti_am3_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_dpll_clock, "ti,am3-dpll-clock", of_ti_am3_dpll_setup);
 
@@ -543,7 +598,6 @@ static void __init of_ti_am3_core_dpll_setup(struct device_node *node)
 	const struct dpll_data dd = {
 		.idlest_mask = 0x1,
 		.enable_mask = 0x7,
-		.autoidle_mask = 0x7,
 		.mult_mask = 0x7ff << 8,
 		.div1_mask = 0x7f,
 		.max_multiplier = 2047,
@@ -552,7 +606,22 @@ static void __init of_ti_am3_core_dpll_setup(struct device_node *node)
 		.modes = (1 << DPLL_LOW_POWER_BYPASS) | (1 << DPLL_LOCKED),
 	};
 
-	of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd, 0);
+	of_ti_dpll_setup(node, &dpll_core_ck_ops, &dd);
 }
 CLK_OF_DECLARE(ti_am3_core_dpll_clock, "ti,am3-dpll-core-clock",
 	       of_ti_am3_core_dpll_setup);
+
+static void __init of_ti_omap2_core_dpll_setup(struct device_node *node)
+{
+	const struct dpll_data dd = {
+		.enable_mask = 0x3,
+		.mult_mask = 0x3ff << 12,
+		.div1_mask = 0xf << 8,
+		.max_divider = 16,
+		.min_divider = 1,
+	};
+
+	of_ti_dpll_setup(node, &omap2_dpll_core_ck_ops, &dd);
+}
+CLK_OF_DECLARE(ti_omap2_core_dpll_clock, "ti,omap2-dpll-core-clock",
+	       of_ti_omap2_core_dpll_setup);
diff --git a/drivers/clk/ti/gate.c b/drivers/clk/ti/gate.c
index 58734817d50..b326d2797fe 100644
--- a/drivers/clk/ti/gate.c
+++ b/drivers/clk/ti/gate.c
@@ -185,7 +185,7 @@ of_ti_composite_no_wait_gate_clk_setup(struct device_node *node)
 CLK_OF_DECLARE(ti_composite_no_wait_gate_clk, "ti,composite-no-wait-gate-clock",
 	       of_ti_composite_no_wait_gate_clk_setup);
 
-#ifdef CONFIG_ARCH_OMAP3
+#if defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3)
 static void __init of_ti_composite_interface_clk_setup(struct device_node *node)
 {
 	_of_ti_composite_gate_clk_setup(node, &clkhwops_iclk_wait);
diff --git a/drivers/clk/ti/interface.c b/drivers/clk/ti/interface.c
index 320a2b168bb..9c3e8c4aaa4 100644
--- a/drivers/clk/ti/interface.c
+++ b/drivers/clk/ti/interface.c
@@ -94,6 +94,7 @@ static void __init of_ti_no_wait_interface_clk_setup(struct device_node *node)
 CLK_OF_DECLARE(ti_no_wait_interface_clk, "ti,omap3-no-wait-interface-clock",
 	       of_ti_no_wait_interface_clk_setup);
 
+#ifdef CONFIG_ARCH_OMAP3
 static void __init of_ti_hsotgusb_interface_clk_setup(struct device_node *node)
 {
 	_of_ti_interface_clk_setup(node,
@@ -123,3 +124,13 @@ static void __init of_ti_am35xx_interface_clk_setup(struct device_node *node)
 }
 CLK_OF_DECLARE(ti_am35xx_interface_clk, "ti,am35xx-interface-clock",
 	       of_ti_am35xx_interface_clk_setup);
+#endif
+
+#ifdef CONFIG_SOC_OMAP2430
+static void __init of_ti_omap2430_interface_clk_setup(struct device_node *node)
+{
+	_of_ti_interface_clk_setup(node, &clkhwops_omap2430_i2chs_wait);
+}
+CLK_OF_DECLARE(ti_omap2430_interface_clk, "ti,omap2430-interface-clock",
+	       of_ti_omap2430_interface_clk_setup);
+#endif
diff --git a/drivers/clk/ti/mux.c b/drivers/clk/ti/mux.c
index 0197a478720..e9d650e5128 100644
--- a/drivers/clk/ti/mux.c
+++ b/drivers/clk/ti/mux.c
@@ -160,7 +160,7 @@ static void of_mux_clk_setup(struct device_node *node)
 	u8 clk_mux_flags = 0;
 	u32 mask = 0;
 	u32 shift = 0;
-	u32 flags = 0;
+	u32 flags = CLK_SET_RATE_NO_REPARENT;
 
 	num_parents = of_clk_get_parent_count(node);
 	if (num_parents < 2) {
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index 8d6420013a0..ab51bf20a3e 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -153,19 +153,16 @@ static void exynos4_mct_write(unsigned int value, unsigned long offset)
 }
 
 /* Clocksource handling */
-static void exynos4_mct_frc_start(u32 hi, u32 lo)
+static void exynos4_mct_frc_start(void)
 {
 	u32 reg;
 
-	exynos4_mct_write(lo, EXYNOS4_MCT_G_CNT_L);
-	exynos4_mct_write(hi, EXYNOS4_MCT_G_CNT_U);
-
 	reg = __raw_readl(reg_base + EXYNOS4_MCT_G_TCON);
 	reg |= MCT_G_TCON_START;
 	exynos4_mct_write(reg, EXYNOS4_MCT_G_TCON);
 }
 
-static cycle_t exynos4_frc_read(struct clocksource *cs)
+static cycle_t notrace _exynos4_frc_read(void)
 {
 	unsigned int lo, hi;
 	u32 hi2 = __raw_readl(reg_base + EXYNOS4_MCT_G_CNT_U);
@@ -179,9 +176,14 @@ static cycle_t exynos4_frc_read(struct clocksource *cs)
 	return ((cycle_t)hi << 32) | lo;
 }
 
+static cycle_t exynos4_frc_read(struct clocksource *cs)
+{
+	return _exynos4_frc_read();
+}
+
 static void exynos4_frc_resume(struct clocksource *cs)
 {
-	exynos4_mct_frc_start(0, 0);
+	exynos4_mct_frc_start();
 }
 
 struct clocksource mct_frc = {
@@ -195,12 +197,23 @@ struct clocksource mct_frc = {
 
 static u64 notrace exynos4_read_sched_clock(void)
 {
-	return exynos4_frc_read(&mct_frc);
+	return _exynos4_frc_read();
+}
+
+static struct delay_timer exynos4_delay_timer;
+
+static cycles_t exynos4_read_current_timer(void)
+{
+	return _exynos4_frc_read();
 }
 
 static void __init exynos4_clocksource_init(void)
 {
-	exynos4_mct_frc_start(0, 0);
+	exynos4_mct_frc_start();
+
+	exynos4_delay_timer.read_current_timer = &exynos4_read_current_timer;
+	exynos4_delay_timer.freq = clk_rate;
+	register_current_timer_delay(&exynos4_delay_timer);
 
 	if (clocksource_register_hz(&mct_frc, clk_rate))
 		panic("%s: can't register clocksource\n", mct_frc.name);
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 1fbe11f2a14..ffe350f86bc 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -185,7 +185,9 @@ config CPU_FREQ_GOV_CONSERVATIVE
 
 config GENERIC_CPUFREQ_CPU0
 	tristate "Generic CPU0 cpufreq driver"
-	depends on HAVE_CLK && REGULATOR && OF && THERMAL && CPU_THERMAL
+	depends on HAVE_CLK && OF
+	# if CPU_THERMAL is on and THERMAL=m, CPU0 cannot be =y:
+	depends on !CPU_THERMAL || THERMAL
 	select PM_OPP
 	help
 	  This adds a generic cpufreq driver for CPU0 frequency management.
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 36d20d0fce2..7364a538e05 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -5,8 +5,7 @@
 # big LITTLE core layer and glue drivers
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
-	depends on (BIG_LITTLE && ARM_CPU_TOPOLOGY) || (ARM64 && SMP)
-	depends on HAVE_CLK
+	depends on ARM && BIG_LITTLE && ARM_CPU_TOPOLOGY && HAVE_CLK
 	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
@@ -105,6 +104,7 @@ config ARM_IMX6Q_CPUFREQ
 	tristate "Freescale i.MX6 cpufreq support"
 	depends on ARCH_MXC
 	depends on REGULATOR_ANATOP
+	select PM_OPP
 	help
 	  This adds cpufreq driver support for Freescale i.MX6 series SoCs.
 
@@ -119,7 +119,7 @@ config ARM_INTEGRATOR
 	  If in doubt, say Y.
 
 config ARM_KIRKWOOD_CPUFREQ
-	def_bool MACH_KIRKWOOD
+	def_bool ARCH_KIRKWOOD || MACH_KIRKWOOD
 	help
 	  This adds the CPUFreq driver for Marvell Kirkwood
 	  SoCs.
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 738c8b7b17d..db6d9a2fea4 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -49,7 +49,7 @@ obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ)	+= arm_big_little.o
 # LITTLE drivers, so that it is probed last.
 obj-$(CONFIG_ARM_DT_BL_CPUFREQ)		+= arm_big_little_dt.o
 
-obj-$(CONFIG_ARCH_DAVINCI_DA850)	+= davinci-cpufreq.o
+obj-$(CONFIG_ARCH_DAVINCI)		+= davinci-cpufreq.o
 obj-$(CONFIG_UX500_SOC_DB8500)		+= dbx500-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS_CPUFREQ)	+= exynos-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS4210_CPUFREQ)	+= exynos4210-cpufreq.o
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 09b9129c7bd..86beda9f950 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -104,7 +104,7 @@ static int cpu0_cpufreq_init(struct cpufreq_policy *policy)
 }
 
 static struct cpufreq_driver cpu0_cpufreq_driver = {
-	.flags = CPUFREQ_STICKY,
+	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = cpu0_set_target,
 	.get = cpufreq_generic_get,
@@ -152,11 +152,8 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 		goto out_put_reg;
 	}
 
-	ret = of_init_opp_table(cpu_dev);
-	if (ret) {
-		pr_err("failed to init OPP table: %d\n", ret);
-		goto out_put_clk;
-	}
+	/* OPPs might be populated at runtime, don't check for error here */
+	of_init_opp_table(cpu_dev);
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index ae11dd51f81..6f024852c6f 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1153,10 +1153,12 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	 * the creation of a brand new one. So we need to perform this update
 	 * by invoking update_policy_cpu().
 	 */
-	if (recover_policy && cpu != policy->cpu)
+	if (recover_policy && cpu != policy->cpu) {
 		update_policy_cpu(policy, cpu);
-	else
+		WARN_ON(kobject_move(&policy->kobj, &dev->kobj));
+	} else {
 		policy->cpu = cpu;
+	}
 
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
 
@@ -1816,20 +1818,55 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
  *                              GOVERNORS                            *
  *********************************************************************/
 
+/* Must set freqs->new to intermediate frequency */
+static int __target_intermediate(struct cpufreq_policy *policy,
+				 struct cpufreq_freqs *freqs, int index)
+{
+	int ret;
+
+	freqs->new = cpufreq_driver->get_intermediate(policy, index);
+
+	/* We don't need to switch to intermediate freq */
+	if (!freqs->new)
+		return 0;
+
+	pr_debug("%s: cpu: %d, switching to intermediate freq: oldfreq: %u, intermediate freq: %u\n",
+		 __func__, policy->cpu, freqs->old, freqs->new);
+
+	cpufreq_freq_transition_begin(policy, freqs);
+	ret = cpufreq_driver->target_intermediate(policy, index);
+	cpufreq_freq_transition_end(policy, freqs, ret);
+
+	if (ret)
+		pr_err("%s: Failed to change to intermediate frequency: %d\n",
+		       __func__, ret);
+
+	return ret;
+}
+
 static int __target_index(struct cpufreq_policy *policy,
 			  struct cpufreq_frequency_table *freq_table, int index)
 {
-	struct cpufreq_freqs freqs;
+	struct cpufreq_freqs freqs = {.old = policy->cur, .flags = 0};
+	unsigned int intermediate_freq = 0;
 	int retval = -EINVAL;
 	bool notify;
 
 	notify = !(cpufreq_driver->flags & CPUFREQ_ASYNC_NOTIFICATION);
-
 	if (notify) {
-		freqs.old = policy->cur;
-		freqs.new = freq_table[index].frequency;
-		freqs.flags = 0;
+		/* Handle switching to intermediate frequency */
+		if (cpufreq_driver->get_intermediate) {
+			retval = __target_intermediate(policy, &freqs, index);
+			if (retval)
+				return retval;
+
+			intermediate_freq = freqs.new;
+			/* Set old freq to intermediate */
+			if (intermediate_freq)
+				freqs.old = freqs.new;
+		}
 
+		freqs.new = freq_table[index].frequency;
 		pr_debug("%s: cpu: %d, oldfreq: %u, new freq: %u\n",
 			 __func__, policy->cpu, freqs.old, freqs.new);
 
@@ -1841,9 +1878,23 @@ static int __target_index(struct cpufreq_policy *policy,
 		pr_err("%s: Failed to change cpu frequency: %d\n", __func__,
 		       retval);
 
-	if (notify)
+	if (notify) {
 		cpufreq_freq_transition_end(policy, &freqs, retval);
 
+		/*
+		 * Failed after setting to intermediate freq? Driver should have
+		 * reverted back to initial frequency and so should we. Check
+		 * here for intermediate_freq instead of get_intermediate, in
+		 * case we have't switched to intermediate freq at all.
+		 */
+		if (unlikely(retval && intermediate_freq)) {
+			freqs.old = intermediate_freq;
+			freqs.new = policy->restore_freq;
+			cpufreq_freq_transition_begin(policy, &freqs);
+			cpufreq_freq_transition_end(policy, &freqs, 0);
+		}
+	}
+
 	return retval;
 }
 
@@ -1875,6 +1926,9 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	if (target_freq == policy->cur)
 		return 0;
 
+	/* Save last value to restore later on errors */
+	policy->restore_freq = policy->cur;
+
 	if (cpufreq_driver->target)
 		retval = cpufreq_driver->target(policy, target_freq, relation);
 	else if (cpufreq_driver->target_index) {
@@ -2190,10 +2244,8 @@ int cpufreq_update_policy(unsigned int cpu)
 	struct cpufreq_policy new_policy;
 	int ret;
 
-	if (!policy) {
-		ret = -ENODEV;
-		goto no_policy;
-	}
+	if (!policy)
+		return -ENODEV;
 
 	down_write(&policy->rwsem);
 
@@ -2212,7 +2264,7 @@ int cpufreq_update_policy(unsigned int cpu)
 		new_policy.cur = cpufreq_driver->get(cpu);
 		if (WARN_ON(!new_policy.cur)) {
 			ret = -EIO;
-			goto no_policy;
+			goto unlock;
 		}
 
 		if (!policy->cur) {
@@ -2227,10 +2279,10 @@ int cpufreq_update_policy(unsigned int cpu)
 
 	ret = cpufreq_set_policy(policy, &new_policy);
 
+unlock:
 	up_write(&policy->rwsem);
 
 	cpufreq_cpu_put(policy);
-no_policy:
 	return ret;
 }
 EXPORT_SYMBOL(cpufreq_update_policy);
@@ -2361,7 +2413,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	    !(driver_data->setpolicy || driver_data->target_index ||
 		    driver_data->target) ||
 	     (driver_data->setpolicy && (driver_data->target_index ||
-		    driver_data->target)))
+		    driver_data->target)) ||
+	     (!!driver_data->get_intermediate != !!driver_data->target_intermediate))
 		return -EINVAL;
 
 	pr_debug("trying to register driver %s\n", driver_data->name);
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index e1c6433b16e..1b44496b2d2 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -36,14 +36,29 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 	struct cpufreq_policy *policy;
+	unsigned int sampling_rate;
 	unsigned int max_load = 0;
 	unsigned int ignore_nice;
 	unsigned int j;
 
-	if (dbs_data->cdata->governor == GOV_ONDEMAND)
+	if (dbs_data->cdata->governor == GOV_ONDEMAND) {
+		struct od_cpu_dbs_info_s *od_dbs_info =
+				dbs_data->cdata->get_cpu_dbs_info_s(cpu);
+
+		/*
+		 * Sometimes, the ondemand governor uses an additional
+		 * multiplier to give long delays. So apply this multiplier to
+		 * the 'sampling_rate', so as to keep the wake-up-from-idle
+		 * detection logic a bit conservative.
+		 */
+		sampling_rate = od_tuners->sampling_rate;
+		sampling_rate *= od_dbs_info->rate_mult;
+
 		ignore_nice = od_tuners->ignore_nice_load;
-	else
+	} else {
+		sampling_rate = cs_tuners->sampling_rate;
 		ignore_nice = cs_tuners->ignore_nice_load;
+	}
 
 	policy = cdbs->cur_policy;
 
@@ -96,7 +111,46 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 		if (unlikely(!wall_time || wall_time < idle_time))
 			continue;
 
-		load = 100 * (wall_time - idle_time) / wall_time;
+		/*
+		 * If the CPU had gone completely idle, and a task just woke up
+		 * on this CPU now, it would be unfair to calculate 'load' the
+		 * usual way for this elapsed time-window, because it will show
+		 * near-zero load, irrespective of how CPU intensive that task
+		 * actually is. This is undesirable for latency-sensitive bursty
+		 * workloads.
+		 *
+		 * To avoid this, we reuse the 'load' from the previous
+		 * time-window and give this task a chance to start with a
+		 * reasonably high CPU frequency. (However, we shouldn't over-do
+		 * this copy, lest we get stuck at a high load (high frequency)
+		 * for too long, even when the current system load has actually
+		 * dropped down. So we perform the copy only once, upon the
+		 * first wake-up from idle.)
+		 *
+		 * Detecting this situation is easy: the governor's deferrable
+		 * timer would not have fired during CPU-idle periods. Hence
+		 * an unusually large 'wall_time' (as compared to the sampling
+		 * rate) indicates this scenario.
+		 *
+		 * prev_load can be zero in two cases and we must recalculate it
+		 * for both cases:
+		 * - during long idle intervals
+		 * - explicitly set to zero
+		 */
+		if (unlikely(wall_time > (2 * sampling_rate) &&
+			     j_cdbs->prev_load)) {
+			load = j_cdbs->prev_load;
+
+			/*
+			 * Perform a destructive copy, to ensure that we copy
+			 * the previous load only once, upon the first wake-up
+			 * from idle.
+			 */
+			j_cdbs->prev_load = 0;
+		} else {
+			load = 100 * (wall_time - idle_time) / wall_time;
+			j_cdbs->prev_load = load;
+		}
 
 		if (load > max_load)
 			max_load = load;
@@ -318,11 +372,18 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		for_each_cpu(j, policy->cpus) {
 			struct cpu_dbs_common_info *j_cdbs =
 				dbs_data->cdata->get_cpu_cdbs(j);
+			unsigned int prev_load;
 
 			j_cdbs->cpu = j;
 			j_cdbs->cur_policy = policy;
 			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j,
 					       &j_cdbs->prev_cpu_wall, io_busy);
+
+			prev_load = (unsigned int)
+				(j_cdbs->prev_cpu_wall - j_cdbs->prev_cpu_idle);
+			j_cdbs->prev_load = 100 * prev_load /
+					(unsigned int) j_cdbs->prev_cpu_wall;
+
 			if (ignore_nice)
 				j_cdbs->prev_cpu_nice =
 					kcpustat_cpu(j).cpustat[CPUTIME_NICE];
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index bfb9ae14142..cc401d147e7 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -134,6 +134,13 @@ struct cpu_dbs_common_info {
 	u64 prev_cpu_idle;
 	u64 prev_cpu_wall;
 	u64 prev_cpu_nice;
+	/*
+	 * Used to keep track of load in the previous interval. However, when
+	 * explicitly set to zero, it is used as a flag to ensure that we copy
+	 * the previous load to the current interval only once, upon the first
+	 * wake-up from idle.
+	 */
+	unsigned int prev_load;
 	struct cpufreq_policy *cur_policy;
 	struct delayed_work work;
 	/*
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index aebd4572eb6..86631cb6f7d 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -128,6 +128,7 @@ static struct pstate_funcs pstate_funcs;
 
 struct perf_limits {
 	int no_turbo;
+	int turbo_disabled;
 	int max_perf_pct;
 	int min_perf_pct;
 	int32_t max_perf;
@@ -196,10 +197,7 @@ static signed int pid_calc(struct _pid *pid, int32_t busy)
 	pid->last_err = fp_error;
 
 	result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;
-	if (result >= 0)
-		result = result + (1 << (FRAC_BITS-1));
-	else
-		result = result - (1 << (FRAC_BITS-1));
+	result = result + (1 << (FRAC_BITS-1));
 	return (signed int)fp_toint(result);
 }
 
@@ -290,7 +288,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 	limits.no_turbo = clamp_t(int, input, 0 , 1);
-
+	if (limits.turbo_disabled) {
+		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
+		limits.no_turbo = limits.turbo_disabled;
+	}
 	return count;
 }
 
@@ -360,21 +361,21 @@ static int byt_get_min_pstate(void)
 {
 	u64 value;
 	rdmsrl(BYT_RATIOS, value);
-	return (value >> 8) & 0x3F;
+	return (value >> 8) & 0x7F;
 }
 
 static int byt_get_max_pstate(void)
 {
 	u64 value;
 	rdmsrl(BYT_RATIOS, value);
-	return (value >> 16) & 0x3F;
+	return (value >> 16) & 0x7F;
 }
 
 static int byt_get_turbo_pstate(void)
 {
 	u64 value;
 	rdmsrl(BYT_TURBO_RATIOS, value);
-	return value & 0x3F;
+	return value & 0x7F;
 }
 
 static void byt_set_pstate(struct cpudata *cpudata, int pstate)
@@ -384,7 +385,7 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 	u32 vid;
 
 	val = pstate << 8;
-	if (limits.no_turbo)
+	if (limits.no_turbo && !limits.turbo_disabled)
 		val |= (u64)1 << 32;
 
 	vid_fp = cpudata->vid.min + mul_fp(
@@ -408,8 +409,8 @@ static void byt_get_vid(struct cpudata *cpudata)
 
 
 	rdmsrl(BYT_VIDS, value);
-	cpudata->vid.min = int_tofp((value >> 8) & 0x3f);
-	cpudata->vid.max = int_tofp((value >> 16) & 0x3f);
+	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
+	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
 	cpudata->vid.ratio = div_fp(
 		cpudata->vid.max - cpudata->vid.min,
 		int_tofp(cpudata->pstate.max_pstate -
@@ -451,7 +452,7 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate)
 	u64 val;
 
 	val = pstate << 8;
-	if (limits.no_turbo)
+	if (limits.no_turbo && !limits.turbo_disabled)
 		val |= (u64)1 << 32;
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
@@ -691,23 +692,16 @@ MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
 
 static int intel_pstate_init_cpu(unsigned int cpunum)
 {
-
-	const struct x86_cpu_id *id;
 	struct cpudata *cpu;
 
-	id = x86_match_cpu(intel_pstate_cpu_ids);
-	if (!id)
-		return -ENODEV;
-
 	all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), GFP_KERNEL);
 	if (!all_cpu_data[cpunum])
 		return -ENOMEM;
 
 	cpu = all_cpu_data[cpunum];
 
-	intel_pstate_get_cpu_pstates(cpu);
-
 	cpu->cpu = cpunum;
+	intel_pstate_get_cpu_pstates(cpu);
 
 	init_timer_deferrable(&cpu->timer);
 	cpu->timer.function = intel_pstate_timer_func;
@@ -750,7 +744,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 		limits.min_perf = int_tofp(1);
 		limits.max_perf_pct = 100;
 		limits.max_perf = int_tofp(1);
-		limits.no_turbo = 0;
+		limits.no_turbo = limits.turbo_disabled;
 		return 0;
 	}
 	limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
@@ -793,6 +787,7 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu;
 	int rc;
+	u64 misc_en;
 
 	rc = intel_pstate_init_cpu(policy->cpu);
 	if (rc)
@@ -800,8 +795,13 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpu = all_cpu_data[policy->cpu];
 
-	if (!limits.no_turbo &&
-		limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
+	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
+	if (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
+		cpu->pstate.max_pstate == cpu->pstate.turbo_pstate) {
+		limits.turbo_disabled = 1;
+		limits.no_turbo = 1;
+	}
+	if (limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
 	else
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c
index 0af618abeba..3607070797a 100644
--- a/drivers/cpufreq/ppc-corenet-cpufreq.c
+++ b/drivers/cpufreq/ppc-corenet-cpufreq.c
@@ -138,7 +138,7 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	struct cpufreq_frequency_table *table;
 	struct cpu_data *data;
 	unsigned int cpu = policy->cpu;
-	u64 transition_latency_hz;
+	u64 u64temp;
 
 	np = of_get_cpu_node(cpu, NULL);
 	if (!np)
@@ -206,9 +206,10 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	for_each_cpu(i, per_cpu(cpu_mask, cpu))
 		per_cpu(cpu_data, i) = data;
 
-	transition_latency_hz = 12ULL * NSEC_PER_SEC;
-	policy->cpuinfo.transition_latency =
-		do_div(transition_latency_hz, fsl_get_sys_freq());
+	/* Minimum transition latency is 12 platform clocks */
+	u64temp = 12ULL * NSEC_PER_SEC;
+	do_div(u64temp, fsl_get_sys_freq());
+	policy->cpuinfo.transition_latency = u64temp + 1;
 
 	of_node_put(np);
 
diff --git a/drivers/cpufreq/sa1110-cpufreq.c b/drivers/cpufreq/sa1110-cpufreq.c
index 546376719d8..b5befc21117 100644
--- a/drivers/cpufreq/sa1110-cpufreq.c
+++ b/drivers/cpufreq/sa1110-cpufreq.c
@@ -349,7 +349,7 @@ static int __init sa1110_clk_init(void)
 			name = "K4S641632D";
 		if (machine_is_h3100())
 			name = "KM416S4030CT";
-		if (machine_is_jornada720())
+		if (machine_is_jornada720() || machine_is_h3600())
 			name = "K4S281632B-1H";
 		if (machine_is_nanoengine())
 			name = "MT48LC8M16A2TG-75";
diff --git a/drivers/cpufreq/tegra-cpufreq.c b/drivers/cpufreq/tegra-cpufreq.c
index 6e774c6ac20..8084c7f7e20 100644
--- a/drivers/cpufreq/tegra-cpufreq.c
+++ b/drivers/cpufreq/tegra-cpufreq.c
@@ -45,46 +45,54 @@ static struct clk *cpu_clk;
 static struct clk *pll_x_clk;
 static struct clk *pll_p_clk;
 static struct clk *emc_clk;
+static bool pll_x_prepared;
 
-static int tegra_cpu_clk_set_rate(unsigned long rate)
+static unsigned int tegra_get_intermediate(struct cpufreq_policy *policy,
+					   unsigned int index)
+{
+	unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
+
+	/*
+	 * Don't switch to intermediate freq if:
+	 * - we are already at it, i.e. policy->cur == ifreq
+	 * - index corresponds to ifreq
+	 */
+	if ((freq_table[index].frequency == ifreq) || (policy->cur == ifreq))
+		return 0;
+
+	return ifreq;
+}
+
+static int tegra_target_intermediate(struct cpufreq_policy *policy,
+				     unsigned int index)
 {
 	int ret;
 
 	/*
 	 * Take an extra reference to the main pll so it doesn't turn
-	 * off when we move the cpu off of it
+	 * off when we move the cpu off of it as enabling it again while we
+	 * switch to it from tegra_target() would take additional time.
+	 *
+	 * When target-freq is equal to intermediate freq we don't need to
+	 * switch to an intermediate freq and so this routine isn't called.
+	 * Also, we wouldn't be using pll_x anymore and must not take extra
+	 * reference to it, as it can be disabled now to save some power.
 	 */
 	clk_prepare_enable(pll_x_clk);
 
 	ret = clk_set_parent(cpu_clk, pll_p_clk);
-	if (ret) {
-		pr_err("Failed to switch cpu to clock pll_p\n");
-		goto out;
-	}
-
-	if (rate == clk_get_rate(pll_p_clk))
-		goto out;
-
-	ret = clk_set_rate(pll_x_clk, rate);
-	if (ret) {
-		pr_err("Failed to change pll_x to %lu\n", rate);
-		goto out;
-	}
-
-	ret = clk_set_parent(cpu_clk, pll_x_clk);
-	if (ret) {
-		pr_err("Failed to switch cpu to clock pll_x\n");
-		goto out;
-	}
+	if (ret)
+		clk_disable_unprepare(pll_x_clk);
+	else
+		pll_x_prepared = true;
 
-out:
-	clk_disable_unprepare(pll_x_clk);
 	return ret;
 }
 
 static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	unsigned long rate = freq_table[index].frequency;
+	unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
 	int ret = 0;
 
 	/*
@@ -98,10 +106,30 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 	else
 		clk_set_rate(emc_clk, 100000000);  /* emc 50Mhz */
 
-	ret = tegra_cpu_clk_set_rate(rate * 1000);
+	/*
+	 * target freq == pll_p, don't need to take extra reference to pll_x_clk
+	 * as it isn't used anymore.
+	 */
+	if (rate == ifreq)
+		return clk_set_parent(cpu_clk, pll_p_clk);
+
+	ret = clk_set_rate(pll_x_clk, rate * 1000);
+	/* Restore to earlier frequency on error, i.e. pll_x */
 	if (ret)
-		pr_err("cpu-tegra: Failed to set cpu frequency to %lu kHz\n",
-			rate);
+		pr_err("Failed to change pll_x to %lu\n", rate);
+
+	ret = clk_set_parent(cpu_clk, pll_x_clk);
+	/* This shouldn't fail while changing or restoring */
+	WARN_ON(ret);
+
+	/*
+	 * Drop count to pll_x clock only if we switched to intermediate freq
+	 * earlier while transitioning to a target frequency.
+	 */
+	if (pll_x_prepared) {
+		clk_disable_unprepare(pll_x_clk);
+		pll_x_prepared = false;
+	}
 
 	return ret;
 }
@@ -137,16 +165,18 @@ static int tegra_cpu_exit(struct cpufreq_policy *policy)
 }
 
 static struct cpufreq_driver tegra_cpufreq_driver = {
-	.flags		= CPUFREQ_NEED_INITIAL_FREQ_CHECK,
-	.verify		= cpufreq_generic_frequency_table_verify,
-	.target_index	= tegra_target,
-	.get		= cpufreq_generic_get,
-	.init		= tegra_cpu_init,
-	.exit		= tegra_cpu_exit,
-	.name		= "tegra",
-	.attr		= cpufreq_generic_attr,
+	.flags			= CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify			= cpufreq_generic_frequency_table_verify,
+	.get_intermediate	= tegra_get_intermediate,
+	.target_intermediate	= tegra_target_intermediate,
+	.target_index		= tegra_target,
+	.get			= cpufreq_generic_get,
+	.init			= tegra_cpu_init,
+	.exit			= tegra_cpu_exit,
+	.name			= "tegra",
+	.attr			= cpufreq_generic_attr,
 #ifdef CONFIG_PM
-	.suspend	= cpufreq_generic_suspend,
+	.suspend		= cpufreq_generic_suspend,
 #endif
 };
 
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig
index f04e25f6c98..1b96fb91d32 100644
--- a/drivers/cpuidle/Kconfig
+++ b/drivers/cpuidle/Kconfig
@@ -35,6 +35,11 @@ depends on ARM
 source "drivers/cpuidle/Kconfig.arm"
 endmenu
 
+menu "MIPS CPU Idle Drivers"
+depends on MIPS
+source "drivers/cpuidle/Kconfig.mips"
+endmenu
+
 menu "POWERPC CPU Idle Drivers"
 depends on PPC
 source "drivers/cpuidle/Kconfig.powerpc"
diff --git a/drivers/cpuidle/Kconfig.mips b/drivers/cpuidle/Kconfig.mips
new file mode 100644
index 00000000000..0e70ee28a5c
--- /dev/null
+++ b/drivers/cpuidle/Kconfig.mips
@@ -0,0 +1,17 @@
+#
+# MIPS CPU Idle Drivers
+#
+config MIPS_CPS_CPUIDLE
+	bool "CPU Idle driver for MIPS CPS platforms"
+	depends on CPU_IDLE
+	depends on SYS_SUPPORTS_MIPS_CPS
+	select ARCH_NEEDS_CPU_IDLE_COUPLED if MIPS_MT
+	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select MIPS_CPS_PM
+	default y
+	help
+	  Select this option to enable processor idle state management
+	  through cpuidle for systems built around the MIPS Coherent
+	  Processing System (CPS) architecture. In order to make use of
+	  the deepest idle states you will need to ensure that you are
+	  also using the CONFIG_MIPS_CPS SMP implementation.
diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile
index 9b5b2b560d7..d8bb1ff7256 100644
--- a/drivers/cpuidle/Makefile
+++ b/drivers/cpuidle/Makefile
@@ -18,6 +18,10 @@ obj-$(CONFIG_ARM_AT91_CPUIDLE)          += cpuidle-at91.o
 obj-$(CONFIG_ARM_EXYNOS_CPUIDLE)        += cpuidle-exynos.o
 
 ###############################################################################
+# MIPS drivers
+obj-$(CONFIG_MIPS_CPS_CPUIDLE)		+= cpuidle-cps.o
+
+###############################################################################
 # POWERPC drivers
 obj-$(CONFIG_PSERIES_CPUIDLE)		+= cpuidle-pseries.o
 obj-$(CONFIG_POWERNV_CPUIDLE)		+= cpuidle-powernv.o
diff --git a/drivers/cpuidle/cpuidle-armada-370-xp.c b/drivers/cpuidle/cpuidle-armada-370-xp.c
index 28587d0f394..a5fba0287bf 100644
--- a/drivers/cpuidle/cpuidle-armada-370-xp.c
+++ b/drivers/cpuidle/cpuidle-armada-370-xp.c
@@ -55,7 +55,7 @@ static struct cpuidle_driver armada_370_xp_idle_driver = {
 		.power_usage		= 50,
 		.target_residency	= 100,
 		.flags			= CPUIDLE_FLAG_TIME_VALID,
-		.name			= "MV CPU IDLE",
+		.name			= "Idle",
 		.desc			= "CPU power down",
 	},
 	.states[2]		= {
@@ -65,7 +65,7 @@ static struct cpuidle_driver armada_370_xp_idle_driver = {
 		.target_residency	= 1000,
 		.flags			= CPUIDLE_FLAG_TIME_VALID |
 						ARMADA_370_XP_FLAG_DEEP_IDLE,
-		.name			= "MV CPU DEEP IDLE",
+		.name			= "Deep idle",
 		.desc			= "CPU and L2 Fabric power down",
 	},
 	.state_count = ARMADA_370_XP_MAX_STATES,
diff --git a/drivers/cpuidle/cpuidle-cps.c b/drivers/cpuidle/cpuidle-cps.c
new file mode 100644
index 00000000000..fc7b62720de
--- /dev/null
+++ b/drivers/cpuidle/cpuidle-cps.c
@@ -0,0 +1,186 @@
+/*
+ * Copyright (C) 2014 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/cpu_pm.h>
+#include <linux/cpuidle.h>
+#include <linux/init.h>
+
+#include <asm/idle.h>
+#include <asm/pm-cps.h>
+
+/* Enumeration of the various idle states this driver may enter */
+enum cps_idle_state {
+	STATE_WAIT = 0,		/* MIPS wait instruction, coherent */
+	STATE_NC_WAIT,		/* MIPS wait instruction, non-coherent */
+	STATE_CLOCK_GATED,	/* Core clock gated */
+	STATE_POWER_GATED,	/* Core power gated */
+	STATE_COUNT
+};
+
+static int cps_nc_enter(struct cpuidle_device *dev,
+			struct cpuidle_driver *drv, int index)
+{
+	enum cps_pm_state pm_state;
+	int err;
+
+	/*
+	 * At least one core must remain powered up & clocked in order for the
+	 * system to have any hope of functioning.
+	 *
+	 * TODO: don't treat core 0 specially, just prevent the final core
+	 * TODO: remap interrupt affinity temporarily
+	 */
+	if (!cpu_data[dev->cpu].core && (index > STATE_NC_WAIT))
+		index = STATE_NC_WAIT;
+
+	/* Select the appropriate cps_pm_state */
+	switch (index) {
+	case STATE_NC_WAIT:
+		pm_state = CPS_PM_NC_WAIT;
+		break;
+	case STATE_CLOCK_GATED:
+		pm_state = CPS_PM_CLOCK_GATED;
+		break;
+	case STATE_POWER_GATED:
+		pm_state = CPS_PM_POWER_GATED;
+		break;
+	default:
+		BUG();
+		return -EINVAL;
+	}
+
+	/* Notify listeners the CPU is about to power down */
+	if ((pm_state == CPS_PM_POWER_GATED) && cpu_pm_enter())
+		return -EINTR;
+
+	/* Enter that state */
+	err = cps_pm_enter_state(pm_state);
+
+	/* Notify listeners the CPU is back up */
+	if (pm_state == CPS_PM_POWER_GATED)
+		cpu_pm_exit();
+
+	return err ?: index;
+}
+
+static struct cpuidle_driver cps_driver = {
+	.name			= "cpc_cpuidle",
+	.owner			= THIS_MODULE,
+	.states = {
+		[STATE_WAIT] = MIPS_CPUIDLE_WAIT_STATE,
+		[STATE_NC_WAIT] = {
+			.enter	= cps_nc_enter,
+			.exit_latency		= 200,
+			.target_residency	= 450,
+			.flags	= CPUIDLE_FLAG_TIME_VALID,
+			.name	= "nc-wait",
+			.desc	= "non-coherent MIPS wait",
+		},
+		[STATE_CLOCK_GATED] = {
+			.enter	= cps_nc_enter,
+			.exit_latency		= 300,
+			.target_residency	= 700,
+			.flags	= CPUIDLE_FLAG_TIME_VALID |
+				  CPUIDLE_FLAG_TIMER_STOP,
+			.name	= "clock-gated",
+			.desc	= "core clock gated",
+		},
+		[STATE_POWER_GATED] = {
+			.enter	= cps_nc_enter,
+			.exit_latency		= 600,
+			.target_residency	= 1000,
+			.flags	= CPUIDLE_FLAG_TIME_VALID |
+				  CPUIDLE_FLAG_TIMER_STOP,
+			.name	= "power-gated",
+			.desc	= "core power gated",
+		},
+	},
+	.state_count		= STATE_COUNT,
+	.safe_state_index	= 0,
+};
+
+static void __init cps_cpuidle_unregister(void)
+{
+	int cpu;
+	struct cpuidle_device *device;
+
+	for_each_possible_cpu(cpu) {
+		device = &per_cpu(cpuidle_dev, cpu);
+		cpuidle_unregister_device(device);
+	}
+
+	cpuidle_unregister_driver(&cps_driver);
+}
+
+static int __init cps_cpuidle_init(void)
+{
+	int err, cpu, core, i;
+	struct cpuidle_device *device;
+
+	/* Detect supported states */
+	if (!cps_pm_support_state(CPS_PM_POWER_GATED))
+		cps_driver.state_count = STATE_CLOCK_GATED + 1;
+	if (!cps_pm_support_state(CPS_PM_CLOCK_GATED))
+		cps_driver.state_count = STATE_NC_WAIT + 1;
+	if (!cps_pm_support_state(CPS_PM_NC_WAIT))
+		cps_driver.state_count = STATE_WAIT + 1;
+
+	/* Inform the user if some states are unavailable */
+	if (cps_driver.state_count < STATE_COUNT) {
+		pr_info("cpuidle-cps: limited to ");
+		switch (cps_driver.state_count - 1) {
+		case STATE_WAIT:
+			pr_cont("coherent wait\n");
+			break;
+		case STATE_NC_WAIT:
+			pr_cont("non-coherent wait\n");
+			break;
+		case STATE_CLOCK_GATED:
+			pr_cont("clock gating\n");
+			break;
+		}
+	}
+
+	/*
+	 * Set the coupled flag on the appropriate states if this system
+	 * requires it.
+	 */
+	if (coupled_coherence)
+		for (i = STATE_NC_WAIT; i < cps_driver.state_count; i++)
+			cps_driver.states[i].flags |= CPUIDLE_FLAG_COUPLED;
+
+	err = cpuidle_register_driver(&cps_driver);
+	if (err) {
+		pr_err("Failed to register CPS cpuidle driver\n");
+		return err;
+	}
+
+	for_each_possible_cpu(cpu) {
+		core = cpu_data[cpu].core;
+		device = &per_cpu(cpuidle_dev, cpu);
+		device->cpu = cpu;
+#ifdef CONFIG_MIPS_MT
+		cpumask_copy(&device->coupled_cpus, &cpu_sibling_map[cpu]);
+#endif
+
+		err = cpuidle_register_device(device);
+		if (err) {
+			pr_err("Failed to register CPU%d cpuidle device\n",
+			       cpu);
+			goto err_out;
+		}
+	}
+
+	return 0;
+err_out:
+	cps_cpuidle_unregister();
+	return err;
+}
+device_initcall(cps_cpuidle_init);
diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c
index 719f6fb5b1c..74f5788d50b 100644
--- a/drivers/cpuidle/cpuidle-powernv.c
+++ b/drivers/cpuidle/cpuidle-powernv.c
@@ -73,12 +73,10 @@ static int fastsleep_loop(struct cpuidle_device *dev,
 		return index;
 
 	new_lpcr = old_lpcr;
-	new_lpcr &= ~(LPCR_MER | LPCR_PECE); /* lpcr[mer] must be 0 */
-
-	/* exit powersave upon external interrupt, but not decrementer
-	 * interrupt.
+	/* Do not exit powersave upon decrementer as we've setup the timer
+	 * offload.
 	 */
-	new_lpcr |= LPCR_PECE0;
+	new_lpcr &= ~LPCR_PECE1;
 
 	mtspr(SPRN_LPCR, new_lpcr);
 	power7_sleep();
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index 136d6a283e0..9634f20e392 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -187,8 +187,11 @@ static int poll_idle(struct cpuidle_device *dev,
 
 	t1 = ktime_get();
 	local_irq_enable();
-	while (!need_resched())
-		cpu_relax();
+	if (!current_set_polling_and_test()) {
+		while (!need_resched())
+			cpu_relax();
+	}
+	current_clr_polling();
 
 	t2 = ktime_get();
 	diff = ktime_to_us(ktime_sub(t2, t1));
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index f066fa23cc0..2fb0fdfc87d 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -313,7 +313,7 @@ config CRYPTO_DEV_S5P
 
 config CRYPTO_DEV_NX
 	bool "Support for IBM Power7+ in-Nest cryptographic acceleration"
-	depends on PPC64 && IBMVIO
+	depends on PPC64 && IBMVIO && !CPU_LITTLE_ENDIAN
 	default n
 	help
 	  Support for Power7+ in-Nest cryptographic acceleration.
@@ -391,7 +391,7 @@ config CRYPTO_DEV_ATMEL_SHA
 
 config CRYPTO_DEV_CCP
 	bool "Support for AMD Cryptographic Coprocessor"
-	depends on X86 && PCI
+	depends on (X86 && PCI) || ARM64
 	default n
 	help
 	  The AMD Cryptographic Coprocessor provides hardware support
@@ -418,4 +418,22 @@ config CRYPTO_DEV_MXS_DCP
 	  To compile this driver as a module, choose M here: the module
 	  will be called mxs-dcp.
 
+source "drivers/crypto/qat/Kconfig"
+
+config CRYPTO_DEV_QCE
+	tristate "Qualcomm crypto engine accelerator"
+	depends on (ARCH_QCOM || COMPILE_TEST) && HAS_DMA && HAS_IOMEM
+	select CRYPTO_AES
+	select CRYPTO_DES
+	select CRYPTO_ECB
+	select CRYPTO_CBC
+	select CRYPTO_XTS
+	select CRYPTO_CTR
+	select CRYPTO_ALGAPI
+	select CRYPTO_BLKCIPHER
+	help
+	  This driver supports Qualcomm crypto engine accelerator
+	  hardware. To compile this driver as a module, choose M here. The
+	  module will be called qcrypto.
+
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 482f090d16d..3924f93d577 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -23,3 +23,5 @@ obj-$(CONFIG_CRYPTO_DEV_S5P) += s5p-sss.o
 obj-$(CONFIG_CRYPTO_DEV_SAHARA) += sahara.o
 obj-$(CONFIG_CRYPTO_DEV_TALITOS) += talitos.o
 obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/
+obj-$(CONFIG_CRYPTO_DEV_QAT) += qat/
+obj-$(CONFIG_CRYPTO_DEV_QCE) += qce/
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 37f9cc98ba1..e4c6c58fbb0 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -1292,7 +1292,7 @@ static struct platform_driver crypto4xx_driver = {
 		.of_match_table = crypto4xx_match,
 	},
 	.probe		= crypto4xx_probe,
-	.remove		= crypto4xx_remove,
+	.remove		= __exit_p(crypto4xx_remove),
 };
 
 module_platform_driver(crypto4xx_driver);
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 0618be06b9f..9a4f69eaa5e 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -1353,7 +1353,6 @@ static struct crypto_platform_data *atmel_sha_of_init(struct platform_device *pd
 					GFP_KERNEL);
 	if (!pdata->dma_slave) {
 		dev_err(&pdev->dev, "could not allocate memory for dma_slave\n");
-		devm_kfree(&pdev->dev, pdata);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1375,7 +1374,8 @@ static int atmel_sha_probe(struct platform_device *pdev)
 	unsigned long sha_phys_size;
 	int err;
 
-	sha_dd = kzalloc(sizeof(struct atmel_sha_dev), GFP_KERNEL);
+	sha_dd = devm_kzalloc(&pdev->dev, sizeof(struct atmel_sha_dev),
+				GFP_KERNEL);
 	if (sha_dd == NULL) {
 		dev_err(dev, "unable to alloc data struct.\n");
 		err = -ENOMEM;
@@ -1490,8 +1490,6 @@ clk_err:
 	free_irq(sha_dd->irq, sha_dd);
 res_err:
 	tasklet_kill(&sha_dd->done_task);
-	kfree(sha_dd);
-	sha_dd = NULL;
 sha_dd_err:
 	dev_err(dev, "initialization failed.\n");
 
@@ -1523,9 +1521,6 @@ static int atmel_sha_remove(struct platform_device *pdev)
 	if (sha_dd->irq >= 0)
 		free_irq(sha_dd->irq, sha_dd);
 
-	kfree(sha_dd);
-	sha_dd = NULL;
-
 	return 0;
 }
 
diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c
index 6cde5b530c6..d3a9041938e 100644
--- a/drivers/crypto/atmel-tdes.c
+++ b/drivers/crypto/atmel-tdes.c
@@ -1337,7 +1337,6 @@ static struct crypto_platform_data *atmel_tdes_of_init(struct platform_device *p
 					GFP_KERNEL);
 	if (!pdata->dma_slave) {
 		dev_err(&pdev->dev, "could not allocate memory for dma_slave\n");
-		devm_kfree(&pdev->dev, pdata);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1359,7 +1358,7 @@ static int atmel_tdes_probe(struct platform_device *pdev)
 	unsigned long tdes_phys_size;
 	int err;
 
-	tdes_dd = kzalloc(sizeof(struct atmel_tdes_dev), GFP_KERNEL);
+	tdes_dd = devm_kmalloc(&pdev->dev, sizeof(*tdes_dd), GFP_KERNEL);
 	if (tdes_dd == NULL) {
 		dev_err(dev, "unable to alloc data struct.\n");
 		err = -ENOMEM;
@@ -1483,8 +1482,6 @@ tdes_irq_err:
 res_err:
 	tasklet_kill(&tdes_dd->done_task);
 	tasklet_kill(&tdes_dd->queue_task);
-	kfree(tdes_dd);
-	tdes_dd = NULL;
 tdes_dd_err:
 	dev_err(dev, "initialization failed.\n");
 
@@ -1519,9 +1516,6 @@ static int atmel_tdes_remove(struct platform_device *pdev)
 	if (tdes_dd->irq >= 0)
 		free_irq(tdes_dd->irq, tdes_dd);
 
-	kfree(tdes_dd);
-	tdes_dd = NULL;
-
 	return 0;
 }
 
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index c09ce1f040d..a80ea853701 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -97,6 +97,13 @@ static inline void append_dec_op1(u32 *desc, u32 type)
 {
 	u32 *jump_cmd, *uncond_jump_cmd;
 
+	/* DK bit is valid only for AES */
+	if ((type & OP_ALG_ALGSEL_MASK) != OP_ALG_ALGSEL_AES) {
+		append_operation(desc, type | OP_ALG_AS_INITFINAL |
+				 OP_ALG_DECRYPT);
+		return;
+	}
+
 	jump_cmd = append_jump(desc, JUMP_TEST_ALL | JUMP_COND_SHRD);
 	append_operation(desc, type | OP_ALG_AS_INITFINAL |
 			 OP_ALG_DECRYPT);
@@ -786,7 +793,7 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 	ctx->sh_desc_dec_dma = dma_map_single(jrdev, desc,
 					      desc_bytes(desc),
 					      DMA_TO_DEVICE);
-	if (dma_mapping_error(jrdev, ctx->sh_desc_enc_dma)) {
+	if (dma_mapping_error(jrdev, ctx->sh_desc_dec_dma)) {
 		dev_err(jrdev, "unable to map shared descriptor\n");
 		return -ENOMEM;
 	}
@@ -1313,8 +1320,13 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 					 DMA_FROM_DEVICE, dst_chained);
 	}
 
-	/* Check if data are contiguous */
 	iv_dma = dma_map_single(jrdev, req->iv, ivsize, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, iv_dma)) {
+		dev_err(jrdev, "unable to map IV\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* Check if data are contiguous */
 	if (assoc_nents || sg_dma_address(req->assoc) + req->assoclen !=
 	    iv_dma || src_nents || iv_dma + ivsize !=
 	    sg_dma_address(req->src)) {
@@ -1345,8 +1357,6 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
 			 desc_bytes;
-	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-					    sec4_sg_bytes, DMA_TO_DEVICE);
 	*all_contig_ptr = all_contig;
 
 	sec4_sg_index = 0;
@@ -1369,6 +1379,12 @@ static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 		sg_to_sec4_sg_last(req->dst, dst_nents,
 				   edesc->sec4_sg + sec4_sg_index, 0);
 	}
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+		dev_err(jrdev, "unable to map S/G table\n");
+		return ERR_PTR(-ENOMEM);
+	}
 
 	return edesc;
 }
@@ -1494,8 +1510,13 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 					 DMA_FROM_DEVICE, dst_chained);
 	}
 
-	/* Check if data are contiguous */
 	iv_dma = dma_map_single(jrdev, greq->giv, ivsize, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, iv_dma)) {
+		dev_err(jrdev, "unable to map IV\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* Check if data are contiguous */
 	if (assoc_nents || sg_dma_address(req->assoc) + req->assoclen !=
 	    iv_dma || src_nents || iv_dma + ivsize != sg_dma_address(req->src))
 		contig &= ~GIV_SRC_CONTIG;
@@ -1534,8 +1555,6 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct aead_edesc) +
 			 desc_bytes;
-	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-					    sec4_sg_bytes, DMA_TO_DEVICE);
 	*contig_ptr = contig;
 
 	sec4_sg_index = 0;
@@ -1559,6 +1578,12 @@ static struct aead_edesc *aead_giv_edesc_alloc(struct aead_givcrypt_request
 		sg_to_sec4_sg_last(req->dst, dst_nents,
 				   edesc->sec4_sg + sec4_sg_index, 0);
 	}
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+		dev_err(jrdev, "unable to map S/G table\n");
+		return ERR_PTR(-ENOMEM);
+	}
 
 	return edesc;
 }
@@ -1650,11 +1675,16 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 					 DMA_FROM_DEVICE, dst_chained);
 	}
 
+	iv_dma = dma_map_single(jrdev, req->info, ivsize, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, iv_dma)) {
+		dev_err(jrdev, "unable to map IV\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
 	/*
 	 * Check if iv can be contiguous with source and destination.
 	 * If so, include it. If not, create scatterlist.
 	 */
-	iv_dma = dma_map_single(jrdev, req->info, ivsize, DMA_TO_DEVICE);
 	if (!src_nents && iv_dma + ivsize == sg_dma_address(req->src))
 		iv_contig = true;
 	else
@@ -1693,6 +1723,11 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
 
 	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
 					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+		dev_err(jrdev, "unable to map S/G table\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
 	edesc->iv_dma = iv_dma;
 
 #ifdef DEBUG
@@ -2441,8 +2476,37 @@ static struct caam_crypto_alg *caam_alg_alloc(struct caam_alg_template
 
 static int __init caam_algapi_init(void)
 {
+	struct device_node *dev_node;
+	struct platform_device *pdev;
+	struct device *ctrldev;
+	void *priv;
 	int i = 0, err = 0;
 
+	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	if (!dev_node) {
+		dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec4.0");
+		if (!dev_node)
+			return -ENODEV;
+	}
+
+	pdev = of_find_device_by_node(dev_node);
+	if (!pdev) {
+		of_node_put(dev_node);
+		return -ENODEV;
+	}
+
+	ctrldev = &pdev->dev;
+	priv = dev_get_drvdata(ctrldev);
+	of_node_put(dev_node);
+
+	/*
+	 * If priv is NULL, it's probably because the caam driver wasn't
+	 * properly initialized (e.g. RNG4 init failed). Thus, bail out here.
+	 */
+	if (!priv)
+		return -ENODEV;
+
+
 	INIT_LIST_HEAD(&alg_list);
 
 	/* register crypto algorithms the device supports */
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 0d9284ef96a..b464d03ebf4 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -137,13 +137,20 @@ struct caam_hash_state {
 /* Common job descriptor seq in/out ptr routines */
 
 /* Map state->caam_ctx, and append seq_out_ptr command that points to it */
-static inline void map_seq_out_ptr_ctx(u32 *desc, struct device *jrdev,
-				       struct caam_hash_state *state,
-				       int ctx_len)
+static inline int map_seq_out_ptr_ctx(u32 *desc, struct device *jrdev,
+				      struct caam_hash_state *state,
+				      int ctx_len)
 {
 	state->ctx_dma = dma_map_single(jrdev, state->caam_ctx,
 					ctx_len, DMA_FROM_DEVICE);
+	if (dma_mapping_error(jrdev, state->ctx_dma)) {
+		dev_err(jrdev, "unable to map ctx\n");
+		return -ENOMEM;
+	}
+
 	append_seq_out_ptr(desc, state->ctx_dma, ctx_len, 0);
+
+	return 0;
 }
 
 /* Map req->result, and append seq_out_ptr command that points to it */
@@ -201,14 +208,19 @@ try_buf_map_to_sec4_sg(struct device *jrdev, struct sec4_sg_entry *sec4_sg,
 }
 
 /* Map state->caam_ctx, and add it to link table */
-static inline void ctx_map_to_sec4_sg(u32 *desc, struct device *jrdev,
-				      struct caam_hash_state *state,
-				      int ctx_len,
-				      struct sec4_sg_entry *sec4_sg,
-				      u32 flag)
+static inline int ctx_map_to_sec4_sg(u32 *desc, struct device *jrdev,
+				     struct caam_hash_state *state, int ctx_len,
+				     struct sec4_sg_entry *sec4_sg, u32 flag)
 {
 	state->ctx_dma = dma_map_single(jrdev, state->caam_ctx, ctx_len, flag);
+	if (dma_mapping_error(jrdev, state->ctx_dma)) {
+		dev_err(jrdev, "unable to map ctx\n");
+		return -ENOMEM;
+	}
+
 	dma_to_sec4_sg_one(sec4_sg, state->ctx_dma, ctx_len, 0);
+
+	return 0;
 }
 
 /* Common shared descriptor commands */
@@ -487,11 +499,11 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
 			       digestsize, 1);
 #endif
 	}
-	*keylen = digestsize;
-
 	dma_unmap_single(jrdev, src_dma, *keylen, DMA_TO_DEVICE);
 	dma_unmap_single(jrdev, dst_dma, digestsize, DMA_FROM_DEVICE);
 
+	*keylen = digestsize;
+
 	kfree(desc);
 
 	return ret;
@@ -706,7 +718,7 @@ static void ahash_done_ctx_src(struct device *jrdev, u32 *desc, u32 err,
 	if (err)
 		caam_jr_strstatus(jrdev, err);
 
-	ahash_unmap_ctx(jrdev, edesc, req, digestsize, DMA_FROM_DEVICE);
+	ahash_unmap_ctx(jrdev, edesc, req, digestsize, DMA_TO_DEVICE);
 	kfree(edesc);
 
 #ifdef DEBUG
@@ -741,7 +753,7 @@ static void ahash_done_ctx_dst(struct device *jrdev, u32 *desc, u32 err,
 	if (err)
 		caam_jr_strstatus(jrdev, err);
 
-	ahash_unmap_ctx(jrdev, edesc, req, ctx->ctx_len, DMA_TO_DEVICE);
+	ahash_unmap_ctx(jrdev, edesc, req, ctx->ctx_len, DMA_FROM_DEVICE);
 	kfree(edesc);
 
 #ifdef DEBUG
@@ -808,12 +820,11 @@ static int ahash_update_ctx(struct ahash_request *req)
 		edesc->sec4_sg_bytes = sec4_sg_bytes;
 		edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 				 DESC_JOB_IO_LEN;
-		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-						     sec4_sg_bytes,
-						     DMA_TO_DEVICE);
 
-		ctx_map_to_sec4_sg(desc, jrdev, state, ctx->ctx_len,
-				   edesc->sec4_sg, DMA_BIDIRECTIONAL);
+		ret = ctx_map_to_sec4_sg(desc, jrdev, state, ctx->ctx_len,
+					 edesc->sec4_sg, DMA_BIDIRECTIONAL);
+		if (ret)
+			return ret;
 
 		state->buf_dma = try_buf_map_to_sec4_sg(jrdev,
 							edesc->sec4_sg + 1,
@@ -839,6 +850,14 @@ static int ahash_update_ctx(struct ahash_request *req)
 		init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER |
 				     HDR_REVERSE);
 
+		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+						     sec4_sg_bytes,
+						     DMA_TO_DEVICE);
+		if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+			dev_err(jrdev, "unable to map S/G table\n");
+			return -ENOMEM;
+		}
+
 		append_seq_in_ptr(desc, edesc->sec4_sg_dma, ctx->ctx_len +
 				       to_hash, LDST_SGF);
 
@@ -911,23 +930,34 @@ static int ahash_final_ctx(struct ahash_request *req)
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 			 DESC_JOB_IO_LEN;
-	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-					    sec4_sg_bytes, DMA_TO_DEVICE);
 	edesc->src_nents = 0;
 
-	ctx_map_to_sec4_sg(desc, jrdev, state, ctx->ctx_len, edesc->sec4_sg,
-			   DMA_TO_DEVICE);
+	ret = ctx_map_to_sec4_sg(desc, jrdev, state, ctx->ctx_len,
+				 edesc->sec4_sg, DMA_TO_DEVICE);
+	if (ret)
+		return ret;
 
 	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1,
 						buf, state->buf_dma, buflen,
 						last_buflen);
 	(edesc->sec4_sg + sec4_sg_bytes - 1)->len |= SEC4_SG_LEN_FIN;
 
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+		dev_err(jrdev, "unable to map S/G table\n");
+		return -ENOMEM;
+	}
+
 	append_seq_in_ptr(desc, edesc->sec4_sg_dma, ctx->ctx_len + buflen,
 			  LDST_SGF);
 
 	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
 						digestsize);
+	if (dma_mapping_error(jrdev, edesc->dst_dma)) {
+		dev_err(jrdev, "unable to map dst\n");
+		return -ENOMEM;
+	}
 
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
@@ -989,11 +1019,11 @@ static int ahash_finup_ctx(struct ahash_request *req)
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 			 DESC_JOB_IO_LEN;
-	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-					    sec4_sg_bytes, DMA_TO_DEVICE);
 
-	ctx_map_to_sec4_sg(desc, jrdev, state, ctx->ctx_len, edesc->sec4_sg,
-			   DMA_TO_DEVICE);
+	ret = ctx_map_to_sec4_sg(desc, jrdev, state, ctx->ctx_len,
+				 edesc->sec4_sg, DMA_TO_DEVICE);
+	if (ret)
+		return ret;
 
 	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1,
 						buf, state->buf_dma, buflen,
@@ -1002,11 +1032,22 @@ static int ahash_finup_ctx(struct ahash_request *req)
 	src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg +
 			   sec4_sg_src_index, chained);
 
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+		dev_err(jrdev, "unable to map S/G table\n");
+		return -ENOMEM;
+	}
+
 	append_seq_in_ptr(desc, edesc->sec4_sg_dma, ctx->ctx_len +
 			       buflen + req->nbytes, LDST_SGF);
 
 	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
 						digestsize);
+	if (dma_mapping_error(jrdev, edesc->dst_dma)) {
+		dev_err(jrdev, "unable to map dst\n");
+		return -ENOMEM;
+	}
 
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
@@ -1056,8 +1097,7 @@ static int ahash_digest(struct ahash_request *req)
 	}
 	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 			  DESC_JOB_IO_LEN;
-	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-					    sec4_sg_bytes, DMA_TO_DEVICE);
+	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->src_nents = src_nents;
 	edesc->chained = chained;
 
@@ -1067,6 +1107,12 @@ static int ahash_digest(struct ahash_request *req)
 
 	if (src_nents) {
 		sg_to_sec4_sg_last(req->src, src_nents, edesc->sec4_sg, 0);
+		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+		if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+			dev_err(jrdev, "unable to map S/G table\n");
+			return -ENOMEM;
+		}
 		src_dma = edesc->sec4_sg_dma;
 		options = LDST_SGF;
 	} else {
@@ -1077,6 +1123,10 @@ static int ahash_digest(struct ahash_request *req)
 
 	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
 						digestsize);
+	if (dma_mapping_error(jrdev, edesc->dst_dma)) {
+		dev_err(jrdev, "unable to map dst\n");
+		return -ENOMEM;
+	}
 
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
@@ -1125,11 +1175,19 @@ static int ahash_final_no_ctx(struct ahash_request *req)
 	init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER | HDR_REVERSE);
 
 	state->buf_dma = dma_map_single(jrdev, buf, buflen, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, state->buf_dma)) {
+		dev_err(jrdev, "unable to map src\n");
+		return -ENOMEM;
+	}
 
 	append_seq_in_ptr(desc, state->buf_dma, buflen, 0);
 
 	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
 						digestsize);
+	if (dma_mapping_error(jrdev, edesc->dst_dma)) {
+		dev_err(jrdev, "unable to map dst\n");
+		return -ENOMEM;
+	}
 	edesc->src_nents = 0;
 
 #ifdef DEBUG
@@ -1197,9 +1255,7 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 		edesc->sec4_sg_bytes = sec4_sg_bytes;
 		edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 				 DESC_JOB_IO_LEN;
-		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-						    sec4_sg_bytes,
-						    DMA_TO_DEVICE);
+		edesc->dst_dma = 0;
 
 		state->buf_dma = buf_map_to_sec4_sg(jrdev, edesc->sec4_sg,
 						    buf, *buflen);
@@ -1216,9 +1272,19 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 		init_job_desc_shared(desc, ptr, sh_len, HDR_SHARE_DEFER |
 				     HDR_REVERSE);
 
+		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+						    sec4_sg_bytes,
+						    DMA_TO_DEVICE);
+		if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+			dev_err(jrdev, "unable to map S/G table\n");
+			return -ENOMEM;
+		}
+
 		append_seq_in_ptr(desc, edesc->sec4_sg_dma, to_hash, LDST_SGF);
 
-		map_seq_out_ptr_ctx(desc, jrdev, state, ctx->ctx_len);
+		ret = map_seq_out_ptr_ctx(desc, jrdev, state, ctx->ctx_len);
+		if (ret)
+			return ret;
 
 #ifdef DEBUG
 		print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
@@ -1297,8 +1363,6 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 	edesc->sec4_sg_bytes = sec4_sg_bytes;
 	edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 			 DESC_JOB_IO_LEN;
-	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-					    sec4_sg_bytes, DMA_TO_DEVICE);
 
 	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg, buf,
 						state->buf_dma, buflen,
@@ -1307,11 +1371,22 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 	src_map_to_sec4_sg(jrdev, req->src, src_nents, edesc->sec4_sg + 1,
 			   chained);
 
+	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
+					    sec4_sg_bytes, DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+		dev_err(jrdev, "unable to map S/G table\n");
+		return -ENOMEM;
+	}
+
 	append_seq_in_ptr(desc, edesc->sec4_sg_dma, buflen +
 			       req->nbytes, LDST_SGF);
 
 	edesc->dst_dma = map_seq_out_ptr_result(desc, jrdev, req->result,
 						digestsize);
+	if (dma_mapping_error(jrdev, edesc->dst_dma)) {
+		dev_err(jrdev, "unable to map dst\n");
+		return -ENOMEM;
+	}
 
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
@@ -1380,13 +1455,19 @@ static int ahash_update_first(struct ahash_request *req)
 		edesc->sec4_sg_bytes = sec4_sg_bytes;
 		edesc->sec4_sg = (void *)edesc + sizeof(struct ahash_edesc) +
 				 DESC_JOB_IO_LEN;
-		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
-						    sec4_sg_bytes,
-						    DMA_TO_DEVICE);
+		edesc->dst_dma = 0;
 
 		if (src_nents) {
 			sg_to_sec4_sg_last(req->src, src_nents,
 					   edesc->sec4_sg, 0);
+			edesc->sec4_sg_dma = dma_map_single(jrdev,
+							    edesc->sec4_sg,
+							    sec4_sg_bytes,
+							    DMA_TO_DEVICE);
+			if (dma_mapping_error(jrdev, edesc->sec4_sg_dma)) {
+				dev_err(jrdev, "unable to map S/G table\n");
+				return -ENOMEM;
+			}
 			src_dma = edesc->sec4_sg_dma;
 			options = LDST_SGF;
 		} else {
@@ -1404,7 +1485,9 @@ static int ahash_update_first(struct ahash_request *req)
 
 		append_seq_in_ptr(desc, src_dma, to_hash, options);
 
-		map_seq_out_ptr_ctx(desc, jrdev, state, ctx->ctx_len);
+		ret = map_seq_out_ptr_ctx(desc, jrdev, state, ctx->ctx_len);
+		if (ret)
+			return ret;
 
 #ifdef DEBUG
 		print_hex_dump(KERN_ERR, "jobdesc@"__stringify(__LINE__)": ",
@@ -1453,6 +1536,7 @@ static int ahash_init(struct ahash_request *req)
 	state->final = ahash_final_no_ctx;
 
 	state->current_buf = 0;
+	state->buf_dma = 0;
 
 	return 0;
 }
@@ -1787,8 +1871,36 @@ caam_hash_alloc(struct caam_hash_template *template,
 
 static int __init caam_algapi_hash_init(void)
 {
+	struct device_node *dev_node;
+	struct platform_device *pdev;
+	struct device *ctrldev;
+	void *priv;
 	int i = 0, err = 0;
 
+	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	if (!dev_node) {
+		dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec4.0");
+		if (!dev_node)
+			return -ENODEV;
+	}
+
+	pdev = of_find_device_by_node(dev_node);
+	if (!pdev) {
+		of_node_put(dev_node);
+		return -ENODEV;
+	}
+
+	ctrldev = &pdev->dev;
+	priv = dev_get_drvdata(ctrldev);
+	of_node_put(dev_node);
+
+	/*
+	 * If priv is NULL, it's probably because the caam driver wasn't
+	 * properly initialized (e.g. RNG4 init failed). Thus, bail out here.
+	 */
+	if (!priv)
+		return -ENODEV;
+
 	INIT_LIST_HEAD(&hash_list);
 
 	/* register crypto algorithms the device supports */
diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c
index 8c07d3153f1..ae31e555793 100644
--- a/drivers/crypto/caam/caamrng.c
+++ b/drivers/crypto/caam/caamrng.c
@@ -185,7 +185,7 @@ static int caam_read(struct hwrng *rng, void *data, size_t max, bool wait)
 				      max - copied_idx, false);
 }
 
-static inline void rng_create_sh_desc(struct caam_rng_ctx *ctx)
+static inline int rng_create_sh_desc(struct caam_rng_ctx *ctx)
 {
 	struct device *jrdev = ctx->jrdev;
 	u32 *desc = ctx->sh_desc;
@@ -203,13 +203,18 @@ static inline void rng_create_sh_desc(struct caam_rng_ctx *ctx)
 
 	ctx->sh_desc_dma = dma_map_single(jrdev, desc, desc_bytes(desc),
 					  DMA_TO_DEVICE);
+	if (dma_mapping_error(jrdev, ctx->sh_desc_dma)) {
+		dev_err(jrdev, "unable to map shared descriptor\n");
+		return -ENOMEM;
+	}
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "rng shdesc@: ", DUMP_PREFIX_ADDRESS, 16, 4,
 		       desc, desc_bytes(desc), 1);
 #endif
+	return 0;
 }
 
-static inline void rng_create_job_desc(struct caam_rng_ctx *ctx, int buf_id)
+static inline int rng_create_job_desc(struct caam_rng_ctx *ctx, int buf_id)
 {
 	struct device *jrdev = ctx->jrdev;
 	struct buf_data *bd = &ctx->bufs[buf_id];
@@ -220,12 +225,17 @@ static inline void rng_create_job_desc(struct caam_rng_ctx *ctx, int buf_id)
 			     HDR_REVERSE);
 
 	bd->addr = dma_map_single(jrdev, bd->buf, RN_BUF_SIZE, DMA_FROM_DEVICE);
+	if (dma_mapping_error(jrdev, bd->addr)) {
+		dev_err(jrdev, "unable to map dst\n");
+		return -ENOMEM;
+	}
 
 	append_seq_out_ptr_intlen(desc, bd->addr, RN_BUF_SIZE, 0);
 #ifdef DEBUG
 	print_hex_dump(KERN_ERR, "rng job desc@: ", DUMP_PREFIX_ADDRESS, 16, 4,
 		       desc, desc_bytes(desc), 1);
 #endif
+	return 0;
 }
 
 static void caam_cleanup(struct hwrng *rng)
@@ -242,24 +252,44 @@ static void caam_cleanup(struct hwrng *rng)
 	rng_unmap_ctx(rng_ctx);
 }
 
-static void caam_init_buf(struct caam_rng_ctx *ctx, int buf_id)
+static int caam_init_buf(struct caam_rng_ctx *ctx, int buf_id)
 {
 	struct buf_data *bd = &ctx->bufs[buf_id];
+	int err;
+
+	err = rng_create_job_desc(ctx, buf_id);
+	if (err)
+		return err;
 
-	rng_create_job_desc(ctx, buf_id);
 	atomic_set(&bd->empty, BUF_EMPTY);
 	submit_job(ctx, buf_id == ctx->current_buf);
 	wait_for_completion(&bd->filled);
+
+	return 0;
 }
 
-static void caam_init_rng(struct caam_rng_ctx *ctx, struct device *jrdev)
+static int caam_init_rng(struct caam_rng_ctx *ctx, struct device *jrdev)
 {
+	int err;
+
 	ctx->jrdev = jrdev;
-	rng_create_sh_desc(ctx);
+
+	err = rng_create_sh_desc(ctx);
+	if (err)
+		return err;
+
 	ctx->current_buf = 0;
 	ctx->cur_buf_idx = 0;
-	caam_init_buf(ctx, 0);
-	caam_init_buf(ctx, 1);
+
+	err = caam_init_buf(ctx, 0);
+	if (err)
+		return err;
+
+	err = caam_init_buf(ctx, 1);
+	if (err)
+		return err;
+
+	return 0;
 }
 
 static struct hwrng caam_rng = {
@@ -278,6 +308,35 @@ static void __exit caam_rng_exit(void)
 static int __init caam_rng_init(void)
 {
 	struct device *dev;
+	struct device_node *dev_node;
+	struct platform_device *pdev;
+	struct device *ctrldev;
+	void *priv;
+	int err;
+
+	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
+	if (!dev_node) {
+		dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec4.0");
+		if (!dev_node)
+			return -ENODEV;
+	}
+
+	pdev = of_find_device_by_node(dev_node);
+	if (!pdev) {
+		of_node_put(dev_node);
+		return -ENODEV;
+	}
+
+	ctrldev = &pdev->dev;
+	priv = dev_get_drvdata(ctrldev);
+	of_node_put(dev_node);
+
+	/*
+	 * If priv is NULL, it's probably because the caam driver wasn't
+	 * properly initialized (e.g. RNG4 init failed). Thus, bail out here.
+	 */
+	if (!priv)
+		return -ENODEV;
 
 	dev = caam_jr_alloc();
 	if (IS_ERR(dev)) {
@@ -287,7 +346,9 @@ static int __init caam_rng_init(void)
 	rng_ctx = kmalloc(sizeof(struct caam_rng_ctx), GFP_DMA);
 	if (!rng_ctx)
 		return -ENOMEM;
-	caam_init_rng(rng_ctx, dev);
+	err = caam_init_rng(rng_ctx, dev);
+	if (err)
+		return err;
 
 	dev_info(dev, "registering rng-caam\n");
 	return hwrng_register(&caam_rng);
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 1c38f86bf63..3cade79ea41 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -5,6 +5,7 @@
  * Copyright 2008-2012 Freescale Semiconductor, Inc.
  */
 
+#include <linux/device.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 
@@ -87,6 +88,17 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 
 	/* Set the bit to request direct access to DECO0 */
 	topregs = (struct caam_full __iomem *)ctrlpriv->ctrl;
+
+	if (ctrlpriv->virt_en == 1) {
+		setbits32(&topregs->ctrl.deco_rsr, DECORSR_JR0);
+
+		while (!(rd_reg32(&topregs->ctrl.deco_rsr) & DECORSR_VALID) &&
+		       --timeout)
+			cpu_relax();
+
+		timeout = 100000;
+	}
+
 	setbits32(&topregs->ctrl.deco_rq, DECORR_RQD0ENABLE);
 
 	while (!(rd_reg32(&topregs->ctrl.deco_rq) & DECORR_DEN0) &&
@@ -129,6 +141,9 @@ static inline int run_descriptor_deco0(struct device *ctrldev, u32 *desc,
 	*status = rd_reg32(&topregs->deco.op_status_hi) &
 		  DECO_OP_STATUS_HI_ERR_MASK;
 
+	if (ctrlpriv->virt_en == 1)
+		clrbits32(&topregs->ctrl.deco_rsr, DECORSR_JR0);
+
 	/* Mark the DECO as free */
 	clrbits32(&topregs->ctrl.deco_rq, DECORR_RQD0ENABLE);
 
@@ -295,9 +310,6 @@ static int caam_remove(struct platform_device *pdev)
 	/* Unmap controller region */
 	iounmap(&topregs->ctrl);
 
-	kfree(ctrlpriv->jrpdev);
-	kfree(ctrlpriv);
-
 	return ret;
 }
 
@@ -380,9 +392,11 @@ static int caam_probe(struct platform_device *pdev)
 #ifdef CONFIG_DEBUG_FS
 	struct caam_perfmon *perfmon;
 #endif
-	u64 cha_vid;
+	u32 scfgr, comp_params;
+	u32 cha_vid_ls;
 
-	ctrlpriv = kzalloc(sizeof(struct caam_drv_private), GFP_KERNEL);
+	ctrlpriv = devm_kzalloc(&pdev->dev, sizeof(struct caam_drv_private),
+				GFP_KERNEL);
 	if (!ctrlpriv)
 		return -ENOMEM;
 
@@ -413,13 +427,40 @@ static int caam_probe(struct platform_device *pdev)
 	setbits32(&topregs->ctrl.mcr, MCFGR_WDENABLE |
 		  (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0));
 
+	/*
+	 *  Read the Compile Time paramters and SCFGR to determine
+	 * if Virtualization is enabled for this platform
+	 */
+	comp_params = rd_reg32(&topregs->ctrl.perfmon.comp_parms_ms);
+	scfgr = rd_reg32(&topregs->ctrl.scfgr);
+
+	ctrlpriv->virt_en = 0;
+	if (comp_params & CTPR_MS_VIRT_EN_INCL) {
+		/* VIRT_EN_INCL = 1 & VIRT_EN_POR = 1 or
+		 * VIRT_EN_INCL = 1 & VIRT_EN_POR = 0 & SCFGR_VIRT_EN = 1
+		 */
+		if ((comp_params & CTPR_MS_VIRT_EN_POR) ||
+		    (!(comp_params & CTPR_MS_VIRT_EN_POR) &&
+		       (scfgr & SCFGR_VIRT_EN)))
+				ctrlpriv->virt_en = 1;
+	} else {
+		/* VIRT_EN_INCL = 0 && VIRT_EN_POR_VALUE = 1 */
+		if (comp_params & CTPR_MS_VIRT_EN_POR)
+				ctrlpriv->virt_en = 1;
+	}
+
+	if (ctrlpriv->virt_en == 1)
+		setbits32(&topregs->ctrl.jrstart, JRSTART_JR0_START |
+			  JRSTART_JR1_START | JRSTART_JR2_START |
+			  JRSTART_JR3_START);
+
 	if (sizeof(dma_addr_t) == sizeof(u64))
 		if (of_device_is_compatible(nprop, "fsl,sec-v5.0"))
-			dma_set_mask(dev, DMA_BIT_MASK(40));
+			dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
 		else
-			dma_set_mask(dev, DMA_BIT_MASK(36));
+			dma_set_mask_and_coherent(dev, DMA_BIT_MASK(36));
 	else
-		dma_set_mask(dev, DMA_BIT_MASK(32));
+		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
 
 	/*
 	 * Detect and enable JobRs
@@ -432,8 +473,9 @@ static int caam_probe(struct platform_device *pdev)
 		    of_device_is_compatible(np, "fsl,sec4.0-job-ring"))
 			rspec++;
 
-	ctrlpriv->jrpdev = kzalloc(sizeof(struct platform_device *) * rspec,
-								GFP_KERNEL);
+	ctrlpriv->jrpdev = devm_kzalloc(&pdev->dev,
+					sizeof(struct platform_device *) * rspec,
+					GFP_KERNEL);
 	if (ctrlpriv->jrpdev == NULL) {
 		iounmap(&topregs->ctrl);
 		return -ENOMEM;
@@ -456,8 +498,9 @@ static int caam_probe(struct platform_device *pdev)
 		}
 
 	/* Check to see if QI present. If so, enable */
-	ctrlpriv->qi_present = !!(rd_reg64(&topregs->ctrl.perfmon.comp_parms) &
-				  CTPR_QI_MASK);
+	ctrlpriv->qi_present =
+			!!(rd_reg32(&topregs->ctrl.perfmon.comp_parms_ms) &
+			   CTPR_MS_QI_MASK);
 	if (ctrlpriv->qi_present) {
 		ctrlpriv->qi = (struct caam_queue_if __force *)&topregs->qi;
 		/* This is all that's required to physically enable QI */
@@ -471,13 +514,13 @@ static int caam_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	cha_vid = rd_reg64(&topregs->ctrl.perfmon.cha_id);
+	cha_vid_ls = rd_reg32(&topregs->ctrl.perfmon.cha_id_ls);
 
 	/*
 	 * If SEC has RNG version >= 4 and RNG state handle has not been
 	 * already instantiated, do RNG instantiation
 	 */
-	if ((cha_vid & CHA_ID_RNG_MASK) >> CHA_ID_RNG_SHIFT >= 4) {
+	if ((cha_vid_ls & CHA_ID_LS_RNG_MASK) >> CHA_ID_LS_RNG_SHIFT >= 4) {
 		ctrlpriv->rng4_sh_init =
 			rd_reg32(&topregs->ctrl.r4tst[0].rdsta);
 		/*
@@ -531,7 +574,8 @@ static int caam_probe(struct platform_device *pdev)
 
 	/* NOTE: RTIC detection ought to go here, around Si time */
 
-	caam_id = rd_reg64(&topregs->ctrl.perfmon.caam_id);
+	caam_id = (u64)rd_reg32(&topregs->ctrl.perfmon.caam_id_ms) << 32 |
+		  (u64)rd_reg32(&topregs->ctrl.perfmon.caam_id_ls);
 
 	/* Report "alive" for developer to see */
 	dev_info(dev, "device ID = 0x%016llx (Era %d)\n", caam_id,
@@ -547,7 +591,7 @@ static int caam_probe(struct platform_device *pdev)
 	 */
 	perfmon = (struct caam_perfmon __force *)&ctrl->perfmon;
 
-	ctrlpriv->dfs_root = debugfs_create_dir("caam", NULL);
+	ctrlpriv->dfs_root = debugfs_create_dir(dev_name(dev), NULL);
 	ctrlpriv->ctl = debugfs_create_dir("ctl", ctrlpriv->dfs_root);
 
 	/* Controller-level - performance monitor counters */
diff --git a/drivers/crypto/caam/desc.h b/drivers/crypto/caam/desc.h
index 7e4500f18df..d397ff9d56f 100644
--- a/drivers/crypto/caam/desc.h
+++ b/drivers/crypto/caam/desc.h
@@ -321,7 +321,6 @@ struct sec4_sg_entry {
 /* Continue - Not the last FIFO store to come */
 #define FIFOST_CONT_SHIFT	23
 #define FIFOST_CONT_MASK	(1 << FIFOST_CONT_SHIFT)
-#define FIFOST_CONT_MASK	(1 << FIFOST_CONT_SHIFT)
 
 /*
  * Extended Length - use 32-bit extended length that
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index 6d85fcc5bd0..97363db4e56 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -82,6 +82,7 @@ struct caam_drv_private {
 	u8 total_jobrs;		/* Total Job Rings in device */
 	u8 qi_present;		/* Nonzero if QI present in device */
 	int secvio_irq;		/* Security violation interrupt number */
+	int virt_en;		/* Virtualization enabled in CAAM */
 
 #define	RNG4_MAX_HANDLES 2
 	/* RNG4 block */
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index 1d80bd3636c..4d18e27ffa9 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -453,8 +453,8 @@ static int caam_jr_probe(struct platform_device *pdev)
 	int error;
 
 	jrdev = &pdev->dev;
-	jrpriv = kmalloc(sizeof(struct caam_drv_private_jr),
-			 GFP_KERNEL);
+	jrpriv = devm_kmalloc(jrdev, sizeof(struct caam_drv_private_jr),
+			      GFP_KERNEL);
 	if (!jrpriv)
 		return -ENOMEM;
 
@@ -476,21 +476,19 @@ static int caam_jr_probe(struct platform_device *pdev)
 
 	if (sizeof(dma_addr_t) == sizeof(u64))
 		if (of_device_is_compatible(nprop, "fsl,sec-v5.0-job-ring"))
-			dma_set_mask(jrdev, DMA_BIT_MASK(40));
+			dma_set_mask_and_coherent(jrdev, DMA_BIT_MASK(40));
 		else
-			dma_set_mask(jrdev, DMA_BIT_MASK(36));
+			dma_set_mask_and_coherent(jrdev, DMA_BIT_MASK(36));
 	else
-		dma_set_mask(jrdev, DMA_BIT_MASK(32));
+		dma_set_mask_and_coherent(jrdev, DMA_BIT_MASK(32));
 
 	/* Identify the interrupt */
 	jrpriv->irq = irq_of_parse_and_map(nprop, 0);
 
 	/* Now do the platform independent part */
 	error = caam_jr_init(jrdev); /* now turn on hardware */
-	if (error) {
-		kfree(jrpriv);
+	if (error)
 		return error;
-	}
 
 	jrpriv->dev = jrdev;
 	spin_lock(&driver_data.jr_alloc_lock);
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index cbde8b95a6f..f48e344ffc3 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -84,6 +84,7 @@
 #endif
 
 #ifndef CONFIG_64BIT
+#ifdef __BIG_ENDIAN
 static inline void wr_reg64(u64 __iomem *reg, u64 data)
 {
 	wr_reg32((u32 __iomem *)reg, (data & 0xffffffff00000000ull) >> 32);
@@ -95,6 +96,21 @@ static inline u64 rd_reg64(u64 __iomem *reg)
 	return (((u64)rd_reg32((u32 __iomem *)reg)) << 32) |
 		((u64)rd_reg32((u32 __iomem *)reg + 1));
 }
+#else
+#ifdef __LITTLE_ENDIAN
+static inline void wr_reg64(u64 __iomem *reg, u64 data)
+{
+	wr_reg32((u32 __iomem *)reg + 1, (data & 0xffffffff00000000ull) >> 32);
+	wr_reg32((u32 __iomem *)reg, data & 0x00000000ffffffffull);
+}
+
+static inline u64 rd_reg64(u64 __iomem *reg)
+{
+	return (((u64)rd_reg32((u32 __iomem *)reg + 1)) << 32) |
+		((u64)rd_reg32((u32 __iomem *)reg));
+}
+#endif
+#endif
 #endif
 
 /*
@@ -114,45 +130,45 @@ struct jr_outentry {
  */
 
 /* Number of DECOs */
-#define CHA_NUM_DECONUM_SHIFT	56
-#define CHA_NUM_DECONUM_MASK	(0xfull << CHA_NUM_DECONUM_SHIFT)
+#define CHA_NUM_MS_DECONUM_SHIFT	24
+#define CHA_NUM_MS_DECONUM_MASK	(0xfull << CHA_NUM_MS_DECONUM_SHIFT)
 
 /* CHA Version IDs */
-#define CHA_ID_AES_SHIFT	0
-#define CHA_ID_AES_MASK		(0xfull << CHA_ID_AES_SHIFT)
+#define CHA_ID_LS_AES_SHIFT	0
+#define CHA_ID_LS_AES_MASK		(0xfull << CHA_ID_LS_AES_SHIFT)
 
-#define CHA_ID_DES_SHIFT	4
-#define CHA_ID_DES_MASK		(0xfull << CHA_ID_DES_SHIFT)
+#define CHA_ID_LS_DES_SHIFT	4
+#define CHA_ID_LS_DES_MASK		(0xfull << CHA_ID_LS_DES_SHIFT)
 
-#define CHA_ID_ARC4_SHIFT	8
-#define CHA_ID_ARC4_MASK	(0xfull << CHA_ID_ARC4_SHIFT)
+#define CHA_ID_LS_ARC4_SHIFT	8
+#define CHA_ID_LS_ARC4_MASK	(0xfull << CHA_ID_LS_ARC4_SHIFT)
 
-#define CHA_ID_MD_SHIFT		12
-#define CHA_ID_MD_MASK		(0xfull << CHA_ID_MD_SHIFT)
+#define CHA_ID_LS_MD_SHIFT	12
+#define CHA_ID_LS_MD_MASK	(0xfull << CHA_ID_LS_MD_SHIFT)
 
-#define CHA_ID_RNG_SHIFT	16
-#define CHA_ID_RNG_MASK		(0xfull << CHA_ID_RNG_SHIFT)
+#define CHA_ID_LS_RNG_SHIFT	16
+#define CHA_ID_LS_RNG_MASK	(0xfull << CHA_ID_LS_RNG_SHIFT)
 
-#define CHA_ID_SNW8_SHIFT	20
-#define CHA_ID_SNW8_MASK	(0xfull << CHA_ID_SNW8_SHIFT)
+#define CHA_ID_LS_SNW8_SHIFT	20
+#define CHA_ID_LS_SNW8_MASK	(0xfull << CHA_ID_LS_SNW8_SHIFT)
 
-#define CHA_ID_KAS_SHIFT	24
-#define CHA_ID_KAS_MASK		(0xfull << CHA_ID_KAS_SHIFT)
+#define CHA_ID_LS_KAS_SHIFT	24
+#define CHA_ID_LS_KAS_MASK	(0xfull << CHA_ID_LS_KAS_SHIFT)
 
-#define CHA_ID_PK_SHIFT		28
-#define CHA_ID_PK_MASK		(0xfull << CHA_ID_PK_SHIFT)
+#define CHA_ID_LS_PK_SHIFT	28
+#define CHA_ID_LS_PK_MASK	(0xfull << CHA_ID_LS_PK_SHIFT)
 
-#define CHA_ID_CRC_SHIFT	32
-#define CHA_ID_CRC_MASK		(0xfull << CHA_ID_CRC_SHIFT)
+#define CHA_ID_MS_CRC_SHIFT	0
+#define CHA_ID_MS_CRC_MASK	(0xfull << CHA_ID_MS_CRC_SHIFT)
 
-#define CHA_ID_SNW9_SHIFT	36
-#define CHA_ID_SNW9_MASK	(0xfull << CHA_ID_SNW9_SHIFT)
+#define CHA_ID_MS_SNW9_SHIFT	4
+#define CHA_ID_MS_SNW9_MASK	(0xfull << CHA_ID_MS_SNW9_SHIFT)
 
-#define CHA_ID_DECO_SHIFT	56
-#define CHA_ID_DECO_MASK	(0xfull << CHA_ID_DECO_SHIFT)
+#define CHA_ID_MS_DECO_SHIFT	24
+#define CHA_ID_MS_DECO_MASK	(0xfull << CHA_ID_MS_DECO_SHIFT)
 
-#define CHA_ID_JR_SHIFT		60
-#define CHA_ID_JR_MASK		(0xfull << CHA_ID_JR_SHIFT)
+#define CHA_ID_MS_JR_SHIFT	28
+#define CHA_ID_MS_JR_MASK	(0xfull << CHA_ID_MS_JR_SHIFT)
 
 struct sec_vid {
 	u16 ip_id;
@@ -172,10 +188,14 @@ struct caam_perfmon {
 	u64 rsvd[13];
 
 	/* CAAM Hardware Instantiation Parameters		fa0-fbf */
-	u64 cha_rev;		/* CRNR - CHA Revision Number		*/
-#define CTPR_QI_SHIFT		57
-#define CTPR_QI_MASK		(0x1ull << CTPR_QI_SHIFT)
-	u64 comp_parms;	/* CTPR - Compile Parameters Register	*/
+	u32 cha_rev_ms;		/* CRNR - CHA Rev No. Most significant half*/
+	u32 cha_rev_ls;		/* CRNR - CHA Rev No. Least significant half*/
+#define CTPR_MS_QI_SHIFT	25
+#define CTPR_MS_QI_MASK		(0x1ull << CTPR_MS_QI_SHIFT)
+#define CTPR_MS_VIRT_EN_INCL	0x00000001
+#define CTPR_MS_VIRT_EN_POR	0x00000002
+	u32 comp_parms_ms;	/* CTPR - Compile Parameters Register	*/
+	u32 comp_parms_ls;	/* CTPR - Compile Parameters Register	*/
 	u64 rsvd1[2];
 
 	/* CAAM Global Status					fc0-fdf */
@@ -189,9 +209,12 @@ struct caam_perfmon {
 	/* Component Instantiation Parameters			fe0-fff */
 	u32 rtic_id;		/* RVID - RTIC Version ID	*/
 	u32 ccb_id;		/* CCBVID - CCB Version ID	*/
-	u64 cha_id;		/* CHAVID - CHA Version ID	*/
-	u64 cha_num;		/* CHANUM - CHA Number		*/
-	u64 caam_id;		/* CAAMVID - CAAM Version ID	*/
+	u32 cha_id_ms;		/* CHAVID - CHA Version ID Most Significant*/
+	u32 cha_id_ls;		/* CHAVID - CHA Version ID Least Significant*/
+	u32 cha_num_ms;		/* CHANUM - CHA Number Most Significant	*/
+	u32 cha_num_ls;		/* CHANUM - CHA Number Least Significant*/
+	u32 caam_id_ms;		/* CAAMVID - CAAM Version ID MS	*/
+	u32 caam_id_ls;		/* CAAMVID - CAAM Version ID LS	*/
 };
 
 /* LIODN programming for DMA configuration */
@@ -304,9 +327,12 @@ struct caam_ctrl {
 	/* Bus Access Configuration Section			010-11f */
 	/* Read/Writable                                                */
 	struct masterid jr_mid[4];	/* JRxLIODNR - JobR LIODN setup */
-	u32 rsvd3[12];
+	u32 rsvd3[11];
+	u32 jrstart;			/* JRSTART - Job Ring Start Register */
 	struct masterid rtic_mid[4];	/* RTICxLIODNR - RTIC LIODN setup */
-	u32 rsvd4[7];
+	u32 rsvd4[5];
+	u32 deco_rsr;			/* DECORSR - Deco Request Source */
+	u32 rsvd11;
 	u32 deco_rq;			/* DECORR - DECO Request */
 	struct partid deco_mid[5];	/* DECOxLIODNR - 1 per DECO */
 	u32 rsvd5[22];
@@ -347,7 +373,10 @@ struct caam_ctrl {
 #define MCFGR_DMA_RESET		0x10000000
 #define MCFGR_LONG_PTR		0x00010000 /* Use >32-bit desc addressing */
 #define SCFGR_RDBENABLE		0x00000400
+#define SCFGR_VIRT_EN		0x00008000
 #define DECORR_RQD0ENABLE	0x00000001 /* Enable DECO0 for direct access */
+#define DECORSR_JR0		0x00000001 /* JR to supply TZ, SDID, ICID */
+#define DECORSR_VALID		0x80000000
 #define DECORR_DEN0		0x00010000 /* DECO0 available for access*/
 
 /* AXI read cache control */
@@ -365,6 +394,12 @@ struct caam_ctrl {
 #define MCFGR_AXIPRI		0x00000008 /* Assert AXI priority sideband */
 #define MCFGR_BURST_64		0x00000001 /* Max burst size */
 
+/* JRSTART register offsets */
+#define JRSTART_JR0_START       0x00000001 /* Start Job ring 0 */
+#define JRSTART_JR1_START       0x00000002 /* Start Job ring 1 */
+#define JRSTART_JR2_START       0x00000004 /* Start Job ring 2 */
+#define JRSTART_JR3_START       0x00000008 /* Start Job ring 3 */
+
 /*
  * caam_job_ring - direct job ring setup
  * 1-4 possible per instantiation, base + 1000/2000/3000/4000
diff --git a/drivers/crypto/ccp/Makefile b/drivers/crypto/ccp/Makefile
index d3505a01872..7f592d8d07b 100644
--- a/drivers/crypto/ccp/Makefile
+++ b/drivers/crypto/ccp/Makefile
@@ -1,6 +1,11 @@
 obj-$(CONFIG_CRYPTO_DEV_CCP_DD) += ccp.o
 ccp-objs := ccp-dev.o ccp-ops.o
+ifdef CONFIG_X86
 ccp-objs += ccp-pci.o
+endif
+ifdef CONFIG_ARM64
+ccp-objs += ccp-platform.o
+endif
 
 obj-$(CONFIG_CRYPTO_DEV_CCP_CRYPTO) += ccp-crypto.o
 ccp-crypto-objs := ccp-crypto-main.o \
diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c
index 2c7816149b0..a7d110652a7 100644
--- a/drivers/crypto/ccp/ccp-dev.c
+++ b/drivers/crypto/ccp/ccp-dev.c
@@ -20,7 +20,9 @@
 #include <linux/delay.h>
 #include <linux/hw_random.h>
 #include <linux/cpu.h>
+#ifdef CONFIG_X86
 #include <asm/cpu_device_id.h>
+#endif
 #include <linux/ccp.h>
 
 #include "ccp-dev.h"
@@ -360,6 +362,12 @@ int ccp_init(struct ccp_device *ccp)
 		/* Build queue interrupt mask (two interrupts per queue) */
 		qim |= cmd_q->int_ok | cmd_q->int_err;
 
+#ifdef CONFIG_ARM64
+		/* For arm64 set the recommended queue cache settings */
+		iowrite32(ccp->axcache, ccp->io_regs + CMD_Q_CACHE_BASE +
+			  (CMD_Q_CACHE_INC * i));
+#endif
+
 		dev_dbg(dev, "queue #%u available\n", i);
 	}
 	if (ccp->cmd_q_count == 0) {
@@ -558,12 +566,15 @@ bool ccp_queues_suspended(struct ccp_device *ccp)
 }
 #endif
 
+#ifdef CONFIG_X86
 static const struct x86_cpu_id ccp_support[] = {
 	{ X86_VENDOR_AMD, 22, },
 };
+#endif
 
 static int __init ccp_mod_init(void)
 {
+#ifdef CONFIG_X86
 	struct cpuinfo_x86 *cpuinfo = &boot_cpu_data;
 	int ret;
 
@@ -589,12 +600,30 @@ static int __init ccp_mod_init(void)
 
 		break;
 	}
+#endif
+
+#ifdef CONFIG_ARM64
+	int ret;
+
+	ret = ccp_platform_init();
+	if (ret)
+		return ret;
+
+	/* Don't leave the driver loaded if init failed */
+	if (!ccp_get_device()) {
+		ccp_platform_exit();
+		return -ENODEV;
+	}
+
+	return 0;
+#endif
 
 	return -ENODEV;
 }
 
 static void __exit ccp_mod_exit(void)
 {
+#ifdef CONFIG_X86
 	struct cpuinfo_x86 *cpuinfo = &boot_cpu_data;
 
 	switch (cpuinfo->x86) {
@@ -602,6 +631,11 @@ static void __exit ccp_mod_exit(void)
 		ccp_pci_exit();
 		break;
 	}
+#endif
+
+#ifdef CONFIG_ARM64
+	ccp_platform_exit();
+#endif
 }
 
 module_init(ccp_mod_init);
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 7ec536e702e..62ff35a6b9e 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -23,8 +23,6 @@
 #include <linux/hw_random.h>
 
 
-#define IO_OFFSET			0x20000
-
 #define MAX_DMAPOOL_NAME_LEN		32
 
 #define MAX_HW_QUEUES			5
@@ -32,6 +30,9 @@
 
 #define TRNG_RETRIES			10
 
+#define CACHE_NONE			0x00
+#define CACHE_WB_NO_ALLOC		0xb7
+
 
 /****** Register Mappings ******/
 #define Q_MASK_REG			0x000
@@ -50,7 +51,7 @@
 #define CMD_Q_INT_STATUS_BASE		0x214
 #define CMD_Q_STATUS_INCR		0x20
 
-#define CMD_Q_CACHE			0x228
+#define CMD_Q_CACHE_BASE		0x228
 #define CMD_Q_CACHE_INC			0x20
 
 #define CMD_Q_ERROR(__qs)		((__qs) & 0x0000003f);
@@ -194,6 +195,7 @@ struct ccp_device {
 	void *dev_specific;
 	int (*get_irq)(struct ccp_device *ccp);
 	void (*free_irq)(struct ccp_device *ccp);
+	unsigned int irq;
 
 	/*
 	 * I/O area used for device communication. The register mapping
@@ -254,12 +256,18 @@ struct ccp_device {
 	/* Suspend support */
 	unsigned int suspending;
 	wait_queue_head_t suspend_queue;
+
+	/* DMA caching attribute support */
+	unsigned int axcache;
 };
 
 
 int ccp_pci_init(void);
 void ccp_pci_exit(void);
 
+int ccp_platform_init(void);
+void ccp_platform_exit(void);
+
 struct ccp_device *ccp_alloc_struct(struct device *dev);
 int ccp_init(struct ccp_device *ccp);
 void ccp_destroy(struct ccp_device *ccp);
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index 9ae006d69df..8729364261d 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -1606,7 +1606,7 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		goto e_ksb;
 
 	ccp_reverse_set_dm_area(&exp, rsa->exp, rsa->exp_len, CCP_KSB_BYTES,
-				true);
+				false);
 	ret = ccp_copy_to_ksb(cmd_q, &exp, op.jobid, op.ksb_key,
 			      CCP_PASSTHRU_BYTESWAP_NOOP);
 	if (ret) {
@@ -1623,10 +1623,10 @@ static int ccp_run_rsa_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		goto e_exp;
 
 	ccp_reverse_set_dm_area(&src, rsa->mod, rsa->mod_len, CCP_KSB_BYTES,
-				true);
+				false);
 	src.address += o_len;	/* Adjust the address for the copy operation */
 	ccp_reverse_set_dm_area(&src, rsa->src, rsa->src_len, CCP_KSB_BYTES,
-				true);
+				false);
 	src.address -= o_len;	/* Reset the address to original value */
 
 	/* Prepare the output area for the operation */
@@ -1841,20 +1841,20 @@ static int ccp_run_ecc_mm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 
 	/* Copy the ECC modulus */
 	ccp_reverse_set_dm_area(&src, ecc->mod, ecc->mod_len,
-				CCP_ECC_OPERAND_SIZE, true);
+				CCP_ECC_OPERAND_SIZE, false);
 	src.address += CCP_ECC_OPERAND_SIZE;
 
 	/* Copy the first operand */
 	ccp_reverse_set_dm_area(&src, ecc->u.mm.operand_1,
 				ecc->u.mm.operand_1_len,
-				CCP_ECC_OPERAND_SIZE, true);
+				CCP_ECC_OPERAND_SIZE, false);
 	src.address += CCP_ECC_OPERAND_SIZE;
 
 	if (ecc->function != CCP_ECC_FUNCTION_MINV_384BIT) {
 		/* Copy the second operand */
 		ccp_reverse_set_dm_area(&src, ecc->u.mm.operand_2,
 					ecc->u.mm.operand_2_len,
-					CCP_ECC_OPERAND_SIZE, true);
+					CCP_ECC_OPERAND_SIZE, false);
 		src.address += CCP_ECC_OPERAND_SIZE;
 	}
 
@@ -1960,17 +1960,17 @@ static int ccp_run_ecc_pm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 
 	/* Copy the ECC modulus */
 	ccp_reverse_set_dm_area(&src, ecc->mod, ecc->mod_len,
-				CCP_ECC_OPERAND_SIZE, true);
+				CCP_ECC_OPERAND_SIZE, false);
 	src.address += CCP_ECC_OPERAND_SIZE;
 
 	/* Copy the first point X and Y coordinate */
 	ccp_reverse_set_dm_area(&src, ecc->u.pm.point_1.x,
 				ecc->u.pm.point_1.x_len,
-				CCP_ECC_OPERAND_SIZE, true);
+				CCP_ECC_OPERAND_SIZE, false);
 	src.address += CCP_ECC_OPERAND_SIZE;
 	ccp_reverse_set_dm_area(&src, ecc->u.pm.point_1.y,
 				ecc->u.pm.point_1.y_len,
-				CCP_ECC_OPERAND_SIZE, true);
+				CCP_ECC_OPERAND_SIZE, false);
 	src.address += CCP_ECC_OPERAND_SIZE;
 
 	/* Set the first point Z coordianate to 1 */
@@ -1981,11 +1981,11 @@ static int ccp_run_ecc_pm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		/* Copy the second point X and Y coordinate */
 		ccp_reverse_set_dm_area(&src, ecc->u.pm.point_2.x,
 					ecc->u.pm.point_2.x_len,
-					CCP_ECC_OPERAND_SIZE, true);
+					CCP_ECC_OPERAND_SIZE, false);
 		src.address += CCP_ECC_OPERAND_SIZE;
 		ccp_reverse_set_dm_area(&src, ecc->u.pm.point_2.y,
 					ecc->u.pm.point_2.y_len,
-					CCP_ECC_OPERAND_SIZE, true);
+					CCP_ECC_OPERAND_SIZE, false);
 		src.address += CCP_ECC_OPERAND_SIZE;
 
 		/* Set the second point Z coordianate to 1 */
@@ -1995,14 +1995,14 @@ static int ccp_run_ecc_pm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 		/* Copy the Domain "a" parameter */
 		ccp_reverse_set_dm_area(&src, ecc->u.pm.domain_a,
 					ecc->u.pm.domain_a_len,
-					CCP_ECC_OPERAND_SIZE, true);
+					CCP_ECC_OPERAND_SIZE, false);
 		src.address += CCP_ECC_OPERAND_SIZE;
 
 		if (ecc->function == CCP_ECC_FUNCTION_PMUL_384BIT) {
 			/* Copy the scalar value */
 			ccp_reverse_set_dm_area(&src, ecc->u.pm.scalar,
 						ecc->u.pm.scalar_len,
-						CCP_ECC_OPERAND_SIZE, true);
+						CCP_ECC_OPERAND_SIZE, false);
 			src.address += CCP_ECC_OPERAND_SIZE;
 		}
 	}
diff --git a/drivers/crypto/ccp/ccp-pci.c b/drivers/crypto/ccp/ccp-pci.c
index 0d746236df5..180cc87b4db 100644
--- a/drivers/crypto/ccp/ccp-pci.c
+++ b/drivers/crypto/ccp/ccp-pci.c
@@ -12,8 +12,10 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
+#include <linux/dma-mapping.h>
 #include <linux/kthread.h>
 #include <linux/sched.h>
 #include <linux/interrupt.h>
@@ -24,6 +26,8 @@
 #include "ccp-dev.h"
 
 #define IO_BAR				2
+#define IO_OFFSET			0x20000
+
 #define MSIX_VECTORS			2
 
 struct ccp_msix {
@@ -89,7 +93,8 @@ static int ccp_get_msi_irq(struct ccp_device *ccp)
 	if (ret)
 		return ret;
 
-	ret = request_irq(pdev->irq, ccp_irq_handler, 0, "ccp", dev);
+	ccp->irq = pdev->irq;
+	ret = request_irq(ccp->irq, ccp_irq_handler, 0, "ccp", dev);
 	if (ret) {
 		dev_notice(dev, "unable to allocate MSI IRQ (%d)\n", ret);
 		goto e_msi;
@@ -136,7 +141,7 @@ static void ccp_free_irqs(struct ccp_device *ccp)
 				 dev);
 		pci_disable_msix(pdev);
 	} else {
-		free_irq(pdev->irq, dev);
+		free_irq(ccp->irq, dev);
 		pci_disable_msi(pdev);
 	}
 }
@@ -147,21 +152,12 @@ static int ccp_find_mmio_area(struct ccp_device *ccp)
 	struct pci_dev *pdev = container_of(dev, struct pci_dev, dev);
 	resource_size_t io_len;
 	unsigned long io_flags;
-	int bar;
 
 	io_flags = pci_resource_flags(pdev, IO_BAR);
 	io_len = pci_resource_len(pdev, IO_BAR);
 	if ((io_flags & IORESOURCE_MEM) && (io_len >= (IO_OFFSET + 0x800)))
 		return IO_BAR;
 
-	for (bar = 0; bar < PCI_STD_RESOURCE_END; bar++) {
-		io_flags = pci_resource_flags(pdev, bar);
-		io_len = pci_resource_len(pdev, bar);
-		if ((io_flags & IORESOURCE_MEM) &&
-		    (io_len >= (IO_OFFSET + 0x800)))
-			return bar;
-	}
-
 	return -EIO;
 }
 
@@ -214,20 +210,13 @@ static int ccp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 	ccp->io_regs = ccp->io_map + IO_OFFSET;
 
-	ret = dma_set_mask(dev, DMA_BIT_MASK(48));
-	if (ret == 0) {
-		ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(48));
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48));
+	if (ret) {
+		ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
 		if (ret) {
-			dev_err(dev,
-				"pci_set_consistent_dma_mask failed (%d)\n",
+			dev_err(dev, "dma_set_mask_and_coherent failed (%d)\n",
 				ret);
-			goto e_bar0;
-		}
-	} else {
-		ret = dma_set_mask(dev, DMA_BIT_MASK(32));
-		if (ret) {
-			dev_err(dev, "pci_set_dma_mask failed (%d)\n", ret);
-			goto e_bar0;
+			goto e_iomap;
 		}
 	}
 
@@ -235,13 +224,13 @@ static int ccp_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	ret = ccp_init(ccp);
 	if (ret)
-		goto e_bar0;
+		goto e_iomap;
 
 	dev_notice(dev, "enabled\n");
 
 	return 0;
 
-e_bar0:
+e_iomap:
 	pci_iounmap(pdev, ccp->io_map);
 
 e_device:
diff --git a/drivers/crypto/ccp/ccp-platform.c b/drivers/crypto/ccp/ccp-platform.c
new file mode 100644
index 00000000000..b0a2806908f
--- /dev/null
+++ b/drivers/crypto/ccp/ccp-platform.c
@@ -0,0 +1,230 @@
+/*
+ * AMD Cryptographic Coprocessor (CCP) driver
+ *
+ * Copyright (C) 2014 Advanced Micro Devices, Inc.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/ioport.h>
+#include <linux/dma-mapping.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/ccp.h>
+#include <linux/of.h>
+
+#include "ccp-dev.h"
+
+
+static int ccp_get_irq(struct ccp_device *ccp)
+{
+	struct device *dev = ccp->dev;
+	struct platform_device *pdev = container_of(dev,
+					struct platform_device, dev);
+	int ret;
+
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		return ret;
+
+	ccp->irq = ret;
+	ret = request_irq(ccp->irq, ccp_irq_handler, 0, "ccp", dev);
+	if (ret) {
+		dev_notice(dev, "unable to allocate IRQ (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int ccp_get_irqs(struct ccp_device *ccp)
+{
+	struct device *dev = ccp->dev;
+	int ret;
+
+	ret = ccp_get_irq(ccp);
+	if (!ret)
+		return 0;
+
+	/* Couldn't get an interrupt */
+	dev_notice(dev, "could not enable interrupts (%d)\n", ret);
+
+	return ret;
+}
+
+static void ccp_free_irqs(struct ccp_device *ccp)
+{
+	struct device *dev = ccp->dev;
+
+	free_irq(ccp->irq, dev);
+}
+
+static struct resource *ccp_find_mmio_area(struct ccp_device *ccp)
+{
+	struct device *dev = ccp->dev;
+	struct platform_device *pdev = container_of(dev,
+					struct platform_device, dev);
+	struct resource *ior;
+
+	ior = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (ior && (resource_size(ior) >= 0x800))
+		return ior;
+
+	return NULL;
+}
+
+static int ccp_platform_probe(struct platform_device *pdev)
+{
+	struct ccp_device *ccp;
+	struct device *dev = &pdev->dev;
+	struct resource *ior;
+	int ret;
+
+	ret = -ENOMEM;
+	ccp = ccp_alloc_struct(dev);
+	if (!ccp)
+		goto e_err;
+
+	ccp->dev_specific = NULL;
+	ccp->get_irq = ccp_get_irqs;
+	ccp->free_irq = ccp_free_irqs;
+
+	ior = ccp_find_mmio_area(ccp);
+	ccp->io_map = devm_ioremap_resource(dev, ior);
+	if (IS_ERR(ccp->io_map)) {
+		ret = PTR_ERR(ccp->io_map);
+		goto e_free;
+	}
+	ccp->io_regs = ccp->io_map;
+
+	if (!dev->dma_mask)
+		dev->dma_mask = &dev->coherent_dma_mask;
+	*(dev->dma_mask) = DMA_BIT_MASK(48);
+	dev->coherent_dma_mask = DMA_BIT_MASK(48);
+
+	if (of_property_read_bool(dev->of_node, "dma-coherent"))
+		ccp->axcache = CACHE_WB_NO_ALLOC;
+	else
+		ccp->axcache = CACHE_NONE;
+
+	dev_set_drvdata(dev, ccp);
+
+	ret = ccp_init(ccp);
+	if (ret)
+		goto e_free;
+
+	dev_notice(dev, "enabled\n");
+
+	return 0;
+
+e_free:
+	kfree(ccp);
+
+e_err:
+	dev_notice(dev, "initialization failed\n");
+	return ret;
+}
+
+static int ccp_platform_remove(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ccp_device *ccp = dev_get_drvdata(dev);
+
+	ccp_destroy(ccp);
+
+	kfree(ccp);
+
+	dev_notice(dev, "disabled\n");
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int ccp_platform_suspend(struct platform_device *pdev,
+				pm_message_t state)
+{
+	struct device *dev = &pdev->dev;
+	struct ccp_device *ccp = dev_get_drvdata(dev);
+	unsigned long flags;
+	unsigned int i;
+
+	spin_lock_irqsave(&ccp->cmd_lock, flags);
+
+	ccp->suspending = 1;
+
+	/* Wake all the queue kthreads to prepare for suspend */
+	for (i = 0; i < ccp->cmd_q_count; i++)
+		wake_up_process(ccp->cmd_q[i].kthread);
+
+	spin_unlock_irqrestore(&ccp->cmd_lock, flags);
+
+	/* Wait for all queue kthreads to say they're done */
+	while (!ccp_queues_suspended(ccp))
+		wait_event_interruptible(ccp->suspend_queue,
+					 ccp_queues_suspended(ccp));
+
+	return 0;
+}
+
+static int ccp_platform_resume(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct ccp_device *ccp = dev_get_drvdata(dev);
+	unsigned long flags;
+	unsigned int i;
+
+	spin_lock_irqsave(&ccp->cmd_lock, flags);
+
+	ccp->suspending = 0;
+
+	/* Wake up all the kthreads */
+	for (i = 0; i < ccp->cmd_q_count; i++) {
+		ccp->cmd_q[i].suspended = 0;
+		wake_up_process(ccp->cmd_q[i].kthread);
+	}
+
+	spin_unlock_irqrestore(&ccp->cmd_lock, flags);
+
+	return 0;
+}
+#endif
+
+static const struct of_device_id ccp_platform_ids[] = {
+	{ .compatible = "amd,ccp-seattle-v1a" },
+	{ },
+};
+
+static struct platform_driver ccp_platform_driver = {
+	.driver = {
+		.name = "AMD Cryptographic Coprocessor",
+		.owner = THIS_MODULE,
+		.of_match_table = ccp_platform_ids,
+	},
+	.probe = ccp_platform_probe,
+	.remove = ccp_platform_remove,
+#ifdef CONFIG_PM
+	.suspend = ccp_platform_suspend,
+	.resume = ccp_platform_resume,
+#endif
+};
+
+int ccp_platform_init(void)
+{
+	return platform_driver_register(&ccp_platform_driver);
+}
+
+void ccp_platform_exit(void)
+{
+	platform_driver_unregister(&ccp_platform_driver);
+}
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index 502edf0a293..544f6d327ed 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -1247,7 +1247,7 @@ static struct vio_device_id nx842_driver_ids[] = {
 static struct vio_driver nx842_driver = {
 	.name = MODULE_NAME,
 	.probe = nx842_probe,
-	.remove = nx842_remove,
+	.remove = __exit_p(nx842_remove),
 	.get_desired_dma = nx842_get_desired_dma,
 	.id_table = nx842_driver_ids,
 };
diff --git a/drivers/crypto/qat/Kconfig b/drivers/crypto/qat/Kconfig
new file mode 100644
index 00000000000..49bede2a9f7
--- /dev/null
+++ b/drivers/crypto/qat/Kconfig
@@ -0,0 +1,23 @@
+config CRYPTO_DEV_QAT
+	tristate
+	select CRYPTO_AEAD
+	select CRYPTO_AUTHENC
+	select CRYPTO_ALGAPI
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_SHA1
+	select CRYPTO_SHA256
+	select CRYPTO_SHA512
+	select FW_LOADER
+
+config CRYPTO_DEV_QAT_DH895xCC
+	tristate "Support for Intel(R) DH895xCC"
+	depends on X86 && PCI
+	default n
+	select CRYPTO_DEV_QAT
+	help
+	  Support for Intel(R) DH895xcc with Intel(R) QuickAssist Technology
+	  for accelerating crypto and compression workloads.
+
+	  To compile this as a module, choose M here: the module
+	  will be called qat_dh895xcc.
diff --git a/drivers/crypto/qat/Makefile b/drivers/crypto/qat/Makefile
new file mode 100644
index 00000000000..d11481be225
--- /dev/null
+++ b/drivers/crypto/qat/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CRYPTO_DEV_QAT) += qat_common/
+obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCC) += qat_dh895xcc/
diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile
new file mode 100644
index 00000000000..e0424dc382f
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/Makefile
@@ -0,0 +1,14 @@
+obj-$(CONFIG_CRYPTO_DEV_QAT) += intel_qat.o
+intel_qat-objs := adf_cfg.o \
+	adf_ctl_drv.o \
+	adf_dev_mgr.o \
+	adf_init.o \
+	adf_accel_engine.o \
+	adf_aer.o \
+	adf_transport.o \
+	qat_crypto.o \
+	qat_algs.o \
+	qat_uclo.o \
+	qat_hal.o
+
+intel_qat-$(CONFIG_DEBUG_FS) += adf_transport_debug.o
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
new file mode 100644
index 00000000000..9282381b03c
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -0,0 +1,205 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_ACCEL_DEVICES_H_
+#define ADF_ACCEL_DEVICES_H_
+#include <linux/module.h>
+#include <linux/atomic.h>
+#include <linux/list.h>
+#include <linux/proc_fs.h>
+#include <linux/io.h>
+#include "adf_cfg_common.h"
+
+#define PCI_VENDOR_ID_INTEL 0x8086
+#define ADF_DH895XCC_DEVICE_NAME "dh895xcc"
+#define ADF_DH895XCC_PCI_DEVICE_ID 0x435
+#define ADF_DH895XCC_PMISC_BAR 1
+#define ADF_DH895XCC_ETR_BAR 2
+#define ADF_PCI_MAX_BARS 3
+#define ADF_DEVICE_NAME_LENGTH 32
+#define ADF_ETR_MAX_RINGS_PER_BANK 16
+#define ADF_MAX_MSIX_VECTOR_NAME 16
+#define ADF_DEVICE_NAME_PREFIX "qat_"
+
+enum adf_accel_capabilities {
+	ADF_ACCEL_CAPABILITIES_NULL = 0,
+	ADF_ACCEL_CAPABILITIES_CRYPTO_SYMMETRIC = 1,
+	ADF_ACCEL_CAPABILITIES_CRYPTO_ASYMMETRIC = 2,
+	ADF_ACCEL_CAPABILITIES_CIPHER = 4,
+	ADF_ACCEL_CAPABILITIES_AUTHENTICATION = 8,
+	ADF_ACCEL_CAPABILITIES_COMPRESSION = 32,
+	ADF_ACCEL_CAPABILITIES_LZS_COMPRESSION = 64,
+	ADF_ACCEL_CAPABILITIES_RANDOM_NUMBER = 128
+};
+
+struct adf_bar {
+	resource_size_t base_addr;
+	void __iomem *virt_addr;
+	resource_size_t size;
+} __packed;
+
+struct adf_accel_msix {
+	struct msix_entry *entries;
+	char **names;
+} __packed;
+
+struct adf_accel_pci {
+	struct pci_dev *pci_dev;
+	struct adf_accel_msix msix_entries;
+	struct adf_bar pci_bars[ADF_PCI_MAX_BARS];
+	uint8_t revid;
+	uint8_t sku;
+} __packed;
+
+enum dev_state {
+	DEV_DOWN = 0,
+	DEV_UP
+};
+
+enum dev_sku_info {
+	DEV_SKU_1 = 0,
+	DEV_SKU_2,
+	DEV_SKU_3,
+	DEV_SKU_4,
+	DEV_SKU_UNKNOWN,
+};
+
+static inline const char *get_sku_info(enum dev_sku_info info)
+{
+	switch (info) {
+	case DEV_SKU_1:
+		return "SKU1";
+	case DEV_SKU_2:
+		return "SKU2";
+	case DEV_SKU_3:
+		return "SKU3";
+	case DEV_SKU_4:
+		return "SKU4";
+	case DEV_SKU_UNKNOWN:
+	default:
+		break;
+	}
+	return "Unknown SKU";
+}
+
+struct adf_hw_device_class {
+	const char *name;
+	const enum adf_device_type type;
+	uint32_t instances;
+} __packed;
+
+struct adf_cfg_device_data;
+struct adf_accel_dev;
+struct adf_etr_data;
+struct adf_etr_ring_data;
+
+struct adf_hw_device_data {
+	struct adf_hw_device_class *dev_class;
+	uint32_t (*get_accel_mask)(uint32_t fuse);
+	uint32_t (*get_ae_mask)(uint32_t fuse);
+	uint32_t (*get_misc_bar_id)(struct adf_hw_device_data *self);
+	uint32_t (*get_etr_bar_id)(struct adf_hw_device_data *self);
+	uint32_t (*get_num_aes)(struct adf_hw_device_data *self);
+	uint32_t (*get_num_accels)(struct adf_hw_device_data *self);
+	enum dev_sku_info (*get_sku)(struct adf_hw_device_data *self);
+	void (*hw_arb_ring_enable)(struct adf_etr_ring_data *ring);
+	void (*hw_arb_ring_disable)(struct adf_etr_ring_data *ring);
+	int (*alloc_irq)(struct adf_accel_dev *accel_dev);
+	void (*free_irq)(struct adf_accel_dev *accel_dev);
+	void (*enable_error_correction)(struct adf_accel_dev *accel_dev);
+	const char *fw_name;
+	uint32_t pci_dev_id;
+	uint32_t fuses;
+	uint32_t accel_capabilities_mask;
+	uint16_t accel_mask;
+	uint16_t ae_mask;
+	uint16_t tx_rings_mask;
+	uint8_t tx_rx_gap;
+	uint8_t instance_id;
+	uint8_t num_banks;
+	uint8_t num_accel;
+	uint8_t num_logical_accel;
+	uint8_t num_engines;
+} __packed;
+
+/* CSR write macro */
+#define ADF_CSR_WR(csr_base, csr_offset, val) \
+	__raw_writel(val, csr_base + csr_offset)
+
+/* CSR read macro */
+#define ADF_CSR_RD(csr_base, csr_offset) __raw_readl(csr_base + csr_offset)
+
+#define GET_DEV(accel_dev) ((accel_dev)->accel_pci_dev.pci_dev->dev)
+#define GET_BARS(accel_dev) ((accel_dev)->accel_pci_dev.pci_bars)
+#define GET_HW_DATA(accel_dev) (accel_dev->hw_device)
+#define GET_MAX_BANKS(accel_dev) (GET_HW_DATA(accel_dev)->num_banks)
+#define GET_MAX_ACCELENGINES(accel_dev) (GET_HW_DATA(accel_dev)->num_engines)
+#define accel_to_pci_dev(accel_ptr) accel_ptr->accel_pci_dev.pci_dev
+
+struct adf_admin_comms;
+struct icp_qat_fw_loader_handle;
+struct adf_fw_loader_data {
+	struct icp_qat_fw_loader_handle *fw_loader;
+	const struct firmware *uof_fw;
+};
+
+struct adf_accel_dev {
+	struct adf_etr_data *transport;
+	struct adf_hw_device_data *hw_device;
+	struct adf_cfg_device_data *cfg;
+	struct adf_fw_loader_data *fw_loader;
+	struct adf_admin_comms *admin;
+	struct list_head crypto_list;
+	unsigned long status;
+	atomic_t ref_count;
+	struct dentry *debugfs_dir;
+	struct list_head list;
+	struct module *owner;
+	uint8_t accel_id;
+	uint8_t numa_node;
+	struct adf_accel_pci accel_pci_dev;
+} __packed;
+#endif
diff --git a/drivers/crypto/qat/qat_common/adf_accel_engine.c b/drivers/crypto/qat/qat_common/adf_accel_engine.c
new file mode 100644
index 00000000000..c77453b900a
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_accel_engine.c
@@ -0,0 +1,168 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/firmware.h>
+#include <linux/pci.h>
+#include "adf_cfg.h"
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+#include "icp_qat_uclo.h"
+
+int adf_ae_fw_load(struct adf_accel_dev *accel_dev)
+{
+	struct adf_fw_loader_data *loader_data = accel_dev->fw_loader;
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	void *uof_addr;
+	uint32_t uof_size;
+
+	if (request_firmware(&loader_data->uof_fw, hw_device->fw_name,
+			     &accel_dev->accel_pci_dev.pci_dev->dev)) {
+		pr_err("QAT: Failed to load firmware %s\n", hw_device->fw_name);
+		return -EFAULT;
+	}
+
+	uof_size = loader_data->uof_fw->size;
+	uof_addr = (void *)loader_data->uof_fw->data;
+	if (qat_uclo_map_uof_obj(loader_data->fw_loader, uof_addr, uof_size)) {
+		pr_err("QAT: Failed to map UOF\n");
+		goto out_err;
+	}
+	if (qat_uclo_wr_all_uimage(loader_data->fw_loader)) {
+		pr_err("QAT: Failed to map UOF\n");
+		goto out_err;
+	}
+	return 0;
+
+out_err:
+	release_firmware(loader_data->uof_fw);
+	return -EFAULT;
+}
+
+int adf_ae_fw_release(struct adf_accel_dev *accel_dev)
+{
+	struct adf_fw_loader_data *loader_data = accel_dev->fw_loader;
+
+	release_firmware(loader_data->uof_fw);
+	qat_uclo_del_uof_obj(loader_data->fw_loader);
+	qat_hal_deinit(loader_data->fw_loader);
+	loader_data->fw_loader = NULL;
+	return 0;
+}
+
+int adf_ae_start(struct adf_accel_dev *accel_dev)
+{
+	struct adf_fw_loader_data *loader_data = accel_dev->fw_loader;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	uint32_t ae_ctr, ae, max_aes = GET_MAX_ACCELENGINES(accel_dev);
+
+	for (ae = 0, ae_ctr = 0; ae < max_aes; ae++) {
+		if (hw_data->ae_mask & (1 << ae)) {
+			qat_hal_start(loader_data->fw_loader, ae, 0xFF);
+			ae_ctr++;
+		}
+	}
+	pr_info("QAT: qat_dev%d started %d acceleration engines\n",
+		accel_dev->accel_id, ae_ctr);
+	return 0;
+}
+
+int adf_ae_stop(struct adf_accel_dev *accel_dev)
+{
+	struct adf_fw_loader_data *loader_data = accel_dev->fw_loader;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	uint32_t ae_ctr, ae, max_aes = GET_MAX_ACCELENGINES(accel_dev);
+
+	for (ae = 0, ae_ctr = 0; ae < max_aes; ae++) {
+		if (hw_data->ae_mask & (1 << ae)) {
+			qat_hal_stop(loader_data->fw_loader, ae, 0xFF);
+			ae_ctr++;
+		}
+	}
+	pr_info("QAT: qat_dev%d stopped %d acceleration engines\n",
+		accel_dev->accel_id, ae_ctr);
+	return 0;
+}
+
+static int adf_ae_reset(struct adf_accel_dev *accel_dev, int ae)
+{
+	struct adf_fw_loader_data *loader_data = accel_dev->fw_loader;
+
+	qat_hal_reset(loader_data->fw_loader);
+	if (qat_hal_clr_reset(loader_data->fw_loader))
+		return -EFAULT;
+
+	return 0;
+}
+
+int adf_ae_init(struct adf_accel_dev *accel_dev)
+{
+	struct adf_fw_loader_data *loader_data;
+
+	loader_data = kzalloc(sizeof(*loader_data), GFP_KERNEL);
+	if (!loader_data)
+		return -ENOMEM;
+
+	accel_dev->fw_loader = loader_data;
+	if (qat_hal_init(accel_dev)) {
+		pr_err("QAT: Failed to init the AEs\n");
+		kfree(loader_data);
+		return -EFAULT;
+	}
+	if (adf_ae_reset(accel_dev, 0)) {
+		pr_err("QAT: Failed to reset the AEs\n");
+		qat_hal_deinit(loader_data->fw_loader);
+		kfree(loader_data);
+		return -EFAULT;
+	}
+	return 0;
+}
+
+int adf_ae_shutdown(struct adf_accel_dev *accel_dev)
+{
+	kfree(accel_dev->fw_loader);
+	accel_dev->fw_loader = NULL;
+	return 0;
+}
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
new file mode 100644
index 00000000000..c29d4c3926b
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -0,0 +1,259 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/aer.h>
+#include <linux/completion.h>
+#include <linux/workqueue.h>
+#include <linux/delay.h>
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+
+static struct workqueue_struct *device_reset_wq;
+
+static pci_ers_result_t adf_error_detected(struct pci_dev *pdev,
+					   pci_channel_state_t state)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	pr_info("QAT: Acceleration driver hardware error detected.\n");
+	if (!accel_dev) {
+		pr_err("QAT: Can't find acceleration device\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	if (state == pci_channel_io_perm_failure) {
+		pr_err("QAT: Can't recover from device error\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/* reset dev data */
+struct adf_reset_dev_data {
+	int mode;
+	struct adf_accel_dev *accel_dev;
+	struct completion compl;
+	struct work_struct reset_work;
+};
+
+#define PPDSTAT_OFFSET 0x7E
+static void adf_dev_restore(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+	struct pci_dev *parent = pdev->bus->self;
+	uint16_t ppdstat = 0, bridge_ctl = 0;
+	int pending = 0;
+
+	pr_info("QAT: Reseting device qat_dev%d\n", accel_dev->accel_id);
+	pci_read_config_word(pdev, PPDSTAT_OFFSET, &ppdstat);
+	pending = ppdstat & PCI_EXP_DEVSTA_TRPND;
+	if (pending) {
+		int ctr = 0;
+
+		do {
+			msleep(100);
+			pci_read_config_word(pdev, PPDSTAT_OFFSET, &ppdstat);
+			pending = ppdstat & PCI_EXP_DEVSTA_TRPND;
+		} while (pending && ctr++ < 10);
+	}
+
+	if (pending)
+		pr_info("QAT: Transaction still in progress. Proceeding\n");
+
+	pci_read_config_word(parent, PCI_BRIDGE_CONTROL, &bridge_ctl);
+	bridge_ctl |= PCI_BRIDGE_CTL_BUS_RESET;
+	pci_write_config_word(parent, PCI_BRIDGE_CONTROL, bridge_ctl);
+	msleep(100);
+	bridge_ctl &= ~PCI_BRIDGE_CTL_BUS_RESET;
+	pci_write_config_word(parent, PCI_BRIDGE_CONTROL, bridge_ctl);
+	msleep(100);
+	pci_restore_state(pdev);
+	pci_save_state(pdev);
+}
+
+static void adf_device_reset_worker(struct work_struct *work)
+{
+	struct adf_reset_dev_data *reset_data =
+		  container_of(work, struct adf_reset_dev_data, reset_work);
+	struct adf_accel_dev *accel_dev = reset_data->accel_dev;
+
+	adf_dev_restarting_notify(accel_dev);
+	adf_dev_stop(accel_dev);
+	adf_dev_restore(accel_dev);
+	if (adf_dev_start(accel_dev)) {
+		/* The device hanged and we can't restart it so stop here */
+		dev_err(&GET_DEV(accel_dev), "Restart device failed\n");
+		kfree(reset_data);
+		WARN(1, "QAT: device restart failed. Device is unusable\n");
+		return;
+	}
+	adf_dev_restarted_notify(accel_dev);
+	clear_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
+
+	/* The dev is back alive. Notify the caller if in sync mode */
+	if (reset_data->mode == ADF_DEV_RESET_SYNC)
+		complete(&reset_data->compl);
+	else
+		kfree(reset_data);
+}
+
+static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev,
+				      enum adf_dev_reset_mode mode)
+{
+	struct adf_reset_dev_data *reset_data;
+
+	if (adf_dev_started(accel_dev) &&
+	    !test_bit(ADF_STATUS_RESTARTING, &accel_dev->status))
+		return 0;
+
+	set_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
+	reset_data = kzalloc(sizeof(*reset_data), GFP_ATOMIC);
+	if (!reset_data)
+		return -ENOMEM;
+	reset_data->accel_dev = accel_dev;
+	init_completion(&reset_data->compl);
+	reset_data->mode = mode;
+	INIT_WORK(&reset_data->reset_work, adf_device_reset_worker);
+	queue_work(device_reset_wq, &reset_data->reset_work);
+
+	/* If in sync mode wait for the result */
+	if (mode == ADF_DEV_RESET_SYNC) {
+		int ret = 0;
+		/* Maximum device reset time is 10 seconds */
+		unsigned long wait_jiffies = msecs_to_jiffies(10000);
+		unsigned long timeout = wait_for_completion_timeout(
+				   &reset_data->compl, wait_jiffies);
+		if (!timeout) {
+			pr_err("QAT: Reset device timeout expired\n");
+			ret = -EFAULT;
+		}
+		kfree(reset_data);
+		return ret;
+	}
+	return 0;
+}
+
+static pci_ers_result_t adf_slot_reset(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	if (!accel_dev) {
+		pr_err("QAT: Can't find acceleration device\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+	pci_cleanup_aer_uncorrect_error_status(pdev);
+	if (adf_dev_aer_schedule_reset(accel_dev, ADF_DEV_RESET_SYNC))
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+static void adf_resume(struct pci_dev *pdev)
+{
+	pr_info("QAT: Acceleration driver reset completed\n");
+	pr_info("QAT: Device is up and runnig\n");
+}
+
+static struct pci_error_handlers adf_err_handler = {
+	.error_detected = adf_error_detected,
+	.slot_reset = adf_slot_reset,
+	.resume = adf_resume,
+};
+
+/**
+ * adf_enable_aer() - Enable Advance Error Reporting for acceleration device
+ * @accel_dev:  Pointer to acceleration device.
+ * @adf:        PCI device driver owning the given acceleration device.
+ *
+ * Function enables PCI Advance Error Reporting for the
+ * QAT acceleration device accel_dev.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_enable_aer(struct adf_accel_dev *accel_dev, struct pci_driver *adf)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+
+	adf->err_handler = &adf_err_handler;
+	pci_enable_pcie_error_reporting(pdev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_enable_aer);
+
+/**
+ * adf_disable_aer() - Enable Advance Error Reporting for acceleration device
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function disables PCI Advance Error Reporting for the
+ * QAT acceleration device accel_dev.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: void
+ */
+void adf_disable_aer(struct adf_accel_dev *accel_dev)
+{
+	struct pci_dev *pdev = accel_to_pci_dev(accel_dev);
+
+	pci_disable_pcie_error_reporting(pdev);
+}
+EXPORT_SYMBOL_GPL(adf_disable_aer);
+
+int adf_init_aer(void)
+{
+	device_reset_wq = create_workqueue("qat_device_reset_wq");
+	return (device_reset_wq == NULL) ? -EFAULT : 0;
+}
+
+void adf_exit_aer(void)
+{
+	if (device_reset_wq)
+		destroy_workqueue(device_reset_wq);
+	device_reset_wq = NULL;
+}
diff --git a/drivers/crypto/qat/qat_common/adf_cfg.c b/drivers/crypto/qat/qat_common/adf_cfg.c
new file mode 100644
index 00000000000..aba7f1d043f
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_cfg.c
@@ -0,0 +1,361 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/seq_file.h>
+#include "adf_accel_devices.h"
+#include "adf_cfg.h"
+
+static DEFINE_MUTEX(qat_cfg_read_lock);
+
+static void *qat_dev_cfg_start(struct seq_file *sfile, loff_t *pos)
+{
+	struct adf_cfg_device_data *dev_cfg = sfile->private;
+
+	mutex_lock(&qat_cfg_read_lock);
+	return seq_list_start(&dev_cfg->sec_list, *pos);
+}
+
+static int qat_dev_cfg_show(struct seq_file *sfile, void *v)
+{
+	struct list_head *list;
+	struct adf_cfg_section *sec =
+				list_entry(v, struct adf_cfg_section, list);
+
+	seq_printf(sfile, "[%s]\n", sec->name);
+	list_for_each(list, &sec->param_head) {
+		struct adf_cfg_key_val *ptr =
+			list_entry(list, struct adf_cfg_key_val, list);
+		seq_printf(sfile, "%s = %s\n", ptr->key, ptr->val);
+	}
+	return 0;
+}
+
+static void *qat_dev_cfg_next(struct seq_file *sfile, void *v, loff_t *pos)
+{
+	struct adf_cfg_device_data *dev_cfg = sfile->private;
+
+	return seq_list_next(v, &dev_cfg->sec_list, pos);
+}
+
+static void qat_dev_cfg_stop(struct seq_file *sfile, void *v)
+{
+	mutex_unlock(&qat_cfg_read_lock);
+}
+
+static const struct seq_operations qat_dev_cfg_sops = {
+	.start = qat_dev_cfg_start,
+	.next = qat_dev_cfg_next,
+	.stop = qat_dev_cfg_stop,
+	.show = qat_dev_cfg_show
+};
+
+static int qat_dev_cfg_open(struct inode *inode, struct file *file)
+{
+	int ret = seq_open(file, &qat_dev_cfg_sops);
+
+	if (!ret) {
+		struct seq_file *seq_f = file->private_data;
+
+		seq_f->private = inode->i_private;
+	}
+	return ret;
+}
+
+static const struct file_operations qat_dev_cfg_fops = {
+	.open = qat_dev_cfg_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release
+};
+
+/**
+ * adf_cfg_dev_add() - Create an acceleration device configuration table.
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function creates a configuration table for the given acceleration device.
+ * The table stores device specific config values.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_cfg_dev_add(struct adf_accel_dev *accel_dev)
+{
+	struct adf_cfg_device_data *dev_cfg_data;
+
+	dev_cfg_data = kzalloc(sizeof(*dev_cfg_data), GFP_KERNEL);
+	if (!dev_cfg_data)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&dev_cfg_data->sec_list);
+	init_rwsem(&dev_cfg_data->lock);
+	accel_dev->cfg = dev_cfg_data;
+
+	/* accel_dev->debugfs_dir should always be non-NULL here */
+	dev_cfg_data->debug = debugfs_create_file("dev_cfg", S_IRUSR,
+						  accel_dev->debugfs_dir,
+						  dev_cfg_data,
+						  &qat_dev_cfg_fops);
+	if (!dev_cfg_data->debug) {
+		pr_err("QAT: Failed to create qat cfg debugfs entry.\n");
+		kfree(dev_cfg_data);
+		accel_dev->cfg = NULL;
+		return -EFAULT;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_cfg_dev_add);
+
+static void adf_cfg_section_del_all(struct list_head *head);
+
+void adf_cfg_del_all(struct adf_accel_dev *accel_dev)
+{
+	struct adf_cfg_device_data *dev_cfg_data = accel_dev->cfg;
+
+	down_write(&dev_cfg_data->lock);
+	adf_cfg_section_del_all(&dev_cfg_data->sec_list);
+	up_write(&dev_cfg_data->lock);
+}
+
+/**
+ * adf_cfg_dev_remove() - Clears acceleration device configuration table.
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function removes configuration table from the given acceleration device
+ * and frees all allocated memory.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: void
+ */
+void adf_cfg_dev_remove(struct adf_accel_dev *accel_dev)
+{
+	struct adf_cfg_device_data *dev_cfg_data = accel_dev->cfg;
+
+	down_write(&dev_cfg_data->lock);
+	adf_cfg_section_del_all(&dev_cfg_data->sec_list);
+	up_write(&dev_cfg_data->lock);
+	debugfs_remove(dev_cfg_data->debug);
+	kfree(dev_cfg_data);
+	accel_dev->cfg = NULL;
+}
+EXPORT_SYMBOL_GPL(adf_cfg_dev_remove);
+
+static void adf_cfg_keyval_add(struct adf_cfg_key_val *new,
+			       struct adf_cfg_section *sec)
+{
+	list_add_tail(&new->list, &sec->param_head);
+}
+
+static void adf_cfg_keyval_del_all(struct list_head *head)
+{
+	struct list_head *list_ptr, *tmp;
+
+	list_for_each_prev_safe(list_ptr, tmp, head) {
+		struct adf_cfg_key_val *ptr =
+			list_entry(list_ptr, struct adf_cfg_key_val, list);
+		list_del(list_ptr);
+		kfree(ptr);
+	}
+}
+
+static void adf_cfg_section_del_all(struct list_head *head)
+{
+	struct adf_cfg_section *ptr;
+	struct list_head *list, *tmp;
+
+	list_for_each_prev_safe(list, tmp, head) {
+		ptr = list_entry(list, struct adf_cfg_section, list);
+		adf_cfg_keyval_del_all(&ptr->param_head);
+		list_del(list);
+		kfree(ptr);
+	}
+}
+
+static struct adf_cfg_key_val *adf_cfg_key_value_find(struct adf_cfg_section *s,
+						      const char *key)
+{
+	struct list_head *list;
+
+	list_for_each(list, &s->param_head) {
+		struct adf_cfg_key_val *ptr =
+			list_entry(list, struct adf_cfg_key_val, list);
+		if (!strcmp(ptr->key, key))
+			return ptr;
+	}
+	return NULL;
+}
+
+static struct adf_cfg_section *adf_cfg_sec_find(struct adf_accel_dev *accel_dev,
+						const char *sec_name)
+{
+	struct adf_cfg_device_data *cfg = accel_dev->cfg;
+	struct list_head *list;
+
+	list_for_each(list, &cfg->sec_list) {
+		struct adf_cfg_section *ptr =
+			list_entry(list, struct adf_cfg_section, list);
+		if (!strcmp(ptr->name, sec_name))
+			return ptr;
+	}
+	return NULL;
+}
+
+static int adf_cfg_key_val_get(struct adf_accel_dev *accel_dev,
+			       const char *sec_name,
+			       const char *key_name,
+			       char *val)
+{
+	struct adf_cfg_section *sec = adf_cfg_sec_find(accel_dev, sec_name);
+	struct adf_cfg_key_val *keyval = NULL;
+
+	if (sec)
+		keyval = adf_cfg_key_value_find(sec, key_name);
+	if (keyval) {
+		memcpy(val, keyval->val, ADF_CFG_MAX_VAL_LEN_IN_BYTES);
+		return 0;
+	}
+	return -1;
+}
+
+/**
+ * adf_cfg_add_key_value_param() - Add key-value config entry to config table.
+ * @accel_dev:  Pointer to acceleration device.
+ * @section_name: Name of the section where the param will be added
+ * @key: The key string
+ * @val: Value pain for the given @key
+ * @type: Type - string, int or address
+ *
+ * Function adds configuration key - value entry in the appropriate section
+ * in the given acceleration device
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_cfg_add_key_value_param(struct adf_accel_dev *accel_dev,
+				const char *section_name,
+				const char *key, const void *val,
+				enum adf_cfg_val_type type)
+{
+	struct adf_cfg_device_data *cfg = accel_dev->cfg;
+	struct adf_cfg_key_val *key_val;
+	struct adf_cfg_section *section = adf_cfg_sec_find(accel_dev,
+							   section_name);
+	if (!section)
+		return -EFAULT;
+
+	key_val = kzalloc(sizeof(*key_val), GFP_KERNEL);
+	if (!key_val)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&key_val->list);
+	strlcpy(key_val->key, key, sizeof(key_val->key));
+
+	if (type == ADF_DEC) {
+		snprintf(key_val->val, ADF_CFG_MAX_VAL_LEN_IN_BYTES,
+			 "%ld", (*((long *)val)));
+	} else if (type == ADF_STR) {
+		strlcpy(key_val->val, (char *)val, sizeof(key_val->val));
+	} else if (type == ADF_HEX) {
+		snprintf(key_val->val, ADF_CFG_MAX_VAL_LEN_IN_BYTES,
+			 "0x%lx", (unsigned long)val);
+	} else {
+		pr_err("QAT: Unknown type given.\n");
+		kfree(key_val);
+		return -1;
+	}
+	key_val->type = type;
+	down_write(&cfg->lock);
+	adf_cfg_keyval_add(key_val, section);
+	up_write(&cfg->lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_cfg_add_key_value_param);
+
+/**
+ * adf_cfg_section_add() - Add config section entry to config table.
+ * @accel_dev:  Pointer to acceleration device.
+ * @name: Name of the section
+ *
+ * Function adds configuration section where key - value entries
+ * will be stored.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_cfg_section_add(struct adf_accel_dev *accel_dev, const char *name)
+{
+	struct adf_cfg_device_data *cfg = accel_dev->cfg;
+	struct adf_cfg_section *sec = adf_cfg_sec_find(accel_dev, name);
+
+	if (sec)
+		return 0;
+
+	sec = kzalloc(sizeof(*sec), GFP_KERNEL);
+	if (!sec)
+		return -ENOMEM;
+
+	strlcpy(sec->name, name, sizeof(sec->name));
+	INIT_LIST_HEAD(&sec->param_head);
+	down_write(&cfg->lock);
+	list_add_tail(&sec->list, &cfg->sec_list);
+	up_write(&cfg->lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_cfg_section_add);
+
+int adf_cfg_get_param_value(struct adf_accel_dev *accel_dev,
+			    const char *section, const char *name,
+			    char *value)
+{
+	struct adf_cfg_device_data *cfg = accel_dev->cfg;
+	int ret;
+
+	down_read(&cfg->lock);
+	ret = adf_cfg_key_val_get(accel_dev, section, name, value);
+	up_read(&cfg->lock);
+	return ret;
+}
diff --git a/drivers/crypto/qat/qat_common/adf_cfg.h b/drivers/crypto/qat/qat_common/adf_cfg.h
new file mode 100644
index 00000000000..6a9c6f6b5ec
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_cfg.h
@@ -0,0 +1,87 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_CFG_H_
+#define ADF_CFG_H_
+
+#include <linux/list.h>
+#include <linux/rwsem.h>
+#include <linux/debugfs.h>
+#include "adf_accel_devices.h"
+#include "adf_cfg_common.h"
+#include "adf_cfg_strings.h"
+
+struct adf_cfg_key_val {
+	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	char val[ADF_CFG_MAX_VAL_LEN_IN_BYTES];
+	enum adf_cfg_val_type type;
+	struct list_head list;
+};
+
+struct adf_cfg_section {
+	char name[ADF_CFG_MAX_SECTION_LEN_IN_BYTES];
+	struct list_head list;
+	struct list_head param_head;
+};
+
+struct adf_cfg_device_data {
+	struct list_head sec_list;
+	struct dentry *debug;
+	struct rw_semaphore lock;
+};
+
+int adf_cfg_dev_add(struct adf_accel_dev *accel_dev);
+void adf_cfg_dev_remove(struct adf_accel_dev *accel_dev);
+int adf_cfg_section_add(struct adf_accel_dev *accel_dev, const char *name);
+void adf_cfg_del_all(struct adf_accel_dev *accel_dev);
+int adf_cfg_add_key_value_param(struct adf_accel_dev *accel_dev,
+				const char *section_name,
+				const char *key, const void *val,
+				enum adf_cfg_val_type type);
+int adf_cfg_get_param_value(struct adf_accel_dev *accel_dev,
+			    const char *section, const char *name, char *value);
+
+#endif
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_common.h b/drivers/crypto/qat/qat_common/adf_cfg_common.h
new file mode 100644
index 00000000000..88b82187ac3
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_cfg_common.h
@@ -0,0 +1,100 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_CFG_COMMON_H_
+#define ADF_CFG_COMMON_H_
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define ADF_CFG_MAX_STR_LEN 64
+#define ADF_CFG_MAX_KEY_LEN_IN_BYTES ADF_CFG_MAX_STR_LEN
+#define ADF_CFG_MAX_VAL_LEN_IN_BYTES ADF_CFG_MAX_STR_LEN
+#define ADF_CFG_MAX_SECTION_LEN_IN_BYTES ADF_CFG_MAX_STR_LEN
+#define ADF_CFG_BASE_DEC 10
+#define ADF_CFG_BASE_HEX 16
+#define ADF_CFG_ALL_DEVICES 0xFE
+#define ADF_CFG_NO_DEVICE 0xFF
+#define ADF_CFG_AFFINITY_WHATEVER 0xFF
+#define MAX_DEVICE_NAME_SIZE 32
+#define ADF_MAX_DEVICES 32
+
+enum adf_cfg_val_type {
+	ADF_DEC,
+	ADF_HEX,
+	ADF_STR
+};
+
+enum adf_device_type {
+	DEV_UNKNOWN = 0,
+	DEV_DH895XCC,
+};
+
+struct adf_dev_status_info {
+	enum adf_device_type type;
+	uint8_t accel_id;
+	uint8_t instance_id;
+	uint8_t num_ae;
+	uint8_t num_accel;
+	uint8_t num_logical_accel;
+	uint8_t banks_per_accel;
+	uint8_t state;
+	uint8_t bus;
+	uint8_t dev;
+	uint8_t fun;
+	char name[MAX_DEVICE_NAME_SIZE];
+};
+
+#define ADF_CTL_IOC_MAGIC 'a'
+#define IOCTL_CONFIG_SYS_RESOURCE_PARAMETERS _IOW(ADF_CTL_IOC_MAGIC, 0, \
+		struct adf_user_cfg_ctl_data)
+#define IOCTL_STOP_ACCEL_DEV _IOW(ADF_CTL_IOC_MAGIC, 1, \
+		struct adf_user_cfg_ctl_data)
+#define IOCTL_START_ACCEL_DEV _IOW(ADF_CTL_IOC_MAGIC, 2, \
+		struct adf_user_cfg_ctl_data)
+#define IOCTL_STATUS_ACCEL_DEV _IOW(ADF_CTL_IOC_MAGIC, 3, uint32_t)
+#define IOCTL_GET_NUM_DEVICES _IOW(ADF_CTL_IOC_MAGIC, 4, int32_t)
+#endif
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_strings.h b/drivers/crypto/qat/qat_common/adf_cfg_strings.h
new file mode 100644
index 00000000000..c7ac758ebc9
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_cfg_strings.h
@@ -0,0 +1,83 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_CFG_STRINGS_H_
+#define ADF_CFG_STRINGS_H_
+
+#define ADF_GENERAL_SEC "GENERAL"
+#define ADF_KERNEL_SEC "KERNEL"
+#define ADF_ACCEL_SEC "Accelerator"
+#define ADF_NUM_CY "NumberCyInstances"
+#define ADF_NUM_DC "NumberDcInstances"
+#define ADF_RING_SYM_SIZE "NumConcurrentSymRequests"
+#define ADF_RING_ASYM_SIZE "NumConcurrentAsymRequests"
+#define ADF_RING_DC_SIZE "NumConcurrentRequests"
+#define ADF_RING_ASYM_TX "RingAsymTx"
+#define ADF_RING_SYM_TX "RingSymTx"
+#define ADF_RING_RND_TX "RingNrbgTx"
+#define ADF_RING_ASYM_RX "RingAsymRx"
+#define ADF_RING_SYM_RX "RinSymRx"
+#define ADF_RING_RND_RX "RingNrbgRx"
+#define ADF_RING_DC_TX "RingTx"
+#define ADF_RING_DC_RX "RingRx"
+#define ADF_ETRMGR_BANK "Bank"
+#define ADF_RING_BANK_NUM "BankNumber"
+#define ADF_CY "Cy"
+#define ADF_DC "Dc"
+#define ADF_ETRMGR_COALESCING_ENABLED "InterruptCoalescingEnabled"
+#define ADF_ETRMGR_COALESCING_ENABLED_FORMAT \
+	ADF_ETRMGR_BANK"%d"ADF_ETRMGR_COALESCING_ENABLED
+#define ADF_ETRMGR_COALESCE_TIMER "InterruptCoalescingTimerNs"
+#define ADF_ETRMGR_COALESCE_TIMER_FORMAT \
+	ADF_ETRMGR_BANK"%d"ADF_ETRMGR_COALESCE_TIMER
+#define ADF_ETRMGR_COALESCING_MSG_ENABLED "InterruptCoalescingNumResponses"
+#define ADF_ETRMGR_COALESCING_MSG_ENABLED_FORMAT \
+	ADF_ETRMGR_BANK"%d"ADF_ETRMGR_COALESCING_MSG_ENABLED
+#define ADF_ETRMGR_CORE_AFFINITY "CoreAffinity"
+#define ADF_ETRMGR_CORE_AFFINITY_FORMAT \
+	ADF_ETRMGR_BANK"%d"ADF_ETRMGR_CORE_AFFINITY
+#define ADF_ACCEL_STR "Accelerator%d"
+#endif
diff --git a/drivers/crypto/qat/qat_common/adf_cfg_user.h b/drivers/crypto/qat/qat_common/adf_cfg_user.h
new file mode 100644
index 00000000000..0c38a155a86
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_cfg_user.h
@@ -0,0 +1,94 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_CFG_USER_H_
+#define ADF_CFG_USER_H_
+
+#include "adf_cfg_common.h"
+#include "adf_cfg_strings.h"
+
+struct adf_user_cfg_key_val {
+	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	char val[ADF_CFG_MAX_VAL_LEN_IN_BYTES];
+	union {
+		char *user_val_ptr;
+		uint64_t padding1;
+	};
+	union {
+		struct adf_user_cfg_key_val *prev;
+		uint64_t padding2;
+	};
+	union {
+		struct adf_user_cfg_key_val *next;
+		uint64_t padding3;
+	};
+	enum adf_cfg_val_type type;
+};
+
+struct adf_user_cfg_section {
+	char name[ADF_CFG_MAX_SECTION_LEN_IN_BYTES];
+	union {
+		struct adf_user_cfg_key_val *params;
+		uint64_t padding1;
+	};
+	union {
+		struct adf_user_cfg_section *prev;
+		uint64_t padding2;
+	};
+	union {
+		struct adf_user_cfg_section *next;
+		uint64_t padding3;
+	};
+};
+
+struct adf_user_cfg_ctl_data {
+	union {
+		struct adf_user_cfg_section *config_section;
+		uint64_t padding;
+	};
+	uint8_t device_id;
+};
+#endif
diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h
new file mode 100644
index 00000000000..5e8f9d431e5
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_common_drv.h
@@ -0,0 +1,192 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_DRV_H
+#define ADF_DRV_H
+
+#include <linux/list.h>
+#include <linux/pci.h>
+#include "adf_accel_devices.h"
+#include "icp_qat_fw_loader_handle.h"
+#include "icp_qat_hal.h"
+
+#define ADF_STATUS_RESTARTING 0
+#define ADF_STATUS_STARTING 1
+#define ADF_STATUS_CONFIGURED 2
+#define ADF_STATUS_STARTED 3
+#define ADF_STATUS_AE_INITIALISED 4
+#define ADF_STATUS_AE_UCODE_LOADED 5
+#define ADF_STATUS_AE_STARTED 6
+#define ADF_STATUS_ORPHAN_TH_RUNNING 7
+#define ADF_STATUS_IRQ_ALLOCATED 8
+
+enum adf_dev_reset_mode {
+	ADF_DEV_RESET_ASYNC = 0,
+	ADF_DEV_RESET_SYNC
+};
+
+enum adf_event {
+	ADF_EVENT_INIT = 0,
+	ADF_EVENT_START,
+	ADF_EVENT_STOP,
+	ADF_EVENT_SHUTDOWN,
+	ADF_EVENT_RESTARTING,
+	ADF_EVENT_RESTARTED,
+};
+
+struct service_hndl {
+	int (*event_hld)(struct adf_accel_dev *accel_dev,
+			 enum adf_event event);
+	unsigned long init_status;
+	unsigned long start_status;
+	char *name;
+	struct list_head list;
+	int admin;
+};
+
+int adf_service_register(struct service_hndl *service);
+int adf_service_unregister(struct service_hndl *service);
+
+int adf_dev_init(struct adf_accel_dev *accel_dev);
+int adf_dev_start(struct adf_accel_dev *accel_dev);
+int adf_dev_stop(struct adf_accel_dev *accel_dev);
+int adf_dev_shutdown(struct adf_accel_dev *accel_dev);
+
+int adf_ctl_dev_register(void);
+void adf_ctl_dev_unregister(void);
+int adf_processes_dev_register(void);
+void adf_processes_dev_unregister(void);
+
+int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev);
+void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev);
+struct list_head *adf_devmgr_get_head(void);
+struct adf_accel_dev *adf_devmgr_get_dev_by_id(uint32_t id);
+struct adf_accel_dev *adf_devmgr_get_first(void);
+struct adf_accel_dev *adf_devmgr_pci_to_accel_dev(struct pci_dev *pci_dev);
+int adf_devmgr_verify_id(uint32_t id);
+void adf_devmgr_get_num_dev(uint32_t *num);
+int adf_devmgr_in_reset(struct adf_accel_dev *accel_dev);
+int adf_dev_started(struct adf_accel_dev *accel_dev);
+int adf_dev_restarting_notify(struct adf_accel_dev *accel_dev);
+int adf_dev_restarted_notify(struct adf_accel_dev *accel_dev);
+int adf_ae_init(struct adf_accel_dev *accel_dev);
+int adf_ae_shutdown(struct adf_accel_dev *accel_dev);
+int adf_ae_fw_load(struct adf_accel_dev *accel_dev);
+int adf_ae_fw_release(struct adf_accel_dev *accel_dev);
+int adf_ae_start(struct adf_accel_dev *accel_dev);
+int adf_ae_stop(struct adf_accel_dev *accel_dev);
+
+int adf_enable_aer(struct adf_accel_dev *accel_dev, struct pci_driver *adf);
+void adf_disable_aer(struct adf_accel_dev *accel_dev);
+int adf_init_aer(void);
+void adf_exit_aer(void);
+
+int adf_dev_get(struct adf_accel_dev *accel_dev);
+void adf_dev_put(struct adf_accel_dev *accel_dev);
+int adf_dev_in_use(struct adf_accel_dev *accel_dev);
+int adf_init_etr_data(struct adf_accel_dev *accel_dev);
+void adf_cleanup_etr_data(struct adf_accel_dev *accel_dev);
+int qat_crypto_register(void);
+int qat_crypto_unregister(void);
+struct qat_crypto_instance *qat_crypto_get_instance_node(int node);
+void qat_crypto_put_instance(struct qat_crypto_instance *inst);
+void qat_alg_callback(void *resp);
+int qat_algs_init(void);
+void qat_algs_exit(void);
+int qat_algs_register(void);
+int qat_algs_unregister(void);
+
+int qat_hal_init(struct adf_accel_dev *accel_dev);
+void qat_hal_deinit(struct icp_qat_fw_loader_handle *handle);
+void qat_hal_start(struct icp_qat_fw_loader_handle *handle, unsigned char ae,
+		   unsigned int ctx_mask);
+void qat_hal_stop(struct icp_qat_fw_loader_handle *handle, unsigned char ae,
+		  unsigned int ctx_mask);
+void qat_hal_reset(struct icp_qat_fw_loader_handle *handle);
+int qat_hal_clr_reset(struct icp_qat_fw_loader_handle *handle);
+void qat_hal_set_live_ctx(struct icp_qat_fw_loader_handle *handle,
+			  unsigned char ae, unsigned int ctx_mask);
+int qat_hal_set_ae_lm_mode(struct icp_qat_fw_loader_handle *handle,
+			   unsigned char ae, enum icp_qat_uof_regtype lm_type,
+			   unsigned char mode);
+int qat_hal_set_ae_ctx_mode(struct icp_qat_fw_loader_handle *handle,
+			    unsigned char ae, unsigned char mode);
+int qat_hal_set_ae_nn_mode(struct icp_qat_fw_loader_handle *handle,
+			   unsigned char ae, unsigned char mode);
+void qat_hal_set_pc(struct icp_qat_fw_loader_handle *handle,
+		    unsigned char ae, unsigned int ctx_mask, unsigned int upc);
+void qat_hal_wr_uwords(struct icp_qat_fw_loader_handle *handle,
+		       unsigned char ae, unsigned int uaddr,
+		       unsigned int words_num, uint64_t *uword);
+void qat_hal_wr_umem(struct icp_qat_fw_loader_handle *handle, unsigned char ae,
+		     unsigned int uword_addr, unsigned int words_num,
+		     unsigned int *data);
+int qat_hal_get_ins_num(void);
+int qat_hal_batch_wr_lm(struct icp_qat_fw_loader_handle *handle,
+			unsigned char ae,
+			struct icp_qat_uof_batch_init *lm_init_header);
+int qat_hal_init_gpr(struct icp_qat_fw_loader_handle *handle,
+		     unsigned char ae, unsigned char ctx_mask,
+		     enum icp_qat_uof_regtype reg_type,
+		     unsigned short reg_num, unsigned int regdata);
+int qat_hal_init_wr_xfer(struct icp_qat_fw_loader_handle *handle,
+			 unsigned char ae, unsigned char ctx_mask,
+			 enum icp_qat_uof_regtype reg_type,
+			 unsigned short reg_num, unsigned int regdata);
+int qat_hal_init_rd_xfer(struct icp_qat_fw_loader_handle *handle,
+			 unsigned char ae, unsigned char ctx_mask,
+			 enum icp_qat_uof_regtype reg_type,
+			 unsigned short reg_num, unsigned int regdata);
+int qat_hal_init_nn(struct icp_qat_fw_loader_handle *handle,
+		    unsigned char ae, unsigned char ctx_mask,
+		    unsigned short reg_num, unsigned int regdata);
+int qat_hal_wr_lm(struct icp_qat_fw_loader_handle *handle,
+		  unsigned char ae, unsigned short lm_addr, unsigned int value);
+int qat_uclo_wr_all_uimage(struct icp_qat_fw_loader_handle *handle);
+void qat_uclo_del_uof_obj(struct icp_qat_fw_loader_handle *handle);
+int qat_uclo_map_uof_obj(struct icp_qat_fw_loader_handle *handle,
+			 void *addr_ptr, int mem_size);
+#endif
diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
new file mode 100644
index 00000000000..d97069b8a8e
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c
@@ -0,0 +1,490 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/bitops.h>
+#include <linux/pci.h>
+#include <linux/cdev.h>
+#include <linux/uaccess.h>
+
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+#include "adf_cfg.h"
+#include "adf_cfg_common.h"
+#include "adf_cfg_user.h"
+
+#define DEVICE_NAME "qat_adf_ctl"
+
+static DEFINE_MUTEX(adf_ctl_lock);
+static long adf_ctl_ioctl(struct file *fp, unsigned int cmd, unsigned long arg);
+
+static const struct file_operations adf_ctl_ops = {
+	.owner = THIS_MODULE,
+	.unlocked_ioctl = adf_ctl_ioctl,
+	.compat_ioctl = adf_ctl_ioctl,
+};
+
+struct adf_ctl_drv_info {
+	unsigned int major;
+	struct cdev drv_cdev;
+	struct class *drv_class;
+};
+
+static struct adf_ctl_drv_info adt_ctl_drv;
+
+static void adf_chr_drv_destroy(void)
+{
+	device_destroy(adt_ctl_drv.drv_class, MKDEV(adt_ctl_drv.major, 0));
+	cdev_del(&adt_ctl_drv.drv_cdev);
+	class_destroy(adt_ctl_drv.drv_class);
+	unregister_chrdev_region(MKDEV(adt_ctl_drv.major, 0), 1);
+}
+
+static int adf_chr_drv_create(void)
+{
+	dev_t dev_id;
+	struct device *drv_device;
+
+	if (alloc_chrdev_region(&dev_id, 0, 1, DEVICE_NAME)) {
+		pr_err("QAT: unable to allocate chrdev region\n");
+		return -EFAULT;
+	}
+
+	adt_ctl_drv.drv_class = class_create(THIS_MODULE, DEVICE_NAME);
+	if (IS_ERR(adt_ctl_drv.drv_class)) {
+		pr_err("QAT: class_create failed for adf_ctl\n");
+		goto err_chrdev_unreg;
+	}
+	adt_ctl_drv.major = MAJOR(dev_id);
+	cdev_init(&adt_ctl_drv.drv_cdev, &adf_ctl_ops);
+	if (cdev_add(&adt_ctl_drv.drv_cdev, dev_id, 1)) {
+		pr_err("QAT: cdev add failed\n");
+		goto err_class_destr;
+	}
+
+	drv_device = device_create(adt_ctl_drv.drv_class, NULL,
+				   MKDEV(adt_ctl_drv.major, 0),
+				   NULL, DEVICE_NAME);
+	if (!drv_device) {
+		pr_err("QAT: failed to create device\n");
+		goto err_cdev_del;
+	}
+	return 0;
+err_cdev_del:
+	cdev_del(&adt_ctl_drv.drv_cdev);
+err_class_destr:
+	class_destroy(adt_ctl_drv.drv_class);
+err_chrdev_unreg:
+	unregister_chrdev_region(dev_id, 1);
+	return -EFAULT;
+}
+
+static int adf_ctl_alloc_resources(struct adf_user_cfg_ctl_data **ctl_data,
+				   unsigned long arg)
+{
+	struct adf_user_cfg_ctl_data *cfg_data;
+
+	cfg_data = kzalloc(sizeof(*cfg_data), GFP_KERNEL);
+	if (!cfg_data)
+		return -ENOMEM;
+
+	/* Initialize device id to NO DEVICE as 0 is a valid device id */
+	cfg_data->device_id = ADF_CFG_NO_DEVICE;
+
+	if (copy_from_user(cfg_data, (void __user *)arg, sizeof(*cfg_data))) {
+		pr_err("QAT: failed to copy from user cfg_data.\n");
+		kfree(cfg_data);
+		return -EIO;
+	}
+
+	*ctl_data = cfg_data;
+	return 0;
+}
+
+static int adf_add_key_value_data(struct adf_accel_dev *accel_dev,
+				  const char *section,
+				  const struct adf_user_cfg_key_val *key_val)
+{
+	if (key_val->type == ADF_HEX) {
+		long *ptr = (long *)key_val->val;
+		long val = *ptr;
+
+		if (adf_cfg_add_key_value_param(accel_dev, section,
+						key_val->key, (void *)val,
+						key_val->type)) {
+			pr_err("QAT: failed to add keyvalue.\n");
+			return -EFAULT;
+		}
+	} else {
+		if (adf_cfg_add_key_value_param(accel_dev, section,
+						key_val->key, key_val->val,
+						key_val->type)) {
+			pr_err("QAT: failed to add keyvalue.\n");
+			return -EFAULT;
+		}
+	}
+	return 0;
+}
+
+static int adf_copy_key_value_data(struct adf_accel_dev *accel_dev,
+				   struct adf_user_cfg_ctl_data *ctl_data)
+{
+	struct adf_user_cfg_key_val key_val;
+	struct adf_user_cfg_key_val *params_head;
+	struct adf_user_cfg_section section, *section_head;
+
+	section_head = ctl_data->config_section;
+
+	while (section_head) {
+		if (copy_from_user(&section, (void __user *)section_head,
+				   sizeof(*section_head))) {
+			pr_err("QAT: failed to copy section info\n");
+			goto out_err;
+		}
+
+		if (adf_cfg_section_add(accel_dev, section.name)) {
+			pr_err("QAT: failed to add section.\n");
+			goto out_err;
+		}
+
+		params_head = section_head->params;
+
+		while (params_head) {
+			if (copy_from_user(&key_val, (void __user *)params_head,
+					   sizeof(key_val))) {
+				pr_err("QAT: Failed to copy keyvalue.\n");
+				goto out_err;
+			}
+			if (adf_add_key_value_data(accel_dev, section.name,
+						   &key_val)) {
+				goto out_err;
+			}
+			params_head = key_val.next;
+		}
+		section_head = section.next;
+	}
+	return 0;
+out_err:
+	adf_cfg_del_all(accel_dev);
+	return -EFAULT;
+}
+
+static int adf_ctl_ioctl_dev_config(struct file *fp, unsigned int cmd,
+				    unsigned long arg)
+{
+	int ret;
+	struct adf_user_cfg_ctl_data *ctl_data;
+	struct adf_accel_dev *accel_dev;
+
+	ret = adf_ctl_alloc_resources(&ctl_data, arg);
+	if (ret)
+		return ret;
+
+	accel_dev = adf_devmgr_get_dev_by_id(ctl_data->device_id);
+	if (!accel_dev) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (adf_dev_started(accel_dev)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (adf_copy_key_value_data(accel_dev, ctl_data)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
+out:
+	kfree(ctl_data);
+	return ret;
+}
+
+static int adf_ctl_is_device_in_use(int id)
+{
+	struct list_head *itr, *head = adf_devmgr_get_head();
+
+	list_for_each(itr, head) {
+		struct adf_accel_dev *dev =
+				list_entry(itr, struct adf_accel_dev, list);
+
+		if (id == dev->accel_id || id == ADF_CFG_ALL_DEVICES) {
+			if (adf_devmgr_in_reset(dev) || adf_dev_in_use(dev)) {
+				pr_info("QAT: device qat_dev%d is busy\n",
+					dev->accel_id);
+				return -EBUSY;
+			}
+		}
+	}
+	return 0;
+}
+
+static int adf_ctl_stop_devices(uint32_t id)
+{
+	struct list_head *itr, *head = adf_devmgr_get_head();
+	int ret = 0;
+
+	list_for_each(itr, head) {
+		struct adf_accel_dev *accel_dev =
+				list_entry(itr, struct adf_accel_dev, list);
+		if (id == accel_dev->accel_id || id == ADF_CFG_ALL_DEVICES) {
+			if (!adf_dev_started(accel_dev))
+				continue;
+
+			if (adf_dev_stop(accel_dev)) {
+				pr_err("QAT: Failed to stop qat_dev%d\n", id);
+				ret = -EFAULT;
+			}
+		}
+	}
+	return ret;
+}
+
+static int adf_ctl_ioctl_dev_stop(struct file *fp, unsigned int cmd,
+				  unsigned long arg)
+{
+	int ret;
+	struct adf_user_cfg_ctl_data *ctl_data;
+
+	ret = adf_ctl_alloc_resources(&ctl_data, arg);
+	if (ret)
+		return ret;
+
+	if (adf_devmgr_verify_id(ctl_data->device_id)) {
+		pr_err("QAT: Device %d not found\n", ctl_data->device_id);
+		ret = -ENODEV;
+		goto out;
+	}
+
+	ret = adf_ctl_is_device_in_use(ctl_data->device_id);
+	if (ret)
+		goto out;
+
+	if (ctl_data->device_id == ADF_CFG_ALL_DEVICES)
+		pr_info("QAT: Stopping all acceleration devices.\n");
+	else
+		pr_info("QAT: Stopping acceleration device qat_dev%d.\n",
+			ctl_data->device_id);
+
+	ret = adf_ctl_stop_devices(ctl_data->device_id);
+	if (ret)
+		pr_err("QAT: failed to stop device.\n");
+out:
+	kfree(ctl_data);
+	return ret;
+}
+
+static int adf_ctl_ioctl_dev_start(struct file *fp, unsigned int cmd,
+				   unsigned long arg)
+{
+	int ret;
+	struct adf_user_cfg_ctl_data *ctl_data;
+	struct adf_accel_dev *accel_dev;
+
+	ret = adf_ctl_alloc_resources(&ctl_data, arg);
+	if (ret)
+		return ret;
+
+	accel_dev = adf_devmgr_get_dev_by_id(ctl_data->device_id);
+	if (!accel_dev) {
+		pr_err("QAT: Device %d not found\n", ctl_data->device_id);
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (!adf_dev_started(accel_dev)) {
+		pr_info("QAT: Starting acceleration device qat_dev%d.\n",
+			ctl_data->device_id);
+		ret = adf_dev_start(accel_dev);
+	} else {
+		pr_info("QAT: Acceleration device qat_dev%d already started.\n",
+			ctl_data->device_id);
+	}
+	if (ret) {
+		pr_err("QAT: Failed to start qat_dev%d\n", ctl_data->device_id);
+		adf_dev_stop(accel_dev);
+	}
+out:
+	kfree(ctl_data);
+	return ret;
+}
+
+static int adf_ctl_ioctl_get_num_devices(struct file *fp, unsigned int cmd,
+					 unsigned long arg)
+{
+	uint32_t num_devices = 0;
+
+	adf_devmgr_get_num_dev(&num_devices);
+	if (copy_to_user((void __user *)arg, &num_devices, sizeof(num_devices)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int adf_ctl_ioctl_get_status(struct file *fp, unsigned int cmd,
+				    unsigned long arg)
+{
+	struct adf_hw_device_data *hw_data;
+	struct adf_dev_status_info dev_info;
+	struct adf_accel_dev *accel_dev;
+
+	if (copy_from_user(&dev_info, (void __user *)arg,
+			   sizeof(struct adf_dev_status_info))) {
+		pr_err("QAT: failed to copy from user.\n");
+		return -EFAULT;
+	}
+
+	accel_dev = adf_devmgr_get_dev_by_id(dev_info.accel_id);
+	if (!accel_dev) {
+		pr_err("QAT: Device %d not found\n", dev_info.accel_id);
+		return -ENODEV;
+	}
+	hw_data = accel_dev->hw_device;
+	dev_info.state = adf_dev_started(accel_dev) ? DEV_UP : DEV_DOWN;
+	dev_info.num_ae = hw_data->get_num_aes(hw_data);
+	dev_info.num_accel = hw_data->get_num_accels(hw_data);
+	dev_info.num_logical_accel = hw_data->num_logical_accel;
+	dev_info.banks_per_accel = hw_data->num_banks
+					/ hw_data->num_logical_accel;
+	strlcpy(dev_info.name, hw_data->dev_class->name, sizeof(dev_info.name));
+	dev_info.instance_id = hw_data->instance_id;
+	dev_info.type = hw_data->dev_class->type;
+	dev_info.bus = accel_to_pci_dev(accel_dev)->bus->number;
+	dev_info.dev = PCI_SLOT(accel_to_pci_dev(accel_dev)->devfn);
+	dev_info.fun = PCI_FUNC(accel_to_pci_dev(accel_dev)->devfn);
+
+	if (copy_to_user((void __user *)arg, &dev_info,
+			 sizeof(struct adf_dev_status_info))) {
+		pr_err("QAT: failed to copy status.\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static long adf_ctl_ioctl(struct file *fp, unsigned int cmd, unsigned long arg)
+{
+	int ret;
+
+	if (mutex_lock_interruptible(&adf_ctl_lock))
+		return -EFAULT;
+
+	switch (cmd) {
+	case IOCTL_CONFIG_SYS_RESOURCE_PARAMETERS:
+		ret = adf_ctl_ioctl_dev_config(fp, cmd, arg);
+		break;
+
+	case IOCTL_STOP_ACCEL_DEV:
+		ret = adf_ctl_ioctl_dev_stop(fp, cmd, arg);
+		break;
+
+	case IOCTL_START_ACCEL_DEV:
+		ret = adf_ctl_ioctl_dev_start(fp, cmd, arg);
+		break;
+
+	case IOCTL_GET_NUM_DEVICES:
+		ret = adf_ctl_ioctl_get_num_devices(fp, cmd, arg);
+		break;
+
+	case IOCTL_STATUS_ACCEL_DEV:
+		ret = adf_ctl_ioctl_get_status(fp, cmd, arg);
+		break;
+	default:
+		pr_err("QAT: Invalid ioclt\n");
+		ret = -EFAULT;
+		break;
+	}
+	mutex_unlock(&adf_ctl_lock);
+	return ret;
+}
+
+static int __init adf_register_ctl_device_driver(void)
+{
+	mutex_init(&adf_ctl_lock);
+
+	if (qat_algs_init())
+		goto err_algs_init;
+
+	if (adf_chr_drv_create())
+		goto err_chr_dev;
+
+	if (adf_init_aer())
+		goto err_aer;
+
+	if (qat_crypto_register())
+		goto err_crypto_register;
+
+	return 0;
+
+err_crypto_register:
+	adf_exit_aer();
+err_aer:
+	adf_chr_drv_destroy();
+err_chr_dev:
+	qat_algs_exit();
+err_algs_init:
+	mutex_destroy(&adf_ctl_lock);
+	return -EFAULT;
+}
+
+static void __exit adf_unregister_ctl_device_driver(void)
+{
+	adf_chr_drv_destroy();
+	adf_exit_aer();
+	qat_crypto_unregister();
+	qat_algs_exit();
+	mutex_destroy(&adf_ctl_lock);
+}
+
+module_init(adf_register_ctl_device_driver);
+module_exit(adf_unregister_ctl_device_driver);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel");
+MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
+MODULE_ALIAS("intel_qat");
diff --git a/drivers/crypto/qat/qat_common/adf_dev_mgr.c b/drivers/crypto/qat/qat_common/adf_dev_mgr.c
new file mode 100644
index 00000000000..ae71555c086
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_dev_mgr.c
@@ -0,0 +1,215 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include "adf_cfg.h"
+#include "adf_common_drv.h"
+
+static LIST_HEAD(accel_table);
+static DEFINE_MUTEX(table_lock);
+static uint32_t num_devices;
+
+/**
+ * adf_devmgr_add_dev() - Add accel_dev to the acceleration framework
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function adds acceleration device to the acceleration framework.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_devmgr_add_dev(struct adf_accel_dev *accel_dev)
+{
+	struct list_head *itr;
+
+	if (num_devices == ADF_MAX_DEVICES) {
+		pr_err("QAT: Only support up to %d devices\n", ADF_MAX_DEVICES);
+		return -EFAULT;
+	}
+
+	mutex_lock(&table_lock);
+	list_for_each(itr, &accel_table) {
+		struct adf_accel_dev *ptr =
+				list_entry(itr, struct adf_accel_dev, list);
+
+		if (ptr == accel_dev) {
+			mutex_unlock(&table_lock);
+			return -EEXIST;
+		}
+	}
+	atomic_set(&accel_dev->ref_count, 0);
+	list_add_tail(&accel_dev->list, &accel_table);
+	accel_dev->accel_id = num_devices++;
+	mutex_unlock(&table_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_devmgr_add_dev);
+
+struct list_head *adf_devmgr_get_head(void)
+{
+	return &accel_table;
+}
+
+/**
+ * adf_devmgr_rm_dev() - Remove accel_dev from the acceleration framework.
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function removes acceleration device from the acceleration framework.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: void
+ */
+void adf_devmgr_rm_dev(struct adf_accel_dev *accel_dev)
+{
+	mutex_lock(&table_lock);
+	list_del(&accel_dev->list);
+	num_devices--;
+	mutex_unlock(&table_lock);
+}
+EXPORT_SYMBOL_GPL(adf_devmgr_rm_dev);
+
+struct adf_accel_dev *adf_devmgr_get_first(void)
+{
+	struct adf_accel_dev *dev = NULL;
+
+	if (!list_empty(&accel_table))
+		dev = list_first_entry(&accel_table, struct adf_accel_dev,
+				       list);
+	return dev;
+}
+
+/**
+ * adf_devmgr_pci_to_accel_dev() - Get accel_dev associated with the pci_dev.
+ * @accel_dev:  Pointer to pci device.
+ *
+ * Function returns acceleration device associated with the given pci device.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: pinter to accel_dev or NULL if not found.
+ */
+struct adf_accel_dev *adf_devmgr_pci_to_accel_dev(struct pci_dev *pci_dev)
+{
+	struct list_head *itr;
+
+	list_for_each(itr, &accel_table) {
+		struct adf_accel_dev *ptr =
+				list_entry(itr, struct adf_accel_dev, list);
+
+		if (ptr->accel_pci_dev.pci_dev == pci_dev) {
+			mutex_unlock(&table_lock);
+			return ptr;
+		}
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(adf_devmgr_pci_to_accel_dev);
+
+struct adf_accel_dev *adf_devmgr_get_dev_by_id(uint32_t id)
+{
+	struct list_head *itr;
+
+	list_for_each(itr, &accel_table) {
+		struct adf_accel_dev *ptr =
+				list_entry(itr, struct adf_accel_dev, list);
+
+		if (ptr->accel_id == id) {
+			mutex_unlock(&table_lock);
+			return ptr;
+		}
+	}
+	return NULL;
+}
+
+int adf_devmgr_verify_id(uint32_t id)
+{
+	if (id == ADF_CFG_ALL_DEVICES)
+		return 0;
+
+	if (adf_devmgr_get_dev_by_id(id))
+		return 0;
+
+	return -ENODEV;
+}
+
+void adf_devmgr_get_num_dev(uint32_t *num)
+{
+	struct list_head *itr;
+
+	*num = 0;
+	list_for_each(itr, &accel_table) {
+		(*num)++;
+	}
+}
+
+int adf_dev_in_use(struct adf_accel_dev *accel_dev)
+{
+	return atomic_read(&accel_dev->ref_count) != 0;
+}
+
+int adf_dev_get(struct adf_accel_dev *accel_dev)
+{
+	if (atomic_add_return(1, &accel_dev->ref_count) == 1)
+		if (!try_module_get(accel_dev->owner))
+			return -EFAULT;
+	return 0;
+}
+
+void adf_dev_put(struct adf_accel_dev *accel_dev)
+{
+	if (atomic_sub_return(1, &accel_dev->ref_count) == 0)
+		module_put(accel_dev->owner);
+}
+
+int adf_devmgr_in_reset(struct adf_accel_dev *accel_dev)
+{
+	return test_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
+}
+
+int adf_dev_started(struct adf_accel_dev *accel_dev)
+{
+	return test_bit(ADF_STATUS_STARTED, &accel_dev->status);
+}
diff --git a/drivers/crypto/qat/qat_common/adf_init.c b/drivers/crypto/qat/qat_common/adf_init.c
new file mode 100644
index 00000000000..5c0e47a00a8
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_init.c
@@ -0,0 +1,388 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include "adf_accel_devices.h"
+#include "adf_cfg.h"
+#include "adf_common_drv.h"
+
+static LIST_HEAD(service_table);
+static DEFINE_MUTEX(service_lock);
+
+static void adf_service_add(struct service_hndl *service)
+{
+	mutex_lock(&service_lock);
+	list_add(&service->list, &service_table);
+	mutex_unlock(&service_lock);
+}
+
+/**
+ * adf_service_register() - Register acceleration service in the accel framework
+ * @service:    Pointer to the service
+ *
+ * Function adds the acceleration service to the acceleration framework.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_service_register(struct service_hndl *service)
+{
+	service->init_status = 0;
+	service->start_status = 0;
+	adf_service_add(service);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_service_register);
+
+static void adf_service_remove(struct service_hndl *service)
+{
+	mutex_lock(&service_lock);
+	list_del(&service->list);
+	mutex_unlock(&service_lock);
+}
+
+/**
+ * adf_service_unregister() - Unregister acceleration service from the framework
+ * @service:    Pointer to the service
+ *
+ * Function remove the acceleration service from the acceleration framework.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_service_unregister(struct service_hndl *service)
+{
+	if (service->init_status || service->start_status) {
+		pr_err("QAT: Could not remove active service\n");
+		return -EFAULT;
+	}
+	adf_service_remove(service);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_service_unregister);
+
+/**
+ * adf_dev_start() - Start acceleration service for the given accel device
+ * @accel_dev:    Pointer to acceleration device.
+ *
+ * Function notifies all the registered services that the acceleration device
+ * is ready to be used.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_dev_start(struct adf_accel_dev *accel_dev)
+{
+	struct service_hndl *service;
+	struct list_head *list_itr;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+
+	if (!test_bit(ADF_STATUS_CONFIGURED, &accel_dev->status)) {
+		pr_info("QAT: Device not configured\n");
+		return -EFAULT;
+	}
+	set_bit(ADF_STATUS_STARTING, &accel_dev->status);
+
+	if (adf_ae_init(accel_dev)) {
+		pr_err("QAT: Failed to initialise Acceleration Engine\n");
+		return -EFAULT;
+	}
+	set_bit(ADF_STATUS_AE_INITIALISED, &accel_dev->status);
+
+	if (adf_ae_fw_load(accel_dev)) {
+		pr_err("QAT: Failed to load acceleration FW\n");
+		adf_ae_fw_release(accel_dev);
+		return -EFAULT;
+	}
+	set_bit(ADF_STATUS_AE_UCODE_LOADED, &accel_dev->status);
+
+	if (hw_data->alloc_irq(accel_dev)) {
+		pr_err("QAT: Failed to allocate interrupts\n");
+		return -EFAULT;
+	}
+	set_bit(ADF_STATUS_IRQ_ALLOCATED, &accel_dev->status);
+
+	/*
+	 * Subservice initialisation is divided into two stages: init and start.
+	 * This is to facilitate any ordering dependencies between services
+	 * prior to starting any of the accelerators.
+	 */
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (!service->admin)
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_INIT)) {
+			pr_err("QAT: Failed to initialise service %s\n",
+			       service->name);
+			return -EFAULT;
+		}
+		set_bit(accel_dev->accel_id, &service->init_status);
+	}
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (service->admin)
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_INIT)) {
+			pr_err("QAT: Failed to initialise service %s\n",
+			       service->name);
+			return -EFAULT;
+		}
+		set_bit(accel_dev->accel_id, &service->init_status);
+	}
+
+	hw_data->enable_error_correction(accel_dev);
+
+	if (adf_ae_start(accel_dev)) {
+		pr_err("QAT: AE Start Failed\n");
+		return -EFAULT;
+	}
+	set_bit(ADF_STATUS_AE_STARTED, &accel_dev->status);
+
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (!service->admin)
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_START)) {
+			pr_err("QAT: Failed to start service %s\n",
+			       service->name);
+			return -EFAULT;
+		}
+		set_bit(accel_dev->accel_id, &service->start_status);
+	}
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (service->admin)
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_START)) {
+			pr_err("QAT: Failed to start service %s\n",
+			       service->name);
+			return -EFAULT;
+		}
+		set_bit(accel_dev->accel_id, &service->start_status);
+	}
+
+	clear_bit(ADF_STATUS_STARTING, &accel_dev->status);
+	set_bit(ADF_STATUS_STARTED, &accel_dev->status);
+
+	if (qat_algs_register()) {
+		pr_err("QAT: Failed to register crypto algs\n");
+		set_bit(ADF_STATUS_STARTING, &accel_dev->status);
+		clear_bit(ADF_STATUS_STARTED, &accel_dev->status);
+		return -EFAULT;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_dev_start);
+
+/**
+ * adf_dev_stop() - Stop acceleration service for the given accel device
+ * @accel_dev:    Pointer to acceleration device.
+ *
+ * Function notifies all the registered services that the acceleration device
+ * is shuting down.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_dev_stop(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct service_hndl *service;
+	struct list_head *list_itr;
+	int ret, wait = 0;
+
+	if (!adf_dev_started(accel_dev) &&
+	    !test_bit(ADF_STATUS_STARTING, &accel_dev->status)) {
+		return 0;
+	}
+	clear_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
+	clear_bit(ADF_STATUS_STARTING, &accel_dev->status);
+	clear_bit(ADF_STATUS_STARTED, &accel_dev->status);
+
+	if (qat_algs_unregister())
+		pr_err("QAT: Failed to unregister crypto algs\n");
+
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (service->admin)
+			continue;
+		if (!test_bit(accel_dev->accel_id, &service->start_status))
+			continue;
+		ret = service->event_hld(accel_dev, ADF_EVENT_STOP);
+		if (!ret) {
+			clear_bit(accel_dev->accel_id, &service->start_status);
+		} else if (ret == -EAGAIN) {
+			wait = 1;
+			clear_bit(accel_dev->accel_id, &service->start_status);
+		}
+	}
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (!service->admin)
+			continue;
+		if (!test_bit(accel_dev->accel_id, &service->start_status))
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_STOP))
+			pr_err("QAT: Failed to shutdown service %s\n",
+			       service->name);
+		else
+			clear_bit(accel_dev->accel_id, &service->start_status);
+	}
+
+	if (wait)
+		msleep(100);
+
+	if (adf_dev_started(accel_dev)) {
+		if (adf_ae_stop(accel_dev))
+			pr_err("QAT: failed to stop AE\n");
+		else
+			clear_bit(ADF_STATUS_AE_STARTED, &accel_dev->status);
+	}
+
+	if (test_bit(ADF_STATUS_AE_UCODE_LOADED, &accel_dev->status)) {
+		if (adf_ae_fw_release(accel_dev))
+			pr_err("QAT: Failed to release the ucode\n");
+		else
+			clear_bit(ADF_STATUS_AE_UCODE_LOADED,
+				  &accel_dev->status);
+	}
+
+	if (test_bit(ADF_STATUS_AE_INITIALISED, &accel_dev->status)) {
+		if (adf_ae_shutdown(accel_dev))
+			pr_err("QAT: Failed to shutdown Accel Engine\n");
+		else
+			clear_bit(ADF_STATUS_AE_INITIALISED,
+				  &accel_dev->status);
+	}
+
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (service->admin)
+			continue;
+		if (!test_bit(accel_dev->accel_id, &service->init_status))
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_SHUTDOWN))
+			pr_err("QAT: Failed to shutdown service %s\n",
+			       service->name);
+		else
+			clear_bit(accel_dev->accel_id, &service->init_status);
+	}
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (!service->admin)
+			continue;
+		if (!test_bit(accel_dev->accel_id, &service->init_status))
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_SHUTDOWN))
+			pr_err("QAT: Failed to shutdown service %s\n",
+			       service->name);
+		else
+			clear_bit(accel_dev->accel_id, &service->init_status);
+	}
+
+	if (test_bit(ADF_STATUS_IRQ_ALLOCATED, &accel_dev->status)) {
+		hw_data->free_irq(accel_dev);
+		clear_bit(ADF_STATUS_IRQ_ALLOCATED, &accel_dev->status);
+	}
+
+	/* Delete configuration only if not restarting */
+	if (!test_bit(ADF_STATUS_RESTARTING, &accel_dev->status))
+		adf_cfg_del_all(accel_dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(adf_dev_stop);
+
+int adf_dev_restarting_notify(struct adf_accel_dev *accel_dev)
+{
+	struct service_hndl *service;
+	struct list_head *list_itr;
+
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (service->admin)
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_RESTARTING))
+			pr_err("QAT: Failed to restart service %s.\n",
+			       service->name);
+	}
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (!service->admin)
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_RESTARTING))
+			pr_err("QAT: Failed to restart service %s.\n",
+			       service->name);
+	}
+	return 0;
+}
+
+int adf_dev_restarted_notify(struct adf_accel_dev *accel_dev)
+{
+	struct service_hndl *service;
+	struct list_head *list_itr;
+
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (service->admin)
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_RESTARTED))
+			pr_err("QAT: Failed to restart service %s.\n",
+			       service->name);
+	}
+	list_for_each(list_itr, &service_table) {
+		service = list_entry(list_itr, struct service_hndl, list);
+		if (!service->admin)
+			continue;
+		if (service->event_hld(accel_dev, ADF_EVENT_RESTARTED))
+			pr_err("QAT: Failed to restart service %s.\n",
+			       service->name);
+	}
+	return 0;
+}
diff --git a/drivers/crypto/qat/qat_common/adf_transport.c b/drivers/crypto/qat/qat_common/adf_transport.c
new file mode 100644
index 00000000000..5f3fa45348b
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_transport.c
@@ -0,0 +1,567 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/delay.h>
+#include "adf_accel_devices.h"
+#include "adf_transport_internal.h"
+#include "adf_transport_access_macros.h"
+#include "adf_cfg.h"
+#include "adf_common_drv.h"
+
+static inline uint32_t adf_modulo(uint32_t data, uint32_t shift)
+{
+	uint32_t div = data >> shift;
+	uint32_t mult = div << shift;
+
+	return data - mult;
+}
+
+static inline int adf_check_ring_alignment(uint64_t addr, uint64_t size)
+{
+	if (((size - 1) & addr) != 0)
+		return -EFAULT;
+	return 0;
+}
+
+static int adf_verify_ring_size(uint32_t msg_size, uint32_t msg_num)
+{
+	int i = ADF_MIN_RING_SIZE;
+
+	for (; i <= ADF_MAX_RING_SIZE; i++)
+		if ((msg_size * msg_num) == ADF_SIZE_TO_RING_SIZE_IN_BYTES(i))
+			return i;
+
+	return ADF_DEFAULT_RING_SIZE;
+}
+
+static int adf_reserve_ring(struct adf_etr_bank_data *bank, uint32_t ring)
+{
+	spin_lock(&bank->lock);
+	if (bank->ring_mask & (1 << ring)) {
+		spin_unlock(&bank->lock);
+		return -EFAULT;
+	}
+	bank->ring_mask |= (1 << ring);
+	spin_unlock(&bank->lock);
+	return 0;
+}
+
+static void adf_unreserve_ring(struct adf_etr_bank_data *bank, uint32_t ring)
+{
+	spin_lock(&bank->lock);
+	bank->ring_mask &= ~(1 << ring);
+	spin_unlock(&bank->lock);
+}
+
+static void adf_enable_ring_irq(struct adf_etr_bank_data *bank, uint32_t ring)
+{
+	spin_lock_bh(&bank->lock);
+	bank->irq_mask |= (1 << ring);
+	spin_unlock_bh(&bank->lock);
+	WRITE_CSR_INT_COL_EN(bank->csr_addr, bank->bank_number, bank->irq_mask);
+	WRITE_CSR_INT_COL_CTL(bank->csr_addr, bank->bank_number,
+			      bank->irq_coalesc_timer);
+}
+
+static void adf_disable_ring_irq(struct adf_etr_bank_data *bank, uint32_t ring)
+{
+	spin_lock_bh(&bank->lock);
+	bank->irq_mask &= ~(1 << ring);
+	spin_unlock_bh(&bank->lock);
+	WRITE_CSR_INT_COL_EN(bank->csr_addr, bank->bank_number, bank->irq_mask);
+}
+
+int adf_send_message(struct adf_etr_ring_data *ring, uint32_t *msg)
+{
+	if (atomic_add_return(1, ring->inflights) >
+	    ADF_MAX_INFLIGHTS(ring->ring_size, ring->msg_size)) {
+		atomic_dec(ring->inflights);
+		return -EAGAIN;
+	}
+	spin_lock_bh(&ring->lock);
+	memcpy(ring->base_addr + ring->tail, msg,
+	       ADF_MSG_SIZE_TO_BYTES(ring->msg_size));
+
+	ring->tail = adf_modulo(ring->tail +
+				ADF_MSG_SIZE_TO_BYTES(ring->msg_size),
+				ADF_RING_SIZE_MODULO(ring->ring_size));
+	WRITE_CSR_RING_TAIL(ring->bank->csr_addr, ring->bank->bank_number,
+			    ring->ring_number, ring->tail);
+	spin_unlock_bh(&ring->lock);
+	return 0;
+}
+
+static int adf_handle_response(struct adf_etr_ring_data *ring)
+{
+	uint32_t msg_counter = 0;
+	uint32_t *msg = (uint32_t *)(ring->base_addr + ring->head);
+
+	while (*msg != ADF_RING_EMPTY_SIG) {
+		ring->callback((uint32_t *)msg);
+		*msg = ADF_RING_EMPTY_SIG;
+		ring->head = adf_modulo(ring->head +
+					ADF_MSG_SIZE_TO_BYTES(ring->msg_size),
+					ADF_RING_SIZE_MODULO(ring->ring_size));
+		msg_counter++;
+		msg = (uint32_t *)(ring->base_addr + ring->head);
+	}
+	if (msg_counter > 0) {
+		WRITE_CSR_RING_HEAD(ring->bank->csr_addr,
+				    ring->bank->bank_number,
+				    ring->ring_number, ring->head);
+		atomic_sub(msg_counter, ring->inflights);
+	}
+	return 0;
+}
+
+static void adf_configure_tx_ring(struct adf_etr_ring_data *ring)
+{
+	uint32_t ring_config = BUILD_RING_CONFIG(ring->ring_size);
+
+	WRITE_CSR_RING_CONFIG(ring->bank->csr_addr, ring->bank->bank_number,
+			      ring->ring_number, ring_config);
+}
+
+static void adf_configure_rx_ring(struct adf_etr_ring_data *ring)
+{
+	uint32_t ring_config =
+			BUILD_RESP_RING_CONFIG(ring->ring_size,
+					       ADF_RING_NEAR_WATERMARK_512,
+					       ADF_RING_NEAR_WATERMARK_0);
+
+	WRITE_CSR_RING_CONFIG(ring->bank->csr_addr, ring->bank->bank_number,
+			      ring->ring_number, ring_config);
+}
+
+static int adf_init_ring(struct adf_etr_ring_data *ring)
+{
+	struct adf_etr_bank_data *bank = ring->bank;
+	struct adf_accel_dev *accel_dev = bank->accel_dev;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	uint64_t ring_base;
+	uint32_t ring_size_bytes =
+			ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size);
+
+	ring_size_bytes = ADF_RING_SIZE_BYTES_MIN(ring_size_bytes);
+	ring->base_addr = dma_alloc_coherent(&GET_DEV(accel_dev),
+					     ring_size_bytes, &ring->dma_addr,
+					     GFP_KERNEL);
+	if (!ring->base_addr)
+		return -ENOMEM;
+
+	memset(ring->base_addr, 0x7F, ring_size_bytes);
+	/* The base_addr has to be aligned to the size of the buffer */
+	if (adf_check_ring_alignment(ring->dma_addr, ring_size_bytes)) {
+		pr_err("QAT: Ring address not aligned\n");
+		dma_free_coherent(&GET_DEV(accel_dev), ring_size_bytes,
+				  ring->base_addr, ring->dma_addr);
+		return -EFAULT;
+	}
+
+	if (hw_data->tx_rings_mask & (1 << ring->ring_number))
+		adf_configure_tx_ring(ring);
+
+	else
+		adf_configure_rx_ring(ring);
+
+	ring_base = BUILD_RING_BASE_ADDR(ring->dma_addr, ring->ring_size);
+	WRITE_CSR_RING_BASE(ring->bank->csr_addr, ring->bank->bank_number,
+			    ring->ring_number, ring_base);
+	spin_lock_init(&ring->lock);
+	return 0;
+}
+
+static void adf_cleanup_ring(struct adf_etr_ring_data *ring)
+{
+	uint32_t ring_size_bytes =
+			ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size);
+	ring_size_bytes = ADF_RING_SIZE_BYTES_MIN(ring_size_bytes);
+
+	if (ring->base_addr) {
+		memset(ring->base_addr, 0x7F, ring_size_bytes);
+		dma_free_coherent(&GET_DEV(ring->bank->accel_dev),
+				  ring_size_bytes, ring->base_addr,
+				  ring->dma_addr);
+	}
+}
+
+int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section,
+		    uint32_t bank_num, uint32_t num_msgs,
+		    uint32_t msg_size, const char *ring_name,
+		    adf_callback_fn callback, int poll_mode,
+		    struct adf_etr_ring_data **ring_ptr)
+{
+	struct adf_etr_data *transport_data = accel_dev->transport;
+	struct adf_etr_bank_data *bank;
+	struct adf_etr_ring_data *ring;
+	char val[ADF_CFG_MAX_VAL_LEN_IN_BYTES];
+	uint32_t ring_num;
+	int ret;
+
+	if (bank_num >= GET_MAX_BANKS(accel_dev)) {
+		pr_err("QAT: Invalid bank number\n");
+		return -EFAULT;
+	}
+	if (msg_size > ADF_MSG_SIZE_TO_BYTES(ADF_MAX_MSG_SIZE)) {
+		pr_err("QAT: Invalid msg size\n");
+		return -EFAULT;
+	}
+	if (ADF_MAX_INFLIGHTS(adf_verify_ring_size(msg_size, num_msgs),
+			      ADF_BYTES_TO_MSG_SIZE(msg_size)) < 2) {
+		pr_err("QAT: Invalid ring size for given msg size\n");
+		return -EFAULT;
+	}
+	if (adf_cfg_get_param_value(accel_dev, section, ring_name, val)) {
+		pr_err("QAT: Section %s, no such entry : %s\n",
+		       section, ring_name);
+		return -EFAULT;
+	}
+	if (kstrtouint(val, 10, &ring_num)) {
+		pr_err("QAT: Can't get ring number\n");
+		return -EFAULT;
+	}
+
+	bank = &transport_data->banks[bank_num];
+	if (adf_reserve_ring(bank, ring_num)) {
+		pr_err("QAT: Ring %d, %s already exists.\n",
+		       ring_num, ring_name);
+		return -EFAULT;
+	}
+	ring = &bank->rings[ring_num];
+	ring->ring_number = ring_num;
+	ring->bank = bank;
+	ring->callback = callback;
+	ring->msg_size = ADF_BYTES_TO_MSG_SIZE(msg_size);
+	ring->ring_size = adf_verify_ring_size(msg_size, num_msgs);
+	ring->head = 0;
+	ring->tail = 0;
+	atomic_set(ring->inflights, 0);
+	ret = adf_init_ring(ring);
+	if (ret)
+		goto err;
+
+	/* Enable HW arbitration for the given ring */
+	accel_dev->hw_device->hw_arb_ring_enable(ring);
+
+	if (adf_ring_debugfs_add(ring, ring_name)) {
+		pr_err("QAT: Couldn't add ring debugfs entry\n");
+		ret = -EFAULT;
+		goto err;
+	}
+
+	/* Enable interrupts if needed */
+	if (callback && (!poll_mode))
+		adf_enable_ring_irq(bank, ring->ring_number);
+	*ring_ptr = ring;
+	return 0;
+err:
+	adf_cleanup_ring(ring);
+	adf_unreserve_ring(bank, ring_num);
+	accel_dev->hw_device->hw_arb_ring_disable(ring);
+	return ret;
+}
+
+void adf_remove_ring(struct adf_etr_ring_data *ring)
+{
+	struct adf_etr_bank_data *bank = ring->bank;
+	struct adf_accel_dev *accel_dev = bank->accel_dev;
+
+	/* Disable interrupts for the given ring */
+	adf_disable_ring_irq(bank, ring->ring_number);
+
+	/* Clear PCI config space */
+	WRITE_CSR_RING_CONFIG(bank->csr_addr, bank->bank_number,
+			      ring->ring_number, 0);
+	WRITE_CSR_RING_BASE(bank->csr_addr, bank->bank_number,
+			    ring->ring_number, 0);
+	adf_ring_debugfs_rm(ring);
+	adf_unreserve_ring(bank, ring->ring_number);
+	/* Disable HW arbitration for the given ring */
+	accel_dev->hw_device->hw_arb_ring_disable(ring);
+	adf_cleanup_ring(ring);
+}
+
+static void adf_ring_response_handler(struct adf_etr_bank_data *bank)
+{
+	uint32_t empty_rings, i;
+
+	empty_rings = READ_CSR_E_STAT(bank->csr_addr, bank->bank_number);
+	empty_rings = ~empty_rings & bank->irq_mask;
+
+	for (i = 0; i < ADF_ETR_MAX_RINGS_PER_BANK; ++i) {
+		if (empty_rings & (1 << i))
+			adf_handle_response(&bank->rings[i]);
+	}
+}
+
+/**
+ * adf_response_handler() - Bottom half handler response handler
+ * @bank_addr:  Address of a ring bank for with the BH was scheduled.
+ *
+ * Function is the bottom half handler for the response from acceleration
+ * device. There is one handler for every ring bank. Function checks all
+ * communication rings in the bank.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: void
+ */
+void adf_response_handler(unsigned long bank_addr)
+{
+	struct adf_etr_bank_data *bank = (void *)bank_addr;
+
+	/* Handle all the responses nad reenable IRQs */
+	adf_ring_response_handler(bank);
+	WRITE_CSR_INT_FLAG_AND_COL(bank->csr_addr, bank->bank_number,
+				   bank->irq_mask);
+}
+EXPORT_SYMBOL_GPL(adf_response_handler);
+
+static inline int adf_get_cfg_int(struct adf_accel_dev *accel_dev,
+				  const char *section, const char *format,
+				  uint32_t key, uint32_t *value)
+{
+	char key_buf[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	char val_buf[ADF_CFG_MAX_VAL_LEN_IN_BYTES];
+
+	snprintf(key_buf, ADF_CFG_MAX_KEY_LEN_IN_BYTES, format, key);
+
+	if (adf_cfg_get_param_value(accel_dev, section, key_buf, val_buf))
+		return -EFAULT;
+
+	if (kstrtouint(val_buf, 10, value))
+		return -EFAULT;
+	return 0;
+}
+
+static void adf_enable_coalesc(struct adf_etr_bank_data *bank,
+			       const char *section, uint32_t bank_num_in_accel)
+{
+	if (adf_get_cfg_int(bank->accel_dev, section,
+			    ADF_ETRMGR_COALESCE_TIMER_FORMAT,
+			    bank_num_in_accel, &bank->irq_coalesc_timer))
+		bank->irq_coalesc_timer = ADF_COALESCING_DEF_TIME;
+
+	if (ADF_COALESCING_MAX_TIME < bank->irq_coalesc_timer ||
+	    ADF_COALESCING_MIN_TIME > bank->irq_coalesc_timer)
+		bank->irq_coalesc_timer = ADF_COALESCING_DEF_TIME;
+}
+
+static int adf_init_bank(struct adf_accel_dev *accel_dev,
+			 struct adf_etr_bank_data *bank,
+			 uint32_t bank_num, void __iomem *csr_addr)
+{
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_etr_ring_data *ring;
+	struct adf_etr_ring_data *tx_ring;
+	uint32_t i, coalesc_enabled;
+
+	memset(bank, 0, sizeof(*bank));
+	bank->bank_number = bank_num;
+	bank->csr_addr = csr_addr;
+	bank->accel_dev = accel_dev;
+	spin_lock_init(&bank->lock);
+
+	/* Enable IRQ coalescing always. This will allow to use
+	 * the optimised flag and coalesc register.
+	 * If it is disabled in the config file just use min time value */
+	if (adf_get_cfg_int(accel_dev, "Accelerator0",
+			    ADF_ETRMGR_COALESCING_ENABLED_FORMAT,
+			    bank_num, &coalesc_enabled) && coalesc_enabled)
+		adf_enable_coalesc(bank, "Accelerator0", bank_num);
+	else
+		bank->irq_coalesc_timer = ADF_COALESCING_MIN_TIME;
+
+	for (i = 0; i < ADF_ETR_MAX_RINGS_PER_BANK; i++) {
+		WRITE_CSR_RING_CONFIG(csr_addr, bank_num, i, 0);
+		WRITE_CSR_RING_BASE(csr_addr, bank_num, i, 0);
+		ring = &bank->rings[i];
+		if (hw_data->tx_rings_mask & (1 << i)) {
+			ring->inflights = kzalloc_node(sizeof(atomic_t),
+						       GFP_KERNEL,
+						       accel_dev->numa_node);
+			if (!ring->inflights)
+				goto err;
+		} else {
+			if (i < hw_data->tx_rx_gap) {
+				pr_err("QAT: Invalid tx rings mask config\n");
+				goto err;
+			}
+			tx_ring = &bank->rings[i - hw_data->tx_rx_gap];
+			ring->inflights = tx_ring->inflights;
+		}
+	}
+	if (adf_bank_debugfs_add(bank)) {
+		pr_err("QAT: Failed to add bank debugfs entry\n");
+		goto err;
+	}
+
+	WRITE_CSR_INT_SRCSEL(csr_addr, bank_num);
+	return 0;
+err:
+	for (i = 0; i < ADF_ETR_MAX_RINGS_PER_BANK; i++) {
+		ring = &bank->rings[i];
+		if (hw_data->tx_rings_mask & (1 << i) && ring->inflights)
+			kfree(ring->inflights);
+	}
+	return -ENOMEM;
+}
+
+/**
+ * adf_init_etr_data() - Initialize transport rings for acceleration device
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function is the initializes the communications channels (rings) to the
+ * acceleration device accel_dev.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: 0 on success, error code othewise.
+ */
+int adf_init_etr_data(struct adf_accel_dev *accel_dev)
+{
+	struct adf_etr_data *etr_data;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	void __iomem *csr_addr;
+	uint32_t size;
+	uint32_t num_banks = 0;
+	int i, ret;
+
+	etr_data = kzalloc_node(sizeof(*etr_data), GFP_KERNEL,
+				accel_dev->numa_node);
+	if (!etr_data)
+		return -ENOMEM;
+
+	num_banks = GET_MAX_BANKS(accel_dev);
+	size = num_banks * sizeof(struct adf_etr_bank_data);
+	etr_data->banks = kzalloc_node(size, GFP_KERNEL, accel_dev->numa_node);
+	if (!etr_data->banks) {
+		ret = -ENOMEM;
+		goto err_bank;
+	}
+
+	accel_dev->transport = etr_data;
+	i = hw_data->get_etr_bar_id(hw_data);
+	csr_addr = accel_dev->accel_pci_dev.pci_bars[i].virt_addr;
+
+	/* accel_dev->debugfs_dir should always be non-NULL here */
+	etr_data->debug = debugfs_create_dir("transport",
+					     accel_dev->debugfs_dir);
+	if (!etr_data->debug) {
+		pr_err("QAT: Unable to create transport debugfs entry\n");
+		ret = -ENOENT;
+		goto err_bank_debug;
+	}
+
+	for (i = 0; i < num_banks; i++) {
+		ret = adf_init_bank(accel_dev, &etr_data->banks[i], i,
+				    csr_addr);
+		if (ret)
+			goto err_bank_all;
+	}
+
+	return 0;
+
+err_bank_all:
+	debugfs_remove(etr_data->debug);
+err_bank_debug:
+	kfree(etr_data->banks);
+err_bank:
+	kfree(etr_data);
+	accel_dev->transport = NULL;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(adf_init_etr_data);
+
+static void cleanup_bank(struct adf_etr_bank_data *bank)
+{
+	uint32_t i;
+
+	for (i = 0; i < ADF_ETR_MAX_RINGS_PER_BANK; i++) {
+		struct adf_accel_dev *accel_dev = bank->accel_dev;
+		struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+		struct adf_etr_ring_data *ring = &bank->rings[i];
+
+		if (bank->ring_mask & (1 << i))
+			adf_cleanup_ring(ring);
+
+		if (hw_data->tx_rings_mask & (1 << i))
+			kfree(ring->inflights);
+	}
+	adf_bank_debugfs_rm(bank);
+	memset(bank, 0, sizeof(*bank));
+}
+
+static void adf_cleanup_etr_handles(struct adf_accel_dev *accel_dev)
+{
+	struct adf_etr_data *etr_data = accel_dev->transport;
+	uint32_t i, num_banks = GET_MAX_BANKS(accel_dev);
+
+	for (i = 0; i < num_banks; i++)
+		cleanup_bank(&etr_data->banks[i]);
+}
+
+/**
+ * adf_cleanup_etr_data() - Clear transport rings for acceleration device
+ * @accel_dev:  Pointer to acceleration device.
+ *
+ * Function is the clears the communications channels (rings) of the
+ * acceleration device accel_dev.
+ * To be used by QAT device specific drivers.
+ *
+ * Return: void
+ */
+void adf_cleanup_etr_data(struct adf_accel_dev *accel_dev)
+{
+	struct adf_etr_data *etr_data = accel_dev->transport;
+
+	if (etr_data) {
+		adf_cleanup_etr_handles(accel_dev);
+		debugfs_remove(etr_data->debug);
+		kfree(etr_data->banks);
+		kfree(etr_data);
+		accel_dev->transport = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(adf_cleanup_etr_data);
diff --git a/drivers/crypto/qat/qat_common/adf_transport.h b/drivers/crypto/qat/qat_common/adf_transport.h
new file mode 100644
index 00000000000..386485bd9c9
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_transport.h
@@ -0,0 +1,63 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_TRANSPORT_H
+#define ADF_TRANSPORT_H
+
+#include "adf_accel_devices.h"
+
+struct adf_etr_ring_data;
+
+typedef void (*adf_callback_fn)(void *resp_msg);
+
+int adf_create_ring(struct adf_accel_dev *accel_dev, const char *section,
+		    uint32_t bank_num, uint32_t num_mgs, uint32_t msg_size,
+		    const char *ring_name, adf_callback_fn callback,
+		    int poll_mode, struct adf_etr_ring_data **ring_ptr);
+
+int adf_send_message(struct adf_etr_ring_data *ring, uint32_t *msg);
+void adf_remove_ring(struct adf_etr_ring_data *ring);
+#endif
diff --git a/drivers/crypto/qat/qat_common/adf_transport_access_macros.h b/drivers/crypto/qat/qat_common/adf_transport_access_macros.h
new file mode 100644
index 00000000000..91d88d67658
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_transport_access_macros.h
@@ -0,0 +1,160 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_TRANSPORT_ACCESS_MACROS_H
+#define ADF_TRANSPORT_ACCESS_MACROS_H
+
+#include "adf_accel_devices.h"
+#define ADF_BANK_INT_SRC_SEL_MASK_0 0x4444444CUL
+#define ADF_BANK_INT_SRC_SEL_MASK_X 0x44444444UL
+#define ADF_RING_CSR_RING_CONFIG 0x000
+#define ADF_RING_CSR_RING_LBASE 0x040
+#define ADF_RING_CSR_RING_UBASE 0x080
+#define ADF_RING_CSR_RING_HEAD 0x0C0
+#define ADF_RING_CSR_RING_TAIL 0x100
+#define ADF_RING_CSR_E_STAT 0x14C
+#define ADF_RING_CSR_INT_SRCSEL 0x174
+#define ADF_RING_CSR_INT_SRCSEL_2 0x178
+#define ADF_RING_CSR_INT_COL_EN 0x17C
+#define ADF_RING_CSR_INT_COL_CTL 0x180
+#define ADF_RING_CSR_INT_FLAG_AND_COL 0x184
+#define ADF_RING_CSR_INT_COL_CTL_ENABLE	0x80000000
+#define ADF_RING_BUNDLE_SIZE 0x1000
+#define ADF_RING_CONFIG_NEAR_FULL_WM 0x0A
+#define ADF_RING_CONFIG_NEAR_EMPTY_WM 0x05
+#define ADF_COALESCING_MIN_TIME 0x1FF
+#define ADF_COALESCING_MAX_TIME 0xFFFFF
+#define ADF_COALESCING_DEF_TIME 0x27FF
+#define ADF_RING_NEAR_WATERMARK_512 0x08
+#define ADF_RING_NEAR_WATERMARK_0 0x00
+#define ADF_RING_EMPTY_SIG 0x7F7F7F7F
+
+/* Valid internal ring size values */
+#define ADF_RING_SIZE_128 0x01
+#define ADF_RING_SIZE_256 0x02
+#define ADF_RING_SIZE_512 0x03
+#define ADF_RING_SIZE_4K 0x06
+#define ADF_RING_SIZE_16K 0x08
+#define ADF_RING_SIZE_4M 0x10
+#define ADF_MIN_RING_SIZE ADF_RING_SIZE_128
+#define ADF_MAX_RING_SIZE ADF_RING_SIZE_4M
+#define ADF_DEFAULT_RING_SIZE ADF_RING_SIZE_16K
+
+/* Valid internal msg size values internal */
+#define ADF_MSG_SIZE_32 0x01
+#define ADF_MSG_SIZE_64 0x02
+#define ADF_MSG_SIZE_128 0x04
+#define ADF_MIN_MSG_SIZE ADF_MSG_SIZE_32
+#define ADF_MAX_MSG_SIZE ADF_MSG_SIZE_128
+
+/* Size to bytes conversion macros for ring and msg values */
+#define ADF_MSG_SIZE_TO_BYTES(SIZE) (SIZE << 5)
+#define ADF_BYTES_TO_MSG_SIZE(SIZE) (SIZE >> 5)
+#define ADF_SIZE_TO_RING_SIZE_IN_BYTES(SIZE) ((1 << (SIZE - 1)) << 7)
+#define ADF_RING_SIZE_IN_BYTES_TO_SIZE(SIZE) ((1 << (SIZE - 1)) >> 7)
+
+/* Minimum ring bufer size for memory allocation */
+#define ADF_RING_SIZE_BYTES_MIN(SIZE) ((SIZE < ADF_RING_SIZE_4K) ? \
+				ADF_RING_SIZE_4K : SIZE)
+#define ADF_RING_SIZE_MODULO(SIZE) (SIZE + 0x6)
+#define ADF_MAX_INFLIGHTS(RING_SIZE, MSG_SIZE) \
+	((((1 << (RING_SIZE - 1)) << 4) >> MSG_SIZE) - 1)
+#define BUILD_RING_CONFIG(size)	\
+	((ADF_RING_NEAR_WATERMARK_0 << ADF_RING_CONFIG_NEAR_FULL_WM) \
+	| (ADF_RING_NEAR_WATERMARK_0 << ADF_RING_CONFIG_NEAR_EMPTY_WM) \
+	| size)
+#define BUILD_RESP_RING_CONFIG(size, watermark_nf, watermark_ne) \
+	((watermark_nf << ADF_RING_CONFIG_NEAR_FULL_WM)	\
+	| (watermark_ne << ADF_RING_CONFIG_NEAR_EMPTY_WM) \
+	| size)
+#define BUILD_RING_BASE_ADDR(addr, size) \
+	((addr >> 6) & (0xFFFFFFFFFFFFFFFFULL << size))
+#define READ_CSR_RING_HEAD(csr_base_addr, bank, ring) \
+	ADF_CSR_RD(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+			ADF_RING_CSR_RING_HEAD + (ring << 2))
+#define READ_CSR_RING_TAIL(csr_base_addr, bank, ring) \
+	ADF_CSR_RD(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+			ADF_RING_CSR_RING_TAIL + (ring << 2))
+#define READ_CSR_E_STAT(csr_base_addr, bank) \
+	ADF_CSR_RD(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+			ADF_RING_CSR_E_STAT)
+#define WRITE_CSR_RING_CONFIG(csr_base_addr, bank, ring, value) \
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+		ADF_RING_CSR_RING_CONFIG + (ring << 2), value)
+#define WRITE_CSR_RING_BASE(csr_base_addr, bank, ring, value) \
+do { \
+	uint32_t l_base = 0, u_base = 0; \
+	l_base = (uint32_t)(value & 0xFFFFFFFF); \
+	u_base = (uint32_t)((value & 0xFFFFFFFF00000000ULL) >> 32); \
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+		ADF_RING_CSR_RING_LBASE + (ring << 2), l_base);	\
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+		ADF_RING_CSR_RING_UBASE + (ring << 2), u_base);	\
+} while (0)
+#define WRITE_CSR_RING_HEAD(csr_base_addr, bank, ring, value) \
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+		ADF_RING_CSR_RING_HEAD + (ring << 2), value)
+#define WRITE_CSR_RING_TAIL(csr_base_addr, bank, ring, value) \
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+		ADF_RING_CSR_RING_TAIL + (ring << 2), value)
+#define WRITE_CSR_INT_SRCSEL(csr_base_addr, bank) \
+do { \
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+	ADF_RING_CSR_INT_SRCSEL, ADF_BANK_INT_SRC_SEL_MASK_0);	\
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+	ADF_RING_CSR_INT_SRCSEL_2, ADF_BANK_INT_SRC_SEL_MASK_X); \
+} while (0)
+#define WRITE_CSR_INT_COL_EN(csr_base_addr, bank, value) \
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+			ADF_RING_CSR_INT_COL_EN, value)
+#define WRITE_CSR_INT_COL_CTL(csr_base_addr, bank, value) \
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+			ADF_RING_CSR_INT_COL_CTL, \
+			ADF_RING_CSR_INT_COL_CTL_ENABLE | value)
+#define WRITE_CSR_INT_FLAG_AND_COL(csr_base_addr, bank, value) \
+	ADF_CSR_WR(csr_base_addr, (ADF_RING_BUNDLE_SIZE * bank) + \
+			ADF_RING_CSR_INT_FLAG_AND_COL, value)
+#endif
diff --git a/drivers/crypto/qat/qat_common/adf_transport_debug.c b/drivers/crypto/qat/qat_common/adf_transport_debug.c
new file mode 100644
index 00000000000..6b697455351
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_transport_debug.c
@@ -0,0 +1,304 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include "adf_accel_devices.h"
+#include "adf_transport_internal.h"
+#include "adf_transport_access_macros.h"
+
+static DEFINE_MUTEX(ring_read_lock);
+static DEFINE_MUTEX(bank_read_lock);
+
+static void *adf_ring_start(struct seq_file *sfile, loff_t *pos)
+{
+	struct adf_etr_ring_data *ring = sfile->private;
+
+	mutex_lock(&ring_read_lock);
+	if (*pos == 0)
+		return SEQ_START_TOKEN;
+
+	if (*pos >= (ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size) /
+		     ADF_MSG_SIZE_TO_BYTES(ring->msg_size)))
+		return NULL;
+
+	return ring->base_addr +
+		(ADF_MSG_SIZE_TO_BYTES(ring->msg_size) * (*pos)++);
+}
+
+static void *adf_ring_next(struct seq_file *sfile, void *v, loff_t *pos)
+{
+	struct adf_etr_ring_data *ring = sfile->private;
+
+	if (*pos >= (ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size) /
+		     ADF_MSG_SIZE_TO_BYTES(ring->msg_size)))
+		return NULL;
+
+	return ring->base_addr +
+		(ADF_MSG_SIZE_TO_BYTES(ring->msg_size) * (*pos)++);
+}
+
+static int adf_ring_show(struct seq_file *sfile, void *v)
+{
+	struct adf_etr_ring_data *ring = sfile->private;
+	struct adf_etr_bank_data *bank = ring->bank;
+	uint32_t *msg = v;
+	void __iomem *csr = ring->bank->csr_addr;
+	int i, x;
+
+	if (v == SEQ_START_TOKEN) {
+		int head, tail, empty;
+
+		head = READ_CSR_RING_HEAD(csr, bank->bank_number,
+					  ring->ring_number);
+		tail = READ_CSR_RING_TAIL(csr, bank->bank_number,
+					  ring->ring_number);
+		empty = READ_CSR_E_STAT(csr, bank->bank_number);
+
+		seq_puts(sfile, "------- Ring configuration -------\n");
+		seq_printf(sfile, "ring num %d, bank num %d\n",
+			   ring->ring_number, ring->bank->bank_number);
+		seq_printf(sfile, "head %x, tail %x, empty: %d\n",
+			   head, tail, (empty & 1 << ring->ring_number)
+			   >> ring->ring_number);
+		seq_printf(sfile, "ring size %d, msg size %d\n",
+			   ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size),
+			   ADF_MSG_SIZE_TO_BYTES(ring->msg_size));
+		seq_puts(sfile, "----------- Ring data ------------\n");
+		return 0;
+	}
+	seq_printf(sfile, "%p:", msg);
+	x = 0;
+	i = 0;
+	for (; i < (ADF_MSG_SIZE_TO_BYTES(ring->msg_size) >> 2); i++) {
+		seq_printf(sfile, " %08X", *(msg + i));
+		if ((ADF_MSG_SIZE_TO_BYTES(ring->msg_size) >> 2) != i + 1 &&
+		    (++x == 8)) {
+			seq_printf(sfile, "\n%p:", msg + i + 1);
+			x = 0;
+		}
+	}
+	seq_puts(sfile, "\n");
+	return 0;
+}
+
+static void adf_ring_stop(struct seq_file *sfile, void *v)
+{
+	mutex_unlock(&ring_read_lock);
+}
+
+static const struct seq_operations adf_ring_sops = {
+	.start = adf_ring_start,
+	.next = adf_ring_next,
+	.stop = adf_ring_stop,
+	.show = adf_ring_show
+};
+
+static int adf_ring_open(struct inode *inode, struct file *file)
+{
+	int ret = seq_open(file, &adf_ring_sops);
+
+	if (!ret) {
+		struct seq_file *seq_f = file->private_data;
+
+		seq_f->private = inode->i_private;
+	}
+	return ret;
+}
+
+static const struct file_operations adf_ring_debug_fops = {
+	.open = adf_ring_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release
+};
+
+int adf_ring_debugfs_add(struct adf_etr_ring_data *ring, const char *name)
+{
+	struct adf_etr_ring_debug_entry *ring_debug;
+	char entry_name[8];
+
+	ring_debug = kzalloc(sizeof(*ring_debug), GFP_KERNEL);
+	if (!ring_debug)
+		return -ENOMEM;
+
+	strlcpy(ring_debug->ring_name, name, sizeof(ring_debug->ring_name));
+	snprintf(entry_name, sizeof(entry_name), "ring_%02d",
+		 ring->ring_number);
+
+	ring_debug->debug = debugfs_create_file(entry_name, S_IRUSR,
+						ring->bank->bank_debug_dir,
+						ring, &adf_ring_debug_fops);
+	if (!ring_debug->debug) {
+		pr_err("QAT: Failed to create ring debug entry.\n");
+		kfree(ring_debug);
+		return -EFAULT;
+	}
+	ring->ring_debug = ring_debug;
+	return 0;
+}
+
+void adf_ring_debugfs_rm(struct adf_etr_ring_data *ring)
+{
+	if (ring->ring_debug) {
+		debugfs_remove(ring->ring_debug->debug);
+		kfree(ring->ring_debug);
+		ring->ring_debug = NULL;
+	}
+}
+
+static void *adf_bank_start(struct seq_file *sfile, loff_t *pos)
+{
+	mutex_lock(&bank_read_lock);
+	if (*pos == 0)
+		return SEQ_START_TOKEN;
+
+	if (*pos >= ADF_ETR_MAX_RINGS_PER_BANK)
+		return NULL;
+
+	return pos;
+}
+
+static void *adf_bank_next(struct seq_file *sfile, void *v, loff_t *pos)
+{
+	if (++(*pos) >= ADF_ETR_MAX_RINGS_PER_BANK)
+		return NULL;
+
+	return pos;
+}
+
+static int adf_bank_show(struct seq_file *sfile, void *v)
+{
+	struct adf_etr_bank_data *bank = sfile->private;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_printf(sfile, "------- Bank %d configuration -------\n",
+			   bank->bank_number);
+	} else {
+		int ring_id = *((int *)v) - 1;
+		struct adf_etr_ring_data *ring = &bank->rings[ring_id];
+		void __iomem *csr = bank->csr_addr;
+		int head, tail, empty;
+
+		if (!(bank->ring_mask & 1 << ring_id))
+			return 0;
+
+		head = READ_CSR_RING_HEAD(csr, bank->bank_number,
+					  ring->ring_number);
+		tail = READ_CSR_RING_TAIL(csr, bank->bank_number,
+					  ring->ring_number);
+		empty = READ_CSR_E_STAT(csr, bank->bank_number);
+
+		seq_printf(sfile,
+			   "ring num %02d, head %04x, tail %04x, empty: %d\n",
+			   ring->ring_number, head, tail,
+			   (empty & 1 << ring->ring_number) >>
+			   ring->ring_number);
+	}
+	return 0;
+}
+
+static void adf_bank_stop(struct seq_file *sfile, void *v)
+{
+	mutex_unlock(&bank_read_lock);
+}
+
+static const struct seq_operations adf_bank_sops = {
+	.start = adf_bank_start,
+	.next = adf_bank_next,
+	.stop = adf_bank_stop,
+	.show = adf_bank_show
+};
+
+static int adf_bank_open(struct inode *inode, struct file *file)
+{
+	int ret = seq_open(file, &adf_bank_sops);
+
+	if (!ret) {
+		struct seq_file *seq_f = file->private_data;
+
+		seq_f->private = inode->i_private;
+	}
+	return ret;
+}
+
+static const struct file_operations adf_bank_debug_fops = {
+	.open = adf_bank_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release
+};
+
+int adf_bank_debugfs_add(struct adf_etr_bank_data *bank)
+{
+	struct adf_accel_dev *accel_dev = bank->accel_dev;
+	struct dentry *parent = accel_dev->transport->debug;
+	char name[8];
+
+	snprintf(name, sizeof(name), "bank_%02d", bank->bank_number);
+	bank->bank_debug_dir = debugfs_create_dir(name, parent);
+	if (!bank->bank_debug_dir) {
+		pr_err("QAT: Failed to create bank debug dir.\n");
+		return -EFAULT;
+	}
+
+	bank->bank_debug_cfg = debugfs_create_file("config", S_IRUSR,
+						   bank->bank_debug_dir, bank,
+						   &adf_bank_debug_fops);
+	if (!bank->bank_debug_cfg) {
+		pr_err("QAT: Failed to create bank debug entry.\n");
+		debugfs_remove(bank->bank_debug_dir);
+		return -EFAULT;
+	}
+	return 0;
+}
+
+void adf_bank_debugfs_rm(struct adf_etr_bank_data *bank)
+{
+	debugfs_remove(bank->bank_debug_cfg);
+	debugfs_remove(bank->bank_debug_dir);
+}
diff --git a/drivers/crypto/qat/qat_common/adf_transport_internal.h b/drivers/crypto/qat/qat_common/adf_transport_internal.h
new file mode 100644
index 00000000000..f854bac276b
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/adf_transport_internal.h
@@ -0,0 +1,118 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_TRANSPORT_INTRN_H
+#define ADF_TRANSPORT_INTRN_H
+
+#include <linux/interrupt.h>
+#include <linux/atomic.h>
+#include <linux/spinlock_types.h>
+#include "adf_transport.h"
+
+struct adf_etr_ring_debug_entry {
+	char ring_name[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	struct dentry *debug;
+};
+
+struct adf_etr_ring_data {
+	void *base_addr;
+	atomic_t *inflights;
+	spinlock_t lock;	/* protects ring data struct */
+	adf_callback_fn callback;
+	struct adf_etr_bank_data *bank;
+	dma_addr_t dma_addr;
+	uint16_t head;
+	uint16_t tail;
+	uint8_t ring_number;
+	uint8_t ring_size;
+	uint8_t msg_size;
+	uint8_t reserved;
+	struct adf_etr_ring_debug_entry *ring_debug;
+} __packed;
+
+struct adf_etr_bank_data {
+	struct adf_etr_ring_data rings[ADF_ETR_MAX_RINGS_PER_BANK];
+	struct tasklet_struct resp_hanlder;
+	void __iomem *csr_addr;
+	struct adf_accel_dev *accel_dev;
+	uint32_t irq_coalesc_timer;
+	uint16_t ring_mask;
+	uint16_t irq_mask;
+	spinlock_t lock;	/* protects bank data struct */
+	struct dentry *bank_debug_dir;
+	struct dentry *bank_debug_cfg;
+	uint32_t bank_number;
+} __packed;
+
+struct adf_etr_data {
+	struct adf_etr_bank_data *banks;
+	struct dentry *debug;
+};
+
+void adf_response_handler(unsigned long bank_addr);
+#ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
+int adf_bank_debugfs_add(struct adf_etr_bank_data *bank);
+void adf_bank_debugfs_rm(struct adf_etr_bank_data *bank);
+int adf_ring_debugfs_add(struct adf_etr_ring_data *ring, const char *name);
+void adf_ring_debugfs_rm(struct adf_etr_ring_data *ring);
+#else
+static inline int adf_bank_debugfs_add(struct adf_etr_bank_data *bank)
+{
+	return 0;
+}
+
+#define adf_bank_debugfs_rm(bank) do {} while (0)
+
+static inline int adf_ring_debugfs_add(struct adf_etr_ring_data *ring,
+				       const char *name)
+{
+	return 0;
+}
+
+#define adf_ring_debugfs_rm(ring) do {} while (0)
+#endif
+#endif
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw.h b/drivers/crypto/qat/qat_common/icp_qat_fw.h
new file mode 100644
index 00000000000..f1e30e24a41
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/icp_qat_fw.h
@@ -0,0 +1,316 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef _ICP_QAT_FW_H_
+#define _ICP_QAT_FW_H_
+#include <linux/types.h>
+#include "icp_qat_hw.h"
+
+#define QAT_FIELD_SET(flags, val, bitpos, mask) \
+{ (flags) = (((flags) & (~((mask) << (bitpos)))) | \
+		(((val) & (mask)) << (bitpos))) ; }
+
+#define QAT_FIELD_GET(flags, bitpos, mask) \
+	(((flags) >> (bitpos)) & (mask))
+
+#define ICP_QAT_FW_REQ_DEFAULT_SZ 128
+#define ICP_QAT_FW_RESP_DEFAULT_SZ 32
+#define ICP_QAT_FW_COMN_ONE_BYTE_SHIFT 8
+#define ICP_QAT_FW_COMN_SINGLE_BYTE_MASK 0xFF
+#define ICP_QAT_FW_NUM_LONGWORDS_1 1
+#define ICP_QAT_FW_NUM_LONGWORDS_2 2
+#define ICP_QAT_FW_NUM_LONGWORDS_3 3
+#define ICP_QAT_FW_NUM_LONGWORDS_4 4
+#define ICP_QAT_FW_NUM_LONGWORDS_5 5
+#define ICP_QAT_FW_NUM_LONGWORDS_6 6
+#define ICP_QAT_FW_NUM_LONGWORDS_7 7
+#define ICP_QAT_FW_NUM_LONGWORDS_10 10
+#define ICP_QAT_FW_NUM_LONGWORDS_13 13
+#define ICP_QAT_FW_NULL_REQ_SERV_ID 1
+
+enum icp_qat_fw_comn_resp_serv_id {
+	ICP_QAT_FW_COMN_RESP_SERV_NULL,
+	ICP_QAT_FW_COMN_RESP_SERV_CPM_FW,
+	ICP_QAT_FW_COMN_RESP_SERV_DELIMITER
+};
+
+enum icp_qat_fw_comn_request_id {
+	ICP_QAT_FW_COMN_REQ_NULL = 0,
+	ICP_QAT_FW_COMN_REQ_CPM_FW_PKE = 3,
+	ICP_QAT_FW_COMN_REQ_CPM_FW_LA = 4,
+	ICP_QAT_FW_COMN_REQ_CPM_FW_DMA = 7,
+	ICP_QAT_FW_COMN_REQ_CPM_FW_COMP = 9,
+	ICP_QAT_FW_COMN_REQ_DELIMITER
+};
+
+struct icp_qat_fw_comn_req_hdr_cd_pars {
+	union {
+		struct {
+			uint64_t content_desc_addr;
+			uint16_t content_desc_resrvd1;
+			uint8_t content_desc_params_sz;
+			uint8_t content_desc_hdr_resrvd2;
+			uint32_t content_desc_resrvd3;
+		} s;
+		struct {
+			uint32_t serv_specif_fields[4];
+		} s1;
+	} u;
+};
+
+struct icp_qat_fw_comn_req_mid {
+	uint64_t opaque_data;
+	uint64_t src_data_addr;
+	uint64_t dest_data_addr;
+	uint32_t src_length;
+	uint32_t dst_length;
+};
+
+struct icp_qat_fw_comn_req_cd_ctrl {
+	uint32_t content_desc_ctrl_lw[ICP_QAT_FW_NUM_LONGWORDS_5];
+};
+
+struct icp_qat_fw_comn_req_hdr {
+	uint8_t resrvd1;
+	uint8_t service_cmd_id;
+	uint8_t service_type;
+	uint8_t hdr_flags;
+	uint16_t serv_specif_flags;
+	uint16_t comn_req_flags;
+};
+
+struct icp_qat_fw_comn_req_rqpars {
+	uint32_t serv_specif_rqpars_lw[ICP_QAT_FW_NUM_LONGWORDS_13];
+};
+
+struct icp_qat_fw_comn_req {
+	struct icp_qat_fw_comn_req_hdr comn_hdr;
+	struct icp_qat_fw_comn_req_hdr_cd_pars cd_pars;
+	struct icp_qat_fw_comn_req_mid comn_mid;
+	struct icp_qat_fw_comn_req_rqpars serv_specif_rqpars;
+	struct icp_qat_fw_comn_req_cd_ctrl cd_ctrl;
+};
+
+struct icp_qat_fw_comn_error {
+	uint8_t xlat_err_code;
+	uint8_t cmp_err_code;
+};
+
+struct icp_qat_fw_comn_resp_hdr {
+	uint8_t resrvd1;
+	uint8_t service_id;
+	uint8_t response_type;
+	uint8_t hdr_flags;
+	struct icp_qat_fw_comn_error comn_error;
+	uint8_t comn_status;
+	uint8_t cmd_id;
+};
+
+struct icp_qat_fw_comn_resp {
+	struct icp_qat_fw_comn_resp_hdr comn_hdr;
+	uint64_t opaque_data;
+	uint32_t resrvd[ICP_QAT_FW_NUM_LONGWORDS_4];
+};
+
+#define ICP_QAT_FW_COMN_REQ_FLAG_SET 1
+#define ICP_QAT_FW_COMN_REQ_FLAG_CLR 0
+#define ICP_QAT_FW_COMN_VALID_FLAG_BITPOS 7
+#define ICP_QAT_FW_COMN_VALID_FLAG_MASK 0x1
+#define ICP_QAT_FW_COMN_HDR_RESRVD_FLD_MASK 0x7F
+
+#define ICP_QAT_FW_COMN_OV_SRV_TYPE_GET(icp_qat_fw_comn_req_hdr_t) \
+	icp_qat_fw_comn_req_hdr_t.service_type
+
+#define ICP_QAT_FW_COMN_OV_SRV_TYPE_SET(icp_qat_fw_comn_req_hdr_t, val) \
+	icp_qat_fw_comn_req_hdr_t.service_type = val
+
+#define ICP_QAT_FW_COMN_OV_SRV_CMD_ID_GET(icp_qat_fw_comn_req_hdr_t) \
+	icp_qat_fw_comn_req_hdr_t.service_cmd_id
+
+#define ICP_QAT_FW_COMN_OV_SRV_CMD_ID_SET(icp_qat_fw_comn_req_hdr_t, val) \
+	icp_qat_fw_comn_req_hdr_t.service_cmd_id = val
+
+#define ICP_QAT_FW_COMN_HDR_VALID_FLAG_GET(hdr_t) \
+	ICP_QAT_FW_COMN_VALID_FLAG_GET(hdr_t.hdr_flags)
+
+#define ICP_QAT_FW_COMN_HDR_VALID_FLAG_SET(hdr_t, val) \
+	ICP_QAT_FW_COMN_VALID_FLAG_SET(hdr_t, val)
+
+#define ICP_QAT_FW_COMN_VALID_FLAG_GET(hdr_flags) \
+	QAT_FIELD_GET(hdr_flags, \
+	ICP_QAT_FW_COMN_VALID_FLAG_BITPOS, \
+	ICP_QAT_FW_COMN_VALID_FLAG_MASK)
+
+#define ICP_QAT_FW_COMN_HDR_RESRVD_FLD_GET(hdr_flags) \
+	(hdr_flags & ICP_QAT_FW_COMN_HDR_RESRVD_FLD_MASK)
+
+#define ICP_QAT_FW_COMN_VALID_FLAG_SET(hdr_t, val) \
+	QAT_FIELD_SET((hdr_t.hdr_flags), (val), \
+	ICP_QAT_FW_COMN_VALID_FLAG_BITPOS, \
+	ICP_QAT_FW_COMN_VALID_FLAG_MASK)
+
+#define ICP_QAT_FW_COMN_HDR_FLAGS_BUILD(valid) \
+	(((valid) & ICP_QAT_FW_COMN_VALID_FLAG_MASK) << \
+	 ICP_QAT_FW_COMN_VALID_FLAG_BITPOS)
+
+#define QAT_COMN_PTR_TYPE_BITPOS 0
+#define QAT_COMN_PTR_TYPE_MASK 0x1
+#define QAT_COMN_CD_FLD_TYPE_BITPOS 1
+#define QAT_COMN_CD_FLD_TYPE_MASK 0x1
+#define QAT_COMN_PTR_TYPE_FLAT 0x0
+#define QAT_COMN_PTR_TYPE_SGL 0x1
+#define QAT_COMN_CD_FLD_TYPE_64BIT_ADR 0x0
+#define QAT_COMN_CD_FLD_TYPE_16BYTE_DATA 0x1
+
+#define ICP_QAT_FW_COMN_FLAGS_BUILD(cdt, ptr) \
+	((((cdt) & QAT_COMN_CD_FLD_TYPE_MASK) << QAT_COMN_CD_FLD_TYPE_BITPOS) \
+	 | (((ptr) & QAT_COMN_PTR_TYPE_MASK) << QAT_COMN_PTR_TYPE_BITPOS))
+
+#define ICP_QAT_FW_COMN_PTR_TYPE_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_COMN_PTR_TYPE_BITPOS, QAT_COMN_PTR_TYPE_MASK)
+
+#define ICP_QAT_FW_COMN_CD_FLD_TYPE_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_COMN_CD_FLD_TYPE_BITPOS, \
+			QAT_COMN_CD_FLD_TYPE_MASK)
+
+#define ICP_QAT_FW_COMN_PTR_TYPE_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_COMN_PTR_TYPE_BITPOS, \
+			QAT_COMN_PTR_TYPE_MASK)
+
+#define ICP_QAT_FW_COMN_CD_FLD_TYPE_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_COMN_CD_FLD_TYPE_BITPOS, \
+			QAT_COMN_CD_FLD_TYPE_MASK)
+
+#define ICP_QAT_FW_COMN_NEXT_ID_BITPOS 4
+#define ICP_QAT_FW_COMN_NEXT_ID_MASK 0xF0
+#define ICP_QAT_FW_COMN_CURR_ID_BITPOS 0
+#define ICP_QAT_FW_COMN_CURR_ID_MASK 0x0F
+
+#define ICP_QAT_FW_COMN_NEXT_ID_GET(cd_ctrl_hdr_t) \
+	((((cd_ctrl_hdr_t)->next_curr_id) & ICP_QAT_FW_COMN_NEXT_ID_MASK) \
+	>> (ICP_QAT_FW_COMN_NEXT_ID_BITPOS))
+
+#define ICP_QAT_FW_COMN_NEXT_ID_SET(cd_ctrl_hdr_t, val) \
+	{ ((cd_ctrl_hdr_t)->next_curr_id) = ((((cd_ctrl_hdr_t)->next_curr_id) \
+	& ICP_QAT_FW_COMN_CURR_ID_MASK) | \
+	((val << ICP_QAT_FW_COMN_NEXT_ID_BITPOS) \
+	 & ICP_QAT_FW_COMN_NEXT_ID_MASK)); }
+
+#define ICP_QAT_FW_COMN_CURR_ID_GET(cd_ctrl_hdr_t) \
+	(((cd_ctrl_hdr_t)->next_curr_id) & ICP_QAT_FW_COMN_CURR_ID_MASK)
+
+#define ICP_QAT_FW_COMN_CURR_ID_SET(cd_ctrl_hdr_t, val) \
+	{ ((cd_ctrl_hdr_t)->next_curr_id) = ((((cd_ctrl_hdr_t)->next_curr_id) \
+	& ICP_QAT_FW_COMN_NEXT_ID_MASK) | \
+	((val) & ICP_QAT_FW_COMN_CURR_ID_MASK)); }
+
+#define QAT_COMN_RESP_CRYPTO_STATUS_BITPOS 7
+#define QAT_COMN_RESP_CRYPTO_STATUS_MASK 0x1
+#define QAT_COMN_RESP_CMP_STATUS_BITPOS 5
+#define QAT_COMN_RESP_CMP_STATUS_MASK 0x1
+#define QAT_COMN_RESP_XLAT_STATUS_BITPOS 4
+#define QAT_COMN_RESP_XLAT_STATUS_MASK 0x1
+#define QAT_COMN_RESP_CMP_END_OF_LAST_BLK_BITPOS 3
+#define QAT_COMN_RESP_CMP_END_OF_LAST_BLK_MASK 0x1
+
+#define ICP_QAT_FW_COMN_RESP_STATUS_BUILD(crypto, comp, xlat, eolb) \
+	((((crypto) & QAT_COMN_RESP_CRYPTO_STATUS_MASK) << \
+	QAT_COMN_RESP_CRYPTO_STATUS_BITPOS) | \
+	(((comp) & QAT_COMN_RESP_CMP_STATUS_MASK) << \
+	QAT_COMN_RESP_CMP_STATUS_BITPOS) | \
+	(((xlat) & QAT_COMN_RESP_XLAT_STATUS_MASK) << \
+	QAT_COMN_RESP_XLAT_STATUS_BITPOS) | \
+	(((eolb) & QAT_COMN_RESP_CMP_END_OF_LAST_BLK_MASK) << \
+	QAT_COMN_RESP_CMP_END_OF_LAST_BLK_BITPOS))
+
+#define ICP_QAT_FW_COMN_RESP_CRYPTO_STAT_GET(status) \
+	QAT_FIELD_GET(status, QAT_COMN_RESP_CRYPTO_STATUS_BITPOS, \
+	QAT_COMN_RESP_CRYPTO_STATUS_MASK)
+
+#define ICP_QAT_FW_COMN_RESP_CMP_STAT_GET(status) \
+	QAT_FIELD_GET(status, QAT_COMN_RESP_CMP_STATUS_BITPOS, \
+	QAT_COMN_RESP_CMP_STATUS_MASK)
+
+#define ICP_QAT_FW_COMN_RESP_XLAT_STAT_GET(status) \
+	QAT_FIELD_GET(status, QAT_COMN_RESP_XLAT_STATUS_BITPOS, \
+	QAT_COMN_RESP_XLAT_STATUS_MASK)
+
+#define ICP_QAT_FW_COMN_RESP_CMP_END_OF_LAST_BLK_FLAG_GET(status) \
+	QAT_FIELD_GET(status, QAT_COMN_RESP_CMP_END_OF_LAST_BLK_BITPOS, \
+	QAT_COMN_RESP_CMP_END_OF_LAST_BLK_MASK)
+
+#define ICP_QAT_FW_COMN_STATUS_FLAG_OK 0
+#define ICP_QAT_FW_COMN_STATUS_FLAG_ERROR 1
+#define ICP_QAT_FW_COMN_STATUS_CMP_END_OF_LAST_BLK_FLAG_CLR 0
+#define ICP_QAT_FW_COMN_STATUS_CMP_END_OF_LAST_BLK_FLAG_SET 1
+#define ERR_CODE_NO_ERROR 0
+#define ERR_CODE_INVALID_BLOCK_TYPE -1
+#define ERR_CODE_NO_MATCH_ONES_COMP -2
+#define ERR_CODE_TOO_MANY_LEN_OR_DIS -3
+#define ERR_CODE_INCOMPLETE_LEN -4
+#define ERR_CODE_RPT_LEN_NO_FIRST_LEN -5
+#define ERR_CODE_RPT_GT_SPEC_LEN -6
+#define ERR_CODE_INV_LIT_LEN_CODE_LEN -7
+#define ERR_CODE_INV_DIS_CODE_LEN -8
+#define ERR_CODE_INV_LIT_LEN_DIS_IN_BLK -9
+#define ERR_CODE_DIS_TOO_FAR_BACK -10
+#define ERR_CODE_OVERFLOW_ERROR -11
+#define ERR_CODE_SOFT_ERROR -12
+#define ERR_CODE_FATAL_ERROR -13
+#define ERR_CODE_SSM_ERROR -14
+#define ERR_CODE_ENDPOINT_ERROR -15
+
+enum icp_qat_fw_slice {
+	ICP_QAT_FW_SLICE_NULL = 0,
+	ICP_QAT_FW_SLICE_CIPHER = 1,
+	ICP_QAT_FW_SLICE_AUTH = 2,
+	ICP_QAT_FW_SLICE_DRAM_RD = 3,
+	ICP_QAT_FW_SLICE_DRAM_WR = 4,
+	ICP_QAT_FW_SLICE_COMP = 5,
+	ICP_QAT_FW_SLICE_XLAT = 6,
+	ICP_QAT_FW_SLICE_DELIMITER
+};
+#endif
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_init_admin.h b/drivers/crypto/qat/qat_common/icp_qat_fw_init_admin.h
new file mode 100644
index 00000000000..72a59faa900
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/icp_qat_fw_init_admin.h
@@ -0,0 +1,131 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef _ICP_QAT_FW_INIT_ADMIN_H_
+#define _ICP_QAT_FW_INIT_ADMIN_H_
+
+#include "icp_qat_fw.h"
+
+enum icp_qat_fw_init_admin_cmd_id {
+	ICP_QAT_FW_INIT_ME = 0,
+	ICP_QAT_FW_TRNG_ENABLE = 1,
+	ICP_QAT_FW_TRNG_DISABLE = 2,
+	ICP_QAT_FW_CONSTANTS_CFG = 3,
+	ICP_QAT_FW_STATUS_GET = 4,
+	ICP_QAT_FW_COUNTERS_GET = 5,
+	ICP_QAT_FW_LOOPBACK = 6,
+	ICP_QAT_FW_HEARTBEAT_SYNC = 7,
+	ICP_QAT_FW_HEARTBEAT_GET = 8
+};
+
+enum icp_qat_fw_init_admin_resp_status {
+	ICP_QAT_FW_INIT_RESP_STATUS_SUCCESS = 0,
+	ICP_QAT_FW_INIT_RESP_STATUS_FAIL
+};
+
+struct icp_qat_fw_init_admin_req {
+	uint16_t init_cfg_sz;
+	uint8_t resrvd1;
+	uint8_t init_admin_cmd_id;
+	uint32_t resrvd2;
+	uint64_t opaque_data;
+	uint64_t init_cfg_ptr;
+	uint64_t resrvd3;
+};
+
+struct icp_qat_fw_init_admin_resp_hdr {
+	uint8_t flags;
+	uint8_t resrvd1;
+	uint8_t status;
+	uint8_t init_admin_cmd_id;
+};
+
+struct icp_qat_fw_init_admin_resp_pars {
+	union {
+		uint32_t resrvd1[ICP_QAT_FW_NUM_LONGWORDS_4];
+		struct {
+			uint32_t version_patch_num;
+			uint8_t context_id;
+			uint8_t ae_id;
+			uint16_t resrvd1;
+			uint64_t resrvd2;
+		} s1;
+		struct {
+			uint64_t req_rec_count;
+			uint64_t resp_sent_count;
+		} s2;
+	} u;
+};
+
+struct icp_qat_fw_init_admin_resp {
+	struct icp_qat_fw_init_admin_resp_hdr init_resp_hdr;
+	union {
+		uint32_t resrvd2;
+		struct {
+			uint16_t version_minor_num;
+			uint16_t version_major_num;
+		} s;
+	} u;
+	uint64_t opaque_data;
+	struct icp_qat_fw_init_admin_resp_pars init_resp_pars;
+};
+
+#define ICP_QAT_FW_COMN_HEARTBEAT_OK 0
+#define ICP_QAT_FW_COMN_HEARTBEAT_BLOCKED 1
+#define ICP_QAT_FW_COMN_HEARTBEAT_FLAG_BITPOS 0
+#define ICP_QAT_FW_COMN_HEARTBEAT_FLAG_MASK 0x1
+#define ICP_QAT_FW_COMN_STATUS_RESRVD_FLD_MASK 0xFE
+#define ICP_QAT_FW_COMN_HEARTBEAT_HDR_FLAG_GET(hdr_t) \
+	ICP_QAT_FW_COMN_HEARTBEAT_FLAG_GET(hdr_t.flags)
+
+#define ICP_QAT_FW_COMN_HEARTBEAT_HDR_FLAG_SET(hdr_t, val) \
+	ICP_QAT_FW_COMN_HEARTBEAT_FLAG_SET(hdr_t, val)
+
+#define ICP_QAT_FW_COMN_HEARTBEAT_FLAG_GET(flags) \
+	QAT_FIELD_GET(flags, \
+		 ICP_QAT_FW_COMN_HEARTBEAT_FLAG_BITPOS, \
+		 ICP_QAT_FW_COMN_HEARTBEAT_FLAG_MASK)
+#endif
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_la.h b/drivers/crypto/qat/qat_common/icp_qat_fw_la.h
new file mode 100644
index 00000000000..c8d26697e8e
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/icp_qat_fw_la.h
@@ -0,0 +1,404 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef _ICP_QAT_FW_LA_H_
+#define _ICP_QAT_FW_LA_H_
+#include "icp_qat_fw.h"
+
+enum icp_qat_fw_la_cmd_id {
+	ICP_QAT_FW_LA_CMD_CIPHER = 0,
+	ICP_QAT_FW_LA_CMD_AUTH = 1,
+	ICP_QAT_FW_LA_CMD_CIPHER_HASH = 2,
+	ICP_QAT_FW_LA_CMD_HASH_CIPHER = 3,
+	ICP_QAT_FW_LA_CMD_TRNG_GET_RANDOM = 4,
+	ICP_QAT_FW_LA_CMD_TRNG_TEST = 5,
+	ICP_QAT_FW_LA_CMD_SSL3_KEY_DERIVE = 6,
+	ICP_QAT_FW_LA_CMD_TLS_V1_1_KEY_DERIVE = 7,
+	ICP_QAT_FW_LA_CMD_TLS_V1_2_KEY_DERIVE = 8,
+	ICP_QAT_FW_LA_CMD_MGF1 = 9,
+	ICP_QAT_FW_LA_CMD_AUTH_PRE_COMP = 10,
+	ICP_QAT_FW_LA_CMD_CIPHER_PRE_COMP = 11,
+	ICP_QAT_FW_LA_CMD_DELIMITER = 12
+};
+
+#define ICP_QAT_FW_LA_ICV_VER_STATUS_PASS ICP_QAT_FW_COMN_STATUS_FLAG_OK
+#define ICP_QAT_FW_LA_ICV_VER_STATUS_FAIL ICP_QAT_FW_COMN_STATUS_FLAG_ERROR
+#define ICP_QAT_FW_LA_TRNG_STATUS_PASS ICP_QAT_FW_COMN_STATUS_FLAG_OK
+#define ICP_QAT_FW_LA_TRNG_STATUS_FAIL ICP_QAT_FW_COMN_STATUS_FLAG_ERROR
+
+struct icp_qat_fw_la_bulk_req {
+	struct icp_qat_fw_comn_req_hdr comn_hdr;
+	struct icp_qat_fw_comn_req_hdr_cd_pars cd_pars;
+	struct icp_qat_fw_comn_req_mid comn_mid;
+	struct icp_qat_fw_comn_req_rqpars serv_specif_rqpars;
+	struct icp_qat_fw_comn_req_cd_ctrl cd_ctrl;
+};
+
+#define ICP_QAT_FW_LA_GCM_IV_LEN_12_OCTETS 1
+#define ICP_QAT_FW_LA_GCM_IV_LEN_NOT_12_OCTETS 0
+#define QAT_FW_LA_ZUC_3G_PROTO_FLAG_BITPOS 12
+#define ICP_QAT_FW_LA_ZUC_3G_PROTO 1
+#define QAT_FW_LA_ZUC_3G_PROTO_FLAG_MASK 0x1
+#define QAT_LA_GCM_IV_LEN_FLAG_BITPOS 11
+#define QAT_LA_GCM_IV_LEN_FLAG_MASK 0x1
+#define ICP_QAT_FW_LA_DIGEST_IN_BUFFER 1
+#define ICP_QAT_FW_LA_NO_DIGEST_IN_BUFFER 0
+#define QAT_LA_DIGEST_IN_BUFFER_BITPOS	10
+#define QAT_LA_DIGEST_IN_BUFFER_MASK 0x1
+#define ICP_QAT_FW_LA_SNOW_3G_PROTO 4
+#define ICP_QAT_FW_LA_GCM_PROTO	2
+#define ICP_QAT_FW_LA_CCM_PROTO	1
+#define ICP_QAT_FW_LA_NO_PROTO 0
+#define QAT_LA_PROTO_BITPOS 7
+#define QAT_LA_PROTO_MASK 0x7
+#define ICP_QAT_FW_LA_CMP_AUTH_RES 1
+#define ICP_QAT_FW_LA_NO_CMP_AUTH_RES 0
+#define QAT_LA_CMP_AUTH_RES_BITPOS 6
+#define QAT_LA_CMP_AUTH_RES_MASK 0x1
+#define ICP_QAT_FW_LA_RET_AUTH_RES 1
+#define ICP_QAT_FW_LA_NO_RET_AUTH_RES 0
+#define QAT_LA_RET_AUTH_RES_BITPOS 5
+#define QAT_LA_RET_AUTH_RES_MASK 0x1
+#define ICP_QAT_FW_LA_UPDATE_STATE 1
+#define ICP_QAT_FW_LA_NO_UPDATE_STATE 0
+#define QAT_LA_UPDATE_STATE_BITPOS 4
+#define QAT_LA_UPDATE_STATE_MASK 0x1
+#define ICP_QAT_FW_CIPH_AUTH_CFG_OFFSET_IN_CD_SETUP 0
+#define ICP_QAT_FW_CIPH_AUTH_CFG_OFFSET_IN_SHRAM_CP 1
+#define QAT_LA_CIPH_AUTH_CFG_OFFSET_BITPOS 3
+#define QAT_LA_CIPH_AUTH_CFG_OFFSET_MASK 0x1
+#define ICP_QAT_FW_CIPH_IV_64BIT_PTR 0
+#define ICP_QAT_FW_CIPH_IV_16BYTE_DATA 1
+#define QAT_LA_CIPH_IV_FLD_BITPOS 2
+#define QAT_LA_CIPH_IV_FLD_MASK   0x1
+#define ICP_QAT_FW_LA_PARTIAL_NONE 0
+#define ICP_QAT_FW_LA_PARTIAL_START 1
+#define ICP_QAT_FW_LA_PARTIAL_MID 3
+#define ICP_QAT_FW_LA_PARTIAL_END 2
+#define QAT_LA_PARTIAL_BITPOS 0
+#define QAT_LA_PARTIAL_MASK 0x3
+#define ICP_QAT_FW_LA_FLAGS_BUILD(zuc_proto, gcm_iv_len, auth_rslt, proto, \
+	cmp_auth, ret_auth, update_state, \
+	ciph_iv, ciphcfg, partial) \
+	(((zuc_proto & QAT_FW_LA_ZUC_3G_PROTO_FLAG_MASK) << \
+	QAT_FW_LA_ZUC_3G_PROTO_FLAG_BITPOS) | \
+	((gcm_iv_len & QAT_LA_GCM_IV_LEN_FLAG_MASK) << \
+	QAT_LA_GCM_IV_LEN_FLAG_BITPOS) | \
+	((auth_rslt & QAT_LA_DIGEST_IN_BUFFER_MASK) << \
+	QAT_LA_DIGEST_IN_BUFFER_BITPOS) | \
+	((proto & QAT_LA_PROTO_MASK) << \
+	QAT_LA_PROTO_BITPOS)	| \
+	((cmp_auth & QAT_LA_CMP_AUTH_RES_MASK) << \
+	QAT_LA_CMP_AUTH_RES_BITPOS) | \
+	((ret_auth & QAT_LA_RET_AUTH_RES_MASK) << \
+	QAT_LA_RET_AUTH_RES_BITPOS) | \
+	((update_state & QAT_LA_UPDATE_STATE_MASK) << \
+	QAT_LA_UPDATE_STATE_BITPOS) | \
+	((ciph_iv & QAT_LA_CIPH_IV_FLD_MASK) << \
+	QAT_LA_CIPH_IV_FLD_BITPOS) | \
+	((ciphcfg & QAT_LA_CIPH_AUTH_CFG_OFFSET_MASK) << \
+	QAT_LA_CIPH_AUTH_CFG_OFFSET_BITPOS) | \
+	((partial & QAT_LA_PARTIAL_MASK) << \
+	QAT_LA_PARTIAL_BITPOS))
+
+#define ICP_QAT_FW_LA_CIPH_IV_FLD_FLAG_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_LA_CIPH_IV_FLD_BITPOS, \
+	QAT_LA_CIPH_IV_FLD_MASK)
+
+#define ICP_QAT_FW_LA_CIPH_AUTH_CFG_OFFSET_FLAG_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_LA_CIPH_AUTH_CFG_OFFSET_BITPOS, \
+	QAT_LA_CIPH_AUTH_CFG_OFFSET_MASK)
+
+#define ICP_QAT_FW_LA_ZUC_3G_PROTO_FLAG_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_FW_LA_ZUC_3G_PROTO_FLAG_BITPOS, \
+	QAT_FW_LA_ZUC_3G_PROTO_FLAG_MASK)
+
+#define ICP_QAT_FW_LA_GCM_IV_LEN_FLAG_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_LA_GCM_IV_LEN_FLAG_BITPOS, \
+	QAT_LA_GCM_IV_LEN_FLAG_MASK)
+
+#define ICP_QAT_FW_LA_PROTO_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_LA_PROTO_BITPOS, QAT_LA_PROTO_MASK)
+
+#define ICP_QAT_FW_LA_CMP_AUTH_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_LA_CMP_AUTH_RES_BITPOS, \
+	QAT_LA_CMP_AUTH_RES_MASK)
+
+#define ICP_QAT_FW_LA_RET_AUTH_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_LA_RET_AUTH_RES_BITPOS, \
+	QAT_LA_RET_AUTH_RES_MASK)
+
+#define ICP_QAT_FW_LA_DIGEST_IN_BUFFER_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_LA_DIGEST_IN_BUFFER_BITPOS, \
+	QAT_LA_DIGEST_IN_BUFFER_MASK)
+
+#define ICP_QAT_FW_LA_UPDATE_STATE_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_LA_UPDATE_STATE_BITPOS, \
+	QAT_LA_UPDATE_STATE_MASK)
+
+#define ICP_QAT_FW_LA_PARTIAL_GET(flags) \
+	QAT_FIELD_GET(flags, QAT_LA_PARTIAL_BITPOS, \
+	QAT_LA_PARTIAL_MASK)
+
+#define ICP_QAT_FW_LA_CIPH_IV_FLD_FLAG_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_LA_CIPH_IV_FLD_BITPOS, \
+	QAT_LA_CIPH_IV_FLD_MASK)
+
+#define ICP_QAT_FW_LA_CIPH_AUTH_CFG_OFFSET_FLAG_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_LA_CIPH_AUTH_CFG_OFFSET_BITPOS, \
+	QAT_LA_CIPH_AUTH_CFG_OFFSET_MASK)
+
+#define ICP_QAT_FW_LA_ZUC_3G_PROTO_FLAG_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_FW_LA_ZUC_3G_PROTO_FLAG_BITPOS, \
+	QAT_FW_LA_ZUC_3G_PROTO_FLAG_MASK)
+
+#define ICP_QAT_FW_LA_GCM_IV_LEN_FLAG_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_LA_GCM_IV_LEN_FLAG_BITPOS, \
+	QAT_LA_GCM_IV_LEN_FLAG_MASK)
+
+#define ICP_QAT_FW_LA_PROTO_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_LA_PROTO_BITPOS, \
+	QAT_LA_PROTO_MASK)
+
+#define ICP_QAT_FW_LA_CMP_AUTH_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_LA_CMP_AUTH_RES_BITPOS, \
+	QAT_LA_CMP_AUTH_RES_MASK)
+
+#define ICP_QAT_FW_LA_RET_AUTH_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_LA_RET_AUTH_RES_BITPOS, \
+	QAT_LA_RET_AUTH_RES_MASK)
+
+#define ICP_QAT_FW_LA_DIGEST_IN_BUFFER_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_LA_DIGEST_IN_BUFFER_BITPOS, \
+	QAT_LA_DIGEST_IN_BUFFER_MASK)
+
+#define ICP_QAT_FW_LA_UPDATE_STATE_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_LA_UPDATE_STATE_BITPOS, \
+	QAT_LA_UPDATE_STATE_MASK)
+
+#define ICP_QAT_FW_LA_PARTIAL_SET(flags, val) \
+	QAT_FIELD_SET(flags, val, QAT_LA_PARTIAL_BITPOS, \
+	QAT_LA_PARTIAL_MASK)
+
+struct icp_qat_fw_cipher_req_hdr_cd_pars {
+	union {
+		struct {
+			uint64_t content_desc_addr;
+			uint16_t content_desc_resrvd1;
+			uint8_t content_desc_params_sz;
+			uint8_t content_desc_hdr_resrvd2;
+			uint32_t content_desc_resrvd3;
+		} s;
+		struct {
+			uint32_t cipher_key_array[ICP_QAT_FW_NUM_LONGWORDS_4];
+		} s1;
+	} u;
+};
+
+struct icp_qat_fw_cipher_auth_req_hdr_cd_pars {
+	union {
+		struct {
+			uint64_t content_desc_addr;
+			uint16_t content_desc_resrvd1;
+			uint8_t content_desc_params_sz;
+			uint8_t content_desc_hdr_resrvd2;
+			uint32_t content_desc_resrvd3;
+		} s;
+		struct {
+			uint32_t cipher_key_array[ICP_QAT_FW_NUM_LONGWORDS_4];
+		} sl;
+	} u;
+};
+
+struct icp_qat_fw_cipher_cd_ctrl_hdr {
+	uint8_t cipher_state_sz;
+	uint8_t cipher_key_sz;
+	uint8_t cipher_cfg_offset;
+	uint8_t next_curr_id;
+	uint8_t cipher_padding_sz;
+	uint8_t resrvd1;
+	uint16_t resrvd2;
+	uint32_t resrvd3[ICP_QAT_FW_NUM_LONGWORDS_3];
+};
+
+struct icp_qat_fw_auth_cd_ctrl_hdr {
+	uint32_t resrvd1;
+	uint8_t resrvd2;
+	uint8_t hash_flags;
+	uint8_t hash_cfg_offset;
+	uint8_t next_curr_id;
+	uint8_t resrvd3;
+	uint8_t outer_prefix_sz;
+	uint8_t final_sz;
+	uint8_t inner_res_sz;
+	uint8_t resrvd4;
+	uint8_t inner_state1_sz;
+	uint8_t inner_state2_offset;
+	uint8_t inner_state2_sz;
+	uint8_t outer_config_offset;
+	uint8_t outer_state1_sz;
+	uint8_t outer_res_sz;
+	uint8_t outer_prefix_offset;
+};
+
+struct icp_qat_fw_cipher_auth_cd_ctrl_hdr {
+	uint8_t cipher_state_sz;
+	uint8_t cipher_key_sz;
+	uint8_t cipher_cfg_offset;
+	uint8_t next_curr_id_cipher;
+	uint8_t cipher_padding_sz;
+	uint8_t hash_flags;
+	uint8_t hash_cfg_offset;
+	uint8_t next_curr_id_auth;
+	uint8_t resrvd1;
+	uint8_t outer_prefix_sz;
+	uint8_t final_sz;
+	uint8_t inner_res_sz;
+	uint8_t resrvd2;
+	uint8_t inner_state1_sz;
+	uint8_t inner_state2_offset;
+	uint8_t inner_state2_sz;
+	uint8_t outer_config_offset;
+	uint8_t outer_state1_sz;
+	uint8_t outer_res_sz;
+	uint8_t outer_prefix_offset;
+};
+
+#define ICP_QAT_FW_AUTH_HDR_FLAG_DO_NESTED 1
+#define ICP_QAT_FW_AUTH_HDR_FLAG_NO_NESTED 0
+#define ICP_QAT_FW_CCM_GCM_AAD_SZ_MAX	240
+#define ICP_QAT_FW_HASH_REQUEST_PARAMETERS_OFFSET \
+	(sizeof(struct icp_qat_fw_la_cipher_req_params_t))
+#define ICP_QAT_FW_CIPHER_REQUEST_PARAMETERS_OFFSET (0)
+
+struct icp_qat_fw_la_cipher_req_params {
+	uint32_t cipher_offset;
+	uint32_t cipher_length;
+	union {
+		uint32_t cipher_IV_array[ICP_QAT_FW_NUM_LONGWORDS_4];
+		struct {
+			uint64_t cipher_IV_ptr;
+			uint64_t resrvd1;
+		} s;
+	} u;
+};
+
+struct icp_qat_fw_la_auth_req_params {
+	uint32_t auth_off;
+	uint32_t auth_len;
+	union {
+		uint64_t auth_partial_st_prefix;
+		uint64_t aad_adr;
+	} u1;
+	uint64_t auth_res_addr;
+	union {
+		uint8_t inner_prefix_sz;
+		uint8_t aad_sz;
+	} u2;
+	uint8_t resrvd1;
+	uint8_t hash_state_sz;
+	uint8_t auth_res_sz;
+} __packed;
+
+struct icp_qat_fw_la_auth_req_params_resrvd_flds {
+	uint32_t resrvd[ICP_QAT_FW_NUM_LONGWORDS_6];
+	union {
+		uint8_t inner_prefix_sz;
+		uint8_t aad_sz;
+	} u2;
+	uint8_t resrvd1;
+	uint16_t resrvd2;
+};
+
+struct icp_qat_fw_la_resp {
+	struct icp_qat_fw_comn_resp_hdr comn_resp;
+	uint64_t opaque_data;
+	uint32_t resrvd[ICP_QAT_FW_NUM_LONGWORDS_4];
+};
+
+#define ICP_QAT_FW_CIPHER_NEXT_ID_GET(cd_ctrl_hdr_t) \
+	((((cd_ctrl_hdr_t)->next_curr_id_cipher) & \
+	  ICP_QAT_FW_COMN_NEXT_ID_MASK) >> (ICP_QAT_FW_COMN_NEXT_ID_BITPOS))
+
+#define ICP_QAT_FW_CIPHER_NEXT_ID_SET(cd_ctrl_hdr_t, val) \
+{ (cd_ctrl_hdr_t)->next_curr_id_cipher = \
+	((((cd_ctrl_hdr_t)->next_curr_id_cipher) \
+	& ICP_QAT_FW_COMN_CURR_ID_MASK) | \
+	((val << ICP_QAT_FW_COMN_NEXT_ID_BITPOS) \
+	& ICP_QAT_FW_COMN_NEXT_ID_MASK)) }
+
+#define ICP_QAT_FW_CIPHER_CURR_ID_GET(cd_ctrl_hdr_t) \
+	(((cd_ctrl_hdr_t)->next_curr_id_cipher) \
+	& ICP_QAT_FW_COMN_CURR_ID_MASK)
+
+#define ICP_QAT_FW_CIPHER_CURR_ID_SET(cd_ctrl_hdr_t, val) \
+{ (cd_ctrl_hdr_t)->next_curr_id_cipher = \
+	((((cd_ctrl_hdr_t)->next_curr_id_cipher) \
+	& ICP_QAT_FW_COMN_NEXT_ID_MASK) | \
+	((val) & ICP_QAT_FW_COMN_CURR_ID_MASK)) }
+
+#define ICP_QAT_FW_AUTH_NEXT_ID_GET(cd_ctrl_hdr_t) \
+	((((cd_ctrl_hdr_t)->next_curr_id_auth) & ICP_QAT_FW_COMN_NEXT_ID_MASK) \
+	>> (ICP_QAT_FW_COMN_NEXT_ID_BITPOS))
+
+#define ICP_QAT_FW_AUTH_NEXT_ID_SET(cd_ctrl_hdr_t, val) \
+{ (cd_ctrl_hdr_t)->next_curr_id_auth = \
+	((((cd_ctrl_hdr_t)->next_curr_id_auth) \
+	& ICP_QAT_FW_COMN_CURR_ID_MASK) | \
+	((val << ICP_QAT_FW_COMN_NEXT_ID_BITPOS) \
+	& ICP_QAT_FW_COMN_NEXT_ID_MASK)) }
+
+#define ICP_QAT_FW_AUTH_CURR_ID_GET(cd_ctrl_hdr_t) \
+	(((cd_ctrl_hdr_t)->next_curr_id_auth) \
+	& ICP_QAT_FW_COMN_CURR_ID_MASK)
+
+#define ICP_QAT_FW_AUTH_CURR_ID_SET(cd_ctrl_hdr_t, val) \
+{ (cd_ctrl_hdr_t)->next_curr_id_auth = \
+	((((cd_ctrl_hdr_t)->next_curr_id_auth) \
+	& ICP_QAT_FW_COMN_NEXT_ID_MASK) | \
+	((val) & ICP_QAT_FW_COMN_CURR_ID_MASK)) }
+
+#endif
diff --git a/drivers/crypto/qat/qat_common/icp_qat_fw_loader_handle.h b/drivers/crypto/qat/qat_common/icp_qat_fw_loader_handle.h
new file mode 100644
index 00000000000..5e1aa40c040
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/icp_qat_fw_loader_handle.h
@@ -0,0 +1,78 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef __ICP_QAT_FW_LOADER_HANDLE_H__
+#define __ICP_QAT_FW_LOADER_HANDLE_H__
+#include "icp_qat_uclo.h"
+
+struct icp_qat_fw_loader_ae_data {
+	unsigned int state;
+	unsigned int ustore_size;
+	unsigned int free_addr;
+	unsigned int free_size;
+	unsigned int live_ctx_mask;
+};
+
+struct icp_qat_fw_loader_hal_handle {
+	struct icp_qat_fw_loader_ae_data aes[ICP_QAT_UCLO_MAX_AE];
+	unsigned int ae_mask;
+	unsigned int slice_mask;
+	unsigned int revision_id;
+	unsigned int ae_max_num;
+	unsigned int upc_mask;
+	unsigned int max_ustore;
+};
+
+struct icp_qat_fw_loader_handle {
+	struct icp_qat_fw_loader_hal_handle *hal_handle;
+	void *obj_handle;
+	void __iomem *hal_sram_addr_v;
+	void __iomem *hal_cap_g_ctl_csr_addr_v;
+	void __iomem *hal_cap_ae_xfer_csr_addr_v;
+	void __iomem *hal_cap_ae_local_csr_addr_v;
+	void __iomem *hal_ep_csr_addr_v;
+};
+#endif
diff --git a/drivers/crypto/qat/qat_common/icp_qat_hal.h b/drivers/crypto/qat/qat_common/icp_qat_hal.h
new file mode 100644
index 00000000000..85b6d241ea8
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/icp_qat_hal.h
@@ -0,0 +1,125 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef __ICP_QAT_HAL_H
+#define __ICP_QAT_HAL_H
+#include "icp_qat_fw_loader_handle.h"
+
+enum hal_global_csr {
+	MISC_CONTROL = 0x04,
+	ICP_RESET = 0x0c,
+	ICP_GLOBAL_CLK_ENABLE = 0x50
+};
+
+enum hal_ae_csr {
+	USTORE_ADDRESS = 0x000,
+	USTORE_DATA_LOWER = 0x004,
+	USTORE_DATA_UPPER = 0x008,
+	ALU_OUT = 0x010,
+	CTX_ARB_CNTL = 0x014,
+	CTX_ENABLES = 0x018,
+	CC_ENABLE = 0x01c,
+	CSR_CTX_POINTER = 0x020,
+	CTX_STS_INDIRECT = 0x040,
+	ACTIVE_CTX_STATUS = 0x044,
+	CTX_SIG_EVENTS_INDIRECT = 0x048,
+	CTX_SIG_EVENTS_ACTIVE = 0x04c,
+	CTX_WAKEUP_EVENTS_INDIRECT = 0x050,
+	LM_ADDR_0_INDIRECT = 0x060,
+	LM_ADDR_1_INDIRECT = 0x068,
+	INDIRECT_LM_ADDR_0_BYTE_INDEX = 0x0e0,
+	INDIRECT_LM_ADDR_1_BYTE_INDEX = 0x0e8,
+	FUTURE_COUNT_SIGNAL_INDIRECT = 0x078,
+	TIMESTAMP_LOW = 0x0c0,
+	TIMESTAMP_HIGH = 0x0c4,
+	PROFILE_COUNT = 0x144,
+	SIGNATURE_ENABLE = 0x150,
+	AE_MISC_CONTROL = 0x160,
+	LOCAL_CSR_STATUS = 0x180,
+};
+
+#define UA_ECS                      (0x1 << 31)
+#define ACS_ABO_BITPOS              31
+#define ACS_ACNO                    0x7
+#define CE_ENABLE_BITPOS            0x8
+#define CE_LMADDR_0_GLOBAL_BITPOS   16
+#define CE_LMADDR_1_GLOBAL_BITPOS   17
+#define CE_NN_MODE_BITPOS           20
+#define CE_REG_PAR_ERR_BITPOS       25
+#define CE_BREAKPOINT_BITPOS        27
+#define CE_CNTL_STORE_PARITY_ERROR_BITPOS 29
+#define CE_INUSE_CONTEXTS_BITPOS    31
+#define CE_NN_MODE                  (0x1 << CE_NN_MODE_BITPOS)
+#define CE_INUSE_CONTEXTS           (0x1 << CE_INUSE_CONTEXTS_BITPOS)
+#define XCWE_VOLUNTARY              (0x1)
+#define LCS_STATUS          (0x1)
+#define MMC_SHARE_CS_BITPOS         2
+#define GLOBAL_CSR                0xA00
+
+#define SET_CAP_CSR(handle, csr, val) \
+	ADF_CSR_WR(handle->hal_cap_g_ctl_csr_addr_v, csr, val)
+#define GET_CAP_CSR(handle, csr) \
+	ADF_CSR_RD(handle->hal_cap_g_ctl_csr_addr_v, csr)
+#define SET_GLB_CSR(handle, csr, val) SET_CAP_CSR(handle, csr + GLOBAL_CSR, val)
+#define GET_GLB_CSR(handle, csr) GET_CAP_CSR(handle, GLOBAL_CSR + csr)
+#define AE_CSR(handle, ae) \
+	(handle->hal_cap_ae_local_csr_addr_v + \
+	((ae & handle->hal_handle->ae_mask) << 12))
+#define AE_CSR_ADDR(handle, ae, csr) (AE_CSR(handle, ae) + (0x3ff & csr))
+#define SET_AE_CSR(handle, ae, csr, val) \
+	ADF_CSR_WR(AE_CSR_ADDR(handle, ae, csr), 0, val)
+#define GET_AE_CSR(handle, ae, csr) ADF_CSR_RD(AE_CSR_ADDR(handle, ae, csr), 0)
+#define AE_XFER(handle, ae) \
+	(handle->hal_cap_ae_xfer_csr_addr_v + \
+	((ae & handle->hal_handle->ae_mask) << 12))
+#define AE_XFER_ADDR(handle, ae, reg) (AE_XFER(handle, ae) + \
+	((reg & 0xff) << 2))
+#define SET_AE_XFER(handle, ae, reg, val) \
+	ADF_CSR_WR(AE_XFER_ADDR(handle, ae, reg), 0, val)
+#define SRAM_WRITE(handle, addr, val) \
+	ADF_CSR_WR(handle->hal_sram_addr_v, addr, val)
+#define SRAM_READ(handle, addr) ADF_CSR_RD(handle->hal_sram_addr_v, addr)
+#endif
diff --git a/drivers/crypto/qat/qat_common/icp_qat_hw.h b/drivers/crypto/qat/qat_common/icp_qat_hw.h
new file mode 100644
index 00000000000..5031f8c10d7
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/icp_qat_hw.h
@@ -0,0 +1,305 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef _ICP_QAT_HW_H_
+#define _ICP_QAT_HW_H_
+
+enum icp_qat_hw_ae_id {
+	ICP_QAT_HW_AE_0 = 0,
+	ICP_QAT_HW_AE_1 = 1,
+	ICP_QAT_HW_AE_2 = 2,
+	ICP_QAT_HW_AE_3 = 3,
+	ICP_QAT_HW_AE_4 = 4,
+	ICP_QAT_HW_AE_5 = 5,
+	ICP_QAT_HW_AE_6 = 6,
+	ICP_QAT_HW_AE_7 = 7,
+	ICP_QAT_HW_AE_8 = 8,
+	ICP_QAT_HW_AE_9 = 9,
+	ICP_QAT_HW_AE_10 = 10,
+	ICP_QAT_HW_AE_11 = 11,
+	ICP_QAT_HW_AE_DELIMITER = 12
+};
+
+enum icp_qat_hw_qat_id {
+	ICP_QAT_HW_QAT_0 = 0,
+	ICP_QAT_HW_QAT_1 = 1,
+	ICP_QAT_HW_QAT_2 = 2,
+	ICP_QAT_HW_QAT_3 = 3,
+	ICP_QAT_HW_QAT_4 = 4,
+	ICP_QAT_HW_QAT_5 = 5,
+	ICP_QAT_HW_QAT_DELIMITER = 6
+};
+
+enum icp_qat_hw_auth_algo {
+	ICP_QAT_HW_AUTH_ALGO_NULL = 0,
+	ICP_QAT_HW_AUTH_ALGO_SHA1 = 1,
+	ICP_QAT_HW_AUTH_ALGO_MD5 = 2,
+	ICP_QAT_HW_AUTH_ALGO_SHA224 = 3,
+	ICP_QAT_HW_AUTH_ALGO_SHA256 = 4,
+	ICP_QAT_HW_AUTH_ALGO_SHA384 = 5,
+	ICP_QAT_HW_AUTH_ALGO_SHA512 = 6,
+	ICP_QAT_HW_AUTH_ALGO_AES_XCBC_MAC = 7,
+	ICP_QAT_HW_AUTH_ALGO_AES_CBC_MAC = 8,
+	ICP_QAT_HW_AUTH_ALGO_AES_F9 = 9,
+	ICP_QAT_HW_AUTH_ALGO_GALOIS_128 = 10,
+	ICP_QAT_HW_AUTH_ALGO_GALOIS_64 = 11,
+	ICP_QAT_HW_AUTH_ALGO_KASUMI_F9 = 12,
+	ICP_QAT_HW_AUTH_ALGO_SNOW_3G_UIA2 = 13,
+	ICP_QAT_HW_AUTH_ALGO_ZUC_3G_128_EIA3 = 14,
+	ICP_QAT_HW_AUTH_RESERVED_1 = 15,
+	ICP_QAT_HW_AUTH_RESERVED_2 = 16,
+	ICP_QAT_HW_AUTH_ALGO_SHA3_256 = 17,
+	ICP_QAT_HW_AUTH_RESERVED_3 = 18,
+	ICP_QAT_HW_AUTH_ALGO_SHA3_512 = 19,
+	ICP_QAT_HW_AUTH_ALGO_DELIMITER = 20
+};
+
+enum icp_qat_hw_auth_mode {
+	ICP_QAT_HW_AUTH_MODE0 = 0,
+	ICP_QAT_HW_AUTH_MODE1 = 1,
+	ICP_QAT_HW_AUTH_MODE2 = 2,
+	ICP_QAT_HW_AUTH_MODE_DELIMITER = 3
+};
+
+struct icp_qat_hw_auth_config {
+	uint32_t config;
+	uint32_t reserved;
+};
+
+#define QAT_AUTH_MODE_BITPOS 4
+#define QAT_AUTH_MODE_MASK 0xF
+#define QAT_AUTH_ALGO_BITPOS 0
+#define QAT_AUTH_ALGO_MASK 0xF
+#define QAT_AUTH_CMP_BITPOS 8
+#define QAT_AUTH_CMP_MASK 0x7F
+#define QAT_AUTH_SHA3_PADDING_BITPOS 16
+#define QAT_AUTH_SHA3_PADDING_MASK 0x1
+#define QAT_AUTH_ALGO_SHA3_BITPOS 22
+#define QAT_AUTH_ALGO_SHA3_MASK 0x3
+#define ICP_QAT_HW_AUTH_CONFIG_BUILD(mode, algo, cmp_len) \
+	(((mode & QAT_AUTH_MODE_MASK) << QAT_AUTH_MODE_BITPOS) | \
+	((algo & QAT_AUTH_ALGO_MASK) << QAT_AUTH_ALGO_BITPOS) | \
+	(((algo >> 4) & QAT_AUTH_ALGO_SHA3_MASK) << \
+	 QAT_AUTH_ALGO_SHA3_BITPOS) | \
+	 (((((algo == ICP_QAT_HW_AUTH_ALGO_SHA3_256) || \
+	(algo == ICP_QAT_HW_AUTH_ALGO_SHA3_512)) ? 1 : 0) \
+	& QAT_AUTH_SHA3_PADDING_MASK) << QAT_AUTH_SHA3_PADDING_BITPOS) | \
+	((cmp_len & QAT_AUTH_CMP_MASK) << QAT_AUTH_CMP_BITPOS))
+
+struct icp_qat_hw_auth_counter {
+	__be32 counter;
+	uint32_t reserved;
+};
+
+#define QAT_AUTH_COUNT_MASK 0xFFFFFFFF
+#define QAT_AUTH_COUNT_BITPOS 0
+#define ICP_QAT_HW_AUTH_COUNT_BUILD(val) \
+	(((val) & QAT_AUTH_COUNT_MASK) << QAT_AUTH_COUNT_BITPOS)
+
+struct icp_qat_hw_auth_setup {
+	struct icp_qat_hw_auth_config auth_config;
+	struct icp_qat_hw_auth_counter auth_counter;
+};
+
+#define QAT_HW_DEFAULT_ALIGNMENT 8
+#define QAT_HW_ROUND_UP(val, n) (((val) + ((n)-1)) & (~(n-1)))
+#define ICP_QAT_HW_NULL_STATE1_SZ 32
+#define ICP_QAT_HW_MD5_STATE1_SZ 16
+#define ICP_QAT_HW_SHA1_STATE1_SZ 20
+#define ICP_QAT_HW_SHA224_STATE1_SZ 32
+#define ICP_QAT_HW_SHA256_STATE1_SZ 32
+#define ICP_QAT_HW_SHA3_256_STATE1_SZ 32
+#define ICP_QAT_HW_SHA384_STATE1_SZ 64
+#define ICP_QAT_HW_SHA512_STATE1_SZ 64
+#define ICP_QAT_HW_SHA3_512_STATE1_SZ 64
+#define ICP_QAT_HW_SHA3_224_STATE1_SZ 28
+#define ICP_QAT_HW_SHA3_384_STATE1_SZ 48
+#define ICP_QAT_HW_AES_XCBC_MAC_STATE1_SZ 16
+#define ICP_QAT_HW_AES_CBC_MAC_STATE1_SZ 16
+#define ICP_QAT_HW_AES_F9_STATE1_SZ 32
+#define ICP_QAT_HW_KASUMI_F9_STATE1_SZ 16
+#define ICP_QAT_HW_GALOIS_128_STATE1_SZ 16
+#define ICP_QAT_HW_SNOW_3G_UIA2_STATE1_SZ 8
+#define ICP_QAT_HW_ZUC_3G_EIA3_STATE1_SZ 8
+#define ICP_QAT_HW_NULL_STATE2_SZ 32
+#define ICP_QAT_HW_MD5_STATE2_SZ 16
+#define ICP_QAT_HW_SHA1_STATE2_SZ 20
+#define ICP_QAT_HW_SHA224_STATE2_SZ 32
+#define ICP_QAT_HW_SHA256_STATE2_SZ 32
+#define ICP_QAT_HW_SHA3_256_STATE2_SZ 0
+#define ICP_QAT_HW_SHA384_STATE2_SZ 64
+#define ICP_QAT_HW_SHA512_STATE2_SZ 64
+#define ICP_QAT_HW_SHA3_512_STATE2_SZ 0
+#define ICP_QAT_HW_SHA3_224_STATE2_SZ 0
+#define ICP_QAT_HW_SHA3_384_STATE2_SZ 0
+#define ICP_QAT_HW_AES_XCBC_MAC_KEY_SZ 16
+#define ICP_QAT_HW_AES_CBC_MAC_KEY_SZ 16
+#define ICP_QAT_HW_AES_CCM_CBC_E_CTR0_SZ 16
+#define ICP_QAT_HW_F9_IK_SZ 16
+#define ICP_QAT_HW_F9_FK_SZ 16
+#define ICP_QAT_HW_KASUMI_F9_STATE2_SZ (ICP_QAT_HW_F9_IK_SZ + \
+	ICP_QAT_HW_F9_FK_SZ)
+#define ICP_QAT_HW_AES_F9_STATE2_SZ ICP_QAT_HW_KASUMI_F9_STATE2_SZ
+#define ICP_QAT_HW_SNOW_3G_UIA2_STATE2_SZ 24
+#define ICP_QAT_HW_ZUC_3G_EIA3_STATE2_SZ 32
+#define ICP_QAT_HW_GALOIS_H_SZ 16
+#define ICP_QAT_HW_GALOIS_LEN_A_SZ 8
+#define ICP_QAT_HW_GALOIS_E_CTR0_SZ 16
+
+struct icp_qat_hw_auth_sha512 {
+	struct icp_qat_hw_auth_setup inner_setup;
+	uint8_t state1[ICP_QAT_HW_SHA512_STATE1_SZ];
+	struct icp_qat_hw_auth_setup outer_setup;
+	uint8_t state2[ICP_QAT_HW_SHA512_STATE2_SZ];
+};
+
+struct icp_qat_hw_auth_algo_blk {
+	struct icp_qat_hw_auth_sha512 sha;
+};
+
+#define ICP_QAT_HW_GALOIS_LEN_A_BITPOS 0
+#define ICP_QAT_HW_GALOIS_LEN_A_MASK 0xFFFFFFFF
+
+enum icp_qat_hw_cipher_algo {
+	ICP_QAT_HW_CIPHER_ALGO_NULL = 0,
+	ICP_QAT_HW_CIPHER_ALGO_DES = 1,
+	ICP_QAT_HW_CIPHER_ALGO_3DES = 2,
+	ICP_QAT_HW_CIPHER_ALGO_AES128 = 3,
+	ICP_QAT_HW_CIPHER_ALGO_AES192 = 4,
+	ICP_QAT_HW_CIPHER_ALGO_AES256 = 5,
+	ICP_QAT_HW_CIPHER_ALGO_ARC4 = 6,
+	ICP_QAT_HW_CIPHER_ALGO_KASUMI = 7,
+	ICP_QAT_HW_CIPHER_ALGO_SNOW_3G_UEA2 = 8,
+	ICP_QAT_HW_CIPHER_ALGO_ZUC_3G_128_EEA3 = 9,
+	ICP_QAT_HW_CIPHER_DELIMITER = 10
+};
+
+enum icp_qat_hw_cipher_mode {
+	ICP_QAT_HW_CIPHER_ECB_MODE = 0,
+	ICP_QAT_HW_CIPHER_CBC_MODE = 1,
+	ICP_QAT_HW_CIPHER_CTR_MODE = 2,
+	ICP_QAT_HW_CIPHER_F8_MODE = 3,
+	ICP_QAT_HW_CIPHER_XTS_MODE = 6,
+	ICP_QAT_HW_CIPHER_MODE_DELIMITER = 7
+};
+
+struct icp_qat_hw_cipher_config {
+	uint32_t val;
+	uint32_t reserved;
+};
+
+enum icp_qat_hw_cipher_dir {
+	ICP_QAT_HW_CIPHER_ENCRYPT = 0,
+	ICP_QAT_HW_CIPHER_DECRYPT = 1,
+};
+
+enum icp_qat_hw_cipher_convert {
+	ICP_QAT_HW_CIPHER_NO_CONVERT = 0,
+	ICP_QAT_HW_CIPHER_KEY_CONVERT = 1,
+};
+
+#define QAT_CIPHER_MODE_BITPOS 4
+#define QAT_CIPHER_MODE_MASK 0xF
+#define QAT_CIPHER_ALGO_BITPOS 0
+#define QAT_CIPHER_ALGO_MASK 0xF
+#define QAT_CIPHER_CONVERT_BITPOS 9
+#define QAT_CIPHER_CONVERT_MASK 0x1
+#define QAT_CIPHER_DIR_BITPOS 8
+#define QAT_CIPHER_DIR_MASK 0x1
+#define QAT_CIPHER_MODE_F8_KEY_SZ_MULT 2
+#define QAT_CIPHER_MODE_XTS_KEY_SZ_MULT 2
+#define ICP_QAT_HW_CIPHER_CONFIG_BUILD(mode, algo, convert, dir) \
+	(((mode & QAT_CIPHER_MODE_MASK) << QAT_CIPHER_MODE_BITPOS) | \
+	((algo & QAT_CIPHER_ALGO_MASK) << QAT_CIPHER_ALGO_BITPOS) | \
+	((convert & QAT_CIPHER_CONVERT_MASK) << QAT_CIPHER_CONVERT_BITPOS) | \
+	((dir & QAT_CIPHER_DIR_MASK) << QAT_CIPHER_DIR_BITPOS))
+#define ICP_QAT_HW_DES_BLK_SZ 8
+#define ICP_QAT_HW_3DES_BLK_SZ 8
+#define ICP_QAT_HW_NULL_BLK_SZ 8
+#define ICP_QAT_HW_AES_BLK_SZ 16
+#define ICP_QAT_HW_KASUMI_BLK_SZ 8
+#define ICP_QAT_HW_SNOW_3G_BLK_SZ 8
+#define ICP_QAT_HW_ZUC_3G_BLK_SZ 8
+#define ICP_QAT_HW_NULL_KEY_SZ 256
+#define ICP_QAT_HW_DES_KEY_SZ 8
+#define ICP_QAT_HW_3DES_KEY_SZ 24
+#define ICP_QAT_HW_AES_128_KEY_SZ 16
+#define ICP_QAT_HW_AES_192_KEY_SZ 24
+#define ICP_QAT_HW_AES_256_KEY_SZ 32
+#define ICP_QAT_HW_AES_128_F8_KEY_SZ (ICP_QAT_HW_AES_128_KEY_SZ * \
+	QAT_CIPHER_MODE_F8_KEY_SZ_MULT)
+#define ICP_QAT_HW_AES_192_F8_KEY_SZ (ICP_QAT_HW_AES_192_KEY_SZ * \
+	QAT_CIPHER_MODE_F8_KEY_SZ_MULT)
+#define ICP_QAT_HW_AES_256_F8_KEY_SZ (ICP_QAT_HW_AES_256_KEY_SZ * \
+	QAT_CIPHER_MODE_F8_KEY_SZ_MULT)
+#define ICP_QAT_HW_AES_128_XTS_KEY_SZ (ICP_QAT_HW_AES_128_KEY_SZ * \
+	QAT_CIPHER_MODE_XTS_KEY_SZ_MULT)
+#define ICP_QAT_HW_AES_256_XTS_KEY_SZ (ICP_QAT_HW_AES_256_KEY_SZ * \
+	QAT_CIPHER_MODE_XTS_KEY_SZ_MULT)
+#define ICP_QAT_HW_KASUMI_KEY_SZ 16
+#define ICP_QAT_HW_KASUMI_F8_KEY_SZ (ICP_QAT_HW_KASUMI_KEY_SZ * \
+	QAT_CIPHER_MODE_F8_KEY_SZ_MULT)
+#define ICP_QAT_HW_AES_128_XTS_KEY_SZ (ICP_QAT_HW_AES_128_KEY_SZ * \
+	QAT_CIPHER_MODE_XTS_KEY_SZ_MULT)
+#define ICP_QAT_HW_AES_256_XTS_KEY_SZ (ICP_QAT_HW_AES_256_KEY_SZ * \
+	QAT_CIPHER_MODE_XTS_KEY_SZ_MULT)
+#define ICP_QAT_HW_ARC4_KEY_SZ 256
+#define ICP_QAT_HW_SNOW_3G_UEA2_KEY_SZ 16
+#define ICP_QAT_HW_SNOW_3G_UEA2_IV_SZ 16
+#define ICP_QAT_HW_ZUC_3G_EEA3_KEY_SZ 16
+#define ICP_QAT_HW_ZUC_3G_EEA3_IV_SZ 16
+#define ICP_QAT_HW_MODE_F8_NUM_REG_TO_CLEAR 2
+#define INIT_SHRAM_CONSTANTS_TABLE_SZ 1024
+
+struct icp_qat_hw_cipher_aes256_f8 {
+	struct icp_qat_hw_cipher_config cipher_config;
+	uint8_t key[ICP_QAT_HW_AES_256_F8_KEY_SZ];
+};
+
+struct icp_qat_hw_cipher_algo_blk {
+	struct icp_qat_hw_cipher_aes256_f8 aes;
+};
+#endif
diff --git a/drivers/crypto/qat/qat_common/icp_qat_uclo.h b/drivers/crypto/qat/qat_common/icp_qat_uclo.h
new file mode 100644
index 00000000000..2132a8cbc4e
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/icp_qat_uclo.h
@@ -0,0 +1,377 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef __ICP_QAT_UCLO_H__
+#define __ICP_QAT_UCLO_H__
+
+#define ICP_QAT_AC_C_CPU_TYPE     0x00400000
+#define ICP_QAT_UCLO_MAX_AE       12
+#define ICP_QAT_UCLO_MAX_CTX      8
+#define ICP_QAT_UCLO_MAX_UIMAGE   (ICP_QAT_UCLO_MAX_AE * ICP_QAT_UCLO_MAX_CTX)
+#define ICP_QAT_UCLO_MAX_USTORE   0x4000
+#define ICP_QAT_UCLO_MAX_XFER_REG 128
+#define ICP_QAT_UCLO_MAX_GPR_REG  128
+#define ICP_QAT_UCLO_MAX_NN_REG   128
+#define ICP_QAT_UCLO_MAX_LMEM_REG 1024
+#define ICP_QAT_UCLO_AE_ALL_CTX   0xff
+#define ICP_QAT_UOF_OBJID_LEN     8
+#define ICP_QAT_UOF_FID 0xc6c2
+#define ICP_QAT_UOF_MAJVER 0x4
+#define ICP_QAT_UOF_MINVER 0x11
+#define ICP_QAT_UOF_NN_MODE_NOTCARE   0xff
+#define ICP_QAT_UOF_OBJS        "UOF_OBJS"
+#define ICP_QAT_UOF_STRT        "UOF_STRT"
+#define ICP_QAT_UOF_GTID        "UOF_GTID"
+#define ICP_QAT_UOF_IMAG        "UOF_IMAG"
+#define ICP_QAT_UOF_IMEM        "UOF_IMEM"
+#define ICP_QAT_UOF_MSEG        "UOF_MSEG"
+#define ICP_QAT_UOF_LOCAL_SCOPE     1
+#define ICP_QAT_UOF_INIT_EXPR               0
+#define ICP_QAT_UOF_INIT_REG                1
+#define ICP_QAT_UOF_INIT_REG_CTX            2
+#define ICP_QAT_UOF_INIT_EXPR_ENDIAN_SWAP   3
+
+#define ICP_QAT_CTX_MODE(ae_mode) ((ae_mode) & 0xf)
+#define ICP_QAT_NN_MODE(ae_mode) (((ae_mode) >> 0x4) & 0xf)
+#define ICP_QAT_SHARED_USTORE_MODE(ae_mode) (((ae_mode) >> 0xb) & 0x1)
+#define RELOADABLE_CTX_SHARED_MODE(ae_mode) (((ae_mode) >> 0xc) & 0x1)
+
+#define ICP_QAT_LOC_MEM0_MODE(ae_mode) (((ae_mode) >> 0x8) & 0x1)
+#define ICP_QAT_LOC_MEM1_MODE(ae_mode) (((ae_mode) >> 0x9) & 0x1)
+
+enum icp_qat_uof_mem_region {
+	ICP_QAT_UOF_SRAM_REGION = 0x0,
+	ICP_QAT_UOF_LMEM_REGION = 0x3,
+	ICP_QAT_UOF_UMEM_REGION = 0x5
+};
+
+enum icp_qat_uof_regtype {
+	ICP_NO_DEST,
+	ICP_GPA_REL,
+	ICP_GPA_ABS,
+	ICP_GPB_REL,
+	ICP_GPB_ABS,
+	ICP_SR_REL,
+	ICP_SR_RD_REL,
+	ICP_SR_WR_REL,
+	ICP_SR_ABS,
+	ICP_SR_RD_ABS,
+	ICP_SR_WR_ABS,
+	ICP_DR_REL,
+	ICP_DR_RD_REL,
+	ICP_DR_WR_REL,
+	ICP_DR_ABS,
+	ICP_DR_RD_ABS,
+	ICP_DR_WR_ABS,
+	ICP_LMEM,
+	ICP_LMEM0,
+	ICP_LMEM1,
+	ICP_NEIGH_REL,
+};
+
+struct icp_qat_uclo_page {
+	struct icp_qat_uclo_encap_page *encap_page;
+	struct icp_qat_uclo_region *region;
+	unsigned int flags;
+};
+
+struct icp_qat_uclo_region {
+	struct icp_qat_uclo_page *loaded;
+	struct icp_qat_uclo_page *page;
+};
+
+struct icp_qat_uclo_aeslice {
+	struct icp_qat_uclo_region *region;
+	struct icp_qat_uclo_page *page;
+	struct icp_qat_uclo_page *cur_page[ICP_QAT_UCLO_MAX_CTX];
+	struct icp_qat_uclo_encapme *encap_image;
+	unsigned int ctx_mask_assigned;
+	unsigned int new_uaddr[ICP_QAT_UCLO_MAX_CTX];
+};
+
+struct icp_qat_uclo_aedata {
+	unsigned int slice_num;
+	unsigned int eff_ustore_size;
+	struct icp_qat_uclo_aeslice ae_slices[ICP_QAT_UCLO_MAX_CTX];
+};
+
+struct icp_qat_uof_encap_obj {
+	char *beg_uof;
+	struct icp_qat_uof_objhdr *obj_hdr;
+	struct icp_qat_uof_chunkhdr *chunk_hdr;
+	struct icp_qat_uof_varmem_seg *var_mem_seg;
+};
+
+struct icp_qat_uclo_encap_uwblock {
+	unsigned int start_addr;
+	unsigned int words_num;
+	uint64_t micro_words;
+};
+
+struct icp_qat_uclo_encap_page {
+	unsigned int def_page;
+	unsigned int page_region;
+	unsigned int beg_addr_v;
+	unsigned int beg_addr_p;
+	unsigned int micro_words_num;
+	unsigned int uwblock_num;
+	struct icp_qat_uclo_encap_uwblock *uwblock;
+};
+
+struct icp_qat_uclo_encapme {
+	struct icp_qat_uof_image *img_ptr;
+	struct icp_qat_uclo_encap_page *page;
+	unsigned int ae_reg_num;
+	struct icp_qat_uof_ae_reg *ae_reg;
+	unsigned int init_regsym_num;
+	struct icp_qat_uof_init_regsym *init_regsym;
+	unsigned int sbreak_num;
+	struct icp_qat_uof_sbreak *sbreak;
+	unsigned int uwords_num;
+};
+
+struct icp_qat_uclo_init_mem_table {
+	unsigned int entry_num;
+	struct icp_qat_uof_initmem *init_mem;
+};
+
+struct icp_qat_uclo_objhdr {
+	char *file_buff;
+	unsigned int checksum;
+	unsigned int size;
+};
+
+struct icp_qat_uof_strtable {
+	unsigned int table_len;
+	unsigned int reserved;
+	uint64_t strings;
+};
+
+struct icp_qat_uclo_objhandle {
+	unsigned int prod_type;
+	unsigned int prod_rev;
+	struct icp_qat_uclo_objhdr *obj_hdr;
+	struct icp_qat_uof_encap_obj encap_uof_obj;
+	struct icp_qat_uof_strtable str_table;
+	struct icp_qat_uclo_encapme ae_uimage[ICP_QAT_UCLO_MAX_UIMAGE];
+	struct icp_qat_uclo_aedata ae_data[ICP_QAT_UCLO_MAX_AE];
+	struct icp_qat_uclo_init_mem_table init_mem_tab;
+	struct icp_qat_uof_batch_init *lm_init_tab[ICP_QAT_UCLO_MAX_AE];
+	struct icp_qat_uof_batch_init *umem_init_tab[ICP_QAT_UCLO_MAX_AE];
+	int uimage_num;
+	int uword_in_bytes;
+	int global_inited;
+	unsigned int ae_num;
+	unsigned int ustore_phy_size;
+	void *obj_buf;
+	uint64_t *uword_buf;
+};
+
+struct icp_qat_uof_uword_block {
+	unsigned int start_addr;
+	unsigned int words_num;
+	unsigned int uword_offset;
+	unsigned int reserved;
+};
+
+struct icp_qat_uof_filehdr {
+	unsigned short file_id;
+	unsigned short reserved1;
+	char min_ver;
+	char maj_ver;
+	unsigned short reserved2;
+	unsigned short max_chunks;
+	unsigned short num_chunks;
+};
+
+struct icp_qat_uof_filechunkhdr {
+	char chunk_id[ICP_QAT_UOF_OBJID_LEN];
+	unsigned int checksum;
+	unsigned int offset;
+	unsigned int size;
+};
+
+struct icp_qat_uof_objhdr {
+	unsigned int cpu_type;
+	unsigned short min_cpu_ver;
+	unsigned short max_cpu_ver;
+	short max_chunks;
+	short num_chunks;
+	unsigned int reserved1;
+	unsigned int reserved2;
+};
+
+struct icp_qat_uof_chunkhdr {
+	char chunk_id[ICP_QAT_UOF_OBJID_LEN];
+	unsigned int offset;
+	unsigned int size;
+};
+
+struct icp_qat_uof_memvar_attr {
+	unsigned int offset_in_byte;
+	unsigned int value;
+};
+
+struct icp_qat_uof_initmem {
+	unsigned int sym_name;
+	char region;
+	char scope;
+	unsigned short reserved1;
+	unsigned int addr;
+	unsigned int num_in_bytes;
+	unsigned int val_attr_num;
+};
+
+struct icp_qat_uof_init_regsym {
+	unsigned int sym_name;
+	char init_type;
+	char value_type;
+	char reg_type;
+	unsigned char ctx;
+	unsigned int reg_addr;
+	unsigned int value;
+};
+
+struct icp_qat_uof_varmem_seg {
+	unsigned int sram_base;
+	unsigned int sram_size;
+	unsigned int sram_alignment;
+	unsigned int sdram_base;
+	unsigned int sdram_size;
+	unsigned int sdram_alignment;
+	unsigned int sdram1_base;
+	unsigned int sdram1_size;
+	unsigned int sdram1_alignment;
+	unsigned int scratch_base;
+	unsigned int scratch_size;
+	unsigned int scratch_alignment;
+};
+
+struct icp_qat_uof_gtid {
+	char tool_id[ICP_QAT_UOF_OBJID_LEN];
+	int tool_ver;
+	unsigned int reserved1;
+	unsigned int reserved2;
+};
+
+struct icp_qat_uof_sbreak {
+	unsigned int page_num;
+	unsigned int virt_uaddr;
+	unsigned char sbreak_type;
+	unsigned char reg_type;
+	unsigned short reserved1;
+	unsigned int addr_offset;
+	unsigned int reg_addr;
+};
+
+struct icp_qat_uof_code_page {
+	unsigned int page_region;
+	unsigned int page_num;
+	unsigned char def_page;
+	unsigned char reserved2;
+	unsigned short reserved1;
+	unsigned int beg_addr_v;
+	unsigned int beg_addr_p;
+	unsigned int neigh_reg_tab_offset;
+	unsigned int uc_var_tab_offset;
+	unsigned int imp_var_tab_offset;
+	unsigned int imp_expr_tab_offset;
+	unsigned int code_area_offset;
+};
+
+struct icp_qat_uof_image {
+	unsigned int img_name;
+	unsigned int ae_assigned;
+	unsigned int ctx_assigned;
+	unsigned int cpu_type;
+	unsigned int entry_address;
+	unsigned int fill_pattern[2];
+	unsigned int reloadable_size;
+	unsigned char sensitivity;
+	unsigned char reserved;
+	unsigned short ae_mode;
+	unsigned short max_ver;
+	unsigned short min_ver;
+	unsigned short image_attrib;
+	unsigned short reserved2;
+	unsigned short page_region_num;
+	unsigned short numpages;
+	unsigned int reg_tab_offset;
+	unsigned int init_reg_sym_tab;
+	unsigned int sbreak_tab;
+	unsigned int app_metadata;
+};
+
+struct icp_qat_uof_objtable {
+	unsigned int entry_num;
+};
+
+struct icp_qat_uof_ae_reg {
+	unsigned int name;
+	unsigned int vis_name;
+	unsigned short type;
+	unsigned short addr;
+	unsigned short access_mode;
+	unsigned char visible;
+	unsigned char reserved1;
+	unsigned short ref_count;
+	unsigned short reserved2;
+	unsigned int xo_id;
+};
+
+struct icp_qat_uof_code_area {
+	unsigned int micro_words_num;
+	unsigned int uword_block_tab;
+};
+
+struct icp_qat_uof_batch_init {
+	unsigned int ae;
+	unsigned int addr;
+	unsigned int *value;
+	unsigned int size;
+	struct icp_qat_uof_batch_init *next;
+};
+#endif
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
new file mode 100644
index 00000000000..59df4887295
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -0,0 +1,1038 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/crypto.h>
+#include <crypto/aead.h>
+#include <crypto/aes.h>
+#include <crypto/sha.h>
+#include <crypto/hash.h>
+#include <crypto/algapi.h>
+#include <crypto/authenc.h>
+#include <crypto/rng.h>
+#include <linux/dma-mapping.h>
+#include "adf_accel_devices.h"
+#include "adf_transport.h"
+#include "adf_common_drv.h"
+#include "qat_crypto.h"
+#include "icp_qat_hw.h"
+#include "icp_qat_fw.h"
+#include "icp_qat_fw_la.h"
+
+#define QAT_AES_HW_CONFIG_ENC(alg) \
+	ICP_QAT_HW_CIPHER_CONFIG_BUILD(ICP_QAT_HW_CIPHER_CBC_MODE, alg, \
+			ICP_QAT_HW_CIPHER_NO_CONVERT, \
+			ICP_QAT_HW_CIPHER_ENCRYPT)
+
+#define QAT_AES_HW_CONFIG_DEC(alg) \
+	ICP_QAT_HW_CIPHER_CONFIG_BUILD(ICP_QAT_HW_CIPHER_CBC_MODE, alg, \
+			ICP_QAT_HW_CIPHER_KEY_CONVERT, \
+			ICP_QAT_HW_CIPHER_DECRYPT)
+
+static atomic_t active_dev;
+
+struct qat_alg_buf {
+	uint32_t len;
+	uint32_t resrvd;
+	uint64_t addr;
+} __packed;
+
+struct qat_alg_buf_list {
+	uint64_t resrvd;
+	uint32_t num_bufs;
+	uint32_t num_mapped_bufs;
+	struct qat_alg_buf bufers[];
+} __packed __aligned(64);
+
+/* Common content descriptor */
+struct qat_alg_cd {
+	union {
+		struct qat_enc { /* Encrypt content desc */
+			struct icp_qat_hw_cipher_algo_blk cipher;
+			struct icp_qat_hw_auth_algo_blk hash;
+		} qat_enc_cd;
+		struct qat_dec { /* Decrytp content desc */
+			struct icp_qat_hw_auth_algo_blk hash;
+			struct icp_qat_hw_cipher_algo_blk cipher;
+		} qat_dec_cd;
+	};
+} __aligned(64);
+
+#define MAX_AUTH_STATE_SIZE sizeof(struct icp_qat_hw_auth_algo_blk)
+
+struct qat_auth_state {
+	uint8_t data[MAX_AUTH_STATE_SIZE];
+} __aligned(64);
+
+struct qat_alg_session_ctx {
+	struct qat_alg_cd *enc_cd;
+	dma_addr_t enc_cd_paddr;
+	struct qat_alg_cd *dec_cd;
+	dma_addr_t dec_cd_paddr;
+	struct qat_auth_state *auth_hw_state_enc;
+	dma_addr_t auth_state_enc_paddr;
+	struct qat_auth_state *auth_hw_state_dec;
+	dma_addr_t auth_state_dec_paddr;
+	struct icp_qat_fw_la_bulk_req enc_fw_req_tmpl;
+	struct icp_qat_fw_la_bulk_req dec_fw_req_tmpl;
+	struct qat_crypto_instance *inst;
+	struct crypto_tfm *tfm;
+	struct crypto_shash *hash_tfm;
+	enum icp_qat_hw_auth_algo qat_hash_alg;
+	uint8_t salt[AES_BLOCK_SIZE];
+	spinlock_t lock;	/* protects qat_alg_session_ctx struct */
+};
+
+static int get_current_node(void)
+{
+	return cpu_data(current_thread_info()->cpu).phys_proc_id;
+}
+
+static int qat_get_inter_state_size(enum icp_qat_hw_auth_algo qat_hash_alg)
+{
+	switch (qat_hash_alg) {
+	case ICP_QAT_HW_AUTH_ALGO_SHA1:
+		return ICP_QAT_HW_SHA1_STATE1_SZ;
+	case ICP_QAT_HW_AUTH_ALGO_SHA256:
+		return ICP_QAT_HW_SHA256_STATE1_SZ;
+	case ICP_QAT_HW_AUTH_ALGO_SHA512:
+		return ICP_QAT_HW_SHA512_STATE1_SZ;
+	default:
+		return -EFAULT;
+	};
+	return -EFAULT;
+}
+
+static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
+				  struct qat_alg_session_ctx *ctx,
+				  const uint8_t *auth_key,
+				  unsigned int auth_keylen, uint8_t *auth_state)
+{
+	struct {
+		struct shash_desc shash;
+		char ctx[crypto_shash_descsize(ctx->hash_tfm)];
+	} desc;
+	struct sha1_state sha1;
+	struct sha256_state sha256;
+	struct sha512_state sha512;
+	int block_size = crypto_shash_blocksize(ctx->hash_tfm);
+	int digest_size = crypto_shash_digestsize(ctx->hash_tfm);
+	uint8_t *ipad = auth_state;
+	uint8_t *opad = ipad + block_size;
+	__be32 *hash_state_out;
+	__be64 *hash512_state_out;
+	int i, offset;
+
+	desc.shash.tfm = ctx->hash_tfm;
+	desc.shash.flags = 0x0;
+
+	if (auth_keylen > block_size) {
+		char buff[SHA512_BLOCK_SIZE];
+		int ret = crypto_shash_digest(&desc.shash, auth_key,
+					      auth_keylen, buff);
+		if (ret)
+			return ret;
+
+		memcpy(ipad, buff, digest_size);
+		memcpy(opad, buff, digest_size);
+		memset(ipad + digest_size, 0, block_size - digest_size);
+		memset(opad + digest_size, 0, block_size - digest_size);
+	} else {
+		memcpy(ipad, auth_key, auth_keylen);
+		memcpy(opad, auth_key, auth_keylen);
+		memset(ipad + auth_keylen, 0, block_size - auth_keylen);
+		memset(opad + auth_keylen, 0, block_size - auth_keylen);
+	}
+
+	for (i = 0; i < block_size; i++) {
+		char *ipad_ptr = ipad + i;
+		char *opad_ptr = opad + i;
+		*ipad_ptr ^= 0x36;
+		*opad_ptr ^= 0x5C;
+	}
+
+	if (crypto_shash_init(&desc.shash))
+		return -EFAULT;
+
+	if (crypto_shash_update(&desc.shash, ipad, block_size))
+		return -EFAULT;
+
+	hash_state_out = (__be32 *)hash->sha.state1;
+	hash512_state_out = (__be64 *)hash_state_out;
+
+	switch (ctx->qat_hash_alg) {
+	case ICP_QAT_HW_AUTH_ALGO_SHA1:
+		if (crypto_shash_export(&desc.shash, &sha1))
+			return -EFAULT;
+		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
+			*hash_state_out = cpu_to_be32(*(sha1.state + i));
+		break;
+	case ICP_QAT_HW_AUTH_ALGO_SHA256:
+		if (crypto_shash_export(&desc.shash, &sha256))
+			return -EFAULT;
+		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
+			*hash_state_out = cpu_to_be32(*(sha256.state + i));
+		break;
+	case ICP_QAT_HW_AUTH_ALGO_SHA512:
+		if (crypto_shash_export(&desc.shash, &sha512))
+			return -EFAULT;
+		for (i = 0; i < digest_size >> 3; i++, hash512_state_out++)
+			*hash512_state_out = cpu_to_be64(*(sha512.state + i));
+		break;
+	default:
+		return -EFAULT;
+	}
+
+	if (crypto_shash_init(&desc.shash))
+		return -EFAULT;
+
+	if (crypto_shash_update(&desc.shash, opad, block_size))
+		return -EFAULT;
+
+	offset = round_up(qat_get_inter_state_size(ctx->qat_hash_alg), 8);
+	hash_state_out = (__be32 *)(hash->sha.state1 + offset);
+	hash512_state_out = (__be64 *)hash_state_out;
+
+	switch (ctx->qat_hash_alg) {
+	case ICP_QAT_HW_AUTH_ALGO_SHA1:
+		if (crypto_shash_export(&desc.shash, &sha1))
+			return -EFAULT;
+		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
+			*hash_state_out = cpu_to_be32(*(sha1.state + i));
+		break;
+	case ICP_QAT_HW_AUTH_ALGO_SHA256:
+		if (crypto_shash_export(&desc.shash, &sha256))
+			return -EFAULT;
+		for (i = 0; i < digest_size >> 2; i++, hash_state_out++)
+			*hash_state_out = cpu_to_be32(*(sha256.state + i));
+		break;
+	case ICP_QAT_HW_AUTH_ALGO_SHA512:
+		if (crypto_shash_export(&desc.shash, &sha512))
+			return -EFAULT;
+		for (i = 0; i < digest_size >> 3; i++, hash512_state_out++)
+			*hash512_state_out = cpu_to_be64(*(sha512.state + i));
+		break;
+	default:
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void qat_alg_init_common_hdr(struct icp_qat_fw_comn_req_hdr *header)
+{
+	header->hdr_flags =
+		ICP_QAT_FW_COMN_HDR_FLAGS_BUILD(ICP_QAT_FW_COMN_REQ_FLAG_SET);
+	header->service_type = ICP_QAT_FW_COMN_REQ_CPM_FW_LA;
+	header->comn_req_flags =
+		ICP_QAT_FW_COMN_FLAGS_BUILD(QAT_COMN_CD_FLD_TYPE_64BIT_ADR,
+					    QAT_COMN_PTR_TYPE_SGL);
+	ICP_QAT_FW_LA_DIGEST_IN_BUFFER_SET(header->serv_specif_flags,
+					   ICP_QAT_FW_LA_DIGEST_IN_BUFFER);
+	ICP_QAT_FW_LA_PARTIAL_SET(header->serv_specif_flags,
+				  ICP_QAT_FW_LA_PARTIAL_NONE);
+	ICP_QAT_FW_LA_CIPH_IV_FLD_FLAG_SET(header->serv_specif_flags,
+					   ICP_QAT_FW_CIPH_IV_16BYTE_DATA);
+	ICP_QAT_FW_LA_PROTO_SET(header->serv_specif_flags,
+				ICP_QAT_FW_LA_NO_PROTO);
+	ICP_QAT_FW_LA_UPDATE_STATE_SET(header->serv_specif_flags,
+				       ICP_QAT_FW_LA_NO_UPDATE_STATE);
+}
+
+static int qat_alg_init_enc_session(struct qat_alg_session_ctx *ctx,
+				    int alg, struct crypto_authenc_keys *keys)
+{
+	struct crypto_aead *aead_tfm = __crypto_aead_cast(ctx->tfm);
+	unsigned int digestsize = crypto_aead_crt(aead_tfm)->authsize;
+	struct qat_enc *enc_ctx = &ctx->enc_cd->qat_enc_cd;
+	struct icp_qat_hw_cipher_algo_blk *cipher = &enc_ctx->cipher;
+	struct icp_qat_hw_auth_algo_blk *hash =
+		(struct icp_qat_hw_auth_algo_blk *)((char *)enc_ctx +
+		sizeof(struct icp_qat_hw_auth_setup) + keys->enckeylen);
+	struct icp_qat_fw_la_bulk_req *req_tmpl = &ctx->enc_fw_req_tmpl;
+	struct icp_qat_fw_comn_req_hdr_cd_pars *cd_pars = &req_tmpl->cd_pars;
+	struct icp_qat_fw_comn_req_hdr *header = &req_tmpl->comn_hdr;
+	void *ptr = &req_tmpl->cd_ctrl;
+	struct icp_qat_fw_cipher_cd_ctrl_hdr *cipher_cd_ctrl = ptr;
+	struct icp_qat_fw_auth_cd_ctrl_hdr *hash_cd_ctrl = ptr;
+	struct icp_qat_fw_la_auth_req_params *auth_param =
+		(struct icp_qat_fw_la_auth_req_params *)
+		((char *)&req_tmpl->serv_specif_rqpars +
+		 sizeof(struct icp_qat_fw_la_cipher_req_params));
+
+	/* CD setup */
+	cipher->aes.cipher_config.val = QAT_AES_HW_CONFIG_ENC(alg);
+	memcpy(cipher->aes.key, keys->enckey, keys->enckeylen);
+	hash->sha.inner_setup.auth_config.config =
+		ICP_QAT_HW_AUTH_CONFIG_BUILD(ICP_QAT_HW_AUTH_MODE1,
+					     ctx->qat_hash_alg, digestsize);
+	hash->sha.inner_setup.auth_counter.counter =
+		cpu_to_be32(crypto_shash_blocksize(ctx->hash_tfm));
+
+	if (qat_alg_do_precomputes(hash, ctx, keys->authkey, keys->authkeylen,
+				   (uint8_t *)ctx->auth_hw_state_enc))
+		return -EFAULT;
+
+	/* Request setup */
+	qat_alg_init_common_hdr(header);
+	header->service_cmd_id = ICP_QAT_FW_LA_CMD_CIPHER_HASH;
+	ICP_QAT_FW_LA_RET_AUTH_SET(header->serv_specif_flags,
+				   ICP_QAT_FW_LA_RET_AUTH_RES);
+	ICP_QAT_FW_LA_CMP_AUTH_SET(header->serv_specif_flags,
+				   ICP_QAT_FW_LA_NO_CMP_AUTH_RES);
+	cd_pars->u.s.content_desc_addr = ctx->enc_cd_paddr;
+	cd_pars->u.s.content_desc_params_sz = sizeof(struct qat_alg_cd) >> 3;
+
+	/* Cipher CD config setup */
+	cipher_cd_ctrl->cipher_key_sz = keys->enckeylen >> 3;
+	cipher_cd_ctrl->cipher_state_sz = AES_BLOCK_SIZE >> 3;
+	cipher_cd_ctrl->cipher_cfg_offset = 0;
+	ICP_QAT_FW_COMN_CURR_ID_SET(cipher_cd_ctrl, ICP_QAT_FW_SLICE_CIPHER);
+	ICP_QAT_FW_COMN_NEXT_ID_SET(cipher_cd_ctrl, ICP_QAT_FW_SLICE_AUTH);
+	/* Auth CD config setup */
+	hash_cd_ctrl->hash_cfg_offset = ((char *)hash - (char *)cipher) >> 3;
+	hash_cd_ctrl->hash_flags = ICP_QAT_FW_AUTH_HDR_FLAG_NO_NESTED;
+	hash_cd_ctrl->inner_res_sz = digestsize;
+	hash_cd_ctrl->final_sz = digestsize;
+
+	switch (ctx->qat_hash_alg) {
+	case ICP_QAT_HW_AUTH_ALGO_SHA1:
+		hash_cd_ctrl->inner_state1_sz =
+			round_up(ICP_QAT_HW_SHA1_STATE1_SZ, 8);
+		hash_cd_ctrl->inner_state2_sz =
+			round_up(ICP_QAT_HW_SHA1_STATE2_SZ, 8);
+		break;
+	case ICP_QAT_HW_AUTH_ALGO_SHA256:
+		hash_cd_ctrl->inner_state1_sz = ICP_QAT_HW_SHA256_STATE1_SZ;
+		hash_cd_ctrl->inner_state2_sz = ICP_QAT_HW_SHA256_STATE2_SZ;
+		break;
+	case ICP_QAT_HW_AUTH_ALGO_SHA512:
+		hash_cd_ctrl->inner_state1_sz = ICP_QAT_HW_SHA512_STATE1_SZ;
+		hash_cd_ctrl->inner_state2_sz = ICP_QAT_HW_SHA512_STATE2_SZ;
+		break;
+	default:
+		break;
+	}
+	hash_cd_ctrl->inner_state2_offset = hash_cd_ctrl->hash_cfg_offset +
+			((sizeof(struct icp_qat_hw_auth_setup) +
+			 round_up(hash_cd_ctrl->inner_state1_sz, 8)) >> 3);
+	auth_param->u1.auth_partial_st_prefix = ctx->auth_state_enc_paddr +
+			sizeof(struct icp_qat_hw_auth_counter) +
+			round_up(hash_cd_ctrl->inner_state1_sz, 8);
+	ICP_QAT_FW_COMN_CURR_ID_SET(hash_cd_ctrl, ICP_QAT_FW_SLICE_AUTH);
+	ICP_QAT_FW_COMN_NEXT_ID_SET(hash_cd_ctrl, ICP_QAT_FW_SLICE_DRAM_WR);
+	return 0;
+}
+
+static int qat_alg_init_dec_session(struct qat_alg_session_ctx *ctx,
+				    int alg, struct crypto_authenc_keys *keys)
+{
+	struct crypto_aead *aead_tfm = __crypto_aead_cast(ctx->tfm);
+	unsigned int digestsize = crypto_aead_crt(aead_tfm)->authsize;
+	struct qat_dec *dec_ctx = &ctx->dec_cd->qat_dec_cd;
+	struct icp_qat_hw_auth_algo_blk *hash = &dec_ctx->hash;
+	struct icp_qat_hw_cipher_algo_blk *cipher =
+		(struct icp_qat_hw_cipher_algo_blk *)((char *)dec_ctx +
+		sizeof(struct icp_qat_hw_auth_setup) +
+		roundup(crypto_shash_digestsize(ctx->hash_tfm), 8) * 2);
+	struct icp_qat_fw_la_bulk_req *req_tmpl = &ctx->dec_fw_req_tmpl;
+	struct icp_qat_fw_comn_req_hdr_cd_pars *cd_pars = &req_tmpl->cd_pars;
+	struct icp_qat_fw_comn_req_hdr *header = &req_tmpl->comn_hdr;
+	void *ptr = &req_tmpl->cd_ctrl;
+	struct icp_qat_fw_cipher_cd_ctrl_hdr *cipher_cd_ctrl = ptr;
+	struct icp_qat_fw_auth_cd_ctrl_hdr *hash_cd_ctrl = ptr;
+	struct icp_qat_fw_la_auth_req_params *auth_param =
+		(struct icp_qat_fw_la_auth_req_params *)
+		((char *)&req_tmpl->serv_specif_rqpars +
+		sizeof(struct icp_qat_fw_la_cipher_req_params));
+
+	/* CD setup */
+	cipher->aes.cipher_config.val = QAT_AES_HW_CONFIG_DEC(alg);
+	memcpy(cipher->aes.key, keys->enckey, keys->enckeylen);
+	hash->sha.inner_setup.auth_config.config =
+		ICP_QAT_HW_AUTH_CONFIG_BUILD(ICP_QAT_HW_AUTH_MODE1,
+					     ctx->qat_hash_alg,
+					     digestsize);
+	hash->sha.inner_setup.auth_counter.counter =
+		cpu_to_be32(crypto_shash_blocksize(ctx->hash_tfm));
+
+	if (qat_alg_do_precomputes(hash, ctx, keys->authkey, keys->authkeylen,
+				   (uint8_t *)ctx->auth_hw_state_dec))
+		return -EFAULT;
+
+	/* Request setup */
+	qat_alg_init_common_hdr(header);
+	header->service_cmd_id = ICP_QAT_FW_LA_CMD_HASH_CIPHER;
+	ICP_QAT_FW_LA_RET_AUTH_SET(header->serv_specif_flags,
+				   ICP_QAT_FW_LA_NO_RET_AUTH_RES);
+	ICP_QAT_FW_LA_CMP_AUTH_SET(header->serv_specif_flags,
+				   ICP_QAT_FW_LA_CMP_AUTH_RES);
+	cd_pars->u.s.content_desc_addr = ctx->dec_cd_paddr;
+	cd_pars->u.s.content_desc_params_sz = sizeof(struct qat_alg_cd) >> 3;
+
+	/* Cipher CD config setup */
+	cipher_cd_ctrl->cipher_key_sz = keys->enckeylen >> 3;
+	cipher_cd_ctrl->cipher_state_sz = AES_BLOCK_SIZE >> 3;
+	cipher_cd_ctrl->cipher_cfg_offset =
+		(sizeof(struct icp_qat_hw_auth_setup) +
+		 roundup(crypto_shash_digestsize(ctx->hash_tfm), 8) * 2) >> 3;
+	ICP_QAT_FW_COMN_CURR_ID_SET(cipher_cd_ctrl, ICP_QAT_FW_SLICE_CIPHER);
+	ICP_QAT_FW_COMN_NEXT_ID_SET(cipher_cd_ctrl, ICP_QAT_FW_SLICE_DRAM_WR);
+
+	/* Auth CD config setup */
+	hash_cd_ctrl->hash_cfg_offset = 0;
+	hash_cd_ctrl->hash_flags = ICP_QAT_FW_AUTH_HDR_FLAG_NO_NESTED;
+	hash_cd_ctrl->inner_res_sz = digestsize;
+	hash_cd_ctrl->final_sz = digestsize;
+
+	switch (ctx->qat_hash_alg) {
+	case ICP_QAT_HW_AUTH_ALGO_SHA1:
+		hash_cd_ctrl->inner_state1_sz =
+			round_up(ICP_QAT_HW_SHA1_STATE1_SZ, 8);
+		hash_cd_ctrl->inner_state2_sz =
+			round_up(ICP_QAT_HW_SHA1_STATE2_SZ, 8);
+		break;
+	case ICP_QAT_HW_AUTH_ALGO_SHA256:
+		hash_cd_ctrl->inner_state1_sz = ICP_QAT_HW_SHA256_STATE1_SZ;
+		hash_cd_ctrl->inner_state2_sz = ICP_QAT_HW_SHA256_STATE2_SZ;
+		break;
+	case ICP_QAT_HW_AUTH_ALGO_SHA512:
+		hash_cd_ctrl->inner_state1_sz = ICP_QAT_HW_SHA512_STATE1_SZ;
+		hash_cd_ctrl->inner_state2_sz = ICP_QAT_HW_SHA512_STATE2_SZ;
+		break;
+	default:
+		break;
+	}
+
+	hash_cd_ctrl->inner_state2_offset = hash_cd_ctrl->hash_cfg_offset +
+			((sizeof(struct icp_qat_hw_auth_setup) +
+			 round_up(hash_cd_ctrl->inner_state1_sz, 8)) >> 3);
+	auth_param->u1.auth_partial_st_prefix = ctx->auth_state_enc_paddr +
+			sizeof(struct icp_qat_hw_auth_counter) +
+			round_up(hash_cd_ctrl->inner_state1_sz, 8);
+	auth_param->auth_res_sz = digestsize;
+	ICP_QAT_FW_COMN_CURR_ID_SET(hash_cd_ctrl, ICP_QAT_FW_SLICE_AUTH);
+	ICP_QAT_FW_COMN_NEXT_ID_SET(hash_cd_ctrl, ICP_QAT_FW_SLICE_CIPHER);
+	return 0;
+}
+
+static int qat_alg_init_sessions(struct qat_alg_session_ctx *ctx,
+				 const uint8_t *key, unsigned int keylen)
+{
+	struct crypto_authenc_keys keys;
+	int alg;
+
+	if (crypto_rng_get_bytes(crypto_default_rng, ctx->salt, AES_BLOCK_SIZE))
+		return -EFAULT;
+
+	if (crypto_authenc_extractkeys(&keys, key, keylen))
+		goto bad_key;
+
+	switch (keys.enckeylen) {
+	case AES_KEYSIZE_128:
+		alg = ICP_QAT_HW_CIPHER_ALGO_AES128;
+		break;
+	case AES_KEYSIZE_192:
+		alg = ICP_QAT_HW_CIPHER_ALGO_AES192;
+		break;
+	case AES_KEYSIZE_256:
+		alg = ICP_QAT_HW_CIPHER_ALGO_AES256;
+		break;
+	default:
+		goto bad_key;
+		break;
+	}
+
+	if (qat_alg_init_enc_session(ctx, alg, &keys))
+		goto error;
+
+	if (qat_alg_init_dec_session(ctx, alg, &keys))
+		goto error;
+
+	return 0;
+bad_key:
+	crypto_tfm_set_flags(ctx->tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	return -EINVAL;
+error:
+	return -EFAULT;
+}
+
+static int qat_alg_setkey(struct crypto_aead *tfm, const uint8_t *key,
+			  unsigned int keylen)
+{
+	struct qat_alg_session_ctx *ctx = crypto_aead_ctx(tfm);
+	struct device *dev;
+
+	spin_lock(&ctx->lock);
+	if (ctx->enc_cd) {
+		/* rekeying */
+		dev = &GET_DEV(ctx->inst->accel_dev);
+		memset(ctx->enc_cd, 0, sizeof(struct qat_alg_cd));
+		memset(ctx->dec_cd, 0, sizeof(struct qat_alg_cd));
+		memset(ctx->auth_hw_state_enc, 0,
+		       sizeof(struct qat_auth_state));
+		memset(ctx->auth_hw_state_dec, 0,
+		       sizeof(struct qat_auth_state));
+		memset(&ctx->enc_fw_req_tmpl, 0,
+		       sizeof(struct icp_qat_fw_la_bulk_req));
+		memset(&ctx->dec_fw_req_tmpl, 0,
+		       sizeof(struct icp_qat_fw_la_bulk_req));
+	} else {
+		/* new key */
+		int node = get_current_node();
+		struct qat_crypto_instance *inst =
+				qat_crypto_get_instance_node(node);
+		if (!inst) {
+			spin_unlock(&ctx->lock);
+			return -EINVAL;
+		}
+
+		dev = &GET_DEV(inst->accel_dev);
+		ctx->inst = inst;
+		ctx->enc_cd = dma_zalloc_coherent(dev,
+						  sizeof(struct qat_alg_cd),
+						  &ctx->enc_cd_paddr,
+						  GFP_ATOMIC);
+		if (!ctx->enc_cd) {
+			spin_unlock(&ctx->lock);
+			return -ENOMEM;
+		}
+		ctx->dec_cd = dma_zalloc_coherent(dev,
+						  sizeof(struct qat_alg_cd),
+						  &ctx->dec_cd_paddr,
+						  GFP_ATOMIC);
+		if (!ctx->dec_cd) {
+			spin_unlock(&ctx->lock);
+			goto out_free_enc;
+		}
+		ctx->auth_hw_state_enc =
+			dma_zalloc_coherent(dev, sizeof(struct qat_auth_state),
+					    &ctx->auth_state_enc_paddr,
+					    GFP_ATOMIC);
+		if (!ctx->auth_hw_state_enc) {
+			spin_unlock(&ctx->lock);
+			goto out_free_dec;
+		}
+		ctx->auth_hw_state_dec =
+			dma_zalloc_coherent(dev, sizeof(struct qat_auth_state),
+					    &ctx->auth_state_dec_paddr,
+					    GFP_ATOMIC);
+		if (!ctx->auth_hw_state_dec) {
+			spin_unlock(&ctx->lock);
+			goto out_free_auth_enc;
+		}
+	}
+	spin_unlock(&ctx->lock);
+	if (qat_alg_init_sessions(ctx, key, keylen))
+		goto out_free_all;
+
+	return 0;
+
+out_free_all:
+	dma_free_coherent(dev, sizeof(struct qat_auth_state),
+			  ctx->auth_hw_state_dec, ctx->auth_state_dec_paddr);
+	ctx->auth_hw_state_dec = NULL;
+out_free_auth_enc:
+	dma_free_coherent(dev, sizeof(struct qat_auth_state),
+			  ctx->auth_hw_state_enc, ctx->auth_state_enc_paddr);
+	ctx->auth_hw_state_enc = NULL;
+out_free_dec:
+	dma_free_coherent(dev, sizeof(struct qat_alg_cd),
+			  ctx->dec_cd, ctx->dec_cd_paddr);
+	ctx->dec_cd = NULL;
+out_free_enc:
+	dma_free_coherent(dev, sizeof(struct qat_alg_cd),
+			  ctx->enc_cd, ctx->enc_cd_paddr);
+	ctx->enc_cd = NULL;
+	return -ENOMEM;
+}
+
+static void qat_alg_free_bufl(struct qat_crypto_instance *inst,
+			      struct qat_crypto_request *qat_req)
+{
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	struct qat_alg_buf_list *bl = qat_req->buf.bl;
+	struct qat_alg_buf_list *blout = qat_req->buf.blout;
+	dma_addr_t blp = qat_req->buf.blp;
+	dma_addr_t blpout = qat_req->buf.bloutp;
+	size_t sz = qat_req->buf.sz;
+	int i, bufs = bl->num_bufs;
+
+	for (i = 0; i < bl->num_bufs; i++)
+		dma_unmap_single(dev, bl->bufers[i].addr,
+				 bl->bufers[i].len, DMA_BIDIRECTIONAL);
+
+	dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE);
+	kfree(bl);
+	if (blp != blpout) {
+		/* If out of place operation dma unmap only data */
+		int bufless = bufs - blout->num_mapped_bufs;
+
+		for (i = bufless; i < bufs; i++) {
+			dma_unmap_single(dev, blout->bufers[i].addr,
+					 blout->bufers[i].len,
+					 DMA_BIDIRECTIONAL);
+		}
+		dma_unmap_single(dev, blpout, sz, DMA_TO_DEVICE);
+		kfree(blout);
+	}
+}
+
+static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst,
+			       struct scatterlist *assoc,
+			       struct scatterlist *sgl,
+			       struct scatterlist *sglout, uint8_t *iv,
+			       uint8_t ivlen,
+			       struct qat_crypto_request *qat_req)
+{
+	struct device *dev = &GET_DEV(inst->accel_dev);
+	int i, bufs = 0, n = sg_nents(sgl), assoc_n = sg_nents(assoc);
+	struct qat_alg_buf_list *bufl;
+	struct qat_alg_buf_list *buflout = NULL;
+	dma_addr_t blp;
+	dma_addr_t bloutp = 0;
+	struct scatterlist *sg;
+	size_t sz = sizeof(struct qat_alg_buf_list) +
+			((1 + n + assoc_n) * sizeof(struct qat_alg_buf));
+
+	if (unlikely(!n))
+		return -EINVAL;
+
+	bufl = kmalloc_node(sz, GFP_ATOMIC, inst->accel_dev->numa_node);
+	if (unlikely(!bufl))
+		return -ENOMEM;
+
+	blp = dma_map_single(dev, bufl, sz, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev, blp)))
+		goto err;
+
+	for_each_sg(assoc, sg, assoc_n, i) {
+		bufl->bufers[bufs].addr = dma_map_single(dev,
+							 sg_virt(sg),
+							 sg->length,
+							 DMA_BIDIRECTIONAL);
+		bufl->bufers[bufs].len = sg->length;
+		if (unlikely(dma_mapping_error(dev, bufl->bufers[bufs].addr)))
+			goto err;
+		bufs++;
+	}
+	bufl->bufers[bufs].addr = dma_map_single(dev, iv, ivlen,
+						 DMA_BIDIRECTIONAL);
+	bufl->bufers[bufs].len = ivlen;
+	if (unlikely(dma_mapping_error(dev, bufl->bufers[bufs].addr)))
+		goto err;
+	bufs++;
+
+	for_each_sg(sgl, sg, n, i) {
+		int y = i + bufs;
+
+		bufl->bufers[y].addr = dma_map_single(dev, sg_virt(sg),
+						      sg->length,
+						      DMA_BIDIRECTIONAL);
+		bufl->bufers[y].len = sg->length;
+		if (unlikely(dma_mapping_error(dev, bufl->bufers[y].addr)))
+			goto err;
+	}
+	bufl->num_bufs = n + bufs;
+	qat_req->buf.bl = bufl;
+	qat_req->buf.blp = blp;
+	qat_req->buf.sz = sz;
+	/* Handle out of place operation */
+	if (sgl != sglout) {
+		struct qat_alg_buf *bufers;
+
+		buflout = kmalloc_node(sz, GFP_ATOMIC,
+				       inst->accel_dev->numa_node);
+		if (unlikely(!buflout))
+			goto err;
+		bloutp = dma_map_single(dev, buflout, sz, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(dev, bloutp)))
+			goto err;
+		bufers = buflout->bufers;
+		/* For out of place operation dma map only data and
+		 * reuse assoc mapping and iv */
+		for (i = 0; i < bufs; i++) {
+			bufers[i].len = bufl->bufers[i].len;
+			bufers[i].addr = bufl->bufers[i].addr;
+		}
+		for_each_sg(sglout, sg, n, i) {
+			int y = i + bufs;
+
+			bufers[y].addr = dma_map_single(dev, sg_virt(sg),
+							sg->length,
+							DMA_BIDIRECTIONAL);
+			buflout->bufers[y].len = sg->length;
+			if (unlikely(dma_mapping_error(dev, bufers[y].addr)))
+				goto err;
+		}
+		buflout->num_bufs = n + bufs;
+		buflout->num_mapped_bufs = n;
+		qat_req->buf.blout = buflout;
+		qat_req->buf.bloutp = bloutp;
+	} else {
+		/* Otherwise set the src and dst to the same address */
+		qat_req->buf.bloutp = qat_req->buf.blp;
+	}
+	return 0;
+err:
+	dev_err(dev, "Failed to map buf for dma\n");
+	for_each_sg(sgl, sg, n + bufs, i) {
+		if (!dma_mapping_error(dev, bufl->bufers[i].addr)) {
+			dma_unmap_single(dev, bufl->bufers[i].addr,
+					 bufl->bufers[i].len,
+					 DMA_BIDIRECTIONAL);
+		}
+	}
+	if (!dma_mapping_error(dev, blp))
+		dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE);
+	kfree(bufl);
+	if (sgl != sglout && buflout) {
+		for_each_sg(sglout, sg, n, i) {
+			int y = i + bufs;
+
+			if (!dma_mapping_error(dev, buflout->bufers[y].addr))
+				dma_unmap_single(dev, buflout->bufers[y].addr,
+						 buflout->bufers[y].len,
+						 DMA_BIDIRECTIONAL);
+		}
+		if (!dma_mapping_error(dev, bloutp))
+			dma_unmap_single(dev, bloutp, sz, DMA_TO_DEVICE);
+		kfree(buflout);
+	}
+	return -ENOMEM;
+}
+
+void qat_alg_callback(void *resp)
+{
+	struct icp_qat_fw_la_resp *qat_resp = resp;
+	struct qat_crypto_request *qat_req =
+				(void *)(__force long)qat_resp->opaque_data;
+	struct qat_alg_session_ctx *ctx = qat_req->ctx;
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct aead_request *areq = qat_req->areq;
+	uint8_t stat_filed = qat_resp->comn_resp.comn_status;
+	int res = 0, qat_res = ICP_QAT_FW_COMN_RESP_CRYPTO_STAT_GET(stat_filed);
+
+	qat_alg_free_bufl(inst, qat_req);
+	if (unlikely(qat_res != ICP_QAT_FW_COMN_STATUS_FLAG_OK))
+		res = -EBADMSG;
+	areq->base.complete(&areq->base, res);
+}
+
+static int qat_alg_dec(struct aead_request *areq)
+{
+	struct crypto_aead *aead_tfm = crypto_aead_reqtfm(areq);
+	struct crypto_tfm *tfm = crypto_aead_tfm(aead_tfm);
+	struct qat_alg_session_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qat_crypto_request *qat_req = aead_request_ctx(areq);
+	struct icp_qat_fw_la_cipher_req_params *cipher_param;
+	struct icp_qat_fw_la_auth_req_params *auth_param;
+	struct icp_qat_fw_la_bulk_req *msg;
+	int digst_size = crypto_aead_crt(aead_tfm)->authsize;
+	int ret, ctr = 0;
+
+	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->src, areq->dst,
+				  areq->iv, AES_BLOCK_SIZE, qat_req);
+	if (unlikely(ret))
+		return ret;
+
+	msg = &qat_req->req;
+	*msg = ctx->dec_fw_req_tmpl;
+	qat_req->ctx = ctx;
+	qat_req->areq = areq;
+	qat_req->req.comn_mid.opaque_data = (uint64_t)(__force long)qat_req;
+	qat_req->req.comn_mid.src_data_addr = qat_req->buf.blp;
+	qat_req->req.comn_mid.dest_data_addr = qat_req->buf.bloutp;
+	cipher_param = (void *)&qat_req->req.serv_specif_rqpars;
+	cipher_param->cipher_length = areq->cryptlen - digst_size;
+	cipher_param->cipher_offset = areq->assoclen + AES_BLOCK_SIZE;
+	memcpy(cipher_param->u.cipher_IV_array, areq->iv, AES_BLOCK_SIZE);
+	auth_param = (void *)((uint8_t *)cipher_param + sizeof(*cipher_param));
+	auth_param->auth_off = 0;
+	auth_param->auth_len = areq->assoclen +
+				cipher_param->cipher_length + AES_BLOCK_SIZE;
+	do {
+		ret = adf_send_message(ctx->inst->sym_tx, (uint32_t *)msg);
+	} while (ret == -EAGAIN && ctr++ < 10);
+
+	if (ret == -EAGAIN) {
+		qat_alg_free_bufl(ctx->inst, qat_req);
+		return -EBUSY;
+	}
+	return -EINPROGRESS;
+}
+
+static int qat_alg_enc_internal(struct aead_request *areq, uint8_t *iv,
+				int enc_iv)
+{
+	struct crypto_aead *aead_tfm = crypto_aead_reqtfm(areq);
+	struct crypto_tfm *tfm = crypto_aead_tfm(aead_tfm);
+	struct qat_alg_session_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qat_crypto_request *qat_req = aead_request_ctx(areq);
+	struct icp_qat_fw_la_cipher_req_params *cipher_param;
+	struct icp_qat_fw_la_auth_req_params *auth_param;
+	struct icp_qat_fw_la_bulk_req *msg;
+	int ret, ctr = 0;
+
+	ret = qat_alg_sgl_to_bufl(ctx->inst, areq->assoc, areq->src, areq->dst,
+				  iv, AES_BLOCK_SIZE, qat_req);
+	if (unlikely(ret))
+		return ret;
+
+	msg = &qat_req->req;
+	*msg = ctx->enc_fw_req_tmpl;
+	qat_req->ctx = ctx;
+	qat_req->areq = areq;
+	qat_req->req.comn_mid.opaque_data = (uint64_t)(__force long)qat_req;
+	qat_req->req.comn_mid.src_data_addr = qat_req->buf.blp;
+	qat_req->req.comn_mid.dest_data_addr = qat_req->buf.bloutp;
+	cipher_param = (void *)&qat_req->req.serv_specif_rqpars;
+	auth_param = (void *)((uint8_t *)cipher_param + sizeof(*cipher_param));
+
+	if (enc_iv) {
+		cipher_param->cipher_length = areq->cryptlen + AES_BLOCK_SIZE;
+		cipher_param->cipher_offset = areq->assoclen;
+	} else {
+		memcpy(cipher_param->u.cipher_IV_array, iv, AES_BLOCK_SIZE);
+		cipher_param->cipher_length = areq->cryptlen;
+		cipher_param->cipher_offset = areq->assoclen + AES_BLOCK_SIZE;
+	}
+	auth_param->auth_off = 0;
+	auth_param->auth_len = areq->assoclen + areq->cryptlen + AES_BLOCK_SIZE;
+
+	do {
+		ret = adf_send_message(ctx->inst->sym_tx, (uint32_t *)msg);
+	} while (ret == -EAGAIN && ctr++ < 10);
+
+	if (ret == -EAGAIN) {
+		qat_alg_free_bufl(ctx->inst, qat_req);
+		return -EBUSY;
+	}
+	return -EINPROGRESS;
+}
+
+static int qat_alg_enc(struct aead_request *areq)
+{
+	return qat_alg_enc_internal(areq, areq->iv, 0);
+}
+
+static int qat_alg_genivenc(struct aead_givcrypt_request *req)
+{
+	struct crypto_aead *aead_tfm = crypto_aead_reqtfm(&req->areq);
+	struct crypto_tfm *tfm = crypto_aead_tfm(aead_tfm);
+	struct qat_alg_session_ctx *ctx = crypto_tfm_ctx(tfm);
+	__be64 seq;
+
+	memcpy(req->giv, ctx->salt, AES_BLOCK_SIZE);
+	seq = cpu_to_be64(req->seq);
+	memcpy(req->giv + AES_BLOCK_SIZE - sizeof(uint64_t),
+	       &seq, sizeof(uint64_t));
+	return qat_alg_enc_internal(&req->areq, req->giv, 1);
+}
+
+static int qat_alg_init(struct crypto_tfm *tfm,
+			enum icp_qat_hw_auth_algo hash, const char *hash_name)
+{
+	struct qat_alg_session_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	memset(ctx, '\0', sizeof(*ctx));
+	ctx->hash_tfm = crypto_alloc_shash(hash_name, 0, 0);
+	if (IS_ERR(ctx->hash_tfm))
+		return -EFAULT;
+	spin_lock_init(&ctx->lock);
+	ctx->qat_hash_alg = hash;
+	tfm->crt_aead.reqsize = sizeof(struct aead_request) +
+				sizeof(struct qat_crypto_request);
+	ctx->tfm = tfm;
+	return 0;
+}
+
+static int qat_alg_sha1_init(struct crypto_tfm *tfm)
+{
+	return qat_alg_init(tfm, ICP_QAT_HW_AUTH_ALGO_SHA1, "sha1");
+}
+
+static int qat_alg_sha256_init(struct crypto_tfm *tfm)
+{
+	return qat_alg_init(tfm, ICP_QAT_HW_AUTH_ALGO_SHA256, "sha256");
+}
+
+static int qat_alg_sha512_init(struct crypto_tfm *tfm)
+{
+	return qat_alg_init(tfm, ICP_QAT_HW_AUTH_ALGO_SHA512, "sha512");
+}
+
+static void qat_alg_exit(struct crypto_tfm *tfm)
+{
+	struct qat_alg_session_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qat_crypto_instance *inst = ctx->inst;
+	struct device *dev;
+
+	if (!IS_ERR(ctx->hash_tfm))
+		crypto_free_shash(ctx->hash_tfm);
+
+	if (!inst)
+		return;
+
+	dev = &GET_DEV(inst->accel_dev);
+	if (ctx->enc_cd)
+		dma_free_coherent(dev, sizeof(struct qat_alg_cd),
+				  ctx->enc_cd, ctx->enc_cd_paddr);
+	if (ctx->dec_cd)
+		dma_free_coherent(dev, sizeof(struct qat_alg_cd),
+				  ctx->dec_cd, ctx->dec_cd_paddr);
+	if (ctx->auth_hw_state_enc)
+		dma_free_coherent(dev, sizeof(struct qat_auth_state),
+				  ctx->auth_hw_state_enc,
+				  ctx->auth_state_enc_paddr);
+
+	if (ctx->auth_hw_state_dec)
+		dma_free_coherent(dev, sizeof(struct qat_auth_state),
+				  ctx->auth_hw_state_dec,
+				  ctx->auth_state_dec_paddr);
+
+	qat_crypto_put_instance(inst);
+}
+
+static struct crypto_alg qat_algs[] = { {
+	.cra_name = "authenc(hmac(sha1),cbc(aes))",
+	.cra_driver_name = "qat_aes_cbc_hmac_sha1",
+	.cra_priority = 4001,
+	.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct qat_alg_session_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_aead_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = qat_alg_sha1_init,
+	.cra_exit = qat_alg_exit,
+	.cra_u = {
+		.aead = {
+			.setkey = qat_alg_setkey,
+			.decrypt = qat_alg_dec,
+			.encrypt = qat_alg_enc,
+			.givencrypt = qat_alg_genivenc,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA1_DIGEST_SIZE,
+		},
+	},
+}, {
+	.cra_name = "authenc(hmac(sha256),cbc(aes))",
+	.cra_driver_name = "qat_aes_cbc_hmac_sha256",
+	.cra_priority = 4001,
+	.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct qat_alg_session_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_aead_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = qat_alg_sha256_init,
+	.cra_exit = qat_alg_exit,
+	.cra_u = {
+		.aead = {
+			.setkey = qat_alg_setkey,
+			.decrypt = qat_alg_dec,
+			.encrypt = qat_alg_enc,
+			.givencrypt = qat_alg_genivenc,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA256_DIGEST_SIZE,
+		},
+	},
+}, {
+	.cra_name = "authenc(hmac(sha512),cbc(aes))",
+	.cra_driver_name = "qat_aes_cbc_hmac_sha512",
+	.cra_priority = 4001,
+	.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC,
+	.cra_blocksize = AES_BLOCK_SIZE,
+	.cra_ctxsize = sizeof(struct qat_alg_session_ctx),
+	.cra_alignmask = 0,
+	.cra_type = &crypto_aead_type,
+	.cra_module = THIS_MODULE,
+	.cra_init = qat_alg_sha512_init,
+	.cra_exit = qat_alg_exit,
+	.cra_u = {
+		.aead = {
+			.setkey = qat_alg_setkey,
+			.decrypt = qat_alg_dec,
+			.encrypt = qat_alg_enc,
+			.givencrypt = qat_alg_genivenc,
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = SHA512_DIGEST_SIZE,
+		},
+	},
+} };
+
+int qat_algs_register(void)
+{
+	if (atomic_add_return(1, &active_dev) == 1) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(qat_algs); i++)
+			qat_algs[i].cra_flags =	CRYPTO_ALG_TYPE_AEAD |
+						CRYPTO_ALG_ASYNC;
+		return crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	}
+	return 0;
+}
+
+int qat_algs_unregister(void)
+{
+	if (atomic_sub_return(1, &active_dev) == 0)
+		return crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	return 0;
+}
+
+int qat_algs_init(void)
+{
+	atomic_set(&active_dev, 0);
+	crypto_get_default_rng();
+	return 0;
+}
+
+void qat_algs_exit(void)
+{
+	crypto_put_default_rng();
+}
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.c b/drivers/crypto/qat/qat_common/qat_crypto.c
new file mode 100644
index 00000000000..0d59bcb50de
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/qat_crypto.c
@@ -0,0 +1,284 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+#include "adf_transport.h"
+#include "adf_cfg.h"
+#include "adf_cfg_strings.h"
+#include "qat_crypto.h"
+#include "icp_qat_fw.h"
+
+#define SEC ADF_KERNEL_SEC
+
+static struct service_hndl qat_crypto;
+
+void qat_crypto_put_instance(struct qat_crypto_instance *inst)
+{
+	if (atomic_sub_return(1, &inst->refctr) == 0)
+		adf_dev_put(inst->accel_dev);
+}
+
+static int qat_crypto_free_instances(struct adf_accel_dev *accel_dev)
+{
+	struct qat_crypto_instance *inst;
+	struct list_head *list_ptr, *tmp;
+	int i;
+
+	list_for_each_safe(list_ptr, tmp, &accel_dev->crypto_list) {
+		inst = list_entry(list_ptr, struct qat_crypto_instance, list);
+
+		for (i = 0; i < atomic_read(&inst->refctr); i++)
+			qat_crypto_put_instance(inst);
+
+		if (inst->sym_tx)
+			adf_remove_ring(inst->sym_tx);
+
+		if (inst->sym_rx)
+			adf_remove_ring(inst->sym_rx);
+
+		if (inst->pke_tx)
+			adf_remove_ring(inst->pke_tx);
+
+		if (inst->pke_rx)
+			adf_remove_ring(inst->pke_rx);
+
+		if (inst->rnd_tx)
+			adf_remove_ring(inst->rnd_tx);
+
+		if (inst->rnd_rx)
+			adf_remove_ring(inst->rnd_rx);
+
+		list_del(list_ptr);
+		kfree(inst);
+	}
+	return 0;
+}
+
+struct qat_crypto_instance *qat_crypto_get_instance_node(int node)
+{
+	struct adf_accel_dev *accel_dev = NULL;
+	struct qat_crypto_instance *inst_best = NULL;
+	struct list_head *itr;
+	unsigned long best = ~0;
+
+	list_for_each(itr, adf_devmgr_get_head()) {
+		accel_dev = list_entry(itr, struct adf_accel_dev, list);
+		if (accel_dev->numa_node == node && adf_dev_started(accel_dev))
+			break;
+		accel_dev = NULL;
+	}
+	if (!accel_dev) {
+		pr_err("QAT: Could not find device on give node\n");
+		accel_dev = adf_devmgr_get_first();
+	}
+	if (!accel_dev || !adf_dev_started(accel_dev))
+		return NULL;
+
+	list_for_each(itr, &accel_dev->crypto_list) {
+		struct qat_crypto_instance *inst;
+		unsigned long cur;
+
+		inst = list_entry(itr, struct qat_crypto_instance, list);
+		cur = atomic_read(&inst->refctr);
+		if (best > cur) {
+			inst_best = inst;
+			best = cur;
+		}
+	}
+	if (inst_best) {
+		if (atomic_add_return(1, &inst_best->refctr) == 1) {
+			if (adf_dev_get(accel_dev)) {
+				atomic_dec(&inst_best->refctr);
+				pr_err("QAT: Could increment dev refctr\n");
+				return NULL;
+			}
+		}
+	}
+	return inst_best;
+}
+
+static int qat_crypto_create_instances(struct adf_accel_dev *accel_dev)
+{
+	int i;
+	unsigned long bank;
+	unsigned long num_inst, num_msg_sym, num_msg_asym;
+	int msg_size;
+	struct qat_crypto_instance *inst;
+	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	char val[ADF_CFG_MAX_VAL_LEN_IN_BYTES];
+
+	INIT_LIST_HEAD(&accel_dev->crypto_list);
+	strlcpy(key, ADF_NUM_CY, sizeof(key));
+
+	if (adf_cfg_get_param_value(accel_dev, SEC, key, val))
+		return -EFAULT;
+
+	if (kstrtoul(val, 0, &num_inst))
+		return -EFAULT;
+
+	for (i = 0; i < num_inst; i++) {
+		inst = kzalloc_node(sizeof(*inst), GFP_KERNEL,
+				    accel_dev->numa_node);
+		if (!inst)
+			goto err;
+
+		list_add_tail(&inst->list, &accel_dev->crypto_list);
+		inst->id = i;
+		atomic_set(&inst->refctr, 0);
+		inst->accel_dev = accel_dev;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_BANK_NUM, i);
+		if (adf_cfg_get_param_value(accel_dev, SEC, key, val))
+			goto err;
+
+		if (kstrtoul(val, 10, &bank))
+			goto err;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_SIZE, i);
+		if (adf_cfg_get_param_value(accel_dev, SEC, key, val))
+			goto err;
+
+		if (kstrtoul(val, 10, &num_msg_sym))
+			goto err;
+		num_msg_sym = num_msg_sym >> 1;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_SIZE, i);
+		if (adf_cfg_get_param_value(accel_dev, SEC, key, val))
+			goto err;
+
+		if (kstrtoul(val, 10, &num_msg_asym))
+			goto err;
+		num_msg_asym = num_msg_asym >> 1;
+
+		msg_size = ICP_QAT_FW_REQ_DEFAULT_SZ;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_TX, i);
+		if (adf_create_ring(accel_dev, SEC, bank, num_msg_sym,
+				    msg_size, key, NULL, 0, &inst->sym_tx))
+			goto err;
+
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_RND_TX, i);
+		if (adf_create_ring(accel_dev, SEC, bank, num_msg_asym,
+				    msg_size, key, NULL, 0, &inst->rnd_tx))
+			goto err;
+
+		msg_size = msg_size >> 1;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_TX, i);
+		if (adf_create_ring(accel_dev, SEC, bank, num_msg_asym,
+				    msg_size, key, NULL, 0, &inst->pke_tx))
+			goto err;
+
+		msg_size = ICP_QAT_FW_RESP_DEFAULT_SZ;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_RX, i);
+		if (adf_create_ring(accel_dev, SEC, bank, num_msg_sym,
+				    msg_size, key, qat_alg_callback, 0,
+				    &inst->sym_rx))
+			goto err;
+
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_RND_RX, i);
+		if (adf_create_ring(accel_dev, SEC, bank, num_msg_asym,
+				    msg_size, key, qat_alg_callback, 0,
+				    &inst->rnd_rx))
+			goto err;
+
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, i);
+		if (adf_create_ring(accel_dev, SEC, bank, num_msg_asym,
+				    msg_size, key, qat_alg_callback, 0,
+				    &inst->pke_rx))
+			goto err;
+	}
+	return 0;
+err:
+	qat_crypto_free_instances(accel_dev);
+	return -ENOMEM;
+}
+
+static int qat_crypto_init(struct adf_accel_dev *accel_dev)
+{
+	if (qat_crypto_create_instances(accel_dev))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int qat_crypto_shutdown(struct adf_accel_dev *accel_dev)
+{
+	return qat_crypto_free_instances(accel_dev);
+}
+
+static int qat_crypto_event_handler(struct adf_accel_dev *accel_dev,
+				    enum adf_event event)
+{
+	int ret;
+
+	switch (event) {
+	case ADF_EVENT_INIT:
+		ret = qat_crypto_init(accel_dev);
+		break;
+	case ADF_EVENT_SHUTDOWN:
+		ret = qat_crypto_shutdown(accel_dev);
+		break;
+	case ADF_EVENT_RESTARTING:
+	case ADF_EVENT_RESTARTED:
+	case ADF_EVENT_START:
+	case ADF_EVENT_STOP:
+	default:
+		ret = 0;
+	}
+	return ret;
+}
+
+int qat_crypto_register(void)
+{
+	memset(&qat_crypto, 0, sizeof(qat_crypto));
+	qat_crypto.event_hld = qat_crypto_event_handler;
+	qat_crypto.name = "qat_crypto";
+	return adf_service_register(&qat_crypto);
+}
+
+int qat_crypto_unregister(void)
+{
+	return adf_service_unregister(&qat_crypto);
+}
diff --git a/drivers/crypto/qat/qat_common/qat_crypto.h b/drivers/crypto/qat/qat_common/qat_crypto.h
new file mode 100644
index 00000000000..ab8468d11dd
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/qat_crypto.h
@@ -0,0 +1,83 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef _QAT_CRYPTO_INSTANCE_H_
+#define _QAT_CRYPTO_INSTANCE_H_
+
+#include <linux/list.h>
+#include <linux/slab.h>
+#include "adf_accel_devices.h"
+#include "icp_qat_fw_la.h"
+
+struct qat_crypto_instance {
+	struct adf_etr_ring_data *sym_tx;
+	struct adf_etr_ring_data *sym_rx;
+	struct adf_etr_ring_data *pke_tx;
+	struct adf_etr_ring_data *pke_rx;
+	struct adf_etr_ring_data *rnd_tx;
+	struct adf_etr_ring_data *rnd_rx;
+	struct adf_accel_dev *accel_dev;
+	struct list_head list;
+	unsigned long state;
+	int id;
+	atomic_t refctr;
+};
+
+struct qat_crypto_request_buffs {
+	struct qat_alg_buf_list *bl;
+	dma_addr_t blp;
+	struct qat_alg_buf_list *blout;
+	dma_addr_t bloutp;
+	size_t sz;
+};
+
+struct qat_crypto_request {
+	struct icp_qat_fw_la_bulk_req req;
+	struct qat_alg_session_ctx *ctx;
+	struct aead_request *areq;
+	struct qat_crypto_request_buffs buf;
+};
+#endif
diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c
new file mode 100644
index 00000000000..9b8a31521ff
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/qat_hal.c
@@ -0,0 +1,1393 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/slab.h>
+
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+#include "icp_qat_hal.h"
+#include "icp_qat_uclo.h"
+
+#define BAD_REGADDR               0xffff
+#define MAX_RETRY_TIMES           10000
+#define INIT_CTX_ARB_VALUE        0x0
+#define INIT_CTX_ENABLE_VALUE     0x0
+#define INIT_PC_VALUE             0x0
+#define INIT_WAKEUP_EVENTS_VALUE  0x1
+#define INIT_SIG_EVENTS_VALUE     0x1
+#define INIT_CCENABLE_VALUE       0x2000
+#define RST_CSR_QAT_LSB           20
+#define RST_CSR_AE_LSB		  0
+#define MC_TIMESTAMP_ENABLE       (0x1 << 7)
+
+#define IGNORE_W1C_MASK ((~(1 << CE_BREAKPOINT_BITPOS)) & \
+	(~(1 << CE_CNTL_STORE_PARITY_ERROR_BITPOS)) & \
+	(~(1 << CE_REG_PAR_ERR_BITPOS)))
+#define INSERT_IMMED_GPRA_CONST(inst, const_val) \
+	(inst = ((inst & 0xFFFF00C03FFull) | \
+		((((const_val) << 12) & 0x0FF00000ull) | \
+		(((const_val) << 10) & 0x0003FC00ull))))
+#define INSERT_IMMED_GPRB_CONST(inst, const_val) \
+	(inst = ((inst & 0xFFFF00FFF00ull) | \
+		((((const_val) << 12) & 0x0FF00000ull) | \
+		(((const_val) <<  0) & 0x000000FFull))))
+
+#define AE(handle, ae) handle->hal_handle->aes[ae]
+
+static const uint64_t inst_4b[] = {
+	0x0F0400C0000ull, 0x0F4400C0000ull, 0x0F040000300ull, 0x0F440000300ull,
+	0x0FC066C0000ull, 0x0F0000C0300ull, 0x0F0000C0300ull, 0x0F0000C0300ull,
+	0x0A021000000ull
+};
+
+static const uint64_t inst[] = {
+	0x0F0000C0000ull, 0x0F000000380ull, 0x0D805000011ull, 0x0FC082C0300ull,
+	0x0F0000C0300ull, 0x0F0000C0300ull, 0x0F0000C0300ull, 0x0F0000C0300ull,
+	0x0A0643C0000ull, 0x0BAC0000301ull, 0x0D802000101ull, 0x0F0000C0001ull,
+	0x0FC066C0001ull, 0x0F0000C0300ull, 0x0F0000C0300ull, 0x0F0000C0300ull,
+	0x0F000400300ull, 0x0A0610C0000ull, 0x0BAC0000301ull, 0x0D804400101ull,
+	0x0A0580C0000ull, 0x0A0581C0000ull, 0x0A0582C0000ull, 0x0A0583C0000ull,
+	0x0A0584C0000ull, 0x0A0585C0000ull, 0x0A0586C0000ull, 0x0A0587C0000ull,
+	0x0A0588C0000ull, 0x0A0589C0000ull, 0x0A058AC0000ull, 0x0A058BC0000ull,
+	0x0A058CC0000ull, 0x0A058DC0000ull, 0x0A058EC0000ull, 0x0A058FC0000ull,
+	0x0A05C0C0000ull, 0x0A05C1C0000ull, 0x0A05C2C0000ull, 0x0A05C3C0000ull,
+	0x0A05C4C0000ull, 0x0A05C5C0000ull, 0x0A05C6C0000ull, 0x0A05C7C0000ull,
+	0x0A05C8C0000ull, 0x0A05C9C0000ull, 0x0A05CAC0000ull, 0x0A05CBC0000ull,
+	0x0A05CCC0000ull, 0x0A05CDC0000ull, 0x0A05CEC0000ull, 0x0A05CFC0000ull,
+	0x0A0400C0000ull, 0x0B0400C0000ull, 0x0A0401C0000ull, 0x0B0401C0000ull,
+	0x0A0402C0000ull, 0x0B0402C0000ull, 0x0A0403C0000ull, 0x0B0403C0000ull,
+	0x0A0404C0000ull, 0x0B0404C0000ull, 0x0A0405C0000ull, 0x0B0405C0000ull,
+	0x0A0406C0000ull, 0x0B0406C0000ull, 0x0A0407C0000ull, 0x0B0407C0000ull,
+	0x0A0408C0000ull, 0x0B0408C0000ull, 0x0A0409C0000ull, 0x0B0409C0000ull,
+	0x0A040AC0000ull, 0x0B040AC0000ull, 0x0A040BC0000ull, 0x0B040BC0000ull,
+	0x0A040CC0000ull, 0x0B040CC0000ull, 0x0A040DC0000ull, 0x0B040DC0000ull,
+	0x0A040EC0000ull, 0x0B040EC0000ull, 0x0A040FC0000ull, 0x0B040FC0000ull,
+	0x0D81581C010ull, 0x0E000010000ull, 0x0E000010000ull,
+};
+
+void qat_hal_set_live_ctx(struct icp_qat_fw_loader_handle *handle,
+			  unsigned char ae, unsigned int ctx_mask)
+{
+	AE(handle, ae).live_ctx_mask = ctx_mask;
+}
+
+#define CSR_RETRY_TIMES 500
+static int qat_hal_rd_ae_csr(struct icp_qat_fw_loader_handle *handle,
+			     unsigned char ae, unsigned int csr,
+			     unsigned int *value)
+{
+	unsigned int iterations = CSR_RETRY_TIMES;
+
+	do {
+		*value = GET_AE_CSR(handle, ae, csr);
+		if (!(GET_AE_CSR(handle, ae, LOCAL_CSR_STATUS) & LCS_STATUS))
+			return 0;
+	} while (iterations--);
+
+	pr_err("QAT: Read CSR timeout\n");
+	return -EFAULT;
+}
+
+static int qat_hal_wr_ae_csr(struct icp_qat_fw_loader_handle *handle,
+			     unsigned char ae, unsigned int csr,
+			     unsigned int value)
+{
+	unsigned int iterations = CSR_RETRY_TIMES;
+
+	do {
+		SET_AE_CSR(handle, ae, csr, value);
+		if (!(GET_AE_CSR(handle, ae, LOCAL_CSR_STATUS) & LCS_STATUS))
+			return 0;
+	} while (iterations--);
+
+	pr_err("QAT: Write CSR Timeout\n");
+	return -EFAULT;
+}
+
+static void qat_hal_get_wakeup_event(struct icp_qat_fw_loader_handle *handle,
+				     unsigned char ae, unsigned char ctx,
+				     unsigned int *events)
+{
+	unsigned int cur_ctx;
+
+	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, ctx);
+	qat_hal_rd_ae_csr(handle, ae, CTX_WAKEUP_EVENTS_INDIRECT, events);
+	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, cur_ctx);
+}
+
+static int qat_hal_wait_cycles(struct icp_qat_fw_loader_handle *handle,
+			       unsigned char ae, unsigned int cycles,
+			       int chk_inactive)
+{
+	unsigned int base_cnt = 0, cur_cnt = 0;
+	unsigned int csr = (1 << ACS_ABO_BITPOS);
+	int times = MAX_RETRY_TIMES;
+	int elapsed_cycles = 0;
+
+	qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT, &base_cnt);
+	base_cnt &= 0xffff;
+	while ((int)cycles > elapsed_cycles && times--) {
+		if (chk_inactive)
+			qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &csr);
+
+		qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT, &cur_cnt);
+		cur_cnt &= 0xffff;
+		elapsed_cycles = cur_cnt - base_cnt;
+
+		if (elapsed_cycles < 0)
+			elapsed_cycles += 0x10000;
+
+		/* ensure at least 8 time cycles elapsed in wait_cycles */
+		if (elapsed_cycles >= 8 && !(csr & (1 << ACS_ABO_BITPOS)))
+			return 0;
+	}
+	if (!times) {
+		pr_err("QAT: wait_num_cycles time out\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+#define CLR_BIT(wrd, bit) (wrd & ~(1 << bit))
+#define SET_BIT(wrd, bit) (wrd | 1 << bit)
+
+int qat_hal_set_ae_ctx_mode(struct icp_qat_fw_loader_handle *handle,
+			    unsigned char ae, unsigned char mode)
+{
+	unsigned int csr, new_csr;
+
+	if ((mode != 4) && (mode != 8)) {
+		pr_err("QAT: bad ctx mode=%d\n", mode);
+		return -EINVAL;
+	}
+
+	/* Sets the accelaration engine context mode to either four or eight */
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &csr);
+	csr = IGNORE_W1C_MASK & csr;
+	new_csr = (mode == 4) ?
+		SET_BIT(csr, CE_INUSE_CONTEXTS_BITPOS) :
+		CLR_BIT(csr, CE_INUSE_CONTEXTS_BITPOS);
+	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, new_csr);
+	return 0;
+}
+
+int qat_hal_set_ae_nn_mode(struct icp_qat_fw_loader_handle *handle,
+			   unsigned char ae, unsigned char mode)
+{
+	unsigned int csr, new_csr;
+
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &csr);
+	csr &= IGNORE_W1C_MASK;
+
+	new_csr = (mode) ?
+		SET_BIT(csr, CE_NN_MODE_BITPOS) :
+		CLR_BIT(csr, CE_NN_MODE_BITPOS);
+
+	if (new_csr != csr)
+		qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, new_csr);
+
+	return 0;
+}
+
+int qat_hal_set_ae_lm_mode(struct icp_qat_fw_loader_handle *handle,
+			   unsigned char ae, enum icp_qat_uof_regtype lm_type,
+			   unsigned char mode)
+{
+	unsigned int csr, new_csr;
+
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &csr);
+	csr &= IGNORE_W1C_MASK;
+	switch (lm_type) {
+	case ICP_LMEM0:
+		new_csr = (mode) ?
+			SET_BIT(csr, CE_LMADDR_0_GLOBAL_BITPOS) :
+			CLR_BIT(csr, CE_LMADDR_0_GLOBAL_BITPOS);
+		break;
+	case ICP_LMEM1:
+		new_csr = (mode) ?
+			SET_BIT(csr, CE_LMADDR_1_GLOBAL_BITPOS) :
+			CLR_BIT(csr, CE_LMADDR_1_GLOBAL_BITPOS);
+		break;
+	default:
+		pr_err("QAT: lmType = 0x%x\n", lm_type);
+		return -EINVAL;
+	}
+
+	if (new_csr != csr)
+		qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, new_csr);
+	return 0;
+}
+
+static unsigned short qat_hal_get_reg_addr(unsigned int type,
+					   unsigned short reg_num)
+{
+	unsigned short reg_addr;
+
+	switch (type) {
+	case ICP_GPA_ABS:
+	case ICP_GPB_ABS:
+		reg_addr = 0x80 | (reg_num & 0x7f);
+		break;
+	case ICP_GPA_REL:
+	case ICP_GPB_REL:
+		reg_addr = reg_num & 0x1f;
+		break;
+	case ICP_SR_RD_REL:
+	case ICP_SR_WR_REL:
+	case ICP_SR_REL:
+		reg_addr = 0x180 | (reg_num & 0x1f);
+		break;
+	case ICP_SR_ABS:
+		reg_addr = 0x140 | ((reg_num & 0x3) << 1);
+		break;
+	case ICP_DR_RD_REL:
+	case ICP_DR_WR_REL:
+	case ICP_DR_REL:
+		reg_addr = 0x1c0 | (reg_num & 0x1f);
+		break;
+	case ICP_DR_ABS:
+		reg_addr = 0x100 | ((reg_num & 0x3) << 1);
+		break;
+	case ICP_NEIGH_REL:
+		reg_addr = 0x280 | (reg_num & 0x1f);
+		break;
+	case ICP_LMEM0:
+		reg_addr = 0x200;
+		break;
+	case ICP_LMEM1:
+		reg_addr = 0x220;
+		break;
+	case ICP_NO_DEST:
+		reg_addr = 0x300 | (reg_num & 0xff);
+		break;
+	default:
+		reg_addr = BAD_REGADDR;
+		break;
+	}
+	return reg_addr;
+}
+
+void qat_hal_reset(struct icp_qat_fw_loader_handle *handle)
+{
+	unsigned int ae_reset_csr;
+
+	ae_reset_csr = GET_GLB_CSR(handle, ICP_RESET);
+	ae_reset_csr |= handle->hal_handle->ae_mask << RST_CSR_AE_LSB;
+	ae_reset_csr |= handle->hal_handle->slice_mask << RST_CSR_QAT_LSB;
+	SET_GLB_CSR(handle, ICP_RESET, ae_reset_csr);
+}
+
+static void qat_hal_wr_indr_csr(struct icp_qat_fw_loader_handle *handle,
+				unsigned char ae, unsigned int ctx_mask,
+				unsigned int ae_csr, unsigned int csr_val)
+{
+	unsigned int ctx, cur_ctx;
+
+	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+
+	for (ctx = 0; ctx < ICP_QAT_UCLO_MAX_CTX; ctx++) {
+		if (!(ctx_mask & (1 << ctx)))
+			continue;
+		qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, ctx);
+		qat_hal_wr_ae_csr(handle, ae, ae_csr, csr_val);
+	}
+
+	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, cur_ctx);
+}
+
+static void qat_hal_rd_indr_csr(struct icp_qat_fw_loader_handle *handle,
+				unsigned char ae, unsigned char ctx,
+				unsigned int ae_csr, unsigned int *csr_val)
+{
+	unsigned int cur_ctx;
+
+	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, ctx);
+	qat_hal_rd_ae_csr(handle, ae, ae_csr, csr_val);
+	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, cur_ctx);
+}
+
+static void qat_hal_put_sig_event(struct icp_qat_fw_loader_handle *handle,
+				  unsigned char ae, unsigned int ctx_mask,
+				  unsigned int events)
+{
+	unsigned int ctx, cur_ctx;
+
+	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+	for (ctx = 0; ctx < ICP_QAT_UCLO_MAX_CTX; ctx++) {
+		if (!(ctx_mask & (1 << ctx)))
+			continue;
+		qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, ctx);
+		qat_hal_wr_ae_csr(handle, ae, CTX_SIG_EVENTS_INDIRECT, events);
+	}
+	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, cur_ctx);
+}
+
+static void qat_hal_put_wakeup_event(struct icp_qat_fw_loader_handle *handle,
+				     unsigned char ae, unsigned int ctx_mask,
+				     unsigned int events)
+{
+	unsigned int ctx, cur_ctx;
+
+	qat_hal_rd_ae_csr(handle, ae, CSR_CTX_POINTER, &cur_ctx);
+	for (ctx = 0; ctx < ICP_QAT_UCLO_MAX_CTX; ctx++) {
+		if (!(ctx_mask & (1 << ctx)))
+			continue;
+		qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, ctx);
+		qat_hal_wr_ae_csr(handle, ae, CTX_WAKEUP_EVENTS_INDIRECT,
+				  events);
+	}
+	qat_hal_wr_ae_csr(handle, ae, CSR_CTX_POINTER, cur_ctx);
+}
+
+static int qat_hal_check_ae_alive(struct icp_qat_fw_loader_handle *handle)
+{
+	unsigned int base_cnt, cur_cnt;
+	unsigned char ae;
+	unsigned int times = MAX_RETRY_TIMES;
+
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		if (!(handle->hal_handle->ae_mask & (1 << ae)))
+			continue;
+
+		qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT,
+				  (unsigned int *)&base_cnt);
+		base_cnt &= 0xffff;
+
+		do {
+			qat_hal_rd_ae_csr(handle, ae, PROFILE_COUNT,
+					  (unsigned int *)&cur_cnt);
+			cur_cnt &= 0xffff;
+		} while (times-- && (cur_cnt == base_cnt));
+
+		if (!times) {
+			pr_err("QAT: AE%d is inactive!!\n", ae);
+			return -EFAULT;
+		}
+	}
+
+	return 0;
+}
+
+static void qat_hal_reset_timestamp(struct icp_qat_fw_loader_handle *handle)
+{
+	unsigned int misc_ctl;
+	unsigned char ae;
+
+	/* stop the timestamp timers */
+	misc_ctl = GET_GLB_CSR(handle, MISC_CONTROL);
+	if (misc_ctl & MC_TIMESTAMP_ENABLE)
+		SET_GLB_CSR(handle, MISC_CONTROL, misc_ctl &
+			    (~MC_TIMESTAMP_ENABLE));
+
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		if (!(handle->hal_handle->ae_mask & (1 << ae)))
+			continue;
+		qat_hal_wr_ae_csr(handle, ae, TIMESTAMP_LOW, 0);
+		qat_hal_wr_ae_csr(handle, ae, TIMESTAMP_HIGH, 0);
+	}
+	/* start timestamp timers */
+	SET_GLB_CSR(handle, MISC_CONTROL, misc_ctl | MC_TIMESTAMP_ENABLE);
+}
+
+#define ESRAM_AUTO_TINIT (1<<2)
+#define ESRAM_AUTO_TINIT_DONE (1<<3)
+#define ESRAM_AUTO_INIT_USED_CYCLES (1640)
+#define ESRAM_AUTO_INIT_CSR_OFFSET 0xC1C
+static int qat_hal_init_esram(struct icp_qat_fw_loader_handle *handle)
+{
+	void __iomem *csr_addr = handle->hal_ep_csr_addr_v +
+				 ESRAM_AUTO_INIT_CSR_OFFSET;
+	unsigned int csr_val, times = 30;
+
+	csr_val = ADF_CSR_RD(csr_addr, 0);
+	if ((csr_val & ESRAM_AUTO_TINIT) && (csr_val & ESRAM_AUTO_TINIT_DONE))
+		return 0;
+
+	csr_val = ADF_CSR_RD(csr_addr, 0);
+	csr_val |= ESRAM_AUTO_TINIT;
+	ADF_CSR_WR(csr_addr, 0, csr_val);
+
+	do {
+		qat_hal_wait_cycles(handle, 0, ESRAM_AUTO_INIT_USED_CYCLES, 0);
+		csr_val = ADF_CSR_RD(csr_addr, 0);
+	} while (!(csr_val & ESRAM_AUTO_TINIT_DONE) && times--);
+	if ((!times)) {
+		pr_err("QAT: Fail to init eSram!\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+#define SHRAM_INIT_CYCLES 2060
+int qat_hal_clr_reset(struct icp_qat_fw_loader_handle *handle)
+{
+	unsigned int ae_reset_csr;
+	unsigned char ae;
+	unsigned int clk_csr;
+	unsigned int times = 100;
+	unsigned int csr;
+
+	/* write to the reset csr */
+	ae_reset_csr = GET_GLB_CSR(handle, ICP_RESET);
+	ae_reset_csr &= ~(handle->hal_handle->ae_mask << RST_CSR_AE_LSB);
+	ae_reset_csr &= ~(handle->hal_handle->slice_mask << RST_CSR_QAT_LSB);
+	do {
+		SET_GLB_CSR(handle, ICP_RESET, ae_reset_csr);
+		if (!(times--))
+			goto out_err;
+		csr = GET_GLB_CSR(handle, ICP_RESET);
+	} while ((handle->hal_handle->ae_mask |
+		 (handle->hal_handle->slice_mask << RST_CSR_QAT_LSB)) & csr);
+	/* enable clock */
+	clk_csr = GET_GLB_CSR(handle, ICP_GLOBAL_CLK_ENABLE);
+	clk_csr |= handle->hal_handle->ae_mask << 0;
+	clk_csr |= handle->hal_handle->slice_mask << 20;
+	SET_GLB_CSR(handle, ICP_GLOBAL_CLK_ENABLE, clk_csr);
+	if (qat_hal_check_ae_alive(handle))
+		goto out_err;
+
+	/* Set undefined power-up/reset states to reasonable default values */
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		if (!(handle->hal_handle->ae_mask & (1 << ae)))
+			continue;
+		qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES,
+				  INIT_CTX_ENABLE_VALUE);
+		qat_hal_wr_indr_csr(handle, ae, ICP_QAT_UCLO_AE_ALL_CTX,
+				    CTX_STS_INDIRECT,
+				    handle->hal_handle->upc_mask &
+				    INIT_PC_VALUE);
+		qat_hal_wr_ae_csr(handle, ae, CTX_ARB_CNTL, INIT_CTX_ARB_VALUE);
+		qat_hal_wr_ae_csr(handle, ae, CC_ENABLE, INIT_CCENABLE_VALUE);
+		qat_hal_put_wakeup_event(handle, ae,
+					 ICP_QAT_UCLO_AE_ALL_CTX,
+					 INIT_WAKEUP_EVENTS_VALUE);
+		qat_hal_put_sig_event(handle, ae,
+				      ICP_QAT_UCLO_AE_ALL_CTX,
+				      INIT_SIG_EVENTS_VALUE);
+	}
+	if (qat_hal_init_esram(handle))
+		goto out_err;
+	if (qat_hal_wait_cycles(handle, 0, SHRAM_INIT_CYCLES, 0))
+		goto out_err;
+	qat_hal_reset_timestamp(handle);
+
+	return 0;
+out_err:
+	pr_err("QAT: failed to get device out of reset\n");
+	return -EFAULT;
+}
+
+static void qat_hal_disable_ctx(struct icp_qat_fw_loader_handle *handle,
+				unsigned char ae, unsigned int ctx_mask)
+{
+	unsigned int ctx;
+
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx);
+	ctx &= IGNORE_W1C_MASK &
+		(~((ctx_mask & ICP_QAT_UCLO_AE_ALL_CTX) << CE_ENABLE_BITPOS));
+	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx);
+}
+
+static uint64_t qat_hal_parity_64bit(uint64_t word)
+{
+	word ^= word >> 1;
+	word ^= word >> 2;
+	word ^= word >> 4;
+	word ^= word >> 8;
+	word ^= word >> 16;
+	word ^= word >> 32;
+	return word & 1;
+}
+
+static uint64_t qat_hal_set_uword_ecc(uint64_t uword)
+{
+	uint64_t bit0_mask = 0xff800007fffULL, bit1_mask = 0x1f801ff801fULL,
+		bit2_mask = 0xe387e0781e1ULL, bit3_mask = 0x7cb8e388e22ULL,
+		bit4_mask = 0xaf5b2c93244ULL, bit5_mask = 0xf56d5525488ULL,
+		bit6_mask = 0xdaf69a46910ULL;
+
+	/* clear the ecc bits */
+	uword &= ~(0x7fULL << 0x2C);
+	uword |= qat_hal_parity_64bit(bit0_mask & uword) << 0x2C;
+	uword |= qat_hal_parity_64bit(bit1_mask & uword) << 0x2D;
+	uword |= qat_hal_parity_64bit(bit2_mask & uword) << 0x2E;
+	uword |= qat_hal_parity_64bit(bit3_mask & uword) << 0x2F;
+	uword |= qat_hal_parity_64bit(bit4_mask & uword) << 0x30;
+	uword |= qat_hal_parity_64bit(bit5_mask & uword) << 0x31;
+	uword |= qat_hal_parity_64bit(bit6_mask & uword) << 0x32;
+	return uword;
+}
+
+void qat_hal_wr_uwords(struct icp_qat_fw_loader_handle *handle,
+		       unsigned char ae, unsigned int uaddr,
+		       unsigned int words_num, uint64_t *uword)
+{
+	unsigned int ustore_addr;
+	unsigned int i;
+
+	qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS, &ustore_addr);
+	uaddr |= UA_ECS;
+	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, uaddr);
+	for (i = 0; i < words_num; i++) {
+		unsigned int uwrd_lo, uwrd_hi;
+		uint64_t tmp;
+
+		tmp = qat_hal_set_uword_ecc(uword[i]);
+		uwrd_lo = (unsigned int)(tmp & 0xffffffff);
+		uwrd_hi = (unsigned int)(tmp >> 0x20);
+		qat_hal_wr_ae_csr(handle, ae, USTORE_DATA_LOWER, uwrd_lo);
+		qat_hal_wr_ae_csr(handle, ae, USTORE_DATA_UPPER, uwrd_hi);
+	}
+	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, ustore_addr);
+}
+
+static void qat_hal_enable_ctx(struct icp_qat_fw_loader_handle *handle,
+			       unsigned char ae, unsigned int ctx_mask)
+{
+	unsigned int ctx;
+
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx);
+	ctx &= IGNORE_W1C_MASK;
+	ctx_mask &= (ctx & CE_INUSE_CONTEXTS) ? 0x55 : 0xFF;
+	ctx |= (ctx_mask << CE_ENABLE_BITPOS);
+	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx);
+}
+
+static int qat_hal_clear_gpr(struct icp_qat_fw_loader_handle *handle)
+{
+	unsigned char ae;
+	unsigned int ctx_mask = ICP_QAT_UCLO_AE_ALL_CTX;
+	int times = MAX_RETRY_TIMES;
+	unsigned int csr_val = 0;
+	unsigned short reg;
+	unsigned int savctx = 0;
+	int ret = 0;
+
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		if (!(handle->hal_handle->ae_mask & (1 << ae)))
+			continue;
+		for (reg = 0; reg < ICP_QAT_UCLO_MAX_GPR_REG; reg++) {
+			qat_hal_init_rd_xfer(handle, ae, 0, ICP_SR_RD_ABS,
+					     reg, 0);
+			qat_hal_init_rd_xfer(handle, ae, 0, ICP_DR_RD_ABS,
+					     reg, 0);
+		}
+		qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL, &csr_val);
+		csr_val &= ~(1 << MMC_SHARE_CS_BITPOS);
+		qat_hal_wr_ae_csr(handle, ae, AE_MISC_CONTROL, csr_val);
+		qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &csr_val);
+		csr_val &= IGNORE_W1C_MASK;
+		csr_val |= CE_NN_MODE;
+		qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, csr_val);
+		qat_hal_wr_uwords(handle, ae, 0, ARRAY_SIZE(inst),
+				  (uint64_t *)inst);
+		qat_hal_wr_indr_csr(handle, ae, ctx_mask, CTX_STS_INDIRECT,
+				    handle->hal_handle->upc_mask &
+				    INIT_PC_VALUE);
+		qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &savctx);
+		qat_hal_wr_ae_csr(handle, ae, ACTIVE_CTX_STATUS, 0);
+		qat_hal_put_wakeup_event(handle, ae, ctx_mask, XCWE_VOLUNTARY);
+		qat_hal_wr_indr_csr(handle, ae, ctx_mask,
+				    CTX_SIG_EVENTS_INDIRECT, 0);
+		qat_hal_wr_ae_csr(handle, ae, CTX_SIG_EVENTS_ACTIVE, 0);
+		qat_hal_enable_ctx(handle, ae, ctx_mask);
+	}
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		if (!(handle->hal_handle->ae_mask & (1 << ae)))
+			continue;
+		/* wait for AE to finish */
+		do {
+			ret = qat_hal_wait_cycles(handle, ae, 20, 1);
+		} while (ret && times--);
+
+		if (!times) {
+			pr_err("QAT: clear GPR of AE %d failed", ae);
+			return -EINVAL;
+		}
+		qat_hal_disable_ctx(handle, ae, ctx_mask);
+		qat_hal_wr_ae_csr(handle, ae, ACTIVE_CTX_STATUS,
+				  savctx & ACS_ACNO);
+		qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES,
+				  INIT_CTX_ENABLE_VALUE);
+		qat_hal_wr_indr_csr(handle, ae, ctx_mask, CTX_STS_INDIRECT,
+				    handle->hal_handle->upc_mask &
+				    INIT_PC_VALUE);
+		qat_hal_wr_ae_csr(handle, ae, CTX_ARB_CNTL, INIT_CTX_ARB_VALUE);
+		qat_hal_wr_ae_csr(handle, ae, CC_ENABLE, INIT_CCENABLE_VALUE);
+		qat_hal_put_wakeup_event(handle, ae, ctx_mask,
+					 INIT_WAKEUP_EVENTS_VALUE);
+		qat_hal_put_sig_event(handle, ae, ctx_mask,
+				      INIT_SIG_EVENTS_VALUE);
+	}
+	return 0;
+}
+
+#define ICP_DH895XCC_AE_OFFSET      0x20000
+#define ICP_DH895XCC_CAP_OFFSET     (ICP_DH895XCC_AE_OFFSET + 0x10000)
+#define LOCAL_TO_XFER_REG_OFFSET    0x800
+#define ICP_DH895XCC_EP_OFFSET      0x3a000
+#define ICP_DH895XCC_PMISC_BAR 1
+int qat_hal_init(struct adf_accel_dev *accel_dev)
+{
+	unsigned char ae;
+	unsigned int max_en_ae_id = 0;
+	struct icp_qat_fw_loader_handle *handle;
+	struct adf_accel_pci *pci_info = &accel_dev->accel_pci_dev;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct adf_bar *bar = &pci_info->pci_bars[ADF_DH895XCC_PMISC_BAR];
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	handle->hal_cap_g_ctl_csr_addr_v = bar->virt_addr +
+						ICP_DH895XCC_CAP_OFFSET;
+	handle->hal_cap_ae_xfer_csr_addr_v = bar->virt_addr +
+						ICP_DH895XCC_AE_OFFSET;
+	handle->hal_ep_csr_addr_v = bar->virt_addr + ICP_DH895XCC_EP_OFFSET;
+	handle->hal_cap_ae_local_csr_addr_v =
+		handle->hal_cap_ae_xfer_csr_addr_v + LOCAL_TO_XFER_REG_OFFSET;
+
+	handle->hal_handle = kzalloc(sizeof(*handle->hal_handle), GFP_KERNEL);
+	if (!handle->hal_handle)
+		goto out_hal_handle;
+	handle->hal_handle->revision_id = accel_dev->accel_pci_dev.revid;
+	handle->hal_handle->ae_mask = hw_data->ae_mask;
+	handle->hal_handle->slice_mask = hw_data->accel_mask;
+	/* create AE objects */
+	handle->hal_handle->upc_mask = 0x1ffff;
+	handle->hal_handle->max_ustore = 0x4000;
+	for (ae = 0; ae < ICP_QAT_UCLO_MAX_AE; ae++) {
+		if (!(hw_data->ae_mask & (1 << ae)))
+			continue;
+		handle->hal_handle->aes[ae].free_addr = 0;
+		handle->hal_handle->aes[ae].free_size =
+		    handle->hal_handle->max_ustore;
+		handle->hal_handle->aes[ae].ustore_size =
+		    handle->hal_handle->max_ustore;
+		handle->hal_handle->aes[ae].live_ctx_mask =
+						ICP_QAT_UCLO_AE_ALL_CTX;
+		max_en_ae_id = ae;
+	}
+	handle->hal_handle->ae_max_num = max_en_ae_id + 1;
+	/* take all AEs out of reset */
+	if (qat_hal_clr_reset(handle)) {
+		pr_err("QAT: qat_hal_clr_reset error\n");
+		goto out_err;
+	}
+	if (qat_hal_clear_gpr(handle))
+		goto out_err;
+	/* Set SIGNATURE_ENABLE[0] to 0x1 in order to enable ALU_OUT csr */
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		unsigned int csr_val = 0;
+
+		if (!(hw_data->ae_mask & (1 << ae)))
+			continue;
+		qat_hal_rd_ae_csr(handle, ae, SIGNATURE_ENABLE, &csr_val);
+		csr_val |= 0x1;
+		qat_hal_wr_ae_csr(handle, ae, SIGNATURE_ENABLE, csr_val);
+	}
+	accel_dev->fw_loader->fw_loader = handle;
+	return 0;
+
+out_err:
+	kfree(handle->hal_handle);
+out_hal_handle:
+	kfree(handle);
+	return -EFAULT;
+}
+
+void qat_hal_deinit(struct icp_qat_fw_loader_handle *handle)
+{
+	if (!handle)
+		return;
+	kfree(handle->hal_handle);
+	kfree(handle);
+}
+
+void qat_hal_start(struct icp_qat_fw_loader_handle *handle, unsigned char ae,
+		   unsigned int ctx_mask)
+{
+	qat_hal_put_wakeup_event(handle, ae, (~ctx_mask) &
+				 ICP_QAT_UCLO_AE_ALL_CTX, 0x10000);
+	qat_hal_enable_ctx(handle, ae, ctx_mask);
+}
+
+void qat_hal_stop(struct icp_qat_fw_loader_handle *handle, unsigned char ae,
+		  unsigned int ctx_mask)
+{
+	qat_hal_disable_ctx(handle, ae, ctx_mask);
+}
+
+void qat_hal_set_pc(struct icp_qat_fw_loader_handle *handle,
+		    unsigned char ae, unsigned int ctx_mask, unsigned int upc)
+{
+	qat_hal_wr_indr_csr(handle, ae, ctx_mask, CTX_STS_INDIRECT,
+			    handle->hal_handle->upc_mask & upc);
+}
+
+static void qat_hal_get_uwords(struct icp_qat_fw_loader_handle *handle,
+			       unsigned char ae, unsigned int uaddr,
+			       unsigned int words_num, uint64_t *uword)
+{
+	unsigned int i, uwrd_lo, uwrd_hi;
+	unsigned int ustore_addr, misc_control;
+
+	qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL, &misc_control);
+	qat_hal_wr_ae_csr(handle, ae, AE_MISC_CONTROL,
+			  misc_control & 0xfffffffb);
+	qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS, &ustore_addr);
+	uaddr |= UA_ECS;
+	for (i = 0; i < words_num; i++) {
+		qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, uaddr);
+		uaddr++;
+		qat_hal_rd_ae_csr(handle, ae, USTORE_DATA_LOWER, &uwrd_lo);
+		qat_hal_rd_ae_csr(handle, ae, USTORE_DATA_UPPER, &uwrd_hi);
+		uword[i] = uwrd_hi;
+		uword[i] = (uword[i] << 0x20) | uwrd_lo;
+	}
+	qat_hal_wr_ae_csr(handle, ae, AE_MISC_CONTROL, misc_control);
+	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, ustore_addr);
+}
+
+void qat_hal_wr_umem(struct icp_qat_fw_loader_handle *handle,
+		     unsigned char ae, unsigned int uaddr,
+		     unsigned int words_num, unsigned int *data)
+{
+	unsigned int i, ustore_addr;
+
+	qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS, &ustore_addr);
+	uaddr |= UA_ECS;
+	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, uaddr);
+	for (i = 0; i < words_num; i++) {
+		unsigned int uwrd_lo, uwrd_hi, tmp;
+
+		uwrd_lo = ((data[i] & 0xfff0000) << 4) | (0x3 << 18) |
+			  ((data[i] & 0xff00) << 2) |
+			  (0x3 << 8) | (data[i] & 0xff);
+		uwrd_hi = (0xf << 4) | ((data[i] & 0xf0000000) >> 28);
+		uwrd_hi |= (hweight32(data[i] & 0xffff) & 0x1) << 8;
+		tmp = ((data[i] >> 0x10) & 0xffff);
+		uwrd_hi |= (hweight32(tmp) & 0x1) << 9;
+		qat_hal_wr_ae_csr(handle, ae, USTORE_DATA_LOWER, uwrd_lo);
+		qat_hal_wr_ae_csr(handle, ae, USTORE_DATA_UPPER, uwrd_hi);
+	}
+	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, ustore_addr);
+}
+
+#define MAX_EXEC_INST 100
+static int qat_hal_exec_micro_inst(struct icp_qat_fw_loader_handle *handle,
+				   unsigned char ae, unsigned char ctx,
+				   uint64_t *micro_inst, unsigned int inst_num,
+				   int code_off, unsigned int max_cycle,
+				   unsigned int *endpc)
+{
+	uint64_t savuwords[MAX_EXEC_INST];
+	unsigned int ind_lm_addr0, ind_lm_addr1;
+	unsigned int ind_lm_addr_byte0, ind_lm_addr_byte1;
+	unsigned int ind_cnt_sig;
+	unsigned int ind_sig, act_sig;
+	unsigned int csr_val = 0, newcsr_val;
+	unsigned int savctx;
+	unsigned int savcc, wakeup_events, savpc;
+	unsigned int ctxarb_ctl, ctx_enables;
+
+	if ((inst_num > handle->hal_handle->max_ustore) || !micro_inst) {
+		pr_err("QAT: invalid instruction num %d\n", inst_num);
+		return -EINVAL;
+	}
+	/* save current context */
+	qat_hal_rd_indr_csr(handle, ae, ctx, LM_ADDR_0_INDIRECT, &ind_lm_addr0);
+	qat_hal_rd_indr_csr(handle, ae, ctx, LM_ADDR_1_INDIRECT, &ind_lm_addr1);
+	qat_hal_rd_indr_csr(handle, ae, ctx, INDIRECT_LM_ADDR_0_BYTE_INDEX,
+			    &ind_lm_addr_byte0);
+	qat_hal_rd_indr_csr(handle, ae, ctx, INDIRECT_LM_ADDR_1_BYTE_INDEX,
+			    &ind_lm_addr_byte1);
+	if (inst_num <= MAX_EXEC_INST)
+		qat_hal_get_uwords(handle, ae, 0, inst_num, savuwords);
+	qat_hal_get_wakeup_event(handle, ae, ctx, &wakeup_events);
+	qat_hal_rd_indr_csr(handle, ae, ctx, CTX_STS_INDIRECT, &savpc);
+	savpc = (savpc & handle->hal_handle->upc_mask) >> 0;
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	ctx_enables &= IGNORE_W1C_MASK;
+	qat_hal_rd_ae_csr(handle, ae, CC_ENABLE, &savcc);
+	qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &savctx);
+	qat_hal_rd_ae_csr(handle, ae, CTX_ARB_CNTL, &ctxarb_ctl);
+	qat_hal_rd_indr_csr(handle, ae, ctx, FUTURE_COUNT_SIGNAL_INDIRECT,
+			    &ind_cnt_sig);
+	qat_hal_rd_indr_csr(handle, ae, ctx, CTX_SIG_EVENTS_INDIRECT, &ind_sig);
+	qat_hal_rd_ae_csr(handle, ae, CTX_SIG_EVENTS_ACTIVE, &act_sig);
+	/* execute micro codes */
+	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx_enables);
+	qat_hal_wr_uwords(handle, ae, 0, inst_num, micro_inst);
+	qat_hal_wr_indr_csr(handle, ae, (1 << ctx), CTX_STS_INDIRECT, 0);
+	qat_hal_wr_ae_csr(handle, ae, ACTIVE_CTX_STATUS, ctx & ACS_ACNO);
+	if (code_off)
+		qat_hal_wr_ae_csr(handle, ae, CC_ENABLE, savcc & 0xffffdfff);
+	qat_hal_put_wakeup_event(handle, ae, (1 << ctx), XCWE_VOLUNTARY);
+	qat_hal_wr_indr_csr(handle, ae, (1 << ctx), CTX_SIG_EVENTS_INDIRECT, 0);
+	qat_hal_wr_ae_csr(handle, ae, CTX_SIG_EVENTS_ACTIVE, 0);
+	qat_hal_enable_ctx(handle, ae, (1 << ctx));
+	/* wait for micro codes to finish */
+	if (qat_hal_wait_cycles(handle, ae, max_cycle, 1) != 0)
+		return -EFAULT;
+	if (endpc) {
+		unsigned int ctx_status;
+
+		qat_hal_rd_indr_csr(handle, ae, ctx, CTX_STS_INDIRECT,
+				    &ctx_status);
+		*endpc = ctx_status & handle->hal_handle->upc_mask;
+	}
+	/* retore to saved context */
+	qat_hal_disable_ctx(handle, ae, (1 << ctx));
+	if (inst_num <= MAX_EXEC_INST)
+		qat_hal_wr_uwords(handle, ae, 0, inst_num, savuwords);
+	qat_hal_put_wakeup_event(handle, ae, (1 << ctx), wakeup_events);
+	qat_hal_wr_indr_csr(handle, ae, (1 << ctx), CTX_STS_INDIRECT,
+			    handle->hal_handle->upc_mask & savpc);
+	qat_hal_rd_ae_csr(handle, ae, AE_MISC_CONTROL, &csr_val);
+	newcsr_val = CLR_BIT(csr_val, MMC_SHARE_CS_BITPOS);
+	qat_hal_wr_ae_csr(handle, ae, AE_MISC_CONTROL, newcsr_val);
+	qat_hal_wr_ae_csr(handle, ae, CC_ENABLE, savcc);
+	qat_hal_wr_ae_csr(handle, ae, ACTIVE_CTX_STATUS, savctx & ACS_ACNO);
+	qat_hal_wr_ae_csr(handle, ae, CTX_ARB_CNTL, ctxarb_ctl);
+	qat_hal_wr_indr_csr(handle, ae, (1 << ctx),
+			    LM_ADDR_0_INDIRECT, ind_lm_addr0);
+	qat_hal_wr_indr_csr(handle, ae, (1 << ctx),
+			    LM_ADDR_1_INDIRECT, ind_lm_addr1);
+	qat_hal_wr_indr_csr(handle, ae, (1 << ctx),
+			    INDIRECT_LM_ADDR_0_BYTE_INDEX, ind_lm_addr_byte0);
+	qat_hal_wr_indr_csr(handle, ae, (1 << ctx),
+			    INDIRECT_LM_ADDR_1_BYTE_INDEX, ind_lm_addr_byte1);
+	qat_hal_wr_indr_csr(handle, ae, (1 << ctx),
+			    FUTURE_COUNT_SIGNAL_INDIRECT, ind_cnt_sig);
+	qat_hal_wr_indr_csr(handle, ae, (1 << ctx),
+			    CTX_SIG_EVENTS_INDIRECT, ind_sig);
+	qat_hal_wr_ae_csr(handle, ae, CTX_SIG_EVENTS_ACTIVE, act_sig);
+	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx_enables);
+
+	return 0;
+}
+
+static int qat_hal_rd_rel_reg(struct icp_qat_fw_loader_handle *handle,
+			      unsigned char ae, unsigned char ctx,
+			      enum icp_qat_uof_regtype reg_type,
+			      unsigned short reg_num, unsigned int *data)
+{
+	unsigned int savctx, uaddr, uwrd_lo, uwrd_hi;
+	unsigned int ctxarb_cntl, ustore_addr, ctx_enables;
+	unsigned short reg_addr;
+	int status = 0;
+	uint64_t insts, savuword;
+
+	reg_addr = qat_hal_get_reg_addr(reg_type, reg_num);
+	if (reg_addr == BAD_REGADDR) {
+		pr_err("QAT: bad regaddr=0x%x\n", reg_addr);
+		return -EINVAL;
+	}
+	switch (reg_type) {
+	case ICP_GPA_REL:
+		insts = 0xA070000000ull | (reg_addr & 0x3ff);
+		break;
+	default:
+		insts = (uint64_t)0xA030000000ull | ((reg_addr & 0x3ff) << 10);
+		break;
+	}
+	qat_hal_rd_ae_csr(handle, ae, ACTIVE_CTX_STATUS, &savctx);
+	qat_hal_rd_ae_csr(handle, ae, CTX_ARB_CNTL, &ctxarb_cntl);
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	ctx_enables &= IGNORE_W1C_MASK;
+	if (ctx != (savctx & ACS_ACNO))
+		qat_hal_wr_ae_csr(handle, ae, ACTIVE_CTX_STATUS,
+				  ctx & ACS_ACNO);
+	qat_hal_get_uwords(handle, ae, 0, 1, &savuword);
+	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx_enables);
+	qat_hal_rd_ae_csr(handle, ae, USTORE_ADDRESS, &ustore_addr);
+	uaddr = UA_ECS;
+	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, uaddr);
+	insts = qat_hal_set_uword_ecc(insts);
+	uwrd_lo = (unsigned int)(insts & 0xffffffff);
+	uwrd_hi = (unsigned int)(insts >> 0x20);
+	qat_hal_wr_ae_csr(handle, ae, USTORE_DATA_LOWER, uwrd_lo);
+	qat_hal_wr_ae_csr(handle, ae, USTORE_DATA_UPPER, uwrd_hi);
+	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, uaddr);
+	/* delay for at least 8 cycles */
+	qat_hal_wait_cycles(handle, ae, 0x8, 0);
+	/*
+	 * read ALU output
+	 * the instruction should have been executed
+	 * prior to clearing the ECS in putUwords
+	 */
+	qat_hal_rd_ae_csr(handle, ae, ALU_OUT, data);
+	qat_hal_wr_ae_csr(handle, ae, USTORE_ADDRESS, ustore_addr);
+	qat_hal_wr_uwords(handle, ae, 0, 1, &savuword);
+	if (ctx != (savctx & ACS_ACNO))
+		qat_hal_wr_ae_csr(handle, ae, ACTIVE_CTX_STATUS,
+				  savctx & ACS_ACNO);
+	qat_hal_wr_ae_csr(handle, ae, CTX_ARB_CNTL, ctxarb_cntl);
+	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx_enables);
+
+	return status;
+}
+
+static int qat_hal_wr_rel_reg(struct icp_qat_fw_loader_handle *handle,
+			      unsigned char ae, unsigned char ctx,
+			      enum icp_qat_uof_regtype reg_type,
+			      unsigned short reg_num, unsigned int data)
+{
+	unsigned short src_hiaddr, src_lowaddr, dest_addr, data16hi, data16lo;
+	uint64_t insts[] = {
+		0x0F440000000ull,
+		0x0F040000000ull,
+		0x0F0000C0300ull,
+		0x0E000010000ull
+	};
+	const int num_inst = ARRAY_SIZE(insts), code_off = 1;
+	const int imm_w1 = 0, imm_w0 = 1;
+
+	dest_addr = qat_hal_get_reg_addr(reg_type, reg_num);
+	if (dest_addr == BAD_REGADDR) {
+		pr_err("QAT: bad destAddr=0x%x\n", dest_addr);
+		return -EINVAL;
+	}
+
+	data16lo = 0xffff & data;
+	data16hi = 0xffff & (data >> 0x10);
+	src_hiaddr = qat_hal_get_reg_addr(ICP_NO_DEST, (unsigned short)
+					  (0xff & data16hi));
+	src_lowaddr = qat_hal_get_reg_addr(ICP_NO_DEST, (unsigned short)
+					   (0xff & data16lo));
+	switch (reg_type) {
+	case ICP_GPA_REL:
+		insts[imm_w1] = insts[imm_w1] | ((data16hi >> 8) << 20) |
+		    ((src_hiaddr & 0x3ff) << 10) | (dest_addr & 0x3ff);
+		insts[imm_w0] = insts[imm_w0] | ((data16lo >> 8) << 20) |
+		    ((src_lowaddr & 0x3ff) << 10) | (dest_addr & 0x3ff);
+		break;
+	default:
+		insts[imm_w1] = insts[imm_w1] | ((data16hi >> 8) << 20) |
+		    ((dest_addr & 0x3ff) << 10) | (src_hiaddr & 0x3ff);
+
+		insts[imm_w0] = insts[imm_w0] | ((data16lo >> 8) << 20) |
+		    ((dest_addr & 0x3ff) << 10) | (src_lowaddr & 0x3ff);
+		break;
+	}
+
+	return qat_hal_exec_micro_inst(handle, ae, ctx, insts, num_inst,
+				       code_off, num_inst * 0x5, NULL);
+}
+
+int qat_hal_get_ins_num(void)
+{
+	return ARRAY_SIZE(inst_4b);
+}
+
+static int qat_hal_concat_micro_code(uint64_t *micro_inst,
+				     unsigned int inst_num, unsigned int size,
+				     unsigned int addr, unsigned int *value)
+{
+	int i, val_indx;
+	unsigned int cur_value;
+	const uint64_t *inst_arr;
+	int fixup_offset;
+	int usize = 0;
+	int orig_num;
+
+	orig_num = inst_num;
+	val_indx = 0;
+	cur_value = value[val_indx++];
+	inst_arr = inst_4b;
+	usize = ARRAY_SIZE(inst_4b);
+	fixup_offset = inst_num;
+	for (i = 0; i < usize; i++)
+		micro_inst[inst_num++] = inst_arr[i];
+	INSERT_IMMED_GPRA_CONST(micro_inst[fixup_offset], (addr));
+	fixup_offset++;
+	INSERT_IMMED_GPRA_CONST(micro_inst[fixup_offset], 0);
+	fixup_offset++;
+	INSERT_IMMED_GPRB_CONST(micro_inst[fixup_offset], (cur_value >> 0));
+	fixup_offset++;
+	INSERT_IMMED_GPRB_CONST(micro_inst[fixup_offset], (cur_value >> 0x10));
+
+	return inst_num - orig_num;
+}
+
+static int qat_hal_exec_micro_init_lm(struct icp_qat_fw_loader_handle *handle,
+				      unsigned char ae, unsigned char ctx,
+				      int *pfirst_exec, uint64_t *micro_inst,
+				      unsigned int inst_num)
+{
+	int stat = 0;
+	unsigned int gpra0 = 0, gpra1 = 0, gpra2 = 0;
+	unsigned int gprb0 = 0, gprb1 = 0;
+
+	if (*pfirst_exec) {
+		qat_hal_rd_rel_reg(handle, ae, ctx, ICP_GPA_REL, 0, &gpra0);
+		qat_hal_rd_rel_reg(handle, ae, ctx, ICP_GPA_REL, 0x1, &gpra1);
+		qat_hal_rd_rel_reg(handle, ae, ctx, ICP_GPA_REL, 0x2, &gpra2);
+		qat_hal_rd_rel_reg(handle, ae, ctx, ICP_GPB_REL, 0, &gprb0);
+		qat_hal_rd_rel_reg(handle, ae, ctx, ICP_GPB_REL, 0x1, &gprb1);
+		*pfirst_exec = 0;
+	}
+	stat = qat_hal_exec_micro_inst(handle, ae, ctx, micro_inst, inst_num, 1,
+				       inst_num * 0x5, NULL);
+	if (stat != 0)
+		return -EFAULT;
+	qat_hal_wr_rel_reg(handle, ae, ctx, ICP_GPA_REL, 0, gpra0);
+	qat_hal_wr_rel_reg(handle, ae, ctx, ICP_GPA_REL, 0x1, gpra1);
+	qat_hal_wr_rel_reg(handle, ae, ctx, ICP_GPA_REL, 0x2, gpra2);
+	qat_hal_wr_rel_reg(handle, ae, ctx, ICP_GPB_REL, 0, gprb0);
+	qat_hal_wr_rel_reg(handle, ae, ctx, ICP_GPB_REL, 0x1, gprb1);
+
+	return 0;
+}
+
+int qat_hal_batch_wr_lm(struct icp_qat_fw_loader_handle *handle,
+			unsigned char ae,
+			struct icp_qat_uof_batch_init *lm_init_header)
+{
+	struct icp_qat_uof_batch_init *plm_init;
+	uint64_t *micro_inst_arry;
+	int micro_inst_num;
+	int alloc_inst_size;
+	int first_exec = 1;
+	int stat = 0;
+
+	plm_init = lm_init_header->next;
+	alloc_inst_size = lm_init_header->size;
+	if ((unsigned int)alloc_inst_size > handle->hal_handle->max_ustore)
+		alloc_inst_size = handle->hal_handle->max_ustore;
+	micro_inst_arry = kmalloc_array(alloc_inst_size, sizeof(uint64_t),
+					GFP_KERNEL);
+	if (!micro_inst_arry)
+		return -ENOMEM;
+	micro_inst_num = 0;
+	while (plm_init) {
+		unsigned int addr, *value, size;
+
+		ae = plm_init->ae;
+		addr = plm_init->addr;
+		value = plm_init->value;
+		size = plm_init->size;
+		micro_inst_num += qat_hal_concat_micro_code(micro_inst_arry,
+							    micro_inst_num,
+							    size, addr, value);
+		plm_init = plm_init->next;
+	}
+	/* exec micro codes */
+	if (micro_inst_arry && (micro_inst_num > 0)) {
+		micro_inst_arry[micro_inst_num++] = 0x0E000010000ull;
+		stat = qat_hal_exec_micro_init_lm(handle, ae, 0, &first_exec,
+						  micro_inst_arry,
+						  micro_inst_num);
+	}
+	kfree(micro_inst_arry);
+	return stat;
+}
+
+static int qat_hal_put_rel_rd_xfer(struct icp_qat_fw_loader_handle *handle,
+				   unsigned char ae, unsigned char ctx,
+				   enum icp_qat_uof_regtype reg_type,
+				   unsigned short reg_num, unsigned int val)
+{
+	int status = 0;
+	unsigned int reg_addr;
+	unsigned int ctx_enables;
+	unsigned short mask;
+	unsigned short dr_offset = 0x10;
+
+	status = qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	if (CE_INUSE_CONTEXTS & ctx_enables) {
+		if (ctx & 0x1) {
+			pr_err("QAT: bad 4-ctx mode,ctx=0x%x\n", ctx);
+			return -EINVAL;
+		}
+		mask = 0x1f;
+		dr_offset = 0x20;
+	} else {
+		mask = 0x0f;
+	}
+	if (reg_num & ~mask)
+		return -EINVAL;
+	reg_addr = reg_num + (ctx << 0x5);
+	switch (reg_type) {
+	case ICP_SR_RD_REL:
+	case ICP_SR_REL:
+		SET_AE_XFER(handle, ae, reg_addr, val);
+		break;
+	case ICP_DR_RD_REL:
+	case ICP_DR_REL:
+		SET_AE_XFER(handle, ae, (reg_addr + dr_offset), val);
+		break;
+	default:
+		status = -EINVAL;
+		break;
+	}
+	return status;
+}
+
+static int qat_hal_put_rel_wr_xfer(struct icp_qat_fw_loader_handle *handle,
+				   unsigned char ae, unsigned char ctx,
+				   enum icp_qat_uof_regtype reg_type,
+				   unsigned short reg_num, unsigned int data)
+{
+	unsigned int gprval, ctx_enables;
+	unsigned short src_hiaddr, src_lowaddr, gpr_addr, xfr_addr, data16hi,
+	    data16low;
+	unsigned short reg_mask;
+	int status = 0;
+	uint64_t micro_inst[] = {
+		0x0F440000000ull,
+		0x0F040000000ull,
+		0x0A000000000ull,
+		0x0F0000C0300ull,
+		0x0E000010000ull
+	};
+	const int num_inst = ARRAY_SIZE(micro_inst), code_off = 1;
+	const unsigned short gprnum = 0, dly = num_inst * 0x5;
+
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	if (CE_INUSE_CONTEXTS & ctx_enables) {
+		if (ctx & 0x1) {
+			pr_err("QAT: 4-ctx mode,ctx=0x%x\n", ctx);
+			return -EINVAL;
+		}
+		reg_mask = (unsigned short)~0x1f;
+	} else {
+		reg_mask = (unsigned short)~0xf;
+	}
+	if (reg_num & reg_mask)
+		return -EINVAL;
+	xfr_addr = qat_hal_get_reg_addr(reg_type, reg_num);
+	if (xfr_addr == BAD_REGADDR) {
+		pr_err("QAT: bad xfrAddr=0x%x\n", xfr_addr);
+		return -EINVAL;
+	}
+	qat_hal_rd_rel_reg(handle, ae, ctx, ICP_GPB_REL, gprnum, &gprval);
+	gpr_addr = qat_hal_get_reg_addr(ICP_GPB_REL, gprnum);
+	data16low = 0xffff & data;
+	data16hi = 0xffff & (data >> 0x10);
+	src_hiaddr = qat_hal_get_reg_addr(ICP_NO_DEST,
+					  (unsigned short)(0xff & data16hi));
+	src_lowaddr = qat_hal_get_reg_addr(ICP_NO_DEST,
+					   (unsigned short)(0xff & data16low));
+	micro_inst[0] = micro_inst[0x0] | ((data16hi >> 8) << 20) |
+	    ((gpr_addr & 0x3ff) << 10) | (src_hiaddr & 0x3ff);
+	micro_inst[1] = micro_inst[0x1] | ((data16low >> 8) << 20) |
+	    ((gpr_addr & 0x3ff) << 10) | (src_lowaddr & 0x3ff);
+	micro_inst[0x2] = micro_inst[0x2] |
+	    ((xfr_addr & 0x3ff) << 20) | ((gpr_addr & 0x3ff) << 10);
+	status = qat_hal_exec_micro_inst(handle, ae, ctx, micro_inst, num_inst,
+					 code_off, dly, NULL);
+	qat_hal_wr_rel_reg(handle, ae, ctx, ICP_GPB_REL, gprnum, gprval);
+	return status;
+}
+
+static int qat_hal_put_rel_nn(struct icp_qat_fw_loader_handle *handle,
+			      unsigned char ae, unsigned char ctx,
+			      unsigned short nn, unsigned int val)
+{
+	unsigned int ctx_enables;
+	int stat = 0;
+
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	ctx_enables &= IGNORE_W1C_MASK;
+	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx_enables | CE_NN_MODE);
+
+	stat = qat_hal_put_rel_wr_xfer(handle, ae, ctx, ICP_NEIGH_REL, nn, val);
+	qat_hal_wr_ae_csr(handle, ae, CTX_ENABLES, ctx_enables);
+	return stat;
+}
+
+static int qat_hal_convert_abs_to_rel(struct icp_qat_fw_loader_handle
+				      *handle, unsigned char ae,
+				      unsigned short absreg_num,
+				      unsigned short *relreg,
+				      unsigned char *ctx)
+{
+	unsigned int ctx_enables;
+
+	qat_hal_rd_ae_csr(handle, ae, CTX_ENABLES, &ctx_enables);
+	if (ctx_enables & CE_INUSE_CONTEXTS) {
+		/* 4-ctx mode */
+		*relreg = absreg_num & 0x1F;
+		*ctx = (absreg_num >> 0x4) & 0x6;
+	} else {
+		/* 8-ctx mode */
+		*relreg = absreg_num & 0x0F;
+		*ctx = (absreg_num >> 0x4) & 0x7;
+	}
+	return 0;
+}
+
+int qat_hal_init_gpr(struct icp_qat_fw_loader_handle *handle,
+		     unsigned char ae, unsigned char ctx_mask,
+		     enum icp_qat_uof_regtype reg_type,
+		     unsigned short reg_num, unsigned int regdata)
+{
+	int stat = 0;
+	unsigned short reg;
+	unsigned char ctx = 0;
+	enum icp_qat_uof_regtype type;
+
+	if (reg_num >= ICP_QAT_UCLO_MAX_GPR_REG)
+		return -EINVAL;
+
+	do {
+		if (ctx_mask == 0) {
+			qat_hal_convert_abs_to_rel(handle, ae, reg_num, &reg,
+						   &ctx);
+			type = reg_type - 1;
+		} else {
+			reg = reg_num;
+			type = reg_type;
+			if (!test_bit(ctx, (unsigned long *)&ctx_mask))
+				continue;
+		}
+		stat = qat_hal_wr_rel_reg(handle, ae, ctx, type, reg, regdata);
+		if (stat) {
+			pr_err("QAT: write gpr fail\n");
+			return -EINVAL;
+		}
+	} while (ctx_mask && (ctx++ < ICP_QAT_UCLO_MAX_CTX));
+
+	return 0;
+}
+
+int qat_hal_init_wr_xfer(struct icp_qat_fw_loader_handle *handle,
+			 unsigned char ae, unsigned char ctx_mask,
+			 enum icp_qat_uof_regtype reg_type,
+			 unsigned short reg_num, unsigned int regdata)
+{
+	int stat = 0;
+	unsigned short reg;
+	unsigned char ctx = 0;
+	enum icp_qat_uof_regtype type;
+
+	if (reg_num >= ICP_QAT_UCLO_MAX_XFER_REG)
+		return -EINVAL;
+
+	do {
+		if (ctx_mask == 0) {
+			qat_hal_convert_abs_to_rel(handle, ae, reg_num, &reg,
+						   &ctx);
+			type = reg_type - 3;
+		} else {
+			reg = reg_num;
+			type = reg_type;
+			if (!test_bit(ctx, (unsigned long *)&ctx_mask))
+				continue;
+		}
+		stat = qat_hal_put_rel_wr_xfer(handle, ae, ctx, type, reg,
+					       regdata);
+		if (stat) {
+			pr_err("QAT: write wr xfer fail\n");
+			return -EINVAL;
+		}
+	} while (ctx_mask && (ctx++ < ICP_QAT_UCLO_MAX_CTX));
+
+	return 0;
+}
+
+int qat_hal_init_rd_xfer(struct icp_qat_fw_loader_handle *handle,
+			 unsigned char ae, unsigned char ctx_mask,
+			 enum icp_qat_uof_regtype reg_type,
+			 unsigned short reg_num, unsigned int regdata)
+{
+	int stat = 0;
+	unsigned short reg;
+	unsigned char ctx = 0;
+	enum icp_qat_uof_regtype type;
+
+	if (reg_num >= ICP_QAT_UCLO_MAX_XFER_REG)
+		return -EINVAL;
+
+	do {
+		if (ctx_mask == 0) {
+			qat_hal_convert_abs_to_rel(handle, ae, reg_num, &reg,
+						   &ctx);
+			type = reg_type - 3;
+		} else {
+			reg = reg_num;
+			type = reg_type;
+			if (!test_bit(ctx, (unsigned long *)&ctx_mask))
+				continue;
+		}
+		stat = qat_hal_put_rel_rd_xfer(handle, ae, ctx, type, reg,
+					       regdata);
+		if (stat) {
+			pr_err("QAT: write rd xfer fail\n");
+			return -EINVAL;
+		}
+	} while (ctx_mask && (ctx++ < ICP_QAT_UCLO_MAX_CTX));
+
+	return 0;
+}
+
+int qat_hal_init_nn(struct icp_qat_fw_loader_handle *handle,
+		    unsigned char ae, unsigned char ctx_mask,
+		    unsigned short reg_num, unsigned int regdata)
+{
+	int stat = 0;
+	unsigned char ctx;
+
+	if (ctx_mask == 0)
+		return -EINVAL;
+
+	for (ctx = 0; ctx < ICP_QAT_UCLO_MAX_CTX; ctx++) {
+		if (!test_bit(ctx, (unsigned long *)&ctx_mask))
+			continue;
+		stat = qat_hal_put_rel_nn(handle, ae, ctx, reg_num, regdata);
+		if (stat) {
+			pr_err("QAT: write neigh error\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/crypto/qat/qat_common/qat_uclo.c b/drivers/crypto/qat/qat_common/qat_uclo.c
new file mode 100644
index 00000000000..1e27f9f7fdd
--- /dev/null
+++ b/drivers/crypto/qat/qat_common/qat_uclo.c
@@ -0,0 +1,1181 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/slab.h>
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+
+#include "adf_accel_devices.h"
+#include "adf_common_drv.h"
+#include "icp_qat_uclo.h"
+#include "icp_qat_hal.h"
+#include "icp_qat_fw_loader_handle.h"
+
+#define UWORD_CPYBUF_SIZE 1024
+#define INVLD_UWORD 0xffffffffffull
+#define PID_MINOR_REV 0xf
+#define PID_MAJOR_REV (0xf << 4)
+
+static int qat_uclo_init_ae_data(struct icp_qat_uclo_objhandle *obj_handle,
+				 unsigned int ae, unsigned int image_num)
+{
+	struct icp_qat_uclo_aedata *ae_data;
+	struct icp_qat_uclo_encapme *encap_image;
+	struct icp_qat_uclo_page *page = NULL;
+	struct icp_qat_uclo_aeslice *ae_slice = NULL;
+
+	ae_data = &obj_handle->ae_data[ae];
+	encap_image = &obj_handle->ae_uimage[image_num];
+	ae_slice = &ae_data->ae_slices[ae_data->slice_num];
+	ae_slice->encap_image = encap_image;
+
+	if (encap_image->img_ptr) {
+		ae_slice->ctx_mask_assigned =
+					encap_image->img_ptr->ctx_assigned;
+		ae_data->eff_ustore_size = obj_handle->ustore_phy_size;
+	} else {
+		ae_slice->ctx_mask_assigned = 0;
+	}
+	ae_slice->region = kzalloc(sizeof(*ae_slice->region), GFP_KERNEL);
+	if (!ae_slice->region)
+		return -ENOMEM;
+	ae_slice->page = kzalloc(sizeof(*ae_slice->page), GFP_KERNEL);
+	if (!ae_slice->page)
+		goto out_err;
+	page = ae_slice->page;
+	page->encap_page = encap_image->page;
+	ae_slice->page->region = ae_slice->region;
+	ae_data->slice_num++;
+	return 0;
+out_err:
+	kfree(ae_slice->region);
+	ae_slice->region = NULL;
+	return -ENOMEM;
+}
+
+static int qat_uclo_free_ae_data(struct icp_qat_uclo_aedata *ae_data)
+{
+	unsigned int i;
+
+	if (!ae_data) {
+		pr_err("QAT: bad argument, ae_data is NULL\n ");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ae_data->slice_num; i++) {
+		kfree(ae_data->ae_slices[i].region);
+		ae_data->ae_slices[i].region = NULL;
+		kfree(ae_data->ae_slices[i].page);
+		ae_data->ae_slices[i].page = NULL;
+	}
+	return 0;
+}
+
+static char *qat_uclo_get_string(struct icp_qat_uof_strtable *str_table,
+				 unsigned int str_offset)
+{
+	if ((!str_table->table_len) || (str_offset > str_table->table_len))
+		return NULL;
+	return (char *)(((unsigned long)(str_table->strings)) + str_offset);
+}
+
+static int qat_uclo_check_format(struct icp_qat_uof_filehdr *hdr)
+{
+	int maj = hdr->maj_ver & 0xff;
+	int min = hdr->min_ver & 0xff;
+
+	if (hdr->file_id != ICP_QAT_UOF_FID) {
+		pr_err("QAT: Invalid header 0x%x\n", hdr->file_id);
+		return -EINVAL;
+	}
+	if (min != ICP_QAT_UOF_MINVER || maj != ICP_QAT_UOF_MAJVER) {
+		pr_err("QAT: bad UOF version, major 0x%x, minor 0x%x\n",
+		       maj, min);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void qat_uclo_wr_sram_by_words(struct icp_qat_fw_loader_handle *handle,
+				      unsigned int addr, unsigned int *val,
+				      unsigned int num_in_bytes)
+{
+	unsigned int outval;
+	unsigned char *ptr = (unsigned char *)val;
+
+	while (num_in_bytes) {
+		memcpy(&outval, ptr, 4);
+		SRAM_WRITE(handle, addr, outval);
+		num_in_bytes -= 4;
+		ptr += 4;
+		addr += 4;
+	}
+}
+
+static void qat_uclo_wr_umem_by_words(struct icp_qat_fw_loader_handle *handle,
+				      unsigned char ae, unsigned int addr,
+				      unsigned int *val,
+				      unsigned int num_in_bytes)
+{
+	unsigned int outval;
+	unsigned char *ptr = (unsigned char *)val;
+
+	addr >>= 0x2; /* convert to uword address */
+
+	while (num_in_bytes) {
+		memcpy(&outval, ptr, 4);
+		qat_hal_wr_umem(handle, ae, addr++, 1, &outval);
+		num_in_bytes -= 4;
+		ptr += 4;
+	}
+}
+
+static void qat_uclo_batch_wr_umem(struct icp_qat_fw_loader_handle *handle,
+				   unsigned char ae,
+				   struct icp_qat_uof_batch_init
+				   *umem_init_header)
+{
+	struct icp_qat_uof_batch_init *umem_init;
+
+	if (!umem_init_header)
+		return;
+	umem_init = umem_init_header->next;
+	while (umem_init) {
+		unsigned int addr, *value, size;
+
+		ae = umem_init->ae;
+		addr = umem_init->addr;
+		value = umem_init->value;
+		size = umem_init->size;
+		qat_uclo_wr_umem_by_words(handle, ae, addr, value, size);
+		umem_init = umem_init->next;
+	}
+}
+
+static void
+qat_uclo_cleanup_batch_init_list(struct icp_qat_fw_loader_handle *handle,
+				 struct icp_qat_uof_batch_init **base)
+{
+	struct icp_qat_uof_batch_init *umem_init;
+
+	umem_init = *base;
+	while (umem_init) {
+		struct icp_qat_uof_batch_init *pre;
+
+		pre = umem_init;
+		umem_init = umem_init->next;
+		kfree(pre);
+	}
+	*base = NULL;
+}
+
+static int qat_uclo_parse_num(char *str, unsigned int *num)
+{
+	char buf[16] = {0};
+	unsigned long ae = 0;
+	int i;
+
+	strncpy(buf, str, 15);
+	for (i = 0; i < 16; i++) {
+		if (!isdigit(buf[i])) {
+			buf[i] = '\0';
+			break;
+		}
+	}
+	if ((kstrtoul(buf, 10, &ae)))
+		return -EFAULT;
+
+	*num = (unsigned int)ae;
+	return 0;
+}
+
+static int qat_uclo_fetch_initmem_ae(struct icp_qat_fw_loader_handle *handle,
+				     struct icp_qat_uof_initmem *init_mem,
+				     unsigned int size_range, unsigned int *ae)
+{
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	char *str;
+
+	if ((init_mem->addr + init_mem->num_in_bytes) > (size_range << 0x2)) {
+		pr_err("QAT: initmem is out of range");
+		return -EINVAL;
+	}
+	if (init_mem->scope != ICP_QAT_UOF_LOCAL_SCOPE) {
+		pr_err("QAT: Memory scope for init_mem error\n");
+		return -EINVAL;
+	}
+	str = qat_uclo_get_string(&obj_handle->str_table, init_mem->sym_name);
+	if (!str) {
+		pr_err("QAT: AE name assigned in UOF init table is NULL\n");
+		return -EINVAL;
+	}
+	if (qat_uclo_parse_num(str, ae)) {
+		pr_err("QAT: Parse num for AE number failed\n");
+		return -EINVAL;
+	}
+	if (*ae >= ICP_QAT_UCLO_MAX_AE) {
+		pr_err("QAT: ae %d out of range\n", *ae);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int qat_uclo_create_batch_init_list(struct icp_qat_fw_loader_handle
+					   *handle, struct icp_qat_uof_initmem
+					   *init_mem, unsigned int ae,
+					   struct icp_qat_uof_batch_init
+					   **init_tab_base)
+{
+	struct icp_qat_uof_batch_init *init_header, *tail;
+	struct icp_qat_uof_batch_init *mem_init, *tail_old;
+	struct icp_qat_uof_memvar_attr *mem_val_attr;
+	unsigned int i, flag = 0;
+
+	mem_val_attr =
+		(struct icp_qat_uof_memvar_attr *)((unsigned long)init_mem +
+		sizeof(struct icp_qat_uof_initmem));
+
+	init_header = *init_tab_base;
+	if (!init_header) {
+		init_header = kzalloc(sizeof(*init_header), GFP_KERNEL);
+		if (!init_header)
+			return -ENOMEM;
+		init_header->size = 1;
+		*init_tab_base = init_header;
+		flag = 1;
+	}
+	tail_old = init_header;
+	while (tail_old->next)
+		tail_old = tail_old->next;
+	tail = tail_old;
+	for (i = 0; i < init_mem->val_attr_num; i++) {
+		mem_init = kzalloc(sizeof(*mem_init), GFP_KERNEL);
+		if (!mem_init)
+			goto out_err;
+		mem_init->ae = ae;
+		mem_init->addr = init_mem->addr + mem_val_attr->offset_in_byte;
+		mem_init->value = &mem_val_attr->value;
+		mem_init->size = 4;
+		mem_init->next = NULL;
+		tail->next = mem_init;
+		tail = mem_init;
+		init_header->size += qat_hal_get_ins_num();
+		mem_val_attr++;
+	}
+	return 0;
+out_err:
+	while (tail_old) {
+		mem_init = tail_old->next;
+		kfree(tail_old);
+		tail_old = mem_init;
+	}
+	if (flag)
+		kfree(*init_tab_base);
+	return -ENOMEM;
+}
+
+static int qat_uclo_init_lmem_seg(struct icp_qat_fw_loader_handle *handle,
+				  struct icp_qat_uof_initmem *init_mem)
+{
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	unsigned int ae;
+
+	if (qat_uclo_fetch_initmem_ae(handle, init_mem,
+				      ICP_QAT_UCLO_MAX_LMEM_REG, &ae))
+		return -EINVAL;
+	if (qat_uclo_create_batch_init_list(handle, init_mem, ae,
+					    &obj_handle->lm_init_tab[ae]))
+		return -EINVAL;
+	return 0;
+}
+
+static int qat_uclo_init_umem_seg(struct icp_qat_fw_loader_handle *handle,
+				  struct icp_qat_uof_initmem *init_mem)
+{
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	unsigned int ae, ustore_size, uaddr, i;
+
+	ustore_size = obj_handle->ustore_phy_size;
+	if (qat_uclo_fetch_initmem_ae(handle, init_mem, ustore_size, &ae))
+		return -EINVAL;
+	if (qat_uclo_create_batch_init_list(handle, init_mem, ae,
+					    &obj_handle->umem_init_tab[ae]))
+		return -EINVAL;
+	/* set the highest ustore address referenced */
+	uaddr = (init_mem->addr + init_mem->num_in_bytes) >> 0x2;
+	for (i = 0; i < obj_handle->ae_data[ae].slice_num; i++) {
+		if (obj_handle->ae_data[ae].ae_slices[i].
+		    encap_image->uwords_num < uaddr)
+			obj_handle->ae_data[ae].ae_slices[i].
+			encap_image->uwords_num = uaddr;
+	}
+	return 0;
+}
+
+#define ICP_DH895XCC_PESRAM_BAR_SIZE 0x80000
+static int qat_uclo_init_ae_memory(struct icp_qat_fw_loader_handle *handle,
+				   struct icp_qat_uof_initmem *init_mem)
+{
+	unsigned int i;
+	struct icp_qat_uof_memvar_attr *mem_val_attr;
+
+	mem_val_attr =
+		(struct icp_qat_uof_memvar_attr *)((unsigned long)init_mem +
+		sizeof(struct icp_qat_uof_initmem));
+
+	switch (init_mem->region) {
+	case ICP_QAT_UOF_SRAM_REGION:
+		if ((init_mem->addr + init_mem->num_in_bytes) >
+		    ICP_DH895XCC_PESRAM_BAR_SIZE) {
+			pr_err("QAT: initmem on SRAM is out of range");
+			return -EINVAL;
+		}
+		for (i = 0; i < init_mem->val_attr_num; i++) {
+			qat_uclo_wr_sram_by_words(handle,
+						  init_mem->addr +
+						  mem_val_attr->offset_in_byte,
+						  &mem_val_attr->value, 4);
+			mem_val_attr++;
+		}
+		break;
+	case ICP_QAT_UOF_LMEM_REGION:
+		if (qat_uclo_init_lmem_seg(handle, init_mem))
+			return -EINVAL;
+		break;
+	case ICP_QAT_UOF_UMEM_REGION:
+		if (qat_uclo_init_umem_seg(handle, init_mem))
+			return -EINVAL;
+		break;
+	default:
+		pr_err("QAT: initmem region error. region type=0x%x\n",
+		       init_mem->region);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int qat_uclo_init_ustore(struct icp_qat_fw_loader_handle *handle,
+				struct icp_qat_uclo_encapme *image)
+{
+	unsigned int i;
+	struct icp_qat_uclo_encap_page *page;
+	struct icp_qat_uof_image *uof_image;
+	unsigned char ae;
+	unsigned int ustore_size;
+	unsigned int patt_pos;
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	uint64_t *fill_data;
+
+	uof_image = image->img_ptr;
+	fill_data = kcalloc(ICP_QAT_UCLO_MAX_USTORE, sizeof(uint64_t),
+			    GFP_KERNEL);
+	if (!fill_data)
+		return -ENOMEM;
+	for (i = 0; i < ICP_QAT_UCLO_MAX_USTORE; i++)
+		memcpy(&fill_data[i], &uof_image->fill_pattern,
+		       sizeof(uint64_t));
+	page = image->page;
+
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		if (!test_bit(ae, (unsigned long *)&uof_image->ae_assigned))
+			continue;
+		ustore_size = obj_handle->ae_data[ae].eff_ustore_size;
+		patt_pos = page->beg_addr_p + page->micro_words_num;
+
+		qat_hal_wr_uwords(handle, (unsigned char)ae, 0,
+				  page->beg_addr_p, &fill_data[0]);
+		qat_hal_wr_uwords(handle, (unsigned char)ae, patt_pos,
+				  ustore_size - patt_pos + 1,
+				  &fill_data[page->beg_addr_p]);
+	}
+	kfree(fill_data);
+	return 0;
+}
+
+static int qat_uclo_init_memory(struct icp_qat_fw_loader_handle *handle)
+{
+	int i, ae;
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	struct icp_qat_uof_initmem *initmem = obj_handle->init_mem_tab.init_mem;
+
+	for (i = 0; i < obj_handle->init_mem_tab.entry_num; i++) {
+		if (initmem->num_in_bytes) {
+			if (qat_uclo_init_ae_memory(handle, initmem))
+				return -EINVAL;
+		}
+		initmem = (struct icp_qat_uof_initmem *)((unsigned long)(
+			(unsigned long)initmem +
+			sizeof(struct icp_qat_uof_initmem)) +
+			(sizeof(struct icp_qat_uof_memvar_attr) *
+			initmem->val_attr_num));
+	}
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		if (qat_hal_batch_wr_lm(handle, ae,
+					obj_handle->lm_init_tab[ae])) {
+			pr_err("QAT: fail to batch init lmem for AE %d\n", ae);
+			return -EINVAL;
+		}
+		qat_uclo_cleanup_batch_init_list(handle,
+						 &obj_handle->lm_init_tab[ae]);
+		qat_uclo_batch_wr_umem(handle, ae,
+				       obj_handle->umem_init_tab[ae]);
+		qat_uclo_cleanup_batch_init_list(handle,
+						 &obj_handle->
+						 umem_init_tab[ae]);
+	}
+	return 0;
+}
+
+static void *qat_uclo_find_chunk(struct icp_qat_uof_objhdr *obj_hdr,
+				 char *chunk_id, void *cur)
+{
+	int i;
+	struct icp_qat_uof_chunkhdr *chunk_hdr =
+	    (struct icp_qat_uof_chunkhdr *)
+	    ((unsigned long)obj_hdr + sizeof(struct icp_qat_uof_objhdr));
+
+	for (i = 0; i < obj_hdr->num_chunks; i++) {
+		if ((cur < (void *)&chunk_hdr[i]) &&
+		    !strncmp(chunk_hdr[i].chunk_id, chunk_id,
+			     ICP_QAT_UOF_OBJID_LEN)) {
+			return &chunk_hdr[i];
+		}
+	}
+	return NULL;
+}
+
+static unsigned int qat_uclo_calc_checksum(unsigned int reg, int ch)
+{
+	int i;
+	unsigned int topbit = 1 << 0xF;
+	unsigned int inbyte = (unsigned int)((reg >> 0x18) ^ ch);
+
+	reg ^= inbyte << 0x8;
+	for (i = 0; i < 0x8; i++) {
+		if (reg & topbit)
+			reg = (reg << 1) ^ 0x1021;
+		else
+			reg <<= 1;
+	}
+	return reg & 0xFFFF;
+}
+
+static unsigned int qat_uclo_calc_str_checksum(char *ptr, int num)
+{
+	unsigned int chksum = 0;
+
+	if (ptr)
+		while (num--)
+			chksum = qat_uclo_calc_checksum(chksum, *ptr++);
+	return chksum;
+}
+
+static struct icp_qat_uclo_objhdr *
+qat_uclo_map_chunk(char *buf, struct icp_qat_uof_filehdr *file_hdr,
+		   char *chunk_id)
+{
+	struct icp_qat_uof_filechunkhdr *file_chunk;
+	struct icp_qat_uclo_objhdr *obj_hdr;
+	char *chunk;
+	int i;
+
+	file_chunk = (struct icp_qat_uof_filechunkhdr *)
+		(buf + sizeof(struct icp_qat_uof_filehdr));
+	for (i = 0; i < file_hdr->num_chunks; i++) {
+		if (!strncmp(file_chunk->chunk_id, chunk_id,
+			     ICP_QAT_UOF_OBJID_LEN)) {
+			chunk = buf + file_chunk->offset;
+			if (file_chunk->checksum != qat_uclo_calc_str_checksum(
+				chunk, file_chunk->size))
+				break;
+			obj_hdr = kzalloc(sizeof(*obj_hdr), GFP_KERNEL);
+			if (!obj_hdr)
+				break;
+			obj_hdr->file_buff = chunk;
+			obj_hdr->checksum = file_chunk->checksum;
+			obj_hdr->size = file_chunk->size;
+			return obj_hdr;
+		}
+		file_chunk++;
+	}
+	return NULL;
+}
+
+static unsigned int
+qat_uclo_check_image_compat(struct icp_qat_uof_encap_obj *encap_uof_obj,
+			    struct icp_qat_uof_image *image)
+{
+	struct icp_qat_uof_objtable *uc_var_tab, *imp_var_tab, *imp_expr_tab;
+	struct icp_qat_uof_objtable *neigh_reg_tab;
+	struct icp_qat_uof_code_page *code_page;
+
+	code_page = (struct icp_qat_uof_code_page *)
+			((char *)image + sizeof(struct icp_qat_uof_image));
+	uc_var_tab = (struct icp_qat_uof_objtable *)(encap_uof_obj->beg_uof +
+		     code_page->uc_var_tab_offset);
+	imp_var_tab = (struct icp_qat_uof_objtable *)(encap_uof_obj->beg_uof +
+		      code_page->imp_var_tab_offset);
+	imp_expr_tab = (struct icp_qat_uof_objtable *)
+		       (encap_uof_obj->beg_uof +
+		       code_page->imp_expr_tab_offset);
+	if (uc_var_tab->entry_num || imp_var_tab->entry_num ||
+	    imp_expr_tab->entry_num) {
+		pr_err("QAT: UOF can't contain imported variable to be parsed");
+		return -EINVAL;
+	}
+	neigh_reg_tab = (struct icp_qat_uof_objtable *)
+			(encap_uof_obj->beg_uof +
+			code_page->neigh_reg_tab_offset);
+	if (neigh_reg_tab->entry_num) {
+		pr_err("QAT: UOF can't contain shared control store feature");
+		return -EINVAL;
+	}
+	if (image->numpages > 1) {
+		pr_err("QAT: UOF can't contain multiple pages");
+		return -EINVAL;
+	}
+	if (ICP_QAT_SHARED_USTORE_MODE(image->ae_mode)) {
+		pr_err("QAT: UOF can't use shared control store feature");
+		return -EFAULT;
+	}
+	if (RELOADABLE_CTX_SHARED_MODE(image->ae_mode)) {
+		pr_err("QAT: UOF can't use reloadable feature");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void qat_uclo_map_image_page(struct icp_qat_uof_encap_obj
+				     *encap_uof_obj,
+				     struct icp_qat_uof_image *img,
+				     struct icp_qat_uclo_encap_page *page)
+{
+	struct icp_qat_uof_code_page *code_page;
+	struct icp_qat_uof_code_area *code_area;
+	struct icp_qat_uof_objtable *uword_block_tab;
+	struct icp_qat_uof_uword_block *uwblock;
+	int i;
+
+	code_page = (struct icp_qat_uof_code_page *)
+			((char *)img + sizeof(struct icp_qat_uof_image));
+	page->def_page = code_page->def_page;
+	page->page_region = code_page->page_region;
+	page->beg_addr_v = code_page->beg_addr_v;
+	page->beg_addr_p = code_page->beg_addr_p;
+	code_area = (struct icp_qat_uof_code_area *)(encap_uof_obj->beg_uof +
+						code_page->code_area_offset);
+	page->micro_words_num = code_area->micro_words_num;
+	uword_block_tab = (struct icp_qat_uof_objtable *)
+			  (encap_uof_obj->beg_uof +
+			  code_area->uword_block_tab);
+	page->uwblock_num = uword_block_tab->entry_num;
+	uwblock = (struct icp_qat_uof_uword_block *)((char *)uword_block_tab +
+			sizeof(struct icp_qat_uof_objtable));
+	page->uwblock = (struct icp_qat_uclo_encap_uwblock *)uwblock;
+	for (i = 0; i < uword_block_tab->entry_num; i++)
+		page->uwblock[i].micro_words =
+		(unsigned long)encap_uof_obj->beg_uof + uwblock[i].uword_offset;
+}
+
+static int qat_uclo_map_uimage(struct icp_qat_uclo_objhandle *obj_handle,
+			       struct icp_qat_uclo_encapme *ae_uimage,
+			       int max_image)
+{
+	int i, j;
+	struct icp_qat_uof_chunkhdr *chunk_hdr = NULL;
+	struct icp_qat_uof_image *image;
+	struct icp_qat_uof_objtable *ae_regtab;
+	struct icp_qat_uof_objtable *init_reg_sym_tab;
+	struct icp_qat_uof_objtable *sbreak_tab;
+	struct icp_qat_uof_encap_obj *encap_uof_obj =
+					&obj_handle->encap_uof_obj;
+
+	for (j = 0; j < max_image; j++) {
+		chunk_hdr = qat_uclo_find_chunk(encap_uof_obj->obj_hdr,
+						ICP_QAT_UOF_IMAG, chunk_hdr);
+		if (!chunk_hdr)
+			break;
+		image = (struct icp_qat_uof_image *)(encap_uof_obj->beg_uof +
+						     chunk_hdr->offset);
+		ae_regtab = (struct icp_qat_uof_objtable *)
+			   (image->reg_tab_offset +
+			   obj_handle->obj_hdr->file_buff);
+		ae_uimage[j].ae_reg_num = ae_regtab->entry_num;
+		ae_uimage[j].ae_reg = (struct icp_qat_uof_ae_reg *)
+			(((char *)ae_regtab) +
+			sizeof(struct icp_qat_uof_objtable));
+		init_reg_sym_tab = (struct icp_qat_uof_objtable *)
+				   (image->init_reg_sym_tab +
+				   obj_handle->obj_hdr->file_buff);
+		ae_uimage[j].init_regsym_num = init_reg_sym_tab->entry_num;
+		ae_uimage[j].init_regsym = (struct icp_qat_uof_init_regsym *)
+			(((char *)init_reg_sym_tab) +
+			sizeof(struct icp_qat_uof_objtable));
+		sbreak_tab = (struct icp_qat_uof_objtable *)
+			(image->sbreak_tab + obj_handle->obj_hdr->file_buff);
+		ae_uimage[j].sbreak_num = sbreak_tab->entry_num;
+		ae_uimage[j].sbreak = (struct icp_qat_uof_sbreak *)
+				      (((char *)sbreak_tab) +
+				      sizeof(struct icp_qat_uof_objtable));
+		ae_uimage[j].img_ptr = image;
+		if (qat_uclo_check_image_compat(encap_uof_obj, image))
+			goto out_err;
+		ae_uimage[j].page =
+			kzalloc(sizeof(struct icp_qat_uclo_encap_page),
+				GFP_KERNEL);
+		if (!ae_uimage[j].page)
+			goto out_err;
+		qat_uclo_map_image_page(encap_uof_obj, image,
+					ae_uimage[j].page);
+	}
+	return j;
+out_err:
+	for (i = 0; i < j; i++)
+		kfree(ae_uimage[i].page);
+	return 0;
+}
+
+static int qat_uclo_map_ae(struct icp_qat_fw_loader_handle *handle, int max_ae)
+{
+	int i, ae;
+	int mflag = 0;
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+
+	for (ae = 0; ae <= max_ae; ae++) {
+		if (!test_bit(ae,
+			      (unsigned long *)&handle->hal_handle->ae_mask))
+			continue;
+		for (i = 0; i < obj_handle->uimage_num; i++) {
+			if (!test_bit(ae, (unsigned long *)
+			&obj_handle->ae_uimage[i].img_ptr->ae_assigned))
+				continue;
+			mflag = 1;
+			if (qat_uclo_init_ae_data(obj_handle, ae, i))
+				return -EINVAL;
+		}
+	}
+	if (!mflag) {
+		pr_err("QAT: uimage uses AE not set");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct icp_qat_uof_strtable *
+qat_uclo_map_str_table(struct icp_qat_uclo_objhdr *obj_hdr,
+		       char *tab_name, struct icp_qat_uof_strtable *str_table)
+{
+	struct icp_qat_uof_chunkhdr *chunk_hdr;
+
+	chunk_hdr = qat_uclo_find_chunk((struct icp_qat_uof_objhdr *)
+					obj_hdr->file_buff, tab_name, NULL);
+	if (chunk_hdr) {
+		int hdr_size;
+
+		memcpy(&str_table->table_len, obj_hdr->file_buff +
+		       chunk_hdr->offset, sizeof(str_table->table_len));
+		hdr_size = (char *)&str_table->strings - (char *)str_table;
+		str_table->strings = (unsigned long)obj_hdr->file_buff +
+					chunk_hdr->offset + hdr_size;
+		return str_table;
+	}
+	return NULL;
+}
+
+static void
+qat_uclo_map_initmem_table(struct icp_qat_uof_encap_obj *encap_uof_obj,
+			   struct icp_qat_uclo_init_mem_table *init_mem_tab)
+{
+	struct icp_qat_uof_chunkhdr *chunk_hdr;
+
+	chunk_hdr = qat_uclo_find_chunk(encap_uof_obj->obj_hdr,
+					ICP_QAT_UOF_IMEM, NULL);
+	if (chunk_hdr) {
+		memmove(&init_mem_tab->entry_num, encap_uof_obj->beg_uof +
+			chunk_hdr->offset, sizeof(unsigned int));
+		init_mem_tab->init_mem = (struct icp_qat_uof_initmem *)
+		(encap_uof_obj->beg_uof + chunk_hdr->offset +
+		sizeof(unsigned int));
+	}
+}
+
+static int qat_uclo_check_uof_compat(struct icp_qat_uclo_objhandle *obj_handle)
+{
+	unsigned int maj_ver, prod_type = obj_handle->prod_type;
+
+	if (!(prod_type & obj_handle->encap_uof_obj.obj_hdr->cpu_type)) {
+		pr_err("QAT: UOF type 0x%x not match with cur platform 0x%x\n",
+		       obj_handle->encap_uof_obj.obj_hdr->cpu_type, prod_type);
+		return -EINVAL;
+	}
+	maj_ver = obj_handle->prod_rev & 0xff;
+	if ((obj_handle->encap_uof_obj.obj_hdr->max_cpu_ver < maj_ver) ||
+	    (obj_handle->encap_uof_obj.obj_hdr->min_cpu_ver > maj_ver)) {
+		pr_err("QAT: UOF majVer 0x%x out of range\n", maj_ver);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int qat_uclo_init_reg(struct icp_qat_fw_loader_handle *handle,
+			     unsigned char ae, unsigned char ctx_mask,
+			     enum icp_qat_uof_regtype reg_type,
+			     unsigned short reg_addr, unsigned int value)
+{
+	switch (reg_type) {
+	case ICP_GPA_ABS:
+	case ICP_GPB_ABS:
+		ctx_mask = 0;
+	case ICP_GPA_REL:
+	case ICP_GPB_REL:
+		return qat_hal_init_gpr(handle, ae, ctx_mask, reg_type,
+					reg_addr, value);
+	case ICP_SR_ABS:
+	case ICP_DR_ABS:
+	case ICP_SR_RD_ABS:
+	case ICP_DR_RD_ABS:
+		ctx_mask = 0;
+	case ICP_SR_REL:
+	case ICP_DR_REL:
+	case ICP_SR_RD_REL:
+	case ICP_DR_RD_REL:
+		return qat_hal_init_rd_xfer(handle, ae, ctx_mask, reg_type,
+					    reg_addr, value);
+	case ICP_SR_WR_ABS:
+	case ICP_DR_WR_ABS:
+		ctx_mask = 0;
+	case ICP_SR_WR_REL:
+	case ICP_DR_WR_REL:
+		return qat_hal_init_wr_xfer(handle, ae, ctx_mask, reg_type,
+					    reg_addr, value);
+	case ICP_NEIGH_REL:
+		return qat_hal_init_nn(handle, ae, ctx_mask, reg_addr, value);
+	default:
+		pr_err("QAT: UOF uses not supported reg type 0x%x\n", reg_type);
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static int qat_uclo_init_reg_sym(struct icp_qat_fw_loader_handle *handle,
+				 unsigned int ae,
+				 struct icp_qat_uclo_encapme *encap_ae)
+{
+	unsigned int i;
+	unsigned char ctx_mask;
+	struct icp_qat_uof_init_regsym *init_regsym;
+
+	if (ICP_QAT_CTX_MODE(encap_ae->img_ptr->ae_mode) ==
+	    ICP_QAT_UCLO_MAX_CTX)
+		ctx_mask = 0xff;
+	else
+		ctx_mask = 0x55;
+
+	for (i = 0; i < encap_ae->init_regsym_num; i++) {
+		unsigned int exp_res;
+
+		init_regsym = &encap_ae->init_regsym[i];
+		exp_res = init_regsym->value;
+		switch (init_regsym->init_type) {
+		case ICP_QAT_UOF_INIT_REG:
+			qat_uclo_init_reg(handle, ae, ctx_mask,
+					  (enum icp_qat_uof_regtype)
+					  init_regsym->reg_type,
+					  (unsigned short)init_regsym->reg_addr,
+					  exp_res);
+			break;
+		case ICP_QAT_UOF_INIT_REG_CTX:
+			/* check if ctx is appropriate for the ctxMode */
+			if (!((1 << init_regsym->ctx) & ctx_mask)) {
+				pr_err("QAT: invalid ctx num = 0x%x\n",
+				       init_regsym->ctx);
+				return -EINVAL;
+			}
+			qat_uclo_init_reg(handle, ae,
+					  (unsigned char)
+					  (1 << init_regsym->ctx),
+					  (enum icp_qat_uof_regtype)
+					  init_regsym->reg_type,
+					  (unsigned short)init_regsym->reg_addr,
+					  exp_res);
+			break;
+		case ICP_QAT_UOF_INIT_EXPR:
+			pr_err("QAT: INIT_EXPR feature not supported\n");
+			return -EINVAL;
+		case ICP_QAT_UOF_INIT_EXPR_ENDIAN_SWAP:
+			pr_err("QAT: INIT_EXPR_ENDIAN_SWAP feature not supported\n");
+			return -EINVAL;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+static int qat_uclo_init_globals(struct icp_qat_fw_loader_handle *handle)
+{
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	unsigned int s, ae;
+
+	if (obj_handle->global_inited)
+		return 0;
+	if (obj_handle->init_mem_tab.entry_num) {
+		if (qat_uclo_init_memory(handle)) {
+			pr_err("QAT: initialize memory failed\n");
+			return -EINVAL;
+		}
+	}
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		for (s = 0; s < obj_handle->ae_data[ae].slice_num; s++) {
+			if (!obj_handle->ae_data[ae].ae_slices[s].encap_image)
+				continue;
+			if (qat_uclo_init_reg_sym(handle, ae,
+						  obj_handle->ae_data[ae].
+						  ae_slices[s].encap_image))
+				return -EINVAL;
+		}
+	}
+	obj_handle->global_inited = 1;
+	return 0;
+}
+
+static int qat_uclo_set_ae_mode(struct icp_qat_fw_loader_handle *handle)
+{
+	unsigned char ae, nn_mode, s;
+	struct icp_qat_uof_image *uof_image;
+	struct icp_qat_uclo_aedata *ae_data;
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		if (!test_bit(ae,
+			      (unsigned long *)&handle->hal_handle->ae_mask))
+			continue;
+		ae_data = &obj_handle->ae_data[ae];
+		for (s = 0; s < min_t(unsigned int, ae_data->slice_num,
+				      ICP_QAT_UCLO_MAX_CTX); s++) {
+			if (!obj_handle->ae_data[ae].ae_slices[s].encap_image)
+				continue;
+			uof_image = ae_data->ae_slices[s].encap_image->img_ptr;
+			if (qat_hal_set_ae_ctx_mode(handle, ae,
+						    (char)ICP_QAT_CTX_MODE
+						    (uof_image->ae_mode))) {
+				pr_err("QAT: qat_hal_set_ae_ctx_mode error\n");
+				return -EFAULT;
+			}
+			nn_mode = ICP_QAT_NN_MODE(uof_image->ae_mode);
+			if (qat_hal_set_ae_nn_mode(handle, ae, nn_mode)) {
+				pr_err("QAT: qat_hal_set_ae_nn_mode error\n");
+				return -EFAULT;
+			}
+			if (qat_hal_set_ae_lm_mode(handle, ae, ICP_LMEM0,
+						   (char)ICP_QAT_LOC_MEM0_MODE
+						   (uof_image->ae_mode))) {
+				pr_err("QAT: qat_hal_set_ae_lm_mode LMEM0 error\n");
+				return -EFAULT;
+			}
+			if (qat_hal_set_ae_lm_mode(handle, ae, ICP_LMEM1,
+						   (char)ICP_QAT_LOC_MEM1_MODE
+						   (uof_image->ae_mode))) {
+				pr_err("QAT: qat_hal_set_ae_lm_mode LMEM1 error\n");
+				return -EFAULT;
+			}
+		}
+	}
+	return 0;
+}
+
+static void qat_uclo_init_uword_num(struct icp_qat_fw_loader_handle *handle)
+{
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	struct icp_qat_uclo_encapme *image;
+	int a;
+
+	for (a = 0; a < obj_handle->uimage_num; a++) {
+		image = &obj_handle->ae_uimage[a];
+		image->uwords_num = image->page->beg_addr_p +
+					image->page->micro_words_num;
+	}
+}
+
+static int qat_uclo_parse_uof_obj(struct icp_qat_fw_loader_handle *handle)
+{
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	unsigned int ae;
+
+	obj_handle->uword_buf = kcalloc(UWORD_CPYBUF_SIZE, sizeof(uint64_t),
+					GFP_KERNEL);
+	if (!obj_handle->uword_buf)
+		return -ENOMEM;
+	obj_handle->encap_uof_obj.beg_uof = obj_handle->obj_hdr->file_buff;
+	obj_handle->encap_uof_obj.obj_hdr = (struct icp_qat_uof_objhdr *)
+					     obj_handle->obj_hdr->file_buff;
+	obj_handle->uword_in_bytes = 6;
+	obj_handle->prod_type = ICP_QAT_AC_C_CPU_TYPE;
+	obj_handle->prod_rev = PID_MAJOR_REV |
+			(PID_MINOR_REV & handle->hal_handle->revision_id);
+	if (qat_uclo_check_uof_compat(obj_handle)) {
+		pr_err("QAT: UOF incompatible\n");
+		return -EINVAL;
+	}
+	obj_handle->ustore_phy_size = ICP_QAT_UCLO_MAX_USTORE;
+	if (!obj_handle->obj_hdr->file_buff ||
+	    !qat_uclo_map_str_table(obj_handle->obj_hdr, ICP_QAT_UOF_STRT,
+				    &obj_handle->str_table)) {
+		pr_err("QAT: UOF doesn't have effective images\n");
+		goto out_err;
+	}
+	obj_handle->uimage_num =
+		qat_uclo_map_uimage(obj_handle, obj_handle->ae_uimage,
+				    ICP_QAT_UCLO_MAX_AE * ICP_QAT_UCLO_MAX_CTX);
+	if (!obj_handle->uimage_num)
+		goto out_err;
+	if (qat_uclo_map_ae(handle, handle->hal_handle->ae_max_num)) {
+		pr_err("QAT: Bad object\n");
+		goto out_check_uof_aemask_err;
+	}
+	qat_uclo_init_uword_num(handle);
+	qat_uclo_map_initmem_table(&obj_handle->encap_uof_obj,
+				   &obj_handle->init_mem_tab);
+	if (qat_uclo_set_ae_mode(handle))
+		goto out_check_uof_aemask_err;
+	return 0;
+out_check_uof_aemask_err:
+	for (ae = 0; ae < obj_handle->uimage_num; ae++)
+		kfree(obj_handle->ae_uimage[ae].page);
+out_err:
+	kfree(obj_handle->uword_buf);
+	return -EFAULT;
+}
+
+int qat_uclo_map_uof_obj(struct icp_qat_fw_loader_handle *handle,
+			 void *addr_ptr, int mem_size)
+{
+	struct icp_qat_uof_filehdr *filehdr;
+	struct icp_qat_uclo_objhandle *objhdl;
+
+	BUILD_BUG_ON(ICP_QAT_UCLO_MAX_AE >=
+		     (sizeof(handle->hal_handle->ae_mask) * 8));
+
+	if (!handle || !addr_ptr || mem_size < 24)
+		return -EINVAL;
+	objhdl = kzalloc(sizeof(*objhdl), GFP_KERNEL);
+	if (!objhdl)
+		return -ENOMEM;
+	objhdl->obj_buf = kmemdup(addr_ptr, mem_size, GFP_KERNEL);
+	if (!objhdl->obj_buf)
+		goto out_objbuf_err;
+	filehdr = (struct icp_qat_uof_filehdr *)objhdl->obj_buf;
+	if (qat_uclo_check_format(filehdr))
+		goto out_objhdr_err;
+	objhdl->obj_hdr = qat_uclo_map_chunk((char *)objhdl->obj_buf, filehdr,
+					     ICP_QAT_UOF_OBJS);
+	if (!objhdl->obj_hdr) {
+		pr_err("QAT: object file chunk is null\n");
+		goto out_objhdr_err;
+	}
+	handle->obj_handle = objhdl;
+	if (qat_uclo_parse_uof_obj(handle))
+		goto out_overlay_obj_err;
+	return 0;
+
+out_overlay_obj_err:
+	handle->obj_handle = NULL;
+	kfree(objhdl->obj_hdr);
+out_objhdr_err:
+	kfree(objhdl->obj_buf);
+out_objbuf_err:
+	kfree(objhdl);
+	return -ENOMEM;
+}
+
+void qat_uclo_del_uof_obj(struct icp_qat_fw_loader_handle *handle)
+{
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	unsigned int a;
+
+	if (!obj_handle)
+		return;
+
+	kfree(obj_handle->uword_buf);
+	for (a = 0; a < obj_handle->uimage_num; a++)
+		kfree(obj_handle->ae_uimage[a].page);
+
+	for (a = 0; a < handle->hal_handle->ae_max_num; a++)
+		qat_uclo_free_ae_data(&obj_handle->ae_data[a]);
+
+	kfree(obj_handle->obj_hdr);
+	kfree(obj_handle->obj_buf);
+	kfree(obj_handle);
+	handle->obj_handle = NULL;
+}
+
+static void qat_uclo_fill_uwords(struct icp_qat_uclo_objhandle *obj_handle,
+				 struct icp_qat_uclo_encap_page *encap_page,
+				 uint64_t *uword, unsigned int addr_p,
+				 unsigned int raddr, uint64_t fill)
+{
+	uint64_t uwrd = 0;
+	unsigned int i;
+
+	if (!encap_page) {
+		*uword = fill;
+		return;
+	}
+	for (i = 0; i < encap_page->uwblock_num; i++) {
+		if (raddr >= encap_page->uwblock[i].start_addr &&
+		    raddr <= encap_page->uwblock[i].start_addr +
+		    encap_page->uwblock[i].words_num - 1) {
+			raddr -= encap_page->uwblock[i].start_addr;
+			raddr *= obj_handle->uword_in_bytes;
+			memcpy(&uwrd, (void *)(((unsigned long)
+			       encap_page->uwblock[i].micro_words) + raddr),
+			       obj_handle->uword_in_bytes);
+			uwrd = uwrd & 0xbffffffffffull;
+		}
+	}
+	*uword = uwrd;
+	if (*uword == INVLD_UWORD)
+		*uword = fill;
+}
+
+static void qat_uclo_wr_uimage_raw_page(struct icp_qat_fw_loader_handle *handle,
+					struct icp_qat_uclo_encap_page
+					*encap_page, unsigned int ae)
+{
+	unsigned int uw_physical_addr, uw_relative_addr, i, words_num, cpylen;
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	uint64_t fill_pat;
+
+	/* load the page starting at appropriate ustore address */
+	/* get fill-pattern from an image -- they are all the same */
+	memcpy(&fill_pat, obj_handle->ae_uimage[0].img_ptr->fill_pattern,
+	       sizeof(uint64_t));
+	uw_physical_addr = encap_page->beg_addr_p;
+	uw_relative_addr = 0;
+	words_num = encap_page->micro_words_num;
+	while (words_num) {
+		if (words_num < UWORD_CPYBUF_SIZE)
+			cpylen = words_num;
+		else
+			cpylen = UWORD_CPYBUF_SIZE;
+
+		/* load the buffer */
+		for (i = 0; i < cpylen; i++)
+			qat_uclo_fill_uwords(obj_handle, encap_page,
+					     &obj_handle->uword_buf[i],
+					     uw_physical_addr + i,
+					     uw_relative_addr + i, fill_pat);
+
+		/* copy the buffer to ustore */
+		qat_hal_wr_uwords(handle, (unsigned char)ae,
+				  uw_physical_addr, cpylen,
+				  obj_handle->uword_buf);
+
+		uw_physical_addr += cpylen;
+		uw_relative_addr += cpylen;
+		words_num -= cpylen;
+	}
+}
+
+static void qat_uclo_wr_uimage_page(struct icp_qat_fw_loader_handle *handle,
+				    struct icp_qat_uof_image *image)
+{
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	unsigned int ctx_mask, s;
+	struct icp_qat_uclo_page *page;
+	unsigned char ae;
+	int ctx;
+
+	if (ICP_QAT_CTX_MODE(image->ae_mode) == ICP_QAT_UCLO_MAX_CTX)
+		ctx_mask = 0xff;
+	else
+		ctx_mask = 0x55;
+	/* load the default page and set assigned CTX PC
+	 * to the entrypoint address */
+	for (ae = 0; ae < handle->hal_handle->ae_max_num; ae++) {
+		if (!test_bit(ae, (unsigned long *)&image->ae_assigned))
+			continue;
+		/* find the slice to which this image is assigned */
+		for (s = 0; s < obj_handle->ae_data[ae].slice_num; s++) {
+			if (image->ctx_assigned & obj_handle->ae_data[ae].
+			    ae_slices[s].ctx_mask_assigned)
+				break;
+		}
+		if (s >= obj_handle->ae_data[ae].slice_num)
+			continue;
+		page = obj_handle->ae_data[ae].ae_slices[s].page;
+		if (!page->encap_page->def_page)
+			continue;
+		qat_uclo_wr_uimage_raw_page(handle, page->encap_page, ae);
+
+		page = obj_handle->ae_data[ae].ae_slices[s].page;
+		for (ctx = 0; ctx < ICP_QAT_UCLO_MAX_CTX; ctx++)
+			obj_handle->ae_data[ae].ae_slices[s].cur_page[ctx] =
+					(ctx_mask & (1 << ctx)) ? page : NULL;
+		qat_hal_set_live_ctx(handle, (unsigned char)ae,
+				     image->ctx_assigned);
+		qat_hal_set_pc(handle, (unsigned char)ae, image->ctx_assigned,
+			       image->entry_address);
+	}
+}
+
+int qat_uclo_wr_all_uimage(struct icp_qat_fw_loader_handle *handle)
+{
+	struct icp_qat_uclo_objhandle *obj_handle = handle->obj_handle;
+	unsigned int i;
+
+	if (qat_uclo_init_globals(handle))
+		return -EINVAL;
+	for (i = 0; i < obj_handle->uimage_num; i++) {
+		if (!obj_handle->ae_uimage[i].img_ptr)
+			return -EINVAL;
+		if (qat_uclo_init_ustore(handle, &obj_handle->ae_uimage[i]))
+			return -EINVAL;
+		qat_uclo_wr_uimage_page(handle,
+					obj_handle->ae_uimage[i].img_ptr);
+	}
+	return 0;
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/Makefile b/drivers/crypto/qat/qat_dh895xcc/Makefile
new file mode 100644
index 00000000000..25171c55704
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xcc/Makefile
@@ -0,0 +1,8 @@
+ccflags-y := -I$(src)/../qat_common
+obj-$(CONFIG_CRYPTO_DEV_QAT_DH895xCC) += qat_dh895xcc.o
+qat_dh895xcc-objs := adf_drv.o \
+		adf_isr.o \
+		adf_dh895xcc_hw_data.o \
+		adf_hw_arbiter.o \
+		qat_admin.o \
+		adf_admin.o
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_admin.c b/drivers/crypto/qat/qat_dh895xcc/adf_admin.c
new file mode 100644
index 00000000000..978d6c56639
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_admin.c
@@ -0,0 +1,144 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include <adf_accel_devices.h>
+#include "adf_drv.h"
+#include "adf_dh895xcc_hw_data.h"
+
+#define ADF_ADMINMSG_LEN 32
+
+struct adf_admin_comms {
+	dma_addr_t phy_addr;
+	void *virt_addr;
+	void __iomem *mailbox_addr;
+	struct mutex lock;	/* protects adf_admin_comms struct */
+};
+
+int adf_put_admin_msg_sync(struct adf_accel_dev *accel_dev,
+			   uint32_t ae, void *in, void *out)
+{
+	struct adf_admin_comms *admin = accel_dev->admin;
+	int offset = ae * ADF_ADMINMSG_LEN * 2;
+	void __iomem *mailbox = admin->mailbox_addr;
+	int mb_offset = ae * ADF_DH895XCC_MAILBOX_STRIDE;
+	int times, received;
+
+	mutex_lock(&admin->lock);
+
+	if (ADF_CSR_RD(mailbox, mb_offset) == 1) {
+		mutex_unlock(&admin->lock);
+		return -EAGAIN;
+	}
+
+	memcpy(admin->virt_addr + offset, in, ADF_ADMINMSG_LEN);
+	ADF_CSR_WR(mailbox, mb_offset, 1);
+	received = 0;
+	for (times = 0; times < 50; times++) {
+		msleep(20);
+		if (ADF_CSR_RD(mailbox, mb_offset) == 0) {
+			received = 1;
+			break;
+		}
+	}
+	if (received)
+		memcpy(out, admin->virt_addr + offset +
+		       ADF_ADMINMSG_LEN, ADF_ADMINMSG_LEN);
+	else
+		pr_err("QAT: Failed to send admin msg to accelerator\n");
+
+	mutex_unlock(&admin->lock);
+	return received ? 0 : -EFAULT;
+}
+
+int adf_init_admin_comms(struct adf_accel_dev *accel_dev)
+{
+	struct adf_admin_comms *admin;
+	struct adf_bar *pmisc = &GET_BARS(accel_dev)[ADF_DH895XCC_PMISC_BAR];
+	void __iomem *csr = pmisc->virt_addr;
+	void __iomem *mailbox = csr + ADF_DH895XCC_MAILBOX_BASE_OFFSET;
+	uint64_t reg_val;
+
+	admin = kzalloc_node(sizeof(*accel_dev->admin), GFP_KERNEL,
+			     accel_dev->numa_node);
+	if (!admin)
+		return -ENOMEM;
+	admin->virt_addr = dma_zalloc_coherent(&GET_DEV(accel_dev), PAGE_SIZE,
+					       &admin->phy_addr, GFP_KERNEL);
+	if (!admin->virt_addr) {
+		dev_err(&GET_DEV(accel_dev), "Failed to allocate dma buff\n");
+		kfree(admin);
+		return -ENOMEM;
+	}
+	reg_val = (uint64_t)admin->phy_addr;
+	ADF_CSR_WR(csr, ADF_DH895XCC_ADMINMSGUR_OFFSET, reg_val >> 32);
+	ADF_CSR_WR(csr, ADF_DH895XCC_ADMINMSGLR_OFFSET, reg_val);
+	mutex_init(&admin->lock);
+	admin->mailbox_addr = mailbox;
+	accel_dev->admin = admin;
+	return 0;
+}
+
+void adf_exit_admin_comms(struct adf_accel_dev *accel_dev)
+{
+	struct adf_admin_comms *admin = accel_dev->admin;
+
+	if (!admin)
+		return;
+
+	if (admin->virt_addr)
+		dma_free_coherent(&GET_DEV(accel_dev), PAGE_SIZE,
+				  admin->virt_addr, admin->phy_addr);
+
+	mutex_destroy(&admin->lock);
+	kfree(admin);
+	accel_dev->admin = NULL;
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
new file mode 100644
index 00000000000..ef05825cc65
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
@@ -0,0 +1,214 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <adf_accel_devices.h>
+#include "adf_dh895xcc_hw_data.h"
+#include "adf_drv.h"
+
+/* Worker thread to service arbiter mappings based on dev SKUs */
+static const uint32_t thrd_to_arb_map_sku4[] = {
+	0x12222AAA, 0x11666666, 0x12222AAA, 0x11666666,
+	0x12222AAA, 0x11222222, 0x12222AAA, 0x11222222,
+	0x00000000, 0x00000000, 0x00000000, 0x00000000
+};
+
+static const uint32_t thrd_to_arb_map_sku6[] = {
+	0x12222AAA, 0x11666666, 0x12222AAA, 0x11666666,
+	0x12222AAA, 0x11222222, 0x12222AAA, 0x11222222,
+	0x12222AAA, 0x11222222, 0x12222AAA, 0x11222222
+};
+
+static struct adf_hw_device_class dh895xcc_class = {
+	.name = ADF_DH895XCC_DEVICE_NAME,
+	.type = DEV_DH895XCC,
+	.instances = 0
+};
+
+static uint32_t get_accel_mask(uint32_t fuse)
+{
+	return (~fuse) >> ADF_DH895XCC_ACCELERATORS_REG_OFFSET &
+			  ADF_DH895XCC_ACCELERATORS_MASK;
+}
+
+static uint32_t get_ae_mask(uint32_t fuse)
+{
+	return (~fuse) & ADF_DH895XCC_ACCELENGINES_MASK;
+}
+
+static uint32_t get_num_accels(struct adf_hw_device_data *self)
+{
+	uint32_t i, ctr = 0;
+
+	if (!self || !self->accel_mask)
+		return 0;
+
+	for (i = 0; i < ADF_DH895XCC_MAX_ACCELERATORS; i++) {
+		if (self->accel_mask & (1 << i))
+			ctr++;
+	}
+	return ctr;
+}
+
+static uint32_t get_num_aes(struct adf_hw_device_data *self)
+{
+	uint32_t i, ctr = 0;
+
+	if (!self || !self->ae_mask)
+		return 0;
+
+	for (i = 0; i < ADF_DH895XCC_MAX_ACCELENGINES; i++) {
+		if (self->ae_mask & (1 << i))
+			ctr++;
+	}
+	return ctr;
+}
+
+static uint32_t get_misc_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_DH895XCC_PMISC_BAR;
+}
+
+static uint32_t get_etr_bar_id(struct adf_hw_device_data *self)
+{
+	return ADF_DH895XCC_ETR_BAR;
+}
+
+static enum dev_sku_info get_sku(struct adf_hw_device_data *self)
+{
+	int sku = (self->fuses & ADF_DH895XCC_FUSECTL_SKU_MASK)
+	    >> ADF_DH895XCC_FUSECTL_SKU_SHIFT;
+
+	switch (sku) {
+	case ADF_DH895XCC_FUSECTL_SKU_1:
+		return DEV_SKU_1;
+	case ADF_DH895XCC_FUSECTL_SKU_2:
+		return DEV_SKU_2;
+	case ADF_DH895XCC_FUSECTL_SKU_3:
+		return DEV_SKU_3;
+	case ADF_DH895XCC_FUSECTL_SKU_4:
+		return DEV_SKU_4;
+	default:
+		return DEV_SKU_UNKNOWN;
+	}
+	return DEV_SKU_UNKNOWN;
+}
+
+void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
+			     uint32_t const **arb_map_config)
+{
+	switch (accel_dev->accel_pci_dev.sku) {
+	case DEV_SKU_1:
+		*arb_map_config = thrd_to_arb_map_sku4;
+		break;
+
+	case DEV_SKU_2:
+	case DEV_SKU_4:
+		*arb_map_config = thrd_to_arb_map_sku6;
+		break;
+	default:
+		pr_err("QAT: The configuration doesn't match any SKU");
+		*arb_map_config = NULL;
+	}
+}
+
+static void adf_enable_error_correction(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	struct adf_bar *misc_bar = &GET_BARS(accel_dev)[ADF_DH895XCC_PMISC_BAR];
+	void __iomem *csr = misc_bar->virt_addr;
+	unsigned int val, i;
+
+	/* Enable Accel Engine error detection & correction */
+	for (i = 0; i < hw_device->get_num_aes(hw_device); i++) {
+		val = ADF_CSR_RD(csr, ADF_DH895XCC_AE_CTX_ENABLES(i));
+		val |= ADF_DH895XCC_ENABLE_AE_ECC_ERR;
+		ADF_CSR_WR(csr, ADF_DH895XCC_AE_CTX_ENABLES(i), val);
+		val = ADF_CSR_RD(csr, ADF_DH895XCC_AE_MISC_CONTROL(i));
+		val |= ADF_DH895XCC_ENABLE_AE_ECC_PARITY_CORR;
+		ADF_CSR_WR(csr, ADF_DH895XCC_AE_MISC_CONTROL(i), val);
+	}
+
+	/* Enable shared memory error detection & correction */
+	for (i = 0; i < hw_device->get_num_accels(hw_device); i++) {
+		val = ADF_CSR_RD(csr, ADF_DH895XCC_UERRSSMSH(i));
+		val |= ADF_DH895XCC_ERRSSMSH_EN;
+		ADF_CSR_WR(csr, ADF_DH895XCC_UERRSSMSH(i), val);
+		val = ADF_CSR_RD(csr, ADF_DH895XCC_CERRSSMSH(i));
+		val |= ADF_DH895XCC_ERRSSMSH_EN;
+		ADF_CSR_WR(csr, ADF_DH895XCC_CERRSSMSH(i), val);
+	}
+}
+
+void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class = &dh895xcc_class;
+	hw_data->instance_id = dh895xcc_class.instances++;
+	hw_data->num_banks = ADF_DH895XCC_ETR_MAX_BANKS;
+	hw_data->num_accel = ADF_DH895XCC_MAX_ACCELERATORS;
+	hw_data->pci_dev_id = ADF_DH895XCC_PCI_DEVICE_ID;
+	hw_data->num_logical_accel = 1;
+	hw_data->num_engines = ADF_DH895XCC_MAX_ACCELENGINES;
+	hw_data->tx_rx_gap = ADF_DH895XCC_RX_RINGS_OFFSET;
+	hw_data->tx_rings_mask = ADF_DH895XCC_TX_RINGS_MASK;
+	hw_data->alloc_irq = adf_isr_resource_alloc;
+	hw_data->free_irq = adf_isr_resource_free;
+	hw_data->enable_error_correction = adf_enable_error_correction;
+	hw_data->hw_arb_ring_enable = adf_update_ring_arb_enable;
+	hw_data->hw_arb_ring_disable = adf_update_ring_arb_enable;
+	hw_data->get_accel_mask = get_accel_mask;
+	hw_data->get_ae_mask = get_ae_mask;
+	hw_data->get_num_accels = get_num_accels;
+	hw_data->get_num_aes = get_num_aes;
+	hw_data->get_etr_bar_id = get_etr_bar_id;
+	hw_data->get_misc_bar_id = get_misc_bar_id;
+	hw_data->get_sku = get_sku;
+	hw_data->fw_name = ADF_DH895XCC_FW;
+}
+
+void adf_clean_hw_data_dh895xcc(struct adf_hw_device_data *hw_data)
+{
+	hw_data->dev_class->instances--;
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
new file mode 100644
index 00000000000..b707f292b37
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.h
@@ -0,0 +1,86 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_DH895x_HW_DATA_H_
+#define ADF_DH895x_HW_DATA_H_
+
+/* PCIe configuration space */
+#define ADF_DH895XCC_RX_RINGS_OFFSET 8
+#define ADF_DH895XCC_TX_RINGS_MASK 0xFF
+#define ADF_DH895XCC_FUSECTL_OFFSET 0x40
+#define ADF_DH895XCC_FUSECTL_SKU_MASK 0x300000
+#define ADF_DH895XCC_FUSECTL_SKU_SHIFT 20
+#define ADF_DH895XCC_FUSECTL_SKU_1 0x0
+#define ADF_DH895XCC_FUSECTL_SKU_2 0x1
+#define ADF_DH895XCC_FUSECTL_SKU_3 0x2
+#define ADF_DH895XCC_FUSECTL_SKU_4 0x3
+#define ADF_DH895XCC_MAX_ACCELERATORS 6
+#define ADF_DH895XCC_MAX_ACCELENGINES 12
+#define ADF_DH895XCC_ACCELERATORS_REG_OFFSET 13
+#define ADF_DH895XCC_ACCELERATORS_MASK 0x3F
+#define ADF_DH895XCC_ACCELENGINES_MASK 0xFFF
+#define ADF_DH895XCC_LEGFUSE_OFFSET 0x4C
+#define ADF_DH895XCC_ETR_MAX_BANKS 32
+#define ADF_DH895XCC_SMIAPF0_MASK_OFFSET (0x3A000 + 0x28)
+#define ADF_DH895XCC_SMIAPF1_MASK_OFFSET (0x3A000 + 0x30)
+#define ADF_DH895XCC_SMIA0_MASK 0xFFFF
+#define ADF_DH895XCC_SMIA1_MASK 0x1
+/* Error detection and correction */
+#define ADF_DH895XCC_AE_CTX_ENABLES(i) (i * 0x1000 + 0x20818)
+#define ADF_DH895XCC_AE_MISC_CONTROL(i) (i * 0x1000 + 0x20960)
+#define ADF_DH895XCC_ENABLE_AE_ECC_ERR (1 << 28)
+#define ADF_DH895XCC_ENABLE_AE_ECC_PARITY_CORR (1 << 24 | 1 << 12)
+#define ADF_DH895XCC_UERRSSMSH(i) (i * 0x4000 + 0x18)
+#define ADF_DH895XCC_CERRSSMSH(i) (i * 0x4000 + 0x10)
+#define ADF_DH895XCC_ERRSSMSH_EN (1 << 3)
+
+/* Admin Messages Registers */
+#define ADF_DH895XCC_ADMINMSGUR_OFFSET (0x3A000 + 0x574)
+#define ADF_DH895XCC_ADMINMSGLR_OFFSET (0x3A000 + 0x578)
+#define ADF_DH895XCC_MAILBOX_BASE_OFFSET 0x20970
+#define ADF_DH895XCC_MAILBOX_STRIDE 0x1000
+#define ADF_DH895XCC_FW "qat_895xcc.bin"
+#endif
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
new file mode 100644
index 00000000000..0d0435a41be
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
@@ -0,0 +1,449 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/workqueue.h>
+#include <linux/io.h>
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_cfg.h>
+#include <adf_transport_access_macros.h>
+#include "adf_dh895xcc_hw_data.h"
+#include "adf_drv.h"
+
+static const char adf_driver_name[] = ADF_DH895XCC_DEVICE_NAME;
+
+#define ADF_SYSTEM_DEVICE(device_id) \
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)}
+
+static const struct pci_device_id adf_pci_tbl[] = {
+	ADF_SYSTEM_DEVICE(ADF_DH895XCC_PCI_DEVICE_ID),
+	{0,}
+};
+MODULE_DEVICE_TABLE(pci, adf_pci_tbl);
+
+static int adf_probe(struct pci_dev *dev, const struct pci_device_id *ent);
+static void adf_remove(struct pci_dev *dev);
+
+static struct pci_driver adf_driver = {
+	.id_table = adf_pci_tbl,
+	.name = adf_driver_name,
+	.probe = adf_probe,
+	.remove = adf_remove
+};
+
+static void adf_cleanup_accel(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *accel_pci_dev = &accel_dev->accel_pci_dev;
+	int i;
+
+	adf_exit_admin_comms(accel_dev);
+	adf_exit_arb(accel_dev);
+	adf_cleanup_etr_data(accel_dev);
+
+	for (i = 0; i < ADF_PCI_MAX_BARS; i++) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i];
+
+		if (bar->virt_addr)
+			pci_iounmap(accel_pci_dev->pci_dev, bar->virt_addr);
+	}
+
+	if (accel_dev->hw_device) {
+		switch (accel_dev->hw_device->pci_dev_id) {
+		case ADF_DH895XCC_PCI_DEVICE_ID:
+			adf_clean_hw_data_dh895xcc(accel_dev->hw_device);
+			break;
+		default:
+			break;
+		}
+		kfree(accel_dev->hw_device);
+	}
+	adf_cfg_dev_remove(accel_dev);
+	debugfs_remove(accel_dev->debugfs_dir);
+	adf_devmgr_rm_dev(accel_dev);
+	pci_release_regions(accel_pci_dev->pci_dev);
+	pci_disable_device(accel_pci_dev->pci_dev);
+	kfree(accel_dev);
+}
+
+static uint8_t adf_get_dev_node_id(struct pci_dev *pdev)
+{
+	unsigned int bus_per_cpu = 0;
+	struct cpuinfo_x86 *c = &cpu_data(num_online_cpus() - 1);
+
+	if (!c->phys_proc_id)
+		return 0;
+
+	bus_per_cpu = 256 / (c->phys_proc_id + 1);
+
+	if (bus_per_cpu != 0)
+		return pdev->bus->number / bus_per_cpu;
+	return 0;
+}
+
+static int qat_dev_start(struct adf_accel_dev *accel_dev)
+{
+	int cpus = num_online_cpus();
+	int banks = GET_MAX_BANKS(accel_dev);
+	int instances = min(cpus, banks);
+	char key[ADF_CFG_MAX_KEY_LEN_IN_BYTES];
+	int i;
+	unsigned long val;
+
+	if (adf_cfg_section_add(accel_dev, ADF_KERNEL_SEC))
+		goto err;
+	if (adf_cfg_section_add(accel_dev, "Accelerator0"))
+		goto err;
+	for (i = 0; i < instances; i++) {
+		val = i;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_BANK_NUM, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_ETRMGR_CORE_AFFINITY,
+			 i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_SIZE, i);
+		val = 128;
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 512;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_SIZE, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 0;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_TX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 2;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_TX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 4;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_RND_TX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 8;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_ASYM_RX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 10;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_SYM_RX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = 12;
+		snprintf(key, sizeof(key), ADF_CY "%d" ADF_RING_RND_RX, i);
+		if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+						key, (void *)&val, ADF_DEC))
+			goto err;
+
+		val = ADF_COALESCING_DEF_TIME;
+		snprintf(key, sizeof(key), ADF_ETRMGR_COALESCE_TIMER_FORMAT, i);
+		if (adf_cfg_add_key_value_param(accel_dev, "Accelerator0",
+						key, (void *)&val, ADF_DEC))
+			goto err;
+	}
+
+	val = i;
+	if (adf_cfg_add_key_value_param(accel_dev, ADF_KERNEL_SEC,
+					ADF_NUM_CY, (void *)&val, ADF_DEC))
+		goto err;
+
+	set_bit(ADF_STATUS_CONFIGURED, &accel_dev->status);
+	return adf_dev_start(accel_dev);
+err:
+	dev_err(&GET_DEV(accel_dev), "Failed to start QAT accel dev\n");
+	return -EINVAL;
+}
+
+static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	struct adf_accel_dev *accel_dev;
+	struct adf_accel_pci *accel_pci_dev;
+	struct adf_hw_device_data *hw_data;
+	void __iomem *pmisc_bar_addr = NULL;
+	char name[ADF_DEVICE_NAME_LENGTH];
+	unsigned int i, bar_nr;
+	uint8_t node;
+	int ret;
+
+	switch (ent->device) {
+	case ADF_DH895XCC_PCI_DEVICE_ID:
+		break;
+	default:
+		dev_err(&pdev->dev, "Invalid device 0x%x.\n", ent->device);
+		return -ENODEV;
+	}
+
+	node = adf_get_dev_node_id(pdev);
+	accel_dev = kzalloc_node(sizeof(*accel_dev), GFP_KERNEL, node);
+	if (!accel_dev)
+		return -ENOMEM;
+
+	accel_dev->numa_node = node;
+	INIT_LIST_HEAD(&accel_dev->crypto_list);
+
+	/* Add accel device to accel table.
+	 * This should be called before adf_cleanup_accel is called */
+	if (adf_devmgr_add_dev(accel_dev)) {
+		dev_err(&pdev->dev, "Failed to add new accelerator device.\n");
+		kfree(accel_dev);
+		return -EFAULT;
+	}
+
+	accel_dev->owner = THIS_MODULE;
+	/* Allocate and configure device configuration structure */
+	hw_data = kzalloc_node(sizeof(*hw_data), GFP_KERNEL, node);
+	if (!hw_data) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	accel_dev->hw_device = hw_data;
+	switch (ent->device) {
+	case ADF_DH895XCC_PCI_DEVICE_ID:
+		adf_init_hw_data_dh895xcc(accel_dev->hw_device);
+		break;
+	default:
+		return -ENODEV;
+	}
+	accel_pci_dev = &accel_dev->accel_pci_dev;
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &accel_pci_dev->revid);
+	pci_read_config_dword(pdev, ADF_DH895XCC_FUSECTL_OFFSET,
+			      &hw_data->fuses);
+
+	/* Get Accelerators and Accelerators Engines masks */
+	hw_data->accel_mask = hw_data->get_accel_mask(hw_data->fuses);
+	hw_data->ae_mask = hw_data->get_ae_mask(hw_data->fuses);
+	accel_pci_dev->sku = hw_data->get_sku(hw_data);
+	accel_pci_dev->pci_dev = pdev;
+	/* If the device has no acceleration engines then ignore it. */
+	if (!hw_data->accel_mask || !hw_data->ae_mask ||
+	    ((~hw_data->ae_mask) & 0x01)) {
+		dev_err(&pdev->dev, "No acceleration units found");
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* Create dev top level debugfs entry */
+	snprintf(name, sizeof(name), "%s%s_dev%d", ADF_DEVICE_NAME_PREFIX,
+		 hw_data->dev_class->name, hw_data->instance_id);
+	accel_dev->debugfs_dir = debugfs_create_dir(name, NULL);
+	if (!accel_dev->debugfs_dir) {
+		dev_err(&pdev->dev, "Could not create debugfs dir\n");
+		ret = -EINVAL;
+		goto out_err;
+	}
+
+	/* Create device configuration table */
+	ret = adf_cfg_dev_add(accel_dev);
+	if (ret)
+		goto out_err;
+
+	/* enable PCI device */
+	if (pci_enable_device(pdev)) {
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* set dma identifier */
+	if (pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+		if ((pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) {
+			dev_err(&pdev->dev, "No usable DMA configuration\n");
+			ret = -EFAULT;
+			goto out_err;
+		} else {
+			pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		}
+
+	} else {
+		pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	}
+
+	if (pci_request_regions(pdev, adf_driver_name)) {
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	/* Read accelerator capabilities mask */
+	pci_read_config_dword(pdev, ADF_DH895XCC_LEGFUSE_OFFSET,
+			      &hw_data->accel_capabilities_mask);
+
+	/* Find and map all the device's BARS */
+	for (i = 0; i < ADF_PCI_MAX_BARS; i++) {
+		struct adf_bar *bar = &accel_pci_dev->pci_bars[i];
+
+		bar_nr = i * 2;
+		bar->base_addr = pci_resource_start(pdev, bar_nr);
+		if (!bar->base_addr)
+			break;
+		bar->size = pci_resource_len(pdev, bar_nr);
+		bar->virt_addr = pci_iomap(accel_pci_dev->pci_dev, bar_nr, 0);
+		if (!bar->virt_addr) {
+			dev_err(&pdev->dev, "Failed to map BAR %d\n", i);
+			ret = -EFAULT;
+			goto out_err;
+		}
+		if (i == ADF_DH895XCC_PMISC_BAR)
+			pmisc_bar_addr = bar->virt_addr;
+	}
+	pci_set_master(pdev);
+
+	if (adf_enable_aer(accel_dev, &adf_driver)) {
+		dev_err(&pdev->dev, "Failed to enable aer\n");
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	if (adf_init_etr_data(accel_dev)) {
+		dev_err(&pdev->dev, "Failed initialize etr\n");
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	if (adf_init_admin_comms(accel_dev)) {
+		dev_err(&pdev->dev, "Failed initialize admin comms\n");
+		ret = -EFAULT;
+		goto out_err;
+	}
+
+	if (adf_init_arb(accel_dev)) {
+		dev_err(&pdev->dev, "Failed initialize hw arbiter\n");
+		ret = -EFAULT;
+		goto out_err;
+	}
+	if (pci_save_state(pdev)) {
+		dev_err(&pdev->dev, "Failed to save pci state\n");
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	/* Enable bundle and misc interrupts */
+	ADF_CSR_WR(pmisc_bar_addr, ADF_DH895XCC_SMIAPF0_MASK_OFFSET,
+		   ADF_DH895XCC_SMIA0_MASK);
+	ADF_CSR_WR(pmisc_bar_addr, ADF_DH895XCC_SMIAPF1_MASK_OFFSET,
+		   ADF_DH895XCC_SMIA1_MASK);
+
+	ret = qat_dev_start(accel_dev);
+	if (ret) {
+		adf_dev_stop(accel_dev);
+		goto out_err;
+	}
+
+	return 0;
+out_err:
+	adf_cleanup_accel(accel_dev);
+	return ret;
+}
+
+static void __exit adf_remove(struct pci_dev *pdev)
+{
+	struct adf_accel_dev *accel_dev = adf_devmgr_pci_to_accel_dev(pdev);
+
+	if (!accel_dev) {
+		pr_err("QAT: Driver removal failed\n");
+		return;
+	}
+	if (adf_dev_stop(accel_dev))
+		dev_err(&GET_DEV(accel_dev), "Failed to stop QAT accel dev\n");
+	adf_disable_aer(accel_dev);
+	adf_cleanup_accel(accel_dev);
+}
+
+static int __init adfdrv_init(void)
+{
+	request_module("intel_qat");
+	if (qat_admin_register())
+		return -EFAULT;
+
+	if (pci_register_driver(&adf_driver)) {
+		pr_err("QAT: Driver initialization failed\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void __exit adfdrv_release(void)
+{
+	pci_unregister_driver(&adf_driver);
+	qat_admin_unregister();
+}
+
+module_init(adfdrv_init);
+module_exit(adfdrv_release);
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Intel");
+MODULE_FIRMWARE("qat_895xcc.bin");
+MODULE_DESCRIPTION("Intel(R) QuickAssist Technology");
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.h b/drivers/crypto/qat/qat_dh895xcc/adf_drv.h
new file mode 100644
index 00000000000..a2fbb6ce75c
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.h
@@ -0,0 +1,67 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#ifndef ADF_DH895x_DRV_H_
+#define ADF_DH895x_DRV_H_
+#include <adf_accel_devices.h>
+#include <adf_transport.h>
+
+void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
+void adf_clean_hw_data_dh895xcc(struct adf_hw_device_data *hw_data);
+int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev);
+void adf_isr_resource_free(struct adf_accel_dev *accel_dev);
+void adf_update_ring_arb_enable(struct adf_etr_ring_data *ring);
+void adf_get_arbiter_mapping(struct adf_accel_dev *accel_dev,
+			     uint32_t const **arb_map_config);
+int adf_init_admin_comms(struct adf_accel_dev *accel_dev);
+void adf_exit_admin_comms(struct adf_accel_dev *accel_dev);
+int adf_put_admin_msg_sync(struct adf_accel_dev *accel_dev,
+			   uint32_t ae, void *in, void *out);
+int qat_admin_register(void);
+int qat_admin_unregister(void);
+int adf_init_arb(struct adf_accel_dev *accel_dev);
+void adf_exit_arb(struct adf_accel_dev *accel_dev);
+#endif
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_hw_arbiter.c b/drivers/crypto/qat/qat_dh895xcc/adf_hw_arbiter.c
new file mode 100644
index 00000000000..1864bdb36f8
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_hw_arbiter.c
@@ -0,0 +1,159 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <adf_accel_devices.h>
+#include <adf_transport_internal.h>
+#include "adf_drv.h"
+
+#define ADF_ARB_NUM 4
+#define ADF_ARB_REQ_RING_NUM 8
+#define ADF_ARB_REG_SIZE 0x4
+#define ADF_ARB_WTR_SIZE 0x20
+#define ADF_ARB_OFFSET 0x30000
+#define ADF_ARB_REG_SLOT 0x1000
+#define ADF_ARB_WTR_OFFSET 0x010
+#define ADF_ARB_RO_EN_OFFSET 0x090
+#define ADF_ARB_WQCFG_OFFSET 0x100
+#define ADF_ARB_WRK_2_SER_MAP_OFFSET 0x180
+#define ADF_ARB_WRK_2_SER_MAP 10
+#define ADF_ARB_RINGSRVARBEN_OFFSET 0x19C
+
+#define WRITE_CSR_ARB_RINGSRVARBEN(csr_addr, index, value) \
+	ADF_CSR_WR(csr_addr, ADF_ARB_RINGSRVARBEN_OFFSET + \
+	(ADF_ARB_REG_SLOT * index), value)
+
+#define WRITE_CSR_ARB_RESPORDERING(csr_addr, index, value) \
+	ADF_CSR_WR(csr_addr, (ADF_ARB_OFFSET + \
+	ADF_ARB_RO_EN_OFFSET) + (ADF_ARB_REG_SIZE * index), value)
+
+#define WRITE_CSR_ARB_WEIGHT(csr_addr, arb, index, value) \
+	ADF_CSR_WR(csr_addr, (ADF_ARB_OFFSET + \
+	ADF_ARB_WTR_OFFSET) + (ADF_ARB_WTR_SIZE * arb) + \
+	(ADF_ARB_REG_SIZE * index), value)
+
+#define WRITE_CSR_ARB_SARCONFIG(csr_addr, index, value) \
+	ADF_CSR_WR(csr_addr, ADF_ARB_OFFSET + \
+	(ADF_ARB_REG_SIZE * index), value)
+
+#define WRITE_CSR_ARB_WRK_2_SER_MAP(csr_addr, index, value) \
+	ADF_CSR_WR(csr_addr, (ADF_ARB_OFFSET + \
+	ADF_ARB_WRK_2_SER_MAP_OFFSET) + \
+	(ADF_ARB_REG_SIZE * index), value)
+
+#define WRITE_CSR_ARB_WQCFG(csr_addr, index, value) \
+	ADF_CSR_WR(csr_addr, (ADF_ARB_OFFSET + \
+	ADF_ARB_WQCFG_OFFSET) + (ADF_ARB_REG_SIZE * index), value)
+
+int adf_init_arb(struct adf_accel_dev *accel_dev)
+{
+	void __iomem *csr = accel_dev->transport->banks[0].csr_addr;
+	uint32_t arb_cfg = 0x1 << 31 | 0x4 << 4 | 0x1;
+	uint32_t arb, i;
+	const uint32_t *thd_2_arb_cfg;
+
+	/* Service arb configured for 32 bytes responses and
+	 * ring flow control check enabled. */
+	for (arb = 0; arb < ADF_ARB_NUM; arb++)
+		WRITE_CSR_ARB_SARCONFIG(csr, arb, arb_cfg);
+
+	/* Setup service weighting */
+	for (arb = 0; arb < ADF_ARB_NUM; arb++)
+		for (i = 0; i < ADF_ARB_REQ_RING_NUM; i++)
+			WRITE_CSR_ARB_WEIGHT(csr, arb, i, 0xFFFFFFFF);
+
+	/* Setup ring response ordering */
+	for (i = 0; i < ADF_ARB_REQ_RING_NUM; i++)
+		WRITE_CSR_ARB_RESPORDERING(csr, i, 0xFFFFFFFF);
+
+	/* Setup worker queue registers */
+	for (i = 0; i < ADF_ARB_WRK_2_SER_MAP; i++)
+		WRITE_CSR_ARB_WQCFG(csr, i, i);
+
+	/* Map worker threads to service arbiters */
+	adf_get_arbiter_mapping(accel_dev, &thd_2_arb_cfg);
+
+	if (!thd_2_arb_cfg)
+		return -EFAULT;
+
+	for (i = 0; i < ADF_ARB_WRK_2_SER_MAP; i++)
+		WRITE_CSR_ARB_WRK_2_SER_MAP(csr, i, *(thd_2_arb_cfg + i));
+
+	return 0;
+}
+
+void adf_update_ring_arb_enable(struct adf_etr_ring_data *ring)
+{
+	WRITE_CSR_ARB_RINGSRVARBEN(ring->bank->csr_addr,
+				   ring->bank->bank_number,
+				   ring->bank->ring_mask & 0xFF);
+}
+
+void adf_exit_arb(struct adf_accel_dev *accel_dev)
+{
+	void __iomem *csr;
+	unsigned int i;
+
+	if (!accel_dev->transport)
+		return;
+
+	csr = accel_dev->transport->banks[0].csr_addr;
+
+	/* Reset arbiter configuration */
+	for (i = 0; i < ADF_ARB_NUM; i++)
+		WRITE_CSR_ARB_SARCONFIG(csr, i, 0);
+
+	/* Shutdown work queue */
+	for (i = 0; i < ADF_ARB_WRK_2_SER_MAP; i++)
+		WRITE_CSR_ARB_WQCFG(csr, i, 0);
+
+	/* Unmap worker threads to service arbiters */
+	for (i = 0; i < ADF_ARB_WRK_2_SER_MAP; i++)
+		WRITE_CSR_ARB_WRK_2_SER_MAP(csr, i, 0);
+
+	/* Disable arbitration on all rings */
+	for (i = 0; i < GET_MAX_BANKS(accel_dev); i++)
+		WRITE_CSR_ARB_RINGSRVARBEN(csr, i, 0);
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_isr.c b/drivers/crypto/qat/qat_dh895xcc/adf_isr.c
new file mode 100644
index 00000000000..d4172dedf77
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_isr.c
@@ -0,0 +1,266 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include <adf_cfg.h>
+#include <adf_cfg_strings.h>
+#include <adf_cfg_common.h>
+#include <adf_transport_access_macros.h>
+#include <adf_transport_internal.h>
+#include "adf_drv.h"
+
+static int adf_enable_msix(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *pci_dev_info = &accel_dev->accel_pci_dev;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	uint32_t msix_num_entries = hw_data->num_banks + 1;
+	int i;
+
+	for (i = 0; i < msix_num_entries; i++)
+		pci_dev_info->msix_entries.entries[i].entry = i;
+
+	if (pci_enable_msix(pci_dev_info->pci_dev,
+			    pci_dev_info->msix_entries.entries,
+			    msix_num_entries)) {
+		pr_err("QAT: Failed to enable MSIX IRQ\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+static void adf_disable_msix(struct adf_accel_pci *pci_dev_info)
+{
+	pci_disable_msix(pci_dev_info->pci_dev);
+}
+
+static irqreturn_t adf_msix_isr_bundle(int irq, void *bank_ptr)
+{
+	struct adf_etr_bank_data *bank = bank_ptr;
+
+	WRITE_CSR_INT_FLAG_AND_COL(bank->csr_addr, bank->bank_number, 0);
+	tasklet_hi_schedule(&bank->resp_hanlder);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t adf_msix_isr_ae(int irq, void *dev_ptr)
+{
+	struct adf_accel_dev *accel_dev = dev_ptr;
+
+	pr_info("QAT: qat_dev%d spurious AE interrupt\n", accel_dev->accel_id);
+	return IRQ_HANDLED;
+}
+
+static int adf_request_irqs(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *pci_dev_info = &accel_dev->accel_pci_dev;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct msix_entry *msixe = pci_dev_info->msix_entries.entries;
+	struct adf_etr_data *etr_data = accel_dev->transport;
+	int ret, i;
+	char *name;
+
+	/* Request msix irq for all banks */
+	for (i = 0; i < hw_data->num_banks; i++) {
+		struct adf_etr_bank_data *bank = &etr_data->banks[i];
+		unsigned int cpu, cpus = num_online_cpus();
+
+		name = *(pci_dev_info->msix_entries.names + i);
+		snprintf(name, ADF_MAX_MSIX_VECTOR_NAME,
+			 "qat%d-bundle%d", accel_dev->accel_id, i);
+		ret = request_irq(msixe[i].vector,
+				  adf_msix_isr_bundle, 0, name, bank);
+		if (ret) {
+			pr_err("QAT: failed to enable irq %d for %s\n",
+			       msixe[i].vector, name);
+			return ret;
+		}
+
+		cpu = ((accel_dev->accel_id * hw_data->num_banks) + i) % cpus;
+		irq_set_affinity_hint(msixe[i].vector, get_cpu_mask(cpu));
+	}
+
+	/* Request msix irq for AE */
+	name = *(pci_dev_info->msix_entries.names + i);
+	snprintf(name, ADF_MAX_MSIX_VECTOR_NAME,
+		 "qat%d-ae-cluster", accel_dev->accel_id);
+	ret = request_irq(msixe[i].vector, adf_msix_isr_ae, 0, name, accel_dev);
+	if (ret) {
+		pr_err("QAT: failed to enable irq %d, for %s\n",
+		       msixe[i].vector, name);
+		return ret;
+	}
+	return ret;
+}
+
+static void adf_free_irqs(struct adf_accel_dev *accel_dev)
+{
+	struct adf_accel_pci *pci_dev_info = &accel_dev->accel_pci_dev;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	struct msix_entry *msixe = pci_dev_info->msix_entries.entries;
+	struct adf_etr_data *etr_data = accel_dev->transport;
+	int i;
+
+	for (i = 0; i < hw_data->num_banks; i++) {
+		irq_set_affinity_hint(msixe[i].vector, NULL);
+		free_irq(msixe[i].vector, &etr_data->banks[i]);
+	}
+	irq_set_affinity_hint(msixe[i].vector, NULL);
+	free_irq(msixe[i].vector, accel_dev);
+}
+
+static int adf_isr_alloc_msix_entry_table(struct adf_accel_dev *accel_dev)
+{
+	int i;
+	char **names;
+	struct msix_entry *entries;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	uint32_t msix_num_entries = hw_data->num_banks + 1;
+
+	entries = kzalloc_node(msix_num_entries * sizeof(*entries),
+			       GFP_KERNEL, accel_dev->numa_node);
+	if (!entries)
+		return -ENOMEM;
+
+	names = kcalloc(msix_num_entries, sizeof(char *), GFP_KERNEL);
+	if (!names) {
+		kfree(entries);
+		return -ENOMEM;
+	}
+	for (i = 0; i < msix_num_entries; i++) {
+		*(names + i) = kzalloc(ADF_MAX_MSIX_VECTOR_NAME, GFP_KERNEL);
+		if (!(*(names + i)))
+			goto err;
+	}
+	accel_dev->accel_pci_dev.msix_entries.entries = entries;
+	accel_dev->accel_pci_dev.msix_entries.names = names;
+	return 0;
+err:
+	for (i = 0; i < msix_num_entries; i++) {
+		if (*(names + i))
+			kfree(*(names + i));
+	}
+	kfree(entries);
+	kfree(names);
+	return -ENOMEM;
+}
+
+static void adf_isr_free_msix_entry_table(struct adf_accel_dev *accel_dev)
+{
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	uint32_t msix_num_entries = hw_data->num_banks + 1;
+	char **names = accel_dev->accel_pci_dev.msix_entries.names;
+	int i;
+
+	kfree(accel_dev->accel_pci_dev.msix_entries.entries);
+	for (i = 0; i < msix_num_entries; i++) {
+		if (*(names + i))
+			kfree(*(names + i));
+	}
+	kfree(names);
+}
+
+static int adf_setup_bh(struct adf_accel_dev *accel_dev)
+{
+	struct adf_etr_data *priv_data = accel_dev->transport;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	int i;
+
+	for (i = 0; i < hw_data->num_banks; i++)
+		tasklet_init(&priv_data->banks[i].resp_hanlder,
+			     adf_response_handler,
+			     (unsigned long)&priv_data->banks[i]);
+	return 0;
+}
+
+static void adf_cleanup_bh(struct adf_accel_dev *accel_dev)
+{
+	struct adf_etr_data *priv_data = accel_dev->transport;
+	struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+	int i;
+
+	for (i = 0; i < hw_data->num_banks; i++) {
+		tasklet_disable(&priv_data->banks[i].resp_hanlder);
+		tasklet_kill(&priv_data->banks[i].resp_hanlder);
+	}
+}
+
+void adf_isr_resource_free(struct adf_accel_dev *accel_dev)
+{
+	adf_free_irqs(accel_dev);
+	adf_cleanup_bh(accel_dev);
+	adf_disable_msix(&accel_dev->accel_pci_dev);
+	adf_isr_free_msix_entry_table(accel_dev);
+}
+
+int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev)
+{
+	int ret;
+
+	ret = adf_isr_alloc_msix_entry_table(accel_dev);
+	if (ret)
+		return ret;
+	if (adf_enable_msix(accel_dev))
+		goto err_out;
+
+	if (adf_setup_bh(accel_dev))
+		goto err_out;
+
+	if (adf_request_irqs(accel_dev))
+		goto err_out;
+
+	return 0;
+err_out:
+	adf_isr_resource_free(accel_dev);
+	return -EFAULT;
+}
diff --git a/drivers/crypto/qat/qat_dh895xcc/qat_admin.c b/drivers/crypto/qat/qat_dh895xcc/qat_admin.c
new file mode 100644
index 00000000000..55b7a8e48ba
--- /dev/null
+++ b/drivers/crypto/qat/qat_dh895xcc/qat_admin.c
@@ -0,0 +1,107 @@
+/*
+  This file is provided under a dual BSD/GPLv2 license.  When using or
+  redistributing this file, you may do so under either license.
+
+  GPL LICENSE SUMMARY
+  Copyright(c) 2014 Intel Corporation.
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of version 2 of the GNU General Public License as
+  published by the Free Software Foundation.
+
+  This program is distributed in the hope that it will be useful, but
+  WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+  General Public License for more details.
+
+  Contact Information:
+  qat-linux@intel.com
+
+  BSD LICENSE
+  Copyright(c) 2014 Intel Corporation.
+  Redistribution and use in source and binary forms, with or without
+  modification, are permitted provided that the following conditions
+  are met:
+
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in
+      the documentation and/or other materials provided with the
+      distribution.
+    * Neither the name of Intel Corporation nor the names of its
+      contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+#include <icp_qat_fw_init_admin.h>
+#include <adf_accel_devices.h>
+#include <adf_common_drv.h>
+#include "adf_drv.h"
+
+static struct service_hndl qat_admin;
+
+static int qat_send_admin_cmd(struct adf_accel_dev *accel_dev, int cmd)
+{
+	struct adf_hw_device_data *hw_device = accel_dev->hw_device;
+	struct icp_qat_fw_init_admin_req req;
+	struct icp_qat_fw_init_admin_resp resp;
+	int i;
+
+	memset(&req, 0, sizeof(struct icp_qat_fw_init_admin_req));
+	req.init_admin_cmd_id = cmd;
+	for (i = 0; i < hw_device->get_num_aes(hw_device); i++) {
+		memset(&resp, 0, sizeof(struct icp_qat_fw_init_admin_resp));
+		if (adf_put_admin_msg_sync(accel_dev, i, &req, &resp) ||
+		    resp.init_resp_hdr.status)
+			return -EFAULT;
+	}
+	return 0;
+}
+
+static int qat_admin_start(struct adf_accel_dev *accel_dev)
+{
+	return qat_send_admin_cmd(accel_dev, ICP_QAT_FW_INIT_ME);
+}
+
+static int qat_admin_event_handler(struct adf_accel_dev *accel_dev,
+				   enum adf_event event)
+{
+	int ret;
+
+	switch (event) {
+	case ADF_EVENT_START:
+		ret = qat_admin_start(accel_dev);
+		break;
+	case ADF_EVENT_STOP:
+	case ADF_EVENT_INIT:
+	case ADF_EVENT_SHUTDOWN:
+	default:
+		ret = 0;
+	}
+	return ret;
+}
+
+int qat_admin_register(void)
+{
+	memset(&qat_admin, 0, sizeof(struct service_hndl));
+	qat_admin.event_hld = qat_admin_event_handler;
+	qat_admin.name = "qat_admin";
+	qat_admin.admin = 1;
+	return adf_service_register(&qat_admin);
+}
+
+int qat_admin_unregister(void)
+{
+	return adf_service_unregister(&qat_admin);
+}
diff --git a/drivers/crypto/qce/Makefile b/drivers/crypto/qce/Makefile
new file mode 100644
index 00000000000..348dc3173af
--- /dev/null
+++ b/drivers/crypto/qce/Makefile
@@ -0,0 +1,6 @@
+obj-$(CONFIG_CRYPTO_DEV_QCE) += qcrypto.o
+qcrypto-objs := core.o \
+		common.o \
+		dma.o \
+		sha.o \
+		ablkcipher.o
diff --git a/drivers/crypto/qce/ablkcipher.c b/drivers/crypto/qce/ablkcipher.c
new file mode 100644
index 00000000000..ad592de475a
--- /dev/null
+++ b/drivers/crypto/qce/ablkcipher.c
@@ -0,0 +1,431 @@
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/types.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/des.h>
+
+#include "cipher.h"
+
+static LIST_HEAD(ablkcipher_algs);
+
+static void qce_ablkcipher_done(void *data)
+{
+	struct crypto_async_request *async_req = data;
+	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
+	struct qce_cipher_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct qce_alg_template *tmpl = to_cipher_tmpl(async_req->tfm);
+	struct qce_device *qce = tmpl->qce;
+	enum dma_data_direction dir_src, dir_dst;
+	u32 status;
+	int error;
+	bool diff_dst;
+
+	diff_dst = (req->src != req->dst) ? true : false;
+	dir_src = diff_dst ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL;
+	dir_dst = diff_dst ? DMA_FROM_DEVICE : DMA_BIDIRECTIONAL;
+
+	error = qce_dma_terminate_all(&qce->dma);
+	if (error)
+		dev_dbg(qce->dev, "ablkcipher dma termination error (%d)\n",
+			error);
+
+	if (diff_dst)
+		qce_unmapsg(qce->dev, rctx->src_sg, rctx->src_nents, dir_src,
+			    rctx->dst_chained);
+	qce_unmapsg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst,
+		    rctx->dst_chained);
+
+	sg_free_table(&rctx->dst_tbl);
+
+	error = qce_check_status(qce, &status);
+	if (error < 0)
+		dev_dbg(qce->dev, "ablkcipher operation error (%x)\n", status);
+
+	qce->async_req_done(tmpl->qce, error);
+}
+
+static int
+qce_ablkcipher_async_req_handle(struct crypto_async_request *async_req)
+{
+	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
+	struct qce_cipher_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct crypto_ablkcipher *ablkcipher = crypto_ablkcipher_reqtfm(req);
+	struct qce_alg_template *tmpl = to_cipher_tmpl(async_req->tfm);
+	struct qce_device *qce = tmpl->qce;
+	enum dma_data_direction dir_src, dir_dst;
+	struct scatterlist *sg;
+	bool diff_dst;
+	gfp_t gfp;
+	int ret;
+
+	rctx->iv = req->info;
+	rctx->ivsize = crypto_ablkcipher_ivsize(ablkcipher);
+	rctx->cryptlen = req->nbytes;
+
+	diff_dst = (req->src != req->dst) ? true : false;
+	dir_src = diff_dst ? DMA_TO_DEVICE : DMA_BIDIRECTIONAL;
+	dir_dst = diff_dst ? DMA_FROM_DEVICE : DMA_BIDIRECTIONAL;
+
+	rctx->src_nents = qce_countsg(req->src, req->nbytes,
+				      &rctx->src_chained);
+	if (diff_dst) {
+		rctx->dst_nents = qce_countsg(req->dst, req->nbytes,
+					      &rctx->dst_chained);
+	} else {
+		rctx->dst_nents = rctx->src_nents;
+		rctx->dst_chained = rctx->src_chained;
+	}
+
+	rctx->dst_nents += 1;
+
+	gfp = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
+						GFP_KERNEL : GFP_ATOMIC;
+
+	ret = sg_alloc_table(&rctx->dst_tbl, rctx->dst_nents, gfp);
+	if (ret)
+		return ret;
+
+	sg_init_one(&rctx->result_sg, qce->dma.result_buf, QCE_RESULT_BUF_SZ);
+
+	sg = qce_sgtable_add(&rctx->dst_tbl, req->dst);
+	if (IS_ERR(sg)) {
+		ret = PTR_ERR(sg);
+		goto error_free;
+	}
+
+	sg = qce_sgtable_add(&rctx->dst_tbl, &rctx->result_sg);
+	if (IS_ERR(sg)) {
+		ret = PTR_ERR(sg);
+		goto error_free;
+	}
+
+	sg_mark_end(sg);
+	rctx->dst_sg = rctx->dst_tbl.sgl;
+
+	ret = qce_mapsg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst,
+			rctx->dst_chained);
+	if (ret < 0)
+		goto error_free;
+
+	if (diff_dst) {
+		ret = qce_mapsg(qce->dev, req->src, rctx->src_nents, dir_src,
+				rctx->src_chained);
+		if (ret < 0)
+			goto error_unmap_dst;
+		rctx->src_sg = req->src;
+	} else {
+		rctx->src_sg = rctx->dst_sg;
+	}
+
+	ret = qce_dma_prep_sgs(&qce->dma, rctx->src_sg, rctx->src_nents,
+			       rctx->dst_sg, rctx->dst_nents,
+			       qce_ablkcipher_done, async_req);
+	if (ret)
+		goto error_unmap_src;
+
+	qce_dma_issue_pending(&qce->dma);
+
+	ret = qce_start(async_req, tmpl->crypto_alg_type, req->nbytes, 0);
+	if (ret)
+		goto error_terminate;
+
+	return 0;
+
+error_terminate:
+	qce_dma_terminate_all(&qce->dma);
+error_unmap_src:
+	if (diff_dst)
+		qce_unmapsg(qce->dev, req->src, rctx->src_nents, dir_src,
+			    rctx->src_chained);
+error_unmap_dst:
+	qce_unmapsg(qce->dev, rctx->dst_sg, rctx->dst_nents, dir_dst,
+		    rctx->dst_chained);
+error_free:
+	sg_free_table(&rctx->dst_tbl);
+	return ret;
+}
+
+static int qce_ablkcipher_setkey(struct crypto_ablkcipher *ablk, const u8 *key,
+				 unsigned int keylen)
+{
+	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(ablk);
+	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	unsigned long flags = to_cipher_tmpl(tfm)->alg_flags;
+	int ret;
+
+	if (!key || !keylen)
+		return -EINVAL;
+
+	if (IS_AES(flags)) {
+		switch (keylen) {
+		case AES_KEYSIZE_128:
+		case AES_KEYSIZE_256:
+			break;
+		default:
+			goto fallback;
+		}
+	} else if (IS_DES(flags)) {
+		u32 tmp[DES_EXPKEY_WORDS];
+
+		ret = des_ekey(tmp, key);
+		if (!ret && crypto_ablkcipher_get_flags(ablk) &
+		    CRYPTO_TFM_REQ_WEAK_KEY)
+			goto weakkey;
+	}
+
+	ctx->enc_keylen = keylen;
+	memcpy(ctx->enc_key, key, keylen);
+	return 0;
+fallback:
+	ret = crypto_ablkcipher_setkey(ctx->fallback, key, keylen);
+	if (!ret)
+		ctx->enc_keylen = keylen;
+	return ret;
+weakkey:
+	crypto_ablkcipher_set_flags(ablk, CRYPTO_TFM_RES_WEAK_KEY);
+	return -EINVAL;
+}
+
+static int qce_ablkcipher_crypt(struct ablkcipher_request *req, int encrypt)
+{
+	struct crypto_tfm *tfm =
+			crypto_ablkcipher_tfm(crypto_ablkcipher_reqtfm(req));
+	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct qce_cipher_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct qce_alg_template *tmpl = to_cipher_tmpl(tfm);
+	int ret;
+
+	rctx->flags = tmpl->alg_flags;
+	rctx->flags |= encrypt ? QCE_ENCRYPT : QCE_DECRYPT;
+
+	if (IS_AES(rctx->flags) && ctx->enc_keylen != AES_KEYSIZE_128 &&
+	    ctx->enc_keylen != AES_KEYSIZE_256) {
+		ablkcipher_request_set_tfm(req, ctx->fallback);
+		ret = encrypt ? crypto_ablkcipher_encrypt(req) :
+				crypto_ablkcipher_decrypt(req);
+		ablkcipher_request_set_tfm(req, __crypto_ablkcipher_cast(tfm));
+		return ret;
+	}
+
+	return tmpl->qce->async_req_enqueue(tmpl->qce, &req->base);
+}
+
+static int qce_ablkcipher_encrypt(struct ablkcipher_request *req)
+{
+	return qce_ablkcipher_crypt(req, 1);
+}
+
+static int qce_ablkcipher_decrypt(struct ablkcipher_request *req)
+{
+	return qce_ablkcipher_crypt(req, 0);
+}
+
+static int qce_ablkcipher_init(struct crypto_tfm *tfm)
+{
+	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	memset(ctx, 0, sizeof(*ctx));
+	tfm->crt_ablkcipher.reqsize = sizeof(struct qce_cipher_reqctx);
+
+	ctx->fallback = crypto_alloc_ablkcipher(crypto_tfm_alg_name(tfm),
+						CRYPTO_ALG_TYPE_ABLKCIPHER,
+						CRYPTO_ALG_ASYNC |
+						CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(ctx->fallback))
+		return PTR_ERR(ctx->fallback);
+
+	return 0;
+}
+
+static void qce_ablkcipher_exit(struct crypto_tfm *tfm)
+{
+	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_ablkcipher(ctx->fallback);
+}
+
+struct qce_ablkcipher_def {
+	unsigned long flags;
+	const char *name;
+	const char *drv_name;
+	unsigned int blocksize;
+	unsigned int ivsize;
+	unsigned int min_keysize;
+	unsigned int max_keysize;
+};
+
+static const struct qce_ablkcipher_def ablkcipher_def[] = {
+	{
+		.flags		= QCE_ALG_AES | QCE_MODE_ECB,
+		.name		= "ecb(aes)",
+		.drv_name	= "ecb-aes-qce",
+		.blocksize	= AES_BLOCK_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+	},
+	{
+		.flags		= QCE_ALG_AES | QCE_MODE_CBC,
+		.name		= "cbc(aes)",
+		.drv_name	= "cbc-aes-qce",
+		.blocksize	= AES_BLOCK_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+	},
+	{
+		.flags		= QCE_ALG_AES | QCE_MODE_CTR,
+		.name		= "ctr(aes)",
+		.drv_name	= "ctr-aes-qce",
+		.blocksize	= AES_BLOCK_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+	},
+	{
+		.flags		= QCE_ALG_AES | QCE_MODE_XTS,
+		.name		= "xts(aes)",
+		.drv_name	= "xts-aes-qce",
+		.blocksize	= AES_BLOCK_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+	},
+	{
+		.flags		= QCE_ALG_DES | QCE_MODE_ECB,
+		.name		= "ecb(des)",
+		.drv_name	= "ecb-des-qce",
+		.blocksize	= DES_BLOCK_SIZE,
+		.ivsize		= 0,
+		.min_keysize	= DES_KEY_SIZE,
+		.max_keysize	= DES_KEY_SIZE,
+	},
+	{
+		.flags		= QCE_ALG_DES | QCE_MODE_CBC,
+		.name		= "cbc(des)",
+		.drv_name	= "cbc-des-qce",
+		.blocksize	= DES_BLOCK_SIZE,
+		.ivsize		= DES_BLOCK_SIZE,
+		.min_keysize	= DES_KEY_SIZE,
+		.max_keysize	= DES_KEY_SIZE,
+	},
+	{
+		.flags		= QCE_ALG_3DES | QCE_MODE_ECB,
+		.name		= "ecb(des3_ede)",
+		.drv_name	= "ecb-3des-qce",
+		.blocksize	= DES3_EDE_BLOCK_SIZE,
+		.ivsize		= 0,
+		.min_keysize	= DES3_EDE_KEY_SIZE,
+		.max_keysize	= DES3_EDE_KEY_SIZE,
+	},
+	{
+		.flags		= QCE_ALG_3DES | QCE_MODE_CBC,
+		.name		= "cbc(des3_ede)",
+		.drv_name	= "cbc-3des-qce",
+		.blocksize	= DES3_EDE_BLOCK_SIZE,
+		.ivsize		= DES3_EDE_BLOCK_SIZE,
+		.min_keysize	= DES3_EDE_KEY_SIZE,
+		.max_keysize	= DES3_EDE_KEY_SIZE,
+	},
+};
+
+static int qce_ablkcipher_register_one(const struct qce_ablkcipher_def *def,
+				       struct qce_device *qce)
+{
+	struct qce_alg_template *tmpl;
+	struct crypto_alg *alg;
+	int ret;
+
+	tmpl = kzalloc(sizeof(*tmpl), GFP_KERNEL);
+	if (!tmpl)
+		return -ENOMEM;
+
+	alg = &tmpl->alg.crypto;
+
+	snprintf(alg->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
+	snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+		 def->drv_name);
+
+	alg->cra_blocksize = def->blocksize;
+	alg->cra_ablkcipher.ivsize = def->ivsize;
+	alg->cra_ablkcipher.min_keysize = def->min_keysize;
+	alg->cra_ablkcipher.max_keysize = def->max_keysize;
+	alg->cra_ablkcipher.setkey = qce_ablkcipher_setkey;
+	alg->cra_ablkcipher.encrypt = qce_ablkcipher_encrypt;
+	alg->cra_ablkcipher.decrypt = qce_ablkcipher_decrypt;
+
+	alg->cra_priority = 300;
+	alg->cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC |
+			 CRYPTO_ALG_NEED_FALLBACK;
+	alg->cra_ctxsize = sizeof(struct qce_cipher_ctx);
+	alg->cra_alignmask = 0;
+	alg->cra_type = &crypto_ablkcipher_type;
+	alg->cra_module = THIS_MODULE;
+	alg->cra_init = qce_ablkcipher_init;
+	alg->cra_exit = qce_ablkcipher_exit;
+	INIT_LIST_HEAD(&alg->cra_list);
+
+	INIT_LIST_HEAD(&tmpl->entry);
+	tmpl->crypto_alg_type = CRYPTO_ALG_TYPE_ABLKCIPHER;
+	tmpl->alg_flags = def->flags;
+	tmpl->qce = qce;
+
+	ret = crypto_register_alg(alg);
+	if (ret) {
+		kfree(tmpl);
+		dev_err(qce->dev, "%s registration failed\n", alg->cra_name);
+		return ret;
+	}
+
+	list_add_tail(&tmpl->entry, &ablkcipher_algs);
+	dev_dbg(qce->dev, "%s is registered\n", alg->cra_name);
+	return 0;
+}
+
+static void qce_ablkcipher_unregister(struct qce_device *qce)
+{
+	struct qce_alg_template *tmpl, *n;
+
+	list_for_each_entry_safe(tmpl, n, &ablkcipher_algs, entry) {
+		crypto_unregister_alg(&tmpl->alg.crypto);
+		list_del(&tmpl->entry);
+		kfree(tmpl);
+	}
+}
+
+static int qce_ablkcipher_register(struct qce_device *qce)
+{
+	int ret, i;
+
+	for (i = 0; i < ARRAY_SIZE(ablkcipher_def); i++) {
+		ret = qce_ablkcipher_register_one(&ablkcipher_def[i], qce);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	qce_ablkcipher_unregister(qce);
+	return ret;
+}
+
+const struct qce_algo_ops ablkcipher_ops = {
+	.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
+	.register_algs = qce_ablkcipher_register,
+	.unregister_algs = qce_ablkcipher_unregister,
+	.async_req_handle = qce_ablkcipher_async_req_handle,
+};
diff --git a/drivers/crypto/qce/cipher.h b/drivers/crypto/qce/cipher.h
new file mode 100644
index 00000000000..d5757cfcda2
--- /dev/null
+++ b/drivers/crypto/qce/cipher.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CIPHER_H_
+#define _CIPHER_H_
+
+#include "common.h"
+#include "core.h"
+
+#define QCE_MAX_KEY_SIZE	64
+
+struct qce_cipher_ctx {
+	u8 enc_key[QCE_MAX_KEY_SIZE];
+	unsigned int enc_keylen;
+	struct crypto_ablkcipher *fallback;
+};
+
+/**
+ * struct qce_cipher_reqctx - holds private cipher objects per request
+ * @flags: operation flags
+ * @iv: pointer to the IV
+ * @ivsize: IV size
+ * @src_nents: source entries
+ * @dst_nents: destination entries
+ * @src_chained: is source chained
+ * @dst_chained: is destination chained
+ * @result_sg: scatterlist used for result buffer
+ * @dst_tbl: destination sg table
+ * @dst_sg: destination sg pointer table beginning
+ * @src_tbl: source sg table
+ * @src_sg: source sg pointer table beginning;
+ * @cryptlen: crypto length
+ */
+struct qce_cipher_reqctx {
+	unsigned long flags;
+	u8 *iv;
+	unsigned int ivsize;
+	int src_nents;
+	int dst_nents;
+	bool src_chained;
+	bool dst_chained;
+	struct scatterlist result_sg;
+	struct sg_table dst_tbl;
+	struct scatterlist *dst_sg;
+	struct sg_table src_tbl;
+	struct scatterlist *src_sg;
+	unsigned int cryptlen;
+};
+
+static inline struct qce_alg_template *to_cipher_tmpl(struct crypto_tfm *tfm)
+{
+	struct crypto_alg *alg = tfm->__crt_alg;
+	return container_of(alg, struct qce_alg_template, alg.crypto);
+}
+
+extern const struct qce_algo_ops ablkcipher_ops;
+
+#endif /* _CIPHER_H_ */
diff --git a/drivers/crypto/qce/common.c b/drivers/crypto/qce/common.c
new file mode 100644
index 00000000000..1fb5fde7fc0
--- /dev/null
+++ b/drivers/crypto/qce/common.c
@@ -0,0 +1,438 @@
+/*
+ * Copyright (c) 2012-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/types.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/sha.h>
+
+#include "cipher.h"
+#include "common.h"
+#include "core.h"
+#include "regs-v5.h"
+#include "sha.h"
+
+#define QCE_SECTOR_SIZE		512
+
+static inline u32 qce_read(struct qce_device *qce, u32 offset)
+{
+	return readl(qce->base + offset);
+}
+
+static inline void qce_write(struct qce_device *qce, u32 offset, u32 val)
+{
+	writel(val, qce->base + offset);
+}
+
+static inline void qce_write_array(struct qce_device *qce, u32 offset,
+				   const u32 *val, unsigned int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		qce_write(qce, offset + i * sizeof(u32), val[i]);
+}
+
+static inline void
+qce_clear_array(struct qce_device *qce, u32 offset, unsigned int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		qce_write(qce, offset + i * sizeof(u32), 0);
+}
+
+static u32 qce_encr_cfg(unsigned long flags, u32 aes_key_size)
+{
+	u32 cfg = 0;
+
+	if (IS_AES(flags)) {
+		if (aes_key_size == AES_KEYSIZE_128)
+			cfg |= ENCR_KEY_SZ_AES128 << ENCR_KEY_SZ_SHIFT;
+		else if (aes_key_size == AES_KEYSIZE_256)
+			cfg |= ENCR_KEY_SZ_AES256 << ENCR_KEY_SZ_SHIFT;
+	}
+
+	if (IS_AES(flags))
+		cfg |= ENCR_ALG_AES << ENCR_ALG_SHIFT;
+	else if (IS_DES(flags) || IS_3DES(flags))
+		cfg |= ENCR_ALG_DES << ENCR_ALG_SHIFT;
+
+	if (IS_DES(flags))
+		cfg |= ENCR_KEY_SZ_DES << ENCR_KEY_SZ_SHIFT;
+
+	if (IS_3DES(flags))
+		cfg |= ENCR_KEY_SZ_3DES << ENCR_KEY_SZ_SHIFT;
+
+	switch (flags & QCE_MODE_MASK) {
+	case QCE_MODE_ECB:
+		cfg |= ENCR_MODE_ECB << ENCR_MODE_SHIFT;
+		break;
+	case QCE_MODE_CBC:
+		cfg |= ENCR_MODE_CBC << ENCR_MODE_SHIFT;
+		break;
+	case QCE_MODE_CTR:
+		cfg |= ENCR_MODE_CTR << ENCR_MODE_SHIFT;
+		break;
+	case QCE_MODE_XTS:
+		cfg |= ENCR_MODE_XTS << ENCR_MODE_SHIFT;
+		break;
+	case QCE_MODE_CCM:
+		cfg |= ENCR_MODE_CCM << ENCR_MODE_SHIFT;
+		cfg |= LAST_CCM_XFR << LAST_CCM_SHIFT;
+		break;
+	default:
+		return ~0;
+	}
+
+	return cfg;
+}
+
+static u32 qce_auth_cfg(unsigned long flags, u32 key_size)
+{
+	u32 cfg = 0;
+
+	if (IS_AES(flags) && (IS_CCM(flags) || IS_CMAC(flags)))
+		cfg |= AUTH_ALG_AES << AUTH_ALG_SHIFT;
+	else
+		cfg |= AUTH_ALG_SHA << AUTH_ALG_SHIFT;
+
+	if (IS_CCM(flags) || IS_CMAC(flags)) {
+		if (key_size == AES_KEYSIZE_128)
+			cfg |= AUTH_KEY_SZ_AES128 << AUTH_KEY_SIZE_SHIFT;
+		else if (key_size == AES_KEYSIZE_256)
+			cfg |= AUTH_KEY_SZ_AES256 << AUTH_KEY_SIZE_SHIFT;
+	}
+
+	if (IS_SHA1(flags) || IS_SHA1_HMAC(flags))
+		cfg |= AUTH_SIZE_SHA1 << AUTH_SIZE_SHIFT;
+	else if (IS_SHA256(flags) || IS_SHA256_HMAC(flags))
+		cfg |= AUTH_SIZE_SHA256 << AUTH_SIZE_SHIFT;
+	else if (IS_CMAC(flags))
+		cfg |= AUTH_SIZE_ENUM_16_BYTES << AUTH_SIZE_SHIFT;
+
+	if (IS_SHA1(flags) || IS_SHA256(flags))
+		cfg |= AUTH_MODE_HASH << AUTH_MODE_SHIFT;
+	else if (IS_SHA1_HMAC(flags) || IS_SHA256_HMAC(flags) ||
+		 IS_CBC(flags) || IS_CTR(flags))
+		cfg |= AUTH_MODE_HMAC << AUTH_MODE_SHIFT;
+	else if (IS_AES(flags) && IS_CCM(flags))
+		cfg |= AUTH_MODE_CCM << AUTH_MODE_SHIFT;
+	else if (IS_AES(flags) && IS_CMAC(flags))
+		cfg |= AUTH_MODE_CMAC << AUTH_MODE_SHIFT;
+
+	if (IS_SHA(flags) || IS_SHA_HMAC(flags))
+		cfg |= AUTH_POS_BEFORE << AUTH_POS_SHIFT;
+
+	if (IS_CCM(flags))
+		cfg |= QCE_MAX_NONCE_WORDS << AUTH_NONCE_NUM_WORDS_SHIFT;
+
+	if (IS_CBC(flags) || IS_CTR(flags) || IS_CCM(flags) ||
+	    IS_CMAC(flags))
+		cfg |= BIT(AUTH_LAST_SHIFT) | BIT(AUTH_FIRST_SHIFT);
+
+	return cfg;
+}
+
+static u32 qce_config_reg(struct qce_device *qce, int little)
+{
+	u32 beats = (qce->burst_size >> 3) - 1;
+	u32 pipe_pair = qce->pipe_pair_id;
+	u32 config;
+
+	config = (beats << REQ_SIZE_SHIFT) & REQ_SIZE_MASK;
+	config |= BIT(MASK_DOUT_INTR_SHIFT) | BIT(MASK_DIN_INTR_SHIFT) |
+		  BIT(MASK_OP_DONE_INTR_SHIFT) | BIT(MASK_ERR_INTR_SHIFT);
+	config |= (pipe_pair << PIPE_SET_SELECT_SHIFT) & PIPE_SET_SELECT_MASK;
+	config &= ~HIGH_SPD_EN_N_SHIFT;
+
+	if (little)
+		config |= BIT(LITTLE_ENDIAN_MODE_SHIFT);
+
+	return config;
+}
+
+void qce_cpu_to_be32p_array(__be32 *dst, const u8 *src, unsigned int len)
+{
+	__be32 *d = dst;
+	const u8 *s = src;
+	unsigned int n;
+
+	n = len / sizeof(u32);
+	for (; n > 0; n--) {
+		*d = cpu_to_be32p((const __u32 *) s);
+		s += sizeof(__u32);
+		d++;
+	}
+}
+
+static void qce_xts_swapiv(__be32 *dst, const u8 *src, unsigned int ivsize)
+{
+	u8 swap[QCE_AES_IV_LENGTH];
+	u32 i, j;
+
+	if (ivsize > QCE_AES_IV_LENGTH)
+		return;
+
+	memset(swap, 0, QCE_AES_IV_LENGTH);
+
+	for (i = (QCE_AES_IV_LENGTH - ivsize), j = ivsize - 1;
+	     i < QCE_AES_IV_LENGTH; i++, j--)
+		swap[i] = src[j];
+
+	qce_cpu_to_be32p_array(dst, swap, QCE_AES_IV_LENGTH);
+}
+
+static void qce_xtskey(struct qce_device *qce, const u8 *enckey,
+		       unsigned int enckeylen, unsigned int cryptlen)
+{
+	u32 xtskey[QCE_MAX_CIPHER_KEY_SIZE / sizeof(u32)] = {0};
+	unsigned int xtsklen = enckeylen / (2 * sizeof(u32));
+	unsigned int xtsdusize;
+
+	qce_cpu_to_be32p_array((__be32 *)xtskey, enckey + enckeylen / 2,
+			       enckeylen / 2);
+	qce_write_array(qce, REG_ENCR_XTS_KEY0, xtskey, xtsklen);
+
+	/* xts du size 512B */
+	xtsdusize = min_t(u32, QCE_SECTOR_SIZE, cryptlen);
+	qce_write(qce, REG_ENCR_XTS_DU_SIZE, xtsdusize);
+}
+
+static void qce_setup_config(struct qce_device *qce)
+{
+	u32 config;
+
+	/* get big endianness */
+	config = qce_config_reg(qce, 0);
+
+	/* clear status */
+	qce_write(qce, REG_STATUS, 0);
+	qce_write(qce, REG_CONFIG, config);
+}
+
+static inline void qce_crypto_go(struct qce_device *qce)
+{
+	qce_write(qce, REG_GOPROC, BIT(GO_SHIFT) | BIT(RESULTS_DUMP_SHIFT));
+}
+
+static int qce_setup_regs_ahash(struct crypto_async_request *async_req,
+				u32 totallen, u32 offset)
+{
+	struct ahash_request *req = ahash_request_cast(async_req);
+	struct crypto_ahash *ahash = __crypto_ahash_cast(async_req->tfm);
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct qce_alg_template *tmpl = to_ahash_tmpl(async_req->tfm);
+	struct qce_device *qce = tmpl->qce;
+	unsigned int digestsize = crypto_ahash_digestsize(ahash);
+	unsigned int blocksize = crypto_tfm_alg_blocksize(async_req->tfm);
+	__be32 auth[SHA256_DIGEST_SIZE / sizeof(__be32)] = {0};
+	__be32 mackey[QCE_SHA_HMAC_KEY_SIZE / sizeof(__be32)] = {0};
+	u32 auth_cfg = 0, config;
+	unsigned int iv_words;
+
+	/* if not the last, the size has to be on the block boundary */
+	if (!rctx->last_blk && req->nbytes % blocksize)
+		return -EINVAL;
+
+	qce_setup_config(qce);
+
+	if (IS_CMAC(rctx->flags)) {
+		qce_write(qce, REG_AUTH_SEG_CFG, 0);
+		qce_write(qce, REG_ENCR_SEG_CFG, 0);
+		qce_write(qce, REG_ENCR_SEG_SIZE, 0);
+		qce_clear_array(qce, REG_AUTH_IV0, 16);
+		qce_clear_array(qce, REG_AUTH_KEY0, 16);
+		qce_clear_array(qce, REG_AUTH_BYTECNT0, 4);
+
+		auth_cfg = qce_auth_cfg(rctx->flags, rctx->authklen);
+	}
+
+	if (IS_SHA_HMAC(rctx->flags) || IS_CMAC(rctx->flags)) {
+		u32 authkey_words = rctx->authklen / sizeof(u32);
+
+		qce_cpu_to_be32p_array(mackey, rctx->authkey, rctx->authklen);
+		qce_write_array(qce, REG_AUTH_KEY0, (u32 *)mackey,
+				authkey_words);
+	}
+
+	if (IS_CMAC(rctx->flags))
+		goto go_proc;
+
+	if (rctx->first_blk)
+		memcpy(auth, rctx->digest, digestsize);
+	else
+		qce_cpu_to_be32p_array(auth, rctx->digest, digestsize);
+
+	iv_words = (IS_SHA1(rctx->flags) || IS_SHA1_HMAC(rctx->flags)) ? 5 : 8;
+	qce_write_array(qce, REG_AUTH_IV0, (u32 *)auth, iv_words);
+
+	if (rctx->first_blk)
+		qce_clear_array(qce, REG_AUTH_BYTECNT0, 4);
+	else
+		qce_write_array(qce, REG_AUTH_BYTECNT0,
+				(u32 *)rctx->byte_count, 2);
+
+	auth_cfg = qce_auth_cfg(rctx->flags, 0);
+
+	if (rctx->last_blk)
+		auth_cfg |= BIT(AUTH_LAST_SHIFT);
+	else
+		auth_cfg &= ~BIT(AUTH_LAST_SHIFT);
+
+	if (rctx->first_blk)
+		auth_cfg |= BIT(AUTH_FIRST_SHIFT);
+	else
+		auth_cfg &= ~BIT(AUTH_FIRST_SHIFT);
+
+go_proc:
+	qce_write(qce, REG_AUTH_SEG_CFG, auth_cfg);
+	qce_write(qce, REG_AUTH_SEG_SIZE, req->nbytes);
+	qce_write(qce, REG_AUTH_SEG_START, 0);
+	qce_write(qce, REG_ENCR_SEG_CFG, 0);
+	qce_write(qce, REG_SEG_SIZE, req->nbytes);
+
+	/* get little endianness */
+	config = qce_config_reg(qce, 1);
+	qce_write(qce, REG_CONFIG, config);
+
+	qce_crypto_go(qce);
+
+	return 0;
+}
+
+static int qce_setup_regs_ablkcipher(struct crypto_async_request *async_req,
+				     u32 totallen, u32 offset)
+{
+	struct ablkcipher_request *req = ablkcipher_request_cast(async_req);
+	struct qce_cipher_reqctx *rctx = ablkcipher_request_ctx(req);
+	struct qce_cipher_ctx *ctx = crypto_tfm_ctx(async_req->tfm);
+	struct qce_alg_template *tmpl = to_cipher_tmpl(async_req->tfm);
+	struct qce_device *qce = tmpl->qce;
+	__be32 enckey[QCE_MAX_CIPHER_KEY_SIZE / sizeof(__be32)] = {0};
+	__be32 enciv[QCE_MAX_IV_SIZE / sizeof(__be32)] = {0};
+	unsigned int enckey_words, enciv_words;
+	unsigned int keylen;
+	u32 encr_cfg = 0, auth_cfg = 0, config;
+	unsigned int ivsize = rctx->ivsize;
+	unsigned long flags = rctx->flags;
+
+	qce_setup_config(qce);
+
+	if (IS_XTS(flags))
+		keylen = ctx->enc_keylen / 2;
+	else
+		keylen = ctx->enc_keylen;
+
+	qce_cpu_to_be32p_array(enckey, ctx->enc_key, keylen);
+	enckey_words = keylen / sizeof(u32);
+
+	qce_write(qce, REG_AUTH_SEG_CFG, auth_cfg);
+
+	encr_cfg = qce_encr_cfg(flags, keylen);
+
+	if (IS_DES(flags)) {
+		enciv_words = 2;
+		enckey_words = 2;
+	} else if (IS_3DES(flags)) {
+		enciv_words = 2;
+		enckey_words = 6;
+	} else if (IS_AES(flags)) {
+		if (IS_XTS(flags))
+			qce_xtskey(qce, ctx->enc_key, ctx->enc_keylen,
+				   rctx->cryptlen);
+		enciv_words = 4;
+	} else {
+		return -EINVAL;
+	}
+
+	qce_write_array(qce, REG_ENCR_KEY0, (u32 *)enckey, enckey_words);
+
+	if (!IS_ECB(flags)) {
+		if (IS_XTS(flags))
+			qce_xts_swapiv(enciv, rctx->iv, ivsize);
+		else
+			qce_cpu_to_be32p_array(enciv, rctx->iv, ivsize);
+
+		qce_write_array(qce, REG_CNTR0_IV0, (u32 *)enciv, enciv_words);
+	}
+
+	if (IS_ENCRYPT(flags))
+		encr_cfg |= BIT(ENCODE_SHIFT);
+
+	qce_write(qce, REG_ENCR_SEG_CFG, encr_cfg);
+	qce_write(qce, REG_ENCR_SEG_SIZE, rctx->cryptlen);
+	qce_write(qce, REG_ENCR_SEG_START, offset & 0xffff);
+
+	if (IS_CTR(flags)) {
+		qce_write(qce, REG_CNTR_MASK, ~0);
+		qce_write(qce, REG_CNTR_MASK0, ~0);
+		qce_write(qce, REG_CNTR_MASK1, ~0);
+		qce_write(qce, REG_CNTR_MASK2, ~0);
+	}
+
+	qce_write(qce, REG_SEG_SIZE, totallen);
+
+	/* get little endianness */
+	config = qce_config_reg(qce, 1);
+	qce_write(qce, REG_CONFIG, config);
+
+	qce_crypto_go(qce);
+
+	return 0;
+}
+
+int qce_start(struct crypto_async_request *async_req, u32 type, u32 totallen,
+	      u32 offset)
+{
+	switch (type) {
+	case CRYPTO_ALG_TYPE_ABLKCIPHER:
+		return qce_setup_regs_ablkcipher(async_req, totallen, offset);
+	case CRYPTO_ALG_TYPE_AHASH:
+		return qce_setup_regs_ahash(async_req, totallen, offset);
+	default:
+		return -EINVAL;
+	}
+}
+
+#define STATUS_ERRORS	\
+		(BIT(SW_ERR_SHIFT) | BIT(AXI_ERR_SHIFT) | BIT(HSD_ERR_SHIFT))
+
+int qce_check_status(struct qce_device *qce, u32 *status)
+{
+	int ret = 0;
+
+	*status = qce_read(qce, REG_STATUS);
+
+	/*
+	 * Don't use result dump status. The operation may not be complete.
+	 * Instead, use the status we just read from device. In case, we need to
+	 * use result_status from result dump the result_status needs to be byte
+	 * swapped, since we set the device to little endian.
+	 */
+	if (*status & STATUS_ERRORS || !(*status & BIT(OPERATION_DONE_SHIFT)))
+		ret = -ENXIO;
+
+	return ret;
+}
+
+void qce_get_version(struct qce_device *qce, u32 *major, u32 *minor, u32 *step)
+{
+	u32 val;
+
+	val = qce_read(qce, REG_VERSION);
+	*major = (val & CORE_MAJOR_REV_MASK) >> CORE_MAJOR_REV_SHIFT;
+	*minor = (val & CORE_MINOR_REV_MASK) >> CORE_MINOR_REV_SHIFT;
+	*step = (val & CORE_STEP_REV_MASK) >> CORE_STEP_REV_SHIFT;
+}
diff --git a/drivers/crypto/qce/common.h b/drivers/crypto/qce/common.h
new file mode 100644
index 00000000000..a4addd4f7d6
--- /dev/null
+++ b/drivers/crypto/qce/common.h
@@ -0,0 +1,102 @@
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _COMMON_H_
+#define _COMMON_H_
+
+#include <linux/crypto.h>
+#include <linux/types.h>
+#include <crypto/aes.h>
+#include <crypto/hash.h>
+
+/* key size in bytes */
+#define QCE_SHA_HMAC_KEY_SIZE		64
+#define QCE_MAX_CIPHER_KEY_SIZE		AES_KEYSIZE_256
+
+/* IV length in bytes */
+#define QCE_AES_IV_LENGTH		AES_BLOCK_SIZE
+/* max of AES_BLOCK_SIZE, DES3_EDE_BLOCK_SIZE */
+#define QCE_MAX_IV_SIZE			AES_BLOCK_SIZE
+
+/* maximum nonce bytes  */
+#define QCE_MAX_NONCE			16
+#define QCE_MAX_NONCE_WORDS		(QCE_MAX_NONCE / sizeof(u32))
+
+/* burst size alignment requirement */
+#define QCE_MAX_ALIGN_SIZE		64
+
+/* cipher algorithms */
+#define QCE_ALG_DES			BIT(0)
+#define QCE_ALG_3DES			BIT(1)
+#define QCE_ALG_AES			BIT(2)
+
+/* hash and hmac algorithms */
+#define QCE_HASH_SHA1			BIT(3)
+#define QCE_HASH_SHA256			BIT(4)
+#define QCE_HASH_SHA1_HMAC		BIT(5)
+#define QCE_HASH_SHA256_HMAC		BIT(6)
+#define QCE_HASH_AES_CMAC		BIT(7)
+
+/* cipher modes */
+#define QCE_MODE_CBC			BIT(8)
+#define QCE_MODE_ECB			BIT(9)
+#define QCE_MODE_CTR			BIT(10)
+#define QCE_MODE_XTS			BIT(11)
+#define QCE_MODE_CCM			BIT(12)
+#define QCE_MODE_MASK			GENMASK(12, 8)
+
+/* cipher encryption/decryption operations */
+#define QCE_ENCRYPT			BIT(13)
+#define QCE_DECRYPT			BIT(14)
+
+#define IS_DES(flags)			(flags & QCE_ALG_DES)
+#define IS_3DES(flags)			(flags & QCE_ALG_3DES)
+#define IS_AES(flags)			(flags & QCE_ALG_AES)
+
+#define IS_SHA1(flags)			(flags & QCE_HASH_SHA1)
+#define IS_SHA256(flags)		(flags & QCE_HASH_SHA256)
+#define IS_SHA1_HMAC(flags)		(flags & QCE_HASH_SHA1_HMAC)
+#define IS_SHA256_HMAC(flags)		(flags & QCE_HASH_SHA256_HMAC)
+#define IS_CMAC(flags)			(flags & QCE_HASH_AES_CMAC)
+#define IS_SHA(flags)			(IS_SHA1(flags) || IS_SHA256(flags))
+#define IS_SHA_HMAC(flags)		\
+		(IS_SHA1_HMAC(flags) || IS_SHA256_HMAC(flags))
+
+#define IS_CBC(mode)			(mode & QCE_MODE_CBC)
+#define IS_ECB(mode)			(mode & QCE_MODE_ECB)
+#define IS_CTR(mode)			(mode & QCE_MODE_CTR)
+#define IS_XTS(mode)			(mode & QCE_MODE_XTS)
+#define IS_CCM(mode)			(mode & QCE_MODE_CCM)
+
+#define IS_ENCRYPT(dir)			(dir & QCE_ENCRYPT)
+#define IS_DECRYPT(dir)			(dir & QCE_DECRYPT)
+
+struct qce_alg_template {
+	struct list_head entry;
+	u32 crypto_alg_type;
+	unsigned long alg_flags;
+	const u32 *std_iv;
+	union {
+		struct crypto_alg crypto;
+		struct ahash_alg ahash;
+	} alg;
+	struct qce_device *qce;
+};
+
+void qce_cpu_to_be32p_array(__be32 *dst, const u8 *src, unsigned int len);
+int qce_check_status(struct qce_device *qce, u32 *status);
+void qce_get_version(struct qce_device *qce, u32 *major, u32 *minor, u32 *step);
+int qce_start(struct crypto_async_request *async_req, u32 type, u32 totallen,
+	      u32 offset);
+
+#endif /* _COMMON_H_ */
diff --git a/drivers/crypto/qce/core.c b/drivers/crypto/qce/core.c
new file mode 100644
index 00000000000..33ae3545dc4
--- /dev/null
+++ b/drivers/crypto/qce/core.c
@@ -0,0 +1,286 @@
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+
+#include "core.h"
+#include "cipher.h"
+#include "sha.h"
+
+#define QCE_MAJOR_VERSION5	0x05
+#define QCE_QUEUE_LENGTH	1
+
+static const struct qce_algo_ops *qce_ops[] = {
+	&ablkcipher_ops,
+	&ahash_ops,
+};
+
+static void qce_unregister_algs(struct qce_device *qce)
+{
+	const struct qce_algo_ops *ops;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(qce_ops); i++) {
+		ops = qce_ops[i];
+		ops->unregister_algs(qce);
+	}
+}
+
+static int qce_register_algs(struct qce_device *qce)
+{
+	const struct qce_algo_ops *ops;
+	int i, ret = -ENODEV;
+
+	for (i = 0; i < ARRAY_SIZE(qce_ops); i++) {
+		ops = qce_ops[i];
+		ret = ops->register_algs(qce);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static int qce_handle_request(struct crypto_async_request *async_req)
+{
+	int ret = -EINVAL, i;
+	const struct qce_algo_ops *ops;
+	u32 type = crypto_tfm_alg_type(async_req->tfm);
+
+	for (i = 0; i < ARRAY_SIZE(qce_ops); i++) {
+		ops = qce_ops[i];
+		if (type != ops->type)
+			continue;
+		ret = ops->async_req_handle(async_req);
+		break;
+	}
+
+	return ret;
+}
+
+static int qce_handle_queue(struct qce_device *qce,
+			    struct crypto_async_request *req)
+{
+	struct crypto_async_request *async_req, *backlog;
+	unsigned long flags;
+	int ret = 0, err;
+
+	spin_lock_irqsave(&qce->lock, flags);
+
+	if (req)
+		ret = crypto_enqueue_request(&qce->queue, req);
+
+	/* busy, do not dequeue request */
+	if (qce->req) {
+		spin_unlock_irqrestore(&qce->lock, flags);
+		return ret;
+	}
+
+	backlog = crypto_get_backlog(&qce->queue);
+	async_req = crypto_dequeue_request(&qce->queue);
+	if (async_req)
+		qce->req = async_req;
+
+	spin_unlock_irqrestore(&qce->lock, flags);
+
+	if (!async_req)
+		return ret;
+
+	if (backlog) {
+		spin_lock_bh(&qce->lock);
+		backlog->complete(backlog, -EINPROGRESS);
+		spin_unlock_bh(&qce->lock);
+	}
+
+	err = qce_handle_request(async_req);
+	if (err) {
+		qce->result = err;
+		tasklet_schedule(&qce->done_tasklet);
+	}
+
+	return ret;
+}
+
+static void qce_tasklet_req_done(unsigned long data)
+{
+	struct qce_device *qce = (struct qce_device *)data;
+	struct crypto_async_request *req;
+	unsigned long flags;
+
+	spin_lock_irqsave(&qce->lock, flags);
+	req = qce->req;
+	qce->req = NULL;
+	spin_unlock_irqrestore(&qce->lock, flags);
+
+	if (req)
+		req->complete(req, qce->result);
+
+	qce_handle_queue(qce, NULL);
+}
+
+static int qce_async_request_enqueue(struct qce_device *qce,
+				     struct crypto_async_request *req)
+{
+	return qce_handle_queue(qce, req);
+}
+
+static void qce_async_request_done(struct qce_device *qce, int ret)
+{
+	qce->result = ret;
+	tasklet_schedule(&qce->done_tasklet);
+}
+
+static int qce_check_version(struct qce_device *qce)
+{
+	u32 major, minor, step;
+
+	qce_get_version(qce, &major, &minor, &step);
+
+	/*
+	 * the driver does not support v5 with minor 0 because it has special
+	 * alignment requirements.
+	 */
+	if (major != QCE_MAJOR_VERSION5 || minor == 0)
+		return -ENODEV;
+
+	qce->burst_size = QCE_BAM_BURST_SIZE;
+	qce->pipe_pair_id = 1;
+
+	dev_dbg(qce->dev, "Crypto device found, version %d.%d.%d\n",
+		major, minor, step);
+
+	return 0;
+}
+
+static int qce_crypto_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct qce_device *qce;
+	struct resource *res;
+	int ret;
+
+	qce = devm_kzalloc(dev, sizeof(*qce), GFP_KERNEL);
+	if (!qce)
+		return -ENOMEM;
+
+	qce->dev = dev;
+	platform_set_drvdata(pdev, qce);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	qce->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(qce->base))
+		return PTR_ERR(qce->base);
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (ret < 0)
+		return ret;
+
+	qce->core = devm_clk_get(qce->dev, "core");
+	if (IS_ERR(qce->core))
+		return PTR_ERR(qce->core);
+
+	qce->iface = devm_clk_get(qce->dev, "iface");
+	if (IS_ERR(qce->iface))
+		return PTR_ERR(qce->iface);
+
+	qce->bus = devm_clk_get(qce->dev, "bus");
+	if (IS_ERR(qce->bus))
+		return PTR_ERR(qce->bus);
+
+	ret = clk_prepare_enable(qce->core);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(qce->iface);
+	if (ret)
+		goto err_clks_core;
+
+	ret = clk_prepare_enable(qce->bus);
+	if (ret)
+		goto err_clks_iface;
+
+	ret = qce_dma_request(qce->dev, &qce->dma);
+	if (ret)
+		goto err_clks;
+
+	ret = qce_check_version(qce);
+	if (ret)
+		goto err_clks;
+
+	spin_lock_init(&qce->lock);
+	tasklet_init(&qce->done_tasklet, qce_tasklet_req_done,
+		     (unsigned long)qce);
+	crypto_init_queue(&qce->queue, QCE_QUEUE_LENGTH);
+
+	qce->async_req_enqueue = qce_async_request_enqueue;
+	qce->async_req_done = qce_async_request_done;
+
+	ret = qce_register_algs(qce);
+	if (ret)
+		goto err_dma;
+
+	return 0;
+
+err_dma:
+	qce_dma_release(&qce->dma);
+err_clks:
+	clk_disable_unprepare(qce->bus);
+err_clks_iface:
+	clk_disable_unprepare(qce->iface);
+err_clks_core:
+	clk_disable_unprepare(qce->core);
+	return ret;
+}
+
+static int qce_crypto_remove(struct platform_device *pdev)
+{
+	struct qce_device *qce = platform_get_drvdata(pdev);
+
+	tasklet_kill(&qce->done_tasklet);
+	qce_unregister_algs(qce);
+	qce_dma_release(&qce->dma);
+	clk_disable_unprepare(qce->bus);
+	clk_disable_unprepare(qce->iface);
+	clk_disable_unprepare(qce->core);
+	return 0;
+}
+
+static const struct of_device_id qce_crypto_of_match[] = {
+	{ .compatible = "qcom,crypto-v5.1", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, qce_crypto_of_match);
+
+static struct platform_driver qce_crypto_driver = {
+	.probe = qce_crypto_probe,
+	.remove = qce_crypto_remove,
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = KBUILD_MODNAME,
+		.of_match_table = qce_crypto_of_match,
+	},
+};
+module_platform_driver(qce_crypto_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Qualcomm crypto engine driver");
+MODULE_ALIAS("platform:" KBUILD_MODNAME);
+MODULE_AUTHOR("The Linux Foundation");
diff --git a/drivers/crypto/qce/core.h b/drivers/crypto/qce/core.h
new file mode 100644
index 00000000000..549965d4d91
--- /dev/null
+++ b/drivers/crypto/qce/core.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CORE_H_
+#define _CORE_H_
+
+#include "dma.h"
+
+/**
+ * struct qce_device - crypto engine device structure
+ * @queue: crypto request queue
+ * @lock: the lock protects queue and req
+ * @done_tasklet: done tasklet object
+ * @req: current active request
+ * @result: result of current transform
+ * @base: virtual IO base
+ * @dev: pointer to device structure
+ * @core: core device clock
+ * @iface: interface clock
+ * @bus: bus clock
+ * @dma: pointer to dma data
+ * @burst_size: the crypto burst size
+ * @pipe_pair_id: which pipe pair id the device using
+ * @async_req_enqueue: invoked by every algorithm to enqueue a request
+ * @async_req_done: invoked by every algorithm to finish its request
+ */
+struct qce_device {
+	struct crypto_queue queue;
+	spinlock_t lock;
+	struct tasklet_struct done_tasklet;
+	struct crypto_async_request *req;
+	int result;
+	void __iomem *base;
+	struct device *dev;
+	struct clk *core, *iface, *bus;
+	struct qce_dma_data dma;
+	int burst_size;
+	unsigned int pipe_pair_id;
+	int (*async_req_enqueue)(struct qce_device *qce,
+				 struct crypto_async_request *req);
+	void (*async_req_done)(struct qce_device *qce, int ret);
+};
+
+/**
+ * struct qce_algo_ops - algorithm operations per crypto type
+ * @type: should be CRYPTO_ALG_TYPE_XXX
+ * @register_algs: invoked by core to register the algorithms
+ * @unregister_algs: invoked by core to unregister the algorithms
+ * @async_req_handle: invoked by core to handle enqueued request
+ */
+struct qce_algo_ops {
+	u32 type;
+	int (*register_algs)(struct qce_device *qce);
+	void (*unregister_algs)(struct qce_device *qce);
+	int (*async_req_handle)(struct crypto_async_request *async_req);
+};
+
+#endif /* _CORE_H_ */
diff --git a/drivers/crypto/qce/dma.c b/drivers/crypto/qce/dma.c
new file mode 100644
index 00000000000..0fb21e13f24
--- /dev/null
+++ b/drivers/crypto/qce/dma.c
@@ -0,0 +1,186 @@
+/*
+ * Copyright (c) 2012-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/dmaengine.h>
+#include <crypto/scatterwalk.h>
+
+#include "dma.h"
+
+int qce_dma_request(struct device *dev, struct qce_dma_data *dma)
+{
+	int ret;
+
+	dma->txchan = dma_request_slave_channel_reason(dev, "tx");
+	if (IS_ERR(dma->txchan))
+		return PTR_ERR(dma->txchan);
+
+	dma->rxchan = dma_request_slave_channel_reason(dev, "rx");
+	if (IS_ERR(dma->rxchan)) {
+		ret = PTR_ERR(dma->rxchan);
+		goto error_rx;
+	}
+
+	dma->result_buf = kmalloc(QCE_RESULT_BUF_SZ + QCE_IGNORE_BUF_SZ,
+				  GFP_KERNEL);
+	if (!dma->result_buf) {
+		ret = -ENOMEM;
+		goto error_nomem;
+	}
+
+	dma->ignore_buf = dma->result_buf + QCE_RESULT_BUF_SZ;
+
+	return 0;
+error_nomem:
+	dma_release_channel(dma->rxchan);
+error_rx:
+	dma_release_channel(dma->txchan);
+	return ret;
+}
+
+void qce_dma_release(struct qce_dma_data *dma)
+{
+	dma_release_channel(dma->txchan);
+	dma_release_channel(dma->rxchan);
+	kfree(dma->result_buf);
+}
+
+int qce_mapsg(struct device *dev, struct scatterlist *sg, int nents,
+	      enum dma_data_direction dir, bool chained)
+{
+	int err;
+
+	if (chained) {
+		while (sg) {
+			err = dma_map_sg(dev, sg, 1, dir);
+			if (!err)
+				return -EFAULT;
+			sg = scatterwalk_sg_next(sg);
+		}
+	} else {
+		err = dma_map_sg(dev, sg, nents, dir);
+		if (!err)
+			return -EFAULT;
+	}
+
+	return nents;
+}
+
+void qce_unmapsg(struct device *dev, struct scatterlist *sg, int nents,
+		 enum dma_data_direction dir, bool chained)
+{
+	if (chained)
+		while (sg) {
+			dma_unmap_sg(dev, sg, 1, dir);
+			sg = scatterwalk_sg_next(sg);
+		}
+	else
+		dma_unmap_sg(dev, sg, nents, dir);
+}
+
+int qce_countsg(struct scatterlist *sglist, int nbytes, bool *chained)
+{
+	struct scatterlist *sg = sglist;
+	int nents = 0;
+
+	if (chained)
+		*chained = false;
+
+	while (nbytes > 0 && sg) {
+		nents++;
+		nbytes -= sg->length;
+		if (!sg_is_last(sg) && (sg + 1)->length == 0 && chained)
+			*chained = true;
+		sg = scatterwalk_sg_next(sg);
+	}
+
+	return nents;
+}
+
+struct scatterlist *
+qce_sgtable_add(struct sg_table *sgt, struct scatterlist *new_sgl)
+{
+	struct scatterlist *sg = sgt->sgl, *sg_last = NULL;
+
+	while (sg) {
+		if (!sg_page(sg))
+			break;
+		sg = sg_next(sg);
+	}
+
+	if (!sg)
+		return ERR_PTR(-EINVAL);
+
+	while (new_sgl && sg) {
+		sg_set_page(sg, sg_page(new_sgl), new_sgl->length,
+			    new_sgl->offset);
+		sg_last = sg;
+		sg = sg_next(sg);
+		new_sgl = sg_next(new_sgl);
+	}
+
+	return sg_last;
+}
+
+static int qce_dma_prep_sg(struct dma_chan *chan, struct scatterlist *sg,
+			   int nents, unsigned long flags,
+			   enum dma_transfer_direction dir,
+			   dma_async_tx_callback cb, void *cb_param)
+{
+	struct dma_async_tx_descriptor *desc;
+	dma_cookie_t cookie;
+
+	if (!sg || !nents)
+		return -EINVAL;
+
+	desc = dmaengine_prep_slave_sg(chan, sg, nents, dir, flags);
+	if (!desc)
+		return -EINVAL;
+
+	desc->callback = cb;
+	desc->callback_param = cb_param;
+	cookie = dmaengine_submit(desc);
+
+	return dma_submit_error(cookie);
+}
+
+int qce_dma_prep_sgs(struct qce_dma_data *dma, struct scatterlist *rx_sg,
+		     int rx_nents, struct scatterlist *tx_sg, int tx_nents,
+		     dma_async_tx_callback cb, void *cb_param)
+{
+	struct dma_chan *rxchan = dma->rxchan;
+	struct dma_chan *txchan = dma->txchan;
+	unsigned long flags = DMA_PREP_INTERRUPT | DMA_CTRL_ACK;
+	int ret;
+
+	ret = qce_dma_prep_sg(rxchan, rx_sg, rx_nents, flags, DMA_MEM_TO_DEV,
+			     NULL, NULL);
+	if (ret)
+		return ret;
+
+	return qce_dma_prep_sg(txchan, tx_sg, tx_nents, flags, DMA_DEV_TO_MEM,
+			       cb, cb_param);
+}
+
+void qce_dma_issue_pending(struct qce_dma_data *dma)
+{
+	dma_async_issue_pending(dma->rxchan);
+	dma_async_issue_pending(dma->txchan);
+}
+
+int qce_dma_terminate_all(struct qce_dma_data *dma)
+{
+	int ret;
+
+	ret = dmaengine_terminate_all(dma->rxchan);
+	return ret ?: dmaengine_terminate_all(dma->txchan);
+}
diff --git a/drivers/crypto/qce/dma.h b/drivers/crypto/qce/dma.h
new file mode 100644
index 00000000000..805e378d59e
--- /dev/null
+++ b/drivers/crypto/qce/dma.h
@@ -0,0 +1,58 @@
+/*
+ * Copyright (c) 2011-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DMA_H_
+#define _DMA_H_
+
+/* maximum data transfer block size between BAM and CE */
+#define QCE_BAM_BURST_SIZE		64
+
+#define QCE_AUTHIV_REGS_CNT		16
+#define QCE_AUTH_BYTECOUNT_REGS_CNT	4
+#define QCE_CNTRIV_REGS_CNT		4
+
+struct qce_result_dump {
+	u32 auth_iv[QCE_AUTHIV_REGS_CNT];
+	u32 auth_byte_count[QCE_AUTH_BYTECOUNT_REGS_CNT];
+	u32 encr_cntr_iv[QCE_CNTRIV_REGS_CNT];
+	u32 status;
+	u32 status2;
+};
+
+#define QCE_IGNORE_BUF_SZ	(2 * QCE_BAM_BURST_SIZE)
+#define QCE_RESULT_BUF_SZ	\
+		ALIGN(sizeof(struct qce_result_dump), QCE_BAM_BURST_SIZE)
+
+struct qce_dma_data {
+	struct dma_chan *txchan;
+	struct dma_chan *rxchan;
+	struct qce_result_dump *result_buf;
+	void *ignore_buf;
+};
+
+int qce_dma_request(struct device *dev, struct qce_dma_data *dma);
+void qce_dma_release(struct qce_dma_data *dma);
+int qce_dma_prep_sgs(struct qce_dma_data *dma, struct scatterlist *sg_in,
+		     int in_ents, struct scatterlist *sg_out, int out_ents,
+		     dma_async_tx_callback cb, void *cb_param);
+void qce_dma_issue_pending(struct qce_dma_data *dma);
+int qce_dma_terminate_all(struct qce_dma_data *dma);
+int qce_countsg(struct scatterlist *sg_list, int nbytes, bool *chained);
+void qce_unmapsg(struct device *dev, struct scatterlist *sg, int nents,
+		 enum dma_data_direction dir, bool chained);
+int qce_mapsg(struct device *dev, struct scatterlist *sg, int nents,
+	      enum dma_data_direction dir, bool chained);
+struct scatterlist *
+qce_sgtable_add(struct sg_table *sgt, struct scatterlist *sg_add);
+
+#endif /* _DMA_H_ */
diff --git a/drivers/crypto/qce/regs-v5.h b/drivers/crypto/qce/regs-v5.h
new file mode 100644
index 00000000000..f0e19e35664
--- /dev/null
+++ b/drivers/crypto/qce/regs-v5.h
@@ -0,0 +1,334 @@
+/*
+ * Copyright (c) 2012-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _REGS_V5_H_
+#define _REGS_V5_H_
+
+#include <linux/bitops.h>
+
+#define REG_VERSION			0x000
+#define REG_STATUS			0x100
+#define REG_STATUS2			0x104
+#define REG_ENGINES_AVAIL		0x108
+#define REG_FIFO_SIZES			0x10c
+#define REG_SEG_SIZE			0x110
+#define REG_GOPROC			0x120
+#define REG_ENCR_SEG_CFG		0x200
+#define REG_ENCR_SEG_SIZE		0x204
+#define REG_ENCR_SEG_START		0x208
+#define REG_CNTR0_IV0			0x20c
+#define REG_CNTR1_IV1			0x210
+#define REG_CNTR2_IV2			0x214
+#define REG_CNTR3_IV3			0x218
+#define REG_CNTR_MASK			0x21C
+#define REG_ENCR_CCM_INT_CNTR0		0x220
+#define REG_ENCR_CCM_INT_CNTR1		0x224
+#define REG_ENCR_CCM_INT_CNTR2		0x228
+#define REG_ENCR_CCM_INT_CNTR3		0x22c
+#define REG_ENCR_XTS_DU_SIZE		0x230
+#define REG_CNTR_MASK2			0x234
+#define REG_CNTR_MASK1			0x238
+#define REG_CNTR_MASK0			0x23c
+#define REG_AUTH_SEG_CFG		0x300
+#define REG_AUTH_SEG_SIZE		0x304
+#define REG_AUTH_SEG_START		0x308
+#define REG_AUTH_IV0			0x310
+#define REG_AUTH_IV1			0x314
+#define REG_AUTH_IV2			0x318
+#define REG_AUTH_IV3			0x31c
+#define REG_AUTH_IV4			0x320
+#define REG_AUTH_IV5			0x324
+#define REG_AUTH_IV6			0x328
+#define REG_AUTH_IV7			0x32c
+#define REG_AUTH_IV8			0x330
+#define REG_AUTH_IV9			0x334
+#define REG_AUTH_IV10			0x338
+#define REG_AUTH_IV11			0x33c
+#define REG_AUTH_IV12			0x340
+#define REG_AUTH_IV13			0x344
+#define REG_AUTH_IV14			0x348
+#define REG_AUTH_IV15			0x34c
+#define REG_AUTH_INFO_NONCE0		0x350
+#define REG_AUTH_INFO_NONCE1		0x354
+#define REG_AUTH_INFO_NONCE2		0x358
+#define REG_AUTH_INFO_NONCE3		0x35c
+#define REG_AUTH_BYTECNT0		0x390
+#define REG_AUTH_BYTECNT1		0x394
+#define REG_AUTH_BYTECNT2		0x398
+#define REG_AUTH_BYTECNT3		0x39c
+#define REG_AUTH_EXP_MAC0		0x3a0
+#define REG_AUTH_EXP_MAC1		0x3a4
+#define REG_AUTH_EXP_MAC2		0x3a8
+#define REG_AUTH_EXP_MAC3		0x3ac
+#define REG_AUTH_EXP_MAC4		0x3b0
+#define REG_AUTH_EXP_MAC5		0x3b4
+#define REG_AUTH_EXP_MAC6		0x3b8
+#define REG_AUTH_EXP_MAC7		0x3bc
+#define REG_CONFIG			0x400
+#define REG_GOPROC_QC_KEY		0x1000
+#define REG_GOPROC_OEM_KEY		0x2000
+#define REG_ENCR_KEY0			0x3000
+#define REG_ENCR_KEY1			0x3004
+#define REG_ENCR_KEY2			0x3008
+#define REG_ENCR_KEY3			0x300c
+#define REG_ENCR_KEY4			0x3010
+#define REG_ENCR_KEY5			0x3014
+#define REG_ENCR_KEY6			0x3018
+#define REG_ENCR_KEY7			0x301c
+#define REG_ENCR_XTS_KEY0		0x3020
+#define REG_ENCR_XTS_KEY1		0x3024
+#define REG_ENCR_XTS_KEY2		0x3028
+#define REG_ENCR_XTS_KEY3		0x302c
+#define REG_ENCR_XTS_KEY4		0x3030
+#define REG_ENCR_XTS_KEY5		0x3034
+#define REG_ENCR_XTS_KEY6		0x3038
+#define REG_ENCR_XTS_KEY7		0x303c
+#define REG_AUTH_KEY0			0x3040
+#define REG_AUTH_KEY1			0x3044
+#define REG_AUTH_KEY2			0x3048
+#define REG_AUTH_KEY3			0x304c
+#define REG_AUTH_KEY4			0x3050
+#define REG_AUTH_KEY5			0x3054
+#define REG_AUTH_KEY6			0x3058
+#define REG_AUTH_KEY7			0x305c
+#define REG_AUTH_KEY8			0x3060
+#define REG_AUTH_KEY9			0x3064
+#define REG_AUTH_KEY10			0x3068
+#define REG_AUTH_KEY11			0x306c
+#define REG_AUTH_KEY12			0x3070
+#define REG_AUTH_KEY13			0x3074
+#define REG_AUTH_KEY14			0x3078
+#define REG_AUTH_KEY15			0x307c
+
+/* Register bits - REG_VERSION */
+#define CORE_STEP_REV_SHIFT		0
+#define CORE_STEP_REV_MASK		GENMASK(15, 0)
+#define CORE_MINOR_REV_SHIFT		16
+#define CORE_MINOR_REV_MASK		GENMASK(23, 16)
+#define CORE_MAJOR_REV_SHIFT		24
+#define CORE_MAJOR_REV_MASK		GENMASK(31, 24)
+
+/* Register bits - REG_STATUS */
+#define MAC_FAILED_SHIFT		31
+#define DOUT_SIZE_AVAIL_SHIFT		26
+#define DOUT_SIZE_AVAIL_MASK		GENMASK(30, 26)
+#define DIN_SIZE_AVAIL_SHIFT		21
+#define DIN_SIZE_AVAIL_MASK		GENMASK(25, 21)
+#define HSD_ERR_SHIFT			20
+#define ACCESS_VIOL_SHIFT		19
+#define PIPE_ACTIVE_ERR_SHIFT		18
+#define CFG_CHNG_ERR_SHIFT		17
+#define DOUT_ERR_SHIFT			16
+#define DIN_ERR_SHIFT			15
+#define AXI_ERR_SHIFT			14
+#define CRYPTO_STATE_SHIFT		10
+#define CRYPTO_STATE_MASK		GENMASK(13, 10)
+#define ENCR_BUSY_SHIFT			9
+#define AUTH_BUSY_SHIFT			8
+#define DOUT_INTR_SHIFT			7
+#define DIN_INTR_SHIFT			6
+#define OP_DONE_INTR_SHIFT		5
+#define ERR_INTR_SHIFT			4
+#define DOUT_RDY_SHIFT			3
+#define DIN_RDY_SHIFT			2
+#define OPERATION_DONE_SHIFT		1
+#define SW_ERR_SHIFT			0
+
+/* Register bits - REG_STATUS2 */
+#define AXI_EXTRA_SHIFT			1
+#define LOCKED_SHIFT			2
+
+/* Register bits - REG_CONFIG */
+#define REQ_SIZE_SHIFT			17
+#define REQ_SIZE_MASK			GENMASK(20, 17)
+#define REQ_SIZE_ENUM_1_BEAT		0
+#define REQ_SIZE_ENUM_2_BEAT		1
+#define REQ_SIZE_ENUM_3_BEAT		2
+#define REQ_SIZE_ENUM_4_BEAT		3
+#define REQ_SIZE_ENUM_5_BEAT		4
+#define REQ_SIZE_ENUM_6_BEAT		5
+#define REQ_SIZE_ENUM_7_BEAT		6
+#define REQ_SIZE_ENUM_8_BEAT		7
+#define REQ_SIZE_ENUM_9_BEAT		8
+#define REQ_SIZE_ENUM_10_BEAT		9
+#define REQ_SIZE_ENUM_11_BEAT		10
+#define REQ_SIZE_ENUM_12_BEAT		11
+#define REQ_SIZE_ENUM_13_BEAT		12
+#define REQ_SIZE_ENUM_14_BEAT		13
+#define REQ_SIZE_ENUM_15_BEAT		14
+#define REQ_SIZE_ENUM_16_BEAT		15
+
+#define MAX_QUEUED_REQ_SHIFT		14
+#define MAX_QUEUED_REQ_MASK		GENMASK(24, 16)
+#define ENUM_1_QUEUED_REQS		0
+#define ENUM_2_QUEUED_REQS		1
+#define ENUM_3_QUEUED_REQS		2
+
+#define IRQ_ENABLES_SHIFT		10
+#define IRQ_ENABLES_MASK		GENMASK(13, 10)
+
+#define LITTLE_ENDIAN_MODE_SHIFT	9
+#define PIPE_SET_SELECT_SHIFT		5
+#define PIPE_SET_SELECT_MASK		GENMASK(8, 5)
+
+#define HIGH_SPD_EN_N_SHIFT		4
+#define MASK_DOUT_INTR_SHIFT		3
+#define MASK_DIN_INTR_SHIFT		2
+#define MASK_OP_DONE_INTR_SHIFT		1
+#define MASK_ERR_INTR_SHIFT		0
+
+/* Register bits - REG_AUTH_SEG_CFG */
+#define COMP_EXP_MAC_SHIFT		24
+#define COMP_EXP_MAC_DISABLED		0
+#define COMP_EXP_MAC_ENABLED		1
+
+#define F9_DIRECTION_SHIFT		23
+#define F9_DIRECTION_UPLINK		0
+#define F9_DIRECTION_DOWNLINK		1
+
+#define AUTH_NONCE_NUM_WORDS_SHIFT	20
+#define AUTH_NONCE_NUM_WORDS_MASK	GENMASK(22, 20)
+
+#define USE_PIPE_KEY_AUTH_SHIFT		19
+#define USE_HW_KEY_AUTH_SHIFT		18
+#define AUTH_FIRST_SHIFT		17
+#define AUTH_LAST_SHIFT			16
+
+#define AUTH_POS_SHIFT			14
+#define AUTH_POS_MASK			GENMASK(15, 14)
+#define AUTH_POS_BEFORE			0
+#define AUTH_POS_AFTER			1
+
+#define AUTH_SIZE_SHIFT			9
+#define AUTH_SIZE_MASK			GENMASK(13, 9)
+#define AUTH_SIZE_SHA1			0
+#define AUTH_SIZE_SHA256		1
+#define AUTH_SIZE_ENUM_1_BYTES		0
+#define AUTH_SIZE_ENUM_2_BYTES		1
+#define AUTH_SIZE_ENUM_3_BYTES		2
+#define AUTH_SIZE_ENUM_4_BYTES		3
+#define AUTH_SIZE_ENUM_5_BYTES		4
+#define AUTH_SIZE_ENUM_6_BYTES		5
+#define AUTH_SIZE_ENUM_7_BYTES		6
+#define AUTH_SIZE_ENUM_8_BYTES		7
+#define AUTH_SIZE_ENUM_9_BYTES		8
+#define AUTH_SIZE_ENUM_10_BYTES		9
+#define AUTH_SIZE_ENUM_11_BYTES		10
+#define AUTH_SIZE_ENUM_12_BYTES		11
+#define AUTH_SIZE_ENUM_13_BYTES		12
+#define AUTH_SIZE_ENUM_14_BYTES		13
+#define AUTH_SIZE_ENUM_15_BYTES		14
+#define AUTH_SIZE_ENUM_16_BYTES		15
+
+#define AUTH_MODE_SHIFT			6
+#define AUTH_MODE_MASK			GENMASK(8, 6)
+#define AUTH_MODE_HASH			0
+#define AUTH_MODE_HMAC			1
+#define AUTH_MODE_CCM			0
+#define AUTH_MODE_CMAC			1
+
+#define AUTH_KEY_SIZE_SHIFT		3
+#define AUTH_KEY_SIZE_MASK		GENMASK(5, 3)
+#define AUTH_KEY_SZ_AES128		0
+#define AUTH_KEY_SZ_AES256		2
+
+#define AUTH_ALG_SHIFT			0
+#define AUTH_ALG_MASK			GENMASK(2, 0)
+#define AUTH_ALG_NONE			0
+#define AUTH_ALG_SHA			1
+#define AUTH_ALG_AES			2
+#define AUTH_ALG_KASUMI			3
+#define AUTH_ALG_SNOW3G			4
+#define AUTH_ALG_ZUC			5
+
+/* Register bits - REG_ENCR_XTS_DU_SIZE */
+#define ENCR_XTS_DU_SIZE_SHIFT		0
+#define ENCR_XTS_DU_SIZE_MASK		GENMASK(19, 0)
+
+/* Register bits - REG_ENCR_SEG_CFG */
+#define F8_KEYSTREAM_ENABLE_SHIFT	17
+#define F8_KEYSTREAM_DISABLED		0
+#define F8_KEYSTREAM_ENABLED		1
+
+#define F8_DIRECTION_SHIFT		16
+#define F8_DIRECTION_UPLINK		0
+#define F8_DIRECTION_DOWNLINK		1
+
+#define USE_PIPE_KEY_ENCR_SHIFT		15
+#define USE_PIPE_KEY_ENCR_ENABLED	1
+#define USE_KEY_REGISTERS		0
+
+#define USE_HW_KEY_ENCR_SHIFT		14
+#define USE_KEY_REG			0
+#define USE_HW_KEY			1
+
+#define LAST_CCM_SHIFT			13
+#define LAST_CCM_XFR			1
+#define INTERM_CCM_XFR			0
+
+#define CNTR_ALG_SHIFT			11
+#define CNTR_ALG_MASK			GENMASK(12, 11)
+#define CNTR_ALG_NIST			0
+
+#define ENCODE_SHIFT			10
+
+#define ENCR_MODE_SHIFT			6
+#define ENCR_MODE_MASK			GENMASK(9, 6)
+#define ENCR_MODE_ECB			0
+#define ENCR_MODE_CBC			1
+#define ENCR_MODE_CTR			2
+#define ENCR_MODE_XTS			3
+#define ENCR_MODE_CCM			4
+
+#define ENCR_KEY_SZ_SHIFT		3
+#define ENCR_KEY_SZ_MASK		GENMASK(5, 3)
+#define ENCR_KEY_SZ_DES			0
+#define ENCR_KEY_SZ_3DES		1
+#define ENCR_KEY_SZ_AES128		0
+#define ENCR_KEY_SZ_AES256		2
+
+#define ENCR_ALG_SHIFT			0
+#define ENCR_ALG_MASK			GENMASK(2, 0)
+#define ENCR_ALG_NONE			0
+#define ENCR_ALG_DES			1
+#define ENCR_ALG_AES			2
+#define ENCR_ALG_KASUMI			4
+#define ENCR_ALG_SNOW_3G		5
+#define ENCR_ALG_ZUC			6
+
+/* Register bits - REG_GOPROC */
+#define GO_SHIFT			0
+#define CLR_CNTXT_SHIFT			1
+#define RESULTS_DUMP_SHIFT		2
+
+/* Register bits - REG_ENGINES_AVAIL */
+#define ENCR_AES_SEL_SHIFT		0
+#define DES_SEL_SHIFT			1
+#define ENCR_SNOW3G_SEL_SHIFT		2
+#define ENCR_KASUMI_SEL_SHIFT		3
+#define SHA_SEL_SHIFT			4
+#define SHA512_SEL_SHIFT		5
+#define AUTH_AES_SEL_SHIFT		6
+#define AUTH_SNOW3G_SEL_SHIFT		7
+#define AUTH_KASUMI_SEL_SHIFT		8
+#define BAM_PIPE_SETS_SHIFT		9
+#define BAM_PIPE_SETS_MASK		GENMASK(12, 9)
+#define AXI_WR_BEATS_SHIFT		13
+#define AXI_WR_BEATS_MASK		GENMASK(18, 13)
+#define AXI_RD_BEATS_SHIFT		19
+#define AXI_RD_BEATS_MASK		GENMASK(24, 19)
+#define ENCR_ZUC_SEL_SHIFT		26
+#define AUTH_ZUC_SEL_SHIFT		27
+#define ZUC_ENABLE_SHIFT		28
+
+#endif /* _REGS_V5_H_ */
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
new file mode 100644
index 00000000000..f3385934eed
--- /dev/null
+++ b/drivers/crypto/qce/sha.c
@@ -0,0 +1,588 @@
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <crypto/internal/hash.h>
+
+#include "common.h"
+#include "core.h"
+#include "sha.h"
+
+/* crypto hw padding constant for first operation */
+#define SHA_PADDING		64
+#define SHA_PADDING_MASK	(SHA_PADDING - 1)
+
+static LIST_HEAD(ahash_algs);
+
+static const u32 std_iv_sha1[SHA256_DIGEST_SIZE / sizeof(u32)] = {
+	SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4, 0, 0, 0
+};
+
+static const u32 std_iv_sha256[SHA256_DIGEST_SIZE / sizeof(u32)] = {
+	SHA256_H0, SHA256_H1, SHA256_H2, SHA256_H3,
+	SHA256_H4, SHA256_H5, SHA256_H6, SHA256_H7
+};
+
+static void qce_ahash_done(void *data)
+{
+	struct crypto_async_request *async_req = data;
+	struct ahash_request *req = ahash_request_cast(async_req);
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct qce_alg_template *tmpl = to_ahash_tmpl(async_req->tfm);
+	struct qce_device *qce = tmpl->qce;
+	struct qce_result_dump *result = qce->dma.result_buf;
+	unsigned int digestsize = crypto_ahash_digestsize(ahash);
+	int error;
+	u32 status;
+
+	error = qce_dma_terminate_all(&qce->dma);
+	if (error)
+		dev_dbg(qce->dev, "ahash dma termination error (%d)\n", error);
+
+	qce_unmapsg(qce->dev, req->src, rctx->src_nents, DMA_TO_DEVICE,
+		    rctx->src_chained);
+	qce_unmapsg(qce->dev, &rctx->result_sg, 1, DMA_FROM_DEVICE, 0);
+
+	memcpy(rctx->digest, result->auth_iv, digestsize);
+	if (req->result)
+		memcpy(req->result, result->auth_iv, digestsize);
+
+	rctx->byte_count[0] = cpu_to_be32(result->auth_byte_count[0]);
+	rctx->byte_count[1] = cpu_to_be32(result->auth_byte_count[1]);
+
+	error = qce_check_status(qce, &status);
+	if (error < 0)
+		dev_dbg(qce->dev, "ahash operation error (%x)\n", status);
+
+	req->src = rctx->src_orig;
+	req->nbytes = rctx->nbytes_orig;
+	rctx->last_blk = false;
+	rctx->first_blk = false;
+
+	qce->async_req_done(tmpl->qce, error);
+}
+
+static int qce_ahash_async_req_handle(struct crypto_async_request *async_req)
+{
+	struct ahash_request *req = ahash_request_cast(async_req);
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct qce_sha_ctx *ctx = crypto_tfm_ctx(async_req->tfm);
+	struct qce_alg_template *tmpl = to_ahash_tmpl(async_req->tfm);
+	struct qce_device *qce = tmpl->qce;
+	unsigned long flags = rctx->flags;
+	int ret;
+
+	if (IS_SHA_HMAC(flags)) {
+		rctx->authkey = ctx->authkey;
+		rctx->authklen = QCE_SHA_HMAC_KEY_SIZE;
+	} else if (IS_CMAC(flags)) {
+		rctx->authkey = ctx->authkey;
+		rctx->authklen = AES_KEYSIZE_128;
+	}
+
+	rctx->src_nents = qce_countsg(req->src, req->nbytes,
+				      &rctx->src_chained);
+	ret = qce_mapsg(qce->dev, req->src, rctx->src_nents, DMA_TO_DEVICE,
+			rctx->src_chained);
+	if (ret < 0)
+		return ret;
+
+	sg_init_one(&rctx->result_sg, qce->dma.result_buf, QCE_RESULT_BUF_SZ);
+
+	ret = qce_mapsg(qce->dev, &rctx->result_sg, 1, DMA_FROM_DEVICE, 0);
+	if (ret < 0)
+		goto error_unmap_src;
+
+	ret = qce_dma_prep_sgs(&qce->dma, req->src, rctx->src_nents,
+			       &rctx->result_sg, 1, qce_ahash_done, async_req);
+	if (ret)
+		goto error_unmap_dst;
+
+	qce_dma_issue_pending(&qce->dma);
+
+	ret = qce_start(async_req, tmpl->crypto_alg_type, 0, 0);
+	if (ret)
+		goto error_terminate;
+
+	return 0;
+
+error_terminate:
+	qce_dma_terminate_all(&qce->dma);
+error_unmap_dst:
+	qce_unmapsg(qce->dev, &rctx->result_sg, 1, DMA_FROM_DEVICE, 0);
+error_unmap_src:
+	qce_unmapsg(qce->dev, req->src, rctx->src_nents, DMA_TO_DEVICE,
+		    rctx->src_chained);
+	return ret;
+}
+
+static int qce_ahash_init(struct ahash_request *req)
+{
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct qce_alg_template *tmpl = to_ahash_tmpl(req->base.tfm);
+	const u32 *std_iv = tmpl->std_iv;
+
+	memset(rctx, 0, sizeof(*rctx));
+	rctx->first_blk = true;
+	rctx->last_blk = false;
+	rctx->flags = tmpl->alg_flags;
+	memcpy(rctx->digest, std_iv, sizeof(rctx->digest));
+
+	return 0;
+}
+
+static int qce_ahash_export(struct ahash_request *req, void *out)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	unsigned long flags = rctx->flags;
+	unsigned int digestsize = crypto_ahash_digestsize(ahash);
+	unsigned int blocksize =
+			crypto_tfm_alg_blocksize(crypto_ahash_tfm(ahash));
+
+	if (IS_SHA1(flags) || IS_SHA1_HMAC(flags)) {
+		struct sha1_state *out_state = out;
+
+		out_state->count = rctx->count;
+		qce_cpu_to_be32p_array((__be32 *)out_state->state,
+				       rctx->digest, digestsize);
+		memcpy(out_state->buffer, rctx->buf, blocksize);
+	} else if (IS_SHA256(flags) || IS_SHA256_HMAC(flags)) {
+		struct sha256_state *out_state = out;
+
+		out_state->count = rctx->count;
+		qce_cpu_to_be32p_array((__be32 *)out_state->state,
+				       rctx->digest, digestsize);
+		memcpy(out_state->buf, rctx->buf, blocksize);
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int qce_import_common(struct ahash_request *req, u64 in_count,
+			     const u32 *state, const u8 *buffer, bool hmac)
+{
+	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	unsigned int digestsize = crypto_ahash_digestsize(ahash);
+	unsigned int blocksize;
+	u64 count = in_count;
+
+	blocksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(ahash));
+	rctx->count = in_count;
+	memcpy(rctx->buf, buffer, blocksize);
+
+	if (in_count <= blocksize) {
+		rctx->first_blk = 1;
+	} else {
+		rctx->first_blk = 0;
+		/*
+		 * For HMAC, there is a hardware padding done when first block
+		 * is set. Therefore the byte_count must be incremened by 64
+		 * after the first block operation.
+		 */
+		if (hmac)
+			count += SHA_PADDING;
+	}
+
+	rctx->byte_count[0] = (__force __be32)(count & ~SHA_PADDING_MASK);
+	rctx->byte_count[1] = (__force __be32)(count >> 32);
+	qce_cpu_to_be32p_array((__be32 *)rctx->digest, (const u8 *)state,
+			       digestsize);
+	rctx->buflen = (unsigned int)(in_count & (blocksize - 1));
+
+	return 0;
+}
+
+static int qce_ahash_import(struct ahash_request *req, const void *in)
+{
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	unsigned long flags = rctx->flags;
+	bool hmac = IS_SHA_HMAC(flags);
+	int ret = -EINVAL;
+
+	if (IS_SHA1(flags) || IS_SHA1_HMAC(flags)) {
+		const struct sha1_state *state = in;
+
+		ret = qce_import_common(req, state->count, state->state,
+					state->buffer, hmac);
+	} else if (IS_SHA256(flags) || IS_SHA256_HMAC(flags)) {
+		const struct sha256_state *state = in;
+
+		ret = qce_import_common(req, state->count, state->state,
+					state->buf, hmac);
+	}
+
+	return ret;
+}
+
+static int qce_ahash_update(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct qce_alg_template *tmpl = to_ahash_tmpl(req->base.tfm);
+	struct qce_device *qce = tmpl->qce;
+	struct scatterlist *sg_last, *sg;
+	unsigned int total, len;
+	unsigned int hash_later;
+	unsigned int nbytes;
+	unsigned int blocksize;
+
+	blocksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm));
+	rctx->count += req->nbytes;
+
+	/* check for buffer from previous updates and append it */
+	total = req->nbytes + rctx->buflen;
+
+	if (total <= blocksize) {
+		scatterwalk_map_and_copy(rctx->buf + rctx->buflen, req->src,
+					 0, req->nbytes, 0);
+		rctx->buflen += req->nbytes;
+		return 0;
+	}
+
+	/* save the original req structure fields */
+	rctx->src_orig = req->src;
+	rctx->nbytes_orig = req->nbytes;
+
+	/*
+	 * if we have data from previous update copy them on buffer. The old
+	 * data will be combined with current request bytes.
+	 */
+	if (rctx->buflen)
+		memcpy(rctx->tmpbuf, rctx->buf, rctx->buflen);
+
+	/* calculate how many bytes will be hashed later */
+	hash_later = total % blocksize;
+	if (hash_later) {
+		unsigned int src_offset = req->nbytes - hash_later;
+		scatterwalk_map_and_copy(rctx->buf, req->src, src_offset,
+					 hash_later, 0);
+	}
+
+	/* here nbytes is multiple of blocksize */
+	nbytes = total - hash_later;
+
+	len = rctx->buflen;
+	sg = sg_last = req->src;
+
+	while (len < nbytes && sg) {
+		if (len + sg_dma_len(sg) > nbytes)
+			break;
+		len += sg_dma_len(sg);
+		sg_last = sg;
+		sg = scatterwalk_sg_next(sg);
+	}
+
+	if (!sg_last)
+		return -EINVAL;
+
+	sg_mark_end(sg_last);
+
+	if (rctx->buflen) {
+		sg_init_table(rctx->sg, 2);
+		sg_set_buf(rctx->sg, rctx->tmpbuf, rctx->buflen);
+		scatterwalk_sg_chain(rctx->sg, 2, req->src);
+		req->src = rctx->sg;
+	}
+
+	req->nbytes = nbytes;
+	rctx->buflen = hash_later;
+
+	return qce->async_req_enqueue(tmpl->qce, &req->base);
+}
+
+static int qce_ahash_final(struct ahash_request *req)
+{
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct qce_alg_template *tmpl = to_ahash_tmpl(req->base.tfm);
+	struct qce_device *qce = tmpl->qce;
+
+	if (!rctx->buflen)
+		return 0;
+
+	rctx->last_blk = true;
+
+	rctx->src_orig = req->src;
+	rctx->nbytes_orig = req->nbytes;
+
+	memcpy(rctx->tmpbuf, rctx->buf, rctx->buflen);
+	sg_init_one(rctx->sg, rctx->tmpbuf, rctx->buflen);
+
+	req->src = rctx->sg;
+	req->nbytes = rctx->buflen;
+
+	return qce->async_req_enqueue(tmpl->qce, &req->base);
+}
+
+static int qce_ahash_digest(struct ahash_request *req)
+{
+	struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct qce_alg_template *tmpl = to_ahash_tmpl(req->base.tfm);
+	struct qce_device *qce = tmpl->qce;
+	int ret;
+
+	ret = qce_ahash_init(req);
+	if (ret)
+		return ret;
+
+	rctx->src_orig = req->src;
+	rctx->nbytes_orig = req->nbytes;
+	rctx->first_blk = true;
+	rctx->last_blk = true;
+
+	return qce->async_req_enqueue(tmpl->qce, &req->base);
+}
+
+struct qce_ahash_result {
+	struct completion completion;
+	int error;
+};
+
+static void qce_digest_complete(struct crypto_async_request *req, int error)
+{
+	struct qce_ahash_result *result = req->data;
+
+	if (error == -EINPROGRESS)
+		return;
+
+	result->error = error;
+	complete(&result->completion);
+}
+
+static int qce_ahash_hmac_setkey(struct crypto_ahash *tfm, const u8 *key,
+				 unsigned int keylen)
+{
+	unsigned int digestsize = crypto_ahash_digestsize(tfm);
+	struct qce_sha_ctx *ctx = crypto_tfm_ctx(&tfm->base);
+	struct qce_ahash_result result;
+	struct ahash_request *req;
+	struct scatterlist sg;
+	unsigned int blocksize;
+	struct crypto_ahash *ahash_tfm;
+	u8 *buf;
+	int ret;
+	const char *alg_name;
+
+	blocksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm));
+	memset(ctx->authkey, 0, sizeof(ctx->authkey));
+
+	if (keylen <= blocksize) {
+		memcpy(ctx->authkey, key, keylen);
+		return 0;
+	}
+
+	if (digestsize == SHA1_DIGEST_SIZE)
+		alg_name = "sha1-qce";
+	else if (digestsize == SHA256_DIGEST_SIZE)
+		alg_name = "sha256-qce";
+	else
+		return -EINVAL;
+
+	ahash_tfm = crypto_alloc_ahash(alg_name, CRYPTO_ALG_TYPE_AHASH,
+				       CRYPTO_ALG_TYPE_AHASH_MASK);
+	if (IS_ERR(ahash_tfm))
+		return PTR_ERR(ahash_tfm);
+
+	req = ahash_request_alloc(ahash_tfm, GFP_KERNEL);
+	if (!req) {
+		ret = -ENOMEM;
+		goto err_free_ahash;
+	}
+
+	init_completion(&result.completion);
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   qce_digest_complete, &result);
+	crypto_ahash_clear_flags(ahash_tfm, ~0);
+
+	buf = kzalloc(keylen + QCE_MAX_ALIGN_SIZE, GFP_KERNEL);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto err_free_req;
+	}
+
+	memcpy(buf, key, keylen);
+	sg_init_one(&sg, buf, keylen);
+	ahash_request_set_crypt(req, &sg, ctx->authkey, keylen);
+
+	ret = crypto_ahash_digest(req);
+	if (ret == -EINPROGRESS || ret == -EBUSY) {
+		ret = wait_for_completion_interruptible(&result.completion);
+		if (!ret)
+			ret = result.error;
+	}
+
+	if (ret)
+		crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+
+	kfree(buf);
+err_free_req:
+	ahash_request_free(req);
+err_free_ahash:
+	crypto_free_ahash(ahash_tfm);
+	return ret;
+}
+
+static int qce_ahash_cra_init(struct crypto_tfm *tfm)
+{
+	struct crypto_ahash *ahash = __crypto_ahash_cast(tfm);
+	struct qce_sha_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_ahash_set_reqsize(ahash, sizeof(struct qce_sha_reqctx));
+	memset(ctx, 0, sizeof(*ctx));
+	return 0;
+}
+
+struct qce_ahash_def {
+	unsigned long flags;
+	const char *name;
+	const char *drv_name;
+	unsigned int digestsize;
+	unsigned int blocksize;
+	unsigned int statesize;
+	const u32 *std_iv;
+};
+
+static const struct qce_ahash_def ahash_def[] = {
+	{
+		.flags		= QCE_HASH_SHA1,
+		.name		= "sha1",
+		.drv_name	= "sha1-qce",
+		.digestsize	= SHA1_DIGEST_SIZE,
+		.blocksize	= SHA1_BLOCK_SIZE,
+		.statesize	= sizeof(struct sha1_state),
+		.std_iv		= std_iv_sha1,
+	},
+	{
+		.flags		= QCE_HASH_SHA256,
+		.name		= "sha256",
+		.drv_name	= "sha256-qce",
+		.digestsize	= SHA256_DIGEST_SIZE,
+		.blocksize	= SHA256_BLOCK_SIZE,
+		.statesize	= sizeof(struct sha256_state),
+		.std_iv		= std_iv_sha256,
+	},
+	{
+		.flags		= QCE_HASH_SHA1_HMAC,
+		.name		= "hmac(sha1)",
+		.drv_name	= "hmac-sha1-qce",
+		.digestsize	= SHA1_DIGEST_SIZE,
+		.blocksize	= SHA1_BLOCK_SIZE,
+		.statesize	= sizeof(struct sha1_state),
+		.std_iv		= std_iv_sha1,
+	},
+	{
+		.flags		= QCE_HASH_SHA256_HMAC,
+		.name		= "hmac(sha256)",
+		.drv_name	= "hmac-sha256-qce",
+		.digestsize	= SHA256_DIGEST_SIZE,
+		.blocksize	= SHA256_BLOCK_SIZE,
+		.statesize	= sizeof(struct sha256_state),
+		.std_iv		= std_iv_sha256,
+	},
+};
+
+static int qce_ahash_register_one(const struct qce_ahash_def *def,
+				  struct qce_device *qce)
+{
+	struct qce_alg_template *tmpl;
+	struct ahash_alg *alg;
+	struct crypto_alg *base;
+	int ret;
+
+	tmpl = kzalloc(sizeof(*tmpl), GFP_KERNEL);
+	if (!tmpl)
+		return -ENOMEM;
+
+	tmpl->std_iv = def->std_iv;
+
+	alg = &tmpl->alg.ahash;
+	alg->init = qce_ahash_init;
+	alg->update = qce_ahash_update;
+	alg->final = qce_ahash_final;
+	alg->digest = qce_ahash_digest;
+	alg->export = qce_ahash_export;
+	alg->import = qce_ahash_import;
+	if (IS_SHA_HMAC(def->flags))
+		alg->setkey = qce_ahash_hmac_setkey;
+	alg->halg.digestsize = def->digestsize;
+	alg->halg.statesize = def->statesize;
+
+	base = &alg->halg.base;
+	base->cra_blocksize = def->blocksize;
+	base->cra_priority = 300;
+	base->cra_flags = CRYPTO_ALG_ASYNC;
+	base->cra_ctxsize = sizeof(struct qce_sha_ctx);
+	base->cra_alignmask = 0;
+	base->cra_module = THIS_MODULE;
+	base->cra_init = qce_ahash_cra_init;
+	INIT_LIST_HEAD(&base->cra_list);
+
+	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
+	snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+		 def->drv_name);
+
+	INIT_LIST_HEAD(&tmpl->entry);
+	tmpl->crypto_alg_type = CRYPTO_ALG_TYPE_AHASH;
+	tmpl->alg_flags = def->flags;
+	tmpl->qce = qce;
+
+	ret = crypto_register_ahash(alg);
+	if (ret) {
+		kfree(tmpl);
+		dev_err(qce->dev, "%s registration failed\n", base->cra_name);
+		return ret;
+	}
+
+	list_add_tail(&tmpl->entry, &ahash_algs);
+	dev_dbg(qce->dev, "%s is registered\n", base->cra_name);
+	return 0;
+}
+
+static void qce_ahash_unregister(struct qce_device *qce)
+{
+	struct qce_alg_template *tmpl, *n;
+
+	list_for_each_entry_safe(tmpl, n, &ahash_algs, entry) {
+		crypto_unregister_ahash(&tmpl->alg.ahash);
+		list_del(&tmpl->entry);
+		kfree(tmpl);
+	}
+}
+
+static int qce_ahash_register(struct qce_device *qce)
+{
+	int ret, i;
+
+	for (i = 0; i < ARRAY_SIZE(ahash_def); i++) {
+		ret = qce_ahash_register_one(&ahash_def[i], qce);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+err:
+	qce_ahash_unregister(qce);
+	return ret;
+}
+
+const struct qce_algo_ops ahash_ops = {
+	.type = CRYPTO_ALG_TYPE_AHASH,
+	.register_algs = qce_ahash_register,
+	.unregister_algs = qce_ahash_unregister,
+	.async_req_handle = qce_ahash_async_req_handle,
+};
diff --git a/drivers/crypto/qce/sha.h b/drivers/crypto/qce/sha.h
new file mode 100644
index 00000000000..286f0d5397f
--- /dev/null
+++ b/drivers/crypto/qce/sha.h
@@ -0,0 +1,81 @@
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _SHA_H_
+#define _SHA_H_
+
+#include <crypto/scatterwalk.h>
+#include <crypto/sha.h>
+
+#include "common.h"
+#include "core.h"
+
+#define QCE_SHA_MAX_BLOCKSIZE		SHA256_BLOCK_SIZE
+#define QCE_SHA_MAX_DIGESTSIZE		SHA256_DIGEST_SIZE
+
+struct qce_sha_ctx {
+	u8 authkey[QCE_SHA_MAX_BLOCKSIZE];
+};
+
+/**
+ * struct qce_sha_reqctx - holds private ahash objects per request
+ * @buf: used during update, import and export
+ * @tmpbuf: buffer for internal use
+ * @digest: calculated digest buffer
+ * @buflen: length of the buffer
+ * @flags: operation flags
+ * @src_orig: original request sg list
+ * @nbytes_orig: original request number of bytes
+ * @src_chained: is source scatterlist chained
+ * @src_nents: source number of entries
+ * @byte_count: byte count
+ * @count: save count in states during update, import and export
+ * @first_blk: is it the first block
+ * @last_blk: is it the last block
+ * @sg: used to chain sg lists
+ * @authkey: pointer to auth key in sha ctx
+ * @authklen: auth key length
+ * @result_sg: scatterlist used for result buffer
+ */
+struct qce_sha_reqctx {
+	u8 buf[QCE_SHA_MAX_BLOCKSIZE];
+	u8 tmpbuf[QCE_SHA_MAX_BLOCKSIZE];
+	u8 digest[QCE_SHA_MAX_DIGESTSIZE];
+	unsigned int buflen;
+	unsigned long flags;
+	struct scatterlist *src_orig;
+	unsigned int nbytes_orig;
+	bool src_chained;
+	int src_nents;
+	__be32 byte_count[2];
+	u64 count;
+	bool first_blk;
+	bool last_blk;
+	struct scatterlist sg[2];
+	u8 *authkey;
+	unsigned int authklen;
+	struct scatterlist result_sg;
+};
+
+static inline struct qce_alg_template *to_ahash_tmpl(struct crypto_tfm *tfm)
+{
+	struct crypto_ahash *ahash = __crypto_ahash_cast(tfm);
+	struct ahash_alg *alg = container_of(crypto_hash_alg_common(ahash),
+					     struct ahash_alg, halg);
+
+	return container_of(alg, struct qce_alg_template, alg.ahash);
+}
+
+extern const struct qce_algo_ops ahash_ops;
+
+#endif /* _SHA_H_ */
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index a999f537228..92105f3dc8e 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -190,7 +190,7 @@ static void add_session_id(struct cryp_ctx *ctx)
 static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 {
 	struct cryp_ctx *ctx;
-	int i;
+	int count;
 	struct cryp_device_data *device_data;
 
 	if (param == NULL) {
@@ -215,12 +215,11 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 	if (cryp_pending_irq_src(device_data,
 				 CRYP_IRQ_SRC_OUTPUT_FIFO)) {
 		if (ctx->outlen / ctx->blocksize > 0) {
-			for (i = 0; i < ctx->blocksize / 4; i++) {
-				*(ctx->outdata) = readl_relaxed(
-						&device_data->base->dout);
-				ctx->outdata += 4;
-				ctx->outlen -= 4;
-			}
+			count = ctx->blocksize / 4;
+
+			readsl(&device_data->base->dout, ctx->outdata, count);
+			ctx->outdata += count;
+			ctx->outlen -= count;
 
 			if (ctx->outlen == 0) {
 				cryp_disable_irq_src(device_data,
@@ -230,12 +229,12 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 	} else if (cryp_pending_irq_src(device_data,
 					CRYP_IRQ_SRC_INPUT_FIFO)) {
 		if (ctx->datalen / ctx->blocksize > 0) {
-			for (i = 0 ; i < ctx->blocksize / 4; i++) {
-				writel_relaxed(ctx->indata,
-						&device_data->base->din);
-				ctx->indata += 4;
-				ctx->datalen -= 4;
-			}
+			count = ctx->blocksize / 4;
+
+			writesl(&device_data->base->din, ctx->indata, count);
+
+			ctx->indata += count;
+			ctx->datalen -= count;
 
 			if (ctx->datalen == 0)
 				cryp_disable_irq_src(device_data,
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 5c5863842de..1eca7b9760e 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -234,7 +234,7 @@ config PL330_DMA
 
 config PCH_DMA
 	tristate "Intel EG20T PCH / LAPIS Semicon IOH(ML7213/ML7223/ML7831) DMA"
-	depends on PCI && X86
+	depends on PCI && (X86_32 || COMPILE_TEST)
 	select DMA_ENGINE
 	help
 	  Enable support for Intel EG20T PCH DMA engine.
@@ -269,7 +269,7 @@ config MXS_DMA
 	select DMA_ENGINE
 	help
 	  Support the MXS DMA engine. This engine including APBH-DMA
-	  and APBX-DMA is integrated into Freescale i.MX23/28 chips.
+	  and APBX-DMA is integrated into Freescale i.MX23/28/MX6Q/MX6DL chips.
 
 config EP93XX_DMA
 	bool "Cirrus Logic EP93xx DMA support"
@@ -361,6 +361,20 @@ config FSL_EDMA
 	  multiplexing capability for DMA request sources(slot).
 	  This module can be found on Freescale Vybrid and LS-1 SoCs.
 
+config XILINX_VDMA
+	tristate "Xilinx AXI VDMA Engine"
+	depends on (ARCH_ZYNQ || MICROBLAZE)
+	select DMA_ENGINE
+	help
+	  Enable support for Xilinx AXI VDMA Soft IP.
+
+	  This engine provides high-bandwidth direct memory access
+	  between memory and AXI4-Stream video type target
+	  peripherals including peripherals which support AXI4-
+	  Stream Video Protocol.  It has two stream interfaces/
+	  channels, Memory Mapped to Stream (MM2S) and Stream to
+	  Memory Mapped (S2MM) for the data transfers.
+
 config DMA_ENGINE
 	bool
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 5150c82c9ca..c779e1eb2db 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -46,3 +46,4 @@ obj-$(CONFIG_K3_DMA) += k3dma.o
 obj-$(CONFIG_MOXART_DMA) += moxart-dma.o
 obj-$(CONFIG_FSL_EDMA) += fsl-edma.o
 obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o
+obj-y += xilinx/
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index d028f36ae65..8f8b0b60887 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -86,6 +86,9 @@
 
 #define USBSS_IRQ_PD_COMP	(1 <<  2)
 
+/* Packet Descriptor */
+#define PD2_ZERO_LENGTH		(1 << 19)
+
 struct cppi41_channel {
 	struct dma_chan chan;
 	struct dma_async_tx_descriptor txd;
@@ -307,7 +310,7 @@ static irqreturn_t cppi41_irq(int irq, void *data)
 			__iormb();
 
 		while (val) {
-			u32 desc;
+			u32 desc, len;
 
 			q_num = __fls(val);
 			val &= ~(1 << q_num);
@@ -319,9 +322,13 @@ static irqreturn_t cppi41_irq(int irq, void *data)
 						q_num, desc);
 				continue;
 			}
-			c->residue = pd_trans_len(c->desc->pd6) -
-				pd_trans_len(c->desc->pd0);
 
+			if (c->desc->pd2 & PD2_ZERO_LENGTH)
+				len = 0;
+			else
+				len = pd_trans_len(c->desc->pd0);
+
+			c->residue = pd_trans_len(c->desc->pd6) - len;
 			dma_cookie_complete(&c->txd);
 			c->txd.callback(c->txd.callback_param);
 		}
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 7a740769c2f..a27ded53ab4 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1493,6 +1493,13 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	dw->regs = chip->regs;
 	chip->dw = dw;
 
+	dw->clk = devm_clk_get(chip->dev, "hclk");
+	if (IS_ERR(dw->clk))
+		return PTR_ERR(dw->clk);
+	err = clk_prepare_enable(dw->clk);
+	if (err)
+		return err;
+
 	dw_params = dma_read_byaddr(chip->regs, DW_PARAMS);
 	autocfg = dw_params >> DW_PARAMS_EN & 0x1;
 
@@ -1500,15 +1507,19 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 	if (!pdata && autocfg) {
 		pdata = devm_kzalloc(chip->dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata)
-			return -ENOMEM;
+		if (!pdata) {
+			err = -ENOMEM;
+			goto err_pdata;
+		}
 
 		/* Fill platform data with the default values */
 		pdata->is_private = true;
 		pdata->chan_allocation_order = CHAN_ALLOCATION_ASCENDING;
 		pdata->chan_priority = CHAN_PRIORITY_ASCENDING;
-	} else if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS)
-		return -EINVAL;
+	} else if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS) {
+		err = -EINVAL;
+		goto err_pdata;
+	}
 
 	if (autocfg)
 		nr_channels = (dw_params >> DW_PARAMS_NR_CHAN & 0x7) + 1;
@@ -1517,13 +1528,10 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 	dw->chan = devm_kcalloc(chip->dev, nr_channels, sizeof(*dw->chan),
 				GFP_KERNEL);
-	if (!dw->chan)
-		return -ENOMEM;
-
-	dw->clk = devm_clk_get(chip->dev, "hclk");
-	if (IS_ERR(dw->clk))
-		return PTR_ERR(dw->clk);
-	clk_prepare_enable(dw->clk);
+	if (!dw->chan) {
+		err = -ENOMEM;
+		goto err_pdata;
+	}
 
 	/* Get hardware configuration parameters */
 	if (autocfg) {
@@ -1553,7 +1561,8 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 					 sizeof(struct dw_desc), 4, 0);
 	if (!dw->desc_pool) {
 		dev_err(chip->dev, "No memory for descriptors dma pool\n");
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err_pdata;
 	}
 
 	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
@@ -1561,7 +1570,7 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	err = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED,
 			  "dw_dmac", dw);
 	if (err)
-		return err;
+		goto err_pdata;
 
 	INIT_LIST_HEAD(&dw->dma.channels);
 	for (i = 0; i < nr_channels; i++) {
@@ -1650,12 +1659,20 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 	dma_writel(dw, CFG, DW_CFG_DMA_EN);
 
+	err = dma_async_device_register(&dw->dma);
+	if (err)
+		goto err_dma_register;
+
 	dev_info(chip->dev, "DesignWare DMA Controller, %d channels\n",
 		 nr_channels);
 
-	dma_async_device_register(&dw->dma);
-
 	return 0;
+
+err_dma_register:
+	free_irq(chip->irq, dw);
+err_pdata:
+	clk_disable_unprepare(dw->clk);
+	return err;
 }
 EXPORT_SYMBOL_GPL(dw_dma_probe);
 
@@ -1676,6 +1693,8 @@ int dw_dma_remove(struct dw_dma_chip *chip)
 		channel_clear_bit(dw, CH_EN, dwc->mask);
 	}
 
+	clk_disable_unprepare(dw->clk);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dw_dma_remove);
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index fec59f1a77b..39e30c3c7a9 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -93,19 +93,13 @@ static int dw_pci_resume_early(struct device *dev)
 	return dw_dma_resume(chip);
 };
 
-#else /* !CONFIG_PM_SLEEP */
-
-#define dw_pci_suspend_late	NULL
-#define dw_pci_resume_early	NULL
-
-#endif /* !CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM_SLEEP */
 
 static const struct dev_pm_ops dw_pci_dev_pm_ops = {
-	.suspend_late = dw_pci_suspend_late,
-	.resume_early = dw_pci_resume_early,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_pci_suspend_late, dw_pci_resume_early)
 };
 
-static DEFINE_PCI_DEVICE_TABLE(dw_pci_id_table) = {
+static const struct pci_device_id dw_pci_id_table[] = {
 	/* Medfield */
 	{ PCI_VDEVICE(INTEL, 0x0827), (kernel_ulong_t)&dw_pci_pdata },
 	{ PCI_VDEVICE(INTEL, 0x0830), (kernel_ulong_t)&dw_pci_pdata },
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index 453822cc4f9..c5b339af6be 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -256,7 +256,7 @@ MODULE_DEVICE_TABLE(acpi, dw_dma_acpi_id_table);
 
 #ifdef CONFIG_PM_SLEEP
 
-static int dw_suspend_noirq(struct device *dev)
+static int dw_suspend_late(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
@@ -264,7 +264,7 @@ static int dw_suspend_noirq(struct device *dev)
 	return dw_dma_suspend(chip);
 }
 
-static int dw_resume_noirq(struct device *dev)
+static int dw_resume_early(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
@@ -272,20 +272,10 @@ static int dw_resume_noirq(struct device *dev)
 	return dw_dma_resume(chip);
 }
 
-#else /* !CONFIG_PM_SLEEP */
-
-#define dw_suspend_noirq	NULL
-#define dw_resume_noirq		NULL
-
-#endif /* !CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM_SLEEP */
 
 static const struct dev_pm_ops dw_dev_pm_ops = {
-	.suspend_noirq = dw_suspend_noirq,
-	.resume_noirq = dw_resume_noirq,
-	.freeze_noirq = dw_suspend_noirq,
-	.thaw_noirq = dw_resume_noirq,
-	.restore_noirq = dw_resume_noirq,
-	.poweroff_noirq = dw_suspend_noirq,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_suspend_late, dw_resume_early)
 };
 
 static struct platform_driver dw_driver = {
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index f157c6f76b3..e0fec68aed2 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -61,6 +61,16 @@ static u32 get_sr(struct fsldma_chan *chan)
 	return DMA_IN(chan, &chan->regs->sr, 32);
 }
 
+static void set_mr(struct fsldma_chan *chan, u32 val)
+{
+	DMA_OUT(chan, &chan->regs->mr, val, 32);
+}
+
+static u32 get_mr(struct fsldma_chan *chan)
+{
+	return DMA_IN(chan, &chan->regs->mr, 32);
+}
+
 static void set_cdar(struct fsldma_chan *chan, dma_addr_t addr)
 {
 	DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64);
@@ -71,6 +81,11 @@ static dma_addr_t get_cdar(struct fsldma_chan *chan)
 	return DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN;
 }
 
+static void set_bcr(struct fsldma_chan *chan, u32 val)
+{
+	DMA_OUT(chan, &chan->regs->bcr, val, 32);
+}
+
 static u32 get_bcr(struct fsldma_chan *chan)
 {
 	return DMA_IN(chan, &chan->regs->bcr, 32);
@@ -135,7 +150,7 @@ static void set_ld_eol(struct fsldma_chan *chan, struct fsl_desc_sw *desc)
 static void dma_init(struct fsldma_chan *chan)
 {
 	/* Reset the channel */
-	DMA_OUT(chan, &chan->regs->mr, 0, 32);
+	set_mr(chan, 0);
 
 	switch (chan->feature & FSL_DMA_IP_MASK) {
 	case FSL_DMA_IP_85XX:
@@ -144,16 +159,15 @@ static void dma_init(struct fsldma_chan *chan)
 		 * EOLNIE - End of links interrupt enable
 		 * BWC - Bandwidth sharing among channels
 		 */
-		DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_BWC
-				| FSL_DMA_MR_EIE | FSL_DMA_MR_EOLNIE, 32);
+		set_mr(chan, FSL_DMA_MR_BWC | FSL_DMA_MR_EIE
+			| FSL_DMA_MR_EOLNIE);
 		break;
 	case FSL_DMA_IP_83XX:
 		/* Set the channel to below modes:
 		 * EOTIE - End-of-transfer interrupt enable
 		 * PRC_RM - PCI read multiple
 		 */
-		DMA_OUT(chan, &chan->regs->mr, FSL_DMA_MR_EOTIE
-				| FSL_DMA_MR_PRC_RM, 32);
+		set_mr(chan, FSL_DMA_MR_EOTIE | FSL_DMA_MR_PRC_RM);
 		break;
 	}
 }
@@ -175,10 +189,10 @@ static void dma_start(struct fsldma_chan *chan)
 {
 	u32 mode;
 
-	mode = DMA_IN(chan, &chan->regs->mr, 32);
+	mode = get_mr(chan);
 
 	if (chan->feature & FSL_DMA_CHAN_PAUSE_EXT) {
-		DMA_OUT(chan, &chan->regs->bcr, 0, 32);
+		set_bcr(chan, 0);
 		mode |= FSL_DMA_MR_EMP_EN;
 	} else {
 		mode &= ~FSL_DMA_MR_EMP_EN;
@@ -191,7 +205,7 @@ static void dma_start(struct fsldma_chan *chan)
 		mode |= FSL_DMA_MR_CS;
 	}
 
-	DMA_OUT(chan, &chan->regs->mr, mode, 32);
+	set_mr(chan, mode);
 }
 
 static void dma_halt(struct fsldma_chan *chan)
@@ -200,7 +214,7 @@ static void dma_halt(struct fsldma_chan *chan)
 	int i;
 
 	/* read the mode register */
-	mode = DMA_IN(chan, &chan->regs->mr, 32);
+	mode = get_mr(chan);
 
 	/*
 	 * The 85xx controller supports channel abort, which will stop
@@ -209,14 +223,14 @@ static void dma_halt(struct fsldma_chan *chan)
 	 */
 	if ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) {
 		mode |= FSL_DMA_MR_CA;
-		DMA_OUT(chan, &chan->regs->mr, mode, 32);
+		set_mr(chan, mode);
 
 		mode &= ~FSL_DMA_MR_CA;
 	}
 
 	/* stop the DMA controller */
 	mode &= ~(FSL_DMA_MR_CS | FSL_DMA_MR_EMS_EN);
-	DMA_OUT(chan, &chan->regs->mr, mode, 32);
+	set_mr(chan, mode);
 
 	/* wait for the DMA controller to become idle */
 	for (i = 0; i < 100; i++) {
@@ -245,7 +259,7 @@ static void fsl_chan_set_src_loop_size(struct fsldma_chan *chan, int size)
 {
 	u32 mode;
 
-	mode = DMA_IN(chan, &chan->regs->mr, 32);
+	mode = get_mr(chan);
 
 	switch (size) {
 	case 0:
@@ -259,7 +273,7 @@ static void fsl_chan_set_src_loop_size(struct fsldma_chan *chan, int size)
 		break;
 	}
 
-	DMA_OUT(chan, &chan->regs->mr, mode, 32);
+	set_mr(chan, mode);
 }
 
 /**
@@ -277,7 +291,7 @@ static void fsl_chan_set_dst_loop_size(struct fsldma_chan *chan, int size)
 {
 	u32 mode;
 
-	mode = DMA_IN(chan, &chan->regs->mr, 32);
+	mode = get_mr(chan);
 
 	switch (size) {
 	case 0:
@@ -291,7 +305,7 @@ static void fsl_chan_set_dst_loop_size(struct fsldma_chan *chan, int size)
 		break;
 	}
 
-	DMA_OUT(chan, &chan->regs->mr, mode, 32);
+	set_mr(chan, mode);
 }
 
 /**
@@ -312,10 +326,10 @@ static void fsl_chan_set_request_count(struct fsldma_chan *chan, int size)
 
 	BUG_ON(size > 1024);
 
-	mode = DMA_IN(chan, &chan->regs->mr, 32);
+	mode = get_mr(chan);
 	mode |= (__ilog2(size) << 24) & 0x0f000000;
 
-	DMA_OUT(chan, &chan->regs->mr, mode, 32);
+	set_mr(chan, mode);
 }
 
 /**
@@ -404,6 +418,19 @@ static dma_cookie_t fsl_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 }
 
 /**
+ * fsl_dma_free_descriptor - Free descriptor from channel's DMA pool.
+ * @chan : Freescale DMA channel
+ * @desc: descriptor to be freed
+ */
+static void fsl_dma_free_descriptor(struct fsldma_chan *chan,
+		struct fsl_desc_sw *desc)
+{
+	list_del(&desc->node);
+	chan_dbg(chan, "LD %p free\n", desc);
+	dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys);
+}
+
+/**
  * fsl_dma_alloc_descriptor - Allocate descriptor from channel's DMA pool.
  * @chan : Freescale DMA channel
  *
@@ -426,14 +453,107 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(struct fsldma_chan *chan)
 	desc->async_tx.tx_submit = fsl_dma_tx_submit;
 	desc->async_tx.phys = pdesc;
 
-#ifdef FSL_DMA_LD_DEBUG
 	chan_dbg(chan, "LD %p allocated\n", desc);
-#endif
 
 	return desc;
 }
 
 /**
+ * fsl_chan_xfer_ld_queue - transfer any pending transactions
+ * @chan : Freescale DMA channel
+ *
+ * HARDWARE STATE: idle
+ * LOCKING: must hold chan->desc_lock
+ */
+static void fsl_chan_xfer_ld_queue(struct fsldma_chan *chan)
+{
+	struct fsl_desc_sw *desc;
+
+	/*
+	 * If the list of pending descriptors is empty, then we
+	 * don't need to do any work at all
+	 */
+	if (list_empty(&chan->ld_pending)) {
+		chan_dbg(chan, "no pending LDs\n");
+		return;
+	}
+
+	/*
+	 * The DMA controller is not idle, which means that the interrupt
+	 * handler will start any queued transactions when it runs after
+	 * this transaction finishes
+	 */
+	if (!chan->idle) {
+		chan_dbg(chan, "DMA controller still busy\n");
+		return;
+	}
+
+	/*
+	 * If there are some link descriptors which have not been
+	 * transferred, we need to start the controller
+	 */
+
+	/*
+	 * Move all elements from the queue of pending transactions
+	 * onto the list of running transactions
+	 */
+	chan_dbg(chan, "idle, starting controller\n");
+	desc = list_first_entry(&chan->ld_pending, struct fsl_desc_sw, node);
+	list_splice_tail_init(&chan->ld_pending, &chan->ld_running);
+
+	/*
+	 * The 85xx DMA controller doesn't clear the channel start bit
+	 * automatically at the end of a transfer. Therefore we must clear
+	 * it in software before starting the transfer.
+	 */
+	if ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) {
+		u32 mode;
+
+		mode = get_mr(chan);
+		mode &= ~FSL_DMA_MR_CS;
+		set_mr(chan, mode);
+	}
+
+	/*
+	 * Program the descriptor's address into the DMA controller,
+	 * then start the DMA transaction
+	 */
+	set_cdar(chan, desc->async_tx.phys);
+	get_cdar(chan);
+
+	dma_start(chan);
+	chan->idle = false;
+}
+
+/**
+ * fsldma_cleanup_descriptor - cleanup and free a single link descriptor
+ * @chan: Freescale DMA channel
+ * @desc: descriptor to cleanup and free
+ *
+ * This function is used on a descriptor which has been executed by the DMA
+ * controller. It will run any callbacks, submit any dependencies, and then
+ * free the descriptor.
+ */
+static void fsldma_cleanup_descriptor(struct fsldma_chan *chan,
+				      struct fsl_desc_sw *desc)
+{
+	struct dma_async_tx_descriptor *txd = &desc->async_tx;
+
+	/* Run the link descriptor callback function */
+	if (txd->callback) {
+		chan_dbg(chan, "LD %p callback\n", desc);
+		txd->callback(txd->callback_param);
+	}
+
+	/* Run any dependencies */
+	dma_run_dependencies(txd);
+
+	dma_descriptor_unmap(txd);
+	chan_dbg(chan, "LD %p free\n", desc);
+	dma_pool_free(chan->desc_pool, desc, txd->phys);
+}
+
+/**
  * fsl_dma_alloc_chan_resources - Allocate resources for DMA channel.
  * @chan : Freescale DMA channel
  *
@@ -477,13 +597,8 @@ static void fsldma_free_desc_list(struct fsldma_chan *chan,
 {
 	struct fsl_desc_sw *desc, *_desc;
 
-	list_for_each_entry_safe(desc, _desc, list, node) {
-		list_del(&desc->node);
-#ifdef FSL_DMA_LD_DEBUG
-		chan_dbg(chan, "LD %p free\n", desc);
-#endif
-		dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys);
-	}
+	list_for_each_entry_safe(desc, _desc, list, node)
+		fsl_dma_free_descriptor(chan, desc);
 }
 
 static void fsldma_free_desc_list_reverse(struct fsldma_chan *chan,
@@ -491,13 +606,8 @@ static void fsldma_free_desc_list_reverse(struct fsldma_chan *chan,
 {
 	struct fsl_desc_sw *desc, *_desc;
 
-	list_for_each_entry_safe_reverse(desc, _desc, list, node) {
-		list_del(&desc->node);
-#ifdef FSL_DMA_LD_DEBUG
-		chan_dbg(chan, "LD %p free\n", desc);
-#endif
-		dma_pool_free(chan->desc_pool, desc, desc->async_tx.phys);
-	}
+	list_for_each_entry_safe_reverse(desc, _desc, list, node)
+		fsl_dma_free_descriptor(chan, desc);
 }
 
 /**
@@ -520,35 +630,6 @@ static void fsl_dma_free_chan_resources(struct dma_chan *dchan)
 }
 
 static struct dma_async_tx_descriptor *
-fsl_dma_prep_interrupt(struct dma_chan *dchan, unsigned long flags)
-{
-	struct fsldma_chan *chan;
-	struct fsl_desc_sw *new;
-
-	if (!dchan)
-		return NULL;
-
-	chan = to_fsl_chan(dchan);
-
-	new = fsl_dma_alloc_descriptor(chan);
-	if (!new) {
-		chan_err(chan, "%s\n", msg_ld_oom);
-		return NULL;
-	}
-
-	new->async_tx.cookie = -EBUSY;
-	new->async_tx.flags = flags;
-
-	/* Insert the link descriptor to the LD ring */
-	list_add_tail(&new->node, &new->tx_list);
-
-	/* Set End-of-link to the last link descriptor of new list */
-	set_ld_eol(chan, new);
-
-	return &new->async_tx;
-}
-
-static struct dma_async_tx_descriptor *
 fsl_dma_prep_memcpy(struct dma_chan *dchan,
 	dma_addr_t dma_dst, dma_addr_t dma_src,
 	size_t len, unsigned long flags)
@@ -817,105 +898,6 @@ static int fsl_dma_device_control(struct dma_chan *dchan,
 }
 
 /**
- * fsldma_cleanup_descriptor - cleanup and free a single link descriptor
- * @chan: Freescale DMA channel
- * @desc: descriptor to cleanup and free
- *
- * This function is used on a descriptor which has been executed by the DMA
- * controller. It will run any callbacks, submit any dependencies, and then
- * free the descriptor.
- */
-static void fsldma_cleanup_descriptor(struct fsldma_chan *chan,
-				      struct fsl_desc_sw *desc)
-{
-	struct dma_async_tx_descriptor *txd = &desc->async_tx;
-
-	/* Run the link descriptor callback function */
-	if (txd->callback) {
-#ifdef FSL_DMA_LD_DEBUG
-		chan_dbg(chan, "LD %p callback\n", desc);
-#endif
-		txd->callback(txd->callback_param);
-	}
-
-	/* Run any dependencies */
-	dma_run_dependencies(txd);
-
-	dma_descriptor_unmap(txd);
-#ifdef FSL_DMA_LD_DEBUG
-	chan_dbg(chan, "LD %p free\n", desc);
-#endif
-	dma_pool_free(chan->desc_pool, desc, txd->phys);
-}
-
-/**
- * fsl_chan_xfer_ld_queue - transfer any pending transactions
- * @chan : Freescale DMA channel
- *
- * HARDWARE STATE: idle
- * LOCKING: must hold chan->desc_lock
- */
-static void fsl_chan_xfer_ld_queue(struct fsldma_chan *chan)
-{
-	struct fsl_desc_sw *desc;
-
-	/*
-	 * If the list of pending descriptors is empty, then we
-	 * don't need to do any work at all
-	 */
-	if (list_empty(&chan->ld_pending)) {
-		chan_dbg(chan, "no pending LDs\n");
-		return;
-	}
-
-	/*
-	 * The DMA controller is not idle, which means that the interrupt
-	 * handler will start any queued transactions when it runs after
-	 * this transaction finishes
-	 */
-	if (!chan->idle) {
-		chan_dbg(chan, "DMA controller still busy\n");
-		return;
-	}
-
-	/*
-	 * If there are some link descriptors which have not been
-	 * transferred, we need to start the controller
-	 */
-
-	/*
-	 * Move all elements from the queue of pending transactions
-	 * onto the list of running transactions
-	 */
-	chan_dbg(chan, "idle, starting controller\n");
-	desc = list_first_entry(&chan->ld_pending, struct fsl_desc_sw, node);
-	list_splice_tail_init(&chan->ld_pending, &chan->ld_running);
-
-	/*
-	 * The 85xx DMA controller doesn't clear the channel start bit
-	 * automatically at the end of a transfer. Therefore we must clear
-	 * it in software before starting the transfer.
-	 */
-	if ((chan->feature & FSL_DMA_IP_MASK) == FSL_DMA_IP_85XX) {
-		u32 mode;
-
-		mode = DMA_IN(chan, &chan->regs->mr, 32);
-		mode &= ~FSL_DMA_MR_CS;
-		DMA_OUT(chan, &chan->regs->mr, mode, 32);
-	}
-
-	/*
-	 * Program the descriptor's address into the DMA controller,
-	 * then start the DMA transaction
-	 */
-	set_cdar(chan, desc->async_tx.phys);
-	get_cdar(chan);
-
-	dma_start(chan);
-	chan->idle = false;
-}
-
-/**
  * fsl_dma_memcpy_issue_pending - Issue the DMA start command
  * @chan : Freescale DMA channel
  */
@@ -1304,12 +1286,10 @@ static int fsldma_of_probe(struct platform_device *op)
 	fdev->irq = irq_of_parse_and_map(op->dev.of_node, 0);
 
 	dma_cap_set(DMA_MEMCPY, fdev->common.cap_mask);
-	dma_cap_set(DMA_INTERRUPT, fdev->common.cap_mask);
 	dma_cap_set(DMA_SG, fdev->common.cap_mask);
 	dma_cap_set(DMA_SLAVE, fdev->common.cap_mask);
 	fdev->common.device_alloc_chan_resources = fsl_dma_alloc_chan_resources;
 	fdev->common.device_free_chan_resources = fsl_dma_free_chan_resources;
-	fdev->common.device_prep_dma_interrupt = fsl_dma_prep_interrupt;
 	fdev->common.device_prep_dma_memcpy = fsl_dma_prep_memcpy;
 	fdev->common.device_prep_dma_sg = fsl_dma_prep_sg;
 	fdev->common.device_tx_status = fsl_tx_status;
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 19041cefabb..14867e3ac8f 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -255,6 +255,7 @@ struct sdma_channel {
 	enum dma_slave_buswidth		word_size;
 	unsigned int			buf_tail;
 	unsigned int			num_bd;
+	unsigned int			period_len;
 	struct sdma_buffer_descriptor	*bd;
 	dma_addr_t			bd_phys;
 	unsigned int			pc_from_device, pc_to_device;
@@ -593,6 +594,12 @@ static void sdma_event_disable(struct sdma_channel *sdmac, unsigned int event)
 
 static void sdma_handle_channel_loop(struct sdma_channel *sdmac)
 {
+	if (sdmac->desc.callback)
+		sdmac->desc.callback(sdmac->desc.callback_param);
+}
+
+static void sdma_update_channel_loop(struct sdma_channel *sdmac)
+{
 	struct sdma_buffer_descriptor *bd;
 
 	/*
@@ -607,15 +614,10 @@ static void sdma_handle_channel_loop(struct sdma_channel *sdmac)
 
 		if (bd->mode.status & BD_RROR)
 			sdmac->status = DMA_ERROR;
-		else
-			sdmac->status = DMA_IN_PROGRESS;
 
 		bd->mode.status |= BD_DONE;
 		sdmac->buf_tail++;
 		sdmac->buf_tail %= sdmac->num_bd;
-
-		if (sdmac->desc.callback)
-			sdmac->desc.callback(sdmac->desc.callback_param);
 	}
 }
 
@@ -671,6 +673,9 @@ static irqreturn_t sdma_int_handler(int irq, void *dev_id)
 		int channel = fls(stat) - 1;
 		struct sdma_channel *sdmac = &sdma->channel[channel];
 
+		if (sdmac->flags & IMX_DMA_SG_LOOP)
+			sdma_update_channel_loop(sdmac);
+
 		tasklet_schedule(&sdmac->tasklet);
 
 		__clear_bit(channel, &stat);
@@ -1131,6 +1136,7 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic(
 	sdmac->status = DMA_IN_PROGRESS;
 
 	sdmac->buf_tail = 0;
+	sdmac->period_len = period_len;
 
 	sdmac->flags |= IMX_DMA_SG_LOOP;
 	sdmac->direction = direction;
@@ -1227,9 +1233,15 @@ static enum dma_status sdma_tx_status(struct dma_chan *chan,
 				      struct dma_tx_state *txstate)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
+	u32 residue;
+
+	if (sdmac->flags & IMX_DMA_SG_LOOP)
+		residue = (sdmac->num_bd - sdmac->buf_tail) * sdmac->period_len;
+	else
+		residue = sdmac->chn_count - sdmac->chn_real_count;
 
 	dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie,
-			sdmac->chn_count - sdmac->chn_real_count);
+			 residue);
 
 	return sdmac->status;
 }
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index bf02e7beb51..a7b186d536b 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -29,8 +29,8 @@
 #define DALGN		0x00a0
 #define DINT		0x00f0
 #define DDADR		0x0200
-#define DSADR		0x0204
-#define DTADR		0x0208
+#define DSADR(n)	(0x0204 + ((n) << 4))
+#define DTADR(n)	(0x0208 + ((n) << 4))
 #define DCMD		0x020c
 
 #define DCSR_RUN	BIT(31)	/* Run Bit (read / write) */
@@ -277,7 +277,7 @@ static void mmp_pdma_free_phy(struct mmp_pdma_chan *pchan)
 		return;
 
 	/* clear the channel mapping in DRCMR */
-	reg = DRCMR(pchan->phy->vchan->drcmr);
+	reg = DRCMR(pchan->drcmr);
 	writel(0, pchan->phy->base + reg);
 
 	spin_lock_irqsave(&pdev->phy_lock, flags);
@@ -748,11 +748,92 @@ static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 	return 0;
 }
 
+static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan,
+				     dma_cookie_t cookie)
+{
+	struct mmp_pdma_desc_sw *sw;
+	u32 curr, residue = 0;
+	bool passed = false;
+	bool cyclic = chan->cyclic_first != NULL;
+
+	/*
+	 * If the channel does not have a phy pointer anymore, it has already
+	 * been completed. Therefore, its residue is 0.
+	 */
+	if (!chan->phy)
+		return 0;
+
+	if (chan->dir == DMA_DEV_TO_MEM)
+		curr = readl(chan->phy->base + DTADR(chan->phy->idx));
+	else
+		curr = readl(chan->phy->base + DSADR(chan->phy->idx));
+
+	list_for_each_entry(sw, &chan->chain_running, node) {
+		u32 start, end, len;
+
+		if (chan->dir == DMA_DEV_TO_MEM)
+			start = sw->desc.dtadr;
+		else
+			start = sw->desc.dsadr;
+
+		len = sw->desc.dcmd & DCMD_LENGTH;
+		end = start + len;
+
+		/*
+		 * 'passed' will be latched once we found the descriptor which
+		 * lies inside the boundaries of the curr pointer. All
+		 * descriptors that occur in the list _after_ we found that
+		 * partially handled descriptor are still to be processed and
+		 * are hence added to the residual bytes counter.
+		 */
+
+		if (passed) {
+			residue += len;
+		} else if (curr >= start && curr <= end) {
+			residue += end - curr;
+			passed = true;
+		}
+
+		/*
+		 * Descriptors that have the ENDIRQEN bit set mark the end of a
+		 * transaction chain, and the cookie assigned with it has been
+		 * returned previously from mmp_pdma_tx_submit().
+		 *
+		 * In case we have multiple transactions in the running chain,
+		 * and the cookie does not match the one the user asked us
+		 * about, reset the state variables and start over.
+		 *
+		 * This logic does not apply to cyclic transactions, where all
+		 * descriptors have the ENDIRQEN bit set, and for which we
+		 * can't have multiple transactions on one channel anyway.
+		 */
+		if (cyclic || !(sw->desc.dcmd & DCMD_ENDIRQEN))
+			continue;
+
+		if (sw->async_tx.cookie == cookie) {
+			return residue;
+		} else {
+			residue = 0;
+			passed = false;
+		}
+	}
+
+	/* We should only get here in case of cyclic transactions */
+	return residue;
+}
+
 static enum dma_status mmp_pdma_tx_status(struct dma_chan *dchan,
 					  dma_cookie_t cookie,
 					  struct dma_tx_state *txstate)
 {
-	return dma_cookie_status(dchan, cookie, txstate);
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+	enum dma_status ret;
+
+	ret = dma_cookie_status(dchan, cookie, txstate);
+	if (likely(ret != DMA_ERROR))
+		dma_set_residue(txstate, mmp_pdma_residue(chan, cookie));
+
+	return ret;
 }
 
 /**
@@ -858,8 +939,7 @@ static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev, int idx, int irq)
 	struct mmp_pdma_chan *chan;
 	int ret;
 
-	chan = devm_kzalloc(pdev->dev, sizeof(struct mmp_pdma_chan),
-			    GFP_KERNEL);
+	chan = devm_kzalloc(pdev->dev, sizeof(*chan), GFP_KERNEL);
 	if (chan == NULL)
 		return -ENOMEM;
 
@@ -946,8 +1026,7 @@ static int mmp_pdma_probe(struct platform_device *op)
 			irq_num++;
 	}
 
-	pdev->phy = devm_kcalloc(pdev->dev,
-				 dma_channels, sizeof(struct mmp_pdma_chan),
+	pdev->phy = devm_kcalloc(pdev->dev, dma_channels, sizeof(*pdev->phy),
 				 GFP_KERNEL);
 	if (pdev->phy == NULL)
 		return -ENOMEM;
diff --git a/drivers/dma/mpc512x_dma.c b/drivers/dma/mpc512x_dma.c
index 448750da440..2ad43738ac8 100644
--- a/drivers/dma/mpc512x_dma.c
+++ b/drivers/dma/mpc512x_dma.c
@@ -2,6 +2,7 @@
  * Copyright (C) Freescale Semicondutor, Inc. 2007, 2008.
  * Copyright (C) Semihalf 2009
  * Copyright (C) Ilya Yanok, Emcraft Systems 2010
+ * Copyright (C) Alexander Popov, Promcontroller 2014
  *
  * Written by Piotr Ziecik <kosmo@semihalf.com>. Hardware description
  * (defines, structures and comments) was taken from MPC5121 DMA driver
@@ -29,8 +30,18 @@
  */
 
 /*
- * This is initial version of MPC5121 DMA driver. Only memory to memory
- * transfers are supported (tested using dmatest module).
+ * MPC512x and MPC8308 DMA driver. It supports
+ * memory to memory data transfers (tested using dmatest module) and
+ * data transfers between memory and peripheral I/O memory
+ * by means of slave scatter/gather with these limitations:
+ *  - chunked transfers (described by s/g lists with more than one item)
+ *     are refused as long as proper support for scatter/gather is missing;
+ *  - transfers on MPC8308 always start from software as this SoC appears
+ *     not to have external request lines for peripheral flow control;
+ *  - only peripheral devices with 4-byte FIFO access register are supported;
+ *  - minimal memory <-> I/O memory transfer chunk is 4 bytes and consequently
+ *     source and destination addresses must be 4-byte aligned
+ *     and transfer size must be aligned on (4 * maxburst) boundary;
  */
 
 #include <linux/module.h>
@@ -52,9 +63,17 @@
 #define MPC_DMA_DESCRIPTORS	64
 
 /* Macro definitions */
-#define MPC_DMA_CHANNELS	64
 #define MPC_DMA_TCD_OFFSET	0x1000
 
+/*
+ * Maximum channel counts for individual hardware variants
+ * and the maximum channel count over all supported controllers,
+ * used for data structure size
+ */
+#define MPC8308_DMACHAN_MAX	16
+#define MPC512x_DMACHAN_MAX	64
+#define MPC_DMA_CHANNELS	64
+
 /* Arbitration mode of group and channel */
 #define MPC_DMA_DMACR_EDCG	(1 << 31)
 #define MPC_DMA_DMACR_ERGA	(1 << 3)
@@ -181,6 +200,7 @@ struct mpc_dma_desc {
 	dma_addr_t			tcd_paddr;
 	int				error;
 	struct list_head		node;
+	int				will_access_peripheral;
 };
 
 struct mpc_dma_chan {
@@ -193,6 +213,12 @@ struct mpc_dma_chan {
 	struct mpc_dma_tcd		*tcd;
 	dma_addr_t			tcd_paddr;
 
+	/* Settings for access to peripheral FIFO */
+	dma_addr_t			src_per_paddr;
+	u32				src_tcd_nunits;
+	dma_addr_t			dst_per_paddr;
+	u32				dst_tcd_nunits;
+
 	/* Lock for this structure */
 	spinlock_t			lock;
 };
@@ -243,8 +269,23 @@ static void mpc_dma_execute(struct mpc_dma_chan *mchan)
 	struct mpc_dma_desc *mdesc;
 	int cid = mchan->chan.chan_id;
 
-	/* Move all queued descriptors to active list */
-	list_splice_tail_init(&mchan->queued, &mchan->active);
+	while (!list_empty(&mchan->queued)) {
+		mdesc = list_first_entry(&mchan->queued,
+						struct mpc_dma_desc, node);
+		/*
+		 * Grab either several mem-to-mem transfer descriptors
+		 * or one peripheral transfer descriptor,
+		 * don't mix mem-to-mem and peripheral transfer descriptors
+		 * within the same 'active' list.
+		 */
+		if (mdesc->will_access_peripheral) {
+			if (list_empty(&mchan->active))
+				list_move_tail(&mdesc->node, &mchan->active);
+			break;
+		} else {
+			list_move_tail(&mdesc->node, &mchan->active);
+		}
+	}
 
 	/* Chain descriptors into one transaction */
 	list_for_each_entry(mdesc, &mchan->active, node) {
@@ -270,7 +311,17 @@ static void mpc_dma_execute(struct mpc_dma_chan *mchan)
 
 	if (first != prev)
 		mdma->tcd[cid].e_sg = 1;
-	out_8(&mdma->regs->dmassrt, cid);
+
+	if (mdma->is_mpc8308) {
+		/* MPC8308, no request lines, software initiated start */
+		out_8(&mdma->regs->dmassrt, cid);
+	} else if (first->will_access_peripheral) {
+		/* Peripherals involved, start by external request signal */
+		out_8(&mdma->regs->dmaserq, cid);
+	} else {
+		/* Memory to memory transfer, software initiated start */
+		out_8(&mdma->regs->dmassrt, cid);
+	}
 }
 
 /* Handle interrupt on one half of DMA controller (32 channels) */
@@ -588,6 +639,7 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 	}
 
 	mdesc->error = 0;
+	mdesc->will_access_peripheral = 0;
 	tcd = mdesc->tcd;
 
 	/* Prepare Transfer Control Descriptor for this transaction */
@@ -635,6 +687,193 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 	return &mdesc->desc;
 }
 
+static struct dma_async_tx_descriptor *
+mpc_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+		unsigned int sg_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context)
+{
+	struct mpc_dma *mdma = dma_chan_to_mpc_dma(chan);
+	struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(chan);
+	struct mpc_dma_desc *mdesc = NULL;
+	dma_addr_t per_paddr;
+	u32 tcd_nunits;
+	struct mpc_dma_tcd *tcd;
+	unsigned long iflags;
+	struct scatterlist *sg;
+	size_t len;
+	int iter, i;
+
+	/* Currently there is no proper support for scatter/gather */
+	if (sg_len != 1)
+		return NULL;
+
+	if (!is_slave_direction(direction))
+		return NULL;
+
+	for_each_sg(sgl, sg, sg_len, i) {
+		spin_lock_irqsave(&mchan->lock, iflags);
+
+		mdesc = list_first_entry(&mchan->free,
+						struct mpc_dma_desc, node);
+		if (!mdesc) {
+			spin_unlock_irqrestore(&mchan->lock, iflags);
+			/* Try to free completed descriptors */
+			mpc_dma_process_completed(mdma);
+			return NULL;
+		}
+
+		list_del(&mdesc->node);
+
+		if (direction == DMA_DEV_TO_MEM) {
+			per_paddr = mchan->src_per_paddr;
+			tcd_nunits = mchan->src_tcd_nunits;
+		} else {
+			per_paddr = mchan->dst_per_paddr;
+			tcd_nunits = mchan->dst_tcd_nunits;
+		}
+
+		spin_unlock_irqrestore(&mchan->lock, iflags);
+
+		if (per_paddr == 0 || tcd_nunits == 0)
+			goto err_prep;
+
+		mdesc->error = 0;
+		mdesc->will_access_peripheral = 1;
+
+		/* Prepare Transfer Control Descriptor for this transaction */
+		tcd = mdesc->tcd;
+
+		memset(tcd, 0, sizeof(struct mpc_dma_tcd));
+
+		if (!IS_ALIGNED(sg_dma_address(sg), 4))
+			goto err_prep;
+
+		if (direction == DMA_DEV_TO_MEM) {
+			tcd->saddr = per_paddr;
+			tcd->daddr = sg_dma_address(sg);
+			tcd->soff = 0;
+			tcd->doff = 4;
+		} else {
+			tcd->saddr = sg_dma_address(sg);
+			tcd->daddr = per_paddr;
+			tcd->soff = 4;
+			tcd->doff = 0;
+		}
+
+		tcd->ssize = MPC_DMA_TSIZE_4;
+		tcd->dsize = MPC_DMA_TSIZE_4;
+
+		len = sg_dma_len(sg);
+		tcd->nbytes = tcd_nunits * 4;
+		if (!IS_ALIGNED(len, tcd->nbytes))
+			goto err_prep;
+
+		iter = len / tcd->nbytes;
+		if (iter >= 1 << 15) {
+			/* len is too big */
+			goto err_prep;
+		}
+		/* citer_linkch contains the high bits of iter */
+		tcd->biter = iter & 0x1ff;
+		tcd->biter_linkch = iter >> 9;
+		tcd->citer = tcd->biter;
+		tcd->citer_linkch = tcd->biter_linkch;
+
+		tcd->e_sg = 0;
+		tcd->d_req = 1;
+
+		/* Place descriptor in prepared list */
+		spin_lock_irqsave(&mchan->lock, iflags);
+		list_add_tail(&mdesc->node, &mchan->prepared);
+		spin_unlock_irqrestore(&mchan->lock, iflags);
+	}
+
+	return &mdesc->desc;
+
+err_prep:
+	/* Put the descriptor back */
+	spin_lock_irqsave(&mchan->lock, iflags);
+	list_add_tail(&mdesc->node, &mchan->free);
+	spin_unlock_irqrestore(&mchan->lock, iflags);
+
+	return NULL;
+}
+
+static int mpc_dma_device_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+							unsigned long arg)
+{
+	struct mpc_dma_chan *mchan;
+	struct mpc_dma *mdma;
+	struct dma_slave_config *cfg;
+	unsigned long flags;
+
+	mchan = dma_chan_to_mpc_dma_chan(chan);
+	switch (cmd) {
+	case DMA_TERMINATE_ALL:
+		/* Disable channel requests */
+		mdma = dma_chan_to_mpc_dma(chan);
+
+		spin_lock_irqsave(&mchan->lock, flags);
+
+		out_8(&mdma->regs->dmacerq, chan->chan_id);
+		list_splice_tail_init(&mchan->prepared, &mchan->free);
+		list_splice_tail_init(&mchan->queued, &mchan->free);
+		list_splice_tail_init(&mchan->active, &mchan->free);
+
+		spin_unlock_irqrestore(&mchan->lock, flags);
+
+		return 0;
+
+	case DMA_SLAVE_CONFIG:
+		/*
+		 * Software constraints:
+		 *  - only transfers between a peripheral device and
+		 *     memory are supported;
+		 *  - only peripheral devices with 4-byte FIFO access register
+		 *     are supported;
+		 *  - minimal transfer chunk is 4 bytes and consequently
+		 *     source and destination addresses must be 4-byte aligned
+		 *     and transfer size must be aligned on (4 * maxburst)
+		 *     boundary;
+		 *  - during the transfer RAM address is being incremented by
+		 *     the size of minimal transfer chunk;
+		 *  - peripheral port's address is constant during the transfer.
+		 */
+
+		cfg = (void *)arg;
+
+		if (cfg->src_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES ||
+		    cfg->dst_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES ||
+		    !IS_ALIGNED(cfg->src_addr, 4) ||
+		    !IS_ALIGNED(cfg->dst_addr, 4)) {
+			return -EINVAL;
+		}
+
+		spin_lock_irqsave(&mchan->lock, flags);
+
+		mchan->src_per_paddr = cfg->src_addr;
+		mchan->src_tcd_nunits = cfg->src_maxburst;
+		mchan->dst_per_paddr = cfg->dst_addr;
+		mchan->dst_tcd_nunits = cfg->dst_maxburst;
+
+		/* Apply defaults */
+		if (mchan->src_tcd_nunits == 0)
+			mchan->src_tcd_nunits = 1;
+		if (mchan->dst_tcd_nunits == 0)
+			mchan->dst_tcd_nunits = 1;
+
+		spin_unlock_irqrestore(&mchan->lock, flags);
+
+		return 0;
+
+	default:
+		/* Unknown command */
+		break;
+	}
+
+	return -ENXIO;
+}
+
 static int mpc_dma_probe(struct platform_device *op)
 {
 	struct device_node *dn = op->dev.of_node;
@@ -649,13 +888,15 @@ static int mpc_dma_probe(struct platform_device *op)
 	mdma = devm_kzalloc(dev, sizeof(struct mpc_dma), GFP_KERNEL);
 	if (!mdma) {
 		dev_err(dev, "Memory exhausted!\n");
-		return -ENOMEM;
+		retval = -ENOMEM;
+		goto err;
 	}
 
 	mdma->irq = irq_of_parse_and_map(dn, 0);
 	if (mdma->irq == NO_IRQ) {
 		dev_err(dev, "Error mapping IRQ!\n");
-		return -EINVAL;
+		retval = -EINVAL;
+		goto err;
 	}
 
 	if (of_device_is_compatible(dn, "fsl,mpc8308-dma")) {
@@ -663,14 +904,15 @@ static int mpc_dma_probe(struct platform_device *op)
 		mdma->irq2 = irq_of_parse_and_map(dn, 1);
 		if (mdma->irq2 == NO_IRQ) {
 			dev_err(dev, "Error mapping IRQ!\n");
-			return -EINVAL;
+			retval = -EINVAL;
+			goto err_dispose1;
 		}
 	}
 
 	retval = of_address_to_resource(dn, 0, &res);
 	if (retval) {
 		dev_err(dev, "Error parsing memory region!\n");
-		return retval;
+		goto err_dispose2;
 	}
 
 	regs_start = res.start;
@@ -678,31 +920,34 @@ static int mpc_dma_probe(struct platform_device *op)
 
 	if (!devm_request_mem_region(dev, regs_start, regs_size, DRV_NAME)) {
 		dev_err(dev, "Error requesting memory region!\n");
-		return -EBUSY;
+		retval = -EBUSY;
+		goto err_dispose2;
 	}
 
 	mdma->regs = devm_ioremap(dev, regs_start, regs_size);
 	if (!mdma->regs) {
 		dev_err(dev, "Error mapping memory region!\n");
-		return -ENOMEM;
+		retval = -ENOMEM;
+		goto err_dispose2;
 	}
 
 	mdma->tcd = (struct mpc_dma_tcd *)((u8 *)(mdma->regs)
 							+ MPC_DMA_TCD_OFFSET);
 
-	retval = devm_request_irq(dev, mdma->irq, &mpc_dma_irq, 0, DRV_NAME,
-									mdma);
+	retval = request_irq(mdma->irq, &mpc_dma_irq, 0, DRV_NAME, mdma);
 	if (retval) {
 		dev_err(dev, "Error requesting IRQ!\n");
-		return -EINVAL;
+		retval = -EINVAL;
+		goto err_dispose2;
 	}
 
 	if (mdma->is_mpc8308) {
-		retval = devm_request_irq(dev, mdma->irq2, &mpc_dma_irq, 0,
-				DRV_NAME, mdma);
+		retval = request_irq(mdma->irq2, &mpc_dma_irq, 0,
+							DRV_NAME, mdma);
 		if (retval) {
 			dev_err(dev, "Error requesting IRQ2!\n");
-			return -EINVAL;
+			retval = -EINVAL;
+			goto err_free1;
 		}
 	}
 
@@ -710,18 +955,21 @@ static int mpc_dma_probe(struct platform_device *op)
 
 	dma = &mdma->dma;
 	dma->dev = dev;
-	if (!mdma->is_mpc8308)
-		dma->chancnt = MPC_DMA_CHANNELS;
+	if (mdma->is_mpc8308)
+		dma->chancnt = MPC8308_DMACHAN_MAX;
 	else
-		dma->chancnt = 16; /* MPC8308 DMA has only 16 channels */
+		dma->chancnt = MPC512x_DMACHAN_MAX;
 	dma->device_alloc_chan_resources = mpc_dma_alloc_chan_resources;
 	dma->device_free_chan_resources = mpc_dma_free_chan_resources;
 	dma->device_issue_pending = mpc_dma_issue_pending;
 	dma->device_tx_status = mpc_dma_tx_status;
 	dma->device_prep_dma_memcpy = mpc_dma_prep_memcpy;
+	dma->device_prep_slave_sg = mpc_dma_prep_slave_sg;
+	dma->device_control = mpc_dma_device_control;
 
 	INIT_LIST_HEAD(&dma->channels);
 	dma_cap_set(DMA_MEMCPY, dma->cap_mask);
+	dma_cap_set(DMA_SLAVE, dma->cap_mask);
 
 	for (i = 0; i < dma->chancnt; i++) {
 		mchan = &mdma->channels[i];
@@ -747,7 +995,19 @@ static int mpc_dma_probe(struct platform_device *op)
 	 * - Round-robin group arbitration,
 	 * - Round-robin channel arbitration.
 	 */
-	if (!mdma->is_mpc8308) {
+	if (mdma->is_mpc8308) {
+		/* MPC8308 has 16 channels and lacks some registers */
+		out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_ERCA);
+
+		/* enable snooping */
+		out_be32(&mdma->regs->dmagpor, MPC_DMA_DMAGPOR_SNOOP_ENABLE);
+		/* Disable error interrupts */
+		out_be32(&mdma->regs->dmaeeil, 0);
+
+		/* Clear interrupts status */
+		out_be32(&mdma->regs->dmaintl, 0xFFFF);
+		out_be32(&mdma->regs->dmaerrl, 0xFFFF);
+	} else {
 		out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_EDCG |
 					MPC_DMA_DMACR_ERGA | MPC_DMA_DMACR_ERCA);
 
@@ -768,29 +1028,28 @@ static int mpc_dma_probe(struct platform_device *op)
 		/* Route interrupts to IPIC */
 		out_be32(&mdma->regs->dmaihsa, 0);
 		out_be32(&mdma->regs->dmailsa, 0);
-	} else {
-		/* MPC8308 has 16 channels and lacks some registers */
-		out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_ERCA);
-
-		/* enable snooping */
-		out_be32(&mdma->regs->dmagpor, MPC_DMA_DMAGPOR_SNOOP_ENABLE);
-		/* Disable error interrupts */
-		out_be32(&mdma->regs->dmaeeil, 0);
-
-		/* Clear interrupts status */
-		out_be32(&mdma->regs->dmaintl, 0xFFFF);
-		out_be32(&mdma->regs->dmaerrl, 0xFFFF);
 	}
 
 	/* Register DMA engine */
 	dev_set_drvdata(dev, mdma);
 	retval = dma_async_device_register(dma);
-	if (retval) {
-		devm_free_irq(dev, mdma->irq, mdma);
-		irq_dispose_mapping(mdma->irq);
-	}
+	if (retval)
+		goto err_free2;
 
 	return retval;
+
+err_free2:
+	if (mdma->is_mpc8308)
+		free_irq(mdma->irq2, mdma);
+err_free1:
+	free_irq(mdma->irq, mdma);
+err_dispose2:
+	if (mdma->is_mpc8308)
+		irq_dispose_mapping(mdma->irq2);
+err_dispose1:
+	irq_dispose_mapping(mdma->irq);
+err:
+	return retval;
 }
 
 static int mpc_dma_remove(struct platform_device *op)
@@ -799,7 +1058,11 @@ static int mpc_dma_remove(struct platform_device *op)
 	struct mpc_dma *mdma = dev_get_drvdata(dev);
 
 	dma_async_device_unregister(&mdma->dma);
-	devm_free_irq(dev, mdma->irq, mdma);
+	if (mdma->is_mpc8308) {
+		free_irq(mdma->irq2, mdma);
+		irq_dispose_mapping(mdma->irq2);
+	}
+	free_irq(mdma->irq, mdma);
 	irq_dispose_mapping(mdma->irq);
 
 	return 0;
@@ -807,6 +1070,7 @@ static int mpc_dma_remove(struct platform_device *op)
 
 static struct of_device_id mpc_dma_match[] = {
 	{ .compatible = "fsl,mpc5121-dma", },
+	{ .compatible = "fsl,mpc8308-dma", },
 	{},
 };
 
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 05fa548bd65..9f9ca9fe5ce 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -21,6 +21,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/pch_dma.h>
@@ -996,7 +997,7 @@ static void pch_dma_remove(struct pci_dev *pdev)
 #define PCI_DEVICE_ID_ML7831_DMA1_8CH	0x8810
 #define PCI_DEVICE_ID_ML7831_DMA2_4CH	0x8815
 
-DEFINE_PCI_DEVICE_TABLE(pch_dma_id_table) = {
+const struct pci_device_id pch_dma_id_table[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_8CH), 8 },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_4CH), 4 },
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA1_8CH), 8}, /* UART Video */
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
index b209a0f1734..012520c9fd7 100644
--- a/drivers/dma/s3c24xx-dma.c
+++ b/drivers/dma/s3c24xx-dma.c
@@ -164,6 +164,7 @@ struct s3c24xx_sg {
  * @disrcc: value for source control register
  * @didstc: value for destination control register
  * @dcon: base value for dcon register
+ * @cyclic: indicate cyclic transfer
  */
 struct s3c24xx_txd {
 	struct virt_dma_desc vd;
@@ -173,6 +174,7 @@ struct s3c24xx_txd {
 	u32 disrcc;
 	u32 didstc;
 	u32 dcon;
+	bool cyclic;
 };
 
 struct s3c24xx_dma_chan;
@@ -669,8 +671,10 @@ static irqreturn_t s3c24xx_dma_irq(int irq, void *data)
 		/* when more sg's are in this txd, start the next one */
 		if (!list_is_last(txd->at, &txd->dsg_list)) {
 			txd->at = txd->at->next;
+			if (txd->cyclic)
+				vchan_cyclic_callback(&txd->vd);
 			s3c24xx_dma_start_next_sg(s3cchan, txd);
-		} else {
+		} else if (!txd->cyclic) {
 			s3cchan->at = NULL;
 			vchan_cookie_complete(&txd->vd);
 
@@ -682,6 +686,12 @@ static irqreturn_t s3c24xx_dma_irq(int irq, void *data)
 				s3c24xx_dma_start_next_txd(s3cchan);
 			else
 				s3c24xx_dma_phy_free(s3cchan);
+		} else {
+			vchan_cyclic_callback(&txd->vd);
+
+			/* Cyclic: reset at beginning */
+			txd->at = txd->dsg_list.next;
+			s3c24xx_dma_start_next_sg(s3cchan, txd);
 		}
 	}
 	spin_unlock(&s3cchan->vc.lock);
@@ -877,6 +887,104 @@ static struct dma_async_tx_descriptor *s3c24xx_dma_prep_memcpy(
 	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
 }
 
+static struct dma_async_tx_descriptor *s3c24xx_dma_prep_dma_cyclic(
+	struct dma_chan *chan, dma_addr_t addr, size_t size, size_t period,
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
+{
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
+	struct s3c24xx_dma_channel *cdata = &pdata->channels[s3cchan->id];
+	struct s3c24xx_txd *txd;
+	struct s3c24xx_sg *dsg;
+	unsigned sg_len;
+	dma_addr_t slave_addr;
+	u32 hwcfg = 0;
+	int i;
+
+	dev_dbg(&s3cdma->pdev->dev,
+		"prepare cyclic transaction of %zu bytes with period %zu from %s\n",
+		size, period, s3cchan->name);
+
+	if (!is_slave_direction(direction)) {
+		dev_err(&s3cdma->pdev->dev,
+			"direction %d unsupported\n", direction);
+		return NULL;
+	}
+
+	txd = s3c24xx_dma_get_txd();
+	if (!txd)
+		return NULL;
+
+	txd->cyclic = 1;
+
+	if (cdata->handshake)
+		txd->dcon |= S3C24XX_DCON_HANDSHAKE;
+
+	switch (cdata->bus) {
+	case S3C24XX_DMA_APB:
+		txd->dcon |= S3C24XX_DCON_SYNC_PCLK;
+		hwcfg |= S3C24XX_DISRCC_LOC_APB;
+		break;
+	case S3C24XX_DMA_AHB:
+		txd->dcon |= S3C24XX_DCON_SYNC_HCLK;
+		hwcfg |= S3C24XX_DISRCC_LOC_AHB;
+		break;
+	}
+
+	/*
+	 * Always assume our peripheral desintation is a fixed
+	 * address in memory.
+	 */
+	hwcfg |= S3C24XX_DISRCC_INC_FIXED;
+
+	/*
+	 * Individual dma operations are requested by the slave,
+	 * so serve only single atomic operations (S3C24XX_DCON_SERV_SINGLE).
+	 */
+	txd->dcon |= S3C24XX_DCON_SERV_SINGLE;
+
+	if (direction == DMA_MEM_TO_DEV) {
+		txd->disrcc = S3C24XX_DISRCC_LOC_AHB |
+			      S3C24XX_DISRCC_INC_INCREMENT;
+		txd->didstc = hwcfg;
+		slave_addr = s3cchan->cfg.dst_addr;
+		txd->width = s3cchan->cfg.dst_addr_width;
+	} else {
+		txd->disrcc = hwcfg;
+		txd->didstc = S3C24XX_DIDSTC_LOC_AHB |
+			      S3C24XX_DIDSTC_INC_INCREMENT;
+		slave_addr = s3cchan->cfg.src_addr;
+		txd->width = s3cchan->cfg.src_addr_width;
+	}
+
+	sg_len = size / period;
+
+	for (i = 0; i < sg_len; i++) {
+		dsg = kzalloc(sizeof(*dsg), GFP_NOWAIT);
+		if (!dsg) {
+			s3c24xx_dma_free_txd(txd);
+			return NULL;
+		}
+		list_add_tail(&dsg->node, &txd->dsg_list);
+
+		dsg->len = period;
+		/* Check last period length */
+		if (i == sg_len - 1)
+			dsg->len = size - period * i;
+		if (direction == DMA_MEM_TO_DEV) {
+			dsg->src_addr = addr + period * i;
+			dsg->dst_addr = slave_addr;
+		} else { /* DMA_DEV_TO_MEM */
+			dsg->src_addr = slave_addr;
+			dsg->dst_addr = addr + period * i;
+		}
+	}
+
+	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
+}
+
 static struct dma_async_tx_descriptor *s3c24xx_dma_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
@@ -961,7 +1069,6 @@ static struct dma_async_tx_descriptor *s3c24xx_dma_prep_slave_sg(
 			dsg->src_addr = slave_addr;
 			dsg->dst_addr = sg_dma_address(sg);
 		}
-		break;
 	}
 
 	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
@@ -1198,6 +1305,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 
 	/* Initialize slave engine for SoC internal dedicated peripherals */
 	dma_cap_set(DMA_SLAVE, s3cdma->slave.cap_mask);
+	dma_cap_set(DMA_CYCLIC, s3cdma->slave.cap_mask);
 	dma_cap_set(DMA_PRIVATE, s3cdma->slave.cap_mask);
 	s3cdma->slave.dev = &pdev->dev;
 	s3cdma->slave.device_alloc_chan_resources =
@@ -1207,6 +1315,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 	s3cdma->slave.device_tx_status = s3c24xx_dma_tx_status;
 	s3cdma->slave.device_issue_pending = s3c24xx_dma_issue_pending;
 	s3cdma->slave.device_prep_slave_sg = s3c24xx_dma_prep_slave_sg;
+	s3cdma->slave.device_prep_dma_cyclic = s3c24xx_dma_prep_dma_cyclic;
 	s3cdma->slave.device_control = s3c24xx_dma_control;
 
 	/* Register as many memcpy channels as there are physical channels */
diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index b4c81383100..0f719816c91 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -4,7 +4,7 @@
 
 config SH_DMAE_BASE
 	bool "Renesas SuperH DMA Engine support"
-	depends on (SUPERH && SH_DMA) || (ARM && ARCH_SHMOBILE)
+	depends on (SUPERH && SH_DMA) || ARCH_SHMOBILE || COMPILE_TEST
 	depends on !SH_DMA_API
 	default y
 	select DMA_ENGINE
diff --git a/drivers/dma/sh/rcar-hpbdma.c b/drivers/dma/sh/rcar-hpbdma.c
index 3083d901a41..b212d9471ab 100644
--- a/drivers/dma/sh/rcar-hpbdma.c
+++ b/drivers/dma/sh/rcar-hpbdma.c
@@ -18,6 +18,7 @@
 
 #include <linux/dmaengine.h>
 #include <linux/delay.h>
+#include <linux/err.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index 52396771acb..b35007e21e6 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -73,8 +73,7 @@ static void shdma_chan_xfer_ld_queue(struct shdma_chan *schan)
 static dma_cookie_t shdma_tx_submit(struct dma_async_tx_descriptor *tx)
 {
 	struct shdma_desc *chunk, *c, *desc =
-		container_of(tx, struct shdma_desc, async_tx),
-		*last = desc;
+		container_of(tx, struct shdma_desc, async_tx);
 	struct shdma_chan *schan = to_shdma_chan(tx->chan);
 	dma_async_tx_callback callback = tx->callback;
 	dma_cookie_t cookie;
@@ -98,19 +97,20 @@ static dma_cookie_t shdma_tx_submit(struct dma_async_tx_descriptor *tx)
 				      &chunk->node == &schan->ld_free))
 			break;
 		chunk->mark = DESC_SUBMITTED;
-		/* Callback goes to the last chunk */
-		chunk->async_tx.callback = NULL;
+		if (chunk->chunks == 1) {
+			chunk->async_tx.callback = callback;
+			chunk->async_tx.callback_param = tx->callback_param;
+		} else {
+			/* Callback goes to the last chunk */
+			chunk->async_tx.callback = NULL;
+		}
 		chunk->cookie = cookie;
 		list_move_tail(&chunk->node, &schan->ld_queue);
-		last = chunk;
 
 		dev_dbg(schan->dev, "submit #%d@%p on %d\n",
-			tx->cookie, &last->async_tx, schan->id);
+			tx->cookie, &chunk->async_tx, schan->id);
 	}
 
-	last->async_tx.callback = callback;
-	last->async_tx.callback_param = tx->callback_param;
-
 	if (power_up) {
 		int ret;
 		schan->pm_state = SHDMA_PM_BUSY;
@@ -304,6 +304,7 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 	dma_async_tx_callback callback = NULL;
 	void *param = NULL;
 	unsigned long flags;
+	LIST_HEAD(cyclic_list);
 
 	spin_lock_irqsave(&schan->chan_lock, flags);
 	list_for_each_entry_safe(desc, _desc, &schan->ld_queue, node) {
@@ -369,10 +370,16 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 		if (((desc->mark == DESC_COMPLETED ||
 		      desc->mark == DESC_WAITING) &&
 		     async_tx_test_ack(&desc->async_tx)) || all) {
-			/* Remove from ld_queue list */
-			desc->mark = DESC_IDLE;
 
-			list_move(&desc->node, &schan->ld_free);
+			if (all || !desc->cyclic) {
+				/* Remove from ld_queue list */
+				desc->mark = DESC_IDLE;
+				list_move(&desc->node, &schan->ld_free);
+			} else {
+				/* reuse as cyclic */
+				desc->mark = DESC_SUBMITTED;
+				list_move_tail(&desc->node, &cyclic_list);
+			}
 
 			if (list_empty(&schan->ld_queue)) {
 				dev_dbg(schan->dev, "Bring down channel %d\n", schan->id);
@@ -389,6 +396,8 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 		 */
 		schan->dma_chan.completed_cookie = schan->dma_chan.cookie;
 
+	list_splice_tail(&cyclic_list, &schan->ld_queue);
+
 	spin_unlock_irqrestore(&schan->chan_lock, flags);
 
 	if (callback)
@@ -521,7 +530,7 @@ static struct shdma_desc *shdma_add_desc(struct shdma_chan *schan,
  */
 static struct dma_async_tx_descriptor *shdma_prep_sg(struct shdma_chan *schan,
 	struct scatterlist *sgl, unsigned int sg_len, dma_addr_t *addr,
-	enum dma_transfer_direction direction, unsigned long flags)
+	enum dma_transfer_direction direction, unsigned long flags, bool cyclic)
 {
 	struct scatterlist *sg;
 	struct shdma_desc *first = NULL, *new = NULL /* compiler... */;
@@ -569,7 +578,11 @@ static struct dma_async_tx_descriptor *shdma_prep_sg(struct shdma_chan *schan,
 			if (!new)
 				goto err_get_desc;
 
-			new->chunks = chunks--;
+			new->cyclic = cyclic;
+			if (cyclic)
+				new->chunks = 1;
+			else
+				new->chunks = chunks--;
 			list_add_tail(&new->node, &tx_list);
 		} while (len);
 	}
@@ -612,7 +625,8 @@ static struct dma_async_tx_descriptor *shdma_prep_memcpy(
 	sg_dma_address(&sg) = dma_src;
 	sg_dma_len(&sg) = len;
 
-	return shdma_prep_sg(schan, &sg, 1, &dma_dest, DMA_MEM_TO_MEM, flags);
+	return shdma_prep_sg(schan, &sg, 1, &dma_dest, DMA_MEM_TO_MEM,
+			     flags, false);
 }
 
 static struct dma_async_tx_descriptor *shdma_prep_slave_sg(
@@ -640,7 +654,58 @@ static struct dma_async_tx_descriptor *shdma_prep_slave_sg(
 	slave_addr = ops->slave_addr(schan);
 
 	return shdma_prep_sg(schan, sgl, sg_len, &slave_addr,
-			      direction, flags);
+			     direction, flags, false);
+}
+
+#define SHDMA_MAX_SG_LEN 32
+
+static struct dma_async_tx_descriptor *shdma_prep_dma_cyclic(
+	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, enum dma_transfer_direction direction,
+	unsigned long flags, void *context)
+{
+	struct shdma_chan *schan = to_shdma_chan(chan);
+	struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device);
+	const struct shdma_ops *ops = sdev->ops;
+	unsigned int sg_len = buf_len / period_len;
+	int slave_id = schan->slave_id;
+	dma_addr_t slave_addr;
+	struct scatterlist sgl[SHDMA_MAX_SG_LEN];
+	int i;
+
+	if (!chan)
+		return NULL;
+
+	BUG_ON(!schan->desc_num);
+
+	if (sg_len > SHDMA_MAX_SG_LEN) {
+		dev_err(schan->dev, "sg length %d exceds limit %d",
+				sg_len, SHDMA_MAX_SG_LEN);
+		return NULL;
+	}
+
+	/* Someone calling slave DMA on a generic channel? */
+	if (slave_id < 0 || (buf_len < period_len)) {
+		dev_warn(schan->dev,
+			"%s: bad parameter: buf_len=%zu, period_len=%zu, id=%d\n",
+			__func__, buf_len, period_len, slave_id);
+		return NULL;
+	}
+
+	slave_addr = ops->slave_addr(schan);
+
+	sg_init_table(sgl, sg_len);
+	for (i = 0; i < sg_len; i++) {
+		dma_addr_t src = buf_addr + (period_len * i);
+
+		sg_set_page(&sgl[i], pfn_to_page(PFN_DOWN(src)), period_len,
+			    offset_in_page(src));
+		sg_dma_address(&sgl[i]) = src;
+		sg_dma_len(&sgl[i]) = period_len;
+	}
+
+	return shdma_prep_sg(schan, sgl, sg_len, &slave_addr,
+			     direction, flags, true);
 }
 
 static int shdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
@@ -915,6 +980,7 @@ int shdma_init(struct device *dev, struct shdma_dev *sdev,
 
 	/* Compulsory for DMA_SLAVE fields */
 	dma_dev->device_prep_slave_sg = shdma_prep_slave_sg;
+	dma_dev->device_prep_dma_cyclic = shdma_prep_dma_cyclic;
 	dma_dev->device_control = shdma_control;
 
 	dma_dev->dev = dev;
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index dda7e7563f5..146d5df926d 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -18,21 +18,22 @@
  *
  */
 
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/err.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kdebug.h>
 #include <linux/module.h>
+#include <linux/notifier.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/dmaengine.h>
-#include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/rculist.h>
 #include <linux/sh_dma.h>
-#include <linux/notifier.h>
-#include <linux/kdebug.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/rculist.h>
 
 #include "../dmaengine.h"
 #include "shdma.h"
diff --git a/drivers/dma/sh/sudmac.c b/drivers/dma/sh/sudmac.c
index 4e7df43b50d..3ce10390989 100644
--- a/drivers/dma/sh/sudmac.c
+++ b/drivers/dma/sh/sudmac.c
@@ -14,12 +14,13 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/dmaengine.h>
+#include <linux/err.h>
 #include <linux/init.h>
-#include <linux/module.h>
-#include <linux/slab.h>
 #include <linux/interrupt.h>
-#include <linux/dmaengine.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 #include <linux/sudmac.h>
 
 struct sudmac_chan {
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index bf18c786ed4..c7984459ede 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -556,7 +556,6 @@ struct d40_gen_dmac {
  * later
  * @reg_val_backup_chan: Backup data for standard channel parameter registers.
  * @gcc_pwr_off_mask: Mask to maintain the channels that can be turned off.
- * @initialized: true if the dma has been initialized
  * @gen_dmac: the struct for generic registers values to represent u8500/8540
  * DMA controller
  */
@@ -594,7 +593,6 @@ struct d40_base {
 	u32				  reg_val_backup_v4[BACKUP_REGS_SZ_MAX];
 	u32				 *reg_val_backup_chan;
 	u16				  gcc_pwr_off_mask;
-	bool				  initialized;
 	struct d40_gen_dmac		  gen_dmac;
 };
 
@@ -1056,62 +1054,6 @@ static int d40_sg_2_dmalen(struct scatterlist *sgl, int sg_len,
 	return len;
 }
 
-
-#ifdef CONFIG_PM
-static void dma40_backup(void __iomem *baseaddr, u32 *backup,
-			 u32 *regaddr, int num, bool save)
-{
-	int i;
-
-	for (i = 0; i < num; i++) {
-		void __iomem *addr = baseaddr + regaddr[i];
-
-		if (save)
-			backup[i] = readl_relaxed(addr);
-		else
-			writel_relaxed(backup[i], addr);
-	}
-}
-
-static void d40_save_restore_registers(struct d40_base *base, bool save)
-{
-	int i;
-
-	/* Save/Restore channel specific registers */
-	for (i = 0; i < base->num_phy_chans; i++) {
-		void __iomem *addr;
-		int idx;
-
-		if (base->phy_res[i].reserved)
-			continue;
-
-		addr = base->virtbase + D40_DREG_PCBASE + i * D40_DREG_PCDELTA;
-		idx = i * ARRAY_SIZE(d40_backup_regs_chan);
-
-		dma40_backup(addr, &base->reg_val_backup_chan[idx],
-			     d40_backup_regs_chan,
-			     ARRAY_SIZE(d40_backup_regs_chan),
-			     save);
-	}
-
-	/* Save/Restore global registers */
-	dma40_backup(base->virtbase, base->reg_val_backup,
-		     d40_backup_regs, ARRAY_SIZE(d40_backup_regs),
-		     save);
-
-	/* Save/Restore registers only existing on dma40 v3 and later */
-	if (base->gen_dmac.backup)
-		dma40_backup(base->virtbase, base->reg_val_backup_v4,
-			     base->gen_dmac.backup,
-			base->gen_dmac.backup_size,
-			save);
-}
-#else
-static void d40_save_restore_registers(struct d40_base *base, bool save)
-{
-}
-#endif
-
 static int __d40_execute_command_phy(struct d40_chan *d40c,
 				     enum d40_command command)
 {
@@ -1495,8 +1437,8 @@ static int d40_pause(struct d40_chan *d40c)
 	if (!d40c->busy)
 		return 0;
 
-	pm_runtime_get_sync(d40c->base->dev);
 	spin_lock_irqsave(&d40c->lock, flags);
+	pm_runtime_get_sync(d40c->base->dev);
 
 	res = d40_channel_execute_command(d40c, D40_DMA_SUSPEND_REQ);
 
@@ -2998,18 +2940,88 @@ failure1:
 }
 
 /* Suspend resume functionality */
-#ifdef CONFIG_PM
-static int dma40_pm_suspend(struct device *dev)
+#ifdef CONFIG_PM_SLEEP
+static int dma40_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct d40_base *base = platform_get_drvdata(pdev);
-	int ret = 0;
+	int ret;
+
+	ret = pm_runtime_force_suspend(dev);
+	if (ret)
+		return ret;
 
 	if (base->lcpa_regulator)
 		ret = regulator_disable(base->lcpa_regulator);
 	return ret;
 }
 
+static int dma40_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct d40_base *base = platform_get_drvdata(pdev);
+	int ret = 0;
+
+	if (base->lcpa_regulator) {
+		ret = regulator_enable(base->lcpa_regulator);
+		if (ret)
+			return ret;
+	}
+
+	return pm_runtime_force_resume(dev);
+}
+#endif
+
+#ifdef CONFIG_PM
+static void dma40_backup(void __iomem *baseaddr, u32 *backup,
+			 u32 *regaddr, int num, bool save)
+{
+	int i;
+
+	for (i = 0; i < num; i++) {
+		void __iomem *addr = baseaddr + regaddr[i];
+
+		if (save)
+			backup[i] = readl_relaxed(addr);
+		else
+			writel_relaxed(backup[i], addr);
+	}
+}
+
+static void d40_save_restore_registers(struct d40_base *base, bool save)
+{
+	int i;
+
+	/* Save/Restore channel specific registers */
+	for (i = 0; i < base->num_phy_chans; i++) {
+		void __iomem *addr;
+		int idx;
+
+		if (base->phy_res[i].reserved)
+			continue;
+
+		addr = base->virtbase + D40_DREG_PCBASE + i * D40_DREG_PCDELTA;
+		idx = i * ARRAY_SIZE(d40_backup_regs_chan);
+
+		dma40_backup(addr, &base->reg_val_backup_chan[idx],
+			     d40_backup_regs_chan,
+			     ARRAY_SIZE(d40_backup_regs_chan),
+			     save);
+	}
+
+	/* Save/Restore global registers */
+	dma40_backup(base->virtbase, base->reg_val_backup,
+		     d40_backup_regs, ARRAY_SIZE(d40_backup_regs),
+		     save);
+
+	/* Save/Restore registers only existing on dma40 v3 and later */
+	if (base->gen_dmac.backup)
+		dma40_backup(base->virtbase, base->reg_val_backup_v4,
+			     base->gen_dmac.backup,
+			base->gen_dmac.backup_size,
+			save);
+}
+
 static int dma40_runtime_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -3030,36 +3042,20 @@ static int dma40_runtime_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct d40_base *base = platform_get_drvdata(pdev);
 
-	if (base->initialized)
-		d40_save_restore_registers(base, false);
+	d40_save_restore_registers(base, false);
 
 	writel_relaxed(D40_DREG_GCC_ENABLE_ALL,
 		       base->virtbase + D40_DREG_GCC);
 	return 0;
 }
-
-static int dma40_resume(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct d40_base *base = platform_get_drvdata(pdev);
-	int ret = 0;
-
-	if (base->lcpa_regulator)
-		ret = regulator_enable(base->lcpa_regulator);
-
-	return ret;
-}
+#endif
 
 static const struct dev_pm_ops dma40_pm_ops = {
-	.suspend		= dma40_pm_suspend,
-	.runtime_suspend	= dma40_runtime_suspend,
-	.runtime_resume		= dma40_runtime_resume,
-	.resume			= dma40_resume,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(dma40_suspend, dma40_resume)
+	SET_PM_RUNTIME_PM_OPS(dma40_runtime_suspend,
+				dma40_runtime_resume,
+				NULL)
 };
-#define DMA40_PM_OPS	(&dma40_pm_ops)
-#else
-#define DMA40_PM_OPS	NULL
-#endif
 
 /* Initialization functions. */
 
@@ -3645,12 +3641,6 @@ static int __init d40_probe(struct platform_device *pdev)
 		goto failure;
 	}
 
-	pm_runtime_irq_safe(base->dev);
-	pm_runtime_set_autosuspend_delay(base->dev, DMA40_AUTOSUSPEND_DELAY);
-	pm_runtime_use_autosuspend(base->dev);
-	pm_runtime_enable(base->dev);
-	pm_runtime_resume(base->dev);
-
 	if (base->plat_data->use_esram_lcla) {
 
 		base->lcpa_regulator = regulator_get(base->dev, "lcla_esram");
@@ -3671,7 +3661,15 @@ static int __init d40_probe(struct platform_device *pdev)
 		}
 	}
 
-	base->initialized = true;
+	writel_relaxed(D40_DREG_GCC_ENABLE_ALL, base->virtbase + D40_DREG_GCC);
+
+	pm_runtime_irq_safe(base->dev);
+	pm_runtime_set_autosuspend_delay(base->dev, DMA40_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(base->dev);
+	pm_runtime_mark_last_busy(base->dev);
+	pm_runtime_set_active(base->dev);
+	pm_runtime_enable(base->dev);
+
 	ret = d40_dmaengine_init(base, num_reserved_chans);
 	if (ret)
 		goto failure;
@@ -3754,7 +3752,7 @@ static struct platform_driver d40_driver = {
 	.driver = {
 		.owner = THIS_MODULE,
 		.name  = D40_NAME,
-		.pm = DMA40_PM_OPS,
+		.pm = &dma40_pm_ops,
 		.of_match_table = d40_match,
 	},
 };
diff --git a/drivers/dma/xilinx/Makefile b/drivers/dma/xilinx/Makefile
new file mode 100644
index 00000000000..3c4e9f2fea2
--- /dev/null
+++ b/drivers/dma/xilinx/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_XILINX_VDMA) += xilinx_vdma.o
diff --git a/drivers/dma/xilinx/xilinx_vdma.c b/drivers/dma/xilinx/xilinx_vdma.c
new file mode 100644
index 00000000000..42a13e8d460
--- /dev/null
+++ b/drivers/dma/xilinx/xilinx_vdma.c
@@ -0,0 +1,1379 @@
+/*
+ * DMA driver for Xilinx Video DMA Engine
+ *
+ * Copyright (C) 2010-2014 Xilinx, Inc. All rights reserved.
+ *
+ * Based on the Freescale DMA driver.
+ *
+ * Description:
+ * The AXI Video Direct Memory Access (AXI VDMA) core is a soft Xilinx IP
+ * core that provides high-bandwidth direct memory access between memory
+ * and AXI4-Stream type video target peripherals. The core provides efficient
+ * two dimensional DMA operations with independent asynchronous read (S2MM)
+ * and write (MM2S) channel operation. It can be configured to have either
+ * one channel or two channels. If configured as two channels, one is to
+ * transmit to the video device (MM2S) and another is to receive from the
+ * video device (S2MM). Initialization, status, interrupt and management
+ * registers are accessed through an AXI4-Lite slave interface.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/amba/xilinx_dma.h>
+#include <linux/bitops.h>
+#include <linux/dmapool.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_dma.h>
+#include <linux/of_platform.h>
+#include <linux/of_irq.h>
+#include <linux/slab.h>
+
+#include "../dmaengine.h"
+
+/* Register/Descriptor Offsets */
+#define XILINX_VDMA_MM2S_CTRL_OFFSET		0x0000
+#define XILINX_VDMA_S2MM_CTRL_OFFSET		0x0030
+#define XILINX_VDMA_MM2S_DESC_OFFSET		0x0050
+#define XILINX_VDMA_S2MM_DESC_OFFSET		0x00a0
+
+/* Control Registers */
+#define XILINX_VDMA_REG_DMACR			0x0000
+#define XILINX_VDMA_DMACR_DELAY_MAX		0xff
+#define XILINX_VDMA_DMACR_DELAY_SHIFT		24
+#define XILINX_VDMA_DMACR_FRAME_COUNT_MAX	0xff
+#define XILINX_VDMA_DMACR_FRAME_COUNT_SHIFT	16
+#define XILINX_VDMA_DMACR_ERR_IRQ		BIT(14)
+#define XILINX_VDMA_DMACR_DLY_CNT_IRQ		BIT(13)
+#define XILINX_VDMA_DMACR_FRM_CNT_IRQ		BIT(12)
+#define XILINX_VDMA_DMACR_MASTER_SHIFT		8
+#define XILINX_VDMA_DMACR_FSYNCSRC_SHIFT	5
+#define XILINX_VDMA_DMACR_FRAMECNT_EN		BIT(4)
+#define XILINX_VDMA_DMACR_GENLOCK_EN		BIT(3)
+#define XILINX_VDMA_DMACR_RESET			BIT(2)
+#define XILINX_VDMA_DMACR_CIRC_EN		BIT(1)
+#define XILINX_VDMA_DMACR_RUNSTOP		BIT(0)
+#define XILINX_VDMA_DMACR_FSYNCSRC_MASK		GENMASK(6, 5)
+
+#define XILINX_VDMA_REG_DMASR			0x0004
+#define XILINX_VDMA_DMASR_EOL_LATE_ERR		BIT(15)
+#define XILINX_VDMA_DMASR_ERR_IRQ		BIT(14)
+#define XILINX_VDMA_DMASR_DLY_CNT_IRQ		BIT(13)
+#define XILINX_VDMA_DMASR_FRM_CNT_IRQ		BIT(12)
+#define XILINX_VDMA_DMASR_SOF_LATE_ERR		BIT(11)
+#define XILINX_VDMA_DMASR_SG_DEC_ERR		BIT(10)
+#define XILINX_VDMA_DMASR_SG_SLV_ERR		BIT(9)
+#define XILINX_VDMA_DMASR_EOF_EARLY_ERR		BIT(8)
+#define XILINX_VDMA_DMASR_SOF_EARLY_ERR		BIT(7)
+#define XILINX_VDMA_DMASR_DMA_DEC_ERR		BIT(6)
+#define XILINX_VDMA_DMASR_DMA_SLAVE_ERR		BIT(5)
+#define XILINX_VDMA_DMASR_DMA_INT_ERR		BIT(4)
+#define XILINX_VDMA_DMASR_IDLE			BIT(1)
+#define XILINX_VDMA_DMASR_HALTED		BIT(0)
+#define XILINX_VDMA_DMASR_DELAY_MASK		GENMASK(31, 24)
+#define XILINX_VDMA_DMASR_FRAME_COUNT_MASK	GENMASK(23, 16)
+
+#define XILINX_VDMA_REG_CURDESC			0x0008
+#define XILINX_VDMA_REG_TAILDESC		0x0010
+#define XILINX_VDMA_REG_REG_INDEX		0x0014
+#define XILINX_VDMA_REG_FRMSTORE		0x0018
+#define XILINX_VDMA_REG_THRESHOLD		0x001c
+#define XILINX_VDMA_REG_FRMPTR_STS		0x0024
+#define XILINX_VDMA_REG_PARK_PTR		0x0028
+#define XILINX_VDMA_PARK_PTR_WR_REF_SHIFT	8
+#define XILINX_VDMA_PARK_PTR_RD_REF_SHIFT	0
+#define XILINX_VDMA_REG_VDMA_VERSION		0x002c
+
+/* Register Direct Mode Registers */
+#define XILINX_VDMA_REG_VSIZE			0x0000
+#define XILINX_VDMA_REG_HSIZE			0x0004
+
+#define XILINX_VDMA_REG_FRMDLY_STRIDE		0x0008
+#define XILINX_VDMA_FRMDLY_STRIDE_FRMDLY_SHIFT	24
+#define XILINX_VDMA_FRMDLY_STRIDE_STRIDE_SHIFT	0
+
+#define XILINX_VDMA_REG_START_ADDRESS(n)	(0x000c + 4 * (n))
+
+/* HW specific definitions */
+#define XILINX_VDMA_MAX_CHANS_PER_DEVICE	0x2
+
+#define XILINX_VDMA_DMAXR_ALL_IRQ_MASK	\
+		(XILINX_VDMA_DMASR_FRM_CNT_IRQ | \
+		 XILINX_VDMA_DMASR_DLY_CNT_IRQ | \
+		 XILINX_VDMA_DMASR_ERR_IRQ)
+
+#define XILINX_VDMA_DMASR_ALL_ERR_MASK	\
+		(XILINX_VDMA_DMASR_EOL_LATE_ERR | \
+		 XILINX_VDMA_DMASR_SOF_LATE_ERR | \
+		 XILINX_VDMA_DMASR_SG_DEC_ERR | \
+		 XILINX_VDMA_DMASR_SG_SLV_ERR | \
+		 XILINX_VDMA_DMASR_EOF_EARLY_ERR | \
+		 XILINX_VDMA_DMASR_SOF_EARLY_ERR | \
+		 XILINX_VDMA_DMASR_DMA_DEC_ERR | \
+		 XILINX_VDMA_DMASR_DMA_SLAVE_ERR | \
+		 XILINX_VDMA_DMASR_DMA_INT_ERR)
+
+/*
+ * Recoverable errors are DMA Internal error, SOF Early, EOF Early
+ * and SOF Late. They are only recoverable when C_FLUSH_ON_FSYNC
+ * is enabled in the h/w system.
+ */
+#define XILINX_VDMA_DMASR_ERR_RECOVER_MASK	\
+		(XILINX_VDMA_DMASR_SOF_LATE_ERR | \
+		 XILINX_VDMA_DMASR_EOF_EARLY_ERR | \
+		 XILINX_VDMA_DMASR_SOF_EARLY_ERR | \
+		 XILINX_VDMA_DMASR_DMA_INT_ERR)
+
+/* Axi VDMA Flush on Fsync bits */
+#define XILINX_VDMA_FLUSH_S2MM		3
+#define XILINX_VDMA_FLUSH_MM2S		2
+#define XILINX_VDMA_FLUSH_BOTH		1
+
+/* Delay loop counter to prevent hardware failure */
+#define XILINX_VDMA_LOOP_COUNT		1000000
+
+/**
+ * struct xilinx_vdma_desc_hw - Hardware Descriptor
+ * @next_desc: Next Descriptor Pointer @0x00
+ * @pad1: Reserved @0x04
+ * @buf_addr: Buffer address @0x08
+ * @pad2: Reserved @0x0C
+ * @vsize: Vertical Size @0x10
+ * @hsize: Horizontal Size @0x14
+ * @stride: Number of bytes between the first
+ *	    pixels of each horizontal line @0x18
+ */
+struct xilinx_vdma_desc_hw {
+	u32 next_desc;
+	u32 pad1;
+	u32 buf_addr;
+	u32 pad2;
+	u32 vsize;
+	u32 hsize;
+	u32 stride;
+} __aligned(64);
+
+/**
+ * struct xilinx_vdma_tx_segment - Descriptor segment
+ * @hw: Hardware descriptor
+ * @node: Node in the descriptor segments list
+ * @phys: Physical address of segment
+ */
+struct xilinx_vdma_tx_segment {
+	struct xilinx_vdma_desc_hw hw;
+	struct list_head node;
+	dma_addr_t phys;
+} __aligned(64);
+
+/**
+ * struct xilinx_vdma_tx_descriptor - Per Transaction structure
+ * @async_tx: Async transaction descriptor
+ * @segments: TX segments list
+ * @node: Node in the channel descriptors list
+ */
+struct xilinx_vdma_tx_descriptor {
+	struct dma_async_tx_descriptor async_tx;
+	struct list_head segments;
+	struct list_head node;
+};
+
+/**
+ * struct xilinx_vdma_chan - Driver specific VDMA channel structure
+ * @xdev: Driver specific device structure
+ * @ctrl_offset: Control registers offset
+ * @desc_offset: TX descriptor registers offset
+ * @lock: Descriptor operation lock
+ * @pending_list: Descriptors waiting
+ * @active_desc: Active descriptor
+ * @allocated_desc: Allocated descriptor
+ * @done_list: Complete descriptors
+ * @common: DMA common channel
+ * @desc_pool: Descriptors pool
+ * @dev: The dma device
+ * @irq: Channel IRQ
+ * @id: Channel ID
+ * @direction: Transfer direction
+ * @num_frms: Number of frames
+ * @has_sg: Support scatter transfers
+ * @genlock: Support genlock mode
+ * @err: Channel has errors
+ * @tasklet: Cleanup work after irq
+ * @config: Device configuration info
+ * @flush_on_fsync: Flush on Frame sync
+ */
+struct xilinx_vdma_chan {
+	struct xilinx_vdma_device *xdev;
+	u32 ctrl_offset;
+	u32 desc_offset;
+	spinlock_t lock;
+	struct list_head pending_list;
+	struct xilinx_vdma_tx_descriptor *active_desc;
+	struct xilinx_vdma_tx_descriptor *allocated_desc;
+	struct list_head done_list;
+	struct dma_chan common;
+	struct dma_pool *desc_pool;
+	struct device *dev;
+	int irq;
+	int id;
+	enum dma_transfer_direction direction;
+	int num_frms;
+	bool has_sg;
+	bool genlock;
+	bool err;
+	struct tasklet_struct tasklet;
+	struct xilinx_vdma_config config;
+	bool flush_on_fsync;
+};
+
+/**
+ * struct xilinx_vdma_device - VDMA device structure
+ * @regs: I/O mapped base address
+ * @dev: Device Structure
+ * @common: DMA device structure
+ * @chan: Driver specific VDMA channel
+ * @has_sg: Specifies whether Scatter-Gather is present or not
+ * @flush_on_fsync: Flush on frame sync
+ */
+struct xilinx_vdma_device {
+	void __iomem *regs;
+	struct device *dev;
+	struct dma_device common;
+	struct xilinx_vdma_chan *chan[XILINX_VDMA_MAX_CHANS_PER_DEVICE];
+	bool has_sg;
+	u32 flush_on_fsync;
+};
+
+/* Macros */
+#define to_xilinx_chan(chan) \
+	container_of(chan, struct xilinx_vdma_chan, common)
+#define to_vdma_tx_descriptor(tx) \
+	container_of(tx, struct xilinx_vdma_tx_descriptor, async_tx)
+
+/* IO accessors */
+static inline u32 vdma_read(struct xilinx_vdma_chan *chan, u32 reg)
+{
+	return ioread32(chan->xdev->regs + reg);
+}
+
+static inline void vdma_write(struct xilinx_vdma_chan *chan, u32 reg, u32 value)
+{
+	iowrite32(value, chan->xdev->regs + reg);
+}
+
+static inline void vdma_desc_write(struct xilinx_vdma_chan *chan, u32 reg,
+				   u32 value)
+{
+	vdma_write(chan, chan->desc_offset + reg, value);
+}
+
+static inline u32 vdma_ctrl_read(struct xilinx_vdma_chan *chan, u32 reg)
+{
+	return vdma_read(chan, chan->ctrl_offset + reg);
+}
+
+static inline void vdma_ctrl_write(struct xilinx_vdma_chan *chan, u32 reg,
+				   u32 value)
+{
+	vdma_write(chan, chan->ctrl_offset + reg, value);
+}
+
+static inline void vdma_ctrl_clr(struct xilinx_vdma_chan *chan, u32 reg,
+				 u32 clr)
+{
+	vdma_ctrl_write(chan, reg, vdma_ctrl_read(chan, reg) & ~clr);
+}
+
+static inline void vdma_ctrl_set(struct xilinx_vdma_chan *chan, u32 reg,
+				 u32 set)
+{
+	vdma_ctrl_write(chan, reg, vdma_ctrl_read(chan, reg) | set);
+}
+
+/* -----------------------------------------------------------------------------
+ * Descriptors and segments alloc and free
+ */
+
+/**
+ * xilinx_vdma_alloc_tx_segment - Allocate transaction segment
+ * @chan: Driver specific VDMA channel
+ *
+ * Return: The allocated segment on success and NULL on failure.
+ */
+static struct xilinx_vdma_tx_segment *
+xilinx_vdma_alloc_tx_segment(struct xilinx_vdma_chan *chan)
+{
+	struct xilinx_vdma_tx_segment *segment;
+	dma_addr_t phys;
+
+	segment = dma_pool_alloc(chan->desc_pool, GFP_ATOMIC, &phys);
+	if (!segment)
+		return NULL;
+
+	memset(segment, 0, sizeof(*segment));
+	segment->phys = phys;
+
+	return segment;
+}
+
+/**
+ * xilinx_vdma_free_tx_segment - Free transaction segment
+ * @chan: Driver specific VDMA channel
+ * @segment: VDMA transaction segment
+ */
+static void xilinx_vdma_free_tx_segment(struct xilinx_vdma_chan *chan,
+					struct xilinx_vdma_tx_segment *segment)
+{
+	dma_pool_free(chan->desc_pool, segment, segment->phys);
+}
+
+/**
+ * xilinx_vdma_tx_descriptor - Allocate transaction descriptor
+ * @chan: Driver specific VDMA channel
+ *
+ * Return: The allocated descriptor on success and NULL on failure.
+ */
+static struct xilinx_vdma_tx_descriptor *
+xilinx_vdma_alloc_tx_descriptor(struct xilinx_vdma_chan *chan)
+{
+	struct xilinx_vdma_tx_descriptor *desc;
+	unsigned long flags;
+
+	if (chan->allocated_desc)
+		return chan->allocated_desc;
+
+	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return NULL;
+
+	spin_lock_irqsave(&chan->lock, flags);
+	chan->allocated_desc = desc;
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	INIT_LIST_HEAD(&desc->segments);
+
+	return desc;
+}
+
+/**
+ * xilinx_vdma_free_tx_descriptor - Free transaction descriptor
+ * @chan: Driver specific VDMA channel
+ * @desc: VDMA transaction descriptor
+ */
+static void
+xilinx_vdma_free_tx_descriptor(struct xilinx_vdma_chan *chan,
+			       struct xilinx_vdma_tx_descriptor *desc)
+{
+	struct xilinx_vdma_tx_segment *segment, *next;
+
+	if (!desc)
+		return;
+
+	list_for_each_entry_safe(segment, next, &desc->segments, node) {
+		list_del(&segment->node);
+		xilinx_vdma_free_tx_segment(chan, segment);
+	}
+
+	kfree(desc);
+}
+
+/* Required functions */
+
+/**
+ * xilinx_vdma_free_desc_list - Free descriptors list
+ * @chan: Driver specific VDMA channel
+ * @list: List to parse and delete the descriptor
+ */
+static void xilinx_vdma_free_desc_list(struct xilinx_vdma_chan *chan,
+					struct list_head *list)
+{
+	struct xilinx_vdma_tx_descriptor *desc, *next;
+
+	list_for_each_entry_safe(desc, next, list, node) {
+		list_del(&desc->node);
+		xilinx_vdma_free_tx_descriptor(chan, desc);
+	}
+}
+
+/**
+ * xilinx_vdma_free_descriptors - Free channel descriptors
+ * @chan: Driver specific VDMA channel
+ */
+static void xilinx_vdma_free_descriptors(struct xilinx_vdma_chan *chan)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	xilinx_vdma_free_desc_list(chan, &chan->pending_list);
+	xilinx_vdma_free_desc_list(chan, &chan->done_list);
+
+	xilinx_vdma_free_tx_descriptor(chan, chan->active_desc);
+	chan->active_desc = NULL;
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+/**
+ * xilinx_vdma_free_chan_resources - Free channel resources
+ * @dchan: DMA channel
+ */
+static void xilinx_vdma_free_chan_resources(struct dma_chan *dchan)
+{
+	struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan);
+
+	dev_dbg(chan->dev, "Free all channel resources.\n");
+
+	xilinx_vdma_free_descriptors(chan);
+	dma_pool_destroy(chan->desc_pool);
+	chan->desc_pool = NULL;
+}
+
+/**
+ * xilinx_vdma_chan_desc_cleanup - Clean channel descriptors
+ * @chan: Driver specific VDMA channel
+ */
+static void xilinx_vdma_chan_desc_cleanup(struct xilinx_vdma_chan *chan)
+{
+	struct xilinx_vdma_tx_descriptor *desc, *next;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	list_for_each_entry_safe(desc, next, &chan->done_list, node) {
+		dma_async_tx_callback callback;
+		void *callback_param;
+
+		/* Remove from the list of running transactions */
+		list_del(&desc->node);
+
+		/* Run the link descriptor callback function */
+		callback = desc->async_tx.callback;
+		callback_param = desc->async_tx.callback_param;
+		if (callback) {
+			spin_unlock_irqrestore(&chan->lock, flags);
+			callback(callback_param);
+			spin_lock_irqsave(&chan->lock, flags);
+		}
+
+		/* Run any dependencies, then free the descriptor */
+		dma_run_dependencies(&desc->async_tx);
+		xilinx_vdma_free_tx_descriptor(chan, desc);
+	}
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+/**
+ * xilinx_vdma_do_tasklet - Schedule completion tasklet
+ * @data: Pointer to the Xilinx VDMA channel structure
+ */
+static void xilinx_vdma_do_tasklet(unsigned long data)
+{
+	struct xilinx_vdma_chan *chan = (struct xilinx_vdma_chan *)data;
+
+	xilinx_vdma_chan_desc_cleanup(chan);
+}
+
+/**
+ * xilinx_vdma_alloc_chan_resources - Allocate channel resources
+ * @dchan: DMA channel
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_vdma_alloc_chan_resources(struct dma_chan *dchan)
+{
+	struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan);
+
+	/* Has this channel already been allocated? */
+	if (chan->desc_pool)
+		return 0;
+
+	/*
+	 * We need the descriptor to be aligned to 64bytes
+	 * for meeting Xilinx VDMA specification requirement.
+	 */
+	chan->desc_pool = dma_pool_create("xilinx_vdma_desc_pool",
+				chan->dev,
+				sizeof(struct xilinx_vdma_tx_segment),
+				__alignof__(struct xilinx_vdma_tx_segment), 0);
+	if (!chan->desc_pool) {
+		dev_err(chan->dev,
+			"unable to allocate channel %d descriptor pool\n",
+			chan->id);
+		return -ENOMEM;
+	}
+
+	dma_cookie_init(dchan);
+	return 0;
+}
+
+/**
+ * xilinx_vdma_tx_status - Get VDMA transaction status
+ * @dchan: DMA channel
+ * @cookie: Transaction identifier
+ * @txstate: Transaction state
+ *
+ * Return: DMA transaction status
+ */
+static enum dma_status xilinx_vdma_tx_status(struct dma_chan *dchan,
+					dma_cookie_t cookie,
+					struct dma_tx_state *txstate)
+{
+	return dma_cookie_status(dchan, cookie, txstate);
+}
+
+/**
+ * xilinx_vdma_is_running - Check if VDMA channel is running
+ * @chan: Driver specific VDMA channel
+ *
+ * Return: '1' if running, '0' if not.
+ */
+static bool xilinx_vdma_is_running(struct xilinx_vdma_chan *chan)
+{
+	return !(vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) &
+		 XILINX_VDMA_DMASR_HALTED) &&
+		(vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR) &
+		 XILINX_VDMA_DMACR_RUNSTOP);
+}
+
+/**
+ * xilinx_vdma_is_idle - Check if VDMA channel is idle
+ * @chan: Driver specific VDMA channel
+ *
+ * Return: '1' if idle, '0' if not.
+ */
+static bool xilinx_vdma_is_idle(struct xilinx_vdma_chan *chan)
+{
+	return vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) &
+		XILINX_VDMA_DMASR_IDLE;
+}
+
+/**
+ * xilinx_vdma_halt - Halt VDMA channel
+ * @chan: Driver specific VDMA channel
+ */
+static void xilinx_vdma_halt(struct xilinx_vdma_chan *chan)
+{
+	int loop = XILINX_VDMA_LOOP_COUNT;
+
+	vdma_ctrl_clr(chan, XILINX_VDMA_REG_DMACR, XILINX_VDMA_DMACR_RUNSTOP);
+
+	/* Wait for the hardware to halt */
+	do {
+		if (vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) &
+		    XILINX_VDMA_DMASR_HALTED)
+			break;
+	} while (loop--);
+
+	if (!loop) {
+		dev_err(chan->dev, "Cannot stop channel %p: %x\n",
+			chan, vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR));
+		chan->err = true;
+	}
+
+	return;
+}
+
+/**
+ * xilinx_vdma_start - Start VDMA channel
+ * @chan: Driver specific VDMA channel
+ */
+static void xilinx_vdma_start(struct xilinx_vdma_chan *chan)
+{
+	int loop = XILINX_VDMA_LOOP_COUNT;
+
+	vdma_ctrl_set(chan, XILINX_VDMA_REG_DMACR, XILINX_VDMA_DMACR_RUNSTOP);
+
+	/* Wait for the hardware to start */
+	do {
+		if (!(vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR) &
+		      XILINX_VDMA_DMASR_HALTED))
+			break;
+	} while (loop--);
+
+	if (!loop) {
+		dev_err(chan->dev, "Cannot start channel %p: %x\n",
+			chan, vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR));
+
+		chan->err = true;
+	}
+
+	return;
+}
+
+/**
+ * xilinx_vdma_start_transfer - Starts VDMA transfer
+ * @chan: Driver specific channel struct pointer
+ */
+static void xilinx_vdma_start_transfer(struct xilinx_vdma_chan *chan)
+{
+	struct xilinx_vdma_config *config = &chan->config;
+	struct xilinx_vdma_tx_descriptor *desc;
+	unsigned long flags;
+	u32 reg;
+	struct xilinx_vdma_tx_segment *head, *tail = NULL;
+
+	if (chan->err)
+		return;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	/* There's already an active descriptor, bail out. */
+	if (chan->active_desc)
+		goto out_unlock;
+
+	if (list_empty(&chan->pending_list))
+		goto out_unlock;
+
+	desc = list_first_entry(&chan->pending_list,
+				struct xilinx_vdma_tx_descriptor, node);
+
+	/* If it is SG mode and hardware is busy, cannot submit */
+	if (chan->has_sg && xilinx_vdma_is_running(chan) &&
+	    !xilinx_vdma_is_idle(chan)) {
+		dev_dbg(chan->dev, "DMA controller still busy\n");
+		goto out_unlock;
+	}
+
+	/*
+	 * If hardware is idle, then all descriptors on the running lists are
+	 * done, start new transfers
+	 */
+	if (chan->has_sg) {
+		head = list_first_entry(&desc->segments,
+					struct xilinx_vdma_tx_segment, node);
+		tail = list_entry(desc->segments.prev,
+				  struct xilinx_vdma_tx_segment, node);
+
+		vdma_ctrl_write(chan, XILINX_VDMA_REG_CURDESC, head->phys);
+	}
+
+	/* Configure the hardware using info in the config structure */
+	reg = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR);
+
+	if (config->frm_cnt_en)
+		reg |= XILINX_VDMA_DMACR_FRAMECNT_EN;
+	else
+		reg &= ~XILINX_VDMA_DMACR_FRAMECNT_EN;
+
+	/*
+	 * With SG, start with circular mode, so that BDs can be fetched.
+	 * In direct register mode, if not parking, enable circular mode
+	 */
+	if (chan->has_sg || !config->park)
+		reg |= XILINX_VDMA_DMACR_CIRC_EN;
+
+	if (config->park)
+		reg &= ~XILINX_VDMA_DMACR_CIRC_EN;
+
+	vdma_ctrl_write(chan, XILINX_VDMA_REG_DMACR, reg);
+
+	if (config->park && (config->park_frm >= 0) &&
+			(config->park_frm < chan->num_frms)) {
+		if (chan->direction == DMA_MEM_TO_DEV)
+			vdma_write(chan, XILINX_VDMA_REG_PARK_PTR,
+				config->park_frm <<
+					XILINX_VDMA_PARK_PTR_RD_REF_SHIFT);
+		else
+			vdma_write(chan, XILINX_VDMA_REG_PARK_PTR,
+				config->park_frm <<
+					XILINX_VDMA_PARK_PTR_WR_REF_SHIFT);
+	}
+
+	/* Start the hardware */
+	xilinx_vdma_start(chan);
+
+	if (chan->err)
+		goto out_unlock;
+
+	/* Start the transfer */
+	if (chan->has_sg) {
+		vdma_ctrl_write(chan, XILINX_VDMA_REG_TAILDESC, tail->phys);
+	} else {
+		struct xilinx_vdma_tx_segment *segment, *last = NULL;
+		int i = 0;
+
+		list_for_each_entry(segment, &desc->segments, node) {
+			vdma_desc_write(chan,
+					XILINX_VDMA_REG_START_ADDRESS(i++),
+					segment->hw.buf_addr);
+			last = segment;
+		}
+
+		if (!last)
+			goto out_unlock;
+
+		/* HW expects these parameters to be same for one transaction */
+		vdma_desc_write(chan, XILINX_VDMA_REG_HSIZE, last->hw.hsize);
+		vdma_desc_write(chan, XILINX_VDMA_REG_FRMDLY_STRIDE,
+				last->hw.stride);
+		vdma_desc_write(chan, XILINX_VDMA_REG_VSIZE, last->hw.vsize);
+	}
+
+	list_del(&desc->node);
+	chan->active_desc = desc;
+
+out_unlock:
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+/**
+ * xilinx_vdma_issue_pending - Issue pending transactions
+ * @dchan: DMA channel
+ */
+static void xilinx_vdma_issue_pending(struct dma_chan *dchan)
+{
+	struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan);
+
+	xilinx_vdma_start_transfer(chan);
+}
+
+/**
+ * xilinx_vdma_complete_descriptor - Mark the active descriptor as complete
+ * @chan : xilinx DMA channel
+ *
+ * CONTEXT: hardirq
+ */
+static void xilinx_vdma_complete_descriptor(struct xilinx_vdma_chan *chan)
+{
+	struct xilinx_vdma_tx_descriptor *desc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	desc = chan->active_desc;
+	if (!desc) {
+		dev_dbg(chan->dev, "no running descriptors\n");
+		goto out_unlock;
+	}
+
+	dma_cookie_complete(&desc->async_tx);
+	list_add_tail(&desc->node, &chan->done_list);
+
+	chan->active_desc = NULL;
+
+out_unlock:
+	spin_unlock_irqrestore(&chan->lock, flags);
+}
+
+/**
+ * xilinx_vdma_reset - Reset VDMA channel
+ * @chan: Driver specific VDMA channel
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_vdma_reset(struct xilinx_vdma_chan *chan)
+{
+	int loop = XILINX_VDMA_LOOP_COUNT;
+	u32 tmp;
+
+	vdma_ctrl_set(chan, XILINX_VDMA_REG_DMACR, XILINX_VDMA_DMACR_RESET);
+
+	tmp = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR) &
+		XILINX_VDMA_DMACR_RESET;
+
+	/* Wait for the hardware to finish reset */
+	do {
+		tmp = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR) &
+			XILINX_VDMA_DMACR_RESET;
+	} while (loop-- && tmp);
+
+	if (!loop) {
+		dev_err(chan->dev, "reset timeout, cr %x, sr %x\n",
+			vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR),
+			vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR));
+		return -ETIMEDOUT;
+	}
+
+	chan->err = false;
+
+	return 0;
+}
+
+/**
+ * xilinx_vdma_chan_reset - Reset VDMA channel and enable interrupts
+ * @chan: Driver specific VDMA channel
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_vdma_chan_reset(struct xilinx_vdma_chan *chan)
+{
+	int err;
+
+	/* Reset VDMA */
+	err = xilinx_vdma_reset(chan);
+	if (err)
+		return err;
+
+	/* Enable interrupts */
+	vdma_ctrl_set(chan, XILINX_VDMA_REG_DMACR,
+		      XILINX_VDMA_DMAXR_ALL_IRQ_MASK);
+
+	return 0;
+}
+
+/**
+ * xilinx_vdma_irq_handler - VDMA Interrupt handler
+ * @irq: IRQ number
+ * @data: Pointer to the Xilinx VDMA channel structure
+ *
+ * Return: IRQ_HANDLED/IRQ_NONE
+ */
+static irqreturn_t xilinx_vdma_irq_handler(int irq, void *data)
+{
+	struct xilinx_vdma_chan *chan = data;
+	u32 status;
+
+	/* Read the status and ack the interrupts. */
+	status = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMASR);
+	if (!(status & XILINX_VDMA_DMAXR_ALL_IRQ_MASK))
+		return IRQ_NONE;
+
+	vdma_ctrl_write(chan, XILINX_VDMA_REG_DMASR,
+			status & XILINX_VDMA_DMAXR_ALL_IRQ_MASK);
+
+	if (status & XILINX_VDMA_DMASR_ERR_IRQ) {
+		/*
+		 * An error occurred. If C_FLUSH_ON_FSYNC is enabled and the
+		 * error is recoverable, ignore it. Otherwise flag the error.
+		 *
+		 * Only recoverable errors can be cleared in the DMASR register,
+		 * make sure not to write to other error bits to 1.
+		 */
+		u32 errors = status & XILINX_VDMA_DMASR_ALL_ERR_MASK;
+		vdma_ctrl_write(chan, XILINX_VDMA_REG_DMASR,
+				errors & XILINX_VDMA_DMASR_ERR_RECOVER_MASK);
+
+		if (!chan->flush_on_fsync ||
+		    (errors & ~XILINX_VDMA_DMASR_ERR_RECOVER_MASK)) {
+			dev_err(chan->dev,
+				"Channel %p has errors %x, cdr %x tdr %x\n",
+				chan, errors,
+				vdma_ctrl_read(chan, XILINX_VDMA_REG_CURDESC),
+				vdma_ctrl_read(chan, XILINX_VDMA_REG_TAILDESC));
+			chan->err = true;
+		}
+	}
+
+	if (status & XILINX_VDMA_DMASR_DLY_CNT_IRQ) {
+		/*
+		 * Device takes too long to do the transfer when user requires
+		 * responsiveness.
+		 */
+		dev_dbg(chan->dev, "Inter-packet latency too long\n");
+	}
+
+	if (status & XILINX_VDMA_DMASR_FRM_CNT_IRQ) {
+		xilinx_vdma_complete_descriptor(chan);
+		xilinx_vdma_start_transfer(chan);
+	}
+
+	tasklet_schedule(&chan->tasklet);
+	return IRQ_HANDLED;
+}
+
+/**
+ * xilinx_vdma_tx_submit - Submit DMA transaction
+ * @tx: Async transaction descriptor
+ *
+ * Return: cookie value on success and failure value on error
+ */
+static dma_cookie_t xilinx_vdma_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct xilinx_vdma_tx_descriptor *desc = to_vdma_tx_descriptor(tx);
+	struct xilinx_vdma_chan *chan = to_xilinx_chan(tx->chan);
+	dma_cookie_t cookie;
+	unsigned long flags;
+	int err;
+
+	if (chan->err) {
+		/*
+		 * If reset fails, need to hard reset the system.
+		 * Channel is no longer functional
+		 */
+		err = xilinx_vdma_chan_reset(chan);
+		if (err < 0)
+			return err;
+	}
+
+	spin_lock_irqsave(&chan->lock, flags);
+
+	cookie = dma_cookie_assign(tx);
+
+	/* Append the transaction to the pending transactions queue. */
+	list_add_tail(&desc->node, &chan->pending_list);
+
+	/* Free the allocated desc */
+	chan->allocated_desc = NULL;
+
+	spin_unlock_irqrestore(&chan->lock, flags);
+
+	return cookie;
+}
+
+/**
+ * xilinx_vdma_dma_prep_interleaved - prepare a descriptor for a
+ *	DMA_SLAVE transaction
+ * @dchan: DMA channel
+ * @xt: Interleaved template pointer
+ * @flags: transfer ack flags
+ *
+ * Return: Async transaction descriptor on success and NULL on failure
+ */
+static struct dma_async_tx_descriptor *
+xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
+				 struct dma_interleaved_template *xt,
+				 unsigned long flags)
+{
+	struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan);
+	struct xilinx_vdma_tx_descriptor *desc;
+	struct xilinx_vdma_tx_segment *segment, *prev = NULL;
+	struct xilinx_vdma_desc_hw *hw;
+
+	if (!is_slave_direction(xt->dir))
+		return NULL;
+
+	if (!xt->numf || !xt->sgl[0].size)
+		return NULL;
+
+	/* Allocate a transaction descriptor. */
+	desc = xilinx_vdma_alloc_tx_descriptor(chan);
+	if (!desc)
+		return NULL;
+
+	dma_async_tx_descriptor_init(&desc->async_tx, &chan->common);
+	desc->async_tx.tx_submit = xilinx_vdma_tx_submit;
+	async_tx_ack(&desc->async_tx);
+
+	/* Allocate the link descriptor from DMA pool */
+	segment = xilinx_vdma_alloc_tx_segment(chan);
+	if (!segment)
+		goto error;
+
+	/* Fill in the hardware descriptor */
+	hw = &segment->hw;
+	hw->vsize = xt->numf;
+	hw->hsize = xt->sgl[0].size;
+	hw->stride = xt->sgl[0].icg <<
+			XILINX_VDMA_FRMDLY_STRIDE_STRIDE_SHIFT;
+	hw->stride |= chan->config.frm_dly <<
+			XILINX_VDMA_FRMDLY_STRIDE_FRMDLY_SHIFT;
+
+	if (xt->dir != DMA_MEM_TO_DEV)
+		hw->buf_addr = xt->dst_start;
+	else
+		hw->buf_addr = xt->src_start;
+
+	/* Link the previous next descriptor to current */
+	prev = list_last_entry(&desc->segments,
+				struct xilinx_vdma_tx_segment, node);
+	prev->hw.next_desc = segment->phys;
+
+	/* Insert the segment into the descriptor segments list. */
+	list_add_tail(&segment->node, &desc->segments);
+
+	prev = segment;
+
+	/* Link the last hardware descriptor with the first. */
+	segment = list_first_entry(&desc->segments,
+				   struct xilinx_vdma_tx_segment, node);
+	prev->hw.next_desc = segment->phys;
+
+	return &desc->async_tx;
+
+error:
+	xilinx_vdma_free_tx_descriptor(chan, desc);
+	return NULL;
+}
+
+/**
+ * xilinx_vdma_terminate_all - Halt the channel and free descriptors
+ * @chan: Driver specific VDMA Channel pointer
+ */
+static void xilinx_vdma_terminate_all(struct xilinx_vdma_chan *chan)
+{
+	/* Halt the DMA engine */
+	xilinx_vdma_halt(chan);
+
+	/* Remove and free all of the descriptors in the lists */
+	xilinx_vdma_free_descriptors(chan);
+}
+
+/**
+ * xilinx_vdma_channel_set_config - Configure VDMA channel
+ * Run-time configuration for Axi VDMA, supports:
+ * . halt the channel
+ * . configure interrupt coalescing and inter-packet delay threshold
+ * . start/stop parking
+ * . enable genlock
+ *
+ * @dchan: DMA channel
+ * @cfg: VDMA device configuration pointer
+ *
+ * Return: '0' on success and failure value on error
+ */
+int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
+					struct xilinx_vdma_config *cfg)
+{
+	struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan);
+	u32 dmacr;
+
+	if (cfg->reset)
+		return xilinx_vdma_chan_reset(chan);
+
+	dmacr = vdma_ctrl_read(chan, XILINX_VDMA_REG_DMACR);
+
+	chan->config.frm_dly = cfg->frm_dly;
+	chan->config.park = cfg->park;
+
+	/* genlock settings */
+	chan->config.gen_lock = cfg->gen_lock;
+	chan->config.master = cfg->master;
+
+	if (cfg->gen_lock && chan->genlock) {
+		dmacr |= XILINX_VDMA_DMACR_GENLOCK_EN;
+		dmacr |= cfg->master << XILINX_VDMA_DMACR_MASTER_SHIFT;
+	}
+
+	chan->config.frm_cnt_en = cfg->frm_cnt_en;
+	if (cfg->park)
+		chan->config.park_frm = cfg->park_frm;
+	else
+		chan->config.park_frm = -1;
+
+	chan->config.coalesc = cfg->coalesc;
+	chan->config.delay = cfg->delay;
+
+	if (cfg->coalesc <= XILINX_VDMA_DMACR_FRAME_COUNT_MAX) {
+		dmacr |= cfg->coalesc << XILINX_VDMA_DMACR_FRAME_COUNT_SHIFT;
+		chan->config.coalesc = cfg->coalesc;
+	}
+
+	if (cfg->delay <= XILINX_VDMA_DMACR_DELAY_MAX) {
+		dmacr |= cfg->delay << XILINX_VDMA_DMACR_DELAY_SHIFT;
+		chan->config.delay = cfg->delay;
+	}
+
+	/* FSync Source selection */
+	dmacr &= ~XILINX_VDMA_DMACR_FSYNCSRC_MASK;
+	dmacr |= cfg->ext_fsync << XILINX_VDMA_DMACR_FSYNCSRC_SHIFT;
+
+	vdma_ctrl_write(chan, XILINX_VDMA_REG_DMACR, dmacr);
+
+	return 0;
+}
+EXPORT_SYMBOL(xilinx_vdma_channel_set_config);
+
+/**
+ * xilinx_vdma_device_control - Configure DMA channel of the device
+ * @dchan: DMA Channel pointer
+ * @cmd: DMA control command
+ * @arg: Channel configuration
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_vdma_device_control(struct dma_chan *dchan,
+				      enum dma_ctrl_cmd cmd, unsigned long arg)
+{
+	struct xilinx_vdma_chan *chan = to_xilinx_chan(dchan);
+
+	if (cmd != DMA_TERMINATE_ALL)
+		return -ENXIO;
+
+	xilinx_vdma_terminate_all(chan);
+
+	return 0;
+}
+
+/* -----------------------------------------------------------------------------
+ * Probe and remove
+ */
+
+/**
+ * xilinx_vdma_chan_remove - Per Channel remove function
+ * @chan: Driver specific VDMA channel
+ */
+static void xilinx_vdma_chan_remove(struct xilinx_vdma_chan *chan)
+{
+	/* Disable all interrupts */
+	vdma_ctrl_clr(chan, XILINX_VDMA_REG_DMACR,
+		      XILINX_VDMA_DMAXR_ALL_IRQ_MASK);
+
+	if (chan->irq > 0)
+		free_irq(chan->irq, chan);
+
+	tasklet_kill(&chan->tasklet);
+
+	list_del(&chan->common.device_node);
+}
+
+/**
+ * xilinx_vdma_chan_probe - Per Channel Probing
+ * It get channel features from the device tree entry and
+ * initialize special channel handling routines
+ *
+ * @xdev: Driver specific device structure
+ * @node: Device node
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_vdma_chan_probe(struct xilinx_vdma_device *xdev,
+				  struct device_node *node)
+{
+	struct xilinx_vdma_chan *chan;
+	bool has_dre = false;
+	u32 value, width;
+	int err;
+
+	/* Allocate and initialize the channel structure */
+	chan = devm_kzalloc(xdev->dev, sizeof(*chan), GFP_KERNEL);
+	if (!chan)
+		return -ENOMEM;
+
+	chan->dev = xdev->dev;
+	chan->xdev = xdev;
+	chan->has_sg = xdev->has_sg;
+
+	spin_lock_init(&chan->lock);
+	INIT_LIST_HEAD(&chan->pending_list);
+	INIT_LIST_HEAD(&chan->done_list);
+
+	/* Retrieve the channel properties from the device tree */
+	has_dre = of_property_read_bool(node, "xlnx,include-dre");
+
+	chan->genlock = of_property_read_bool(node, "xlnx,genlock-mode");
+
+	err = of_property_read_u32(node, "xlnx,datawidth", &value);
+	if (err) {
+		dev_err(xdev->dev, "missing xlnx,datawidth property\n");
+		return err;
+	}
+	width = value >> 3; /* Convert bits to bytes */
+
+	/* If data width is greater than 8 bytes, DRE is not in hw */
+	if (width > 8)
+		has_dre = false;
+
+	if (!has_dre)
+		xdev->common.copy_align = fls(width - 1);
+
+	if (of_device_is_compatible(node, "xlnx,axi-vdma-mm2s-channel")) {
+		chan->direction = DMA_MEM_TO_DEV;
+		chan->id = 0;
+
+		chan->ctrl_offset = XILINX_VDMA_MM2S_CTRL_OFFSET;
+		chan->desc_offset = XILINX_VDMA_MM2S_DESC_OFFSET;
+
+		if (xdev->flush_on_fsync == XILINX_VDMA_FLUSH_BOTH ||
+		    xdev->flush_on_fsync == XILINX_VDMA_FLUSH_MM2S)
+			chan->flush_on_fsync = true;
+	} else if (of_device_is_compatible(node,
+					    "xlnx,axi-vdma-s2mm-channel")) {
+		chan->direction = DMA_DEV_TO_MEM;
+		chan->id = 1;
+
+		chan->ctrl_offset = XILINX_VDMA_S2MM_CTRL_OFFSET;
+		chan->desc_offset = XILINX_VDMA_S2MM_DESC_OFFSET;
+
+		if (xdev->flush_on_fsync == XILINX_VDMA_FLUSH_BOTH ||
+		    xdev->flush_on_fsync == XILINX_VDMA_FLUSH_S2MM)
+			chan->flush_on_fsync = true;
+	} else {
+		dev_err(xdev->dev, "Invalid channel compatible node\n");
+		return -EINVAL;
+	}
+
+	/* Request the interrupt */
+	chan->irq = irq_of_parse_and_map(node, 0);
+	err = request_irq(chan->irq, xilinx_vdma_irq_handler, IRQF_SHARED,
+			  "xilinx-vdma-controller", chan);
+	if (err) {
+		dev_err(xdev->dev, "unable to request IRQ %d\n", chan->irq);
+		return err;
+	}
+
+	/* Initialize the tasklet */
+	tasklet_init(&chan->tasklet, xilinx_vdma_do_tasklet,
+			(unsigned long)chan);
+
+	/*
+	 * Initialize the DMA channel and add it to the DMA engine channels
+	 * list.
+	 */
+	chan->common.device = &xdev->common;
+
+	list_add_tail(&chan->common.device_node, &xdev->common.channels);
+	xdev->chan[chan->id] = chan;
+
+	/* Reset the channel */
+	err = xilinx_vdma_chan_reset(chan);
+	if (err < 0) {
+		dev_err(xdev->dev, "Reset channel failed\n");
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * of_dma_xilinx_xlate - Translation function
+ * @dma_spec: Pointer to DMA specifier as found in the device tree
+ * @ofdma: Pointer to DMA controller data
+ *
+ * Return: DMA channel pointer on success and NULL on error
+ */
+static struct dma_chan *of_dma_xilinx_xlate(struct of_phandle_args *dma_spec,
+						struct of_dma *ofdma)
+{
+	struct xilinx_vdma_device *xdev = ofdma->of_dma_data;
+	int chan_id = dma_spec->args[0];
+
+	if (chan_id >= XILINX_VDMA_MAX_CHANS_PER_DEVICE)
+		return NULL;
+
+	return dma_get_slave_channel(&xdev->chan[chan_id]->common);
+}
+
+/**
+ * xilinx_vdma_probe - Driver probe function
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: '0' on success and failure value on error
+ */
+static int xilinx_vdma_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct xilinx_vdma_device *xdev;
+	struct device_node *child;
+	struct resource *io;
+	u32 num_frames;
+	int i, err;
+
+	/* Allocate and initialize the DMA engine structure */
+	xdev = devm_kzalloc(&pdev->dev, sizeof(*xdev), GFP_KERNEL);
+	if (!xdev)
+		return -ENOMEM;
+
+	xdev->dev = &pdev->dev;
+
+	/* Request and map I/O memory */
+	io = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	xdev->regs = devm_ioremap_resource(&pdev->dev, io);
+	if (IS_ERR(xdev->regs))
+		return PTR_ERR(xdev->regs);
+
+	/* Retrieve the DMA engine properties from the device tree */
+	xdev->has_sg = of_property_read_bool(node, "xlnx,include-sg");
+
+	err = of_property_read_u32(node, "xlnx,num-fstores", &num_frames);
+	if (err < 0) {
+		dev_err(xdev->dev, "missing xlnx,num-fstores property\n");
+		return err;
+	}
+
+	err = of_property_read_u32(node, "xlnx,flush-fsync",
+					&xdev->flush_on_fsync);
+	if (err < 0)
+		dev_warn(xdev->dev, "missing xlnx,flush-fsync property\n");
+
+	/* Initialize the DMA engine */
+	xdev->common.dev = &pdev->dev;
+
+	INIT_LIST_HEAD(&xdev->common.channels);
+	dma_cap_set(DMA_SLAVE, xdev->common.cap_mask);
+	dma_cap_set(DMA_PRIVATE, xdev->common.cap_mask);
+
+	xdev->common.device_alloc_chan_resources =
+				xilinx_vdma_alloc_chan_resources;
+	xdev->common.device_free_chan_resources =
+				xilinx_vdma_free_chan_resources;
+	xdev->common.device_prep_interleaved_dma =
+				xilinx_vdma_dma_prep_interleaved;
+	xdev->common.device_control = xilinx_vdma_device_control;
+	xdev->common.device_tx_status = xilinx_vdma_tx_status;
+	xdev->common.device_issue_pending = xilinx_vdma_issue_pending;
+
+	platform_set_drvdata(pdev, xdev);
+
+	/* Initialize the channels */
+	for_each_child_of_node(node, child) {
+		err = xilinx_vdma_chan_probe(xdev, child);
+		if (err < 0)
+			goto error;
+	}
+
+	for (i = 0; i < XILINX_VDMA_MAX_CHANS_PER_DEVICE; i++)
+		if (xdev->chan[i])
+			xdev->chan[i]->num_frms = num_frames;
+
+	/* Register the DMA engine with the core */
+	dma_async_device_register(&xdev->common);
+
+	err = of_dma_controller_register(node, of_dma_xilinx_xlate,
+					 xdev);
+	if (err < 0) {
+		dev_err(&pdev->dev, "Unable to register DMA to DT\n");
+		dma_async_device_unregister(&xdev->common);
+		goto error;
+	}
+
+	dev_info(&pdev->dev, "Xilinx AXI VDMA Engine Driver Probed!!\n");
+
+	return 0;
+
+error:
+	for (i = 0; i < XILINX_VDMA_MAX_CHANS_PER_DEVICE; i++)
+		if (xdev->chan[i])
+			xilinx_vdma_chan_remove(xdev->chan[i]);
+
+	return err;
+}
+
+/**
+ * xilinx_vdma_remove - Driver remove function
+ * @pdev: Pointer to the platform_device structure
+ *
+ * Return: Always '0'
+ */
+static int xilinx_vdma_remove(struct platform_device *pdev)
+{
+	struct xilinx_vdma_device *xdev = platform_get_drvdata(pdev);
+	int i;
+
+	of_dma_controller_free(pdev->dev.of_node);
+
+	dma_async_device_unregister(&xdev->common);
+
+	for (i = 0; i < XILINX_VDMA_MAX_CHANS_PER_DEVICE; i++)
+		if (xdev->chan[i])
+			xilinx_vdma_chan_remove(xdev->chan[i]);
+
+	return 0;
+}
+
+static const struct of_device_id xilinx_vdma_of_ids[] = {
+	{ .compatible = "xlnx,axi-vdma-1.00.a",},
+	{}
+};
+
+static struct platform_driver xilinx_vdma_driver = {
+	.driver = {
+		.name = "xilinx-vdma",
+		.owner = THIS_MODULE,
+		.of_match_table = xilinx_vdma_of_ids,
+	},
+	.probe = xilinx_vdma_probe,
+	.remove = xilinx_vdma_remove,
+};
+
+module_platform_driver(xilinx_vdma_driver);
+
+MODULE_AUTHOR("Xilinx, Inc.");
+MODULE_DESCRIPTION("Xilinx VDMA driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 878f09005fa..e339c6b9142 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -186,6 +186,13 @@ config EDAC_I3200
 	  Support for error detection and correction on the Intel
 	  3200 and 3210 server chipsets.
 
+config EDAC_IE31200
+	tristate "Intel e312xx"
+	depends on EDAC_MM_EDAC && PCI && X86
+	help
+	  Support for error detection and correction on the Intel
+	  E3-1200 based DRAM controllers.
+
 config EDAC_X38
 	tristate "Intel X38"
 	depends on EDAC_MM_EDAC && PCI && X86
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index 4154ed6a02c..c479a24d8f7 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_EDAC_I82875P)		+= i82875p_edac.o
 obj-$(CONFIG_EDAC_I82975X)		+= i82975x_edac.o
 obj-$(CONFIG_EDAC_I3000)		+= i3000_edac.o
 obj-$(CONFIG_EDAC_I3200)		+= i3200_edac.o
+obj-$(CONFIG_EDAC_IE31200)		+= ie31200_edac.o
 obj-$(CONFIG_EDAC_X38)			+= x38_edac.o
 obj-$(CONFIG_EDAC_I82860)		+= i82860_edac.o
 obj-$(CONFIG_EDAC_R82600)		+= r82600_edac.o
diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
index a66941fea5a..e6d1691dfa4 100644
--- a/drivers/edac/edac_module.c
+++ b/drivers/edac/edac_module.c
@@ -28,7 +28,7 @@ static int edac_set_debug_level(const char *buf, struct kernel_param *kp)
 	if (ret)
 		return ret;
 
-	if (val < 0 || val > 4)
+	if (val > 4)
 		return -EINVAL;
 
 	return param_set_int(buf, kp);
diff --git a/drivers/edac/ie31200_edac.c b/drivers/edac/ie31200_edac.c
new file mode 100644
index 00000000000..a981dc6fd88
--- /dev/null
+++ b/drivers/edac/ie31200_edac.c
@@ -0,0 +1,536 @@
+/*
+ * Intel E3-1200
+ * Copyright (C) 2014 Jason Baron <jbaron@akamai.com>
+ *
+ * Support for the E3-1200 processor family. Heavily based on previous
+ * Intel EDAC drivers.
+ *
+ * Since the DRAM controller is on the cpu chip, we can use its PCI device
+ * id to identify these processors.
+ *
+ * PCI DRAM controller device ids (Taken from The PCI ID Repository - http://pci-ids.ucw.cz/)
+ *
+ * 0108: Xeon E3-1200 Processor Family DRAM Controller
+ * 010c: Xeon E3-1200/2nd Generation Core Processor Family DRAM Controller
+ * 0150: Xeon E3-1200 v2/3rd Gen Core processor DRAM Controller
+ * 0158: Xeon E3-1200 v2/Ivy Bridge DRAM Controller
+ * 015c: Xeon E3-1200 v2/3rd Gen Core processor DRAM Controller
+ * 0c04: Xeon E3-1200 v3/4th Gen Core Processor DRAM Controller
+ * 0c08: Xeon E3-1200 v3 Processor DRAM Controller
+ *
+ * Based on Intel specification:
+ * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/xeon-e3-1200v3-vol-2-datasheet.pdf
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e3-1200-family-vol-2-datasheet.html
+ *
+ * According to the above datasheet (p.16):
+ * "
+ * 6. Software must not access B0/D0/F0 32-bit memory-mapped registers with
+ * requests that cross a DW boundary.
+ * "
+ *
+ * Thus, we make use of the explicit: lo_hi_readq(), which breaks the readq into
+ * 2 readl() calls. This restriction may be lifted in subsequent chip releases,
+ * but lo_hi_readq() ensures that we are safe across all e3-1200 processors.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/edac.h>
+
+#include <asm-generic/io-64-nonatomic-lo-hi.h>
+#include "edac_core.h"
+
+#define IE31200_REVISION "1.0"
+#define EDAC_MOD_STR "ie31200_edac"
+
+#define ie31200_printk(level, fmt, arg...) \
+	edac_printk(level, "ie31200", fmt, ##arg)
+
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_1 0x0108
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_2 0x010c
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_3 0x0150
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_4 0x0158
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_5 0x015c
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_6 0x0c04
+#define PCI_DEVICE_ID_INTEL_IE31200_HB_7 0x0c08
+
+#define IE31200_DIMMS			4
+#define IE31200_RANKS			8
+#define IE31200_RANKS_PER_CHANNEL	4
+#define IE31200_DIMMS_PER_CHANNEL	2
+#define IE31200_CHANNELS		2
+
+/* Intel IE31200 register addresses - device 0 function 0 - DRAM Controller */
+#define IE31200_MCHBAR_LOW		0x48
+#define IE31200_MCHBAR_HIGH		0x4c
+#define IE31200_MCHBAR_MASK		GENMASK_ULL(38, 15)
+#define IE31200_MMR_WINDOW_SIZE		BIT(15)
+
+/*
+ * Error Status Register (16b)
+ *
+ * 15    reserved
+ * 14    Isochronous TBWRR Run Behind FIFO Full
+ *       (ITCV)
+ * 13    Isochronous TBWRR Run Behind FIFO Put
+ *       (ITSTV)
+ * 12    reserved
+ * 11    MCH Thermal Sensor Event
+ *       for SMI/SCI/SERR (GTSE)
+ * 10    reserved
+ *  9    LOCK to non-DRAM Memory Flag (LCKF)
+ *  8    reserved
+ *  7    DRAM Throttle Flag (DTF)
+ *  6:2  reserved
+ *  1    Multi-bit DRAM ECC Error Flag (DMERR)
+ *  0    Single-bit DRAM ECC Error Flag (DSERR)
+ */
+#define IE31200_ERRSTS			0xc8
+#define IE31200_ERRSTS_UE		BIT(1)
+#define IE31200_ERRSTS_CE		BIT(0)
+#define IE31200_ERRSTS_BITS		(IE31200_ERRSTS_UE | IE31200_ERRSTS_CE)
+
+/*
+ * Channel 0 ECC Error Log (64b)
+ *
+ * 63:48 Error Column Address (ERRCOL)
+ * 47:32 Error Row Address (ERRROW)
+ * 31:29 Error Bank Address (ERRBANK)
+ * 28:27 Error Rank Address (ERRRANK)
+ * 26:24 reserved
+ * 23:16 Error Syndrome (ERRSYND)
+ * 15: 2 reserved
+ *    1  Multiple Bit Error Status (MERRSTS)
+ *    0  Correctable Error Status (CERRSTS)
+ */
+#define IE31200_C0ECCERRLOG			0x40c8
+#define IE31200_C1ECCERRLOG			0x44c8
+#define IE31200_ECCERRLOG_CE			BIT(0)
+#define IE31200_ECCERRLOG_UE			BIT(1)
+#define IE31200_ECCERRLOG_RANK_BITS		GENMASK_ULL(28, 27)
+#define IE31200_ECCERRLOG_RANK_SHIFT		27
+#define IE31200_ECCERRLOG_SYNDROME_BITS		GENMASK_ULL(23, 16)
+#define IE31200_ECCERRLOG_SYNDROME_SHIFT	16
+
+#define IE31200_ECCERRLOG_SYNDROME(log)		   \
+	((log & IE31200_ECCERRLOG_SYNDROME_BITS) >> \
+	 IE31200_ECCERRLOG_SYNDROME_SHIFT)
+
+#define IE31200_CAPID0			0xe4
+#define IE31200_CAPID0_PDCD		BIT(4)
+#define IE31200_CAPID0_DDPCD		BIT(6)
+#define IE31200_CAPID0_ECC		BIT(1)
+
+#define IE31200_MAD_DIMM_0_OFFSET	0x5004
+#define IE31200_MAD_DIMM_SIZE		GENMASK_ULL(7, 0)
+#define IE31200_MAD_DIMM_A_RANK		BIT(17)
+#define IE31200_MAD_DIMM_A_WIDTH	BIT(19)
+
+#define IE31200_PAGES(n)		(n << (28 - PAGE_SHIFT))
+
+static int nr_channels;
+
+struct ie31200_priv {
+	void __iomem *window;
+};
+
+enum ie31200_chips {
+	IE31200 = 0,
+};
+
+struct ie31200_dev_info {
+	const char *ctl_name;
+};
+
+struct ie31200_error_info {
+	u16 errsts;
+	u16 errsts2;
+	u64 eccerrlog[IE31200_CHANNELS];
+};
+
+static const struct ie31200_dev_info ie31200_devs[] = {
+	[IE31200] = {
+		.ctl_name = "IE31200"
+	},
+};
+
+struct dimm_data {
+	u8 size; /* in 256MB multiples */
+	u8 dual_rank : 1,
+	   x16_width : 1; /* 0 means x8 width */
+};
+
+static int how_many_channels(struct pci_dev *pdev)
+{
+	int n_channels;
+	unsigned char capid0_2b; /* 2nd byte of CAPID0 */
+
+	pci_read_config_byte(pdev, IE31200_CAPID0 + 1, &capid0_2b);
+
+	/* check PDCD: Dual Channel Disable */
+	if (capid0_2b & IE31200_CAPID0_PDCD) {
+		edac_dbg(0, "In single channel mode\n");
+		n_channels = 1;
+	} else {
+		edac_dbg(0, "In dual channel mode\n");
+		n_channels = 2;
+	}
+
+	/* check DDPCD - check if both channels are filled */
+	if (capid0_2b & IE31200_CAPID0_DDPCD)
+		edac_dbg(0, "2 DIMMS per channel disabled\n");
+	else
+		edac_dbg(0, "2 DIMMS per channel enabled\n");
+
+	return n_channels;
+}
+
+static bool ecc_capable(struct pci_dev *pdev)
+{
+	unsigned char capid0_4b; /* 4th byte of CAPID0 */
+
+	pci_read_config_byte(pdev, IE31200_CAPID0 + 3, &capid0_4b);
+	if (capid0_4b & IE31200_CAPID0_ECC)
+		return false;
+	return true;
+}
+
+static int eccerrlog_row(int channel, u64 log)
+{
+	int rank = ((log & IE31200_ECCERRLOG_RANK_BITS) >>
+		IE31200_ECCERRLOG_RANK_SHIFT);
+	return rank | (channel * IE31200_RANKS_PER_CHANNEL);
+}
+
+static void ie31200_clear_error_info(struct mem_ctl_info *mci)
+{
+	/*
+	 * Clear any error bits.
+	 * (Yes, we really clear bits by writing 1 to them.)
+	 */
+	pci_write_bits16(to_pci_dev(mci->pdev), IE31200_ERRSTS,
+			 IE31200_ERRSTS_BITS, IE31200_ERRSTS_BITS);
+}
+
+static void ie31200_get_and_clear_error_info(struct mem_ctl_info *mci,
+					     struct ie31200_error_info *info)
+{
+	struct pci_dev *pdev;
+	struct ie31200_priv *priv = mci->pvt_info;
+	void __iomem *window = priv->window;
+
+	pdev = to_pci_dev(mci->pdev);
+
+	/*
+	 * This is a mess because there is no atomic way to read all the
+	 * registers at once and the registers can transition from CE being
+	 * overwritten by UE.
+	 */
+	pci_read_config_word(pdev, IE31200_ERRSTS, &info->errsts);
+	if (!(info->errsts & IE31200_ERRSTS_BITS))
+		return;
+
+	info->eccerrlog[0] = lo_hi_readq(window + IE31200_C0ECCERRLOG);
+	if (nr_channels == 2)
+		info->eccerrlog[1] = lo_hi_readq(window + IE31200_C1ECCERRLOG);
+
+	pci_read_config_word(pdev, IE31200_ERRSTS, &info->errsts2);
+
+	/*
+	 * If the error is the same for both reads then the first set
+	 * of reads is valid.  If there is a change then there is a CE
+	 * with no info and the second set of reads is valid and
+	 * should be UE info.
+	 */
+	if ((info->errsts ^ info->errsts2) & IE31200_ERRSTS_BITS) {
+		info->eccerrlog[0] = lo_hi_readq(window + IE31200_C0ECCERRLOG);
+		if (nr_channels == 2)
+			info->eccerrlog[1] =
+				lo_hi_readq(window + IE31200_C1ECCERRLOG);
+	}
+
+	ie31200_clear_error_info(mci);
+}
+
+static void ie31200_process_error_info(struct mem_ctl_info *mci,
+				       struct ie31200_error_info *info)
+{
+	int channel;
+	u64 log;
+
+	if (!(info->errsts & IE31200_ERRSTS_BITS))
+		return;
+
+	if ((info->errsts ^ info->errsts2) & IE31200_ERRSTS_BITS) {
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0,
+				     -1, -1, -1, "UE overwrote CE", "");
+		info->errsts = info->errsts2;
+	}
+
+	for (channel = 0; channel < nr_channels; channel++) {
+		log = info->eccerrlog[channel];
+		if (log & IE31200_ECCERRLOG_UE) {
+			edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+					     0, 0, 0,
+					     eccerrlog_row(channel, log),
+					     channel, -1,
+					     "ie31200 UE", "");
+		} else if (log & IE31200_ECCERRLOG_CE) {
+			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
+					     0, 0,
+					     IE31200_ECCERRLOG_SYNDROME(log),
+					     eccerrlog_row(channel, log),
+					     channel, -1,
+					     "ie31200 CE", "");
+		}
+	}
+}
+
+static void ie31200_check(struct mem_ctl_info *mci)
+{
+	struct ie31200_error_info info;
+
+	edac_dbg(1, "MC%d\n", mci->mc_idx);
+	ie31200_get_and_clear_error_info(mci, &info);
+	ie31200_process_error_info(mci, &info);
+}
+
+static void __iomem *ie31200_map_mchbar(struct pci_dev *pdev)
+{
+	union {
+		u64 mchbar;
+		struct {
+			u32 mchbar_low;
+			u32 mchbar_high;
+		};
+	} u;
+	void __iomem *window;
+
+	pci_read_config_dword(pdev, IE31200_MCHBAR_LOW, &u.mchbar_low);
+	pci_read_config_dword(pdev, IE31200_MCHBAR_HIGH, &u.mchbar_high);
+	u.mchbar &= IE31200_MCHBAR_MASK;
+
+	if (u.mchbar != (resource_size_t)u.mchbar) {
+		ie31200_printk(KERN_ERR, "mmio space beyond accessible range (0x%llx)\n",
+			       (unsigned long long)u.mchbar);
+		return NULL;
+	}
+
+	window = ioremap_nocache(u.mchbar, IE31200_MMR_WINDOW_SIZE);
+	if (!window)
+		ie31200_printk(KERN_ERR, "Cannot map mmio space at 0x%llx\n",
+			       (unsigned long long)u.mchbar);
+
+	return window;
+}
+
+static int ie31200_probe1(struct pci_dev *pdev, int dev_idx)
+{
+	int i, j, ret;
+	struct mem_ctl_info *mci = NULL;
+	struct edac_mc_layer layers[2];
+	struct dimm_data dimm_info[IE31200_CHANNELS][IE31200_DIMMS_PER_CHANNEL];
+	void __iomem *window;
+	struct ie31200_priv *priv;
+	u32 addr_decode;
+
+	edac_dbg(0, "MC:\n");
+
+	if (!ecc_capable(pdev)) {
+		ie31200_printk(KERN_INFO, "No ECC support\n");
+		return -ENODEV;
+	}
+
+	nr_channels = how_many_channels(pdev);
+	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
+	layers[0].size = IE31200_DIMMS;
+	layers[0].is_virt_csrow = true;
+	layers[1].type = EDAC_MC_LAYER_CHANNEL;
+	layers[1].size = nr_channels;
+	layers[1].is_virt_csrow = false;
+	mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers,
+			    sizeof(struct ie31200_priv));
+	if (!mci)
+		return -ENOMEM;
+
+	window = ie31200_map_mchbar(pdev);
+	if (!window) {
+		ret = -ENODEV;
+		goto fail_free;
+	}
+
+	edac_dbg(3, "MC: init mci\n");
+	mci->pdev = &pdev->dev;
+	mci->mtype_cap = MEM_FLAG_DDR3;
+	mci->edac_ctl_cap = EDAC_FLAG_SECDED;
+	mci->edac_cap = EDAC_FLAG_SECDED;
+	mci->mod_name = EDAC_MOD_STR;
+	mci->mod_ver = IE31200_REVISION;
+	mci->ctl_name = ie31200_devs[dev_idx].ctl_name;
+	mci->dev_name = pci_name(pdev);
+	mci->edac_check = ie31200_check;
+	mci->ctl_page_to_phys = NULL;
+	priv = mci->pvt_info;
+	priv->window = window;
+
+	/* populate DIMM info */
+	for (i = 0; i < IE31200_CHANNELS; i++) {
+		addr_decode = readl(window + IE31200_MAD_DIMM_0_OFFSET +
+					(i * 4));
+		edac_dbg(0, "addr_decode: 0x%x\n", addr_decode);
+		for (j = 0; j < IE31200_DIMMS_PER_CHANNEL; j++) {
+			dimm_info[i][j].size = (addr_decode >> (j * 8)) &
+						IE31200_MAD_DIMM_SIZE;
+			dimm_info[i][j].dual_rank = (addr_decode &
+				(IE31200_MAD_DIMM_A_RANK << j)) ? 1 : 0;
+			dimm_info[i][j].x16_width = (addr_decode &
+				(IE31200_MAD_DIMM_A_WIDTH << j)) ? 1 : 0;
+			edac_dbg(0, "size: 0x%x, rank: %d, width: %d\n",
+				 dimm_info[i][j].size,
+				 dimm_info[i][j].dual_rank,
+				 dimm_info[i][j].x16_width);
+		}
+	}
+
+	/*
+	 * The dram rank boundary (DRB) reg values are boundary addresses
+	 * for each DRAM rank with a granularity of 64MB.  DRB regs are
+	 * cumulative; the last one will contain the total memory
+	 * contained in all ranks.
+	 */
+	for (i = 0; i < IE31200_DIMMS_PER_CHANNEL; i++) {
+		for (j = 0; j < IE31200_CHANNELS; j++) {
+			struct dimm_info *dimm;
+			unsigned long nr_pages;
+
+			nr_pages = IE31200_PAGES(dimm_info[j][i].size);
+			if (nr_pages == 0)
+				continue;
+
+			if (dimm_info[j][i].dual_rank) {
+				nr_pages = nr_pages / 2;
+				dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
+						     mci->n_layers, (i * 2) + 1,
+						     j, 0);
+				dimm->nr_pages = nr_pages;
+				edac_dbg(0, "set nr pages: 0x%lx\n", nr_pages);
+				dimm->grain = 8; /* just a guess */
+				dimm->mtype = MEM_DDR3;
+				dimm->dtype = DEV_UNKNOWN;
+				dimm->edac_mode = EDAC_UNKNOWN;
+			}
+			dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
+					     mci->n_layers, i * 2, j, 0);
+			dimm->nr_pages = nr_pages;
+			edac_dbg(0, "set nr pages: 0x%lx\n", nr_pages);
+			dimm->grain = 8; /* same guess */
+			dimm->mtype = MEM_DDR3;
+			dimm->dtype = DEV_UNKNOWN;
+			dimm->edac_mode = EDAC_UNKNOWN;
+		}
+	}
+
+	ie31200_clear_error_info(mci);
+
+	if (edac_mc_add_mc(mci)) {
+		edac_dbg(3, "MC: failed edac_mc_add_mc()\n");
+		ret = -ENODEV;
+		goto fail_unmap;
+	}
+
+	/* get this far and it's successful */
+	edac_dbg(3, "MC: success\n");
+	return 0;
+
+fail_unmap:
+	iounmap(window);
+
+fail_free:
+	edac_mc_free(mci);
+
+	return ret;
+}
+
+static int ie31200_init_one(struct pci_dev *pdev,
+			    const struct pci_device_id *ent)
+{
+	edac_dbg(0, "MC:\n");
+
+	if (pci_enable_device(pdev) < 0)
+		return -EIO;
+
+	return ie31200_probe1(pdev, ent->driver_data);
+}
+
+static void ie31200_remove_one(struct pci_dev *pdev)
+{
+	struct mem_ctl_info *mci;
+	struct ie31200_priv *priv;
+
+	edac_dbg(0, "\n");
+	mci = edac_mc_del_mc(&pdev->dev);
+	if (!mci)
+		return;
+	priv = mci->pvt_info;
+	iounmap(priv->window);
+	edac_mc_free(mci);
+}
+
+static const struct pci_device_id ie31200_pci_tbl[] = {
+	{
+		PCI_VEND_DEV(INTEL, IE31200_HB_1), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		IE31200},
+	{
+		PCI_VEND_DEV(INTEL, IE31200_HB_2), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		IE31200},
+	{
+		PCI_VEND_DEV(INTEL, IE31200_HB_3), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		IE31200},
+	{
+		PCI_VEND_DEV(INTEL, IE31200_HB_4), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		IE31200},
+	{
+		PCI_VEND_DEV(INTEL, IE31200_HB_5), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		IE31200},
+	{
+		PCI_VEND_DEV(INTEL, IE31200_HB_6), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		IE31200},
+	{
+		PCI_VEND_DEV(INTEL, IE31200_HB_7), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		IE31200},
+	{
+		0,
+	}            /* 0 terminated list. */
+};
+MODULE_DEVICE_TABLE(pci, ie31200_pci_tbl);
+
+static struct pci_driver ie31200_driver = {
+	.name = EDAC_MOD_STR,
+	.probe = ie31200_init_one,
+	.remove = ie31200_remove_one,
+	.id_table = ie31200_pci_tbl,
+};
+
+static int __init ie31200_init(void)
+{
+	edac_dbg(3, "MC:\n");
+	/* Ensure that the OPSTATE is set correctly for POLL or NMI */
+	opstate_init();
+
+	return pci_register_driver(&ie31200_driver);
+}
+
+static void __exit ie31200_exit(void)
+{
+	edac_dbg(3, "MC:\n");
+	pci_unregister_driver(&ie31200_driver);
+}
+
+module_init(ie31200_init);
+module_exit(ie31200_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jason Baron <jbaron@akamai.com>");
+MODULE_DESCRIPTION("MC support for Intel Processor E31200 memory hub controllers");
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 5f43620d580..f78c1c54dbd 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -78,7 +78,8 @@ static const char * const f15h_mc1_mce_desc[] = {
 	"uop queue",
 	"insn buffer",
 	"predecode buffer",
-	"fetch address FIFO"
+	"fetch address FIFO",
+	"dispatch uop queue"
 };
 
 static const char * const f15h_mc2_mce_desc[] = {
@@ -267,6 +268,12 @@ static bool f15h_mc0_mce(u16 ec, u8 xec)
 			pr_cont("System Read Data Error.\n");
 		else
 			pr_cont(" Internal error condition type %d.\n", xec);
+	} else if (INT_ERROR(ec)) {
+		if (xec <= 0x1f)
+			pr_cont("Hardware Assert.\n");
+		else
+			ret = false;
+
 	} else
 		ret = false;
 
@@ -373,7 +380,7 @@ static bool f15h_mc1_mce(u16 ec, u8 xec)
 		pr_cont("%s.\n", f15h_mc1_mce_desc[xec-4]);
 		break;
 
-	case 0x11 ... 0x14:
+	case 0x11 ... 0x15:
 		pr_cont("Decoder %s parity error.\n", f15h_mc1_mce_desc[xec-4]);
 		break;
 
@@ -397,10 +404,20 @@ static void decode_mc1_mce(struct mce *m)
 		bool k8 = (boot_cpu_data.x86 == 0xf && (m->status & BIT_64(58)));
 
 		pr_cont("during %s.\n", (k8 ? "system linefill" : "NB data read"));
+	} else if (INT_ERROR(ec)) {
+		if (xec <= 0x3f)
+			pr_cont("Hardware Assert.\n");
+		else
+			goto wrong_mc1_mce;
 	} else if (fam_ops->mc1_mce(ec, xec))
 		;
 	else
-		pr_emerg(HW_ERR "Corrupted MC1 MCE info?\n");
+		goto wrong_mc1_mce;
+
+	return;
+
+wrong_mc1_mce:
+	pr_emerg(HW_ERR "Corrupted MC1 MCE info?\n");
 }
 
 static bool k8_mc2_mce(u16 ec, u8 xec)
@@ -468,6 +485,11 @@ static bool f15h_mc2_mce(u16 ec, u8 xec)
 		default:
 			ret = false;
 		}
+	} else if (INT_ERROR(ec)) {
+		if (xec <= 0x3f)
+			pr_cont("Hardware Assert.\n");
+		else
+			ret = false;
 	}
 
 	return ret;
@@ -615,6 +637,7 @@ static void decode_mc4_mce(struct mce *m)
 static void decode_mc5_mce(struct mce *m)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
+	u16 ec = EC(m->status);
 	u8 xec = XEC(m->status, xec_mask);
 
 	if (c->x86 == 0xf || c->x86 == 0x11)
@@ -622,6 +645,14 @@ static void decode_mc5_mce(struct mce *m)
 
 	pr_emerg(HW_ERR "MC5 Error: ");
 
+	if (INT_ERROR(ec)) {
+		if (xec <= 0x1f) {
+			pr_cont("Hardware Assert.\n");
+			return;
+		} else
+			goto wrong_mc5_mce;
+	}
+
 	if (xec == 0x0 || xec == 0xc)
 		pr_cont("%s.\n", mc5_mce_desc[xec]);
 	else if (xec <= 0xd)
@@ -642,6 +673,10 @@ static void decode_mc6_mce(struct mce *m)
 	pr_emerg(HW_ERR "MC6 Error: ");
 
 	switch (xec) {
+	case 0x0:
+		pr_cont("Hardware Assertion");
+		break;
+
 	case 0x1:
 		pr_cont("Free List");
 		break;
@@ -857,7 +892,8 @@ static int __init mce_amd_init(void)
 		break;
 
 	case 0x15:
-		xec_mask = 0x1f;
+		xec_mask = c->x86_model == 0x60 ? 0x3f : 0x1f;
+
 		fam_ops->mc0_mce = f15h_mc0_mce;
 		fam_ops->mc1_mce = f15h_mc1_mce;
 		fam_ops->mc2_mce = f15h_mc2_mce;
diff --git a/drivers/edac/x38_edac.c b/drivers/edac/x38_edac.c
index 4891b450830..e644b52c287 100644
--- a/drivers/edac/x38_edac.c
+++ b/drivers/edac/x38_edac.c
@@ -14,6 +14,8 @@
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
 #include <linux/edac.h>
+
+#include <asm-generic/io-64-nonatomic-lo-hi.h>
 #include "edac_core.h"
 
 #define X38_REVISION		"1.1"
@@ -161,11 +163,6 @@ static void x38_clear_error_info(struct mem_ctl_info *mci)
 			 X38_ERRSTS_BITS);
 }
 
-static u64 x38_readq(const void __iomem *addr)
-{
-	return readl(addr) | (((u64)readl(addr + 4)) << 32);
-}
-
 static void x38_get_and_clear_error_info(struct mem_ctl_info *mci,
 				 struct x38_error_info *info)
 {
@@ -183,9 +180,9 @@ static void x38_get_and_clear_error_info(struct mem_ctl_info *mci,
 	if (!(info->errsts & X38_ERRSTS_BITS))
 		return;
 
-	info->eccerrlog[0] = x38_readq(window + X38_C0ECCERRLOG);
+	info->eccerrlog[0] = lo_hi_readq(window + X38_C0ECCERRLOG);
 	if (x38_channel_num == 2)
-		info->eccerrlog[1] = x38_readq(window + X38_C1ECCERRLOG);
+		info->eccerrlog[1] = lo_hi_readq(window + X38_C1ECCERRLOG);
 
 	pci_read_config_word(pdev, X38_ERRSTS, &info->errsts2);
 
@@ -196,10 +193,10 @@ static void x38_get_and_clear_error_info(struct mem_ctl_info *mci,
 	 * should be UE info.
 	 */
 	if ((info->errsts ^ info->errsts2) & X38_ERRSTS_BITS) {
-		info->eccerrlog[0] = x38_readq(window + X38_C0ECCERRLOG);
+		info->eccerrlog[0] = lo_hi_readq(window + X38_C0ECCERRLOG);
 		if (x38_channel_num == 2)
 			info->eccerrlog[1] =
-				x38_readq(window + X38_C1ECCERRLOG);
+				lo_hi_readq(window + X38_C1ECCERRLOG);
 	}
 
 	x38_clear_error_info(mci);
diff --git a/drivers/firewire/Kconfig b/drivers/firewire/Kconfig
index 4199849e375..145974f9662 100644
--- a/drivers/firewire/Kconfig
+++ b/drivers/firewire/Kconfig
@@ -1,4 +1,5 @@
 menu "IEEE 1394 (FireWire) support"
+	depends on HAS_DMA
 	depends on PCI || COMPILE_TEST
 	# firewire-core does not depend on PCI but is
 	# not useful without PCI controller driver
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 57985410f12..a66a3217f1d 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -336,10 +336,10 @@ static const struct {
 		QUIRK_CYCLE_TIMER | QUIRK_IR_WAKE},
 
 	{PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT6315, 0,
-		QUIRK_CYCLE_TIMER | QUIRK_NO_MSI},
+		QUIRK_CYCLE_TIMER /* FIXME: necessary? */ | QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_VT6315, PCI_ANY_ID,
-		0},
+		QUIRK_NO_MSI},
 
 	{PCI_VENDOR_ID_VIA, PCI_ANY_ID, PCI_ANY_ID,
 		QUIRK_CYCLE_TIMER | QUIRK_NO_MSI},
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index d420ae2d341..f712d47f30d 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -54,6 +54,12 @@ config EFI_PARAMS_FROM_FDT
 	  the EFI runtime support gets system table address, memory
           map address, and other parameters from the device tree.
 
+config EFI_RUNTIME_WRAPPERS
+	bool
+
+config EFI_ARMSTUB
+	bool
+
 endmenu
 
 config UEFI_CPER
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 9553496b0f4..d8be608a9f3 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -1,8 +1,10 @@
 #
 # Makefile for linux kernel
 #
-obj-$(CONFIG_EFI)			+= efi.o vars.o
+obj-$(CONFIG_EFI)			+= efi.o vars.o reboot.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
 obj-$(CONFIG_EFI_VARS_PSTORE)		+= efi-pstore.o
 obj-$(CONFIG_UEFI_CPER)			+= cper.o
 obj-$(CONFIG_EFI_RUNTIME_MAP)		+= runtime-map.o
+obj-$(CONFIG_EFI_RUNTIME_WRAPPERS)	+= runtime-wrappers.o
+obj-$(CONFIG_EFI_STUB)			+= libstub/
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index 4b9dc836dcf..e992abc5ef2 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -40,7 +40,7 @@ struct pstore_read_data {
 static inline u64 generic_id(unsigned long timestamp,
 			     unsigned int part, int count)
 {
-	return (timestamp * 100 + part) * 1000 + count;
+	return ((u64) timestamp * 100 + part) * 1000 + count;
 }
 
 static int efi_pstore_read_func(struct efivar_entry *entry, void *data)
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index cd36deb619f..64ecbb501c5 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -23,6 +23,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/io.h>
+#include <linux/platform_device.h>
 
 struct efi __read_mostly efi = {
 	.mps        = EFI_INVALID_TABLE_ADDR,
@@ -104,16 +105,19 @@ static struct attribute *efi_subsys_attrs[] = {
 static umode_t efi_attr_is_visible(struct kobject *kobj,
 				   struct attribute *attr, int n)
 {
-	umode_t mode = attr->mode;
-
-	if (attr == &efi_attr_fw_vendor.attr)
-		return (efi.fw_vendor == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
-	else if (attr == &efi_attr_runtime.attr)
-		return (efi.runtime == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
-	else if (attr == &efi_attr_config_table.attr)
-		return (efi.config_table == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+	if (attr == &efi_attr_fw_vendor.attr) {
+		if (efi_enabled(EFI_PARAVIRT) ||
+				efi.fw_vendor == EFI_INVALID_TABLE_ADDR)
+			return 0;
+	} else if (attr == &efi_attr_runtime.attr) {
+		if (efi.runtime == EFI_INVALID_TABLE_ADDR)
+			return 0;
+	} else if (attr == &efi_attr_config_table.attr) {
+		if (efi.config_table == EFI_INVALID_TABLE_ADDR)
+			return 0;
+	}
 
-	return mode;
+	return attr->mode;
 }
 
 static struct attribute_group efi_subsys_attr_group = {
@@ -298,7 +302,7 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables)
 			if (table64 >> 32) {
 				pr_cont("\n");
 				pr_err("Table located above 4GB, disabling EFI.\n");
-				early_iounmap(config_tables,
+				early_memunmap(config_tables,
 					       efi.systab->nr_tables * sz);
 				return -EINVAL;
 			}
@@ -314,13 +318,27 @@ int __init efi_config_init(efi_config_table_type_t *arch_tables)
 		tablep += sz;
 	}
 	pr_cont("\n");
-	early_iounmap(config_tables, efi.systab->nr_tables * sz);
+	early_memunmap(config_tables, efi.systab->nr_tables * sz);
 
 	set_bit(EFI_CONFIG_TABLES, &efi.flags);
 
 	return 0;
 }
 
+#ifdef CONFIG_EFI_VARS_MODULE
+static int __init efi_load_efivars(void)
+{
+	struct platform_device *pdev;
+
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+		return 0;
+
+	pdev = platform_device_register_simple("efivars", 0, NULL, 0);
+	return IS_ERR(pdev) ? PTR_ERR(pdev) : 0;
+}
+device_initcall(efi_load_efivars);
+#endif
+
 #ifdef CONFIG_EFI_PARAMS_FROM_FDT
 
 #define UEFI_PARAM(name, prop, field)			   \
@@ -346,6 +364,7 @@ static __initdata struct {
 
 struct param_info {
 	int verbose;
+	int found;
 	void *params;
 };
 
@@ -353,25 +372,21 @@ static int __init fdt_find_uefi_params(unsigned long node, const char *uname,
 				       int depth, void *data)
 {
 	struct param_info *info = data;
-	void *prop, *dest;
-	unsigned long len;
+	const void *prop;
+	void *dest;
 	u64 val;
-	int i;
+	int i, len;
 
 	if (depth != 1 ||
 	    (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0))
 		return 0;
 
-	pr_info("Getting parameters from FDT:\n");
-
 	for (i = 0; i < ARRAY_SIZE(dt_params); i++) {
 		prop = of_get_flat_dt_prop(node, dt_params[i].propname, &len);
-		if (!prop) {
-			pr_err("Can't find %s in device tree!\n",
-			       dt_params[i].name);
+		if (!prop)
 			return 0;
-		}
 		dest = info->params + dt_params[i].offset;
+		info->found++;
 
 		val = of_read_number(prop, len / sizeof(u32));
 
@@ -390,10 +405,21 @@ static int __init fdt_find_uefi_params(unsigned long node, const char *uname,
 int __init efi_get_fdt_params(struct efi_fdt_params *params, int verbose)
 {
 	struct param_info info;
+	int ret;
+
+	pr_info("Getting EFI parameters from FDT:\n");
 
 	info.verbose = verbose;
+	info.found = 0;
 	info.params = params;
 
-	return of_scan_flat_dt(fdt_find_uefi_params, &info);
+	ret = of_scan_flat_dt(fdt_find_uefi_params, &info);
+	if (!info.found)
+		pr_info("UEFI not found.\n");
+	else if (!ret)
+		pr_err("Can't find '%s' in device tree!\n",
+		       dt_params[info.found].name);
+
+	return ret;
 }
 #endif /* CONFIG_EFI_PARAMS_FROM_FDT */
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 463c56545ae..f256ecd8a17 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -78,6 +78,7 @@ MODULE_AUTHOR("Matt Domsch <Matt_Domsch@Dell.com>");
 MODULE_DESCRIPTION("sysfs interface to EFI Variables");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(EFIVARS_VERSION);
+MODULE_ALIAS("platform:efivars");
 
 LIST_HEAD(efivar_sysfs_list);
 EXPORT_SYMBOL_GPL(efivar_sysfs_list);
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
new file mode 100644
index 00000000000..b14bc2b9fb4
--- /dev/null
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -0,0 +1,26 @@
+#
+# The stub may be linked into the kernel proper or into a separate boot binary,
+# but in either case, it executes before the kernel does (with MMU disabled) so
+# things like ftrace and stack-protector are likely to cause trouble if left
+# enabled, even if doing so doesn't break the build.
+#
+cflags-$(CONFIG_X86_32)		:= -march=i386
+cflags-$(CONFIG_X86_64)		:= -mcmodel=small
+cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 \
+				   -fPIC -fno-strict-aliasing -mno-red-zone \
+				   -mno-mmx -mno-sse -DDISABLE_BRANCH_PROFILING
+
+cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS))
+cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
+				   -fno-builtin -fpic -mno-single-pic-base
+
+KBUILD_CFLAGS			:= $(cflags-y) \
+				   $(call cc-option,-ffreestanding) \
+				   $(call cc-option,-fno-stack-protector)
+
+GCOV_PROFILE			:= n
+
+lib-y				:= efi-stub-helper.o
+lib-$(CONFIG_EFI_ARMSTUB)	+= arm-stub.o fdt.o
+
+CFLAGS_fdt.o			+= -I$(srctree)/scripts/dtc/libfdt/
diff --git a/drivers/firmware/efi/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 41114ce03b0..480339b6b11 100644
--- a/drivers/firmware/efi/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -12,6 +12,11 @@
  *
  */
 
+#include <linux/efi.h>
+#include <asm/efi.h>
+
+#include "efistub.h"
+
 static int __init efi_secureboot_enabled(efi_system_table_t *sys_table_arg)
 {
 	static efi_guid_t const var_guid __initconst = EFI_GLOBAL_VARIABLE_GUID;
@@ -36,8 +41,8 @@ static int __init efi_secureboot_enabled(efi_system_table_t *sys_table_arg)
 	}
 }
 
-static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
-				    void *__image, void **__fh)
+efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
+			     void *__image, void **__fh)
 {
 	efi_file_io_interface_t *io;
 	efi_loaded_image_t *image = __image;
@@ -60,14 +65,15 @@ static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
 	*__fh = fh;
 	return status;
 }
-static efi_status_t efi_file_close(void *handle)
+
+efi_status_t efi_file_close(void *handle)
 {
 	efi_file_handle_t *fh = handle;
 
 	return fh->close(handle);
 }
 
-static efi_status_t
+efi_status_t
 efi_file_read(void *handle, unsigned long *size, void *addr)
 {
 	efi_file_handle_t *fh = handle;
@@ -76,7 +82,7 @@ efi_file_read(void *handle, unsigned long *size, void *addr)
 }
 
 
-static efi_status_t
+efi_status_t
 efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
 	      efi_char16_t *filename_16, void **handle, u64 *file_sz)
 {
@@ -129,7 +135,7 @@ grow:
 
 
 
-static void efi_char16_printk(efi_system_table_t *sys_table_arg,
+void efi_char16_printk(efi_system_table_t *sys_table_arg,
 			      efi_char16_t *str)
 {
 	struct efi_simple_text_output_protocol *out;
@@ -145,13 +151,13 @@ static void efi_char16_printk(efi_system_table_t *sys_table_arg,
  * must be reserved. On failure it is required to free all
  * all allocations it has made.
  */
-static efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
-					unsigned long *image_addr,
-					unsigned long *image_size,
-					unsigned long *reserve_addr,
-					unsigned long *reserve_size,
-					unsigned long dram_base,
-					efi_loaded_image_t *image);
+efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
+				 unsigned long *image_addr,
+				 unsigned long *image_size,
+				 unsigned long *reserve_addr,
+				 unsigned long *reserve_size,
+				 unsigned long dram_base,
+				 efi_loaded_image_t *image);
 /*
  * EFI entry point for the arm/arm64 EFI stubs.  This is the entrypoint
  * that is described in the PE/COFF header.  Most of the code is the same
diff --git a/drivers/firmware/efi/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index eb6d4be9e72..32d5cca30f4 100644
--- a/drivers/firmware/efi/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -9,18 +9,20 @@
  * under the terms of the GNU General Public License version 2.
  *
  */
-#define EFI_READ_CHUNK_SIZE	(1024 * 1024)
 
-/* error code which can't be mistaken for valid address */
-#define EFI_ERROR	(~0UL)
+#include <linux/efi.h>
+#include <asm/efi.h>
+
+#include "efistub.h"
 
+#define EFI_READ_CHUNK_SIZE	(1024 * 1024)
 
 struct file_info {
 	efi_file_handle_t *handle;
 	u64 size;
 };
 
-static void efi_printk(efi_system_table_t *sys_table_arg, char *str)
+void efi_printk(efi_system_table_t *sys_table_arg, char *str)
 {
 	char *s8;
 
@@ -37,16 +39,12 @@ static void efi_printk(efi_system_table_t *sys_table_arg, char *str)
 	}
 }
 
-#define pr_efi(sys_table, msg)     efi_printk(sys_table, "EFI stub: "msg)
-#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg)
-
-
-static efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
-				       efi_memory_desc_t **map,
-				       unsigned long *map_size,
-				       unsigned long *desc_size,
-				       u32 *desc_ver,
-				       unsigned long *key_ptr)
+efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
+				efi_memory_desc_t **map,
+				unsigned long *map_size,
+				unsigned long *desc_size,
+				u32 *desc_ver,
+				unsigned long *key_ptr)
 {
 	efi_memory_desc_t *m = NULL;
 	efi_status_t status;
@@ -88,7 +86,7 @@ fail:
 }
 
 
-static unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg)
+unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg)
 {
 	efi_status_t status;
 	unsigned long map_size;
@@ -116,9 +114,9 @@ static unsigned long __init get_dram_base(efi_system_table_t *sys_table_arg)
 /*
  * Allocate at the highest possible address that is not above 'max'.
  */
-static efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
-			       unsigned long size, unsigned long align,
-			       unsigned long *addr, unsigned long max)
+efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
+			    unsigned long size, unsigned long align,
+			    unsigned long *addr, unsigned long max)
 {
 	unsigned long map_size, desc_size;
 	efi_memory_desc_t *map;
@@ -202,9 +200,9 @@ fail:
 /*
  * Allocate at the lowest possible address.
  */
-static efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
-			      unsigned long size, unsigned long align,
-			      unsigned long *addr)
+efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
+			   unsigned long size, unsigned long align,
+			   unsigned long *addr)
 {
 	unsigned long map_size, desc_size;
 	efi_memory_desc_t *map;
@@ -271,8 +269,8 @@ fail:
 	return status;
 }
 
-static void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
-		     unsigned long addr)
+void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
+	      unsigned long addr)
 {
 	unsigned long nr_pages;
 
@@ -290,12 +288,12 @@ static void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
  * We only support loading a file from the same filesystem as
  * the kernel image.
  */
-static efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
-					 efi_loaded_image_t *image,
-					 char *cmd_line, char *option_string,
-					 unsigned long max_addr,
-					 unsigned long *load_addr,
-					 unsigned long *load_size)
+efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
+				  efi_loaded_image_t *image,
+				  char *cmd_line, char *option_string,
+				  unsigned long max_addr,
+				  unsigned long *load_addr,
+				  unsigned long *load_size)
 {
 	struct file_info *files;
 	unsigned long file_addr;
@@ -477,12 +475,12 @@ fail:
  * address is not available the lowest available address will
  * be used.
  */
-static efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
-					unsigned long *image_addr,
-					unsigned long image_size,
-					unsigned long alloc_size,
-					unsigned long preferred_addr,
-					unsigned long alignment)
+efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
+				 unsigned long *image_addr,
+				 unsigned long image_size,
+				 unsigned long alloc_size,
+				 unsigned long preferred_addr,
+				 unsigned long alignment)
 {
 	unsigned long cur_image_addr;
 	unsigned long new_addr = 0;
@@ -589,9 +587,9 @@ static u8 *efi_utf16_to_utf8(u8 *dst, const u16 *src, int n)
  * Size of memory allocated return in *cmd_line_len.
  * Returns NULL on error.
  */
-static char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
-				 efi_loaded_image_t *image,
-				 int *cmd_line_len)
+char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
+			  efi_loaded_image_t *image,
+			  int *cmd_line_len)
 {
 	const u16 *s2;
 	u8 *s1 = NULL;
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
new file mode 100644
index 00000000000..304ab295ca1
--- /dev/null
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -0,0 +1,42 @@
+
+#ifndef _DRIVERS_FIRMWARE_EFI_EFISTUB_H
+#define _DRIVERS_FIRMWARE_EFI_EFISTUB_H
+
+/* error code which can't be mistaken for valid address */
+#define EFI_ERROR	(~0UL)
+
+void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
+
+efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
+			     void **__fh);
+
+efi_status_t efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
+			   efi_char16_t *filename_16, void **handle,
+			   u64 *file_sz);
+
+efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr);
+
+efi_status_t efi_file_close(void *handle);
+
+unsigned long get_dram_base(efi_system_table_t *sys_table_arg);
+
+efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
+			unsigned long orig_fdt_size,
+			void *fdt, int new_fdt_size, char *cmdline_ptr,
+			u64 initrd_addr, u64 initrd_size,
+			efi_memory_desc_t *memory_map,
+			unsigned long map_size, unsigned long desc_size,
+			u32 desc_ver);
+
+efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
+					    void *handle,
+					    unsigned long *new_fdt_addr,
+					    unsigned long max_addr,
+					    u64 initrd_addr, u64 initrd_size,
+					    char *cmdline_ptr,
+					    unsigned long fdt_addr,
+					    unsigned long fdt_size);
+
+void *get_fdt(efi_system_table_t *sys_table);
+
+#endif
diff --git a/drivers/firmware/efi/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index 5c6a8e8a958..a56bb352875 100644
--- a/drivers/firmware/efi/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -10,29 +10,23 @@
  *
  */
 
-static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
-			       unsigned long orig_fdt_size,
-			       void *fdt, int new_fdt_size, char *cmdline_ptr,
-			       u64 initrd_addr, u64 initrd_size,
-			       efi_memory_desc_t *memory_map,
-			       unsigned long map_size, unsigned long desc_size,
-			       u32 desc_ver)
+#include <linux/efi.h>
+#include <linux/libfdt.h>
+#include <asm/efi.h>
+
+efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
+			unsigned long orig_fdt_size,
+			void *fdt, int new_fdt_size, char *cmdline_ptr,
+			u64 initrd_addr, u64 initrd_size,
+			efi_memory_desc_t *memory_map,
+			unsigned long map_size, unsigned long desc_size,
+			u32 desc_ver)
 {
 	int node, prev;
 	int status;
 	u32 fdt_val32;
 	u64 fdt_val64;
 
-	/*
-	 * Copy definition of linux_banner here.  Since this code is
-	 * built as part of the decompressor for ARM v7, pulling
-	 * in version.c where linux_banner is defined for the
-	 * kernel brings other kernel dependencies with it.
-	 */
-	const char linux_banner[] =
-	    "Linux version " UTS_RELEASE " (" LINUX_COMPILE_BY "@"
-	    LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION "\n";
-
 	/* Do some checks on provided FDT, if it exists*/
 	if (orig_fdt) {
 		if (fdt_check_header(orig_fdt)) {
@@ -63,7 +57,7 @@ static efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
 	 */
 	prev = 0;
 	for (;;) {
-		const char *type, *name;
+		const char *type;
 		int len;
 
 		node = fdt_next_node(fdt, prev, NULL);
@@ -265,7 +259,7 @@ fail:
 	return EFI_LOAD_ERROR;
 }
 
-static void *get_fdt(efi_system_table_t *sys_table)
+void *get_fdt(efi_system_table_t *sys_table)
 {
 	efi_guid_t fdt_guid = DEVICE_TREE_GUID;
 	efi_config_table_t *tables;
diff --git a/drivers/firmware/efi/reboot.c b/drivers/firmware/efi/reboot.c
new file mode 100644
index 00000000000..9c59d1c795d
--- /dev/null
+++ b/drivers/firmware/efi/reboot.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ * Copyright (c) 2014 Red Hat, Inc., Mark Salter <msalter@redhat.com>
+ */
+#include <linux/efi.h>
+#include <linux/reboot.h>
+
+int efi_reboot_quirk_mode = -1;
+
+void efi_reboot(enum reboot_mode reboot_mode, const char *__unused)
+{
+	int efi_mode;
+
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+		return;
+
+	switch (reboot_mode) {
+	case REBOOT_WARM:
+	case REBOOT_SOFT:
+		efi_mode = EFI_RESET_WARM;
+		break;
+	default:
+		efi_mode = EFI_RESET_COLD;
+		break;
+	}
+
+	/*
+	 * If a quirk forced an EFI reset mode, always use that.
+	 */
+	if (efi_reboot_quirk_mode != -1)
+		efi_mode = efi_reboot_quirk_mode;
+
+	efi.reset_system(efi_mode, EFI_SUCCESS, 0, NULL);
+}
+
+bool __weak efi_poweroff_required(void)
+{
+	return false;
+}
+
+static void efi_power_off(void)
+{
+	efi.reset_system(EFI_RESET_SHUTDOWN, EFI_SUCCESS, 0, NULL);
+}
+
+static int __init efi_shutdown_init(void)
+{
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+		return -ENODEV;
+
+	if (efi_poweroff_required())
+		pm_power_off = efi_power_off;
+
+	return 0;
+}
+late_initcall(efi_shutdown_init);
diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
new file mode 100644
index 00000000000..10daa4bbb25
--- /dev/null
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -0,0 +1,161 @@
+/*
+ * runtime-wrappers.c - Runtime Services function call wrappers
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * Split off from arch/x86/platform/efi/efi.c
+ *
+ * Copyright (C) 1999 VA Linux Systems
+ * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
+ * Copyright (C) 1999-2002 Hewlett-Packard Co.
+ * Copyright (C) 2005-2008 Intel Co.
+ * Copyright (C) 2013 SuSE Labs
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/efi.h>
+#include <linux/spinlock.h>             /* spinlock_t */
+#include <asm/efi.h>
+
+/*
+ * As per commit ef68c8f87ed1 ("x86: Serialize EFI time accesses on rtc_lock"),
+ * the EFI specification requires that callers of the time related runtime
+ * functions serialize with other CMOS accesses in the kernel, as the EFI time
+ * functions may choose to also use the legacy CMOS RTC.
+ */
+__weak DEFINE_SPINLOCK(rtc_lock);
+
+static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+{
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	status = efi_call_virt(get_time, tm, tc);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
+}
+
+static efi_status_t virt_efi_set_time(efi_time_t *tm)
+{
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	status = efi_call_virt(set_time, tm);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
+}
+
+static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
+					     efi_bool_t *pending,
+					     efi_time_t *tm)
+{
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
+}
+
+static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+{
+	unsigned long flags;
+	efi_status_t status;
+
+	spin_lock_irqsave(&rtc_lock, flags);
+	status = efi_call_virt(set_wakeup_time, enabled, tm);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+	return status;
+}
+
+static efi_status_t virt_efi_get_variable(efi_char16_t *name,
+					  efi_guid_t *vendor,
+					  u32 *attr,
+					  unsigned long *data_size,
+					  void *data)
+{
+	return efi_call_virt(get_variable, name, vendor, attr, data_size, data);
+}
+
+static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
+					       efi_char16_t *name,
+					       efi_guid_t *vendor)
+{
+	return efi_call_virt(get_next_variable, name_size, name, vendor);
+}
+
+static efi_status_t virt_efi_set_variable(efi_char16_t *name,
+					  efi_guid_t *vendor,
+					  u32 attr,
+					  unsigned long data_size,
+					  void *data)
+{
+	return efi_call_virt(set_variable, name, vendor, attr, data_size, data);
+}
+
+static efi_status_t virt_efi_query_variable_info(u32 attr,
+						 u64 *storage_space,
+						 u64 *remaining_space,
+						 u64 *max_variable_size)
+{
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	return efi_call_virt(query_variable_info, attr, storage_space,
+			     remaining_space, max_variable_size);
+}
+
+static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
+{
+	return efi_call_virt(get_next_high_mono_count, count);
+}
+
+static void virt_efi_reset_system(int reset_type,
+				  efi_status_t status,
+				  unsigned long data_size,
+				  efi_char16_t *data)
+{
+	__efi_call_virt(reset_system, reset_type, status, data_size, data);
+}
+
+static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
+					    unsigned long count,
+					    unsigned long sg_list)
+{
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	return efi_call_virt(update_capsule, capsules, count, sg_list);
+}
+
+static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
+						unsigned long count,
+						u64 *max_size,
+						int *reset_type)
+{
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	return efi_call_virt(query_capsule_caps, capsules, count, max_size,
+			     reset_type);
+}
+
+void efi_native_runtime_setup(void)
+{
+	efi.get_time = virt_efi_get_time;
+	efi.set_time = virt_efi_set_time;
+	efi.get_wakeup_time = virt_efi_get_wakeup_time;
+	efi.set_wakeup_time = virt_efi_set_wakeup_time;
+	efi.get_variable = virt_efi_get_variable;
+	efi.get_next_variable = virt_efi_get_next_variable;
+	efi.set_variable = virt_efi_set_variable;
+	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
+	efi.reset_system = virt_efi_reset_system;
+	efi.query_variable_info = virt_efi_query_variable_info;
+	efi.update_capsule = virt_efi_update_capsule;
+	efi.query_capsule_caps = virt_efi_query_capsule_caps;
+}
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index fe7c0e211f9..57adbc90fda 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -900,8 +900,6 @@ static int mcp23s08_probe(struct spi_device *spi)
 			if (spi_present_mask & (1 << addr))
 				chips++;
 		}
-		if (!chips)
-			return -ENODEV;
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
 		pdata = dev_get_platdata(&spi->dev);
@@ -940,10 +938,6 @@ static int mcp23s08_probe(struct spi_device *spi)
 		if (!(spi_present_mask & (1 << addr)))
 			continue;
 		chips--;
-		if (chips < 0) {
-			dev_err(&spi->dev, "FATAL: invalid negative chip id\n");
-			goto fail;
-		}
 		data->mcp[addr] = &data->chip[chips];
 		status = mcp23s08_probe_one(data->mcp[addr], &spi->dev, spi,
 					    0x40 | (addr << 1), type, base,
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 0c9f803fc1a..b6ae89ea881 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -284,6 +284,7 @@ static int gpio_rcar_irq_domain_map(struct irq_domain *h, unsigned int irq,
 
 static struct irq_domain_ops gpio_rcar_irq_domain_ops = {
 	.map	= gpio_rcar_irq_domain_map,
+	.xlate	= irq_domain_xlate_twocell,
 };
 
 struct gpio_rcar_info {
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index d9c9cb4665d..2ebc9071e35 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2614,7 +2614,7 @@ static struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
 
 		desc = of_get_named_gpiod_flags(dev->of_node, prop_name, idx,
 						&of_flags);
-		if (!IS_ERR(desc))
+		if (!IS_ERR(desc) || (PTR_ERR(desc) == -EPROBE_DEFER))
 			break;
 	}
 
diff --git a/drivers/gpu/Makefile b/drivers/gpu/Makefile
index d8a22c2a579..70da9eb52a4 100644
--- a/drivers/gpu/Makefile
+++ b/drivers/gpu/Makefile
@@ -1,2 +1,3 @@
 obj-y			+= drm/ vga/
 obj-$(CONFIG_TEGRA_HOST1X)	+= host1x/
+obj-$(CONFIG_IMX_IPUV3_CORE)	+= ipu-v3/
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index d1cc2f613a7..f5120046ff8 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -83,6 +83,8 @@ config DRM_KMS_CMA_HELPER
 
 source "drivers/gpu/drm/i2c/Kconfig"
 
+source "drivers/gpu/drm/bridge/Kconfig"
+
 config DRM_TDFX
 	tristate "3dfx Banshee/Voodoo3+"
 	depends on DRM && PCI
@@ -199,5 +201,3 @@ source "drivers/gpu/drm/msm/Kconfig"
 source "drivers/gpu/drm/tegra/Kconfig"
 
 source "drivers/gpu/drm/panel/Kconfig"
-
-source "drivers/gpu/drm/bridge/Kconfig"
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 48e38ba2278..dd2ba426974 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -14,7 +14,7 @@ drm-y       :=	drm_auth.o drm_buffer.o drm_bufs.o drm_cache.o \
 		drm_info.o drm_debugfs.o drm_encoder_slave.o \
 		drm_trace_points.o drm_global.o drm_prime.o \
 		drm_rect.o drm_vma_manager.o drm_flip_work.o \
-		drm_plane_helper.o
+		drm_modeset_lock.o
 
 drm-$(CONFIG_COMPAT) += drm_ioc32.o
 drm-$(CONFIG_DRM_GEM_CMA_HELPER) += drm_gem_cma_helper.o
@@ -23,7 +23,8 @@ drm-$(CONFIG_DRM_PANEL) += drm_panel.o
 
 drm-usb-y   := drm_usb.o
 
-drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_probe_helper.o
+drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_probe_helper.o \
+		drm_plane_helper.o
 drm_kms_helper-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o
 drm_kms_helper-$(CONFIG_DRM_KMS_FB_HELPER) += drm_fb_helper.o
 drm_kms_helper-$(CONFIG_DRM_KMS_CMA_HELPER) += drm_fb_cma_helper.o
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 32982da8269..8ab3cd1a8cd 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -173,7 +173,7 @@ static int armada_drm_load(struct drm_device *dev, unsigned long flags)
 	if (ret)
 		goto err_kms;
 
-	ret = drm_irq_install(dev);
+	ret = drm_irq_install(dev, platform_get_irq(dev->platformdev, 0));
 	if (ret)
 		goto err_kms;
 
@@ -402,7 +402,7 @@ static struct platform_driver armada_drm_platform_driver = {
 
 static int __init armada_drm_init(void)
 {
-	armada_drm_driver.num_ioctls = DRM_ARRAY_SIZE(armada_ioctls);
+	armada_drm_driver.num_ioctls = ARRAY_SIZE(armada_ioctls);
 	return platform_driver_register(&armada_drm_platform_driver);
 }
 module_init(armada_drm_init);
diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c
index 948cb14c561..fd166f532ab 100644
--- a/drivers/gpu/drm/armada/armada_fbdev.c
+++ b/drivers/gpu/drm/armada/armada_fbdev.c
@@ -181,10 +181,8 @@ void armada_fbdev_lastclose(struct drm_device *dev)
 {
 	struct armada_private *priv = dev->dev_private;
 
-	drm_modeset_lock_all(dev);
 	if (priv->fbdev)
-		drm_fb_helper_restore_fbdev_mode(priv->fbdev);
-	drm_modeset_unlock_all(dev);
+		drm_fb_helper_restore_fbdev_mode_unlocked(priv->fbdev);
 }
 
 void armada_fbdev_fini(struct drm_device *dev)
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index 887816f4347..bb9b642d848 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -433,7 +433,6 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
 
 	if (dobj->obj.filp) {
 		struct address_space *mapping;
-		gfp_t gfp;
 		int count;
 
 		count = dobj->obj.size / PAGE_SIZE;
@@ -441,12 +440,11 @@ armada_gem_prime_map_dma_buf(struct dma_buf_attachment *attach,
 			goto free_sgt;
 
 		mapping = file_inode(dobj->obj.filp)->i_mapping;
-		gfp = mapping_gfp_mask(mapping);
 
 		for_each_sg(sgt->sgl, sg, count, i) {
 			struct page *page;
 
-			page = shmem_read_mapping_page_gfp(mapping, i, gfp);
+			page = shmem_read_mapping_page(mapping, i);
 			if (IS_ERR(page)) {
 				num = i;
 				goto release;
diff --git a/drivers/gpu/drm/ast/Makefile b/drivers/gpu/drm/ast/Makefile
index 8df4f284ee2..171aa0622b6 100644
--- a/drivers/gpu/drm/ast/Makefile
+++ b/drivers/gpu/drm/ast/Makefile
@@ -4,6 +4,6 @@
 
 ccflags-y := -Iinclude/drm
 
-ast-y := ast_drv.o ast_main.o ast_mode.o ast_fb.o ast_ttm.o ast_post.o
+ast-y := ast_drv.o ast_main.o ast_mode.o ast_fb.o ast_ttm.o ast_post.o ast_dp501.o
 
-obj-$(CONFIG_DRM_AST) := ast.o
\ No newline at end of file
+obj-$(CONFIG_DRM_AST) := ast.o
diff --git a/drivers/gpu/drm/ast/ast_dp501.c b/drivers/gpu/drm/ast/ast_dp501.c
new file mode 100644
index 00000000000..5da4b62285f
--- /dev/null
+++ b/drivers/gpu/drm/ast/ast_dp501.c
@@ -0,0 +1,410 @@
+
+#include <linux/firmware.h>
+#include <drm/drmP.h>
+#include "ast_drv.h"
+MODULE_FIRMWARE("ast_dp501_fw.bin");
+
+int ast_load_dp501_microcode(struct drm_device *dev)
+{
+	struct ast_private *ast = dev->dev_private;
+	static char *fw_name = "ast_dp501_fw.bin";
+	int err;
+	err = request_firmware(&ast->dp501_fw, fw_name, dev->dev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static void send_ack(struct ast_private *ast)
+{
+	u8 sendack;
+	sendack = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, 0xff);
+	sendack |= 0x80;
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, 0x00, sendack);
+}
+
+static void send_nack(struct ast_private *ast)
+{
+	u8 sendack;
+	sendack = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, 0xff);
+	sendack &= ~0x80;
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, 0x00, sendack);
+}
+
+static bool wait_ack(struct ast_private *ast)
+{
+	u8 waitack;
+	u32 retry = 0;
+	do {
+		waitack = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd2, 0xff);
+		waitack &= 0x80;
+		udelay(100);
+	} while ((!waitack) && (retry++ < 1000));
+
+	if (retry < 1000)
+		return true;
+	else
+		return false;
+}
+
+static bool wait_nack(struct ast_private *ast)
+{
+	u8 waitack;
+	u32 retry = 0;
+	do {
+		waitack = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd2, 0xff);
+		waitack &= 0x80;
+		udelay(100);
+	} while ((waitack) && (retry++ < 1000));
+
+	if (retry < 1000)
+		return true;
+	else
+		return false;
+}
+
+static void set_cmd_trigger(struct ast_private *ast)
+{
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, ~0x40, 0x40);
+}
+
+static void clear_cmd_trigger(struct ast_private *ast)
+{
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9b, ~0x40, 0x00);
+}
+
+#if 0
+static bool wait_fw_ready(struct ast_private *ast)
+{
+	u8 waitready;
+	u32 retry = 0;
+	do {
+		waitready = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd2, 0xff);
+		waitready &= 0x40;
+		udelay(100);
+	} while ((!waitready) && (retry++ < 1000));
+
+	if (retry < 1000)
+		return true;
+	else
+		return false;
+}
+#endif
+
+static bool ast_write_cmd(struct drm_device *dev, u8 data)
+{
+	struct ast_private *ast = dev->dev_private;
+	int retry = 0;
+	if (wait_nack(ast)) {
+		send_nack(ast);
+		ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9a, 0x00, data);
+		send_ack(ast);
+		set_cmd_trigger(ast);
+		do {
+			if (wait_ack(ast)) {
+				clear_cmd_trigger(ast);
+				send_nack(ast);
+				return true;
+			}
+		} while (retry++ < 100);
+	}
+	clear_cmd_trigger(ast);
+	send_nack(ast);
+	return false;
+}
+
+static bool ast_write_data(struct drm_device *dev, u8 data)
+{
+	struct ast_private *ast = dev->dev_private;
+
+	if (wait_nack(ast)) {
+		send_nack(ast);
+		ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9a, 0x00, data);
+		send_ack(ast);
+		if (wait_ack(ast)) {
+			send_nack(ast);
+			return true;
+		}
+	}
+	send_nack(ast);
+	return false;
+}
+
+#if 0
+static bool ast_read_data(struct drm_device *dev, u8 *data)
+{
+	struct ast_private *ast = dev->dev_private;
+	u8 tmp;
+
+	*data = 0;
+
+	if (wait_ack(ast) == false)
+		return false;
+	tmp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd3, 0xff);
+	*data = tmp;
+	if (wait_nack(ast) == false) {
+		send_nack(ast);
+		return false;
+	}
+	send_nack(ast);
+	return true;
+}
+
+static void clear_cmd(struct ast_private *ast)
+{
+	send_nack(ast);
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x9a, 0x00, 0x00);
+}
+#endif
+
+void ast_set_dp501_video_output(struct drm_device *dev, u8 mode)
+{
+	ast_write_cmd(dev, 0x40);
+	ast_write_data(dev, mode);
+
+	msleep(10);
+}
+
+static u32 get_fw_base(struct ast_private *ast)
+{
+	return ast_mindwm(ast, 0x1e6e2104) & 0x7fffffff;
+}
+
+bool ast_backup_fw(struct drm_device *dev, u8 *addr, u32 size)
+{
+	struct ast_private *ast = dev->dev_private;
+	u32 i, data;
+	u32 boot_address;
+
+	data = ast_mindwm(ast, 0x1e6e2100) & 0x01;
+	if (data) {
+		boot_address = get_fw_base(ast);
+		for (i = 0; i < size; i += 4)
+			*(u32 *)(addr + i) = ast_mindwm(ast, boot_address + i);
+		return true;
+	}
+	return false;
+}
+
+bool ast_launch_m68k(struct drm_device *dev)
+{
+	struct ast_private *ast = dev->dev_private;
+	u32 i, data, len = 0;
+	u32 boot_address;
+	u8 *fw_addr = NULL;
+	u8 jreg;
+
+	data = ast_mindwm(ast, 0x1e6e2100) & 0x01;
+	if (!data) {
+
+		if (ast->dp501_fw_addr) {
+			fw_addr = ast->dp501_fw_addr;
+			len = 32*1024;
+		} else if (ast->dp501_fw) {
+			fw_addr = (u8 *)ast->dp501_fw->data;
+			len = ast->dp501_fw->size;
+		}
+		/* Get BootAddress */
+		ast_moutdwm(ast, 0x1e6e2000, 0x1688a8a8);
+		data = ast_mindwm(ast, 0x1e6e0004);
+		switch (data & 0x03) {
+		case 0:
+			boot_address = 0x44000000;
+			break;
+		default:
+		case 1:
+			boot_address = 0x48000000;
+			break;
+		case 2:
+			boot_address = 0x50000000;
+			break;
+		case 3:
+			boot_address = 0x60000000;
+			break;
+		}
+		boot_address -= 0x200000; /* -2MB */
+
+		/* copy image to buffer */
+		for (i = 0; i < len; i += 4) {
+			data = *(u32 *)(fw_addr + i);
+			ast_moutdwm(ast, boot_address + i, data);
+		}
+
+		/* Init SCU */
+		ast_moutdwm(ast, 0x1e6e2000, 0x1688a8a8);
+
+		/* Launch FW */
+		ast_moutdwm(ast, 0x1e6e2104, 0x80000000 + boot_address);
+		ast_moutdwm(ast, 0x1e6e2100, 1);
+
+		/* Update Scratch */
+		data = ast_mindwm(ast, 0x1e6e2040) & 0xfffff1ff;		/* D[11:9] = 100b: UEFI handling */
+		data |= 0x800;
+		ast_moutdwm(ast, 0x1e6e2040, data);
+
+		jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x99, 0xfc); /* D[1:0]: Reserved Video Buffer */
+		jreg |= 0x02;
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x99, jreg);
+	}
+	return true;
+}
+
+u8 ast_get_dp501_max_clk(struct drm_device *dev)
+{
+	struct ast_private *ast = dev->dev_private;
+	u32 boot_address, offset, data;
+	u8 linkcap[4], linkrate, linklanes, maxclk = 0xff;
+
+	boot_address = get_fw_base(ast);
+
+	/* validate FW version */
+	offset = 0xf000;
+	data = ast_mindwm(ast, boot_address + offset);
+	if ((data & 0xf0) != 0x10) /* version: 1x */
+		return maxclk;
+
+	/* Read Link Capability */
+	offset  = 0xf014;
+	*(u32 *)linkcap = ast_mindwm(ast, boot_address + offset);
+	if (linkcap[2] == 0) {
+		linkrate = linkcap[0];
+		linklanes = linkcap[1];
+		data = (linkrate == 0x0a) ? (90 * linklanes) : (54 * linklanes);
+		if (data > 0xff)
+			data = 0xff;
+		maxclk = (u8)data;
+	}
+	return maxclk;
+}
+
+bool ast_dp501_read_edid(struct drm_device *dev, u8 *ediddata)
+{
+	struct ast_private *ast = dev->dev_private;
+	u32 i, boot_address, offset, data;
+
+	boot_address = get_fw_base(ast);
+
+	/* validate FW version */
+	offset = 0xf000;
+	data = ast_mindwm(ast, boot_address + offset);
+	if ((data & 0xf0) != 0x10)
+		return false;
+
+	/* validate PnP Monitor */
+	offset = 0xf010;
+	data = ast_mindwm(ast, boot_address + offset);
+	if (!(data & 0x01))
+		return false;
+
+	/* Read EDID */
+	offset = 0xf020;
+	for (i = 0; i < 128; i += 4) {
+		data = ast_mindwm(ast, boot_address + offset + i);
+		*(u32 *)(ediddata + i) = data;
+	}
+
+	return true;
+}
+
+static bool ast_init_dvo(struct drm_device *dev)
+{
+	struct ast_private *ast = dev->dev_private;
+	u8 jreg;
+	u32 data;
+	ast_write32(ast, 0xf004, 0x1e6e0000);
+	ast_write32(ast, 0xf000, 0x1);
+	ast_write32(ast, 0x12000, 0x1688a8a8);
+
+	jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd0, 0xff);
+	if (!(jreg & 0x80)) {
+		/* Init SCU DVO Settings */
+		data = ast_read32(ast, 0x12008);
+		/* delay phase */
+		data &= 0xfffff8ff;
+		data |= 0x00000500;
+		ast_write32(ast, 0x12008, data);
+
+		if (ast->chip == AST2300) {
+			data = ast_read32(ast, 0x12084);
+			/* multi-pins for DVO single-edge */
+			data |= 0xfffe0000;
+			ast_write32(ast, 0x12084, data);
+
+			data = ast_read32(ast, 0x12088);
+			/* multi-pins for DVO single-edge */
+			data |= 0x000fffff;
+			ast_write32(ast, 0x12088, data);
+
+			data = ast_read32(ast, 0x12090);
+			/* multi-pins for DVO single-edge */
+			data &= 0xffffffcf;
+			data |= 0x00000020;
+			ast_write32(ast, 0x12090, data);
+		} else { /* AST2400 */
+			data = ast_read32(ast, 0x12088);
+			/* multi-pins for DVO single-edge */
+			data |= 0x30000000;
+			ast_write32(ast, 0x12088, data);
+
+			data = ast_read32(ast, 0x1208c);
+			/* multi-pins for DVO single-edge */
+			data |= 0x000000cf;
+			ast_write32(ast, 0x1208c, data);
+
+			data = ast_read32(ast, 0x120a4);
+			/* multi-pins for DVO single-edge */
+			data |= 0xffff0000;
+			ast_write32(ast, 0x120a4, data);
+
+			data = ast_read32(ast, 0x120a8);
+			/* multi-pins for DVO single-edge */
+			data |= 0x0000000f;
+			ast_write32(ast, 0x120a8, data);
+
+			data = ast_read32(ast, 0x12094);
+			/* multi-pins for DVO single-edge */
+			data |= 0x00000002;
+			ast_write32(ast, 0x12094, data);
+		}
+	}
+
+	/* Force to DVO */
+	data = ast_read32(ast, 0x1202c);
+	data &= 0xfffbffff;
+	ast_write32(ast, 0x1202c, data);
+
+	/* Init VGA DVO Settings */
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80);
+	return true;
+}
+
+void ast_init_3rdtx(struct drm_device *dev)
+{
+	struct ast_private *ast = dev->dev_private;
+	u8 jreg;
+	u32 data;
+	if (ast->chip == AST2300 || ast->chip == AST2400) {
+		jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff);
+		switch (jreg & 0x0e) {
+		case 0x04:
+			ast_init_dvo(dev);
+			break;
+		case 0x08:
+			ast_launch_m68k(dev);
+			break;
+		case 0x0c:
+			ast_init_dvo(dev);
+			break;
+		default:
+			if (ast->tx_chip_type == AST_TX_SIL164)
+				ast_init_dvo(dev);
+			else {
+				ast_write32(ast, 0x12000, 0x1688a8a8);
+				data = ast_read32(ast, 0x1202c);
+				data &= 0xfffcffff;
+				ast_write32(ast, 0, data);
+			}
+		}
+	}
+}
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index 5137f15dba1..44074fbcf7f 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -94,9 +94,7 @@ static int ast_drm_thaw(struct drm_device *dev)
 	ast_post_gpu(dev);
 
 	drm_mode_config_reset(dev);
-	drm_modeset_lock_all(dev);
 	drm_helper_resume_force_mode(dev);
-	drm_modeset_unlock_all(dev);
 
 	console_lock();
 	ast_fbdev_set_suspend(dev, 0);
@@ -198,7 +196,6 @@ static const struct file_operations ast_fops = {
 
 static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM,
-	.dev_priv_size = 0,
 
 	.load = ast_driver_load,
 	.unload = ast_driver_unload,
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 9833a1b1acc..5d6a87573c3 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -61,9 +61,17 @@ enum ast_chip {
 	AST2200,
 	AST2150,
 	AST2300,
+	AST2400,
 	AST1180,
 };
 
+enum ast_tx_chip {
+	AST_TX_NONE,
+	AST_TX_SIL164,
+	AST_TX_ITE66121,
+	AST_TX_DP501,
+};
+
 #define AST_DRAM_512Mx16 0
 #define AST_DRAM_1Gx16   1
 #define AST_DRAM_512Mx32 2
@@ -102,6 +110,12 @@ struct ast_private {
 	 * we have. */
 	struct ttm_bo_kmap_obj cache_kmap;
 	int next_cursor;
+	bool support_wide_screen;
+
+	enum ast_tx_chip tx_chip_type;
+	u8 dp501_maxclk;
+	u8 *dp501_fw_addr;
+	const struct firmware *dp501_fw;	/* dp501 fw */
 };
 
 int ast_driver_load(struct drm_device *dev, unsigned long flags);
@@ -368,4 +382,14 @@ int ast_mmap(struct file *filp, struct vm_area_struct *vma);
 
 /* ast post */
 void ast_post_gpu(struct drm_device *dev);
+u32 ast_mindwm(struct ast_private *ast, u32 r);
+void ast_moutdwm(struct ast_private *ast, u32 r, u32 v);
+/* ast dp501 */
+int ast_load_dp501_microcode(struct drm_device *dev);
+void ast_set_dp501_video_output(struct drm_device *dev, u8 mode);
+bool ast_launch_m68k(struct drm_device *dev);
+bool ast_backup_fw(struct drm_device *dev, u8 *addr, u32 size);
+bool ast_dp501_read_edid(struct drm_device *dev, u8 *ediddata);
+u8 ast_get_dp501_max_clk(struct drm_device *dev);
+void ast_init_3rdtx(struct drm_device *dev);
 #endif
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 50535fd5a88..a2cc6be9798 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -66,12 +66,16 @@ uint8_t ast_get_index_reg_mask(struct ast_private *ast,
 static int ast_detect_chip(struct drm_device *dev)
 {
 	struct ast_private *ast = dev->dev_private;
+	uint32_t data, jreg;
 
 	if (dev->pdev->device == PCI_CHIP_AST1180) {
 		ast->chip = AST1100;
 		DRM_INFO("AST 1180 detected\n");
 	} else {
-		if (dev->pdev->revision >= 0x20) {
+		if (dev->pdev->revision >= 0x30) {
+			ast->chip = AST2400;
+			DRM_INFO("AST 2400 detected\n");
+		} else if (dev->pdev->revision >= 0x20) {
 			ast->chip = AST2300;
 			DRM_INFO("AST 2300 detected\n");
 		} else if (dev->pdev->revision >= 0x10) {
@@ -104,6 +108,59 @@ static int ast_detect_chip(struct drm_device *dev)
 			DRM_INFO("AST 2000 detected\n");
 		}
 	}
+
+	switch (ast->chip) {
+	case AST1180:
+		ast->support_wide_screen = true;
+		break;
+	case AST2000:
+		ast->support_wide_screen = false;
+		break;
+	default:
+		jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd0, 0xff);
+		if (!(jreg & 0x80))
+			ast->support_wide_screen = true;
+		else if (jreg & 0x01)
+			ast->support_wide_screen = true;
+		else {
+			ast->support_wide_screen = false;
+			ast_write32(ast, 0xf004, 0x1e6e0000);
+			ast_write32(ast, 0xf000, 0x1);
+			data = ast_read32(ast, 0x1207c);
+			data &= 0x300;
+			if (ast->chip == AST2300 && data == 0x0) /* ast1300 */
+				ast->support_wide_screen = true;
+			if (ast->chip == AST2400 && data == 0x100) /* ast1400 */
+				ast->support_wide_screen = true;
+		}
+		break;
+	}
+
+	ast->tx_chip_type = AST_TX_NONE;
+	jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xff);
+	if (jreg & 0x80)
+		ast->tx_chip_type = AST_TX_SIL164;
+	if ((ast->chip == AST2300) || (ast->chip == AST2400)) {
+		jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff);
+		switch (jreg) {
+		case 0x04:
+			ast->tx_chip_type = AST_TX_SIL164;
+			break;
+		case 0x08:
+			ast->dp501_fw_addr = kzalloc(32*1024, GFP_KERNEL);
+			if (ast->dp501_fw_addr) {
+				/* backup firmware */
+				if (ast_backup_fw(dev, ast->dp501_fw_addr, 32*1024)) {
+					kfree(ast->dp501_fw_addr);
+					ast->dp501_fw_addr = NULL;
+				}
+			}
+			/* fallthrough */
+		case 0x0c:
+			ast->tx_chip_type = AST_TX_DP501;
+		}
+	}
+
 	return 0;
 }
 
@@ -129,7 +186,7 @@ static int ast_get_dram_info(struct drm_device *dev)
 	else
 		ast->dram_bus_width = 32;
 
-	if (ast->chip == AST2300) {
+	if (ast->chip == AST2300 || ast->chip == AST2400) {
 		switch (data & 0x03) {
 		case 0:
 			ast->dram_type = AST_DRAM_512Mx16;
@@ -257,17 +314,32 @@ static u32 ast_get_vram_info(struct drm_device *dev)
 {
 	struct ast_private *ast = dev->dev_private;
 	u8 jreg;
-
+	u32 vram_size;
 	ast_open_key(ast);
 
+	vram_size = AST_VIDMEM_DEFAULT_SIZE;
 	jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xaa, 0xff);
 	switch (jreg & 3) {
-	case 0: return AST_VIDMEM_SIZE_8M;
-	case 1: return AST_VIDMEM_SIZE_16M;
-	case 2: return AST_VIDMEM_SIZE_32M;
-	case 3: return AST_VIDMEM_SIZE_64M;
+	case 0: vram_size = AST_VIDMEM_SIZE_8M; break;
+	case 1: vram_size = AST_VIDMEM_SIZE_16M; break;
+	case 2: vram_size = AST_VIDMEM_SIZE_32M; break;
+	case 3: vram_size = AST_VIDMEM_SIZE_64M; break;
+	}
+
+	jreg = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x99, 0xff);
+	switch (jreg & 0x03) {
+	case 1:
+		vram_size -= 0x100000;
+		break;
+	case 2:
+		vram_size -= 0x200000;
+		break;
+	case 3:
+		vram_size -= 0x400000;
+		break;
 	}
-	return AST_VIDMEM_DEFAULT_SIZE;
+
+	return vram_size;
 }
 
 int ast_driver_load(struct drm_device *dev, unsigned long flags)
@@ -316,6 +388,7 @@ int ast_driver_load(struct drm_device *dev, unsigned long flags)
 	if (ast->chip == AST2100 ||
 	    ast->chip == AST2200 ||
 	    ast->chip == AST2300 ||
+	    ast->chip == AST2400 ||
 	    ast->chip == AST1180) {
 		dev->mode_config.max_width = 1920;
 		dev->mode_config.max_height = 2048;
@@ -343,6 +416,7 @@ int ast_driver_unload(struct drm_device *dev)
 {
 	struct ast_private *ast = dev->dev_private;
 
+	kfree(ast->dp501_fw_addr);
 	ast_mode_fini(dev);
 	ast_fbdev_fini(dev);
 	drm_mode_config_cleanup(dev);
@@ -411,16 +485,13 @@ static void ast_bo_unref(struct ast_bo **bo)
 
 	tbo = &((*bo)->bo);
 	ttm_bo_unref(&tbo);
-	if (tbo == NULL)
-		*bo = NULL;
-
+	*bo = NULL;
 }
+
 void ast_gem_free_object(struct drm_gem_object *obj)
 {
 	struct ast_bo *ast_bo = gem_to_ast_bo(obj);
 
-	if (!ast_bo)
-		return;
 	ast_bo_unref(&ast_bo);
 }
 
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index a4afdc8bb57..114aee941d4 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -115,11 +115,17 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		else
 			vbios_mode->enh_table = &res_1280x1024[refresh_rate_index];
 		break;
+	case 1360:
+		vbios_mode->enh_table = &res_1360x768[refresh_rate_index];
+		break;
 	case 1440:
 		vbios_mode->enh_table = &res_1440x900[refresh_rate_index];
 		break;
 	case 1600:
-		vbios_mode->enh_table = &res_1600x1200[refresh_rate_index];
+		if (crtc->mode.crtc_vdisplay == 900)
+			vbios_mode->enh_table = &res_1600x900[refresh_rate_index];
+		else
+			vbios_mode->enh_table = &res_1600x1200[refresh_rate_index];
 		break;
 	case 1680:
 		vbios_mode->enh_table = &res_1680x1050[refresh_rate_index];
@@ -175,14 +181,17 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8d, refresh_rate_index & 0xff);
 		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8e, mode_id & 0xff);
 
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8);
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x92, crtc->primary->fb->bits_per_pixel);
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x93, adjusted_mode->clock / 1000);
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x94, adjusted_mode->crtc_hdisplay);
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x95, adjusted_mode->crtc_hdisplay >> 8);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0x00);
+		if (vbios_mode->enh_table->flags & NewModeInfo) {
+			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8);
+			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x92, crtc->primary->fb->bits_per_pixel);
+			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x93, adjusted_mode->clock / 1000);
+			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x94, adjusted_mode->crtc_hdisplay);
+			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x95, adjusted_mode->crtc_hdisplay >> 8);
 
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x96, adjusted_mode->crtc_vdisplay);
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x97, adjusted_mode->crtc_vdisplay >> 8);
+			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x96, adjusted_mode->crtc_vdisplay);
+			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x97, adjusted_mode->crtc_vdisplay >> 8);
+		}
 	}
 
 	return true;
@@ -389,7 +398,7 @@ static void ast_set_ext_reg(struct drm_crtc *crtc, struct drm_display_mode *mode
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa8, 0xfd, jregA8);
 
 	/* Set Threshold */
-	if (ast->chip == AST2300) {
+	if (ast->chip == AST2300 || ast->chip == AST2400) {
 		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa7, 0x78);
 		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa6, 0x60);
 	} else if (ast->chip == AST2100 ||
@@ -451,9 +460,13 @@ static void ast_crtc_dpms(struct drm_crtc *crtc, int mode)
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 		ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0);
+		if (ast->tx_chip_type == AST_TX_DP501)
+			ast_set_dp501_video_output(crtc->dev, 1);
 		ast_crtc_load_lut(crtc);
 		break;
 	case DRM_MODE_DPMS_OFF:
+		if (ast->tx_chip_type == AST_TX_DP501)
+			ast_set_dp501_video_output(crtc->dev, 0);
 		ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0x20);
 		break;
 	}
@@ -729,10 +742,24 @@ static int ast_encoder_init(struct drm_device *dev)
 static int ast_get_modes(struct drm_connector *connector)
 {
 	struct ast_connector *ast_connector = to_ast_connector(connector);
+	struct ast_private *ast = connector->dev->dev_private;
 	struct edid *edid;
 	int ret;
-
-	edid = drm_get_edid(connector, &ast_connector->i2c->adapter);
+	bool flags = false;
+	if (ast->tx_chip_type == AST_TX_DP501) {
+		ast->dp501_maxclk = 0xff;
+		edid = kmalloc(128, GFP_KERNEL);
+		if (!edid)
+			return -ENOMEM;
+
+		flags = ast_dp501_read_edid(connector->dev, (u8 *)edid);
+		if (flags)
+			ast->dp501_maxclk = ast_get_dp501_max_clk(connector->dev);
+		else
+			kfree(edid);
+	}
+	if (!flags)
+		edid = drm_get_edid(connector, &ast_connector->i2c->adapter);
 	if (edid) {
 		drm_mode_connector_update_edid_property(&ast_connector->base, edid);
 		ret = drm_add_edid_modes(connector, edid);
@@ -746,7 +773,56 @@ static int ast_get_modes(struct drm_connector *connector)
 static int ast_mode_valid(struct drm_connector *connector,
 			  struct drm_display_mode *mode)
 {
-	return MODE_OK;
+	struct ast_private *ast = connector->dev->dev_private;
+	int flags = MODE_NOMODE;
+	uint32_t jtemp;
+
+	if (ast->support_wide_screen) {
+		if ((mode->hdisplay == 1680) && (mode->vdisplay == 1050))
+			return MODE_OK;
+		if ((mode->hdisplay == 1280) && (mode->vdisplay == 800))
+			return MODE_OK;
+		if ((mode->hdisplay == 1440) && (mode->vdisplay == 900))
+			return MODE_OK;
+		if ((mode->hdisplay == 1360) && (mode->vdisplay == 768))
+			return MODE_OK;
+		if ((mode->hdisplay == 1600) && (mode->vdisplay == 900))
+			return MODE_OK;
+
+		if ((ast->chip == AST2100) || (ast->chip == AST2200) || (ast->chip == AST2300) || (ast->chip == AST2400) || (ast->chip == AST1180)) {
+			if ((mode->hdisplay == 1920) && (mode->vdisplay == 1080))
+				return MODE_OK;
+
+			if ((mode->hdisplay == 1920) && (mode->vdisplay == 1200)) {
+				jtemp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xd1, 0xff);
+				if (jtemp & 0x01)
+					return MODE_NOMODE;
+				else
+					return MODE_OK;
+			}
+		}
+	}
+	switch (mode->hdisplay) {
+	case 640:
+		if (mode->vdisplay == 480) flags = MODE_OK;
+		break;
+	case 800:
+		if (mode->vdisplay == 600) flags = MODE_OK;
+		break;
+	case 1024:
+		if (mode->vdisplay == 768) flags = MODE_OK;
+		break;
+	case 1280:
+		if (mode->vdisplay == 1024) flags = MODE_OK;
+		break;
+	case 1600:
+		if (mode->vdisplay == 1200) flags = MODE_OK;
+		break;
+	default:
+		return flags;
+	}
+
+	return flags;
 }
 
 static void ast_connector_destroy(struct drm_connector *connector)
diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c
index 635f6ffc27c..38d437f3a26 100644
--- a/drivers/gpu/drm/ast/ast_post.c
+++ b/drivers/gpu/drm/ast/ast_post.c
@@ -78,7 +78,7 @@ ast_set_def_ext_reg(struct drm_device *dev)
 	for (i = 0x81; i <= 0x8f; i++)
 		ast_set_index_reg(ast, AST_IO_CRTC_PORT, i, 0x00);
 
-	if (ast->chip == AST2300) {
+	if (ast->chip == AST2300 || ast->chip == AST2400) {
 		if (dev->pdev->revision >= 0x20)
 			ext_reg_info = extreginfo_ast2300;
 		else
@@ -102,23 +102,32 @@ ast_set_def_ext_reg(struct drm_device *dev)
 
 	/* Enable RAMDAC for A1 */
 	reg = 0x04;
-	if (ast->chip == AST2300)
+	if (ast->chip == AST2300 || ast->chip == AST2400)
 		reg |= 0x20;
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb6, 0xff, reg);
 }
 
-static inline u32 mindwm(struct ast_private *ast, u32 r)
+u32 ast_mindwm(struct ast_private *ast, u32 r)
 {
+	uint32_t data;
+
 	ast_write32(ast, 0xf004, r & 0xffff0000);
 	ast_write32(ast, 0xf000, 0x1);
 
+	do {
+		data = ast_read32(ast, 0xf004) & 0xffff0000;
+	} while (data != (r & 0xffff0000));
 	return ast_read32(ast, 0x10000 + (r & 0x0000ffff));
 }
 
-static inline void moutdwm(struct ast_private *ast, u32 r, u32 v)
+void ast_moutdwm(struct ast_private *ast, u32 r, u32 v)
 {
+	uint32_t data;
 	ast_write32(ast, 0xf004, r & 0xffff0000);
 	ast_write32(ast, 0xf000, 0x1);
+	do {
+		data = ast_read32(ast, 0xf004) & 0xffff0000;
+	} while (data != (r & 0xffff0000));
 	ast_write32(ast, 0x10000 + (r & 0x0000ffff), v);
 }
 
@@ -154,28 +163,28 @@ static u32 mmctestburst2_ast2150(struct ast_private *ast, u32 datagen)
 {
 	u32 data, timeout;
 
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
-	moutdwm(ast, 0x1e6e0070, 0x00000001 | (datagen << 3));
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000001 | (datagen << 3));
 	timeout = 0;
 	do {
-		data = mindwm(ast, 0x1e6e0070) & 0x40;
+		data = ast_mindwm(ast, 0x1e6e0070) & 0x40;
 		if (++timeout > TIMEOUT_AST2150) {
-			moutdwm(ast, 0x1e6e0070, 0x00000000);
+			ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
 			return 0xffffffff;
 		}
 	} while (!data);
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
-	moutdwm(ast, 0x1e6e0070, 0x00000003 | (datagen << 3));
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000003 | (datagen << 3));
 	timeout = 0;
 	do {
-		data = mindwm(ast, 0x1e6e0070) & 0x40;
+		data = ast_mindwm(ast, 0x1e6e0070) & 0x40;
 		if (++timeout > TIMEOUT_AST2150) {
-			moutdwm(ast, 0x1e6e0070, 0x00000000);
+			ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
 			return 0xffffffff;
 		}
 	} while (!data);
-	data = (mindwm(ast, 0x1e6e0070) & 0x80) >> 7;
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
+	data = (ast_mindwm(ast, 0x1e6e0070) & 0x80) >> 7;
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
 	return data;
 }
 
@@ -184,18 +193,18 @@ static u32 mmctestsingle2_ast2150(struct ast_private *ast, u32 datagen)
 {
 	u32 data, timeout;
 
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
-	moutdwm(ast, 0x1e6e0070, 0x00000005 | (datagen << 3));
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000005 | (datagen << 3));
 	timeout = 0;
 	do {
-		data = mindwm(ast, 0x1e6e0070) & 0x40;
+		data = ast_mindwm(ast, 0x1e6e0070) & 0x40;
 		if (++timeout > TIMEOUT_AST2150) {
-			moutdwm(ast, 0x1e6e0070, 0x00000000);
+			ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
 			return 0xffffffff;
 		}
 	} while (!data);
-	data = (mindwm(ast, 0x1e6e0070) & 0x80) >> 7;
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
+	data = (ast_mindwm(ast, 0x1e6e0070) & 0x80) >> 7;
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
 	return data;
 }
 #endif
@@ -215,7 +224,7 @@ static int cbrscan_ast2150(struct ast_private *ast, int busw)
 	u32 patcnt, loop;
 
 	for (patcnt = 0; patcnt < CBR_PATNUM_AST2150; patcnt++) {
-		moutdwm(ast, 0x1e6e007c, pattern_AST2150[patcnt]);
+		ast_moutdwm(ast, 0x1e6e007c, pattern_AST2150[patcnt]);
 		for (loop = 0; loop < CBR_PASSNUM_AST2150; loop++) {
 			if (cbrtest_ast2150(ast))
 				break;
@@ -237,7 +246,7 @@ cbr_start:
 	passcnt = 0;
 
 	for (dlli = 0; dlli < 100; dlli++) {
-		moutdwm(ast, 0x1e6e0068, dlli | (dlli << 8) | (dlli << 16) | (dlli << 24));
+		ast_moutdwm(ast, 0x1e6e0068, dlli | (dlli << 8) | (dlli << 16) | (dlli << 24));
 		data = cbrscan_ast2150(ast, busw);
 		if (data != 0) {
 			if (data & 0x1) {
@@ -254,7 +263,7 @@ cbr_start:
 		goto cbr_start;
 
 	dlli = dll_min[0] + (((dll_max[0] - dll_min[0]) * 7) >> 4);
-	moutdwm(ast, 0x1e6e0068, dlli | (dlli << 8) | (dlli << 16) | (dlli << 24));
+	ast_moutdwm(ast, 0x1e6e0068, dlli | (dlli << 8) | (dlli << 16) | (dlli << 24));
 }
 
 
@@ -365,10 +374,12 @@ void ast_post_gpu(struct drm_device *dev)
 	ast_open_key(ast);
 	ast_set_def_ext_reg(dev);
 
-	if (ast->chip == AST2300)
+	if (ast->chip == AST2300 || ast->chip == AST2400)
 		ast_init_dram_2300(dev);
 	else
 		ast_init_dram_reg(dev);
+
+	ast_init_3rdtx(dev);
 }
 
 /* AST 2300 DRAM settings */
@@ -403,6 +414,7 @@ struct ast2300_dram_param {
 /*
  * DQSI DLL CBR Setting
  */
+#define CBR_SIZE0            ((1  << 10) - 1)
 #define CBR_SIZE1            ((4  << 10) - 1)
 #define CBR_SIZE2            ((64 << 10) - 1)
 #define CBR_PASSNUM          5
@@ -423,88 +435,84 @@ static const u32 pattern[8] = {
 	0x7C61D253
 };
 
-#if 0 /* unused in DDX, included for completeness */
 static int mmc_test_burst(struct ast_private *ast, u32 datagen)
 {
 	u32 data, timeout;
 
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
-	moutdwm(ast, 0x1e6e0070, 0x000000c1 | (datagen << 3));
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
+	ast_moutdwm(ast, 0x1e6e0070, 0x000000c1 | (datagen << 3));
 	timeout = 0;
 	do {
-		data = mindwm(ast, 0x1e6e0070) & 0x3000;
+		data = ast_mindwm(ast, 0x1e6e0070) & 0x3000;
 		if (data & 0x2000) {
 			return 0;
 		}
 		if (++timeout > TIMEOUT) {
-			moutdwm(ast, 0x1e6e0070, 0x00000000);
+			ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
 			return 0;
 		}
 	} while (!data);
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
 	return 1;
 }
-#endif
 
 static int mmc_test_burst2(struct ast_private *ast, u32 datagen)
 {
 	u32 data, timeout;
 
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
-	moutdwm(ast, 0x1e6e0070, 0x00000041 | (datagen << 3));
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000041 | (datagen << 3));
 	timeout = 0;
 	do {
-		data = mindwm(ast, 0x1e6e0070) & 0x1000;
+		data = ast_mindwm(ast, 0x1e6e0070) & 0x1000;
 		if (++timeout > TIMEOUT) {
-			moutdwm(ast, 0x1e6e0070, 0x0);
+			ast_moutdwm(ast, 0x1e6e0070, 0x0);
 			return -1;
 		}
 	} while (!data);
-	data = mindwm(ast, 0x1e6e0078);
+	data = ast_mindwm(ast, 0x1e6e0078);
 	data = (data | (data >> 16)) & 0xffff;
-	moutdwm(ast, 0x1e6e0070, 0x0);
+	ast_moutdwm(ast, 0x1e6e0070, 0x0);
 	return data;
 }
 
-#if 0 /* Unused in DDX here for completeness */
 static int mmc_test_single(struct ast_private *ast, u32 datagen)
 {
 	u32 data, timeout;
 
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
-	moutdwm(ast, 0x1e6e0070, 0x000000c5 | (datagen << 3));
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
+	ast_moutdwm(ast, 0x1e6e0070, 0x000000c5 | (datagen << 3));
 	timeout = 0;
 	do {
-		data = mindwm(ast, 0x1e6e0070) & 0x3000;
+		data = ast_mindwm(ast, 0x1e6e0070) & 0x3000;
 		if (data & 0x2000)
 			return 0;
 		if (++timeout > TIMEOUT) {
-			moutdwm(ast, 0x1e6e0070, 0x0);
+			ast_moutdwm(ast, 0x1e6e0070, 0x0);
 			return 0;
 		}
 	} while (!data);
-	moutdwm(ast, 0x1e6e0070, 0x0);
+	ast_moutdwm(ast, 0x1e6e0070, 0x0);
 	return 1;
 }
-#endif
 
 static int mmc_test_single2(struct ast_private *ast, u32 datagen)
 {
 	u32 data, timeout;
 
-	moutdwm(ast, 0x1e6e0070, 0x00000000);
-	moutdwm(ast, 0x1e6e0070, 0x00000005 | (datagen << 3));
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000000);
+	ast_moutdwm(ast, 0x1e6e0070, 0x00000005 | (datagen << 3));
 	timeout = 0;
 	do {
-		data = mindwm(ast, 0x1e6e0070) & 0x1000;
+		data = ast_mindwm(ast, 0x1e6e0070) & 0x1000;
 		if (++timeout > TIMEOUT) {
-			moutdwm(ast, 0x1e6e0070, 0x0);
+			ast_moutdwm(ast, 0x1e6e0070, 0x0);
 			return -1;
 		}
 	} while (!data);
-	data = mindwm(ast, 0x1e6e0078);
+	data = ast_mindwm(ast, 0x1e6e0078);
 	data = (data | (data >> 16)) & 0xffff;
-	moutdwm(ast, 0x1e6e0070, 0x0);
+	ast_moutdwm(ast, 0x1e6e0070, 0x0);
 	return data;
 }
 
@@ -533,7 +541,7 @@ static int cbr_scan(struct ast_private *ast)
 
 	data2 = 3;
 	for (patcnt = 0; patcnt < CBR_PATNUM; patcnt++) {
-		moutdwm(ast, 0x1e6e007c, pattern[patcnt]);
+		ast_moutdwm(ast, 0x1e6e007c, pattern[patcnt]);
 		for (loop = 0; loop < CBR_PASSNUM2; loop++) {
 			if ((data = cbr_test(ast)) != 0) {
 				data2 &= data;
@@ -568,7 +576,7 @@ static u32 cbr_scan2(struct ast_private *ast)
 
 	data2 = 0xffff;
 	for (patcnt = 0; patcnt < CBR_PATNUM; patcnt++) {
-		moutdwm(ast, 0x1e6e007c, pattern[patcnt]);
+		ast_moutdwm(ast, 0x1e6e007c, pattern[patcnt]);
 		for (loop = 0; loop < CBR_PASSNUM2; loop++) {
 			if ((data = cbr_test2(ast)) != 0) {
 				data2 &= data;
@@ -583,106 +591,35 @@ static u32 cbr_scan2(struct ast_private *ast)
 	return data2;
 }
 
-#if 0 /* unused in DDX - added for completeness */
-static void finetuneDQI(struct ast_private *ast, struct ast2300_dram_param *param)
+static u32 cbr_test3(struct ast_private *ast)
 {
-	u32 gold_sadj[2], dllmin[16], dllmax[16], dlli, data, cnt, mask, passcnt;
-
-	gold_sadj[0] = (mindwm(ast, 0x1E6E0024) >> 16) & 0xffff;
-	gold_sadj[1] = gold_sadj[0] >> 8;
-	gold_sadj[0] = gold_sadj[0] & 0xff;
-	gold_sadj[0] = (gold_sadj[0] + gold_sadj[1]) >> 1;
-	gold_sadj[1] = gold_sadj[0];
-
-	for (cnt = 0; cnt < 16; cnt++) {
-		dllmin[cnt] = 0xff;
-		dllmax[cnt] = 0x0;
-	}
-	passcnt = 0;
-	for (dlli = 0; dlli < 76; dlli++) {
-		moutdwm(ast, 0x1E6E0068, 0x00001400 | (dlli << 16) | (dlli << 24));
-		/* Wait DQSI latch phase calibration */
-		moutdwm(ast, 0x1E6E0074, 0x00000010);
-		moutdwm(ast, 0x1E6E0070, 0x00000003);
-		do {
-			data = mindwm(ast, 0x1E6E0070);
-		} while (!(data & 0x00001000));
-		moutdwm(ast, 0x1E6E0070, 0x00000000);
+	if (!mmc_test_burst(ast, 0))
+		return 0;
+	if (!mmc_test_single(ast, 0))
+		return 0;
+	return 1;
+}
 
-		moutdwm(ast, 0x1E6E0074, CBR_SIZE1);
-		data = cbr_scan2(ast);
-		if (data != 0) {
-			mask = 0x00010001;
-			for (cnt = 0; cnt < 16; cnt++) {
-				if (data & mask) {
-					if (dllmin[cnt] > dlli) {
-						dllmin[cnt] = dlli;
-					}
-					if (dllmax[cnt] < dlli) {
-						dllmax[cnt] = dlli;
-					}
-				}
-				mask <<= 1;
-			}
-			passcnt++;
-		} else if (passcnt >= CBR_THRESHOLD) {
-			break;
-		}
-	}
-	data = 0;
-	for (cnt = 0; cnt < 8; cnt++) {
-		data >>= 3;
-		if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD)) {
-			dlli = (dllmin[cnt] + dllmax[cnt]) >> 1;
-			if (gold_sadj[0] >= dlli) {
-				dlli = (gold_sadj[0] - dlli) >> 1;
-				if (dlli > 3) {
-					dlli = 3;
-				}
-			} else {
-				dlli = (dlli - gold_sadj[0]) >> 1;
-				if (dlli > 4) {
-					dlli = 4;
-				}
-				dlli = (8 - dlli) & 0x7;
-			}
-			data |= dlli << 21;
-		}
-	}
-	moutdwm(ast, 0x1E6E0080, data);
+static u32 cbr_scan3(struct ast_private *ast)
+{
+	u32 patcnt, loop;
 
-	data = 0;
-	for (cnt = 8; cnt < 16; cnt++) {
-		data >>= 3;
-		if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD)) {
-			dlli = (dllmin[cnt] + dllmax[cnt]) >> 1;
-			if (gold_sadj[1] >= dlli) {
-				dlli = (gold_sadj[1] - dlli) >> 1;
-				if (dlli > 3) {
-					dlli = 3;
-				} else {
-					dlli = (dlli - 1) & 0x7;
-				}
-			} else {
-				dlli = (dlli - gold_sadj[1]) >> 1;
-				dlli += 1;
-				if (dlli > 4) {
-					dlli = 4;
-				}
-				dlli = (8 - dlli) & 0x7;
-			}
-			data |= dlli << 21;
+	for (patcnt = 0; patcnt < CBR_PATNUM; patcnt++) {
+		ast_moutdwm(ast, 0x1e6e007c, pattern[patcnt]);
+		for (loop = 0; loop < 2; loop++) {
+			if (cbr_test3(ast))
+				break;
 		}
+		if (loop == 2)
+			return 0;
 	}
-	moutdwm(ast, 0x1E6E0084, data);
-
-} /* finetuneDQI */
-#endif
+	return 1;
+}
 
-static void finetuneDQI_L(struct ast_private *ast, struct ast2300_dram_param *param)
+static bool finetuneDQI_L(struct ast_private *ast, struct ast2300_dram_param *param)
 {
-	u32 gold_sadj[2], dllmin[16], dllmax[16], dlli, data, cnt, mask, passcnt;
-
+	u32 gold_sadj[2], dllmin[16], dllmax[16], dlli, data, cnt, mask, passcnt, retry = 0;
+	bool status = false;
 FINETUNE_START:
 	for (cnt = 0; cnt < 16; cnt++) {
 		dllmin[cnt] = 0xff;
@@ -690,16 +627,8 @@ FINETUNE_START:
 	}
 	passcnt = 0;
 	for (dlli = 0; dlli < 76; dlli++) {
-		moutdwm(ast, 0x1E6E0068, 0x00001400 | (dlli << 16) | (dlli << 24));
-		/* Wait DQSI latch phase calibration */
-		moutdwm(ast, 0x1E6E0074, 0x00000010);
-		moutdwm(ast, 0x1E6E0070, 0x00000003);
-		do {
-			data = mindwm(ast, 0x1E6E0070);
-		} while (!(data & 0x00001000));
-		moutdwm(ast, 0x1E6E0070, 0x00000000);
-
-		moutdwm(ast, 0x1E6E0074, CBR_SIZE1);
+		ast_moutdwm(ast, 0x1E6E0068, 0x00001400 | (dlli << 16) | (dlli << 24));
+		ast_moutdwm(ast, 0x1E6E0074, CBR_SIZE1);
 		data = cbr_scan2(ast);
 		if (data != 0) {
 			mask = 0x00010001;
@@ -727,9 +656,13 @@ FINETUNE_START:
 			passcnt++;
 		}
 	}
+	if (retry++ > 10)
+		goto FINETUNE_DONE;
 	if (passcnt != 16) {
 		goto FINETUNE_START;
 	}
+	status = true;
+FINETUNE_DONE:
 	gold_sadj[0] = gold_sadj[0] >> 4;
 	gold_sadj[1] = gold_sadj[0];
 
@@ -753,7 +686,7 @@ FINETUNE_START:
 			data |= dlli << 21;
 		}
 	}
-	moutdwm(ast, 0x1E6E0080, data);
+	ast_moutdwm(ast, 0x1E6E0080, data);
 
 	data = 0;
 	for (cnt = 8; cnt < 16; cnt++) {
@@ -778,162 +711,116 @@ FINETUNE_START:
 			data |= dlli << 21;
 		}
 	}
-	moutdwm(ast, 0x1E6E0084, data);
-
+	ast_moutdwm(ast, 0x1E6E0084, data);
+	return status;
 } /* finetuneDQI_L */
 
-static void finetuneDQI_L2(struct ast_private *ast, struct ast2300_dram_param *param)
+static void finetuneDQSI(struct ast_private *ast)
 {
-	u32 gold_sadj[2], dllmin[16], dllmax[16], dlli, data, cnt, mask, passcnt, data2;
+	u32 dlli, dqsip, dqidly;
+	u32 reg_mcr18, reg_mcr0c, passcnt[2], diff;
+	u32 g_dqidly, g_dqsip, g_margin, g_side;
+	u16 pass[32][2][2];
+	char tag[2][76];
+
+	/* Disable DQI CBR */
+	reg_mcr0c  = ast_mindwm(ast, 0x1E6E000C);
+	reg_mcr18  = ast_mindwm(ast, 0x1E6E0018);
+	reg_mcr18 &= 0x0000ffff;
+	ast_moutdwm(ast, 0x1E6E0018, reg_mcr18);
 
-	for (cnt = 0; cnt < 16; cnt++) {
-		dllmin[cnt] = 0xff;
-		dllmax[cnt] = 0x0;
-	}
-	passcnt = 0;
 	for (dlli = 0; dlli < 76; dlli++) {
-		moutdwm(ast, 0x1E6E0068, 0x00001400 | (dlli << 16) | (dlli << 24));
-		/* Wait DQSI latch phase calibration */
-		moutdwm(ast, 0x1E6E0074, 0x00000010);
-		moutdwm(ast, 0x1E6E0070, 0x00000003);
-		do {
-			data = mindwm(ast, 0x1E6E0070);
-		} while (!(data & 0x00001000));
-		moutdwm(ast, 0x1E6E0070, 0x00000000);
-
-		moutdwm(ast, 0x1E6E0074, CBR_SIZE2);
-		data = cbr_scan2(ast);
-		if (data != 0) {
-			mask = 0x00010001;
-			for (cnt = 0; cnt < 16; cnt++) {
-				if (data & mask) {
-					if (dllmin[cnt] > dlli) {
-						dllmin[cnt] = dlli;
-					}
-					if (dllmax[cnt] < dlli) {
-						dllmax[cnt] = dlli;
-					}
-				}
-				mask <<= 1;
-			}
-			passcnt++;
-		} else if (passcnt >= CBR_THRESHOLD2) {
-			break;
-		}
+		tag[0][dlli] = 0x0;
+		tag[1][dlli] = 0x0;
 	}
-	gold_sadj[0] = 0x0;
-	gold_sadj[1] = 0xFF;
-	for (cnt = 0; cnt < 8; cnt++) {
-		if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD2)) {
-			if (gold_sadj[0] < dllmin[cnt]) {
-				gold_sadj[0] = dllmin[cnt];
-			}
-			if (gold_sadj[1] > dllmax[cnt]) {
-				gold_sadj[1] = dllmax[cnt];
-			}
-		}
+	for (dqidly = 0; dqidly < 32; dqidly++) {
+		pass[dqidly][0][0] = 0xff;
+		pass[dqidly][0][1] = 0x0;
+		pass[dqidly][1][0] = 0xff;
+		pass[dqidly][1][1] = 0x0;
 	}
-	gold_sadj[0] = (gold_sadj[1] + gold_sadj[0]) >> 1;
-	gold_sadj[1] = mindwm(ast, 0x1E6E0080);
-
-	data = 0;
-	for (cnt = 0; cnt < 8; cnt++) {
-		data >>= 3;
-		data2 = gold_sadj[1] & 0x7;
-		gold_sadj[1] >>= 3;
-		if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD2)) {
-			dlli = (dllmin[cnt] + dllmax[cnt]) >> 1;
-			if (gold_sadj[0] >= dlli) {
-				dlli = (gold_sadj[0] - dlli) >> 1;
-				if (dlli > 0) {
-					dlli = 1;
-				}
-				if (data2 != 3) {
-					data2 = (data2 + dlli) & 0x7;
-				}
-			} else {
-				dlli = (dlli - gold_sadj[0]) >> 1;
-				if (dlli > 0) {
-					dlli = 1;
-				}
-				if (data2 != 4) {
-					data2 = (data2 - dlli) & 0x7;
+	for (dqidly = 0; dqidly < 32; dqidly++) {
+		passcnt[0] = passcnt[1] = 0;
+		for (dqsip = 0; dqsip < 2; dqsip++) {
+			ast_moutdwm(ast, 0x1E6E000C, 0);
+			ast_moutdwm(ast, 0x1E6E0018, reg_mcr18 | (dqidly << 16) | (dqsip << 23));
+			ast_moutdwm(ast, 0x1E6E000C, reg_mcr0c);
+			for (dlli = 0; dlli < 76; dlli++) {
+				ast_moutdwm(ast, 0x1E6E0068, 0x00001300 | (dlli << 16) | (dlli << 24));
+				ast_moutdwm(ast, 0x1E6E0070, 0);
+				ast_moutdwm(ast, 0x1E6E0074, CBR_SIZE0);
+				if (cbr_scan3(ast)) {
+					if (dlli == 0)
+						break;
+					passcnt[dqsip]++;
+					tag[dqsip][dlli] = 'P';
+					if (dlli < pass[dqidly][dqsip][0])
+						pass[dqidly][dqsip][0] = (u16) dlli;
+					if (dlli > pass[dqidly][dqsip][1])
+						pass[dqidly][dqsip][1] = (u16) dlli;
+				} else if (passcnt[dqsip] >= 5)
+					break;
+				else {
+					pass[dqidly][dqsip][0] = 0xff;
+					pass[dqidly][dqsip][1] = 0x0;
 				}
 			}
 		}
-		data |= data2 << 21;
-	}
-	moutdwm(ast, 0x1E6E0080, data);
-
-	gold_sadj[0] = 0x0;
-	gold_sadj[1] = 0xFF;
-	for (cnt = 8; cnt < 16; cnt++) {
-		if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD2)) {
-			if (gold_sadj[0] < dllmin[cnt]) {
-				gold_sadj[0] = dllmin[cnt];
-			}
-			if (gold_sadj[1] > dllmax[cnt]) {
-				gold_sadj[1] = dllmax[cnt];
-			}
-		}
+		if (passcnt[0] == 0 && passcnt[1] == 0)
+			dqidly++;
 	}
-	gold_sadj[0] = (gold_sadj[1] + gold_sadj[0]) >> 1;
-	gold_sadj[1] = mindwm(ast, 0x1E6E0084);
-
-	data = 0;
-	for (cnt = 8; cnt < 16; cnt++) {
-		data >>= 3;
-		data2 = gold_sadj[1] & 0x7;
-		gold_sadj[1] >>= 3;
-		if ((dllmax[cnt] > dllmin[cnt]) && ((dllmax[cnt] - dllmin[cnt]) >= CBR_THRESHOLD2)) {
-			dlli = (dllmin[cnt] + dllmax[cnt]) >> 1;
-			if (gold_sadj[0] >= dlli) {
-				dlli = (gold_sadj[0] - dlli) >> 1;
-				if (dlli > 0) {
-					dlli = 1;
-				}
-				if (data2 != 3) {
-					data2 = (data2 + dlli) & 0x7;
-				}
-			} else {
-				dlli = (dlli - gold_sadj[0]) >> 1;
-				if (dlli > 0) {
-					dlli = 1;
-				}
-				if (data2 != 4) {
-					data2 = (data2 - dlli) & 0x7;
-				}
+	/* Search margin */
+	g_dqidly = g_dqsip = g_margin = g_side = 0;
+
+	for (dqidly = 0; dqidly < 32; dqidly++) {
+		for (dqsip = 0; dqsip < 2; dqsip++) {
+			if (pass[dqidly][dqsip][0] > pass[dqidly][dqsip][1])
+				continue;
+			diff = pass[dqidly][dqsip][1] - pass[dqidly][dqsip][0];
+			if ((diff+2) < g_margin)
+				continue;
+			passcnt[0] = passcnt[1] = 0;
+			for (dlli = pass[dqidly][dqsip][0]; dlli > 0  && tag[dqsip][dlli] != 0; dlli--, passcnt[0]++);
+			for (dlli = pass[dqidly][dqsip][1]; dlli < 76 && tag[dqsip][dlli] != 0; dlli++, passcnt[1]++);
+			if (passcnt[0] > passcnt[1])
+				passcnt[0] = passcnt[1];
+			passcnt[1] = 0;
+			if (passcnt[0] > g_side)
+				passcnt[1] = passcnt[0] - g_side;
+			if (diff > (g_margin+1) && (passcnt[1] > 0 || passcnt[0] > 8)) {
+				g_margin = diff;
+				g_dqidly = dqidly;
+				g_dqsip  = dqsip;
+				g_side   = passcnt[0];
+			} else if (passcnt[1] > 1 && g_side < 8) {
+				if (diff > g_margin)
+					g_margin = diff;
+				g_dqidly = dqidly;
+				g_dqsip  = dqsip;
+				g_side   = passcnt[0];
 			}
 		}
-		data |= data2 << 21;
 	}
-	moutdwm(ast, 0x1E6E0084, data);
-
-} /* finetuneDQI_L2 */
+	reg_mcr18 = reg_mcr18 | (g_dqidly << 16) | (g_dqsip << 23);
+	ast_moutdwm(ast, 0x1E6E0018, reg_mcr18);
 
-static void cbr_dll2(struct ast_private *ast, struct ast2300_dram_param *param)
+}
+static bool cbr_dll2(struct ast_private *ast, struct ast2300_dram_param *param)
 {
-	u32 dllmin[2], dllmax[2], dlli, data, data2, passcnt;
+	u32 dllmin[2], dllmax[2], dlli, data, passcnt, retry = 0;
+	bool status = false;
 
-
-	finetuneDQI_L(ast, param);
-	finetuneDQI_L2(ast, param);
+	finetuneDQSI(ast);
+	if (finetuneDQI_L(ast, param) == false)
+		return status;
 
 CBR_START2:
 	dllmin[0] = dllmin[1] = 0xff;
 	dllmax[0] = dllmax[1] = 0x0;
 	passcnt = 0;
 	for (dlli = 0; dlli < 76; dlli++) {
-		moutdwm(ast, 0x1E6E0068, 0x00001300 | (dlli << 16) | (dlli << 24));
-		/* Wait DQSI latch phase calibration */
-		moutdwm(ast, 0x1E6E0074, 0x00000010);
-		moutdwm(ast, 0x1E6E0070, 0x00000003);
-		do {
-			data = mindwm(ast, 0x1E6E0070);
-		} while (!(data & 0x00001000));
-		moutdwm(ast, 0x1E6E0070, 0x00000000);
-
-		moutdwm(ast, 0x1E6E0074, CBR_SIZE2);
+		ast_moutdwm(ast, 0x1E6E0068, 0x00001300 | (dlli << 16) | (dlli << 24));
+		ast_moutdwm(ast, 0x1E6E0074, CBR_SIZE2);
 		data = cbr_scan(ast);
 		if (data != 0) {
 			if (data & 0x1) {
@@ -957,44 +844,31 @@ CBR_START2:
 			break;
 		}
 	}
+	if (retry++ > 10)
+		goto CBR_DONE2;
 	if (dllmax[0] == 0 || (dllmax[0]-dllmin[0]) < CBR_THRESHOLD) {
 		goto CBR_START2;
 	}
 	if (dllmax[1] == 0 || (dllmax[1]-dllmin[1]) < CBR_THRESHOLD) {
 		goto CBR_START2;
 	}
+	status = true;
+CBR_DONE2:
 	dlli  = (dllmin[1] + dllmax[1]) >> 1;
 	dlli <<= 8;
 	dlli += (dllmin[0] + dllmax[0]) >> 1;
-	moutdwm(ast, 0x1E6E0068, (mindwm(ast, 0x1E6E0068) & 0xFFFF) | (dlli << 16));
-
-	data  = (mindwm(ast, 0x1E6E0080) >> 24) & 0x1F;
-	data2 = (mindwm(ast, 0x1E6E0018) & 0xff80ffff) | (data << 16);
-	moutdwm(ast, 0x1E6E0018, data2);
-	moutdwm(ast, 0x1E6E0024, 0x8001 | (data << 1) | (param->dll2_finetune_step << 8));
-
-	/* Wait DQSI latch phase calibration */
-	moutdwm(ast, 0x1E6E0074, 0x00000010);
-	moutdwm(ast, 0x1E6E0070, 0x00000003);
-	do {
-		data = mindwm(ast, 0x1E6E0070);
-	} while (!(data & 0x00001000));
-	moutdwm(ast, 0x1E6E0070, 0x00000000);
-	moutdwm(ast, 0x1E6E0070, 0x00000003);
-	do {
-		data = mindwm(ast, 0x1E6E0070);
-	} while (!(data & 0x00001000));
-	moutdwm(ast, 0x1E6E0070, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0068, ast_mindwm(ast, 0x1E720058) | (dlli << 16));
+	return status;
 } /* CBRDLL2 */
 
 static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *param)
 {
 	u32 trap, trap_AC2, trap_MRS;
 
-	moutdwm(ast, 0x1E6E2000, 0x1688A8A8);
+	ast_moutdwm(ast, 0x1E6E2000, 0x1688A8A8);
 
 	/* Ger trap info */
-	trap = (mindwm(ast, 0x1E6E2070) >> 25) & 0x3;
+	trap = (ast_mindwm(ast, 0x1E6E2070) >> 25) & 0x3;
 	trap_AC2  = 0x00020000 + (trap << 16);
 	trap_AC2 |= 0x00300000 + ((trap & 0x2) << 19);
 	trap_MRS  = 0x00000010 + (trap << 4);
@@ -1008,22 +882,35 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 
 	switch (param->dram_freq) {
 	case 336:
-		moutdwm(ast, 0x1E6E2020, 0x0190);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0190);
 		param->wodt          = 0;
 		param->reg_AC1       = 0x22202725;
 		param->reg_AC2       = 0xAA007613 | trap_AC2;
 		param->reg_DQSIC     = 0x000000BA;
 		param->reg_MRS       = 0x04001400 | trap_MRS;
 		param->reg_EMRS      = 0x00000000;
-		param->reg_IOZ       = 0x00000034;
+		param->reg_IOZ       = 0x00000023;
 		param->reg_DQIDLY    = 0x00000074;
 		param->reg_FREQ      = 0x00004DC0;
 		param->madj_max      = 96;
 		param->dll2_finetune_step = 3;
+		switch (param->dram_chipid) {
+		default:
+		case AST_DRAM_512Mx16:
+		case AST_DRAM_1Gx16:
+			param->reg_AC2   = 0xAA007613 | trap_AC2;
+			break;
+		case AST_DRAM_2Gx16:
+			param->reg_AC2   = 0xAA00761C | trap_AC2;
+			break;
+		case AST_DRAM_4Gx16:
+			param->reg_AC2   = 0xAA007636 | trap_AC2;
+			break;
+		}
 		break;
 	default:
 	case 396:
-		moutdwm(ast, 0x1E6E2020, 0x03F1);
+		ast_moutdwm(ast, 0x1E6E2020, 0x03F1);
 		param->wodt          = 1;
 		param->reg_AC1       = 0x33302825;
 		param->reg_AC2       = 0xCC009617 | trap_AC2;
@@ -1033,7 +920,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->reg_IOZ       = 0x00000034;
 		param->reg_DRV       = 0x000000FA;
 		param->reg_DQIDLY    = 0x00000089;
-		param->reg_FREQ      = 0x000050C0;
+		param->reg_FREQ      = 0x00005040;
 		param->madj_max      = 96;
 		param->dll2_finetune_step = 4;
 
@@ -1053,14 +940,14 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		break;
 
 	case 408:
-		moutdwm(ast, 0x1E6E2020, 0x01F0);
+		ast_moutdwm(ast, 0x1E6E2020, 0x01F0);
 		param->wodt          = 1;
 		param->reg_AC1       = 0x33302825;
 		param->reg_AC2       = 0xCC009617 | trap_AC2;
 		param->reg_DQSIC     = 0x000000E2;
 		param->reg_MRS       = 0x04001600 | trap_MRS;
 		param->reg_EMRS      = 0x00000000;
-		param->reg_IOZ       = 0x00000034;
+		param->reg_IOZ       = 0x00000023;
 		param->reg_DRV       = 0x000000FA;
 		param->reg_DQIDLY    = 0x00000089;
 		param->reg_FREQ      = 0x000050C0;
@@ -1083,7 +970,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 
 		break;
 	case 456:
-		moutdwm(ast, 0x1E6E2020, 0x0230);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0230);
 		param->wodt          = 0;
 		param->reg_AC1       = 0x33302926;
 		param->reg_AC2       = 0xCD44961A;
@@ -1097,7 +984,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 4;
 		break;
 	case 504:
-		moutdwm(ast, 0x1E6E2020, 0x0270);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0270);
 		param->wodt          = 1;
 		param->reg_AC1       = 0x33302926;
 		param->reg_AC2       = 0xDE44A61D;
@@ -1111,7 +998,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 4;
 		break;
 	case 528:
-		moutdwm(ast, 0x1E6E2020, 0x0290);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0290);
 		param->wodt          = 1;
 		param->rodt          = 1;
 		param->reg_AC1       = 0x33302926;
@@ -1127,7 +1014,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 3;
 		break;
 	case 576:
-		moutdwm(ast, 0x1E6E2020, 0x0140);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0140);
 		param->reg_MADJ      = 0x00136868;
 		param->reg_SADJ      = 0x00004534;
 		param->wodt          = 1;
@@ -1145,7 +1032,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 3;
 		break;
 	case 600:
-		moutdwm(ast, 0x1E6E2020, 0x02E1);
+		ast_moutdwm(ast, 0x1E6E2020, 0x02E1);
 		param->reg_MADJ      = 0x00136868;
 		param->reg_SADJ      = 0x00004534;
 		param->wodt          = 1;
@@ -1163,7 +1050,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 3;
 		break;
 	case 624:
-		moutdwm(ast, 0x1E6E2020, 0x0160);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0160);
 		param->reg_MADJ      = 0x00136868;
 		param->reg_SADJ      = 0x00004534;
 		param->wodt          = 1;
@@ -1196,7 +1083,7 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 	case AST_DRAM_4Gx16:
 		param->dram_config = 0x133;
 		break;
-	}; /* switch size */
+	} /* switch size */
 
 	switch (param->vram_size) {
 	default:
@@ -1218,106 +1105,98 @@ static void get_ddr3_info(struct ast_private *ast, struct ast2300_dram_param *pa
 
 static void ddr3_init(struct ast_private *ast, struct ast2300_dram_param *param)
 {
-	u32 data, data2;
+	u32 data, data2, retry = 0;
 
-	moutdwm(ast, 0x1E6E0000, 0xFC600309);
-	moutdwm(ast, 0x1E6E0018, 0x00000100);
-	moutdwm(ast, 0x1E6E0024, 0x00000000);
-	moutdwm(ast, 0x1E6E0034, 0x00000000);
+ddr3_init_start:
+	ast_moutdwm(ast, 0x1E6E0000, 0xFC600309);
+	ast_moutdwm(ast, 0x1E6E0018, 0x00000100);
+	ast_moutdwm(ast, 0x1E6E0024, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0034, 0x00000000);
 	udelay(10);
-	moutdwm(ast, 0x1E6E0064, param->reg_MADJ);
-	moutdwm(ast, 0x1E6E0068, param->reg_SADJ);
+	ast_moutdwm(ast, 0x1E6E0064, param->reg_MADJ);
+	ast_moutdwm(ast, 0x1E6E0068, param->reg_SADJ);
 	udelay(10);
-	moutdwm(ast, 0x1E6E0064, param->reg_MADJ | 0xC0000);
+	ast_moutdwm(ast, 0x1E6E0064, param->reg_MADJ | 0xC0000);
 	udelay(10);
 
-	moutdwm(ast, 0x1E6E0004, param->dram_config);
-	moutdwm(ast, 0x1E6E0008, 0x90040f);
-	moutdwm(ast, 0x1E6E0010, param->reg_AC1);
-	moutdwm(ast, 0x1E6E0014, param->reg_AC2);
-	moutdwm(ast, 0x1E6E0020, param->reg_DQSIC);
-	moutdwm(ast, 0x1E6E0080, 0x00000000);
-	moutdwm(ast, 0x1E6E0084, 0x00000000);
-	moutdwm(ast, 0x1E6E0088, param->reg_DQIDLY);
-	moutdwm(ast, 0x1E6E0018, 0x4040A170);
-	moutdwm(ast, 0x1E6E0018, 0x20402370);
-	moutdwm(ast, 0x1E6E0038, 0x00000000);
-	moutdwm(ast, 0x1E6E0040, 0xFF444444);
-	moutdwm(ast, 0x1E6E0044, 0x22222222);
-	moutdwm(ast, 0x1E6E0048, 0x22222222);
-	moutdwm(ast, 0x1E6E004C, 0x00000002);
-	moutdwm(ast, 0x1E6E0050, 0x80000000);
-	moutdwm(ast, 0x1E6E0050, 0x00000000);
-	moutdwm(ast, 0x1E6E0054, 0);
-	moutdwm(ast, 0x1E6E0060, param->reg_DRV);
-	moutdwm(ast, 0x1E6E006C, param->reg_IOZ);
-	moutdwm(ast, 0x1E6E0070, 0x00000000);
-	moutdwm(ast, 0x1E6E0074, 0x00000000);
-	moutdwm(ast, 0x1E6E0078, 0x00000000);
-	moutdwm(ast, 0x1E6E007C, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0004, param->dram_config);
+	ast_moutdwm(ast, 0x1E6E0008, 0x90040f);
+	ast_moutdwm(ast, 0x1E6E0010, param->reg_AC1);
+	ast_moutdwm(ast, 0x1E6E0014, param->reg_AC2);
+	ast_moutdwm(ast, 0x1E6E0020, param->reg_DQSIC);
+	ast_moutdwm(ast, 0x1E6E0080, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0084, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0088, param->reg_DQIDLY);
+	ast_moutdwm(ast, 0x1E6E0018, 0x4000A170);
+	ast_moutdwm(ast, 0x1E6E0018, 0x00002370);
+	ast_moutdwm(ast, 0x1E6E0038, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0040, 0xFF444444);
+	ast_moutdwm(ast, 0x1E6E0044, 0x22222222);
+	ast_moutdwm(ast, 0x1E6E0048, 0x22222222);
+	ast_moutdwm(ast, 0x1E6E004C, 0x00000002);
+	ast_moutdwm(ast, 0x1E6E0050, 0x80000000);
+	ast_moutdwm(ast, 0x1E6E0050, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0054, 0);
+	ast_moutdwm(ast, 0x1E6E0060, param->reg_DRV);
+	ast_moutdwm(ast, 0x1E6E006C, param->reg_IOZ);
+	ast_moutdwm(ast, 0x1E6E0070, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0074, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0078, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E007C, 0x00000000);
 	/* Wait MCLK2X lock to MCLK */
 	do {
-		data = mindwm(ast, 0x1E6E001C);
+		data = ast_mindwm(ast, 0x1E6E001C);
 	} while (!(data & 0x08000000));
-	moutdwm(ast, 0x1E6E0034, 0x00000001);
-	moutdwm(ast, 0x1E6E000C, 0x00005C04);
-	udelay(10);
-	moutdwm(ast, 0x1E6E000C, 0x00000000);
-	moutdwm(ast, 0x1E6E0034, 0x00000000);
-	data = mindwm(ast, 0x1E6E001C);
+	data = ast_mindwm(ast, 0x1E6E001C);
 	data = (data >> 8) & 0xff;
 	while ((data & 0x08) || ((data & 0x7) < 2) || (data < 4)) {
-		data2 = (mindwm(ast, 0x1E6E0064) & 0xfff3ffff) + 4;
+		data2 = (ast_mindwm(ast, 0x1E6E0064) & 0xfff3ffff) + 4;
 		if ((data2 & 0xff) > param->madj_max) {
 			break;
 		}
-		moutdwm(ast, 0x1E6E0064, data2);
+		ast_moutdwm(ast, 0x1E6E0064, data2);
 		if (data2 & 0x00100000) {
 			data2 = ((data2 & 0xff) >> 3) + 3;
 		} else {
 			data2 = ((data2 & 0xff) >> 2) + 5;
 		}
-		data = mindwm(ast, 0x1E6E0068) & 0xffff00ff;
+		data = ast_mindwm(ast, 0x1E6E0068) & 0xffff00ff;
 		data2 += data & 0xff;
 		data = data | (data2 << 8);
-		moutdwm(ast, 0x1E6E0068, data);
+		ast_moutdwm(ast, 0x1E6E0068, data);
 		udelay(10);
-		moutdwm(ast, 0x1E6E0064, mindwm(ast, 0x1E6E0064) | 0xC0000);
+		ast_moutdwm(ast, 0x1E6E0064, ast_mindwm(ast, 0x1E6E0064) | 0xC0000);
 		udelay(10);
-		data = mindwm(ast, 0x1E6E0018) & 0xfffff1ff;
-		moutdwm(ast, 0x1E6E0018, data);
+		data = ast_mindwm(ast, 0x1E6E0018) & 0xfffff1ff;
+		ast_moutdwm(ast, 0x1E6E0018, data);
 		data = data | 0x200;
-		moutdwm(ast, 0x1E6E0018, data);
+		ast_moutdwm(ast, 0x1E6E0018, data);
 		do {
-			data = mindwm(ast, 0x1E6E001C);
+			data = ast_mindwm(ast, 0x1E6E001C);
 		} while (!(data & 0x08000000));
 
-		moutdwm(ast, 0x1E6E0034, 0x00000001);
-		moutdwm(ast, 0x1E6E000C, 0x00005C04);
-		udelay(10);
-		moutdwm(ast, 0x1E6E000C, 0x00000000);
-		moutdwm(ast, 0x1E6E0034, 0x00000000);
-		data = mindwm(ast, 0x1E6E001C);
+		data = ast_mindwm(ast, 0x1E6E001C);
 		data = (data >> 8) & 0xff;
 	}
-	data = mindwm(ast, 0x1E6E0018) | 0xC00;
-	moutdwm(ast, 0x1E6E0018, data);
+	ast_moutdwm(ast, 0x1E720058, ast_mindwm(ast, 0x1E6E0068) & 0xffff);
+	data = ast_mindwm(ast, 0x1E6E0018) | 0xC00;
+	ast_moutdwm(ast, 0x1E6E0018, data);
 
-	moutdwm(ast, 0x1E6E0034, 0x00000001);
-	moutdwm(ast, 0x1E6E000C, 0x00000040);
+	ast_moutdwm(ast, 0x1E6E0034, 0x00000001);
+	ast_moutdwm(ast, 0x1E6E000C, 0x00000040);
 	udelay(50);
 	/* Mode Register Setting */
-	moutdwm(ast, 0x1E6E002C, param->reg_MRS | 0x100);
-	moutdwm(ast, 0x1E6E0030, param->reg_EMRS);
-	moutdwm(ast, 0x1E6E0028, 0x00000005);
-	moutdwm(ast, 0x1E6E0028, 0x00000007);
-	moutdwm(ast, 0x1E6E0028, 0x00000003);
-	moutdwm(ast, 0x1E6E0028, 0x00000001);
-	moutdwm(ast, 0x1E6E002C, param->reg_MRS);
-	moutdwm(ast, 0x1E6E000C, 0x00005C08);
-	moutdwm(ast, 0x1E6E0028, 0x00000001);
-
-	moutdwm(ast, 0x1E6E000C, 0x7FFF5C01);
+	ast_moutdwm(ast, 0x1E6E002C, param->reg_MRS | 0x100);
+	ast_moutdwm(ast, 0x1E6E0030, param->reg_EMRS);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000005);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000007);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000003);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000001);
+	ast_moutdwm(ast, 0x1E6E002C, param->reg_MRS);
+	ast_moutdwm(ast, 0x1E6E000C, 0x00005C08);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000001);
+
+	ast_moutdwm(ast, 0x1E6E000C, 0x00005C01);
 	data = 0;
 	if (param->wodt) {
 		data = 0x300;
@@ -1325,30 +1204,23 @@ static void ddr3_init(struct ast_private *ast, struct ast2300_dram_param *param)
 	if (param->rodt) {
 		data = data | 0x3000 | ((param->reg_AC2 & 0x60000) >> 3);
 	}
-	moutdwm(ast, 0x1E6E0034, data | 0x3);
+	ast_moutdwm(ast, 0x1E6E0034, data | 0x3);
 
-	/* Wait DQI delay lock */
-	do {
-		data = mindwm(ast, 0x1E6E0080);
-	} while (!(data & 0x40000000));
-	/* Wait DQSI delay lock */
-	do {
-		data = mindwm(ast, 0x1E6E0020);
-	} while (!(data & 0x00000800));
 	/* Calibrate the DQSI delay */
-	cbr_dll2(ast, param);
+	if ((cbr_dll2(ast, param) == false) && (retry++ < 10))
+		goto ddr3_init_start;
 
-	moutdwm(ast, 0x1E6E0120, param->reg_FREQ);
+	ast_moutdwm(ast, 0x1E6E0120, param->reg_FREQ);
 	/* ECC Memory Initialization */
 #ifdef ECC
-	moutdwm(ast, 0x1E6E007C, 0x00000000);
-	moutdwm(ast, 0x1E6E0070, 0x221);
+	ast_moutdwm(ast, 0x1E6E007C, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0070, 0x221);
 	do {
-		data = mindwm(ast, 0x1E6E0070);
+		data = ast_mindwm(ast, 0x1E6E0070);
 	} while (!(data & 0x00001000));
-	moutdwm(ast, 0x1E6E0070, 0x00000000);
-	moutdwm(ast, 0x1E6E0050, 0x80000000);
-	moutdwm(ast, 0x1E6E0050, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0070, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0050, 0x80000000);
+	ast_moutdwm(ast, 0x1E6E0050, 0x00000000);
 #endif
 
 
@@ -1358,10 +1230,10 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 {
 	u32 trap, trap_AC2, trap_MRS;
 
-	moutdwm(ast, 0x1E6E2000, 0x1688A8A8);
+	ast_moutdwm(ast, 0x1E6E2000, 0x1688A8A8);
 
 	/* Ger trap info */
-	trap = (mindwm(ast, 0x1E6E2070) >> 25) & 0x3;
+	trap = (ast_mindwm(ast, 0x1E6E2070) >> 25) & 0x3;
 	trap_AC2  = (trap << 20) | (trap << 16);
 	trap_AC2 += 0x00110000;
 	trap_MRS  = 0x00000040 | (trap << 4);
@@ -1375,7 +1247,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 
 	switch (param->dram_freq) {
 	case 264:
-		moutdwm(ast, 0x1E6E2020, 0x0130);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0130);
 		param->wodt          = 0;
 		param->reg_AC1       = 0x11101513;
 		param->reg_AC2       = 0x78117011;
@@ -1390,7 +1262,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 3;
 		break;
 	case 336:
-		moutdwm(ast, 0x1E6E2020, 0x0190);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0190);
 		param->wodt          = 1;
 		param->reg_AC1       = 0x22202613;
 		param->reg_AC2       = 0xAA009016 | trap_AC2;
@@ -1403,10 +1275,25 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->reg_FREQ      = 0x00004DC0;
 		param->madj_max      = 96;
 		param->dll2_finetune_step = 3;
+		switch (param->dram_chipid) {
+		default:
+		case AST_DRAM_512Mx16:
+			param->reg_AC2   = 0xAA009012 | trap_AC2;
+			break;
+		case AST_DRAM_1Gx16:
+			param->reg_AC2   = 0xAA009016 | trap_AC2;
+			break;
+		case AST_DRAM_2Gx16:
+			param->reg_AC2   = 0xAA009023 | trap_AC2;
+			break;
+		case AST_DRAM_4Gx16:
+			param->reg_AC2   = 0xAA00903B | trap_AC2;
+			break;
+		}
 		break;
 	default:
 	case 396:
-		moutdwm(ast, 0x1E6E2020, 0x03F1);
+		ast_moutdwm(ast, 0x1E6E2020, 0x03F1);
 		param->wodt          = 1;
 		param->rodt          = 0;
 		param->reg_AC1       = 0x33302714;
@@ -1417,7 +1304,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->reg_DRV       = 0x000000FA;
 		param->reg_IOZ       = 0x00000034;
 		param->reg_DQIDLY    = 0x00000089;
-		param->reg_FREQ      = 0x000050C0;
+		param->reg_FREQ      = 0x00005040;
 		param->madj_max      = 96;
 		param->dll2_finetune_step = 4;
 
@@ -1440,7 +1327,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		break;
 
 	case 408:
-		moutdwm(ast, 0x1E6E2020, 0x01F0);
+		ast_moutdwm(ast, 0x1E6E2020, 0x01F0);
 		param->wodt          = 1;
 		param->rodt          = 0;
 		param->reg_AC1       = 0x33302714;
@@ -1473,7 +1360,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 
 		break;
 	case 456:
-		moutdwm(ast, 0x1E6E2020, 0x0230);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0230);
 		param->wodt          = 0;
 		param->reg_AC1       = 0x33302815;
 		param->reg_AC2       = 0xCD44B01E;
@@ -1488,7 +1375,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 3;
 		break;
 	case 504:
-		moutdwm(ast, 0x1E6E2020, 0x0261);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0261);
 		param->wodt          = 1;
 		param->rodt          = 1;
 		param->reg_AC1       = 0x33302815;
@@ -1504,7 +1391,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 3;
 		break;
 	case 528:
-		moutdwm(ast, 0x1E6E2020, 0x0120);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0120);
 		param->wodt          = 1;
 		param->rodt          = 1;
 		param->reg_AC1       = 0x33302815;
@@ -1520,7 +1407,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 3;
 		break;
 	case 552:
-		moutdwm(ast, 0x1E6E2020, 0x02A1);
+		ast_moutdwm(ast, 0x1E6E2020, 0x02A1);
 		param->wodt          = 1;
 		param->rodt          = 1;
 		param->reg_AC1       = 0x43402915;
@@ -1536,7 +1423,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 		param->dll2_finetune_step = 3;
 		break;
 	case 576:
-		moutdwm(ast, 0x1E6E2020, 0x0140);
+		ast_moutdwm(ast, 0x1E6E2020, 0x0140);
 		param->wodt          = 1;
 		param->rodt          = 1;
 		param->reg_AC1       = 0x43402915;
@@ -1567,7 +1454,7 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 	case AST_DRAM_4Gx16:
 		param->dram_config = 0x123;
 		break;
-	}; /* switch size */
+	} /* switch size */
 
 	switch (param->vram_size) {
 	default:
@@ -1588,110 +1475,102 @@ static void get_ddr2_info(struct ast_private *ast, struct ast2300_dram_param *pa
 
 static void ddr2_init(struct ast_private *ast, struct ast2300_dram_param *param)
 {
-	u32 data, data2;
-
-	moutdwm(ast, 0x1E6E0000, 0xFC600309);
-	moutdwm(ast, 0x1E6E0018, 0x00000100);
-	moutdwm(ast, 0x1E6E0024, 0x00000000);
-	moutdwm(ast, 0x1E6E0064, param->reg_MADJ);
-	moutdwm(ast, 0x1E6E0068, param->reg_SADJ);
+	u32 data, data2, retry = 0;
+
+ddr2_init_start:
+	ast_moutdwm(ast, 0x1E6E0000, 0xFC600309);
+	ast_moutdwm(ast, 0x1E6E0018, 0x00000100);
+	ast_moutdwm(ast, 0x1E6E0024, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0064, param->reg_MADJ);
+	ast_moutdwm(ast, 0x1E6E0068, param->reg_SADJ);
 	udelay(10);
-	moutdwm(ast, 0x1E6E0064, param->reg_MADJ | 0xC0000);
+	ast_moutdwm(ast, 0x1E6E0064, param->reg_MADJ | 0xC0000);
 	udelay(10);
 
-	moutdwm(ast, 0x1E6E0004, param->dram_config);
-	moutdwm(ast, 0x1E6E0008, 0x90040f);
-	moutdwm(ast, 0x1E6E0010, param->reg_AC1);
-	moutdwm(ast, 0x1E6E0014, param->reg_AC2);
-	moutdwm(ast, 0x1E6E0020, param->reg_DQSIC);
-	moutdwm(ast, 0x1E6E0080, 0x00000000);
-	moutdwm(ast, 0x1E6E0084, 0x00000000);
-	moutdwm(ast, 0x1E6E0088, param->reg_DQIDLY);
-	moutdwm(ast, 0x1E6E0018, 0x4040A130);
-	moutdwm(ast, 0x1E6E0018, 0x20402330);
-	moutdwm(ast, 0x1E6E0038, 0x00000000);
-	moutdwm(ast, 0x1E6E0040, 0xFF808000);
-	moutdwm(ast, 0x1E6E0044, 0x88848466);
-	moutdwm(ast, 0x1E6E0048, 0x44440008);
-	moutdwm(ast, 0x1E6E004C, 0x00000000);
-	moutdwm(ast, 0x1E6E0050, 0x80000000);
-	moutdwm(ast, 0x1E6E0050, 0x00000000);
-	moutdwm(ast, 0x1E6E0054, 0);
-	moutdwm(ast, 0x1E6E0060, param->reg_DRV);
-	moutdwm(ast, 0x1E6E006C, param->reg_IOZ);
-	moutdwm(ast, 0x1E6E0070, 0x00000000);
-	moutdwm(ast, 0x1E6E0074, 0x00000000);
-	moutdwm(ast, 0x1E6E0078, 0x00000000);
-	moutdwm(ast, 0x1E6E007C, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0004, param->dram_config);
+	ast_moutdwm(ast, 0x1E6E0008, 0x90040f);
+	ast_moutdwm(ast, 0x1E6E0010, param->reg_AC1);
+	ast_moutdwm(ast, 0x1E6E0014, param->reg_AC2);
+	ast_moutdwm(ast, 0x1E6E0020, param->reg_DQSIC);
+	ast_moutdwm(ast, 0x1E6E0080, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0084, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0088, param->reg_DQIDLY);
+	ast_moutdwm(ast, 0x1E6E0018, 0x4000A130);
+	ast_moutdwm(ast, 0x1E6E0018, 0x00002330);
+	ast_moutdwm(ast, 0x1E6E0038, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0040, 0xFF808000);
+	ast_moutdwm(ast, 0x1E6E0044, 0x88848466);
+	ast_moutdwm(ast, 0x1E6E0048, 0x44440008);
+	ast_moutdwm(ast, 0x1E6E004C, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0050, 0x80000000);
+	ast_moutdwm(ast, 0x1E6E0050, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0054, 0);
+	ast_moutdwm(ast, 0x1E6E0060, param->reg_DRV);
+	ast_moutdwm(ast, 0x1E6E006C, param->reg_IOZ);
+	ast_moutdwm(ast, 0x1E6E0070, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0074, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0078, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E007C, 0x00000000);
 
 	/* Wait MCLK2X lock to MCLK */
 	do {
-		data = mindwm(ast, 0x1E6E001C);
+		data = ast_mindwm(ast, 0x1E6E001C);
 	} while (!(data & 0x08000000));
-	moutdwm(ast, 0x1E6E0034, 0x00000001);
-	moutdwm(ast, 0x1E6E000C, 0x00005C04);
-	udelay(10);
-	moutdwm(ast, 0x1E6E000C, 0x00000000);
-	moutdwm(ast, 0x1E6E0034, 0x00000000);
-	data = mindwm(ast, 0x1E6E001C);
+	data = ast_mindwm(ast, 0x1E6E001C);
 	data = (data >> 8) & 0xff;
 	while ((data & 0x08) || ((data & 0x7) < 2) || (data < 4)) {
-		data2 = (mindwm(ast, 0x1E6E0064) & 0xfff3ffff) + 4;
+		data2 = (ast_mindwm(ast, 0x1E6E0064) & 0xfff3ffff) + 4;
 		if ((data2 & 0xff) > param->madj_max) {
 			break;
 		}
-		moutdwm(ast, 0x1E6E0064, data2);
+		ast_moutdwm(ast, 0x1E6E0064, data2);
 		if (data2 & 0x00100000) {
 			data2 = ((data2 & 0xff) >> 3) + 3;
 		} else {
 			data2 = ((data2 & 0xff) >> 2) + 5;
 		}
-		data = mindwm(ast, 0x1E6E0068) & 0xffff00ff;
+		data = ast_mindwm(ast, 0x1E6E0068) & 0xffff00ff;
 		data2 += data & 0xff;
 		data = data | (data2 << 8);
-		moutdwm(ast, 0x1E6E0068, data);
+		ast_moutdwm(ast, 0x1E6E0068, data);
 		udelay(10);
-		moutdwm(ast, 0x1E6E0064, mindwm(ast, 0x1E6E0064) | 0xC0000);
+		ast_moutdwm(ast, 0x1E6E0064, ast_mindwm(ast, 0x1E6E0064) | 0xC0000);
 		udelay(10);
-		data = mindwm(ast, 0x1E6E0018) & 0xfffff1ff;
-		moutdwm(ast, 0x1E6E0018, data);
+		data = ast_mindwm(ast, 0x1E6E0018) & 0xfffff1ff;
+		ast_moutdwm(ast, 0x1E6E0018, data);
 		data = data | 0x200;
-		moutdwm(ast, 0x1E6E0018, data);
+		ast_moutdwm(ast, 0x1E6E0018, data);
 		do {
-			data = mindwm(ast, 0x1E6E001C);
+			data = ast_mindwm(ast, 0x1E6E001C);
 		} while (!(data & 0x08000000));
 
-		moutdwm(ast, 0x1E6E0034, 0x00000001);
-		moutdwm(ast, 0x1E6E000C, 0x00005C04);
-		udelay(10);
-		moutdwm(ast, 0x1E6E000C, 0x00000000);
-		moutdwm(ast, 0x1E6E0034, 0x00000000);
-		data = mindwm(ast, 0x1E6E001C);
+		data = ast_mindwm(ast, 0x1E6E001C);
 		data = (data >> 8) & 0xff;
 	}
-	data = mindwm(ast, 0x1E6E0018) | 0xC00;
-	moutdwm(ast, 0x1E6E0018, data);
+	ast_moutdwm(ast, 0x1E720058, ast_mindwm(ast, 0x1E6E0008) & 0xffff);
+	data = ast_mindwm(ast, 0x1E6E0018) | 0xC00;
+	ast_moutdwm(ast, 0x1E6E0018, data);
 
-	moutdwm(ast, 0x1E6E0034, 0x00000001);
-	moutdwm(ast, 0x1E6E000C, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0034, 0x00000001);
+	ast_moutdwm(ast, 0x1E6E000C, 0x00000000);
 	udelay(50);
 	/* Mode Register Setting */
-	moutdwm(ast, 0x1E6E002C, param->reg_MRS | 0x100);
-	moutdwm(ast, 0x1E6E0030, param->reg_EMRS);
-	moutdwm(ast, 0x1E6E0028, 0x00000005);
-	moutdwm(ast, 0x1E6E0028, 0x00000007);
-	moutdwm(ast, 0x1E6E0028, 0x00000003);
-	moutdwm(ast, 0x1E6E0028, 0x00000001);
-
-	moutdwm(ast, 0x1E6E000C, 0x00005C08);
-	moutdwm(ast, 0x1E6E002C, param->reg_MRS);
-	moutdwm(ast, 0x1E6E0028, 0x00000001);
-	moutdwm(ast, 0x1E6E0030, param->reg_EMRS | 0x380);
-	moutdwm(ast, 0x1E6E0028, 0x00000003);
-	moutdwm(ast, 0x1E6E0030, param->reg_EMRS);
-	moutdwm(ast, 0x1E6E0028, 0x00000003);
-
-	moutdwm(ast, 0x1E6E000C, 0x7FFF5C01);
+	ast_moutdwm(ast, 0x1E6E002C, param->reg_MRS | 0x100);
+	ast_moutdwm(ast, 0x1E6E0030, param->reg_EMRS);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000005);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000007);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000003);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000001);
+
+	ast_moutdwm(ast, 0x1E6E000C, 0x00005C08);
+	ast_moutdwm(ast, 0x1E6E002C, param->reg_MRS);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000001);
+	ast_moutdwm(ast, 0x1E6E0030, param->reg_EMRS | 0x380);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000003);
+	ast_moutdwm(ast, 0x1E6E0030, param->reg_EMRS);
+	ast_moutdwm(ast, 0x1E6E0028, 0x00000003);
+
+	ast_moutdwm(ast, 0x1E6E000C, 0x7FFF5C01);
 	data = 0;
 	if (param->wodt) {
 		data = 0x500;
@@ -1699,30 +1578,23 @@ static void ddr2_init(struct ast_private *ast, struct ast2300_dram_param *param)
 	if (param->rodt) {
 		data = data | 0x3000 | ((param->reg_AC2 & 0x60000) >> 3);
 	}
-	moutdwm(ast, 0x1E6E0034, data | 0x3);
-	moutdwm(ast, 0x1E6E0120, param->reg_FREQ);
+	ast_moutdwm(ast, 0x1E6E0034, data | 0x3);
+	ast_moutdwm(ast, 0x1E6E0120, param->reg_FREQ);
 
-	/* Wait DQI delay lock */
-	do {
-		data = mindwm(ast, 0x1E6E0080);
-	} while (!(data & 0x40000000));
-	/* Wait DQSI delay lock */
-	do {
-		data = mindwm(ast, 0x1E6E0020);
-	} while (!(data & 0x00000800));
 	/* Calibrate the DQSI delay */
-	cbr_dll2(ast, param);
+	if ((cbr_dll2(ast, param) == false) && (retry++ < 10))
+		goto ddr2_init_start;
 
 	/* ECC Memory Initialization */
 #ifdef ECC
-	moutdwm(ast, 0x1E6E007C, 0x00000000);
-	moutdwm(ast, 0x1E6E0070, 0x221);
+	ast_moutdwm(ast, 0x1E6E007C, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0070, 0x221);
 	do {
-		data = mindwm(ast, 0x1E6E0070);
+		data = ast_mindwm(ast, 0x1E6E0070);
 	} while (!(data & 0x00001000));
-	moutdwm(ast, 0x1E6E0070, 0x00000000);
-	moutdwm(ast, 0x1E6E0050, 0x80000000);
-	moutdwm(ast, 0x1E6E0050, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0070, 0x00000000);
+	ast_moutdwm(ast, 0x1E6E0050, 0x80000000);
+	ast_moutdwm(ast, 0x1E6E0050, 0x00000000);
 #endif
 
 }
@@ -1768,8 +1640,8 @@ static void ast_init_dram_2300(struct drm_device *dev)
 			ddr2_init(ast, &param);
 		}
 
-		temp = mindwm(ast, 0x1e6e2040);
-		moutdwm(ast, 0x1e6e2040, temp | 0x40);
+		temp = ast_mindwm(ast, 0x1e6e2040);
+		ast_moutdwm(ast, 0x1e6e2040, temp | 0x40);
 	}
 
 	/* wait ready */
diff --git a/drivers/gpu/drm/ast/ast_tables.h b/drivers/gpu/drm/ast/ast_tables.h
index 95fa6aba26b..4c761dcea97 100644
--- a/drivers/gpu/drm/ast/ast_tables.h
+++ b/drivers/gpu/drm/ast/ast_tables.h
@@ -42,7 +42,7 @@
 #define HBorder                 0x00000020
 #define VBorder                 0x00000010
 #define WideScreenMode		0x00000100
-
+#define NewModeInfo		0x00000200
 
 /* DCLK Index */
 #define VCLK25_175     		0x00
@@ -67,6 +67,11 @@
 #define VCLK106_5   		0x12
 #define VCLK146_25  		0x13
 #define VCLK148_5   		0x14
+#define VCLK71      		0x15
+#define VCLK88_75   		0x16
+#define VCLK119     		0x17
+#define VCLK85_5     		0x18
+#define VCLK97_75     		0x19
 
 static struct ast_vbios_dclk_info dclk_table[] = {
 	{0x2C, 0xE7, 0x03},					/* 00: VCLK25_175	*/
@@ -90,6 +95,10 @@ static struct ast_vbios_dclk_info dclk_table[] = {
 	{0x28, 0x49, 0x80},					/* 12: VCLK106.5        */
 	{0x37, 0x49, 0x80},					/* 13: VCLK146.25       */
 	{0x1f, 0x45, 0x80},					/* 14: VCLK148.5        */
+	{0x47, 0x6c, 0x80},					/* 15: VCLK71       */
+	{0x25, 0x65, 0x80},					/* 16: VCLK88.75    */
+	{0x77, 0x58, 0x80},					/* 17: VCLK119      */
+	{0x32, 0x67, 0x80},				    /* 18: VCLK85_5     */
 };
 
 static struct ast_vbios_stdtable vbios_stdtable[] = {
@@ -225,41 +234,63 @@ static struct ast_vbios_enhtable res_1600x1200[] = {
 	 (SyncPP | Charx8Dot), 0xFF, 1, 0x33 },
 };
 
-static struct ast_vbios_enhtable res_1920x1200[] = {
-	{2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154,	/* 60Hz */
-	 (SyncNP | Charx8Dot), 60, 1, 0x34 },
-	{2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154,	/* 60Hz */
-	 (SyncNP | Charx8Dot), 0xFF, 1, 0x34 },
+/* 16:9 */
+static struct ast_vbios_enhtable res_1360x768[] = {
+	{1792, 1360, 64,112, 795,  768, 3, 6, VCLK85_5,	         /* 60Hz */
+	 (SyncPP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x39 },
+	{1792, 1360, 64,112, 795,  768, 3, 6, VCLK85_5,	         /* end */
+	 (SyncPP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x39 },
+};
+
+static struct ast_vbios_enhtable res_1600x900[] = {
+	{1760, 1600, 48, 32, 926,  900, 3, 5, VCLK97_75,	/* 60Hz CVT RB */
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x3A },
+	{1760, 1600, 48, 32, 926,  900, 3, 5, VCLK97_75,	/* end */
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x3A }
 };
 
+static struct ast_vbios_enhtable res_1920x1080[] = {
+	{2200, 1920, 88, 44, 1125, 1080, 4, 5, VCLK148_5,	/* 60Hz */
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x38 },
+	{2200, 1920, 88, 44, 1125, 1080, 4, 5, VCLK148_5,	/* 60Hz */
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x38 },
+};
+
+
 /* 16:10 */
 static struct ast_vbios_enhtable res_1280x800[] = {
+	{1440, 1280, 48, 32,  823,  800, 3, 6, VCLK71,	/* 60Hz RB */
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 35 },
 	{1680, 1280, 72,128,  831,  800, 3, 6, VCLK83_5,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 60, 1, 0x35 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x35 },
 	{1680, 1280, 72,128,  831,  800, 3, 6, VCLK83_5,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 0xFF, 1, 0x35 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x35 },
 
 };
 
 static struct ast_vbios_enhtable res_1440x900[] = {
+	{1600, 1440, 48, 32,  926,  900, 3, 6, VCLK88_75,	/* 60Hz RB */
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x36 },
 	{1904, 1440, 80,152,  934,  900, 3, 6, VCLK106_5,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 60, 1, 0x36 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x36 },
 	{1904, 1440, 80,152,  934,  900, 3, 6, VCLK106_5,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 0xFF, 1, 0x36 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x36 },
 };
 
 static struct ast_vbios_enhtable res_1680x1050[] = {
+	{1840, 1680, 48, 32, 1080, 1050, 3, 6, VCLK119,	/* 60Hz RB */
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x37 },
 	{2240, 1680,104,176, 1089, 1050, 3, 6, VCLK146_25,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 60, 1, 0x37 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x37 },
 	{2240, 1680,104,176, 1089, 1050, 3, 6, VCLK146_25,	/* 60Hz */
-	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode), 0xFF, 1, 0x37 },
+	 (SyncPN | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x37 },
 };
 
-/* HDTV */
-static struct ast_vbios_enhtable res_1920x1080[] = {
-	{2200, 1920, 88, 44, 1125, 1080, 4, 5, VCLK148_5,	/* 60Hz */
-	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode), 60, 1, 0x38 },
-	{2200, 1920, 88, 44, 1125, 1080, 4, 5, VCLK148_5,	/* 60Hz */
-	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode), 0xFF, 1, 0x38 },
+static struct ast_vbios_enhtable res_1920x1200[] = {
+	{2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154,	/* 60Hz */
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 1, 0x34 },
+	{2080, 1920, 48, 32, 1235, 1200, 3, 6, VCLK154,	/* 60Hz */
+	 (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 0xFF, 1, 0x34 },
 };
+
 #endif
diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c
index f488be55d65..b9a695d9279 100644
--- a/drivers/gpu/drm/bochs/bochs_mm.c
+++ b/drivers/gpu/drm/bochs/bochs_mm.c
@@ -434,17 +434,13 @@ static void bochs_bo_unref(struct bochs_bo **bo)
 
 	tbo = &((*bo)->bo);
 	ttm_bo_unref(&tbo);
-	if (tbo == NULL)
-		*bo = NULL;
-
+	*bo = NULL;
 }
 
 void bochs_gem_free_object(struct drm_gem_object *obj)
 {
 	struct bochs_bo *bochs_bo = gem_to_bochs_bo(obj);
 
-	if (!bochs_bo)
-		return;
 	bochs_bo_unref(&bochs_bo);
 }
 
diff --git a/drivers/gpu/drm/bridge/ptn3460.c b/drivers/gpu/drm/bridge/ptn3460.c
index b171901a355..98fd17ae491 100644
--- a/drivers/gpu/drm/bridge/ptn3460.c
+++ b/drivers/gpu/drm/bridge/ptn3460.c
@@ -225,12 +225,6 @@ out:
 	return num_modes;
 }
 
-static int ptn3460_mode_valid(struct drm_connector *connector,
-		struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
 struct drm_encoder *ptn3460_best_encoder(struct drm_connector *connector)
 {
 	struct ptn3460_bridge *ptn_bridge;
@@ -242,7 +236,6 @@ struct drm_encoder *ptn3460_best_encoder(struct drm_connector *connector)
 
 struct drm_connector_helper_funcs ptn3460_connector_helper_funcs = {
 	.get_modes = ptn3460_get_modes,
-	.mode_valid = ptn3460_mode_valid,
 	.best_encoder = ptn3460_best_encoder,
 };
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index 4b0170cf53f..99c1983f99d 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -264,17 +264,13 @@ static void cirrus_bo_unref(struct cirrus_bo **bo)
 
 	tbo = &((*bo)->bo);
 	ttm_bo_unref(&tbo);
-	if (tbo == NULL)
-		*bo = NULL;
-
+	*bo = NULL;
 }
 
 void cirrus_gem_free_object(struct drm_gem_object *obj)
 {
 	struct cirrus_bo *cirrus_bo = gem_to_cirrus_bo(obj);
 
-	if (!cirrus_bo)
-		return;
 	cirrus_bo_unref(&cirrus_bo);
 }
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index f59433b7610..49332c5fe35 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -505,13 +505,6 @@ static int cirrus_vga_get_modes(struct drm_connector *connector)
 	return count;
 }
 
-static int cirrus_vga_mode_valid(struct drm_connector *connector,
-				 struct drm_display_mode *mode)
-{
-	/* Any mode we've added is valid */
-	return MODE_OK;
-}
-
 static struct drm_encoder *cirrus_connector_best_encoder(struct drm_connector
 						  *connector)
 {
@@ -546,7 +539,6 @@ static void cirrus_connector_destroy(struct drm_connector *connector)
 
 struct drm_connector_helper_funcs cirrus_vga_connector_helper_funcs = {
 	.get_modes = cirrus_vga_get_modes,
-	.mode_valid = cirrus_vga_mode_valid,
 	.best_encoder = cirrus_connector_best_encoder,
 };
 
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index edec31fe3fe..68175b54504 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -363,7 +363,7 @@ static int drm_addmap_core(struct drm_device * dev, resource_size_t offset,
 		list->master = dev->primary->master;
 	*maplist = list;
 	return 0;
-	}
+}
 
 int drm_addmap(struct drm_device * dev, resource_size_t offset,
 	       unsigned int size, enum drm_map_type type,
@@ -656,13 +656,13 @@ int drm_addbufs_agp(struct drm_device * dev, struct drm_buf_desc * request)
 		DRM_DEBUG("zone invalid\n");
 		return -EINVAL;
 	}
-	spin_lock(&dev->count_lock);
+	spin_lock(&dev->buf_lock);
 	if (dev->buf_use) {
-		spin_unlock(&dev->count_lock);
+		spin_unlock(&dev->buf_lock);
 		return -EBUSY;
 	}
 	atomic_inc(&dev->buf_alloc);
-	spin_unlock(&dev->count_lock);
+	spin_unlock(&dev->buf_lock);
 
 	mutex_lock(&dev->struct_mutex);
 	entry = &dma->bufs[order];
@@ -805,13 +805,13 @@ int drm_addbufs_pci(struct drm_device * dev, struct drm_buf_desc * request)
 	page_order = order - PAGE_SHIFT > 0 ? order - PAGE_SHIFT : 0;
 	total = PAGE_SIZE << page_order;
 
-	spin_lock(&dev->count_lock);
+	spin_lock(&dev->buf_lock);
 	if (dev->buf_use) {
-		spin_unlock(&dev->count_lock);
+		spin_unlock(&dev->buf_lock);
 		return -EBUSY;
 	}
 	atomic_inc(&dev->buf_alloc);
-	spin_unlock(&dev->count_lock);
+	spin_unlock(&dev->buf_lock);
 
 	mutex_lock(&dev->struct_mutex);
 	entry = &dma->bufs[order];
@@ -1015,13 +1015,13 @@ static int drm_addbufs_sg(struct drm_device * dev, struct drm_buf_desc * request
 	if (order < DRM_MIN_ORDER || order > DRM_MAX_ORDER)
 		return -EINVAL;
 
-	spin_lock(&dev->count_lock);
+	spin_lock(&dev->buf_lock);
 	if (dev->buf_use) {
-		spin_unlock(&dev->count_lock);
+		spin_unlock(&dev->buf_lock);
 		return -EBUSY;
 	}
 	atomic_inc(&dev->buf_alloc);
-	spin_unlock(&dev->count_lock);
+	spin_unlock(&dev->buf_lock);
 
 	mutex_lock(&dev->struct_mutex);
 	entry = &dma->bufs[order];
@@ -1175,7 +1175,7 @@ int drm_addbufs(struct drm_device *dev, void *data,
  * \param arg pointer to a drm_buf_info structure.
  * \return zero on success or a negative number on failure.
  *
- * Increments drm_device::buf_use while holding the drm_device::count_lock
+ * Increments drm_device::buf_use while holding the drm_device::buf_lock
  * lock, preventing of allocating more buffers after this call. Information
  * about each requested buffer is then copied into user space.
  */
@@ -1196,13 +1196,13 @@ int drm_infobufs(struct drm_device *dev, void *data,
 	if (!dma)
 		return -EINVAL;
 
-	spin_lock(&dev->count_lock);
+	spin_lock(&dev->buf_lock);
 	if (atomic_read(&dev->buf_alloc)) {
-		spin_unlock(&dev->count_lock);
+		spin_unlock(&dev->buf_lock);
 		return -EBUSY;
 	}
 	++dev->buf_use;		/* Can't allocate more after this call */
-	spin_unlock(&dev->count_lock);
+	spin_unlock(&dev->buf_lock);
 
 	for (i = 0, count = 0; i < DRM_MAX_ORDER + 1; i++) {
 		if (dma->bufs[i].buf_count)
@@ -1381,13 +1381,13 @@ int drm_mapbufs(struct drm_device *dev, void *data,
 	if (!dma)
 		return -EINVAL;
 
-	spin_lock(&dev->count_lock);
+	spin_lock(&dev->buf_lock);
 	if (atomic_read(&dev->buf_alloc)) {
-		spin_unlock(&dev->count_lock);
+		spin_unlock(&dev->buf_lock);
 		return -EBUSY;
 	}
 	dev->buf_use++;		/* Can't allocate more after this call */
-	spin_unlock(&dev->count_lock);
+	spin_unlock(&dev->buf_lock);
 
 	if (request->count >= dma->buf_count) {
 		if ((dev->agp && (dma->flags & _DRM_DMA_USE_AGP))
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
index 534cb89b160..a6b690626a6 100644
--- a/drivers/gpu/drm/drm_cache.c
+++ b/drivers/gpu/drm/drm_cache.c
@@ -131,14 +131,14 @@ drm_clflush_sg(struct sg_table *st)
 EXPORT_SYMBOL(drm_clflush_sg);
 
 void
-drm_clflush_virt_range(char *addr, unsigned long length)
+drm_clflush_virt_range(void *addr, unsigned long length)
 {
 #if defined(CONFIG_X86)
 	if (cpu_has_clflush) {
-		char *end = addr + length;
+		void *end = addr + length;
 		mb();
 		for (; addr < end; addr += boot_cpu_data.x86_clflush_size)
-			clflush(addr);
+			clflushopt(addr);
 		clflushopt(end - 1);
 		mb();
 		return;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index d8b7099abec..fe94cc10cd3 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -37,6 +37,7 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_modeset_lock.h>
 
 #include "drm_crtc_internal.h"
 
@@ -50,12 +51,42 @@
  */
 void drm_modeset_lock_all(struct drm_device *dev)
 {
-	struct drm_crtc *crtc;
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_modeset_acquire_ctx *ctx;
+	int ret;
 
-	mutex_lock(&dev->mode_config.mutex);
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (WARN_ON(!ctx))
+		return;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
-		mutex_lock_nest_lock(&crtc->mutex, &dev->mode_config.mutex);
+	mutex_lock(&config->mutex);
+
+	drm_modeset_acquire_init(ctx, 0);
+
+retry:
+	ret = drm_modeset_lock(&config->connection_mutex, ctx);
+	if (ret)
+		goto fail;
+	ret = drm_modeset_lock_all_crtcs(dev, ctx);
+	if (ret)
+		goto fail;
+
+	WARN_ON(config->acquire_ctx);
+
+	/* now we hold the locks, so now that it is safe, stash the
+	 * ctx for drm_modeset_unlock_all():
+	 */
+	config->acquire_ctx = ctx;
+
+	drm_warn_on_modeset_not_all_locked(dev);
+
+	return;
+
+fail:
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(ctx);
+		goto retry;
+	}
 }
 EXPORT_SYMBOL(drm_modeset_lock_all);
 
@@ -67,10 +98,17 @@ EXPORT_SYMBOL(drm_modeset_lock_all);
  */
 void drm_modeset_unlock_all(struct drm_device *dev)
 {
-	struct drm_crtc *crtc;
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
-		mutex_unlock(&crtc->mutex);
+	if (WARN_ON(!ctx))
+		return;
+
+	config->acquire_ctx = NULL;
+	drm_modeset_drop_locks(ctx);
+	drm_modeset_acquire_fini(ctx);
+
+	kfree(ctx);
 
 	mutex_unlock(&dev->mode_config.mutex);
 }
@@ -91,8 +129,9 @@ void drm_warn_on_modeset_not_all_locked(struct drm_device *dev)
 		return;
 
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
-		WARN_ON(!mutex_is_locked(&crtc->mutex));
+		WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 
+	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
 	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
 }
 EXPORT_SYMBOL(drm_warn_on_modeset_not_all_locked);
@@ -227,6 +266,7 @@ static const struct drm_prop_enum_list drm_encoder_enum_list[] =
 	{ DRM_MODE_ENCODER_TVDAC, "TV" },
 	{ DRM_MODE_ENCODER_VIRTUAL, "Virtual" },
 	{ DRM_MODE_ENCODER_DSI, "DSI" },
+	{ DRM_MODE_ENCODER_DPMST, "DP MST" },
 };
 
 static const struct drm_prop_enum_list drm_subpixel_enum_list[] =
@@ -256,46 +296,6 @@ void drm_connector_ida_destroy(void)
 }
 
 /**
- * drm_get_encoder_name - return a string for encoder
- * @encoder: encoder to compute name of
- *
- * Note that the buffer used by this function is globally shared and owned by
- * the function itself.
- *
- * FIXME: This isn't really multithreading safe.
- */
-const char *drm_get_encoder_name(const struct drm_encoder *encoder)
-{
-	static char buf[32];
-
-	snprintf(buf, 32, "%s-%d",
-		 drm_encoder_enum_list[encoder->encoder_type].name,
-		 encoder->base.id);
-	return buf;
-}
-EXPORT_SYMBOL(drm_get_encoder_name);
-
-/**
- * drm_get_connector_name - return a string for connector
- * @connector: connector to compute name of
- *
- * Note that the buffer used by this function is globally shared and owned by
- * the function itself.
- *
- * FIXME: This isn't really multithreading safe.
- */
-const char *drm_get_connector_name(const struct drm_connector *connector)
-{
-	static char buf[32];
-
-	snprintf(buf, 32, "%s-%d",
-		 drm_connector_enum_list[connector->connector_type].name,
-		 connector->connector_type_id);
-	return buf;
-}
-EXPORT_SYMBOL(drm_get_connector_name);
-
-/**
  * drm_get_connector_status_name - return a string for connector status
  * @status: connector status to compute name of
  *
@@ -409,6 +409,21 @@ void drm_mode_object_put(struct drm_device *dev,
 	mutex_unlock(&dev->mode_config.idr_mutex);
 }
 
+static struct drm_mode_object *_object_find(struct drm_device *dev,
+		uint32_t id, uint32_t type)
+{
+	struct drm_mode_object *obj = NULL;
+
+	mutex_lock(&dev->mode_config.idr_mutex);
+	obj = idr_find(&dev->mode_config.crtc_idr, id);
+	if (!obj || (type != DRM_MODE_OBJECT_ANY && obj->type != type) ||
+	    (obj->id != id))
+		obj = NULL;
+	mutex_unlock(&dev->mode_config.idr_mutex);
+
+	return obj;
+}
+
 /**
  * drm_mode_object_find - look up a drm object with static lifetime
  * @dev: drm device
@@ -416,7 +431,9 @@ void drm_mode_object_put(struct drm_device *dev,
  * @type: type of the mode object
  *
  * Note that framebuffers cannot be looked up with this functions - since those
- * are reference counted, they need special treatment.
+ * are reference counted, they need special treatment.  Even with
+ * DRM_MODE_OBJECT_ANY (although that will simply return NULL
+ * rather than WARN_ON()).
  */
 struct drm_mode_object *drm_mode_object_find(struct drm_device *dev,
 		uint32_t id, uint32_t type)
@@ -426,13 +443,10 @@ struct drm_mode_object *drm_mode_object_find(struct drm_device *dev,
 	/* Framebuffers are reference counted and need their own lookup
 	 * function.*/
 	WARN_ON(type == DRM_MODE_OBJECT_FB);
-
-	mutex_lock(&dev->mode_config.idr_mutex);
-	obj = idr_find(&dev->mode_config.crtc_idr, id);
-	if (!obj || (obj->type != type) || (obj->id != id))
+	obj = _object_find(dev, id, type);
+	/* don't leak out unref'd fb's */
+	if (obj && (obj->type == DRM_MODE_OBJECT_FB))
 		obj = NULL;
-	mutex_unlock(&dev->mode_config.idr_mutex);
-
 	return obj;
 }
 EXPORT_SYMBOL(drm_mode_object_find);
@@ -538,7 +552,7 @@ EXPORT_SYMBOL(drm_framebuffer_lookup);
  */
 void drm_framebuffer_unreference(struct drm_framebuffer *fb)
 {
-	DRM_DEBUG("FB ID: %d\n", fb->base.id);
+	DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount));
 	kref_put(&fb->refcount, drm_framebuffer_free);
 }
 EXPORT_SYMBOL(drm_framebuffer_unreference);
@@ -551,7 +565,7 @@ EXPORT_SYMBOL(drm_framebuffer_unreference);
  */
 void drm_framebuffer_reference(struct drm_framebuffer *fb)
 {
-	DRM_DEBUG("FB ID: %d\n", fb->base.id);
+	DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount));
 	kref_get(&fb->refcount);
 }
 EXPORT_SYMBOL(drm_framebuffer_reference);
@@ -563,7 +577,7 @@ static void drm_framebuffer_free_bug(struct kref *kref)
 
 static void __drm_framebuffer_unreference(struct drm_framebuffer *fb)
 {
-	DRM_DEBUG("FB ID: %d\n", fb->base.id);
+	DRM_DEBUG("%p: FB ID: %d (%d)\n", fb, fb->base.id, atomic_read(&fb->refcount.refcount));
 	kref_put(&fb->refcount, drm_framebuffer_free_bug);
 }
 
@@ -691,6 +705,8 @@ void drm_framebuffer_remove(struct drm_framebuffer *fb)
 }
 EXPORT_SYMBOL(drm_framebuffer_remove);
 
+DEFINE_WW_CLASS(crtc_ww_class);
+
 /**
  * drm_crtc_init_with_planes - Initialise a new CRTC object with
  *    specified primary and cursor planes.
@@ -710,6 +726,7 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 			      void *cursor,
 			      const struct drm_crtc_funcs *funcs)
 {
+	struct drm_mode_config *config = &dev->mode_config;
 	int ret;
 
 	crtc->dev = dev;
@@ -717,8 +734,9 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	crtc->invert_dimensions = false;
 
 	drm_modeset_lock_all(dev);
-	mutex_init(&crtc->mutex);
-	mutex_lock_nest_lock(&crtc->mutex, &dev->mode_config.mutex);
+	drm_modeset_lock_init(&crtc->mutex);
+	/* dropped by _unlock_all(): */
+	drm_modeset_lock(&crtc->mutex, config->acquire_ctx);
 
 	ret = drm_mode_object_get(dev, &crtc->base, DRM_MODE_OBJECT_CRTC);
 	if (ret)
@@ -726,8 +744,8 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 
 	crtc->base.properties = &crtc->properties;
 
-	list_add_tail(&crtc->head, &dev->mode_config.crtc_list);
-	dev->mode_config.num_crtc++;
+	list_add_tail(&crtc->head, &config->crtc_list);
+	config->num_crtc++;
 
 	crtc->primary = primary;
 	if (primary)
@@ -755,6 +773,8 @@ void drm_crtc_cleanup(struct drm_crtc *crtc)
 	kfree(crtc->gamma_store);
 	crtc->gamma_store = NULL;
 
+	drm_modeset_lock_fini(&crtc->mutex);
+
 	drm_mode_object_put(dev, &crtc->base);
 	list_del(&crtc->head);
 	dev->mode_config.num_crtc--;
@@ -824,7 +844,7 @@ int drm_connector_init(struct drm_device *dev,
 
 	ret = drm_mode_object_get(dev, &connector->base, DRM_MODE_OBJECT_CONNECTOR);
 	if (ret)
-		goto out;
+		goto out_unlock;
 
 	connector->base.properties = &connector->properties;
 	connector->dev = dev;
@@ -834,9 +854,17 @@ int drm_connector_init(struct drm_device *dev,
 		ida_simple_get(connector_ida, 1, 0, GFP_KERNEL);
 	if (connector->connector_type_id < 0) {
 		ret = connector->connector_type_id;
-		drm_mode_object_put(dev, &connector->base);
-		goto out;
+		goto out_put;
+	}
+	connector->name =
+		kasprintf(GFP_KERNEL, "%s-%d",
+			  drm_connector_enum_list[connector_type].name,
+			  connector->connector_type_id);
+	if (!connector->name) {
+		ret = -ENOMEM;
+		goto out_put;
 	}
+
 	INIT_LIST_HEAD(&connector->probed_modes);
 	INIT_LIST_HEAD(&connector->modes);
 	connector->edid_blob_ptr = NULL;
@@ -853,7 +881,11 @@ int drm_connector_init(struct drm_device *dev,
 	drm_object_attach_property(&connector->base,
 				      dev->mode_config.dpms_property, 0);
 
- out:
+out_put:
+	if (ret)
+		drm_mode_object_put(dev, &connector->base);
+
+out_unlock:
 	drm_modeset_unlock_all(dev);
 
 	return ret;
@@ -881,6 +913,8 @@ void drm_connector_cleanup(struct drm_connector *connector)
 		   connector->connector_type_id);
 
 	drm_mode_object_put(dev, &connector->base);
+	kfree(connector->name);
+	connector->name = NULL;
 	list_del(&connector->head);
 	dev->mode_config.num_connector--;
 }
@@ -982,16 +1016,27 @@ int drm_encoder_init(struct drm_device *dev,
 
 	ret = drm_mode_object_get(dev, &encoder->base, DRM_MODE_OBJECT_ENCODER);
 	if (ret)
-		goto out;
+		goto out_unlock;
 
 	encoder->dev = dev;
 	encoder->encoder_type = encoder_type;
 	encoder->funcs = funcs;
+	encoder->name = kasprintf(GFP_KERNEL, "%s-%d",
+				  drm_encoder_enum_list[encoder_type].name,
+				  encoder->base.id);
+	if (!encoder->name) {
+		ret = -ENOMEM;
+		goto out_put;
+	}
 
 	list_add_tail(&encoder->head, &dev->mode_config.encoder_list);
 	dev->mode_config.num_encoder++;
 
- out:
+out_put:
+	if (ret)
+		drm_mode_object_put(dev, &encoder->base);
+
+out_unlock:
 	drm_modeset_unlock_all(dev);
 
 	return ret;
@@ -1009,6 +1054,8 @@ void drm_encoder_cleanup(struct drm_encoder *encoder)
 	struct drm_device *dev = encoder->dev;
 	drm_modeset_lock_all(dev);
 	drm_mode_object_put(dev, &encoder->base);
+	kfree(encoder->name);
+	encoder->name = NULL;
 	list_del(&encoder->head);
 	dev->mode_config.num_encoder--;
 	drm_modeset_unlock_all(dev);
@@ -1145,16 +1192,19 @@ EXPORT_SYMBOL(drm_plane_cleanup);
  */
 void drm_plane_force_disable(struct drm_plane *plane)
 {
+	struct drm_framebuffer *old_fb = plane->fb;
 	int ret;
 
-	if (!plane->fb)
+	if (!old_fb)
 		return;
 
 	ret = plane->funcs->disable_plane(plane);
-	if (ret)
+	if (ret) {
 		DRM_ERROR("failed to disable plane with busy fb\n");
+		return;
+	}
 	/* disconnect the plane from the fb and crtc: */
-	__drm_framebuffer_unreference(plane->fb);
+	__drm_framebuffer_unreference(old_fb);
 	plane->fb = NULL;
 	plane->crtc = NULL;
 }
@@ -1378,6 +1428,12 @@ static int drm_mode_group_init(struct drm_device *dev, struct drm_mode_group *gr
 	return 0;
 }
 
+void drm_mode_group_destroy(struct drm_mode_group *group)
+{
+	kfree(group->id_list);
+	group->id_list = NULL;
+}
+
 /*
  * NOTE: Driver's shouldn't ever call drm_mode_group_init_legacy_group - it is
  * the drm core's responsibility to set up mode control groups.
@@ -1614,7 +1670,7 @@ int drm_mode_getresources(struct drm_device *dev, void *data,
 					    &dev->mode_config.encoder_list,
 					    head) {
 				DRM_DEBUG_KMS("[ENCODER:%d:%s]\n", encoder->base.id,
-						drm_get_encoder_name(encoder));
+						encoder->name);
 				if (put_user(encoder->base.id, encoder_id +
 					     copied)) {
 					ret = -EFAULT;
@@ -1646,7 +1702,7 @@ int drm_mode_getresources(struct drm_device *dev, void *data,
 					    head) {
 				DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 					connector->base.id,
-					drm_get_connector_name(connector));
+					connector->name);
 				if (put_user(connector->base.id,
 					     connector_id + copied)) {
 					ret = -EFAULT;
@@ -1695,7 +1751,6 @@ int drm_mode_getcrtc(struct drm_device *dev,
 {
 	struct drm_mode_crtc *crtc_resp = data;
 	struct drm_crtc *crtc;
-	struct drm_mode_object *obj;
 	int ret = 0;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
@@ -1703,13 +1758,11 @@ int drm_mode_getcrtc(struct drm_device *dev,
 
 	drm_modeset_lock_all(dev);
 
-	obj = drm_mode_object_find(dev, crtc_resp->crtc_id,
-				   DRM_MODE_OBJECT_CRTC);
-	if (!obj) {
+	crtc = drm_crtc_find(dev, crtc_resp->crtc_id);
+	if (!crtc) {
 		ret = -ENOENT;
 		goto out;
 	}
-	crtc = obj_to_crtc(obj);
 
 	crtc_resp->x = crtc->x;
 	crtc_resp->y = crtc->y;
@@ -1763,7 +1816,6 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 			  struct drm_file *file_priv)
 {
 	struct drm_mode_get_connector *out_resp = data;
-	struct drm_mode_object *obj;
 	struct drm_connector *connector;
 	struct drm_display_mode *mode;
 	int mode_count = 0;
@@ -1787,13 +1839,11 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 
 	mutex_lock(&dev->mode_config.mutex);
 
-	obj = drm_mode_object_find(dev, out_resp->connector_id,
-				   DRM_MODE_OBJECT_CONNECTOR);
-	if (!obj) {
+	connector = drm_connector_find(dev, out_resp->connector_id);
+	if (!connector) {
 		ret = -ENOENT;
 		goto out;
 	}
-	connector = obj_to_connector(obj);
 
 	props_count = connector->properties.count;
 
@@ -1821,10 +1871,12 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	out_resp->mm_height = connector->display_info.height_mm;
 	out_resp->subpixel = connector->display_info.subpixel_order;
 	out_resp->connection = connector->status;
+	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 	if (connector->encoder)
 		out_resp->encoder_id = connector->encoder->base.id;
 	else
 		out_resp->encoder_id = 0;
+	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 
 	/*
 	 * This ioctl is called twice, once to determine how much space is
@@ -1908,7 +1960,6 @@ int drm_mode_getencoder(struct drm_device *dev, void *data,
 			struct drm_file *file_priv)
 {
 	struct drm_mode_get_encoder *enc_resp = data;
-	struct drm_mode_object *obj;
 	struct drm_encoder *encoder;
 	int ret = 0;
 
@@ -1916,13 +1967,11 @@ int drm_mode_getencoder(struct drm_device *dev, void *data,
 		return -EINVAL;
 
 	drm_modeset_lock_all(dev);
-	obj = drm_mode_object_find(dev, enc_resp->encoder_id,
-				   DRM_MODE_OBJECT_ENCODER);
-	if (!obj) {
+	encoder = drm_encoder_find(dev, enc_resp->encoder_id);
+	if (!encoder) {
 		ret = -ENOENT;
 		goto out;
 	}
-	encoder = obj_to_encoder(obj);
 
 	if (encoder->crtc)
 		enc_resp->crtc_id = encoder->crtc->base.id;
@@ -2020,7 +2069,6 @@ int drm_mode_getplane(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv)
 {
 	struct drm_mode_get_plane *plane_resp = data;
-	struct drm_mode_object *obj;
 	struct drm_plane *plane;
 	uint32_t __user *format_ptr;
 	int ret = 0;
@@ -2029,13 +2077,11 @@ int drm_mode_getplane(struct drm_device *dev, void *data,
 		return -EINVAL;
 
 	drm_modeset_lock_all(dev);
-	obj = drm_mode_object_find(dev, plane_resp->plane_id,
-				   DRM_MODE_OBJECT_PLANE);
-	if (!obj) {
+	plane = drm_plane_find(dev, plane_resp->plane_id);
+	if (!plane) {
 		ret = -ENOENT;
 		goto out;
 	}
-	plane = obj_to_plane(obj);
 
 	if (plane->crtc)
 		plane_resp->crtc_id = plane->crtc->base.id;
@@ -2088,7 +2134,6 @@ int drm_mode_setplane(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv)
 {
 	struct drm_mode_set_plane *plane_req = data;
-	struct drm_mode_object *obj;
 	struct drm_plane *plane;
 	struct drm_crtc *crtc;
 	struct drm_framebuffer *fb = NULL, *old_fb = NULL;
@@ -2103,35 +2148,42 @@ int drm_mode_setplane(struct drm_device *dev, void *data,
 	 * First, find the plane, crtc, and fb objects.  If not available,
 	 * we don't bother to call the driver.
 	 */
-	obj = drm_mode_object_find(dev, plane_req->plane_id,
-				   DRM_MODE_OBJECT_PLANE);
-	if (!obj) {
+	plane = drm_plane_find(dev, plane_req->plane_id);
+	if (!plane) {
 		DRM_DEBUG_KMS("Unknown plane ID %d\n",
 			      plane_req->plane_id);
 		return -ENOENT;
 	}
-	plane = obj_to_plane(obj);
 
 	/* No fb means shut it down */
 	if (!plane_req->fb_id) {
 		drm_modeset_lock_all(dev);
 		old_fb = plane->fb;
-		plane->funcs->disable_plane(plane);
-		plane->crtc = NULL;
-		plane->fb = NULL;
+		ret = plane->funcs->disable_plane(plane);
+		if (!ret) {
+			plane->crtc = NULL;
+			plane->fb = NULL;
+		} else {
+			old_fb = NULL;
+		}
 		drm_modeset_unlock_all(dev);
 		goto out;
 	}
 
-	obj = drm_mode_object_find(dev, plane_req->crtc_id,
-				   DRM_MODE_OBJECT_CRTC);
-	if (!obj) {
+	crtc = drm_crtc_find(dev, plane_req->crtc_id);
+	if (!crtc) {
 		DRM_DEBUG_KMS("Unknown crtc ID %d\n",
 			      plane_req->crtc_id);
 		ret = -ENOENT;
 		goto out;
 	}
-	crtc = obj_to_crtc(obj);
+
+	/* Check whether this plane is usable on this CRTC */
+	if (!(plane->possible_crtcs & drm_crtc_mask(crtc))) {
+		DRM_DEBUG_KMS("Invalid crtc for plane\n");
+		ret = -EINVAL;
+		goto out;
+	}
 
 	fb = drm_framebuffer_lookup(dev, plane_req->fb_id);
 	if (!fb) {
@@ -2187,16 +2239,18 @@ int drm_mode_setplane(struct drm_device *dev, void *data,
 	}
 
 	drm_modeset_lock_all(dev);
+	old_fb = plane->fb;
 	ret = plane->funcs->update_plane(plane, crtc, fb,
 					 plane_req->crtc_x, plane_req->crtc_y,
 					 plane_req->crtc_w, plane_req->crtc_h,
 					 plane_req->src_x, plane_req->src_y,
 					 plane_req->src_w, plane_req->src_h);
 	if (!ret) {
-		old_fb = plane->fb;
 		plane->crtc = crtc;
 		plane->fb = fb;
 		fb = NULL;
+	} else {
+		old_fb = NULL;
 	}
 	drm_modeset_unlock_all(dev);
 
@@ -2239,9 +2293,7 @@ int drm_mode_set_config_internal(struct drm_mode_set *set)
 	ret = crtc->funcs->set_config(set);
 	if (ret == 0) {
 		crtc->primary->crtc = crtc;
-
-		/* crtc->fb must be updated by ->set_config, enforces this. */
-		WARN_ON(fb != crtc->primary->fb);
+		crtc->primary->fb = fb;
 	}
 
 	list_for_each_entry(tmp, &crtc->dev->mode_config.crtc_list, head) {
@@ -2318,7 +2370,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 {
 	struct drm_mode_config *config = &dev->mode_config;
 	struct drm_mode_crtc *crtc_req = data;
-	struct drm_mode_object *obj;
 	struct drm_crtc *crtc;
 	struct drm_connector **connector_set = NULL, *connector;
 	struct drm_framebuffer *fb = NULL;
@@ -2336,14 +2387,12 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 		return -ERANGE;
 
 	drm_modeset_lock_all(dev);
-	obj = drm_mode_object_find(dev, crtc_req->crtc_id,
-				   DRM_MODE_OBJECT_CRTC);
-	if (!obj) {
+	crtc = drm_crtc_find(dev, crtc_req->crtc_id);
+	if (!crtc) {
 		DRM_DEBUG_KMS("Unknown CRTC ID %d\n", crtc_req->crtc_id);
 		ret = -ENOENT;
 		goto out;
 	}
-	crtc = obj_to_crtc(obj);
 	DRM_DEBUG_KMS("[CRTC:%d]\n", crtc->base.id);
 
 	if (crtc_req->mode_valid) {
@@ -2426,18 +2475,16 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data,
 				goto out;
 			}
 
-			obj = drm_mode_object_find(dev, out_id,
-						   DRM_MODE_OBJECT_CONNECTOR);
-			if (!obj) {
+			connector = drm_connector_find(dev, out_id);
+			if (!connector) {
 				DRM_DEBUG_KMS("Connector id %d unknown\n",
 						out_id);
 				ret = -ENOENT;
 				goto out;
 			}
-			connector = obj_to_connector(obj);
 			DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 					connector->base.id,
-					drm_get_connector_name(connector));
+					connector->name);
 
 			connector_set[i] = connector;
 		}
@@ -2466,7 +2513,6 @@ static int drm_mode_cursor_common(struct drm_device *dev,
 				  struct drm_mode_cursor2 *req,
 				  struct drm_file *file_priv)
 {
-	struct drm_mode_object *obj;
 	struct drm_crtc *crtc;
 	int ret = 0;
 
@@ -2476,14 +2522,13 @@ static int drm_mode_cursor_common(struct drm_device *dev,
 	if (!req->flags || (~DRM_MODE_CURSOR_FLAGS & req->flags))
 		return -EINVAL;
 
-	obj = drm_mode_object_find(dev, req->crtc_id, DRM_MODE_OBJECT_CRTC);
-	if (!obj) {
+	crtc = drm_crtc_find(dev, req->crtc_id);
+	if (!crtc) {
 		DRM_DEBUG_KMS("Unknown CRTC ID %d\n", req->crtc_id);
 		return -ENOENT;
 	}
-	crtc = obj_to_crtc(obj);
 
-	mutex_lock(&crtc->mutex);
+	drm_modeset_lock(&crtc->mutex, NULL);
 	if (req->flags & DRM_MODE_CURSOR_BO) {
 		if (!crtc->funcs->cursor_set && !crtc->funcs->cursor_set2) {
 			ret = -ENXIO;
@@ -2507,7 +2552,7 @@ static int drm_mode_cursor_common(struct drm_device *dev,
 		}
 	}
 out:
-	mutex_unlock(&crtc->mutex);
+	drm_modeset_unlock(&crtc->mutex);
 
 	return ret;
 
@@ -3097,6 +3142,8 @@ struct drm_property *drm_property_create(struct drm_device *dev, int flags,
 	if (!property)
 		return NULL;
 
+	property->dev = dev;
+
 	if (num_values) {
 		property->values = kzalloc(sizeof(uint64_t)*num_values, GFP_KERNEL);
 		if (!property->values)
@@ -3117,6 +3164,9 @@ struct drm_property *drm_property_create(struct drm_device *dev, int flags,
 	}
 
 	list_add_tail(&property->head, &dev->mode_config.property_list);
+
+	WARN_ON(!drm_property_type_valid(property));
+
 	return property;
 fail:
 	kfree(property->values);
@@ -3217,6 +3267,22 @@ struct drm_property *drm_property_create_bitmask(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_property_create_bitmask);
 
+static struct drm_property *property_create_range(struct drm_device *dev,
+					 int flags, const char *name,
+					 uint64_t min, uint64_t max)
+{
+	struct drm_property *property;
+
+	property = drm_property_create(dev, flags, name, 2);
+	if (!property)
+		return NULL;
+
+	property->values[0] = min;
+	property->values[1] = max;
+
+	return property;
+}
+
 /**
  * drm_property_create - create a new ranged property type
  * @dev: drm device
@@ -3239,20 +3305,36 @@ struct drm_property *drm_property_create_range(struct drm_device *dev, int flags
 					 const char *name,
 					 uint64_t min, uint64_t max)
 {
+	return property_create_range(dev, DRM_MODE_PROP_RANGE | flags,
+			name, min, max);
+}
+EXPORT_SYMBOL(drm_property_create_range);
+
+struct drm_property *drm_property_create_signed_range(struct drm_device *dev,
+					 int flags, const char *name,
+					 int64_t min, int64_t max)
+{
+	return property_create_range(dev, DRM_MODE_PROP_SIGNED_RANGE | flags,
+			name, I642U64(min), I642U64(max));
+}
+EXPORT_SYMBOL(drm_property_create_signed_range);
+
+struct drm_property *drm_property_create_object(struct drm_device *dev,
+					 int flags, const char *name, uint32_t type)
+{
 	struct drm_property *property;
 
-	flags |= DRM_MODE_PROP_RANGE;
+	flags |= DRM_MODE_PROP_OBJECT;
 
-	property = drm_property_create(dev, flags, name, 2);
+	property = drm_property_create(dev, flags, name, 1);
 	if (!property)
 		return NULL;
 
-	property->values[0] = min;
-	property->values[1] = max;
+	property->values[0] = type;
 
 	return property;
 }
-EXPORT_SYMBOL(drm_property_create_range);
+EXPORT_SYMBOL(drm_property_create_object);
 
 /**
  * drm_property_add_enum - add a possible value to an enumeration property
@@ -3274,14 +3356,16 @@ int drm_property_add_enum(struct drm_property *property, int index,
 {
 	struct drm_property_enum *prop_enum;
 
-	if (!(property->flags & (DRM_MODE_PROP_ENUM | DRM_MODE_PROP_BITMASK)))
+	if (!(drm_property_type_is(property, DRM_MODE_PROP_ENUM) ||
+			drm_property_type_is(property, DRM_MODE_PROP_BITMASK)))
 		return -EINVAL;
 
 	/*
 	 * Bitmask enum properties have the additional constraint of values
 	 * from 0 to 63
 	 */
-	if ((property->flags & DRM_MODE_PROP_BITMASK) && (value > 63))
+	if (drm_property_type_is(property, DRM_MODE_PROP_BITMASK) &&
+			(value > 63))
 		return -EINVAL;
 
 	if (!list_empty(&property->enum_blob_list)) {
@@ -3438,7 +3522,6 @@ EXPORT_SYMBOL(drm_object_property_get_value);
 int drm_mode_getproperty_ioctl(struct drm_device *dev,
 			       void *data, struct drm_file *file_priv)
 {
-	struct drm_mode_object *obj;
 	struct drm_mode_get_property *out_resp = data;
 	struct drm_property *property;
 	int enum_count = 0;
@@ -3457,17 +3540,17 @@ int drm_mode_getproperty_ioctl(struct drm_device *dev,
 		return -EINVAL;
 
 	drm_modeset_lock_all(dev);
-	obj = drm_mode_object_find(dev, out_resp->prop_id, DRM_MODE_OBJECT_PROPERTY);
-	if (!obj) {
+	property = drm_property_find(dev, out_resp->prop_id);
+	if (!property) {
 		ret = -ENOENT;
 		goto done;
 	}
-	property = obj_to_property(obj);
 
-	if (property->flags & (DRM_MODE_PROP_ENUM | DRM_MODE_PROP_BITMASK)) {
+	if (drm_property_type_is(property, DRM_MODE_PROP_ENUM) ||
+			drm_property_type_is(property, DRM_MODE_PROP_BITMASK)) {
 		list_for_each_entry(prop_enum, &property->enum_blob_list, head)
 			enum_count++;
-	} else if (property->flags & DRM_MODE_PROP_BLOB) {
+	} else if (drm_property_type_is(property, DRM_MODE_PROP_BLOB)) {
 		list_for_each_entry(prop_blob, &property->enum_blob_list, head)
 			blob_count++;
 	}
@@ -3489,7 +3572,8 @@ int drm_mode_getproperty_ioctl(struct drm_device *dev,
 	}
 	out_resp->count_values = value_count;
 
-	if (property->flags & (DRM_MODE_PROP_ENUM | DRM_MODE_PROP_BITMASK)) {
+	if (drm_property_type_is(property, DRM_MODE_PROP_ENUM) ||
+			drm_property_type_is(property, DRM_MODE_PROP_BITMASK)) {
 		if ((out_resp->count_enum_blobs >= enum_count) && enum_count) {
 			copied = 0;
 			enum_ptr = (struct drm_mode_property_enum __user *)(unsigned long)out_resp->enum_blob_ptr;
@@ -3511,7 +3595,7 @@ int drm_mode_getproperty_ioctl(struct drm_device *dev,
 		out_resp->count_enum_blobs = enum_count;
 	}
 
-	if (property->flags & DRM_MODE_PROP_BLOB) {
+	if (drm_property_type_is(property, DRM_MODE_PROP_BLOB)) {
 		if ((out_resp->count_enum_blobs >= blob_count) && blob_count) {
 			copied = 0;
 			blob_id_ptr = (uint32_t __user *)(unsigned long)out_resp->enum_blob_ptr;
@@ -3590,7 +3674,6 @@ static void drm_property_destroy_blob(struct drm_device *dev,
 int drm_mode_getblob_ioctl(struct drm_device *dev,
 			   void *data, struct drm_file *file_priv)
 {
-	struct drm_mode_object *obj;
 	struct drm_mode_get_blob *out_resp = data;
 	struct drm_property_blob *blob;
 	int ret = 0;
@@ -3600,12 +3683,11 @@ int drm_mode_getblob_ioctl(struct drm_device *dev,
 		return -EINVAL;
 
 	drm_modeset_lock_all(dev);
-	obj = drm_mode_object_find(dev, out_resp->blob_id, DRM_MODE_OBJECT_BLOB);
-	if (!obj) {
+	blob = drm_property_blob_find(dev, out_resp->blob_id);
+	if (!blob) {
 		ret = -ENOENT;
 		goto done;
 	}
-	blob = obj_to_blob(obj);
 
 	if (out_resp->length == blob->length) {
 		blob_ptr = (void __user *)(unsigned long)out_resp->data;
@@ -3667,19 +3749,40 @@ static bool drm_property_change_is_valid(struct drm_property *property,
 {
 	if (property->flags & DRM_MODE_PROP_IMMUTABLE)
 		return false;
-	if (property->flags & DRM_MODE_PROP_RANGE) {
+
+	if (drm_property_type_is(property, DRM_MODE_PROP_RANGE)) {
 		if (value < property->values[0] || value > property->values[1])
 			return false;
 		return true;
-	} else if (property->flags & DRM_MODE_PROP_BITMASK) {
+	} else if (drm_property_type_is(property, DRM_MODE_PROP_SIGNED_RANGE)) {
+		int64_t svalue = U642I64(value);
+		if (svalue < U642I64(property->values[0]) ||
+				svalue > U642I64(property->values[1]))
+			return false;
+		return true;
+	} else if (drm_property_type_is(property, DRM_MODE_PROP_BITMASK)) {
 		int i;
 		uint64_t valid_mask = 0;
 		for (i = 0; i < property->num_values; i++)
 			valid_mask |= (1ULL << property->values[i]);
 		return !(value & ~valid_mask);
-	} else if (property->flags & DRM_MODE_PROP_BLOB) {
+	} else if (drm_property_type_is(property, DRM_MODE_PROP_BLOB)) {
 		/* Only the driver knows */
 		return true;
+	} else if (drm_property_type_is(property, DRM_MODE_PROP_OBJECT)) {
+		struct drm_mode_object *obj;
+		/* a zero value for an object property translates to null: */
+		if (value == 0)
+			return true;
+		/*
+		 * NOTE: use _object_find() directly to bypass restriction on
+		 * looking up refcnt'd objects (ie. fb's).  For a refcnt'd
+		 * object this could race against object finalization, so it
+		 * simply tells us that the object *was* valid.  Which is good
+		 * enough.
+		 */
+		obj = _object_find(property->dev, value, property->values[0]);
+		return obj != NULL;
 	} else {
 		int i;
 		for (i = 0; i < property->num_values; i++)
@@ -3987,7 +4090,6 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev,
 			     void *data, struct drm_file *file_priv)
 {
 	struct drm_mode_crtc_lut *crtc_lut = data;
-	struct drm_mode_object *obj;
 	struct drm_crtc *crtc;
 	void *r_base, *g_base, *b_base;
 	int size;
@@ -3997,12 +4099,11 @@ int drm_mode_gamma_set_ioctl(struct drm_device *dev,
 		return -EINVAL;
 
 	drm_modeset_lock_all(dev);
-	obj = drm_mode_object_find(dev, crtc_lut->crtc_id, DRM_MODE_OBJECT_CRTC);
-	if (!obj) {
+	crtc = drm_crtc_find(dev, crtc_lut->crtc_id);
+	if (!crtc) {
 		ret = -ENOENT;
 		goto out;
 	}
-	crtc = obj_to_crtc(obj);
 
 	if (crtc->funcs->gamma_set == NULL) {
 		ret = -ENOSYS;
@@ -4061,7 +4162,6 @@ int drm_mode_gamma_get_ioctl(struct drm_device *dev,
 			     void *data, struct drm_file *file_priv)
 {
 	struct drm_mode_crtc_lut *crtc_lut = data;
-	struct drm_mode_object *obj;
 	struct drm_crtc *crtc;
 	void *r_base, *g_base, *b_base;
 	int size;
@@ -4071,12 +4171,11 @@ int drm_mode_gamma_get_ioctl(struct drm_device *dev,
 		return -EINVAL;
 
 	drm_modeset_lock_all(dev);
-	obj = drm_mode_object_find(dev, crtc_lut->crtc_id, DRM_MODE_OBJECT_CRTC);
-	if (!obj) {
+	crtc = drm_crtc_find(dev, crtc_lut->crtc_id);
+	if (!crtc) {
 		ret = -ENOENT;
 		goto out;
 	}
-	crtc = obj_to_crtc(obj);
 
 	/* memcpy into gamma store */
 	if (crtc_lut->gamma_size != crtc->gamma_size) {
@@ -4129,7 +4228,6 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 			     void *data, struct drm_file *file_priv)
 {
 	struct drm_mode_crtc_page_flip *page_flip = data;
-	struct drm_mode_object *obj;
 	struct drm_crtc *crtc;
 	struct drm_framebuffer *fb = NULL, *old_fb = NULL;
 	struct drm_pending_vblank_event *e = NULL;
@@ -4143,12 +4241,11 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev,
 	if ((page_flip->flags & DRM_MODE_PAGE_FLIP_ASYNC) && !dev->mode_config.async_page_flip)
 		return -EINVAL;
 
-	obj = drm_mode_object_find(dev, page_flip->crtc_id, DRM_MODE_OBJECT_CRTC);
-	if (!obj)
+	crtc = drm_crtc_find(dev, page_flip->crtc_id);
+	if (!crtc)
 		return -ENOENT;
-	crtc = obj_to_crtc(obj);
 
-	mutex_lock(&crtc->mutex);
+	drm_modeset_lock(&crtc->mutex, NULL);
 	if (crtc->primary->fb == NULL) {
 		/* The framebuffer is currently unbound, presumably
 		 * due to a hotplug event, that userspace has not
@@ -4232,7 +4329,7 @@ out:
 		drm_framebuffer_unreference(fb);
 	if (old_fb)
 		drm_framebuffer_unreference(old_fb);
-	mutex_unlock(&crtc->mutex);
+	drm_modeset_unlock(&crtc->mutex);
 
 	return ret;
 }
@@ -4597,6 +4694,7 @@ EXPORT_SYMBOL(drm_format_vert_chroma_subsampling);
 void drm_mode_config_init(struct drm_device *dev)
 {
 	mutex_init(&dev->mode_config.mutex);
+	drm_modeset_lock_init(&dev->mode_config.connection_mutex);
 	mutex_init(&dev->mode_config.idr_mutex);
 	mutex_init(&dev->mode_config.fb_lock);
 	INIT_LIST_HEAD(&dev->mode_config.fb_list);
@@ -4696,5 +4794,6 @@ void drm_mode_config_cleanup(struct drm_device *dev)
 	}
 
 	idr_destroy(&dev->mode_config.crtc_idr);
+	drm_modeset_lock_fini(&dev->mode_config.connection_mutex);
 }
 EXPORT_SYMBOL(drm_mode_config_cleanup);
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 872ba11c453..78b37f3febd 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -93,8 +93,10 @@ bool drm_helper_encoder_in_use(struct drm_encoder *encoder)
 	 * We can expect this mutex to be locked if we are not panicking.
 	 * Locking is currently fubar in the panic handler.
 	 */
-	if (!oops_in_progress)
+	if (!oops_in_progress) {
 		WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
+		WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+	}
 
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
 		if (connector->encoder == encoder)
@@ -153,20 +155,14 @@ drm_encoder_disable(struct drm_encoder *encoder)
 static void __drm_helper_disable_unused_functions(struct drm_device *dev)
 {
 	struct drm_encoder *encoder;
-	struct drm_connector *connector;
 	struct drm_crtc *crtc;
 
 	drm_warn_on_modeset_not_all_locked(dev);
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		if (!connector->encoder)
-			continue;
-	}
-
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 		if (!drm_helper_encoder_in_use(encoder)) {
 			drm_encoder_disable(encoder);
-			/* disconnector encoder from any connector */
+			/* disconnect encoder from any connector */
 			encoder->crtc = NULL;
 		}
 	}
@@ -349,7 +345,7 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
 			continue;
 
 		DRM_DEBUG_KMS("[ENCODER:%d:%s] set [MODE:%d:%s]\n",
-			encoder->base.id, drm_get_encoder_name(encoder),
+			encoder->base.id, encoder->name,
 			mode->base.id, mode->name);
 		encoder_funcs = encoder->helper_private;
 		encoder_funcs->mode_set(encoder, mode, adjusted_mode);
@@ -400,8 +396,7 @@ done:
 }
 EXPORT_SYMBOL(drm_crtc_helper_set_mode);
 
-
-static int
+static void
 drm_crtc_helper_disable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -430,7 +425,6 @@ drm_crtc_helper_disable(struct drm_crtc *crtc)
 	}
 
 	__drm_helper_disable_unused_functions(dev);
-	return 0;
 }
 
 /**
@@ -481,7 +475,8 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 				(int)set->num_connectors, set->x, set->y);
 	} else {
 		DRM_DEBUG_KMS("[CRTC:%d] [NOFB]\n", set->crtc->base.id);
-		return drm_crtc_helper_disable(set->crtc);
+		drm_crtc_helper_disable(set->crtc);
+		return 0;
 	}
 
 	dev = set->crtc->dev;
@@ -620,11 +615,11 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 		}
 		if (new_crtc) {
 			DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [CRTC:%d]\n",
-				connector->base.id, drm_get_connector_name(connector),
+				connector->base.id, connector->name,
 				new_crtc->base.id);
 		} else {
 			DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [NOCRTC]\n",
-				connector->base.id, drm_get_connector_name(connector));
+				connector->base.id, connector->name);
 		}
 	}
 
@@ -650,7 +645,7 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 			DRM_DEBUG_KMS("Setting connector DPMS state to on\n");
 			for (i = 0; i < set->num_connectors; i++) {
 				DRM_DEBUG_KMS("\t[CONNECTOR:%d:%s] set DPMS on\n", set->connectors[i]->base.id,
-					      drm_get_connector_name(set->connectors[i]));
+					      set->connectors[i]->name);
 				set->connectors[i]->funcs->dpms(set->connectors[i], DRM_MODE_DPMS_ON);
 			}
 		}
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 4b6e6f3ba0a..08e33b8b13a 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -206,13 +206,17 @@ i2c_dp_aux_prepare_bus(struct i2c_adapter *adapter)
  * i2c_dp_aux_add_bus() - register an i2c adapter using the aux ch helper
  * @adapter: i2c adapter to register
  *
- * This registers an i2c adapater that uses dp aux channel as it's underlaying
+ * This registers an i2c adapter that uses dp aux channel as it's underlaying
  * transport. The driver needs to fill out the &i2c_algo_dp_aux_data structure
  * and store it in the algo_data member of the @adapter argument. This will be
  * used by the i2c over dp aux algorithm to drive the hardware.
  *
  * RETURNS:
  * 0 on success, -ERRNO on failure.
+ *
+ * IMPORTANT:
+ * This interface is deprecated, please switch to the new dp aux helpers and
+ * drm_dp_aux_register().
  */
 int
 i2c_dp_aux_add_bus(struct i2c_adapter *adapter)
@@ -378,7 +382,10 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request,
 	 * transactions.
 	 */
 	for (retry = 0; retry < 7; retry++) {
+
+		mutex_lock(&aux->hw_mutex);
 		err = aux->transfer(aux, &msg);
+		mutex_unlock(&aux->hw_mutex);
 		if (err < 0) {
 			if (err == -EBUSY)
 				continue;
@@ -592,7 +599,9 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
 	 * before giving up the AUX transaction.
 	 */
 	for (retry = 0; retry < 7; retry++) {
+		mutex_lock(&aux->hw_mutex);
 		err = aux->transfer(aux, msg);
+		mutex_unlock(&aux->hw_mutex);
 		if (err < 0) {
 			if (err == -EBUSY)
 				continue;
@@ -725,13 +734,15 @@ static const struct i2c_algorithm drm_dp_i2c_algo = {
 };
 
 /**
- * drm_dp_aux_register_i2c_bus() - register an I2C adapter for I2C-over-AUX
+ * drm_dp_aux_register() - initialise and register aux channel
  * @aux: DisplayPort AUX channel
  *
  * Returns 0 on success or a negative error code on failure.
  */
-int drm_dp_aux_register_i2c_bus(struct drm_dp_aux *aux)
+int drm_dp_aux_register(struct drm_dp_aux *aux)
 {
+	mutex_init(&aux->hw_mutex);
+
 	aux->ddc.algo = &drm_dp_i2c_algo;
 	aux->ddc.algo_data = aux;
 	aux->ddc.retries = 3;
@@ -746,14 +757,14 @@ int drm_dp_aux_register_i2c_bus(struct drm_dp_aux *aux)
 
 	return i2c_add_adapter(&aux->ddc);
 }
-EXPORT_SYMBOL(drm_dp_aux_register_i2c_bus);
+EXPORT_SYMBOL(drm_dp_aux_register);
 
 /**
- * drm_dp_aux_unregister_i2c_bus() - unregister an I2C-over-AUX adapter
+ * drm_dp_aux_unregister() - unregister an AUX adapter
  * @aux: DisplayPort AUX channel
  */
-void drm_dp_aux_unregister_i2c_bus(struct drm_dp_aux *aux)
+void drm_dp_aux_unregister(struct drm_dp_aux *aux)
 {
 	i2c_del_adapter(&aux->ddc);
 }
-EXPORT_SYMBOL(drm_dp_aux_unregister_i2c_bus);
+EXPORT_SYMBOL(drm_dp_aux_unregister);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 03711d00aaa..8218078b613 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -419,8 +419,9 @@ long drm_ioctl(struct file *filp,
 			retcode = -EFAULT;
 			goto err_i1;
 		}
-	} else
+	} else if (cmd & IOC_OUT) {
 		memset(kdata, 0, usize);
+	}
 
 	if (ioctl->flags & DRM_UNLOCKED)
 		retcode = func(dev, kdata, file_priv);
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index d4e3f9d9370..dfa9769b26b 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -70,6 +70,8 @@
 #define EDID_QUIRK_FORCE_REDUCED_BLANKING	(1 << 7)
 /* Force 8bpc */
 #define EDID_QUIRK_FORCE_8BPC			(1 << 8)
+/* Force 12bpc */
+#define EDID_QUIRK_FORCE_12BPC			(1 << 9)
 
 struct detailed_mode_closure {
 	struct drm_connector *connector;
@@ -125,6 +127,9 @@ static struct edid_quirk {
 	{ "SAM", 596, EDID_QUIRK_PREFER_LARGE_60 },
 	{ "SAM", 638, EDID_QUIRK_PREFER_LARGE_60 },
 
+	/* Sony PVM-2541A does up to 12 bpc, but only reports max 8 bpc */
+	{ "SNY", 0x2541, EDID_QUIRK_FORCE_12BPC },
+
 	/* ViewSonic VA2026w */
 	{ "VSC", 5020, EDID_QUIRK_FORCE_REDUCED_BLANKING },
 
@@ -984,9 +989,13 @@ static const u8 edid_header[] = {
 	0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00
 };
 
- /*
- * Sanity check the header of the base EDID block.  Return 8 if the header
- * is perfect, down to 0 if it's totally wrong.
+/**
+ * drm_edid_header_is_valid - sanity check the header of the base EDID block
+ * @raw_edid: pointer to raw base EDID block
+ *
+ * Sanity check the header of the base EDID block.
+ *
+ * Return: 8 if the header is perfect, down to 0 if it's totally wrong.
  */
 int drm_edid_header_is_valid(const u8 *raw_edid)
 {
@@ -1005,9 +1014,16 @@ module_param_named(edid_fixup, edid_fixup, int, 0400);
 MODULE_PARM_DESC(edid_fixup,
 		 "Minimum number of valid EDID header bytes (0-8, default 6)");
 
-/*
- * Sanity check the EDID block (base or extension).  Return 0 if the block
- * doesn't check out, or 1 if it's valid.
+/**
+ * drm_edid_block_valid - Sanity check the EDID block (base or extension)
+ * @raw_edid: pointer to raw EDID block
+ * @block: type of block to validate (0 for base, extension otherwise)
+ * @print_bad_edid: if true, dump bad EDID blocks to the console
+ *
+ * Validate a base or extension EDID block and optionally dump bad blocks to
+ * the console.
+ *
+ * Return: True if the block is valid, false otherwise.
  */
 bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid)
 {
@@ -1077,6 +1093,8 @@ EXPORT_SYMBOL(drm_edid_block_valid);
  * @edid: EDID data
  *
  * Sanity-check an entire EDID record (including extensions)
+ *
+ * Return: True if the EDID data is valid, false otherwise.
  */
 bool drm_edid_is_valid(struct edid *edid)
 {
@@ -1096,18 +1114,15 @@ EXPORT_SYMBOL(drm_edid_is_valid);
 
 #define DDC_SEGMENT_ADDR 0x30
 /**
- * Get EDID information via I2C.
- *
- * @adapter : i2c device adaptor
+ * drm_do_probe_ddc_edid() - get EDID information via I2C
+ * @adapter: I2C device adaptor
  * @buf: EDID data buffer to be filled
  * @block: 128 byte EDID block to start fetching from
  * @len: EDID data buffer length to fetch
  *
- * Returns:
- *
- * 0 on success or -1 on failure.
+ * Try to fetch EDID information by calling I2C driver functions.
  *
- * Try to fetch EDID information by calling i2c driver function.
+ * Return: 0 on success or -1 on failure.
  */
 static int
 drm_do_probe_ddc_edid(struct i2c_adapter *adapter, unsigned char *buf,
@@ -1118,7 +1133,8 @@ drm_do_probe_ddc_edid(struct i2c_adapter *adapter, unsigned char *buf,
 	unsigned char xfers = segment ? 3 : 2;
 	int ret, retries = 5;
 
-	/* The core i2c driver will automatically retry the transfer if the
+	/*
+	 * The core I2C driver will automatically retry the transfer if the
 	 * adapter reports EAGAIN. However, we find that bit-banging transfers
 	 * are susceptible to errors under a heavily loaded machine and
 	 * generate spurious NAKs and timeouts. Retrying the transfer
@@ -1144,10 +1160,10 @@ drm_do_probe_ddc_edid(struct i2c_adapter *adapter, unsigned char *buf,
 			}
 		};
 
-	/*
-	 * Avoid sending the segment addr to not upset non-compliant ddc
-	 * monitors.
-	 */
+		/*
+		 * Avoid sending the segment addr to not upset non-compliant
+		 * DDC monitors.
+		 */
 		ret = i2c_transfer(adapter, &msgs[3 - xfers], xfers);
 
 		if (ret == -ENXIO) {
@@ -1216,7 +1232,7 @@ drm_do_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter)
 		if (i == 4 && print_bad_edid) {
 			dev_warn(connector->dev->dev,
 			 "%s: Ignoring invalid EDID block %d.\n",
-			 drm_get_connector_name(connector), j);
+			 connector->name, j);
 
 			connector->bad_edid_counter++;
 		}
@@ -1236,7 +1252,7 @@ drm_do_get_edid(struct drm_connector *connector, struct i2c_adapter *adapter)
 carp:
 	if (print_bad_edid) {
 		dev_warn(connector->dev->dev, "%s: EDID block %d invalid.\n",
-			 drm_get_connector_name(connector), j);
+			 connector->name, j);
 	}
 	connector->bad_edid_counter++;
 
@@ -1246,12 +1262,10 @@ out:
 }
 
 /**
- * Probe DDC presence.
- * @adapter: i2c adapter to probe
+ * drm_probe_ddc() - probe DDC presence
+ * @adapter: I2C adapter to probe
  *
- * Returns:
- *
- * 1 on success
+ * Return: True on success, false on failure.
  */
 bool
 drm_probe_ddc(struct i2c_adapter *adapter)
@@ -1265,12 +1279,12 @@ EXPORT_SYMBOL(drm_probe_ddc);
 /**
  * drm_get_edid - get EDID data, if available
  * @connector: connector we're probing
- * @adapter: i2c adapter to use for DDC
+ * @adapter: I2C adapter to use for DDC
  *
- * Poke the given i2c channel to grab EDID data if possible.  If found,
+ * Poke the given I2C channel to grab EDID data if possible.  If found,
  * attach it to the connector.
  *
- * Return edid data or NULL if we couldn't find any.
+ * Return: Pointer to valid EDID or NULL if we couldn't find any.
  */
 struct edid *drm_get_edid(struct drm_connector *connector,
 			  struct i2c_adapter *adapter)
@@ -1288,7 +1302,7 @@ EXPORT_SYMBOL(drm_get_edid);
  * drm_edid_duplicate - duplicate an EDID and the extensions
  * @edid: EDID to duplicate
  *
- * Return duplicate edid or NULL on allocation failure.
+ * Return: Pointer to duplicated EDID or NULL on allocation failure.
  */
 struct edid *drm_edid_duplicate(const struct edid *edid)
 {
@@ -1411,7 +1425,8 @@ mode_is_rb(const struct drm_display_mode *mode)
  * @rb: Mode reduced-blanking-ness
  *
  * Walk the DMT mode list looking for a match for the given parameters.
- * Return a newly allocated copy of the mode, or NULL if not found.
+ *
+ * Return: A newly allocated copy of the mode, or NULL if not found.
  */
 struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev,
 					   int hsize, int vsize, int fresh,
@@ -1595,14 +1610,13 @@ bad_std_timing(u8 a, u8 b)
  * @connector: connector of for the EDID block
  * @edid: EDID block to scan
  * @t: standard timing params
- * @revision: standard timing level
  *
  * Take the standard timing params (in this case width, aspect, and refresh)
  * and convert them into a real mode using CVT/GTF/DMT.
  */
 static struct drm_display_mode *
 drm_mode_std(struct drm_connector *connector, struct edid *edid,
-	     struct std_timing *t, int revision)
+	     struct std_timing *t)
 {
 	struct drm_device *dev = connector->dev;
 	struct drm_display_mode *m, *mode = NULL;
@@ -1623,7 +1637,7 @@ drm_mode_std(struct drm_connector *connector, struct edid *edid,
 	vrefresh_rate = vfreq + 60;
 	/* the vdisplay is calculated based on the aspect ratio */
 	if (aspect_ratio == 0) {
-		if (revision < 3)
+		if (edid->revision < 3)
 			vsize = hsize;
 		else
 			vsize = (hsize * 10) / 16;
@@ -2140,7 +2154,7 @@ do_established_modes(struct detailed_timing *timing, void *c)
 
 /**
  * add_established_modes - get est. modes from EDID and add them
- * @connector: connector of for the EDID block
+ * @connector: connector to add mode(s) to
  * @edid: EDID block to scan
  *
  * Each EDID block contains a bitmap of the supported "established modes" list
@@ -2191,8 +2205,7 @@ do_standard_modes(struct detailed_timing *timing, void *c)
 			struct drm_display_mode *newmode;
 
 			std = &data->data.timings[i];
-			newmode = drm_mode_std(connector, edid, std,
-					       edid->revision);
+			newmode = drm_mode_std(connector, edid, std);
 			if (newmode) {
 				drm_mode_probed_add(connector, newmode);
 				closure->modes++;
@@ -2203,7 +2216,7 @@ do_standard_modes(struct detailed_timing *timing, void *c)
 
 /**
  * add_standard_modes - get std. modes from EDID and add them
- * @connector: connector of for the EDID block
+ * @connector: connector to add mode(s) to
  * @edid: EDID block to scan
  *
  * Standard modes can be calculated using the appropriate standard (DMT,
@@ -2221,8 +2234,7 @@ add_standard_modes(struct drm_connector *connector, struct edid *edid)
 		struct drm_display_mode *newmode;
 
 		newmode = drm_mode_std(connector, edid,
-				       &edid->standard_timings[i],
-				       edid->revision);
+				       &edid->standard_timings[i]);
 		if (newmode) {
 			drm_mode_probed_add(connector, newmode);
 			modes++;
@@ -2425,7 +2437,7 @@ cea_mode_alternate_clock(const struct drm_display_mode *cea_mode)
  * drm_match_cea_mode - look for a CEA mode matching given mode
  * @to_match: display mode
  *
- * Returns the CEA Video ID (VIC) of the mode or 0 if it isn't a CEA-861
+ * Return: The CEA Video ID (VIC) of the mode or 0 if it isn't a CEA-861
  * mode.
  */
 u8 drm_match_cea_mode(const struct drm_display_mode *to_match)
@@ -2452,6 +2464,22 @@ u8 drm_match_cea_mode(const struct drm_display_mode *to_match)
 }
 EXPORT_SYMBOL(drm_match_cea_mode);
 
+/**
+ * drm_get_cea_aspect_ratio - get the picture aspect ratio corresponding to
+ * the input VIC from the CEA mode list
+ * @video_code: ID given to each of the CEA modes
+ *
+ * Returns picture aspect ratio
+ */
+enum hdmi_picture_aspect drm_get_cea_aspect_ratio(const u8 video_code)
+{
+	/* return picture aspect ratio for video_code - 1 to access the
+	 * right array element
+	*/
+	return edid_cea_modes[video_code-1].picture_aspect_ratio;
+}
+EXPORT_SYMBOL(drm_get_cea_aspect_ratio);
+
 /*
  * Calculate the alternate clock for HDMI modes (those from the HDMI vendor
  * specific block).
@@ -3023,11 +3051,9 @@ monitor_name(struct detailed_timing *t, void *data)
  * @connector: connector corresponding to the HDMI/DP sink
  * @edid: EDID to parse
  *
- * Fill the ELD (EDID-Like Data) buffer for passing to the audio driver.
- * Some ELD fields are left to the graphics driver caller:
- * - Conn_Type
- * - HDCP
- * - Port_ID
+ * Fill the ELD (EDID-Like Data) buffer for passing to the audio driver. The
+ * Conn_Type, HDCP and Port_ID ELD fields are left for the graphics driver to
+ * fill in.
  */
 void drm_edid_to_eld(struct drm_connector *connector, struct edid *edid)
 {
@@ -3111,9 +3137,10 @@ EXPORT_SYMBOL(drm_edid_to_eld);
  * @sads: pointer that will be set to the extracted SADs
  *
  * Looks for CEA EDID block and extracts SADs (Short Audio Descriptors) from it.
- * Note: returned pointer needs to be kfreed
  *
- * Return number of found SADs or negative number on error.
+ * Note: The returned pointer needs to be freed using kfree().
+ *
+ * Return: The number of found SADs or negative number on error.
  */
 int drm_edid_to_sad(struct edid *edid, struct cea_sad **sads)
 {
@@ -3170,9 +3197,11 @@ EXPORT_SYMBOL(drm_edid_to_sad);
  * @sadb: pointer to the speaker block
  *
  * Looks for CEA EDID block and extracts the Speaker Allocation Data Block from it.
- * Note: returned pointer needs to be kfreed
  *
- * Return number of found Speaker Allocation Blocks or negative number on error.
+ * Note: The returned pointer needs to be freed using kfree().
+ *
+ * Return: The number of found Speaker Allocation Blocks or negative number on
+ * error.
  */
 int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb)
 {
@@ -3204,10 +3233,9 @@ int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb)
 
 			/* Speaker Allocation Data Block */
 			if (dbl == 3) {
-				*sadb = kmalloc(dbl, GFP_KERNEL);
+				*sadb = kmemdup(&db[1], dbl, GFP_KERNEL);
 				if (!*sadb)
 					return -ENOMEM;
-				memcpy(*sadb, &db[1], dbl);
 				count = dbl;
 				break;
 			}
@@ -3219,9 +3247,12 @@ int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb)
 EXPORT_SYMBOL(drm_edid_to_speaker_allocation);
 
 /**
- * drm_av_sync_delay - HDMI/DP sink audio-video sync delay in millisecond
+ * drm_av_sync_delay - compute the HDMI/DP sink audio-video sync delay
  * @connector: connector associated with the HDMI/DP sink
  * @mode: the display mode
+ *
+ * Return: The HDMI/DP sink's audio-video sync delay in milliseconds or 0 if
+ * the sink doesn't support audio or video.
  */
 int drm_av_sync_delay(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
@@ -3263,6 +3294,9 @@ EXPORT_SYMBOL(drm_av_sync_delay);
  *
  * It's possible for one encoder to be associated with multiple HDMI/DP sinks.
  * The policy is now hard coded to simply use the first HDMI/DP sink's ELD.
+ *
+ * Return: The connector associated with the first HDMI/DP sink that has ELD
+ * attached to it.
  */
 struct drm_connector *drm_select_eld(struct drm_encoder *encoder,
 				     struct drm_display_mode *mode)
@@ -3270,6 +3304,8 @@ struct drm_connector *drm_select_eld(struct drm_encoder *encoder,
 	struct drm_connector *connector;
 	struct drm_device *dev = encoder->dev;
 
+	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
+
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
 		if (connector->encoder == encoder && connector->eld[0])
 			return connector;
@@ -3279,11 +3315,12 @@ struct drm_connector *drm_select_eld(struct drm_encoder *encoder,
 EXPORT_SYMBOL(drm_select_eld);
 
 /**
- * drm_detect_hdmi_monitor - detect whether monitor is hdmi.
+ * drm_detect_hdmi_monitor - detect whether monitor is HDMI
  * @edid: monitor EDID information
  *
  * Parse the CEA extension according to CEA-861-B.
- * Return true if HDMI, false if not or unknown.
+ *
+ * Return: True if the monitor is HDMI, false if not or unknown.
  */
 bool drm_detect_hdmi_monitor(struct edid *edid)
 {
@@ -3321,6 +3358,7 @@ EXPORT_SYMBOL(drm_detect_hdmi_monitor);
  * audio format, assume at least 'basic audio' support, even if 'basic
  * audio' is not defined in EDID.
  *
+ * Return: True if the monitor supports audio, false otherwise.
  */
 bool drm_detect_monitor_audio(struct edid *edid)
 {
@@ -3364,6 +3402,8 @@ EXPORT_SYMBOL(drm_detect_monitor_audio);
  * Check whether the monitor reports the RGB quantization range selection
  * as supported. The AVI infoframe can then be used to inform the monitor
  * which quantization range (full or limited) is used.
+ *
+ * Return: True if the RGB quantization range is selectable, false otherwise.
  */
 bool drm_rgb_quant_range_selectable(struct edid *edid)
 {
@@ -3390,16 +3430,119 @@ bool drm_rgb_quant_range_selectable(struct edid *edid)
 EXPORT_SYMBOL(drm_rgb_quant_range_selectable);
 
 /**
+ * drm_assign_hdmi_deep_color_info - detect whether monitor supports
+ * hdmi deep color modes and update drm_display_info if so.
+ *
+ * @edid: monitor EDID information
+ * @info: Updated with maximum supported deep color bpc and color format
+ *        if deep color supported.
+ *
+ * Parse the CEA extension according to CEA-861-B.
+ * Return true if HDMI deep color supported, false if not or unknown.
+ */
+static bool drm_assign_hdmi_deep_color_info(struct edid *edid,
+                                            struct drm_display_info *info,
+                                            struct drm_connector *connector)
+{
+	u8 *edid_ext, *hdmi;
+	int i;
+	int start_offset, end_offset;
+	unsigned int dc_bpc = 0;
+
+	edid_ext = drm_find_cea_extension(edid);
+	if (!edid_ext)
+		return false;
+
+	if (cea_db_offsets(edid_ext, &start_offset, &end_offset))
+		return false;
+
+	/*
+	 * Because HDMI identifier is in Vendor Specific Block,
+	 * search it from all data blocks of CEA extension.
+	 */
+	for_each_cea_db(edid_ext, i, start_offset, end_offset) {
+		if (cea_db_is_hdmi_vsdb(&edid_ext[i])) {
+			/* HDMI supports at least 8 bpc */
+			info->bpc = 8;
+
+			hdmi = &edid_ext[i];
+			if (cea_db_payload_len(hdmi) < 6)
+				return false;
+
+			if (hdmi[6] & DRM_EDID_HDMI_DC_30) {
+				dc_bpc = 10;
+				info->edid_hdmi_dc_modes |= DRM_EDID_HDMI_DC_30;
+				DRM_DEBUG("%s: HDMI sink does deep color 30.\n",
+						  connector->name);
+			}
+
+			if (hdmi[6] & DRM_EDID_HDMI_DC_36) {
+				dc_bpc = 12;
+				info->edid_hdmi_dc_modes |= DRM_EDID_HDMI_DC_36;
+				DRM_DEBUG("%s: HDMI sink does deep color 36.\n",
+						  connector->name);
+			}
+
+			if (hdmi[6] & DRM_EDID_HDMI_DC_48) {
+				dc_bpc = 16;
+				info->edid_hdmi_dc_modes |= DRM_EDID_HDMI_DC_48;
+				DRM_DEBUG("%s: HDMI sink does deep color 48.\n",
+						  connector->name);
+			}
+
+			if (dc_bpc > 0) {
+				DRM_DEBUG("%s: Assigning HDMI sink color depth as %d bpc.\n",
+						  connector->name, dc_bpc);
+				info->bpc = dc_bpc;
+
+				/*
+				 * Deep color support mandates RGB444 support for all video
+				 * modes and forbids YCRCB422 support for all video modes per
+				 * HDMI 1.3 spec.
+				 */
+				info->color_formats = DRM_COLOR_FORMAT_RGB444;
+
+				/* YCRCB444 is optional according to spec. */
+				if (hdmi[6] & DRM_EDID_HDMI_DC_Y444) {
+					info->color_formats |= DRM_COLOR_FORMAT_YCRCB444;
+					DRM_DEBUG("%s: HDMI sink does YCRCB444 in deep color.\n",
+							  connector->name);
+				}
+
+				/*
+				 * Spec says that if any deep color mode is supported at all,
+				 * then deep color 36 bit must be supported.
+				 */
+				if (!(hdmi[6] & DRM_EDID_HDMI_DC_36)) {
+					DRM_DEBUG("%s: HDMI sink should do DC_36, but does not!\n",
+							  connector->name);
+				}
+
+				return true;
+			}
+			else {
+				DRM_DEBUG("%s: No deep color support on this HDMI sink.\n",
+						  connector->name);
+			}
+		}
+	}
+
+	return false;
+}
+
+/**
  * drm_add_display_info - pull display info out if present
  * @edid: EDID data
  * @info: display info (attached to connector)
+ * @connector: connector whose edid is used to build display info
  *
  * Grab any available display info and stuff it into the drm_display_info
  * structure that's part of the connector.  Useful for tracking bpp and
  * color spaces.
  */
 static void drm_add_display_info(struct edid *edid,
-				 struct drm_display_info *info)
+                                 struct drm_display_info *info,
+                                 struct drm_connector *connector)
 {
 	u8 *edid_ext;
 
@@ -3429,6 +3572,9 @@ static void drm_add_display_info(struct edid *edid,
 			info->color_formats |= DRM_COLOR_FORMAT_YCRCB422;
 	}
 
+	/* HDMI deep color modes supported? Assign to info, if so */
+	drm_assign_hdmi_deep_color_info(edid, info, connector);
+
 	/* Only defined for 1.4 with digital displays */
 	if (edid->revision < 4)
 		return;
@@ -3458,6 +3604,9 @@ static void drm_add_display_info(struct edid *edid,
 		break;
 	}
 
+	DRM_DEBUG("%s: Assigning EDID-1.4 digital sink color depth as %d bpc.\n",
+			  connector->name, info->bpc);
+
 	info->color_formats |= DRM_COLOR_FORMAT_RGB444;
 	if (edid->features & DRM_EDID_FEATURE_RGB_YCRCB444)
 		info->color_formats |= DRM_COLOR_FORMAT_YCRCB444;
@@ -3468,11 +3617,11 @@ static void drm_add_display_info(struct edid *edid,
 /**
  * drm_add_edid_modes - add modes from EDID data, if available
  * @connector: connector we're probing
- * @edid: edid data
+ * @edid: EDID data
  *
  * Add the specified modes to the connector's mode list.
  *
- * Return number of modes added or 0 if we couldn't find any.
+ * Return: The number of modes added or 0 if we couldn't find any.
  */
 int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid)
 {
@@ -3484,7 +3633,7 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid)
 	}
 	if (!drm_edid_is_valid(edid)) {
 		dev_warn(connector->dev->dev, "%s: EDID invalid.\n",
-			 drm_get_connector_name(connector));
+			 connector->name);
 		return 0;
 	}
 
@@ -3516,11 +3665,14 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid)
 	if (quirks & (EDID_QUIRK_PREFER_LARGE_60 | EDID_QUIRK_PREFER_LARGE_75))
 		edid_fixup_preferred(connector, quirks);
 
-	drm_add_display_info(edid, &connector->display_info);
+	drm_add_display_info(edid, &connector->display_info, connector);
 
 	if (quirks & EDID_QUIRK_FORCE_8BPC)
 		connector->display_info.bpc = 8;
 
+	if (quirks & EDID_QUIRK_FORCE_12BPC)
+		connector->display_info.bpc = 12;
+
 	return num_modes;
 }
 EXPORT_SYMBOL(drm_add_edid_modes);
@@ -3534,7 +3686,7 @@ EXPORT_SYMBOL(drm_add_edid_modes);
  * Add the specified modes to the connector's mode list. Only when the
  * hdisplay/vdisplay is not beyond the given limit, it will be added.
  *
- * Return number of modes added or 0 if we couldn't find any.
+ * Return: The number of modes added or 0 if we couldn't find any.
  */
 int drm_add_modes_noedid(struct drm_connector *connector,
 			int hdisplay, int vdisplay)
@@ -3573,13 +3725,22 @@ int drm_add_modes_noedid(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_add_modes_noedid);
 
+/**
+ * drm_set_preferred_mode - Sets the preferred mode of a connector
+ * @connector: connector whose mode list should be processed
+ * @hpref: horizontal resolution of preferred mode
+ * @vpref: vertical resolution of preferred mode
+ *
+ * Marks a mode as preferred if it matches the resolution specified by @hpref
+ * and @vpref.
+ */
 void drm_set_preferred_mode(struct drm_connector *connector,
 			   int hpref, int vpref)
 {
 	struct drm_display_mode *mode;
 
 	list_for_each_entry(mode, &connector->probed_modes, head) {
-		if (mode->hdisplay  == hpref &&
+		if (mode->hdisplay == hpref &&
 		    mode->vdisplay == vpref)
 			mode->type |= DRM_MODE_TYPE_PREFERRED;
 	}
@@ -3592,7 +3753,7 @@ EXPORT_SYMBOL(drm_set_preferred_mode);
  * @frame: HDMI AVI infoframe
  * @mode: DRM display mode
  *
- * Returns 0 on success or a negative error code on failure.
+ * Return: 0 on success or a negative error code on failure.
  */
 int
 drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
@@ -3613,6 +3774,12 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 	frame->video_code = drm_match_cea_mode(mode);
 
 	frame->picture_aspect = HDMI_PICTURE_ASPECT_NONE;
+
+	/* Populate picture aspect ratio from CEA mode list */
+	if (frame->video_code > 0)
+		frame->picture_aspect = drm_get_cea_aspect_ratio(
+						frame->video_code);
+
 	frame->active_aspect = HDMI_ACTIVE_ASPECT_PICTURE;
 	frame->scan_mode = HDMI_SCAN_MODE_UNDERSCAN;
 
@@ -3657,7 +3824,7 @@ s3d_structure_from_display_mode(const struct drm_display_mode *mode)
  * 4k or stereoscopic 3D mode. So when giving any other mode as input this
  * function will return -EINVAL, error that can be safely ignored.
  *
- * Returns 0 on success or a negative error code on failure.
+ * Return: 0 on success or a negative error code on failure.
  */
 int
 drm_hdmi_vendor_infoframe_from_display_mode(struct hdmi_vendor_infoframe *frame,
diff --git a/drivers/gpu/drm/drm_edid_load.c b/drivers/gpu/drm/drm_edid_load.c
index 1b4c7a5442c..0a235fe61c9 100644
--- a/drivers/gpu/drm/drm_edid_load.c
+++ b/drivers/gpu/drm/drm_edid_load.c
@@ -31,8 +31,9 @@ module_param_string(edid_firmware, edid_firmware, sizeof(edid_firmware), 0644);
 MODULE_PARM_DESC(edid_firmware, "Do not probe monitor, use specified EDID blob "
 	"from built-in data or /lib/firmware instead. ");
 
-#define GENERIC_EDIDS 5
+#define GENERIC_EDIDS 6
 static const char *generic_edid_name[GENERIC_EDIDS] = {
+	"edid/800x600.bin",
 	"edid/1024x768.bin",
 	"edid/1280x1024.bin",
 	"edid/1600x1200.bin",
@@ -44,6 +45,24 @@ static const u8 generic_edid[GENERIC_EDIDS][128] = {
 	{
 	0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
 	0x31, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	0x05, 0x16, 0x01, 0x03, 0x6d, 0x1b, 0x14, 0x78,
+	0xea, 0x5e, 0xc0, 0xa4, 0x59, 0x4a, 0x98, 0x25,
+	0x20, 0x50, 0x54, 0x01, 0x00, 0x00, 0x45, 0x40,
+	0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+	0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0xa0, 0x0f,
+	0x20, 0x00, 0x31, 0x58, 0x1c, 0x20, 0x28, 0x80,
+	0x14, 0x00, 0x15, 0xd0, 0x10, 0x00, 0x00, 0x1e,
+	0x00, 0x00, 0x00, 0xff, 0x00, 0x4c, 0x69, 0x6e,
+	0x75, 0x78, 0x20, 0x23, 0x30, 0x0a, 0x20, 0x20,
+	0x20, 0x20, 0x00, 0x00, 0x00, 0xfd, 0x00, 0x3b,
+	0x3d, 0x24, 0x26, 0x05, 0x00, 0x0a, 0x20, 0x20,
+	0x20, 0x20, 0x20, 0x20, 0x00, 0x00, 0x00, 0xfc,
+	0x00, 0x4c, 0x69, 0x6e, 0x75, 0x78, 0x20, 0x53,
+	0x56, 0x47, 0x41, 0x0a, 0x20, 0x20, 0x00, 0xc2,
+	},
+	{
+	0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00,
+	0x31, 0xd8, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
 	0x05, 0x16, 0x01, 0x03, 0x6d, 0x23, 0x1a, 0x78,
 	0xea, 0x5e, 0xc0, 0xa4, 0x59, 0x4a, 0x98, 0x25,
 	0x20, 0x50, 0x54, 0x00, 0x08, 0x00, 0x61, 0x40,
@@ -242,7 +261,7 @@ out:
 
 int drm_load_edid_firmware(struct drm_connector *connector)
 {
-	const char *connector_name = drm_get_connector_name(connector);
+	const char *connector_name = connector->name;
 	char *edidname = edid_firmware, *last, *colon;
 	int ret;
 	struct edid *edid;
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 61b5a47ad23..f27c883be39 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -429,13 +429,8 @@ EXPORT_SYMBOL_GPL(drm_fbdev_cma_fini);
  */
 void drm_fbdev_cma_restore_mode(struct drm_fbdev_cma *fbdev_cma)
 {
-	if (fbdev_cma) {
-		struct drm_device *dev = fbdev_cma->fb_helper.dev;
-
-		drm_modeset_lock_all(dev);
-		drm_fb_helper_restore_fbdev_mode(&fbdev_cma->fb_helper);
-		drm_modeset_unlock_all(dev);
-	}
+	if (fbdev_cma)
+		drm_fb_helper_restore_fbdev_mode_unlocked(&fbdev_cma->fb_helper);
 }
 EXPORT_SYMBOL_GPL(drm_fbdev_cma_restore_mode);
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 04d3fd3658f..d5d8cea1a67 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -45,13 +45,13 @@ static LIST_HEAD(kernel_fb_helper_list);
  * DOC: fbdev helpers
  *
  * The fb helper functions are useful to provide an fbdev on top of a drm kernel
- * mode setting driver. They can be used mostly independantely from the crtc
+ * mode setting driver. They can be used mostly independently from the crtc
  * helper functions used by many drivers to implement the kernel mode setting
  * interfaces.
  *
  * Initialization is done as a three-step process with drm_fb_helper_init(),
  * drm_fb_helper_single_add_all_connectors() and drm_fb_helper_initial_config().
- * Drivers with fancier requirements than the default beheviour can override the
+ * Drivers with fancier requirements than the default behaviour can override the
  * second step with their own code.  Teardown is done with drm_fb_helper_fini().
  *
  * At runtime drivers should restore the fbdev console by calling
@@ -59,7 +59,7 @@ static LIST_HEAD(kernel_fb_helper_list);
  * should also notify the fb helper code from updates to the output
  * configuration by calling drm_fb_helper_hotplug_event(). For easier
  * integration with the output polling code in drm_crtc_helper.c the modeset
- * code proves a ->output_poll_changed callback.
+ * code provides a ->output_poll_changed callback.
  *
  * All other functions exported by the fb helper library can be used to
  * implement the fbdev driver interface by the driver.
@@ -120,7 +120,7 @@ static int drm_fb_helper_parse_command_line(struct drm_fb_helper *fb_helper)
 		mode = &fb_helper_conn->cmdline_mode;
 
 		/* do something on return - turn off connector maybe */
-		if (fb_get_options(drm_get_connector_name(connector), &option))
+		if (fb_get_options(connector->name, &option))
 			continue;
 
 		if (drm_mode_parse_command_line_for_connector(option,
@@ -142,12 +142,12 @@ static int drm_fb_helper_parse_command_line(struct drm_fb_helper *fb_helper)
 				}
 
 				DRM_INFO("forcing %s connector %s\n",
-					 drm_get_connector_name(connector), s);
+					 connector->name, s);
 				connector->force = mode->force;
 			}
 
 			DRM_DEBUG_KMS("cmdline mode for connector %s %dx%d@%dHz%s%s%s\n",
-				      drm_get_connector_name(connector),
+				      connector->name,
 				      mode->xres, mode->yres,
 				      mode->refresh_specified ? mode->refresh : 60,
 				      mode->rb ? " reduced blanking" : "",
@@ -273,15 +273,7 @@ int drm_fb_helper_debug_leave(struct fb_info *info)
 }
 EXPORT_SYMBOL(drm_fb_helper_debug_leave);
 
-/**
- * drm_fb_helper_restore_fbdev_mode - restore fbdev configuration
- * @fb_helper: fbcon to restore
- *
- * This should be called from driver's drm ->lastclose callback
- * when implementing an fbcon on top of kms using this helper. This ensures that
- * the user isn't greeted with a black screen when e.g. X dies.
- */
-bool drm_fb_helper_restore_fbdev_mode(struct drm_fb_helper *fb_helper)
+static bool restore_fbdev_mode(struct drm_fb_helper *fb_helper)
 {
 	struct drm_device *dev = fb_helper->dev;
 	struct drm_plane *plane;
@@ -311,7 +303,40 @@ bool drm_fb_helper_restore_fbdev_mode(struct drm_fb_helper *fb_helper)
 	}
 	return error;
 }
-EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode);
+/**
+ * drm_fb_helper_restore_fbdev_mode - restore fbdev configuration
+ * @fb_helper: fbcon to restore
+ *
+ * This should be called from driver's drm ->lastclose callback
+ * when implementing an fbcon on top of kms using this helper. This ensures that
+ * the user isn't greeted with a black screen when e.g. X dies.
+ *
+ * Use this variant if you need to bypass locking (panic), or already
+ * hold all modeset locks.  Otherwise use drm_fb_helper_restore_fbdev_mode_unlocked()
+ */
+static bool drm_fb_helper_restore_fbdev_mode(struct drm_fb_helper *fb_helper)
+{
+	return restore_fbdev_mode(fb_helper);
+}
+
+/**
+ * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration
+ * @fb_helper: fbcon to restore
+ *
+ * This should be called from driver's drm ->lastclose callback
+ * when implementing an fbcon on top of kms using this helper. This ensures that
+ * the user isn't greeted with a black screen when e.g. X dies.
+ */
+bool drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)
+{
+	struct drm_device *dev = fb_helper->dev;
+	bool ret;
+	drm_modeset_lock_all(dev);
+	ret = restore_fbdev_mode(fb_helper);
+	drm_modeset_unlock_all(dev);
+	return ret;
+}
+EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked);
 
 /*
  * restore fbcon display for all kms driver's using this helper, used for sysrq
@@ -326,12 +351,25 @@ static bool drm_fb_helper_force_kernel_mode(void)
 		return false;
 
 	list_for_each_entry(helper, &kernel_fb_helper_list, kernel_fb_list) {
-		if (helper->dev->switch_power_state == DRM_SWITCH_POWER_OFF)
+		struct drm_device *dev = helper->dev;
+
+		if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
+			continue;
+
+		/* NOTE: we use lockless flag below to avoid grabbing other
+		 * modeset locks.  So just trylock the underlying mutex
+		 * directly:
+		 */
+		if (!mutex_trylock(&dev->mode_config.mutex)) {
+			error = true;
 			continue;
+		}
 
 		ret = drm_fb_helper_restore_fbdev_mode(helper);
 		if (ret)
 			error = true;
+
+		mutex_unlock(&dev->mode_config.mutex);
 	}
 	return error;
 }
@@ -811,7 +849,6 @@ EXPORT_SYMBOL(drm_fb_helper_check_var);
 int drm_fb_helper_set_par(struct fb_info *info)
 {
 	struct drm_fb_helper *fb_helper = info->par;
-	struct drm_device *dev = fb_helper->dev;
 	struct fb_var_screeninfo *var = &info->var;
 
 	if (var->pixclock != 0) {
@@ -819,9 +856,7 @@ int drm_fb_helper_set_par(struct fb_info *info)
 		return -EINVAL;
 	}
 
-	drm_modeset_lock_all(dev);
-	drm_fb_helper_restore_fbdev_mode(fb_helper);
-	drm_modeset_unlock_all(dev);
+	drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
 
 	if (fb_helper->delayed_hotplug) {
 		fb_helper->delayed_hotplug = false;
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index e1eba0b7cd4..021fe5d11df 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -43,8 +43,7 @@
 DEFINE_MUTEX(drm_global_mutex);
 EXPORT_SYMBOL(drm_global_mutex);
 
-static int drm_open_helper(struct inode *inode, struct file *filp,
-			   struct drm_minor *minor);
+static int drm_open_helper(struct file *filp, struct drm_minor *minor);
 
 static int drm_setup(struct drm_device * dev)
 {
@@ -95,7 +94,7 @@ int drm_open(struct inode *inode, struct file *filp)
 	/* share address_space across all char-devs of a single device */
 	filp->f_mapping = dev->anon_inode->i_mapping;
 
-	retcode = drm_open_helper(inode, filp, minor);
+	retcode = drm_open_helper(filp, minor);
 	if (retcode)
 		goto err_undo;
 	if (need_setup) {
@@ -171,7 +170,6 @@ static int drm_cpu_valid(void)
 /**
  * Called whenever a process opens /dev/drm.
  *
- * \param inode device inode.
  * \param filp file pointer.
  * \param minor acquired minor-object.
  * \return zero on success or a negative number on failure.
@@ -179,8 +177,7 @@ static int drm_cpu_valid(void)
  * Creates and initializes a drm_file structure for the file private data in \p
  * filp and add it into the double linked list in \p dev.
  */
-static int drm_open_helper(struct inode *inode, struct file *filp,
-			   struct drm_minor *minor)
+static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 {
 	struct drm_device *dev = minor->dev;
 	struct drm_file *priv;
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 9909bef5980..f7d71190aad 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -474,21 +474,10 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj, gfp_t gfpmask)
 			goto fail;
 		pages[i] = p;
 
-		/* There is a hypothetical issue w/ drivers that require
-		 * buffer memory in the low 4GB.. if the pages are un-
-		 * pinned, and swapped out, they can end up swapped back
-		 * in above 4GB.  If pages are already in memory, then
-		 * shmem_read_mapping_page_gfp will ignore the gfpmask,
-		 * even if the already in-memory page disobeys the mask.
-		 *
-		 * It is only a theoretical issue today, because none of
-		 * the devices with this limitation can be populated with
-		 * enough memory to trigger the issue.  But this BUG_ON()
-		 * is here as a reminder in case the problem with
-		 * shmem_read_mapping_page_gfp() isn't solved by the time
-		 * it does become a real issue.
-		 *
-		 * See this thread: http://lkml.org/lkml/2011/7/11/238
+		/* Make sure shmem keeps __GFP_DMA32 allocated pages in the
+		 * correct region during swapin. Note that this requires
+		 * __GFP_DMA32 to be set in mapping_gfp_mask(inode->i_mapping)
+		 * so shmem can relocate pages during swapin if required.
 		 */
 		BUG_ON((gfpmask & __GFP_DMA32) &&
 				(page_to_pfn(p) >= 0x00100000UL));
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index 7473035dd28..86feedd5e6f 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -47,18 +47,16 @@ int drm_name_info(struct seq_file *m, void *data)
 	struct drm_minor *minor = node->minor;
 	struct drm_device *dev = minor->dev;
 	struct drm_master *master = minor->master;
-	const char *bus_name;
 	if (!master)
 		return 0;
 
-	bus_name = dev->driver->bus->get_name(dev);
 	if (master->unique) {
 		seq_printf(m, "%s %s %s\n",
-			   bus_name,
+			   dev->driver->name,
 			   dev_name(dev->dev), master->unique);
 	} else {
 		seq_printf(m, "%s %s\n",
-			   bus_name, dev_name(dev->dev));
+			   dev->driver->name, dev_name(dev->dev));
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 93a42040bed..69c61f392e6 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -72,9 +72,6 @@ static void
 drm_unset_busid(struct drm_device *dev,
 		struct drm_master *master)
 {
-	kfree(dev->devname);
-	dev->devname = NULL;
-
 	kfree(master->unique);
 	master->unique = NULL;
 	master->unique_len = 0;
@@ -93,7 +90,8 @@ drm_unset_busid(struct drm_device *dev,
  * Copies the bus id from userspace into drm_device::unique, and verifies that
  * it matches the device this DRM is attached to (EINVAL otherwise).  Deprecated
  * in interface version 1.1 and will return EBUSY when setversion has requested
- * version 1.1 or greater.
+ * version 1.1 or greater. Also note that KMS is all version 1.1 and later and
+ * UMS was only ever supported on pci devices.
  */
 int drm_setunique(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
@@ -108,10 +106,13 @@ int drm_setunique(struct drm_device *dev, void *data,
 	if (!u->unique_len || u->unique_len > 1024)
 		return -EINVAL;
 
-	if (!dev->driver->bus->set_unique)
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return 0;
+
+	if (WARN_ON(!dev->pdev))
 		return -EINVAL;
 
-	ret = dev->driver->bus->set_unique(dev, master, u);
+	ret = drm_pci_set_unique(dev, master, u);
 	if (ret)
 		goto err;
 
@@ -130,13 +131,25 @@ static int drm_set_busid(struct drm_device *dev, struct drm_file *file_priv)
 	if (master->unique != NULL)
 		drm_unset_busid(dev, master);
 
-	ret = dev->driver->bus->set_busid(dev, master);
-	if (ret)
-		goto err;
+	if (dev->driver->bus && dev->driver->bus->set_busid) {
+		ret = dev->driver->bus->set_busid(dev, master);
+		if (ret) {
+			drm_unset_busid(dev, master);
+			return ret;
+		}
+	} else {
+		if (WARN(dev->unique == NULL,
+			 "No drm_bus.set_busid() implementation provided by "
+			 "%ps. Use drm_dev_set_unique() to set the unique "
+			 "name explicitly.", dev->driver))
+			return -EINVAL;
+
+		master->unique = kstrdup(dev->unique, GFP_KERNEL);
+		if (master->unique)
+			master->unique_len = strlen(dev->unique);
+	}
+
 	return 0;
-err:
-	drm_unset_busid(dev, master);
-	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index ec5c3f4cdd0..0de123afdb3 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -1,6 +1,5 @@
-/**
- * \file drm_irq.c
- * IRQ support
+/*
+ * drm_irq.c IRQ and vblank support
  *
  * \author Rickard E. (Rik) Faith <faith@valinux.com>
  * \author Gareth Hughes <gareth@valinux.com>
@@ -56,33 +55,6 @@
  */
 #define DRM_REDUNDANT_VBLIRQ_THRESH_NS 1000000
 
-/**
- * Get interrupt from bus id.
- *
- * \param inode device inode.
- * \param file_priv DRM file private.
- * \param cmd command.
- * \param arg user argument, pointing to a drm_irq_busid structure.
- * \return zero on success or a negative number on failure.
- *
- * Finds the PCI device with the specified bus id and gets its IRQ number.
- * This IOCTL is deprecated, and will now return EINVAL for any busid not equal
- * to that of the device that this DRM instance attached to.
- */
-int drm_irq_by_busid(struct drm_device *dev, void *data,
-		     struct drm_file *file_priv)
-{
-	struct drm_irq_busid *p = data;
-
-	if (!dev->driver->bus->irq_by_busid)
-		return -EINVAL;
-
-	if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
-		return -EINVAL;
-
-	return dev->driver->bus->irq_by_busid(dev, p);
-}
-
 /*
  * Clear vblank timestamp buffer for a crtc.
  */
@@ -167,33 +139,40 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 
 static void vblank_disable_fn(unsigned long arg)
 {
-	struct drm_device *dev = (struct drm_device *)arg;
+	struct drm_vblank_crtc *vblank = (void *)arg;
+	struct drm_device *dev = vblank->dev;
 	unsigned long irqflags;
-	int i;
+	int crtc = vblank->crtc;
 
 	if (!dev->vblank_disable_allowed)
 		return;
 
-	for (i = 0; i < dev->num_crtcs; i++) {
-		spin_lock_irqsave(&dev->vbl_lock, irqflags);
-		if (atomic_read(&dev->vblank[i].refcount) == 0 &&
-		    dev->vblank[i].enabled) {
-			DRM_DEBUG("disabling vblank on crtc %d\n", i);
-			vblank_disable_and_save(dev, i);
-		}
-		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+	spin_lock_irqsave(&dev->vbl_lock, irqflags);
+	if (atomic_read(&vblank->refcount) == 0 && vblank->enabled) {
+		DRM_DEBUG("disabling vblank on crtc %d\n", crtc);
+		vblank_disable_and_save(dev, crtc);
 	}
+	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 }
 
+/**
+ * drm_vblank_cleanup - cleanup vblank support
+ * @dev: DRM device
+ *
+ * This function cleans up any resources allocated in drm_vblank_init.
+ */
 void drm_vblank_cleanup(struct drm_device *dev)
 {
+	int crtc;
+
 	/* Bail if the driver didn't call drm_vblank_init() */
 	if (dev->num_crtcs == 0)
 		return;
 
-	del_timer_sync(&dev->vblank_disable_timer);
-
-	vblank_disable_fn((unsigned long)dev);
+	for (crtc = 0; crtc < dev->num_crtcs; crtc++) {
+		del_timer_sync(&dev->vblank[crtc].disable_timer);
+		vblank_disable_fn((unsigned long)&dev->vblank[crtc]);
+	}
 
 	kfree(dev->vblank);
 
@@ -201,12 +180,20 @@ void drm_vblank_cleanup(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_vblank_cleanup);
 
+/**
+ * drm_vblank_init - initialize vblank support
+ * @dev: drm_device
+ * @num_crtcs: number of crtcs supported by @dev
+ *
+ * This function initializes vblank support for @num_crtcs display pipelines.
+ *
+ * Returns:
+ * Zero on success or a negative error code on failure.
+ */
 int drm_vblank_init(struct drm_device *dev, int num_crtcs)
 {
 	int i, ret = -ENOMEM;
 
-	setup_timer(&dev->vblank_disable_timer, vblank_disable_fn,
-		    (unsigned long)dev);
 	spin_lock_init(&dev->vbl_lock);
 	spin_lock_init(&dev->vblank_time_lock);
 
@@ -216,8 +203,13 @@ int drm_vblank_init(struct drm_device *dev, int num_crtcs)
 	if (!dev->vblank)
 		goto err;
 
-	for (i = 0; i < num_crtcs; i++)
+	for (i = 0; i < num_crtcs; i++) {
+		dev->vblank[i].dev = dev;
+		dev->vblank[i].crtc = i;
 		init_waitqueue_head(&dev->vblank[i].queue);
+		setup_timer(&dev->vblank[i].disable_timer, vblank_disable_fn,
+			    (unsigned long)&dev->vblank[i]);
+	}
 
 	DRM_INFO("Supports vblank timestamp caching Rev 2 (21.10.2013).\n");
 
@@ -261,42 +253,42 @@ static void drm_irq_vgaarb_nokms(void *cookie, bool state)
 }
 
 /**
- * Install IRQ handler.
- *
- * \param dev DRM device.
+ * drm_irq_install - install IRQ handler
+ * @dev: DRM device
+ * @irq: IRQ number to install the handler for
  *
  * Initializes the IRQ related data. Installs the handler, calling the driver
- * \c irq_preinstall() and \c irq_postinstall() functions
- * before and after the installation.
+ * irq_preinstall() and irq_postinstall() functions before and after the
+ * installation.
+ *
+ * This is the simplified helper interface provided for drivers with no special
+ * needs. Drivers which need to install interrupt handlers for multiple
+ * interrupts must instead set drm_device->irq_enabled to signal the DRM core
+ * that vblank interrupts are available.
+ *
+ * Returns:
+ * Zero on success or a negative error code on failure.
  */
-int drm_irq_install(struct drm_device *dev)
+int drm_irq_install(struct drm_device *dev, int irq)
 {
 	int ret;
 	unsigned long sh_flags = 0;
-	char *irqname;
 
 	if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
 		return -EINVAL;
 
-	if (drm_dev_to_irq(dev) == 0)
+	if (irq == 0)
 		return -EINVAL;
 
-	mutex_lock(&dev->struct_mutex);
-
 	/* Driver must have been initialized */
-	if (!dev->dev_private) {
-		mutex_unlock(&dev->struct_mutex);
+	if (!dev->dev_private)
 		return -EINVAL;
-	}
 
-	if (dev->irq_enabled) {
-		mutex_unlock(&dev->struct_mutex);
+	if (dev->irq_enabled)
 		return -EBUSY;
-	}
 	dev->irq_enabled = true;
-	mutex_unlock(&dev->struct_mutex);
 
-	DRM_DEBUG("irq=%d\n", drm_dev_to_irq(dev));
+	DRM_DEBUG("irq=%d\n", irq);
 
 	/* Before installing handler */
 	if (dev->driver->irq_preinstall)
@@ -306,18 +298,11 @@ int drm_irq_install(struct drm_device *dev)
 	if (drm_core_check_feature(dev, DRIVER_IRQ_SHARED))
 		sh_flags = IRQF_SHARED;
 
-	if (dev->devname)
-		irqname = dev->devname;
-	else
-		irqname = dev->driver->name;
-
-	ret = request_irq(drm_dev_to_irq(dev), dev->driver->irq_handler,
-			  sh_flags, irqname, dev);
+	ret = request_irq(irq, dev->driver->irq_handler,
+			  sh_flags, dev->driver->name, dev);
 
 	if (ret < 0) {
-		mutex_lock(&dev->struct_mutex);
 		dev->irq_enabled = false;
-		mutex_unlock(&dev->struct_mutex);
 		return ret;
 	}
 
@@ -329,12 +314,12 @@ int drm_irq_install(struct drm_device *dev)
 		ret = dev->driver->irq_postinstall(dev);
 
 	if (ret < 0) {
-		mutex_lock(&dev->struct_mutex);
 		dev->irq_enabled = false;
-		mutex_unlock(&dev->struct_mutex);
 		if (!drm_core_check_feature(dev, DRIVER_MODESET))
 			vga_client_register(dev->pdev, NULL, NULL, NULL);
-		free_irq(drm_dev_to_irq(dev), dev);
+		free_irq(irq, dev);
+	} else {
+		dev->irq = irq;
 	}
 
 	return ret;
@@ -342,11 +327,20 @@ int drm_irq_install(struct drm_device *dev)
 EXPORT_SYMBOL(drm_irq_install);
 
 /**
- * Uninstall the IRQ handler.
+ * drm_irq_uninstall - uninstall the IRQ handler
+ * @dev: DRM device
+ *
+ * Calls the driver's irq_uninstall() function and unregisters the IRQ handler.
+ * This should only be called by drivers which used drm_irq_install() to set up
+ * their interrupt handler. Other drivers must only reset
+ * drm_device->irq_enabled to false.
  *
- * \param dev DRM device.
+ * Note that for kernel modesetting drivers it is a bug if this function fails.
+ * The sanity checks are only to catch buggy user modesetting drivers which call
+ * the same function through an ioctl.
  *
- * Calls the driver's \c irq_uninstall() function, and stops the irq.
+ * Returns:
+ * Zero on success or a negative error code on failure.
  */
 int drm_irq_uninstall(struct drm_device *dev)
 {
@@ -357,10 +351,8 @@ int drm_irq_uninstall(struct drm_device *dev)
 	if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
 		return -EINVAL;
 
-	mutex_lock(&dev->struct_mutex);
 	irq_enabled = dev->irq_enabled;
 	dev->irq_enabled = false;
-	mutex_unlock(&dev->struct_mutex);
 
 	/*
 	 * Wake up any waiters so they don't hang.
@@ -379,7 +371,7 @@ int drm_irq_uninstall(struct drm_device *dev)
 	if (!irq_enabled)
 		return -EINVAL;
 
-	DRM_DEBUG("irq=%d\n", drm_dev_to_irq(dev));
+	DRM_DEBUG("irq=%d\n", dev->irq);
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		vga_client_register(dev->pdev, NULL, NULL, NULL);
@@ -387,13 +379,13 @@ int drm_irq_uninstall(struct drm_device *dev)
 	if (dev->driver->irq_uninstall)
 		dev->driver->irq_uninstall(dev);
 
-	free_irq(drm_dev_to_irq(dev), dev);
+	free_irq(dev->irq, dev);
 
 	return 0;
 }
 EXPORT_SYMBOL(drm_irq_uninstall);
 
-/**
+/*
  * IRQ control ioctl.
  *
  * \param inode device inode.
@@ -408,43 +400,52 @@ int drm_control(struct drm_device *dev, void *data,
 		struct drm_file *file_priv)
 {
 	struct drm_control *ctl = data;
+	int ret = 0, irq;
 
 	/* if we haven't irq we fallback for compatibility reasons -
 	 * this used to be a separate function in drm_dma.h
 	 */
 
+	if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
+		return 0;
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return 0;
+	/* UMS was only ever support on pci devices. */
+	if (WARN_ON(!dev->pdev))
+		return -EINVAL;
 
 	switch (ctl->func) {
 	case DRM_INST_HANDLER:
-		if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
-			return 0;
-		if (drm_core_check_feature(dev, DRIVER_MODESET))
-			return 0;
+		irq = dev->pdev->irq;
+
 		if (dev->if_version < DRM_IF_VERSION(1, 2) &&
-		    ctl->irq != drm_dev_to_irq(dev))
+		    ctl->irq != irq)
 			return -EINVAL;
-		return drm_irq_install(dev);
+		mutex_lock(&dev->struct_mutex);
+		ret = drm_irq_install(dev, irq);
+		mutex_unlock(&dev->struct_mutex);
+
+		return ret;
 	case DRM_UNINST_HANDLER:
-		if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
-			return 0;
-		if (drm_core_check_feature(dev, DRIVER_MODESET))
-			return 0;
-		return drm_irq_uninstall(dev);
+		mutex_lock(&dev->struct_mutex);
+		ret = drm_irq_uninstall(dev);
+		mutex_unlock(&dev->struct_mutex);
+
+		return ret;
 	default:
 		return -EINVAL;
 	}
 }
 
 /**
- * drm_calc_timestamping_constants - Calculate vblank timestamp constants
- *
- * @crtc drm_crtc whose timestamp constants should be updated.
- * @mode display mode containing the scanout timings
+ * drm_calc_timestamping_constants - calculate vblank timestamp constants
+ * @crtc: drm_crtc whose timestamp constants should be updated.
+ * @mode: display mode containing the scanout timings
  *
  * Calculate and store various constants which are later
  * needed by vblank and swap-completion timestamping, e.g,
  * by drm_calc_vbltimestamp_from_scanoutpos(). They are
- * derived from crtc's true scanout timing, so they take
+ * derived from CRTC's true scanout timing, so they take
  * things like panel scaling or other adjustments into account.
  */
 void drm_calc_timestamping_constants(struct drm_crtc *crtc,
@@ -489,11 +490,22 @@ void drm_calc_timestamping_constants(struct drm_crtc *crtc,
 EXPORT_SYMBOL(drm_calc_timestamping_constants);
 
 /**
- * drm_calc_vbltimestamp_from_scanoutpos - helper routine for kms
- * drivers. Implements calculation of exact vblank timestamps from
- * given drm_display_mode timings and current video scanout position
- * of a crtc. This can be called from within get_vblank_timestamp()
- * implementation of a kms driver to implement the actual timestamping.
+ * drm_calc_vbltimestamp_from_scanoutpos - precise vblank timestamp helper
+ * @dev: DRM device
+ * @crtc: Which CRTC's vblank timestamp to retrieve
+ * @max_error: Desired maximum allowable error in timestamps (nanosecs)
+ *             On return contains true maximum error of timestamp
+ * @vblank_time: Pointer to struct timeval which should receive the timestamp
+ * @flags: Flags to pass to driver:
+ *         0 = Default,
+ *         DRM_CALLED_FROM_VBLIRQ = If function is called from vbl IRQ handler
+ * @refcrtc: CRTC which defines scanout timing
+ * @mode: mode which defines the scanout timings
+ *
+ * Implements calculation of exact vblank timestamps from given drm_display_mode
+ * timings and current video scanout position of a CRTC. This can be called from
+ * within get_vblank_timestamp() implementation of a kms driver to implement the
+ * actual timestamping.
  *
  * Should return timestamps conforming to the OML_sync_control OpenML
  * extension specification. The timestamp corresponds to the end of
@@ -508,21 +520,11 @@ EXPORT_SYMBOL(drm_calc_timestamping_constants);
  * returns as no operation if a doublescan or interlaced video mode is
  * active. Higher level code is expected to handle this.
  *
- * @dev: DRM device.
- * @crtc: Which crtc's vblank timestamp to retrieve.
- * @max_error: Desired maximum allowable error in timestamps (nanosecs).
- *             On return contains true maximum error of timestamp.
- * @vblank_time: Pointer to struct timeval which should receive the timestamp.
- * @flags: Flags to pass to driver:
- *         0 = Default.
- *         DRM_CALLED_FROM_VBLIRQ = If function is called from vbl irq handler.
- * @refcrtc: drm_crtc* of crtc which defines scanout timing.
- * @mode: mode which defines the scanout timings
- *
- * Returns negative value on error, failure or if not supported in current
+ * Returns:
+ * Negative value on error, failure or if not supported in current
  * video mode:
  *
- * -EINVAL   - Invalid crtc.
+ * -EINVAL   - Invalid CRTC.
  * -EAGAIN   - Temporary unavailable, e.g., called before initial modeset.
  * -ENOTSUPP - Function not supported in current display mode.
  * -EIO      - Failed, e.g., due to failed scanout position query.
@@ -671,23 +673,23 @@ static struct timeval get_drm_timestamp(void)
 
 /**
  * drm_get_last_vbltimestamp - retrieve raw timestamp for the most recent
- * vblank interval.
- *
+ * 			       vblank interval
  * @dev: DRM device
- * @crtc: which crtc's vblank timestamp to retrieve
+ * @crtc: which CRTC's vblank timestamp to retrieve
  * @tvblank: Pointer to target struct timeval which should receive the timestamp
  * @flags: Flags to pass to driver:
- *         0 = Default.
- *         DRM_CALLED_FROM_VBLIRQ = If function is called from vbl irq handler.
+ *         0 = Default,
+ *         DRM_CALLED_FROM_VBLIRQ = If function is called from vbl IRQ handler
  *
  * Fetches the system timestamp corresponding to the time of the most recent
- * vblank interval on specified crtc. May call into kms-driver to
+ * vblank interval on specified CRTC. May call into kms-driver to
  * compute the timestamp with a high-precision GPU specific method.
  *
  * Returns zero if timestamp originates from uncorrected do_gettimeofday()
  * call, i.e., it isn't very precisely locked to the true vblank.
  *
- * Returns non-zero if timestamp is considered to be very precise.
+ * Returns:
+ * Non-zero if timestamp is considered to be very precise, zero otherwise.
  */
 u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
 			      struct timeval *tvblank, unsigned flags)
@@ -722,6 +724,9 @@ EXPORT_SYMBOL(drm_get_last_vbltimestamp);
  * Fetches the "cooked" vblank count value that represents the number of
  * vblank events since the system was booted, including lost events due to
  * modesetting activity.
+ *
+ * Returns:
+ * The software vblank counter.
  */
 u32 drm_vblank_count(struct drm_device *dev, int crtc)
 {
@@ -740,8 +745,7 @@ EXPORT_SYMBOL(drm_vblank_count);
  * Fetches the "cooked" vblank count value that represents the number of
  * vblank events since the system was booted, including lost events due to
  * modesetting activity. Returns corresponding system timestamp of the time
- * of the vblank interval that corresponds to the current value vblank counter
- * value.
+ * of the vblank interval that corresponds to the current vblank counter value.
  */
 u32 drm_vblank_count_and_time(struct drm_device *dev, int crtc,
 			      struct timeval *vblanktime)
@@ -870,6 +874,42 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 }
 
 /**
+ * drm_vblank_enable - enable the vblank interrupt on a CRTC
+ * @dev: DRM device
+ * @crtc: CRTC in question
+ */
+static int drm_vblank_enable(struct drm_device *dev, int crtc)
+{
+	int ret = 0;
+
+	assert_spin_locked(&dev->vbl_lock);
+
+	spin_lock(&dev->vblank_time_lock);
+
+	if (!dev->vblank[crtc].enabled) {
+		/*
+		 * Enable vblank irqs under vblank_time_lock protection.
+		 * All vblank count & timestamp updates are held off
+		 * until we are done reinitializing master counter and
+		 * timestamps. Filtercode in drm_handle_vblank() will
+		 * prevent double-accounting of same vblank interval.
+		 */
+		ret = dev->driver->enable_vblank(dev, crtc);
+		DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n", crtc, ret);
+		if (ret)
+			atomic_dec(&dev->vblank[crtc].refcount);
+		else {
+			dev->vblank[crtc].enabled = true;
+			drm_update_vblank_count(dev, crtc);
+		}
+	}
+
+	spin_unlock(&dev->vblank_time_lock);
+
+	return ret;
+}
+
+/**
  * drm_vblank_get - get a reference count on vblank events
  * @dev: DRM device
  * @crtc: which CRTC to own
@@ -877,36 +917,20 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
  * Acquire a reference count on vblank events to avoid having them disabled
  * while in use.
  *
- * RETURNS
+ * This is the legacy version of drm_crtc_vblank_get().
+ *
+ * Returns:
  * Zero on success, nonzero on failure.
  */
 int drm_vblank_get(struct drm_device *dev, int crtc)
 {
-	unsigned long irqflags, irqflags2;
+	unsigned long irqflags;
 	int ret = 0;
 
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
 	/* Going from 0->1 means we have to enable interrupts again */
 	if (atomic_add_return(1, &dev->vblank[crtc].refcount) == 1) {
-		spin_lock_irqsave(&dev->vblank_time_lock, irqflags2);
-		if (!dev->vblank[crtc].enabled) {
-			/* Enable vblank irqs under vblank_time_lock protection.
-			 * All vblank count & timestamp updates are held off
-			 * until we are done reinitializing master counter and
-			 * timestamps. Filtercode in drm_handle_vblank() will
-			 * prevent double-accounting of same vblank interval.
-			 */
-			ret = dev->driver->enable_vblank(dev, crtc);
-			DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n",
-				  crtc, ret);
-			if (ret)
-				atomic_dec(&dev->vblank[crtc].refcount);
-			else {
-				dev->vblank[crtc].enabled = true;
-				drm_update_vblank_count(dev, crtc);
-			}
-		}
-		spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags2);
+		ret = drm_vblank_enable(dev, crtc);
 	} else {
 		if (!dev->vblank[crtc].enabled) {
 			atomic_dec(&dev->vblank[crtc].refcount);
@@ -920,12 +944,32 @@ int drm_vblank_get(struct drm_device *dev, int crtc)
 EXPORT_SYMBOL(drm_vblank_get);
 
 /**
+ * drm_crtc_vblank_get - get a reference count on vblank events
+ * @crtc: which CRTC to own
+ *
+ * Acquire a reference count on vblank events to avoid having them disabled
+ * while in use.
+ *
+ * This is the native kms version of drm_vblank_off().
+ *
+ * Returns:
+ * Zero on success, nonzero on failure.
+ */
+int drm_crtc_vblank_get(struct drm_crtc *crtc)
+{
+	return drm_vblank_get(crtc->dev, drm_crtc_index(crtc));
+}
+EXPORT_SYMBOL(drm_crtc_vblank_get);
+
+/**
  * drm_vblank_put - give up ownership of vblank events
  * @dev: DRM device
  * @crtc: which counter to give up
  *
  * Release ownership of a given vblank counter, turning off interrupts
  * if possible. Disable interrupts after drm_vblank_offdelay milliseconds.
+ *
+ * This is the legacy version of drm_crtc_vblank_put().
  */
 void drm_vblank_put(struct drm_device *dev, int crtc)
 {
@@ -934,17 +978,39 @@ void drm_vblank_put(struct drm_device *dev, int crtc)
 	/* Last user schedules interrupt disable */
 	if (atomic_dec_and_test(&dev->vblank[crtc].refcount) &&
 	    (drm_vblank_offdelay > 0))
-		mod_timer(&dev->vblank_disable_timer,
+		mod_timer(&dev->vblank[crtc].disable_timer,
 			  jiffies + ((drm_vblank_offdelay * HZ)/1000));
 }
 EXPORT_SYMBOL(drm_vblank_put);
 
 /**
+ * drm_crtc_vblank_put - give up ownership of vblank events
+ * @crtc: which counter to give up
+ *
+ * Release ownership of a given vblank counter, turning off interrupts
+ * if possible. Disable interrupts after drm_vblank_offdelay milliseconds.
+ *
+ * This is the native kms version of drm_vblank_put().
+ */
+void drm_crtc_vblank_put(struct drm_crtc *crtc)
+{
+	drm_vblank_put(crtc->dev, drm_crtc_index(crtc));
+}
+EXPORT_SYMBOL(drm_crtc_vblank_put);
+
+/**
  * drm_vblank_off - disable vblank events on a CRTC
  * @dev: DRM device
  * @crtc: CRTC in question
  *
- * Caller must hold event lock.
+ * Drivers can use this function to shut down the vblank interrupt handling when
+ * disabling a crtc. This function ensures that the latest vblank frame count is
+ * stored so that drm_vblank_on() can restore it again.
+ *
+ * Drivers must use this function when the hardware vblank counter can get
+ * reset, e.g. when suspending.
+ *
+ * This is the legacy version of drm_crtc_vblank_off().
  */
 void drm_vblank_off(struct drm_device *dev, int crtc)
 {
@@ -978,12 +1044,87 @@ void drm_vblank_off(struct drm_device *dev, int crtc)
 EXPORT_SYMBOL(drm_vblank_off);
 
 /**
+ * drm_crtc_vblank_off - disable vblank events on a CRTC
+ * @crtc: CRTC in question
+ *
+ * Drivers can use this function to shut down the vblank interrupt handling when
+ * disabling a crtc. This function ensures that the latest vblank frame count is
+ * stored so that drm_vblank_on can restore it again.
+ *
+ * Drivers must use this function when the hardware vblank counter can get
+ * reset, e.g. when suspending.
+ *
+ * This is the native kms version of drm_vblank_off().
+ */
+void drm_crtc_vblank_off(struct drm_crtc *crtc)
+{
+	drm_vblank_off(crtc->dev, drm_crtc_index(crtc));
+}
+EXPORT_SYMBOL(drm_crtc_vblank_off);
+
+/**
+ * drm_vblank_on - enable vblank events on a CRTC
+ * @dev: DRM device
+ * @crtc: CRTC in question
+ *
+ * This functions restores the vblank interrupt state captured with
+ * drm_vblank_off() again. Note that calls to drm_vblank_on() and
+ * drm_vblank_off() can be unbalanced and so can also be unconditionaly called
+ * in driver load code to reflect the current hardware state of the crtc.
+ *
+ * This is the legacy version of drm_crtc_vblank_on().
+ */
+void drm_vblank_on(struct drm_device *dev, int crtc)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&dev->vbl_lock, irqflags);
+	/* re-enable interrupts if there's are users left */
+	if (atomic_read(&dev->vblank[crtc].refcount) != 0)
+		WARN_ON(drm_vblank_enable(dev, crtc));
+	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+}
+EXPORT_SYMBOL(drm_vblank_on);
+
+/**
+ * drm_crtc_vblank_on - enable vblank events on a CRTC
+ * @crtc: CRTC in question
+ *
+ * This functions restores the vblank interrupt state captured with
+ * drm_vblank_off() again. Note that calls to drm_vblank_on() and
+ * drm_vblank_off() can be unbalanced and so can also be unconditionaly called
+ * in driver load code to reflect the current hardware state of the crtc.
+ *
+ * This is the native kms version of drm_vblank_on().
+ */
+void drm_crtc_vblank_on(struct drm_crtc *crtc)
+{
+	drm_vblank_on(crtc->dev, drm_crtc_index(crtc));
+}
+EXPORT_SYMBOL(drm_crtc_vblank_on);
+
+/**
  * drm_vblank_pre_modeset - account for vblanks across mode sets
  * @dev: DRM device
  * @crtc: CRTC in question
  *
  * Account for vblank events across mode setting events, which will likely
  * reset the hardware frame counter.
+ *
+ * This is done by grabbing a temporary vblank reference to ensure that the
+ * vblank interrupt keeps running across the modeset sequence. With this the
+ * software-side vblank frame counting will ensure that there are no jumps or
+ * discontinuities.
+ *
+ * Unfortunately this approach is racy and also doesn't work when the vblank
+ * interrupt stops running, e.g. across system suspend resume. It is therefore
+ * highly recommended that drivers use the newer drm_vblank_off() and
+ * drm_vblank_on() instead. drm_vblank_pre_modeset() only works correctly when
+ * using "cooked" software vblank frame counters and not relying on any hardware
+ * counters.
+ *
+ * Drivers must call drm_vblank_post_modeset() when re-enabling the same crtc
+ * again.
  */
 void drm_vblank_pre_modeset(struct drm_device *dev, int crtc)
 {
@@ -1005,6 +1146,14 @@ void drm_vblank_pre_modeset(struct drm_device *dev, int crtc)
 }
 EXPORT_SYMBOL(drm_vblank_pre_modeset);
 
+/**
+ * drm_vblank_post_modeset - undo drm_vblank_pre_modeset changes
+ * @dev: DRM device
+ * @crtc: CRTC in question
+ *
+ * This function again drops the temporary vblank reference acquired in
+ * drm_vblank_pre_modeset.
+ */
 void drm_vblank_post_modeset(struct drm_device *dev, int crtc)
 {
 	unsigned long irqflags;
@@ -1026,7 +1175,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, int crtc)
 }
 EXPORT_SYMBOL(drm_vblank_post_modeset);
 
-/**
+/*
  * drm_modeset_ctl - handle vblank event counter changes across mode switch
  * @DRM_IOCTL_ARGS: standard ioctl arguments
  *
@@ -1139,7 +1288,7 @@ err_put:
 	return ret;
 }
 
-/**
+/*
  * Wait for VBLANK.
  *
  * \param inode device inode.
@@ -1150,7 +1299,7 @@ err_put:
  *
  * This function enables the vblank interrupt on the pipe requested, then
  * sleeps waiting for the requested sequence number to occur, and drops
- * the vblank interrupt refcount afterwards. (vblank irq disable follows that
+ * the vblank interrupt refcount afterwards. (vblank IRQ disable follows that
  * after a timeout with no further vblank waits scheduled).
  */
 int drm_wait_vblank(struct drm_device *dev, void *data,
@@ -1160,9 +1309,8 @@ int drm_wait_vblank(struct drm_device *dev, void *data,
 	int ret;
 	unsigned int flags, seq, crtc, high_crtc;
 
-	if (drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
-		if ((!drm_dev_to_irq(dev)) || (!dev->irq_enabled))
-			return -EINVAL;
+	if (!dev->irq_enabled)
+		return -EINVAL;
 
 	if (vblwait->request.type & _DRM_VBLANK_SIGNAL)
 		return -EINVAL;
@@ -1222,6 +1370,7 @@ int drm_wait_vblank(struct drm_device *dev, void *data,
 	DRM_WAIT_ON(ret, dev->vblank[crtc].queue, 3 * HZ,
 		    (((drm_vblank_count(dev, crtc) -
 		       vblwait->request.sequence) <= (1 << 23)) ||
+		     !dev->vblank[crtc].enabled ||
 		     !dev->irq_enabled));
 
 	if (ret != -EINTR) {
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index 09821f46d76..e633df2f68d 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -282,6 +282,14 @@ static int mipi_dsi_drv_remove(struct device *dev)
 	return drv->remove(dsi);
 }
 
+static void mipi_dsi_drv_shutdown(struct device *dev)
+{
+	struct mipi_dsi_driver *drv = to_mipi_dsi_driver(dev->driver);
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev);
+
+	drv->shutdown(dsi);
+}
+
 /**
  * mipi_dsi_driver_register - register a driver for DSI devices
  * @drv: DSI driver structure
@@ -293,6 +301,8 @@ int mipi_dsi_driver_register(struct mipi_dsi_driver *drv)
 		drv->driver.probe = mipi_dsi_drv_probe;
 	if (drv->remove)
 		drv->driver.remove = mipi_dsi_drv_remove;
+	if (drv->shutdown)
+		drv->driver.shutdown = mipi_dsi_drv_shutdown;
 
 	return driver_register(&drv->driver);
 }
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 8b410576fce..bedf1894e17 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1013,6 +1013,7 @@ EXPORT_SYMBOL(drm_mode_sort);
 /**
  * drm_mode_connector_list_update - update the mode list for the connector
  * @connector: the connector to update
+ * @merge_type_bits: whether to merge or overright type bits.
  *
  * This moves the modes from the @connector probed_modes list
  * to the actual mode list. It compares the probed mode against the current
@@ -1021,7 +1022,8 @@ EXPORT_SYMBOL(drm_mode_sort);
  * This is just a helper functions doesn't validate any modes itself and also
  * doesn't prune any invalid modes. Callers need to do that themselves.
  */
-void drm_mode_connector_list_update(struct drm_connector *connector)
+void drm_mode_connector_list_update(struct drm_connector *connector,
+				    bool merge_type_bits)
 {
 	struct drm_display_mode *mode;
 	struct drm_display_mode *pmode, *pt;
@@ -1039,7 +1041,10 @@ void drm_mode_connector_list_update(struct drm_connector *connector)
 				/* if equal delete the probed mode */
 				mode->status = pmode->status;
 				/* Merge type bits together */
-				mode->type |= pmode->type;
+				if (merge_type_bits)
+					mode->type |= pmode->type;
+				else
+					mode->type = pmode->type;
 				list_del(&pmode->head);
 				drm_mode_destroy(connector->dev, pmode);
 				break;
diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
new file mode 100644
index 00000000000..0dc57d5ecd1
--- /dev/null
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -0,0 +1,248 @@
+/*
+ * Copyright (C) 2014 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_modeset_lock.h>
+
+/**
+ * DOC: kms locking
+ *
+ * As KMS moves toward more fine grained locking, and atomic ioctl where
+ * userspace can indirectly control locking order, it becomes necessary
+ * to use ww_mutex and acquire-contexts to avoid deadlocks.  But because
+ * the locking is more distributed around the driver code, we want a bit
+ * of extra utility/tracking out of our acquire-ctx.  This is provided
+ * by drm_modeset_lock / drm_modeset_acquire_ctx.
+ *
+ * For basic principles of ww_mutex, see: Documentation/ww-mutex-design.txt
+ *
+ * The basic usage pattern is to:
+ *
+ *     drm_modeset_acquire_init(&ctx)
+ *   retry:
+ *     foreach (lock in random_ordered_set_of_locks) {
+ *       ret = drm_modeset_lock(lock, &ctx)
+ *       if (ret == -EDEADLK) {
+ *          drm_modeset_backoff(&ctx);
+ *          goto retry;
+ *       }
+ *     }
+ *
+ *     ... do stuff ...
+ *
+ *     drm_modeset_drop_locks(&ctx);
+ *     drm_modeset_acquire_fini(&ctx);
+ */
+
+
+/**
+ * drm_modeset_acquire_init - initialize acquire context
+ * @ctx: the acquire context
+ * @flags: for future
+ */
+void drm_modeset_acquire_init(struct drm_modeset_acquire_ctx *ctx,
+		uint32_t flags)
+{
+	memset(ctx, 0, sizeof(*ctx));
+	ww_acquire_init(&ctx->ww_ctx, &crtc_ww_class);
+	INIT_LIST_HEAD(&ctx->locked);
+}
+EXPORT_SYMBOL(drm_modeset_acquire_init);
+
+/**
+ * drm_modeset_acquire_fini - cleanup acquire context
+ * @ctx: the acquire context
+ */
+void drm_modeset_acquire_fini(struct drm_modeset_acquire_ctx *ctx)
+{
+	ww_acquire_fini(&ctx->ww_ctx);
+}
+EXPORT_SYMBOL(drm_modeset_acquire_fini);
+
+/**
+ * drm_modeset_drop_locks - drop all locks
+ * @ctx: the acquire context
+ *
+ * Drop all locks currently held against this acquire context.
+ */
+void drm_modeset_drop_locks(struct drm_modeset_acquire_ctx *ctx)
+{
+	WARN_ON(ctx->contended);
+	while (!list_empty(&ctx->locked)) {
+		struct drm_modeset_lock *lock;
+
+		lock = list_first_entry(&ctx->locked,
+				struct drm_modeset_lock, head);
+
+		drm_modeset_unlock(lock);
+	}
+}
+EXPORT_SYMBOL(drm_modeset_drop_locks);
+
+static inline int modeset_lock(struct drm_modeset_lock *lock,
+		struct drm_modeset_acquire_ctx *ctx,
+		bool interruptible, bool slow)
+{
+	int ret;
+
+	WARN_ON(ctx->contended);
+
+	if (interruptible && slow) {
+		ret = ww_mutex_lock_slow_interruptible(&lock->mutex, &ctx->ww_ctx);
+	} else if (interruptible) {
+		ret = ww_mutex_lock_interruptible(&lock->mutex, &ctx->ww_ctx);
+	} else if (slow) {
+		ww_mutex_lock_slow(&lock->mutex, &ctx->ww_ctx);
+		ret = 0;
+	} else {
+		ret = ww_mutex_lock(&lock->mutex, &ctx->ww_ctx);
+	}
+	if (!ret) {
+		WARN_ON(!list_empty(&lock->head));
+		list_add(&lock->head, &ctx->locked);
+	} else if (ret == -EALREADY) {
+		/* we already hold the lock.. this is fine.  For atomic
+		 * we will need to be able to drm_modeset_lock() things
+		 * without having to keep track of what is already locked
+		 * or not.
+		 */
+		ret = 0;
+	} else if (ret == -EDEADLK) {
+		ctx->contended = lock;
+	}
+
+	return ret;
+}
+
+static int modeset_backoff(struct drm_modeset_acquire_ctx *ctx,
+		bool interruptible)
+{
+	struct drm_modeset_lock *contended = ctx->contended;
+
+	ctx->contended = NULL;
+
+	if (WARN_ON(!contended))
+		return 0;
+
+	drm_modeset_drop_locks(ctx);
+
+	return modeset_lock(contended, ctx, interruptible, true);
+}
+
+/**
+ * drm_modeset_backoff - deadlock avoidance backoff
+ * @ctx: the acquire context
+ *
+ * If deadlock is detected (ie. drm_modeset_lock() returns -EDEADLK),
+ * you must call this function to drop all currently held locks and
+ * block until the contended lock becomes available.
+ */
+void drm_modeset_backoff(struct drm_modeset_acquire_ctx *ctx)
+{
+	modeset_backoff(ctx, false);
+}
+EXPORT_SYMBOL(drm_modeset_backoff);
+
+/**
+ * drm_modeset_backoff_interruptible - deadlock avoidance backoff
+ * @ctx: the acquire context
+ *
+ * Interruptible version of drm_modeset_backoff()
+ */
+int drm_modeset_backoff_interruptible(struct drm_modeset_acquire_ctx *ctx)
+{
+	return modeset_backoff(ctx, true);
+}
+EXPORT_SYMBOL(drm_modeset_backoff_interruptible);
+
+/**
+ * drm_modeset_lock - take modeset lock
+ * @lock: lock to take
+ * @ctx: acquire ctx
+ *
+ * If ctx is not NULL, then its ww acquire context is used and the
+ * lock will be tracked by the context and can be released by calling
+ * drm_modeset_drop_locks().  If -EDEADLK is returned, this means a
+ * deadlock scenario has been detected and it is an error to attempt
+ * to take any more locks without first calling drm_modeset_backoff().
+ */
+int drm_modeset_lock(struct drm_modeset_lock *lock,
+		struct drm_modeset_acquire_ctx *ctx)
+{
+	if (ctx)
+		return modeset_lock(lock, ctx, false, false);
+
+	ww_mutex_lock(&lock->mutex, NULL);
+	return 0;
+}
+EXPORT_SYMBOL(drm_modeset_lock);
+
+/**
+ * drm_modeset_lock_interruptible - take modeset lock
+ * @lock: lock to take
+ * @ctx: acquire ctx
+ *
+ * Interruptible version of drm_modeset_lock()
+ */
+int drm_modeset_lock_interruptible(struct drm_modeset_lock *lock,
+		struct drm_modeset_acquire_ctx *ctx)
+{
+	if (ctx)
+		return modeset_lock(lock, ctx, true, false);
+
+	return ww_mutex_lock_interruptible(&lock->mutex, NULL);
+}
+EXPORT_SYMBOL(drm_modeset_lock_interruptible);
+
+/**
+ * drm_modeset_unlock - drop modeset lock
+ * @lock: lock to release
+ */
+void drm_modeset_unlock(struct drm_modeset_lock *lock)
+{
+	list_del_init(&lock->head);
+	ww_mutex_unlock(&lock->mutex);
+}
+EXPORT_SYMBOL(drm_modeset_unlock);
+
+/* Temporary.. until we have sufficiently fine grained locking, there
+ * are a couple scenarios where it is convenient to grab all crtc locks.
+ * It is planned to remove this:
+ */
+int drm_modeset_lock_all_crtcs(struct drm_device *dev,
+		struct drm_modeset_acquire_ctx *ctx)
+{
+	struct drm_mode_config *config = &dev->mode_config;
+	struct drm_crtc *crtc;
+	int ret = 0;
+
+	list_for_each_entry(crtc, &config->crtc_list, head) {
+		ret = drm_modeset_lock(&crtc->mutex, ctx);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_modeset_lock_all_crtcs);
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 9c696a5ad74..020cfd93485 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -1,17 +1,3 @@
-/* drm_pci.h -- PCI DMA memory management wrappers for DRM -*- linux-c -*- */
-/**
- * \file drm_pci.c
- * \brief Functions and ioctls to manage PCI memory
- *
- * \warning These interfaces aren't stable yet.
- *
- * \todo Implement the remaining ioctl's for the PCI pools.
- * \todo The wrappers here are so thin that they would be better off inlined..
- *
- * \author José Fonseca <jrfonseca@tungstengraphics.com>
- * \author Leif Delgass <ldelgass@retinalburn.net>
- */
-
 /*
  * Copyright 2003 José Fonseca.
  * Copyright 2003 Leif Delgass.
@@ -42,12 +28,14 @@
 #include <linux/export.h>
 #include <drm/drmP.h>
 
-/**********************************************************************/
-/** \name PCI memory */
-/*@{*/
-
 /**
- * \brief Allocate a PCI consistent memory block, for DMA.
+ * drm_pci_alloc - Allocate a PCI consistent memory block, for DMA.
+ * @dev: DRM device
+ * @size: size of block to allocate
+ * @align: alignment of block
+ *
+ * Return: A handle to the allocated memory block on success or NULL on
+ * failure.
  */
 drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t align)
 {
@@ -88,8 +76,8 @@ drm_dma_handle_t *drm_pci_alloc(struct drm_device * dev, size_t size, size_t ali
 
 EXPORT_SYMBOL(drm_pci_alloc);
 
-/**
- * \brief Free a PCI consistent memory block without freeing its descriptor.
+/*
+ * Free a PCI consistent memory block without freeing its descriptor.
  *
  * This function is for internal use in the Linux-specific DRM core code.
  */
@@ -111,7 +99,9 @@ void __drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 }
 
 /**
- * \brief Free a PCI consistent memory block
+ * drm_pci_free - Free a PCI consistent memory block
+ * @dev: DRM device
+ * @dmah: handle to memory block
  */
 void drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 {
@@ -137,21 +127,9 @@ static int drm_get_pci_domain(struct drm_device *dev)
 	return pci_domain_nr(dev->pdev->bus);
 }
 
-static int drm_pci_get_irq(struct drm_device *dev)
-{
-	return dev->pdev->irq;
-}
-
-static const char *drm_pci_get_name(struct drm_device *dev)
-{
-	struct pci_driver *pdriver = dev->driver->kdriver.pci;
-	return pdriver->name;
-}
-
 static int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master)
 {
 	int len, ret;
-	struct pci_driver *pdriver = dev->driver->kdriver.pci;
 	master->unique_len = 40;
 	master->unique_size = master->unique_len;
 	master->unique = kmalloc(master->unique_size, GFP_KERNEL);
@@ -173,29 +151,16 @@ static int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master)
 	} else
 		master->unique_len = len;
 
-	dev->devname =
-		kmalloc(strlen(pdriver->name) +
-			master->unique_len + 2, GFP_KERNEL);
-
-	if (dev->devname == NULL) {
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	sprintf(dev->devname, "%s@%s", pdriver->name,
-		master->unique);
-
 	return 0;
 err:
 	return ret;
 }
 
-static int drm_pci_set_unique(struct drm_device *dev,
-			      struct drm_master *master,
-			      struct drm_unique *u)
+int drm_pci_set_unique(struct drm_device *dev,
+		       struct drm_master *master,
+		       struct drm_unique *u)
 {
 	int domain, bus, slot, func, ret;
-	const char *bus_name;
 
 	master->unique_len = u->unique_len;
 	master->unique_size = u->unique_len + 1;
@@ -212,17 +177,6 @@ static int drm_pci_set_unique(struct drm_device *dev,
 
 	master->unique[master->unique_len] = '\0';
 
-	bus_name = dev->driver->bus->get_name(dev);
-	dev->devname = kmalloc(strlen(bus_name) +
-			       strlen(master->unique) + 2, GFP_KERNEL);
-	if (!dev->devname) {
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	sprintf(dev->devname, "%s@%s", bus_name,
-		master->unique);
-
 	/* Return error if the busid submitted doesn't match the device's actual
 	 * busid.
 	 */
@@ -247,7 +201,6 @@ err:
 	return ret;
 }
 
-
 static int drm_pci_irq_by_busid(struct drm_device *dev, struct drm_irq_busid *p)
 {
 	if ((p->busnum >> 8) != drm_get_pci_domain(dev) ||
@@ -262,6 +215,36 @@ static int drm_pci_irq_by_busid(struct drm_device *dev, struct drm_irq_busid *p)
 	return 0;
 }
 
+/**
+ * drm_irq_by_busid - Get interrupt from bus ID
+ * @dev: DRM device
+ * @data: IOCTL parameter pointing to a drm_irq_busid structure
+ * @file_priv: DRM file private.
+ *
+ * Finds the PCI device with the specified bus id and gets its IRQ number.
+ * This IOCTL is deprecated, and will now return EINVAL for any busid not equal
+ * to that of the device that this DRM instance attached to.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int drm_irq_by_busid(struct drm_device *dev, void *data,
+		     struct drm_file *file_priv)
+{
+	struct drm_irq_busid *p = data;
+
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
+	/* UMS was only ever support on PCI devices. */
+	if (WARN_ON(!dev->pdev))
+		return -EINVAL;
+
+	if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
+		return -EINVAL;
+
+	return drm_pci_irq_by_busid(dev, p);
+}
+
 static void drm_pci_agp_init(struct drm_device *dev)
 {
 	if (drm_core_check_feature(dev, DRIVER_USE_AGP)) {
@@ -287,24 +270,20 @@ void drm_pci_agp_destroy(struct drm_device *dev)
 }
 
 static struct drm_bus drm_pci_bus = {
-	.bus_type = DRIVER_BUS_PCI,
-	.get_irq = drm_pci_get_irq,
-	.get_name = drm_pci_get_name,
 	.set_busid = drm_pci_set_busid,
-	.set_unique = drm_pci_set_unique,
-	.irq_by_busid = drm_pci_irq_by_busid,
 };
 
 /**
- * Register.
- *
- * \param pdev - PCI device structure
- * \param ent entry from the PCI ID table with device type flags
- * \return zero on success or a negative number on failure.
+ * drm_get_pci_dev - Register a PCI device with the DRM subsystem
+ * @pdev: PCI device
+ * @ent: entry from the PCI ID table that matches @pdev
+ * @driver: DRM device driver
  *
  * Attempt to gets inter module "drm" information. If we are first
  * then register the character device and inter module information.
  * Try and register, if we fail to register, backout previous work.
+ *
+ * Return: 0 on success or a negative error code on failure.
  */
 int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
 		    struct drm_driver *driver)
@@ -357,15 +336,14 @@ err_free:
 EXPORT_SYMBOL(drm_get_pci_dev);
 
 /**
- * PCI device initialization. Called direct from modules at load time.
- *
- * \return zero on success or a negative number on failure.
+ * drm_pci_init - Register matching PCI devices with the DRM subsystem
+ * @driver: DRM device driver
+ * @pdriver: PCI device driver
  *
- * Initializes a drm_device structures,registering the
- * stubs and initializing the AGP device.
+ * Initializes a drm_device structures, registering the stubs and initializing
+ * the AGP device.
  *
- * Expands the \c DRIVER_PREINIT and \c DRIVER_POST_INIT macros before and
- * after the initialization for driver customization.
+ * Return: 0 on success or a negative error code on failure.
  */
 int drm_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 {
@@ -375,7 +353,6 @@ int drm_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 
 	DRM_DEBUG("\n");
 
-	driver->kdriver.pci = pdriver;
 	driver->bus = &drm_pci_bus;
 
 	if (driver->driver_features & DRIVER_MODESET)
@@ -453,11 +430,31 @@ int drm_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 }
 
 void drm_pci_agp_destroy(struct drm_device *dev) {}
+
+int drm_irq_by_busid(struct drm_device *dev, void *data,
+		     struct drm_file *file_priv)
+{
+	return -EINVAL;
+}
+
+int drm_pci_set_unique(struct drm_device *dev,
+		       struct drm_master *master,
+		       struct drm_unique *u)
+{
+	return -EINVAL;
+}
 #endif
 
 EXPORT_SYMBOL(drm_pci_init);
 
-/*@}*/
+/**
+ * drm_pci_exit - Unregister matching PCI devices from the DRM subsystem
+ * @driver: DRM device driver
+ * @pdriver: PCI device driver
+ *
+ * Unregisters one or more devices matched by a PCI driver from the DRM
+ * subsystem.
+ */
 void drm_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver)
 {
 	struct drm_device *dev, *tmp;
diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c
index d2b1c03b3d7..6d133149cc7 100644
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@@ -25,7 +25,9 @@
 
 #include <linux/list.h>
 #include <drm/drmP.h>
+#include <drm/drm_plane_helper.h>
 #include <drm/drm_rect.h>
+#include <drm/drm_plane_helper.h>
 
 #define SUBPIXEL_MASK 0xffff
 
@@ -36,9 +38,9 @@
  * creating the primary plane.  However drivers that still call
  * drm_plane_init() will use this minimal format list as the default.
  */
-const static uint32_t safe_modeset_formats[] = {
-       DRM_FORMAT_XRGB8888,
-       DRM_FORMAT_ARGB8888,
+static const uint32_t safe_modeset_formats[] = {
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
 };
 
 /*
@@ -54,6 +56,13 @@ static int get_connectors_for_crtc(struct drm_crtc *crtc,
 	struct drm_connector *connector;
 	int count = 0;
 
+	/*
+	 * Note: Once we change the plane hooks to more fine-grained locking we
+	 * need to grab the connection_mutex here to be able to make these
+	 * checks.
+	 */
+	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
 		if (connector->encoder && connector->encoder->crtc == crtc) {
 			if (connector_list != NULL && count < num_connectors)
@@ -66,6 +75,79 @@ static int get_connectors_for_crtc(struct drm_crtc *crtc,
 }
 
 /**
+ * drm_plane_helper_check_update() - Check plane update for validity
+ * @plane: plane object to update
+ * @crtc: owning CRTC of owning plane
+ * @fb: framebuffer to flip onto plane
+ * @src: source coordinates in 16.16 fixed point
+ * @dest: integer destination coordinates
+ * @clip: integer clipping coordinates
+ * @min_scale: minimum @src:@dest scaling factor in 16.16 fixed point
+ * @max_scale: maximum @src:@dest scaling factor in 16.16 fixed point
+ * @can_position: is it legal to position the plane such that it
+ *                doesn't cover the entire crtc?  This will generally
+ *                only be false for primary planes.
+ * @can_update_disabled: can the plane be updated while the crtc
+ *                       is disabled?
+ * @visible: output parameter indicating whether plane is still visible after
+ *           clipping
+ *
+ * Checks that a desired plane update is valid.  Drivers that provide
+ * their own plane handling rather than helper-provided implementations may
+ * still wish to call this function to avoid duplication of error checking
+ * code.
+ *
+ * RETURNS:
+ * Zero if update appears valid, error code on failure
+ */
+int drm_plane_helper_check_update(struct drm_plane *plane,
+				    struct drm_crtc *crtc,
+				    struct drm_framebuffer *fb,
+				    struct drm_rect *src,
+				    struct drm_rect *dest,
+				    const struct drm_rect *clip,
+				    int min_scale,
+				    int max_scale,
+				    bool can_position,
+				    bool can_update_disabled,
+				    bool *visible)
+{
+	int hscale, vscale;
+
+	if (!crtc->enabled && !can_update_disabled) {
+		DRM_DEBUG_KMS("Cannot update plane of a disabled CRTC.\n");
+		return -EINVAL;
+	}
+
+	/* Check scaling */
+	hscale = drm_rect_calc_hscale(src, dest, min_scale, max_scale);
+	vscale = drm_rect_calc_vscale(src, dest, min_scale, max_scale);
+	if (hscale < 0 || vscale < 0) {
+		DRM_DEBUG_KMS("Invalid scaling of plane\n");
+		return -ERANGE;
+	}
+
+	*visible = drm_rect_clip_scaled(src, dest, clip, hscale, vscale);
+	if (!*visible)
+		/*
+		 * Plane isn't visible; some drivers can handle this
+		 * so we just return success here.  Drivers that can't
+		 * (including those that use the primary plane helper's
+		 * update function) will return an error from their
+		 * update_plane handler.
+		 */
+		return 0;
+
+	if (!can_position && !drm_rect_equals(dest, clip)) {
+		DRM_DEBUG_KMS("Plane must cover entire CRTC\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_plane_helper_check_update);
+
+/**
  * drm_primary_helper_update() - Helper for primary plane update
  * @plane: plane object to update
  * @crtc: owning CRTC of owning plane
@@ -113,56 +195,42 @@ int drm_primary_helper_update(struct drm_plane *plane, struct drm_crtc *crtc,
 		.x = src_x >> 16,
 		.y = src_y >> 16,
 	};
+	struct drm_rect src = {
+		.x1 = src_x,
+		.y1 = src_y,
+		.x2 = src_x + src_w,
+		.y2 = src_y + src_h,
+	};
 	struct drm_rect dest = {
 		.x1 = crtc_x,
 		.y1 = crtc_y,
 		.x2 = crtc_x + crtc_w,
 		.y2 = crtc_y + crtc_h,
 	};
-	struct drm_rect clip = {
+	const struct drm_rect clip = {
 		.x2 = crtc->mode.hdisplay,
 		.y2 = crtc->mode.vdisplay,
 	};
 	struct drm_connector **connector_list;
-	struct drm_framebuffer *tmpfb;
 	int num_connectors, ret;
+	bool visible;
 
-	if (!crtc->enabled) {
-		DRM_DEBUG_KMS("Cannot update primary plane of a disabled CRTC.\n");
-		return -EINVAL;
-	}
-
-	/* Disallow subpixel positioning */
-	if ((src_x | src_y | src_w | src_h) & SUBPIXEL_MASK) {
-		DRM_DEBUG_KMS("Primary plane does not support subpixel positioning\n");
-		return -EINVAL;
-	}
-
-	/* Primary planes are locked to their owning CRTC */
-	if (plane->possible_crtcs != drm_crtc_mask(crtc)) {
-		DRM_DEBUG_KMS("Cannot change primary plane CRTC\n");
-		return -EINVAL;
-	}
-
-	/* Disallow scaling */
-	if (crtc_w != src_w || crtc_h != src_h) {
-		DRM_DEBUG_KMS("Can't scale primary plane\n");
-		return -EINVAL;
-	}
-
-	/* Make sure primary plane covers entire CRTC */
-	drm_rect_intersect(&dest, &clip);
-	if (dest.x1 != 0 || dest.y1 != 0 ||
-	    dest.x2 != crtc->mode.hdisplay || dest.y2 != crtc->mode.vdisplay) {
-		DRM_DEBUG_KMS("Primary plane must cover entire CRTC\n");
-		return -EINVAL;
-	}
-
-	/* Framebuffer must be big enough to cover entire plane */
-	ret = drm_crtc_check_viewport(crtc, crtc_x, crtc_y, &crtc->mode, fb);
+	ret = drm_plane_helper_check_update(plane, crtc, fb,
+					    &src, &dest, &clip,
+					    DRM_PLANE_HELPER_NO_SCALING,
+					    DRM_PLANE_HELPER_NO_SCALING,
+					    false, false, &visible);
 	if (ret)
 		return ret;
 
+	if (!visible)
+		/*
+		 * Primary plane isn't visible.  Note that unless a driver
+		 * provides their own disable function, this will just
+		 * wind up returning -EINVAL to userspace.
+		 */
+		return plane->funcs->disable_plane(plane);
+
 	/* Find current connectors for CRTC */
 	num_connectors = get_connectors_for_crtc(crtc, NULL, 0);
 	BUG_ON(num_connectors == 0);
@@ -176,21 +244,14 @@ int drm_primary_helper_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	set.num_connectors = num_connectors;
 
 	/*
-	 * set_config() adjusts crtc->primary->fb; however the DRM setplane
-	 * code that called us expects to handle the framebuffer update and
-	 * reference counting; save and restore the current fb before
-	 * calling it.
-	 *
-	 * N.B., we call set_config() directly here rather than using
+	 * We call set_config() directly here rather than using
 	 * drm_mode_set_config_internal.  We're reprogramming the same
 	 * connectors that were already in use, so we shouldn't need the extra
 	 * cross-CRTC fb refcounting to accomodate stealing connectors.
 	 * drm_mode_setplane() already handles the basic refcounting for the
 	 * framebuffers involved in this operation.
 	 */
-	tmpfb = plane->fb;
 	ret = crtc->funcs->set_config(&set);
-	plane->fb = tmpfb;
 
 	kfree(connector_list);
 	return ret;
@@ -232,7 +293,6 @@ EXPORT_SYMBOL(drm_primary_helper_disable);
  */
 void drm_primary_helper_destroy(struct drm_plane *plane)
 {
-	plane->funcs->disable_plane(plane);
 	drm_plane_cleanup(plane);
 	kfree(plane);
 }
diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c
index 319ff538560..d5b76f148c1 100644
--- a/drivers/gpu/drm/drm_platform.c
+++ b/drivers/gpu/drm/drm_platform.c
@@ -68,16 +68,6 @@ err_free:
 	return ret;
 }
 
-static int drm_platform_get_irq(struct drm_device *dev)
-{
-	return platform_get_irq(dev->platformdev, 0);
-}
-
-static const char *drm_platform_get_name(struct drm_device *dev)
-{
-	return dev->platformdev->name;
-}
-
 static int drm_platform_set_busid(struct drm_device *dev, struct drm_master *master)
 {
 	int len, ret, id;
@@ -106,46 +96,30 @@ static int drm_platform_set_busid(struct drm_device *dev, struct drm_master *mas
 		goto err;
 	}
 
-	dev->devname =
-		kmalloc(strlen(dev->platformdev->name) +
-			master->unique_len + 2, GFP_KERNEL);
-
-	if (dev->devname == NULL) {
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	sprintf(dev->devname, "%s@%s", dev->platformdev->name,
-		master->unique);
 	return 0;
 err:
 	return ret;
 }
 
 static struct drm_bus drm_platform_bus = {
-	.bus_type = DRIVER_BUS_PLATFORM,
-	.get_irq = drm_platform_get_irq,
-	.get_name = drm_platform_get_name,
 	.set_busid = drm_platform_set_busid,
 };
 
 /**
- * Platform device initialization. Called direct from modules.
+ * drm_platform_init - Register a platform device with the DRM subsystem
+ * @driver: DRM device driver
+ * @platform_device: platform device to register
  *
- * \return zero on success or a negative number on failure.
- *
- * Initializes a drm_device structures,registering the
- * stubs
+ * Registers the specified DRM device driver and platform device with the DRM
+ * subsystem, initializing a drm_device structure and calling the driver's
+ * .load() function.
  *
- * Expands the \c DRIVER_PREINIT and \c DRIVER_POST_INIT macros before and
- * after the initialization for driver customization.
+ * Return: 0 on success or a negative error code on failure.
  */
-
 int drm_platform_init(struct drm_driver *driver, struct platform_device *platform_device)
 {
 	DRM_DEBUG("\n");
 
-	driver->kdriver.platform_device = platform_device;
 	driver->bus = &drm_platform_bus;
 	return drm_get_platform_dev(platform_device, driver);
 }
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index e70f54d4a58..d22676b89cb 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -82,26 +82,8 @@ static void drm_mode_validate_flag(struct drm_connector *connector,
 	return;
 }
 
-/**
- * drm_helper_probe_single_connector_modes - get complete set of display modes
- * @connector: connector to probe
- * @maxX: max width for modes
- * @maxY: max height for modes
- *
- * Based on the helper callbacks implemented by @connector try to detect all
- * valid modes.  Modes will first be added to the connector's probed_modes list,
- * then culled (based on validity and the @maxX, @maxY parameters) and put into
- * the normal modes list.
- *
- * Intended to be use as a generic implementation of the ->fill_modes()
- * @connector vfunc for drivers that use the crtc helpers for output mode
- * filtering and detection.
- *
- * Returns:
- * The number of modes found on @connector.
- */
-int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
-					    uint32_t maxX, uint32_t maxY)
+static int drm_helper_probe_single_connector_modes_merge_bits(struct drm_connector *connector,
+							      uint32_t maxX, uint32_t maxY, bool merge_type_bits)
 {
 	struct drm_device *dev = connector->dev;
 	struct drm_display_mode *mode;
@@ -114,7 +96,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id,
-			drm_get_connector_name(connector));
+			connector->name);
 	/* set all modes to the unverified state */
 	list_for_each_entry(mode, &connector->modes, head)
 		mode->status = MODE_UNVERIFIED;
@@ -138,7 +120,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 
 	if (connector->status == connector_status_disconnected) {
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n",
-			connector->base.id, drm_get_connector_name(connector));
+			connector->base.id, connector->name);
 		drm_mode_connector_update_edid_property(connector, NULL);
 		verbose_prune = false;
 		goto prune;
@@ -155,7 +137,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 	if (count == 0)
 		goto prune;
 
-	drm_mode_connector_list_update(connector);
+	drm_mode_connector_list_update(connector, merge_type_bits);
 
 	if (maxX && maxY)
 		drm_mode_validate_size(dev, &connector->modes, maxX, maxY);
@@ -169,7 +151,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 	drm_mode_validate_flag(connector, mode_flags);
 
 	list_for_each_entry(mode, &connector->modes, head) {
-		if (mode->status == MODE_OK)
+		if (mode->status == MODE_OK && connector_funcs->mode_valid)
 			mode->status = connector_funcs->mode_valid(connector,
 								   mode);
 	}
@@ -186,7 +168,7 @@ prune:
 	drm_mode_sort(&connector->modes);
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] probed modes :\n", connector->base.id,
-			drm_get_connector_name(connector));
+			connector->name);
 	list_for_each_entry(mode, &connector->modes, head) {
 		drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
 		drm_mode_debug_printmodeline(mode);
@@ -194,9 +176,49 @@ prune:
 
 	return count;
 }
+
+/**
+ * drm_helper_probe_single_connector_modes - get complete set of display modes
+ * @connector: connector to probe
+ * @maxX: max width for modes
+ * @maxY: max height for modes
+ *
+ * Based on the helper callbacks implemented by @connector try to detect all
+ * valid modes.  Modes will first be added to the connector's probed_modes list,
+ * then culled (based on validity and the @maxX, @maxY parameters) and put into
+ * the normal modes list.
+ *
+ * Intended to be use as a generic implementation of the ->fill_modes()
+ * @connector vfunc for drivers that use the crtc helpers for output mode
+ * filtering and detection.
+ *
+ * Returns:
+ * The number of modes found on @connector.
+ */
+int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
+					    uint32_t maxX, uint32_t maxY)
+{
+	return drm_helper_probe_single_connector_modes_merge_bits(connector, maxX, maxY, true);
+}
 EXPORT_SYMBOL(drm_helper_probe_single_connector_modes);
 
 /**
+ * drm_helper_probe_single_connector_modes_nomerge - get complete set of display modes
+ * @connector: connector to probe
+ * @maxX: max width for modes
+ * @maxY: max height for modes
+ *
+ * This operates like drm_hehlper_probe_single_connector_modes except it
+ * replaces the mode bits instead of merging them for preferred modes.
+ */
+int drm_helper_probe_single_connector_modes_nomerge(struct drm_connector *connector,
+					    uint32_t maxX, uint32_t maxY)
+{
+	return drm_helper_probe_single_connector_modes_merge_bits(connector, maxX, maxY, false);
+}
+EXPORT_SYMBOL(drm_helper_probe_single_connector_modes_nomerge);
+
+/**
  * drm_kms_helper_hotplug_event - fire off KMS hotplug events
  * @dev: drm_device whose connector state changed
  *
@@ -264,7 +286,7 @@ static void output_poll_execute(struct work_struct *work)
 			DRM_DEBUG_KMS("[CONNECTOR:%d:%s] "
 				      "status updated from %s to %s\n",
 				      connector->base.id,
-				      drm_get_connector_name(connector),
+				      connector->name,
 				      old, new);
 
 			changed = true;
@@ -409,7 +431,7 @@ bool drm_helper_hpd_irq_event(struct drm_device *dev)
 		connector->status = connector->funcs->detect(connector, false);
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %s to %s\n",
 			      connector->base.id,
-			      drm_get_connector_name(connector),
+			      connector->name,
 			      drm_get_connector_status_name(old_status),
 			      drm_get_connector_status_name(connector->status));
 		if (old_status != connector->status)
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 4c24c3ac1ef..14d16464000 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -1,16 +1,11 @@
-/**
- * \file drm_stub.h
- * Stub support
- *
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
- */
-
 /*
  * Created: Fri Jan 19 10:48:35 2001 by faith@acm.org
  *
  * Copyright 2001 VA Linux Systems, Inc., Sunnyvale, California.
  * All Rights Reserved.
  *
+ * Author Rickard E. (Rik) Faith <faith@valinux.com>
+ *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
  * to deal in the Software without restriction, including without limitation
@@ -128,7 +123,10 @@ struct drm_master *drm_master_create(struct drm_minor *minor)
 	kref_init(&master->refcount);
 	spin_lock_init(&master->lock.spinlock);
 	init_waitqueue_head(&master->lock.lock_queue);
-	drm_ht_create(&master->magiclist, DRM_MAGIC_HASH_ORDER);
+	if (drm_ht_create(&master->magiclist, DRM_MAGIC_HASH_ORDER)) {
+		kfree(master);
+		return NULL;
+	}
 	INIT_LIST_HEAD(&master->magicfree);
 	master->minor = minor;
 
@@ -166,9 +164,6 @@ static void drm_master_destroy(struct kref *kref)
 		master->unique_len = 0;
 	}
 
-	kfree(dev->devname);
-	dev->devname = NULL;
-
 	list_for_each_entry_safe(pt, next, &master->magicfree, head) {
 		list_del(&pt->head);
 		drm_ht_remove_item(&master->magiclist, &pt->hash_item);
@@ -294,6 +289,7 @@ static void drm_minor_free(struct drm_device *dev, unsigned int type)
 
 	slot = drm_minor_get_slot(dev, type);
 	if (*slot) {
+		drm_mode_group_destroy(&(*slot)->mode_group);
 		kfree(*slot);
 		*slot = NULL;
 	}
@@ -424,11 +420,15 @@ void drm_minor_release(struct drm_minor *minor)
 }
 
 /**
- * Called via drm_exit() at module unload time or when pci device is
- * unplugged.
+ * drm_put_dev - Unregister and release a DRM device
+ * @dev: DRM device
  *
- * Cleans up all DRM device, calling drm_lastclose().
+ * Called at module unload time or when a PCI device is unplugged.
  *
+ * Use of this function is discouraged. It will eventually go away completely.
+ * Please use drm_dev_unregister() and drm_dev_unref() explicitly instead.
+ *
+ * Cleans up all DRM device, calling drm_lastclose().
  */
 void drm_put_dev(struct drm_device *dev)
 {
@@ -535,7 +535,7 @@ static void drm_fs_inode_free(struct inode *inode)
 }
 
 /**
- * drm_dev_alloc - Allocate new drm device
+ * drm_dev_alloc - Allocate new DRM device
  * @driver: DRM driver to allocate device for
  * @parent: Parent device object
  *
@@ -569,7 +569,7 @@ struct drm_device *drm_dev_alloc(struct drm_driver *driver,
 	INIT_LIST_HEAD(&dev->maplist);
 	INIT_LIST_HEAD(&dev->vblank_event_list);
 
-	spin_lock_init(&dev->count_lock);
+	spin_lock_init(&dev->buf_lock);
 	spin_lock_init(&dev->event_lock);
 	mutex_init(&dev->struct_mutex);
 	mutex_init(&dev->ctxlist_mutex);
@@ -648,9 +648,8 @@ static void drm_dev_release(struct kref *ref)
 	drm_minor_free(dev, DRM_MINOR_RENDER);
 	drm_minor_free(dev, DRM_MINOR_CONTROL);
 
-	kfree(dev->devname);
-
 	mutex_destroy(&dev->master_mutex);
+	kfree(dev->unique);
 	kfree(dev);
 }
 
@@ -690,6 +689,7 @@ EXPORT_SYMBOL(drm_dev_unref);
 /**
  * drm_dev_register - Register DRM device
  * @dev: Device to register
+ * @flags: Flags passed to the driver's .load() function
  *
  * Register the DRM device @dev with the system, advertise device to user-space
  * and start normal device operation. @dev must be allocated via drm_dev_alloc()
@@ -778,3 +778,28 @@ void drm_dev_unregister(struct drm_device *dev)
 	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 }
 EXPORT_SYMBOL(drm_dev_unregister);
+
+/**
+ * drm_dev_set_unique - Set the unique name of a DRM device
+ * @dev: device of which to set the unique name
+ * @fmt: format string for unique name
+ *
+ * Sets the unique name of a DRM device using the specified format string and
+ * a variable list of arguments. Drivers can use this at driver probe time if
+ * the unique name of the devices they drive is static.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int drm_dev_set_unique(struct drm_device *dev, const char *fmt, ...)
+{
+	va_list ap;
+
+	kfree(dev->unique);
+
+	va_start(ap, fmt);
+	dev->unique = kvasprintf(GFP_KERNEL, fmt, ap);
+	va_end(ap);
+
+	return dev->unique ? 0 : -ENOMEM;
+}
+EXPORT_SYMBOL(drm_dev_set_unique);
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index c22c3097c3e..369b26278e7 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -380,9 +380,9 @@ int drm_sysfs_connector_add(struct drm_connector *connector)
 
 	connector->kdev = device_create(drm_class, dev->primary->kdev,
 					0, connector, "card%d-%s",
-					dev->primary->index, drm_get_connector_name(connector));
+					dev->primary->index, connector->name);
 	DRM_DEBUG("adding \"%s\" to sysfs\n",
-		  drm_get_connector_name(connector));
+		  connector->name);
 
 	if (IS_ERR(connector->kdev)) {
 		DRM_ERROR("failed to register connector device: %ld\n", PTR_ERR(connector->kdev));
@@ -460,7 +460,7 @@ void drm_sysfs_connector_remove(struct drm_connector *connector)
 	if (!connector->kdev)
 		return;
 	DRM_DEBUG("removing \"%s\" from sysfs\n",
-		  drm_get_connector_name(connector));
+		  connector->name);
 
 	for (i = 0; i < ARRAY_SIZE(connector_attrs); i++)
 		device_remove_file(connector->kdev, &connector_attrs[i]);
diff --git a/drivers/gpu/drm/drm_usb.c b/drivers/gpu/drm/drm_usb.c
index c3406aad294..f2fe94aab90 100644
--- a/drivers/gpu/drm/drm_usb.c
+++ b/drivers/gpu/drm/drm_usb.c
@@ -36,16 +36,6 @@ err_free:
 }
 EXPORT_SYMBOL(drm_get_usb_dev);
 
-static int drm_usb_get_irq(struct drm_device *dev)
-{
-	return 0;
-}
-
-static const char *drm_usb_get_name(struct drm_device *dev)
-{
-	return "USB";
-}
-
 static int drm_usb_set_busid(struct drm_device *dev,
 			       struct drm_master *master)
 {
@@ -53,18 +43,24 @@ static int drm_usb_set_busid(struct drm_device *dev,
 }
 
 static struct drm_bus drm_usb_bus = {
-	.bus_type = DRIVER_BUS_USB,
-	.get_irq = drm_usb_get_irq,
-	.get_name = drm_usb_get_name,
 	.set_busid = drm_usb_set_busid,
 };
-    
+
+/**
+ * drm_usb_init - Register matching USB devices with the DRM subsystem
+ * @driver: DRM device driver
+ * @udriver: USB device driver
+ *
+ * Registers one or more devices matched by a USB driver with the DRM
+ * subsystem.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
 int drm_usb_init(struct drm_driver *driver, struct usb_driver *udriver)
 {
 	int res;
 	DRM_DEBUG("\n");
 
-	driver->kdriver.usb = udriver;
 	driver->bus = &drm_usb_bus;
 
 	res = usb_register(udriver);
@@ -72,6 +68,14 @@ int drm_usb_init(struct drm_driver *driver, struct usb_driver *udriver)
 }
 EXPORT_SYMBOL(drm_usb_init);
 
+/**
+ * drm_usb_exit - Unregister matching USB devices from the DRM subsystem
+ * @driver: DRM device driver
+ * @udriver: USB device driver
+ *
+ * Unregisters one or more devices matched by a USB driver from the DRM
+ * subsystem.
+ */
 void drm_usb_exit(struct drm_driver *driver,
 		  struct usb_driver *udriver)
 {
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 5bf5bca94f5..178d2a9672a 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -26,14 +26,14 @@ config DRM_EXYNOS_DMABUF
 
 config DRM_EXYNOS_FIMD
 	bool "Exynos DRM FIMD"
-	depends on DRM_EXYNOS && !FB_S3C && !ARCH_MULTIPLATFORM
+	depends on DRM_EXYNOS && !FB_S3C
 	select FB_MODE_HELPERS
 	help
 	  Choose this option if you want to use Exynos FIMD for DRM.
 
 config DRM_EXYNOS_DPI
 	bool "EXYNOS DRM parallel output support"
-	depends on DRM_EXYNOS
+	depends on DRM_EXYNOS_FIMD
 	select DRM_PANEL
 	default n
 	help
@@ -41,7 +41,7 @@ config DRM_EXYNOS_DPI
 
 config DRM_EXYNOS_DSI
 	bool "EXYNOS DRM MIPI-DSI driver support"
-	depends on DRM_EXYNOS
+	depends on DRM_EXYNOS_FIMD
 	select DRM_MIPI_DSI
 	select DRM_PANEL
 	default n
@@ -50,7 +50,7 @@ config DRM_EXYNOS_DSI
 
 config DRM_EXYNOS_DP
 	bool "EXYNOS DRM DP driver support"
-	depends on DRM_EXYNOS && ARCH_EXYNOS
+	depends on DRM_EXYNOS_FIMD && ARCH_EXYNOS && (DRM_PTN3460=n || DRM_PTN3460=y || DRM_PTN3460=DRM_EXYNOS)
 	default DRM_EXYNOS
 	help
 	  This enables support for DP device.
diff --git a/drivers/gpu/drm/exynos/exynos_ddc.c b/drivers/gpu/drm/exynos/exynos_ddc.c
deleted file mode 100644
index 6a8c84e7c83..00000000000
--- a/drivers/gpu/drm/exynos/exynos_ddc.c
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Copyright (C) 2011 Samsung Electronics Co.Ltd
- * Authors:
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *	Inki Dae <inki.dae@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- */
-
-#include <drm/drmP.h>
-
-#include <linux/kernel.h>
-#include <linux/i2c.h>
-#include <linux/of.h>
-
-#include "exynos_drm_drv.h"
-#include "exynos_hdmi.h"
-
-static int s5p_ddc_probe(struct i2c_client *client,
-			const struct i2c_device_id *dev_id)
-{
-	hdmi_attach_ddc_client(client);
-
-	dev_info(&client->adapter->dev,
-		"attached %s into i2c adapter successfully\n",
-		client->name);
-
-	return 0;
-}
-
-static int s5p_ddc_remove(struct i2c_client *client)
-{
-	dev_info(&client->adapter->dev,
-		"detached %s from i2c adapter successfully\n",
-		client->name);
-
-	return 0;
-}
-
-static struct of_device_id hdmiddc_match_types[] = {
-	{
-		.compatible = "samsung,exynos5-hdmiddc",
-	}, {
-		.compatible = "samsung,exynos4210-hdmiddc",
-	}, {
-		/* end node */
-	}
-};
-
-struct i2c_driver ddc_driver = {
-	.driver = {
-		.name = "exynos-hdmiddc",
-		.owner = THIS_MODULE,
-		.of_match_table = hdmiddc_match_types,
-	},
-	.probe		= s5p_ddc_probe,
-	.remove		= s5p_ddc_remove,
-	.command		= NULL,
-};
diff --git a/drivers/gpu/drm/exynos/exynos_dp_core.c b/drivers/gpu/drm/exynos/exynos_dp_core.c
index aed533bbfd3..a8ffc8c1477 100644
--- a/drivers/gpu/drm/exynos/exynos_dp_core.c
+++ b/drivers/gpu/drm/exynos/exynos_dp_core.c
@@ -18,6 +18,9 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/of.h>
+#include <linux/of_gpio.h>
+#include <linux/gpio.h>
+#include <linux/component.h>
 #include <linux/phy/phy.h>
 #include <video/of_display_timing.h>
 #include <video/of_videomode.h>
@@ -141,15 +144,15 @@ static int exynos_dp_read_edid(struct exynos_dp_device *dp)
 			return -EIO;
 		}
 
-		exynos_dp_read_byte_from_dpcd(dp, DPCD_ADDR_TEST_REQUEST,
+		exynos_dp_read_byte_from_dpcd(dp, DP_TEST_REQUEST,
 					&test_vector);
-		if (test_vector & DPCD_TEST_EDID_READ) {
+		if (test_vector & DP_TEST_LINK_EDID_READ) {
 			exynos_dp_write_byte_to_dpcd(dp,
-				DPCD_ADDR_TEST_EDID_CHECKSUM,
+				DP_TEST_EDID_CHECKSUM,
 				edid[EDID_BLOCK_LENGTH + EDID_CHECKSUM]);
 			exynos_dp_write_byte_to_dpcd(dp,
-				DPCD_ADDR_TEST_RESPONSE,
-				DPCD_TEST_EDID_CHECKSUM_WRITE);
+				DP_TEST_RESPONSE,
+				DP_TEST_EDID_CHECKSUM_WRITE);
 		}
 	} else {
 		dev_info(dp->dev, "EDID data does not include any extensions.\n");
@@ -171,15 +174,15 @@ static int exynos_dp_read_edid(struct exynos_dp_device *dp)
 		}
 
 		exynos_dp_read_byte_from_dpcd(dp,
-			DPCD_ADDR_TEST_REQUEST,
+			DP_TEST_REQUEST,
 			&test_vector);
-		if (test_vector & DPCD_TEST_EDID_READ) {
+		if (test_vector & DP_TEST_LINK_EDID_READ) {
 			exynos_dp_write_byte_to_dpcd(dp,
-				DPCD_ADDR_TEST_EDID_CHECKSUM,
+				DP_TEST_EDID_CHECKSUM,
 				edid[EDID_CHECKSUM]);
 			exynos_dp_write_byte_to_dpcd(dp,
-				DPCD_ADDR_TEST_RESPONSE,
-				DPCD_TEST_EDID_CHECKSUM_WRITE);
+				DP_TEST_RESPONSE,
+				DP_TEST_EDID_CHECKSUM_WRITE);
 		}
 	}
 
@@ -193,8 +196,8 @@ static int exynos_dp_handle_edid(struct exynos_dp_device *dp)
 	int i;
 	int retval;
 
-	/* Read DPCD DPCD_ADDR_DPCD_REV~RECEIVE_PORT1_CAP_1 */
-	retval = exynos_dp_read_bytes_from_dpcd(dp, DPCD_ADDR_DPCD_REV,
+	/* Read DPCD DP_DPCD_REV~RECEIVE_PORT1_CAP_1 */
+	retval = exynos_dp_read_bytes_from_dpcd(dp, DP_DPCD_REV,
 				12, buf);
 	if (retval)
 		return retval;
@@ -214,14 +217,14 @@ static void exynos_dp_enable_rx_to_enhanced_mode(struct exynos_dp_device *dp,
 {
 	u8 data;
 
-	exynos_dp_read_byte_from_dpcd(dp, DPCD_ADDR_LANE_COUNT_SET, &data);
+	exynos_dp_read_byte_from_dpcd(dp, DP_LANE_COUNT_SET, &data);
 
 	if (enable)
-		exynos_dp_write_byte_to_dpcd(dp, DPCD_ADDR_LANE_COUNT_SET,
-			DPCD_ENHANCED_FRAME_EN |
+		exynos_dp_write_byte_to_dpcd(dp, DP_LANE_COUNT_SET,
+			DP_LANE_COUNT_ENHANCED_FRAME_EN |
 			DPCD_LANE_COUNT_SET(data));
 	else
-		exynos_dp_write_byte_to_dpcd(dp, DPCD_ADDR_LANE_COUNT_SET,
+		exynos_dp_write_byte_to_dpcd(dp, DP_LANE_COUNT_SET,
 			DPCD_LANE_COUNT_SET(data));
 }
 
@@ -230,7 +233,7 @@ static int exynos_dp_is_enhanced_mode_available(struct exynos_dp_device *dp)
 	u8 data;
 	int retval;
 
-	exynos_dp_read_byte_from_dpcd(dp, DPCD_ADDR_MAX_LANE_COUNT, &data);
+	exynos_dp_read_byte_from_dpcd(dp, DP_MAX_LANE_COUNT, &data);
 	retval = DPCD_ENHANCED_FRAME_CAP(data);
 
 	return retval;
@@ -250,8 +253,8 @@ static void exynos_dp_training_pattern_dis(struct exynos_dp_device *dp)
 	exynos_dp_set_training_pattern(dp, DP_NONE);
 
 	exynos_dp_write_byte_to_dpcd(dp,
-		DPCD_ADDR_TRAINING_PATTERN_SET,
-		DPCD_TRAINING_PATTERN_DISABLED);
+		DP_TRAINING_PATTERN_SET,
+		DP_TRAINING_PATTERN_DISABLE);
 }
 
 static void exynos_dp_set_lane_lane_pre_emphasis(struct exynos_dp_device *dp,
@@ -295,7 +298,7 @@ static int exynos_dp_link_start(struct exynos_dp_device *dp)
 	/* Setup RX configuration */
 	buf[0] = dp->link_train.link_rate;
 	buf[1] = dp->link_train.lane_count;
-	retval = exynos_dp_write_bytes_to_dpcd(dp, DPCD_ADDR_LINK_BW_SET,
+	retval = exynos_dp_write_bytes_to_dpcd(dp, DP_LINK_BW_SET,
 				2, buf);
 	if (retval)
 		return retval;
@@ -322,16 +325,16 @@ static int exynos_dp_link_start(struct exynos_dp_device *dp)
 
 	/* Set RX training pattern */
 	retval = exynos_dp_write_byte_to_dpcd(dp,
-			DPCD_ADDR_TRAINING_PATTERN_SET,
-			DPCD_SCRAMBLING_DISABLED | DPCD_TRAINING_PATTERN_1);
+			DP_TRAINING_PATTERN_SET,
+			DP_LINK_SCRAMBLING_DISABLE | DP_TRAINING_PATTERN_1);
 	if (retval)
 		return retval;
 
 	for (lane = 0; lane < lane_count; lane++)
-		buf[lane] = DPCD_PRE_EMPHASIS_PATTERN2_LEVEL0 |
-			    DPCD_VOLTAGE_SWING_PATTERN1_LEVEL0;
+		buf[lane] = DP_TRAIN_PRE_EMPHASIS_0 |
+			    DP_TRAIN_VOLTAGE_SWING_400;
 
-	retval = exynos_dp_write_bytes_to_dpcd(dp, DPCD_ADDR_TRAINING_LANE0_SET,
+	retval = exynos_dp_write_bytes_to_dpcd(dp, DP_TRAINING_LANE0_SET,
 			lane_count, buf);
 
 	return retval;
@@ -352,7 +355,7 @@ static int exynos_dp_clock_recovery_ok(u8 link_status[2], int lane_count)
 
 	for (lane = 0; lane < lane_count; lane++) {
 		lane_status = exynos_dp_get_lane_status(link_status, lane);
-		if ((lane_status & DPCD_LANE_CR_DONE) == 0)
+		if ((lane_status & DP_LANE_CR_DONE) == 0)
 			return -EINVAL;
 	}
 	return 0;
@@ -364,13 +367,13 @@ static int exynos_dp_channel_eq_ok(u8 link_status[2], u8 link_align,
 	int lane;
 	u8 lane_status;
 
-	if ((link_align & DPCD_INTERLANE_ALIGN_DONE) == 0)
+	if ((link_align & DP_INTERLANE_ALIGN_DONE) == 0)
 		return -EINVAL;
 
 	for (lane = 0; lane < lane_count; lane++) {
 		lane_status = exynos_dp_get_lane_status(link_status, lane);
-		lane_status &= DPCD_CHANNEL_EQ_BITS;
-		if (lane_status != DPCD_CHANNEL_EQ_BITS)
+		lane_status &= DP_CHANNEL_EQ_BITS;
+		if (lane_status != DP_CHANNEL_EQ_BITS)
 			return -EINVAL;
 	}
 
@@ -468,9 +471,9 @@ static void exynos_dp_get_adjust_training_lane(struct exynos_dp_device *dp,
 				DPCD_PRE_EMPHASIS_SET(pre_emphasis);
 
 		if (voltage_swing == VOLTAGE_LEVEL_3)
-			training_lane |= DPCD_MAX_SWING_REACHED;
+			training_lane |= DP_TRAIN_MAX_SWING_REACHED;
 		if (pre_emphasis == PRE_EMPHASIS_LEVEL_3)
-			training_lane |= DPCD_MAX_PRE_EMPHASIS_REACHED;
+			training_lane |= DP_TRAIN_MAX_PRE_EMPHASIS_REACHED;
 
 		dp->link_train.training_lane[lane] = training_lane;
 	}
@@ -487,12 +490,12 @@ static int exynos_dp_process_clock_recovery(struct exynos_dp_device *dp)
 	lane_count = dp->link_train.lane_count;
 
 	retval =  exynos_dp_read_bytes_from_dpcd(dp,
-			DPCD_ADDR_LANE0_1_STATUS, 2, link_status);
+			DP_LANE0_1_STATUS, 2, link_status);
 	if (retval)
 		return retval;
 
 	retval =  exynos_dp_read_bytes_from_dpcd(dp,
-			DPCD_ADDR_ADJUST_REQUEST_LANE0_1, 2, adjust_request);
+			DP_ADJUST_REQUEST_LANE0_1, 2, adjust_request);
 	if (retval)
 		return retval;
 
@@ -501,9 +504,9 @@ static int exynos_dp_process_clock_recovery(struct exynos_dp_device *dp)
 		exynos_dp_set_training_pattern(dp, TRAINING_PTN2);
 
 		retval = exynos_dp_write_byte_to_dpcd(dp,
-				DPCD_ADDR_TRAINING_PATTERN_SET,
-				DPCD_SCRAMBLING_DISABLED |
-				DPCD_TRAINING_PATTERN_2);
+				DP_TRAINING_PATTERN_SET,
+				DP_LINK_SCRAMBLING_DISABLE |
+				DP_TRAINING_PATTERN_2);
 		if (retval)
 			return retval;
 
@@ -543,7 +546,7 @@ static int exynos_dp_process_clock_recovery(struct exynos_dp_device *dp)
 			dp->link_train.training_lane[lane], lane);
 
 	retval = exynos_dp_write_bytes_to_dpcd(dp,
-			DPCD_ADDR_TRAINING_LANE0_SET, lane_count,
+			DP_TRAINING_LANE0_SET, lane_count,
 			dp->link_train.training_lane);
 	if (retval)
 		return retval;
@@ -562,7 +565,7 @@ static int exynos_dp_process_equalizer_training(struct exynos_dp_device *dp)
 	lane_count = dp->link_train.lane_count;
 
 	retval = exynos_dp_read_bytes_from_dpcd(dp,
-			DPCD_ADDR_LANE0_1_STATUS, 2, link_status);
+			DP_LANE0_1_STATUS, 2, link_status);
 	if (retval)
 		return retval;
 
@@ -572,12 +575,12 @@ static int exynos_dp_process_equalizer_training(struct exynos_dp_device *dp)
 	}
 
 	retval = exynos_dp_read_bytes_from_dpcd(dp,
-			DPCD_ADDR_ADJUST_REQUEST_LANE0_1, 2, adjust_request);
+			DP_ADJUST_REQUEST_LANE0_1, 2, adjust_request);
 	if (retval)
 		return retval;
 
 	retval = exynos_dp_read_byte_from_dpcd(dp,
-			DPCD_ADDR_LANE_ALIGN_STATUS_UPDATED, &link_align);
+			DP_LANE_ALIGN_STATUS_UPDATED, &link_align);
 	if (retval)
 		return retval;
 
@@ -619,7 +622,7 @@ static int exynos_dp_process_equalizer_training(struct exynos_dp_device *dp)
 		exynos_dp_set_lane_link_training(dp,
 			dp->link_train.training_lane[lane], lane);
 
-	retval = exynos_dp_write_bytes_to_dpcd(dp, DPCD_ADDR_TRAINING_LANE0_SET,
+	retval = exynos_dp_write_bytes_to_dpcd(dp, DP_TRAINING_LANE0_SET,
 			lane_count, dp->link_train.training_lane);
 
 	return retval;
@@ -634,7 +637,7 @@ static void exynos_dp_get_max_rx_bandwidth(struct exynos_dp_device *dp,
 	 * For DP rev.1.1, Maximum link rate of Main Link lanes
 	 * 0x06 = 1.62 Gbps, 0x0a = 2.7 Gbps
 	 */
-	exynos_dp_read_byte_from_dpcd(dp, DPCD_ADDR_MAX_LINK_RATE, &data);
+	exynos_dp_read_byte_from_dpcd(dp, DP_MAX_LINK_RATE, &data);
 	*bandwidth = data;
 }
 
@@ -647,7 +650,7 @@ static void exynos_dp_get_max_rx_lane_count(struct exynos_dp_device *dp,
 	 * For DP rev.1.1, Maximum number of Main Link lanes
 	 * 0x01 = 1 lane, 0x02 = 2 lanes, 0x04 = 4 lanes
 	 */
-	exynos_dp_read_byte_from_dpcd(dp, DPCD_ADDR_MAX_LANE_COUNT, &data);
+	exynos_dp_read_byte_from_dpcd(dp, DP_MAX_LANE_COUNT, &data);
 	*lane_count = DPCD_MAX_LANE_COUNT(data);
 }
 
@@ -819,20 +822,20 @@ static void exynos_dp_enable_scramble(struct exynos_dp_device *dp, bool enable)
 		exynos_dp_enable_scrambling(dp);
 
 		exynos_dp_read_byte_from_dpcd(dp,
-			DPCD_ADDR_TRAINING_PATTERN_SET,
+			DP_TRAINING_PATTERN_SET,
 			&data);
 		exynos_dp_write_byte_to_dpcd(dp,
-			DPCD_ADDR_TRAINING_PATTERN_SET,
-			(u8)(data & ~DPCD_SCRAMBLING_DISABLED));
+			DP_TRAINING_PATTERN_SET,
+			(u8)(data & ~DP_LINK_SCRAMBLING_DISABLE));
 	} else {
 		exynos_dp_disable_scrambling(dp);
 
 		exynos_dp_read_byte_from_dpcd(dp,
-			DPCD_ADDR_TRAINING_PATTERN_SET,
+			DP_TRAINING_PATTERN_SET,
 			&data);
 		exynos_dp_write_byte_to_dpcd(dp,
-			DPCD_ADDR_TRAINING_PATTERN_SET,
-			(u8)(data | DPCD_SCRAMBLING_DISABLED));
+			DP_TRAINING_PATTERN_SET,
+			(u8)(data | DP_LINK_SCRAMBLING_DISABLE));
 	}
 }
 
@@ -949,12 +952,6 @@ static int exynos_dp_get_modes(struct drm_connector *connector)
 	return 1;
 }
 
-static int exynos_dp_mode_valid(struct drm_connector *connector,
-			struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
 static struct drm_encoder *exynos_dp_best_encoder(
 			struct drm_connector *connector)
 {
@@ -965,20 +962,9 @@ static struct drm_encoder *exynos_dp_best_encoder(
 
 static struct drm_connector_helper_funcs exynos_dp_connector_helper_funcs = {
 	.get_modes = exynos_dp_get_modes,
-	.mode_valid = exynos_dp_mode_valid,
 	.best_encoder = exynos_dp_best_encoder,
 };
 
-static int exynos_dp_initialize(struct exynos_drm_display *display,
-				struct drm_device *drm_dev)
-{
-	struct exynos_dp_device *dp = display->ctx;
-
-	dp->drm_dev = drm_dev;
-
-	return 0;
-}
-
 static bool find_bridge(const char *compat, struct bridge_init *bridge)
 {
 	bridge->client = NULL;
@@ -1101,12 +1087,11 @@ static void exynos_dp_dpms(struct exynos_drm_display *display, int mode)
 		break;
 	default:
 		break;
-	};
+	}
 	dp->dpms_mode = mode;
 }
 
 static struct exynos_drm_display_ops exynos_dp_display_ops = {
-	.initialize = exynos_dp_initialize,
 	.create_connector = exynos_dp_create_connector,
 	.dpms = exynos_dp_dpms,
 };
@@ -1123,10 +1108,8 @@ static struct video_info *exynos_dp_dt_parse_pdata(struct device *dev)
 
 	dp_video_config = devm_kzalloc(dev,
 				sizeof(*dp_video_config), GFP_KERNEL);
-	if (!dp_video_config) {
-		dev_err(dev, "memory allocation for video config failed\n");
+	if (!dp_video_config)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	dp_video_config->h_sync_polarity =
 		of_property_read_bool(dp_node, "hsync-active-high");
@@ -1185,10 +1168,7 @@ static int exynos_dp_dt_parse_phydata(struct exynos_dp_device *dp)
 	dp_phy_node = of_find_node_by_name(dp_phy_node, "dptx-phy");
 	if (!dp_phy_node) {
 		dp->phy = devm_phy_get(dp->dev, "dp");
-		if (IS_ERR(dp->phy))
-			return PTR_ERR(dp->phy);
-		else
-			return 0;
+		return PTR_ERR_OR_ZERO(dp->phy);
 	}
 
 	if (of_property_read_u32(dp_phy_node, "reg", &phy_base)) {
@@ -1230,19 +1210,20 @@ static int exynos_dp_dt_parse_panel(struct exynos_dp_device *dp)
 	return 0;
 }
 
-static int exynos_dp_probe(struct platform_device *pdev)
+static int exynos_dp_bind(struct device *dev, struct device *master, void *data)
 {
+	struct platform_device *pdev = to_platform_device(dev);
+	struct drm_device *drm_dev = data;
 	struct resource *res;
 	struct exynos_dp_device *dp;
+	unsigned int irq_flags;
 
 	int ret = 0;
 
 	dp = devm_kzalloc(&pdev->dev, sizeof(struct exynos_dp_device),
 				GFP_KERNEL);
-	if (!dp) {
-		dev_err(&pdev->dev, "no memory for device data\n");
+	if (!dp)
 		return -ENOMEM;
-	}
 
 	dp->dev = &pdev->dev;
 	dp->dpms_mode = DRM_MODE_DPMS_OFF;
@@ -1273,7 +1254,30 @@ static int exynos_dp_probe(struct platform_device *pdev)
 	if (IS_ERR(dp->reg_base))
 		return PTR_ERR(dp->reg_base);
 
-	dp->irq = platform_get_irq(pdev, 0);
+	dp->hpd_gpio = of_get_named_gpio(dev->of_node, "samsung,hpd-gpio", 0);
+
+	if (gpio_is_valid(dp->hpd_gpio)) {
+		/*
+		 * Set up the hotplug GPIO from the device tree as an interrupt.
+		 * Simply specifying a different interrupt in the device tree
+		 * doesn't work since we handle hotplug rather differently when
+		 * using a GPIO.  We also need the actual GPIO specifier so
+		 * that we can get the current state of the GPIO.
+		 */
+		ret = devm_gpio_request_one(&pdev->dev, dp->hpd_gpio, GPIOF_IN,
+					    "hpd_gpio");
+		if (ret) {
+			dev_err(&pdev->dev, "failed to get hpd gpio\n");
+			return ret;
+		}
+		dp->irq = gpio_to_irq(dp->hpd_gpio);
+		irq_flags = IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING;
+	} else {
+		dp->hpd_gpio = -ENODEV;
+		dp->irq = platform_get_irq(pdev, 0);
+		irq_flags = 0;
+	}
+
 	if (dp->irq == -ENXIO) {
 		dev_err(&pdev->dev, "failed to get irq\n");
 		return -ENODEV;
@@ -1285,28 +1289,61 @@ static int exynos_dp_probe(struct platform_device *pdev)
 
 	exynos_dp_init_dp(dp);
 
-	ret = devm_request_irq(&pdev->dev, dp->irq, exynos_dp_irq_handler, 0,
-				"exynos-dp", dp);
+	ret = devm_request_irq(&pdev->dev, dp->irq, exynos_dp_irq_handler,
+			irq_flags, "exynos-dp", dp);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to request irq\n");
 		return ret;
 	}
 	disable_irq(dp->irq);
 
+	dp->drm_dev = drm_dev;
 	exynos_dp_display.ctx = dp;
 
 	platform_set_drvdata(pdev, &exynos_dp_display);
-	exynos_drm_display_register(&exynos_dp_display);
 
-	return 0;
+	return exynos_drm_create_enc_conn(drm_dev, &exynos_dp_display);
 }
 
-static int exynos_dp_remove(struct platform_device *pdev)
+static void exynos_dp_unbind(struct device *dev, struct device *master,
+				void *data)
 {
-	struct exynos_drm_display *display = platform_get_drvdata(pdev);
+	struct exynos_drm_display *display = dev_get_drvdata(dev);
+	struct exynos_dp_device *dp = display->ctx;
+	struct drm_encoder *encoder = dp->encoder;
 
 	exynos_dp_dpms(display, DRM_MODE_DPMS_OFF);
-	exynos_drm_display_unregister(&exynos_dp_display);
+
+	encoder->funcs->destroy(encoder);
+	drm_connector_cleanup(&dp->connector);
+}
+
+static const struct component_ops exynos_dp_ops = {
+	.bind	= exynos_dp_bind,
+	.unbind	= exynos_dp_unbind,
+};
+
+static int exynos_dp_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	ret = exynos_drm_component_add(&pdev->dev, EXYNOS_DEVICE_TYPE_CONNECTOR,
+					exynos_dp_display.type);
+	if (ret)
+		return ret;
+
+	ret = component_add(&pdev->dev, &exynos_dp_ops);
+	if (ret)
+		exynos_drm_component_del(&pdev->dev,
+						EXYNOS_DEVICE_TYPE_CONNECTOR);
+
+	return ret;
+}
+
+static int exynos_dp_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &exynos_dp_ops);
+	exynos_drm_component_del(&pdev->dev, EXYNOS_DEVICE_TYPE_CONNECTOR);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_dp_core.h b/drivers/gpu/drm/exynos/exynos_dp_core.h
index d6a900d4ee4..02cc4f9ab90 100644
--- a/drivers/gpu/drm/exynos/exynos_dp_core.h
+++ b/drivers/gpu/drm/exynos/exynos_dp_core.h
@@ -14,6 +14,7 @@
 #define _EXYNOS_DP_CORE_H
 
 #include <drm/drm_crtc.h>
+#include <drm/drm_dp_helper.h>
 #include <drm/exynos_drm.h>
 
 #define DP_TIMEOUT_LOOP_COUNT 100
@@ -159,6 +160,7 @@ struct exynos_dp_device {
 	struct work_struct	hotplug_work;
 	struct phy		*phy;
 	int			dpms_mode;
+	int			hpd_gpio;
 
 	struct exynos_drm_panel_info panel;
 };
@@ -261,69 +263,17 @@ void exynos_dp_disable_scrambling(struct exynos_dp_device *dp);
 #define EDID_EXTENSION_FLAG			0x7e
 #define EDID_CHECKSUM				0x7f
 
-/* Definition for DPCD Register */
-#define DPCD_ADDR_DPCD_REV			0x0000
-#define DPCD_ADDR_MAX_LINK_RATE			0x0001
-#define DPCD_ADDR_MAX_LANE_COUNT		0x0002
-#define DPCD_ADDR_LINK_BW_SET			0x0100
-#define DPCD_ADDR_LANE_COUNT_SET		0x0101
-#define DPCD_ADDR_TRAINING_PATTERN_SET		0x0102
-#define DPCD_ADDR_TRAINING_LANE0_SET		0x0103
-#define DPCD_ADDR_LANE0_1_STATUS		0x0202
-#define DPCD_ADDR_LANE_ALIGN_STATUS_UPDATED	0x0204
-#define DPCD_ADDR_ADJUST_REQUEST_LANE0_1	0x0206
-#define DPCD_ADDR_ADJUST_REQUEST_LANE2_3	0x0207
-#define DPCD_ADDR_TEST_REQUEST			0x0218
-#define DPCD_ADDR_TEST_RESPONSE			0x0260
-#define DPCD_ADDR_TEST_EDID_CHECKSUM		0x0261
-#define DPCD_ADDR_SINK_POWER_STATE		0x0600
-
-/* DPCD_ADDR_MAX_LANE_COUNT */
+/* DP_MAX_LANE_COUNT */
 #define DPCD_ENHANCED_FRAME_CAP(x)		(((x) >> 7) & 0x1)
 #define DPCD_MAX_LANE_COUNT(x)			((x) & 0x1f)
 
-/* DPCD_ADDR_LANE_COUNT_SET */
-#define DPCD_ENHANCED_FRAME_EN			(0x1 << 7)
+/* DP_LANE_COUNT_SET */
 #define DPCD_LANE_COUNT_SET(x)			((x) & 0x1f)
 
-/* DPCD_ADDR_TRAINING_PATTERN_SET */
-#define DPCD_SCRAMBLING_DISABLED		(0x1 << 5)
-#define DPCD_SCRAMBLING_ENABLED			(0x0 << 5)
-#define DPCD_TRAINING_PATTERN_2			(0x2 << 0)
-#define DPCD_TRAINING_PATTERN_1			(0x1 << 0)
-#define DPCD_TRAINING_PATTERN_DISABLED		(0x0 << 0)
-
-/* DPCD_ADDR_TRAINING_LANE0_SET */
-#define DPCD_MAX_PRE_EMPHASIS_REACHED		(0x1 << 5)
+/* DP_TRAINING_LANE0_SET */
 #define DPCD_PRE_EMPHASIS_SET(x)		(((x) & 0x3) << 3)
 #define DPCD_PRE_EMPHASIS_GET(x)		(((x) >> 3) & 0x3)
-#define DPCD_PRE_EMPHASIS_PATTERN2_LEVEL0	(0x0 << 3)
-#define DPCD_MAX_SWING_REACHED			(0x1 << 2)
 #define DPCD_VOLTAGE_SWING_SET(x)		(((x) & 0x3) << 0)
 #define DPCD_VOLTAGE_SWING_GET(x)		(((x) >> 0) & 0x3)
-#define DPCD_VOLTAGE_SWING_PATTERN1_LEVEL0	(0x0 << 0)
-
-/* DPCD_ADDR_LANE0_1_STATUS */
-#define DPCD_LANE_SYMBOL_LOCKED			(0x1 << 2)
-#define DPCD_LANE_CHANNEL_EQ_DONE		(0x1 << 1)
-#define DPCD_LANE_CR_DONE			(0x1 << 0)
-#define DPCD_CHANNEL_EQ_BITS			(DPCD_LANE_CR_DONE|	\
-						 DPCD_LANE_CHANNEL_EQ_DONE|\
-						 DPCD_LANE_SYMBOL_LOCKED)
-
-/* DPCD_ADDR_LANE_ALIGN__STATUS_UPDATED */
-#define DPCD_LINK_STATUS_UPDATED		(0x1 << 7)
-#define DPCD_DOWNSTREAM_PORT_STATUS_CHANGED	(0x1 << 6)
-#define DPCD_INTERLANE_ALIGN_DONE		(0x1 << 0)
-
-/* DPCD_ADDR_TEST_REQUEST */
-#define DPCD_TEST_EDID_READ			(0x1 << 2)
-
-/* DPCD_ADDR_TEST_RESPONSE */
-#define DPCD_TEST_EDID_CHECKSUM_WRITE		(0x1 << 2)
-
-/* DPCD_ADDR_SINK_POWER_STATE */
-#define DPCD_SET_POWER_STATE_D0			(0x1 << 0)
-#define DPCD_SET_POWER_STATE_D4			(0x2 << 0)
 
 #endif /* _EXYNOS_DP_CORE_H */
diff --git a/drivers/gpu/drm/exynos/exynos_dp_reg.c b/drivers/gpu/drm/exynos/exynos_dp_reg.c
index b70da5052ff..c1f87a2a928 100644
--- a/drivers/gpu/drm/exynos/exynos_dp_reg.c
+++ b/drivers/gpu/drm/exynos/exynos_dp_reg.c
@@ -13,6 +13,7 @@
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/delay.h>
+#include <linux/gpio.h>
 
 #include "exynos_dp_core.h"
 #include "exynos_dp_reg.h"
@@ -326,6 +327,9 @@ void exynos_dp_clear_hotplug_interrupts(struct exynos_dp_device *dp)
 {
 	u32 reg;
 
+	if (gpio_is_valid(dp->hpd_gpio))
+		return;
+
 	reg = HOTPLUG_CHG | HPD_LOST | PLUG;
 	writel(reg, dp->reg_base + EXYNOS_DP_COMMON_INT_STA_4);
 
@@ -337,6 +341,9 @@ void exynos_dp_init_hpd(struct exynos_dp_device *dp)
 {
 	u32 reg;
 
+	if (gpio_is_valid(dp->hpd_gpio))
+		return;
+
 	exynos_dp_clear_hotplug_interrupts(dp);
 
 	reg = readl(dp->reg_base + EXYNOS_DP_SYS_CTL_3);
@@ -348,19 +355,27 @@ enum dp_irq_type exynos_dp_get_irq_type(struct exynos_dp_device *dp)
 {
 	u32 reg;
 
-	/* Parse hotplug interrupt status register */
-	reg = readl(dp->reg_base + EXYNOS_DP_COMMON_INT_STA_4);
+	if (gpio_is_valid(dp->hpd_gpio)) {
+		reg = gpio_get_value(dp->hpd_gpio);
+		if (reg)
+			return DP_IRQ_TYPE_HP_CABLE_IN;
+		else
+			return DP_IRQ_TYPE_HP_CABLE_OUT;
+	} else {
+		/* Parse hotplug interrupt status register */
+		reg = readl(dp->reg_base + EXYNOS_DP_COMMON_INT_STA_4);
 
-	if (reg & PLUG)
-		return DP_IRQ_TYPE_HP_CABLE_IN;
+		if (reg & PLUG)
+			return DP_IRQ_TYPE_HP_CABLE_IN;
 
-	if (reg & HPD_LOST)
-		return DP_IRQ_TYPE_HP_CABLE_OUT;
+		if (reg & HPD_LOST)
+			return DP_IRQ_TYPE_HP_CABLE_OUT;
 
-	if (reg & HOTPLUG_CHG)
-		return DP_IRQ_TYPE_HP_CHANGE;
+		if (reg & HOTPLUG_CHG)
+			return DP_IRQ_TYPE_HP_CHANGE;
 
-	return DP_IRQ_TYPE_UNKNOWN;
+		return DP_IRQ_TYPE_UNKNOWN;
+	}
 }
 
 void exynos_dp_reset_aux(struct exynos_dp_device *dp)
@@ -386,7 +401,7 @@ void exynos_dp_init_aux(struct exynos_dp_device *dp)
 	/* Disable AUX transaction H/W retry */
 	reg = AUX_BIT_PERIOD_EXPECTED_DELAY(3) | AUX_HW_RETRY_COUNT_SEL(0)|
 		AUX_HW_RETRY_INTERVAL_600_MICROSECONDS;
-	writel(reg, dp->reg_base + EXYNOS_DP_AUX_HW_RETRY_CTL) ;
+	writel(reg, dp->reg_base + EXYNOS_DP_AUX_HW_RETRY_CTL);
 
 	/* Receive AUX Channel DEFER commands equal to DEFFER_COUNT*64 */
 	reg = DEFER_CTRL_EN | DEFER_COUNT(1);
@@ -402,9 +417,14 @@ int exynos_dp_get_plug_in_status(struct exynos_dp_device *dp)
 {
 	u32 reg;
 
-	reg = readl(dp->reg_base + EXYNOS_DP_SYS_CTL_3);
-	if (reg & HPD_STATUS)
-		return 0;
+	if (gpio_is_valid(dp->hpd_gpio)) {
+		if (gpio_get_value(dp->hpd_gpio))
+			return 0;
+	} else {
+		reg = readl(dp->reg_base + EXYNOS_DP_SYS_CTL_3);
+		if (reg & HPD_STATUS)
+			return 0;
+	}
 
 	return -EINVAL;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
index 0e9e06ce36b..4c9f972eaa0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_core.c
@@ -19,21 +19,19 @@
 #include "exynos_drm_fbdev.h"
 
 static LIST_HEAD(exynos_drm_subdrv_list);
-static LIST_HEAD(exynos_drm_manager_list);
-static LIST_HEAD(exynos_drm_display_list);
 
-static int exynos_drm_create_enc_conn(struct drm_device *dev,
+int exynos_drm_create_enc_conn(struct drm_device *dev,
 					struct exynos_drm_display *display)
 {
 	struct drm_encoder *encoder;
-	struct exynos_drm_manager *manager;
 	int ret;
 	unsigned long possible_crtcs = 0;
 
-	/* Find possible crtcs for this display */
-	list_for_each_entry(manager, &exynos_drm_manager_list, list)
-		if (manager->type == display->type)
-			possible_crtcs |= 1 << manager->pipe;
+	ret = exynos_drm_crtc_get_pipe_from_type(dev, display->type);
+	if (ret < 0)
+		return ret;
+
+	possible_crtcs |= 1 << ret;
 
 	/* create and initialize a encoder for this sub driver. */
 	encoder = exynos_drm_encoder_create(dev, display, possible_crtcs);
@@ -57,127 +55,29 @@ err_destroy_encoder:
 	return ret;
 }
 
-static int exynos_drm_subdrv_probe(struct drm_device *dev,
-					struct exynos_drm_subdrv *subdrv)
-{
-	if (subdrv->probe) {
-		int ret;
-
-		subdrv->drm_dev = dev;
-
-		/*
-		 * this probe callback would be called by sub driver
-		 * after setting of all resources to this sub driver,
-		 * such as clock, irq and register map are done or by load()
-		 * of exynos drm driver.
-		 *
-		 * P.S. note that this driver is considered for modularization.
-		 */
-		ret = subdrv->probe(dev, subdrv->dev);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-static void exynos_drm_subdrv_remove(struct drm_device *dev,
-				      struct exynos_drm_subdrv *subdrv)
-{
-	if (subdrv->remove)
-		subdrv->remove(dev, subdrv->dev);
-}
-
-int exynos_drm_initialize_managers(struct drm_device *dev)
+int exynos_drm_subdrv_register(struct exynos_drm_subdrv *subdrv)
 {
-	struct exynos_drm_manager *manager, *n;
-	int ret, pipe = 0;
-
-	list_for_each_entry(manager, &exynos_drm_manager_list, list) {
-		if (manager->ops->initialize) {
-			ret = manager->ops->initialize(manager, dev, pipe);
-			if (ret) {
-				DRM_ERROR("Mgr init [%d] failed with %d\n",
-						manager->type, ret);
-				goto err;
-			}
-		}
+	if (!subdrv)
+		return -EINVAL;
 
-		manager->drm_dev = dev;
-		manager->pipe = pipe++;
+	list_add_tail(&subdrv->list, &exynos_drm_subdrv_list);
 
-		ret = exynos_drm_crtc_create(manager);
-		if (ret) {
-			DRM_ERROR("CRTC create [%d] failed with %d\n",
-					manager->type, ret);
-			goto err;
-		}
-	}
 	return 0;
-
-err:
-	list_for_each_entry_safe(manager, n, &exynos_drm_manager_list, list) {
-		if (pipe-- > 0)
-			exynos_drm_manager_unregister(manager);
-		else
-			list_del(&manager->list);
-	}
-	return ret;
-}
-
-void exynos_drm_remove_managers(struct drm_device *dev)
-{
-	struct exynos_drm_manager *manager, *n;
-
-	list_for_each_entry_safe(manager, n, &exynos_drm_manager_list, list)
-		exynos_drm_manager_unregister(manager);
 }
+EXPORT_SYMBOL_GPL(exynos_drm_subdrv_register);
 
-int exynos_drm_initialize_displays(struct drm_device *dev)
+int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv)
 {
-	struct exynos_drm_display *display, *n;
-	int ret, initialized = 0;
-
-	list_for_each_entry(display, &exynos_drm_display_list, list) {
-		if (display->ops->initialize) {
-			ret = display->ops->initialize(display, dev);
-			if (ret) {
-				DRM_ERROR("Display init [%d] failed with %d\n",
-						display->type, ret);
-				goto err;
-			}
-		}
+	if (!subdrv)
+		return -EINVAL;
 
-		initialized++;
+	list_del(&subdrv->list);
 
-		ret = exynos_drm_create_enc_conn(dev, display);
-		if (ret) {
-			DRM_ERROR("Encoder create [%d] failed with %d\n",
-					display->type, ret);
-			goto err;
-		}
-	}
 	return 0;
-
-err:
-	list_for_each_entry_safe(display, n, &exynos_drm_display_list, list) {
-		if (initialized-- > 0)
-			exynos_drm_display_unregister(display);
-		else
-			list_del(&display->list);
-	}
-	return ret;
-}
-
-void exynos_drm_remove_displays(struct drm_device *dev)
-{
-	struct exynos_drm_display *display, *n;
-
-	list_for_each_entry_safe(display, n, &exynos_drm_display_list, list)
-		exynos_drm_display_unregister(display);
 }
+EXPORT_SYMBOL_GPL(exynos_drm_subdrv_unregister);
 
-int exynos_drm_device_register(struct drm_device *dev)
+int exynos_drm_device_subdrv_probe(struct drm_device *dev)
 {
 	struct exynos_drm_subdrv *subdrv, *n;
 	int err;
@@ -186,19 +86,28 @@ int exynos_drm_device_register(struct drm_device *dev)
 		return -EINVAL;
 
 	list_for_each_entry_safe(subdrv, n, &exynos_drm_subdrv_list, list) {
-		err = exynos_drm_subdrv_probe(dev, subdrv);
-		if (err) {
-			DRM_DEBUG("exynos drm subdrv probe failed.\n");
-			list_del(&subdrv->list);
-			continue;
+		if (subdrv->probe) {
+			subdrv->drm_dev = dev;
+
+			/*
+			 * this probe callback would be called by sub driver
+			 * after setting of all resources to this sub driver,
+			 * such as clock, irq and register map are done.
+			 */
+			err = subdrv->probe(dev, subdrv->dev);
+			if (err) {
+				DRM_DEBUG("exynos drm subdrv probe failed.\n");
+				list_del(&subdrv->list);
+				continue;
+			}
 		}
 	}
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(exynos_drm_device_register);
+EXPORT_SYMBOL_GPL(exynos_drm_device_subdrv_probe);
 
-int exynos_drm_device_unregister(struct drm_device *dev)
+int exynos_drm_device_subdrv_remove(struct drm_device *dev)
 {
 	struct exynos_drm_subdrv *subdrv;
 
@@ -208,66 +117,13 @@ int exynos_drm_device_unregister(struct drm_device *dev)
 	}
 
 	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		exynos_drm_subdrv_remove(dev, subdrv);
+		if (subdrv->remove)
+			subdrv->remove(dev, subdrv->dev);
 	}
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(exynos_drm_device_unregister);
-
-int exynos_drm_manager_register(struct exynos_drm_manager *manager)
-{
-	BUG_ON(!manager->ops);
-	list_add_tail(&manager->list, &exynos_drm_manager_list);
-	return 0;
-}
-
-int exynos_drm_manager_unregister(struct exynos_drm_manager *manager)
-{
-	if (manager->ops->remove)
-		manager->ops->remove(manager);
-
-	list_del(&manager->list);
-	return 0;
-}
-
-int exynos_drm_display_register(struct exynos_drm_display *display)
-{
-	BUG_ON(!display->ops);
-	list_add_tail(&display->list, &exynos_drm_display_list);
-	return 0;
-}
-
-int exynos_drm_display_unregister(struct exynos_drm_display *display)
-{
-	if (display->ops->remove)
-		display->ops->remove(display);
-
-	list_del(&display->list);
-	return 0;
-}
-
-int exynos_drm_subdrv_register(struct exynos_drm_subdrv *subdrv)
-{
-	if (!subdrv)
-		return -EINVAL;
-
-	list_add_tail(&subdrv->list, &exynos_drm_subdrv_list);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(exynos_drm_subdrv_register);
-
-int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv)
-{
-	if (!subdrv)
-		return -EINVAL;
-
-	list_del(&subdrv->list);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(exynos_drm_subdrv_unregister);
+EXPORT_SYMBOL_GPL(exynos_drm_device_subdrv_remove);
 
 int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file)
 {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 1ef5ab9c9d5..95c9435d026 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -368,6 +368,7 @@ int exynos_drm_crtc_create(struct exynos_drm_manager *manager)
 		return -ENOMEM;
 	}
 
+	manager->crtc = &exynos_crtc->drm_crtc;
 	crtc = &exynos_crtc->drm_crtc;
 
 	private->crtc[manager->pipe] = crtc;
@@ -491,3 +492,19 @@ void exynos_drm_crtc_complete_scanout(struct drm_framebuffer *fb)
 			manager->ops->wait_for_vblank(manager);
 	}
 }
+
+int exynos_drm_crtc_get_pipe_from_type(struct drm_device *drm_dev,
+					unsigned int out_type)
+{
+	struct drm_crtc *crtc;
+
+	list_for_each_entry(crtc, &drm_dev->mode_config.crtc_list, head) {
+		struct exynos_drm_crtc *exynos_crtc;
+
+		exynos_crtc = to_exynos_crtc(crtc);
+		if (exynos_crtc->manager->type == out_type)
+			return exynos_crtc->manager->pipe;
+	}
+
+	return -EPERM;
+}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.h b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
index c27b66cc5d2..9f74b10a8a0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
@@ -32,4 +32,8 @@ void exynos_drm_crtc_plane_commit(struct drm_crtc *crtc, int zpos);
 void exynos_drm_crtc_plane_enable(struct drm_crtc *crtc, int zpos);
 void exynos_drm_crtc_plane_disable(struct drm_crtc *crtc, int zpos);
 
+/* This function gets pipe value to crtc device matched with out_type. */
+int exynos_drm_crtc_get_pipe_from_type(struct drm_device *drm_dev,
+					unsigned int out_type);
+
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index 2b09c7c0bfc..9e530f205ad 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -40,20 +40,10 @@ exynos_dpi_detect(struct drm_connector *connector, bool force)
 {
 	struct exynos_dpi *ctx = connector_to_dpi(connector);
 
-	/* panels supported only by boot-loader are always connected */
-	if (!ctx->panel_node)
-		return connector_status_connected;
-
-	if (!ctx->panel) {
-		ctx->panel = of_drm_find_panel(ctx->panel_node);
-		if (ctx->panel)
-			drm_panel_attach(ctx->panel, &ctx->connector);
-	}
-
-	if (ctx->panel)
-		return connector_status_connected;
+	if (ctx->panel && !ctx->panel->connector)
+		drm_panel_attach(ctx->panel, &ctx->connector);
 
-	return connector_status_disconnected;
+	return connector_status_connected;
 }
 
 static void exynos_dpi_connector_destroy(struct drm_connector *connector)
@@ -94,12 +84,6 @@ static int exynos_dpi_get_modes(struct drm_connector *connector)
 	return 0;
 }
 
-static int exynos_dpi_mode_valid(struct drm_connector *connector,
-				 struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
 static struct drm_encoder *
 exynos_dpi_best_encoder(struct drm_connector *connector)
 {
@@ -110,7 +94,6 @@ exynos_dpi_best_encoder(struct drm_connector *connector)
 
 static struct drm_connector_helper_funcs exynos_dpi_connector_helper_funcs = {
 	.get_modes = exynos_dpi_get_modes,
-	.mode_valid = exynos_dpi_mode_valid,
 	.best_encoder = exynos_dpi_best_encoder,
 };
 
@@ -123,10 +106,7 @@ static int exynos_dpi_create_connector(struct exynos_drm_display *display,
 
 	ctx->encoder = encoder;
 
-	if (ctx->panel_node)
-		connector->polled = DRM_CONNECTOR_POLL_CONNECT;
-	else
-		connector->polled = DRM_CONNECTOR_POLL_HPD;
+	connector->polled = DRM_CONNECTOR_POLL_HPD;
 
 	ret = drm_connector_init(encoder->dev, connector,
 				 &exynos_dpi_connector_funcs,
@@ -172,7 +152,7 @@ static void exynos_dpi_dpms(struct exynos_drm_display *display, int mode)
 		break;
 	default:
 		break;
-	};
+	}
 	ctx->dpms_mode = mode;
 }
 
@@ -294,8 +274,10 @@ static int exynos_dpi_parse_dt(struct exynos_dpi *ctx)
 			return -ENOMEM;
 
 		ret = of_get_videomode(dn, vm, 0);
-		if (ret < 0)
+		if (ret < 0) {
+			devm_kfree(dev, vm);
 			return ret;
+		}
 
 		ctx->vm = vm;
 
@@ -308,32 +290,58 @@ static int exynos_dpi_parse_dt(struct exynos_dpi *ctx)
 	return 0;
 }
 
-int exynos_dpi_probe(struct device *dev)
+struct exynos_drm_display *exynos_dpi_probe(struct device *dev)
 {
 	struct exynos_dpi *ctx;
 	int ret;
 
+	ret = exynos_drm_component_add(dev,
+					EXYNOS_DEVICE_TYPE_CONNECTOR,
+					exynos_dpi_display.type);
+	if (ret)
+		return ERR_PTR(ret);
+
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
-		return -ENOMEM;
+		goto err_del_component;
 
 	ctx->dev = dev;
 	exynos_dpi_display.ctx = ctx;
 	ctx->dpms_mode = DRM_MODE_DPMS_OFF;
 
 	ret = exynos_dpi_parse_dt(ctx);
-	if (ret < 0)
-		return ret;
+	if (ret < 0) {
+		devm_kfree(dev, ctx);
+		goto err_del_component;
+	}
 
-	exynos_drm_display_register(&exynos_dpi_display);
+	if (ctx->panel_node) {
+		ctx->panel = of_drm_find_panel(ctx->panel_node);
+		if (!ctx->panel) {
+			exynos_drm_component_del(dev,
+						EXYNOS_DEVICE_TYPE_CONNECTOR);
+			return ERR_PTR(-EPROBE_DEFER);
+		}
+	}
 
-	return 0;
+	return &exynos_dpi_display;
+
+err_del_component:
+	exynos_drm_component_del(dev, EXYNOS_DEVICE_TYPE_CONNECTOR);
+
+	return NULL;
 }
 
 int exynos_dpi_remove(struct device *dev)
 {
+	struct drm_encoder *encoder = exynos_dpi_display.encoder;
+	struct exynos_dpi *ctx = exynos_dpi_display.ctx;
+
 	exynos_dpi_dpms(&exynos_dpi_display, DRM_MODE_DPMS_OFF);
-	exynos_drm_display_unregister(&exynos_dpi_display);
+	encoder->funcs->destroy(encoder);
+	drm_connector_cleanup(&ctx->connector);
+
+	exynos_drm_component_del(dev, EXYNOS_DEVICE_TYPE_CONNECTOR);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 2d27ba23a6a..ab7d182063c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -16,6 +16,7 @@
 #include <drm/drm_crtc_helper.h>
 
 #include <linux/anon_inodes.h>
+#include <linux/component.h>
 
 #include <drm/exynos_drm.h>
 
@@ -40,9 +41,19 @@
 
 #define VBLANK_OFF_DELAY	50000
 
-/* platform device pointer for eynos drm device. */
 static struct platform_device *exynos_drm_pdev;
 
+static DEFINE_MUTEX(drm_component_lock);
+static LIST_HEAD(drm_component_list);
+
+struct component_dev {
+	struct list_head list;
+	struct device *crtc_dev;
+	struct device *conn_dev;
+	enum exynos_drm_output_type out_type;
+	unsigned int dev_type_flag;
+};
+
 static int exynos_drm_load(struct drm_device *dev, unsigned long flags)
 {
 	struct exynos_drm_private *private;
@@ -73,38 +84,21 @@ static int exynos_drm_load(struct drm_device *dev, unsigned long flags)
 
 	exynos_drm_mode_config_init(dev);
 
-	ret = exynos_drm_initialize_managers(dev);
-	if (ret)
-		goto err_mode_config_cleanup;
-
 	for (nr = 0; nr < MAX_PLANE; nr++) {
 		struct drm_plane *plane;
 		unsigned long possible_crtcs = (1 << MAX_CRTC) - 1;
 
 		plane = exynos_plane_init(dev, possible_crtcs, false);
 		if (!plane)
-			goto err_manager_cleanup;
+			goto err_mode_config_cleanup;
 	}
 
-	ret = exynos_drm_initialize_displays(dev);
-	if (ret)
-		goto err_manager_cleanup;
-
 	/* init kms poll for handling hpd */
 	drm_kms_helper_poll_init(dev);
 
 	ret = drm_vblank_init(dev, MAX_CRTC);
 	if (ret)
-		goto err_display_cleanup;
-
-	/*
-	 * probe sub drivers such as display controller and hdmi driver,
-	 * that were registered at probe() of platform driver
-	 * to the sub driver and create encoder and connector for them.
-	 */
-	ret = exynos_drm_device_register(dev);
-	if (ret)
-		goto err_vblank;
+		goto err_mode_config_cleanup;
 
 	/* setup possible_clones. */
 	exynos_drm_encoder_setup(dev);
@@ -113,17 +107,25 @@ static int exynos_drm_load(struct drm_device *dev, unsigned long flags)
 
 	platform_set_drvdata(dev->platformdev, dev);
 
+	/* Try to bind all sub drivers. */
+	ret = component_bind_all(dev->dev, dev);
+	if (ret)
+		goto err_cleanup_vblank;
+
+	/* Probe non kms sub drivers and virtual display driver. */
+	ret = exynos_drm_device_subdrv_probe(dev);
+	if (ret)
+		goto err_unbind_all;
+
 	/* force connectors detection */
 	drm_helper_hpd_irq_event(dev);
 
 	return 0;
 
-err_vblank:
+err_unbind_all:
+	component_unbind_all(dev->dev, dev);
+err_cleanup_vblank:
 	drm_vblank_cleanup(dev);
-err_display_cleanup:
-	exynos_drm_remove_displays(dev);
-err_manager_cleanup:
-	exynos_drm_remove_managers(dev);
 err_mode_config_cleanup:
 	drm_mode_config_cleanup(dev);
 	drm_release_iommu_mapping(dev);
@@ -135,17 +137,17 @@ err_free_private:
 
 static int exynos_drm_unload(struct drm_device *dev)
 {
+	exynos_drm_device_subdrv_remove(dev);
+
 	exynos_drm_fbdev_fini(dev);
-	exynos_drm_device_unregister(dev);
 	drm_vblank_cleanup(dev);
 	drm_kms_helper_poll_fini(dev);
-	exynos_drm_remove_displays(dev);
-	exynos_drm_remove_managers(dev);
 	drm_mode_config_cleanup(dev);
 
 	drm_release_iommu_mapping(dev);
 	kfree(dev->dev_private);
 
+	component_unbind_all(dev->dev, dev);
 	dev->dev_private = NULL;
 
 	return 0;
@@ -183,9 +185,9 @@ static int exynos_drm_resume(struct drm_device *dev)
 		if (connector->funcs->dpms)
 			connector->funcs->dpms(connector, connector->dpms);
 	}
+	drm_modeset_unlock_all(dev);
 
 	drm_helper_resume_force_mode(dev);
-	drm_modeset_unlock_all(dev);
 
 	return 0;
 }
@@ -323,8 +325,7 @@ static const struct file_operations exynos_drm_driver_fops = {
 };
 
 static struct drm_driver exynos_drm_driver = {
-	.driver_features	= DRIVER_HAVE_IRQ | DRIVER_MODESET |
-					DRIVER_GEM | DRIVER_PRIME,
+	.driver_features	= DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME,
 	.load			= exynos_drm_load,
 	.unload			= exynos_drm_unload,
 	.suspend		= exynos_drm_suspend,
@@ -355,27 +356,6 @@ static struct drm_driver exynos_drm_driver = {
 	.minor	= DRIVER_MINOR,
 };
 
-static int exynos_drm_platform_probe(struct platform_device *pdev)
-{
-	int ret;
-
-	ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
-	if (ret)
-		return ret;
-
-	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
-
-	return drm_platform_init(&exynos_drm_driver, pdev);
-}
-
-static int exynos_drm_platform_remove(struct platform_device *pdev)
-{
-	drm_put_dev(platform_get_drvdata(pdev));
-
-	return 0;
-}
-
 #ifdef CONFIG_PM_SLEEP
 static int exynos_drm_sys_suspend(struct device *dev)
 {
@@ -400,196 +380,319 @@ static int exynos_drm_sys_resume(struct device *dev)
 }
 #endif
 
-#ifdef CONFIG_PM_RUNTIME
-static int exynos_drm_runtime_suspend(struct device *dev)
+static const struct dev_pm_ops exynos_drm_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(exynos_drm_sys_suspend, exynos_drm_sys_resume)
+};
+
+int exynos_drm_component_add(struct device *dev,
+				enum exynos_drm_device_type dev_type,
+				enum exynos_drm_output_type out_type)
 {
-	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	pm_message_t message;
+	struct component_dev *cdev;
 
-	if (pm_runtime_suspended(dev))
-		return 0;
+	if (dev_type != EXYNOS_DEVICE_TYPE_CRTC &&
+			dev_type != EXYNOS_DEVICE_TYPE_CONNECTOR) {
+		DRM_ERROR("invalid device type.\n");
+		return -EINVAL;
+	}
 
-	message.event = PM_EVENT_SUSPEND;
-	return exynos_drm_suspend(drm_dev, message);
+	mutex_lock(&drm_component_lock);
+
+	/*
+	 * Make sure to check if there is a component which has two device
+	 * objects, for connector and for encoder/connector.
+	 * It should make sure that crtc and encoder/connector drivers are
+	 * ready before exynos drm core binds them.
+	 */
+	list_for_each_entry(cdev, &drm_component_list, list) {
+		if (cdev->out_type == out_type) {
+			/*
+			 * If crtc and encoder/connector device objects are
+			 * added already just return.
+			 */
+			if (cdev->dev_type_flag == (EXYNOS_DEVICE_TYPE_CRTC |
+						EXYNOS_DEVICE_TYPE_CONNECTOR)) {
+				mutex_unlock(&drm_component_lock);
+				return 0;
+			}
+
+			if (dev_type == EXYNOS_DEVICE_TYPE_CRTC) {
+				cdev->crtc_dev = dev;
+				cdev->dev_type_flag |= dev_type;
+			}
+
+			if (dev_type == EXYNOS_DEVICE_TYPE_CONNECTOR) {
+				cdev->conn_dev = dev;
+				cdev->dev_type_flag |= dev_type;
+			}
+
+			mutex_unlock(&drm_component_lock);
+			return 0;
+		}
+	}
+
+	mutex_unlock(&drm_component_lock);
+
+	cdev = kzalloc(sizeof(*cdev), GFP_KERNEL);
+	if (!cdev)
+		return -ENOMEM;
+
+	if (dev_type == EXYNOS_DEVICE_TYPE_CRTC)
+		cdev->crtc_dev = dev;
+	if (dev_type == EXYNOS_DEVICE_TYPE_CONNECTOR)
+		cdev->conn_dev = dev;
+
+	cdev->out_type = out_type;
+	cdev->dev_type_flag = dev_type;
+
+	mutex_lock(&drm_component_lock);
+	list_add_tail(&cdev->list, &drm_component_list);
+	mutex_unlock(&drm_component_lock);
+
+	return 0;
 }
 
-static int exynos_drm_runtime_resume(struct device *dev)
+void exynos_drm_component_del(struct device *dev,
+				enum exynos_drm_device_type dev_type)
 {
-	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct component_dev *cdev, *next;
 
-	if (!pm_runtime_suspended(dev))
-		return 0;
+	mutex_lock(&drm_component_lock);
 
-	return exynos_drm_resume(drm_dev);
+	list_for_each_entry_safe(cdev, next, &drm_component_list, list) {
+		if (dev_type == EXYNOS_DEVICE_TYPE_CRTC) {
+			if (cdev->crtc_dev == dev) {
+				cdev->crtc_dev = NULL;
+				cdev->dev_type_flag &= ~dev_type;
+			}
+		}
+
+		if (dev_type == EXYNOS_DEVICE_TYPE_CONNECTOR) {
+			if (cdev->conn_dev == dev) {
+				cdev->conn_dev = NULL;
+				cdev->dev_type_flag &= ~dev_type;
+			}
+		}
+
+		/*
+		 * Release cdev object only in case that both of crtc and
+		 * encoder/connector device objects are NULL.
+		 */
+		if (!cdev->crtc_dev && !cdev->conn_dev) {
+			list_del(&cdev->list);
+			kfree(cdev);
+		}
+
+		break;
+	}
+
+	mutex_unlock(&drm_component_lock);
 }
-#endif
 
-static const struct dev_pm_ops exynos_drm_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(exynos_drm_sys_suspend, exynos_drm_sys_resume)
-	SET_RUNTIME_PM_OPS(exynos_drm_runtime_suspend,
-			exynos_drm_runtime_resume, NULL)
-};
+static int compare_of(struct device *dev, void *data)
+{
+	return dev == (struct device *)data;
+}
 
-static struct platform_driver exynos_drm_platform_driver = {
-	.probe		= exynos_drm_platform_probe,
-	.remove		= exynos_drm_platform_remove,
-	.driver		= {
-		.owner	= THIS_MODULE,
-		.name	= "exynos-drm",
-		.pm	= &exynos_drm_pm_ops,
-	},
+static int exynos_drm_add_components(struct device *dev, struct master *m)
+{
+	struct component_dev *cdev;
+	unsigned int attach_cnt = 0;
+
+	mutex_lock(&drm_component_lock);
+
+	list_for_each_entry(cdev, &drm_component_list, list) {
+		int ret;
+
+		/*
+		 * Add components to master only in case that crtc and
+		 * encoder/connector device objects exist.
+		 */
+		if (!cdev->crtc_dev || !cdev->conn_dev)
+			continue;
+
+		attach_cnt++;
+
+		mutex_unlock(&drm_component_lock);
+
+		/*
+		 * fimd and dpi modules have same device object so add
+		 * only crtc device object in this case.
+		 *
+		 * TODO. if dpi module follows driver-model driver then
+		 * below codes can be removed.
+		 */
+		if (cdev->crtc_dev == cdev->conn_dev) {
+			ret = component_master_add_child(m, compare_of,
+					cdev->crtc_dev);
+			if (ret < 0)
+				return ret;
+
+			goto out_lock;
+		}
+
+		/*
+		 * Do not chage below call order.
+		 * crtc device first should be added to master because
+		 * connector/encoder need pipe number of crtc when they
+		 * are created.
+		 */
+		ret = component_master_add_child(m, compare_of, cdev->crtc_dev);
+		ret |= component_master_add_child(m, compare_of,
+							cdev->conn_dev);
+		if (ret < 0)
+			return ret;
+
+out_lock:
+		mutex_lock(&drm_component_lock);
+	}
+
+	mutex_unlock(&drm_component_lock);
+
+	return attach_cnt ? 0 : -ENODEV;
+}
+
+static int exynos_drm_bind(struct device *dev)
+{
+	return drm_platform_init(&exynos_drm_driver, to_platform_device(dev));
+}
+
+static void exynos_drm_unbind(struct device *dev)
+{
+	drm_put_dev(dev_get_drvdata(dev));
+}
+
+static const struct component_master_ops exynos_drm_ops = {
+	.add_components = exynos_drm_add_components,
+	.bind		= exynos_drm_bind,
+	.unbind		= exynos_drm_unbind,
 };
 
-static int __init exynos_drm_init(void)
+static int exynos_drm_platform_probe(struct platform_device *pdev)
 {
 	int ret;
 
+	pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	exynos_drm_driver.num_ioctls = ARRAY_SIZE(exynos_ioctls);
+
+#ifdef CONFIG_DRM_EXYNOS_FIMD
+	ret = platform_driver_register(&fimd_driver);
+	if (ret < 0)
+		return ret;
+#endif
+
 #ifdef CONFIG_DRM_EXYNOS_DP
 	ret = platform_driver_register(&dp_driver);
 	if (ret < 0)
-		goto out_dp;
+		goto err_unregister_fimd_drv;
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_DSI
 	ret = platform_driver_register(&dsi_driver);
 	if (ret < 0)
-		goto out_dsi;
-#endif
-
-#ifdef CONFIG_DRM_EXYNOS_FIMD
-	ret = platform_driver_register(&fimd_driver);
-	if (ret < 0)
-		goto out_fimd;
+		goto err_unregister_dp_drv;
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_HDMI
-	ret = platform_driver_register(&hdmi_driver);
-	if (ret < 0)
-		goto out_hdmi;
 	ret = platform_driver_register(&mixer_driver);
 	if (ret < 0)
-		goto out_mixer;
-#endif
-
-#ifdef CONFIG_DRM_EXYNOS_VIDI
-	ret = platform_driver_register(&vidi_driver);
+		goto err_unregister_dsi_drv;
+	ret = platform_driver_register(&hdmi_driver);
 	if (ret < 0)
-		goto out_vidi;
+		goto err_unregister_mixer_drv;
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_G2D
 	ret = platform_driver_register(&g2d_driver);
 	if (ret < 0)
-		goto out_g2d;
+		goto err_unregister_hdmi_drv;
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_FIMC
 	ret = platform_driver_register(&fimc_driver);
 	if (ret < 0)
-		goto out_fimc;
+		goto err_unregister_g2d_drv;
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_ROTATOR
 	ret = platform_driver_register(&rotator_driver);
 	if (ret < 0)
-		goto out_rotator;
+		goto err_unregister_fimc_drv;
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_GSC
 	ret = platform_driver_register(&gsc_driver);
 	if (ret < 0)
-		goto out_gsc;
+		goto err_unregister_rotator_drv;
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_IPP
 	ret = platform_driver_register(&ipp_driver);
 	if (ret < 0)
-		goto out_ipp;
+		goto err_unregister_gsc_drv;
 
 	ret = exynos_platform_device_ipp_register();
 	if (ret < 0)
-		goto out_ipp_dev;
+		goto err_unregister_ipp_drv;
 #endif
 
-	ret = platform_driver_register(&exynos_drm_platform_driver);
+	ret = component_master_add(&pdev->dev, &exynos_drm_ops);
 	if (ret < 0)
-		goto out_drm;
-
-	exynos_drm_pdev = platform_device_register_simple("exynos-drm", -1,
-				NULL, 0);
-	if (IS_ERR(exynos_drm_pdev)) {
-		ret = PTR_ERR(exynos_drm_pdev);
-		goto out;
-	}
+		DRM_DEBUG_KMS("re-tried by last sub driver probed later.\n");
 
 	return 0;
 
-out:
-	platform_driver_unregister(&exynos_drm_platform_driver);
-
-out_drm:
 #ifdef CONFIG_DRM_EXYNOS_IPP
-	exynos_platform_device_ipp_unregister();
-out_ipp_dev:
+err_unregister_ipp_drv:
 	platform_driver_unregister(&ipp_driver);
-out_ipp:
+err_unregister_gsc_drv:
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_GSC
 	platform_driver_unregister(&gsc_driver);
-out_gsc:
+err_unregister_rotator_drv:
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_ROTATOR
 	platform_driver_unregister(&rotator_driver);
-out_rotator:
+err_unregister_fimc_drv:
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_FIMC
 	platform_driver_unregister(&fimc_driver);
-out_fimc:
+err_unregister_g2d_drv:
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_G2D
 	platform_driver_unregister(&g2d_driver);
-out_g2d:
-#endif
-
-#ifdef CONFIG_DRM_EXYNOS_VIDI
-	platform_driver_unregister(&vidi_driver);
-out_vidi:
+err_unregister_hdmi_drv:
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_HDMI
-	platform_driver_unregister(&mixer_driver);
-out_mixer:
 	platform_driver_unregister(&hdmi_driver);
-out_hdmi:
-#endif
-
-#ifdef CONFIG_DRM_EXYNOS_FIMD
-	platform_driver_unregister(&fimd_driver);
-out_fimd:
+err_unregister_mixer_drv:
+	platform_driver_unregister(&mixer_driver);
+err_unregister_dsi_drv:
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_DSI
 	platform_driver_unregister(&dsi_driver);
-out_dsi:
+err_unregister_dp_drv:
 #endif
 
 #ifdef CONFIG_DRM_EXYNOS_DP
 	platform_driver_unregister(&dp_driver);
-out_dp:
+err_unregister_fimd_drv:
+#endif
+
+#ifdef CONFIG_DRM_EXYNOS_FIMD
+	platform_driver_unregister(&fimd_driver);
 #endif
 	return ret;
 }
 
-static void __exit exynos_drm_exit(void)
+static int exynos_drm_platform_remove(struct platform_device *pdev)
 {
-	platform_device_unregister(exynos_drm_pdev);
-
-	platform_driver_unregister(&exynos_drm_platform_driver);
-
 #ifdef CONFIG_DRM_EXYNOS_IPP
 	exynos_platform_device_ipp_unregister();
 	platform_driver_unregister(&ipp_driver);
@@ -616,10 +719,6 @@ static void __exit exynos_drm_exit(void)
 	platform_driver_unregister(&hdmi_driver);
 #endif
 
-#ifdef CONFIG_DRM_EXYNOS_VIDI
-	platform_driver_unregister(&vidi_driver);
-#endif
-
 #ifdef CONFIG_DRM_EXYNOS_FIMD
 	platform_driver_unregister(&fimd_driver);
 #endif
@@ -631,6 +730,59 @@ static void __exit exynos_drm_exit(void)
 #ifdef CONFIG_DRM_EXYNOS_DP
 	platform_driver_unregister(&dp_driver);
 #endif
+	component_master_del(&pdev->dev, &exynos_drm_ops);
+	return 0;
+}
+
+static struct platform_driver exynos_drm_platform_driver = {
+	.probe	= exynos_drm_platform_probe,
+	.remove	= exynos_drm_platform_remove,
+	.driver	= {
+		.owner	= THIS_MODULE,
+		.name	= "exynos-drm",
+		.pm	= &exynos_drm_pm_ops,
+	},
+};
+
+static int exynos_drm_init(void)
+{
+	int ret;
+
+	exynos_drm_pdev = platform_device_register_simple("exynos-drm", -1,
+								NULL, 0);
+	if (IS_ERR(exynos_drm_pdev))
+		return PTR_ERR(exynos_drm_pdev);
+
+#ifdef CONFIG_DRM_EXYNOS_VIDI
+	ret = exynos_drm_probe_vidi();
+	if (ret < 0)
+		goto err_unregister_pd;
+#endif
+
+	ret = platform_driver_register(&exynos_drm_platform_driver);
+	if (ret)
+		goto err_remove_vidi;
+
+	return 0;
+
+err_remove_vidi:
+#ifdef CONFIG_DRM_EXYNOS_VIDI
+	exynos_drm_remove_vidi();
+
+err_unregister_pd:
+#endif
+	platform_device_unregister(exynos_drm_pdev);
+
+	return ret;
+}
+
+static void exynos_drm_exit(void)
+{
+	platform_driver_unregister(&exynos_drm_platform_driver);
+#ifdef CONFIG_DRM_EXYNOS_VIDI
+	exynos_drm_remove_vidi();
+#endif
+	platform_device_unregister(exynos_drm_pdev);
 }
 
 module_init(exynos_drm_init);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index ce3e6a30dea..06cde450627 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -42,6 +42,13 @@ struct drm_connector;
 
 extern unsigned int drm_vblank_offdelay;
 
+/* This enumerates device type. */
+enum exynos_drm_device_type {
+	EXYNOS_DEVICE_TYPE_NONE,
+	EXYNOS_DEVICE_TYPE_CRTC,
+	EXYNOS_DEVICE_TYPE_CONNECTOR,
+};
+
 /* this enumerates display type. */
 enum exynos_drm_output_type {
 	EXYNOS_DISPLAY_TYPE_NONE,
@@ -122,7 +129,6 @@ struct exynos_drm_overlay {
  * Exynos DRM Display Structure.
  *	- this structure is common to analog tv, digital tv and lcd panel.
  *
- * @initialize: initializes the display with drm_dev
  * @remove: cleans up the display for removal
  * @mode_fixup: fix mode data comparing to hw specific display mode.
  * @mode_set: convert drm_display_mode to hw specific display mode and
@@ -133,8 +139,6 @@ struct exynos_drm_overlay {
  */
 struct exynos_drm_display;
 struct exynos_drm_display_ops {
-	int (*initialize)(struct exynos_drm_display *display,
-				struct drm_device *drm_dev);
 	int (*create_connector)(struct exynos_drm_display *display,
 				struct drm_encoder *encoder);
 	void (*remove)(struct exynos_drm_display *display);
@@ -172,8 +176,6 @@ struct exynos_drm_display {
 /*
  * Exynos drm manager ops
  *
- * @initialize: initializes the manager with drm_dev
- * @remove: cleans up the manager for removal
  * @dpms: control device power.
  * @mode_fixup: fix mode data before applying it
  * @mode_set: set the given mode to the manager
@@ -189,9 +191,6 @@ struct exynos_drm_display {
  */
 struct exynos_drm_manager;
 struct exynos_drm_manager_ops {
-	int (*initialize)(struct exynos_drm_manager *mgr,
-				struct drm_device *drm_dev, int pipe);
-	void (*remove)(struct exynos_drm_manager *mgr);
 	void (*dpms)(struct exynos_drm_manager *mgr, int mode);
 	bool (*mode_fixup)(struct exynos_drm_manager *mgr,
 				const struct drm_display_mode *mode,
@@ -215,6 +214,7 @@ struct exynos_drm_manager_ops {
  * @list: the list entry for this manager
  * @type: one of EXYNOS_DISPLAY_TYPE_LCD and HDMI.
  * @drm_dev: pointer to the drm device
+ * @crtc: crtc object.
  * @pipe: the pipe number for this crtc/manager
  * @ops: pointer to callbacks for exynos drm specific functionality
  * @ctx: A pointer to the manager's implementation specific context
@@ -223,6 +223,7 @@ struct exynos_drm_manager {
 	struct list_head list;
 	enum exynos_drm_output_type type;
 	struct drm_device *drm_dev;
+	struct drm_crtc *crtc;
 	int pipe;
 	struct exynos_drm_manager_ops *ops;
 	void *ctx;
@@ -254,6 +255,7 @@ struct drm_exynos_file_private {
  *	otherwise default one.
  * @da_space_size: size of device address space.
  *	if 0 then default value is used for it.
+ * @pipe: the pipe number for this crtc/manager.
  */
 struct exynos_drm_private {
 	struct drm_fb_helper *fb_helper;
@@ -271,6 +273,8 @@ struct exynos_drm_private {
 
 	unsigned long da_start;
 	unsigned long da_space_size;
+
+	unsigned int pipe;
 };
 
 /*
@@ -281,11 +285,11 @@ struct exynos_drm_private {
  * @drm_dev: pointer to drm_device and this pointer would be set
  *	when sub driver calls exynos_drm_subdrv_register().
  * @manager: subdrv has its own manager to control a hardware appropriately
- *	and we can access a hardware drawing on this manager.
+ *     and we can access a hardware drawing on this manager.
  * @probe: this callback would be called by exynos drm driver after
- *	subdrv is registered to it.
+ *     subdrv is registered to it.
  * @remove: this callback is used to release resources created
- *	by probe callback.
+ *     by probe callback.
  * @open: this would be called with drm device file open.
  * @close: this would be called with drm device file close.
  */
@@ -302,39 +306,14 @@ struct exynos_drm_subdrv {
 			struct drm_file *file);
 };
 
-/*
- * this function calls a probe callback registered to sub driver list and
- * create its own encoder and connector and then set drm_device object
- * to global one.
- */
-int exynos_drm_device_register(struct drm_device *dev);
-/*
- * this function calls a remove callback registered to sub driver list and
- * destroy its own encoder and connetor.
- */
-int exynos_drm_device_unregister(struct drm_device *dev);
-
-int exynos_drm_initialize_managers(struct drm_device *dev);
-void exynos_drm_remove_managers(struct drm_device *dev);
-int exynos_drm_initialize_displays(struct drm_device *dev);
-void exynos_drm_remove_displays(struct drm_device *dev);
-
-int exynos_drm_manager_register(struct exynos_drm_manager *manager);
-int exynos_drm_manager_unregister(struct exynos_drm_manager *manager);
-int exynos_drm_display_register(struct exynos_drm_display *display);
-int exynos_drm_display_unregister(struct exynos_drm_display *display);
-
-/*
- * this function would be called by sub drivers such as display controller
- * or hdmi driver to register this sub driver object to exynos drm driver
- * and when a sub driver is registered to exynos drm driver a probe callback
- * of the sub driver is called and creates its own encoder and connector.
- */
+ /* This function would be called by non kms drivers such as g2d and ipp. */
 int exynos_drm_subdrv_register(struct exynos_drm_subdrv *drm_subdrv);
 
 /* this function removes subdrv list from exynos drm driver */
 int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *drm_subdrv);
 
+int exynos_drm_device_subdrv_probe(struct drm_device *dev);
+int exynos_drm_device_subdrv_remove(struct drm_device *dev);
 int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file);
 void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file);
 
@@ -360,18 +339,40 @@ int exynos_platform_device_ipp_register(void);
 void exynos_platform_device_ipp_unregister(void);
 
 #ifdef CONFIG_DRM_EXYNOS_DPI
-int exynos_dpi_probe(struct device *dev);
+struct exynos_drm_display * exynos_dpi_probe(struct device *dev);
 int exynos_dpi_remove(struct device *dev);
 #else
-static inline int exynos_dpi_probe(struct device *dev) { return 0; }
+static inline struct exynos_drm_display *
+exynos_dpi_probe(struct device *dev) { return NULL; }
 static inline int exynos_dpi_remove(struct device *dev) { return 0; }
 #endif
 
+/*
+ * this function registers exynos drm vidi platform device/driver.
+ */
+int exynos_drm_probe_vidi(void);
+
+/*
+ * this function unregister exynos drm vidi platform device/driver.
+ */
+void exynos_drm_remove_vidi(void);
+
+/* This function creates a encoder and a connector, and initializes them. */
+int exynos_drm_create_enc_conn(struct drm_device *dev,
+				struct exynos_drm_display *display);
+
+int exynos_drm_component_add(struct device *dev,
+				enum exynos_drm_device_type dev_type,
+				enum exynos_drm_output_type out_type);
+
+void exynos_drm_component_del(struct device *dev,
+				enum exynos_drm_device_type dev_type);
+
+extern struct platform_driver fimd_driver;
 extern struct platform_driver dp_driver;
 extern struct platform_driver dsi_driver;
-extern struct platform_driver fimd_driver;
-extern struct platform_driver hdmi_driver;
 extern struct platform_driver mixer_driver;
+extern struct platform_driver hdmi_driver;
 extern struct platform_driver exynos_drm_common_hdmi_driver;
 extern struct platform_driver vidi_driver;
 extern struct platform_driver g2d_driver;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 4ac43818756..6302aa64f6c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -19,6 +19,7 @@
 #include <linux/irq.h>
 #include <linux/phy/phy.h>
 #include <linux/regulator/consumer.h>
+#include <linux/component.h>
 
 #include <video/mipi_display.h>
 #include <video/videomode.h>
@@ -1378,16 +1379,60 @@ end:
 	return ret;
 }
 
+static int exynos_dsi_bind(struct device *dev, struct device *master,
+				void *data)
+{
+	struct drm_device *drm_dev = data;
+	struct exynos_dsi *dsi;
+	int ret;
+
+	ret = exynos_drm_create_enc_conn(drm_dev, &exynos_dsi_display);
+	if (ret) {
+		DRM_ERROR("Encoder create [%d] failed with %d\n",
+				exynos_dsi_display.type, ret);
+		return ret;
+	}
+
+	dsi = exynos_dsi_display.ctx;
+
+	return mipi_dsi_host_register(&dsi->dsi_host);
+}
+
+static void exynos_dsi_unbind(struct device *dev, struct device *master,
+				void *data)
+{
+	struct exynos_dsi *dsi = exynos_dsi_display.ctx;
+	struct drm_encoder *encoder = dsi->encoder;
+
+	exynos_dsi_dpms(&exynos_dsi_display, DRM_MODE_DPMS_OFF);
+
+	mipi_dsi_host_unregister(&dsi->dsi_host);
+
+	encoder->funcs->destroy(encoder);
+	drm_connector_cleanup(&dsi->connector);
+}
+
+static const struct component_ops exynos_dsi_component_ops = {
+	.bind	= exynos_dsi_bind,
+	.unbind	= exynos_dsi_unbind,
+};
+
 static int exynos_dsi_probe(struct platform_device *pdev)
 {
 	struct resource *res;
 	struct exynos_dsi *dsi;
 	int ret;
 
+	ret = exynos_drm_component_add(&pdev->dev, EXYNOS_DEVICE_TYPE_CONNECTOR,
+					exynos_dsi_display.type);
+	if (ret)
+		return ret;
+
 	dsi = devm_kzalloc(&pdev->dev, sizeof(*dsi), GFP_KERNEL);
 	if (!dsi) {
 		dev_err(&pdev->dev, "failed to allocate dsi object.\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_del_component;
 	}
 
 	init_completion(&dsi->completed);
@@ -1401,7 +1446,7 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 
 	ret = exynos_dsi_parse_dt(dsi);
 	if (ret)
-		return ret;
+		goto err_del_component;
 
 	dsi->supplies[0].supply = "vddcore";
 	dsi->supplies[1].supply = "vddio";
@@ -1415,32 +1460,37 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 	dsi->pll_clk = devm_clk_get(&pdev->dev, "pll_clk");
 	if (IS_ERR(dsi->pll_clk)) {
 		dev_info(&pdev->dev, "failed to get dsi pll input clock\n");
-		return -EPROBE_DEFER;
+		ret = PTR_ERR(dsi->pll_clk);
+		goto err_del_component;
 	}
 
 	dsi->bus_clk = devm_clk_get(&pdev->dev, "bus_clk");
 	if (IS_ERR(dsi->bus_clk)) {
 		dev_info(&pdev->dev, "failed to get dsi bus clock\n");
-		return -EPROBE_DEFER;
+		ret = PTR_ERR(dsi->bus_clk);
+		goto err_del_component;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	dsi->reg_base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(dsi->reg_base)) {
 		dev_err(&pdev->dev, "failed to remap io region\n");
-		return PTR_ERR(dsi->reg_base);
+		ret = PTR_ERR(dsi->reg_base);
+		goto err_del_component;
 	}
 
 	dsi->phy = devm_phy_get(&pdev->dev, "dsim");
 	if (IS_ERR(dsi->phy)) {
 		dev_info(&pdev->dev, "failed to get dsim phy\n");
-		return -EPROBE_DEFER;
+		ret = PTR_ERR(dsi->phy);
+		goto err_del_component;
 	}
 
 	dsi->irq = platform_get_irq(pdev, 0);
 	if (dsi->irq < 0) {
 		dev_err(&pdev->dev, "failed to request dsi irq resource\n");
-		return dsi->irq;
+		ret = dsi->irq;
+		goto err_del_component;
 	}
 
 	irq_set_status_flags(dsi->irq, IRQ_NOAUTOEN);
@@ -1449,58 +1499,31 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 					dev_name(&pdev->dev), dsi);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to request dsi irq\n");
-		return ret;
+		goto err_del_component;
 	}
 
 	exynos_dsi_display.ctx = dsi;
 
 	platform_set_drvdata(pdev, &exynos_dsi_display);
-	exynos_drm_display_register(&exynos_dsi_display);
-
-	return mipi_dsi_host_register(&dsi->dsi_host);
-}
-
-static int exynos_dsi_remove(struct platform_device *pdev)
-{
-	struct exynos_dsi *dsi = exynos_dsi_display.ctx;
-
-	exynos_dsi_dpms(&exynos_dsi_display, DRM_MODE_DPMS_OFF);
-
-	exynos_drm_display_unregister(&exynos_dsi_display);
-	mipi_dsi_host_unregister(&dsi->dsi_host);
-
-	return 0;
-}
 
-#if CONFIG_PM_SLEEP
-static int exynos_dsi_resume(struct device *dev)
-{
-	struct exynos_dsi *dsi = exynos_dsi_display.ctx;
+	ret = component_add(&pdev->dev, &exynos_dsi_component_ops);
+	if (ret)
+		goto err_del_component;
 
-	if (dsi->state & DSIM_STATE_ENABLED) {
-		dsi->state &= ~DSIM_STATE_ENABLED;
-		exynos_dsi_enable(dsi);
-	}
+	return ret;
 
-	return 0;
+err_del_component:
+	exynos_drm_component_del(&pdev->dev, EXYNOS_DEVICE_TYPE_CONNECTOR);
+	return ret;
 }
 
-static int exynos_dsi_suspend(struct device *dev)
+static int exynos_dsi_remove(struct platform_device *pdev)
 {
-	struct exynos_dsi *dsi = exynos_dsi_display.ctx;
-
-	if (dsi->state & DSIM_STATE_ENABLED) {
-		exynos_dsi_disable(dsi);
-		dsi->state |= DSIM_STATE_ENABLED;
-	}
+	component_del(&pdev->dev, &exynos_dsi_component_ops);
+	exynos_drm_component_del(&pdev->dev, EXYNOS_DEVICE_TYPE_CONNECTOR);
 
 	return 0;
 }
-#endif
-
-static const struct dev_pm_ops exynos_dsi_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(exynos_dsi_suspend, exynos_dsi_resume)
-};
 
 static struct of_device_id exynos_dsi_of_match[] = {
 	{ .compatible = "samsung,exynos4210-mipi-dsi" },
@@ -1513,7 +1536,6 @@ struct platform_driver dsi_driver = {
 	.driver = {
 		   .name = "exynos-dsi",
 		   .owner = THIS_MODULE,
-		   .pm = &exynos_dsi_pm_ops,
 		   .of_match_table = exynos_dsi_of_match,
 	},
 };
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index addbf7536da..d771b467cf0 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -121,16 +121,8 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper,
 	offset = fbi->var.xoffset * (fb->bits_per_pixel >> 3);
 	offset += fbi->var.yoffset * fb->pitches[0];
 
-	dev->mode_config.fb_base = (resource_size_t)buffer->dma_addr;
 	fbi->screen_base = buffer->kvaddr + offset;
-	if (is_drm_iommu_supported(dev))
-		fbi->fix.smem_start = (unsigned long)
-			(page_to_phys(sg_page(buffer->sgt->sgl)) + offset);
-	else
-		fbi->fix.smem_start = (unsigned long)buffer->dma_addr;
-
 	fbi->screen_size = size;
-	fbi->fix.smem_len = size;
 
 	return 0;
 }
@@ -237,7 +229,7 @@ static struct drm_fb_helper_funcs exynos_drm_fb_helper_funcs = {
 	.fb_probe =	exynos_drm_fbdev_create,
 };
 
-bool exynos_drm_fbdev_is_anything_connected(struct drm_device *dev)
+static bool exynos_drm_fbdev_is_anything_connected(struct drm_device *dev)
 {
 	struct drm_connector *connector;
 	bool ret = false;
@@ -375,7 +367,5 @@ void exynos_drm_fbdev_restore_mode(struct drm_device *dev)
 	if (!private || !private->fb_helper)
 		return;
 
-	drm_modeset_lock_all(dev);
-	drm_fb_helper_restore_fbdev_mode(private->fb_helper);
-	drm_modeset_unlock_all(dev);
+	drm_fb_helper_restore_fbdev_mode_unlocked(private->fb_helper);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 30d76b2ff9c..831dde9034c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -18,6 +18,7 @@
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
+#include <linux/spinlock.h>
 
 #include <drm/drmP.h>
 #include <drm/exynos_drm.h>
@@ -57,7 +58,6 @@
 #define FIMC_SHFACTOR	10
 #define FIMC_BUF_STOP	1
 #define FIMC_BUF_START	2
-#define FIMC_REG_SZ		32
 #define FIMC_WIDTH_ITU_709	1280
 #define FIMC_REFRESH_MAX	60
 #define FIMC_REFRESH_MIN	12
@@ -69,9 +69,6 @@
 #define get_fimc_context(dev)	platform_get_drvdata(to_platform_device(dev))
 #define get_ctx_from_ippdrv(ippdrv)	container_of(ippdrv,\
 					struct fimc_context, ippdrv);
-#define fimc_read(offset)		readl(ctx->regs + (offset))
-#define fimc_write(cfg, offset)	writel(cfg, ctx->regs + (offset))
-
 enum fimc_wb {
 	FIMC_WB_NONE,
 	FIMC_WB_A,
@@ -161,7 +158,7 @@ struct fimc_context {
 	struct exynos_drm_ippdrv	ippdrv;
 	struct resource	*regs_res;
 	void __iomem	*regs;
-	struct mutex	lock;
+	spinlock_t	lock;
 	struct clk	*clocks[FIMC_CLKS_MAX];
 	u32		clk_frequency;
 	struct regmap	*sysreg;
@@ -172,39 +169,53 @@ struct fimc_context {
 	bool	suspended;
 };
 
+static u32 fimc_read(struct fimc_context *ctx, u32 reg)
+{
+	return readl(ctx->regs + reg);
+}
+
+static void fimc_write(struct fimc_context *ctx, u32 val, u32 reg)
+{
+	writel(val, ctx->regs + reg);
+}
+
+static void fimc_set_bits(struct fimc_context *ctx, u32 reg, u32 bits)
+{
+	void __iomem *r = ctx->regs + reg;
+
+	writel(readl(r) | bits, r);
+}
+
+static void fimc_clear_bits(struct fimc_context *ctx, u32 reg, u32 bits)
+{
+	void __iomem *r = ctx->regs + reg;
+
+	writel(readl(r) & ~bits, r);
+}
+
 static void fimc_sw_reset(struct fimc_context *ctx)
 {
 	u32 cfg;
 
 	/* stop dma operation */
-	cfg = fimc_read(EXYNOS_CISTATUS);
-	if (EXYNOS_CISTATUS_GET_ENVID_STATUS(cfg)) {
-		cfg = fimc_read(EXYNOS_MSCTRL);
-		cfg &= ~EXYNOS_MSCTRL_ENVID;
-		fimc_write(cfg, EXYNOS_MSCTRL);
-	}
+	cfg = fimc_read(ctx, EXYNOS_CISTATUS);
+	if (EXYNOS_CISTATUS_GET_ENVID_STATUS(cfg))
+		fimc_clear_bits(ctx, EXYNOS_MSCTRL, EXYNOS_MSCTRL_ENVID);
 
-	cfg = fimc_read(EXYNOS_CISRCFMT);
-	cfg |= EXYNOS_CISRCFMT_ITU601_8BIT;
-	fimc_write(cfg, EXYNOS_CISRCFMT);
+	fimc_set_bits(ctx, EXYNOS_CISRCFMT, EXYNOS_CISRCFMT_ITU601_8BIT);
 
 	/* disable image capture */
-	cfg = fimc_read(EXYNOS_CIIMGCPT);
-	cfg &= ~(EXYNOS_CIIMGCPT_IMGCPTEN_SC | EXYNOS_CIIMGCPT_IMGCPTEN);
-	fimc_write(cfg, EXYNOS_CIIMGCPT);
+	fimc_clear_bits(ctx, EXYNOS_CIIMGCPT,
+		EXYNOS_CIIMGCPT_IMGCPTEN_SC | EXYNOS_CIIMGCPT_IMGCPTEN);
 
 	/* s/w reset */
-	cfg = fimc_read(EXYNOS_CIGCTRL);
-	cfg |= (EXYNOS_CIGCTRL_SWRST);
-	fimc_write(cfg, EXYNOS_CIGCTRL);
+	fimc_set_bits(ctx, EXYNOS_CIGCTRL, EXYNOS_CIGCTRL_SWRST);
 
 	/* s/w reset complete */
-	cfg = fimc_read(EXYNOS_CIGCTRL);
-	cfg &= ~EXYNOS_CIGCTRL_SWRST;
-	fimc_write(cfg, EXYNOS_CIGCTRL);
+	fimc_clear_bits(ctx, EXYNOS_CIGCTRL, EXYNOS_CIGCTRL_SWRST);
 
 	/* reset sequence */
-	fimc_write(0x0, EXYNOS_CIFCNTSEQ);
+	fimc_write(ctx, 0x0, EXYNOS_CIFCNTSEQ);
 }
 
 static int fimc_set_camblk_fimd0_wb(struct fimc_context *ctx)
@@ -220,7 +231,7 @@ static void fimc_set_type_ctrl(struct fimc_context *ctx, enum fimc_wb wb)
 
 	DRM_DEBUG_KMS("wb[%d]\n", wb);
 
-	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CIGCTRL);
 	cfg &= ~(EXYNOS_CIGCTRL_TESTPATTERN_MASK |
 		EXYNOS_CIGCTRL_SELCAM_ITU_MASK |
 		EXYNOS_CIGCTRL_SELCAM_MIPI_MASK |
@@ -246,7 +257,7 @@ static void fimc_set_type_ctrl(struct fimc_context *ctx, enum fimc_wb wb)
 		break;
 	}
 
-	fimc_write(cfg, EXYNOS_CIGCTRL);
+	fimc_write(ctx, cfg, EXYNOS_CIGCTRL);
 }
 
 static void fimc_set_polarity(struct fimc_context *ctx,
@@ -259,7 +270,7 @@ static void fimc_set_polarity(struct fimc_context *ctx,
 	DRM_DEBUG_KMS("inv_href[%d]inv_hsync[%d]\n",
 		pol->inv_href, pol->inv_hsync);
 
-	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CIGCTRL);
 	cfg &= ~(EXYNOS_CIGCTRL_INVPOLPCLK | EXYNOS_CIGCTRL_INVPOLVSYNC |
 		 EXYNOS_CIGCTRL_INVPOLHREF | EXYNOS_CIGCTRL_INVPOLHSYNC);
 
@@ -272,7 +283,7 @@ static void fimc_set_polarity(struct fimc_context *ctx,
 	if (pol->inv_hsync)
 		cfg |= EXYNOS_CIGCTRL_INVPOLHSYNC;
 
-	fimc_write(cfg, EXYNOS_CIGCTRL);
+	fimc_write(ctx, cfg, EXYNOS_CIGCTRL);
 }
 
 static void fimc_handle_jpeg(struct fimc_context *ctx, bool enable)
@@ -281,70 +292,54 @@ static void fimc_handle_jpeg(struct fimc_context *ctx, bool enable)
 
 	DRM_DEBUG_KMS("enable[%d]\n", enable);
 
-	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CIGCTRL);
 	if (enable)
 		cfg |= EXYNOS_CIGCTRL_CAM_JPEG;
 	else
 		cfg &= ~EXYNOS_CIGCTRL_CAM_JPEG;
 
-	fimc_write(cfg, EXYNOS_CIGCTRL);
+	fimc_write(ctx, cfg, EXYNOS_CIGCTRL);
 }
 
-static void fimc_handle_irq(struct fimc_context *ctx, bool enable,
-		bool overflow, bool level)
+static void fimc_mask_irq(struct fimc_context *ctx, bool enable)
 {
 	u32 cfg;
 
-	DRM_DEBUG_KMS("enable[%d]overflow[%d]level[%d]\n",
-			enable, overflow, level);
+	DRM_DEBUG_KMS("enable[%d]\n", enable);
 
-	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CIGCTRL);
 	if (enable) {
-		cfg &= ~(EXYNOS_CIGCTRL_IRQ_OVFEN | EXYNOS_CIGCTRL_IRQ_LEVEL);
-		cfg |= EXYNOS_CIGCTRL_IRQ_ENABLE;
-		if (overflow)
-			cfg |= EXYNOS_CIGCTRL_IRQ_OVFEN;
-		if (level)
-			cfg |= EXYNOS_CIGCTRL_IRQ_LEVEL;
+		cfg &= ~EXYNOS_CIGCTRL_IRQ_OVFEN;
+		cfg |= EXYNOS_CIGCTRL_IRQ_ENABLE | EXYNOS_CIGCTRL_IRQ_LEVEL;
 	} else
-		cfg &= ~(EXYNOS_CIGCTRL_IRQ_OVFEN | EXYNOS_CIGCTRL_IRQ_ENABLE);
-
-	fimc_write(cfg, EXYNOS_CIGCTRL);
+		cfg &= ~EXYNOS_CIGCTRL_IRQ_ENABLE;
+	fimc_write(ctx, cfg, EXYNOS_CIGCTRL);
 }
 
 static void fimc_clear_irq(struct fimc_context *ctx)
 {
-	u32 cfg;
-
-	cfg = fimc_read(EXYNOS_CIGCTRL);
-	cfg |= EXYNOS_CIGCTRL_IRQ_CLR;
-	fimc_write(cfg, EXYNOS_CIGCTRL);
+	fimc_set_bits(ctx, EXYNOS_CIGCTRL, EXYNOS_CIGCTRL_IRQ_CLR);
 }
 
 static bool fimc_check_ovf(struct fimc_context *ctx)
 {
 	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	u32 cfg, status, flag;
+	u32 status, flag;
 
-	status = fimc_read(EXYNOS_CISTATUS);
+	status = fimc_read(ctx, EXYNOS_CISTATUS);
 	flag = EXYNOS_CISTATUS_OVFIY | EXYNOS_CISTATUS_OVFICB |
 		EXYNOS_CISTATUS_OVFICR;
 
 	DRM_DEBUG_KMS("flag[0x%x]\n", flag);
 
 	if (status & flag) {
-		cfg = fimc_read(EXYNOS_CIWDOFST);
-		cfg |= (EXYNOS_CIWDOFST_CLROVFIY | EXYNOS_CIWDOFST_CLROVFICB |
+		fimc_set_bits(ctx, EXYNOS_CIWDOFST,
+			EXYNOS_CIWDOFST_CLROVFIY | EXYNOS_CIWDOFST_CLROVFICB |
 			EXYNOS_CIWDOFST_CLROVFICR);
-
-		fimc_write(cfg, EXYNOS_CIWDOFST);
-
-		cfg = fimc_read(EXYNOS_CIWDOFST);
-		cfg &= ~(EXYNOS_CIWDOFST_CLROVFIY | EXYNOS_CIWDOFST_CLROVFICB |
+		fimc_clear_bits(ctx, EXYNOS_CIWDOFST,
+			EXYNOS_CIWDOFST_CLROVFIY | EXYNOS_CIWDOFST_CLROVFICB |
 			EXYNOS_CIWDOFST_CLROVFICR);
 
-		fimc_write(cfg, EXYNOS_CIWDOFST);
-
 		dev_err(ippdrv->dev, "occurred overflow at %d, status 0x%x.\n",
 			ctx->id, status);
 		return true;
@@ -357,7 +352,7 @@ static bool fimc_check_frame_end(struct fimc_context *ctx)
 {
 	u32 cfg;
 
-	cfg = fimc_read(EXYNOS_CISTATUS);
+	cfg = fimc_read(ctx, EXYNOS_CISTATUS);
 
 	DRM_DEBUG_KMS("cfg[0x%x]\n", cfg);
 
@@ -365,7 +360,7 @@ static bool fimc_check_frame_end(struct fimc_context *ctx)
 		return false;
 
 	cfg &= ~(EXYNOS_CISTATUS_FRAMEEND);
-	fimc_write(cfg, EXYNOS_CISTATUS);
+	fimc_write(ctx, cfg, EXYNOS_CISTATUS);
 
 	return true;
 }
@@ -375,7 +370,7 @@ static int fimc_get_buf_id(struct fimc_context *ctx)
 	u32 cfg;
 	int frame_cnt, buf_id;
 
-	cfg = fimc_read(EXYNOS_CISTATUS2);
+	cfg = fimc_read(ctx, EXYNOS_CISTATUS2);
 	frame_cnt = EXYNOS_CISTATUS2_GET_FRAMECOUNT_BEFORE(cfg);
 
 	if (frame_cnt == 0)
@@ -402,13 +397,13 @@ static void fimc_handle_lastend(struct fimc_context *ctx, bool enable)
 
 	DRM_DEBUG_KMS("enable[%d]\n", enable);
 
-	cfg = fimc_read(EXYNOS_CIOCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CIOCTRL);
 	if (enable)
 		cfg |= EXYNOS_CIOCTRL_LASTENDEN;
 	else
 		cfg &= ~EXYNOS_CIOCTRL_LASTENDEN;
 
-	fimc_write(cfg, EXYNOS_CIOCTRL);
+	fimc_write(ctx, cfg, EXYNOS_CIOCTRL);
 }
 
 
@@ -420,18 +415,18 @@ static int fimc_src_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
 
 	/* RGB */
-	cfg = fimc_read(EXYNOS_CISCCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CISCCTRL);
 	cfg &= ~EXYNOS_CISCCTRL_INRGB_FMT_RGB_MASK;
 
 	switch (fmt) {
 	case DRM_FORMAT_RGB565:
 		cfg |= EXYNOS_CISCCTRL_INRGB_FMT_RGB565;
-		fimc_write(cfg, EXYNOS_CISCCTRL);
+		fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
 		return 0;
 	case DRM_FORMAT_RGB888:
 	case DRM_FORMAT_XRGB8888:
 		cfg |= EXYNOS_CISCCTRL_INRGB_FMT_RGB888;
-		fimc_write(cfg, EXYNOS_CISCCTRL);
+		fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
 		return 0;
 	default:
 		/* bypass */
@@ -439,7 +434,7 @@ static int fimc_src_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 	}
 
 	/* YUV */
-	cfg = fimc_read(EXYNOS_MSCTRL);
+	cfg = fimc_read(ctx, EXYNOS_MSCTRL);
 	cfg &= ~(EXYNOS_MSCTRL_ORDER2P_SHIFT_MASK |
 		EXYNOS_MSCTRL_C_INT_IN_2PLANE |
 		EXYNOS_MSCTRL_ORDER422_YCBYCR);
@@ -479,7 +474,7 @@ static int fimc_src_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 		return -EINVAL;
 	}
 
-	fimc_write(cfg, EXYNOS_MSCTRL);
+	fimc_write(ctx, cfg, EXYNOS_MSCTRL);
 
 	return 0;
 }
@@ -492,7 +487,7 @@ static int fimc_src_set_fmt(struct device *dev, u32 fmt)
 
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
 
-	cfg = fimc_read(EXYNOS_MSCTRL);
+	cfg = fimc_read(ctx, EXYNOS_MSCTRL);
 	cfg &= ~EXYNOS_MSCTRL_INFORMAT_RGB;
 
 	switch (fmt) {
@@ -527,9 +522,9 @@ static int fimc_src_set_fmt(struct device *dev, u32 fmt)
 		return -EINVAL;
 	}
 
-	fimc_write(cfg, EXYNOS_MSCTRL);
+	fimc_write(ctx, cfg, EXYNOS_MSCTRL);
 
-	cfg = fimc_read(EXYNOS_CIDMAPARAM);
+	cfg = fimc_read(ctx, EXYNOS_CIDMAPARAM);
 	cfg &= ~EXYNOS_CIDMAPARAM_R_MODE_MASK;
 
 	if (fmt == DRM_FORMAT_NV12MT)
@@ -537,7 +532,7 @@ static int fimc_src_set_fmt(struct device *dev, u32 fmt)
 	else
 		cfg |= EXYNOS_CIDMAPARAM_R_MODE_LINEAR;
 
-	fimc_write(cfg, EXYNOS_CIDMAPARAM);
+	fimc_write(ctx, cfg, EXYNOS_CIDMAPARAM);
 
 	return fimc_src_set_fmt_order(ctx, fmt);
 }
@@ -552,11 +547,11 @@ static int fimc_src_set_transf(struct device *dev,
 
 	DRM_DEBUG_KMS("degree[%d]flip[0x%x]\n", degree, flip);
 
-	cfg1 = fimc_read(EXYNOS_MSCTRL);
+	cfg1 = fimc_read(ctx, EXYNOS_MSCTRL);
 	cfg1 &= ~(EXYNOS_MSCTRL_FLIP_X_MIRROR |
 		EXYNOS_MSCTRL_FLIP_Y_MIRROR);
 
-	cfg2 = fimc_read(EXYNOS_CITRGFMT);
+	cfg2 = fimc_read(ctx, EXYNOS_CITRGFMT);
 	cfg2 &= ~EXYNOS_CITRGFMT_INROT90_CLOCKWISE;
 
 	switch (degree) {
@@ -595,8 +590,8 @@ static int fimc_src_set_transf(struct device *dev,
 		return -EINVAL;
 	}
 
-	fimc_write(cfg1, EXYNOS_MSCTRL);
-	fimc_write(cfg2, EXYNOS_CITRGFMT);
+	fimc_write(ctx, cfg1, EXYNOS_MSCTRL);
+	fimc_write(ctx, cfg2, EXYNOS_CITRGFMT);
 	*swap = (cfg2 & EXYNOS_CITRGFMT_INROT90_CLOCKWISE) ? 1 : 0;
 
 	return 0;
@@ -621,17 +616,17 @@ static int fimc_set_window(struct fimc_context *ctx,
 	 * set window offset 1, 2 size
 	 * check figure 43-21 in user manual
 	 */
-	cfg = fimc_read(EXYNOS_CIWDOFST);
+	cfg = fimc_read(ctx, EXYNOS_CIWDOFST);
 	cfg &= ~(EXYNOS_CIWDOFST_WINHOROFST_MASK |
 		EXYNOS_CIWDOFST_WINVEROFST_MASK);
 	cfg |= (EXYNOS_CIWDOFST_WINHOROFST(h1) |
 		EXYNOS_CIWDOFST_WINVEROFST(v1));
 	cfg |= EXYNOS_CIWDOFST_WINOFSEN;
-	fimc_write(cfg, EXYNOS_CIWDOFST);
+	fimc_write(ctx, cfg, EXYNOS_CIWDOFST);
 
 	cfg = (EXYNOS_CIWDOFST2_WINHOROFST2(h2) |
 		EXYNOS_CIWDOFST2_WINVEROFST2(v2));
-	fimc_write(cfg, EXYNOS_CIWDOFST2);
+	fimc_write(ctx, cfg, EXYNOS_CIWDOFST2);
 
 	return 0;
 }
@@ -651,7 +646,7 @@ static int fimc_src_set_size(struct device *dev, int swap,
 	cfg = (EXYNOS_ORGISIZE_HORIZONTAL(img_sz.hsize) |
 		EXYNOS_ORGISIZE_VERTICAL(img_sz.vsize));
 
-	fimc_write(cfg, EXYNOS_ORGISIZE);
+	fimc_write(ctx, cfg, EXYNOS_ORGISIZE);
 
 	DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]\n", pos->x, pos->y, pos->w, pos->h);
 
@@ -663,12 +658,12 @@ static int fimc_src_set_size(struct device *dev, int swap,
 	}
 
 	/* set input DMA image size */
-	cfg = fimc_read(EXYNOS_CIREAL_ISIZE);
+	cfg = fimc_read(ctx, EXYNOS_CIREAL_ISIZE);
 	cfg &= ~(EXYNOS_CIREAL_ISIZE_HEIGHT_MASK |
 		EXYNOS_CIREAL_ISIZE_WIDTH_MASK);
 	cfg |= (EXYNOS_CIREAL_ISIZE_WIDTH(img_pos.w) |
 		EXYNOS_CIREAL_ISIZE_HEIGHT(img_pos.h));
-	fimc_write(cfg, EXYNOS_CIREAL_ISIZE);
+	fimc_write(ctx, cfg, EXYNOS_CIREAL_ISIZE);
 
 	/*
 	 * set input FIFO image size
@@ -677,18 +672,18 @@ static int fimc_src_set_size(struct device *dev, int swap,
 	cfg = (EXYNOS_CISRCFMT_ITU601_8BIT |
 		EXYNOS_CISRCFMT_SOURCEHSIZE(img_sz.hsize) |
 		EXYNOS_CISRCFMT_SOURCEVSIZE(img_sz.vsize));
-	fimc_write(cfg, EXYNOS_CISRCFMT);
+	fimc_write(ctx, cfg, EXYNOS_CISRCFMT);
 
 	/* offset Y(RGB), Cb, Cr */
 	cfg = (EXYNOS_CIIYOFF_HORIZONTAL(img_pos.x) |
 		EXYNOS_CIIYOFF_VERTICAL(img_pos.y));
-	fimc_write(cfg, EXYNOS_CIIYOFF);
+	fimc_write(ctx, cfg, EXYNOS_CIIYOFF);
 	cfg = (EXYNOS_CIICBOFF_HORIZONTAL(img_pos.x) |
 		EXYNOS_CIICBOFF_VERTICAL(img_pos.y));
-	fimc_write(cfg, EXYNOS_CIICBOFF);
+	fimc_write(ctx, cfg, EXYNOS_CIICBOFF);
 	cfg = (EXYNOS_CIICROFF_HORIZONTAL(img_pos.x) |
 		EXYNOS_CIICROFF_VERTICAL(img_pos.y));
-	fimc_write(cfg, EXYNOS_CIICROFF);
+	fimc_write(ctx, cfg, EXYNOS_CIICROFF);
 
 	return fimc_set_window(ctx, &img_pos, &img_sz);
 }
@@ -722,25 +717,25 @@ static int fimc_src_set_addr(struct device *dev,
 	switch (buf_type) {
 	case IPP_BUF_ENQUEUE:
 		config = &property->config[EXYNOS_DRM_OPS_SRC];
-		fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_Y],
+		fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_Y],
 			EXYNOS_CIIYSA(buf_id));
 
 		if (config->fmt == DRM_FORMAT_YVU420) {
-			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
+			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
 				EXYNOS_CIICBSA(buf_id));
-			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
+			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
 				EXYNOS_CIICRSA(buf_id));
 		} else {
-			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
+			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
 				EXYNOS_CIICBSA(buf_id));
-			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
+			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
 				EXYNOS_CIICRSA(buf_id));
 		}
 		break;
 	case IPP_BUF_DEQUEUE:
-		fimc_write(0x0, EXYNOS_CIIYSA(buf_id));
-		fimc_write(0x0, EXYNOS_CIICBSA(buf_id));
-		fimc_write(0x0, EXYNOS_CIICRSA(buf_id));
+		fimc_write(ctx, 0x0, EXYNOS_CIIYSA(buf_id));
+		fimc_write(ctx, 0x0, EXYNOS_CIICBSA(buf_id));
+		fimc_write(ctx, 0x0, EXYNOS_CIICRSA(buf_id));
 		break;
 	default:
 		/* bypass */
@@ -765,22 +760,22 @@ static int fimc_dst_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
 
 	/* RGB */
-	cfg = fimc_read(EXYNOS_CISCCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CISCCTRL);
 	cfg &= ~EXYNOS_CISCCTRL_OUTRGB_FMT_RGB_MASK;
 
 	switch (fmt) {
 	case DRM_FORMAT_RGB565:
 		cfg |= EXYNOS_CISCCTRL_OUTRGB_FMT_RGB565;
-		fimc_write(cfg, EXYNOS_CISCCTRL);
+		fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
 		return 0;
 	case DRM_FORMAT_RGB888:
 		cfg |= EXYNOS_CISCCTRL_OUTRGB_FMT_RGB888;
-		fimc_write(cfg, EXYNOS_CISCCTRL);
+		fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
 		return 0;
 	case DRM_FORMAT_XRGB8888:
 		cfg |= (EXYNOS_CISCCTRL_OUTRGB_FMT_RGB888 |
 			EXYNOS_CISCCTRL_EXTRGB_EXTENSION);
-		fimc_write(cfg, EXYNOS_CISCCTRL);
+		fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
 		break;
 	default:
 		/* bypass */
@@ -788,7 +783,7 @@ static int fimc_dst_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 	}
 
 	/* YUV */
-	cfg = fimc_read(EXYNOS_CIOCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CIOCTRL);
 	cfg &= ~(EXYNOS_CIOCTRL_ORDER2P_MASK |
 		EXYNOS_CIOCTRL_ORDER422_MASK |
 		EXYNOS_CIOCTRL_YCBCR_PLANE_MASK);
@@ -830,7 +825,7 @@ static int fimc_dst_set_fmt_order(struct fimc_context *ctx, u32 fmt)
 		return -EINVAL;
 	}
 
-	fimc_write(cfg, EXYNOS_CIOCTRL);
+	fimc_write(ctx, cfg, EXYNOS_CIOCTRL);
 
 	return 0;
 }
@@ -843,16 +838,16 @@ static int fimc_dst_set_fmt(struct device *dev, u32 fmt)
 
 	DRM_DEBUG_KMS("fmt[0x%x]\n", fmt);
 
-	cfg = fimc_read(EXYNOS_CIEXTEN);
+	cfg = fimc_read(ctx, EXYNOS_CIEXTEN);
 
 	if (fmt == DRM_FORMAT_AYUV) {
 		cfg |= EXYNOS_CIEXTEN_YUV444_OUT;
-		fimc_write(cfg, EXYNOS_CIEXTEN);
+		fimc_write(ctx, cfg, EXYNOS_CIEXTEN);
 	} else {
 		cfg &= ~EXYNOS_CIEXTEN_YUV444_OUT;
-		fimc_write(cfg, EXYNOS_CIEXTEN);
+		fimc_write(ctx, cfg, EXYNOS_CIEXTEN);
 
-		cfg = fimc_read(EXYNOS_CITRGFMT);
+		cfg = fimc_read(ctx, EXYNOS_CITRGFMT);
 		cfg &= ~EXYNOS_CITRGFMT_OUTFORMAT_MASK;
 
 		switch (fmt) {
@@ -885,10 +880,10 @@ static int fimc_dst_set_fmt(struct device *dev, u32 fmt)
 			return -EINVAL;
 		}
 
-		fimc_write(cfg, EXYNOS_CITRGFMT);
+		fimc_write(ctx, cfg, EXYNOS_CITRGFMT);
 	}
 
-	cfg = fimc_read(EXYNOS_CIDMAPARAM);
+	cfg = fimc_read(ctx, EXYNOS_CIDMAPARAM);
 	cfg &= ~EXYNOS_CIDMAPARAM_W_MODE_MASK;
 
 	if (fmt == DRM_FORMAT_NV12MT)
@@ -896,7 +891,7 @@ static int fimc_dst_set_fmt(struct device *dev, u32 fmt)
 	else
 		cfg |= EXYNOS_CIDMAPARAM_W_MODE_LINEAR;
 
-	fimc_write(cfg, EXYNOS_CIDMAPARAM);
+	fimc_write(ctx, cfg, EXYNOS_CIDMAPARAM);
 
 	return fimc_dst_set_fmt_order(ctx, fmt);
 }
@@ -911,7 +906,7 @@ static int fimc_dst_set_transf(struct device *dev,
 
 	DRM_DEBUG_KMS("degree[%d]flip[0x%x]\n", degree, flip);
 
-	cfg = fimc_read(EXYNOS_CITRGFMT);
+	cfg = fimc_read(ctx, EXYNOS_CITRGFMT);
 	cfg &= ~EXYNOS_CITRGFMT_FLIP_MASK;
 	cfg &= ~EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE;
 
@@ -951,53 +946,23 @@ static int fimc_dst_set_transf(struct device *dev,
 		return -EINVAL;
 	}
 
-	fimc_write(cfg, EXYNOS_CITRGFMT);
+	fimc_write(ctx, cfg, EXYNOS_CITRGFMT);
 	*swap = (cfg & EXYNOS_CITRGFMT_OUTROT90_CLOCKWISE) ? 1 : 0;
 
 	return 0;
 }
 
-static int fimc_get_ratio_shift(u32 src, u32 dst, u32 *ratio, u32 *shift)
-{
-	DRM_DEBUG_KMS("src[%d]dst[%d]\n", src, dst);
-
-	if (src >= dst * 64) {
-		DRM_ERROR("failed to make ratio and shift.\n");
-		return -EINVAL;
-	} else if (src >= dst * 32) {
-		*ratio = 32;
-		*shift = 5;
-	} else if (src >= dst * 16) {
-		*ratio = 16;
-		*shift = 4;
-	} else if (src >= dst * 8) {
-		*ratio = 8;
-		*shift = 3;
-	} else if (src >= dst * 4) {
-		*ratio = 4;
-		*shift = 2;
-	} else if (src >= dst * 2) {
-		*ratio = 2;
-		*shift = 1;
-	} else {
-		*ratio = 1;
-		*shift = 0;
-	}
-
-	return 0;
-}
-
 static int fimc_set_prescaler(struct fimc_context *ctx, struct fimc_scaler *sc,
 		struct drm_exynos_pos *src, struct drm_exynos_pos *dst)
 {
 	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 	u32 cfg, cfg_ext, shfactor;
 	u32 pre_dst_width, pre_dst_height;
-	u32 pre_hratio, hfactor, pre_vratio, vfactor;
+	u32 hfactor, vfactor;
 	int ret = 0;
 	u32 src_w, src_h, dst_w, dst_h;
 
-	cfg_ext = fimc_read(EXYNOS_CITRGFMT);
+	cfg_ext = fimc_read(ctx, EXYNOS_CITRGFMT);
 	if (cfg_ext & EXYNOS_CITRGFMT_INROT90_CLOCKWISE) {
 		src_w = src->h;
 		src_h = src->w;
@@ -1014,24 +979,24 @@ static int fimc_set_prescaler(struct fimc_context *ctx, struct fimc_scaler *sc,
 		dst_h = dst->h;
 	}
 
-	ret = fimc_get_ratio_shift(src_w, dst_w, &pre_hratio, &hfactor);
-	if (ret) {
+	/* fimc_ippdrv_check_property assures that dividers are not null */
+	hfactor = fls(src_w / dst_w / 2);
+	if (hfactor > FIMC_SHFACTOR / 2) {
 		dev_err(ippdrv->dev, "failed to get ratio horizontal.\n");
-		return ret;
+		return -EINVAL;
 	}
 
-	ret = fimc_get_ratio_shift(src_h, dst_h, &pre_vratio, &vfactor);
-	if (ret) {
+	vfactor = fls(src_h / dst_h / 2);
+	if (vfactor > FIMC_SHFACTOR / 2) {
 		dev_err(ippdrv->dev, "failed to get ratio vertical.\n");
-		return ret;
+		return -EINVAL;
 	}
 
-	pre_dst_width = src_w / pre_hratio;
-	pre_dst_height = src_h / pre_vratio;
+	pre_dst_width = src_w >> hfactor;
+	pre_dst_height = src_h >> vfactor;
 	DRM_DEBUG_KMS("pre_dst_width[%d]pre_dst_height[%d]\n",
 		pre_dst_width, pre_dst_height);
-	DRM_DEBUG_KMS("pre_hratio[%d]hfactor[%d]pre_vratio[%d]vfactor[%d]\n",
-		pre_hratio, hfactor, pre_vratio, vfactor);
+	DRM_DEBUG_KMS("hfactor[%d]vfactor[%d]\n", hfactor, vfactor);
 
 	sc->hratio = (src_w << 14) / (dst_w << hfactor);
 	sc->vratio = (src_h << 14) / (dst_h << vfactor);
@@ -1044,13 +1009,13 @@ static int fimc_set_prescaler(struct fimc_context *ctx, struct fimc_scaler *sc,
 	DRM_DEBUG_KMS("shfactor[%d]\n", shfactor);
 
 	cfg = (EXYNOS_CISCPRERATIO_SHFACTOR(shfactor) |
-		EXYNOS_CISCPRERATIO_PREHORRATIO(pre_hratio) |
-		EXYNOS_CISCPRERATIO_PREVERRATIO(pre_vratio));
-	fimc_write(cfg, EXYNOS_CISCPRERATIO);
+		EXYNOS_CISCPRERATIO_PREHORRATIO(1 << hfactor) |
+		EXYNOS_CISCPRERATIO_PREVERRATIO(1 << vfactor));
+	fimc_write(ctx, cfg, EXYNOS_CISCPRERATIO);
 
 	cfg = (EXYNOS_CISCPREDST_PREDSTWIDTH(pre_dst_width) |
 		EXYNOS_CISCPREDST_PREDSTHEIGHT(pre_dst_height));
-	fimc_write(cfg, EXYNOS_CISCPREDST);
+	fimc_write(ctx, cfg, EXYNOS_CISCPREDST);
 
 	return ret;
 }
@@ -1064,7 +1029,7 @@ static void fimc_set_scaler(struct fimc_context *ctx, struct fimc_scaler *sc)
 	DRM_DEBUG_KMS("hratio[%d]vratio[%d]\n",
 		sc->hratio, sc->vratio);
 
-	cfg = fimc_read(EXYNOS_CISCCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CISCCTRL);
 	cfg &= ~(EXYNOS_CISCCTRL_SCALERBYPASS |
 		EXYNOS_CISCCTRL_SCALEUP_H | EXYNOS_CISCCTRL_SCALEUP_V |
 		EXYNOS_CISCCTRL_MAIN_V_RATIO_MASK |
@@ -1084,14 +1049,14 @@ static void fimc_set_scaler(struct fimc_context *ctx, struct fimc_scaler *sc)
 
 	cfg |= (EXYNOS_CISCCTRL_MAINHORRATIO((sc->hratio >> 6)) |
 		EXYNOS_CISCCTRL_MAINVERRATIO((sc->vratio >> 6)));
-	fimc_write(cfg, EXYNOS_CISCCTRL);
+	fimc_write(ctx, cfg, EXYNOS_CISCCTRL);
 
-	cfg_ext = fimc_read(EXYNOS_CIEXTEN);
+	cfg_ext = fimc_read(ctx, EXYNOS_CIEXTEN);
 	cfg_ext &= ~EXYNOS_CIEXTEN_MAINHORRATIO_EXT_MASK;
 	cfg_ext &= ~EXYNOS_CIEXTEN_MAINVERRATIO_EXT_MASK;
 	cfg_ext |= (EXYNOS_CIEXTEN_MAINHORRATIO_EXT(sc->hratio) |
 		EXYNOS_CIEXTEN_MAINVERRATIO_EXT(sc->vratio));
-	fimc_write(cfg_ext, EXYNOS_CIEXTEN);
+	fimc_write(ctx, cfg_ext, EXYNOS_CIEXTEN);
 }
 
 static int fimc_dst_set_size(struct device *dev, int swap,
@@ -1109,12 +1074,12 @@ static int fimc_dst_set_size(struct device *dev, int swap,
 	cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(img_sz.hsize) |
 		EXYNOS_ORGOSIZE_VERTICAL(img_sz.vsize));
 
-	fimc_write(cfg, EXYNOS_ORGOSIZE);
+	fimc_write(ctx, cfg, EXYNOS_ORGOSIZE);
 
 	DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]\n", pos->x, pos->y, pos->w, pos->h);
 
 	/* CSC ITU */
-	cfg = fimc_read(EXYNOS_CIGCTRL);
+	cfg = fimc_read(ctx, EXYNOS_CIGCTRL);
 	cfg &= ~EXYNOS_CIGCTRL_CSC_MASK;
 
 	if (sz->hsize >= FIMC_WIDTH_ITU_709)
@@ -1122,7 +1087,7 @@ static int fimc_dst_set_size(struct device *dev, int swap,
 	else
 		cfg |= EXYNOS_CIGCTRL_CSC_ITU601;
 
-	fimc_write(cfg, EXYNOS_CIGCTRL);
+	fimc_write(ctx, cfg, EXYNOS_CIGCTRL);
 
 	if (swap) {
 		img_pos.w = pos->h;
@@ -1132,41 +1097,38 @@ static int fimc_dst_set_size(struct device *dev, int swap,
 	}
 
 	/* target image size */
-	cfg = fimc_read(EXYNOS_CITRGFMT);
+	cfg = fimc_read(ctx, EXYNOS_CITRGFMT);
 	cfg &= ~(EXYNOS_CITRGFMT_TARGETH_MASK |
 		EXYNOS_CITRGFMT_TARGETV_MASK);
 	cfg |= (EXYNOS_CITRGFMT_TARGETHSIZE(img_pos.w) |
 		EXYNOS_CITRGFMT_TARGETVSIZE(img_pos.h));
-	fimc_write(cfg, EXYNOS_CITRGFMT);
+	fimc_write(ctx, cfg, EXYNOS_CITRGFMT);
 
 	/* target area */
 	cfg = EXYNOS_CITAREA_TARGET_AREA(img_pos.w * img_pos.h);
-	fimc_write(cfg, EXYNOS_CITAREA);
+	fimc_write(ctx, cfg, EXYNOS_CITAREA);
 
 	/* offset Y(RGB), Cb, Cr */
 	cfg = (EXYNOS_CIOYOFF_HORIZONTAL(img_pos.x) |
 		EXYNOS_CIOYOFF_VERTICAL(img_pos.y));
-	fimc_write(cfg, EXYNOS_CIOYOFF);
+	fimc_write(ctx, cfg, EXYNOS_CIOYOFF);
 	cfg = (EXYNOS_CIOCBOFF_HORIZONTAL(img_pos.x) |
 		EXYNOS_CIOCBOFF_VERTICAL(img_pos.y));
-	fimc_write(cfg, EXYNOS_CIOCBOFF);
+	fimc_write(ctx, cfg, EXYNOS_CIOCBOFF);
 	cfg = (EXYNOS_CIOCROFF_HORIZONTAL(img_pos.x) |
 		EXYNOS_CIOCROFF_VERTICAL(img_pos.y));
-	fimc_write(cfg, EXYNOS_CIOCROFF);
+	fimc_write(ctx, cfg, EXYNOS_CIOCROFF);
 
 	return 0;
 }
 
-static int fimc_dst_get_buf_seq(struct fimc_context *ctx)
+static int fimc_dst_get_buf_count(struct fimc_context *ctx)
 {
-	u32 cfg, i, buf_num = 0;
-	u32 mask = 0x00000001;
+	u32 cfg, buf_num;
 
-	cfg = fimc_read(EXYNOS_CIFCNTSEQ);
+	cfg = fimc_read(ctx, EXYNOS_CIFCNTSEQ);
 
-	for (i = 0; i < FIMC_REG_SZ; i++)
-		if (cfg & (mask << i))
-			buf_num++;
+	buf_num = hweight32(cfg);
 
 	DRM_DEBUG_KMS("buf_num[%d]\n", buf_num);
 
@@ -1181,13 +1143,14 @@ static int fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
 	u32 cfg;
 	u32 mask = 0x00000001 << buf_id;
 	int ret = 0;
+	unsigned long flags;
 
 	DRM_DEBUG_KMS("buf_id[%d]buf_type[%d]\n", buf_id, buf_type);
 
-	mutex_lock(&ctx->lock);
+	spin_lock_irqsave(&ctx->lock, flags);
 
 	/* mask register set */
-	cfg = fimc_read(EXYNOS_CIFCNTSEQ);
+	cfg = fimc_read(ctx, EXYNOS_CIFCNTSEQ);
 
 	switch (buf_type) {
 	case IPP_BUF_ENQUEUE:
@@ -1205,20 +1168,20 @@ static int fimc_dst_set_buf_seq(struct fimc_context *ctx, u32 buf_id,
 	/* sequence id */
 	cfg &= ~mask;
 	cfg |= (enable << buf_id);
-	fimc_write(cfg, EXYNOS_CIFCNTSEQ);
+	fimc_write(ctx, cfg, EXYNOS_CIFCNTSEQ);
 
 	/* interrupt enable */
 	if (buf_type == IPP_BUF_ENQUEUE &&
-	    fimc_dst_get_buf_seq(ctx) >= FIMC_BUF_START)
-		fimc_handle_irq(ctx, true, false, true);
+	    fimc_dst_get_buf_count(ctx) >= FIMC_BUF_START)
+		fimc_mask_irq(ctx, true);
 
 	/* interrupt disable */
 	if (buf_type == IPP_BUF_DEQUEUE &&
-	    fimc_dst_get_buf_seq(ctx) <= FIMC_BUF_STOP)
-		fimc_handle_irq(ctx, false, false, true);
+	    fimc_dst_get_buf_count(ctx) <= FIMC_BUF_STOP)
+		fimc_mask_irq(ctx, false);
 
 err_unlock:
-	mutex_unlock(&ctx->lock);
+	spin_unlock_irqrestore(&ctx->lock, flags);
 	return ret;
 }
 
@@ -1252,25 +1215,25 @@ static int fimc_dst_set_addr(struct device *dev,
 	case IPP_BUF_ENQUEUE:
 		config = &property->config[EXYNOS_DRM_OPS_DST];
 
-		fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_Y],
+		fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_Y],
 			EXYNOS_CIOYSA(buf_id));
 
 		if (config->fmt == DRM_FORMAT_YVU420) {
-			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
+			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
 				EXYNOS_CIOCBSA(buf_id));
-			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
+			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
 				EXYNOS_CIOCRSA(buf_id));
 		} else {
-			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CB],
+			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CB],
 				EXYNOS_CIOCBSA(buf_id));
-			fimc_write(buf_info->base[EXYNOS_DRM_PLANAR_CR],
+			fimc_write(ctx, buf_info->base[EXYNOS_DRM_PLANAR_CR],
 				EXYNOS_CIOCRSA(buf_id));
 		}
 		break;
 	case IPP_BUF_DEQUEUE:
-		fimc_write(0x0, EXYNOS_CIOYSA(buf_id));
-		fimc_write(0x0, EXYNOS_CIOCBSA(buf_id));
-		fimc_write(0x0, EXYNOS_CIOCRSA(buf_id));
+		fimc_write(ctx, 0x0, EXYNOS_CIOYSA(buf_id));
+		fimc_write(ctx, 0x0, EXYNOS_CIOCBSA(buf_id));
+		fimc_write(ctx, 0x0, EXYNOS_CIOCRSA(buf_id));
 		break;
 	default:
 		/* bypass */
@@ -1342,11 +1305,7 @@ static irqreturn_t fimc_irq_handler(int irq, void *dev_id)
 
 static int fimc_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
 {
-	struct drm_exynos_ipp_prop_list *prop_list;
-
-	prop_list = devm_kzalloc(ippdrv->dev, sizeof(*prop_list), GFP_KERNEL);
-	if (!prop_list)
-		return -ENOMEM;
+	struct drm_exynos_ipp_prop_list *prop_list = &ippdrv->prop_list;
 
 	prop_list->version = 1;
 	prop_list->writeback = 1;
@@ -1371,8 +1330,6 @@ static int fimc_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
 	prop_list->scale_min.hsize = FIMC_SCALE_MIN;
 	prop_list->scale_min.vsize = FIMC_SCALE_MIN;
 
-	ippdrv->prop_list = prop_list;
-
 	return 0;
 }
 
@@ -1395,7 +1352,7 @@ static int fimc_ippdrv_check_property(struct device *dev,
 {
 	struct fimc_context *ctx = get_fimc_context(dev);
 	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_prop_list *pp = ippdrv->prop_list;
+	struct drm_exynos_ipp_prop_list *pp = &ippdrv->prop_list;
 	struct drm_exynos_ipp_config *config;
 	struct drm_exynos_pos *pos;
 	struct drm_exynos_sz *sz;
@@ -1508,15 +1465,15 @@ static void fimc_clear_addr(struct fimc_context *ctx)
 	int i;
 
 	for (i = 0; i < FIMC_MAX_SRC; i++) {
-		fimc_write(0, EXYNOS_CIIYSA(i));
-		fimc_write(0, EXYNOS_CIICBSA(i));
-		fimc_write(0, EXYNOS_CIICRSA(i));
+		fimc_write(ctx, 0, EXYNOS_CIIYSA(i));
+		fimc_write(ctx, 0, EXYNOS_CIICBSA(i));
+		fimc_write(ctx, 0, EXYNOS_CIICRSA(i));
 	}
 
 	for (i = 0; i < FIMC_MAX_DST; i++) {
-		fimc_write(0, EXYNOS_CIOYSA(i));
-		fimc_write(0, EXYNOS_CIOCBSA(i));
-		fimc_write(0, EXYNOS_CIOCRSA(i));
+		fimc_write(ctx, 0, EXYNOS_CIOYSA(i));
+		fimc_write(ctx, 0, EXYNOS_CIOCBSA(i));
+		fimc_write(ctx, 0, EXYNOS_CIOCRSA(i));
 	}
 }
 
@@ -1556,7 +1513,7 @@ static int fimc_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
 
 	property = &c_node->property;
 
-	fimc_handle_irq(ctx, true, false, true);
+	fimc_mask_irq(ctx, true);
 
 	for_each_ipp_ops(i) {
 		config = &property->config[i];
@@ -1582,10 +1539,10 @@ static int fimc_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
 		fimc_handle_lastend(ctx, false);
 
 		/* setup dma */
-		cfg0 = fimc_read(EXYNOS_MSCTRL);
+		cfg0 = fimc_read(ctx, EXYNOS_MSCTRL);
 		cfg0 &= ~EXYNOS_MSCTRL_INPUT_MASK;
 		cfg0 |= EXYNOS_MSCTRL_INPUT_MEMORY;
-		fimc_write(cfg0, EXYNOS_MSCTRL);
+		fimc_write(ctx, cfg0, EXYNOS_MSCTRL);
 		break;
 	case IPP_CMD_WB:
 		fimc_set_type_ctrl(ctx, FIMC_WB_A);
@@ -1610,41 +1567,33 @@ static int fimc_ippdrv_start(struct device *dev, enum drm_exynos_ipp_cmd cmd)
 	}
 
 	/* Reset status */
-	fimc_write(0x0, EXYNOS_CISTATUS);
+	fimc_write(ctx, 0x0, EXYNOS_CISTATUS);
 
-	cfg0 = fimc_read(EXYNOS_CIIMGCPT);
+	cfg0 = fimc_read(ctx, EXYNOS_CIIMGCPT);
 	cfg0 &= ~EXYNOS_CIIMGCPT_IMGCPTEN_SC;
 	cfg0 |= EXYNOS_CIIMGCPT_IMGCPTEN_SC;
 
 	/* Scaler */
-	cfg1 = fimc_read(EXYNOS_CISCCTRL);
+	cfg1 = fimc_read(ctx, EXYNOS_CISCCTRL);
 	cfg1 &= ~EXYNOS_CISCCTRL_SCAN_MASK;
 	cfg1 |= (EXYNOS_CISCCTRL_PROGRESSIVE |
 		EXYNOS_CISCCTRL_SCALERSTART);
 
-	fimc_write(cfg1, EXYNOS_CISCCTRL);
+	fimc_write(ctx, cfg1, EXYNOS_CISCCTRL);
 
 	/* Enable image capture*/
 	cfg0 |= EXYNOS_CIIMGCPT_IMGCPTEN;
-	fimc_write(cfg0, EXYNOS_CIIMGCPT);
+	fimc_write(ctx, cfg0, EXYNOS_CIIMGCPT);
 
 	/* Disable frame end irq */
-	cfg0 = fimc_read(EXYNOS_CIGCTRL);
-	cfg0 &= ~EXYNOS_CIGCTRL_IRQ_END_DISABLE;
-	fimc_write(cfg0, EXYNOS_CIGCTRL);
+	fimc_clear_bits(ctx, EXYNOS_CIGCTRL, EXYNOS_CIGCTRL_IRQ_END_DISABLE);
 
-	cfg0 = fimc_read(EXYNOS_CIOCTRL);
-	cfg0 &= ~EXYNOS_CIOCTRL_WEAVE_MASK;
-	fimc_write(cfg0, EXYNOS_CIOCTRL);
+	fimc_clear_bits(ctx, EXYNOS_CIOCTRL, EXYNOS_CIOCTRL_WEAVE_MASK);
 
 	if (cmd == IPP_CMD_M2M) {
-		cfg0 = fimc_read(EXYNOS_MSCTRL);
-		cfg0 |= EXYNOS_MSCTRL_ENVID;
-		fimc_write(cfg0, EXYNOS_MSCTRL);
+		fimc_set_bits(ctx, EXYNOS_MSCTRL, EXYNOS_MSCTRL_ENVID);
 
-		cfg0 = fimc_read(EXYNOS_MSCTRL);
-		cfg0 |= EXYNOS_MSCTRL_ENVID;
-		fimc_write(cfg0, EXYNOS_MSCTRL);
+		fimc_set_bits(ctx, EXYNOS_MSCTRL, EXYNOS_MSCTRL_ENVID);
 	}
 
 	return 0;
@@ -1661,10 +1610,10 @@ static void fimc_ippdrv_stop(struct device *dev, enum drm_exynos_ipp_cmd cmd)
 	switch (cmd) {
 	case IPP_CMD_M2M:
 		/* Source clear */
-		cfg = fimc_read(EXYNOS_MSCTRL);
+		cfg = fimc_read(ctx, EXYNOS_MSCTRL);
 		cfg &= ~EXYNOS_MSCTRL_INPUT_MASK;
 		cfg &= ~EXYNOS_MSCTRL_ENVID;
-		fimc_write(cfg, EXYNOS_MSCTRL);
+		fimc_write(ctx, cfg, EXYNOS_MSCTRL);
 		break;
 	case IPP_CMD_WB:
 		exynos_drm_ippnb_send_event(IPP_SET_WRITEBACK, (void *)&set_wb);
@@ -1675,25 +1624,20 @@ static void fimc_ippdrv_stop(struct device *dev, enum drm_exynos_ipp_cmd cmd)
 		break;
 	}
 
-	fimc_handle_irq(ctx, false, false, true);
+	fimc_mask_irq(ctx, false);
 
 	/* reset sequence */
-	fimc_write(0x0, EXYNOS_CIFCNTSEQ);
+	fimc_write(ctx, 0x0, EXYNOS_CIFCNTSEQ);
 
 	/* Scaler disable */
-	cfg = fimc_read(EXYNOS_CISCCTRL);
-	cfg &= ~EXYNOS_CISCCTRL_SCALERSTART;
-	fimc_write(cfg, EXYNOS_CISCCTRL);
+	fimc_clear_bits(ctx, EXYNOS_CISCCTRL, EXYNOS_CISCCTRL_SCALERSTART);
 
 	/* Disable image capture */
-	cfg = fimc_read(EXYNOS_CIIMGCPT);
-	cfg &= ~(EXYNOS_CIIMGCPT_IMGCPTEN_SC | EXYNOS_CIIMGCPT_IMGCPTEN);
-	fimc_write(cfg, EXYNOS_CIIMGCPT);
+	fimc_clear_bits(ctx, EXYNOS_CIIMGCPT,
+		EXYNOS_CIIMGCPT_IMGCPTEN_SC | EXYNOS_CIIMGCPT_IMGCPTEN);
 
 	/* Enable frame end irq */
-	cfg = fimc_read(EXYNOS_CIGCTRL);
-	cfg |= EXYNOS_CIGCTRL_IRQ_END_DISABLE;
-	fimc_write(cfg, EXYNOS_CIGCTRL);
+	fimc_set_bits(ctx, EXYNOS_CIGCTRL, EXYNOS_CIGCTRL_IRQ_END_DISABLE);
 }
 
 static void fimc_put_clocks(struct fimc_context *ctx)
@@ -1848,7 +1792,7 @@ static int fimc_probe(struct platform_device *pdev)
 
 	DRM_DEBUG_KMS("id[%d]ippdrv[0x%x]\n", ctx->id, (int)ippdrv);
 
-	mutex_init(&ctx->lock);
+	spin_lock_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
 
 	pm_runtime_set_active(dev);
@@ -1879,7 +1823,6 @@ static int fimc_remove(struct platform_device *pdev)
 	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
 
 	exynos_drm_ippdrv_unregister(ippdrv);
-	mutex_destroy(&ctx->lock);
 
 	fimc_put_clocks(ctx);
 	pm_runtime_set_suspended(dev);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 40fd6ccfcd6..33161ad3820 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -19,6 +19,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/component.h>
 
 #include <video/of_display_timing.h>
 #include <video/of_videomode.h>
@@ -38,6 +39,7 @@
  */
 
 #define FIMD_DEFAULT_FRAMERATE 60
+#define MIN_FB_WIDTH_FOR_16WORD_BURST 128
 
 /* position control register for hardware window 0, 2 ~ 4.*/
 #define VIDOSD_A(win)		(VIDOSD_BASE + 0x00 + (win) * 16)
@@ -122,6 +124,7 @@ struct fimd_context {
 
 	struct exynos_drm_panel_info panel;
 	struct fimd_driver_data *driver_data;
+	struct exynos_drm_display *display;
 };
 
 static const struct of_device_id fimd_driver_dt_match[] = {
@@ -143,13 +146,57 @@ static inline struct fimd_driver_data *drm_fimd_get_driver_data(
 	return (struct fimd_driver_data *)of_id->data;
 }
 
+static void fimd_wait_for_vblank(struct exynos_drm_manager *mgr)
+{
+	struct fimd_context *ctx = mgr->ctx;
+
+	if (ctx->suspended)
+		return;
+
+	atomic_set(&ctx->wait_vsync_event, 1);
+
+	/*
+	 * wait for FIMD to signal VSYNC interrupt or return after
+	 * timeout which is set to 50ms (refresh rate of 20).
+	 */
+	if (!wait_event_timeout(ctx->wait_vsync_queue,
+				!atomic_read(&ctx->wait_vsync_event),
+				HZ/20))
+		DRM_DEBUG_KMS("vblank wait timed out.\n");
+}
+
+
+static void fimd_clear_channel(struct exynos_drm_manager *mgr)
+{
+	struct fimd_context *ctx = mgr->ctx;
+	int win, ch_enabled = 0;
+
+	DRM_DEBUG_KMS("%s\n", __FILE__);
+
+	/* Check if any channel is enabled. */
+	for (win = 0; win < WINDOWS_NR; win++) {
+		u32 val = readl(ctx->regs + SHADOWCON);
+		if (val & SHADOWCON_CHx_ENABLE(win)) {
+			val &= ~SHADOWCON_CHx_ENABLE(win);
+			writel(val, ctx->regs + SHADOWCON);
+			ch_enabled = 1;
+		}
+	}
+
+	/* Wait for vsync, as disable channel takes effect at next vsync */
+	if (ch_enabled)
+		fimd_wait_for_vblank(mgr);
+}
+
 static int fimd_mgr_initialize(struct exynos_drm_manager *mgr,
-			struct drm_device *drm_dev, int pipe)
+			struct drm_device *drm_dev)
 {
 	struct fimd_context *ctx = mgr->ctx;
+	struct exynos_drm_private *priv;
+	priv = drm_dev->dev_private;
 
-	ctx->drm_dev = drm_dev;
-	ctx->pipe = pipe;
+	mgr->drm_dev = ctx->drm_dev = drm_dev;
+	mgr->pipe = ctx->pipe = priv->pipe++;
 
 	/*
 	 * enable drm irq mode.
@@ -169,8 +216,14 @@ static int fimd_mgr_initialize(struct exynos_drm_manager *mgr,
 	drm_dev->vblank_disable_allowed = true;
 
 	/* attach this sub driver to iommu mapping if supported. */
-	if (is_drm_iommu_supported(ctx->drm_dev))
+	if (is_drm_iommu_supported(ctx->drm_dev)) {
+		/*
+		 * If any channel is already active, iommu will throw
+		 * a PAGE FAULT when enabled. So clear any channel if enabled.
+		 */
+		fimd_clear_channel(mgr);
 		drm_iommu_attach_device(ctx->drm_dev, ctx->dev);
+	}
 
 	return 0;
 }
@@ -324,25 +377,6 @@ static void fimd_disable_vblank(struct exynos_drm_manager *mgr)
 	}
 }
 
-static void fimd_wait_for_vblank(struct exynos_drm_manager *mgr)
-{
-	struct fimd_context *ctx = mgr->ctx;
-
-	if (ctx->suspended)
-		return;
-
-	atomic_set(&ctx->wait_vsync_event, 1);
-
-	/*
-	 * wait for FIMD to signal VSYNC interrupt or return after
-	 * timeout which is set to 50ms (refresh rate of 20).
-	 */
-	if (!wait_event_timeout(ctx->wait_vsync_queue,
-				!atomic_read(&ctx->wait_vsync_event),
-				HZ/20))
-		DRM_DEBUG_KMS("vblank wait timed out.\n");
-}
-
 static void fimd_win_mode_set(struct exynos_drm_manager *mgr,
 			struct exynos_drm_overlay *overlay)
 {
@@ -446,6 +480,19 @@ static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win)
 
 	DRM_DEBUG_KMS("bpp = %d\n", win_data->bpp);
 
+	/*
+	 * In case of exynos, setting dma-burst to 16Word causes permanent
+	 * tearing for very small buffers, e.g. cursor buffer. Burst Mode
+	 * switching which is based on overlay size is not recommended as
+	 * overlay size varies alot towards the end of the screen and rapid
+	 * movement causes unstable DMA which results into iommu crash/tear.
+	 */
+
+	if (win_data->fb_width < MIN_FB_WIDTH_FOR_16WORD_BURST) {
+		val &= ~WINCONx_BURSTLEN_MASK;
+		val |= WINCONx_BURSTLEN_4WORD;
+	}
+
 	writel(val, ctx->regs + WINCON(win));
 }
 
@@ -656,19 +703,6 @@ static void fimd_win_disable(struct exynos_drm_manager *mgr, int zpos)
 	win_data->enabled = false;
 }
 
-static void fimd_clear_win(struct fimd_context *ctx, int win)
-{
-	writel(0, ctx->regs + WINCON(win));
-	writel(0, ctx->regs + VIDOSD_A(win));
-	writel(0, ctx->regs + VIDOSD_B(win));
-	writel(0, ctx->regs + VIDOSD_C(win));
-
-	if (win == 1 || win == 2)
-		writel(0, ctx->regs + VIDOSD_D(win));
-
-	fimd_shadow_protect_win(ctx, win, false);
-}
-
 static void fimd_window_suspend(struct exynos_drm_manager *mgr)
 {
 	struct fimd_context *ctx = mgr->ctx;
@@ -707,6 +741,8 @@ static void fimd_apply(struct exynos_drm_manager *mgr)
 		win_data = &ctx->win_data[i];
 		if (win_data->enabled)
 			fimd_win_commit(mgr, i);
+		else
+			fimd_win_disable(mgr, i);
 	}
 
 	fimd_commit(mgr);
@@ -803,8 +839,6 @@ static void fimd_dpms(struct exynos_drm_manager *mgr, int mode)
 }
 
 static struct exynos_drm_manager_ops fimd_manager_ops = {
-	.initialize = fimd_mgr_initialize,
-	.remove = fimd_mgr_remove,
 	.dpms = fimd_dpms,
 	.mode_fixup = fimd_mode_fixup,
 	.mode_set = fimd_mode_set,
@@ -849,20 +883,64 @@ out:
 	return IRQ_HANDLED;
 }
 
+static int fimd_bind(struct device *dev, struct device *master, void *data)
+{
+	struct fimd_context *ctx = fimd_manager.ctx;
+	struct drm_device *drm_dev = data;
+
+	fimd_mgr_initialize(&fimd_manager, drm_dev);
+	exynos_drm_crtc_create(&fimd_manager);
+	if (ctx->display)
+		exynos_drm_create_enc_conn(drm_dev, ctx->display);
+
+	return 0;
+
+}
+
+static void fimd_unbind(struct device *dev, struct device *master,
+			void *data)
+{
+	struct exynos_drm_manager *mgr = dev_get_drvdata(dev);
+	struct fimd_context *ctx = fimd_manager.ctx;
+	struct drm_crtc *crtc = mgr->crtc;
+
+	fimd_dpms(mgr, DRM_MODE_DPMS_OFF);
+
+	if (ctx->display)
+		exynos_dpi_remove(dev);
+
+	fimd_mgr_remove(mgr);
+
+	crtc->funcs->destroy(crtc);
+}
+
+static const struct component_ops fimd_component_ops = {
+	.bind	= fimd_bind,
+	.unbind = fimd_unbind,
+};
+
 static int fimd_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct fimd_context *ctx;
 	struct resource *res;
-	int win;
 	int ret = -EINVAL;
 
-	if (!dev->of_node)
-		return -ENODEV;
+	ret = exynos_drm_component_add(&pdev->dev, EXYNOS_DEVICE_TYPE_CRTC,
+					fimd_manager.type);
+	if (ret)
+		return ret;
+
+	if (!dev->of_node) {
+		ret = -ENODEV;
+		goto err_del_component;
+	}
 
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
-	if (!ctx)
-		return -ENOMEM;
+	if (!ctx) {
+		ret = -ENOMEM;
+		goto err_del_component;
+	}
 
 	ctx->dev = dev;
 	ctx->suspended = true;
@@ -875,32 +953,37 @@ static int fimd_probe(struct platform_device *pdev)
 	ctx->bus_clk = devm_clk_get(dev, "fimd");
 	if (IS_ERR(ctx->bus_clk)) {
 		dev_err(dev, "failed to get bus clock\n");
-		return PTR_ERR(ctx->bus_clk);
+		ret = PTR_ERR(ctx->bus_clk);
+		goto err_del_component;
 	}
 
 	ctx->lcd_clk = devm_clk_get(dev, "sclk_fimd");
 	if (IS_ERR(ctx->lcd_clk)) {
 		dev_err(dev, "failed to get lcd clock\n");
-		return PTR_ERR(ctx->lcd_clk);
+		ret = PTR_ERR(ctx->lcd_clk);
+		goto err_del_component;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
 	ctx->regs = devm_ioremap_resource(dev, res);
-	if (IS_ERR(ctx->regs))
-		return PTR_ERR(ctx->regs);
+	if (IS_ERR(ctx->regs)) {
+		ret = PTR_ERR(ctx->regs);
+		goto err_del_component;
+	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, "vsync");
 	if (!res) {
 		dev_err(dev, "irq request failed.\n");
-		return -ENXIO;
+		ret = -ENXIO;
+		goto err_del_component;
 	}
 
 	ret = devm_request_irq(dev, res->start, fimd_irq_handler,
 							0, "drm_fimd", ctx);
 	if (ret) {
 		dev_err(dev, "irq request failed.\n");
-		return ret;
+		goto err_del_component;
 	}
 
 	ctx->driver_data = drm_fimd_get_driver_data(pdev);
@@ -910,30 +993,34 @@ static int fimd_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, &fimd_manager);
 
 	fimd_manager.ctx = ctx;
-	exynos_drm_manager_register(&fimd_manager);
 
-	exynos_dpi_probe(ctx->dev);
+	ctx->display = exynos_dpi_probe(dev);
+	if (IS_ERR(ctx->display))
+		return PTR_ERR(ctx->display);
 
-	pm_runtime_enable(dev);
+	pm_runtime_enable(&pdev->dev);
 
-	for (win = 0; win < WINDOWS_NR; win++)
-		fimd_clear_win(ctx, win);
+	ret = component_add(&pdev->dev, &fimd_component_ops);
+	if (ret)
+		goto err_disable_pm_runtime;
 
-	return 0;
+	return ret;
+
+err_disable_pm_runtime:
+	pm_runtime_disable(&pdev->dev);
+
+err_del_component:
+	exynos_drm_component_del(&pdev->dev, EXYNOS_DEVICE_TYPE_CRTC);
+	return ret;
 }
 
 static int fimd_remove(struct platform_device *pdev)
 {
-	struct exynos_drm_manager *mgr = platform_get_drvdata(pdev);
-
-	exynos_dpi_remove(&pdev->dev);
-
-	exynos_drm_manager_unregister(&fimd_manager);
-
-	fimd_dpms(mgr, DRM_MODE_DPMS_OFF);
-
 	pm_runtime_disable(&pdev->dev);
 
+	component_del(&pdev->dev, &fimd_component_ops);
+	exynos_drm_component_del(&pdev->dev, EXYNOS_DEVICE_TYPE_CRTC);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 42d2904d88c..163a054922c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -612,22 +612,20 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv,
 	args->pitch = args->width * ((args->bpp + 7) / 8);
 	args->size = args->pitch * args->height;
 
-	exynos_gem_obj = exynos_drm_gem_create(dev, EXYNOS_BO_CONTIG |
-						EXYNOS_BO_WC, args->size);
-	/*
-	 * If physically contiguous memory allocation fails and if IOMMU is
-	 * supported then try to get buffer from non physically contiguous
-	 * memory area.
-	 */
-	if (IS_ERR(exynos_gem_obj) && is_drm_iommu_supported(dev)) {
-		dev_warn(dev->dev, "contiguous FB allocation failed, falling back to non-contiguous\n");
+	if (is_drm_iommu_supported(dev)) {
+		exynos_gem_obj = exynos_drm_gem_create(dev,
+			EXYNOS_BO_NONCONTIG | EXYNOS_BO_WC,
+			args->size);
+	} else {
 		exynos_gem_obj = exynos_drm_gem_create(dev,
-					EXYNOS_BO_NONCONTIG | EXYNOS_BO_WC,
-					args->size);
+			EXYNOS_BO_CONTIG | EXYNOS_BO_WC,
+			args->size);
 	}
 
-	if (IS_ERR(exynos_gem_obj))
+	if (IS_ERR(exynos_gem_obj)) {
+		dev_warn(dev->dev, "FB allocation failed.\n");
 		return PTR_ERR(exynos_gem_obj);
+	}
 
 	ret = exynos_drm_gem_handle_create(&exynos_gem_obj->base, file_priv,
 			&args->handle);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index fa75059a610..9e3ff167296 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -1335,11 +1335,7 @@ static irqreturn_t gsc_irq_handler(int irq, void *dev_id)
 
 static int gsc_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
 {
-	struct drm_exynos_ipp_prop_list *prop_list;
-
-	prop_list = devm_kzalloc(ippdrv->dev, sizeof(*prop_list), GFP_KERNEL);
-	if (!prop_list)
-		return -ENOMEM;
+	struct drm_exynos_ipp_prop_list *prop_list = &ippdrv->prop_list;
 
 	prop_list->version = 1;
 	prop_list->writeback = 1;
@@ -1363,8 +1359,6 @@ static int gsc_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
 	prop_list->scale_min.hsize = GSC_SCALE_MIN;
 	prop_list->scale_min.vsize = GSC_SCALE_MIN;
 
-	ippdrv->prop_list = prop_list;
-
 	return 0;
 }
 
@@ -1387,7 +1381,7 @@ static int gsc_ippdrv_check_property(struct device *dev,
 {
 	struct gsc_context *ctx = get_gsc_context(dev);
 	struct exynos_drm_ippdrv *ippdrv = &ctx->ippdrv;
-	struct drm_exynos_ipp_prop_list *pp = ippdrv->prop_list;
+	struct drm_exynos_ipp_prop_list *pp = &ippdrv->prop_list;
 	struct drm_exynos_ipp_config *config;
 	struct drm_exynos_pos *pos;
 	struct drm_exynos_sz *sz;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index 3d78144387a..a1888e128f1 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -167,6 +167,13 @@ static int ipp_create_id(struct idr *id_idr, struct mutex *lock, void *obj,
 	return 0;
 }
 
+static void ipp_remove_id(struct idr *id_idr, struct mutex *lock, u32 id)
+{
+	mutex_lock(lock);
+	idr_remove(id_idr, id);
+	mutex_unlock(lock);
+}
+
 static void *ipp_find_obj(struct idr *id_idr, struct mutex *lock, u32 id)
 {
 	void *obj;
@@ -276,11 +283,6 @@ static struct exynos_drm_ippdrv *ipp_find_drv_by_handle(u32 prop_id)
 
 	DRM_DEBUG_KMS("prop_id[%d]\n", prop_id);
 
-	if (list_empty(&exynos_drm_ippdrv_list)) {
-		DRM_DEBUG_KMS("ippdrv_list is empty.\n");
-		return ERR_PTR(-ENODEV);
-	}
-
 	/*
 	 * This case is search ipp driver by prop_id handle.
 	 * sometimes, ipp subsystem find driver by prop_id.
@@ -289,11 +291,14 @@ static struct exynos_drm_ippdrv *ipp_find_drv_by_handle(u32 prop_id)
 	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
 		DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]\n", count++, (int)ippdrv);
 
-		if (!list_empty(&ippdrv->cmd_list)) {
-			list_for_each_entry(c_node, &ippdrv->cmd_list, list)
-				if (c_node->property.prop_id == prop_id)
-					return ippdrv;
+		mutex_lock(&ippdrv->cmd_lock);
+		list_for_each_entry(c_node, &ippdrv->cmd_list, list) {
+			if (c_node->property.prop_id == prop_id) {
+				mutex_unlock(&ippdrv->cmd_lock);
+				return ippdrv;
+			}
 		}
+		mutex_unlock(&ippdrv->cmd_lock);
 	}
 
 	return ERR_PTR(-ENODEV);
@@ -325,6 +330,7 @@ int exynos_drm_ipp_get_property(struct drm_device *drm_dev, void *data,
 	if (!prop_list->ipp_id) {
 		list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list)
 			count++;
+
 		/*
 		 * Supports ippdrv list count for user application.
 		 * First step user application getting ippdrv count.
@@ -346,7 +352,7 @@ int exynos_drm_ipp_get_property(struct drm_device *drm_dev, void *data,
 			return PTR_ERR(ippdrv);
 		}
 
-		prop_list = ippdrv->prop_list;
+		*prop_list = ippdrv->prop_list;
 	}
 
 	return 0;
@@ -386,9 +392,11 @@ static int ipp_find_and_set_property(struct drm_exynos_ipp_property *property)
 	 * when we find this command no using prop_id.
 	 * return property information set in this command node.
 	 */
+	mutex_lock(&ippdrv->cmd_lock);
 	list_for_each_entry(c_node, &ippdrv->cmd_list, list) {
 		if ((c_node->property.prop_id == prop_id) &&
 		    (c_node->state == IPP_STATE_STOP)) {
+			mutex_unlock(&ippdrv->cmd_lock);
 			DRM_DEBUG_KMS("found cmd[%d]ippdrv[0x%x]\n",
 				property->cmd, (int)ippdrv);
 
@@ -396,6 +404,7 @@ static int ipp_find_and_set_property(struct drm_exynos_ipp_property *property)
 			return 0;
 		}
 	}
+	mutex_unlock(&ippdrv->cmd_lock);
 
 	DRM_ERROR("failed to search property.\n");
 
@@ -499,7 +508,7 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 	c_node->start_work = ipp_create_cmd_work();
 	if (IS_ERR(c_node->start_work)) {
 		DRM_ERROR("failed to create start work.\n");
-		goto err_clear;
+		goto err_remove_id;
 	}
 
 	c_node->stop_work = ipp_create_cmd_work();
@@ -514,7 +523,7 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 		goto err_free_stop;
 	}
 
-	mutex_init(&c_node->cmd_lock);
+	mutex_init(&c_node->lock);
 	mutex_init(&c_node->mem_lock);
 	mutex_init(&c_node->event_lock);
 
@@ -526,7 +535,9 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data,
 
 	INIT_LIST_HEAD(&c_node->event_list);
 	list_splice_init(&priv->event_list, &c_node->event_list);
+	mutex_lock(&ippdrv->cmd_lock);
 	list_add_tail(&c_node->list, &ippdrv->cmd_list);
+	mutex_unlock(&ippdrv->cmd_lock);
 
 	/* make dedicated state without m2m */
 	if (!ipp_is_m2m_cmd(property->cmd))
@@ -538,18 +549,24 @@ err_free_stop:
 	kfree(c_node->stop_work);
 err_free_start:
 	kfree(c_node->start_work);
+err_remove_id:
+	ipp_remove_id(&ctx->prop_idr, &ctx->prop_lock, property->prop_id);
 err_clear:
 	kfree(c_node);
 	return ret;
 }
 
-static void ipp_clean_cmd_node(struct drm_exynos_ipp_cmd_node *c_node)
+static void ipp_clean_cmd_node(struct ipp_context *ctx,
+				struct drm_exynos_ipp_cmd_node *c_node)
 {
 	/* delete list */
 	list_del(&c_node->list);
 
+	ipp_remove_id(&ctx->prop_idr, &ctx->prop_lock,
+			c_node->property.prop_id);
+
 	/* destroy mutex */
-	mutex_destroy(&c_node->cmd_lock);
+	mutex_destroy(&c_node->lock);
 	mutex_destroy(&c_node->mem_lock);
 	mutex_destroy(&c_node->event_lock);
 
@@ -567,17 +584,10 @@ static int ipp_check_mem_list(struct drm_exynos_ipp_cmd_node *c_node)
 	struct list_head *head;
 	int ret, i, count[EXYNOS_DRM_OPS_MAX] = { 0, };
 
-	mutex_lock(&c_node->mem_lock);
-
 	for_each_ipp_ops(i) {
 		/* source/destination memory list */
 		head = &c_node->mem_list[i];
 
-		if (list_empty(head)) {
-			DRM_DEBUG_KMS("%s memory empty.\n", i ? "dst" : "src");
-			continue;
-		}
-
 		/* find memory node entry */
 		list_for_each_entry(m_node, head, list) {
 			DRM_DEBUG_KMS("%s,count[%d]m_node[0x%x]\n",
@@ -602,8 +612,6 @@ static int ipp_check_mem_list(struct drm_exynos_ipp_cmd_node *c_node)
 		ret = max(count[EXYNOS_DRM_OPS_SRC],
 			count[EXYNOS_DRM_OPS_DST]);
 
-	mutex_unlock(&c_node->mem_lock);
-
 	return ret;
 }
 
@@ -646,16 +654,13 @@ static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv,
 		return -EFAULT;
 	}
 
-	mutex_lock(&c_node->mem_lock);
-
 	DRM_DEBUG_KMS("ops_id[%d]\n", m_node->ops_id);
 
 	/* get operations callback */
 	ops = ippdrv->ops[m_node->ops_id];
 	if (!ops) {
 		DRM_ERROR("not support ops.\n");
-		ret = -EFAULT;
-		goto err_unlock;
+		return -EFAULT;
 	}
 
 	/* set address and enable irq */
@@ -664,12 +669,10 @@ static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv,
 			m_node->buf_id, IPP_BUF_ENQUEUE);
 		if (ret) {
 			DRM_ERROR("failed to set addr.\n");
-			goto err_unlock;
+			return ret;
 		}
 	}
 
-err_unlock:
-	mutex_unlock(&c_node->mem_lock);
 	return ret;
 }
 
@@ -684,11 +687,9 @@ static struct drm_exynos_ipp_mem_node
 	void *addr;
 	int i;
 
-	mutex_lock(&c_node->mem_lock);
-
 	m_node = kzalloc(sizeof(*m_node), GFP_KERNEL);
 	if (!m_node)
-		goto err_unlock;
+		return ERR_PTR(-ENOMEM);
 
 	/* clear base address for error handling */
 	memset(&buf_info, 0x0, sizeof(buf_info));
@@ -722,15 +723,14 @@ static struct drm_exynos_ipp_mem_node
 
 	m_node->filp = file;
 	m_node->buf_info = buf_info;
+	mutex_lock(&c_node->mem_lock);
 	list_add_tail(&m_node->list, &c_node->mem_list[qbuf->ops_id]);
-
 	mutex_unlock(&c_node->mem_lock);
+
 	return m_node;
 
 err_clear:
 	kfree(m_node);
-err_unlock:
-	mutex_unlock(&c_node->mem_lock);
 	return ERR_PTR(-EFAULT);
 }
 
@@ -747,13 +747,6 @@ static int ipp_put_mem_node(struct drm_device *drm_dev,
 		return -EFAULT;
 	}
 
-	if (list_empty(&m_node->list)) {
-		DRM_ERROR("empty memory node.\n");
-		return -ENOMEM;
-	}
-
-	mutex_lock(&c_node->mem_lock);
-
 	DRM_DEBUG_KMS("ops_id[%d]\n", m_node->ops_id);
 
 	/* put gem buffer */
@@ -768,8 +761,6 @@ static int ipp_put_mem_node(struct drm_device *drm_dev,
 	list_del(&m_node->list);
 	kfree(m_node);
 
-	mutex_unlock(&c_node->mem_lock);
-
 	return 0;
 }
 
@@ -805,7 +796,9 @@ static int ipp_get_event(struct drm_device *drm_dev,
 	e->base.event = &e->event.base;
 	e->base.file_priv = file;
 	e->base.destroy = ipp_free_event;
+	mutex_lock(&c_node->event_lock);
 	list_add_tail(&e->base.link, &c_node->event_list);
+	mutex_unlock(&c_node->event_lock);
 
 	return 0;
 }
@@ -816,11 +809,7 @@ static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node,
 	struct drm_exynos_ipp_send_event *e, *te;
 	int count = 0;
 
-	if (list_empty(&c_node->event_list)) {
-		DRM_DEBUG_KMS("event_list is empty.\n");
-		return;
-	}
-
+	mutex_lock(&c_node->event_lock);
 	list_for_each_entry_safe(e, te, &c_node->event_list, base.link) {
 		DRM_DEBUG_KMS("count[%d]e[0x%x]\n", count++, (int)e);
 
@@ -841,9 +830,13 @@ static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node,
 			/* delete list */
 			list_del(&e->base.link);
 			kfree(e);
-			return;
+			goto out_unlock;
 		}
 	}
+
+out_unlock:
+	mutex_unlock(&c_node->event_lock);
+	return;
 }
 
 static void ipp_handle_cmd_work(struct device *dev,
@@ -887,7 +880,9 @@ static int ipp_queue_buf_with_run(struct device *dev,
 		return 0;
 	}
 
+	mutex_lock(&c_node->mem_lock);
 	if (!ipp_check_mem_list(c_node)) {
+		mutex_unlock(&c_node->mem_lock);
 		DRM_DEBUG_KMS("empty memory.\n");
 		return 0;
 	}
@@ -904,10 +899,12 @@ static int ipp_queue_buf_with_run(struct device *dev,
 	} else {
 		ret = ipp_set_mem_node(ippdrv, c_node, m_node);
 		if (ret) {
+			mutex_unlock(&c_node->mem_lock);
 			DRM_ERROR("failed to set m node.\n");
 			return ret;
 		}
 	}
+	mutex_unlock(&c_node->mem_lock);
 
 	return 0;
 }
@@ -918,15 +915,15 @@ static void ipp_clean_queue_buf(struct drm_device *drm_dev,
 {
 	struct drm_exynos_ipp_mem_node *m_node, *tm_node;
 
-	if (!list_empty(&c_node->mem_list[qbuf->ops_id])) {
-		/* delete list */
-		list_for_each_entry_safe(m_node, tm_node,
-			&c_node->mem_list[qbuf->ops_id], list) {
-			if (m_node->buf_id == qbuf->buf_id &&
-			    m_node->ops_id == qbuf->ops_id)
-				ipp_put_mem_node(drm_dev, c_node, m_node);
-		}
+	/* delete list */
+	mutex_lock(&c_node->mem_lock);
+	list_for_each_entry_safe(m_node, tm_node,
+		&c_node->mem_list[qbuf->ops_id], list) {
+		if (m_node->buf_id == qbuf->buf_id &&
+		    m_node->ops_id == qbuf->ops_id)
+			ipp_put_mem_node(drm_dev, c_node, m_node);
 	}
+	mutex_unlock(&c_node->mem_lock);
 }
 
 int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev, void *data,
@@ -998,7 +995,7 @@ int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev, void *data,
 		}
 		break;
 	case IPP_BUF_DEQUEUE:
-		mutex_lock(&c_node->cmd_lock);
+		mutex_lock(&c_node->lock);
 
 		/* put event for destination buffer */
 		if (qbuf->ops_id == EXYNOS_DRM_OPS_DST)
@@ -1006,7 +1003,7 @@ int exynos_drm_ipp_queue_buf(struct drm_device *drm_dev, void *data,
 
 		ipp_clean_queue_buf(drm_dev, c_node, qbuf);
 
-		mutex_unlock(&c_node->cmd_lock);
+		mutex_unlock(&c_node->lock);
 		break;
 	default:
 		DRM_ERROR("invalid buffer control.\n");
@@ -1109,12 +1106,12 @@ int exynos_drm_ipp_cmd_ctrl(struct drm_device *drm_dev, void *data,
 	case IPP_CTRL_PLAY:
 		if (pm_runtime_suspended(ippdrv->dev))
 			pm_runtime_get_sync(ippdrv->dev);
+
 		c_node->state = IPP_STATE_START;
 
 		cmd_work = c_node->start_work;
 		cmd_work->ctrl = cmd_ctrl->ctrl;
 		ipp_handle_cmd_work(dev, ippdrv, cmd_work, c_node);
-		c_node->state = IPP_STATE_START;
 		break;
 	case IPP_CTRL_STOP:
 		cmd_work = c_node->stop_work;
@@ -1129,10 +1126,12 @@ int exynos_drm_ipp_cmd_ctrl(struct drm_device *drm_dev, void *data,
 
 		c_node->state = IPP_STATE_STOP;
 		ippdrv->dedicated = false;
-		ipp_clean_cmd_node(c_node);
+		mutex_lock(&ippdrv->cmd_lock);
+		ipp_clean_cmd_node(ctx, c_node);
 
 		if (list_empty(&ippdrv->cmd_list))
 			pm_runtime_put_sync(ippdrv->dev);
+		mutex_unlock(&ippdrv->cmd_lock);
 		break;
 	case IPP_CTRL_PAUSE:
 		cmd_work = c_node->stop_work;
@@ -1260,9 +1259,11 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 	/* store command info in ippdrv */
 	ippdrv->c_node = c_node;
 
+	mutex_lock(&c_node->mem_lock);
 	if (!ipp_check_mem_list(c_node)) {
 		DRM_DEBUG_KMS("empty memory.\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_unlock;
 	}
 
 	/* set current property in ippdrv */
@@ -1270,7 +1271,7 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 	if (ret) {
 		DRM_ERROR("failed to set property.\n");
 		ippdrv->c_node = NULL;
-		return ret;
+		goto err_unlock;
 	}
 
 	/* check command */
@@ -1285,7 +1286,7 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 			if (!m_node) {
 				DRM_ERROR("failed to get node.\n");
 				ret = -EFAULT;
-				return ret;
+				goto err_unlock;
 			}
 
 			DRM_DEBUG_KMS("m_node[0x%x]\n", (int)m_node);
@@ -1293,7 +1294,7 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 			ret = ipp_set_mem_node(ippdrv, c_node, m_node);
 			if (ret) {
 				DRM_ERROR("failed to set m node.\n");
-				return ret;
+				goto err_unlock;
 			}
 		}
 		break;
@@ -1305,7 +1306,7 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 			ret = ipp_set_mem_node(ippdrv, c_node, m_node);
 			if (ret) {
 				DRM_ERROR("failed to set m node.\n");
-				return ret;
+				goto err_unlock;
 			}
 		}
 		break;
@@ -1317,14 +1318,16 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 			ret = ipp_set_mem_node(ippdrv, c_node, m_node);
 			if (ret) {
 				DRM_ERROR("failed to set m node.\n");
-				return ret;
+				goto err_unlock;
 			}
 		}
 		break;
 	default:
 		DRM_ERROR("invalid operations.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_unlock;
 	}
+	mutex_unlock(&c_node->mem_lock);
 
 	DRM_DEBUG_KMS("cmd[%d]\n", property->cmd);
 
@@ -1333,11 +1336,17 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv,
 		ret = ippdrv->start(ippdrv->dev, property->cmd);
 		if (ret) {
 			DRM_ERROR("failed to start ops.\n");
+			ippdrv->c_node = NULL;
 			return ret;
 		}
 	}
 
 	return 0;
+
+err_unlock:
+	mutex_unlock(&c_node->mem_lock);
+	ippdrv->c_node = NULL;
+	return ret;
 }
 
 static int ipp_stop_property(struct drm_device *drm_dev,
@@ -1354,6 +1363,8 @@ static int ipp_stop_property(struct drm_device *drm_dev,
 	/* put event */
 	ipp_put_event(c_node, NULL);
 
+	mutex_lock(&c_node->mem_lock);
+
 	/* check command */
 	switch (property->cmd) {
 	case IPP_CMD_M2M:
@@ -1361,11 +1372,6 @@ static int ipp_stop_property(struct drm_device *drm_dev,
 			/* source/destination memory list */
 			head = &c_node->mem_list[i];
 
-			if (list_empty(head)) {
-				DRM_DEBUG_KMS("mem_list is empty.\n");
-				break;
-			}
-
 			list_for_each_entry_safe(m_node, tm_node,
 				head, list) {
 				ret = ipp_put_mem_node(drm_dev, c_node,
@@ -1381,11 +1387,6 @@ static int ipp_stop_property(struct drm_device *drm_dev,
 		/* destination memory list */
 		head = &c_node->mem_list[EXYNOS_DRM_OPS_DST];
 
-		if (list_empty(head)) {
-			DRM_DEBUG_KMS("mem_list is empty.\n");
-			break;
-		}
-
 		list_for_each_entry_safe(m_node, tm_node, head, list) {
 			ret = ipp_put_mem_node(drm_dev, c_node, m_node);
 			if (ret) {
@@ -1398,11 +1399,6 @@ static int ipp_stop_property(struct drm_device *drm_dev,
 		/* source memory list */
 		head = &c_node->mem_list[EXYNOS_DRM_OPS_SRC];
 
-		if (list_empty(head)) {
-			DRM_DEBUG_KMS("mem_list is empty.\n");
-			break;
-		}
-
 		list_for_each_entry_safe(m_node, tm_node, head, list) {
 			ret = ipp_put_mem_node(drm_dev, c_node, m_node);
 			if (ret) {
@@ -1418,6 +1414,8 @@ static int ipp_stop_property(struct drm_device *drm_dev,
 	}
 
 err_clear:
+	mutex_unlock(&c_node->mem_lock);
+
 	/* stop operations */
 	if (ippdrv->stop)
 		ippdrv->stop(ippdrv->dev, property->cmd);
@@ -1446,7 +1444,7 @@ void ipp_sched_cmd(struct work_struct *work)
 		return;
 	}
 
-	mutex_lock(&c_node->cmd_lock);
+	mutex_lock(&c_node->lock);
 
 	property = &c_node->property;
 
@@ -1494,7 +1492,7 @@ void ipp_sched_cmd(struct work_struct *work)
 	DRM_DEBUG_KMS("ctrl[%d] done.\n", cmd_work->ctrl);
 
 err_unlock:
-	mutex_unlock(&c_node->cmd_lock);
+	mutex_unlock(&c_node->lock);
 }
 
 static int ipp_send_event(struct exynos_drm_ippdrv *ippdrv,
@@ -1524,14 +1522,18 @@ static int ipp_send_event(struct exynos_drm_ippdrv *ippdrv,
 		return -EINVAL;
 	}
 
+	mutex_lock(&c_node->event_lock);
 	if (list_empty(&c_node->event_list)) {
 		DRM_DEBUG_KMS("event list is empty.\n");
-		return 0;
+		ret = 0;
+		goto err_event_unlock;
 	}
 
+	mutex_lock(&c_node->mem_lock);
 	if (!ipp_check_mem_list(c_node)) {
 		DRM_DEBUG_KMS("empty memory.\n");
-		return 0;
+		ret = 0;
+		goto err_mem_unlock;
 	}
 
 	/* check command */
@@ -1545,7 +1547,8 @@ static int ipp_send_event(struct exynos_drm_ippdrv *ippdrv,
 				struct drm_exynos_ipp_mem_node, list);
 			if (!m_node) {
 				DRM_ERROR("empty memory node.\n");
-				return -ENOMEM;
+				ret = -ENOMEM;
+				goto err_mem_unlock;
 			}
 
 			tbuf_id[i] = m_node->buf_id;
@@ -1567,7 +1570,8 @@ static int ipp_send_event(struct exynos_drm_ippdrv *ippdrv,
 		m_node = ipp_find_mem_node(c_node, &qbuf);
 		if (!m_node) {
 			DRM_ERROR("empty memory node.\n");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto err_mem_unlock;
 		}
 
 		tbuf_id[EXYNOS_DRM_OPS_DST] = m_node->buf_id;
@@ -1584,7 +1588,8 @@ static int ipp_send_event(struct exynos_drm_ippdrv *ippdrv,
 			struct drm_exynos_ipp_mem_node, list);
 		if (!m_node) {
 			DRM_ERROR("empty memory node.\n");
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto err_mem_unlock;
 		}
 
 		tbuf_id[EXYNOS_DRM_OPS_SRC] = m_node->buf_id;
@@ -1595,8 +1600,10 @@ static int ipp_send_event(struct exynos_drm_ippdrv *ippdrv,
 		break;
 	default:
 		DRM_ERROR("invalid operations.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_mem_unlock;
 	}
+	mutex_unlock(&c_node->mem_lock);
 
 	if (tbuf_id[EXYNOS_DRM_OPS_DST] != buf_id[EXYNOS_DRM_OPS_DST])
 		DRM_ERROR("failed to match buf_id[%d %d]prop_id[%d]\n",
@@ -1611,11 +1618,6 @@ static int ipp_send_event(struct exynos_drm_ippdrv *ippdrv,
 	e = list_first_entry(&c_node->event_list,
 		struct drm_exynos_ipp_send_event, base.link);
 
-	if (!e) {
-		DRM_ERROR("empty event.\n");
-		return -EINVAL;
-	}
-
 	do_gettimeofday(&now);
 	DRM_DEBUG_KMS("tv_sec[%ld]tv_usec[%ld]\n", now.tv_sec, now.tv_usec);
 	e->event.tv_sec = now.tv_sec;
@@ -1630,11 +1632,18 @@ static int ipp_send_event(struct exynos_drm_ippdrv *ippdrv,
 	list_move_tail(&e->base.link, &e->base.file_priv->event_list);
 	wake_up_interruptible(&e->base.file_priv->event_wait);
 	spin_unlock_irqrestore(&drm_dev->event_lock, flags);
+	mutex_unlock(&c_node->event_lock);
 
 	DRM_DEBUG_KMS("done cmd[%d]prop_id[%d]buf_id[%d]\n",
 		property->cmd, property->prop_id, tbuf_id[EXYNOS_DRM_OPS_DST]);
 
 	return 0;
+
+err_mem_unlock:
+	mutex_unlock(&c_node->mem_lock);
+err_event_unlock:
+	mutex_unlock(&c_node->event_lock);
+	return ret;
 }
 
 void ipp_sched_event(struct work_struct *work)
@@ -1676,8 +1685,6 @@ void ipp_sched_event(struct work_struct *work)
 		goto err_completion;
 	}
 
-	mutex_lock(&c_node->event_lock);
-
 	ret = ipp_send_event(ippdrv, c_node, event_work->buf_id);
 	if (ret) {
 		DRM_ERROR("failed to send event.\n");
@@ -1687,8 +1694,6 @@ void ipp_sched_event(struct work_struct *work)
 err_completion:
 	if (ipp_is_m2m_cmd(c_node->property.cmd))
 		complete(&c_node->start_complete);
-
-	mutex_unlock(&c_node->event_lock);
 }
 
 static int ipp_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
@@ -1699,23 +1704,21 @@ static int ipp_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 
 	/* get ipp driver entry */
 	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
+		u32 ipp_id;
+
 		ippdrv->drm_dev = drm_dev;
 
 		ret = ipp_create_id(&ctx->ipp_idr, &ctx->ipp_lock, ippdrv,
-			&ippdrv->ipp_id);
-		if (ret) {
+				    &ipp_id);
+		if (ret || ipp_id == 0) {
 			DRM_ERROR("failed to create id.\n");
-			goto err_idr;
+			goto err;
 		}
 
 		DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]ipp_id[%d]\n",
-			count++, (int)ippdrv, ippdrv->ipp_id);
+			count++, (int)ippdrv, ipp_id);
 
-		if (ippdrv->ipp_id == 0) {
-			DRM_ERROR("failed to get ipp_id[%d]\n",
-				ippdrv->ipp_id);
-			goto err_idr;
-		}
+		ippdrv->prop_list.ipp_id = ipp_id;
 
 		/* store parent device for node */
 		ippdrv->parent_dev = dev;
@@ -1724,39 +1727,46 @@ static int ipp_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 		ippdrv->event_workq = ctx->event_workq;
 		ippdrv->sched_event = ipp_sched_event;
 		INIT_LIST_HEAD(&ippdrv->cmd_list);
+		mutex_init(&ippdrv->cmd_lock);
 
 		if (is_drm_iommu_supported(drm_dev)) {
 			ret = drm_iommu_attach_device(drm_dev, ippdrv->dev);
 			if (ret) {
 				DRM_ERROR("failed to activate iommu\n");
-				goto err_iommu;
+				goto err;
 			}
 		}
 	}
 
 	return 0;
 
-err_iommu:
+err:
 	/* get ipp driver entry */
-	list_for_each_entry_reverse(ippdrv, &exynos_drm_ippdrv_list, drv_list)
+	list_for_each_entry_continue_reverse(ippdrv, &exynos_drm_ippdrv_list,
+						drv_list) {
 		if (is_drm_iommu_supported(drm_dev))
 			drm_iommu_detach_device(drm_dev, ippdrv->dev);
 
-err_idr:
-	idr_destroy(&ctx->ipp_idr);
-	idr_destroy(&ctx->prop_idr);
+		ipp_remove_id(&ctx->ipp_idr, &ctx->ipp_lock,
+				ippdrv->prop_list.ipp_id);
+	}
+
 	return ret;
 }
 
 static void ipp_subdrv_remove(struct drm_device *drm_dev, struct device *dev)
 {
 	struct exynos_drm_ippdrv *ippdrv;
+	struct ipp_context *ctx = get_ipp_context(dev);
 
 	/* get ipp driver entry */
 	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
 		if (is_drm_iommu_supported(drm_dev))
 			drm_iommu_detach_device(drm_dev, ippdrv->dev);
 
+		ipp_remove_id(&ctx->ipp_idr, &ctx->ipp_lock,
+				ippdrv->prop_list.ipp_id);
+
 		ippdrv->drm_dev = NULL;
 		exynos_drm_ippdrv_unregister(ippdrv);
 	}
@@ -1787,20 +1797,14 @@ static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev,
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
 	struct exynos_drm_ipp_private *priv = file_priv->ipp_priv;
 	struct exynos_drm_ippdrv *ippdrv = NULL;
+	struct ipp_context *ctx = get_ipp_context(dev);
 	struct drm_exynos_ipp_cmd_node *c_node, *tc_node;
 	int count = 0;
 
 	DRM_DEBUG_KMS("for priv[0x%x]\n", (int)priv);
 
-	if (list_empty(&exynos_drm_ippdrv_list)) {
-		DRM_DEBUG_KMS("ippdrv_list is empty.\n");
-		goto err_clear;
-	}
-
 	list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) {
-		if (list_empty(&ippdrv->cmd_list))
-			continue;
-
+		mutex_lock(&ippdrv->cmd_lock);
 		list_for_each_entry_safe(c_node, tc_node,
 			&ippdrv->cmd_list, list) {
 			DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]\n",
@@ -1820,14 +1824,14 @@ static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev,
 				}
 
 				ippdrv->dedicated = false;
-				ipp_clean_cmd_node(c_node);
+				ipp_clean_cmd_node(ctx, c_node);
 				if (list_empty(&ippdrv->cmd_list))
 					pm_runtime_put_sync(ippdrv->dev);
 			}
 		}
+		mutex_unlock(&ippdrv->cmd_lock);
 	}
 
-err_clear:
 	kfree(priv);
 	return;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.h b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
index ab1634befc0..7aaeaae757c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.h
@@ -52,7 +52,7 @@ struct drm_exynos_ipp_cmd_work {
  * @list: list head to command queue information.
  * @event_list: list head of event.
  * @mem_list: list head to source,destination memory queue information.
- * @cmd_lock: lock for synchronization of access to ioctl.
+ * @lock: lock for synchronization of access to ioctl.
  * @mem_lock: lock for synchronization of access to memory nodes.
  * @event_lock: lock for synchronization of access to scheduled event.
  * @start_complete: completion of start of command.
@@ -68,7 +68,7 @@ struct drm_exynos_ipp_cmd_node {
 	struct list_head	list;
 	struct list_head	event_list;
 	struct list_head	mem_list[EXYNOS_DRM_OPS_MAX];
-	struct mutex	cmd_lock;
+	struct mutex	lock;
 	struct mutex	mem_lock;
 	struct mutex	event_lock;
 	struct completion	start_complete;
@@ -83,7 +83,7 @@ struct drm_exynos_ipp_cmd_node {
 /*
  * A structure of buffer information.
  *
- * @gem_objs: Y, Cb, Cr each gem object.
+ * @handles: Y, Cb, Cr each gem object handle.
  * @base: Y, Cb, Cr each planar address.
  */
 struct drm_exynos_ipp_buf_info {
@@ -142,12 +142,12 @@ struct exynos_drm_ipp_ops {
  * @parent_dev: parent device information.
  * @dev: platform device.
  * @drm_dev: drm device.
- * @ipp_id: id of ipp driver.
  * @dedicated: dedicated ipp device.
  * @ops: source, destination operations.
  * @event_workq: event work queue.
  * @c_node: current command information.
  * @cmd_list: list head for command information.
+ * @cmd_lock: lock for synchronization of access to cmd_list.
  * @prop_list: property informations of current ipp driver.
  * @check_property: check property about format, size, buffer.
  * @reset: reset ipp block.
@@ -160,13 +160,13 @@ struct exynos_drm_ippdrv {
 	struct device	*parent_dev;
 	struct device	*dev;
 	struct drm_device	*drm_dev;
-	u32	ipp_id;
 	bool	dedicated;
 	struct exynos_drm_ipp_ops	*ops[EXYNOS_DRM_OPS_MAX];
 	struct workqueue_struct	*event_workq;
 	struct drm_exynos_ipp_cmd_node *c_node;
 	struct list_head	cmd_list;
-	struct drm_exynos_ipp_prop_list *prop_list;
+	struct mutex	cmd_lock;
+	struct drm_exynos_ipp_prop_list prop_list;
 
 	int (*check_property)(struct device *dev,
 		struct drm_exynos_ipp_property *property);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 7b901688def..f01fbb6dc1f 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -158,8 +158,9 @@ static irqreturn_t rotator_irq_handler(int irq, void *arg)
 			rot->cur_buf_id[EXYNOS_DRM_OPS_DST];
 		queue_work(ippdrv->event_workq,
 			(struct work_struct *)event_work);
-	} else
+	} else {
 		DRM_ERROR("the SFR is set illegally\n");
+	}
 
 	return IRQ_HANDLED;
 }
@@ -469,11 +470,7 @@ static struct exynos_drm_ipp_ops rot_dst_ops = {
 
 static int rotator_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
 {
-	struct drm_exynos_ipp_prop_list *prop_list;
-
-	prop_list = devm_kzalloc(ippdrv->dev, sizeof(*prop_list), GFP_KERNEL);
-	if (!prop_list)
-		return -ENOMEM;
+	struct drm_exynos_ipp_prop_list *prop_list = &ippdrv->prop_list;
 
 	prop_list->version = 1;
 	prop_list->flip = (1 << EXYNOS_DRM_FLIP_VERTICAL) |
@@ -486,8 +483,6 @@ static int rotator_init_prop_list(struct exynos_drm_ippdrv *ippdrv)
 	prop_list->crop = 0;
 	prop_list->scale = 0;
 
-	ippdrv->prop_list = prop_list;
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 852f2dadaeb..2fb8705d646 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -51,6 +51,7 @@ struct vidi_context {
 	struct drm_crtc			*crtc;
 	struct drm_encoder		*encoder;
 	struct drm_connector		connector;
+	struct exynos_drm_subdrv	subdrv;
 	struct vidi_win_data		win_data[WINDOWS_NR];
 	struct edid			*raw_edid;
 	unsigned int			clkdiv;
@@ -294,14 +295,13 @@ static void vidi_dpms(struct exynos_drm_manager *mgr, int mode)
 }
 
 static int vidi_mgr_initialize(struct exynos_drm_manager *mgr,
-			struct drm_device *drm_dev, int pipe)
+			struct drm_device *drm_dev)
 {
 	struct vidi_context *ctx = mgr->ctx;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
 
-	DRM_ERROR("vidi initialize ct=%p dev=%p pipe=%d\n", ctx, drm_dev, pipe);
-
-	ctx->drm_dev = drm_dev;
-	ctx->pipe = pipe;
+	mgr->drm_dev = ctx->drm_dev = drm_dev;
+	mgr->pipe = ctx->pipe = priv->pipe++;
 
 	/*
 	 * enable drm irq mode.
@@ -324,7 +324,6 @@ static int vidi_mgr_initialize(struct exynos_drm_manager *mgr,
 }
 
 static struct exynos_drm_manager_ops vidi_manager_ops = {
-	.initialize = vidi_mgr_initialize,
 	.dpms = vidi_dpms,
 	.commit = vidi_commit,
 	.enable_vblank = vidi_enable_vblank,
@@ -533,12 +532,6 @@ static int vidi_get_modes(struct drm_connector *connector)
 	return drm_add_edid_modes(connector, edid);
 }
 
-static int vidi_mode_valid(struct drm_connector *connector,
-			struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
 static struct drm_encoder *vidi_best_encoder(struct drm_connector *connector)
 {
 	struct vidi_context *ctx = ctx_from_connector(connector);
@@ -548,7 +541,6 @@ static struct drm_encoder *vidi_best_encoder(struct drm_connector *connector)
 
 static struct drm_connector_helper_funcs vidi_connector_helper_funcs = {
 	.get_modes = vidi_get_modes,
-	.mode_valid = vidi_mode_valid,
 	.best_encoder = vidi_best_encoder,
 };
 
@@ -586,13 +578,38 @@ static struct exynos_drm_display vidi_display = {
 	.ops = &vidi_display_ops,
 };
 
+static int vidi_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
+{
+	struct exynos_drm_manager *mgr = get_vidi_mgr(dev);
+	struct vidi_context *ctx = mgr->ctx;
+	struct drm_crtc *crtc = ctx->crtc;
+	int ret;
+
+	vidi_mgr_initialize(mgr, drm_dev);
+
+	ret = exynos_drm_crtc_create(&vidi_manager);
+	if (ret) {
+		DRM_ERROR("failed to create crtc.\n");
+		return ret;
+	}
+
+	ret = exynos_drm_create_enc_conn(drm_dev, &vidi_display);
+	if (ret) {
+		crtc->funcs->destroy(crtc);
+		DRM_ERROR("failed to create encoder and connector.\n");
+		return ret;
+	}
+
+	return 0;
+}
+
 static int vidi_probe(struct platform_device *pdev)
 {
-	struct device *dev = &pdev->dev;
+	struct exynos_drm_subdrv *subdrv;
 	struct vidi_context *ctx;
 	int ret;
 
-	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
@@ -607,28 +624,43 @@ static int vidi_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, &vidi_manager);
 
-	ret = device_create_file(dev, &dev_attr_connection);
-	if (ret < 0)
-		DRM_INFO("failed to create connection sysfs.\n");
+	subdrv = &ctx->subdrv;
+	subdrv->dev = &pdev->dev;
+	subdrv->probe = vidi_subdrv_probe;
+
+	ret = exynos_drm_subdrv_register(subdrv);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to register drm vidi device\n");
+		return ret;
+	}
 
-	exynos_drm_manager_register(&vidi_manager);
-	exynos_drm_display_register(&vidi_display);
+	ret = device_create_file(&pdev->dev, &dev_attr_connection);
+	if (ret < 0) {
+		exynos_drm_subdrv_unregister(subdrv);
+		DRM_INFO("failed to create connection sysfs.\n");
+	}
 
 	return 0;
 }
 
 static int vidi_remove(struct platform_device *pdev)
 {
-	struct vidi_context *ctx = platform_get_drvdata(pdev);
-
-	exynos_drm_display_unregister(&vidi_display);
-	exynos_drm_manager_unregister(&vidi_manager);
+	struct exynos_drm_manager *mgr = platform_get_drvdata(pdev);
+	struct vidi_context *ctx = mgr->ctx;
+	struct drm_encoder *encoder = ctx->encoder;
+	struct drm_crtc *crtc = mgr->crtc;
 
 	if (ctx->raw_edid != (struct edid *)fake_edid_info) {
 		kfree(ctx->raw_edid);
 		ctx->raw_edid = NULL;
+
+		return -EINVAL;
 	}
 
+	crtc->funcs->destroy(crtc);
+	encoder->funcs->destroy(encoder);
+	drm_connector_cleanup(&ctx->connector);
+
 	return 0;
 }
 
@@ -640,3 +672,31 @@ struct platform_driver vidi_driver = {
 		.owner	= THIS_MODULE,
 	},
 };
+
+int exynos_drm_probe_vidi(void)
+{
+	struct platform_device *pdev;
+	int ret;
+
+	pdev = platform_device_register_simple("exynos-drm-vidi", -1, NULL, 0);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	ret = platform_driver_register(&vidi_driver);
+	if (ret) {
+		platform_device_unregister(pdev);
+		return ret;
+	}
+
+	return ret;
+}
+
+void exynos_drm_remove_vidi(void)
+{
+	struct vidi_context *ctx = vidi_manager.ctx;
+	struct exynos_drm_subdrv *subdrv = &ctx->subdrv;
+	struct platform_device *pdev = to_platform_device(subdrv->dev);
+
+	platform_driver_unregister(&vidi_driver);
+	platform_device_unregister(pdev);
+}
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 9a6d652a3ef..aa259b0a873 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -33,13 +33,17 @@
 #include <linux/regulator/consumer.h>
 #include <linux/io.h>
 #include <linux/of.h>
-#include <linux/i2c.h>
+#include <linux/of_address.h>
 #include <linux/of_gpio.h>
 #include <linux/hdmi.h>
+#include <linux/component.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include <drm/exynos_drm.h>
 
 #include "exynos_drm_drv.h"
+#include "exynos_drm_crtc.h"
 #include "exynos_mixer.h"
 
 #include <linux/gpio.h>
@@ -48,6 +52,8 @@
 #define get_hdmi_display(dev)	platform_get_drvdata(to_platform_device(dev))
 #define ctx_from_connector(c)	container_of(c, struct hdmi_context, connector)
 
+#define HOTPLUG_DEBOUNCE_MS		1100
+
 /* AVI header and aspect ratio */
 #define HDMI_AVI_VERSION		0x02
 #define HDMI_AVI_LENGTH		0x0D
@@ -66,6 +72,8 @@ enum hdmi_type {
 
 struct hdmi_driver_data {
 	unsigned int type;
+	const struct hdmiphy_config *phy_confs;
+	unsigned int phy_conf_count;
 	unsigned int is_apb_phy:1;
 };
 
@@ -74,7 +82,6 @@ struct hdmi_resources {
 	struct clk			*sclk_hdmi;
 	struct clk			*sclk_pixel;
 	struct clk			*sclk_hdmiphy;
-	struct clk			*hdmiphy;
 	struct clk			*mout_hdmi;
 	struct regulator_bulk_data	*regul_bulk;
 	int				regul_count;
@@ -185,17 +192,23 @@ struct hdmi_context {
 
 	void __iomem			*regs;
 	int				irq;
+	struct delayed_work		hotplug_work;
 
 	struct i2c_adapter		*ddc_adpt;
 	struct i2c_client		*hdmiphy_port;
 
 	/* current hdmiphy conf regs */
+	struct drm_display_mode		current_mode;
 	struct hdmi_conf_regs		mode_conf;
 
 	struct hdmi_resources		res;
 
 	int				hpd_gpio;
+	void __iomem			*regs_hdmiphy;
+	const struct hdmiphy_config		*phy_confs;
+	unsigned int			phy_conf_count;
 
+	struct regmap			*pmureg;
 	enum hdmi_type			type;
 };
 
@@ -204,14 +217,6 @@ struct hdmiphy_config {
 	u8 conf[32];
 };
 
-struct hdmi_driver_data exynos4212_hdmi_driver_data = {
-	.type	= HDMI_TYPE14,
-};
-
-struct hdmi_driver_data exynos5_hdmi_driver_data = {
-	.type	= HDMI_TYPE14,
-};
-
 /* list of phy config settings */
 static const struct hdmiphy_config hdmiphy_v13_configs[] = {
 	{
@@ -319,18 +324,18 @@ static const struct hdmiphy_config hdmiphy_v14_configs[] = {
 	{
 		.pixel_clock = 71000000,
 		.conf = {
-			0x01, 0x91, 0x1e, 0x15, 0x40, 0x3c, 0xce, 0x08,
-			0x04, 0x20, 0xb2, 0xd8, 0x45, 0xa0, 0xac, 0x80,
-			0x06, 0x80, 0x11, 0x04, 0x02, 0x22, 0x44, 0x86,
+			0x01, 0xd1, 0x3b, 0x35, 0x40, 0x0c, 0x04, 0x08,
+			0x85, 0xa0, 0x63, 0xd9, 0x45, 0xa0, 0xac, 0x80,
+			0x08, 0x80, 0x11, 0x04, 0x02, 0x22, 0x44, 0x86,
 			0x54, 0xad, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
 		},
 	},
 	{
 		.pixel_clock = 73250000,
 		.conf = {
-			0x01, 0xd1, 0x1f, 0x15, 0x40, 0x18, 0xe9, 0x08,
-			0x02, 0xa0, 0xb7, 0xd8, 0x45, 0xa0, 0xac, 0x80,
-			0x06, 0x80, 0x11, 0x04, 0x02, 0x22, 0x44, 0x86,
+			0x01, 0xd1, 0x3d, 0x35, 0x40, 0x18, 0x02, 0x08,
+			0x83, 0xa0, 0x6e, 0xd9, 0x45, 0xa0, 0xac, 0x80,
+			0x08, 0x80, 0x11, 0x04, 0x02, 0x22, 0x44, 0x86,
 			0x54, 0xa8, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
 		},
 	},
@@ -362,15 +367,6 @@ static const struct hdmiphy_config hdmiphy_v14_configs[] = {
 		},
 	},
 	{
-		.pixel_clock = 88750000,
-		.conf = {
-			0x01, 0x91, 0x25, 0x17, 0x40, 0x30, 0xfe, 0x08,
-			0x06, 0x20, 0xde, 0xd8, 0x45, 0xa0, 0xac, 0x80,
-			0x06, 0x80, 0x11, 0x04, 0x02, 0x22, 0x44, 0x86,
-			0x54, 0x8a, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
-		},
-	},
-	{
 		.pixel_clock = 106500000,
 		.conf = {
 			0x01, 0xd1, 0x2c, 0x12, 0x40, 0x0c, 0x09, 0x08,
@@ -391,18 +387,18 @@ static const struct hdmiphy_config hdmiphy_v14_configs[] = {
 	{
 		.pixel_clock = 115500000,
 		.conf = {
-			0x01, 0xd1, 0x30, 0x1a, 0x40, 0x40, 0x10, 0x04,
-			0x04, 0xa0, 0x21, 0xd9, 0x45, 0xa0, 0xac, 0x80,
-			0x06, 0x80, 0x11, 0x04, 0x02, 0x22, 0x44, 0x86,
+			0x01, 0xd1, 0x30, 0x12, 0x40, 0x40, 0x10, 0x08,
+			0x80, 0x80, 0x21, 0xd9, 0x45, 0xa0, 0xac, 0x80,
+			0x08, 0x80, 0x11, 0x04, 0x02, 0x22, 0x44, 0x86,
 			0x54, 0xaa, 0x25, 0x03, 0x00, 0x00, 0x01, 0x80,
 		},
 	},
 	{
 		.pixel_clock = 119000000,
 		.conf = {
-			0x01, 0x91, 0x32, 0x14, 0x40, 0x60, 0xd8, 0x08,
-			0x06, 0x20, 0x2a, 0xd9, 0x45, 0xa0, 0xac, 0x80,
-			0x06, 0x80, 0x11, 0x04, 0x02, 0x22, 0x44, 0x86,
+			0x01, 0xd1, 0x32, 0x1a, 0x40, 0x30, 0xd8, 0x08,
+			0x04, 0xa0, 0x2a, 0xd9, 0x45, 0xa0, 0xac, 0x80,
+			0x08, 0x80, 0x11, 0x04, 0x02, 0x22, 0x44, 0x86,
 			0x54, 0x9d, 0x25, 0x03, 0x00, 0x00, 0x01, 0x80,
 		},
 	},
@@ -426,6 +422,183 @@ static const struct hdmiphy_config hdmiphy_v14_configs[] = {
 	},
 };
 
+static const struct hdmiphy_config hdmiphy_5420_configs[] = {
+	{
+		.pixel_clock = 25200000,
+		.conf = {
+			0x01, 0x52, 0x3F, 0x55, 0x40, 0x01, 0x00, 0xC8,
+			0x82, 0xC8, 0xBD, 0xD8, 0x45, 0xA0, 0xAC, 0x80,
+			0x06, 0x80, 0x01, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0xF4, 0x24, 0x00, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 27000000,
+		.conf = {
+			0x01, 0xD1, 0x22, 0x51, 0x40, 0x08, 0xFC, 0xE0,
+			0x98, 0xE8, 0xCB, 0xD8, 0x45, 0xA0, 0xAC, 0x80,
+			0x06, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0xE4, 0x24, 0x00, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 27027000,
+		.conf = {
+			0x01, 0xD1, 0x2D, 0x72, 0x40, 0x64, 0x12, 0xC8,
+			0x43, 0xE8, 0x0E, 0xD9, 0x45, 0xA0, 0xAC, 0x80,
+			0x26, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0xE3, 0x24, 0x00, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 36000000,
+		.conf = {
+			0x01, 0x51, 0x2D, 0x55, 0x40, 0x40, 0x00, 0xC8,
+			0x02, 0xC8, 0x0E, 0xD9, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0xAB, 0x24, 0x00, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 40000000,
+		.conf = {
+			0x01, 0xD1, 0x21, 0x31, 0x40, 0x3C, 0x28, 0xC8,
+			0x87, 0xE8, 0xC8, 0xD8, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0x9A, 0x24, 0x00, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 65000000,
+		.conf = {
+			0x01, 0xD1, 0x36, 0x34, 0x40, 0x0C, 0x04, 0xC8,
+			0x82, 0xE8, 0x45, 0xD9, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0xBD, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 71000000,
+		.conf = {
+			0x01, 0xD1, 0x3B, 0x35, 0x40, 0x0C, 0x04, 0xC8,
+			0x85, 0xE8, 0x63, 0xD9, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0x57, 0x24, 0x00, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 73250000,
+		.conf = {
+			0x01, 0xD1, 0x1F, 0x10, 0x40, 0x78, 0x8D, 0xC8,
+			0x81, 0xE8, 0xB7, 0xD8, 0x45, 0xA0, 0xAC, 0x80,
+			0x56, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0xA8, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 74176000,
+		.conf = {
+			0x01, 0xD1, 0x1F, 0x10, 0x40, 0x5B, 0xEF, 0xC8,
+			0x81, 0xE8, 0xB9, 0xD8, 0x45, 0xA0, 0xAC, 0x80,
+			0x56, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0xA6, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 74250000,
+		.conf = {
+			0x01, 0xD1, 0x1F, 0x10, 0x40, 0x40, 0xF8, 0x08,
+			0x81, 0xE8, 0xBA, 0xD8, 0x45, 0xA0, 0xAC, 0x80,
+			0x26, 0x80, 0x09, 0x84, 0x05, 0x22, 0x24, 0x66,
+			0x54, 0xA5, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 83500000,
+		.conf = {
+			0x01, 0xD1, 0x23, 0x11, 0x40, 0x0C, 0xFB, 0xC8,
+			0x85, 0xE8, 0xD1, 0xD8, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0x4A, 0x24, 0x00, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 88750000,
+		.conf = {
+			0x01, 0xD1, 0x25, 0x11, 0x40, 0x18, 0xFF, 0xC8,
+			0x83, 0xE8, 0xDE, 0xD8, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0x45, 0x24, 0x00, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 106500000,
+		.conf = {
+			0x01, 0xD1, 0x2C, 0x12, 0x40, 0x0C, 0x09, 0xC8,
+			0x84, 0xE8, 0x0A, 0xD9, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0x73, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 108000000,
+		.conf = {
+			0x01, 0x51, 0x2D, 0x15, 0x40, 0x01, 0x00, 0xC8,
+			0x82, 0xC8, 0x0E, 0xD9, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0xC7, 0x25, 0x03, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 115500000,
+		.conf = {
+			0x01, 0xD1, 0x30, 0x14, 0x40, 0x0C, 0x03, 0xC8,
+			0x88, 0xE8, 0x21, 0xD9, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0x6A, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 146250000,
+		.conf = {
+			0x01, 0xD1, 0x3D, 0x15, 0x40, 0x18, 0xFD, 0xC8,
+			0x83, 0xE8, 0x6E, 0xD9, 0x45, 0xA0, 0xAC, 0x80,
+			0x08, 0x80, 0x09, 0x84, 0x05, 0x02, 0x24, 0x66,
+			0x54, 0x54, 0x24, 0x01, 0x00, 0x00, 0x01, 0x80,
+		},
+	},
+	{
+		.pixel_clock = 148500000,
+		.conf = {
+			0x01, 0xD1, 0x1F, 0x00, 0x40, 0x40, 0xF8, 0x08,
+			0x81, 0xE8, 0xBA, 0xD8, 0x45, 0xA0, 0xAC, 0x80,
+			0x26, 0x80, 0x09, 0x84, 0x05, 0x22, 0x24, 0x66,
+			0x54, 0x4B, 0x25, 0x03, 0x00, 0x80, 0x01, 0x80,
+		},
+	},
+};
+
+static struct hdmi_driver_data exynos5420_hdmi_driver_data = {
+	.type		= HDMI_TYPE14,
+	.phy_confs	= hdmiphy_5420_configs,
+	.phy_conf_count	= ARRAY_SIZE(hdmiphy_5420_configs),
+	.is_apb_phy	= 1,
+};
+
+static struct hdmi_driver_data exynos4212_hdmi_driver_data = {
+	.type		= HDMI_TYPE14,
+	.phy_confs	= hdmiphy_v14_configs,
+	.phy_conf_count	= ARRAY_SIZE(hdmiphy_v14_configs),
+	.is_apb_phy	= 0,
+};
+
+static struct hdmi_driver_data exynos5_hdmi_driver_data = {
+	.type		= HDMI_TYPE14,
+	.phy_confs	= hdmiphy_v13_configs,
+	.phy_conf_count	= ARRAY_SIZE(hdmiphy_v13_configs),
+	.is_apb_phy	= 0,
+};
+
 static inline u32 hdmi_reg_read(struct hdmi_context *hdata, u32 reg_id)
 {
 	return readl(hdata->regs + reg_id);
@@ -445,6 +618,48 @@ static inline void hdmi_reg_writemask(struct hdmi_context *hdata,
 	writel(value, hdata->regs + reg_id);
 }
 
+static int hdmiphy_reg_writeb(struct hdmi_context *hdata,
+			u32 reg_offset, u8 value)
+{
+	if (hdata->hdmiphy_port) {
+		u8 buffer[2];
+		int ret;
+
+		buffer[0] = reg_offset;
+		buffer[1] = value;
+
+		ret = i2c_master_send(hdata->hdmiphy_port, buffer, 2);
+		if (ret == 2)
+			return 0;
+		return ret;
+	} else {
+		writeb(value, hdata->regs_hdmiphy + (reg_offset<<2));
+		return 0;
+	}
+}
+
+static int hdmiphy_reg_write_buf(struct hdmi_context *hdata,
+			u32 reg_offset, const u8 *buf, u32 len)
+{
+	if ((reg_offset + len) > 32)
+		return -EINVAL;
+
+	if (hdata->hdmiphy_port) {
+		int ret;
+
+		ret = i2c_master_send(hdata->hdmiphy_port, buf, len);
+		if (ret == len)
+			return 0;
+		return ret;
+	} else {
+		int i;
+		for (i = 0; i < len; i++)
+			writeb(buf[i], hdata->regs_hdmiphy +
+				((reg_offset + i)<<2));
+		return 0;
+	}
+}
+
 static void hdmi_v13_regs_dump(struct hdmi_context *hdata, char *prefix)
 {
 #define DUMPREG(reg_id) \
@@ -809,6 +1024,8 @@ static enum drm_connector_status hdmi_detect(struct drm_connector *connector,
 {
 	struct hdmi_context *hdata = ctx_from_connector(connector);
 
+	hdata->hpd = gpio_get_value(hdata->hpd_gpio);
+
 	return hdata->hpd ? connector_status_connected :
 			connector_status_disconnected;
 }
@@ -848,20 +1065,10 @@ static int hdmi_get_modes(struct drm_connector *connector)
 
 static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock)
 {
-	const struct hdmiphy_config *confs;
-	int count, i;
-
-	if (hdata->type == HDMI_TYPE13) {
-		confs = hdmiphy_v13_configs;
-		count = ARRAY_SIZE(hdmiphy_v13_configs);
-	} else if (hdata->type == HDMI_TYPE14) {
-		confs = hdmiphy_v14_configs;
-		count = ARRAY_SIZE(hdmiphy_v14_configs);
-	} else
-		return -EINVAL;
+	int i;
 
-	for (i = 0; i < count; i++)
-		if (confs[i].pixel_clock == pixel_clock)
+	for (i = 0; i < hdata->phy_conf_count; i++)
+		if (hdata->phy_confs[i].pixel_clock == pixel_clock)
 			return i;
 
 	DRM_DEBUG_KMS("Could not find phy config for %d\n", pixel_clock);
@@ -928,16 +1135,6 @@ static int hdmi_create_connector(struct exynos_drm_display *display,
 	return 0;
 }
 
-static int hdmi_initialize(struct exynos_drm_display *display,
-			struct drm_device *drm_dev)
-{
-	struct hdmi_context *hdata = display->ctx;
-
-	hdata->drm_dev = drm_dev;
-
-	return 0;
-}
-
 static void hdmi_mode_fixup(struct exynos_drm_display *display,
 				struct drm_connector *connector,
 				const struct drm_display_mode *mode,
@@ -1136,20 +1333,15 @@ static void hdmi_audio_control(struct hdmi_context *hdata, bool onoff)
 			HDMI_ASP_EN : HDMI_ASP_DIS, HDMI_ASP_MASK);
 }
 
-static void hdmi_conf_reset(struct hdmi_context *hdata)
+static void hdmi_start(struct hdmi_context *hdata, bool start)
 {
-	u32 reg;
+	u32 val = start ? HDMI_TG_EN : 0;
 
-	if (hdata->type == HDMI_TYPE13)
-		reg = HDMI_V13_CORE_RSTOUT;
-	else
-		reg = HDMI_CORE_RSTOUT;
+	if (hdata->current_mode.flags & DRM_MODE_FLAG_INTERLACE)
+		val |= HDMI_FIELD_EN;
 
-	/* resetting HDMI core */
-	hdmi_reg_writemask(hdata, reg,  0, HDMI_CORE_SW_RSTOUT);
-	usleep_range(10000, 12000);
-	hdmi_reg_writemask(hdata, reg, ~0, HDMI_CORE_SW_RSTOUT);
-	usleep_range(10000, 12000);
+	hdmi_reg_writemask(hdata, HDMI_CON_0, val, HDMI_EN);
+	hdmi_reg_writemask(hdata, HDMI_TG_CMD, val, HDMI_TG_EN | HDMI_FIELD_EN);
 }
 
 static void hdmi_conf_init(struct hdmi_context *hdata)
@@ -1163,6 +1355,8 @@ static void hdmi_conf_init(struct hdmi_context *hdata)
 	/* choose HDMI mode */
 	hdmi_reg_writemask(hdata, HDMI_MODE_SEL,
 		HDMI_MODE_HDMI_EN, HDMI_MODE_MASK);
+	/* Apply Video preable and Guard band in HDMI mode only */
+	hdmi_reg_writeb(hdata, HDMI_CON_2, 0);
 	/* disable bluescreen */
 	hdmi_reg_writemask(hdata, HDMI_CON_0, 0, HDMI_BLUE_SCR_EN);
 
@@ -1286,12 +1480,7 @@ static void hdmi_v13_mode_apply(struct hdmi_context *hdata)
 	clk_prepare_enable(hdata->res.sclk_hdmi);
 
 	/* enable HDMI and timing generator */
-	hdmi_reg_writemask(hdata, HDMI_CON_0, ~0, HDMI_EN);
-	if (core->int_pro_mode[0])
-		hdmi_reg_writemask(hdata, HDMI_TG_CMD, ~0, HDMI_TG_EN |
-				HDMI_FIELD_EN);
-	else
-		hdmi_reg_writemask(hdata, HDMI_TG_CMD, ~0, HDMI_TG_EN);
+	hdmi_start(hdata, true);
 }
 
 static void hdmi_v14_mode_apply(struct hdmi_context *hdata)
@@ -1453,12 +1642,7 @@ static void hdmi_v14_mode_apply(struct hdmi_context *hdata)
 	clk_prepare_enable(hdata->res.sclk_hdmi);
 
 	/* enable HDMI and timing generator */
-	hdmi_reg_writemask(hdata, HDMI_CON_0, ~0, HDMI_EN);
-	if (core->int_pro_mode[0])
-		hdmi_reg_writemask(hdata, HDMI_TG_CMD, ~0, HDMI_TG_EN |
-				HDMI_FIELD_EN);
-	else
-		hdmi_reg_writemask(hdata, HDMI_TG_CMD, ~0, HDMI_TG_EN);
+	hdmi_start(hdata, true);
 }
 
 static void hdmi_mode_apply(struct hdmi_context *hdata)
@@ -1499,32 +1683,51 @@ static void hdmiphy_conf_reset(struct hdmi_context *hdata)
 
 static void hdmiphy_poweron(struct hdmi_context *hdata)
 {
-	if (hdata->type == HDMI_TYPE14)
-		hdmi_reg_writemask(hdata, HDMI_PHY_CON_0, 0,
-			HDMI_PHY_POWER_OFF_EN);
+	if (hdata->type != HDMI_TYPE14)
+		return;
+
+	DRM_DEBUG_KMS("\n");
+
+	/* For PHY Mode Setting */
+	hdmiphy_reg_writeb(hdata, HDMIPHY_MODE_SET_DONE,
+				HDMI_PHY_ENABLE_MODE_SET);
+	/* Phy Power On */
+	hdmiphy_reg_writeb(hdata, HDMIPHY_POWER,
+				HDMI_PHY_POWER_ON);
+	/* For PHY Mode Setting */
+	hdmiphy_reg_writeb(hdata, HDMIPHY_MODE_SET_DONE,
+				HDMI_PHY_DISABLE_MODE_SET);
+	/* PHY SW Reset */
+	hdmiphy_conf_reset(hdata);
 }
 
 static void hdmiphy_poweroff(struct hdmi_context *hdata)
 {
-	if (hdata->type == HDMI_TYPE14)
-		hdmi_reg_writemask(hdata, HDMI_PHY_CON_0, ~0,
-			HDMI_PHY_POWER_OFF_EN);
+	if (hdata->type != HDMI_TYPE14)
+		return;
+
+	DRM_DEBUG_KMS("\n");
+
+	/* PHY SW Reset */
+	hdmiphy_conf_reset(hdata);
+	/* For PHY Mode Setting */
+	hdmiphy_reg_writeb(hdata, HDMIPHY_MODE_SET_DONE,
+				HDMI_PHY_ENABLE_MODE_SET);
+
+	/* PHY Power Off */
+	hdmiphy_reg_writeb(hdata, HDMIPHY_POWER,
+				HDMI_PHY_POWER_OFF);
+
+	/* For PHY Mode Setting */
+	hdmiphy_reg_writeb(hdata, HDMIPHY_MODE_SET_DONE,
+				HDMI_PHY_DISABLE_MODE_SET);
 }
 
 static void hdmiphy_conf_apply(struct hdmi_context *hdata)
 {
-	const u8 *hdmiphy_data;
-	u8 buffer[32];
-	u8 operation[2];
-	u8 read_buffer[32] = {0, };
 	int ret;
 	int i;
 
-	if (!hdata->hdmiphy_port) {
-		DRM_ERROR("hdmiphy is not attached\n");
-		return;
-	}
-
 	/* pixel clock */
 	i = hdmi_find_phy_conf(hdata, hdata->mode_conf.pixel_clock);
 	if (i < 0) {
@@ -1532,39 +1735,21 @@ static void hdmiphy_conf_apply(struct hdmi_context *hdata)
 		return;
 	}
 
-	if (hdata->type == HDMI_TYPE13)
-		hdmiphy_data = hdmiphy_v13_configs[i].conf;
-	else
-		hdmiphy_data = hdmiphy_v14_configs[i].conf;
-
-	memcpy(buffer, hdmiphy_data, 32);
-	ret = i2c_master_send(hdata->hdmiphy_port, buffer, 32);
-	if (ret != 32) {
-		DRM_ERROR("failed to configure HDMIPHY via I2C\n");
+	ret = hdmiphy_reg_write_buf(hdata, 0, hdata->phy_confs[i].conf, 32);
+	if (ret) {
+		DRM_ERROR("failed to configure hdmiphy\n");
 		return;
 	}
 
 	usleep_range(10000, 12000);
 
-	/* operation mode */
-	operation[0] = 0x1f;
-	operation[1] = 0x80;
-
-	ret = i2c_master_send(hdata->hdmiphy_port, operation, 2);
-	if (ret != 2) {
+	ret = hdmiphy_reg_writeb(hdata, HDMIPHY_MODE_SET_DONE,
+				HDMI_PHY_DISABLE_MODE_SET);
+	if (ret) {
 		DRM_ERROR("failed to enable hdmiphy\n");
 		return;
 	}
 
-	ret = i2c_master_recv(hdata->hdmiphy_port, read_buffer, 32);
-	if (ret < 0) {
-		DRM_ERROR("failed to read hdmiphy config\n");
-		return;
-	}
-
-	for (i = 0; i < ret; i++)
-		DRM_DEBUG_KMS("hdmiphy[0x%02x] write[0x%02x] - "
-			"recv [0x%02x]\n", i, buffer[i], read_buffer[i]);
 }
 
 static void hdmi_conf_apply(struct hdmi_context *hdata)
@@ -1573,7 +1758,7 @@ static void hdmi_conf_apply(struct hdmi_context *hdata)
 	hdmiphy_conf_apply(hdata);
 
 	mutex_lock(&hdata->hdmi_mutex);
-	hdmi_conf_reset(hdata);
+	hdmi_start(hdata, false);
 	hdmi_conf_init(hdata);
 	mutex_unlock(&hdata->hdmi_mutex);
 
@@ -1814,6 +1999,9 @@ static void hdmi_mode_set(struct exynos_drm_display *display,
 		m->vrefresh, (m->flags & DRM_MODE_FLAG_INTERLACE) ?
 		"INTERLACED" : "PROGERESSIVE");
 
+	/* preserve mode information for later use. */
+	drm_mode_copy(&hdata->current_mode, mode);
+
 	if (hdata->type == HDMI_TYPE13)
 		hdmi_v13_mode_set(hdata, mode);
 	else
@@ -1854,7 +2042,10 @@ static void hdmi_poweron(struct exynos_drm_display *display)
 	if (regulator_bulk_enable(res->regul_count, res->regul_bulk))
 		DRM_DEBUG_KMS("failed to enable regulator bulk\n");
 
-	clk_prepare_enable(res->hdmiphy);
+	/* set pmu hdmiphy control bit to enable hdmiphy */
+	regmap_update_bits(hdata->pmureg, PMU_HDMI_PHY_CONTROL,
+			PMU_HDMI_PHY_ENABLE_BIT, 1);
+
 	clk_prepare_enable(res->hdmi);
 	clk_prepare_enable(res->sclk_hdmi);
 
@@ -1872,16 +2063,20 @@ static void hdmi_poweroff(struct exynos_drm_display *display)
 		goto out;
 	mutex_unlock(&hdata->hdmi_mutex);
 
-	/*
-	 * The TV power domain needs any condition of hdmiphy to turn off and
-	 * its reset state seems to meet the condition.
-	 */
-	hdmiphy_conf_reset(hdata);
+	/* HDMI System Disable */
+	hdmi_reg_writemask(hdata, HDMI_CON_0, 0, HDMI_EN);
+
 	hdmiphy_poweroff(hdata);
 
+	cancel_delayed_work(&hdata->hotplug_work);
+
 	clk_disable_unprepare(res->sclk_hdmi);
 	clk_disable_unprepare(res->hdmi);
-	clk_disable_unprepare(res->hdmiphy);
+
+	/* reset pmu hdmiphy control bit to disable hdmiphy */
+	regmap_update_bits(hdata->pmureg, PMU_HDMI_PHY_CONTROL,
+			PMU_HDMI_PHY_ENABLE_BIT, 0);
+
 	regulator_bulk_disable(res->regul_count, res->regul_bulk);
 
 	pm_runtime_put_sync(hdata->dev);
@@ -1895,6 +2090,11 @@ out:
 
 static void hdmi_dpms(struct exynos_drm_display *display, int mode)
 {
+	struct hdmi_context *hdata = display->ctx;
+	struct drm_encoder *encoder = hdata->encoder;
+	struct drm_crtc *crtc = encoder->crtc;
+	struct drm_crtc_helper_funcs *funcs = NULL;
+
 	DRM_DEBUG_KMS("mode %d\n", mode);
 
 	switch (mode) {
@@ -1904,6 +2104,20 @@ static void hdmi_dpms(struct exynos_drm_display *display, int mode)
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 	case DRM_MODE_DPMS_OFF:
+		/*
+		 * The SFRs of VP and Mixer are updated by Vertical Sync of
+		 * Timing generator which is a part of HDMI so the sequence
+		 * to disable TV Subsystem should be as following,
+		 *	VP -> Mixer -> HDMI
+		 *
+		 * Below codes will try to disable Mixer and VP(if used)
+		 * prior to disabling HDMI.
+		 */
+		if (crtc)
+			funcs = crtc->helper_private;
+		if (funcs && funcs->dpms)
+			(*funcs->dpms)(crtc, mode);
+
 		hdmi_poweroff(display);
 		break;
 	default:
@@ -1913,7 +2127,6 @@ static void hdmi_dpms(struct exynos_drm_display *display, int mode)
 }
 
 static struct exynos_drm_display_ops hdmi_display_ops = {
-	.initialize	= hdmi_initialize,
 	.create_connector = hdmi_create_connector,
 	.mode_fixup	= hdmi_mode_fixup,
 	.mode_set	= hdmi_mode_set,
@@ -1926,9 +2139,11 @@ static struct exynos_drm_display hdmi_display = {
 	.ops = &hdmi_display_ops,
 };
 
-static irqreturn_t hdmi_irq_thread(int irq, void *arg)
+static void hdmi_hotplug_work_func(struct work_struct *work)
 {
-	struct hdmi_context *hdata = arg;
+	struct hdmi_context *hdata;
+
+	hdata = container_of(work, struct hdmi_context, hotplug_work.work);
 
 	mutex_lock(&hdata->hdmi_mutex);
 	hdata->hpd = gpio_get_value(hdata->hpd_gpio);
@@ -1936,6 +2151,14 @@ static irqreturn_t hdmi_irq_thread(int irq, void *arg)
 
 	if (hdata->drm_dev)
 		drm_helper_hpd_irq_event(hdata->drm_dev);
+}
+
+static irqreturn_t hdmi_irq_thread(int irq, void *arg)
+{
+	struct hdmi_context *hdata = arg;
+
+	mod_delayed_work(system_wq, &hdata->hotplug_work,
+			msecs_to_jiffies(HOTPLUG_DEBOUNCE_MS));
 
 	return IRQ_HANDLED;
 }
@@ -1954,37 +2177,35 @@ static int hdmi_resources_init(struct hdmi_context *hdata)
 
 	DRM_DEBUG_KMS("HDMI resource init\n");
 
-	memset(res, 0, sizeof(*res));
-
 	/* get clocks, power */
 	res->hdmi = devm_clk_get(dev, "hdmi");
 	if (IS_ERR(res->hdmi)) {
 		DRM_ERROR("failed to get clock 'hdmi'\n");
+		ret = PTR_ERR(res->hdmi);
 		goto fail;
 	}
 	res->sclk_hdmi = devm_clk_get(dev, "sclk_hdmi");
 	if (IS_ERR(res->sclk_hdmi)) {
 		DRM_ERROR("failed to get clock 'sclk_hdmi'\n");
+		ret = PTR_ERR(res->sclk_hdmi);
 		goto fail;
 	}
 	res->sclk_pixel = devm_clk_get(dev, "sclk_pixel");
 	if (IS_ERR(res->sclk_pixel)) {
 		DRM_ERROR("failed to get clock 'sclk_pixel'\n");
+		ret = PTR_ERR(res->sclk_pixel);
 		goto fail;
 	}
 	res->sclk_hdmiphy = devm_clk_get(dev, "sclk_hdmiphy");
 	if (IS_ERR(res->sclk_hdmiphy)) {
 		DRM_ERROR("failed to get clock 'sclk_hdmiphy'\n");
-		goto fail;
-	}
-	res->hdmiphy = devm_clk_get(dev, "hdmiphy");
-	if (IS_ERR(res->hdmiphy)) {
-		DRM_ERROR("failed to get clock 'hdmiphy'\n");
+		ret = PTR_ERR(res->sclk_hdmiphy);
 		goto fail;
 	}
 	res->mout_hdmi = devm_clk_get(dev, "mout_hdmi");
 	if (IS_ERR(res->mout_hdmi)) {
 		DRM_ERROR("failed to get clock 'mout_hdmi'\n");
+		ret = PTR_ERR(res->mout_hdmi);
 		goto fail;
 	}
 
@@ -1992,8 +2213,10 @@ static int hdmi_resources_init(struct hdmi_context *hdata)
 
 	res->regul_bulk = devm_kzalloc(dev, ARRAY_SIZE(supply) *
 		sizeof(res->regul_bulk[0]), GFP_KERNEL);
-	if (!res->regul_bulk)
+	if (!res->regul_bulk) {
+		ret = -ENOMEM;
 		goto fail;
+	}
 	for (i = 0; i < ARRAY_SIZE(supply); ++i) {
 		res->regul_bulk[i].supply = supply[i];
 		res->regul_bulk[i].consumer = NULL;
@@ -2001,14 +2224,14 @@ static int hdmi_resources_init(struct hdmi_context *hdata)
 	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(supply), res->regul_bulk);
 	if (ret) {
 		DRM_ERROR("failed to get regulators\n");
-		goto fail;
+		return ret;
 	}
 	res->regul_count = ARRAY_SIZE(supply);
 
-	return 0;
+	return ret;
 fail:
 	DRM_ERROR("HDMI resource init - failed\n");
-	return -ENODEV;
+	return ret;
 }
 
 static struct s5p_hdmi_platform_data *drm_hdmi_dt_parse_pdata
@@ -2043,42 +2266,105 @@ static struct of_device_id hdmi_match_types[] = {
 		.compatible = "samsung,exynos4212-hdmi",
 		.data = &exynos4212_hdmi_driver_data,
 	}, {
+		.compatible = "samsung,exynos5420-hdmi",
+		.data = &exynos5420_hdmi_driver_data,
+	}, {
 		/* end node */
 	}
 };
 
+static int hdmi_bind(struct device *dev, struct device *master, void *data)
+{
+	struct drm_device *drm_dev = data;
+	struct hdmi_context *hdata;
+
+	hdata = hdmi_display.ctx;
+	hdata->drm_dev = drm_dev;
+
+	return exynos_drm_create_enc_conn(drm_dev, &hdmi_display);
+}
+
+static void hdmi_unbind(struct device *dev, struct device *master, void *data)
+{
+	struct exynos_drm_display *display = get_hdmi_display(dev);
+	struct drm_encoder *encoder = display->encoder;
+	struct hdmi_context *hdata = display->ctx;
+
+	encoder->funcs->destroy(encoder);
+	drm_connector_cleanup(&hdata->connector);
+}
+
+static const struct component_ops hdmi_component_ops = {
+	.bind	= hdmi_bind,
+	.unbind = hdmi_unbind,
+};
+
+static struct device_node *hdmi_legacy_ddc_dt_binding(struct device *dev)
+{
+	const char *compatible_str = "samsung,exynos4210-hdmiddc";
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL, compatible_str);
+	if (np)
+		return of_get_next_parent(np);
+
+	return NULL;
+}
+
+static struct device_node *hdmi_legacy_phy_dt_binding(struct device *dev)
+{
+	const char *compatible_str = "samsung,exynos4212-hdmiphy";
+
+	return of_find_compatible_node(NULL, NULL, compatible_str);
+}
+
 static int hdmi_probe(struct platform_device *pdev)
 {
+	struct device_node *ddc_node, *phy_node;
+	struct s5p_hdmi_platform_data *pdata;
+	struct hdmi_driver_data *drv_data;
+	const struct of_device_id *match;
 	struct device *dev = &pdev->dev;
 	struct hdmi_context *hdata;
-	struct s5p_hdmi_platform_data *pdata;
 	struct resource *res;
-	const struct of_device_id *match;
-	struct device_node *ddc_node, *phy_node;
-	struct hdmi_driver_data *drv_data;
 	int ret;
 
-	 if (!dev->of_node)
-		return -ENODEV;
+	ret = exynos_drm_component_add(&pdev->dev, EXYNOS_DEVICE_TYPE_CONNECTOR,
+					hdmi_display.type);
+	if (ret)
+		return ret;
+
+	if (!dev->of_node) {
+		ret = -ENODEV;
+		goto err_del_component;
+	}
 
 	pdata = drm_hdmi_dt_parse_pdata(dev);
-	if (!pdata)
-		return -EINVAL;
+	if (!pdata) {
+		ret = -EINVAL;
+		goto err_del_component;
+	}
 
 	hdata = devm_kzalloc(dev, sizeof(struct hdmi_context), GFP_KERNEL);
-	if (!hdata)
-		return -ENOMEM;
+	if (!hdata) {
+		ret = -ENOMEM;
+		goto err_del_component;
+	}
 
 	mutex_init(&hdata->hdmi_mutex);
 
 	platform_set_drvdata(pdev, &hdmi_display);
 
 	match = of_match_node(hdmi_match_types, dev->of_node);
-	if (!match)
-		return -ENODEV;
+	if (!match) {
+		ret = -ENODEV;
+		goto err_del_component;
+	}
 
 	drv_data = (struct hdmi_driver_data *)match->data;
 	hdata->type = drv_data->type;
+	hdata->phy_confs = drv_data->phy_confs;
+	hdata->phy_conf_count = drv_data->phy_conf_count;
 
 	hdata->hpd_gpio = pdata->hpd_gpio;
 	hdata->dev = dev;
@@ -2086,35 +2372,44 @@ static int hdmi_probe(struct platform_device *pdev)
 	ret = hdmi_resources_init(hdata);
 	if (ret) {
 		DRM_ERROR("hdmi_resources_init failed\n");
-		return -EINVAL;
+		return ret;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	hdata->regs = devm_ioremap_resource(dev, res);
-	if (IS_ERR(hdata->regs))
-		return PTR_ERR(hdata->regs);
+	if (IS_ERR(hdata->regs)) {
+		ret = PTR_ERR(hdata->regs);
+		goto err_del_component;
+	}
 
 	ret = devm_gpio_request(dev, hdata->hpd_gpio, "HPD");
 	if (ret) {
 		DRM_ERROR("failed to request HPD gpio\n");
-		return ret;
+		goto err_del_component;
 	}
 
+	ddc_node = hdmi_legacy_ddc_dt_binding(dev);
+	if (ddc_node)
+		goto out_get_ddc_adpt;
+
 	/* DDC i2c driver */
 	ddc_node = of_parse_phandle(dev->of_node, "ddc", 0);
 	if (!ddc_node) {
 		DRM_ERROR("Failed to find ddc node in device tree\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_del_component;
 	}
+
+out_get_ddc_adpt:
 	hdata->ddc_adpt = of_find_i2c_adapter_by_node(ddc_node);
 	if (!hdata->ddc_adpt) {
 		DRM_ERROR("Failed to get ddc i2c adapter by node\n");
-		return -ENODEV;
+		return -EPROBE_DEFER;
 	}
 
-	/* Not support APB PHY yet. */
-	if (drv_data->is_apb_phy)
-		return -EPERM;
+	phy_node = hdmi_legacy_phy_dt_binding(dev);
+	if (phy_node)
+		goto out_get_phy_port;
 
 	/* hdmiphy i2c driver */
 	phy_node = of_parse_phandle(dev->of_node, "phy", 0);
@@ -2123,11 +2418,22 @@ static int hdmi_probe(struct platform_device *pdev)
 		ret = -ENODEV;
 		goto err_ddc;
 	}
-	hdata->hdmiphy_port = of_find_i2c_device_by_node(phy_node);
-	if (!hdata->hdmiphy_port) {
-		DRM_ERROR("Failed to get hdmi phy i2c client from node\n");
-		ret = -ENODEV;
-		goto err_ddc;
+
+out_get_phy_port:
+	if (drv_data->is_apb_phy) {
+		hdata->regs_hdmiphy = of_iomap(phy_node, 0);
+		if (!hdata->regs_hdmiphy) {
+			DRM_ERROR("failed to ioremap hdmi phy\n");
+			ret = -ENOMEM;
+			goto err_ddc;
+		}
+	} else {
+		hdata->hdmiphy_port = of_find_i2c_device_by_node(phy_node);
+		if (!hdata->hdmiphy_port) {
+			DRM_ERROR("Failed to get hdmi phy i2c client\n");
+			ret = -EPROBE_DEFER;
+			goto err_ddc;
+		}
 	}
 
 	hdata->irq = gpio_to_irq(hdata->hpd_gpio);
@@ -2139,6 +2445,8 @@ static int hdmi_probe(struct platform_device *pdev)
 
 	hdata->hpd = gpio_get_value(hdata->hpd_gpio);
 
+	INIT_DELAYED_WORK(&hdata->hotplug_work, hdmi_hotplug_work_func);
+
 	ret = devm_request_threaded_irq(dev, hdata->irq, NULL,
 			hdmi_irq_thread, IRQF_TRIGGER_RISING |
 			IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
@@ -2148,30 +2456,51 @@ static int hdmi_probe(struct platform_device *pdev)
 		goto err_hdmiphy;
 	}
 
-	pm_runtime_enable(dev);
+	hdata->pmureg = syscon_regmap_lookup_by_phandle(dev->of_node,
+			"samsung,syscon-phandle");
+	if (IS_ERR(hdata->pmureg)) {
+		DRM_ERROR("syscon regmap lookup failed.\n");
+		ret = -EPROBE_DEFER;
+		goto err_hdmiphy;
+	}
 
+	pm_runtime_enable(dev);
 	hdmi_display.ctx = hdata;
-	exynos_drm_display_register(&hdmi_display);
 
-	return 0;
+	ret = component_add(&pdev->dev, &hdmi_component_ops);
+	if (ret)
+		goto err_disable_pm_runtime;
+
+	return ret;
+
+err_disable_pm_runtime:
+	pm_runtime_disable(dev);
 
 err_hdmiphy:
-	put_device(&hdata->hdmiphy_port->dev);
+	if (hdata->hdmiphy_port)
+		put_device(&hdata->hdmiphy_port->dev);
 err_ddc:
 	put_device(&hdata->ddc_adpt->dev);
+
+err_del_component:
+	exynos_drm_component_del(&pdev->dev, EXYNOS_DEVICE_TYPE_CONNECTOR);
+
 	return ret;
 }
 
 static int hdmi_remove(struct platform_device *pdev)
 {
-	struct device *dev = &pdev->dev;
-	struct exynos_drm_display *display = get_hdmi_display(dev);
-	struct hdmi_context *hdata = display->ctx;
+	struct hdmi_context *hdata = hdmi_display.ctx;
+
+	cancel_delayed_work_sync(&hdata->hotplug_work);
 
 	put_device(&hdata->hdmiphy_port->dev);
 	put_device(&hdata->ddc_adpt->dev);
+
 	pm_runtime_disable(&pdev->dev);
+	component_del(&pdev->dev, &hdmi_component_ops);
 
+	exynos_drm_component_del(&pdev->dev, EXYNOS_DEVICE_TYPE_CONNECTOR);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.h b/drivers/gpu/drm/exynos/exynos_hdmi.h
deleted file mode 100644
index 0ddf3957de1..00000000000
--- a/drivers/gpu/drm/exynos/exynos_hdmi.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- * Authors:
- *	Inki Dae <inki.dae@samsung.com>
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#ifndef _EXYNOS_HDMI_H_
-#define _EXYNOS_HDMI_H_
-
-void hdmi_attach_ddc_client(struct i2c_client *ddc);
-void hdmi_attach_hdmiphy_client(struct i2c_client *hdmiphy);
-
-extern struct i2c_driver hdmiphy_driver;
-extern struct i2c_driver ddc_driver;
-
-#endif
diff --git a/drivers/gpu/drm/exynos/exynos_hdmiphy.c b/drivers/gpu/drm/exynos/exynos_hdmiphy.c
deleted file mode 100644
index 59abb1494ce..00000000000
--- a/drivers/gpu/drm/exynos/exynos_hdmiphy.c
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- * Copyright (C) 2011 Samsung Electronics Co.Ltd
- * Authors:
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *	Inki Dae <inki.dae@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- */
-
-#include <drm/drmP.h>
-
-#include <linux/kernel.h>
-#include <linux/i2c.h>
-#include <linux/of.h>
-
-#include "exynos_drm_drv.h"
-#include "exynos_hdmi.h"
-
-
-static int hdmiphy_probe(struct i2c_client *client,
-	const struct i2c_device_id *id)
-{
-	hdmi_attach_hdmiphy_client(client);
-
-	dev_info(&client->adapter->dev, "attached s5p_hdmiphy "
-		"into i2c adapter successfully\n");
-
-	return 0;
-}
-
-static int hdmiphy_remove(struct i2c_client *client)
-{
-	dev_info(&client->adapter->dev, "detached s5p_hdmiphy "
-		"from i2c adapter successfully\n");
-
-	return 0;
-}
-
-static struct of_device_id hdmiphy_match_types[] = {
-	{
-		.compatible = "samsung,exynos5-hdmiphy",
-	}, {
-		.compatible = "samsung,exynos4210-hdmiphy",
-	}, {
-		.compatible = "samsung,exynos4212-hdmiphy",
-	}, {
-		/* end node */
-	}
-};
-
-struct i2c_driver hdmiphy_driver = {
-	.driver = {
-		.name	= "exynos-hdmiphy",
-		.owner	= THIS_MODULE,
-		.of_match_table = hdmiphy_match_types,
-	},
-	.probe		= hdmiphy_probe,
-	.remove		= hdmiphy_remove,
-	.command		= NULL,
-};
-EXPORT_SYMBOL(hdmiphy_driver);
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index ce288818d2c..7529946d0a7 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -31,6 +31,7 @@
 #include <linux/clk.h>
 #include <linux/regulator/consumer.h>
 #include <linux/of.h>
+#include <linux/component.h>
 
 #include <drm/exynos_drm.h>
 
@@ -376,6 +377,20 @@ static void mixer_run(struct mixer_context *ctx)
 	mixer_regs_dump(ctx);
 }
 
+static void mixer_stop(struct mixer_context *ctx)
+{
+	struct mixer_resources *res = &ctx->mixer_res;
+	int timeout = 20;
+
+	mixer_reg_writemask(res, MXR_STATUS, 0, MXR_STATUS_REG_RUN);
+
+	while (!(mixer_reg_read(res, MXR_STATUS) & MXR_STATUS_REG_IDLE) &&
+			--timeout)
+		usleep_range(10000, 12000);
+
+	mixer_regs_dump(ctx);
+}
+
 static void vp_video_buffer(struct mixer_context *ctx, int win)
 {
 	struct mixer_resources *res = &ctx->mixer_res;
@@ -496,13 +511,8 @@ static void vp_video_buffer(struct mixer_context *ctx, int win)
 static void mixer_layer_update(struct mixer_context *ctx)
 {
 	struct mixer_resources *res = &ctx->mixer_res;
-	u32 val;
 
-	val = mixer_reg_read(res, MXR_CFG);
-
-	/* allow one update per vsync only */
-	if (!(val & MXR_CFG_LAYER_UPDATE_COUNT_MASK))
-		mixer_reg_writemask(res, MXR_CFG, ~0, MXR_CFG_LAYER_UPDATE);
+	mixer_reg_writemask(res, MXR_CFG, ~0, MXR_CFG_LAYER_UPDATE);
 }
 
 static void mixer_graph_buffer(struct mixer_context *ctx, int win)
@@ -830,13 +840,15 @@ static int vp_resources_init(struct mixer_context *mixer_ctx)
 }
 
 static int mixer_initialize(struct exynos_drm_manager *mgr,
-			struct drm_device *drm_dev, int pipe)
+			struct drm_device *drm_dev)
 {
 	int ret;
 	struct mixer_context *mixer_ctx = mgr->ctx;
+	struct exynos_drm_private *priv;
+	priv = drm_dev->dev_private;
 
-	mixer_ctx->drm_dev = drm_dev;
-	mixer_ctx->pipe = pipe;
+	mgr->drm_dev = mixer_ctx->drm_dev = drm_dev;
+	mgr->pipe = mixer_ctx->pipe = priv->pipe++;
 
 	/* acquire resources: regs, irqs, clocks */
 	ret = mixer_resources_init(mixer_ctx);
@@ -1007,6 +1019,8 @@ static void mixer_wait_for_vblank(struct exynos_drm_manager *mgr)
 	}
 	mutex_unlock(&mixer_ctx->mixer_mutex);
 
+	drm_vblank_get(mgr->crtc->dev, mixer_ctx->pipe);
+
 	atomic_set(&mixer_ctx->wait_vsync_event, 1);
 
 	/*
@@ -1017,6 +1031,8 @@ static void mixer_wait_for_vblank(struct exynos_drm_manager *mgr)
 				!atomic_read(&mixer_ctx->wait_vsync_event),
 				HZ/20))
 		DRM_DEBUG_KMS("vblank wait timed out.\n");
+
+	drm_vblank_put(mgr->crtc->dev, mixer_ctx->pipe);
 }
 
 static void mixer_window_suspend(struct exynos_drm_manager *mgr)
@@ -1058,7 +1074,7 @@ static void mixer_poweron(struct exynos_drm_manager *mgr)
 		mutex_unlock(&ctx->mixer_mutex);
 		return;
 	}
-	ctx->powered = true;
+
 	mutex_unlock(&ctx->mixer_mutex);
 
 	pm_runtime_get_sync(ctx->dev);
@@ -1069,6 +1085,12 @@ static void mixer_poweron(struct exynos_drm_manager *mgr)
 		clk_prepare_enable(res->sclk_mixer);
 	}
 
+	mutex_lock(&ctx->mixer_mutex);
+	ctx->powered = true;
+	mutex_unlock(&ctx->mixer_mutex);
+
+	mixer_reg_writemask(res, MXR_STATUS, ~0, MXR_STATUS_SOFT_RESET);
+
 	mixer_reg_write(res, MXR_INT_EN, ctx->int_en);
 	mixer_win_reset(ctx);
 
@@ -1081,14 +1103,21 @@ static void mixer_poweroff(struct exynos_drm_manager *mgr)
 	struct mixer_resources *res = &ctx->mixer_res;
 
 	mutex_lock(&ctx->mixer_mutex);
-	if (!ctx->powered)
-		goto out;
+	if (!ctx->powered) {
+		mutex_unlock(&ctx->mixer_mutex);
+		return;
+	}
 	mutex_unlock(&ctx->mixer_mutex);
 
+	mixer_stop(ctx);
 	mixer_window_suspend(mgr);
 
 	ctx->int_en = mixer_reg_read(res, MXR_INT_EN);
 
+	mutex_lock(&ctx->mixer_mutex);
+	ctx->powered = false;
+	mutex_unlock(&ctx->mixer_mutex);
+
 	clk_disable_unprepare(res->mixer);
 	if (ctx->vp_enabled) {
 		clk_disable_unprepare(res->vp);
@@ -1096,12 +1125,6 @@ static void mixer_poweroff(struct exynos_drm_manager *mgr)
 	}
 
 	pm_runtime_put_sync(ctx->dev);
-
-	mutex_lock(&ctx->mixer_mutex);
-	ctx->powered = false;
-
-out:
-	mutex_unlock(&ctx->mixer_mutex);
 }
 
 static void mixer_dpms(struct exynos_drm_manager *mgr, int mode)
@@ -1142,8 +1165,6 @@ int mixer_check_mode(struct drm_display_mode *mode)
 }
 
 static struct exynos_drm_manager_ops mixer_manager_ops = {
-	.initialize		= mixer_initialize,
-	.remove			= mixer_mgr_remove,
 	.dpms			= mixer_dpms,
 	.enable_vblank		= mixer_enable_vblank,
 	.disable_vblank		= mixer_disable_vblank,
@@ -1200,11 +1221,13 @@ static struct of_device_id mixer_match_types[] = {
 	}
 };
 
-static int mixer_probe(struct platform_device *pdev)
+static int mixer_bind(struct device *dev, struct device *manager, void *data)
 {
-	struct device *dev = &pdev->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct drm_device *drm_dev = data;
 	struct mixer_context *ctx;
 	struct mixer_drv_data *drv;
+	int ret;
 
 	dev_info(dev, "probe start\n");
 
@@ -1233,19 +1256,61 @@ static int mixer_probe(struct platform_device *pdev)
 	atomic_set(&ctx->wait_vsync_event, 0);
 
 	mixer_manager.ctx = ctx;
+	ret = mixer_initialize(&mixer_manager, drm_dev);
+	if (ret)
+		return ret;
+
 	platform_set_drvdata(pdev, &mixer_manager);
-	exynos_drm_manager_register(&mixer_manager);
+	ret = exynos_drm_crtc_create(&mixer_manager);
+	if (ret) {
+		mixer_mgr_remove(&mixer_manager);
+		return ret;
+	}
 
 	pm_runtime_enable(dev);
 
 	return 0;
 }
 
-static int mixer_remove(struct platform_device *pdev)
+static void mixer_unbind(struct device *dev, struct device *master, void *data)
 {
-	dev_info(&pdev->dev, "remove successful\n");
+	struct exynos_drm_manager *mgr = dev_get_drvdata(dev);
+	struct drm_crtc *crtc = mgr->crtc;
+
+	dev_info(dev, "remove successful\n");
 
-	pm_runtime_disable(&pdev->dev);
+	mixer_mgr_remove(mgr);
+
+	pm_runtime_disable(dev);
+
+	crtc->funcs->destroy(crtc);
+}
+
+static const struct component_ops mixer_component_ops = {
+	.bind	= mixer_bind,
+	.unbind	= mixer_unbind,
+};
+
+static int mixer_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	ret = exynos_drm_component_add(&pdev->dev, EXYNOS_DEVICE_TYPE_CRTC,
+					mixer_manager.type);
+	if (ret)
+		return ret;
+
+	ret = component_add(&pdev->dev, &mixer_component_ops);
+	if (ret)
+		exynos_drm_component_del(&pdev->dev, EXYNOS_DEVICE_TYPE_CRTC);
+
+	return ret;
+}
+
+static int mixer_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &mixer_component_ops);
+	exynos_drm_component_del(&pdev->dev, EXYNOS_DEVICE_TYPE_CRTC);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/regs-hdmi.h b/drivers/gpu/drm/exynos/regs-hdmi.h
index ef1b3eb3ba6..3f35ac6d8a4 100644
--- a/drivers/gpu/drm/exynos/regs-hdmi.h
+++ b/drivers/gpu/drm/exynos/regs-hdmi.h
@@ -578,4 +578,20 @@
 #define HDMI_TG_VACT_ST4_H		HDMI_TG_BASE(0x0074)
 #define HDMI_TG_3D			HDMI_TG_BASE(0x00F0)
 
+/* HDMI PHY Registers Offsets*/
+#define HDMIPHY_POWER		(0x74 >> 2)
+#define HDMIPHY_MODE_SET_DONE		(0x7c >> 2)
+
+/* HDMI PHY Values */
+#define HDMI_PHY_POWER_ON              0x80
+#define HDMI_PHY_POWER_OFF             0xff
+
+/* HDMI PHY Values */
+#define HDMI_PHY_DISABLE_MODE_SET	0x80
+#define HDMI_PHY_ENABLE_MODE_SET	0x00
+
+/* PMU Registers for PHY */
+#define PMU_HDMI_PHY_CONTROL		0x700
+#define PMU_HDMI_PHY_ENABLE_BIT		BIT(0)
+
 #endif /* SAMSUNG_REGS_HDMI_H */
diff --git a/drivers/gpu/drm/exynos/regs-mixer.h b/drivers/gpu/drm/exynos/regs-mixer.h
index 4537026bc38..5f32e1a2941 100644
--- a/drivers/gpu/drm/exynos/regs-mixer.h
+++ b/drivers/gpu/drm/exynos/regs-mixer.h
@@ -78,6 +78,7 @@
 #define MXR_STATUS_BIG_ENDIAN		(1 << 3)
 #define MXR_STATUS_ENDIAN_MASK		(1 << 3)
 #define MXR_STATUS_SYNC_ENABLE		(1 << 2)
+#define MXR_STATUS_REG_IDLE		(1 << 1)
 #define MXR_STATUS_REG_RUN		(1 << 0)
 
 /* bits for MXR_CFG */
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c
index 489ffd2c66e..87885d8c06e 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c
@@ -148,7 +148,7 @@ static int handle_dsi_error(struct mdfld_dsi_pkg_sender *sender, u32 mask)
 		break;
 	case BIT(14):
 		/*wait for all fifo empty*/
-		/*wait_for_all_fifos_empty(sender)*/;
+		/*wait_for_all_fifos_empty(sender)*/
 		break;
 	case BIT(15):
 		dev_dbg(sender->dev->dev, "No Action required\n");
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index b686e56646e..6e8fe9ec02b 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -112,11 +112,9 @@ static void psb_driver_lastclose(struct drm_device *dev)
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_fbdev *fbdev = dev_priv->fbdev;
 
-	drm_modeset_lock_all(dev);
-	ret = drm_fb_helper_restore_fbdev_mode(&fbdev->psb_fb_helper);
+	ret = drm_fb_helper_restore_fbdev_mode_unlocked(&fbdev->psb_fb_helper);
 	if (ret)
 		DRM_DEBUG("failed to restore crtc mode\n");
-	drm_modeset_unlock_all(dev);
 
 	return;
 }
@@ -354,7 +352,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags)
 	PSB_WVDC32(0xFFFFFFFF, PSB_INT_MASK_R);
 	spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags);
 
-	drm_irq_install(dev);
+	drm_irq_install(dev, dev->pdev->irq);
 
 	dev->vblank_disable_allowed = true;
 	dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */
@@ -479,7 +477,7 @@ static struct drm_driver driver = {
 	.lastclose = psb_driver_lastclose,
 	.preclose = psb_driver_preclose,
 
-	.num_ioctls = DRM_ARRAY_SIZE(psb_ioctls),
+	.num_ioctls = ARRAY_SIZE(psb_ioctls),
 	.device_is_agp = psb_driver_device_is_agp,
 	.irq_preinstall = psb_irq_preinstall,
 	.irq_postinstall = psb_irq_postinstall,
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 48af5cac190..ac357b02bd3 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -568,11 +568,11 @@ static irqreturn_t tda998x_irq_thread(int irq, void *data)
 
 static uint8_t tda998x_cksum(uint8_t *buf, size_t bytes)
 {
-	uint8_t sum = 0;
+	int sum = 0;
 
 	while (bytes--)
-		sum += *buf++;
-	return (255 - sum) + 1;
+		sum -= *buf++;
+	return sum;
 }
 
 #define HB(x) (x)
@@ -810,6 +810,12 @@ static int
 tda998x_encoder_mode_valid(struct drm_encoder *encoder,
 			  struct drm_display_mode *mode)
 {
+	if (mode->clock > 150000)
+		return MODE_CLOCK_HIGH;
+	if (mode->htotal >= BIT(13))
+		return MODE_BAD_HVALUE;
+	if (mode->vtotal >= BIT(11))
+		return MODE_BAD_VVALUE;
 	return MODE_OK;
 }
 
@@ -1048,8 +1054,8 @@ read_edid_block(struct drm_encoder *encoder, uint8_t *buf, int blk)
 			return i;
 		}
 	} else {
-		for (i = 10; i > 0; i--) {
-			msleep(10);
+		for (i = 100; i > 0; i--) {
+			msleep(1);
 			ret = reg_read(priv, REG_INT_FLAGS_2);
 			if (ret < 0)
 				return ret;
@@ -1183,7 +1189,6 @@ static void
 tda998x_encoder_destroy(struct drm_encoder *encoder)
 {
 	struct tda998x_priv *priv = to_tda998x_priv(encoder);
-	drm_i2c_encoder_destroy(encoder);
 
 	/* disable all IRQs and free the IRQ handler */
 	cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
@@ -1193,6 +1198,7 @@ tda998x_encoder_destroy(struct drm_encoder *encoder)
 
 	if (priv->cec)
 		i2c_unregister_device(priv->cec);
+	drm_i2c_encoder_destroy(encoder);
 	kfree(priv);
 }
 
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index aeace37415a..e88bac1d781 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -1251,7 +1251,7 @@ const struct drm_ioctl_desc i810_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I810_FLIP, i810_flip_bufs, DRM_AUTH|DRM_UNLOCKED),
 };
 
-int i810_max_ioctl = DRM_ARRAY_SIZE(i810_ioctls);
+int i810_max_ioctl = ARRAY_SIZE(i810_ioctls);
 
 /**
  * Determine if the device really is AGP or not.
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index bea2d67196f..437e1824d0b 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -5,6 +5,7 @@ config DRM_I915
 	depends on (AGP || AGP=n)
 	select INTEL_GTT
 	select AGP_INTEL if AGP
+	select INTERVAL_TREE
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs
 	select SHMEM
@@ -71,7 +72,7 @@ config DRM_I915_PRELIMINARY_HW_SUPPORT
 
 config DRM_I915_UMS
 	bool "Enable userspace modesetting on Intel hardware (DEPRECATED)"
-	depends on DRM_I915
+	depends on DRM_I915 && BROKEN
 	default n
 	help
 	  Choose this option if you still need userspace modesetting.
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index b1445b73465..cad1683d8bb 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -18,6 +18,7 @@ i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o
 # GEM code
 i915-y += i915_cmd_parser.o \
 	  i915_gem_context.o \
+	  i915_gem_render_state.o \
 	  i915_gem_debug.o \
 	  i915_gem_dmabuf.o \
 	  i915_gem_evict.o \
@@ -26,12 +27,18 @@ i915-y += i915_cmd_parser.o \
 	  i915_gem.o \
 	  i915_gem_stolen.o \
 	  i915_gem_tiling.o \
+	  i915_gem_userptr.o \
 	  i915_gpu_error.o \
 	  i915_irq.o \
 	  i915_trace_points.o \
 	  intel_ringbuffer.o \
 	  intel_uncore.o
 
+# autogenerated null render state
+i915-y += intel_renderstate_gen6.o \
+	  intel_renderstate_gen7.o \
+	  intel_renderstate_gen8.o
+
 # modesetting core code
 i915-y += intel_bios.o \
 	  intel_display.o \
@@ -55,6 +62,7 @@ i915-y += dvo_ch7017.o \
 	  intel_dsi_cmd.o \
 	  intel_dsi.o \
 	  intel_dsi_pll.o \
+	  intel_dsi_panel_vbt.o \
 	  intel_dvo.o \
 	  intel_hdmi.o \
 	  intel_i2c.o \
diff --git a/drivers/gpu/drm/i915/dvo_ch7xxx.c b/drivers/gpu/drm/i915/dvo_ch7xxx.c
index a0f5bdd6949..80449f47596 100644
--- a/drivers/gpu/drm/i915/dvo_ch7xxx.c
+++ b/drivers/gpu/drm/i915/dvo_ch7xxx.c
@@ -160,7 +160,7 @@ static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
 	if (i2c_transfer(adapter, msgs, 2) == 2) {
 		*ch = in_buf[0];
 		return true;
-	};
+	}
 
 	if (!ch7xxx->quiet) {
 		DRM_DEBUG_KMS("Unable to read register 0x%02x from %s:%02x.\n",
diff --git a/drivers/gpu/drm/i915/dvo_ivch.c b/drivers/gpu/drm/i915/dvo_ivch.c
index 0f1865d7d4d..0f2587ff347 100644
--- a/drivers/gpu/drm/i915/dvo_ivch.c
+++ b/drivers/gpu/drm/i915/dvo_ivch.c
@@ -195,7 +195,7 @@ static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data)
 	if (i2c_transfer(adapter, msgs, 3) == 3) {
 		*data = (in_buf[1] << 8) | in_buf[0];
 		return true;
-	};
+	}
 
 	if (!priv->quiet) {
 		DRM_DEBUG_KMS("Unable to read register 0x%02x from "
diff --git a/drivers/gpu/drm/i915/dvo_ns2501.c b/drivers/gpu/drm/i915/dvo_ns2501.c
index 8155ded7907..74f2af7c2d3 100644
--- a/drivers/gpu/drm/i915/dvo_ns2501.c
+++ b/drivers/gpu/drm/i915/dvo_ns2501.c
@@ -121,7 +121,7 @@ static bool ns2501_readb(struct intel_dvo_device *dvo, int addr, uint8_t * ch)
 	if (i2c_transfer(adapter, msgs, 2) == 2) {
 		*ch = in_buf[0];
 		return true;
-	};
+	}
 
 	if (!ns->quiet) {
 		DRM_DEBUG_KMS
@@ -233,9 +233,8 @@ static enum drm_mode_status ns2501_mode_valid(struct intel_dvo_device *dvo,
 					      struct drm_display_mode *mode)
 {
 	DRM_DEBUG_KMS
-	    ("%s: is mode valid (hdisplay=%d,htotal=%d,vdisplay=%d,vtotal=%d)\n",
-	     __FUNCTION__, mode->hdisplay, mode->htotal, mode->vdisplay,
-	     mode->vtotal);
+	    ("is mode valid (hdisplay=%d,htotal=%d,vdisplay=%d,vtotal=%d)\n",
+	     mode->hdisplay, mode->htotal, mode->vdisplay, mode->vtotal);
 
 	/*
 	 * Currently, these are all the modes I have data from.
@@ -261,9 +260,8 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo,
 	struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv);
 
 	DRM_DEBUG_KMS
-	    ("%s: set mode (hdisplay=%d,htotal=%d,vdisplay=%d,vtotal=%d).\n",
-	     __FUNCTION__, mode->hdisplay, mode->htotal, mode->vdisplay,
-	     mode->vtotal);
+	    ("set mode (hdisplay=%d,htotal=%d,vdisplay=%d,vtotal=%d).\n",
+	     mode->hdisplay, mode->htotal, mode->vdisplay, mode->vtotal);
 
 	/*
 	 * Where do I find the native resolution for which scaling is not required???
@@ -277,8 +275,7 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo,
 		if (mode->hdisplay == 800 && mode->vdisplay == 600) {
 			/* mode 277 */
 			ns->reg_8_shadow &= ~NS2501_8_BPAS;
-			DRM_DEBUG_KMS("%s: switching to 800x600\n",
-				      __FUNCTION__);
+			DRM_DEBUG_KMS("switching to 800x600\n");
 
 			/*
 			 * No, I do not know where this data comes from.
@@ -341,8 +338,7 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo,
 
 		} else if (mode->hdisplay == 640 && mode->vdisplay == 480) {
 			/* mode 274 */
-			DRM_DEBUG_KMS("%s: switching to 640x480\n",
-				      __FUNCTION__);
+			DRM_DEBUG_KMS("switching to 640x480\n");
 			/*
 			 * No, I do not know where this data comes from.
 			 * It is just what the video bios left in the DVO, so
@@ -406,8 +402,7 @@ static void ns2501_mode_set(struct intel_dvo_device *dvo,
 
 		} else if (mode->hdisplay == 1024 && mode->vdisplay == 768) {
 			/* mode 280 */
-			DRM_DEBUG_KMS("%s: switching to 1024x768\n",
-				      __FUNCTION__);
+			DRM_DEBUG_KMS("switching to 1024x768\n");
 			/*
 			 * This might or might not work, actually. I'm silently
 			 * assuming here that the native panel resolution is
@@ -458,8 +453,7 @@ static void ns2501_dpms(struct intel_dvo_device *dvo, bool enable)
 	struct ns2501_priv *ns = (struct ns2501_priv *)(dvo->dev_priv);
 	unsigned char ch;
 
-	DRM_DEBUG_KMS("%s: Trying set the dpms of the DVO to %i\n",
-		      __FUNCTION__, enable);
+	DRM_DEBUG_KMS("Trying set the dpms of the DVO to %i\n", enable);
 
 	ch = ns->reg_8_shadow;
 
diff --git a/drivers/gpu/drm/i915/dvo_sil164.c b/drivers/gpu/drm/i915/dvo_sil164.c
index 7b3e9e93620..fa011496707 100644
--- a/drivers/gpu/drm/i915/dvo_sil164.c
+++ b/drivers/gpu/drm/i915/dvo_sil164.c
@@ -93,7 +93,7 @@ static bool sil164_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
 	if (i2c_transfer(adapter, msgs, 2) == 2) {
 		*ch = in_buf[0];
 		return true;
-	};
+	}
 
 	if (!sil->quiet) {
 		DRM_DEBUG_KMS("Unable to read register 0x%02x from %s:%02x.\n",
diff --git a/drivers/gpu/drm/i915/dvo_tfp410.c b/drivers/gpu/drm/i915/dvo_tfp410.c
index 12ea4b16469..7853719a0e8 100644
--- a/drivers/gpu/drm/i915/dvo_tfp410.c
+++ b/drivers/gpu/drm/i915/dvo_tfp410.c
@@ -118,7 +118,7 @@ static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
 	if (i2c_transfer(adapter, msgs, 2) == 2) {
 		*ch = in_buf[0];
 		return true;
-	};
+	}
 
 	if (!tfp->quiet) {
 		DRM_DEBUG_KMS("Unable to read register 0x%02x from %s:%02x.\n",
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 4cf6d020d51..9d7954366bd 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -28,7 +28,7 @@
 #include "i915_drv.h"
 
 /**
- * DOC: i915 batch buffer command parser
+ * DOC: batch buffer command parser
  *
  * Motivation:
  * Certain OpenGL features (e.g. transform feedback, performance monitoring)
@@ -86,6 +86,367 @@
  * general bitmasking mechanism.
  */
 
+#define STD_MI_OPCODE_MASK  0xFF800000
+#define STD_3D_OPCODE_MASK  0xFFFF0000
+#define STD_2D_OPCODE_MASK  0xFFC00000
+#define STD_MFX_OPCODE_MASK 0xFFFF0000
+
+#define CMD(op, opm, f, lm, fl, ...)				\
+	{							\
+		.flags = (fl) | ((f) ? CMD_DESC_FIXED : 0),	\
+		.cmd = { (op), (opm) }, 			\
+		.length = { (lm) },				\
+		__VA_ARGS__					\
+	}
+
+/* Convenience macros to compress the tables */
+#define SMI STD_MI_OPCODE_MASK
+#define S3D STD_3D_OPCODE_MASK
+#define S2D STD_2D_OPCODE_MASK
+#define SMFX STD_MFX_OPCODE_MASK
+#define F true
+#define S CMD_DESC_SKIP
+#define R CMD_DESC_REJECT
+#define W CMD_DESC_REGISTER
+#define B CMD_DESC_BITMASK
+#define M CMD_DESC_MASTER
+
+/*            Command                          Mask   Fixed Len   Action
+	      ---------------------------------------------------------- */
+static const struct drm_i915_cmd_descriptor common_cmds[] = {
+	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
+	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      R  ),
+	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      M  ),
+	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
+	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
+	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
+	CMD(  MI_SEMAPHORE_MBOX,                SMI,   !F,  0xFF,   R  ),
+	CMD(  MI_STORE_DWORD_INDEX,             SMI,   !F,  0xFF,   R  ),
+	CMD(  MI_LOAD_REGISTER_IMM(1),          SMI,   !F,  0xFF,   W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
+	CMD(  MI_STORE_REGISTER_MEM(1),         SMI,   !F,  0xFF,   W | B,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC },
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+	CMD(  MI_LOAD_REGISTER_MEM,             SMI,   !F,  0xFF,   W | B,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC },
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+	CMD(  MI_BATCH_BUFFER_START,            SMI,   !F,  0xFF,   S  ),
+};
+
+static const struct drm_i915_cmd_descriptor render_cmds[] = {
+	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
+	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
+	CMD(  MI_PREDICATE,                     SMI,    F,  1,      S  ),
+	CMD(  MI_TOPOLOGY_FILTER,               SMI,    F,  1,      S  ),
+	CMD(  MI_DISPLAY_FLIP,                  SMI,   !F,  0xFF,   R  ),
+	CMD(  MI_SET_CONTEXT,                   SMI,   !F,  0xFF,   R  ),
+	CMD(  MI_URB_CLEAR,                     SMI,   !F,  0xFF,   S  ),
+	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3F,   B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0xFF,   R  ),
+	CMD(  MI_CLFLUSH,                       SMI,   !F,  0x3FF,  B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+	CMD(  MI_REPORT_PERF_COUNT,             SMI,   !F,  0x3F,   B,
+	      .bits = {{
+			.offset = 1,
+			.mask = MI_REPORT_PERF_COUNT_GGTT,
+			.expected = 0,
+	      }},						       ),
+	CMD(  MI_CONDITIONAL_BATCH_BUFFER_END,  SMI,   !F,  0xFF,   B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+	CMD(  GFX_OP_3DSTATE_VF_STATISTICS,     S3D,    F,  1,      S  ),
+	CMD(  PIPELINE_SELECT,                  S3D,    F,  1,      S  ),
+	CMD(  MEDIA_VFE_STATE,			S3D,   !F,  0xFFFF, B,
+	      .bits = {{
+			.offset = 2,
+			.mask = MEDIA_VFE_STATE_MMIO_ACCESS_MASK,
+			.expected = 0,
+	      }},						       ),
+	CMD(  GPGPU_OBJECT,                     S3D,   !F,  0xFF,   S  ),
+	CMD(  GPGPU_WALKER,                     S3D,   !F,  0xFF,   S  ),
+	CMD(  GFX_OP_3DSTATE_SO_DECL_LIST,      S3D,   !F,  0x1FF,  S  ),
+	CMD(  GFX_OP_PIPE_CONTROL(5),           S3D,   !F,  0xFF,   B,
+	      .bits = {{
+			.offset = 1,
+			.mask = (PIPE_CONTROL_MMIO_WRITE | PIPE_CONTROL_NOTIFY),
+			.expected = 0,
+	      },
+	      {
+			.offset = 1,
+		        .mask = (PIPE_CONTROL_GLOBAL_GTT_IVB |
+				 PIPE_CONTROL_STORE_DATA_INDEX),
+			.expected = 0,
+			.condition_offset = 1,
+			.condition_mask = PIPE_CONTROL_POST_SYNC_OP_MASK,
+	      }},						       ),
+};
+
+static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
+	CMD(  MI_SET_PREDICATE,                 SMI,    F,  1,      S  ),
+	CMD(  MI_RS_CONTROL,                    SMI,    F,  1,      S  ),
+	CMD(  MI_URB_ATOMIC_ALLOC,              SMI,    F,  1,      S  ),
+	CMD(  MI_RS_CONTEXT,                    SMI,    F,  1,      S  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
+	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
+	CMD(  MI_LOAD_REGISTER_REG,             SMI,   !F,  0xFF,   R  ),
+	CMD(  MI_RS_STORE_DATA_IMM,             SMI,   !F,  0xFF,   S  ),
+	CMD(  MI_LOAD_URB_MEM,                  SMI,   !F,  0xFF,   S  ),
+	CMD(  MI_STORE_URB_MEM,                 SMI,   !F,  0xFF,   S  ),
+	CMD(  GFX_OP_3DSTATE_DX9_CONSTANTF_VS,  S3D,   !F,  0x7FF,  S  ),
+	CMD(  GFX_OP_3DSTATE_DX9_CONSTANTF_PS,  S3D,   !F,  0x7FF,  S  ),
+
+	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_VS,  S3D,   !F,  0x1FF,  S  ),
+	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_GS,  S3D,   !F,  0x1FF,  S  ),
+	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_HS,  S3D,   !F,  0x1FF,  S  ),
+	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_DS,  S3D,   !F,  0x1FF,  S  ),
+	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS,  S3D,   !F,  0x1FF,  S  ),
+};
+
+static const struct drm_i915_cmd_descriptor video_cmds[] = {
+	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
+	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3F,   R  ),
+	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_FLUSH_DW_NOTIFY,
+			.expected = 0,
+	      },
+	      {
+			.offset = 1,
+			.mask = MI_FLUSH_DW_USE_GTT,
+			.expected = 0,
+			.condition_offset = 0,
+			.condition_mask = MI_FLUSH_DW_OP_MASK,
+	      },
+	      {
+			.offset = 0,
+			.mask = MI_FLUSH_DW_STORE_INDEX,
+			.expected = 0,
+			.condition_offset = 0,
+			.condition_mask = MI_FLUSH_DW_OP_MASK,
+	      }},						       ),
+	CMD(  MI_CONDITIONAL_BATCH_BUFFER_END,  SMI,   !F,  0xFF,   B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+	/*
+	 * MFX_WAIT doesn't fit the way we handle length for most commands.
+	 * It has a length field but it uses a non-standard length bias.
+	 * It is always 1 dword though, so just treat it as fixed length.
+	 */
+	CMD(  MFX_WAIT,                         SMFX,   F,  1,      S  ),
+};
+
+static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
+	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
+	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3F,   R  ),
+	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_FLUSH_DW_NOTIFY,
+			.expected = 0,
+	      },
+	      {
+			.offset = 1,
+			.mask = MI_FLUSH_DW_USE_GTT,
+			.expected = 0,
+			.condition_offset = 0,
+			.condition_mask = MI_FLUSH_DW_OP_MASK,
+	      },
+	      {
+			.offset = 0,
+			.mask = MI_FLUSH_DW_STORE_INDEX,
+			.expected = 0,
+			.condition_offset = 0,
+			.condition_mask = MI_FLUSH_DW_OP_MASK,
+	      }},						       ),
+	CMD(  MI_CONDITIONAL_BATCH_BUFFER_END,  SMI,   !F,  0xFF,   B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+};
+
+static const struct drm_i915_cmd_descriptor blt_cmds[] = {
+	CMD(  MI_DISPLAY_FLIP,                  SMI,   !F,  0xFF,   R  ),
+	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_GLOBAL_GTT,
+			.expected = 0,
+	      }},						       ),
+	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3F,   R  ),
+	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_FLUSH_DW_NOTIFY,
+			.expected = 0,
+	      },
+	      {
+			.offset = 1,
+			.mask = MI_FLUSH_DW_USE_GTT,
+			.expected = 0,
+			.condition_offset = 0,
+			.condition_mask = MI_FLUSH_DW_OP_MASK,
+	      },
+	      {
+			.offset = 0,
+			.mask = MI_FLUSH_DW_STORE_INDEX,
+			.expected = 0,
+			.condition_offset = 0,
+			.condition_mask = MI_FLUSH_DW_OP_MASK,
+	      }},						       ),
+	CMD(  COLOR_BLT,                        S2D,   !F,  0x3F,   S  ),
+	CMD(  SRC_COPY_BLT,                     S2D,   !F,  0x3F,   S  ),
+};
+
+static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = {
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
+	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
+};
+
+#undef CMD
+#undef SMI
+#undef S3D
+#undef S2D
+#undef SMFX
+#undef F
+#undef S
+#undef R
+#undef W
+#undef B
+#undef M
+
+static const struct drm_i915_cmd_table gen7_render_cmds[] = {
+	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ render_cmds, ARRAY_SIZE(render_cmds) },
+};
+
+static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = {
+	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ render_cmds, ARRAY_SIZE(render_cmds) },
+	{ hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) },
+};
+
+static const struct drm_i915_cmd_table gen7_video_cmds[] = {
+	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ video_cmds, ARRAY_SIZE(video_cmds) },
+};
+
+static const struct drm_i915_cmd_table hsw_vebox_cmds[] = {
+	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ vecs_cmds, ARRAY_SIZE(vecs_cmds) },
+};
+
+static const struct drm_i915_cmd_table gen7_blt_cmds[] = {
+	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ blt_cmds, ARRAY_SIZE(blt_cmds) },
+};
+
+static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = {
+	{ common_cmds, ARRAY_SIZE(common_cmds) },
+	{ blt_cmds, ARRAY_SIZE(blt_cmds) },
+	{ hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) },
+};
+
+/*
+ * Register whitelists, sorted by increasing register offset.
+ *
+ * Some registers that userspace accesses are 64 bits. The register
+ * access commands only allow 32-bit accesses. Hence, we have to include
+ * entries for both halves of the 64-bit registers.
+ */
+
+/* Convenience macro for adding 64-bit registers */
+#define REG64(addr) (addr), (addr + sizeof(u32))
+
+static const u32 gen7_render_regs[] = {
+	REG64(HS_INVOCATION_COUNT),
+	REG64(DS_INVOCATION_COUNT),
+	REG64(IA_VERTICES_COUNT),
+	REG64(IA_PRIMITIVES_COUNT),
+	REG64(VS_INVOCATION_COUNT),
+	REG64(GS_INVOCATION_COUNT),
+	REG64(GS_PRIMITIVES_COUNT),
+	REG64(CL_INVOCATION_COUNT),
+	REG64(CL_PRIMITIVES_COUNT),
+	REG64(PS_INVOCATION_COUNT),
+	REG64(PS_DEPTH_COUNT),
+	OACONTROL, /* Only allowed for LRI and SRM. See below. */
+	GEN7_3DPRIM_END_OFFSET,
+	GEN7_3DPRIM_START_VERTEX,
+	GEN7_3DPRIM_VERTEX_COUNT,
+	GEN7_3DPRIM_INSTANCE_COUNT,
+	GEN7_3DPRIM_START_INSTANCE,
+	GEN7_3DPRIM_BASE_VERTEX,
+	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(0)),
+	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(1)),
+	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(2)),
+	REG64(GEN7_SO_NUM_PRIMS_WRITTEN(3)),
+	REG64(GEN7_SO_PRIM_STORAGE_NEEDED(0)),
+	REG64(GEN7_SO_PRIM_STORAGE_NEEDED(1)),
+	REG64(GEN7_SO_PRIM_STORAGE_NEEDED(2)),
+	REG64(GEN7_SO_PRIM_STORAGE_NEEDED(3)),
+	GEN7_SO_WRITE_OFFSET(0),
+	GEN7_SO_WRITE_OFFSET(1),
+	GEN7_SO_WRITE_OFFSET(2),
+	GEN7_SO_WRITE_OFFSET(3),
+};
+
+static const u32 gen7_blt_regs[] = {
+	BCS_SWCTRL,
+};
+
+static const u32 ivb_master_regs[] = {
+	FORCEWAKE_MT,
+	DERRMR,
+	GEN7_PIPE_DE_LOAD_SL(PIPE_A),
+	GEN7_PIPE_DE_LOAD_SL(PIPE_B),
+	GEN7_PIPE_DE_LOAD_SL(PIPE_C),
+};
+
+static const u32 hsw_master_regs[] = {
+	FORCEWAKE_MT,
+	DERRMR,
+};
+
+#undef REG64
+
 static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
 {
 	u32 client = (cmd_header & INSTR_CLIENT_MASK) >> INSTR_CLIENT_SHIFT;
@@ -137,15 +498,18 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
 	return 0;
 }
 
-static void validate_cmds_sorted(struct intel_ring_buffer *ring)
+static bool validate_cmds_sorted(struct intel_engine_cs *ring,
+				 const struct drm_i915_cmd_table *cmd_tables,
+				 int cmd_table_count)
 {
 	int i;
+	bool ret = true;
 
-	if (!ring->cmd_tables || ring->cmd_table_count == 0)
-		return;
+	if (!cmd_tables || cmd_table_count == 0)
+		return true;
 
-	for (i = 0; i < ring->cmd_table_count; i++) {
-		const struct drm_i915_cmd_table *table = &ring->cmd_tables[i];
+	for (i = 0; i < cmd_table_count; i++) {
+		const struct drm_i915_cmd_table *table = &cmd_tables[i];
 		u32 previous = 0;
 		int j;
 
@@ -154,35 +518,107 @@ static void validate_cmds_sorted(struct intel_ring_buffer *ring)
 				&table->table[i];
 			u32 curr = desc->cmd.value & desc->cmd.mask;
 
-			if (curr < previous)
+			if (curr < previous) {
 				DRM_ERROR("CMD: table not sorted ring=%d table=%d entry=%d cmd=0x%08X prev=0x%08X\n",
 					  ring->id, i, j, curr, previous);
+				ret = false;
+			}
 
 			previous = curr;
 		}
 	}
+
+	return ret;
 }
 
-static void check_sorted(int ring_id, const u32 *reg_table, int reg_count)
+static bool check_sorted(int ring_id, const u32 *reg_table, int reg_count)
 {
 	int i;
 	u32 previous = 0;
+	bool ret = true;
 
 	for (i = 0; i < reg_count; i++) {
 		u32 curr = reg_table[i];
 
-		if (curr < previous)
+		if (curr < previous) {
 			DRM_ERROR("CMD: table not sorted ring=%d entry=%d reg=0x%08X prev=0x%08X\n",
 				  ring_id, i, curr, previous);
+			ret = false;
+		}
 
 		previous = curr;
 	}
+
+	return ret;
+}
+
+static bool validate_regs_sorted(struct intel_engine_cs *ring)
+{
+	return check_sorted(ring->id, ring->reg_table, ring->reg_count) &&
+		check_sorted(ring->id, ring->master_reg_table,
+			     ring->master_reg_count);
+}
+
+struct cmd_node {
+	const struct drm_i915_cmd_descriptor *desc;
+	struct hlist_node node;
+};
+
+/*
+ * Different command ranges have different numbers of bits for the opcode. For
+ * example, MI commands use bits 31:23 while 3D commands use bits 31:16. The
+ * problem is that, for example, MI commands use bits 22:16 for other fields
+ * such as GGTT vs PPGTT bits. If we include those bits in the mask then when
+ * we mask a command from a batch it could hash to the wrong bucket due to
+ * non-opcode bits being set. But if we don't include those bits, some 3D
+ * commands may hash to the same bucket due to not including opcode bits that
+ * make the command unique. For now, we will risk hashing to the same bucket.
+ *
+ * If we attempt to generate a perfect hash, we should be able to look at bits
+ * 31:29 of a command from a batch buffer and use the full mask for that
+ * client. The existing INSTR_CLIENT_MASK/SHIFT defines can be used for this.
+ */
+#define CMD_HASH_MASK STD_MI_OPCODE_MASK
+
+static int init_hash_table(struct intel_engine_cs *ring,
+			   const struct drm_i915_cmd_table *cmd_tables,
+			   int cmd_table_count)
+{
+	int i, j;
+
+	hash_init(ring->cmd_hash);
+
+	for (i = 0; i < cmd_table_count; i++) {
+		const struct drm_i915_cmd_table *table = &cmd_tables[i];
+
+		for (j = 0; j < table->count; j++) {
+			const struct drm_i915_cmd_descriptor *desc =
+				&table->table[j];
+			struct cmd_node *desc_node =
+				kmalloc(sizeof(*desc_node), GFP_KERNEL);
+
+			if (!desc_node)
+				return -ENOMEM;
+
+			desc_node->desc = desc;
+			hash_add(ring->cmd_hash, &desc_node->node,
+				 desc->cmd.value & CMD_HASH_MASK);
+		}
+	}
+
+	return 0;
 }
 
-static void validate_regs_sorted(struct intel_ring_buffer *ring)
+static void fini_hash_table(struct intel_engine_cs *ring)
 {
-	check_sorted(ring->id, ring->reg_table, ring->reg_count);
-	check_sorted(ring->id, ring->master_reg_table, ring->master_reg_count);
+	struct hlist_node *tmp;
+	struct cmd_node *desc_node;
+	int i;
+
+	hash_for_each_safe(ring->cmd_hash, i, tmp, desc_node, node) {
+		hash_del(&desc_node->node);
+		kfree(desc_node);
+	}
 }
 
 /**
@@ -190,25 +626,74 @@ static void validate_regs_sorted(struct intel_ring_buffer *ring)
  * @ring: the ringbuffer to initialize
  *
  * Optionally initializes fields related to batch buffer command parsing in the
- * struct intel_ring_buffer based on whether the platform requires software
+ * struct intel_engine_cs based on whether the platform requires software
  * command parsing.
+ *
+ * Return: non-zero if initialization fails
  */
-void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring)
+int i915_cmd_parser_init_ring(struct intel_engine_cs *ring)
 {
+	const struct drm_i915_cmd_table *cmd_tables;
+	int cmd_table_count;
+	int ret;
+
 	if (!IS_GEN7(ring->dev))
-		return;
+		return 0;
 
 	switch (ring->id) {
 	case RCS:
+		if (IS_HASWELL(ring->dev)) {
+			cmd_tables = hsw_render_ring_cmds;
+			cmd_table_count =
+				ARRAY_SIZE(hsw_render_ring_cmds);
+		} else {
+			cmd_tables = gen7_render_cmds;
+			cmd_table_count = ARRAY_SIZE(gen7_render_cmds);
+		}
+
+		ring->reg_table = gen7_render_regs;
+		ring->reg_count = ARRAY_SIZE(gen7_render_regs);
+
+		if (IS_HASWELL(ring->dev)) {
+			ring->master_reg_table = hsw_master_regs;
+			ring->master_reg_count = ARRAY_SIZE(hsw_master_regs);
+		} else {
+			ring->master_reg_table = ivb_master_regs;
+			ring->master_reg_count = ARRAY_SIZE(ivb_master_regs);
+		}
+
 		ring->get_cmd_length_mask = gen7_render_get_cmd_length_mask;
 		break;
 	case VCS:
+		cmd_tables = gen7_video_cmds;
+		cmd_table_count = ARRAY_SIZE(gen7_video_cmds);
 		ring->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
 	case BCS:
+		if (IS_HASWELL(ring->dev)) {
+			cmd_tables = hsw_blt_ring_cmds;
+			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds);
+		} else {
+			cmd_tables = gen7_blt_cmds;
+			cmd_table_count = ARRAY_SIZE(gen7_blt_cmds);
+		}
+
+		ring->reg_table = gen7_blt_regs;
+		ring->reg_count = ARRAY_SIZE(gen7_blt_regs);
+
+		if (IS_HASWELL(ring->dev)) {
+			ring->master_reg_table = hsw_master_regs;
+			ring->master_reg_count = ARRAY_SIZE(hsw_master_regs);
+		} else {
+			ring->master_reg_table = ivb_master_regs;
+			ring->master_reg_count = ARRAY_SIZE(ivb_master_regs);
+		}
+
 		ring->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
 		break;
 	case VECS:
+		cmd_tables = hsw_vebox_cmds;
+		cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds);
 		/* VECS can use the same length_mask function as VCS */
 		ring->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
@@ -218,18 +703,45 @@ void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring)
 		BUG();
 	}
 
-	validate_cmds_sorted(ring);
-	validate_regs_sorted(ring);
+	BUG_ON(!validate_cmds_sorted(ring, cmd_tables, cmd_table_count));
+	BUG_ON(!validate_regs_sorted(ring));
+
+	ret = init_hash_table(ring, cmd_tables, cmd_table_count);
+	if (ret) {
+		DRM_ERROR("CMD: cmd_parser_init failed!\n");
+		fini_hash_table(ring);
+		return ret;
+	}
+
+	ring->needs_cmd_parser = true;
+
+	return 0;
+}
+
+/**
+ * i915_cmd_parser_fini_ring() - clean up cmd parser related fields
+ * @ring: the ringbuffer to clean up
+ *
+ * Releases any resources related to command parsing that may have been
+ * initialized for the specified ring.
+ */
+void i915_cmd_parser_fini_ring(struct intel_engine_cs *ring)
+{
+	if (!ring->needs_cmd_parser)
+		return;
+
+	fini_hash_table(ring);
 }
 
 static const struct drm_i915_cmd_descriptor*
-find_cmd_in_table(const struct drm_i915_cmd_table *table,
+find_cmd_in_table(struct intel_engine_cs *ring,
 		  u32 cmd_header)
 {
-	int i;
+	struct cmd_node *desc_node;
 
-	for (i = 0; i < table->count; i++) {
-		const struct drm_i915_cmd_descriptor *desc = &table->table[i];
+	hash_for_each_possible(ring->cmd_hash, desc_node, node,
+			       cmd_header & CMD_HASH_MASK) {
+		const struct drm_i915_cmd_descriptor *desc = desc_node->desc;
 		u32 masked_cmd = desc->cmd.mask & cmd_header;
 		u32 masked_value = desc->cmd.value & desc->cmd.mask;
 
@@ -249,20 +761,16 @@ find_cmd_in_table(const struct drm_i915_cmd_table *table,
  * ring's default length encoding and returns default_desc.
  */
 static const struct drm_i915_cmd_descriptor*
-find_cmd(struct intel_ring_buffer *ring,
+find_cmd(struct intel_engine_cs *ring,
 	 u32 cmd_header,
 	 struct drm_i915_cmd_descriptor *default_desc)
 {
+	const struct drm_i915_cmd_descriptor *desc;
 	u32 mask;
-	int i;
 
-	for (i = 0; i < ring->cmd_table_count; i++) {
-		const struct drm_i915_cmd_descriptor *desc;
-
-		desc = find_cmd_in_table(&ring->cmd_tables[i], cmd_header);
-		if (desc)
-			return desc;
-	}
+	desc = find_cmd_in_table(ring, cmd_header);
+	if (desc)
+		return desc;
 
 	mask = ring->get_cmd_length_mask(cmd_header);
 	if (!mask)
@@ -329,15 +837,112 @@ finish:
  *
  * Return: true if the ring requires software command parsing
  */
-bool i915_needs_cmd_parser(struct intel_ring_buffer *ring)
+bool i915_needs_cmd_parser(struct intel_engine_cs *ring)
 {
-	/* No command tables indicates a platform without parsing */
-	if (!ring->cmd_tables)
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+
+	if (!ring->needs_cmd_parser)
+		return false;
+
+	/*
+	 * XXX: VLV is Gen7 and therefore has cmd_tables, but has PPGTT
+	 * disabled. That will cause all of the parser's PPGTT checks to
+	 * fail. For now, disable parsing when PPGTT is off.
+	 */
+	if (!dev_priv->mm.aliasing_ppgtt)
 		return false;
 
 	return (i915.enable_cmd_parser == 1);
 }
 
+static bool check_cmd(const struct intel_engine_cs *ring,
+		      const struct drm_i915_cmd_descriptor *desc,
+		      const u32 *cmd,
+		      const bool is_master,
+		      bool *oacontrol_set)
+{
+	if (desc->flags & CMD_DESC_REJECT) {
+		DRM_DEBUG_DRIVER("CMD: Rejected command: 0x%08X\n", *cmd);
+		return false;
+	}
+
+	if ((desc->flags & CMD_DESC_MASTER) && !is_master) {
+		DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n",
+				 *cmd);
+		return false;
+	}
+
+	if (desc->flags & CMD_DESC_REGISTER) {
+		u32 reg_addr = cmd[desc->reg.offset] & desc->reg.mask;
+
+		/*
+		 * OACONTROL requires some special handling for writes. We
+		 * want to make sure that any batch which enables OA also
+		 * disables it before the end of the batch. The goal is to
+		 * prevent one process from snooping on the perf data from
+		 * another process. To do that, we need to check the value
+		 * that will be written to the register. Hence, limit
+		 * OACONTROL writes to only MI_LOAD_REGISTER_IMM commands.
+		 */
+		if (reg_addr == OACONTROL) {
+			if (desc->cmd.value == MI_LOAD_REGISTER_MEM)
+				return false;
+
+			if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1))
+				*oacontrol_set = (cmd[2] != 0);
+		}
+
+		if (!valid_reg(ring->reg_table,
+			       ring->reg_count, reg_addr)) {
+			if (!is_master ||
+			    !valid_reg(ring->master_reg_table,
+				       ring->master_reg_count,
+				       reg_addr)) {
+				DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (ring=%d)\n",
+						 reg_addr,
+						 *cmd,
+						 ring->id);
+				return false;
+			}
+		}
+	}
+
+	if (desc->flags & CMD_DESC_BITMASK) {
+		int i;
+
+		for (i = 0; i < MAX_CMD_DESC_BITMASKS; i++) {
+			u32 dword;
+
+			if (desc->bits[i].mask == 0)
+				break;
+
+			if (desc->bits[i].condition_mask != 0) {
+				u32 offset =
+					desc->bits[i].condition_offset;
+				u32 condition = cmd[offset] &
+					desc->bits[i].condition_mask;
+
+				if (condition == 0)
+					continue;
+			}
+
+			dword = cmd[desc->bits[i].offset] &
+				desc->bits[i].mask;
+
+			if (dword != desc->bits[i].expected) {
+				DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (ring=%d)\n",
+						 *cmd,
+						 desc->bits[i].mask,
+						 desc->bits[i].expected,
+						 dword, ring->id);
+				return false;
+			}
+		}
+	}
+
+	return true;
+}
+
 #define LENGTH_BIAS 2
 
 /**
@@ -352,7 +957,7 @@ bool i915_needs_cmd_parser(struct intel_ring_buffer *ring)
  *
  * Return: non-zero if the parser finds violations or otherwise fails
  */
-int i915_parse_cmds(struct intel_ring_buffer *ring,
+int i915_parse_cmds(struct intel_engine_cs *ring,
 		    struct drm_i915_gem_object *batch_obj,
 		    u32 batch_start_offset,
 		    bool is_master)
@@ -361,6 +966,7 @@ int i915_parse_cmds(struct intel_ring_buffer *ring,
 	u32 *cmd, *batch_base, *batch_end;
 	struct drm_i915_cmd_descriptor default_desc = { 0 };
 	int needs_clflush = 0;
+	bool oacontrol_set = false; /* OACONTROL tracking. See check_cmd() */
 
 	ret = i915_gem_obj_prepare_shmem_read(batch_obj, &needs_clflush);
 	if (ret) {
@@ -402,76 +1008,27 @@ int i915_parse_cmds(struct intel_ring_buffer *ring,
 			length = ((*cmd & desc->length.mask) + LENGTH_BIAS);
 
 		if ((batch_end - cmd) < length) {
-			DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%d batchlen=%td\n",
+			DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n",
 					 *cmd,
 					 length,
-					 (unsigned long)(batch_end - cmd));
+					 batch_end - cmd);
 			ret = -EINVAL;
 			break;
 		}
 
-		if (desc->flags & CMD_DESC_REJECT) {
-			DRM_DEBUG_DRIVER("CMD: Rejected command: 0x%08X\n", *cmd);
+		if (!check_cmd(ring, desc, cmd, is_master, &oacontrol_set)) {
 			ret = -EINVAL;
 			break;
 		}
 
-		if ((desc->flags & CMD_DESC_MASTER) && !is_master) {
-			DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n",
-					 *cmd);
-			ret = -EINVAL;
-			break;
-		}
-
-		if (desc->flags & CMD_DESC_REGISTER) {
-			u32 reg_addr = cmd[desc->reg.offset] & desc->reg.mask;
-
-			if (!valid_reg(ring->reg_table,
-				       ring->reg_count, reg_addr)) {
-				if (!is_master ||
-				    !valid_reg(ring->master_reg_table,
-					       ring->master_reg_count,
-					       reg_addr)) {
-					DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (ring=%d)\n",
-							 reg_addr,
-							 *cmd,
-							 ring->id);
-					ret = -EINVAL;
-					break;
-				}
-			}
-		}
-
-		if (desc->flags & CMD_DESC_BITMASK) {
-			int i;
-
-			for (i = 0; i < MAX_CMD_DESC_BITMASKS; i++) {
-				u32 dword;
-
-				if (desc->bits[i].mask == 0)
-					break;
-
-				dword = cmd[desc->bits[i].offset] &
-					desc->bits[i].mask;
-
-				if (dword != desc->bits[i].expected) {
-					DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (ring=%d)\n",
-							 *cmd,
-							 desc->bits[i].mask,
-							 desc->bits[i].expected,
-							 dword, ring->id);
-					ret = -EINVAL;
-					break;
-				}
-			}
-
-			if (ret)
-				break;
-		}
-
 		cmd += length;
 	}
 
+	if (oacontrol_set) {
+		DRM_DEBUG_DRIVER("CMD: batch set OACONTROL but did not clear it\n");
+		ret = -EINVAL;
+	}
+
 	if (cmd >= batch_end) {
 		DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
 		ret = -EINVAL;
@@ -483,3 +1040,22 @@ int i915_parse_cmds(struct intel_ring_buffer *ring,
 
 	return ret;
 }
+
+/**
+ * i915_cmd_parser_get_version() - get the cmd parser version number
+ *
+ * The cmd parser maintains a simple increasing integer version number suitable
+ * for passing to userspace clients to determine what operations are permitted.
+ *
+ * Return: the current version number of the cmd parser
+ */
+int i915_cmd_parser_get_version(void)
+{
+	/*
+	 * Command parser version history
+	 *
+	 * 1. Initial version. Checks batches and reports violations, but leaves
+	 *    hardware parsing enabled (so does not allow new use cases).
+	 */
+	return 1;
+}
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 195fe5bc0aa..b8c689202c4 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -79,7 +79,7 @@ drm_add_fake_info_node(struct drm_minor *minor,
 
 static int i915_capabilities(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	const struct intel_device_info *info = INTEL_INFO(dev);
 
@@ -172,7 +172,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (%s)", obj->ring->name);
 }
 
-static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx)
+static void describe_ctx(struct seq_file *m, struct intel_context *ctx)
 {
 	seq_putc(m, ctx->is_initialized ? 'I' : 'i');
 	seq_putc(m, ctx->remap_slice ? 'R' : 'r');
@@ -181,7 +181,7 @@ static void describe_ctx(struct seq_file *m, struct i915_hw_context *ctx)
 
 static int i915_gem_object_list_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	uintptr_t list = (uintptr_t) node->info_ent->data;
 	struct list_head *head;
 	struct drm_device *dev = node->minor->dev;
@@ -239,7 +239,7 @@ static int obj_rank_by_stolen(void *priv,
 
 static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
@@ -371,7 +371,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 
 static int i915_gem_object_info(struct seq_file *m, void* data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 count, mappable_count, purgeable_count;
@@ -446,7 +446,9 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 
 		memset(&stats, 0, sizeof(stats));
 		stats.file_priv = file->driver_priv;
+		spin_lock(&file->table_lock);
 		idr_for_each(&file->object_idr, per_file_stats, &stats);
+		spin_unlock(&file->table_lock);
 		/*
 		 * Although we have a valid reference on file->pid, that does
 		 * not guarantee that the task_struct who called get_pid() is
@@ -474,7 +476,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 
 static int i915_gem_gtt_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	uintptr_t list = (uintptr_t) node->info_ent->data;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -509,12 +511,12 @@ static int i915_gem_gtt_info(struct seq_file *m, void *data)
 
 static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	unsigned long flags;
 	struct intel_crtc *crtc;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		const char pipe = pipe_name(crtc->pipe);
 		const char plane = plane_name(crtc->plane);
 		struct intel_unpin_work *work;
@@ -559,10 +561,10 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 
 static int i915_gem_request_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	struct drm_i915_gem_request *gem_request;
 	int ret, count, i;
 
@@ -594,7 +596,7 @@ static int i915_gem_request_info(struct seq_file *m, void *data)
 }
 
 static void i915_ring_seqno_info(struct seq_file *m,
-				 struct intel_ring_buffer *ring)
+				 struct intel_engine_cs *ring)
 {
 	if (ring->get_seqno) {
 		seq_printf(m, "Current sequence (%s): %u\n",
@@ -604,10 +606,10 @@ static void i915_ring_seqno_info(struct seq_file *m,
 
 static int i915_gem_seqno_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int ret, i;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -627,10 +629,10 @@ static int i915_gem_seqno_info(struct seq_file *m, void *data)
 
 static int i915_interrupt_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int ret, i, pipe;
 
 	ret = mutex_lock_interruptible(&dev->struct_mutex);
@@ -638,7 +640,47 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 		return ret;
 	intel_runtime_pm_get(dev_priv);
 
-	if (INTEL_INFO(dev)->gen >= 8) {
+	if (IS_CHERRYVIEW(dev)) {
+		int i;
+		seq_printf(m, "Master Interrupt Control:\t%08x\n",
+			   I915_READ(GEN8_MASTER_IRQ));
+
+		seq_printf(m, "Display IER:\t%08x\n",
+			   I915_READ(VLV_IER));
+		seq_printf(m, "Display IIR:\t%08x\n",
+			   I915_READ(VLV_IIR));
+		seq_printf(m, "Display IIR_RW:\t%08x\n",
+			   I915_READ(VLV_IIR_RW));
+		seq_printf(m, "Display IMR:\t%08x\n",
+			   I915_READ(VLV_IMR));
+		for_each_pipe(pipe)
+			seq_printf(m, "Pipe %c stat:\t%08x\n",
+				   pipe_name(pipe),
+				   I915_READ(PIPESTAT(pipe)));
+
+		seq_printf(m, "Port hotplug:\t%08x\n",
+			   I915_READ(PORT_HOTPLUG_EN));
+		seq_printf(m, "DPFLIPSTAT:\t%08x\n",
+			   I915_READ(VLV_DPFLIPSTAT));
+		seq_printf(m, "DPINVGTT:\t%08x\n",
+			   I915_READ(DPINVGTT));
+
+		for (i = 0; i < 4; i++) {
+			seq_printf(m, "GT Interrupt IMR %d:\t%08x\n",
+				   i, I915_READ(GEN8_GT_IMR(i)));
+			seq_printf(m, "GT Interrupt IIR %d:\t%08x\n",
+				   i, I915_READ(GEN8_GT_IIR(i)));
+			seq_printf(m, "GT Interrupt IER %d:\t%08x\n",
+				   i, I915_READ(GEN8_GT_IER(i)));
+		}
+
+		seq_printf(m, "PCU interrupt mask:\t%08x\n",
+			   I915_READ(GEN8_PCU_IMR));
+		seq_printf(m, "PCU interrupt identity:\t%08x\n",
+			   I915_READ(GEN8_PCU_IIR));
+		seq_printf(m, "PCU interrupt enable:\t%08x\n",
+			   I915_READ(GEN8_PCU_IER));
+	} else if (INTEL_INFO(dev)->gen >= 8) {
 		seq_printf(m, "Master Interrupt Control:\t%08x\n",
 			   I915_READ(GEN8_MASTER_IRQ));
 
@@ -768,7 +810,7 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 
 static int i915_gem_fence_regs_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i, ret;
@@ -797,10 +839,10 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data)
 
 static int i915_hws_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	const u32 *hws;
 	int i;
 
@@ -945,7 +987,7 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_next_seqno_fops,
 
 static int i915_rstdby_delays(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u16 crstanddelay;
@@ -966,9 +1008,9 @@ static int i915_rstdby_delays(struct seq_file *m, void *unused)
 	return 0;
 }
 
-static int i915_cur_delayinfo(struct seq_file *m, void *unused)
+static int i915_frequency_info(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret = 0;
@@ -991,6 +1033,7 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 		u32 rp_state_limits = I915_READ(GEN6_RP_STATE_LIMITS);
 		u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
+		u32 rpmodectl, rpinclimit, rpdeclimit;
 		u32 rpstat, cagf, reqf;
 		u32 rpupei, rpcurup, rpprevup;
 		u32 rpdownei, rpcurdown, rpprevdown;
@@ -1011,6 +1054,10 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 			reqf >>= 25;
 		reqf *= GT_FREQUENCY_MULTIPLIER;
 
+		rpmodectl = I915_READ(GEN6_RP_CONTROL);
+		rpinclimit = I915_READ(GEN6_RP_UP_THRESHOLD);
+		rpdeclimit = I915_READ(GEN6_RP_DOWN_THRESHOLD);
+
 		rpstat = I915_READ(GEN6_RPSTAT1);
 		rpupei = I915_READ(GEN6_RP_CUR_UP_EI);
 		rpcurup = I915_READ(GEN6_RP_CUR_UP);
@@ -1027,14 +1074,23 @@ static int i915_cur_delayinfo(struct seq_file *m, void *unused)
 		gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 		mutex_unlock(&dev->struct_mutex);
 
+		seq_printf(m, "PM IER=0x%08x IMR=0x%08x ISR=0x%08x IIR=0x%08x, MASK=0x%08x\n",
+			   I915_READ(GEN6_PMIER),
+			   I915_READ(GEN6_PMIMR),
+			   I915_READ(GEN6_PMISR),
+			   I915_READ(GEN6_PMIIR),
+			   I915_READ(GEN6_PMINTRMSK));
 		seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
-		seq_printf(m, "RPSTAT1: 0x%08x\n", rpstat);
 		seq_printf(m, "Render p-state ratio: %d\n",
 			   (gt_perf_status & 0xff00) >> 8);
 		seq_printf(m, "Render p-state VID: %d\n",
 			   gt_perf_status & 0xff);
 		seq_printf(m, "Render p-state limit: %d\n",
 			   rp_state_limits & 0xff);
+		seq_printf(m, "RPSTAT1: 0x%08x\n", rpstat);
+		seq_printf(m, "RPMODECTL: 0x%08x\n", rpmodectl);
+		seq_printf(m, "RPINCLIMIT: 0x%08x\n", rpinclimit);
+		seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
 		seq_printf(m, "RPNSWREQ: %dMHz\n", reqf);
 		seq_printf(m, "CAGF: %dMHz\n", cagf);
 		seq_printf(m, "RP CUR UP EI: %dus\n", rpupei &
@@ -1094,7 +1150,7 @@ out:
 
 static int i915_delayfreq_table(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 delayfreq;
@@ -1125,7 +1181,7 @@ static inline int MAP_TO_MV(int map)
 
 static int i915_inttoext_table(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 inttoext;
@@ -1149,7 +1205,7 @@ static int i915_inttoext_table(struct seq_file *m, void *unused)
 
 static int ironlake_drpc_info(struct seq_file *m)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 rgvmodectl, rstdbyctl;
@@ -1219,15 +1275,19 @@ static int ironlake_drpc_info(struct seq_file *m)
 static int vlv_drpc_info(struct seq_file *m)
 {
 
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 rpmodectl1, rcctl1;
 	unsigned fw_rendercount = 0, fw_mediacount = 0;
 
+	intel_runtime_pm_get(dev_priv);
+
 	rpmodectl1 = I915_READ(GEN6_RP_CONTROL);
 	rcctl1 = I915_READ(GEN6_RC_CONTROL);
 
+	intel_runtime_pm_put(dev_priv);
+
 	seq_printf(m, "Video Turbo Mode: %s\n",
 		   yesno(rpmodectl1 & GEN6_RP_MEDIA_TURBO));
 	seq_printf(m, "Turbo enabled: %s\n",
@@ -1247,6 +1307,11 @@ static int vlv_drpc_info(struct seq_file *m)
 			(I915_READ(VLV_GTLC_PW_STATUS) &
 				VLV_GTLC_PW_MEDIA_STATUS_MASK) ? "Up" : "Down");
 
+	seq_printf(m, "Render RC6 residency since boot: %u\n",
+		   I915_READ(VLV_GT_RENDER_RC6));
+	seq_printf(m, "Media RC6 residency since boot: %u\n",
+		   I915_READ(VLV_GT_MEDIA_RC6));
+
 	spin_lock_irq(&dev_priv->uncore.lock);
 	fw_rendercount = dev_priv->uncore.fw_rendercount;
 	fw_mediacount = dev_priv->uncore.fw_mediacount;
@@ -1263,7 +1328,7 @@ static int vlv_drpc_info(struct seq_file *m)
 static int gen6_drpc_info(struct seq_file *m)
 {
 
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 rpmodectl1, gt_core_status, rcctl1, rc6vids = 0;
@@ -1362,7 +1427,7 @@ static int gen6_drpc_info(struct seq_file *m)
 
 static int i915_drpc_info(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 
 	if (IS_VALLEYVIEW(dev))
@@ -1375,7 +1440,7 @@ static int i915_drpc_info(struct seq_file *m, void *unused)
 
 static int i915_fbc_status(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -1437,7 +1502,7 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 
 static int i915_ips_status(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -1460,7 +1525,7 @@ static int i915_ips_status(struct seq_file *m, void *unused)
 
 static int i915_sr_status(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	bool sr_enabled = false;
@@ -1486,7 +1551,7 @@ static int i915_sr_status(struct seq_file *m, void *unused)
 
 static int i915_emon_status(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long temp, chipset, gfx;
@@ -1514,7 +1579,7 @@ static int i915_emon_status(struct seq_file *m, void *unused)
 
 static int i915_ring_freq_table(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret = 0;
@@ -1557,7 +1622,7 @@ out:
 
 static int i915_gfxec(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
@@ -1577,7 +1642,7 @@ static int i915_gfxec(struct seq_file *m, void *unused)
 
 static int i915_opregion(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_opregion *opregion = &dev_priv->opregion;
@@ -1605,7 +1670,7 @@ out:
 
 static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct intel_fbdev *ifbdev = NULL;
 	struct intel_framebuffer *fb;
@@ -1651,11 +1716,11 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 
 static int i915_context_status(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
-	struct i915_hw_context *ctx;
+	struct intel_engine_cs *ring;
+	struct intel_context *ctx;
 	int ret, i;
 
 	ret = mutex_lock_interruptible(&dev->mode_config.mutex);
@@ -1675,6 +1740,9 @@ static int i915_context_status(struct seq_file *m, void *unused)
 	}
 
 	list_for_each_entry(ctx, &dev_priv->context_list, link) {
+		if (ctx->obj == NULL)
+			continue;
+
 		seq_puts(m, "HW context ");
 		describe_ctx(m, ctx);
 		for_each_ring(ring, dev_priv, i)
@@ -1692,7 +1760,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 static int i915_gen6_forcewake_count_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned forcewake_count = 0, fw_rendercount = 0, fw_mediacount = 0;
@@ -1740,7 +1808,7 @@ static const char *swizzle_string(unsigned swizzle)
 
 static int i915_swizzle_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
@@ -1788,10 +1856,14 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 
 static int per_file_ctx(int id, void *ptr, void *data)
 {
-	struct i915_hw_context *ctx = ptr;
+	struct intel_context *ctx = ptr;
 	struct seq_file *m = data;
 	struct i915_hw_ppgtt *ppgtt = ctx_to_ppgtt(ctx);
 
+	if (i915_gem_context_is_default(ctx))
+		seq_puts(m, "  default context:\n");
+	else
+		seq_printf(m, "  context %d:\n", ctx->id);
 	ppgtt->debug_dump(ppgtt, m);
 
 	return 0;
@@ -1800,7 +1872,7 @@ static int per_file_ctx(int id, void *ptr, void *data)
 static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
 	int unused, i;
 
@@ -1816,8 +1888,7 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 			u64 pdp = I915_READ(ring->mmio_base + offset + 4);
 			pdp <<= 32;
 			pdp |= I915_READ(ring->mmio_base + offset);
-			for (i = 0; i < 4; i++)
-				seq_printf(m, "\tPDP%d 0x%016llx\n", i, pdp);
+			seq_printf(m, "\tPDP%d 0x%016llx\n", i, pdp);
 		}
 	}
 }
@@ -1825,7 +1896,7 @@ static void gen8_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	struct drm_file *file;
 	int i;
 
@@ -1852,12 +1923,9 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 
 	list_for_each_entry_reverse(file, &dev->filelist, lhead) {
 		struct drm_i915_file_private *file_priv = file->driver_priv;
-		struct i915_hw_ppgtt *pvt_ppgtt;
 
-		pvt_ppgtt = ctx_to_ppgtt(file_priv->private_default_ctx);
 		seq_printf(m, "proc: %s\n",
 			   get_pid_task(file->pid, PIDTYPE_PID)->comm);
-		seq_puts(m, "  default context:\n");
 		idr_for_each(&file_priv->context_idr, per_file_ctx, m);
 	}
 	seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK));
@@ -1865,7 +1933,7 @@ static void gen6_ppgtt_info(struct seq_file *m, struct drm_device *dev)
 
 static int i915_ppgtt_info(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -1885,56 +1953,9 @@ static int i915_ppgtt_info(struct seq_file *m, void *data)
 	return 0;
 }
 
-static int i915_dpio_info(struct seq_file *m, void *data)
-{
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
-	struct drm_device *dev = node->minor->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret;
-
-
-	if (!IS_VALLEYVIEW(dev)) {
-		seq_puts(m, "unsupported\n");
-		return 0;
-	}
-
-	ret = mutex_lock_interruptible(&dev_priv->dpio_lock);
-	if (ret)
-		return ret;
-
-	seq_printf(m, "DPIO_CTL: 0x%08x\n", I915_READ(DPIO_CTL));
-
-	seq_printf(m, "DPIO PLL DW3 CH0 : 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW3(0)));
-	seq_printf(m, "DPIO PLL DW3 CH1: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW3(1)));
-
-	seq_printf(m, "DPIO PLL DW5 CH0: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW5(0)));
-	seq_printf(m, "DPIO PLL DW5 CH1: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW5(1)));
-
-	seq_printf(m, "DPIO PLL DW7 CH0: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW7(0)));
-	seq_printf(m, "DPIO PLL DW7 CH1: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW7(1)));
-
-	seq_printf(m, "DPIO PLL DW10 CH0: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW10(0)));
-	seq_printf(m, "DPIO PLL DW10 CH1: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_PLL_DW10(1)));
-
-	seq_printf(m, "DPIO_FASTCLK_DISABLE: 0x%08x\n",
-		   vlv_dpio_read(dev_priv, PIPE_A, VLV_CMN_DW0));
-
-	mutex_unlock(&dev_priv->dpio_lock);
-
-	return 0;
-}
-
 static int i915_llc(struct seq_file *m, void *data)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -2040,11 +2061,11 @@ static int i915_energy_uJ(struct seq_file *m, void *data)
 
 static int i915_pc8_status(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (!IS_HASWELL(dev)) {
+	if (!IS_HASWELL(dev) && !IS_BROADWELL(dev)) {
 		seq_puts(m, "not supported\n");
 		return 0;
 	}
@@ -2115,7 +2136,7 @@ static const char *power_domain_str(enum intel_display_power_domain domain)
 
 static int i915_power_domain_info(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
@@ -2170,7 +2191,7 @@ static void intel_encoder_info(struct seq_file *m,
 			       struct intel_crtc *intel_crtc,
 			       struct intel_encoder *intel_encoder)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_crtc *crtc = &intel_crtc->base;
 	struct intel_connector *intel_connector;
@@ -2178,12 +2199,12 @@ static void intel_encoder_info(struct seq_file *m,
 
 	encoder = &intel_encoder->base;
 	seq_printf(m, "\tencoder %d: type: %s, connectors:\n",
-		   encoder->base.id, drm_get_encoder_name(encoder));
+		   encoder->base.id, encoder->name);
 	for_each_connector_on_encoder(dev, encoder, intel_connector) {
 		struct drm_connector *connector = &intel_connector->base;
 		seq_printf(m, "\t\tconnector %d: type: %s, status: %s",
 			   connector->base.id,
-			   drm_get_connector_name(connector),
+			   connector->name,
 			   drm_get_connector_status_name(connector->status));
 		if (connector->status == connector_status_connected) {
 			struct drm_display_mode *mode = &crtc->mode;
@@ -2197,7 +2218,7 @@ static void intel_encoder_info(struct seq_file *m,
 
 static void intel_crtc_info(struct seq_file *m, struct intel_crtc *intel_crtc)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_crtc *crtc = &intel_crtc->base;
 	struct intel_encoder *intel_encoder;
@@ -2254,7 +2275,7 @@ static void intel_connector_info(struct seq_file *m,
 	struct drm_display_mode *mode;
 
 	seq_printf(m, "connector %d: type %s, status: %s\n",
-		   connector->base.id, drm_get_connector_name(connector),
+		   connector->base.id, connector->name,
 		   drm_get_connector_status_name(connector->status));
 	if (connector->status == connector_status_connected) {
 		seq_printf(m, "\tname: %s\n", connector->display_info.name);
@@ -2286,10 +2307,8 @@ static bool cursor_active(struct drm_device *dev, int pipe)
 
 	if (IS_845G(dev) || IS_I865G(dev))
 		state = I915_READ(_CURACNTR) & CURSOR_ENABLE;
-	else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev))
-		state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
 	else
-		state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE;
+		state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
 
 	return state;
 }
@@ -2299,10 +2318,7 @@ static bool cursor_position(struct drm_device *dev, int pipe, int *x, int *y)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 pos;
 
-	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev))
-		pos = I915_READ(CURPOS_IVB(pipe));
-	else
-		pos = I915_READ(CURPOS(pipe));
+	pos = I915_READ(CURPOS(pipe));
 
 	*x = (pos >> CURSOR_X_SHIFT) & CURSOR_POS_MASK;
 	if (pos & (CURSOR_POS_SIGN << CURSOR_X_SHIFT))
@@ -2317,7 +2333,7 @@ static bool cursor_position(struct drm_device *dev, int pipe, int *x, int *y)
 
 static int i915_display_info(struct seq_file *m, void *unused)
 {
-	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_info_node *node = m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *crtc;
@@ -2327,7 +2343,7 @@ static int i915_display_info(struct seq_file *m, void *unused)
 	drm_modeset_lock_all(dev);
 	seq_printf(m, "CRTC info\n");
 	seq_printf(m, "---------\n");
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		bool active;
 		int x, y;
 
@@ -2339,10 +2355,14 @@ static int i915_display_info(struct seq_file *m, void *unused)
 
 			active = cursor_position(dev, crtc->pipe, &x, &y);
 			seq_printf(m, "\tcursor visible? %s, position (%d, %d), addr 0x%08x, active? %s\n",
-				   yesno(crtc->cursor_visible),
+				   yesno(crtc->cursor_base),
 				   x, y, crtc->cursor_addr,
 				   yesno(active));
 		}
+
+		seq_printf(m, "\tunderrun reporting: cpu=%s pch=%s \n",
+			   yesno(!crtc->cpu_fifo_underrun_disabled),
+			   yesno(!crtc->pch_fifo_underrun_disabled));
 	}
 
 	seq_printf(m, "\n");
@@ -2595,7 +2615,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_device *dev, enum pipe pipe,
 
 	*source = INTEL_PIPE_CRC_SOURCE_PIPE;
 
-	mutex_lock(&dev->mode_config.mutex);
+	drm_modeset_lock_all(dev);
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list,
 			    base.head) {
 		if (!encoder->base.crtc)
@@ -2631,7 +2651,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_device *dev, enum pipe pipe,
 			break;
 		}
 	}
-	mutex_unlock(&dev->mode_config.mutex);
+	drm_modeset_unlock_all(dev);
 
 	return ret;
 }
@@ -3106,7 +3126,7 @@ static const struct file_operations i915_display_crc_ctl_fops = {
 static void wm_latency_show(struct seq_file *m, const uint16_t wm[5])
 {
 	struct drm_device *dev = m->private;
-	int num_levels = IS_HASWELL(dev) || IS_BROADWELL(dev) ? 5 : 4;
+	int num_levels = ilk_wm_max_level(dev) + 1;
 	int level;
 
 	drm_modeset_lock_all(dev);
@@ -3189,7 +3209,7 @@ static ssize_t wm_latency_write(struct file *file, const char __user *ubuf,
 	struct seq_file *m = file->private_data;
 	struct drm_device *dev = m->private;
 	uint16_t new[5] = { 0 };
-	int num_levels = IS_HASWELL(dev) || IS_BROADWELL(dev) ? 5 : 4;
+	int num_levels = ilk_wm_max_level(dev) + 1;
 	int level;
 	int ret;
 	char tmp[32];
@@ -3286,9 +3306,15 @@ static int
 i915_wedged_set(void *data, u64 val)
 {
 	struct drm_device *dev = data;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	intel_runtime_pm_get(dev_priv);
 
 	i915_handle_error(dev, val,
 			  "Manually setting wedged to %llu", val);
+
+	intel_runtime_pm_put(dev_priv);
+
 	return 0;
 }
 
@@ -3774,7 +3800,7 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_gem_hws_bsd", i915_hws_info, 0, (void *)VCS},
 	{"i915_gem_hws_vebox", i915_hws_info, 0, (void *)VECS},
 	{"i915_rstdby_delays", i915_rstdby_delays, 0},
-	{"i915_cur_delayinfo", i915_cur_delayinfo, 0},
+	{"i915_frequency_info", i915_frequency_info, 0},
 	{"i915_delayfreq_table", i915_delayfreq_table, 0},
 	{"i915_inttoext_table", i915_inttoext_table, 0},
 	{"i915_drpc_info", i915_drpc_info, 0},
@@ -3790,7 +3816,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_gen6_forcewake_count", i915_gen6_forcewake_count_info, 0},
 	{"i915_swizzle_info", i915_swizzle_info, 0},
 	{"i915_ppgtt_info", i915_ppgtt_info, 0},
-	{"i915_dpio", i915_dpio_info, 0},
 	{"i915_llc", i915_llc, 0},
 	{"i915_edp_psr_status", i915_edp_psr_status, 0},
 	{"i915_sink_crc_eDP1", i915_sink_crc, 0},
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index eedb023af27..d4434414062 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -36,6 +36,8 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include <linux/pci.h>
+#include <linux/console.h>
+#include <linux/vt.h>
 #include <linux/vgaarb.h>
 #include <linux/acpi.h>
 #include <linux/pnp.h>
@@ -44,6 +46,7 @@
 #include <acpi/video.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
+#include <linux/oom.h>
 
 #define LP_RING(d) (&((struct drm_i915_private *)(d))->ring[RCS])
 
@@ -63,7 +66,7 @@
  * has access to the ring.
  */
 #define RING_LOCK_TEST_WITH_RETURN(dev, file) do {			\
-	if (LP_RING(dev->dev_private)->obj == NULL)			\
+	if (LP_RING(dev->dev_private)->buffer->obj == NULL)			\
 		LOCK_TEST_WITH_RETURN(dev, file);			\
 } while (0)
 
@@ -119,7 +122,7 @@ static void i915_write_hws_pga(struct drm_device *dev)
 static void i915_free_hws(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = LP_RING(dev_priv);
+	struct intel_engine_cs *ring = LP_RING(dev_priv);
 
 	if (dev_priv->status_page_dmah) {
 		drm_pci_free(dev, dev_priv->status_page_dmah);
@@ -139,7 +142,8 @@ void i915_kernel_lost_context(struct drm_device * dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv;
-	struct intel_ring_buffer *ring = LP_RING(dev_priv);
+	struct intel_engine_cs *ring = LP_RING(dev_priv);
+	struct intel_ringbuffer *ringbuf = ring->buffer;
 
 	/*
 	 * We should never lose context on the ring with modesetting
@@ -148,17 +152,17 @@ void i915_kernel_lost_context(struct drm_device * dev)
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return;
 
-	ring->head = I915_READ_HEAD(ring) & HEAD_ADDR;
-	ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
-	ring->space = ring->head - (ring->tail + I915_RING_FREE_SPACE);
-	if (ring->space < 0)
-		ring->space += ring->size;
+	ringbuf->head = I915_READ_HEAD(ring) & HEAD_ADDR;
+	ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
+	ringbuf->space = ringbuf->head - (ringbuf->tail + I915_RING_FREE_SPACE);
+	if (ringbuf->space < 0)
+		ringbuf->space += ringbuf->size;
 
 	if (!dev->primary->master)
 		return;
 
 	master_priv = dev->primary->master->driver_priv;
-	if (ring->head == ring->tail && master_priv->sarea_priv)
+	if (ringbuf->head == ringbuf->tail && master_priv->sarea_priv)
 		master_priv->sarea_priv->perf_boxes |= I915_BOX_RING_EMPTY;
 }
 
@@ -201,7 +205,7 @@ static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init)
 	}
 
 	if (init->ring_size != 0) {
-		if (LP_RING(dev_priv)->obj != NULL) {
+		if (LP_RING(dev_priv)->buffer->obj != NULL) {
 			i915_dma_cleanup(dev);
 			DRM_ERROR("Client tried to initialize ringbuffer in "
 				  "GEM mode\n");
@@ -234,11 +238,11 @@ static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init)
 static int i915_dma_resume(struct drm_device * dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = LP_RING(dev_priv);
+	struct intel_engine_cs *ring = LP_RING(dev_priv);
 
 	DRM_DEBUG_DRIVER("%s\n", __func__);
 
-	if (ring->virtual_start == NULL) {
+	if (ring->buffer->virtual_start == NULL) {
 		DRM_ERROR("can not ioremap virtual address for"
 			  " ring buffer\n");
 		return -ENOMEM;
@@ -360,7 +364,7 @@ static int i915_emit_cmds(struct drm_device * dev, int *buffer, int dwords)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i, ret;
 
-	if ((dwords+1) * sizeof(int) >= LP_RING(dev_priv)->size - 8)
+	if ((dwords+1) * sizeof(int) >= LP_RING(dev_priv)->buffer->size - 8)
 		return -EINVAL;
 
 	for (i = 0; i < dwords;) {
@@ -782,7 +786,7 @@ static int i915_wait_irq(struct drm_device * dev, int irq_nr)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
 	int ret = 0;
-	struct intel_ring_buffer *ring = LP_RING(dev_priv);
+	struct intel_engine_cs *ring = LP_RING(dev_priv);
 
 	DRM_DEBUG_DRIVER("irq_nr=%d breadcrumb=%d\n", irq_nr,
 		  READ_BREADCRUMB(dev_priv));
@@ -823,7 +827,7 @@ static int i915_irq_emit(struct drm_device *dev, void *data,
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return -ENODEV;
 
-	if (!dev_priv || !LP_RING(dev_priv)->virtual_start) {
+	if (!dev_priv || !LP_RING(dev_priv)->buffer->virtual_start) {
 		DRM_ERROR("called with no initialization\n");
 		return -EINVAL;
 	}
@@ -1017,6 +1021,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_EXEC_HANDLE_LUT:
 		value = 1;
 		break;
+	case I915_PARAM_CMD_PARSER_VERSION:
+		value = i915_cmd_parser_get_version();
+		break;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", param->param);
 		return -EINVAL;
@@ -1070,7 +1077,7 @@ static int i915_set_status_page(struct drm_device *dev, void *data,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	drm_i915_hws_addr_t *hws = data;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return -ENODEV;
@@ -1277,12 +1284,13 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_
 static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	bool can_switch;
 
-	spin_lock(&dev->count_lock);
-	can_switch = (dev->open_count == 0);
-	spin_unlock(&dev->count_lock);
-	return can_switch;
+	/*
+	 * FIXME: open_count is protected by drm_global_mutex but that would lead to
+	 * locking inversion with the driver load path. And the access here is
+	 * completely racy anyway. So don't bother with locking for now.
+	 */
+	return dev->open_count == 0;
 }
 
 static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
@@ -1326,7 +1334,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	intel_power_domains_init_hw(dev_priv);
 
-	ret = drm_irq_install(dev);
+	ret = drm_irq_install(dev, dev->pdev->irq);
 	if (ret)
 		goto cleanup_gem_stolen;
 
@@ -1336,7 +1344,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	ret = i915_gem_init(dev);
 	if (ret)
-		goto cleanup_power;
+		goto cleanup_irq;
 
 	INIT_WORK(&dev_priv->console_resume_work, intel_console_resume);
 
@@ -1345,10 +1353,8 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	/* Always safe in the mode setting case. */
 	/* FIXME: do pre/post-mode set stuff in core KMS code */
 	dev->vblank_disable_allowed = true;
-	if (INTEL_INFO(dev)->num_pipes == 0) {
-		intel_display_power_put(dev_priv, POWER_DOMAIN_VGA);
+	if (INTEL_INFO(dev)->num_pipes == 0)
 		return 0;
-	}
 
 	ret = intel_fbdev_init(dev);
 	if (ret)
@@ -1382,9 +1388,7 @@ cleanup_gem:
 	i915_gem_context_fini(dev);
 	mutex_unlock(&dev->struct_mutex);
 	WARN_ON(dev_priv->mm.aliasing_ppgtt);
-	drm_mm_takedown(&dev_priv->gtt.base.mm);
-cleanup_power:
-	intel_display_power_put(dev_priv, POWER_DOMAIN_VGA);
+cleanup_irq:
 	drm_irq_uninstall(dev);
 cleanup_gem_stolen:
 	i915_gem_cleanup_stolen(dev);
@@ -1447,6 +1451,39 @@ static void i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
 }
 #endif
 
+#if !defined(CONFIG_VGA_CONSOLE)
+static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
+{
+	return 0;
+}
+#elif !defined(CONFIG_DUMMY_CONSOLE)
+static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
+{
+	return -ENODEV;
+}
+#else
+static int i915_kick_out_vgacon(struct drm_i915_private *dev_priv)
+{
+	int ret = 0;
+
+	DRM_INFO("Replacing VGA console driver\n");
+
+	console_lock();
+	if (con_is_bound(&vga_con))
+		ret = do_take_over_console(&dummy_con, 0, MAX_NR_CONSOLES - 1, 1);
+	if (ret == 0) {
+		ret = do_unregister_con_driver(&vga_con);
+
+		/* Ignore "already unregistered". */
+		if (ret == -ENODEV)
+			ret = 0;
+	}
+	console_unlock();
+
+	return ret;
+}
+#endif
+
 static void i915_dump_device_info(struct drm_i915_private *dev_priv)
 {
 	const struct intel_device_info *info = &dev_priv->info;
@@ -1620,8 +1657,15 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	if (ret)
 		goto out_regs;
 
-	if (drm_core_check_feature(dev, DRIVER_MODESET))
+	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+		ret = i915_kick_out_vgacon(dev_priv);
+		if (ret) {
+			DRM_ERROR("failed to remove conflicting VGA console\n");
+			goto out_gtt;
+		}
+
 		i915_kick_out_firmware_fb(dev_priv);
+	}
 
 	pci_set_master(dev->pdev);
 
@@ -1739,8 +1783,8 @@ out_power_well:
 	intel_power_domains_remove(dev_priv);
 	drm_vblank_cleanup(dev);
 out_gem_unload:
-	if (dev_priv->mm.inactive_shrinker.scan_objects)
-		unregister_shrinker(&dev_priv->mm.inactive_shrinker);
+	WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier));
+	unregister_shrinker(&dev_priv->mm.shrinker);
 
 	if (dev->pdev->msi_enabled)
 		pci_disable_msi(dev->pdev);
@@ -1753,8 +1797,6 @@ out_mtrrfree:
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
 	io_mapping_free(dev_priv->gtt.mappable);
 out_gtt:
-	list_del(&dev_priv->gtt.base.global_link);
-	drm_mm_takedown(&dev_priv->gtt.base.mm);
 	dev_priv->gtt.base.cleanup(&dev_priv->gtt.base);
 out_regs:
 	intel_uncore_fini(dev);
@@ -1791,8 +1833,8 @@ int i915_driver_unload(struct drm_device *dev)
 
 	i915_teardown_sysfs(dev);
 
-	if (dev_priv->mm.inactive_shrinker.scan_objects)
-		unregister_shrinker(&dev_priv->mm.inactive_shrinker);
+	WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier));
+	unregister_shrinker(&dev_priv->mm.shrinker);
 
 	io_mapping_free(dev_priv->gtt.mappable);
 	arch_phys_wc_del(dev_priv->gtt.mtrr);
@@ -1843,7 +1885,6 @@ int i915_driver_unload(struct drm_device *dev)
 			i915_free_hws(dev);
 	}
 
-	list_del(&dev_priv->gtt.base.global_link);
 	WARN_ON(!list_empty(&dev_priv->vm_list));
 
 	drm_vblank_cleanup(dev);
@@ -1864,7 +1905,7 @@ int i915_driver_unload(struct drm_device *dev)
 		kmem_cache_destroy(dev_priv->slab);
 
 	pci_dev_put(dev_priv->bridge_dev);
-	kfree(dev->dev_private);
+	kfree(dev_priv);
 
 	return 0;
 }
@@ -1925,6 +1966,8 @@ void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 
+	if (file_priv && file_priv->bsd_ring)
+		file_priv->bsd_ring = NULL;
 	kfree(file_priv);
 }
 
@@ -1978,9 +2021,10 @@ const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_DESTROY, i915_gem_context_destroy_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_REG_READ, i915_reg_read_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GET_RESET_STATS, i915_get_reset_stats_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_USERPTR, i915_gem_userptr_ioctl, DRM_UNLOCKED|DRM_RENDER_ALLOW),
 };
 
-int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls);
+int i915_max_ioctl = ARRAY_SIZE(i915_ioctls);
 
 /*
  * This is really ugly: Because old userspace abused the linux agp interface to
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 82f4d1f47d3..651e65e051c 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -36,6 +36,7 @@
 
 #include <linux/console.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
 
 static struct drm_driver driver;
@@ -49,12 +50,30 @@ static struct drm_driver driver;
 	.dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET }, \
 	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET }
 
+#define GEN_CHV_PIPEOFFSETS \
+	.pipe_offsets = { PIPE_A_OFFSET, PIPE_B_OFFSET, \
+			  CHV_PIPE_C_OFFSET }, \
+	.trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \
+			   CHV_TRANSCODER_C_OFFSET, }, \
+	.dpll_offsets = { DPLL_A_OFFSET, DPLL_B_OFFSET, \
+			  CHV_DPLL_C_OFFSET }, \
+	.dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET, \
+			     CHV_DPLL_C_MD_OFFSET }, \
+	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET, \
+			     CHV_PALETTE_C_OFFSET }
+
+#define CURSOR_OFFSETS \
+	.cursor_offsets = { CURSOR_A_OFFSET, CURSOR_B_OFFSET, CHV_CURSOR_C_OFFSET }
+
+#define IVB_CURSOR_OFFSETS \
+	.cursor_offsets = { CURSOR_A_OFFSET, IVB_CURSOR_B_OFFSET, IVB_CURSOR_C_OFFSET }
 
 static const struct intel_device_info intel_i830_info = {
 	.gen = 2, .is_mobile = 1, .cursor_needs_physical = 1, .num_pipes = 2,
 	.has_overlay = 1, .overlay_needs_physical = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_845g_info = {
@@ -62,6 +81,7 @@ static const struct intel_device_info intel_845g_info = {
 	.has_overlay = 1, .overlay_needs_physical = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_i85x_info = {
@@ -71,6 +91,7 @@ static const struct intel_device_info intel_i85x_info = {
 	.has_fbc = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_i865g_info = {
@@ -78,6 +99,7 @@ static const struct intel_device_info intel_i865g_info = {
 	.has_overlay = 1, .overlay_needs_physical = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_i915g_info = {
@@ -85,6 +107,7 @@ static const struct intel_device_info intel_i915g_info = {
 	.has_overlay = 1, .overlay_needs_physical = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 static const struct intel_device_info intel_i915gm_info = {
 	.gen = 3, .is_mobile = 1, .num_pipes = 2,
@@ -94,12 +117,14 @@ static const struct intel_device_info intel_i915gm_info = {
 	.has_fbc = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 static const struct intel_device_info intel_i945g_info = {
 	.gen = 3, .has_hotplug = 1, .cursor_needs_physical = 1, .num_pipes = 2,
 	.has_overlay = 1, .overlay_needs_physical = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 static const struct intel_device_info intel_i945gm_info = {
 	.gen = 3, .is_i945gm = 1, .is_mobile = 1, .num_pipes = 2,
@@ -109,6 +134,7 @@ static const struct intel_device_info intel_i945gm_info = {
 	.has_fbc = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_i965g_info = {
@@ -117,6 +143,7 @@ static const struct intel_device_info intel_i965g_info = {
 	.has_overlay = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_i965gm_info = {
@@ -126,6 +153,7 @@ static const struct intel_device_info intel_i965gm_info = {
 	.supports_tv = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_g33_info = {
@@ -134,6 +162,7 @@ static const struct intel_device_info intel_g33_info = {
 	.has_overlay = 1,
 	.ring_mask = RENDER_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_g45_info = {
@@ -141,6 +170,7 @@ static const struct intel_device_info intel_g45_info = {
 	.has_pipe_cxsr = 1, .has_hotplug = 1,
 	.ring_mask = RENDER_RING | BSD_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_gm45_info = {
@@ -150,6 +180,7 @@ static const struct intel_device_info intel_gm45_info = {
 	.supports_tv = 1,
 	.ring_mask = RENDER_RING | BSD_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_pineview_info = {
@@ -157,6 +188,7 @@ static const struct intel_device_info intel_pineview_info = {
 	.need_gfx_hws = 1, .has_hotplug = 1,
 	.has_overlay = 1,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_ironlake_d_info = {
@@ -164,6 +196,7 @@ static const struct intel_device_info intel_ironlake_d_info = {
 	.need_gfx_hws = 1, .has_hotplug = 1,
 	.ring_mask = RENDER_RING | BSD_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_ironlake_m_info = {
@@ -172,6 +205,7 @@ static const struct intel_device_info intel_ironlake_m_info = {
 	.has_fbc = 1,
 	.ring_mask = RENDER_RING | BSD_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_sandybridge_d_info = {
@@ -181,6 +215,7 @@ static const struct intel_device_info intel_sandybridge_d_info = {
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING,
 	.has_llc = 1,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_sandybridge_m_info = {
@@ -190,6 +225,7 @@ static const struct intel_device_info intel_sandybridge_m_info = {
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING,
 	.has_llc = 1,
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 #define GEN7_FEATURES  \
@@ -203,6 +239,7 @@ static const struct intel_device_info intel_ivybridge_d_info = {
 	GEN7_FEATURES,
 	.is_ivybridge = 1,
 	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_ivybridge_m_info = {
@@ -210,6 +247,7 @@ static const struct intel_device_info intel_ivybridge_m_info = {
 	.is_ivybridge = 1,
 	.is_mobile = 1,
 	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_ivybridge_q_info = {
@@ -217,6 +255,7 @@ static const struct intel_device_info intel_ivybridge_q_info = {
 	.is_ivybridge = 1,
 	.num_pipes = 0, /* legal, last one wins */
 	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_valleyview_m_info = {
@@ -228,6 +267,7 @@ static const struct intel_device_info intel_valleyview_m_info = {
 	.has_fbc = 0, /* legal, last one wins */
 	.has_llc = 0, /* legal, last one wins */
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_valleyview_d_info = {
@@ -238,6 +278,7 @@ static const struct intel_device_info intel_valleyview_d_info = {
 	.has_fbc = 0, /* legal, last one wins */
 	.has_llc = 0, /* legal, last one wins */
 	GEN_DEFAULT_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_haswell_d_info = {
@@ -247,6 +288,7 @@ static const struct intel_device_info intel_haswell_d_info = {
 	.has_fpga_dbg = 1,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_haswell_m_info = {
@@ -257,6 +299,7 @@ static const struct intel_device_info intel_haswell_m_info = {
 	.has_fpga_dbg = 1,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
 	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_broadwell_d_info = {
@@ -267,6 +310,7 @@ static const struct intel_device_info intel_broadwell_d_info = {
 	.has_ddi = 1,
 	.has_fbc = 1,
 	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
 };
 
 static const struct intel_device_info intel_broadwell_m_info = {
@@ -277,6 +321,40 @@ static const struct intel_device_info intel_broadwell_m_info = {
 	.has_ddi = 1,
 	.has_fbc = 1,
 	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_broadwell_gt3d_info = {
+	.gen = 8, .num_pipes = 3,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+	.has_llc = 1,
+	.has_ddi = 1,
+	.has_fbc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_broadwell_gt3m_info = {
+	.gen = 8, .is_mobile = 1, .num_pipes = 3,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING | BSD2_RING,
+	.has_llc = 1,
+	.has_ddi = 1,
+	.has_fbc = 1,
+	GEN_DEFAULT_PIPEOFFSETS,
+	IVB_CURSOR_OFFSETS,
+};
+
+static const struct intel_device_info intel_cherryview_info = {
+	.is_preliminary = 1,
+	.gen = 8, .num_pipes = 3,
+	.need_gfx_hws = 1, .has_hotplug = 1,
+	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
+	.is_valleyview = 1,
+	.display_mmio_offset = VLV_DISPLAY_BASE,
+	GEN_CHV_PIPEOFFSETS,
+	CURSOR_OFFSETS,
 };
 
 /*
@@ -311,8 +389,11 @@ static const struct intel_device_info intel_broadwell_m_info = {
 	INTEL_HSW_M_IDS(&intel_haswell_m_info), \
 	INTEL_VLV_M_IDS(&intel_valleyview_m_info),	\
 	INTEL_VLV_D_IDS(&intel_valleyview_d_info),	\
-	INTEL_BDW_M_IDS(&intel_broadwell_m_info),	\
-	INTEL_BDW_D_IDS(&intel_broadwell_d_info)
+	INTEL_BDW_GT12M_IDS(&intel_broadwell_m_info),	\
+	INTEL_BDW_GT12D_IDS(&intel_broadwell_d_info),	\
+	INTEL_BDW_GT3M_IDS(&intel_broadwell_gt3m_info),	\
+	INTEL_BDW_GT3D_IDS(&intel_broadwell_gt3d_info), \
+	INTEL_CHV_IDS(&intel_cherryview_info)
 
 static const struct pci_device_id pciidlist[] = {		/* aka */
 	INTEL_PCI_IDS,
@@ -445,18 +526,20 @@ static int i915_drm_freeze(struct drm_device *dev)
 			return error;
 		}
 
-		cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
-
 		drm_irq_uninstall(dev);
 		dev_priv->enable_hotplug_processing = false;
+
+		intel_disable_gt_powersave(dev);
+
 		/*
 		 * Disable CRTCs directly since we want to preserve sw state
 		 * for _thaw.
 		 */
-		mutex_lock(&dev->mode_config.mutex);
-		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
+		drm_modeset_lock_all(dev);
+		for_each_crtc(dev, crtc) {
 			dev_priv->display.crtc_disable(crtc);
-		mutex_unlock(&dev->mode_config.mutex);
+		}
+		drm_modeset_unlock_all(dev);
 
 		intel_modeset_suspend_hw(dev);
 	}
@@ -519,24 +602,6 @@ void intel_console_resume(struct work_struct *work)
 	console_unlock();
 }
 
-static void intel_resume_hotplug(struct drm_device *dev)
-{
-	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct intel_encoder *encoder;
-
-	mutex_lock(&mode_config->mutex);
-	DRM_DEBUG_KMS("running encoder hotplug functions\n");
-
-	list_for_each_entry(encoder, &mode_config->encoder_list, base.head)
-		if (encoder->hot_plug)
-			encoder->hot_plug(encoder);
-
-	mutex_unlock(&mode_config->mutex);
-
-	/* Just fire off a uevent and let userspace tell us what to do */
-	drm_helper_hpd_irq_event(dev);
-}
-
 static int i915_drm_thaw_early(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -551,7 +616,6 @@ static int i915_drm_thaw_early(struct drm_device *dev)
 static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int error = 0;
 
 	if (drm_core_check_feature(dev, DRIVER_MODESET) &&
 	    restore_gtt_mappings) {
@@ -569,12 +633,14 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 		drm_mode_config_reset(dev);
 
 		mutex_lock(&dev->struct_mutex);
-
-		error = i915_gem_init_hw(dev);
+		if (i915_gem_init_hw(dev)) {
+			DRM_ERROR("failed to re-initialize GPU, declaring wedged!\n");
+			atomic_set_mask(I915_WEDGED, &dev_priv->gpu_error.reset_counter);
+		}
 		mutex_unlock(&dev->struct_mutex);
 
 		/* We need working interrupts for modeset enabling ... */
-		drm_irq_install(dev);
+		drm_irq_install(dev, dev->pdev->irq);
 
 		intel_modeset_init_hw(dev);
 
@@ -591,7 +657,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 		intel_hpd_init(dev);
 		dev_priv->enable_hotplug_processing = true;
 		/* Config may have changed between suspend and resume */
-		intel_resume_hotplug(dev);
+		drm_helper_hpd_irq_event(dev);
 	}
 
 	intel_opregion_init(dev);
@@ -613,7 +679,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 	mutex_unlock(&dev_priv->modeset_restore_lock);
 
 	intel_runtime_pm_put(dev_priv);
-	return error;
+	return 0;
 }
 
 static int i915_drm_thaw(struct drm_device *dev)
@@ -746,18 +812,20 @@ int i915_reset(struct drm_device *dev)
 			return ret;
 		}
 
-		drm_irq_uninstall(dev);
-		drm_irq_install(dev);
+		/*
+		 * FIXME: This races pretty badly against concurrent holders of
+		 * ring interrupts. This is possible since we've started to drop
+		 * dev->struct_mutex in select places when waiting for the gpu.
+		 */
 
-		/* rps/rc6 re-init is necessary to restore state lost after the
-		 * reset and the re-install of drm irq. Skip for ironlake per
+		/*
+		 * rps/rc6 re-init is necessary to restore state lost after the
+		 * reset and the re-install of gt irqs. Skip for ironlake per
 		 * previous concerns that it doesn't respond well to some forms
-		 * of re-init after reset. */
-		if (INTEL_INFO(dev)->gen > 5) {
-			mutex_lock(&dev->struct_mutex);
-			intel_enable_gt_powersave(dev);
-			mutex_unlock(&dev->struct_mutex);
-		}
+		 * of re-init after reset.
+		 */
+		if (INTEL_INFO(dev)->gen > 5)
+			intel_reset_gt_powersave(dev);
 
 		intel_hpd_init(dev);
 	} else {
@@ -891,21 +959,453 @@ static int i915_pm_poweroff(struct device *dev)
 	return i915_drm_freeze(drm_dev);
 }
 
-static int i915_runtime_suspend(struct device *device)
+static int hsw_runtime_suspend(struct drm_i915_private *dev_priv)
+{
+	hsw_enable_pc8(dev_priv);
+
+	return 0;
+}
+
+static int snb_runtime_resume(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+
+	intel_init_pch_refclk(dev);
+
+	return 0;
+}
+
+static int hsw_runtime_resume(struct drm_i915_private *dev_priv)
+{
+	hsw_disable_pc8(dev_priv);
+
+	return 0;
+}
+
+/*
+ * Save all Gunit registers that may be lost after a D3 and a subsequent
+ * S0i[R123] transition. The list of registers needing a save/restore is
+ * defined in the VLV2_S0IXRegs document. This documents marks all Gunit
+ * registers in the following way:
+ * - Driver: saved/restored by the driver
+ * - Punit : saved/restored by the Punit firmware
+ * - No, w/o marking: no need to save/restore, since the register is R/O or
+ *                    used internally by the HW in a way that doesn't depend
+ *                    keeping the content across a suspend/resume.
+ * - Debug : used for debugging
+ *
+ * We save/restore all registers marked with 'Driver', with the following
+ * exceptions:
+ * - Registers out of use, including also registers marked with 'Debug'.
+ *   These have no effect on the driver's operation, so we don't save/restore
+ *   them to reduce the overhead.
+ * - Registers that are fully setup by an initialization function called from
+ *   the resume path. For example many clock gating and RPS/RC6 registers.
+ * - Registers that provide the right functionality with their reset defaults.
+ *
+ * TODO: Except for registers that based on the above 3 criteria can be safely
+ * ignored, we save/restore all others, practically treating the HW context as
+ * a black-box for the driver. Further investigation is needed to reduce the
+ * saved/restored registers even further, by following the same 3 criteria.
+ */
+static void vlv_save_gunit_s0ix_state(struct drm_i915_private *dev_priv)
+{
+	struct vlv_s0ix_state *s = &dev_priv->vlv_s0ix_state;
+	int i;
+
+	/* GAM 0x4000-0x4770 */
+	s->wr_watermark		= I915_READ(GEN7_WR_WATERMARK);
+	s->gfx_prio_ctrl	= I915_READ(GEN7_GFX_PRIO_CTRL);
+	s->arb_mode		= I915_READ(ARB_MODE);
+	s->gfx_pend_tlb0	= I915_READ(GEN7_GFX_PEND_TLB0);
+	s->gfx_pend_tlb1	= I915_READ(GEN7_GFX_PEND_TLB1);
+
+	for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++)
+		s->lra_limits[i] = I915_READ(GEN7_LRA_LIMITS_BASE + i * 4);
+
+	s->media_max_req_count	= I915_READ(GEN7_MEDIA_MAX_REQ_COUNT);
+	s->gfx_max_req_count	= I915_READ(GEN7_MEDIA_MAX_REQ_COUNT);
+
+	s->render_hwsp		= I915_READ(RENDER_HWS_PGA_GEN7);
+	s->ecochk		= I915_READ(GAM_ECOCHK);
+	s->bsd_hwsp		= I915_READ(BSD_HWS_PGA_GEN7);
+	s->blt_hwsp		= I915_READ(BLT_HWS_PGA_GEN7);
+
+	s->tlb_rd_addr		= I915_READ(GEN7_TLB_RD_ADDR);
+
+	/* MBC 0x9024-0x91D0, 0x8500 */
+	s->g3dctl		= I915_READ(VLV_G3DCTL);
+	s->gsckgctl		= I915_READ(VLV_GSCKGCTL);
+	s->mbctl		= I915_READ(GEN6_MBCTL);
+
+	/* GCP 0x9400-0x9424, 0x8100-0x810C */
+	s->ucgctl1		= I915_READ(GEN6_UCGCTL1);
+	s->ucgctl3		= I915_READ(GEN6_UCGCTL3);
+	s->rcgctl1		= I915_READ(GEN6_RCGCTL1);
+	s->rcgctl2		= I915_READ(GEN6_RCGCTL2);
+	s->rstctl		= I915_READ(GEN6_RSTCTL);
+	s->misccpctl		= I915_READ(GEN7_MISCCPCTL);
+
+	/* GPM 0xA000-0xAA84, 0x8000-0x80FC */
+	s->gfxpause		= I915_READ(GEN6_GFXPAUSE);
+	s->rpdeuhwtc		= I915_READ(GEN6_RPDEUHWTC);
+	s->rpdeuc		= I915_READ(GEN6_RPDEUC);
+	s->ecobus		= I915_READ(ECOBUS);
+	s->pwrdwnupctl		= I915_READ(VLV_PWRDWNUPCTL);
+	s->rp_down_timeout	= I915_READ(GEN6_RP_DOWN_TIMEOUT);
+	s->rp_deucsw		= I915_READ(GEN6_RPDEUCSW);
+	s->rcubmabdtmr		= I915_READ(GEN6_RCUBMABDTMR);
+	s->rcedata		= I915_READ(VLV_RCEDATA);
+	s->spare2gh		= I915_READ(VLV_SPAREG2H);
+
+	/* Display CZ domain, 0x4400C-0x4402C, 0x4F000-0x4F11F */
+	s->gt_imr		= I915_READ(GTIMR);
+	s->gt_ier		= I915_READ(GTIER);
+	s->pm_imr		= I915_READ(GEN6_PMIMR);
+	s->pm_ier		= I915_READ(GEN6_PMIER);
+
+	for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++)
+		s->gt_scratch[i] = I915_READ(GEN7_GT_SCRATCH_BASE + i * 4);
+
+	/* GT SA CZ domain, 0x100000-0x138124 */
+	s->tilectl		= I915_READ(TILECTL);
+	s->gt_fifoctl		= I915_READ(GTFIFOCTL);
+	s->gtlc_wake_ctrl	= I915_READ(VLV_GTLC_WAKE_CTRL);
+	s->gtlc_survive		= I915_READ(VLV_GTLC_SURVIVABILITY_REG);
+	s->pmwgicz		= I915_READ(VLV_PMWGICZ);
+
+	/* Gunit-Display CZ domain, 0x182028-0x1821CF */
+	s->gu_ctl0		= I915_READ(VLV_GU_CTL0);
+	s->gu_ctl1		= I915_READ(VLV_GU_CTL1);
+	s->clock_gate_dis2	= I915_READ(VLV_GUNIT_CLOCK_GATE2);
+
+	/*
+	 * Not saving any of:
+	 * DFT,		0x9800-0x9EC0
+	 * SARB,	0xB000-0xB1FC
+	 * GAC,		0x5208-0x524C, 0x14000-0x14C000
+	 * PCI CFG
+	 */
+}
+
+static void vlv_restore_gunit_s0ix_state(struct drm_i915_private *dev_priv)
+{
+	struct vlv_s0ix_state *s = &dev_priv->vlv_s0ix_state;
+	u32 val;
+	int i;
+
+	/* GAM 0x4000-0x4770 */
+	I915_WRITE(GEN7_WR_WATERMARK,	s->wr_watermark);
+	I915_WRITE(GEN7_GFX_PRIO_CTRL,	s->gfx_prio_ctrl);
+	I915_WRITE(ARB_MODE,		s->arb_mode | (0xffff << 16));
+	I915_WRITE(GEN7_GFX_PEND_TLB0,	s->gfx_pend_tlb0);
+	I915_WRITE(GEN7_GFX_PEND_TLB1,	s->gfx_pend_tlb1);
+
+	for (i = 0; i < ARRAY_SIZE(s->lra_limits); i++)
+		I915_WRITE(GEN7_LRA_LIMITS_BASE + i * 4, s->lra_limits[i]);
+
+	I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->media_max_req_count);
+	I915_WRITE(GEN7_MEDIA_MAX_REQ_COUNT, s->gfx_max_req_count);
+
+	I915_WRITE(RENDER_HWS_PGA_GEN7,	s->render_hwsp);
+	I915_WRITE(GAM_ECOCHK,		s->ecochk);
+	I915_WRITE(BSD_HWS_PGA_GEN7,	s->bsd_hwsp);
+	I915_WRITE(BLT_HWS_PGA_GEN7,	s->blt_hwsp);
+
+	I915_WRITE(GEN7_TLB_RD_ADDR,	s->tlb_rd_addr);
+
+	/* MBC 0x9024-0x91D0, 0x8500 */
+	I915_WRITE(VLV_G3DCTL,		s->g3dctl);
+	I915_WRITE(VLV_GSCKGCTL,	s->gsckgctl);
+	I915_WRITE(GEN6_MBCTL,		s->mbctl);
+
+	/* GCP 0x9400-0x9424, 0x8100-0x810C */
+	I915_WRITE(GEN6_UCGCTL1,	s->ucgctl1);
+	I915_WRITE(GEN6_UCGCTL3,	s->ucgctl3);
+	I915_WRITE(GEN6_RCGCTL1,	s->rcgctl1);
+	I915_WRITE(GEN6_RCGCTL2,	s->rcgctl2);
+	I915_WRITE(GEN6_RSTCTL,		s->rstctl);
+	I915_WRITE(GEN7_MISCCPCTL,	s->misccpctl);
+
+	/* GPM 0xA000-0xAA84, 0x8000-0x80FC */
+	I915_WRITE(GEN6_GFXPAUSE,	s->gfxpause);
+	I915_WRITE(GEN6_RPDEUHWTC,	s->rpdeuhwtc);
+	I915_WRITE(GEN6_RPDEUC,		s->rpdeuc);
+	I915_WRITE(ECOBUS,		s->ecobus);
+	I915_WRITE(VLV_PWRDWNUPCTL,	s->pwrdwnupctl);
+	I915_WRITE(GEN6_RP_DOWN_TIMEOUT,s->rp_down_timeout);
+	I915_WRITE(GEN6_RPDEUCSW,	s->rp_deucsw);
+	I915_WRITE(GEN6_RCUBMABDTMR,	s->rcubmabdtmr);
+	I915_WRITE(VLV_RCEDATA,		s->rcedata);
+	I915_WRITE(VLV_SPAREG2H,	s->spare2gh);
+
+	/* Display CZ domain, 0x4400C-0x4402C, 0x4F000-0x4F11F */
+	I915_WRITE(GTIMR,		s->gt_imr);
+	I915_WRITE(GTIER,		s->gt_ier);
+	I915_WRITE(GEN6_PMIMR,		s->pm_imr);
+	I915_WRITE(GEN6_PMIER,		s->pm_ier);
+
+	for (i = 0; i < ARRAY_SIZE(s->gt_scratch); i++)
+		I915_WRITE(GEN7_GT_SCRATCH_BASE + i * 4, s->gt_scratch[i]);
+
+	/* GT SA CZ domain, 0x100000-0x138124 */
+	I915_WRITE(TILECTL,			s->tilectl);
+	I915_WRITE(GTFIFOCTL,			s->gt_fifoctl);
+	/*
+	 * Preserve the GT allow wake and GFX force clock bit, they are not
+	 * be restored, as they are used to control the s0ix suspend/resume
+	 * sequence by the caller.
+	 */
+	val = I915_READ(VLV_GTLC_WAKE_CTRL);
+	val &= VLV_GTLC_ALLOWWAKEREQ;
+	val |= s->gtlc_wake_ctrl & ~VLV_GTLC_ALLOWWAKEREQ;
+	I915_WRITE(VLV_GTLC_WAKE_CTRL, val);
+
+	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
+	val &= VLV_GFX_CLK_FORCE_ON_BIT;
+	val |= s->gtlc_survive & ~VLV_GFX_CLK_FORCE_ON_BIT;
+	I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, val);
+
+	I915_WRITE(VLV_PMWGICZ,			s->pmwgicz);
+
+	/* Gunit-Display CZ domain, 0x182028-0x1821CF */
+	I915_WRITE(VLV_GU_CTL0,			s->gu_ctl0);
+	I915_WRITE(VLV_GU_CTL1,			s->gu_ctl1);
+	I915_WRITE(VLV_GUNIT_CLOCK_GATE2,	s->clock_gate_dis2);
+}
+
+int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool force_on)
+{
+	u32 val;
+	int err;
+
+	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
+	WARN_ON(!!(val & VLV_GFX_CLK_FORCE_ON_BIT) == force_on);
+
+#define COND (I915_READ(VLV_GTLC_SURVIVABILITY_REG) & VLV_GFX_CLK_STATUS_BIT)
+	/* Wait for a previous force-off to settle */
+	if (force_on) {
+		err = wait_for(!COND, 20);
+		if (err) {
+			DRM_ERROR("timeout waiting for GFX clock force-off (%08x)\n",
+				  I915_READ(VLV_GTLC_SURVIVABILITY_REG));
+			return err;
+		}
+	}
+
+	val = I915_READ(VLV_GTLC_SURVIVABILITY_REG);
+	val &= ~VLV_GFX_CLK_FORCE_ON_BIT;
+	if (force_on)
+		val |= VLV_GFX_CLK_FORCE_ON_BIT;
+	I915_WRITE(VLV_GTLC_SURVIVABILITY_REG, val);
+
+	if (!force_on)
+		return 0;
+
+	err = wait_for(COND, 20);
+	if (err)
+		DRM_ERROR("timeout waiting for GFX clock force-on (%08x)\n",
+			  I915_READ(VLV_GTLC_SURVIVABILITY_REG));
+
+	return err;
+#undef COND
+}
+
+static int vlv_allow_gt_wake(struct drm_i915_private *dev_priv, bool allow)
+{
+	u32 val;
+	int err = 0;
+
+	val = I915_READ(VLV_GTLC_WAKE_CTRL);
+	val &= ~VLV_GTLC_ALLOWWAKEREQ;
+	if (allow)
+		val |= VLV_GTLC_ALLOWWAKEREQ;
+	I915_WRITE(VLV_GTLC_WAKE_CTRL, val);
+	POSTING_READ(VLV_GTLC_WAKE_CTRL);
+
+#define COND (!!(I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_ALLOWWAKEACK) == \
+	      allow)
+	err = wait_for(COND, 1);
+	if (err)
+		DRM_ERROR("timeout disabling GT waking\n");
+	return err;
+#undef COND
+}
+
+static int vlv_wait_for_gt_wells(struct drm_i915_private *dev_priv,
+				 bool wait_for_on)
+{
+	u32 mask;
+	u32 val;
+	int err;
+
+	mask = VLV_GTLC_PW_MEDIA_STATUS_MASK | VLV_GTLC_PW_RENDER_STATUS_MASK;
+	val = wait_for_on ? mask : 0;
+#define COND ((I915_READ(VLV_GTLC_PW_STATUS) & mask) == val)
+	if (COND)
+		return 0;
+
+	DRM_DEBUG_KMS("waiting for GT wells to go %s (%08x)\n",
+			wait_for_on ? "on" : "off",
+			I915_READ(VLV_GTLC_PW_STATUS));
+
+	/*
+	 * RC6 transitioning can be delayed up to 2 msec (see
+	 * valleyview_enable_rps), use 3 msec for safety.
+	 */
+	err = wait_for(COND, 3);
+	if (err)
+		DRM_ERROR("timeout waiting for GT wells to go %s\n",
+			  wait_for_on ? "on" : "off");
+
+	return err;
+#undef COND
+}
+
+static void vlv_check_no_gt_access(struct drm_i915_private *dev_priv)
+{
+	if (!(I915_READ(VLV_GTLC_PW_STATUS) & VLV_GTLC_ALLOWWAKEERR))
+		return;
+
+	DRM_ERROR("GT register access while GT waking disabled\n");
+	I915_WRITE(VLV_GTLC_PW_STATUS, VLV_GTLC_ALLOWWAKEERR);
+}
+
+static int vlv_runtime_suspend(struct drm_i915_private *dev_priv)
+{
+	u32 mask;
+	int err;
+
+	/*
+	 * Bspec defines the following GT well on flags as debug only, so
+	 * don't treat them as hard failures.
+	 */
+	(void)vlv_wait_for_gt_wells(dev_priv, false);
+
+	mask = VLV_GTLC_RENDER_CTX_EXISTS | VLV_GTLC_MEDIA_CTX_EXISTS;
+	WARN_ON((I915_READ(VLV_GTLC_WAKE_CTRL) & mask) != mask);
+
+	vlv_check_no_gt_access(dev_priv);
+
+	err = vlv_force_gfx_clock(dev_priv, true);
+	if (err)
+		goto err1;
+
+	err = vlv_allow_gt_wake(dev_priv, false);
+	if (err)
+		goto err2;
+	vlv_save_gunit_s0ix_state(dev_priv);
+
+	err = vlv_force_gfx_clock(dev_priv, false);
+	if (err)
+		goto err2;
+
+	return 0;
+
+err2:
+	/* For safety always re-enable waking and disable gfx clock forcing */
+	vlv_allow_gt_wake(dev_priv, true);
+err1:
+	vlv_force_gfx_clock(dev_priv, false);
+
+	return err;
+}
+
+static int vlv_runtime_resume(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	int err;
+	int ret;
+
+	/*
+	 * If any of the steps fail just try to continue, that's the best we
+	 * can do at this point. Return the first error code (which will also
+	 * leave RPM permanently disabled).
+	 */
+	ret = vlv_force_gfx_clock(dev_priv, true);
+
+	vlv_restore_gunit_s0ix_state(dev_priv);
+
+	err = vlv_allow_gt_wake(dev_priv, true);
+	if (!ret)
+		ret = err;
+
+	err = vlv_force_gfx_clock(dev_priv, false);
+	if (!ret)
+		ret = err;
+
+	vlv_check_no_gt_access(dev_priv);
+
+	intel_init_clock_gating(dev);
+	i915_gem_restore_fences(dev);
+
+	return ret;
+}
+
+static int intel_runtime_suspend(struct device *device)
 {
 	struct pci_dev *pdev = to_pci_dev(device);
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
+	if (WARN_ON_ONCE(!(dev_priv->rps.enabled && intel_enable_rc6(dev))))
+		return -ENODEV;
 
 	WARN_ON(!HAS_RUNTIME_PM(dev));
 	assert_force_wake_inactive(dev_priv);
 
 	DRM_DEBUG_KMS("Suspending device\n");
 
-	if (HAS_PC8(dev))
-		hsw_enable_pc8(dev_priv);
+	/*
+	 * We could deadlock here in case another thread holding struct_mutex
+	 * calls RPM suspend concurrently, since the RPM suspend will wait
+	 * first for this RPM suspend to finish. In this case the concurrent
+	 * RPM resume will be followed by its RPM suspend counterpart. Still
+	 * for consistency return -EAGAIN, which will reschedule this suspend.
+	 */
+	if (!mutex_trylock(&dev->struct_mutex)) {
+		DRM_DEBUG_KMS("device lock contention, deffering suspend\n");
+		/*
+		 * Bump the expiration timestamp, otherwise the suspend won't
+		 * be rescheduled.
+		 */
+		pm_runtime_mark_last_busy(device);
 
+		return -EAGAIN;
+	}
+	/*
+	 * We are safe here against re-faults, since the fault handler takes
+	 * an RPM reference.
+	 */
 	i915_gem_release_all_mmaps(dev_priv);
+	mutex_unlock(&dev->struct_mutex);
+
+	/*
+	 * rps.work can't be rearmed here, since we get here only after making
+	 * sure the GPU is idle and the RPS freq is set to the minimum. See
+	 * intel_mark_idle().
+	 */
+	cancel_work_sync(&dev_priv->rps.work);
+	intel_runtime_pm_disable_interrupts(dev);
+
+	if (IS_GEN6(dev)) {
+		ret = 0;
+	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
+		ret = hsw_runtime_suspend(dev_priv);
+	} else if (IS_VALLEYVIEW(dev)) {
+		ret = vlv_runtime_suspend(dev_priv);
+	} else {
+		ret = -ENODEV;
+		WARN_ON(1);
+	}
+
+	if (ret) {
+		DRM_ERROR("Runtime suspend failed, disabling it (%d)\n", ret);
+		intel_runtime_pm_restore_interrupts(dev);
+
+		return ret;
+	}
 
 	del_timer_sync(&dev_priv->gpu_error.hangcheck_timer);
 	dev_priv->pm.suspended = true;
@@ -923,11 +1423,12 @@ static int i915_runtime_suspend(struct device *device)
 	return 0;
 }
 
-static int i915_runtime_resume(struct device *device)
+static int intel_runtime_resume(struct device *device)
 {
 	struct pci_dev *pdev = to_pci_dev(device);
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
 
 	WARN_ON(!HAS_RUNTIME_PM(dev));
 
@@ -936,11 +1437,33 @@ static int i915_runtime_resume(struct device *device)
 	intel_opregion_notify_adapter(dev, PCI_D0);
 	dev_priv->pm.suspended = false;
 
-	if (HAS_PC8(dev))
-		hsw_disable_pc8(dev_priv);
+	if (IS_GEN6(dev)) {
+		ret = snb_runtime_resume(dev_priv);
+	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
+		ret = hsw_runtime_resume(dev_priv);
+	} else if (IS_VALLEYVIEW(dev)) {
+		ret = vlv_runtime_resume(dev_priv);
+	} else {
+		WARN_ON(1);
+		ret = -ENODEV;
+	}
 
-	DRM_DEBUG_KMS("Device resumed\n");
-	return 0;
+	/*
+	 * No point of rolling back things in case of an error, as the best
+	 * we can do is to hope that things will still work (and disable RPM).
+	 */
+	i915_gem_init_swizzling(dev);
+	gen6_update_ring_freq(dev);
+
+	intel_runtime_pm_restore_interrupts(dev);
+	intel_reset_gt_powersave(dev);
+
+	if (ret)
+		DRM_ERROR("Runtime resume failed, disabling it (%d)\n", ret);
+	else
+		DRM_DEBUG_KMS("Device resumed\n");
+
+	return ret;
 }
 
 static const struct dev_pm_ops i915_pm_ops = {
@@ -954,8 +1477,8 @@ static const struct dev_pm_ops i915_pm_ops = {
 	.poweroff = i915_pm_poweroff,
 	.restore_early = i915_pm_resume_early,
 	.restore = i915_pm_resume,
-	.runtime_suspend = i915_runtime_suspend,
-	.runtime_resume = i915_runtime_resume,
+	.runtime_suspend = intel_runtime_suspend,
+	.runtime_resume = intel_runtime_resume,
 };
 
 static const struct vm_operations_struct i915_gem_vm_ops = {
@@ -1062,6 +1585,7 @@ static int __init i915_init(void)
 		driver.get_vblank_timestamp = NULL;
 #ifndef CONFIG_DRM_I915_UMS
 		/* Silently fail loading to not upset userspace. */
+		DRM_DEBUG_DRIVER("KMS and UMS disabled.\n");
 		return 0;
 #endif
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 388c028e223..374f964323a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -35,11 +35,13 @@
 #include "i915_reg.h"
 #include "intel_bios.h"
 #include "intel_ringbuffer.h"
+#include "i915_gem_gtt.h"
 #include <linux/io-mapping.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 #include <drm/intel-gtt.h>
 #include <linux/backlight.h>
+#include <linux/hashtable.h>
 #include <linux/intel-iommu.h>
 #include <linux/kref.h>
 #include <linux/pm_qos.h>
@@ -91,7 +93,7 @@ enum port {
 };
 #define port_name(p) ((p) + 'A')
 
-#define I915_NUM_PHYS_VLV 1
+#define I915_NUM_PHYS_VLV 2
 
 enum dpio_channel {
 	DPIO_CH0,
@@ -162,6 +164,12 @@ enum hpd_pin {
 #define for_each_pipe(p) for ((p) = 0; (p) < INTEL_INFO(dev)->num_pipes; (p)++)
 #define for_each_sprite(p, s) for ((s) = 0; (s) < INTEL_INFO(dev)->num_sprites[(p)]; (s)++)
 
+#define for_each_crtc(dev, crtc) \
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
+
+#define for_each_intel_crtc(dev, intel_crtc) \
+	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head)
+
 #define for_each_encoder_on_crtc(dev, __crtc, intel_encoder) \
 	list_for_each_entry((intel_encoder), &(dev)->mode_config.encoder_list, base.head) \
 		if ((intel_encoder)->base.crtc == (__crtc))
@@ -171,6 +179,7 @@ enum hpd_pin {
 		if ((intel_connector)->base.encoder == (__encoder))
 
 struct drm_i915_private;
+struct i915_mmu_object;
 
 enum intel_dpll_id {
 	DPLL_ID_PRIVATE = -1, /* non-shared dpll in use */
@@ -312,7 +321,6 @@ struct drm_i915_error_state {
 	u32 gab_ctl;
 	u32 gfx_mode;
 	u32 extra_instdone[I915_NUM_INSTDONE_REG];
-	u32 pipestat[I915_MAX_PIPES];
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct intel_overlay_error_state *overlay;
 	struct intel_display_error_state *display;
@@ -346,7 +354,7 @@ struct drm_i915_error_state {
 		u64 bbaddr;
 		u64 acthd;
 		u32 fault_reg;
-		u32 faddr;
+		u64 faddr;
 		u32 rc_psmi; /* sleep state */
 		u32 semaphore_mboxes[I915_NUM_RINGS - 1];
 
@@ -385,6 +393,7 @@ struct drm_i915_error_state {
 		u32 tiling:2;
 		u32 dirty:1;
 		u32 purgeable:1;
+		u32 userptr:1;
 		s32 ring:4;
 		u32 cache_level:3;
 	} **active_bo, **pinned_bo;
@@ -449,10 +458,11 @@ struct drm_i915_display_funcs {
 	int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc,
 			  struct drm_framebuffer *fb,
 			  struct drm_i915_gem_object *obj,
+			  struct intel_engine_cs *ring,
 			  uint32_t flags);
-	int (*update_primary_plane)(struct drm_crtc *crtc,
-				    struct drm_framebuffer *fb,
-				    int x, int y);
+	void (*update_primary_plane)(struct drm_crtc *crtc,
+				     struct drm_framebuffer *fb,
+				     int x, int y);
 	void (*hpd_irq_setup)(struct drm_device *dev);
 	/* clock updates for mode set */
 	/* cursor updates */
@@ -545,6 +555,7 @@ struct intel_device_info {
 	int dpll_offsets[I915_MAX_PIPES];
 	int dpll_md_offsets[I915_MAX_PIPES];
 	int palette_offsets[I915_MAX_PIPES];
+	int cursor_offsets[I915_MAX_PIPES];
 };
 
 #undef DEFINE_FLAG
@@ -560,168 +571,6 @@ enum i915_cache_level {
 	I915_CACHE_WT, /* hsw:gt3e WriteThrough for scanouts */
 };
 
-typedef uint32_t gen6_gtt_pte_t;
-
-/**
- * A VMA represents a GEM BO that is bound into an address space. Therefore, a
- * VMA's presence cannot be guaranteed before binding, or after unbinding the
- * object into/from the address space.
- *
- * To make things as simple as possible (ie. no refcounting), a VMA's lifetime
- * will always be <= an objects lifetime. So object refcounting should cover us.
- */
-struct i915_vma {
-	struct drm_mm_node node;
-	struct drm_i915_gem_object *obj;
-	struct i915_address_space *vm;
-
-	/** This object's place on the active/inactive lists */
-	struct list_head mm_list;
-
-	struct list_head vma_link; /* Link in the object's VMA list */
-
-	/** This vma's place in the batchbuffer or on the eviction list */
-	struct list_head exec_list;
-
-	/**
-	 * Used for performing relocations during execbuffer insertion.
-	 */
-	struct hlist_node exec_node;
-	unsigned long exec_handle;
-	struct drm_i915_gem_exec_object2 *exec_entry;
-
-	/**
-	 * How many users have pinned this object in GTT space. The following
-	 * users can each hold at most one reference: pwrite/pread, pin_ioctl
-	 * (via user_pin_count), execbuffer (objects are not allowed multiple
-	 * times for the same batchbuffer), and the framebuffer code. When
-	 * switching/pageflipping, the framebuffer code has at most two buffers
-	 * pinned per crtc.
-	 *
-	 * In the worst case this is 1 + 1 + 1 + 2*2 = 7. That would fit into 3
-	 * bits with absolutely no headroom. So use 4 bits. */
-	unsigned int pin_count:4;
-#define DRM_I915_GEM_OBJECT_MAX_PIN_COUNT 0xf
-
-	/** Unmap an object from an address space. This usually consists of
-	 * setting the valid PTE entries to a reserved scratch page. */
-	void (*unbind_vma)(struct i915_vma *vma);
-	/* Map an object into an address space with the given cache flags. */
-#define GLOBAL_BIND (1<<0)
-	void (*bind_vma)(struct i915_vma *vma,
-			 enum i915_cache_level cache_level,
-			 u32 flags);
-};
-
-struct i915_address_space {
-	struct drm_mm mm;
-	struct drm_device *dev;
-	struct list_head global_link;
-	unsigned long start;		/* Start offset always 0 for dri2 */
-	size_t total;		/* size addr space maps (ex. 2GB for ggtt) */
-
-	struct {
-		dma_addr_t addr;
-		struct page *page;
-	} scratch;
-
-	/**
-	 * List of objects currently involved in rendering.
-	 *
-	 * Includes buffers having the contents of their GPU caches
-	 * flushed, not necessarily primitives.  last_rendering_seqno
-	 * represents when the rendering involved will be completed.
-	 *
-	 * A reference is held on the buffer while on this list.
-	 */
-	struct list_head active_list;
-
-	/**
-	 * LRU list of objects which are not in the ringbuffer and
-	 * are ready to unbind, but are still in the GTT.
-	 *
-	 * last_rendering_seqno is 0 while an object is in this list.
-	 *
-	 * A reference is not held on the buffer while on this list,
-	 * as merely being GTT-bound shouldn't prevent its being
-	 * freed, and we'll pull it off the list in the free path.
-	 */
-	struct list_head inactive_list;
-
-	/* FIXME: Need a more generic return type */
-	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
-				     enum i915_cache_level level,
-				     bool valid); /* Create a valid PTE */
-	void (*clear_range)(struct i915_address_space *vm,
-			    uint64_t start,
-			    uint64_t length,
-			    bool use_scratch);
-	void (*insert_entries)(struct i915_address_space *vm,
-			       struct sg_table *st,
-			       uint64_t start,
-			       enum i915_cache_level cache_level);
-	void (*cleanup)(struct i915_address_space *vm);
-};
-
-/* The Graphics Translation Table is the way in which GEN hardware translates a
- * Graphics Virtual Address into a Physical Address. In addition to the normal
- * collateral associated with any va->pa translations GEN hardware also has a
- * portion of the GTT which can be mapped by the CPU and remain both coherent
- * and correct (in cases like swizzling). That region is referred to as GMADR in
- * the spec.
- */
-struct i915_gtt {
-	struct i915_address_space base;
-	size_t stolen_size;		/* Total size of stolen memory */
-
-	unsigned long mappable_end;	/* End offset that we can CPU map */
-	struct io_mapping *mappable;	/* Mapping to our CPU mappable region */
-	phys_addr_t mappable_base;	/* PA of our GMADR */
-
-	/** "Graphics Stolen Memory" holds the global PTEs */
-	void __iomem *gsm;
-
-	bool do_idle_maps;
-
-	int mtrr;
-
-	/* global gtt ops */
-	int (*gtt_probe)(struct drm_device *dev, size_t *gtt_total,
-			  size_t *stolen, phys_addr_t *mappable_base,
-			  unsigned long *mappable_end);
-};
-#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT)
-
-#define GEN8_LEGACY_PDPS 4
-struct i915_hw_ppgtt {
-	struct i915_address_space base;
-	struct kref ref;
-	struct drm_mm_node node;
-	unsigned num_pd_entries;
-	unsigned num_pd_pages; /* gen8+ */
-	union {
-		struct page **pt_pages;
-		struct page **gen8_pt_pages[GEN8_LEGACY_PDPS];
-	};
-	struct page *pd_pages;
-	union {
-		uint32_t pd_offset;
-		dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS];
-	};
-	union {
-		dma_addr_t *pt_dma_addr;
-		dma_addr_t *gen8_pt_dma_addr[4];
-	};
-
-	struct i915_hw_context *ctx;
-
-	int (*enable)(struct i915_hw_ppgtt *ppgtt);
-	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
-			 struct intel_ring_buffer *ring,
-			 bool synchronous);
-	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
-};
-
 struct i915_ctx_hang_stats {
 	/* This context had batch pending when hang was declared */
 	unsigned batch_pending;
@@ -738,13 +587,13 @@ struct i915_ctx_hang_stats {
 
 /* This must match up with the value previously used for execbuf2.rsvd1. */
 #define DEFAULT_CONTEXT_ID 0
-struct i915_hw_context {
+struct intel_context {
 	struct kref ref;
 	int id;
 	bool is_initialized;
 	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
-	struct intel_ring_buffer *last_ring;
+	struct intel_engine_cs *last_ring;
 	struct drm_i915_gem_object *obj;
 	struct i915_ctx_hang_stats hang_stats;
 	struct i915_address_space *vm;
@@ -782,6 +631,10 @@ struct i915_fbc {
 	} no_fbc_reason;
 };
 
+struct i915_drrs {
+	struct intel_connector *connector;
+};
+
 struct i915_psr {
 	bool sink_support;
 	bool source_ok;
@@ -803,6 +656,7 @@ enum intel_sbi_destination {
 #define QUIRK_PIPEA_FORCE (1<<0)
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
 #define QUIRK_INVERT_BRIGHTNESS (1<<2)
+#define QUIRK_BACKLIGHT_PRESENT (1<<3)
 
 struct intel_fbdev;
 struct intel_fbc_work;
@@ -965,6 +819,67 @@ struct i915_suspend_saved_registers {
 	u32 savePCH_PORT_HOTPLUG;
 };
 
+struct vlv_s0ix_state {
+	/* GAM */
+	u32 wr_watermark;
+	u32 gfx_prio_ctrl;
+	u32 arb_mode;
+	u32 gfx_pend_tlb0;
+	u32 gfx_pend_tlb1;
+	u32 lra_limits[GEN7_LRA_LIMITS_REG_NUM];
+	u32 media_max_req_count;
+	u32 gfx_max_req_count;
+	u32 render_hwsp;
+	u32 ecochk;
+	u32 bsd_hwsp;
+	u32 blt_hwsp;
+	u32 tlb_rd_addr;
+
+	/* MBC */
+	u32 g3dctl;
+	u32 gsckgctl;
+	u32 mbctl;
+
+	/* GCP */
+	u32 ucgctl1;
+	u32 ucgctl3;
+	u32 rcgctl1;
+	u32 rcgctl2;
+	u32 rstctl;
+	u32 misccpctl;
+
+	/* GPM */
+	u32 gfxpause;
+	u32 rpdeuhwtc;
+	u32 rpdeuc;
+	u32 ecobus;
+	u32 pwrdwnupctl;
+	u32 rp_down_timeout;
+	u32 rp_deucsw;
+	u32 rcubmabdtmr;
+	u32 rcedata;
+	u32 spare2gh;
+
+	/* Display 1 CZ domain */
+	u32 gt_imr;
+	u32 gt_ier;
+	u32 pm_imr;
+	u32 pm_ier;
+	u32 gt_scratch[GEN7_GT_SCRATCH_REG_NUM];
+
+	/* GT SA CZ domain */
+	u32 tilectl;
+	u32 gt_fifoctl;
+	u32 gtlc_wake_ctrl;
+	u32 gtlc_survive;
+	u32 pmwgicz;
+
+	/* Display 2 CZ domain */
+	u32 gu_ctl0;
+	u32 gu_ctl1;
+	u32 clock_gate_dis2;
+};
+
 struct intel_gen6_power_mgmt {
 	/* work and pm_iir are protected by dev_priv->irq_lock */
 	struct work_struct work;
@@ -1063,6 +978,8 @@ struct i915_power_well {
 	bool always_on;
 	/* power well enable/disable usage count */
 	int count;
+	/* cached hw enabled state */
+	bool hw_enabled;
 	unsigned long domains;
 	unsigned long data;
 	const struct i915_power_well_ops *ops;
@@ -1074,6 +991,7 @@ struct i915_power_domains {
 	 * time are on. They are kept on until after the first modeset.
 	 */
 	bool init_power_on;
+	bool initializing;
 	int power_well_count;
 
 	struct mutex lock;
@@ -1132,7 +1050,8 @@ struct i915_gem_mm {
 	/** PPGTT used for aliasing the PPGTT with the GTT */
 	struct i915_hw_ppgtt *aliasing_ppgtt;
 
-	struct shrinker inactive_shrinker;
+	struct notifier_block oom_notifier;
+	struct shrinker shrinker;
 	bool shrinker_no_lock_stealing;
 
 	/** LRU list of objects with fence regs on them. */
@@ -1170,6 +1089,9 @@ struct i915_gem_mm {
 	 */
 	bool busy;
 
+	/* the indicator for dispatch video commands on two BSD rings */
+	int bsd_ring_dispatch_index;
+
 	/** Bit 6 swizzling required for X tiling */
 	uint32_t bit_6_swizzle_x;
 	/** Bit 6 swizzling required for Y tiling */
@@ -1245,8 +1167,12 @@ struct i915_gpu_error {
 	 */
 	wait_queue_head_t reset_queue;
 
-	/* For gpu hang simulation. */
-	unsigned int stop_rings;
+	/* Userspace knobs for gpu hang simulation;
+	 * combines both a ring mask, and extra flags
+	 */
+	u32 stop_rings;
+#define I915_STOP_RING_ALLOW_BAN       (1 << 31)
+#define I915_STOP_RING_ALLOW_WARN      (1 << 30)
 
 	/* For missed irq/seqno simulation. */
 	unsigned int test_irq_rings;
@@ -1266,6 +1192,12 @@ struct ddi_vbt_port_info {
 	uint8_t supports_dp:1;
 };
 
+enum drrs_support_type {
+	DRRS_NOT_SUPPORTED = 0,
+	STATIC_DRRS_SUPPORT = 1,
+	SEAMLESS_DRRS_SUPPORT = 2
+};
+
 struct intel_vbt_data {
 	struct drm_display_mode *lfp_lvds_vbt_mode; /* if any */
 	struct drm_display_mode *sdvo_lvds_vbt_mode; /* if any */
@@ -1278,9 +1210,12 @@ struct intel_vbt_data {
 	unsigned int lvds_use_ssc:1;
 	unsigned int display_clock_mode:1;
 	unsigned int fdi_rx_polarity_inverted:1;
+	unsigned int has_mipi:1;
 	int lvds_ssc_freq;
 	unsigned int bios_lvds_val; /* initial [PCH_]LVDS reg val in VBIOS */
 
+	enum drrs_support_type drrs_type;
+
 	/* eDP */
 	int edp_rate;
 	int edp_lanes;
@@ -1299,7 +1234,14 @@ struct intel_vbt_data {
 
 	/* MIPI DSI */
 	struct {
+		u16 port;
 		u16 panel_id;
+		struct mipi_config *config;
+		struct mipi_pps_data *pps;
+		u8 seq_version;
+		u32 size;
+		u8 *data;
+		u8 *sequence[MIPI_SEQ_MAX];
 	} dsi;
 
 	int crt_ddc_pin;
@@ -1351,23 +1293,13 @@ struct ilk_wm_values {
  * goes back to false exactly before we reenable the IRQs. We use this variable
  * to check if someone is trying to enable/disable IRQs while they're supposed
  * to be disabled. This shouldn't happen and we'll print some error messages in
- * case it happens, but if it actually happens we'll also update the variables
- * inside struct regsave so when we restore the IRQs they will contain the
- * latest expected values.
+ * case it happens.
  *
  * For more, read the Documentation/power/runtime_pm.txt.
  */
 struct i915_runtime_pm {
 	bool suspended;
 	bool irqs_disabled;
-
-	struct {
-		uint32_t deimr;
-		uint32_t sdeimr;
-		uint32_t gtimr;
-		uint32_t gtier;
-		uint32_t gen6_pmimr;
-	} regsave;
 };
 
 enum intel_pipe_crc_source {
@@ -1400,7 +1332,7 @@ struct intel_pipe_crc {
 	wait_queue_head_t wq;
 };
 
-typedef struct drm_i915_private {
+struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
 
@@ -1424,10 +1356,13 @@ typedef struct drm_i915_private {
 	 */
 	uint32_t gpio_mmio_base;
 
+	/* MMIO base address for MIPI regs */
+	uint32_t mipi_mmio_base;
+
 	wait_queue_head_t gmbus_wait_queue;
 
 	struct pci_dev *bridge_dev;
-	struct intel_ring_buffer ring[I915_NUM_RINGS];
+	struct intel_engine_cs ring[I915_NUM_RINGS];
 	uint32_t last_seqno, next_seqno;
 
 	drm_dma_handle_t *status_page_dmah;
@@ -1469,6 +1404,7 @@ typedef struct drm_i915_private {
 	struct timer_list hotplug_reenable_timer;
 
 	struct i915_fbc fbc;
+	struct i915_drrs drrs;
 	struct intel_opregion opregion;
 	struct intel_vbt_data vbt;
 
@@ -1486,6 +1422,7 @@ typedef struct drm_i915_private {
 	int num_fence_regs; /* 8 on pre-965, 16 otherwise */
 
 	unsigned int fsb_freq, mem_freq, is_ddr3;
+	unsigned int vlv_cdclk_freq;
 
 	/**
 	 * wq - Driver workqueue for GEM.
@@ -1509,9 +1446,12 @@ typedef struct drm_i915_private {
 	struct mutex modeset_restore_lock;
 
 	struct list_head vm_list; /* Global list of all address spaces */
-	struct i915_gtt gtt; /* VMA representing the global address space */
+	struct i915_gtt gtt; /* VM representing the global address space */
 
 	struct i915_gem_mm mm;
+#if defined(CONFIG_MMU_NOTIFIER)
+	DECLARE_HASHTABLE(mmu_notifiers, 7);
+#endif
 
 	/* Kernel Modesetting */
 
@@ -1580,6 +1520,7 @@ typedef struct drm_i915_private {
 
 	u32 suspend_count;
 	struct i915_suspend_saved_registers regfile;
+	struct vlv_s0ix_state vlv_s0ix_state;
 
 	struct {
 		/*
@@ -1605,7 +1546,12 @@ typedef struct drm_i915_private {
 	struct i915_dri1_state dri1;
 	/* Old ums support infrastructure, same warning applies. */
 	struct i915_ums_state ums;
-} drm_i915_private_t;
+
+	/*
+	 * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
+	 * will be rejected. Instead look for a better place.
+	 */
+};
 
 static inline struct drm_i915_private *to_i915(const struct drm_device *dev)
 {
@@ -1642,6 +1588,8 @@ struct drm_i915_gem_object_ops {
 	 */
 	int (*get_pages)(struct drm_i915_gem_object *);
 	void (*put_pages)(struct drm_i915_gem_object *);
+	int (*dmabuf_export)(struct drm_i915_gem_object *);
+	void (*release)(struct drm_i915_gem_object *);
 };
 
 struct drm_i915_gem_object {
@@ -1732,7 +1680,7 @@ struct drm_i915_gem_object {
 	void *dma_buf_vmapping;
 	int vmapping_count;
 
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 
 	/** Breadcrumb of last rendering to the buffer. */
 	uint32_t last_read_seqno;
@@ -1755,8 +1703,20 @@ struct drm_i915_gem_object {
 
 	/** for phy allocated objects */
 	drm_dma_handle_t *phys_handle;
-};
 
+	union {
+		struct i915_gem_userptr {
+			uintptr_t ptr;
+			unsigned read_only :1;
+			unsigned workers :4;
+#define I915_GEM_USERPTR_MAX_WORKERS 15
+
+			struct mm_struct *mm;
+			struct i915_mmu_object *mn;
+			struct work_struct *work;
+		} userptr;
+	};
+};
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
 /**
@@ -1771,7 +1731,7 @@ struct drm_i915_gem_object {
  */
 struct drm_i915_gem_request {
 	/** On Which ring this request was generated */
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 
 	/** GEM sequence number associated with this request. */
 	uint32_t seqno;
@@ -1783,7 +1743,7 @@ struct drm_i915_gem_request {
 	u32 tail;
 
 	/** Context related to this request */
-	struct i915_hw_context *ctx;
+	struct intel_context *ctx;
 
 	/** Batch buffer related to this request if any */
 	struct drm_i915_gem_object *batch_obj;
@@ -1810,8 +1770,8 @@ struct drm_i915_file_private {
 	} mm;
 	struct idr context_idr;
 
-	struct i915_hw_context *private_default_ctx;
 	atomic_t rps_wait_boost;
+	struct  intel_engine_cs *bsd_ring;
 };
 
 /*
@@ -1879,11 +1839,17 @@ struct drm_i915_cmd_descriptor {
 	 * the expected value, the parser rejects it. Only valid if flags has
 	 * the CMD_DESC_BITMASK bit set. Only entries where mask is non-zero
 	 * are valid.
+	 *
+	 * If the check specifies a non-zero condition_mask then the parser
+	 * only performs the check when the bits specified by condition_mask
+	 * are non-zero.
 	 */
 	struct {
 		u32 offset;
 		u32 mask;
 		u32 expected;
+		u32 condition_offset;
+		u32 condition_mask;
 	} bits[MAX_CMD_DESC_BITMASKS];
 };
 
@@ -1925,8 +1891,9 @@ struct drm_i915_cmd_table {
 				 (dev)->pdev->device == 0x0106 || \
 				 (dev)->pdev->device == 0x010A)
 #define IS_VALLEYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview)
+#define IS_CHERRYVIEW(dev)	(INTEL_INFO(dev)->is_valleyview && IS_GEN8(dev))
 #define IS_HASWELL(dev)	(INTEL_INFO(dev)->is_haswell)
-#define IS_BROADWELL(dev)	(INTEL_INFO(dev)->gen == 8)
+#define IS_BROADWELL(dev)	(!INTEL_INFO(dev)->is_valleyview && IS_GEN8(dev))
 #define IS_MOBILE(dev)		(INTEL_INFO(dev)->is_mobile)
 #define IS_HSW_EARLY_SDV(dev)	(IS_HASWELL(dev) && \
 				 ((dev)->pdev->device & 0xFF00) == 0x0C00)
@@ -1962,17 +1929,21 @@ struct drm_i915_cmd_table {
 #define BSD_RING		(1<<VCS)
 #define BLT_RING		(1<<BCS)
 #define VEBOX_RING		(1<<VECS)
-#define HAS_BSD(dev)            (INTEL_INFO(dev)->ring_mask & BSD_RING)
-#define HAS_BLT(dev)            (INTEL_INFO(dev)->ring_mask & BLT_RING)
-#define HAS_VEBOX(dev)            (INTEL_INFO(dev)->ring_mask & VEBOX_RING)
-#define HAS_LLC(dev)            (INTEL_INFO(dev)->has_llc)
-#define HAS_WT(dev)            (IS_HASWELL(dev) && to_i915(dev)->ellc_size)
+#define BSD2_RING		(1<<VCS2)
+#define HAS_BSD(dev)		(INTEL_INFO(dev)->ring_mask & BSD_RING)
+#define HAS_BSD2(dev)		(INTEL_INFO(dev)->ring_mask & BSD2_RING)
+#define HAS_BLT(dev)		(INTEL_INFO(dev)->ring_mask & BLT_RING)
+#define HAS_VEBOX(dev)		(INTEL_INFO(dev)->ring_mask & VEBOX_RING)
+#define HAS_LLC(dev)		(INTEL_INFO(dev)->has_llc)
+#define HAS_WT(dev)		((IS_HASWELL(dev) || IS_BROADWELL(dev)) && \
+				 to_i915(dev)->ellc_size)
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 
 #define HAS_HW_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 6)
-#define HAS_ALIASING_PPGTT(dev)	(INTEL_INFO(dev)->gen >= 6 && !IS_VALLEYVIEW(dev))
-#define HAS_PPGTT(dev)		(INTEL_INFO(dev)->gen >= 7 && !IS_VALLEYVIEW(dev) \
-				 && !IS_BROADWELL(dev))
+#define HAS_ALIASING_PPGTT(dev)	(INTEL_INFO(dev)->gen >= 6 && \
+				 (!IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)))
+#define HAS_PPGTT(dev)		(INTEL_INFO(dev)->gen >= 7 \
+				 && !IS_GEN8(dev))
 #define USES_PPGTT(dev)		intel_enable_ppgtt(dev, false)
 #define USES_FULL_PPGTT(dev)	intel_enable_ppgtt(dev, true)
 
@@ -2010,8 +1981,8 @@ struct drm_i915_cmd_table {
 #define HAS_DDI(dev)		(INTEL_INFO(dev)->has_ddi)
 #define HAS_FPGA_DBG_UNCLAIMED(dev)	(INTEL_INFO(dev)->has_fpga_dbg)
 #define HAS_PSR(dev)		(IS_HASWELL(dev) || IS_BROADWELL(dev))
-#define HAS_PC8(dev)		(IS_HASWELL(dev)) /* XXX HSW:ULX */
-#define HAS_RUNTIME_PM(dev)	(IS_HASWELL(dev))
+#define HAS_RUNTIME_PM(dev)	(IS_GEN6(dev) || IS_HASWELL(dev) || \
+				 IS_BROADWELL(dev) || IS_VALLEYVIEW(dev))
 
 #define INTEL_PCH_DEVICE_ID_MASK		0xff00
 #define INTEL_PCH_IBX_DEVICE_ID_TYPE		0x3b00
@@ -2068,6 +2039,7 @@ struct i915_params {
 	bool prefault_disable;
 	bool reset;
 	bool disable_display;
+	bool disable_vtd_wa;
 };
 extern struct i915_params i915 __read_mostly;
 
@@ -2096,6 +2068,7 @@ extern unsigned long i915_chipset_val(struct drm_i915_private *dev_priv);
 extern unsigned long i915_mch_val(struct drm_i915_private *dev_priv);
 extern unsigned long i915_gfx_val(struct drm_i915_private *dev_priv);
 extern void i915_update_gfx_val(struct drm_i915_private *dev_priv);
+int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
 
 extern void intel_console_resume(struct work_struct *work);
 
@@ -2170,6 +2143,9 @@ int i915_gem_set_tiling(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 int i915_gem_get_tiling(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
+int i915_gem_init_userptr(struct drm_device *dev);
+int i915_gem_userptr_ioctl(struct drm_device *dev, void *data,
+			   struct drm_file *file);
 int i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
 int i915_gem_wait_ioctl(struct drm_device *dev, void *data,
@@ -2227,9 +2203,9 @@ static inline void i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj)
 
 int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
 int i915_gem_object_sync(struct drm_i915_gem_object *obj,
-			 struct intel_ring_buffer *to);
+			 struct intel_engine_cs *to);
 void i915_vma_move_to_active(struct i915_vma *vma,
-			     struct intel_ring_buffer *ring);
+			     struct intel_engine_cs *ring);
 int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_device *dev,
 			 struct drm_mode_create_dumb *args);
@@ -2249,31 +2225,14 @@ int __must_check i915_gem_set_seqno(struct drm_device *dev, u32 seqno);
 int __must_check i915_gem_object_get_fence(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_object_put_fence(struct drm_i915_gem_object *obj);
 
-static inline bool
-i915_gem_object_pin_fence(struct drm_i915_gem_object *obj)
-{
-	if (obj->fence_reg != I915_FENCE_REG_NONE) {
-		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
-		dev_priv->fence_regs[obj->fence_reg].pin_count++;
-		return true;
-	} else
-		return false;
-}
-
-static inline void
-i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj)
-{
-	if (obj->fence_reg != I915_FENCE_REG_NONE) {
-		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
-		WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count <= 0);
-		dev_priv->fence_regs[obj->fence_reg].pin_count--;
-	}
-}
+bool i915_gem_object_pin_fence(struct drm_i915_gem_object *obj);
+void i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj);
 
 struct drm_i915_gem_request *
-i915_gem_find_active_request(struct intel_ring_buffer *ring);
+i915_gem_find_active_request(struct intel_engine_cs *ring);
 
 bool i915_gem_retire_requests(struct drm_device *dev);
+void i915_gem_retire_requests_ring(struct intel_engine_cs *ring);
 int __must_check i915_gem_check_wedge(struct i915_gpu_error *error,
 				      bool interruptible);
 static inline bool i915_reset_in_progress(struct i915_gpu_error *error)
@@ -2292,23 +2251,35 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 	return ((atomic_read(&error->reset_counter) & ~I915_WEDGED) + 1) / 2;
 }
 
+static inline bool i915_stop_ring_allow_ban(struct drm_i915_private *dev_priv)
+{
+	return dev_priv->gpu_error.stop_rings == 0 ||
+		dev_priv->gpu_error.stop_rings & I915_STOP_RING_ALLOW_BAN;
+}
+
+static inline bool i915_stop_ring_allow_warn(struct drm_i915_private *dev_priv)
+{
+	return dev_priv->gpu_error.stop_rings == 0 ||
+		dev_priv->gpu_error.stop_rings & I915_STOP_RING_ALLOW_WARN;
+}
+
 void i915_gem_reset(struct drm_device *dev);
 bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, bool force);
 int __must_check i915_gem_object_finish_gpu(struct drm_i915_gem_object *obj);
 int __must_check i915_gem_init(struct drm_device *dev);
 int __must_check i915_gem_init_hw(struct drm_device *dev);
-int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice);
+int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice);
 void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
 int __must_check i915_gem_suspend(struct drm_device *dev);
-int __i915_add_request(struct intel_ring_buffer *ring,
+int __i915_add_request(struct intel_engine_cs *ring,
 		       struct drm_file *file,
 		       struct drm_i915_gem_object *batch_obj,
 		       u32 *seqno);
 #define i915_add_request(ring, seqno) \
 	__i915_add_request(ring, NULL, NULL, seqno)
-int __must_check i915_wait_seqno(struct intel_ring_buffer *ring,
+int __must_check i915_wait_seqno(struct intel_engine_cs *ring,
 				 uint32_t seqno);
 int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 int __must_check
@@ -2319,7 +2290,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write);
 int __must_check
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
-				     struct intel_ring_buffer *pipelined);
+				     struct intel_engine_cs *pipelined);
 void i915_gem_object_unpin_from_display_plane(struct drm_i915_gem_object *obj);
 int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj,
 				int align);
@@ -2416,22 +2387,22 @@ void i915_gem_context_reset(struct drm_device *dev);
 int i915_gem_context_open(struct drm_device *dev, struct drm_file *file);
 int i915_gem_context_enable(struct drm_i915_private *dev_priv);
 void i915_gem_context_close(struct drm_device *dev, struct drm_file *file);
-int i915_switch_context(struct intel_ring_buffer *ring,
-			struct i915_hw_context *to);
-struct i915_hw_context *
+int i915_switch_context(struct intel_engine_cs *ring,
+			struct intel_context *to);
+struct intel_context *
 i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id);
 void i915_gem_context_free(struct kref *ctx_ref);
-static inline void i915_gem_context_reference(struct i915_hw_context *ctx)
+static inline void i915_gem_context_reference(struct intel_context *ctx)
 {
 	kref_get(&ctx->ref);
 }
 
-static inline void i915_gem_context_unreference(struct i915_hw_context *ctx)
+static inline void i915_gem_context_unreference(struct intel_context *ctx)
 {
 	kref_put(&ctx->ref, i915_gem_context_free);
 }
 
-static inline bool i915_gem_context_is_default(const struct i915_hw_context *c)
+static inline bool i915_gem_context_is_default(const struct intel_context *c)
 {
 	return c->id == DEFAULT_CONTEXT_ID;
 }
@@ -2441,6 +2412,8 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 				   struct drm_file *file);
 
+/* i915_gem_render_state.c */
+int i915_gem_render_state_init(struct intel_engine_cs *ring);
 /* i915_gem_evict.c */
 int __must_check i915_gem_evict_something(struct drm_device *dev,
 					  struct i915_address_space *vm,
@@ -2453,23 +2426,12 @@ int __must_check i915_gem_evict_something(struct drm_device *dev,
 int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle);
 int i915_gem_evict_everything(struct drm_device *dev);
 
-/* i915_gem_gtt.c */
-void i915_check_and_clear_faults(struct drm_device *dev);
-void i915_gem_suspend_gtt_mappings(struct drm_device *dev);
-void i915_gem_restore_gtt_mappings(struct drm_device *dev);
-int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj);
-void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj);
-void i915_gem_init_global_gtt(struct drm_device *dev);
-void i915_gem_setup_global_gtt(struct drm_device *dev, unsigned long start,
-			       unsigned long mappable_end, unsigned long end);
-int i915_gem_gtt_init(struct drm_device *dev);
+/* belongs in i915_gem_gtt.h */
 static inline void i915_gem_chipset_flush(struct drm_device *dev)
 {
 	if (INTEL_INFO(dev)->gen < 6)
 		intel_gtt_chipset_flush();
 }
-int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
-bool intel_enable_ppgtt(struct drm_device *dev, bool full);
 
 /* i915_gem_stolen.c */
 int i915_gem_init_stolen(struct drm_device *dev);
@@ -2537,9 +2499,11 @@ void i915_get_extra_instdone(struct drm_device *dev, uint32_t *instdone);
 const char *i915_cache_level_str(int type);
 
 /* i915_cmd_parser.c */
-void i915_cmd_parser_init_ring(struct intel_ring_buffer *ring);
-bool i915_needs_cmd_parser(struct intel_ring_buffer *ring);
-int i915_parse_cmds(struct intel_ring_buffer *ring,
+int i915_cmd_parser_get_version(void);
+int i915_cmd_parser_init_ring(struct intel_engine_cs *ring);
+void i915_cmd_parser_fini_ring(struct intel_engine_cs *ring);
+bool i915_needs_cmd_parser(struct intel_engine_cs *ring);
+int i915_parse_cmds(struct intel_engine_cs *ring,
 		    struct drm_i915_gem_object *batch_obj,
 		    u32 batch_start_offset,
 		    bool is_master);
@@ -2688,20 +2652,6 @@ void vlv_flisdsi_write(struct drm_i915_private *dev_priv, u32 reg, u32 val);
 int vlv_gpu_freq(struct drm_i915_private *dev_priv, int val);
 int vlv_freq_opcode(struct drm_i915_private *dev_priv, int val);
 
-void vlv_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine);
-void vlv_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine);
-
-#define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \
-	(((reg) >= 0x2000 && (reg) < 0x4000) ||\
-	((reg) >= 0x5000 && (reg) < 0x8000) ||\
-	((reg) >= 0xB000 && (reg) < 0x12000) ||\
-	((reg) >= 0x2E000 && (reg) < 0x30000))
-
-#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)\
-	(((reg) >= 0x12000 && (reg) < 0x14000) ||\
-	((reg) >= 0x22000 && (reg) < 0x24000) ||\
-	((reg) >= 0x30000 && (reg) < 0x40000))
-
 #define FORCEWAKE_RENDER	(1 << 0)
 #define FORCEWAKE_MEDIA		(1 << 1)
 #define FORCEWAKE_ALL		(FORCEWAKE_RENDER | FORCEWAKE_MEDIA)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 3326770c9ed..d893e4da5dc 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -31,6 +31,7 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
+#include <linux/oom.h>
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -43,6 +44,8 @@ static void i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *o
 static __must_check int
 i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
 			       bool readonly);
+static void
+i915_gem_object_retire(struct drm_i915_gem_object *obj);
 
 static void i915_gem_write_fence(struct drm_device *dev, int reg,
 				 struct drm_i915_gem_object *obj);
@@ -50,14 +53,15 @@ static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 					 struct drm_i915_fence_reg *fence,
 					 bool enable);
 
-static unsigned long i915_gem_inactive_count(struct shrinker *shrinker,
+static unsigned long i915_gem_shrinker_count(struct shrinker *shrinker,
 					     struct shrink_control *sc);
-static unsigned long i915_gem_inactive_scan(struct shrinker *shrinker,
+static unsigned long i915_gem_shrinker_scan(struct shrinker *shrinker,
 					    struct shrink_control *sc);
+static int i915_gem_shrinker_oom(struct notifier_block *nb,
+				 unsigned long event,
+				 void *ptr);
 static unsigned long i915_gem_purge(struct drm_i915_private *dev_priv, long target);
 static unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv);
-static void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
-static void i915_gem_retire_requests_ring(struct intel_ring_buffer *ring);
 
 static bool cpu_cache_is_coherent(struct drm_device *dev,
 				  enum i915_cache_level level)
@@ -470,6 +474,8 @@ int i915_gem_obj_prepare_shmem_read(struct drm_i915_gem_object *obj,
 		ret = i915_gem_object_wait_rendering(obj, true);
 		if (ret)
 			return ret;
+
+		i915_gem_object_retire(obj);
 	}
 
 	ret = i915_gem_object_get_pages(obj);
@@ -885,6 +891,8 @@ i915_gem_shmem_pwrite(struct drm_device *dev,
 		ret = i915_gem_object_wait_rendering(obj, false);
 		if (ret)
 			return ret;
+
+		i915_gem_object_retire(obj);
 	}
 	/* Same trick applies to invalidate partially written cachelines read
 	 * before writing. */
@@ -1088,7 +1096,7 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
  * equal.
  */
 static int
-i915_gem_check_olr(struct intel_ring_buffer *ring, u32 seqno)
+i915_gem_check_olr(struct intel_engine_cs *ring, u32 seqno)
 {
 	int ret;
 
@@ -1107,7 +1115,7 @@ static void fake_irq(unsigned long data)
 }
 
 static bool missed_irq(struct drm_i915_private *dev_priv,
-		       struct intel_ring_buffer *ring)
+		       struct intel_engine_cs *ring)
 {
 	return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings);
 }
@@ -1138,7 +1146,7 @@ static bool can_wait_boost(struct drm_i915_file_private *file_priv)
  * Returns 0 if the seqno was found within the alloted time. Else returns the
  * errno with remaining time filled in timeout argument.
  */
-static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
+static int __wait_seqno(struct intel_engine_cs *ring, u32 seqno,
 			unsigned reset_counter,
 			bool interruptible,
 			struct timespec *timeout,
@@ -1245,7 +1253,7 @@ static int __wait_seqno(struct intel_ring_buffer *ring, u32 seqno,
  * request and object lists appropriately for that event.
  */
 int
-i915_wait_seqno(struct intel_ring_buffer *ring, uint32_t seqno)
+i915_wait_seqno(struct intel_engine_cs *ring, uint32_t seqno)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1270,9 +1278,10 @@ i915_wait_seqno(struct intel_ring_buffer *ring, uint32_t seqno)
 
 static int
 i915_gem_object_wait_rendering__tail(struct drm_i915_gem_object *obj,
-				     struct intel_ring_buffer *ring)
+				     struct intel_engine_cs *ring)
 {
-	i915_gem_retire_requests_ring(ring);
+	if (!obj->active)
+		return 0;
 
 	/* Manually manage the write flush as we may have not yet
 	 * retired the buffer.
@@ -1282,7 +1291,6 @@ i915_gem_object_wait_rendering__tail(struct drm_i915_gem_object *obj,
 	 * we know we have passed the last write.
 	 */
 	obj->last_write_seqno = 0;
-	obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
 
 	return 0;
 }
@@ -1295,7 +1303,7 @@ static __must_check int
 i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
 			       bool readonly)
 {
-	struct intel_ring_buffer *ring = obj->ring;
+	struct intel_engine_cs *ring = obj->ring;
 	u32 seqno;
 	int ret;
 
@@ -1320,7 +1328,7 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = obj->ring;
+	struct intel_engine_cs *ring = obj->ring;
 	unsigned reset_counter;
 	u32 seqno;
 	int ret;
@@ -1536,7 +1544,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	/* Access to snoopable pages through the GTT is incoherent. */
 	if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(dev)) {
-		ret = -EINVAL;
+		ret = -EFAULT;
 		goto unlock;
 	}
 
@@ -1608,22 +1616,6 @@ out:
 	return ret;
 }
 
-void i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv)
-{
-	struct i915_vma *vma;
-
-	/*
-	 * Only the global gtt is relevant for gtt memory mappings, so restrict
-	 * list traversal to objects bound into the global address space. Note
-	 * that the active list should be empty, but better safe than sorry.
-	 */
-	WARN_ON(!list_empty(&dev_priv->gtt.base.active_list));
-	list_for_each_entry(vma, &dev_priv->gtt.base.active_list, mm_list)
-		i915_gem_release_mmap(vma->obj);
-	list_for_each_entry(vma, &dev_priv->gtt.base.inactive_list, mm_list)
-		i915_gem_release_mmap(vma->obj);
-}
-
 /**
  * i915_gem_release_mmap - remove physical page mappings
  * @obj: obj in question
@@ -1649,6 +1641,15 @@ i915_gem_release_mmap(struct drm_i915_gem_object *obj)
 	obj->fault_mappable = false;
 }
 
+void
+i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv)
+{
+	struct drm_i915_gem_object *obj;
+
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
+		i915_gem_release_mmap(obj);
+}
+
 uint32_t
 i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode)
 {
@@ -1803,12 +1804,16 @@ i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
 	return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset);
 }
 
+static inline int
+i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj)
+{
+	return obj->madv == I915_MADV_DONTNEED;
+}
+
 /* Immediately discard the backing storage */
 static void
 i915_gem_object_truncate(struct drm_i915_gem_object *obj)
 {
-	struct inode *inode;
-
 	i915_gem_object_free_mmap_offset(obj);
 
 	if (obj->base.filp == NULL)
@@ -1819,16 +1824,28 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj)
 	 * To do this we must instruct the shmfs to drop all of its
 	 * backing pages, *now*.
 	 */
-	inode = file_inode(obj->base.filp);
-	shmem_truncate_range(inode, 0, (loff_t)-1);
-
+	shmem_truncate_range(file_inode(obj->base.filp), 0, (loff_t)-1);
 	obj->madv = __I915_MADV_PURGED;
 }
 
-static inline int
-i915_gem_object_is_purgeable(struct drm_i915_gem_object *obj)
+/* Try to discard unwanted pages */
+static void
+i915_gem_object_invalidate(struct drm_i915_gem_object *obj)
 {
-	return obj->madv == I915_MADV_DONTNEED;
+	struct address_space *mapping;
+
+	switch (obj->madv) {
+	case I915_MADV_DONTNEED:
+		i915_gem_object_truncate(obj);
+	case __I915_MADV_PURGED:
+		return;
+	}
+
+	if (obj->base.filp == NULL)
+		return;
+
+	mapping = file_inode(obj->base.filp)->i_mapping,
+	invalidate_mapping_pages(mapping, 0, (loff_t)-1);
 }
 
 static void
@@ -1893,8 +1910,7 @@ i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 	ops->put_pages(obj);
 	obj->pages = NULL;
 
-	if (i915_gem_object_is_purgeable(obj))
-		i915_gem_object_truncate(obj);
+	i915_gem_object_invalidate(obj);
 
 	return 0;
 }
@@ -1903,58 +1919,58 @@ static unsigned long
 __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 		  bool purgeable_only)
 {
-	struct list_head still_bound_list;
-	struct drm_i915_gem_object *obj, *next;
+	struct list_head still_in_list;
+	struct drm_i915_gem_object *obj;
 	unsigned long count = 0;
 
-	list_for_each_entry_safe(obj, next,
-				 &dev_priv->mm.unbound_list,
-				 global_list) {
-		if ((i915_gem_object_is_purgeable(obj) || !purgeable_only) &&
-		    i915_gem_object_put_pages(obj) == 0) {
-			count += obj->base.size >> PAGE_SHIFT;
-			if (count >= target)
-				return count;
-		}
-	}
-
 	/*
-	 * As we may completely rewrite the bound list whilst unbinding
+	 * As we may completely rewrite the (un)bound list whilst unbinding
 	 * (due to retiring requests) we have to strictly process only
 	 * one element of the list at the time, and recheck the list
 	 * on every iteration.
+	 *
+	 * In particular, we must hold a reference whilst removing the
+	 * object as we may end up waiting for and/or retiring the objects.
+	 * This might release the final reference (held by the active list)
+	 * and result in the object being freed from under us. This is
+	 * similar to the precautions the eviction code must take whilst
+	 * removing objects.
+	 *
+	 * Also note that although these lists do not hold a reference to
+	 * the object we can safely grab one here: The final object
+	 * unreferencing and the bound_list are both protected by the
+	 * dev->struct_mutex and so we won't ever be able to observe an
+	 * object on the bound_list with a reference count equals 0.
 	 */
-	INIT_LIST_HEAD(&still_bound_list);
+	INIT_LIST_HEAD(&still_in_list);
+	while (count < target && !list_empty(&dev_priv->mm.unbound_list)) {
+		obj = list_first_entry(&dev_priv->mm.unbound_list,
+				       typeof(*obj), global_list);
+		list_move_tail(&obj->global_list, &still_in_list);
+
+		if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
+			continue;
+
+		drm_gem_object_reference(&obj->base);
+
+		if (i915_gem_object_put_pages(obj) == 0)
+			count += obj->base.size >> PAGE_SHIFT;
+
+		drm_gem_object_unreference(&obj->base);
+	}
+	list_splice(&still_in_list, &dev_priv->mm.unbound_list);
+
+	INIT_LIST_HEAD(&still_in_list);
 	while (count < target && !list_empty(&dev_priv->mm.bound_list)) {
 		struct i915_vma *vma, *v;
 
 		obj = list_first_entry(&dev_priv->mm.bound_list,
 				       typeof(*obj), global_list);
-		list_move_tail(&obj->global_list, &still_bound_list);
+		list_move_tail(&obj->global_list, &still_in_list);
 
 		if (!i915_gem_object_is_purgeable(obj) && purgeable_only)
 			continue;
 
-		/*
-		 * Hold a reference whilst we unbind this object, as we may
-		 * end up waiting for and retiring requests. This might
-		 * release the final reference (held by the active list)
-		 * and result in the object being freed from under us.
-		 * in this object being freed.
-		 *
-		 * Note 1: Shrinking the bound list is special since only active
-		 * (and hence bound objects) can contain such limbo objects, so
-		 * we don't need special tricks for shrinking the unbound list.
-		 * The only other place where we have to be careful with active
-		 * objects suddenly disappearing due to retiring requests is the
-		 * eviction code.
-		 *
-		 * Note 2: Even though the bound list doesn't hold a reference
-		 * to the object we can safely grab one here: The final object
-		 * unreferencing and the bound_list are both protected by the
-		 * dev->struct_mutex and so we won't ever be able to observe an
-		 * object on the bound_list with a reference count equals 0.
-		 */
 		drm_gem_object_reference(&obj->base);
 
 		list_for_each_entry_safe(vma, v, &obj->vma_list, vma_link)
@@ -1966,7 +1982,7 @@ __i915_gem_shrink(struct drm_i915_private *dev_priv, long target,
 
 		drm_gem_object_unreference(&obj->base);
 	}
-	list_splice(&still_bound_list, &dev_priv->mm.bound_list);
+	list_splice(&still_in_list, &dev_priv->mm.bound_list);
 
 	return count;
 }
@@ -1980,17 +1996,8 @@ i915_gem_purge(struct drm_i915_private *dev_priv, long target)
 static unsigned long
 i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_gem_object *obj, *next;
-	long freed = 0;
-
 	i915_gem_evict_everything(dev_priv->dev);
-
-	list_for_each_entry_safe(obj, next, &dev_priv->mm.unbound_list,
-				 global_list) {
-		if (i915_gem_object_put_pages(obj) == 0)
-			freed += obj->base.size >> PAGE_SHIFT;
-	}
-	return freed;
+	return __i915_gem_shrink(dev_priv, LONG_MAX, false);
 }
 
 static int
@@ -2094,7 +2101,19 @@ err_pages:
 		page_cache_release(sg_page_iter_page(&sg_iter));
 	sg_free_table(st);
 	kfree(st);
-	return PTR_ERR(page);
+
+	/* shmemfs first checks if there is enough memory to allocate the page
+	 * and reports ENOSPC should there be insufficient, along with the usual
+	 * ENOMEM for a genuine allocation failure.
+	 *
+	 * We use ENOSPC in our driver to mean that we have run out of aperture
+	 * space and so want to translate the error from shmemfs back to our
+	 * usual understanding of ENOMEM.
+	 */
+	if (PTR_ERR(page) == -ENOSPC)
+		return -ENOMEM;
+	else
+		return PTR_ERR(page);
 }
 
 /* Ensure that the associated pages are gathered from the backing storage
@@ -2131,7 +2150,7 @@ i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 
 static void
 i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
-			       struct intel_ring_buffer *ring)
+			       struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2169,7 +2188,7 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 }
 
 void i915_vma_move_to_active(struct i915_vma *vma,
-			     struct intel_ring_buffer *ring)
+			     struct intel_engine_cs *ring)
 {
 	list_move_tail(&vma->mm_list, &vma->vm->active_list);
 	return i915_gem_object_move_to_active(vma->obj, ring);
@@ -2207,11 +2226,24 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
 	WARN_ON(i915_verify_lists(dev));
 }
 
+static void
+i915_gem_object_retire(struct drm_i915_gem_object *obj)
+{
+	struct intel_engine_cs *ring = obj->ring;
+
+	if (ring == NULL)
+		return;
+
+	if (i915_seqno_passed(ring->get_seqno(ring, true),
+			      obj->last_read_seqno))
+		i915_gem_object_move_to_inactive(obj);
+}
+
 static int
 i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int ret, i, j;
 
 	/* Carefully retire all requests without writing to the rings */
@@ -2226,8 +2258,8 @@ i915_gem_init_seqno(struct drm_device *dev, u32 seqno)
 	for_each_ring(ring, dev_priv, i) {
 		intel_ring_init_seqno(ring, seqno);
 
-		for (j = 0; j < ARRAY_SIZE(ring->sync_seqno); j++)
-			ring->sync_seqno[j] = 0;
+		for (j = 0; j < ARRAY_SIZE(ring->semaphore.sync_seqno); j++)
+			ring->semaphore.sync_seqno[j] = 0;
 	}
 
 	return 0;
@@ -2277,7 +2309,7 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
 	return 0;
 }
 
-int __i915_add_request(struct intel_ring_buffer *ring,
+int __i915_add_request(struct intel_engine_cs *ring,
 		       struct drm_file *file,
 		       struct drm_i915_gem_object *obj,
 		       u32 *out_seqno)
@@ -2382,7 +2414,7 @@ i915_gem_request_remove_from_client(struct drm_i915_gem_request *request)
 }
 
 static bool i915_context_is_banned(struct drm_i915_private *dev_priv,
-				   const struct i915_hw_context *ctx)
+				   const struct intel_context *ctx)
 {
 	unsigned long elapsed;
 
@@ -2395,8 +2427,9 @@ static bool i915_context_is_banned(struct drm_i915_private *dev_priv,
 		if (!i915_gem_context_is_default(ctx)) {
 			DRM_DEBUG("context hanging too fast, banning!\n");
 			return true;
-		} else if (dev_priv->gpu_error.stop_rings == 0) {
-			DRM_ERROR("gpu hanging too fast, banning!\n");
+		} else if (i915_stop_ring_allow_ban(dev_priv)) {
+			if (i915_stop_ring_allow_warn(dev_priv))
+				DRM_ERROR("gpu hanging too fast, banning!\n");
 			return true;
 		}
 	}
@@ -2405,7 +2438,7 @@ static bool i915_context_is_banned(struct drm_i915_private *dev_priv,
 }
 
 static void i915_set_reset_status(struct drm_i915_private *dev_priv,
-				  struct i915_hw_context *ctx,
+				  struct intel_context *ctx,
 				  const bool guilty)
 {
 	struct i915_ctx_hang_stats *hs;
@@ -2436,7 +2469,7 @@ static void i915_gem_free_request(struct drm_i915_gem_request *request)
 }
 
 struct drm_i915_gem_request *
-i915_gem_find_active_request(struct intel_ring_buffer *ring)
+i915_gem_find_active_request(struct intel_engine_cs *ring)
 {
 	struct drm_i915_gem_request *request;
 	u32 completed_seqno;
@@ -2454,7 +2487,7 @@ i915_gem_find_active_request(struct intel_ring_buffer *ring)
 }
 
 static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv,
-				       struct intel_ring_buffer *ring)
+				       struct intel_engine_cs *ring)
 {
 	struct drm_i915_gem_request *request;
 	bool ring_hung;
@@ -2473,7 +2506,7 @@ static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv,
 }
 
 static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
-					struct intel_ring_buffer *ring)
+					struct intel_engine_cs *ring)
 {
 	while (!list_empty(&ring->active_list)) {
 		struct drm_i915_gem_object *obj;
@@ -2501,6 +2534,11 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv,
 
 		i915_gem_free_request(request);
 	}
+
+	/* These may not have been flush before the reset, do so now */
+	kfree(ring->preallocated_lazy_request);
+	ring->preallocated_lazy_request = NULL;
+	ring->outstanding_lazy_seqno = 0;
 }
 
 void i915_gem_restore_fences(struct drm_device *dev)
@@ -2527,7 +2565,7 @@ void i915_gem_restore_fences(struct drm_device *dev)
 void i915_gem_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int i;
 
 	/*
@@ -2541,8 +2579,6 @@ void i915_gem_reset(struct drm_device *dev)
 	for_each_ring(ring, dev_priv, i)
 		i915_gem_reset_ring_cleanup(dev_priv, ring);
 
-	i915_gem_cleanup_ringbuffer(dev);
-
 	i915_gem_context_reset(dev);
 
 	i915_gem_restore_fences(dev);
@@ -2551,8 +2587,8 @@ void i915_gem_reset(struct drm_device *dev)
 /**
  * This function clears the request list as sequence numbers are passed.
  */
-static void
-i915_gem_retire_requests_ring(struct intel_ring_buffer *ring)
+void
+i915_gem_retire_requests_ring(struct intel_engine_cs *ring)
 {
 	uint32_t seqno;
 
@@ -2597,7 +2633,7 @@ i915_gem_retire_requests_ring(struct intel_ring_buffer *ring)
 		 * of tail of the request to update the last known position
 		 * of the GPU head.
 		 */
-		ring->last_retired_head = request->tail;
+		ring->buffer->last_retired_head = request->tail;
 
 		i915_gem_free_request(request);
 	}
@@ -2615,7 +2651,7 @@ bool
 i915_gem_retire_requests(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	bool idle = true;
 	int i;
 
@@ -2709,7 +2745,7 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_wait *args = data;
 	struct drm_i915_gem_object *obj;
-	struct intel_ring_buffer *ring = NULL;
+	struct intel_engine_cs *ring = NULL;
 	struct timespec timeout_stack, *timeout = NULL;
 	unsigned reset_counter;
 	u32 seqno = 0;
@@ -2780,9 +2816,9 @@ out:
  */
 int
 i915_gem_object_sync(struct drm_i915_gem_object *obj,
-		     struct intel_ring_buffer *to)
+		     struct intel_engine_cs *to)
 {
-	struct intel_ring_buffer *from = obj->ring;
+	struct intel_engine_cs *from = obj->ring;
 	u32 seqno;
 	int ret, idx;
 
@@ -2795,7 +2831,7 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
 	idx = intel_ring_sync_index(from, to);
 
 	seqno = obj->last_read_seqno;
-	if (seqno <= from->sync_seqno[idx])
+	if (seqno <= from->semaphore.sync_seqno[idx])
 		return 0;
 
 	ret = i915_gem_check_olr(obj->ring, seqno);
@@ -2803,13 +2839,13 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
 		return ret;
 
 	trace_i915_gem_ring_sync_to(from, to, seqno);
-	ret = to->sync_to(to, from, seqno);
+	ret = to->semaphore.sync_to(to, from, seqno);
 	if (!ret)
 		/* We use last_read_seqno because sync_to()
 		 * might have just caused seqno wrap under
 		 * the radar.
 		 */
-		from->sync_seqno[idx] = obj->last_read_seqno;
+		from->semaphore.sync_seqno[idx] = obj->last_read_seqno;
 
 	return ret;
 }
@@ -2865,12 +2901,14 @@ int i915_vma_unbind(struct i915_vma *vma)
 	 * cause memory corruption through use-after-free.
 	 */
 
-	i915_gem_object_finish_gtt(obj);
+	if (i915_is_ggtt(vma->vm)) {
+		i915_gem_object_finish_gtt(obj);
 
-	/* release the fence reg _after_ flushing */
-	ret = i915_gem_object_put_fence(obj);
-	if (ret)
-		return ret;
+		/* release the fence reg _after_ flushing */
+		ret = i915_gem_object_put_fence(obj);
+		if (ret)
+			return ret;
+	}
 
 	trace_i915_vma_unbind(vma);
 
@@ -2903,7 +2941,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 int i915_gpu_idle(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int ret, i;
 
 	/* Flush everything onto the inactive list. */
@@ -3144,6 +3182,9 @@ i915_gem_object_put_fence(struct drm_i915_gem_object *obj)
 
 	fence = &dev_priv->fence_regs[obj->fence_reg];
 
+	if (WARN_ON(fence->pin_count))
+		return -EBUSY;
+
 	i915_gem_object_fence_lost(obj);
 	i915_gem_object_update_fence(obj, fence, false);
 
@@ -3548,6 +3589,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	if (ret)
 		return ret;
 
+	i915_gem_object_retire(obj);
 	i915_gem_object_flush_cpu_write_domain(obj, false);
 
 	/* Serialise direct access to this object with the barriers for
@@ -3646,6 +3688,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		 * in obj->write_domain and have been skipping the clflushes.
 		 * Just set it to the CPU cache for now.
 		 */
+		i915_gem_object_retire(obj);
 		WARN_ON(obj->base.write_domain & ~I915_GEM_DOMAIN_CPU);
 
 		old_read_domains = obj->base.read_domains;
@@ -3743,6 +3786,15 @@ unlock:
 
 static bool is_pin_display(struct drm_i915_gem_object *obj)
 {
+	struct i915_vma *vma;
+
+	if (list_empty(&obj->vma_list))
+		return false;
+
+	vma = i915_gem_obj_to_ggtt(obj);
+	if (!vma)
+		return false;
+
 	/* There are 3 sources that pin objects:
 	 *   1. The display engine (scanouts, sprites, cursors);
 	 *   2. Reservations for execbuffer;
@@ -3754,7 +3806,7 @@ static bool is_pin_display(struct drm_i915_gem_object *obj)
 	 * subtracting the potential reference by the user, any pin_count
 	 * remains, it must be due to another use by the display engine.
 	 */
-	return i915_gem_obj_to_ggtt(obj)->pin_count - !!obj->user_pin_count;
+	return vma->pin_count - !!obj->user_pin_count;
 }
 
 /*
@@ -3765,9 +3817,10 @@ static bool is_pin_display(struct drm_i915_gem_object *obj)
 int
 i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     u32 alignment,
-				     struct intel_ring_buffer *pipelined)
+				     struct intel_engine_cs *pipelined)
 {
 	u32 old_read_domains, old_write_domain;
+	bool was_pin_display;
 	int ret;
 
 	if (pipelined != obj->ring) {
@@ -3779,6 +3832,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	/* Mark the pin_display early so that we account for the
 	 * display coherency whilst setting up the cache domains.
 	 */
+	was_pin_display = obj->pin_display;
 	obj->pin_display = true;
 
 	/* The display engine is not coherent with the LLC cache on gen6.  As
@@ -3821,7 +3875,8 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	return 0;
 
 err_unpin_display:
-	obj->pin_display = is_pin_display(obj);
+	WARN_ON(was_pin_display != is_pin_display(obj));
+	obj->pin_display = was_pin_display;
 	return ret;
 }
 
@@ -3868,6 +3923,7 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 	if (ret)
 		return ret;
 
+	i915_gem_object_retire(obj);
 	i915_gem_object_flush_gtt_write_domain(obj);
 
 	old_write_domain = obj->base.write_domain;
@@ -3917,7 +3973,7 @@ i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file)
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	unsigned long recent_enough = jiffies - msecs_to_jiffies(20);
 	struct drm_i915_gem_request *request;
-	struct intel_ring_buffer *ring = NULL;
+	struct intel_engine_cs *ring = NULL;
 	unsigned reset_counter;
 	u32 seqno = 0;
 	int ret;
@@ -3976,9 +4032,13 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 		    uint32_t alignment,
 		    uint64_t flags)
 {
+	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
 	struct i915_vma *vma;
 	int ret;
 
+	if (WARN_ON(vm == &dev_priv->mm.aliasing_ppgtt->base))
+		return -ENODEV;
+
 	if (WARN_ON(flags & (PIN_GLOBAL | PIN_MAPPABLE) && !i915_is_ggtt(vm)))
 		return -EINVAL;
 
@@ -4032,6 +4092,32 @@ i915_gem_object_ggtt_unpin(struct drm_i915_gem_object *obj)
 		obj->pin_mappable = false;
 }
 
+bool
+i915_gem_object_pin_fence(struct drm_i915_gem_object *obj)
+{
+	if (obj->fence_reg != I915_FENCE_REG_NONE) {
+		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+		struct i915_vma *ggtt_vma = i915_gem_obj_to_ggtt(obj);
+
+		WARN_ON(!ggtt_vma ||
+			dev_priv->fence_regs[obj->fence_reg].pin_count >
+			ggtt_vma->pin_count);
+		dev_priv->fence_regs[obj->fence_reg].pin_count++;
+		return true;
+	} else
+		return false;
+}
+
+void
+i915_gem_object_unpin_fence(struct drm_i915_gem_object *obj)
+{
+	if (obj->fence_reg != I915_FENCE_REG_NONE) {
+		struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
+		WARN_ON(dev_priv->fence_regs[obj->fence_reg].pin_count <= 0);
+		dev_priv->fence_regs[obj->fence_reg].pin_count--;
+	}
+}
+
 int
 i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 		   struct drm_file *file)
@@ -4292,6 +4378,30 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 	return obj;
 }
 
+static bool discard_backing_storage(struct drm_i915_gem_object *obj)
+{
+	/* If we are the last user of the backing storage (be it shmemfs
+	 * pages or stolen etc), we know that the pages are going to be
+	 * immediately released. In this case, we can then skip copying
+	 * back the contents from the GPU.
+	 */
+
+	if (obj->madv != I915_MADV_WILLNEED)
+		return false;
+
+	if (obj->base.filp == NULL)
+		return true;
+
+	/* At first glance, this looks racy, but then again so would be
+	 * userspace racing mmap against close. However, the first external
+	 * reference to the filp can only be obtained through the
+	 * i915_gem_mmap_ioctl() which safeguards us against the user
+	 * acquiring such a reference whilst we are in the middle of
+	 * freeing the object.
+	 */
+	return atomic_long_read(&obj->base.filp->f_count) == 1;
+}
+
 void i915_gem_free_object(struct drm_gem_object *gem_obj)
 {
 	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
@@ -4329,6 +4439,8 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 
 	if (WARN_ON(obj->pages_pin_count))
 		obj->pages_pin_count = 0;
+	if (discard_backing_storage(obj))
+		obj->madv = I915_MADV_DONTNEED;
 	i915_gem_object_put_pages(obj);
 	i915_gem_object_free_mmap_offset(obj);
 	i915_gem_object_release_stolen(obj);
@@ -4338,6 +4450,9 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	if (obj->base.import_attach)
 		drm_prime_gem_destroy(&obj->base, NULL);
 
+	if (obj->ops->release)
+		obj->ops->release(obj);
+
 	drm_gem_object_release(&obj->base);
 	i915_gem_info_remove_obj(dev_priv, obj->base.size);
 
@@ -4371,6 +4486,17 @@ void i915_gem_vma_destroy(struct i915_vma *vma)
 	kfree(vma);
 }
 
+static void
+i915_gem_stop_ringbuffers(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring;
+	int i;
+
+	for_each_ring(ring, dev_priv, i)
+		intel_stop_ring_buffer(ring);
+}
+
 int
 i915_gem_suspend(struct drm_device *dev)
 {
@@ -4392,7 +4518,7 @@ i915_gem_suspend(struct drm_device *dev)
 		i915_gem_evict_everything(dev);
 
 	i915_kernel_lost_context(dev);
-	i915_gem_cleanup_ringbuffer(dev);
+	i915_gem_stop_ringbuffers(dev);
 
 	/* Hack!  Don't let anybody do execbuf while we don't control the chip.
 	 * We need to replace this with a semaphore, or something.
@@ -4413,7 +4539,7 @@ err:
 	return ret;
 }
 
-int i915_gem_l3_remap(struct intel_ring_buffer *ring, int slice)
+int i915_gem_l3_remap(struct intel_engine_cs *ring, int slice)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4512,13 +4638,20 @@ static int i915_gem_init_rings(struct drm_device *dev)
 			goto cleanup_blt_ring;
 	}
 
+	if (HAS_BSD2(dev)) {
+		ret = intel_init_bsd2_ring_buffer(dev);
+		if (ret)
+			goto cleanup_vebox_ring;
+	}
 
 	ret = i915_gem_set_seqno(dev, ((u32)~0 - 0x1000));
 	if (ret)
-		goto cleanup_vebox_ring;
+		goto cleanup_bsd2_ring;
 
 	return 0;
 
+cleanup_bsd2_ring:
+	intel_cleanup_ring_buffer(&dev_priv->ring[VCS2]);
 cleanup_vebox_ring:
 	intel_cleanup_ring_buffer(&dev_priv->ring[VECS]);
 cleanup_blt_ring:
@@ -4576,15 +4709,11 @@ i915_gem_init_hw(struct drm_device *dev)
 	 * the do_switch), but before enabling PPGTT. So don't move this.
 	 */
 	ret = i915_gem_context_enable(dev_priv);
-	if (ret) {
+	if (ret && ret != -EIO) {
 		DRM_ERROR("Context enable failed %d\n", ret);
-		goto err_out;
+		i915_gem_cleanup_ringbuffer(dev);
 	}
 
-	return 0;
-
-err_out:
-	i915_gem_cleanup_ringbuffer(dev);
 	return ret;
 }
 
@@ -4597,11 +4726,13 @@ int i915_gem_init(struct drm_device *dev)
 
 	if (IS_VALLEYVIEW(dev)) {
 		/* VLVA0 (potential hack), BIOS isn't actually waking us */
-		I915_WRITE(VLV_GTLC_WAKE_CTRL, 1);
-		if (wait_for((I915_READ(VLV_GTLC_PW_STATUS) & 1) == 1, 10))
+		I915_WRITE(VLV_GTLC_WAKE_CTRL, VLV_GTLC_ALLOWWAKEREQ);
+		if (wait_for((I915_READ(VLV_GTLC_PW_STATUS) &
+			      VLV_GTLC_ALLOWWAKEACK), 10))
 			DRM_DEBUG_DRIVER("allow wake ack timed out\n");
 	}
 
+	i915_gem_init_userptr(dev);
 	i915_gem_init_global_gtt(dev);
 
 	ret = i915_gem_context_init(dev);
@@ -4611,25 +4742,28 @@ int i915_gem_init(struct drm_device *dev)
 	}
 
 	ret = i915_gem_init_hw(dev);
-	mutex_unlock(&dev->struct_mutex);
-	if (ret) {
-		WARN_ON(dev_priv->mm.aliasing_ppgtt);
-		i915_gem_context_fini(dev);
-		drm_mm_takedown(&dev_priv->gtt.base.mm);
-		return ret;
+	if (ret == -EIO) {
+		/* Allow ring initialisation to fail by marking the GPU as
+		 * wedged. But we only want to do this where the GPU is angry,
+		 * for all other failure, such as an allocation failure, bail.
+		 */
+		DRM_ERROR("Failed to initialize GPU, declaring it wedged\n");
+		atomic_set_mask(I915_WEDGED, &dev_priv->gpu_error.reset_counter);
+		ret = 0;
 	}
+	mutex_unlock(&dev->struct_mutex);
 
 	/* Allow hardware batchbuffers unless told otherwise, but not for KMS. */
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		dev_priv->dri1.allow_batchbuffer = 1;
-	return 0;
+	return ret;
 }
 
 void
 i915_gem_cleanup_ringbuffer(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int i;
 
 	for_each_ring(ring, dev_priv, i)
@@ -4661,16 +4795,15 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
 	}
 
 	BUG_ON(!list_empty(&dev_priv->gtt.base.active_list));
-	mutex_unlock(&dev->struct_mutex);
 
-	ret = drm_irq_install(dev);
+	ret = drm_irq_install(dev, dev->pdev->irq);
 	if (ret)
 		goto cleanup_ringbuffer;
+	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
 
 cleanup_ringbuffer:
-	mutex_lock(&dev->struct_mutex);
 	i915_gem_cleanup_ringbuffer(dev);
 	dev_priv->ums.mm_suspended = 1;
 	mutex_unlock(&dev->struct_mutex);
@@ -4685,7 +4818,9 @@ i915_gem_leavevt_ioctl(struct drm_device *dev, void *data,
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		return 0;
 
+	mutex_lock(&dev->struct_mutex);
 	drm_irq_uninstall(dev);
+	mutex_unlock(&dev->struct_mutex);
 
 	return i915_gem_suspend(dev);
 }
@@ -4704,7 +4839,7 @@ i915_gem_lastclose(struct drm_device *dev)
 }
 
 static void
-init_ring_lists(struct intel_ring_buffer *ring)
+init_ring_lists(struct intel_engine_cs *ring)
 {
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
@@ -4752,7 +4887,7 @@ i915_gem_load(struct drm_device *dev)
 	init_waitqueue_head(&dev_priv->gpu_error.reset_queue);
 
 	/* On GEN3 we really need to make sure the ARB C3 LP bit is set */
-	if (IS_GEN3(dev)) {
+	if (!drm_core_check_feature(dev, DRIVER_MODESET) && IS_GEN3(dev)) {
 		I915_WRITE(MI_ARB_STATE,
 			   _MASKED_BIT_ENABLE(MI_ARB_C3_LP_WRITE_ENABLE));
 	}
@@ -4779,10 +4914,13 @@ i915_gem_load(struct drm_device *dev)
 
 	dev_priv->mm.interruptible = true;
 
-	dev_priv->mm.inactive_shrinker.scan_objects = i915_gem_inactive_scan;
-	dev_priv->mm.inactive_shrinker.count_objects = i915_gem_inactive_count;
-	dev_priv->mm.inactive_shrinker.seeks = DEFAULT_SEEKS;
-	register_shrinker(&dev_priv->mm.inactive_shrinker);
+	dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
+	dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count;
+	dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS;
+	register_shrinker(&dev_priv->mm.shrinker);
+
+	dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
+	register_oom_notifier(&dev_priv->mm.oom_notifier);
 }
 
 void i915_gem_release(struct drm_device *dev, struct drm_file *file)
@@ -4857,27 +4995,46 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 #endif
 }
 
+static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
+{
+	if (!mutex_trylock(&dev->struct_mutex)) {
+		if (!mutex_is_locked_by(&dev->struct_mutex, current))
+			return false;
+
+		if (to_i915(dev)->mm.shrinker_no_lock_stealing)
+			return false;
+
+		*unlock = false;
+	} else
+		*unlock = true;
+
+	return true;
+}
+
+static int num_vma_bound(struct drm_i915_gem_object *obj)
+{
+	struct i915_vma *vma;
+	int count = 0;
+
+	list_for_each_entry(vma, &obj->vma_list, vma_link)
+		if (drm_mm_node_allocated(&vma->node))
+			count++;
+
+	return count;
+}
+
 static unsigned long
-i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
+i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 {
 	struct drm_i915_private *dev_priv =
-		container_of(shrinker,
-			     struct drm_i915_private,
-			     mm.inactive_shrinker);
+		container_of(shrinker, struct drm_i915_private, mm.shrinker);
 	struct drm_device *dev = dev_priv->dev;
 	struct drm_i915_gem_object *obj;
-	bool unlock = true;
 	unsigned long count;
+	bool unlock;
 
-	if (!mutex_trylock(&dev->struct_mutex)) {
-		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return 0;
-
-		if (dev_priv->mm.shrinker_no_lock_stealing)
-			return 0;
-
-		unlock = false;
-	}
+	if (!i915_gem_shrinker_lock(dev, &unlock))
+		return 0;
 
 	count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
@@ -4885,10 +5042,8 @@ i915_gem_inactive_count(struct shrinker *shrinker, struct shrink_control *sc)
 			count += obj->base.size >> PAGE_SHIFT;
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (obj->active)
-			continue;
-
-		if (!i915_gem_obj_is_pinned(obj) && obj->pages_pin_count == 0)
+		if (!i915_gem_obj_is_pinned(obj) &&
+		    obj->pages_pin_count == num_vma_bound(obj))
 			count += obj->base.size >> PAGE_SHIFT;
 	}
 
@@ -4961,44 +5116,99 @@ unsigned long i915_gem_obj_size(struct drm_i915_gem_object *o,
 }
 
 static unsigned long
-i915_gem_inactive_scan(struct shrinker *shrinker, struct shrink_control *sc)
+i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 {
 	struct drm_i915_private *dev_priv =
-		container_of(shrinker,
-			     struct drm_i915_private,
-			     mm.inactive_shrinker);
+		container_of(shrinker, struct drm_i915_private, mm.shrinker);
 	struct drm_device *dev = dev_priv->dev;
 	unsigned long freed;
-	bool unlock = true;
-
-	if (!mutex_trylock(&dev->struct_mutex)) {
-		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return SHRINK_STOP;
+	bool unlock;
 
-		if (dev_priv->mm.shrinker_no_lock_stealing)
-			return SHRINK_STOP;
-
-		unlock = false;
-	}
+	if (!i915_gem_shrinker_lock(dev, &unlock))
+		return SHRINK_STOP;
 
 	freed = i915_gem_purge(dev_priv, sc->nr_to_scan);
 	if (freed < sc->nr_to_scan)
 		freed += __i915_gem_shrink(dev_priv,
 					   sc->nr_to_scan - freed,
 					   false);
-	if (freed < sc->nr_to_scan)
-		freed += i915_gem_shrink_all(dev_priv);
-
 	if (unlock)
 		mutex_unlock(&dev->struct_mutex);
 
 	return freed;
 }
 
+static int
+i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(nb, struct drm_i915_private, mm.oom_notifier);
+	struct drm_device *dev = dev_priv->dev;
+	struct drm_i915_gem_object *obj;
+	unsigned long timeout = msecs_to_jiffies(5000) + 1;
+	unsigned long pinned, bound, unbound, freed;
+	bool was_interruptible;
+	bool unlock;
+
+	while (!i915_gem_shrinker_lock(dev, &unlock) && --timeout)
+		schedule_timeout_killable(1);
+	if (timeout == 0) {
+		pr_err("Unable to purge GPU memory due lock contention.\n");
+		return NOTIFY_DONE;
+	}
+
+	was_interruptible = dev_priv->mm.interruptible;
+	dev_priv->mm.interruptible = false;
+
+	freed = i915_gem_shrink_all(dev_priv);
+
+	dev_priv->mm.interruptible = was_interruptible;
+
+	/* Because we may be allocating inside our own driver, we cannot
+	 * assert that there are no objects with pinned pages that are not
+	 * being pointed to by hardware.
+	 */
+	unbound = bound = pinned = 0;
+	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list) {
+		if (!obj->base.filp) /* not backed by a freeable object */
+			continue;
+
+		if (obj->pages_pin_count)
+			pinned += obj->base.size;
+		else
+			unbound += obj->base.size;
+	}
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		if (!obj->base.filp)
+			continue;
+
+		if (obj->pages_pin_count)
+			pinned += obj->base.size;
+		else
+			bound += obj->base.size;
+	}
+
+	if (unlock)
+		mutex_unlock(&dev->struct_mutex);
+
+	pr_info("Purging GPU memory, %lu bytes freed, %lu bytes still pinned.\n",
+		freed, pinned);
+	if (unbound || bound)
+		pr_err("%lu and %lu bytes still available in the "
+		       "bound and unbound GPU page lists.\n",
+		       bound, unbound);
+
+	*(unsigned long *)ptr += freed;
+	return NOTIFY_DONE;
+}
+
 struct i915_vma *i915_gem_obj_to_ggtt(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
 
+	/* This WARN has probably outlived its usefulness (callers already
+	 * WARN if they don't find the GGTT vma they expect). When removing,
+	 * remember to remove the pre-check in is_pin_display() as well */
 	if (WARN_ON(list_empty(&obj->vma_list)))
 		return NULL;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index d72db15afa0..a5ddf3bce9c 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -178,7 +178,7 @@ static int get_context_size(struct drm_device *dev)
 
 void i915_gem_context_free(struct kref *ctx_ref)
 {
-	struct i915_hw_context *ctx = container_of(ctx_ref,
+	struct intel_context *ctx = container_of(ctx_ref,
 						   typeof(*ctx), ref);
 	struct i915_hw_ppgtt *ppgtt = NULL;
 
@@ -199,7 +199,7 @@ void i915_gem_context_free(struct kref *ctx_ref)
 }
 
 static struct i915_hw_ppgtt *
-create_vm_for_ctx(struct drm_device *dev, struct i915_hw_context *ctx)
+create_vm_for_ctx(struct drm_device *dev, struct intel_context *ctx)
 {
 	struct i915_hw_ppgtt *ppgtt;
 	int ret;
@@ -218,12 +218,12 @@ create_vm_for_ctx(struct drm_device *dev, struct i915_hw_context *ctx)
 	return ppgtt;
 }
 
-static struct i915_hw_context *
+static struct intel_context *
 __create_hw_context(struct drm_device *dev,
 		  struct drm_i915_file_private *file_priv)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_hw_context *ctx;
+	struct intel_context *ctx;
 	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -240,7 +240,15 @@ __create_hw_context(struct drm_device *dev,
 			goto err_out;
 		}
 
-		if (INTEL_INFO(dev)->gen >= 7) {
+		/*
+		 * Try to make the context utilize L3 as well as LLC.
+		 *
+		 * On VLV we don't have L3 controls in the PTEs so we
+		 * shouldn't touch the cache level, especially as that
+		 * would make the object snooped which might have a
+		 * negative performance impact.
+		 */
+		if (INTEL_INFO(dev)->gen >= 7 && !IS_VALLEYVIEW(dev)) {
 			ret = i915_gem_object_set_cache_level(ctx->obj,
 							      I915_CACHE_L3_LLC);
 			/* Failure shouldn't ever happen this early */
@@ -277,14 +285,14 @@ err_out:
  * context state of the GPU for applications that don't utilize HW contexts, as
  * well as an idle case.
  */
-static struct i915_hw_context *
+static struct intel_context *
 i915_gem_create_context(struct drm_device *dev,
 			struct drm_i915_file_private *file_priv,
 			bool create_vm)
 {
 	const bool is_global_default_ctx = file_priv == NULL;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_hw_context *ctx;
+	struct intel_context *ctx;
 	int ret = 0;
 
 	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
@@ -356,8 +364,8 @@ void i915_gem_context_reset(struct drm_device *dev)
 	/* Prevent the hardware from restoring the last context (which hung) on
 	 * the next switch */
 	for (i = 0; i < I915_NUM_RINGS; i++) {
-		struct intel_ring_buffer *ring = &dev_priv->ring[i];
-		struct i915_hw_context *dctx = ring->default_context;
+		struct intel_engine_cs *ring = &dev_priv->ring[i];
+		struct intel_context *dctx = ring->default_context;
 
 		/* Do a fake switch to the default context */
 		if (ring->last_context == dctx)
@@ -383,7 +391,7 @@ void i915_gem_context_reset(struct drm_device *dev)
 int i915_gem_context_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_hw_context *ctx;
+	struct intel_context *ctx;
 	int i;
 
 	/* Init should only be called once per module load. Eventually the
@@ -418,7 +426,7 @@ int i915_gem_context_init(struct drm_device *dev)
 void i915_gem_context_fini(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct i915_hw_context *dctx = dev_priv->ring[RCS].default_context;
+	struct intel_context *dctx = dev_priv->ring[RCS].default_context;
 	int i;
 
 	if (dctx->obj) {
@@ -441,10 +449,12 @@ void i915_gem_context_fini(struct drm_device *dev)
 			i915_gem_context_unreference(dctx);
 			dev_priv->ring[RCS].last_context = NULL;
 		}
+
+		i915_gem_object_ggtt_unpin(dctx->obj);
 	}
 
 	for (i = 0; i < I915_NUM_RINGS; i++) {
-		struct intel_ring_buffer *ring = &dev_priv->ring[i];
+		struct intel_engine_cs *ring = &dev_priv->ring[i];
 
 		if (ring->last_context)
 			i915_gem_context_unreference(ring->last_context);
@@ -453,13 +463,12 @@ void i915_gem_context_fini(struct drm_device *dev)
 		ring->last_context = NULL;
 	}
 
-	i915_gem_object_ggtt_unpin(dctx->obj);
 	i915_gem_context_unreference(dctx);
 }
 
 int i915_gem_context_enable(struct drm_i915_private *dev_priv)
 {
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int ret, i;
 
 	/* This is the only place the aliasing PPGTT gets enabled, which means
@@ -486,11 +495,7 @@ int i915_gem_context_enable(struct drm_i915_private *dev_priv)
 
 static int context_idr_cleanup(int id, void *p, void *data)
 {
-	struct i915_hw_context *ctx = p;
-
-	/* Ignore the default context because close will handle it */
-	if (i915_gem_context_is_default(ctx))
-		return 0;
+	struct intel_context *ctx = p;
 
 	i915_gem_context_unreference(ctx);
 	return 0;
@@ -499,17 +504,17 @@ static int context_idr_cleanup(int id, void *p, void *data)
 int i915_gem_context_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
+	struct intel_context *ctx;
 
 	idr_init(&file_priv->context_idr);
 
 	mutex_lock(&dev->struct_mutex);
-	file_priv->private_default_ctx =
-		i915_gem_create_context(dev, file_priv, USES_FULL_PPGTT(dev));
+	ctx = i915_gem_create_context(dev, file_priv, USES_FULL_PPGTT(dev));
 	mutex_unlock(&dev->struct_mutex);
 
-	if (IS_ERR(file_priv->private_default_ctx)) {
+	if (IS_ERR(ctx)) {
 		idr_destroy(&file_priv->context_idr);
-		return PTR_ERR(file_priv->private_default_ctx);
+		return PTR_ERR(ctx);
 	}
 
 	return 0;
@@ -521,16 +526,14 @@ void i915_gem_context_close(struct drm_device *dev, struct drm_file *file)
 
 	idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL);
 	idr_destroy(&file_priv->context_idr);
-
-	i915_gem_context_unreference(file_priv->private_default_ctx);
 }
 
-struct i915_hw_context *
+struct intel_context *
 i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
 {
-	struct i915_hw_context *ctx;
+	struct intel_context *ctx;
 
-	ctx = (struct i915_hw_context *)idr_find(&file_priv->context_idr, id);
+	ctx = (struct intel_context *)idr_find(&file_priv->context_idr, id);
 	if (!ctx)
 		return ERR_PTR(-ENOENT);
 
@@ -538,8 +541,8 @@ i915_gem_context_get(struct drm_i915_file_private *file_priv, u32 id)
 }
 
 static inline int
-mi_set_context(struct intel_ring_buffer *ring,
-	       struct i915_hw_context *new_context,
+mi_set_context(struct intel_engine_cs *ring,
+	       struct intel_context *new_context,
 	       u32 hw_flags)
 {
 	int ret;
@@ -549,7 +552,7 @@ mi_set_context(struct intel_ring_buffer *ring,
 	 * explicitly, so we rely on the value at ring init, stored in
 	 * itlb_before_ctx_switch.
 	 */
-	if (IS_GEN6(ring->dev) && ring->itlb_before_ctx_switch) {
+	if (IS_GEN6(ring->dev)) {
 		ret = ring->flush(ring, I915_GEM_GPU_DOMAINS, 0);
 		if (ret)
 			return ret;
@@ -559,8 +562,8 @@ mi_set_context(struct intel_ring_buffer *ring,
 	if (ret)
 		return ret;
 
-	/* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw */
-	if (IS_GEN7(ring->dev))
+	/* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw,chv */
+	if (INTEL_INFO(ring->dev)->gen >= 7)
 		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_DISABLE);
 	else
 		intel_ring_emit(ring, MI_NOOP);
@@ -578,7 +581,7 @@ mi_set_context(struct intel_ring_buffer *ring,
 	 */
 	intel_ring_emit(ring, MI_NOOP);
 
-	if (IS_GEN7(ring->dev))
+	if (INTEL_INFO(ring->dev)->gen >= 7)
 		intel_ring_emit(ring, MI_ARB_ON_OFF | MI_ARB_ENABLE);
 	else
 		intel_ring_emit(ring, MI_NOOP);
@@ -588,13 +591,14 @@ mi_set_context(struct intel_ring_buffer *ring,
 	return ret;
 }
 
-static int do_switch(struct intel_ring_buffer *ring,
-		     struct i915_hw_context *to)
+static int do_switch(struct intel_engine_cs *ring,
+		     struct intel_context *to)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	struct i915_hw_context *from = ring->last_context;
+	struct intel_context *from = ring->last_context;
 	struct i915_hw_ppgtt *ppgtt = ctx_to_ppgtt(to);
 	u32 hw_flags = 0;
+	bool uninitialized = false;
 	int ret, i;
 
 	if (from != NULL && ring == &dev_priv->ring[RCS]) {
@@ -693,6 +697,7 @@ static int do_switch(struct intel_ring_buffer *ring,
 		i915_gem_context_unreference(from);
 	}
 
+	uninitialized = !to->is_initialized && from == NULL;
 	to->is_initialized = true;
 
 done:
@@ -700,6 +705,12 @@ done:
 	ring->last_context = to;
 	to->last_ring = ring;
 
+	if (uninitialized) {
+		ret = i915_gem_render_state_init(ring);
+		if (ret)
+			DRM_ERROR("init render state: %d\n", ret);
+	}
+
 	return 0;
 
 unpin_out:
@@ -718,8 +729,8 @@ unpin_out:
  * it will have a refoucnt > 1. This allows us to destroy the context abstract
  * object while letting the normal object tracking destroy the backing BO.
  */
-int i915_switch_context(struct intel_ring_buffer *ring,
-			struct i915_hw_context *to)
+int i915_switch_context(struct intel_engine_cs *ring,
+			struct intel_context *to)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 
@@ -748,7 +759,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_gem_context_create *args = data;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
-	struct i915_hw_context *ctx;
+	struct intel_context *ctx;
 	int ret;
 
 	if (!hw_context_enabled(dev))
@@ -774,7 +785,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_gem_context_destroy *args = data;
 	struct drm_i915_file_private *file_priv = file->driver_priv;
-	struct i915_hw_context *ctx;
+	struct intel_context *ctx;
 	int ret;
 
 	if (args->ctx_id == DEFAULT_CONTEXT_ID)
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 9bb533e0d76..580aa42443e 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -161,12 +161,8 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
 	struct drm_device *dev = obj->base.dev;
-	int ret;
-
-	ret = i915_mutex_lock_interruptible(dev);
-	if (ret)
-		return;
 
+	mutex_lock(&dev->struct_mutex);
 	if (--obj->vmapping_count == 0) {
 		vunmap(obj->dma_buf_vmapping);
 		obj->dma_buf_vmapping = NULL;
@@ -233,6 +229,14 @@ static const struct dma_buf_ops i915_dmabuf_ops =  {
 struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 				      struct drm_gem_object *gem_obj, int flags)
 {
+	struct drm_i915_gem_object *obj = to_intel_bo(gem_obj);
+
+	if (obj->ops->dmabuf_export) {
+		int ret = obj->ops->dmabuf_export(obj);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
 	return dma_buf_export(gem_obj, &i915_dmabuf_ops, gem_obj->size, flags);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 20fef6c5026..3a30133f93e 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -265,10 +265,12 @@ static inline int use_cpu_reloc(struct drm_i915_gem_object *obj)
 
 static int
 relocate_entry_cpu(struct drm_i915_gem_object *obj,
-		   struct drm_i915_gem_relocation_entry *reloc)
+		   struct drm_i915_gem_relocation_entry *reloc,
+		   uint64_t target_offset)
 {
 	struct drm_device *dev = obj->base.dev;
 	uint32_t page_offset = offset_in_page(reloc->offset);
+	uint64_t delta = reloc->delta + target_offset;
 	char *vaddr;
 	int ret;
 
@@ -278,7 +280,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 
 	vaddr = kmap_atomic(i915_gem_object_get_page(obj,
 				reloc->offset >> PAGE_SHIFT));
-	*(uint32_t *)(vaddr + page_offset) = reloc->delta;
+	*(uint32_t *)(vaddr + page_offset) = lower_32_bits(delta);
 
 	if (INTEL_INFO(dev)->gen >= 8) {
 		page_offset = offset_in_page(page_offset + sizeof(uint32_t));
@@ -289,7 +291,7 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 			    (reloc->offset + sizeof(uint32_t)) >> PAGE_SHIFT));
 		}
 
-		*(uint32_t *)(vaddr + page_offset) = 0;
+		*(uint32_t *)(vaddr + page_offset) = upper_32_bits(delta);
 	}
 
 	kunmap_atomic(vaddr);
@@ -299,10 +301,12 @@ relocate_entry_cpu(struct drm_i915_gem_object *obj,
 
 static int
 relocate_entry_gtt(struct drm_i915_gem_object *obj,
-		   struct drm_i915_gem_relocation_entry *reloc)
+		   struct drm_i915_gem_relocation_entry *reloc,
+		   uint64_t target_offset)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	uint64_t delta = reloc->delta + target_offset;
 	uint32_t __iomem *reloc_entry;
 	void __iomem *reloc_page;
 	int ret;
@@ -321,7 +325,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 			reloc->offset & PAGE_MASK);
 	reloc_entry = (uint32_t __iomem *)
 		(reloc_page + offset_in_page(reloc->offset));
-	iowrite32(reloc->delta, reloc_entry);
+	iowrite32(lower_32_bits(delta), reloc_entry);
 
 	if (INTEL_INFO(dev)->gen >= 8) {
 		reloc_entry += 1;
@@ -334,7 +338,7 @@ relocate_entry_gtt(struct drm_i915_gem_object *obj,
 			reloc_entry = reloc_page;
 		}
 
-		iowrite32(0, reloc_entry);
+		iowrite32(upper_32_bits(delta), reloc_entry);
 	}
 
 	io_mapping_unmap_atomic(reloc_page);
@@ -351,7 +355,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	struct drm_gem_object *target_obj;
 	struct drm_i915_gem_object *target_i915_obj;
 	struct i915_vma *target_vma;
-	uint32_t target_offset;
+	uint64_t target_offset;
 	int ret;
 
 	/* we've already hold a reference to all valid objects */
@@ -429,11 +433,10 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 	if (obj->active && in_atomic())
 		return -EFAULT;
 
-	reloc->delta += target_offset;
 	if (use_cpu_reloc(obj))
-		ret = relocate_entry_cpu(obj, reloc);
+		ret = relocate_entry_cpu(obj, reloc, target_offset);
 	else
-		ret = relocate_entry_gtt(obj, reloc);
+		ret = relocate_entry_gtt(obj, reloc, target_offset);
 
 	if (ret)
 		return ret;
@@ -541,7 +544,7 @@ need_reloc_mappable(struct i915_vma *vma)
 
 static int
 i915_gem_execbuffer_reserve_vma(struct i915_vma *vma,
-				struct intel_ring_buffer *ring,
+				struct intel_engine_cs *ring,
 				bool *need_reloc)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
@@ -628,7 +631,7 @@ eb_vma_misplaced(struct i915_vma *vma, bool has_fenced_gpu_access)
 }
 
 static int
-i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
+i915_gem_execbuffer_reserve(struct intel_engine_cs *ring,
 			    struct list_head *vmas,
 			    bool *need_relocs)
 {
@@ -642,6 +645,8 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 	if (list_empty(vmas))
 		return 0;
 
+	i915_gem_retire_requests_ring(ring);
+
 	vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm;
 
 	INIT_LIST_HEAD(&ordered_vmas);
@@ -727,7 +732,7 @@ static int
 i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 				  struct drm_i915_gem_execbuffer2 *args,
 				  struct drm_file *file,
-				  struct intel_ring_buffer *ring,
+				  struct intel_engine_cs *ring,
 				  struct eb_vmas *eb,
 				  struct drm_i915_gem_exec_object2 *exec)
 {
@@ -843,7 +848,7 @@ err:
 }
 
 static int
-i915_gem_execbuffer_move_to_gpu(struct intel_ring_buffer *ring,
+i915_gem_execbuffer_move_to_gpu(struct intel_engine_cs *ring,
 				struct list_head *vmas)
 {
 	struct i915_vma *vma;
@@ -926,11 +931,11 @@ validate_exec_list(struct drm_i915_gem_exec_object2 *exec,
 	return 0;
 }
 
-static struct i915_hw_context *
+static struct intel_context *
 i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
-			  struct intel_ring_buffer *ring, const u32 ctx_id)
+			  struct intel_engine_cs *ring, const u32 ctx_id)
 {
-	struct i915_hw_context *ctx = NULL;
+	struct intel_context *ctx = NULL;
 	struct i915_ctx_hang_stats *hs;
 
 	if (ring->id != RCS && ctx_id != DEFAULT_CONTEXT_ID)
@@ -951,7 +956,7 @@ i915_gem_validate_context(struct drm_device *dev, struct drm_file *file,
 
 static void
 i915_gem_execbuffer_move_to_active(struct list_head *vmas,
-				   struct intel_ring_buffer *ring)
+				   struct intel_engine_cs *ring)
 {
 	struct i915_vma *vma;
 
@@ -974,6 +979,9 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 			if (i915_gem_obj_ggtt_bound(obj) &&
 			    i915_gem_obj_to_ggtt(obj)->pin_count)
 				intel_mark_fb_busy(obj, ring);
+
+			/* update for the implicit flush after a batch */
+			obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
 		}
 
 		trace_i915_gem_object_change_domain(obj, old_read, old_write);
@@ -983,7 +991,7 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 static void
 i915_gem_execbuffer_retire_commands(struct drm_device *dev,
 				    struct drm_file *file,
-				    struct intel_ring_buffer *ring,
+				    struct intel_engine_cs *ring,
 				    struct drm_i915_gem_object *obj)
 {
 	/* Unconditionally force add_request to emit a full flush. */
@@ -995,13 +1003,15 @@ i915_gem_execbuffer_retire_commands(struct drm_device *dev,
 
 static int
 i915_reset_gen7_sol_offsets(struct drm_device *dev,
-			    struct intel_ring_buffer *ring)
+			    struct intel_engine_cs *ring)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret, i;
 
-	if (!IS_GEN7(dev) || ring != &dev_priv->ring[RCS])
-		return 0;
+	if (!IS_GEN7(dev) || ring != &dev_priv->ring[RCS]) {
+		DRM_DEBUG("sol reset is gen7/rcs only\n");
+		return -EINVAL;
+	}
 
 	ret = intel_ring_begin(ring, 4 * 3);
 	if (ret)
@@ -1018,6 +1028,37 @@ i915_reset_gen7_sol_offsets(struct drm_device *dev,
 	return 0;
 }
 
+/**
+ * Find one BSD ring to dispatch the corresponding BSD command.
+ * The Ring ID is returned.
+ */
+static int gen8_dispatch_bsd_ring(struct drm_device *dev,
+				  struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_file_private *file_priv = file->driver_priv;
+
+	/* Check whether the file_priv is using one ring */
+	if (file_priv->bsd_ring)
+		return file_priv->bsd_ring->id;
+	else {
+		/* If no, use the ping-pong mechanism to select one ring */
+		int ring_id;
+
+		mutex_lock(&dev->struct_mutex);
+		if (dev_priv->mm.bsd_ring_dispatch_index == 0) {
+			ring_id = VCS;
+			dev_priv->mm.bsd_ring_dispatch_index = 1;
+		} else {
+			ring_id = VCS2;
+			dev_priv->mm.bsd_ring_dispatch_index = 0;
+		}
+		file_priv->bsd_ring = &dev_priv->ring[ring_id];
+		mutex_unlock(&dev->struct_mutex);
+		return ring_id;
+	}
+}
+
 static struct drm_i915_gem_object *
 eb_get_batch(struct eb_vmas *eb)
 {
@@ -1047,11 +1088,11 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	struct eb_vmas *eb;
 	struct drm_i915_gem_object *batch_obj;
 	struct drm_clip_rect *cliprects = NULL;
-	struct intel_ring_buffer *ring;
-	struct i915_hw_context *ctx;
+	struct intel_engine_cs *ring;
+	struct intel_context *ctx;
 	struct i915_address_space *vm;
 	const u32 ctx_id = i915_execbuffer2_get_context_id(*args);
-	u32 exec_start = args->batch_start_offset, exec_len;
+	u64 exec_start = args->batch_start_offset, exec_len;
 	u32 mask, flags;
 	int ret, mode, i;
 	bool need_relocs;
@@ -1073,7 +1114,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		flags |= I915_DISPATCH_PINNED;
 
-	if ((args->flags & I915_EXEC_RING_MASK) > I915_NUM_RINGS) {
+	if ((args->flags & I915_EXEC_RING_MASK) > LAST_USER_RING) {
 		DRM_DEBUG("execbuf with unknown ring: %d\n",
 			  (int)(args->flags & I915_EXEC_RING_MASK));
 		return -EINVAL;
@@ -1081,7 +1122,14 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_DEFAULT)
 		ring = &dev_priv->ring[RCS];
-	else
+	else if ((args->flags & I915_EXEC_RING_MASK) == I915_EXEC_BSD) {
+		if (HAS_BSD2(dev)) {
+			int ring_id;
+			ring_id = gen8_dispatch_bsd_ring(dev, file);
+			ring = &dev_priv->ring[ring_id];
+		} else
+			ring = &dev_priv->ring[VCS];
+	} else
 		ring = &dev_priv->ring[(args->flags & I915_EXEC_RING_MASK) - 1];
 
 	if (!intel_ring_initialized(ring)) {
@@ -1096,14 +1144,22 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 	case I915_EXEC_CONSTANTS_REL_GENERAL:
 	case I915_EXEC_CONSTANTS_ABSOLUTE:
 	case I915_EXEC_CONSTANTS_REL_SURFACE:
-		if (ring == &dev_priv->ring[RCS] &&
-		    mode != dev_priv->relative_constants_mode) {
-			if (INTEL_INFO(dev)->gen < 4)
+		if (mode != 0 && ring != &dev_priv->ring[RCS]) {
+			DRM_DEBUG("non-0 rel constants mode on non-RCS\n");
+			return -EINVAL;
+		}
+
+		if (mode != dev_priv->relative_constants_mode) {
+			if (INTEL_INFO(dev)->gen < 4) {
+				DRM_DEBUG("no rel constants on pre-gen4\n");
 				return -EINVAL;
+			}
 
 			if (INTEL_INFO(dev)->gen > 5 &&
-			    mode == I915_EXEC_CONSTANTS_REL_SURFACE)
+			    mode == I915_EXEC_CONSTANTS_REL_SURFACE) {
+				DRM_DEBUG("rel surface constants mode invalid on gen5+\n");
 				return -EINVAL;
+			}
 
 			/* The HW changed the meaning on this bit on gen6 */
 			if (INTEL_INFO(dev)->gen >= 6)
@@ -1151,6 +1207,16 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			ret = -EFAULT;
 			goto pre_mutex_err;
 		}
+	} else {
+		if (args->DR4 == 0xffffffff) {
+			DRM_DEBUG("UXA submitting garbage DR4, fixing up\n");
+			args->DR4 = 0;
+		}
+
+		if (args->DR1 || args->DR4 || args->cliprects_ptr) {
+			DRM_DEBUG("0 cliprects but dirt in cliprects fields\n");
+			return -EINVAL;
+		}
 	}
 
 	intel_runtime_pm_get(dev_priv);
@@ -1170,7 +1236,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 		mutex_unlock(&dev->struct_mutex);
 		ret = PTR_ERR(ctx);
 		goto pre_mutex_err;
-	} 
+	}
 
 	i915_gem_context_reference(ctx);
 
@@ -1180,6 +1246,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 
 	eb = eb_create(args);
 	if (eb == NULL) {
+		i915_gem_context_unreference(ctx);
 		mutex_unlock(&dev->struct_mutex);
 		ret = -ENOMEM;
 		goto pre_mutex_err;
@@ -1430,6 +1497,11 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
+	if (args->rsvd2 != 0) {
+		DRM_DEBUG("dirty rvsd2 field\n");
+		return -EINVAL;
+	}
+
 	exec2_list = kmalloc(sizeof(*exec2_list)*args->buffer_count,
 			     GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
 	if (exec2_list == NULL)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 5deb22864c5..8b3cde70336 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -30,7 +30,8 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
-static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv);
+static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv);
+static void chv_setup_private_ppat(struct drm_i915_private *dev_priv);
 
 bool intel_enable_ppgtt(struct drm_device *dev, bool full)
 {
@@ -65,59 +66,6 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
 	return HAS_ALIASING_PPGTT(dev) ? 1 : 0;
 }
 
-#define GEN6_PPGTT_PD_ENTRIES 512
-#define I915_PPGTT_PT_ENTRIES (PAGE_SIZE / sizeof(gen6_gtt_pte_t))
-typedef uint64_t gen8_gtt_pte_t;
-typedef gen8_gtt_pte_t gen8_ppgtt_pde_t;
-
-/* PPGTT stuff */
-#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
-#define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
-
-#define GEN6_PDE_VALID			(1 << 0)
-/* gen6+ has bit 11-4 for physical addr bit 39-32 */
-#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
-
-#define GEN6_PTE_VALID			(1 << 0)
-#define GEN6_PTE_UNCACHED		(1 << 1)
-#define HSW_PTE_UNCACHED		(0)
-#define GEN6_PTE_CACHE_LLC		(2 << 1)
-#define GEN7_PTE_CACHE_L3_LLC		(3 << 1)
-#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
-#define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)
-
-/* Cacheability Control is a 4-bit value. The low three bits are stored in *
- * bits 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
- */
-#define HSW_CACHEABILITY_CONTROL(bits)	((((bits) & 0x7) << 1) | \
-					 (((bits) & 0x8) << (11 - 3)))
-#define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
-#define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
-#define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
-#define HSW_WB_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x8)
-#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
-#define HSW_WT_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x7)
-
-#define GEN8_PTES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_gtt_pte_t))
-#define GEN8_PDES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_ppgtt_pde_t))
-
-/* GEN8 legacy style addressis defined as a 3 level page table:
- * 31:30 | 29:21 | 20:12 |  11:0
- * PDPE  |  PDE  |  PTE  | offset
- * The difference as compared to normal x86 3 level page table is the PDPEs are
- * programmed via register.
- */
-#define GEN8_PDPE_SHIFT			30
-#define GEN8_PDPE_MASK			0x3
-#define GEN8_PDE_SHIFT			21
-#define GEN8_PDE_MASK			0x1ff
-#define GEN8_PTE_SHIFT			12
-#define GEN8_PTE_MASK			0x1ff
-
-#define PPAT_UNCACHED_INDEX		(_PAGE_PWT | _PAGE_PCD)
-#define PPAT_CACHED_PDE_INDEX		0 /* WB LLC */
-#define PPAT_CACHED_INDEX		_PAGE_PAT /* WB LLCeLLC */
-#define PPAT_DISPLAY_ELLC_INDEX		_PAGE_PCD /* WT eLLC */
 
 static void ppgtt_bind_vma(struct i915_vma *vma,
 			   enum i915_cache_level cache_level,
@@ -131,10 +79,19 @@ static inline gen8_gtt_pte_t gen8_pte_encode(dma_addr_t addr,
 {
 	gen8_gtt_pte_t pte = valid ? _PAGE_PRESENT | _PAGE_RW : 0;
 	pte |= addr;
-	if (level != I915_CACHE_NONE)
-		pte |= PPAT_CACHED_INDEX;
-	else
+
+	switch (level) {
+	case I915_CACHE_NONE:
 		pte |= PPAT_UNCACHED_INDEX;
+		break;
+	case I915_CACHE_WT:
+		pte |= PPAT_DISPLAY_ELLC_INDEX;
+		break;
+	default:
+		pte |= PPAT_CACHED_INDEX;
+		break;
+	}
+
 	return pte;
 }
 
@@ -197,9 +154,6 @@ static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
-#define BYT_PTE_WRITEABLE		(1 << 1)
-#define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
-
 static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
 				     bool valid)
@@ -253,7 +207,7 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
 }
 
 /* Broadwell Page Directory Pointer Descriptors */
-static int gen8_write_pdp(struct intel_ring_buffer *ring, unsigned entry,
+static int gen8_write_pdp(struct intel_engine_cs *ring, unsigned entry,
 			   uint64_t val, bool synchronous)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -283,7 +237,7 @@ static int gen8_write_pdp(struct intel_ring_buffer *ring, unsigned entry,
 }
 
 static int gen8_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct intel_ring_buffer *ring,
+			  struct intel_engine_cs *ring,
 			  bool synchronous)
 {
 	int i, ret;
@@ -332,6 +286,8 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 			num_entries--;
 		}
 
+		if (!HAS_LLC(ppgtt->base.dev))
+			drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
 		kunmap_atomic(pt_vaddr);
 
 		pte = 0;
@@ -368,6 +324,8 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 			gen8_pte_encode(sg_page_iter_dma_address(&sg_iter),
 					cache_level, true);
 		if (++pte == GEN8_PTES_PER_PAGE) {
+			if (!HAS_LLC(ppgtt->base.dev))
+				drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
 			kunmap_atomic(pt_vaddr);
 			pt_vaddr = NULL;
 			if (++pde == GEN8_PDES_PER_PAGE) {
@@ -377,8 +335,11 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 			pte = 0;
 		}
 	}
-	if (pt_vaddr)
+	if (pt_vaddr) {
+		if (!HAS_LLC(ppgtt->base.dev))
+			drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
 		kunmap_atomic(pt_vaddr);
+	}
 }
 
 static void gen8_free_page_tables(struct page **pt_pages)
@@ -641,6 +602,8 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt, uint64_t size)
 			pd_vaddr[j] = gen8_pde_encode(ppgtt->base.dev, addr,
 						      I915_CACHE_LLC);
 		}
+		if (!HAS_LLC(ppgtt->base.dev))
+			drm_clflush_virt_range(pd_vaddr, PAGE_SIZE);
 		kunmap_atomic(pd_vaddr);
 	}
 
@@ -753,7 +716,7 @@ static uint32_t get_pd_offset(struct i915_hw_ppgtt *ppgtt)
 }
 
 static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			 struct intel_ring_buffer *ring,
+			 struct intel_engine_cs *ring,
 			 bool synchronous)
 {
 	struct drm_device *dev = ppgtt->base.dev;
@@ -797,7 +760,7 @@ static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
 }
 
 static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct intel_ring_buffer *ring,
+			  struct intel_engine_cs *ring,
 			  bool synchronous)
 {
 	struct drm_device *dev = ppgtt->base.dev;
@@ -848,7 +811,7 @@ static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
 }
 
 static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct intel_ring_buffer *ring,
+			  struct intel_engine_cs *ring,
 			  bool synchronous)
 {
 	struct drm_device *dev = ppgtt->base.dev;
@@ -869,7 +832,7 @@ static int gen8_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
 {
 	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int j, ret;
 
 	for_each_ring(ring, dev_priv, j) {
@@ -899,7 +862,7 @@ static int gen7_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
 {
 	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	uint32_t ecochk, ecobits;
 	int i;
 
@@ -938,7 +901,7 @@ static int gen6_ppgtt_enable(struct i915_hw_ppgtt *ppgtt)
 {
 	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	uint32_t ecochk, gab_ctl, ecobits;
 	int i;
 
@@ -1067,8 +1030,6 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 
 static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
 {
-#define GEN6_PD_ALIGN (PAGE_SIZE * 16)
-#define GEN6_PD_SIZE (GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE)
 	struct drm_device *dev = ppgtt->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	bool retried = false;
@@ -1084,8 +1045,7 @@ alloc:
 						  &ppgtt->node, GEN6_PD_SIZE,
 						  GEN6_PD_ALIGN, 0,
 						  0, dev_priv->gtt.base.total,
-						  DRM_MM_SEARCH_DEFAULT,
-						  DRM_MM_CREATE_DEFAULT);
+						  DRM_MM_TOPDOWN);
 	if (ret == -ENOSPC && !retried) {
 		ret = i915_gem_evict_something(dev, &dev_priv->gtt.base,
 					       GEN6_PD_SIZE, GEN6_PD_ALIGN,
@@ -1311,7 +1271,7 @@ static void undo_idling(struct drm_i915_private *dev_priv, bool interruptible)
 void i915_check_and_clear_faults(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int i;
 
 	if (INTEL_INFO(dev)->gen < 6)
@@ -1386,7 +1346,11 @@ void i915_gem_restore_gtt_mappings(struct drm_device *dev)
 
 
 	if (INTEL_INFO(dev)->gen >= 8) {
-		gen8_setup_private_ppat(dev_priv);
+		if (IS_CHERRYVIEW(dev))
+			chv_setup_private_ppat(dev_priv);
+		else
+			bdw_setup_private_ppat(dev_priv);
+
 		return;
 	}
 
@@ -1438,7 +1402,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 		(gen8_gtt_pte_t __iomem *)dev_priv->gtt.gsm + first_entry;
 	int i = 0;
 	struct sg_page_iter sg_iter;
-	dma_addr_t addr;
+	dma_addr_t addr = 0;
 
 	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
 		addr = sg_dma_address(sg_iter.sg) +
@@ -1811,9 +1775,27 @@ static inline unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
 	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
 	if (bdw_gmch_ctl)
 		bdw_gmch_ctl = 1 << bdw_gmch_ctl;
+
+#ifdef CONFIG_X86_32
+	/* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * PAGE_SIZE */
+	if (bdw_gmch_ctl > 4)
+		bdw_gmch_ctl = 4;
+#endif
+
 	return bdw_gmch_ctl << 20;
 }
 
+static inline unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
+{
+	gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
+	gmch_ctrl &= SNB_GMCH_GGMS_MASK;
+
+	if (gmch_ctrl)
+		return 1 << (20 + gmch_ctrl);
+
+	return 0;
+}
+
 static inline size_t gen6_get_stolen_size(u16 snb_gmch_ctl)
 {
 	snb_gmch_ctl >>= SNB_GMCH_GMS_SHIFT;
@@ -1828,6 +1810,24 @@ static inline size_t gen8_get_stolen_size(u16 bdw_gmch_ctl)
 	return bdw_gmch_ctl << 25; /* 32 MB units */
 }
 
+static size_t chv_get_stolen_size(u16 gmch_ctrl)
+{
+	gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
+	gmch_ctrl &= SNB_GMCH_GMS_MASK;
+
+	/*
+	 * 0x0  to 0x10: 32MB increments starting at 0MB
+	 * 0x11 to 0x16: 4MB increments starting at 8MB
+	 * 0x17 to 0x1d: 4MB increments start at 36MB
+	 */
+	if (gmch_ctrl < 0x11)
+		return gmch_ctrl << 25;
+	else if (gmch_ctrl < 0x17)
+		return (gmch_ctrl - 0x11 + 2) << 22;
+	else
+		return (gmch_ctrl - 0x17 + 9) << 22;
+}
+
 static int ggtt_probe_common(struct drm_device *dev,
 			     size_t gtt_size)
 {
@@ -1858,19 +1858,8 @@ static int ggtt_probe_common(struct drm_device *dev,
 /* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
  * bits. When using advanced contexts each context stores its own PAT, but
  * writing this data shouldn't be harmful even in those cases. */
-static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv)
-{
-#define GEN8_PPAT_UC		(0<<0)
-#define GEN8_PPAT_WC		(1<<0)
-#define GEN8_PPAT_WT		(2<<0)
-#define GEN8_PPAT_WB		(3<<0)
-#define GEN8_PPAT_ELLC_OVERRIDE	(0<<2)
-/* FIXME(BDW): Bspec is completely confused about cache control bits. */
-#define GEN8_PPAT_LLC		(1<<2)
-#define GEN8_PPAT_LLCELLC	(2<<2)
-#define GEN8_PPAT_LLCeLLC	(3<<2)
-#define GEN8_PPAT_AGE(x)	(x<<4)
-#define GEN8_PPAT(i, x) ((uint64_t) (x) << ((i) * 8))
+static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
+{
 	uint64_t pat;
 
 	pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC)     | /* for normal objects, no eLLC */
@@ -1888,6 +1877,33 @@ static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32);
 }
 
+static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
+{
+	uint64_t pat;
+
+	/*
+	 * Map WB on BDW to snooped on CHV.
+	 *
+	 * Only the snoop bit has meaning for CHV, the rest is
+	 * ignored.
+	 *
+	 * Note that the harware enforces snooping for all page
+	 * table accesses. The snoop bit is actually ignored for
+	 * PDEs.
+	 */
+	pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(1, 0) |
+	      GEN8_PPAT(2, 0) |
+	      GEN8_PPAT(3, 0) |
+	      GEN8_PPAT(4, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(5, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(6, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(7, CHV_PPAT_SNOOP);
+
+	I915_WRITE(GEN8_PRIVATE_PAT, pat);
+	I915_WRITE(GEN8_PRIVATE_PAT + 4, pat >> 32);
+}
+
 static int gen8_gmch_probe(struct drm_device *dev,
 			   size_t *gtt_total,
 			   size_t *stolen,
@@ -1908,12 +1924,20 @@ static int gen8_gmch_probe(struct drm_device *dev,
 
 	pci_read_config_word(dev->pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 
-	*stolen = gen8_get_stolen_size(snb_gmch_ctl);
+	if (IS_CHERRYVIEW(dev)) {
+		*stolen = chv_get_stolen_size(snb_gmch_ctl);
+		gtt_size = chv_get_total_gtt_size(snb_gmch_ctl);
+	} else {
+		*stolen = gen8_get_stolen_size(snb_gmch_ctl);
+		gtt_size = gen8_get_total_gtt_size(snb_gmch_ctl);
+	}
 
-	gtt_size = gen8_get_total_gtt_size(snb_gmch_ctl);
 	*gtt_total = (gtt_size / sizeof(gen8_gtt_pte_t)) << PAGE_SHIFT;
 
-	gen8_setup_private_ppat(dev_priv);
+	if (IS_CHERRYVIEW(dev))
+		chv_setup_private_ppat(dev_priv);
+	else
+		bdw_setup_private_ppat(dev_priv);
 
 	ret = ggtt_probe_common(dev, gtt_size);
 
@@ -1968,7 +1992,10 @@ static void gen6_gmch_remove(struct i915_address_space *vm)
 
 	struct i915_gtt *gtt = container_of(vm, struct i915_gtt, base);
 
-	drm_mm_takedown(&vm->mm);
+	if (drm_mm_initialized(&vm->mm)) {
+		drm_mm_takedown(&vm->mm);
+		list_del(&vm->global_link);
+	}
 	iounmap(gtt->gsm);
 	teardown_scratch_page(vm->dev);
 }
@@ -2001,6 +2028,10 @@ static int i915_gmch_probe(struct drm_device *dev,
 
 static void i915_gmch_remove(struct i915_address_space *vm)
 {
+	if (drm_mm_initialized(&vm->mm)) {
+		drm_mm_takedown(&vm->mm);
+		list_del(&vm->global_link);
+	}
 	intel_gmch_remove();
 }
 
@@ -2043,6 +2074,10 @@ int i915_gem_gtt_init(struct drm_device *dev)
 		 gtt->base.total >> 20);
 	DRM_DEBUG_DRIVER("GMADR size = %ldM\n", gtt->mappable_end >> 20);
 	DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", gtt->stolen_size >> 20);
+#ifdef CONFIG_INTEL_IOMMU
+	if (intel_iommu_gfx_mapped)
+		DRM_INFO("VT-d active for gfx access\n");
+#endif
 	/*
 	 * i915.enable_ppgtt is read-only, so do an early pass to validate the
 	 * user's requested state against the hardware/driver capabilities.  We
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
new file mode 100644
index 00000000000..1b96a06be3c
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -0,0 +1,284 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Please try to maintain the following order within this file unless it makes
+ * sense to do otherwise. From top to bottom:
+ * 1. typedefs
+ * 2. #defines, and macros
+ * 3. structure definitions
+ * 4. function prototypes
+ *
+ * Within each section, please try to order by generation in ascending order,
+ * from top to bottom (ie. gen6 on the top, gen8 on the bottom).
+ */
+
+#ifndef __I915_GEM_GTT_H__
+#define __I915_GEM_GTT_H__
+
+typedef uint32_t gen6_gtt_pte_t;
+typedef uint64_t gen8_gtt_pte_t;
+typedef gen8_gtt_pte_t gen8_ppgtt_pde_t;
+
+#define gtt_total_entries(gtt) ((gtt).base.total >> PAGE_SHIFT)
+
+#define I915_PPGTT_PT_ENTRIES		(PAGE_SIZE / sizeof(gen6_gtt_pte_t))
+/* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
+#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
+#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+#define GEN6_PTE_CACHE_LLC		(2 << 1)
+#define GEN6_PTE_UNCACHED		(1 << 1)
+#define GEN6_PTE_VALID			(1 << 0)
+
+#define GEN6_PPGTT_PD_ENTRIES		512
+#define GEN6_PD_SIZE			(GEN6_PPGTT_PD_ENTRIES * PAGE_SIZE)
+#define GEN6_PD_ALIGN			(PAGE_SIZE * 16)
+#define GEN6_PDE_VALID			(1 << 0)
+
+#define GEN7_PTE_CACHE_L3_LLC		(3 << 1)
+
+#define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
+#define BYT_PTE_WRITEABLE		(1 << 1)
+
+/* Cacheability Control is a 4-bit value. The low three bits are stored in bits
+ * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
+ */
+#define HSW_CACHEABILITY_CONTROL(bits)	((((bits) & 0x7) << 1) | \
+					 (((bits) & 0x8) << (11 - 3)))
+#define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
+#define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
+#define HSW_WB_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x8)
+#define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
+#define HSW_WT_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x7)
+#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
+#define HSW_PTE_UNCACHED		(0)
+#define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
+#define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)
+
+/* GEN8 legacy style address is defined as a 3 level page table:
+ * 31:30 | 29:21 | 20:12 |  11:0
+ * PDPE  |  PDE  |  PTE  | offset
+ * The difference as compared to normal x86 3 level page table is the PDPEs are
+ * programmed via register.
+ */
+#define GEN8_PDPE_SHIFT			30
+#define GEN8_PDPE_MASK			0x3
+#define GEN8_PDE_SHIFT			21
+#define GEN8_PDE_MASK			0x1ff
+#define GEN8_PTE_SHIFT			12
+#define GEN8_PTE_MASK			0x1ff
+#define GEN8_LEGACY_PDPS		4
+#define GEN8_PTES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_gtt_pte_t))
+#define GEN8_PDES_PER_PAGE		(PAGE_SIZE / sizeof(gen8_ppgtt_pde_t))
+
+#define PPAT_UNCACHED_INDEX		(_PAGE_PWT | _PAGE_PCD)
+#define PPAT_CACHED_PDE_INDEX		0 /* WB LLC */
+#define PPAT_CACHED_INDEX		_PAGE_PAT /* WB LLCeLLC */
+#define PPAT_DISPLAY_ELLC_INDEX		_PAGE_PCD /* WT eLLC */
+
+#define CHV_PPAT_SNOOP			(1<<6)
+#define GEN8_PPAT_AGE(x)		(x<<4)
+#define GEN8_PPAT_LLCeLLC		(3<<2)
+#define GEN8_PPAT_LLCELLC		(2<<2)
+#define GEN8_PPAT_LLC			(1<<2)
+#define GEN8_PPAT_WB			(3<<0)
+#define GEN8_PPAT_WT			(2<<0)
+#define GEN8_PPAT_WC			(1<<0)
+#define GEN8_PPAT_UC			(0<<0)
+#define GEN8_PPAT_ELLC_OVERRIDE		(0<<2)
+#define GEN8_PPAT(i, x)			((uint64_t) (x) << ((i) * 8))
+
+enum i915_cache_level;
+/**
+ * A VMA represents a GEM BO that is bound into an address space. Therefore, a
+ * VMA's presence cannot be guaranteed before binding, or after unbinding the
+ * object into/from the address space.
+ *
+ * To make things as simple as possible (ie. no refcounting), a VMA's lifetime
+ * will always be <= an objects lifetime. So object refcounting should cover us.
+ */
+struct i915_vma {
+	struct drm_mm_node node;
+	struct drm_i915_gem_object *obj;
+	struct i915_address_space *vm;
+
+	/** This object's place on the active/inactive lists */
+	struct list_head mm_list;
+
+	struct list_head vma_link; /* Link in the object's VMA list */
+
+	/** This vma's place in the batchbuffer or on the eviction list */
+	struct list_head exec_list;
+
+	/**
+	 * Used for performing relocations during execbuffer insertion.
+	 */
+	struct hlist_node exec_node;
+	unsigned long exec_handle;
+	struct drm_i915_gem_exec_object2 *exec_entry;
+
+	/**
+	 * How many users have pinned this object in GTT space. The following
+	 * users can each hold at most one reference: pwrite/pread, pin_ioctl
+	 * (via user_pin_count), execbuffer (objects are not allowed multiple
+	 * times for the same batchbuffer), and the framebuffer code. When
+	 * switching/pageflipping, the framebuffer code has at most two buffers
+	 * pinned per crtc.
+	 *
+	 * In the worst case this is 1 + 1 + 1 + 2*2 = 7. That would fit into 3
+	 * bits with absolutely no headroom. So use 4 bits. */
+	unsigned int pin_count:4;
+#define DRM_I915_GEM_OBJECT_MAX_PIN_COUNT 0xf
+
+	/** Unmap an object from an address space. This usually consists of
+	 * setting the valid PTE entries to a reserved scratch page. */
+	void (*unbind_vma)(struct i915_vma *vma);
+	/* Map an object into an address space with the given cache flags. */
+#define GLOBAL_BIND (1<<0)
+	void (*bind_vma)(struct i915_vma *vma,
+			 enum i915_cache_level cache_level,
+			 u32 flags);
+};
+
+struct i915_address_space {
+	struct drm_mm mm;
+	struct drm_device *dev;
+	struct list_head global_link;
+	unsigned long start;		/* Start offset always 0 for dri2 */
+	size_t total;		/* size addr space maps (ex. 2GB for ggtt) */
+
+	struct {
+		dma_addr_t addr;
+		struct page *page;
+	} scratch;
+
+	/**
+	 * List of objects currently involved in rendering.
+	 *
+	 * Includes buffers having the contents of their GPU caches
+	 * flushed, not necessarily primitives.  last_rendering_seqno
+	 * represents when the rendering involved will be completed.
+	 *
+	 * A reference is held on the buffer while on this list.
+	 */
+	struct list_head active_list;
+
+	/**
+	 * LRU list of objects which are not in the ringbuffer and
+	 * are ready to unbind, but are still in the GTT.
+	 *
+	 * last_rendering_seqno is 0 while an object is in this list.
+	 *
+	 * A reference is not held on the buffer while on this list,
+	 * as merely being GTT-bound shouldn't prevent its being
+	 * freed, and we'll pull it off the list in the free path.
+	 */
+	struct list_head inactive_list;
+
+	/* FIXME: Need a more generic return type */
+	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
+				     enum i915_cache_level level,
+				     bool valid); /* Create a valid PTE */
+	void (*clear_range)(struct i915_address_space *vm,
+			    uint64_t start,
+			    uint64_t length,
+			    bool use_scratch);
+	void (*insert_entries)(struct i915_address_space *vm,
+			       struct sg_table *st,
+			       uint64_t start,
+			       enum i915_cache_level cache_level);
+	void (*cleanup)(struct i915_address_space *vm);
+};
+
+/* The Graphics Translation Table is the way in which GEN hardware translates a
+ * Graphics Virtual Address into a Physical Address. In addition to the normal
+ * collateral associated with any va->pa translations GEN hardware also has a
+ * portion of the GTT which can be mapped by the CPU and remain both coherent
+ * and correct (in cases like swizzling). That region is referred to as GMADR in
+ * the spec.
+ */
+struct i915_gtt {
+	struct i915_address_space base;
+	size_t stolen_size;		/* Total size of stolen memory */
+
+	unsigned long mappable_end;	/* End offset that we can CPU map */
+	struct io_mapping *mappable;	/* Mapping to our CPU mappable region */
+	phys_addr_t mappable_base;	/* PA of our GMADR */
+
+	/** "Graphics Stolen Memory" holds the global PTEs */
+	void __iomem *gsm;
+
+	bool do_idle_maps;
+
+	int mtrr;
+
+	/* global gtt ops */
+	int (*gtt_probe)(struct drm_device *dev, size_t *gtt_total,
+			  size_t *stolen, phys_addr_t *mappable_base,
+			  unsigned long *mappable_end);
+};
+
+struct i915_hw_ppgtt {
+	struct i915_address_space base;
+	struct kref ref;
+	struct drm_mm_node node;
+	unsigned num_pd_entries;
+	unsigned num_pd_pages; /* gen8+ */
+	union {
+		struct page **pt_pages;
+		struct page **gen8_pt_pages[GEN8_LEGACY_PDPS];
+	};
+	struct page *pd_pages;
+	union {
+		uint32_t pd_offset;
+		dma_addr_t pd_dma_addr[GEN8_LEGACY_PDPS];
+	};
+	union {
+		dma_addr_t *pt_dma_addr;
+		dma_addr_t *gen8_pt_dma_addr[4];
+	};
+
+	struct intel_context *ctx;
+
+	int (*enable)(struct i915_hw_ppgtt *ppgtt);
+	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
+			 struct intel_engine_cs *ring,
+			 bool synchronous);
+	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
+};
+
+int i915_gem_gtt_init(struct drm_device *dev);
+void i915_gem_init_global_gtt(struct drm_device *dev);
+void i915_gem_setup_global_gtt(struct drm_device *dev, unsigned long start,
+			       unsigned long mappable_end, unsigned long end);
+
+bool intel_enable_ppgtt(struct drm_device *dev, bool full);
+int i915_gem_init_ppgtt(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt);
+
+void i915_check_and_clear_faults(struct drm_device *dev);
+void i915_gem_suspend_gtt_mappings(struct drm_device *dev);
+void i915_gem_restore_gtt_mappings(struct drm_device *dev);
+
+int __must_check i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj);
+void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj);
+
+#endif
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
new file mode 100644
index 00000000000..34894b57306
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -0,0 +1,198 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Mika Kuoppala <mika.kuoppala@intel.com>
+ *
+ */
+
+#include "i915_drv.h"
+#include "intel_renderstate.h"
+
+struct i915_render_state {
+	struct drm_i915_gem_object *obj;
+	unsigned long ggtt_offset;
+	u32 *batch;
+	u32 size;
+	u32 len;
+};
+
+static struct i915_render_state *render_state_alloc(struct drm_device *dev)
+{
+	struct i915_render_state *so;
+	struct page *page;
+	int ret;
+
+	so = kzalloc(sizeof(*so), GFP_KERNEL);
+	if (!so)
+		return ERR_PTR(-ENOMEM);
+
+	so->obj = i915_gem_alloc_object(dev, 4096);
+	if (so->obj == NULL) {
+		ret = -ENOMEM;
+		goto free;
+	}
+	so->size = 4096;
+
+	ret = i915_gem_obj_ggtt_pin(so->obj, 4096, 0);
+	if (ret)
+		goto free_gem;
+
+	BUG_ON(so->obj->pages->nents != 1);
+	page = sg_page(so->obj->pages->sgl);
+
+	so->batch = kmap(page);
+	if (!so->batch) {
+		ret = -ENOMEM;
+		goto unpin;
+	}
+
+	so->ggtt_offset = i915_gem_obj_ggtt_offset(so->obj);
+
+	return so;
+unpin:
+	i915_gem_object_ggtt_unpin(so->obj);
+free_gem:
+	drm_gem_object_unreference(&so->obj->base);
+free:
+	kfree(so);
+	return ERR_PTR(ret);
+}
+
+static void render_state_free(struct i915_render_state *so)
+{
+	kunmap(kmap_to_page(so->batch));
+	i915_gem_object_ggtt_unpin(so->obj);
+	drm_gem_object_unreference(&so->obj->base);
+	kfree(so);
+}
+
+static const struct intel_renderstate_rodata *
+render_state_get_rodata(struct drm_device *dev, const int gen)
+{
+	switch (gen) {
+	case 6:
+		return &gen6_null_state;
+	case 7:
+		return &gen7_null_state;
+	case 8:
+		return &gen8_null_state;
+	}
+
+	return NULL;
+}
+
+static int render_state_setup(const int gen,
+			      const struct intel_renderstate_rodata *rodata,
+			      struct i915_render_state *so)
+{
+	const u64 goffset = i915_gem_obj_ggtt_offset(so->obj);
+	u32 reloc_index = 0;
+	u32 * const d = so->batch;
+	unsigned int i = 0;
+	int ret;
+
+	if (!rodata || rodata->batch_items * 4 > so->size)
+		return -EINVAL;
+
+	ret = i915_gem_object_set_to_cpu_domain(so->obj, true);
+	if (ret)
+		return ret;
+
+	while (i < rodata->batch_items) {
+		u32 s = rodata->batch[i];
+
+		if (reloc_index < rodata->reloc_items &&
+		    i * 4  == rodata->reloc[reloc_index]) {
+
+			s += goffset & 0xffffffff;
+
+			/* We keep batch offsets max 32bit */
+			if (gen >= 8) {
+				if (i + 1 >= rodata->batch_items ||
+				    rodata->batch[i + 1] != 0)
+					return -EINVAL;
+
+				d[i] = s;
+				i++;
+				s = (goffset & 0xffffffff00000000ull) >> 32;
+			}
+
+			reloc_index++;
+		}
+
+		d[i] = s;
+		i++;
+	}
+
+	ret = i915_gem_object_set_to_gtt_domain(so->obj, false);
+	if (ret)
+		return ret;
+
+	if (rodata->reloc_items != reloc_index) {
+		DRM_ERROR("not all relocs resolved, %d out of %d\n",
+			  reloc_index, rodata->reloc_items);
+		return -EINVAL;
+	}
+
+	so->len = rodata->batch_items * 4;
+
+	return 0;
+}
+
+int i915_gem_render_state_init(struct intel_engine_cs *ring)
+{
+	const int gen = INTEL_INFO(ring->dev)->gen;
+	struct i915_render_state *so;
+	const struct intel_renderstate_rodata *rodata;
+	int ret;
+
+	if (WARN_ON(ring->id != RCS))
+		return -ENOENT;
+
+	rodata = render_state_get_rodata(ring->dev, gen);
+	if (rodata == NULL)
+		return 0;
+
+	so = render_state_alloc(ring->dev);
+	if (IS_ERR(so))
+		return PTR_ERR(so);
+
+	ret = render_state_setup(gen, rodata, so);
+	if (ret)
+		goto out;
+
+	ret = ring->dispatch_execbuffer(ring,
+					i915_gem_obj_ggtt_offset(so->obj),
+					so->len,
+					I915_DISPATCH_SECURE);
+	if (ret)
+		goto out;
+
+	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so->obj), ring);
+
+	ret = __i915_add_request(ring, NULL, so->obj, NULL);
+	/* __i915_add_request moves object to inactive if it fails */
+out:
+	render_state_free(so);
+	return ret;
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 62ef55ba061..7465ab0fd39 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -74,6 +74,50 @@ static unsigned long i915_stolen_to_physical(struct drm_device *dev)
 	if (base == 0)
 		return 0;
 
+	/* make sure we don't clobber the GTT if it's within stolen memory */
+	if (INTEL_INFO(dev)->gen <= 4 && !IS_G33(dev) && !IS_G4X(dev)) {
+		struct {
+			u32 start, end;
+		} stolen[2] = {
+			{ .start = base, .end = base + dev_priv->gtt.stolen_size, },
+			{ .start = base, .end = base + dev_priv->gtt.stolen_size, },
+		};
+		u64 gtt_start, gtt_end;
+
+		gtt_start = I915_READ(PGTBL_CTL);
+		if (IS_GEN4(dev))
+			gtt_start = (gtt_start & PGTBL_ADDRESS_LO_MASK) |
+				(gtt_start & PGTBL_ADDRESS_HI_MASK) << 28;
+		else
+			gtt_start &= PGTBL_ADDRESS_LO_MASK;
+		gtt_end = gtt_start + gtt_total_entries(dev_priv->gtt) * 4;
+
+		if (gtt_start >= stolen[0].start && gtt_start < stolen[0].end)
+			stolen[0].end = gtt_start;
+		if (gtt_end > stolen[1].start && gtt_end <= stolen[1].end)
+			stolen[1].start = gtt_end;
+
+		/* pick the larger of the two chunks */
+		if (stolen[0].end - stolen[0].start >
+		    stolen[1].end - stolen[1].start) {
+			base = stolen[0].start;
+			dev_priv->gtt.stolen_size = stolen[0].end - stolen[0].start;
+		} else {
+			base = stolen[1].start;
+			dev_priv->gtt.stolen_size = stolen[1].end - stolen[1].start;
+		}
+
+		if (stolen[0].start != stolen[1].start ||
+		    stolen[0].end != stolen[1].end) {
+			DRM_DEBUG_KMS("GTT within stolen memory at 0x%llx-0x%llx\n",
+				      (unsigned long long) gtt_start,
+				      (unsigned long long) gtt_end - 1);
+			DRM_DEBUG_KMS("Stolen memory adjusted to 0x%x-0x%x\n",
+				      base, base + (u32) dev_priv->gtt.stolen_size - 1);
+		}
+	}
+
+
 	/* Verify that nothing else uses this physical address. Stolen
 	 * memory should be reserved by the BIOS and hidden from the
 	 * kernel. So if the region is already marked as busy, something
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
new file mode 100644
index 00000000000..21ea92886a5
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -0,0 +1,711 @@
+/*
+ * Copyright © 2012-2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#include "drmP.h"
+#include "i915_drm.h"
+#include "i915_drv.h"
+#include "i915_trace.h"
+#include "intel_drv.h"
+#include <linux/mmu_context.h>
+#include <linux/mmu_notifier.h>
+#include <linux/mempolicy.h>
+#include <linux/swap.h>
+
+#if defined(CONFIG_MMU_NOTIFIER)
+#include <linux/interval_tree.h>
+
+struct i915_mmu_notifier {
+	spinlock_t lock;
+	struct hlist_node node;
+	struct mmu_notifier mn;
+	struct rb_root objects;
+	struct drm_device *dev;
+	struct mm_struct *mm;
+	struct work_struct work;
+	unsigned long count;
+	unsigned long serial;
+};
+
+struct i915_mmu_object {
+	struct i915_mmu_notifier *mmu;
+	struct interval_tree_node it;
+	struct drm_i915_gem_object *obj;
+};
+
+static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
+						       struct mm_struct *mm,
+						       unsigned long start,
+						       unsigned long end)
+{
+	struct i915_mmu_notifier *mn = container_of(_mn, struct i915_mmu_notifier, mn);
+	struct interval_tree_node *it = NULL;
+	unsigned long serial = 0;
+
+	end--; /* interval ranges are inclusive, but invalidate range is exclusive */
+	while (start < end) {
+		struct drm_i915_gem_object *obj;
+
+		obj = NULL;
+		spin_lock(&mn->lock);
+		if (serial == mn->serial)
+			it = interval_tree_iter_next(it, start, end);
+		else
+			it = interval_tree_iter_first(&mn->objects, start, end);
+		if (it != NULL) {
+			obj = container_of(it, struct i915_mmu_object, it)->obj;
+			drm_gem_object_reference(&obj->base);
+			serial = mn->serial;
+		}
+		spin_unlock(&mn->lock);
+		if (obj == NULL)
+			return;
+
+		mutex_lock(&mn->dev->struct_mutex);
+		/* Cancel any active worker and force us to re-evaluate gup */
+		obj->userptr.work = NULL;
+
+		if (obj->pages != NULL) {
+			struct drm_i915_private *dev_priv = to_i915(mn->dev);
+			struct i915_vma *vma, *tmp;
+			bool was_interruptible;
+
+			was_interruptible = dev_priv->mm.interruptible;
+			dev_priv->mm.interruptible = false;
+
+			list_for_each_entry_safe(vma, tmp, &obj->vma_list, vma_link) {
+				int ret = i915_vma_unbind(vma);
+				WARN_ON(ret && ret != -EIO);
+			}
+			WARN_ON(i915_gem_object_put_pages(obj));
+
+			dev_priv->mm.interruptible = was_interruptible;
+		}
+
+		start = obj->userptr.ptr + obj->base.size;
+
+		drm_gem_object_unreference(&obj->base);
+		mutex_unlock(&mn->dev->struct_mutex);
+	}
+}
+
+static const struct mmu_notifier_ops i915_gem_userptr_notifier = {
+	.invalidate_range_start = i915_gem_userptr_mn_invalidate_range_start,
+};
+
+static struct i915_mmu_notifier *
+__i915_mmu_notifier_lookup(struct drm_device *dev, struct mm_struct *mm)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_mmu_notifier *mmu;
+
+	/* Protected by dev->struct_mutex */
+	hash_for_each_possible(dev_priv->mmu_notifiers, mmu, node, (unsigned long)mm)
+		if (mmu->mm == mm)
+			return mmu;
+
+	return NULL;
+}
+
+static struct i915_mmu_notifier *
+i915_mmu_notifier_get(struct drm_device *dev, struct mm_struct *mm)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_mmu_notifier *mmu;
+	int ret;
+
+	lockdep_assert_held(&dev->struct_mutex);
+
+	mmu = __i915_mmu_notifier_lookup(dev, mm);
+	if (mmu)
+		return mmu;
+
+	mmu = kmalloc(sizeof(*mmu), GFP_KERNEL);
+	if (mmu == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&mmu->lock);
+	mmu->dev = dev;
+	mmu->mn.ops = &i915_gem_userptr_notifier;
+	mmu->mm = mm;
+	mmu->objects = RB_ROOT;
+	mmu->count = 0;
+	mmu->serial = 0;
+
+	/* Protected by mmap_sem (write-lock) */
+	ret = __mmu_notifier_register(&mmu->mn, mm);
+	if (ret) {
+		kfree(mmu);
+		return ERR_PTR(ret);
+	}
+
+	/* Protected by dev->struct_mutex */
+	hash_add(dev_priv->mmu_notifiers, &mmu->node, (unsigned long)mm);
+	return mmu;
+}
+
+static void
+__i915_mmu_notifier_destroy_worker(struct work_struct *work)
+{
+	struct i915_mmu_notifier *mmu = container_of(work, typeof(*mmu), work);
+	mmu_notifier_unregister(&mmu->mn, mmu->mm);
+	kfree(mmu);
+}
+
+static void
+__i915_mmu_notifier_destroy(struct i915_mmu_notifier *mmu)
+{
+	lockdep_assert_held(&mmu->dev->struct_mutex);
+
+	/* Protected by dev->struct_mutex */
+	hash_del(&mmu->node);
+
+	/* Our lock ordering is: mmap_sem, mmu_notifier_scru, struct_mutex.
+	 * We enter the function holding struct_mutex, therefore we need
+	 * to drop our mutex prior to calling mmu_notifier_unregister in
+	 * order to prevent lock inversion (and system-wide deadlock)
+	 * between the mmap_sem and struct-mutex. Hence we defer the
+	 * unregistration to a workqueue where we hold no locks.
+	 */
+	INIT_WORK(&mmu->work, __i915_mmu_notifier_destroy_worker);
+	schedule_work(&mmu->work);
+}
+
+static void __i915_mmu_notifier_update_serial(struct i915_mmu_notifier *mmu)
+{
+	if (++mmu->serial == 0)
+		mmu->serial = 1;
+}
+
+static void
+i915_mmu_notifier_del(struct i915_mmu_notifier *mmu,
+		      struct i915_mmu_object *mn)
+{
+	lockdep_assert_held(&mmu->dev->struct_mutex);
+
+	spin_lock(&mmu->lock);
+	interval_tree_remove(&mn->it, &mmu->objects);
+	__i915_mmu_notifier_update_serial(mmu);
+	spin_unlock(&mmu->lock);
+
+	/* Protected against _add() by dev->struct_mutex */
+	if (--mmu->count == 0)
+		__i915_mmu_notifier_destroy(mmu);
+}
+
+static int
+i915_mmu_notifier_add(struct i915_mmu_notifier *mmu,
+		      struct i915_mmu_object *mn)
+{
+	struct interval_tree_node *it;
+	int ret;
+
+	ret = i915_mutex_lock_interruptible(mmu->dev);
+	if (ret)
+		return ret;
+
+	/* Make sure we drop the final active reference (and thereby
+	 * remove the objects from the interval tree) before we do
+	 * the check for overlapping objects.
+	 */
+	i915_gem_retire_requests(mmu->dev);
+
+	/* Disallow overlapping userptr objects */
+	spin_lock(&mmu->lock);
+	it = interval_tree_iter_first(&mmu->objects,
+				      mn->it.start, mn->it.last);
+	if (it) {
+		struct drm_i915_gem_object *obj;
+
+		/* We only need to check the first object in the range as it
+		 * either has cancelled gup work queued and we need to
+		 * return back to the user to give time for the gup-workers
+		 * to flush their object references upon which the object will
+		 * be removed from the interval-tree, or the the range is
+		 * still in use by another client and the overlap is invalid.
+		 */
+
+		obj = container_of(it, struct i915_mmu_object, it)->obj;
+		ret = obj->userptr.workers ? -EAGAIN : -EINVAL;
+	} else {
+		interval_tree_insert(&mn->it, &mmu->objects);
+		__i915_mmu_notifier_update_serial(mmu);
+		ret = 0;
+	}
+	spin_unlock(&mmu->lock);
+	mutex_unlock(&mmu->dev->struct_mutex);
+
+	return ret;
+}
+
+static void
+i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj)
+{
+	struct i915_mmu_object *mn;
+
+	mn = obj->userptr.mn;
+	if (mn == NULL)
+		return;
+
+	i915_mmu_notifier_del(mn->mmu, mn);
+	obj->userptr.mn = NULL;
+}
+
+static int
+i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj,
+				    unsigned flags)
+{
+	struct i915_mmu_notifier *mmu;
+	struct i915_mmu_object *mn;
+	int ret;
+
+	if (flags & I915_USERPTR_UNSYNCHRONIZED)
+		return capable(CAP_SYS_ADMIN) ? 0 : -EPERM;
+
+	down_write(&obj->userptr.mm->mmap_sem);
+	ret = i915_mutex_lock_interruptible(obj->base.dev);
+	if (ret == 0) {
+		mmu = i915_mmu_notifier_get(obj->base.dev, obj->userptr.mm);
+		if (!IS_ERR(mmu))
+			mmu->count++; /* preemptive add to act as a refcount */
+		else
+			ret = PTR_ERR(mmu);
+		mutex_unlock(&obj->base.dev->struct_mutex);
+	}
+	up_write(&obj->userptr.mm->mmap_sem);
+	if (ret)
+		return ret;
+
+	mn = kzalloc(sizeof(*mn), GFP_KERNEL);
+	if (mn == NULL) {
+		ret = -ENOMEM;
+		goto destroy_mmu;
+	}
+
+	mn->mmu = mmu;
+	mn->it.start = obj->userptr.ptr;
+	mn->it.last = mn->it.start + obj->base.size - 1;
+	mn->obj = obj;
+
+	ret = i915_mmu_notifier_add(mmu, mn);
+	if (ret)
+		goto free_mn;
+
+	obj->userptr.mn = mn;
+	return 0;
+
+free_mn:
+	kfree(mn);
+destroy_mmu:
+	mutex_lock(&obj->base.dev->struct_mutex);
+	if (--mmu->count == 0)
+		__i915_mmu_notifier_destroy(mmu);
+	mutex_unlock(&obj->base.dev->struct_mutex);
+	return ret;
+}
+
+#else
+
+static void
+i915_gem_userptr_release__mmu_notifier(struct drm_i915_gem_object *obj)
+{
+}
+
+static int
+i915_gem_userptr_init__mmu_notifier(struct drm_i915_gem_object *obj,
+				    unsigned flags)
+{
+	if ((flags & I915_USERPTR_UNSYNCHRONIZED) == 0)
+		return -ENODEV;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return 0;
+}
+#endif
+
+struct get_pages_work {
+	struct work_struct work;
+	struct drm_i915_gem_object *obj;
+	struct task_struct *task;
+};
+
+
+#if IS_ENABLED(CONFIG_SWIOTLB)
+#define swiotlb_active() swiotlb_nr_tbl()
+#else
+#define swiotlb_active() 0
+#endif
+
+static int
+st_set_pages(struct sg_table **st, struct page **pvec, int num_pages)
+{
+	struct scatterlist *sg;
+	int ret, n;
+
+	*st = kmalloc(sizeof(**st), GFP_KERNEL);
+	if (*st == NULL)
+		return -ENOMEM;
+
+	if (swiotlb_active()) {
+		ret = sg_alloc_table(*st, num_pages, GFP_KERNEL);
+		if (ret)
+			goto err;
+
+		for_each_sg((*st)->sgl, sg, num_pages, n)
+			sg_set_page(sg, pvec[n], PAGE_SIZE, 0);
+	} else {
+		ret = sg_alloc_table_from_pages(*st, pvec, num_pages,
+						0, num_pages << PAGE_SHIFT,
+						GFP_KERNEL);
+		if (ret)
+			goto err;
+	}
+
+	return 0;
+
+err:
+	kfree(*st);
+	*st = NULL;
+	return ret;
+}
+
+static void
+__i915_gem_userptr_get_pages_worker(struct work_struct *_work)
+{
+	struct get_pages_work *work = container_of(_work, typeof(*work), work);
+	struct drm_i915_gem_object *obj = work->obj;
+	struct drm_device *dev = obj->base.dev;
+	const int num_pages = obj->base.size >> PAGE_SHIFT;
+	struct page **pvec;
+	int pinned, ret;
+
+	ret = -ENOMEM;
+	pinned = 0;
+
+	pvec = kmalloc(num_pages*sizeof(struct page *),
+		       GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
+	if (pvec == NULL)
+		pvec = drm_malloc_ab(num_pages, sizeof(struct page *));
+	if (pvec != NULL) {
+		struct mm_struct *mm = obj->userptr.mm;
+
+		down_read(&mm->mmap_sem);
+		while (pinned < num_pages) {
+			ret = get_user_pages(work->task, mm,
+					     obj->userptr.ptr + pinned * PAGE_SIZE,
+					     num_pages - pinned,
+					     !obj->userptr.read_only, 0,
+					     pvec + pinned, NULL);
+			if (ret < 0)
+				break;
+
+			pinned += ret;
+		}
+		up_read(&mm->mmap_sem);
+	}
+
+	mutex_lock(&dev->struct_mutex);
+	if (obj->userptr.work != &work->work) {
+		ret = 0;
+	} else if (pinned == num_pages) {
+		ret = st_set_pages(&obj->pages, pvec, num_pages);
+		if (ret == 0) {
+			list_add_tail(&obj->global_list, &to_i915(dev)->mm.unbound_list);
+			pinned = 0;
+		}
+	}
+
+	obj->userptr.work = ERR_PTR(ret);
+	obj->userptr.workers--;
+	drm_gem_object_unreference(&obj->base);
+	mutex_unlock(&dev->struct_mutex);
+
+	release_pages(pvec, pinned, 0);
+	drm_free_large(pvec);
+
+	put_task_struct(work->task);
+	kfree(work);
+}
+
+static int
+i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
+{
+	const int num_pages = obj->base.size >> PAGE_SHIFT;
+	struct page **pvec;
+	int pinned, ret;
+
+	/* If userspace should engineer that these pages are replaced in
+	 * the vma between us binding this page into the GTT and completion
+	 * of rendering... Their loss. If they change the mapping of their
+	 * pages they need to create a new bo to point to the new vma.
+	 *
+	 * However, that still leaves open the possibility of the vma
+	 * being copied upon fork. Which falls under the same userspace
+	 * synchronisation issue as a regular bo, except that this time
+	 * the process may not be expecting that a particular piece of
+	 * memory is tied to the GPU.
+	 *
+	 * Fortunately, we can hook into the mmu_notifier in order to
+	 * discard the page references prior to anything nasty happening
+	 * to the vma (discard or cloning) which should prevent the more
+	 * egregious cases from causing harm.
+	 */
+
+	pvec = NULL;
+	pinned = 0;
+	if (obj->userptr.mm == current->mm) {
+		pvec = kmalloc(num_pages*sizeof(struct page *),
+			       GFP_TEMPORARY | __GFP_NOWARN | __GFP_NORETRY);
+		if (pvec == NULL) {
+			pvec = drm_malloc_ab(num_pages, sizeof(struct page *));
+			if (pvec == NULL)
+				return -ENOMEM;
+		}
+
+		pinned = __get_user_pages_fast(obj->userptr.ptr, num_pages,
+					       !obj->userptr.read_only, pvec);
+	}
+	if (pinned < num_pages) {
+		if (pinned < 0) {
+			ret = pinned;
+			pinned = 0;
+		} else {
+			/* Spawn a worker so that we can acquire the
+			 * user pages without holding our mutex. Access
+			 * to the user pages requires mmap_sem, and we have
+			 * a strict lock ordering of mmap_sem, struct_mutex -
+			 * we already hold struct_mutex here and so cannot
+			 * call gup without encountering a lock inversion.
+			 *
+			 * Userspace will keep on repeating the operation
+			 * (thanks to EAGAIN) until either we hit the fast
+			 * path or the worker completes. If the worker is
+			 * cancelled or superseded, the task is still run
+			 * but the results ignored. (This leads to
+			 * complications that we may have a stray object
+			 * refcount that we need to be wary of when
+			 * checking for existing objects during creation.)
+			 * If the worker encounters an error, it reports
+			 * that error back to this function through
+			 * obj->userptr.work = ERR_PTR.
+			 */
+			ret = -EAGAIN;
+			if (obj->userptr.work == NULL &&
+			    obj->userptr.workers < I915_GEM_USERPTR_MAX_WORKERS) {
+				struct get_pages_work *work;
+
+				work = kmalloc(sizeof(*work), GFP_KERNEL);
+				if (work != NULL) {
+					obj->userptr.work = &work->work;
+					obj->userptr.workers++;
+
+					work->obj = obj;
+					drm_gem_object_reference(&obj->base);
+
+					work->task = current;
+					get_task_struct(work->task);
+
+					INIT_WORK(&work->work, __i915_gem_userptr_get_pages_worker);
+					schedule_work(&work->work);
+				} else
+					ret = -ENOMEM;
+			} else {
+				if (IS_ERR(obj->userptr.work)) {
+					ret = PTR_ERR(obj->userptr.work);
+					obj->userptr.work = NULL;
+				}
+			}
+		}
+	} else {
+		ret = st_set_pages(&obj->pages, pvec, num_pages);
+		if (ret == 0) {
+			obj->userptr.work = NULL;
+			pinned = 0;
+		}
+	}
+
+	release_pages(pvec, pinned, 0);
+	drm_free_large(pvec);
+	return ret;
+}
+
+static void
+i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
+{
+	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(obj->userptr.work != NULL);
+
+	if (obj->madv != I915_MADV_WILLNEED)
+		obj->dirty = 0;
+
+	for_each_sg(obj->pages->sgl, sg, obj->pages->nents, i) {
+		struct page *page = sg_page(sg);
+
+		if (obj->dirty)
+			set_page_dirty(page);
+
+		mark_page_accessed(page);
+		page_cache_release(page);
+	}
+	obj->dirty = 0;
+
+	sg_free_table(obj->pages);
+	kfree(obj->pages);
+}
+
+static void
+i915_gem_userptr_release(struct drm_i915_gem_object *obj)
+{
+	i915_gem_userptr_release__mmu_notifier(obj);
+
+	if (obj->userptr.mm) {
+		mmput(obj->userptr.mm);
+		obj->userptr.mm = NULL;
+	}
+}
+
+static int
+i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
+{
+	if (obj->userptr.mn)
+		return 0;
+
+	return i915_gem_userptr_init__mmu_notifier(obj, 0);
+}
+
+static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
+	.dmabuf_export = i915_gem_userptr_dmabuf_export,
+	.get_pages = i915_gem_userptr_get_pages,
+	.put_pages = i915_gem_userptr_put_pages,
+	.release = i915_gem_userptr_release,
+};
+
+/**
+ * Creates a new mm object that wraps some normal memory from the process
+ * context - user memory.
+ *
+ * We impose several restrictions upon the memory being mapped
+ * into the GPU.
+ * 1. It must be page aligned (both start/end addresses, i.e ptr and size).
+ * 2. It cannot overlap any other userptr object in the same address space.
+ * 3. It must be normal system memory, not a pointer into another map of IO
+ *    space (e.g. it must not be a GTT mmapping of another object).
+ * 4. We only allow a bo as large as we could in theory map into the GTT,
+ *    that is we limit the size to the total size of the GTT.
+ * 5. The bo is marked as being snoopable. The backing pages are left
+ *    accessible directly by the CPU, but reads and writes by the GPU may
+ *    incur the cost of a snoop (unless you have an LLC architecture).
+ *
+ * Synchronisation between multiple users and the GPU is left to userspace
+ * through the normal set-domain-ioctl. The kernel will enforce that the
+ * GPU relinquishes the VMA before it is returned back to the system
+ * i.e. upon free(), munmap() or process termination. However, the userspace
+ * malloc() library may not immediately relinquish the VMA after free() and
+ * instead reuse it whilst the GPU is still reading and writing to the VMA.
+ * Caveat emptor.
+ *
+ * Also note, that the object created here is not currently a "first class"
+ * object, in that several ioctls are banned. These are the CPU access
+ * ioctls: mmap(), pwrite and pread. In practice, you are expected to use
+ * direct access via your pointer rather than use those ioctls.
+ *
+ * If you think this is a good interface to use to pass GPU memory between
+ * drivers, please use dma-buf instead. In fact, wherever possible use
+ * dma-buf instead.
+ */
+int
+i915_gem_userptr_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_gem_userptr *args = data;
+	struct drm_i915_gem_object *obj;
+	int ret;
+	u32 handle;
+
+	if (args->flags & ~(I915_USERPTR_READ_ONLY |
+			    I915_USERPTR_UNSYNCHRONIZED))
+		return -EINVAL;
+
+	if (offset_in_page(args->user_ptr | args->user_size))
+		return -EINVAL;
+
+	if (args->user_size > dev_priv->gtt.base.total)
+		return -E2BIG;
+
+	if (!access_ok(args->flags & I915_USERPTR_READ_ONLY ? VERIFY_READ : VERIFY_WRITE,
+		       (char __user *)(unsigned long)args->user_ptr, args->user_size))
+		return -EFAULT;
+
+	if (args->flags & I915_USERPTR_READ_ONLY) {
+		/* On almost all of the current hw, we cannot tell the GPU that a
+		 * page is readonly, so this is just a placeholder in the uAPI.
+		 */
+		return -ENODEV;
+	}
+
+	/* Allocate the new object */
+	obj = i915_gem_object_alloc(dev);
+	if (obj == NULL)
+		return -ENOMEM;
+
+	drm_gem_private_object_init(dev, &obj->base, args->user_size);
+	i915_gem_object_init(obj, &i915_gem_userptr_ops);
+	obj->cache_level = I915_CACHE_LLC;
+	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
+	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
+
+	obj->userptr.ptr = args->user_ptr;
+	obj->userptr.read_only = !!(args->flags & I915_USERPTR_READ_ONLY);
+
+	/* And keep a pointer to the current->mm for resolving the user pages
+	 * at binding. This means that we need to hook into the mmu_notifier
+	 * in order to detect if the mmu is destroyed.
+	 */
+	ret = -ENOMEM;
+	if ((obj->userptr.mm = get_task_mm(current)))
+		ret = i915_gem_userptr_init__mmu_notifier(obj, args->flags);
+	if (ret == 0)
+		ret = drm_gem_handle_create(file, &obj->base, &handle);
+
+	/* drop reference from allocate - handle holds it now */
+	drm_gem_object_unreference_unlocked(&obj->base);
+	if (ret)
+		return ret;
+
+	args->handle = handle;
+	return 0;
+}
+
+int
+i915_gem_init_userptr(struct drm_device *dev)
+{
+#if defined(CONFIG_MMU_NOTIFIER)
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	hash_init(dev_priv->mmu_notifiers);
+#endif
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 12f1d43b2d6..66cf41765bf 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -42,6 +42,7 @@ static const char *ring_str(int ring)
 	case VCS: return "bsd";
 	case BCS: return "blt";
 	case VECS: return "vebox";
+	case VCS2: return "bsd2";
 	default: return "";
 	}
 }
@@ -204,6 +205,7 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 		err_puts(m, tiling_flag(err->tiling));
 		err_puts(m, dirty_flag(err->dirty));
 		err_puts(m, purgeable_flag(err->purgeable));
+		err_puts(m, err->userptr ? " userptr" : "");
 		err_puts(m, err->ring != -1 ? " " : "");
 		err_puts(m, ring_str(err->ring));
 		err_puts(m, i915_cache_level_str(err->cache_level));
@@ -257,7 +259,8 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "  INSTPS: 0x%08x\n", ring->instps);
 	}
 	err_printf(m, "  INSTPM: 0x%08x\n", ring->instpm);
-	err_printf(m, "  FADDR: 0x%08x\n", ring->faddr);
+	err_printf(m, "  FADDR: 0x%08x %08x\n", upper_32_bits(ring->faddr),
+		   lower_32_bits(ring->faddr));
 	if (INTEL_INFO(dev)->gen >= 6) {
 		err_printf(m, "  RC PSMI: 0x%08x\n", ring->rc_psmi);
 		err_printf(m, "  FAULT_REG: 0x%08x\n", ring->fault_reg);
@@ -452,16 +455,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 			err_printf(m, "%s --- HW Context = 0x%08x\n",
 				   dev_priv->ring[i].name,
 				   obj->gtt_offset);
-			offset = 0;
-			for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
-				err_printf(m, "[%04x] %08x %08x %08x %08x\n",
-					   offset,
-					   obj->pages[0][elt],
-					   obj->pages[0][elt+1],
-					   obj->pages[0][elt+2],
-					   obj->pages[0][elt+3]);
-					offset += 16;
-			}
+			print_error_obj(m, obj);
 		}
 	}
 
@@ -648,6 +642,7 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 	err->tiling = obj->tiling_mode;
 	err->dirty = obj->dirty;
 	err->purgeable = obj->madv != I915_MADV_WILLNEED;
+	err->userptr = obj->userptr.mm != NULL;
 	err->ring = obj->ring ? obj->ring->id : -1;
 	err->cache_level = obj->cache_level;
 }
@@ -752,7 +747,7 @@ static void i915_gem_record_fences(struct drm_device *dev,
 }
 
 static void i915_record_ring_state(struct drm_device *dev,
-				   struct intel_ring_buffer *ring,
+				   struct intel_engine_cs *ring,
 				   struct drm_i915_error_ring *ering)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -764,14 +759,14 @@ static void i915_record_ring_state(struct drm_device *dev,
 			= I915_READ(RING_SYNC_0(ring->mmio_base));
 		ering->semaphore_mboxes[1]
 			= I915_READ(RING_SYNC_1(ring->mmio_base));
-		ering->semaphore_seqno[0] = ring->sync_seqno[0];
-		ering->semaphore_seqno[1] = ring->sync_seqno[1];
+		ering->semaphore_seqno[0] = ring->semaphore.sync_seqno[0];
+		ering->semaphore_seqno[1] = ring->semaphore.sync_seqno[1];
 	}
 
 	if (HAS_VEBOX(dev)) {
 		ering->semaphore_mboxes[2] =
 			I915_READ(RING_SYNC_2(ring->mmio_base));
-		ering->semaphore_seqno[2] = ring->sync_seqno[2];
+		ering->semaphore_seqno[2] = ring->semaphore.sync_seqno[2];
 	}
 
 	if (INTEL_INFO(dev)->gen >= 4) {
@@ -781,8 +776,10 @@ static void i915_record_ring_state(struct drm_device *dev,
 		ering->instdone = I915_READ(RING_INSTDONE(ring->mmio_base));
 		ering->instps = I915_READ(RING_INSTPS(ring->mmio_base));
 		ering->bbaddr = I915_READ(RING_BBADDR(ring->mmio_base));
-		if (INTEL_INFO(dev)->gen >= 8)
+		if (INTEL_INFO(dev)->gen >= 8) {
+			ering->faddr |= (u64) I915_READ(RING_DMA_FADD_UDW(ring->mmio_base)) << 32;
 			ering->bbaddr |= (u64) I915_READ(RING_BBADDR_UDW(ring->mmio_base)) << 32;
+		}
 		ering->bbstate = I915_READ(RING_BBSTATE(ring->mmio_base));
 	} else {
 		ering->faddr = I915_READ(DMA_FADD_I8XX);
@@ -828,8 +825,8 @@ static void i915_record_ring_state(struct drm_device *dev,
 		ering->hws = I915_READ(mmio);
 	}
 
-	ering->cpu_ring_head = ring->head;
-	ering->cpu_ring_tail = ring->tail;
+	ering->cpu_ring_head = ring->buffer->head;
+	ering->cpu_ring_tail = ring->buffer->tail;
 
 	ering->hangcheck_score = ring->hangcheck.score;
 	ering->hangcheck_action = ring->hangcheck.action;
@@ -862,7 +859,7 @@ static void i915_record_ring_state(struct drm_device *dev,
 }
 
 
-static void i915_gem_record_active_context(struct intel_ring_buffer *ring,
+static void i915_gem_record_active_context(struct intel_engine_cs *ring,
 					   struct drm_i915_error_state *error,
 					   struct drm_i915_error_ring *ering)
 {
@@ -875,10 +872,7 @@ static void i915_gem_record_active_context(struct intel_ring_buffer *ring,
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		if ((error->ccid & PAGE_MASK) == i915_gem_obj_ggtt_offset(obj)) {
-			ering->ctx = i915_error_object_create_sized(dev_priv,
-								    obj,
-								    &dev_priv->gtt.base,
-								    1);
+			ering->ctx = i915_error_ggtt_object_create(dev_priv, obj);
 			break;
 		}
 	}
@@ -892,7 +886,9 @@ static void i915_gem_record_rings(struct drm_device *dev,
 	int i, count;
 
 	for (i = 0; i < I915_NUM_RINGS; i++) {
-		struct intel_ring_buffer *ring = &dev_priv->ring[i];
+		struct intel_engine_cs *ring = &dev_priv->ring[i];
+
+		error->ring[i].pid = -1;
 
 		if (ring->dev == NULL)
 			continue;
@@ -901,7 +897,6 @@ static void i915_gem_record_rings(struct drm_device *dev,
 
 		i915_record_ring_state(dev, ring, &error->ring[i]);
 
-		error->ring[i].pid = -1;
 		request = i915_gem_find_active_request(ring);
 		if (request) {
 			/* We need to copy these to an anonymous buffer
@@ -936,7 +931,7 @@ static void i915_gem_record_rings(struct drm_device *dev,
 		}
 
 		error->ring[i].ringbuffer =
-			i915_error_ggtt_object_create(dev_priv, ring->obj);
+			i915_error_ggtt_object_create(dev_priv, ring->buffer->obj);
 
 		if (ring->status_page.obj)
 			error->ring[i].hws_page =
@@ -1037,7 +1032,6 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 				   struct drm_i915_error_state *error)
 {
 	struct drm_device *dev = dev_priv->dev;
-	int pipe;
 
 	/* General organization
 	 * 1. Registers specific to a single generation
@@ -1062,9 +1056,6 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 		error->gfx_mode = I915_READ(GFX_MODE);
 	}
 
-	if (IS_GEN2(dev))
-		error->ier = I915_READ16(IER);
-
 	/* 2: Registers which belong to multiple generations */
 	if (INTEL_INFO(dev)->gen >= 7)
 		error->forcewake = I915_READ(FORCEWAKE_MT);
@@ -1088,9 +1079,10 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 	if (HAS_PCH_SPLIT(dev))
 		error->ier = I915_READ(DEIER) | I915_READ(GTIER);
 	else {
-		error->ier = I915_READ(IER);
-		for_each_pipe(pipe)
-			error->pipestat[pipe] = I915_READ(PIPESTAT(pipe));
+		if (IS_GEN2(dev))
+			error->ier = I915_READ16(IER);
+		else
+			error->ier = I915_READ(IER);
 	}
 
 	/* 4: Everything else */
diff --git a/drivers/gpu/drm/i915/i915_ioc32.c b/drivers/gpu/drm/i915/i915_ioc32.c
index 3c59584161c..2e0613e2625 100644
--- a/drivers/gpu/drm/i915/i915_ioc32.c
+++ b/drivers/gpu/drm/i915/i915_ioc32.c
@@ -208,7 +208,7 @@ long i915_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	if (nr < DRM_COMMAND_BASE)
 		return drm_compat_ioctl(filp, cmd, arg);
 
-	if (nr < DRM_COMMAND_BASE + DRM_ARRAY_SIZE(i915_compat_ioctls))
+	if (nr < DRM_COMMAND_BASE + ARRAY_SIZE(i915_compat_ioctls))
 		fn = i915_compat_ioctls[nr - DRM_COMMAND_BASE];
 
 	if (fn != NULL)
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0b99de95593..c05c84f3f09 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -80,17 +80,64 @@ static const u32 hpd_status_i915[] = { /* i915 and valleyview are the same */
 	[HPD_PORT_D] = PORTD_HOTPLUG_INT_STATUS
 };
 
+/* IIR can theoretically queue up two events. Be paranoid. */
+#define GEN8_IRQ_RESET_NDX(type, which) do { \
+	I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \
+	POSTING_READ(GEN8_##type##_IMR(which)); \
+	I915_WRITE(GEN8_##type##_IER(which), 0); \
+	I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \
+	POSTING_READ(GEN8_##type##_IIR(which)); \
+	I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \
+	POSTING_READ(GEN8_##type##_IIR(which)); \
+} while (0)
+
+#define GEN5_IRQ_RESET(type) do { \
+	I915_WRITE(type##IMR, 0xffffffff); \
+	POSTING_READ(type##IMR); \
+	I915_WRITE(type##IER, 0); \
+	I915_WRITE(type##IIR, 0xffffffff); \
+	POSTING_READ(type##IIR); \
+	I915_WRITE(type##IIR, 0xffffffff); \
+	POSTING_READ(type##IIR); \
+} while (0)
+
+/*
+ * We should clear IMR at preinstall/uninstall, and just check at postinstall.
+ */
+#define GEN5_ASSERT_IIR_IS_ZERO(reg) do { \
+	u32 val = I915_READ(reg); \
+	if (val) { \
+		WARN(1, "Interrupt register 0x%x is not zero: 0x%08x\n", \
+		     (reg), val); \
+		I915_WRITE((reg), 0xffffffff); \
+		POSTING_READ(reg); \
+		I915_WRITE((reg), 0xffffffff); \
+		POSTING_READ(reg); \
+	} \
+} while (0)
+
+#define GEN8_IRQ_INIT_NDX(type, which, imr_val, ier_val) do { \
+	GEN5_ASSERT_IIR_IS_ZERO(GEN8_##type##_IIR(which)); \
+	I915_WRITE(GEN8_##type##_IMR(which), (imr_val)); \
+	I915_WRITE(GEN8_##type##_IER(which), (ier_val)); \
+	POSTING_READ(GEN8_##type##_IER(which)); \
+} while (0)
+
+#define GEN5_IRQ_INIT(type, imr_val, ier_val) do { \
+	GEN5_ASSERT_IIR_IS_ZERO(type##IIR); \
+	I915_WRITE(type##IMR, (imr_val)); \
+	I915_WRITE(type##IER, (ier_val)); \
+	POSTING_READ(type##IER); \
+} while (0)
+
 /* For display hotplug interrupt */
 static void
 ironlake_enable_display_irq(struct drm_i915_private *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pm.irqs_disabled) {
-		WARN(1, "IRQs disabled\n");
-		dev_priv->pm.regsave.deimr &= ~mask;
+	if (WARN_ON(dev_priv->pm.irqs_disabled))
 		return;
-	}
 
 	if ((dev_priv->irq_mask & mask) != 0) {
 		dev_priv->irq_mask &= ~mask;
@@ -104,11 +151,8 @@ ironlake_disable_display_irq(struct drm_i915_private *dev_priv, u32 mask)
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pm.irqs_disabled) {
-		WARN(1, "IRQs disabled\n");
-		dev_priv->pm.regsave.deimr |= mask;
+	if (WARN_ON(dev_priv->pm.irqs_disabled))
 		return;
-	}
 
 	if ((dev_priv->irq_mask & mask) != mask) {
 		dev_priv->irq_mask |= mask;
@@ -129,13 +173,8 @@ static void ilk_update_gt_irq(struct drm_i915_private *dev_priv,
 {
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pm.irqs_disabled) {
-		WARN(1, "IRQs disabled\n");
-		dev_priv->pm.regsave.gtimr &= ~interrupt_mask;
-		dev_priv->pm.regsave.gtimr |= (~enabled_irq_mask &
-						interrupt_mask);
+	if (WARN_ON(dev_priv->pm.irqs_disabled))
 		return;
-	}
 
 	dev_priv->gt_irq_mask &= ~interrupt_mask;
 	dev_priv->gt_irq_mask |= (~enabled_irq_mask & interrupt_mask);
@@ -167,13 +206,8 @@ static void snb_update_pm_irq(struct drm_i915_private *dev_priv,
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pm.irqs_disabled) {
-		WARN(1, "IRQs disabled\n");
-		dev_priv->pm.regsave.gen6_pmimr &= ~interrupt_mask;
-		dev_priv->pm.regsave.gen6_pmimr |= (~enabled_irq_mask &
-						     interrupt_mask);
+	if (WARN_ON(dev_priv->pm.irqs_disabled))
 		return;
-	}
 
 	new_val = dev_priv->pm_irq_mask;
 	new_val &= ~interrupt_mask;
@@ -214,6 +248,46 @@ static bool ivb_can_enable_err_int(struct drm_device *dev)
 	return true;
 }
 
+/**
+  * bdw_update_pm_irq - update GT interrupt 2
+  * @dev_priv: driver private
+  * @interrupt_mask: mask of interrupt bits to update
+  * @enabled_irq_mask: mask of interrupt bits to enable
+  *
+  * Copied from the snb function, updated with relevant register offsets
+  */
+static void bdw_update_pm_irq(struct drm_i915_private *dev_priv,
+			      uint32_t interrupt_mask,
+			      uint32_t enabled_irq_mask)
+{
+	uint32_t new_val;
+
+	assert_spin_locked(&dev_priv->irq_lock);
+
+	if (WARN_ON(dev_priv->pm.irqs_disabled))
+		return;
+
+	new_val = dev_priv->pm_irq_mask;
+	new_val &= ~interrupt_mask;
+	new_val |= (~enabled_irq_mask & interrupt_mask);
+
+	if (new_val != dev_priv->pm_irq_mask) {
+		dev_priv->pm_irq_mask = new_val;
+		I915_WRITE(GEN8_GT_IMR(2), dev_priv->pm_irq_mask);
+		POSTING_READ(GEN8_GT_IMR(2));
+	}
+}
+
+void bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	bdw_update_pm_irq(dev_priv, mask, mask);
+}
+
+void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask)
+{
+	bdw_update_pm_irq(dev_priv, mask, 0);
+}
+
 static bool cpt_can_enable_serr_int(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -232,16 +306,51 @@ static bool cpt_can_enable_serr_int(struct drm_device *dev)
 	return true;
 }
 
-static void i9xx_clear_fifo_underrun(struct drm_device *dev, enum pipe pipe)
+void i9xx_check_fifo_underruns(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *crtc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+
+	for_each_intel_crtc(dev, crtc) {
+		u32 reg = PIPESTAT(crtc->pipe);
+		u32 pipestat;
+
+		if (crtc->cpu_fifo_underrun_disabled)
+			continue;
+
+		pipestat = I915_READ(reg) & 0xffff0000;
+		if ((pipestat & PIPE_FIFO_UNDERRUN_STATUS) == 0)
+			continue;
+
+		I915_WRITE(reg, pipestat | PIPE_FIFO_UNDERRUN_STATUS);
+		POSTING_READ(reg);
+
+		DRM_ERROR("pipe %c underrun\n", pipe_name(crtc->pipe));
+	}
+
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+}
+
+static void i9xx_set_fifo_underrun_reporting(struct drm_device *dev,
+					     enum pipe pipe,
+					     bool enable, bool old)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 reg = PIPESTAT(pipe);
-	u32 pipestat = I915_READ(reg) & 0x7fff0000;
+	u32 pipestat = I915_READ(reg) & 0xffff0000;
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	I915_WRITE(reg, pipestat | PIPE_FIFO_UNDERRUN_STATUS);
-	POSTING_READ(reg);
+	if (enable) {
+		I915_WRITE(reg, pipestat | PIPE_FIFO_UNDERRUN_STATUS);
+		POSTING_READ(reg);
+	} else {
+		if (old && pipestat & PIPE_FIFO_UNDERRUN_STATUS)
+			DRM_ERROR("pipe %c underrun\n", pipe_name(pipe));
+	}
 }
 
 static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev,
@@ -258,7 +367,8 @@ static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev,
 }
 
 static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev,
-						  enum pipe pipe, bool enable)
+						  enum pipe pipe,
+						  bool enable, bool old)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	if (enable) {
@@ -269,15 +379,12 @@ static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev,
 
 		ironlake_enable_display_irq(dev_priv, DE_ERR_INT_IVB);
 	} else {
-		bool was_enabled = !(I915_READ(DEIMR) & DE_ERR_INT_IVB);
-
-		/* Change the state _after_ we've read out the current one. */
 		ironlake_disable_display_irq(dev_priv, DE_ERR_INT_IVB);
 
-		if (!was_enabled &&
-		    (I915_READ(GEN7_ERR_INT) & ERR_INT_FIFO_UNDERRUN(pipe))) {
-			DRM_DEBUG_KMS("uncleared fifo underrun on pipe %c\n",
-				      pipe_name(pipe));
+		if (old &&
+		    I915_READ(GEN7_ERR_INT) & ERR_INT_FIFO_UNDERRUN(pipe)) {
+			DRM_ERROR("uncleared fifo underrun on pipe %c\n",
+				  pipe_name(pipe));
 		}
 	}
 }
@@ -313,14 +420,8 @@ static void ibx_display_interrupt_update(struct drm_i915_private *dev_priv,
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (dev_priv->pm.irqs_disabled &&
-	    (interrupt_mask & SDE_HOTPLUG_MASK_CPT)) {
-		WARN(1, "IRQs disabled\n");
-		dev_priv->pm.regsave.sdeimr &= ~interrupt_mask;
-		dev_priv->pm.regsave.sdeimr |= (~enabled_irq_mask &
-						 interrupt_mask);
+	if (WARN_ON(dev_priv->pm.irqs_disabled))
 		return;
-	}
 
 	I915_WRITE(SDEIMR, sdeimr);
 	POSTING_READ(SDEIMR);
@@ -346,7 +447,7 @@ static void ibx_set_fifo_underrun_reporting(struct drm_device *dev,
 
 static void cpt_set_fifo_underrun_reporting(struct drm_device *dev,
 					    enum transcoder pch_transcoder,
-					    bool enable)
+					    bool enable, bool old)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -359,16 +460,12 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev,
 
 		ibx_enable_display_interrupt(dev_priv, SDE_ERROR_CPT);
 	} else {
-		uint32_t tmp = I915_READ(SERR_INT);
-		bool was_enabled = !(I915_READ(SDEIMR) & SDE_ERROR_CPT);
-
-		/* Change the state _after_ we've read out the current one. */
 		ibx_disable_display_interrupt(dev_priv, SDE_ERROR_CPT);
 
-		if (!was_enabled &&
-		    (tmp & SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder))) {
-			DRM_DEBUG_KMS("uncleared pch fifo underrun on pch transcoder %c\n",
-				      transcoder_name(pch_transcoder));
+		if (old && I915_READ(SERR_INT) &
+		    SERR_INT_TRANS_FIFO_UNDERRUN(pch_transcoder)) {
+			DRM_ERROR("uncleared pch fifo underrun on pch transcoder %c\n",
+				  transcoder_name(pch_transcoder));
 		}
 	}
 }
@@ -387,34 +484,29 @@ static void cpt_set_fifo_underrun_reporting(struct drm_device *dev,
  *
  * Returns the previous state of underrun reporting.
  */
-bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
-					     enum pipe pipe, bool enable)
+static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
+						    enum pipe pipe, bool enable)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe];
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	bool ret;
+	bool old;
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	ret = !intel_crtc->cpu_fifo_underrun_disabled;
-
-	if (enable == ret)
-		goto done;
-
+	old = !intel_crtc->cpu_fifo_underrun_disabled;
 	intel_crtc->cpu_fifo_underrun_disabled = !enable;
 
-	if (enable && (INTEL_INFO(dev)->gen < 5 || IS_VALLEYVIEW(dev)))
-		i9xx_clear_fifo_underrun(dev, pipe);
+	if (INTEL_INFO(dev)->gen < 5 || IS_VALLEYVIEW(dev))
+		i9xx_set_fifo_underrun_reporting(dev, pipe, enable, old);
 	else if (IS_GEN5(dev) || IS_GEN6(dev))
 		ironlake_set_fifo_underrun_reporting(dev, pipe, enable);
 	else if (IS_GEN7(dev))
-		ivybridge_set_fifo_underrun_reporting(dev, pipe, enable);
+		ivybridge_set_fifo_underrun_reporting(dev, pipe, enable, old);
 	else if (IS_GEN8(dev))
 		broadwell_set_fifo_underrun_reporting(dev, pipe, enable);
 
-done:
-	return ret;
+	return old;
 }
 
 bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
@@ -463,7 +555,7 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev,
 	struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pch_transcoder];
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	unsigned long flags;
-	bool ret;
+	bool old;
 
 	/*
 	 * NOTE: Pre-LPT has a fixed cpu pipe -> pch transcoder mapping, but LPT
@@ -476,21 +568,16 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev,
 
 	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 
-	ret = !intel_crtc->pch_fifo_underrun_disabled;
-
-	if (enable == ret)
-		goto done;
-
+	old = !intel_crtc->pch_fifo_underrun_disabled;
 	intel_crtc->pch_fifo_underrun_disabled = !enable;
 
 	if (HAS_PCH_IBX(dev))
 		ibx_set_fifo_underrun_reporting(dev, pch_transcoder, enable);
 	else
-		cpt_set_fifo_underrun_reporting(dev, pch_transcoder, enable);
+		cpt_set_fifo_underrun_reporting(dev, pch_transcoder, enable, old);
 
-done:
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
-	return ret;
+	return old;
 }
 
 
@@ -503,8 +590,10 @@ __i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (WARN_ON_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK ||
-	                 status_mask & ~PIPESTAT_INT_STATUS_MASK))
+	if (WARN_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK ||
+		      status_mask & ~PIPESTAT_INT_STATUS_MASK,
+		      "pipe %c: enable_mask=0x%x, status_mask=0x%x\n",
+		      pipe_name(pipe), enable_mask, status_mask))
 		return;
 
 	if ((pipestat & enable_mask) == enable_mask)
@@ -527,8 +616,10 @@ __i915_disable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
 
 	assert_spin_locked(&dev_priv->irq_lock);
 
-	if (WARN_ON_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK ||
-	                 status_mask & ~PIPESTAT_INT_STATUS_MASK))
+	if (WARN_ONCE(enable_mask & ~PIPESTAT_INT_ENABLE_MASK ||
+		      status_mask & ~PIPESTAT_INT_STATUS_MASK,
+		      "pipe %c: enable_mask=0x%x, status_mask=0x%x\n",
+		      pipe_name(pipe), enable_mask, status_mask))
 		return;
 
 	if ((pipestat & enable_mask) == 0)
@@ -546,11 +637,17 @@ static u32 vlv_get_pipestat_enable_mask(struct drm_device *dev, u32 status_mask)
 	u32 enable_mask = status_mask << 16;
 
 	/*
-	 * On pipe A we don't support the PSR interrupt yet, on pipe B the
-	 * same bit MBZ.
+	 * On pipe A we don't support the PSR interrupt yet,
+	 * on pipe B and C the same bit MBZ.
 	 */
 	if (WARN_ON_ONCE(status_mask & PIPE_A_PSR_STATUS_VLV))
 		return 0;
+	/*
+	 * On pipe B and C we don't support the PSR interrupt yet, on pipe
+	 * A the same bit is for perf counters which we don't use either.
+	 */
+	if (WARN_ON_ONCE(status_mask & PIPE_B_PSR_STATUS_VLV))
+		return 0;
 
 	enable_mask &= ~(PIPE_FIFO_UNDERRUN_STATUS |
 			 SPRITE0_FLIP_DONE_INT_EN_VLV |
@@ -637,6 +734,56 @@ i915_pipe_enabled(struct drm_device *dev, int pipe)
 	}
 }
 
+/*
+ * This timing diagram depicts the video signal in and
+ * around the vertical blanking period.
+ *
+ * Assumptions about the fictitious mode used in this example:
+ *  vblank_start >= 3
+ *  vsync_start = vblank_start + 1
+ *  vsync_end = vblank_start + 2
+ *  vtotal = vblank_start + 3
+ *
+ *           start of vblank:
+ *           latch double buffered registers
+ *           increment frame counter (ctg+)
+ *           generate start of vblank interrupt (gen4+)
+ *           |
+ *           |          frame start:
+ *           |          generate frame start interrupt (aka. vblank interrupt) (gmch)
+ *           |          may be shifted forward 1-3 extra lines via PIPECONF
+ *           |          |
+ *           |          |  start of vsync:
+ *           |          |  generate vsync interrupt
+ *           |          |  |
+ * ___xxxx___    ___xxxx___    ___xxxx___    ___xxxx___    ___xxxx___    ___xxxx
+ *       .   \hs/   .      \hs/          \hs/          \hs/   .      \hs/
+ * ----va---> <-----------------vb--------------------> <--------va-------------
+ *       |          |       <----vs----->                     |
+ * -vbs-----> <---vbs+1---> <---vbs+2---> <-----0-----> <-----1-----> <-----2--- (scanline counter gen2)
+ * -vbs-2---> <---vbs-1---> <---vbs-----> <---vbs+1---> <---vbs+2---> <-----0--- (scanline counter gen3+)
+ * -vbs-2---> <---vbs-2---> <---vbs-1---> <---vbs-----> <---vbs+1---> <---vbs+2- (scanline counter hsw+ hdmi)
+ *       |          |                                         |
+ *       last visible pixel                                   first visible pixel
+ *                  |                                         increment frame counter (gen3/4)
+ *                  pixel counter = vblank_start * htotal     pixel counter = 0 (gen3/4)
+ *
+ * x  = horizontal active
+ * _  = horizontal blanking
+ * hs = horizontal sync
+ * va = vertical active
+ * vb = vertical blanking
+ * vs = vertical sync
+ * vbs = vblank_start (number)
+ *
+ * Summary:
+ * - most events happen at the start of horizontal sync
+ * - frame start happens at the start of horizontal blank, 1-4 lines
+ *   (depending on PIPECONF settings) after the start of vblank
+ * - gen3/4 pixel and frame counter are synchronized with the start
+ *   of horizontal active on the first line of vertical active
+ */
+
 static u32 i8xx_get_vblank_counter(struct drm_device *dev, int pipe)
 {
 	/* Gen2 doesn't have a hardware frame counter */
@@ -651,7 +798,7 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long high_frame;
 	unsigned long low_frame;
-	u32 high1, high2, low, pixel, vbl_start;
+	u32 high1, high2, low, pixel, vbl_start, hsync_start, htotal;
 
 	if (!i915_pipe_enabled(dev, pipe)) {
 		DRM_DEBUG_DRIVER("trying to get vblank count for disabled "
@@ -665,17 +812,28 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe)
 		const struct drm_display_mode *mode =
 			&intel_crtc->config.adjusted_mode;
 
-		vbl_start = mode->crtc_vblank_start * mode->crtc_htotal;
+		htotal = mode->crtc_htotal;
+		hsync_start = mode->crtc_hsync_start;
+		vbl_start = mode->crtc_vblank_start;
+		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+			vbl_start = DIV_ROUND_UP(vbl_start, 2);
 	} else {
 		enum transcoder cpu_transcoder = (enum transcoder) pipe;
-		u32 htotal;
 
 		htotal = ((I915_READ(HTOTAL(cpu_transcoder)) >> 16) & 0x1fff) + 1;
+		hsync_start = (I915_READ(HSYNC(cpu_transcoder))  & 0x1fff) + 1;
 		vbl_start = (I915_READ(VBLANK(cpu_transcoder)) & 0x1fff) + 1;
-
-		vbl_start *= htotal;
+		if ((I915_READ(PIPECONF(cpu_transcoder)) &
+		     PIPECONF_INTERLACE_MASK) != PIPECONF_PROGRESSIVE)
+			vbl_start = DIV_ROUND_UP(vbl_start, 2);
 	}
 
+	/* Convert to pixel count */
+	vbl_start *= htotal;
+
+	/* Start of vblank event occurs at start of hsync */
+	vbl_start -= htotal - hsync_start;
+
 	high_frame = PIPEFRAME(pipe);
 	low_frame = PIPEFRAMEPIXEL(pipe);
 
@@ -719,24 +877,28 @@ static u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe)
 /* raw reads, only for fast reads of display block, no need for forcewake etc. */
 #define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__))
 
-static bool ilk_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe)
+static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 {
+	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	uint32_t status;
-	int reg;
+	const struct drm_display_mode *mode = &crtc->config.adjusted_mode;
+	enum pipe pipe = crtc->pipe;
+	int position, vtotal;
 
-	if (INTEL_INFO(dev)->gen >= 8) {
-		status = GEN8_PIPE_VBLANK;
-		reg = GEN8_DE_PIPE_ISR(pipe);
-	} else if (INTEL_INFO(dev)->gen >= 7) {
-		status = DE_PIPE_VBLANK_IVB(pipe);
-		reg = DEISR;
-	} else {
-		status = DE_PIPE_VBLANK(pipe);
-		reg = DEISR;
-	}
+	vtotal = mode->crtc_vtotal;
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		vtotal /= 2;
 
-	return __raw_i915_read32(dev_priv, reg) & status;
+	if (IS_GEN2(dev))
+		position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN2;
+	else
+		position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
+
+	/*
+	 * See update_scanline_offset() for the details on the
+	 * scanline_offset adjustment.
+	 */
+	return (position + crtc->scanline_offset) % vtotal;
 }
 
 static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
@@ -748,7 +910,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	const struct drm_display_mode *mode = &intel_crtc->config.adjusted_mode;
 	int position;
-	int vbl_start, vbl_end, htotal, vtotal;
+	int vbl_start, vbl_end, hsync_start, htotal, vtotal;
 	bool in_vbl = true;
 	int ret = 0;
 	unsigned long irqflags;
@@ -760,6 +922,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 	}
 
 	htotal = mode->crtc_htotal;
+	hsync_start = mode->crtc_hsync_start;
 	vtotal = mode->crtc_vtotal;
 	vbl_start = mode->crtc_vblank_start;
 	vbl_end = mode->crtc_vblank_end;
@@ -778,7 +941,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 	 * following code must not block on uncore.lock.
 	 */
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
-	
+
 	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
 
 	/* Get optional system timestamp before query. */
@@ -789,68 +952,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 		/* No obvious pixelcount register. Only query vertical
 		 * scanout position from Display scan line register.
 		 */
-		if (IS_GEN2(dev))
-			position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN2;
-		else
-			position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
-
-		if (HAS_DDI(dev)) {
-			/*
-			 * On HSW HDMI outputs there seems to be a 2 line
-			 * difference, whereas eDP has the normal 1 line
-			 * difference that earlier platforms have. External
-			 * DP is unknown. For now just check for the 2 line
-			 * difference case on all output types on HSW+.
-			 *
-			 * This might misinterpret the scanline counter being
-			 * one line too far along on eDP, but that's less
-			 * dangerous than the alternative since that would lead
-			 * the vblank timestamp code astray when it sees a
-			 * scanline count before vblank_start during a vblank
-			 * interrupt.
-			 */
-			in_vbl = ilk_pipe_in_vblank_locked(dev, pipe);
-			if ((in_vbl && (position == vbl_start - 2 ||
-					position == vbl_start - 1)) ||
-			    (!in_vbl && (position == vbl_end - 2 ||
-					 position == vbl_end - 1)))
-				position = (position + 2) % vtotal;
-		} else if (HAS_PCH_SPLIT(dev)) {
-			/*
-			 * The scanline counter increments at the leading edge
-			 * of hsync, ie. it completely misses the active portion
-			 * of the line. Fix up the counter at both edges of vblank
-			 * to get a more accurate picture whether we're in vblank
-			 * or not.
-			 */
-			in_vbl = ilk_pipe_in_vblank_locked(dev, pipe);
-			if ((in_vbl && position == vbl_start - 1) ||
-			    (!in_vbl && position == vbl_end - 1))
-				position = (position + 1) % vtotal;
-		} else {
-			/*
-			 * ISR vblank status bits don't work the way we'd want
-			 * them to work on non-PCH platforms (for
-			 * ilk_pipe_in_vblank_locked()), and there doesn't
-			 * appear any other way to determine if we're currently
-			 * in vblank.
-			 *
-			 * Instead let's assume that we're already in vblank if
-			 * we got called from the vblank interrupt and the
-			 * scanline counter value indicates that we're on the
-			 * line just prior to vblank start. This should result
-			 * in the correct answer, unless the vblank interrupt
-			 * delivery really got delayed for almost exactly one
-			 * full frame/field.
-			 */
-			if (flags & DRM_CALLED_FROM_VBLIRQ &&
-			    position == vbl_start - 1) {
-				position = (position + 1) % vtotal;
-
-				/* Signal this correction as "applied". */
-				ret |= 0x8;
-			}
-		}
+		position = __intel_get_crtc_scanline(intel_crtc);
 	} else {
 		/* Have access to pixelcount since start of frame.
 		 * We can split this into vertical and horizontal
@@ -862,6 +964,29 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 		vbl_start *= htotal;
 		vbl_end *= htotal;
 		vtotal *= htotal;
+
+		/*
+		 * In interlaced modes, the pixel counter counts all pixels,
+		 * so one field will have htotal more pixels. In order to avoid
+		 * the reported position from jumping backwards when the pixel
+		 * counter is beyond the length of the shorter field, just
+		 * clamp the position the length of the shorter field. This
+		 * matches how the scanline counter based position works since
+		 * the scanline counter doesn't count the two half lines.
+		 */
+		if (position >= vtotal)
+			position = vtotal - 1;
+
+		/*
+		 * Start of vblank interrupt is triggered at start of hsync,
+		 * just prior to the first active line of vblank. However we
+		 * consider lines to start at the leading edge of horizontal
+		 * active. So, should we get here before we've crossed into
+		 * the horizontal active of the first line in vblank, we would
+		 * not set the DRM_SCANOUTPOS_INVBL flag. In order to fix that,
+		 * always add htotal-hsync_start to the current pixel position.
+		 */
+		position = (position + htotal - hsync_start) % vtotal;
 	}
 
 	/* Get optional system timestamp after query. */
@@ -900,6 +1025,19 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
 	return ret;
 }
 
+int intel_get_crtc_scanline(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	unsigned long irqflags;
+	int position;
+
+	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+	position = __intel_get_crtc_scanline(crtc);
+	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+
+	return position;
+}
+
 static int i915_get_vblank_timestamp(struct drm_device *dev, int pipe,
 			      int *max_error,
 			      struct timeval *vblank_time,
@@ -945,7 +1083,7 @@ static bool intel_hpd_irq_event(struct drm_device *dev,
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] status updated from %s to %s\n",
 		      connector->base.id,
-		      drm_get_connector_name(connector),
+		      connector->name,
 		      drm_get_connector_status_name(old_status),
 		      drm_get_connector_status_name(connector->status));
 
@@ -990,7 +1128,7 @@ static void i915_hotplug_work_func(struct work_struct *work)
 		    connector->polled == DRM_CONNECTOR_POLL_HPD) {
 			DRM_INFO("HPD interrupt storm detected on connector %s: "
 				 "switching from hotplug detection to polling\n",
-				drm_get_connector_name(connector));
+				connector->name);
 			dev_priv->hpd_stats[intel_encoder->hpd_pin].hpd_mark = HPD_DISABLED;
 			connector->polled = DRM_CONNECTOR_POLL_CONNECT
 				| DRM_CONNECTOR_POLL_DISCONNECT;
@@ -998,7 +1136,7 @@ static void i915_hotplug_work_func(struct work_struct *work)
 		}
 		if (hpd_event_bits & (1 << intel_encoder->hpd_pin)) {
 			DRM_DEBUG_KMS("Connector %s (pin %i) received hotplug event.\n",
-				      drm_get_connector_name(connector), intel_encoder->hpd_pin);
+				      connector->name, intel_encoder->hpd_pin);
 		}
 	}
 	 /* if there were no outputs to poll, poll was disabled,
@@ -1073,9 +1211,9 @@ static void ironlake_rps_change_irq_handler(struct drm_device *dev)
 }
 
 static void notify_ring(struct drm_device *dev,
-			struct intel_ring_buffer *ring)
+			struct intel_engine_cs *ring)
 {
-	if (ring->obj == NULL)
+	if (!intel_ring_initialized(ring))
 		return;
 
 	trace_i915_gem_request_complete(ring);
@@ -1094,8 +1232,12 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	spin_lock_irq(&dev_priv->irq_lock);
 	pm_iir = dev_priv->rps.pm_iir;
 	dev_priv->rps.pm_iir = 0;
-	/* Make sure not to corrupt PMIMR state used by ringbuffer code */
-	snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
+	if (IS_BROADWELL(dev_priv->dev))
+		bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
+	else {
+		/* Make sure not to corrupt PMIMR state used by ringbuffer */
+		snb_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
+	}
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	/* Make sure we didn't queue anything we're not going to process. */
@@ -1292,6 +1434,19 @@ static void snb_gt_irq_handler(struct drm_device *dev,
 		ivybridge_parity_error_irq_handler(dev, gt_iir);
 }
 
+static void gen8_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
+{
+	if ((pm_iir & dev_priv->pm_rps_events) == 0)
+		return;
+
+	spin_lock(&dev_priv->irq_lock);
+	dev_priv->rps.pm_iir |= pm_iir & dev_priv->pm_rps_events;
+	bdw_disable_pm_irq(dev_priv, pm_iir & dev_priv->pm_rps_events);
+	spin_unlock(&dev_priv->irq_lock);
+
+	queue_work(dev_priv->wq, &dev_priv->rps.work);
+}
+
 static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 				       struct drm_i915_private *dev_priv,
 				       u32 master_ctl)
@@ -1315,18 +1470,32 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 			DRM_ERROR("The master control interrupt lied (GT0)!\n");
 	}
 
-	if (master_ctl & GEN8_GT_VCS1_IRQ) {
+	if (master_ctl & (GEN8_GT_VCS1_IRQ | GEN8_GT_VCS2_IRQ)) {
 		tmp = I915_READ(GEN8_GT_IIR(1));
 		if (tmp) {
 			ret = IRQ_HANDLED;
 			vcs = tmp >> GEN8_VCS1_IRQ_SHIFT;
 			if (vcs & GT_RENDER_USER_INTERRUPT)
 				notify_ring(dev, &dev_priv->ring[VCS]);
+			vcs = tmp >> GEN8_VCS2_IRQ_SHIFT;
+			if (vcs & GT_RENDER_USER_INTERRUPT)
+				notify_ring(dev, &dev_priv->ring[VCS2]);
 			I915_WRITE(GEN8_GT_IIR(1), tmp);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT1)!\n");
 	}
 
+	if (master_ctl & GEN8_GT_PM_IRQ) {
+		tmp = I915_READ(GEN8_GT_IIR(2));
+		if (tmp & dev_priv->pm_rps_events) {
+			ret = IRQ_HANDLED;
+			gen8_rps_irq_handler(dev_priv, tmp);
+			I915_WRITE(GEN8_GT_IIR(2),
+				   tmp & dev_priv->pm_rps_events);
+		} else
+			DRM_ERROR("The master control interrupt lied (PM)!\n");
+	}
+
 	if (master_ctl & GEN8_GT_VECS_IRQ) {
 		tmp = I915_READ(GEN8_GT_IIR(3));
 		if (tmp) {
@@ -1549,6 +1718,19 @@ static void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
 	}
 }
 
+static bool intel_pipe_handle_vblank(struct drm_device *dev, enum pipe pipe)
+{
+	struct intel_crtc *crtc;
+
+	if (!drm_handle_vblank(dev, pipe))
+		return false;
+
+	crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe));
+	wake_up(&crtc->vbl_wait);
+
+	return true;
+}
+
 static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1578,6 +1760,9 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 		case PIPE_B:
 			iir_bit = I915_DISPLAY_PIPE_B_EVENT_INTERRUPT;
 			break;
+		case PIPE_C:
+			iir_bit = I915_DISPLAY_PIPE_C_EVENT_INTERRUPT;
+			break;
 		}
 		if (iir & iir_bit)
 			mask |= dev_priv->pipestat_irq_mask[pipe];
@@ -1600,7 +1785,7 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 
 	for_each_pipe(pipe) {
 		if (pipe_stats[pipe] & PIPE_START_VBLANK_INTERRUPT_STATUS)
-			drm_handle_vblank(dev, pipe);
+			intel_pipe_handle_vblank(dev, pipe);
 
 		if (pipe_stats[pipe] & PLANE_FLIP_DONE_INT_STATUS_VLV) {
 			intel_prepare_page_flip(dev, pipe);
@@ -1619,9 +1804,36 @@ static void valleyview_pipestat_irq_handler(struct drm_device *dev, u32 iir)
 		gmbus_irq_handler(dev);
 }
 
+static void i9xx_hpd_irq_handler(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
+
+	if (IS_G4X(dev)) {
+		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
+
+		intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_g4x);
+	} else {
+		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
+
+		intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_i915);
+	}
+
+	if ((IS_G4X(dev) || IS_VALLEYVIEW(dev)) &&
+	    hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
+		dp_aux_irq_handler(dev);
+
+	I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
+	/*
+	 * Make sure hotplug status is cleared before we clear IIR, or else we
+	 * may miss hotplug events.
+	 */
+	POSTING_READ(PORT_HOTPLUG_STAT);
+}
+
 static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 {
-	struct drm_device *dev = (struct drm_device *) arg;
+	struct drm_device *dev = arg;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 iir, gt_iir, pm_iir;
 	irqreturn_t ret = IRQ_NONE;
@@ -1641,19 +1853,8 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 		valleyview_pipestat_irq_handler(dev, iir);
 
 		/* Consume port.  Then clear IIR or we'll miss events */
-		if (iir & I915_DISPLAY_PORT_INTERRUPT) {
-			u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
-			u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
-
-			intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_i915);
-
-			if (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
-				dp_aux_irq_handler(dev);
-
-			I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
-			I915_READ(PORT_HOTPLUG_STAT);
-		}
-
+		if (iir & I915_DISPLAY_PORT_INTERRUPT)
+			i9xx_hpd_irq_handler(dev);
 
 		if (pm_iir)
 			gen6_rps_irq_handler(dev_priv, pm_iir);
@@ -1667,6 +1868,40 @@ out:
 	return ret;
 }
 
+static irqreturn_t cherryview_irq_handler(int irq, void *arg)
+{
+	struct drm_device *dev = arg;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 master_ctl, iir;
+	irqreturn_t ret = IRQ_NONE;
+
+	for (;;) {
+		master_ctl = I915_READ(GEN8_MASTER_IRQ) & ~GEN8_MASTER_IRQ_CONTROL;
+		iir = I915_READ(VLV_IIR);
+
+		if (master_ctl == 0 && iir == 0)
+			break;
+
+		I915_WRITE(GEN8_MASTER_IRQ, 0);
+
+		gen8_gt_irq_handler(dev, dev_priv, master_ctl);
+
+		valleyview_pipestat_irq_handler(dev, iir);
+
+		/* Consume port.  Then clear IIR or we'll miss events */
+		i9xx_hpd_irq_handler(dev);
+
+		I915_WRITE(VLV_IIR, iir);
+
+		I915_WRITE(GEN8_MASTER_IRQ, DE_MASTER_IRQ_CONTROL);
+		POSTING_READ(GEN8_MASTER_IRQ);
+
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
 static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1827,7 +2062,7 @@ static void ilk_display_irq_handler(struct drm_device *dev, u32 de_iir)
 
 	for_each_pipe(pipe) {
 		if (de_iir & DE_PIPE_VBLANK(pipe))
-			drm_handle_vblank(dev, pipe);
+			intel_pipe_handle_vblank(dev, pipe);
 
 		if (de_iir & DE_PIPE_FIFO_UNDERRUN(pipe))
 			if (intel_set_cpu_fifo_underrun_reporting(dev, pipe, false))
@@ -1877,7 +2112,7 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
 
 	for_each_pipe(pipe) {
 		if (de_iir & (DE_PIPE_VBLANK_IVB(pipe)))
-			drm_handle_vblank(dev, pipe);
+			intel_pipe_handle_vblank(dev, pipe);
 
 		/* plane/pipes map 1:1 on ilk+ */
 		if (de_iir & DE_PLANE_FLIP_DONE_IVB(pipe)) {
@@ -1899,7 +2134,7 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
 
 static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 {
-	struct drm_device *dev = (struct drm_device *) arg;
+	struct drm_device *dev = arg;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 de_iir, gt_iir, de_ier, sde_ier = 0;
 	irqreturn_t ret = IRQ_NONE;
@@ -2020,9 +2255,9 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 
 		pipe_iir = I915_READ(GEN8_DE_PIPE_IIR(pipe));
 		if (pipe_iir & GEN8_PIPE_VBLANK)
-			drm_handle_vblank(dev, pipe);
+			intel_pipe_handle_vblank(dev, pipe);
 
-		if (pipe_iir & GEN8_PIPE_FLIP_DONE) {
+		if (pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE) {
 			intel_prepare_page_flip(dev, pipe);
 			intel_finish_page_flip_plane(dev, pipe);
 		}
@@ -2075,7 +2310,7 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 static void i915_error_wake_up(struct drm_i915_private *dev_priv,
 			       bool reset_completed)
 {
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int i;
 
 	/*
@@ -2137,6 +2372,14 @@ static void i915_error_work_func(struct work_struct *work)
 				   reset_event);
 
 		/*
+		 * In most cases it's guaranteed that we get here with an RPM
+		 * reference held, for example because there is a pending GPU
+		 * request that won't finish until the reset is done. This
+		 * isn't the case at least when we get here by doing a
+		 * simulated reset via debugs, so get an RPM reference.
+		 */
+		intel_runtime_pm_get(dev_priv);
+		/*
 		 * All state reset _must_ be completed before we update the
 		 * reset counter, for otherwise waiters might miss the reset
 		 * pending state and not properly drop locks, resulting in
@@ -2146,6 +2389,8 @@ static void i915_error_work_func(struct work_struct *work)
 
 		intel_display_handle_reset(dev);
 
+		intel_runtime_pm_put(dev_priv);
+
 		if (ret == 0) {
 			/*
 			 * After all the gem state is reset, increment the reset
@@ -2383,10 +2628,6 @@ static int i915_enable_vblank(struct drm_device *dev, int pipe)
 	else
 		i915_enable_pipestat(dev_priv, pipe,
 				     PIPE_VBLANK_INTERRUPT_STATUS);
-
-	/* maintain vblank delivery even in deep C-states */
-	if (INTEL_INFO(dev)->gen == 3)
-		I915_WRITE(INSTPM, _MASKED_BIT_DISABLE(INSTPM_AGPBUSY_DIS));
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
 	return 0;
@@ -2450,9 +2691,6 @@ static void i915_disable_vblank(struct drm_device *dev, int pipe)
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	if (INTEL_INFO(dev)->gen == 3)
-		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_AGPBUSY_DIS));
-
 	i915_disable_pipestat(dev_priv, pipe,
 			      PIPE_VBLANK_INTERRUPT_STATUS |
 			      PIPE_START_VBLANK_INTERRUPT_STATUS);
@@ -2498,29 +2736,77 @@ static void gen8_disable_vblank(struct drm_device *dev, int pipe)
 }
 
 static u32
-ring_last_seqno(struct intel_ring_buffer *ring)
+ring_last_seqno(struct intel_engine_cs *ring)
 {
 	return list_entry(ring->request_list.prev,
 			  struct drm_i915_gem_request, list)->seqno;
 }
 
 static bool
-ring_idle(struct intel_ring_buffer *ring, u32 seqno)
+ring_idle(struct intel_engine_cs *ring, u32 seqno)
 {
 	return (list_empty(&ring->request_list) ||
 		i915_seqno_passed(seqno, ring_last_seqno(ring)));
 }
 
-static struct intel_ring_buffer *
-semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno)
+static bool
+ipehr_is_semaphore_wait(struct drm_device *dev, u32 ipehr)
+{
+	if (INTEL_INFO(dev)->gen >= 8) {
+		/*
+		 * FIXME: gen8 semaphore support - currently we don't emit
+		 * semaphores on bdw anyway, but this needs to be addressed when
+		 * we merge that code.
+		 */
+		return false;
+	} else {
+		ipehr &= ~MI_SEMAPHORE_SYNC_MASK;
+		return ipehr == (MI_SEMAPHORE_MBOX | MI_SEMAPHORE_COMPARE |
+				 MI_SEMAPHORE_REGISTER);
+	}
+}
+
+static struct intel_engine_cs *
+semaphore_wait_to_signaller_ring(struct intel_engine_cs *ring, u32 ipehr)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct intel_engine_cs *signaller;
+	int i;
+
+	if (INTEL_INFO(dev_priv->dev)->gen >= 8) {
+		/*
+		 * FIXME: gen8 semaphore support - currently we don't emit
+		 * semaphores on bdw anyway, but this needs to be addressed when
+		 * we merge that code.
+		 */
+		return NULL;
+	} else {
+		u32 sync_bits = ipehr & MI_SEMAPHORE_SYNC_MASK;
+
+		for_each_ring(signaller, dev_priv, i) {
+			if(ring == signaller)
+				continue;
+
+			if (sync_bits == signaller->semaphore.mbox.wait[ring->id])
+				return signaller;
+		}
+	}
+
+	DRM_ERROR("No signaller ring found for ring %i, ipehr 0x%08x\n",
+		  ring->id, ipehr);
+
+	return NULL;
+}
+
+static struct intel_engine_cs *
+semaphore_waits_for(struct intel_engine_cs *ring, u32 *seqno)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	u32 cmd, ipehr, head;
 	int i;
 
 	ipehr = I915_READ(RING_IPEHR(ring->mmio_base));
-	if ((ipehr & ~(0x3 << 16)) !=
-	    (MI_SEMAPHORE_MBOX | MI_SEMAPHORE_COMPARE | MI_SEMAPHORE_REGISTER))
+	if (!ipehr_is_semaphore_wait(ring->dev, ipehr))
 		return NULL;
 
 	/*
@@ -2538,10 +2824,10 @@ semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno)
 		 * our ring is smaller than what the hardware (and hence
 		 * HEAD_ADDR) allows. Also handles wrap-around.
 		 */
-		head &= ring->size - 1;
+		head &= ring->buffer->size - 1;
 
 		/* This here seems to blow up */
-		cmd = ioread32(ring->virtual_start + head);
+		cmd = ioread32(ring->buffer->virtual_start + head);
 		if (cmd == ipehr)
 			break;
 
@@ -2551,41 +2837,48 @@ semaphore_waits_for(struct intel_ring_buffer *ring, u32 *seqno)
 	if (!i)
 		return NULL;
 
-	*seqno = ioread32(ring->virtual_start + head + 4) + 1;
-	return &dev_priv->ring[(ring->id + (((ipehr >> 17) & 1) + 1)) % 3];
+	*seqno = ioread32(ring->buffer->virtual_start + head + 4) + 1;
+	return semaphore_wait_to_signaller_ring(ring, ipehr);
 }
 
-static int semaphore_passed(struct intel_ring_buffer *ring)
+static int semaphore_passed(struct intel_engine_cs *ring)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	struct intel_ring_buffer *signaller;
-	u32 seqno, ctl;
+	struct intel_engine_cs *signaller;
+	u32 seqno;
 
-	ring->hangcheck.deadlock = true;
+	ring->hangcheck.deadlock++;
 
 	signaller = semaphore_waits_for(ring, &seqno);
-	if (signaller == NULL || signaller->hangcheck.deadlock)
+	if (signaller == NULL)
 		return -1;
 
+	/* Prevent pathological recursion due to driver bugs */
+	if (signaller->hangcheck.deadlock >= I915_NUM_RINGS)
+		return -1;
+
+	if (i915_seqno_passed(signaller->get_seqno(signaller, false), seqno))
+		return 1;
+
 	/* cursory check for an unkickable deadlock */
-	ctl = I915_READ_CTL(signaller);
-	if (ctl & RING_WAIT_SEMAPHORE && semaphore_passed(signaller) < 0)
+	if (I915_READ_CTL(signaller) & RING_WAIT_SEMAPHORE &&
+	    semaphore_passed(signaller) < 0)
 		return -1;
 
-	return i915_seqno_passed(signaller->get_seqno(signaller, false), seqno);
+	return 0;
 }
 
 static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
 {
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int i;
 
 	for_each_ring(ring, dev_priv, i)
-		ring->hangcheck.deadlock = false;
+		ring->hangcheck.deadlock = 0;
 }
 
 static enum intel_ring_hangcheck_action
-ring_stuck(struct intel_ring_buffer *ring, u64 acthd)
+ring_stuck(struct intel_engine_cs *ring, u64 acthd)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2641,7 +2934,7 @@ static void i915_hangcheck_elapsed(unsigned long data)
 {
 	struct drm_device *dev = (struct drm_device *)data;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	int i;
 	int busy_count = 0, rings_hung = 0;
 	bool stuck[I915_NUM_RINGS] = { 0 };
@@ -2759,57 +3052,63 @@ void i915_queue_hangcheck(struct drm_device *dev)
 		  round_jiffies_up(jiffies + DRM_I915_HANGCHECK_JIFFIES));
 }
 
-static void ibx_irq_preinstall(struct drm_device *dev)
+static void ibx_irq_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	if (HAS_PCH_NOP(dev))
 		return;
 
-	/* south display irq */
-	I915_WRITE(SDEIMR, 0xffffffff);
-	/*
-	 * SDEIER is also touched by the interrupt handler to work around missed
-	 * PCH interrupts. Hence we can't update it after the interrupt handler
-	 * is enabled - instead we unconditionally enable all PCH interrupt
-	 * sources here, but then only unmask them as needed with SDEIMR.
-	 */
+	GEN5_IRQ_RESET(SDE);
+
+	if (HAS_PCH_CPT(dev) || HAS_PCH_LPT(dev))
+		I915_WRITE(SERR_INT, 0xffffffff);
+}
+
+/*
+ * SDEIER is also touched by the interrupt handler to work around missed PCH
+ * interrupts. Hence we can't update it after the interrupt handler is enabled -
+ * instead we unconditionally enable all PCH interrupt sources here, but then
+ * only unmask them as needed with SDEIMR.
+ *
+ * This function needs to be called before interrupts are enabled.
+ */
+static void ibx_irq_pre_postinstall(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (HAS_PCH_NOP(dev))
+		return;
+
+	WARN_ON(I915_READ(SDEIER) != 0);
 	I915_WRITE(SDEIER, 0xffffffff);
 	POSTING_READ(SDEIER);
 }
 
-static void gen5_gt_irq_preinstall(struct drm_device *dev)
+static void gen5_gt_irq_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	/* and GT */
-	I915_WRITE(GTIMR, 0xffffffff);
-	I915_WRITE(GTIER, 0x0);
-	POSTING_READ(GTIER);
-
-	if (INTEL_INFO(dev)->gen >= 6) {
-		/* and PM */
-		I915_WRITE(GEN6_PMIMR, 0xffffffff);
-		I915_WRITE(GEN6_PMIER, 0x0);
-		POSTING_READ(GEN6_PMIER);
-	}
+	GEN5_IRQ_RESET(GT);
+	if (INTEL_INFO(dev)->gen >= 6)
+		GEN5_IRQ_RESET(GEN6_PM);
 }
 
 /* drm_dma.h hooks
 */
-static void ironlake_irq_preinstall(struct drm_device *dev)
+static void ironlake_irq_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	I915_WRITE(HWSTAM, 0xeffe);
+	I915_WRITE(HWSTAM, 0xffffffff);
 
-	I915_WRITE(DEIMR, 0xffffffff);
-	I915_WRITE(DEIER, 0x0);
-	POSTING_READ(DEIER);
+	GEN5_IRQ_RESET(DE);
+	if (IS_GEN7(dev))
+		I915_WRITE(GEN7_ERR_INT, 0xffffffff);
 
-	gen5_gt_irq_preinstall(dev);
+	gen5_gt_irq_reset(dev);
 
-	ibx_irq_preinstall(dev);
+	ibx_irq_reset(dev);
 }
 
 static void valleyview_irq_preinstall(struct drm_device *dev)
@@ -2827,7 +3126,7 @@ static void valleyview_irq_preinstall(struct drm_device *dev)
 	I915_WRITE(GTIIR, I915_READ(GTIIR));
 	I915_WRITE(GTIIR, I915_READ(GTIIR));
 
-	gen5_gt_irq_preinstall(dev);
+	gen5_gt_irq_reset(dev);
 
 	I915_WRITE(DPINVGTT, 0xff);
 
@@ -2841,7 +3140,15 @@ static void valleyview_irq_preinstall(struct drm_device *dev)
 	POSTING_READ(VLV_IER);
 }
 
-static void gen8_irq_preinstall(struct drm_device *dev)
+static void gen8_gt_irq_reset(struct drm_i915_private *dev_priv)
+{
+	GEN8_IRQ_RESET_NDX(GT, 0);
+	GEN8_IRQ_RESET_NDX(GT, 1);
+	GEN8_IRQ_RESET_NDX(GT, 2);
+	GEN8_IRQ_RESET_NDX(GT, 3);
+}
+
+static void gen8_irq_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe;
@@ -2849,43 +3156,44 @@ static void gen8_irq_preinstall(struct drm_device *dev)
 	I915_WRITE(GEN8_MASTER_IRQ, 0);
 	POSTING_READ(GEN8_MASTER_IRQ);
 
-	/* IIR can theoretically queue up two events. Be paranoid */
-#define GEN8_IRQ_INIT_NDX(type, which) do { \
-		I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \
-		POSTING_READ(GEN8_##type##_IMR(which)); \
-		I915_WRITE(GEN8_##type##_IER(which), 0); \
-		I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \
-		POSTING_READ(GEN8_##type##_IIR(which)); \
-		I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \
-	} while (0)
-
-#define GEN8_IRQ_INIT(type) do { \
-		I915_WRITE(GEN8_##type##_IMR, 0xffffffff); \
-		POSTING_READ(GEN8_##type##_IMR); \
-		I915_WRITE(GEN8_##type##_IER, 0); \
-		I915_WRITE(GEN8_##type##_IIR, 0xffffffff); \
-		POSTING_READ(GEN8_##type##_IIR); \
-		I915_WRITE(GEN8_##type##_IIR, 0xffffffff); \
-	} while (0)
-
-	GEN8_IRQ_INIT_NDX(GT, 0);
-	GEN8_IRQ_INIT_NDX(GT, 1);
-	GEN8_IRQ_INIT_NDX(GT, 2);
-	GEN8_IRQ_INIT_NDX(GT, 3);
+	gen8_gt_irq_reset(dev_priv);
 
-	for_each_pipe(pipe) {
-		GEN8_IRQ_INIT_NDX(DE_PIPE, pipe);
-	}
+	for_each_pipe(pipe)
+		GEN8_IRQ_RESET_NDX(DE_PIPE, pipe);
+
+	GEN5_IRQ_RESET(GEN8_DE_PORT_);
+	GEN5_IRQ_RESET(GEN8_DE_MISC_);
+	GEN5_IRQ_RESET(GEN8_PCU_);
+
+	ibx_irq_reset(dev);
+}
+
+static void cherryview_irq_preinstall(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe;
+
+	I915_WRITE(GEN8_MASTER_IRQ, 0);
+	POSTING_READ(GEN8_MASTER_IRQ);
+
+	gen8_gt_irq_reset(dev_priv);
 
-	GEN8_IRQ_INIT(DE_PORT);
-	GEN8_IRQ_INIT(DE_MISC);
-	GEN8_IRQ_INIT(PCU);
-#undef GEN8_IRQ_INIT
-#undef GEN8_IRQ_INIT_NDX
+	GEN5_IRQ_RESET(GEN8_PCU_);
 
 	POSTING_READ(GEN8_PCU_IIR);
 
-	ibx_irq_preinstall(dev);
+	I915_WRITE(DPINVGTT, DPINVGTT_STATUS_MASK_CHV);
+
+	I915_WRITE(PORT_HOTPLUG_EN, 0);
+	I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
+
+	for_each_pipe(pipe)
+		I915_WRITE(PIPESTAT(pipe), 0xffff);
+
+	I915_WRITE(VLV_IMR, 0xffffffff);
+	I915_WRITE(VLV_IER, 0x0);
+	I915_WRITE(VLV_IIR, 0xffffffff);
+	POSTING_READ(VLV_IIR);
 }
 
 static void ibx_hpd_irq_setup(struct drm_device *dev)
@@ -2931,15 +3239,12 @@ static void ibx_irq_postinstall(struct drm_device *dev)
 	if (HAS_PCH_NOP(dev))
 		return;
 
-	if (HAS_PCH_IBX(dev)) {
+	if (HAS_PCH_IBX(dev))
 		mask = SDE_GMBUS | SDE_AUX_MASK | SDE_POISON;
-	} else {
+	else
 		mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT;
 
-		I915_WRITE(SERR_INT, I915_READ(SERR_INT));
-	}
-
-	I915_WRITE(SDEIIR, I915_READ(SDEIIR));
+	GEN5_ASSERT_IIR_IS_ZERO(SDEIIR);
 	I915_WRITE(SDEIMR, ~mask);
 }
 
@@ -2965,10 +3270,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 		gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT;
 	}
 
-	I915_WRITE(GTIIR, I915_READ(GTIIR));
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-	I915_WRITE(GTIER, gt_irqs);
-	POSTING_READ(GTIER);
+	GEN5_IRQ_INIT(GT, dev_priv->gt_irq_mask, gt_irqs);
 
 	if (INTEL_INFO(dev)->gen >= 6) {
 		pm_irqs |= dev_priv->pm_rps_events;
@@ -2977,10 +3279,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev)
 			pm_irqs |= PM_VEBOX_USER_INTERRUPT;
 
 		dev_priv->pm_irq_mask = 0xffffffff;
-		I915_WRITE(GEN6_PMIIR, I915_READ(GEN6_PMIIR));
-		I915_WRITE(GEN6_PMIMR, dev_priv->pm_irq_mask);
-		I915_WRITE(GEN6_PMIER, pm_irqs);
-		POSTING_READ(GEN6_PMIER);
+		GEN5_IRQ_INIT(GEN6_PM, dev_priv->pm_irq_mask, pm_irqs);
 	}
 }
 
@@ -2997,8 +3296,6 @@ static int ironlake_irq_postinstall(struct drm_device *dev)
 				DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB);
 		extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB |
 			      DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB);
-
-		I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT));
 	} else {
 		display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT |
 				DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE |
@@ -3011,11 +3308,11 @@ static int ironlake_irq_postinstall(struct drm_device *dev)
 
 	dev_priv->irq_mask = ~display_mask;
 
-	/* should always can generate irq */
-	I915_WRITE(DEIIR, I915_READ(DEIIR));
-	I915_WRITE(DEIMR, dev_priv->irq_mask);
-	I915_WRITE(DEIER, display_mask | extra_mask);
-	POSTING_READ(DEIER);
+	I915_WRITE(HWSTAM, 0xeffe);
+
+	ibx_irq_pre_postinstall(dev);
+
+	GEN5_IRQ_INIT(DE, dev_priv->irq_mask, display_mask | extra_mask);
 
 	gen5_gt_irq_postinstall(dev);
 
@@ -3175,21 +3472,16 @@ static void gen8_gt_irq_postinstall(struct drm_i915_private *dev_priv)
 		GT_RENDER_USER_INTERRUPT << GEN8_VECS_IRQ_SHIFT
 		};
 
-	for (i = 0; i < ARRAY_SIZE(gt_interrupts); i++) {
-		u32 tmp = I915_READ(GEN8_GT_IIR(i));
-		if (tmp)
-			DRM_ERROR("Interrupt (%d) should have been masked in pre-install 0x%08x\n",
-				  i, tmp);
-		I915_WRITE(GEN8_GT_IMR(i), ~gt_interrupts[i]);
-		I915_WRITE(GEN8_GT_IER(i), gt_interrupts[i]);
-	}
-	POSTING_READ(GEN8_GT_IER(0));
+	for (i = 0; i < ARRAY_SIZE(gt_interrupts); i++)
+		GEN8_IRQ_INIT_NDX(GT, i, ~gt_interrupts[i], gt_interrupts[i]);
+
+	dev_priv->pm_irq_mask = 0xffffffff;
 }
 
 static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
-	uint32_t de_pipe_masked = GEN8_PIPE_FLIP_DONE |
+	uint32_t de_pipe_masked = GEN8_PIPE_PRIMARY_FLIP_DONE |
 		GEN8_PIPE_CDCLK_CRC_DONE |
 		GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
 	uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
@@ -3199,25 +3491,19 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	dev_priv->de_irq_mask[PIPE_B] = ~de_pipe_masked;
 	dev_priv->de_irq_mask[PIPE_C] = ~de_pipe_masked;
 
-	for_each_pipe(pipe) {
-		u32 tmp = I915_READ(GEN8_DE_PIPE_IIR(pipe));
-		if (tmp)
-			DRM_ERROR("Interrupt (%d) should have been masked in pre-install 0x%08x\n",
-				  pipe, tmp);
-		I915_WRITE(GEN8_DE_PIPE_IMR(pipe), dev_priv->de_irq_mask[pipe]);
-		I915_WRITE(GEN8_DE_PIPE_IER(pipe), de_pipe_enables);
-	}
-	POSTING_READ(GEN8_DE_PIPE_ISR(0));
+	for_each_pipe(pipe)
+		GEN8_IRQ_INIT_NDX(DE_PIPE, pipe, dev_priv->de_irq_mask[pipe],
+				  de_pipe_enables);
 
-	I915_WRITE(GEN8_DE_PORT_IMR, ~GEN8_AUX_CHANNEL_A);
-	I915_WRITE(GEN8_DE_PORT_IER, GEN8_AUX_CHANNEL_A);
-	POSTING_READ(GEN8_DE_PORT_IER);
+	GEN5_IRQ_INIT(GEN8_DE_PORT_, ~GEN8_AUX_CHANNEL_A, GEN8_AUX_CHANNEL_A);
 }
 
 static int gen8_irq_postinstall(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
+	ibx_irq_pre_postinstall(dev);
+
 	gen8_gt_irq_postinstall(dev_priv);
 	gen8_de_irq_postinstall(dev_priv);
 
@@ -3229,44 +3515,55 @@ static int gen8_irq_postinstall(struct drm_device *dev)
 	return 0;
 }
 
-static void gen8_irq_uninstall(struct drm_device *dev)
+static int cherryview_irq_postinstall(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 enable_mask = I915_DISPLAY_PORT_INTERRUPT |
+		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
+		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		I915_DISPLAY_PIPE_C_EVENT_INTERRUPT;
+	u32 pipestat_enable = PLANE_FLIP_DONE_INT_STATUS_VLV |
+		PIPE_CRC_DONE_INTERRUPT_STATUS;
+	unsigned long irqflags;
 	int pipe;
 
-	if (!dev_priv)
-		return;
+	/*
+	 * Leave vblank interrupts masked initially.  enable/disable will
+	 * toggle them based on usage.
+	 */
+	dev_priv->irq_mask = ~enable_mask;
 
-	I915_WRITE(GEN8_MASTER_IRQ, 0);
+	for_each_pipe(pipe)
+		I915_WRITE(PIPESTAT(pipe), 0xffff);
 
-#define GEN8_IRQ_FINI_NDX(type, which) do { \
-		I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \
-		I915_WRITE(GEN8_##type##_IER(which), 0); \
-		I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff); \
-	} while (0)
+	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
+	i915_enable_pipestat(dev_priv, PIPE_A, PIPE_GMBUS_INTERRUPT_STATUS);
+	for_each_pipe(pipe)
+		i915_enable_pipestat(dev_priv, pipe, pipestat_enable);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 
-#define GEN8_IRQ_FINI(type) do { \
-		I915_WRITE(GEN8_##type##_IMR, 0xffffffff); \
-		I915_WRITE(GEN8_##type##_IER, 0); \
-		I915_WRITE(GEN8_##type##_IIR, 0xffffffff); \
-	} while (0)
+	I915_WRITE(VLV_IIR, 0xffffffff);
+	I915_WRITE(VLV_IMR, dev_priv->irq_mask);
+	I915_WRITE(VLV_IER, enable_mask);
 
-	GEN8_IRQ_FINI_NDX(GT, 0);
-	GEN8_IRQ_FINI_NDX(GT, 1);
-	GEN8_IRQ_FINI_NDX(GT, 2);
-	GEN8_IRQ_FINI_NDX(GT, 3);
+	gen8_gt_irq_postinstall(dev_priv);
 
-	for_each_pipe(pipe) {
-		GEN8_IRQ_FINI_NDX(DE_PIPE, pipe);
-	}
+	I915_WRITE(GEN8_MASTER_IRQ, MASTER_INTERRUPT_ENABLE);
+	POSTING_READ(GEN8_MASTER_IRQ);
 
-	GEN8_IRQ_FINI(DE_PORT);
-	GEN8_IRQ_FINI(DE_MISC);
-	GEN8_IRQ_FINI(PCU);
-#undef GEN8_IRQ_FINI
-#undef GEN8_IRQ_FINI_NDX
+	return 0;
+}
 
-	POSTING_READ(GEN8_PCU_IIR);
+static void gen8_irq_uninstall(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!dev_priv)
+		return;
+
+	intel_hpd_irq_uninstall(dev_priv);
+
+	gen8_irq_reset(dev);
 }
 
 static void valleyview_irq_uninstall(struct drm_device *dev)
@@ -3278,6 +3575,8 @@ static void valleyview_irq_uninstall(struct drm_device *dev)
 	if (!dev_priv)
 		return;
 
+	I915_WRITE(VLV_MASTER_IER, 0);
+
 	intel_hpd_irq_uninstall(dev_priv);
 
 	for_each_pipe(pipe)
@@ -3300,35 +3599,67 @@ static void valleyview_irq_uninstall(struct drm_device *dev)
 	POSTING_READ(VLV_IER);
 }
 
-static void ironlake_irq_uninstall(struct drm_device *dev)
+static void cherryview_irq_uninstall(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe;
 
 	if (!dev_priv)
 		return;
 
-	intel_hpd_irq_uninstall(dev_priv);
+	I915_WRITE(GEN8_MASTER_IRQ, 0);
+	POSTING_READ(GEN8_MASTER_IRQ);
 
-	I915_WRITE(HWSTAM, 0xffffffff);
+#define GEN8_IRQ_FINI_NDX(type, which)				\
+do {								\
+	I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff);	\
+	I915_WRITE(GEN8_##type##_IER(which), 0);		\
+	I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff);	\
+	POSTING_READ(GEN8_##type##_IIR(which));			\
+	I915_WRITE(GEN8_##type##_IIR(which), 0xffffffff);	\
+} while (0)
+
+#define GEN8_IRQ_FINI(type)				\
+do {							\
+	I915_WRITE(GEN8_##type##_IMR, 0xffffffff);	\
+	I915_WRITE(GEN8_##type##_IER, 0);		\
+	I915_WRITE(GEN8_##type##_IIR, 0xffffffff);	\
+	POSTING_READ(GEN8_##type##_IIR);		\
+	I915_WRITE(GEN8_##type##_IIR, 0xffffffff);	\
+} while (0)
 
-	I915_WRITE(DEIMR, 0xffffffff);
-	I915_WRITE(DEIER, 0x0);
-	I915_WRITE(DEIIR, I915_READ(DEIIR));
-	if (IS_GEN7(dev))
-		I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT));
+	GEN8_IRQ_FINI_NDX(GT, 0);
+	GEN8_IRQ_FINI_NDX(GT, 1);
+	GEN8_IRQ_FINI_NDX(GT, 2);
+	GEN8_IRQ_FINI_NDX(GT, 3);
 
-	I915_WRITE(GTIMR, 0xffffffff);
-	I915_WRITE(GTIER, 0x0);
-	I915_WRITE(GTIIR, I915_READ(GTIIR));
+	GEN8_IRQ_FINI(PCU);
 
-	if (HAS_PCH_NOP(dev))
+#undef GEN8_IRQ_FINI
+#undef GEN8_IRQ_FINI_NDX
+
+	I915_WRITE(PORT_HOTPLUG_EN, 0);
+	I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
+
+	for_each_pipe(pipe)
+		I915_WRITE(PIPESTAT(pipe), 0xffff);
+
+	I915_WRITE(VLV_IMR, 0xffffffff);
+	I915_WRITE(VLV_IER, 0x0);
+	I915_WRITE(VLV_IIR, 0xffffffff);
+	POSTING_READ(VLV_IIR);
+}
+
+static void ironlake_irq_uninstall(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!dev_priv)
 		return;
 
-	I915_WRITE(SDEIMR, 0xffffffff);
-	I915_WRITE(SDEIER, 0x0);
-	I915_WRITE(SDEIIR, I915_READ(SDEIIR));
-	if (HAS_PCH_CPT(dev) || HAS_PCH_LPT(dev))
-		I915_WRITE(SERR_INT, I915_READ(SERR_INT));
+	intel_hpd_irq_uninstall(dev_priv);
+
+	ironlake_irq_reset(dev);
 }
 
 static void i8xx_irq_preinstall(struct drm_device * dev)
@@ -3386,7 +3717,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u16 flip_pending = DISPLAY_PLANE_FLIP_PENDING(plane);
 
-	if (!drm_handle_vblank(dev, pipe))
+	if (!intel_pipe_handle_vblank(dev, pipe))
 		return false;
 
 	if ((iir & flip_pending) == 0)
@@ -3410,7 +3741,7 @@ static bool i8xx_handle_vblank(struct drm_device *dev,
 
 static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 {
-	struct drm_device *dev = (struct drm_device *) arg;
+	struct drm_device *dev = arg;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u16 iir, new_iir;
 	u32 pipe_stats[2];
@@ -3571,7 +3902,7 @@ static bool i915_handle_vblank(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 flip_pending = DISPLAY_PLANE_FLIP_PENDING(plane);
 
-	if (!drm_handle_vblank(dev, pipe))
+	if (!intel_pipe_handle_vblank(dev, pipe))
 		return false;
 
 	if ((iir & flip_pending) == 0)
@@ -3595,7 +3926,7 @@ static bool i915_handle_vblank(struct drm_device *dev,
 
 static irqreturn_t i915_irq_handler(int irq, void *arg)
 {
-	struct drm_device *dev = (struct drm_device *) arg;
+	struct drm_device *dev = arg;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 iir, new_iir, pipe_stats[I915_MAX_PIPES];
 	unsigned long irqflags;
@@ -3636,16 +3967,9 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 			break;
 
 		/* Consume port.  Then clear IIR or we'll miss events */
-		if ((I915_HAS_HOTPLUG(dev)) &&
-		    (iir & I915_DISPLAY_PORT_INTERRUPT)) {
-			u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
-			u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
-
-			intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_i915);
-
-			I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
-			POSTING_READ(PORT_HOTPLUG_STAT);
-		}
+		if (I915_HAS_HOTPLUG(dev) &&
+		    iir & I915_DISPLAY_PORT_INTERRUPT)
+			i9xx_hpd_irq_handler(dev);
 
 		I915_WRITE(IIR, iir & ~flip_mask);
 		new_iir = I915_READ(IIR); /* Flush posted writes */
@@ -3832,7 +4156,7 @@ static void i915_hpd_irq_setup(struct drm_device *dev)
 
 static irqreturn_t i965_irq_handler(int irq, void *arg)
 {
-	struct drm_device *dev = (struct drm_device *) arg;
+	struct drm_device *dev = arg;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 iir, new_iir;
 	u32 pipe_stats[I915_MAX_PIPES];
@@ -3879,22 +4203,8 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		ret = IRQ_HANDLED;
 
 		/* Consume port.  Then clear IIR or we'll miss events */
-		if (iir & I915_DISPLAY_PORT_INTERRUPT) {
-			u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
-			u32 hotplug_trigger = hotplug_status & (IS_G4X(dev) ?
-								  HOTPLUG_INT_STATUS_G4X :
-								  HOTPLUG_INT_STATUS_I915);
-
-			intel_hpd_irq_handler(dev, hotplug_trigger,
-					      IS_G4X(dev) ? hpd_status_g4x : hpd_status_i915);
-
-			if (IS_G4X(dev) &&
-			    (hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X))
-				dp_aux_irq_handler(dev);
-
-			I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
-			I915_READ(PORT_HOTPLUG_STAT);
-		}
+		if (iir & I915_DISPLAY_PORT_INTERRUPT)
+			i9xx_hpd_irq_handler(dev);
 
 		I915_WRITE(IIR, iir & ~flip_mask);
 		new_iir = I915_READ(IIR); /* Flush posted writes */
@@ -3997,7 +4307,7 @@ static void intel_hpd_irq_reenable(unsigned long data)
 			if (intel_connector->encoder->hpd_pin == i) {
 				if (connector->polled != intel_connector->polled)
 					DRM_DEBUG_DRIVER("Reenabling HPD on connector %s\n",
-							 drm_get_connector_name(connector));
+							 connector->name);
 				connector->polled = intel_connector->polled;
 				if (!connector->polled)
 					connector->polled = DRM_CONNECTOR_POLL_HPD;
@@ -4045,7 +4355,15 @@ void intel_irq_init(struct drm_device *dev)
 		dev->driver->get_scanout_position = i915_get_crtc_scanoutpos;
 	}
 
-	if (IS_VALLEYVIEW(dev)) {
+	if (IS_CHERRYVIEW(dev)) {
+		dev->driver->irq_handler = cherryview_irq_handler;
+		dev->driver->irq_preinstall = cherryview_irq_preinstall;
+		dev->driver->irq_postinstall = cherryview_irq_postinstall;
+		dev->driver->irq_uninstall = cherryview_irq_uninstall;
+		dev->driver->enable_vblank = valleyview_enable_vblank;
+		dev->driver->disable_vblank = valleyview_disable_vblank;
+		dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup;
+	} else if (IS_VALLEYVIEW(dev)) {
 		dev->driver->irq_handler = valleyview_irq_handler;
 		dev->driver->irq_preinstall = valleyview_irq_preinstall;
 		dev->driver->irq_postinstall = valleyview_irq_postinstall;
@@ -4055,7 +4373,7 @@ void intel_irq_init(struct drm_device *dev)
 		dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup;
 	} else if (IS_GEN8(dev)) {
 		dev->driver->irq_handler = gen8_irq_handler;
-		dev->driver->irq_preinstall = gen8_irq_preinstall;
+		dev->driver->irq_preinstall = gen8_irq_reset;
 		dev->driver->irq_postinstall = gen8_irq_postinstall;
 		dev->driver->irq_uninstall = gen8_irq_uninstall;
 		dev->driver->enable_vblank = gen8_enable_vblank;
@@ -4063,7 +4381,7 @@ void intel_irq_init(struct drm_device *dev)
 		dev_priv->display.hpd_irq_setup = ibx_hpd_irq_setup;
 	} else if (HAS_PCH_SPLIT(dev)) {
 		dev->driver->irq_handler = ironlake_irq_handler;
-		dev->driver->irq_preinstall = ironlake_irq_preinstall;
+		dev->driver->irq_preinstall = ironlake_irq_reset;
 		dev->driver->irq_postinstall = ironlake_irq_postinstall;
 		dev->driver->irq_uninstall = ironlake_irq_uninstall;
 		dev->driver->enable_vblank = ironlake_enable_vblank;
@@ -4121,57 +4439,20 @@ void intel_hpd_init(struct drm_device *dev)
 }
 
 /* Disable interrupts so we can allow runtime PM. */
-void hsw_runtime_pm_disable_interrupts(struct drm_device *dev)
+void intel_runtime_pm_disable_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long irqflags;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-
-	dev_priv->pm.regsave.deimr = I915_READ(DEIMR);
-	dev_priv->pm.regsave.sdeimr = I915_READ(SDEIMR);
-	dev_priv->pm.regsave.gtimr = I915_READ(GTIMR);
-	dev_priv->pm.regsave.gtier = I915_READ(GTIER);
-	dev_priv->pm.regsave.gen6_pmimr = I915_READ(GEN6_PMIMR);
-
-	ironlake_disable_display_irq(dev_priv, 0xffffffff);
-	ibx_disable_display_interrupt(dev_priv, 0xffffffff);
-	ilk_disable_gt_irq(dev_priv, 0xffffffff);
-	snb_disable_pm_irq(dev_priv, 0xffffffff);
 
+	dev->driver->irq_uninstall(dev);
 	dev_priv->pm.irqs_disabled = true;
-
-	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
 /* Restore interrupts so we can recover from runtime PM. */
-void hsw_runtime_pm_restore_interrupts(struct drm_device *dev)
+void intel_runtime_pm_restore_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	unsigned long irqflags;
-	uint32_t val;
-
-	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-
-	val = I915_READ(DEIMR);
-	WARN(val != 0xffffffff, "DEIMR is 0x%08x\n", val);
-
-	val = I915_READ(SDEIMR);
-	WARN(val != 0xffffffff, "SDEIMR is 0x%08x\n", val);
-
-	val = I915_READ(GTIMR);
-	WARN(val != 0xffffffff, "GTIMR is 0x%08x\n", val);
-
-	val = I915_READ(GEN6_PMIMR);
-	WARN(val != 0xffffffff, "GEN6_PMIMR is 0x%08x\n", val);
 
 	dev_priv->pm.irqs_disabled = false;
-
-	ironlake_enable_display_irq(dev_priv, ~dev_priv->pm.regsave.deimr);
-	ibx_enable_display_interrupt(dev_priv, ~dev_priv->pm.regsave.sdeimr);
-	ilk_enable_gt_irq(dev_priv, ~dev_priv->pm.regsave.gtimr);
-	snb_enable_pm_irq(dev_priv, ~dev_priv->pm.regsave.gen6_pmimr);
-	I915_WRITE(GTIER, dev_priv->pm.regsave.gtier);
-
-	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+	dev->driver->irq_preinstall(dev);
+	dev->driver->irq_postinstall(dev);
 }
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index d1d7980f0e0..d05a2afa17d 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -46,7 +46,8 @@ struct i915_params i915 __read_mostly = {
 	.reset = true,
 	.invert_brightness = 0,
 	.disable_display = 0,
-	.enable_cmd_parser = 0,
+	.enable_cmd_parser = 1,
+	.disable_vtd_wa = 0,
 };
 
 module_param_named(modeset, i915.modeset, int, 0400);
@@ -149,6 +150,9 @@ MODULE_PARM_DESC(invert_brightness,
 module_param_named(disable_display, i915.disable_display, bool, 0600);
 MODULE_PARM_DESC(disable_display, "Disable display (default: false)");
 
+module_param_named(disable_vtd_wa, i915.disable_vtd_wa, bool, 0600);
+MODULE_PARM_DESC(disable_vtd_wa, "Disable all VT-d workarounds (default: false)");
+
 module_param_named(enable_cmd_parser, i915.enable_cmd_parser, int, 0600);
 MODULE_PARM_DESC(enable_cmd_parser,
-		 "Enable command parsing (1=enabled, 0=disabled [default])");
+		 "Enable command parsing (1=enabled [default], 0=disabled)");
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c77af69c2d8..a5bab61bfc0 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -29,6 +29,8 @@
 #define _TRANSCODER(tran, a, b) ((a) + (tran)*((b)-(a)))
 
 #define _PORT(port, a, b) ((a) + (port)*((b)-(a)))
+#define _PIPE3(pipe, a, b, c) (pipe < 2 ? _PIPE(pipe, a, b) : c)
+#define _PORT3(port, a, b, c) (port < 2 ? _PORT(port, a, b) : c)
 
 #define _MASKED_BIT_ENABLE(a) (((a) << 16) | (a))
 #define _MASKED_BIT_DISABLE(a) ((a) << 16)
@@ -77,13 +79,19 @@
 
 /* Graphics reset regs */
 #define I965_GDRST 0xc0 /* PCI config register */
-#define ILK_GDSR 0x2ca4 /* MCHBAR offset */
 #define  GRDOM_FULL	(0<<2)
 #define  GRDOM_RENDER	(1<<2)
 #define  GRDOM_MEDIA	(3<<2)
 #define  GRDOM_MASK	(3<<2)
 #define  GRDOM_RESET_ENABLE (1<<0)
 
+#define ILK_GDSR 0x2ca4 /* MCHBAR offset */
+#define  ILK_GRDOM_FULL		(0<<1)
+#define  ILK_GRDOM_RENDER	(1<<1)
+#define  ILK_GRDOM_MEDIA	(3<<1)
+#define  ILK_GRDOM_MASK		(3<<1)
+#define  ILK_GRDOM_RESET_ENABLE (1<<0)
+
 #define GEN6_MBCUNIT_SNPCR	0x900c /* for LLC config */
 #define   GEN6_MBC_SNPCR_SHIFT	21
 #define   GEN6_MBC_SNPCR_MASK	(3<<21)
@@ -92,6 +100,9 @@
 #define   GEN6_MBC_SNPCR_LOW	(2<<21)
 #define   GEN6_MBC_SNPCR_MIN	(3<<21) /* only 1/16th of the cache is shared */
 
+#define VLV_G3DCTL		0x9024
+#define VLV_GSCKGCTL		0x9028
+
 #define GEN6_MBCTL		0x0907c
 #define   GEN6_MBCTL_ENABLE_BOOT_FETCH	(1 << 4)
 #define   GEN6_MBCTL_CTX_FETCH_NEEDED	(1 << 3)
@@ -190,6 +201,8 @@
  * Memory interface instructions used by the kernel
  */
 #define MI_INSTR(opcode, flags) (((opcode) << 23) | (flags))
+/* Many MI commands use bit 22 of the header dword for GGTT vs PPGTT */
+#define  MI_GLOBAL_GTT    (1<<22)
 
 #define MI_NOOP			MI_INSTR(0, 0)
 #define MI_USER_INTERRUPT	MI_INSTR(0x02, 0)
@@ -244,7 +257,8 @@
 #define   MI_SEMAPHORE_SYNC_BVE	    (0<<16) /* VECS wait for BCS  (VEBSYNC) */
 #define   MI_SEMAPHORE_SYNC_VVE	    (1<<16) /* VECS wait for VCS  (VEVSYNC) */
 #define   MI_SEMAPHORE_SYNC_RVE	    (2<<16) /* VECS wait for RCS  (VERSYNC) */
-#define   MI_SEMAPHORE_SYNC_INVALID  (3<<16)
+#define   MI_SEMAPHORE_SYNC_INVALID (3<<16)
+#define   MI_SEMAPHORE_SYNC_MASK    (3<<16)
 #define MI_SET_CONTEXT		MI_INSTR(0x18, 0)
 #define   MI_MM_SPACE_GTT		(1<<8)
 #define   MI_MM_SPACE_PHYSICAL		(0<<8)
@@ -262,13 +276,16 @@
  * - One can actually load arbitrary many arbitrary registers: Simply issue x
  *   address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
  */
-#define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*x-1)
-#define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*x-1)
+#define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*(x)-1)
+#define MI_STORE_REGISTER_MEM(x) MI_INSTR(0x24, 2*(x)-1)
+#define MI_STORE_REGISTER_MEM_GEN8(x) MI_INSTR(0x24, 3*(x)-1)
 #define   MI_SRM_LRM_GLOBAL_GTT		(1<<22)
 #define MI_FLUSH_DW		MI_INSTR(0x26, 1) /* for GEN6 */
 #define   MI_FLUSH_DW_STORE_INDEX	(1<<21)
 #define   MI_INVALIDATE_TLB		(1<<18)
 #define   MI_FLUSH_DW_OP_STOREDW	(1<<14)
+#define   MI_FLUSH_DW_OP_MASK		(3<<14)
+#define   MI_FLUSH_DW_NOTIFY		(1<<8)
 #define   MI_INVALIDATE_BSD		(1<<7)
 #define   MI_FLUSH_DW_USE_GTT		(1<<2)
 #define   MI_FLUSH_DW_USE_PPGTT		(0<<2)
@@ -330,9 +347,12 @@
 #define   DISPLAY_PLANE_B           (1<<20)
 #define GFX_OP_PIPE_CONTROL(len)	((0x3<<29)|(0x3<<27)|(0x2<<24)|(len-2))
 #define   PIPE_CONTROL_GLOBAL_GTT_IVB			(1<<24) /* gen7+ */
+#define   PIPE_CONTROL_MMIO_WRITE			(1<<23)
+#define   PIPE_CONTROL_STORE_DATA_INDEX			(1<<21)
 #define   PIPE_CONTROL_CS_STALL				(1<<20)
 #define   PIPE_CONTROL_TLB_INVALIDATE			(1<<18)
 #define   PIPE_CONTROL_QW_WRITE				(1<<14)
+#define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
 #define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
 #define   PIPE_CONTROL_WRITE_FLUSH			(1<<12)
 #define   PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH	(1<<12) /* gen6+ */
@@ -347,6 +367,94 @@
 #define   PIPE_CONTROL_DEPTH_CACHE_FLUSH		(1<<0)
 #define   PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */
 
+/*
+ * Commands used only by the command parser
+ */
+#define MI_SET_PREDICATE        MI_INSTR(0x01, 0)
+#define MI_ARB_CHECK            MI_INSTR(0x05, 0)
+#define MI_RS_CONTROL           MI_INSTR(0x06, 0)
+#define MI_URB_ATOMIC_ALLOC     MI_INSTR(0x09, 0)
+#define MI_PREDICATE            MI_INSTR(0x0C, 0)
+#define MI_RS_CONTEXT           MI_INSTR(0x0F, 0)
+#define MI_TOPOLOGY_FILTER      MI_INSTR(0x0D, 0)
+#define MI_LOAD_SCAN_LINES_EXCL MI_INSTR(0x13, 0)
+#define MI_URB_CLEAR            MI_INSTR(0x19, 0)
+#define MI_UPDATE_GTT           MI_INSTR(0x23, 0)
+#define MI_CLFLUSH              MI_INSTR(0x27, 0)
+#define MI_REPORT_PERF_COUNT    MI_INSTR(0x28, 0)
+#define   MI_REPORT_PERF_COUNT_GGTT (1<<0)
+#define MI_LOAD_REGISTER_MEM    MI_INSTR(0x29, 0)
+#define MI_LOAD_REGISTER_REG    MI_INSTR(0x2A, 0)
+#define MI_RS_STORE_DATA_IMM    MI_INSTR(0x2B, 0)
+#define MI_LOAD_URB_MEM         MI_INSTR(0x2C, 0)
+#define MI_STORE_URB_MEM        MI_INSTR(0x2D, 0)
+#define MI_CONDITIONAL_BATCH_BUFFER_END MI_INSTR(0x36, 0)
+
+#define PIPELINE_SELECT                ((0x3<<29)|(0x1<<27)|(0x1<<24)|(0x4<<16))
+#define GFX_OP_3DSTATE_VF_STATISTICS   ((0x3<<29)|(0x1<<27)|(0x0<<24)|(0xB<<16))
+#define MEDIA_VFE_STATE                ((0x3<<29)|(0x2<<27)|(0x0<<24)|(0x0<<16))
+#define  MEDIA_VFE_STATE_MMIO_ACCESS_MASK (0x18)
+#define GPGPU_OBJECT                   ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x4<<16))
+#define GPGPU_WALKER                   ((0x3<<29)|(0x2<<27)|(0x1<<24)|(0x5<<16))
+#define GFX_OP_3DSTATE_DX9_CONSTANTF_VS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x39<<16))
+#define GFX_OP_3DSTATE_DX9_CONSTANTF_PS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x3A<<16))
+#define GFX_OP_3DSTATE_SO_DECL_LIST \
+	((0x3<<29)|(0x3<<27)|(0x1<<24)|(0x17<<16))
+
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_VS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x43<<16))
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_GS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x44<<16))
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_HS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x45<<16))
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_DS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x46<<16))
+#define GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS \
+	((0x3<<29)|(0x3<<27)|(0x0<<24)|(0x47<<16))
+
+#define MFX_WAIT  ((0x3<<29)|(0x1<<27)|(0x0<<16))
+
+#define COLOR_BLT     ((0x2<<29)|(0x40<<22))
+#define SRC_COPY_BLT  ((0x2<<29)|(0x43<<22))
+
+/*
+ * Registers used only by the command parser
+ */
+#define BCS_SWCTRL 0x22200
+
+#define HS_INVOCATION_COUNT 0x2300
+#define DS_INVOCATION_COUNT 0x2308
+#define IA_VERTICES_COUNT   0x2310
+#define IA_PRIMITIVES_COUNT 0x2318
+#define VS_INVOCATION_COUNT 0x2320
+#define GS_INVOCATION_COUNT 0x2328
+#define GS_PRIMITIVES_COUNT 0x2330
+#define CL_INVOCATION_COUNT 0x2338
+#define CL_PRIMITIVES_COUNT 0x2340
+#define PS_INVOCATION_COUNT 0x2348
+#define PS_DEPTH_COUNT      0x2350
+
+/* There are the 4 64-bit counter registers, one for each stream output */
+#define GEN7_SO_NUM_PRIMS_WRITTEN(n) (0x5200 + (n) * 8)
+
+#define GEN7_SO_PRIM_STORAGE_NEEDED(n)  (0x5240 + (n) * 8)
+
+#define GEN7_3DPRIM_END_OFFSET          0x2420
+#define GEN7_3DPRIM_START_VERTEX        0x2430
+#define GEN7_3DPRIM_VERTEX_COUNT        0x2434
+#define GEN7_3DPRIM_INSTANCE_COUNT      0x2438
+#define GEN7_3DPRIM_START_INSTANCE      0x243C
+#define GEN7_3DPRIM_BASE_VERTEX         0x2440
+
+#define OACONTROL 0x2360
+
+#define _GEN7_PIPEA_DE_LOAD_SL	0x70068
+#define _GEN7_PIPEB_DE_LOAD_SL	0x71068
+#define GEN7_PIPE_DE_LOAD_SL(pipe) _PIPE(pipe, \
+					 _GEN7_PIPEA_DE_LOAD_SL, \
+					 _GEN7_PIPEB_DE_LOAD_SL)
 
 /*
  * Reset registers
@@ -370,6 +478,7 @@
 #define   IOSF_PORT_PUNIT			0x4
 #define   IOSF_PORT_NC				0x11
 #define   IOSF_PORT_DPIO			0x12
+#define   IOSF_PORT_DPIO_2			0x1a
 #define   IOSF_PORT_GPIO_NC			0x13
 #define   IOSF_PORT_CCK				0x14
 #define   IOSF_PORT_CCU				0xA9
@@ -381,9 +490,6 @@
 /* See configdb bunit SB addr map */
 #define BUNIT_REG_BISOC				0x11
 
-#define PUNIT_OPCODE_REG_READ			6
-#define PUNIT_OPCODE_REG_WRITE			7
-
 #define PUNIT_REG_DSPFREQ			0x36
 #define   DSPFREQSTAT_SHIFT			30
 #define   DSPFREQSTAT_MASK			(0x3 << DSPFREQSTAT_SHIFT)
@@ -469,16 +575,91 @@ enum punit_power_well {
 #define  DSI_PLL_M1_DIV_MASK			(0x1ff << 0)
 #define CCK_DISPLAY_CLOCK_CONTROL		0x6b
 
-/*
- * DPIO - a special bus for various display related registers to hide behind
+/**
+ * DOC: DPIO
+ *
+ * VLV and CHV have slightly peculiar display PHYs for driving DP/HDMI
+ * ports. DPIO is the name given to such a display PHY. These PHYs
+ * don't follow the standard programming model using direct MMIO
+ * registers, and instead their registers must be accessed trough IOSF
+ * sideband. VLV has one such PHY for driving ports B and C, and CHV
+ * adds another PHY for driving port D. Each PHY responds to specific
+ * IOSF-SB port.
+ *
+ * Each display PHY is made up of one or two channels. Each channel
+ * houses a common lane part which contains the PLL and other common
+ * logic. CH0 common lane also contains the IOSF-SB logic for the
+ * Common Register Interface (CRI) ie. the DPIO registers. CRI clock
+ * must be running when any DPIO registers are accessed.
+ *
+ * In addition to having their own registers, the PHYs are also
+ * controlled through some dedicated signals from the display
+ * controller. These include PLL reference clock enable, PLL enable,
+ * and CRI clock selection, for example.
  *
- * DPIO is VLV only.
+ * Eeach channel also has two splines (also called data lanes), and
+ * each spline is made up of one Physical Access Coding Sub-Layer
+ * (PCS) block and two TX lanes. So each channel has two PCS blocks
+ * and four TX lanes. The TX lanes are used as DP lanes or TMDS
+ * data/clock pairs depending on the output type.
+ *
+ * Additionally the PHY also contains an AUX lane with AUX blocks
+ * for each channel. This is used for DP AUX communication, but
+ * this fact isn't really relevant for the driver since AUX is
+ * controlled from the display controller side. No DPIO registers
+ * need to be accessed during AUX communication,
+ *
+ * Generally the common lane corresponds to the pipe and
+ * the spline (PCS/TX) correponds to the port.
+ *
+ * For dual channel PHY (VLV/CHV):
+ *
+ *  pipe A == CMN/PLL/REF CH0
+ *
+ *  pipe B == CMN/PLL/REF CH1
+ *
+ *  port B == PCS/TX CH0
+ *
+ *  port C == PCS/TX CH1
+ *
+ * This is especially important when we cross the streams
+ * ie. drive port B with pipe B, or port C with pipe A.
+ *
+ * For single channel PHY (CHV):
+ *
+ *  pipe C == CMN/PLL/REF CH0
+ *
+ *  port D == PCS/TX CH0
+ *
+ * Note: digital port B is DDI0, digital port C is DDI1,
+ * digital port D is DDI2
+ */
+/*
+ * Dual channel PHY (VLV/CHV)
+ * ---------------------------------
+ * |      CH0      |      CH1      |
+ * |  CMN/PLL/REF  |  CMN/PLL/REF  |
+ * |---------------|---------------| Display PHY
+ * | PCS01 | PCS23 | PCS01 | PCS23 |
+ * |-------|-------|-------|-------|
+ * |TX0|TX1|TX2|TX3|TX0|TX1|TX2|TX3|
+ * ---------------------------------
+ * |     DDI0      |     DDI1      | DP/HDMI ports
+ * ---------------------------------
  *
- * Note: digital port B is DDI0, digital pot C is DDI1
+ * Single channel PHY (CHV)
+ * -----------------
+ * |      CH0      |
+ * |  CMN/PLL/REF  |
+ * |---------------| Display PHY
+ * | PCS01 | PCS23 |
+ * |-------|-------|
+ * |TX0|TX1|TX2|TX3|
+ * -----------------
+ * |     DDI2      | DP/HDMI port
+ * -----------------
  */
 #define DPIO_DEVFN			0
-#define DPIO_OPCODE_REG_WRITE		1
-#define DPIO_OPCODE_REG_READ		0
 
 #define DPIO_CTL			(VLV_DISPLAY_BASE + 0x2110)
 #define  DPIO_MODSEL1			(1<<3) /* if ref clk b == 27 */
@@ -555,14 +736,29 @@ enum punit_power_well {
 #define   DPIO_PCS_TX_LANE1_RESET	(1<<7)
 #define VLV_PCS_DW0(ch) _PORT(ch, _VLV_PCS_DW0_CH0, _VLV_PCS_DW0_CH1)
 
+#define _VLV_PCS01_DW0_CH0		0x200
+#define _VLV_PCS23_DW0_CH0		0x400
+#define _VLV_PCS01_DW0_CH1		0x2600
+#define _VLV_PCS23_DW0_CH1		0x2800
+#define VLV_PCS01_DW0(ch) _PORT(ch, _VLV_PCS01_DW0_CH0, _VLV_PCS01_DW0_CH1)
+#define VLV_PCS23_DW0(ch) _PORT(ch, _VLV_PCS23_DW0_CH0, _VLV_PCS23_DW0_CH1)
+
 #define _VLV_PCS_DW1_CH0		0x8204
 #define _VLV_PCS_DW1_CH1		0x8404
+#define   CHV_PCS_REQ_SOFTRESET_EN	(1<<23)
 #define   DPIO_PCS_CLK_CRI_RXEB_EIOS_EN	(1<<22)
 #define   DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN (1<<21)
 #define   DPIO_PCS_CLK_DATAWIDTH_SHIFT	(6)
 #define   DPIO_PCS_CLK_SOFT_RESET	(1<<5)
 #define VLV_PCS_DW1(ch) _PORT(ch, _VLV_PCS_DW1_CH0, _VLV_PCS_DW1_CH1)
 
+#define _VLV_PCS01_DW1_CH0		0x204
+#define _VLV_PCS23_DW1_CH0		0x404
+#define _VLV_PCS01_DW1_CH1		0x2604
+#define _VLV_PCS23_DW1_CH1		0x2804
+#define VLV_PCS01_DW1(ch) _PORT(ch, _VLV_PCS01_DW1_CH0, _VLV_PCS01_DW1_CH1)
+#define VLV_PCS23_DW1(ch) _PORT(ch, _VLV_PCS23_DW1_CH0, _VLV_PCS23_DW1_CH1)
+
 #define _VLV_PCS_DW8_CH0		0x8220
 #define _VLV_PCS_DW8_CH1		0x8420
 #define VLV_PCS_DW8(ch) _PORT(ch, _VLV_PCS_DW8_CH0, _VLV_PCS_DW8_CH1)
@@ -578,6 +774,19 @@ enum punit_power_well {
 #define _VLV_PCS_DW9_CH1		0x8424
 #define	VLV_PCS_DW9(ch) _PORT(ch, _VLV_PCS_DW9_CH0, _VLV_PCS_DW9_CH1)
 
+#define _CHV_PCS_DW10_CH0		0x8228
+#define _CHV_PCS_DW10_CH1		0x8428
+#define   DPIO_PCS_SWING_CALC_TX0_TX2	(1<<30)
+#define   DPIO_PCS_SWING_CALC_TX1_TX3	(1<<31)
+#define CHV_PCS_DW10(ch) _PORT(ch, _CHV_PCS_DW10_CH0, _CHV_PCS_DW10_CH1)
+
+#define _VLV_PCS01_DW10_CH0		0x0228
+#define _VLV_PCS23_DW10_CH0		0x0428
+#define _VLV_PCS01_DW10_CH1		0x2628
+#define _VLV_PCS23_DW10_CH1		0x2828
+#define VLV_PCS01_DW10(port) _PORT(port, _VLV_PCS01_DW10_CH0, _VLV_PCS01_DW10_CH1)
+#define VLV_PCS23_DW10(port) _PORT(port, _VLV_PCS23_DW10_CH0, _VLV_PCS23_DW10_CH1)
+
 #define _VLV_PCS_DW11_CH0		0x822c
 #define _VLV_PCS_DW11_CH1		0x842c
 #define VLV_PCS_DW11(ch) _PORT(ch, _VLV_PCS_DW11_CH0, _VLV_PCS_DW11_CH1)
@@ -596,14 +805,21 @@ enum punit_power_well {
 
 #define _VLV_TX_DW2_CH0			0x8288
 #define _VLV_TX_DW2_CH1			0x8488
+#define   DPIO_SWING_MARGIN_SHIFT	16
+#define   DPIO_SWING_MARGIN_MASK	(0xff << DPIO_SWING_MARGIN_SHIFT)
+#define   DPIO_UNIQ_TRANS_SCALE_SHIFT	8
 #define VLV_TX_DW2(ch) _PORT(ch, _VLV_TX_DW2_CH0, _VLV_TX_DW2_CH1)
 
 #define _VLV_TX_DW3_CH0			0x828c
 #define _VLV_TX_DW3_CH1			0x848c
+/* The following bit for CHV phy */
+#define   DPIO_TX_UNIQ_TRANS_SCALE_EN	(1<<27)
 #define VLV_TX_DW3(ch) _PORT(ch, _VLV_TX_DW3_CH0, _VLV_TX_DW3_CH1)
 
 #define _VLV_TX_DW4_CH0			0x8290
 #define _VLV_TX_DW4_CH1			0x8490
+#define   DPIO_SWING_DEEMPH9P5_SHIFT	24
+#define   DPIO_SWING_DEEMPH9P5_MASK	(0xff << DPIO_SWING_DEEMPH9P5_SHIFT)
 #define VLV_TX_DW4(ch) _PORT(ch, _VLV_TX_DW4_CH0, _VLV_TX_DW4_CH1)
 
 #define _VLV_TX3_DW4_CH0		0x690
@@ -623,6 +839,73 @@ enum punit_power_well {
 #define _VLV_TX_DW14_CH1		0x84b8
 #define VLV_TX_DW14(ch) _PORT(ch, _VLV_TX_DW14_CH0, _VLV_TX_DW14_CH1)
 
+/* CHV dpPhy registers */
+#define _CHV_PLL_DW0_CH0		0x8000
+#define _CHV_PLL_DW0_CH1		0x8180
+#define CHV_PLL_DW0(ch) _PIPE(ch, _CHV_PLL_DW0_CH0, _CHV_PLL_DW0_CH1)
+
+#define _CHV_PLL_DW1_CH0		0x8004
+#define _CHV_PLL_DW1_CH1		0x8184
+#define   DPIO_CHV_N_DIV_SHIFT		8
+#define   DPIO_CHV_M1_DIV_BY_2		(0 << 0)
+#define CHV_PLL_DW1(ch) _PIPE(ch, _CHV_PLL_DW1_CH0, _CHV_PLL_DW1_CH1)
+
+#define _CHV_PLL_DW2_CH0		0x8008
+#define _CHV_PLL_DW2_CH1		0x8188
+#define CHV_PLL_DW2(ch) _PIPE(ch, _CHV_PLL_DW2_CH0, _CHV_PLL_DW2_CH1)
+
+#define _CHV_PLL_DW3_CH0		0x800c
+#define _CHV_PLL_DW3_CH1		0x818c
+#define  DPIO_CHV_FRAC_DIV_EN		(1 << 16)
+#define  DPIO_CHV_FIRST_MOD		(0 << 8)
+#define  DPIO_CHV_SECOND_MOD		(1 << 8)
+#define  DPIO_CHV_FEEDFWD_GAIN_SHIFT	0
+#define CHV_PLL_DW3(ch) _PIPE(ch, _CHV_PLL_DW3_CH0, _CHV_PLL_DW3_CH1)
+
+#define _CHV_PLL_DW6_CH0		0x8018
+#define _CHV_PLL_DW6_CH1		0x8198
+#define   DPIO_CHV_GAIN_CTRL_SHIFT	16
+#define	  DPIO_CHV_INT_COEFF_SHIFT	8
+#define   DPIO_CHV_PROP_COEFF_SHIFT	0
+#define CHV_PLL_DW6(ch) _PIPE(ch, _CHV_PLL_DW6_CH0, _CHV_PLL_DW6_CH1)
+
+#define _CHV_CMN_DW13_CH0		0x8134
+#define _CHV_CMN_DW0_CH1		0x8080
+#define   DPIO_CHV_S1_DIV_SHIFT		21
+#define   DPIO_CHV_P1_DIV_SHIFT		13 /* 3 bits */
+#define   DPIO_CHV_P2_DIV_SHIFT		8  /* 5 bits */
+#define   DPIO_CHV_K_DIV_SHIFT		4
+#define   DPIO_PLL_FREQLOCK		(1 << 1)
+#define   DPIO_PLL_LOCK			(1 << 0)
+#define CHV_CMN_DW13(ch) _PIPE(ch, _CHV_CMN_DW13_CH0, _CHV_CMN_DW0_CH1)
+
+#define _CHV_CMN_DW14_CH0		0x8138
+#define _CHV_CMN_DW1_CH1		0x8084
+#define   DPIO_AFC_RECAL		(1 << 14)
+#define   DPIO_DCLKP_EN			(1 << 13)
+#define CHV_CMN_DW14(ch) _PIPE(ch, _CHV_CMN_DW14_CH0, _CHV_CMN_DW1_CH1)
+
+#define CHV_CMN_DW30			0x8178
+#define   DPIO_LRC_BYPASS		(1 << 3)
+
+#define _TXLANE(ch, lane, offset) ((ch ? 0x2400 : 0) + \
+					(lane) * 0x200 + (offset))
+
+#define CHV_TX_DW0(ch, lane) _TXLANE(ch, lane, 0x80)
+#define CHV_TX_DW1(ch, lane) _TXLANE(ch, lane, 0x84)
+#define CHV_TX_DW2(ch, lane) _TXLANE(ch, lane, 0x88)
+#define CHV_TX_DW3(ch, lane) _TXLANE(ch, lane, 0x8c)
+#define CHV_TX_DW4(ch, lane) _TXLANE(ch, lane, 0x90)
+#define CHV_TX_DW5(ch, lane) _TXLANE(ch, lane, 0x94)
+#define CHV_TX_DW6(ch, lane) _TXLANE(ch, lane, 0x98)
+#define CHV_TX_DW7(ch, lane) _TXLANE(ch, lane, 0x9c)
+#define CHV_TX_DW8(ch, lane) _TXLANE(ch, lane, 0xa0)
+#define CHV_TX_DW9(ch, lane) _TXLANE(ch, lane, 0xa4)
+#define CHV_TX_DW10(ch, lane) _TXLANE(ch, lane, 0xa8)
+#define CHV_TX_DW11(ch, lane) _TXLANE(ch, lane, 0xac)
+#define   DPIO_FRC_LATENCY_SHFIT	8
+#define CHV_TX_DW14(ch, lane) _TXLANE(ch, lane, 0xb8)
+#define   DPIO_UPAR_SHIFT		30
 /*
  * Fence registers
  */
@@ -659,10 +942,14 @@ enum punit_power_well {
 /*
  * Instruction and interrupt control regs
  */
+#define PGTBL_CTL	0x02020
+#define   PGTBL_ADDRESS_LO_MASK	0xfffff000 /* bits [31:12] */
+#define   PGTBL_ADDRESS_HI_MASK	0x000000f0 /* bits [35:32] (gen4) */
 #define PGTBL_ER	0x02024
 #define RENDER_RING_BASE	0x02000
 #define BSD_RING_BASE		0x04000
 #define GEN6_BSD_RING_BASE	0x12000
+#define GEN8_BSD2_RING_BASE	0x1c000
 #define VEBOX_RING_BASE		0x1a000
 #define BLT_RING_BASE		0x22000
 #define RING_TAIL(base)		((base)+0x30)
@@ -688,9 +975,20 @@ enum punit_power_well {
 #define RING_MAX_IDLE(base)	((base)+0x54)
 #define RING_HWS_PGA(base)	((base)+0x80)
 #define RING_HWS_PGA_GEN6(base)	((base)+0x2080)
-#define ARB_MODE		0x04030
+
+#define GEN7_WR_WATERMARK	0x4028
+#define GEN7_GFX_PRIO_CTRL	0x402C
+#define ARB_MODE		0x4030
 #define   ARB_MODE_SWIZZLE_SNB	(1<<4)
 #define   ARB_MODE_SWIZZLE_IVB	(1<<5)
+#define GEN7_GFX_PEND_TLB0	0x4034
+#define GEN7_GFX_PEND_TLB1	0x4038
+/* L3, CVS, ZTLB, RCC, CASC LRA min, max values */
+#define GEN7_LRA_LIMITS_BASE	0x403C
+#define GEN7_LRA_LIMITS_REG_NUM	13
+#define GEN7_MEDIA_MAX_REQ_COUNT	0x4070
+#define GEN7_GFX_MAX_REQ_COUNT		0x4074
+
 #define GAMTARBMODE		0x04a08
 #define   ARB_MODE_BWGTLB_DISABLE (1<<9)
 #define   ARB_MODE_SWIZZLE_BDW	(1<<1)
@@ -725,6 +1023,9 @@ enum punit_power_well {
 #define   RING_WAIT_I8XX	(1<<0) /* gen2, PRBx_HEAD */
 #define   RING_WAIT		(1<<11) /* gen3+, PRBx_CTL */
 #define   RING_WAIT_SEMAPHORE	(1<<10) /* gen6+ */
+
+#define GEN7_TLB_RD_ADDR	0x4700
+
 #if 0
 #define PRB0_TAIL	0x02030
 #define PRB0_HEAD	0x02034
@@ -748,6 +1049,7 @@ enum punit_power_well {
 #define RING_INSTDONE(base)	((base)+0x6c)
 #define RING_INSTPS(base)	((base)+0x70)
 #define RING_DMA_FADD(base)	((base)+0x78)
+#define RING_DMA_FADD_UDW(base)	((base)+0x60) /* gen8+ */
 #define RING_INSTPM(base)	((base)+0xc0)
 #define RING_MI_MODE(base)	((base)+0x9c)
 #define INSTPS		0x02070 /* 965+ only */
@@ -842,21 +1144,26 @@ enum punit_power_well {
 #define GFX_MODE_GEN7	0x0229c
 #define RING_MODE_GEN7(ring)	((ring)->mmio_base+0x29c)
 #define   GFX_RUN_LIST_ENABLE		(1<<15)
-#define   GFX_TLB_INVALIDATE_ALWAYS	(1<<13)
+#define   GFX_TLB_INVALIDATE_EXPLICIT	(1<<13)
 #define   GFX_SURFACE_FAULT_ENABLE	(1<<12)
 #define   GFX_REPLAY_MODE		(1<<11)
 #define   GFX_PSMI_GRANULARITY		(1<<10)
 #define   GFX_PPGTT_ENABLE		(1<<9)
 
 #define VLV_DISPLAY_BASE 0x180000
+#define VLV_MIPI_BASE VLV_DISPLAY_BASE
 
+#define VLV_GU_CTL0	(VLV_DISPLAY_BASE + 0x2030)
+#define VLV_GU_CTL1	(VLV_DISPLAY_BASE + 0x2034)
 #define SCPD0		0x0209c /* 915+ only */
 #define IER		0x020a0
 #define IIR		0x020a4
 #define IMR		0x020a8
 #define ISR		0x020ac
 #define VLV_GUNIT_CLOCK_GATE	(VLV_DISPLAY_BASE + 0x2060)
+#define   GINT_DIS		(1<<22)
 #define   GCFG_DIS		(1<<8)
+#define VLV_GUNIT_CLOCK_GATE2	(VLV_DISPLAY_BASE + 0x2064)
 #define VLV_IIR_RW	(VLV_DISPLAY_BASE + 0x2084)
 #define VLV_IER		(VLV_DISPLAY_BASE + 0x20a0)
 #define VLV_IIR		(VLV_DISPLAY_BASE + 0x20a4)
@@ -875,7 +1182,7 @@ enum punit_power_well {
 #define   I915_ERROR_INSTRUCTION			(1<<0)
 #define INSTPM	        0x020c0
 #define   INSTPM_SELF_EN (1<<12) /* 915GM only */
-#define   INSTPM_AGPBUSY_DIS (1<<11) /* gen3: when disabled, pending interrupts
+#define   INSTPM_AGPBUSY_INT_EN (1<<11) /* gen3: when disabled, pending interrupts
 					will not assert AGPBUSY# and will only
 					be delivered when out of C3. */
 #define   INSTPM_FORCE_ORDERING				(1<<7) /* GEN6+ */
@@ -956,6 +1263,10 @@ enum punit_power_well {
 #define   MI_ARB_DISPLAY_PRIORITY_A_B		(0 << 0)	/* display A > display B */
 #define   MI_ARB_DISPLAY_PRIORITY_B_A		(1 << 0)	/* display B > display A */
 
+#define MI_STATE	0x020e4 /* gen2 only */
+#define   MI_AGPBUSY_INT_EN			(1 << 1) /* 85x only */
+#define   MI_AGPBUSY_830_MODE			(1 << 0) /* 85x only */
+
 #define CACHE_MODE_0	0x02120 /* 915+ only */
 #define   CM0_PIPELINED_RENDER_FLUSH_DISABLE (1<<8)
 #define   CM0_IZ_OPT_DISABLE      (1<<6)
@@ -973,6 +1284,7 @@ enum punit_power_well {
 #define   ECO_FLIP_DONE		(1<<0)
 
 #define CACHE_MODE_0_GEN7	0x7000 /* IVB+ */
+#define RC_OP_FLUSH_ENABLE (1<<0)
 #define   HIZ_RAW_STALL_OPT_DISABLE (1<<2)
 #define CACHE_MODE_1		0x7004 /* IVB+ */
 #define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	(1<<6)
@@ -984,6 +1296,7 @@ enum punit_power_well {
 
 #define GEN6_RC_SLEEP_PSMI_CONTROL	0x2050
 #define   GEN8_RC_SEMA_IDLE_MSG_DISABLE	(1 << 12)
+#define   GEN8_FF_DOP_CLOCK_GATE_DISABLE	(1<<10)
 
 #define GEN6_BSD_SLEEP_PSMI_CONTROL	0x12050
 #define   GEN6_BSD_SLEEP_MSG_DISABLE	(1 << 0)
@@ -1024,24 +1337,43 @@ enum punit_power_well {
 
 /* These are all the "old" interrupts */
 #define ILK_BSD_USER_INTERRUPT				(1<<5)
+
+#define I915_PM_INTERRUPT				(1<<31)
+#define I915_ISP_INTERRUPT				(1<<22)
+#define I915_LPE_PIPE_B_INTERRUPT			(1<<21)
+#define I915_LPE_PIPE_A_INTERRUPT			(1<<20)
+#define I915_MIPIB_INTERRUPT				(1<<19)
+#define I915_MIPIA_INTERRUPT				(1<<18)
 #define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
 #define I915_DISPLAY_PORT_INTERRUPT			(1<<17)
+#define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT		(1<<16)
+#define I915_MASTER_ERROR_INTERRUPT			(1<<15)
 #define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT	(1<<15)
+#define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT		(1<<14)
 #define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT	(1<<14) /* p-state */
+#define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT		(1<<13)
 #define I915_HWB_OOM_INTERRUPT				(1<<13)
+#define I915_LPE_PIPE_C_INTERRUPT			(1<<12)
 #define I915_SYNC_STATUS_INTERRUPT			(1<<12)
+#define I915_MISC_INTERRUPT				(1<<11)
 #define I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT	(1<<11)
+#define I915_DISPLAY_PIPE_C_VBLANK_INTERRUPT		(1<<10)
 #define I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT	(1<<10)
+#define I915_DISPLAY_PIPE_C_EVENT_INTERRUPT		(1<<9)
 #define I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT	(1<<9)
+#define I915_DISPLAY_PIPE_C_DPBM_INTERRUPT		(1<<8)
 #define I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT	(1<<8)
 #define I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT		(1<<7)
 #define I915_DISPLAY_PIPE_A_EVENT_INTERRUPT		(1<<6)
 #define I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT		(1<<5)
 #define I915_DISPLAY_PIPE_B_EVENT_INTERRUPT		(1<<4)
+#define I915_DISPLAY_PIPE_A_DPBM_INTERRUPT		(1<<3)
+#define I915_DISPLAY_PIPE_B_DPBM_INTERRUPT		(1<<2)
 #define I915_DEBUG_INTERRUPT				(1<<2)
+#define I915_WINVALID_INTERRUPT				(1<<1)
 #define I915_USER_INTERRUPT				(1<<1)
 #define I915_ASLE_INTERRUPT				(1<<0)
-#define I915_BSD_USER_INTERRUPT				(1 << 25)
+#define I915_BSD_USER_INTERRUPT				(1<<25)
 
 #define GEN6_BSD_RNCID			0x12198
 
@@ -1198,6 +1530,7 @@ enum punit_power_well {
 #define   GMBUS_PORT_SSC	1
 #define   GMBUS_PORT_VGADDC	2
 #define   GMBUS_PORT_PANEL	3
+#define   GMBUS_PORT_DPD_CHV	3 /* HDMID_CHV */
 #define   GMBUS_PORT_DPC	4 /* HDMIC */
 #define   GMBUS_PORT_DPB	5 /* SDVO, HDMIB */
 #define   GMBUS_PORT_DPD	6 /* HDMID */
@@ -1239,6 +1572,7 @@ enum punit_power_well {
  */
 #define DPLL_A_OFFSET 0x6014
 #define DPLL_B_OFFSET 0x6018
+#define CHV_DPLL_C_OFFSET 0x6030
 #define DPLL(pipe) (dev_priv->info.dpll_offsets[pipe] + \
 		    dev_priv->info.display_mmio_offset)
 
@@ -1273,10 +1607,23 @@ enum punit_power_well {
 #define   DPLL_LOCK_VLV			(1<<15)
 #define   DPLL_INTEGRATED_CRI_CLK_VLV	(1<<14)
 #define   DPLL_INTEGRATED_CLOCK_VLV	(1<<13)
+#define   DPLL_SSC_REF_CLOCK_CHV	(1<<13)
 #define   DPLL_PORTC_READY_MASK		(0xf << 4)
 #define   DPLL_PORTB_READY_MASK		(0xf)
 
 #define   DPLL_FPA01_P1_POST_DIV_MASK_I830	0x001f0000
+
+/* Additional CHV pll/phy registers */
+#define DPIO_PHY_STATUS			(VLV_DISPLAY_BASE + 0x6240)
+#define   DPLL_PORTD_READY_MASK		(0xf)
+#define DISPLAY_PHY_CONTROL (VLV_DISPLAY_BASE + 0x60100)
+#define   PHY_COM_LANE_RESET_DEASSERT(phy, val) \
+				((phy == DPIO_PHY0) ? (val | 1) : (val | 2))
+#define   PHY_COM_LANE_RESET_ASSERT(phy, val) \
+				((phy == DPIO_PHY0) ? (val & ~1) : (val & ~2))
+#define DISPLAY_PHY_STATUS (VLV_DISPLAY_BASE + 0x60104)
+#define   PHY_POWERGOOD(phy)	((phy == DPIO_PHY0) ? (1<<31) : (1<<30))
+
 /*
  * The i830 generation, in LVDS mode, defines P1 as the bit number set within
  * this field (only one bit may be set).
@@ -1317,6 +1664,7 @@ enum punit_power_well {
 
 #define DPLL_A_MD_OFFSET 0x601c /* 965+ only */
 #define DPLL_B_MD_OFFSET 0x6020 /* 965+ only */
+#define CHV_DPLL_C_MD_OFFSET 0x603c
 #define DPLL_MD(pipe) (dev_priv->info.dpll_md_offsets[pipe] + \
 		       dev_priv->info.display_mmio_offset)
 
@@ -1416,7 +1764,7 @@ enum punit_power_well {
 # define DPIOUNIT_CLOCK_GATE_DISABLE		(1 << 6) /* 915-945 */
 # define OVFUNIT_CLOCK_GATE_DISABLE		(1 << 5)
 # define OVBUNIT_CLOCK_GATE_DISABLE		(1 << 4)
-/**
+/*
  * This bit must be set on the 830 to prevent hangs when turning off the
  * overlay scaler.
  */
@@ -1436,12 +1784,12 @@ enum punit_power_well {
 # define COLOR_CALCULATOR_CLOCK_GATE_DISABLE	(1 << 7)
 # define MOTION_COMP_CLOCK_GATE_DISABLE		(1 << 6)
 # define MAG_CLOCK_GATE_DISABLE			(1 << 5)
-/** This bit must be unset on 855,865 */
+/* This bit must be unset on 855,865 */
 # define MECI_CLOCK_GATE_DISABLE		(1 << 4)
 # define DCMP_CLOCK_GATE_DISABLE		(1 << 3)
 # define MEC_CLOCK_GATE_DISABLE			(1 << 2)
 # define MECO_CLOCK_GATE_DISABLE		(1 << 1)
-/** This bit must be set on 855,865. */
+/* This bit must be set on 855,865. */
 # define SV_CLOCK_GATE_DISABLE			(1 << 0)
 # define I915_MPEG_CLOCK_GATE_DISABLE		(1 << 16)
 # define I915_VLD_IP_PR_CLOCK_GATE_DISABLE	(1 << 15)
@@ -1462,14 +1810,14 @@ enum punit_power_well {
 # define I915_BY_CLOCK_GATE_DISABLE		(1 << 0)
 
 # define I965_RCZ_CLOCK_GATE_DISABLE		(1 << 30)
-/** This bit must always be set on 965G/965GM */
+/* This bit must always be set on 965G/965GM */
 # define I965_RCC_CLOCK_GATE_DISABLE		(1 << 29)
 # define I965_RCPB_CLOCK_GATE_DISABLE		(1 << 28)
 # define I965_DAP_CLOCK_GATE_DISABLE		(1 << 27)
 # define I965_ROC_CLOCK_GATE_DISABLE		(1 << 26)
 # define I965_GW_CLOCK_GATE_DISABLE		(1 << 25)
 # define I965_TD_CLOCK_GATE_DISABLE		(1 << 24)
-/** This bit must always be set on 965G */
+/* This bit must always be set on 965G */
 # define I965_ISC_CLOCK_GATE_DISABLE		(1 << 23)
 # define I965_IC_CLOCK_GATE_DISABLE		(1 << 22)
 # define I965_EU_CLOCK_GATE_DISABLE		(1 << 21)
@@ -1494,6 +1842,10 @@ enum punit_power_well {
 #define VF_UNIT_CLOCK_GATE_DISABLE		(1 << 9)
 #define GS_UNIT_CLOCK_GATE_DISABLE		(1 << 7)
 #define CL_UNIT_CLOCK_GATE_DISABLE		(1 << 6)
+
+#define VDECCLK_GATE_D		0x620C		/* g4x only */
+#define  VCP_UNIT_CLOCK_GATE_DISABLE		(1 << 4)
+
 #define RAMCLK_GATE_D		0x6210		/* CRL only */
 #define DEUC			0x6214          /* CRL only */
 
@@ -1513,6 +1865,7 @@ enum punit_power_well {
  */
 #define PALETTE_A_OFFSET 0xa000
 #define PALETTE_B_OFFSET 0xa800
+#define CHV_PALETTE_C_OFFSET 0xc000
 #define PALETTE(pipe) (dev_priv->info.palette_offsets[pipe] + \
 		       dev_priv->info.display_mmio_offset)
 
@@ -1535,7 +1888,7 @@ enum punit_power_well {
 /* Memory controller frequency in MCHBAR for Haswell (possible SNB+) */
 #define DCLK (MCHBAR_MIRROR_BASE_SNB + 0x5e04)
 
-/** 915-945 and GM965 MCH register controlling DRAM channel access */
+/* 915-945 and GM965 MCH register controlling DRAM channel access */
 #define DCC			0x10200
 #define DCC_ADDRESSING_MODE_SINGLE_CHANNEL		(0 << 0)
 #define DCC_ADDRESSING_MODE_DUAL_CHANNEL_ASYMMETRIC	(1 << 0)
@@ -1544,15 +1897,15 @@ enum punit_power_well {
 #define DCC_CHANNEL_XOR_DISABLE				(1 << 10)
 #define DCC_CHANNEL_XOR_BIT_17				(1 << 9)
 
-/** Pineview MCH register contains DDR3 setting */
+/* Pineview MCH register contains DDR3 setting */
 #define CSHRDDR3CTL            0x101a8
 #define CSHRDDR3CTL_DDR3       (1 << 2)
 
-/** 965 MCH register controlling DRAM channel configuration */
+/* 965 MCH register controlling DRAM channel configuration */
 #define C0DRB3			0x10206
 #define C1DRB3			0x10606
 
-/** snb MCH registers for reading the DRAM channel configuration */
+/* snb MCH registers for reading the DRAM channel configuration */
 #define MAD_DIMM_C0			(MCHBAR_MIRROR_BASE_SNB + 0x5004)
 #define MAD_DIMM_C1			(MCHBAR_MIRROR_BASE_SNB + 0x5008)
 #define MAD_DIMM_C2			(MCHBAR_MIRROR_BASE_SNB + 0x500C)
@@ -1574,7 +1927,7 @@ enum punit_power_well {
 #define   MAD_DIMM_A_SIZE_SHIFT		0
 #define   MAD_DIMM_A_SIZE_MASK		(0xff << MAD_DIMM_A_SIZE_SHIFT)
 
-/** snb MCH registers for priority tuning */
+/* snb MCH registers for priority tuning */
 #define MCH_SSKPD			(MCHBAR_MIRROR_BASE_SNB + 0x5d10)
 #define   MCH_SSKPD_WM0_MASK		0x3f
 #define   MCH_SSKPD_WM0_VAL		0xc
@@ -2002,6 +2355,7 @@ enum punit_power_well {
 #define TRANSCODER_A_OFFSET 0x60000
 #define TRANSCODER_B_OFFSET 0x61000
 #define TRANSCODER_C_OFFSET 0x62000
+#define CHV_TRANSCODER_C_OFFSET 0x63000
 #define TRANSCODER_EDP_OFFSET 0x6f000
 
 #define _TRANSCODER2(pipe, reg) (dev_priv->info.trans_offsets[(pipe)] - \
@@ -2226,6 +2580,7 @@ enum punit_power_well {
 #define GEN3_SDVOC	0x61160
 #define GEN4_HDMIB	GEN3_SDVOB
 #define GEN4_HDMIC	GEN3_SDVOC
+#define CHV_HDMID	0x6116C
 #define PCH_SDVOB	0xe1140
 #define PCH_HDMIB	PCH_SDVOB
 #define PCH_HDMIC	0xe1150
@@ -2246,7 +2601,7 @@ enum punit_power_well {
 #define   SDVO_PIPE_B_SELECT			(1 << 30)
 #define   SDVO_STALL_SELECT			(1 << 29)
 #define   SDVO_INTERRUPT_ENABLE			(1 << 26)
-/**
+/*
  * 915G/GM SDVO pixel multiplier.
  * Programmed value is multiplier - 1, up to 5x.
  * \sa DPLL_MD_UDI_MULTIPLIER_MASK
@@ -2286,6 +2641,10 @@ enum punit_power_well {
 #define   SDVO_PIPE_SEL_CPT(pipe)		((pipe) << 29)
 #define   SDVO_PIPE_SEL_MASK_CPT		(3 << 29)
 
+/* CHV SDVO/HDMI bits: */
+#define   SDVO_PIPE_SEL_CHV(pipe)		((pipe) << 24)
+#define   SDVO_PIPE_SEL_MASK_CHV		(3 << 24)
+
 
 /* DVO port control */
 #define DVOA			0x61120
@@ -2556,65 +2915,65 @@ enum punit_power_well {
 
 /* TV port control */
 #define TV_CTL			0x68000
-/** Enables the TV encoder */
+/* Enables the TV encoder */
 # define TV_ENC_ENABLE			(1 << 31)
-/** Sources the TV encoder input from pipe B instead of A. */
+/* Sources the TV encoder input from pipe B instead of A. */
 # define TV_ENC_PIPEB_SELECT		(1 << 30)
-/** Outputs composite video (DAC A only) */
+/* Outputs composite video (DAC A only) */
 # define TV_ENC_OUTPUT_COMPOSITE	(0 << 28)
-/** Outputs SVideo video (DAC B/C) */
+/* Outputs SVideo video (DAC B/C) */
 # define TV_ENC_OUTPUT_SVIDEO		(1 << 28)
-/** Outputs Component video (DAC A/B/C) */
+/* Outputs Component video (DAC A/B/C) */
 # define TV_ENC_OUTPUT_COMPONENT	(2 << 28)
-/** Outputs Composite and SVideo (DAC A/B/C) */
+/* Outputs Composite and SVideo (DAC A/B/C) */
 # define TV_ENC_OUTPUT_SVIDEO_COMPOSITE	(3 << 28)
 # define TV_TRILEVEL_SYNC		(1 << 21)
-/** Enables slow sync generation (945GM only) */
+/* Enables slow sync generation (945GM only) */
 # define TV_SLOW_SYNC			(1 << 20)
-/** Selects 4x oversampling for 480i and 576p */
+/* Selects 4x oversampling for 480i and 576p */
 # define TV_OVERSAMPLE_4X		(0 << 18)
-/** Selects 2x oversampling for 720p and 1080i */
+/* Selects 2x oversampling for 720p and 1080i */
 # define TV_OVERSAMPLE_2X		(1 << 18)
-/** Selects no oversampling for 1080p */
+/* Selects no oversampling for 1080p */
 # define TV_OVERSAMPLE_NONE		(2 << 18)
-/** Selects 8x oversampling */
+/* Selects 8x oversampling */
 # define TV_OVERSAMPLE_8X		(3 << 18)
-/** Selects progressive mode rather than interlaced */
+/* Selects progressive mode rather than interlaced */
 # define TV_PROGRESSIVE			(1 << 17)
-/** Sets the colorburst to PAL mode.  Required for non-M PAL modes. */
+/* Sets the colorburst to PAL mode.  Required for non-M PAL modes. */
 # define TV_PAL_BURST			(1 << 16)
-/** Field for setting delay of Y compared to C */
+/* Field for setting delay of Y compared to C */
 # define TV_YC_SKEW_MASK		(7 << 12)
-/** Enables a fix for 480p/576p standard definition modes on the 915GM only */
+/* Enables a fix for 480p/576p standard definition modes on the 915GM only */
 # define TV_ENC_SDP_FIX			(1 << 11)
-/**
+/*
  * Enables a fix for the 915GM only.
  *
  * Not sure what it does.
  */
 # define TV_ENC_C0_FIX			(1 << 10)
-/** Bits that must be preserved by software */
+/* Bits that must be preserved by software */
 # define TV_CTL_SAVE			((1 << 11) | (3 << 9) | (7 << 6) | 0xf)
 # define TV_FUSE_STATE_MASK		(3 << 4)
-/** Read-only state that reports all features enabled */
+/* Read-only state that reports all features enabled */
 # define TV_FUSE_STATE_ENABLED		(0 << 4)
-/** Read-only state that reports that Macrovision is disabled in hardware*/
+/* Read-only state that reports that Macrovision is disabled in hardware*/
 # define TV_FUSE_STATE_NO_MACROVISION	(1 << 4)
-/** Read-only state that reports that TV-out is disabled in hardware. */
+/* Read-only state that reports that TV-out is disabled in hardware. */
 # define TV_FUSE_STATE_DISABLED		(2 << 4)
-/** Normal operation */
+/* Normal operation */
 # define TV_TEST_MODE_NORMAL		(0 << 0)
-/** Encoder test pattern 1 - combo pattern */
+/* Encoder test pattern 1 - combo pattern */
 # define TV_TEST_MODE_PATTERN_1		(1 << 0)
-/** Encoder test pattern 2 - full screen vertical 75% color bars */
+/* Encoder test pattern 2 - full screen vertical 75% color bars */
 # define TV_TEST_MODE_PATTERN_2		(2 << 0)
-/** Encoder test pattern 3 - full screen horizontal 75% color bars */
+/* Encoder test pattern 3 - full screen horizontal 75% color bars */
 # define TV_TEST_MODE_PATTERN_3		(3 << 0)
-/** Encoder test pattern 4 - random noise */
+/* Encoder test pattern 4 - random noise */
 # define TV_TEST_MODE_PATTERN_4		(4 << 0)
-/** Encoder test pattern 5 - linear color ramps */
+/* Encoder test pattern 5 - linear color ramps */
 # define TV_TEST_MODE_PATTERN_5		(5 << 0)
-/**
+/*
  * This test mode forces the DACs to 50% of full output.
  *
  * This is used for load detection in combination with TVDAC_SENSE_MASK
@@ -2624,35 +2983,35 @@ enum punit_power_well {
 
 #define TV_DAC			0x68004
 # define TV_DAC_SAVE		0x00ffff00
-/**
+/*
  * Reports that DAC state change logic has reported change (RO).
  *
  * This gets cleared when TV_DAC_STATE_EN is cleared
 */
 # define TVDAC_STATE_CHG		(1 << 31)
 # define TVDAC_SENSE_MASK		(7 << 28)
-/** Reports that DAC A voltage is above the detect threshold */
+/* Reports that DAC A voltage is above the detect threshold */
 # define TVDAC_A_SENSE			(1 << 30)
-/** Reports that DAC B voltage is above the detect threshold */
+/* Reports that DAC B voltage is above the detect threshold */
 # define TVDAC_B_SENSE			(1 << 29)
-/** Reports that DAC C voltage is above the detect threshold */
+/* Reports that DAC C voltage is above the detect threshold */
 # define TVDAC_C_SENSE			(1 << 28)
-/**
+/*
  * Enables DAC state detection logic, for load-based TV detection.
  *
  * The PLL of the chosen pipe (in TV_CTL) must be running, and the encoder set
  * to off, for load detection to work.
  */
 # define TVDAC_STATE_CHG_EN		(1 << 27)
-/** Sets the DAC A sense value to high */
+/* Sets the DAC A sense value to high */
 # define TVDAC_A_SENSE_CTL		(1 << 26)
-/** Sets the DAC B sense value to high */
+/* Sets the DAC B sense value to high */
 # define TVDAC_B_SENSE_CTL		(1 << 25)
-/** Sets the DAC C sense value to high */
+/* Sets the DAC C sense value to high */
 # define TVDAC_C_SENSE_CTL		(1 << 24)
-/** Overrides the ENC_ENABLE and DAC voltage levels */
+/* Overrides the ENC_ENABLE and DAC voltage levels */
 # define DAC_CTL_OVERRIDE		(1 << 7)
-/** Sets the slew rate.  Must be preserved in software */
+/* Sets the slew rate.  Must be preserved in software */
 # define ENC_TVDAC_SLEW_FAST		(1 << 6)
 # define DAC_A_1_3_V			(0 << 4)
 # define DAC_A_1_1_V			(1 << 4)
@@ -2667,7 +3026,7 @@ enum punit_power_well {
 # define DAC_C_0_7_V			(2 << 0)
 # define DAC_C_MASK			(3 << 0)
 
-/**
+/*
  * CSC coefficients are stored in a floating point format with 9 bits of
  * mantissa and 2 or 3 bits of exponent.  The exponent is represented as 2**-n,
  * where 2-bit exponents are unsigned n, and 3-bit exponents are signed n with
@@ -2682,7 +3041,7 @@ enum punit_power_well {
 #define TV_CSC_Y2		0x68014
 # define TV_BY_MASK			0x07ff0000
 # define TV_BY_SHIFT			16
-/**
+/*
  * Y attenuation for component video.
  *
  * Stored in 1.9 fixed point.
@@ -2699,7 +3058,7 @@ enum punit_power_well {
 #define TV_CSC_U2		0x6801c
 # define TV_BU_MASK			0x07ff0000
 # define TV_BU_SHIFT			16
-/**
+/*
  * U attenuation for component video.
  *
  * Stored in 1.9 fixed point.
@@ -2716,7 +3075,7 @@ enum punit_power_well {
 #define TV_CSC_V2		0x68024
 # define TV_BV_MASK			0x07ff0000
 # define TV_BV_SHIFT			16
-/**
+/*
  * V attenuation for component video.
  *
  * Stored in 1.9 fixed point.
@@ -2725,74 +3084,74 @@ enum punit_power_well {
 # define TV_AV_SHIFT			0
 
 #define TV_CLR_KNOBS		0x68028
-/** 2s-complement brightness adjustment */
+/* 2s-complement brightness adjustment */
 # define TV_BRIGHTNESS_MASK		0xff000000
 # define TV_BRIGHTNESS_SHIFT		24
-/** Contrast adjustment, as a 2.6 unsigned floating point number */
+/* Contrast adjustment, as a 2.6 unsigned floating point number */
 # define TV_CONTRAST_MASK		0x00ff0000
 # define TV_CONTRAST_SHIFT		16
-/** Saturation adjustment, as a 2.6 unsigned floating point number */
+/* Saturation adjustment, as a 2.6 unsigned floating point number */
 # define TV_SATURATION_MASK		0x0000ff00
 # define TV_SATURATION_SHIFT		8
-/** Hue adjustment, as an integer phase angle in degrees */
+/* Hue adjustment, as an integer phase angle in degrees */
 # define TV_HUE_MASK			0x000000ff
 # define TV_HUE_SHIFT			0
 
 #define TV_CLR_LEVEL		0x6802c
-/** Controls the DAC level for black */
+/* Controls the DAC level for black */
 # define TV_BLACK_LEVEL_MASK		0x01ff0000
 # define TV_BLACK_LEVEL_SHIFT		16
-/** Controls the DAC level for blanking */
+/* Controls the DAC level for blanking */
 # define TV_BLANK_LEVEL_MASK		0x000001ff
 # define TV_BLANK_LEVEL_SHIFT		0
 
 #define TV_H_CTL_1		0x68030
-/** Number of pixels in the hsync. */
+/* Number of pixels in the hsync. */
 # define TV_HSYNC_END_MASK		0x1fff0000
 # define TV_HSYNC_END_SHIFT		16
-/** Total number of pixels minus one in the line (display and blanking). */
+/* Total number of pixels minus one in the line (display and blanking). */
 # define TV_HTOTAL_MASK			0x00001fff
 # define TV_HTOTAL_SHIFT		0
 
 #define TV_H_CTL_2		0x68034
-/** Enables the colorburst (needed for non-component color) */
+/* Enables the colorburst (needed for non-component color) */
 # define TV_BURST_ENA			(1 << 31)
-/** Offset of the colorburst from the start of hsync, in pixels minus one. */
+/* Offset of the colorburst from the start of hsync, in pixels minus one. */
 # define TV_HBURST_START_SHIFT		16
 # define TV_HBURST_START_MASK		0x1fff0000
-/** Length of the colorburst */
+/* Length of the colorburst */
 # define TV_HBURST_LEN_SHIFT		0
 # define TV_HBURST_LEN_MASK		0x0001fff
 
 #define TV_H_CTL_3		0x68038
-/** End of hblank, measured in pixels minus one from start of hsync */
+/* End of hblank, measured in pixels minus one from start of hsync */
 # define TV_HBLANK_END_SHIFT		16
 # define TV_HBLANK_END_MASK		0x1fff0000
-/** Start of hblank, measured in pixels minus one from start of hsync */
+/* Start of hblank, measured in pixels minus one from start of hsync */
 # define TV_HBLANK_START_SHIFT		0
 # define TV_HBLANK_START_MASK		0x0001fff
 
 #define TV_V_CTL_1		0x6803c
-/** XXX */
+/* XXX */
 # define TV_NBR_END_SHIFT		16
 # define TV_NBR_END_MASK		0x07ff0000
-/** XXX */
+/* XXX */
 # define TV_VI_END_F1_SHIFT		8
 # define TV_VI_END_F1_MASK		0x00003f00
-/** XXX */
+/* XXX */
 # define TV_VI_END_F2_SHIFT		0
 # define TV_VI_END_F2_MASK		0x0000003f
 
 #define TV_V_CTL_2		0x68040
-/** Length of vsync, in half lines */
+/* Length of vsync, in half lines */
 # define TV_VSYNC_LEN_MASK		0x07ff0000
 # define TV_VSYNC_LEN_SHIFT		16
-/** Offset of the start of vsync in field 1, measured in one less than the
+/* Offset of the start of vsync in field 1, measured in one less than the
  * number of half lines.
  */
 # define TV_VSYNC_START_F1_MASK		0x00007f00
 # define TV_VSYNC_START_F1_SHIFT	8
-/**
+/*
  * Offset of the start of vsync in field 2, measured in one less than the
  * number of half lines.
  */
@@ -2800,17 +3159,17 @@ enum punit_power_well {
 # define TV_VSYNC_START_F2_SHIFT	0
 
 #define TV_V_CTL_3		0x68044
-/** Enables generation of the equalization signal */
+/* Enables generation of the equalization signal */
 # define TV_EQUAL_ENA			(1 << 31)
-/** Length of vsync, in half lines */
+/* Length of vsync, in half lines */
 # define TV_VEQ_LEN_MASK		0x007f0000
 # define TV_VEQ_LEN_SHIFT		16
-/** Offset of the start of equalization in field 1, measured in one less than
+/* Offset of the start of equalization in field 1, measured in one less than
  * the number of half lines.
  */
 # define TV_VEQ_START_F1_MASK		0x0007f00
 # define TV_VEQ_START_F1_SHIFT		8
-/**
+/*
  * Offset of the start of equalization in field 2, measured in one less than
  * the number of half lines.
  */
@@ -2818,13 +3177,13 @@ enum punit_power_well {
 # define TV_VEQ_START_F2_SHIFT		0
 
 #define TV_V_CTL_4		0x68048
-/**
+/*
  * Offset to start of vertical colorburst, measured in one less than the
  * number of lines from vertical start.
  */
 # define TV_VBURST_START_F1_MASK	0x003f0000
 # define TV_VBURST_START_F1_SHIFT	16
-/**
+/*
  * Offset to the end of vertical colorburst, measured in one less than the
  * number of lines from the start of NBR.
  */
@@ -2832,13 +3191,13 @@ enum punit_power_well {
 # define TV_VBURST_END_F1_SHIFT		0
 
 #define TV_V_CTL_5		0x6804c
-/**
+/*
  * Offset to start of vertical colorburst, measured in one less than the
  * number of lines from vertical start.
  */
 # define TV_VBURST_START_F2_MASK	0x003f0000
 # define TV_VBURST_START_F2_SHIFT	16
-/**
+/*
  * Offset to the end of vertical colorburst, measured in one less than the
  * number of lines from the start of NBR.
  */
@@ -2846,13 +3205,13 @@ enum punit_power_well {
 # define TV_VBURST_END_F2_SHIFT		0
 
 #define TV_V_CTL_6		0x68050
-/**
+/*
  * Offset to start of vertical colorburst, measured in one less than the
  * number of lines from vertical start.
  */
 # define TV_VBURST_START_F3_MASK	0x003f0000
 # define TV_VBURST_START_F3_SHIFT	16
-/**
+/*
  * Offset to the end of vertical colorburst, measured in one less than the
  * number of lines from the start of NBR.
  */
@@ -2860,13 +3219,13 @@ enum punit_power_well {
 # define TV_VBURST_END_F3_SHIFT		0
 
 #define TV_V_CTL_7		0x68054
-/**
+/*
  * Offset to start of vertical colorburst, measured in one less than the
  * number of lines from vertical start.
  */
 # define TV_VBURST_START_F4_MASK	0x003f0000
 # define TV_VBURST_START_F4_SHIFT	16
-/**
+/*
  * Offset to the end of vertical colorburst, measured in one less than the
  * number of lines from the start of NBR.
  */
@@ -2874,56 +3233,56 @@ enum punit_power_well {
 # define TV_VBURST_END_F4_SHIFT		0
 
 #define TV_SC_CTL_1		0x68060
-/** Turns on the first subcarrier phase generation DDA */
+/* Turns on the first subcarrier phase generation DDA */
 # define TV_SC_DDA1_EN			(1 << 31)
-/** Turns on the first subcarrier phase generation DDA */
+/* Turns on the first subcarrier phase generation DDA */
 # define TV_SC_DDA2_EN			(1 << 30)
-/** Turns on the first subcarrier phase generation DDA */
+/* Turns on the first subcarrier phase generation DDA */
 # define TV_SC_DDA3_EN			(1 << 29)
-/** Sets the subcarrier DDA to reset frequency every other field */
+/* Sets the subcarrier DDA to reset frequency every other field */
 # define TV_SC_RESET_EVERY_2		(0 << 24)
-/** Sets the subcarrier DDA to reset frequency every fourth field */
+/* Sets the subcarrier DDA to reset frequency every fourth field */
 # define TV_SC_RESET_EVERY_4		(1 << 24)
-/** Sets the subcarrier DDA to reset frequency every eighth field */
+/* Sets the subcarrier DDA to reset frequency every eighth field */
 # define TV_SC_RESET_EVERY_8		(2 << 24)
-/** Sets the subcarrier DDA to never reset the frequency */
+/* Sets the subcarrier DDA to never reset the frequency */
 # define TV_SC_RESET_NEVER		(3 << 24)
-/** Sets the peak amplitude of the colorburst.*/
+/* Sets the peak amplitude of the colorburst.*/
 # define TV_BURST_LEVEL_MASK		0x00ff0000
 # define TV_BURST_LEVEL_SHIFT		16
-/** Sets the increment of the first subcarrier phase generation DDA */
+/* Sets the increment of the first subcarrier phase generation DDA */
 # define TV_SCDDA1_INC_MASK		0x00000fff
 # define TV_SCDDA1_INC_SHIFT		0
 
 #define TV_SC_CTL_2		0x68064
-/** Sets the rollover for the second subcarrier phase generation DDA */
+/* Sets the rollover for the second subcarrier phase generation DDA */
 # define TV_SCDDA2_SIZE_MASK		0x7fff0000
 # define TV_SCDDA2_SIZE_SHIFT		16
-/** Sets the increent of the second subcarrier phase generation DDA */
+/* Sets the increent of the second subcarrier phase generation DDA */
 # define TV_SCDDA2_INC_MASK		0x00007fff
 # define TV_SCDDA2_INC_SHIFT		0
 
 #define TV_SC_CTL_3		0x68068
-/** Sets the rollover for the third subcarrier phase generation DDA */
+/* Sets the rollover for the third subcarrier phase generation DDA */
 # define TV_SCDDA3_SIZE_MASK		0x7fff0000
 # define TV_SCDDA3_SIZE_SHIFT		16
-/** Sets the increent of the third subcarrier phase generation DDA */
+/* Sets the increent of the third subcarrier phase generation DDA */
 # define TV_SCDDA3_INC_MASK		0x00007fff
 # define TV_SCDDA3_INC_SHIFT		0
 
 #define TV_WIN_POS		0x68070
-/** X coordinate of the display from the start of horizontal active */
+/* X coordinate of the display from the start of horizontal active */
 # define TV_XPOS_MASK			0x1fff0000
 # define TV_XPOS_SHIFT			16
-/** Y coordinate of the display from the start of vertical active (NBR) */
+/* Y coordinate of the display from the start of vertical active (NBR) */
 # define TV_YPOS_MASK			0x00000fff
 # define TV_YPOS_SHIFT			0
 
 #define TV_WIN_SIZE		0x68074
-/** Horizontal size of the display window, measured in pixels*/
+/* Horizontal size of the display window, measured in pixels*/
 # define TV_XSIZE_MASK			0x1fff0000
 # define TV_XSIZE_SHIFT			16
-/**
+/*
  * Vertical size of the display window, measured in pixels.
  *
  * Must be even for interlaced modes.
@@ -2932,28 +3291,28 @@ enum punit_power_well {
 # define TV_YSIZE_SHIFT			0
 
 #define TV_FILTER_CTL_1		0x68080
-/**
+/*
  * Enables automatic scaling calculation.
  *
  * If set, the rest of the registers are ignored, and the calculated values can
  * be read back from the register.
  */
 # define TV_AUTO_SCALE			(1 << 31)
-/**
+/*
  * Disables the vertical filter.
  *
  * This is required on modes more than 1024 pixels wide */
 # define TV_V_FILTER_BYPASS		(1 << 29)
-/** Enables adaptive vertical filtering */
+/* Enables adaptive vertical filtering */
 # define TV_VADAPT			(1 << 28)
 # define TV_VADAPT_MODE_MASK		(3 << 26)
-/** Selects the least adaptive vertical filtering mode */
+/* Selects the least adaptive vertical filtering mode */
 # define TV_VADAPT_MODE_LEAST		(0 << 26)
-/** Selects the moderately adaptive vertical filtering mode */
+/* Selects the moderately adaptive vertical filtering mode */
 # define TV_VADAPT_MODE_MODERATE	(1 << 26)
-/** Selects the most adaptive vertical filtering mode */
+/* Selects the most adaptive vertical filtering mode */
 # define TV_VADAPT_MODE_MOST		(3 << 26)
-/**
+/*
  * Sets the horizontal scaling factor.
  *
  * This should be the fractional part of the horizontal scaling factor divided
@@ -2965,14 +3324,14 @@ enum punit_power_well {
 # define TV_HSCALE_FRAC_SHIFT		0
 
 #define TV_FILTER_CTL_2		0x68084
-/**
+/*
  * Sets the integer part of the 3.15 fixed-point vertical scaling factor.
  *
  * TV_VSCALE should be (src height - 1) / ((interlace * dest height) - 1)
  */
 # define TV_VSCALE_INT_MASK		0x00038000
 # define TV_VSCALE_INT_SHIFT		15
-/**
+/*
  * Sets the fractional part of the 3.15 fixed-point vertical scaling factor.
  *
  * \sa TV_VSCALE_INT_MASK
@@ -2981,7 +3340,7 @@ enum punit_power_well {
 # define TV_VSCALE_FRAC_SHIFT		0
 
 #define TV_FILTER_CTL_3		0x68088
-/**
+/*
  * Sets the integer part of the 3.15 fixed-point vertical scaling factor.
  *
  * TV_VSCALE should be (src height - 1) / (1/4 * (dest height - 1))
@@ -2990,7 +3349,7 @@ enum punit_power_well {
  */
 # define TV_VSCALE_IP_INT_MASK		0x00038000
 # define TV_VSCALE_IP_INT_SHIFT		15
-/**
+/*
  * Sets the fractional part of the 3.15 fixed-point vertical scaling factor.
  *
  * For progressive modes, TV_VSCALE_IP_INT should be set to zeroes.
@@ -3002,26 +3361,26 @@ enum punit_power_well {
 
 #define TV_CC_CONTROL		0x68090
 # define TV_CC_ENABLE			(1 << 31)
-/**
+/*
  * Specifies which field to send the CC data in.
  *
  * CC data is usually sent in field 0.
  */
 # define TV_CC_FID_MASK			(1 << 27)
 # define TV_CC_FID_SHIFT		27
-/** Sets the horizontal position of the CC data.  Usually 135. */
+/* Sets the horizontal position of the CC data.  Usually 135. */
 # define TV_CC_HOFF_MASK		0x03ff0000
 # define TV_CC_HOFF_SHIFT		16
-/** Sets the vertical position of the CC data.  Usually 21 */
+/* Sets the vertical position of the CC data.  Usually 21 */
 # define TV_CC_LINE_MASK		0x0000003f
 # define TV_CC_LINE_SHIFT		0
 
 #define TV_CC_DATA		0x68094
 # define TV_CC_RDY			(1 << 31)
-/** Second word of CC data to be transmitted. */
+/* Second word of CC data to be transmitted. */
 # define TV_CC_DATA_2_MASK		0x007f0000
 # define TV_CC_DATA_2_SHIFT		16
-/** First word of CC data to be transmitted. */
+/* First word of CC data to be transmitted. */
 # define TV_CC_DATA_1_MASK		0x0000007f
 # define TV_CC_DATA_1_SHIFT		0
 
@@ -3043,6 +3402,8 @@ enum punit_power_well {
 #define   DP_PORT_EN			(1 << 31)
 #define   DP_PIPEB_SELECT		(1 << 30)
 #define   DP_PIPE_MASK			(1 << 30)
+#define   DP_PIPE_SELECT_CHV(pipe)	((pipe) << 16)
+#define   DP_PIPE_MASK_CHV		(3 << 16)
 
 /* Link training mode - select a suitable mode for each stage */
 #define   DP_LINK_TRAIN_PAT_1		(0 << 28)
@@ -3090,32 +3451,32 @@ enum punit_power_well {
 #define   DP_PLL_FREQ_160MHZ		(1 << 16)
 #define   DP_PLL_FREQ_MASK		(3 << 16)
 
-/** locked once port is enabled */
+/* locked once port is enabled */
 #define   DP_PORT_REVERSAL		(1 << 15)
 
 /* eDP */
 #define   DP_PLL_ENABLE			(1 << 14)
 
-/** sends the clock on lane 15 of the PEG for debug */
+/* sends the clock on lane 15 of the PEG for debug */
 #define   DP_CLOCK_OUTPUT_ENABLE	(1 << 13)
 
 #define   DP_SCRAMBLING_DISABLE		(1 << 12)
 #define   DP_SCRAMBLING_DISABLE_IRONLAKE	(1 << 7)
 
-/** limit RGB values to avoid confusing TVs */
+/* limit RGB values to avoid confusing TVs */
 #define   DP_COLOR_RANGE_16_235		(1 << 8)
 
-/** Turn on the audio link */
+/* Turn on the audio link */
 #define   DP_AUDIO_OUTPUT_ENABLE	(1 << 6)
 
-/** vs and hs sync polarity */
+/* vs and hs sync polarity */
 #define   DP_SYNC_VS_HIGH		(1 << 4)
 #define   DP_SYNC_HS_HIGH		(1 << 3)
 
-/** A fantasy */
+/* A fantasy */
 #define   DP_DETECTED			(1 << 2)
 
-/** The aux channel provides a way to talk to the
+/* The aux channel provides a way to talk to the
  * signal sink for DDC etc. Max packet size supported
  * is 20 bytes in each direction, hence the 5 fixed
  * data registers
@@ -3258,6 +3619,7 @@ enum punit_power_well {
 #define   PIPECONF_INTERLACED_DBL_ILK		(4 << 21) /* ilk/snb only */
 #define   PIPECONF_PFIT_PF_INTERLACED_DBL_ILK	(5 << 21) /* ilk/snb only */
 #define   PIPECONF_INTERLACE_MODE_MASK		(7 << 21)
+#define   PIPECONF_EDP_RR_MODE_SWITCH		(1 << 20)
 #define   PIPECONF_CXSR_DOWNCLOCK	(1<<16)
 #define   PIPECONF_COLOR_RANGE_SELECT	(1 << 13)
 #define   PIPECONF_BPC_MASK	(0x7 << 5)
@@ -3276,6 +3638,7 @@ enum punit_power_well {
 #define   SPRITE1_FLIP_DONE_INT_EN_VLV		(1UL<<30)
 #define   PIPE_CRC_ERROR_ENABLE			(1UL<<29)
 #define   PIPE_CRC_DONE_ENABLE			(1UL<<28)
+#define   PERF_COUNTER2_INTERRUPT_EN		(1UL<<27)
 #define   PIPE_GMBUS_EVENT_ENABLE		(1UL<<27)
 #define   PLANE_FLIP_DONE_INT_EN_VLV		(1UL<<26)
 #define   PIPE_HOTPLUG_INTERRUPT_ENABLE		(1UL<<26)
@@ -3287,8 +3650,10 @@ enum punit_power_well {
 #define   PIPE_ODD_FIELD_INTERRUPT_ENABLE	(1UL<<21)
 #define   PIPE_EVEN_FIELD_INTERRUPT_ENABLE	(1UL<<20)
 #define   PIPE_B_PSR_INTERRUPT_ENABLE_VLV	(1UL<<19)
+#define   PERF_COUNTER_INTERRUPT_EN		(1UL<<19)
 #define   PIPE_HOTPLUG_TV_INTERRUPT_ENABLE	(1UL<<18) /* pre-965 */
 #define   PIPE_START_VBLANK_INTERRUPT_ENABLE	(1UL<<18) /* 965 or later */
+#define   PIPE_FRAMESTART_INTERRUPT_ENABLE	(1UL<<17)
 #define   PIPE_VBLANK_INTERRUPT_ENABLE		(1UL<<17)
 #define   PIPEA_HBLANK_INT_EN_VLV		(1UL<<16)
 #define   PIPE_OVERLAY_UPDATED_ENABLE		(1UL<<16)
@@ -3296,6 +3661,7 @@ enum punit_power_well {
 #define   SPRITE0_FLIP_DONE_INT_STATUS_VLV	(1UL<<14)
 #define   PIPE_CRC_ERROR_INTERRUPT_STATUS	(1UL<<13)
 #define   PIPE_CRC_DONE_INTERRUPT_STATUS	(1UL<<12)
+#define   PERF_COUNTER2_INTERRUPT_STATUS	(1UL<<11)
 #define   PIPE_GMBUS_INTERRUPT_STATUS		(1UL<<11)
 #define   PLANE_FLIP_DONE_INT_STATUS_VLV	(1UL<<10)
 #define   PIPE_HOTPLUG_INTERRUPT_STATUS		(1UL<<10)
@@ -3304,20 +3670,25 @@ enum punit_power_well {
 #define   PIPE_DPST_EVENT_STATUS		(1UL<<7)
 #define   PIPE_LEGACY_BLC_EVENT_STATUS		(1UL<<6)
 #define   PIPE_A_PSR_STATUS_VLV			(1UL<<6)
+#define   PIPE_LEGACY_BLC_EVENT_STATUS		(1UL<<6)
 #define   PIPE_ODD_FIELD_INTERRUPT_STATUS	(1UL<<5)
 #define   PIPE_EVEN_FIELD_INTERRUPT_STATUS	(1UL<<4)
 #define   PIPE_B_PSR_STATUS_VLV			(1UL<<3)
+#define   PERF_COUNTER_INTERRUPT_STATUS		(1UL<<3)
 #define   PIPE_HOTPLUG_TV_INTERRUPT_STATUS	(1UL<<2) /* pre-965 */
 #define   PIPE_START_VBLANK_INTERRUPT_STATUS	(1UL<<2) /* 965 or later */
+#define   PIPE_FRAMESTART_INTERRUPT_STATUS	(1UL<<1)
 #define   PIPE_VBLANK_INTERRUPT_STATUS		(1UL<<1)
+#define   PIPE_HBLANK_INT_STATUS		(1UL<<0)
 #define   PIPE_OVERLAY_UPDATED_STATUS		(1UL<<0)
 
 #define PIPESTAT_INT_ENABLE_MASK		0x7fff0000
 #define PIPESTAT_INT_STATUS_MASK		0x0000ffff
 
-#define PIPE_A_OFFSET	0x70000
-#define PIPE_B_OFFSET	0x71000
-#define PIPE_C_OFFSET	0x72000
+#define PIPE_A_OFFSET		0x70000
+#define PIPE_B_OFFSET		0x71000
+#define PIPE_C_OFFSET		0x72000
+#define CHV_PIPE_C_OFFSET	0x74000
 /*
  * There's actually no pipe EDP. Some pipe registers have
  * simply shifted from the pipe to the transcoder, while
@@ -3355,14 +3726,25 @@ enum punit_power_well {
 #define   SPRITED_FLIP_DONE_INT_EN		(1<<26)
 #define   SPRITEC_FLIP_DONE_INT_EN		(1<<25)
 #define   PLANEB_FLIP_DONE_INT_EN		(1<<24)
+#define   PIPE_PSR_INT_EN			(1<<22)
 #define   PIPEA_LINE_COMPARE_INT_EN		(1<<21)
 #define   PIPEA_HLINE_INT_EN			(1<<20)
 #define   PIPEA_VBLANK_INT_EN			(1<<19)
 #define   SPRITEB_FLIP_DONE_INT_EN		(1<<18)
 #define   SPRITEA_FLIP_DONE_INT_EN		(1<<17)
 #define   PLANEA_FLIPDONE_INT_EN		(1<<16)
-
-#define DPINVGTT				(VLV_DISPLAY_BASE + 0x7002c) /* VLV only */
+#define   PIPEC_LINE_COMPARE_INT_EN		(1<<13)
+#define   PIPEC_HLINE_INT_EN			(1<<12)
+#define   PIPEC_VBLANK_INT_EN			(1<<11)
+#define   SPRITEF_FLIPDONE_INT_EN		(1<<10)
+#define   SPRITEE_FLIPDONE_INT_EN		(1<<9)
+#define   PLANEC_FLIPDONE_INT_EN		(1<<8)
+
+#define DPINVGTT				(VLV_DISPLAY_BASE + 0x7002c) /* VLV/CHV only */
+#define   SPRITEF_INVALID_GTT_INT_EN		(1<<27)
+#define   SPRITEE_INVALID_GTT_INT_EN		(1<<26)
+#define   PLANEC_INVALID_GTT_INT_EN		(1<<25)
+#define   CURSORC_INVALID_GTT_INT_EN		(1<<24)
 #define   CURSORB_INVALID_GTT_INT_EN		(1<<23)
 #define   CURSORA_INVALID_GTT_INT_EN		(1<<22)
 #define   SPRITED_INVALID_GTT_INT_EN		(1<<21)
@@ -3372,6 +3754,11 @@ enum punit_power_well {
 #define   SPRITEA_INVALID_GTT_INT_EN		(1<<17)
 #define   PLANEA_INVALID_GTT_INT_EN		(1<<16)
 #define   DPINVGTT_EN_MASK			0xff0000
+#define   DPINVGTT_EN_MASK_CHV			0xfff0000
+#define   SPRITEF_INVALID_GTT_STATUS		(1<<11)
+#define   SPRITEE_INVALID_GTT_STATUS		(1<<10)
+#define   PLANEC_INVALID_GTT_STATUS		(1<<9)
+#define   CURSORC_INVALID_GTT_STATUS		(1<<8)
 #define   CURSORB_INVALID_GTT_STATUS		(1<<7)
 #define   CURSORA_INVALID_GTT_STATUS		(1<<6)
 #define   SPRITED_INVALID_GTT_STATUS		(1<<5)
@@ -3381,6 +3768,7 @@ enum punit_power_well {
 #define   SPRITEA_INVALID_GTT_STATUS		(1<<1)
 #define   PLANEA_INVALID_GTT_STATUS		(1<<0)
 #define   DPINVGTT_STATUS_MASK			0xff
+#define   DPINVGTT_STATUS_MASK_CHV		0xfff
 
 #define DSPARB			0x70030
 #define   DSPARB_CSTART_MASK	(0x7f << 7)
@@ -3420,14 +3808,43 @@ enum punit_power_well {
 #define DDL_CURSORA_PRECISION_32	(1<<31)
 #define DDL_CURSORA_PRECISION_16	(0<<31)
 #define DDL_CURSORA_SHIFT		24
+#define DDL_SPRITEB_PRECISION_32	(1<<23)
+#define DDL_SPRITEB_PRECISION_16	(0<<23)
+#define DDL_SPRITEB_SHIFT		16
+#define DDL_SPRITEA_PRECISION_32	(1<<15)
+#define DDL_SPRITEA_PRECISION_16	(0<<15)
+#define DDL_SPRITEA_SHIFT		8
 #define DDL_PLANEA_PRECISION_32		(1<<7)
 #define DDL_PLANEA_PRECISION_16		(0<<7)
+#define DDL_PLANEA_SHIFT		0
+
 #define VLV_DDL2			(VLV_DISPLAY_BASE + 0x70054)
 #define DDL_CURSORB_PRECISION_32	(1<<31)
 #define DDL_CURSORB_PRECISION_16	(0<<31)
 #define DDL_CURSORB_SHIFT		24
+#define DDL_SPRITED_PRECISION_32	(1<<23)
+#define DDL_SPRITED_PRECISION_16	(0<<23)
+#define DDL_SPRITED_SHIFT		16
+#define DDL_SPRITEC_PRECISION_32	(1<<15)
+#define DDL_SPRITEC_PRECISION_16	(0<<15)
+#define DDL_SPRITEC_SHIFT		8
 #define DDL_PLANEB_PRECISION_32		(1<<7)
 #define DDL_PLANEB_PRECISION_16		(0<<7)
+#define DDL_PLANEB_SHIFT		0
+
+#define VLV_DDL3			(VLV_DISPLAY_BASE + 0x70058)
+#define DDL_CURSORC_PRECISION_32	(1<<31)
+#define DDL_CURSORC_PRECISION_16	(0<<31)
+#define DDL_CURSORC_SHIFT		24
+#define DDL_SPRITEF_PRECISION_32	(1<<23)
+#define DDL_SPRITEF_PRECISION_16	(0<<23)
+#define DDL_SPRITEF_SHIFT		16
+#define DDL_SPRITEE_PRECISION_32	(1<<15)
+#define DDL_SPRITEE_PRECISION_16	(0<<15)
+#define DDL_SPRITEE_SHIFT		8
+#define DDL_PLANEC_PRECISION_32		(1<<7)
+#define DDL_PLANEC_PRECISION_16		(0<<7)
+#define DDL_PLANEC_SHIFT		0
 
 /* FIFO watermark sizes etc */
 #define G4X_FIFO_LINE_SIZE	64
@@ -3535,12 +3952,13 @@ enum punit_power_well {
 #define   PIPE_PIXEL_MASK         0x00ffffff
 #define   PIPE_PIXEL_SHIFT        0
 /* GM45+ just has to be different */
-#define _PIPEA_FRMCOUNT_GM45	(dev_priv->info.display_mmio_offset + 0x70040)
-#define _PIPEA_FLIPCOUNT_GM45	(dev_priv->info.display_mmio_offset + 0x70044)
-#define PIPE_FRMCOUNT_GM45(pipe) _PIPE(pipe, _PIPEA_FRMCOUNT_GM45, _PIPEB_FRMCOUNT_GM45)
+#define _PIPEA_FRMCOUNT_GM45	0x70040
+#define _PIPEA_FLIPCOUNT_GM45	0x70044
+#define PIPE_FRMCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FRMCOUNT_GM45)
+#define PIPE_FLIPCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FLIPCOUNT_GM45)
 
 /* Cursor A & B regs */
-#define _CURACNTR		(dev_priv->info.display_mmio_offset + 0x70080)
+#define _CURACNTR		0x70080
 /* Old style CUR*CNTR flags (desktop 8xx) */
 #define   CURSOR_ENABLE		0x80000000
 #define   CURSOR_GAMMA_ENABLE	0x40000000
@@ -3567,28 +3985,34 @@ enum punit_power_well {
 #define   MCURSOR_PIPE_B	(1 << 28)
 #define   MCURSOR_GAMMA_ENABLE  (1 << 26)
 #define   CURSOR_TRICKLE_FEED_DISABLE	(1 << 14)
-#define _CURABASE		(dev_priv->info.display_mmio_offset + 0x70084)
-#define _CURAPOS		(dev_priv->info.display_mmio_offset + 0x70088)
+#define _CURABASE		0x70084
+#define _CURAPOS		0x70088
 #define   CURSOR_POS_MASK       0x007FF
 #define   CURSOR_POS_SIGN       0x8000
 #define   CURSOR_X_SHIFT        0
 #define   CURSOR_Y_SHIFT        16
 #define CURSIZE			0x700a0
-#define _CURBCNTR		(dev_priv->info.display_mmio_offset + 0x700c0)
-#define _CURBBASE		(dev_priv->info.display_mmio_offset + 0x700c4)
-#define _CURBPOS		(dev_priv->info.display_mmio_offset + 0x700c8)
+#define _CURBCNTR		0x700c0
+#define _CURBBASE		0x700c4
+#define _CURBPOS		0x700c8
 
 #define _CURBCNTR_IVB		0x71080
 #define _CURBBASE_IVB		0x71084
 #define _CURBPOS_IVB		0x71088
 
-#define CURCNTR(pipe) _PIPE(pipe, _CURACNTR, _CURBCNTR)
-#define CURBASE(pipe) _PIPE(pipe, _CURABASE, _CURBBASE)
-#define CURPOS(pipe) _PIPE(pipe, _CURAPOS, _CURBPOS)
+#define _CURSOR2(pipe, reg) (dev_priv->info.cursor_offsets[(pipe)] - \
+	dev_priv->info.cursor_offsets[PIPE_A] + (reg) + \
+	dev_priv->info.display_mmio_offset)
+
+#define CURCNTR(pipe) _CURSOR2(pipe, _CURACNTR)
+#define CURBASE(pipe) _CURSOR2(pipe, _CURABASE)
+#define CURPOS(pipe) _CURSOR2(pipe, _CURAPOS)
 
-#define CURCNTR_IVB(pipe) _PIPE(pipe, _CURACNTR, _CURBCNTR_IVB)
-#define CURBASE_IVB(pipe) _PIPE(pipe, _CURABASE, _CURBBASE_IVB)
-#define CURPOS_IVB(pipe) _PIPE(pipe, _CURAPOS, _CURBPOS_IVB)
+#define CURSOR_A_OFFSET 0x70080
+#define CURSOR_B_OFFSET 0x700c0
+#define CHV_CURSOR_C_OFFSET 0x700e0
+#define IVB_CURSOR_B_OFFSET 0x71080
+#define IVB_CURSOR_C_OFFSET 0x72080
 
 /* Display A control */
 #define _DSPACNTR				0x70180
@@ -4093,6 +4517,7 @@ enum punit_power_well {
 #define  GEN8_DE_PIPE_A_IRQ		(1<<16)
 #define  GEN8_DE_PIPE_IRQ(pipe)		(1<<(16+pipe))
 #define  GEN8_GT_VECS_IRQ		(1<<6)
+#define  GEN8_GT_PM_IRQ			(1<<4)
 #define  GEN8_GT_VCS2_IRQ		(1<<3)
 #define  GEN8_GT_VCS1_IRQ		(1<<2)
 #define  GEN8_GT_BCS_IRQ		(1<<1)
@@ -4120,7 +4545,7 @@ enum punit_power_well {
 #define  GEN8_PIPE_SPRITE_FAULT		(1 << 9)
 #define  GEN8_PIPE_PRIMARY_FAULT	(1 << 8)
 #define  GEN8_PIPE_SPRITE_FLIP_DONE	(1 << 5)
-#define  GEN8_PIPE_FLIP_DONE		(1 << 4)
+#define  GEN8_PIPE_PRIMARY_FLIP_DONE	(1 << 4)
 #define  GEN8_PIPE_SCAN_LINE_EVENT	(1 << 2)
 #define  GEN8_PIPE_VSYNC		(1 << 1)
 #define  GEN8_PIPE_VBLANK		(1 << 0)
@@ -4832,6 +5257,8 @@ enum punit_power_well {
 #define  PORT_TRANS_SEL_CPT(pipe)	((pipe) << 29)
 #define  PORT_TO_PIPE(val)	(((val) & (1<<30)) >> 30)
 #define  PORT_TO_PIPE_CPT(val)	(((val) & PORT_TRANS_SEL_MASK) >> 29)
+#define  SDVO_PORT_TO_PIPE_CHV(val)	(((val) & (3<<24)) >> 24)
+#define  DP_PORT_TO_PIPE_CHV(val)	(((val) & (3<<16)) >> 16)
 
 #define TRANS_DP_CTL_A		0xe0300
 #define TRANS_DP_CTL_B		0xe1300
@@ -4888,6 +5315,8 @@ enum punit_power_well {
 
 #define  EDP_LINK_TRAIN_VOL_EMP_MASK_IVB	(0x3f<<22)
 
+#define  VLV_PMWGICZ				0x1300a4
+
 #define  FORCEWAKE				0xA18C
 #define  FORCEWAKE_VLV				0x1300b0
 #define  FORCEWAKE_ACK_VLV			0x1300b4
@@ -4896,15 +5325,22 @@ enum punit_power_well {
 #define  FORCEWAKE_ACK_HSW			0x130044
 #define  FORCEWAKE_ACK				0x130090
 #define  VLV_GTLC_WAKE_CTRL			0x130090
+#define   VLV_GTLC_RENDER_CTX_EXISTS		(1 << 25)
+#define   VLV_GTLC_MEDIA_CTX_EXISTS		(1 << 24)
+#define   VLV_GTLC_ALLOWWAKEREQ			(1 << 0)
+
 #define  VLV_GTLC_PW_STATUS			0x130094
-#define VLV_GTLC_PW_RENDER_STATUS_MASK		0x80
-#define VLV_GTLC_PW_MEDIA_STATUS_MASK		0x20
+#define   VLV_GTLC_ALLOWWAKEACK			(1 << 0)
+#define   VLV_GTLC_ALLOWWAKEERR			(1 << 1)
+#define   VLV_GTLC_PW_MEDIA_STATUS_MASK		(1 << 5)
+#define   VLV_GTLC_PW_RENDER_STATUS_MASK	(1 << 7)
 #define  FORCEWAKE_MT				0xa188 /* multi-threaded */
 #define   FORCEWAKE_KERNEL			0x1
 #define   FORCEWAKE_USER			0x2
 #define  FORCEWAKE_MT_ACK			0x130040
 #define  ECOBUS					0xa180
 #define    FORCEWAKE_MT_ENABLE			(1<<5)
+#define  VLV_SPAREG2H				0xA194
 
 #define  GTFIFODBG				0x120000
 #define    GT_FIFO_SBDROPERR			(1<<6)
@@ -4924,6 +5360,7 @@ enum punit_power_well {
 #define  HSW_EDRAM_PRESENT			0x120010
 
 #define GEN6_UCGCTL1				0x9400
+# define GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE		(1 << 16)
 # define GEN6_BLBUNIT_CLOCK_GATE_DISABLE		(1 << 5)
 # define GEN6_CSUNIT_CLOCK_GATE_DISABLE			(1 << 7)
 
@@ -4934,12 +5371,19 @@ enum punit_power_well {
 # define GEN6_RCPBUNIT_CLOCK_GATE_DISABLE		(1 << 12)
 # define GEN6_RCCUNIT_CLOCK_GATE_DISABLE		(1 << 11)
 
+#define GEN6_UCGCTL3				0x9408
+
 #define GEN7_UCGCTL4				0x940c
 #define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1<<25)
 
+#define GEN6_RCGCTL1				0x9410
+#define GEN6_RCGCTL2				0x9414
+#define GEN6_RSTCTL				0x9420
+
 #define GEN8_UCGCTL6				0x9430
 #define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1<<14)
 
+#define GEN6_GFXPAUSE				0xA000
 #define GEN6_RPNSWREQ				0xA008
 #define   GEN6_TURBO_DISABLE			(1<<31)
 #define   GEN6_FREQUENCY(x)			((x)<<25)
@@ -4992,6 +5436,9 @@ enum punit_power_well {
 #define GEN6_RP_UP_EI				0xA068
 #define GEN6_RP_DOWN_EI				0xA06C
 #define GEN6_RP_IDLE_HYSTERSIS			0xA070
+#define GEN6_RPDEUHWTC				0xA080
+#define GEN6_RPDEUC				0xA084
+#define GEN6_RPDEUCSW				0xA088
 #define GEN6_RC_STATE				0xA094
 #define GEN6_RC1_WAKE_RATE_LIMIT		0xA098
 #define GEN6_RC6_WAKE_RATE_LIMIT		0xA09C
@@ -4999,11 +5446,15 @@ enum punit_power_well {
 #define GEN6_RC_EVALUATION_INTERVAL		0xA0A8
 #define GEN6_RC_IDLE_HYSTERSIS			0xA0AC
 #define GEN6_RC_SLEEP				0xA0B0
+#define GEN6_RCUBMABDTMR			0xA0B0
 #define GEN6_RC1e_THRESHOLD			0xA0B4
 #define GEN6_RC6_THRESHOLD			0xA0B8
 #define GEN6_RC6p_THRESHOLD			0xA0BC
+#define VLV_RCEDATA				0xA0BC
 #define GEN6_RC6pp_THRESHOLD			0xA0C0
 #define GEN6_PMINTRMSK				0xA168
+#define GEN8_PMINTR_REDIRECT_TO_NON_DISP	(1<<31)
+#define VLV_PWRDWNUPCTL				0xA294
 
 #define GEN6_PMISR				0x44020
 #define GEN6_PMIMR				0x44024 /* rps_lock */
@@ -5020,6 +5471,9 @@ enum punit_power_well {
 						 GEN6_PM_RP_DOWN_THRESHOLD | \
 						 GEN6_PM_RP_DOWN_TIMEOUT)
 
+#define GEN7_GT_SCRATCH_BASE			0x4F100
+#define GEN7_GT_SCRATCH_REG_NUM			8
+
 #define VLV_GTLC_SURVIVABILITY_REG              0x130098
 #define VLV_GFX_CLK_STATUS_BIT			(1<<3)
 #define VLV_GFX_CLK_FORCE_ON_BIT		(1<<2)
@@ -5030,6 +5484,9 @@ enum punit_power_well {
 #define   VLV_MEDIA_RC6_COUNT_EN		(1<<1)
 #define   VLV_RENDER_RC6_COUNT_EN		(1<<0)
 #define GEN6_GT_GFX_RC6				0x138108
+#define VLV_GT_RENDER_RC6			0x138108
+#define VLV_GT_MEDIA_RC6			0x13810C
+
 #define GEN6_GT_GFX_RC6p			0x13810C
 #define GEN6_GT_GFX_RC6pp			0x138110
 
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 56785e8fb2e..043123c77a1 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -328,8 +328,6 @@ int i915_save_state(struct drm_device *dev)
 		}
 	}
 
-	intel_disable_gt_powersave(dev);
-
 	/* Cache mode state */
 	if (INTEL_INFO(dev)->gen < 7)
 		dev_priv->regfile.saveCACHE_MODE_0 = I915_READ(CACHE_MODE_0);
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 9c57029f6f4..86ce39aad0f 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -186,7 +186,7 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct drm_minor *dminor = dev_to_drm_minor(dev);
 	struct drm_device *drm_dev = dminor->dev;
 	struct drm_i915_private *dev_priv = drm_dev->dev_private;
-	struct i915_hw_context *ctx;
+	struct intel_context *ctx;
 	u32 *temp = NULL; /* Just here to make handling failures easy */
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
@@ -263,6 +263,8 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
 
+	intel_runtime_pm_get(dev_priv);
+
 	mutex_lock(&dev_priv->rps.hw_lock);
 	if (IS_VALLEYVIEW(dev_priv->dev)) {
 		u32 freq;
@@ -273,6 +275,8 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 	}
 	mutex_unlock(&dev_priv->rps.hw_lock);
 
+	intel_runtime_pm_put(dev_priv);
+
 	return snprintf(buf, PAGE_SIZE, "%d\n", ret);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 23c26f1f8b3..f5aa0067755 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -7,6 +7,7 @@
 
 #include <drm/drmP.h>
 #include "i915_drv.h"
+#include "intel_drv.h"
 #include "intel_ringbuffer.h"
 
 #undef TRACE_SYSTEM
@@ -14,6 +15,80 @@
 #define TRACE_SYSTEM_STRING __stringify(TRACE_SYSTEM)
 #define TRACE_INCLUDE_FILE i915_trace
 
+/* pipe updates */
+
+TRACE_EVENT(i915_pipe_update_start,
+	    TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max),
+	    TP_ARGS(crtc, min, max),
+
+	    TP_STRUCT__entry(
+			     __field(enum pipe, pipe)
+			     __field(u32, frame)
+			     __field(u32, scanline)
+			     __field(u32, min)
+			     __field(u32, max)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pipe = crtc->pipe;
+			   __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
+										       crtc->pipe);
+			   __entry->scanline = intel_get_crtc_scanline(crtc);
+			   __entry->min = min;
+			   __entry->max = max;
+			   ),
+
+	    TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u",
+		      pipe_name(__entry->pipe), __entry->frame,
+		       __entry->scanline, __entry->min, __entry->max)
+);
+
+TRACE_EVENT(i915_pipe_update_vblank_evaded,
+	    TP_PROTO(struct intel_crtc *crtc, u32 min, u32 max, u32 frame),
+	    TP_ARGS(crtc, min, max, frame),
+
+	    TP_STRUCT__entry(
+			     __field(enum pipe, pipe)
+			     __field(u32, frame)
+			     __field(u32, scanline)
+			     __field(u32, min)
+			     __field(u32, max)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pipe = crtc->pipe;
+			   __entry->frame = frame;
+			   __entry->scanline = intel_get_crtc_scanline(crtc);
+			   __entry->min = min;
+			   __entry->max = max;
+			   ),
+
+	    TP_printk("pipe %c, frame=%u, scanline=%u, min=%u, max=%u",
+		      pipe_name(__entry->pipe), __entry->frame,
+		       __entry->scanline, __entry->min, __entry->max)
+);
+
+TRACE_EVENT(i915_pipe_update_end,
+	    TP_PROTO(struct intel_crtc *crtc, u32 frame),
+	    TP_ARGS(crtc, frame),
+
+	    TP_STRUCT__entry(
+			     __field(enum pipe, pipe)
+			     __field(u32, frame)
+			     __field(u32, scanline)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->pipe = crtc->pipe;
+			   __entry->frame = frame;
+			   __entry->scanline = intel_get_crtc_scanline(crtc);
+			   ),
+
+	    TP_printk("pipe %c, frame=%u, scanline=%u",
+		      pipe_name(__entry->pipe), __entry->frame,
+		      __entry->scanline)
+);
+
 /* object tracking */
 
 TRACE_EVENT(i915_gem_object_create,
@@ -251,8 +326,8 @@ TRACE_EVENT(i915_gem_evict_vm,
 );
 
 TRACE_EVENT(i915_gem_ring_sync_to,
-	    TP_PROTO(struct intel_ring_buffer *from,
-		     struct intel_ring_buffer *to,
+	    TP_PROTO(struct intel_engine_cs *from,
+		     struct intel_engine_cs *to,
 		     u32 seqno),
 	    TP_ARGS(from, to, seqno),
 
@@ -277,7 +352,7 @@ TRACE_EVENT(i915_gem_ring_sync_to,
 );
 
 TRACE_EVENT(i915_gem_ring_dispatch,
-	    TP_PROTO(struct intel_ring_buffer *ring, u32 seqno, u32 flags),
+	    TP_PROTO(struct intel_engine_cs *ring, u32 seqno, u32 flags),
 	    TP_ARGS(ring, seqno, flags),
 
 	    TP_STRUCT__entry(
@@ -300,7 +375,7 @@ TRACE_EVENT(i915_gem_ring_dispatch,
 );
 
 TRACE_EVENT(i915_gem_ring_flush,
-	    TP_PROTO(struct intel_ring_buffer *ring, u32 invalidate, u32 flush),
+	    TP_PROTO(struct intel_engine_cs *ring, u32 invalidate, u32 flush),
 	    TP_ARGS(ring, invalidate, flush),
 
 	    TP_STRUCT__entry(
@@ -323,7 +398,7 @@ TRACE_EVENT(i915_gem_ring_flush,
 );
 
 DECLARE_EVENT_CLASS(i915_gem_request,
-	    TP_PROTO(struct intel_ring_buffer *ring, u32 seqno),
+	    TP_PROTO(struct intel_engine_cs *ring, u32 seqno),
 	    TP_ARGS(ring, seqno),
 
 	    TP_STRUCT__entry(
@@ -343,12 +418,12 @@ DECLARE_EVENT_CLASS(i915_gem_request,
 );
 
 DEFINE_EVENT(i915_gem_request, i915_gem_request_add,
-	    TP_PROTO(struct intel_ring_buffer *ring, u32 seqno),
+	    TP_PROTO(struct intel_engine_cs *ring, u32 seqno),
 	    TP_ARGS(ring, seqno)
 );
 
 TRACE_EVENT(i915_gem_request_complete,
-	    TP_PROTO(struct intel_ring_buffer *ring),
+	    TP_PROTO(struct intel_engine_cs *ring),
 	    TP_ARGS(ring),
 
 	    TP_STRUCT__entry(
@@ -368,12 +443,12 @@ TRACE_EVENT(i915_gem_request_complete,
 );
 
 DEFINE_EVENT(i915_gem_request, i915_gem_request_retire,
-	    TP_PROTO(struct intel_ring_buffer *ring, u32 seqno),
+	    TP_PROTO(struct intel_engine_cs *ring, u32 seqno),
 	    TP_ARGS(ring, seqno)
 );
 
 TRACE_EVENT(i915_gem_request_wait_begin,
-	    TP_PROTO(struct intel_ring_buffer *ring, u32 seqno),
+	    TP_PROTO(struct intel_engine_cs *ring, u32 seqno),
 	    TP_ARGS(ring, seqno),
 
 	    TP_STRUCT__entry(
@@ -402,12 +477,12 @@ TRACE_EVENT(i915_gem_request_wait_begin,
 );
 
 DEFINE_EVENT(i915_gem_request, i915_gem_request_wait_end,
-	    TP_PROTO(struct intel_ring_buffer *ring, u32 seqno),
+	    TP_PROTO(struct intel_engine_cs *ring, u32 seqno),
 	    TP_ARGS(ring, seqno)
 );
 
 DECLARE_EVENT_CLASS(i915_ring,
-	    TP_PROTO(struct intel_ring_buffer *ring),
+	    TP_PROTO(struct intel_engine_cs *ring),
 	    TP_ARGS(ring),
 
 	    TP_STRUCT__entry(
@@ -424,12 +499,12 @@ DECLARE_EVENT_CLASS(i915_ring,
 );
 
 DEFINE_EVENT(i915_ring, i915_ring_wait_begin,
-	    TP_PROTO(struct intel_ring_buffer *ring),
+	    TP_PROTO(struct intel_engine_cs *ring),
 	    TP_ARGS(ring)
 );
 
 DEFINE_EVENT(i915_ring, i915_ring_wait_end,
-	    TP_PROTO(struct intel_ring_buffer *ring),
+	    TP_PROTO(struct intel_engine_cs *ring),
 	    TP_ARGS(ring)
 );
 
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index aff4a113cda..827498e081d 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -49,13 +49,19 @@ find_section(struct bdb_header *bdb, int section_id)
 	total = bdb->bdb_size;
 
 	/* walk the sections looking for section_id */
-	while (index < total) {
+	while (index + 3 < total) {
 		current_id = *(base + index);
 		index++;
+
 		current_size = *((u16 *)(base + index));
 		index += 2;
+
+		if (index + current_size > total)
+			return NULL;
+
 		if (current_id == section_id)
 			return base + index;
+
 		index += current_size;
 	}
 
@@ -206,7 +212,7 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 	const struct lvds_dvo_timing *panel_dvo_timing;
 	const struct lvds_fp_timing *fp_timing;
 	struct drm_display_mode *panel_fixed_mode;
-	int i, downclock;
+	int i, downclock, drrs_mode;
 
 	lvds_options = find_section(bdb, BDB_LVDS_OPTIONS);
 	if (!lvds_options)
@@ -218,6 +224,28 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 
 	panel_type = lvds_options->panel_type;
 
+	drrs_mode = (lvds_options->dps_panel_type_bits
+				>> (panel_type * 2)) & MODE_MASK;
+	/*
+	 * VBT has static DRRS = 0 and seamless DRRS = 2.
+	 * The below piece of code is required to adjust vbt.drrs_type
+	 * to match the enum drrs_support_type.
+	 */
+	switch (drrs_mode) {
+	case 0:
+		dev_priv->vbt.drrs_type = STATIC_DRRS_SUPPORT;
+		DRM_DEBUG_KMS("DRRS supported mode is static\n");
+		break;
+	case 2:
+		dev_priv->vbt.drrs_type = SEAMLESS_DRRS_SUPPORT;
+		DRM_DEBUG_KMS("DRRS supported mode is seamless\n");
+		break;
+	default:
+		dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED;
+		DRM_DEBUG_KMS("DRRS not supported (VBT input)\n");
+		break;
+	}
+
 	lvds_lfp_data = find_section(bdb, BDB_LVDS_LFP_DATA);
 	if (!lvds_lfp_data)
 		return;
@@ -287,9 +315,6 @@ parse_lfp_backlight(struct drm_i915_private *dev_priv, struct bdb_header *bdb)
 	const struct bdb_lfp_backlight_data *backlight_data;
 	const struct bdb_lfp_backlight_data_entry *entry;
 
-	/* Err to enabling backlight if no backlight block. */
-	dev_priv->vbt.backlight.present = true;
-
 	backlight_data = find_section(bdb, BDB_LVDS_BACKLIGHT);
 	if (!backlight_data)
 		return;
@@ -526,6 +551,16 @@ parse_driver_features(struct drm_i915_private *dev_priv,
 
 	if (driver->dual_frequency)
 		dev_priv->render_reclock_avail = true;
+
+	DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled);
+	/*
+	 * If DRRS is not supported, drrs_type has to be set to 0.
+	 * This is because, VBT is configured in such a way that
+	 * static DRRS is 0 and DRRS not supported is represented by
+	 * driver->drrs_enabled=false
+	 */
+	if (!driver->drrs_enabled)
+		dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED;
 }
 
 static void
@@ -628,19 +663,221 @@ parse_edp(struct drm_i915_private *dev_priv, struct bdb_header *bdb)
 	}
 }
 
+static u8 *goto_next_sequence(u8 *data, int *size)
+{
+	u16 len;
+	int tmp = *size;
+
+	if (--tmp < 0)
+		return NULL;
+
+	/* goto first element */
+	data++;
+	while (1) {
+		switch (*data) {
+		case MIPI_SEQ_ELEM_SEND_PKT:
+			/*
+			 * skip by this element payload size
+			 * skip elem id, command flag and data type
+			 */
+			tmp -= 5;
+			if (tmp < 0)
+				return NULL;
+
+			data += 3;
+			len = *((u16 *)data);
+
+			tmp -= len;
+			if (tmp < 0)
+				return NULL;
+
+			/* skip by len */
+			data = data + 2 + len;
+			break;
+		case MIPI_SEQ_ELEM_DELAY:
+			/* skip by elem id, and delay is 4 bytes */
+			tmp -= 5;
+			if (tmp < 0)
+				return NULL;
+
+			data += 5;
+			break;
+		case MIPI_SEQ_ELEM_GPIO:
+			tmp -= 3;
+			if (tmp < 0)
+				return NULL;
+
+			data += 3;
+			break;
+		default:
+			DRM_ERROR("Unknown element\n");
+			return NULL;
+		}
+
+		/* end of sequence ? */
+		if (*data == 0)
+			break;
+	}
+
+	/* goto next sequence or end of block byte */
+	if (--tmp < 0)
+		return NULL;
+
+	data++;
+
+	/* update amount of data left for the sequence block to be parsed */
+	*size = tmp;
+	return data;
+}
+
 static void
 parse_mipi(struct drm_i915_private *dev_priv, struct bdb_header *bdb)
 {
-	struct bdb_mipi *mipi;
+	struct bdb_mipi_config *start;
+	struct bdb_mipi_sequence *sequence;
+	struct mipi_config *config;
+	struct mipi_pps_data *pps;
+	u8 *data, *seq_data;
+	int i, panel_id, seq_size;
+	u16 block_size;
+
+	/* parse MIPI blocks only if LFP type is MIPI */
+	if (!dev_priv->vbt.has_mipi)
+		return;
+
+	/* Initialize this to undefined indicating no generic MIPI support */
+	dev_priv->vbt.dsi.panel_id = MIPI_DSI_UNDEFINED_PANEL_ID;
 
-	mipi = find_section(bdb, BDB_MIPI_CONFIG);
-	if (!mipi) {
-		DRM_DEBUG_KMS("No MIPI BDB found");
+	/* Block #40 is already parsed and panel_fixed_mode is
+	 * stored in dev_priv->lfp_lvds_vbt_mode
+	 * resuse this when needed
+	 */
+
+	/* Parse #52 for panel index used from panel_type already
+	 * parsed
+	 */
+	start = find_section(bdb, BDB_MIPI_CONFIG);
+	if (!start) {
+		DRM_DEBUG_KMS("No MIPI config BDB found");
 		return;
 	}
 
-	/* XXX: add more info */
+	DRM_DEBUG_DRIVER("Found MIPI Config block, panel index = %d\n",
+								panel_type);
+
+	/*
+	 * get hold of the correct configuration block and pps data as per
+	 * the panel_type as index
+	 */
+	config = &start->config[panel_type];
+	pps = &start->pps[panel_type];
+
+	/* store as of now full data. Trim when we realise all is not needed */
+	dev_priv->vbt.dsi.config = kmemdup(config, sizeof(struct mipi_config), GFP_KERNEL);
+	if (!dev_priv->vbt.dsi.config)
+		return;
+
+	dev_priv->vbt.dsi.pps = kmemdup(pps, sizeof(struct mipi_pps_data), GFP_KERNEL);
+	if (!dev_priv->vbt.dsi.pps) {
+		kfree(dev_priv->vbt.dsi.config);
+		return;
+	}
+
+	/* We have mandatory mipi config blocks. Initialize as generic panel */
 	dev_priv->vbt.dsi.panel_id = MIPI_DSI_GENERIC_PANEL_ID;
+
+	/* Check if we have sequence block as well */
+	sequence = find_section(bdb, BDB_MIPI_SEQUENCE);
+	if (!sequence) {
+		DRM_DEBUG_KMS("No MIPI Sequence found, parsing complete\n");
+		return;
+	}
+
+	DRM_DEBUG_DRIVER("Found MIPI sequence block\n");
+
+	block_size = get_blocksize(sequence);
+
+	/*
+	 * parse the sequence block for individual sequences
+	 */
+	dev_priv->vbt.dsi.seq_version = sequence->version;
+
+	seq_data = &sequence->data[0];
+
+	/*
+	 * sequence block is variable length and hence we need to parse and
+	 * get the sequence data for specific panel id
+	 */
+	for (i = 0; i < MAX_MIPI_CONFIGURATIONS; i++) {
+		panel_id = *seq_data;
+		seq_size = *((u16 *) (seq_data + 1));
+		if (panel_id == panel_type)
+			break;
+
+		/* skip the sequence including seq header of 3 bytes */
+		seq_data = seq_data + 3 + seq_size;
+		if ((seq_data - &sequence->data[0]) > block_size) {
+			DRM_ERROR("Sequence start is beyond sequence block size, corrupted sequence block\n");
+			return;
+		}
+	}
+
+	if (i == MAX_MIPI_CONFIGURATIONS) {
+		DRM_ERROR("Sequence block detected but no valid configuration\n");
+		return;
+	}
+
+	/* check if found sequence is completely within the sequence block
+	 * just being paranoid */
+	if (seq_size > block_size) {
+		DRM_ERROR("Corrupted sequence/size, bailing out\n");
+		return;
+	}
+
+	/* skip the panel id(1 byte) and seq size(2 bytes) */
+	dev_priv->vbt.dsi.data = kmemdup(seq_data + 3, seq_size, GFP_KERNEL);
+	if (!dev_priv->vbt.dsi.data)
+		return;
+
+	/*
+	 * loop into the sequence data and split into multiple sequneces
+	 * There are only 5 types of sequences as of now
+	 */
+	data = dev_priv->vbt.dsi.data;
+	dev_priv->vbt.dsi.size = seq_size;
+
+	/* two consecutive 0x00 indicate end of all sequences */
+	while (1) {
+		int seq_id = *data;
+		if (MIPI_SEQ_MAX > seq_id && seq_id > MIPI_SEQ_UNDEFINED) {
+			dev_priv->vbt.dsi.sequence[seq_id] = data;
+			DRM_DEBUG_DRIVER("Found mipi sequence - %d\n", seq_id);
+		} else {
+			DRM_ERROR("undefined sequence\n");
+			goto err;
+		}
+
+		/* partial parsing to skip elements */
+		data = goto_next_sequence(data, &seq_size);
+
+		if (data == NULL) {
+			DRM_ERROR("Sequence elements going beyond block itself. Sequence block parsing failed\n");
+			goto err;
+		}
+
+		if (*data == 0)
+			break; /* end of sequence reached */
+	}
+
+	DRM_DEBUG_DRIVER("MIPI related vbt parsing complete\n");
+	return;
+err:
+	kfree(dev_priv->vbt.dsi.data);
+	dev_priv->vbt.dsi.data = NULL;
+
+	/* error during parsing so set all pointers to null
+	 * because of partial parsing */
+	memset(dev_priv->vbt.dsi.sequence, 0, MIPI_SEQ_MAX);
 }
 
 static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
@@ -823,6 +1060,15 @@ parse_device_mapping(struct drm_i915_private *dev_priv,
 			/* skip the device block if device type is invalid */
 			continue;
 		}
+
+		if (p_child->common.dvo_port >= DVO_PORT_MIPIA
+		    && p_child->common.dvo_port <= DVO_PORT_MIPID
+		    &&p_child->common.device_type & DEVICE_TYPE_MIPI_OUTPUT) {
+			DRM_DEBUG_KMS("Found MIPI as LFP\n");
+			dev_priv->vbt.has_mipi = 1;
+			dev_priv->vbt.dsi.port = p_child->common.dvo_port;
+		}
+
 		child_dev_ptr = dev_priv->vbt.child_dev + count;
 		count++;
 		memcpy((void *)child_dev_ptr, (void *)p_child,
@@ -839,6 +1085,9 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 
 	dev_priv->vbt.crt_ddc_pin = GMBUS_PORT_VGADDC;
 
+	/* Default to having backlight */
+	dev_priv->vbt.backlight.present = true;
+
 	/* LFP panel data */
 	dev_priv->vbt.lvds_dither = 1;
 	dev_priv->vbt.lvds_vbt = 0;
@@ -893,6 +1142,46 @@ static const struct dmi_system_id intel_no_opregion_vbt[] = {
 	{ }
 };
 
+static struct bdb_header *validate_vbt(char *base, size_t size,
+				       struct vbt_header *vbt,
+				       const char *source)
+{
+	size_t offset;
+	struct bdb_header *bdb;
+
+	if (vbt == NULL) {
+		DRM_DEBUG_DRIVER("VBT signature missing\n");
+		return NULL;
+	}
+
+	offset = (char *)vbt - base;
+	if (offset + sizeof(struct vbt_header) > size) {
+		DRM_DEBUG_DRIVER("VBT header incomplete\n");
+		return NULL;
+	}
+
+	if (memcmp(vbt->signature, "$VBT", 4)) {
+		DRM_DEBUG_DRIVER("VBT invalid signature\n");
+		return NULL;
+	}
+
+	offset += vbt->bdb_offset;
+	if (offset + sizeof(struct bdb_header) > size) {
+		DRM_DEBUG_DRIVER("BDB header incomplete\n");
+		return NULL;
+	}
+
+	bdb = (struct bdb_header *)(base + offset);
+	if (offset + bdb->bdb_size > size) {
+		DRM_DEBUG_DRIVER("BDB incomplete\n");
+		return NULL;
+	}
+
+	DRM_DEBUG_KMS("Using VBT from %s: %20s\n",
+		      source, vbt->signature);
+	return bdb;
+}
+
 /**
  * intel_parse_bios - find VBT and initialize settings from the BIOS
  * @dev: DRM device
@@ -916,20 +1205,13 @@ intel_parse_bios(struct drm_device *dev)
 	init_vbt_defaults(dev_priv);
 
 	/* XXX Should this validation be moved to intel_opregion.c? */
-	if (!dmi_check_system(intel_no_opregion_vbt) && dev_priv->opregion.vbt) {
-		struct vbt_header *vbt = dev_priv->opregion.vbt;
-		if (memcmp(vbt->signature, "$VBT", 4) == 0) {
-			DRM_DEBUG_KMS("Using VBT from OpRegion: %20s\n",
-					 vbt->signature);
-			bdb = (struct bdb_header *)((char *)vbt + vbt->bdb_offset);
-		} else
-			dev_priv->opregion.vbt = NULL;
-	}
+	if (!dmi_check_system(intel_no_opregion_vbt) && dev_priv->opregion.vbt)
+		bdb = validate_vbt((char *)dev_priv->opregion.header, OPREGION_SIZE,
+				   (struct vbt_header *)dev_priv->opregion.vbt,
+				   "OpRegion");
 
 	if (bdb == NULL) {
-		struct vbt_header *vbt = NULL;
-		size_t size;
-		int i;
+		size_t i, size;
 
 		bios = pci_map_rom(pdev, &size);
 		if (!bios)
@@ -937,19 +1219,18 @@ intel_parse_bios(struct drm_device *dev)
 
 		/* Scour memory looking for the VBT signature */
 		for (i = 0; i + 4 < size; i++) {
-			if (!memcmp(bios + i, "$VBT", 4)) {
-				vbt = (struct vbt_header *)(bios + i);
+			if (memcmp(bios + i, "$VBT", 4) == 0) {
+				bdb = validate_vbt(bios, size,
+						   (struct vbt_header *)(bios + i),
+						   "PCI ROM");
 				break;
 			}
 		}
 
-		if (!vbt) {
-			DRM_DEBUG_DRIVER("VBT signature missing\n");
+		if (!bdb) {
 			pci_unmap_rom(pdev, bios);
 			return -1;
 		}
-
-		bdb = (struct bdb_header *)(bios + i + vbt->bdb_offset);
 	}
 
 	/* Grab useful general definitions */
diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h
index f27f7b28246..b9866779633 100644
--- a/drivers/gpu/drm/i915/intel_bios.h
+++ b/drivers/gpu/drm/i915/intel_bios.h
@@ -282,6 +282,9 @@ struct bdb_general_definitions {
 	union child_device_config devices[0];
 } __packed;
 
+/* Mask for DRRS / Panel Channel / SSC / BLT control bits extraction */
+#define MODE_MASK		0x3
+
 struct bdb_lvds_options {
 	u8 panel_type;
 	u8 rsvd1;
@@ -294,6 +297,18 @@ struct bdb_lvds_options {
 	u8 lvds_edid:1;
 	u8 rsvd2:1;
 	u8 rsvd4;
+	/* LVDS Panel channel bits stored here */
+	u32 lvds_panel_channel_bits;
+	/* LVDS SSC (Spread Spectrum Clock) bits stored here. */
+	u16 ssc_bits;
+	u16 ssc_freq;
+	u16 ssc_ddt;
+	/* Panel color depth defined here */
+	u16 panel_color_depth;
+	/* LVDS panel type bits stored here */
+	u32 dps_panel_type_bits;
+	/* LVDS backlight control type bits stored here */
+	u32 blt_control_type_bits;
 } __packed;
 
 /* LFP pointer table contains entries to the struct below */
@@ -482,6 +497,20 @@ struct bdb_driver_features {
 
 	u8 hdmi_termination;
 	u8 custom_vbt_version;
+	/* Driver features data block */
+	u16 rmpm_enabled:1;
+	u16 s2ddt_enabled:1;
+	u16 dpst_enabled:1;
+	u16 bltclt_enabled:1;
+	u16 adb_enabled:1;
+	u16 drrs_enabled:1;
+	u16 grs_enabled:1;
+	u16 gpmt_enabled:1;
+	u16 tbt_enabled:1;
+	u16 psr_enabled:1;
+	u16 ips_enabled:1;
+	u16 reserved3:4;
+	u16 pc_feature_valid:1;
 } __packed;
 
 #define EDP_18BPP	0
@@ -714,6 +743,10 @@ int intel_parse_bios(struct drm_device *dev);
 #define DVO_PORT_DPC	8
 #define DVO_PORT_DPD	9
 #define DVO_PORT_DPA	10
+#define DVO_PORT_MIPIA	21
+#define DVO_PORT_MIPIB	22
+#define DVO_PORT_MIPIC	23
+#define DVO_PORT_MIPID	24
 
 /* Block 52 contains MIPI Panel info
  * 6 such enteries will there. Index into correct
@@ -870,4 +903,35 @@ struct bdb_mipi_sequence {
 	u8 data[0];
 };
 
+/* MIPI Sequnece Block definitions */
+enum mipi_seq {
+	MIPI_SEQ_UNDEFINED = 0,
+	MIPI_SEQ_ASSERT_RESET,
+	MIPI_SEQ_INIT_OTP,
+	MIPI_SEQ_DISPLAY_ON,
+	MIPI_SEQ_DISPLAY_OFF,
+	MIPI_SEQ_DEASSERT_RESET,
+	MIPI_SEQ_MAX
+};
+
+enum mipi_seq_element {
+	MIPI_SEQ_ELEM_UNDEFINED = 0,
+	MIPI_SEQ_ELEM_SEND_PKT,
+	MIPI_SEQ_ELEM_DELAY,
+	MIPI_SEQ_ELEM_GPIO,
+	MIPI_SEQ_ELEM_STATUS,
+	MIPI_SEQ_ELEM_MAX
+};
+
+enum mipi_gpio_pin_index {
+	MIPI_GPIO_UNDEFINED = 0,
+	MIPI_GPIO_PANEL_ENABLE,
+	MIPI_GPIO_BL_ENABLE,
+	MIPI_GPIO_PWM_ENABLE,
+	MIPI_GPIO_RESET_N,
+	MIPI_GPIO_PWR_DOWN_R,
+	MIPI_GPIO_STDBY_RST_N,
+	MIPI_GPIO_MAX
+};
+
 #endif /* _I830_BIOS_H_ */
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index aa5a3dc4334..5a045d3bd77 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -144,28 +144,49 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder, int mode)
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
-	u32 temp;
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
+	u32 adpa;
+
+	if (INTEL_INFO(dev)->gen >= 5)
+		adpa = ADPA_HOTPLUG_BITS;
+	else
+		adpa = 0;
 
-	temp = I915_READ(crt->adpa_reg);
-	temp &= ~(ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE);
-	temp &= ~ADPA_DAC_ENABLE;
+	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
+		adpa |= ADPA_HSYNC_ACTIVE_HIGH;
+	if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
+		adpa |= ADPA_VSYNC_ACTIVE_HIGH;
+
+	/* For CPT allow 3 pipe config, for others just use A or B */
+	if (HAS_PCH_LPT(dev))
+		; /* Those bits don't exist here */
+	else if (HAS_PCH_CPT(dev))
+		adpa |= PORT_TRANS_SEL_CPT(crtc->pipe);
+	else if (crtc->pipe == 0)
+		adpa |= ADPA_PIPE_A_SELECT;
+	else
+		adpa |= ADPA_PIPE_B_SELECT;
+
+	if (!HAS_PCH_SPLIT(dev))
+		I915_WRITE(BCLRPAT(crtc->pipe), 0);
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
-		temp |= ADPA_DAC_ENABLE;
+		adpa |= ADPA_DAC_ENABLE;
 		break;
 	case DRM_MODE_DPMS_STANDBY:
-		temp |= ADPA_DAC_ENABLE | ADPA_HSYNC_CNTL_DISABLE;
+		adpa |= ADPA_DAC_ENABLE | ADPA_HSYNC_CNTL_DISABLE;
 		break;
 	case DRM_MODE_DPMS_SUSPEND:
-		temp |= ADPA_DAC_ENABLE | ADPA_VSYNC_CNTL_DISABLE;
+		adpa |= ADPA_DAC_ENABLE | ADPA_VSYNC_CNTL_DISABLE;
 		break;
 	case DRM_MODE_DPMS_OFF:
-		temp |= ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE;
+		adpa |= ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE;
 		break;
 	}
 
-	I915_WRITE(crt->adpa_reg, temp);
+	I915_WRITE(crt->adpa_reg, adpa);
 }
 
 static void intel_disable_crt(struct intel_encoder *encoder)
@@ -274,42 +295,6 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_crt_mode_set(struct intel_encoder *encoder)
-{
-
-	struct drm_device *dev = encoder->base.dev;
-	struct intel_crt *crt = intel_encoder_to_crt(encoder);
-	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
-	u32 adpa;
-
-	if (INTEL_INFO(dev)->gen >= 5)
-		adpa = ADPA_HOTPLUG_BITS;
-	else
-		adpa = 0;
-
-	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
-		adpa |= ADPA_HSYNC_ACTIVE_HIGH;
-	if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
-		adpa |= ADPA_VSYNC_ACTIVE_HIGH;
-
-	/* For CPT allow 3 pipe config, for others just use A or B */
-	if (HAS_PCH_LPT(dev))
-		; /* Those bits don't exist here */
-	else if (HAS_PCH_CPT(dev))
-		adpa |= PORT_TRANS_SEL_CPT(crtc->pipe);
-	else if (crtc->pipe == 0)
-		adpa |= ADPA_PIPE_A_SELECT;
-	else
-		adpa |= ADPA_PIPE_B_SELECT;
-
-	if (!HAS_PCH_SPLIT(dev))
-		I915_WRITE(BCLRPAT(crtc->pipe), 0);
-
-	I915_WRITE(crt->adpa_reg, adpa);
-}
-
 static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
@@ -645,11 +630,12 @@ intel_crt_detect(struct drm_connector *connector, bool force)
 	enum intel_display_power_domain power_domain;
 	enum drm_connector_status status;
 	struct intel_load_detect_pipe tmp;
+	struct drm_modeset_acquire_ctx ctx;
 
 	intel_runtime_pm_get(dev_priv);
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n",
-		      connector->base.id, drm_get_connector_name(connector),
+		      connector->base.id, connector->name,
 		      force);
 
 	power_domain = intel_display_port_power_domain(intel_encoder);
@@ -688,12 +674,12 @@ intel_crt_detect(struct drm_connector *connector, bool force)
 	}
 
 	/* for pre-945g platforms use load detect */
-	if (intel_get_load_detect_pipe(connector, NULL, &tmp)) {
+	if (intel_get_load_detect_pipe(connector, NULL, &tmp, &ctx)) {
 		if (intel_crt_detect_ddc(connector))
 			status = connector_status_connected;
 		else
 			status = intel_crt_load_detect(crt);
-		intel_release_load_detect_pipe(connector, &tmp);
+		intel_release_load_detect_pipe(connector, &tmp, &ctx);
 	} else
 		status = connector_status_unknown;
 
@@ -867,7 +853,6 @@ void intel_crt_init(struct drm_device *dev)
 		crt->adpa_reg = ADPA;
 
 	crt->base.compute_config = intel_crt_compute_config;
-	crt->base.mode_set = intel_crt_mode_set;
 	crt->base.disable = intel_disable_crt;
 	crt->base.enable = intel_enable_crt;
 	if (I915_HAS_HOTPLUG(dev))
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 0ad4e960006..b17b9c7c769 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -364,55 +364,6 @@ void hsw_fdi_link_train(struct drm_crtc *crtc)
 	DRM_ERROR("FDI link training failed!\n");
 }
 
-static void intel_ddi_mode_set(struct intel_encoder *encoder)
-{
-	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
-	int port = intel_ddi_get_encoder_port(encoder);
-	int pipe = crtc->pipe;
-	int type = encoder->type;
-	struct drm_display_mode *adjusted_mode = &crtc->config.adjusted_mode;
-
-	DRM_DEBUG_KMS("Preparing DDI mode on port %c, pipe %c\n",
-		      port_name(port), pipe_name(pipe));
-
-	crtc->eld_vld = false;
-	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-		struct intel_digital_port *intel_dig_port =
-			enc_to_dig_port(&encoder->base);
-
-		intel_dp->DP = intel_dig_port->saved_port_bits |
-			       DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW;
-		intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count);
-
-		if (intel_dp->has_audio) {
-			DRM_DEBUG_DRIVER("DP audio on pipe %c on DDI\n",
-					 pipe_name(crtc->pipe));
-
-			/* write eld */
-			DRM_DEBUG_DRIVER("DP audio: write eld information\n");
-			intel_write_eld(&encoder->base, adjusted_mode);
-		}
-	} else if (type == INTEL_OUTPUT_HDMI) {
-		struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
-
-		if (intel_hdmi->has_audio) {
-			/* Proper support for digital audio needs a new logic
-			 * and a new set of registers, so we leave it for future
-			 * patch bombing.
-			 */
-			DRM_DEBUG_DRIVER("HDMI audio on pipe %c on DDI\n",
-					 pipe_name(crtc->pipe));
-
-			/* write eld */
-			DRM_DEBUG_DRIVER("HDMI audio: write eld information\n");
-			intel_write_eld(&encoder->base, adjusted_mode);
-		}
-
-		intel_hdmi->set_infoframes(&encoder->base, adjusted_mode);
-	}
-}
-
 static struct intel_encoder *
 intel_ddi_get_crtc_encoder(struct drm_crtc *crtc)
 {
@@ -1062,9 +1013,7 @@ void intel_ddi_enable_transcoder_func(struct drm_crtc *crtc)
 	}
 
 	if (type == INTEL_OUTPUT_HDMI) {
-		struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
-
-		if (intel_hdmi->has_hdmi_sink)
+		if (intel_crtc->config.has_hdmi_sink)
 			temp |= TRANS_DDI_MODE_SELECT_HDMI;
 		else
 			temp |= TRANS_DDI_MODE_SELECT_DVI;
@@ -1293,28 +1242,48 @@ void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc)
 static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder)
 {
 	struct drm_encoder *encoder = &intel_encoder->base;
-	struct drm_crtc *crtc = encoder->crtc;
 	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_crtc *crtc = to_intel_crtc(encoder->crtc);
 	enum port port = intel_ddi_get_encoder_port(intel_encoder);
 	int type = intel_encoder->type;
 
+	if (crtc->config.has_audio) {
+		DRM_DEBUG_DRIVER("Audio on pipe %c on DDI\n",
+				 pipe_name(crtc->pipe));
+
+		/* write eld */
+		DRM_DEBUG_DRIVER("DDI audio: write eld information\n");
+		intel_write_eld(encoder, &crtc->config.adjusted_mode);
+	}
+
 	if (type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 		intel_edp_panel_on(intel_dp);
 	}
 
-	WARN_ON(intel_crtc->ddi_pll_sel == PORT_CLK_SEL_NONE);
-	I915_WRITE(PORT_CLK_SEL(port), intel_crtc->ddi_pll_sel);
+	WARN_ON(crtc->ddi_pll_sel == PORT_CLK_SEL_NONE);
+	I915_WRITE(PORT_CLK_SEL(port), crtc->ddi_pll_sel);
 
 	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+		struct intel_digital_port *intel_dig_port =
+			enc_to_dig_port(encoder);
+
+		intel_dp->DP = intel_dig_port->saved_port_bits |
+			       DDI_BUF_CTL_ENABLE | DDI_BUF_EMP_400MV_0DB_HSW;
+		intel_dp->DP |= DDI_PORT_WIDTH(intel_dp->lane_count);
 
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 		intel_dp_start_link_train(intel_dp);
 		intel_dp_complete_link_train(intel_dp);
 		if (port != PORT_A)
 			intel_dp_stop_link_train(intel_dp);
+	} else if (type == INTEL_OUTPUT_HDMI) {
+		struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+
+		intel_hdmi->set_infoframes(encoder,
+					   crtc->config.has_hdmi_sink,
+					   &crtc->config.adjusted_mode);
 	}
 }
 
@@ -1385,7 +1354,8 @@ static void intel_enable_ddi(struct intel_encoder *intel_encoder)
 		intel_edp_psr_enable(intel_dp);
 	}
 
-	if (intel_crtc->eld_vld && type != INTEL_OUTPUT_EDP) {
+	if (intel_crtc->config.has_audio) {
+		intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
 		tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
 		tmp |= ((AUDIO_OUTPUT_ENABLE_A | AUDIO_ELD_VALID_A) << (pipe * 4));
 		I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp);
@@ -1403,11 +1373,14 @@ static void intel_disable_ddi(struct intel_encoder *intel_encoder)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
 
-	if (intel_crtc->eld_vld && type != INTEL_OUTPUT_EDP) {
+	/* We can't touch HSW_AUD_PIN_ELD_CP_VLD uncionditionally because this
+	 * register is part of the power well on Haswell. */
+	if (intel_crtc->config.has_audio) {
 		tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
 		tmp &= ~((AUDIO_OUTPUT_ENABLE_A | AUDIO_ELD_VALID_A) <<
 			 (pipe * 4));
 		I915_WRITE(HSW_AUD_PIN_ELD_CP_VLD, tmp);
+		intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
 	}
 
 	if (type == INTEL_OUTPUT_EDP) {
@@ -1580,6 +1553,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 
 	switch (temp & TRANS_DDI_MODE_SELECT_MASK) {
 	case TRANS_DDI_MODE_SELECT_HDMI:
+		pipe_config->has_hdmi_sink = true;
 	case TRANS_DDI_MODE_SELECT_DVI:
 	case TRANS_DDI_MODE_SELECT_FDI:
 		break;
@@ -1592,6 +1566,12 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 		break;
 	}
 
+	if (intel_display_power_enabled(dev_priv, POWER_DOMAIN_AUDIO)) {
+		temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
+		if (temp & (AUDIO_OUTPUT_ENABLE_A << (intel_crtc->pipe * 4)))
+			pipe_config->has_audio = true;
+	}
+
 	if (encoder->type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp_bpp &&
 	    pipe_config->pipe_bpp > dev_priv->vbt.edp_bpp) {
 		/*
@@ -1708,7 +1688,6 @@ void intel_ddi_init(struct drm_device *dev, enum port port)
 			 DRM_MODE_ENCODER_TMDS);
 
 	intel_encoder->compute_config = intel_ddi_compute_config;
-	intel_encoder->mode_set = intel_ddi_mode_set;
 	intel_encoder->enable = intel_enable_ddi;
 	intel_encoder->pre_enable = intel_ddi_pre_enable;
 	intel_encoder->disable = intel_disable_ddi;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5b60e25baa3..f0be855ddf4 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -41,6 +41,9 @@
 #include <drm/drm_crtc_helper.h>
 #include <linux/dma_remapping.h>
 
+#define DIV_ROUND_CLOSEST_ULL(ll, d)	\
+	({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; })
+
 static void intel_increase_pllclock(struct drm_crtc *crtc);
 static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on);
 
@@ -55,6 +58,15 @@ static int intel_framebuffer_init(struct drm_device *dev,
 				  struct intel_framebuffer *ifb,
 				  struct drm_mode_fb_cmd2 *mode_cmd,
 				  struct drm_i915_gem_object *obj);
+static void intel_dp_set_m_n(struct intel_crtc *crtc);
+static void i9xx_set_pipeconf(struct intel_crtc *intel_crtc);
+static void intel_set_pipe_timings(struct intel_crtc *intel_crtc);
+static void intel_cpu_transcoder_set_m_n(struct intel_crtc *crtc,
+					 struct intel_link_m_n *m_n);
+static void ironlake_set_pipeconf(struct drm_crtc *crtc);
+static void haswell_set_pipeconf(struct drm_crtc *crtc);
+static void intel_set_pipe_csc(struct drm_crtc *crtc);
+static void vlv_prepare_pll(struct intel_crtc *crtc);
 
 typedef struct {
 	int	min, max;
@@ -328,6 +340,22 @@ static const intel_limit_t intel_limits_vlv = {
 	.p2 = { .p2_slow = 2, .p2_fast = 20 }, /* slow=min, fast=max */
 };
 
+static const intel_limit_t intel_limits_chv = {
+	/*
+	 * These are the data rate limits (measured in fast clocks)
+	 * since those are the strictest limits we have.  The fast
+	 * clock and actual rate limits are more relaxed, so checking
+	 * them would make no difference.
+	 */
+	.dot = { .min = 25000 * 5, .max = 540000 * 5},
+	.vco = { .min = 4860000, .max = 6700000 },
+	.n = { .min = 1, .max = 1 },
+	.m1 = { .min = 2, .max = 2 },
+	.m2 = { .min = 24 << 22, .max = 175 << 22 },
+	.p1 = { .min = 2, .max = 4 },
+	.p2 = {	.p2_slow = 1, .p2_fast = 14 },
+};
+
 static void vlv_clock(int refclk, intel_clock_t *clock)
 {
 	clock->m = clock->m1 * clock->m2;
@@ -412,6 +440,8 @@ static const intel_limit_t *intel_limit(struct drm_crtc *crtc, int refclk)
 			limit = &intel_limits_pineview_lvds;
 		else
 			limit = &intel_limits_pineview_sdvo;
+	} else if (IS_CHERRYVIEW(dev)) {
+		limit = &intel_limits_chv;
 	} else if (IS_VALLEYVIEW(dev)) {
 		limit = &intel_limits_vlv;
 	} else if (!IS_GEN2(dev)) {
@@ -456,6 +486,17 @@ static void i9xx_clock(int refclk, intel_clock_t *clock)
 	clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
 }
 
+static void chv_clock(int refclk, intel_clock_t *clock)
+{
+	clock->m = clock->m1 * clock->m2;
+	clock->p = clock->p1 * clock->p2;
+	if (WARN_ON(clock->n == 0 || clock->p == 0))
+		return;
+	clock->vco = DIV_ROUND_CLOSEST_ULL((uint64_t)refclk * clock->m,
+			clock->n << 22);
+	clock->dot = DIV_ROUND_CLOSEST(clock->vco, clock->p);
+}
+
 #define INTELPllInvalid(s)   do { /* DRM_DEBUG(s); */ return false; } while (0)
 /**
  * Returns whether the given set of divisors are valid for a given refclk with
@@ -731,6 +772,58 @@ vlv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
 	return found;
 }
 
+static bool
+chv_find_best_dpll(const intel_limit_t *limit, struct drm_crtc *crtc,
+		   int target, int refclk, intel_clock_t *match_clock,
+		   intel_clock_t *best_clock)
+{
+	struct drm_device *dev = crtc->dev;
+	intel_clock_t clock;
+	uint64_t m2;
+	int found = false;
+
+	memset(best_clock, 0, sizeof(*best_clock));
+
+	/*
+	 * Based on hardware doc, the n always set to 1, and m1 always
+	 * set to 2.  If requires to support 200Mhz refclk, we need to
+	 * revisit this because n may not 1 anymore.
+	 */
+	clock.n = 1, clock.m1 = 2;
+	target *= 5;	/* fast clock */
+
+	for (clock.p1 = limit->p1.max; clock.p1 >= limit->p1.min; clock.p1--) {
+		for (clock.p2 = limit->p2.p2_fast;
+				clock.p2 >= limit->p2.p2_slow;
+				clock.p2 -= clock.p2 > 10 ? 2 : 1) {
+
+			clock.p = clock.p1 * clock.p2;
+
+			m2 = DIV_ROUND_CLOSEST_ULL(((uint64_t)target * clock.p *
+					clock.n) << 22, refclk * clock.m1);
+
+			if (m2 > INT_MAX/clock.m1)
+				continue;
+
+			clock.m2 = m2;
+
+			chv_clock(refclk, &clock);
+
+			if (!intel_PLL_is_valid(dev, limit, &clock))
+				continue;
+
+			/* based on hardware requirement, prefer bigger p
+			 */
+			if (clock.p > best_clock->p) {
+				*best_clock = clock;
+				found = true;
+			}
+		}
+	}
+
+	return found;
+}
+
 bool intel_crtc_active(struct drm_crtc *crtc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -765,7 +858,7 @@ static void g4x_wait_for_vblank(struct drm_device *dev, int pipe)
 	frame = I915_READ(frame_reg);
 
 	if (wait_for(I915_READ_NOTRACE(frame_reg) != frame, 50))
-		DRM_DEBUG_KMS("vblank wait timed out\n");
+		WARN(1, "vblank wait timed out\n");
 }
 
 /**
@@ -878,7 +971,7 @@ bool ibx_digital_port_connected(struct drm_i915_private *dev_priv,
 	u32 bit;
 
 	if (HAS_PCH_IBX(dev_priv->dev)) {
-		switch(port->port) {
+		switch (port->port) {
 		case PORT_B:
 			bit = SDE_PORTB_HOTPLUG;
 			break;
@@ -892,7 +985,7 @@ bool ibx_digital_port_connected(struct drm_i915_private *dev_priv,
 			return true;
 		}
 	} else {
-		switch(port->port) {
+		switch (port->port) {
 		case PORT_B:
 			bit = SDE_PORTB_HOTPLUG_CPT;
 			break;
@@ -1097,10 +1190,8 @@ static void assert_cursor(struct drm_i915_private *dev_priv,
 
 	if (IS_845G(dev) || IS_I865G(dev))
 		cur_state = I915_READ(_CURACNTR) & CURSOR_ENABLE;
-	else if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev))
-		cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
 	else
-		cur_state = I915_READ(CURCNTR_IVB(pipe)) & CURSOR_MODE;
+		cur_state = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
 
 	WARN(cur_state != state,
 	     "cursor on pipe %c assertion failure (expected %s, current %s)\n",
@@ -1253,6 +1344,9 @@ static bool dp_pipe_enabled(struct drm_i915_private *dev_priv,
 		u32	trans_dp_ctl = I915_READ(trans_dp_ctl_reg);
 		if ((trans_dp_ctl & TRANS_DP_PORT_SEL_MASK) != port_sel)
 			return false;
+	} else if (IS_CHERRYVIEW(dev_priv->dev)) {
+		if ((val & DP_PIPE_MASK_CHV) != DP_PIPE_SELECT_CHV(pipe))
+			return false;
 	} else {
 		if ((val & DP_PIPE_MASK) != (pipe << 30))
 			return false;
@@ -1269,6 +1363,9 @@ static bool hdmi_pipe_enabled(struct drm_i915_private *dev_priv,
 	if (HAS_PCH_CPT(dev_priv->dev)) {
 		if ((val & SDVO_PIPE_SEL_MASK_CPT) != SDVO_PIPE_SEL_CPT(pipe))
 			return false;
+	} else if (IS_CHERRYVIEW(dev_priv->dev)) {
+		if ((val & SDVO_PIPE_SEL_MASK_CHV) != SDVO_PIPE_SEL_CHV(pipe))
+			return false;
 	} else {
 		if ((val & SDVO_PIPE_SEL_MASK) != SDVO_PIPE_SEL(pipe))
 			return false;
@@ -1367,7 +1464,17 @@ static void intel_init_dpio(struct drm_device *dev)
 	if (!IS_VALLEYVIEW(dev))
 		return;
 
-	DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO;
+	/*
+	 * IOSF_PORT_DPIO is used for VLV x2 PHY (DP/HDMI B and C),
+	 * CHV x1 PHY (DP/HDMI D)
+	 * IOSF_PORT_DPIO_2 is used for CHV x2 PHY (DP/HDMI B and C)
+	 */
+	if (IS_CHERRYVIEW(dev)) {
+		DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO_2;
+		DPIO_PHY_IOSF_PORT(DPIO_PHY1) = IOSF_PORT_DPIO;
+	} else {
+		DPIO_PHY_IOSF_PORT(DPIO_PHY0) = IOSF_PORT_DPIO;
+	}
 }
 
 static void intel_reset_dpio(struct drm_device *dev)
@@ -1377,25 +1484,48 @@ static void intel_reset_dpio(struct drm_device *dev)
 	if (!IS_VALLEYVIEW(dev))
 		return;
 
-	/*
-	 * Enable the CRI clock source so we can get at the display and the
-	 * reference clock for VGA hotplug / manual detection.
-	 */
-	I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) |
-		   DPLL_REFA_CLK_ENABLE_VLV |
-		   DPLL_INTEGRATED_CRI_CLK_VLV);
+	if (IS_CHERRYVIEW(dev)) {
+		enum dpio_phy phy;
+		u32 val;
 
-	/*
-	 * From VLV2A0_DP_eDP_DPIO_driver_vbios_notes_10.docx -
-	 *  6.	De-assert cmn_reset/side_reset. Same as VLV X0.
-	 *   a.	GUnit 0x2110 bit[0] set to 1 (def 0)
-	 *   b.	The other bits such as sfr settings / modesel may all be set
-	 *      to 0.
-	 *
-	 * This should only be done on init and resume from S3 with both
-	 * PLLs disabled, or we risk losing DPIO and PLL synchronization.
-	 */
-	I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) | DPIO_CMNRST);
+		for (phy = DPIO_PHY0; phy < I915_NUM_PHYS_VLV; phy++) {
+			/* Poll for phypwrgood signal */
+			if (wait_for(I915_READ(DISPLAY_PHY_STATUS) &
+						PHY_POWERGOOD(phy), 1))
+				DRM_ERROR("Display PHY %d is not power up\n", phy);
+
+			/*
+			 * Deassert common lane reset for PHY.
+			 *
+			 * This should only be done on init and resume from S3
+			 * with both PLLs disabled, or we risk losing DPIO and
+			 * PLL synchronization.
+			 */
+			val = I915_READ(DISPLAY_PHY_CONTROL);
+			I915_WRITE(DISPLAY_PHY_CONTROL,
+				PHY_COM_LANE_RESET_DEASSERT(phy, val));
+		}
+
+	} else {
+		/*
+		 * If DPIO has already been reset, e.g. by BIOS, just skip all
+		 * this.
+		 */
+		if (I915_READ(DPIO_CTL) & DPIO_CMNRST)
+			return;
+
+		/*
+		 * From VLV2A0_DP_eDP_HDMI_DPIO_driver_vbios_notes_11.docx:
+		 * Need to assert and de-assert PHY SB reset by gating the
+		 * common lane power, then un-gating it.
+		 * Simply ungating isn't enough to reset the PHY enough to get
+		 * ports and lanes running.
+		 */
+		__vlv_set_power_well(dev_priv, PUNIT_POWER_WELL_DPIO_CMN_BC,
+				     false);
+		__vlv_set_power_well(dev_priv, PUNIT_POWER_WELL_DPIO_CMN_BC,
+				     true);
+	}
 }
 
 static void vlv_enable_pll(struct intel_crtc *crtc)
@@ -1436,6 +1566,44 @@ static void vlv_enable_pll(struct intel_crtc *crtc)
 	udelay(150); /* wait for warmup */
 }
 
+static void chv_enable_pll(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe = crtc->pipe;
+	enum dpio_channel port = vlv_pipe_to_channel(pipe);
+	u32 tmp;
+
+	assert_pipe_disabled(dev_priv, crtc->pipe);
+
+	BUG_ON(!IS_CHERRYVIEW(dev_priv->dev));
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* Enable back the 10bit clock to display controller */
+	tmp = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port));
+	tmp |= DPIO_DCLKP_EN;
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), tmp);
+
+	/*
+	 * Need to wait > 100ns between dclkp clock enable bit and PLL enable.
+	 */
+	udelay(1);
+
+	/* Enable PLL */
+	I915_WRITE(DPLL(pipe), crtc->config.dpll_hw_state.dpll);
+
+	/* Check PLL is locked */
+	if (wait_for(((I915_READ(DPLL(pipe)) & DPLL_LOCK_VLV) == DPLL_LOCK_VLV), 1))
+		DRM_ERROR("PLL %d failed to lock\n", pipe);
+
+	/* not sure when this should be written */
+	I915_WRITE(DPLL_MD(pipe), crtc->config.dpll_hw_state.dpll_md);
+	POSTING_READ(DPLL_MD(pipe));
+
+	mutex_unlock(&dev_priv->dpio_lock);
+}
+
 static void i9xx_enable_pll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -1519,45 +1687,92 @@ static void vlv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 		val = DPLL_INTEGRATED_CRI_CLK_VLV | DPLL_REFA_CLK_ENABLE_VLV;
 	I915_WRITE(DPLL(pipe), val);
 	POSTING_READ(DPLL(pipe));
+
+}
+
+static void chv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
+{
+	enum dpio_channel port = vlv_pipe_to_channel(pipe);
+	u32 val;
+
+	/* Make sure the pipe isn't still relying on us */
+	assert_pipe_disabled(dev_priv, pipe);
+
+	/* Set PLL en = 0 */
+	val = DPLL_SSC_REF_CLOCK_CHV;
+	if (pipe != PIPE_A)
+		val |= DPLL_INTEGRATED_CRI_CLK_VLV;
+	I915_WRITE(DPLL(pipe), val);
+	POSTING_READ(DPLL(pipe));
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* Disable 10bit clock to display controller */
+	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port));
+	val &= ~DPIO_DCLKP_EN;
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), val);
+
+	mutex_unlock(&dev_priv->dpio_lock);
 }
 
 void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 		struct intel_digital_port *dport)
 {
 	u32 port_mask;
+	int dpll_reg;
 
 	switch (dport->port) {
 	case PORT_B:
 		port_mask = DPLL_PORTB_READY_MASK;
+		dpll_reg = DPLL(0);
 		break;
 	case PORT_C:
 		port_mask = DPLL_PORTC_READY_MASK;
+		dpll_reg = DPLL(0);
+		break;
+	case PORT_D:
+		port_mask = DPLL_PORTD_READY_MASK;
+		dpll_reg = DPIO_PHY_STATUS;
 		break;
 	default:
 		BUG();
 	}
 
-	if (wait_for((I915_READ(DPLL(0)) & port_mask) == 0, 1000))
+	if (wait_for((I915_READ(dpll_reg) & port_mask) == 0, 1000))
 		WARN(1, "timed out waiting for port %c ready: 0x%08x\n",
-		     port_name(dport->port), I915_READ(DPLL(0)));
+		     port_name(dport->port), I915_READ(dpll_reg));
+}
+
+static void intel_prepare_shared_dpll(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc);
+
+	WARN_ON(!pll->refcount);
+	if (pll->active == 0) {
+		DRM_DEBUG_DRIVER("setting up %s\n", pll->name);
+		WARN_ON(pll->on);
+		assert_shared_dpll_disabled(dev_priv, pll);
+
+		pll->mode_set(dev_priv, pll);
+	}
 }
 
 /**
- * ironlake_enable_shared_dpll - enable PCH PLL
+ * intel_enable_shared_dpll - enable PCH PLL
  * @dev_priv: i915 private structure
  * @pipe: pipe PLL to enable
  *
  * The PCH PLL needs to be enabled before the PCH transcoder, since it
  * drives the transcoder clock.
  */
-static void ironlake_enable_shared_dpll(struct intel_crtc *crtc)
+static void intel_enable_shared_dpll(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc);
 
-	/* PCH PLLs only available on ILK, SNB and IVB */
-	BUG_ON(INTEL_INFO(dev)->gen < 5);
 	if (WARN_ON(pll == NULL))
 		return;
 
@@ -1804,16 +2019,6 @@ static void intel_enable_pipe(struct intel_crtc *crtc)
 
 	I915_WRITE(reg, val | PIPECONF_ENABLE);
 	POSTING_READ(reg);
-
-	/*
-	 * There's no guarantee the pipe will really start running now. It
-	 * depends on the Gen, the output type and the relative order between
-	 * pipe and plane enabling. Avoid waiting on HSW+ since it's not
-	 * necessary.
-	 * TODO: audit the previous gens.
-	 */
-	if (INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev))
-		intel_wait_for_vblank(dev_priv->dev, pipe);
 }
 
 /**
@@ -1882,6 +2087,7 @@ void intel_flush_primary_plane(struct drm_i915_private *dev_priv,
 static void intel_enable_primary_hw_plane(struct drm_i915_private *dev_priv,
 					  enum plane plane, enum pipe pipe)
 {
+	struct drm_device *dev = dev_priv->dev;
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 	int reg;
@@ -1890,18 +2096,25 @@ static void intel_enable_primary_hw_plane(struct drm_i915_private *dev_priv,
 	/* If the pipe isn't enabled, we can't pump pixels and may hang */
 	assert_pipe_enabled(dev_priv, pipe);
 
-	WARN(intel_crtc->primary_enabled, "Primary plane already enabled\n");
+	if (intel_crtc->primary_enabled)
+		return;
 
 	intel_crtc->primary_enabled = true;
 
 	reg = DSPCNTR(plane);
 	val = I915_READ(reg);
-	if (val & DISPLAY_PLANE_ENABLE)
-		return;
+	WARN_ON(val & DISPLAY_PLANE_ENABLE);
 
 	I915_WRITE(reg, val | DISPLAY_PLANE_ENABLE);
 	intel_flush_primary_plane(dev_priv, plane);
-	intel_wait_for_vblank(dev_priv->dev, pipe);
+
+	/*
+	 * BDW signals flip done immediately if the plane
+	 * is disabled, even if the plane enable is already
+	 * armed to occur at the next vblank :(
+	 */
+	if (IS_BROADWELL(dev))
+		intel_wait_for_vblank(dev, intel_crtc->pipe);
 }
 
 /**
@@ -1920,18 +2133,17 @@ static void intel_disable_primary_hw_plane(struct drm_i915_private *dev_priv,
 	int reg;
 	u32 val;
 
-	WARN(!intel_crtc->primary_enabled, "Primary plane already disabled\n");
+	if (!intel_crtc->primary_enabled)
+		return;
 
 	intel_crtc->primary_enabled = false;
 
 	reg = DSPCNTR(plane);
 	val = I915_READ(reg);
-	if ((val & DISPLAY_PLANE_ENABLE) == 0)
-		return;
+	WARN_ON((val & DISPLAY_PLANE_ENABLE) == 0);
 
 	I915_WRITE(reg, val & ~DISPLAY_PLANE_ENABLE);
 	intel_flush_primary_plane(dev_priv, plane);
-	intel_wait_for_vblank(dev_priv->dev, pipe);
 }
 
 static bool need_vtd_wa(struct drm_device *dev)
@@ -1954,7 +2166,7 @@ static int intel_align_height(struct drm_device *dev, int height, bool tiled)
 int
 intel_pin_and_fence_fb_obj(struct drm_device *dev,
 			   struct drm_i915_gem_object *obj,
-			   struct intel_ring_buffer *pipelined)
+			   struct intel_engine_cs *pipelined)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 alignment;
@@ -2134,7 +2346,7 @@ static void intel_find_plane_obj(struct intel_crtc *intel_crtc,
 	 * Failed to alloc the obj, check to see if we should share
 	 * an fb with another CRTC instead
 	 */
-	list_for_each_entry(c, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, c) {
 		i = to_intel_crtc(c);
 
 		if (c == &intel_crtc->base)
@@ -2152,9 +2364,9 @@ static void intel_find_plane_obj(struct intel_crtc *intel_crtc,
 	}
 }
 
-static int i9xx_update_primary_plane(struct drm_crtc *crtc,
-				     struct drm_framebuffer *fb,
-				     int x, int y)
+static void i9xx_update_primary_plane(struct drm_crtc *crtc,
+				      struct drm_framebuffer *fb,
+				      int x, int y)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2166,15 +2378,6 @@ static int i9xx_update_primary_plane(struct drm_crtc *crtc,
 	u32 dspcntr;
 	u32 reg;
 
-	switch (plane) {
-	case 0:
-	case 1:
-		break;
-	default:
-		DRM_ERROR("Can't update plane %c in SAREA\n", plane_name(plane));
-		return -EINVAL;
-	}
-
 	intel_fb = to_intel_framebuffer(fb);
 	obj = intel_fb->obj;
 
@@ -2249,13 +2452,11 @@ static int i9xx_update_primary_plane(struct drm_crtc *crtc,
 	} else
 		I915_WRITE(DSPADDR(plane), i915_gem_obj_ggtt_offset(obj) + linear_offset);
 	POSTING_READ(reg);
-
-	return 0;
 }
 
-static int ironlake_update_primary_plane(struct drm_crtc *crtc,
-					 struct drm_framebuffer *fb,
-					 int x, int y)
+static void ironlake_update_primary_plane(struct drm_crtc *crtc,
+					  struct drm_framebuffer *fb,
+					  int x, int y)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2267,16 +2468,6 @@ static int ironlake_update_primary_plane(struct drm_crtc *crtc,
 	u32 dspcntr;
 	u32 reg;
 
-	switch (plane) {
-	case 0:
-	case 1:
-	case 2:
-		break;
-	default:
-		DRM_ERROR("Can't update plane %c in SAREA\n", plane_name(plane));
-		return -EINVAL;
-	}
-
 	intel_fb = to_intel_framebuffer(fb);
 	obj = intel_fb->obj;
 
@@ -2343,8 +2534,6 @@ static int ironlake_update_primary_plane(struct drm_crtc *crtc,
 		I915_WRITE(DSPLINOFF(plane), linear_offset);
 	}
 	POSTING_READ(reg);
-
-	return 0;
 }
 
 /* Assume fb object is pinned & idle & fenced and just update base pointers */
@@ -2359,7 +2548,9 @@ intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		dev_priv->display.disable_fbc(dev);
 	intel_increase_pllclock(crtc);
 
-	return dev_priv->display.update_primary_plane(crtc, fb, x, y);
+	dev_priv->display.update_primary_plane(crtc, fb, x, y);
+
+	return 0;
 }
 
 void intel_display_handle_reset(struct drm_device *dev)
@@ -2381,7 +2572,7 @@ void intel_display_handle_reset(struct drm_device *dev)
 	 * pending_flip_queue really got woken up.
 	 */
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 		enum plane plane = intel_crtc->plane;
 
@@ -2389,10 +2580,10 @@ void intel_display_handle_reset(struct drm_device *dev)
 		intel_finish_page_flip_plane(dev, plane);
 	}
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-		mutex_lock(&crtc->mutex);
+		drm_modeset_lock(&crtc->mutex, NULL);
 		/*
 		 * FIXME: Once we have proper support for primary planes (and
 		 * disabling them without disabling the entire crtc) allow again
@@ -2403,7 +2594,7 @@ void intel_display_handle_reset(struct drm_device *dev)
 							       crtc->primary->fb,
 							       crtc->x,
 							       crtc->y);
-		mutex_unlock(&crtc->mutex);
+		drm_modeset_unlock(&crtc->mutex);
 	}
 }
 
@@ -2518,14 +2709,7 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 		intel_crtc->config.pipe_src_h = adjusted_mode->crtc_vdisplay;
 	}
 
-	ret = dev_priv->display.update_primary_plane(crtc, fb, x, y);
-	if (ret) {
-		mutex_lock(&dev->struct_mutex);
-		intel_unpin_fb_obj(to_intel_framebuffer(fb)->obj);
-		mutex_unlock(&dev->struct_mutex);
-		DRM_ERROR("failed to update base address\n");
-		return ret;
-	}
+	dev_priv->display.update_primary_plane(crtc, fb, x, y);
 
 	old_fb = crtc->primary->fb;
 	crtc->primary->fb = fb;
@@ -2628,12 +2812,10 @@ static void ironlake_fdi_link_train(struct drm_crtc *crtc)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
 	u32 reg, temp, tries;
 
-	/* FDI needs bits from pipe & plane first */
+	/* FDI needs bits from pipe first */
 	assert_pipe_enabled(dev_priv, pipe);
-	assert_plane_enabled(dev_priv, plane);
 
 	/* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit
 	   for train result */
@@ -3064,9 +3246,8 @@ static void ironlake_fdi_disable(struct drm_crtc *crtc)
 	udelay(100);
 
 	/* Ironlake workaround, disable clock pointer after downing FDI */
-	if (HAS_PCH_IBX(dev)) {
+	if (HAS_PCH_IBX(dev))
 		I915_WRITE(FDI_RX_CHICKEN(pipe), FDI_RX_PHASE_SYNC_POINTER_OVR);
-	}
 
 	/* still set train pattern 1 */
 	reg = FDI_TX_CTL(pipe);
@@ -3104,7 +3285,7 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev)
 	 * cannot claim and pin a new fb without at least acquring the
 	 * struct_mutex and so serialising with us.
 	 */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		if (atomic_read(&crtc->unpin_work_count) == 0)
 			continue;
 
@@ -3117,7 +3298,7 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev)
 	return false;
 }
 
-static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
+void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3127,8 +3308,9 @@ static void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
 
 	WARN_ON(waitqueue_active(&dev_priv->pending_flip_queue));
 
-	wait_event(dev_priv->pending_flip_queue,
-		   !intel_crtc_has_pending_flip(crtc));
+	WARN_ON(wait_event_timeout(dev_priv->pending_flip_queue,
+				   !intel_crtc_has_pending_flip(crtc),
+				   60*HZ) == 0);
 
 	mutex_lock(&dev->struct_mutex);
 	intel_finish_fb(crtc->primary->fb);
@@ -3341,7 +3523,7 @@ static void ironlake_pch_enable(struct drm_crtc *crtc)
 	 * Note that enable_shared_dpll tries to do the right thing, but
 	 * get_shared_dpll unconditionally resets the pll - we need that to have
 	 * the right LVDS enable sequence. */
-	ironlake_enable_shared_dpll(intel_crtc);
+	intel_enable_shared_dpll(intel_crtc);
 
 	/* set transcoder timing, panel must allow it */
 	assert_panel_unlocked(dev_priv, pipe);
@@ -3445,6 +3627,8 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc)
 		DRM_DEBUG_KMS("CRTC:%d using pre-allocated %s\n",
 			      crtc->base.base.id, pll->name);
 
+		WARN_ON(pll->refcount);
+
 		goto found;
 	}
 
@@ -3478,20 +3662,13 @@ static struct intel_shared_dpll *intel_get_shared_dpll(struct intel_crtc *crtc)
 	return NULL;
 
 found:
+	if (pll->refcount == 0)
+		pll->hw_state = crtc->config.dpll_hw_state;
+
 	crtc->config.shared_dpll = i;
 	DRM_DEBUG_DRIVER("using %s for pipe %c\n", pll->name,
 			 pipe_name(crtc->pipe));
 
-	if (pll->active == 0) {
-		memcpy(&pll->hw_state, &crtc->config.dpll_hw_state,
-		       sizeof(pll->hw_state));
-
-		DRM_DEBUG_DRIVER("setting up %s\n", pll->name);
-		WARN_ON(pll->on);
-		assert_shared_dpll_disabled(dev_priv, pll);
-
-		pll->mode_set(dev_priv, pll);
-	}
 	pll->refcount++;
 
 	return pll;
@@ -3562,17 +3739,17 @@ static void intel_disable_planes(struct drm_crtc *crtc)
 
 void hsw_enable_ips(struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	if (!crtc->config.ips_enabled)
 		return;
 
-	/* We can only enable IPS after we enable a plane and wait for a vblank.
-	 * We guarantee that the plane is enabled by calling intel_enable_ips
-	 * only after intel_enable_plane. And intel_enable_plane already waits
-	 * for a vblank, so all we need to do here is to enable the IPS bit. */
+	/* We can only enable IPS after we enable a plane and wait for a vblank */
+	intel_wait_for_vblank(dev, crtc->pipe);
+
 	assert_plane_enabled(dev_priv, crtc->plane);
-	if (IS_BROADWELL(crtc->base.dev)) {
+	if (IS_BROADWELL(dev)) {
 		mutex_lock(&dev_priv->rps.hw_lock);
 		WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0xc0000000));
 		mutex_unlock(&dev_priv->rps.hw_lock);
@@ -3602,10 +3779,13 @@ void hsw_disable_ips(struct intel_crtc *crtc)
 		return;
 
 	assert_plane_enabled(dev_priv, crtc->plane);
-	if (IS_BROADWELL(crtc->base.dev)) {
+	if (IS_BROADWELL(dev)) {
 		mutex_lock(&dev_priv->rps.hw_lock);
 		WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0));
 		mutex_unlock(&dev_priv->rps.hw_lock);
+		/* wait for pcode to finish disabling IPS, which may take up to 42ms */
+		if (wait_for((I915_READ(IPS_CTL) & IPS_ENABLE) == 0, 42))
+			DRM_ERROR("Timed out waiting for IPS disable\n");
 	} else {
 		I915_WRITE(IPS_CTL, 0);
 		POSTING_READ(IPS_CTL);
@@ -3662,6 +3842,94 @@ static void intel_crtc_load_lut(struct drm_crtc *crtc)
 		hsw_enable_ips(intel_crtc);
 }
 
+static void intel_crtc_dpms_overlay(struct intel_crtc *intel_crtc, bool enable)
+{
+	if (!enable && intel_crtc->overlay) {
+		struct drm_device *dev = intel_crtc->base.dev;
+		struct drm_i915_private *dev_priv = dev->dev_private;
+
+		mutex_lock(&dev->struct_mutex);
+		dev_priv->mm.interruptible = false;
+		(void) intel_overlay_switch_off(intel_crtc->overlay);
+		dev_priv->mm.interruptible = true;
+		mutex_unlock(&dev->struct_mutex);
+	}
+
+	/* Let userspace switch the overlay on again. In most cases userspace
+	 * has to recompute where to put it anyway.
+	 */
+}
+
+/**
+ * i9xx_fixup_plane - ugly workaround for G45 to fire up the hardware
+ * cursor plane briefly if not already running after enabling the display
+ * plane.
+ * This workaround avoids occasional blank screens when self refresh is
+ * enabled.
+ */
+static void
+g4x_fixup_plane(struct drm_i915_private *dev_priv, enum pipe pipe)
+{
+	u32 cntl = I915_READ(CURCNTR(pipe));
+
+	if ((cntl & CURSOR_MODE) == 0) {
+		u32 fw_bcl_self = I915_READ(FW_BLC_SELF);
+
+		I915_WRITE(FW_BLC_SELF, fw_bcl_self & ~FW_BLC_SELF_EN);
+		I915_WRITE(CURCNTR(pipe), CURSOR_MODE_64_ARGB_AX);
+		intel_wait_for_vblank(dev_priv->dev, pipe);
+		I915_WRITE(CURCNTR(pipe), cntl);
+		I915_WRITE(CURBASE(pipe), I915_READ(CURBASE(pipe)));
+		I915_WRITE(FW_BLC_SELF, fw_bcl_self);
+	}
+}
+
+static void intel_crtc_enable_planes(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	int pipe = intel_crtc->pipe;
+	int plane = intel_crtc->plane;
+
+	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
+	intel_enable_planes(crtc);
+	/* The fixup needs to happen before cursor is enabled */
+	if (IS_G4X(dev))
+		g4x_fixup_plane(dev_priv, pipe);
+	intel_crtc_update_cursor(crtc, true);
+	intel_crtc_dpms_overlay(intel_crtc, true);
+
+	hsw_enable_ips(intel_crtc);
+
+	mutex_lock(&dev->struct_mutex);
+	intel_update_fbc(dev);
+	intel_edp_psr_update(dev);
+	mutex_unlock(&dev->struct_mutex);
+}
+
+static void intel_crtc_disable_planes(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	int pipe = intel_crtc->pipe;
+	int plane = intel_crtc->plane;
+
+	intel_crtc_wait_for_pending_flips(crtc);
+	drm_crtc_vblank_off(crtc);
+
+	if (dev_priv->fbc.plane == plane)
+		intel_disable_fbc(dev);
+
+	hsw_disable_ips(intel_crtc);
+
+	intel_crtc_dpms_overlay(intel_crtc, false);
+	intel_crtc_update_cursor(crtc, false);
+	intel_disable_planes(crtc);
+	intel_disable_primary_hw_plane(dev_priv, plane, pipe);
+}
+
 static void ironlake_crtc_enable(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -3669,13 +3937,35 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
+	enum plane plane = intel_crtc->plane;
 
 	WARN_ON(!crtc->enabled);
 
 	if (intel_crtc->active)
 		return;
 
+	if (intel_crtc->config.has_pch_encoder)
+		intel_prepare_shared_dpll(intel_crtc);
+
+	if (intel_crtc->config.has_dp_encoder)
+		intel_dp_set_m_n(intel_crtc);
+
+	intel_set_pipe_timings(intel_crtc);
+
+	if (intel_crtc->config.has_pch_encoder) {
+		intel_cpu_transcoder_set_m_n(intel_crtc,
+					     &intel_crtc->config.fdi_m_n);
+	}
+
+	ironlake_set_pipeconf(crtc);
+
+	/* Set up the display plane register */
+	I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE);
+	POSTING_READ(DSPCNTR(plane));
+
+	dev_priv->display.update_primary_plane(crtc, crtc->primary->fb,
+					       crtc->x, crtc->y);
+
 	intel_crtc->active = true;
 
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
@@ -3705,32 +3995,19 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 
 	intel_update_watermarks(crtc);
 	intel_enable_pipe(intel_crtc);
-	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
-	intel_enable_planes(crtc);
-	intel_crtc_update_cursor(crtc, true);
 
 	if (intel_crtc->config.has_pch_encoder)
 		ironlake_pch_enable(crtc);
 
-	mutex_lock(&dev->struct_mutex);
-	intel_update_fbc(dev);
-	mutex_unlock(&dev->struct_mutex);
-
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		encoder->enable(encoder);
 
 	if (HAS_PCH_CPT(dev))
 		cpt_verify_modeset(dev, intel_crtc->pipe);
 
-	/*
-	 * There seems to be a race in PCH platform hw (at least on some
-	 * outputs) where an enabled pipe still completes any pageflip right
-	 * away (as if the pipe is off) instead of waiting for vblank. As soon
-	 * as the first vblank happend, everything works as expected. Hence just
-	 * wait for one vblank before returning to avoid strange things
-	 * happening.
-	 */
-	intel_wait_for_vblank(dev, intel_crtc->pipe);
+	intel_crtc_enable_planes(crtc);
+
+	drm_crtc_vblank_on(crtc);
 }
 
 /* IPS only exists on ULT machines and is tied to pipe A. */
@@ -3739,47 +4016,6 @@ static bool hsw_crtc_supports_ips(struct intel_crtc *crtc)
 	return HAS_IPS(crtc->base.dev) && crtc->pipe == PIPE_A;
 }
 
-static void haswell_crtc_enable_planes(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
-
-	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
-	intel_enable_planes(crtc);
-	intel_crtc_update_cursor(crtc, true);
-
-	hsw_enable_ips(intel_crtc);
-
-	mutex_lock(&dev->struct_mutex);
-	intel_update_fbc(dev);
-	mutex_unlock(&dev->struct_mutex);
-}
-
-static void haswell_crtc_disable_planes(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
-
-	intel_crtc_wait_for_pending_flips(crtc);
-	drm_vblank_off(dev, pipe);
-
-	/* FBC must be disabled before disabling the plane on HSW. */
-	if (dev_priv->fbc.plane == plane)
-		intel_disable_fbc(dev);
-
-	hsw_disable_ips(intel_crtc);
-
-	intel_crtc_update_cursor(crtc, false);
-	intel_disable_planes(crtc);
-	intel_disable_primary_hw_plane(dev_priv, plane, pipe);
-}
-
 /*
  * This implements the workaround described in the "notes" section of the mode
  * set sequence documentation. When going from no pipes or single pipe to
@@ -3793,7 +4029,7 @@ static void haswell_mode_set_planes_workaround(struct intel_crtc *crtc)
 
 	/* We want to get the other_active_crtc only if there's only 1 other
 	 * active crtc. */
-	list_for_each_entry(crtc_it, &dev->mode_config.crtc_list, base.head) {
+	for_each_intel_crtc(dev, crtc_it) {
 		if (!crtc_it->active || crtc_it == crtc)
 			continue;
 
@@ -3816,12 +4052,34 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
+	enum plane plane = intel_crtc->plane;
 
 	WARN_ON(!crtc->enabled);
 
 	if (intel_crtc->active)
 		return;
 
+	if (intel_crtc->config.has_dp_encoder)
+		intel_dp_set_m_n(intel_crtc);
+
+	intel_set_pipe_timings(intel_crtc);
+
+	if (intel_crtc->config.has_pch_encoder) {
+		intel_cpu_transcoder_set_m_n(intel_crtc,
+					     &intel_crtc->config.fdi_m_n);
+	}
+
+	haswell_set_pipeconf(crtc);
+
+	intel_set_pipe_csc(crtc);
+
+	/* Set up the display plane register */
+	I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE | DISPPLANE_PIPE_CSC_ENABLE);
+	POSTING_READ(DSPCNTR(plane));
+
+	dev_priv->display.update_primary_plane(crtc, crtc->primary->fb,
+					       crtc->x, crtc->y);
+
 	intel_crtc->active = true;
 
 	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
@@ -3862,7 +4120,9 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 	/* If we change the relative order between pipe/planes enabling, we need
 	 * to change the workaround. */
 	haswell_mode_set_planes_workaround(intel_crtc);
-	haswell_crtc_enable_planes(crtc);
+	intel_crtc_enable_planes(crtc);
+
+	drm_crtc_vblank_on(crtc);
 }
 
 static void ironlake_pfit_disable(struct intel_crtc *crtc)
@@ -3887,26 +4147,16 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
 	u32 reg, temp;
 
-
 	if (!intel_crtc->active)
 		return;
 
+	intel_crtc_disable_planes(crtc);
+
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		encoder->disable(encoder);
 
-	intel_crtc_wait_for_pending_flips(crtc);
-	drm_vblank_off(dev, pipe);
-
-	if (dev_priv->fbc.plane == plane)
-		intel_disable_fbc(dev);
-
-	intel_crtc_update_cursor(crtc, false);
-	intel_disable_planes(crtc);
-	intel_disable_primary_hw_plane(dev_priv, plane, pipe);
-
 	if (intel_crtc->config.has_pch_encoder)
 		intel_set_pch_fifo_underrun_reporting(dev, pipe, false);
 
@@ -3950,6 +4200,7 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 
 	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
+	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
 }
 
@@ -3965,7 +4216,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 	if (!intel_crtc->active)
 		return;
 
-	haswell_crtc_disable_planes(crtc);
+	intel_crtc_disable_planes(crtc);
 
 	for_each_encoder_on_crtc(dev, crtc, encoder) {
 		intel_opregion_notify_encoder(encoder, false);
@@ -3997,6 +4248,7 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 
 	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
+	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
 }
 
@@ -4011,48 +4263,6 @@ static void haswell_crtc_off(struct drm_crtc *crtc)
 	intel_ddi_put_crtc_pll(crtc);
 }
 
-static void intel_crtc_dpms_overlay(struct intel_crtc *intel_crtc, bool enable)
-{
-	if (!enable && intel_crtc->overlay) {
-		struct drm_device *dev = intel_crtc->base.dev;
-		struct drm_i915_private *dev_priv = dev->dev_private;
-
-		mutex_lock(&dev->struct_mutex);
-		dev_priv->mm.interruptible = false;
-		(void) intel_overlay_switch_off(intel_crtc->overlay);
-		dev_priv->mm.interruptible = true;
-		mutex_unlock(&dev->struct_mutex);
-	}
-
-	/* Let userspace switch the overlay on again. In most cases userspace
-	 * has to recompute where to put it anyway.
-	 */
-}
-
-/**
- * i9xx_fixup_plane - ugly workaround for G45 to fire up the hardware
- * cursor plane briefly if not already running after enabling the display
- * plane.
- * This workaround avoids occasional blank screens when self refresh is
- * enabled.
- */
-static void
-g4x_fixup_plane(struct drm_i915_private *dev_priv, enum pipe pipe)
-{
-	u32 cntl = I915_READ(CURCNTR(pipe));
-
-	if ((cntl & CURSOR_MODE) == 0) {
-		u32 fw_bcl_self = I915_READ(FW_BLC_SELF);
-
-		I915_WRITE(FW_BLC_SELF, fw_bcl_self & ~FW_BLC_SELF_EN);
-		I915_WRITE(CURCNTR(pipe), CURSOR_MODE_64_ARGB_AX);
-		intel_wait_for_vblank(dev_priv->dev, pipe);
-		I915_WRITE(CURCNTR(pipe), cntl);
-		I915_WRITE(CURBASE(pipe), I915_READ(CURBASE(pipe)));
-		I915_WRITE(FW_BLC_SELF, fw_bcl_self);
-	}
-}
-
 static void i9xx_pfit_enable(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -4164,7 +4374,7 @@ static void modeset_update_crtc_power_domains(struct drm_device *dev)
 	 * First get all needed power domains, then put all unneeded, to avoid
 	 * any unnecessary toggling of the power wells.
 	 */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		enum intel_display_power_domain domain;
 
 		if (!crtc->base.enabled)
@@ -4176,7 +4386,7 @@ static void modeset_update_crtc_power_domains(struct drm_device *dev)
 			intel_display_power_get(dev_priv, domain);
 	}
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		enum intel_display_power_domain domain;
 
 		for_each_power_domain(domain, crtc->enabled_power_domains)
@@ -4207,6 +4417,9 @@ static void valleyview_set_cdclk(struct drm_device *dev, int cdclk)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 val, cmd;
 
+	WARN_ON(valleyview_cur_cdclk(dev_priv) != dev_priv->vlv_cdclk_freq);
+	dev_priv->vlv_cdclk_freq = cdclk;
+
 	if (cdclk >= 320) /* jump to highest voltage for 400MHz too */
 		cmd = 2;
 	else if (cdclk == 266)
@@ -4261,7 +4474,7 @@ static void valleyview_set_cdclk(struct drm_device *dev, int cdclk)
 	intel_i2c_reset(dev);
 }
 
-static int valleyview_cur_cdclk(struct drm_i915_private *dev_priv)
+int valleyview_cur_cdclk(struct drm_i915_private *dev_priv)
 {
 	int cur_cdclk, vco;
 	int divider;
@@ -4282,10 +4495,6 @@ static int valleyview_cur_cdclk(struct drm_i915_private *dev_priv)
 static int valleyview_calc_cdclk(struct drm_i915_private *dev_priv,
 				 int max_pixclk)
 {
-	int cur_cdclk;
-
-	cur_cdclk = valleyview_cur_cdclk(dev_priv);
-
 	/*
 	 * Really only a few cases to deal with, as only 4 CDclks are supported:
 	 *   200MHz
@@ -4311,8 +4520,7 @@ static int intel_mode_max_pixclk(struct drm_i915_private *dev_priv)
 	struct intel_crtc *intel_crtc;
 	int max_pixclk = 0;
 
-	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, intel_crtc) {
 		if (intel_crtc->new_enabled)
 			max_pixclk = max(max_pixclk,
 					 intel_crtc->new_config->adjusted_mode.crtc_clock);
@@ -4327,14 +4535,13 @@ static void valleyview_modeset_global_pipes(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc;
 	int max_pixclk = intel_mode_max_pixclk(dev_priv);
-	int cur_cdclk = valleyview_cur_cdclk(dev_priv);
 
-	if (valleyview_calc_cdclk(dev_priv, max_pixclk) == cur_cdclk)
+	if (valleyview_calc_cdclk(dev_priv, max_pixclk) ==
+	    dev_priv->vlv_cdclk_freq)
 		return;
 
 	/* disable/enable all currently active pipes while we change cdclk */
-	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list,
-			    base.head)
+	for_each_intel_crtc(dev, intel_crtc)
 		if (intel_crtc->base.enabled)
 			*prepare_pipes |= (1 << intel_crtc->pipe);
 }
@@ -4343,10 +4550,9 @@ static void valleyview_modeset_global_resources(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int max_pixclk = intel_mode_max_pixclk(dev_priv);
-	int cur_cdclk = valleyview_cur_cdclk(dev_priv);
 	int req_cdclk = valleyview_calc_cdclk(dev_priv, max_pixclk);
 
-	if (req_cdclk != cur_cdclk)
+	if (req_cdclk != dev_priv->vlv_cdclk_freq)
 		valleyview_set_cdclk(dev, req_cdclk);
 	modeset_update_crtc_power_domains(dev);
 }
@@ -4360,22 +4566,56 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 	int pipe = intel_crtc->pipe;
 	int plane = intel_crtc->plane;
 	bool is_dsi;
+	u32 dspcntr;
 
 	WARN_ON(!crtc->enabled);
 
 	if (intel_crtc->active)
 		return;
 
+	is_dsi = intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI);
+
+	if (!is_dsi && !IS_CHERRYVIEW(dev))
+		vlv_prepare_pll(intel_crtc);
+
+	/* Set up the display plane register */
+	dspcntr = DISPPLANE_GAMMA_ENABLE;
+
+	if (intel_crtc->config.has_dp_encoder)
+		intel_dp_set_m_n(intel_crtc);
+
+	intel_set_pipe_timings(intel_crtc);
+
+	/* pipesrc and dspsize control the size that is scaled from,
+	 * which should always be the user's requested size.
+	 */
+	I915_WRITE(DSPSIZE(plane),
+		   ((intel_crtc->config.pipe_src_h - 1) << 16) |
+		   (intel_crtc->config.pipe_src_w - 1));
+	I915_WRITE(DSPPOS(plane), 0);
+
+	i9xx_set_pipeconf(intel_crtc);
+
+	I915_WRITE(DSPCNTR(plane), dspcntr);
+	POSTING_READ(DSPCNTR(plane));
+
+	dev_priv->display.update_primary_plane(crtc, crtc->primary->fb,
+					       crtc->x, crtc->y);
+
 	intel_crtc->active = true;
 
+	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
+
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		if (encoder->pre_pll_enable)
 			encoder->pre_pll_enable(encoder);
 
-	is_dsi = intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI);
-
-	if (!is_dsi)
-		vlv_enable_pll(intel_crtc);
+	if (!is_dsi) {
+		if (IS_CHERRYVIEW(dev))
+			chv_enable_pll(intel_crtc);
+		else
+			vlv_enable_pll(intel_crtc);
+	}
 
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		if (encoder->pre_enable)
@@ -4387,15 +4627,25 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 
 	intel_update_watermarks(crtc);
 	intel_enable_pipe(intel_crtc);
-	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
-	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
-	intel_enable_planes(crtc);
-	intel_crtc_update_cursor(crtc, true);
-
-	intel_update_fbc(dev);
 
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		encoder->enable(encoder);
+
+	intel_crtc_enable_planes(crtc);
+
+	drm_crtc_vblank_on(crtc);
+
+	/* Underruns don't raise interrupts, so check manually. */
+	i9xx_check_fifo_underruns(dev);
+}
+
+static void i9xx_set_pll_dividers(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	I915_WRITE(FP0(crtc->pipe), crtc->config.dpll_hw_state.fp0);
+	I915_WRITE(FP1(crtc->pipe), crtc->config.dpll_hw_state.fp1);
 }
 
 static void i9xx_crtc_enable(struct drm_crtc *crtc)
@@ -4406,14 +4656,49 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc)
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
 	int plane = intel_crtc->plane;
+	u32 dspcntr;
 
 	WARN_ON(!crtc->enabled);
 
 	if (intel_crtc->active)
 		return;
 
+	i9xx_set_pll_dividers(intel_crtc);
+
+	/* Set up the display plane register */
+	dspcntr = DISPPLANE_GAMMA_ENABLE;
+
+	if (pipe == 0)
+		dspcntr &= ~DISPPLANE_SEL_PIPE_MASK;
+	else
+		dspcntr |= DISPPLANE_SEL_PIPE_B;
+
+	if (intel_crtc->config.has_dp_encoder)
+		intel_dp_set_m_n(intel_crtc);
+
+	intel_set_pipe_timings(intel_crtc);
+
+	/* pipesrc and dspsize control the size that is scaled from,
+	 * which should always be the user's requested size.
+	 */
+	I915_WRITE(DSPSIZE(plane),
+		   ((intel_crtc->config.pipe_src_h - 1) << 16) |
+		   (intel_crtc->config.pipe_src_w - 1));
+	I915_WRITE(DSPPOS(plane), 0);
+
+	i9xx_set_pipeconf(intel_crtc);
+
+	I915_WRITE(DSPCNTR(plane), dspcntr);
+	POSTING_READ(DSPCNTR(plane));
+
+	dev_priv->display.update_primary_plane(crtc, crtc->primary->fb,
+					       crtc->x, crtc->y);
+
 	intel_crtc->active = true;
 
+	if (!IS_GEN2(dev))
+		intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
+
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		if (encoder->pre_enable)
 			encoder->pre_enable(encoder);
@@ -4426,21 +4711,26 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc)
 
 	intel_update_watermarks(crtc);
 	intel_enable_pipe(intel_crtc);
-	intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
-	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
-	intel_enable_planes(crtc);
-	/* The fixup needs to happen before cursor is enabled */
-	if (IS_G4X(dev))
-		g4x_fixup_plane(dev_priv, pipe);
-	intel_crtc_update_cursor(crtc, true);
-
-	/* Give the overlay scaler a chance to enable if it's on this pipe */
-	intel_crtc_dpms_overlay(intel_crtc, true);
-
-	intel_update_fbc(dev);
 
 	for_each_encoder_on_crtc(dev, crtc, encoder)
 		encoder->enable(encoder);
+
+	intel_crtc_enable_planes(crtc);
+
+	/*
+	 * Gen2 reports pipe underruns whenever all planes are disabled.
+	 * So don't enable underrun reporting before at least some planes
+	 * are enabled.
+	 * FIXME: Need to fix the logic to work when we turn off all planes
+	 * but leave the pipe running.
+	 */
+	if (IS_GEN2(dev))
+		intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
+
+	drm_crtc_vblank_on(crtc);
+
+	/* Underruns don't raise interrupts, so check manually. */
+	i9xx_check_fifo_underruns(dev);
 }
 
 static void i9xx_pfit_disable(struct intel_crtc *crtc)
@@ -4465,27 +4755,31 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *encoder;
 	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
 
 	if (!intel_crtc->active)
 		return;
 
-	for_each_encoder_on_crtc(dev, crtc, encoder)
-		encoder->disable(encoder);
+	/*
+	 * Gen2 reports pipe underruns whenever all planes are disabled.
+	 * So diasble underrun reporting before all the planes get disabled.
+	 * FIXME: Need to fix the logic to work when we turn off all planes
+	 * but leave the pipe running.
+	 */
+	if (IS_GEN2(dev))
+		intel_set_cpu_fifo_underrun_reporting(dev, pipe, false);
 
-	/* Give the overlay scaler a chance to disable if it's on this pipe */
-	intel_crtc_wait_for_pending_flips(crtc);
-	drm_vblank_off(dev, pipe);
+	intel_crtc_disable_planes(crtc);
 
-	if (dev_priv->fbc.plane == plane)
-		intel_disable_fbc(dev);
+	for_each_encoder_on_crtc(dev, crtc, encoder)
+		encoder->disable(encoder);
 
-	intel_crtc_dpms_overlay(intel_crtc, false);
-	intel_crtc_update_cursor(crtc, false);
-	intel_disable_planes(crtc);
-	intel_disable_primary_hw_plane(dev_priv, plane, pipe);
+	/*
+	 * On gen2 planes are double buffered but the pipe isn't, so we must
+	 * wait for planes to fully turn off before disabling the pipe.
+	 */
+	if (IS_GEN2(dev))
+		intel_wait_for_vblank(dev, pipe);
 
-	intel_set_cpu_fifo_underrun_reporting(dev, pipe, false);
 	intel_disable_pipe(dev_priv, pipe);
 
 	i9xx_pfit_disable(intel_crtc);
@@ -4494,15 +4788,25 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 		if (encoder->post_disable)
 			encoder->post_disable(encoder);
 
-	if (IS_VALLEYVIEW(dev) && !intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI))
-		vlv_disable_pll(dev_priv, pipe);
-	else if (!IS_VALLEYVIEW(dev))
-		i9xx_disable_pll(dev_priv, pipe);
+	if (!intel_pipe_has_type(crtc, INTEL_OUTPUT_DSI)) {
+		if (IS_CHERRYVIEW(dev))
+			chv_disable_pll(dev_priv, pipe);
+		else if (IS_VALLEYVIEW(dev))
+			vlv_disable_pll(dev_priv, pipe);
+		else
+			i9xx_disable_pll(dev_priv, pipe);
+	}
+
+	if (!IS_GEN2(dev))
+		intel_set_cpu_fifo_underrun_reporting(dev, pipe, false);
 
 	intel_crtc->active = false;
 	intel_update_watermarks(crtc);
 
+	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
+	intel_edp_psr_update(dev);
+	mutex_unlock(&dev->struct_mutex);
 }
 
 static void i9xx_crtc_off(struct drm_crtc *crtc)
@@ -4565,13 +4869,11 @@ static void intel_crtc_disable(struct drm_crtc *crtc)
 	struct drm_device *dev = crtc->dev;
 	struct drm_connector *connector;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
 	/* crtc should still be enabled when we disable it. */
 	WARN_ON(!crtc->enabled);
 
 	dev_priv->display.crtc_disable(crtc);
-	intel_crtc->eld_vld = false;
 	intel_crtc_update_sarea(crtc, false);
 	dev_priv->display.off(crtc);
 
@@ -4635,7 +4937,7 @@ static void intel_connector_check_state(struct intel_connector *connector)
 
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 			      connector->base.base.id,
-			      drm_get_connector_name(&connector->base));
+			      connector->base.name);
 
 		WARN(connector->base.dpms == DRM_MODE_DPMS_OFF,
 		     "wrong connector dpms state\n");
@@ -5039,8 +5341,6 @@ static void i9xx_update_pll_dividers(struct intel_crtc *crtc,
 				     intel_clock_t *reduced_clock)
 {
 	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	int pipe = crtc->pipe;
 	u32 fp, fp2 = 0;
 
 	if (IS_PINEVIEW(dev)) {
@@ -5053,17 +5353,14 @@ static void i9xx_update_pll_dividers(struct intel_crtc *crtc,
 			fp2 = i9xx_dpll_compute_fp(reduced_clock);
 	}
 
-	I915_WRITE(FP0(pipe), fp);
 	crtc->config.dpll_hw_state.fp0 = fp;
 
 	crtc->lowfreq_avail = false;
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_LVDS) &&
 	    reduced_clock && i915.powersave) {
-		I915_WRITE(FP1(pipe), fp2);
 		crtc->config.dpll_hw_state.fp1 = fp2;
 		crtc->lowfreq_avail = true;
 	} else {
-		I915_WRITE(FP1(pipe), fp);
 		crtc->config.dpll_hw_state.fp1 = fp;
 	}
 }
@@ -5141,12 +5438,34 @@ static void intel_dp_set_m_n(struct intel_crtc *crtc)
 
 static void vlv_update_pll(struct intel_crtc *crtc)
 {
+	u32 dpll, dpll_md;
+
+	/*
+	 * Enable DPIO clock input. We should never disable the reference
+	 * clock for pipe B, since VGA hotplug / manual detection depends
+	 * on it.
+	 */
+	dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV |
+		DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV;
+	/* We should never disable this, set it here for state tracking */
+	if (crtc->pipe == PIPE_B)
+		dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
+	dpll |= DPLL_VCO_ENABLE;
+	crtc->config.dpll_hw_state.dpll = dpll;
+
+	dpll_md = (crtc->config.pixel_multiplier - 1)
+		<< DPLL_MD_UDI_MULTIPLIER_SHIFT;
+	crtc->config.dpll_hw_state.dpll_md = dpll_md;
+}
+
+static void vlv_prepare_pll(struct intel_crtc *crtc)
+{
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int pipe = crtc->pipe;
-	u32 dpll, mdiv;
+	u32 mdiv;
 	u32 bestn, bestm1, bestm2, bestp1, bestp2;
-	u32 coreclk, reg_val, dpll_md;
+	u32 coreclk, reg_val;
 
 	mutex_lock(&dev_priv->dpio_lock);
 
@@ -5159,7 +5478,7 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 	/* See eDP HDMI DPIO driver vbios notes doc */
 
 	/* PLL B needs special handling */
-	if (pipe)
+	if (pipe == PIPE_B)
 		vlv_pllb_recal_opamp(dev_priv, pipe);
 
 	/* Set up Tx target for periodic Rcomp update */
@@ -5203,7 +5522,7 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 	if (intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_EDP) ||
 	    intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_DISPLAYPORT)) {
 		/* Use SSC source */
-		if (!pipe)
+		if (pipe == PIPE_A)
 			vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe),
 					 0x0df40000);
 		else
@@ -5211,7 +5530,7 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 					 0x0df70000);
 	} else { /* HDMI or VGA */
 		/* Use bend source */
-		if (!pipe)
+		if (pipe == PIPE_A)
 			vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW5(pipe),
 					 0x0df70000);
 		else
@@ -5227,26 +5546,84 @@ static void vlv_update_pll(struct intel_crtc *crtc)
 	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW7(pipe), coreclk);
 
 	vlv_dpio_write(dev_priv, pipe, VLV_PLL_DW11(pipe), 0x87871000);
+	mutex_unlock(&dev_priv->dpio_lock);
+}
+
+static void chv_update_pll(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe = crtc->pipe;
+	int dpll_reg = DPLL(crtc->pipe);
+	enum dpio_channel port = vlv_pipe_to_channel(pipe);
+	u32 loopfilter, intcoeff;
+	u32 bestn, bestm1, bestm2, bestp1, bestp2, bestm2_frac;
+	int refclk;
+
+	crtc->config.dpll_hw_state.dpll = DPLL_SSC_REF_CLOCK_CHV |
+		DPLL_REFA_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS |
+		DPLL_VCO_ENABLE;
+	if (pipe != PIPE_A)
+		crtc->config.dpll_hw_state.dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
+
+	crtc->config.dpll_hw_state.dpll_md =
+		(crtc->config.pixel_multiplier - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT;
+
+	bestn = crtc->config.dpll.n;
+	bestm2_frac = crtc->config.dpll.m2 & 0x3fffff;
+	bestm1 = crtc->config.dpll.m1;
+	bestm2 = crtc->config.dpll.m2 >> 22;
+	bestp1 = crtc->config.dpll.p1;
+	bestp2 = crtc->config.dpll.p2;
 
 	/*
-	 * Enable DPIO clock input. We should never disable the reference
-	 * clock for pipe B, since VGA hotplug / manual detection depends
-	 * on it.
+	 * Enable Refclk and SSC
 	 */
-	dpll = DPLL_EXT_BUFFER_ENABLE_VLV | DPLL_REFA_CLK_ENABLE_VLV |
-		DPLL_VGA_MODE_DIS | DPLL_INTEGRATED_CLOCK_VLV;
-	/* We should never disable this, set it here for state tracking */
-	if (pipe == PIPE_B)
-		dpll |= DPLL_INTEGRATED_CRI_CLK_VLV;
-	dpll |= DPLL_VCO_ENABLE;
-	crtc->config.dpll_hw_state.dpll = dpll;
+	I915_WRITE(dpll_reg,
+		   crtc->config.dpll_hw_state.dpll & ~DPLL_VCO_ENABLE);
 
-	dpll_md = (crtc->config.pixel_multiplier - 1)
-		<< DPLL_MD_UDI_MULTIPLIER_SHIFT;
-	crtc->config.dpll_hw_state.dpll_md = dpll_md;
+	mutex_lock(&dev_priv->dpio_lock);
 
-	if (crtc->config.has_dp_encoder)
-		intel_dp_set_m_n(crtc);
+	/* p1 and p2 divider */
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW13(port),
+			5 << DPIO_CHV_S1_DIV_SHIFT |
+			bestp1 << DPIO_CHV_P1_DIV_SHIFT |
+			bestp2 << DPIO_CHV_P2_DIV_SHIFT |
+			1 << DPIO_CHV_K_DIV_SHIFT);
+
+	/* Feedback post-divider - m2 */
+	vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW0(port), bestm2);
+
+	/* Feedback refclk divider - n and m1 */
+	vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW1(port),
+			DPIO_CHV_M1_DIV_BY_2 |
+			1 << DPIO_CHV_N_DIV_SHIFT);
+
+	/* M2 fraction division */
+	vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW2(port), bestm2_frac);
+
+	/* M2 fraction division enable */
+	vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW3(port),
+		       DPIO_CHV_FRAC_DIV_EN |
+		       (2 << DPIO_CHV_FEEDFWD_GAIN_SHIFT));
+
+	/* Loop filter */
+	refclk = i9xx_get_refclk(&crtc->base, 0);
+	loopfilter = 5 << DPIO_CHV_PROP_COEFF_SHIFT |
+		2 << DPIO_CHV_GAIN_CTRL_SHIFT;
+	if (refclk == 100000)
+		intcoeff = 11;
+	else if (refclk == 38400)
+		intcoeff = 10;
+	else
+		intcoeff = 9;
+	loopfilter |= intcoeff << DPIO_CHV_INT_COEFF_SHIFT;
+	vlv_dpio_write(dev_priv, pipe, CHV_PLL_DW6(port), loopfilter);
+
+	/* AFC Recal */
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port),
+			vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW14(port)) |
+			DPIO_AFC_RECAL);
 
 	mutex_unlock(&dev_priv->dpio_lock);
 }
@@ -5325,9 +5702,6 @@ static void i9xx_update_pll(struct intel_crtc *crtc,
 			<< DPLL_MD_UDI_MULTIPLIER_SHIFT;
 		crtc->config.dpll_hw_state.dpll_md = dpll_md;
 	}
-
-	if (crtc->config.has_dp_encoder)
-		intel_dp_set_m_n(crtc);
 }
 
 static void i8xx_update_pll(struct intel_crtc *crtc,
@@ -5567,16 +5941,12 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
 	int refclk, num_connectors = 0;
 	intel_clock_t clock, reduced_clock;
-	u32 dspcntr;
 	bool ok, has_reduced_clock = false;
 	bool is_lvds = false, is_dsi = false;
 	struct intel_encoder *encoder;
 	const intel_limit_t *limit;
-	int ret;
 
 	for_each_encoder_on_crtc(dev, crtc, encoder) {
 		switch (encoder->type) {
@@ -5592,7 +5962,7 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc,
 	}
 
 	if (is_dsi)
-		goto skip_dpll;
+		return 0;
 
 	if (!intel_crtc->config.clock_set) {
 		refclk = i9xx_get_refclk(crtc, num_connectors);
@@ -5637,43 +6007,17 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc,
 		i8xx_update_pll(intel_crtc,
 				has_reduced_clock ? &reduced_clock : NULL,
 				num_connectors);
+	} else if (IS_CHERRYVIEW(dev)) {
+		chv_update_pll(intel_crtc);
 	} else if (IS_VALLEYVIEW(dev)) {
 		vlv_update_pll(intel_crtc);
 	} else {
 		i9xx_update_pll(intel_crtc,
 				has_reduced_clock ? &reduced_clock : NULL,
-                                num_connectors);
-	}
-
-skip_dpll:
-	/* Set up the display plane register */
-	dspcntr = DISPPLANE_GAMMA_ENABLE;
-
-	if (!IS_VALLEYVIEW(dev)) {
-		if (pipe == 0)
-			dspcntr &= ~DISPPLANE_SEL_PIPE_MASK;
-		else
-			dspcntr |= DISPPLANE_SEL_PIPE_B;
+				num_connectors);
 	}
 
-	intel_set_pipe_timings(intel_crtc);
-
-	/* pipesrc and dspsize control the size that is scaled from,
-	 * which should always be the user's requested size.
-	 */
-	I915_WRITE(DSPSIZE(plane),
-		   ((intel_crtc->config.pipe_src_h - 1) << 16) |
-		   (intel_crtc->config.pipe_src_w - 1));
-	I915_WRITE(DSPPOS(plane), 0);
-
-	i9xx_set_pipeconf(intel_crtc);
-
-	I915_WRITE(DSPCNTR(plane), dspcntr);
-	POSTING_READ(DSPCNTR(plane));
-
-	ret = intel_pipe_set_base(crtc, x, y, fb);
-
-	return ret;
+	return 0;
 }
 
 static void i9xx_get_pfit_config(struct intel_crtc *crtc,
@@ -5793,6 +6137,36 @@ static void i9xx_get_plane_config(struct intel_crtc *crtc,
 
 }
 
+static void chv_crtc_clock_get(struct intel_crtc *crtc,
+			       struct intel_crtc_config *pipe_config)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int pipe = pipe_config->cpu_transcoder;
+	enum dpio_channel port = vlv_pipe_to_channel(pipe);
+	intel_clock_t clock;
+	u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2;
+	int refclk = 100000;
+
+	mutex_lock(&dev_priv->dpio_lock);
+	cmn_dw13 = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW13(port));
+	pll_dw0 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW0(port));
+	pll_dw1 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW1(port));
+	pll_dw2 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW2(port));
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	clock.m1 = (pll_dw1 & 0x7) == DPIO_CHV_M1_DIV_BY_2 ? 2 : 0;
+	clock.m2 = ((pll_dw0 & 0xff) << 22) | (pll_dw2 & 0x3fffff);
+	clock.n = (pll_dw1 >> DPIO_CHV_N_DIV_SHIFT) & 0xf;
+	clock.p1 = (cmn_dw13 >> DPIO_CHV_P1_DIV_SHIFT) & 0x7;
+	clock.p2 = (cmn_dw13 >> DPIO_CHV_P2_DIV_SHIFT) & 0x1f;
+
+	chv_clock(refclk, &clock);
+
+	/* clock.dot is the fast clock */
+	pipe_config->port_clock = clock.dot / 5;
+}
+
 static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 				 struct intel_crtc_config *pipe_config)
 {
@@ -5827,6 +6201,9 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 		}
 	}
 
+	if (IS_VALLEYVIEW(dev) && (tmp & PIPECONF_COLOR_RANGE_SELECT))
+		pipe_config->limited_color_range = true;
+
 	if (INTEL_INFO(dev)->gen < 4)
 		pipe_config->double_wide = tmp & PIPECONF_DOUBLE_WIDE;
 
@@ -5862,7 +6239,9 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 						     DPLL_PORTB_READY_MASK);
 	}
 
-	if (IS_VALLEYVIEW(dev))
+	if (IS_CHERRYVIEW(dev))
+		chv_crtc_clock_get(crtc, pipe_config);
+	else if (IS_VALLEYVIEW(dev))
 		vlv_crtc_clock_get(crtc, pipe_config);
 	else
 		i9xx_crtc_clock_get(crtc, pipe_config);
@@ -5983,8 +6362,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev)
 			if (intel_panel_use_ssc(dev_priv) && can_ssc) {
 				DRM_DEBUG_KMS("Using SSC on eDP\n");
 				val |= DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD;
-			}
-			else
+			} else
 				val |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD;
 		} else
 			val |= DREF_CPU_SOURCE_OUTPUT_DISABLE;
@@ -6563,10 +6941,7 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 				  struct drm_framebuffer *fb)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
-	int plane = intel_crtc->plane;
 	int num_connectors = 0;
 	intel_clock_t clock, reduced_clock;
 	u32 dpll = 0, fp = 0, fp2 = 0;
@@ -6574,7 +6949,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 	bool is_lvds = false;
 	struct intel_encoder *encoder;
 	struct intel_shared_dpll *pll;
-	int ret;
 
 	for_each_encoder_on_crtc(dev, crtc, encoder) {
 		switch (encoder->type) {
@@ -6624,36 +6998,18 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 		pll = intel_get_shared_dpll(intel_crtc);
 		if (pll == NULL) {
 			DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n",
-					 pipe_name(pipe));
+					 pipe_name(intel_crtc->pipe));
 			return -EINVAL;
 		}
 	} else
 		intel_put_shared_dpll(intel_crtc);
 
-	if (intel_crtc->config.has_dp_encoder)
-		intel_dp_set_m_n(intel_crtc);
-
 	if (is_lvds && has_reduced_clock && i915.powersave)
 		intel_crtc->lowfreq_avail = true;
 	else
 		intel_crtc->lowfreq_avail = false;
 
-	intel_set_pipe_timings(intel_crtc);
-
-	if (intel_crtc->config.has_pch_encoder) {
-		intel_cpu_transcoder_set_m_n(intel_crtc,
-					     &intel_crtc->config.fdi_m_n);
-	}
-
-	ironlake_set_pipeconf(crtc);
-
-	/* Set up the display plane register */
-	I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE);
-	POSTING_READ(DSPCNTR(plane));
-
-	ret = intel_pipe_set_base(crtc, x, y, fb);
-
-	return ret;
+	return 0;
 }
 
 static void intel_pch_transcoder_get_m_n(struct intel_crtc *crtc,
@@ -6831,6 +7187,9 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 		break;
 	}
 
+	if (tmp & PIPECONF_COLOR_RANGE_SELECT)
+		pipe_config->limited_color_range = true;
+
 	if (I915_READ(PCH_TRANSCONF(crtc->pipe)) & TRANS_ENABLE) {
 		struct intel_shared_dpll *pll;
 
@@ -6880,10 +7239,8 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
 	struct drm_device *dev = dev_priv->dev;
 	struct intel_ddi_plls *plls = &dev_priv->ddi_plls;
 	struct intel_crtc *crtc;
-	unsigned long irqflags;
-	uint32_t val;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head)
+	for_each_intel_crtc(dev, crtc)
 		WARN(crtc->active, "CRTC for pipe %c enabled\n",
 		     pipe_name(crtc->pipe));
 
@@ -6902,14 +7259,29 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv)
 	     "Utility pin enabled\n");
 	WARN(I915_READ(PCH_GTC_CTL) & PCH_GTC_ENABLE, "PCH GTC enabled\n");
 
-	spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-	val = I915_READ(DEIMR);
-	WARN((val | DE_PCH_EVENT_IVB) != 0xffffffff,
-	     "Unexpected DEIMR bits enabled: 0x%x\n", val);
-	val = I915_READ(SDEIMR);
-	WARN((val | SDE_HOTPLUG_MASK_CPT) != 0xffffffff,
-	     "Unexpected SDEIMR bits enabled: 0x%x\n", val);
-	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
+	/*
+	 * In theory we can still leave IRQs enabled, as long as only the HPD
+	 * interrupts remain enabled. We used to check for that, but since it's
+	 * gen-specific and since we only disable LCPLL after we fully disable
+	 * the interrupts, the check below should be enough.
+	 */
+	WARN(!dev_priv->pm.irqs_disabled, "IRQs enabled\n");
+}
+
+static void hsw_write_dcomp(struct drm_i915_private *dev_priv, uint32_t val)
+{
+	struct drm_device *dev = dev_priv->dev;
+
+	if (IS_HASWELL(dev)) {
+		mutex_lock(&dev_priv->rps.hw_lock);
+		if (sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_D_COMP,
+					    val))
+			DRM_ERROR("Failed to disable D_COMP\n");
+		mutex_unlock(&dev_priv->rps.hw_lock);
+	} else {
+		I915_WRITE(D_COMP, val);
+	}
+	POSTING_READ(D_COMP);
 }
 
 /*
@@ -6949,11 +7321,7 @@ static void hsw_disable_lcpll(struct drm_i915_private *dev_priv,
 
 	val = I915_READ(D_COMP);
 	val |= D_COMP_COMP_DISABLE;
-	mutex_lock(&dev_priv->rps.hw_lock);
-	if (sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_D_COMP, val))
-		DRM_ERROR("Failed to disable D_COMP\n");
-	mutex_unlock(&dev_priv->rps.hw_lock);
-	POSTING_READ(D_COMP);
+	hsw_write_dcomp(dev_priv, val);
 	ndelay(100);
 
 	if (wait_for((I915_READ(D_COMP) & D_COMP_RCOMP_IN_PROGRESS) == 0, 1))
@@ -7008,11 +7376,7 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv)
 	val = I915_READ(D_COMP);
 	val |= D_COMP_COMP_FORCE;
 	val &= ~D_COMP_COMP_DISABLE;
-	mutex_lock(&dev_priv->rps.hw_lock);
-	if (sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_D_COMP, val))
-		DRM_ERROR("Failed to enable D_COMP\n");
-	mutex_unlock(&dev_priv->rps.hw_lock);
-	POSTING_READ(D_COMP);
+	hsw_write_dcomp(dev_priv, val);
 
 	val = I915_READ(LCPLL_CTL);
 	val &= ~LCPLL_PLL_DISABLE;
@@ -7066,8 +7430,6 @@ void hsw_enable_pc8(struct drm_i915_private *dev_priv)
 	struct drm_device *dev = dev_priv->dev;
 	uint32_t val;
 
-	WARN_ON(!HAS_PC8(dev));
-
 	DRM_DEBUG_KMS("Enabling package C8+\n");
 
 	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
@@ -7077,7 +7439,6 @@ void hsw_enable_pc8(struct drm_i915_private *dev_priv)
 	}
 
 	lpt_disable_clkout_dp(dev);
-	hsw_runtime_pm_disable_interrupts(dev);
 	hsw_disable_lcpll(dev_priv, true, true);
 }
 
@@ -7086,12 +7447,9 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 	struct drm_device *dev = dev_priv->dev;
 	uint32_t val;
 
-	WARN_ON(!HAS_PC8(dev));
-
 	DRM_DEBUG_KMS("Disabling package C8+\n");
 
 	hsw_restore_lcpll(dev_priv);
-	hsw_runtime_pm_restore_interrupts(dev);
 	lpt_init_pch_refclk(dev);
 
 	if (dev_priv->pch_id == INTEL_PCH_LPT_LP_DEVICE_ID_TYPE) {
@@ -7101,10 +7459,11 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 	}
 
 	intel_prepare_ddi(dev);
-	i915_gem_init_swizzling(dev);
-	mutex_lock(&dev_priv->rps.hw_lock);
-	gen6_update_ring_freq(dev);
-	mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
+static void snb_modeset_global_resources(struct drm_device *dev)
+{
+	modeset_update_crtc_power_domains(dev);
 }
 
 static void haswell_modeset_global_resources(struct drm_device *dev)
@@ -7116,39 +7475,15 @@ static int haswell_crtc_mode_set(struct drm_crtc *crtc,
 				 int x, int y,
 				 struct drm_framebuffer *fb)
 {
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int plane = intel_crtc->plane;
-	int ret;
 
 	if (!intel_ddi_pll_select(intel_crtc))
 		return -EINVAL;
 	intel_ddi_pll_enable(intel_crtc);
 
-	if (intel_crtc->config.has_dp_encoder)
-		intel_dp_set_m_n(intel_crtc);
-
 	intel_crtc->lowfreq_avail = false;
 
-	intel_set_pipe_timings(intel_crtc);
-
-	if (intel_crtc->config.has_pch_encoder) {
-		intel_cpu_transcoder_set_m_n(intel_crtc,
-					     &intel_crtc->config.fdi_m_n);
-	}
-
-	haswell_set_pipeconf(crtc);
-
-	intel_set_pipe_csc(crtc);
-
-	/* Set up the display plane register */
-	I915_WRITE(DSPCNTR(plane), DISPPLANE_GAMMA_ENABLE | DISPPLANE_PIPE_CSC_ENABLE);
-	POSTING_READ(DSPCNTR(plane));
-
-	ret = intel_pipe_set_base(crtc, x, y, fb);
-
-	return ret;
+	return 0;
 }
 
 static bool haswell_get_pipe_config(struct intel_crtc *crtc,
@@ -7228,38 +7563,6 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	return true;
 }
 
-static int intel_crtc_mode_set(struct drm_crtc *crtc,
-			       int x, int y,
-			       struct drm_framebuffer *fb)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_encoder *encoder;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_display_mode *mode = &intel_crtc->config.requested_mode;
-	int pipe = intel_crtc->pipe;
-	int ret;
-
-	drm_vblank_pre_modeset(dev, pipe);
-
-	ret = dev_priv->display.crtc_mode_set(crtc, x, y, fb);
-
-	drm_vblank_post_modeset(dev, pipe);
-
-	if (ret != 0)
-		return ret;
-
-	for_each_encoder_on_crtc(dev, crtc, encoder) {
-		DRM_DEBUG_KMS("[ENCODER:%d:%s] set [MODE:%d:%s]\n",
-			encoder->base.base.id,
-			drm_get_encoder_name(&encoder->base),
-			mode->base.id, mode->name);
-		encoder->mode_set(encoder);
-	}
-
-	return 0;
-}
-
 static struct {
 	int clock;
 	u32 config;
@@ -7374,8 +7677,6 @@ static void haswell_write_eld(struct drm_connector *connector,
 {
 	struct drm_i915_private *dev_priv = connector->dev->dev_private;
 	uint8_t *eld = connector->eld;
-	struct drm_device *dev = crtc->dev;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	uint32_t eldv;
 	uint32_t i;
 	int len;
@@ -7387,17 +7688,14 @@ static void haswell_write_eld(struct drm_connector *connector,
 	int aud_config = HSW_AUD_CFG(pipe);
 	int aud_cntrl_st2 = HSW_AUD_PIN_ELD_CP_VLD;
 
-
-	DRM_DEBUG_DRIVER("HDMI: Haswell Audio initialize....\n");
-
 	/* Audio output enable */
 	DRM_DEBUG_DRIVER("HDMI audio: enable codec\n");
 	tmp = I915_READ(aud_cntrl_st2);
 	tmp |= (AUDIO_OUTPUT_ENABLE_A << (pipe * 4));
 	I915_WRITE(aud_cntrl_st2, tmp);
+	POSTING_READ(aud_cntrl_st2);
 
-	/* Wait for 1 vertical blank */
-	intel_wait_for_vblank(dev, pipe);
+	assert_pipe_disabled(dev_priv, to_intel_crtc(crtc)->pipe);
 
 	/* Set ELD valid state */
 	tmp = I915_READ(aud_cntrl_st2);
@@ -7417,7 +7715,6 @@ static void haswell_write_eld(struct drm_connector *connector,
 	DRM_DEBUG_DRIVER("ELD on pipe %c\n", pipe_name(pipe));
 
 	eldv = AUDIO_ELD_VALID_A << (pipe * 4);
-	intel_crtc->eld_vld = true;
 
 	if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) {
 		DRM_DEBUG_DRIVER("ELD: DisplayPort detected\n");
@@ -7564,9 +7861,9 @@ void intel_write_eld(struct drm_encoder *encoder,
 
 	DRM_DEBUG_DRIVER("ELD on [CONNECTOR:%d:%s], [ENCODER:%d:%s]\n",
 			 connector->base.id,
-			 drm_get_connector_name(connector),
+			 connector->name,
 			 connector->encoder->base.id,
-			 drm_get_encoder_name(connector->encoder));
+			 connector->encoder->name);
 
 	connector->eld[6] = drm_av_sync_delay(connector, mode) / 2;
 
@@ -7579,29 +7876,33 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base)
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	bool visible = base != 0;
-	u32 cntl;
-
-	if (intel_crtc->cursor_visible == visible)
-		return;
+	uint32_t cntl;
 
-	cntl = I915_READ(_CURACNTR);
-	if (visible) {
+	if (base != intel_crtc->cursor_base) {
 		/* On these chipsets we can only modify the base whilst
 		 * the cursor is disabled.
 		 */
+		if (intel_crtc->cursor_cntl) {
+			I915_WRITE(_CURACNTR, 0);
+			POSTING_READ(_CURACNTR);
+			intel_crtc->cursor_cntl = 0;
+		}
+
 		I915_WRITE(_CURABASE, base);
+		POSTING_READ(_CURABASE);
+	}
 
-		cntl &= ~(CURSOR_FORMAT_MASK);
-		/* XXX width must be 64, stride 256 => 0x00 << 28 */
-		cntl |= CURSOR_ENABLE |
+	/* XXX width must be 64, stride 256 => 0x00 << 28 */
+	cntl = 0;
+	if (base)
+		cntl = (CURSOR_ENABLE |
 			CURSOR_GAMMA_ENABLE |
-			CURSOR_FORMAT_ARGB;
-	} else
-		cntl &= ~(CURSOR_ENABLE | CURSOR_GAMMA_ENABLE);
-	I915_WRITE(_CURACNTR, cntl);
-
-	intel_crtc->cursor_visible = visible;
+			CURSOR_FORMAT_ARGB);
+	if (intel_crtc->cursor_cntl != cntl) {
+		I915_WRITE(_CURACNTR, cntl);
+		POSTING_READ(_CURACNTR);
+		intel_crtc->cursor_cntl = cntl;
+	}
 }
 
 static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
@@ -7610,16 +7911,12 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	bool visible = base != 0;
-
-	if (intel_crtc->cursor_visible != visible) {
-		int16_t width = intel_crtc->cursor_width;
-		uint32_t cntl = I915_READ(CURCNTR(pipe));
-		if (base) {
-			cntl &= ~(CURSOR_MODE | MCURSOR_PIPE_SELECT);
-			cntl |= MCURSOR_GAMMA_ENABLE;
+	uint32_t cntl;
 
-			switch (width) {
+	cntl = 0;
+	if (base) {
+		cntl = MCURSOR_GAMMA_ENABLE;
+		switch (intel_crtc->cursor_width) {
 			case 64:
 				cntl |= CURSOR_MODE_64_ARGB_AX;
 				break;
@@ -7632,18 +7929,16 @@ static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base)
 			default:
 				WARN_ON(1);
 				return;
-			}
-			cntl |= pipe << 28; /* Connect to correct pipe */
-		} else {
-			cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE);
-			cntl |= CURSOR_MODE_DISABLE;
 		}
+		cntl |= pipe << 28; /* Connect to correct pipe */
+	}
+	if (intel_crtc->cursor_cntl != cntl) {
 		I915_WRITE(CURCNTR(pipe), cntl);
-
-		intel_crtc->cursor_visible = visible;
+		POSTING_READ(CURCNTR(pipe));
+		intel_crtc->cursor_cntl = cntl;
 	}
+
 	/* and commit changes on next vblank */
-	POSTING_READ(CURCNTR(pipe));
 	I915_WRITE(CURBASE(pipe), base);
 	POSTING_READ(CURBASE(pipe));
 }
@@ -7654,15 +7949,12 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	bool visible = base != 0;
-
-	if (intel_crtc->cursor_visible != visible) {
-		int16_t width = intel_crtc->cursor_width;
-		uint32_t cntl = I915_READ(CURCNTR_IVB(pipe));
-		if (base) {
-			cntl &= ~CURSOR_MODE;
-			cntl |= MCURSOR_GAMMA_ENABLE;
-			switch (width) {
+	uint32_t cntl;
+
+	cntl = 0;
+	if (base) {
+		cntl = MCURSOR_GAMMA_ENABLE;
+		switch (intel_crtc->cursor_width) {
 			case 64:
 				cntl |= CURSOR_MODE_64_ARGB_AX;
 				break;
@@ -7675,23 +7967,20 @@ static void ivb_update_cursor(struct drm_crtc *crtc, u32 base)
 			default:
 				WARN_ON(1);
 				return;
-			}
-		} else {
-			cntl &= ~(CURSOR_MODE | MCURSOR_GAMMA_ENABLE);
-			cntl |= CURSOR_MODE_DISABLE;
-		}
-		if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
-			cntl |= CURSOR_PIPE_CSC_ENABLE;
-			cntl &= ~CURSOR_TRICKLE_FEED_DISABLE;
 		}
-		I915_WRITE(CURCNTR_IVB(pipe), cntl);
+	}
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		cntl |= CURSOR_PIPE_CSC_ENABLE;
 
-		intel_crtc->cursor_visible = visible;
+	if (intel_crtc->cursor_cntl != cntl) {
+		I915_WRITE(CURCNTR(pipe), cntl);
+		POSTING_READ(CURCNTR(pipe));
+		intel_crtc->cursor_cntl = cntl;
 	}
+
 	/* and commit changes on next vblank */
-	POSTING_READ(CURCNTR_IVB(pipe));
-	I915_WRITE(CURBASE_IVB(pipe), base);
-	POSTING_READ(CURBASE_IVB(pipe));
+	I915_WRITE(CURBASE(pipe), base);
+	POSTING_READ(CURBASE(pipe));
 }
 
 /* If no-part of the cursor is visible on the framebuffer, then the GPU may hang... */
@@ -7705,7 +7994,6 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc,
 	int x = intel_crtc->cursor_x;
 	int y = intel_crtc->cursor_y;
 	u32 base = 0, pos = 0;
-	bool visible;
 
 	if (on)
 		base = intel_crtc->cursor_addr;
@@ -7734,20 +8022,18 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc,
 	}
 	pos |= y << CURSOR_Y_SHIFT;
 
-	visible = base != 0;
-	if (!visible && !intel_crtc->cursor_visible)
+	if (base == 0 && intel_crtc->cursor_base == 0)
 		return;
 
-	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev)) {
-		I915_WRITE(CURPOS_IVB(pipe), pos);
+	I915_WRITE(CURPOS(pipe), pos);
+
+	if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev) || IS_BROADWELL(dev))
 		ivb_update_cursor(crtc, base);
-	} else {
-		I915_WRITE(CURPOS(pipe), pos);
-		if (IS_845G(dev) || IS_I865G(dev))
-			i845_update_cursor(crtc, base);
-		else
-			i9xx_update_cursor(crtc, base);
-	}
+	else if (IS_845G(dev) || IS_I865G(dev))
+		i845_update_cursor(crtc, base);
+	else
+		i9xx_update_cursor(crtc, base);
+	intel_crtc->cursor_base = base;
 }
 
 static int intel_crtc_cursor_set(struct drm_crtc *crtc,
@@ -8015,7 +8301,8 @@ mode_fits_in_fbdev(struct drm_device *dev,
 
 bool intel_get_load_detect_pipe(struct drm_connector *connector,
 				struct drm_display_mode *mode,
-				struct intel_load_detect_pipe *old)
+				struct intel_load_detect_pipe *old,
+				struct drm_modeset_acquire_ctx *ctx)
 {
 	struct intel_crtc *intel_crtc;
 	struct intel_encoder *intel_encoder =
@@ -8025,11 +8312,19 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector,
 	struct drm_crtc *crtc = NULL;
 	struct drm_device *dev = encoder->dev;
 	struct drm_framebuffer *fb;
-	int i = -1;
+	struct drm_mode_config *config = &dev->mode_config;
+	int ret, i = -1;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s], [ENCODER:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector),
-		      encoder->base.id, drm_get_encoder_name(encoder));
+		      connector->base.id, connector->name,
+		      encoder->base.id, encoder->name);
+
+	drm_modeset_acquire_init(ctx, 0);
+
+retry:
+	ret = drm_modeset_lock(&config->connection_mutex, ctx);
+	if (ret)
+		goto fail_unlock;
 
 	/*
 	 * Algorithm gets a little messy:
@@ -8045,7 +8340,9 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector,
 	if (encoder->crtc) {
 		crtc = encoder->crtc;
 
-		mutex_lock(&crtc->mutex);
+		ret = drm_modeset_lock(&crtc->mutex, ctx);
+		if (ret)
+			goto fail_unlock;
 
 		old->dpms_mode = connector->dpms;
 		old->load_detect_temp = false;
@@ -8058,7 +8355,7 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector,
 	}
 
 	/* Find an unused one (if possible) */
-	list_for_each_entry(possible_crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, possible_crtc) {
 		i++;
 		if (!(encoder->possible_crtcs & (1 << i)))
 			continue;
@@ -8073,10 +8370,12 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector,
 	 */
 	if (!crtc) {
 		DRM_DEBUG_KMS("no pipe available for load-detect\n");
-		return false;
+		goto fail_unlock;
 	}
 
-	mutex_lock(&crtc->mutex);
+	ret = drm_modeset_lock(&crtc->mutex, ctx);
+	if (ret)
+		goto fail_unlock;
 	intel_encoder->new_crtc = to_intel_crtc(crtc);
 	to_intel_connector(connector)->new_encoder = intel_encoder;
 
@@ -8126,12 +8425,21 @@ bool intel_get_load_detect_pipe(struct drm_connector *connector,
 		intel_crtc->new_config = &intel_crtc->config;
 	else
 		intel_crtc->new_config = NULL;
-	mutex_unlock(&crtc->mutex);
+fail_unlock:
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(ctx);
+		goto retry;
+	}
+
+	drm_modeset_drop_locks(ctx);
+	drm_modeset_acquire_fini(ctx);
+
 	return false;
 }
 
 void intel_release_load_detect_pipe(struct drm_connector *connector,
-				    struct intel_load_detect_pipe *old)
+				    struct intel_load_detect_pipe *old,
+				    struct drm_modeset_acquire_ctx *ctx)
 {
 	struct intel_encoder *intel_encoder =
 		intel_attached_encoder(connector);
@@ -8140,8 +8448,8 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s], [ENCODER:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector),
-		      encoder->base.id, drm_get_encoder_name(encoder));
+		      connector->base.id, connector->name,
+		      encoder->base.id, encoder->name);
 
 	if (old->load_detect_temp) {
 		to_intel_connector(connector)->new_encoder = NULL;
@@ -8155,7 +8463,7 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 			drm_framebuffer_unreference(old->release_fb);
 		}
 
-		mutex_unlock(&crtc->mutex);
+		goto unlock;
 		return;
 	}
 
@@ -8163,7 +8471,9 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 	if (old->dpms_mode != DRM_MODE_DPMS_ON)
 		connector->funcs->dpms(connector, old->dpms_mode);
 
-	mutex_unlock(&crtc->mutex);
+unlock:
+	drm_modeset_drop_locks(ctx);
+	drm_modeset_acquire_fini(ctx);
 }
 
 static int i9xx_pll_refclk(struct drm_device *dev,
@@ -8449,7 +8759,7 @@ void intel_mark_idle(struct drm_device *dev)
 	if (!i915.powersave)
 		goto out;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		if (!crtc->primary->fb)
 			continue;
 
@@ -8464,7 +8774,7 @@ out:
 }
 
 void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
-			struct intel_ring_buffer *ring)
+			struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = obj->base.dev;
 	struct drm_crtc *crtc;
@@ -8472,7 +8782,7 @@ void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
 	if (!i915.powersave)
 		return;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		if (!crtc->primary->fb)
 			continue;
 
@@ -8560,7 +8870,7 @@ static void do_intel_finish_page_flip(struct drm_device *dev,
 	if (work->event)
 		drm_send_vblank_event(dev, intel_crtc->pipe, work->event);
 
-	drm_vblank_put(dev, intel_crtc->pipe);
+	drm_crtc_vblank_put(crtc);
 
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
@@ -8587,6 +8897,48 @@ void intel_finish_page_flip_plane(struct drm_device *dev, int plane)
 	do_intel_finish_page_flip(dev, crtc);
 }
 
+/* Is 'a' after or equal to 'b'? */
+static bool g4x_flip_count_after_eq(u32 a, u32 b)
+{
+	return !((a - b) & 0x80000000);
+}
+
+static bool page_flip_finished(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/*
+	 * The relevant registers doen't exist on pre-ctg.
+	 * As the flip done interrupt doesn't trigger for mmio
+	 * flips on gmch platforms, a flip count check isn't
+	 * really needed there. But since ctg has the registers,
+	 * include it in the check anyway.
+	 */
+	if (INTEL_INFO(dev)->gen < 5 && !IS_G4X(dev))
+		return true;
+
+	/*
+	 * A DSPSURFLIVE check isn't enough in case the mmio and CS flips
+	 * used the same base address. In that case the mmio flip might
+	 * have completed, but the CS hasn't even executed the flip yet.
+	 *
+	 * A flip count check isn't enough as the CS might have updated
+	 * the base address just after start of vblank, but before we
+	 * managed to process the interrupt. This means we'd complete the
+	 * CS flip too soon.
+	 *
+	 * Combining both checks should get us a good enough result. It may
+	 * still happen that the CS flip has been executed, but has not
+	 * yet actually completed. But in case the base address is the same
+	 * anyway, we don't really care.
+	 */
+	return (I915_READ(DSPSURFLIVE(crtc->plane)) & ~0xfff) ==
+		crtc->unpin_work->gtt_offset &&
+		g4x_flip_count_after_eq(I915_READ(PIPE_FLIPCOUNT_GM45(crtc->pipe)),
+				    crtc->unpin_work->flip_count);
+}
+
 void intel_prepare_page_flip(struct drm_device *dev, int plane)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -8599,12 +8951,12 @@ void intel_prepare_page_flip(struct drm_device *dev, int plane)
 	 * is also accompanied by a spurious intel_prepare_page_flip().
 	 */
 	spin_lock_irqsave(&dev->event_lock, flags);
-	if (intel_crtc->unpin_work)
+	if (intel_crtc->unpin_work && page_flip_finished(intel_crtc))
 		atomic_inc_not_zero(&intel_crtc->unpin_work->pending);
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
 
-inline static void intel_mark_page_flip_active(struct intel_crtc *intel_crtc)
+static inline void intel_mark_page_flip_active(struct intel_crtc *intel_crtc)
 {
 	/* Ensure that the work item is consistent when activating it ... */
 	smp_wmb();
@@ -8617,21 +8969,16 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
 				 struct drm_i915_gem_object *obj,
+				 struct intel_engine_cs *ring,
 				 uint32_t flags)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	u32 flip_mask;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
 	int ret;
 
-	ret = intel_pin_and_fence_fb_obj(dev, obj, ring);
-	if (ret)
-		goto err;
-
 	ret = intel_ring_begin(ring, 6);
 	if (ret)
-		goto err_unpin;
+		return ret;
 
 	/* Can't queue multiple flips, so wait for the previous
 	 * one to finish before executing the next.
@@ -8645,38 +8992,28 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 	intel_ring_emit(ring, 0); /* aux display base address, unused */
 
 	intel_mark_page_flip_active(intel_crtc);
 	__intel_ring_advance(ring);
 	return 0;
-
-err_unpin:
-	intel_unpin_fb_obj(obj);
-err:
-	return ret;
 }
 
 static int intel_gen3_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
 				 struct drm_i915_gem_object *obj,
+				 struct intel_engine_cs *ring,
 				 uint32_t flags)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	u32 flip_mask;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
 	int ret;
 
-	ret = intel_pin_and_fence_fb_obj(dev, obj, ring);
-	if (ret)
-		goto err;
-
 	ret = intel_ring_begin(ring, 6);
 	if (ret)
-		goto err_unpin;
+		return ret;
 
 	if (intel_crtc->plane)
 		flip_mask = MI_WAIT_FOR_PLANE_B_FLIP;
@@ -8687,38 +9024,29 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 	intel_ring_emit(ring, MI_NOOP);
 
 	intel_mark_page_flip_active(intel_crtc);
 	__intel_ring_advance(ring);
 	return 0;
-
-err_unpin:
-	intel_unpin_fb_obj(obj);
-err:
-	return ret;
 }
 
 static int intel_gen4_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
 				 struct drm_i915_gem_object *obj,
+				 struct intel_engine_cs *ring,
 				 uint32_t flags)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	uint32_t pf, pipesrc;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
 	int ret;
 
-	ret = intel_pin_and_fence_fb_obj(dev, obj, ring);
-	if (ret)
-		goto err;
-
 	ret = intel_ring_begin(ring, 4);
 	if (ret)
-		goto err_unpin;
+		return ret;
 
 	/* i965+ uses the linear or tiled offsets from the
 	 * Display Registers (which do not change across a page-flip)
@@ -8727,8 +9055,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring,
-			(i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset) |
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset |
 			obj->tiling_mode);
 
 	/* XXX Enabling the panel-fitter across page-flip is so far
@@ -8742,37 +9069,28 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 	intel_mark_page_flip_active(intel_crtc);
 	__intel_ring_advance(ring);
 	return 0;
-
-err_unpin:
-	intel_unpin_fb_obj(obj);
-err:
-	return ret;
 }
 
 static int intel_gen6_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
 				 struct drm_i915_gem_object *obj,
+				 struct intel_engine_cs *ring,
 				 uint32_t flags)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
 	uint32_t pf, pipesrc;
 	int ret;
 
-	ret = intel_pin_and_fence_fb_obj(dev, obj, ring);
-	if (ret)
-		goto err;
-
 	ret = intel_ring_begin(ring, 4);
 	if (ret)
-		goto err_unpin;
+		return ret;
 
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 
 	/* Contrary to the suggestions in the documentation,
 	 * "Enable Panel Fitter" does not seem to be required when page
@@ -8787,34 +9105,20 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	intel_mark_page_flip_active(intel_crtc);
 	__intel_ring_advance(ring);
 	return 0;
-
-err_unpin:
-	intel_unpin_fb_obj(obj);
-err:
-	return ret;
 }
 
 static int intel_gen7_queue_flip(struct drm_device *dev,
 				 struct drm_crtc *crtc,
 				 struct drm_framebuffer *fb,
 				 struct drm_i915_gem_object *obj,
+				 struct intel_engine_cs *ring,
 				 uint32_t flags)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_ring_buffer *ring;
 	uint32_t plane_bit = 0;
 	int len, ret;
 
-	ring = obj->ring;
-	if (IS_VALLEYVIEW(dev) || ring == NULL || ring->id != RCS)
-		ring = &dev_priv->ring[BCS];
-
-	ret = intel_pin_and_fence_fb_obj(dev, obj, ring);
-	if (ret)
-		goto err;
-
-	switch(intel_crtc->plane) {
+	switch (intel_crtc->plane) {
 	case PLANE_A:
 		plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_A;
 		break;
@@ -8826,13 +9130,20 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 		break;
 	default:
 		WARN_ONCE(1, "unknown plane in flip command\n");
-		ret = -ENODEV;
-		goto err_unpin;
+		return -ENODEV;
 	}
 
 	len = 4;
-	if (ring->id == RCS)
+	if (ring->id == RCS) {
 		len += 6;
+		/*
+		 * On Gen 8, SRM is now taking an extra dword to accommodate
+		 * 48bits addresses, and we need a NOOP for the batch size to
+		 * stay even.
+		 */
+		if (IS_GEN8(dev))
+			len += 2;
+	}
 
 	/*
 	 * BSpec MI_DISPLAY_FLIP for IVB:
@@ -8846,11 +9157,11 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 	 */
 	ret = intel_ring_cacheline_align(ring);
 	if (ret)
-		goto err_unpin;
+		return ret;
 
 	ret = intel_ring_begin(ring, len);
 	if (ret)
-		goto err_unpin;
+		return ret;
 
 	/* Unmask the flip-done completion message. Note that the bspec says that
 	 * we should do this for both the BCS and RCS, and that we must not unmask
@@ -8867,31 +9178,35 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 		intel_ring_emit(ring, ~(DERRMR_PIPEA_PRI_FLIP_DONE |
 					DERRMR_PIPEB_PRI_FLIP_DONE |
 					DERRMR_PIPEC_PRI_FLIP_DONE));
-		intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1) |
-				MI_SRM_LRM_GLOBAL_GTT);
+		if (IS_GEN8(dev))
+			intel_ring_emit(ring, MI_STORE_REGISTER_MEM_GEN8(1) |
+					      MI_SRM_LRM_GLOBAL_GTT);
+		else
+			intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1) |
+					      MI_SRM_LRM_GLOBAL_GTT);
 		intel_ring_emit(ring, DERRMR);
 		intel_ring_emit(ring, ring->scratch.gtt_offset + 256);
+		if (IS_GEN8(dev)) {
+			intel_ring_emit(ring, 0);
+			intel_ring_emit(ring, MI_NOOP);
+		}
 	}
 
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit);
 	intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode));
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 	intel_ring_emit(ring, (MI_NOOP));
 
 	intel_mark_page_flip_active(intel_crtc);
 	__intel_ring_advance(ring);
 	return 0;
-
-err_unpin:
-	intel_unpin_fb_obj(obj);
-err:
-	return ret;
 }
 
 static int intel_default_queue_flip(struct drm_device *dev,
 				    struct drm_crtc *crtc,
 				    struct drm_framebuffer *fb,
 				    struct drm_i915_gem_object *obj,
+				    struct intel_engine_cs *ring,
 				    uint32_t flags)
 {
 	return -ENODEV;
@@ -8908,6 +9223,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	struct drm_i915_gem_object *obj = to_intel_framebuffer(fb)->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_unpin_work *work;
+	struct intel_engine_cs *ring;
 	unsigned long flags;
 	int ret;
 
@@ -8936,7 +9252,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	work->old_fb_obj = to_intel_framebuffer(old_fb)->obj;
 	INIT_WORK(&work->work, intel_unpin_work_fn);
 
-	ret = drm_vblank_get(dev, intel_crtc->pipe);
+	ret = drm_crtc_vblank_get(crtc);
 	if (ret)
 		goto free_work;
 
@@ -8945,7 +9261,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	if (intel_crtc->unpin_work) {
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 		kfree(work);
-		drm_vblank_put(dev, intel_crtc->pipe);
+		drm_crtc_vblank_put(crtc);
 
 		DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
 		return -EBUSY;
@@ -8973,10 +9289,30 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	atomic_inc(&intel_crtc->unpin_work_count);
 	intel_crtc->reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
 
-	ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, page_flip_flags);
+	if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev))
+		work->flip_count = I915_READ(PIPE_FLIPCOUNT_GM45(intel_crtc->pipe)) + 1;
+
+	if (IS_VALLEYVIEW(dev)) {
+		ring = &dev_priv->ring[BCS];
+	} else if (INTEL_INFO(dev)->gen >= 7) {
+		ring = obj->ring;
+		if (ring == NULL || ring->id != RCS)
+			ring = &dev_priv->ring[BCS];
+	} else {
+		ring = &dev_priv->ring[RCS];
+	}
+
+	ret = intel_pin_and_fence_fb_obj(dev, obj, ring);
 	if (ret)
 		goto cleanup_pending;
 
+	work->gtt_offset =
+		i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset;
+
+	ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring, page_flip_flags);
+	if (ret)
+		goto cleanup_unpin;
+
 	intel_disable_fbc(dev);
 	intel_mark_fb_busy(obj, NULL);
 	mutex_unlock(&dev->struct_mutex);
@@ -8985,6 +9321,8 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 
 	return 0;
 
+cleanup_unpin:
+	intel_unpin_fb_obj(obj);
 cleanup_pending:
 	atomic_dec(&intel_crtc->unpin_work_count);
 	crtc->primary->fb = old_fb;
@@ -8997,7 +9335,7 @@ cleanup:
 	intel_crtc->unpin_work = NULL;
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 
-	drm_vblank_put(dev, intel_crtc->pipe);
+	drm_crtc_vblank_put(crtc);
 free_work:
 	kfree(work);
 
@@ -9040,8 +9378,7 @@ static void intel_modeset_update_staged_output_state(struct drm_device *dev)
 			to_intel_crtc(encoder->base.crtc);
 	}
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		crtc->new_enabled = crtc->base.enabled;
 
 		if (crtc->new_enabled)
@@ -9072,21 +9409,20 @@ static void intel_modeset_commit_output_state(struct drm_device *dev)
 		encoder->base.crtc = &encoder->new_crtc->base;
 	}
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		crtc->base.enabled = crtc->new_enabled;
 	}
 }
 
 static void
-connected_sink_compute_bpp(struct intel_connector * connector,
+connected_sink_compute_bpp(struct intel_connector *connector,
 			   struct intel_crtc_config *pipe_config)
 {
 	int bpp = pipe_config->pipe_bpp;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] checking for sink bpp constrains\n",
 		connector->base.base.id,
-		drm_get_connector_name(&connector->base));
+		connector->base.name);
 
 	/* Don't use an invalid EDID bpc value */
 	if (connector->base.display_info.bpc &&
@@ -9427,8 +9763,7 @@ intel_modeset_affected_pipes(struct drm_crtc *crtc, unsigned *modeset_pipes,
 	}
 
 	/* Check for pipes that will be enabled/disabled ... */
-	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, intel_crtc) {
 		if (intel_crtc->base.enabled == intel_crtc->new_enabled)
 			continue;
 
@@ -9501,8 +9836,7 @@ intel_modeset_update_state(struct drm_device *dev, unsigned prepare_pipes)
 	intel_modeset_commit_output_state(dev);
 
 	/* Double check state. */
-	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, intel_crtc) {
 		WARN_ON(intel_crtc->base.enabled != intel_crtc_in_use(&intel_crtc->base));
 		WARN_ON(intel_crtc->new_config &&
 			intel_crtc->new_config != &intel_crtc->config);
@@ -9631,6 +9965,12 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_I(adjusted_mode.crtc_vsync_end);
 
 	PIPE_CONF_CHECK_I(pixel_multiplier);
+	PIPE_CONF_CHECK_I(has_hdmi_sink);
+	if ((INTEL_INFO(dev)->gen < 8 && !IS_HASWELL(dev)) ||
+	    IS_VALLEYVIEW(dev))
+		PIPE_CONF_CHECK_I(limited_color_range);
+
+	PIPE_CONF_CHECK_I(has_audio);
 
 	PIPE_CONF_CHECK_FLAGS(adjusted_mode.flags,
 			      DRM_MODE_FLAG_INTERLACE);
@@ -9728,7 +10068,7 @@ check_encoder_state(struct drm_device *dev)
 
 		DRM_DEBUG_KMS("[ENCODER:%d:%s]\n",
 			      encoder->base.base.id,
-			      drm_get_encoder_name(&encoder->base));
+			      encoder->base.name);
 
 		WARN(&encoder->new_crtc->base != encoder->base.crtc,
 		     "encoder's stage crtc doesn't match current crtc\n");
@@ -9780,8 +10120,7 @@ check_crtc_state(struct drm_device *dev)
 	struct intel_encoder *encoder;
 	struct intel_crtc_config pipe_config;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		bool enabled = false;
 		bool active = false;
 
@@ -9870,8 +10209,7 @@ check_shared_dpll_state(struct drm_device *dev)
 		     "pll on state mismatch (expected %i, found %i)\n",
 		     pll->on, active);
 
-		list_for_each_entry(crtc, &dev->mode_config.crtc_list,
-				    base.head) {
+		for_each_intel_crtc(dev, crtc) {
 			if (crtc->base.enabled && intel_crtc_to_shared_dpll(crtc) == pll)
 				enabled_crtcs++;
 			if (crtc->active && intel_crtc_to_shared_dpll(crtc) == pll)
@@ -9911,6 +10249,44 @@ void ironlake_check_encoder_dotclock(const struct intel_crtc_config *pipe_config
 	     pipe_config->adjusted_mode.crtc_clock, dotclock);
 }
 
+static void update_scanline_offset(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+
+	/*
+	 * The scanline counter increments at the leading edge of hsync.
+	 *
+	 * On most platforms it starts counting from vtotal-1 on the
+	 * first active line. That means the scanline counter value is
+	 * always one less than what we would expect. Ie. just after
+	 * start of vblank, which also occurs at start of hsync (on the
+	 * last active line), the scanline counter will read vblank_start-1.
+	 *
+	 * On gen2 the scanline counter starts counting from 1 instead
+	 * of vtotal-1, so we have to subtract one (or rather add vtotal-1
+	 * to keep the value positive), instead of adding one.
+	 *
+	 * On HSW+ the behaviour of the scanline counter depends on the output
+	 * type. For DP ports it behaves like most other platforms, but on HDMI
+	 * there's an extra 1 line difference. So we need to add two instead of
+	 * one to the value.
+	 */
+	if (IS_GEN2(dev)) {
+		const struct drm_display_mode *mode = &crtc->config.adjusted_mode;
+		int vtotal;
+
+		vtotal = mode->crtc_vtotal;
+		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+			vtotal /= 2;
+
+		crtc->scanline_offset = vtotal - 1;
+	} else if (HAS_DDI(dev) &&
+		   intel_pipe_has_type(&crtc->base, INTEL_OUTPUT_HDMI)) {
+		crtc->scanline_offset = 2;
+	} else
+		crtc->scanline_offset = 1;
+}
+
 static int __intel_set_mode(struct drm_crtc *crtc,
 			    struct drm_display_mode *mode,
 			    int x, int y, struct drm_framebuffer *fb)
@@ -10002,15 +10378,38 @@ static int __intel_set_mode(struct drm_crtc *crtc,
 	 * on the DPLL.
 	 */
 	for_each_intel_crtc_masked(dev, modeset_pipes, intel_crtc) {
-		ret = intel_crtc_mode_set(&intel_crtc->base,
-					  x, y, fb);
+		struct drm_framebuffer *old_fb;
+
+		mutex_lock(&dev->struct_mutex);
+		ret = intel_pin_and_fence_fb_obj(dev,
+						 to_intel_framebuffer(fb)->obj,
+						 NULL);
+		if (ret != 0) {
+			DRM_ERROR("pin & fence failed\n");
+			mutex_unlock(&dev->struct_mutex);
+			goto done;
+		}
+		old_fb = crtc->primary->fb;
+		if (old_fb)
+			intel_unpin_fb_obj(to_intel_framebuffer(old_fb)->obj);
+		mutex_unlock(&dev->struct_mutex);
+
+		crtc->primary->fb = fb;
+		crtc->x = x;
+		crtc->y = y;
+
+		ret = dev_priv->display.crtc_mode_set(&intel_crtc->base,
+						      x, y, fb);
 		if (ret)
 			goto done;
 	}
 
 	/* Now enable the clocks, plane, pipe, and connectors that we set up. */
-	for_each_intel_crtc_masked(dev, prepare_pipes, intel_crtc)
+	for_each_intel_crtc_masked(dev, prepare_pipes, intel_crtc) {
+		update_scanline_offset(intel_crtc);
+
 		dev_priv->display.crtc_enable(&intel_crtc->base);
+	}
 
 	/* FIXME: add subpixel order */
 done:
@@ -10086,7 +10485,7 @@ static int intel_set_config_save_state(struct drm_device *dev,
 	 * restored, not the drivers personal bookkeeping.
 	 */
 	count = 0;
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		config->save_crtc_enabled[count++] = crtc->enabled;
 	}
 
@@ -10112,7 +10511,7 @@ static void intel_set_config_restore_state(struct drm_device *dev,
 	int count;
 
 	count = 0;
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		crtc->new_enabled = config->save_crtc_enabled[count++];
 
 		if (crtc->new_enabled)
@@ -10236,7 +10635,7 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 
 			DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [NOCRTC]\n",
 				connector->base.base.id,
-				drm_get_connector_name(&connector->base));
+				connector->base.name);
 		}
 
 
@@ -10271,7 +10670,7 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] to [CRTC:%d]\n",
 			connector->base.base.id,
-			drm_get_connector_name(&connector->base),
+			connector->base.name,
 			new_crtc->base.id);
 	}
 
@@ -10302,8 +10701,7 @@ intel_modeset_stage_output_state(struct drm_device *dev,
 	}
 	/* Now we've also updated encoder->new_crtc for all encoders. */
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		crtc->new_enabled = false;
 
 		list_for_each_entry(encoder,
@@ -10516,7 +10914,7 @@ static void ibx_pch_dpll_disable(struct drm_i915_private *dev_priv,
 	struct intel_crtc *crtc;
 
 	/* Make sure no transcoder isn't still depending on us. */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		if (intel_crtc_to_shared_dpll(crtc) == pll)
 			assert_pch_transcoder_disabled(dev_priv, crtc->pipe);
 	}
@@ -10573,16 +10971,6 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 
 	drm_crtc_init(dev, &intel_crtc->base, &intel_crtc_funcs);
 
-	if (IS_GEN2(dev)) {
-		intel_crtc->max_cursor_width = GEN2_CURSOR_WIDTH;
-		intel_crtc->max_cursor_height = GEN2_CURSOR_HEIGHT;
-	} else {
-		intel_crtc->max_cursor_width = CURSOR_WIDTH;
-		intel_crtc->max_cursor_height = CURSOR_HEIGHT;
-	}
-	dev->mode_config.cursor_width = intel_crtc->max_cursor_width;
-	dev->mode_config.cursor_height = intel_crtc->max_cursor_height;
-
 	drm_mode_crtc_set_gamma_size(&intel_crtc->base, 256);
 	for (i = 0; i < 256; i++) {
 		intel_crtc->lut_r[i] = i;
@@ -10601,19 +10989,27 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 		intel_crtc->plane = !pipe;
 	}
 
+	intel_crtc->cursor_base = ~0;
+	intel_crtc->cursor_cntl = ~0;
+
+	init_waitqueue_head(&intel_crtc->vbl_wait);
+
 	BUG_ON(pipe >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) ||
 	       dev_priv->plane_to_crtc_mapping[intel_crtc->plane] != NULL);
 	dev_priv->plane_to_crtc_mapping[intel_crtc->plane] = &intel_crtc->base;
 	dev_priv->pipe_to_crtc_mapping[intel_crtc->pipe] = &intel_crtc->base;
 
 	drm_crtc_helper_add(&intel_crtc->base, &intel_helper_funcs);
+
+	WARN_ON(drm_crtc_index(&intel_crtc->base) != intel_crtc->pipe);
 }
 
 enum pipe intel_get_pipe_from_connector(struct intel_connector *connector)
 {
 	struct drm_encoder *encoder = connector->base.encoder;
+	struct drm_device *dev = connector->base.dev;
 
-	WARN_ON(!mutex_is_locked(&connector->base.dev->mode_config.mutex));
+	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
 
 	if (!encoder)
 		return INVALID_PIPE;
@@ -10701,6 +11097,22 @@ const char *intel_output_name(int output)
 	return names[output];
 }
 
+static bool intel_crt_present(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (IS_ULT(dev))
+		return false;
+
+	if (IS_CHERRYVIEW(dev))
+		return false;
+
+	if (IS_VALLEYVIEW(dev) && !dev_priv->vbt.int_crt_support)
+		return false;
+
+	return true;
+}
+
 static void intel_setup_outputs(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -10709,7 +11121,7 @@ static void intel_setup_outputs(struct drm_device *dev)
 
 	intel_lvds_init(dev);
 
-	if (!IS_ULT(dev))
+	if (intel_crt_present(dev))
 		intel_crt_init(dev);
 
 	if (HAS_DDI(dev)) {
@@ -10773,6 +11185,15 @@ static void intel_setup_outputs(struct drm_device *dev)
 				intel_dp_init(dev, VLV_DISPLAY_BASE + DP_C, PORT_C);
 		}
 
+		if (IS_CHERRYVIEW(dev)) {
+			if (I915_READ(VLV_DISPLAY_BASE + CHV_HDMID) & SDVO_DETECTED) {
+				intel_hdmi_init(dev, VLV_DISPLAY_BASE + CHV_HDMID,
+						PORT_D);
+				if (I915_READ(VLV_DISPLAY_BASE + DP_D) & DP_DETECTED)
+					intel_dp_init(dev, VLV_DISPLAY_BASE + DP_D, PORT_D);
+			}
+		}
+
 		intel_dsi_init(dev);
 	} else if (SUPPORTS_DIGITAL_OUTPUTS(dev)) {
 		bool found = false;
@@ -11002,6 +11423,8 @@ static void intel_init_display(struct drm_device *dev)
 
 	if (HAS_PCH_SPLIT(dev) || IS_G4X(dev))
 		dev_priv->display.find_dpll = g4x_find_best_dpll;
+	else if (IS_CHERRYVIEW(dev))
+		dev_priv->display.find_dpll = chv_find_best_dpll;
 	else if (IS_VALLEYVIEW(dev))
 		dev_priv->display.find_dpll = vlv_find_best_dpll;
 	else if (IS_PINEVIEW(dev))
@@ -11083,6 +11506,8 @@ static void intel_init_display(struct drm_device *dev)
 		} else if (IS_GEN6(dev)) {
 			dev_priv->display.fdi_link_train = gen6_fdi_link_train;
 			dev_priv->display.write_eld = ironlake_write_eld;
+			dev_priv->display.modeset_global_resources =
+				snb_modeset_global_resources;
 		} else if (IS_IVYBRIDGE(dev)) {
 			/* FIXME: detect B0+ stepping and use auto training */
 			dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train;
@@ -11166,6 +11591,14 @@ static void quirk_invert_brightness(struct drm_device *dev)
 	DRM_INFO("applying inverted panel brightness quirk\n");
 }
 
+/* Some VBT's incorrectly indicate no backlight is present */
+static void quirk_backlight_present(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	dev_priv->quirks |= QUIRK_BACKLIGHT_PRESENT;
+	DRM_INFO("applying backlight present quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -11211,9 +11644,6 @@ static struct intel_quirk intel_quirks[] = {
 	/* ThinkPad T60 needs pipe A force quirk (bug #16494) */
 	{ 0x2782, 0x17aa, 0x201a, quirk_pipea_force },
 
-	/* 830 needs to leave pipe A & dpll A up */
-	{ 0x3577, PCI_ANY_ID, PCI_ANY_ID, quirk_pipea_force },
-
 	/* Lenovo U160 cannot use SSC on LVDS */
 	{ 0x0046, 0x17aa, 0x3920, quirk_ssc_force_disable },
 
@@ -11237,6 +11667,15 @@ static struct intel_quirk intel_quirks[] = {
 
 	/* Acer Aspire 5336 */
 	{ 0x2a42, 0x1025, 0x048a, quirk_invert_brightness },
+
+	/* Acer C720 and C720P Chromebooks (Celeron 2955U) have backlights */
+	{ 0x0a06, 0x1025, 0x0a11, quirk_backlight_present },
+
+	/* Toshiba CB35 Chromebook (Celeron 2955U) */
+	{ 0x0a06, 0x1179, 0x0a88, quirk_backlight_present },
+
+	/* HP Chromebook 14 (Celeron 2955U) */
+	{ 0x0a06, 0x103c, 0x21ed, quirk_backlight_present },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
@@ -11287,9 +11726,7 @@ void intel_modeset_init_hw(struct drm_device *dev)
 
 	intel_reset_dpio(dev);
 
-	mutex_lock(&dev->struct_mutex);
 	intel_enable_gt_powersave(dev);
-	mutex_unlock(&dev->struct_mutex);
 }
 
 void intel_modeset_suspend_hw(struct drm_device *dev)
@@ -11333,6 +11770,15 @@ void intel_modeset_init(struct drm_device *dev)
 		dev->mode_config.max_width = 8192;
 		dev->mode_config.max_height = 8192;
 	}
+
+	if (IS_GEN2(dev)) {
+		dev->mode_config.cursor_width = GEN2_CURSOR_WIDTH;
+		dev->mode_config.cursor_height = GEN2_CURSOR_HEIGHT;
+	} else {
+		dev->mode_config.cursor_width = MAX_CURSOR_WIDTH;
+		dev->mode_config.cursor_height = MAX_CURSOR_HEIGHT;
+	}
+
 	dev->mode_config.fb_base = dev_priv->gtt.mappable_base;
 
 	DRM_DEBUG_KMS("%d display pipe%s available.\n",
@@ -11362,12 +11808,11 @@ void intel_modeset_init(struct drm_device *dev)
 	/* Just in case the BIOS is doing something questionable. */
 	intel_disable_fbc(dev);
 
-	mutex_lock(&dev->mode_config.mutex);
+	drm_modeset_lock_all(dev);
 	intel_modeset_setup_hw_state(dev, false);
-	mutex_unlock(&dev->mode_config.mutex);
+	drm_modeset_unlock_all(dev);
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		if (!crtc->active)
 			continue;
 
@@ -11395,6 +11840,7 @@ static void intel_enable_pipe_a(struct drm_device *dev)
 	struct intel_connector *connector;
 	struct drm_connector *crt = NULL;
 	struct intel_load_detect_pipe load_detect_temp;
+	struct drm_modeset_acquire_ctx ctx;
 
 	/* We can't just switch on the pipe A, we need to set things up with a
 	 * proper mode and output configuration. As a gross hack, enable pipe A
@@ -11411,8 +11857,8 @@ static void intel_enable_pipe_a(struct drm_device *dev)
 	if (!crt)
 		return;
 
-	if (intel_get_load_detect_pipe(crt, NULL, &load_detect_temp))
-		intel_release_load_detect_pipe(crt, &load_detect_temp);
+	if (intel_get_load_detect_pipe(crt, NULL, &load_detect_temp, &ctx))
+		intel_release_load_detect_pipe(crt, &load_detect_temp, &ctx);
 
 
 }
@@ -11447,6 +11893,12 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 	reg = PIPECONF(crtc->config.cpu_transcoder);
 	I915_WRITE(reg, I915_READ(reg) & ~PIPECONF_FRAME_START_DELAY_MASK);
 
+	/* restore vblank interrupts to correct state */
+	if (crtc->active)
+		drm_vblank_on(dev, crtc->pipe);
+	else
+		drm_vblank_off(dev, crtc->pipe);
+
 	/* We need to sanitize the plane -> pipe mapping first because this will
 	 * disable the crtc (and hence change the state) if it is wrong. Note
 	 * that gen4+ has a fixed plane -> pipe mapping.  */
@@ -11462,6 +11914,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 		 * ...  */
 		plane = crtc->plane;
 		crtc->plane = !plane;
+		crtc->primary_enabled = true;
 		dev_priv->display.crtc_disable(&crtc->base);
 		crtc->plane = plane;
 
@@ -11525,16 +11978,25 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 			encoder->base.crtc = NULL;
 		}
 	}
-	if (crtc->active) {
+
+	if (crtc->active || IS_VALLEYVIEW(dev) || INTEL_INFO(dev)->gen < 5) {
 		/*
 		 * We start out with underrun reporting disabled to avoid races.
 		 * For correct bookkeeping mark this on active crtcs.
 		 *
+		 * Also on gmch platforms we dont have any hardware bits to
+		 * disable the underrun reporting. Which means we need to start
+		 * out with underrun reporting disabled also on inactive pipes,
+		 * since otherwise we'll complain about the garbage we read when
+		 * e.g. coming up after runtime pm.
+		 *
 		 * No protection against concurrent access is required - at
 		 * worst a fifo underrun happens which also sets this to false.
 		 */
 		crtc->cpu_fifo_underrun_disabled = true;
 		crtc->pch_fifo_underrun_disabled = true;
+
+		update_scanline_offset(crtc);
 	}
 }
 
@@ -11552,7 +12014,7 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 	if (encoder->connectors_active && !has_active_crtc) {
 		DRM_DEBUG_KMS("[ENCODER:%d:%s] has active connectors but no active pipe!\n",
 			      encoder->base.base.id,
-			      drm_get_encoder_name(&encoder->base));
+			      encoder->base.name);
 
 		/* Connector is active, but has no active pipe. This is
 		 * fallout from our resume register restoring. Disable
@@ -11560,7 +12022,7 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 		if (encoder->base.crtc) {
 			DRM_DEBUG_KMS("[ENCODER:%d:%s] manually disabled\n",
 				      encoder->base.base.id,
-				      drm_get_encoder_name(&encoder->base));
+				      encoder->base.name);
 			encoder->disable(encoder);
 		}
 		encoder->base.crtc = NULL;
@@ -11611,6 +12073,16 @@ void i915_redisable_vga(struct drm_device *dev)
 	i915_redisable_vga_power_on(dev);
 }
 
+static bool primary_get_hw_state(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+
+	if (!crtc->active)
+		return false;
+
+	return I915_READ(DSPCNTR(crtc->plane)) & DISPLAY_PLANE_ENABLE;
+}
+
 static void intel_modeset_readout_hw_state(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -11620,8 +12092,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 	struct intel_connector *connector;
 	int i;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		memset(&crtc->config, 0, sizeof(crtc->config));
 
 		crtc->config.quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE;
@@ -11630,7 +12101,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 								 &crtc->config);
 
 		crtc->base.enabled = crtc->active;
-		crtc->primary_enabled = crtc->active;
+		crtc->primary_enabled = primary_get_hw_state(crtc);
 
 		DRM_DEBUG_KMS("[CRTC:%d] hw state readout: %s\n",
 			      crtc->base.base.id,
@@ -11646,8 +12117,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 
 		pll->on = pll->get_hw_state(dev_priv, pll, &pll->hw_state);
 		pll->active = 0;
-		list_for_each_entry(crtc, &dev->mode_config.crtc_list,
-				    base.head) {
+		for_each_intel_crtc(dev, crtc) {
 			if (crtc->active && intel_crtc_to_shared_dpll(crtc) == pll)
 				pll->active++;
 		}
@@ -11672,7 +12142,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		encoder->connectors_active = false;
 		DRM_DEBUG_KMS("[ENCODER:%d:%s] hw state readout: %s, pipe %c\n",
 			      encoder->base.base.id,
-			      drm_get_encoder_name(&encoder->base),
+			      encoder->base.name,
 			      encoder->base.crtc ? "enabled" : "disabled",
 			      pipe_name(pipe));
 	}
@@ -11689,7 +12159,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		}
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] hw state readout: %s\n",
 			      connector->base.base.id,
-			      drm_get_connector_name(&connector->base),
+			      connector->base.name,
 			      connector->base.encoder ? "enabled" : "disabled");
 	}
 }
@@ -11712,8 +12182,7 @@ void intel_modeset_setup_hw_state(struct drm_device *dev,
 	 * Note that this could go away if we move to using crtc_config
 	 * checking everywhere.
 	 */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list,
-			    base.head) {
+	for_each_intel_crtc(dev, crtc) {
 		if (crtc->active && i915.fastboot) {
 			intel_mode_from_pipe_config(&crtc->base.mode, &crtc->config);
 			DRM_DEBUG_KMS("[CRTC:%d] found active mode: ",
@@ -11789,7 +12258,7 @@ void intel_modeset_gem_init(struct drm_device *dev)
 	 * for this.
 	 */
 	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(c, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, c) {
 		if (!c->primary->fb)
 			continue;
 
@@ -11835,7 +12304,7 @@ void intel_modeset_cleanup(struct drm_device *dev)
 
 	intel_unregister_dsm_handler();
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		/* Skip inactive CRTCs */
 		if (!crtc->primary->fb)
 			continue;
@@ -11933,6 +12402,7 @@ struct intel_display_error_state {
 	struct intel_pipe_error_state {
 		bool power_domain_on;
 		u32 source;
+		u32 stat;
 	} pipe[I915_MAX_PIPES];
 
 	struct intel_plane_error_state {
@@ -11985,20 +12455,14 @@ intel_display_capture_error_state(struct drm_device *dev)
 
 	for_each_pipe(i) {
 		error->pipe[i].power_domain_on =
-			intel_display_power_enabled_sw(dev_priv,
-						       POWER_DOMAIN_PIPE(i));
+			intel_display_power_enabled_unlocked(dev_priv,
+							   POWER_DOMAIN_PIPE(i));
 		if (!error->pipe[i].power_domain_on)
 			continue;
 
-		if (INTEL_INFO(dev)->gen <= 6 || IS_VALLEYVIEW(dev)) {
-			error->cursor[i].control = I915_READ(CURCNTR(i));
-			error->cursor[i].position = I915_READ(CURPOS(i));
-			error->cursor[i].base = I915_READ(CURBASE(i));
-		} else {
-			error->cursor[i].control = I915_READ(CURCNTR_IVB(i));
-			error->cursor[i].position = I915_READ(CURPOS_IVB(i));
-			error->cursor[i].base = I915_READ(CURBASE_IVB(i));
-		}
+		error->cursor[i].control = I915_READ(CURCNTR(i));
+		error->cursor[i].position = I915_READ(CURPOS(i));
+		error->cursor[i].base = I915_READ(CURBASE(i));
 
 		error->plane[i].control = I915_READ(DSPCNTR(i));
 		error->plane[i].stride = I915_READ(DSPSTRIDE(i));
@@ -12014,6 +12478,9 @@ intel_display_capture_error_state(struct drm_device *dev)
 		}
 
 		error->pipe[i].source = I915_READ(PIPESRC(i));
+
+		if (!HAS_PCH_SPLIT(dev))
+			error->pipe[i].stat = I915_READ(PIPESTAT(i));
 	}
 
 	error->num_transcoders = INTEL_INFO(dev)->num_pipes;
@@ -12024,7 +12491,7 @@ intel_display_capture_error_state(struct drm_device *dev)
 		enum transcoder cpu_transcoder = transcoders[i];
 
 		error->transcoder[i].power_domain_on =
-			intel_display_power_enabled_sw(dev_priv,
+			intel_display_power_enabled_unlocked(dev_priv,
 				POWER_DOMAIN_TRANSCODER(cpu_transcoder));
 		if (!error->transcoder[i].power_domain_on)
 			continue;
@@ -12064,6 +12531,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 		err_printf(m, "  Power: %s\n",
 			   error->pipe[i].power_domain_on ? "on" : "off");
 		err_printf(m, "  SRC: %08x\n", error->pipe[i].source);
+		err_printf(m, "  STAT: %08x\n", error->pipe[i].stat);
 
 		err_printf(m, "Plane [%d]:\n", i);
 		err_printf(m, "  CNTR: %08x\n", error->plane[i].control);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2a00cb828d2..8a1a4fbc06a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -28,6 +28,8 @@
 #include <linux/i2c.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
@@ -64,6 +66,24 @@ static const struct dp_link_dpll vlv_dpll[] = {
 		{ .p1 = 2, .p2 = 2, .n = 1, .m1 = 2, .m2 = 27 } }
 };
 
+/*
+ * CHV supports eDP 1.4 that have  more link rates.
+ * Below only provides the fixed rate but exclude variable rate.
+ */
+static const struct dp_link_dpll chv_dpll[] = {
+	/*
+	 * CHV requires to program fractional division for m2.
+	 * m2 is stored in fixed point format using formula below
+	 * (m2_int << 22) | m2_fraction
+	 */
+	{ DP_LINK_BW_1_62,	/* m2_int = 32, m2_fraction = 1677722 */
+		{ .p1 = 4, .p2 = 2, .n = 1, .m1 = 2, .m2 = 0x819999a } },
+	{ DP_LINK_BW_2_7,	/* m2_int = 27, m2_fraction = 0 */
+		{ .p1 = 4, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } },
+	{ DP_LINK_BW_5_4,	/* m2_int = 27, m2_fraction = 0 */
+		{ .p1 = 2, .p2 = 1, .n = 1, .m1 = 2, .m2 = 0x6c00000 } }
+};
+
 /**
  * is_edp - is the given port attached to an eDP panel (either CPU or PCH)
  * @intel_dp: DP struct
@@ -318,6 +338,37 @@ static u32 _pp_stat_reg(struct intel_dp *intel_dp)
 		return VLV_PIPE_PP_STATUS(vlv_power_sequencer_pipe(intel_dp));
 }
 
+/* Reboot notifier handler to shutdown panel power to guarantee T12 timing
+   This function only applicable when panel PM state is not to be tracked */
+static int edp_notify_handler(struct notifier_block *this, unsigned long code,
+			      void *unused)
+{
+	struct intel_dp *intel_dp = container_of(this, typeof(* intel_dp),
+						 edp_notifier);
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 pp_div;
+	u32 pp_ctrl_reg, pp_div_reg;
+	enum pipe pipe = vlv_power_sequencer_pipe(intel_dp);
+
+	if (!is_edp(intel_dp) || code != SYS_RESTART)
+		return 0;
+
+	if (IS_VALLEYVIEW(dev)) {
+		pp_ctrl_reg = VLV_PIPE_PP_CONTROL(pipe);
+		pp_div_reg  = VLV_PIPE_PP_DIVISOR(pipe);
+		pp_div = I915_READ(pp_div_reg);
+		pp_div &= PP_REFERENCE_DIVIDER_MASK;
+
+		/* 0x1F write to PP_DIV_REG sets max cycle delay */
+		I915_WRITE(pp_div_reg, pp_div | 0x1F);
+		I915_WRITE(pp_ctrl_reg, PANEL_UNLOCK_REGS | PANEL_POWER_OFF);
+		msleep(intel_dp->panel_power_cycle_delay);
+	}
+
+	return 0;
+}
+
 static bool edp_have_panel_power(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
@@ -330,8 +381,12 @@ static bool edp_have_panel_vdd(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *intel_encoder = &intel_dig_port->base;
+	enum intel_display_power_domain power_domain;
 
-	return !dev_priv->pm.suspended &&
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	return intel_display_power_enabled(dev_priv, power_domain) &&
 	       (I915_READ(_pp_ctrl_reg(intel_dp)) & EDP_FORCE_VDD) != 0;
 }
 
@@ -697,9 +752,9 @@ intel_dp_aux_init(struct intel_dp *intel_dp, struct intel_connector *connector)
 	DRM_DEBUG_KMS("registering %s bus for %s\n", name,
 		      connector->base.kdev->kobj.name);
 
-	ret = drm_dp_aux_register_i2c_bus(&intel_dp->aux);
+	ret = drm_dp_aux_register(&intel_dp->aux);
 	if (ret < 0) {
-		DRM_ERROR("drm_dp_aux_register_i2c_bus() for %s failed (%d)\n",
+		DRM_ERROR("drm_dp_aux_register() for %s failed (%d)\n",
 			  name, ret);
 		return;
 	}
@@ -709,7 +764,7 @@ intel_dp_aux_init(struct intel_dp *intel_dp, struct intel_connector *connector)
 				intel_dp->aux.ddc.dev.kobj.name);
 	if (ret < 0) {
 		DRM_ERROR("sysfs_create_link() for %s failed (%d)\n", name, ret);
-		drm_dp_aux_unregister_i2c_bus(&intel_dp->aux);
+		drm_dp_aux_unregister(&intel_dp->aux);
 	}
 }
 
@@ -739,6 +794,9 @@ intel_dp_set_clock(struct intel_encoder *encoder,
 	} else if (HAS_PCH_SPLIT(dev)) {
 		divisor = pch_dpll;
 		count = ARRAY_SIZE(pch_dpll);
+	} else if (IS_CHERRYVIEW(dev)) {
+		divisor = chv_dpll;
+		count = ARRAY_SIZE(chv_dpll);
 	} else if (IS_VALLEYVIEW(dev)) {
 		divisor = vlv_dpll;
 		count = ARRAY_SIZE(vlv_dpll);
@@ -755,6 +813,20 @@ intel_dp_set_clock(struct intel_encoder *encoder,
 	}
 }
 
+static void
+intel_dp_set_m2_n2(struct intel_crtc *crtc, struct intel_link_m_n *m_n)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum transcoder transcoder = crtc->config.cpu_transcoder;
+
+	I915_WRITE(PIPE_DATA_M2(transcoder),
+		TU_SIZE(m_n->tu) | m_n->gmch_m);
+	I915_WRITE(PIPE_DATA_N2(transcoder), m_n->gmch_n);
+	I915_WRITE(PIPE_LINK_M2(transcoder), m_n->link_m);
+	I915_WRITE(PIPE_LINK_N2(transcoder), m_n->link_n);
+}
+
 bool
 intel_dp_compute_config(struct intel_encoder *encoder,
 			struct intel_crtc_config *pipe_config)
@@ -780,6 +852,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		pipe_config->has_pch_encoder = true;
 
 	pipe_config->has_dp_encoder = true;
+	pipe_config->has_audio = intel_dp->has_audio;
 
 	if (is_edp(intel_dp) && intel_connector->panel.fixed_mode) {
 		intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
@@ -833,8 +906,8 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock,
 						   bpp);
 
-		for (lane_count = min_lane_count; lane_count <= max_lane_count; lane_count <<= 1) {
-			for (clock = min_clock; clock <= max_clock; clock++) {
+		for (clock = min_clock; clock <= max_clock; clock++) {
+			for (lane_count = min_lane_count; lane_count <= max_lane_count; lane_count <<= 1) {
 				link_clock = drm_dp_bw_code_to_link_rate(bws[clock]);
 				link_avail = intel_dp_max_data_rate(link_clock,
 								    lane_count);
@@ -880,6 +953,14 @@ found:
 			       pipe_config->port_clock,
 			       &pipe_config->dp_m_n);
 
+	if (intel_connector->panel.downclock_mode != NULL &&
+		intel_dp->drrs_state.type == SEAMLESS_DRRS_SUPPORT) {
+			intel_link_compute_m_n(bpp, lane_count,
+				intel_connector->panel.downclock_mode->clock,
+				pipe_config->port_clock,
+				&pipe_config->dp_m2_n2);
+	}
+
 	intel_dp_set_clock(encoder, pipe_config, intel_dp->link_bw);
 
 	return true;
@@ -915,7 +996,7 @@ static void ironlake_set_pll_cpu_edp(struct intel_dp *intel_dp)
 	udelay(500);
 }
 
-static void intel_dp_mode_set(struct intel_encoder *encoder)
+static void intel_dp_prepare(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -950,7 +1031,7 @@ static void intel_dp_mode_set(struct intel_encoder *encoder)
 	intel_dp->DP |= DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
 	intel_dp->DP |= DP_PORT_WIDTH(intel_dp->lane_count);
 
-	if (intel_dp->has_audio) {
+	if (crtc->config.has_audio) {
 		DRM_DEBUG_DRIVER("Enabling DP audio on pipe %c\n",
 				 pipe_name(crtc->pipe));
 		intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE;
@@ -983,14 +1064,15 @@ static void intel_dp_mode_set(struct intel_encoder *encoder)
 		if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
 			intel_dp->DP |= DP_ENHANCED_FRAMING;
 
-		if (crtc->pipe == 1)
-			intel_dp->DP |= DP_PIPEB_SELECT;
+		if (!IS_CHERRYVIEW(dev)) {
+			if (crtc->pipe == 1)
+				intel_dp->DP |= DP_PIPEB_SELECT;
+		} else {
+			intel_dp->DP |= DP_PIPE_SELECT_CHV(crtc->pipe);
+		}
 	} else {
 		intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
 	}
-
-	if (port == PORT_A && !IS_VALLEYVIEW(dev))
-		ironlake_set_pll_cpu_edp(intel_dp);
 }
 
 #define IDLE_ON_MASK		(PP_ON | PP_SEQUENCE_MASK | 0                     | PP_SEQUENCE_STATE_MASK)
@@ -1082,7 +1164,10 @@ static  u32 ironlake_get_pp_control(struct intel_dp *intel_dp)
 static bool _edp_panel_vdd_on(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	u32 pp;
 	u32 pp_stat_reg, pp_ctrl_reg;
 	bool need_to_disable = !intel_dp->want_panel_vdd;
@@ -1095,7 +1180,8 @@ static bool _edp_panel_vdd_on(struct intel_dp *intel_dp)
 	if (edp_have_panel_vdd(intel_dp))
 		return need_to_disable;
 
-	intel_runtime_pm_get(dev_priv);
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_get(dev_priv, power_domain);
 
 	DRM_DEBUG_KMS("Turning eDP VDD on\n");
 
@@ -1139,9 +1225,14 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 	u32 pp;
 	u32 pp_stat_reg, pp_ctrl_reg;
 
-	WARN_ON(!mutex_is_locked(&dev->mode_config.mutex));
+	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
 
 	if (!intel_dp->want_panel_vdd && edp_have_panel_vdd(intel_dp)) {
+		struct intel_digital_port *intel_dig_port =
+						dp_to_dig_port(intel_dp);
+		struct intel_encoder *intel_encoder = &intel_dig_port->base;
+		enum intel_display_power_domain power_domain;
+
 		DRM_DEBUG_KMS("Turning eDP VDD off\n");
 
 		pp = ironlake_get_pp_control(intel_dp);
@@ -1160,7 +1251,8 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 		if ((pp & POWER_TARGET_ON) == 0)
 			intel_dp->last_power_cycle = jiffies;
 
-		intel_runtime_pm_put(dev_priv);
+		power_domain = intel_display_port_power_domain(intel_encoder);
+		intel_display_power_put(dev_priv, power_domain);
 	}
 }
 
@@ -1170,9 +1262,9 @@ static void edp_panel_vdd_work(struct work_struct *__work)
 						 struct intel_dp, panel_vdd_work);
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 
-	mutex_lock(&dev->mode_config.mutex);
+	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 	edp_panel_vdd_off_sync(intel_dp);
-	mutex_unlock(&dev->mode_config.mutex);
+	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 }
 
 static void edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
@@ -1244,8 +1336,11 @@ void intel_edp_panel_on(struct intel_dp *intel_dp)
 
 void intel_edp_panel_off(struct intel_dp *intel_dp)
 {
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	enum intel_display_power_domain power_domain;
 	u32 pp;
 	u32 pp_ctrl_reg;
 
@@ -1275,7 +1370,8 @@ void intel_edp_panel_off(struct intel_dp *intel_dp)
 	wait_panel_off(intel_dp);
 
 	/* We got a reference when we enabled the VDD. */
-	intel_runtime_pm_put(dev_priv);
+	power_domain = intel_display_port_power_domain(intel_encoder);
+	intel_display_power_put(dev_priv, power_domain);
 }
 
 void intel_edp_backlight_on(struct intel_dp *intel_dp)
@@ -1432,6 +1528,8 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 
 	if (port == PORT_A && IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) {
 		*pipe = PORT_TO_PIPE_CPT(tmp);
+	} else if (IS_CHERRYVIEW(dev)) {
+		*pipe = DP_PORT_TO_PIPE_CHV(tmp);
 	} else if (!HAS_PCH_CPT(dev) || port == PORT_A) {
 		*pipe = PORT_TO_PIPE(tmp);
 	} else {
@@ -1479,8 +1577,11 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
 	int dotclock;
 
+	tmp = I915_READ(intel_dp->output_reg);
+	if (tmp & DP_AUDIO_OUTPUT_ENABLE)
+		pipe_config->has_audio = true;
+
 	if ((port == PORT_A) || !HAS_PCH_CPT(dev)) {
-		tmp = I915_READ(intel_dp->output_reg);
 		if (tmp & DP_SYNC_HS_HIGH)
 			flags |= DRM_MODE_FLAG_PHSYNC;
 		else
@@ -1816,17 +1917,59 @@ static void intel_disable_dp(struct intel_encoder *encoder)
 		intel_dp_link_down(intel_dp);
 }
 
-static void intel_post_disable_dp(struct intel_encoder *encoder)
+static void g4x_post_disable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = dp_to_dig_port(intel_dp)->port;
+
+	if (port != PORT_A)
+		return;
+
+	intel_dp_link_down(intel_dp);
+	ironlake_edp_pll_off(intel_dp);
+}
+
+static void vlv_post_disable_dp(struct intel_encoder *encoder)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+
+	intel_dp_link_down(intel_dp);
+}
+
+static void chv_post_disable_dp(struct intel_encoder *encoder)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	enum pipe pipe = intel_crtc->pipe;
+	u32 val;
 
-	if (port == PORT_A || IS_VALLEYVIEW(dev)) {
-		intel_dp_link_down(intel_dp);
-		if (!IS_VALLEYVIEW(dev))
-			ironlake_edp_pll_off(intel_dp);
-	}
+	intel_dp_link_down(intel_dp);
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* Propagate soft reset to data lane reset */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
+	val |= CHV_PCS_REQ_SOFTRESET_EN;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
+	val |= CHV_PCS_REQ_SOFTRESET_EN;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
+	val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
+	val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+
+	mutex_unlock(&dev_priv->dpio_lock);
 }
 
 static void intel_enable_dp(struct intel_encoder *encoder)
@@ -1868,8 +2011,13 @@ static void g4x_pre_enable_dp(struct intel_encoder *encoder)
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
 
-	if (dport->port == PORT_A)
+	intel_dp_prepare(encoder);
+
+	/* Only ilk+ has port A */
+	if (dport->port == PORT_A) {
+		ironlake_set_pll_cpu_edp(intel_dp);
 		ironlake_edp_pll_on(intel_dp);
+	}
 }
 
 static void vlv_pre_enable_dp(struct intel_encoder *encoder)
@@ -1921,6 +2069,8 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder)
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
 
+	intel_dp_prepare(encoder);
+
 	/* Program Tx lane resets to default */
 	mutex_lock(&dev_priv->dpio_lock);
 	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW0(port),
@@ -1939,6 +2089,69 @@ static void vlv_dp_pre_pll_enable(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
+static void chv_pre_enable_dp(struct intel_encoder *encoder)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct edp_power_seq power_seq;
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	int pipe = intel_crtc->pipe;
+	int data, i;
+	u32 val;
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* Deassert soft data lane reset*/
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
+	val |= CHV_PCS_REQ_SOFTRESET_EN;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
+	val |= CHV_PCS_REQ_SOFTRESET_EN;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
+	val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
+	val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+
+	/* Program Tx lane latency optimal setting*/
+	for (i = 0; i < 4; i++) {
+		/* Set the latency optimal bit */
+		data = (i == 1) ? 0x0 : 0x6;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW11(ch, i),
+				data << DPIO_FRC_LATENCY_SHFIT);
+
+		/* Set the upar bit */
+		data = (i == 1) ? 0x0 : 0x1;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i),
+				data << DPIO_UPAR_SHIFT);
+	}
+
+	/* Data lane stagger programming */
+	/* FIXME: Fix up value only after power analysis */
+
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	if (is_edp(intel_dp)) {
+		/* init power sequencer on this pipe and port */
+		intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq);
+		intel_dp_init_panel_power_sequencer_registers(dev, intel_dp,
+							      &power_seq);
+	}
+
+	intel_enable_dp(encoder);
+
+	vlv_wait_port_ready(dev_priv, dport);
+}
+
 /*
  * Native read with retry for link status and receiver capability reads for
  * cases where the sink may still be asleep.
@@ -2163,6 +2376,166 @@ static uint32_t intel_vlv_signal_levels(struct intel_dp *intel_dp)
 	return 0;
 }
 
+static uint32_t intel_chv_signal_levels(struct intel_dp *intel_dp)
+{
+	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
+	struct intel_crtc *intel_crtc = to_intel_crtc(dport->base.base.crtc);
+	u32 deemph_reg_value, margin_reg_value, val;
+	uint8_t train_set = intel_dp->train_set[0];
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	enum pipe pipe = intel_crtc->pipe;
+	int i;
+
+	switch (train_set & DP_TRAIN_PRE_EMPHASIS_MASK) {
+	case DP_TRAIN_PRE_EMPHASIS_0:
+		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
+		case DP_TRAIN_VOLTAGE_SWING_400:
+			deemph_reg_value = 128;
+			margin_reg_value = 52;
+			break;
+		case DP_TRAIN_VOLTAGE_SWING_600:
+			deemph_reg_value = 128;
+			margin_reg_value = 77;
+			break;
+		case DP_TRAIN_VOLTAGE_SWING_800:
+			deemph_reg_value = 128;
+			margin_reg_value = 102;
+			break;
+		case DP_TRAIN_VOLTAGE_SWING_1200:
+			deemph_reg_value = 128;
+			margin_reg_value = 154;
+			/* FIXME extra to set for 1200 */
+			break;
+		default:
+			return 0;
+		}
+		break;
+	case DP_TRAIN_PRE_EMPHASIS_3_5:
+		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
+		case DP_TRAIN_VOLTAGE_SWING_400:
+			deemph_reg_value = 85;
+			margin_reg_value = 78;
+			break;
+		case DP_TRAIN_VOLTAGE_SWING_600:
+			deemph_reg_value = 85;
+			margin_reg_value = 116;
+			break;
+		case DP_TRAIN_VOLTAGE_SWING_800:
+			deemph_reg_value = 85;
+			margin_reg_value = 154;
+			break;
+		default:
+			return 0;
+		}
+		break;
+	case DP_TRAIN_PRE_EMPHASIS_6:
+		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
+		case DP_TRAIN_VOLTAGE_SWING_400:
+			deemph_reg_value = 64;
+			margin_reg_value = 104;
+			break;
+		case DP_TRAIN_VOLTAGE_SWING_600:
+			deemph_reg_value = 64;
+			margin_reg_value = 154;
+			break;
+		default:
+			return 0;
+		}
+		break;
+	case DP_TRAIN_PRE_EMPHASIS_9_5:
+		switch (train_set & DP_TRAIN_VOLTAGE_SWING_MASK) {
+		case DP_TRAIN_VOLTAGE_SWING_400:
+			deemph_reg_value = 43;
+			margin_reg_value = 154;
+			break;
+		default:
+			return 0;
+		}
+		break;
+	default:
+		return 0;
+	}
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* Clear calc init */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
+	val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
+	val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+
+	/* Program swing deemph */
+	for (i = 0; i < 4; i++) {
+		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i));
+		val &= ~DPIO_SWING_DEEMPH9P5_MASK;
+		val |= deemph_reg_value << DPIO_SWING_DEEMPH9P5_SHIFT;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW4(ch, i), val);
+	}
+
+	/* Program swing margin */
+	for (i = 0; i < 4; i++) {
+		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
+		val &= ~DPIO_SWING_MARGIN_MASK;
+		val |= margin_reg_value << DPIO_SWING_MARGIN_SHIFT;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
+	}
+
+	/* Disable unique transition scale */
+	for (i = 0; i < 4; i++) {
+		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i));
+		val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
+	}
+
+	if (((train_set & DP_TRAIN_PRE_EMPHASIS_MASK)
+			== DP_TRAIN_PRE_EMPHASIS_0) &&
+		((train_set & DP_TRAIN_VOLTAGE_SWING_MASK)
+			== DP_TRAIN_VOLTAGE_SWING_1200)) {
+
+		/*
+		 * The document said it needs to set bit 27 for ch0 and bit 26
+		 * for ch1. Might be a typo in the doc.
+		 * For now, for this unique transition scale selection, set bit
+		 * 27 for ch0 and ch1.
+		 */
+		for (i = 0; i < 4; i++) {
+			val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i));
+			val |= DPIO_TX_UNIQ_TRANS_SCALE_EN;
+			vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
+		}
+
+		for (i = 0; i < 4; i++) {
+			val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
+			val &= ~(0xff << DPIO_UNIQ_TRANS_SCALE_SHIFT);
+			val |= (0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT);
+			vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
+		}
+	}
+
+	/* Start swing calculation */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
+	val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
+	val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+
+	/* LRC Bypass */
+	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30);
+	val |= DPIO_LRC_BYPASS;
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, val);
+
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	return 0;
+}
+
 static void
 intel_get_adjust_train(struct intel_dp *intel_dp,
 		       const uint8_t link_status[DP_LINK_STATUS_SIZE])
@@ -2377,6 +2750,9 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp, uint32_t *DP)
 	} else if (IS_HASWELL(dev)) {
 		signal_levels = intel_hsw_signal_levels(train_set);
 		mask = DDI_BUF_EMP_MASK;
+	} else if (IS_CHERRYVIEW(dev)) {
+		signal_levels = intel_chv_signal_levels(intel_dp);
+		mask = 0;
 	} else if (IS_VALLEYVIEW(dev)) {
 		signal_levels = intel_vlv_signal_levels(intel_dp);
 		mask = 0;
@@ -2743,22 +3119,7 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 		to_intel_crtc(intel_dig_port->base.base.crtc);
 	uint32_t DP = intel_dp->DP;
 
-	/*
-	 * DDI code has a strict mode set sequence and we should try to respect
-	 * it, otherwise we might hang the machine in many different ways. So we
-	 * really should be disabling the port only on a complete crtc_disable
-	 * sequence. This function is just called under two conditions on DDI
-	 * code:
-	 * - Link train failed while doing crtc_enable, and on this case we
-	 *   really should respect the mode set sequence and wait for a
-	 *   crtc_disable.
-	 * - Someone turned the monitor off and intel_dp_check_link_status
-	 *   called us. We don't need to disable the whole port on this case, so
-	 *   when someone turns the monitor on again,
-	 *   intel_ddi_prepare_link_retrain will take care of redoing the link
-	 *   train.
-	 */
-	if (HAS_DDI(dev))
+	if (WARN_ON(HAS_DDI(dev)))
 		return;
 
 	if (WARN_ON((I915_READ(intel_dp->output_reg) & DP_PORT_EN) == 0))
@@ -2775,9 +3136,6 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 	}
 	POSTING_READ(intel_dp->output_reg);
 
-	/* We don't really know why we're doing this */
-	intel_wait_for_vblank(dev, intel_crtc->pipe);
-
 	if (HAS_PCH_IBX(dev) &&
 	    I915_READ(intel_dp->output_reg) & DP_PIPEB_SELECT) {
 		struct drm_crtc *crtc = intel_dig_port->base.base.crtc;
@@ -2948,6 +3306,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 	u8 sink_irq_vector;
 	u8 link_status[DP_LINK_STATUS_SIZE];
 
+	/* FIXME: This access isn't protected by any locks. */
 	if (!intel_encoder->connectors_active)
 		return;
 
@@ -2980,7 +3339,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 
 	if (!drm_dp_channel_eq_ok(link_status, intel_dp->lane_count)) {
 		DRM_DEBUG_KMS("%s: channel EQ not ok, retraining\n",
-			      drm_get_encoder_name(&intel_encoder->base));
+			      intel_encoder->base.name);
 		intel_dp_start_link_train(intel_dp);
 		intel_dp_complete_link_train(intel_dp);
 		intel_dp_stop_link_train(intel_dp);
@@ -3166,7 +3525,7 @@ intel_dp_detect(struct drm_connector *connector, bool force)
 	intel_display_power_get(dev_priv, power_domain);
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector));
+		      connector->base.id, connector->name);
 
 	intel_dp->has_audio = false;
 
@@ -3374,13 +3733,17 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 
-	drm_dp_aux_unregister_i2c_bus(&intel_dp->aux);
+	drm_dp_aux_unregister(&intel_dp->aux);
 	drm_encoder_cleanup(encoder);
 	if (is_edp(intel_dp)) {
 		cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
-		mutex_lock(&dev->mode_config.mutex);
+		drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 		edp_panel_vdd_off_sync(intel_dp);
-		mutex_unlock(&dev->mode_config.mutex);
+		drm_modeset_unlock(&dev->mode_config.connection_mutex);
+		if (intel_dp->edp_notifier.notifier_call) {
+			unregister_reboot_notifier(&intel_dp->edp_notifier);
+			intel_dp->edp_notifier.notifier_call = NULL;
+		}
 	}
 	kfree(intel_dig_port);
 }
@@ -3651,6 +4014,130 @@ intel_dp_init_panel_power_sequencer_registers(struct drm_device *dev,
 		      I915_READ(pp_div_reg));
 }
 
+void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_encoder *encoder;
+	struct intel_dp *intel_dp = NULL;
+	struct intel_crtc_config *config = NULL;
+	struct intel_crtc *intel_crtc = NULL;
+	struct intel_connector *intel_connector = dev_priv->drrs.connector;
+	u32 reg, val;
+	enum edp_drrs_refresh_rate_type index = DRRS_HIGH_RR;
+
+	if (refresh_rate <= 0) {
+		DRM_DEBUG_KMS("Refresh rate should be positive non-zero.\n");
+		return;
+	}
+
+	if (intel_connector == NULL) {
+		DRM_DEBUG_KMS("DRRS supported for eDP only.\n");
+		return;
+	}
+
+	if (INTEL_INFO(dev)->gen < 8 && intel_edp_is_psr_enabled(dev)) {
+		DRM_DEBUG_KMS("DRRS is disabled as PSR is enabled\n");
+		return;
+	}
+
+	encoder = intel_attached_encoder(&intel_connector->base);
+	intel_dp = enc_to_intel_dp(&encoder->base);
+	intel_crtc = encoder->new_crtc;
+
+	if (!intel_crtc) {
+		DRM_DEBUG_KMS("DRRS: intel_crtc not initialized\n");
+		return;
+	}
+
+	config = &intel_crtc->config;
+
+	if (intel_dp->drrs_state.type < SEAMLESS_DRRS_SUPPORT) {
+		DRM_DEBUG_KMS("Only Seamless DRRS supported.\n");
+		return;
+	}
+
+	if (intel_connector->panel.downclock_mode->vrefresh == refresh_rate)
+		index = DRRS_LOW_RR;
+
+	if (index == intel_dp->drrs_state.refresh_rate_type) {
+		DRM_DEBUG_KMS(
+			"DRRS requested for previously set RR...ignoring\n");
+		return;
+	}
+
+	if (!intel_crtc->active) {
+		DRM_DEBUG_KMS("eDP encoder disabled. CRTC not Active\n");
+		return;
+	}
+
+	if (INTEL_INFO(dev)->gen > 6 && INTEL_INFO(dev)->gen < 8) {
+		reg = PIPECONF(intel_crtc->config.cpu_transcoder);
+		val = I915_READ(reg);
+		if (index > DRRS_HIGH_RR) {
+			val |= PIPECONF_EDP_RR_MODE_SWITCH;
+			intel_dp_set_m2_n2(intel_crtc, &config->dp_m2_n2);
+		} else {
+			val &= ~PIPECONF_EDP_RR_MODE_SWITCH;
+		}
+		I915_WRITE(reg, val);
+	}
+
+	/*
+	 * mutex taken to ensure that there is no race between differnt
+	 * drrs calls trying to update refresh rate. This scenario may occur
+	 * in future when idleness detection based DRRS in kernel and
+	 * possible calls from user space to set differnt RR are made.
+	 */
+
+	mutex_lock(&intel_dp->drrs_state.mutex);
+
+	intel_dp->drrs_state.refresh_rate_type = index;
+
+	mutex_unlock(&intel_dp->drrs_state.mutex);
+
+	DRM_DEBUG_KMS("eDP Refresh Rate set to : %dHz\n", refresh_rate);
+}
+
+static struct drm_display_mode *
+intel_dp_drrs_init(struct intel_digital_port *intel_dig_port,
+			struct intel_connector *intel_connector,
+			struct drm_display_mode *fixed_mode)
+{
+	struct drm_connector *connector = &intel_connector->base;
+	struct intel_dp *intel_dp = &intel_dig_port->dp;
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_display_mode *downclock_mode = NULL;
+
+	if (INTEL_INFO(dev)->gen <= 6) {
+		DRM_DEBUG_KMS("DRRS supported for Gen7 and above\n");
+		return NULL;
+	}
+
+	if (dev_priv->vbt.drrs_type != SEAMLESS_DRRS_SUPPORT) {
+		DRM_INFO("VBT doesn't support DRRS\n");
+		return NULL;
+	}
+
+	downclock_mode = intel_find_panel_downclock
+					(dev, fixed_mode, connector);
+
+	if (!downclock_mode) {
+		DRM_INFO("DRRS not supported\n");
+		return NULL;
+	}
+
+	dev_priv->drrs.connector = intel_connector;
+
+	mutex_init(&intel_dp->drrs_state.mutex);
+
+	intel_dp->drrs_state.type = dev_priv->vbt.drrs_type;
+
+	intel_dp->drrs_state.refresh_rate_type = DRRS_HIGH_RR;
+	DRM_INFO("seamless DRRS supported for eDP panel.\n");
+	return downclock_mode;
+}
+
 static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 				     struct intel_connector *intel_connector,
 				     struct edp_power_seq *power_seq)
@@ -3661,10 +4148,13 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_display_mode *fixed_mode = NULL;
+	struct drm_display_mode *downclock_mode = NULL;
 	bool has_dpcd;
 	struct drm_display_mode *scan;
 	struct edid *edid;
 
+	intel_dp->drrs_state.type = DRRS_NOT_SUPPORTED;
+
 	if (!is_edp(intel_dp))
 		return true;
 
@@ -3715,6 +4205,9 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	list_for_each_entry(scan, &connector->probed_modes, head) {
 		if ((scan->type & DRM_MODE_TYPE_PREFERRED)) {
 			fixed_mode = drm_mode_duplicate(dev, scan);
+			downclock_mode = intel_dp_drrs_init(
+						intel_dig_port,
+						intel_connector, fixed_mode);
 			break;
 		}
 	}
@@ -3728,7 +4221,12 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	}
 	mutex_unlock(&dev->mode_config.mutex);
 
-	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
+	if (IS_VALLEYVIEW(dev)) {
+		intel_dp->edp_notifier.notifier_call = edp_notify_handler;
+		register_reboot_notifier(&intel_dp->edp_notifier);
+	}
+
+	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
 	intel_panel_setup_backlight(connector);
 
 	return true;
@@ -3826,12 +4324,12 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	intel_dp->psr_setup_done = false;
 
 	if (!intel_edp_init_connector(intel_dp, intel_connector, &power_seq)) {
-		drm_dp_aux_unregister_i2c_bus(&intel_dp->aux);
+		drm_dp_aux_unregister(&intel_dp->aux);
 		if (is_edp(intel_dp)) {
 			cancel_delayed_work_sync(&intel_dp->panel_vdd_work);
-			mutex_lock(&dev->mode_config.mutex);
+			drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 			edp_panel_vdd_off_sync(intel_dp);
-			mutex_unlock(&dev->mode_config.mutex);
+			drm_modeset_unlock(&dev->mode_config.connection_mutex);
 		}
 		drm_sysfs_connector_remove(connector);
 		drm_connector_cleanup(connector);
@@ -3877,25 +4375,36 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 			 DRM_MODE_ENCODER_TMDS);
 
 	intel_encoder->compute_config = intel_dp_compute_config;
-	intel_encoder->mode_set = intel_dp_mode_set;
 	intel_encoder->disable = intel_disable_dp;
-	intel_encoder->post_disable = intel_post_disable_dp;
 	intel_encoder->get_hw_state = intel_dp_get_hw_state;
 	intel_encoder->get_config = intel_dp_get_config;
-	if (IS_VALLEYVIEW(dev)) {
+	if (IS_CHERRYVIEW(dev)) {
+		intel_encoder->pre_enable = chv_pre_enable_dp;
+		intel_encoder->enable = vlv_enable_dp;
+		intel_encoder->post_disable = chv_post_disable_dp;
+	} else if (IS_VALLEYVIEW(dev)) {
 		intel_encoder->pre_pll_enable = vlv_dp_pre_pll_enable;
 		intel_encoder->pre_enable = vlv_pre_enable_dp;
 		intel_encoder->enable = vlv_enable_dp;
+		intel_encoder->post_disable = vlv_post_disable_dp;
 	} else {
 		intel_encoder->pre_enable = g4x_pre_enable_dp;
 		intel_encoder->enable = g4x_enable_dp;
+		intel_encoder->post_disable = g4x_post_disable_dp;
 	}
 
 	intel_dig_port->port = port;
 	intel_dig_port->dp.output_reg = output_reg;
 
 	intel_encoder->type = INTEL_OUTPUT_DISPLAYPORT;
-	intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
+	if (IS_CHERRYVIEW(dev)) {
+		if (port == PORT_D)
+			intel_encoder->crtc_mask = 1 << 2;
+		else
+			intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
+	} else {
+		intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
+	}
 	intel_encoder->cloneable = 0;
 	intel_encoder->hot_plug = intel_dp_hot_plug;
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 328b1a70264..f67340ed2c1 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -81,8 +81,8 @@
 /* Maximum cursor sizes */
 #define GEN2_CURSOR_WIDTH 64
 #define GEN2_CURSOR_HEIGHT 64
-#define CURSOR_WIDTH 256
-#define CURSOR_HEIGHT 256
+#define MAX_CURSOR_WIDTH 256
+#define MAX_CURSOR_HEIGHT 256
 
 #define INTEL_I2C_BUS_DVO 1
 #define INTEL_I2C_BUS_SDVO 2
@@ -106,8 +106,8 @@
 #define INTEL_DVO_CHIP_TMDS 2
 #define INTEL_DVO_CHIP_TVOUT 4
 
-#define INTEL_DSI_COMMAND_MODE	0
-#define INTEL_DSI_VIDEO_MODE	1
+#define INTEL_DSI_VIDEO_MODE	0
+#define INTEL_DSI_COMMAND_MODE	1
 
 struct intel_framebuffer {
 	struct drm_framebuffer base;
@@ -273,6 +273,13 @@ struct intel_crtc_config {
 	 * accordingly. */
 	bool has_dp_encoder;
 
+	/* Whether we should send NULL infoframes. Required for audio. */
+	bool has_hdmi_sink;
+
+	/* Audio enabled on this pipe. Only valid if either has_hdmi_sink or
+	 * has_dp_encoder is set. */
+	bool has_audio;
+
 	/*
 	 * Enable dithering, used when the selected pipe bpp doesn't match the
 	 * plane bpp.
@@ -306,6 +313,9 @@ struct intel_crtc_config {
 	int pipe_bpp;
 	struct intel_link_m_n dp_m_n;
 
+	/* m2_n2 for eDP downclock */
+	struct intel_link_m_n dp_m2_n2;
+
 	/*
 	 * Frequence the dpll for the port should run at. Differs from the
 	 * adjusted dotclock e.g. for DP or 12bpc hdmi mode. This is also
@@ -343,6 +353,9 @@ struct intel_pipe_wm {
 	struct intel_wm_level wm[5];
 	uint32_t linetime;
 	bool fbc_wm_enabled;
+	bool pipe_enabled;
+	bool sprites_enabled;
+	bool sprites_scaled;
 };
 
 struct intel_crtc {
@@ -357,7 +370,6 @@ struct intel_crtc {
 	 */
 	bool active;
 	unsigned long enabled_power_domains;
-	bool eld_vld;
 	bool primary_enabled; /* is the primary plane (partially) visible? */
 	bool lowfreq_avail;
 	struct intel_overlay *overlay;
@@ -374,8 +386,8 @@ struct intel_crtc {
 	uint32_t cursor_addr;
 	int16_t cursor_x, cursor_y;
 	int16_t cursor_width, cursor_height;
-	int16_t max_cursor_width, max_cursor_height;
-	bool cursor_visible;
+	uint32_t cursor_cntl;
+	uint32_t cursor_base;
 
 	struct intel_plane_config plane_config;
 	struct intel_crtc_config config;
@@ -396,6 +408,10 @@ struct intel_crtc {
 		/* watermarks currently being used  */
 		struct intel_pipe_wm active;
 	} wm;
+
+	wait_queue_head_t vbl_wait;
+
+	int scanline_offset;
 };
 
 struct intel_plane_wm_parameters {
@@ -479,11 +495,23 @@ struct intel_hdmi {
 				enum hdmi_infoframe_type type,
 				const void *frame, ssize_t len);
 	void (*set_infoframes)(struct drm_encoder *encoder,
+			       bool enable,
 			       struct drm_display_mode *adjusted_mode);
 };
 
 #define DP_MAX_DOWNSTREAM_PORTS		0x10
 
+/**
+ * HIGH_RR is the highest eDP panel refresh rate read from EDID
+ * LOW_RR is the lowest eDP panel refresh rate found from EDID
+ * parsing for same resolution.
+ */
+enum edp_drrs_refresh_rate_type {
+	DRRS_HIGH_RR,
+	DRRS_LOW_RR,
+	DRRS_MAX_RR, /* RR count */
+};
+
 struct intel_dp {
 	uint32_t output_reg;
 	uint32_t aux_ch_ctl_reg;
@@ -510,6 +538,8 @@ struct intel_dp {
 	unsigned long last_power_on;
 	unsigned long last_backlight_off;
 	bool psr_setup_done;
+	struct notifier_block edp_notifier;
+
 	bool use_tps3;
 	struct intel_connector *attached_connector;
 
@@ -522,6 +552,12 @@ struct intel_dp {
 				     bool has_aux_irq,
 				     int send_bytes,
 				     uint32_t aux_clock_divider);
+	struct {
+		enum drrs_support_type type;
+		enum edp_drrs_refresh_rate_type refresh_rate_type;
+		struct mutex mutex;
+	} drrs_state;
+
 };
 
 struct intel_digital_port {
@@ -537,6 +573,7 @@ vlv_dport_to_channel(struct intel_digital_port *dport)
 {
 	switch (dport->port) {
 	case PORT_B:
+	case PORT_D:
 		return DPIO_CH0;
 	case PORT_C:
 		return DPIO_CH1;
@@ -545,6 +582,20 @@ vlv_dport_to_channel(struct intel_digital_port *dport)
 	}
 }
 
+static inline int
+vlv_pipe_to_channel(enum pipe pipe)
+{
+	switch (pipe) {
+	case PIPE_A:
+	case PIPE_C:
+		return DPIO_CH0;
+	case PIPE_B:
+		return DPIO_CH1;
+	default:
+		BUG();
+	}
+}
+
 static inline struct drm_crtc *
 intel_get_crtc_for_pipe(struct drm_device *dev, int pipe)
 {
@@ -569,6 +620,8 @@ struct intel_unpin_work {
 #define INTEL_FLIP_INACTIVE	0
 #define INTEL_FLIP_PENDING	1
 #define INTEL_FLIP_COMPLETE	2
+	u32 flip_count;
+	u32 gtt_offset;
 	bool enable_stall_check;
 };
 
@@ -620,8 +673,6 @@ hdmi_to_dig_port(struct intel_hdmi *intel_hdmi)
 /* i915_irq.c */
 bool intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
 					   enum pipe pipe, bool enable);
-bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
-					     enum pipe pipe, bool enable);
 bool intel_set_pch_fifo_underrun_reporting(struct drm_device *dev,
 					   enum transcoder pch_transcoder,
 					   bool enable);
@@ -629,8 +680,12 @@ void ilk_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void ilk_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void snb_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void snb_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
-void hsw_runtime_pm_disable_interrupts(struct drm_device *dev);
-void hsw_runtime_pm_restore_interrupts(struct drm_device *dev);
+void bdw_enable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
+void bdw_disable_pm_irq(struct drm_i915_private *dev_priv, uint32_t mask);
+void intel_runtime_pm_disable_interrupts(struct drm_device *dev);
+void intel_runtime_pm_restore_interrupts(struct drm_device *dev);
+int intel_get_crtc_scanline(struct intel_crtc *crtc);
+void i9xx_check_fifo_underruns(struct drm_device *dev);
 
 
 /* intel_crt.c */
@@ -666,9 +721,10 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 const char *intel_output_name(int output);
 bool intel_has_pending_fb_unpin(struct drm_device *dev);
 int intel_pch_rawclk(struct drm_device *dev);
+int valleyview_cur_cdclk(struct drm_i915_private *dev_priv);
 void intel_mark_busy(struct drm_device *dev);
 void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
-			struct intel_ring_buffer *ring);
+			struct intel_engine_cs *ring);
 void intel_mark_idle(struct drm_device *dev);
 void intel_crtc_restore_mode(struct drm_crtc *crtc);
 void intel_crtc_update_dpms(struct drm_crtc *crtc);
@@ -695,12 +751,14 @@ void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 			 struct intel_digital_port *dport);
 bool intel_get_load_detect_pipe(struct drm_connector *connector,
 				struct drm_display_mode *mode,
-				struct intel_load_detect_pipe *old);
+				struct intel_load_detect_pipe *old,
+				struct drm_modeset_acquire_ctx *ctx);
 void intel_release_load_detect_pipe(struct drm_connector *connector,
-				    struct intel_load_detect_pipe *old);
+				    struct intel_load_detect_pipe *old,
+				    struct drm_modeset_acquire_ctx *ctx);
 int intel_pin_and_fence_fb_obj(struct drm_device *dev,
 			       struct drm_i915_gem_object *obj,
-			       struct intel_ring_buffer *pipelined);
+			       struct intel_engine_cs *pipelined);
 void intel_unpin_fb_obj(struct drm_i915_gem_object *obj);
 struct drm_framebuffer *
 __intel_framebuffer_create(struct drm_device *dev,
@@ -751,6 +809,8 @@ int valleyview_get_vco(struct drm_i915_private *dev_priv);
 void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 				 struct intel_crtc_config *pipe_config);
 int intel_format_to_fourcc(int format);
+void intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc);
+
 
 /* intel_dp.c */
 void intel_dp_init(struct drm_device *dev, int output_reg, enum port port);
@@ -774,7 +834,7 @@ void intel_edp_panel_off(struct intel_dp *intel_dp);
 void intel_edp_psr_enable(struct intel_dp *intel_dp);
 void intel_edp_psr_disable(struct intel_dp *intel_dp);
 void intel_edp_psr_update(struct drm_device *dev);
-
+void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate);
 
 /* intel_dsi.c */
 bool intel_dsi_init(struct drm_device *dev);
@@ -876,6 +936,7 @@ extern struct drm_display_mode *intel_find_panel_downclock(
 /* intel_pm.c */
 void intel_init_clock_gating(struct drm_device *dev);
 void intel_suspend_hw(struct drm_device *dev);
+int ilk_wm_max_level(const struct drm_device *dev);
 void intel_update_watermarks(struct drm_crtc *crtc);
 void intel_update_sprite_watermarks(struct drm_plane *plane,
 				    struct drm_crtc *crtc,
@@ -891,8 +952,8 @@ int intel_power_domains_init(struct drm_i915_private *);
 void intel_power_domains_remove(struct drm_i915_private *);
 bool intel_display_power_enabled(struct drm_i915_private *dev_priv,
 				 enum intel_display_power_domain domain);
-bool intel_display_power_enabled_sw(struct drm_i915_private *dev_priv,
-				    enum intel_display_power_domain domain);
+bool intel_display_power_enabled_unlocked(struct drm_i915_private *dev_priv,
+					  enum intel_display_power_domain domain);
 void intel_display_power_get(struct drm_i915_private *dev_priv,
 			     enum intel_display_power_domain domain);
 void intel_display_power_put(struct drm_i915_private *dev_priv,
@@ -902,6 +963,7 @@ void intel_init_gt_powersave(struct drm_device *dev);
 void intel_cleanup_gt_powersave(struct drm_device *dev);
 void intel_enable_gt_powersave(struct drm_device *dev);
 void intel_disable_gt_powersave(struct drm_device *dev);
+void intel_reset_gt_powersave(struct drm_device *dev);
 void ironlake_teardown_rc6(struct drm_device *dev);
 void gen6_update_ring_freq(struct drm_device *dev);
 void gen6_rps_idle(struct drm_i915_private *dev_priv);
@@ -909,11 +971,13 @@ void gen6_rps_boost(struct drm_i915_private *dev_priv);
 void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
 void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
+void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_put(struct drm_i915_private *dev_priv);
 void intel_init_runtime_pm(struct drm_i915_private *dev_priv);
 void intel_fini_runtime_pm(struct drm_i915_private *dev_priv);
 void ilk_wm_get_hw_state(struct drm_device *dev);
-
+void __vlv_set_power_well(struct drm_i915_private *dev_priv,
+			  enum punit_power_well power_well_id, bool enable);
 
 /* intel_sdvo.c */
 bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob);
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 33656647f8b..3fd082933c8 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -35,6 +35,11 @@
 
 /* the sub-encoders aka panel drivers */
 static const struct intel_dsi_device intel_dsi_devices[] = {
+	{
+		.panel_id = MIPI_DSI_GENERIC_PANEL_ID,
+		.name = "vbt-generic-dsi-vid-mode-display",
+		.dev_ops = &vbt_generic_dsi_display_ops,
+	},
 };
 
 static void band_gap_reset(struct drm_i915_private *dev_priv)
@@ -59,12 +64,12 @@ static struct intel_dsi *intel_attached_dsi(struct drm_connector *connector)
 
 static inline bool is_vid_mode(struct intel_dsi *intel_dsi)
 {
-	return intel_dsi->dev.type == INTEL_DSI_VIDEO_MODE;
+	return intel_dsi->operation_mode == INTEL_DSI_VIDEO_MODE;
 }
 
 static inline bool is_cmd_mode(struct intel_dsi *intel_dsi)
 {
-	return intel_dsi->dev.type == INTEL_DSI_COMMAND_MODE;
+	return intel_dsi->operation_mode == INTEL_DSI_COMMAND_MODE;
 }
 
 static void intel_dsi_hot_plug(struct intel_encoder *encoder)
@@ -94,13 +99,6 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_dsi_pre_pll_enable(struct intel_encoder *encoder)
-{
-	DRM_DEBUG_KMS("\n");
-
-	vlv_enable_dsi_pll(encoder);
-}
-
 static void intel_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
@@ -110,32 +108,27 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder)
 
 	DRM_DEBUG_KMS("\n");
 
+	mutex_lock(&dev_priv->dpio_lock);
+	/* program rcomp for compliance, reduce from 50 ohms to 45 ohms
+	 * needed everytime after power gate */
+	vlv_flisdsi_write(dev_priv, 0x04, 0x0004);
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	/* bandgap reset is needed after everytime we do power gate */
+	band_gap_reset(dev_priv);
+
+	I915_WRITE(MIPI_DEVICE_READY(pipe), ULPS_STATE_ENTER);
+	usleep_range(2500, 3000);
+
 	val = I915_READ(MIPI_PORT_CTRL(pipe));
 	I915_WRITE(MIPI_PORT_CTRL(pipe), val | LP_OUTPUT_HOLD);
 	usleep_range(1000, 1500);
-	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY | ULPS_STATE_EXIT);
-	usleep_range(2000, 2500);
-	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY);
-	usleep_range(2000, 2500);
-	I915_WRITE(MIPI_DEVICE_READY(pipe), 0x00);
-	usleep_range(2000, 2500);
-	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY);
-	usleep_range(2000, 2500);
-}
-static void intel_dsi_pre_enable(struct intel_encoder *encoder)
-{
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-
-	DRM_DEBUG_KMS("\n");
-
-	if (intel_dsi->dev.dev_ops->panel_reset)
-		intel_dsi->dev.dev_ops->panel_reset(&intel_dsi->dev);
 
-	/* put device in ready state */
-	intel_dsi_device_ready(encoder);
+	I915_WRITE(MIPI_DEVICE_READY(pipe), ULPS_STATE_EXIT);
+	usleep_range(2500, 3000);
 
-	if (intel_dsi->dev.dev_ops->send_otp_cmds)
-		intel_dsi->dev.dev_ops->send_otp_cmds(&intel_dsi->dev);
+	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY);
+	usleep_range(2500, 3000);
 }
 
 static void intel_dsi_enable(struct intel_encoder *encoder)
@@ -153,18 +146,78 @@ static void intel_dsi_enable(struct intel_encoder *encoder)
 		I915_WRITE(MIPI_MAX_RETURN_PKT_SIZE(pipe), 8 * 4);
 	else {
 		msleep(20); /* XXX */
-		dpi_send_cmd(intel_dsi, TURN_ON);
+		dpi_send_cmd(intel_dsi, TURN_ON, DPI_LP_MODE_EN);
 		msleep(100);
 
+		if (intel_dsi->dev.dev_ops->enable)
+			intel_dsi->dev.dev_ops->enable(&intel_dsi->dev);
+
 		/* assert ip_tg_enable signal */
 		temp = I915_READ(MIPI_PORT_CTRL(pipe)) & ~LANE_CONFIGURATION_MASK;
 		temp = temp | intel_dsi->port_bits;
 		I915_WRITE(MIPI_PORT_CTRL(pipe), temp | DPI_ENABLE);
 		POSTING_READ(MIPI_PORT_CTRL(pipe));
 	}
+}
+
+static void intel_dsi_pre_enable(struct intel_encoder *encoder)
+{
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	enum pipe pipe = intel_crtc->pipe;
+	u32 tmp;
+
+	DRM_DEBUG_KMS("\n");
+
+	/* Disable DPOunit clock gating, can stall pipe
+	 * and we need DPLL REFA always enabled */
+	tmp = I915_READ(DPLL(pipe));
+	tmp |= DPLL_REFA_CLK_ENABLE_VLV;
+	I915_WRITE(DPLL(pipe), tmp);
+
+	tmp = I915_READ(DSPCLK_GATE_D);
+	tmp |= DPOUNIT_CLOCK_GATE_DISABLE;
+	I915_WRITE(DSPCLK_GATE_D, tmp);
+
+	/* put device in ready state */
+	intel_dsi_device_ready(encoder);
+
+	msleep(intel_dsi->panel_on_delay);
+
+	if (intel_dsi->dev.dev_ops->panel_reset)
+		intel_dsi->dev.dev_ops->panel_reset(&intel_dsi->dev);
+
+	if (intel_dsi->dev.dev_ops->send_otp_cmds)
+		intel_dsi->dev.dev_ops->send_otp_cmds(&intel_dsi->dev);
+
+	/* Enable port in pre-enable phase itself because as per hw team
+	 * recommendation, port should be enabled befor plane & pipe */
+	intel_dsi_enable(encoder);
+}
+
+static void intel_dsi_enable_nop(struct intel_encoder *encoder)
+{
+	DRM_DEBUG_KMS("\n");
+
+	/* for DSI port enable has to be done before pipe
+	 * and plane enable, so port enable is done in
+	 * pre_enable phase itself unlike other encoders
+	 */
+}
+
+static void intel_dsi_pre_disable(struct intel_encoder *encoder)
+{
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+
+	DRM_DEBUG_KMS("\n");
 
-	if (intel_dsi->dev.dev_ops->enable)
-		intel_dsi->dev.dev_ops->enable(&intel_dsi->dev);
+	if (is_vid_mode(intel_dsi)) {
+		/* Send Shutdown command to the panel in LP mode */
+		dpi_send_cmd(intel_dsi, SHUTDOWN, DPI_LP_MODE_EN);
+		msleep(10);
+	}
 }
 
 static void intel_dsi_disable(struct intel_encoder *encoder)
@@ -179,9 +232,6 @@ static void intel_dsi_disable(struct intel_encoder *encoder)
 	DRM_DEBUG_KMS("\n");
 
 	if (is_vid_mode(intel_dsi)) {
-		dpi_send_cmd(intel_dsi, SHUTDOWN);
-		msleep(10);
-
 		/* de-assert ip_tg_enable signal */
 		temp = I915_READ(MIPI_PORT_CTRL(pipe));
 		I915_WRITE(MIPI_PORT_CTRL(pipe), temp & ~DPI_ENABLE);
@@ -190,6 +240,23 @@ static void intel_dsi_disable(struct intel_encoder *encoder)
 		msleep(2);
 	}
 
+	/* Panel commands can be sent when clock is in LP11 */
+	I915_WRITE(MIPI_DEVICE_READY(pipe), 0x0);
+
+	temp = I915_READ(MIPI_CTRL(pipe));
+	temp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
+	I915_WRITE(MIPI_CTRL(pipe), temp |
+			intel_dsi->escape_clk_div <<
+			ESCAPE_CLOCK_DIVIDER_SHIFT);
+
+	I915_WRITE(MIPI_EOT_DISABLE(pipe), CLOCKSTOP);
+
+	temp = I915_READ(MIPI_DSI_FUNC_PRG(pipe));
+	temp &= ~VID_MODE_FORMAT_MASK;
+	I915_WRITE(MIPI_DSI_FUNC_PRG(pipe), temp);
+
+	I915_WRITE(MIPI_DEVICE_READY(pipe), 0x1);
+
 	/* if disable packets are sent before sending shutdown packet then in
 	 * some next enable sequence send turn on packet error is observed */
 	if (intel_dsi->dev.dev_ops->disable)
@@ -205,38 +272,50 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 
 	DRM_DEBUG_KMS("\n");
 
-	I915_WRITE(MIPI_DEVICE_READY(pipe), ULPS_STATE_ENTER);
+	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY | ULPS_STATE_ENTER);
 	usleep_range(2000, 2500);
 
-	I915_WRITE(MIPI_DEVICE_READY(pipe), ULPS_STATE_EXIT);
+	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY | ULPS_STATE_EXIT);
 	usleep_range(2000, 2500);
 
-	I915_WRITE(MIPI_DEVICE_READY(pipe), ULPS_STATE_ENTER);
+	I915_WRITE(MIPI_DEVICE_READY(pipe), DEVICE_READY | ULPS_STATE_ENTER);
 	usleep_range(2000, 2500);
 
-	val = I915_READ(MIPI_PORT_CTRL(pipe));
-	I915_WRITE(MIPI_PORT_CTRL(pipe), val & ~LP_OUTPUT_HOLD);
-	usleep_range(1000, 1500);
-
 	if (wait_for(((I915_READ(MIPI_PORT_CTRL(pipe)) & AFE_LATCHOUT)
 					== 0x00000), 30))
 		DRM_ERROR("DSI LP not going Low\n");
 
+	val = I915_READ(MIPI_PORT_CTRL(pipe));
+	I915_WRITE(MIPI_PORT_CTRL(pipe), val & ~LP_OUTPUT_HOLD);
+	usleep_range(1000, 1500);
+
 	I915_WRITE(MIPI_DEVICE_READY(pipe), 0x00);
 	usleep_range(2000, 2500);
 
 	vlv_disable_dsi_pll(encoder);
 }
+
 static void intel_dsi_post_disable(struct intel_encoder *encoder)
 {
+	struct drm_i915_private *dev_priv = encoder->base.dev->dev_private;
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	u32 val;
 
 	DRM_DEBUG_KMS("\n");
 
+	intel_dsi_disable(encoder);
+
 	intel_dsi_clear_device_ready(encoder);
 
+	val = I915_READ(DSPCLK_GATE_D);
+	val &= ~DPOUNIT_CLOCK_GATE_DISABLE;
+	I915_WRITE(DSPCLK_GATE_D, val);
+
 	if (intel_dsi->dev.dev_ops->disable_panel_power)
 		intel_dsi->dev.dev_ops->disable_panel_power(&intel_dsi->dev);
+
+	msleep(intel_dsi->panel_off_delay);
+	msleep(intel_dsi->panel_pwr_cycle_delay);
 }
 
 static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
@@ -364,7 +443,7 @@ static void set_dsi_timings(struct drm_encoder *encoder,
 	I915_WRITE(MIPI_VBP_COUNT(pipe), vbp);
 }
 
-static void intel_dsi_mode_set(struct intel_encoder *intel_encoder)
+static void intel_dsi_prepare(struct intel_encoder *intel_encoder)
 {
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_device *dev = encoder->dev;
@@ -379,9 +458,6 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder)
 
 	DRM_DEBUG_KMS("pipe %c\n", pipe_name(pipe));
 
-	/* XXX: Location of the call */
-	band_gap_reset(dev_priv);
-
 	/* escape clock divider, 20MHz, shared for A and C. device ready must be
 	 * off when doing this! txclkesc? */
 	tmp = I915_READ(MIPI_CTRL(0));
@@ -452,10 +528,20 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder)
 	/* dphy stuff */
 
 	/* in terms of low power clock */
-	I915_WRITE(MIPI_INIT_COUNT(pipe), txclkesc(ESCAPE_CLOCK_DIVIDER_1, 100));
+	I915_WRITE(MIPI_INIT_COUNT(pipe), txclkesc(intel_dsi->escape_clk_div, 100));
+
+	val = 0;
+	if (intel_dsi->eotp_pkt == 0)
+		val |= EOT_DISABLE;
+
+	if (intel_dsi->clock_stop)
+		val |= CLOCKSTOP;
 
 	/* recovery disables */
-	I915_WRITE(MIPI_EOT_DISABLE(pipe), intel_dsi->eot_disable);
+	I915_WRITE(MIPI_EOT_DISABLE(pipe), val);
+
+	/* in terms of low power clock */
+	I915_WRITE(MIPI_INIT_COUNT(pipe), intel_dsi->init_count);
 
 	/* in terms of txbyteclkhs. actual high to low switch +
 	 * MIPI_STOP_STATE_STALL * MIPI_LP_BYTECLK.
@@ -484,9 +570,23 @@ static void intel_dsi_mode_set(struct intel_encoder *intel_encoder)
 		   intel_dsi->clk_hs_to_lp_count << HS_LP_PWR_SW_CNT_SHIFT);
 
 	if (is_vid_mode(intel_dsi))
+		/* Some panels might have resolution which is not a multiple of
+		 * 64 like 1366 x 768. Enable RANDOM resolution support for such
+		 * panels by default */
 		I915_WRITE(MIPI_VIDEO_MODE_FORMAT(pipe),
 				intel_dsi->video_frmt_cfg_bits |
-				intel_dsi->video_mode_format);
+				intel_dsi->video_mode_format |
+				IP_TG_CONFIG |
+				RANDOM_DPI_DISPLAY_RESOLUTION);
+}
+
+static void intel_dsi_pre_pll_enable(struct intel_encoder *encoder)
+{
+	DRM_DEBUG_KMS("\n");
+
+	intel_dsi_prepare(encoder);
+
+	vlv_enable_dsi_pll(encoder);
 }
 
 static enum drm_connector_status
@@ -566,11 +666,16 @@ bool intel_dsi_init(struct drm_device *dev)
 	struct intel_connector *intel_connector;
 	struct drm_connector *connector;
 	struct drm_display_mode *fixed_mode = NULL;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	const struct intel_dsi_device *dsi;
 	unsigned int i;
 
 	DRM_DEBUG_KMS("\n");
 
+	/* There is no detection method for MIPI so rely on VBT */
+	if (!dev_priv->vbt.has_mipi)
+		return false;
+
 	intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL);
 	if (!intel_dsi)
 		return false;
@@ -585,6 +690,13 @@ bool intel_dsi_init(struct drm_device *dev)
 	encoder = &intel_encoder->base;
 	intel_dsi->attached_connector = intel_connector;
 
+	if (IS_VALLEYVIEW(dev)) {
+		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
+	} else {
+		DRM_ERROR("Unsupported Mipi device to reg base");
+		return false;
+	}
+
 	connector = &intel_connector->base;
 
 	drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI);
@@ -594,9 +706,8 @@ bool intel_dsi_init(struct drm_device *dev)
 	intel_encoder->compute_config = intel_dsi_compute_config;
 	intel_encoder->pre_pll_enable = intel_dsi_pre_pll_enable;
 	intel_encoder->pre_enable = intel_dsi_pre_enable;
-	intel_encoder->enable = intel_dsi_enable;
-	intel_encoder->mode_set = intel_dsi_mode_set;
-	intel_encoder->disable = intel_dsi_disable;
+	intel_encoder->enable = intel_dsi_enable_nop;
+	intel_encoder->disable = intel_dsi_pre_disable;
 	intel_encoder->post_disable = intel_dsi_post_disable;
 	intel_encoder->get_hw_state = intel_dsi_get_hw_state;
 	intel_encoder->get_config = intel_dsi_get_config;
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index b4a27cec882..31db33d3e5c 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -31,7 +31,6 @@
 struct intel_dsi_device {
 	unsigned int panel_id;
 	const char *name;
-	int type;
 	const struct intel_dsi_dev_ops *dev_ops;
 	void *dev_priv;
 };
@@ -85,6 +84,9 @@ struct intel_dsi {
 	/* virtual channel */
 	int channel;
 
+	/* Video mode or command mode */
+	u16 operation_mode;
+
 	/* number of DSI lanes */
 	unsigned int lane_count;
 
@@ -95,8 +97,10 @@ struct intel_dsi {
 	u32 video_mode_format;
 
 	/* eot for MIPI_EOT_DISABLE register */
-	u32 eot_disable;
+	u8 eotp_pkt;
+	u8 clock_stop;
 
+	u8 escape_clk_div;
 	u32 port_bits;
 	u32 bw_timer;
 	u32 dphy_reg;
@@ -110,6 +114,15 @@ struct intel_dsi {
 	u16 hs_to_lp_count;
 	u16 clk_lp_to_hs_count;
 	u16 clk_hs_to_lp_count;
+
+	u16 init_count;
+
+	/* all delays in ms */
+	u16 backlight_off_delay;
+	u16 backlight_on_delay;
+	u16 panel_on_delay;
+	u16 panel_off_delay;
+	u16 panel_pwr_cycle_delay;
 };
 
 static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
@@ -120,4 +133,6 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
 extern void vlv_enable_dsi_pll(struct intel_encoder *encoder);
 extern void vlv_disable_dsi_pll(struct intel_encoder *encoder);
 
+extern struct intel_dsi_dev_ops vbt_generic_dsi_display_ops;
+
 #endif /* _INTEL_DSI_H */
diff --git a/drivers/gpu/drm/i915/intel_dsi_cmd.c b/drivers/gpu/drm/i915/intel_dsi_cmd.c
index 7c40f981d2c..933c8630523 100644
--- a/drivers/gpu/drm/i915/intel_dsi_cmd.c
+++ b/drivers/gpu/drm/i915/intel_dsi_cmd.c
@@ -389,7 +389,7 @@ int dsi_vc_generic_read(struct intel_dsi *intel_dsi, int channel,
  *
  * XXX: commands with data in MIPI_DPI_DATA?
  */
-int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd)
+int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd, bool hs)
 {
 	struct drm_encoder *encoder = &intel_dsi->base.base;
 	struct drm_device *dev = encoder->dev;
@@ -399,17 +399,11 @@ int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd)
 	u32 mask;
 
 	/* XXX: pipe, hs */
-	if (intel_dsi->hs)
+	if (hs)
 		cmd &= ~DPI_LP_MODE;
 	else
 		cmd |= DPI_LP_MODE;
 
-	/* DPI virtual channel?! */
-
-	mask = DPI_FIFO_EMPTY;
-	if (wait_for((I915_READ(MIPI_GEN_FIFO_STAT(pipe)) & mask) == mask, 50))
-		DRM_ERROR("Timeout waiting for DPI FIFO empty.\n");
-
 	/* clear bit */
 	I915_WRITE(MIPI_INTR_STAT(pipe), SPL_PKT_SENT_INTERRUPT);
 
diff --git a/drivers/gpu/drm/i915/intel_dsi_cmd.h b/drivers/gpu/drm/i915/intel_dsi_cmd.h
index 54c8a234a2e..9a18cbfa546 100644
--- a/drivers/gpu/drm/i915/intel_dsi_cmd.h
+++ b/drivers/gpu/drm/i915/intel_dsi_cmd.h
@@ -33,6 +33,9 @@
 #include "intel_drv.h"
 #include "intel_dsi.h"
 
+#define DPI_LP_MODE_EN	false
+#define DPI_HS_MODE_EN	true
+
 void dsi_hs_mode_enable(struct intel_dsi *intel_dsi, bool enable);
 
 int dsi_vc_dcs_write(struct intel_dsi *intel_dsi, int channel,
@@ -47,7 +50,7 @@ int dsi_vc_dcs_read(struct intel_dsi *intel_dsi, int channel, u8 dcs_cmd,
 int dsi_vc_generic_read(struct intel_dsi *intel_dsi, int channel,
 			u8 *reqdata, int reqlen, u8 *buf, int buflen);
 
-int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd);
+int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd, bool hs);
 
 /* XXX: questionable write helpers */
 static inline int dsi_vc_dcs_write_0(struct intel_dsi *intel_dsi,
diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
new file mode 100644
index 00000000000..21a0d348ced
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c
@@ -0,0 +1,589 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Author: Shobhit Kumar <shobhit.kumar@intel.com>
+ *
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_edid.h>
+#include <drm/i915_drm.h>
+#include <linux/slab.h>
+#include <video/mipi_display.h>
+#include <asm/intel-mid.h>
+#include <video/mipi_display.h>
+#include "i915_drv.h"
+#include "intel_drv.h"
+#include "intel_dsi.h"
+#include "intel_dsi_cmd.h"
+
+#define MIPI_TRANSFER_MODE_SHIFT	0
+#define MIPI_VIRTUAL_CHANNEL_SHIFT	1
+#define MIPI_PORT_SHIFT			3
+
+#define PREPARE_CNT_MAX		0x3F
+#define EXIT_ZERO_CNT_MAX	0x3F
+#define CLK_ZERO_CNT_MAX	0xFF
+#define TRAIL_CNT_MAX		0x1F
+
+#define NS_KHZ_RATIO 1000000
+
+#define GPI0_NC_0_HV_DDI0_HPD           0x4130
+#define GPIO_NC_0_HV_DDI0_PAD           0x4138
+#define GPIO_NC_1_HV_DDI0_DDC_SDA       0x4120
+#define GPIO_NC_1_HV_DDI0_DDC_SDA_PAD   0x4128
+#define GPIO_NC_2_HV_DDI0_DDC_SCL       0x4110
+#define GPIO_NC_2_HV_DDI0_DDC_SCL_PAD   0x4118
+#define GPIO_NC_3_PANEL0_VDDEN          0x4140
+#define GPIO_NC_3_PANEL0_VDDEN_PAD      0x4148
+#define GPIO_NC_4_PANEL0_BLKEN          0x4150
+#define GPIO_NC_4_PANEL0_BLKEN_PAD      0x4158
+#define GPIO_NC_5_PANEL0_BLKCTL         0x4160
+#define GPIO_NC_5_PANEL0_BLKCTL_PAD     0x4168
+#define GPIO_NC_6_PCONF0                0x4180
+#define GPIO_NC_6_PAD                   0x4188
+#define GPIO_NC_7_PCONF0                0x4190
+#define GPIO_NC_7_PAD                   0x4198
+#define GPIO_NC_8_PCONF0                0x4170
+#define GPIO_NC_8_PAD                   0x4178
+#define GPIO_NC_9_PCONF0                0x4100
+#define GPIO_NC_9_PAD                   0x4108
+#define GPIO_NC_10_PCONF0               0x40E0
+#define GPIO_NC_10_PAD                  0x40E8
+#define GPIO_NC_11_PCONF0               0x40F0
+#define GPIO_NC_11_PAD                  0x40F8
+
+struct gpio_table {
+	u16 function_reg;
+	u16 pad_reg;
+	u8 init;
+};
+
+static struct gpio_table gtable[] = {
+	{ GPI0_NC_0_HV_DDI0_HPD, GPIO_NC_0_HV_DDI0_PAD, 0 },
+	{ GPIO_NC_1_HV_DDI0_DDC_SDA, GPIO_NC_1_HV_DDI0_DDC_SDA_PAD, 0 },
+	{ GPIO_NC_2_HV_DDI0_DDC_SCL, GPIO_NC_2_HV_DDI0_DDC_SCL_PAD, 0 },
+	{ GPIO_NC_3_PANEL0_VDDEN, GPIO_NC_3_PANEL0_VDDEN_PAD, 0 },
+	{ GPIO_NC_4_PANEL0_BLKEN, GPIO_NC_4_PANEL0_BLKEN_PAD, 0 },
+	{ GPIO_NC_5_PANEL0_BLKCTL, GPIO_NC_5_PANEL0_BLKCTL_PAD, 0 },
+	{ GPIO_NC_6_PCONF0, GPIO_NC_6_PAD, 0 },
+	{ GPIO_NC_7_PCONF0, GPIO_NC_7_PAD, 0 },
+	{ GPIO_NC_8_PCONF0, GPIO_NC_8_PAD, 0 },
+	{ GPIO_NC_9_PCONF0, GPIO_NC_9_PAD, 0 },
+	{ GPIO_NC_10_PCONF0, GPIO_NC_10_PAD, 0},
+	{ GPIO_NC_11_PCONF0, GPIO_NC_11_PAD, 0}
+};
+
+static u8 *mipi_exec_send_packet(struct intel_dsi *intel_dsi, u8 *data)
+{
+	u8 type, byte, mode, vc, port;
+	u16 len;
+
+	byte = *data++;
+	mode = (byte >> MIPI_TRANSFER_MODE_SHIFT) & 0x1;
+	vc = (byte >> MIPI_VIRTUAL_CHANNEL_SHIFT) & 0x3;
+	port = (byte >> MIPI_PORT_SHIFT) & 0x3;
+
+	/* LP or HS mode */
+	intel_dsi->hs = mode;
+
+	/* get packet type and increment the pointer */
+	type = *data++;
+
+	len = *((u16 *) data);
+	data += 2;
+
+	switch (type) {
+	case MIPI_DSI_GENERIC_SHORT_WRITE_0_PARAM:
+		dsi_vc_generic_write_0(intel_dsi, vc);
+		break;
+	case MIPI_DSI_GENERIC_SHORT_WRITE_1_PARAM:
+		dsi_vc_generic_write_1(intel_dsi, vc, *data);
+		break;
+	case MIPI_DSI_GENERIC_SHORT_WRITE_2_PARAM:
+		dsi_vc_generic_write_2(intel_dsi, vc, *data, *(data + 1));
+		break;
+	case MIPI_DSI_GENERIC_READ_REQUEST_0_PARAM:
+	case MIPI_DSI_GENERIC_READ_REQUEST_1_PARAM:
+	case MIPI_DSI_GENERIC_READ_REQUEST_2_PARAM:
+		DRM_DEBUG_DRIVER("Generic Read not yet implemented or used\n");
+		break;
+	case MIPI_DSI_GENERIC_LONG_WRITE:
+		dsi_vc_generic_write(intel_dsi, vc, data, len);
+		break;
+	case MIPI_DSI_DCS_SHORT_WRITE:
+		dsi_vc_dcs_write_0(intel_dsi, vc, *data);
+		break;
+	case MIPI_DSI_DCS_SHORT_WRITE_PARAM:
+		dsi_vc_dcs_write_1(intel_dsi, vc, *data, *(data + 1));
+		break;
+	case MIPI_DSI_DCS_READ:
+		DRM_DEBUG_DRIVER("DCS Read not yet implemented or used\n");
+		break;
+	case MIPI_DSI_DCS_LONG_WRITE:
+		dsi_vc_dcs_write(intel_dsi, vc, data, len);
+		break;
+	};
+
+	data += len;
+
+	return data;
+}
+
+static u8 *mipi_exec_delay(struct intel_dsi *intel_dsi, u8 *data)
+{
+	u32 delay = *((u32 *) data);
+
+	usleep_range(delay, delay + 10);
+	data += 4;
+
+	return data;
+}
+
+static u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, u8 *data)
+{
+	u8 gpio, action;
+	u16 function, pad;
+	u32 val;
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	gpio = *data++;
+
+	/* pull up/down */
+	action = *data++;
+
+	function = gtable[gpio].function_reg;
+	pad = gtable[gpio].pad_reg;
+
+	mutex_lock(&dev_priv->dpio_lock);
+	if (!gtable[gpio].init) {
+		/* program the function */
+		/* FIXME: remove constant below */
+		vlv_gpio_nc_write(dev_priv, function, 0x2000CC00);
+		gtable[gpio].init = 1;
+	}
+
+	val = 0x4 | action;
+
+	/* pull up/down */
+	vlv_gpio_nc_write(dev_priv, pad, val);
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	return data;
+}
+
+typedef u8 * (*fn_mipi_elem_exec)(struct intel_dsi *intel_dsi, u8 *data);
+static const fn_mipi_elem_exec exec_elem[] = {
+	NULL, /* reserved */
+	mipi_exec_send_packet,
+	mipi_exec_delay,
+	mipi_exec_gpio,
+	NULL, /* status read; later */
+};
+
+/*
+ * MIPI Sequence from VBT #53 parsing logic
+ * We have already separated each seqence during bios parsing
+ * Following is generic execution function for any sequence
+ */
+
+static const char * const seq_name[] = {
+	"UNDEFINED",
+	"MIPI_SEQ_ASSERT_RESET",
+	"MIPI_SEQ_INIT_OTP",
+	"MIPI_SEQ_DISPLAY_ON",
+	"MIPI_SEQ_DISPLAY_OFF",
+	"MIPI_SEQ_DEASSERT_RESET"
+};
+
+static void generic_exec_sequence(struct intel_dsi *intel_dsi, char *sequence)
+{
+	u8 *data = sequence;
+	fn_mipi_elem_exec mipi_elem_exec;
+	int index;
+
+	if (!sequence)
+		return;
+
+	DRM_DEBUG_DRIVER("Starting MIPI sequence - %s\n", seq_name[*data]);
+
+	/* go to the first element of the sequence */
+	data++;
+
+	/* parse each byte till we reach end of sequence byte - 0x00 */
+	while (1) {
+		index = *data;
+		mipi_elem_exec = exec_elem[index];
+		if (!mipi_elem_exec) {
+			DRM_ERROR("Unsupported MIPI element, skipping sequence execution\n");
+			return;
+		}
+
+		/* goto element payload */
+		data++;
+
+		/* execute the element specific rotines */
+		data = mipi_elem_exec(intel_dsi, data);
+
+		/*
+		 * After processing the element, data should point to
+		 * next element or end of sequence
+		 * check if have we reached end of sequence
+		 */
+		if (*data == 0x00)
+			break;
+	}
+}
+
+static bool generic_init(struct intel_dsi_device *dsi)
+{
+	struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev);
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct mipi_config *mipi_config = dev_priv->vbt.dsi.config;
+	struct mipi_pps_data *pps = dev_priv->vbt.dsi.pps;
+	struct drm_display_mode *mode = dev_priv->vbt.lfp_lvds_vbt_mode;
+	u32 bits_per_pixel = 24;
+	u32 tlpx_ns, extra_byte_count, bitrate, tlpx_ui;
+	u32 ui_num, ui_den;
+	u32 prepare_cnt, exit_zero_cnt, clk_zero_cnt, trail_cnt;
+	u32 ths_prepare_ns, tclk_trail_ns;
+	u32 tclk_prepare_clkzero, ths_prepare_hszero;
+	u32 lp_to_hs_switch, hs_to_lp_switch;
+
+	DRM_DEBUG_KMS("\n");
+
+	intel_dsi->eotp_pkt = mipi_config->eot_pkt_disabled ? 0 : 1;
+	intel_dsi->clock_stop = mipi_config->enable_clk_stop ? 1 : 0;
+	intel_dsi->lane_count = mipi_config->lane_cnt + 1;
+	intel_dsi->pixel_format = mipi_config->videomode_color_format << 7;
+
+	if (intel_dsi->pixel_format == VID_MODE_FORMAT_RGB666)
+		bits_per_pixel = 18;
+	else if (intel_dsi->pixel_format == VID_MODE_FORMAT_RGB565)
+		bits_per_pixel = 16;
+
+	bitrate = (mode->clock * bits_per_pixel) / intel_dsi->lane_count;
+
+	intel_dsi->operation_mode = mipi_config->is_cmd_mode;
+	intel_dsi->video_mode_format = mipi_config->video_transfer_mode;
+	intel_dsi->escape_clk_div = mipi_config->byte_clk_sel;
+	intel_dsi->lp_rx_timeout = mipi_config->lp_rx_timeout;
+	intel_dsi->turn_arnd_val = mipi_config->turn_around_timeout;
+	intel_dsi->rst_timer_val = mipi_config->device_reset_timer;
+	intel_dsi->init_count = mipi_config->master_init_timer;
+	intel_dsi->bw_timer = mipi_config->dbi_bw_timer;
+	intel_dsi->video_frmt_cfg_bits = mipi_config->bta_enabled ? DISABLE_VIDEO_BTA : 0;
+
+	switch (intel_dsi->escape_clk_div) {
+	case 0:
+		tlpx_ns = 50;
+		break;
+	case 1:
+		tlpx_ns = 100;
+		break;
+
+	case 2:
+		tlpx_ns = 200;
+		break;
+	default:
+		tlpx_ns = 50;
+		break;
+	}
+
+	switch (intel_dsi->lane_count) {
+	case 1:
+	case 2:
+		extra_byte_count = 2;
+		break;
+	case 3:
+		extra_byte_count = 4;
+		break;
+	case 4:
+	default:
+		extra_byte_count = 3;
+		break;
+	}
+
+	/*
+	 * ui(s) = 1/f [f in hz]
+	 * ui(ns) = 10^9 / (f*10^6) [f in Mhz] -> 10^3/f(Mhz)
+	 */
+
+	/* in Kbps */
+	ui_num = NS_KHZ_RATIO;
+	ui_den = bitrate;
+
+	tclk_prepare_clkzero = mipi_config->tclk_prepare_clkzero;
+	ths_prepare_hszero = mipi_config->ths_prepare_hszero;
+
+	/*
+	 * B060
+	 * LP byte clock = TLPX/ (8UI)
+	 */
+	intel_dsi->lp_byte_clk = DIV_ROUND_UP(tlpx_ns * ui_den, 8 * ui_num);
+
+	/* count values in UI = (ns value) * (bitrate / (2 * 10^6))
+	 *
+	 * Since txddrclkhs_i is 2xUI, all the count values programmed in
+	 * DPHY param register are divided by 2
+	 *
+	 * prepare count
+	 */
+	ths_prepare_ns = max(mipi_config->ths_prepare, mipi_config->tclk_prepare);
+	prepare_cnt = DIV_ROUND_UP(ths_prepare_ns * ui_den, ui_num * 2);
+
+	/* exit zero count */
+	exit_zero_cnt = DIV_ROUND_UP(
+				(ths_prepare_hszero - ths_prepare_ns) * ui_den,
+				ui_num * 2
+				);
+
+	/*
+	 * Exit zero  is unified val ths_zero and ths_exit
+	 * minimum value for ths_exit = 110ns
+	 * min (exit_zero_cnt * 2) = 110/UI
+	 * exit_zero_cnt = 55/UI
+	 */
+	 if (exit_zero_cnt < (55 * ui_den / ui_num))
+		if ((55 * ui_den) % ui_num)
+			exit_zero_cnt += 1;
+
+	/* clk zero count */
+	clk_zero_cnt = DIV_ROUND_UP(
+			(tclk_prepare_clkzero -	ths_prepare_ns)
+			* ui_den, 2 * ui_num);
+
+	/* trail count */
+	tclk_trail_ns = max(mipi_config->tclk_trail, mipi_config->ths_trail);
+	trail_cnt = DIV_ROUND_UP(tclk_trail_ns * ui_den, 2 * ui_num);
+
+	if (prepare_cnt > PREPARE_CNT_MAX ||
+		exit_zero_cnt > EXIT_ZERO_CNT_MAX ||
+		clk_zero_cnt > CLK_ZERO_CNT_MAX ||
+		trail_cnt > TRAIL_CNT_MAX)
+		DRM_DEBUG_DRIVER("Values crossing maximum limits, restricting to max values\n");
+
+	if (prepare_cnt > PREPARE_CNT_MAX)
+		prepare_cnt = PREPARE_CNT_MAX;
+
+	if (exit_zero_cnt > EXIT_ZERO_CNT_MAX)
+		exit_zero_cnt = EXIT_ZERO_CNT_MAX;
+
+	if (clk_zero_cnt > CLK_ZERO_CNT_MAX)
+		clk_zero_cnt = CLK_ZERO_CNT_MAX;
+
+	if (trail_cnt > TRAIL_CNT_MAX)
+		trail_cnt = TRAIL_CNT_MAX;
+
+	/* B080 */
+	intel_dsi->dphy_reg = exit_zero_cnt << 24 | trail_cnt << 16 |
+						clk_zero_cnt << 8 | prepare_cnt;
+
+	/*
+	 * LP to HS switch count = 4TLPX + PREP_COUNT * 2 + EXIT_ZERO_COUNT * 2
+	 *					+ 10UI + Extra Byte Count
+	 *
+	 * HS to LP switch count = THS-TRAIL + 2TLPX + Extra Byte Count
+	 * Extra Byte Count is calculated according to number of lanes.
+	 * High Low Switch Count is the Max of LP to HS and
+	 * HS to LP switch count
+	 *
+	 */
+	tlpx_ui = DIV_ROUND_UP(tlpx_ns * ui_den, ui_num);
+
+	/* B044 */
+	/* FIXME:
+	 * The comment above does not match with the code */
+	lp_to_hs_switch = DIV_ROUND_UP(4 * tlpx_ui + prepare_cnt * 2 +
+						exit_zero_cnt * 2 + 10, 8);
+
+	hs_to_lp_switch = DIV_ROUND_UP(mipi_config->ths_trail + 2 * tlpx_ui, 8);
+
+	intel_dsi->hs_to_lp_count = max(lp_to_hs_switch, hs_to_lp_switch);
+	intel_dsi->hs_to_lp_count += extra_byte_count;
+
+	/* B088 */
+	/* LP -> HS for clock lanes
+	 * LP clk sync + LP11 + LP01 + tclk_prepare + tclk_zero +
+	 *						extra byte count
+	 * 2TPLX + 1TLPX + 1 TPLX(in ns) + prepare_cnt * 2 + clk_zero_cnt *
+	 *					2(in UI) + extra byte count
+	 * In byteclks = (4TLPX + prepare_cnt * 2 + clk_zero_cnt *2 (in UI)) /
+	 *					8 + extra byte count
+	 */
+	intel_dsi->clk_lp_to_hs_count =
+		DIV_ROUND_UP(
+			4 * tlpx_ui + prepare_cnt * 2 +
+			clk_zero_cnt * 2,
+			8);
+
+	intel_dsi->clk_lp_to_hs_count += extra_byte_count;
+
+	/* HS->LP for Clock Lanes
+	 * Low Power clock synchronisations + 1Tx byteclk + tclk_trail +
+	 *						Extra byte count
+	 * 2TLPX + 8UI + (trail_count*2)(in UI) + Extra byte count
+	 * In byteclks = (2*TLpx(in UI) + trail_count*2 +8)(in UI)/8 +
+	 *						Extra byte count
+	 */
+	intel_dsi->clk_hs_to_lp_count =
+		DIV_ROUND_UP(2 * tlpx_ui + trail_cnt * 2 + 8,
+			8);
+	intel_dsi->clk_hs_to_lp_count += extra_byte_count;
+
+	DRM_DEBUG_KMS("Eot %s\n", intel_dsi->eotp_pkt ? "enabled" : "disabled");
+	DRM_DEBUG_KMS("Clockstop %s\n", intel_dsi->clock_stop ?
+						"disabled" : "enabled");
+	DRM_DEBUG_KMS("Mode %s\n", intel_dsi->operation_mode ? "command" : "video");
+	DRM_DEBUG_KMS("Pixel Format %d\n", intel_dsi->pixel_format);
+	DRM_DEBUG_KMS("TLPX %d\n", intel_dsi->escape_clk_div);
+	DRM_DEBUG_KMS("LP RX Timeout 0x%x\n", intel_dsi->lp_rx_timeout);
+	DRM_DEBUG_KMS("Turnaround Timeout 0x%x\n", intel_dsi->turn_arnd_val);
+	DRM_DEBUG_KMS("Init Count 0x%x\n", intel_dsi->init_count);
+	DRM_DEBUG_KMS("HS to LP Count 0x%x\n", intel_dsi->hs_to_lp_count);
+	DRM_DEBUG_KMS("LP Byte Clock %d\n", intel_dsi->lp_byte_clk);
+	DRM_DEBUG_KMS("DBI BW Timer 0x%x\n", intel_dsi->bw_timer);
+	DRM_DEBUG_KMS("LP to HS Clock Count 0x%x\n", intel_dsi->clk_lp_to_hs_count);
+	DRM_DEBUG_KMS("HS to LP Clock Count 0x%x\n", intel_dsi->clk_hs_to_lp_count);
+	DRM_DEBUG_KMS("BTA %s\n",
+			intel_dsi->video_frmt_cfg_bits & DISABLE_VIDEO_BTA ?
+			"disabled" : "enabled");
+
+	/* delays in VBT are in unit of 100us, so need to convert
+	 * here in ms
+	 * Delay (100us) * 100 /1000 = Delay / 10 (ms) */
+	intel_dsi->backlight_off_delay = pps->bl_disable_delay / 10;
+	intel_dsi->backlight_on_delay = pps->bl_enable_delay / 10;
+	intel_dsi->panel_on_delay = pps->panel_on_delay / 10;
+	intel_dsi->panel_off_delay = pps->panel_off_delay / 10;
+	intel_dsi->panel_pwr_cycle_delay = pps->panel_power_cycle_delay / 10;
+
+	return true;
+}
+
+static int generic_mode_valid(struct intel_dsi_device *dsi,
+		   struct drm_display_mode *mode)
+{
+	return MODE_OK;
+}
+
+static bool generic_mode_fixup(struct intel_dsi_device *dsi,
+		    const struct drm_display_mode *mode,
+		    struct drm_display_mode *adjusted_mode) {
+	return true;
+}
+
+static void generic_panel_reset(struct intel_dsi_device *dsi)
+{
+	struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev);
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_ASSERT_RESET];
+
+	generic_exec_sequence(intel_dsi, sequence);
+}
+
+static void generic_disable_panel_power(struct intel_dsi_device *dsi)
+{
+	struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev);
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET];
+
+	generic_exec_sequence(intel_dsi, sequence);
+}
+
+static void generic_send_otp_cmds(struct intel_dsi_device *dsi)
+{
+	struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev);
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_INIT_OTP];
+
+	generic_exec_sequence(intel_dsi, sequence);
+}
+
+static void generic_enable(struct intel_dsi_device *dsi)
+{
+	struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev);
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_ON];
+
+	generic_exec_sequence(intel_dsi, sequence);
+}
+
+static void generic_disable(struct intel_dsi_device *dsi)
+{
+	struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev);
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	char *sequence = dev_priv->vbt.dsi.sequence[MIPI_SEQ_DISPLAY_OFF];
+
+	generic_exec_sequence(intel_dsi, sequence);
+}
+
+static enum drm_connector_status generic_detect(struct intel_dsi_device *dsi)
+{
+	return connector_status_connected;
+}
+
+static bool generic_get_hw_state(struct intel_dsi_device *dev)
+{
+	return true;
+}
+
+static struct drm_display_mode *generic_get_modes(struct intel_dsi_device *dsi)
+{
+	struct intel_dsi *intel_dsi = container_of(dsi, struct intel_dsi, dev);
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	dev_priv->vbt.lfp_lvds_vbt_mode->type |= DRM_MODE_TYPE_PREFERRED;
+	return dev_priv->vbt.lfp_lvds_vbt_mode;
+}
+
+static void generic_destroy(struct intel_dsi_device *dsi) { }
+
+/* Callbacks. We might not need them all. */
+struct intel_dsi_dev_ops vbt_generic_dsi_display_ops = {
+	.init = generic_init,
+	.mode_valid = generic_mode_valid,
+	.mode_fixup = generic_mode_fixup,
+	.panel_reset = generic_panel_reset,
+	.disable_panel_power = generic_disable_panel_power,
+	.send_otp_cmds = generic_send_otp_cmds,
+	.enable = generic_enable,
+	.disable = generic_disable,
+	.detect = generic_detect,
+	.get_hw_state = generic_get_hw_state,
+	.get_modes = generic_get_modes,
+	.destroy = generic_destroy,
+};
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 7fe3feedfe0..a3631c0a5c2 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -285,7 +285,7 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_dvo_mode_set(struct intel_encoder *encoder)
+static void intel_dvo_pre_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -343,7 +343,7 @@ intel_dvo_detect(struct drm_connector *connector, bool force)
 {
 	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector));
+		      connector->base.id, connector->name);
 	return intel_dvo->dev.dev_ops->detect(&intel_dvo->dev);
 }
 
@@ -475,7 +475,7 @@ void intel_dvo_init(struct drm_device *dev)
 	intel_encoder->get_hw_state = intel_dvo_get_hw_state;
 	intel_encoder->get_config = intel_dvo_get_config;
 	intel_encoder->compute_config = intel_dvo_compute_config;
-	intel_encoder->mode_set = intel_dvo_mode_set;
+	intel_encoder->pre_enable = intel_dvo_pre_enable;
 	intel_connector->get_hw_state = intel_dvo_connector_get_hw_state;
 	intel_connector->unregister = intel_connector_unregister;
 
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index f73ba5e6b7a..088fe9378a4 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -343,15 +343,15 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 			num_connectors_detected++;
 
 		if (!enabled[i]) {
-			DRM_DEBUG_KMS("connector %d not enabled, skipping\n",
-				      connector->base.id);
+			DRM_DEBUG_KMS("connector %s not enabled, skipping\n",
+				      connector->name);
 			continue;
 		}
 
 		encoder = connector->encoder;
 		if (!encoder || WARN_ON(!encoder->crtc)) {
-			DRM_DEBUG_KMS("connector %d has no encoder or crtc, skipping\n",
-				      connector->base.id);
+			DRM_DEBUG_KMS("connector %s has no encoder or crtc, skipping\n",
+				      connector->name);
 			enabled[i] = false;
 			continue;
 		}
@@ -373,16 +373,16 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 			}
 		}
 
-		DRM_DEBUG_KMS("looking for cmdline mode on connector %d\n",
-			      fb_conn->connector->base.id);
+		DRM_DEBUG_KMS("looking for cmdline mode on connector %s\n",
+			      connector->name);
 
 		/* go for command line mode first */
 		modes[i] = drm_pick_cmdline_mode(fb_conn, width, height);
 
 		/* try for preferred next */
 		if (!modes[i]) {
-			DRM_DEBUG_KMS("looking for preferred mode on connector %d\n",
-				      fb_conn->connector->base.id);
+			DRM_DEBUG_KMS("looking for preferred mode on connector %s\n",
+				      connector->name);
 			modes[i] = drm_has_preferred_mode(fb_conn, width,
 							  height);
 		}
@@ -390,7 +390,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 		/* No preferred mode marked by the EDID? Are there any modes? */
 		if (!modes[i] && !list_empty(&connector->modes)) {
 			DRM_DEBUG_KMS("using first mode listed on connector %s\n",
-				      drm_get_connector_name(connector));
+				      connector->name);
 			modes[i] = list_first_entry(&connector->modes,
 						    struct drm_display_mode,
 						    head);
@@ -409,16 +409,20 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 			 * since the fb helper layer wants a pointer to
 			 * something we own.
 			 */
+			DRM_DEBUG_KMS("looking for current mode on connector %s\n",
+				      connector->name);
 			intel_mode_from_pipe_config(&encoder->crtc->hwmode,
 						    &to_intel_crtc(encoder->crtc)->config);
 			modes[i] = &encoder->crtc->hwmode;
 		}
 		crtcs[i] = new_crtc;
 
-		DRM_DEBUG_KMS("connector %s on crtc %d: %s\n",
-			      drm_get_connector_name(connector),
+		DRM_DEBUG_KMS("connector %s on pipe %d [CRTC:%d]: %dx%d%s\n",
+			      connector->name,
+			      pipe_name(to_intel_crtc(encoder->crtc)->pipe),
 			      encoder->crtc->base.id,
-			      modes[i]->name);
+			      modes[i]->hdisplay, modes[i]->vdisplay,
+			      modes[i]->flags & DRM_MODE_FLAG_INTERLACE ? "i" :"");
 
 		fallback = false;
 	}
@@ -497,7 +501,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 		return false;
 
 	/* Find the largest fb */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		intel_crtc = to_intel_crtc(crtc);
 
 		if (!intel_crtc->active || !crtc->primary->fb) {
@@ -521,7 +525,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 	}
 
 	/* Now make sure all the pipes will fit into it */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		unsigned int cur_size;
 
 		intel_crtc = to_intel_crtc(crtc);
@@ -586,7 +590,7 @@ static bool intel_fbdev_init_bios(struct drm_device *dev,
 	drm_framebuffer_reference(&ifbdev->fb->base);
 
 	/* Final pass to check if any active pipes don't have fbs */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		intel_crtc = to_intel_crtc(crtc);
 
 		if (!intel_crtc->active)
@@ -692,11 +696,7 @@ void intel_fbdev_restore_mode(struct drm_device *dev)
 	if (!dev_priv->fbdev)
 		return;
 
-	drm_modeset_lock_all(dev);
-
-	ret = drm_fb_helper_restore_fbdev_mode(&dev_priv->fbdev->helper);
+	ret = drm_fb_helper_restore_fbdev_mode_unlocked(&dev_priv->fbdev->helper);
 	if (ret)
 		DRM_DEBUG("failed to restore crtc mode\n");
-
-	drm_modeset_unlock_all(dev);
 }
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 157267aa356..eee2bbec295 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -418,6 +418,7 @@ intel_hdmi_set_hdmi_infoframe(struct drm_encoder *encoder,
 }
 
 static void g4x_set_infoframes(struct drm_encoder *encoder,
+			       bool enable,
 			       struct drm_display_mode *adjusted_mode)
 {
 	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
@@ -440,7 +441,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder,
 	 * either. */
 	val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC;
 
-	if (!intel_hdmi->has_hdmi_sink) {
+	if (!enable) {
 		if (!(val & VIDEO_DIP_ENABLE))
 			return;
 		val &= ~VIDEO_DIP_ENABLE;
@@ -471,6 +472,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder,
 }
 
 static void ibx_set_infoframes(struct drm_encoder *encoder,
+			       bool enable,
 			       struct drm_display_mode *adjusted_mode)
 {
 	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
@@ -486,7 +488,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder,
 	/* See the big comment in g4x_set_infoframes() */
 	val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC;
 
-	if (!intel_hdmi->has_hdmi_sink) {
+	if (!enable) {
 		if (!(val & VIDEO_DIP_ENABLE))
 			return;
 		val &= ~VIDEO_DIP_ENABLE;
@@ -518,6 +520,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder,
 }
 
 static void cpt_set_infoframes(struct drm_encoder *encoder,
+			       bool enable,
 			       struct drm_display_mode *adjusted_mode)
 {
 	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
@@ -531,7 +534,7 @@ static void cpt_set_infoframes(struct drm_encoder *encoder,
 	/* See the big comment in g4x_set_infoframes() */
 	val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC;
 
-	if (!intel_hdmi->has_hdmi_sink) {
+	if (!enable) {
 		if (!(val & VIDEO_DIP_ENABLE))
 			return;
 		val &= ~(VIDEO_DIP_ENABLE | VIDEO_DIP_ENABLE_AVI);
@@ -554,20 +557,23 @@ static void cpt_set_infoframes(struct drm_encoder *encoder,
 }
 
 static void vlv_set_infoframes(struct drm_encoder *encoder,
+			       bool enable,
 			       struct drm_display_mode *adjusted_mode)
 {
 	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->crtc);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	u32 reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
+	u32 port = VIDEO_DIP_PORT(intel_dig_port->port);
 
 	assert_hdmi_port_disabled(intel_hdmi);
 
 	/* See the big comment in g4x_set_infoframes() */
 	val |= VIDEO_DIP_SELECT_AVI | VIDEO_DIP_FREQ_VSYNC;
 
-	if (!intel_hdmi->has_hdmi_sink) {
+	if (!enable) {
 		if (!(val & VIDEO_DIP_ENABLE))
 			return;
 		val &= ~VIDEO_DIP_ENABLE;
@@ -576,9 +582,19 @@ static void vlv_set_infoframes(struct drm_encoder *encoder,
 		return;
 	}
 
+	if (port != (val & VIDEO_DIP_PORT_MASK)) {
+		if (val & VIDEO_DIP_ENABLE) {
+			val &= ~VIDEO_DIP_ENABLE;
+			I915_WRITE(reg, val);
+			POSTING_READ(reg);
+		}
+		val &= ~VIDEO_DIP_PORT_MASK;
+		val |= port;
+	}
+
 	val |= VIDEO_DIP_ENABLE;
-	val &= ~(VIDEO_DIP_ENABLE_VENDOR | VIDEO_DIP_ENABLE_GAMUT |
-		 VIDEO_DIP_ENABLE_GCP);
+	val &= ~(VIDEO_DIP_ENABLE_AVI | VIDEO_DIP_ENABLE_VENDOR |
+		 VIDEO_DIP_ENABLE_GAMUT | VIDEO_DIP_ENABLE_GCP);
 
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
@@ -589,6 +605,7 @@ static void vlv_set_infoframes(struct drm_encoder *encoder,
 }
 
 static void hsw_set_infoframes(struct drm_encoder *encoder,
+			       bool enable,
 			       struct drm_display_mode *adjusted_mode)
 {
 	struct drm_i915_private *dev_priv = encoder->dev->dev_private;
@@ -599,7 +616,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 
 	assert_hdmi_port_disabled(intel_hdmi);
 
-	if (!intel_hdmi->has_hdmi_sink) {
+	if (!enable) {
 		I915_WRITE(reg, 0);
 		POSTING_READ(reg);
 		return;
@@ -616,7 +633,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 	intel_hdmi_set_hdmi_infoframe(encoder, adjusted_mode);
 }
 
-static void intel_hdmi_mode_set(struct intel_encoder *encoder)
+static void intel_hdmi_prepare(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -638,27 +655,26 @@ static void intel_hdmi_mode_set(struct intel_encoder *encoder)
 	else
 		hdmi_val |= SDVO_COLOR_FORMAT_8bpc;
 
-	/* Required on CPT */
-	if (intel_hdmi->has_hdmi_sink && HAS_PCH_CPT(dev))
+	if (crtc->config.has_hdmi_sink)
 		hdmi_val |= HDMI_MODE_SELECT_HDMI;
 
-	if (intel_hdmi->has_audio) {
+	if (crtc->config.has_audio) {
+		WARN_ON(!crtc->config.has_hdmi_sink);
 		DRM_DEBUG_DRIVER("Enabling HDMI audio on pipe %c\n",
 				 pipe_name(crtc->pipe));
 		hdmi_val |= SDVO_AUDIO_ENABLE;
-		hdmi_val |= HDMI_MODE_SELECT_HDMI;
 		intel_write_eld(&encoder->base, adjusted_mode);
 	}
 
 	if (HAS_PCH_CPT(dev))
 		hdmi_val |= SDVO_PIPE_SEL_CPT(crtc->pipe);
+	else if (IS_CHERRYVIEW(dev))
+		hdmi_val |= SDVO_PIPE_SEL_CHV(crtc->pipe);
 	else
 		hdmi_val |= SDVO_PIPE_SEL(crtc->pipe);
 
 	I915_WRITE(intel_hdmi->hdmi_reg, hdmi_val);
 	POSTING_READ(intel_hdmi->hdmi_reg);
-
-	intel_hdmi->set_infoframes(&encoder->base, adjusted_mode);
 }
 
 static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
@@ -681,6 +697,8 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 
 	if (HAS_PCH_CPT(dev))
 		*pipe = PORT_TO_PIPE_CPT(tmp);
+	else if (IS_CHERRYVIEW(dev))
+		*pipe = SDVO_PORT_TO_PIPE_CHV(tmp);
 	else
 		*pipe = PORT_TO_PIPE(tmp);
 
@@ -707,6 +725,12 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder,
 	else
 		flags |= DRM_MODE_FLAG_NVSYNC;
 
+	if (tmp & HDMI_MODE_SELECT_HDMI)
+		pipe_config->has_hdmi_sink = true;
+
+	if (tmp & HDMI_MODE_SELECT_HDMI)
+		pipe_config->has_audio = true;
+
 	pipe_config->adjusted_mode.flags |= flags;
 
 	if ((tmp & SDVO_COLOR_FORMAT_MASK) == HDMI_COLOR_FORMAT_12bpc)
@@ -729,7 +753,7 @@ static void intel_enable_hdmi(struct intel_encoder *encoder)
 	u32 temp;
 	u32 enable_bits = SDVO_ENABLE;
 
-	if (intel_hdmi->has_audio)
+	if (intel_crtc->config.has_audio)
 		enable_bits |= SDVO_AUDIO_ENABLE;
 
 	temp = I915_READ(intel_hdmi->hdmi_reg);
@@ -883,9 +907,11 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	int portclock_limit = hdmi_portclock_limit(intel_hdmi, false);
 	int desired_bpp;
 
+	pipe_config->has_hdmi_sink = intel_hdmi->has_hdmi_sink;
+
 	if (intel_hdmi->color_range_auto) {
 		/* See CEA-861-E - 5.1 Default Encoding Parameters */
-		if (intel_hdmi->has_hdmi_sink &&
+		if (pipe_config->has_hdmi_sink &&
 		    drm_match_cea_mode(adjusted_mode) > 1)
 			intel_hdmi->color_range = HDMI_COLOR_RANGE_16_235;
 		else
@@ -898,13 +924,16 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (HAS_PCH_SPLIT(dev) && !HAS_DDI(dev))
 		pipe_config->has_pch_encoder = true;
 
+	if (pipe_config->has_hdmi_sink && intel_hdmi->has_audio)
+		pipe_config->has_audio = true;
+
 	/*
 	 * HDMI is either 12 or 8, so if the display lets 10bpc sneak
 	 * through, clamp it down. Note that g4x/vlv don't support 12bpc hdmi
 	 * outputs. We also need to check that the higher clock still fits
 	 * within limits.
 	 */
-	if (pipe_config->pipe_bpp > 8*3 && intel_hdmi->has_hdmi_sink &&
+	if (pipe_config->pipe_bpp > 8*3 && pipe_config->has_hdmi_sink &&
 	    clock_12bpc <= portclock_limit &&
 	    hdmi_12bpc_possible(encoder->new_crtc)) {
 		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
@@ -944,7 +973,7 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status status = connector_status_disconnected;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector));
+		      connector->base.id, connector->name);
 
 	power_domain = intel_display_port_power_domain(intel_encoder);
 	intel_display_power_get(dev_priv, power_domain);
@@ -1104,20 +1133,34 @@ done:
 	return 0;
 }
 
+static void intel_hdmi_pre_enable(struct intel_encoder *encoder)
+{
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
+	struct drm_display_mode *adjusted_mode =
+		&intel_crtc->config.adjusted_mode;
+
+	intel_hdmi_prepare(encoder);
+
+	intel_hdmi->set_infoframes(&encoder->base,
+				   intel_crtc->config.has_hdmi_sink,
+				   adjusted_mode);
+}
+
 static void vlv_hdmi_pre_enable(struct intel_encoder *encoder)
 {
 	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_hdmi *intel_hdmi = &dport->hdmi;
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc =
 		to_intel_crtc(encoder->base.crtc);
+	struct drm_display_mode *adjusted_mode =
+		&intel_crtc->config.adjusted_mode;
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
 	u32 val;
 
-	if (!IS_VALLEYVIEW(dev))
-		return;
-
 	/* Enable clock channels for this port */
 	mutex_lock(&dev_priv->dpio_lock);
 	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(port));
@@ -1144,6 +1187,10 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder)
 	vlv_dpio_write(dev_priv, pipe, VLV_PCS_DW23(port), 0x00400888);
 	mutex_unlock(&dev_priv->dpio_lock);
 
+	intel_hdmi->set_infoframes(&encoder->base,
+				   intel_crtc->config.has_hdmi_sink,
+				   adjusted_mode);
+
 	intel_enable_hdmi(encoder);
 
 	vlv_wait_port_ready(dev_priv, dport);
@@ -1159,8 +1206,7 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	int pipe = intel_crtc->pipe;
 
-	if (!IS_VALLEYVIEW(dev))
-		return;
+	intel_hdmi_prepare(encoder);
 
 	/* Program Tx lane resets to default */
 	mutex_lock(&dev_priv->dpio_lock);
@@ -1199,6 +1245,152 @@ static void vlv_hdmi_post_disable(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
+static void chv_hdmi_post_disable(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	enum pipe pipe = intel_crtc->pipe;
+	u32 val;
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* Propagate soft reset to data lane reset */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
+	val |= CHV_PCS_REQ_SOFTRESET_EN;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
+	val |= CHV_PCS_REQ_SOFTRESET_EN;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
+	val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
+	val &= ~(DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+
+	mutex_unlock(&dev_priv->dpio_lock);
+}
+
+static void chv_hdmi_pre_enable(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	int pipe = intel_crtc->pipe;
+	int data, i;
+	u32 val;
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* Deassert soft data lane reset*/
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW1(ch));
+	val |= CHV_PCS_REQ_SOFTRESET_EN;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW1(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW1(ch));
+	val |= CHV_PCS_REQ_SOFTRESET_EN;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW1(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW0(ch));
+	val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW0(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW0(ch));
+	val |= (DPIO_PCS_TX_LANE2_RESET | DPIO_PCS_TX_LANE1_RESET);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW0(ch), val);
+
+	/* Program Tx latency optimal setting */
+	for (i = 0; i < 4; i++) {
+		/* Set the latency optimal bit */
+		data = (i == 1) ? 0x0 : 0x6;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW11(ch, i),
+				data << DPIO_FRC_LATENCY_SHFIT);
+
+		/* Set the upar bit */
+		data = (i == 1) ? 0x0 : 0x1;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW14(ch, i),
+				data << DPIO_UPAR_SHIFT);
+	}
+
+	/* Data lane stagger programming */
+	/* FIXME: Fix up value only after power analysis */
+
+	/* Clear calc init */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
+	val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
+	val &= ~(DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3);
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+
+	/* FIXME: Program the support xxx V-dB */
+	/* Use 800mV-0dB */
+	for (i = 0; i < 4; i++) {
+		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW4(ch, i));
+		val &= ~DPIO_SWING_DEEMPH9P5_MASK;
+		val |= 128 << DPIO_SWING_DEEMPH9P5_SHIFT;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW4(ch, i), val);
+	}
+
+	for (i = 0; i < 4; i++) {
+		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW2(ch, i));
+		val &= ~DPIO_SWING_MARGIN_MASK;
+		val |= 102 << DPIO_SWING_MARGIN_SHIFT;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW2(ch, i), val);
+	}
+
+	/* Disable unique transition scale */
+	for (i = 0; i < 4; i++) {
+		val = vlv_dpio_read(dev_priv, pipe, CHV_TX_DW3(ch, i));
+		val &= ~DPIO_TX_UNIQ_TRANS_SCALE_EN;
+		vlv_dpio_write(dev_priv, pipe, CHV_TX_DW3(ch, i), val);
+	}
+
+	/* Additional steps for 1200mV-0dB */
+#if 0
+	val = vlv_dpio_read(dev_priv, pipe, VLV_TX_DW3(ch));
+	if (ch)
+		val |= DPIO_TX_UNIQ_TRANS_SCALE_CH1;
+	else
+		val |= DPIO_TX_UNIQ_TRANS_SCALE_CH0;
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW3(ch), val);
+
+	vlv_dpio_write(dev_priv, pipe, VLV_TX_DW2(ch),
+			vlv_dpio_read(dev_priv, pipe, VLV_TX_DW2(ch)) |
+				(0x9a << DPIO_UNIQ_TRANS_SCALE_SHIFT));
+#endif
+	/* Start swing calculation */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW10(ch));
+	val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW10(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW10(ch));
+	val |= DPIO_PCS_SWING_CALC_TX0_TX2 | DPIO_PCS_SWING_CALC_TX1_TX3;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW10(ch), val);
+
+	/* LRC Bypass */
+	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW30);
+	val |= DPIO_LRC_BYPASS;
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW30, val);
+
+	mutex_unlock(&dev_priv->dpio_lock);
+
+	intel_enable_hdmi(encoder);
+
+	vlv_wait_port_ready(dev_priv, dport);
+}
+
 static void intel_hdmi_destroy(struct drm_connector *connector)
 {
 	drm_connector_cleanup(connector);
@@ -1259,7 +1451,10 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 		intel_encoder->hpd_pin = HPD_PORT_C;
 		break;
 	case PORT_D:
-		intel_hdmi->ddc_bus = GMBUS_PORT_DPD;
+		if (IS_CHERRYVIEW(dev))
+			intel_hdmi->ddc_bus = GMBUS_PORT_DPD_CHV;
+		else
+			intel_hdmi->ddc_bus = GMBUS_PORT_DPD;
 		intel_encoder->hpd_pin = HPD_PORT_D;
 		break;
 	case PORT_A:
@@ -1329,21 +1524,32 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port)
 			 DRM_MODE_ENCODER_TMDS);
 
 	intel_encoder->compute_config = intel_hdmi_compute_config;
-	intel_encoder->mode_set = intel_hdmi_mode_set;
 	intel_encoder->disable = intel_disable_hdmi;
 	intel_encoder->get_hw_state = intel_hdmi_get_hw_state;
 	intel_encoder->get_config = intel_hdmi_get_config;
-	if (IS_VALLEYVIEW(dev)) {
+	if (IS_CHERRYVIEW(dev)) {
+		intel_encoder->pre_enable = chv_hdmi_pre_enable;
+		intel_encoder->enable = vlv_enable_hdmi;
+		intel_encoder->post_disable = chv_hdmi_post_disable;
+	} else if (IS_VALLEYVIEW(dev)) {
 		intel_encoder->pre_pll_enable = vlv_hdmi_pre_pll_enable;
 		intel_encoder->pre_enable = vlv_hdmi_pre_enable;
 		intel_encoder->enable = vlv_enable_hdmi;
 		intel_encoder->post_disable = vlv_hdmi_post_disable;
 	} else {
+		intel_encoder->pre_enable = intel_hdmi_pre_enable;
 		intel_encoder->enable = intel_enable_hdmi;
 	}
 
 	intel_encoder->type = INTEL_OUTPUT_HDMI;
-	intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
+	if (IS_CHERRYVIEW(dev)) {
+		if (port == PORT_D)
+			intel_encoder->crtc_mask = 1 << 2;
+		else
+			intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
+	} else {
+		intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
+	}
 	intel_encoder->cloneable = 1 << INTEL_OUTPUT_ANALOG;
 	/*
 	 * BSpec is unclear about HDMI+HDMI cloning on g4x, but it seems
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index f1ecf916474..5e5a72fca5f 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -126,10 +126,6 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 	pipe_config->adjusted_mode.crtc_clock = dotclock;
 }
 
-/* The LVDS pin pair needs to be on before the DPLLs are enabled.
- * This is an exception to the general rule that mode_set doesn't turn
- * things on.
- */
 static void intel_pre_enable_lvds(struct intel_encoder *encoder)
 {
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
@@ -331,15 +327,6 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	return true;
 }
 
-static void intel_lvds_mode_set(struct intel_encoder *encoder)
-{
-	/*
-	 * We don't do anything here, the LVDS port is fully set up in the pre
-	 * enable hook - the ordering constraints for enabling the lvds port vs.
-	 * enabling the display pll are too strict.
-	 */
-}
-
 /**
  * Detect the LVDS connection.
  *
@@ -354,7 +341,7 @@ intel_lvds_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status status;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector));
+		      connector->base.id, connector->name);
 
 	status = intel_panel_detect(dev);
 	if (status != connector_status_unknown)
@@ -953,7 +940,6 @@ void intel_lvds_init(struct drm_device *dev)
 	intel_encoder->enable = intel_enable_lvds;
 	intel_encoder->pre_enable = intel_pre_enable_lvds;
 	intel_encoder->compute_config = intel_lvds_compute_config;
-	intel_encoder->mode_set = intel_lvds_mode_set;
 	intel_encoder->disable = intel_disable_lvds;
 	intel_encoder->get_hw_state = intel_lvds_get_hw_state;
 	intel_encoder->get_config = intel_lvds_get_config;
diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index acde2945eb8..4f6b53998d7 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -403,6 +403,15 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 
 	DRM_DEBUG_DRIVER("bclp = 0x%08x\n", bclp);
 
+	/*
+	 * If the acpi_video interface is not supposed to be used, don't
+	 * bother processing backlight level change requests from firmware.
+	 */
+	if (!acpi_video_verify_backlight_support()) {
+		DRM_DEBUG_KMS("opregion backlight request ignored\n");
+		return 0;
+	}
+
 	if (!(bclp & ASLE_BCLP_VALID))
 		return ASLC_BACKLIGHT_FAILED;
 
@@ -410,7 +419,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 	if (bclp > 255)
 		return ASLC_BACKLIGHT_FAILED;
 
-	mutex_lock(&dev->mode_config.mutex);
+	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 
 	/*
 	 * Update backlight on all connectors that support backlight (usually
@@ -421,7 +430,7 @@ static u32 asle_set_backlight(struct drm_device *dev, u32 bclp)
 		intel_panel_set_backlight(intel_connector, bclp, 255);
 	iowrite32(DIV_ROUND_UP(bclp * 100, 255) | ASLE_CBLV_VALID, &asle->cblv);
 
-	mutex_unlock(&dev->mode_config.mutex);
+	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 129db0c7d83..daa118978ee 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -213,7 +213,7 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
 {
 	struct drm_device *dev = overlay->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
 	int ret;
 
 	BUG_ON(overlay->last_flip_req);
@@ -236,7 +236,7 @@ static int intel_overlay_on(struct intel_overlay *overlay)
 {
 	struct drm_device *dev = overlay->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
 	int ret;
 
 	BUG_ON(overlay->active);
@@ -263,7 +263,7 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
 {
 	struct drm_device *dev = overlay->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
 	u32 flip_addr = overlay->flip_addr;
 	u32 tmp;
 	int ret;
@@ -320,7 +320,7 @@ static int intel_overlay_off(struct intel_overlay *overlay)
 {
 	struct drm_device *dev = overlay->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
 	u32 flip_addr = overlay->flip_addr;
 	int ret;
 
@@ -363,7 +363,7 @@ static int intel_overlay_recover_from_interrupt(struct intel_overlay *overlay)
 {
 	struct drm_device *dev = overlay->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
 	int ret;
 
 	if (overlay->last_flip_req == 0)
@@ -389,7 +389,7 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
 {
 	struct drm_device *dev = overlay->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
 	int ret;
 
 	/* Only wait if there is actually an old frame to release to
@@ -688,7 +688,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	u32 swidth, swidthsw, sheight, ostride;
 
 	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
-	BUG_ON(!mutex_is_locked(&dev->mode_config.mutex));
+	BUG_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
 	BUG_ON(!overlay);
 
 	ret = intel_overlay_release_old_vid(overlay);
@@ -793,7 +793,7 @@ int intel_overlay_switch_off(struct intel_overlay *overlay)
 	int ret;
 
 	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
-	BUG_ON(!mutex_is_locked(&dev->mode_config.mutex));
+	BUG_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
 
 	ret = intel_overlay_recover_from_interrupt(overlay);
 	if (ret != 0)
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index cb8cfb7e097..12b02fe1d0a 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -42,6 +42,59 @@ intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode,
 	drm_mode_set_crtcinfo(adjusted_mode, 0);
 }
 
+/**
+ * intel_find_panel_downclock - find the reduced downclock for LVDS in EDID
+ * @dev: drm device
+ * @fixed_mode : panel native mode
+ * @connector: LVDS/eDP connector
+ *
+ * Return downclock_avail
+ * Find the reduced downclock for LVDS/eDP in EDID.
+ */
+struct drm_display_mode *
+intel_find_panel_downclock(struct drm_device *dev,
+			struct drm_display_mode *fixed_mode,
+			struct drm_connector *connector)
+{
+	struct drm_display_mode *scan, *tmp_mode;
+	int temp_downclock;
+
+	temp_downclock = fixed_mode->clock;
+	tmp_mode = NULL;
+
+	list_for_each_entry(scan, &connector->probed_modes, head) {
+		/*
+		 * If one mode has the same resolution with the fixed_panel
+		 * mode while they have the different refresh rate, it means
+		 * that the reduced downclock is found. In such
+		 * case we can set the different FPx0/1 to dynamically select
+		 * between low and high frequency.
+		 */
+		if (scan->hdisplay == fixed_mode->hdisplay &&
+		    scan->hsync_start == fixed_mode->hsync_start &&
+		    scan->hsync_end == fixed_mode->hsync_end &&
+		    scan->htotal == fixed_mode->htotal &&
+		    scan->vdisplay == fixed_mode->vdisplay &&
+		    scan->vsync_start == fixed_mode->vsync_start &&
+		    scan->vsync_end == fixed_mode->vsync_end &&
+		    scan->vtotal == fixed_mode->vtotal) {
+			if (scan->clock < temp_downclock) {
+				/*
+				 * The downclock is already found. But we
+				 * expect to find the lower downclock.
+				 */
+				temp_downclock = scan->clock;
+				tmp_mode = scan;
+			}
+		}
+	}
+
+	if (temp_downclock < fixed_mode->clock)
+		return drm_mode_duplicate(dev, tmp_mode);
+	else
+		return NULL;
+}
+
 /* adjusted_mode has been preset to be the panel's fixed mode */
 void
 intel_pch_panel_fitting(struct intel_crtc *intel_crtc,
@@ -323,6 +376,28 @@ out:
 	pipe_config->gmch_pfit.lvds_border_bits = border;
 }
 
+enum drm_connector_status
+intel_panel_detect(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* Assume that the BIOS does not lie through the OpRegion... */
+	if (!i915.panel_ignore_lid && dev_priv->opregion.lid_state) {
+		return ioread32(dev_priv->opregion.lid_state) & 0x1 ?
+			connector_status_connected :
+			connector_status_disconnected;
+	}
+
+	switch (i915.panel_ignore_lid) {
+	case -2:
+		return connector_status_connected;
+	case -1:
+		return connector_status_disconnected;
+	default:
+		return connector_status_unknown;
+	}
+}
+
 static u32 intel_panel_compute_brightness(struct intel_connector *connector,
 					  u32 val)
 {
@@ -723,9 +798,6 @@ static void i965_enable_backlight(struct intel_connector *connector)
 	ctl = freq << 16;
 	I915_WRITE(BLC_PWM_CTL, ctl);
 
-	/* XXX: combine this into above write? */
-	intel_panel_actually_set_backlight(connector, panel->backlight.level);
-
 	ctl2 = BLM_PIPE(pipe);
 	if (panel->backlight.combination_mode)
 		ctl2 |= BLM_COMBINATION_MODE;
@@ -734,6 +806,8 @@ static void i965_enable_backlight(struct intel_connector *connector)
 	I915_WRITE(BLC_PWM_CTL2, ctl2);
 	POSTING_READ(BLC_PWM_CTL2);
 	I915_WRITE(BLC_PWM_CTL2, ctl2 | BLM_PWM_ENABLE);
+
+	intel_panel_actually_set_backlight(connector, panel->backlight.level);
 }
 
 static void vlv_enable_backlight(struct intel_connector *connector)
@@ -795,40 +869,18 @@ void intel_panel_enable_backlight(struct intel_connector *connector)
 	spin_unlock_irqrestore(&dev_priv->backlight_lock, flags);
 }
 
-enum drm_connector_status
-intel_panel_detect(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	/* Assume that the BIOS does not lie through the OpRegion... */
-	if (!i915.panel_ignore_lid && dev_priv->opregion.lid_state) {
-		return ioread32(dev_priv->opregion.lid_state) & 0x1 ?
-			connector_status_connected :
-			connector_status_disconnected;
-	}
-
-	switch (i915.panel_ignore_lid) {
-	case -2:
-		return connector_status_connected;
-	case -1:
-		return connector_status_disconnected;
-	default:
-		return connector_status_unknown;
-	}
-}
-
 #if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE)
 static int intel_backlight_device_update_status(struct backlight_device *bd)
 {
 	struct intel_connector *connector = bl_get_data(bd);
 	struct drm_device *dev = connector->base.dev;
 
-	mutex_lock(&dev->mode_config.mutex);
+	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 	DRM_DEBUG_KMS("updating intel_backlight, brightness=%d/%d\n",
 		      bd->props.brightness, bd->props.max_brightness);
 	intel_panel_set_backlight(connector, bd->props.brightness,
 				  bd->props.max_brightness);
-	mutex_unlock(&dev->mode_config.mutex);
+	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 	return 0;
 }
 
@@ -840,9 +892,9 @@ static int intel_backlight_device_get_brightness(struct backlight_device *bd)
 	int ret;
 
 	intel_runtime_pm_get(dev_priv);
-	mutex_lock(&dev->mode_config.mutex);
+	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
 	ret = intel_panel_get_backlight(connector);
-	mutex_unlock(&dev->mode_config.mutex);
+	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 	intel_runtime_pm_put(dev_priv);
 
 	return ret;
@@ -1066,8 +1118,12 @@ int intel_panel_setup_backlight(struct drm_connector *connector)
 	int ret;
 
 	if (!dev_priv->vbt.backlight.present) {
-		DRM_DEBUG_KMS("native backlight control not available per VBT\n");
-		return 0;
+		if (dev_priv->quirks & QUIRK_BACKLIGHT_PRESENT) {
+			DRM_DEBUG_KMS("no backlight present per VBT, but present per quirk\n");
+		} else {
+			DRM_DEBUG_KMS("no backlight present per VBT\n");
+			return 0;
+		}
 	}
 
 	/* set level and max in panel struct */
@@ -1077,7 +1133,7 @@ int intel_panel_setup_backlight(struct drm_connector *connector)
 
 	if (ret) {
 		DRM_DEBUG_KMS("failed to setup backlight for connector %s\n",
-			      drm_get_connector_name(connector));
+			      connector->name);
 		return ret;
 	}
 
@@ -1103,59 +1159,6 @@ void intel_panel_destroy_backlight(struct drm_connector *connector)
 	intel_backlight_device_unregister(intel_connector);
 }
 
-/**
- * intel_find_panel_downclock - find the reduced downclock for LVDS in EDID
- * @dev: drm device
- * @fixed_mode : panel native mode
- * @connector: LVDS/eDP connector
- *
- * Return downclock_avail
- * Find the reduced downclock for LVDS/eDP in EDID.
- */
-struct drm_display_mode *
-intel_find_panel_downclock(struct drm_device *dev,
-			struct drm_display_mode *fixed_mode,
-			struct drm_connector *connector)
-{
-	struct drm_display_mode *scan, *tmp_mode;
-	int temp_downclock;
-
-	temp_downclock = fixed_mode->clock;
-	tmp_mode = NULL;
-
-	list_for_each_entry(scan, &connector->probed_modes, head) {
-		/*
-		 * If one mode has the same resolution with the fixed_panel
-		 * mode while they have the different refresh rate, it means
-		 * that the reduced downclock is found. In such
-		 * case we can set the different FPx0/1 to dynamically select
-		 * between low and high frequency.
-		 */
-		if (scan->hdisplay == fixed_mode->hdisplay &&
-		    scan->hsync_start == fixed_mode->hsync_start &&
-		    scan->hsync_end == fixed_mode->hsync_end &&
-		    scan->htotal == fixed_mode->htotal &&
-		    scan->vdisplay == fixed_mode->vdisplay &&
-		    scan->vsync_start == fixed_mode->vsync_start &&
-		    scan->vsync_end == fixed_mode->vsync_end &&
-		    scan->vtotal == fixed_mode->vtotal) {
-			if (scan->clock < temp_downclock) {
-				/*
-				 * The downclock is already found. But we
-				 * expect to find the lower downclock.
-				 */
-				temp_downclock = scan->clock;
-				tmp_mode = scan;
-			}
-		}
-	}
-
-	if (temp_downclock < fixed_mode->clock)
-		return drm_mode_duplicate(dev, tmp_mode);
-	else
-		return NULL;
-}
-
 /* Set up chip specific backlight functions */
 void intel_panel_init_backlight_funcs(struct drm_device *dev)
 {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d93dcf683e8..ee72807069e 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -487,7 +487,7 @@ void intel_update_fbc(struct drm_device *dev)
 	 *   - new fb is too large to fit in compressed buffer
 	 *   - going to an unsupported config (interlace, pixel multiply, etc.)
 	 */
-	list_for_each_entry(tmp_crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, tmp_crtc) {
 		if (intel_crtc_active(tmp_crtc) &&
 		    to_intel_crtc(tmp_crtc)->primary_enabled) {
 			if (crtc) {
@@ -511,8 +511,7 @@ void intel_update_fbc(struct drm_device *dev)
 	obj = intel_fb->obj;
 	adjusted_mode = &intel_crtc->config.adjusted_mode;
 
-	if (i915.enable_fbc < 0 &&
-	    INTEL_INFO(dev)->gen <= 7 && !IS_HASWELL(dev)) {
+	if (i915.enable_fbc < 0) {
 		if (set_no_fbc_reason(dev_priv, FBC_CHIP_DEFAULT))
 			DRM_DEBUG_KMS("disabled per chip default\n");
 		goto out_disable;
@@ -1010,7 +1009,7 @@ static struct drm_crtc *single_enabled_crtc(struct drm_device *dev)
 {
 	struct drm_crtc *crtc, *enabled = NULL;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+	for_each_crtc(dev, crtc) {
 		if (intel_crtc_active(crtc)) {
 			if (enabled)
 				return NULL;
@@ -1831,6 +1830,40 @@ static unsigned int ilk_display_fifo_size(const struct drm_device *dev)
 		return 512;
 }
 
+static unsigned int ilk_plane_wm_reg_max(const struct drm_device *dev,
+					 int level, bool is_sprite)
+{
+	if (INTEL_INFO(dev)->gen >= 8)
+		/* BDW primary/sprite plane watermarks */
+		return level == 0 ? 255 : 2047;
+	else if (INTEL_INFO(dev)->gen >= 7)
+		/* IVB/HSW primary/sprite plane watermarks */
+		return level == 0 ? 127 : 1023;
+	else if (!is_sprite)
+		/* ILK/SNB primary plane watermarks */
+		return level == 0 ? 127 : 511;
+	else
+		/* ILK/SNB sprite plane watermarks */
+		return level == 0 ? 63 : 255;
+}
+
+static unsigned int ilk_cursor_wm_reg_max(const struct drm_device *dev,
+					  int level)
+{
+	if (INTEL_INFO(dev)->gen >= 7)
+		return level == 0 ? 63 : 255;
+	else
+		return level == 0 ? 31 : 63;
+}
+
+static unsigned int ilk_fbc_wm_reg_max(const struct drm_device *dev)
+{
+	if (INTEL_INFO(dev)->gen >= 8)
+		return 31;
+	else
+		return 15;
+}
+
 /* Calculate the maximum primary/sprite plane watermark */
 static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
 				     int level,
@@ -1839,7 +1872,6 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
 				     bool is_sprite)
 {
 	unsigned int fifo_size = ilk_display_fifo_size(dev);
-	unsigned int max;
 
 	/* if sprites aren't enabled, sprites get nothing */
 	if (is_sprite && !config->sprites_enabled)
@@ -1870,19 +1902,7 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev,
 	}
 
 	/* clamp to max that the registers can hold */
-	if (INTEL_INFO(dev)->gen >= 8)
-		max = level == 0 ? 255 : 2047;
-	else if (INTEL_INFO(dev)->gen >= 7)
-		/* IVB/HSW primary/sprite plane watermarks */
-		max = level == 0 ? 127 : 1023;
-	else if (!is_sprite)
-		/* ILK/SNB primary plane watermarks */
-		max = level == 0 ? 127 : 511;
-	else
-		/* ILK/SNB sprite plane watermarks */
-		max = level == 0 ? 63 : 255;
-
-	return min(fifo_size, max);
+	return min(fifo_size, ilk_plane_wm_reg_max(dev, level, is_sprite));
 }
 
 /* Calculate the maximum cursor plane watermark */
@@ -1895,20 +1915,7 @@ static unsigned int ilk_cursor_wm_max(const struct drm_device *dev,
 		return 64;
 
 	/* otherwise just report max that registers can hold */
-	if (INTEL_INFO(dev)->gen >= 7)
-		return level == 0 ? 63 : 255;
-	else
-		return level == 0 ? 31 : 63;
-}
-
-/* Calculate the maximum FBC watermark */
-static unsigned int ilk_fbc_wm_max(const struct drm_device *dev)
-{
-	/* max that registers can hold */
-	if (INTEL_INFO(dev)->gen >= 8)
-		return 31;
-	else
-		return 15;
+	return ilk_cursor_wm_reg_max(dev, level);
 }
 
 static void ilk_compute_wm_maximums(const struct drm_device *dev,
@@ -1920,7 +1927,17 @@ static void ilk_compute_wm_maximums(const struct drm_device *dev,
 	max->pri = ilk_plane_wm_max(dev, level, config, ddb_partitioning, false);
 	max->spr = ilk_plane_wm_max(dev, level, config, ddb_partitioning, true);
 	max->cur = ilk_cursor_wm_max(dev, level, config);
-	max->fbc = ilk_fbc_wm_max(dev);
+	max->fbc = ilk_fbc_wm_reg_max(dev);
+}
+
+static void ilk_compute_wm_reg_maximums(struct drm_device *dev,
+					int level,
+					struct ilk_wm_maximums *max)
+{
+	max->pri = ilk_plane_wm_reg_max(dev, level, false);
+	max->spr = ilk_plane_wm_reg_max(dev, level, true);
+	max->cur = ilk_cursor_wm_reg_max(dev, level);
+	max->fbc = ilk_fbc_wm_reg_max(dev);
 }
 
 static bool ilk_validate_wm_level(int level,
@@ -2059,7 +2076,7 @@ static void intel_fixup_cur_wm_latency(struct drm_device *dev, uint16_t wm[5])
 		wm[3] *= 2;
 }
 
-static int ilk_wm_max_level(const struct drm_device *dev)
+int ilk_wm_max_level(const struct drm_device *dev)
 {
 	/* how many WM levels are we expecting */
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
@@ -2155,38 +2172,52 @@ static void ilk_setup_wm_latency(struct drm_device *dev)
 }
 
 static void ilk_compute_wm_parameters(struct drm_crtc *crtc,
-				      struct ilk_pipe_wm_parameters *p,
-				      struct intel_wm_config *config)
+				      struct ilk_pipe_wm_parameters *p)
 {
 	struct drm_device *dev = crtc->dev;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum pipe pipe = intel_crtc->pipe;
 	struct drm_plane *plane;
 
-	p->active = intel_crtc_active(crtc);
-	if (p->active) {
-		p->pipe_htotal = intel_crtc->config.adjusted_mode.crtc_htotal;
-		p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc);
-		p->pri.bytes_per_pixel = crtc->primary->fb->bits_per_pixel / 8;
-		p->cur.bytes_per_pixel = 4;
-		p->pri.horiz_pixels = intel_crtc->config.pipe_src_w;
-		p->cur.horiz_pixels = intel_crtc->cursor_width;
-		/* TODO: for now, assume primary and cursor planes are always enabled. */
-		p->pri.enabled = true;
-		p->cur.enabled = true;
-	}
+	if (!intel_crtc_active(crtc))
+		return;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
-		config->num_pipes_active += intel_crtc_active(crtc);
+	p->active = true;
+	p->pipe_htotal = intel_crtc->config.adjusted_mode.crtc_htotal;
+	p->pixel_rate = ilk_pipe_pixel_rate(dev, crtc);
+	p->pri.bytes_per_pixel = crtc->primary->fb->bits_per_pixel / 8;
+	p->cur.bytes_per_pixel = 4;
+	p->pri.horiz_pixels = intel_crtc->config.pipe_src_w;
+	p->cur.horiz_pixels = intel_crtc->cursor_width;
+	/* TODO: for now, assume primary and cursor planes are always enabled. */
+	p->pri.enabled = true;
+	p->cur.enabled = true;
 
 	drm_for_each_legacy_plane(plane, &dev->mode_config.plane_list) {
 		struct intel_plane *intel_plane = to_intel_plane(plane);
 
-		if (intel_plane->pipe == pipe)
+		if (intel_plane->pipe == pipe) {
 			p->spr = intel_plane->wm;
+			break;
+		}
+	}
+}
 
-		config->sprites_enabled |= intel_plane->wm.enabled;
-		config->sprites_scaled |= intel_plane->wm.scaled;
+static void ilk_compute_wm_config(struct drm_device *dev,
+				  struct intel_wm_config *config)
+{
+	struct intel_crtc *intel_crtc;
+
+	/* Compute the currently _active_ config */
+	for_each_intel_crtc(dev, intel_crtc) {
+		const struct intel_pipe_wm *wm = &intel_crtc->wm.active;
+
+		if (!wm->pipe_enabled)
+			continue;
+
+		config->sprites_enabled |= wm->sprites_enabled;
+		config->sprites_scaled |= wm->sprites_scaled;
+		config->num_pipes_active++;
 	}
 }
 
@@ -2206,8 +2237,9 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc,
 	};
 	struct ilk_wm_maximums max;
 
-	/* LP0 watermarks always use 1/2 DDB partitioning */
-	ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);
+	pipe_wm->pipe_enabled = params->active;
+	pipe_wm->sprites_enabled = params->spr.enabled;
+	pipe_wm->sprites_scaled = params->spr.scaled;
 
 	/* ILK/SNB: LP2+ watermarks only w/o sprites */
 	if (INTEL_INFO(dev)->gen <= 6 && params->spr.enabled)
@@ -2217,15 +2249,37 @@ static bool intel_compute_pipe_wm(struct drm_crtc *crtc,
 	if (params->spr.scaled)
 		max_level = 0;
 
-	for (level = 0; level <= max_level; level++)
-		ilk_compute_wm_level(dev_priv, level, params,
-				     &pipe_wm->wm[level]);
+	ilk_compute_wm_level(dev_priv, 0, params, &pipe_wm->wm[0]);
 
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		pipe_wm->linetime = hsw_compute_linetime_wm(dev, crtc);
 
+	/* LP0 watermarks always use 1/2 DDB partitioning */
+	ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max);
+
 	/* At least LP0 must be valid */
-	return ilk_validate_wm_level(0, &max, &pipe_wm->wm[0]);
+	if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0]))
+		return false;
+
+	ilk_compute_wm_reg_maximums(dev, 1, &max);
+
+	for (level = 1; level <= max_level; level++) {
+		struct intel_wm_level wm = {};
+
+		ilk_compute_wm_level(dev_priv, level, params, &wm);
+
+		/*
+		 * Disable any watermark level that exceeds the
+		 * register maximums since such watermarks are
+		 * always invalid.
+		 */
+		if (!ilk_validate_wm_level(level, &max, &wm))
+			break;
+
+		pipe_wm->wm[level] = wm;
+	}
+
+	return true;
 }
 
 /*
@@ -2237,20 +2291,28 @@ static void ilk_merge_wm_level(struct drm_device *dev,
 {
 	const struct intel_crtc *intel_crtc;
 
-	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) {
-		const struct intel_wm_level *wm =
-			&intel_crtc->wm.active.wm[level];
+	ret_wm->enable = true;
+
+	for_each_intel_crtc(dev, intel_crtc) {
+		const struct intel_pipe_wm *active = &intel_crtc->wm.active;
+		const struct intel_wm_level *wm = &active->wm[level];
+
+		if (!active->pipe_enabled)
+			continue;
 
+		/*
+		 * The watermark values may have been used in the past,
+		 * so we must maintain them in the registers for some
+		 * time even if the level is now disabled.
+		 */
 		if (!wm->enable)
-			return;
+			ret_wm->enable = false;
 
 		ret_wm->pri_val = max(ret_wm->pri_val, wm->pri_val);
 		ret_wm->spr_val = max(ret_wm->spr_val, wm->spr_val);
 		ret_wm->cur_val = max(ret_wm->cur_val, wm->cur_val);
 		ret_wm->fbc_val = max(ret_wm->fbc_val, wm->fbc_val);
 	}
-
-	ret_wm->enable = true;
 }
 
 /*
@@ -2262,6 +2324,7 @@ static void ilk_wm_merge(struct drm_device *dev,
 			 struct intel_pipe_wm *merged)
 {
 	int level, max_level = ilk_wm_max_level(dev);
+	int last_enabled_level = max_level;
 
 	/* ILK/SNB/IVB: LP1+ watermarks only w/ single pipe */
 	if ((INTEL_INFO(dev)->gen <= 6 || IS_IVYBRIDGE(dev)) &&
@@ -2277,15 +2340,19 @@ static void ilk_wm_merge(struct drm_device *dev,
 
 		ilk_merge_wm_level(dev, level, wm);
 
-		if (!ilk_validate_wm_level(level, max, wm))
-			break;
+		if (level > last_enabled_level)
+			wm->enable = false;
+		else if (!ilk_validate_wm_level(level, max, wm))
+			/* make sure all following levels get disabled */
+			last_enabled_level = level - 1;
 
 		/*
 		 * The spec says it is preferred to disable
 		 * FBC WMs instead of disabling a WM level.
 		 */
 		if (wm->fbc_val > max->fbc) {
-			merged->fbc_wm_enabled = false;
+			if (wm->enable)
+				merged->fbc_wm_enabled = false;
 			wm->fbc_val = 0;
 		}
 	}
@@ -2340,14 +2407,19 @@ static void ilk_compute_wm_results(struct drm_device *dev,
 		level = ilk_wm_lp_to_level(wm_lp, merged);
 
 		r = &merged->wm[level];
-		if (!r->enable)
-			break;
 
-		results->wm_lp[wm_lp - 1] = WM3_LP_EN |
+		/*
+		 * Maintain the watermark values even if the level is
+		 * disabled. Doing otherwise could cause underruns.
+		 */
+		results->wm_lp[wm_lp - 1] =
 			(ilk_wm_lp_latency(dev, level) << WM1_LP_LATENCY_SHIFT) |
 			(r->pri_val << WM1_LP_SR_SHIFT) |
 			r->cur_val;
 
+		if (r->enable)
+			results->wm_lp[wm_lp - 1] |= WM1_LP_SR_EN;
+
 		if (INTEL_INFO(dev)->gen >= 8)
 			results->wm_lp[wm_lp - 1] |=
 				r->fbc_val << WM1_LP_FBC_SHIFT_BDW;
@@ -2355,6 +2427,10 @@ static void ilk_compute_wm_results(struct drm_device *dev,
 			results->wm_lp[wm_lp - 1] |=
 				r->fbc_val << WM1_LP_FBC_SHIFT;
 
+		/*
+		 * Always set WM1S_LP_EN when spr_val != 0, even if the
+		 * level is disabled. Doing otherwise could cause underruns.
+		 */
 		if (INTEL_INFO(dev)->gen <= 6 && r->spr_val) {
 			WARN_ON(wm_lp != 1);
 			results->wm_lp_spr[wm_lp - 1] = WM1S_LP_EN | r->spr_val;
@@ -2363,7 +2439,7 @@ static void ilk_compute_wm_results(struct drm_device *dev,
 	}
 
 	/* LP0 register values */
-	list_for_each_entry(intel_crtc, &dev->mode_config.crtc_list, base.head) {
+	for_each_intel_crtc(dev, intel_crtc) {
 		enum pipe pipe = intel_crtc->pipe;
 		const struct intel_wm_level *r =
 			&intel_crtc->wm.active.wm[0];
@@ -2598,7 +2674,7 @@ static void ilk_update_wm(struct drm_crtc *crtc)
 	struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm;
 	struct intel_wm_config config = {};
 
-	ilk_compute_wm_parameters(crtc, &params, &config);
+	ilk_compute_wm_parameters(crtc, &params);
 
 	intel_compute_pipe_wm(crtc, &params, &pipe_wm);
 
@@ -2607,6 +2683,8 @@ static void ilk_update_wm(struct drm_crtc *crtc)
 
 	intel_crtc->wm.active = pipe_wm;
 
+	ilk_compute_wm_config(dev, &config);
+
 	ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_1_2, &max);
 	ilk_wm_merge(dev, &config, &max, &lp_wm_1_2);
 
@@ -2673,7 +2751,9 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc)
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe));
 
-	if (intel_crtc_active(crtc)) {
+	active->pipe_enabled = intel_crtc_active(crtc);
+
+	if (active->pipe_enabled) {
 		u32 tmp = hw->wm_pipe[pipe];
 
 		/*
@@ -2706,7 +2786,7 @@ void ilk_wm_get_hw_state(struct drm_device *dev)
 	struct ilk_wm_values *hw = &dev_priv->wm.hw;
 	struct drm_crtc *crtc;
 
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head)
+	for_each_crtc(dev, crtc)
 		ilk_pipe_wm_get_hw_state(crtc);
 
 	hw->wm_lp[0] = I915_READ(WM1_LP_ILK);
@@ -2714,8 +2794,10 @@ void ilk_wm_get_hw_state(struct drm_device *dev)
 	hw->wm_lp[2] = I915_READ(WM3_LP_ILK);
 
 	hw->wm_lp_spr[0] = I915_READ(WM1S_LP_ILK);
-	hw->wm_lp_spr[1] = I915_READ(WM2S_LP_IVB);
-	hw->wm_lp_spr[2] = I915_READ(WM3S_LP_IVB);
+	if (INTEL_INFO(dev)->gen >= 7) {
+		hw->wm_lp_spr[1] = I915_READ(WM2S_LP_IVB);
+		hw->wm_lp_spr[2] = I915_READ(WM3S_LP_IVB);
+	}
 
 	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 		hw->partitioning = (I915_READ(WM_MISC) & WM_MISC_DATA_PARTITION_5_6) ?
@@ -3071,6 +3153,9 @@ static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
 	if (INTEL_INFO(dev_priv->dev)->gen <= 7 && !IS_HASWELL(dev_priv->dev))
 		mask |= GEN6_PM_RP_UP_EI_EXPIRED;
 
+	if (IS_GEN8(dev_priv->dev))
+		mask |= GEN8_PMINTR_REDIRECT_TO_NON_DISP;
+
 	return ~mask;
 }
 
@@ -3091,7 +3176,7 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 	if (val != dev_priv->rps.cur_freq) {
 		gen6_set_rps_thresholds(dev_priv, val);
 
-		if (IS_HASWELL(dev))
+		if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 			I915_WRITE(GEN6_RPNSWREQ,
 				   HSW_FREQUENCY(val));
 		else
@@ -3124,6 +3209,14 @@ void gen6_set_rps(struct drm_device *dev, u8 val)
 */
 static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 {
+	struct drm_device *dev = dev_priv->dev;
+
+	/* Latest VLV doesn't need to force the gfx clock */
+	if (dev->pdev->revision >= 0xd) {
+		valleyview_set_rps(dev_priv->dev, dev_priv->rps.min_freq_softlimit);
+		return;
+	}
+
 	/*
 	 * When we are idle.  Drop to min voltage state.
 	 */
@@ -3134,16 +3227,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 	/* Mask turbo interrupt so that they will not come in between */
 	I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
 
-	/* Bring up the Gfx clock */
-	I915_WRITE(VLV_GTLC_SURVIVABILITY_REG,
-		I915_READ(VLV_GTLC_SURVIVABILITY_REG) |
-				VLV_GFX_CLK_FORCE_ON_BIT);
-
-	if (wait_for(((VLV_GFX_CLK_STATUS_BIT &
-		I915_READ(VLV_GTLC_SURVIVABILITY_REG)) != 0), 5)) {
-			DRM_ERROR("GFX_CLK_ON request timed out\n");
-		return;
-	}
+	vlv_force_gfx_clock(dev_priv, true);
 
 	dev_priv->rps.cur_freq = dev_priv->rps.min_freq_softlimit;
 
@@ -3154,10 +3238,7 @@ static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
 				& GENFREQSTATUS) == 0, 5))
 		DRM_ERROR("timed out waiting for Punit\n");
 
-	/* Release the Gfx clock */
-	I915_WRITE(VLV_GTLC_SURVIVABILITY_REG,
-		I915_READ(VLV_GTLC_SURVIVABILITY_REG) &
-				~VLV_GFX_CLK_FORCE_ON_BIT);
+	vlv_force_gfx_clock(dev_priv, false);
 
 	I915_WRITE(GEN6_PMINTRMSK,
 		   gen6_rps_pm_mask(dev_priv, dev_priv->rps.cur_freq));
@@ -3215,6 +3296,26 @@ void valleyview_set_rps(struct drm_device *dev, u8 val)
 	trace_intel_gpu_freq_change(vlv_gpu_freq(dev_priv, val));
 }
 
+static void gen8_disable_rps_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	I915_WRITE(GEN6_PMINTRMSK, ~GEN8_PMINTR_REDIRECT_TO_NON_DISP);
+	I915_WRITE(GEN8_GT_IER(2), I915_READ(GEN8_GT_IER(2)) &
+				   ~dev_priv->pm_rps_events);
+	/* Complete PM interrupt masking here doesn't race with the rps work
+	 * item again unmasking PM interrupts because that is using a different
+	 * register (GEN8_GT_IMR(2)) to mask PM interrupts. The only risk is in
+	 * leaving stale bits in GEN8_GT_IIR(2) and GEN8_GT_IMR(2) which
+	 * gen8_enable_rps will clean up. */
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	dev_priv->rps.pm_iir = 0;
+	spin_unlock_irq(&dev_priv->irq_lock);
+
+	I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
+}
+
 static void gen6_disable_rps_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3241,7 +3342,10 @@ static void gen6_disable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 
-	gen6_disable_rps_interrupts(dev);
+	if (IS_BROADWELL(dev))
+		gen8_disable_rps_interrupts(dev);
+	else
+		gen6_disable_rps_interrupts(dev);
 }
 
 static void valleyview_disable_rps(struct drm_device *dev)
@@ -3255,21 +3359,44 @@ static void valleyview_disable_rps(struct drm_device *dev)
 
 static void intel_print_rc6_info(struct drm_device *dev, u32 mode)
 {
+	if (IS_VALLEYVIEW(dev)) {
+		if (mode & (GEN7_RC_CTL_TO_MODE | GEN6_RC_CTL_EI_MODE(1)))
+			mode = GEN6_RC_CTL_RC6_ENABLE;
+		else
+			mode = 0;
+	}
 	DRM_INFO("Enabling RC6 states: RC6 %s, RC6p %s, RC6pp %s\n",
 		 (mode & GEN6_RC_CTL_RC6_ENABLE) ? "on" : "off",
 		 (mode & GEN6_RC_CTL_RC6p_ENABLE) ? "on" : "off",
 		 (mode & GEN6_RC_CTL_RC6pp_ENABLE) ? "on" : "off");
 }
 
-int intel_enable_rc6(const struct drm_device *dev)
+static int sanitize_rc6_option(const struct drm_device *dev, int enable_rc6)
 {
 	/* No RC6 before Ironlake */
 	if (INTEL_INFO(dev)->gen < 5)
 		return 0;
 
+	/* RC6 is only on Ironlake mobile not on desktop */
+	if (INTEL_INFO(dev)->gen == 5 && !IS_IRONLAKE_M(dev))
+		return 0;
+
 	/* Respect the kernel parameter if it is set */
-	if (i915.enable_rc6 >= 0)
-		return i915.enable_rc6;
+	if (enable_rc6 >= 0) {
+		int mask;
+
+		if (INTEL_INFO(dev)->gen == 6 || IS_IVYBRIDGE(dev))
+			mask = INTEL_RC6_ENABLE | INTEL_RC6p_ENABLE |
+			       INTEL_RC6pp_ENABLE;
+		else
+			mask = INTEL_RC6_ENABLE;
+
+		if ((enable_rc6 & mask) != enable_rc6)
+			DRM_INFO("Adjusting RC6 mask to %d (requested %d, valid %d)\n",
+				 enable_rc6 & mask, enable_rc6, mask);
+
+		return enable_rc6 & mask;
+	}
 
 	/* Disable RC6 on Ironlake */
 	if (INTEL_INFO(dev)->gen == 5)
@@ -3281,6 +3408,22 @@ int intel_enable_rc6(const struct drm_device *dev)
 	return INTEL_RC6_ENABLE;
 }
 
+int intel_enable_rc6(const struct drm_device *dev)
+{
+	return i915.enable_rc6;
+}
+
+static void gen8_enable_rps_interrupts(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	spin_lock_irq(&dev_priv->irq_lock);
+	WARN_ON(dev_priv->rps.pm_iir);
+	bdw_enable_pm_irq(dev_priv, dev_priv->pm_rps_events);
+	I915_WRITE(GEN8_GT_IIR(2), dev_priv->pm_rps_events);
+	spin_unlock_irq(&dev_priv->irq_lock);
+}
+
 static void gen6_enable_rps_interrupts(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3292,10 +3435,31 @@ static void gen6_enable_rps_interrupts(struct drm_device *dev)
 	spin_unlock_irq(&dev_priv->irq_lock);
 }
 
+static void parse_rp_state_cap(struct drm_i915_private *dev_priv, u32 rp_state_cap)
+{
+	/* All of these values are in units of 50MHz */
+	dev_priv->rps.cur_freq		= 0;
+	/* static values from HW: RP0 < RPe < RP1 < RPn (min_freq) */
+	dev_priv->rps.rp1_freq		= (rp_state_cap >>  8) & 0xff;
+	dev_priv->rps.rp0_freq		= (rp_state_cap >>  0) & 0xff;
+	dev_priv->rps.min_freq		= (rp_state_cap >> 16) & 0xff;
+	/* XXX: only BYT has a special efficient freq */
+	dev_priv->rps.efficient_freq	= dev_priv->rps.rp1_freq;
+	/* hw_max = RP0 until we check for overclocking */
+	dev_priv->rps.max_freq		= dev_priv->rps.rp0_freq;
+
+	/* Preserve min/max settings in case of re-init */
+	if (dev_priv->rps.max_freq_softlimit == 0)
+		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
+
+	if (dev_priv->rps.min_freq_softlimit == 0)
+		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
+}
+
 static void gen8_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	uint32_t rc6_mask = 0, rp_state_cap;
 	int unused;
 
@@ -3310,6 +3474,7 @@ static void gen8_enable_rps(struct drm_device *dev)
 	I915_WRITE(GEN6_RC_CONTROL, 0);
 
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
+	parse_rp_state_cap(dev_priv, rp_state_cap);
 
 	/* 2b: Program RC6 thresholds.*/
 	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
@@ -3329,8 +3494,10 @@ static void gen8_enable_rps(struct drm_device *dev)
 				    rc6_mask);
 
 	/* 4 Program defaults and thresholds for RPS*/
-	I915_WRITE(GEN6_RPNSWREQ, HSW_FREQUENCY(10)); /* Request 500 MHz */
-	I915_WRITE(GEN6_RC_VIDEO_FREQ, HSW_FREQUENCY(12)); /* Request 600 MHz */
+	I915_WRITE(GEN6_RPNSWREQ,
+		   HSW_FREQUENCY(dev_priv->rps.rp1_freq));
+	I915_WRITE(GEN6_RC_VIDEO_FREQ,
+		   HSW_FREQUENCY(dev_priv->rps.rp1_freq));
 	/* NB: Docs say 1s, and 1000000 - which aren't equivalent */
 	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 100000000 / 128); /* 1 second timeout */
 
@@ -3359,7 +3526,7 @@ static void gen8_enable_rps(struct drm_device *dev)
 
 	gen6_set_rps(dev, (I915_READ(GEN6_GT_PERF_STATUS) & 0xff00) >> 8);
 
-	gen6_enable_rps_interrupts(dev);
+	gen8_enable_rps_interrupts(dev);
 
 	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
@@ -3367,7 +3534,7 @@ static void gen8_enable_rps(struct drm_device *dev)
 static void gen6_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	u32 rp_state_cap;
 	u32 gt_perf_status;
 	u32 rc6vids, pcu_mbox = 0, rc6_mask = 0;
@@ -3396,23 +3563,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 	rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
 	gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 
-	/* All of these values are in units of 50MHz */
-	dev_priv->rps.cur_freq		= 0;
-	/* static values from HW: RP0 < RPe < RP1 < RPn (min_freq) */
-	dev_priv->rps.rp1_freq		= (rp_state_cap >>  8) & 0xff;
-	dev_priv->rps.rp0_freq		= (rp_state_cap >>  0) & 0xff;
-	dev_priv->rps.min_freq		= (rp_state_cap >> 16) & 0xff;
-	/* XXX: only BYT has a special efficient freq */
-	dev_priv->rps.efficient_freq	= dev_priv->rps.rp1_freq;
-	/* hw_max = RP0 until we check for overclocking */
-	dev_priv->rps.max_freq		= dev_priv->rps.rp0_freq;
-
-	/* Preserve min/max settings in case of re-init */
-	if (dev_priv->rps.max_freq_softlimit == 0)
-		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
-
-	if (dev_priv->rps.min_freq_softlimit == 0)
-		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
+	parse_rp_state_cap(dev_priv, rp_state_cap);
 
 	/* disable the counters and set deterministic thresholds */
 	I915_WRITE(GEN6_RC_CONTROL, 0);
@@ -3494,7 +3645,7 @@ static void gen6_enable_rps(struct drm_device *dev)
 	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
 }
 
-void gen6_update_ring_freq(struct drm_device *dev)
+static void __gen6_update_ring_freq(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int min_freq = 15;
@@ -3564,6 +3715,18 @@ void gen6_update_ring_freq(struct drm_device *dev)
 	}
 }
 
+void gen6_update_ring_freq(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (INTEL_INFO(dev)->gen < 6 || IS_VALLEYVIEW(dev))
+		return;
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+	__gen6_update_ring_freq(dev);
+	mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
 int valleyview_rps_max_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val, rp0;
@@ -3658,10 +3821,49 @@ static void valleyview_cleanup_pctx(struct drm_device *dev)
 	dev_priv->vlv_pctx = NULL;
 }
 
+static void valleyview_init_gt_powersave(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	valleyview_setup_pctx(dev);
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+	dev_priv->rps.max_freq = valleyview_rps_max_freq(dev_priv);
+	dev_priv->rps.rp0_freq = dev_priv->rps.max_freq;
+	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq),
+			 dev_priv->rps.max_freq);
+
+	dev_priv->rps.efficient_freq = valleyview_rps_rpe_freq(dev_priv);
+	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+			 dev_priv->rps.efficient_freq);
+
+	dev_priv->rps.min_freq = valleyview_rps_min_freq(dev_priv);
+	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
+			 dev_priv->rps.min_freq);
+
+	/* Preserve min/max settings in case of re-init */
+	if (dev_priv->rps.max_freq_softlimit == 0)
+		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
+
+	if (dev_priv->rps.min_freq_softlimit == 0)
+		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
+
+	mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
+static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
+{
+	valleyview_cleanup_pctx(dev);
+}
+
 static void valleyview_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	u32 gtfifodbg, val, rc6_mode = 0;
 	int i;
 
@@ -3724,29 +3926,6 @@ static void valleyview_enable_rps(struct drm_device *dev)
 			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
 			 dev_priv->rps.cur_freq);
 
-	dev_priv->rps.max_freq = valleyview_rps_max_freq(dev_priv);
-	dev_priv->rps.rp0_freq  = dev_priv->rps.max_freq;
-	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq),
-			 dev_priv->rps.max_freq);
-
-	dev_priv->rps.efficient_freq = valleyview_rps_rpe_freq(dev_priv);
-	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
-			 dev_priv->rps.efficient_freq);
-
-	dev_priv->rps.min_freq = valleyview_rps_min_freq(dev_priv);
-	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
-			 dev_priv->rps.min_freq);
-
-	/* Preserve min/max settings in case of re-init */
-	if (dev_priv->rps.max_freq_softlimit == 0)
-		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
-
-	if (dev_priv->rps.min_freq_softlimit == 0)
-		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
-
 	DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n",
 			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
 			 dev_priv->rps.efficient_freq);
@@ -3815,7 +3994,7 @@ static int ironlake_setup_rc6(struct drm_device *dev)
 static void ironlake_enable_rc6(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
 	bool was_interruptible;
 	int ret;
 
@@ -3873,7 +4052,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 	I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
 	I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
 
-	intel_print_rc6_info(dev, INTEL_RC6_ENABLE);
+	intel_print_rc6_info(dev, GEN6_RC_CTL_RC6_ENABLE);
 }
 
 static unsigned long intel_pxfreq(u32 vidfreq)
@@ -4327,7 +4506,7 @@ EXPORT_SYMBOL_GPL(i915_gpu_lower);
 bool i915_gpu_busy(void)
 {
 	struct drm_i915_private *dev_priv;
-	struct intel_ring_buffer *ring;
+	struct intel_engine_cs *ring;
 	bool ret = false;
 	int i;
 
@@ -4487,14 +4666,16 @@ static void intel_init_emon(struct drm_device *dev)
 
 void intel_init_gt_powersave(struct drm_device *dev)
 {
+	i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
+
 	if (IS_VALLEYVIEW(dev))
-		valleyview_setup_pctx(dev);
+		valleyview_init_gt_powersave(dev);
 }
 
 void intel_cleanup_gt_powersave(struct drm_device *dev)
 {
 	if (IS_VALLEYVIEW(dev))
-		valleyview_cleanup_pctx(dev);
+		valleyview_cleanup_gt_powersave(dev);
 }
 
 void intel_disable_gt_powersave(struct drm_device *dev)
@@ -4507,8 +4688,10 @@ void intel_disable_gt_powersave(struct drm_device *dev)
 	if (IS_IRONLAKE_M(dev)) {
 		ironlake_disable_drps(dev);
 		ironlake_disable_rc6(dev);
-	} else if (INTEL_INFO(dev)->gen >= 6) {
-		cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work);
+	} else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) {
+		if (cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work))
+			intel_runtime_pm_put(dev_priv);
+
 		cancel_work_sync(&dev_priv->rps.work);
 		mutex_lock(&dev_priv->rps.hw_lock);
 		if (IS_VALLEYVIEW(dev))
@@ -4533,13 +4716,15 @@ static void intel_gen6_powersave_work(struct work_struct *work)
 		valleyview_enable_rps(dev);
 	} else if (IS_BROADWELL(dev)) {
 		gen8_enable_rps(dev);
-		gen6_update_ring_freq(dev);
+		__gen6_update_ring_freq(dev);
 	} else {
 		gen6_enable_rps(dev);
-		gen6_update_ring_freq(dev);
+		__gen6_update_ring_freq(dev);
 	}
 	dev_priv->rps.enabled = true;
 	mutex_unlock(&dev_priv->rps.hw_lock);
+
+	intel_runtime_pm_put(dev_priv);
 }
 
 void intel_enable_gt_powersave(struct drm_device *dev)
@@ -4547,20 +4732,38 @@ void intel_enable_gt_powersave(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	if (IS_IRONLAKE_M(dev)) {
+		mutex_lock(&dev->struct_mutex);
 		ironlake_enable_drps(dev);
 		ironlake_enable_rc6(dev);
 		intel_init_emon(dev);
-	} else if (IS_GEN6(dev) || IS_GEN7(dev)) {
+		mutex_unlock(&dev->struct_mutex);
+	} else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) {
 		/*
 		 * PCU communication is slow and this doesn't need to be
 		 * done at any specific time, so do this out of our fast path
 		 * to make resume and init faster.
+		 *
+		 * We depend on the HW RC6 power context save/restore
+		 * mechanism when entering D3 through runtime PM suspend. So
+		 * disable RPM until RPS/RC6 is properly setup. We can only
+		 * get here via the driver load/system resume/runtime resume
+		 * paths, so the _noresume version is enough (and in case of
+		 * runtime resume it's necessary).
 		 */
-		schedule_delayed_work(&dev_priv->rps.delayed_resume_work,
-				      round_jiffies_up_relative(HZ));
+		if (schedule_delayed_work(&dev_priv->rps.delayed_resume_work,
+					   round_jiffies_up_relative(HZ)))
+			intel_runtime_pm_get_noresume(dev_priv);
 	}
 }
 
+void intel_reset_gt_powersave(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	dev_priv->rps.enabled = false;
+	intel_enable_gt_powersave(dev);
+}
+
 static void ibx_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4666,6 +4869,9 @@ static void ironlake_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(CACHE_MODE_0,
 		   _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
 
+	/* WaDisable_RenderCache_OperationalFlush:ilk */
+	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+
 	g4x_disable_trickle_feed(dev);
 
 	ibx_init_clock_gating(dev);
@@ -4741,6 +4947,9 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 		I915_WRITE(GEN6_GT_MODE,
 			   _MASKED_BIT_ENABLE(GEN6_TD_FOUR_ROW_DISPATCH_DISABLE));
 
+	/* WaDisable_RenderCache_OperationalFlush:snb */
+	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+
 	/*
 	 * BSpec recoomends 8x4 when MSAA is used,
 	 * however in practice 16x4 seems fastest.
@@ -4909,6 +5118,10 @@ static void gen8_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
 		   _MASKED_BIT_ENABLE(GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE));
 
+	/* WaDisableDopClockGating:bdw May not be needed for production */
+	I915_WRITE(GEN7_ROW_CHICKEN2,
+		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+
 	/* WaSwitchSolVfFArbitrationPriority:bdw */
 	I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
 
@@ -4980,6 +5193,9 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_FF_THREAD_MODE,
 		   I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME);
 
+	/* WaDisable_RenderCache_OperationalFlush:hsw */
+	I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+
 	/* enable HiZ Raw Stall Optimization */
 	I915_WRITE(CACHE_MODE_0_GEN7,
 		   _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
@@ -5032,6 +5248,9 @@ static void ivybridge_init_clock_gating(struct drm_device *dev)
 		I915_WRITE(GEN7_HALF_SLICE_CHICKEN1,
 			   _MASKED_BIT_ENABLE(GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
 
+	/* WaDisable_RenderCache_OperationalFlush:ivb */
+	I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+
 	/* Apply the WaDisableRHWOOptimizationForRenderHang:ivb workaround. */
 	I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1,
 		   GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
@@ -5126,6 +5345,10 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 	}
 	DRM_DEBUG_DRIVER("DDR speed: %d MHz", dev_priv->mem_freq);
 
+	dev_priv->vlv_cdclk_freq = valleyview_cur_cdclk(dev_priv);
+	DRM_DEBUG_DRIVER("Current CD clock rate: %d MHz",
+			 dev_priv->vlv_cdclk_freq);
+
 	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaDisableEarlyCull:vlv */
@@ -5143,6 +5366,9 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 		   _MASKED_BIT_ENABLE(GEN7_MAX_PS_THREAD_DEP |
 				      GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE));
 
+	/* WaDisable_RenderCache_OperationalFlush:vlv */
+	I915_WRITE(CACHE_MODE_0_GEN7, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+
 	/* WaForceL3Serialization:vlv */
 	I915_WRITE(GEN7_L3SQCREG4, I915_READ(GEN7_L3SQCREG4) &
 		   ~L3SQ_URB_READ_CAM_MATCH_DISABLE);
@@ -5165,8 +5391,11 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN6_UCGCTL2,
 		   GEN6_RCZUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaDisableL3Bank2xClockGate:vlv */
-	I915_WRITE(GEN7_UCGCTL4, GEN7_L3BANK2X_CLOCK_GATE_DISABLE);
+	/* WaDisableL3Bank2xClockGate:vlv
+	 * Disabling L3 clock gating- MMIO 940c[25] = 1
+	 * Set bit 25, to disable L3_BANK_2x_CLK_GATING */
+	I915_WRITE(GEN7_UCGCTL4,
+		   I915_READ(GEN7_UCGCTL4) | GEN7_L3BANK2X_CLOCK_GATE_DISABLE);
 
 	I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE);
 
@@ -5191,6 +5420,59 @@ static void valleyview_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(VLV_GUNIT_CLOCK_GATE, GCFG_DIS);
 }
 
+static void cherryview_init_clock_gating(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	I915_WRITE(DSPCLK_GATE_D, VRHUNIT_CLOCK_GATE_DISABLE);
+
+	I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE);
+
+	/* WaDisablePartialInstShootdown:chv */
+	I915_WRITE(GEN8_ROW_CHICKEN,
+		   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
+
+	/* WaDisableThreadStallDopClockGating:chv */
+	I915_WRITE(GEN8_ROW_CHICKEN,
+		   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
+
+	/* WaVSRefCountFullforceMissDisable:chv */
+	/* WaDSRefCountFullforceMissDisable:chv */
+	I915_WRITE(GEN7_FF_THREAD_MODE,
+		   I915_READ(GEN7_FF_THREAD_MODE) &
+		   ~(GEN8_FF_DS_REF_CNT_FFME | GEN7_FF_VS_REF_CNT_FFME));
+
+	/* WaDisableSemaphoreAndSyncFlipWait:chv */
+	I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL,
+		   _MASKED_BIT_ENABLE(GEN8_RC_SEMA_IDLE_MSG_DISABLE));
+
+	/* WaDisableCSUnitClockGating:chv */
+	I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
+		   GEN6_CSUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaDisableSDEUnitClockGating:chv */
+	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
+		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+
+	/* WaDisableSamplerPowerBypass:chv (pre-production hw) */
+	I915_WRITE(HALF_SLICE_CHICKEN3,
+		   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
+
+	/* WaDisableGunitClockGating:chv (pre-production hw) */
+	I915_WRITE(VLV_GUNIT_CLOCK_GATE, I915_READ(VLV_GUNIT_CLOCK_GATE) |
+		   GINT_DIS);
+
+	/* WaDisableFfDopClockGating:chv (pre-production hw) */
+	I915_WRITE(GEN6_RC_SLEEP_PSMI_CONTROL,
+		   _MASKED_BIT_ENABLE(GEN8_FF_DOP_CLOCK_GATE_DISABLE));
+
+	/* WaDisableDopClockGating:chv (pre-production hw) */
+	I915_WRITE(GEN7_ROW_CHICKEN2,
+		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+	I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
+		   GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE);
+}
+
 static void g4x_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -5212,6 +5494,9 @@ static void g4x_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(CACHE_MODE_0,
 		   _MASKED_BIT_ENABLE(CM0_PIPELINED_RENDER_FLUSH_DISABLE));
 
+	/* WaDisable_RenderCache_OperationalFlush:g4x */
+	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
+
 	g4x_disable_trickle_feed(dev);
 }
 
@@ -5226,6 +5511,9 @@ static void crestline_init_clock_gating(struct drm_device *dev)
 	I915_WRITE16(DEUC, 0);
 	I915_WRITE(MI_ARB_STATE,
 		   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
+
+	/* WaDisable_RenderCache_OperationalFlush:gen4 */
+	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
 }
 
 static void broadwater_init_clock_gating(struct drm_device *dev)
@@ -5240,6 +5528,9 @@ static void broadwater_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(RENCLK_GATE_D2, 0);
 	I915_WRITE(MI_ARB_STATE,
 		   _MASKED_BIT_ENABLE(MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE));
+
+	/* WaDisable_RenderCache_OperationalFlush:gen4 */
+	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
 }
 
 static void gen3_init_clock_gating(struct drm_device *dev)
@@ -5256,6 +5547,12 @@ static void gen3_init_clock_gating(struct drm_device *dev)
 
 	/* IIR "flip pending" means done if this bit is set */
 	I915_WRITE(ECOSKPD, _MASKED_BIT_DISABLE(ECO_FLIP_DONE));
+
+	/* interrupts should cause a wake up from C3 */
+	I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_AGPBUSY_INT_EN));
+
+	/* On GEN3 we really need to make sure the ARB C3 LP bit is set */
+	I915_WRITE(MI_ARB_STATE, _MASKED_BIT_ENABLE(MI_ARB_C3_LP_WRITE_ENABLE));
 }
 
 static void i85x_init_clock_gating(struct drm_device *dev)
@@ -5263,6 +5560,10 @@ static void i85x_init_clock_gating(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	I915_WRITE(RENCLK_GATE_D1, SV_CLOCK_GATE_DISABLE);
+
+	/* interrupts should cause a wake up from C3 */
+	I915_WRITE(MI_STATE, _MASKED_BIT_ENABLE(MI_AGPBUSY_INT_EN) |
+		   _MASKED_BIT_DISABLE(MI_AGPBUSY_830_MODE));
 }
 
 static void i830_init_clock_gating(struct drm_device *dev)
@@ -5310,18 +5611,8 @@ static bool hsw_power_well_enabled(struct drm_i915_private *dev_priv,
 		     (HSW_PWR_WELL_ENABLE_REQUEST | HSW_PWR_WELL_STATE_ENABLED);
 }
 
-bool intel_display_power_enabled_sw(struct drm_i915_private *dev_priv,
-				    enum intel_display_power_domain domain)
-{
-	struct i915_power_domains *power_domains;
-
-	power_domains = &dev_priv->power_domains;
-
-	return power_domains->domain_use_count[domain];
-}
-
-bool intel_display_power_enabled(struct drm_i915_private *dev_priv,
-				 enum intel_display_power_domain domain)
+bool intel_display_power_enabled_unlocked(struct drm_i915_private *dev_priv,
+					  enum intel_display_power_domain domain)
 {
 	struct i915_power_domains *power_domains;
 	struct i915_power_well *power_well;
@@ -5335,21 +5626,34 @@ bool intel_display_power_enabled(struct drm_i915_private *dev_priv,
 
 	is_enabled = true;
 
-	mutex_lock(&power_domains->lock);
 	for_each_power_well_rev(i, power_well, BIT(domain), power_domains) {
 		if (power_well->always_on)
 			continue;
 
-		if (!power_well->ops->is_enabled(dev_priv, power_well)) {
+		if (!power_well->hw_enabled) {
 			is_enabled = false;
 			break;
 		}
 	}
-	mutex_unlock(&power_domains->lock);
 
 	return is_enabled;
 }
 
+bool intel_display_power_enabled(struct drm_i915_private *dev_priv,
+				 enum intel_display_power_domain domain)
+{
+	struct i915_power_domains *power_domains;
+	bool ret;
+
+	power_domains = &dev_priv->power_domains;
+
+	mutex_lock(&power_domains->lock);
+	ret = intel_display_power_enabled_unlocked(dev_priv, domain);
+	mutex_unlock(&power_domains->lock);
+
+	return ret;
+}
+
 /*
  * Starting with Haswell, we have a "Power Down Well" that can be turned off
  * when not needed anymore. We have 4 registers that can request the power well
@@ -5392,33 +5696,6 @@ static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv)
 	}
 }
 
-static void reset_vblank_counter(struct drm_device *dev, enum pipe pipe)
-{
-	assert_spin_locked(&dev->vbl_lock);
-
-	dev->vblank[pipe].last = 0;
-}
-
-static void hsw_power_well_post_disable(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = dev_priv->dev;
-	enum pipe pipe;
-	unsigned long irqflags;
-
-	/*
-	 * After this, the registers on the pipes that are part of the power
-	 * well will become zero, so we have to adjust our counters according to
-	 * that.
-	 *
-	 * FIXME: Should we do this in general in drm_vblank_post_modeset?
-	 */
-	spin_lock_irqsave(&dev->vbl_lock, irqflags);
-	for_each_pipe(pipe)
-		if (pipe != PIPE_A)
-			reset_vblank_counter(dev, pipe);
-	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
-}
-
 static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 			       struct i915_power_well *power_well, bool enable)
 {
@@ -5447,8 +5724,6 @@ static void hsw_set_power_well(struct drm_i915_private *dev_priv,
 			I915_WRITE(HSW_PWR_WELL_DRIVER, 0);
 			POSTING_READ(HSW_PWR_WELL_DRIVER);
 			DRM_DEBUG_KMS("Requesting to disable the power well\n");
-
-			hsw_power_well_post_disable(dev_priv);
 		}
 	}
 }
@@ -5489,13 +5764,34 @@ static bool i9xx_always_on_power_well_enabled(struct drm_i915_private *dev_priv,
 	return true;
 }
 
-static void vlv_set_power_well(struct drm_i915_private *dev_priv,
-			       struct i915_power_well *power_well, bool enable)
+void __vlv_set_power_well(struct drm_i915_private *dev_priv,
+			  enum punit_power_well power_well_id, bool enable)
 {
-	enum punit_power_well power_well_id = power_well->data;
+	struct drm_device *dev = dev_priv->dev;
 	u32 mask;
 	u32 state;
 	u32 ctrl;
+	enum pipe pipe;
+
+	if (power_well_id == PUNIT_POWER_WELL_DPIO_CMN_BC) {
+		if (enable) {
+			/*
+			 * Enable the CRI clock source so we can get at the
+			 * display and the reference clock for VGA
+			 * hotplug / manual detection.
+			 */
+			I915_WRITE(DPLL(PIPE_B), I915_READ(DPLL(PIPE_B)) |
+				   DPLL_REFA_CLK_ENABLE_VLV |
+				   DPLL_INTEGRATED_CRI_CLK_VLV);
+			udelay(1); /* >10ns for cmnreset, >0ns for sidereset */
+		} else {
+			for_each_pipe(pipe)
+				assert_pll_disabled(dev_priv, pipe);
+			/* Assert common reset */
+			I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) &
+				   ~DPIO_CMNRST);
+		}
+	}
 
 	mask = PUNIT_PWRGT_MASK(power_well_id);
 	state = enable ? PUNIT_PWRGT_PWR_ON(power_well_id) :
@@ -5523,6 +5819,28 @@ static void vlv_set_power_well(struct drm_i915_private *dev_priv,
 
 out:
 	mutex_unlock(&dev_priv->rps.hw_lock);
+
+	/*
+	 * From VLV2A0_DP_eDP_DPIO_driver_vbios_notes_10.docx -
+	 *  6.	De-assert cmn_reset/side_reset. Same as VLV X0.
+	 *   a.	GUnit 0x2110 bit[0] set to 1 (def 0)
+	 *   b.	The other bits such as sfr settings / modesel may all
+	 *	be set to 0.
+	 *
+	 * This should only be done on init and resume from S3 with
+	 * both PLLs disabled, or we risk losing DPIO and PLL
+	 * synchronization.
+	 */
+	if (power_well_id == PUNIT_POWER_WELL_DPIO_CMN_BC && enable)
+		I915_WRITE(DPIO_CTL, I915_READ(DPIO_CTL) | DPIO_CMNRST);
+}
+
+static void vlv_set_power_well(struct drm_i915_private *dev_priv,
+			       struct i915_power_well *power_well, bool enable)
+{
+	enum punit_power_well power_well_id = power_well->data;
+
+	__vlv_set_power_well(dev_priv, power_well_id, enable);
 }
 
 static void vlv_power_well_sync_hw(struct drm_i915_private *dev_priv,
@@ -5591,11 +5909,13 @@ static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv,
 	spin_unlock_irq(&dev_priv->irq_lock);
 
 	/*
-	 * During driver initialization we need to defer enabling hotplug
-	 * processing until fbdev is set up.
+	 * During driver initialization/resume we can avoid restoring the
+	 * part of the HW/SW state that will be inited anyway explicitly.
 	 */
-	if (dev_priv->enable_hotplug_processing)
-		intel_hpd_init(dev_priv->dev);
+	if (dev_priv->power_domains.initializing)
+		return;
+
+	intel_hpd_init(dev_priv->dev);
 
 	i915_redisable_vga_power_on(dev_priv->dev);
 }
@@ -5603,23 +5923,12 @@ static void vlv_display_power_well_enable(struct drm_i915_private *dev_priv,
 static void vlv_display_power_well_disable(struct drm_i915_private *dev_priv,
 					   struct i915_power_well *power_well)
 {
-	struct drm_device *dev = dev_priv->dev;
-	enum pipe pipe;
-
 	WARN_ON_ONCE(power_well->data != PUNIT_POWER_WELL_DISP2D);
 
 	spin_lock_irq(&dev_priv->irq_lock);
-	for_each_pipe(pipe)
-		__intel_set_cpu_fifo_underrun_reporting(dev, pipe, false);
-
 	valleyview_disable_display_irqs(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	spin_lock_irq(&dev->vbl_lock);
-	for_each_pipe(pipe)
-		reset_vblank_counter(dev, pipe);
-	spin_unlock_irq(&dev->vbl_lock);
-
 	vlv_set_power_well(dev_priv, power_well, false);
 }
 
@@ -5663,6 +5972,7 @@ void intel_display_power_get(struct drm_i915_private *dev_priv,
 		if (!power_well->count++) {
 			DRM_DEBUG_KMS("enabling %s\n", power_well->name);
 			power_well->ops->enable(dev_priv, power_well);
+			power_well->hw_enabled = true;
 		}
 
 		check_power_well_state(dev_priv, power_well);
@@ -5692,6 +6002,7 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 
 		if (!--power_well->count && i915.disable_power_well) {
 			DRM_DEBUG_KMS("disabling %s\n", power_well->name);
+			power_well->hw_enabled = false;
 			power_well->ops->disable(dev_priv, power_well);
 		}
 
@@ -5706,33 +6017,56 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 static struct i915_power_domains *hsw_pwr;
 
 /* Display audio driver power well request */
-void i915_request_power_well(void)
+int i915_request_power_well(void)
 {
 	struct drm_i915_private *dev_priv;
 
-	if (WARN_ON(!hsw_pwr))
-		return;
+	if (!hsw_pwr)
+		return -ENODEV;
 
 	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
 				power_domains);
 	intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(i915_request_power_well);
 
 /* Display audio driver power well release */
-void i915_release_power_well(void)
+int i915_release_power_well(void)
 {
 	struct drm_i915_private *dev_priv;
 
-	if (WARN_ON(!hsw_pwr))
-		return;
+	if (!hsw_pwr)
+		return -ENODEV;
 
 	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
 				power_domains);
 	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(i915_release_power_well);
 
+/*
+ * Private interface for the audio driver to get CDCLK in kHz.
+ *
+ * Caller must request power well using i915_request_power_well() prior to
+ * making the call.
+ */
+int i915_get_cdclk_freq(void)
+{
+	struct drm_i915_private *dev_priv;
+
+	if (!hsw_pwr)
+		return -ENODEV;
+
+	dev_priv = container_of(hsw_pwr, struct drm_i915_private,
+				power_domains);
+
+	return intel_ddi_get_cdclk_freq(dev_priv);
+}
+EXPORT_SYMBOL_GPL(i915_get_cdclk_freq);
+
+
 #define POWER_DOMAIN_MASK (BIT(POWER_DOMAIN_NUM) - 1)
 
 #define HSW_ALWAYS_ON_POWER_DOMAINS (			\
@@ -5867,12 +6201,6 @@ static struct i915_power_well vlv_power_wells[] = {
 		.ops = &vlv_display_power_well_ops,
 	},
 	{
-		.name = "dpio-common",
-		.domains = VLV_DPIO_CMN_BC_POWER_DOMAINS,
-		.data = PUNIT_POWER_WELL_DPIO_CMN_BC,
-		.ops = &vlv_dpio_power_well_ops,
-	},
-	{
 		.name = "dpio-tx-b-01",
 		.domains = VLV_DPIO_TX_B_LANES_01_POWER_DOMAINS |
 			   VLV_DPIO_TX_B_LANES_23_POWER_DOMAINS |
@@ -5908,6 +6236,12 @@ static struct i915_power_well vlv_power_wells[] = {
 		.ops = &vlv_dpio_power_well_ops,
 		.data = PUNIT_POWER_WELL_DPIO_TX_C_LANES_23,
 	},
+	{
+		.name = "dpio-common",
+		.domains = VLV_DPIO_CMN_BC_POWER_DOMAINS,
+		.data = PUNIT_POWER_WELL_DPIO_CMN_BC,
+		.ops = &vlv_dpio_power_well_ops,
+	},
 };
 
 #define set_power_wells(power_domains, __power_wells) ({		\
@@ -5952,16 +6286,23 @@ static void intel_power_domains_resume(struct drm_i915_private *dev_priv)
 	int i;
 
 	mutex_lock(&power_domains->lock);
-	for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains)
+	for_each_power_well(i, power_well, POWER_DOMAIN_MASK, power_domains) {
 		power_well->ops->sync_hw(dev_priv, power_well);
+		power_well->hw_enabled = power_well->ops->is_enabled(dev_priv,
+								     power_well);
+	}
 	mutex_unlock(&power_domains->lock);
 }
 
 void intel_power_domains_init_hw(struct drm_i915_private *dev_priv)
 {
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+
+	power_domains->initializing = true;
 	/* For now, we need the power well to be always enabled. */
 	intel_display_set_init_power(dev_priv, true);
 	intel_power_domains_resume(dev_priv);
+	power_domains->initializing = false;
 }
 
 void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv)
@@ -5986,6 +6327,18 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
 	WARN(dev_priv->pm.suspended, "Device still suspended.\n");
 }
 
+void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = dev_priv->dev;
+	struct device *device = &dev->pdev->dev;
+
+	if (!HAS_RUNTIME_PM(dev))
+		return;
+
+	WARN(dev_priv->pm.suspended, "Getting nosync-ref while suspended.\n");
+	pm_runtime_get_noresume(device);
+}
+
 void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = dev_priv->dev;
@@ -6008,6 +6361,15 @@ void intel_init_runtime_pm(struct drm_i915_private *dev_priv)
 
 	pm_runtime_set_active(device);
 
+	/*
+	 * RPM depends on RC6 to save restore the GT HW context, so make RC6 a
+	 * requirement.
+	 */
+	if (!intel_enable_rc6(dev)) {
+		DRM_INFO("RC6 disabled, disabling runtime PM support\n");
+		return;
+	}
+
 	pm_runtime_set_autosuspend_delay(device, 10000); /* 10s */
 	pm_runtime_mark_last_busy(device);
 	pm_runtime_use_autosuspend(device);
@@ -6023,6 +6385,9 @@ void intel_fini_runtime_pm(struct drm_i915_private *dev_priv)
 	if (!HAS_RUNTIME_PM(dev))
 		return;
 
+	if (!intel_enable_rc6(dev))
+		return;
+
 	/* Make sure we're not suspended first. */
 	pm_runtime_get_sync(device);
 	pm_runtime_disable(device);
@@ -6087,6 +6452,10 @@ void intel_init_pm(struct drm_device *dev)
 			dev_priv->display.init_clock_gating = haswell_init_clock_gating;
 		else if (INTEL_INFO(dev)->gen == 8)
 			dev_priv->display.init_clock_gating = gen8_init_clock_gating;
+	} else if (IS_CHERRYVIEW(dev)) {
+		dev_priv->display.update_wm = valleyview_update_wm;
+		dev_priv->display.init_clock_gating =
+			cherryview_init_clock_gating;
 	} else if (IS_VALLEYVIEW(dev)) {
 		dev_priv->display.update_wm = valleyview_update_wm;
 		dev_priv->display.init_clock_gating =
diff --git a/drivers/gpu/drm/i915/intel_renderstate.h b/drivers/gpu/drm/i915/intel_renderstate.h
new file mode 100644
index 00000000000..a5e783a9928
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_renderstate.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright © 2014 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _INTEL_RENDERSTATE_H
+#define _INTEL_RENDERSTATE_H
+
+#include <linux/types.h>
+
+struct intel_renderstate_rodata {
+	const u32 *reloc;
+	const u32 reloc_items;
+	const u32 *batch;
+	const u32 batch_items;
+};
+
+extern const struct intel_renderstate_rodata gen6_null_state;
+extern const struct intel_renderstate_rodata gen7_null_state;
+extern const struct intel_renderstate_rodata gen8_null_state;
+
+#define RO_RENDERSTATE(_g)						\
+	const struct intel_renderstate_rodata gen ## _g ## _null_state = { \
+		.reloc = gen ## _g ## _null_state_relocs,		\
+		.reloc_items = sizeof(gen ## _g ## _null_state_relocs)/4, \
+		.batch = gen ## _g ## _null_state_batch,		\
+		.batch_items = sizeof(gen ## _g ## _null_state_batch)/4, \
+	}
+
+#endif /* INTEL_RENDERSTATE_H */
diff --git a/drivers/gpu/drm/i915/intel_renderstate_gen6.c b/drivers/gpu/drm/i915/intel_renderstate_gen6.c
new file mode 100644
index 00000000000..740538ad097
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_renderstate_gen6.c
@@ -0,0 +1,289 @@
+#include "intel_renderstate.h"
+
+static const u32 gen6_null_state_relocs[] = {
+	0x00000020,
+	0x00000024,
+	0x0000002c,
+	0x000001e0,
+	0x000001e4,
+};
+
+static const u32 gen6_null_state_batch[] = {
+	0x69040000,
+	0x790d0001,
+	0x00000000,
+	0x00000000,
+	0x78180000,
+	0x00000001,
+	0x61010008,
+	0x00000000,
+	0x00000001,	 /* reloc */
+	0x00000001,	 /* reloc */
+	0x00000000,
+	0x00000001,	 /* reloc */
+	0x00000000,
+	0x00000001,
+	0x00000000,
+	0x00000001,
+	0x61020000,
+	0x00000000,
+	0x78050001,
+	0x00000018,
+	0x00000000,
+	0x780d1002,
+	0x00000000,
+	0x00000000,
+	0x00000420,
+	0x78150003,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78100004,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78160003,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78110005,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78120002,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78170003,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x79050005,
+	0xe0040000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x79100000,
+	0x00000000,
+	0x79000002,
+	0xffffffff,
+	0x00000000,
+	0x00000000,
+	0x780e0002,
+	0x00000441,
+	0x00000401,
+	0x00000401,
+	0x78021002,
+	0x00000000,
+	0x00000000,
+	0x00000400,
+	0x78130012,
+	0x00400810,
+	0x00000000,
+	0x20000000,
+	0x04000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78140007,
+	0x00000280,
+	0x08080000,
+	0x00000000,
+	0x00060000,
+	0x4e080002,
+	0x00100400,
+	0x00000000,
+	0x00000000,
+	0x78090005,
+	0x02000000,
+	0x22220000,
+	0x02f60000,
+	0x11330000,
+	0x02850004,
+	0x11220000,
+	0x78011002,
+	0x00000000,
+	0x00000000,
+	0x00000200,
+	0x78080003,
+	0x00002000,
+	0x00000448,	 /* reloc */
+	0x00000448,	 /* reloc */
+	0x00000000,
+	0x05000000,	 /* cmds end */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000220,	 /* state start */
+	0x00000240,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0060005a,
+	0x204077be,
+	0x000000c0,
+	0x008d0040,
+	0x0060005a,
+	0x206077be,
+	0x000000c0,
+	0x008d0080,
+	0x0060005a,
+	0x208077be,
+	0x000000d0,
+	0x008d0040,
+	0x0060005a,
+	0x20a077be,
+	0x000000d0,
+	0x008d0080,
+	0x00000201,
+	0x20080061,
+	0x00000000,
+	0x00000000,
+	0x00600001,
+	0x20200022,
+	0x008d0000,
+	0x00000000,
+	0x02800031,
+	0x21c01cc9,
+	0x00000020,
+	0x0a8a0001,
+	0x00600001,
+	0x204003be,
+	0x008d01c0,
+	0x00000000,
+	0x00600001,
+	0x206003be,
+	0x008d01e0,
+	0x00000000,
+	0x00600001,
+	0x208003be,
+	0x008d0200,
+	0x00000000,
+	0x00600001,
+	0x20a003be,
+	0x008d0220,
+	0x00000000,
+	0x00600001,
+	0x20c003be,
+	0x008d0240,
+	0x00000000,
+	0x00600001,
+	0x20e003be,
+	0x008d0260,
+	0x00000000,
+	0x00600001,
+	0x210003be,
+	0x008d0280,
+	0x00000000,
+	0x00600001,
+	0x212003be,
+	0x008d02a0,
+	0x00000000,
+	0x05800031,
+	0x24001cc8,
+	0x00000040,
+	0x90019000,
+	0x0000007e,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000007e,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000007e,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000007e,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000007e,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000007e,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000007e,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000007e,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x30000000,
+	0x00000124,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0xf99a130c,
+	0x799a130c,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x80000031,
+	0x00000003,
+	0x00000000,	 /* state end */
+};
+
+RO_RENDERSTATE(6);
diff --git a/drivers/gpu/drm/i915/intel_renderstate_gen7.c b/drivers/gpu/drm/i915/intel_renderstate_gen7.c
new file mode 100644
index 00000000000..6fa7ff2a129
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_renderstate_gen7.c
@@ -0,0 +1,253 @@
+#include "intel_renderstate.h"
+
+static const u32 gen7_null_state_relocs[] = {
+	0x0000000c,
+	0x00000010,
+	0x00000018,
+	0x000001ec,
+};
+
+static const u32 gen7_null_state_batch[] = {
+	0x69040000,
+	0x61010008,
+	0x00000000,
+	0x00000001,	 /* reloc */
+	0x00000001,	 /* reloc */
+	0x00000000,
+	0x00000001,	 /* reloc */
+	0x00000000,
+	0x00000001,
+	0x00000000,
+	0x00000001,
+	0x790d0002,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78180000,
+	0x00000001,
+	0x79160000,
+	0x00000008,
+	0x78300000,
+	0x02010040,
+	0x78310000,
+	0x04000000,
+	0x78320000,
+	0x04000000,
+	0x78330000,
+	0x02000000,
+	0x78100004,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x781b0005,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x781c0002,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x781d0004,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78110005,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78120002,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78210000,
+	0x00000000,
+	0x78130005,
+	0x00000000,
+	0x20000000,
+	0x04000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78140001,
+	0x20000800,
+	0x00000000,
+	0x781e0001,
+	0x00000000,
+	0x00000000,
+	0x78050005,
+	0xe0040000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78040001,
+	0x00000000,
+	0x00000000,
+	0x78240000,
+	0x00000240,
+	0x78230000,
+	0x00000260,
+	0x782f0000,
+	0x00000280,
+	0x781f000c,
+	0x00400810,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78200006,
+	0x000002c0,
+	0x08080000,
+	0x00000000,
+	0x28000402,
+	0x00060000,
+	0x00000000,
+	0x00000000,
+	0x78090005,
+	0x02000000,
+	0x22220000,
+	0x02f60000,
+	0x11230000,
+	0x02f60004,
+	0x11230000,
+	0x78080003,
+	0x00006008,
+	0x00000340,	 /* reloc */
+	0xffffffff,
+	0x00000000,
+	0x782a0000,
+	0x00000360,
+	0x79000002,
+	0xffffffff,
+	0x00000000,
+	0x00000000,
+	0x7b000005,
+	0x0000000f,
+	0x00000003,
+	0x00000000,
+	0x00000001,
+	0x00000000,
+	0x00000000,
+	0x05000000,	 /* cmds end */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000031,	 /* state start */
+	0x00000003,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0xf99a130c,
+	0x799a130c,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000492,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0080005a,
+	0x2e2077bd,
+	0x000000c0,
+	0x008d0040,
+	0x0080005a,
+	0x2e6077bd,
+	0x000000d0,
+	0x008d0040,
+	0x02800031,
+	0x21801fa9,
+	0x008d0e20,
+	0x08840001,
+	0x00800001,
+	0x2e2003bd,
+	0x008d0180,
+	0x00000000,
+	0x00800001,
+	0x2e6003bd,
+	0x008d01c0,
+	0x00000000,
+	0x00800001,
+	0x2ea003bd,
+	0x008d0200,
+	0x00000000,
+	0x00800001,
+	0x2ee003bd,
+	0x008d0240,
+	0x00000000,
+	0x05800031,
+	0x20001fa8,
+	0x008d0e20,
+	0x90031000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000380,
+	0x000003a0,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,	 /* state end */
+};
+
+RO_RENDERSTATE(7);
diff --git a/drivers/gpu/drm/i915/intel_renderstate_gen8.c b/drivers/gpu/drm/i915/intel_renderstate_gen8.c
new file mode 100644
index 00000000000..5c875615d42
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_renderstate_gen8.c
@@ -0,0 +1,479 @@
+#include "intel_renderstate.h"
+
+static const u32 gen8_null_state_relocs[] = {
+	0x00000048,
+	0x00000050,
+	0x00000060,
+	0x000003ec,
+};
+
+static const u32 gen8_null_state_batch[] = {
+	0x69040000,
+	0x61020001,
+	0x00000000,
+	0x00000000,
+	0x79120000,
+	0x00000000,
+	0x79130000,
+	0x00000000,
+	0x79140000,
+	0x00000000,
+	0x79150000,
+	0x00000000,
+	0x79160000,
+	0x00000000,
+	0x6101000e,
+	0x00000001,
+	0x00000000,
+	0x00000001,
+	0x00000001,	 /* reloc */
+	0x00000000,
+	0x00000001,	 /* reloc */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000001,	 /* reloc */
+	0x00000000,
+	0xfffff001,
+	0x00001001,
+	0xfffff001,
+	0x00001001,
+	0x78230000,
+	0x000006e0,
+	0x78210000,
+	0x00000700,
+	0x78300000,
+	0x08010040,
+	0x78330000,
+	0x08000000,
+	0x78310000,
+	0x08000000,
+	0x78320000,
+	0x08000000,
+	0x78240000,
+	0x00000641,
+	0x780e0000,
+	0x00000601,
+	0x780d0000,
+	0x00000000,
+	0x78180000,
+	0x00000001,
+	0x78520003,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78190009,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x781b0007,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78270000,
+	0x00000000,
+	0x782c0000,
+	0x00000000,
+	0x781c0002,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78160009,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78110008,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78290000,
+	0x00000000,
+	0x782e0000,
+	0x00000000,
+	0x781a0009,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x781d0007,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78280000,
+	0x00000000,
+	0x782d0000,
+	0x00000000,
+	0x78260000,
+	0x00000000,
+	0x782b0000,
+	0x00000000,
+	0x78150009,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78100007,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x781e0003,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78120002,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x781f0002,
+	0x30400820,
+	0x00000000,
+	0x00000000,
+	0x78510009,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78500003,
+	0x00210000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78130002,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x782a0000,
+	0x00000480,
+	0x782f0000,
+	0x00000540,
+	0x78140000,
+	0x00000800,
+	0x78170009,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x7820000a,
+	0x00000580,
+	0x00000000,
+	0x08080000,
+	0x00000000,
+	0x00000000,
+	0x1f000002,
+	0x00060000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x784d0000,
+	0x40000000,
+	0x784f0000,
+	0x80000100,
+	0x780f0000,
+	0x00000740,
+	0x78050006,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78070003,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78060003,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x78040001,
+	0x00000000,
+	0x00000001,
+	0x79000002,
+	0xffffffff,
+	0x00000000,
+	0x00000000,
+	0x78080003,
+	0x00006000,
+	0x000005e0,	 /* reloc */
+	0x00000000,
+	0x00000000,
+	0x78090005,
+	0x02000000,
+	0x22220000,
+	0x02f60000,
+	0x11230000,
+	0x02850004,
+	0x11230000,
+	0x784b0000,
+	0x0000000f,
+	0x78490001,
+	0x00000000,
+	0x00000000,
+	0x7b000005,
+	0x00000000,
+	0x00000003,
+	0x00000000,
+	0x00000001,
+	0x00000000,
+	0x00000000,
+	0x05000000,	 /* cmds end */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x000004c0,	 /* state start */
+	0x00000500,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000092,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0060005a,
+	0x21403ae8,
+	0x3a0000c0,
+	0x008d0040,
+	0x0060005a,
+	0x21603ae8,
+	0x3a0000c0,
+	0x008d0080,
+	0x0060005a,
+	0x21803ae8,
+	0x3a0000d0,
+	0x008d0040,
+	0x0060005a,
+	0x21a03ae8,
+	0x3a0000d0,
+	0x008d0080,
+	0x02800031,
+	0x2e0022e8,
+	0x0e000140,
+	0x08840001,
+	0x05800031,
+	0x200022e0,
+	0x0e000e00,
+	0x90031000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x06200000,
+	0x00000002,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0xf99a130c,
+	0x799a130c,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x3f800000,
+	0x00000000,
+	0x3f800000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,	 /* state end */
+};
+
+RO_RENDERSTATE(8);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 79fb4cc2137..279488addf3 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -33,26 +33,44 @@
 #include "i915_trace.h"
 #include "intel_drv.h"
 
-static inline int ring_space(struct intel_ring_buffer *ring)
+/* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
+ * but keeps the logic simple. Indeed, the whole purpose of this macro is just
+ * to give some inclination as to some of the magic values used in the various
+ * workarounds!
+ */
+#define CACHELINE_BYTES 64
+
+static inline int __ring_space(int head, int tail, int size)
 {
-	int space = (ring->head & HEAD_ADDR) - (ring->tail + I915_RING_FREE_SPACE);
+	int space = head - (tail + I915_RING_FREE_SPACE);
 	if (space < 0)
-		space += ring->size;
+		space += size;
 	return space;
 }
 
-void __intel_ring_advance(struct intel_ring_buffer *ring)
+static inline int ring_space(struct intel_engine_cs *ring)
+{
+	struct intel_ringbuffer *ringbuf = ring->buffer;
+	return __ring_space(ringbuf->head & HEAD_ADDR, ringbuf->tail, ringbuf->size);
+}
+
+static bool intel_ring_stopped(struct intel_engine_cs *ring)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	return dev_priv->gpu_error.stop_rings & intel_ring_flag(ring);
+}
 
-	ring->tail &= ring->size - 1;
-	if (dev_priv->gpu_error.stop_rings & intel_ring_flag(ring))
+void __intel_ring_advance(struct intel_engine_cs *ring)
+{
+	struct intel_ringbuffer *ringbuf = ring->buffer;
+	ringbuf->tail &= ringbuf->size - 1;
+	if (intel_ring_stopped(ring))
 		return;
-	ring->write_tail(ring, ring->tail);
+	ring->write_tail(ring, ringbuf->tail);
 }
 
 static int
-gen2_render_ring_flush(struct intel_ring_buffer *ring,
+gen2_render_ring_flush(struct intel_engine_cs *ring,
 		       u32	invalidate_domains,
 		       u32	flush_domains)
 {
@@ -78,7 +96,7 @@ gen2_render_ring_flush(struct intel_ring_buffer *ring,
 }
 
 static int
-gen4_render_ring_flush(struct intel_ring_buffer *ring,
+gen4_render_ring_flush(struct intel_engine_cs *ring,
 		       u32	invalidate_domains,
 		       u32	flush_domains)
 {
@@ -173,9 +191,9 @@ gen4_render_ring_flush(struct intel_ring_buffer *ring,
  * really our business.  That leaves only stall at scoreboard.
  */
 static int
-intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring)
+intel_emit_post_sync_nonzero_flush(struct intel_engine_cs *ring)
 {
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 
@@ -208,11 +226,11 @@ intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring)
 }
 
 static int
-gen6_render_ring_flush(struct intel_ring_buffer *ring,
+gen6_render_ring_flush(struct intel_engine_cs *ring,
                          u32 invalidate_domains, u32 flush_domains)
 {
 	u32 flags = 0;
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 	/* Force SNB workarounds for PIPE_CONTROL flushes */
@@ -260,7 +278,7 @@ gen6_render_ring_flush(struct intel_ring_buffer *ring,
 }
 
 static int
-gen7_render_ring_cs_stall_wa(struct intel_ring_buffer *ring)
+gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring)
 {
 	int ret;
 
@@ -278,7 +296,7 @@ gen7_render_ring_cs_stall_wa(struct intel_ring_buffer *ring)
 	return 0;
 }
 
-static int gen7_ring_fbc_flush(struct intel_ring_buffer *ring, u32 value)
+static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value)
 {
 	int ret;
 
@@ -302,11 +320,11 @@ static int gen7_ring_fbc_flush(struct intel_ring_buffer *ring, u32 value)
 }
 
 static int
-gen7_render_ring_flush(struct intel_ring_buffer *ring,
+gen7_render_ring_flush(struct intel_engine_cs *ring,
 		       u32 invalidate_domains, u32 flush_domains)
 {
 	u32 flags = 0;
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 	/*
@@ -363,11 +381,11 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring,
 }
 
 static int
-gen8_render_ring_flush(struct intel_ring_buffer *ring,
+gen8_render_ring_flush(struct intel_engine_cs *ring,
 		       u32 invalidate_domains, u32 flush_domains)
 {
 	u32 flags = 0;
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 	flags |= PIPE_CONTROL_CS_STALL;
@@ -403,14 +421,14 @@ gen8_render_ring_flush(struct intel_ring_buffer *ring,
 
 }
 
-static void ring_write_tail(struct intel_ring_buffer *ring,
+static void ring_write_tail(struct intel_engine_cs *ring,
 			    u32 value)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	I915_WRITE_TAIL(ring, value);
 }
 
-u64 intel_ring_get_active_head(struct intel_ring_buffer *ring)
+u64 intel_ring_get_active_head(struct intel_engine_cs *ring)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	u64 acthd;
@@ -426,7 +444,7 @@ u64 intel_ring_get_active_head(struct intel_ring_buffer *ring)
 	return acthd;
 }
 
-static void ring_setup_phys_status_page(struct intel_ring_buffer *ring)
+static void ring_setup_phys_status_page(struct intel_engine_cs *ring)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	u32 addr;
@@ -437,7 +455,7 @@ static void ring_setup_phys_status_page(struct intel_ring_buffer *ring)
 	I915_WRITE(HWS_PGA, addr);
 }
 
-static bool stop_ring(struct intel_ring_buffer *ring)
+static bool stop_ring(struct intel_engine_cs *ring)
 {
 	struct drm_i915_private *dev_priv = to_i915(ring->dev);
 
@@ -461,11 +479,12 @@ static bool stop_ring(struct intel_ring_buffer *ring)
 	return (I915_READ_HEAD(ring) & HEAD_ADDR) == 0;
 }
 
-static int init_ring_common(struct intel_ring_buffer *ring)
+static int init_ring_common(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj = ring->obj;
+	struct intel_ringbuffer *ringbuf = ring->buffer;
+	struct drm_i915_gem_object *obj = ringbuf->obj;
 	int ret = 0;
 
 	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
@@ -504,7 +523,7 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	 * register values. */
 	I915_WRITE_START(ring, i915_gem_obj_ggtt_offset(obj));
 	I915_WRITE_CTL(ring,
-			((ring->size - PAGE_SIZE) & RING_NR_PAGES)
+			((ringbuf->size - PAGE_SIZE) & RING_NR_PAGES)
 			| RING_VALID);
 
 	/* If the head is still not zero, the ring is dead */
@@ -512,12 +531,11 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 		     I915_READ_START(ring) == i915_gem_obj_ggtt_offset(obj) &&
 		     (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) {
 		DRM_ERROR("%s initialization failed "
-				"ctl %08x head %08x tail %08x start %08x\n",
-				ring->name,
-				I915_READ_CTL(ring),
-				I915_READ_HEAD(ring),
-				I915_READ_TAIL(ring),
-				I915_READ_START(ring));
+			  "ctl %08x (valid? %d) head %08x tail %08x start %08x [expected %08lx]\n",
+			  ring->name,
+			  I915_READ_CTL(ring), I915_READ_CTL(ring) & RING_VALID,
+			  I915_READ_HEAD(ring), I915_READ_TAIL(ring),
+			  I915_READ_START(ring), (unsigned long)i915_gem_obj_ggtt_offset(obj));
 		ret = -EIO;
 		goto out;
 	}
@@ -525,10 +543,10 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	if (!drm_core_check_feature(ring->dev, DRIVER_MODESET))
 		i915_kernel_lost_context(ring->dev);
 	else {
-		ring->head = I915_READ_HEAD(ring);
-		ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
-		ring->space = ring_space(ring);
-		ring->last_retired_head = -1;
+		ringbuf->head = I915_READ_HEAD(ring);
+		ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
+		ringbuf->space = ring_space(ring);
+		ringbuf->last_retired_head = -1;
 	}
 
 	memset(&ring->hangcheck, 0, sizeof(ring->hangcheck));
@@ -540,7 +558,7 @@ out:
 }
 
 static int
-init_pipe_control(struct intel_ring_buffer *ring)
+init_pipe_control(struct intel_engine_cs *ring)
 {
 	int ret;
 
@@ -581,7 +599,7 @@ err:
 	return ret;
 }
 
-static int init_render_ring(struct intel_ring_buffer *ring)
+static int init_render_ring(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -595,19 +613,21 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
 	 * programmed to '1' on all products.
 	 *
-	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw
+	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv
 	 */
 	if (INTEL_INFO(dev)->gen >= 6)
 		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
 
 	/* Required for the hardware to program scanline values for waiting */
+	/* WaEnableFlushTlbInvalidationMode:snb */
 	if (INTEL_INFO(dev)->gen == 6)
 		I915_WRITE(GFX_MODE,
-			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_ALWAYS));
+			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT));
 
+	/* WaBCSVCSTlbInvalidationMode:ivb,vlv,hsw */
 	if (IS_GEN7(dev))
 		I915_WRITE(GFX_MODE_GEN7,
-			   _MASKED_BIT_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) |
+			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT) |
 			   _MASKED_BIT_ENABLE(GFX_REPLAY_MODE));
 
 	if (INTEL_INFO(dev)->gen >= 5) {
@@ -624,13 +644,6 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 		 */
 		I915_WRITE(CACHE_MODE_0,
 			   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
-
-		/* This is not explicitly set for GEN6, so read the register.
-		 * see intel_ring_mi_set_context() for why we care.
-		 * TODO: consider explicitly setting the bit for GEN5
-		 */
-		ring->itlb_before_ctx_switch =
-			!!(I915_READ(GFX_MODE) & GFX_TLB_INVALIDATE_ALWAYS);
 	}
 
 	if (INTEL_INFO(dev)->gen >= 6)
@@ -642,7 +655,7 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	return ret;
 }
 
-static void render_ring_cleanup(struct intel_ring_buffer *ring)
+static void render_ring_cleanup(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 
@@ -658,20 +671,46 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring)
 	ring->scratch.obj = NULL;
 }
 
-static void
-update_mboxes(struct intel_ring_buffer *ring,
-	      u32 mmio_offset)
+static int gen6_signal(struct intel_engine_cs *signaller,
+		       unsigned int num_dwords)
 {
-/* NB: In order to be able to do semaphore MBOX updates for varying number
- * of rings, it's easiest if we round up each individual update to a
- * multiple of 2 (since ring updates must always be a multiple of 2)
- * even though the actual update only requires 3 dwords.
- */
+	struct drm_device *dev = signaller->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *useless;
+	int i, ret;
+
+	/* NB: In order to be able to do semaphore MBOX updates for varying
+	 * number of rings, it's easiest if we round up each individual update
+	 * to a multiple of 2 (since ring updates must always be a multiple of
+	 * 2) even though the actual update only requires 3 dwords.
+	 */
 #define MBOX_UPDATE_DWORDS 4
-	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-	intel_ring_emit(ring, mmio_offset);
-	intel_ring_emit(ring, ring->outstanding_lazy_seqno);
-	intel_ring_emit(ring, MI_NOOP);
+	if (i915_semaphore_is_enabled(dev))
+		num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS);
+	else
+		return intel_ring_begin(signaller, num_dwords);
+
+	ret = intel_ring_begin(signaller, num_dwords);
+	if (ret)
+		return ret;
+#undef MBOX_UPDATE_DWORDS
+
+	for_each_ring(useless, dev_priv, i) {
+		u32 mbox_reg = signaller->semaphore.mbox.signal[i];
+		if (mbox_reg != GEN6_NOSYNC) {
+			intel_ring_emit(signaller, MI_LOAD_REGISTER_IMM(1));
+			intel_ring_emit(signaller, mbox_reg);
+			intel_ring_emit(signaller, signaller->outstanding_lazy_seqno);
+			intel_ring_emit(signaller, MI_NOOP);
+		} else {
+			intel_ring_emit(signaller, MI_NOOP);
+			intel_ring_emit(signaller, MI_NOOP);
+			intel_ring_emit(signaller, MI_NOOP);
+			intel_ring_emit(signaller, MI_NOOP);
+		}
+	}
+
+	return 0;
 }
 
 /**
@@ -684,29 +723,14 @@ update_mboxes(struct intel_ring_buffer *ring,
  * This acts like a signal in the canonical semaphore.
  */
 static int
-gen6_add_request(struct intel_ring_buffer *ring)
+gen6_add_request(struct intel_engine_cs *ring)
 {
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *useless;
-	int i, ret, num_dwords = 4;
-
-	if (i915_semaphore_is_enabled(dev))
-		num_dwords += ((I915_NUM_RINGS-1) * MBOX_UPDATE_DWORDS);
-#undef MBOX_UPDATE_DWORDS
+	int ret;
 
-	ret = intel_ring_begin(ring, num_dwords);
+	ret = ring->semaphore.signal(ring, 4);
 	if (ret)
 		return ret;
 
-	if (i915_semaphore_is_enabled(dev)) {
-		for_each_ring(useless, dev_priv, i) {
-			u32 mbox_reg = ring->signal_mbox[i];
-			if (mbox_reg != GEN6_NOSYNC)
-				update_mboxes(ring, mbox_reg);
-		}
-	}
-
 	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
 	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
 	intel_ring_emit(ring, ring->outstanding_lazy_seqno);
@@ -731,14 +755,15 @@ static inline bool i915_gem_has_seqno_wrapped(struct drm_device *dev,
  * @seqno - seqno which the waiter will block on
  */
 static int
-gen6_ring_sync(struct intel_ring_buffer *waiter,
-	       struct intel_ring_buffer *signaller,
+gen6_ring_sync(struct intel_engine_cs *waiter,
+	       struct intel_engine_cs *signaller,
 	       u32 seqno)
 {
-	int ret;
 	u32 dw1 = MI_SEMAPHORE_MBOX |
 		  MI_SEMAPHORE_COMPARE |
 		  MI_SEMAPHORE_REGISTER;
+	u32 wait_mbox = signaller->semaphore.mbox.wait[waiter->id];
+	int ret;
 
 	/* Throughout all of the GEM code, seqno passed implies our current
 	 * seqno is >= the last seqno executed. However for hardware the
@@ -746,8 +771,7 @@ gen6_ring_sync(struct intel_ring_buffer *waiter,
 	 */
 	seqno -= 1;
 
-	WARN_ON(signaller->semaphore_register[waiter->id] ==
-		MI_SEMAPHORE_SYNC_INVALID);
+	WARN_ON(wait_mbox == MI_SEMAPHORE_SYNC_INVALID);
 
 	ret = intel_ring_begin(waiter, 4);
 	if (ret)
@@ -755,9 +779,7 @@ gen6_ring_sync(struct intel_ring_buffer *waiter,
 
 	/* If seqno wrap happened, omit the wait with no-ops */
 	if (likely(!i915_gem_has_seqno_wrapped(waiter->dev, seqno))) {
-		intel_ring_emit(waiter,
-				dw1 |
-				signaller->semaphore_register[waiter->id]);
+		intel_ring_emit(waiter, dw1 | wait_mbox);
 		intel_ring_emit(waiter, seqno);
 		intel_ring_emit(waiter, 0);
 		intel_ring_emit(waiter, MI_NOOP);
@@ -782,9 +804,9 @@ do {									\
 } while (0)
 
 static int
-pc_render_add_request(struct intel_ring_buffer *ring)
+pc_render_add_request(struct intel_engine_cs *ring)
 {
-	u32 scratch_addr = ring->scratch.gtt_offset + 128;
+	u32 scratch_addr = ring->scratch.gtt_offset + 2 * CACHELINE_BYTES;
 	int ret;
 
 	/* For Ironlake, MI_USER_INTERRUPT was deprecated and apparently
@@ -806,15 +828,15 @@ pc_render_add_request(struct intel_ring_buffer *ring)
 	intel_ring_emit(ring, ring->outstanding_lazy_seqno);
 	intel_ring_emit(ring, 0);
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128; /* write to separate cachelines */
+	scratch_addr += 2 * CACHELINE_BYTES; /* write to separate cachelines */
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128;
+	scratch_addr += 2 * CACHELINE_BYTES;
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128;
+	scratch_addr += 2 * CACHELINE_BYTES;
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128;
+	scratch_addr += 2 * CACHELINE_BYTES;
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
-	scratch_addr += 128;
+	scratch_addr += 2 * CACHELINE_BYTES;
 	PIPE_CONTROL_FLUSH(ring, scratch_addr);
 
 	intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |
@@ -830,7 +852,7 @@ pc_render_add_request(struct intel_ring_buffer *ring)
 }
 
 static u32
-gen6_ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
+gen6_ring_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency)
 {
 	/* Workaround to force correct ordering between irq and seqno writes on
 	 * ivb (and maybe also on snb) by reading from a CS register (like
@@ -844,31 +866,31 @@ gen6_ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
 }
 
 static u32
-ring_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
+ring_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency)
 {
 	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
 }
 
 static void
-ring_set_seqno(struct intel_ring_buffer *ring, u32 seqno)
+ring_set_seqno(struct intel_engine_cs *ring, u32 seqno)
 {
 	intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
 }
 
 static u32
-pc_render_get_seqno(struct intel_ring_buffer *ring, bool lazy_coherency)
+pc_render_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency)
 {
 	return ring->scratch.cpu_page[0];
 }
 
 static void
-pc_render_set_seqno(struct intel_ring_buffer *ring, u32 seqno)
+pc_render_set_seqno(struct intel_engine_cs *ring, u32 seqno)
 {
 	ring->scratch.cpu_page[0] = seqno;
 }
 
 static bool
-gen5_ring_get_irq(struct intel_ring_buffer *ring)
+gen5_ring_get_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -886,7 +908,7 @@ gen5_ring_get_irq(struct intel_ring_buffer *ring)
 }
 
 static void
-gen5_ring_put_irq(struct intel_ring_buffer *ring)
+gen5_ring_put_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -899,7 +921,7 @@ gen5_ring_put_irq(struct intel_ring_buffer *ring)
 }
 
 static bool
-i9xx_ring_get_irq(struct intel_ring_buffer *ring)
+i9xx_ring_get_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -920,7 +942,7 @@ i9xx_ring_get_irq(struct intel_ring_buffer *ring)
 }
 
 static void
-i9xx_ring_put_irq(struct intel_ring_buffer *ring)
+i9xx_ring_put_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -936,7 +958,7 @@ i9xx_ring_put_irq(struct intel_ring_buffer *ring)
 }
 
 static bool
-i8xx_ring_get_irq(struct intel_ring_buffer *ring)
+i8xx_ring_get_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -957,7 +979,7 @@ i8xx_ring_get_irq(struct intel_ring_buffer *ring)
 }
 
 static void
-i8xx_ring_put_irq(struct intel_ring_buffer *ring)
+i8xx_ring_put_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -972,7 +994,7 @@ i8xx_ring_put_irq(struct intel_ring_buffer *ring)
 	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
 
-void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
+void intel_ring_setup_status_page(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -989,6 +1011,11 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 		case BCS:
 			mmio = BLT_HWS_PGA_GEN7;
 			break;
+		/*
+		 * VCS2 actually doesn't exist on Gen7. Only shut up
+		 * gcc switch check warning
+		 */
+		case VCS2:
 		case VCS:
 			mmio = BSD_HWS_PGA_GEN7;
 			break;
@@ -1030,7 +1057,7 @@ void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
 }
 
 static int
-bsd_ring_flush(struct intel_ring_buffer *ring,
+bsd_ring_flush(struct intel_engine_cs *ring,
 	       u32     invalidate_domains,
 	       u32     flush_domains)
 {
@@ -1047,7 +1074,7 @@ bsd_ring_flush(struct intel_ring_buffer *ring,
 }
 
 static int
-i9xx_add_request(struct intel_ring_buffer *ring)
+i9xx_add_request(struct intel_engine_cs *ring)
 {
 	int ret;
 
@@ -1065,7 +1092,7 @@ i9xx_add_request(struct intel_ring_buffer *ring)
 }
 
 static bool
-gen6_ring_get_irq(struct intel_ring_buffer *ring)
+gen6_ring_get_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1090,7 +1117,7 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring)
 }
 
 static void
-gen6_ring_put_irq(struct intel_ring_buffer *ring)
+gen6_ring_put_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1108,7 +1135,7 @@ gen6_ring_put_irq(struct intel_ring_buffer *ring)
 }
 
 static bool
-hsw_vebox_get_irq(struct intel_ring_buffer *ring)
+hsw_vebox_get_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1128,7 +1155,7 @@ hsw_vebox_get_irq(struct intel_ring_buffer *ring)
 }
 
 static void
-hsw_vebox_put_irq(struct intel_ring_buffer *ring)
+hsw_vebox_put_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1146,7 +1173,7 @@ hsw_vebox_put_irq(struct intel_ring_buffer *ring)
 }
 
 static bool
-gen8_ring_get_irq(struct intel_ring_buffer *ring)
+gen8_ring_get_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1172,7 +1199,7 @@ gen8_ring_get_irq(struct intel_ring_buffer *ring)
 }
 
 static void
-gen8_ring_put_irq(struct intel_ring_buffer *ring)
+gen8_ring_put_irq(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1192,8 +1219,8 @@ gen8_ring_put_irq(struct intel_ring_buffer *ring)
 }
 
 static int
-i965_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			 u32 offset, u32 length,
+i965_dispatch_execbuffer(struct intel_engine_cs *ring,
+			 u64 offset, u32 length,
 			 unsigned flags)
 {
 	int ret;
@@ -1215,8 +1242,8 @@ i965_dispatch_execbuffer(struct intel_ring_buffer *ring,
 /* Just userspace ABI convention to limit the wa batch bo to a resonable size */
 #define I830_BATCH_LIMIT (256*1024)
 static int
-i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
-				u32 offset, u32 len,
+i830_dispatch_execbuffer(struct intel_engine_cs *ring,
+				u64 offset, u32 len,
 				unsigned flags)
 {
 	int ret;
@@ -1266,8 +1293,8 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 }
 
 static int
-i915_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			 u32 offset, u32 len,
+i915_dispatch_execbuffer(struct intel_engine_cs *ring,
+			 u64 offset, u32 len,
 			 unsigned flags)
 {
 	int ret;
@@ -1283,7 +1310,7 @@ i915_dispatch_execbuffer(struct intel_ring_buffer *ring,
 	return 0;
 }
 
-static void cleanup_status_page(struct intel_ring_buffer *ring)
+static void cleanup_status_page(struct intel_engine_cs *ring)
 {
 	struct drm_i915_gem_object *obj;
 
@@ -1297,50 +1324,44 @@ static void cleanup_status_page(struct intel_ring_buffer *ring)
 	ring->status_page.obj = NULL;
 }
 
-static int init_status_page(struct intel_ring_buffer *ring)
+static int init_status_page(struct intel_engine_cs *ring)
 {
-	struct drm_device *dev = ring->dev;
 	struct drm_i915_gem_object *obj;
-	int ret;
 
-	obj = i915_gem_alloc_object(dev, 4096);
-	if (obj == NULL) {
-		DRM_ERROR("Failed to allocate status page\n");
-		ret = -ENOMEM;
-		goto err;
-	}
+	if ((obj = ring->status_page.obj) == NULL) {
+		int ret;
 
-	ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
-	if (ret)
-		goto err_unref;
+		obj = i915_gem_alloc_object(ring->dev, 4096);
+		if (obj == NULL) {
+			DRM_ERROR("Failed to allocate status page\n");
+			return -ENOMEM;
+		}
 
-	ret = i915_gem_obj_ggtt_pin(obj, 4096, 0);
-	if (ret)
-		goto err_unref;
+		ret = i915_gem_object_set_cache_level(obj, I915_CACHE_LLC);
+		if (ret)
+			goto err_unref;
+
+		ret = i915_gem_obj_ggtt_pin(obj, 4096, 0);
+		if (ret) {
+err_unref:
+			drm_gem_object_unreference(&obj->base);
+			return ret;
+		}
+
+		ring->status_page.obj = obj;
+	}
 
 	ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj);
 	ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl));
-	if (ring->status_page.page_addr == NULL) {
-		ret = -ENOMEM;
-		goto err_unpin;
-	}
-	ring->status_page.obj = obj;
 	memset(ring->status_page.page_addr, 0, PAGE_SIZE);
 
 	DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n",
 			ring->name, ring->status_page.gfx_addr);
 
 	return 0;
-
-err_unpin:
-	i915_gem_object_ggtt_unpin(obj);
-err_unref:
-	drm_gem_object_unreference(&obj->base);
-err:
-	return ret;
 }
 
-static int init_phys_status_page(struct intel_ring_buffer *ring)
+static int init_phys_status_page(struct intel_engine_cs *ring)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 
@@ -1357,44 +1378,24 @@ static int init_phys_status_page(struct intel_ring_buffer *ring)
 	return 0;
 }
 
-static int intel_init_ring_buffer(struct drm_device *dev,
-				  struct intel_ring_buffer *ring)
+static int allocate_ring_buffer(struct intel_engine_cs *ring)
 {
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_ringbuffer *ringbuf = ring->buffer;
 	struct drm_i915_gem_object *obj;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	ring->dev = dev;
-	INIT_LIST_HEAD(&ring->active_list);
-	INIT_LIST_HEAD(&ring->request_list);
-	ring->size = 32 * PAGE_SIZE;
-	memset(ring->sync_seqno, 0, sizeof(ring->sync_seqno));
-
-	init_waitqueue_head(&ring->irq_queue);
-
-	if (I915_NEED_GFX_HWS(dev)) {
-		ret = init_status_page(ring);
-		if (ret)
-			return ret;
-	} else {
-		BUG_ON(ring->id != RCS);
-		ret = init_phys_status_page(ring);
-		if (ret)
-			return ret;
-	}
+	if (intel_ring_initialized(ring))
+		return 0;
 
 	obj = NULL;
 	if (!HAS_LLC(dev))
-		obj = i915_gem_object_create_stolen(dev, ring->size);
+		obj = i915_gem_object_create_stolen(dev, ringbuf->size);
 	if (obj == NULL)
-		obj = i915_gem_alloc_object(dev, ring->size);
-	if (obj == NULL) {
-		DRM_ERROR("Failed to allocate ringbuffer\n");
-		ret = -ENOMEM;
-		goto err_hws;
-	}
-
-	ring->obj = obj;
+		obj = i915_gem_alloc_object(dev, ringbuf->size);
+	if (obj == NULL)
+		return -ENOMEM;
 
 	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
 	if (ret)
@@ -1404,65 +1405,102 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 	if (ret)
 		goto err_unpin;
 
-	ring->virtual_start =
+	ringbuf->virtual_start =
 		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
-			   ring->size);
-	if (ring->virtual_start == NULL) {
-		DRM_ERROR("Failed to map ringbuffer.\n");
+				ringbuf->size);
+	if (ringbuf->virtual_start == NULL) {
 		ret = -EINVAL;
 		goto err_unpin;
 	}
 
-	ret = ring->init(ring);
-	if (ret)
-		goto err_unmap;
+	ringbuf->obj = obj;
+	return 0;
+
+err_unpin:
+	i915_gem_object_ggtt_unpin(obj);
+err_unref:
+	drm_gem_object_unreference(&obj->base);
+	return ret;
+}
+
+static int intel_init_ring_buffer(struct drm_device *dev,
+				  struct intel_engine_cs *ring)
+{
+	struct intel_ringbuffer *ringbuf = ring->buffer;
+	int ret;
+
+	if (ringbuf == NULL) {
+		ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);
+		if (!ringbuf)
+			return -ENOMEM;
+		ring->buffer = ringbuf;
+	}
+
+	ring->dev = dev;
+	INIT_LIST_HEAD(&ring->active_list);
+	INIT_LIST_HEAD(&ring->request_list);
+	ringbuf->size = 32 * PAGE_SIZE;
+	memset(ring->semaphore.sync_seqno, 0, sizeof(ring->semaphore.sync_seqno));
+
+	init_waitqueue_head(&ring->irq_queue);
+
+	if (I915_NEED_GFX_HWS(dev)) {
+		ret = init_status_page(ring);
+		if (ret)
+			goto error;
+	} else {
+		BUG_ON(ring->id != RCS);
+		ret = init_phys_status_page(ring);
+		if (ret)
+			goto error;
+	}
+
+	ret = allocate_ring_buffer(ring);
+	if (ret) {
+		DRM_ERROR("Failed to allocate ringbuffer %s: %d\n", ring->name, ret);
+		goto error;
+	}
 
 	/* Workaround an erratum on the i830 which causes a hang if
 	 * the TAIL pointer points to within the last 2 cachelines
 	 * of the buffer.
 	 */
-	ring->effective_size = ring->size;
-	if (IS_I830(ring->dev) || IS_845G(ring->dev))
-		ring->effective_size -= 128;
+	ringbuf->effective_size = ringbuf->size;
+	if (IS_I830(dev) || IS_845G(dev))
+		ringbuf->effective_size -= 2 * CACHELINE_BYTES;
 
-	i915_cmd_parser_init_ring(ring);
+	ret = i915_cmd_parser_init_ring(ring);
+	if (ret)
+		goto error;
+
+	ret = ring->init(ring);
+	if (ret)
+		goto error;
 
 	return 0;
 
-err_unmap:
-	iounmap(ring->virtual_start);
-err_unpin:
-	i915_gem_object_ggtt_unpin(obj);
-err_unref:
-	drm_gem_object_unreference(&obj->base);
-	ring->obj = NULL;
-err_hws:
-	cleanup_status_page(ring);
+error:
+	kfree(ringbuf);
+	ring->buffer = NULL;
 	return ret;
 }
 
-void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring)
+void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
 {
-	struct drm_i915_private *dev_priv;
-	int ret;
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
+	struct intel_ringbuffer *ringbuf = ring->buffer;
 
-	if (ring->obj == NULL)
+	if (!intel_ring_initialized(ring))
 		return;
 
-	/* Disable the ring buffer. The ring must be idle at this point */
-	dev_priv = ring->dev->dev_private;
-	ret = intel_ring_idle(ring);
-	if (ret && !i915_reset_in_progress(&dev_priv->gpu_error))
-		DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n",
-			  ring->name, ret);
-
-	I915_WRITE_CTL(ring, 0);
+	intel_stop_ring_buffer(ring);
+	WARN_ON(!IS_GEN2(ring->dev) && (I915_READ_MODE(ring) & MODE_IDLE) == 0);
 
-	iounmap(ring->virtual_start);
+	iounmap(ringbuf->virtual_start);
 
-	i915_gem_object_ggtt_unpin(ring->obj);
-	drm_gem_object_unreference(&ring->obj->base);
-	ring->obj = NULL;
+	i915_gem_object_ggtt_unpin(ringbuf->obj);
+	drm_gem_object_unreference(&ringbuf->obj->base);
+	ringbuf->obj = NULL;
 	ring->preallocated_lazy_request = NULL;
 	ring->outstanding_lazy_seqno = 0;
 
@@ -1470,44 +1508,34 @@ void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring)
 		ring->cleanup(ring);
 
 	cleanup_status_page(ring);
+
+	i915_cmd_parser_fini_ring(ring);
+
+	kfree(ringbuf);
+	ring->buffer = NULL;
 }
 
-static int intel_ring_wait_request(struct intel_ring_buffer *ring, int n)
+static int intel_ring_wait_request(struct intel_engine_cs *ring, int n)
 {
+	struct intel_ringbuffer *ringbuf = ring->buffer;
 	struct drm_i915_gem_request *request;
-	u32 seqno = 0, tail;
+	u32 seqno = 0;
 	int ret;
 
-	if (ring->last_retired_head != -1) {
-		ring->head = ring->last_retired_head;
-		ring->last_retired_head = -1;
+	if (ringbuf->last_retired_head != -1) {
+		ringbuf->head = ringbuf->last_retired_head;
+		ringbuf->last_retired_head = -1;
 
-		ring->space = ring_space(ring);
-		if (ring->space >= n)
+		ringbuf->space = ring_space(ring);
+		if (ringbuf->space >= n)
 			return 0;
 	}
 
 	list_for_each_entry(request, &ring->request_list, list) {
-		int space;
-
-		if (request->tail == -1)
-			continue;
-
-		space = request->tail - (ring->tail + I915_RING_FREE_SPACE);
-		if (space < 0)
-			space += ring->size;
-		if (space >= n) {
+		if (__ring_space(request->tail, ringbuf->tail, ringbuf->size) >= n) {
 			seqno = request->seqno;
-			tail = request->tail;
 			break;
 		}
-
-		/* Consume this request in case we need more space than
-		 * is available and so need to prevent a race between
-		 * updating last_retired_head and direct reads of
-		 * I915_RING_HEAD. It also provides a nice sanity check.
-		 */
-		request->tail = -1;
 	}
 
 	if (seqno == 0)
@@ -1517,18 +1545,19 @@ static int intel_ring_wait_request(struct intel_ring_buffer *ring, int n)
 	if (ret)
 		return ret;
 
-	ring->head = tail;
-	ring->space = ring_space(ring);
-	if (WARN_ON(ring->space < n))
-		return -ENOSPC;
+	i915_gem_retire_requests_ring(ring);
+	ringbuf->head = ringbuf->last_retired_head;
+	ringbuf->last_retired_head = -1;
 
+	ringbuf->space = ring_space(ring);
 	return 0;
 }
 
-static int ring_wait_for_space(struct intel_ring_buffer *ring, int n)
+static int ring_wait_for_space(struct intel_engine_cs *ring, int n)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ringbuffer *ringbuf = ring->buffer;
 	unsigned long end;
 	int ret;
 
@@ -1539,7 +1568,6 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n)
 	/* force the tail write in case we have been skipping them */
 	__intel_ring_advance(ring);
 
-	trace_i915_ring_wait_begin(ring);
 	/* With GEM the hangcheck timer should kick us out of the loop,
 	 * leaving it early runs the risk of corrupting GEM state (due
 	 * to running on almost untested codepaths). But on resume
@@ -1547,12 +1575,13 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n)
 	 * case by choosing an insanely large timeout. */
 	end = jiffies + 60 * HZ;
 
+	trace_i915_ring_wait_begin(ring);
 	do {
-		ring->head = I915_READ_HEAD(ring);
-		ring->space = ring_space(ring);
-		if (ring->space >= n) {
-			trace_i915_ring_wait_end(ring);
-			return 0;
+		ringbuf->head = I915_READ_HEAD(ring);
+		ringbuf->space = ring_space(ring);
+		if (ringbuf->space >= n) {
+			ret = 0;
+			break;
 		}
 
 		if (!drm_core_check_feature(dev, DRIVER_MODESET) &&
@@ -1564,38 +1593,49 @@ static int ring_wait_for_space(struct intel_ring_buffer *ring, int n)
 
 		msleep(1);
 
+		if (dev_priv->mm.interruptible && signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
 		ret = i915_gem_check_wedge(&dev_priv->gpu_error,
 					   dev_priv->mm.interruptible);
 		if (ret)
-			return ret;
-	} while (!time_after(jiffies, end));
+			break;
+
+		if (time_after(jiffies, end)) {
+			ret = -EBUSY;
+			break;
+		}
+	} while (1);
 	trace_i915_ring_wait_end(ring);
-	return -EBUSY;
+	return ret;
 }
 
-static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring)
+static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
 {
 	uint32_t __iomem *virt;
-	int rem = ring->size - ring->tail;
+	struct intel_ringbuffer *ringbuf = ring->buffer;
+	int rem = ringbuf->size - ringbuf->tail;
 
-	if (ring->space < rem) {
+	if (ringbuf->space < rem) {
 		int ret = ring_wait_for_space(ring, rem);
 		if (ret)
 			return ret;
 	}
 
-	virt = ring->virtual_start + ring->tail;
+	virt = ringbuf->virtual_start + ringbuf->tail;
 	rem /= 4;
 	while (rem--)
 		iowrite32(MI_NOOP, virt++);
 
-	ring->tail = 0;
-	ring->space = ring_space(ring);
+	ringbuf->tail = 0;
+	ringbuf->space = ring_space(ring);
 
 	return 0;
 }
 
-int intel_ring_idle(struct intel_ring_buffer *ring)
+int intel_ring_idle(struct intel_engine_cs *ring)
 {
 	u32 seqno;
 	int ret;
@@ -1619,7 +1659,7 @@ int intel_ring_idle(struct intel_ring_buffer *ring)
 }
 
 static int
-intel_ring_alloc_seqno(struct intel_ring_buffer *ring)
+intel_ring_alloc_seqno(struct intel_engine_cs *ring)
 {
 	if (ring->outstanding_lazy_seqno)
 		return 0;
@@ -1637,18 +1677,19 @@ intel_ring_alloc_seqno(struct intel_ring_buffer *ring)
 	return i915_gem_get_seqno(ring->dev, &ring->outstanding_lazy_seqno);
 }
 
-static int __intel_ring_prepare(struct intel_ring_buffer *ring,
+static int __intel_ring_prepare(struct intel_engine_cs *ring,
 				int bytes)
 {
+	struct intel_ringbuffer *ringbuf = ring->buffer;
 	int ret;
 
-	if (unlikely(ring->tail + bytes > ring->effective_size)) {
+	if (unlikely(ringbuf->tail + bytes > ringbuf->effective_size)) {
 		ret = intel_wrap_ring_buffer(ring);
 		if (unlikely(ret))
 			return ret;
 	}
 
-	if (unlikely(ring->space < bytes)) {
+	if (unlikely(ringbuf->space < bytes)) {
 		ret = ring_wait_for_space(ring, bytes);
 		if (unlikely(ret))
 			return ret;
@@ -1657,7 +1698,7 @@ static int __intel_ring_prepare(struct intel_ring_buffer *ring,
 	return 0;
 }
 
-int intel_ring_begin(struct intel_ring_buffer *ring,
+int intel_ring_begin(struct intel_engine_cs *ring,
 		     int num_dwords)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -1677,19 +1718,20 @@ int intel_ring_begin(struct intel_ring_buffer *ring,
 	if (ret)
 		return ret;
 
-	ring->space -= num_dwords * sizeof(uint32_t);
+	ring->buffer->space -= num_dwords * sizeof(uint32_t);
 	return 0;
 }
 
 /* Align the ring tail to a cacheline boundary */
-int intel_ring_cacheline_align(struct intel_ring_buffer *ring)
+int intel_ring_cacheline_align(struct intel_engine_cs *ring)
 {
-	int num_dwords = (64 - (ring->tail & 63)) / sizeof(uint32_t);
+	int num_dwords = (ring->buffer->tail & (CACHELINE_BYTES - 1)) / sizeof(uint32_t);
 	int ret;
 
 	if (num_dwords == 0)
 		return 0;
 
+	num_dwords = CACHELINE_BYTES / sizeof(uint32_t) - num_dwords;
 	ret = intel_ring_begin(ring, num_dwords);
 	if (ret)
 		return ret;
@@ -1702,7 +1744,7 @@ int intel_ring_cacheline_align(struct intel_ring_buffer *ring)
 	return 0;
 }
 
-void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
+void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 
@@ -1719,7 +1761,7 @@ void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno)
 	ring->hangcheck.seqno = seqno;
 }
 
-static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring,
+static void gen6_bsd_ring_write_tail(struct intel_engine_cs *ring,
 				     u32 value)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -1752,7 +1794,7 @@ static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring,
 		   _MASKED_BIT_DISABLE(GEN6_BSD_SLEEP_MSG_DISABLE));
 }
 
-static int gen6_bsd_ring_flush(struct intel_ring_buffer *ring,
+static int gen6_bsd_ring_flush(struct intel_engine_cs *ring,
 			       u32 invalidate, u32 flush)
 {
 	uint32_t cmd;
@@ -1788,8 +1830,8 @@ static int gen6_bsd_ring_flush(struct intel_ring_buffer *ring,
 }
 
 static int
-gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			      u32 offset, u32 len,
+gen8_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
+			      u64 offset, u32 len,
 			      unsigned flags)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -1803,8 +1845,8 @@ gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 
 	/* FIXME(BDW): Address space and security selectors. */
 	intel_ring_emit(ring, MI_BATCH_BUFFER_START_GEN8 | (ppgtt<<8));
-	intel_ring_emit(ring, offset);
-	intel_ring_emit(ring, 0);
+	intel_ring_emit(ring, lower_32_bits(offset));
+	intel_ring_emit(ring, upper_32_bits(offset));
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
 
@@ -1812,8 +1854,8 @@ gen8_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 }
 
 static int
-hsw_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			      u32 offset, u32 len,
+hsw_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
+			      u64 offset, u32 len,
 			      unsigned flags)
 {
 	int ret;
@@ -1833,8 +1875,8 @@ hsw_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 }
 
 static int
-gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
-			      u32 offset, u32 len,
+gen6_ring_dispatch_execbuffer(struct intel_engine_cs *ring,
+			      u64 offset, u32 len,
 			      unsigned flags)
 {
 	int ret;
@@ -1855,7 +1897,7 @@ gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 
 /* Blitter support (SandyBridge+) */
 
-static int gen6_ring_flush(struct intel_ring_buffer *ring,
+static int gen6_ring_flush(struct intel_engine_cs *ring,
 			   u32 invalidate, u32 flush)
 {
 	struct drm_device *dev = ring->dev;
@@ -1898,7 +1940,7 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring,
 int intel_init_render_ring_buffer(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
 
 	ring->name = "render ring";
 	ring->id = RCS;
@@ -1920,15 +1962,24 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
-		ring->sync_to = gen6_ring_sync;
-		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID;
-		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV;
-		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB;
-		ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_RVE;
-		ring->signal_mbox[RCS] = GEN6_NOSYNC;
-		ring->signal_mbox[VCS] = GEN6_VRSYNC;
-		ring->signal_mbox[BCS] = GEN6_BRSYNC;
-		ring->signal_mbox[VECS] = GEN6_VERSYNC;
+		ring->semaphore.sync_to = gen6_ring_sync;
+		ring->semaphore.signal = gen6_signal;
+		/*
+		 * The current semaphore is only applied on pre-gen8 platform.
+		 * And there is no VCS2 ring on the pre-gen8 platform. So the
+		 * semaphore between RCS and VCS2 is initialized as INVALID.
+		 * Gen8 will initialize the sema between VCS2 and RCS later.
+		 */
+		ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_RV;
+		ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_RB;
+		ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_RVE;
+		ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore.mbox.signal[RCS] = GEN6_NOSYNC;
+		ring->semaphore.mbox.signal[VCS] = GEN6_VRSYNC;
+		ring->semaphore.mbox.signal[BCS] = GEN6_BRSYNC;
+		ring->semaphore.mbox.signal[VECS] = GEN6_VERSYNC;
+		ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
 	} else if (IS_GEN5(dev)) {
 		ring->add_request = pc_render_add_request;
 		ring->flush = gen4_render_ring_flush;
@@ -1999,16 +2050,25 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
+	struct intel_ringbuffer *ringbuf = ring->buffer;
 	int ret;
 
+	if (ringbuf == NULL) {
+		ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);
+		if (!ringbuf)
+			return -ENOMEM;
+		ring->buffer = ringbuf;
+	}
+
 	ring->name = "render ring";
 	ring->id = RCS;
 	ring->mmio_base = RENDER_RING_BASE;
 
 	if (INTEL_INFO(dev)->gen >= 6) {
 		/* non-kms not supported on gen6+ */
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_ringbuf;
 	}
 
 	/* Note: gem is not supported on gen5/ilk without kms (the corresponding
@@ -2043,31 +2103,39 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
 
-	ring->size = size;
-	ring->effective_size = ring->size;
+	ringbuf->size = size;
+	ringbuf->effective_size = ringbuf->size;
 	if (IS_I830(ring->dev) || IS_845G(ring->dev))
-		ring->effective_size -= 128;
+		ringbuf->effective_size -= 2 * CACHELINE_BYTES;
 
-	ring->virtual_start = ioremap_wc(start, size);
-	if (ring->virtual_start == NULL) {
+	ringbuf->virtual_start = ioremap_wc(start, size);
+	if (ringbuf->virtual_start == NULL) {
 		DRM_ERROR("can not ioremap virtual address for"
 			  " ring buffer\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_ringbuf;
 	}
 
 	if (!I915_NEED_GFX_HWS(dev)) {
 		ret = init_phys_status_page(ring);
 		if (ret)
-			return ret;
+			goto err_vstart;
 	}
 
 	return 0;
+
+err_vstart:
+	iounmap(ringbuf->virtual_start);
+err_ringbuf:
+	kfree(ringbuf);
+	ring->buffer = NULL;
+	return ret;
 }
 
 int intel_init_bsd_ring_buffer(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[VCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[VCS];
 
 	ring->name = "bsd ring";
 	ring->id = VCS;
@@ -2096,15 +2164,24 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 			ring->dispatch_execbuffer =
 				gen6_ring_dispatch_execbuffer;
 		}
-		ring->sync_to = gen6_ring_sync;
-		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR;
-		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID;
-		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB;
-		ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_VVE;
-		ring->signal_mbox[RCS] = GEN6_RVSYNC;
-		ring->signal_mbox[VCS] = GEN6_NOSYNC;
-		ring->signal_mbox[BCS] = GEN6_BVSYNC;
-		ring->signal_mbox[VECS] = GEN6_VEVSYNC;
+		ring->semaphore.sync_to = gen6_ring_sync;
+		ring->semaphore.signal = gen6_signal;
+		/*
+		 * The current semaphore is only applied on pre-gen8 platform.
+		 * And there is no VCS2 ring on the pre-gen8 platform. So the
+		 * semaphore between VCS and VCS2 is initialized as INVALID.
+		 * Gen8 will initialize the sema between VCS2 and VCS later.
+		 */
+		ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_VR;
+		ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_VB;
+		ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_VVE;
+		ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore.mbox.signal[RCS] = GEN6_RVSYNC;
+		ring->semaphore.mbox.signal[VCS] = GEN6_NOSYNC;
+		ring->semaphore.mbox.signal[BCS] = GEN6_BVSYNC;
+		ring->semaphore.mbox.signal[VECS] = GEN6_VEVSYNC;
+		ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
 	} else {
 		ring->mmio_base = BSD_RING_BASE;
 		ring->flush = bsd_ring_flush;
@@ -2127,10 +2204,63 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 	return intel_init_ring_buffer(dev, ring);
 }
 
+/**
+ * Initialize the second BSD ring for Broadwell GT3.
+ * It is noted that this only exists on Broadwell GT3.
+ */
+int intel_init_bsd2_ring_buffer(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring = &dev_priv->ring[VCS2];
+
+	if ((INTEL_INFO(dev)->gen != 8)) {
+		DRM_ERROR("No dual-BSD ring on non-BDW machine\n");
+		return -EINVAL;
+	}
+
+	ring->name = "bds2_ring";
+	ring->id = VCS2;
+
+	ring->write_tail = ring_write_tail;
+	ring->mmio_base = GEN8_BSD2_RING_BASE;
+	ring->flush = gen6_bsd_ring_flush;
+	ring->add_request = gen6_add_request;
+	ring->get_seqno = gen6_ring_get_seqno;
+	ring->set_seqno = ring_set_seqno;
+	ring->irq_enable_mask =
+			GT_RENDER_USER_INTERRUPT << GEN8_VCS2_IRQ_SHIFT;
+	ring->irq_get = gen8_ring_get_irq;
+	ring->irq_put = gen8_ring_put_irq;
+	ring->dispatch_execbuffer =
+			gen8_ring_dispatch_execbuffer;
+	ring->semaphore.sync_to = gen6_ring_sync;
+	ring->semaphore.signal = gen6_signal;
+	/*
+	 * The current semaphore is only applied on the pre-gen8. And there
+	 * is no bsd2 ring on the pre-gen8. So now the semaphore_register
+	 * between VCS2 and other ring is initialized as invalid.
+	 * Gen8 will initialize the sema between VCS2 and other ring later.
+	 */
+	ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.signal[RCS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VCS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[BCS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VECS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
+
+	ring->init = init_ring_common;
+
+	return intel_init_ring_buffer(dev, ring);
+}
+
 int intel_init_blt_ring_buffer(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[BCS];
+	struct intel_engine_cs *ring = &dev_priv->ring[BCS];
 
 	ring->name = "blitter ring";
 	ring->id = BCS;
@@ -2153,15 +2283,24 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 		ring->irq_put = gen6_ring_put_irq;
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	}
-	ring->sync_to = gen6_ring_sync;
-	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR;
-	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV;
-	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID;
-	ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_BVE;
-	ring->signal_mbox[RCS] = GEN6_RBSYNC;
-	ring->signal_mbox[VCS] = GEN6_VBSYNC;
-	ring->signal_mbox[BCS] = GEN6_NOSYNC;
-	ring->signal_mbox[VECS] = GEN6_VEBSYNC;
+	ring->semaphore.sync_to = gen6_ring_sync;
+	ring->semaphore.signal = gen6_signal;
+	/*
+	 * The current semaphore is only applied on pre-gen8 platform. And
+	 * there is no VCS2 ring on the pre-gen8 platform. So the semaphore
+	 * between BCS and VCS2 is initialized as INVALID.
+	 * Gen8 will initialize the sema between BCS and VCS2 later.
+	 */
+	ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_BR;
+	ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_BV;
+	ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_BVE;
+	ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.signal[RCS] = GEN6_RBSYNC;
+	ring->semaphore.mbox.signal[VCS] = GEN6_VBSYNC;
+	ring->semaphore.mbox.signal[BCS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VECS] = GEN6_VEBSYNC;
+	ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
 	ring->init = init_ring_common;
 
 	return intel_init_ring_buffer(dev, ring);
@@ -2170,7 +2309,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 int intel_init_vebox_ring_buffer(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_ring_buffer *ring = &dev_priv->ring[VECS];
+	struct intel_engine_cs *ring = &dev_priv->ring[VECS];
 
 	ring->name = "video enhancement ring";
 	ring->id = VECS;
@@ -2194,22 +2333,25 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
 		ring->irq_put = hsw_vebox_put_irq;
 		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
 	}
-	ring->sync_to = gen6_ring_sync;
-	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VER;
-	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_VEV;
-	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VEB;
-	ring->semaphore_register[VECS] = MI_SEMAPHORE_SYNC_INVALID;
-	ring->signal_mbox[RCS] = GEN6_RVESYNC;
-	ring->signal_mbox[VCS] = GEN6_VVESYNC;
-	ring->signal_mbox[BCS] = GEN6_BVESYNC;
-	ring->signal_mbox[VECS] = GEN6_NOSYNC;
+	ring->semaphore.sync_to = gen6_ring_sync;
+	ring->semaphore.signal = gen6_signal;
+	ring->semaphore.mbox.wait[RCS] = MI_SEMAPHORE_SYNC_VER;
+	ring->semaphore.mbox.wait[VCS] = MI_SEMAPHORE_SYNC_VEV;
+	ring->semaphore.mbox.wait[BCS] = MI_SEMAPHORE_SYNC_VEB;
+	ring->semaphore.mbox.wait[VECS] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.wait[VCS2] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->semaphore.mbox.signal[RCS] = GEN6_RVESYNC;
+	ring->semaphore.mbox.signal[VCS] = GEN6_VVESYNC;
+	ring->semaphore.mbox.signal[BCS] = GEN6_BVESYNC;
+	ring->semaphore.mbox.signal[VECS] = GEN6_NOSYNC;
+	ring->semaphore.mbox.signal[VCS2] = GEN6_NOSYNC;
 	ring->init = init_ring_common;
 
 	return intel_init_ring_buffer(dev, ring);
 }
 
 int
-intel_ring_flush_all_caches(struct intel_ring_buffer *ring)
+intel_ring_flush_all_caches(struct intel_engine_cs *ring)
 {
 	int ret;
 
@@ -2227,7 +2369,7 @@ intel_ring_flush_all_caches(struct intel_ring_buffer *ring)
 }
 
 int
-intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring)
+intel_ring_invalidate_all_caches(struct intel_engine_cs *ring)
 {
 	uint32_t flush_domains;
 	int ret;
@@ -2245,3 +2387,19 @@ intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring)
 	ring->gpu_caches_dirty = false;
 	return 0;
 }
+
+void
+intel_stop_ring_buffer(struct intel_engine_cs *ring)
+{
+	int ret;
+
+	if (!intel_ring_initialized(ring))
+		return;
+
+	ret = intel_ring_idle(ring);
+	if (ret && !i915_reset_in_progress(&to_i915(ring->dev)->gpu_error))
+		DRM_ERROR("failed to quiesce %s whilst cleaning up: %d\n",
+			  ring->name, ret);
+
+	stop_ring(ring);
+}
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 2b91c4b4d34..e72017bdcd7 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -1,6 +1,10 @@
 #ifndef _INTEL_RINGBUFFER_H_
 #define _INTEL_RINGBUFFER_H_
 
+#include <linux/hashtable.h>
+
+#define I915_CMD_HASH_ORDER 9
+
 /*
  * Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use"
  * Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use"
@@ -51,79 +55,96 @@ struct intel_ring_hangcheck {
 	u32 seqno;
 	int score;
 	enum intel_ring_hangcheck_action action;
-	bool deadlock;
+	int deadlock;
 };
 
-struct  intel_ring_buffer {
+struct intel_ringbuffer {
+	struct drm_i915_gem_object *obj;
+	void __iomem *virtual_start;
+
+	u32 head;
+	u32 tail;
+	int space;
+	int size;
+	int effective_size;
+
+	/** We track the position of the requests in the ring buffer, and
+	 * when each is retired we increment last_retired_head as the GPU
+	 * must have finished processing the request and so we know we
+	 * can advance the ringbuffer up to that position.
+	 *
+	 * last_retired_head is set to -1 after the value is consumed so
+	 * we can detect new retirements.
+	 */
+	u32 last_retired_head;
+};
+
+struct  intel_engine_cs {
 	const char	*name;
 	enum intel_ring_id {
 		RCS = 0x0,
 		VCS,
 		BCS,
 		VECS,
+		VCS2
 	} id;
-#define I915_NUM_RINGS 4
+#define I915_NUM_RINGS 5
+#define LAST_USER_RING (VECS + 1)
 	u32		mmio_base;
-	void		__iomem *virtual_start;
 	struct		drm_device *dev;
-	struct		drm_i915_gem_object *obj;
+	struct intel_ringbuffer *buffer;
 
-	u32		head;
-	u32		tail;
-	int		space;
-	int		size;
-	int		effective_size;
 	struct intel_hw_status_page status_page;
 
-	/** We track the position of the requests in the ring buffer, and
-	 * when each is retired we increment last_retired_head as the GPU
-	 * must have finished processing the request and so we know we
-	 * can advance the ringbuffer up to that position.
-	 *
-	 * last_retired_head is set to -1 after the value is consumed so
-	 * we can detect new retirements.
-	 */
-	u32		last_retired_head;
-
 	unsigned irq_refcount; /* protected by dev_priv->irq_lock */
 	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
 	u32		trace_irq_seqno;
-	u32		sync_seqno[I915_NUM_RINGS-1];
-	bool __must_check (*irq_get)(struct intel_ring_buffer *ring);
-	void		(*irq_put)(struct intel_ring_buffer *ring);
+	bool __must_check (*irq_get)(struct intel_engine_cs *ring);
+	void		(*irq_put)(struct intel_engine_cs *ring);
 
-	int		(*init)(struct intel_ring_buffer *ring);
+	int		(*init)(struct intel_engine_cs *ring);
 
-	void		(*write_tail)(struct intel_ring_buffer *ring,
+	void		(*write_tail)(struct intel_engine_cs *ring,
 				      u32 value);
-	int __must_check (*flush)(struct intel_ring_buffer *ring,
+	int __must_check (*flush)(struct intel_engine_cs *ring,
 				  u32	invalidate_domains,
 				  u32	flush_domains);
-	int		(*add_request)(struct intel_ring_buffer *ring);
+	int		(*add_request)(struct intel_engine_cs *ring);
 	/* Some chipsets are not quite as coherent as advertised and need
 	 * an expensive kick to force a true read of the up-to-date seqno.
 	 * However, the up-to-date seqno is not always required and the last
 	 * seen value is good enough. Note that the seqno will always be
 	 * monotonic, even if not coherent.
 	 */
-	u32		(*get_seqno)(struct intel_ring_buffer *ring,
+	u32		(*get_seqno)(struct intel_engine_cs *ring,
 				     bool lazy_coherency);
-	void		(*set_seqno)(struct intel_ring_buffer *ring,
+	void		(*set_seqno)(struct intel_engine_cs *ring,
 				     u32 seqno);
-	int		(*dispatch_execbuffer)(struct intel_ring_buffer *ring,
-					       u32 offset, u32 length,
+	int		(*dispatch_execbuffer)(struct intel_engine_cs *ring,
+					       u64 offset, u32 length,
 					       unsigned flags);
 #define I915_DISPATCH_SECURE 0x1
 #define I915_DISPATCH_PINNED 0x2
-	void		(*cleanup)(struct intel_ring_buffer *ring);
-	int		(*sync_to)(struct intel_ring_buffer *ring,
-				   struct intel_ring_buffer *to,
-				   u32 seqno);
+	void		(*cleanup)(struct intel_engine_cs *ring);
 
-	/* our mbox written by others */
-	u32		semaphore_register[I915_NUM_RINGS];
-	/* mboxes this ring signals to */
-	u32		signal_mbox[I915_NUM_RINGS];
+	struct {
+		u32	sync_seqno[I915_NUM_RINGS-1];
+
+		struct {
+			/* our mbox written by others */
+			u32		wait[I915_NUM_RINGS];
+			/* mboxes this ring signals to */
+			u32		signal[I915_NUM_RINGS];
+		} mbox;
+
+		/* AKA wait() */
+		int	(*sync_to)(struct intel_engine_cs *ring,
+				   struct intel_engine_cs *to,
+				   u32 seqno);
+		int	(*signal)(struct intel_engine_cs *signaller,
+				  /* num_dwords needed by caller */
+				  unsigned int num_dwords);
+	} semaphore;
 
 	/**
 	 * List of objects currently involved in rendering from the
@@ -153,12 +174,8 @@ struct  intel_ring_buffer {
 
 	wait_queue_head_t irq_queue;
 
-	/**
-	 * Do an explicit TLB flush before MI_SET_CONTEXT
-	 */
-	bool itlb_before_ctx_switch;
-	struct i915_hw_context *default_context;
-	struct i915_hw_context *last_context;
+	struct intel_context *default_context;
+	struct intel_context *last_context;
 
 	struct intel_ring_hangcheck hangcheck;
 
@@ -168,12 +185,13 @@ struct  intel_ring_buffer {
 		volatile u32 *cpu_page;
 	} scratch;
 
+	bool needs_cmd_parser;
+
 	/*
-	 * Tables of commands the command parser needs to know about
+	 * Table of commands the command parser needs to know about
 	 * for this ring.
 	 */
-	const struct drm_i915_cmd_table *cmd_tables;
-	int cmd_table_count;
+	DECLARE_HASHTABLE(cmd_hash, I915_CMD_HASH_ORDER);
 
 	/*
 	 * Table of registers allowed in commands that read/write registers.
@@ -202,20 +220,20 @@ struct  intel_ring_buffer {
 };
 
 static inline bool
-intel_ring_initialized(struct intel_ring_buffer *ring)
+intel_ring_initialized(struct intel_engine_cs *ring)
 {
-	return ring->obj != NULL;
+	return ring->buffer && ring->buffer->obj;
 }
 
 static inline unsigned
-intel_ring_flag(struct intel_ring_buffer *ring)
+intel_ring_flag(struct intel_engine_cs *ring)
 {
 	return 1 << ring->id;
 }
 
 static inline u32
-intel_ring_sync_index(struct intel_ring_buffer *ring,
-		      struct intel_ring_buffer *other)
+intel_ring_sync_index(struct intel_engine_cs *ring,
+		      struct intel_engine_cs *other)
 {
 	int idx;
 
@@ -233,7 +251,7 @@ intel_ring_sync_index(struct intel_ring_buffer *ring,
 }
 
 static inline u32
-intel_read_status_page(struct intel_ring_buffer *ring,
+intel_read_status_page(struct intel_engine_cs *ring,
 		       int reg)
 {
 	/* Ensure that the compiler doesn't optimize away the load. */
@@ -242,7 +260,7 @@ intel_read_status_page(struct intel_ring_buffer *ring,
 }
 
 static inline void
-intel_write_status_page(struct intel_ring_buffer *ring,
+intel_write_status_page(struct intel_engine_cs *ring,
 			int reg, u32 value)
 {
 	ring->status_page.page_addr[reg] = value;
@@ -267,47 +285,51 @@ intel_write_status_page(struct intel_ring_buffer *ring,
 #define I915_GEM_HWS_SCRATCH_INDEX	0x30
 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 
-void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);
+void intel_stop_ring_buffer(struct intel_engine_cs *ring);
+void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
 
-int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n);
-int __must_check intel_ring_cacheline_align(struct intel_ring_buffer *ring);
-static inline void intel_ring_emit(struct intel_ring_buffer *ring,
+int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
+int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
+static inline void intel_ring_emit(struct intel_engine_cs *ring,
 				   u32 data)
 {
-	iowrite32(data, ring->virtual_start + ring->tail);
-	ring->tail += 4;
+	struct intel_ringbuffer *ringbuf = ring->buffer;
+	iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
+	ringbuf->tail += 4;
 }
-static inline void intel_ring_advance(struct intel_ring_buffer *ring)
+static inline void intel_ring_advance(struct intel_engine_cs *ring)
 {
-	ring->tail &= ring->size - 1;
+	struct intel_ringbuffer *ringbuf = ring->buffer;
+	ringbuf->tail &= ringbuf->size - 1;
 }
-void __intel_ring_advance(struct intel_ring_buffer *ring);
+void __intel_ring_advance(struct intel_engine_cs *ring);
 
-int __must_check intel_ring_idle(struct intel_ring_buffer *ring);
-void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno);
-int intel_ring_flush_all_caches(struct intel_ring_buffer *ring);
-int intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring);
+int __must_check intel_ring_idle(struct intel_engine_cs *ring);
+void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
+int intel_ring_flush_all_caches(struct intel_engine_cs *ring);
+int intel_ring_invalidate_all_caches(struct intel_engine_cs *ring);
 
 int intel_init_render_ring_buffer(struct drm_device *dev);
 int intel_init_bsd_ring_buffer(struct drm_device *dev);
+int intel_init_bsd2_ring_buffer(struct drm_device *dev);
 int intel_init_blt_ring_buffer(struct drm_device *dev);
 int intel_init_vebox_ring_buffer(struct drm_device *dev);
 
-u64 intel_ring_get_active_head(struct intel_ring_buffer *ring);
-void intel_ring_setup_status_page(struct intel_ring_buffer *ring);
+u64 intel_ring_get_active_head(struct intel_engine_cs *ring);
+void intel_ring_setup_status_page(struct intel_engine_cs *ring);
 
-static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring)
+static inline u32 intel_ring_get_tail(struct intel_engine_cs *ring)
 {
-	return ring->tail;
+	return ring->buffer->tail;
 }
 
-static inline u32 intel_ring_get_seqno(struct intel_ring_buffer *ring)
+static inline u32 intel_ring_get_seqno(struct intel_engine_cs *ring)
 {
 	BUG_ON(ring->outstanding_lazy_seqno == 0);
 	return ring->outstanding_lazy_seqno;
 }
 
-static inline void i915_trace_irq_get(struct intel_ring_buffer *ring, u32 seqno)
+static inline void i915_trace_irq_get(struct intel_engine_cs *ring, u32 seqno)
 {
 	if (ring->trace_irq_seqno == 0 && ring->irq_get(ring))
 		ring->trace_irq_seqno = seqno;
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 46be00d66df..20375cc7f82 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1153,20 +1153,21 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder,
 	pipe_config->pixel_multiplier =
 		intel_sdvo_get_pixel_multiplier(adjusted_mode);
 
+	pipe_config->has_hdmi_sink = intel_sdvo->has_hdmi_monitor;
+
 	if (intel_sdvo->color_range_auto) {
 		/* See CEA-861-E - 5.1 Default Encoding Parameters */
 		/* FIXME: This bit is only valid when using TMDS encoding and 8
 		 * bit per color mode. */
-		if (intel_sdvo->has_hdmi_monitor &&
+		if (pipe_config->has_hdmi_sink &&
 		    drm_match_cea_mode(adjusted_mode) > 1)
-			intel_sdvo->color_range = HDMI_COLOR_RANGE_16_235;
-		else
-			intel_sdvo->color_range = 0;
+			pipe_config->limited_color_range = true;
+	} else {
+		if (pipe_config->has_hdmi_sink &&
+		    intel_sdvo->color_range == HDMI_COLOR_RANGE_16_235)
+			pipe_config->limited_color_range = true;
 	}
 
-	if (intel_sdvo->color_range)
-		pipe_config->limited_color_range = true;
-
 	/* Clock computation needs to happen after pixel multiplier. */
 	if (intel_sdvo->is_tv)
 		i9xx_adjust_sdvo_tv_clock(pipe_config);
@@ -1174,7 +1175,7 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder)
+static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder)
 {
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1223,7 +1224,7 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder)
 	if (!intel_sdvo_set_target_input(intel_sdvo))
 		return;
 
-	if (intel_sdvo->has_hdmi_monitor) {
+	if (crtc->config.has_hdmi_sink) {
 		intel_sdvo_set_encode(intel_sdvo, SDVO_ENCODE_HDMI);
 		intel_sdvo_set_colorimetry(intel_sdvo,
 					   SDVO_COLORIMETRY_RGB256);
@@ -1258,8 +1259,8 @@ static void intel_sdvo_mode_set(struct intel_encoder *intel_encoder)
 		/* The real mode polarity is set by the SDVO commands, using
 		 * struct intel_sdvo_dtd. */
 		sdvox = SDVO_VSYNC_ACTIVE_HIGH | SDVO_HSYNC_ACTIVE_HIGH;
-		if (!HAS_PCH_SPLIT(dev) && intel_sdvo->is_hdmi)
-			sdvox |= intel_sdvo->color_range;
+		if (!HAS_PCH_SPLIT(dev) && crtc->config.limited_color_range)
+			sdvox |= HDMI_COLOR_RANGE_16_235;
 		if (INTEL_INFO(dev)->gen < 5)
 			sdvox |= SDVO_BORDER_ENABLE;
 	} else {
@@ -1349,6 +1350,8 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 	u8 val;
 	bool ret;
 
+	sdvox = I915_READ(intel_sdvo->sdvo_reg);
+
 	ret = intel_sdvo_get_input_timing(intel_sdvo, &dtd);
 	if (!ret) {
 		/* Some sdvo encoders are not spec compliant and don't
@@ -1377,13 +1380,14 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 	 * other platfroms.
 	 */
 	if (IS_I915G(dev) || IS_I915GM(dev)) {
-		sdvox = I915_READ(intel_sdvo->sdvo_reg);
 		pipe_config->pixel_multiplier =
 			((sdvox & SDVO_PORT_MULTIPLY_MASK)
 			 >> SDVO_PORT_MULTIPLY_SHIFT) + 1;
 	}
 
-	dotclock = pipe_config->port_clock / pipe_config->pixel_multiplier;
+	dotclock = pipe_config->port_clock;
+	if (pipe_config->pixel_multiplier)
+		dotclock /= pipe_config->pixel_multiplier;
 
 	if (HAS_PCH_SPLIT(dev))
 		ironlake_check_encoder_dotclock(pipe_config, dotclock);
@@ -1406,6 +1410,15 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 		}
 	}
 
+	if (sdvox & HDMI_COLOR_RANGE_16_235)
+		pipe_config->limited_color_range = true;
+
+	if (intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ENCODE,
+				 &val, 1)) {
+		if (val == SDVO_ENCODE_HDMI)
+			pipe_config->has_hdmi_sink = true;
+	}
+
 	WARN(encoder_pixel_multiplier != pipe_config->pixel_multiplier,
 	     "SDVO pixel multiplier mismatch, port: %i, encoder: %i\n",
 	     pipe_config->pixel_multiplier, encoder_pixel_multiplier);
@@ -1732,7 +1745,7 @@ intel_sdvo_detect(struct drm_connector *connector, bool force)
 	enum drm_connector_status ret;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector));
+		      connector->base.id, connector->name);
 
 	if (!intel_sdvo_get_value(intel_sdvo,
 				  SDVO_CMD_GET_ATTACHED_DISPLAYS,
@@ -1794,7 +1807,7 @@ static void intel_sdvo_get_ddc_modes(struct drm_connector *connector)
 	struct edid *edid;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector));
+		      connector->base.id, connector->name);
 
 	/* set the bus switch and get the modes */
 	edid = intel_sdvo_get_edid(connector);
@@ -1892,7 +1905,7 @@ static void intel_sdvo_get_tv_modes(struct drm_connector *connector)
 	int i;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector));
+		      connector->base.id, connector->name);
 
 	/* Read the list of supported input resolutions for the selected TV
 	 * format.
@@ -1929,7 +1942,7 @@ static void intel_sdvo_get_lvds_modes(struct drm_connector *connector)
 	struct drm_display_mode *newmode;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, drm_get_connector_name(connector));
+		      connector->base.id, connector->name);
 
 	/*
 	 * Fetch modes from VBT. For SDVO prefer the VBT mode since some
@@ -2999,7 +3012,7 @@ bool intel_sdvo_init(struct drm_device *dev, uint32_t sdvo_reg, bool is_sdvob)
 
 	intel_encoder->compute_config = intel_sdvo_compute_config;
 	intel_encoder->disable = intel_disable_sdvo;
-	intel_encoder->mode_set = intel_sdvo_mode_set;
+	intel_encoder->pre_enable = intel_sdvo_pre_enable;
 	intel_encoder->enable = intel_enable_sdvo;
 	intel_encoder->get_hw_state = intel_sdvo_get_hw_state;
 	intel_encoder->get_config = intel_sdvo_get_config;
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index 0954f132726..01d841ea314 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -29,12 +29,21 @@
  * IOSF sideband, see VLV2_SidebandMsg_HAS.docx and
  * VLV_VLV2_PUNIT_HAS_0.8.docx
  */
+
+/* Standard MMIO read, non-posted */
+#define SB_MRD_NP	0x00
+/* Standard MMIO write, non-posted */
+#define SB_MWR_NP	0x01
+/* Private register read, double-word addressing, non-posted */
+#define SB_CRRDDA_NP	0x06
+/* Private register write, double-word addressing, non-posted */
+#define SB_CRWRDA_NP	0x07
+
 static int vlv_sideband_rw(struct drm_i915_private *dev_priv, u32 devfn,
 			   u32 port, u32 opcode, u32 addr, u32 *val)
 {
 	u32 cmd, be = 0xf, bar = 0;
-	bool is_read = (opcode == PUNIT_OPCODE_REG_READ ||
-			opcode == DPIO_OPCODE_REG_READ);
+	bool is_read = (opcode == SB_MRD_NP || opcode == SB_CRRDDA_NP);
 
 	cmd = (devfn << IOSF_DEVFN_SHIFT) | (opcode << IOSF_OPCODE_SHIFT) |
 		(port << IOSF_PORT_SHIFT) | (be << IOSF_BYTE_ENABLES_SHIFT) |
@@ -74,7 +83,7 @@ u32 vlv_punit_read(struct drm_i915_private *dev_priv, u8 addr)
 
 	mutex_lock(&dev_priv->dpio_lock);
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
-			PUNIT_OPCODE_REG_READ, addr, &val);
+			SB_CRRDDA_NP, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 
 	return val;
@@ -86,7 +95,7 @@ void vlv_punit_write(struct drm_i915_private *dev_priv, u8 addr, u32 val)
 
 	mutex_lock(&dev_priv->dpio_lock);
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_PUNIT,
-			PUNIT_OPCODE_REG_WRITE, addr, &val);
+			SB_CRWRDA_NP, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
@@ -95,7 +104,7 @@ u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg)
 	u32 val = 0;
 
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT,
-			PUNIT_OPCODE_REG_READ, reg, &val);
+			SB_CRRDDA_NP, reg, &val);
 
 	return val;
 }
@@ -103,7 +112,7 @@ u32 vlv_bunit_read(struct drm_i915_private *dev_priv, u32 reg)
 void vlv_bunit_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_BUNIT,
-			PUNIT_OPCODE_REG_WRITE, reg, &val);
+			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr)
@@ -114,7 +123,7 @@ u32 vlv_nc_read(struct drm_i915_private *dev_priv, u8 addr)
 
 	mutex_lock(&dev_priv->dpio_lock);
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_NC,
-			PUNIT_OPCODE_REG_READ, addr, &val);
+			SB_CRRDDA_NP, addr, &val);
 	mutex_unlock(&dev_priv->dpio_lock);
 
 	return val;
@@ -124,56 +133,56 @@ u32 vlv_gpio_nc_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC,
-			PUNIT_OPCODE_REG_READ, reg, &val);
+			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_gpio_nc_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPIO_NC,
-			PUNIT_OPCODE_REG_WRITE, reg, &val);
+			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_cck_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK,
-			PUNIT_OPCODE_REG_READ, reg, &val);
+			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_cck_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCK,
-			PUNIT_OPCODE_REG_WRITE, reg, &val);
+			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_ccu_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU,
-			PUNIT_OPCODE_REG_READ, reg, &val);
+			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_ccu_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_CCU,
-			PUNIT_OPCODE_REG_WRITE, reg, &val);
+			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_gps_core_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE,
-			PUNIT_OPCODE_REG_READ, reg, &val);
+			SB_CRRDDA_NP, reg, &val);
 	return val;
 }
 
 void vlv_gps_core_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
 	vlv_sideband_rw(dev_priv, PCI_DEVFN(2, 0), IOSF_PORT_GPS_CORE,
-			PUNIT_OPCODE_REG_WRITE, reg, &val);
+			SB_CRWRDA_NP, reg, &val);
 }
 
 u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg)
@@ -181,14 +190,22 @@ u32 vlv_dpio_read(struct drm_i915_private *dev_priv, enum pipe pipe, int reg)
 	u32 val = 0;
 
 	vlv_sideband_rw(dev_priv, DPIO_DEVFN, DPIO_PHY_IOSF_PORT(DPIO_PHY(pipe)),
-			DPIO_OPCODE_REG_READ, reg, &val);
+			SB_MRD_NP, reg, &val);
+
+	/*
+	 * FIXME: There might be some registers where all 1's is a valid value,
+	 * so ideally we should check the register offset instead...
+	 */
+	WARN(val == 0xffffffff, "DPIO read pipe %c reg 0x%x == 0x%x\n",
+	     pipe_name(pipe), reg, val);
+
 	return val;
 }
 
 void vlv_dpio_write(struct drm_i915_private *dev_priv, enum pipe pipe, int reg, u32 val)
 {
 	vlv_sideband_rw(dev_priv, DPIO_DEVFN, DPIO_PHY_IOSF_PORT(DPIO_PHY(pipe)),
-			DPIO_OPCODE_REG_WRITE, reg, &val);
+			SB_MWR_NP, reg, &val);
 }
 
 /* SBI access */
@@ -253,13 +270,13 @@ void intel_sbi_write(struct drm_i915_private *dev_priv, u16 reg, u32 value,
 u32 vlv_flisdsi_read(struct drm_i915_private *dev_priv, u32 reg)
 {
 	u32 val = 0;
-	vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI,
-					DPIO_OPCODE_REG_READ, reg, &val);
+	vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRRDDA_NP,
+			reg, &val);
 	return val;
 }
 
 void vlv_flisdsi_write(struct drm_i915_private *dev_priv, u32 reg, u32 val)
 {
-	vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI,
-					DPIO_OPCODE_REG_WRITE, reg, &val);
+	vlv_sideband_rw(dev_priv, DPIO_DEVFN, IOSF_PORT_FLISDSI, SB_CRWRDA_NP,
+			reg, &val);
 }
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 336ae6c602f..9a17b4e92ef 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -37,6 +37,106 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
+static int usecs_to_scanlines(const struct drm_display_mode *mode, int usecs)
+{
+	/* paranoia */
+	if (!mode->crtc_htotal)
+		return 1;
+
+	return DIV_ROUND_UP(usecs * mode->crtc_clock, 1000 * mode->crtc_htotal);
+}
+
+static bool intel_pipe_update_start(struct intel_crtc *crtc, uint32_t *start_vbl_count)
+{
+	struct drm_device *dev = crtc->base.dev;
+	const struct drm_display_mode *mode = &crtc->config.adjusted_mode;
+	enum pipe pipe = crtc->pipe;
+	long timeout = msecs_to_jiffies_timeout(1);
+	int scanline, min, max, vblank_start;
+	DEFINE_WAIT(wait);
+
+	WARN_ON(!drm_modeset_is_locked(&crtc->base.mutex));
+
+	vblank_start = mode->crtc_vblank_start;
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		vblank_start = DIV_ROUND_UP(vblank_start, 2);
+
+	/* FIXME needs to be calibrated sensibly */
+	min = vblank_start - usecs_to_scanlines(mode, 100);
+	max = vblank_start - 1;
+
+	if (min <= 0 || max <= 0)
+		return false;
+
+	if (WARN_ON(drm_vblank_get(dev, pipe)))
+		return false;
+
+	local_irq_disable();
+
+	trace_i915_pipe_update_start(crtc, min, max);
+
+	for (;;) {
+		/*
+		 * prepare_to_wait() has a memory barrier, which guarantees
+		 * other CPUs can see the task state update by the time we
+		 * read the scanline.
+		 */
+		prepare_to_wait(&crtc->vbl_wait, &wait, TASK_UNINTERRUPTIBLE);
+
+		scanline = intel_get_crtc_scanline(crtc);
+		if (scanline < min || scanline > max)
+			break;
+
+		if (timeout <= 0) {
+			DRM_ERROR("Potential atomic update failure on pipe %c\n",
+				  pipe_name(crtc->pipe));
+			break;
+		}
+
+		local_irq_enable();
+
+		timeout = schedule_timeout(timeout);
+
+		local_irq_disable();
+	}
+
+	finish_wait(&crtc->vbl_wait, &wait);
+
+	drm_vblank_put(dev, pipe);
+
+	*start_vbl_count = dev->driver->get_vblank_counter(dev, pipe);
+
+	trace_i915_pipe_update_vblank_evaded(crtc, min, max, *start_vbl_count);
+
+	return true;
+}
+
+static void intel_pipe_update_end(struct intel_crtc *crtc, u32 start_vbl_count)
+{
+	struct drm_device *dev = crtc->base.dev;
+	enum pipe pipe = crtc->pipe;
+	u32 end_vbl_count = dev->driver->get_vblank_counter(dev, pipe);
+
+	trace_i915_pipe_update_end(crtc, end_vbl_count);
+
+	local_irq_enable();
+
+	if (start_vbl_count != end_vbl_count)
+		DRM_ERROR("Atomic update failure on pipe %c (start=%u end=%u)\n",
+			  pipe_name(pipe), start_vbl_count, end_vbl_count);
+}
+
+static void intel_update_primary_plane(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = crtc->base.dev->dev_private;
+	int reg = DSPCNTR(crtc->plane);
+
+	if (crtc->primary_enabled)
+		I915_WRITE(reg, I915_READ(reg) | DISPLAY_PLANE_ENABLE);
+	else
+		I915_WRITE(reg, I915_READ(reg) & ~DISPLAY_PLANE_ENABLE);
+}
+
 static void
 vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 		 struct drm_framebuffer *fb,
@@ -48,11 +148,14 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 	struct drm_device *dev = dplane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(dplane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
 	int plane = intel_plane->plane;
 	u32 sprctl;
 	unsigned long sprsurf_offset, linear_offset;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	u32 start_vbl_count;
+	bool atomic_update;
 
 	sprctl = I915_READ(SPCNTR(pipe, plane));
 
@@ -131,6 +234,10 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 							fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
+
 	I915_WRITE(SPSTRIDE(pipe, plane), fb->pitches[0]);
 	I915_WRITE(SPPOS(pipe, plane), (crtc_y << 16) | crtc_x);
 
@@ -143,7 +250,11 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_crtc *crtc,
 	I915_WRITE(SPCNTR(pipe, plane), sprctl);
 	I915_WRITE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) +
 		   sprsurf_offset);
-	POSTING_READ(SPSURF(pipe, plane));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 }
 
 static void
@@ -152,14 +263,25 @@ vlv_disable_plane(struct drm_plane *dplane, struct drm_crtc *crtc)
 	struct drm_device *dev = dplane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(dplane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
 	int plane = intel_plane->plane;
+	u32 start_vbl_count;
+	bool atomic_update;
+
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
 
 	I915_WRITE(SPCNTR(pipe, plane), I915_READ(SPCNTR(pipe, plane)) &
 		   ~SP_ENABLE);
 	/* Activate double buffered register update */
 	I915_WRITE(SPSURF(pipe, plane), 0);
-	POSTING_READ(SPSURF(pipe, plane));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 
 	intel_update_sprite_watermarks(dplane, crtc, 0, 0, false, false);
 }
@@ -226,10 +348,13 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
 	u32 sprctl, sprscale = 0;
 	unsigned long sprsurf_offset, linear_offset;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	u32 start_vbl_count;
+	bool atomic_update;
 
 	sprctl = I915_READ(SPRCTL(pipe));
 
@@ -299,6 +424,10 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 					       pixel_size, fb->pitches[0]);
 	linear_offset -= sprsurf_offset;
 
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
+
 	I915_WRITE(SPRSTRIDE(pipe), fb->pitches[0]);
 	I915_WRITE(SPRPOS(pipe), (crtc_y << 16) | crtc_x);
 
@@ -317,7 +446,11 @@ ivb_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	I915_WRITE(SPRCTL(pipe), sprctl);
 	I915_WRITE(SPRSURF(pipe),
 		   i915_gem_obj_ggtt_offset(obj) + sprsurf_offset);
-	POSTING_READ(SPRSURF(pipe));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 }
 
 static void
@@ -326,7 +459,14 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
+	u32 start_vbl_count;
+	bool atomic_update;
+
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
 
 	I915_WRITE(SPRCTL(pipe), I915_READ(SPRCTL(pipe)) & ~SPRITE_ENABLE);
 	/* Can't leave the scaler enabled... */
@@ -334,7 +474,11 @@ ivb_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 		I915_WRITE(SPRSCALE(pipe), 0);
 	/* Activate double buffered register update */
 	I915_WRITE(SPRSURF(pipe), 0);
-	POSTING_READ(SPRSURF(pipe));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 
 	/*
 	 * Avoid underruns when disabling the sprite.
@@ -410,10 +554,13 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
 	unsigned long dvssurf_offset, linear_offset;
 	u32 dvscntr, dvsscale;
 	int pixel_size = drm_format_plane_cpp(fb->pixel_format, 0);
+	u32 start_vbl_count;
+	bool atomic_update;
 
 	dvscntr = I915_READ(DVSCNTR(pipe));
 
@@ -478,6 +625,10 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 					       pixel_size, fb->pitches[0]);
 	linear_offset -= dvssurf_offset;
 
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
+
 	I915_WRITE(DVSSTRIDE(pipe), fb->pitches[0]);
 	I915_WRITE(DVSPOS(pipe), (crtc_y << 16) | crtc_x);
 
@@ -491,7 +642,11 @@ ilk_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	I915_WRITE(DVSCNTR(pipe), dvscntr);
 	I915_WRITE(DVSSURF(pipe),
 		   i915_gem_obj_ggtt_offset(obj) + dvssurf_offset);
-	POSTING_READ(DVSSURF(pipe));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 }
 
 static void
@@ -500,14 +655,25 @@ ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 	struct drm_device *dev = plane->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_plane->pipe;
+	u32 start_vbl_count;
+	bool atomic_update;
+
+	atomic_update = intel_pipe_update_start(intel_crtc, &start_vbl_count);
+
+	intel_update_primary_plane(intel_crtc);
 
 	I915_WRITE(DVSCNTR(pipe), I915_READ(DVSCNTR(pipe)) & ~DVS_ENABLE);
 	/* Disable the scaler */
 	I915_WRITE(DVSSCALE(pipe), 0);
 	/* Flush double buffered register updates */
 	I915_WRITE(DVSSURF(pipe), 0);
-	POSTING_READ(DVSSURF(pipe));
+
+	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+
+	if (atomic_update)
+		intel_pipe_update_end(intel_crtc, start_vbl_count);
 
 	/*
 	 * Avoid underruns when disabling the sprite.
@@ -519,20 +685,18 @@ ilk_disable_plane(struct drm_plane *plane, struct drm_crtc *crtc)
 }
 
 static void
-intel_enable_primary(struct drm_crtc *crtc)
+intel_post_enable_primary(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int reg = DSPCNTR(intel_crtc->plane);
 
-	if (intel_crtc->primary_enabled)
-		return;
-
-	intel_crtc->primary_enabled = true;
-
-	I915_WRITE(reg, I915_READ(reg) | DISPLAY_PLANE_ENABLE);
-	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
+	/*
+	 * BDW signals flip done immediately if the plane
+	 * is disabled, even if the plane enable is already
+	 * armed to occur at the next vblank :(
+	 */
+	if (IS_BROADWELL(dev))
+		intel_wait_for_vblank(dev, intel_crtc->pipe);
 
 	/*
 	 * FIXME IPS should be fine as long as one plane is
@@ -540,10 +704,7 @@ intel_enable_primary(struct drm_crtc *crtc)
 	 * when going from primary only to sprite only and vice
 	 * versa.
 	 */
-	if (intel_crtc->config.ips_enabled) {
-		intel_wait_for_vblank(dev, intel_crtc->pipe);
-		hsw_enable_ips(intel_crtc);
-	}
+	hsw_enable_ips(intel_crtc);
 
 	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
@@ -551,17 +712,11 @@ intel_enable_primary(struct drm_crtc *crtc)
 }
 
 static void
-intel_disable_primary(struct drm_crtc *crtc)
+intel_pre_disable_primary(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int reg = DSPCNTR(intel_crtc->plane);
-
-	if (!intel_crtc->primary_enabled)
-		return;
-
-	intel_crtc->primary_enabled = false;
 
 	mutex_lock(&dev->struct_mutex);
 	if (dev_priv->fbc.plane == intel_crtc->plane)
@@ -575,9 +730,6 @@ intel_disable_primary(struct drm_crtc *crtc)
 	 * versa.
 	 */
 	hsw_disable_ips(intel_crtc);
-
-	I915_WRITE(reg, I915_READ(reg) & ~DISPLAY_PLANE_ENABLE);
-	intel_flush_primary_plane(dev_priv, intel_crtc->plane);
 }
 
 static int
@@ -671,7 +823,7 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct drm_i915_gem_object *old_obj = intel_plane->obj;
 	int ret;
-	bool disable_primary = false;
+	bool primary_enabled;
 	bool visible;
 	int hscale, vscale;
 	int max_scale, min_scale;
@@ -842,8 +994,8 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	 * If the sprite is completely covering the primary plane,
 	 * we can disable the primary and save power.
 	 */
-	disable_primary = drm_rect_equals(&dst, &clip) && !colorkey_enabled(intel_plane);
-	WARN_ON(disable_primary && !visible && intel_crtc->active);
+	primary_enabled = !drm_rect_equals(&dst, &clip) || colorkey_enabled(intel_plane);
+	WARN_ON(!primary_enabled && !visible && intel_crtc->active);
 
 	mutex_lock(&dev->struct_mutex);
 
@@ -870,12 +1022,15 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	intel_plane->obj = obj;
 
 	if (intel_crtc->active) {
-		/*
-		 * Be sure to re-enable the primary before the sprite is no longer
-		 * covering it fully.
-		 */
-		if (!disable_primary)
-			intel_enable_primary(crtc);
+		bool primary_was_enabled = intel_crtc->primary_enabled;
+
+		intel_crtc->primary_enabled = primary_enabled;
+
+		if (primary_was_enabled != primary_enabled)
+			intel_crtc_wait_for_pending_flips(crtc);
+
+		if (primary_was_enabled && !primary_enabled)
+			intel_pre_disable_primary(crtc);
 
 		if (visible)
 			intel_plane->update_plane(plane, crtc, fb, obj,
@@ -884,8 +1039,8 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		else
 			intel_plane->disable_plane(plane, crtc);
 
-		if (disable_primary)
-			intel_disable_primary(crtc);
+		if (!primary_was_enabled && primary_enabled)
+			intel_post_enable_primary(crtc);
 	}
 
 	/* Unpin old obj after new one is active to avoid ugliness */
@@ -923,8 +1078,14 @@ intel_disable_plane(struct drm_plane *plane)
 	intel_crtc = to_intel_crtc(plane->crtc);
 
 	if (intel_crtc->active) {
-		intel_enable_primary(plane->crtc);
+		bool primary_was_enabled = intel_crtc->primary_enabled;
+
+		intel_crtc->primary_enabled = true;
+
 		intel_plane->disable_plane(plane, plane->crtc);
+
+		if (!primary_was_enabled && intel_crtc->primary_enabled)
+			intel_post_enable_primary(plane->crtc);
 	}
 
 	if (intel_plane->obj) {
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index bafe92e317d..67c6c9a2eb1 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -934,7 +934,86 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 	return true;
 }
 
-static void intel_tv_mode_set(struct intel_encoder *encoder)
+static void
+set_tv_mode_timings(struct drm_i915_private *dev_priv,
+		    const struct tv_mode *tv_mode,
+		    bool burst_ena)
+{
+	u32 hctl1, hctl2, hctl3;
+	u32 vctl1, vctl2, vctl3, vctl4, vctl5, vctl6, vctl7;
+
+	hctl1 = (tv_mode->hsync_end << TV_HSYNC_END_SHIFT) |
+		(tv_mode->htotal << TV_HTOTAL_SHIFT);
+
+	hctl2 = (tv_mode->hburst_start << 16) |
+		(tv_mode->hburst_len << TV_HBURST_LEN_SHIFT);
+
+	if (burst_ena)
+		hctl2 |= TV_BURST_ENA;
+
+	hctl3 = (tv_mode->hblank_start << TV_HBLANK_START_SHIFT) |
+		(tv_mode->hblank_end << TV_HBLANK_END_SHIFT);
+
+	vctl1 = (tv_mode->nbr_end << TV_NBR_END_SHIFT) |
+		(tv_mode->vi_end_f1 << TV_VI_END_F1_SHIFT) |
+		(tv_mode->vi_end_f2 << TV_VI_END_F2_SHIFT);
+
+	vctl2 = (tv_mode->vsync_len << TV_VSYNC_LEN_SHIFT) |
+		(tv_mode->vsync_start_f1 << TV_VSYNC_START_F1_SHIFT) |
+		(tv_mode->vsync_start_f2 << TV_VSYNC_START_F2_SHIFT);
+
+	vctl3 = (tv_mode->veq_len << TV_VEQ_LEN_SHIFT) |
+		(tv_mode->veq_start_f1 << TV_VEQ_START_F1_SHIFT) |
+		(tv_mode->veq_start_f2 << TV_VEQ_START_F2_SHIFT);
+
+	if (tv_mode->veq_ena)
+		vctl3 |= TV_EQUAL_ENA;
+
+	vctl4 = (tv_mode->vburst_start_f1 << TV_VBURST_START_F1_SHIFT) |
+		(tv_mode->vburst_end_f1 << TV_VBURST_END_F1_SHIFT);
+
+	vctl5 = (tv_mode->vburst_start_f2 << TV_VBURST_START_F2_SHIFT) |
+		(tv_mode->vburst_end_f2 << TV_VBURST_END_F2_SHIFT);
+
+	vctl6 = (tv_mode->vburst_start_f3 << TV_VBURST_START_F3_SHIFT) |
+		(tv_mode->vburst_end_f3 << TV_VBURST_END_F3_SHIFT);
+
+	vctl7 = (tv_mode->vburst_start_f4 << TV_VBURST_START_F4_SHIFT) |
+		(tv_mode->vburst_end_f4 << TV_VBURST_END_F4_SHIFT);
+
+	I915_WRITE(TV_H_CTL_1, hctl1);
+	I915_WRITE(TV_H_CTL_2, hctl2);
+	I915_WRITE(TV_H_CTL_3, hctl3);
+	I915_WRITE(TV_V_CTL_1, vctl1);
+	I915_WRITE(TV_V_CTL_2, vctl2);
+	I915_WRITE(TV_V_CTL_3, vctl3);
+	I915_WRITE(TV_V_CTL_4, vctl4);
+	I915_WRITE(TV_V_CTL_5, vctl5);
+	I915_WRITE(TV_V_CTL_6, vctl6);
+	I915_WRITE(TV_V_CTL_7, vctl7);
+}
+
+static void set_color_conversion(struct drm_i915_private *dev_priv,
+				 const struct color_conversion *color_conversion)
+{
+	if (!color_conversion)
+		return;
+
+	I915_WRITE(TV_CSC_Y, (color_conversion->ry << 16) |
+		   color_conversion->gy);
+	I915_WRITE(TV_CSC_Y2, (color_conversion->by << 16) |
+		   color_conversion->ay);
+	I915_WRITE(TV_CSC_U, (color_conversion->ru << 16) |
+		   color_conversion->gu);
+	I915_WRITE(TV_CSC_U2, (color_conversion->bu << 16) |
+		   color_conversion->au);
+	I915_WRITE(TV_CSC_V, (color_conversion->rv << 16) |
+		   color_conversion->gv);
+	I915_WRITE(TV_CSC_V2, (color_conversion->bv << 16) |
+		   color_conversion->av);
+}
+
+static void intel_tv_pre_enable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -942,14 +1021,13 @@ static void intel_tv_mode_set(struct intel_encoder *encoder)
 	struct intel_tv *intel_tv = enc_to_tv(encoder);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(intel_tv);
 	u32 tv_ctl;
-	u32 hctl1, hctl2, hctl3;
-	u32 vctl1, vctl2, vctl3, vctl4, vctl5, vctl6, vctl7;
 	u32 scctl1, scctl2, scctl3;
 	int i, j;
 	const struct video_levels *video_levels;
 	const struct color_conversion *color_conversion;
 	bool burst_ena;
-	int pipe = intel_crtc->pipe;
+	int xpos = 0x0, ypos = 0x0;
+	unsigned int xsize, ysize;
 
 	if (!tv_mode)
 		return;	/* can't happen (mode_prepare prevents this) */
@@ -982,44 +1060,6 @@ static void intel_tv_mode_set(struct intel_encoder *encoder)
 		burst_ena = tv_mode->burst_ena;
 		break;
 	}
-	hctl1 = (tv_mode->hsync_end << TV_HSYNC_END_SHIFT) |
-		(tv_mode->htotal << TV_HTOTAL_SHIFT);
-
-	hctl2 = (tv_mode->hburst_start << 16) |
-		(tv_mode->hburst_len << TV_HBURST_LEN_SHIFT);
-
-	if (burst_ena)
-		hctl2 |= TV_BURST_ENA;
-
-	hctl3 = (tv_mode->hblank_start << TV_HBLANK_START_SHIFT) |
-		(tv_mode->hblank_end << TV_HBLANK_END_SHIFT);
-
-	vctl1 = (tv_mode->nbr_end << TV_NBR_END_SHIFT) |
-		(tv_mode->vi_end_f1 << TV_VI_END_F1_SHIFT) |
-		(tv_mode->vi_end_f2 << TV_VI_END_F2_SHIFT);
-
-	vctl2 = (tv_mode->vsync_len << TV_VSYNC_LEN_SHIFT) |
-		(tv_mode->vsync_start_f1 << TV_VSYNC_START_F1_SHIFT) |
-		(tv_mode->vsync_start_f2 << TV_VSYNC_START_F2_SHIFT);
-
-	vctl3 = (tv_mode->veq_len << TV_VEQ_LEN_SHIFT) |
-		(tv_mode->veq_start_f1 << TV_VEQ_START_F1_SHIFT) |
-		(tv_mode->veq_start_f2 << TV_VEQ_START_F2_SHIFT);
-
-	if (tv_mode->veq_ena)
-		vctl3 |= TV_EQUAL_ENA;
-
-	vctl4 = (tv_mode->vburst_start_f1 << TV_VBURST_START_F1_SHIFT) |
-		(tv_mode->vburst_end_f1 << TV_VBURST_END_F1_SHIFT);
-
-	vctl5 = (tv_mode->vburst_start_f2 << TV_VBURST_START_F2_SHIFT) |
-		(tv_mode->vburst_end_f2 << TV_VBURST_END_F2_SHIFT);
-
-	vctl6 = (tv_mode->vburst_start_f3 << TV_VBURST_START_F3_SHIFT) |
-		(tv_mode->vburst_end_f3 << TV_VBURST_END_F3_SHIFT);
-
-	vctl7 = (tv_mode->vburst_start_f4 << TV_VBURST_START_F4_SHIFT) |
-		(tv_mode->vburst_end_f4 << TV_VBURST_END_F4_SHIFT);
 
 	if (intel_crtc->pipe == 1)
 		tv_ctl |= TV_ENC_PIPEB_SELECT;
@@ -1051,37 +1091,16 @@ static void intel_tv_mode_set(struct intel_encoder *encoder)
 		tv_mode->dda3_inc << TV_SCDDA3_INC_SHIFT;
 
 	/* Enable two fixes for the chips that need them. */
-	if (dev->pdev->device < 0x2772)
+	if (IS_I915GM(dev))
 		tv_ctl |= TV_ENC_C0_FIX | TV_ENC_SDP_FIX;
 
-	I915_WRITE(TV_H_CTL_1, hctl1);
-	I915_WRITE(TV_H_CTL_2, hctl2);
-	I915_WRITE(TV_H_CTL_3, hctl3);
-	I915_WRITE(TV_V_CTL_1, vctl1);
-	I915_WRITE(TV_V_CTL_2, vctl2);
-	I915_WRITE(TV_V_CTL_3, vctl3);
-	I915_WRITE(TV_V_CTL_4, vctl4);
-	I915_WRITE(TV_V_CTL_5, vctl5);
-	I915_WRITE(TV_V_CTL_6, vctl6);
-	I915_WRITE(TV_V_CTL_7, vctl7);
+	set_tv_mode_timings(dev_priv, tv_mode, burst_ena);
+
 	I915_WRITE(TV_SC_CTL_1, scctl1);
 	I915_WRITE(TV_SC_CTL_2, scctl2);
 	I915_WRITE(TV_SC_CTL_3, scctl3);
 
-	if (color_conversion) {
-		I915_WRITE(TV_CSC_Y, (color_conversion->ry << 16) |
-			   color_conversion->gy);
-		I915_WRITE(TV_CSC_Y2, (color_conversion->by << 16) |
-			   color_conversion->ay);
-		I915_WRITE(TV_CSC_U, (color_conversion->ru << 16) |
-			   color_conversion->gu);
-		I915_WRITE(TV_CSC_U2, (color_conversion->bu << 16) |
-			   color_conversion->au);
-		I915_WRITE(TV_CSC_V, (color_conversion->rv << 16) |
-			   color_conversion->gv);
-		I915_WRITE(TV_CSC_V2, (color_conversion->bv << 16) |
-			   color_conversion->av);
-	}
+	set_color_conversion(dev_priv, color_conversion);
 
 	if (INTEL_INFO(dev)->gen >= 4)
 		I915_WRITE(TV_CLR_KNOBS, 0x00404000);
@@ -1092,46 +1111,25 @@ static void intel_tv_mode_set(struct intel_encoder *encoder)
 		I915_WRITE(TV_CLR_LEVEL,
 			   ((video_levels->black << TV_BLACK_LEVEL_SHIFT) |
 			    (video_levels->blank << TV_BLANK_LEVEL_SHIFT)));
-	{
-		int pipeconf_reg = PIPECONF(pipe);
-		int dspcntr_reg = DSPCNTR(intel_crtc->plane);
-		int pipeconf = I915_READ(pipeconf_reg);
-		int dspcntr = I915_READ(dspcntr_reg);
-		int xpos = 0x0, ypos = 0x0;
-		unsigned int xsize, ysize;
-		/* Pipe must be off here */
-		I915_WRITE(dspcntr_reg, dspcntr & ~DISPLAY_PLANE_ENABLE);
-		intel_flush_primary_plane(dev_priv, intel_crtc->plane);
-
-		/* Wait for vblank for the disable to take effect */
-		if (IS_GEN2(dev))
-			intel_wait_for_vblank(dev, intel_crtc->pipe);
-
-		I915_WRITE(pipeconf_reg, pipeconf & ~PIPECONF_ENABLE);
-		/* Wait for vblank for the disable to take effect. */
-		intel_wait_for_pipe_off(dev, intel_crtc->pipe);
-
-		/* Filter ctl must be set before TV_WIN_SIZE */
-		I915_WRITE(TV_FILTER_CTL_1, TV_AUTO_SCALE);
-		xsize = tv_mode->hblank_start - tv_mode->hblank_end;
-		if (tv_mode->progressive)
-			ysize = tv_mode->nbr_end + 1;
-		else
-			ysize = 2*tv_mode->nbr_end + 1;
-
-		xpos += intel_tv->margin[TV_MARGIN_LEFT];
-		ypos += intel_tv->margin[TV_MARGIN_TOP];
-		xsize -= (intel_tv->margin[TV_MARGIN_LEFT] +
-			  intel_tv->margin[TV_MARGIN_RIGHT]);
-		ysize -= (intel_tv->margin[TV_MARGIN_TOP] +
-			  intel_tv->margin[TV_MARGIN_BOTTOM]);
-		I915_WRITE(TV_WIN_POS, (xpos<<16)|ypos);
-		I915_WRITE(TV_WIN_SIZE, (xsize<<16)|ysize);
-
-		I915_WRITE(pipeconf_reg, pipeconf);
-		I915_WRITE(dspcntr_reg, dspcntr);
-		intel_flush_primary_plane(dev_priv, intel_crtc->plane);
-	}
+
+	assert_pipe_disabled(dev_priv, intel_crtc->pipe);
+
+	/* Filter ctl must be set before TV_WIN_SIZE */
+	I915_WRITE(TV_FILTER_CTL_1, TV_AUTO_SCALE);
+	xsize = tv_mode->hblank_start - tv_mode->hblank_end;
+	if (tv_mode->progressive)
+		ysize = tv_mode->nbr_end + 1;
+	else
+		ysize = 2*tv_mode->nbr_end + 1;
+
+	xpos += intel_tv->margin[TV_MARGIN_LEFT];
+	ypos += intel_tv->margin[TV_MARGIN_TOP];
+	xsize -= (intel_tv->margin[TV_MARGIN_LEFT] +
+		  intel_tv->margin[TV_MARGIN_RIGHT]);
+	ysize -= (intel_tv->margin[TV_MARGIN_TOP] +
+		  intel_tv->margin[TV_MARGIN_BOTTOM]);
+	I915_WRITE(TV_WIN_POS, (xpos<<16)|ypos);
+	I915_WRITE(TV_WIN_SIZE, (xsize<<16)|ysize);
 
 	j = 0;
 	for (i = 0; i < 60; i++)
@@ -1316,17 +1314,18 @@ intel_tv_detect(struct drm_connector *connector, bool force)
 	int type;
 
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s] force=%d\n",
-		      connector->base.id, drm_get_connector_name(connector),
+		      connector->base.id, connector->name,
 		      force);
 
 	mode = reported_modes[0];
 
 	if (force) {
 		struct intel_load_detect_pipe tmp;
+		struct drm_modeset_acquire_ctx ctx;
 
-		if (intel_get_load_detect_pipe(connector, &mode, &tmp)) {
+		if (intel_get_load_detect_pipe(connector, &mode, &tmp, &ctx)) {
 			type = intel_tv_detect_type(intel_tv, connector);
-			intel_release_load_detect_pipe(connector, &tmp);
+			intel_release_load_detect_pipe(connector, &tmp, &ctx);
 		} else
 			return connector_status_unknown;
 	} else
@@ -1634,7 +1633,7 @@ intel_tv_init(struct drm_device *dev)
 
 	intel_encoder->compute_config = intel_tv_compute_config;
 	intel_encoder->get_config = intel_tv_get_config;
-	intel_encoder->mode_set = intel_tv_mode_set;
+	intel_encoder->pre_enable = intel_tv_pre_enable;
 	intel_encoder->enable = intel_enable_tv;
 	intel_encoder->disable = intel_disable_tv;
 	intel_encoder->get_hw_state = intel_tv_get_hw_state;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index d0c75779d3f..4f6fef7ac06 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -255,8 +255,7 @@ static void __vlv_force_wake_put(struct drm_i915_private *dev_priv,
 
 }
 
-void vlv_force_wake_get(struct drm_i915_private *dev_priv,
-						int fw_engine)
+static void vlv_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine)
 {
 	unsigned long irqflags;
 
@@ -275,8 +274,7 @@ void vlv_force_wake_get(struct drm_i915_private *dev_priv,
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
-void vlv_force_wake_put(struct drm_i915_private *dev_priv,
-						int fw_engine)
+static void vlv_force_wake_put(struct drm_i915_private *dev_priv, int fw_engine)
 {
 	unsigned long irqflags;
 
@@ -322,7 +320,8 @@ static void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
 
-	del_timer_sync(&dev_priv->uncore.force_wake_timer);
+	if (del_timer_sync(&dev_priv->uncore.force_wake_timer))
+		gen6_force_wake_timer((unsigned long)dev_priv);
 
 	/* Hold uncore.lock across reset to prevent any register access
 	 * with forcewake not set correctly
@@ -374,7 +373,7 @@ void intel_uncore_early_sanitize(struct drm_device *dev)
 	if (HAS_FPGA_DBG_UNCLAIMED(dev))
 		__raw_i915_write32(dev_priv, FPGA_DBG, FPGA_DBG_RM_NOCLAIM);
 
-	if (IS_HASWELL(dev) &&
+	if ((IS_HASWELL(dev) || IS_BROADWELL(dev)) &&
 	    (__raw_i915_read32(dev_priv, HSW_EDRAM_PRESENT) == 1)) {
 		/* The docs do not explain exactly how the calculation can be
 		 * made. It is somewhat guessable, but for now, it's always
@@ -395,26 +394,8 @@ void intel_uncore_early_sanitize(struct drm_device *dev)
 
 void intel_uncore_sanitize(struct drm_device *dev)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 reg_val;
-
 	/* BIOS often leaves RC6 enabled, but disable it for hw init */
 	intel_disable_gt_powersave(dev);
-
-	/* Turn off power gate, require especially for the BIOS less system */
-	if (IS_VALLEYVIEW(dev)) {
-
-		mutex_lock(&dev_priv->rps.hw_lock);
-		reg_val = vlv_punit_read(dev_priv, PUNIT_REG_PWRGT_STATUS);
-
-		if (reg_val & (PUNIT_PWRGT_PWR_GATE(PUNIT_POWER_WELL_RENDER) |
-			       PUNIT_PWRGT_PWR_GATE(PUNIT_POWER_WELL_MEDIA) |
-			       PUNIT_PWRGT_PWR_GATE(PUNIT_POWER_WELL_DISP2D)))
-			vlv_punit_write(dev_priv, PUNIT_REG_PWRGT_CTRL, 0x0);
-
-		mutex_unlock(&dev_priv->rps.hw_lock);
-
-	}
 }
 
 /*
@@ -488,6 +469,17 @@ void assert_force_wake_inactive(struct drm_i915_private *dev_priv)
 #define NEEDS_FORCE_WAKE(dev_priv, reg) \
 	 ((reg) < 0x40000 && (reg) != FORCEWAKE)
 
+#define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \
+	(((reg) >= 0x2000 && (reg) < 0x4000) ||\
+	((reg) >= 0x5000 && (reg) < 0x8000) ||\
+	((reg) >= 0xB000 && (reg) < 0x12000) ||\
+	((reg) >= 0x2E000 && (reg) < 0x30000))
+
+#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)\
+	(((reg) >= 0x12000 && (reg) < 0x14000) ||\
+	((reg) >= 0x22000 && (reg) < 0x24000) ||\
+	((reg) >= 0x30000 && (reg) < 0x40000))
+
 static void
 ilk_dummy_write(struct drm_i915_private *dev_priv)
 {
@@ -854,12 +846,15 @@ void intel_uncore_fini(struct drm_device *dev)
 	intel_uncore_forcewake_reset(dev, false);
 }
 
+#define GEN_RANGE(l, h) GENMASK(h, l)
+
 static const struct register_whitelist {
 	uint64_t offset;
 	uint32_t size;
-	uint32_t gen_bitmask; /* support gens, 0x10 for 4, 0x30 for 4 and 5, etc. */
+	/* supported gens, 0x10 for 4, 0x30 for 4 and 5, etc. */
+	uint32_t gen_bitmask;
 } whitelist[] = {
-	{ RING_TIMESTAMP(RENDER_RING_BASE), 8, 0x1F0 },
+	{ RING_TIMESTAMP(RENDER_RING_BASE), 8, GEN_RANGE(4, 8) },
 };
 
 int i915_reg_read_ioctl(struct drm_device *dev,
@@ -911,7 +906,7 @@ int i915_get_reset_stats_ioctl(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_reset_stats *args = data;
 	struct i915_ctx_hang_stats *hs;
-	struct i915_hw_context *ctx;
+	struct intel_context *ctx;
 	int ret;
 
 	if (args->flags || args->pad)
@@ -955,6 +950,9 @@ static int i965_do_reset(struct drm_device *dev)
 {
 	int ret;
 
+	/* FIXME: i965g/gm need a display save/restore for gpu reset. */
+	return -ENODEV;
+
 	/*
 	 * Set the domains we want to reset (GRDOM/bits 2 and 3) as
 	 * well as the reset bit (GR/bit 0).  Setting the GR bit
@@ -966,7 +964,6 @@ static int i965_do_reset(struct drm_device *dev)
 	if (ret)
 		return ret;
 
-	/* We can't reset render&media without also resetting display ... */
 	pci_write_config_byte(dev->pdev, I965_GDRST,
 			      GRDOM_MEDIA | GRDOM_RESET_ENABLE);
 
@@ -979,26 +976,58 @@ static int i965_do_reset(struct drm_device *dev)
 	return 0;
 }
 
+static int g4x_do_reset(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	int ret;
+
+	pci_write_config_byte(dev->pdev, I965_GDRST,
+			      GRDOM_RENDER | GRDOM_RESET_ENABLE);
+	ret =  wait_for(i965_reset_complete(dev), 500);
+	if (ret)
+		return ret;
+
+	/* WaVcpClkGateDisableForMediaReset:ctg,elk */
+	I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) | VCP_UNIT_CLOCK_GATE_DISABLE);
+	POSTING_READ(VDECCLK_GATE_D);
+
+	pci_write_config_byte(dev->pdev, I965_GDRST,
+			      GRDOM_MEDIA | GRDOM_RESET_ENABLE);
+	ret =  wait_for(i965_reset_complete(dev), 500);
+	if (ret)
+		return ret;
+
+	/* WaVcpClkGateDisableForMediaReset:ctg,elk */
+	I915_WRITE(VDECCLK_GATE_D, I915_READ(VDECCLK_GATE_D) & ~VCP_UNIT_CLOCK_GATE_DISABLE);
+	POSTING_READ(VDECCLK_GATE_D);
+
+	pci_write_config_byte(dev->pdev, I965_GDRST, 0);
+
+	return 0;
+}
+
 static int ironlake_do_reset(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 gdrst;
 	int ret;
 
-	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
-	gdrst &= ~GRDOM_MASK;
 	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
-		   gdrst | GRDOM_RENDER | GRDOM_RESET_ENABLE);
-	ret = wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
+		   ILK_GRDOM_RENDER | ILK_GRDOM_RESET_ENABLE);
+	ret = wait_for((I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) &
+			ILK_GRDOM_RESET_ENABLE) == 0, 500);
 	if (ret)
 		return ret;
 
-	/* We can't reset render&media without also resetting display ... */
-	gdrst = I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR);
-	gdrst &= ~GRDOM_MASK;
 	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR,
-		   gdrst | GRDOM_MEDIA | GRDOM_RESET_ENABLE);
-	return wait_for(I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) & 0x1, 500);
+		   ILK_GRDOM_MEDIA | ILK_GRDOM_RESET_ENABLE);
+	ret = wait_for((I915_READ(MCHBAR_MIRROR_BASE + ILK_GDSR) &
+			ILK_GRDOM_RESET_ENABLE) == 0, 500);
+	if (ret)
+		return ret;
+
+	I915_WRITE(MCHBAR_MIRROR_BASE + ILK_GDSR, 0);
+
+	return 0;
 }
 
 static int gen6_do_reset(struct drm_device *dev)
@@ -1029,7 +1058,11 @@ int intel_gpu_reset(struct drm_device *dev)
 	case 7:
 	case 6: return gen6_do_reset(dev);
 	case 5: return ironlake_do_reset(dev);
-	case 4: return i965_do_reset(dev);
+	case 4:
+		if (IS_G4X(dev))
+			return g4x_do_reset(dev);
+		else
+			return i965_do_reset(dev);
 	default: return -ENODEV;
 	}
 }
diff --git a/drivers/gpu/drm/mga/mga_ioc32.c b/drivers/gpu/drm/mga/mga_ioc32.c
index 86b4bb80485..729bfd56b55 100644
--- a/drivers/gpu/drm/mga/mga_ioc32.c
+++ b/drivers/gpu/drm/mga/mga_ioc32.c
@@ -214,7 +214,7 @@ long mga_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	if (nr < DRM_COMMAND_BASE)
 		return drm_compat_ioctl(filp, cmd, arg);
 
-	if (nr < DRM_COMMAND_BASE + DRM_ARRAY_SIZE(mga_compat_ioctls))
+	if (nr < DRM_COMMAND_BASE + ARRAY_SIZE(mga_compat_ioctls))
 		fn = mga_compat_ioctls[nr - DRM_COMMAND_BASE];
 
 	if (fn != NULL)
diff --git a/drivers/gpu/drm/mga/mga_state.c b/drivers/gpu/drm/mga/mga_state.c
index 314685b7f41..792f924496f 100644
--- a/drivers/gpu/drm/mga/mga_state.c
+++ b/drivers/gpu/drm/mga/mga_state.c
@@ -1020,7 +1020,7 @@ static int mga_getparam(struct drm_device *dev, void *data, struct drm_file *fil
 
 	switch (param->param) {
 	case MGA_PARAM_IRQ_NR:
-		value = drm_dev_to_irq(dev);
+		value = dev->pdev->irq;
 		break;
 	case MGA_PARAM_CARD_TYPE:
 		value = dev_priv->chipset;
@@ -1099,4 +1099,4 @@ const struct drm_ioctl_desc mga_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(MGA_DMA_BOOTSTRAP, mga_dma_bootstrap, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 };
 
-int mga_max_ioctl = DRM_ARRAY_SIZE(mga_ioctls);
+int mga_max_ioctl = ARRAY_SIZE(mga_ioctls);
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index 26868e5c55b..f6b283b8375 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -322,17 +322,13 @@ static void mgag200_bo_unref(struct mgag200_bo **bo)
 
 	tbo = &((*bo)->bo);
 	ttm_bo_unref(&tbo);
-	if (tbo == NULL)
-		*bo = NULL;
-
+	*bo = NULL;
 }
 
 void mgag200_gem_free_object(struct drm_gem_object *obj)
 {
 	struct mgag200_bo *mgag200_bo = gem_to_mga_bo(obj);
 
-	if (!mgag200_bo)
-		return;
 	mgag200_bo_unref(&mgag200_bo);
 }
 
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index b6984971ce0..f1238896785 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -3,7 +3,7 @@ config DRM_MSM
 	tristate "MSM DRM"
 	depends on DRM
 	depends on MSM_IOMMU
-	depends on ARCH_MSM8960 || (ARM && COMPILE_TEST)
+	depends on ARCH_QCOM || (ARM && COMPILE_TEST)
 	select DRM_KMS_HELPER
 	select SHMEM
 	select TMPFS
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 5e1e6b0cd8a..93ca49c8df4 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -34,6 +34,8 @@ msm-y := \
 	msm_gem_submit.o \
 	msm_gpu.o \
 	msm_iommu.o \
+	msm_perf.o \
+	msm_rd.o \
 	msm_ringbuffer.o
 
 msm-$(CONFIG_DRM_MSM_FBDEV) += msm_fbdev.o
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index f20fbde5dc4..942e09d898a 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -207,11 +207,11 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 	/* Turn on performance counters: */
 	gpu_write(gpu, REG_A3XX_RBBM_PERFCTR_CTL, 0x01);
 
-	/* Set SP perfcounter 7 to count SP_FS_FULL_ALU_INSTRUCTIONS
-	 * we will use this to augment our hang detection:
-	 */
-	gpu_write(gpu, REG_A3XX_SP_PERFCOUNTER7_SELECT,
-			SP_FS_FULL_ALU_INSTRUCTIONS);
+	/* Enable the perfcntrs that we use.. */
+	for (i = 0; i < gpu->num_perfcntrs; i++) {
+		const struct msm_gpu_perfcntr *perfcntr = &gpu->perfcntrs[i];
+		gpu_write(gpu, perfcntr->select_reg, perfcntr->select_val);
+	}
 
 	gpu_write(gpu, REG_A3XX_RBBM_INT_0_MASK, A3XX_INT0_MASK);
 
@@ -465,6 +465,13 @@ static const struct adreno_gpu_funcs funcs = {
 	},
 };
 
+static const struct msm_gpu_perfcntr perfcntrs[] = {
+	{ REG_A3XX_SP_PERFCOUNTER6_SELECT, REG_A3XX_RBBM_PERFCTR_SP_6_LO,
+			SP_ALU_ACTIVE_CYCLES, "ALUACTIVE" },
+	{ REG_A3XX_SP_PERFCOUNTER7_SELECT, REG_A3XX_RBBM_PERFCTR_SP_7_LO,
+			SP_FS_FULL_ALU_INSTRUCTIONS, "ALUFULL" },
+};
+
 struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 {
 	struct a3xx_gpu *a3xx_gpu = NULL;
@@ -504,6 +511,9 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 	DBG("fast_rate=%u, slow_rate=%u, bus_freq=%u",
 			gpu->fast_rate, gpu->slow_rate, gpu->bus_freq);
 
+	gpu->perfcntrs = perfcntrs;
+	gpu->num_perfcntrs = ARRAY_SIZE(perfcntrs);
+
 	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, config->rev);
 	if (ret)
 		goto fail;
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c
index ae750f6928c..7f7aadef8a8 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -277,6 +277,7 @@ static int hdmi_bind(struct device *dev, struct device *master, void *data)
 	static const char *hpd_reg_names[] = {"hpd-gdsc", "hpd-5v"};
 	static const char *pwr_reg_names[] = {"core-vdda", "core-vcc"};
 	static const char *hpd_clk_names[] = {"iface_clk", "core_clk", "mdp_core_clk"};
+	static unsigned long hpd_clk_freq[] = {0, 19200000, 0};
 	static const char *pwr_clk_names[] = {"extp_clk", "alt_iface_clk"};
 
 	config.phy_init      = hdmi_phy_8x74_init;
@@ -286,6 +287,7 @@ static int hdmi_bind(struct device *dev, struct device *master, void *data)
 	config.pwr_reg_names = pwr_reg_names;
 	config.pwr_reg_cnt   = ARRAY_SIZE(pwr_reg_names);
 	config.hpd_clk_names = hpd_clk_names;
+	config.hpd_freq      = hpd_clk_freq;
 	config.hpd_clk_cnt   = ARRAY_SIZE(hpd_clk_names);
 	config.pwr_clk_names = pwr_clk_names;
 	config.pwr_clk_cnt   = ARRAY_SIZE(pwr_clk_names);
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h
index 9fafee6a3e4..9d7723c6528 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.h
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.h
@@ -87,6 +87,7 @@ struct hdmi_platform_config {
 
 	/* clks that need to be on for hpd: */
 	const char **hpd_clk_names;
+	const long unsigned *hpd_freq;
 	int hpd_clk_cnt;
 
 	/* clks that need to be on for screen pwr (ie pixel clk): */
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
index 7dedfdd1207..28f7e3ec6c2 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -127,6 +127,14 @@ static int hpd_enable(struct hdmi_connector *hdmi_connector)
 	}
 
 	for (i = 0; i < config->hpd_clk_cnt; i++) {
+		if (config->hpd_freq && config->hpd_freq[i]) {
+			ret = clk_set_rate(hdmi->hpd_clks[i],
+					config->hpd_freq[i]);
+			if (ret)
+				dev_warn(dev->dev, "failed to set clk %s (%d)\n",
+						config->hpd_clk_names[i], ret);
+		}
+
 		ret = clk_prepare_enable(hdmi->hpd_clks[i]);
 		if (ret) {
 			dev_err(dev->dev, "failed to enable hpd clk: %s (%d)\n",
@@ -247,36 +255,49 @@ void hdmi_connector_irq(struct drm_connector *connector)
 	}
 }
 
+static enum drm_connector_status detect_reg(struct hdmi *hdmi)
+{
+	uint32_t hpd_int_status = hdmi_read(hdmi, REG_HDMI_HPD_INT_STATUS);
+	return (hpd_int_status & HDMI_HPD_INT_STATUS_CABLE_DETECTED) ?
+			connector_status_connected : connector_status_disconnected;
+}
+
+static enum drm_connector_status detect_gpio(struct hdmi *hdmi)
+{
+	const struct hdmi_platform_config *config = hdmi->config;
+	return gpio_get_value(config->hpd_gpio) ?
+			connector_status_connected :
+			connector_status_disconnected;
+}
+
 static enum drm_connector_status hdmi_connector_detect(
 		struct drm_connector *connector, bool force)
 {
 	struct hdmi_connector *hdmi_connector = to_hdmi_connector(connector);
 	struct hdmi *hdmi = hdmi_connector->hdmi;
-	const struct hdmi_platform_config *config = hdmi->config;
-	uint32_t hpd_int_status;
+	enum drm_connector_status stat_gpio, stat_reg;
 	int retry = 20;
 
-	hpd_int_status = hdmi_read(hdmi, REG_HDMI_HPD_INT_STATUS);
+	do {
+		stat_gpio = detect_gpio(hdmi);
+		stat_reg  = detect_reg(hdmi);
 
-	/* sense seems to in some cases be momentarily de-asserted, don't
-	 * let that trick us into thinking the monitor is gone:
-	 */
-	while (retry-- && !(hpd_int_status & HDMI_HPD_INT_STATUS_CABLE_DETECTED)) {
-		/* hdmi debounce logic seems to get stuck sometimes,
-		 * read directly the gpio to get a second opinion:
-		 */
-		if (gpio_get_value(config->hpd_gpio)) {
-			DBG("gpio tells us we are connected!");
-			hpd_int_status |= HDMI_HPD_INT_STATUS_CABLE_DETECTED;
+		if (stat_gpio == stat_reg)
 			break;
-		}
+
 		mdelay(10);
-		hpd_int_status = hdmi_read(hdmi, REG_HDMI_HPD_INT_STATUS);
-		DBG("status=%08x", hpd_int_status);
+	} while (--retry);
+
+	/* the status we get from reading gpio seems to be more reliable,
+	 * so trust that one the most if we didn't manage to get hdmi and
+	 * gpio status to agree:
+	 */
+	if (stat_gpio != stat_reg) {
+		DBG("HDMI_HPD_INT_STATUS tells us: %d", stat_reg);
+		DBG("hpd gpio tells us: %d", stat_gpio);
 	}
 
-	return (hpd_int_status & HDMI_HPD_INT_STATUS_CABLE_DETECTED) ?
-			connector_status_connected : connector_status_disconnected;
+	return stat_gpio;
 }
 
 static void hdmi_connector_destroy(struct drm_connector *connector)
@@ -389,7 +410,8 @@ struct drm_connector *hdmi_connector_init(struct hdmi *hdmi)
 			DRM_MODE_CONNECTOR_HDMIA);
 	drm_connector_helper_add(connector, &hdmi_connector_helper_funcs);
 
-	connector->polled = DRM_CONNECTOR_POLL_HPD;
+	connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+			DRM_CONNECTOR_POLL_DISCONNECT;
 
 	connector->interlace_allowed = 1;
 	connector->doublescan_allowed = 0;
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
index ef9957dbac9..74cebb51e8c 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
@@ -217,8 +217,6 @@ static void mdp4_crtc_destroy(struct drm_crtc *crtc)
 {
 	struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc);
 
-	mdp4_crtc->plane->funcs->destroy(mdp4_crtc->plane);
-
 	drm_crtc_cleanup(crtc);
 	drm_flip_work_cleanup(&mdp4_crtc->unref_fb_work);
 	drm_flip_work_cleanup(&mdp4_crtc->unref_cursor_work);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
index 6ea10bdb6e8..ebe2e60f3ab 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c
@@ -195,8 +195,6 @@ static void mdp5_crtc_destroy(struct drm_crtc *crtc)
 {
 	struct mdp5_crtc *mdp5_crtc = to_mdp5_crtc(crtc);
 
-	mdp5_crtc->plane->funcs->destroy(mdp5_crtc->plane);
-
 	drm_crtc_cleanup(crtc);
 	drm_flip_work_cleanup(&mdp5_crtc->unref_fb_work);
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index ee8446c1b5f..71510ee26e9 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -20,6 +20,10 @@
 #include "msm_mmu.h"
 #include "mdp5_kms.h"
 
+static const char *iommu_ports[] = {
+		"mdp_0",
+};
+
 static struct mdp5_platform_config *mdp5_get_config(struct platform_device *dev);
 
 static int mdp5_hw_init(struct msm_kms *kms)
@@ -104,6 +108,12 @@ static void mdp5_preclose(struct msm_kms *kms, struct drm_file *file)
 static void mdp5_destroy(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
+	struct msm_mmu *mmu = mdp5_kms->mmu;
+
+	if (mmu) {
+		mmu->funcs->detach(mmu, iommu_ports, ARRAY_SIZE(iommu_ports));
+		mmu->funcs->destroy(mmu);
+	}
 	kfree(mdp5_kms);
 }
 
@@ -216,10 +226,6 @@ fail:
 	return ret;
 }
 
-static const char *iommu_ports[] = {
-		"mdp_0",
-};
-
 static int get_clk(struct platform_device *pdev, struct clk **clkp,
 		const char *name)
 {
@@ -280,12 +286,22 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 		goto fail;
 	}
 
-	ret = get_clk(pdev, &mdp5_kms->axi_clk, "bus_clk") ||
-			get_clk(pdev, &mdp5_kms->ahb_clk, "iface_clk") ||
-			get_clk(pdev, &mdp5_kms->src_clk, "core_clk_src") ||
-			get_clk(pdev, &mdp5_kms->core_clk, "core_clk") ||
-			get_clk(pdev, &mdp5_kms->lut_clk, "lut_clk") ||
-			get_clk(pdev, &mdp5_kms->vsync_clk, "vsync_clk");
+	ret = get_clk(pdev, &mdp5_kms->axi_clk, "bus_clk");
+	if (ret)
+		goto fail;
+	ret = get_clk(pdev, &mdp5_kms->ahb_clk, "iface_clk");
+	if (ret)
+		goto fail;
+	ret = get_clk(pdev, &mdp5_kms->src_clk, "core_clk_src");
+	if (ret)
+		goto fail;
+	ret = get_clk(pdev, &mdp5_kms->core_clk, "core_clk");
+	if (ret)
+		goto fail;
+	ret = get_clk(pdev, &mdp5_kms->lut_clk, "lut_clk");
+	if (ret)
+		goto fail;
+	ret = get_clk(pdev, &mdp5_kms->vsync_clk, "vsync_clk");
 	if (ret)
 		goto fail;
 
@@ -307,17 +323,23 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 		mmu = msm_iommu_new(dev, config->iommu);
 		if (IS_ERR(mmu)) {
 			ret = PTR_ERR(mmu);
+			dev_err(dev->dev, "failed to init iommu: %d\n", ret);
 			goto fail;
 		}
+
 		ret = mmu->funcs->attach(mmu, iommu_ports,
 				ARRAY_SIZE(iommu_ports));
-		if (ret)
+		if (ret) {
+			dev_err(dev->dev, "failed to attach iommu: %d\n", ret);
+			mmu->funcs->destroy(mmu);
 			goto fail;
+		}
 	} else {
 		dev_info(dev->dev, "no iommu, fallback to phys "
 				"contig buffers for scanout\n");
 		mmu = NULL;
 	}
+	mdp5_kms->mmu = mmu;
 
 	mdp5_kms->id = msm_register_mmu(dev, mmu);
 	if (mdp5_kms->id < 0) {
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
index c8b1a2522c2..6e981b692d1 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
@@ -33,6 +33,7 @@ struct mdp5_kms {
 
 	/* mapper-id used to request GEM buffer mapped for scanout: */
 	int id;
+	struct msm_mmu *mmu;
 
 	/* for tracking smp allocation amongst pipes: */
 	mdp5_smp_state_t smp_state;
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index 47f7bbb9c15..f3daec4412a 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -85,8 +85,11 @@ static int mdp5_plane_disable(struct drm_plane *plane)
 static void mdp5_plane_destroy(struct drm_plane *plane)
 {
 	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
+	struct msm_drm_private *priv = plane->dev->dev_private;
+
+	if (priv->kms)
+		mdp5_plane_disable(plane);
 
-	mdp5_plane_disable(plane);
 	drm_plane_cleanup(plane);
 
 	kfree(mdp5_plane);
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index f9de156b9e6..9a5d87db5c2 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -159,7 +159,7 @@ static int msm_unload(struct drm_device *dev)
 static int get_mdp_ver(struct platform_device *pdev)
 {
 #ifdef CONFIG_OF
-	const static struct of_device_id match_types[] = { {
+	static const struct of_device_id match_types[] = { {
 		.compatible = "qcom,mdss_mdp",
 		.data	= (void	*)5,
 	}, {
@@ -220,7 +220,7 @@ static int msm_load(struct drm_device *dev, unsigned long flags)
 		 * is bogus, but non-null if allocation succeeded:
 		 */
 		p = dma_alloc_attrs(dev->dev, size,
-				&priv->vram.paddr, 0, &attrs);
+				&priv->vram.paddr, GFP_KERNEL, &attrs);
 		if (!p) {
 			dev_err(dev->dev, "failed to allocate VRAM\n");
 			priv->vram.paddr = 0;
@@ -288,7 +288,7 @@ static int msm_load(struct drm_device *dev, unsigned long flags)
 	}
 
 	pm_runtime_get_sync(dev->dev);
-	ret = drm_irq_install(dev);
+	ret = drm_irq_install(dev, platform_get_irq(dev->platformdev, 0));
 	pm_runtime_put_sync(dev->dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to install IRQ handler\n");
@@ -299,6 +299,10 @@ static int msm_load(struct drm_device *dev, unsigned long flags)
 	priv->fbdev = msm_fbdev_init(dev);
 #endif
 
+	ret = msm_debugfs_late_init(dev);
+	if (ret)
+		goto fail;
+
 	drm_kms_helper_poll_init(dev);
 
 	return 0;
@@ -382,11 +386,8 @@ static void msm_preclose(struct drm_device *dev, struct drm_file *file)
 static void msm_lastclose(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
-	if (priv->fbdev) {
-		drm_modeset_lock_all(dev);
-		drm_fb_helper_restore_fbdev_mode(priv->fbdev);
-		drm_modeset_unlock_all(dev);
-	}
+	if (priv->fbdev)
+		drm_fb_helper_restore_fbdev_mode_unlocked(priv->fbdev);
 }
 
 static irqreturn_t msm_irq(int irq, void *arg)
@@ -531,6 +532,41 @@ static struct drm_info_list msm_debugfs_list[] = {
 		{ "fb", show_locked, 0, msm_fb_show },
 };
 
+static int late_init_minor(struct drm_minor *minor)
+{
+	int ret;
+
+	if (!minor)
+		return 0;
+
+	ret = msm_rd_debugfs_init(minor);
+	if (ret) {
+		dev_err(minor->dev->dev, "could not install rd debugfs\n");
+		return ret;
+	}
+
+	ret = msm_perf_debugfs_init(minor);
+	if (ret) {
+		dev_err(minor->dev->dev, "could not install perf debugfs\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+int msm_debugfs_late_init(struct drm_device *dev)
+{
+	int ret;
+	ret = late_init_minor(dev->primary);
+	if (ret)
+		return ret;
+	ret = late_init_minor(dev->render);
+	if (ret)
+		return ret;
+	ret = late_init_minor(dev->control);
+	return ret;
+}
+
 static int msm_debugfs_init(struct drm_minor *minor)
 {
 	struct drm_device *dev = minor->dev;
@@ -545,13 +581,17 @@ static int msm_debugfs_init(struct drm_minor *minor)
 		return ret;
 	}
 
-	return ret;
+	return 0;
 }
 
 static void msm_debugfs_cleanup(struct drm_minor *minor)
 {
 	drm_debugfs_remove_files(msm_debugfs_list,
 			ARRAY_SIZE(msm_debugfs_list), minor);
+	if (!minor->dev->dev_private)
+		return;
+	msm_rd_debugfs_cleanup(minor);
+	msm_perf_debugfs_cleanup(minor);
 }
 #endif
 
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 9d10ee0b5aa..8a2c5fd0893 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -33,7 +33,7 @@
 #include <asm/sizes.h>
 
 
-#if defined(CONFIG_COMPILE_TEST) && !defined(CONFIG_ARCH_MSM)
+#if defined(CONFIG_COMPILE_TEST) && !defined(CONFIG_ARCH_QCOM)
 /* stubs we need for compile-test: */
 static inline struct device *msm_iommu_get_ctx(const char *ctx_name)
 {
@@ -55,6 +55,9 @@ static inline struct device *msm_iommu_get_ctx(const char *ctx_name)
 struct msm_kms;
 struct msm_gpu;
 struct msm_mmu;
+struct msm_rd_state;
+struct msm_perf_state;
+struct msm_gem_submit;
 
 #define NUM_DOMAINS 2    /* one for KMS, then one per gpu core (?) */
 
@@ -82,6 +85,9 @@ struct msm_drm_private {
 	uint32_t next_fence, completed_fence;
 	wait_queue_head_t fence_event;
 
+	struct msm_rd_state *rd;
+	struct msm_perf_state *perf;
+
 	/* list of GEM objects: */
 	struct list_head inactive_list;
 
@@ -204,6 +210,15 @@ void __exit hdmi_unregister(void);
 void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m);
 void msm_gem_describe_objects(struct list_head *list, struct seq_file *m);
 void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m);
+int msm_debugfs_late_init(struct drm_device *dev);
+int msm_rd_debugfs_init(struct drm_minor *minor);
+void msm_rd_debugfs_cleanup(struct drm_minor *minor);
+void msm_rd_dump_submit(struct msm_gem_submit *submit);
+int msm_perf_debugfs_init(struct drm_minor *minor);
+void msm_perf_debugfs_cleanup(struct drm_minor *minor);
+#else
+static inline int msm_debugfs_late_init(struct drm_device *dev) { return 0; }
+static inline void msm_rd_dump_submit(struct msm_gem_submit *submit) {}
 #endif
 
 void __iomem *msm_ioremap(struct platform_device *pdev, const char *name,
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index a752ab83b81..5107fc4826b 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -59,7 +59,7 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 	struct drm_framebuffer *fb = NULL;
 	struct fb_info *fbi = NULL;
 	struct drm_mode_fb_cmd2 mode_cmd = {0};
-	dma_addr_t paddr;
+	uint32_t paddr;
 	int ret, size;
 
 	sizes->surface_bpp = 32;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index bb8026daebc..690d7e7b6d1 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -278,6 +278,7 @@ int msm_gem_get_iova_locked(struct drm_gem_object *obj, int id,
 		uint32_t *iova)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
+	struct drm_device *dev = obj->dev;
 	int ret = 0;
 
 	if (!msm_obj->domain[id].iova) {
@@ -285,6 +286,11 @@ int msm_gem_get_iova_locked(struct drm_gem_object *obj, int id,
 		struct msm_mmu *mmu = priv->mmus[id];
 		struct page **pages = get_pages(obj);
 
+		if (!mmu) {
+			dev_err(dev->dev, "null MMU pointer\n");
+			return -EINVAL;
+		}
+
 		if (IS_ERR(pages))
 			return PTR_ERR(pages);
 
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index 3246bb46c4f..bfb052688f8 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -90,6 +90,7 @@ struct msm_gem_submit {
 		uint32_t type;
 		uint32_t size;  /* in dwords */
 		uint32_t iova;
+		uint32_t idx;   /* cmdstream buffer idx in bos[] */
 	} cmd[MAX_CMDS];
 	struct {
 		uint32_t flags;
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 1f1f4cffdae..cd0554f6831 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -402,6 +402,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		submit->cmd[i].type = submit_cmd.type;
 		submit->cmd[i].size = submit_cmd.size / 4;
 		submit->cmd[i].iova = iova + submit_cmd.submit_offset;
+		submit->cmd[i].idx  = submit_cmd.submit_idx;
 
 		if (submit->valid)
 			continue;
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 3e667ca1f2b..c6322197db8 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -320,6 +320,101 @@ static void hangcheck_handler(unsigned long data)
 }
 
 /*
+ * Performance Counters:
+ */
+
+/* called under perf_lock */
+static int update_hw_cntrs(struct msm_gpu *gpu, uint32_t ncntrs, uint32_t *cntrs)
+{
+	uint32_t current_cntrs[ARRAY_SIZE(gpu->last_cntrs)];
+	int i, n = min(ncntrs, gpu->num_perfcntrs);
+
+	/* read current values: */
+	for (i = 0; i < gpu->num_perfcntrs; i++)
+		current_cntrs[i] = gpu_read(gpu, gpu->perfcntrs[i].sample_reg);
+
+	/* update cntrs: */
+	for (i = 0; i < n; i++)
+		cntrs[i] = current_cntrs[i] - gpu->last_cntrs[i];
+
+	/* save current values: */
+	for (i = 0; i < gpu->num_perfcntrs; i++)
+		gpu->last_cntrs[i] = current_cntrs[i];
+
+	return n;
+}
+
+static void update_sw_cntrs(struct msm_gpu *gpu)
+{
+	ktime_t time;
+	uint32_t elapsed;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gpu->perf_lock, flags);
+	if (!gpu->perfcntr_active)
+		goto out;
+
+	time = ktime_get();
+	elapsed = ktime_to_us(ktime_sub(time, gpu->last_sample.time));
+
+	gpu->totaltime += elapsed;
+	if (gpu->last_sample.active)
+		gpu->activetime += elapsed;
+
+	gpu->last_sample.active = msm_gpu_active(gpu);
+	gpu->last_sample.time = time;
+
+out:
+	spin_unlock_irqrestore(&gpu->perf_lock, flags);
+}
+
+void msm_gpu_perfcntr_start(struct msm_gpu *gpu)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&gpu->perf_lock, flags);
+	/* we could dynamically enable/disable perfcntr registers too.. */
+	gpu->last_sample.active = msm_gpu_active(gpu);
+	gpu->last_sample.time = ktime_get();
+	gpu->activetime = gpu->totaltime = 0;
+	gpu->perfcntr_active = true;
+	update_hw_cntrs(gpu, 0, NULL);
+	spin_unlock_irqrestore(&gpu->perf_lock, flags);
+}
+
+void msm_gpu_perfcntr_stop(struct msm_gpu *gpu)
+{
+	gpu->perfcntr_active = false;
+}
+
+/* returns -errno or # of cntrs sampled */
+int msm_gpu_perfcntr_sample(struct msm_gpu *gpu, uint32_t *activetime,
+		uint32_t *totaltime, uint32_t ncntrs, uint32_t *cntrs)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&gpu->perf_lock, flags);
+
+	if (!gpu->perfcntr_active) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	*activetime = gpu->activetime;
+	*totaltime = gpu->totaltime;
+
+	gpu->activetime = gpu->totaltime = 0;
+
+	ret = update_hw_cntrs(gpu, ncntrs, cntrs);
+
+out:
+	spin_unlock_irqrestore(&gpu->perf_lock, flags);
+
+	return ret;
+}
+
+/*
  * Cmdstream submission/retirement:
  */
 
@@ -361,6 +456,7 @@ void msm_gpu_retire(struct msm_gpu *gpu)
 {
 	struct msm_drm_private *priv = gpu->dev->dev_private;
 	queue_work(priv->wq, &gpu->retire_work);
+	update_sw_cntrs(gpu);
 }
 
 /* add bo's to gpu's ring, and kick gpu: */
@@ -377,6 +473,12 @@ int msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 
 	inactive_cancel(gpu);
 
+	msm_rd_dump_submit(submit);
+
+	gpu->submitted_fence = submit->fence;
+
+	update_sw_cntrs(gpu);
+
 	ret = gpu->funcs->submit(gpu, submit, ctx);
 	priv->lastctx = ctx;
 
@@ -429,6 +531,9 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	struct iommu_domain *iommu;
 	int i, ret;
 
+	if (WARN_ON(gpu->num_perfcntrs > ARRAY_SIZE(gpu->last_cntrs)))
+		gpu->num_perfcntrs = ARRAY_SIZE(gpu->last_cntrs);
+
 	gpu->dev = drm;
 	gpu->funcs = funcs;
 	gpu->name = name;
@@ -444,6 +549,8 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	setup_timer(&gpu->hangcheck_timer, hangcheck_handler,
 			(unsigned long)gpu);
 
+	spin_lock_init(&gpu->perf_lock);
+
 	BUG_ON(ARRAY_SIZE(clk_names) != ARRAY_SIZE(gpu->grp_clks));
 
 	/* Map registers: */
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index fad27008922..9b579b79284 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -25,6 +25,7 @@
 #include "msm_ringbuffer.h"
 
 struct msm_gem_submit;
+struct msm_gpu_perfcntr;
 
 /* So far, with hardware that I've seen to date, we can have:
  *  + zero, one, or two z180 2d cores
@@ -64,6 +65,18 @@ struct msm_gpu {
 	struct drm_device *dev;
 	const struct msm_gpu_funcs *funcs;
 
+	/* performance counters (hw & sw): */
+	spinlock_t perf_lock;
+	bool perfcntr_active;
+	struct {
+		bool active;
+		ktime_t time;
+	} last_sample;
+	uint32_t totaltime, activetime;    /* sw counters */
+	uint32_t last_cntrs[5];            /* hw counters */
+	const struct msm_gpu_perfcntr *perfcntrs;
+	uint32_t num_perfcntrs;
+
 	struct msm_ringbuffer *rb;
 	uint32_t rb_iova;
 
@@ -113,6 +126,19 @@ static inline bool msm_gpu_active(struct msm_gpu *gpu)
 	return gpu->submitted_fence > gpu->funcs->last_fence(gpu);
 }
 
+/* Perf-Counters:
+ * The select_reg and select_val are just there for the benefit of the child
+ * class that actually enables the perf counter..  but msm_gpu base class
+ * will handle sampling/displaying the counters.
+ */
+
+struct msm_gpu_perfcntr {
+	uint32_t select_reg;
+	uint32_t sample_reg;
+	uint32_t select_val;
+	const char *name;
+};
+
 static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
 {
 	msm_writel(data, gpu->mmio + (reg << 2));
@@ -126,6 +152,11 @@ static inline u32 gpu_read(struct msm_gpu *gpu, u32 reg)
 int msm_gpu_pm_suspend(struct msm_gpu *gpu);
 int msm_gpu_pm_resume(struct msm_gpu *gpu);
 
+void msm_gpu_perfcntr_start(struct msm_gpu *gpu);
+void msm_gpu_perfcntr_stop(struct msm_gpu *gpu);
+int msm_gpu_perfcntr_sample(struct msm_gpu *gpu, uint32_t *activetime,
+		uint32_t *totaltime, uint32_t ncntrs, uint32_t *cntrs);
+
 void msm_gpu_retire(struct msm_gpu *gpu);
 int msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		struct msm_file_private *ctx);
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 92b74598623..4b2ad9181ed 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -28,7 +28,7 @@ static int msm_fault_handler(struct iommu_domain *iommu, struct device *dev,
 		unsigned long iova, int flags, void *arg)
 {
 	DBG("*** fault: iova=%08lx, flags=%d", iova, flags);
-	return 0;
+	return -ENOSYS;
 }
 
 static int msm_iommu_attach(struct msm_mmu *mmu, const char **names, int cnt)
@@ -40,8 +40,10 @@ static int msm_iommu_attach(struct msm_mmu *mmu, const char **names, int cnt)
 	for (i = 0; i < cnt; i++) {
 		struct device *msm_iommu_get_ctx(const char *ctx_name);
 		struct device *ctx = msm_iommu_get_ctx(names[i]);
-		if (IS_ERR_OR_NULL(ctx))
+		if (IS_ERR_OR_NULL(ctx)) {
+			dev_warn(dev->dev, "couldn't get %s context", names[i]);
 			continue;
+		}
 		ret = iommu_attach_device(iommu->domain, ctx);
 		if (ret) {
 			dev_warn(dev->dev, "could not attach iommu to %s", names[i]);
@@ -52,6 +54,20 @@ static int msm_iommu_attach(struct msm_mmu *mmu, const char **names, int cnt)
 	return 0;
 }
 
+static void msm_iommu_detach(struct msm_mmu *mmu, const char **names, int cnt)
+{
+	struct msm_iommu *iommu = to_msm_iommu(mmu);
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		struct device *msm_iommu_get_ctx(const char *ctx_name);
+		struct device *ctx = msm_iommu_get_ctx(names[i]);
+		if (IS_ERR_OR_NULL(ctx))
+			continue;
+		iommu_detach_device(iommu->domain, ctx);
+	}
+}
+
 static int msm_iommu_map(struct msm_mmu *mmu, uint32_t iova,
 		struct sg_table *sgt, unsigned len, int prot)
 {
@@ -110,7 +126,7 @@ static int msm_iommu_unmap(struct msm_mmu *mmu, uint32_t iova,
 
 		VERB("unmap[%d]: %08x(%x)", i, iova, bytes);
 
-		BUG_ON(!IS_ALIGNED(bytes, PAGE_SIZE));
+		BUG_ON(!PAGE_ALIGNED(bytes));
 
 		da += bytes;
 	}
@@ -127,6 +143,7 @@ static void msm_iommu_destroy(struct msm_mmu *mmu)
 
 static const struct msm_mmu_funcs funcs = {
 		.attach = msm_iommu_attach,
+		.detach = msm_iommu_detach,
 		.map = msm_iommu_map,
 		.unmap = msm_iommu_unmap,
 		.destroy = msm_iommu_destroy,
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index 030324482b4..21da6d154f7 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -22,6 +22,7 @@
 
 struct msm_mmu_funcs {
 	int (*attach)(struct msm_mmu *mmu, const char **names, int cnt);
+	void (*detach)(struct msm_mmu *mmu, const char **names, int cnt);
 	int (*map)(struct msm_mmu *mmu, uint32_t iova, struct sg_table *sgt,
 			unsigned len, int prot);
 	int (*unmap)(struct msm_mmu *mmu, uint32_t iova, struct sg_table *sgt,
diff --git a/drivers/gpu/drm/msm/msm_perf.c b/drivers/gpu/drm/msm/msm_perf.c
new file mode 100644
index 00000000000..830857c47c8
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_perf.c
@@ -0,0 +1,275 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/* For profiling, userspace can:
+ *
+ *   tail -f /sys/kernel/debug/dri/<minor>/gpu
+ *
+ * This will enable performance counters/profiling to track the busy time
+ * and any gpu specific performance counters that are supported.
+ */
+
+#ifdef CONFIG_DEBUG_FS
+
+#include <linux/debugfs.h>
+
+#include "msm_drv.h"
+#include "msm_gpu.h"
+
+struct msm_perf_state {
+	struct drm_device *dev;
+
+	bool open;
+	int cnt;
+	struct mutex read_lock;
+
+	char buf[256];
+	int buftot, bufpos;
+
+	unsigned long next_jiffies;
+
+	struct dentry *ent;
+	struct drm_info_node *node;
+};
+
+#define SAMPLE_TIME (HZ/4)
+
+/* wait for next sample time: */
+static int wait_sample(struct msm_perf_state *perf)
+{
+	unsigned long start_jiffies = jiffies;
+
+	if (time_after(perf->next_jiffies, start_jiffies)) {
+		unsigned long remaining_jiffies =
+			perf->next_jiffies - start_jiffies;
+		int ret = schedule_timeout_interruptible(remaining_jiffies);
+		if (ret > 0) {
+			/* interrupted */
+			return -ERESTARTSYS;
+		}
+	}
+	perf->next_jiffies += SAMPLE_TIME;
+	return 0;
+}
+
+static int refill_buf(struct msm_perf_state *perf)
+{
+	struct msm_drm_private *priv = perf->dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	char *ptr = perf->buf;
+	int rem = sizeof(perf->buf);
+	int i, n;
+
+	if ((perf->cnt++ % 32) == 0) {
+		/* Header line: */
+		n = snprintf(ptr, rem, "%%BUSY");
+		ptr += n;
+		rem -= n;
+
+		for (i = 0; i < gpu->num_perfcntrs; i++) {
+			const struct msm_gpu_perfcntr *perfcntr = &gpu->perfcntrs[i];
+			n = snprintf(ptr, rem, "\t%s", perfcntr->name);
+			ptr += n;
+			rem -= n;
+		}
+	} else {
+		/* Sample line: */
+		uint32_t activetime = 0, totaltime = 0;
+		uint32_t cntrs[5];
+		uint32_t val;
+		int ret;
+
+		/* sleep until next sample time: */
+		ret = wait_sample(perf);
+		if (ret)
+			return ret;
+
+		ret = msm_gpu_perfcntr_sample(gpu, &activetime, &totaltime,
+				ARRAY_SIZE(cntrs), cntrs);
+		if (ret < 0)
+			return ret;
+
+		val = totaltime ? 1000 * activetime / totaltime : 0;
+		n = snprintf(ptr, rem, "%3d.%d%%", val / 10, val % 10);
+		ptr += n;
+		rem -= n;
+
+		for (i = 0; i < ret; i++) {
+			/* cycle counters (I think).. convert to MHz.. */
+			val = cntrs[i] / 10000;
+			n = snprintf(ptr, rem, "\t%5d.%02d",
+					val / 100, val % 100);
+			ptr += n;
+			rem -= n;
+		}
+	}
+
+	n = snprintf(ptr, rem, "\n");
+	ptr += n;
+	rem -= n;
+
+	perf->bufpos = 0;
+	perf->buftot = ptr - perf->buf;
+
+	return 0;
+}
+
+static ssize_t perf_read(struct file *file, char __user *buf,
+		size_t sz, loff_t *ppos)
+{
+	struct msm_perf_state *perf = file->private_data;
+	int n = 0, ret;
+
+	mutex_lock(&perf->read_lock);
+
+	if (perf->bufpos >= perf->buftot) {
+		ret = refill_buf(perf);
+		if (ret)
+			goto out;
+	}
+
+	n = min((int)sz, perf->buftot - perf->bufpos);
+	ret = copy_to_user(buf, &perf->buf[perf->bufpos], n);
+	if (ret)
+		goto out;
+
+	perf->bufpos += n;
+	*ppos += n;
+
+out:
+	mutex_unlock(&perf->read_lock);
+	if (ret)
+		return ret;
+	return n;
+}
+
+static int perf_open(struct inode *inode, struct file *file)
+{
+	struct msm_perf_state *perf = inode->i_private;
+	struct drm_device *dev = perf->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	int ret = 0;
+
+	mutex_lock(&dev->struct_mutex);
+
+	if (perf->open || !gpu) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	file->private_data = perf;
+	perf->open = true;
+	perf->cnt = 0;
+	perf->buftot = 0;
+	perf->bufpos = 0;
+	msm_gpu_perfcntr_start(gpu);
+	perf->next_jiffies = jiffies + SAMPLE_TIME;
+
+out:
+	mutex_unlock(&dev->struct_mutex);
+	return ret;
+}
+
+static int perf_release(struct inode *inode, struct file *file)
+{
+	struct msm_perf_state *perf = inode->i_private;
+	struct msm_drm_private *priv = perf->dev->dev_private;
+	msm_gpu_perfcntr_stop(priv->gpu);
+	perf->open = false;
+	return 0;
+}
+
+
+static const struct file_operations perf_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = perf_open,
+	.read = perf_read,
+	.llseek = no_llseek,
+	.release = perf_release,
+};
+
+int msm_perf_debugfs_init(struct drm_minor *minor)
+{
+	struct msm_drm_private *priv = minor->dev->dev_private;
+	struct msm_perf_state *perf;
+
+	/* only create on first minor: */
+	if (priv->perf)
+		return 0;
+
+	perf = kzalloc(sizeof(*perf), GFP_KERNEL);
+	if (!perf)
+		return -ENOMEM;
+
+	perf->dev = minor->dev;
+
+	mutex_init(&perf->read_lock);
+	priv->perf = perf;
+
+	perf->node = kzalloc(sizeof(*perf->node), GFP_KERNEL);
+	if (!perf->node)
+		goto fail;
+
+	perf->ent = debugfs_create_file("perf", S_IFREG | S_IRUGO,
+			minor->debugfs_root, perf, &perf_debugfs_fops);
+	if (!perf->ent) {
+		DRM_ERROR("Cannot create /sys/kernel/debug/dri/%s/perf\n",
+				minor->debugfs_root->d_name.name);
+		goto fail;
+	}
+
+	perf->node->minor = minor;
+	perf->node->dent  = perf->ent;
+	perf->node->info_ent = NULL;
+
+	mutex_lock(&minor->debugfs_lock);
+	list_add(&perf->node->list, &minor->debugfs_list);
+	mutex_unlock(&minor->debugfs_lock);
+
+	return 0;
+
+fail:
+	msm_perf_debugfs_cleanup(minor);
+	return -1;
+}
+
+void msm_perf_debugfs_cleanup(struct drm_minor *minor)
+{
+	struct msm_drm_private *priv = minor->dev->dev_private;
+	struct msm_perf_state *perf = priv->perf;
+
+	if (!perf)
+		return;
+
+	priv->perf = NULL;
+
+	debugfs_remove(perf->ent);
+
+	if (perf->node) {
+		mutex_lock(&minor->debugfs_lock);
+		list_del(&perf->node->list);
+		mutex_unlock(&minor->debugfs_lock);
+		kfree(perf->node);
+	}
+
+	mutex_destroy(&perf->read_lock);
+
+	kfree(perf);
+}
+
+#endif
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
new file mode 100644
index 00000000000..9a78c48817c
--- /dev/null
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -0,0 +1,337 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/* For debugging crashes, userspace can:
+ *
+ *   tail -f /sys/kernel/debug/dri/<minor>/rd > logfile.rd
+ *
+ * To log the cmdstream in a format that is understood by freedreno/cffdump
+ * utility.  By comparing the last successfully completed fence #, to the
+ * cmdstream for the next fence, you can narrow down which process and submit
+ * caused the gpu crash/lockup.
+ *
+ * This bypasses drm_debugfs_create_files() mainly because we need to use
+ * our own fops for a bit more control.  In particular, we don't want to
+ * do anything if userspace doesn't have the debugfs file open.
+ */
+
+#ifdef CONFIG_DEBUG_FS
+
+#include <linux/kfifo.h>
+#include <linux/debugfs.h>
+#include <linux/circ_buf.h>
+#include <linux/wait.h>
+
+#include "msm_drv.h"
+#include "msm_gpu.h"
+#include "msm_gem.h"
+
+enum rd_sect_type {
+	RD_NONE,
+	RD_TEST,       /* ascii text */
+	RD_CMD,        /* ascii text */
+	RD_GPUADDR,    /* u32 gpuaddr, u32 size */
+	RD_CONTEXT,    /* raw dump */
+	RD_CMDSTREAM,  /* raw dump */
+	RD_CMDSTREAM_ADDR, /* gpu addr of cmdstream */
+	RD_PARAM,      /* u32 param_type, u32 param_val, u32 bitlen */
+	RD_FLUSH,      /* empty, clear previous params */
+	RD_PROGRAM,    /* shader program, raw dump */
+	RD_VERT_SHADER,
+	RD_FRAG_SHADER,
+	RD_BUFFER_CONTENTS,
+	RD_GPU_ID,
+};
+
+#define BUF_SZ 512  /* should be power of 2 */
+
+/* space used: */
+#define circ_count(circ) \
+	(CIRC_CNT((circ)->head, (circ)->tail, BUF_SZ))
+#define circ_count_to_end(circ) \
+	(CIRC_CNT_TO_END((circ)->head, (circ)->tail, BUF_SZ))
+/* space available: */
+#define circ_space(circ) \
+	(CIRC_SPACE((circ)->head, (circ)->tail, BUF_SZ))
+#define circ_space_to_end(circ) \
+	(CIRC_SPACE_TO_END((circ)->head, (circ)->tail, BUF_SZ))
+
+struct msm_rd_state {
+	struct drm_device *dev;
+
+	bool open;
+
+	struct dentry *ent;
+	struct drm_info_node *node;
+
+	/* current submit to read out: */
+	struct msm_gem_submit *submit;
+
+	/* fifo access is synchronized on the producer side by
+	 * struct_mutex held by submit code (otherwise we could
+	 * end up w/ cmds logged in different order than they
+	 * were executed).  And read_lock synchronizes the reads
+	 */
+	struct mutex read_lock;
+
+	wait_queue_head_t fifo_event;
+	struct circ_buf fifo;
+
+	char buf[BUF_SZ];
+};
+
+static void rd_write(struct msm_rd_state *rd, const void *buf, int sz)
+{
+	struct circ_buf *fifo = &rd->fifo;
+	const char *ptr = buf;
+
+	while (sz > 0) {
+		char *fptr = &fifo->buf[fifo->head];
+		int n;
+
+		wait_event(rd->fifo_event, circ_space(&rd->fifo) > 0);
+
+		n = min(sz, circ_space_to_end(&rd->fifo));
+		memcpy(fptr, ptr, n);
+
+		fifo->head = (fifo->head + n) & (BUF_SZ - 1);
+		sz  -= n;
+		ptr += n;
+
+		wake_up_all(&rd->fifo_event);
+	}
+}
+
+static void rd_write_section(struct msm_rd_state *rd,
+		enum rd_sect_type type, const void *buf, int sz)
+{
+	rd_write(rd, &type, 4);
+	rd_write(rd, &sz, 4);
+	rd_write(rd, buf, sz);
+}
+
+static ssize_t rd_read(struct file *file, char __user *buf,
+		size_t sz, loff_t *ppos)
+{
+	struct msm_rd_state *rd = file->private_data;
+	struct circ_buf *fifo = &rd->fifo;
+	const char *fptr = &fifo->buf[fifo->tail];
+	int n = 0, ret = 0;
+
+	mutex_lock(&rd->read_lock);
+
+	ret = wait_event_interruptible(rd->fifo_event,
+			circ_count(&rd->fifo) > 0);
+	if (ret)
+		goto out;
+
+	n = min_t(int, sz, circ_count_to_end(&rd->fifo));
+	ret = copy_to_user(buf, fptr, n);
+	if (ret)
+		goto out;
+
+	fifo->tail = (fifo->tail + n) & (BUF_SZ - 1);
+	*ppos += n;
+
+	wake_up_all(&rd->fifo_event);
+
+out:
+	mutex_unlock(&rd->read_lock);
+	if (ret)
+		return ret;
+	return n;
+}
+
+static int rd_open(struct inode *inode, struct file *file)
+{
+	struct msm_rd_state *rd = inode->i_private;
+	struct drm_device *dev = rd->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	uint64_t val;
+	uint32_t gpu_id;
+	int ret = 0;
+
+	mutex_lock(&dev->struct_mutex);
+
+	if (rd->open || !gpu) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	file->private_data = rd;
+	rd->open = true;
+
+	/* the parsing tools need to know gpu-id to know which
+	 * register database to load.
+	 */
+	gpu->funcs->get_param(gpu, MSM_PARAM_GPU_ID, &val);
+	gpu_id = val;
+
+	rd_write_section(rd, RD_GPU_ID, &gpu_id, sizeof(gpu_id));
+
+out:
+	mutex_unlock(&dev->struct_mutex);
+	return ret;
+}
+
+static int rd_release(struct inode *inode, struct file *file)
+{
+	struct msm_rd_state *rd = inode->i_private;
+	rd->open = false;
+	return 0;
+}
+
+
+static const struct file_operations rd_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = rd_open,
+	.read = rd_read,
+	.llseek = no_llseek,
+	.release = rd_release,
+};
+
+int msm_rd_debugfs_init(struct drm_minor *minor)
+{
+	struct msm_drm_private *priv = minor->dev->dev_private;
+	struct msm_rd_state *rd;
+
+	/* only create on first minor: */
+	if (priv->rd)
+		return 0;
+
+	rd = kzalloc(sizeof(*rd), GFP_KERNEL);
+	if (!rd)
+		return -ENOMEM;
+
+	rd->dev = minor->dev;
+	rd->fifo.buf = rd->buf;
+
+	mutex_init(&rd->read_lock);
+	priv->rd = rd;
+
+	init_waitqueue_head(&rd->fifo_event);
+
+	rd->node = kzalloc(sizeof(*rd->node), GFP_KERNEL);
+	if (!rd->node)
+		goto fail;
+
+	rd->ent = debugfs_create_file("rd", S_IFREG | S_IRUGO,
+			minor->debugfs_root, rd, &rd_debugfs_fops);
+	if (!rd->ent) {
+		DRM_ERROR("Cannot create /sys/kernel/debug/dri/%s/rd\n",
+				minor->debugfs_root->d_name.name);
+		goto fail;
+	}
+
+	rd->node->minor = minor;
+	rd->node->dent  = rd->ent;
+	rd->node->info_ent = NULL;
+
+	mutex_lock(&minor->debugfs_lock);
+	list_add(&rd->node->list, &minor->debugfs_list);
+	mutex_unlock(&minor->debugfs_lock);
+
+	return 0;
+
+fail:
+	msm_rd_debugfs_cleanup(minor);
+	return -1;
+}
+
+void msm_rd_debugfs_cleanup(struct drm_minor *minor)
+{
+	struct msm_drm_private *priv = minor->dev->dev_private;
+	struct msm_rd_state *rd = priv->rd;
+
+	if (!rd)
+		return;
+
+	priv->rd = NULL;
+
+	debugfs_remove(rd->ent);
+
+	if (rd->node) {
+		mutex_lock(&minor->debugfs_lock);
+		list_del(&rd->node->list);
+		mutex_unlock(&minor->debugfs_lock);
+		kfree(rd->node);
+	}
+
+	mutex_destroy(&rd->read_lock);
+
+	kfree(rd);
+}
+
+/* called under struct_mutex */
+void msm_rd_dump_submit(struct msm_gem_submit *submit)
+{
+	struct drm_device *dev = submit->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	struct msm_rd_state *rd = priv->rd;
+	char msg[128];
+	int i, n;
+
+	if (!rd->open)
+		return;
+
+	/* writing into fifo is serialized by caller, and
+	 * rd->read_lock is used to serialize the reads
+	 */
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	n = snprintf(msg, sizeof(msg), "%.*s/%d: fence=%u",
+			TASK_COMM_LEN, current->comm, task_pid_nr(current),
+			submit->fence);
+
+	rd_write_section(rd, RD_CMD, msg, ALIGN(n, 4));
+
+	/* could be nice to have an option (module-param?) to snapshot
+	 * all the bo's associated with the submit.  Handy to see vtx
+	 * buffers, etc.  For now just the cmdstream bo's is enough.
+	 */
+
+	for (i = 0; i < submit->nr_cmds; i++) {
+		uint32_t idx  = submit->cmd[i].idx;
+		uint32_t iova = submit->cmd[i].iova;
+		uint32_t szd  = submit->cmd[i].size; /* in dwords */
+		struct msm_gem_object *obj = submit->bos[idx].obj;
+		const char *buf = msm_gem_vaddr_locked(&obj->base);
+
+		buf += iova - submit->bos[idx].iova;
+
+		rd_write_section(rd, RD_GPUADDR,
+				(uint32_t[2]){ iova, szd * 4 }, 8);
+		rd_write_section(rd, RD_BUFFER_CONTENTS,
+				buf, szd * 4);
+
+		switch (submit->cmd[i].type) {
+		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
+			/* ignore IB-targets, we've logged the buffer, the
+			 * parser tool will follow the IB based on the logged
+			 * buffer/gpuaddr, so nothing more to do.
+			 */
+			break;
+		case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
+		case MSM_SUBMIT_CMD_BUF:
+			rd_write_section(rd, RD_CMDSTREAM_ADDR,
+					(uint32_t[2]){ iova, szd }, 8);
+			break;
+		}
+	}
+}
+#endif
diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile
index b7d21626477..8b307e14363 100644
--- a/drivers/gpu/drm/nouveau/Makefile
+++ b/drivers/gpu/drm/nouveau/Makefile
@@ -102,6 +102,7 @@ nouveau-y += core/subdev/fb/nvaa.o
 nouveau-y += core/subdev/fb/nvaf.o
 nouveau-y += core/subdev/fb/nvc0.o
 nouveau-y += core/subdev/fb/nve0.o
+nouveau-y += core/subdev/fb/gk20a.o
 nouveau-y += core/subdev/fb/gm107.o
 nouveau-y += core/subdev/fb/ramnv04.o
 nouveau-y += core/subdev/fb/ramnv10.o
@@ -117,25 +118,33 @@ nouveau-y += core/subdev/fb/ramnva3.o
 nouveau-y += core/subdev/fb/ramnvaa.o
 nouveau-y += core/subdev/fb/ramnvc0.o
 nouveau-y += core/subdev/fb/ramnve0.o
+nouveau-y += core/subdev/fb/ramgk20a.o
 nouveau-y += core/subdev/fb/ramgm107.o
 nouveau-y += core/subdev/fb/sddr3.o
 nouveau-y += core/subdev/fb/gddr5.o
 nouveau-y += core/subdev/gpio/base.o
 nouveau-y += core/subdev/gpio/nv10.o
 nouveau-y += core/subdev/gpio/nv50.o
+nouveau-y += core/subdev/gpio/nv92.o
 nouveau-y += core/subdev/gpio/nvd0.o
 nouveau-y += core/subdev/gpio/nve0.o
 nouveau-y += core/subdev/i2c/base.o
 nouveau-y += core/subdev/i2c/anx9805.o
 nouveau-y += core/subdev/i2c/aux.o
 nouveau-y += core/subdev/i2c/bit.o
+nouveau-y += core/subdev/i2c/pad.o
+nouveau-y += core/subdev/i2c/padnv04.o
+nouveau-y += core/subdev/i2c/padnv94.o
 nouveau-y += core/subdev/i2c/nv04.o
 nouveau-y += core/subdev/i2c/nv4e.o
 nouveau-y += core/subdev/i2c/nv50.o
 nouveau-y += core/subdev/i2c/nv94.o
 nouveau-y += core/subdev/i2c/nvd0.o
+nouveau-y += core/subdev/i2c/gf117.o
+nouveau-y += core/subdev/i2c/nve0.o
 nouveau-y += core/subdev/ibus/nvc0.o
 nouveau-y += core/subdev/ibus/nve0.o
+nouveau-y += core/subdev/ibus/gk20a.o
 nouveau-y += core/subdev/instmem/base.o
 nouveau-y += core/subdev/instmem/nv04.o
 nouveau-y += core/subdev/instmem/nv40.o
@@ -214,6 +223,9 @@ nouveau-y += core/engine/device/nvc0.o
 nouveau-y += core/engine/device/nve0.o
 nouveau-y += core/engine/device/gm100.o
 nouveau-y += core/engine/disp/base.o
+nouveau-y += core/engine/disp/conn.o
+nouveau-y += core/engine/disp/outp.o
+nouveau-y += core/engine/disp/outpdp.o
 nouveau-y += core/engine/disp/nv04.o
 nouveau-y += core/engine/disp/nv50.o
 nouveau-y += core/engine/disp/nv84.o
@@ -245,6 +257,7 @@ nouveau-y += core/engine/fifo/nv50.o
 nouveau-y += core/engine/fifo/nv84.o
 nouveau-y += core/engine/fifo/nvc0.o
 nouveau-y += core/engine/fifo/nve0.o
+nouveau-y += core/engine/fifo/gk20a.o
 nouveau-y += core/engine/fifo/nv108.o
 nouveau-y += core/engine/graph/ctxnv40.o
 nouveau-y += core/engine/graph/ctxnv50.o
@@ -255,6 +268,7 @@ nouveau-y += core/engine/graph/ctxnvc8.o
 nouveau-y += core/engine/graph/ctxnvd7.o
 nouveau-y += core/engine/graph/ctxnvd9.o
 nouveau-y += core/engine/graph/ctxnve4.o
+nouveau-y += core/engine/graph/ctxgk20a.o
 nouveau-y += core/engine/graph/ctxnvf0.o
 nouveau-y += core/engine/graph/ctxnv108.o
 nouveau-y += core/engine/graph/ctxgm107.o
@@ -275,6 +289,7 @@ nouveau-y += core/engine/graph/nvc8.o
 nouveau-y += core/engine/graph/nvd7.o
 nouveau-y += core/engine/graph/nvd9.o
 nouveau-y += core/engine/graph/nve4.o
+nouveau-y += core/engine/graph/gk20a.o
 nouveau-y += core/engine/graph/nvf0.o
 nouveau-y += core/engine/graph/nv108.o
 nouveau-y += core/engine/graph/gm107.o
diff --git a/drivers/gpu/drm/nouveau/core/core/event.c b/drivers/gpu/drm/nouveau/core/core/event.c
index 3f3c76581a9..ae81d3b5d8b 100644
--- a/drivers/gpu/drm/nouveau/core/core/event.c
+++ b/drivers/gpu/drm/nouveau/core/core/event.c
@@ -28,14 +28,20 @@ nouveau_event_put(struct nouveau_eventh *handler)
 {
 	struct nouveau_event *event = handler->event;
 	unsigned long flags;
-	if (__test_and_clear_bit(NVKM_EVENT_ENABLE, &handler->flags)) {
-		spin_lock_irqsave(&event->refs_lock, flags);
-		if (!--event->index[handler->index].refs) {
+	u32 m, t;
+
+	if (!__test_and_clear_bit(NVKM_EVENT_ENABLE, &handler->flags))
+		return;
+
+	spin_lock_irqsave(&event->refs_lock, flags);
+	for (m = handler->types; t = __ffs(m), m; m &= ~(1 << t)) {
+		if (!--event->refs[handler->index * event->types_nr + t]) {
 			if (event->disable)
-				event->disable(event, handler->index);
+				event->disable(event, 1 << t, handler->index);
 		}
-		spin_unlock_irqrestore(&event->refs_lock, flags);
+
 	}
+	spin_unlock_irqrestore(&event->refs_lock, flags);
 }
 
 void
@@ -43,14 +49,20 @@ nouveau_event_get(struct nouveau_eventh *handler)
 {
 	struct nouveau_event *event = handler->event;
 	unsigned long flags;
-	if (!__test_and_set_bit(NVKM_EVENT_ENABLE, &handler->flags)) {
-		spin_lock_irqsave(&event->refs_lock, flags);
-		if (!event->index[handler->index].refs++) {
+	u32 m, t;
+
+	if (__test_and_set_bit(NVKM_EVENT_ENABLE, &handler->flags))
+		return;
+
+	spin_lock_irqsave(&event->refs_lock, flags);
+	for (m = handler->types; t = __ffs(m), m; m &= ~(1 << t)) {
+		if (!event->refs[handler->index * event->types_nr + t]++) {
 			if (event->enable)
-				event->enable(event, handler->index);
+				event->enable(event, 1 << t, handler->index);
 		}
-		spin_unlock_irqrestore(&event->refs_lock, flags);
+
 	}
+	spin_unlock_irqrestore(&event->refs_lock, flags);
 }
 
 static void
@@ -65,38 +77,47 @@ nouveau_event_fini(struct nouveau_eventh *handler)
 }
 
 static int
-nouveau_event_init(struct nouveau_event *event, int index,
-		   int (*func)(void *, int), void *priv,
+nouveau_event_init(struct nouveau_event *event, u32 types, int index,
+		   int (*func)(void *, u32, int), void *priv,
 		   struct nouveau_eventh *handler)
 {
 	unsigned long flags;
 
+	if (types & ~((1 << event->types_nr) - 1))
+		return -EINVAL;
 	if (index >= event->index_nr)
 		return -EINVAL;
 
 	handler->event = event;
 	handler->flags = 0;
+	handler->types = types;
 	handler->index = index;
 	handler->func = func;
 	handler->priv = priv;
 
 	spin_lock_irqsave(&event->list_lock, flags);
-	list_add_tail(&handler->head, &event->index[index].list);
+	list_add_tail(&handler->head, &event->list[index]);
 	spin_unlock_irqrestore(&event->list_lock, flags);
 	return 0;
 }
 
 int
-nouveau_event_new(struct nouveau_event *event, int index,
-		  int (*func)(void *, int), void *priv,
+nouveau_event_new(struct nouveau_event *event, u32 types, int index,
+		  int (*func)(void *, u32, int), void *priv,
 		  struct nouveau_eventh **phandler)
 {
 	struct nouveau_eventh *handler;
 	int ret = -ENOMEM;
 
+	if (event->check) {
+		ret = event->check(event, types, index);
+		if (ret)
+			return ret;
+	}
+
 	handler = *phandler = kmalloc(sizeof(*handler), GFP_KERNEL);
 	if (handler) {
-		ret = nouveau_event_init(event, index, func, priv, handler);
+		ret = nouveau_event_init(event, types, index, func, priv, handler);
 		if (ret)
 			kfree(handler);
 	}
@@ -116,7 +137,7 @@ nouveau_event_ref(struct nouveau_eventh *handler, struct nouveau_eventh **ref)
 }
 
 void
-nouveau_event_trigger(struct nouveau_event *event, int index)
+nouveau_event_trigger(struct nouveau_event *event, u32 types, int index)
 {
 	struct nouveau_eventh *handler;
 	unsigned long flags;
@@ -125,10 +146,15 @@ nouveau_event_trigger(struct nouveau_event *event, int index)
 		return;
 
 	spin_lock_irqsave(&event->list_lock, flags);
-	list_for_each_entry(handler, &event->index[index].list, head) {
-		if (test_bit(NVKM_EVENT_ENABLE, &handler->flags) &&
-		    handler->func(handler->priv, index) == NVKM_EVENT_DROP)
-			nouveau_event_put(handler);
+	list_for_each_entry(handler, &event->list[index], head) {
+		if (!test_bit(NVKM_EVENT_ENABLE, &handler->flags))
+			continue;
+		if (!(handler->types & types))
+			continue;
+		if (handler->func(handler->priv, handler->types & types, index)
+				!= NVKM_EVENT_DROP)
+			continue;
+		nouveau_event_put(handler);
 	}
 	spin_unlock_irqrestore(&event->list_lock, flags);
 }
@@ -144,20 +170,27 @@ nouveau_event_destroy(struct nouveau_event **pevent)
 }
 
 int
-nouveau_event_create(int index_nr, struct nouveau_event **pevent)
+nouveau_event_create(int types_nr, int index_nr, struct nouveau_event **pevent)
 {
 	struct nouveau_event *event;
 	int i;
 
-	event = *pevent = kzalloc(sizeof(*event) + index_nr *
-				  sizeof(event->index[0]), GFP_KERNEL);
+	event = *pevent = kzalloc(sizeof(*event) + (index_nr * types_nr) *
+				  sizeof(event->refs[0]), GFP_KERNEL);
 	if (!event)
 		return -ENOMEM;
 
+	event->list = kmalloc(sizeof(*event->list) * index_nr, GFP_KERNEL);
+	if (!event->list) {
+		kfree(event);
+		return -ENOMEM;
+	}
+
 	spin_lock_init(&event->list_lock);
 	spin_lock_init(&event->refs_lock);
 	for (i = 0; i < index_nr; i++)
-		INIT_LIST_HEAD(&event->index[i].list);
+		INIT_LIST_HEAD(&event->list[i]);
+	event->types_nr = types_nr;
 	event->index_nr = index_nr;
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/core/object.c b/drivers/gpu/drm/nouveau/core/core/object.c
index 7f48e288215..12453855590 100644
--- a/drivers/gpu/drm/nouveau/core/core/object.c
+++ b/drivers/gpu/drm/nouveau/core/core/object.c
@@ -156,7 +156,7 @@ nouveau_object_ctor(struct nouveau_object *parent,
 	}
 
 	if (ret == 0) {
-		nv_debug(object, "created\n");
+		nv_trace(object, "created\n");
 		atomic_set(&object->refcount, 1);
 	}
 
@@ -166,7 +166,7 @@ nouveau_object_ctor(struct nouveau_object *parent,
 static void
 nouveau_object_dtor(struct nouveau_object *object)
 {
-	nv_debug(object, "destroying\n");
+	nv_trace(object, "destroying\n");
 	nv_ofuncs(object)->dtor(object);
 }
 
@@ -337,7 +337,7 @@ nouveau_object_inc(struct nouveau_object *object)
 		goto fail_self;
 	}
 
-	nv_debug(object, "initialised\n");
+	nv_trace(object, "initialised\n");
 	return 0;
 
 fail_self:
@@ -375,7 +375,7 @@ nouveau_object_decf(struct nouveau_object *object)
 	if (object->parent)
 		nouveau_object_dec(object->parent, false);
 
-	nv_debug(object, "stopped\n");
+	nv_trace(object, "stopped\n");
 	return 0;
 }
 
@@ -411,7 +411,7 @@ nouveau_object_decs(struct nouveau_object *object)
 		}
 	}
 
-	nv_debug(object, "suspended\n");
+	nv_trace(object, "suspended\n");
 	return 0;
 
 fail_parent:
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/gm100.c b/drivers/gpu/drm/nouveau/core/engine/device/gm100.c
index d258c21c4a2..a520029e25d 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/gm100.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/gm100.c
@@ -60,8 +60,8 @@ gm100_identify(struct nouveau_device *device)
 	case 0x117:
 		device->cname = "GM107";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nve0_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nvd0_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 #if 0
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv04.c b/drivers/gpu/drm/nouveau/core/engine/device/nv04.c
index 0a51ff4e9e0..40b29d0214c 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nv04.c
@@ -47,7 +47,7 @@ nv04_identify(struct nouveau_device *device)
 	case 0x04:
 		device->cname = "NV04";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv04_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -65,7 +65,7 @@ nv04_identify(struct nouveau_device *device)
 	case 0x05:
 		device->cname = "NV05";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv05_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv10.c b/drivers/gpu/drm/nouveau/core/engine/device/nv10.c
index e008de8b51b..5f7c25ff523 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nv10.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nv10.c
@@ -48,8 +48,8 @@ nv10_identify(struct nouveau_device *device)
 	case 0x10:
 		device->cname = "NV10";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv10_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -65,8 +65,8 @@ nv10_identify(struct nouveau_device *device)
 	case 0x15:
 		device->cname = "NV15";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv10_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -84,8 +84,8 @@ nv10_identify(struct nouveau_device *device)
 	case 0x16:
 		device->cname = "NV16";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv10_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -103,8 +103,8 @@ nv10_identify(struct nouveau_device *device)
 	case 0x1a:
 		device->cname = "nForce";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -122,8 +122,8 @@ nv10_identify(struct nouveau_device *device)
 	case 0x11:
 		device->cname = "NV11";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv10_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -141,8 +141,8 @@ nv10_identify(struct nouveau_device *device)
 	case 0x17:
 		device->cname = "NV17";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv10_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -160,8 +160,8 @@ nv10_identify(struct nouveau_device *device)
 	case 0x1f:
 		device->cname = "nForce2";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -179,8 +179,8 @@ nv10_identify(struct nouveau_device *device)
 	case 0x18:
 		device->cname = "NV18";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv10_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv20.c b/drivers/gpu/drm/nouveau/core/engine/device/nv20.c
index 7b629a3aed0..75fed11bba0 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nv20.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nv20.c
@@ -49,8 +49,8 @@ nv20_identify(struct nouveau_device *device)
 	case 0x20:
 		device->cname = "NV20";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv20_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -68,8 +68,8 @@ nv20_identify(struct nouveau_device *device)
 	case 0x25:
 		device->cname = "NV25";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv20_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -87,8 +87,8 @@ nv20_identify(struct nouveau_device *device)
 	case 0x28:
 		device->cname = "NV28";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv20_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -106,8 +106,8 @@ nv20_identify(struct nouveau_device *device)
 	case 0x2a:
 		device->cname = "NV2A";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv20_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv30.c b/drivers/gpu/drm/nouveau/core/engine/device/nv30.c
index 7dfddd5a190..36919d7db7c 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nv30.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nv30.c
@@ -49,8 +49,8 @@ nv30_identify(struct nouveau_device *device)
 	case 0x30:
 		device->cname = "NV30";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv20_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -68,8 +68,8 @@ nv30_identify(struct nouveau_device *device)
 	case 0x35:
 		device->cname = "NV35";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv20_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -87,8 +87,8 @@ nv30_identify(struct nouveau_device *device)
 	case 0x31:
 		device->cname = "NV31";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv20_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -107,8 +107,8 @@ nv30_identify(struct nouveau_device *device)
 	case 0x36:
 		device->cname = "NV36";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv20_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
@@ -127,8 +127,8 @@ nv30_identify(struct nouveau_device *device)
 	case 0x34:
 		device->cname = "NV34";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv04_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv10_devinit_oclass;
 		device->oclass[NVDEV_SUBDEV_MC     ] =  nv04_mc_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv40.c b/drivers/gpu/drm/nouveau/core/engine/device/nv40.c
index 7c1ce6cf4f1..1130a62be2c 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nv40.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nv40.c
@@ -53,8 +53,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x40:
 		device->cname = "NV40";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -76,8 +76,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x41:
 		device->cname = "NV41";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -99,8 +99,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x42:
 		device->cname = "NV42";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -122,8 +122,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x43:
 		device->cname = "NV43";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -145,8 +145,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x45:
 		device->cname = "NV45";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -168,8 +168,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x47:
 		device->cname = "G70";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -191,8 +191,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x49:
 		device->cname = "G71";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -214,8 +214,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x4b:
 		device->cname = "G73";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -237,8 +237,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x44:
 		device->cname = "NV44";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -260,8 +260,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x46:
 		device->cname = "G72";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -283,8 +283,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x4a:
 		device->cname = "NV44A";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -306,8 +306,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x4c:
 		device->cname = "C61";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -329,8 +329,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x4e:
 		device->cname = "C51";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv4e_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv4e_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -352,8 +352,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x63:
 		device->cname = "C73";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -375,8 +375,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x67:
 		device->cname = "C67";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
@@ -398,8 +398,8 @@ nv40_identify(struct nouveau_device *device)
 	case 0x68:
 		device->cname = "C68";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv10_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv04_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv10_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv04_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nv40_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv40_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nv1a_devinit_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv50.c b/drivers/gpu/drm/nouveau/core/engine/device/nv50.c
index 66499fa0f75..ef0b0bde1a9 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nv50.c
@@ -60,8 +60,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0x50:
 		device->cname = "G80";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv50_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv50_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv50_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -85,8 +85,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0x84:
 		device->cname = "G84";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv50_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -113,8 +113,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0x86:
 		device->cname = "G86";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv50_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -141,8 +141,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0x92:
 		device->cname = "G92";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -169,8 +169,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0x94:
 		device->cname = "G94";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -197,8 +197,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0x96:
 		device->cname = "G96";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -225,8 +225,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0x98:
 		device->cname = "G98";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -253,8 +253,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0xa0:
 		device->cname = "G200";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv50_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv50_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nv84_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -281,8 +281,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0xaa:
 		device->cname = "MCP77/MCP78";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nvaa_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -309,8 +309,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0xac:
 		device->cname = "MCP79/MCP7A";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] =  nvaa_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nv84_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -337,8 +337,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0xa3:
 		device->cname = "GT215";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nva3_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -367,8 +367,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0xa5:
 		device->cname = "GT216";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nva3_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -396,8 +396,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0xa8:
 		device->cname = "GT218";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nva3_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -425,8 +425,8 @@ nv50_identify(struct nouveau_device *device)
 	case 0xaf:
 		device->cname = "MCP89";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nva3_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
index 2075b302705..8d55ed633b1 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
@@ -60,8 +60,8 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc0:
 		device->cname = "GF100";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -92,8 +92,8 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc4:
 		device->cname = "GF104";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -124,8 +124,8 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc3:
 		device->cname = "GF106";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -155,8 +155,8 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xce:
 		device->cname = "GF114";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -187,8 +187,8 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xcf:
 		device->cname = "GF116";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -219,8 +219,8 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc1:
 		device->cname = "GF108";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -250,8 +250,8 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xc8:
 		device->cname = "GF110";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nv50_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nv94_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nv92_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nv94_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -282,8 +282,8 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xd9:
 		device->cname = "GF119";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nvd0_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nvd0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nvd0_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -313,8 +313,8 @@ nvc0_identify(struct nouveau_device *device)
 	case 0xd7:
 		device->cname = "GF117";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nvd0_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nvd0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  gf117_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nvc0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nve0.c b/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
index 9784cbf8a9d..2d1e97d4264 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nve0.c
@@ -60,8 +60,8 @@ nve0_identify(struct nouveau_device *device)
 	case 0xe4:
 		device->cname = "GK104";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nve0_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -93,8 +93,8 @@ nve0_identify(struct nouveau_device *device)
 	case 0xe7:
 		device->cname = "GK107";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nve0_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -126,8 +126,8 @@ nve0_identify(struct nouveau_device *device)
 	case 0xe6:
 		device->cname = "GK106";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nve0_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -156,11 +156,61 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
 		device->oclass[NVDEV_ENGINE_PERFMON] = &nve0_perfmon_oclass;
 		break;
+	case 0xea:
+		device->cname = "GK20A";
+		device->oclass[NVDEV_SUBDEV_MC     ] =  nvc3_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_BUS    ] =  nvc0_bus_oclass;
+		device->oclass[NVDEV_SUBDEV_TIMER  ] = &gk20a_timer_oclass;
+		device->oclass[NVDEV_SUBDEV_FB     ] =  gk20a_fb_oclass;
+		device->oclass[NVDEV_SUBDEV_IBUS   ] = &gk20a_ibus_oclass;
+		device->oclass[NVDEV_SUBDEV_INSTMEM] = nv50_instmem_oclass;
+		device->oclass[NVDEV_SUBDEV_VM     ] = &nvc0_vmmgr_oclass;
+		device->oclass[NVDEV_SUBDEV_BAR    ] = &nvc0_bar_oclass;
+		device->oclass[NVDEV_ENGINE_DMAOBJ ] = &nvd0_dmaeng_oclass;
+		device->oclass[NVDEV_ENGINE_FIFO   ] =  gk20a_fifo_oclass;
+		device->oclass[NVDEV_ENGINE_SW     ] =  nvc0_software_oclass;
+		device->oclass[NVDEV_ENGINE_GR     ] =  gk20a_graph_oclass;
+		device->oclass[NVDEV_ENGINE_COPY2  ] = &nve0_copy2_oclass;
+		device->oclass[NVDEV_ENGINE_PERFMON] = &nve0_perfmon_oclass;
+		break;
 	case 0xf0:
 		device->cname = "GK110";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nve0_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
+		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
+		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
+		device->oclass[NVDEV_SUBDEV_DEVINIT] =  nvc0_devinit_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  nvc3_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_BUS    ] =  nvc0_bus_oclass;
+		device->oclass[NVDEV_SUBDEV_TIMER  ] = &nv04_timer_oclass;
+		device->oclass[NVDEV_SUBDEV_FB     ] =  nve0_fb_oclass;
+		device->oclass[NVDEV_SUBDEV_LTCG   ] =  gf100_ltcg_oclass;
+		device->oclass[NVDEV_SUBDEV_IBUS   ] = &nve0_ibus_oclass;
+		device->oclass[NVDEV_SUBDEV_INSTMEM] =  nv50_instmem_oclass;
+		device->oclass[NVDEV_SUBDEV_VM     ] = &nvc0_vmmgr_oclass;
+		device->oclass[NVDEV_SUBDEV_BAR    ] = &nvc0_bar_oclass;
+		device->oclass[NVDEV_SUBDEV_PWR    ] = &nvd0_pwr_oclass;
+		device->oclass[NVDEV_SUBDEV_VOLT   ] = &nv40_volt_oclass;
+		device->oclass[NVDEV_ENGINE_DMAOBJ ] = &nvd0_dmaeng_oclass;
+		device->oclass[NVDEV_ENGINE_FIFO   ] =  nve0_fifo_oclass;
+		device->oclass[NVDEV_ENGINE_SW     ] =  nvc0_software_oclass;
+		device->oclass[NVDEV_ENGINE_GR     ] =  nvf0_graph_oclass;
+		device->oclass[NVDEV_ENGINE_DISP   ] =  nvf0_disp_oclass;
+		device->oclass[NVDEV_ENGINE_COPY0  ] = &nve0_copy0_oclass;
+		device->oclass[NVDEV_ENGINE_COPY1  ] = &nve0_copy1_oclass;
+		device->oclass[NVDEV_ENGINE_COPY2  ] = &nve0_copy2_oclass;
+		device->oclass[NVDEV_ENGINE_BSP    ] = &nve0_bsp_oclass;
+		device->oclass[NVDEV_ENGINE_VP     ] = &nve0_vp_oclass;
+		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
+		device->oclass[NVDEV_ENGINE_PERFMON] = &nvf0_perfmon_oclass;
+		break;
+	case 0xf1:
+		device->cname = "GK110B";
+		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nvd0_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -184,18 +234,16 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_ENGINE_COPY0  ] = &nve0_copy0_oclass;
 		device->oclass[NVDEV_ENGINE_COPY1  ] = &nve0_copy1_oclass;
 		device->oclass[NVDEV_ENGINE_COPY2  ] = &nve0_copy2_oclass;
-#if 0
 		device->oclass[NVDEV_ENGINE_BSP    ] = &nve0_bsp_oclass;
 		device->oclass[NVDEV_ENGINE_VP     ] = &nve0_vp_oclass;
 		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
-#endif
 		device->oclass[NVDEV_ENGINE_PERFMON] = &nvf0_perfmon_oclass;
 		break;
 	case 0x108:
 		device->cname = "GK208";
 		device->oclass[NVDEV_SUBDEV_VBIOS  ] = &nouveau_bios_oclass;
-		device->oclass[NVDEV_SUBDEV_GPIO   ] = &nve0_gpio_oclass;
-		device->oclass[NVDEV_SUBDEV_I2C    ] = &nvd0_i2c_oclass;
+		device->oclass[NVDEV_SUBDEV_GPIO   ] =  nve0_gpio_oclass;
+		device->oclass[NVDEV_SUBDEV_I2C    ] =  nve0_i2c_oclass;
 		device->oclass[NVDEV_SUBDEV_CLOCK  ] = &nve0_clock_oclass;
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nvd0_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
@@ -219,11 +267,9 @@ nve0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_ENGINE_COPY0  ] = &nve0_copy0_oclass;
 		device->oclass[NVDEV_ENGINE_COPY1  ] = &nve0_copy1_oclass;
 		device->oclass[NVDEV_ENGINE_COPY2  ] = &nve0_copy2_oclass;
-#if 0
 		device->oclass[NVDEV_ENGINE_BSP    ] = &nve0_bsp_oclass;
 		device->oclass[NVDEV_ENGINE_VP     ] = &nve0_vp_oclass;
 		device->oclass[NVDEV_ENGINE_PPP    ] = &nvc0_ppp_oclass;
-#endif
 		break;
 	default:
 		nv_fatal(device, "unknown Kepler chipset\n");
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/base.c b/drivers/gpu/drm/nouveau/core/engine/disp/base.c
index 7a5cae42834..9c38c5e4050 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/base.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/base.c
@@ -22,13 +22,89 @@
  * Authors: Ben Skeggs
  */
 
-#include <engine/disp.h>
+#include "priv.h"
+#include "outp.h"
+#include "conn.h"
+
+static int
+nouveau_disp_hpd_check(struct nouveau_event *event, u32 types, int index)
+{
+	struct nouveau_disp *disp = event->priv;
+	struct nvkm_output *outp;
+	list_for_each_entry(outp, &disp->outp, head) {
+		if (outp->conn->index == index) {
+			if (outp->conn->hpd.event)
+				return 0;
+			break;
+		}
+	}
+	return -ENOSYS;
+}
+
+int
+_nouveau_disp_fini(struct nouveau_object *object, bool suspend)
+{
+	struct nouveau_disp *disp = (void *)object;
+	struct nvkm_output *outp;
+	int ret;
+
+	list_for_each_entry(outp, &disp->outp, head) {
+		ret = nv_ofuncs(outp)->fini(nv_object(outp), suspend);
+		if (ret && suspend)
+			goto fail_outp;
+	}
+
+	return nouveau_engine_fini(&disp->base, suspend);
+
+fail_outp:
+	list_for_each_entry_continue_reverse(outp, &disp->outp, head) {
+		nv_ofuncs(outp)->init(nv_object(outp));
+	}
+
+	return ret;
+}
+
+int
+_nouveau_disp_init(struct nouveau_object *object)
+{
+	struct nouveau_disp *disp = (void *)object;
+	struct nvkm_output *outp;
+	int ret;
+
+	ret = nouveau_engine_init(&disp->base);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(outp, &disp->outp, head) {
+		ret = nv_ofuncs(outp)->init(nv_object(outp));
+		if (ret)
+			goto fail_outp;
+	}
+
+	return ret;
+
+fail_outp:
+	list_for_each_entry_continue_reverse(outp, &disp->outp, head) {
+		nv_ofuncs(outp)->fini(nv_object(outp), false);
+	}
+
+	return ret;
+}
 
 void
 _nouveau_disp_dtor(struct nouveau_object *object)
 {
 	struct nouveau_disp *disp = (void *)object;
+	struct nvkm_output *outp, *outt;
+
 	nouveau_event_destroy(&disp->vblank);
+
+	if (disp->outp.next) {
+		list_for_each_entry_safe(outp, outt, &disp->outp, head) {
+			nouveau_object_ref(NULL, (struct nouveau_object **)&outp);
+		}
+	}
+
 	nouveau_engine_destroy(&disp->base);
 }
 
@@ -39,8 +115,15 @@ nouveau_disp_create_(struct nouveau_object *parent,
 		     const char *intname, const char *extname,
 		     int length, void **pobject)
 {
+	struct nouveau_disp_impl *impl = (void *)oclass;
+	struct nouveau_bios *bios = nouveau_bios(parent);
 	struct nouveau_disp *disp;
-	int ret;
+	struct nouveau_oclass **sclass;
+	struct nouveau_object *object;
+	struct dcb_output dcbE;
+	u8  hpd = 0, ver, hdr;
+	u32 data;
+	int ret, i;
 
 	ret = nouveau_engine_create_(parent, engine, oclass, true,
 				     intname, extname, length, pobject);
@@ -48,5 +131,42 @@ nouveau_disp_create_(struct nouveau_object *parent,
 	if (ret)
 		return ret;
 
-	return nouveau_event_create(heads, &disp->vblank);
+	INIT_LIST_HEAD(&disp->outp);
+
+	/* create output objects for each display path in the vbios */
+	i = -1;
+	while ((data = dcb_outp_parse(bios, ++i, &ver, &hdr, &dcbE))) {
+		if (dcbE.type == DCB_OUTPUT_UNUSED)
+			continue;
+		if (dcbE.type == DCB_OUTPUT_EOL)
+			break;
+		data = dcbE.location << 4 | dcbE.type;
+
+		oclass = nvkm_output_oclass;
+		sclass = impl->outp;
+		while (sclass && sclass[0]) {
+			if (sclass[0]->handle == data) {
+				oclass = sclass[0];
+				break;
+			}
+			sclass++;
+		}
+
+		nouveau_object_ctor(*pobject, *pobject, oclass,
+				    &dcbE, i, &object);
+		hpd = max(hpd, (u8)(dcbE.connector + 1));
+	}
+
+	ret = nouveau_event_create(3, hpd, &disp->hpd);
+	if (ret)
+		return ret;
+
+	disp->hpd->priv = disp;
+	disp->hpd->check = nouveau_disp_hpd_check;
+
+	ret = nouveau_event_create(1, heads, &disp->vblank);
+	if (ret)
+		return ret;
+
+	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/conn.c b/drivers/gpu/drm/nouveau/core/engine/disp/conn.c
new file mode 100644
index 00000000000..4ffbc70ecf5
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/conn.c
@@ -0,0 +1,172 @@
+/*
+ * Copyright 2014 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include <subdev/gpio.h>
+
+#include "conn.h"
+#include "outp.h"
+
+static void
+nvkm_connector_hpd_work(struct work_struct *w)
+{
+	struct nvkm_connector *conn = container_of(w, typeof(*conn), hpd.work);
+	struct nouveau_disp *disp = nouveau_disp(conn);
+	struct nouveau_gpio *gpio = nouveau_gpio(conn);
+	u32 send = NVKM_HPD_UNPLUG;
+	if (gpio->get(gpio, 0, DCB_GPIO_UNUSED, conn->hpd.event->index))
+		send = NVKM_HPD_PLUG;
+	nouveau_event_trigger(disp->hpd, send, conn->index);
+	nouveau_event_get(conn->hpd.event);
+}
+
+static int
+nvkm_connector_hpd(void *data, u32 type, int index)
+{
+	struct nvkm_connector *conn = data;
+	DBG("HPD: %d\n", type);
+	schedule_work(&conn->hpd.work);
+	return NVKM_EVENT_DROP;
+}
+
+int
+_nvkm_connector_fini(struct nouveau_object *object, bool suspend)
+{
+	struct nvkm_connector *conn = (void *)object;
+	if (conn->hpd.event)
+		nouveau_event_put(conn->hpd.event);
+	return nouveau_object_fini(&conn->base, suspend);
+}
+
+int
+_nvkm_connector_init(struct nouveau_object *object)
+{
+	struct nvkm_connector *conn = (void *)object;
+	int ret = nouveau_object_init(&conn->base);
+	if (ret == 0) {
+		if (conn->hpd.event)
+			nouveau_event_get(conn->hpd.event);
+	}
+	return ret;
+}
+
+void
+_nvkm_connector_dtor(struct nouveau_object *object)
+{
+	struct nvkm_connector *conn = (void *)object;
+	nouveau_event_ref(NULL, &conn->hpd.event);
+	nouveau_object_destroy(&conn->base);
+}
+
+int
+nvkm_connector_create_(struct nouveau_object *parent,
+		       struct nouveau_object *engine,
+		       struct nouveau_oclass *oclass,
+		       struct nvbios_connE *info, int index,
+		       int length, void **pobject)
+{
+	static const u8 hpd[] = { 0x07, 0x08, 0x51, 0x52, 0x5e, 0x5f, 0x60 };
+	struct nouveau_gpio *gpio = nouveau_gpio(parent);
+	struct nouveau_disp *disp = (void *)engine;
+	struct nvkm_connector *conn;
+	struct nvkm_output *outp;
+	struct dcb_gpio_func func;
+	int ret;
+
+	list_for_each_entry(outp, &disp->outp, head) {
+		if (outp->conn && outp->conn->index == index) {
+			atomic_inc(&nv_object(outp->conn)->refcount);
+			*pobject = outp->conn;
+			return 1;
+		}
+	}
+
+	ret = nouveau_object_create_(parent, engine, oclass, 0, length, pobject);
+	conn = *pobject;
+	if (ret)
+		return ret;
+
+	conn->info = *info;
+	conn->index = index;
+
+	DBG("type %02x loc %d hpd %02x dp %x di %x sr %x lcdid %x\n",
+	    info->type, info->location, info->hpd, info->dp,
+	    info->di, info->sr, info->lcdid);
+
+	if ((info->hpd = ffs(info->hpd))) {
+		if (--info->hpd >= ARRAY_SIZE(hpd)) {
+			ERR("hpd %02x unknown\n", info->hpd);
+			goto done;
+		}
+		info->hpd = hpd[info->hpd];
+
+		ret = gpio->find(gpio, 0, info->hpd, DCB_GPIO_UNUSED, &func);
+		if (ret) {
+			ERR("func %02x lookup failed, %d\n", info->hpd, ret);
+			goto done;
+		}
+
+		ret = nouveau_event_new(gpio->events, NVKM_GPIO_TOGGLED,
+					func.line, nvkm_connector_hpd,
+					conn, &conn->hpd.event);
+		if (ret) {
+			ERR("func %02x failed, %d\n", info->hpd, ret);
+		} else {
+			DBG("func %02x (HPD)\n", info->hpd);
+		}
+	}
+
+done:
+	INIT_WORK(&conn->hpd.work, nvkm_connector_hpd_work);
+	return 0;
+}
+
+int
+_nvkm_connector_ctor(struct nouveau_object *parent,
+		     struct nouveau_object *engine,
+		     struct nouveau_oclass *oclass, void *info, u32 index,
+		     struct nouveau_object **pobject)
+{
+	struct nvkm_connector *conn;
+	int ret;
+
+	ret = nvkm_connector_create(parent, engine, oclass, info, index, &conn);
+	*pobject = nv_object(conn);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+struct nouveau_oclass *
+nvkm_connector_oclass = &(struct nvkm_connector_impl) {
+	.base = {
+		.handle = 0,
+		.ofuncs = &(struct nouveau_ofuncs) {
+			.ctor = _nvkm_connector_ctor,
+			.dtor = _nvkm_connector_dtor,
+			.init = _nvkm_connector_init,
+			.fini = _nvkm_connector_fini,
+		},
+	},
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/conn.h b/drivers/gpu/drm/nouveau/core/engine/disp/conn.h
new file mode 100644
index 00000000000..035ebeacbb1
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/conn.h
@@ -0,0 +1,59 @@
+#ifndef __NVKM_DISP_CONN_H__
+#define __NVKM_DISP_CONN_H__
+
+#include "priv.h"
+
+struct nvkm_connector {
+	struct nouveau_object base;
+	struct list_head head;
+
+	struct nvbios_connE info;
+	int index;
+
+	struct {
+		struct nouveau_eventh *event;
+		struct work_struct work;
+	} hpd;
+};
+
+#define nvkm_connector_create(p,e,c,b,i,d)                                     \
+	nvkm_connector_create_((p), (e), (c), (b), (i), sizeof(**d), (void **)d)
+#define nvkm_connector_destroy(d) ({                                           \
+	struct nvkm_connector *disp = (d);                                     \
+	_nvkm_connector_dtor(nv_object(disp));                                 \
+})
+#define nvkm_connector_init(d) ({                                              \
+	struct nvkm_connector *disp = (d);                                     \
+	_nvkm_connector_init(nv_object(disp));                                 \
+})
+#define nvkm_connector_fini(d,s) ({                                            \
+	struct nvkm_connector *disp = (d);                                     \
+	_nvkm_connector_fini(nv_object(disp), (s));                            \
+})
+
+int nvkm_connector_create_(struct nouveau_object *, struct nouveau_object *,
+			   struct nouveau_oclass *, struct nvbios_connE *,
+			   int, int, void **);
+
+int  _nvkm_connector_ctor(struct nouveau_object *, struct nouveau_object *,
+			  struct nouveau_oclass *, void *, u32,
+			  struct nouveau_object **);
+void _nvkm_connector_dtor(struct nouveau_object *);
+int  _nvkm_connector_init(struct nouveau_object *);
+int  _nvkm_connector_fini(struct nouveau_object *, bool);
+
+struct nvkm_connector_impl {
+	struct nouveau_oclass base;
+};
+
+#ifndef MSG
+#define MSG(l,f,a...) do {                                                     \
+	struct nvkm_connector *_conn = (void *)conn;                           \
+	nv_##l(nv_object(conn)->engine, "%02x:%02x%02x: "f, _conn->index,      \
+	       _conn->info.location, _conn->info.type, ##a);                   \
+} while(0)
+#define DBG(f,a...) MSG(debug, f, ##a)
+#define ERR(f,a...) MSG(error, f, ##a)
+#endif
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/dport.c b/drivers/gpu/drm/nouveau/core/engine/disp/dport.c
index 3ca2d25b7f5..5a5b59b2113 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/dport.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/dport.c
@@ -30,42 +30,38 @@
 
 #include <engine/disp.h>
 
-#include "dport.h"
+#include <core/class.h>
 
-#define DBG(fmt, args...) nv_debug(dp->disp, "DP:%04x:%04x: " fmt,             \
-				   dp->outp->hasht, dp->outp->hashm, ##args)
-#define ERR(fmt, args...) nv_error(dp->disp, "DP:%04x:%04x: " fmt,             \
-				   dp->outp->hasht, dp->outp->hashm, ##args)
+#include "dport.h"
+#include "outpdp.h"
 
 /******************************************************************************
  * link training
  *****************************************************************************/
 struct dp_state {
-	const struct nouveau_dp_func *func;
-	struct nouveau_disp *disp;
-	struct dcb_output *outp;
-	struct nvbios_dpout info;
-	u8 version;
-	struct nouveau_i2c_port *aux;
-	int head;
-	u8  dpcd[4];
+	struct nvkm_output_dp *outp;
 	int link_nr;
 	u32 link_bw;
 	u8  stat[6];
 	u8  conf[4];
+	bool pc2;
+	u8  pc2stat;
+	u8  pc2conf[2];
 };
 
 static int
 dp_set_link_config(struct dp_state *dp)
 {
-	struct nouveau_disp *disp = dp->disp;
+	struct nvkm_output_dp_impl *impl = (void *)nv_oclass(dp->outp);
+	struct nvkm_output_dp *outp = dp->outp;
+	struct nouveau_disp *disp = nouveau_disp(outp);
 	struct nouveau_bios *bios = nouveau_bios(disp);
 	struct nvbios_init init = {
-		.subdev = nv_subdev(dp->disp),
+		.subdev = nv_subdev(disp),
 		.bios = bios,
 		.offset = 0x0000,
-		.outp = dp->outp,
-		.crtc = dp->head,
+		.outp = &outp->base.info,
+		.crtc = -1,
 		.execute = 1,
 	};
 	u32 lnkcmp;
@@ -75,8 +71,8 @@ dp_set_link_config(struct dp_state *dp)
 	DBG("%d lanes at %d KB/s\n", dp->link_nr, dp->link_bw);
 
 	/* set desired link configuration on the source */
-	if ((lnkcmp = dp->info.lnkcmp)) {
-		if (dp->version < 0x30) {
+	if ((lnkcmp = dp->outp->info.lnkcmp)) {
+		if (outp->version < 0x30) {
 			while ((dp->link_bw / 10) < nv_ro16(bios, lnkcmp))
 				lnkcmp += 4;
 			init.offset = nv_ro16(bios, lnkcmp + 2);
@@ -89,73 +85,112 @@ dp_set_link_config(struct dp_state *dp)
 		nvbios_exec(&init);
 	}
 
-	ret = dp->func->lnk_ctl(dp->disp, dp->outp, dp->head,
-				dp->link_nr, dp->link_bw / 27000,
-				dp->dpcd[DPCD_RC02] &
-					 DPCD_RC02_ENHANCED_FRAME_CAP);
+	ret = impl->lnk_ctl(outp, dp->link_nr, dp->link_bw / 27000,
+			    outp->dpcd[DPCD_RC02] &
+				       DPCD_RC02_ENHANCED_FRAME_CAP);
 	if (ret) {
-		ERR("lnk_ctl failed with %d\n", ret);
+		if (ret < 0)
+			ERR("lnk_ctl failed with %d\n", ret);
 		return ret;
 	}
 
+	impl->lnk_pwr(outp, dp->link_nr);
+
 	/* set desired link configuration on the sink */
 	sink[0] = dp->link_bw / 27000;
 	sink[1] = dp->link_nr;
-	if (dp->dpcd[DPCD_RC02] & DPCD_RC02_ENHANCED_FRAME_CAP)
+	if (outp->dpcd[DPCD_RC02] & DPCD_RC02_ENHANCED_FRAME_CAP)
 		sink[1] |= DPCD_LC01_ENHANCED_FRAME_EN;
 
-	return nv_wraux(dp->aux, DPCD_LC00, sink, 2);
+	return nv_wraux(outp->base.edid, DPCD_LC00_LINK_BW_SET, sink, 2);
 }
 
 static void
 dp_set_training_pattern(struct dp_state *dp, u8 pattern)
 {
+	struct nvkm_output_dp_impl *impl = (void *)nv_oclass(dp->outp);
+	struct nvkm_output_dp *outp = dp->outp;
 	u8 sink_tp;
 
 	DBG("training pattern %d\n", pattern);
-	dp->func->pattern(dp->disp, dp->outp, dp->head, pattern);
+	impl->pattern(outp, pattern);
 
-	nv_rdaux(dp->aux, DPCD_LC02, &sink_tp, 1);
+	nv_rdaux(outp->base.edid, DPCD_LC02, &sink_tp, 1);
 	sink_tp &= ~DPCD_LC02_TRAINING_PATTERN_SET;
 	sink_tp |= pattern;
-	nv_wraux(dp->aux, DPCD_LC02, &sink_tp, 1);
+	nv_wraux(outp->base.edid, DPCD_LC02, &sink_tp, 1);
 }
 
 static int
-dp_link_train_commit(struct dp_state *dp)
+dp_link_train_commit(struct dp_state *dp, bool pc)
 {
-	int i;
+	struct nvkm_output_dp_impl *impl = (void *)nv_oclass(dp->outp);
+	struct nvkm_output_dp *outp = dp->outp;
+	int ret, i;
 
 	for (i = 0; i < dp->link_nr; i++) {
 		u8 lane = (dp->stat[4 + (i >> 1)] >> ((i & 1) * 4)) & 0xf;
+		u8 lpc2 = (dp->pc2stat >> (i * 2)) & 0x3;
 		u8 lpre = (lane & 0x0c) >> 2;
 		u8 lvsw = (lane & 0x03) >> 0;
+		u8 hivs = 3 - lpre;
+		u8 hipe = 3;
+		u8 hipc = 3;
+
+		if (lpc2 >= hipc)
+			lpc2 = hipc | DPCD_LC0F_LANE0_MAX_POST_CURSOR2_REACHED;
+		if (lpre >= hipe) {
+			lpre = hipe | DPCD_LC03_MAX_SWING_REACHED; /* yes. */
+			lvsw = hivs = 3 - (lpre & 3);
+		} else
+		if (lvsw >= hivs) {
+			lvsw = hivs | DPCD_LC03_MAX_SWING_REACHED;
+		}
 
 		dp->conf[i] = (lpre << 3) | lvsw;
-		if (lvsw == 3)
-			dp->conf[i] |= DPCD_LC03_MAX_SWING_REACHED;
-		if (lpre == 3)
-			dp->conf[i] |= DPCD_LC03_MAX_PRE_EMPHASIS_REACHED;
+		dp->pc2conf[i >> 1] |= lpc2 << ((i & 1) * 4);
+
+		DBG("config lane %d %02x %02x\n", i, dp->conf[i], lpc2);
+		impl->drv_ctl(outp, i, lvsw & 3, lpre & 3, lpc2 & 3);
+	}
+
+	ret = nv_wraux(outp->base.edid, DPCD_LC03(0), dp->conf, 4);
+	if (ret)
+		return ret;
 
-		DBG("config lane %d %02x\n", i, dp->conf[i]);
-		dp->func->drv_ctl(dp->disp, dp->outp, dp->head, i, lvsw, lpre);
+	if (pc) {
+		ret = nv_wraux(outp->base.edid, DPCD_LC0F, dp->pc2conf, 2);
+		if (ret)
+			return ret;
 	}
 
-	return nv_wraux(dp->aux, DPCD_LC03(0), dp->conf, 4);
+	return 0;
 }
 
 static int
-dp_link_train_update(struct dp_state *dp, u32 delay)
+dp_link_train_update(struct dp_state *dp, bool pc, u32 delay)
 {
+	struct nvkm_output_dp *outp = dp->outp;
 	int ret;
 
-	udelay(delay);
+	if (outp->dpcd[DPCD_RC0E_AUX_RD_INTERVAL])
+		mdelay(outp->dpcd[DPCD_RC0E_AUX_RD_INTERVAL] * 4);
+	else
+		udelay(delay);
 
-	ret = nv_rdaux(dp->aux, DPCD_LS02, dp->stat, 6);
+	ret = nv_rdaux(outp->base.edid, DPCD_LS02, dp->stat, 6);
 	if (ret)
 		return ret;
 
-	DBG("status %6ph\n", dp->stat);
+	if (pc) {
+		ret = nv_rdaux(outp->base.edid, DPCD_LS0C, &dp->pc2stat, 1);
+		if (ret)
+			dp->pc2stat = 0x00;
+		DBG("status %6ph pc2 %02x\n", dp->stat, dp->pc2stat);
+	} else {
+		DBG("status %6ph\n", dp->stat);
+	}
+
 	return 0;
 }
 
@@ -169,8 +204,8 @@ dp_link_train_cr(struct dp_state *dp)
 	dp_set_training_pattern(dp, 1);
 
 	do {
-		if (dp_link_train_commit(dp) ||
-		    dp_link_train_update(dp, 100))
+		if (dp_link_train_commit(dp, false) ||
+		    dp_link_train_update(dp, false, 100))
 			break;
 
 		cr_done = true;
@@ -196,13 +231,19 @@ dp_link_train_cr(struct dp_state *dp)
 static int
 dp_link_train_eq(struct dp_state *dp)
 {
+	struct nvkm_output_dp *outp = dp->outp;
 	bool eq_done = false, cr_done = true;
 	int tries = 0, i;
 
-	dp_set_training_pattern(dp, 2);
+	if (outp->dpcd[2] & DPCD_RC02_TPS3_SUPPORTED)
+		dp_set_training_pattern(dp, 3);
+	else
+		dp_set_training_pattern(dp, 2);
 
 	do {
-		if (dp_link_train_update(dp, 400))
+		if ((tries &&
+		    dp_link_train_commit(dp, dp->pc2)) ||
+		    dp_link_train_update(dp, dp->pc2, 400))
 			break;
 
 		eq_done = !!(dp->stat[2] & DPCD_LS04_INTERLANE_ALIGN_DONE);
@@ -214,9 +255,6 @@ dp_link_train_eq(struct dp_state *dp)
 			    !(lane & DPCD_LS02_LANE0_SYMBOL_LOCKED))
 				eq_done = false;
 		}
-
-		if (dp_link_train_commit(dp))
-			break;
 	} while (!eq_done && cr_done && ++tries <= 5);
 
 	return eq_done ? 0 : -1;
@@ -225,121 +263,109 @@ dp_link_train_eq(struct dp_state *dp)
 static void
 dp_link_train_init(struct dp_state *dp, bool spread)
 {
+	struct nvkm_output_dp *outp = dp->outp;
+	struct nouveau_disp *disp = nouveau_disp(outp);
+	struct nouveau_bios *bios = nouveau_bios(disp);
 	struct nvbios_init init = {
-		.subdev = nv_subdev(dp->disp),
-		.bios = nouveau_bios(dp->disp),
-		.outp = dp->outp,
-		.crtc = dp->head,
+		.subdev = nv_subdev(disp),
+		.bios = bios,
+		.outp = &outp->base.info,
+		.crtc = -1,
 		.execute = 1,
 	};
 
 	/* set desired spread */
 	if (spread)
-		init.offset = dp->info.script[2];
+		init.offset = outp->info.script[2];
 	else
-		init.offset = dp->info.script[3];
+		init.offset = outp->info.script[3];
 	nvbios_exec(&init);
 
 	/* pre-train script */
-	init.offset = dp->info.script[0];
+	init.offset = outp->info.script[0];
 	nvbios_exec(&init);
 }
 
 static void
 dp_link_train_fini(struct dp_state *dp)
 {
+	struct nvkm_output_dp *outp = dp->outp;
+	struct nouveau_disp *disp = nouveau_disp(outp);
+	struct nouveau_bios *bios = nouveau_bios(disp);
 	struct nvbios_init init = {
-		.subdev = nv_subdev(dp->disp),
-		.bios = nouveau_bios(dp->disp),
-		.outp = dp->outp,
-		.crtc = dp->head,
+		.subdev = nv_subdev(disp),
+		.bios = bios,
+		.outp = &outp->base.info,
+		.crtc = -1,
 		.execute = 1,
 	};
 
 	/* post-train script */
-	init.offset = dp->info.script[1],
+	init.offset = outp->info.script[1],
 	nvbios_exec(&init);
 }
 
-int
-nouveau_dp_train(struct nouveau_disp *disp, const struct nouveau_dp_func *func,
-		 struct dcb_output *outp, int head, u32 datarate)
+static const struct dp_rates {
+	u32 rate;
+	u8  bw;
+	u8  nr;
+} nouveau_dp_rates[] = {
+	{ 2160000, 0x14, 4 },
+	{ 1080000, 0x0a, 4 },
+	{ 1080000, 0x14, 2 },
+	{  648000, 0x06, 4 },
+	{  540000, 0x0a, 2 },
+	{  540000, 0x14, 1 },
+	{  324000, 0x06, 2 },
+	{  270000, 0x0a, 1 },
+	{  162000, 0x06, 1 },
+	{}
+};
+
+void
+nouveau_dp_train(struct work_struct *w)
 {
-	struct nouveau_bios *bios = nouveau_bios(disp);
-	struct nouveau_i2c *i2c = nouveau_i2c(disp);
+	struct nvkm_output_dp *outp = container_of(w, typeof(*outp), lt.work);
+	struct nouveau_disp *disp = nouveau_disp(outp);
+	const struct dp_rates *cfg = nouveau_dp_rates;
 	struct dp_state _dp = {
-		.disp = disp,
-		.func = func,
 		.outp = outp,
-		.head = head,
 	}, *dp = &_dp;
-	const u32 bw_list[] = { 540000, 270000, 162000, 0 };
-	const u32 *link_bw = bw_list;
-	u8  hdr, cnt, len;
-	u32 data;
+	u32 datarate = 0;
 	int ret;
 
-	/* find the bios displayport data relevant to this output */
-	data = nvbios_dpout_match(bios, outp->hasht, outp->hashm, &dp->version,
-				 &hdr, &cnt, &len, &dp->info);
-	if (!data) {
-		ERR("bios data not found\n");
-		return -EINVAL;
-	}
-
-	/* acquire the aux channel and fetch some info about the display */
-	if (outp->location)
-		dp->aux = i2c->find_type(i2c, NV_I2C_TYPE_EXTAUX(outp->extdev));
-	else
-		dp->aux = i2c->find(i2c, NV_I2C_TYPE_DCBI2C(outp->i2c_index));
-	if (!dp->aux) {
-		ERR("no aux channel?!\n");
-		return -ENODEV;
-	}
-
-	ret = nv_rdaux(dp->aux, 0x00000, dp->dpcd, sizeof(dp->dpcd));
-	if (ret) {
-		/* it's possible the display has been unplugged before we
-		 * get here.  we still need to execute the full set of
-		 * vbios scripts, and program the OR at a high enough
-		 * frequency to satisfy the target mode.  failure to do
-		 * so results at best in an UPDATE hanging, and at worst
-		 * with PDISP running away to join the circus.
-		 */
-		dp->dpcd[1] = link_bw[0] / 27000;
-		dp->dpcd[2] = 4;
-		dp->dpcd[3] = 0x00;
-		ERR("failed to read DPCD\n");
-	}
-
 	/* bring capabilities within encoder limits */
-	if ((dp->dpcd[2] & 0x1f) > dp->outp->dpconf.link_nr) {
-		dp->dpcd[2] &= ~0x1f;
-		dp->dpcd[2] |= dp->outp->dpconf.link_nr;
+	if (nv_mclass(disp) < NVD0_DISP_CLASS)
+		outp->dpcd[2] &= ~DPCD_RC02_TPS3_SUPPORTED;
+	if ((outp->dpcd[2] & 0x1f) > outp->base.info.dpconf.link_nr) {
+		outp->dpcd[2] &= ~DPCD_RC02_MAX_LANE_COUNT;
+		outp->dpcd[2] |= outp->base.info.dpconf.link_nr;
+	}
+	if (outp->dpcd[1] > outp->base.info.dpconf.link_bw)
+		outp->dpcd[1] = outp->base.info.dpconf.link_bw;
+	dp->pc2 = outp->dpcd[2] & DPCD_RC02_TPS3_SUPPORTED;
+
+	/* restrict link config to the lowest required rate, if requested */
+	if (datarate) {
+		datarate = (datarate / 8) * 10; /* 8B/10B coding overhead */
+		while (cfg[1].rate >= datarate)
+			cfg++;
 	}
-	if (dp->dpcd[1] > dp->outp->dpconf.link_bw)
-		dp->dpcd[1] = dp->outp->dpconf.link_bw;
+	cfg--;
 
-	/* adjust required bandwidth for 8B/10B coding overhead */
-	datarate = (datarate / 8) * 10;
+	/* disable link interrupt handling during link training */
+	nouveau_event_put(outp->irq);
 
 	/* enable down-spreading and execute pre-train script from vbios */
-	dp_link_train_init(dp, dp->dpcd[3] & 0x01);
+	dp_link_train_init(dp, outp->dpcd[3] & 0x01);
 
-	/* start off at highest link rate supported by encoder and display */
-	while (*link_bw > (dp->dpcd[1] * 27000))
-		link_bw++;
-
-	while ((ret = -EIO) && link_bw[0]) {
-		/* find minimum required lane count at this link rate */
-		dp->link_nr = dp->dpcd[2] & DPCD_RC02_MAX_LANE_COUNT;
-		while ((dp->link_nr >> 1) * link_bw[0] > datarate)
-			dp->link_nr >>= 1;
-
-		/* drop link rate to minimum with this lane count */
-		while ((link_bw[1] * dp->link_nr) > datarate)
-			link_bw++;
-		dp->link_bw = link_bw[0];
+	while (ret = -EIO, (++cfg)->rate) {
+		/* select next configuration supported by encoder and sink */
+		while (cfg->nr > (outp->dpcd[2] & DPCD_RC02_MAX_LANE_COUNT) ||
+		       cfg->bw > (outp->dpcd[DPCD_RC01_MAX_LINK_RATE]))
+			cfg++;
+		dp->link_bw = cfg->bw * 27000;
+		dp->link_nr = cfg->nr;
 
 		/* program selected link configuration */
 		ret = dp_set_link_config(dp);
@@ -356,17 +382,18 @@ nouveau_dp_train(struct nouveau_disp *disp, const struct nouveau_dp_func *func,
 			 */
 			break;
 		}
-
-		/* retry at lower rate */
-		link_bw++;
 	}
 
-	/* finish link training */
+	/* finish link training and execute post-train script from vbios */
 	dp_set_training_pattern(dp, 0);
 	if (ret < 0)
 		ERR("link training failed\n");
 
-	/* execute post-train script from vbios */
 	dp_link_train_fini(dp);
-	return (ret < 0) ? false : true;
+
+	/* signal completion and enable link interrupt handling */
+	DBG("training complete\n");
+	atomic_set(&outp->lt.done, 1);
+	wake_up(&outp->lt.wait);
+	nouveau_event_get(outp->irq);
 }
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/dport.h b/drivers/gpu/drm/nouveau/core/engine/disp/dport.h
index 0e1bbd18ff6..5628d2d5ec7 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/dport.h
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/dport.h
@@ -2,19 +2,18 @@
 #define __NVKM_DISP_DPORT_H__
 
 /* DPCD Receiver Capabilities */
-#define DPCD_RC00                                                       0x00000
-#define DPCD_RC00_DPCD_REV                                                 0xff
-#define DPCD_RC01                                                       0x00001
-#define DPCD_RC01_MAX_LINK_RATE                                            0xff
+#define DPCD_RC00_DPCD_REV                                              0x00000
+#define DPCD_RC01_MAX_LINK_RATE                                         0x00001
 #define DPCD_RC02                                                       0x00002
 #define DPCD_RC02_ENHANCED_FRAME_CAP                                       0x80
+#define DPCD_RC02_TPS3_SUPPORTED                                           0x40
 #define DPCD_RC02_MAX_LANE_COUNT                                           0x1f
 #define DPCD_RC03                                                       0x00003
 #define DPCD_RC03_MAX_DOWNSPREAD                                           0x01
+#define DPCD_RC0E_AUX_RD_INTERVAL                                       0x0000e
 
 /* DPCD Link Configuration */
-#define DPCD_LC00                                                       0x00100
-#define DPCD_LC00_LINK_BW_SET                                              0xff
+#define DPCD_LC00_LINK_BW_SET                                           0x00100
 #define DPCD_LC01                                                       0x00101
 #define DPCD_LC01_ENHANCED_FRAME_EN                                        0x80
 #define DPCD_LC01_LANE_COUNT_SET                                           0x1f
@@ -25,6 +24,16 @@
 #define DPCD_LC03_PRE_EMPHASIS_SET                                         0x18
 #define DPCD_LC03_MAX_SWING_REACHED                                        0x04
 #define DPCD_LC03_VOLTAGE_SWING_SET                                        0x03
+#define DPCD_LC0F                                                       0x0010f
+#define DPCD_LC0F_LANE1_MAX_POST_CURSOR2_REACHED                           0x40
+#define DPCD_LC0F_LANE1_POST_CURSOR2_SET                                   0x30
+#define DPCD_LC0F_LANE0_MAX_POST_CURSOR2_REACHED                           0x04
+#define DPCD_LC0F_LANE0_POST_CURSOR2_SET                                   0x03
+#define DPCD_LC10                                                       0x00110
+#define DPCD_LC10_LANE3_MAX_POST_CURSOR2_REACHED                           0x40
+#define DPCD_LC10_LANE3_POST_CURSOR2_SET                                   0x30
+#define DPCD_LC10_LANE2_MAX_POST_CURSOR2_REACHED                           0x04
+#define DPCD_LC10_LANE2_POST_CURSOR2_SET                                   0x03
 
 /* DPCD Link/Sink Status */
 #define DPCD_LS02                                                       0x00202
@@ -55,24 +64,12 @@
 #define DPCD_LS07_LANE3_VOLTAGE_SWING                                      0x30
 #define DPCD_LS07_LANE2_PRE_EMPHASIS                                       0x0c
 #define DPCD_LS07_LANE2_VOLTAGE_SWING                                      0x03
+#define DPCD_LS0C                                                       0x0020c
+#define DPCD_LS0C_LANE3_POST_CURSOR2                                       0xc0
+#define DPCD_LS0C_LANE2_POST_CURSOR2                                       0x30
+#define DPCD_LS0C_LANE1_POST_CURSOR2                                       0x0c
+#define DPCD_LS0C_LANE0_POST_CURSOR2                                       0x03
 
-struct nouveau_disp;
-struct dcb_output;
-
-struct nouveau_dp_func {
-	int (*pattern)(struct nouveau_disp *, struct dcb_output *,
-		       int head, int pattern);
-	int (*lnk_ctl)(struct nouveau_disp *, struct dcb_output *, int head,
-		       int link_nr, int link_bw, bool enh_frame);
-	int (*drv_ctl)(struct nouveau_disp *, struct dcb_output *, int head,
-		       int lane, int swing, int preem);
-};
-
-extern const struct nouveau_dp_func nv94_sor_dp_func;
-extern const struct nouveau_dp_func nvd0_sor_dp_func;
-extern const struct nouveau_dp_func nv50_pior_dp_func;
-
-int nouveau_dp_train(struct nouveau_disp *, const struct nouveau_dp_func *,
-		     struct dcb_output *, int, u32);
+void nouveau_dp_train(struct work_struct *);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/gm107.c b/drivers/gpu/drm/nouveau/core/engine/disp/gm107.c
index cf6f59677b7..9fc7447fec9 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/gm107.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/gm107.c
@@ -81,7 +81,6 @@ gm107_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hda_eld = nvd0_hda_eld;
 	priv->sor.hdmi = nvd0_hdmi_ctrl;
-	priv->sor.dp = &nvd0_sor_dp_func;
 	return 0;
 }
 
@@ -94,6 +93,7 @@ gm107_disp_oclass = &(struct nv50_disp_impl) {
 		.init = _nouveau_disp_init,
 		.fini = _nouveau_disp_fini,
 	},
+	.base.outp =  nvd0_disp_outp_sclass,
 	.mthd.core = &nve0_disp_mast_mthd_chan,
 	.mthd.base = &nvd0_disp_sync_mthd_chan,
 	.mthd.ovly = &nve0_disp_ovly_mthd_chan,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c
index 6c89af79288..a32666ed0c4 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv04.c
@@ -51,6 +51,14 @@ nv04_disp_scanoutpos(struct nouveau_object *object, u32 mthd,
 	args->htotal  = nv_rd32(priv, 0x680824 + (head * 0x2000)) & 0xffff;
 	args->hblanke = args->htotal - 1;
 
+	/*
+	 * If output is vga instead of digital then vtotal/htotal is invalid
+	 * so we have to give up and trigger the timestamping fallback in the
+	 * drm core.
+	 */
+	if (!args->vtotal || !args->htotal)
+		return -ENOTSUPP;
+
 	args->time[0] = ktime_to_ns(ktime_get());
 	line = nv_rd32(priv, 0x600868 + (head * 0x2000));
 	args->time[1] = ktime_to_ns(ktime_get());
@@ -78,13 +86,13 @@ nv04_disp_sclass[] = {
  ******************************************************************************/
 
 static void
-nv04_disp_vblank_enable(struct nouveau_event *event, int head)
+nv04_disp_vblank_enable(struct nouveau_event *event, int type, int head)
 {
 	nv_wr32(event->priv, 0x600140 + (head * 0x2000) , 0x00000001);
 }
 
 static void
-nv04_disp_vblank_disable(struct nouveau_event *event, int head)
+nv04_disp_vblank_disable(struct nouveau_event *event, int type, int head)
 {
 	nv_wr32(event->priv, 0x600140 + (head * 0x2000) , 0x00000000);
 }
@@ -98,12 +106,12 @@ nv04_disp_intr(struct nouveau_subdev *subdev)
 	u32 pvideo;
 
 	if (crtc0 & 0x00000001) {
-		nouveau_event_trigger(priv->base.vblank, 0);
+		nouveau_event_trigger(priv->base.vblank, 1, 0);
 		nv_wr32(priv, 0x600100, 0x00000001);
 	}
 
 	if (crtc1 & 0x00000001) {
-		nouveau_event_trigger(priv->base.vblank, 1);
+		nouveau_event_trigger(priv->base.vblank, 1, 1);
 		nv_wr32(priv, 0x602100, 0x00000001);
 	}
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
index 9a0cab9c3ad..2283c442a10 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c
@@ -829,13 +829,13 @@ nv50_disp_base_scanoutpos(struct nouveau_object *object, u32 mthd,
 }
 
 static void
-nv50_disp_base_vblank_enable(struct nouveau_event *event, int head)
+nv50_disp_base_vblank_enable(struct nouveau_event *event, int type, int head)
 {
 	nv_mask(event->priv, 0x61002c, (4 << head), (4 << head));
 }
 
 static void
-nv50_disp_base_vblank_disable(struct nouveau_event *event, int head)
+nv50_disp_base_vblank_disable(struct nouveau_event *event, int type, int head)
 {
 	nv_mask(event->priv, 0x61002c, (4 << head), 0);
 }
@@ -1114,19 +1114,20 @@ nv50_disp_intr_error(struct nv50_disp_priv *priv, int chid)
 	nv_wr32(priv, 0x610080 + (chid * 0x08), 0x90000000);
 }
 
-static u16
-exec_lookup(struct nv50_disp_priv *priv, int head, int outp, u32 ctrl,
-	    struct dcb_output *dcb, u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+static struct nvkm_output *
+exec_lookup(struct nv50_disp_priv *priv, int head, int or, u32 ctrl,
+	    u32 *data, u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
 	    struct nvbios_outp *info)
 {
 	struct nouveau_bios *bios = nouveau_bios(priv);
-	u16 mask, type, data;
+	struct nvkm_output *outp;
+	u16 mask, type;
 
-	if (outp < 4) {
+	if (or < 4) {
 		type = DCB_OUTPUT_ANALOG;
 		mask = 0;
 	} else
-	if (outp < 8) {
+	if (or < 8) {
 		switch (ctrl & 0x00000f00) {
 		case 0x00000000: type = DCB_OUTPUT_LVDS; mask = 1; break;
 		case 0x00000100: type = DCB_OUTPUT_TMDS; mask = 1; break;
@@ -1136,45 +1137,48 @@ exec_lookup(struct nv50_disp_priv *priv, int head, int outp, u32 ctrl,
 		case 0x00000900: type = DCB_OUTPUT_DP; mask = 2; break;
 		default:
 			nv_error(priv, "unknown SOR mc 0x%08x\n", ctrl);
-			return 0x0000;
+			return NULL;
 		}
-		outp -= 4;
+		or  -= 4;
 	} else {
-		outp = outp - 8;
+		or   = or - 8;
 		type = 0x0010;
 		mask = 0;
 		switch (ctrl & 0x00000f00) {
-		case 0x00000000: type |= priv->pior.type[outp]; break;
+		case 0x00000000: type |= priv->pior.type[or]; break;
 		default:
 			nv_error(priv, "unknown PIOR mc 0x%08x\n", ctrl);
-			return 0x0000;
+			return NULL;
 		}
 	}
 
 	mask  = 0x00c0 & (mask << 6);
-	mask |= 0x0001 << outp;
+	mask |= 0x0001 << or;
 	mask |= 0x0100 << head;
 
-	data = dcb_outp_match(bios, type, mask, ver, hdr, dcb);
-	if (!data)
-		return 0x0000;
-
-	/* off-chip encoders require matching the exact encoder type */
-	if (dcb->location != 0)
-		type |= dcb->extdev << 8;
+	list_for_each_entry(outp, &priv->base.outp, head) {
+		if ((outp->info.hasht & 0xff) == type &&
+		    (outp->info.hashm & mask) == mask) {
+			*data = nvbios_outp_match(bios, outp->info.hasht,
+							outp->info.hashm,
+						  ver, hdr, cnt, len, info);
+			if (!*data)
+				return NULL;
+			return outp;
+		}
+	}
 
-	return nvbios_outp_match(bios, type, mask, ver, hdr, cnt, len, info);
+	return NULL;
 }
 
-static bool
+static struct nvkm_output *
 exec_script(struct nv50_disp_priv *priv, int head, int id)
 {
 	struct nouveau_bios *bios = nouveau_bios(priv);
+	struct nvkm_output *outp;
 	struct nvbios_outp info;
-	struct dcb_output dcb;
 	u8  ver, hdr, cnt, len;
-	u16 data;
-	u32 ctrl = 0x00000000;
+	u32 data, ctrl = 0;
 	u32 reg;
 	int i;
 
@@ -1204,36 +1208,35 @@ exec_script(struct nv50_disp_priv *priv, int head, int id)
 	}
 
 	if (!(ctrl & (1 << head)))
-		return false;
+		return NULL;
 	i--;
 
-	data = exec_lookup(priv, head, i, ctrl, &dcb, &ver, &hdr, &cnt, &len, &info);
-	if (data) {
+	outp = exec_lookup(priv, head, i, ctrl, &data, &ver, &hdr, &cnt, &len, &info);
+	if (outp) {
 		struct nvbios_init init = {
 			.subdev = nv_subdev(priv),
 			.bios = bios,
 			.offset = info.script[id],
-			.outp = &dcb,
+			.outp = &outp->info,
 			.crtc = head,
 			.execute = 1,
 		};
 
-		return nvbios_exec(&init) == 0;
+		nvbios_exec(&init);
 	}
 
-	return false;
+	return outp;
 }
 
-static u32
-exec_clkcmp(struct nv50_disp_priv *priv, int head, int id, u32 pclk,
-	    struct dcb_output *outp)
+static struct nvkm_output *
+exec_clkcmp(struct nv50_disp_priv *priv, int head, int id, u32 pclk, u32 *conf)
 {
 	struct nouveau_bios *bios = nouveau_bios(priv);
+	struct nvkm_output *outp;
 	struct nvbios_outp info1;
 	struct nvbios_ocfg info2;
 	u8  ver, hdr, cnt, len;
-	u32 ctrl = 0x00000000;
-	u32 data, conf = ~0;
+	u32 data, ctrl = 0;
 	u32 reg;
 	int i;
 
@@ -1263,37 +1266,37 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id, u32 pclk,
 	}
 
 	if (!(ctrl & (1 << head)))
-		return conf;
+		return NULL;
 	i--;
 
-	data = exec_lookup(priv, head, i, ctrl, outp, &ver, &hdr, &cnt, &len, &info1);
-	if (!data)
-		return conf;
+	outp = exec_lookup(priv, head, i, ctrl, &data, &ver, &hdr, &cnt, &len, &info1);
+	if (!outp)
+		return NULL;
 
-	if (outp->location == 0) {
-		switch (outp->type) {
+	if (outp->info.location == 0) {
+		switch (outp->info.type) {
 		case DCB_OUTPUT_TMDS:
-			conf = (ctrl & 0x00000f00) >> 8;
+			*conf = (ctrl & 0x00000f00) >> 8;
 			if (pclk >= 165000)
-				conf |= 0x0100;
+				*conf |= 0x0100;
 			break;
 		case DCB_OUTPUT_LVDS:
-			conf = priv->sor.lvdsconf;
+			*conf = priv->sor.lvdsconf;
 			break;
 		case DCB_OUTPUT_DP:
-			conf = (ctrl & 0x00000f00) >> 8;
+			*conf = (ctrl & 0x00000f00) >> 8;
 			break;
 		case DCB_OUTPUT_ANALOG:
 		default:
-			conf = 0x00ff;
+			*conf = 0x00ff;
 			break;
 		}
 	} else {
-		conf = (ctrl & 0x00000f00) >> 8;
+		*conf = (ctrl & 0x00000f00) >> 8;
 		pclk = pclk / 2;
 	}
 
-	data = nvbios_ocfg_match(bios, data, conf, &ver, &hdr, &cnt, &len, &info2);
+	data = nvbios_ocfg_match(bios, data, *conf, &ver, &hdr, &cnt, &len, &info2);
 	if (data && id < 0xff) {
 		data = nvbios_oclk_match(bios, info2.clkcmp[id], pclk);
 		if (data) {
@@ -1301,7 +1304,7 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id, u32 pclk,
 				.subdev = nv_subdev(priv),
 				.bios = bios,
 				.offset = data,
-				.outp = outp,
+				.outp = &outp->info,
 				.crtc = head,
 				.execute = 1,
 			};
@@ -1310,7 +1313,7 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id, u32 pclk,
 		}
 	}
 
-	return conf;
+	return outp;
 }
 
 static void
@@ -1322,7 +1325,35 @@ nv50_disp_intr_unk10_0(struct nv50_disp_priv *priv, int head)
 static void
 nv50_disp_intr_unk20_0(struct nv50_disp_priv *priv, int head)
 {
-	exec_script(priv, head, 2);
+	struct nvkm_output *outp = exec_script(priv, head, 2);
+
+	/* the binary driver does this outside of the supervisor handling
+	 * (after the third supervisor from a detach).  we (currently?)
+	 * allow both detach/attach to happen in the same set of
+	 * supervisor interrupts, so it would make sense to execute this
+	 * (full power down?) script after all the detach phases of the
+	 * supervisor handling.  like with training if needed from the
+	 * second supervisor, nvidia doesn't do this, so who knows if it's
+	 * entirely safe, but it does appear to work..
+	 *
+	 * without this script being run, on some configurations i've
+	 * seen, switching from DP to TMDS on a DP connector may result
+	 * in a blank screen (SOR_PWR off/on can restore it)
+	 */
+	if (outp && outp->info.type == DCB_OUTPUT_DP) {
+		struct nvkm_output_dp *outpdp = (void *)outp;
+		struct nvbios_init init = {
+			.subdev = nv_subdev(priv),
+			.bios = nouveau_bios(priv),
+			.outp = &outp->info,
+			.crtc = head,
+			.offset = outpdp->info.script[4],
+			.execute = 1,
+		};
+
+		nvbios_exec(&init);
+		atomic_set(&outpdp->lt.done, 0);
+	}
 }
 
 static void
@@ -1444,56 +1475,83 @@ nv50_disp_intr_unk20_2_dp(struct nv50_disp_priv *priv,
 static void
 nv50_disp_intr_unk20_2(struct nv50_disp_priv *priv, int head)
 {
-	struct dcb_output outp;
+	struct nvkm_output *outp;
 	u32 pclk = nv_rd32(priv, 0x610ad0 + (head * 0x540)) & 0x3fffff;
 	u32 hval, hreg = 0x614200 + (head * 0x800);
 	u32 oval, oreg;
-	u32 mask;
-	u32 conf = exec_clkcmp(priv, head, 0xff, pclk, &outp);
-	if (conf != ~0) {
-		if (outp.location == 0 && outp.type == DCB_OUTPUT_DP) {
-			u32 soff = (ffs(outp.or) - 1) * 0x08;
-			u32 ctrl = nv_rd32(priv, 0x610794 + soff);
-			u32 datarate;
-
-			switch ((ctrl & 0x000f0000) >> 16) {
-			case 6: datarate = pclk * 30 / 8; break;
-			case 5: datarate = pclk * 24 / 8; break;
-			case 2:
-			default:
-				datarate = pclk * 18 / 8;
-				break;
-			}
+	u32 mask, conf;
 
-			nouveau_dp_train(&priv->base, priv->sor.dp,
-					 &outp, head, datarate);
-		}
+	outp = exec_clkcmp(priv, head, 0xff, pclk, &conf);
+	if (!outp)
+		return;
+
+	/* we allow both encoder attach and detach operations to occur
+	 * within a single supervisor (ie. modeset) sequence.  the
+	 * encoder detach scripts quite often switch off power to the
+	 * lanes, which requires the link to be re-trained.
+	 *
+	 * this is not generally an issue as the sink "must" (heh)
+	 * signal an irq when it's lost sync so the driver can
+	 * re-train.
+	 *
+	 * however, on some boards, if one does not configure at least
+	 * the gpu side of the link *before* attaching, then various
+	 * things can go horribly wrong (PDISP disappearing from mmio,
+	 * third supervisor never happens, etc).
+	 *
+	 * the solution is simply to retrain here, if necessary.  last
+	 * i checked, the binary driver userspace does not appear to
+	 * trigger this situation (it forces an UPDATE between steps).
+	 */
+	if (outp->info.type == DCB_OUTPUT_DP) {
+		u32 soff = (ffs(outp->info.or) - 1) * 0x08;
+		u32 ctrl, datarate;
 
-		exec_clkcmp(priv, head, 0, pclk, &outp);
-
-		if (!outp.location && outp.type == DCB_OUTPUT_ANALOG) {
-			oreg = 0x614280 + (ffs(outp.or) - 1) * 0x800;
-			oval = 0x00000000;
-			hval = 0x00000000;
-			mask = 0xffffffff;
-		} else
-		if (!outp.location) {
-			if (outp.type == DCB_OUTPUT_DP)
-				nv50_disp_intr_unk20_2_dp(priv, &outp, pclk);
-			oreg = 0x614300 + (ffs(outp.or) - 1) * 0x800;
-			oval = (conf & 0x0100) ? 0x00000101 : 0x00000000;
-			hval = 0x00000000;
-			mask = 0x00000707;
+		if (outp->info.location == 0) {
+			ctrl = nv_rd32(priv, 0x610794 + soff);
+			soff = 1;
 		} else {
-			oreg = 0x614380 + (ffs(outp.or) - 1) * 0x800;
-			oval = 0x00000001;
-			hval = 0x00000001;
-			mask = 0x00000707;
+			ctrl = nv_rd32(priv, 0x610b80 + soff);
+			soff = 2;
+		}
+
+		switch ((ctrl & 0x000f0000) >> 16) {
+		case 6: datarate = pclk * 30; break;
+		case 5: datarate = pclk * 24; break;
+		case 2:
+		default:
+			datarate = pclk * 18;
+			break;
 		}
 
-		nv_mask(priv, hreg, 0x0000000f, hval);
-		nv_mask(priv, oreg, mask, oval);
+		if (nvkm_output_dp_train(outp, datarate / soff, true))
+			ERR("link not trained before attach\n");
 	}
+
+	exec_clkcmp(priv, head, 0, pclk, &conf);
+
+	if (!outp->info.location && outp->info.type == DCB_OUTPUT_ANALOG) {
+		oreg = 0x614280 + (ffs(outp->info.or) - 1) * 0x800;
+		oval = 0x00000000;
+		hval = 0x00000000;
+		mask = 0xffffffff;
+	} else
+	if (!outp->info.location) {
+		if (outp->info.type == DCB_OUTPUT_DP)
+			nv50_disp_intr_unk20_2_dp(priv, &outp->info, pclk);
+		oreg = 0x614300 + (ffs(outp->info.or) - 1) * 0x800;
+		oval = (conf & 0x0100) ? 0x00000101 : 0x00000000;
+		hval = 0x00000000;
+		mask = 0x00000707;
+	} else {
+		oreg = 0x614380 + (ffs(outp->info.or) - 1) * 0x800;
+		oval = 0x00000001;
+		hval = 0x00000001;
+		mask = 0x00000707;
+	}
+
+	nv_mask(priv, hreg, 0x0000000f, hval);
+	nv_mask(priv, oreg, mask, oval);
 }
 
 /* If programming a TMDS output on a SOR that can also be configured for
@@ -1521,30 +1579,16 @@ nv50_disp_intr_unk40_0_tmds(struct nv50_disp_priv *priv, struct dcb_output *outp
 static void
 nv50_disp_intr_unk40_0(struct nv50_disp_priv *priv, int head)
 {
-	struct dcb_output outp;
+	struct nvkm_output *outp;
 	u32 pclk = nv_rd32(priv, 0x610ad0 + (head * 0x540)) & 0x3fffff;
-	if (exec_clkcmp(priv, head, 1, pclk, &outp) != ~0) {
-		if (outp.location == 0 && outp.type == DCB_OUTPUT_TMDS)
-			nv50_disp_intr_unk40_0_tmds(priv, &outp);
-		else
-		if (outp.location == 1 && outp.type == DCB_OUTPUT_DP) {
-			u32 soff = (ffs(outp.or) - 1) * 0x08;
-			u32 ctrl = nv_rd32(priv, 0x610b84 + soff);
-			u32 datarate;
-
-			switch ((ctrl & 0x000f0000) >> 16) {
-			case 6: datarate = pclk * 30 / 8; break;
-			case 5: datarate = pclk * 24 / 8; break;
-			case 2:
-			default:
-				datarate = pclk * 18 / 8;
-				break;
-			}
+	u32 conf;
 
-			nouveau_dp_train(&priv->base, priv->pior.dp,
-					 &outp, head, datarate);
-		}
-	}
+	outp = exec_clkcmp(priv, head, 1, pclk, &conf);
+	if (!outp)
+		return;
+
+	if (outp->info.location == 0 && outp->info.type == DCB_OUTPUT_TMDS)
+		nv50_disp_intr_unk40_0_tmds(priv, &outp->info);
 }
 
 void
@@ -1610,13 +1654,13 @@ nv50_disp_intr(struct nouveau_subdev *subdev)
 	}
 
 	if (intr1 & 0x00000004) {
-		nouveau_event_trigger(priv->base.vblank, 0);
+		nouveau_event_trigger(priv->base.vblank, 1, 0);
 		nv_wr32(priv, 0x610024, 0x00000004);
 		intr1 &= ~0x00000004;
 	}
 
 	if (intr1 & 0x00000008) {
-		nouveau_event_trigger(priv->base.vblank, 1);
+		nouveau_event_trigger(priv->base.vblank, 1, 1);
 		nv_wr32(priv, 0x610024, 0x00000008);
 		intr1 &= ~0x00000008;
 	}
@@ -1656,11 +1700,16 @@ nv50_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->dac.sense = nv50_dac_sense;
 	priv->sor.power = nv50_sor_power;
 	priv->pior.power = nv50_pior_power;
-	priv->pior.dp = &nv50_pior_dp_func;
 	return 0;
 }
 
 struct nouveau_oclass *
+nv50_disp_outp_sclass[] = {
+	&nv50_pior_dp_impl.base.base,
+	NULL
+};
+
+struct nouveau_oclass *
 nv50_disp_oclass = &(struct nv50_disp_impl) {
 	.base.base.handle = NV_ENGINE(DISP, 0x50),
 	.base.base.ofuncs = &(struct nouveau_ofuncs) {
@@ -1669,6 +1718,7 @@ nv50_disp_oclass = &(struct nv50_disp_impl) {
 		.init = _nouveau_disp_init,
 		.fini = _nouveau_disp_fini,
 	},
+	.base.outp =  nv50_disp_outp_sclass,
 	.mthd.core = &nv50_disp_mast_mthd_chan,
 	.mthd.base = &nv50_disp_sync_mthd_chan,
 	.mthd.ovly = &nv50_disp_ovly_mthd_chan,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.h b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.h
index 48d59db47f0..1a886472b6f 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.h
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.h
@@ -11,6 +11,8 @@
 
 #include "dport.h"
 #include "priv.h"
+#include "outp.h"
+#include "outpdp.h"
 
 struct nv50_disp_impl {
 	struct nouveau_disp_impl base;
@@ -43,13 +45,11 @@ struct nv50_disp_priv {
 		int (*hda_eld)(struct nv50_disp_priv *, int sor, u8 *, u32);
 		int (*hdmi)(struct nv50_disp_priv *, int head, int sor, u32);
 		u32 lvdsconf;
-		const struct nouveau_dp_func *dp;
 	} sor;
 	struct {
 		int nr;
 		int (*power)(struct nv50_disp_priv *, int ext, u32 data);
 		u8 type[3];
-		const struct nouveau_dp_func *dp;
 	} pior;
 };
 
@@ -199,4 +199,14 @@ void nvd0_disp_intr(struct nouveau_subdev *);
 extern const struct nv50_disp_mthd_chan nve0_disp_mast_mthd_chan;
 extern const struct nv50_disp_mthd_chan nve0_disp_ovly_mthd_chan;
 
+extern struct nvkm_output_dp_impl nv50_pior_dp_impl;
+extern struct nouveau_oclass *nv50_disp_outp_sclass[];
+
+extern struct nvkm_output_dp_impl nv94_sor_dp_impl;
+int nv94_sor_dp_lnk_pwr(struct nvkm_output_dp *, int);
+extern struct nouveau_oclass *nv94_disp_outp_sclass[];
+
+extern struct nvkm_output_dp_impl nvd0_sor_dp_impl;
+extern struct nouveau_oclass *nvd0_disp_outp_sclass[];
+
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv84.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv84.c
index 98c5b19bc2b..1cc62e43468 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv84.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv84.c
@@ -264,7 +264,6 @@ nv84_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hdmi = nv84_hdmi_ctrl;
 	priv->pior.power = nv50_pior_power;
-	priv->pior.dp = &nv50_pior_dp_func;
 	return 0;
 }
 
@@ -277,6 +276,7 @@ nv84_disp_oclass = &(struct nv50_disp_impl) {
 		.init = _nouveau_disp_init,
 		.fini = _nouveau_disp_fini,
 	},
+	.base.outp =  nv50_disp_outp_sclass,
 	.mthd.core = &nv84_disp_mast_mthd_chan,
 	.mthd.base = &nv84_disp_sync_mthd_chan,
 	.mthd.ovly = &nv84_disp_ovly_mthd_chan,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv94.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv94.c
index 6844061c7e0..4f718a9f5ae 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nv94.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv94.c
@@ -77,6 +77,7 @@ nv94_disp_base_omthds[] = {
 	{ SOR_MTHD(NV50_DISP_SOR_PWR)         , nv50_sor_mthd },
 	{ SOR_MTHD(NV84_DISP_SOR_HDMI_PWR)    , nv50_sor_mthd },
 	{ SOR_MTHD(NV50_DISP_SOR_LVDS_SCRIPT) , nv50_sor_mthd },
+	{ SOR_MTHD(NV94_DISP_SOR_DP_PWR)      , nv50_sor_mthd },
 	{ DAC_MTHD(NV50_DISP_DAC_PWR)         , nv50_dac_mthd },
 	{ DAC_MTHD(NV50_DISP_DAC_LOAD)        , nv50_dac_mthd },
 	{ PIOR_MTHD(NV50_DISP_PIOR_PWR)       , nv50_pior_mthd },
@@ -122,13 +123,18 @@ nv94_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->dac.sense = nv50_dac_sense;
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hdmi = nv84_hdmi_ctrl;
-	priv->sor.dp = &nv94_sor_dp_func;
 	priv->pior.power = nv50_pior_power;
-	priv->pior.dp = &nv50_pior_dp_func;
 	return 0;
 }
 
 struct nouveau_oclass *
+nv94_disp_outp_sclass[] = {
+	&nv50_pior_dp_impl.base.base,
+	&nv94_sor_dp_impl.base.base,
+	NULL
+};
+
+struct nouveau_oclass *
 nv94_disp_oclass = &(struct nv50_disp_impl) {
 	.base.base.handle = NV_ENGINE(DISP, 0x88),
 	.base.base.ofuncs = &(struct nouveau_ofuncs) {
@@ -137,6 +143,7 @@ nv94_disp_oclass = &(struct nv50_disp_impl) {
 		.init = _nouveau_disp_init,
 		.fini = _nouveau_disp_fini,
 	},
+	.base.outp =  nv94_disp_outp_sclass,
 	.mthd.core = &nv94_disp_mast_mthd_chan,
 	.mthd.base = &nv84_disp_sync_mthd_chan,
 	.mthd.ovly = &nv84_disp_ovly_mthd_chan,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nva0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nva0.c
index 88c96241c02..6237a9a36f7 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nva0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nva0.c
@@ -126,7 +126,6 @@ nva0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hdmi = nv84_hdmi_ctrl;
 	priv->pior.power = nv50_pior_power;
-	priv->pior.dp = &nv50_pior_dp_func;
 	return 0;
 }
 
@@ -139,6 +138,7 @@ nva0_disp_oclass = &(struct nv50_disp_impl) {
 		.init = _nouveau_disp_init,
 		.fini = _nouveau_disp_fini,
 	},
+	.base.outp =  nv50_disp_outp_sclass,
 	.mthd.core = &nv84_disp_mast_mthd_chan,
 	.mthd.base = &nv84_disp_sync_mthd_chan,
 	.mthd.ovly = &nva0_disp_ovly_mthd_chan,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nva3.c b/drivers/gpu/drm/nouveau/core/engine/disp/nva3.c
index 46cb2ce0e82..019124d4782 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nva3.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nva3.c
@@ -50,6 +50,7 @@ nva3_disp_base_omthds[] = {
 	{ SOR_MTHD(NVA3_DISP_SOR_HDA_ELD)     , nv50_sor_mthd },
 	{ SOR_MTHD(NV84_DISP_SOR_HDMI_PWR)    , nv50_sor_mthd },
 	{ SOR_MTHD(NV50_DISP_SOR_LVDS_SCRIPT) , nv50_sor_mthd },
+	{ SOR_MTHD(NV94_DISP_SOR_DP_PWR)      , nv50_sor_mthd },
 	{ DAC_MTHD(NV50_DISP_DAC_PWR)         , nv50_dac_mthd },
 	{ DAC_MTHD(NV50_DISP_DAC_LOAD)        , nv50_dac_mthd },
 	{ PIOR_MTHD(NV50_DISP_PIOR_PWR)       , nv50_pior_mthd },
@@ -96,9 +97,7 @@ nva3_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hda_eld = nva3_hda_eld;
 	priv->sor.hdmi = nva3_hdmi_ctrl;
-	priv->sor.dp = &nv94_sor_dp_func;
 	priv->pior.power = nv50_pior_power;
-	priv->pior.dp = &nv50_pior_dp_func;
 	return 0;
 }
 
@@ -111,6 +110,7 @@ nva3_disp_oclass = &(struct nv50_disp_impl) {
 		.init = _nouveau_disp_init,
 		.fini = _nouveau_disp_fini,
 	},
+	.base.outp =  nv94_disp_outp_sclass,
 	.mthd.core = &nv94_disp_mast_mthd_chan,
 	.mthd.base = &nv84_disp_sync_mthd_chan,
 	.mthd.ovly = &nv84_disp_ovly_mthd_chan,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
index 876de9ac379..fa30d8196f3 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
@@ -748,13 +748,13 @@ nvd0_disp_base_scanoutpos(struct nouveau_object *object, u32 mthd,
 }
 
 static void
-nvd0_disp_base_vblank_enable(struct nouveau_event *event, int head)
+nvd0_disp_base_vblank_enable(struct nouveau_event *event, int type, int head)
 {
 	nv_mask(event->priv, 0x6100c0 + (head * 0x800), 0x00000001, 0x00000001);
 }
 
 static void
-nvd0_disp_base_vblank_disable(struct nouveau_event *event, int head)
+nvd0_disp_base_vblank_disable(struct nouveau_event *event, int type, int head)
 {
 	nv_mask(event->priv, 0x6100c0 + (head * 0x800), 0x00000001, 0x00000000);
 }
@@ -887,6 +887,7 @@ nvd0_disp_base_omthds[] = {
 	{ SOR_MTHD(NVA3_DISP_SOR_HDA_ELD)     , nv50_sor_mthd },
 	{ SOR_MTHD(NV84_DISP_SOR_HDMI_PWR)    , nv50_sor_mthd },
 	{ SOR_MTHD(NV50_DISP_SOR_LVDS_SCRIPT) , nv50_sor_mthd },
+	{ SOR_MTHD(NV94_DISP_SOR_DP_PWR)      , nv50_sor_mthd },
 	{ DAC_MTHD(NV50_DISP_DAC_PWR)         , nv50_dac_mthd },
 	{ DAC_MTHD(NV50_DISP_DAC_LOAD)        , nv50_dac_mthd },
 	{ PIOR_MTHD(NV50_DISP_PIOR_PWR)       , nv50_pior_mthd },
@@ -915,19 +916,20 @@ nvd0_disp_sclass[] = {
  * Display engine implementation
  ******************************************************************************/
 
-static u16
-exec_lookup(struct nv50_disp_priv *priv, int head, int outp, u32 ctrl,
-	    struct dcb_output *dcb, u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+static struct nvkm_output *
+exec_lookup(struct nv50_disp_priv *priv, int head, int or, u32 ctrl,
+	    u32 *data, u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
 	    struct nvbios_outp *info)
 {
 	struct nouveau_bios *bios = nouveau_bios(priv);
-	u16 mask, type, data;
+	struct nvkm_output *outp;
+	u16 mask, type;
 
-	if (outp < 4) {
+	if (or < 4) {
 		type = DCB_OUTPUT_ANALOG;
 		mask = 0;
 	} else {
-		outp -= 4;
+		or -= 4;
 		switch (ctrl & 0x00000f00) {
 		case 0x00000000: type = DCB_OUTPUT_LVDS; mask = 1; break;
 		case 0x00000100: type = DCB_OUTPUT_TMDS; mask = 1; break;
@@ -939,101 +941,106 @@ exec_lookup(struct nv50_disp_priv *priv, int head, int outp, u32 ctrl,
 			nv_error(priv, "unknown SOR mc 0x%08x\n", ctrl);
 			return 0x0000;
 		}
-		dcb->sorconf.link = mask;
 	}
 
 	mask  = 0x00c0 & (mask << 6);
-	mask |= 0x0001 << outp;
+	mask |= 0x0001 << or;
 	mask |= 0x0100 << head;
 
-	data = dcb_outp_match(bios, type, mask, ver, hdr, dcb);
-	if (!data)
-		return 0x0000;
+	list_for_each_entry(outp, &priv->base.outp, head) {
+		if ((outp->info.hasht & 0xff) == type &&
+		    (outp->info.hashm & mask) == mask) {
+			*data = nvbios_outp_match(bios, outp->info.hasht,
+							outp->info.hashm,
+						  ver, hdr, cnt, len, info);
+			if (!*data)
+				return NULL;
+			return outp;
+		}
+	}
 
-	return nvbios_outp_match(bios, type, mask, ver, hdr, cnt, len, info);
+	return NULL;
 }
 
-static bool
+static struct nvkm_output *
 exec_script(struct nv50_disp_priv *priv, int head, int id)
 {
 	struct nouveau_bios *bios = nouveau_bios(priv);
+	struct nvkm_output *outp;
 	struct nvbios_outp info;
-	struct dcb_output dcb;
 	u8  ver, hdr, cnt, len;
-	u32 ctrl = 0x00000000;
-	u16 data;
-	int outp;
+	u32 data, ctrl = 0;
+	int or;
 
-	for (outp = 0; !(ctrl & (1 << head)) && outp < 8; outp++) {
-		ctrl = nv_rd32(priv, 0x640180 + (outp * 0x20));
+	for (or = 0; !(ctrl & (1 << head)) && or < 8; or++) {
+		ctrl = nv_rd32(priv, 0x640180 + (or * 0x20));
 		if (ctrl & (1 << head))
 			break;
 	}
 
-	if (outp == 8)
-		return false;
+	if (or == 8)
+		return NULL;
 
-	data = exec_lookup(priv, head, outp, ctrl, &dcb, &ver, &hdr, &cnt, &len, &info);
-	if (data) {
+	outp = exec_lookup(priv, head, or, ctrl, &data, &ver, &hdr, &cnt, &len, &info);
+	if (outp) {
 		struct nvbios_init init = {
 			.subdev = nv_subdev(priv),
 			.bios = bios,
 			.offset = info.script[id],
-			.outp = &dcb,
+			.outp = &outp->info,
 			.crtc = head,
 			.execute = 1,
 		};
 
-		return nvbios_exec(&init) == 0;
+		nvbios_exec(&init);
 	}
 
-	return false;
+	return outp;
 }
 
-static u32
-exec_clkcmp(struct nv50_disp_priv *priv, int head, int id,
-	    u32 pclk, struct dcb_output *dcb)
+static struct nvkm_output *
+exec_clkcmp(struct nv50_disp_priv *priv, int head, int id, u32 pclk, u32 *conf)
 {
 	struct nouveau_bios *bios = nouveau_bios(priv);
+	struct nvkm_output *outp;
 	struct nvbios_outp info1;
 	struct nvbios_ocfg info2;
 	u8  ver, hdr, cnt, len;
-	u32 ctrl = 0x00000000;
-	u32 data, conf = ~0;
-	int outp;
+	u32 data, ctrl = 0;
+	int or;
 
-	for (outp = 0; !(ctrl & (1 << head)) && outp < 8; outp++) {
-		ctrl = nv_rd32(priv, 0x660180 + (outp * 0x20));
+	for (or = 0; !(ctrl & (1 << head)) && or < 8; or++) {
+		ctrl = nv_rd32(priv, 0x660180 + (or * 0x20));
 		if (ctrl & (1 << head))
 			break;
 	}
 
-	if (outp == 8)
-		return conf;
+	if (or == 8)
+		return NULL;
 
-	data = exec_lookup(priv, head, outp, ctrl, dcb, &ver, &hdr, &cnt, &len, &info1);
-	if (data == 0x0000)
-		return conf;
+	outp = exec_lookup(priv, head, or, ctrl, &data, &ver, &hdr, &cnt, &len, &info1);
+	if (!outp)
+		return NULL;
 
-	switch (dcb->type) {
+	switch (outp->info.type) {
 	case DCB_OUTPUT_TMDS:
-		conf = (ctrl & 0x00000f00) >> 8;
+		*conf = (ctrl & 0x00000f00) >> 8;
 		if (pclk >= 165000)
-			conf |= 0x0100;
+			*conf |= 0x0100;
 		break;
 	case DCB_OUTPUT_LVDS:
-		conf = priv->sor.lvdsconf;
+		*conf = priv->sor.lvdsconf;
 		break;
 	case DCB_OUTPUT_DP:
-		conf = (ctrl & 0x00000f00) >> 8;
+		*conf = (ctrl & 0x00000f00) >> 8;
 		break;
 	case DCB_OUTPUT_ANALOG:
 	default:
-		conf = 0x00ff;
+		*conf = 0x00ff;
 		break;
 	}
 
-	data = nvbios_ocfg_match(bios, data, conf, &ver, &hdr, &cnt, &len, &info2);
+	data = nvbios_ocfg_match(bios, data, *conf, &ver, &hdr, &cnt, &len, &info2);
 	if (data && id < 0xff) {
 		data = nvbios_oclk_match(bios, info2.clkcmp[id], pclk);
 		if (data) {
@@ -1041,7 +1048,7 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id,
 				.subdev = nv_subdev(priv),
 				.bios = bios,
 				.offset = data,
-				.outp = dcb,
+				.outp = &outp->info,
 				.crtc = head,
 				.execute = 1,
 			};
@@ -1050,7 +1057,7 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id,
 		}
 	}
 
-	return conf;
+	return outp;
 }
 
 static void
@@ -1062,7 +1069,23 @@ nvd0_disp_intr_unk1_0(struct nv50_disp_priv *priv, int head)
 static void
 nvd0_disp_intr_unk2_0(struct nv50_disp_priv *priv, int head)
 {
-	exec_script(priv, head, 2);
+	struct nvkm_output *outp = exec_script(priv, head, 2);
+
+	/* see note in nv50_disp_intr_unk20_0() */
+	if (outp && outp->info.type == DCB_OUTPUT_DP) {
+		struct nvkm_output_dp *outpdp = (void *)outp;
+		struct nvbios_init init = {
+			.subdev = nv_subdev(priv),
+			.bios = nouveau_bios(priv),
+			.outp = &outp->info,
+			.crtc = head,
+			.offset = outpdp->info.script[4],
+			.execute = 1,
+		};
+
+		nvbios_exec(&init);
+		atomic_set(&outpdp->lt.done, 0);
+	}
 }
 
 static void
@@ -1124,49 +1147,52 @@ nvd0_disp_intr_unk2_2_tu(struct nv50_disp_priv *priv, int head,
 static void
 nvd0_disp_intr_unk2_2(struct nv50_disp_priv *priv, int head)
 {
-	struct dcb_output outp;
+	struct nvkm_output *outp;
 	u32 pclk = nv_rd32(priv, 0x660450 + (head * 0x300)) / 1000;
-	u32 conf = exec_clkcmp(priv, head, 0xff, pclk, &outp);
-	if (conf != ~0) {
-		u32 addr, data;
-
-		if (outp.type == DCB_OUTPUT_DP) {
-			u32 sync = nv_rd32(priv, 0x660404 + (head * 0x300));
-			switch ((sync & 0x000003c0) >> 6) {
-			case 6: pclk = pclk * 30 / 8; break;
-			case 5: pclk = pclk * 24 / 8; break;
-			case 2:
-			default:
-				pclk = pclk * 18 / 8;
-				break;
-			}
-
-			nouveau_dp_train(&priv->base, priv->sor.dp,
-					 &outp, head, pclk);
+	u32 conf, addr, data;
+
+	outp = exec_clkcmp(priv, head, 0xff, pclk, &conf);
+	if (!outp)
+		return;
+
+	/* see note in nv50_disp_intr_unk20_2() */
+	if (outp->info.type == DCB_OUTPUT_DP) {
+		u32 sync = nv_rd32(priv, 0x660404 + (head * 0x300));
+		switch ((sync & 0x000003c0) >> 6) {
+		case 6: pclk = pclk * 30; break;
+		case 5: pclk = pclk * 24; break;
+		case 2:
+		default:
+			pclk = pclk * 18;
+			break;
 		}
 
-		exec_clkcmp(priv, head, 0, pclk, &outp);
+		if (nvkm_output_dp_train(outp, pclk, true))
+			ERR("link not trained before attach\n");
+	}
 
-		if (outp.type == DCB_OUTPUT_ANALOG) {
-			addr = 0x612280 + (ffs(outp.or) - 1) * 0x800;
-			data = 0x00000000;
-		} else {
-			if (outp.type == DCB_OUTPUT_DP)
-				nvd0_disp_intr_unk2_2_tu(priv, head, &outp);
-			addr = 0x612300 + (ffs(outp.or) - 1) * 0x800;
-			data = (conf & 0x0100) ? 0x00000101 : 0x00000000;
-		}
+	exec_clkcmp(priv, head, 0, pclk, &conf);
 
-		nv_mask(priv, addr, 0x00000707, data);
+	if (outp->info.type == DCB_OUTPUT_ANALOG) {
+		addr = 0x612280 + (ffs(outp->info.or) - 1) * 0x800;
+		data = 0x00000000;
+	} else {
+		if (outp->info.type == DCB_OUTPUT_DP)
+			nvd0_disp_intr_unk2_2_tu(priv, head, &outp->info);
+		addr = 0x612300 + (ffs(outp->info.or) - 1) * 0x800;
+		data = (conf & 0x0100) ? 0x00000101 : 0x00000000;
 	}
+
+	nv_mask(priv, addr, 0x00000707, data);
 }
 
 static void
 nvd0_disp_intr_unk4_0(struct nv50_disp_priv *priv, int head)
 {
-	struct dcb_output outp;
 	u32 pclk = nv_rd32(priv, 0x660450 + (head * 0x300)) / 1000;
-	exec_clkcmp(priv, head, 1, pclk, &outp);
+	u32 conf;
+
+	exec_clkcmp(priv, head, 1, pclk, &conf);
 }
 
 void
@@ -1240,7 +1266,7 @@ nvd0_disp_intr_error(struct nv50_disp_priv *priv, int chid)
 		 chid, (mthd & 0x0000ffc), data, mthd, unkn);
 
 	if (chid == 0) {
-		switch (mthd) {
+		switch (mthd & 0xffc) {
 		case 0x0080:
 			nv50_disp_mthd_chan(priv, NV_DBG_ERROR, chid - 0,
 					    impl->mthd.core);
@@ -1250,7 +1276,7 @@ nvd0_disp_intr_error(struct nv50_disp_priv *priv, int chid)
 		}
 	} else
 	if (chid <= 4) {
-		switch (mthd) {
+		switch (mthd & 0xffc) {
 		case 0x0080:
 			nv50_disp_mthd_chan(priv, NV_DBG_ERROR, chid - 1,
 					    impl->mthd.base);
@@ -1260,7 +1286,7 @@ nvd0_disp_intr_error(struct nv50_disp_priv *priv, int chid)
 		}
 	} else
 	if (chid <= 8) {
-		switch (mthd) {
+		switch (mthd & 0xffc) {
 		case 0x0080:
 			nv50_disp_mthd_chan(priv, NV_DBG_ERROR, chid - 5,
 					    impl->mthd.ovly);
@@ -1317,7 +1343,7 @@ nvd0_disp_intr(struct nouveau_subdev *subdev)
 		if (mask & intr) {
 			u32 stat = nv_rd32(priv, 0x6100bc + (i * 0x800));
 			if (stat & 0x00000001)
-				nouveau_event_trigger(priv->base.vblank, i);
+				nouveau_event_trigger(priv->base.vblank, 1, i);
 			nv_mask(priv, 0x6100bc + (i * 0x800), 0, 0);
 			nv_rd32(priv, 0x6100c0 + (i * 0x800));
 		}
@@ -1352,11 +1378,16 @@ nvd0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hda_eld = nvd0_hda_eld;
 	priv->sor.hdmi = nvd0_hdmi_ctrl;
-	priv->sor.dp = &nvd0_sor_dp_func;
 	return 0;
 }
 
 struct nouveau_oclass *
+nvd0_disp_outp_sclass[] = {
+	&nvd0_sor_dp_impl.base.base,
+	NULL
+};
+
+struct nouveau_oclass *
 nvd0_disp_oclass = &(struct nv50_disp_impl) {
 	.base.base.handle = NV_ENGINE(DISP, 0x90),
 	.base.base.ofuncs = &(struct nouveau_ofuncs) {
@@ -1365,6 +1396,7 @@ nvd0_disp_oclass = &(struct nv50_disp_impl) {
 		.init = _nouveau_disp_init,
 		.fini = _nouveau_disp_fini,
 	},
+	.base.outp =  nvd0_disp_outp_sclass,
 	.mthd.core = &nvd0_disp_mast_mthd_chan,
 	.mthd.base = &nvd0_disp_sync_mthd_chan,
 	.mthd.ovly = &nvd0_disp_ovly_mthd_chan,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nve0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nve0.c
index 44e0b8f34c1..11328e3f5df 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nve0.c
@@ -246,7 +246,6 @@ nve0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hda_eld = nvd0_hda_eld;
 	priv->sor.hdmi = nvd0_hdmi_ctrl;
-	priv->sor.dp = &nvd0_sor_dp_func;
 	return 0;
 }
 
@@ -259,6 +258,7 @@ nve0_disp_oclass = &(struct nv50_disp_impl) {
 		.init = _nouveau_disp_init,
 		.fini = _nouveau_disp_fini,
 	},
+	.base.outp =  nvd0_disp_outp_sclass,
 	.mthd.core = &nve0_disp_mast_mthd_chan,
 	.mthd.base = &nvd0_disp_sync_mthd_chan,
 	.mthd.ovly = &nve0_disp_ovly_mthd_chan,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nvf0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nvf0.c
index 482585d375f..104388081d7 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nvf0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nvf0.c
@@ -81,7 +81,6 @@ nvf0_disp_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	priv->sor.power = nv50_sor_power;
 	priv->sor.hda_eld = nvd0_hda_eld;
 	priv->sor.hdmi = nvd0_hdmi_ctrl;
-	priv->sor.dp = &nvd0_sor_dp_func;
 	return 0;
 }
 
@@ -94,6 +93,7 @@ nvf0_disp_oclass = &(struct nv50_disp_impl) {
 		.init = _nouveau_disp_init,
 		.fini = _nouveau_disp_fini,
 	},
+	.base.outp =  nvd0_disp_outp_sclass,
 	.mthd.core = &nve0_disp_mast_mthd_chan,
 	.mthd.base = &nvd0_disp_sync_mthd_chan,
 	.mthd.ovly = &nve0_disp_ovly_mthd_chan,
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/outp.c b/drivers/gpu/drm/nouveau/core/engine/disp/outp.c
new file mode 100644
index 00000000000..ad9ba7ccec7
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/outp.c
@@ -0,0 +1,137 @@
+/*
+ * Copyright 2014 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include <subdev/i2c.h>
+#include <subdev/bios.h>
+#include <subdev/bios/conn.h>
+
+#include "outp.h"
+
+int
+_nvkm_output_fini(struct nouveau_object *object, bool suspend)
+{
+	struct nvkm_output *outp = (void *)object;
+	nv_ofuncs(outp->conn)->fini(nv_object(outp->conn), suspend);
+	return nouveau_object_fini(&outp->base, suspend);
+}
+
+int
+_nvkm_output_init(struct nouveau_object *object)
+{
+	struct nvkm_output *outp = (void *)object;
+	int ret = nouveau_object_init(&outp->base);
+	if (ret == 0)
+		nv_ofuncs(outp->conn)->init(nv_object(outp->conn));
+	return 0;
+}
+
+void
+_nvkm_output_dtor(struct nouveau_object *object)
+{
+	struct nvkm_output *outp = (void *)object;
+	list_del(&outp->head);
+	nouveau_object_ref(NULL, (void *)&outp->conn);
+	nouveau_object_destroy(&outp->base);
+}
+
+int
+nvkm_output_create_(struct nouveau_object *parent,
+		    struct nouveau_object *engine,
+		    struct nouveau_oclass *oclass,
+		    struct dcb_output *dcbE, int index,
+		    int length, void **pobject)
+{
+	struct nouveau_bios *bios = nouveau_bios(engine);
+	struct nouveau_i2c *i2c = nouveau_i2c(parent);
+	struct nouveau_disp *disp = (void *)engine;
+	struct nvbios_connE connE;
+	struct nvkm_output *outp;
+	u8  ver, hdr;
+	u32 data;
+	int ret;
+
+	ret = nouveau_object_create_(parent, engine, oclass, 0, length, pobject);
+	outp = *pobject;
+	if (ret)
+		return ret;
+
+	outp->info = *dcbE;
+	outp->index = index;
+
+	DBG("type %02x loc %d or %d link %d con %x edid %x bus %d head %x\n",
+	    dcbE->type, dcbE->location, dcbE->or, dcbE->type >= 2 ?
+	    dcbE->sorconf.link : 0, dcbE->connector, dcbE->i2c_index,
+	    dcbE->bus, dcbE->heads);
+
+	outp->port = i2c->find(i2c, outp->info.i2c_index);
+	outp->edid = outp->port;
+
+	data = nvbios_connEp(bios, outp->info.connector, &ver, &hdr, &connE);
+	if (!data) {
+		DBG("vbios connector data not found\n");
+		memset(&connE, 0x00, sizeof(connE));
+		connE.type = DCB_CONNECTOR_NONE;
+	}
+
+	ret = nouveau_object_ctor(parent, engine, nvkm_connector_oclass,
+				 &connE, outp->info.connector,
+				 (struct nouveau_object **)&outp->conn);
+	if (ret < 0) {
+		ERR("error %d creating connector, disabling\n", ret);
+		return ret;
+	}
+
+	list_add_tail(&outp->head, &disp->outp);
+	return 0;
+}
+
+int
+_nvkm_output_ctor(struct nouveau_object *parent,
+		  struct nouveau_object *engine,
+		  struct nouveau_oclass *oclass, void *dcbE, u32 index,
+		  struct nouveau_object **pobject)
+{
+	struct nvkm_output *outp;
+	int ret;
+
+	ret = nvkm_output_create(parent, engine, oclass, dcbE, index, &outp);
+	*pobject = nv_object(outp);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+struct nouveau_oclass *
+nvkm_output_oclass = &(struct nvkm_output_impl) {
+	.base = {
+		.handle = 0,
+		.ofuncs = &(struct nouveau_ofuncs) {
+			.ctor = _nvkm_output_ctor,
+			.dtor = _nvkm_output_dtor,
+			.init = _nvkm_output_init,
+			.fini = _nvkm_output_fini,
+		},
+	},
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/outp.h b/drivers/gpu/drm/nouveau/core/engine/disp/outp.h
new file mode 100644
index 00000000000..bc76fbf8571
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/outp.h
@@ -0,0 +1,59 @@
+#ifndef __NVKM_DISP_OUTP_H__
+#define __NVKM_DISP_OUTP_H__
+
+#include "priv.h"
+
+struct nvkm_output {
+	struct nouveau_object base;
+	struct list_head head;
+
+	struct dcb_output info;
+	int index;
+
+	struct nouveau_i2c_port *port;
+	struct nouveau_i2c_port *edid;
+
+	struct nvkm_connector *conn;
+};
+
+#define nvkm_output_create(p,e,c,b,i,d)                                        \
+	nvkm_output_create_((p), (e), (c), (b), (i), sizeof(**d), (void **)d)
+#define nvkm_output_destroy(d) ({                                              \
+	struct nvkm_output *_outp = (d);                                       \
+	_nvkm_output_dtor(nv_object(_outp));                                   \
+})
+#define nvkm_output_init(d) ({                                                 \
+	struct nvkm_output *_outp = (d);                                       \
+	_nvkm_output_init(nv_object(_outp));                                   \
+})
+#define nvkm_output_fini(d,s) ({                                               \
+	struct nvkm_output *_outp = (d);                                       \
+	_nvkm_output_fini(nv_object(_outp), (s));                              \
+})
+
+int nvkm_output_create_(struct nouveau_object *, struct nouveau_object *,
+			struct nouveau_oclass *, struct dcb_output *,
+			int, int, void **);
+
+int  _nvkm_output_ctor(struct nouveau_object *, struct nouveau_object *,
+		       struct nouveau_oclass *, void *, u32,
+		       struct nouveau_object **);
+void _nvkm_output_dtor(struct nouveau_object *);
+int  _nvkm_output_init(struct nouveau_object *);
+int  _nvkm_output_fini(struct nouveau_object *, bool);
+
+struct nvkm_output_impl {
+	struct nouveau_oclass base;
+};
+
+#ifndef MSG
+#define MSG(l,f,a...) do {                                                     \
+	struct nvkm_output *_outp = (void *)outp;                              \
+	nv_##l(nv_object(outp)->engine, "%02x:%04x:%04x: "f, _outp->index,     \
+	       _outp->info.hasht, _outp->info.hashm, ##a);                     \
+} while(0)
+#define DBG(f,a...) MSG(debug, f, ##a)
+#define ERR(f,a...) MSG(error, f, ##a)
+#endif
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.c b/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.c
new file mode 100644
index 00000000000..eb2d7789555
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.c
@@ -0,0 +1,278 @@
+/*
+ * Copyright 2014 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include <subdev/i2c.h>
+
+#include "outpdp.h"
+#include "conn.h"
+#include "dport.h"
+
+int
+nvkm_output_dp_train(struct nvkm_output *base, u32 datarate, bool wait)
+{
+	struct nvkm_output_dp *outp = (void *)base;
+	bool retrain = true;
+	u8 link[2], stat[3];
+	u32 linkrate;
+	int ret, i;
+
+	/* check that the link is trained at a high enough rate */
+	ret = nv_rdaux(outp->base.edid, DPCD_LC00_LINK_BW_SET, link, 2);
+	if (ret) {
+		DBG("failed to read link config, assuming no sink\n");
+		goto done;
+	}
+
+	linkrate = link[0] * 27000 * (link[1] & DPCD_LC01_LANE_COUNT_SET);
+	linkrate = (linkrate * 8) / 10; /* 8B/10B coding overhead */
+	datarate = (datarate + 9) / 10; /* -> decakilobits */
+	if (linkrate < datarate) {
+		DBG("link not trained at sufficient rate\n");
+		goto done;
+	}
+
+	/* check that link is still trained */
+	ret = nv_rdaux(outp->base.edid, DPCD_LS02, stat, 3);
+	if (ret) {
+		DBG("failed to read link status, assuming no sink\n");
+		goto done;
+	}
+
+	if (stat[2] & DPCD_LS04_INTERLANE_ALIGN_DONE) {
+		for (i = 0; i < (link[1] & DPCD_LC01_LANE_COUNT_SET); i++) {
+			u8 lane = (stat[i >> 1] >> ((i & 1) * 4)) & 0x0f;
+			if (!(lane & DPCD_LS02_LANE0_CR_DONE) ||
+			    !(lane & DPCD_LS02_LANE0_CHANNEL_EQ_DONE) ||
+			    !(lane & DPCD_LS02_LANE0_SYMBOL_LOCKED)) {
+				DBG("lane %d not equalised\n", lane);
+				goto done;
+			}
+		}
+		retrain = false;
+	} else {
+		DBG("no inter-lane alignment\n");
+	}
+
+done:
+	if (retrain || !atomic_read(&outp->lt.done)) {
+		/* no sink, but still need to configure source */
+		if (outp->dpcd[DPCD_RC00_DPCD_REV] == 0x00) {
+			outp->dpcd[DPCD_RC01_MAX_LINK_RATE] =
+				outp->base.info.dpconf.link_bw;
+			outp->dpcd[DPCD_RC02] =
+				outp->base.info.dpconf.link_nr;
+		}
+		atomic_set(&outp->lt.done, 0);
+		schedule_work(&outp->lt.work);
+	} else {
+		nouveau_event_get(outp->irq);
+	}
+
+	if (wait) {
+		if (!wait_event_timeout(outp->lt.wait,
+					atomic_read(&outp->lt.done),
+					msecs_to_jiffies(2000)))
+			ret = -ETIMEDOUT;
+	}
+
+	return ret;
+}
+
+static void
+nvkm_output_dp_enable(struct nvkm_output_dp *outp, bool present)
+{
+	struct nouveau_i2c_port *port = outp->base.edid;
+	if (present) {
+		if (!outp->present) {
+			nouveau_i2c(port)->acquire_pad(port, 0);
+			DBG("aux power -> always\n");
+			outp->present = true;
+		}
+		nvkm_output_dp_train(&outp->base, 0, true);
+	} else {
+		if (outp->present) {
+			nouveau_i2c(port)->release_pad(port);
+			DBG("aux power -> demand\n");
+			outp->present = false;
+		}
+		atomic_set(&outp->lt.done, 0);
+	}
+}
+
+static void
+nvkm_output_dp_detect(struct nvkm_output_dp *outp)
+{
+	struct nouveau_i2c_port *port = outp->base.edid;
+	int ret = nouveau_i2c(port)->acquire_pad(port, 0);
+	if (ret == 0) {
+		ret = nv_rdaux(outp->base.edid, DPCD_RC00_DPCD_REV,
+			       outp->dpcd, sizeof(outp->dpcd));
+		nvkm_output_dp_enable(outp, ret == 0);
+		nouveau_i2c(port)->release_pad(port);
+	}
+}
+
+static void
+nvkm_output_dp_service_work(struct work_struct *work)
+{
+	struct nvkm_output_dp *outp = container_of(work, typeof(*outp), work);
+	struct nouveau_disp *disp = nouveau_disp(outp);
+	int type = atomic_xchg(&outp->pending, 0);
+	u32 send = 0;
+
+	if (type & (NVKM_I2C_PLUG | NVKM_I2C_UNPLUG)) {
+		nvkm_output_dp_detect(outp);
+		if (type & NVKM_I2C_UNPLUG)
+			send |= NVKM_HPD_UNPLUG;
+		if (type & NVKM_I2C_PLUG)
+			send |= NVKM_HPD_PLUG;
+		nouveau_event_get(outp->base.conn->hpd.event);
+	}
+
+	if (type & NVKM_I2C_IRQ) {
+		nvkm_output_dp_train(&outp->base, 0, true);
+		send |= NVKM_HPD_IRQ;
+	}
+
+	nouveau_event_trigger(disp->hpd, send, outp->base.info.connector);
+}
+
+static int
+nvkm_output_dp_service(void *data, u32 type, int index)
+{
+	struct nvkm_output_dp *outp = data;
+	DBG("HPD: %d\n", type);
+	atomic_or(type, &outp->pending);
+	schedule_work(&outp->work);
+	return NVKM_EVENT_DROP;
+}
+
+int
+_nvkm_output_dp_fini(struct nouveau_object *object, bool suspend)
+{
+	struct nvkm_output_dp *outp = (void *)object;
+	nouveau_event_put(outp->irq);
+	nvkm_output_dp_enable(outp, false);
+	return nvkm_output_fini(&outp->base, suspend);
+}
+
+int
+_nvkm_output_dp_init(struct nouveau_object *object)
+{
+	struct nvkm_output_dp *outp = (void *)object;
+	nvkm_output_dp_detect(outp);
+	return nvkm_output_init(&outp->base);
+}
+
+void
+_nvkm_output_dp_dtor(struct nouveau_object *object)
+{
+	struct nvkm_output_dp *outp = (void *)object;
+	nouveau_event_ref(NULL, &outp->irq);
+	nvkm_output_destroy(&outp->base);
+}
+
+int
+nvkm_output_dp_create_(struct nouveau_object *parent,
+		       struct nouveau_object *engine,
+		       struct nouveau_oclass *oclass,
+		       struct dcb_output *info, int index,
+		       int length, void **pobject)
+{
+	struct nouveau_bios *bios = nouveau_bios(parent);
+	struct nouveau_i2c *i2c = nouveau_i2c(parent);
+	struct nvkm_output_dp *outp;
+	u8  hdr, cnt, len;
+	u32 data;
+	int ret;
+
+	ret = nvkm_output_create_(parent, engine, oclass, info, index,
+				  length, pobject);
+	outp = *pobject;
+	if (ret)
+		return ret;
+
+	nouveau_event_ref(NULL, &outp->base.conn->hpd.event);
+
+	/* access to the aux channel is not optional... */
+	if (!outp->base.edid) {
+		ERR("aux channel not found\n");
+		return -ENODEV;
+	}
+
+	/* nor is the bios data for this output... */
+	data = nvbios_dpout_match(bios, outp->base.info.hasht,
+				  outp->base.info.hashm, &outp->version,
+				  &hdr, &cnt, &len, &outp->info);
+	if (!data) {
+		ERR("no bios dp data\n");
+		return -ENODEV;
+	}
+
+	DBG("bios dp %02x %02x %02x %02x\n", outp->version, hdr, cnt, len);
+
+	/* link training */
+	INIT_WORK(&outp->lt.work, nouveau_dp_train);
+	init_waitqueue_head(&outp->lt.wait);
+	atomic_set(&outp->lt.done, 0);
+
+	/* link maintenance */
+	ret = nouveau_event_new(i2c->ntfy, NVKM_I2C_IRQ, outp->base.edid->index,
+				nvkm_output_dp_service, outp, &outp->irq);
+	if (ret) {
+		ERR("error monitoring aux irq event: %d\n", ret);
+		return ret;
+	}
+
+	INIT_WORK(&outp->work, nvkm_output_dp_service_work);
+
+	/* hotplug detect, replaces gpio-based mechanism with aux events */
+	ret = nouveau_event_new(i2c->ntfy, NVKM_I2C_PLUG | NVKM_I2C_UNPLUG,
+				outp->base.edid->index,
+				nvkm_output_dp_service, outp,
+			       &outp->base.conn->hpd.event);
+	if (ret) {
+		ERR("error monitoring aux hpd events: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int
+_nvkm_output_dp_ctor(struct nouveau_object *parent,
+		     struct nouveau_object *engine,
+		     struct nouveau_oclass *oclass, void *info, u32 index,
+		     struct nouveau_object **pobject)
+{
+	struct nvkm_output_dp *outp;
+	int ret;
+
+	ret = nvkm_output_dp_create(parent, engine, oclass, info, index, &outp);
+	*pobject = nv_object(outp);
+	if (ret)
+		return ret;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.h b/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.h
new file mode 100644
index 00000000000..ff33ba12cb6
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/outpdp.h
@@ -0,0 +1,65 @@
+#ifndef __NVKM_DISP_OUTP_DP_H__
+#define __NVKM_DISP_OUTP_DP_H__
+
+#include <subdev/bios.h>
+#include <subdev/bios/dp.h>
+
+#include "outp.h"
+
+struct nvkm_output_dp {
+	struct nvkm_output base;
+
+	struct nvbios_dpout info;
+	u8 version;
+
+	struct nouveau_eventh *irq;
+	struct nouveau_eventh *hpd;
+	struct work_struct work;
+	atomic_t pending;
+	bool present;
+	u8 dpcd[16];
+
+	struct {
+		struct work_struct work;
+		wait_queue_head_t wait;
+		atomic_t done;
+	} lt;
+};
+
+#define nvkm_output_dp_create(p,e,c,b,i,d)                                     \
+	nvkm_output_dp_create_((p), (e), (c), (b), (i), sizeof(**d), (void **)d)
+#define nvkm_output_dp_destroy(d) ({                                           \
+	struct nvkm_output_dp *_outp = (d);                                    \
+	_nvkm_output_dp_dtor(nv_object(_outp));                                \
+})
+#define nvkm_output_dp_init(d) ({                                              \
+	struct nvkm_output_dp *_outp = (d);                                    \
+	_nvkm_output_dp_init(nv_object(_outp));                                \
+})
+#define nvkm_output_dp_fini(d,s) ({                                            \
+	struct nvkm_output_dp *_outp = (d);                                    \
+	_nvkm_output_dp_fini(nv_object(_outp), (s));                           \
+})
+
+int nvkm_output_dp_create_(struct nouveau_object *, struct nouveau_object *,
+			   struct nouveau_oclass *, struct dcb_output *,
+			   int, int, void **);
+
+int  _nvkm_output_dp_ctor(struct nouveau_object *, struct nouveau_object *,
+			  struct nouveau_oclass *, void *, u32,
+			  struct nouveau_object **);
+void _nvkm_output_dp_dtor(struct nouveau_object *);
+int  _nvkm_output_dp_init(struct nouveau_object *);
+int  _nvkm_output_dp_fini(struct nouveau_object *, bool);
+
+struct nvkm_output_dp_impl {
+	struct nvkm_output_impl base;
+	int (*pattern)(struct nvkm_output_dp *, int);
+	int (*lnk_pwr)(struct nvkm_output_dp *, int nr);
+	int (*lnk_ctl)(struct nvkm_output_dp *, int nr, int bw, bool ef);
+	int (*drv_ctl)(struct nvkm_output_dp *, int ln, int vs, int pe, int pc);
+};
+
+int nvkm_output_dp_train(struct nvkm_output *, u32 rate, bool wait);
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/piornv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/piornv50.c
index 2c8ce351b52..fe0f256f11b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/piornv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/piornv50.c
@@ -33,68 +33,107 @@
 #include "nv50.h"
 
 /******************************************************************************
- * DisplayPort
+ * TMDS
  *****************************************************************************/
-static struct nouveau_i2c_port *
-nv50_pior_dp_find(struct nouveau_disp *disp, struct dcb_output *outp)
+
+static int
+nv50_pior_tmds_ctor(struct nouveau_object *parent,
+		    struct nouveau_object *engine,
+		    struct nouveau_oclass *oclass, void *info, u32 index,
+		    struct nouveau_object **pobject)
 {
-	struct nouveau_i2c *i2c = nouveau_i2c(disp);
-	return i2c->find_type(i2c, NV_I2C_TYPE_EXTAUX(outp->extdev));
+	struct nouveau_i2c *i2c = nouveau_i2c(parent);
+	struct nvkm_output *outp;
+	int ret;
+
+	ret = nvkm_output_create(parent, engine, oclass, info, index, &outp);
+	*pobject = nv_object(outp);
+	if (ret)
+		return ret;
+
+	outp->edid = i2c->find_type(i2c, NV_I2C_TYPE_EXTDDC(outp->info.extdev));
+	return 0;
 }
 
+struct nvkm_output_impl
+nv50_pior_tmds_impl = {
+	.base.handle = DCB_OUTPUT_TMDS | 0x0100,
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = nv50_pior_tmds_ctor,
+		.dtor = _nvkm_output_dtor,
+		.init = _nvkm_output_init,
+		.fini = _nvkm_output_fini,
+	},
+};
+
+/******************************************************************************
+ * DisplayPort
+ *****************************************************************************/
+
 static int
-nv50_pior_dp_pattern(struct nouveau_disp *disp, struct dcb_output *outp,
-		     int head, int pattern)
+nv50_pior_dp_pattern(struct nvkm_output_dp *outp, int pattern)
 {
-	struct nouveau_i2c_port *port;
-	int ret = -EINVAL;
-
-	port = nv50_pior_dp_find(disp, outp);
-	if (port) {
-		if (port->func->pattern)
-			ret = port->func->pattern(port, pattern);
-		else
-			ret = 0;
-	}
-
-	return ret;
+	struct nouveau_i2c_port *port = outp->base.edid;
+	if (port && port->func->pattern)
+		return port->func->pattern(port, pattern);
+	return port ? 0 : -ENODEV;
 }
 
 static int
-nv50_pior_dp_lnk_ctl(struct nouveau_disp *disp, struct dcb_output *outp,
-		     int head, int lane_nr, int link_bw, bool enh)
+nv50_pior_dp_lnk_pwr(struct nvkm_output_dp *outp, int nr)
 {
-	struct nouveau_i2c_port *port;
-	int ret = -EINVAL;
+	return 0;
+}
 
-	port = nv50_pior_dp_find(disp, outp);
+static int
+nv50_pior_dp_lnk_ctl(struct nvkm_output_dp *outp, int nr, int bw, bool ef)
+{
+	struct nouveau_i2c_port *port = outp->base.edid;
 	if (port && port->func->lnk_ctl)
-		ret = port->func->lnk_ctl(port, lane_nr, link_bw, enh);
+		return port->func->lnk_ctl(port, nr, bw, ef);
+	return port ? 0 : -ENODEV;
+}
 
-	return ret;
+static int
+nv50_pior_dp_drv_ctl(struct nvkm_output_dp *outp, int ln, int vs, int pe, int pc)
+{
+	struct nouveau_i2c_port *port = outp->base.edid;
+	if (port && port->func->drv_ctl)
+		return port->func->drv_ctl(port, ln, vs, pe);
+	return port ? 0 : -ENODEV;
 }
 
 static int
-nv50_pior_dp_drv_ctl(struct nouveau_disp *disp, struct dcb_output *outp,
-		     int head, int lane, int vsw, int pre)
+nv50_pior_dp_ctor(struct nouveau_object *parent,
+		  struct nouveau_object *engine,
+		  struct nouveau_oclass *oclass, void *info, u32 index,
+		  struct nouveau_object **pobject)
 {
-	struct nouveau_i2c_port *port;
-	int ret = -EINVAL;
-
-	port = nv50_pior_dp_find(disp, outp);
-	if (port) {
-		if (port->func->drv_ctl)
-			ret = port->func->drv_ctl(port, lane, vsw, pre);
-		else
-			ret = 0;
-	}
+	struct nouveau_i2c *i2c = nouveau_i2c(parent);
+	struct nvkm_output_dp *outp;
+	int ret;
 
-	return ret;
+	ret = nvkm_output_dp_create(parent, engine, oclass, info, index, &outp);
+	*pobject = nv_object(outp);
+	if (ret)
+		return ret;
+
+	outp->base.edid = i2c->find_type(i2c, NV_I2C_TYPE_EXTAUX(
+					 outp->base.info.extdev));
+	return 0;
 }
 
-const struct nouveau_dp_func
-nv50_pior_dp_func = {
+struct nvkm_output_dp_impl
+nv50_pior_dp_impl = {
+	.base.base.handle = DCB_OUTPUT_DP | 0x0010,
+	.base.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = nv50_pior_dp_ctor,
+		.dtor = _nvkm_output_dp_dtor,
+		.init = _nvkm_output_dp_init,
+		.fini = _nvkm_output_dp_fini,
+	},
 	.pattern = nv50_pior_dp_pattern,
+	.lnk_pwr = nv50_pior_dp_lnk_pwr,
 	.lnk_ctl = nv50_pior_dp_lnk_ctl,
 	.drv_ctl = nv50_pior_dp_drv_ctl,
 };
@@ -102,6 +141,7 @@ nv50_pior_dp_func = {
 /******************************************************************************
  * General PIOR handling
  *****************************************************************************/
+
 int
 nv50_pior_power(struct nv50_disp_priv *priv, int or, u32 data)
 {
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/priv.h b/drivers/gpu/drm/nouveau/core/engine/disp/priv.h
index cc3c7a4ca74..26e9a42569c 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/priv.h
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/priv.h
@@ -1,10 +1,42 @@
 #ifndef __NVKM_DISP_PRIV_H__
 #define __NVKM_DISP_PRIV_H__
 
+#include <subdev/bios.h>
+#include <subdev/bios/dcb.h>
+#include <subdev/bios/conn.h>
+
 #include <engine/disp.h>
 
 struct nouveau_disp_impl {
 	struct nouveau_oclass base;
+	struct nouveau_oclass **outp;
+	struct nouveau_oclass **conn;
 };
 
+#define nouveau_disp_create(p,e,c,h,i,x,d)                                     \
+	nouveau_disp_create_((p), (e), (c), (h), (i), (x),                     \
+			     sizeof(**d), (void **)d)
+#define nouveau_disp_destroy(d) ({                                             \
+	struct nouveau_disp *disp = (d);                                       \
+	_nouveau_disp_dtor(nv_object(disp));                                   \
+})
+#define nouveau_disp_init(d) ({                                                \
+	struct nouveau_disp *disp = (d);                                       \
+	_nouveau_disp_init(nv_object(disp));                                   \
+})
+#define nouveau_disp_fini(d,s) ({                                              \
+	struct nouveau_disp *disp = (d);                                       \
+	_nouveau_disp_fini(nv_object(disp), (s));                              \
+})
+
+int  nouveau_disp_create_(struct nouveau_object *, struct nouveau_object *,
+			  struct nouveau_oclass *, int heads,
+			  const char *, const char *, int, void **);
+void _nouveau_disp_dtor(struct nouveau_object *);
+int  _nouveau_disp_init(struct nouveau_object *);
+int  _nouveau_disp_fini(struct nouveau_object *, bool);
+
+extern struct nouveau_oclass *nvkm_output_oclass;
+extern struct nouveau_oclass *nvkm_connector_oclass;
+
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
index 526b7524289..7a1ebdfa9e1 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/sornv50.c
@@ -47,8 +47,12 @@ int
 nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size)
 {
 	struct nv50_disp_priv *priv = (void *)object->engine;
+	const u8  type = (mthd & NV50_DISP_SOR_MTHD_TYPE) >> 12;
 	const u8  head = (mthd & NV50_DISP_SOR_MTHD_HEAD) >> 3;
+	const u8  link = (mthd & NV50_DISP_SOR_MTHD_LINK) >> 2;
 	const u8    or = (mthd & NV50_DISP_SOR_MTHD_OR);
+	const u16 mask = (0x0100 << head) | (0x0040 << link) | (0x0001 << or);
+	struct nvkm_output *outp = NULL, *temp;
 	u32 data;
 	int ret = -EINVAL;
 
@@ -56,6 +60,13 @@ nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size)
 		return -EINVAL;
 	data = *(u32 *)args;
 
+	list_for_each_entry(temp, &priv->base.outp, head) {
+		if ((temp->info.hasht & 0xff) == type &&
+		    (temp->info.hashm & mask) == mask) {
+			outp = temp;
+			break;
+		}
+	}
 
 	switch (mthd & ~0x3f) {
 	case NV50_DISP_SOR_PWR:
@@ -71,6 +82,24 @@ nv50_sor_mthd(struct nouveau_object *object, u32 mthd, void *args, u32 size)
 		priv->sor.lvdsconf = data & NV50_DISP_SOR_LVDS_SCRIPT_ID;
 		ret = 0;
 		break;
+	case NV94_DISP_SOR_DP_PWR:
+		if (outp) {
+			struct nvkm_output_dp *outpdp = (void *)outp;
+			switch (data) {
+			case NV94_DISP_SOR_DP_PWR_STATE_OFF:
+				nouveau_event_put(outpdp->irq);
+				((struct nvkm_output_dp_impl *)nv_oclass(outp))
+					->lnk_pwr(outpdp, 0);
+				atomic_set(&outpdp->lt.done, 0);
+				break;
+			case NV94_DISP_SOR_DP_PWR_STATE_ON:
+				nvkm_output_dp_train(&outpdp->base, 0, true);
+				break;
+			default:
+				return -EINVAL;
+			}
+		}
+		break;
 	default:
 		BUG_ON(1);
 	}
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/sornv94.c b/drivers/gpu/drm/nouveau/core/engine/disp/sornv94.c
index eea3ef59693..05487cda84a 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/sornv94.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/sornv94.c
@@ -29,19 +29,21 @@
 #include <subdev/bios/dcb.h>
 #include <subdev/bios/dp.h>
 #include <subdev/bios/init.h>
+#include <subdev/timer.h>
 
 #include "nv50.h"
+#include "outpdp.h"
 
 static inline u32
-nv94_sor_soff(struct dcb_output *outp)
+nv94_sor_soff(struct nvkm_output_dp *outp)
 {
-	return (ffs(outp->or) - 1) * 0x800;
+	return (ffs(outp->base.info.or) - 1) * 0x800;
 }
 
 static inline u32
-nv94_sor_loff(struct dcb_output *outp)
+nv94_sor_loff(struct nvkm_output_dp *outp)
 {
-	return nv94_sor_soff(outp) + !(outp->sorconf.link & 1) * 0x80;
+	return nv94_sor_soff(outp) + !(outp->base.info.sorconf.link & 1) * 0x80;
 }
 
 static inline u32
@@ -55,77 +57,96 @@ nv94_sor_dp_lane_map(struct nv50_disp_priv *priv, u8 lane)
 }
 
 static int
-nv94_sor_dp_pattern(struct nouveau_disp *disp, struct dcb_output *outp,
-		    int head, int pattern)
+nv94_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
 {
-	struct nv50_disp_priv *priv = (void *)disp;
+	struct nv50_disp_priv *priv = (void *)nouveau_disp(outp);
 	const u32 loff = nv94_sor_loff(outp);
 	nv_mask(priv, 0x61c10c + loff, 0x0f000000, pattern << 24);
 	return 0;
 }
 
+int
+nv94_sor_dp_lnk_pwr(struct nvkm_output_dp *outp, int nr)
+{
+	struct nv50_disp_priv *priv = (void *)nouveau_disp(outp);
+	const u32 soff = nv94_sor_soff(outp);
+	const u32 loff = nv94_sor_loff(outp);
+	u32 mask = 0, i;
+
+	for (i = 0; i < nr; i++)
+		mask |= 1 << (nv94_sor_dp_lane_map(priv, i) >> 3);
+
+	nv_mask(priv, 0x61c130 + loff, 0x0000000f, mask);
+	nv_mask(priv, 0x61c034 + soff, 0x80000000, 0x80000000);
+	nv_wait(priv, 0x61c034 + soff, 0x80000000, 0x00000000);
+	return 0;
+}
+
 static int
-nv94_sor_dp_lnk_ctl(struct nouveau_disp *disp, struct dcb_output *outp,
-		    int head, int link_nr, int link_bw, bool enh_frame)
+nv94_sor_dp_lnk_ctl(struct nvkm_output_dp *outp, int nr, int bw, bool ef)
 {
-	struct nv50_disp_priv *priv = (void *)disp;
+	struct nv50_disp_priv *priv = (void *)nouveau_disp(outp);
 	const u32 soff = nv94_sor_soff(outp);
 	const u32 loff = nv94_sor_loff(outp);
 	u32 dpctrl = 0x00000000;
 	u32 clksor = 0x00000000;
-	u32 lane = 0;
-	int i;
 
-	dpctrl |= ((1 << link_nr) - 1) << 16;
-	if (enh_frame)
+	dpctrl |= ((1 << nr) - 1) << 16;
+	if (ef)
 		dpctrl |= 0x00004000;
-	if (link_bw > 0x06)
+	if (bw > 0x06)
 		clksor |= 0x00040000;
 
-	for (i = 0; i < link_nr; i++)
-		lane |= 1 << (nv94_sor_dp_lane_map(priv, i) >> 3);
-
 	nv_mask(priv, 0x614300 + soff, 0x000c0000, clksor);
 	nv_mask(priv, 0x61c10c + loff, 0x001f4000, dpctrl);
-	nv_mask(priv, 0x61c130 + loff, 0x0000000f, lane);
 	return 0;
 }
 
 static int
-nv94_sor_dp_drv_ctl(struct nouveau_disp *disp, struct dcb_output *outp,
-		    int head, int lane, int swing, int preem)
+nv94_sor_dp_drv_ctl(struct nvkm_output_dp *outp, int ln, int vs, int pe, int pc)
 {
-	struct nouveau_bios *bios = nouveau_bios(disp);
-	struct nv50_disp_priv *priv = (void *)disp;
-	const u32 shift = nv94_sor_dp_lane_map(priv, lane);
+	struct nv50_disp_priv *priv = (void *)nouveau_disp(outp);
+	struct nouveau_bios *bios = nouveau_bios(priv);
+	const u32 shift = nv94_sor_dp_lane_map(priv, ln);
 	const u32 loff = nv94_sor_loff(outp);
 	u32 addr, data[3];
 	u8  ver, hdr, cnt, len;
 	struct nvbios_dpout info;
 	struct nvbios_dpcfg ocfg;
 
-	addr = nvbios_dpout_match(bios, outp->hasht, outp->hashm,
+	addr = nvbios_dpout_match(bios, outp->base.info.hasht,
+					outp->base.info.hashm,
 				 &ver, &hdr, &cnt, &len, &info);
 	if (!addr)
 		return -ENODEV;
 
-	addr = nvbios_dpcfg_match(bios, addr, 0, swing, preem,
+	addr = nvbios_dpcfg_match(bios, addr, 0, vs, pe,
 				 &ver, &hdr, &cnt, &len, &ocfg);
 	if (!addr)
 		return -EINVAL;
 
 	data[0] = nv_rd32(priv, 0x61c118 + loff) & ~(0x000000ff << shift);
 	data[1] = nv_rd32(priv, 0x61c120 + loff) & ~(0x000000ff << shift);
-	data[2] = nv_rd32(priv, 0x61c130 + loff) & ~(0x0000ff00);
-	nv_wr32(priv, 0x61c118 + loff, data[0] | (ocfg.drv << shift));
-	nv_wr32(priv, 0x61c120 + loff, data[1] | (ocfg.pre << shift));
-	nv_wr32(priv, 0x61c130 + loff, data[2] | (ocfg.unk << 8));
+	data[2] = nv_rd32(priv, 0x61c130 + loff);
+	if ((data[2] & 0x0000ff00) < (ocfg.tx_pu << 8) || ln == 0)
+		data[2] = (data[2] & ~0x0000ff00) | (ocfg.tx_pu << 8);
+	nv_wr32(priv, 0x61c118 + loff, data[0] | (ocfg.dc << shift));
+	nv_wr32(priv, 0x61c120 + loff, data[1] | (ocfg.pe << shift));
+	nv_wr32(priv, 0x61c130 + loff, data[2] | (ocfg.tx_pu << 8));
 	return 0;
 }
 
-const struct nouveau_dp_func
-nv94_sor_dp_func = {
+struct nvkm_output_dp_impl
+nv94_sor_dp_impl = {
+	.base.base.handle = DCB_OUTPUT_DP,
+	.base.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nvkm_output_dp_ctor,
+		.dtor = _nvkm_output_dp_dtor,
+		.init = _nvkm_output_dp_init,
+		.fini = _nvkm_output_dp_fini,
+	},
 	.pattern = nv94_sor_dp_pattern,
+	.lnk_pwr = nv94_sor_dp_lnk_pwr,
 	.lnk_ctl = nv94_sor_dp_lnk_ctl,
 	.drv_ctl = nv94_sor_dp_drv_ctl,
 };
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/sornvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/sornvd0.c
index d2df572f16a..97f0e9cd3d4 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/sornvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/sornvd0.c
@@ -29,19 +29,20 @@
 #include <subdev/bios/dcb.h>
 #include <subdev/bios/dp.h>
 #include <subdev/bios/init.h>
+#include <subdev/timer.h>
 
 #include "nv50.h"
 
 static inline u32
-nvd0_sor_soff(struct dcb_output *outp)
+nvd0_sor_soff(struct nvkm_output_dp *outp)
 {
-	return (ffs(outp->or) - 1) * 0x800;
+	return (ffs(outp->base.info.or) - 1) * 0x800;
 }
 
 static inline u32
-nvd0_sor_loff(struct dcb_output *outp)
+nvd0_sor_loff(struct nvkm_output_dp *outp)
 {
-	return nvd0_sor_soff(outp) + !(outp->sorconf.link & 1) * 0x80;
+	return nvd0_sor_soff(outp) + !(outp->base.info.sorconf.link & 1) * 0x80;
 }
 
 static inline u32
@@ -52,77 +53,80 @@ nvd0_sor_dp_lane_map(struct nv50_disp_priv *priv, u8 lane)
 }
 
 static int
-nvd0_sor_dp_pattern(struct nouveau_disp *disp, struct dcb_output *outp,
-		    int head, int pattern)
+nvd0_sor_dp_pattern(struct nvkm_output_dp *outp, int pattern)
 {
-	struct nv50_disp_priv *priv = (void *)disp;
+	struct nv50_disp_priv *priv = (void *)nouveau_disp(outp);
 	const u32 loff = nvd0_sor_loff(outp);
 	nv_mask(priv, 0x61c110 + loff, 0x0f0f0f0f, 0x01010101 * pattern);
 	return 0;
 }
 
 static int
-nvd0_sor_dp_lnk_ctl(struct nouveau_disp *disp, struct dcb_output *outp,
-		    int head, int link_nr, int link_bw, bool enh_frame)
+nvd0_sor_dp_lnk_ctl(struct nvkm_output_dp *outp, int nr, int bw, bool ef)
 {
-	struct nv50_disp_priv *priv = (void *)disp;
+	struct nv50_disp_priv *priv = (void *)nouveau_disp(outp);
 	const u32 soff = nvd0_sor_soff(outp);
 	const u32 loff = nvd0_sor_loff(outp);
 	u32 dpctrl = 0x00000000;
 	u32 clksor = 0x00000000;
-	u32 lane = 0;
-	int i;
 
-	clksor |= link_bw << 18;
-	dpctrl |= ((1 << link_nr) - 1) << 16;
-	if (enh_frame)
+	clksor |= bw << 18;
+	dpctrl |= ((1 << nr) - 1) << 16;
+	if (ef)
 		dpctrl |= 0x00004000;
 
-	for (i = 0; i < link_nr; i++)
-		lane |= 1 << (nvd0_sor_dp_lane_map(priv, i) >> 3);
-
 	nv_mask(priv, 0x612300 + soff, 0x007c0000, clksor);
 	nv_mask(priv, 0x61c10c + loff, 0x001f4000, dpctrl);
-	nv_mask(priv, 0x61c130 + loff, 0x0000000f, lane);
 	return 0;
 }
 
 static int
-nvd0_sor_dp_drv_ctl(struct nouveau_disp *disp, struct dcb_output *outp,
-		    int head, int lane, int swing, int preem)
+nvd0_sor_dp_drv_ctl(struct nvkm_output_dp *outp, int ln, int vs, int pe, int pc)
 {
-	struct nouveau_bios *bios = nouveau_bios(disp);
-	struct nv50_disp_priv *priv = (void *)disp;
-	const u32 shift = nvd0_sor_dp_lane_map(priv, lane);
+	struct nv50_disp_priv *priv = (void *)nouveau_disp(outp);
+	struct nouveau_bios *bios = nouveau_bios(priv);
+	const u32 shift = nvd0_sor_dp_lane_map(priv, ln);
 	const u32 loff = nvd0_sor_loff(outp);
-	u32 addr, data[3];
+	u32 addr, data[4];
 	u8  ver, hdr, cnt, len;
 	struct nvbios_dpout info;
 	struct nvbios_dpcfg ocfg;
 
-	addr = nvbios_dpout_match(bios, outp->hasht, outp->hashm,
+	addr = nvbios_dpout_match(bios, outp->base.info.hasht,
+					outp->base.info.hashm,
 				 &ver, &hdr, &cnt, &len, &info);
 	if (!addr)
 		return -ENODEV;
 
-	addr = nvbios_dpcfg_match(bios, addr, 0, swing, preem,
+	addr = nvbios_dpcfg_match(bios, addr, pc, vs, pe,
 				 &ver, &hdr, &cnt, &len, &ocfg);
 	if (!addr)
 		return -EINVAL;
 
 	data[0] = nv_rd32(priv, 0x61c118 + loff) & ~(0x000000ff << shift);
 	data[1] = nv_rd32(priv, 0x61c120 + loff) & ~(0x000000ff << shift);
-	data[2] = nv_rd32(priv, 0x61c130 + loff) & ~(0x0000ff00);
-	nv_wr32(priv, 0x61c118 + loff, data[0] | (ocfg.drv << shift));
-	nv_wr32(priv, 0x61c120 + loff, data[1] | (ocfg.pre << shift));
-	nv_wr32(priv, 0x61c130 + loff, data[2] | (ocfg.unk << 8));
-	nv_mask(priv, 0x61c13c + loff, 0x00000000, 0x00000000);
+	data[2] = nv_rd32(priv, 0x61c130 + loff);
+	if ((data[2] & 0x0000ff00) < (ocfg.tx_pu << 8) || ln == 0)
+		data[2] = (data[2] & ~0x0000ff00) | (ocfg.tx_pu << 8);
+	nv_wr32(priv, 0x61c118 + loff, data[0] | (ocfg.dc << shift));
+	nv_wr32(priv, 0x61c120 + loff, data[1] | (ocfg.pe << shift));
+	nv_wr32(priv, 0x61c130 + loff, data[2] | (ocfg.tx_pu << 8));
+	data[3] = nv_rd32(priv, 0x61c13c + loff) & ~(0x000000ff << shift);
+	nv_wr32(priv, 0x61c13c + loff, data[3] | (ocfg.pc << shift));
 	return 0;
 }
 
-const struct nouveau_dp_func
-nvd0_sor_dp_func = {
+struct nvkm_output_dp_impl
+nvd0_sor_dp_impl = {
+	.base.base.handle = DCB_OUTPUT_DP,
+	.base.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nvkm_output_dp_ctor,
+		.dtor = _nvkm_output_dp_dtor,
+		.init = _nvkm_output_dp_init,
+		.fini = _nvkm_output_dp_fini,
+	},
 	.pattern = nvd0_sor_dp_pattern,
+	.lnk_pwr = nv94_sor_dp_lnk_pwr,
 	.lnk_ctl = nvd0_sor_dp_lnk_ctl,
 	.drv_ctl = nvd0_sor_dp_drv_ctl,
 };
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/base.c b/drivers/gpu/drm/nouveau/core/engine/fifo/base.c
index 6f9041ced9a..56ed3d73bf8 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/base.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/base.c
@@ -91,7 +91,7 @@ nouveau_fifo_channel_create_(struct nouveau_object *parent,
 	if (!chan->user)
 		return -EFAULT;
 
-	nouveau_event_trigger(priv->cevent, 0);
+	nouveau_event_trigger(priv->cevent, 1, 0);
 
 	chan->size = size;
 	return 0;
@@ -194,11 +194,11 @@ nouveau_fifo_create_(struct nouveau_object *parent,
 	if (!priv->channel)
 		return -ENOMEM;
 
-	ret = nouveau_event_create(1, &priv->cevent);
+	ret = nouveau_event_create(1, 1, &priv->cevent);
 	if (ret)
 		return ret;
 
-	ret = nouveau_event_create(1, &priv->uevent);
+	ret = nouveau_event_create(1, 1, &priv->uevent);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/gk20a.c b/drivers/gpu/drm/nouveau/core/engine/fifo/gk20a.c
new file mode 100644
index 00000000000..327456eae96
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/gk20a.c
@@ -0,0 +1,35 @@
+/*
+ * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#include "nve0.h"
+
+struct nouveau_oclass *
+gk20a_fifo_oclass = &(struct nve0_fifo_impl) {
+	.base.handle = NV_ENGINE(FIFO, 0xea),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = nve0_fifo_ctor,
+		.dtor = nve0_fifo_dtor,
+		.init = nve0_fifo_init,
+		.fini = nve0_fifo_fini,
+	},
+	.channels = 128,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nv04.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nv04.c
index 54f26cc801c..c61b16a6388 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nv04.c
@@ -539,7 +539,7 @@ nv04_fifo_intr(struct nouveau_subdev *subdev)
 			}
 
 			if (status & 0x40000000) {
-				nouveau_event_trigger(priv->base.uevent, 0);
+				nouveau_event_trigger(priv->base.uevent, 1, 0);
 				nv_wr32(priv, 0x002100, 0x40000000);
 				status &= ~0x40000000;
 			}
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nv84.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nv84.c
index fe0f41e65d9..6e5ac16e546 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nv84.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nv84.c
@@ -389,14 +389,14 @@ nv84_fifo_cclass = {
  ******************************************************************************/
 
 static void
-nv84_fifo_uevent_enable(struct nouveau_event *event, int index)
+nv84_fifo_uevent_enable(struct nouveau_event *event, int type, int index)
 {
 	struct nv84_fifo_priv *priv = event->priv;
 	nv_mask(priv, 0x002140, 0x40000000, 0x40000000);
 }
 
 static void
-nv84_fifo_uevent_disable(struct nouveau_event *event, int index)
+nv84_fifo_uevent_disable(struct nouveau_event *event, int type, int index)
 {
 	struct nv84_fifo_priv *priv = event->priv;
 	nv_mask(priv, 0x002140, 0x40000000, 0x00000000);
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c
index fa1e719872b..ae4a4dc5642 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nvc0.c
@@ -730,7 +730,7 @@ nvc0_fifo_intr_engine_unit(struct nvc0_fifo_priv *priv, int engn)
 	for (unkn = 0; unkn < 8; unkn++) {
 		u32 ints = (intr >> (unkn * 0x04)) & inte;
 		if (ints & 0x1) {
-			nouveau_event_trigger(priv->base.uevent, 0);
+			nouveau_event_trigger(priv->base.uevent, 1, 0);
 			ints &= ~1;
 		}
 		if (ints) {
@@ -827,14 +827,14 @@ nvc0_fifo_intr(struct nouveau_subdev *subdev)
 }
 
 static void
-nvc0_fifo_uevent_enable(struct nouveau_event *event, int index)
+nvc0_fifo_uevent_enable(struct nouveau_event *event, int type, int index)
 {
 	struct nvc0_fifo_priv *priv = event->priv;
 	nv_mask(priv, 0x002140, 0x80000000, 0x80000000);
 }
 
 static void
-nvc0_fifo_uevent_disable(struct nouveau_event *event, int index)
+nvc0_fifo_uevent_disable(struct nouveau_event *event, int type, int index)
 {
 	struct nvc0_fifo_priv *priv = event->priv;
 	nv_mask(priv, 0x002140, 0x80000000, 0x00000000);
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
index a9a1a9c9f9f..298063edb92 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c
@@ -859,7 +859,7 @@ nve0_fifo_intr_runlist(struct nve0_fifo_priv *priv)
 static void
 nve0_fifo_intr_engine(struct nve0_fifo_priv *priv)
 {
-	nouveau_event_trigger(priv->base.uevent, 0);
+	nouveau_event_trigger(priv->base.uevent, 1, 0);
 }
 
 static void
@@ -952,14 +952,14 @@ nve0_fifo_intr(struct nouveau_subdev *subdev)
 }
 
 static void
-nve0_fifo_uevent_enable(struct nouveau_event *event, int index)
+nve0_fifo_uevent_enable(struct nouveau_event *event, int type, int index)
 {
 	struct nve0_fifo_priv *priv = event->priv;
 	nv_mask(priv, 0x002140, 0x80000000, 0x80000000);
 }
 
 static void
-nve0_fifo_uevent_disable(struct nouveau_event *event, int index)
+nve0_fifo_uevent_disable(struct nouveau_event *event, int type, int index)
 {
 	struct nve0_fifo_priv *priv = event->priv;
 	nv_mask(priv, 0x002140, 0x80000000, 0x00000000);
diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.h b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.h
index 014344ebee6..e96b32bb1bb 100644
--- a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.h
+++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.h
@@ -8,6 +8,7 @@ int  nve0_fifo_ctor(struct nouveau_object *, struct nouveau_object *,
 		    struct nouveau_object **);
 void nve0_fifo_dtor(struct nouveau_object *);
 int  nve0_fifo_init(struct nouveau_object *);
+int  nve0_fifo_fini(struct nouveau_object *, bool);
 
 struct nve0_fifo_impl {
 	struct nouveau_oclass base;
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/ctxgk20a.c b/drivers/gpu/drm/nouveau/core/engine/graph/ctxgk20a.c
new file mode 100644
index 00000000000..224ee0287ab
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/ctxgk20a.c
@@ -0,0 +1,53 @@
+/*
+ * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#include "ctxnvc0.h"
+
+static const struct nvc0_graph_pack
+gk20a_grctx_pack_mthd[] = {
+	{ nve4_grctx_init_a097_0, 0xa297 },
+	{ nvc0_grctx_init_902d_0, 0x902d },
+	{}
+};
+
+struct nouveau_oclass *
+gk20a_grctx_oclass = &(struct nvc0_grctx_oclass) {
+	.base.handle = NV_ENGCTX(GR, 0xea),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = nvc0_graph_context_ctor,
+		.dtor = nvc0_graph_context_dtor,
+		.init = _nouveau_graph_context_init,
+		.fini = _nouveau_graph_context_fini,
+		.rd32 = _nouveau_graph_context_rd32,
+		.wr32 = _nouveau_graph_context_wr32,
+	},
+	.main  = nve4_grctx_generate_main,
+	.mods  = nve4_grctx_generate_mods,
+	.unkn  = nve4_grctx_generate_unkn,
+	.hub   = nve4_grctx_pack_hub,
+	.gpc   = nve4_grctx_pack_gpc,
+	.zcull = nvc0_grctx_pack_zcull,
+	.tpc   = nve4_grctx_pack_tpc,
+	.ppc   = nve4_grctx_pack_ppc,
+	.icmd  = nve4_grctx_pack_icmd,
+	.mthd  = gk20a_grctx_pack_mthd,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c
index 48351b4d6d6..8de4a429154 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnv108.c
@@ -545,10 +545,12 @@ nv108_grctx_generate_mods(struct nvc0_graph_priv *priv, struct nvc0_grctx *info)
 	mmio_list(0x408010, 0x80000000,  0, 0);
 	mmio_list(0x419004, 0x00000000,  8, 1);
 	mmio_list(0x419008, 0x00000000,  0, 0);
+	mmio_list(0x4064cc, 0x80000000,  0, 0);
 	mmio_list(0x408004, 0x00000000,  8, 0);
 	mmio_list(0x408008, 0x80000030,  0, 0);
 	mmio_list(0x418808, 0x00000000,  8, 0);
 	mmio_list(0x41880c, 0x80000030,  0, 0);
+	mmio_list(0x4064c8, 0x00c20200,  0, 0);
 	mmio_list(0x418810, 0x80000000, 12, 2);
 	mmio_list(0x419848, 0x10000000, 12, 2);
 
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnvc0.h b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnvc0.h
index 9c815d1f99e..8da8b627b9d 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnvc0.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnvc0.h
@@ -69,7 +69,9 @@ extern struct nouveau_oclass *nvd7_grctx_oclass;
 extern struct nouveau_oclass *nvd9_grctx_oclass;
 
 extern struct nouveau_oclass *nve4_grctx_oclass;
+extern struct nouveau_oclass *gk20a_grctx_oclass;
 void nve4_grctx_generate_main(struct nvc0_graph_priv *, struct nvc0_grctx *);
+void nve4_grctx_generate_mods(struct nvc0_graph_priv *, struct nvc0_grctx *);
 void nve4_grctx_generate_unkn(struct nvc0_graph_priv *);
 void nve4_grctx_generate_r418bb8(struct nvc0_graph_priv *);
 
@@ -151,6 +153,13 @@ extern const struct nvc0_graph_init nve4_grctx_init_gpm_0[];
 
 extern const struct nvc0_graph_init nve4_grctx_init_pes_0[];
 
+extern const struct nvc0_graph_pack nve4_grctx_pack_hub[];
+extern const struct nvc0_graph_pack nve4_grctx_pack_gpc[];
+extern const struct nvc0_graph_pack nve4_grctx_pack_tpc[];
+extern const struct nvc0_graph_pack nve4_grctx_pack_ppc[];
+extern const struct nvc0_graph_pack nve4_grctx_pack_icmd[];
+extern const struct nvc0_graph_init nve4_grctx_init_a097_0[];
+
 extern const struct nvc0_graph_pack nvf0_grctx_pack_mthd[];
 
 extern const struct nvc0_graph_init nvf0_grctx_init_pri_0[];
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnve4.c b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnve4.c
index 49a14b116a5..c5b24923858 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnve4.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnve4.c
@@ -272,13 +272,13 @@ nve4_grctx_init_icmd_0[] = {
 	{}
 };
 
-static const struct nvc0_graph_pack
+const struct nvc0_graph_pack
 nve4_grctx_pack_icmd[] = {
 	{ nve4_grctx_init_icmd_0 },
 	{}
 };
 
-static const struct nvc0_graph_init
+const struct nvc0_graph_init
 nve4_grctx_init_a097_0[] = {
 	{ 0x000800,   8, 0x40, 0x00000000 },
 	{ 0x000804,   8, 0x40, 0x00000000 },
@@ -697,7 +697,7 @@ nve4_grctx_init_be_0[] = {
 	{}
 };
 
-static const struct nvc0_graph_pack
+const struct nvc0_graph_pack
 nve4_grctx_pack_hub[] = {
 	{ nvc0_grctx_init_main_0 },
 	{ nve4_grctx_init_fe_0 },
@@ -737,7 +737,7 @@ nve4_grctx_init_gpm_0[] = {
 	{}
 };
 
-static const struct nvc0_graph_pack
+const struct nvc0_graph_pack
 nve4_grctx_pack_gpc[] = {
 	{ nvc0_grctx_init_gpc_unk_0 },
 	{ nvd9_grctx_init_prop_0 },
@@ -802,7 +802,7 @@ nve4_grctx_init_sm_0[] = {
 	{}
 };
 
-static const struct nvc0_graph_pack
+const struct nvc0_graph_pack
 nve4_grctx_pack_tpc[] = {
 	{ nvd7_grctx_init_pe_0 },
 	{ nve4_grctx_init_tex_0 },
@@ -826,7 +826,7 @@ nve4_grctx_init_cbm_0[] = {
 	{}
 };
 
-static const struct nvc0_graph_pack
+const struct nvc0_graph_pack
 nve4_grctx_pack_ppc[] = {
 	{ nve4_grctx_init_pes_0 },
 	{ nve4_grctx_init_cbm_0 },
@@ -838,7 +838,7 @@ nve4_grctx_pack_ppc[] = {
  * PGRAPH context implementation
  ******************************************************************************/
 
-static void
+void
 nve4_grctx_generate_mods(struct nvc0_graph_priv *priv, struct nvc0_grctx *info)
 {
 	u32 magic[GPC_MAX][2];
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnvf0.c b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnvf0.c
index 0fab95e49f5..dec03f04114 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/ctxnvf0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/ctxnvf0.c
@@ -842,7 +842,7 @@ nvf0_grctx_generate_mods(struct nvc0_graph_priv *priv, struct nvc0_grctx *info)
 		u16 magic3 = 0x0648;
 		magic[gpc][0]  = 0x10000000 | (magic0 << 16) | offset;
 		magic[gpc][1]  = 0x00000000 | (magic1 << 16);
-		offset += 0x0324 * (priv->tpc_nr[gpc] - 1);;
+		offset += 0x0324 * (priv->tpc_nr[gpc] - 1);
 		magic[gpc][2]  = 0x10000000 | (magic2 << 16) | offset;
 		magic[gpc][3]  = 0x00000000 | (magic3 << 16);
 		offset += 0x0324;
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/gpc.fuc b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/gpc.fuc
index 2f7345f7fe0..7445f12b1d9 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/gpc.fuc
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/gpc.fuc
@@ -54,7 +54,7 @@ mmio_list_base:
 #ifdef INCLUDE_CODE
 // reports an exception to the host
 //
-// In: $r15 error code (see nvc0.fuc)
+// In: $r15 error code (see os.h)
 //
 error:
 	push $r14
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hub.fuc b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hub.fuc
index c8ddb8d71b9..b4ad18bf5a2 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hub.fuc
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hub.fuc
@@ -49,7 +49,7 @@ hub_mmio_list_next:
 #ifdef INCLUDE_CODE
 // reports an exception to the host
 //
-// In: $r15 error code (see nvc0.fuc)
+// In: $r15 error code (see os.h)
 //
 error:
 	nv_iowr(NV_PGRAPH_FECS_CC_SCRATCH_VAL(5), 0, $r15)
@@ -343,13 +343,25 @@ ih:
 	ih_no_ctxsw:
 	and $r11 $r10 NV_PGRAPH_FECS_INTR_FWMTHD
 	bra e #ih_no_fwmthd
-		// none we handle, ack, and fall-through to unhandled
+		// none we handle; report to host and ack
+		nv_rd32($r15, NV_PGRAPH_TRAPPED_DATA_LO)
+		nv_iowr(NV_PGRAPH_FECS_CC_SCRATCH_VAL(4), 0, $r15)
+		nv_rd32($r15, NV_PGRAPH_TRAPPED_ADDR)
+		nv_iowr(NV_PGRAPH_FECS_CC_SCRATCH_VAL(3), 0, $r15)
+		extr $r14 $r15 16:18
+		shl b32 $r14 $r14 2
+		imm32($r15, NV_PGRAPH_FE_OBJECT_TABLE(0))
+		add b32 $r14 $r15
+		call(nv_rd32)
+		nv_iowr(NV_PGRAPH_FECS_CC_SCRATCH_VAL(2), 0, $r15)
+		mov $r15 E_BAD_FWMTHD
+		call(error)
 		mov $r11 0x100
 		nv_wr32(0x400144, $r11)
 
 	// anything we didn't handle, bring it to the host's attention
 	ih_no_fwmthd:
-	mov $r11 0x104 // FIFO | CHSW
+	mov $r11 0x504 // FIFO | CHSW | FWMTHD
 	not b32 $r11
 	and $r11 $r10 $r11
 	bra e #ih_no_other
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubgm107.fuc5.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubgm107.fuc5.h
index 214dd16ec56..5f953c5c20b 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubgm107.fuc5.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubgm107.fuc5.h
@@ -478,10 +478,10 @@ uint32_t gm107_grhub_code[] = {
 	0x01040080,
 	0xbd0001f6,
 	0x01004104,
-	0x627e020f,
-	0x717e0006,
+	0xa87e020f,
+	0xb77e0006,
 	0x100f0006,
-	0x0006b37e,
+	0x0006f97e,
 	0x98000e98,
 	0x207e010f,
 	0x14950001,
@@ -523,8 +523,8 @@ uint32_t gm107_grhub_code[] = {
 	0x800040b7,
 	0xf40132b6,
 	0x000fb41b,
-	0x0006b37e,
-	0x627e000f,
+	0x0006f97e,
+	0xa87e000f,
 	0x00800006,
 	0x01f60201,
 	0xbd04bd00,
@@ -554,7 +554,7 @@ uint32_t gm107_grhub_code[] = {
 	0x0009f602,
 	0x32f404bd,
 	0x0231f401,
-	0x0008367e,
+	0x00087c7e,
 	0x99f094bd,
 	0x17008007,
 	0x0009f602,
@@ -563,7 +563,7 @@ uint32_t gm107_grhub_code[] = {
 	0x37008006,
 	0x0009f602,
 	0x31f404bd,
-	0x08367e01,
+	0x087c7e01,
 	0xf094bd00,
 	0x00800699,
 	0x09f60217,
@@ -572,7 +572,7 @@ uint32_t gm107_grhub_code[] = {
 	0x20f92f0e,
 	0x32f412b2,
 	0x0232f401,
-	0x0008367e,
+	0x00087c7e,
 	0x008020fc,
 	0x02f602c0,
 	0xf404bd00,
@@ -580,7 +580,7 @@ uint32_t gm107_grhub_code[] = {
 	0x23c8130e,
 	0x0d0bf41f,
 	0xf40131f4,
-	0x367e0232,
+	0x7c7e0232,
 /* 0x054e: chsw_done */
 	0x01020008,
 	0x02c30080,
@@ -593,7 +593,7 @@ uint32_t gm107_grhub_code[] = {
 	0xb0ff2a0e,
 	0x1bf401e4,
 	0x7ef2b20c,
-	0xf40007d6,
+	0xf400081c,
 /* 0x057a: main_not_ctx_chan */
 	0xe4b0400e,
 	0x2c1bf402,
@@ -602,7 +602,7 @@ uint32_t gm107_grhub_code[] = {
 	0x0009f602,
 	0x32f404bd,
 	0x0232f401,
-	0x0008367e,
+	0x00087c7e,
 	0x99f094bd,
 	0x17008007,
 	0x0009f602,
@@ -642,238 +642,238 @@ uint32_t gm107_grhub_code[] = {
 /* 0x061a: ih_no_ctxsw */
 	0xabe40000,
 	0x0bf40400,
-	0x01004b10,
-	0x448ebfb2,
-	0x8f7e4001,
-/* 0x062e: ih_no_fwmthd */
-	0x044b0000,
-	0xffb0bd01,
-	0x0bf4b4ab,
-	0x0700800c,
-	0x000bf603,
-/* 0x0642: ih_no_other */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0x0032f480,
-/* 0x0662: ctx_4170s */
-	0xf5f001f8,
-	0x8effb210,
-	0x7e404170,
-	0xf800008f,
-/* 0x0671: ctx_4170w */
-	0x41708e00,
+	0x07088e56,
 	0x00657e40,
-	0xf0ffb200,
-	0x1bf410f4,
-/* 0x0683: ctx_redswitch */
-	0x4e00f8f3,
-	0xe5f00200,
-	0x20e5f040,
-	0x8010e5f0,
-	0xf6018500,
-	0x04bd000e,
-/* 0x069a: ctx_redswitch_delay */
-	0xf2b6080f,
-	0xfd1bf401,
-	0x0400e5f1,
-	0x0100e5f1,
-	0x01850080,
-	0xbd000ef6,
-/* 0x06b3: ctx_86c */
-	0x8000f804,
-	0xf6022300,
+	0x80ffb200,
+	0xf6020400,
 	0x04bd000f,
-	0x148effb2,
-	0x8f7e408a,
-	0xffb20000,
-	0x41a88c8e,
+	0x4007048e,
+	0x0000657e,
+	0x0080ffb2,
+	0x0ff60203,
+	0xc704bd00,
+	0xee9450fe,
+	0x07008f02,
+	0x00efbb40,
+	0x0000657e,
+	0x02020080,
+	0xbd000ff6,
+	0x7e030f04,
+	0x4b0002f8,
+	0xbfb20100,
+	0x4001448e,
 	0x00008f7e,
-/* 0x06d2: ctx_mem */
-	0x008000f8,
-	0x0ff60284,
-/* 0x06db: ctx_mem_wait */
-	0x8f04bd00,
-	0xcf028400,
-	0xfffd00ff,
-	0xf61bf405,
-/* 0x06ea: ctx_load */
-	0x94bd00f8,
-	0x800599f0,
-	0xf6023700,
-	0x04bd0009,
-	0xb87e0c0a,
-	0xf4bd0000,
-	0x02890080,
+/* 0x0674: ih_no_fwmthd */
+	0xbd05044b,
+	0xb4abffb0,
+	0x800c0bf4,
+	0xf6030700,
+	0x04bd000b,
+/* 0x0688: ih_no_other */
+	0xf6010040,
+	0x04bd000a,
+	0xe0fcf0fc,
+	0xb0fcd0fc,
+	0x90fca0fc,
+	0x88fe80fc,
+	0xf480fc00,
+	0x01f80032,
+/* 0x06a8: ctx_4170s */
+	0xb210f5f0,
+	0x41708eff,
+	0x008f7e40,
+/* 0x06b7: ctx_4170w */
+	0x8e00f800,
+	0x7e404170,
+	0xb2000065,
+	0x10f4f0ff,
+	0xf8f31bf4,
+/* 0x06c9: ctx_redswitch */
+	0x02004e00,
+	0xf040e5f0,
+	0xe5f020e5,
+	0x85008010,
+	0x000ef601,
+	0x080f04bd,
+/* 0x06e0: ctx_redswitch_delay */
+	0xf401f2b6,
+	0xe5f1fd1b,
+	0xe5f10400,
+	0x00800100,
+	0x0ef60185,
+	0xf804bd00,
+/* 0x06f9: ctx_86c */
+	0x23008000,
+	0x000ff602,
+	0xffb204bd,
+	0x408a148e,
+	0x00008f7e,
+	0x8c8effb2,
+	0x8f7e41a8,
+	0x00f80000,
+/* 0x0718: ctx_mem */
+	0x02840080,
 	0xbd000ff6,
-	0xc1008004,
-	0x0002f602,
-	0x008004bd,
-	0x02f60283,
-	0x0f04bd00,
-	0x06d27e07,
-	0xc0008000,
-	0x0002f602,
-	0x0bfe04bd,
-	0x1f2af000,
-	0xb60424b6,
-	0x94bd0220,
-	0x800899f0,
-	0xf6023700,
-	0x04bd0009,
-	0x02810080,
-	0xbd0002f6,
-	0x0000d204,
-	0x25f08000,
-	0x88008002,
-	0x0002f602,
-	0x100104bd,
-	0xf0020042,
-	0x12fa0223,
-	0xbd03f805,
-	0x0899f094,
-	0x02170080,
-	0xbd0009f6,
-	0x81019804,
-	0x981814b6,
-	0x25b68002,
-	0x0512fd08,
-	0xbd1601b5,
-	0x0999f094,
-	0x02370080,
-	0xbd0009f6,
-	0x81008004,
-	0x0001f602,
-	0x010204bd,
-	0x02880080,
+/* 0x0721: ctx_mem_wait */
+	0x84008f04,
+	0x00ffcf02,
+	0xf405fffd,
+	0x00f8f61b,
+/* 0x0730: ctx_load */
+	0x99f094bd,
+	0x37008005,
+	0x0009f602,
+	0x0c0a04bd,
+	0x0000b87e,
+	0x0080f4bd,
+	0x0ff60289,
+	0x8004bd00,
+	0xf602c100,
+	0x04bd0002,
+	0x02830080,
 	0xbd0002f6,
-	0x01004104,
-	0xfa0613f0,
-	0x03f80501,
+	0x7e070f04,
+	0x80000718,
+	0xf602c000,
+	0x04bd0002,
+	0xf0000bfe,
+	0x24b61f2a,
+	0x0220b604,
 	0x99f094bd,
-	0x17008009,
+	0x37008008,
 	0x0009f602,
-	0x94bd04bd,
-	0x800599f0,
+	0x008004bd,
+	0x02f60281,
+	0xd204bd00,
+	0x80000000,
+	0x800225f0,
+	0xf6028800,
+	0x04bd0002,
+	0x00421001,
+	0x0223f002,
+	0xf80512fa,
+	0xf094bd03,
+	0x00800899,
+	0x09f60217,
+	0x9804bd00,
+	0x14b68101,
+	0x80029818,
+	0xfd0825b6,
+	0x01b50512,
+	0xf094bd16,
+	0x00800999,
+	0x09f60237,
+	0x8004bd00,
+	0xf6028100,
+	0x04bd0001,
+	0x00800102,
+	0x02f60288,
+	0x4104bd00,
+	0x13f00100,
+	0x0501fa06,
+	0x94bd03f8,
+	0x800999f0,
 	0xf6021700,
 	0x04bd0009,
-/* 0x07d6: ctx_chan */
-	0xea7e00f8,
-	0x0c0a0006,
-	0x0000b87e,
-	0xd27e050f,
-	0x00f80006,
-/* 0x07e8: ctx_mmio_exec */
-	0x80410398,
+	0x99f094bd,
+	0x17008005,
+	0x0009f602,
+	0x00f804bd,
+/* 0x081c: ctx_chan */
+	0x0007307e,
+	0xb87e0c0a,
+	0x050f0000,
+	0x0007187e,
+/* 0x082e: ctx_mmio_exec */
+	0x039800f8,
+	0x81008041,
+	0x0003f602,
+	0x34bd04bd,
+/* 0x083c: ctx_mmio_loop */
+	0xf4ff34c4,
+	0x00450e1b,
+	0x0653f002,
+	0xf80535fa,
+/* 0x084d: ctx_mmio_pull */
+	0x804e9803,
+	0x7e814f98,
+	0xb600008f,
+	0x12b60830,
+	0xdf1bf401,
+/* 0x0860: ctx_mmio_done */
+	0x80160398,
 	0xf6028100,
 	0x04bd0003,
-/* 0x07f6: ctx_mmio_loop */
-	0x34c434bd,
-	0x0e1bf4ff,
-	0xf0020045,
-	0x35fa0653,
-/* 0x0807: ctx_mmio_pull */
-	0x9803f805,
-	0x4f98804e,
-	0x008f7e81,
-	0x0830b600,
-	0xf40112b6,
-/* 0x081a: ctx_mmio_done */
-	0x0398df1b,
-	0x81008016,
-	0x0003f602,
-	0x00b504bd,
-	0x01004140,
-	0xfa0613f0,
-	0x03f80601,
-/* 0x0836: ctx_xfer */
-	0x040e00f8,
-	0x03020080,
-	0xbd000ef6,
-/* 0x0841: ctx_xfer_idle */
-	0x00008e04,
-	0x00eecf03,
-	0x2000e4f1,
-	0xf4f51bf4,
-	0x02f40611,
-/* 0x0855: ctx_xfer_pre */
-	0x7e100f0c,
-	0xf40006b3,
-/* 0x085e: ctx_xfer_pre_load */
-	0x020f1b11,
-	0x0006627e,
-	0x0006717e,
-	0x0006837e,
-	0x627ef4bd,
-	0xea7e0006,
-/* 0x0876: ctx_xfer_exec */
-	0x01980006,
-	0x8024bd16,
-	0xf6010500,
-	0x04bd0002,
-	0x008e1fb2,
-	0x8f7e41a5,
-	0xfcf00000,
-	0x022cf001,
-	0xfd0124b6,
-	0xffb205f2,
-	0x41a5048e,
+	0x414000b5,
+	0x13f00100,
+	0x0601fa06,
+	0x00f803f8,
+/* 0x087c: ctx_xfer */
+	0x0080040e,
+	0x0ef60302,
+/* 0x0887: ctx_xfer_idle */
+	0x8e04bd00,
+	0xcf030000,
+	0xe4f100ee,
+	0x1bf42000,
+	0x0611f4f5,
+/* 0x089b: ctx_xfer_pre */
+	0x0f0c02f4,
+	0x06f97e10,
+	0x1b11f400,
+/* 0x08a4: ctx_xfer_pre_load */
+	0xa87e020f,
+	0xb77e0006,
+	0xc97e0006,
+	0xf4bd0006,
+	0x0006a87e,
+	0x0007307e,
+/* 0x08bc: ctx_xfer_exec */
+	0xbd160198,
+	0x05008024,
+	0x0002f601,
+	0x1fb204bd,
+	0x41a5008e,
 	0x00008f7e,
-	0x0002167e,
-	0xfc8024bd,
-	0x02f60247,
-	0xf004bd00,
-	0x20b6012c,
-	0x4afc8003,
-	0x0002f602,
-	0xacf004bd,
-	0x06a5f001,
-	0x0c98000b,
-	0x010d9800,
-	0x3d7e000e,
-	0x080a0001,
-	0x0000ec7e,
-	0x00020a7e,
-	0x0a1201f4,
-	0x00b87e0c,
-	0x7e050f00,
-	0xf40006d2,
-/* 0x08f2: ctx_xfer_post */
-	0x020f2d02,
-	0x0006627e,
-	0xb37ef4bd,
-	0x277e0006,
-	0x717e0002,
+	0xf001fcf0,
+	0x24b6022c,
+	0x05f2fd01,
+	0x048effb2,
+	0x8f7e41a5,
+	0x167e0000,
+	0x24bd0002,
+	0x0247fc80,
+	0xbd0002f6,
+	0x012cf004,
+	0x800320b6,
+	0xf6024afc,
+	0x04bd0002,
+	0xf001acf0,
+	0x000b06a5,
+	0x98000c98,
+	0x000e010d,
+	0x00013d7e,
+	0xec7e080a,
+	0x0a7e0000,
+	0x01f40002,
+	0x7e0c0a12,
+	0x0f0000b8,
+	0x07187e05,
+	0x2d02f400,
+/* 0x0938: ctx_xfer_post */
+	0xa87e020f,
 	0xf4bd0006,
-	0x0006627e,
-	0x981011f4,
-	0x11fd4001,
-	0x070bf405,
-	0x0007e87e,
-/* 0x091c: ctx_xfer_no_post_mmio */
-/* 0x091c: ctx_xfer_done */
-	0x000000f8,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
+	0x0006f97e,
+	0x0002277e,
+	0x0006b77e,
+	0xa87ef4bd,
+	0x11f40006,
+	0x40019810,
+	0xf40511fd,
+	0x2e7e070b,
+/* 0x0962: ctx_xfer_no_post_mmio */
+/* 0x0962: ctx_xfer_done */
+	0x00f80008,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnv108.fuc5.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnv108.fuc5.h
index 64dfd75192b..e49b5a877ae 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnv108.fuc5.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnv108.fuc5.h
@@ -478,10 +478,10 @@ uint32_t nv108_grhub_code[] = {
 	0x01040080,
 	0xbd0001f6,
 	0x01004104,
-	0x627e020f,
-	0x717e0006,
+	0xa87e020f,
+	0xb77e0006,
 	0x100f0006,
-	0x0006b37e,
+	0x0006f97e,
 	0x98000e98,
 	0x207e010f,
 	0x14950001,
@@ -523,8 +523,8 @@ uint32_t nv108_grhub_code[] = {
 	0x800040b7,
 	0xf40132b6,
 	0x000fb41b,
-	0x0006b37e,
-	0x627e000f,
+	0x0006f97e,
+	0xa87e000f,
 	0x00800006,
 	0x01f60201,
 	0xbd04bd00,
@@ -554,7 +554,7 @@ uint32_t nv108_grhub_code[] = {
 	0x0009f602,
 	0x32f404bd,
 	0x0231f401,
-	0x0008367e,
+	0x00087c7e,
 	0x99f094bd,
 	0x17008007,
 	0x0009f602,
@@ -563,7 +563,7 @@ uint32_t nv108_grhub_code[] = {
 	0x37008006,
 	0x0009f602,
 	0x31f404bd,
-	0x08367e01,
+	0x087c7e01,
 	0xf094bd00,
 	0x00800699,
 	0x09f60217,
@@ -572,7 +572,7 @@ uint32_t nv108_grhub_code[] = {
 	0x20f92f0e,
 	0x32f412b2,
 	0x0232f401,
-	0x0008367e,
+	0x00087c7e,
 	0x008020fc,
 	0x02f602c0,
 	0xf404bd00,
@@ -580,7 +580,7 @@ uint32_t nv108_grhub_code[] = {
 	0x23c8130e,
 	0x0d0bf41f,
 	0xf40131f4,
-	0x367e0232,
+	0x7c7e0232,
 /* 0x054e: chsw_done */
 	0x01020008,
 	0x02c30080,
@@ -593,7 +593,7 @@ uint32_t nv108_grhub_code[] = {
 	0xb0ff2a0e,
 	0x1bf401e4,
 	0x7ef2b20c,
-	0xf40007d6,
+	0xf400081c,
 /* 0x057a: main_not_ctx_chan */
 	0xe4b0400e,
 	0x2c1bf402,
@@ -602,7 +602,7 @@ uint32_t nv108_grhub_code[] = {
 	0x0009f602,
 	0x32f404bd,
 	0x0232f401,
-	0x0008367e,
+	0x00087c7e,
 	0x99f094bd,
 	0x17008007,
 	0x0009f602,
@@ -642,238 +642,238 @@ uint32_t nv108_grhub_code[] = {
 /* 0x061a: ih_no_ctxsw */
 	0xabe40000,
 	0x0bf40400,
-	0x01004b10,
-	0x448ebfb2,
-	0x8f7e4001,
-/* 0x062e: ih_no_fwmthd */
-	0x044b0000,
-	0xffb0bd01,
-	0x0bf4b4ab,
-	0x0700800c,
-	0x000bf603,
-/* 0x0642: ih_no_other */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0x0032f480,
-/* 0x0662: ctx_4170s */
-	0xf5f001f8,
-	0x8effb210,
-	0x7e404170,
-	0xf800008f,
-/* 0x0671: ctx_4170w */
-	0x41708e00,
+	0x07088e56,
 	0x00657e40,
-	0xf0ffb200,
-	0x1bf410f4,
-/* 0x0683: ctx_redswitch */
-	0x4e00f8f3,
-	0xe5f00200,
-	0x20e5f040,
-	0x8010e5f0,
-	0xf6018500,
-	0x04bd000e,
-/* 0x069a: ctx_redswitch_delay */
-	0xf2b6080f,
-	0xfd1bf401,
-	0x0400e5f1,
-	0x0100e5f1,
-	0x01850080,
-	0xbd000ef6,
-/* 0x06b3: ctx_86c */
-	0x8000f804,
-	0xf6022300,
+	0x80ffb200,
+	0xf6020400,
 	0x04bd000f,
-	0x148effb2,
-	0x8f7e408a,
-	0xffb20000,
-	0x41a88c8e,
+	0x4007048e,
+	0x0000657e,
+	0x0080ffb2,
+	0x0ff60203,
+	0xc704bd00,
+	0xee9450fe,
+	0x07008f02,
+	0x00efbb40,
+	0x0000657e,
+	0x02020080,
+	0xbd000ff6,
+	0x7e030f04,
+	0x4b0002f8,
+	0xbfb20100,
+	0x4001448e,
 	0x00008f7e,
-/* 0x06d2: ctx_mem */
-	0x008000f8,
-	0x0ff60284,
-/* 0x06db: ctx_mem_wait */
-	0x8f04bd00,
-	0xcf028400,
-	0xfffd00ff,
-	0xf61bf405,
-/* 0x06ea: ctx_load */
-	0x94bd00f8,
-	0x800599f0,
-	0xf6023700,
-	0x04bd0009,
-	0xb87e0c0a,
-	0xf4bd0000,
-	0x02890080,
+/* 0x0674: ih_no_fwmthd */
+	0xbd05044b,
+	0xb4abffb0,
+	0x800c0bf4,
+	0xf6030700,
+	0x04bd000b,
+/* 0x0688: ih_no_other */
+	0xf6010040,
+	0x04bd000a,
+	0xe0fcf0fc,
+	0xb0fcd0fc,
+	0x90fca0fc,
+	0x88fe80fc,
+	0xf480fc00,
+	0x01f80032,
+/* 0x06a8: ctx_4170s */
+	0xb210f5f0,
+	0x41708eff,
+	0x008f7e40,
+/* 0x06b7: ctx_4170w */
+	0x8e00f800,
+	0x7e404170,
+	0xb2000065,
+	0x10f4f0ff,
+	0xf8f31bf4,
+/* 0x06c9: ctx_redswitch */
+	0x02004e00,
+	0xf040e5f0,
+	0xe5f020e5,
+	0x85008010,
+	0x000ef601,
+	0x080f04bd,
+/* 0x06e0: ctx_redswitch_delay */
+	0xf401f2b6,
+	0xe5f1fd1b,
+	0xe5f10400,
+	0x00800100,
+	0x0ef60185,
+	0xf804bd00,
+/* 0x06f9: ctx_86c */
+	0x23008000,
+	0x000ff602,
+	0xffb204bd,
+	0x408a148e,
+	0x00008f7e,
+	0x8c8effb2,
+	0x8f7e41a8,
+	0x00f80000,
+/* 0x0718: ctx_mem */
+	0x02840080,
 	0xbd000ff6,
-	0xc1008004,
-	0x0002f602,
-	0x008004bd,
-	0x02f60283,
-	0x0f04bd00,
-	0x06d27e07,
-	0xc0008000,
-	0x0002f602,
-	0x0bfe04bd,
-	0x1f2af000,
-	0xb60424b6,
-	0x94bd0220,
-	0x800899f0,
-	0xf6023700,
-	0x04bd0009,
-	0x02810080,
-	0xbd0002f6,
-	0x0000d204,
-	0x25f08000,
-	0x88008002,
-	0x0002f602,
-	0x100104bd,
-	0xf0020042,
-	0x12fa0223,
-	0xbd03f805,
-	0x0899f094,
-	0x02170080,
-	0xbd0009f6,
-	0x81019804,
-	0x981814b6,
-	0x25b68002,
-	0x0512fd08,
-	0xbd1601b5,
-	0x0999f094,
-	0x02370080,
-	0xbd0009f6,
-	0x81008004,
-	0x0001f602,
-	0x010204bd,
-	0x02880080,
+/* 0x0721: ctx_mem_wait */
+	0x84008f04,
+	0x00ffcf02,
+	0xf405fffd,
+	0x00f8f61b,
+/* 0x0730: ctx_load */
+	0x99f094bd,
+	0x37008005,
+	0x0009f602,
+	0x0c0a04bd,
+	0x0000b87e,
+	0x0080f4bd,
+	0x0ff60289,
+	0x8004bd00,
+	0xf602c100,
+	0x04bd0002,
+	0x02830080,
 	0xbd0002f6,
-	0x01004104,
-	0xfa0613f0,
-	0x03f80501,
+	0x7e070f04,
+	0x80000718,
+	0xf602c000,
+	0x04bd0002,
+	0xf0000bfe,
+	0x24b61f2a,
+	0x0220b604,
 	0x99f094bd,
-	0x17008009,
+	0x37008008,
 	0x0009f602,
-	0x94bd04bd,
-	0x800599f0,
+	0x008004bd,
+	0x02f60281,
+	0xd204bd00,
+	0x80000000,
+	0x800225f0,
+	0xf6028800,
+	0x04bd0002,
+	0x00421001,
+	0x0223f002,
+	0xf80512fa,
+	0xf094bd03,
+	0x00800899,
+	0x09f60217,
+	0x9804bd00,
+	0x14b68101,
+	0x80029818,
+	0xfd0825b6,
+	0x01b50512,
+	0xf094bd16,
+	0x00800999,
+	0x09f60237,
+	0x8004bd00,
+	0xf6028100,
+	0x04bd0001,
+	0x00800102,
+	0x02f60288,
+	0x4104bd00,
+	0x13f00100,
+	0x0501fa06,
+	0x94bd03f8,
+	0x800999f0,
 	0xf6021700,
 	0x04bd0009,
-/* 0x07d6: ctx_chan */
-	0xea7e00f8,
-	0x0c0a0006,
-	0x0000b87e,
-	0xd27e050f,
-	0x00f80006,
-/* 0x07e8: ctx_mmio_exec */
-	0x80410398,
+	0x99f094bd,
+	0x17008005,
+	0x0009f602,
+	0x00f804bd,
+/* 0x081c: ctx_chan */
+	0x0007307e,
+	0xb87e0c0a,
+	0x050f0000,
+	0x0007187e,
+/* 0x082e: ctx_mmio_exec */
+	0x039800f8,
+	0x81008041,
+	0x0003f602,
+	0x34bd04bd,
+/* 0x083c: ctx_mmio_loop */
+	0xf4ff34c4,
+	0x00450e1b,
+	0x0653f002,
+	0xf80535fa,
+/* 0x084d: ctx_mmio_pull */
+	0x804e9803,
+	0x7e814f98,
+	0xb600008f,
+	0x12b60830,
+	0xdf1bf401,
+/* 0x0860: ctx_mmio_done */
+	0x80160398,
 	0xf6028100,
 	0x04bd0003,
-/* 0x07f6: ctx_mmio_loop */
-	0x34c434bd,
-	0x0e1bf4ff,
-	0xf0020045,
-	0x35fa0653,
-/* 0x0807: ctx_mmio_pull */
-	0x9803f805,
-	0x4f98804e,
-	0x008f7e81,
-	0x0830b600,
-	0xf40112b6,
-/* 0x081a: ctx_mmio_done */
-	0x0398df1b,
-	0x81008016,
-	0x0003f602,
-	0x00b504bd,
-	0x01004140,
-	0xfa0613f0,
-	0x03f80601,
-/* 0x0836: ctx_xfer */
-	0x040e00f8,
-	0x03020080,
-	0xbd000ef6,
-/* 0x0841: ctx_xfer_idle */
-	0x00008e04,
-	0x00eecf03,
-	0x2000e4f1,
-	0xf4f51bf4,
-	0x02f40611,
-/* 0x0855: ctx_xfer_pre */
-	0x7e100f0c,
-	0xf40006b3,
-/* 0x085e: ctx_xfer_pre_load */
-	0x020f1b11,
-	0x0006627e,
-	0x0006717e,
-	0x0006837e,
-	0x627ef4bd,
-	0xea7e0006,
-/* 0x0876: ctx_xfer_exec */
-	0x01980006,
-	0x8024bd16,
-	0xf6010500,
-	0x04bd0002,
-	0x008e1fb2,
-	0x8f7e41a5,
-	0xfcf00000,
-	0x022cf001,
-	0xfd0124b6,
-	0xffb205f2,
-	0x41a5048e,
+	0x414000b5,
+	0x13f00100,
+	0x0601fa06,
+	0x00f803f8,
+/* 0x087c: ctx_xfer */
+	0x0080040e,
+	0x0ef60302,
+/* 0x0887: ctx_xfer_idle */
+	0x8e04bd00,
+	0xcf030000,
+	0xe4f100ee,
+	0x1bf42000,
+	0x0611f4f5,
+/* 0x089b: ctx_xfer_pre */
+	0x0f0c02f4,
+	0x06f97e10,
+	0x1b11f400,
+/* 0x08a4: ctx_xfer_pre_load */
+	0xa87e020f,
+	0xb77e0006,
+	0xc97e0006,
+	0xf4bd0006,
+	0x0006a87e,
+	0x0007307e,
+/* 0x08bc: ctx_xfer_exec */
+	0xbd160198,
+	0x05008024,
+	0x0002f601,
+	0x1fb204bd,
+	0x41a5008e,
 	0x00008f7e,
-	0x0002167e,
-	0xfc8024bd,
-	0x02f60247,
-	0xf004bd00,
-	0x20b6012c,
-	0x4afc8003,
-	0x0002f602,
-	0xacf004bd,
-	0x06a5f001,
-	0x0c98000b,
-	0x010d9800,
-	0x3d7e000e,
-	0x080a0001,
-	0x0000ec7e,
-	0x00020a7e,
-	0x0a1201f4,
-	0x00b87e0c,
-	0x7e050f00,
-	0xf40006d2,
-/* 0x08f2: ctx_xfer_post */
-	0x020f2d02,
-	0x0006627e,
-	0xb37ef4bd,
-	0x277e0006,
-	0x717e0002,
+	0xf001fcf0,
+	0x24b6022c,
+	0x05f2fd01,
+	0x048effb2,
+	0x8f7e41a5,
+	0x167e0000,
+	0x24bd0002,
+	0x0247fc80,
+	0xbd0002f6,
+	0x012cf004,
+	0x800320b6,
+	0xf6024afc,
+	0x04bd0002,
+	0xf001acf0,
+	0x000b06a5,
+	0x98000c98,
+	0x000e010d,
+	0x00013d7e,
+	0xec7e080a,
+	0x0a7e0000,
+	0x01f40002,
+	0x7e0c0a12,
+	0x0f0000b8,
+	0x07187e05,
+	0x2d02f400,
+/* 0x0938: ctx_xfer_post */
+	0xa87e020f,
 	0xf4bd0006,
-	0x0006627e,
-	0x981011f4,
-	0x11fd4001,
-	0x070bf405,
-	0x0007e87e,
-/* 0x091c: ctx_xfer_no_post_mmio */
-/* 0x091c: ctx_xfer_done */
-	0x000000f8,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
-	0x00000000,
+	0x0006f97e,
+	0x0002277e,
+	0x0006b77e,
+	0xa87ef4bd,
+	0x11f40006,
+	0x40019810,
+	0xf40511fd,
+	0x2e7e070b,
+/* 0x0962: ctx_xfer_no_post_mmio */
+/* 0x0962: ctx_xfer_done */
+	0x00f80008,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvc0.fuc.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvc0.fuc.h
index f8f7b278a13..92dfe6a4ac8 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvc0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvc0.fuc.h
@@ -528,10 +528,10 @@ uint32_t nvc0_grhub_code[] = {
 	0x0001d001,
 	0x17f104bd,
 	0xf7f00100,
-	0xb521f502,
-	0xc721f507,
-	0x10f7f007,
-	0x081421f5,
+	0x0d21f502,
+	0x1f21f508,
+	0x10f7f008,
+	0x086c21f5,
 	0x98000e98,
 	0x21f5010f,
 	0x14950150,
@@ -574,9 +574,9 @@ uint32_t nvc0_grhub_code[] = {
 	0xb6800040,
 	0x1bf40132,
 	0x00f7f0be,
-	0x081421f5,
+	0x086c21f5,
 	0xf500f7f0,
-	0xf107b521,
+	0xf1080d21,
 	0xf0010007,
 	0x01d00203,
 	0xbd04bd00,
@@ -610,8 +610,8 @@ uint32_t nvc0_grhub_code[] = {
 	0x09d00203,
 	0xf404bd00,
 	0x31f40132,
-	0xe821f502,
-	0xf094bd09,
+	0x4021f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -621,7 +621,7 @@ uint32_t nvc0_grhub_code[] = {
 	0x0203f00f,
 	0xbd0009d0,
 	0x0131f404,
-	0x09e821f5,
+	0x0a4021f5,
 	0x99f094bd,
 	0x0007f106,
 	0x0203f017,
@@ -631,7 +631,7 @@ uint32_t nvc0_grhub_code[] = {
 	0x12b920f9,
 	0x0132f402,
 	0xf50232f4,
-	0xfc09e821,
+	0xfc0a4021,
 	0x0007f120,
 	0x0203f0c0,
 	0xbd0002d0,
@@ -640,7 +640,7 @@ uint32_t nvc0_grhub_code[] = {
 	0xf41f23c8,
 	0x31f40d0b,
 	0x0232f401,
-	0x09e821f5,
+	0x0a4021f5,
 /* 0x063c: chsw_done */
 	0xf10127f0,
 	0xf0c30007,
@@ -654,7 +654,7 @@ uint32_t nvc0_grhub_code[] = {
 /* 0x0660: main_not_ctx_switch */
 	0xf401e4b0,
 	0xf2b90d1b,
-	0x7821f502,
+	0xd021f502,
 	0x460ef409,
 /* 0x0670: main_not_ctx_chan */
 	0xf402e4b0,
@@ -664,8 +664,8 @@ uint32_t nvc0_grhub_code[] = {
 	0x09d00203,
 	0xf404bd00,
 	0x32f40132,
-	0xe821f502,
-	0xf094bd09,
+	0x4021f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -710,18 +710,40 @@ uint32_t nvc0_grhub_code[] = {
 /* 0x072b: ih_no_ctxsw */
 	0xe40421f4,
 	0xf40400ab,
-	0xb7f1140b,
+	0xe7f16c0b,
+	0xe3f00708,
+	0x6821f440,
+	0xf102ffb9,
+	0xf0040007,
+	0x0fd00203,
+	0xf104bd00,
+	0xf00704e7,
+	0x21f440e3,
+	0x02ffb968,
+	0x030007f1,
+	0xd00203f0,
+	0x04bd000f,
+	0x9450fec7,
+	0xf7f102ee,
+	0xf3f00700,
+	0x00efbb40,
+	0xf16821f4,
+	0xf0020007,
+	0x0fd00203,
+	0xf004bd00,
+	0x21f503f7,
+	0xb7f1037e,
 	0xbfb90100,
 	0x44e7f102,
 	0x40e3f001,
-/* 0x0743: ih_no_fwmthd */
+/* 0x079b: ih_no_fwmthd */
 	0xf19d21f4,
-	0xbd0104b7,
+	0xbd0504b7,
 	0xb4abffb0,
 	0xf10f0bf4,
 	0xf0070007,
 	0x0bd00303,
-/* 0x075b: ih_no_other */
+/* 0x07b3: ih_no_other */
 	0xf104bd00,
 	0xf0010007,
 	0x0ad00003,
@@ -731,36 +753,36 @@ uint32_t nvc0_grhub_code[] = {
 	0xfc90fca0,
 	0x0088fe80,
 	0x32f480fc,
-/* 0x077f: ctx_4160s */
+/* 0x07d7: ctx_4160s */
 	0xf001f800,
 	0xffb901f7,
 	0x60e7f102,
 	0x40e3f041,
-/* 0x078f: ctx_4160s_wait */
+/* 0x07e7: ctx_4160s_wait */
 	0xf19d21f4,
 	0xf04160e7,
 	0x21f440e3,
 	0x02ffb968,
 	0xf404ffc8,
 	0x00f8f00b,
-/* 0x07a4: ctx_4160c */
+/* 0x07fc: ctx_4160c */
 	0xffb9f4bd,
 	0x60e7f102,
 	0x40e3f041,
 	0xf89d21f4,
-/* 0x07b5: ctx_4170s */
+/* 0x080d: ctx_4170s */
 	0x10f5f000,
 	0xf102ffb9,
 	0xf04170e7,
 	0x21f440e3,
-/* 0x07c7: ctx_4170w */
+/* 0x081f: ctx_4170w */
 	0xf100f89d,
 	0xf04170e7,
 	0x21f440e3,
 	0x02ffb968,
 	0xf410f4f0,
 	0x00f8f01b,
-/* 0x07dc: ctx_redswitch */
+/* 0x0834: ctx_redswitch */
 	0x0200e7f1,
 	0xf040e5f0,
 	0xe5f020e5,
@@ -768,7 +790,7 @@ uint32_t nvc0_grhub_code[] = {
 	0x0103f085,
 	0xbd000ed0,
 	0x08f7f004,
-/* 0x07f8: ctx_redswitch_delay */
+/* 0x0850: ctx_redswitch_delay */
 	0xf401f2b6,
 	0xe5f1fd1b,
 	0xe5f10400,
@@ -776,7 +798,7 @@ uint32_t nvc0_grhub_code[] = {
 	0x03f08500,
 	0x000ed001,
 	0x00f804bd,
-/* 0x0814: ctx_86c */
+/* 0x086c: ctx_86c */
 	0x1b0007f1,
 	0xd00203f0,
 	0x04bd000f,
@@ -787,16 +809,16 @@ uint32_t nvc0_grhub_code[] = {
 	0xa86ce7f1,
 	0xf441e3f0,
 	0x00f89d21,
-/* 0x083c: ctx_mem */
+/* 0x0894: ctx_mem */
 	0x840007f1,
 	0xd00203f0,
 	0x04bd000f,
-/* 0x0848: ctx_mem_wait */
+/* 0x08a0: ctx_mem_wait */
 	0x8400f7f1,
 	0xcf02f3f0,
 	0xfffd00ff,
 	0xf31bf405,
-/* 0x085a: ctx_load */
+/* 0x08b2: ctx_load */
 	0x94bd00f8,
 	0xf10599f0,
 	0xf00f0007,
@@ -814,7 +836,7 @@ uint32_t nvc0_grhub_code[] = {
 	0x02d00203,
 	0xf004bd00,
 	0x21f507f7,
-	0x07f1083c,
+	0x07f10894,
 	0x03f0c000,
 	0x0002d002,
 	0x0bfe04bd,
@@ -869,31 +891,31 @@ uint32_t nvc0_grhub_code[] = {
 	0x03f01700,
 	0x0009d002,
 	0x00f804bd,
-/* 0x0978: ctx_chan */
-	0x077f21f5,
-	0x085a21f5,
+/* 0x09d0: ctx_chan */
+	0x07d721f5,
+	0x08b221f5,
 	0xf40ca7f0,
 	0xf7f0d021,
-	0x3c21f505,
-	0xa421f508,
-/* 0x0993: ctx_mmio_exec */
+	0x9421f505,
+	0xfc21f508,
+/* 0x09eb: ctx_mmio_exec */
 	0x9800f807,
 	0x07f14103,
 	0x03f08100,
 	0x0003d002,
 	0x34bd04bd,
-/* 0x09a4: ctx_mmio_loop */
+/* 0x09fc: ctx_mmio_loop */
 	0xf4ff34c4,
 	0x57f10f1b,
 	0x53f00200,
 	0x0535fa06,
-/* 0x09b6: ctx_mmio_pull */
+/* 0x0a0e: ctx_mmio_pull */
 	0x4e9803f8,
 	0x814f9880,
 	0xb69d21f4,
 	0x12b60830,
 	0xdf1bf401,
-/* 0x09c8: ctx_mmio_done */
+/* 0x0a20: ctx_mmio_done */
 	0xf1160398,
 	0xf0810007,
 	0x03d00203,
@@ -902,30 +924,30 @@ uint32_t nvc0_grhub_code[] = {
 	0x13f00100,
 	0x0601fa06,
 	0x00f803f8,
-/* 0x09e8: ctx_xfer */
+/* 0x0a40: ctx_xfer */
 	0xf104e7f0,
 	0xf0020007,
 	0x0ed00303,
-/* 0x09f7: ctx_xfer_idle */
+/* 0x0a4f: ctx_xfer_idle */
 	0xf104bd00,
 	0xf00000e7,
 	0xeecf03e3,
 	0x00e4f100,
 	0xf21bf420,
 	0xf40611f4,
-/* 0x0a0e: ctx_xfer_pre */
+/* 0x0a66: ctx_xfer_pre */
 	0xf7f01102,
-	0x1421f510,
-	0x7f21f508,
+	0x6c21f510,
+	0xd721f508,
 	0x1c11f407,
-/* 0x0a1c: ctx_xfer_pre_load */
+/* 0x0a74: ctx_xfer_pre_load */
 	0xf502f7f0,
-	0xf507b521,
-	0xf507c721,
-	0xbd07dc21,
-	0xb521f5f4,
-	0x5a21f507,
-/* 0x0a35: ctx_xfer_exec */
+	0xf5080d21,
+	0xf5081f21,
+	0xbd083421,
+	0x0d21f5f4,
+	0xb221f508,
+/* 0x0a8d: ctx_xfer_exec */
 	0x16019808,
 	0x07f124bd,
 	0x03f00500,
@@ -960,23 +982,65 @@ uint32_t nvc0_grhub_code[] = {
 	0x1301f402,
 	0xf40ca7f0,
 	0xf7f0d021,
-	0x3c21f505,
+	0x9421f505,
 	0x3202f408,
-/* 0x0ac4: ctx_xfer_post */
+/* 0x0b1c: ctx_xfer_post */
 	0xf502f7f0,
-	0xbd07b521,
-	0x1421f5f4,
+	0xbd080d21,
+	0x6c21f5f4,
 	0x7f21f508,
-	0xc721f502,
-	0xf5f4bd07,
-	0xf407b521,
+	0x1f21f502,
+	0xf5f4bd08,
+	0xf4080d21,
 	0x01981011,
 	0x0511fd40,
 	0xf5070bf4,
-/* 0x0aef: ctx_xfer_no_post_mmio */
-	0xf5099321,
-/* 0x0af3: ctx_xfer_done */
-	0xf807a421,
+/* 0x0b47: ctx_xfer_no_post_mmio */
+	0xf509eb21,
+/* 0x0b4b: ctx_xfer_done */
+	0xf807fc21,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvd7.fuc.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvd7.fuc.h
index 624215a005b..62b0c7601d8 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvd7.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvd7.fuc.h
@@ -528,10 +528,10 @@ uint32_t nvd7_grhub_code[] = {
 	0x0001d001,
 	0x17f104bd,
 	0xf7f00100,
-	0xb521f502,
-	0xc721f507,
-	0x10f7f007,
-	0x081421f5,
+	0x0d21f502,
+	0x1f21f508,
+	0x10f7f008,
+	0x086c21f5,
 	0x98000e98,
 	0x21f5010f,
 	0x14950150,
@@ -574,9 +574,9 @@ uint32_t nvd7_grhub_code[] = {
 	0xb6800040,
 	0x1bf40132,
 	0x00f7f0be,
-	0x081421f5,
+	0x086c21f5,
 	0xf500f7f0,
-	0xf107b521,
+	0xf1080d21,
 	0xf0010007,
 	0x01d00203,
 	0xbd04bd00,
@@ -610,8 +610,8 @@ uint32_t nvd7_grhub_code[] = {
 	0x09d00203,
 	0xf404bd00,
 	0x31f40132,
-	0xe821f502,
-	0xf094bd09,
+	0x4021f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -621,7 +621,7 @@ uint32_t nvd7_grhub_code[] = {
 	0x0203f00f,
 	0xbd0009d0,
 	0x0131f404,
-	0x09e821f5,
+	0x0a4021f5,
 	0x99f094bd,
 	0x0007f106,
 	0x0203f017,
@@ -631,7 +631,7 @@ uint32_t nvd7_grhub_code[] = {
 	0x12b920f9,
 	0x0132f402,
 	0xf50232f4,
-	0xfc09e821,
+	0xfc0a4021,
 	0x0007f120,
 	0x0203f0c0,
 	0xbd0002d0,
@@ -640,7 +640,7 @@ uint32_t nvd7_grhub_code[] = {
 	0xf41f23c8,
 	0x31f40d0b,
 	0x0232f401,
-	0x09e821f5,
+	0x0a4021f5,
 /* 0x063c: chsw_done */
 	0xf10127f0,
 	0xf0c30007,
@@ -654,7 +654,7 @@ uint32_t nvd7_grhub_code[] = {
 /* 0x0660: main_not_ctx_switch */
 	0xf401e4b0,
 	0xf2b90d1b,
-	0x7821f502,
+	0xd021f502,
 	0x460ef409,
 /* 0x0670: main_not_ctx_chan */
 	0xf402e4b0,
@@ -664,8 +664,8 @@ uint32_t nvd7_grhub_code[] = {
 	0x09d00203,
 	0xf404bd00,
 	0x32f40132,
-	0xe821f502,
-	0xf094bd09,
+	0x4021f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -710,18 +710,40 @@ uint32_t nvd7_grhub_code[] = {
 /* 0x072b: ih_no_ctxsw */
 	0xe40421f4,
 	0xf40400ab,
-	0xb7f1140b,
+	0xe7f16c0b,
+	0xe3f00708,
+	0x6821f440,
+	0xf102ffb9,
+	0xf0040007,
+	0x0fd00203,
+	0xf104bd00,
+	0xf00704e7,
+	0x21f440e3,
+	0x02ffb968,
+	0x030007f1,
+	0xd00203f0,
+	0x04bd000f,
+	0x9450fec7,
+	0xf7f102ee,
+	0xf3f00700,
+	0x00efbb40,
+	0xf16821f4,
+	0xf0020007,
+	0x0fd00203,
+	0xf004bd00,
+	0x21f503f7,
+	0xb7f1037e,
 	0xbfb90100,
 	0x44e7f102,
 	0x40e3f001,
-/* 0x0743: ih_no_fwmthd */
+/* 0x079b: ih_no_fwmthd */
 	0xf19d21f4,
-	0xbd0104b7,
+	0xbd0504b7,
 	0xb4abffb0,
 	0xf10f0bf4,
 	0xf0070007,
 	0x0bd00303,
-/* 0x075b: ih_no_other */
+/* 0x07b3: ih_no_other */
 	0xf104bd00,
 	0xf0010007,
 	0x0ad00003,
@@ -731,36 +753,36 @@ uint32_t nvd7_grhub_code[] = {
 	0xfc90fca0,
 	0x0088fe80,
 	0x32f480fc,
-/* 0x077f: ctx_4160s */
+/* 0x07d7: ctx_4160s */
 	0xf001f800,
 	0xffb901f7,
 	0x60e7f102,
 	0x40e3f041,
-/* 0x078f: ctx_4160s_wait */
+/* 0x07e7: ctx_4160s_wait */
 	0xf19d21f4,
 	0xf04160e7,
 	0x21f440e3,
 	0x02ffb968,
 	0xf404ffc8,
 	0x00f8f00b,
-/* 0x07a4: ctx_4160c */
+/* 0x07fc: ctx_4160c */
 	0xffb9f4bd,
 	0x60e7f102,
 	0x40e3f041,
 	0xf89d21f4,
-/* 0x07b5: ctx_4170s */
+/* 0x080d: ctx_4170s */
 	0x10f5f000,
 	0xf102ffb9,
 	0xf04170e7,
 	0x21f440e3,
-/* 0x07c7: ctx_4170w */
+/* 0x081f: ctx_4170w */
 	0xf100f89d,
 	0xf04170e7,
 	0x21f440e3,
 	0x02ffb968,
 	0xf410f4f0,
 	0x00f8f01b,
-/* 0x07dc: ctx_redswitch */
+/* 0x0834: ctx_redswitch */
 	0x0200e7f1,
 	0xf040e5f0,
 	0xe5f020e5,
@@ -768,7 +790,7 @@ uint32_t nvd7_grhub_code[] = {
 	0x0103f085,
 	0xbd000ed0,
 	0x08f7f004,
-/* 0x07f8: ctx_redswitch_delay */
+/* 0x0850: ctx_redswitch_delay */
 	0xf401f2b6,
 	0xe5f1fd1b,
 	0xe5f10400,
@@ -776,7 +798,7 @@ uint32_t nvd7_grhub_code[] = {
 	0x03f08500,
 	0x000ed001,
 	0x00f804bd,
-/* 0x0814: ctx_86c */
+/* 0x086c: ctx_86c */
 	0x1b0007f1,
 	0xd00203f0,
 	0x04bd000f,
@@ -787,16 +809,16 @@ uint32_t nvd7_grhub_code[] = {
 	0xa86ce7f1,
 	0xf441e3f0,
 	0x00f89d21,
-/* 0x083c: ctx_mem */
+/* 0x0894: ctx_mem */
 	0x840007f1,
 	0xd00203f0,
 	0x04bd000f,
-/* 0x0848: ctx_mem_wait */
+/* 0x08a0: ctx_mem_wait */
 	0x8400f7f1,
 	0xcf02f3f0,
 	0xfffd00ff,
 	0xf31bf405,
-/* 0x085a: ctx_load */
+/* 0x08b2: ctx_load */
 	0x94bd00f8,
 	0xf10599f0,
 	0xf00f0007,
@@ -814,7 +836,7 @@ uint32_t nvd7_grhub_code[] = {
 	0x02d00203,
 	0xf004bd00,
 	0x21f507f7,
-	0x07f1083c,
+	0x07f10894,
 	0x03f0c000,
 	0x0002d002,
 	0x0bfe04bd,
@@ -869,31 +891,31 @@ uint32_t nvd7_grhub_code[] = {
 	0x03f01700,
 	0x0009d002,
 	0x00f804bd,
-/* 0x0978: ctx_chan */
-	0x077f21f5,
-	0x085a21f5,
+/* 0x09d0: ctx_chan */
+	0x07d721f5,
+	0x08b221f5,
 	0xf40ca7f0,
 	0xf7f0d021,
-	0x3c21f505,
-	0xa421f508,
-/* 0x0993: ctx_mmio_exec */
+	0x9421f505,
+	0xfc21f508,
+/* 0x09eb: ctx_mmio_exec */
 	0x9800f807,
 	0x07f14103,
 	0x03f08100,
 	0x0003d002,
 	0x34bd04bd,
-/* 0x09a4: ctx_mmio_loop */
+/* 0x09fc: ctx_mmio_loop */
 	0xf4ff34c4,
 	0x57f10f1b,
 	0x53f00200,
 	0x0535fa06,
-/* 0x09b6: ctx_mmio_pull */
+/* 0x0a0e: ctx_mmio_pull */
 	0x4e9803f8,
 	0x814f9880,
 	0xb69d21f4,
 	0x12b60830,
 	0xdf1bf401,
-/* 0x09c8: ctx_mmio_done */
+/* 0x0a20: ctx_mmio_done */
 	0xf1160398,
 	0xf0810007,
 	0x03d00203,
@@ -902,30 +924,30 @@ uint32_t nvd7_grhub_code[] = {
 	0x13f00100,
 	0x0601fa06,
 	0x00f803f8,
-/* 0x09e8: ctx_xfer */
+/* 0x0a40: ctx_xfer */
 	0xf104e7f0,
 	0xf0020007,
 	0x0ed00303,
-/* 0x09f7: ctx_xfer_idle */
+/* 0x0a4f: ctx_xfer_idle */
 	0xf104bd00,
 	0xf00000e7,
 	0xeecf03e3,
 	0x00e4f100,
 	0xf21bf420,
 	0xf40611f4,
-/* 0x0a0e: ctx_xfer_pre */
+/* 0x0a66: ctx_xfer_pre */
 	0xf7f01102,
-	0x1421f510,
-	0x7f21f508,
+	0x6c21f510,
+	0xd721f508,
 	0x1c11f407,
-/* 0x0a1c: ctx_xfer_pre_load */
+/* 0x0a74: ctx_xfer_pre_load */
 	0xf502f7f0,
-	0xf507b521,
-	0xf507c721,
-	0xbd07dc21,
-	0xb521f5f4,
-	0x5a21f507,
-/* 0x0a35: ctx_xfer_exec */
+	0xf5080d21,
+	0xf5081f21,
+	0xbd083421,
+	0x0d21f5f4,
+	0xb221f508,
+/* 0x0a8d: ctx_xfer_exec */
 	0x16019808,
 	0x07f124bd,
 	0x03f00500,
@@ -960,23 +982,65 @@ uint32_t nvd7_grhub_code[] = {
 	0x1301f402,
 	0xf40ca7f0,
 	0xf7f0d021,
-	0x3c21f505,
+	0x9421f505,
 	0x3202f408,
-/* 0x0ac4: ctx_xfer_post */
+/* 0x0b1c: ctx_xfer_post */
 	0xf502f7f0,
-	0xbd07b521,
-	0x1421f5f4,
+	0xbd080d21,
+	0x6c21f5f4,
 	0x7f21f508,
-	0xc721f502,
-	0xf5f4bd07,
-	0xf407b521,
+	0x1f21f502,
+	0xf5f4bd08,
+	0xf4080d21,
 	0x01981011,
 	0x0511fd40,
 	0xf5070bf4,
-/* 0x0aef: ctx_xfer_no_post_mmio */
-	0xf5099321,
-/* 0x0af3: ctx_xfer_done */
-	0xf807a421,
+/* 0x0b47: ctx_xfer_no_post_mmio */
+	0xf509eb21,
+/* 0x0b4b: ctx_xfer_done */
+	0xf807fc21,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnve0.fuc.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnve0.fuc.h
index 6547b3dfc7e..51c3797d853 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnve0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnve0.fuc.h
@@ -528,10 +528,10 @@ uint32_t nve0_grhub_code[] = {
 	0x0001d001,
 	0x17f104bd,
 	0xf7f00100,
-	0x7f21f502,
-	0x9121f507,
+	0xd721f502,
+	0xe921f507,
 	0x10f7f007,
-	0x07de21f5,
+	0x083621f5,
 	0x98000e98,
 	0x21f5010f,
 	0x14950150,
@@ -574,9 +574,9 @@ uint32_t nve0_grhub_code[] = {
 	0xb6800040,
 	0x1bf40132,
 	0x00f7f0be,
-	0x07de21f5,
+	0x083621f5,
 	0xf500f7f0,
-	0xf1077f21,
+	0xf107d721,
 	0xf0010007,
 	0x01d00203,
 	0xbd04bd00,
@@ -610,8 +610,8 @@ uint32_t nve0_grhub_code[] = {
 	0x09d00203,
 	0xf404bd00,
 	0x31f40132,
-	0xaa21f502,
-	0xf094bd09,
+	0x0221f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -621,7 +621,7 @@ uint32_t nve0_grhub_code[] = {
 	0x0203f00f,
 	0xbd0009d0,
 	0x0131f404,
-	0x09aa21f5,
+	0x0a0221f5,
 	0x99f094bd,
 	0x0007f106,
 	0x0203f017,
@@ -631,7 +631,7 @@ uint32_t nve0_grhub_code[] = {
 	0x12b920f9,
 	0x0132f402,
 	0xf50232f4,
-	0xfc09aa21,
+	0xfc0a0221,
 	0x0007f120,
 	0x0203f0c0,
 	0xbd0002d0,
@@ -640,7 +640,7 @@ uint32_t nve0_grhub_code[] = {
 	0xf41f23c8,
 	0x31f40d0b,
 	0x0232f401,
-	0x09aa21f5,
+	0x0a0221f5,
 /* 0x063c: chsw_done */
 	0xf10127f0,
 	0xf0c30007,
@@ -654,7 +654,7 @@ uint32_t nve0_grhub_code[] = {
 /* 0x0660: main_not_ctx_switch */
 	0xf401e4b0,
 	0xf2b90d1b,
-	0x4221f502,
+	0x9a21f502,
 	0x460ef409,
 /* 0x0670: main_not_ctx_chan */
 	0xf402e4b0,
@@ -664,8 +664,8 @@ uint32_t nve0_grhub_code[] = {
 	0x09d00203,
 	0xf404bd00,
 	0x32f40132,
-	0xaa21f502,
-	0xf094bd09,
+	0x0221f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -710,18 +710,40 @@ uint32_t nve0_grhub_code[] = {
 /* 0x072b: ih_no_ctxsw */
 	0xe40421f4,
 	0xf40400ab,
-	0xb7f1140b,
+	0xe7f16c0b,
+	0xe3f00708,
+	0x6821f440,
+	0xf102ffb9,
+	0xf0040007,
+	0x0fd00203,
+	0xf104bd00,
+	0xf00704e7,
+	0x21f440e3,
+	0x02ffb968,
+	0x030007f1,
+	0xd00203f0,
+	0x04bd000f,
+	0x9450fec7,
+	0xf7f102ee,
+	0xf3f00700,
+	0x00efbb40,
+	0xf16821f4,
+	0xf0020007,
+	0x0fd00203,
+	0xf004bd00,
+	0x21f503f7,
+	0xb7f1037e,
 	0xbfb90100,
 	0x44e7f102,
 	0x40e3f001,
-/* 0x0743: ih_no_fwmthd */
+/* 0x079b: ih_no_fwmthd */
 	0xf19d21f4,
-	0xbd0104b7,
+	0xbd0504b7,
 	0xb4abffb0,
 	0xf10f0bf4,
 	0xf0070007,
 	0x0bd00303,
-/* 0x075b: ih_no_other */
+/* 0x07b3: ih_no_other */
 	0xf104bd00,
 	0xf0010007,
 	0x0ad00003,
@@ -731,19 +753,19 @@ uint32_t nve0_grhub_code[] = {
 	0xfc90fca0,
 	0x0088fe80,
 	0x32f480fc,
-/* 0x077f: ctx_4170s */
+/* 0x07d7: ctx_4170s */
 	0xf001f800,
 	0xffb910f5,
 	0x70e7f102,
 	0x40e3f041,
 	0xf89d21f4,
-/* 0x0791: ctx_4170w */
+/* 0x07e9: ctx_4170w */
 	0x70e7f100,
 	0x40e3f041,
 	0xb96821f4,
 	0xf4f002ff,
 	0xf01bf410,
-/* 0x07a6: ctx_redswitch */
+/* 0x07fe: ctx_redswitch */
 	0xe7f100f8,
 	0xe5f00200,
 	0x20e5f040,
@@ -751,7 +773,7 @@ uint32_t nve0_grhub_code[] = {
 	0xf0850007,
 	0x0ed00103,
 	0xf004bd00,
-/* 0x07c2: ctx_redswitch_delay */
+/* 0x081a: ctx_redswitch_delay */
 	0xf2b608f7,
 	0xfd1bf401,
 	0x0400e5f1,
@@ -759,7 +781,7 @@ uint32_t nve0_grhub_code[] = {
 	0x850007f1,
 	0xd00103f0,
 	0x04bd000e,
-/* 0x07de: ctx_86c */
+/* 0x0836: ctx_86c */
 	0x07f100f8,
 	0x03f01b00,
 	0x000fd002,
@@ -770,17 +792,17 @@ uint32_t nve0_grhub_code[] = {
 	0xe7f102ff,
 	0xe3f0a86c,
 	0x9d21f441,
-/* 0x0806: ctx_mem */
+/* 0x085e: ctx_mem */
 	0x07f100f8,
 	0x03f08400,
 	0x000fd002,
-/* 0x0812: ctx_mem_wait */
+/* 0x086a: ctx_mem_wait */
 	0xf7f104bd,
 	0xf3f08400,
 	0x00ffcf02,
 	0xf405fffd,
 	0x00f8f31b,
-/* 0x0824: ctx_load */
+/* 0x087c: ctx_load */
 	0x99f094bd,
 	0x0007f105,
 	0x0203f00f,
@@ -797,7 +819,7 @@ uint32_t nve0_grhub_code[] = {
 	0x0203f083,
 	0xbd0002d0,
 	0x07f7f004,
-	0x080621f5,
+	0x085e21f5,
 	0xc00007f1,
 	0xd00203f0,
 	0x04bd0002,
@@ -852,29 +874,29 @@ uint32_t nve0_grhub_code[] = {
 	0x170007f1,
 	0xd00203f0,
 	0x04bd0009,
-/* 0x0942: ctx_chan */
+/* 0x099a: ctx_chan */
 	0x21f500f8,
-	0xa7f00824,
+	0xa7f0087c,
 	0xd021f40c,
 	0xf505f7f0,
-	0xf8080621,
-/* 0x0955: ctx_mmio_exec */
+	0xf8085e21,
+/* 0x09ad: ctx_mmio_exec */
 	0x41039800,
 	0x810007f1,
 	0xd00203f0,
 	0x04bd0003,
-/* 0x0966: ctx_mmio_loop */
+/* 0x09be: ctx_mmio_loop */
 	0x34c434bd,
 	0x0f1bf4ff,
 	0x020057f1,
 	0xfa0653f0,
 	0x03f80535,
-/* 0x0978: ctx_mmio_pull */
+/* 0x09d0: ctx_mmio_pull */
 	0x98804e98,
 	0x21f4814f,
 	0x0830b69d,
 	0xf40112b6,
-/* 0x098a: ctx_mmio_done */
+/* 0x09e2: ctx_mmio_done */
 	0x0398df1b,
 	0x0007f116,
 	0x0203f081,
@@ -883,30 +905,30 @@ uint32_t nve0_grhub_code[] = {
 	0x010017f1,
 	0xfa0613f0,
 	0x03f80601,
-/* 0x09aa: ctx_xfer */
+/* 0x0a02: ctx_xfer */
 	0xe7f000f8,
 	0x0007f104,
 	0x0303f002,
 	0xbd000ed0,
-/* 0x09b9: ctx_xfer_idle */
+/* 0x0a11: ctx_xfer_idle */
 	0x00e7f104,
 	0x03e3f000,
 	0xf100eecf,
 	0xf42000e4,
 	0x11f4f21b,
 	0x0d02f406,
-/* 0x09d0: ctx_xfer_pre */
+/* 0x0a28: ctx_xfer_pre */
 	0xf510f7f0,
-	0xf407de21,
-/* 0x09da: ctx_xfer_pre_load */
+	0xf4083621,
+/* 0x0a32: ctx_xfer_pre_load */
 	0xf7f01c11,
-	0x7f21f502,
-	0x9121f507,
-	0xa621f507,
+	0xd721f502,
+	0xe921f507,
+	0xfe21f507,
 	0xf5f4bd07,
-	0xf5077f21,
-/* 0x09f3: ctx_xfer_exec */
-	0x98082421,
+	0xf507d721,
+/* 0x0a4b: ctx_xfer_exec */
+	0x98087c21,
 	0x24bd1601,
 	0x050007f1,
 	0xd00103f0,
@@ -941,21 +963,21 @@ uint32_t nve0_grhub_code[] = {
 	0xa7f01301,
 	0xd021f40c,
 	0xf505f7f0,
-	0xf4080621,
-/* 0x0a82: ctx_xfer_post */
+	0xf4085e21,
+/* 0x0ada: ctx_xfer_post */
 	0xf7f02e02,
-	0x7f21f502,
+	0xd721f502,
 	0xf5f4bd07,
-	0xf507de21,
+	0xf5083621,
 	0xf5027f21,
-	0xbd079121,
-	0x7f21f5f4,
+	0xbd07e921,
+	0xd721f5f4,
 	0x1011f407,
 	0xfd400198,
 	0x0bf40511,
-	0x5521f507,
-/* 0x0aad: ctx_xfer_no_post_mmio */
-/* 0x0aad: ctx_xfer_done */
+	0xad21f507,
+/* 0x0b05: ctx_xfer_no_post_mmio */
+/* 0x0b05: ctx_xfer_done */
 	0x0000f809,
 	0x00000000,
 	0x00000000,
@@ -977,4 +999,46 @@ uint32_t nve0_grhub_code[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 };
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvf0.fuc.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvf0.fuc.h
index a5aee5a4302..a0af4b703a8 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvf0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/hubnvf0.fuc.h
@@ -528,10 +528,10 @@ uint32_t nvf0_grhub_code[] = {
 	0x0001d001,
 	0x17f104bd,
 	0xf7f00100,
-	0x7f21f502,
-	0x9121f507,
+	0xd721f502,
+	0xe921f507,
 	0x10f7f007,
-	0x07de21f5,
+	0x083621f5,
 	0x98000e98,
 	0x21f5010f,
 	0x14950150,
@@ -574,9 +574,9 @@ uint32_t nvf0_grhub_code[] = {
 	0xb6800040,
 	0x1bf40132,
 	0x00f7f0be,
-	0x07de21f5,
+	0x083621f5,
 	0xf500f7f0,
-	0xf1077f21,
+	0xf107d721,
 	0xf0010007,
 	0x01d00203,
 	0xbd04bd00,
@@ -610,8 +610,8 @@ uint32_t nvf0_grhub_code[] = {
 	0x09d00203,
 	0xf404bd00,
 	0x31f40132,
-	0xaa21f502,
-	0xf094bd09,
+	0x0221f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -621,7 +621,7 @@ uint32_t nvf0_grhub_code[] = {
 	0x0203f037,
 	0xbd0009d0,
 	0x0131f404,
-	0x09aa21f5,
+	0x0a0221f5,
 	0x99f094bd,
 	0x0007f106,
 	0x0203f017,
@@ -631,7 +631,7 @@ uint32_t nvf0_grhub_code[] = {
 	0x12b920f9,
 	0x0132f402,
 	0xf50232f4,
-	0xfc09aa21,
+	0xfc0a0221,
 	0x0007f120,
 	0x0203f0c0,
 	0xbd0002d0,
@@ -640,7 +640,7 @@ uint32_t nvf0_grhub_code[] = {
 	0xf41f23c8,
 	0x31f40d0b,
 	0x0232f401,
-	0x09aa21f5,
+	0x0a0221f5,
 /* 0x063c: chsw_done */
 	0xf10127f0,
 	0xf0c30007,
@@ -654,7 +654,7 @@ uint32_t nvf0_grhub_code[] = {
 /* 0x0660: main_not_ctx_switch */
 	0xf401e4b0,
 	0xf2b90d1b,
-	0x4221f502,
+	0x9a21f502,
 	0x460ef409,
 /* 0x0670: main_not_ctx_chan */
 	0xf402e4b0,
@@ -664,8 +664,8 @@ uint32_t nvf0_grhub_code[] = {
 	0x09d00203,
 	0xf404bd00,
 	0x32f40132,
-	0xaa21f502,
-	0xf094bd09,
+	0x0221f502,
+	0xf094bd0a,
 	0x07f10799,
 	0x03f01700,
 	0x0009d002,
@@ -710,18 +710,40 @@ uint32_t nvf0_grhub_code[] = {
 /* 0x072b: ih_no_ctxsw */
 	0xe40421f4,
 	0xf40400ab,
-	0xb7f1140b,
+	0xe7f16c0b,
+	0xe3f00708,
+	0x6821f440,
+	0xf102ffb9,
+	0xf0040007,
+	0x0fd00203,
+	0xf104bd00,
+	0xf00704e7,
+	0x21f440e3,
+	0x02ffb968,
+	0x030007f1,
+	0xd00203f0,
+	0x04bd000f,
+	0x9450fec7,
+	0xf7f102ee,
+	0xf3f00700,
+	0x00efbb40,
+	0xf16821f4,
+	0xf0020007,
+	0x0fd00203,
+	0xf004bd00,
+	0x21f503f7,
+	0xb7f1037e,
 	0xbfb90100,
 	0x44e7f102,
 	0x40e3f001,
-/* 0x0743: ih_no_fwmthd */
+/* 0x079b: ih_no_fwmthd */
 	0xf19d21f4,
-	0xbd0104b7,
+	0xbd0504b7,
 	0xb4abffb0,
 	0xf10f0bf4,
 	0xf0070007,
 	0x0bd00303,
-/* 0x075b: ih_no_other */
+/* 0x07b3: ih_no_other */
 	0xf104bd00,
 	0xf0010007,
 	0x0ad00003,
@@ -731,19 +753,19 @@ uint32_t nvf0_grhub_code[] = {
 	0xfc90fca0,
 	0x0088fe80,
 	0x32f480fc,
-/* 0x077f: ctx_4170s */
+/* 0x07d7: ctx_4170s */
 	0xf001f800,
 	0xffb910f5,
 	0x70e7f102,
 	0x40e3f041,
 	0xf89d21f4,
-/* 0x0791: ctx_4170w */
+/* 0x07e9: ctx_4170w */
 	0x70e7f100,
 	0x40e3f041,
 	0xb96821f4,
 	0xf4f002ff,
 	0xf01bf410,
-/* 0x07a6: ctx_redswitch */
+/* 0x07fe: ctx_redswitch */
 	0xe7f100f8,
 	0xe5f00200,
 	0x20e5f040,
@@ -751,7 +773,7 @@ uint32_t nvf0_grhub_code[] = {
 	0xf0850007,
 	0x0ed00103,
 	0xf004bd00,
-/* 0x07c2: ctx_redswitch_delay */
+/* 0x081a: ctx_redswitch_delay */
 	0xf2b608f7,
 	0xfd1bf401,
 	0x0400e5f1,
@@ -759,7 +781,7 @@ uint32_t nvf0_grhub_code[] = {
 	0x850007f1,
 	0xd00103f0,
 	0x04bd000e,
-/* 0x07de: ctx_86c */
+/* 0x0836: ctx_86c */
 	0x07f100f8,
 	0x03f02300,
 	0x000fd002,
@@ -770,17 +792,17 @@ uint32_t nvf0_grhub_code[] = {
 	0xe7f102ff,
 	0xe3f0a88c,
 	0x9d21f441,
-/* 0x0806: ctx_mem */
+/* 0x085e: ctx_mem */
 	0x07f100f8,
 	0x03f08400,
 	0x000fd002,
-/* 0x0812: ctx_mem_wait */
+/* 0x086a: ctx_mem_wait */
 	0xf7f104bd,
 	0xf3f08400,
 	0x00ffcf02,
 	0xf405fffd,
 	0x00f8f31b,
-/* 0x0824: ctx_load */
+/* 0x087c: ctx_load */
 	0x99f094bd,
 	0x0007f105,
 	0x0203f037,
@@ -797,7 +819,7 @@ uint32_t nvf0_grhub_code[] = {
 	0x0203f083,
 	0xbd0002d0,
 	0x07f7f004,
-	0x080621f5,
+	0x085e21f5,
 	0xc00007f1,
 	0xd00203f0,
 	0x04bd0002,
@@ -852,29 +874,29 @@ uint32_t nvf0_grhub_code[] = {
 	0x170007f1,
 	0xd00203f0,
 	0x04bd0009,
-/* 0x0942: ctx_chan */
+/* 0x099a: ctx_chan */
 	0x21f500f8,
-	0xa7f00824,
+	0xa7f0087c,
 	0xd021f40c,
 	0xf505f7f0,
-	0xf8080621,
-/* 0x0955: ctx_mmio_exec */
+	0xf8085e21,
+/* 0x09ad: ctx_mmio_exec */
 	0x41039800,
 	0x810007f1,
 	0xd00203f0,
 	0x04bd0003,
-/* 0x0966: ctx_mmio_loop */
+/* 0x09be: ctx_mmio_loop */
 	0x34c434bd,
 	0x0f1bf4ff,
 	0x020057f1,
 	0xfa0653f0,
 	0x03f80535,
-/* 0x0978: ctx_mmio_pull */
+/* 0x09d0: ctx_mmio_pull */
 	0x98804e98,
 	0x21f4814f,
 	0x0830b69d,
 	0xf40112b6,
-/* 0x098a: ctx_mmio_done */
+/* 0x09e2: ctx_mmio_done */
 	0x0398df1b,
 	0x0007f116,
 	0x0203f081,
@@ -883,30 +905,30 @@ uint32_t nvf0_grhub_code[] = {
 	0x010017f1,
 	0xfa0613f0,
 	0x03f80601,
-/* 0x09aa: ctx_xfer */
+/* 0x0a02: ctx_xfer */
 	0xe7f000f8,
 	0x0007f104,
 	0x0303f002,
 	0xbd000ed0,
-/* 0x09b9: ctx_xfer_idle */
+/* 0x0a11: ctx_xfer_idle */
 	0x00e7f104,
 	0x03e3f000,
 	0xf100eecf,
 	0xf42000e4,
 	0x11f4f21b,
 	0x0d02f406,
-/* 0x09d0: ctx_xfer_pre */
+/* 0x0a28: ctx_xfer_pre */
 	0xf510f7f0,
-	0xf407de21,
-/* 0x09da: ctx_xfer_pre_load */
+	0xf4083621,
+/* 0x0a32: ctx_xfer_pre_load */
 	0xf7f01c11,
-	0x7f21f502,
-	0x9121f507,
-	0xa621f507,
+	0xd721f502,
+	0xe921f507,
+	0xfe21f507,
 	0xf5f4bd07,
-	0xf5077f21,
-/* 0x09f3: ctx_xfer_exec */
-	0x98082421,
+	0xf507d721,
+/* 0x0a4b: ctx_xfer_exec */
+	0x98087c21,
 	0x24bd1601,
 	0x050007f1,
 	0xd00103f0,
@@ -941,21 +963,21 @@ uint32_t nvf0_grhub_code[] = {
 	0xa7f01301,
 	0xd021f40c,
 	0xf505f7f0,
-	0xf4080621,
-/* 0x0a82: ctx_xfer_post */
+	0xf4085e21,
+/* 0x0ada: ctx_xfer_post */
 	0xf7f02e02,
-	0x7f21f502,
+	0xd721f502,
 	0xf5f4bd07,
-	0xf507de21,
+	0xf5083621,
 	0xf5027f21,
-	0xbd079121,
-	0x7f21f5f4,
+	0xbd07e921,
+	0xd721f5f4,
 	0x1011f407,
 	0xfd400198,
 	0x0bf40511,
-	0x5521f507,
-/* 0x0aad: ctx_xfer_no_post_mmio */
-/* 0x0aad: ctx_xfer_done */
+	0xad21f507,
+/* 0x0b05: ctx_xfer_no_post_mmio */
+/* 0x0b05: ctx_xfer_done */
 	0x0000f809,
 	0x00000000,
 	0x00000000,
@@ -977,4 +999,46 @@ uint32_t nvf0_grhub_code[] = {
 	0x00000000,
 	0x00000000,
 	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
 };
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/macros.fuc b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/macros.fuc
index a47d49db523..2a0b0f84429 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/macros.fuc
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/macros.fuc
@@ -30,6 +30,12 @@
 #define GK110 0xf0
 #define GK208 0x108
 
+#define NV_PGRAPH_TRAPPED_ADDR                                         0x400704
+#define NV_PGRAPH_TRAPPED_DATA_LO                                      0x400708
+#define NV_PGRAPH_TRAPPED_DATA_HI                                      0x40070c
+
+#define NV_PGRAPH_FE_OBJECT_TABLE(n)                        ((n) * 4 + 0x400700)
+
 #define NV_PGRAPH_FECS_INTR_ACK                                        0x409004
 #define NV_PGRAPH_FECS_INTR                                            0x409008
 #define NV_PGRAPH_FECS_INTR_FWMTHD                                   0x00000400
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/os.h b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/os.h
index fd1d380de09..1718ae4e822 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/fuc/os.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/fuc/os.h
@@ -3,5 +3,6 @@
 
 #define E_BAD_COMMAND  0x00000001
 #define E_CMD_OVERFLOW 0x00000002
+#define E_BAD_FWMTHD   0x00000003
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/gk20a.c b/drivers/gpu/drm/nouveau/core/engine/graph/gk20a.c
new file mode 100644
index 00000000000..83048a56430
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/gk20a.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#include "nvc0.h"
+#include "ctxnvc0.h"
+
+static struct nouveau_oclass
+gk20a_graph_sclass[] = {
+	{ 0x902d, &nouveau_object_ofuncs },
+	{ 0xa040, &nouveau_object_ofuncs },
+	{ 0xa297, &nouveau_object_ofuncs },
+	{ 0xa0c0, &nouveau_object_ofuncs },
+	{}
+};
+
+struct nouveau_oclass *
+gk20a_graph_oclass = &(struct nvc0_graph_oclass) {
+	.base.handle = NV_ENGINE(GR, 0xea),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = nvc0_graph_ctor,
+		.dtor = nvc0_graph_dtor,
+		.init = nve4_graph_init,
+		.fini = nve4_graph_fini,
+	},
+	.cclass = &gk20a_grctx_oclass,
+	.sclass = gk20a_graph_sclass,
+	.mmio = nve4_graph_pack_mmio,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
index 2c7809e1a09..20665c21d80 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
@@ -901,7 +901,7 @@ nv50_graph_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 		nv_engine(priv)->sclass = nvaf_graph_sclass;
 		break;
 
-	};
+	}
 
 	/* unfortunate hw bug workaround... */
 	if (nv_device(priv)->chipset != 0x50 &&
@@ -976,7 +976,6 @@ nv50_graph_init(struct nouveau_object *object)
 		break;
 	case 0xa0:
 	default:
-		nv_wr32(priv, 0x402cc0, 0x00000000);
 		if (nv_device(priv)->chipset == 0xa0 ||
 		    nv_device(priv)->chipset == 0xaa ||
 		    nv_device(priv)->chipset == 0xac) {
@@ -991,10 +990,10 @@ nv50_graph_init(struct nouveau_object *object)
 
 	/* zero out zcull regions */
 	for (i = 0; i < 8; i++) {
-		nv_wr32(priv, 0x402c20 + (i * 8), 0x00000000);
-		nv_wr32(priv, 0x402c24 + (i * 8), 0x00000000);
-		nv_wr32(priv, 0x402c28 + (i * 8), 0x00000000);
-		nv_wr32(priv, 0x402c2c + (i * 8), 0x00000000);
+		nv_wr32(priv, 0x402c20 + (i * 0x10), 0x00000000);
+		nv_wr32(priv, 0x402c24 + (i * 0x10), 0x00000000);
+		nv_wr32(priv, 0x402c28 + (i * 0x10), 0x00000000);
+		nv_wr32(priv, 0x402c2c + (i * 0x10), 0x00000000);
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
index f3c7329da0a..aa083891635 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
@@ -789,17 +789,40 @@ nvc0_graph_ctxctl_debug(struct nvc0_graph_priv *priv)
 static void
 nvc0_graph_ctxctl_isr(struct nvc0_graph_priv *priv)
 {
-	u32 ustat = nv_rd32(priv, 0x409c18);
+	u32 stat = nv_rd32(priv, 0x409c18);
 
-	if (ustat & 0x00000001)
-		nv_error(priv, "CTXCTL ucode error\n");
-	if (ustat & 0x00080000)
-		nv_error(priv, "CTXCTL watchdog timeout\n");
-	if (ustat & ~0x00080001)
-		nv_error(priv, "CTXCTL 0x%08x\n", ustat);
+	if (stat & 0x00000001) {
+		u32 code = nv_rd32(priv, 0x409814);
+		if (code == E_BAD_FWMTHD) {
+			u32 class = nv_rd32(priv, 0x409808);
+			u32  addr = nv_rd32(priv, 0x40980c);
+			u32  subc = (addr & 0x00070000) >> 16;
+			u32  mthd = (addr & 0x00003ffc);
+			u32  data = nv_rd32(priv, 0x409810);
+
+			nv_error(priv, "FECS MTHD subc %d class 0x%04x "
+				       "mthd 0x%04x data 0x%08x\n",
+				 subc, class, mthd, data);
+
+			nv_wr32(priv, 0x409c20, 0x00000001);
+			stat &= ~0x00000001;
+		} else {
+			nv_error(priv, "FECS ucode error %d\n", code);
+		}
+	}
 
-	nvc0_graph_ctxctl_debug(priv);
-	nv_wr32(priv, 0x409c20, ustat);
+	if (stat & 0x00080000) {
+		nv_error(priv, "FECS watchdog timeout\n");
+		nvc0_graph_ctxctl_debug(priv);
+		nv_wr32(priv, 0x409c20, 0x00080000);
+		stat &= ~0x00080000;
+	}
+
+	if (stat) {
+		nv_error(priv, "FECS 0x%08x\n", stat);
+		nvc0_graph_ctxctl_debug(priv);
+		nv_wr32(priv, 0x409c20, stat);
+	}
 }
 
 static void
@@ -894,6 +917,10 @@ nvc0_graph_init_fw(struct nvc0_graph_priv *priv, u32 fuc_base,
 			nv_wr32(priv, fuc_base + 0x0188, i >> 6);
 		nv_wr32(priv, fuc_base + 0x0184, code->data[i]);
 	}
+
+	/* code must be padded to 0x40 words */
+	for (; i & 0x3f; i++)
+		nv_wr32(priv, fuc_base + 0x0184, 0);
 }
 
 static void
@@ -1259,10 +1286,14 @@ nvc0_graph_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nvc0_graph_oclass *oclass = (void *)bclass;
 	struct nouveau_device *device = nv_device(parent);
 	struct nvc0_graph_priv *priv;
+	bool use_ext_fw, enable;
 	int ret, i;
 
-	ret = nouveau_graph_create(parent, engine, bclass,
-				   (oclass->fecs.ucode != NULL), &priv);
+	use_ext_fw = nouveau_boolopt(device->cfgopt, "NvGrUseFW",
+				     oclass->fecs.ucode == NULL);
+	enable = use_ext_fw || oclass->fecs.ucode != NULL;
+
+	ret = nouveau_graph_create(parent, engine, bclass, enable, &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
@@ -1272,7 +1303,7 @@ nvc0_graph_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 
 	priv->base.units = nvc0_graph_units;
 
-	if (nouveau_boolopt(device->cfgopt, "NvGrUseFW", false)) {
+	if (use_ext_fw) {
 		nv_info(priv, "using external firmware\n");
 		if (nvc0_graph_ctor_fw(priv, "fuc409c", &priv->fuc409c) ||
 		    nvc0_graph_ctor_fw(priv, "fuc409d", &priv->fuc409d) ||
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.h b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.h
index 90d44616c87..ffc289198dd 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.h
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.h
@@ -38,6 +38,8 @@
 #include <engine/fifo.h>
 #include <engine/graph.h>
 
+#include "fuc/os.h"
+
 #define GPC_MAX 32
 #define TPC_MAX (GPC_MAX * 8)
 
@@ -116,6 +118,7 @@ int  nvc0_graph_ctor(struct nouveau_object *, struct nouveau_object *,
 		     struct nouveau_object **);
 void nvc0_graph_dtor(struct nouveau_object *);
 int  nvc0_graph_init(struct nouveau_object *);
+int  nve4_graph_fini(struct nouveau_object *, bool);
 int  nve4_graph_init(struct nouveau_object *);
 
 extern struct nouveau_oclass nvc0_graph_sclass[];
@@ -217,6 +220,7 @@ extern const struct nvc0_graph_init nve4_graph_init_main_0[];
 extern const struct nvc0_graph_init nve4_graph_init_tpccs_0[];
 extern const struct nvc0_graph_init nve4_graph_init_pe_0[];
 extern const struct nvc0_graph_init nve4_graph_init_be_0[];
+extern const struct nvc0_graph_pack nve4_graph_pack_mmio[];
 
 extern const struct nvc0_graph_init nvf0_graph_init_fe_0[];
 extern const struct nvc0_graph_init nvf0_graph_init_sked_0[];
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nve4.c b/drivers/gpu/drm/nouveau/core/engine/graph/nve4.c
index f7c01121717..51e0c075ad3 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nve4.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nve4.c
@@ -151,7 +151,7 @@ nve4_graph_init_be_0[] = {
 	{}
 };
 
-static const struct nvc0_graph_pack
+const struct nvc0_graph_pack
 nve4_graph_pack_mmio[] = {
 	{ nve4_graph_init_main_0 },
 	{ nvc0_graph_init_fe_0 },
@@ -189,7 +189,7 @@ nve4_graph_pack_mmio[] = {
  * PGRAPH engine/subdev functions
  ******************************************************************************/
 
-static int
+int
 nve4_graph_fini(struct nouveau_object *object, bool suspend)
 {
 	struct nvc0_graph_priv *priv = (void *)object;
diff --git a/drivers/gpu/drm/nouveau/core/engine/software/nv50.c b/drivers/gpu/drm/nouveau/core/engine/software/nv50.c
index 5ce686ee729..f3b4d9dbf23 100644
--- a/drivers/gpu/drm/nouveau/core/engine/software/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/software/nv50.c
@@ -124,7 +124,7 @@ nv50_software_sclass[] = {
  ******************************************************************************/
 
 static int
-nv50_software_vblsem_release(void *data, int head)
+nv50_software_vblsem_release(void *data, u32 type, int head)
 {
 	struct nv50_software_chan *chan = data;
 	struct nv50_software_priv *priv = (void *)nv_object(chan)->engine;
@@ -183,7 +183,7 @@ nv50_software_context_ctor(struct nouveau_object *parent,
 		return -ENOMEM;
 
 	for (i = 0; i < chan->vblank.nr_event; i++) {
-		ret = nouveau_event_new(pdisp->vblank, i, pclass->vblank,
+		ret = nouveau_event_new(pdisp->vblank, 1, i, pclass->vblank,
 					chan, &chan->vblank.event[i]);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/nouveau/core/engine/software/nv50.h b/drivers/gpu/drm/nouveau/core/engine/software/nv50.h
index 2de370c2127..bb49a7a2085 100644
--- a/drivers/gpu/drm/nouveau/core/engine/software/nv50.h
+++ b/drivers/gpu/drm/nouveau/core/engine/software/nv50.h
@@ -19,7 +19,7 @@ int  nv50_software_ctor(struct nouveau_object *, struct nouveau_object *,
 
 struct nv50_software_cclass {
 	struct nouveau_oclass base;
-	int (*vblank)(void *, int);
+	int (*vblank)(void *, u32, int);
 };
 
 struct nv50_software_chan {
diff --git a/drivers/gpu/drm/nouveau/core/engine/software/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/software/nvc0.c
index f9430c1bf3e..135c20f3835 100644
--- a/drivers/gpu/drm/nouveau/core/engine/software/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/software/nvc0.c
@@ -104,7 +104,7 @@ nvc0_software_sclass[] = {
  ******************************************************************************/
 
 static int
-nvc0_software_vblsem_release(void *data, int head)
+nvc0_software_vblsem_release(void *data, u32 type, int head)
 {
 	struct nv50_software_chan *chan = data;
 	struct nv50_software_priv *priv = (void *)nv_object(chan)->engine;
diff --git a/drivers/gpu/drm/nouveau/core/include/core/class.h b/drivers/gpu/drm/nouveau/core/include/core/class.h
index 9c0cd73462d..e0c812bc884 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/class.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/class.h
@@ -295,6 +295,10 @@ struct nv04_display_scanoutpos {
 #define NV84_DISP_SOR_HDMI_PWR_REKEY                                 0x0000007f
 #define NV50_DISP_SOR_LVDS_SCRIPT                                    0x00013000
 #define NV50_DISP_SOR_LVDS_SCRIPT_ID                                 0x0000ffff
+#define NV94_DISP_SOR_DP_PWR                                         0x00016000
+#define NV94_DISP_SOR_DP_PWR_STATE                                   0x00000001
+#define NV94_DISP_SOR_DP_PWR_STATE_OFF                               0x00000000
+#define NV94_DISP_SOR_DP_PWR_STATE_ON                                0x00000001
 
 #define NV50_DISP_DAC_MTHD                                           0x00020000
 #define NV50_DISP_DAC_MTHD_TYPE                                      0x0000f000
diff --git a/drivers/gpu/drm/nouveau/core/include/core/event.h b/drivers/gpu/drm/nouveau/core/include/core/event.h
index 5d539ebff3e..ba3f1a76a81 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/event.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/event.h
@@ -12,32 +12,33 @@ struct nouveau_eventh {
 	struct nouveau_event *event;
 	struct list_head head;
 	unsigned long flags;
+	u32 types;
 	int index;
-	int (*func)(void *, int);
+	int (*func)(void *, u32, int);
 	void *priv;
 };
 
 struct nouveau_event {
-	spinlock_t list_lock;
-	spinlock_t refs_lock;
-
 	void *priv;
-	void (*enable)(struct nouveau_event *, int index);
-	void (*disable)(struct nouveau_event *, int index);
+	int (*check)(struct nouveau_event *, u32 type, int index);
+	void (*enable)(struct nouveau_event *, int type, int index);
+	void (*disable)(struct nouveau_event *, int type, int index);
 
+	int types_nr;
 	int index_nr;
-	struct {
-		struct list_head list;
-		int refs;
-	} index[];
+
+	spinlock_t list_lock;
+	struct list_head *list;
+	spinlock_t refs_lock;
+	int refs[];
 };
 
-int  nouveau_event_create(int index_nr, struct nouveau_event **);
+int  nouveau_event_create(int types_nr, int index_nr, struct nouveau_event **);
 void nouveau_event_destroy(struct nouveau_event **);
-void nouveau_event_trigger(struct nouveau_event *, int index);
+void nouveau_event_trigger(struct nouveau_event *, u32 types, int index);
 
-int  nouveau_event_new(struct nouveau_event *, int index,
-		       int (*func)(void *, int), void *,
+int  nouveau_event_new(struct nouveau_event *, u32 types, int index,
+		       int (*func)(void *, u32, int), void *,
 		       struct nouveau_eventh **);
 void nouveau_event_ref(struct nouveau_eventh *, struct nouveau_eventh **);
 void nouveau_event_get(struct nouveau_eventh *);
diff --git a/drivers/gpu/drm/nouveau/core/include/engine/disp.h b/drivers/gpu/drm/nouveau/core/include/engine/disp.h
index fd0c68804de..fde84289680 100644
--- a/drivers/gpu/drm/nouveau/core/include/engine/disp.h
+++ b/drivers/gpu/drm/nouveau/core/include/engine/disp.h
@@ -6,8 +6,19 @@
 #include <core/device.h>
 #include <core/event.h>
 
+enum nvkm_hpd_event {
+	NVKM_HPD_PLUG = 1,
+	NVKM_HPD_UNPLUG = 2,
+	NVKM_HPD_IRQ = 4,
+	NVKM_HPD = (NVKM_HPD_PLUG | NVKM_HPD_UNPLUG | NVKM_HPD_IRQ)
+};
+
 struct nouveau_disp {
 	struct nouveau_engine base;
+
+	struct list_head outp;
+	struct nouveau_event *hpd;
+
 	struct nouveau_event *vblank;
 };
 
@@ -17,25 +28,6 @@ nouveau_disp(void *obj)
 	return (void *)nv_device(obj)->subdev[NVDEV_ENGINE_DISP];
 }
 
-#define nouveau_disp_create(p,e,c,h,i,x,d)                                     \
-	nouveau_disp_create_((p), (e), (c), (h), (i), (x),                     \
-			     sizeof(**d), (void **)d)
-#define nouveau_disp_destroy(d) ({                                             \
-	struct nouveau_disp *disp = (d);                                       \
-	_nouveau_disp_dtor(nv_object(disp));                                   \
-})
-#define nouveau_disp_init(d)                                                   \
-	nouveau_engine_init(&(d)->base)
-#define nouveau_disp_fini(d,s)                                                 \
-	nouveau_engine_fini(&(d)->base, (s))
-
-int  nouveau_disp_create_(struct nouveau_object *, struct nouveau_object *,
-			  struct nouveau_oclass *, int heads,
-			  const char *, const char *, int, void **);
-void _nouveau_disp_dtor(struct nouveau_object *);
-#define _nouveau_disp_init _nouveau_engine_init
-#define _nouveau_disp_fini _nouveau_engine_fini
-
 extern struct nouveau_oclass *nv04_disp_oclass;
 extern struct nouveau_oclass *nv50_disp_oclass;
 extern struct nouveau_oclass *nv84_disp_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/include/engine/fifo.h b/drivers/gpu/drm/nouveau/core/include/engine/fifo.h
index 26b6b2bb111..b639eb2c74f 100644
--- a/drivers/gpu/drm/nouveau/core/include/engine/fifo.h
+++ b/drivers/gpu/drm/nouveau/core/include/engine/fifo.h
@@ -109,6 +109,7 @@ extern struct nouveau_oclass *nv50_fifo_oclass;
 extern struct nouveau_oclass *nv84_fifo_oclass;
 extern struct nouveau_oclass *nvc0_fifo_oclass;
 extern struct nouveau_oclass *nve0_fifo_oclass;
+extern struct nouveau_oclass *gk20a_fifo_oclass;
 extern struct nouveau_oclass *nv108_fifo_oclass;
 
 void nv04_fifo_intr(struct nouveau_subdev *);
diff --git a/drivers/gpu/drm/nouveau/core/include/engine/graph.h b/drivers/gpu/drm/nouveau/core/include/engine/graph.h
index 871edfdf3d5..8c1d4772da0 100644
--- a/drivers/gpu/drm/nouveau/core/include/engine/graph.h
+++ b/drivers/gpu/drm/nouveau/core/include/engine/graph.h
@@ -68,6 +68,7 @@ extern struct nouveau_oclass *nvc8_graph_oclass;
 extern struct nouveau_oclass *nvd7_graph_oclass;
 extern struct nouveau_oclass *nvd9_graph_oclass;
 extern struct nouveau_oclass *nve4_graph_oclass;
+extern struct nouveau_oclass *gk20a_graph_oclass;
 extern struct nouveau_oclass *nvf0_graph_oclass;
 extern struct nouveau_oclass *nv108_graph_oclass;
 extern struct nouveau_oclass *gm107_graph_oclass;
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bios/conn.h b/drivers/gpu/drm/nouveau/core/include/subdev/bios/conn.h
index a32feb3f3fb..f3930c27cb7 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/bios/conn.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/bios/conn.h
@@ -22,7 +22,25 @@ enum dcb_connector_type {
 	DCB_CONNECTOR_NONE = 0xff
 };
 
-u16 dcb_conntab(struct nouveau_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len);
-u16 dcb_conn(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len);
+struct nvbios_connT {
+};
+
+u32 nvbios_connTe(struct nouveau_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len);
+u32 nvbios_connTp(struct nouveau_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+		  struct nvbios_connT *info);
+
+struct nvbios_connE {
+	u8 type;
+	u8 location;
+	u8 hpd;
+	u8 dp;
+	u8 di;
+	u8 sr;
+	u8 lcdid;
+};
+
+u32 nvbios_connEe(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *hdr);
+u32 nvbios_connEp(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *hdr,
+		  struct nvbios_connE *info);
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/bios/dp.h b/drivers/gpu/drm/nouveau/core/include/subdev/bios/dp.h
index 6e54218b55f..728206e2177 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/bios/dp.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/bios/dp.h
@@ -17,9 +17,10 @@ u16 nvbios_dpout_match(struct nouveau_bios *, u16 type, u16 mask,
 		       struct nvbios_dpout *);
 
 struct nvbios_dpcfg {
-	u8 drv;
-	u8 pre;
-	u8 unk;
+	u8 pc;
+	u8 dc;
+	u8 pe;
+	u8 tx_pu;
 };
 
 u16
@@ -27,7 +28,7 @@ nvbios_dpcfg_parse(struct nouveau_bios *, u16 outp, u8 idx,
 		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
 		   struct nvbios_dpcfg *);
 u16
-nvbios_dpcfg_match(struct nouveau_bios *, u16 outp, u8 un, u8 vs, u8 pe,
+nvbios_dpcfg_match(struct nouveau_bios *, u16 outp, u8 pc, u8 vs, u8 pe,
 		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
 		   struct nvbios_dpcfg *);
 
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/clock.h b/drivers/gpu/drm/nouveau/core/include/subdev/clock.h
index 8f4ced75444..c01e29c9f89 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/clock.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/clock.h
@@ -77,6 +77,8 @@ struct nouveau_clock {
 	int tstate; /* thermal adjustment (max-) */
 	int dstate; /* display adjustment (min+) */
 
+	bool allow_reclock;
+
 	int  (*read)(struct nouveau_clock *, enum nv_clk_src);
 	int  (*calc)(struct nouveau_clock *, struct nouveau_cstate *);
 	int  (*prog)(struct nouveau_clock *);
@@ -106,8 +108,8 @@ struct nouveau_clocks {
 	int mdiv;
 };
 
-#define nouveau_clock_create(p,e,o,i,d)                                        \
-	nouveau_clock_create_((p), (e), (o), (i), sizeof(**d), (void **)d)
+#define nouveau_clock_create(p,e,o,i,r,d)                                      \
+	nouveau_clock_create_((p), (e), (o), (i), (r), sizeof(**d), (void **)d)
 #define nouveau_clock_destroy(p) ({                                            \
 	struct nouveau_clock *clk = (p);                                       \
 	_nouveau_clock_dtor(nv_object(clk));                                   \
@@ -121,7 +123,7 @@ struct nouveau_clocks {
 
 int  nouveau_clock_create_(struct nouveau_object *, struct nouveau_object *,
 			   struct nouveau_oclass *,
-			   struct nouveau_clocks *, int, void **);
+			   struct nouveau_clocks *, bool, int, void **);
 void _nouveau_clock_dtor(struct nouveau_object *);
 int _nouveau_clock_init(struct nouveau_object *);
 #define _nouveau_clock_fini _nouveau_subdev_fini
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
index 58c7ccdebb0..871e73914b2 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
@@ -105,6 +105,7 @@ extern struct nouveau_oclass *nvaa_fb_oclass;
 extern struct nouveau_oclass *nvaf_fb_oclass;
 extern struct nouveau_oclass *nvc0_fb_oclass;
 extern struct nouveau_oclass *nve0_fb_oclass;
+extern struct nouveau_oclass *gk20a_fb_oclass;
 extern struct nouveau_oclass *gm107_fb_oclass;
 
 #include <subdev/bios/ramcfg.h>
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/gpio.h b/drivers/gpu/drm/nouveau/core/include/subdev/gpio.h
index c85b9f1579a..612d82ab683 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/gpio.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/gpio.h
@@ -8,17 +8,18 @@
 #include <subdev/bios.h>
 #include <subdev/bios/gpio.h>
 
+enum nvkm_gpio_event {
+	NVKM_GPIO_HI = 1,
+	NVKM_GPIO_LO = 2,
+	NVKM_GPIO_TOGGLED = (NVKM_GPIO_HI | NVKM_GPIO_LO),
+};
+
 struct nouveau_gpio {
 	struct nouveau_subdev base;
 
 	struct nouveau_event *events;
 
-	/* hardware interfaces */
 	void (*reset)(struct nouveau_gpio *, u8 func);
-	int  (*drive)(struct nouveau_gpio *, int line, int dir, int out);
-	int  (*sense)(struct nouveau_gpio *, int line);
-
-	/* software interfaces */
 	int  (*find)(struct nouveau_gpio *, int idx, u8 tag, u8 line,
 		     struct dcb_gpio_func *);
 	int  (*set)(struct nouveau_gpio *, int idx, u8 tag, u8 line, int state);
@@ -31,23 +32,10 @@ nouveau_gpio(void *obj)
 	return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_GPIO];
 }
 
-#define nouveau_gpio_create(p,e,o,l,d)                                         \
-	nouveau_gpio_create_((p), (e), (o), (l), sizeof(**d), (void **)d)
-#define nouveau_gpio_destroy(p) ({                                             \
-	struct nouveau_gpio *gpio = (p);                                       \
-	_nouveau_gpio_dtor(nv_object(gpio));                                   \
-})
-#define nouveau_gpio_fini(p,s)                                                 \
-	nouveau_subdev_fini(&(p)->base, (s))
-
-int  nouveau_gpio_create_(struct nouveau_object *, struct nouveau_object *,
-			  struct nouveau_oclass *, int, int, void **);
-void _nouveau_gpio_dtor(struct nouveau_object *);
-int  nouveau_gpio_init(struct nouveau_gpio *);
-
-extern struct nouveau_oclass nv10_gpio_oclass;
-extern struct nouveau_oclass nv50_gpio_oclass;
-extern struct nouveau_oclass nvd0_gpio_oclass;
-extern struct nouveau_oclass nve0_gpio_oclass;
+extern struct nouveau_oclass *nv10_gpio_oclass;
+extern struct nouveau_oclass *nv50_gpio_oclass;
+extern struct nouveau_oclass *nv92_gpio_oclass;
+extern struct nouveau_oclass *nvd0_gpio_oclass;
+extern struct nouveau_oclass *nve0_gpio_oclass;
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h b/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
index 7f50a858b16..825f7bb46b6 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
@@ -14,52 +14,41 @@
 #define NV_I2C_TYPE_EXTDDC(e) (0x0005 | (e) << 8)
 #define NV_I2C_TYPE_EXTAUX(e) (0x0006 | (e) << 8)
 
+enum nvkm_i2c_event {
+	NVKM_I2C_PLUG = 1,
+	NVKM_I2C_UNPLUG = 2,
+	NVKM_I2C_IRQ = 4,
+	NVKM_I2C_DONE = 8,
+	NVKM_I2C_ANY = (NVKM_I2C_PLUG |
+			NVKM_I2C_UNPLUG |
+			NVKM_I2C_IRQ |
+			NVKM_I2C_DONE),
+};
+
 struct nouveau_i2c_port {
 	struct nouveau_object base;
 	struct i2c_adapter adapter;
+	struct mutex mutex;
 
 	struct list_head head;
 	u8  index;
+	int aux;
 
 	const struct nouveau_i2c_func *func;
 };
 
 struct nouveau_i2c_func {
-	void (*acquire)(struct nouveau_i2c_port *);
-	void (*release)(struct nouveau_i2c_port *);
-
 	void (*drive_scl)(struct nouveau_i2c_port *, int);
 	void (*drive_sda)(struct nouveau_i2c_port *, int);
 	int  (*sense_scl)(struct nouveau_i2c_port *);
 	int  (*sense_sda)(struct nouveau_i2c_port *);
 
-	int  (*aux)(struct nouveau_i2c_port *, u8, u32, u8 *, u8);
+	int  (*aux)(struct nouveau_i2c_port *, bool, u8, u32, u8 *, u8);
 	int  (*pattern)(struct nouveau_i2c_port *, int pattern);
 	int  (*lnk_ctl)(struct nouveau_i2c_port *, int nr, int bw, bool enh);
 	int  (*drv_ctl)(struct nouveau_i2c_port *, int lane, int sw, int pe);
 };
 
-#define nouveau_i2c_port_create(p,e,o,i,a,f,d)                                 \
-	nouveau_i2c_port_create_((p), (e), (o), (i), (a), (f),                 \
-				 sizeof(**d), (void **)d)
-#define nouveau_i2c_port_destroy(p) ({                                         \
-	struct nouveau_i2c_port *port = (p);                                   \
-	_nouveau_i2c_port_dtor(nv_object(i2c));                                \
-})
-#define nouveau_i2c_port_init(p)                                               \
-	nouveau_object_init(&(p)->base)
-#define nouveau_i2c_port_fini(p,s)                                             \
-	nouveau_object_fini(&(p)->base, (s))
-
-int nouveau_i2c_port_create_(struct nouveau_object *, struct nouveau_object *,
-			     struct nouveau_oclass *, u8,
-			     const struct i2c_algorithm *,
-			     const struct nouveau_i2c_func *,
-			     int, void **);
-void _nouveau_i2c_port_dtor(struct nouveau_object *);
-#define _nouveau_i2c_port_init nouveau_object_init
-#define _nouveau_i2c_port_fini nouveau_object_fini
-
 struct nouveau_i2c_board_info {
 	struct i2c_board_info dev;
 	u8 udelay; /* set to 0 to use the standard delay */
@@ -67,13 +56,20 @@ struct nouveau_i2c_board_info {
 
 struct nouveau_i2c {
 	struct nouveau_subdev base;
+	struct nouveau_event *ntfy;
 
 	struct nouveau_i2c_port *(*find)(struct nouveau_i2c *, u8 index);
 	struct nouveau_i2c_port *(*find_type)(struct nouveau_i2c *, u16 type);
+	int  (*acquire_pad)(struct nouveau_i2c_port *, unsigned long timeout);
+	void (*release_pad)(struct nouveau_i2c_port *);
+	int  (*acquire)(struct nouveau_i2c_port *, unsigned long timeout);
+	void (*release)(struct nouveau_i2c_port *);
 	int (*identify)(struct nouveau_i2c *, int index,
 			const char *what, struct nouveau_i2c_board_info *,
 			bool (*match)(struct nouveau_i2c_port *,
 				      struct i2c_board_info *, void *), void *);
+
+	wait_queue_head_t wait;
 	struct list_head ports;
 };
 
@@ -83,37 +79,13 @@ nouveau_i2c(void *obj)
 	return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_I2C];
 }
 
-#define nouveau_i2c_create(p,e,o,s,d)                                          \
-	nouveau_i2c_create_((p), (e), (o), (s), sizeof(**d), (void **)d)
-#define nouveau_i2c_destroy(p) ({                                              \
-	struct nouveau_i2c *i2c = (p);                                         \
-	_nouveau_i2c_dtor(nv_object(i2c));                                     \
-})
-#define nouveau_i2c_init(p) ({                                                 \
-	struct nouveau_i2c *i2c = (p);                                         \
-	_nouveau_i2c_init(nv_object(i2c));                                     \
-})
-#define nouveau_i2c_fini(p,s) ({                                               \
-	struct nouveau_i2c *i2c = (p);                                         \
-	_nouveau_i2c_fini(nv_object(i2c), (s));                                \
-})
-
-int nouveau_i2c_create_(struct nouveau_object *, struct nouveau_object *,
-			struct nouveau_oclass *, struct nouveau_oclass *,
-			int, void **);
-void _nouveau_i2c_dtor(struct nouveau_object *);
-int  _nouveau_i2c_init(struct nouveau_object *);
-int  _nouveau_i2c_fini(struct nouveau_object *, bool);
-
-extern struct nouveau_oclass nv04_i2c_oclass;
-extern struct nouveau_oclass nv4e_i2c_oclass;
-extern struct nouveau_oclass nv50_i2c_oclass;
-extern struct nouveau_oclass nv94_i2c_oclass;
-extern struct nouveau_oclass nvd0_i2c_oclass;
-extern struct nouveau_oclass nouveau_anx9805_sclass[];
-
-extern const struct i2c_algorithm nouveau_i2c_bit_algo;
-extern const struct i2c_algorithm nouveau_i2c_aux_algo;
+extern struct nouveau_oclass *nv04_i2c_oclass;
+extern struct nouveau_oclass *nv4e_i2c_oclass;
+extern struct nouveau_oclass *nv50_i2c_oclass;
+extern struct nouveau_oclass *nv94_i2c_oclass;
+extern struct nouveau_oclass *nvd0_i2c_oclass;
+extern struct nouveau_oclass *gf117_i2c_oclass;
+extern struct nouveau_oclass *nve0_i2c_oclass;
 
 static inline int
 nv_rdi2cr(struct nouveau_i2c_port *port, u8 addr, u8 reg)
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/ibus.h b/drivers/gpu/drm/nouveau/core/include/subdev/ibus.h
index 88814f159d8..31df634c0fd 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/ibus.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/ibus.h
@@ -30,5 +30,6 @@ nouveau_ibus(void *obj)
 
 extern struct nouveau_oclass nvc0_ibus_oclass;
 extern struct nouveau_oclass nve0_ibus_oclass;
+extern struct nouveau_oclass gk20a_ibus_oclass;
 
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bar/base.c b/drivers/gpu/drm/nouveau/core/subdev/bar/base.c
index bdf594116f3..73b1ed20c8d 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bar/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bar/base.c
@@ -118,8 +118,10 @@ nouveau_bar_create_(struct nouveau_object *parent,
 	if (ret)
 		return ret;
 
-	bar->iomem = ioremap(nv_device_resource_start(device, 3),
-			     nv_device_resource_len(device, 3));
+	if (nv_device_resource_len(device, 3) != 0)
+		bar->iomem = ioremap(nv_device_resource_start(device, 3),
+				     nv_device_resource_len(device, 3));
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bar/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/bar/nvc0.c
index 3f30db62e65..ca8139b9ab2 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bar/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bar/nvc0.c
@@ -30,14 +30,16 @@
 
 #include "priv.h"
 
+struct nvc0_bar_priv_vm {
+	struct nouveau_gpuobj *mem;
+	struct nouveau_gpuobj *pgd;
+	struct nouveau_vm *vm;
+};
+
 struct nvc0_bar_priv {
 	struct nouveau_bar base;
 	spinlock_t lock;
-	struct {
-		struct nouveau_gpuobj *mem;
-		struct nouveau_gpuobj *pgd;
-		struct nouveau_vm *vm;
-	} bar[2];
+	struct nvc0_bar_priv_vm bar[2];
 };
 
 static int
@@ -79,87 +81,87 @@ nvc0_bar_unmap(struct nouveau_bar *bar, struct nouveau_vma *vma)
 }
 
 static int
-nvc0_bar_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	      struct nouveau_oclass *oclass, void *data, u32 size,
-	      struct nouveau_object **pobject)
+nvc0_bar_init_vm(struct nvc0_bar_priv *priv, struct nvc0_bar_priv_vm *bar_vm,
+		 int bar_nr)
 {
-	struct nouveau_device *device = nv_device(parent);
-	struct nvc0_bar_priv *priv;
-	struct nouveau_gpuobj *mem;
+	struct nouveau_device *device = nv_device(&priv->base);
 	struct nouveau_vm *vm;
+	resource_size_t bar_len;
 	int ret;
 
-	ret = nouveau_bar_create(parent, engine, oclass, &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	/* BAR3 */
 	ret = nouveau_gpuobj_new(nv_object(priv), NULL, 0x1000, 0, 0,
-				&priv->bar[0].mem);
-	mem = priv->bar[0].mem;
+				&bar_vm->mem);
 	if (ret)
 		return ret;
 
 	ret = nouveau_gpuobj_new(nv_object(priv), NULL, 0x8000, 0, 0,
-				&priv->bar[0].pgd);
+				&bar_vm->pgd);
 	if (ret)
 		return ret;
 
-	ret = nouveau_vm_new(device, 0, nv_device_resource_len(device, 3), 0, &vm);
+	bar_len = nv_device_resource_len(device, bar_nr);
+
+	ret = nouveau_vm_new(device, 0, bar_len, 0, &vm);
 	if (ret)
 		return ret;
 
 	atomic_inc(&vm->engref[NVDEV_SUBDEV_BAR]);
 
-	ret = nouveau_gpuobj_new(nv_object(priv), NULL,
-				 (nv_device_resource_len(device, 3) >> 12) * 8,
-				 0x1000, NVOBJ_FLAG_ZERO_ALLOC,
-				 &vm->pgt[0].obj[0]);
-	vm->pgt[0].refcount[0] = 1;
-	if (ret)
-		return ret;
+	/*
+	 * Bootstrap page table lookup.
+	 */
+	if (bar_nr == 3) {
+		ret = nouveau_gpuobj_new(nv_object(priv), NULL,
+					 (bar_len >> 12) * 8, 0x1000,
+					 NVOBJ_FLAG_ZERO_ALLOC,
+					&vm->pgt[0].obj[0]);
+		vm->pgt[0].refcount[0] = 1;
+		if (ret)
+			return ret;
+	}
 
-	ret = nouveau_vm_ref(vm, &priv->bar[0].vm, priv->bar[0].pgd);
+	ret = nouveau_vm_ref(vm, &bar_vm->vm, bar_vm->pgd);
 	nouveau_vm_ref(NULL, &vm, NULL);
 	if (ret)
 		return ret;
 
-	nv_wo32(mem, 0x0200, lower_32_bits(priv->bar[0].pgd->addr));
-	nv_wo32(mem, 0x0204, upper_32_bits(priv->bar[0].pgd->addr));
-	nv_wo32(mem, 0x0208, lower_32_bits(nv_device_resource_len(device, 3) - 1));
-	nv_wo32(mem, 0x020c, upper_32_bits(nv_device_resource_len(device, 3) - 1));
+	nv_wo32(bar_vm->mem, 0x0200, lower_32_bits(bar_vm->pgd->addr));
+	nv_wo32(bar_vm->mem, 0x0204, upper_32_bits(bar_vm->pgd->addr));
+	nv_wo32(bar_vm->mem, 0x0208, lower_32_bits(bar_len - 1));
+	nv_wo32(bar_vm->mem, 0x020c, upper_32_bits(bar_len - 1));
 
-	/* BAR1 */
-	ret = nouveau_gpuobj_new(nv_object(priv), NULL, 0x1000, 0, 0,
-				&priv->bar[1].mem);
-	mem = priv->bar[1].mem;
-	if (ret)
-		return ret;
+	return 0;
+}
 
-	ret = nouveau_gpuobj_new(nv_object(priv), NULL, 0x8000, 0, 0,
-				&priv->bar[1].pgd);
-	if (ret)
-		return ret;
+static int
+nvc0_bar_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+	      struct nouveau_oclass *oclass, void *data, u32 size,
+	      struct nouveau_object **pobject)
+{
+	struct nouveau_device *device = nv_device(parent);
+	struct nvc0_bar_priv *priv;
+	bool has_bar3 = nv_device_resource_len(device, 3) != 0;
+	int ret;
 
-	ret = nouveau_vm_new(device, 0, nv_device_resource_len(device, 1), 0, &vm);
+	ret = nouveau_bar_create(parent, engine, oclass, &priv);
+	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
 
-	atomic_inc(&vm->engref[NVDEV_SUBDEV_BAR]);
+	/* BAR3 */
+	if (has_bar3) {
+		ret = nvc0_bar_init_vm(priv, &priv->bar[0], 3);
+		if (ret)
+			return ret;
+		priv->base.alloc = nouveau_bar_alloc;
+		priv->base.kmap = nvc0_bar_kmap;
+	}
 
-	ret = nouveau_vm_ref(vm, &priv->bar[1].vm, priv->bar[1].pgd);
-	nouveau_vm_ref(NULL, &vm, NULL);
+	/* BAR1 */
+	ret = nvc0_bar_init_vm(priv, &priv->bar[1], 1);
 	if (ret)
 		return ret;
 
-	nv_wo32(mem, 0x0200, lower_32_bits(priv->bar[1].pgd->addr));
-	nv_wo32(mem, 0x0204, upper_32_bits(priv->bar[1].pgd->addr));
-	nv_wo32(mem, 0x0208, lower_32_bits(nv_device_resource_len(device, 1) - 1));
-	nv_wo32(mem, 0x020c, upper_32_bits(nv_device_resource_len(device, 1) - 1));
-
-	priv->base.alloc = nouveau_bar_alloc;
-	priv->base.kmap = nvc0_bar_kmap;
 	priv->base.umap = nvc0_bar_umap;
 	priv->base.unmap = nvc0_bar_unmap;
 	priv->base.flush = nv84_bar_flush;
@@ -201,7 +203,9 @@ nvc0_bar_init(struct nouveau_object *object)
 	nv_mask(priv, 0x100c80, 0x00000001, 0x00000000);
 
 	nv_wr32(priv, 0x001704, 0x80000000 | priv->bar[1].mem->addr >> 12);
-	nv_wr32(priv, 0x001714, 0xc0000000 | priv->bar[0].mem->addr >> 12);
+	if (priv->bar[0].mem)
+		nv_wr32(priv, 0x001714,
+			0xc0000000 | priv->bar[0].mem->addr >> 12);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
index 222e8ebb669..d45704a2c2d 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
@@ -183,10 +183,11 @@ nouveau_bios_shadow_prom(struct nouveau_bios *bios)
 		goto out;
 
 	bios->data = kmalloc(bios->size, GFP_KERNEL);
-	if (bios->data) {
-		for (i = 0; i < bios->size; i += 4)
-			((u32 *)bios->data)[i/4] = nv_rd32(bios, 0x300000 + i);
-	}
+	if (!bios->data)
+		goto out;
+
+	for (i = 0; i < bios->size; i += 4)
+		((u32 *)bios->data)[i/4] = nv_rd32(bios, 0x300000 + i);
 
 	/* check the PCI record header */
 	pcir = nv_ro16(bios, 0x0018);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/conn.c b/drivers/gpu/drm/nouveau/core/subdev/bios/conn.c
index 5ac010efd95..2ede3bcd96a 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/conn.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/conn.c
@@ -28,12 +28,12 @@
 #include <subdev/bios/dcb.h>
 #include <subdev/bios/conn.h>
 
-u16
-dcb_conntab(struct nouveau_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
+u32
+nvbios_connTe(struct nouveau_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
 {
-	u16 dcb = dcb_table(bios, ver, hdr, cnt, len);
+	u32 dcb = dcb_table(bios, ver, hdr, cnt, len);
 	if (dcb && *ver >= 0x30 && *hdr >= 0x16) {
-		u16 data = nv_ro16(bios, dcb + 0x14);
+		u32 data = nv_ro16(bios, dcb + 0x14);
 		if (data) {
 			*ver = nv_ro08(bios, data + 0);
 			*hdr = nv_ro08(bios, data + 1);
@@ -42,15 +42,59 @@ dcb_conntab(struct nouveau_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len)
 			return data;
 		}
 	}
-	return 0x0000;
+	return 0x00000000;
 }
 
-u16
-dcb_conn(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len)
+u32
+nvbios_connTp(struct nouveau_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
+	      struct nvbios_connT *info)
+{
+	u32 data = nvbios_connTe(bios, ver, hdr, cnt, len);
+	memset(info, 0x00, sizeof(*info));
+	switch (!!data * *ver) {
+	case 0x30:
+	case 0x40:
+		return data;
+	default:
+		break;
+	}
+	return 0x00000000;
+}
+
+u32
+nvbios_connEe(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len)
 {
 	u8  hdr, cnt;
-	u16 data = dcb_conntab(bios, ver, &hdr, &cnt, len);
+	u32 data = nvbios_connTe(bios, ver, &hdr, &cnt, len);
 	if (data && idx < cnt)
 		return data + hdr + (idx * *len);
-	return 0x0000;
+	return 0x00000000;
+}
+
+u32
+nvbios_connEp(struct nouveau_bios *bios, u8 idx, u8 *ver, u8 *len,
+	      struct nvbios_connE *info)
+{
+	u32 data = nvbios_connEe(bios, idx, ver, len);
+	memset(info, 0x00, sizeof(*info));
+	switch (!!data * *ver) {
+	case 0x30:
+	case 0x40:
+		info->type     =  nv_ro08(bios, data + 0x00);
+		info->location =  nv_ro08(bios, data + 0x01) & 0x0f;
+		info->hpd      = (nv_ro08(bios, data + 0x01) & 0x30) >> 4;
+		info->dp       = (nv_ro08(bios, data + 0x01) & 0xc0) >> 6;
+		if (*len < 4)
+			return data;
+		info->hpd     |= (nv_ro08(bios, data + 0x02) & 0x03) << 2;
+		info->dp      |=  nv_ro08(bios, data + 0x02) & 0x0c;
+		info->di       = (nv_ro08(bios, data + 0x02) & 0xf0) >> 4;
+		info->hpd     |= (nv_ro08(bios, data + 0x03) & 0x07) << 4;
+		info->sr       = (nv_ro08(bios, data + 0x03) & 0x08) >> 3;
+		info->lcdid    = (nv_ro08(bios, data + 0x03) & 0x70) >> 4;
+		return data;
+	default:
+		break;
+	}
+	return 0x00000000;
 }
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/dp.c b/drivers/gpu/drm/nouveau/core/subdev/bios/dp.c
index 7628fe75922..f309dd65725 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/dp.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/dp.c
@@ -162,18 +162,20 @@ nvbios_dpcfg_parse(struct nouveau_bios *bios, u16 outp, u8 idx,
 		   struct nvbios_dpcfg *info)
 {
 	u16 data = nvbios_dpcfg_entry(bios, outp, idx, ver, hdr, cnt, len);
+	memset(info, 0x00, sizeof(*info));
 	if (data) {
 		switch (*ver) {
 		case 0x21:
-			info->drv = nv_ro08(bios, data + 0x02);
-			info->pre = nv_ro08(bios, data + 0x03);
-			info->unk = nv_ro08(bios, data + 0x04);
+			info->dc    = nv_ro08(bios, data + 0x02);
+			info->pe    = nv_ro08(bios, data + 0x03);
+			info->tx_pu = nv_ro08(bios, data + 0x04);
 			break;
 		case 0x30:
 		case 0x40:
-			info->drv = nv_ro08(bios, data + 0x01);
-			info->pre = nv_ro08(bios, data + 0x02);
-			info->unk = nv_ro08(bios, data + 0x03);
+			info->pc    = nv_ro08(bios, data + 0x00);
+			info->dc    = nv_ro08(bios, data + 0x01);
+			info->pe    = nv_ro08(bios, data + 0x02);
+			info->tx_pu = nv_ro08(bios, data + 0x03);
 			break;
 		default:
 			data = 0x0000;
@@ -184,7 +186,7 @@ nvbios_dpcfg_parse(struct nouveau_bios *bios, u16 outp, u8 idx,
 }
 
 u16
-nvbios_dpcfg_match(struct nouveau_bios *bios, u16 outp, u8 un, u8 vs, u8 pe,
+nvbios_dpcfg_match(struct nouveau_bios *bios, u16 outp, u8 pc, u8 vs, u8 pe,
 		   u8 *ver, u8 *hdr, u8 *cnt, u8 *len,
 		   struct nvbios_dpcfg *info)
 {
@@ -193,16 +195,15 @@ nvbios_dpcfg_match(struct nouveau_bios *bios, u16 outp, u8 un, u8 vs, u8 pe,
 
 	if (*ver >= 0x30) {
 		const u8 vsoff[] = { 0, 4, 7, 9 };
-		idx = (un * 10) + vsoff[vs] + pe;
+		idx = (pc * 10) + vsoff[vs] + pe;
 	} else {
-		while ((data = nvbios_dpcfg_entry(bios, outp, idx,
+		while ((data = nvbios_dpcfg_entry(bios, outp, ++idx,
 						  ver, hdr, cnt, len))) {
 			if (nv_ro08(bios, data + 0x00) == vs &&
 			    nv_ro08(bios, data + 0x01) == pe)
 				break;
-			idx++;
 		}
 	}
 
-	return nvbios_dpcfg_parse(bios, outp, pe, ver, hdr, cnt, len, info);
+	return nvbios_dpcfg_parse(bios, outp, idx, ver, hdr, cnt, len, info);
 }
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
index acaeaf79e3f..626380f9e4c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
@@ -98,15 +98,16 @@ static u8
 init_conn(struct nvbios_init *init)
 {
 	struct nouveau_bios *bios = init->bios;
-	u8  ver, len;
-	u16 conn;
+	struct nvbios_connE connE;
+	u8  ver, hdr;
+	u32 conn;
 
 	if (init_exec(init)) {
 		if (init->outp) {
 			conn = init->outp->connector;
-			conn = dcb_conn(bios, conn, &ver, &len);
+			conn = nvbios_connEp(bios, conn, &ver, &hdr, &connE);
 			if (conn)
-				return nv_ro08(bios, conn);
+				return connE.type;
 		}
 
 		error("script needs connector type\n");
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/base.c b/drivers/gpu/drm/nouveau/core/subdev/clock/base.c
index dd62baead39..22351f594d2 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/base.c
@@ -346,8 +346,8 @@ nouveau_clock_ustate_update(struct nouveau_clock *clk, int req)
 	struct nouveau_pstate *pstate;
 	int i = 0;
 
-	/* YKW repellant */
-	return -ENOSYS;
+	if (!clk->allow_reclock)
+		return -ENOSYS;
 
 	if (req != -1 && req != -2) {
 		list_for_each_entry(pstate, &clk->states, head) {
@@ -456,6 +456,7 @@ nouveau_clock_create_(struct nouveau_object *parent,
 		      struct nouveau_object *engine,
 		      struct nouveau_oclass *oclass,
 		      struct nouveau_clocks *clocks,
+		      bool allow_reclock,
 		      int length, void **object)
 {
 	struct nouveau_device *device = nv_device(parent);
@@ -478,6 +479,8 @@ nouveau_clock_create_(struct nouveau_object *parent,
 		ret = nouveau_pstate_new(clk, idx++);
 	} while (ret == 0);
 
+	clk->allow_reclock = allow_reclock;
+
 	mode = nouveau_stropt(device->cfgopt, "NvClkMode", &arglen);
 	if (mode) {
 		if (!strncasecmpz(mode, "disabled", arglen)) {
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nv04.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nv04.c
index b74db6cfc4e..eb2d4425a49 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nv04.c
@@ -82,7 +82,8 @@ nv04_clock_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nv04_clock_priv *priv;
 	int ret;
 
-	ret = nouveau_clock_create(parent, engine, oclass, nv04_domain, &priv);
+	ret = nouveau_clock_create(parent, engine, oclass, nv04_domain, false,
+				   &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nv40.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nv40.c
index db7346f7908..8a9e1683979 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nv40.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nv40.c
@@ -213,7 +213,8 @@ nv40_clock_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nv40_clock_priv *priv;
 	int ret;
 
-	ret = nouveau_clock_create(parent, engine, oclass, nv40_domain, &priv);
+	ret = nouveau_clock_create(parent, engine, oclass, nv40_domain, true,
+				   &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nv50.c
index 250a6d96016..8c132772ba9 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nv50.c
@@ -507,7 +507,7 @@ nv50_clock_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	int ret;
 
 	ret = nouveau_clock_create(parent, engine, oclass, pclass->domains,
-				  &priv);
+				   false, &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.c
index 4f5a1373f00..9fb58354a80 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nva3.c
@@ -302,7 +302,8 @@ nva3_clock_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nva3_clock_priv *priv;
 	int ret;
 
-	ret = nouveau_clock_create(parent, engine, oclass, nva3_domain, &priv);
+	ret = nouveau_clock_create(parent, engine, oclass, nva3_domain, false,
+				   &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nvaa.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nvaa.c
index 7a723b4f564..6a65fc9e966 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nvaa.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nvaa.c
@@ -421,7 +421,8 @@ nvaa_clock_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nvaa_clock_priv *priv;
 	int ret;
 
-	ret = nouveau_clock_create(parent, engine, oclass, nvaa_domains, &priv);
+	ret = nouveau_clock_create(parent, engine, oclass, nvaa_domains, true,
+				   &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nvc0.c
index c3105720ed2..dbf8517f54d 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nvc0.c
@@ -437,7 +437,8 @@ nvc0_clock_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nvc0_clock_priv *priv;
 	int ret;
 
-	ret = nouveau_clock_create(parent, engine, oclass, nvc0_domain, &priv);
+	ret = nouveau_clock_create(parent, engine, oclass, nvc0_domain, false,
+				   &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/clock/nve0.c b/drivers/gpu/drm/nouveau/core/subdev/clock/nve0.c
index d3c37c96f0e..0e62a324014 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/clock/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/clock/nve0.c
@@ -307,7 +307,6 @@ calc_clk(struct nve0_clock_priv *priv,
 		info->dsrc = src0;
 		if (div0) {
 			info->ddiv |= 0x80000000;
-			info->ddiv |= div0 << 8;
 			info->ddiv |= div0;
 		}
 		if (div1D) {
@@ -352,7 +351,7 @@ nve0_clock_prog_0(struct nve0_clock_priv *priv, int clk)
 {
 	struct nve0_clock_info *info = &priv->eng[clk];
 	if (!info->ssel) {
-		nv_mask(priv, 0x1371d0 + (clk * 0x04), 0x80003f3f, info->ddiv);
+		nv_mask(priv, 0x1371d0 + (clk * 0x04), 0x8000003f, info->ddiv);
 		nv_wr32(priv, 0x137160 + (clk * 0x04), info->dsrc);
 	}
 }
@@ -389,7 +388,10 @@ static void
 nve0_clock_prog_3(struct nve0_clock_priv *priv, int clk)
 {
 	struct nve0_clock_info *info = &priv->eng[clk];
-	nv_mask(priv, 0x137250 + (clk * 0x04), 0x00003f3f, info->mdiv);
+	if (info->ssel)
+		nv_mask(priv, 0x137250 + (clk * 0x04), 0x00003f00, info->mdiv);
+	else
+		nv_mask(priv, 0x137250 + (clk * 0x04), 0x0000003f, info->mdiv);
 }
 
 static void
@@ -473,7 +475,8 @@ nve0_clock_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	struct nve0_clock_priv *priv;
 	int ret;
 
-	ret = nouveau_clock_create(parent, engine, oclass, nve0_domain, &priv);
+	ret = nouveau_clock_create(parent, engine, oclass, nve0_domain, true,
+				   &priv);
 	*pobject = nv_object(priv);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/gk20a.c b/drivers/gpu/drm/nouveau/core/subdev/fb/gk20a.c
new file mode 100644
index 00000000000..a16024a7477
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/gk20a.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#include "nvc0.h"
+
+struct gk20a_fb_priv {
+	struct nouveau_fb base;
+};
+
+static int
+gk20a_fb_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+	     struct nouveau_oclass *oclass, void *data, u32 size,
+	     struct nouveau_object **pobject)
+{
+	struct gk20a_fb_priv *priv;
+	int ret;
+
+	ret = nouveau_fb_create(parent, engine, oclass, &priv);
+	*pobject = nv_object(priv);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+struct nouveau_oclass *
+gk20a_fb_oclass = &(struct nouveau_fb_impl) {
+	.base.handle = NV_SUBDEV(FB, 0xea),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = gk20a_fb_ctor,
+		.dtor = _nouveau_fb_dtor,
+		.init = _nouveau_fb_init,
+		.fini = _nouveau_fb_fini,
+	},
+	.memtype = nvc0_fb_memtype_valid,
+	.ram = &gk20a_ram_oclass,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h
index da74c889aed..82273f832e4 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/priv.h
@@ -32,6 +32,7 @@ extern struct nouveau_oclass nva3_ram_oclass;
 extern struct nouveau_oclass nvaa_ram_oclass;
 extern struct nouveau_oclass nvc0_ram_oclass;
 extern struct nouveau_oclass nve0_ram_oclass;
+extern struct nouveau_oclass gk20a_ram_oclass;
 extern struct nouveau_oclass gm107_ram_oclass;
 
 int nouveau_sddr3_calc(struct nouveau_ram *ram);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramfuc.h b/drivers/gpu/drm/nouveau/core/subdev/fb/ramfuc.h
index 0f57fcfe0bb..2af9cfd2c60 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramfuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramfuc.h
@@ -26,7 +26,7 @@ ramfuc_reg2(u32 addr1, u32 addr2)
 	};
 }
 
-static inline struct ramfuc_reg
+static noinline struct ramfuc_reg
 ramfuc_reg(u32 addr)
 {
 	return ramfuc_reg2(addr, addr);
@@ -107,7 +107,7 @@ ramfuc_nsec(struct ramfuc *ram, u32 nsec)
 
 #define ram_init(s,p)       ramfuc_init(&(s)->base, (p))
 #define ram_exec(s,e)       ramfuc_exec(&(s)->base, (e))
-#define ram_have(s,r)       ((s)->r_##r.addr != 0x000000)
+#define ram_have(s,r)       ((s)->r_##r.addr[0] != 0x000000)
 #define ram_rd32(s,r)       ramfuc_rd32(&(s)->base, &(s)->r_##r)
 #define ram_wr32(s,r,d)     ramfuc_wr32(&(s)->base, &(s)->r_##r, (d))
 #define ram_nuke(s,r)       ramfuc_nuke(&(s)->base, &(s)->r_##r)
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramgk20a.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramgk20a.c
new file mode 100644
index 00000000000..4d77d75e467
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramgk20a.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#include "priv.h"
+
+#include <subdev/fb.h>
+
+struct gk20a_mem {
+	struct nouveau_mem base;
+	void *cpuaddr;
+	dma_addr_t handle;
+};
+#define to_gk20a_mem(m) container_of(m, struct gk20a_mem, base)
+
+static void
+gk20a_ram_put(struct nouveau_fb *pfb, struct nouveau_mem **pmem)
+{
+	struct device *dev = nv_device_base(nv_device(pfb));
+	struct gk20a_mem *mem = to_gk20a_mem(*pmem);
+
+	*pmem = NULL;
+	if (unlikely(mem == NULL))
+		return;
+
+	if (likely(mem->cpuaddr))
+		dma_free_coherent(dev, mem->base.size << PAGE_SHIFT,
+				  mem->cpuaddr, mem->handle);
+
+	kfree(mem->base.pages);
+	kfree(mem);
+}
+
+static int
+gk20a_ram_get(struct nouveau_fb *pfb, u64 size, u32 align, u32 ncmin,
+	     u32 memtype, struct nouveau_mem **pmem)
+{
+	struct device *dev = nv_device_base(nv_device(pfb));
+	struct gk20a_mem *mem;
+	u32 type = memtype & 0xff;
+	u32 npages, order;
+	int i;
+
+	nv_debug(pfb, "%s: size: %llx align: %x, ncmin: %x\n", __func__, size,
+		 align, ncmin);
+
+	npages = size >> PAGE_SHIFT;
+	if (npages == 0)
+		npages = 1;
+
+	if (align == 0)
+		align = PAGE_SIZE;
+	align >>= PAGE_SHIFT;
+
+	/* round alignment to the next power of 2, if needed */
+	order = fls(align);
+	if ((align & (align - 1)) == 0)
+		order--;
+	align = BIT(order);
+
+	/* ensure returned address is correctly aligned */
+	npages = max(align, npages);
+
+	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+	if (!mem)
+		return -ENOMEM;
+
+	mem->base.size = npages;
+	mem->base.memtype = type;
+
+	mem->base.pages = kzalloc(sizeof(dma_addr_t) * npages, GFP_KERNEL);
+	if (!mem->base.pages) {
+		kfree(mem);
+		return -ENOMEM;
+	}
+
+	*pmem = &mem->base;
+
+	mem->cpuaddr = dma_alloc_coherent(dev, npages << PAGE_SHIFT,
+					  &mem->handle, GFP_KERNEL);
+	if (!mem->cpuaddr) {
+		nv_error(pfb, "%s: cannot allocate memory!\n", __func__);
+		gk20a_ram_put(pfb, pmem);
+		return -ENOMEM;
+	}
+
+	align <<= PAGE_SHIFT;
+
+	/* alignment check */
+	if (unlikely(mem->handle & (align - 1)))
+		nv_warn(pfb, "memory not aligned as requested: %pad (0x%x)\n",
+			&mem->handle, align);
+
+	nv_debug(pfb, "alloc size: 0x%x, align: 0x%x, paddr: %pad, vaddr: %p\n",
+		 npages << PAGE_SHIFT, align, &mem->handle, mem->cpuaddr);
+
+	for (i = 0; i < npages; i++)
+		mem->base.pages[i] = mem->handle + (PAGE_SIZE * i);
+
+	mem->base.offset = (u64)mem->base.pages[0];
+
+	return 0;
+}
+
+static int
+gk20a_ram_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+	      struct nouveau_oclass *oclass, void *data, u32 datasize,
+	      struct nouveau_object **pobject)
+{
+	struct nouveau_ram *ram;
+	int ret;
+
+	ret = nouveau_ram_create(parent, engine, oclass, &ram);
+	*pobject = nv_object(ram);
+	if (ret)
+		return ret;
+	ram->type = NV_MEM_TYPE_STOLEN;
+	ram->size = get_num_physpages() << PAGE_SHIFT;
+
+	ram->get = gk20a_ram_get;
+	ram->put = gk20a_ram_put;
+
+	return 0;
+}
+
+struct nouveau_oclass
+gk20a_ram_oclass = {
+	.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = gk20a_ram_ctor,
+		.dtor = _nouveau_ram_dtor,
+		.init = _nouveau_ram_init,
+		.fini = _nouveau_ram_fini,
+	},
+};
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c
index ef91b6e893af..e5d12c24cc4 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnv50.c
@@ -211,7 +211,7 @@ nv50_ram_prog(struct nouveau_fb *pfb)
 	struct nv50_ram *ram = (void *)pfb->ram;
 	struct nv50_ramseq *hwsq = &ram->hwsq;
 
-	ram_exec(hwsq, nouveau_boolopt(device->cfgopt, "NvMemExec", false));
+	ram_exec(hwsq, nouveau_boolopt(device->cfgopt, "NvMemExec", true));
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnva3.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnva3.c
index 6eb97f16fbd..8076fb195dd 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnva3.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnva3.c
@@ -309,7 +309,7 @@ nva3_ram_prog(struct nouveau_fb *pfb)
 	struct nouveau_device *device = nv_device(pfb);
 	struct nva3_ram *ram = (void *)pfb->ram;
 	struct nva3_ramfuc *fuc = &ram->fuc;
-	ram_exec(fuc, nouveau_boolopt(device->cfgopt, "NvMemExec", false));
+	ram_exec(fuc, nouveau_boolopt(device->cfgopt, "NvMemExec", true));
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c
index 8edc92224c8..5a6a5027f74 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnvc0.c
@@ -408,7 +408,7 @@ nvc0_ram_prog(struct nouveau_fb *pfb)
 	struct nouveau_device *device = nv_device(pfb);
 	struct nvc0_ram *ram = (void *)pfb->ram;
 	struct nvc0_ramfuc *fuc = &ram->fuc;
-	ram_exec(fuc, nouveau_boolopt(device->cfgopt, "NvMemExec", false));
+	ram_exec(fuc, nouveau_boolopt(device->cfgopt, "NvMemExec", true));
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c
index 16752192cf8..c5b46e30231 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/ramnve0.c
@@ -200,6 +200,7 @@ r1373f4_init(struct nve0_ramfuc *fuc)
 	/* (re)program mempll, if required */
 	if (ram->mode == 2) {
 		ram_mask(fuc, 0x1373f4, 0x00010000, 0x00000000);
+		ram_mask(fuc, 0x132000, 0x80000000, 0x80000000);
 		ram_mask(fuc, 0x132000, 0x00000001, 0x00000000);
 		ram_mask(fuc, 0x132004, 0x103fffff, mcoef);
 		ram_mask(fuc, 0x132000, 0x00000001, 0x00000001);
@@ -262,8 +263,8 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	struct nve0_ram *ram = (void *)pfb->ram;
 	struct nve0_ramfuc *fuc = &ram->fuc;
 	struct nouveau_ram_data *next = ram->base.next;
-	int vc = !(next->bios.ramcfg_11_02_08);
-	int mv = !(next->bios.ramcfg_11_02_04);
+	int vc = !next->bios.ramcfg_11_02_08;
+	int mv = !next->bios.ramcfg_11_02_04;
 	u32 mask, data;
 
 	ram_mask(fuc, 0x10f808, 0x40000000, 0x40000000);
@@ -370,8 +371,8 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 		}
 	}
 
-	if ( (next->bios.ramcfg_11_02_40) ||
-	     (next->bios.ramcfg_11_07_10)) {
+	if (next->bios.ramcfg_11_02_40 ||
+	    next->bios.ramcfg_11_07_10) {
 		ram_mask(fuc, 0x132040, 0x00010000, 0x00010000);
 		ram_nsec(fuc, 20000);
 	}
@@ -417,7 +418,7 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 		ram_mask(fuc, 0x10f694, 0xff00ff00, data);
 	}
 
-	if (ram->mode == 2 && (next->bios.ramcfg_11_08_10))
+	if (ram->mode == 2 && next->bios.ramcfg_11_08_10)
 		data = 0x00000080;
 	else
 		data = 0x00000000;
@@ -425,13 +426,13 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 
 	mask = 0x00070000;
 	data = 0x00000000;
-	if (!(next->bios.ramcfg_11_02_80))
+	if (!next->bios.ramcfg_11_02_80)
 		data |= 0x03000000;
-	if (!(next->bios.ramcfg_11_02_40))
+	if (!next->bios.ramcfg_11_02_40)
 		data |= 0x00002000;
-	if (!(next->bios.ramcfg_11_07_10))
+	if (!next->bios.ramcfg_11_07_10)
 		data |= 0x00004000;
-	if (!(next->bios.ramcfg_11_07_08))
+	if (!next->bios.ramcfg_11_07_08)
 		data |= 0x00000003;
 	else
 		data |= 0x74000000;
@@ -486,7 +487,7 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 
 	data = mask = 0x00000000;
 	if (NOTE00(ramcfg_02_03 != 0)) {
-		data |= (next->bios.ramcfg_11_02_03) << 8;
+		data |= next->bios.ramcfg_11_02_03 << 8;
 		mask |= 0x00000300;
 	}
 	if (NOTE00(ramcfg_01_10)) {
@@ -498,7 +499,7 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 
 	data = mask = 0x00000000;
 	if (NOTE00(timing_30_07 != 0)) {
-		data |= (next->bios.timing_20_30_07) << 28;
+		data |= next->bios.timing_20_30_07 << 28;
 		mask |= 0x70000000;
 	}
 	if (NOTE00(ramcfg_01_01)) {
@@ -510,7 +511,7 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 
 	data = mask = 0x00000000;
 	if (NOTE00(timing_30_07 != 0)) {
-		data |= (next->bios.timing_20_30_07) << 28;
+		data |= next->bios.timing_20_30_07 << 28;
 		mask |= 0x70000000;
 	}
 	if (NOTE00(ramcfg_01_02)) {
@@ -522,16 +523,16 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 
 	mask = 0x33f00000;
 	data = 0x00000000;
-	if (!(next->bios.ramcfg_11_01_04))
+	if (!next->bios.ramcfg_11_01_04)
 		data |= 0x20200000;
-	if (!(next->bios.ramcfg_11_07_80))
+	if (!next->bios.ramcfg_11_07_80)
 		data |= 0x12800000;
 	/*XXX: see note above about there probably being some condition
 	 *     for the 10f824 stuff that uses ramcfg 3...
 	 */
-	if ( (next->bios.ramcfg_11_03_f0)) {
+	if (next->bios.ramcfg_11_03_f0) {
 		if (next->bios.rammap_11_08_0c) {
-			if (!(next->bios.ramcfg_11_07_80))
+			if (!next->bios.ramcfg_11_07_80)
 				mask |= 0x00000020;
 			else
 				data |= 0x00000020;
@@ -563,7 +564,7 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 		ram_wait(fuc, 0x100710, 0x80000000, 0x80000000, 200000);
 	}
 
-	data = (next->bios.timing_20_30_07) << 8;
+	data = next->bios.timing_20_30_07 << 8;
 	if (next->bios.ramcfg_11_01_01)
 		data |= 0x80000000;
 	ram_mask(fuc, 0x100778, 0x00000700, data);
@@ -588,7 +589,7 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	ram_wr32(fuc, 0x10f310, 0x00000001); /* REFRESH */
 	ram_wr32(fuc, 0x10f210, 0x80000000); /* REFRESH_AUTO = 1 */
 
-	if ((next->bios.ramcfg_11_08_10) && (ram->mode == 2) /*XXX*/) {
+	if (next->bios.ramcfg_11_08_10 && (ram->mode == 2) /*XXX*/) {
 		u32 temp = ram_mask(fuc, 0x10f294, 0xff000000, 0x24000000);
 		nve0_ram_train(fuc, 0xbc0e0000, 0xa4010000); /*XXX*/
 		ram_nsec(fuc, 1000);
@@ -621,8 +622,8 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 	data  = ram_rd32(fuc, 0x10f978);
 	data &= ~0x00046144;
 	data |=  0x0000000b;
-	if (!(next->bios.ramcfg_11_07_08)) {
-		if (!(next->bios.ramcfg_11_07_04))
+	if (!next->bios.ramcfg_11_07_08) {
+		if (!next->bios.ramcfg_11_07_04)
 			data |= 0x0000200c;
 		else
 			data |= 0x00000000;
@@ -636,11 +637,11 @@ nve0_ram_calc_gddr5(struct nouveau_fb *pfb, u32 freq)
 		ram_wr32(fuc, 0x10f830, data);
 	}
 
-	if (!(next->bios.ramcfg_11_07_08)) {
+	if (!next->bios.ramcfg_11_07_08) {
 		data = 0x88020000;
-		if ( (next->bios.ramcfg_11_07_04))
+		if ( next->bios.ramcfg_11_07_04)
 			data |= 0x10000000;
-		if (!(next->bios.rammap_11_08_10))
+		if (!next->bios.rammap_11_08_10)
 			data |= 0x00080000;
 	} else {
 		data = 0xa40e0000;
@@ -689,8 +690,8 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
 	const u32 runk0 = ram->fN1 << 16;
 	const u32 runk1 = ram->fN1;
 	struct nouveau_ram_data *next = ram->base.next;
-	int vc = !(next->bios.ramcfg_11_02_08);
-	int mv = !(next->bios.ramcfg_11_02_04);
+	int vc = !next->bios.ramcfg_11_02_08;
+	int mv = !next->bios.ramcfg_11_02_04;
 	u32 mask, data;
 
 	ram_mask(fuc, 0x10f808, 0x40000000, 0x40000000);
@@ -705,7 +706,7 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
 	}
 
 	ram_mask(fuc, 0x10f200, 0x00000800, 0x00000000);
-	if ((next->bios.ramcfg_11_03_f0))
+	if (next->bios.ramcfg_11_03_f0)
 		ram_mask(fuc, 0x10f808, 0x04000000, 0x04000000);
 
 	ram_wr32(fuc, 0x10f314, 0x00000001); /* PRECHARGE */
@@ -761,7 +762,7 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
 
 	ram_mask(fuc, 0x1373f4, 0x00000000, 0x00010010);
 	data  = ram_rd32(fuc, 0x1373ec) & ~0x00030000;
-	data |= (next->bios.ramcfg_11_03_30) << 12;
+	data |= next->bios.ramcfg_11_03_30 << 16;
 	ram_wr32(fuc, 0x1373ec, data);
 	ram_mask(fuc, 0x1373f4, 0x00000003, 0x00000000);
 	ram_mask(fuc, 0x1373f4, 0x00000010, 0x00000000);
@@ -793,8 +794,8 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
 		}
 	}
 
-	if ( (next->bios.ramcfg_11_02_40) ||
-	     (next->bios.ramcfg_11_07_10)) {
+	if (next->bios.ramcfg_11_02_40 ||
+	    next->bios.ramcfg_11_07_10) {
 		ram_mask(fuc, 0x132040, 0x00010000, 0x00010000);
 		ram_nsec(fuc, 20000);
 	}
@@ -810,13 +811,13 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
 
 	mask = 0x00010000;
 	data = 0x00000000;
-	if (!(next->bios.ramcfg_11_02_80))
+	if (!next->bios.ramcfg_11_02_80)
 		data |= 0x03000000;
-	if (!(next->bios.ramcfg_11_02_40))
+	if (!next->bios.ramcfg_11_02_40)
 		data |= 0x00002000;
-	if (!(next->bios.ramcfg_11_07_10))
+	if (!next->bios.ramcfg_11_07_10)
 		data |= 0x00004000;
-	if (!(next->bios.ramcfg_11_07_08))
+	if (!next->bios.ramcfg_11_07_08)
 		data |= 0x00000003;
 	else
 		data |= 0x14000000;
@@ -844,16 +845,16 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
 
 	mask = 0x33f00000;
 	data = 0x00000000;
-	if (!(next->bios.ramcfg_11_01_04))
+	if (!next->bios.ramcfg_11_01_04)
 		data |= 0x20200000;
-	if (!(next->bios.ramcfg_11_07_80))
+	if (!next->bios.ramcfg_11_07_80)
 		data |= 0x12800000;
 	/*XXX: see note above about there probably being some condition
 	 *     for the 10f824 stuff that uses ramcfg 3...
 	 */
-	if ( (next->bios.ramcfg_11_03_f0)) {
+	if (next->bios.ramcfg_11_03_f0) {
 		if (next->bios.rammap_11_08_0c) {
-			if (!(next->bios.ramcfg_11_07_80))
+			if (!next->bios.ramcfg_11_07_80)
 				mask |= 0x00000020;
 			else
 				data |= 0x00000020;
@@ -876,7 +877,7 @@ nve0_ram_calc_sddr3(struct nouveau_fb *pfb, u32 freq)
 		data = next->bios.timing_20_2c_1fc0;
 	ram_mask(fuc, 0x10f24c, 0x7f000000, data << 24);
 
-	ram_mask(fuc, 0x10f224, 0x001f0000, next->bios.timing_20_30_f8);
+	ram_mask(fuc, 0x10f224, 0x001f0000, next->bios.timing_20_30_f8 << 16);
 
 	ram_wr32(fuc, 0x10f090, 0x4000007f);
 	ram_nsec(fuc, 1000);
@@ -1111,7 +1112,7 @@ nve0_ram_prog(struct nouveau_fb *pfb)
 	struct nouveau_device *device = nv_device(pfb);
 	struct nve0_ram *ram = (void *)pfb->ram;
 	struct nve0_ramfuc *fuc = &ram->fuc;
-	ram_exec(fuc, nouveau_boolopt(device->cfgopt, "NvMemExec", false));
+	ram_exec(fuc, nouveau_boolopt(device->cfgopt, "NvMemExec", true));
 	return (ram->base.next == &ram->base.xition);
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/base.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/base.c
index f572c2804c3..45e0202f315 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/base.c
@@ -22,21 +22,24 @@
  * Authors: Ben Skeggs
  */
 
-#include <subdev/gpio.h>
 #include <subdev/bios.h>
 #include <subdev/bios/gpio.h>
 
+#include "priv.h"
+
 static int
 nouveau_gpio_drive(struct nouveau_gpio *gpio,
 		   int idx, int line, int dir, int out)
 {
-	return gpio->drive ? gpio->drive(gpio, line, dir, out) : -ENODEV;
+	const struct nouveau_gpio_impl *impl = (void *)nv_object(gpio)->oclass;
+	return impl->drive ? impl->drive(gpio, line, dir, out) : -ENODEV;
 }
 
 static int
 nouveau_gpio_sense(struct nouveau_gpio *gpio, int idx, int line)
 {
-	return gpio->sense ? gpio->sense(gpio, line) : -ENODEV;
+	const struct nouveau_gpio_impl *impl = (void *)nv_object(gpio)->oclass;
+	return impl->sense ? impl->sense(gpio, line) : -ENODEV;
 }
 
 static int
@@ -102,6 +105,80 @@ nouveau_gpio_get(struct nouveau_gpio *gpio, int idx, u8 tag, u8 line)
 	return ret;
 }
 
+static void
+nouveau_gpio_intr_disable(struct nouveau_event *event, int type, int index)
+{
+	struct nouveau_gpio *gpio = nouveau_gpio(event->priv);
+	const struct nouveau_gpio_impl *impl = (void *)nv_object(gpio)->oclass;
+	impl->intr_mask(gpio, type, 1 << index, 0);
+}
+
+static void
+nouveau_gpio_intr_enable(struct nouveau_event *event, int type, int index)
+{
+	struct nouveau_gpio *gpio = nouveau_gpio(event->priv);
+	const struct nouveau_gpio_impl *impl = (void *)nv_object(gpio)->oclass;
+	impl->intr_mask(gpio, type, 1 << index, 1 << index);
+}
+
+static void
+nouveau_gpio_intr(struct nouveau_subdev *subdev)
+{
+	struct nouveau_gpio *gpio = nouveau_gpio(subdev);
+	const struct nouveau_gpio_impl *impl = (void *)nv_object(gpio)->oclass;
+	u32 hi, lo, e, i;
+
+	impl->intr_stat(gpio, &hi, &lo);
+
+	for (i = 0; e = 0, (hi | lo) && i < impl->lines; i++) {
+		if (hi & (1 << i))
+			e |= NVKM_GPIO_HI;
+		if (lo & (1 << i))
+			e |= NVKM_GPIO_LO;
+		nouveau_event_trigger(gpio->events, e, i);
+	}
+}
+
+int
+_nouveau_gpio_fini(struct nouveau_object *object, bool suspend)
+{
+	const struct nouveau_gpio_impl *impl = (void *)object->oclass;
+	struct nouveau_gpio *gpio = nouveau_gpio(object);
+	u32 mask = (1 << impl->lines) - 1;
+
+	impl->intr_mask(gpio, NVKM_GPIO_TOGGLED, mask, 0);
+	impl->intr_stat(gpio, &mask, &mask);
+
+	return nouveau_subdev_fini(&gpio->base, suspend);
+}
+
+static struct dmi_system_id gpio_reset_ids[] = {
+	{
+		.ident = "Apple Macbook 10,1",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro10,1"),
+		}
+	},
+	{ }
+};
+
+int
+_nouveau_gpio_init(struct nouveau_object *object)
+{
+	struct nouveau_gpio *gpio = nouveau_gpio(object);
+	int ret;
+
+	ret = nouveau_subdev_init(&gpio->base);
+	if (ret)
+		return ret;
+
+	if (gpio->reset && dmi_check_system(gpio_reset_ids))
+		gpio->reset(gpio, DCB_GPIO_UNUSED);
+
+	return ret;
+}
+
 void
 _nouveau_gpio_dtor(struct nouveau_object *object)
 {
@@ -113,9 +190,10 @@ _nouveau_gpio_dtor(struct nouveau_object *object)
 int
 nouveau_gpio_create_(struct nouveau_object *parent,
 		     struct nouveau_object *engine,
-		     struct nouveau_oclass *oclass, int lines,
+		     struct nouveau_oclass *oclass,
 		     int length, void **pobject)
 {
+	const struct nouveau_gpio_impl *impl = (void *)oclass;
 	struct nouveau_gpio *gpio;
 	int ret;
 
@@ -125,34 +203,34 @@ nouveau_gpio_create_(struct nouveau_object *parent,
 	if (ret)
 		return ret;
 
-	ret = nouveau_event_create(lines, &gpio->events);
-	if (ret)
-		return ret;
-
 	gpio->find = nouveau_gpio_find;
 	gpio->set  = nouveau_gpio_set;
 	gpio->get  = nouveau_gpio_get;
+	gpio->reset = impl->reset;
+
+	ret = nouveau_event_create(2, impl->lines, &gpio->events);
+	if (ret)
+		return ret;
+
+	gpio->events->priv = gpio;
+	gpio->events->enable = nouveau_gpio_intr_enable;
+	gpio->events->disable = nouveau_gpio_intr_disable;
+	nv_subdev(gpio)->intr = nouveau_gpio_intr;
 	return 0;
 }
 
-static struct dmi_system_id gpio_reset_ids[] = {
-	{
-		.ident = "Apple Macbook 10,1",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro10,1"),
-		}
-	},
-	{ }
-};
-
 int
-nouveau_gpio_init(struct nouveau_gpio *gpio)
+_nouveau_gpio_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+		   struct nouveau_oclass *oclass, void *data, u32 size,
+		   struct nouveau_object **pobject)
 {
-	int ret = nouveau_subdev_init(&gpio->base);
-	if (ret == 0 && gpio->reset) {
-		if (dmi_check_system(gpio_reset_ids))
-			gpio->reset(gpio, DCB_GPIO_UNUSED);
-	}
-	return ret;
+	struct nouveau_gpio *gpio;
+	int ret;
+
+	ret = nouveau_gpio_create(parent, engine, oclass, &gpio);
+	*pobject = nv_object(gpio);
+	if (ret)
+		return ret;
+
+	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/nv10.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv10.c
index 76d5d5465dd..27ad23eaf18 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/nv10.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv10.c
@@ -26,10 +26,6 @@
 
 #include "priv.h"
 
-struct nv10_gpio_priv {
-	struct nouveau_gpio base;
-};
-
 static int
 nv10_gpio_sense(struct nouveau_gpio *gpio, int line)
 {
@@ -83,95 +79,38 @@ nv10_gpio_drive(struct nouveau_gpio *gpio, int line, int dir, int out)
 }
 
 static void
-nv10_gpio_intr(struct nouveau_subdev *subdev)
-{
-	struct nv10_gpio_priv *priv = (void *)subdev;
-	u32 intr = nv_rd32(priv, 0x001104);
-	u32 hi = (intr & 0x0000ffff) >> 0;
-	u32 lo = (intr & 0xffff0000) >> 16;
-	int i;
-
-	for (i = 0; (hi | lo) && i < 32; i++) {
-		if ((hi | lo) & (1 << i))
-			nouveau_event_trigger(priv->base.events, i);
-	}
-
-	nv_wr32(priv, 0x001104, intr);
-}
-
-static void
-nv10_gpio_intr_enable(struct nouveau_event *event, int line)
-{
-	nv_wr32(event->priv, 0x001104, 0x00010001 << line);
-	nv_mask(event->priv, 0x001144, 0x00010001 << line, 0x00010001 << line);
-}
-
-static void
-nv10_gpio_intr_disable(struct nouveau_event *event, int line)
-{
-	nv_wr32(event->priv, 0x001104, 0x00010001 << line);
-	nv_mask(event->priv, 0x001144, 0x00010001 << line, 0x00000000);
-}
-
-static int
-nv10_gpio_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	       struct nouveau_oclass *oclass, void *data, u32 size,
-	       struct nouveau_object **pobject)
+nv10_gpio_intr_stat(struct nouveau_gpio *gpio, u32 *hi, u32 *lo)
 {
-	struct nv10_gpio_priv *priv;
-	int ret;
-
-	ret = nouveau_gpio_create(parent, engine, oclass, 16, &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	priv->base.drive = nv10_gpio_drive;
-	priv->base.sense = nv10_gpio_sense;
-	priv->base.events->priv = priv;
-	priv->base.events->enable = nv10_gpio_intr_enable;
-	priv->base.events->disable = nv10_gpio_intr_disable;
-	nv_subdev(priv)->intr = nv10_gpio_intr;
-	return 0;
+	u32 intr = nv_rd32(gpio, 0x001104);
+	u32 stat = nv_rd32(gpio, 0x001144) & intr;
+	*lo = (stat & 0xffff0000) >> 16;
+	*hi = (stat & 0x0000ffff);
+	nv_wr32(gpio, 0x001104, intr);
 }
 
 static void
-nv10_gpio_dtor(struct nouveau_object *object)
-{
-	struct nv10_gpio_priv *priv = (void *)object;
-	nouveau_gpio_destroy(&priv->base);
-}
-
-static int
-nv10_gpio_init(struct nouveau_object *object)
-{
-	struct nv10_gpio_priv *priv = (void *)object;
-	int ret;
-
-	ret = nouveau_gpio_init(&priv->base);
-	if (ret)
-		return ret;
-
-	nv_wr32(priv, 0x001144, 0x00000000);
-	nv_wr32(priv, 0x001104, 0xffffffff);
-	return 0;
-}
-
-static int
-nv10_gpio_fini(struct nouveau_object *object, bool suspend)
+nv10_gpio_intr_mask(struct nouveau_gpio *gpio, u32 type, u32 mask, u32 data)
 {
-	struct nv10_gpio_priv *priv = (void *)object;
-	nv_wr32(priv, 0x001144, 0x00000000);
-	return nouveau_gpio_fini(&priv->base, suspend);
+	u32 inte = nv_rd32(gpio, 0x001144);
+	if (type & NVKM_GPIO_LO)
+		inte = (inte & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte = (inte & ~mask) | data;
+	nv_wr32(gpio, 0x001144, inte);
 }
 
-struct nouveau_oclass
-nv10_gpio_oclass = {
-	.handle = NV_SUBDEV(GPIO, 0x10),
-	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = nv10_gpio_ctor,
-		.dtor = nv10_gpio_dtor,
-		.init = nv10_gpio_init,
-		.fini = nv10_gpio_fini,
+struct nouveau_oclass *
+nv10_gpio_oclass = &(struct nouveau_gpio_impl) {
+	.base.handle = NV_SUBDEV(GPIO, 0x10),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_gpio_ctor,
+		.dtor = _nouveau_gpio_dtor,
+		.init = _nouveau_gpio_init,
+		.fini = _nouveau_gpio_fini,
 	},
-};
+	.lines = 16,
+	.intr_stat = nv10_gpio_intr_stat,
+	.intr_mask = nv10_gpio_intr_mask,
+	.drive = nv10_gpio_drive,
+	.sense = nv10_gpio_sense,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv50.c
index 2ef77473162..1864fa98e6b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv50.c
@@ -24,15 +24,10 @@
 
 #include "priv.h"
 
-struct nv50_gpio_priv {
-	struct nouveau_gpio base;
-};
-
-static void
+void
 nv50_gpio_reset(struct nouveau_gpio *gpio, u8 match)
 {
 	struct nouveau_bios *bios = nouveau_bios(gpio);
-	struct nv50_gpio_priv *priv = (void *)gpio;
 	u8 ver, len;
 	u16 entry;
 	int ent = -1;
@@ -55,7 +50,7 @@ nv50_gpio_reset(struct nouveau_gpio *gpio, u8 match)
 
 		gpio->set(gpio, 0, func, line, defs);
 
-		nv_mask(priv, reg, 0x00010001 << lsh, val << lsh);
+		nv_mask(gpio, reg, 0x00010001 << lsh, val << lsh);
 	}
 }
 
@@ -72,7 +67,7 @@ nv50_gpio_location(int line, u32 *reg, u32 *shift)
 	return 0;
 }
 
-static int
+int
 nv50_gpio_drive(struct nouveau_gpio *gpio, int line, int dir, int out)
 {
 	u32 reg, shift;
@@ -84,7 +79,7 @@ nv50_gpio_drive(struct nouveau_gpio *gpio, int line, int dir, int out)
 	return 0;
 }
 
-static int
+int
 nv50_gpio_sense(struct nouveau_gpio *gpio, int line)
 {
 	u32 reg, shift;
@@ -95,119 +90,40 @@ nv50_gpio_sense(struct nouveau_gpio *gpio, int line)
 	return !!(nv_rd32(gpio, reg) & (4 << shift));
 }
 
-void
-nv50_gpio_intr(struct nouveau_subdev *subdev)
-{
-	struct nv50_gpio_priv *priv = (void *)subdev;
-	u32 intr0, intr1 = 0;
-	u32 hi, lo;
-	int i;
-
-	intr0 = nv_rd32(priv, 0xe054) & nv_rd32(priv, 0xe050);
-	if (nv_device(priv)->chipset > 0x92)
-		intr1 = nv_rd32(priv, 0xe074) & nv_rd32(priv, 0xe070);
-
-	hi = (intr0 & 0x0000ffff) | (intr1 << 16);
-	lo = (intr0 >> 16) | (intr1 & 0xffff0000);
-
-	for (i = 0; (hi | lo) && i < 32; i++) {
-		if ((hi | lo) & (1 << i))
-			nouveau_event_trigger(priv->base.events, i);
-	}
-
-	nv_wr32(priv, 0xe054, intr0);
-	if (nv_device(priv)->chipset > 0x92)
-		nv_wr32(priv, 0xe074, intr1);
-}
-
-void
-nv50_gpio_intr_enable(struct nouveau_event *event, int line)
-{
-	const u32 addr = line < 16 ? 0xe050 : 0xe070;
-	const u32 mask = 0x00010001 << (line & 0xf);
-	nv_wr32(event->priv, addr + 0x04, mask);
-	nv_mask(event->priv, addr + 0x00, mask, mask);
-}
-
-void
-nv50_gpio_intr_disable(struct nouveau_event *event, int line)
-{
-	const u32 addr = line < 16 ? 0xe050 : 0xe070;
-	const u32 mask = 0x00010001 << (line & 0xf);
-	nv_wr32(event->priv, addr + 0x04, mask);
-	nv_mask(event->priv, addr + 0x00, mask, 0x00000000);
-}
-
-static int
-nv50_gpio_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	       struct nouveau_oclass *oclass, void *data, u32 size,
-	       struct nouveau_object **pobject)
-{
-	struct nv50_gpio_priv *priv;
-	int ret;
-
-	ret = nouveau_gpio_create(parent, engine, oclass,
-				  nv_device(parent)->chipset > 0x92 ? 32 : 16,
-				  &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	priv->base.reset = nv50_gpio_reset;
-	priv->base.drive = nv50_gpio_drive;
-	priv->base.sense = nv50_gpio_sense;
-	priv->base.events->priv = priv;
-	priv->base.events->enable = nv50_gpio_intr_enable;
-	priv->base.events->disable = nv50_gpio_intr_disable;
-	nv_subdev(priv)->intr = nv50_gpio_intr;
-	return 0;
-}
-
-void
-nv50_gpio_dtor(struct nouveau_object *object)
-{
-	struct nv50_gpio_priv *priv = (void *)object;
-	nouveau_gpio_destroy(&priv->base);
-}
-
-int
-nv50_gpio_init(struct nouveau_object *object)
+static void
+nv50_gpio_intr_stat(struct nouveau_gpio *gpio, u32 *hi, u32 *lo)
 {
-	struct nv50_gpio_priv *priv = (void *)object;
-	int ret;
-
-	ret = nouveau_gpio_init(&priv->base);
-	if (ret)
-		return ret;
-
-	/* disable, and ack any pending gpio interrupts */
-	nv_wr32(priv, 0xe050, 0x00000000);
-	nv_wr32(priv, 0xe054, 0xffffffff);
-	if (nv_device(priv)->chipset > 0x92) {
-		nv_wr32(priv, 0xe070, 0x00000000);
-		nv_wr32(priv, 0xe074, 0xffffffff);
-	}
-
-	return 0;
+	u32 intr = nv_rd32(gpio, 0x00e054);
+	u32 stat = nv_rd32(gpio, 0x00e050) & intr;
+	*lo = (stat & 0xffff0000) >> 16;
+	*hi = (stat & 0x0000ffff);
+	nv_wr32(gpio, 0x00e054, intr);
 }
 
-int
-nv50_gpio_fini(struct nouveau_object *object, bool suspend)
+static void
+nv50_gpio_intr_mask(struct nouveau_gpio *gpio, u32 type, u32 mask, u32 data)
 {
-	struct nv50_gpio_priv *priv = (void *)object;
-	nv_wr32(priv, 0xe050, 0x00000000);
-	if (nv_device(priv)->chipset > 0x92)
-		nv_wr32(priv, 0xe070, 0x00000000);
-	return nouveau_gpio_fini(&priv->base, suspend);
+	u32 inte = nv_rd32(gpio, 0x00e050);
+	if (type & NVKM_GPIO_LO)
+		inte = (inte & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte = (inte & ~mask) | data;
+	nv_wr32(gpio, 0x00e050, inte);
 }
 
-struct nouveau_oclass
-nv50_gpio_oclass = {
-	.handle = NV_SUBDEV(GPIO, 0x50),
-	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = nv50_gpio_ctor,
-		.dtor = nv50_gpio_dtor,
-		.init = nv50_gpio_init,
-		.fini = nv50_gpio_fini,
+struct nouveau_oclass *
+nv50_gpio_oclass = &(struct nouveau_gpio_impl) {
+	.base.handle = NV_SUBDEV(GPIO, 0x50),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_gpio_ctor,
+		.dtor = _nouveau_gpio_dtor,
+		.init = _nouveau_gpio_init,
+		.fini = _nouveau_gpio_fini,
 	},
-};
+	.lines = 16,
+	.intr_stat = nv50_gpio_intr_stat,
+	.intr_mask = nv50_gpio_intr_mask,
+	.drive = nv50_gpio_drive,
+	.sense = nv50_gpio_sense,
+	.reset = nv50_gpio_reset,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/nv92.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv92.c
new file mode 100644
index 00000000000..252083d376f
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/nv92.c
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2012 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include "priv.h"
+
+void
+nv92_gpio_intr_stat(struct nouveau_gpio *gpio, u32 *hi, u32 *lo)
+{
+	u32 intr0 = nv_rd32(gpio, 0x00e054);
+	u32 intr1 = nv_rd32(gpio, 0x00e074);
+	u32 stat0 = nv_rd32(gpio, 0x00e050) & intr0;
+	u32 stat1 = nv_rd32(gpio, 0x00e070) & intr1;
+	*lo = (stat1 & 0xffff0000) | (stat0 >> 16);
+	*hi = (stat1 << 16) | (stat0 & 0x0000ffff);
+	nv_wr32(gpio, 0x00e054, intr0);
+	nv_wr32(gpio, 0x00e074, intr1);
+}
+
+void
+nv92_gpio_intr_mask(struct nouveau_gpio *gpio, u32 type, u32 mask, u32 data)
+{
+	u32 inte0 = nv_rd32(gpio, 0x00e050);
+	u32 inte1 = nv_rd32(gpio, 0x00e070);
+	if (type & NVKM_GPIO_LO)
+		inte0 = (inte0 & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte0 = (inte0 & ~(mask & 0xffff)) | (data & 0xffff);
+	mask >>= 16;
+	data >>= 16;
+	if (type & NVKM_GPIO_LO)
+		inte1 = (inte1 & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte1 = (inte1 & ~mask) | data;
+	nv_wr32(gpio, 0x00e050, inte0);
+	nv_wr32(gpio, 0x00e070, inte1);
+}
+
+struct nouveau_oclass *
+nv92_gpio_oclass = &(struct nouveau_gpio_impl) {
+	.base.handle = NV_SUBDEV(GPIO, 0x92),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_gpio_ctor,
+		.dtor = _nouveau_gpio_dtor,
+		.init = _nouveau_gpio_init,
+		.fini = _nouveau_gpio_fini,
+	},
+	.lines = 32,
+	.intr_stat = nv92_gpio_intr_stat,
+	.intr_mask = nv92_gpio_intr_mask,
+	.drive = nv50_gpio_drive,
+	.sense = nv50_gpio_sense,
+	.reset = nv50_gpio_reset,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/nvd0.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/nvd0.c
index 010431e3ace..a4682b0956a 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/nvd0.c
@@ -24,15 +24,10 @@
 
 #include "priv.h"
 
-struct nvd0_gpio_priv {
-	struct nouveau_gpio base;
-};
-
 void
 nvd0_gpio_reset(struct nouveau_gpio *gpio, u8 match)
 {
 	struct nouveau_bios *bios = nouveau_bios(gpio);
-	struct nvd0_gpio_priv *priv = (void *)gpio;
 	u8 ver, len;
 	u16 entry;
 	int ent = -1;
@@ -51,9 +46,9 @@ nvd0_gpio_reset(struct nouveau_gpio *gpio, u8 match)
 
 		gpio->set(gpio, 0, func, line, defs);
 
-		nv_mask(priv, 0x00d610 + (line * 4), 0xff, unk0);
+		nv_mask(gpio, 0x00d610 + (line * 4), 0xff, unk0);
 		if (unk1--)
-			nv_mask(priv, 0x00d740 + (unk1 * 4), 0xff, line);
+			nv_mask(gpio, 0x00d740 + (unk1 * 4), 0xff, line);
 	}
 }
 
@@ -72,36 +67,19 @@ nvd0_gpio_sense(struct nouveau_gpio *gpio, int line)
 	return !!(nv_rd32(gpio, 0x00d610 + (line * 4)) & 0x00004000);
 }
 
-static int
-nvd0_gpio_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	       struct nouveau_oclass *oclass, void *data, u32 size,
-	       struct nouveau_object **pobject)
-{
-	struct nvd0_gpio_priv *priv;
-	int ret;
-
-	ret = nouveau_gpio_create(parent, engine, oclass, 32, &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	priv->base.reset = nvd0_gpio_reset;
-	priv->base.drive = nvd0_gpio_drive;
-	priv->base.sense = nvd0_gpio_sense;
-	priv->base.events->priv = priv;
-	priv->base.events->enable = nv50_gpio_intr_enable;
-	priv->base.events->disable = nv50_gpio_intr_disable;
-	nv_subdev(priv)->intr = nv50_gpio_intr;
-	return 0;
-}
-
-struct nouveau_oclass
-nvd0_gpio_oclass = {
-	.handle = NV_SUBDEV(GPIO, 0xd0),
-	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = nvd0_gpio_ctor,
-		.dtor = nv50_gpio_dtor,
-		.init = nv50_gpio_init,
-		.fini = nv50_gpio_fini,
+struct nouveau_oclass *
+nvd0_gpio_oclass = &(struct nouveau_gpio_impl) {
+	.base.handle = NV_SUBDEV(GPIO, 0xd0),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_gpio_ctor,
+		.dtor = _nouveau_gpio_dtor,
+		.init = _nouveau_gpio_init,
+		.fini = _nouveau_gpio_fini,
 	},
-};
+	.lines = 32,
+	.intr_stat = nv92_gpio_intr_stat,
+	.intr_mask = nv92_gpio_intr_mask,
+	.drive = nvd0_gpio_drive,
+	.sense = nvd0_gpio_sense,
+	.reset = nvd0_gpio_reset,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/nve0.c b/drivers/gpu/drm/nouveau/core/subdev/gpio/nve0.c
index 16b8c5bf5ef..e1145b48c76 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/nve0.c
@@ -24,108 +24,51 @@
 
 #include "priv.h"
 
-struct nve0_gpio_priv {
-	struct nouveau_gpio base;
-};
-
-void
-nve0_gpio_intr(struct nouveau_subdev *subdev)
+static void
+nve0_gpio_intr_stat(struct nouveau_gpio *gpio, u32 *hi, u32 *lo)
 {
-	struct nve0_gpio_priv *priv = (void *)subdev;
-	u32 intr0 = nv_rd32(priv, 0xdc00) & nv_rd32(priv, 0xdc08);
-	u32 intr1 = nv_rd32(priv, 0xdc80) & nv_rd32(priv, 0xdc88);
-	u32 hi = (intr0 & 0x0000ffff) | (intr1 << 16);
-	u32 lo = (intr0 >> 16) | (intr1 & 0xffff0000);
-	int i;
-
-	for (i = 0; (hi | lo) && i < 32; i++) {
-		if ((hi | lo) & (1 << i))
-			nouveau_event_trigger(priv->base.events, i);
-	}
-
-	nv_wr32(priv, 0xdc00, intr0);
-	nv_wr32(priv, 0xdc88, intr1);
+	u32 intr0 = nv_rd32(gpio, 0x00dc00);
+	u32 intr1 = nv_rd32(gpio, 0x00dc80);
+	u32 stat0 = nv_rd32(gpio, 0x00dc08) & intr0;
+	u32 stat1 = nv_rd32(gpio, 0x00dc88) & intr1;
+	*lo = (stat1 & 0xffff0000) | (stat0 >> 16);
+	*hi = (stat1 << 16) | (stat0 & 0x0000ffff);
+	nv_wr32(gpio, 0x00dc00, intr0);
+	nv_wr32(gpio, 0x00dc80, intr1);
 }
 
 void
-nve0_gpio_intr_enable(struct nouveau_event *event, int line)
+nve0_gpio_intr_mask(struct nouveau_gpio *gpio, u32 type, u32 mask, u32 data)
 {
-	const u32 addr = line < 16 ? 0xdc00 : 0xdc80;
-	const u32 mask = 0x00010001 << (line & 0xf);
-	nv_wr32(event->priv, addr + 0x08, mask);
-	nv_mask(event->priv, addr + 0x00, mask, mask);
-}
-
-void
-nve0_gpio_intr_disable(struct nouveau_event *event, int line)
-{
-	const u32 addr = line < 16 ? 0xdc00 : 0xdc80;
-	const u32 mask = 0x00010001 << (line & 0xf);
-	nv_wr32(event->priv, addr + 0x08, mask);
-	nv_mask(event->priv, addr + 0x00, mask, 0x00000000);
-}
-
-int
-nve0_gpio_fini(struct nouveau_object *object, bool suspend)
-{
-	struct nve0_gpio_priv *priv = (void *)object;
-	nv_wr32(priv, 0xdc08, 0x00000000);
-	nv_wr32(priv, 0xdc88, 0x00000000);
-	return nouveau_gpio_fini(&priv->base, suspend);
-}
-
-int
-nve0_gpio_init(struct nouveau_object *object)
-{
-	struct nve0_gpio_priv *priv = (void *)object;
-	int ret;
-
-	ret = nouveau_gpio_init(&priv->base);
-	if (ret)
-		return ret;
-
-	nv_wr32(priv, 0xdc00, 0xffffffff);
-	nv_wr32(priv, 0xdc80, 0xffffffff);
-	return 0;
-}
-
-void
-nve0_gpio_dtor(struct nouveau_object *object)
-{
-	struct nve0_gpio_priv *priv = (void *)object;
-	nouveau_gpio_destroy(&priv->base);
-}
-
-static int
-nve0_gpio_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	       struct nouveau_oclass *oclass, void *data, u32 size,
-	       struct nouveau_object **pobject)
-{
-	struct nve0_gpio_priv *priv;
-	int ret;
-
-	ret = nouveau_gpio_create(parent, engine, oclass, 32, &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	priv->base.reset = nvd0_gpio_reset;
-	priv->base.drive = nvd0_gpio_drive;
-	priv->base.sense = nvd0_gpio_sense;
-	priv->base.events->priv = priv;
-	priv->base.events->enable = nve0_gpio_intr_enable;
-	priv->base.events->disable = nve0_gpio_intr_disable;
-	nv_subdev(priv)->intr = nve0_gpio_intr;
-	return 0;
+	u32 inte0 = nv_rd32(gpio, 0x00dc08);
+	u32 inte1 = nv_rd32(gpio, 0x00dc88);
+	if (type & NVKM_GPIO_LO)
+		inte0 = (inte0 & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte0 = (inte0 & ~(mask & 0xffff)) | (data & 0xffff);
+	mask >>= 16;
+	data >>= 16;
+	if (type & NVKM_GPIO_LO)
+		inte1 = (inte1 & ~(mask << 16)) | (data << 16);
+	if (type & NVKM_GPIO_HI)
+		inte1 = (inte1 & ~mask) | data;
+	nv_wr32(gpio, 0x00dc08, inte0);
+	nv_wr32(gpio, 0x00dc88, inte1);
 }
 
-struct nouveau_oclass
-nve0_gpio_oclass = {
-	.handle = NV_SUBDEV(GPIO, 0xe0),
-	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = nve0_gpio_ctor,
-		.dtor = nv50_gpio_dtor,
-		.init = nve0_gpio_init,
-		.fini = nve0_gpio_fini,
+struct nouveau_oclass *
+nve0_gpio_oclass = &(struct nouveau_gpio_impl) {
+	.base.handle = NV_SUBDEV(GPIO, 0xe0),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_gpio_ctor,
+		.dtor = _nouveau_gpio_dtor,
+		.init = _nouveau_gpio_init,
+		.fini = _nouveau_gpio_fini,
 	},
-};
+	.lines = 32,
+	.intr_stat = nve0_gpio_intr_stat,
+	.intr_mask = nve0_gpio_intr_mask,
+	.drive = nvd0_gpio_drive,
+	.sense = nvd0_gpio_sense,
+	.reset = nvd0_gpio_reset,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/gpio/priv.h b/drivers/gpu/drm/nouveau/core/subdev/gpio/priv.h
index 2ee1c895c78..e1724dfc86a 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/gpio/priv.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/gpio/priv.h
@@ -3,15 +3,65 @@
 
 #include <subdev/gpio.h>
 
-void nv50_gpio_dtor(struct nouveau_object *);
-int  nv50_gpio_init(struct nouveau_object *);
-int  nv50_gpio_fini(struct nouveau_object *, bool);
-void nv50_gpio_intr(struct nouveau_subdev *);
-void nv50_gpio_intr_enable(struct nouveau_event *, int line);
-void nv50_gpio_intr_disable(struct nouveau_event *, int line);
+#define nouveau_gpio_create(p,e,o,d)                                           \
+	nouveau_gpio_create_((p), (e), (o), sizeof(**d), (void **)d)
+#define nouveau_gpio_destroy(p) ({                                             \
+	struct nouveau_gpio *gpio = (p);                                       \
+	_nouveau_gpio_dtor(nv_object(gpio));                                   \
+})
+#define nouveau_gpio_init(p) ({                                                \
+	struct nouveau_gpio *gpio = (p);                                       \
+	_nouveau_gpio_init(nv_object(gpio));                                   \
+})
+#define nouveau_gpio_fini(p,s) ({                                              \
+	struct nouveau_gpio *gpio = (p);                                       \
+	_nouveau_gpio_fini(nv_object(gpio), (s));                              \
+})
+
+int  nouveau_gpio_create_(struct nouveau_object *, struct nouveau_object *,
+			  struct nouveau_oclass *, int, void **);
+int  _nouveau_gpio_ctor(struct nouveau_object *, struct nouveau_object *,
+			struct nouveau_oclass *, void *, u32,
+			struct nouveau_object **);
+void _nouveau_gpio_dtor(struct nouveau_object *);
+int  _nouveau_gpio_init(struct nouveau_object *);
+int  _nouveau_gpio_fini(struct nouveau_object *, bool);
+
+struct nouveau_gpio_impl {
+	struct nouveau_oclass base;
+	int lines;
+
+	/* read and ack pending interrupts, returning only data
+	 * for lines that have not been masked off, while still
+	 * performing the ack for anything that was pending.
+	 */
+	void (*intr_stat)(struct nouveau_gpio *, u32 *, u32 *);
+
+	/* mask on/off interrupts for hi/lo transitions on a
+	 * given set of gpio lines
+	 */
+	void (*intr_mask)(struct nouveau_gpio *, u32, u32, u32);
+
+	/* configure gpio direction and output value */
+	int  (*drive)(struct nouveau_gpio *, int line, int dir, int out);
+
+	/* sense current state of given gpio line */
+	int  (*sense)(struct nouveau_gpio *, int line);
+
+	/*XXX*/
+	void (*reset)(struct nouveau_gpio *, u8);
+};
+
+void nv50_gpio_reset(struct nouveau_gpio *, u8);
+int  nv50_gpio_drive(struct nouveau_gpio *, int, int, int);
+int  nv50_gpio_sense(struct nouveau_gpio *, int);
+
+void nv92_gpio_intr_stat(struct nouveau_gpio *, u32 *, u32 *);
+void nv92_gpio_intr_mask(struct nouveau_gpio *, u32, u32, u32);
 
 void nvd0_gpio_reset(struct nouveau_gpio *, u8);
 int  nvd0_gpio_drive(struct nouveau_gpio *, int, int, int);
 int  nvd0_gpio_sense(struct nouveau_gpio *, int);
 
+
 #endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/anx9805.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/anx9805.c
index 4b195ac4da6..2c2731a6cf9 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/anx9805.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/anx9805.c
@@ -22,7 +22,7 @@
  * Authors: Ben Skeggs <bskeggs@redhat.com>
  */
 
-#include <subdev/i2c.h>
+#include "port.h"
 
 struct anx9805_i2c_port {
 	struct nouveau_i2c_port base;
@@ -37,6 +37,8 @@ anx9805_train(struct nouveau_i2c_port *port, int link_nr, int link_bw, bool enh)
 	struct nouveau_i2c_port *mast = (void *)nv_object(chan)->parent;
 	u8 tmp, i;
 
+	DBG("ANX9805 train %d 0x%02x %d\n", link_nr, link_bw, enh);
+
 	nv_wri2cr(mast, chan->addr, 0xa0, link_bw);
 	nv_wri2cr(mast, chan->addr, 0xa1, link_nr | (enh ? 0x80 : 0x00));
 	nv_wri2cr(mast, chan->addr, 0xa2, 0x01);
@@ -60,21 +62,29 @@ anx9805_train(struct nouveau_i2c_port *port, int link_nr, int link_bw, bool enh)
 }
 
 static int
-anx9805_aux(struct nouveau_i2c_port *port, u8 type, u32 addr, u8 *data, u8 size)
+anx9805_aux(struct nouveau_i2c_port *port, bool retry,
+	    u8 type, u32 addr, u8 *data, u8 size)
 {
 	struct anx9805_i2c_port *chan = (void *)port;
 	struct nouveau_i2c_port *mast = (void *)nv_object(chan)->parent;
 	int i, ret = -ETIMEDOUT;
+	u8 buf[16] = {};
 	u8 tmp;
 
+	DBG("%02x %05x %d\n", type, addr, size);
+
 	tmp = nv_rdi2cr(mast, chan->ctrl, 0x07) & ~0x04;
 	nv_wri2cr(mast, chan->ctrl, 0x07, tmp | 0x04);
 	nv_wri2cr(mast, chan->ctrl, 0x07, tmp);
 	nv_wri2cr(mast, chan->ctrl, 0xf7, 0x01);
 
 	nv_wri2cr(mast, chan->addr, 0xe4, 0x80);
-	for (i = 0; !(type & 1) && i < size; i++)
-		nv_wri2cr(mast, chan->addr, 0xf0 + i, data[i]);
+	if (!(type & 1)) {
+		memcpy(buf, data, size);
+		DBG("%16ph", buf);
+		for (i = 0; i < size; i++)
+			nv_wri2cr(mast, chan->addr, 0xf0 + i, buf[i]);
+	}
 	nv_wri2cr(mast, chan->addr, 0xe5, ((size - 1) << 4) | type);
 	nv_wri2cr(mast, chan->addr, 0xe6, (addr & 0x000ff) >>  0);
 	nv_wri2cr(mast, chan->addr, 0xe7, (addr & 0x0ff00) >>  8);
@@ -93,8 +103,13 @@ anx9805_aux(struct nouveau_i2c_port *port, u8 type, u32 addr, u8 *data, u8 size)
 		goto done;
 	}
 
-	for (i = 0; (type & 1) && i < size; i++)
-		data[i] = nv_rdi2cr(mast, chan->addr, 0xf0 + i);
+	if (type & 1) {
+		for (i = 0; i < size; i++)
+			buf[i] = nv_rdi2cr(mast, chan->addr, 0xf0 + i);
+		DBG("%16ph", buf);
+		memcpy(data, buf, size);
+	}
+
 	ret = 0;
 done:
 	nv_wri2cr(mast, chan->ctrl, 0xf7, 0x01);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/aux.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/aux.c
index 5de074ad170..02eb42be2e9 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/aux.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/aux.c
@@ -22,15 +22,19 @@
  * Authors: Ben Skeggs
  */
 
-#include <subdev/i2c.h>
+#include "priv.h"
 
 int
 nv_rdaux(struct nouveau_i2c_port *port, u32 addr, u8 *data, u8 size)
 {
+	struct nouveau_i2c *i2c = nouveau_i2c(port);
 	if (port->func->aux) {
-		if (port->func->acquire)
-			port->func->acquire(port);
-		return port->func->aux(port, 9, addr, data, size);
+		int ret = i2c->acquire(port, 0);
+		if (ret == 0) {
+			ret = port->func->aux(port, true, 9, addr, data, size);
+			i2c->release(port);
+		}
+		return ret;
 	}
 	return -ENODEV;
 }
@@ -38,10 +42,14 @@ nv_rdaux(struct nouveau_i2c_port *port, u32 addr, u8 *data, u8 size)
 int
 nv_wraux(struct nouveau_i2c_port *port, u32 addr, u8 *data, u8 size)
 {
+	struct nouveau_i2c *i2c = nouveau_i2c(port);
 	if (port->func->aux) {
-		if (port->func->acquire)
-			port->func->acquire(port);
-		return port->func->aux(port, 8, addr, data, size);
+		int ret = i2c->acquire(port, 0);
+		if (ret == 0) {
+			ret = port->func->aux(port, true, 8, addr, data, size);
+			i2c->release(port);
+		}
+		return ret;
 	}
 	return -ENODEV;
 }
@@ -50,13 +58,16 @@ static int
 aux_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
 {
 	struct nouveau_i2c_port *port = adap->algo_data;
+	struct nouveau_i2c *i2c = nouveau_i2c(port);
 	struct i2c_msg *msg = msgs;
 	int ret, mcnt = num;
 
 	if (!port->func->aux)
 		return -ENODEV;
-	if ( port->func->acquire)
-		port->func->acquire(port);
+
+	ret = i2c->acquire(port, 0);
+	if (ret)
+		return ret;
 
 	while (mcnt--) {
 		u8 remaining = msg->len;
@@ -74,9 +85,11 @@ aux_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
 			if (mcnt || remaining > 16)
 				cmd |= 4; /* MOT */
 
-			ret = port->func->aux(port, cmd, msg->addr, ptr, cnt);
-			if (ret < 0)
+			ret = port->func->aux(port, true, cmd, msg->addr, ptr, cnt);
+			if (ret < 0) {
+				i2c->release(port);
 				return ret;
+			}
 
 			ptr += cnt;
 			remaining -= cnt;
@@ -85,6 +98,7 @@ aux_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
 		msg++;
 	}
 
+	i2c->release(port);
 	return num;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
index 378e05b88e6..09ba2cc851c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
@@ -23,13 +23,16 @@
  */
 
 #include <core/option.h>
+#include <core/event.h>
 
 #include <subdev/bios.h>
 #include <subdev/bios/dcb.h>
 #include <subdev/bios/i2c.h>
-#include <subdev/i2c.h>
 #include <subdev/vga.h>
 
+#include "priv.h"
+#include "pad.h"
+
 /******************************************************************************
  * interface to linux i2c bit-banging algorithm
  *****************************************************************************/
@@ -45,9 +48,15 @@ nouveau_i2c_pre_xfer(struct i2c_adapter *adap)
 {
 	struct i2c_algo_bit_data *bit = adap->algo_data;
 	struct nouveau_i2c_port *port = bit->data;
-	if (port->func->acquire)
-		port->func->acquire(port);
-	return 0;
+	return nouveau_i2c(port)->acquire(port, bit->timeout);
+}
+
+static void
+nouveau_i2c_post_xfer(struct i2c_adapter *adap)
+{
+	struct i2c_algo_bit_data *bit = adap->algo_data;
+	struct nouveau_i2c_port *port = bit->data;
+	return nouveau_i2c(port)->release(port);
 }
 
 static void
@@ -82,6 +91,15 @@ nouveau_i2c_getsda(void *data)
  * base i2c "port" class implementation
  *****************************************************************************/
 
+int
+_nouveau_i2c_port_fini(struct nouveau_object *object, bool suspend)
+{
+	struct nouveau_i2c_port *port = (void *)object;
+	struct nvkm_i2c_pad *pad = nvkm_i2c_pad(port);
+	nv_ofuncs(pad)->fini(nv_object(pad), suspend);
+	return nouveau_object_fini(&port->base, suspend);
+}
+
 void
 _nouveau_i2c_port_dtor(struct nouveau_object *object)
 {
@@ -98,7 +116,7 @@ nouveau_i2c_port_create_(struct nouveau_object *parent,
 			 const struct nouveau_i2c_func *func,
 			 int size, void **pobject)
 {
-	struct nouveau_device *device = nv_device(parent);
+	struct nouveau_device *device = nv_device(engine);
 	struct nouveau_i2c *i2c = (void *)engine;
 	struct nouveau_i2c_port *port;
 	int ret;
@@ -113,8 +131,9 @@ nouveau_i2c_port_create_(struct nouveau_object *parent,
 	port->adapter.owner = THIS_MODULE;
 	port->adapter.dev.parent = nv_device_base(device);
 	port->index = index;
+	port->aux = -1;
 	port->func = func;
-	i2c_set_adapdata(&port->adapter, i2c);
+	mutex_init(&port->mutex);
 
 	if ( algo == &nouveau_i2c_bit_algo &&
 	    !nouveau_boolopt(device->cfgopt, "NvI2C", CSTMSEL)) {
@@ -128,6 +147,7 @@ nouveau_i2c_port_create_(struct nouveau_object *parent,
 		bit->timeout = usecs_to_jiffies(2200);
 		bit->data = port;
 		bit->pre_xfer = nouveau_i2c_pre_xfer;
+		bit->post_xfer = nouveau_i2c_post_xfer;
 		bit->setsda = nouveau_i2c_setsda;
 		bit->setscl = nouveau_i2c_setscl;
 		bit->getsda = nouveau_i2c_getsda;
@@ -141,7 +161,6 @@ nouveau_i2c_port_create_(struct nouveau_object *parent,
 		ret = i2c_add_adapter(&port->adapter);
 	}
 
-	/* drop port's i2c subdev refcount, i2c handles this itself */
 	if (ret == 0)
 		list_add_tail(&port->head, &i2c->ports);
 	return ret;
@@ -193,6 +212,75 @@ nouveau_i2c_find_type(struct nouveau_i2c *i2c, u16 type)
 	return NULL;
 }
 
+static void
+nouveau_i2c_release_pad(struct nouveau_i2c_port *port)
+{
+	struct nvkm_i2c_pad *pad = nvkm_i2c_pad(port);
+	struct nouveau_i2c *i2c = nouveau_i2c(port);
+
+	if (atomic_dec_and_test(&nv_object(pad)->usecount)) {
+		nv_ofuncs(pad)->fini(nv_object(pad), false);
+		wake_up_all(&i2c->wait);
+	}
+}
+
+static int
+nouveau_i2c_try_acquire_pad(struct nouveau_i2c_port *port)
+{
+	struct nvkm_i2c_pad *pad = nvkm_i2c_pad(port);
+
+	if (atomic_add_return(1, &nv_object(pad)->usecount) != 1) {
+		struct nouveau_object *owner = (void *)pad->port;
+		do {
+			if (owner == (void *)port)
+				return 0;
+			owner = owner->parent;
+		} while(owner);
+		nouveau_i2c_release_pad(port);
+		return -EBUSY;
+	}
+
+	pad->next = port;
+	nv_ofuncs(pad)->init(nv_object(pad));
+	return 0;
+}
+
+static int
+nouveau_i2c_acquire_pad(struct nouveau_i2c_port *port, unsigned long timeout)
+{
+	struct nouveau_i2c *i2c = nouveau_i2c(port);
+
+	if (timeout) {
+		if (wait_event_timeout(i2c->wait,
+				       nouveau_i2c_try_acquire_pad(port) == 0,
+				       timeout) == 0)
+			return -EBUSY;
+	} else {
+		wait_event(i2c->wait, nouveau_i2c_try_acquire_pad(port) == 0);
+	}
+
+	return 0;
+}
+
+static void
+nouveau_i2c_release(struct nouveau_i2c_port *port)
+__releases(pad->mutex)
+{
+	nouveau_i2c(port)->release_pad(port);
+	mutex_unlock(&port->mutex);
+}
+
+static int
+nouveau_i2c_acquire(struct nouveau_i2c_port *port, unsigned long timeout)
+__acquires(pad->mutex)
+{
+	int ret;
+	mutex_lock(&port->mutex);
+	if ((ret = nouveau_i2c(port)->acquire_pad(port, timeout)))
+		mutex_unlock(&port->mutex);
+	return ret;
+}
+
 static int
 nouveau_i2c_identify(struct nouveau_i2c *i2c, int index, const char *what,
 		     struct nouveau_i2c_board_info *info,
@@ -237,11 +325,59 @@ nouveau_i2c_identify(struct nouveau_i2c *i2c, int index, const char *what,
 	return -ENODEV;
 }
 
+static void
+nouveau_i2c_intr_disable(struct nouveau_event *event, int type, int index)
+{
+	struct nouveau_i2c *i2c = nouveau_i2c(event->priv);
+	struct nouveau_i2c_port *port = i2c->find(i2c, index);
+	const struct nouveau_i2c_impl *impl = (void *)nv_object(i2c)->oclass;
+	if (port && port->aux >= 0)
+		impl->aux_mask(i2c, type, 1 << port->aux, 0);
+}
+
+static void
+nouveau_i2c_intr_enable(struct nouveau_event *event, int type, int index)
+{
+	struct nouveau_i2c *i2c = nouveau_i2c(event->priv);
+	struct nouveau_i2c_port *port = i2c->find(i2c, index);
+	const struct nouveau_i2c_impl *impl = (void *)nv_object(i2c)->oclass;
+	if (port && port->aux >= 0)
+		impl->aux_mask(i2c, type, 1 << port->aux, 1 << port->aux);
+}
+
+static void
+nouveau_i2c_intr(struct nouveau_subdev *subdev)
+{
+	struct nouveau_i2c_impl *impl = (void *)nv_oclass(subdev);
+	struct nouveau_i2c *i2c = nouveau_i2c(subdev);
+	struct nouveau_i2c_port *port;
+	u32 hi, lo, rq, tx, e;
+
+	if (impl->aux_stat) {
+		impl->aux_stat(i2c, &hi, &lo, &rq, &tx);
+		if (hi || lo || rq || tx) {
+			list_for_each_entry(port, &i2c->ports, head) {
+				if (e = 0, port->aux < 0)
+					continue;
+
+				if (hi & (1 << port->aux)) e |= NVKM_I2C_PLUG;
+				if (lo & (1 << port->aux)) e |= NVKM_I2C_UNPLUG;
+				if (rq & (1 << port->aux)) e |= NVKM_I2C_IRQ;
+				if (tx & (1 << port->aux)) e |= NVKM_I2C_DONE;
+
+				nouveau_event_trigger(i2c->ntfy, e, port->index);
+			}
+		}
+	}
+}
+
 int
 _nouveau_i2c_fini(struct nouveau_object *object, bool suspend)
 {
+	struct nouveau_i2c_impl *impl = (void *)nv_oclass(object);
 	struct nouveau_i2c *i2c = (void *)object;
 	struct nouveau_i2c_port *port;
+	u32 mask;
 	int ret;
 
 	list_for_each_entry(port, &i2c->ports, head) {
@@ -250,6 +386,11 @@ _nouveau_i2c_fini(struct nouveau_object *object, bool suspend)
 			goto fail;
 	}
 
+	if ((mask = (1 << impl->aux) - 1), impl->aux_stat) {
+		impl->aux_mask(i2c, NVKM_I2C_ANY, mask, 0);
+		impl->aux_stat(i2c, &mask, &mask, &mask, &mask);
+	}
+
 	return nouveau_subdev_fini(&i2c->base, suspend);
 fail:
 	list_for_each_entry_continue_reverse(port, &i2c->ports, head) {
@@ -290,6 +431,8 @@ _nouveau_i2c_dtor(struct nouveau_object *object)
 	struct nouveau_i2c *i2c = (void *)object;
 	struct nouveau_i2c_port *port, *temp;
 
+	nouveau_event_destroy(&i2c->ntfy);
+
 	list_for_each_entry_safe(port, temp, &i2c->ports, head) {
 		nouveau_object_ref(NULL, (struct nouveau_object **)&port);
 	}
@@ -306,14 +449,14 @@ int
 nouveau_i2c_create_(struct nouveau_object *parent,
 		    struct nouveau_object *engine,
 		    struct nouveau_oclass *oclass,
-		    struct nouveau_oclass *sclass,
 		    int length, void **pobject)
 {
+	const struct nouveau_i2c_impl *impl = (void *)oclass;
 	struct nouveau_bios *bios = nouveau_bios(parent);
 	struct nouveau_i2c *i2c;
 	struct nouveau_object *object;
 	struct dcb_i2c_entry info;
-	int ret, i, j, index = -1;
+	int ret, i, j, index = -1, pad;
 	struct dcb_output outp;
 	u8  ver, hdr;
 	u32 data;
@@ -324,24 +467,48 @@ nouveau_i2c_create_(struct nouveau_object *parent,
 	if (ret)
 		return ret;
 
+	nv_subdev(i2c)->intr = nouveau_i2c_intr;
 	i2c->find = nouveau_i2c_find;
 	i2c->find_type = nouveau_i2c_find_type;
+	i2c->acquire_pad = nouveau_i2c_acquire_pad;
+	i2c->release_pad = nouveau_i2c_release_pad;
+	i2c->acquire = nouveau_i2c_acquire;
+	i2c->release = nouveau_i2c_release;
 	i2c->identify = nouveau_i2c_identify;
+	init_waitqueue_head(&i2c->wait);
 	INIT_LIST_HEAD(&i2c->ports);
 
 	while (!dcb_i2c_parse(bios, ++index, &info)) {
 		if (info.type == DCB_I2C_UNUSED)
 			continue;
 
-		oclass = sclass;
+		if (info.share != DCB_I2C_UNUSED) {
+			if (info.type == DCB_I2C_NVIO_AUX)
+				pad = info.drive;
+			else
+				pad = info.share;
+			oclass = impl->pad_s;
+		} else {
+			pad = 0x100 + info.drive;
+			oclass = impl->pad_x;
+		}
+
+		ret = nouveau_object_ctor(NULL, *pobject, oclass,
+					  NULL, pad, &parent);
+		if (ret < 0)
+			continue;
+
+		oclass = impl->sclass;
 		do {
 			ret = -EINVAL;
 			if (oclass->handle == info.type) {
-				ret = nouveau_object_ctor(*pobject, *pobject,
+				ret = nouveau_object_ctor(parent, *pobject,
 							  oclass, &info,
 							  index, &object);
 			}
 		} while (ret && (++oclass)->handle);
+
+		nouveau_object_ref(NULL, &parent);
 	}
 
 	/* in addition to the busses specified in the i2c table, there
@@ -380,5 +547,28 @@ nouveau_i2c_create_(struct nouveau_object *parent,
 		}
 	}
 
+	ret = nouveau_event_create(4, index, &i2c->ntfy);
+	if (ret)
+		return ret;
+
+	i2c->ntfy->priv = i2c;
+	i2c->ntfy->enable = nouveau_i2c_intr_enable;
+	i2c->ntfy->disable = nouveau_i2c_intr_disable;
+	return 0;
+}
+
+int
+_nouveau_i2c_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+		  struct nouveau_oclass *oclass, void *data, u32 size,
+		  struct nouveau_object **pobject)
+{
+	struct nouveau_i2c *i2c;
+	int ret;
+
+	ret = nouveau_i2c_create(parent, engine, oclass, &i2c);
+	*pobject = nv_object(i2c);
+	if (ret)
+		return ret;
+
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/bit.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/bit.c
index a6e72d3b06b..813ffc96e86 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/bit.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/bit.c
@@ -22,7 +22,7 @@
  * Authors: Ben Skeggs
  */
 
-#include "subdev/i2c.h"
+#include "priv.h"
 
 #ifdef CONFIG_NOUVEAU_I2C_INTERNAL
 #define T_TIMEOUT  2200000
@@ -187,8 +187,9 @@ i2c_bit_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
 	struct i2c_msg *msg = msgs;
 	int ret = 0, mcnt = num;
 
-	if (port->func->acquire)
-		port->func->acquire(port);
+	ret = nouveau_i2c(port)->acquire(port, nsecs_to_jiffies(T_TIMEOUT));
+	if (ret)
+		return ret;
 
 	while (!ret && mcnt--) {
 		u8 remaining = msg->len;
@@ -210,6 +211,7 @@ i2c_bit_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
 	}
 
 	i2c_stop(port);
+	nouveau_i2c(port)->release(port);
 	return (ret < 0) ? ret : num;
 }
 #else
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/gf117.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/gf117.c
new file mode 100644
index 00000000000..fa891c39866
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/gf117.c
@@ -0,0 +1,39 @@
+/*
+ * Copyright 2012 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include "nv50.h"
+
+struct nouveau_oclass *
+gf117_i2c_oclass = &(struct nouveau_i2c_impl) {
+	.base.handle = NV_SUBDEV(I2C, 0xd7),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_i2c_ctor,
+		.dtor = _nouveau_i2c_dtor,
+		.init = _nouveau_i2c_init,
+		.fini = _nouveau_i2c_fini,
+	},
+	.sclass = nvd0_i2c_sclass,
+	.pad_x = &nv04_i2c_pad_oclass,
+	.pad_s = &nv04_i2c_pad_oclass,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv04.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv04.c
index 860d5d2365d..b1725bdea96 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv04.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv04.c
@@ -22,9 +22,10 @@
  * Authors: Ben Skeggs
  */
 
-#include <subdev/i2c.h>
 #include <subdev/vga.h>
 
+#include "priv.h"
+
 struct nv04_i2c_priv {
 	struct nouveau_i2c base;
 };
@@ -115,29 +116,15 @@ nv04_i2c_sclass[] = {
 	{}
 };
 
-static int
-nv04_i2c_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	      struct nouveau_oclass *oclass, void *data, u32 size,
-	      struct nouveau_object **pobject)
-{
-	struct nv04_i2c_priv *priv;
-	int ret;
-
-	ret = nouveau_i2c_create(parent, engine, oclass, nv04_i2c_sclass, &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-struct nouveau_oclass
-nv04_i2c_oclass = {
-	.handle = NV_SUBDEV(I2C, 0x04),
-	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = nv04_i2c_ctor,
+struct nouveau_oclass *
+nv04_i2c_oclass = &(struct nouveau_i2c_impl) {
+	.base.handle = NV_SUBDEV(I2C, 0x04),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_i2c_ctor,
 		.dtor = _nouveau_i2c_dtor,
 		.init = _nouveau_i2c_init,
 		.fini = _nouveau_i2c_fini,
 	},
-};
+	.sclass = nv04_i2c_sclass,
+	.pad_x = &nv04_i2c_pad_oclass,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv4e.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv4e.c
index 0c2655a03bb..f16c87ce5ba 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv4e.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv4e.c
@@ -22,9 +22,10 @@
  * Authors: Ben Skeggs
  */
 
-#include <subdev/i2c.h>
 #include <subdev/vga.h>
 
+#include "priv.h"
+
 struct nv4e_i2c_priv {
 	struct nouveau_i2c base;
 };
@@ -107,29 +108,15 @@ nv4e_i2c_sclass[] = {
 	{}
 };
 
-static int
-nv4e_i2c_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	      struct nouveau_oclass *oclass, void *data, u32 size,
-	      struct nouveau_object **pobject)
-{
-	struct nv4e_i2c_priv *priv;
-	int ret;
-
-	ret = nouveau_i2c_create(parent, engine, oclass, nv4e_i2c_sclass, &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-struct nouveau_oclass
-nv4e_i2c_oclass = {
-	.handle = NV_SUBDEV(I2C, 0x4e),
-	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = nv4e_i2c_ctor,
+struct nouveau_oclass *
+nv4e_i2c_oclass = &(struct nouveau_i2c_impl) {
+	.base.handle = NV_SUBDEV(I2C, 0x4e),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_i2c_ctor,
 		.dtor = _nouveau_i2c_dtor,
 		.init = _nouveau_i2c_init,
 		.fini = _nouveau_i2c_fini,
 	},
-};
+	.sclass = nv4e_i2c_sclass,
+	.pad_x = &nv04_i2c_pad_oclass,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.c
index a8d67a28770..7b8756d4df0 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.c
@@ -121,29 +121,15 @@ nv50_i2c_sclass[] = {
 	{}
 };
 
-static int
-nv50_i2c_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	      struct nouveau_oclass *oclass, void *data, u32 size,
-	      struct nouveau_object **pobject)
-{
-	struct nv50_i2c_priv *priv;
-	int ret;
-
-	ret = nouveau_i2c_create(parent, engine, oclass, nv50_i2c_sclass, &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-struct nouveau_oclass
-nv50_i2c_oclass = {
-	.handle = NV_SUBDEV(I2C, 0x50),
-	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = nv50_i2c_ctor,
+struct nouveau_oclass *
+nv50_i2c_oclass = &(struct nouveau_i2c_impl) {
+	.base.handle = NV_SUBDEV(I2C, 0x50),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_i2c_ctor,
 		.dtor = _nouveau_i2c_dtor,
 		.init = _nouveau_i2c_init,
 		.fini = _nouveau_i2c_fini,
 	},
-};
+	.sclass = nv50_i2c_sclass,
+	.pad_x = &nv04_i2c_pad_oclass,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.h b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.h
index 4e5ba48ebf5..5d2a77421c7 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv50.h
@@ -1,7 +1,7 @@
 #ifndef __NV50_I2C_H__
 #define __NV50_I2C_H__
 
-#include <subdev/i2c.h>
+#include "priv.h"
 
 struct nv50_i2c_priv {
 	struct nouveau_i2c base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv94.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv94.c
index df6d3e4b68b..f59c3a25546 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nv94.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nv94.c
@@ -24,6 +24,36 @@
 
 #include "nv50.h"
 
+void
+nv94_aux_stat(struct nouveau_i2c *i2c, u32 *hi, u32 *lo, u32 *rq, u32 *tx)
+{
+	u32 intr = nv_rd32(i2c, 0x00e06c);
+	u32 stat = nv_rd32(i2c, 0x00e068) & intr, i;
+	for (i = 0, *hi = *lo = *rq = *tx = 0; i < 8; i++) {
+		if ((stat & (1 << (i * 4)))) *hi |= 1 << i;
+		if ((stat & (2 << (i * 4)))) *lo |= 1 << i;
+		if ((stat & (4 << (i * 4)))) *rq |= 1 << i;
+		if ((stat & (8 << (i * 4)))) *tx |= 1 << i;
+	}
+	nv_wr32(i2c, 0x00e06c, intr);
+}
+
+void
+nv94_aux_mask(struct nouveau_i2c *i2c, u32 type, u32 mask, u32 data)
+{
+	u32 temp = nv_rd32(i2c, 0x00e068), i;
+	for (i = 0; i < 8; i++) {
+		if (mask & (1 << i)) {
+			if (!(data & (1 << i))) {
+				temp &= ~(type << (i * 4));
+				continue;
+			}
+			temp |= type << (i * 4);
+		}
+	}
+	nv_wr32(i2c, 0x00e068, temp);
+}
+
 #define AUX_DBG(fmt, args...) nv_debug(aux, "AUXCH(%d): " fmt, ch, ##args)
 #define AUX_ERR(fmt, args...) nv_error(aux, "AUXCH(%d): " fmt, ch, ##args)
 
@@ -69,7 +99,8 @@ auxch_init(struct nouveau_i2c *aux, int ch)
 }
 
 int
-nv94_aux(struct nouveau_i2c_port *base, u8 type, u32 addr, u8 *data, u8 size)
+nv94_aux(struct nouveau_i2c_port *base, bool retry,
+	 u8 type, u32 addr, u8 *data, u8 size)
 {
 	struct nouveau_i2c *aux = nouveau_i2c(base);
 	struct nv50_i2c_port *port = (void *)base;
@@ -105,9 +136,8 @@ nv94_aux(struct nouveau_i2c_port *base, u8 type, u32 addr, u8 *data, u8 size)
 	ctrl |= size - 1;
 	nv_wr32(aux, 0x00e4e0 + (ch * 0x50), addr);
 
-	/* retry transaction a number of times on failure... */
-	ret = -EREMOTEIO;
-	for (retries = 0; retries < 32; retries++) {
+	/* (maybe) retry transaction a number of times on failure... */
+	for (retries = 0; !ret && retries < 32; retries++) {
 		/* reset, and delay a while if this is a retry */
 		nv_wr32(aux, 0x00e4e4 + (ch * 0x50), 0x80000000 | ctrl);
 		nv_wr32(aux, 0x00e4e4 + (ch * 0x50), 0x00000000 | ctrl);
@@ -123,16 +153,21 @@ nv94_aux(struct nouveau_i2c_port *base, u8 type, u32 addr, u8 *data, u8 size)
 			udelay(1);
 			if (!timeout--) {
 				AUX_ERR("tx req timeout 0x%08x\n", ctrl);
+				ret = -EIO;
 				goto out;
 			}
 		} while (ctrl & 0x00010000);
+		ret = 1;
 
 		/* read status, and check if transaction completed ok */
 		stat = nv_mask(aux, 0x00e4e8 + (ch * 0x50), 0, 0);
-		if (!(stat & 0x000f0f00)) {
-			ret = 0;
-			break;
-		}
+		if ((stat & 0x000f0000) == 0x00080000 ||
+		    (stat & 0x000f0000) == 0x00020000)
+			ret = retry ? 0 : 1;
+		if ((stat & 0x00000100))
+			ret = -ETIMEDOUT;
+		if ((stat & 0x00000e00))
+			ret = -EIO;
 
 		AUX_DBG("%02d 0x%08x 0x%08x\n", retries, ctrl, stat);
 	}
@@ -147,29 +182,11 @@ nv94_aux(struct nouveau_i2c_port *base, u8 type, u32 addr, u8 *data, u8 size)
 
 out:
 	auxch_fini(aux, ch);
-	return ret;
-}
-
-void
-nv94_i2c_acquire(struct nouveau_i2c_port *base)
-{
-	struct nv50_i2c_priv *priv = (void *)nv_object(base)->engine;
-	struct nv50_i2c_port *port = (void *)base;
-	if (port->ctrl) {
-		nv_mask(priv, port->ctrl + 0x0c, 0x00000001, 0x00000000);
-		nv_mask(priv, port->ctrl + 0x00, 0x0000f003, port->data);
-	}
-}
-
-void
-nv94_i2c_release(struct nouveau_i2c_port *base)
-{
+	return ret < 0 ? ret : (stat & 0x000f0000) >> 16;
 }
 
 static const struct nouveau_i2c_func
 nv94_i2c_func = {
-	.acquire   = nv94_i2c_acquire,
-	.release   = nv94_i2c_release,
 	.drive_scl = nv50_i2c_drive_scl,
 	.drive_sda = nv50_i2c_drive_sda,
 	.sense_scl = nv50_i2c_sense_scl,
@@ -206,8 +223,6 @@ nv94_i2c_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 
 static const struct nouveau_i2c_func
 nv94_aux_func = {
-	.acquire   = nv94_i2c_acquire,
-	.release   = nv94_i2c_release,
 	.aux       = nv94_aux,
 };
 
@@ -227,6 +242,7 @@ nv94_aux_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	if (ret)
 		return ret;
 
+	port->base.aux = info->drive;
 	port->addr = info->drive;
 	if (info->share != DCB_I2C_UNUSED) {
 		port->ctrl = 0x00e500 + (info->drive * 0x50);
@@ -257,29 +273,19 @@ nv94_i2c_sclass[] = {
 	{}
 };
 
-static int
-nv94_i2c_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	      struct nouveau_oclass *oclass, void *data, u32 size,
-	      struct nouveau_object **pobject)
-{
-	struct nv50_i2c_priv *priv;
-	int ret;
-
-	ret = nouveau_i2c_create(parent, engine, oclass, nv94_i2c_sclass, &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-struct nouveau_oclass
-nv94_i2c_oclass = {
-	.handle = NV_SUBDEV(I2C, 0x94),
-	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = nv94_i2c_ctor,
+struct nouveau_oclass *
+nv94_i2c_oclass = &(struct nouveau_i2c_impl) {
+	.base.handle = NV_SUBDEV(I2C, 0x94),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_i2c_ctor,
 		.dtor = _nouveau_i2c_dtor,
 		.init = _nouveau_i2c_init,
 		.fini = _nouveau_i2c_fini,
 	},
-};
+	.sclass = nv94_i2c_sclass,
+	.pad_x = &nv04_i2c_pad_oclass,
+	.pad_s = &nv94_i2c_pad_oclass,
+	.aux = 4,
+	.aux_stat = nv94_aux_stat,
+	.aux_mask = nv94_aux_mask,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nvd0.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nvd0.c
index 29967d30f97..364ddb1c5f0 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nvd0.c
@@ -42,8 +42,6 @@ nvd0_i2c_sense_sda(struct nouveau_i2c_port *base)
 
 static const struct nouveau_i2c_func
 nvd0_i2c_func = {
-	.acquire   = nv94_i2c_acquire,
-	.release   = nv94_i2c_release,
 	.drive_scl = nv50_i2c_drive_scl,
 	.drive_sda = nv50_i2c_drive_sda,
 	.sense_scl = nvd0_i2c_sense_scl,
@@ -75,7 +73,7 @@ nvd0_i2c_port_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	return 0;
 }
 
-static struct nouveau_oclass
+struct nouveau_oclass
 nvd0_i2c_sclass[] = {
 	{ .handle = NV_I2C_TYPE_DCBI2C(DCB_I2C_NVIO_BIT),
 	  .ofuncs = &(struct nouveau_ofuncs) {
@@ -96,29 +94,19 @@ nvd0_i2c_sclass[] = {
 	{}
 };
 
-static int
-nvd0_i2c_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
-	      struct nouveau_oclass *oclass, void *data, u32 size,
-	      struct nouveau_object **pobject)
-{
-	struct nv50_i2c_priv *priv;
-	int ret;
-
-	ret = nouveau_i2c_create(parent, engine, oclass, nvd0_i2c_sclass, &priv);
-	*pobject = nv_object(priv);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-struct nouveau_oclass
-nvd0_i2c_oclass = {
-	.handle = NV_SUBDEV(I2C, 0xd0),
-	.ofuncs = &(struct nouveau_ofuncs) {
-		.ctor = nvd0_i2c_ctor,
+struct nouveau_oclass *
+nvd0_i2c_oclass = &(struct nouveau_i2c_impl) {
+	.base.handle = NV_SUBDEV(I2C, 0xd0),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_i2c_ctor,
 		.dtor = _nouveau_i2c_dtor,
 		.init = _nouveau_i2c_init,
 		.fini = _nouveau_i2c_fini,
 	},
-};
+	.sclass = nvd0_i2c_sclass,
+	.pad_x = &nv04_i2c_pad_oclass,
+	.pad_s = &nv94_i2c_pad_oclass,
+	.aux = 4,
+	.aux_stat = nv94_aux_stat,
+	.aux_mask = nv94_aux_mask,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/nve0.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/nve0.c
new file mode 100644
index 00000000000..cae77e1ad8d
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/nve0.c
@@ -0,0 +1,72 @@
+/*
+ * Copyright 2012 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include "nv50.h"
+
+static void
+nve0_aux_stat(struct nouveau_i2c *i2c, u32 *hi, u32 *lo, u32 *rq, u32 *tx)
+{
+	u32 intr = nv_rd32(i2c, 0x00dc60);
+	u32 stat = nv_rd32(i2c, 0x00dc68) & intr, i;
+	for (i = 0, *hi = *lo = *rq = *tx = 0; i < 8; i++) {
+		if ((stat & (1 << (i * 4)))) *hi |= 1 << i;
+		if ((stat & (2 << (i * 4)))) *lo |= 1 << i;
+		if ((stat & (4 << (i * 4)))) *rq |= 1 << i;
+		if ((stat & (8 << (i * 4)))) *tx |= 1 << i;
+	}
+	nv_wr32(i2c, 0x00dc60, intr);
+}
+
+static void
+nve0_aux_mask(struct nouveau_i2c *i2c, u32 type, u32 mask, u32 data)
+{
+	u32 temp = nv_rd32(i2c, 0x00dc68), i;
+	for (i = 0; i < 8; i++) {
+		if (mask & (1 << i)) {
+			if (!(data & (1 << i))) {
+				temp &= ~(type << (i * 4));
+				continue;
+			}
+			temp |= type << (i * 4);
+		}
+	}
+	nv_wr32(i2c, 0x00dc68, temp);
+}
+
+struct nouveau_oclass *
+nve0_i2c_oclass = &(struct nouveau_i2c_impl) {
+	.base.handle = NV_SUBDEV(I2C, 0xe0),
+	.base.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nouveau_i2c_ctor,
+		.dtor = _nouveau_i2c_dtor,
+		.init = _nouveau_i2c_init,
+		.fini = _nouveau_i2c_fini,
+	},
+	.sclass = nvd0_i2c_sclass,
+	.pad_x = &nv04_i2c_pad_oclass,
+	.pad_s = &nv94_i2c_pad_oclass,
+	.aux = 4,
+	.aux_stat = nve0_aux_stat,
+	.aux_mask = nve0_aux_mask,
+}.base;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/pad.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/pad.c
new file mode 100644
index 00000000000..e9e412477c1
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/pad.c
@@ -0,0 +1,84 @@
+/*
+ * Copyright 2014 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include "pad.h"
+
+int
+_nvkm_i2c_pad_fini(struct nouveau_object *object, bool suspend)
+{
+	struct nvkm_i2c_pad *pad = (void *)object;
+	DBG("-> NULL\n");
+	pad->port = NULL;
+	return nouveau_object_fini(&pad->base, suspend);
+}
+
+int
+_nvkm_i2c_pad_init(struct nouveau_object *object)
+{
+	struct nvkm_i2c_pad *pad = (void *)object;
+	DBG("-> PORT:%02x\n", pad->next->index);
+	pad->port = pad->next;
+	return nouveau_object_init(&pad->base);
+}
+
+int
+nvkm_i2c_pad_create_(struct nouveau_object *parent,
+		     struct nouveau_object *engine,
+		     struct nouveau_oclass *oclass, int index,
+		     int size, void **pobject)
+{
+	struct nouveau_i2c *i2c = (void *)engine;
+	struct nouveau_i2c_port *port;
+	struct nvkm_i2c_pad *pad;
+	int ret;
+
+	list_for_each_entry(port, &i2c->ports, head) {
+		pad = nvkm_i2c_pad(port);
+		if (pad->index == index) {
+			atomic_inc(&nv_object(pad)->refcount);
+			*pobject = pad;
+			return 1;
+		}
+	}
+
+	ret = nouveau_object_create_(parent, engine, oclass, 0, size, pobject);
+	pad = *pobject;
+	if (ret)
+		return ret;
+
+	pad->index = index;
+	return 0;
+}
+
+int
+_nvkm_i2c_pad_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+		   struct nouveau_oclass *oclass, void *data, u32 index,
+		   struct nouveau_object **pobject)
+{
+	struct nvkm_i2c_pad *pad;
+	int ret;
+	ret = nvkm_i2c_pad_create(parent, engine, oclass, index, &pad);
+	*pobject = nv_object(pad);
+	return ret;
+}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/pad.h b/drivers/gpu/drm/nouveau/core/subdev/i2c/pad.h
new file mode 100644
index 00000000000..452ac10c300
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/pad.h
@@ -0,0 +1,58 @@
+#ifndef __NVKM_I2C_PAD_H__
+#define __NVKM_I2C_PAD_H__
+
+#include "priv.h"
+
+struct nvkm_i2c_pad {
+	struct nouveau_object base;
+	int index;
+	struct nouveau_i2c_port *port;
+	struct nouveau_i2c_port *next;
+};
+
+static inline struct nvkm_i2c_pad *
+nvkm_i2c_pad(struct nouveau_i2c_port *port)
+{
+	struct nouveau_object *pad = nv_object(port);
+	while (pad->parent)
+		pad = pad->parent;
+	return (void *)pad;
+}
+
+#define nvkm_i2c_pad_create(p,e,o,i,d)                                         \
+	nvkm_i2c_pad_create_((p), (e), (o), (i), sizeof(**d), (void **)d)
+#define nvkm_i2c_pad_destroy(p) ({                                             \
+	struct nvkm_i2c_pad *_p = (p);                                         \
+	_nvkm_i2c_pad_dtor(nv_object(_p));                                     \
+})
+#define nvkm_i2c_pad_init(p) ({                                                \
+	struct nvkm_i2c_pad *_p = (p);                                         \
+	_nvkm_i2c_pad_init(nv_object(_p));                                     \
+})
+#define nvkm_i2c_pad_fini(p,s) ({                                              \
+	struct nvkm_i2c_pad *_p = (p);                                         \
+	_nvkm_i2c_pad_fini(nv_object(_p), (s));                                \
+})
+
+int nvkm_i2c_pad_create_(struct nouveau_object *, struct nouveau_object *,
+			 struct nouveau_oclass *, int index, int, void **);
+
+int _nvkm_i2c_pad_ctor(struct nouveau_object *, struct nouveau_object *,
+		       struct nouveau_oclass *, void *, u32,
+		       struct nouveau_object **);
+#define _nvkm_i2c_pad_dtor nouveau_object_destroy
+int _nvkm_i2c_pad_init(struct nouveau_object *);
+int _nvkm_i2c_pad_fini(struct nouveau_object *, bool);
+
+#ifndef MSG
+#define MSG(l,f,a...) do {                                                     \
+	struct nvkm_i2c_pad *_pad = (void *)pad;                               \
+	nv_##l(nv_object(_pad)->engine, "PAD:%c:%02x: "f,                      \
+	       _pad->index >= 0x100 ? 'X' : 'S',                               \
+	       _pad->index >= 0x100 ? _pad->index - 0x100 : _pad->index, ##a); \
+} while(0)
+#define DBG(f,a...) MSG(debug, f, ##a)
+#define ERR(f,a...) MSG(error, f, ##a)
+#endif
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/padnv04.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/padnv04.c
new file mode 100644
index 00000000000..2c4b61296dd
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/padnv04.c
@@ -0,0 +1,35 @@
+/*
+ * Copyright 2014 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include "pad.h"
+
+struct nouveau_oclass
+nv04_i2c_pad_oclass = {
+	.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = _nvkm_i2c_pad_ctor,
+		.dtor = _nvkm_i2c_pad_dtor,
+		.init = _nvkm_i2c_pad_init,
+		.fini = _nvkm_i2c_pad_fini,
+	},
+};
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/padnv94.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/padnv94.c
new file mode 100644
index 00000000000..0dc6753014f
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/padnv94.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2014 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Ben Skeggs
+ */
+
+#include "pad.h"
+
+struct nv94_i2c_pad {
+	struct nvkm_i2c_pad base;
+	int addr;
+};
+
+static int
+nv94_i2c_pad_fini(struct nouveau_object *object, bool suspend)
+{
+	struct nouveau_i2c *i2c = (void *)object->engine;
+	struct nv94_i2c_pad *pad = (void *)object;
+	nv_mask(i2c, 0x00e50c + pad->addr, 0x00000001, 0x00000001);
+	return nvkm_i2c_pad_fini(&pad->base, suspend);
+}
+
+static int
+nv94_i2c_pad_init(struct nouveau_object *object)
+{
+	struct nouveau_i2c *i2c = (void *)object->engine;
+	struct nv94_i2c_pad *pad = (void *)object;
+
+	switch (nv_oclass(pad->base.next)->handle) {
+	case NV_I2C_TYPE_DCBI2C(DCB_I2C_NVIO_AUX):
+		nv_mask(i2c, 0x00e500 + pad->addr, 0x0000c003, 0x00000002);
+		break;
+	case NV_I2C_TYPE_DCBI2C(DCB_I2C_NVIO_BIT):
+	default:
+		nv_mask(i2c, 0x00e500 + pad->addr, 0x0000c003, 0x0000c001);
+		break;
+	}
+
+	nv_mask(i2c, 0x00e50c + pad->addr, 0x00000001, 0x00000000);
+	return nvkm_i2c_pad_init(&pad->base);
+}
+
+static int
+nv94_i2c_pad_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+		  struct nouveau_oclass *oclass, void *data, u32 index,
+		  struct nouveau_object **pobject)
+{
+	struct nv94_i2c_pad *pad;
+	int ret;
+
+	ret = nvkm_i2c_pad_create(parent, engine, oclass, index, &pad);
+	*pobject = nv_object(pad);
+	if (ret)
+		return ret;
+
+	pad->addr = index * 0x50;;
+	return 0;
+}
+
+struct nouveau_oclass
+nv94_i2c_pad_oclass = {
+	.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = nv94_i2c_pad_ctor,
+		.dtor = _nvkm_i2c_pad_dtor,
+		.init = nv94_i2c_pad_init,
+		.fini = nv94_i2c_pad_fini,
+	},
+};
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/port.h b/drivers/gpu/drm/nouveau/core/subdev/i2c/port.h
new file mode 100644
index 00000000000..a8ff6e077af
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/port.h
@@ -0,0 +1,15 @@
+#ifndef __NVKM_I2C_PORT_H__
+#define __NVKM_I2C_PORT_H__
+
+#include "priv.h"
+
+#ifndef MSG
+#define MSG(l,f,a...) do {                                                     \
+	struct nouveau_i2c_port *_port = (void *)port;                         \
+	nv_##l(nv_object(_port)->engine, "PORT:%02x: "f, _port->index, ##a);   \
+} while(0)
+#define DBG(f,a...) MSG(debug, f, ##a)
+#define ERR(f,a...) MSG(error, f, ##a)
+#endif
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/priv.h b/drivers/gpu/drm/nouveau/core/subdev/i2c/priv.h
new file mode 100644
index 00000000000..780090b6425
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/priv.h
@@ -0,0 +1,85 @@
+#ifndef __NVKM_I2C_H__
+#define __NVKM_I2C_H__
+
+#include <subdev/i2c.h>
+
+extern struct nouveau_oclass nv04_i2c_pad_oclass;
+extern struct nouveau_oclass nv94_i2c_pad_oclass;
+
+#define nouveau_i2c_port_create(p,e,o,i,a,f,d)                                 \
+	nouveau_i2c_port_create_((p), (e), (o), (i), (a), (f),                 \
+				 sizeof(**d), (void **)d)
+#define nouveau_i2c_port_destroy(p) ({                                         \
+	struct nouveau_i2c_port *port = (p);                                   \
+	_nouveau_i2c_port_dtor(nv_object(i2c));                                \
+})
+#define nouveau_i2c_port_init(p)                                               \
+	nouveau_object_init(&(p)->base)
+#define nouveau_i2c_port_fini(p,s)                                             \
+	nouveau_object_fini(&(p)->base, (s))
+
+int nouveau_i2c_port_create_(struct nouveau_object *, struct nouveau_object *,
+			     struct nouveau_oclass *, u8,
+			     const struct i2c_algorithm *,
+			     const struct nouveau_i2c_func *,
+			     int, void **);
+void _nouveau_i2c_port_dtor(struct nouveau_object *);
+#define _nouveau_i2c_port_init nouveau_object_init
+int  _nouveau_i2c_port_fini(struct nouveau_object *, bool);
+
+#define nouveau_i2c_create(p,e,o,d)                                            \
+	nouveau_i2c_create_((p), (e), (o), sizeof(**d), (void **)d)
+#define nouveau_i2c_destroy(p) ({                                              \
+	struct nouveau_i2c *i2c = (p);                                         \
+	_nouveau_i2c_dtor(nv_object(i2c));                                     \
+})
+#define nouveau_i2c_init(p) ({                                                 \
+	struct nouveau_i2c *i2c = (p);                                         \
+	_nouveau_i2c_init(nv_object(i2c));                                     \
+})
+#define nouveau_i2c_fini(p,s) ({                                               \
+	struct nouveau_i2c *i2c = (p);                                         \
+	_nouveau_i2c_fini(nv_object(i2c), (s));                                \
+})
+
+int nouveau_i2c_create_(struct nouveau_object *, struct nouveau_object *,
+			struct nouveau_oclass *, int, void **);
+int  _nouveau_i2c_ctor(struct nouveau_object *, struct nouveau_object *,
+		       struct nouveau_oclass *, void *, u32,
+		       struct nouveau_object **);
+void _nouveau_i2c_dtor(struct nouveau_object *);
+int  _nouveau_i2c_init(struct nouveau_object *);
+int  _nouveau_i2c_fini(struct nouveau_object *, bool);
+
+extern struct nouveau_oclass nouveau_anx9805_sclass[];
+extern struct nouveau_oclass nvd0_i2c_sclass[];
+
+extern const struct i2c_algorithm nouveau_i2c_bit_algo;
+extern const struct i2c_algorithm nouveau_i2c_aux_algo;
+
+struct nouveau_i2c_impl {
+	struct nouveau_oclass base;
+
+	/* supported i2c port classes */
+	struct nouveau_oclass *sclass;
+	struct nouveau_oclass *pad_x;
+	struct nouveau_oclass *pad_s;
+
+	/* number of native dp aux channels present */
+	int aux;
+
+	/* read and ack pending interrupts, returning only data
+	 * for ports that have not been masked off, while still
+	 * performing the ack for anything that was pending.
+	 */
+	void (*aux_stat)(struct nouveau_i2c *, u32 *, u32 *, u32 *, u32 *);
+
+	/* mask on/off interrupt types for a given set of auxch
+	 */
+	void (*aux_mask)(struct nouveau_i2c *, u32, u32, u32);
+};
+
+void nv94_aux_stat(struct nouveau_i2c *, u32 *, u32 *, u32 *, u32 *);
+void nv94_aux_mask(struct nouveau_i2c *, u32, u32, u32);
+
+#endif
diff --git a/drivers/gpu/drm/nouveau/core/subdev/ibus/gk20a.c b/drivers/gpu/drm/nouveau/core/subdev/ibus/gk20a.c
new file mode 100644
index 00000000000..245f0ebaa6a
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/core/subdev/ibus/gk20a.c
@@ -0,0 +1,103 @@
+/*
+ * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+#include <subdev/ibus.h>
+#include <subdev/timer.h>
+
+struct gk20a_ibus_priv {
+	struct nouveau_ibus base;
+};
+
+static void
+gk20a_ibus_init_priv_ring(struct gk20a_ibus_priv *priv)
+{
+	nv_mask(priv, 0x137250, 0x3f, 0);
+
+	nv_mask(priv, 0x000200, 0x20, 0);
+	usleep_range(20, 30);
+	nv_mask(priv, 0x000200, 0x20, 0x20);
+
+	nv_wr32(priv, 0x12004c, 0x4);
+	nv_wr32(priv, 0x122204, 0x2);
+	nv_rd32(priv, 0x122204);
+}
+
+static void
+gk20a_ibus_intr(struct nouveau_subdev *subdev)
+{
+	struct gk20a_ibus_priv *priv = (void *)subdev;
+	u32 status0 = nv_rd32(priv, 0x120058);
+
+	if (status0 & 0x7) {
+		nv_debug(priv, "resetting priv ring\n");
+		gk20a_ibus_init_priv_ring(priv);
+	}
+
+	/* Acknowledge interrupt */
+	nv_mask(priv, 0x12004c, 0x2, 0x2);
+
+	if (!nv_wait(subdev, 0x12004c, 0x3f, 0x00))
+		nv_warn(priv, "timeout waiting for ringmaster ack\n");
+}
+
+static int
+gk20a_ibus_init(struct nouveau_object *object)
+{
+	struct gk20a_ibus_priv *priv = (void *)object;
+	int ret;
+
+	ret = _nouveau_ibus_init(object);
+	if (ret)
+		return ret;
+
+	gk20a_ibus_init_priv_ring(priv);
+
+	return 0;
+}
+
+static int
+gk20a_ibus_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
+	       struct nouveau_oclass *oclass, void *data, u32 size,
+	       struct nouveau_object **pobject)
+{
+	struct gk20a_ibus_priv *priv;
+	int ret;
+
+	ret = nouveau_ibus_create(parent, engine, oclass, &priv);
+	*pobject = nv_object(priv);
+	if (ret)
+		return ret;
+
+	nv_subdev(priv)->intr = gk20a_ibus_intr;
+	return 0;
+}
+
+struct nouveau_oclass
+gk20a_ibus_oclass = {
+	.handle = NV_SUBDEV(IBUS, 0xea),
+	.ofuncs = &(struct nouveau_ofuncs) {
+		.ctor = gk20a_ibus_ctor,
+		.dtor = _nouveau_ibus_dtor,
+		.init = gk20a_ibus_init,
+		.fini = _nouveau_ibus_fini,
+	},
+};
diff --git a/drivers/gpu/drm/nouveau/core/subdev/ibus/nve0.c b/drivers/gpu/drm/nouveau/core/subdev/ibus/nve0.c
index 7120124dcea..ebef970a064 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/ibus/nve0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/ibus/nve0.c
@@ -95,6 +95,23 @@ nve0_ibus_intr(struct nouveau_subdev *subdev)
 }
 
 static int
+nve0_ibus_init(struct nouveau_object *object)
+{
+	struct nve0_ibus_priv *priv = (void *)object;
+	int ret = nouveau_ibus_init(&priv->base);
+	if (ret == 0) {
+		nv_mask(priv, 0x122318, 0x0003ffff, 0x00001000);
+		nv_mask(priv, 0x12231c, 0x0003ffff, 0x00000200);
+		nv_mask(priv, 0x122310, 0x0003ffff, 0x00000800);
+		nv_mask(priv, 0x122348, 0x0003ffff, 0x00000100);
+		nv_mask(priv, 0x1223b0, 0x0003ffff, 0x00000fff);
+		nv_mask(priv, 0x122348, 0x0003ffff, 0x00000200);
+		nv_mask(priv, 0x122358, 0x0003ffff, 0x00002880);
+	}
+	return ret;
+}
+
+static int
 nve0_ibus_ctor(struct nouveau_object *parent, struct nouveau_object *engine,
 	       struct nouveau_oclass *oclass, void *data, u32 size,
 	       struct nouveau_object **pobject)
@@ -117,7 +134,7 @@ nve0_ibus_oclass = {
 	.ofuncs = &(struct nouveau_ofuncs) {
 		.ctor = nve0_ibus_ctor,
 		.dtor = _nouveau_ibus_dtor,
-		.init = _nouveau_ibus_init,
+		.init = nve0_ibus_init,
 		.fini = _nouveau_ibus_fini,
 	},
 };
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
index e8822a934c4..9ca93e2718f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv50.c
@@ -26,6 +26,7 @@
 
 const struct nouveau_mc_intr
 nv50_mc_intr[] = {
+	{ 0x04000000, NVDEV_ENGINE_DISP },  /* DISP before FIFO, so pageflip-timestamping works! */
 	{ 0x00000001, NVDEV_ENGINE_MPEG },
 	{ 0x00000100, NVDEV_ENGINE_FIFO },
 	{ 0x00001000, NVDEV_ENGINE_GR },
@@ -33,8 +34,8 @@ nv50_mc_intr[] = {
 	{ 0x00008000, NVDEV_ENGINE_BSP },	/* NV84- */
 	{ 0x00020000, NVDEV_ENGINE_VP },	/* NV84- */
 	{ 0x00100000, NVDEV_SUBDEV_TIMER },
-	{ 0x00200000, NVDEV_SUBDEV_GPIO },
-	{ 0x04000000, NVDEV_ENGINE_DISP },
+	{ 0x00200000, NVDEV_SUBDEV_GPIO },	/* PMGR->GPIO */
+	{ 0x00200000, NVDEV_SUBDEV_I2C }, 	/* PMGR->I2C/AUX */
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x80000000, NVDEV_ENGINE_SW },
 	{ 0x0002d101, NVDEV_SUBDEV_FB },
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
index f8a6f18e2d3..3c76d9038f3 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv98.c
@@ -26,6 +26,7 @@
 
 static const struct nouveau_mc_intr
 nv98_mc_intr[] = {
+	{ 0x04000000, NVDEV_ENGINE_DISP },  /* DISP first, so pageflip timestamps work */
 	{ 0x00000001, NVDEV_ENGINE_PPP },
 	{ 0x00000100, NVDEV_ENGINE_FIFO },
 	{ 0x00001000, NVDEV_ENGINE_GR },
@@ -35,9 +36,9 @@ nv98_mc_intr[] = {
 	{ 0x00040000, NVDEV_SUBDEV_PWR },	/* NVA3:NVC0 */
 	{ 0x00080000, NVDEV_SUBDEV_THERM },	/* NVA3:NVC0 */
 	{ 0x00100000, NVDEV_SUBDEV_TIMER },
-	{ 0x00200000, NVDEV_SUBDEV_GPIO },
+	{ 0x00200000, NVDEV_SUBDEV_GPIO },	/* PMGR->GPIO */
+	{ 0x00200000, NVDEV_SUBDEV_I2C }, 	/* PMGR->I2C/AUX */
 	{ 0x00400000, NVDEV_ENGINE_COPY0 },	/* NVA3-     */
-	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x80000000, NVDEV_ENGINE_SW },
 	{ 0x0042d101, NVDEV_SUBDEV_FB },
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
index 34472d31709..f9c6a678b47 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nvc0.c
@@ -26,6 +26,7 @@
 
 const struct nouveau_mc_intr
 nvc0_mc_intr[] = {
+	{ 0x04000000, NVDEV_ENGINE_DISP },  /* DISP first, so pageflip timestamps work. */
 	{ 0x00000001, NVDEV_ENGINE_PPP },
 	{ 0x00000020, NVDEV_ENGINE_COPY0 },
 	{ 0x00000040, NVDEV_ENGINE_COPY1 },
@@ -37,10 +38,10 @@ nvc0_mc_intr[] = {
 	{ 0x00040000, NVDEV_SUBDEV_THERM },
 	{ 0x00020000, NVDEV_ENGINE_VP },
 	{ 0x00100000, NVDEV_SUBDEV_TIMER },
-	{ 0x00200000, NVDEV_SUBDEV_GPIO },
+	{ 0x00200000, NVDEV_SUBDEV_GPIO },	/* PMGR->GPIO */
+	{ 0x00200000, NVDEV_SUBDEV_I2C },	/* PMGR->I2C/AUX */
 	{ 0x01000000, NVDEV_SUBDEV_PWR },
 	{ 0x02000000, NVDEV_SUBDEV_LTCG },
-	{ 0x04000000, NVDEV_ENGINE_DISP },
 	{ 0x08000000, NVDEV_SUBDEV_FB },
 	{ 0x10000000, NVDEV_SUBDEV_BUS },
 	{ 0x40000000, NVDEV_SUBDEV_IBUS },
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mxm/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/mxm/nv50.c
index 64f8b4702bf..fcaabe8456e 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mxm/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mxm/nv50.c
@@ -150,7 +150,7 @@ mxm_dcb_sanitise_entry(struct nouveau_bios *bios, void *data, int idx, u16 pdcb)
 	 * common example is DP->eDP.
 	 */
 	conn  = bios->data;
-	conn += dcb_conn(bios, (ctx.outp[0] & 0x0000f000) >> 12, &ver, &len);
+	conn += nvbios_connEe(bios, (ctx.outp[0] & 0x0000f000) >> 12, &ver, &len);
 	type  = conn[0];
 	switch (ctx.desc.conn_type) {
 	case 0x01: /* LVDS */
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/host.fuc b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/host.fuc
index 2284ecb1c9b..c2bb616a8da 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/host.fuc
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/host.fuc
@@ -83,7 +83,7 @@ host_send:
 		// increment GET
 		add b32 $r1 0x1
 		and $r14 $r1 #fifo_qmaskf
-		nv_iowr(NV_PPWR_FIFO_GET(0), $r1)
+		nv_iowr(NV_PPWR_FIFO_GET(0), $r14)
 		bra #host_send
 	host_send_done:
 	ret
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h
index 4bd43a99fdc..39a5dc150a0 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nv108.fuc.h
@@ -1018,7 +1018,7 @@ uint32_t nv108_pwr_code[] = {
 	0xb600023f,
 	0x1ec40110,
 	0x04b0400f,
-	0xbd0001f6,
+	0xbd000ef6,
 	0xc70ef404,
 /* 0x0328: host_send_done */
 /* 0x032a: host_recv */
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h
index 5a73fa62097..254205cd516 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nva3.fuc.h
@@ -1124,7 +1124,7 @@ uint32_t nva3_pwr_code[] = {
 	0x0f1ec401,
 	0x04b007f1,
 	0xd00604b6,
-	0x04bd0001,
+	0x04bd000e,
 /* 0x03cb: host_send_done */
 	0xf8ba0ef4,
 /* 0x03cd: host_recv */
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h
index 4dba00d2dd1..7ac87405d01 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvc0.fuc.h
@@ -1124,7 +1124,7 @@ uint32_t nvc0_pwr_code[] = {
 	0x0f1ec401,
 	0x04b007f1,
 	0xd00604b6,
-	0x04bd0001,
+	0x04bd000e,
 /* 0x03cb: host_send_done */
 	0xf8ba0ef4,
 /* 0x03cd: host_recv */
diff --git a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h
index 5e24c6bc041..cd9ff1a7328 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h
+++ b/drivers/gpu/drm/nouveau/core/subdev/pwr/fuc/nvd0.fuc.h
@@ -1033,7 +1033,7 @@ uint32_t nvd0_pwr_code[] = {
 	0xb6026b21,
 	0x1ec40110,
 	0xb007f10f,
-	0x0001d004,
+	0x000ed004,
 	0x0ef404bd,
 /* 0x0365: host_send_done */
 /* 0x0367: host_recv */
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/ic.c b/drivers/gpu/drm/nouveau/core/subdev/therm/ic.c
index 7610fc5f8fa..ca9ad9fd47b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/ic.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/ic.c
@@ -60,9 +60,9 @@ static struct nouveau_i2c_board_info
 nv_board_infos[] = {
 	{ { I2C_BOARD_INFO("w83l785ts", 0x2d) }, 0 },
 	{ { I2C_BOARD_INFO("w83781d", 0x2d) }, 0  },
-	{ { I2C_BOARD_INFO("adt7473", 0x2e) }, 20  },
-	{ { I2C_BOARD_INFO("adt7473", 0x2d) }, 20  },
-	{ { I2C_BOARD_INFO("adt7473", 0x2c) }, 20  },
+	{ { I2C_BOARD_INFO("adt7473", 0x2e) }, 40  },
+	{ { I2C_BOARD_INFO("adt7473", 0x2d) }, 40  },
+	{ { I2C_BOARD_INFO("adt7473", 0x2c) }, 40  },
 	{ { I2C_BOARD_INFO("f75375", 0x2e) }, 0  },
 	{ { I2C_BOARD_INFO("lm99", 0x4c) }, 0  },
 	{ { I2C_BOARD_INFO("lm90", 0x4c) }, 0  },
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/nva3.c b/drivers/gpu/drm/nouveau/core/subdev/therm/nva3.c
index 3b2c4580098..0478b2e3fb1 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/nva3.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/nva3.c
@@ -36,7 +36,7 @@ nva3_therm_fan_sense(struct nouveau_therm *therm)
 	u32 tach = nv_rd32(therm, 0x00e728) & 0x0000ffff;
 	u32 ctrl = nv_rd32(therm, 0x00e720);
 	if (ctrl & 0x00000001)
-		return tach * 60;
+		return tach * 60 / 2;
 	return -ENODEV;
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c b/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c
index cfde9eb44ad..6212537b90c 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/temp.c
@@ -192,11 +192,11 @@ alarm_timer_callback(struct nouveau_alarm *alarm)
 	nouveau_therm_threshold_hyst_polling(therm, &sensor->thrs_shutdown,
 					     NOUVEAU_THERM_THRS_SHUTDOWN);
 
+	spin_unlock_irqrestore(&priv->sensor.alarm_program_lock, flags);
+
 	/* schedule the next poll in one second */
 	if (therm->temp_get(therm) >= 0 && list_empty(&alarm->head))
-		ptimer->alarm(ptimer, 1000 * 1000 * 1000, alarm);
-
-	spin_unlock_irqrestore(&priv->sensor.alarm_program_lock, flags);
+		ptimer->alarm(ptimer, 1000000000ULL, alarm);
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dac.c b/drivers/gpu/drm/nouveau/dispnv04/dac.c
index 434b920f6bd..a96dda48718 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dac.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dac.c
@@ -414,7 +414,7 @@ static void nv04_dac_commit(struct drm_encoder *encoder)
 	helper->dpms(encoder, DRM_MODE_DPMS_ON);
 
 	NV_DEBUG(drm, "Output %s is running on CRTC %d using output %c\n",
-		 drm_get_connector_name(&nouveau_encoder_connector_get(nv_encoder)->base),
+		 nouveau_encoder_connector_get(nv_encoder)->base.name,
 		 nv_crtc->index, '@' + ffs(nv_encoder->dcb->or));
 }
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dfp.c b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
index a2d669b4acf..e57babb206d 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dfp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
@@ -477,7 +477,7 @@ static void nv04_dfp_commit(struct drm_encoder *encoder)
 	helper->dpms(encoder, DRM_MODE_DPMS_ON);
 
 	NV_DEBUG(drm, "Output %s is running on CRTC %d using output %c\n",
-		 drm_get_connector_name(&nouveau_encoder_connector_get(nv_encoder)->base),
+		 nouveau_encoder_connector_get(nv_encoder)->base.name,
 		 nv_crtc->index, '@' + ffs(nv_encoder->dcb->or));
 }
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c
index 2f1ed61f7c8..4342fdaee70 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c
@@ -115,7 +115,7 @@ nv04_display_create(struct drm_device *dev)
 				 &dev->mode_config.connector_list, head) {
 		if (!connector->encoder_ids[0]) {
 			NV_WARN(drm, "%s has no encoders, removing\n",
-				drm_get_connector_name(connector));
+				connector->name);
 			connector->funcs->destroy(connector);
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
index 244822df8ff..8667620b703 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
@@ -171,7 +171,8 @@ static void nv04_tv_commit(struct drm_encoder *encoder)
 	helper->dpms(encoder, DRM_MODE_DPMS_ON);
 
 	NV_DEBUG(drm, "Output %s is running on CRTC %d using output %c\n",
-		 drm_get_connector_name(&nouveau_encoder_connector_get(nv_encoder)->base), nv_crtc->index, '@' + ffs(nv_encoder->dcb->or));
+		 nouveau_encoder_connector_get(nv_encoder)->base.name,
+		 nv_crtc->index, '@' + ffs(nv_encoder->dcb->or));
 }
 
 static void nv04_tv_destroy(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
index acef48f4a4e..195bd8e86c6 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
@@ -612,8 +612,7 @@ static void nv17_tv_commit(struct drm_encoder *encoder)
 	helper->dpms(encoder, DRM_MODE_DPMS_ON);
 
 	NV_INFO(drm, "Output %s is running on CRTC %d using output %c\n",
-		drm_get_connector_name(
-			&nouveau_encoder_connector_get(nv_encoder)->base),
+		nouveau_encoder_connector_get(nv_encoder)->base.name,
 		nv_crtc->index, '@' + ffs(nv_encoder->dcb->or));
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index d07ce028af5..1fa222e8f00 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -44,6 +44,7 @@
 
 #include <subdev/i2c.h>
 #include <subdev/gpio.h>
+#include <engine/disp.h>
 
 MODULE_PARM_DESC(tv_disable, "Disable TV-out detection");
 static int nouveau_tv_disable = 0;
@@ -75,7 +76,8 @@ find_encoder(struct drm_connector *connector, int type)
 			continue;
 		nv_encoder = nouveau_encoder(obj_to_encoder(obj));
 
-		if (type == DCB_OUTPUT_ANY || nv_encoder->dcb->type == type)
+		if (type == DCB_OUTPUT_ANY ||
+		    (nv_encoder->dcb && nv_encoder->dcb->type == type))
 			return nv_encoder;
 	}
 
@@ -100,22 +102,24 @@ static void
 nouveau_connector_destroy(struct drm_connector *connector)
 {
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
-	nouveau_event_ref(NULL, &nv_connector->hpd_func);
+	nouveau_event_ref(NULL, &nv_connector->hpd);
 	kfree(nv_connector->edid);
 	drm_sysfs_connector_remove(connector);
 	drm_connector_cleanup(connector);
+	if (nv_connector->aux.transfer)
+		drm_dp_aux_unregister(&nv_connector->aux);
 	kfree(connector);
 }
 
-static struct nouveau_i2c_port *
-nouveau_connector_ddc_detect(struct drm_connector *connector,
-			     struct nouveau_encoder **pnv_encoder)
+static struct nouveau_encoder *
+nouveau_connector_ddc_detect(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_gpio *gpio = nouveau_gpio(drm->device);
-	struct nouveau_i2c_port *port = NULL;
+	struct nouveau_encoder *nv_encoder;
+	struct drm_mode_object *obj;
 	int i, panel = -ENODEV;
 
 	/* eDP panels need powering on by us (if the VBIOS doesn't default it
@@ -130,13 +134,9 @@ nouveau_connector_ddc_detect(struct drm_connector *connector,
 		}
 	}
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		struct nouveau_encoder *nv_encoder;
-		struct drm_mode_object *obj;
-		int id;
-
-		id = connector->encoder_ids[i];
-		if (!id)
+	for (i = 0; nv_encoder = NULL, i < DRM_CONNECTOR_MAX_ENCODER; i++) {
+		int id = connector->encoder_ids[i];
+		if (id == 0)
 			break;
 
 		obj = drm_mode_object_find(dev, id, DRM_MODE_OBJECT_ENCODER);
@@ -144,22 +144,24 @@ nouveau_connector_ddc_detect(struct drm_connector *connector,
 			continue;
 		nv_encoder = nouveau_encoder(obj_to_encoder(obj));
 
-		port = nv_encoder->i2c;
-		if (port && nv_probe_i2c(port, 0x50)) {
-			*pnv_encoder = nv_encoder;
-			break;
+		if (nv_encoder->dcb->type == DCB_OUTPUT_DP) {
+			int ret = nouveau_dp_detect(nv_encoder);
+			if (ret == 0)
+				break;
+		} else
+		if (nv_encoder->i2c) {
+			if (nv_probe_i2c(nv_encoder->i2c, 0x50))
+				break;
 		}
-
-		port = NULL;
 	}
 
 	/* eDP panel not detected, restore panel power GPIO to previous
 	 * state to avoid confusing the SOR for other output types.
 	 */
-	if (!port && panel == 0)
+	if (!nv_encoder && panel == 0)
 		gpio->set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, panel);
 
-	return port;
+	return nv_encoder;
 }
 
 static struct nouveau_encoder *
@@ -258,25 +260,17 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 	if (ret < 0 && ret != -EACCES)
 		return conn_status;
 
-	i2c = nouveau_connector_ddc_detect(connector, &nv_encoder);
-	if (i2c) {
+	nv_encoder = nouveau_connector_ddc_detect(connector);
+	if (nv_encoder && (i2c = nv_encoder->i2c) != NULL) {
 		nv_connector->edid = drm_get_edid(connector, &i2c->adapter);
 		drm_mode_connector_update_edid_property(connector,
 							nv_connector->edid);
 		if (!nv_connector->edid) {
 			NV_ERROR(drm, "DDC responded, but no EDID for %s\n",
-				 drm_get_connector_name(connector));
+				 connector->name);
 			goto detect_analog;
 		}
 
-		if (nv_encoder->dcb->type == DCB_OUTPUT_DP &&
-		    !nouveau_dp_detect(to_drm_encoder(nv_encoder))) {
-			NV_ERROR(drm, "Detected %s, but failed init\n",
-				 drm_get_connector_name(connector));
-			conn_status = connector_status_disconnected;
-			goto out;
-		}
-
 		/* Override encoder type for DVI-I based on whether EDID
 		 * says the display is digital or analog, both use the
 		 * same i2c channel so the value returned from ddc_detect
@@ -437,7 +431,7 @@ nouveau_connector_force(struct drm_connector *connector)
 	nv_encoder = find_encoder(connector, type);
 	if (!nv_encoder) {
 		NV_ERROR(drm, "can't find encoder to force %s on!\n",
-			 drm_get_connector_name(connector));
+			 connector->name);
 		connector->status = connector_status_disconnected;
 		return;
 	}
@@ -912,33 +906,103 @@ nouveau_connector_funcs_lvds = {
 };
 
 static void
+nouveau_connector_dp_dpms(struct drm_connector *connector, int mode)
+{
+	struct nouveau_encoder *nv_encoder = NULL;
+
+	if (connector->encoder)
+		nv_encoder = nouveau_encoder(connector->encoder);
+	if (nv_encoder && nv_encoder->dcb &&
+	    nv_encoder->dcb->type == DCB_OUTPUT_DP) {
+		if (mode == DRM_MODE_DPMS_ON) {
+			u8 data = DP_SET_POWER_D0;
+			nv_wraux(nv_encoder->i2c, DP_SET_POWER, &data, 1);
+			usleep_range(1000, 2000);
+		} else {
+			u8 data = DP_SET_POWER_D3;
+			nv_wraux(nv_encoder->i2c, DP_SET_POWER, &data, 1);
+		}
+	}
+
+	drm_helper_connector_dpms(connector, mode);
+}
+
+static const struct drm_connector_funcs
+nouveau_connector_funcs_dp = {
+	.dpms = nouveau_connector_dp_dpms,
+	.save = NULL,
+	.restore = NULL,
+	.detect = nouveau_connector_detect,
+	.destroy = nouveau_connector_destroy,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.set_property = nouveau_connector_set_property,
+	.force = nouveau_connector_force
+};
+
+static void
 nouveau_connector_hotplug_work(struct work_struct *work)
 {
 	struct nouveau_connector *nv_connector =
-		container_of(work, struct nouveau_connector, hpd_work);
+		container_of(work, typeof(*nv_connector), work);
 	struct drm_connector *connector = &nv_connector->base;
-	struct drm_device *dev = connector->dev;
-	struct nouveau_drm *drm = nouveau_drm(dev);
-	struct nouveau_gpio *gpio = nouveau_gpio(drm->device);
-	bool plugged = gpio->get(gpio, 0, nv_connector->hpd.func, 0xff);
+	struct nouveau_drm *drm = nouveau_drm(connector->dev);
+	const char *name = connector->name;
 
-	NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un",
-		 drm_get_connector_name(connector));
+	if (nv_connector->status & NVKM_HPD_IRQ) {
+	} else {
+		bool plugged = (nv_connector->status != NVKM_HPD_UNPLUG);
 
-	if (plugged)
-		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
-	else
-		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
+		NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name);
 
-	drm_helper_hpd_irq_event(dev);
+		if (plugged)
+			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
+		else
+			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
+		drm_helper_hpd_irq_event(connector->dev);
+	}
+
+	nouveau_event_get(nv_connector->hpd);
 }
 
 static int
-nouveau_connector_hotplug(void *data, int index)
+nouveau_connector_hotplug(void *data, u32 type, int index)
 {
 	struct nouveau_connector *nv_connector = data;
-	schedule_work(&nv_connector->hpd_work);
-	return NVKM_EVENT_KEEP;
+	nv_connector->status = type;
+	schedule_work(&nv_connector->work);
+	return NVKM_EVENT_DROP;
+}
+
+static ssize_t
+nouveau_connector_aux_xfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg)
+{
+	struct nouveau_connector *nv_connector =
+		container_of(aux, typeof(*nv_connector), aux);
+	struct nouveau_encoder *nv_encoder;
+	struct nouveau_i2c_port *port;
+	int ret;
+
+	nv_encoder = find_encoder(&nv_connector->base, DCB_OUTPUT_DP);
+	if (!nv_encoder || !(port = nv_encoder->i2c))
+		return -ENODEV;
+	if (WARN_ON(msg->size > 16))
+		return -E2BIG;
+	if (msg->size == 0)
+		return msg->size;
+
+	ret = nouveau_i2c(port)->acquire(port, 0);
+	if (ret)
+		return ret;
+
+	ret = port->func->aux(port, false, msg->request, msg->address,
+			      msg->buffer, msg->size);
+	nouveau_i2c(port)->release(port);
+	if (ret >= 0) {
+		msg->reply = ret;
+		return msg->size;
+	}
+
+	return ret;
 }
 
 static int
@@ -974,9 +1038,9 @@ nouveau_connector_create(struct drm_device *dev, int index)
 {
 	const struct drm_connector_funcs *funcs = &nouveau_connector_funcs;
 	struct nouveau_drm *drm = nouveau_drm(dev);
-	struct nouveau_gpio *gpio = nouveau_gpio(drm->device);
 	struct nouveau_display *disp = nouveau_display(dev);
 	struct nouveau_connector *nv_connector = NULL;
+	struct nouveau_disp *pdisp = nouveau_disp(drm->device);
 	struct drm_connector *connector;
 	int type, ret = 0;
 	bool dummy;
@@ -992,33 +1056,15 @@ nouveau_connector_create(struct drm_device *dev, int index)
 		return ERR_PTR(-ENOMEM);
 
 	connector = &nv_connector->base;
-	INIT_WORK(&nv_connector->hpd_work, nouveau_connector_hotplug_work);
 	nv_connector->index = index;
 
 	/* attempt to parse vbios connector type and hotplug gpio */
 	nv_connector->dcb = olddcb_conn(dev, index);
 	if (nv_connector->dcb) {
-		static const u8 hpd[16] = {
-			0xff, 0x07, 0x08, 0xff, 0xff, 0x51, 0x52, 0xff,
-			0xff, 0xff, 0xff, 0xff, 0xff, 0x5e, 0x5f, 0x60,
-		};
-
 		u32 entry = ROM16(nv_connector->dcb[0]);
 		if (olddcb_conntab(dev)[3] >= 4)
 			entry |= (u32)ROM16(nv_connector->dcb[2]) << 16;
 
-		ret = gpio->find(gpio, 0, hpd[ffs((entry & 0x07033000) >> 12)],
-				 DCB_GPIO_UNUSED, &nv_connector->hpd);
-		if (ret)
-			nv_connector->hpd.func = DCB_GPIO_UNUSED;
-
-		if (nv_connector->hpd.func != DCB_GPIO_UNUSED) {
-			nouveau_event_new(gpio->events, nv_connector->hpd.line,
-					  nouveau_connector_hotplug,
-					  nv_connector,
-					 &nv_connector->hpd_func);
-		}
-
 		nv_connector->type = nv_connector->dcb[0];
 		if (drm_conntype_from_dcb(nv_connector->type) ==
 					  DRM_MODE_CONNECTOR_Unknown) {
@@ -1040,7 +1086,6 @@ nouveau_connector_create(struct drm_device *dev, int index)
 		}
 	} else {
 		nv_connector->type = DCB_CONNECTOR_NONE;
-		nv_connector->hpd.func = DCB_GPIO_UNUSED;
 	}
 
 	/* no vbios data, or an unknown dcb connector type - attempt to
@@ -1080,8 +1125,8 @@ nouveau_connector_create(struct drm_device *dev, int index)
 		}
 	}
 
-	type = drm_conntype_from_dcb(nv_connector->type);
-	if (type == DRM_MODE_CONNECTOR_LVDS) {
+	switch ((type = drm_conntype_from_dcb(nv_connector->type))) {
+	case DRM_MODE_CONNECTOR_LVDS:
 		ret = nouveau_bios_parse_lvds_table(dev, 0, &dummy, &dummy);
 		if (ret) {
 			NV_ERROR(drm, "Error parsing LVDS table, disabling\n");
@@ -1090,8 +1135,23 @@ nouveau_connector_create(struct drm_device *dev, int index)
 		}
 
 		funcs = &nouveau_connector_funcs_lvds;
-	} else {
+		break;
+	case DRM_MODE_CONNECTOR_DisplayPort:
+	case DRM_MODE_CONNECTOR_eDP:
+		nv_connector->aux.dev = dev->dev;
+		nv_connector->aux.transfer = nouveau_connector_aux_xfer;
+		ret = drm_dp_aux_register(&nv_connector->aux);
+		if (ret) {
+			NV_ERROR(drm, "failed to register aux channel\n");
+			kfree(nv_connector);
+			return ERR_PTR(ret);
+		}
+
+		funcs = &nouveau_connector_funcs_dp;
+		break;
+	default:
 		funcs = &nouveau_connector_funcs;
+		break;
 	}
 
 	/* defaults, will get overridden in detect() */
@@ -1166,10 +1226,16 @@ nouveau_connector_create(struct drm_device *dev, int index)
 		break;
 	}
 
-	connector->polled = DRM_CONNECTOR_POLL_CONNECT;
-	if (nv_connector->hpd.func != DCB_GPIO_UNUSED)
+	ret = nouveau_event_new(pdisp->hpd, NVKM_HPD, index,
+				nouveau_connector_hotplug,
+				nv_connector, &nv_connector->hpd);
+	if (ret)
+		connector->polled = DRM_CONNECTOR_POLL_CONNECT;
+	else
 		connector->polled = DRM_CONNECTOR_POLL_HPD;
 
+	INIT_WORK(&nv_connector->work, nouveau_connector_hotplug_work);
+
 	drm_sysfs_connector_add(connector);
 	return connector;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index 264a778f473..8861b6c579a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -28,12 +28,12 @@
 #define __NOUVEAU_CONNECTOR_H__
 
 #include <drm/drm_edid.h>
+#include <drm/drm_dp_helper.h>
 #include "nouveau_crtc.h"
 
 #include <core/event.h>
 
 #include <subdev/bios.h>
-#include <subdev/bios/gpio.h>
 
 struct nouveau_i2c_port;
 
@@ -67,9 +67,11 @@ struct nouveau_connector {
 	u8 index;
 	u8 *dcb;
 
-	struct dcb_gpio_func hpd;
-	struct work_struct hpd_work;
-	struct nouveau_eventh *hpd_func;
+	struct nouveau_eventh *hpd;
+	u32 status;
+	struct work_struct work;
+
+	struct drm_dp_aux aux;
 
 	int dithering_mode;
 	int dithering_depth;
diff --git a/drivers/gpu/drm/nouveau/nouveau_crtc.h b/drivers/gpu/drm/nouveau/nouveau_crtc.h
index d1e5890784d..a0534489d23 100644
--- a/drivers/gpu/drm/nouveau/nouveau_crtc.h
+++ b/drivers/gpu/drm/nouveau/nouveau_crtc.h
@@ -74,7 +74,7 @@ struct nouveau_crtc {
 
 static inline struct nouveau_crtc *nouveau_crtc(struct drm_crtc *crtc)
 {
-	return container_of(crtc, struct nouveau_crtc, base);
+	return crtc ? container_of(crtc, struct nouveau_crtc, base) : NULL;
 }
 
 static inline struct drm_crtc *to_drm_crtc(struct nouveau_crtc *crtc)
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index da764a4ed95..47ad74255bf 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -42,7 +42,7 @@
 #include <core/class.h>
 
 static int
-nouveau_display_vblank_handler(void *data, int head)
+nouveau_display_vblank_handler(void *data, u32 type, int head)
 {
 	struct nouveau_drm *drm = data;
 	drm_handle_vblank(drm->dev, head);
@@ -178,7 +178,7 @@ nouveau_display_vblank_init(struct drm_device *dev)
 		return -ENOMEM;
 
 	for (i = 0; i < dev->mode_config.num_crtc; i++) {
-		ret = nouveau_event_new(pdisp->vblank, i,
+		ret = nouveau_event_new(pdisp->vblank, 1, i,
 					nouveau_display_vblank_handler,
 					drm, &disp->vblank[i]);
 		if (ret) {
@@ -393,7 +393,7 @@ nouveau_display_init(struct drm_device *dev)
 	/* enable hotplug interrupts */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		struct nouveau_connector *conn = nouveau_connector(connector);
-		if (conn->hpd_func) nouveau_event_get(conn->hpd_func);
+		if (conn->hpd) nouveau_event_get(conn->hpd);
 	}
 
 	return ret;
@@ -408,7 +408,7 @@ nouveau_display_fini(struct drm_device *dev)
 	/* disable hotplug interrupts */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		struct nouveau_connector *conn = nouveau_connector(connector);
-		if (conn->hpd_func) nouveau_event_put(conn->hpd_func);
+		if (conn->hpd) nouveau_event_put(conn->hpd);
 	}
 
 	drm_kms_helper_poll_disable(dev);
@@ -736,6 +736,9 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		  fb->bits_per_pixel, fb->pitches[0], crtc->x, crtc->y,
 		  new_bo->bo.offset };
 
+	/* Keep vblanks on during flip, for the target crtc of this flip */
+	drm_vblank_get(dev, nouveau_crtc(crtc)->index);
+
 	/* Emit a page flip */
 	if (nv_device(drm->device)->card_type >= NV_50) {
 		ret = nv50_display_flip_next(crtc, fb, chan, swap_interval);
@@ -779,6 +782,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	return 0;
 
 fail_unreserve:
+	drm_vblank_put(dev, nouveau_crtc(crtc)->index);
 	ttm_bo_unreserve(&old_bo->bo);
 fail_unpin:
 	mutex_unlock(&chan->cli->mutex);
@@ -798,6 +802,7 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 	struct drm_device *dev = drm->dev;
 	struct nouveau_page_flip_state *s;
 	unsigned long flags;
+	int crtcid = -1;
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 
@@ -808,8 +813,16 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 	}
 
 	s = list_first_entry(&fctx->flip, struct nouveau_page_flip_state, head);
-	if (s->event)
-		drm_send_vblank_event(dev, s->crtc, s->event);
+	if (s->event) {
+		/* Vblank timestamps/counts are only correct on >= NV-50 */
+		if (nv_device(drm->device)->card_type >= NV_50)
+			crtcid = s->crtc;
+
+		drm_send_vblank_event(dev, crtcid, s->event);
+	}
+
+	/* Give up ownership of vblank for page-flipped crtc */
+	drm_vblank_put(dev, s->crtc);
 
 	list_del(&s->head);
 	if (ps)
diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c
index 36fd2250056..5675ffc175a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dp.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dp.c
@@ -55,11 +55,10 @@ nouveau_dp_probe_oui(struct drm_device *dev, struct nouveau_i2c_port *auxch,
 
 }
 
-bool
-nouveau_dp_detect(struct drm_encoder *encoder)
+int
+nouveau_dp_detect(struct nouveau_encoder *nv_encoder)
 {
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct drm_device *dev = encoder->dev;
+	struct drm_device *dev = nv_encoder->base.base.dev;
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nouveau_i2c_port *auxch;
 	u8 *dpcd = nv_encoder->dp.dpcd;
@@ -67,11 +66,11 @@ nouveau_dp_detect(struct drm_encoder *encoder)
 
 	auxch = nv_encoder->i2c;
 	if (!auxch)
-		return false;
+		return -ENODEV;
 
 	ret = nv_rdaux(auxch, DP_DPCD_REV, dpcd, 8);
 	if (ret)
-		return false;
+		return ret;
 
 	nv_encoder->dp.link_bw = 27000 * dpcd[1];
 	nv_encoder->dp.link_nr = dpcd[2] & DP_MAX_LANE_COUNT_MASK;
@@ -91,6 +90,5 @@ nouveau_dp_detect(struct drm_encoder *encoder)
 		     nv_encoder->dp.link_nr, nv_encoder->dp.link_bw);
 
 	nouveau_dp_probe_oui(dev, auxch, dpcd);
-
-	return true;
+	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index ddd83756b9a..5425ffe3931 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -652,12 +652,12 @@ int nouveau_pmops_resume(struct device *dev)
 	ret = nouveau_do_resume(drm_dev);
 	if (ret)
 		return ret;
-	if (drm_dev->mode_config.num_crtc)
-		nouveau_fbcon_set_suspend(drm_dev, 0);
 
-	nouveau_fbcon_zfill_all(drm_dev);
-	if (drm_dev->mode_config.num_crtc)
+	if (drm_dev->mode_config.num_crtc) {
 		nouveau_display_resume(drm_dev);
+		nouveau_fbcon_set_suspend(drm_dev, 0);
+	}
+
 	return 0;
 }
 
@@ -683,11 +683,12 @@ static int nouveau_pmops_thaw(struct device *dev)
 	ret = nouveau_do_resume(drm_dev);
 	if (ret)
 		return ret;
-	if (drm_dev->mode_config.num_crtc)
-		nouveau_fbcon_set_suspend(drm_dev, 0);
-	nouveau_fbcon_zfill_all(drm_dev);
-	if (drm_dev->mode_config.num_crtc)
+
+	if (drm_dev->mode_config.num_crtc) {
 		nouveau_display_resume(drm_dev);
+		nouveau_fbcon_set_suspend(drm_dev, 0);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_encoder.h b/drivers/gpu/drm/nouveau/nouveau_encoder.h
index 24660c0f713..5f0e37fc284 100644
--- a/drivers/gpu/drm/nouveau/nouveau_encoder.h
+++ b/drivers/gpu/drm/nouveau/nouveau_encoder.h
@@ -46,6 +46,7 @@ struct nouveau_encoder {
 	/* different to drm_encoder.crtc, this reflects what's
 	 * actually programmed on the hw, not the proposed crtc */
 	struct drm_crtc *crtc;
+	u32 ctrl;
 
 	struct drm_display_mode mode;
 	int last_dpms;
@@ -84,9 +85,7 @@ get_slave_funcs(struct drm_encoder *enc)
 }
 
 /* nouveau_dp.c */
-bool nouveau_dp_detect(struct drm_encoder *);
-void nouveau_dp_dpms(struct drm_encoder *, int mode, u32 datarate,
-		     struct nouveau_object *);
+int nouveau_dp_detect(struct nouveau_encoder *);
 
 struct nouveau_connector *
 nouveau_encoder_connector_get(struct nouveau_encoder *encoder);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 64a42cfd371..191665ee7f5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -531,17 +531,10 @@ nouveau_fbcon_set_suspend(struct drm_device *dev, int state)
 		if (state == 1)
 			nouveau_fbcon_save_disable_accel(dev);
 		fb_set_suspend(drm->fbcon->helper.fbdev, state);
-		if (state == 0)
+		if (state == 0) {
 			nouveau_fbcon_restore_accel(dev);
+			nouveau_fbcon_zfill(dev, drm->fbcon);
+		}
 		console_unlock();
 	}
 }
-
-void
-nouveau_fbcon_zfill_all(struct drm_device *dev)
-{
-	struct nouveau_drm *drm = nouveau_drm(dev);
-	if (drm->fbcon) {
-		nouveau_fbcon_zfill(dev, drm->fbcon);
-	}
-}
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.h b/drivers/gpu/drm/nouveau/nouveau_fbcon.h
index fdfc0c94fbc..fcff797d208 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.h
@@ -61,7 +61,6 @@ void nouveau_fbcon_gpu_lockup(struct fb_info *info);
 int nouveau_fbcon_init(struct drm_device *dev);
 void nouveau_fbcon_fini(struct drm_device *dev);
 void nouveau_fbcon_set_suspend(struct drm_device *dev, int state);
-void nouveau_fbcon_zfill_all(struct drm_device *dev);
 void nouveau_fbcon_save_disable_accel(struct drm_device *dev);
 void nouveau_fbcon_restore_accel(struct drm_device *dev);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 90074d620e3..ab5ea3b0d66 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -166,7 +166,7 @@ nouveau_fence_done(struct nouveau_fence *fence)
 }
 
 static int
-nouveau_fence_wait_uevent_handler(void *data, int index)
+nouveau_fence_wait_uevent_handler(void *data, u32 type, int index)
 {
 	struct nouveau_fence_priv *priv = data;
 	wake_up_all(&priv->waiting);
@@ -183,7 +183,7 @@ nouveau_fence_wait_uevent(struct nouveau_fence *fence, bool intr)
 	struct nouveau_eventh *handler;
 	int ret = 0;
 
-	ret = nouveau_event_new(pfifo->uevent, 0,
+	ret = nouveau_event_new(pfifo->uevent, 1, 0,
 				nouveau_fence_wait_uevent_handler,
 				priv, &handler);
 	if (ret)
diff --git a/drivers/gpu/drm/nouveau/nouveau_ioc32.c b/drivers/gpu/drm/nouveau/nouveau_ioc32.c
index c1a7e5a73a2..462679a8fec 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ioc32.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ioc32.c
@@ -57,7 +57,7 @@ long nouveau_compat_ioctl(struct file *filp, unsigned int cmd,
 		return drm_compat_ioctl(filp, cmd, arg);
 
 #if 0
-	if (nr < DRM_COMMAND_BASE + DRM_ARRAY_SIZE(mga_compat_ioctls))
+	if (nr < DRM_COMMAND_BASE + ARRAY_SIZE(mga_compat_ioctls))
 		fn = nouveau_compat_ioctls[nr - DRM_COMMAND_BASE];
 #endif
 	if (fn != NULL)
diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c
index fb84da3cb50..4f4c3fec691 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vga.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vga.c
@@ -64,12 +64,13 @@ static bool
 nouveau_switcheroo_can_switch(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	bool can_switch;
 
-	spin_lock(&dev->count_lock);
-	can_switch = (dev->open_count == 0);
-	spin_unlock(&dev->count_lock);
-	return can_switch;
+	/*
+	 * FIXME: open_count is protected by drm_global_mutex but that would lead to
+	 * locking inversion with the driver load path. And the access here is
+	 * completely racy anyway. So don't bother with locking for now.
+	 */
+	return dev->open_count == 0;
 }
 
 static const struct vga_switcheroo_client_ops
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 58af547b0b9..4c534b7b04d 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -1,4 +1,4 @@
-	/*
+/*
  * Copyright 2011 Red Hat Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
@@ -26,6 +26,7 @@
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_dp_helper.h>
 
 #include "nouveau_drm.h"
 #include "nouveau_dma.h"
@@ -957,7 +958,7 @@ nv50_crtc_prepare(struct drm_crtc *crtc)
 
 	nv50_display_flip_stop(crtc);
 
-	push = evo_wait(mast, 2);
+	push = evo_wait(mast, 6);
 	if (push) {
 		if (nv50_vers(mast) < NV84_DISP_MAST_CLASS) {
 			evo_mthd(push, 0x0874 + (nv_crtc->index * 0x400), 1);
@@ -1207,6 +1208,7 @@ static void
 nv50_crtc_disable(struct drm_crtc *crtc)
 {
 	struct nv50_head *head = nv50_head(crtc);
+	evo_sync(crtc->dev);
 	if (head->image)
 		nouveau_bo_unpin(head->image);
 	nouveau_bo_ref(NULL, &head->image);
@@ -1700,10 +1702,9 @@ nv50_hdmi_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode)
 }
 
 static void
-nv50_hdmi_disconnect(struct drm_encoder *encoder)
+nv50_hdmi_disconnect(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nouveau_crtc *nv_crtc = nouveau_crtc(nv_encoder->crtc);
 	struct nv50_disp *disp = nv50_disp(encoder->dev);
 	const u32 moff = (nv_crtc->index << 3) | nv_encoder->or;
 
@@ -1722,7 +1723,7 @@ nv50_sor_dpms(struct drm_encoder *encoder, int mode)
 	struct drm_device *dev = encoder->dev;
 	struct nv50_disp *disp = nv50_disp(dev);
 	struct drm_encoder *partner;
-	int or = nv_encoder->or;
+	u32 mthd;
 
 	nv_encoder->last_dpms = mode;
 
@@ -1740,7 +1741,18 @@ nv50_sor_dpms(struct drm_encoder *encoder, int mode)
 		}
 	}
 
-	nv_call(disp->core, NV50_DISP_SOR_PWR + or, (mode == DRM_MODE_DPMS_ON));
+	mthd  = (ffs(nv_encoder->dcb->heads) - 1) << 3;
+	mthd |= (ffs(nv_encoder->dcb->sorconf.link) - 1) << 2;
+	mthd |= nv_encoder->or;
+
+	if (nv_encoder->dcb->type == DCB_OUTPUT_DP) {
+		nv_call(disp->core, NV50_DISP_SOR_PWR | mthd, 1);
+		mthd |= NV94_DISP_SOR_DP_PWR;
+	} else {
+		mthd |= NV50_DISP_SOR_PWR;
+	}
+
+	nv_call(disp->core, mthd, (mode == DRM_MODE_DPMS_ON));
 }
 
 static bool
@@ -1764,33 +1776,36 @@ nv50_sor_mode_fixup(struct drm_encoder *encoder,
 }
 
 static void
-nv50_sor_disconnect(struct drm_encoder *encoder)
+nv50_sor_ctrl(struct nouveau_encoder *nv_encoder, u32 mask, u32 data)
 {
-	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
-	struct nv50_mast *mast = nv50_mast(encoder->dev);
-	const int or = nv_encoder->or;
-	u32 *push;
-
-	if (nv_encoder->crtc) {
-		nv50_crtc_prepare(nv_encoder->crtc);
-
-		push = evo_wait(mast, 4);
-		if (push) {
-			if (nv50_vers(mast) < NVD0_DISP_MAST_CLASS) {
-				evo_mthd(push, 0x0600 + (or * 0x40), 1);
-				evo_data(push, 0x00000000);
-			} else {
-				evo_mthd(push, 0x0200 + (or * 0x20), 1);
-				evo_data(push, 0x00000000);
-			}
-			evo_kick(push, mast);
+	struct nv50_mast *mast = nv50_mast(nv_encoder->base.base.dev);
+	u32 temp = (nv_encoder->ctrl & ~mask) | (data & mask), *push;
+	if (temp != nv_encoder->ctrl && (push = evo_wait(mast, 2))) {
+		if (nv50_vers(mast) < NVD0_DISP_MAST_CLASS) {
+			evo_mthd(push, 0x0600 + (nv_encoder->or * 0x40), 1);
+			evo_data(push, (nv_encoder->ctrl = temp));
+		} else {
+			evo_mthd(push, 0x0200 + (nv_encoder->or * 0x20), 1);
+			evo_data(push, (nv_encoder->ctrl = temp));
 		}
-
-		nv50_hdmi_disconnect(encoder);
+		evo_kick(push, mast);
 	}
+}
+
+static void
+nv50_sor_disconnect(struct drm_encoder *encoder)
+{
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct nouveau_crtc *nv_crtc = nouveau_crtc(nv_encoder->crtc);
 
 	nv_encoder->last_dpms = DRM_MODE_DPMS_OFF;
 	nv_encoder->crtc = NULL;
+
+	if (nv_crtc) {
+		nv50_crtc_prepare(&nv_crtc->base);
+		nv50_sor_ctrl(nv_encoder, 1 << nv_crtc->index, 0);
+		nv50_hdmi_disconnect(&nv_encoder->base.base, nv_crtc);
+	}
 }
 
 static void
@@ -1810,12 +1825,14 @@ nv50_sor_mode_set(struct drm_encoder *encoder, struct drm_display_mode *umode,
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
 	struct nouveau_connector *nv_connector;
 	struct nvbios *bios = &drm->vbios;
-	u32 *push, lvds = 0;
+	u32 lvds = 0, mask, ctrl;
 	u8 owner = 1 << nv_crtc->index;
 	u8 proto = 0xf;
 	u8 depth = 0x0;
 
 	nv_connector = nouveau_encoder_connector_get(nv_encoder);
+	nv_encoder->crtc = encoder->crtc;
+
 	switch (nv_encoder->dcb->type) {
 	case DCB_OUTPUT_TMDS:
 		if (nv_encoder->dcb->sorconf.link & 1) {
@@ -1827,7 +1844,7 @@ nv50_sor_mode_set(struct drm_encoder *encoder, struct drm_display_mode *umode,
 			proto = 0x2;
 		}
 
-		nv50_hdmi_mode_set(encoder, mode);
+		nv50_hdmi_mode_set(&nv_encoder->base.base, mode);
 		break;
 	case DCB_OUTPUT_LVDS:
 		proto = 0x0;
@@ -1883,19 +1900,11 @@ nv50_sor_mode_set(struct drm_encoder *encoder, struct drm_display_mode *umode,
 		break;
 	}
 
-	nv50_sor_dpms(encoder, DRM_MODE_DPMS_ON);
+	nv50_sor_dpms(&nv_encoder->base.base, DRM_MODE_DPMS_ON);
 
-	push = evo_wait(nv50_mast(dev), 8);
-	if (push) {
-		if (nv50_vers(mast) < NVD0_DISP_CLASS) {
-			u32 ctrl = (depth << 16) | (proto << 8) | owner;
-			if (mode->flags & DRM_MODE_FLAG_NHSYNC)
-				ctrl |= 0x00001000;
-			if (mode->flags & DRM_MODE_FLAG_NVSYNC)
-				ctrl |= 0x00002000;
-			evo_mthd(push, 0x0600 + (nv_encoder->or * 0x040), 1);
-			evo_data(push, ctrl);
-		} else {
+	if (nv50_vers(mast) >= NVD0_DISP_CLASS) {
+		u32 *push = evo_wait(mast, 3);
+		if (push) {
 			u32 magic = 0x31ec6000 | (nv_crtc->index << 25);
 			u32 syncs = 0x00000001;
 
@@ -1910,14 +1919,21 @@ nv50_sor_mode_set(struct drm_encoder *encoder, struct drm_display_mode *umode,
 			evo_mthd(push, 0x0404 + (nv_crtc->index * 0x300), 2);
 			evo_data(push, syncs | (depth << 6));
 			evo_data(push, magic);
-			evo_mthd(push, 0x0200 + (nv_encoder->or * 0x020), 1);
-			evo_data(push, owner | (proto << 8));
+			evo_kick(push, mast);
 		}
 
-		evo_kick(push, mast);
+		ctrl = proto << 8;
+		mask = 0x00000f00;
+	} else {
+		ctrl = (depth << 16) | (proto << 8);
+		if (mode->flags & DRM_MODE_FLAG_NHSYNC)
+			ctrl |= 0x00001000;
+		if (mode->flags & DRM_MODE_FLAG_NVSYNC)
+			ctrl |= 0x00002000;
+		mask = 0x000f3f00;
 	}
 
-	nv_encoder->crtc = encoder->crtc;
+	nv50_sor_ctrl(nv_encoder, mask | owner, ctrl | owner);
 }
 
 static void
@@ -2295,7 +2311,7 @@ nv50_display_create(struct drm_device *dev)
 			continue;
 
 		NV_WARN(drm, "%s has no encoders, removing\n",
-			drm_get_connector_name(connector));
+			connector->name);
 		connector->funcs->destroy(connector);
 	}
 
diff --git a/drivers/gpu/drm/omapdrm/omap_crtc.c b/drivers/gpu/drm/omapdrm/omap_crtc.c
index e3c47a8005f..2d28dc337cf 100644
--- a/drivers/gpu/drm/omapdrm/omap_crtc.c
+++ b/drivers/gpu/drm/omapdrm/omap_crtc.c
@@ -319,13 +319,13 @@ static void page_flip_worker(struct work_struct *work)
 	struct drm_display_mode *mode = &crtc->mode;
 	struct drm_gem_object *bo;
 
-	mutex_lock(&crtc->mutex);
+	drm_modeset_lock(&crtc->mutex, NULL);
 	omap_plane_mode_set(omap_crtc->plane, crtc, crtc->primary->fb,
 			0, 0, mode->hdisplay, mode->vdisplay,
 			crtc->x << 16, crtc->y << 16,
 			mode->hdisplay << 16, mode->vdisplay << 16,
 			vblank_cb, crtc);
-	mutex_unlock(&crtc->mutex);
+	drm_modeset_unlock(&crtc->mutex);
 
 	bo = omap_framebuffer_bo(crtc->primary->fb, 0);
 	drm_gem_object_unreference_unlocked(bo);
@@ -465,7 +465,7 @@ static void apply_worker(struct work_struct *work)
 	 * the callbacks and list modification all serialized
 	 * with respect to modesetting ioctls from userspace.
 	 */
-	mutex_lock(&crtc->mutex);
+	drm_modeset_lock(&crtc->mutex, NULL);
 	dispc_runtime_get();
 
 	/*
@@ -510,7 +510,7 @@ static void apply_worker(struct work_struct *work)
 
 out:
 	dispc_runtime_put();
-	mutex_unlock(&crtc->mutex);
+	drm_modeset_unlock(&crtc->mutex);
 }
 
 int omap_crtc_apply(struct drm_crtc *crtc,
@@ -518,7 +518,7 @@ int omap_crtc_apply(struct drm_crtc *crtc,
 {
 	struct omap_crtc *omap_crtc = to_omap_crtc(crtc);
 
-	WARN_ON(!mutex_is_locked(&crtc->mutex));
+	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 
 	/* no need to queue it again if it is already queued: */
 	if (apply->queued)
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index c8270e4b26f..002b9721e85 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -588,9 +588,7 @@ static void dev_lastclose(struct drm_device *dev)
 		}
 	}
 
-	drm_modeset_lock_all(dev);
-	ret = drm_fb_helper_restore_fbdev_mode(priv->fbdev);
-	drm_modeset_unlock_all(dev);
+	ret = drm_fb_helper_restore_fbdev_mode_unlocked(priv->fbdev);
 	if (ret)
 		DBG("failed to restore crtc mode");
 }
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 8b019602ffe..2a5cacdc344 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -346,6 +346,7 @@ void omap_framebuffer_flush(struct drm_framebuffer *fb,
 
 	VERB("flush: %d,%d %dx%d, fb=%p", x, y, w, h, fb);
 
+	/* FIXME: This is racy - no protection against modeset config changes. */
 	while ((connector = omap_framebuffer_get_next_connector(fb, connector))) {
 		/* only consider connectors that are part of a chain */
 		if (connector->encoder && connector->encoder->crtc) {
diff --git a/drivers/gpu/drm/panel/panel-ld9040.c b/drivers/gpu/drm/panel/panel-ld9040.c
index 1f1f8371a19..db1601fdbe2 100644
--- a/drivers/gpu/drm/panel/panel-ld9040.c
+++ b/drivers/gpu/drm/panel/panel-ld9040.c
@@ -27,6 +27,7 @@
 #define MCS_ELVSS_ON		0xb1
 #define MCS_USER_SETTING	0xf0
 #define MCS_DISPCTL		0xf2
+#define MCS_POWER_CTRL		0xf4
 #define MCS_GTCON		0xf7
 #define MCS_PANEL_CONDITION	0xf8
 #define MCS_GAMMA_SET1		0xf9
@@ -182,6 +183,8 @@ static void ld9040_init(struct ld9040 *ctx)
 	ld9040_dcs_write_seq_static(ctx, MCS_DISPCTL,
 		0x02, 0x08, 0x08, 0x10, 0x10);
 	ld9040_dcs_write_seq_static(ctx, MCS_MANPWR, 0x04);
+	ld9040_dcs_write_seq_static(ctx, MCS_POWER_CTRL,
+		0x0a, 0x87, 0x25, 0x6a, 0x44, 0x02, 0x88);
 	ld9040_dcs_write_seq_static(ctx, MCS_ELVSS_ON, 0x0d, 0x00, 0x16);
 	ld9040_dcs_write_seq_static(ctx, MCS_GTCON, 0x09, 0x00, 0x00);
 	ld9040_brightness_set(ctx);
diff --git a/drivers/gpu/drm/panel/panel-s6e8aa0.c b/drivers/gpu/drm/panel/panel-s6e8aa0.c
index 35941d2412b..06e57a26db7 100644
--- a/drivers/gpu/drm/panel/panel-s6e8aa0.c
+++ b/drivers/gpu/drm/panel/panel-s6e8aa0.c
@@ -847,6 +847,7 @@ static void s6e8aa0_read_mtp_id(struct s6e8aa0 *ctx)
 	if (i >= ARRAY_SIZE(s6e8aa0_variants)) {
 		dev_err(ctx->dev, "unsupported display version %d\n", id[1]);
 		ctx->error = -EINVAL;
+		return;
 	}
 
 	ctx->variant = &s6e8aa0_variants[i];
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 309f29e9234..a25136132c3 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -262,6 +262,13 @@ static int panel_simple_remove(struct device *dev)
 	return 0;
 }
 
+static void panel_simple_shutdown(struct device *dev)
+{
+	struct panel_simple *panel = dev_get_drvdata(dev);
+
+	panel_simple_disable(&panel->base);
+}
+
 static const struct drm_display_mode auo_b101aw03_mode = {
 	.clock = 51450,
 	.hdisplay = 1024,
@@ -284,6 +291,28 @@ static const struct panel_desc auo_b101aw03 = {
 	},
 };
 
+static const struct drm_display_mode auo_b133xtn01_mode = {
+	.clock = 69500,
+	.hdisplay = 1366,
+	.hsync_start = 1366 + 48,
+	.hsync_end = 1366 + 48 + 32,
+	.htotal = 1366 + 48 + 32 + 20,
+	.vdisplay = 768,
+	.vsync_start = 768 + 3,
+	.vsync_end = 768 + 3 + 6,
+	.vtotal = 768 + 3 + 6 + 13,
+	.vrefresh = 60,
+};
+
+static const struct panel_desc auo_b133xtn01 = {
+	.modes = &auo_b133xtn01_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 293,
+		.height = 165,
+	},
+};
+
 static const struct drm_display_mode chunghwa_claa101wa01a_mode = {
 	.clock = 72070,
 	.hdisplay = 1366,
@@ -328,6 +357,52 @@ static const struct panel_desc chunghwa_claa101wb01 = {
 	},
 };
 
+static const struct drm_display_mode edt_et057090dhu_mode = {
+	.clock = 25175,
+	.hdisplay = 640,
+	.hsync_start = 640 + 16,
+	.hsync_end = 640 + 16 + 30,
+	.htotal = 640 + 16 + 30 + 114,
+	.vdisplay = 480,
+	.vsync_start = 480 + 10,
+	.vsync_end = 480 + 10 + 3,
+	.vtotal = 480 + 10 + 3 + 32,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc edt_et057090dhu = {
+	.modes = &edt_et057090dhu_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 115,
+		.height = 86,
+	},
+};
+
+static const struct drm_display_mode edt_etm0700g0dh6_mode = {
+	.clock = 33260,
+	.hdisplay = 800,
+	.hsync_start = 800 + 40,
+	.hsync_end = 800 + 40 + 128,
+	.htotal = 800 + 40 + 128 + 88,
+	.vdisplay = 480,
+	.vsync_start = 480 + 10,
+	.vsync_end = 480 + 10 + 2,
+	.vtotal = 480 + 10 + 2 + 33,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC,
+};
+
+static const struct panel_desc edt_etm0700g0dh6 = {
+	.modes = &edt_etm0700g0dh6_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+};
+
 static const struct drm_display_mode lg_lp129qe_mode = {
 	.clock = 285250,
 	.hdisplay = 2560,
@@ -377,12 +452,24 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "auo,b101aw03",
 		.data = &auo_b101aw03,
 	}, {
+		.compatible = "auo,b133xtn01",
+		.data = &auo_b133xtn01,
+	}, {
 		.compatible = "chunghwa,claa101wa01a",
 		.data = &chunghwa_claa101wa01a
 	}, {
 		.compatible = "chunghwa,claa101wb01",
 		.data = &chunghwa_claa101wb01
 	}, {
+		.compatible = "edt,et057090dhu",
+		.data = &edt_et057090dhu,
+	}, {
+		.compatible = "edt,et070080dh6",
+		.data = &edt_etm0700g0dh6,
+	}, {
+		.compatible = "edt,etm0700g0dh6",
+		.data = &edt_etm0700g0dh6,
+	}, {
 		.compatible = "lg,lp129qe",
 		.data = &lg_lp129qe,
 	}, {
@@ -412,6 +499,11 @@ static int panel_simple_platform_remove(struct platform_device *pdev)
 	return panel_simple_remove(&pdev->dev);
 }
 
+static void panel_simple_platform_shutdown(struct platform_device *pdev)
+{
+	panel_simple_shutdown(&pdev->dev);
+}
+
 static struct platform_driver panel_simple_platform_driver = {
 	.driver = {
 		.name = "panel-simple",
@@ -420,6 +512,7 @@ static struct platform_driver panel_simple_platform_driver = {
 	},
 	.probe = panel_simple_platform_probe,
 	.remove = panel_simple_platform_remove,
+	.shutdown = panel_simple_platform_shutdown,
 };
 
 struct panel_desc_dsi {
@@ -561,6 +654,11 @@ static int panel_simple_dsi_remove(struct mipi_dsi_device *dsi)
 	return panel_simple_remove(&dsi->dev);
 }
 
+static void panel_simple_dsi_shutdown(struct mipi_dsi_device *dsi)
+{
+	panel_simple_shutdown(&dsi->dev);
+}
+
 static struct mipi_dsi_driver panel_simple_dsi_driver = {
 	.driver = {
 		.name = "panel-simple-dsi",
@@ -569,6 +667,7 @@ static struct mipi_dsi_driver panel_simple_dsi_driver = {
 	},
 	.probe = panel_simple_dsi_probe,
 	.remove = panel_simple_dsi_remove,
+	.shutdown = panel_simple_dsi_shutdown,
 };
 
 static int __init panel_simple_init(void)
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 41bdd174657..5d7ea246185 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -574,6 +574,10 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc,
 			   bo->surf.height, bo->surf.stride, bo->surf.format);
 		qxl_io_create_primary(qdev, base_offset, bo);
 		bo->is_primary = true;
+	}
+
+	if (bo->is_primary) {
+		DRM_DEBUG_KMS("setting surface_id to 0 for primary surface %d on crtc %d\n", bo->surface_id, qcrtc->index);
 		surf_id = 0;
 	} else {
 		surf_id = bo->surface_id;
@@ -841,7 +845,7 @@ static const struct drm_connector_funcs qxl_connector_funcs = {
 	.save = qxl_conn_save,
 	.restore = qxl_conn_restore,
 	.detect = qxl_conn_detect,
-	.fill_modes = drm_helper_probe_single_connector_modes,
+	.fill_modes = drm_helper_probe_single_connector_modes_nomerge,
 	.set_property = qxl_conn_set_property,
 	.destroy = qxl_conn_destroy,
 };
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index fee8748bdca..6e936634d65 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -214,7 +214,6 @@ static struct pci_driver qxl_pci_driver = {
 static struct drm_driver qxl_driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET |
 			   DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED,
-	.dev_priv_size = 0,
 	.load = qxl_driver_load,
 	.unload = qxl_driver_unload,
 
diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c
index 0bb86e6d41b..b110883f825 100644
--- a/drivers/gpu/drm/qxl/qxl_ioctl.c
+++ b/drivers/gpu/drm/qxl/qxl_ioctl.c
@@ -451,4 +451,4 @@ const struct drm_ioctl_desc qxl_ioctls[] = {
 			  DRM_AUTH|DRM_UNLOCKED),
 };
 
-int qxl_max_ioctls = DRM_ARRAY_SIZE(qxl_ioctls);
+int qxl_max_ioctls = ARRAY_SIZE(qxl_ioctls);
diff --git a/drivers/gpu/drm/qxl/qxl_irq.c b/drivers/gpu/drm/qxl/qxl_irq.c
index 28f84b4fce3..0bf1e20c6e4 100644
--- a/drivers/gpu/drm/qxl/qxl_irq.c
+++ b/drivers/gpu/drm/qxl/qxl_irq.c
@@ -33,6 +33,9 @@ irqreturn_t qxl_irq_handler(int irq, void *arg)
 
 	pending = xchg(&qdev->ram_header->int_pending, 0);
 
+	if (!pending)
+		return IRQ_NONE;
+
 	atomic_inc(&qdev->irq_received);
 
 	if (pending & QXL_INTERRUPT_DISPLAY) {
@@ -87,7 +90,7 @@ int qxl_irq_init(struct qxl_device *qdev)
 	atomic_set(&qdev->irq_received_cursor, 0);
 	atomic_set(&qdev->irq_received_io_cmd, 0);
 	qdev->irq_received_error = 0;
-	ret = drm_irq_install(qdev->ddev);
+	ret = drm_irq_install(qdev->ddev, qdev->ddev->pdev->irq);
 	qdev->ram_header->int_mask = QXL_INTERRUPT_MASK;
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Failed installing irq: %d\n", ret);
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index d52c27527b9..71a1baeac14 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -109,13 +109,11 @@ static const struct vm_operations_struct *ttm_vm_ops;
 static int qxl_ttm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct ttm_buffer_object *bo;
-	struct qxl_device *qdev;
 	int r;
 
 	bo = (struct ttm_buffer_object *)vma->vm_private_data;
 	if (bo == NULL)
 		return VM_FAULT_NOPAGE;
-	qdev = qxl_get_qdev(bo->bdev);
 	r = ttm_vm_ops->fault(vma, vmf);
 	return r;
 }
@@ -162,10 +160,6 @@ static int qxl_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags)
 static int qxl_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
 			     struct ttm_mem_type_manager *man)
 {
-	struct qxl_device *qdev;
-
-	qdev = qxl_get_qdev(bdev);
-
 	switch (type) {
 	case TTM_PL_SYSTEM:
 		/* System memory */
diff --git a/drivers/gpu/drm/r128/r128_ioc32.c b/drivers/gpu/drm/r128/r128_ioc32.c
index b0d0fd3e437..663f38c63ba 100644
--- a/drivers/gpu/drm/r128/r128_ioc32.c
+++ b/drivers/gpu/drm/r128/r128_ioc32.c
@@ -203,7 +203,7 @@ long r128_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	if (nr < DRM_COMMAND_BASE)
 		return drm_compat_ioctl(filp, cmd, arg);
 
-	if (nr < DRM_COMMAND_BASE + DRM_ARRAY_SIZE(r128_compat_ioctls))
+	if (nr < DRM_COMMAND_BASE + ARRAY_SIZE(r128_compat_ioctls))
 		fn = r128_compat_ioctls[nr - DRM_COMMAND_BASE];
 
 	if (fn != NULL)
diff --git a/drivers/gpu/drm/r128/r128_state.c b/drivers/gpu/drm/r128/r128_state.c
index e806dacd452..575e986f82a 100644
--- a/drivers/gpu/drm/r128/r128_state.c
+++ b/drivers/gpu/drm/r128/r128_state.c
@@ -1594,7 +1594,7 @@ static int r128_getparam(struct drm_device *dev, void *data, struct drm_file *fi
 
 	switch (param->param) {
 	case R128_PARAM_IRQ_NR:
-		value = drm_dev_to_irq(dev);
+		value = dev->pdev->irq;
 		break;
 	default:
 		return -EINVAL;
@@ -1641,4 +1641,4 @@ const struct drm_ioctl_desc r128_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(R128_GETPARAM, r128_getparam, DRM_AUTH),
 };
 
-int r128_max_ioctl = DRM_ARRAY_SIZE(r128_ioctls);
+int r128_max_ioctl = ARRAY_SIZE(r128_ioctls);
diff --git a/drivers/gpu/drm/radeon/Makefile b/drivers/gpu/drm/radeon/Makefile
index 09433534dc4..dbcbfe80aac 100644
--- a/drivers/gpu/drm/radeon/Makefile
+++ b/drivers/gpu/drm/radeon/Makefile
@@ -72,7 +72,7 @@ radeon-y += radeon_device.o radeon_asic.o radeon_kms.o \
 	radeon_cs.o radeon_bios.o radeon_benchmark.o r100.o r300.o r420.o \
 	rs400.o rs600.o rs690.o rv515.o r520.o r600.o rv770.o radeon_test.o \
 	r200.o radeon_legacy_tv.o r600_cs.o r600_blit_shaders.o \
-	radeon_pm.o atombios_dp.o r600_audio.o r600_hdmi.o \
+	radeon_pm.o atombios_dp.o r600_audio.o r600_hdmi.o dce3_1_afmt.o \
 	evergreen.o evergreen_cs.o evergreen_blit_shaders.o \
 	evergreen_hdmi.o radeon_trace_points.o ni.o cayman_blit_shaders.o \
 	atombios_encoders.o radeon_semaphore.o radeon_sa.o atombios_i2c.o si.o \
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index e911898348f..30d242b2507 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -557,6 +557,7 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 	u32 adjusted_clock = mode->clock;
 	int encoder_mode = atombios_get_encoder_mode(encoder);
 	u32 dp_clock = mode->clock;
+	u32 clock = mode->clock;
 	int bpc = radeon_crtc->bpc;
 	bool is_duallink = radeon_dig_monitor_is_duallink(encoder, mode->clock);
 
@@ -632,6 +633,24 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 			radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
 	}
 
+	/* adjust pll for deep color modes */
+	if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+		switch (bpc) {
+		case 8:
+		default:
+			break;
+		case 10:
+			clock = (clock * 5) / 4;
+			break;
+		case 12:
+			clock = (clock * 3) / 2;
+			break;
+		case 16:
+			clock = clock * 2;
+			break;
+		}
+	}
+
 	/* DCE3+ has an AdjustDisplayPll that will adjust the pixel clock
 	 * accordingly based on the encoder/transmitter to work around
 	 * special hw requirements.
@@ -653,7 +672,7 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 			switch (crev) {
 			case 1:
 			case 2:
-				args.v1.usPixelClock = cpu_to_le16(mode->clock / 10);
+				args.v1.usPixelClock = cpu_to_le16(clock / 10);
 				args.v1.ucTransmitterID = radeon_encoder->encoder_id;
 				args.v1.ucEncodeMode = encoder_mode;
 				if (radeon_crtc->ss_enabled && radeon_crtc->ss.percentage)
@@ -665,7 +684,7 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 				adjusted_clock = le16_to_cpu(args.v1.usPixelClock) * 10;
 				break;
 			case 3:
-				args.v3.sInput.usPixelClock = cpu_to_le16(mode->clock / 10);
+				args.v3.sInput.usPixelClock = cpu_to_le16(clock / 10);
 				args.v3.sInput.ucTransmitterID = radeon_encoder->encoder_id;
 				args.v3.sInput.ucEncodeMode = encoder_mode;
 				args.v3.sInput.ucDispPllConfig = 0;
@@ -679,10 +698,6 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc,
 					args.v3.sInput.usPixelClock = cpu_to_le16(dp_clock / 10);
 				} else if (radeon_encoder->devices & (ATOM_DEVICE_DFP_SUPPORT)) {
 					struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-					if (encoder_mode == ATOM_ENCODER_MODE_HDMI)
-						/* deep color support */
-						args.v3.sInput.usPixelClock =
-							cpu_to_le16((mode->clock * bpc / 8) / 10);
 					if (dig->coherent_mode)
 						args.v3.sInput.ucDispPllConfig |=
 							DISPPLL_CONFIG_COHERENT_MODE;
@@ -862,14 +877,21 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 			args.v5.ucMiscInfo = 0; /* HDMI depth, etc. */
 			if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
 				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_REF_DIV_SRC;
-			switch (bpc) {
-			case 8:
-			default:
-				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
-				break;
-			case 10:
-				args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
-				break;
+			if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+				switch (bpc) {
+				case 8:
+				default:
+					args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_24BPP;
+					break;
+				case 10:
+					/* yes this is correct, the atom define is wrong */
+					args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_32BPP;
+					break;
+				case 12:
+					/* yes this is correct, the atom define is wrong */
+					args.v5.ucMiscInfo |= PIXEL_CLOCK_V5_MISC_HDMI_30BPP;
+					break;
+				}
 			}
 			args.v5.ucTransmitterID = encoder_id;
 			args.v5.ucEncoderMode = encoder_mode;
@@ -884,20 +906,22 @@ static void atombios_crtc_program_pll(struct drm_crtc *crtc,
 			args.v6.ucMiscInfo = 0; /* HDMI depth, etc. */
 			if (ss_enabled && (ss->type & ATOM_EXTERNAL_SS_MASK))
 				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_REF_DIV_SRC;
-			switch (bpc) {
-			case 8:
-			default:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
-				break;
-			case 10:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP;
-				break;
-			case 12:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP;
-				break;
-			case 16:
-				args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
-				break;
+			if (encoder_mode == ATOM_ENCODER_MODE_HDMI) {
+				switch (bpc) {
+				case 8:
+				default:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_24BPP;
+					break;
+				case 10:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_30BPP_V6;
+					break;
+				case 12:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_36BPP_V6;
+					break;
+				case 16:
+					args.v6.ucMiscInfo |= PIXEL_CLOCK_V6_MISC_HDMI_48BPP;
+					break;
+				}
 			}
 			args.v6.ucTransmitterID = encoder_id;
 			args.v6.ucEncoderMode = encoder_mode;
@@ -938,6 +962,9 @@ static bool atombios_crtc_prepare_pll(struct drm_crtc *crtc, struct drm_display_
 		struct radeon_connector_atom_dig *dig_connector =
 			radeon_connector->con_priv;
 		int dp_clock;
+
+		/* Assign mode clock for hdmi deep color max clock limit check */
+		radeon_connector->pixelclock_for_modeset = mode->clock;
 		radeon_crtc->bpc = radeon_get_monitor_bpc(connector);
 
 		switch (encoder_mode) {
@@ -1019,10 +1046,17 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 	struct radeon_encoder *radeon_encoder =
 		to_radeon_encoder(radeon_crtc->encoder);
 	u32 pll_clock = mode->clock;
+	u32 clock = mode->clock;
 	u32 ref_div = 0, fb_div = 0, frac_fb_div = 0, post_div = 0;
 	struct radeon_pll *pll;
 	int encoder_mode = atombios_get_encoder_mode(radeon_crtc->encoder);
 
+	/* pass the actual clock to atombios_crtc_program_pll for DCE5,6 for HDMI */
+	if (ASIC_IS_DCE5(rdev) &&
+	    (encoder_mode == ATOM_ENCODER_MODE_HDMI) &&
+	    (radeon_crtc->bpc > 8))
+		clock = radeon_crtc->adjusted_clock;
+
 	switch (radeon_crtc->pll_id) {
 	case ATOM_PPLL1:
 		pll = &rdev->clock.p1pll;
@@ -1057,7 +1091,7 @@ static void atombios_crtc_set_pll(struct drm_crtc *crtc, struct drm_display_mode
 				 radeon_crtc->crtc_id, &radeon_crtc->ss);
 
 	atombios_crtc_program_pll(crtc, radeon_crtc->crtc_id, radeon_crtc->pll_id,
-				  encoder_mode, radeon_encoder->encoder_id, mode->clock,
+				  encoder_mode, radeon_encoder->encoder_id, clock,
 				  ref_div, fb_div, frac_fb_div, post_div,
 				  radeon_crtc->bpc, radeon_crtc->ss_enabled, &radeon_crtc->ss);
 
@@ -1102,6 +1136,7 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	u32 fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_NONE);
 	u32 tmp, viewport_w, viewport_h;
 	int r;
+	bool bypass_lut = false;
 
 	/* no fb bound */
 	if (!atomic && !crtc->primary->fb) {
@@ -1140,33 +1175,73 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL);
 	radeon_bo_unreserve(rbo);
 
-	switch (target_fb->bits_per_pixel) {
-	case 8:
+	switch (target_fb->pixel_format) {
+	case DRM_FORMAT_C8:
 		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_8BPP) |
 			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_INDEXED));
 		break;
-	case 15:
+	case DRM_FORMAT_XRGB4444:
+	case DRM_FORMAT_ARGB4444:
+		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_16BPP) |
+			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB4444));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN16);
+#endif
+		break;
+	case DRM_FORMAT_XRGB1555:
+	case DRM_FORMAT_ARGB1555:
 		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_16BPP) |
 			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB1555));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN16);
+#endif
+		break;
+	case DRM_FORMAT_BGRX5551:
+	case DRM_FORMAT_BGRA5551:
+		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_16BPP) |
+			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_BGRA5551));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN16);
+#endif
 		break;
-	case 16:
+	case DRM_FORMAT_RGB565:
 		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_16BPP) |
 			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB565));
 #ifdef __BIG_ENDIAN
 		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN16);
 #endif
 		break;
-	case 24:
-	case 32:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
 		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_32BPP) |
 			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB8888));
 #ifdef __BIG_ENDIAN
 		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN32);
 #endif
 		break;
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_ARGB2101010:
+		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_32BPP) |
+			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_ARGB2101010));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN32);
+#endif
+		/* Greater 8 bpc fb needs to bypass hw-lut to retain precision */
+		bypass_lut = true;
+		break;
+	case DRM_FORMAT_BGRX1010102:
+	case DRM_FORMAT_BGRA1010102:
+		fb_format = (EVERGREEN_GRPH_DEPTH(EVERGREEN_GRPH_DEPTH_32BPP) |
+			     EVERGREEN_GRPH_FORMAT(EVERGREEN_GRPH_FORMAT_BGRA1010102));
+#ifdef __BIG_ENDIAN
+		fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_8IN32);
+#endif
+		/* Greater 8 bpc fb needs to bypass hw-lut to retain precision */
+		bypass_lut = true;
+		break;
 	default:
-		DRM_ERROR("Unsupported screen depth %d\n",
-			  target_fb->bits_per_pixel);
+		DRM_ERROR("Unsupported screen format %s\n",
+			  drm_get_format_name(target_fb->pixel_format));
 		return -EINVAL;
 	}
 
@@ -1295,6 +1370,18 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	WREG32(EVERGREEN_GRPH_CONTROL + radeon_crtc->crtc_offset, fb_format);
 	WREG32(EVERGREEN_GRPH_SWAP_CONTROL + radeon_crtc->crtc_offset, fb_swap);
 
+	/*
+	 * The LUT only has 256 slots for indexing by a 8 bpc fb. Bypass the LUT
+	 * for > 8 bpc scanout to avoid truncation of fb indices to 8 msb's, to
+	 * retain the full precision throughout the pipeline.
+	 */
+	WREG32_P(EVERGREEN_GRPH_LUT_10BIT_BYPASS_CONTROL + radeon_crtc->crtc_offset,
+		 (bypass_lut ? EVERGREEN_LUT_10BIT_BYPASS_EN : 0),
+		 ~EVERGREEN_LUT_10BIT_BYPASS_EN);
+
+	if (bypass_lut)
+		DRM_DEBUG_KMS("Bypassing hardware LUT due to 10 bit fb scanout.\n");
+
 	WREG32(EVERGREEN_GRPH_SURFACE_OFFSET_X + radeon_crtc->crtc_offset, 0);
 	WREG32(EVERGREEN_GRPH_SURFACE_OFFSET_Y + radeon_crtc->crtc_offset, 0);
 	WREG32(EVERGREEN_GRPH_X_START + radeon_crtc->crtc_offset, 0);
@@ -1327,8 +1414,8 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	tmp &= ~EVERGREEN_GRPH_SURFACE_UPDATE_H_RETRACE_EN;
 	WREG32(EVERGREEN_GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset, tmp);
 
-	/* set pageflip to happen anywhere in vblank interval */
-	WREG32(EVERGREEN_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 0);
+	/* set pageflip to happen only at start of vblank interval (front porch) */
+	WREG32(EVERGREEN_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 3);
 
 	if (!atomic && fb && fb != crtc->primary->fb) {
 		radeon_fb = to_radeon_framebuffer(fb);
@@ -1362,6 +1449,7 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	u32 fb_swap = R600_D1GRPH_SWAP_ENDIAN_NONE;
 	u32 tmp, viewport_w, viewport_h;
 	int r;
+	bool bypass_lut = false;
 
 	/* no fb bound */
 	if (!atomic && !crtc->primary->fb) {
@@ -1399,18 +1487,30 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL);
 	radeon_bo_unreserve(rbo);
 
-	switch (target_fb->bits_per_pixel) {
-	case 8:
+	switch (target_fb->pixel_format) {
+	case DRM_FORMAT_C8:
 		fb_format =
 		    AVIVO_D1GRPH_CONTROL_DEPTH_8BPP |
 		    AVIVO_D1GRPH_CONTROL_8BPP_INDEXED;
 		break;
-	case 15:
+	case DRM_FORMAT_XRGB4444:
+	case DRM_FORMAT_ARGB4444:
+		fb_format =
+		    AVIVO_D1GRPH_CONTROL_DEPTH_16BPP |
+		    AVIVO_D1GRPH_CONTROL_16BPP_ARGB4444;
+#ifdef __BIG_ENDIAN
+		fb_swap = R600_D1GRPH_SWAP_ENDIAN_16BIT;
+#endif
+		break;
+	case DRM_FORMAT_XRGB1555:
 		fb_format =
 		    AVIVO_D1GRPH_CONTROL_DEPTH_16BPP |
 		    AVIVO_D1GRPH_CONTROL_16BPP_ARGB1555;
+#ifdef __BIG_ENDIAN
+		fb_swap = R600_D1GRPH_SWAP_ENDIAN_16BIT;
+#endif
 		break;
-	case 16:
+	case DRM_FORMAT_RGB565:
 		fb_format =
 		    AVIVO_D1GRPH_CONTROL_DEPTH_16BPP |
 		    AVIVO_D1GRPH_CONTROL_16BPP_RGB565;
@@ -1418,8 +1518,8 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 		fb_swap = R600_D1GRPH_SWAP_ENDIAN_16BIT;
 #endif
 		break;
-	case 24:
-	case 32:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
 		fb_format =
 		    AVIVO_D1GRPH_CONTROL_DEPTH_32BPP |
 		    AVIVO_D1GRPH_CONTROL_32BPP_ARGB8888;
@@ -1427,9 +1527,20 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 		fb_swap = R600_D1GRPH_SWAP_ENDIAN_32BIT;
 #endif
 		break;
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_ARGB2101010:
+		fb_format =
+		    AVIVO_D1GRPH_CONTROL_DEPTH_32BPP |
+		    AVIVO_D1GRPH_CONTROL_32BPP_ARGB2101010;
+#ifdef __BIG_ENDIAN
+		fb_swap = R600_D1GRPH_SWAP_ENDIAN_32BIT;
+#endif
+		/* Greater 8 bpc fb needs to bypass hw-lut to retain precision */
+		bypass_lut = true;
+		break;
 	default:
-		DRM_ERROR("Unsupported screen depth %d\n",
-			  target_fb->bits_per_pixel);
+		DRM_ERROR("Unsupported screen format %s\n",
+			  drm_get_format_name(target_fb->pixel_format));
 		return -EINVAL;
 	}
 
@@ -1468,6 +1579,13 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	if (rdev->family >= CHIP_R600)
 		WREG32(R600_D1GRPH_SWAP_CONTROL + radeon_crtc->crtc_offset, fb_swap);
 
+	/* LUT only has 256 slots for 8 bpc fb. Bypass for > 8 bpc scanout for precision */
+	WREG32_P(AVIVO_D1GRPH_LUT_SEL + radeon_crtc->crtc_offset,
+		 (bypass_lut ? AVIVO_LUT_10BIT_BYPASS_EN : 0), ~AVIVO_LUT_10BIT_BYPASS_EN);
+
+	if (bypass_lut)
+		DRM_DEBUG_KMS("Bypassing hardware LUT due to 10 bit fb scanout.\n");
+
 	WREG32(AVIVO_D1GRPH_SURFACE_OFFSET_X + radeon_crtc->crtc_offset, 0);
 	WREG32(AVIVO_D1GRPH_SURFACE_OFFSET_Y + radeon_crtc->crtc_offset, 0);
 	WREG32(AVIVO_D1GRPH_X_START + radeon_crtc->crtc_offset, 0);
@@ -1496,8 +1614,8 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	tmp &= ~AVIVO_D1GRPH_SURFACE_UPDATE_H_RETRACE_EN;
 	WREG32(AVIVO_D1GRPH_FLIP_CONTROL + radeon_crtc->crtc_offset, tmp);
 
-	/* set pageflip to happen anywhere in vblank interval */
-	WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 0);
+	/* set pageflip to happen only at start of vblank interval (front porch) */
+	WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + radeon_crtc->crtc_offset, 3);
 
 	if (!atomic && fb && fb != crtc->primary->fb) {
 		radeon_fb = to_radeon_framebuffer(fb);
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 54e4f52549a..b1e11f8434e 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -95,9 +95,12 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 	int index = GetIndexIntoMasterTable(COMMAND, ProcessAuxChannelTransaction);
 	unsigned char *base;
 	int recv_bytes;
+	int r = 0;
 
 	memset(&args, 0, sizeof(args));
 
+	mutex_lock(&chan->mutex);
+
 	base = (unsigned char *)(rdev->mode_info.atom_context->scratch + 1);
 
 	radeon_atom_copy_swap(base, send, send_bytes, true);
@@ -117,19 +120,22 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 	/* timeout */
 	if (args.v1.ucReplyStatus == 1) {
 		DRM_DEBUG_KMS("dp_aux_ch timeout\n");
-		return -ETIMEDOUT;
+		r = -ETIMEDOUT;
+		goto done;
 	}
 
 	/* flags not zero */
 	if (args.v1.ucReplyStatus == 2) {
 		DRM_DEBUG_KMS("dp_aux_ch flags not zero\n");
-		return -EBUSY;
+		r = -EIO;
+		goto done;
 	}
 
 	/* error */
 	if (args.v1.ucReplyStatus == 3) {
 		DRM_DEBUG_KMS("dp_aux_ch error\n");
-		return -EIO;
+		r = -EIO;
+		goto done;
 	}
 
 	recv_bytes = args.v1.ucDataOutLen;
@@ -139,7 +145,11 @@ static int radeon_process_aux_ch(struct radeon_i2c_chan *chan,
 	if (recv && recv_size)
 		radeon_atom_copy_swap(recv, base + 16, recv_bytes, false);
 
-	return recv_bytes;
+	r = recv_bytes;
+done:
+	mutex_unlock(&chan->mutex);
+
+	return r;
 }
 
 #define BARE_ADDRESS_SIZE 3
@@ -212,11 +222,12 @@ void radeon_dp_aux_init(struct radeon_connector *radeon_connector)
 	radeon_connector->ddc_bus->rec.hpd = radeon_connector->hpd.hpd;
 	radeon_connector->ddc_bus->aux.dev = radeon_connector->base.kdev;
 	radeon_connector->ddc_bus->aux.transfer = radeon_dp_aux_transfer;
-	ret = drm_dp_aux_register_i2c_bus(&radeon_connector->ddc_bus->aux);
+
+	ret = drm_dp_aux_register(&radeon_connector->ddc_bus->aux);
 	if (!ret)
 		radeon_connector->ddc_bus->has_aux = true;
 
-	WARN(ret, "drm_dp_aux_register_i2c_bus() failed with error %d\n", ret);
+	WARN(ret, "drm_dp_aux_register() failed with error %d\n", ret);
 }
 
 /***** general DP utility functions *****/
@@ -281,6 +292,19 @@ static int dp_get_max_dp_pix_clock(int link_rate,
 
 /***** radeon specific DP functions *****/
 
+static int radeon_dp_get_max_link_rate(struct drm_connector *connector,
+				       u8 dpcd[DP_DPCD_SIZE])
+{
+	int max_link_rate;
+
+	if (radeon_connector_is_dp12_capable(connector))
+		max_link_rate = min(drm_dp_max_link_rate(dpcd), 540000);
+	else
+		max_link_rate = min(drm_dp_max_link_rate(dpcd), 270000);
+
+	return max_link_rate;
+}
+
 /* First get the min lane# when low rate is used according to pixel clock
  * (prefer low rate), second check max lane# supported by DP panel,
  * if the max lane# < low rate lane# then use max lane# instead.
@@ -290,7 +314,7 @@ static int radeon_dp_get_dp_lane_number(struct drm_connector *connector,
 					int pix_clock)
 {
 	int bpp = convert_bpc_to_bpp(radeon_get_monitor_bpc(connector));
-	int max_link_rate = drm_dp_max_link_rate(dpcd);
+	int max_link_rate = radeon_dp_get_max_link_rate(connector, dpcd);
 	int max_lane_num = drm_dp_max_lane_count(dpcd);
 	int lane_num;
 	int max_dp_pix_clock;
@@ -328,7 +352,7 @@ static int radeon_dp_get_dp_link_clock(struct drm_connector *connector,
 			return 540000;
 	}
 
-	return drm_dp_max_link_rate(dpcd);
+	return radeon_dp_get_max_link_rate(connector, dpcd);
 }
 
 static u8 radeon_dp_encoder_service(struct radeon_device *rdev,
@@ -379,16 +403,18 @@ bool radeon_dp_getdpcd(struct radeon_connector *radeon_connector)
 {
 	struct radeon_connector_atom_dig *dig_connector = radeon_connector->con_priv;
 	u8 msg[DP_DPCD_SIZE];
-	int ret, i;
+	int ret;
+
+	char dpcd_hex_dump[DP_DPCD_SIZE * 3];
 
 	ret = drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_DPCD_REV, msg,
 			       DP_DPCD_SIZE);
 	if (ret > 0) {
 		memcpy(dig_connector->dpcd, msg, DP_DPCD_SIZE);
-		DRM_DEBUG_KMS("DPCD: ");
-		for (i = 0; i < DP_DPCD_SIZE; i++)
-			DRM_DEBUG_KMS("%02x ", msg[i]);
-		DRM_DEBUG_KMS("\n");
+
+		hex_dump_to_buffer(dig_connector->dpcd, sizeof(dig_connector->dpcd),
+				   32, 1, dpcd_hex_dump, sizeof(dpcd_hex_dump), false);
+		DRM_DEBUG_KMS("DPCD: %s\n", dpcd_hex_dump);
 
 		radeon_dp_probe_oui(radeon_connector);
 
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index e6eb5097597..7d68203a373 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -183,7 +183,6 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 	struct backlight_properties props;
 	struct radeon_backlight_privdata *pdata;
 	struct radeon_encoder_atom_dig *dig;
-	u8 backlight_level;
 	char bl_name[16];
 
 	/* Mac laptops with multiple GPUs use the gmux driver for backlight
@@ -222,12 +221,17 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 
 	pdata->encoder = radeon_encoder;
 
-	backlight_level = radeon_atom_get_backlight_level_from_reg(rdev);
-
 	dig = radeon_encoder->enc_priv;
 	dig->bl_dev = bd;
 
 	bd->props.brightness = radeon_atom_backlight_get_brightness(bd);
+	/* Set a reasonable default here if the level is 0 otherwise
+	 * fbdev will attempt to turn the backlight on after console
+	 * unblanking and it will try and restore 0 which turns the backlight
+	 * off again.
+	 */
+	if (bd->props.brightness == 0)
+		bd->props.brightness = RADEON_MAX_BL_LEVEL;
 	bd->props.power = FB_BLANK_UNBLANK;
 	backlight_update_status(bd);
 
@@ -1884,8 +1888,11 @@ atombios_set_encoder_crtc_source(struct drm_encoder *encoder)
 					args.v2.ucEncodeMode = ATOM_ENCODER_MODE_CRT;
 				else
 					args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
-			} else
+			} else if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
+				args.v2.ucEncodeMode = ATOM_ENCODER_MODE_LVDS;
+			} else {
 				args.v2.ucEncodeMode = atombios_get_encoder_mode(encoder);
+			}
 			switch (radeon_encoder->encoder_id) {
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY:
 			case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1:
diff --git a/drivers/gpu/drm/radeon/atombios_i2c.c b/drivers/gpu/drm/radeon/atombios_i2c.c
index b5162c3b611..9c570fb15b8 100644
--- a/drivers/gpu/drm/radeon/atombios_i2c.c
+++ b/drivers/gpu/drm/radeon/atombios_i2c.c
@@ -43,15 +43,19 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 	int index = GetIndexIntoMasterTable(COMMAND, ProcessI2cChannelTransaction);
 	unsigned char *base;
 	u16 out = cpu_to_le16(0);
+	int r = 0;
 
 	memset(&args, 0, sizeof(args));
 
+	mutex_lock(&chan->mutex);
+
 	base = (unsigned char *)rdev->mode_info.atom_context->scratch;
 
 	if (flags & HW_I2C_WRITE) {
 		if (num > ATOM_MAX_HW_I2C_WRITE) {
 			DRM_ERROR("hw i2c: tried to write too many bytes (%d vs 3)\n", num);
-			return -EINVAL;
+			r = -EINVAL;
+			goto done;
 		}
 		if (buf == NULL)
 			args.ucRegIndex = 0;
@@ -65,7 +69,8 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 	} else {
 		if (num > ATOM_MAX_HW_I2C_READ) {
 			DRM_ERROR("hw i2c: tried to read too many bytes (%d vs 255)\n", num);
-			return -EINVAL;
+			r = -EINVAL;
+			goto done;
 		}
 		args.ucRegIndex = 0;
 		args.lpI2CDataOut = 0;
@@ -82,13 +87,17 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 	/* error */
 	if (args.ucStatus != HW_ASSISTED_I2C_STATUS_SUCCESS) {
 		DRM_DEBUG_KMS("hw_i2c error\n");
-		return -EIO;
+		r = -EIO;
+		goto done;
 	}
 
 	if (!(flags & HW_I2C_WRITE))
 		radeon_atom_copy_swap(buf, base, num, false);
 
-	return 0;
+done:
+	mutex_unlock(&chan->mutex);
+
+	return r;
 }
 
 int radeon_atom_hw_i2c_xfer(struct i2c_adapter *i2c_adap,
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 10dae4106c0..584090ac3eb 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -1179,7 +1179,7 @@ static int ci_stop_dpm(struct radeon_device *rdev)
 	tmp &= ~GLOBAL_PWRMGT_EN;
 	WREG32_SMC(GENERAL_PWRMGT, tmp);
 
-	tmp = RREG32(SCLK_PWRMGT_CNTL);
+	tmp = RREG32_SMC(SCLK_PWRMGT_CNTL);
 	tmp &= ~DYNAMIC_PM_EN;
 	WREG32_SMC(SCLK_PWRMGT_CNTL, tmp);
 
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index d2fd9896808..c0ea66192fe 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -80,6 +80,7 @@ extern int sumo_rlc_init(struct radeon_device *rdev);
 extern void si_vram_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
 extern void si_rlc_reset(struct radeon_device *rdev);
 extern void si_init_uvd_internal_cg(struct radeon_device *rdev);
+static u32 cik_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh);
 extern int cik_sdma_resume(struct radeon_device *rdev);
 extern void cik_sdma_enable(struct radeon_device *rdev, bool enable);
 extern void cik_sdma_fini(struct radeon_device *rdev);
@@ -2290,6 +2291,7 @@ static void cik_tiling_mode_table_init(struct radeon_device *rdev)
 				gb_tile_moden = 0;
 				break;
 			}
+			rdev->config.cik.macrotile_mode_array[reg_offset] = gb_tile_moden;
 			WREG32(GB_MACROTILE_MODE0 + (reg_offset * 4), gb_tile_moden);
 		}
 	} else if (num_pipe_configs == 8) {
@@ -3257,7 +3259,7 @@ static void cik_gpu_init(struct radeon_device *rdev)
 	u32 mc_shared_chmap, mc_arb_ramcfg;
 	u32 hdp_host_path_cntl;
 	u32 tmp;
-	int i, j;
+	int i, j, k;
 
 	switch (rdev->family) {
 	case CHIP_BONAIRE:
@@ -3446,6 +3448,15 @@ static void cik_gpu_init(struct radeon_device *rdev)
 		     rdev->config.cik.max_sh_per_se,
 		     rdev->config.cik.max_backends_per_se);
 
+	for (i = 0; i < rdev->config.cik.max_shader_engines; i++) {
+		for (j = 0; j < rdev->config.cik.max_sh_per_se; j++) {
+			for (k = 0; k < rdev->config.cik.max_cu_per_sh; k++) {
+				rdev->config.cik.active_cus +=
+					hweight32(cik_get_cu_active_bitmap(rdev, i, j));
+			}
+		}
+	}
+
 	/* set HW defaults for 3D engine */
 	WREG32(CP_MEQ_THRESHOLDS, MEQ1_START(0x30) | MEQ2_START(0x60));
 
@@ -3698,7 +3709,7 @@ bool cik_semaphore_ring_emit(struct radeon_device *rdev,
 	unsigned sel = emit_wait ? PACKET3_SEM_SEL_WAIT : PACKET3_SEM_SEL_SIGNAL;
 
 	radeon_ring_write(ring, PACKET3(PACKET3_MEM_SEMAPHORE, 1));
-	radeon_ring_write(ring, addr & 0xffffffff);
+	radeon_ring_write(ring, lower_32_bits(addr));
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xffff) | sel);
 
 	return true;
@@ -3818,7 +3829,7 @@ void cik_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 			radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 			radeon_ring_write(ring, WRITE_DATA_DST_SEL(1));
 			radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-			radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+			radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr));
 			radeon_ring_write(ring, next_rptr);
 		}
 
@@ -5396,6 +5407,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev)
 	WREG32(MC_VM_MX_L1_TLB_CNTL,
 	       (0xA << 7) |
 	       ENABLE_L1_TLB |
+	       ENABLE_L1_FRAGMENT_PROCESSING |
 	       SYSTEM_ACCESS_MODE_NOT_IN_SYS |
 	       ENABLE_ADVANCED_DRIVER_MODEL |
 	       SYSTEM_APERTURE_UNMAPPED_ACCESS_PASS_THRU);
@@ -5408,7 +5420,8 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev)
 	       CONTEXT1_IDENTITY_ACCESS_MODE(1));
 	WREG32(VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS | INVALIDATE_L2_CACHE);
 	WREG32(VM_L2_CNTL3, L2_CACHE_BIGK_ASSOCIATIVITY |
-	       L2_CACHE_BIGK_FRAGMENT_SIZE(6));
+	       BANK_SELECT(4) |
+	       L2_CACHE_BIGK_FRAGMENT_SIZE(4));
 	/* setup context0 */
 	WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
 	WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
@@ -5444,6 +5457,7 @@ static int cik_pcie_gart_enable(struct radeon_device *rdev)
 	       (u32)(rdev->dummy_page.addr >> 12));
 	WREG32(VM_CONTEXT1_CNTL2, 4);
 	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(1) |
+				PAGE_TABLE_BLOCK_SIZE(radeon_vm_block_size - 9) |
 				RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
 				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT |
 				DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
@@ -7363,6 +7377,7 @@ static inline u32 cik_get_ih_wptr(struct radeon_device *rdev)
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_WPTR_OVERFLOW_CLEAR;
 		WREG32(IH_RB_CNTL, tmp);
+		wptr &= ~RB_OVERFLOW;
 	}
 	return (wptr & rdev->ih.ptr_mask);
 }
@@ -7450,7 +7465,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_flip(rdev, 0);
+						radeon_crtc_handle_vblank(rdev, 0);
 					rdev->irq.stat_regs.cik.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D1 vblank\n");
 				}
@@ -7476,7 +7491,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_flip(rdev, 1);
+						radeon_crtc_handle_vblank(rdev, 1);
 					rdev->irq.stat_regs.cik.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D2 vblank\n");
 				}
@@ -7502,7 +7517,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[2]))
-						radeon_crtc_handle_flip(rdev, 2);
+						radeon_crtc_handle_vblank(rdev, 2);
 					rdev->irq.stat_regs.cik.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D3 vblank\n");
 				}
@@ -7528,7 +7543,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[3]))
-						radeon_crtc_handle_flip(rdev, 3);
+						radeon_crtc_handle_vblank(rdev, 3);
 					rdev->irq.stat_regs.cik.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D4 vblank\n");
 				}
@@ -7554,7 +7569,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[4]))
-						radeon_crtc_handle_flip(rdev, 4);
+						radeon_crtc_handle_vblank(rdev, 4);
 					rdev->irq.stat_regs.cik.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D5 vblank\n");
 				}
@@ -7580,7 +7595,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[5]))
-						radeon_crtc_handle_flip(rdev, 5);
+						radeon_crtc_handle_vblank(rdev, 5);
 					rdev->irq.stat_regs.cik.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D6 vblank\n");
 				}
@@ -7663,14 +7678,16 @@ restart_ih:
 			addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR);
 			status = RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS);
 			mc_client = RREG32(VM_CONTEXT1_PROTECTION_FAULT_MCCLIENT);
+			/* reset addr and status */
+			WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
+			if (addr == 0x0 && status == 0x0)
+				break;
 			dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
 				addr);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 				status);
 			cik_vm_decode_fault(rdev, status, addr, mc_client);
-			/* reset addr and status */
-			WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
 			break;
 		case 167: /* VCE */
 			DRM_DEBUG("IH: VCE int: 0x%08x\n", src_data);
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index 72e464c79a8..8e9d0f1d858 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -141,7 +141,7 @@ void cik_sdma_ring_ib_execute(struct radeon_device *rdev,
 		next_rptr += 4;
 		radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
 		radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+		radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr));
 		radeon_ring_write(ring, 1); /* number of DWs to follow */
 		radeon_ring_write(ring, next_rptr);
 	}
@@ -151,7 +151,7 @@ void cik_sdma_ring_ib_execute(struct radeon_device *rdev,
 		radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0));
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_INDIRECT_BUFFER, 0, extra_bits));
 	radeon_ring_write(ring, ib->gpu_addr & 0xffffffe0); /* base must be 32 byte aligned */
-	radeon_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xffffffff);
+	radeon_ring_write(ring, upper_32_bits(ib->gpu_addr));
 	radeon_ring_write(ring, ib->length_dw);
 
 }
@@ -203,8 +203,8 @@ void cik_sdma_fence_ring_emit(struct radeon_device *rdev,
 
 	/* write the fence */
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_FENCE, 0, 0));
-	radeon_ring_write(ring, addr & 0xffffffff);
-	radeon_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+	radeon_ring_write(ring, lower_32_bits(addr));
+	radeon_ring_write(ring, upper_32_bits(addr));
 	radeon_ring_write(ring, fence->seq);
 	/* generate an interrupt */
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_TRAP, 0, 0));
@@ -233,7 +233,7 @@ bool cik_sdma_semaphore_ring_emit(struct radeon_device *rdev,
 
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_SEMAPHORE, 0, extra_bits));
 	radeon_ring_write(ring, addr & 0xfffffff8);
-	radeon_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
+	radeon_ring_write(ring, upper_32_bits(addr));
 
 	return true;
 }
@@ -551,10 +551,10 @@ int cik_copy_dma(struct radeon_device *rdev,
 		radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_COPY, SDMA_COPY_SUB_OPCODE_LINEAR, 0));
 		radeon_ring_write(ring, cur_size_in_bytes);
 		radeon_ring_write(ring, 0); /* src/dst endian swap */
-		radeon_ring_write(ring, src_offset & 0xffffffff);
-		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xffffffff);
-		radeon_ring_write(ring, dst_offset & 0xffffffff);
-		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xffffffff);
+		radeon_ring_write(ring, lower_32_bits(src_offset));
+		radeon_ring_write(ring, upper_32_bits(src_offset));
+		radeon_ring_write(ring, lower_32_bits(dst_offset));
+		radeon_ring_write(ring, upper_32_bits(dst_offset));
 		src_offset += cur_size_in_bytes;
 		dst_offset += cur_size_in_bytes;
 	}
@@ -605,7 +605,7 @@ int cik_sdma_ring_test(struct radeon_device *rdev,
 	}
 	radeon_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0));
 	radeon_ring_write(ring, rdev->vram_scratch.gpu_addr & 0xfffffffc);
-	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xffffffff);
+	radeon_ring_write(ring, upper_32_bits(rdev->vram_scratch.gpu_addr));
 	radeon_ring_write(ring, 1); /* number of DWs to follow */
 	radeon_ring_write(ring, 0xDEADBEEF);
 	radeon_ring_unlock_commit(rdev, ring);
@@ -660,7 +660,7 @@ int cik_sdma_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 
 	ib.ptr[0] = SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
 	ib.ptr[1] = rdev->vram_scratch.gpu_addr & 0xfffffffc;
-	ib.ptr[2] = upper_32_bits(rdev->vram_scratch.gpu_addr) & 0xffffffff;
+	ib.ptr[2] = upper_32_bits(rdev->vram_scratch.gpu_addr);
 	ib.ptr[3] = 1;
 	ib.ptr[4] = 0xDEADBEEF;
 	ib.length_dw = 5;
@@ -742,7 +742,26 @@ void cik_sdma_vm_set_page(struct radeon_device *rdev,
 
 	trace_radeon_vm_set_page(pe, addr, count, incr, flags);
 
-	if (flags & R600_PTE_SYSTEM) {
+	if (flags == R600_PTE_GART) {
+		uint64_t src = rdev->gart.table_addr + (addr >> 12) * 8;
+		while (count) {
+			unsigned bytes = count * 8;
+			if (bytes > 0x1FFFF8)
+				bytes = 0x1FFFF8;
+
+			ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_COPY, SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
+			ib->ptr[ib->length_dw++] = bytes;
+			ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */
+			ib->ptr[ib->length_dw++] = lower_32_bits(src);
+			ib->ptr[ib->length_dw++] = upper_32_bits(src);
+			ib->ptr[ib->length_dw++] = lower_32_bits(pe);
+			ib->ptr[ib->length_dw++] = upper_32_bits(pe);
+
+			pe += bytes;
+			src += bytes;
+			count -= bytes / 8;
+		}
+	} else if (flags & R600_PTE_SYSTEM) {
 		while (count) {
 			ndw = count * 2;
 			if (ndw > 0xFFFFE)
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index dd7926394a8..0c6e1b55d96 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -482,6 +482,7 @@
 #define		READ_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 16)
 #define		WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT		(1 << 18)
 #define		WRITE_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 19)
+#define		PAGE_TABLE_BLOCK_SIZE(x)			(((x) & 0xF) << 24)
 #define VM_CONTEXT1_CNTL				0x1414
 #define VM_CONTEXT0_CNTL2				0x1430
 #define VM_CONTEXT1_CNTL2				0x1434
@@ -1751,12 +1752,12 @@
 #define		EOP_TC_WB_ACTION_EN                     (1 << 15) /* L2 */
 #define		EOP_TCL1_ACTION_EN                      (1 << 16)
 #define		EOP_TC_ACTION_EN                        (1 << 17) /* L2 */
+#define		EOP_TCL2_VOLATILE                       (1 << 24)
 #define		EOP_CACHE_POLICY(x)                     ((x) << 25)
                 /* 0 - LRU
 		 * 1 - Stream
 		 * 2 - Bypass
 		 */
-#define		EOP_TCL2_VOLATILE                       (1 << 27)
 #define		DATA_SEL(x)                             ((x) << 29)
                 /* 0 - discard
 		 * 1 - send low 32bit data
diff --git a/drivers/gpu/drm/radeon/clearstate_cayman.h b/drivers/gpu/drm/radeon/clearstate_cayman.h
index aa908c55a51..e48a14037b7 100644
--- a/drivers/gpu/drm/radeon/clearstate_cayman.h
+++ b/drivers/gpu/drm/radeon/clearstate_cayman.h
@@ -1050,7 +1050,7 @@ static const struct cs_extent_def SECT_CONTEXT_defs[] =
     {SECT_CONTEXT_def_5, 0x0000a29e, 5 },
     {SECT_CONTEXT_def_6, 0x0000a2a5, 56 },
     {SECT_CONTEXT_def_7, 0x0000a2de, 290 },
-    { 0, 0, 0 }
+    { NULL, 0, 0 }
 };
 static const u32 SECT_CLEAR_def_1[] =
 {
@@ -1061,7 +1061,7 @@ static const u32 SECT_CLEAR_def_1[] =
 static const struct cs_extent_def SECT_CLEAR_defs[] =
 {
     {SECT_CLEAR_def_1, 0x0000ffc0, 3 },
-    { 0, 0, 0 }
+    { NULL, 0, 0 }
 };
 static const u32 SECT_CTRLCONST_def_1[] =
 {
@@ -1071,11 +1071,11 @@ static const u32 SECT_CTRLCONST_def_1[] =
 static const struct cs_extent_def SECT_CTRLCONST_defs[] =
 {
     {SECT_CTRLCONST_def_1, 0x0000f3fc, 2 },
-    { 0, 0, 0 }
+    { NULL, 0, 0 }
 };
 static const struct cs_section_def cayman_cs_data[] = {
     { SECT_CONTEXT_defs, SECT_CONTEXT },
     { SECT_CLEAR_defs, SECT_CLEAR },
     { SECT_CTRLCONST_defs, SECT_CTRLCONST },
-    { 0, SECT_NONE }
+    { NULL, SECT_NONE }
 };
diff --git a/drivers/gpu/drm/radeon/clearstate_ci.h b/drivers/gpu/drm/radeon/clearstate_ci.h
index c3982f9475f..f55d06664e3 100644
--- a/drivers/gpu/drm/radeon/clearstate_ci.h
+++ b/drivers/gpu/drm/radeon/clearstate_ci.h
@@ -936,9 +936,9 @@ static const struct cs_extent_def ci_SECT_CONTEXT_defs[] =
     {ci_SECT_CONTEXT_def_5, 0x0000a2a0, 2 },
     {ci_SECT_CONTEXT_def_6, 0x0000a2a3, 1 },
     {ci_SECT_CONTEXT_def_7, 0x0000a2a5, 233 },
-    { 0, 0, 0 }
+    { NULL, 0, 0 }
 };
 static const struct cs_section_def ci_cs_data[] = {
     { ci_SECT_CONTEXT_defs, SECT_CONTEXT },
-    { 0, SECT_NONE }
+    { NULL, SECT_NONE }
 };
diff --git a/drivers/gpu/drm/radeon/clearstate_si.h b/drivers/gpu/drm/radeon/clearstate_si.h
index b994cb2a35a..66e39cdb5cb 100644
--- a/drivers/gpu/drm/radeon/clearstate_si.h
+++ b/drivers/gpu/drm/radeon/clearstate_si.h
@@ -933,9 +933,9 @@ static const struct cs_extent_def si_SECT_CONTEXT_defs[] =
     {si_SECT_CONTEXT_def_5, 0x0000a2a1, 1 },
     {si_SECT_CONTEXT_def_6, 0x0000a2a3, 1 },
     {si_SECT_CONTEXT_def_7, 0x0000a2a5, 233 },
-    { 0, 0, 0 }
+    { NULL, 0, 0 }
 };
 static const struct cs_section_def si_cs_data[] = {
     { si_SECT_CONTEXT_defs, SECT_CONTEXT },
-    { 0, SECT_NONE }
+    { NULL, SECT_NONE }
 };
diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c
index 5a9a5f4d788..47d31e91575 100644
--- a/drivers/gpu/drm/radeon/cypress_dpm.c
+++ b/drivers/gpu/drm/radeon/cypress_dpm.c
@@ -1551,7 +1551,7 @@ int cypress_populate_smc_voltage_tables(struct radeon_device *rdev,
 
 		table->voltageMaskTable.highMask[RV770_SMC_VOLTAGEMASK_VDDCI] = 0;
 		table->voltageMaskTable.lowMask[RV770_SMC_VOLTAGEMASK_VDDCI] =
-			cpu_to_be32(eg_pi->vddc_voltage_table.mask_low);
+			cpu_to_be32(eg_pi->vddci_voltage_table.mask_low);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/radeon/dce3_1_afmt.c b/drivers/gpu/drm/radeon/dce3_1_afmt.c
new file mode 100644
index 00000000000..51800e340a5
--- /dev/null
+++ b/drivers/gpu/drm/radeon/dce3_1_afmt.c
@@ -0,0 +1,244 @@
+/*
+ * Copyright 2013 Advanced Micro Devices, Inc.
+ * Copyright 2014 Rafał Miłecki
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include <linux/hdmi.h>
+#include <drm/drmP.h>
+#include "radeon.h"
+#include "radeon_asic.h"
+#include "r600d.h"
+
+static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	u32 tmp;
+	u8 *sadb;
+	int sad_count;
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder) {
+			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
+	if (sad_count < 0) {
+		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
+		return;
+	}
+
+	/* program the speaker allocation */
+	tmp = RREG32(AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER);
+	tmp &= ~(DP_CONNECTION | SPEAKER_ALLOCATION_MASK);
+	/* set HDMI mode */
+	tmp |= HDMI_CONNECTION;
+	if (sad_count)
+		tmp |= SPEAKER_ALLOCATION(sadb[0]);
+	else
+		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
+	WREG32(AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER, tmp);
+
+	kfree(sadb);
+}
+
+static void dce3_2_afmt_write_sad_regs(struct drm_encoder *encoder)
+{
+	struct radeon_device *rdev = encoder->dev->dev_private;
+	struct drm_connector *connector;
+	struct radeon_connector *radeon_connector = NULL;
+	struct cea_sad *sads;
+	int i, sad_count;
+
+	static const u16 eld_reg_to_type[][2] = {
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR0, HDMI_AUDIO_CODING_TYPE_PCM },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR1, HDMI_AUDIO_CODING_TYPE_AC3 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR2, HDMI_AUDIO_CODING_TYPE_MPEG1 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR3, HDMI_AUDIO_CODING_TYPE_MP3 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR4, HDMI_AUDIO_CODING_TYPE_MPEG2 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR5, HDMI_AUDIO_CODING_TYPE_AAC_LC },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR6, HDMI_AUDIO_CODING_TYPE_DTS },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR7, HDMI_AUDIO_CODING_TYPE_ATRAC },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR9, HDMI_AUDIO_CODING_TYPE_EAC3 },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR10, HDMI_AUDIO_CODING_TYPE_DTS_HD },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR11, HDMI_AUDIO_CODING_TYPE_MLP },
+		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO },
+	};
+
+	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+		if (connector->encoder == encoder) {
+			radeon_connector = to_radeon_connector(connector);
+			break;
+		}
+	}
+
+	if (!radeon_connector) {
+		DRM_ERROR("Couldn't find encoder's connector\n");
+		return;
+	}
+
+	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
+	if (sad_count < 0) {
+		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
+		return;
+	}
+	BUG_ON(!sads);
+
+	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
+		u32 value = 0;
+		u8 stereo_freqs = 0;
+		int max_channels = -1;
+		int j;
+
+		for (j = 0; j < sad_count; j++) {
+			struct cea_sad *sad = &sads[j];
+
+			if (sad->format == eld_reg_to_type[i][1]) {
+				if (sad->channels > max_channels) {
+					value = MAX_CHANNELS(sad->channels) |
+						DESCRIPTOR_BYTE_2(sad->byte2) |
+						SUPPORTED_FREQUENCIES(sad->freq);
+					max_channels = sad->channels;
+				}
+
+				if (sad->format == HDMI_AUDIO_CODING_TYPE_PCM)
+					stereo_freqs |= sad->freq;
+				else
+					break;
+			}
+		}
+
+		value |= SUPPORTED_FREQUENCIES_STEREO(stereo_freqs);
+
+		WREG32(eld_reg_to_type[i][0], value);
+	}
+
+	kfree(sads);
+}
+
+/*
+ * update the info frames with the data from the current display mode
+ */
+void dce3_1_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mode)
+{
+	struct drm_device *dev = encoder->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
+	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	u8 buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE];
+	struct hdmi_avi_infoframe frame;
+	uint32_t offset;
+	ssize_t err;
+
+	if (!dig || !dig->afmt)
+		return;
+
+	/* Silent, r600_hdmi_enable will raise WARN for us */
+	if (!dig->afmt->enabled)
+		return;
+	offset = dig->afmt->offset;
+
+	/* disable audio prior to setting up hw */
+	dig->afmt->pin = r600_audio_get_pin(rdev);
+	r600_audio_enable(rdev, dig->afmt->pin, false);
+
+	r600_audio_set_dto(encoder, mode->clock);
+
+	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
+	       HDMI0_NULL_SEND); /* send null packets when required */
+
+	WREG32(HDMI0_AUDIO_CRC_CONTROL + offset, 0x1000);
+
+	if (ASIC_IS_DCE32(rdev)) {
+		WREG32(HDMI0_AUDIO_PACKET_CONTROL + offset,
+		       HDMI0_AUDIO_DELAY_EN(1) | /* default audio delay */
+		       HDMI0_AUDIO_PACKETS_PER_LINE(3)); /* should be suffient for all audio modes and small enough for all hblanks */
+		WREG32(AFMT_AUDIO_PACKET_CONTROL + offset,
+		       AFMT_AUDIO_SAMPLE_SEND | /* send audio packets */
+		       AFMT_60958_CS_UPDATE); /* allow 60958 channel status fields to be updated */
+	} else {
+		WREG32(HDMI0_AUDIO_PACKET_CONTROL + offset,
+		       HDMI0_AUDIO_SAMPLE_SEND | /* send audio packets */
+		       HDMI0_AUDIO_DELAY_EN(1) | /* default audio delay */
+		       HDMI0_AUDIO_PACKETS_PER_LINE(3) | /* should be suffient for all audio modes and small enough for all hblanks */
+		       HDMI0_60958_CS_UPDATE); /* allow 60958 channel status fields to be updated */
+	}
+
+	if (ASIC_IS_DCE32(rdev)) {
+		dce3_2_afmt_write_speaker_allocation(encoder);
+		dce3_2_afmt_write_sad_regs(encoder);
+	}
+
+	WREG32(HDMI0_ACR_PACKET_CONTROL + offset,
+	       HDMI0_ACR_SOURCE | /* select SW CTS value - XXX verify that hw CTS works on all families */
+	       HDMI0_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
+
+	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
+	       HDMI0_NULL_SEND | /* send null packets when required */
+	       HDMI0_GC_SEND | /* send general control packets */
+	       HDMI0_GC_CONT); /* send general control packets every frame */
+
+	/* TODO: HDMI0_AUDIO_INFO_UPDATE */
+	WREG32(HDMI0_INFOFRAME_CONTROL0 + offset,
+	       HDMI0_AVI_INFO_SEND | /* enable AVI info frames */
+	       HDMI0_AVI_INFO_CONT | /* send AVI info frames every frame/field */
+	       HDMI0_AUDIO_INFO_SEND | /* enable audio info frames (frames won't be set until audio is enabled) */
+	       HDMI0_AUDIO_INFO_CONT); /* send audio info frames every frame/field */
+
+	WREG32(HDMI0_INFOFRAME_CONTROL1 + offset,
+	       HDMI0_AVI_INFO_LINE(2) | /* anything other than 0 */
+	       HDMI0_AUDIO_INFO_LINE(2)); /* anything other than 0 */
+
+	WREG32(HDMI0_GC + offset, 0); /* unset HDMI0_GC_AVMUTE */
+
+	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
+	if (err < 0) {
+		DRM_ERROR("failed to setup AVI infoframe: %zd\n", err);
+		return;
+	}
+
+	err = hdmi_avi_infoframe_pack(&frame, buffer, sizeof(buffer));
+	if (err < 0) {
+		DRM_ERROR("failed to pack AVI infoframe: %zd\n", err);
+		return;
+	}
+
+	r600_hdmi_update_avi_infoframe(encoder, buffer, sizeof(buffer));
+	r600_hdmi_update_ACR(encoder, mode->clock);
+
+	/* it's unknown what these bits do excatly, but it's indeed quite useful for debugging */
+	WREG32(HDMI0_RAMP_CONTROL0 + offset, 0x00FFFFFF);
+	WREG32(HDMI0_RAMP_CONTROL1 + offset, 0x007FFFFF);
+	WREG32(HDMI0_RAMP_CONTROL2 + offset, 0x00000001);
+	WREG32(HDMI0_RAMP_CONTROL3 + offset, 0x00000001);
+
+	r600_hdmi_audio_workaround(encoder);
+
+	/* enable audio after to setting up hw */
+	r600_audio_enable(rdev, dig->afmt->pin, true);
+}
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 0f7a51a3694..15e4f28015e 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -189,7 +189,7 @@ static const u32 evergreen_golden_registers[] =
 	0x8c1c, 0xffffffff, 0x00001010,
 	0x28350, 0xffffffff, 0x00000000,
 	0xa008, 0xffffffff, 0x00010000,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x9508, 0xffffffff, 0x00000002,
 	0x913c, 0x0000000f, 0x0000000a
 };
@@ -476,7 +476,7 @@ static const u32 cedar_golden_registers[] =
 	0x8c1c, 0xffffffff, 0x00001010,
 	0x28350, 0xffffffff, 0x00000000,
 	0xa008, 0xffffffff, 0x00010000,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x9508, 0xffffffff, 0x00000002
 };
 
@@ -635,7 +635,7 @@ static const u32 juniper_mgcg_init[] =
 static const u32 supersumo_golden_registers[] =
 {
 	0x5eb4, 0xffffffff, 0x00000002,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x7030, 0xffffffff, 0x00000011,
 	0x7c30, 0xffffffff, 0x00000011,
 	0x6104, 0x01000300, 0x00000000,
@@ -719,7 +719,7 @@ static const u32 sumo_golden_registers[] =
 static const u32 wrestler_golden_registers[] =
 {
 	0x5eb4, 0xffffffff, 0x00000002,
-	0x5cc, 0xffffffff, 0x00000001,
+	0x5c4, 0xffffffff, 0x00000001,
 	0x7030, 0xffffffff, 0x00000011,
 	0x7c30, 0xffffffff, 0x00000011,
 	0x6104, 0x01000300, 0x00000000,
@@ -1301,36 +1301,6 @@ void dce4_wait_for_vblank(struct radeon_device *rdev, int crtc)
 }
 
 /**
- * radeon_irq_kms_pflip_irq_get - pre-pageflip callback.
- *
- * @rdev: radeon_device pointer
- * @crtc: crtc to prepare for pageflip on
- *
- * Pre-pageflip callback (evergreen+).
- * Enables the pageflip irq (vblank irq).
- */
-void evergreen_pre_page_flip(struct radeon_device *rdev, int crtc)
-{
-	/* enable the pflip int */
-	radeon_irq_kms_pflip_irq_get(rdev, crtc);
-}
-
-/**
- * evergreen_post_page_flip - pos-pageflip callback.
- *
- * @rdev: radeon_device pointer
- * @crtc: crtc to cleanup pageflip on
- *
- * Post-pageflip callback (evergreen+).
- * Disables the pageflip irq (vblank irq).
- */
-void evergreen_post_page_flip(struct radeon_device *rdev, int crtc)
-{
-	/* disable the pflip int */
-	radeon_irq_kms_pflip_irq_put(rdev, crtc);
-}
-
-/**
  * evergreen_page_flip - pageflip callback.
  *
  * @rdev: radeon_device pointer
@@ -1343,7 +1313,7 @@ void evergreen_post_page_flip(struct radeon_device *rdev, int crtc)
  * double buffered update to take place.
  * Returns the current update pending status.
  */
-u32 evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
+void evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset);
@@ -1375,9 +1345,23 @@ u32 evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	/* Unlock the lock, so double-buffering can take place inside vblank */
 	tmp &= ~EVERGREEN_GRPH_UPDATE_LOCK;
 	WREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset, tmp);
+}
+
+/**
+ * evergreen_page_flip_pending - check if page flip is still pending
+ *
+ * @rdev: radeon_device pointer
+ * @crtc_id: crtc to check
+ *
+ * Returns the current update pending status.
+ */
+bool evergreen_page_flip_pending(struct radeon_device *rdev, int crtc_id)
+{
+	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 
 	/* Return current update_pending status: */
-	return RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset) & EVERGREEN_GRPH_SURFACE_UPDATE_PENDING;
+	return !!(RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset) &
+		EVERGREEN_GRPH_SURFACE_UPDATE_PENDING);
 }
 
 /* get temperature in millidegrees */
@@ -2658,8 +2642,9 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s
 	for (i = 0; i < rdev->num_crtc; i++) {
 		if (save->crtc_enabled[i]) {
 			tmp = RREG32(EVERGREEN_MASTER_UPDATE_MODE + crtc_offsets[i]);
-			if ((tmp & 0x3) != 0) {
-				tmp &= ~0x3;
+			if ((tmp & 0x7) != 3) {
+				tmp &= ~0x7;
+				tmp |= 0x3;
 				WREG32(EVERGREEN_MASTER_UPDATE_MODE + crtc_offsets[i], tmp);
 			}
 			tmp = RREG32(EVERGREEN_GRPH_UPDATE + crtc_offsets[i]);
@@ -3353,6 +3338,18 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 			disabled_rb_mask &= ~(1 << i);
 	}
 
+	for (i = 0; i < rdev->config.evergreen.num_ses; i++) {
+		u32 simd_disable_bitmap;
+
+		WREG32(GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES | SE_INDEX(i));
+		WREG32(RLC_GFX_INDEX, INSTANCE_BROADCAST_WRITES | SE_INDEX(i));
+		simd_disable_bitmap = (RREG32(CC_GC_SHADER_PIPE_CONFIG) & 0xffff0000) >> 16;
+		simd_disable_bitmap |= 0xffffffff << rdev->config.evergreen.max_simds;
+		tmp <<= 16;
+		tmp |= simd_disable_bitmap;
+	}
+	rdev->config.evergreen.active_simds = hweight32(~tmp);
+
 	WREG32(GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES | SE_BROADCAST_WRITES);
 	WREG32(RLC_GFX_INDEX, INSTANCE_BROADCAST_WRITES | SE_BROADCAST_WRITES);
 
@@ -4759,6 +4756,7 @@ static u32 evergreen_get_ih_wptr(struct radeon_device *rdev)
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_WPTR_OVERFLOW_CLEAR;
 		WREG32(IH_RB_CNTL, tmp);
+		wptr &= ~RB_OVERFLOW;
 	}
 	return (wptr & rdev->ih.ptr_mask);
 }
@@ -4810,7 +4808,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_flip(rdev, 0);
+						radeon_crtc_handle_vblank(rdev, 0);
 					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D1 vblank\n");
 				}
@@ -4836,7 +4834,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_flip(rdev, 1);
+						radeon_crtc_handle_vblank(rdev, 1);
 					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D2 vblank\n");
 				}
@@ -4862,7 +4860,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[2]))
-						radeon_crtc_handle_flip(rdev, 2);
+						radeon_crtc_handle_vblank(rdev, 2);
 					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D3 vblank\n");
 				}
@@ -4888,7 +4886,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[3]))
-						radeon_crtc_handle_flip(rdev, 3);
+						radeon_crtc_handle_vblank(rdev, 3);
 					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D4 vblank\n");
 				}
@@ -4914,7 +4912,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[4]))
-						radeon_crtc_handle_flip(rdev, 4);
+						radeon_crtc_handle_vblank(rdev, 4);
 					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D5 vblank\n");
 				}
@@ -4940,7 +4938,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[5]))
-						radeon_crtc_handle_flip(rdev, 5);
+						radeon_crtc_handle_vblank(rdev, 5);
 					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D6 vblank\n");
 				}
@@ -5070,14 +5068,16 @@ restart_ih:
 		case 147:
 			addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR);
 			status = RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS);
+			/* reset addr and status */
+			WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
+			if (addr == 0x0 && status == 0x0)
+				break;
 			dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
 				addr);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 				status);
 			cayman_vm_decode_fault(rdev, status, addr);
-			/* reset addr and status */
-			WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
 			break;
 		case 176: /* CP_INT in ring buffer */
 		case 177: /* CP_INT in IB1 */
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index 05b0c95813f..1ec0e6e83f9 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -293,10 +293,13 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	u8 buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE];
 	struct hdmi_avi_infoframe frame;
 	uint32_t offset;
 	ssize_t err;
+	uint32_t val;
+	int bpc = 8;
 
 	if (!dig || !dig->afmt)
 		return;
@@ -306,6 +309,12 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 		return;
 	offset = dig->afmt->offset;
 
+	/* hdmi deep color mode general control packets setup, if bpc > 8 */
+	if (encoder->crtc) {
+		struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
+		bpc = radeon_crtc->bpc;
+	}
+
 	/* disable audio prior to setting up hw */
 	if (ASIC_IS_DCE6(rdev)) {
 		dig->afmt->pin = dce6_audio_get_pin(rdev);
@@ -322,6 +331,35 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 
 	WREG32(AFMT_AUDIO_CRC_CONTROL + offset, 0x1000);
 
+	val = RREG32(HDMI_CONTROL + offset);
+	val &= ~HDMI_DEEP_COLOR_ENABLE;
+	val &= ~HDMI_DEEP_COLOR_DEPTH_MASK;
+
+	switch (bpc) {
+		case 0:
+		case 6:
+		case 8:
+		case 16:
+		default:
+			DRM_DEBUG("%s: Disabling hdmi deep color for %d bpc.\n",
+					 connector->name, bpc);
+			break;
+		case 10:
+			val |= HDMI_DEEP_COLOR_ENABLE;
+			val |= HDMI_DEEP_COLOR_DEPTH(HDMI_30BIT_DEEP_COLOR);
+			DRM_DEBUG("%s: Enabling hdmi deep color 30 for 10 bpc.\n",
+					 connector->name);
+			break;
+		case 12:
+			val |= HDMI_DEEP_COLOR_ENABLE;
+			val |= HDMI_DEEP_COLOR_DEPTH(HDMI_36BIT_DEEP_COLOR);
+			DRM_DEBUG("%s: Enabling hdmi deep color 36 for 12 bpc.\n",
+					 connector->name);
+			break;
+	}
+
+	WREG32(HDMI_CONTROL + offset, val);
+
 	WREG32(HDMI_VBI_PACKET_CONTROL + offset,
 	       HDMI_NULL_SEND | /* send null packets when required */
 	       HDMI_GC_SEND | /* send general control packets */
@@ -348,9 +386,13 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 
 	/* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */
 
-	WREG32(HDMI_ACR_PACKET_CONTROL + offset,
-	       HDMI_ACR_SOURCE | /* select SW CTS value */
-	       HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
+	if (bpc > 8)
+		WREG32(HDMI_ACR_PACKET_CONTROL + offset,
+		       HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
+	else
+		WREG32(HDMI_ACR_PACKET_CONTROL + offset,
+		       HDMI_ACR_SOURCE | /* select SW CTS value */
+		       HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	evergreen_hdmi_update_ACR(encoder, mode->clock);
 
diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h
index a0f63ff5a5e..23bff590fb6 100644
--- a/drivers/gpu/drm/radeon/evergreen_reg.h
+++ b/drivers/gpu/drm/radeon/evergreen_reg.h
@@ -116,6 +116,8 @@
 #       define EVERGREEN_GRPH_ARRAY_LINEAR_ALIGNED      1
 #       define EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1      2
 #       define EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1      4
+#define EVERGREEN_GRPH_LUT_10BIT_BYPASS_CONTROL         0x6808
+#       define EVERGREEN_LUT_10BIT_BYPASS_EN            (1 << 8)
 #define EVERGREEN_GRPH_SWAP_CONTROL                     0x680c
 #       define EVERGREEN_GRPH_ENDIAN_SWAP(x)            (((x) & 0x3) << 0)
 #       define EVERGREEN_GRPH_ENDIAN_NONE               0
@@ -237,7 +239,6 @@
 #       define EVERGREEN_CRTC_V_BLANK                   (1 << 0)
 #define EVERGREEN_CRTC_STATUS_POSITION                  0x6e90
 #define EVERGREEN_CRTC_STATUS_HV_COUNT                  0x6ea0
-#define EVERGREEN_MASTER_UPDATE_MODE                    0x6ef8
 #define EVERGREEN_CRTC_UPDATE_LOCK                      0x6ed4
 #define EVERGREEN_MASTER_UPDATE_LOCK                    0x6ef4
 #define EVERGREEN_MASTER_UPDATE_MODE                    0x6ef8
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index f9c7963b3ee..b066d6711b8 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -517,10 +517,11 @@
 #       define HDMI_ERROR_ACK                (1 << 8)
 #       define HDMI_ERROR_MASK               (1 << 9)
 #       define HDMI_DEEP_COLOR_ENABLE        (1 << 24)
-#       define HDMI_DEEP_COLOR_DEPTH         (((x) & 3) << 28)
+#       define HDMI_DEEP_COLOR_DEPTH(x)      (((x) & 3) << 28)
 #       define HDMI_24BIT_DEEP_COLOR         0
 #       define HDMI_30BIT_DEEP_COLOR         1
 #       define HDMI_36BIT_DEEP_COLOR         2
+#       define HDMI_DEEP_COLOR_DEPTH_MASK    (3 << 28)
 #define HDMI_STATUS                          0x7034
 #       define HDMI_ACTIVE_AVMUTE            (1 << 0)
 #       define HDMI_AUDIO_PACKET_ERROR       (1 << 16)
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 3f6e817d97e..9ef8c38f2d6 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -2726,7 +2726,7 @@ int kv_dpm_init(struct radeon_device *rdev)
 	pi->caps_sclk_ds = true;
 	pi->enable_auto_thermal_throttling = true;
 	pi->disable_nb_ps3_in_battery = false;
-	pi->bapm_enable = false;
+	pi->bapm_enable = true;
 	pi->voltage_drop_t = 0;
 	pi->caps_sclk_throttle_low_notification = false;
 	pi->caps_fps = false; /* true? */
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index d246e043421..5a33ca68186 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1057,6 +1057,18 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 			disabled_rb_mask &= ~(1 << i);
 	}
 
+	for (i = 0; i < rdev->config.cayman.max_shader_engines; i++) {
+		u32 simd_disable_bitmap;
+
+		WREG32(GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES | SE_INDEX(i));
+		WREG32(RLC_GFX_INDEX, INSTANCE_BROADCAST_WRITES | SE_INDEX(i));
+		simd_disable_bitmap = (RREG32(CC_GC_SHADER_PIPE_CONFIG) & 0xffff0000) >> 16;
+		simd_disable_bitmap |= 0xffffffff << rdev->config.cayman.max_simds_per_se;
+		tmp <<= 16;
+		tmp |= simd_disable_bitmap;
+	}
+	rdev->config.cayman.active_simds = hweight32(~tmp);
+
 	WREG32(GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES | SE_BROADCAST_WRITES);
 	WREG32(RLC_GFX_INDEX, INSTANCE_BROADCAST_WRITES | SE_BROADCAST_WRITES);
 
@@ -1228,12 +1240,14 @@ static int cayman_pcie_gart_enable(struct radeon_device *rdev)
 	       SYSTEM_APERTURE_UNMAPPED_ACCESS_PASS_THRU);
 	/* Setup L2 cache */
 	WREG32(VM_L2_CNTL, ENABLE_L2_CACHE |
+	       ENABLE_L2_FRAGMENT_PROCESSING |
 	       ENABLE_L2_PTE_CACHE_LRU_UPDATE_BY_WRITE |
 	       ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE |
 	       EFFECTIVE_L2_QUEUE_SIZE(7) |
 	       CONTEXT1_IDENTITY_ACCESS_MODE(1));
 	WREG32(VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS | INVALIDATE_L2_CACHE);
 	WREG32(VM_L2_CNTL3, L2_CACHE_BIGK_ASSOCIATIVITY |
+	       BANK_SELECT(6) |
 	       L2_CACHE_BIGK_FRAGMENT_SIZE(6));
 	/* setup context0 */
 	WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
@@ -1266,6 +1280,7 @@ static int cayman_pcie_gart_enable(struct radeon_device *rdev)
 	       (u32)(rdev->dummy_page.addr >> 12));
 	WREG32(VM_CONTEXT1_CNTL2, 4);
 	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(1) |
+				PAGE_TABLE_BLOCK_SIZE(radeon_vm_block_size - 9) |
 				RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
 				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT |
 				DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
@@ -1343,7 +1358,7 @@ void cayman_fence_ring_emit(struct radeon_device *rdev,
 	/* EVENT_WRITE_EOP - flush caches, send int */
 	radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
 	radeon_ring_write(ring, EVENT_TYPE(CACHE_FLUSH_AND_INV_EVENT_TS) | EVENT_INDEX(5));
-	radeon_ring_write(ring, addr & 0xffffffff);
+	radeon_ring_write(ring, lower_32_bits(addr));
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff) | DATA_SEL(1) | INT_SEL(2));
 	radeon_ring_write(ring, fence->seq);
 	radeon_ring_write(ring, 0);
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 004c931606c..01fc4888e6f 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -1315,7 +1315,7 @@ static void ni_populate_smc_voltage_tables(struct radeon_device *rdev,
 
 		table->voltageMaskTable.highMask[NISLANDS_SMC_VOLTAGEMASK_VDDCI] = 0;
 		table->voltageMaskTable.lowMask[NISLANDS_SMC_VOLTAGEMASK_VDDCI] =
-			cpu_to_be32(eg_pi->vddc_voltage_table.mask_low);
+			cpu_to_be32(eg_pi->vddci_voltage_table.mask_low);
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index d996033c243..2e12e4d6925 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -128,6 +128,7 @@
 #define		READ_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 16)
 #define		WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT		(1 << 18)
 #define		WRITE_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 19)
+#define		PAGE_TABLE_BLOCK_SIZE(x)			(((x) & 0xF) << 24)
 #define VM_CONTEXT1_CNTL				0x1414
 #define VM_CONTEXT0_CNTL2				0x1430
 #define VM_CONTEXT1_CNTL2				0x1434
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index b6c32640df2..1544efcf1c3 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -142,36 +142,6 @@ void r100_wait_for_vblank(struct radeon_device *rdev, int crtc)
 }
 
 /**
- * r100_pre_page_flip - pre-pageflip callback.
- *
- * @rdev: radeon_device pointer
- * @crtc: crtc to prepare for pageflip on
- *
- * Pre-pageflip callback (r1xx-r4xx).
- * Enables the pageflip irq (vblank irq).
- */
-void r100_pre_page_flip(struct radeon_device *rdev, int crtc)
-{
-	/* enable the pflip int */
-	radeon_irq_kms_pflip_irq_get(rdev, crtc);
-}
-
-/**
- * r100_post_page_flip - pos-pageflip callback.
- *
- * @rdev: radeon_device pointer
- * @crtc: crtc to cleanup pageflip on
- *
- * Post-pageflip callback (r1xx-r4xx).
- * Disables the pageflip irq (vblank irq).
- */
-void r100_post_page_flip(struct radeon_device *rdev, int crtc)
-{
-	/* disable the pflip int */
-	radeon_irq_kms_pflip_irq_put(rdev, crtc);
-}
-
-/**
  * r100_page_flip - pageflip callback.
  *
  * @rdev: radeon_device pointer
@@ -182,9 +152,8 @@ void r100_post_page_flip(struct radeon_device *rdev, int crtc)
  * During vblank we take the crtc lock and wait for the update_pending
  * bit to go high, when it does, we release the lock, and allow the
  * double buffered update to take place.
- * Returns the current update pending status.
  */
-u32 r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
+void r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = ((u32)crtc_base) | RADEON_CRTC_OFFSET__OFFSET_LOCK;
@@ -206,8 +175,24 @@ u32 r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	tmp &= ~RADEON_CRTC_OFFSET__OFFSET_LOCK;
 	WREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset, tmp);
 
+}
+
+/**
+ * r100_page_flip_pending - check if page flip is still pending
+ *
+ * @rdev: radeon_device pointer
+ * @crtc_id: crtc to check
+ *
+ * Check if the last pagefilp is still pending (r1xx-r4xx).
+ * Returns the current update pending status.
+ */
+bool r100_page_flip_pending(struct radeon_device *rdev, int crtc_id)
+{
+	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+
 	/* Return current update_pending status: */
-	return RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET;
+	return !!(RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) &
+		RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET);
 }
 
 /**
@@ -697,15 +682,11 @@ void r100_pci_gart_disable(struct radeon_device *rdev)
 	WREG32(RADEON_AIC_HI_ADDR, 0);
 }
 
-int r100_pci_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
+void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
+			    uint64_t addr)
 {
 	u32 *gtt = rdev->gart.ptr;
-
-	if (i < 0 || i > rdev->gart.num_gpu_pages) {
-		return -EINVAL;
-	}
 	gtt[i] = cpu_to_le32(lower_32_bits(addr));
-	return 0;
 }
 
 void r100_pci_gart_fini(struct radeon_device *rdev)
@@ -794,7 +775,7 @@ int r100_irq_process(struct radeon_device *rdev)
 				wake_up(&rdev->irq.vblank_queue);
 			}
 			if (atomic_read(&rdev->irq.pflip[0]))
-				radeon_crtc_handle_flip(rdev, 0);
+				radeon_crtc_handle_vblank(rdev, 0);
 		}
 		if (status & RADEON_CRTC2_VBLANK_STAT) {
 			if (rdev->irq.crtc_vblank_int[1]) {
@@ -803,7 +784,7 @@ int r100_irq_process(struct radeon_device *rdev)
 				wake_up(&rdev->irq.vblank_queue);
 			}
 			if (atomic_read(&rdev->irq.pflip[1]))
-				radeon_crtc_handle_flip(rdev, 1);
+				radeon_crtc_handle_vblank(rdev, 1);
 		}
 		if (status & RADEON_FP_DETECT_STAT) {
 			queue_hotplug = true;
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 206caf9700b..3c21d77a483 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -72,13 +72,11 @@ void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev)
 #define R300_PTE_WRITEABLE (1 << 2)
 #define R300_PTE_READABLE  (1 << 3)
 
-int rv370_pcie_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
+void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
+			      uint64_t addr)
 {
 	void __iomem *ptr = rdev->gart.ptr;
 
-	if (i < 0 || i > rdev->gart.num_gpu_pages) {
-		return -EINVAL;
-	}
 	addr = (lower_32_bits(addr) >> 8) |
 	       ((upper_32_bits(addr) & 0xff) << 24) |
 	       R300_PTE_WRITEABLE | R300_PTE_READABLE;
@@ -86,7 +84,6 @@ int rv370_pcie_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
 	 * on powerpc without HW swappers, it'll get swapped on way
 	 * into VRAM - so no need for cpu_to_le32 on VRAM tables */
 	writel(addr, ((void __iomem *)ptr) + (i * 4));
-	return 0;
 }
 
 int rv370_pcie_gart_init(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/r500_reg.h b/drivers/gpu/drm/radeon/r500_reg.h
index 1dd0d32993d..136b7bc7cd2 100644
--- a/drivers/gpu/drm/radeon/r500_reg.h
+++ b/drivers/gpu/drm/radeon/r500_reg.h
@@ -402,6 +402,7 @@
  * block and vice versa.  This applies to GRPH, CUR, etc.
  */
 #define AVIVO_D1GRPH_LUT_SEL                                    0x6108
+#       define AVIVO_LUT_10BIT_BYPASS_EN                        (1 << 8)
 #define AVIVO_D1GRPH_PRIMARY_SURFACE_ADDRESS                    0x6110
 #define R700_D1GRPH_PRIMARY_SURFACE_ADDRESS_HIGH                0x6914
 #define R700_D2GRPH_PRIMARY_SURFACE_ADDRESS_HIGH                0x6114
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index bbc189fd3dd..3c69f58e46e 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -1958,6 +1958,9 @@ static void r600_gpu_init(struct radeon_device *rdev)
 	if (tmp < rdev->config.r600.max_simds) {
 		rdev->config.r600.max_simds = tmp;
 	}
+	tmp = rdev->config.r600.max_simds -
+		r600_count_pipe_bits((cc_gc_shader_pipe_config >> 16) & R6XX_MAX_SIMDS_MASK);
+	rdev->config.r600.active_simds = tmp;
 
 	disabled_rb_mask = (RREG32(CC_RB_BACKEND_DISABLE) >> 16) & R6XX_MAX_BACKENDS_MASK;
 	tmp = (tiling_config & PIPE_TILING__MASK) >> PIPE_TILING__SHIFT;
@@ -2724,7 +2727,7 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
 		/* EVENT_WRITE_EOP - flush caches, send int */
 		radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
 		radeon_ring_write(ring, EVENT_TYPE(CACHE_FLUSH_AND_INV_EVENT_TS) | EVENT_INDEX(5));
-		radeon_ring_write(ring, addr & 0xffffffff);
+		radeon_ring_write(ring, lower_32_bits(addr));
 		radeon_ring_write(ring, (upper_32_bits(addr) & 0xff) | DATA_SEL(1) | INT_SEL(2));
 		radeon_ring_write(ring, fence->seq);
 		radeon_ring_write(ring, 0);
@@ -2763,7 +2766,7 @@ bool r600_semaphore_ring_emit(struct radeon_device *rdev,
 		sel |= PACKET3_SEM_WAIT_ON_SIGNAL;
 
 	radeon_ring_write(ring, PACKET3(PACKET3_MEM_SEMAPHORE, 1));
-	radeon_ring_write(ring, addr & 0xffffffff);
+	radeon_ring_write(ring, lower_32_bits(addr));
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff) | sel);
 
 	return true;
@@ -2824,9 +2827,9 @@ int r600_copy_cpdma(struct radeon_device *rdev,
 		if (size_in_bytes == 0)
 			tmp |= PACKET3_CP_DMA_CP_SYNC;
 		radeon_ring_write(ring, PACKET3(PACKET3_CP_DMA, 4));
-		radeon_ring_write(ring, src_offset & 0xffffffff);
+		radeon_ring_write(ring, lower_32_bits(src_offset));
 		radeon_ring_write(ring, tmp);
-		radeon_ring_write(ring, dst_offset & 0xffffffff);
+		radeon_ring_write(ring, lower_32_bits(dst_offset));
 		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
 		radeon_ring_write(ring, cur_size_in_bytes);
 		src_offset += cur_size_in_bytes;
@@ -3792,6 +3795,7 @@ static u32 r600_get_ih_wptr(struct radeon_device *rdev)
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_WPTR_OVERFLOW_CLEAR;
 		WREG32(IH_RB_CNTL, tmp);
+		wptr &= ~RB_OVERFLOW;
 	}
 	return (wptr & rdev->ih.ptr_mask);
 }
@@ -3876,7 +3880,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_flip(rdev, 0);
+						radeon_crtc_handle_vblank(rdev, 0);
 					rdev->irq.stat_regs.r600.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D1 vblank\n");
 				}
@@ -3902,7 +3906,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_flip(rdev, 1);
+						radeon_crtc_handle_vblank(rdev, 1);
 					rdev->irq.stat_regs.r600.disp_int &= ~LB_D2_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D2 vblank\n");
 				}
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index 85a2bb28aed..26ef8ced6f8 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -133,7 +133,7 @@ struct radeon_hdmi_acr r600_hdmi_acr(uint32_t clock)
 /*
  * update the N and CTS parameters for a given pixel clock rate
  */
-static void r600_hdmi_update_ACR(struct drm_encoder *encoder, uint32_t clock)
+void r600_hdmi_update_ACR(struct drm_encoder *encoder, uint32_t clock)
 {
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
@@ -142,21 +142,33 @@ static void r600_hdmi_update_ACR(struct drm_encoder *encoder, uint32_t clock)
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 	uint32_t offset = dig->afmt->offset;
 
-	WREG32(HDMI0_ACR_32_0 + offset, HDMI0_ACR_CTS_32(acr.cts_32khz));
-	WREG32(HDMI0_ACR_32_1 + offset, acr.n_32khz);
-
-	WREG32(HDMI0_ACR_44_0 + offset, HDMI0_ACR_CTS_44(acr.cts_44_1khz));
-	WREG32(HDMI0_ACR_44_1 + offset, acr.n_44_1khz);
-
-	WREG32(HDMI0_ACR_48_0 + offset, HDMI0_ACR_CTS_48(acr.cts_48khz));
-	WREG32(HDMI0_ACR_48_1 + offset, acr.n_48khz);
+	WREG32_P(HDMI0_ACR_32_0 + offset,
+		 HDMI0_ACR_CTS_32(acr.cts_32khz),
+		 ~HDMI0_ACR_CTS_32_MASK);
+	WREG32_P(HDMI0_ACR_32_1 + offset,
+		 HDMI0_ACR_N_32(acr.n_32khz),
+		 ~HDMI0_ACR_N_32_MASK);
+
+	WREG32_P(HDMI0_ACR_44_0 + offset,
+		 HDMI0_ACR_CTS_44(acr.cts_44_1khz),
+		 ~HDMI0_ACR_CTS_44_MASK);
+	WREG32_P(HDMI0_ACR_44_1 + offset,
+		 HDMI0_ACR_N_44(acr.n_44_1khz),
+		 ~HDMI0_ACR_N_44_MASK);
+
+	WREG32_P(HDMI0_ACR_48_0 + offset,
+		 HDMI0_ACR_CTS_48(acr.cts_48khz),
+		 ~HDMI0_ACR_CTS_48_MASK);
+	WREG32_P(HDMI0_ACR_48_1 + offset,
+		 HDMI0_ACR_N_48(acr.n_48khz),
+		 ~HDMI0_ACR_N_48_MASK);
 }
 
 /*
  * build a HDMI Video Info Frame
  */
-static void r600_hdmi_update_avi_infoframe(struct drm_encoder *encoder,
-					   void *buffer, size_t size)
+void r600_hdmi_update_avi_infoframe(struct drm_encoder *encoder, void *buffer,
+				    size_t size)
 {
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
@@ -231,7 +243,7 @@ int r600_hdmi_buffer_status_changed(struct drm_encoder *encoder)
 /*
  * write the audio workaround status to the hardware
  */
-static void r600_hdmi_audio_workaround(struct drm_encoder *encoder)
+void r600_hdmi_audio_workaround(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
@@ -250,7 +262,7 @@ static void r600_hdmi_audio_workaround(struct drm_encoder *encoder)
 		 value, ~HDMI0_AUDIO_TEST_EN);
 }
 
-static void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
+void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 {
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
@@ -320,121 +332,6 @@ static void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock)
 	}
 }
 
-static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder)
-{
-	struct radeon_device *rdev = encoder->dev->dev_private;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
-	u32 tmp;
-	u8 *sadb;
-	int sad_count;
-
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
-		return;
-	}
-
-	sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb);
-	if (sad_count < 0) {
-		DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count);
-		return;
-	}
-
-	/* program the speaker allocation */
-	tmp = RREG32(AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER);
-	tmp &= ~(DP_CONNECTION | SPEAKER_ALLOCATION_MASK);
-	/* set HDMI mode */
-	tmp |= HDMI_CONNECTION;
-	if (sad_count)
-		tmp |= SPEAKER_ALLOCATION(sadb[0]);
-	else
-		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
-	WREG32(AZ_F0_CODEC_PIN0_CONTROL_CHANNEL_SPEAKER, tmp);
-
-	kfree(sadb);
-}
-
-static void dce3_2_afmt_write_sad_regs(struct drm_encoder *encoder)
-{
-	struct radeon_device *rdev = encoder->dev->dev_private;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
-	struct cea_sad *sads;
-	int i, sad_count;
-
-	static const u16 eld_reg_to_type[][2] = {
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR0, HDMI_AUDIO_CODING_TYPE_PCM },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR1, HDMI_AUDIO_CODING_TYPE_AC3 },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR2, HDMI_AUDIO_CODING_TYPE_MPEG1 },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR3, HDMI_AUDIO_CODING_TYPE_MP3 },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR4, HDMI_AUDIO_CODING_TYPE_MPEG2 },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR5, HDMI_AUDIO_CODING_TYPE_AAC_LC },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR6, HDMI_AUDIO_CODING_TYPE_DTS },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR7, HDMI_AUDIO_CODING_TYPE_ATRAC },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR9, HDMI_AUDIO_CODING_TYPE_EAC3 },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR10, HDMI_AUDIO_CODING_TYPE_DTS_HD },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR11, HDMI_AUDIO_CODING_TYPE_MLP },
-		{ AZ_F0_CODEC_PIN0_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO },
-	};
-
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
-		return;
-	}
-
-	sad_count = drm_edid_to_sad(radeon_connector->edid, &sads);
-	if (sad_count < 0) {
-		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
-		return;
-	}
-	BUG_ON(!sads);
-
-	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
-		u32 value = 0;
-		u8 stereo_freqs = 0;
-		int max_channels = -1;
-		int j;
-
-		for (j = 0; j < sad_count; j++) {
-			struct cea_sad *sad = &sads[j];
-
-			if (sad->format == eld_reg_to_type[i][1]) {
-				if (sad->channels > max_channels) {
-					value = MAX_CHANNELS(sad->channels) |
-						DESCRIPTOR_BYTE_2(sad->byte2) |
-						SUPPORTED_FREQUENCIES(sad->freq);
-					max_channels = sad->channels;
-				}
-
-				if (sad->format == HDMI_AUDIO_CODING_TYPE_PCM)
-					stereo_freqs |= sad->freq;
-				else
-					break;
-			}
-		}
-
-		value |= SUPPORTED_FREQUENCIES_STEREO(stereo_freqs);
-
-		WREG32(eld_reg_to_type[i][0], value);
-	}
-
-	kfree(sads);
-}
-
 /*
  * update the info frames with the data from the current display mode
  */
@@ -447,6 +344,7 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 	u8 buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE];
 	struct hdmi_avi_infoframe frame;
 	uint32_t offset;
+	uint32_t acr_ctl;
 	ssize_t err;
 
 	if (!dig || !dig->afmt)
@@ -463,52 +361,44 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 
 	r600_audio_set_dto(encoder, mode->clock);
 
-	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
-	       HDMI0_NULL_SEND); /* send null packets when required */
-
-	WREG32(HDMI0_AUDIO_CRC_CONTROL + offset, 0x1000);
-
-	if (ASIC_IS_DCE32(rdev)) {
-		WREG32(HDMI0_AUDIO_PACKET_CONTROL + offset,
-		       HDMI0_AUDIO_DELAY_EN(1) | /* default audio delay */
-		       HDMI0_AUDIO_PACKETS_PER_LINE(3)); /* should be suffient for all audio modes and small enough for all hblanks */
-		WREG32(AFMT_AUDIO_PACKET_CONTROL + offset,
-		       AFMT_AUDIO_SAMPLE_SEND | /* send audio packets */
-		       AFMT_60958_CS_UPDATE); /* allow 60958 channel status fields to be updated */
-	} else {
-		WREG32(HDMI0_AUDIO_PACKET_CONTROL + offset,
-		       HDMI0_AUDIO_SAMPLE_SEND | /* send audio packets */
-		       HDMI0_AUDIO_DELAY_EN(1) | /* default audio delay */
-		       HDMI0_AUDIO_PACKETS_PER_LINE(3) | /* should be suffient for all audio modes and small enough for all hblanks */
-		       HDMI0_60958_CS_UPDATE); /* allow 60958 channel status fields to be updated */
-	}
-
-	if (ASIC_IS_DCE32(rdev)) {
-		dce3_2_afmt_write_speaker_allocation(encoder);
-		dce3_2_afmt_write_sad_regs(encoder);
-	}
-
-	WREG32(HDMI0_ACR_PACKET_CONTROL + offset,
-	       HDMI0_ACR_SOURCE | /* select SW CTS value - XXX verify that hw CTS works on all families */
-	       HDMI0_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
-
-	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
-	       HDMI0_NULL_SEND | /* send null packets when required */
-	       HDMI0_GC_SEND | /* send general control packets */
-	       HDMI0_GC_CONT); /* send general control packets every frame */
-
-	/* TODO: HDMI0_AUDIO_INFO_UPDATE */
-	WREG32(HDMI0_INFOFRAME_CONTROL0 + offset,
-	       HDMI0_AVI_INFO_SEND | /* enable AVI info frames */
-	       HDMI0_AVI_INFO_CONT | /* send AVI info frames every frame/field */
-	       HDMI0_AUDIO_INFO_SEND | /* enable audio info frames (frames won't be set until audio is enabled) */
-	       HDMI0_AUDIO_INFO_CONT); /* send audio info frames every frame/field */
-
-	WREG32(HDMI0_INFOFRAME_CONTROL1 + offset,
-	       HDMI0_AVI_INFO_LINE(2) | /* anything other than 0 */
-	       HDMI0_AUDIO_INFO_LINE(2)); /* anything other than 0 */
-
-	WREG32(HDMI0_GC + offset, 0); /* unset HDMI0_GC_AVMUTE */
+	WREG32_P(HDMI0_AUDIO_PACKET_CONTROL + offset,
+		 HDMI0_AUDIO_SAMPLE_SEND | /* send audio packets */
+		 HDMI0_AUDIO_DELAY_EN(1) | /* default audio delay */
+		 HDMI0_AUDIO_PACKETS_PER_LINE(3) | /* should be suffient for all audio modes and small enough for all hblanks */
+		 HDMI0_60958_CS_UPDATE, /* allow 60958 channel status fields to be updated */
+		 ~(HDMI0_AUDIO_SAMPLE_SEND |
+		   HDMI0_AUDIO_DELAY_EN_MASK |
+		   HDMI0_AUDIO_PACKETS_PER_LINE_MASK |
+		   HDMI0_60958_CS_UPDATE));
+
+	/* DCE 3.0 uses register that's normally for CRC_CONTROL */
+	acr_ctl = ASIC_IS_DCE3(rdev) ? DCE3_HDMI0_ACR_PACKET_CONTROL :
+				       HDMI0_ACR_PACKET_CONTROL;
+	WREG32_P(acr_ctl + offset,
+		 HDMI0_ACR_SOURCE | /* select SW CTS value - XXX verify that hw CTS works on all families */
+		 HDMI0_ACR_AUTO_SEND, /* allow hw to sent ACR packets when required */
+		 ~(HDMI0_ACR_SOURCE |
+		   HDMI0_ACR_AUTO_SEND));
+
+	WREG32_OR(HDMI0_VBI_PACKET_CONTROL + offset,
+		  HDMI0_NULL_SEND | /* send null packets when required */
+		  HDMI0_GC_SEND | /* send general control packets */
+		  HDMI0_GC_CONT); /* send general control packets every frame */
+
+	WREG32_OR(HDMI0_INFOFRAME_CONTROL0 + offset,
+		  HDMI0_AVI_INFO_SEND | /* enable AVI info frames */
+		  HDMI0_AVI_INFO_CONT | /* send AVI info frames every frame/field */
+		  HDMI0_AUDIO_INFO_SEND | /* enable audio info frames (frames won't be set until audio is enabled) */
+		  HDMI0_AUDIO_INFO_UPDATE); /* required for audio info values to be updated */
+
+	WREG32_P(HDMI0_INFOFRAME_CONTROL1 + offset,
+		 HDMI0_AVI_INFO_LINE(2) | /* anything other than 0 */
+		 HDMI0_AUDIO_INFO_LINE(2), /* anything other than 0 */
+		 ~(HDMI0_AVI_INFO_LINE_MASK |
+		   HDMI0_AUDIO_INFO_LINE_MASK));
+
+	WREG32_AND(HDMI0_GC + offset,
+		   ~HDMI0_GC_AVMUTE); /* unset HDMI0_GC_AVMUTE */
 
 	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
 	if (err < 0) {
@@ -523,22 +413,45 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 	}
 
 	r600_hdmi_update_avi_infoframe(encoder, buffer, sizeof(buffer));
+
+	/* fglrx duplicates INFOFRAME_CONTROL0 & INFOFRAME_CONTROL1 ops here */
+
+	WREG32_AND(HDMI0_GENERIC_PACKET_CONTROL + offset,
+		   ~(HDMI0_GENERIC0_SEND |
+		     HDMI0_GENERIC0_CONT |
+		     HDMI0_GENERIC0_UPDATE |
+		     HDMI0_GENERIC1_SEND |
+		     HDMI0_GENERIC1_CONT |
+		     HDMI0_GENERIC0_LINE_MASK |
+		     HDMI0_GENERIC1_LINE_MASK));
+
 	r600_hdmi_update_ACR(encoder, mode->clock);
 
+	WREG32_P(HDMI0_60958_0 + offset,
+		 HDMI0_60958_CS_CHANNEL_NUMBER_L(1),
+		 ~(HDMI0_60958_CS_CHANNEL_NUMBER_L_MASK |
+		   HDMI0_60958_CS_CLOCK_ACCURACY_MASK));
+
+	WREG32_P(HDMI0_60958_1 + offset,
+		 HDMI0_60958_CS_CHANNEL_NUMBER_R(2),
+		 ~HDMI0_60958_CS_CHANNEL_NUMBER_R_MASK);
+
 	/* it's unknown what these bits do excatly, but it's indeed quite useful for debugging */
 	WREG32(HDMI0_RAMP_CONTROL0 + offset, 0x00FFFFFF);
 	WREG32(HDMI0_RAMP_CONTROL1 + offset, 0x007FFFFF);
 	WREG32(HDMI0_RAMP_CONTROL2 + offset, 0x00000001);
 	WREG32(HDMI0_RAMP_CONTROL3 + offset, 0x00000001);
 
-	r600_hdmi_audio_workaround(encoder);
-
 	/* enable audio after to setting up hw */
 	r600_audio_enable(rdev, dig->afmt->pin, true);
 }
 
-/*
- * update settings with current parameters from audio engine
+/**
+ * r600_hdmi_update_audio_settings - Update audio infoframe
+ *
+ * @encoder: drm encoder
+ *
+ * Gets info about current audio stream and updates audio infoframe.
  */
 void r600_hdmi_update_audio_settings(struct drm_encoder *encoder)
 {
@@ -550,7 +463,7 @@ void r600_hdmi_update_audio_settings(struct drm_encoder *encoder)
 	uint8_t buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AUDIO_INFOFRAME_SIZE];
 	struct hdmi_audio_infoframe frame;
 	uint32_t offset;
-	uint32_t iec;
+	uint32_t value;
 	ssize_t err;
 
 	if (!dig->afmt || !dig->afmt->enabled)
@@ -563,60 +476,6 @@ void r600_hdmi_update_audio_settings(struct drm_encoder *encoder)
 	DRM_DEBUG("0x%02X IEC60958 status bits and 0x%02X category code\n",
 		  (int)audio.status_bits, (int)audio.category_code);
 
-	iec = 0;
-	if (audio.status_bits & AUDIO_STATUS_PROFESSIONAL)
-		iec |= 1 << 0;
-	if (audio.status_bits & AUDIO_STATUS_NONAUDIO)
-		iec |= 1 << 1;
-	if (audio.status_bits & AUDIO_STATUS_COPYRIGHT)
-		iec |= 1 << 2;
-	if (audio.status_bits & AUDIO_STATUS_EMPHASIS)
-		iec |= 1 << 3;
-
-	iec |= HDMI0_60958_CS_CATEGORY_CODE(audio.category_code);
-
-	switch (audio.rate) {
-	case 32000:
-		iec |= HDMI0_60958_CS_SAMPLING_FREQUENCY(0x3);
-		break;
-	case 44100:
-		iec |= HDMI0_60958_CS_SAMPLING_FREQUENCY(0x0);
-		break;
-	case 48000:
-		iec |= HDMI0_60958_CS_SAMPLING_FREQUENCY(0x2);
-		break;
-	case 88200:
-		iec |= HDMI0_60958_CS_SAMPLING_FREQUENCY(0x8);
-		break;
-	case 96000:
-		iec |= HDMI0_60958_CS_SAMPLING_FREQUENCY(0xa);
-		break;
-	case 176400:
-		iec |= HDMI0_60958_CS_SAMPLING_FREQUENCY(0xc);
-		break;
-	case 192000:
-		iec |= HDMI0_60958_CS_SAMPLING_FREQUENCY(0xe);
-		break;
-	}
-
-	WREG32(HDMI0_60958_0 + offset, iec);
-
-	iec = 0;
-	switch (audio.bits_per_sample) {
-	case 16:
-		iec |= HDMI0_60958_CS_WORD_LENGTH(0x2);
-		break;
-	case 20:
-		iec |= HDMI0_60958_CS_WORD_LENGTH(0x3);
-		break;
-	case 24:
-		iec |= HDMI0_60958_CS_WORD_LENGTH(0xb);
-		break;
-	}
-	if (audio.status_bits & AUDIO_STATUS_V)
-		iec |= 0x5 << 16;
-	WREG32_P(HDMI0_60958_1 + offset, iec, ~0x5000f);
-
 	err = hdmi_audio_infoframe_init(&frame);
 	if (err < 0) {
 		DRM_ERROR("failed to setup audio infoframe\n");
@@ -631,8 +490,22 @@ void r600_hdmi_update_audio_settings(struct drm_encoder *encoder)
 		return;
 	}
 
+	value = RREG32(HDMI0_AUDIO_PACKET_CONTROL + offset);
+	if (value & HDMI0_AUDIO_TEST_EN)
+		WREG32(HDMI0_AUDIO_PACKET_CONTROL + offset,
+		       value & ~HDMI0_AUDIO_TEST_EN);
+
+	WREG32_OR(HDMI0_CONTROL + offset,
+		  HDMI0_ERROR_ACK);
+
+	WREG32_AND(HDMI0_INFOFRAME_CONTROL0 + offset,
+		   ~HDMI0_AUDIO_INFO_SOURCE);
+
 	r600_hdmi_update_audio_infoframe(encoder, buffer, sizeof(buffer));
-	r600_hdmi_audio_workaround(encoder);
+
+	WREG32_OR(HDMI0_INFOFRAME_CONTROL0 + offset,
+		  HDMI0_AUDIO_INFO_CONT |
+		  HDMI0_AUDIO_INFO_UPDATE);
 }
 
 /*
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index 37455f65107..f94e7a9afe7 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1029,15 +1029,18 @@
 #define HDMI0_AUDIO_PACKET_CONTROL   0x7408
 #       define HDMI0_AUDIO_SAMPLE_SEND  (1 << 0)
 #       define HDMI0_AUDIO_DELAY_EN(x)  (((x) & 3) << 4)
+#       define HDMI0_AUDIO_DELAY_EN_MASK	(3 << 4)
 #       define HDMI0_AUDIO_SEND_MAX_PACKETS  (1 << 8)
 #       define HDMI0_AUDIO_TEST_EN         (1 << 12)
 #       define HDMI0_AUDIO_PACKETS_PER_LINE(x)  (((x) & 0x1f) << 16)
+#       define HDMI0_AUDIO_PACKETS_PER_LINE_MASK	(0x1f << 16)
 #       define HDMI0_AUDIO_CHANNEL_SWAP    (1 << 24)
 #       define HDMI0_60958_CS_UPDATE       (1 << 26)
 #       define HDMI0_AZ_FORMAT_WTRIG_MASK  (1 << 28)
 #       define HDMI0_AZ_FORMAT_WTRIG_ACK   (1 << 29)
 #define HDMI0_AUDIO_CRC_CONTROL      0x740c
 #       define HDMI0_AUDIO_CRC_EN    (1 << 0)
+#define DCE3_HDMI0_ACR_PACKET_CONTROL	0x740c
 #define HDMI0_VBI_PACKET_CONTROL     0x7410
 #       define HDMI0_NULL_SEND       (1 << 0)
 #       define HDMI0_GC_SEND         (1 << 4)
@@ -1054,7 +1057,9 @@
 #       define HDMI0_MPEG_INFO_UPDATE  (1 << 10)
 #define HDMI0_INFOFRAME_CONTROL1     0x7418
 #       define HDMI0_AVI_INFO_LINE(x)  (((x) & 0x3f) << 0)
+#       define HDMI0_AVI_INFO_LINE_MASK		(0x3f << 0)
 #       define HDMI0_AUDIO_INFO_LINE(x)  (((x) & 0x3f) << 8)
+#       define HDMI0_AUDIO_INFO_LINE_MASK	(0x3f << 8)
 #       define HDMI0_MPEG_INFO_LINE(x)  (((x) & 0x3f) << 16)
 #define HDMI0_GENERIC_PACKET_CONTROL 0x741c
 #       define HDMI0_GENERIC0_SEND   (1 << 0)
@@ -1063,7 +1068,9 @@
 #       define HDMI0_GENERIC1_SEND   (1 << 4)
 #       define HDMI0_GENERIC1_CONT   (1 << 5)
 #       define HDMI0_GENERIC0_LINE(x)  (((x) & 0x3f) << 16)
+#       define HDMI0_GENERIC0_LINE_MASK		(0x3f << 16)
 #       define HDMI0_GENERIC1_LINE(x)  (((x) & 0x3f) << 24)
+#       define HDMI0_GENERIC1_LINE_MASK		(0x3f << 24)
 #define HDMI0_GC                     0x7428
 #       define HDMI0_GC_AVMUTE       (1 << 0)
 #define HDMI0_AVI_INFO0              0x7454
@@ -1119,16 +1126,22 @@
 #define HDMI0_GENERIC1_6             0x74a8
 #define HDMI0_ACR_32_0               0x74ac
 #       define HDMI0_ACR_CTS_32(x)   (((x) & 0xfffff) << 12)
+#       define HDMI0_ACR_CTS_32_MASK		(0xfffff << 12)
 #define HDMI0_ACR_32_1               0x74b0
 #       define HDMI0_ACR_N_32(x)   (((x) & 0xfffff) << 0)
+#       define HDMI0_ACR_N_32_MASK		(0xfffff << 0)
 #define HDMI0_ACR_44_0               0x74b4
 #       define HDMI0_ACR_CTS_44(x)   (((x) & 0xfffff) << 12)
+#       define HDMI0_ACR_CTS_44_MASK		(0xfffff << 12)
 #define HDMI0_ACR_44_1               0x74b8
 #       define HDMI0_ACR_N_44(x)   (((x) & 0xfffff) << 0)
+#       define HDMI0_ACR_N_44_MASK		(0xfffff << 0)
 #define HDMI0_ACR_48_0               0x74bc
 #       define HDMI0_ACR_CTS_48(x)   (((x) & 0xfffff) << 12)
+#       define HDMI0_ACR_CTS_48_MASK		(0xfffff << 12)
 #define HDMI0_ACR_48_1               0x74c0
 #       define HDMI0_ACR_N_48(x)   (((x) & 0xfffff) << 0)
+#       define HDMI0_ACR_N_48_MASK		(0xfffff << 0)
 #define HDMI0_ACR_STATUS_0           0x74c4
 #define HDMI0_ACR_STATUS_1           0x74c8
 #define HDMI0_AUDIO_INFO0            0x74cc
@@ -1148,14 +1161,17 @@
 #       define HDMI0_60958_CS_CATEGORY_CODE(x)      (((x) & 0xff) << 8)
 #       define HDMI0_60958_CS_SOURCE_NUMBER(x)      (((x) & 0xf) << 16)
 #       define HDMI0_60958_CS_CHANNEL_NUMBER_L(x)   (((x) & 0xf) << 20)
+#       define HDMI0_60958_CS_CHANNEL_NUMBER_L_MASK	(0xf << 20)
 #       define HDMI0_60958_CS_SAMPLING_FREQUENCY(x) (((x) & 0xf) << 24)
 #       define HDMI0_60958_CS_CLOCK_ACCURACY(x)     (((x) & 3) << 28)
+#       define HDMI0_60958_CS_CLOCK_ACCURACY_MASK	(3 << 28)
 #define HDMI0_60958_1                0x74d8
 #       define HDMI0_60958_CS_WORD_LENGTH(x)        (((x) & 0xf) << 0)
 #       define HDMI0_60958_CS_ORIGINAL_SAMPLING_FREQUENCY(x)   (((x) & 0xf) << 4)
 #       define HDMI0_60958_CS_VALID_L(x)   (((x) & 1) << 16)
 #       define HDMI0_60958_CS_VALID_R(x)   (((x) & 1) << 18)
 #       define HDMI0_60958_CS_CHANNEL_NUMBER_R(x)   (((x) & 0xf) << 20)
+#       define HDMI0_60958_CS_CHANNEL_NUMBER_R_MASK	(0xf << 20)
 #define HDMI0_ACR_PACKET_CONTROL     0x74dc
 #       define HDMI0_ACR_SEND        (1 << 0)
 #       define HDMI0_ACR_CONT        (1 << 1)
@@ -1166,6 +1182,7 @@
 #       define HDMI0_ACR_48          3
 #       define HDMI0_ACR_SOURCE      (1 << 8) /* 0 - hw; 1 - cts value */
 #       define HDMI0_ACR_AUTO_SEND   (1 << 12)
+#define DCE3_HDMI0_AUDIO_CRC_CONTROL	0x74dc
 #define HDMI0_RAMP_CONTROL0          0x74e0
 #       define HDMI0_RAMP_MAX_COUNT(x)   (((x) & 0xffffff) << 0)
 #define HDMI0_RAMP_CONTROL1          0x74e4
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 8149e7cf430..60c47f82912 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -100,6 +100,9 @@ extern int radeon_dpm;
 extern int radeon_aspm;
 extern int radeon_runtime_pm;
 extern int radeon_hard_reset;
+extern int radeon_vm_size;
+extern int radeon_vm_block_size;
+extern int radeon_deep_color;
 
 /*
  * Copy from radeon_drv.h so we don't have to include both and have conflicting
@@ -446,6 +449,7 @@ struct radeon_bo_va {
 
 	/* protected by vm mutex */
 	struct list_head		vm_list;
+	struct list_head		vm_status;
 
 	/* constant after initialization */
 	struct radeon_vm		*vm;
@@ -676,14 +680,15 @@ void radeon_doorbell_free(struct radeon_device *rdev, u32 doorbell);
  * IRQS.
  */
 
-struct radeon_unpin_work {
-	struct work_struct work;
-	struct radeon_device *rdev;
-	int crtc_id;
-	struct radeon_fence *fence;
+struct radeon_flip_work {
+	struct work_struct		flip_work;
+	struct work_struct		unpin_work;
+	struct radeon_device		*rdev;
+	int				crtc_id;
+	uint64_t			base;
 	struct drm_pending_vblank_event *event;
-	struct radeon_bo *old_rbo;
-	u64 new_crtc_base;
+	struct radeon_bo		*old_rbo;
+	struct radeon_fence		*fence;
 };
 
 struct r500_irq_stat_regs {
@@ -745,10 +750,6 @@ union radeon_irq_stat_regs {
 	struct cik_irq_stat_regs cik;
 };
 
-#define RADEON_MAX_HPD_PINS 7
-#define RADEON_MAX_CRTCS 6
-#define RADEON_MAX_AFMT_BLOCKS 7
-
 struct radeon_irq {
 	bool				installed;
 	spinlock_t			lock;
@@ -835,13 +836,8 @@ struct radeon_mec {
 /* maximum number of VMIDs */
 #define RADEON_NUM_VM	16
 
-/* defines number of bits in page table versus page directory,
- * a page is 4KB so we have 12 bits offset, 9 bits in the page
- * table and the remaining 19 bits are in the page directory */
-#define RADEON_VM_BLOCK_SIZE   9
-
 /* number of entries in page table */
-#define RADEON_VM_PTE_COUNT (1 << RADEON_VM_BLOCK_SIZE)
+#define RADEON_VM_PTE_COUNT (1 << radeon_vm_block_size)
 
 /* PTBs (Page Table Blocks) need to be aligned to 32K */
 #define RADEON_VM_PTB_ALIGN_SIZE   32768
@@ -854,6 +850,15 @@ struct radeon_mec {
 #define R600_PTE_READABLE	(1 << 5)
 #define R600_PTE_WRITEABLE	(1 << 6)
 
+/* PTE (Page Table Entry) fragment field for different page sizes */
+#define R600_PTE_FRAG_4KB	(0 << 7)
+#define R600_PTE_FRAG_64KB	(4 << 7)
+#define R600_PTE_FRAG_256KB	(6 << 7)
+
+/* flags used for GART page table entries on R600+ */
+#define R600_PTE_GART	( R600_PTE_VALID | R600_PTE_SYSTEM | R600_PTE_SNOOPED \
+			| R600_PTE_READABLE | R600_PTE_WRITEABLE)
+
 struct radeon_vm_pt {
 	struct radeon_bo		*bo;
 	uint64_t			addr;
@@ -863,6 +868,9 @@ struct radeon_vm {
 	struct list_head		va;
 	unsigned			id;
 
+	/* BOs freed, but not yet updated in the PT */
+	struct list_head		freed;
+
 	/* contains the page directory */
 	struct radeon_bo		*page_directory;
 	uint64_t			pd_gpu_addr;
@@ -871,6 +879,8 @@ struct radeon_vm {
 	/* array of page tables, one for each page directory entry */
 	struct radeon_vm_pt		*page_tables;
 
+	struct radeon_bo_va		*ib_bo_va;
+
 	struct mutex			mutex;
 	/* last fence for cs using this vm */
 	struct radeon_fence		*fence;
@@ -986,8 +996,8 @@ struct radeon_cs_reloc {
 	struct radeon_bo		*robj;
 	struct ttm_validate_buffer	tv;
 	uint64_t			gpu_offset;
-	unsigned			domain;
-	unsigned			alt_domain;
+	unsigned			prefered_domains;
+	unsigned			allowed_domains;
 	uint32_t			tiling_flags;
 	uint32_t			handle;
 };
@@ -1771,7 +1781,8 @@ struct radeon_asic {
 	/* gart */
 	struct {
 		void (*tlb_flush)(struct radeon_device *rdev);
-		int (*set_page)(struct radeon_device *rdev, int i, uint64_t addr);
+		void (*set_page)(struct radeon_device *rdev, unsigned i,
+				 uint64_t addr);
 	} gart;
 	struct {
 		int (*init)(struct radeon_device *rdev);
@@ -1883,9 +1894,8 @@ struct radeon_asic {
 	} dpm;
 	/* pageflipping */
 	struct {
-		void (*pre_page_flip)(struct radeon_device *rdev, int crtc);
-		u32 (*page_flip)(struct radeon_device *rdev, int crtc, u64 crtc_base);
-		void (*post_page_flip)(struct radeon_device *rdev, int crtc);
+		void (*page_flip)(struct radeon_device *rdev, int crtc, u64 crtc_base);
+		bool (*page_flip_pending)(struct radeon_device *rdev, int crtc);
 	} pflip;
 };
 
@@ -1924,6 +1934,7 @@ struct r600_asic {
 	unsigned		tiling_group_size;
 	unsigned		tile_config;
 	unsigned		backend_map;
+	unsigned		active_simds;
 };
 
 struct rv770_asic {
@@ -1949,6 +1960,7 @@ struct rv770_asic {
 	unsigned		tiling_group_size;
 	unsigned		tile_config;
 	unsigned		backend_map;
+	unsigned		active_simds;
 };
 
 struct evergreen_asic {
@@ -1975,6 +1987,7 @@ struct evergreen_asic {
 	unsigned tiling_group_size;
 	unsigned tile_config;
 	unsigned backend_map;
+	unsigned active_simds;
 };
 
 struct cayman_asic {
@@ -2013,6 +2026,7 @@ struct cayman_asic {
 	unsigned multi_gpu_tile_size;
 
 	unsigned tile_config;
+	unsigned active_simds;
 };
 
 struct si_asic {
@@ -2043,6 +2057,7 @@ struct si_asic {
 
 	unsigned tile_config;
 	uint32_t tile_mode_array[32];
+	uint32_t active_cus;
 };
 
 struct cik_asic {
@@ -2074,6 +2089,7 @@ struct cik_asic {
 	unsigned tile_config;
 	uint32_t tile_mode_array[32];
 	uint32_t macrotile_mode_array[16];
+	uint32_t active_cus;
 };
 
 union radeon_asic_config {
@@ -2745,9 +2761,8 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_pm_finish(rdev) (rdev)->asic->pm.finish((rdev))
 #define radeon_pm_init_profile(rdev) (rdev)->asic->pm.init_profile((rdev))
 #define radeon_pm_get_dynpm_state(rdev) (rdev)->asic->pm.get_dynpm_state((rdev))
-#define radeon_pre_page_flip(rdev, crtc) (rdev)->asic->pflip.pre_page_flip((rdev), (crtc))
 #define radeon_page_flip(rdev, crtc, base) (rdev)->asic->pflip.page_flip((rdev), (crtc), (base))
-#define radeon_post_page_flip(rdev, crtc) (rdev)->asic->pflip.post_page_flip((rdev), (crtc))
+#define radeon_page_flip_pending(rdev, crtc) (rdev)->asic->pflip.page_flip_pending((rdev), (crtc))
 #define radeon_wait_for_vblank(rdev, crtc) (rdev)->asic->display.wait_for_vblank((rdev), (crtc))
 #define radeon_mc_wait_for_idle(rdev) (rdev)->asic->mc_wait_for_idle((rdev))
 #define radeon_get_xclk(rdev) (rdev)->asic->get_xclk((rdev))
@@ -2823,9 +2838,10 @@ void radeon_vm_fence(struct radeon_device *rdev,
 uint64_t radeon_vm_map_gart(struct radeon_device *rdev, uint64_t addr);
 int radeon_vm_update_page_directory(struct radeon_device *rdev,
 				    struct radeon_vm *vm);
+int radeon_vm_clear_freed(struct radeon_device *rdev,
+			  struct radeon_vm *vm);
 int radeon_vm_bo_update(struct radeon_device *rdev,
-			struct radeon_vm *vm,
-			struct radeon_bo *bo,
+			struct radeon_bo_va *bo_va,
 			struct ttm_mem_reg *mem);
 void radeon_vm_bo_invalidate(struct radeon_device *rdev,
 			     struct radeon_bo *bo);
@@ -2838,8 +2854,8 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 			  struct radeon_bo_va *bo_va,
 			  uint64_t offset,
 			  uint32_t flags);
-int radeon_vm_bo_rmv(struct radeon_device *rdev,
-		     struct radeon_bo_va *bo_va);
+void radeon_vm_bo_rmv(struct radeon_device *rdev,
+		      struct radeon_bo_va *bo_va);
 
 /* audio */
 void r600_audio_update_hdmi(struct work_struct *work);
diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c
index 42433344cb1..a9297b2c352 100644
--- a/drivers/gpu/drm/radeon/radeon_agp.c
+++ b/drivers/gpu/drm/radeon/radeon_agp.c
@@ -117,9 +117,6 @@ static struct radeon_agpmode_quirk radeon_agpmode_quirk_list[] = {
 	/* ATI Host Bridge / RV280 [M9+] Needs AGPMode 1 (phoronix forum) */
 	{ PCI_VENDOR_ID_ATI, 0xcbb2, PCI_VENDOR_ID_ATI, 0x5c61,
 		PCI_VENDOR_ID_SONY, 0x8175, 1},
-	/* HP Host Bridge / R300 [FireGL X1] Needs AGPMode 2 (fdo #7770) */
-	{ PCI_VENDOR_ID_HP, 0x122e, PCI_VENDOR_ID_ATI, 0x4e47,
-		PCI_VENDOR_ID_ATI, 0x0152, 2},
 	{ 0, 0, 0, 0, 0, 0, 0 },
 };
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index e5f0177bea1..34b9aa9e3c0 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -248,9 +248,8 @@ static struct radeon_asic r100_asic = {
 		.set_clock_gating = &radeon_legacy_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &r100_pre_page_flip,
 		.page_flip = &r100_page_flip,
-		.post_page_flip = &r100_post_page_flip,
+		.page_flip_pending = &r100_page_flip_pending,
 	},
 };
 
@@ -315,9 +314,8 @@ static struct radeon_asic r200_asic = {
 		.set_clock_gating = &radeon_legacy_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &r100_pre_page_flip,
 		.page_flip = &r100_page_flip,
-		.post_page_flip = &r100_post_page_flip,
+		.page_flip_pending = &r100_page_flip_pending,
 	},
 };
 
@@ -396,9 +394,8 @@ static struct radeon_asic r300_asic = {
 		.set_clock_gating = &radeon_legacy_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &r100_pre_page_flip,
 		.page_flip = &r100_page_flip,
-		.post_page_flip = &r100_post_page_flip,
+		.page_flip_pending = &r100_page_flip_pending,
 	},
 };
 
@@ -463,9 +460,8 @@ static struct radeon_asic r300_asic_pcie = {
 		.set_clock_gating = &radeon_legacy_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &r100_pre_page_flip,
 		.page_flip = &r100_page_flip,
-		.post_page_flip = &r100_post_page_flip,
+		.page_flip_pending = &r100_page_flip_pending,
 	},
 };
 
@@ -530,9 +526,8 @@ static struct radeon_asic r420_asic = {
 		.set_clock_gating = &radeon_atom_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &r100_pre_page_flip,
 		.page_flip = &r100_page_flip,
-		.post_page_flip = &r100_post_page_flip,
+		.page_flip_pending = &r100_page_flip_pending,
 	},
 };
 
@@ -597,9 +592,8 @@ static struct radeon_asic rs400_asic = {
 		.set_clock_gating = &radeon_legacy_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &r100_pre_page_flip,
 		.page_flip = &r100_page_flip,
-		.post_page_flip = &r100_post_page_flip,
+		.page_flip_pending = &r100_page_flip_pending,
 	},
 };
 
@@ -666,9 +660,8 @@ static struct radeon_asic rs600_asic = {
 		.set_clock_gating = &radeon_atom_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &rs600_pre_page_flip,
 		.page_flip = &rs600_page_flip,
-		.post_page_flip = &rs600_post_page_flip,
+		.page_flip_pending = &rs600_page_flip_pending,
 	},
 };
 
@@ -735,9 +728,8 @@ static struct radeon_asic rs690_asic = {
 		.set_clock_gating = &radeon_atom_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &rs600_pre_page_flip,
 		.page_flip = &rs600_page_flip,
-		.post_page_flip = &rs600_post_page_flip,
+		.page_flip_pending = &rs600_page_flip_pending,
 	},
 };
 
@@ -802,9 +794,8 @@ static struct radeon_asic rv515_asic = {
 		.set_clock_gating = &radeon_atom_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &rs600_pre_page_flip,
 		.page_flip = &rs600_page_flip,
-		.post_page_flip = &rs600_post_page_flip,
+		.page_flip_pending = &rs600_page_flip_pending,
 	},
 };
 
@@ -869,9 +860,8 @@ static struct radeon_asic r520_asic = {
 		.set_clock_gating = &radeon_atom_set_clock_gating,
 	},
 	.pflip = {
-		.pre_page_flip = &rs600_pre_page_flip,
 		.page_flip = &rs600_page_flip,
-		.post_page_flip = &rs600_post_page_flip,
+		.page_flip_pending = &rs600_page_flip_pending,
 	},
 };
 
@@ -968,9 +958,8 @@ static struct radeon_asic r600_asic = {
 		.get_temperature = &rv6xx_get_temp,
 	},
 	.pflip = {
-		.pre_page_flip = &rs600_pre_page_flip,
 		.page_flip = &rs600_page_flip,
-		.post_page_flip = &rs600_post_page_flip,
+		.page_flip_pending = &rs600_page_flip_pending,
 	},
 };
 
@@ -1059,9 +1048,8 @@ static struct radeon_asic rv6xx_asic = {
 		.force_performance_level = &rv6xx_dpm_force_performance_level,
 	},
 	.pflip = {
-		.pre_page_flip = &rs600_pre_page_flip,
 		.page_flip = &rs600_page_flip,
-		.post_page_flip = &rs600_post_page_flip,
+		.page_flip_pending = &rs600_page_flip_pending,
 	},
 };
 
@@ -1150,9 +1138,8 @@ static struct radeon_asic rs780_asic = {
 		.force_performance_level = &rs780_dpm_force_performance_level,
 	},
 	.pflip = {
-		.pre_page_flip = &rs600_pre_page_flip,
 		.page_flip = &rs600_page_flip,
-		.post_page_flip = &rs600_post_page_flip,
+		.page_flip_pending = &rs600_page_flip_pending,
 	},
 };
 
@@ -1201,7 +1188,7 @@ static struct radeon_asic rv770_asic = {
 		.set_backlight_level = &atombios_set_backlight_level,
 		.get_backlight_level = &atombios_get_backlight_level,
 		.hdmi_enable = &r600_hdmi_enable,
-		.hdmi_setmode = &r600_hdmi_setmode,
+		.hdmi_setmode = &dce3_1_hdmi_setmode,
 	},
 	.copy = {
 		.blit = &r600_copy_cpdma,
@@ -1256,9 +1243,8 @@ static struct radeon_asic rv770_asic = {
 		.vblank_too_short = &rv770_dpm_vblank_too_short,
 	},
 	.pflip = {
-		.pre_page_flip = &rs600_pre_page_flip,
 		.page_flip = &rv770_page_flip,
-		.post_page_flip = &rs600_post_page_flip,
+		.page_flip_pending = &rv770_page_flip_pending,
 	},
 };
 
@@ -1375,9 +1361,8 @@ static struct radeon_asic evergreen_asic = {
 		.vblank_too_short = &cypress_dpm_vblank_too_short,
 	},
 	.pflip = {
-		.pre_page_flip = &evergreen_pre_page_flip,
 		.page_flip = &evergreen_page_flip,
-		.post_page_flip = &evergreen_post_page_flip,
+		.page_flip_pending = &evergreen_page_flip_pending,
 	},
 };
 
@@ -1467,9 +1452,8 @@ static struct radeon_asic sumo_asic = {
 		.force_performance_level = &sumo_dpm_force_performance_level,
 	},
 	.pflip = {
-		.pre_page_flip = &evergreen_pre_page_flip,
 		.page_flip = &evergreen_page_flip,
-		.post_page_flip = &evergreen_post_page_flip,
+		.page_flip_pending = &evergreen_page_flip_pending,
 	},
 };
 
@@ -1560,9 +1544,8 @@ static struct radeon_asic btc_asic = {
 		.vblank_too_short = &btc_dpm_vblank_too_short,
 	},
 	.pflip = {
-		.pre_page_flip = &evergreen_pre_page_flip,
 		.page_flip = &evergreen_page_flip,
-		.post_page_flip = &evergreen_post_page_flip,
+		.page_flip_pending = &evergreen_page_flip_pending,
 	},
 };
 
@@ -1704,9 +1687,8 @@ static struct radeon_asic cayman_asic = {
 		.vblank_too_short = &ni_dpm_vblank_too_short,
 	},
 	.pflip = {
-		.pre_page_flip = &evergreen_pre_page_flip,
 		.page_flip = &evergreen_page_flip,
-		.post_page_flip = &evergreen_post_page_flip,
+		.page_flip_pending = &evergreen_page_flip_pending,
 	},
 };
 
@@ -1805,9 +1787,8 @@ static struct radeon_asic trinity_asic = {
 		.enable_bapm = &trinity_dpm_enable_bapm,
 	},
 	.pflip = {
-		.pre_page_flip = &evergreen_pre_page_flip,
 		.page_flip = &evergreen_page_flip,
-		.post_page_flip = &evergreen_post_page_flip,
+		.page_flip_pending = &evergreen_page_flip_pending,
 	},
 };
 
@@ -1936,9 +1917,8 @@ static struct radeon_asic si_asic = {
 		.vblank_too_short = &ni_dpm_vblank_too_short,
 	},
 	.pflip = {
-		.pre_page_flip = &evergreen_pre_page_flip,
 		.page_flip = &evergreen_page_flip,
-		.post_page_flip = &evergreen_post_page_flip,
+		.page_flip_pending = &evergreen_page_flip_pending,
 	},
 };
 
@@ -2049,8 +2029,8 @@ static struct radeon_asic ci_asic = {
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &cik_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.copy = &cik_copy_cpdma,
-		.copy_ring_index = RADEON_RING_TYPE_GFX_INDEX,
+		.copy = &cik_copy_dma,
+		.copy_ring_index = R600_RING_TYPE_DMA_INDEX,
 	},
 	.surface = {
 		.set_reg = r600_set_surface_reg,
@@ -2099,9 +2079,8 @@ static struct radeon_asic ci_asic = {
 		.powergate_uvd = &ci_dpm_powergate_uvd,
 	},
 	.pflip = {
-		.pre_page_flip = &evergreen_pre_page_flip,
 		.page_flip = &evergreen_page_flip,
-		.post_page_flip = &evergreen_post_page_flip,
+		.page_flip_pending = &evergreen_page_flip_pending,
 	},
 };
 
@@ -2204,9 +2183,8 @@ static struct radeon_asic kv_asic = {
 		.enable_bapm = &kv_dpm_enable_bapm,
 	},
 	.pflip = {
-		.pre_page_flip = &evergreen_pre_page_flip,
 		.page_flip = &evergreen_page_flip,
-		.post_page_flip = &evergreen_post_page_flip,
+		.page_flip_pending = &evergreen_page_flip_pending,
 	},
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 3d55a3a39e8..01e7c0ad8f0 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -67,7 +67,8 @@ bool r100_gpu_is_lockup(struct radeon_device *rdev, struct radeon_ring *cp);
 int r100_asic_reset(struct radeon_device *rdev);
 u32 r100_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void r100_pci_gart_tlb_flush(struct radeon_device *rdev);
-int r100_pci_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr);
+void r100_pci_gart_set_page(struct radeon_device *rdev, unsigned i,
+			    uint64_t addr);
 void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring);
 int r100_irq_set(struct radeon_device *rdev);
 int r100_irq_process(struct radeon_device *rdev);
@@ -135,9 +136,9 @@ extern void r100_pm_prepare(struct radeon_device *rdev);
 extern void r100_pm_finish(struct radeon_device *rdev);
 extern void r100_pm_init_profile(struct radeon_device *rdev);
 extern void r100_pm_get_dynpm_state(struct radeon_device *rdev);
-extern void r100_pre_page_flip(struct radeon_device *rdev, int crtc);
-extern u32 r100_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
-extern void r100_post_page_flip(struct radeon_device *rdev, int crtc);
+extern void r100_page_flip(struct radeon_device *rdev, int crtc,
+			   u64 crtc_base);
+extern bool r100_page_flip_pending(struct radeon_device *rdev, int crtc);
 extern void r100_wait_for_vblank(struct radeon_device *rdev, int crtc);
 extern int r100_mc_wait_for_idle(struct radeon_device *rdev);
 
@@ -171,7 +172,8 @@ extern void r300_fence_ring_emit(struct radeon_device *rdev,
 				struct radeon_fence *fence);
 extern int r300_cs_parse(struct radeon_cs_parser *p);
 extern void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev);
-extern int rv370_pcie_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr);
+extern void rv370_pcie_gart_set_page(struct radeon_device *rdev, unsigned i,
+				     uint64_t addr);
 extern void rv370_set_pcie_lanes(struct radeon_device *rdev, int lanes);
 extern int rv370_get_pcie_lanes(struct radeon_device *rdev);
 extern void r300_set_reg_safe(struct radeon_device *rdev);
@@ -206,7 +208,8 @@ extern void rs400_fini(struct radeon_device *rdev);
 extern int rs400_suspend(struct radeon_device *rdev);
 extern int rs400_resume(struct radeon_device *rdev);
 void rs400_gart_tlb_flush(struct radeon_device *rdev);
-int rs400_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr);
+void rs400_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t addr);
 uint32_t rs400_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs400_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 int rs400_gart_init(struct radeon_device *rdev);
@@ -229,7 +232,8 @@ int rs600_irq_process(struct radeon_device *rdev);
 void rs600_irq_disable(struct radeon_device *rdev);
 u32 rs600_get_vblank_counter(struct radeon_device *rdev, int crtc);
 void rs600_gart_tlb_flush(struct radeon_device *rdev);
-int rs600_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr);
+void rs600_gart_set_page(struct radeon_device *rdev, unsigned i,
+			 uint64_t addr);
 uint32_t rs600_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rs600_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 void rs600_bandwidth_update(struct radeon_device *rdev);
@@ -241,9 +245,9 @@ void rs600_hpd_set_polarity(struct radeon_device *rdev,
 extern void rs600_pm_misc(struct radeon_device *rdev);
 extern void rs600_pm_prepare(struct radeon_device *rdev);
 extern void rs600_pm_finish(struct radeon_device *rdev);
-extern void rs600_pre_page_flip(struct radeon_device *rdev, int crtc);
-extern u32 rs600_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
-extern void rs600_post_page_flip(struct radeon_device *rdev, int crtc);
+extern void rs600_page_flip(struct radeon_device *rdev, int crtc,
+			    u64 crtc_base);
+extern bool rs600_page_flip_pending(struct radeon_device *rdev, int crtc);
 void rs600_set_safe_registers(struct radeon_device *rdev);
 extern void avivo_wait_for_vblank(struct radeon_device *rdev, int crtc);
 extern int rs600_mc_wait_for_idle(struct radeon_device *rdev);
@@ -387,6 +391,11 @@ void r600_rlc_stop(struct radeon_device *rdev);
 int r600_audio_init(struct radeon_device *rdev);
 struct r600_audio_pin r600_audio_status(struct radeon_device *rdev);
 void r600_audio_fini(struct radeon_device *rdev);
+void r600_audio_set_dto(struct drm_encoder *encoder, u32 clock);
+void r600_hdmi_update_avi_infoframe(struct drm_encoder *encoder, void *buffer,
+				    size_t size);
+void r600_hdmi_update_ACR(struct drm_encoder *encoder, uint32_t clock);
+void r600_hdmi_audio_workaround(struct drm_encoder *encoder);
 int r600_hdmi_buffer_status_changed(struct drm_encoder *encoder);
 void r600_hdmi_update_audio_settings(struct drm_encoder *encoder);
 void r600_hdmi_enable(struct drm_encoder *encoder, bool enable);
@@ -447,7 +456,8 @@ void rv770_fini(struct radeon_device *rdev);
 int rv770_suspend(struct radeon_device *rdev);
 int rv770_resume(struct radeon_device *rdev);
 void rv770_pm_misc(struct radeon_device *rdev);
-u32 rv770_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
+void rv770_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
+bool rv770_page_flip_pending(struct radeon_device *rdev, int crtc);
 void r700_vram_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
 void r700_cp_stop(struct radeon_device *rdev);
 void r700_cp_fini(struct radeon_device *rdev);
@@ -458,6 +468,8 @@ int rv770_copy_dma(struct radeon_device *rdev,
 u32 rv770_get_xclk(struct radeon_device *rdev);
 int rv770_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
 int rv770_get_temp(struct radeon_device *rdev);
+/* hdmi */
+void dce3_1_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mode);
 /* rv7xx pm */
 int rv770_dpm_init(struct radeon_device *rdev);
 int rv770_dpm_enable(struct radeon_device *rdev);
@@ -513,9 +525,9 @@ extern void sumo_pm_init_profile(struct radeon_device *rdev);
 extern void btc_pm_init_profile(struct radeon_device *rdev);
 int sumo_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
 int evergreen_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk);
-extern void evergreen_pre_page_flip(struct radeon_device *rdev, int crtc);
-extern u32 evergreen_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
-extern void evergreen_post_page_flip(struct radeon_device *rdev, int crtc);
+extern void evergreen_page_flip(struct radeon_device *rdev, int crtc,
+				u64 crtc_base);
+extern bool evergreen_page_flip_pending(struct radeon_device *rdev, int crtc);
 extern void dce4_wait_for_vblank(struct radeon_device *rdev, int crtc);
 void evergreen_disable_interrupt_state(struct radeon_device *rdev);
 int evergreen_mc_wait_for_idle(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 30844814c25..173f378428a 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -1227,11 +1227,19 @@ bool radeon_atom_get_clock_info(struct drm_device *dev)
 			rdev->clock.default_dispclk =
 				le32_to_cpu(firmware_info->info_21.ulDefaultDispEngineClkFreq);
 			if (rdev->clock.default_dispclk == 0) {
-				if (ASIC_IS_DCE5(rdev))
+				if (ASIC_IS_DCE6(rdev))
+					rdev->clock.default_dispclk = 60000; /* 600 Mhz */
+				else if (ASIC_IS_DCE5(rdev))
 					rdev->clock.default_dispclk = 54000; /* 540 Mhz */
 				else
 					rdev->clock.default_dispclk = 60000; /* 600 Mhz */
 			}
+			/* set a reasonable default for DP */
+			if (ASIC_IS_DCE6(rdev) && (rdev->clock.default_dispclk < 53900)) {
+				DRM_INFO("Changing default dispclk from %dMhz to 600Mhz\n",
+					 rdev->clock.default_dispclk / 100);
+				rdev->clock.default_dispclk = 60000;
+			}
 			rdev->clock.dp_extclk =
 				le16_to_cpu(firmware_info->info_21.usUniphyDPModeExtClkFreq);
 			rdev->clock.current_dispclk = rdev->clock.default_dispclk;
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 9ab30976287..6a03624fada 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -626,7 +626,7 @@ static bool radeon_acpi_vfct_bios(struct radeon_device *rdev)
 	    vhdr->DeviceID != rdev->pdev->device) {
 		DRM_INFO("ACPI VFCT table is not for this card\n");
 		goto out_unmap;
-	};
+	}
 
 	if (vfct->VBIOSImageOffset + sizeof(VFCT_IMAGE_HEADER) + vhdr->ImageLength > tbl_size) {
 		DRM_ERROR("ACPI VFCT image truncated\n");
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index ea50e0ae7bf..44831197e82 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -48,6 +48,7 @@ void radeon_connector_hotplug(struct drm_connector *connector)
 	radeon_hpd_set_polarity(rdev, radeon_connector->hpd.hpd);
 
 	/* if the connector is already off, don't turn it back on */
+	/* FIXME: This access isn't protected by any locks. */
 	if (connector->dpms != DRM_MODE_DPMS_ON)
 		return;
 
@@ -100,6 +101,7 @@ int radeon_get_monitor_bpc(struct drm_connector *connector)
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *dig_connector;
 	int bpc = 8;
+	int mode_clock, max_tmds_clock;
 
 	switch (connector->connector_type) {
 	case DRM_MODE_CONNECTOR_DVII:
@@ -145,6 +147,64 @@ int radeon_get_monitor_bpc(struct drm_connector *connector)
 		}
 		break;
 	}
+
+	if (drm_detect_hdmi_monitor(radeon_connector->edid)) {
+		/* hdmi deep color only implemented on DCE4+ */
+		if ((bpc > 8) && !ASIC_IS_DCE4(rdev)) {
+			DRM_DEBUG("%s: HDMI deep color %d bpc unsupported. Using 8 bpc.\n",
+					  connector->name, bpc);
+			bpc = 8;
+		}
+
+		/*
+		 * Pre DCE-8 hw can't handle > 12 bpc, and more than 12 bpc doesn't make
+		 * much sense without support for > 12 bpc framebuffers. RGB 4:4:4 at
+		 * 12 bpc is always supported on hdmi deep color sinks, as this is
+		 * required by the HDMI-1.3 spec. Clamp to a safe 12 bpc maximum.
+		 */
+		if (bpc > 12) {
+			DRM_DEBUG("%s: HDMI deep color %d bpc unsupported. Using 12 bpc.\n",
+					  connector->name, bpc);
+			bpc = 12;
+		}
+
+		/* Any defined maximum tmds clock limit we must not exceed? */
+		if (connector->max_tmds_clock > 0) {
+			/* mode_clock is clock in kHz for mode to be modeset on this connector */
+			mode_clock = radeon_connector->pixelclock_for_modeset;
+
+			/* Maximum allowable input clock in kHz */
+			max_tmds_clock = connector->max_tmds_clock * 1000;
+
+			DRM_DEBUG("%s: hdmi mode dotclock %d kHz, max tmds input clock %d kHz.\n",
+					  connector->name, mode_clock, max_tmds_clock);
+
+			/* Check if bpc is within clock limit. Try to degrade gracefully otherwise */
+			if ((bpc == 12) && (mode_clock * 3/2 > max_tmds_clock)) {
+				if ((connector->display_info.edid_hdmi_dc_modes & DRM_EDID_HDMI_DC_30) &&
+					(mode_clock * 5/4 <= max_tmds_clock))
+					bpc = 10;
+				else
+					bpc = 8;
+
+				DRM_DEBUG("%s: HDMI deep color 12 bpc exceeds max tmds clock. Using %d bpc.\n",
+						  connector->name, bpc);
+			}
+
+			if ((bpc == 10) && (mode_clock * 5/4 > max_tmds_clock)) {
+				bpc = 8;
+				DRM_DEBUG("%s: HDMI deep color 10 bpc exceeds max tmds clock. Using %d bpc.\n",
+						  connector->name, bpc);
+			}
+		}
+	}
+
+	if ((radeon_deep_color == 0) && (bpc > 8))
+		bpc = 8;
+
+	DRM_DEBUG("%s: Display bpc=%d, returned bpc=%d\n",
+			  connector->name, connector->display_info.bpc, bpc);
+
 	return bpc;
 }
 
@@ -260,13 +320,17 @@ radeon_connector_analog_encoder_conflict_solve(struct drm_connector *connector,
 					continue;
 
 				if (priority == true) {
-					DRM_DEBUG_KMS("1: conflicting encoders switching off %s\n", drm_get_connector_name(conflict));
-					DRM_DEBUG_KMS("in favor of %s\n", drm_get_connector_name(connector));
+					DRM_DEBUG_KMS("1: conflicting encoders switching off %s\n",
+						      conflict->name);
+					DRM_DEBUG_KMS("in favor of %s\n",
+						      connector->name);
 					conflict->status = connector_status_disconnected;
 					radeon_connector_update_scratch_regs(conflict, connector_status_disconnected);
 				} else {
-					DRM_DEBUG_KMS("2: conflicting encoders switching off %s\n", drm_get_connector_name(connector));
-					DRM_DEBUG_KMS("in favor of %s\n", drm_get_connector_name(conflict));
+					DRM_DEBUG_KMS("2: conflicting encoders switching off %s\n",
+						      connector->name);
+					DRM_DEBUG_KMS("in favor of %s\n",
+						      conflict->name);
 					current_status = connector_status_disconnected;
 				}
 				break;
@@ -787,7 +851,7 @@ radeon_vga_detect(struct drm_connector *connector, bool force)
 
 		if (!radeon_connector->edid) {
 			DRM_ERROR("%s: probed a monitor but no|invalid EDID\n",
-					drm_get_connector_name(connector));
+					connector->name);
 			ret = connector_status_connected;
 		} else {
 			radeon_connector->use_digital = !!(radeon_connector->edid->input & DRM_EDID_INPUT_DIGITAL);
@@ -1010,12 +1074,13 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 
 		if (!radeon_connector->edid) {
 			DRM_ERROR("%s: probed a monitor but no|invalid EDID\n",
-					drm_get_connector_name(connector));
+					connector->name);
 			/* rs690 seems to have a problem with connectors not existing and always
 			 * return a block of 0's. If we see this just stop polling on this output */
 			if ((rdev->family == CHIP_RS690 || rdev->family == CHIP_RS740) && radeon_connector->base.null_edid_counter) {
 				ret = connector_status_disconnected;
-				DRM_ERROR("%s: detected RS690 floating bus bug, stopping ddc detect\n", drm_get_connector_name(connector));
+				DRM_ERROR("%s: detected RS690 floating bus bug, stopping ddc detect\n",
+					  connector->name);
 				radeon_connector->ddc_bus = NULL;
 			} else {
 				ret = connector_status_connected;
@@ -1226,17 +1291,15 @@ static int radeon_dvi_mode_valid(struct drm_connector *connector,
 		    (radeon_connector->connector_object_id == CONNECTOR_OBJECT_ID_DUAL_LINK_DVI_D) ||
 		    (radeon_connector->connector_object_id == CONNECTOR_OBJECT_ID_HDMI_TYPE_B))
 			return MODE_OK;
-		else if (radeon_connector->connector_object_id == CONNECTOR_OBJECT_ID_HDMI_TYPE_A) {
-			if (ASIC_IS_DCE6(rdev)) {
-				/* HDMI 1.3+ supports max clock of 340 Mhz */
-				if (mode->clock > 340000)
-					return MODE_CLOCK_HIGH;
-				else
-					return MODE_OK;
-			} else
+		else if (ASIC_IS_DCE6(rdev) && drm_detect_hdmi_monitor(radeon_connector->edid)) {
+			/* HDMI 1.3+ supports max clock of 340 Mhz */
+			if (mode->clock > 340000)
 				return MODE_CLOCK_HIGH;
-		} else
+			else
+				return MODE_OK;
+		} else {
 			return MODE_CLOCK_HIGH;
+		}
 	}
 
 	/* check against the max pixel clock */
@@ -1387,7 +1450,7 @@ bool radeon_connector_is_dp12_capable(struct drm_connector *connector)
 	struct radeon_device *rdev = dev->dev_private;
 
 	if (ASIC_IS_DCE5(rdev) &&
-	    (rdev->clock.dp_extclk >= 53900) &&
+	    (rdev->clock.default_dispclk >= 53900) &&
 	    radeon_connector_encoder_is_hbr2(connector)) {
 		return true;
 	}
@@ -1487,6 +1550,8 @@ out:
 static int radeon_dp_mode_valid(struct drm_connector *connector,
 				  struct drm_display_mode *mode)
 {
+	struct drm_device *dev = connector->dev;
+	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct radeon_connector_atom_dig *radeon_dig_connector = radeon_connector->con_priv;
 
@@ -1517,14 +1582,23 @@ static int radeon_dp_mode_valid(struct drm_connector *connector,
 					return MODE_PANEL;
 			}
 		}
-		return MODE_OK;
 	} else {
 		if ((radeon_dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) ||
-		    (radeon_dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP))
+		    (radeon_dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) {
 			return radeon_dp_mode_valid_helper(connector, mode);
-		else
-			return MODE_OK;
+		} else {
+			if (ASIC_IS_DCE6(rdev) && drm_detect_hdmi_monitor(radeon_connector->edid)) {
+				/* HDMI 1.3+ supports max clock of 340 Mhz */
+				if (mode->clock > 340000)
+					return MODE_CLOCK_HIGH;
+			} else {
+				if (mode->clock > 165000)
+					return MODE_CLOCK_HIGH;
+			}
+		}
 	}
+
+	return MODE_OK;
 }
 
 static const struct drm_connector_helper_funcs radeon_dp_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 41ecf8a6061..ae763f60c8a 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -140,10 +140,10 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 		if (p->ring == R600_RING_TYPE_UVD_INDEX &&
 		    (i == 0 || drm_pci_device_is_agp(p->rdev->ddev))) {
 			/* TODO: is this still needed for NI+ ? */
-			p->relocs[i].domain =
+			p->relocs[i].prefered_domains =
 				RADEON_GEM_DOMAIN_VRAM;
 
-			p->relocs[i].alt_domain =
+			p->relocs[i].allowed_domains =
 				RADEON_GEM_DOMAIN_VRAM;
 
 			/* prioritize this over any other relocation */
@@ -158,10 +158,10 @@ static int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 				return -EINVAL;
 			}
 
-			p->relocs[i].domain = domain;
+			p->relocs[i].prefered_domains = domain;
 			if (domain == RADEON_GEM_DOMAIN_VRAM)
 				domain |= RADEON_GEM_DOMAIN_GTT;
-			p->relocs[i].alt_domain = domain;
+			p->relocs[i].allowed_domains = domain;
 		}
 
 		p->relocs[i].tv.bo = &p->relocs[i].robj->tbo;
@@ -461,13 +461,23 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p,
 				   struct radeon_vm *vm)
 {
 	struct radeon_device *rdev = p->rdev;
+	struct radeon_bo_va *bo_va;
 	int i, r;
 
 	r = radeon_vm_update_page_directory(rdev, vm);
 	if (r)
 		return r;
 
-	r = radeon_vm_bo_update(rdev, vm, rdev->ring_tmp_bo.bo,
+	r = radeon_vm_clear_freed(rdev, vm);
+	if (r)
+		return r;
+
+	if (vm->ib_bo_va == NULL) {
+		DRM_ERROR("Tmp BO not in VM!\n");
+		return -EINVAL;
+	}
+
+	r = radeon_vm_bo_update(rdev, vm->ib_bo_va,
 				&rdev->ring_tmp_bo.bo->tbo.mem);
 	if (r)
 		return r;
@@ -480,7 +490,13 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p,
 			continue;
 
 		bo = p->relocs[i].robj;
-		r = radeon_vm_bo_update(rdev, vm, bo, &bo->tbo.mem);
+		bo_va = radeon_vm_bo_find(vm, bo);
+		if (bo_va == NULL) {
+			dev_err(rdev->dev, "bo %p not in vm %p\n", bo, vm);
+			return -EINVAL;
+		}
+
+		r = radeon_vm_bo_update(rdev, bo_va, &bo->tbo.mem);
 		if (r)
 			return r;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 2cd144c378d..697add2cd4e 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1052,6 +1052,43 @@ static void radeon_check_arguments(struct radeon_device *rdev)
 		radeon_agpmode = 0;
 		break;
 	}
+
+	if (!radeon_check_pot_argument(radeon_vm_size)) {
+		dev_warn(rdev->dev, "VM size (%d) must be a power of 2\n",
+			 radeon_vm_size);
+		radeon_vm_size = 4;
+	}
+
+	if (radeon_vm_size < 1) {
+		dev_warn(rdev->dev, "VM size (%d) to small, min is 1GB\n",
+			 radeon_vm_size);
+		radeon_vm_size = 4;
+	}
+
+       /*
+        * Max GPUVM size for Cayman, SI and CI are 40 bits.
+        */
+	if (radeon_vm_size > 1024) {
+		dev_warn(rdev->dev, "VM size (%d) too large, max is 1TB\n",
+			 radeon_vm_size);
+		radeon_vm_size = 4;
+	}
+
+	/* defines number of bits in page table versus page directory,
+	 * a page is 4KB so we have 12 bits offset, minimum 9 bits in the
+	 * page table and the remaining bits are in the page directory */
+	if (radeon_vm_block_size < 9) {
+		dev_warn(rdev->dev, "VM page table size (%d) too small\n",
+			 radeon_vm_block_size);
+		radeon_vm_block_size = 9;
+	}
+
+	if (radeon_vm_block_size > 24 ||
+	    (radeon_vm_size * 1024) < (1ull << radeon_vm_block_size)) {
+		dev_warn(rdev->dev, "VM page table size (%d) too large\n",
+			 radeon_vm_block_size);
+		radeon_vm_block_size = 9;
+	}
 }
 
 /**
@@ -1126,12 +1163,13 @@ static void radeon_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 static bool radeon_switcheroo_can_switch(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	bool can_switch;
 
-	spin_lock(&dev->count_lock);
-	can_switch = (dev->open_count == 0);
-	spin_unlock(&dev->count_lock);
-	return can_switch;
+	/*
+	 * FIXME: open_count is protected by drm_global_mutex but that would lead to
+	 * locking inversion with the driver load path. And the access here is
+	 * completely racy anyway. So don't bother with locking for now.
+	 */
+	return dev->open_count == 0;
 }
 
 static const struct vga_switcheroo_client_ops radeon_switcheroo_ops = {
@@ -1196,17 +1234,16 @@ int radeon_device_init(struct radeon_device *rdev,
 	if (r)
 		return r;
 
+	radeon_check_arguments(rdev);
 	/* Adjust VM size here.
-	 * Currently set to 4GB ((1 << 20) 4k pages).
-	 * Max GPUVM size for cayman and SI is 40 bits.
+	 * Max GPUVM size for cayman+ is 40 bits.
 	 */
-	rdev->vm_manager.max_pfn = 1 << 20;
+	rdev->vm_manager.max_pfn = radeon_vm_size << 18;
 
 	/* Set asic functions */
 	r = radeon_asic_init(rdev);
 	if (r)
 		return r;
-	radeon_check_arguments(rdev);
 
 	/* all of the newer IGP chips have an internal gart
 	 * However some rs4xx report as AGP, so remove that here.
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 356b733caaf..bf25061c8ac 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -66,7 +66,8 @@ static void avivo_crtc_load_lut(struct drm_crtc *crtc)
 			     (radeon_crtc->lut_b[i] << 0));
 	}
 
-	WREG32(AVIVO_D1GRPH_LUT_SEL + radeon_crtc->crtc_offset, radeon_crtc->crtc_id);
+	/* Only change bit 0 of LUT_SEL, other bits are set elsewhere */
+	WREG32_P(AVIVO_D1GRPH_LUT_SEL + radeon_crtc->crtc_offset, radeon_crtc->crtc_id, ~1);
 }
 
 static void dce4_crtc_load_lut(struct drm_crtc *crtc)
@@ -249,16 +250,21 @@ static void radeon_crtc_destroy(struct drm_crtc *crtc)
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 
 	drm_crtc_cleanup(crtc);
+	destroy_workqueue(radeon_crtc->flip_queue);
 	kfree(radeon_crtc);
 }
 
-/*
- * Handle unpin events outside the interrupt handler proper.
+/**
+ * radeon_unpin_work_func - unpin old buffer object
+ *
+ * @__work - kernel work item
+ *
+ * Unpin the old frame buffer object outside of the interrupt handler
  */
 static void radeon_unpin_work_func(struct work_struct *__work)
 {
-	struct radeon_unpin_work *work =
-		container_of(__work, struct radeon_unpin_work, work);
+	struct radeon_flip_work *work =
+		container_of(__work, struct radeon_flip_work, unpin_work);
 	int r;
 
 	/* unpin of the old buffer */
@@ -276,10 +282,9 @@ static void radeon_unpin_work_func(struct work_struct *__work)
 	kfree(work);
 }
 
-void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
+void radeon_crtc_handle_vblank(struct radeon_device *rdev, int crtc_id)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
-	struct radeon_unpin_work *work;
 	unsigned long flags;
 	u32 update_pending;
 	int vpos, hpos;
@@ -289,24 +294,16 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
 		return;
 
 	spin_lock_irqsave(&rdev->ddev->event_lock, flags);
-	work = radeon_crtc->unpin_work;
-	if (work == NULL ||
-	    (work->fence && !radeon_fence_signaled(work->fence))) {
+	if (radeon_crtc->flip_status != RADEON_FLIP_SUBMITTED) {
+		DRM_DEBUG_DRIVER("radeon_crtc->flip_status = %d != "
+				 "RADEON_FLIP_SUBMITTED(%d)\n",
+				 radeon_crtc->flip_status,
+				 RADEON_FLIP_SUBMITTED);
 		spin_unlock_irqrestore(&rdev->ddev->event_lock, flags);
 		return;
 	}
-	/* New pageflip, or just completion of a previous one? */
-	if (!radeon_crtc->deferred_flip_completion) {
-		/* do the flip (mmio) */
-		update_pending = radeon_page_flip(rdev, crtc_id, work->new_crtc_base);
-	} else {
-		/* This is just a completion of a flip queued in crtc
-		 * at last invocation. Make sure we go directly to
-		 * completion routine.
-		 */
-		update_pending = 0;
-		radeon_crtc->deferred_flip_completion = 0;
-	}
+
+	update_pending = radeon_page_flip_pending(rdev, crtc_id);
 
 	/* Has the pageflip already completed in crtc, or is it certain
 	 * to complete in this vblank?
@@ -324,19 +321,43 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
 		 */
 		update_pending = 0;
 	}
-	if (update_pending) {
-		/* crtc didn't flip in this target vblank interval,
-		 * but flip is pending in crtc. It will complete it
-		 * in next vblank interval, so complete the flip at
-		 * next vblank irq.
-		 */
-		radeon_crtc->deferred_flip_completion = 1;
+	spin_unlock_irqrestore(&rdev->ddev->event_lock, flags);
+	if (!update_pending)
+		radeon_crtc_handle_flip(rdev, crtc_id);
+}
+
+/**
+ * radeon_crtc_handle_flip - page flip completed
+ *
+ * @rdev: radeon device pointer
+ * @crtc_id: crtc number this event is for
+ *
+ * Called when we are sure that a page flip for this crtc is completed.
+ */
+void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
+{
+	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
+	struct radeon_flip_work *work;
+	unsigned long flags;
+
+	/* this can happen at init */
+	if (radeon_crtc == NULL)
+		return;
+
+	spin_lock_irqsave(&rdev->ddev->event_lock, flags);
+	work = radeon_crtc->flip_work;
+	if (radeon_crtc->flip_status != RADEON_FLIP_SUBMITTED) {
+		DRM_DEBUG_DRIVER("radeon_crtc->flip_status = %d != "
+				 "RADEON_FLIP_SUBMITTED(%d)\n",
+				 radeon_crtc->flip_status,
+				 RADEON_FLIP_SUBMITTED);
 		spin_unlock_irqrestore(&rdev->ddev->event_lock, flags);
 		return;
 	}
 
-	/* Pageflip (will be) certainly completed in this vblank. Clean up. */
-	radeon_crtc->unpin_work = NULL;
+	/* Pageflip completed. Clean up. */
+	radeon_crtc->flip_status = RADEON_FLIP_NONE;
+	radeon_crtc->flip_work = NULL;
 
 	/* wakeup userspace */
 	if (work->event)
@@ -345,9 +366,59 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
 	spin_unlock_irqrestore(&rdev->ddev->event_lock, flags);
 
 	drm_vblank_put(rdev->ddev, radeon_crtc->crtc_id);
-	radeon_fence_unref(&work->fence);
-	radeon_post_page_flip(work->rdev, work->crtc_id);
-	schedule_work(&work->work);
+	radeon_irq_kms_pflip_irq_put(rdev, work->crtc_id);
+	queue_work(radeon_crtc->flip_queue, &work->unpin_work);
+}
+
+/**
+ * radeon_flip_work_func - page flip framebuffer
+ *
+ * @work - kernel work item
+ *
+ * Wait for the buffer object to become idle and do the actual page flip
+ */
+static void radeon_flip_work_func(struct work_struct *__work)
+{
+	struct radeon_flip_work *work =
+		container_of(__work, struct radeon_flip_work, flip_work);
+	struct radeon_device *rdev = work->rdev;
+	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[work->crtc_id];
+
+	struct drm_crtc *crtc = &radeon_crtc->base;
+	unsigned long flags;
+	int r;
+
+        down_read(&rdev->exclusive_lock);
+	if (work->fence) {
+		r = radeon_fence_wait(work->fence, false);
+		if (r == -EDEADLK) {
+			up_read(&rdev->exclusive_lock);
+			r = radeon_gpu_reset(rdev);
+			down_read(&rdev->exclusive_lock);
+		}
+		if (r)
+			DRM_ERROR("failed to wait on page flip fence (%d)!\n", r);
+
+		/* We continue with the page flip even if we failed to wait on
+		 * the fence, otherwise the DRM core and userspace will be
+		 * confused about which BO the CRTC is scanning out
+		 */
+
+		radeon_fence_unref(&work->fence);
+	}
+
+	/* We borrow the event spin lock for protecting flip_status */
+	spin_lock_irqsave(&crtc->dev->event_lock, flags);
+
+	/* set the proper interrupt */
+	radeon_irq_kms_pflip_irq_get(rdev, radeon_crtc->crtc_id);
+
+	/* do the flip (mmio) */
+	radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base);
+
+	radeon_crtc->flip_status = RADEON_FLIP_SUBMITTED;
+	spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+	up_read(&rdev->exclusive_lock);
 }
 
 static int radeon_crtc_page_flip(struct drm_crtc *crtc,
@@ -361,69 +432,61 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	struct radeon_framebuffer *old_radeon_fb;
 	struct radeon_framebuffer *new_radeon_fb;
 	struct drm_gem_object *obj;
-	struct radeon_bo *rbo;
-	struct radeon_unpin_work *work;
+	struct radeon_flip_work *work;
+	struct radeon_bo *new_rbo;
+	uint32_t tiling_flags, pitch_pixels;
+	uint64_t base;
 	unsigned long flags;
-	u32 tiling_flags, pitch_pixels;
-	u64 base;
 	int r;
 
 	work = kzalloc(sizeof *work, GFP_KERNEL);
 	if (work == NULL)
 		return -ENOMEM;
 
-	work->event = event;
+	INIT_WORK(&work->flip_work, radeon_flip_work_func);
+	INIT_WORK(&work->unpin_work, radeon_unpin_work_func);
+
 	work->rdev = rdev;
 	work->crtc_id = radeon_crtc->crtc_id;
-	old_radeon_fb = to_radeon_framebuffer(crtc->primary->fb);
-	new_radeon_fb = to_radeon_framebuffer(fb);
+	work->event = event;
+
 	/* schedule unpin of the old buffer */
+	old_radeon_fb = to_radeon_framebuffer(crtc->primary->fb);
 	obj = old_radeon_fb->obj;
+
 	/* take a reference to the old object */
 	drm_gem_object_reference(obj);
-	rbo = gem_to_radeon_bo(obj);
-	work->old_rbo = rbo;
-	obj = new_radeon_fb->obj;
-	rbo = gem_to_radeon_bo(obj);
-
-	spin_lock(&rbo->tbo.bdev->fence_lock);
-	if (rbo->tbo.sync_obj)
-		work->fence = radeon_fence_ref(rbo->tbo.sync_obj);
-	spin_unlock(&rbo->tbo.bdev->fence_lock);
+	work->old_rbo = gem_to_radeon_bo(obj);
 
-	INIT_WORK(&work->work, radeon_unpin_work_func);
+	new_radeon_fb = to_radeon_framebuffer(fb);
+	obj = new_radeon_fb->obj;
+	new_rbo = gem_to_radeon_bo(obj);
 
-	/* We borrow the event spin lock for protecting unpin_work */
-	spin_lock_irqsave(&dev->event_lock, flags);
-	if (radeon_crtc->unpin_work) {
-		DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
-		r = -EBUSY;
-		goto unlock_free;
-	}
-	radeon_crtc->unpin_work = work;
-	radeon_crtc->deferred_flip_completion = 0;
-	spin_unlock_irqrestore(&dev->event_lock, flags);
+	spin_lock(&new_rbo->tbo.bdev->fence_lock);
+	if (new_rbo->tbo.sync_obj)
+		work->fence = radeon_fence_ref(new_rbo->tbo.sync_obj);
+	spin_unlock(&new_rbo->tbo.bdev->fence_lock);
 
 	/* pin the new buffer */
-	DRM_DEBUG_DRIVER("flip-ioctl() cur_fbo = %p, cur_bbo = %p\n",
-			 work->old_rbo, rbo);
+	DRM_DEBUG_DRIVER("flip-ioctl() cur_rbo = %p, new_rbo = %p\n",
+			 work->old_rbo, new_rbo);
 
-	r = radeon_bo_reserve(rbo, false);
+	r = radeon_bo_reserve(new_rbo, false);
 	if (unlikely(r != 0)) {
 		DRM_ERROR("failed to reserve new rbo buffer before flip\n");
-		goto pflip_cleanup;
+		goto cleanup;
 	}
 	/* Only 27 bit offset for legacy CRTC */
-	r = radeon_bo_pin_restricted(rbo, RADEON_GEM_DOMAIN_VRAM,
+	r = radeon_bo_pin_restricted(new_rbo, RADEON_GEM_DOMAIN_VRAM,
 				     ASIC_IS_AVIVO(rdev) ? 0 : 1 << 27, &base);
 	if (unlikely(r != 0)) {
-		radeon_bo_unreserve(rbo);
+		radeon_bo_unreserve(new_rbo);
 		r = -EINVAL;
 		DRM_ERROR("failed to pin new rbo buffer before flip\n");
-		goto pflip_cleanup;
+		goto cleanup;
 	}
-	radeon_bo_get_tiling_flags(rbo, &tiling_flags, NULL);
-	radeon_bo_unreserve(rbo);
+	radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL);
+	radeon_bo_unreserve(new_rbo);
 
 	if (!ASIC_IS_AVIVO(rdev)) {
 		/* crtc offset is from display base addr not FB location */
@@ -460,41 +523,49 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 		}
 		base &= ~7;
 	}
+	work->base = base;
 
-	spin_lock_irqsave(&dev->event_lock, flags);
-	work->new_crtc_base = base;
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-
-	/* update crtc fb */
-	crtc->primary->fb = fb;
-
-	r = drm_vblank_get(dev, radeon_crtc->crtc_id);
+	r = drm_vblank_get(crtc->dev, radeon_crtc->crtc_id);
 	if (r) {
 		DRM_ERROR("failed to get vblank before flip\n");
-		goto pflip_cleanup1;
+		goto pflip_cleanup;
 	}
 
-	/* set the proper interrupt */
-	radeon_pre_page_flip(rdev, radeon_crtc->crtc_id);
+	/* We borrow the event spin lock for protecting flip_work */
+	spin_lock_irqsave(&crtc->dev->event_lock, flags);
+
+	if (radeon_crtc->flip_status != RADEON_FLIP_NONE) {
+		DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+		r = -EBUSY;
+		goto vblank_cleanup;
+	}
+	radeon_crtc->flip_status = RADEON_FLIP_PENDING;
+	radeon_crtc->flip_work = work;
 
+	/* update crtc fb */
+	crtc->primary->fb = fb;
+
+	spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
+	queue_work(radeon_crtc->flip_queue, &work->flip_work);
 	return 0;
 
-pflip_cleanup1:
-	if (unlikely(radeon_bo_reserve(rbo, false) != 0)) {
+vblank_cleanup:
+	drm_vblank_put(crtc->dev, radeon_crtc->crtc_id);
+
+pflip_cleanup:
+	if (unlikely(radeon_bo_reserve(new_rbo, false) != 0)) {
 		DRM_ERROR("failed to reserve new rbo in error path\n");
-		goto pflip_cleanup;
+		goto cleanup;
 	}
-	if (unlikely(radeon_bo_unpin(rbo) != 0)) {
+	if (unlikely(radeon_bo_unpin(new_rbo) != 0)) {
 		DRM_ERROR("failed to unpin new rbo in error path\n");
 	}
-	radeon_bo_unreserve(rbo);
+	radeon_bo_unreserve(new_rbo);
 
-pflip_cleanup:
-	spin_lock_irqsave(&dev->event_lock, flags);
-	radeon_crtc->unpin_work = NULL;
-unlock_free:
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-	drm_gem_object_unreference_unlocked(old_radeon_fb->obj);
+cleanup:
+	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
 	radeon_fence_unref(&work->fence);
 	kfree(work);
 
@@ -568,6 +639,7 @@ static void radeon_crtc_init(struct drm_device *dev, int index)
 
 	drm_mode_crtc_set_gamma_size(&radeon_crtc->base, 256);
 	radeon_crtc->crtc_id = index;
+	radeon_crtc->flip_queue = create_singlethread_workqueue("radeon-crtc");
 	rdev->mode_info.crtcs[index] = radeon_crtc;
 
 	if (rdev->family >= CHIP_BONAIRE) {
@@ -661,7 +733,7 @@ static void radeon_print_display_setup(struct drm_device *dev)
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		radeon_connector = to_radeon_connector(connector);
 		DRM_INFO("Connector %d:\n", i);
-		DRM_INFO("  %s\n", drm_get_connector_name(connector));
+		DRM_INFO("  %s\n", connector->name);
 		if (radeon_connector->hpd.hpd != RADEON_HPD_NONE)
 			DRM_INFO("  %s\n", hpd_names[radeon_connector->hpd.hpd]);
 		if (radeon_connector->ddc_bus) {
@@ -757,6 +829,10 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector)
 	struct radeon_device *rdev = dev->dev_private;
 	int ret = 0;
 
+	/* don't leak the edid if we already fetched it in detect() */
+	if (radeon_connector->edid)
+		goto got_edid;
+
 	/* on hw with routers, select right port */
 	if (radeon_connector->router.ddc_valid)
 		radeon_router_select_ddc_port(radeon_connector);
@@ -795,6 +871,7 @@ int radeon_ddc_get_modes(struct radeon_connector *radeon_connector)
 			radeon_connector->edid = radeon_bios_get_hardcoded_edid(rdev);
 	}
 	if (radeon_connector->edid) {
+got_edid:
 		drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
 		ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid);
 		drm_edid_to_eld(&radeon_connector->base, radeon_connector->edid);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index c00a2f58518..e9e36108424 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -81,9 +81,10 @@
  *   2.37.0 - allow GS ring setup on r6xx/r7xx
  *   2.38.0 - RADEON_GEM_OP (GET_INITIAL_DOMAIN, SET_INITIAL_DOMAIN),
  *            CIK: 1D and linear tiling modes contain valid PIPE_CONFIG
+ *   2.39.0 - Add INFO query for number of active CUs
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	38
+#define KMS_DRIVER_MINOR	39
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
@@ -172,6 +173,9 @@ int radeon_dpm = -1;
 int radeon_aspm = -1;
 int radeon_runtime_pm = -1;
 int radeon_hard_reset = 0;
+int radeon_vm_size = 4;
+int radeon_vm_block_size = 9;
+int radeon_deep_color = 0;
 
 MODULE_PARM_DESC(no_wb, "Disable AGP writeback for scratch registers");
 module_param_named(no_wb, radeon_no_wb, int, 0444);
@@ -239,6 +243,15 @@ module_param_named(runpm, radeon_runtime_pm, int, 0444);
 MODULE_PARM_DESC(hard_reset, "PCI config reset (1 = force enable, 0 = disable (default))");
 module_param_named(hard_reset, radeon_hard_reset, int, 0444);
 
+MODULE_PARM_DESC(vm_size, "VM address space size in gigabytes (default 4GB)");
+module_param_named(vm_size, radeon_vm_size, int, 0444);
+
+MODULE_PARM_DESC(vm_block_size, "VM page table size in bits (default 9)");
+module_param_named(vm_block_size, radeon_vm_block_size, int, 0444);
+
+MODULE_PARM_DESC(deep_color, "Deep Color support (1 = enable, 0 = disable (default))");
+module_param_named(deep_color, radeon_deep_color, int, 0444);
+
 static struct pci_device_id pciidlist[] = {
 	radeon_PCI_IDS
 };
@@ -519,7 +532,6 @@ static struct drm_driver kms_driver = {
 	    DRIVER_USE_AGP |
 	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM |
 	    DRIVER_PRIME | DRIVER_RENDER,
-	.dev_priv_size = 0,
 	.load = radeon_driver_load_kms,
 	.open = radeon_driver_open_kms,
 	.preclose = radeon_driver_preclose_kms,
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index a77b1c13ea4..913787085df 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -819,15 +819,35 @@ static int radeon_debugfs_fence_info(struct seq_file *m, void *data)
 	return 0;
 }
 
+/**
+ * radeon_debugfs_gpu_reset - manually trigger a gpu reset
+ *
+ * Manually trigger a gpu reset at the next fence wait.
+ */
+static int radeon_debugfs_gpu_reset(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = (struct drm_info_node *) m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct radeon_device *rdev = dev->dev_private;
+
+	down_read(&rdev->exclusive_lock);
+	seq_printf(m, "%d\n", rdev->needs_reset);
+	rdev->needs_reset = true;
+	up_read(&rdev->exclusive_lock);
+
+	return 0;
+}
+
 static struct drm_info_list radeon_debugfs_fence_list[] = {
 	{"radeon_fence_info", &radeon_debugfs_fence_info, 0, NULL},
+	{"radeon_gpu_reset", &radeon_debugfs_gpu_reset, 0, NULL}
 };
 #endif
 
 int radeon_debugfs_fence_init(struct radeon_device *rdev)
 {
 #if defined(CONFIG_DEBUG_FS)
-	return radeon_debugfs_add_files(rdev, radeon_debugfs_fence_list, 1);
+	return radeon_debugfs_add_files(rdev, radeon_debugfs_fence_list, 2);
 #else
 	return 0;
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index 7b944142a9f..add62200840 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -94,6 +94,8 @@ static int pre_xfer(struct i2c_adapter *i2c_adap)
 	struct radeon_i2c_bus_rec *rec = &i2c->rec;
 	uint32_t temp;
 
+	mutex_lock(&i2c->mutex);
+
 	/* RV410 appears to have a bug where the hw i2c in reset
 	 * holds the i2c port in a bad state - switch hw i2c away before
 	 * doing DDC - do this for all r200s/r300s/r400s for safety sake
@@ -170,6 +172,8 @@ static void post_xfer(struct i2c_adapter *i2c_adap)
 	temp = RREG32(rec->mask_data_reg) & ~rec->mask_data_mask;
 	WREG32(rec->mask_data_reg, temp);
 	temp = RREG32(rec->mask_data_reg);
+
+	mutex_unlock(&i2c->mutex);
 }
 
 static int get_clock(void *i2c_priv)
@@ -813,6 +817,8 @@ static int radeon_hw_i2c_xfer(struct i2c_adapter *i2c_adap,
 	struct radeon_i2c_bus_rec *rec = &i2c->rec;
 	int ret = 0;
 
+	mutex_lock(&i2c->mutex);
+
 	switch (rdev->family) {
 	case CHIP_R100:
 	case CHIP_RV100:
@@ -879,6 +885,8 @@ static int radeon_hw_i2c_xfer(struct i2c_adapter *i2c_adap,
 		break;
 	}
 
+	mutex_unlock(&i2c->mutex);
+
 	return ret;
 }
 
@@ -919,6 +927,7 @@ struct radeon_i2c_chan *radeon_i2c_create(struct drm_device *dev,
 	i2c->adapter.dev.parent = &dev->pdev->dev;
 	i2c->dev = dev;
 	i2c_set_adapdata(&i2c->adapter, i2c);
+	mutex_init(&i2c->mutex);
 	if (rec->mm_i2c ||
 	    (rec->hw_capable &&
 	     radeon_hw_i2c &&
@@ -979,7 +988,7 @@ void radeon_i2c_destroy(struct radeon_i2c_chan *i2c)
 		return;
 	i2c_del_adapter(&i2c->adapter);
 	if (i2c->has_aux)
-		drm_dp_aux_unregister_i2c_bus(&i2c->aux);
+		drm_dp_aux_unregister(&i2c->aux);
 	kfree(i2c);
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_ioc32.c b/drivers/gpu/drm/radeon/radeon_ioc32.c
index bdb0f93e73b..0b98ea13457 100644
--- a/drivers/gpu/drm/radeon/radeon_ioc32.c
+++ b/drivers/gpu/drm/radeon/radeon_ioc32.c
@@ -399,7 +399,7 @@ long radeon_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	if (nr < DRM_COMMAND_BASE)
 		return drm_compat_ioctl(filp, cmd, arg);
 
-	if (nr < DRM_COMMAND_BASE + DRM_ARRAY_SIZE(radeon_compat_ioctls))
+	if (nr < DRM_COMMAND_BASE + ARRAY_SIZE(radeon_compat_ioctls))
 		fn = radeon_compat_ioctls[nr - DRM_COMMAND_BASE];
 
 	if (fn != NULL)
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 089c9ffb0aa..16807afab36 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -287,7 +287,7 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 	INIT_WORK(&rdev->reset_work, radeon_irq_reset_work_func);
 
 	rdev->irq.installed = true;
-	r = drm_irq_install(rdev->ddev);
+	r = drm_irq_install(rdev->ddev, rdev->ddev->pdev->irq);
 	if (r) {
 		rdev->irq.installed = false;
 		flush_work(&rdev->hotplug_work);
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index eaaedba0467..d25ae6acfd5 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -513,6 +513,22 @@ static int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		value_size = sizeof(uint64_t);
 		value64 = atomic64_read(&rdev->gtt_usage);
 		break;
+	case RADEON_INFO_ACTIVE_CU_COUNT:
+		if (rdev->family >= CHIP_BONAIRE)
+			*value = rdev->config.cik.active_cus;
+		else if (rdev->family >= CHIP_TAHITI)
+			*value = rdev->config.si.active_cus;
+		else if (rdev->family >= CHIP_CAYMAN)
+			*value = rdev->config.cayman.active_simds;
+		else if (rdev->family >= CHIP_CEDAR)
+			*value = rdev->config.evergreen.active_simds;
+		else if (rdev->family >= CHIP_RV770)
+			*value = rdev->config.rv770.active_simds;
+		else if (rdev->family >= CHIP_R600)
+			*value = rdev->config.r600.active_simds;
+		else
+			*value = 1;
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
@@ -563,7 +579,7 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 	/* new gpu have virtual address space support */
 	if (rdev->family >= CHIP_CAYMAN) {
 		struct radeon_fpriv *fpriv;
-		struct radeon_bo_va *bo_va;
+		struct radeon_vm *vm;
 		int r;
 
 		fpriv = kzalloc(sizeof(*fpriv), GFP_KERNEL);
@@ -571,7 +587,8 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 			return -ENOMEM;
 		}
 
-		r = radeon_vm_init(rdev, &fpriv->vm);
+		vm = &fpriv->vm;
+		r = radeon_vm_init(rdev, vm);
 		if (r) {
 			kfree(fpriv);
 			return r;
@@ -580,22 +597,23 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 		if (rdev->accel_working) {
 			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 			if (r) {
-				radeon_vm_fini(rdev, &fpriv->vm);
+				radeon_vm_fini(rdev, vm);
 				kfree(fpriv);
 				return r;
 			}
 
 			/* map the ib pool buffer read only into
 			 * virtual address space */
-			bo_va = radeon_vm_bo_add(rdev, &fpriv->vm,
-						 rdev->ring_tmp_bo.bo);
-			r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET,
+			vm->ib_bo_va = radeon_vm_bo_add(rdev, vm,
+							rdev->ring_tmp_bo.bo);
+			r = radeon_vm_bo_set_addr(rdev, vm->ib_bo_va,
+						  RADEON_VA_IB_OFFSET,
 						  RADEON_VM_PAGE_READABLE |
 						  RADEON_VM_PAGE_SNOOPED);
 
 			radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 			if (r) {
-				radeon_vm_fini(rdev, &fpriv->vm);
+				radeon_vm_fini(rdev, vm);
 				kfree(fpriv);
 				return r;
 			}
@@ -624,21 +642,19 @@ void radeon_driver_postclose_kms(struct drm_device *dev,
 	/* new gpu have virtual address space support */
 	if (rdev->family >= CHIP_CAYMAN && file_priv->driver_priv) {
 		struct radeon_fpriv *fpriv = file_priv->driver_priv;
-		struct radeon_bo_va *bo_va;
+		struct radeon_vm *vm = &fpriv->vm;
 		int r;
 
 		if (rdev->accel_working) {
 			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 			if (!r) {
-				bo_va = radeon_vm_bo_find(&fpriv->vm,
-							  rdev->ring_tmp_bo.bo);
-				if (bo_va)
-					radeon_vm_bo_rmv(rdev, bo_va);
+				if (vm->ib_bo_va)
+					radeon_vm_bo_rmv(rdev, vm->ib_bo_va);
 				radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 			}
 		}
 
-		radeon_vm_fini(rdev, &fpriv->vm);
+		radeon_vm_fini(rdev, vm);
 		kfree(fpriv);
 		file_priv->driver_priv = NULL;
 	}
@@ -859,4 +875,4 @@ const struct drm_ioctl_desc radeon_ioctls_kms[] = {
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_VA, radeon_gem_va_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(RADEON_GEM_OP, radeon_gem_op_ioctl, DRM_AUTH|DRM_UNLOCKED|DRM_RENDER_ALLOW),
 };
-int radeon_max_kms_ioctl = DRM_ARRAY_SIZE(radeon_ioctls_kms);
+int radeon_max_kms_ioctl = ARRAY_SIZE(radeon_ioctls_kms);
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 6ddf31a2d34..0592ddb0904 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -46,6 +46,10 @@ struct radeon_device;
 #define to_radeon_encoder(x) container_of(x, struct radeon_encoder, base)
 #define to_radeon_framebuffer(x) container_of(x, struct radeon_framebuffer, base)
 
+#define RADEON_MAX_HPD_PINS 7
+#define RADEON_MAX_CRTCS 6
+#define RADEON_MAX_AFMT_BLOCKS 7
+
 enum radeon_rmx_type {
 	RMX_OFF,
 	RMX_FULL,
@@ -191,6 +195,7 @@ struct radeon_i2c_chan {
 	struct radeon_i2c_bus_rec rec;
 	struct drm_dp_aux aux;
 	bool has_aux;
+	struct mutex mutex;
 };
 
 /* mostly for macs, but really any system without connector tables */
@@ -232,8 +237,8 @@ struct radeon_mode_info {
 	struct card_info *atom_card_info;
 	enum radeon_connector_table connector_table;
 	bool mode_config_initialized;
-	struct radeon_crtc *crtcs[6];
-	struct radeon_afmt *afmt[7];
+	struct radeon_crtc *crtcs[RADEON_MAX_CRTCS];
+	struct radeon_afmt *afmt[RADEON_MAX_AFMT_BLOCKS];
 	/* DVI-I properties */
 	struct drm_property *coherent_mode_property;
 	/* DAC enable load detect */
@@ -301,6 +306,12 @@ struct radeon_atom_ss {
 	uint16_t amount;
 };
 
+enum radeon_flip_status {
+	RADEON_FLIP_NONE,
+	RADEON_FLIP_PENDING,
+	RADEON_FLIP_SUBMITTED
+};
+
 struct radeon_crtc {
 	struct drm_crtc base;
 	int crtc_id;
@@ -324,8 +335,9 @@ struct radeon_crtc {
 	struct drm_display_mode native_mode;
 	int pll_id;
 	/* page flipping */
-	struct radeon_unpin_work *unpin_work;
-	int deferred_flip_completion;
+	struct workqueue_struct *flip_queue;
+	struct radeon_flip_work *flip_work;
+	enum radeon_flip_status flip_status;
 	/* pll sharing */
 	struct radeon_atom_ss ss;
 	bool ss_enabled;
@@ -505,6 +517,7 @@ struct radeon_connector {
 	struct radeon_i2c_chan *router_bus;
 	enum radeon_connector_audio audio;
 	enum radeon_connector_dither dither;
+	int pixelclock_for_modeset;
 };
 
 struct radeon_framebuffer {
@@ -906,6 +919,7 @@ bool radeon_fbdev_robj_is_fb(struct radeon_device *rdev, struct radeon_bo *robj)
 
 void radeon_fb_output_poll_changed(struct radeon_device *rdev);
 
+void radeon_crtc_handle_vblank(struct radeon_device *rdev, int crtc_id);
 void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id);
 
 int radeon_align_pitch(struct radeon_device *rdev, int width, int bpp, bool tiled);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 4faa4d6f9bb..6c717b257d6 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -446,7 +446,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 	list_for_each_entry(lobj, head, tv.head) {
 		bo = lobj->robj;
 		if (!bo->pin_count) {
-			u32 domain = lobj->domain;
+			u32 domain = lobj->prefered_domains;
 			u32 current_domain =
 				radeon_mem_type_to_domain(bo->tbo.mem.mem_type);
 
@@ -458,7 +458,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 			 * into account. We don't want to disallow buffer moves
 			 * completely.
 			 */
-			if ((lobj->alt_domain & current_domain) != 0 &&
+			if ((lobj->allowed_domains & current_domain) != 0 &&
 			    (domain & current_domain) == 0 && /* will be moved */
 			    bytes_moved > bytes_moved_threshold) {
 				/* don't move it */
@@ -476,8 +476,9 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 				       initial_bytes_moved;
 
 			if (unlikely(r)) {
-				if (r != -ERESTARTSYS && domain != lobj->alt_domain) {
-					domain = lobj->alt_domain;
+				if (r != -ERESTARTSYS &&
+				    domain != lobj->allowed_domains) {
+					domain = lobj->allowed_domains;
 					goto retry;
 				}
 				ttm_eu_backoff_reservation(ticket, head);
@@ -730,7 +731,7 @@ int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type, bool no_wait)
 {
 	int r;
 
-	r = ttm_bo_reserve(&bo->tbo, true, no_wait, false, 0);
+	r = ttm_bo_reserve(&bo->tbo, true, no_wait, false, NULL);
 	if (unlikely(r != 0))
 		return r;
 	spin_lock(&bo->tbo.bdev->fence_lock);
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 9e7b25a0629..5a873f31a17 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -65,7 +65,7 @@ static inline int radeon_bo_reserve(struct radeon_bo *bo, bool no_intr)
 {
 	int r;
 
-	r = ttm_bo_reserve(&bo->tbo, !no_intr, false, false, 0);
+	r = ttm_bo_reserve(&bo->tbo, !no_intr, false, false, NULL);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
 			dev_err(bo->rdev->dev, "%p reserve failed\n", bo);
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 2bdae61c0ac..e447e390d09 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -73,8 +73,10 @@ void radeon_pm_acpi_event_handler(struct radeon_device *rdev)
 			rdev->pm.dpm.ac_power = true;
 		else
 			rdev->pm.dpm.ac_power = false;
-		if (rdev->asic->dpm.enable_bapm)
-			radeon_dpm_enable_bapm(rdev, rdev->pm.dpm.ac_power);
+		if (rdev->family == CHIP_ARUBA) {
+			if (rdev->asic->dpm.enable_bapm)
+				radeon_dpm_enable_bapm(rdev, rdev->pm.dpm.ac_power);
+		}
 		mutex_unlock(&rdev->pm.mutex);
         } else if (rdev->pm.pm_method == PM_METHOD_PROFILE) {
 		if (rdev->pm.profile == PM_PROFILE_AUTO) {
@@ -984,6 +986,8 @@ void radeon_dpm_enable_uvd(struct radeon_device *rdev, bool enable)
 		if (enable) {
 			mutex_lock(&rdev->pm.mutex);
 			rdev->pm.dpm.uvd_active = true;
+			/* disable this for now */
+#if 0
 			if ((rdev->pm.dpm.sd == 1) && (rdev->pm.dpm.hd == 0))
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_SD;
 			else if ((rdev->pm.dpm.sd == 2) && (rdev->pm.dpm.hd == 0))
@@ -993,6 +997,7 @@ void radeon_dpm_enable_uvd(struct radeon_device *rdev, bool enable)
 			else if ((rdev->pm.dpm.sd == 0) && (rdev->pm.dpm.hd == 2))
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD2;
 			else
+#endif
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD;
 			rdev->pm.dpm.state = dpm_state;
 			mutex_unlock(&rdev->pm.mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c
index 956ab7f14e1..23bb64fd775 100644
--- a/drivers/gpu/drm/radeon/radeon_state.c
+++ b/drivers/gpu/drm/radeon/radeon_state.c
@@ -3054,7 +3054,7 @@ static int radeon_cp_getparam(struct drm_device *dev, void *data, struct drm_fil
 		if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_R600)
 			value = 0;
 		else
-			value = drm_dev_to_irq(dev);
+			value = dev->pdev->irq;
 		break;
 	case RADEON_PARAM_GART_BASE:
 		value = dev_priv->gart_vm_start;
@@ -3258,4 +3258,4 @@ struct drm_ioctl_desc radeon_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(RADEON_CS, r600_cs_legacy_ioctl, DRM_AUTH)
 };
 
-int radeon_max_ioctl = DRM_ARRAY_SIZE(radeon_ioctls);
+int radeon_max_ioctl = ARRAY_SIZE(radeon_ioctls);
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 1b65ae2433c..a4ad270e826 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -812,7 +812,8 @@ void radeon_uvd_note_usage(struct radeon_device *rdev)
 		    (rdev->pm.dpm.hd != hd)) {
 			rdev->pm.dpm.sd = sd;
 			rdev->pm.dpm.hd = hd;
-			streams_changed = true;
+			/* disable this for now */
+			/*streams_changed = true;*/
 		}
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index 3971d968af6..aa21c31a846 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -66,6 +66,7 @@ int radeon_vce_init(struct radeon_device *rdev)
 	case CHIP_BONAIRE:
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
+	case CHIP_HAWAII:
 	case CHIP_MULLINS:
 		fw_name = FIRMWARE_BONAIRE;
 		break;
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index c11b71d249e..725d3669014 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -59,7 +59,7 @@
  */
 static unsigned radeon_vm_num_pdes(struct radeon_device *rdev)
 {
-	return rdev->vm_manager.max_pfn >> RADEON_VM_BLOCK_SIZE;
+	return rdev->vm_manager.max_pfn >> radeon_vm_block_size;
 }
 
 /**
@@ -140,8 +140,8 @@ struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev,
 	/* add the vm page table to the list */
 	list[0].gobj = NULL;
 	list[0].robj = vm->page_directory;
-	list[0].domain = RADEON_GEM_DOMAIN_VRAM;
-	list[0].alt_domain = RADEON_GEM_DOMAIN_VRAM;
+	list[0].prefered_domains = RADEON_GEM_DOMAIN_VRAM;
+	list[0].allowed_domains = RADEON_GEM_DOMAIN_VRAM;
 	list[0].tv.bo = &vm->page_directory->tbo;
 	list[0].tiling_flags = 0;
 	list[0].handle = 0;
@@ -153,8 +153,8 @@ struct radeon_cs_reloc *radeon_vm_get_bos(struct radeon_device *rdev,
 
 		list[idx].gobj = NULL;
 		list[idx].robj = vm->page_tables[i].bo;
-		list[idx].domain = RADEON_GEM_DOMAIN_VRAM;
-		list[idx].alt_domain = RADEON_GEM_DOMAIN_VRAM;
+		list[idx].prefered_domains = RADEON_GEM_DOMAIN_VRAM;
+		list[idx].allowed_domains = RADEON_GEM_DOMAIN_VRAM;
 		list[idx].tv.bo = &list[idx].robj->tbo;
 		list[idx].tiling_flags = 0;
 		list[idx].handle = 0;
@@ -332,6 +332,7 @@ struct radeon_bo_va *radeon_vm_bo_add(struct radeon_device *rdev,
 	bo_va->ref_count = 1;
 	INIT_LIST_HEAD(&bo_va->bo_list);
 	INIT_LIST_HEAD(&bo_va->vm_list);
+	INIT_LIST_HEAD(&bo_va->vm_status);
 
 	mutex_lock(&vm->mutex);
 	list_add(&bo_va->vm_list, &vm->va);
@@ -468,14 +469,29 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 		head = &tmp->vm_list;
 	}
 
+	if (bo_va->soffset) {
+		/* add a clone of the bo_va to clear the old address */
+		tmp = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
+		if (!tmp) {
+			mutex_unlock(&vm->mutex);
+			return -ENOMEM;
+		}
+		tmp->soffset = bo_va->soffset;
+		tmp->eoffset = bo_va->eoffset;
+		tmp->vm = vm;
+		list_add(&tmp->vm_status, &vm->freed);
+	}
+
 	bo_va->soffset = soffset;
 	bo_va->eoffset = eoffset;
 	bo_va->flags = flags;
 	bo_va->valid = false;
 	list_move(&bo_va->vm_list, head);
 
-	soffset = (soffset / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE;
-	eoffset = (eoffset / RADEON_GPU_PAGE_SIZE) >> RADEON_VM_BLOCK_SIZE;
+	soffset = (soffset / RADEON_GPU_PAGE_SIZE) >> radeon_vm_block_size;
+	eoffset = (eoffset / RADEON_GPU_PAGE_SIZE) >> radeon_vm_block_size;
+
+	BUG_ON(eoffset >= radeon_vm_num_pdes(rdev));
 
 	if (eoffset > vm->max_pde_used)
 		vm->max_pde_used = eoffset;
@@ -493,7 +509,7 @@ int radeon_vm_bo_set_addr(struct radeon_device *rdev,
 		mutex_unlock(&vm->mutex);
 
 		r = radeon_bo_create(rdev, RADEON_VM_PTE_COUNT * 8,
-				     RADEON_GPU_PAGE_SIZE, false, 
+				     RADEON_GPU_PAGE_SIZE, true,
 				     RADEON_GEM_DOMAIN_VRAM, NULL, &pt);
 		if (r)
 			return r;
@@ -583,10 +599,9 @@ static uint32_t radeon_vm_page_flags(uint32_t flags)
 int radeon_vm_update_page_directory(struct radeon_device *rdev,
 				    struct radeon_vm *vm)
 {
-	static const uint32_t incr = RADEON_VM_PTE_COUNT * 8;
-
 	struct radeon_bo *pd = vm->page_directory;
 	uint64_t pd_addr = radeon_bo_gpu_offset(pd);
+	uint32_t incr = RADEON_VM_PTE_COUNT * 8;
 	uint64_t last_pde = ~0, last_pt = ~0;
 	unsigned count = 0, pt_idx, ndw;
 	struct radeon_ib ib;
@@ -660,6 +675,84 @@ int radeon_vm_update_page_directory(struct radeon_device *rdev,
 }
 
 /**
+ * radeon_vm_frag_ptes - add fragment information to PTEs
+ *
+ * @rdev: radeon_device pointer
+ * @ib: IB for the update
+ * @pe_start: first PTE to handle
+ * @pe_end: last PTE to handle
+ * @addr: addr those PTEs should point to
+ * @flags: hw mapping flags
+ *
+ * Global and local mutex must be locked!
+ */
+static void radeon_vm_frag_ptes(struct radeon_device *rdev,
+				struct radeon_ib *ib,
+				uint64_t pe_start, uint64_t pe_end,
+				uint64_t addr, uint32_t flags)
+{
+	/**
+	 * The MC L1 TLB supports variable sized pages, based on a fragment
+	 * field in the PTE. When this field is set to a non-zero value, page
+	 * granularity is increased from 4KB to (1 << (12 + frag)). The PTE
+	 * flags are considered valid for all PTEs within the fragment range
+	 * and corresponding mappings are assumed to be physically contiguous.
+	 *
+	 * The L1 TLB can store a single PTE for the whole fragment,
+	 * significantly increasing the space available for translation
+	 * caching. This leads to large improvements in throughput when the
+	 * TLB is under pressure.
+	 *
+	 * The L2 TLB distributes small and large fragments into two
+	 * asymmetric partitions. The large fragment cache is significantly
+	 * larger. Thus, we try to use large fragments wherever possible.
+	 * Userspace can support this by aligning virtual base address and
+	 * allocation size to the fragment size.
+	 */
+
+	/* NI is optimized for 256KB fragments, SI and newer for 64KB */
+	uint64_t frag_flags = rdev->family == CHIP_CAYMAN ?
+			R600_PTE_FRAG_256KB : R600_PTE_FRAG_64KB;
+	uint64_t frag_align = rdev->family == CHIP_CAYMAN ? 0x200 : 0x80;
+
+	uint64_t frag_start = ALIGN(pe_start, frag_align);
+	uint64_t frag_end = pe_end & ~(frag_align - 1);
+
+	unsigned count;
+
+	/* system pages are non continuously */
+	if ((flags & R600_PTE_SYSTEM) || !(flags & R600_PTE_VALID) ||
+	    (frag_start >= frag_end)) {
+
+		count = (pe_end - pe_start) / 8;
+		radeon_asic_vm_set_page(rdev, ib, pe_start, addr, count,
+					RADEON_GPU_PAGE_SIZE, flags);
+		return;
+	}
+
+	/* handle the 4K area at the beginning */
+	if (pe_start != frag_start) {
+		count = (frag_start - pe_start) / 8;
+		radeon_asic_vm_set_page(rdev, ib, pe_start, addr, count,
+					RADEON_GPU_PAGE_SIZE, flags);
+		addr += RADEON_GPU_PAGE_SIZE * count;
+	}
+
+	/* handle the area in the middle */
+	count = (frag_end - frag_start) / 8;
+	radeon_asic_vm_set_page(rdev, ib, frag_start, addr, count,
+				RADEON_GPU_PAGE_SIZE, flags | frag_flags);
+
+	/* handle the 4K area at the end */
+	if (frag_end != pe_end) {
+		addr += RADEON_GPU_PAGE_SIZE * count;
+		count = (pe_end - frag_end) / 8;
+		radeon_asic_vm_set_page(rdev, ib, frag_end, addr, count,
+					RADEON_GPU_PAGE_SIZE, flags);
+	}
+}
+
+/**
  * radeon_vm_update_ptes - make sure that page tables are valid
  *
  * @rdev: radeon_device pointer
@@ -679,8 +772,7 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 				  uint64_t start, uint64_t end,
 				  uint64_t dst, uint32_t flags)
 {
-	static const uint64_t mask = RADEON_VM_PTE_COUNT - 1;
-
+	uint64_t mask = RADEON_VM_PTE_COUNT - 1;
 	uint64_t last_pte = ~0, last_dst = ~0;
 	unsigned count = 0;
 	uint64_t addr;
@@ -690,7 +782,7 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 
 	/* walk over the address space and update the page tables */
 	for (addr = start; addr < end; ) {
-		uint64_t pt_idx = addr >> RADEON_VM_BLOCK_SIZE;
+		uint64_t pt_idx = addr >> radeon_vm_block_size;
 		struct radeon_bo *pt = vm->page_tables[pt_idx].bo;
 		unsigned nptes;
 		uint64_t pte;
@@ -708,10 +800,9 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 		if ((last_pte + 8 * count) != pte) {
 
 			if (count) {
-				radeon_asic_vm_set_page(rdev, ib, last_pte,
-							last_dst, count,
-							RADEON_GPU_PAGE_SIZE,
-							flags);
+				radeon_vm_frag_ptes(rdev, ib, last_pte,
+						    last_pte + 8 * count,
+						    last_dst, flags);
 			}
 
 			count = nptes;
@@ -726,9 +817,9 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 	}
 
 	if (count) {
-		radeon_asic_vm_set_page(rdev, ib, last_pte,
-					last_dst, count,
-					RADEON_GPU_PAGE_SIZE, flags);
+		radeon_vm_frag_ptes(rdev, ib, last_pte,
+				    last_pte + 8 * count,
+				    last_dst, flags);
 	}
 }
 
@@ -746,25 +837,19 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
  * Object have to be reserved and mutex must be locked!
  */
 int radeon_vm_bo_update(struct radeon_device *rdev,
-			struct radeon_vm *vm,
-			struct radeon_bo *bo,
+			struct radeon_bo_va *bo_va,
 			struct ttm_mem_reg *mem)
 {
+	struct radeon_vm *vm = bo_va->vm;
 	struct radeon_ib ib;
-	struct radeon_bo_va *bo_va;
 	unsigned nptes, ndw;
 	uint64_t addr;
 	int r;
 
-	bo_va = radeon_vm_bo_find(vm, bo);
-	if (bo_va == NULL) {
-		dev_err(rdev->dev, "bo %p not in vm %p\n", bo, vm);
-		return -EINVAL;
-	}
 
 	if (!bo_va->soffset) {
 		dev_err(rdev->dev, "bo %p don't has a mapping in vm %p\n",
-			bo, vm);
+			bo_va->bo, vm);
 		return -EINVAL;
 	}
 
@@ -791,18 +876,18 @@ int radeon_vm_bo_update(struct radeon_device *rdev,
 
 	trace_radeon_vm_bo_update(bo_va);
 
-	nptes = radeon_bo_ngpu_pages(bo);
+	nptes = (bo_va->eoffset - bo_va->soffset) / RADEON_GPU_PAGE_SIZE;
 
 	/* padding, etc. */
 	ndw = 64;
 
-	if (RADEON_VM_BLOCK_SIZE > 11)
+	if (radeon_vm_block_size > 11)
 		/* reserve space for one header for every 2k dwords */
 		ndw += (nptes >> 11) * 4;
 	else
 		/* reserve space for one header for
 		    every (1 << BLOCK_SIZE) entries */
-		ndw += (nptes >> RADEON_VM_BLOCK_SIZE) * 4;
+		ndw += (nptes >> radeon_vm_block_size) * 4;
 
 	/* reserve space for pte addresses */
 	ndw += nptes * 2;
@@ -834,33 +919,61 @@ int radeon_vm_bo_update(struct radeon_device *rdev,
 }
 
 /**
+ * radeon_vm_clear_freed - clear freed BOs in the PT
+ *
+ * @rdev: radeon_device pointer
+ * @vm: requested vm
+ *
+ * Make sure all freed BOs are cleared in the PT.
+ * Returns 0 for success.
+ *
+ * PTs have to be reserved and mutex must be locked!
+ */
+int radeon_vm_clear_freed(struct radeon_device *rdev,
+			  struct radeon_vm *vm)
+{
+	struct radeon_bo_va *bo_va, *tmp;
+	int r;
+
+	list_for_each_entry_safe(bo_va, tmp, &vm->freed, vm_status) {
+		list_del(&bo_va->vm_status);
+		r = radeon_vm_bo_update(rdev, bo_va, NULL);
+		kfree(bo_va);
+		if (r)
+			return r;
+	}
+	return 0;
+
+}
+
+/**
  * radeon_vm_bo_rmv - remove a bo to a specific vm
  *
  * @rdev: radeon_device pointer
  * @bo_va: requested bo_va
  *
  * Remove @bo_va->bo from the requested vm (cayman+).
- * Remove @bo_va->bo from the list of bos associated with the bo_va->vm and
- * remove the ptes for @bo_va in the page table.
- * Returns 0 for success.
  *
  * Object have to be reserved!
  */
-int radeon_vm_bo_rmv(struct radeon_device *rdev,
-		     struct radeon_bo_va *bo_va)
+void radeon_vm_bo_rmv(struct radeon_device *rdev,
+		      struct radeon_bo_va *bo_va)
 {
-	int r = 0;
+	struct radeon_vm *vm = bo_va->vm;
 
-	mutex_lock(&bo_va->vm->mutex);
-	if (bo_va->soffset)
-		r = radeon_vm_bo_update(rdev, bo_va->vm, bo_va->bo, NULL);
+	list_del(&bo_va->bo_list);
 
+	mutex_lock(&vm->mutex);
 	list_del(&bo_va->vm_list);
-	mutex_unlock(&bo_va->vm->mutex);
-	list_del(&bo_va->bo_list);
 
-	kfree(bo_va);
-	return r;
+	if (bo_va->soffset) {
+		bo_va->bo = NULL;
+		list_add(&bo_va->vm_status, &vm->freed);
+	} else {
+		kfree(bo_va);
+	}
+
+	mutex_unlock(&vm->mutex);
 }
 
 /**
@@ -892,15 +1005,19 @@ void radeon_vm_bo_invalidate(struct radeon_device *rdev,
  */
 int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 {
+	const unsigned align = min(RADEON_VM_PTB_ALIGN_SIZE,
+		RADEON_VM_PTE_COUNT * 8);
 	unsigned pd_size, pd_entries, pts_size;
 	int r;
 
 	vm->id = 0;
+	vm->ib_bo_va = NULL;
 	vm->fence = NULL;
 	vm->last_flush = NULL;
 	vm->last_id_use = NULL;
 	mutex_init(&vm->mutex);
 	INIT_LIST_HEAD(&vm->va);
+	INIT_LIST_HEAD(&vm->freed);
 
 	pd_size = radeon_vm_directory_size(rdev);
 	pd_entries = radeon_vm_num_pdes(rdev);
@@ -913,7 +1030,7 @@ int radeon_vm_init(struct radeon_device *rdev, struct radeon_vm *vm)
 		return -ENOMEM;
 	}
 
-	r = radeon_bo_create(rdev, pd_size, RADEON_VM_PTB_ALIGN_SIZE, false,
+	r = radeon_bo_create(rdev, pd_size, align, true,
 			     RADEON_GEM_DOMAIN_VRAM, NULL,
 			     &vm->page_directory);
 	if (r)
@@ -955,7 +1072,8 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 			kfree(bo_va);
 		}
 	}
-
+	list_for_each_entry_safe(bo_va, tmp, &vm->freed, vm_status)
+		kfree(bo_va);
 
 	for (i = 0; i < radeon_vm_num_pdes(rdev); i++)
 		radeon_bo_unref(&vm->page_tables[i].bo);
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index 130d5cc50d4..a0f96decece 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -212,21 +212,16 @@ void rs400_gart_fini(struct radeon_device *rdev)
 #define RS400_PTE_WRITEABLE (1 << 2)
 #define RS400_PTE_READABLE  (1 << 3)
 
-int rs400_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
+void rs400_gart_set_page(struct radeon_device *rdev, unsigned i, uint64_t addr)
 {
 	uint32_t entry;
 	u32 *gtt = rdev->gart.ptr;
 
-	if (i < 0 || i > rdev->gart.num_gpu_pages) {
-		return -EINVAL;
-	}
-
 	entry = (lower_32_bits(addr) & PAGE_MASK) |
 		((upper_32_bits(addr) & 0xff) << 4) |
 		RS400_PTE_WRITEABLE | RS400_PTE_READABLE;
 	entry = cpu_to_le32(entry);
 	gtt[i] = entry;
-	return 0;
 }
 
 int rs400_mc_wait_for_idle(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 72d3616de08..d1a35cb1c91 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -109,19 +109,7 @@ void avivo_wait_for_vblank(struct radeon_device *rdev, int crtc)
 	}
 }
 
-void rs600_pre_page_flip(struct radeon_device *rdev, int crtc)
-{
-	/* enable the pflip int */
-	radeon_irq_kms_pflip_irq_get(rdev, crtc);
-}
-
-void rs600_post_page_flip(struct radeon_device *rdev, int crtc)
-{
-	/* disable the pflip int */
-	radeon_irq_kms_pflip_irq_put(rdev, crtc);
-}
-
-u32 rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
+void rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
@@ -148,9 +136,15 @@ u32 rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	/* Unlock the lock, so double-buffering can take place inside vblank */
 	tmp &= ~AVIVO_D1GRPH_UPDATE_LOCK;
 	WREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset, tmp);
+}
+
+bool rs600_page_flip_pending(struct radeon_device *rdev, int crtc_id)
+{
+	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 
 	/* Return current update_pending status: */
-	return RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING;
+	return !!(RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) &
+		AVIVO_D1GRPH_SURFACE_UPDATE_PENDING);
 }
 
 void avivo_program_fmt(struct drm_encoder *encoder)
@@ -632,24 +626,16 @@ static void rs600_gart_fini(struct radeon_device *rdev)
 	radeon_gart_table_vram_free(rdev);
 }
 
-#define R600_PTE_VALID     (1 << 0)
-#define R600_PTE_SYSTEM    (1 << 1)
-#define R600_PTE_SNOOPED   (1 << 2)
-#define R600_PTE_READABLE  (1 << 5)
-#define R600_PTE_WRITEABLE (1 << 6)
-
-int rs600_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr)
+void rs600_gart_set_page(struct radeon_device *rdev, unsigned i, uint64_t addr)
 {
 	void __iomem *ptr = (void *)rdev->gart.ptr;
 
-	if (i < 0 || i > rdev->gart.num_gpu_pages) {
-		return -EINVAL;
-	}
 	addr = addr & 0xFFFFFFFFFFFFF000ULL;
-	addr |= R600_PTE_VALID | R600_PTE_SYSTEM | R600_PTE_SNOOPED;
-	addr |= R600_PTE_READABLE | R600_PTE_WRITEABLE;
+	if (addr == rdev->dummy_page.addr)
+		addr |= R600_PTE_SYSTEM | R600_PTE_SNOOPED;
+	else
+		addr |= R600_PTE_GART;
 	writeq(addr, ptr + (i * 8));
-	return 0;
 }
 
 int rs600_irq_set(struct radeon_device *rdev)
@@ -787,7 +773,7 @@ int rs600_irq_process(struct radeon_device *rdev)
 				wake_up(&rdev->irq.vblank_queue);
 			}
 			if (atomic_read(&rdev->irq.pflip[0]))
-				radeon_crtc_handle_flip(rdev, 0);
+				radeon_crtc_handle_vblank(rdev, 0);
 		}
 		if (G_007EDC_LB_D2_VBLANK_INTERRUPT(rdev->irq.stat_regs.r500.disp_int)) {
 			if (rdev->irq.crtc_vblank_int[1]) {
@@ -796,7 +782,7 @@ int rs600_irq_process(struct radeon_device *rdev)
 				wake_up(&rdev->irq.vblank_queue);
 			}
 			if (atomic_read(&rdev->irq.pflip[1]))
-				radeon_crtc_handle_flip(rdev, 1);
+				radeon_crtc_handle_vblank(rdev, 1);
 		}
 		if (G_007EDC_DC_HOT_PLUG_DETECT1_INTERRUPT(rdev->irq.stat_regs.r500.disp_int)) {
 			queue_hotplug = true;
diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c
index 237dd29d9f1..3e21e869015 100644
--- a/drivers/gpu/drm/radeon/rv515.c
+++ b/drivers/gpu/drm/radeon/rv515.c
@@ -406,8 +406,9 @@ void rv515_mc_resume(struct radeon_device *rdev, struct rv515_mc_save *save)
 	for (i = 0; i < rdev->num_crtc; i++) {
 		if (save->crtc_enabled[i]) {
 			tmp = RREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + crtc_offsets[i]);
-			if ((tmp & 0x3) != 0) {
-				tmp &= ~0x3;
+			if ((tmp & 0x7) != 3) {
+				tmp &= ~0x7;
+				tmp |= 0x3;
 				WREG32(AVIVO_D1MODE_MASTER_UPDATE_MODE + crtc_offsets[i], tmp);
 			}
 			tmp = RREG32(AVIVO_D1GRPH_UPDATE + crtc_offsets[i]);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index fef310773aa..da8703d8d45 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -801,7 +801,7 @@ u32 rv770_get_xclk(struct radeon_device *rdev)
 	return reference_clock;
 }
 
-u32 rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
+void rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
@@ -835,9 +835,15 @@ u32 rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	/* Unlock the lock, so double-buffering can take place inside vblank */
 	tmp &= ~AVIVO_D1GRPH_UPDATE_LOCK;
 	WREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset, tmp);
+}
+
+bool rv770_page_flip_pending(struct radeon_device *rdev, int crtc_id)
+{
+	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 
 	/* Return current update_pending status: */
-	return RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING;
+	return !!(RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) &
+		AVIVO_D1GRPH_SURFACE_UPDATE_PENDING);
 }
 
 /* get temperature in millidegrees */
@@ -1321,6 +1327,9 @@ static void rv770_gpu_init(struct radeon_device *rdev)
 	if (tmp < rdev->config.rv770.max_simds) {
 		rdev->config.rv770.max_simds = tmp;
 	}
+	tmp = rdev->config.rv770.max_simds -
+		r600_count_pipe_bits((cc_gc_shader_pipe_config >> 16) & R7XX_MAX_SIMDS_MASK);
+	rdev->config.rv770.active_simds = tmp;
 
 	switch (rdev->config.rv770.max_tile_pipes) {
 	case 1:
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index da041a43d82..3c76e1dcdf0 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2329,12 +2329,6 @@ void rv770_get_engine_memory_ss(struct radeon_device *rdev)
 	pi->mclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss,
 						       ASIC_INTERNAL_MEMORY_SS, 0);
 
-	/* disable ss, causes hangs on some cayman boards */
-	if (rdev->family == CHIP_CAYMAN) {
-		pi->sclk_ss = false;
-		pi->mclk_ss = false;
-	}
-
 	if (pi->sclk_ss || pi->mclk_ss)
 		pi->dynamic_ss = true;
 	else
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 22a63c98ba1..9e854fd016d 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -71,6 +71,7 @@ MODULE_FIRMWARE("radeon/HAINAN_mc2.bin");
 MODULE_FIRMWARE("radeon/HAINAN_rlc.bin");
 MODULE_FIRMWARE("radeon/HAINAN_smc.bin");
 
+static u32 si_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh);
 static void si_pcie_gen3_enable(struct radeon_device *rdev);
 static void si_program_aspm(struct radeon_device *rdev);
 extern void sumo_rlc_fini(struct radeon_device *rdev);
@@ -2900,7 +2901,7 @@ static void si_gpu_init(struct radeon_device *rdev)
 	u32 sx_debug_1;
 	u32 hdp_host_path_cntl;
 	u32 tmp;
-	int i, j;
+	int i, j, k;
 
 	switch (rdev->family) {
 	case CHIP_TAHITI:
@@ -3098,6 +3099,14 @@ static void si_gpu_init(struct radeon_device *rdev)
 		     rdev->config.si.max_sh_per_se,
 		     rdev->config.si.max_cu_per_sh);
 
+	for (i = 0; i < rdev->config.si.max_shader_engines; i++) {
+		for (j = 0; j < rdev->config.si.max_sh_per_se; j++) {
+			for (k = 0; k < rdev->config.si.max_cu_per_sh; k++) {
+				rdev->config.si.active_cus +=
+					hweight32(si_get_cu_active_bitmap(rdev, i, j));
+			}
+		}
+	}
 
 	/* set HW defaults for 3D engine */
 	WREG32(CP_QUEUE_THRESHOLDS, (ROQ_IB1_START(0x16) |
@@ -3186,7 +3195,7 @@ void si_fence_ring_emit(struct radeon_device *rdev,
 	/* EVENT_WRITE_EOP - flush caches, send int */
 	radeon_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE_EOP, 4));
 	radeon_ring_write(ring, EVENT_TYPE(CACHE_FLUSH_AND_INV_TS_EVENT) | EVENT_INDEX(5));
-	radeon_ring_write(ring, addr & 0xffffffff);
+	radeon_ring_write(ring, lower_32_bits(addr));
 	radeon_ring_write(ring, (upper_32_bits(addr) & 0xff) | DATA_SEL(1) | INT_SEL(2));
 	radeon_ring_write(ring, fence->seq);
 	radeon_ring_write(ring, 0);
@@ -3219,7 +3228,7 @@ void si_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib)
 			radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
 			radeon_ring_write(ring, (1 << 8));
 			radeon_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
-			radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+			radeon_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr));
 			radeon_ring_write(ring, next_rptr);
 		}
 
@@ -4044,18 +4053,21 @@ static int si_pcie_gart_enable(struct radeon_device *rdev)
 	WREG32(MC_VM_MX_L1_TLB_CNTL,
 	       (0xA << 7) |
 	       ENABLE_L1_TLB |
+	       ENABLE_L1_FRAGMENT_PROCESSING |
 	       SYSTEM_ACCESS_MODE_NOT_IN_SYS |
 	       ENABLE_ADVANCED_DRIVER_MODEL |
 	       SYSTEM_APERTURE_UNMAPPED_ACCESS_PASS_THRU);
 	/* Setup L2 cache */
 	WREG32(VM_L2_CNTL, ENABLE_L2_CACHE |
+	       ENABLE_L2_FRAGMENT_PROCESSING |
 	       ENABLE_L2_PTE_CACHE_LRU_UPDATE_BY_WRITE |
 	       ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE |
 	       EFFECTIVE_L2_QUEUE_SIZE(7) |
 	       CONTEXT1_IDENTITY_ACCESS_MODE(1));
 	WREG32(VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS | INVALIDATE_L2_CACHE);
 	WREG32(VM_L2_CNTL3, L2_CACHE_BIGK_ASSOCIATIVITY |
-	       L2_CACHE_BIGK_FRAGMENT_SIZE(0));
+	       BANK_SELECT(4) |
+	       L2_CACHE_BIGK_FRAGMENT_SIZE(4));
 	/* setup context0 */
 	WREG32(VM_CONTEXT0_PAGE_TABLE_START_ADDR, rdev->mc.gtt_start >> 12);
 	WREG32(VM_CONTEXT0_PAGE_TABLE_END_ADDR, rdev->mc.gtt_end >> 12);
@@ -4092,6 +4104,7 @@ static int si_pcie_gart_enable(struct radeon_device *rdev)
 	       (u32)(rdev->dummy_page.addr >> 12));
 	WREG32(VM_CONTEXT1_CNTL2, 4);
 	WREG32(VM_CONTEXT1_CNTL, ENABLE_CONTEXT | PAGE_TABLE_DEPTH(1) |
+				PAGE_TABLE_BLOCK_SIZE(radeon_vm_block_size - 9) |
 				RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
 				RANGE_PROTECTION_FAULT_ENABLE_DEFAULT |
 				DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT |
@@ -6090,6 +6103,7 @@ static inline u32 si_get_ih_wptr(struct radeon_device *rdev)
 		tmp = RREG32(IH_RB_CNTL);
 		tmp |= IH_WPTR_OVERFLOW_CLEAR;
 		WREG32(IH_RB_CNTL, tmp);
+		wptr &= ~RB_OVERFLOW;
 	}
 	return (wptr & rdev->ih.ptr_mask);
 }
@@ -6151,7 +6165,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_flip(rdev, 0);
+						radeon_crtc_handle_vblank(rdev, 0);
 					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D1 vblank\n");
 				}
@@ -6177,7 +6191,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_flip(rdev, 1);
+						radeon_crtc_handle_vblank(rdev, 1);
 					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D2 vblank\n");
 				}
@@ -6203,7 +6217,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[2]))
-						radeon_crtc_handle_flip(rdev, 2);
+						radeon_crtc_handle_vblank(rdev, 2);
 					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D3 vblank\n");
 				}
@@ -6229,7 +6243,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[3]))
-						radeon_crtc_handle_flip(rdev, 3);
+						radeon_crtc_handle_vblank(rdev, 3);
 					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D4 vblank\n");
 				}
@@ -6255,7 +6269,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[4]))
-						radeon_crtc_handle_flip(rdev, 4);
+						radeon_crtc_handle_vblank(rdev, 4);
 					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D5 vblank\n");
 				}
@@ -6281,7 +6295,7 @@ restart_ih:
 						wake_up(&rdev->irq.vblank_queue);
 					}
 					if (atomic_read(&rdev->irq.pflip[5]))
-						radeon_crtc_handle_flip(rdev, 5);
+						radeon_crtc_handle_vblank(rdev, 5);
 					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
 					DRM_DEBUG("IH: D6 vblank\n");
 				}
@@ -6363,14 +6377,16 @@ restart_ih:
 		case 147:
 			addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR);
 			status = RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS);
+			/* reset addr and status */
+			WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
+			if (addr == 0x0 && status == 0x0)
+				break;
 			dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
 				addr);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 				status);
 			si_vm_decode_fault(rdev, status, addr);
-			/* reset addr and status */
-			WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
 			break;
 		case 176: /* RINGID0 CP_INT */
 			radeon_fence_process(rdev, RADEON_RING_TYPE_GFX_INDEX);
diff --git a/drivers/gpu/drm/radeon/si_dma.c b/drivers/gpu/drm/radeon/si_dma.c
index de0ca070122..e24c94b6d14 100644
--- a/drivers/gpu/drm/radeon/si_dma.c
+++ b/drivers/gpu/drm/radeon/si_dma.c
@@ -79,7 +79,25 @@ void si_dma_vm_set_page(struct radeon_device *rdev,
 
 	trace_radeon_vm_set_page(pe, addr, count, incr, flags);
 
-	if (flags & R600_PTE_SYSTEM) {
+	if (flags == R600_PTE_GART) {
+		uint64_t src = rdev->gart.table_addr + (addr >> 12) * 8;
+		while (count) {
+			unsigned bytes = count * 8;
+			if (bytes > 0xFFFF8)
+				bytes = 0xFFFF8;
+
+			ib->ptr[ib->length_dw++] = DMA_PACKET(DMA_PACKET_COPY,
+							      1, 0, 0, bytes);
+			ib->ptr[ib->length_dw++] = lower_32_bits(pe);
+			ib->ptr[ib->length_dw++] = lower_32_bits(src);
+			ib->ptr[ib->length_dw++] = upper_32_bits(pe) & 0xff;
+			ib->ptr[ib->length_dw++] = upper_32_bits(src) & 0xff;
+
+			pe += bytes;
+			src += bytes;
+			count -= bytes / 8;
+		}
+	} else if (flags & R600_PTE_SYSTEM) {
 		while (count) {
 			ndw = count * 2;
 			if (ndw > 0xFFFFE)
@@ -202,8 +220,8 @@ int si_copy_dma(struct radeon_device *rdev,
 			cur_size_in_bytes = 0xFFFFF;
 		size_in_bytes -= cur_size_in_bytes;
 		radeon_ring_write(ring, DMA_PACKET(DMA_PACKET_COPY, 1, 0, 0, cur_size_in_bytes));
-		radeon_ring_write(ring, dst_offset & 0xffffffff);
-		radeon_ring_write(ring, src_offset & 0xffffffff);
+		radeon_ring_write(ring, lower_32_bits(dst_offset));
+		radeon_ring_write(ring, lower_32_bits(src_offset));
 		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
 		radeon_ring_write(ring, upper_32_bits(src_offset) & 0xff);
 		src_offset += cur_size_in_bytes;
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 9a3567bedaa..58918868f89 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -1948,6 +1948,10 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
 			si_pi->cac_weights = cac_weights_cape_verde_pro;
 			si_pi->dte_data = dte_data_cape_verde;
 			break;
+		case 0x682C:
+			si_pi->cac_weights = cac_weights_cape_verde_pro;
+			si_pi->dte_data = dte_data_sun_xt;
+			break;
 		case 0x6825:
 		case 0x6827:
 			si_pi->cac_weights = cac_weights_heathrow;
@@ -1971,10 +1975,9 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
 			si_pi->dte_data = dte_data_venus_xt;
 			break;
 		case 0x6823:
-			si_pi->cac_weights = cac_weights_chelsea_pro;
-			si_pi->dte_data = dte_data_venus_pro;
-			break;
 		case 0x682B:
+		case 0x6822:
+		case 0x682A:
 			si_pi->cac_weights = cac_weights_chelsea_pro;
 			si_pi->dte_data = dte_data_venus_pro;
 			break;
@@ -1988,6 +1991,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
 		case 0x6601:
 		case 0x6621:
 		case 0x6603:
+		case 0x6605:
 			si_pi->cac_weights = cac_weights_mars_pro;
 			si_pi->lcac_config = lcac_mars_pro;
 			si_pi->cac_override = cac_override_oland;
@@ -1998,6 +2002,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
 		case 0x6600:
 		case 0x6606:
 		case 0x6620:
+		case 0x6604:
 			si_pi->cac_weights = cac_weights_mars_xt;
 			si_pi->lcac_config = lcac_mars_pro;
 			si_pi->cac_override = cac_override_oland;
@@ -2006,6 +2011,8 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
 			update_dte_from_pl2 = true;
 			break;
 		case 0x6611:
+		case 0x6613:
+		case 0x6608:
 			si_pi->cac_weights = cac_weights_oland_pro;
 			si_pi->lcac_config = lcac_mars_pro;
 			si_pi->cac_override = cac_override_oland;
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 7321283602c..fd414d34d88 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -362,6 +362,7 @@
 #define		READ_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 16)
 #define		WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT		(1 << 18)
 #define		WRITE_PROTECTION_FAULT_ENABLE_DEFAULT		(1 << 19)
+#define		PAGE_TABLE_BLOCK_SIZE(x)			(((x) & 0xF) << 24)
 #define VM_CONTEXT1_CNTL				0x1414
 #define VM_CONTEXT0_CNTL2				0x1430
 #define VM_CONTEXT1_CNTL2				0x1434
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index 2a2822c0332..32e50be9c4a 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -1874,7 +1874,16 @@ int trinity_dpm_init(struct radeon_device *rdev)
 	for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++)
 		pi->at[i] = TRINITY_AT_DFLT;
 
-	pi->enable_bapm = false;
+	/* There are stability issues reported on with
+	 * bapm enabled when switching between AC and battery
+	 * power.  At the same time, some MSI boards hang
+	 * if it's not enabled and dpm is enabled.  Just enable
+	 * it for MSI boards right now.
+	 */
+	if (rdev->pdev->subsystem_vendor == 0x1462)
+		pi->enable_bapm = true;
+	else
+		pi->enable_bapm = false;
 	pi->enable_nbps_policy = true;
 	pi->enable_sclk_ds = true;
 	pi->enable_gfx_power_gating = true;
diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c
index d1771004cb5..8bfdadd5659 100644
--- a/drivers/gpu/drm/radeon/uvd_v2_2.c
+++ b/drivers/gpu/drm/radeon/uvd_v2_2.c
@@ -45,7 +45,7 @@ void uvd_v2_2_fence_emit(struct radeon_device *rdev,
 	radeon_ring_write(ring, PACKET0(UVD_CONTEXT_ID, 0));
 	radeon_ring_write(ring, fence->seq);
 	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA0, 0));
-	radeon_ring_write(ring, addr & 0xffffffff);
+	radeon_ring_write(ring, lower_32_bits(addr));
 	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_DATA1, 0));
 	radeon_ring_write(ring, upper_32_bits(addr) & 0xff);
 	radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0));
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index d8e835ac2c5..2e3d7b5b0ad 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -1,6 +1,7 @@
 config DRM_RCAR_DU
 	tristate "DRM Support for R-Car Display Unit"
 	depends on DRM && ARM
+	depends on ARCH_SHMOBILE || COMPILE_TEST
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
@@ -12,6 +13,7 @@ config DRM_RCAR_DU
 config DRM_RCAR_LVDS
 	bool "R-Car DU LVDS Encoder Support"
 	depends on DRM_RCAR_DU
+	depends on ARCH_R8A7790 || ARCH_R8A7791 || COMPILE_TEST
 	help
 	  Enable support the R-Car Display Unit embedded LVDS encoders
 	  (currently only on R8A7790).
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
index 4f3ba93cd91..289048d1c7b 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_lvdscon.c
@@ -57,15 +57,8 @@ static int rcar_du_lvds_connector_get_modes(struct drm_connector *connector)
 	return 1;
 }
 
-static int rcar_du_lvds_connector_mode_valid(struct drm_connector *connector,
-					    struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
 static const struct drm_connector_helper_funcs connector_helper_funcs = {
 	.get_modes = rcar_du_lvds_connector_get_modes,
-	.mode_valid = rcar_du_lvds_connector_mode_valid,
 	.best_encoder = rcar_du_connector_best_encoder,
 };
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
index 41d563adfea..ccfe64c7188 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_vgacon.c
@@ -25,15 +25,8 @@ static int rcar_du_vga_connector_get_modes(struct drm_connector *connector)
 	return 0;
 }
 
-static int rcar_du_vga_connector_mode_valid(struct drm_connector *connector,
-					    struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
 static const struct drm_connector_helper_funcs connector_helper_funcs = {
 	.get_modes = rcar_du_vga_connector_get_modes,
-	.mode_valid = rcar_du_vga_connector_mode_valid,
 	.best_encoder = rcar_du_connector_best_encoder,
 };
 
diff --git a/drivers/gpu/drm/savage/savage_bci.c b/drivers/gpu/drm/savage/savage_bci.c
index d2b2df9e26f..c97cdc9ab23 100644
--- a/drivers/gpu/drm/savage/savage_bci.c
+++ b/drivers/gpu/drm/savage/savage_bci.c
@@ -1079,4 +1079,4 @@ const struct drm_ioctl_desc savage_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(SAVAGE_BCI_EVENT_WAIT, savage_bci_event_wait, DRM_AUTH),
 };
 
-int savage_max_ioctl = DRM_ARRAY_SIZE(savage_ioctls);
+int savage_max_ioctl = ARRAY_SIZE(savage_ioctls);
diff --git a/drivers/gpu/drm/shmobile/Kconfig b/drivers/gpu/drm/shmobile/Kconfig
index 2ee44ca9d67..a50fe0eeaa0 100644
--- a/drivers/gpu/drm/shmobile/Kconfig
+++ b/drivers/gpu/drm/shmobile/Kconfig
@@ -1,6 +1,7 @@
 config DRM_SHMOBILE
 	tristate "DRM Support for SH Mobile"
-	depends on DRM && (ARM || SUPERH)
+	depends on DRM && ARM
+	depends on ARCH_SHMOBILE || COMPILE_TEST
 	select BACKLIGHT_CLASS_DEVICE
 	select DRM_KMS_HELPER
 	select DRM_KMS_FB_HELPER
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
index e9e5e6d368c..faf176b2daf 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
@@ -674,12 +674,6 @@ static int shmob_drm_connector_get_modes(struct drm_connector *connector)
 	return 1;
 }
 
-static int shmob_drm_connector_mode_valid(struct drm_connector *connector,
-					  struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-
 static struct drm_encoder *
 shmob_drm_connector_best_encoder(struct drm_connector *connector)
 {
@@ -690,7 +684,6 @@ shmob_drm_connector_best_encoder(struct drm_connector *connector)
 
 static const struct drm_connector_helper_funcs connector_helper_funcs = {
 	.get_modes = shmob_drm_connector_get_modes,
-	.mode_valid = shmob_drm_connector_mode_valid,
 	.best_encoder = shmob_drm_connector_best_encoder,
 };
 
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
index c839c9c89ef..82c84c7fd4f 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_drv.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
@@ -185,7 +185,7 @@ static int shmob_drm_load(struct drm_device *dev, unsigned long flags)
 		goto done;
 	}
 
-	ret = drm_irq_install(dev);
+	ret = drm_irq_install(dev, platform_get_irq(dev->platformdev, 0));
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to install IRQ handler\n");
 		goto done;
diff --git a/drivers/gpu/drm/sis/sis_mm.c b/drivers/gpu/drm/sis/sis_mm.c
index 0573be0d293..77f288e4a0a 100644
--- a/drivers/gpu/drm/sis/sis_mm.c
+++ b/drivers/gpu/drm/sis/sis_mm.c
@@ -359,4 +359,4 @@ const struct drm_ioctl_desc sis_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(SIS_FB_INIT, sis_fb_init, DRM_AUTH | DRM_MASTER | DRM_ROOT_ONLY),
 };
 
-int sis_max_ioctl = DRM_ARRAY_SIZE(sis_ioctls);
+int sis_max_ioctl = ARRAY_SIZE(sis_ioctls);
diff --git a/drivers/gpu/drm/tegra/Makefile b/drivers/gpu/drm/tegra/Makefile
index d43f21bb459..2c66a8db9da 100644
--- a/drivers/gpu/drm/tegra/Makefile
+++ b/drivers/gpu/drm/tegra/Makefile
@@ -1,7 +1,6 @@
 ccflags-$(CONFIG_DRM_TEGRA_DEBUG) += -DDEBUG
 
 tegra-drm-y := \
-	bus.o \
 	drm.o \
 	gem.o \
 	fb.o \
diff --git a/drivers/gpu/drm/tegra/bus.c b/drivers/gpu/drm/tegra/bus.c
deleted file mode 100644
index 71cef5c13dc..00000000000
--- a/drivers/gpu/drm/tegra/bus.c
+++ /dev/null
@@ -1,75 +0,0 @@
-/*
- * Copyright (C) 2013 NVIDIA Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include "drm.h"
-
-static int drm_host1x_set_busid(struct drm_device *dev,
-				struct drm_master *master)
-{
-	const char *device = dev_name(dev->dev);
-	const char *driver = dev->driver->name;
-	const char *bus = dev->dev->bus->name;
-	int length;
-
-	master->unique_len = strlen(bus) + 1 + strlen(device);
-	master->unique_size = master->unique_len;
-
-	master->unique = kmalloc(master->unique_len + 1, GFP_KERNEL);
-	if (!master->unique)
-		return -ENOMEM;
-
-	snprintf(master->unique, master->unique_len + 1, "%s:%s", bus, device);
-
-	length = strlen(driver) + 1 + master->unique_len;
-
-	dev->devname = kmalloc(length + 1, GFP_KERNEL);
-	if (!dev->devname)
-		return -ENOMEM;
-
-	snprintf(dev->devname, length + 1, "%s@%s", driver, master->unique);
-
-	return 0;
-}
-
-static struct drm_bus drm_host1x_bus = {
-	.bus_type = DRIVER_BUS_HOST1X,
-	.set_busid = drm_host1x_set_busid,
-};
-
-int drm_host1x_init(struct drm_driver *driver, struct host1x_device *device)
-{
-	struct drm_device *drm;
-	int ret;
-
-	driver->bus = &drm_host1x_bus;
-
-	drm = drm_dev_alloc(driver, &device->dev);
-	if (!drm)
-		return -ENOMEM;
-
-	ret = drm_dev_register(drm, 0);
-	if (ret)
-		goto err_free;
-
-	DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n", driver->name,
-		 driver->major, driver->minor, driver->patchlevel,
-		 driver->date, drm->primary->index);
-
-	return 0;
-
-err_free:
-	drm_dev_unref(drm);
-	return ret;
-}
-
-void drm_host1x_exit(struct drm_driver *driver, struct host1x_device *device)
-{
-	struct tegra_drm *tegra = dev_get_drvdata(&device->dev);
-
-	drm_put_dev(tegra->drm);
-}
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index edb871d7d39..ef40381f390 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -17,6 +17,7 @@
 
 struct tegra_dc_soc_info {
 	bool supports_interlacing;
+	bool supports_cursor;
 };
 
 struct tegra_plane {
@@ -29,6 +30,254 @@ static inline struct tegra_plane *to_tegra_plane(struct drm_plane *plane)
 	return container_of(plane, struct tegra_plane, base);
 }
 
+static unsigned int tegra_dc_format(uint32_t format, uint32_t *swap)
+{
+	/* assume no swapping of fetched data */
+	if (swap)
+		*swap = BYTE_SWAP_NOSWAP;
+
+	switch (format) {
+	case DRM_FORMAT_XBGR8888:
+		return WIN_COLOR_DEPTH_R8G8B8A8;
+
+	case DRM_FORMAT_XRGB8888:
+		return WIN_COLOR_DEPTH_B8G8R8A8;
+
+	case DRM_FORMAT_RGB565:
+		return WIN_COLOR_DEPTH_B5G6R5;
+
+	case DRM_FORMAT_UYVY:
+		return WIN_COLOR_DEPTH_YCbCr422;
+
+	case DRM_FORMAT_YUYV:
+		if (swap)
+			*swap = BYTE_SWAP_SWAP2;
+
+		return WIN_COLOR_DEPTH_YCbCr422;
+
+	case DRM_FORMAT_YUV420:
+		return WIN_COLOR_DEPTH_YCbCr420P;
+
+	case DRM_FORMAT_YUV422:
+		return WIN_COLOR_DEPTH_YCbCr422P;
+
+	default:
+		break;
+	}
+
+	WARN(1, "unsupported pixel format %u, using default\n", format);
+	return WIN_COLOR_DEPTH_B8G8R8A8;
+}
+
+static bool tegra_dc_format_is_yuv(unsigned int format, bool *planar)
+{
+	switch (format) {
+	case WIN_COLOR_DEPTH_YCbCr422:
+	case WIN_COLOR_DEPTH_YUV422:
+		if (planar)
+			*planar = false;
+
+		return true;
+
+	case WIN_COLOR_DEPTH_YCbCr420P:
+	case WIN_COLOR_DEPTH_YUV420P:
+	case WIN_COLOR_DEPTH_YCbCr422P:
+	case WIN_COLOR_DEPTH_YUV422P:
+	case WIN_COLOR_DEPTH_YCbCr422R:
+	case WIN_COLOR_DEPTH_YUV422R:
+	case WIN_COLOR_DEPTH_YCbCr422RA:
+	case WIN_COLOR_DEPTH_YUV422RA:
+		if (planar)
+			*planar = true;
+
+		return true;
+	}
+
+	return false;
+}
+
+static inline u32 compute_dda_inc(unsigned int in, unsigned int out, bool v,
+				  unsigned int bpp)
+{
+	fixed20_12 outf = dfixed_init(out);
+	fixed20_12 inf = dfixed_init(in);
+	u32 dda_inc;
+	int max;
+
+	if (v)
+		max = 15;
+	else {
+		switch (bpp) {
+		case 2:
+			max = 8;
+			break;
+
+		default:
+			WARN_ON_ONCE(1);
+			/* fallthrough */
+		case 4:
+			max = 4;
+			break;
+		}
+	}
+
+	outf.full = max_t(u32, outf.full - dfixed_const(1), dfixed_const(1));
+	inf.full -= dfixed_const(1);
+
+	dda_inc = dfixed_div(inf, outf);
+	dda_inc = min_t(u32, dda_inc, dfixed_const(max));
+
+	return dda_inc;
+}
+
+static inline u32 compute_initial_dda(unsigned int in)
+{
+	fixed20_12 inf = dfixed_init(in);
+	return dfixed_frac(inf);
+}
+
+static int tegra_dc_setup_window(struct tegra_dc *dc, unsigned int index,
+				 const struct tegra_dc_window *window)
+{
+	unsigned h_offset, v_offset, h_size, v_size, h_dda, v_dda, bpp;
+	unsigned long value;
+	bool yuv, planar;
+
+	/*
+	 * For YUV planar modes, the number of bytes per pixel takes into
+	 * account only the luma component and therefore is 1.
+	 */
+	yuv = tegra_dc_format_is_yuv(window->format, &planar);
+	if (!yuv)
+		bpp = window->bits_per_pixel / 8;
+	else
+		bpp = planar ? 1 : 2;
+
+	value = WINDOW_A_SELECT << index;
+	tegra_dc_writel(dc, value, DC_CMD_DISPLAY_WINDOW_HEADER);
+
+	tegra_dc_writel(dc, window->format, DC_WIN_COLOR_DEPTH);
+	tegra_dc_writel(dc, window->swap, DC_WIN_BYTE_SWAP);
+
+	value = V_POSITION(window->dst.y) | H_POSITION(window->dst.x);
+	tegra_dc_writel(dc, value, DC_WIN_POSITION);
+
+	value = V_SIZE(window->dst.h) | H_SIZE(window->dst.w);
+	tegra_dc_writel(dc, value, DC_WIN_SIZE);
+
+	h_offset = window->src.x * bpp;
+	v_offset = window->src.y;
+	h_size = window->src.w * bpp;
+	v_size = window->src.h;
+
+	value = V_PRESCALED_SIZE(v_size) | H_PRESCALED_SIZE(h_size);
+	tegra_dc_writel(dc, value, DC_WIN_PRESCALED_SIZE);
+
+	/*
+	 * For DDA computations the number of bytes per pixel for YUV planar
+	 * modes needs to take into account all Y, U and V components.
+	 */
+	if (yuv && planar)
+		bpp = 2;
+
+	h_dda = compute_dda_inc(window->src.w, window->dst.w, false, bpp);
+	v_dda = compute_dda_inc(window->src.h, window->dst.h, true, bpp);
+
+	value = V_DDA_INC(v_dda) | H_DDA_INC(h_dda);
+	tegra_dc_writel(dc, value, DC_WIN_DDA_INC);
+
+	h_dda = compute_initial_dda(window->src.x);
+	v_dda = compute_initial_dda(window->src.y);
+
+	tegra_dc_writel(dc, h_dda, DC_WIN_H_INITIAL_DDA);
+	tegra_dc_writel(dc, v_dda, DC_WIN_V_INITIAL_DDA);
+
+	tegra_dc_writel(dc, 0, DC_WIN_UV_BUF_STRIDE);
+	tegra_dc_writel(dc, 0, DC_WIN_BUF_STRIDE);
+
+	tegra_dc_writel(dc, window->base[0], DC_WINBUF_START_ADDR);
+
+	if (yuv && planar) {
+		tegra_dc_writel(dc, window->base[1], DC_WINBUF_START_ADDR_U);
+		tegra_dc_writel(dc, window->base[2], DC_WINBUF_START_ADDR_V);
+		value = window->stride[1] << 16 | window->stride[0];
+		tegra_dc_writel(dc, value, DC_WIN_LINE_STRIDE);
+	} else {
+		tegra_dc_writel(dc, window->stride[0], DC_WIN_LINE_STRIDE);
+	}
+
+	if (window->bottom_up)
+		v_offset += window->src.h - 1;
+
+	tegra_dc_writel(dc, h_offset, DC_WINBUF_ADDR_H_OFFSET);
+	tegra_dc_writel(dc, v_offset, DC_WINBUF_ADDR_V_OFFSET);
+
+	if (window->tiled) {
+		value = DC_WIN_BUFFER_ADDR_MODE_TILE_UV |
+			DC_WIN_BUFFER_ADDR_MODE_TILE;
+	} else {
+		value = DC_WIN_BUFFER_ADDR_MODE_LINEAR_UV |
+			DC_WIN_BUFFER_ADDR_MODE_LINEAR;
+	}
+
+	tegra_dc_writel(dc, value, DC_WIN_BUFFER_ADDR_MODE);
+
+	value = WIN_ENABLE;
+
+	if (yuv) {
+		/* setup default colorspace conversion coefficients */
+		tegra_dc_writel(dc, 0x00f0, DC_WIN_CSC_YOF);
+		tegra_dc_writel(dc, 0x012a, DC_WIN_CSC_KYRGB);
+		tegra_dc_writel(dc, 0x0000, DC_WIN_CSC_KUR);
+		tegra_dc_writel(dc, 0x0198, DC_WIN_CSC_KVR);
+		tegra_dc_writel(dc, 0x039b, DC_WIN_CSC_KUG);
+		tegra_dc_writel(dc, 0x032f, DC_WIN_CSC_KVG);
+		tegra_dc_writel(dc, 0x0204, DC_WIN_CSC_KUB);
+		tegra_dc_writel(dc, 0x0000, DC_WIN_CSC_KVB);
+
+		value |= CSC_ENABLE;
+	} else if (window->bits_per_pixel < 24) {
+		value |= COLOR_EXPAND;
+	}
+
+	if (window->bottom_up)
+		value |= V_DIRECTION;
+
+	tegra_dc_writel(dc, value, DC_WIN_WIN_OPTIONS);
+
+	/*
+	 * Disable blending and assume Window A is the bottom-most window,
+	 * Window C is the top-most window and Window B is in the middle.
+	 */
+	tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_NOKEY);
+	tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_1WIN);
+
+	switch (index) {
+	case 0:
+		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_2WIN_X);
+		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_2WIN_Y);
+		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_3WIN_XY);
+		break;
+
+	case 1:
+		tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_2WIN_X);
+		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_2WIN_Y);
+		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_3WIN_XY);
+		break;
+
+	case 2:
+		tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_2WIN_X);
+		tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_2WIN_Y);
+		tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_3WIN_XY);
+		break;
+	}
+
+	tegra_dc_writel(dc, WIN_A_UPDATE << index, DC_CMD_STATE_CONTROL);
+	tegra_dc_writel(dc, WIN_A_ACT_REQ << index, DC_CMD_STATE_CONTROL);
+
+	return 0;
+}
+
 static int tegra_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 			      struct drm_framebuffer *fb, int crtc_x,
 			      int crtc_y, unsigned int crtc_w,
@@ -49,7 +298,7 @@ static int tegra_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	window.dst.y = crtc_y;
 	window.dst.w = crtc_w;
 	window.dst.h = crtc_h;
-	window.format = tegra_dc_format(fb->pixel_format);
+	window.format = tegra_dc_format(fb->pixel_format, &window.swap);
 	window.bits_per_pixel = fb->bits_per_pixel;
 	window.bottom_up = tegra_fb_is_bottom_up(fb);
 	window.tiled = tegra_fb_is_tiled(fb);
@@ -117,6 +366,7 @@ static const uint32_t plane_formats[] = {
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_RGB565,
 	DRM_FORMAT_UYVY,
+	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YUV420,
 	DRM_FORMAT_YUV422,
 };
@@ -150,9 +400,9 @@ static int tegra_dc_add_planes(struct drm_device *drm, struct tegra_dc *dc)
 static int tegra_dc_set_base(struct tegra_dc *dc, int x, int y,
 			     struct drm_framebuffer *fb)
 {
-	unsigned int format = tegra_dc_format(fb->pixel_format);
 	struct tegra_bo *bo = tegra_fb_get_plane(fb, 0);
 	unsigned int h_offset = 0, v_offset = 0;
+	unsigned int format, swap;
 	unsigned long value;
 
 	tegra_dc_writel(dc, WINDOW_A_SELECT, DC_CMD_DISPLAY_WINDOW_HEADER);
@@ -162,7 +412,10 @@ static int tegra_dc_set_base(struct tegra_dc *dc, int x, int y,
 
 	tegra_dc_writel(dc, bo->paddr + value, DC_WINBUF_START_ADDR);
 	tegra_dc_writel(dc, fb->pitches[0], DC_WIN_LINE_STRIDE);
+
+	format = tegra_dc_format(fb->pixel_format, &swap);
 	tegra_dc_writel(dc, format, DC_WIN_COLOR_DEPTH);
+	tegra_dc_writel(dc, swap, DC_WIN_BYTE_SWAP);
 
 	if (tegra_fb_is_tiled(fb)) {
 		value = DC_WIN_BUFFER_ADDR_MODE_TILE_UV |
@@ -177,13 +430,13 @@ static int tegra_dc_set_base(struct tegra_dc *dc, int x, int y,
 	/* make sure bottom-up buffers are properly displayed */
 	if (tegra_fb_is_bottom_up(fb)) {
 		value = tegra_dc_readl(dc, DC_WIN_WIN_OPTIONS);
-		value |= INVERT_V;
+		value |= V_DIRECTION;
 		tegra_dc_writel(dc, value, DC_WIN_WIN_OPTIONS);
 
 		v_offset += fb->height - 1;
 	} else {
 		value = tegra_dc_readl(dc, DC_WIN_WIN_OPTIONS);
-		value &= ~INVERT_V;
+		value &= ~V_DIRECTION;
 		tegra_dc_writel(dc, value, DC_WIN_WIN_OPTIONS);
 	}
 
@@ -225,6 +478,109 @@ void tegra_dc_disable_vblank(struct tegra_dc *dc)
 	spin_unlock_irqrestore(&dc->lock, flags);
 }
 
+static int tegra_dc_cursor_set2(struct drm_crtc *crtc, struct drm_file *file,
+				uint32_t handle, uint32_t width,
+				uint32_t height, int32_t hot_x, int32_t hot_y)
+{
+	unsigned long value = CURSOR_CLIP_DISPLAY;
+	struct tegra_dc *dc = to_tegra_dc(crtc);
+	struct drm_gem_object *gem;
+	struct tegra_bo *bo = NULL;
+
+	if (!dc->soc->supports_cursor)
+		return -ENXIO;
+
+	if (width != height)
+		return -EINVAL;
+
+	switch (width) {
+	case 32:
+		value |= CURSOR_SIZE_32x32;
+		break;
+
+	case 64:
+		value |= CURSOR_SIZE_64x64;
+		break;
+
+	case 128:
+		value |= CURSOR_SIZE_128x128;
+
+	case 256:
+		value |= CURSOR_SIZE_256x256;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (handle) {
+		gem = drm_gem_object_lookup(crtc->dev, file, handle);
+		if (!gem)
+			return -ENOENT;
+
+		bo = to_tegra_bo(gem);
+	}
+
+	if (bo) {
+		unsigned long addr = (bo->paddr & 0xfffffc00) >> 10;
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		unsigned long high = (bo->paddr & 0xfffffffc) >> 32;
+#endif
+
+		tegra_dc_writel(dc, value | addr, DC_DISP_CURSOR_START_ADDR);
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		tegra_dc_writel(dc, high, DC_DISP_CURSOR_START_ADDR_HI);
+#endif
+
+		value = tegra_dc_readl(dc, DC_DISP_DISP_WIN_OPTIONS);
+		value |= CURSOR_ENABLE;
+		tegra_dc_writel(dc, value, DC_DISP_DISP_WIN_OPTIONS);
+
+		value = tegra_dc_readl(dc, DC_DISP_BLEND_CURSOR_CONTROL);
+		value &= ~CURSOR_DST_BLEND_MASK;
+		value &= ~CURSOR_SRC_BLEND_MASK;
+		value |= CURSOR_MODE_NORMAL;
+		value |= CURSOR_DST_BLEND_NEG_K1_TIMES_SRC;
+		value |= CURSOR_SRC_BLEND_K1_TIMES_SRC;
+		value |= CURSOR_ALPHA;
+		tegra_dc_writel(dc, value, DC_DISP_BLEND_CURSOR_CONTROL);
+	} else {
+		value = tegra_dc_readl(dc, DC_DISP_DISP_WIN_OPTIONS);
+		value &= ~CURSOR_ENABLE;
+		tegra_dc_writel(dc, value, DC_DISP_DISP_WIN_OPTIONS);
+	}
+
+	tegra_dc_writel(dc, CURSOR_ACT_REQ << 8, DC_CMD_STATE_CONTROL);
+	tegra_dc_writel(dc, CURSOR_ACT_REQ, DC_CMD_STATE_CONTROL);
+
+	tegra_dc_writel(dc, GENERAL_ACT_REQ << 8, DC_CMD_STATE_CONTROL);
+	tegra_dc_writel(dc, GENERAL_ACT_REQ, DC_CMD_STATE_CONTROL);
+
+	return 0;
+}
+
+static int tegra_dc_cursor_move(struct drm_crtc *crtc, int x, int y)
+{
+	struct tegra_dc *dc = to_tegra_dc(crtc);
+	unsigned long value;
+
+	if (!dc->soc->supports_cursor)
+		return -ENXIO;
+
+	value = ((y & 0x3fff) << 16) | (x & 0x3fff);
+	tegra_dc_writel(dc, value, DC_DISP_CURSOR_POSITION);
+
+	tegra_dc_writel(dc, CURSOR_ACT_REQ << 8, DC_CMD_STATE_CONTROL);
+	tegra_dc_writel(dc, CURSOR_ACT_REQ, DC_CMD_STATE_CONTROL);
+
+	/* XXX: only required on generations earlier than Tegra124? */
+	tegra_dc_writel(dc, GENERAL_ACT_REQ << 8, DC_CMD_STATE_CONTROL);
+	tegra_dc_writel(dc, GENERAL_ACT_REQ, DC_CMD_STATE_CONTROL);
+
+	return 0;
+}
+
 static void tegra_dc_finish_page_flip(struct tegra_dc *dc)
 {
 	struct drm_device *drm = dc->base.dev;
@@ -301,6 +657,8 @@ static void tegra_dc_destroy(struct drm_crtc *crtc)
 }
 
 static const struct drm_crtc_funcs tegra_crtc_funcs = {
+	.cursor_set2 = tegra_dc_cursor_set2,
+	.cursor_move = tegra_dc_cursor_move,
 	.page_flip = tegra_dc_page_flip,
 	.set_config = drm_crtc_helper_set_config,
 	.destroy = tegra_dc_destroy,
@@ -334,52 +692,11 @@ static bool tegra_crtc_mode_fixup(struct drm_crtc *crtc,
 	return true;
 }
 
-static inline u32 compute_dda_inc(unsigned int in, unsigned int out, bool v,
-				  unsigned int bpp)
-{
-	fixed20_12 outf = dfixed_init(out);
-	fixed20_12 inf = dfixed_init(in);
-	u32 dda_inc;
-	int max;
-
-	if (v)
-		max = 15;
-	else {
-		switch (bpp) {
-		case 2:
-			max = 8;
-			break;
-
-		default:
-			WARN_ON_ONCE(1);
-			/* fallthrough */
-		case 4:
-			max = 4;
-			break;
-		}
-	}
-
-	outf.full = max_t(u32, outf.full - dfixed_const(1), dfixed_const(1));
-	inf.full -= dfixed_const(1);
-
-	dda_inc = dfixed_div(inf, outf);
-	dda_inc = min_t(u32, dda_inc, dfixed_const(max));
-
-	return dda_inc;
-}
-
-static inline u32 compute_initial_dda(unsigned int in)
-{
-	fixed20_12 inf = dfixed_init(in);
-	return dfixed_frac(inf);
-}
-
 static int tegra_dc_set_timings(struct tegra_dc *dc,
 				struct drm_display_mode *mode)
 {
-	/* TODO: For HDMI compliance, h & v ref_to_sync should be set to 1 */
-	unsigned int h_ref_to_sync = 0;
-	unsigned int v_ref_to_sync = 0;
+	unsigned int h_ref_to_sync = 1;
+	unsigned int v_ref_to_sync = 1;
 	unsigned long value;
 
 	tegra_dc_writel(dc, 0x0, DC_DISP_DISP_TIMING_OPTIONS);
@@ -406,13 +723,14 @@ static int tegra_dc_set_timings(struct tegra_dc *dc,
 }
 
 static int tegra_crtc_setup_clk(struct drm_crtc *crtc,
-				struct drm_display_mode *mode,
-				unsigned long *div)
+				struct drm_display_mode *mode)
 {
-	unsigned long pclk = mode->clock * 1000, rate;
+	unsigned long pclk = mode->clock * 1000;
 	struct tegra_dc *dc = to_tegra_dc(crtc);
 	struct tegra_output *output = NULL;
 	struct drm_encoder *encoder;
+	unsigned int div;
+	u32 value;
 	long err;
 
 	list_for_each_entry(encoder, &crtc->dev->mode_config.encoder_list, head)
@@ -425,221 +743,23 @@ static int tegra_crtc_setup_clk(struct drm_crtc *crtc,
 		return -ENODEV;
 
 	/*
-	 * This assumes that the display controller will divide its parent
-	 * clock by 2 to generate the pixel clock.
+	 * This assumes that the parent clock is pll_d_out0 or pll_d2_out
+	 * respectively, each of which divides the base pll_d by 2.
 	 */
-	err = tegra_output_setup_clock(output, dc->clk, pclk * 2);
+	err = tegra_output_setup_clock(output, dc->clk, pclk, &div);
 	if (err < 0) {
 		dev_err(dc->dev, "failed to setup clock: %ld\n", err);
 		return err;
 	}
 
-	rate = clk_get_rate(dc->clk);
-	*div = (rate * 2 / pclk) - 2;
-
-	DRM_DEBUG_KMS("rate: %lu, div: %lu\n", rate, *div);
-
-	return 0;
-}
-
-static bool tegra_dc_format_is_yuv(unsigned int format, bool *planar)
-{
-	switch (format) {
-	case WIN_COLOR_DEPTH_YCbCr422:
-	case WIN_COLOR_DEPTH_YUV422:
-		if (planar)
-			*planar = false;
-
-		return true;
-
-	case WIN_COLOR_DEPTH_YCbCr420P:
-	case WIN_COLOR_DEPTH_YUV420P:
-	case WIN_COLOR_DEPTH_YCbCr422P:
-	case WIN_COLOR_DEPTH_YUV422P:
-	case WIN_COLOR_DEPTH_YCbCr422R:
-	case WIN_COLOR_DEPTH_YUV422R:
-	case WIN_COLOR_DEPTH_YCbCr422RA:
-	case WIN_COLOR_DEPTH_YUV422RA:
-		if (planar)
-			*planar = true;
-
-		return true;
-	}
-
-	return false;
-}
-
-int tegra_dc_setup_window(struct tegra_dc *dc, unsigned int index,
-			  const struct tegra_dc_window *window)
-{
-	unsigned h_offset, v_offset, h_size, v_size, h_dda, v_dda, bpp;
-	unsigned long value;
-	bool yuv, planar;
-
-	/*
-	 * For YUV planar modes, the number of bytes per pixel takes into
-	 * account only the luma component and therefore is 1.
-	 */
-	yuv = tegra_dc_format_is_yuv(window->format, &planar);
-	if (!yuv)
-		bpp = window->bits_per_pixel / 8;
-	else
-		bpp = planar ? 1 : 2;
-
-	value = WINDOW_A_SELECT << index;
-	tegra_dc_writel(dc, value, DC_CMD_DISPLAY_WINDOW_HEADER);
-
-	tegra_dc_writel(dc, window->format, DC_WIN_COLOR_DEPTH);
-	tegra_dc_writel(dc, 0, DC_WIN_BYTE_SWAP);
-
-	value = V_POSITION(window->dst.y) | H_POSITION(window->dst.x);
-	tegra_dc_writel(dc, value, DC_WIN_POSITION);
-
-	value = V_SIZE(window->dst.h) | H_SIZE(window->dst.w);
-	tegra_dc_writel(dc, value, DC_WIN_SIZE);
-
-	h_offset = window->src.x * bpp;
-	v_offset = window->src.y;
-	h_size = window->src.w * bpp;
-	v_size = window->src.h;
-
-	value = V_PRESCALED_SIZE(v_size) | H_PRESCALED_SIZE(h_size);
-	tegra_dc_writel(dc, value, DC_WIN_PRESCALED_SIZE);
-
-	/*
-	 * For DDA computations the number of bytes per pixel for YUV planar
-	 * modes needs to take into account all Y, U and V components.
-	 */
-	if (yuv && planar)
-		bpp = 2;
-
-	h_dda = compute_dda_inc(window->src.w, window->dst.w, false, bpp);
-	v_dda = compute_dda_inc(window->src.h, window->dst.h, true, bpp);
-
-	value = V_DDA_INC(v_dda) | H_DDA_INC(h_dda);
-	tegra_dc_writel(dc, value, DC_WIN_DDA_INC);
-
-	h_dda = compute_initial_dda(window->src.x);
-	v_dda = compute_initial_dda(window->src.y);
-
-	tegra_dc_writel(dc, h_dda, DC_WIN_H_INITIAL_DDA);
-	tegra_dc_writel(dc, v_dda, DC_WIN_V_INITIAL_DDA);
-
-	tegra_dc_writel(dc, 0, DC_WIN_UV_BUF_STRIDE);
-	tegra_dc_writel(dc, 0, DC_WIN_BUF_STRIDE);
-
-	tegra_dc_writel(dc, window->base[0], DC_WINBUF_START_ADDR);
-
-	if (yuv && planar) {
-		tegra_dc_writel(dc, window->base[1], DC_WINBUF_START_ADDR_U);
-		tegra_dc_writel(dc, window->base[2], DC_WINBUF_START_ADDR_V);
-		value = window->stride[1] << 16 | window->stride[0];
-		tegra_dc_writel(dc, value, DC_WIN_LINE_STRIDE);
-	} else {
-		tegra_dc_writel(dc, window->stride[0], DC_WIN_LINE_STRIDE);
-	}
-
-	if (window->bottom_up)
-		v_offset += window->src.h - 1;
+	DRM_DEBUG_KMS("rate: %lu, div: %u\n", clk_get_rate(dc->clk), div);
 
-	tegra_dc_writel(dc, h_offset, DC_WINBUF_ADDR_H_OFFSET);
-	tegra_dc_writel(dc, v_offset, DC_WINBUF_ADDR_V_OFFSET);
-
-	if (window->tiled) {
-		value = DC_WIN_BUFFER_ADDR_MODE_TILE_UV |
-			DC_WIN_BUFFER_ADDR_MODE_TILE;
-	} else {
-		value = DC_WIN_BUFFER_ADDR_MODE_LINEAR_UV |
-			DC_WIN_BUFFER_ADDR_MODE_LINEAR;
-	}
-
-	tegra_dc_writel(dc, value, DC_WIN_BUFFER_ADDR_MODE);
-
-	value = WIN_ENABLE;
-
-	if (yuv) {
-		/* setup default colorspace conversion coefficients */
-		tegra_dc_writel(dc, 0x00f0, DC_WIN_CSC_YOF);
-		tegra_dc_writel(dc, 0x012a, DC_WIN_CSC_KYRGB);
-		tegra_dc_writel(dc, 0x0000, DC_WIN_CSC_KUR);
-		tegra_dc_writel(dc, 0x0198, DC_WIN_CSC_KVR);
-		tegra_dc_writel(dc, 0x039b, DC_WIN_CSC_KUG);
-		tegra_dc_writel(dc, 0x032f, DC_WIN_CSC_KVG);
-		tegra_dc_writel(dc, 0x0204, DC_WIN_CSC_KUB);
-		tegra_dc_writel(dc, 0x0000, DC_WIN_CSC_KVB);
-
-		value |= CSC_ENABLE;
-	} else if (window->bits_per_pixel < 24) {
-		value |= COLOR_EXPAND;
-	}
-
-	if (window->bottom_up)
-		value |= INVERT_V;
-
-	tegra_dc_writel(dc, value, DC_WIN_WIN_OPTIONS);
-
-	/*
-	 * Disable blending and assume Window A is the bottom-most window,
-	 * Window C is the top-most window and Window B is in the middle.
-	 */
-	tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_NOKEY);
-	tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_1WIN);
-
-	switch (index) {
-	case 0:
-		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_2WIN_X);
-		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_2WIN_Y);
-		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_3WIN_XY);
-		break;
-
-	case 1:
-		tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_2WIN_X);
-		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_2WIN_Y);
-		tegra_dc_writel(dc, 0x000000, DC_WIN_BLEND_3WIN_XY);
-		break;
-
-	case 2:
-		tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_2WIN_X);
-		tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_2WIN_Y);
-		tegra_dc_writel(dc, 0xffff00, DC_WIN_BLEND_3WIN_XY);
-		break;
-	}
-
-	tegra_dc_writel(dc, WIN_A_UPDATE << index, DC_CMD_STATE_CONTROL);
-	tegra_dc_writel(dc, WIN_A_ACT_REQ << index, DC_CMD_STATE_CONTROL);
+	value = SHIFT_CLK_DIVIDER(div) | PIXEL_CLK_DIVIDER_PCD1;
+	tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL);
 
 	return 0;
 }
 
-unsigned int tegra_dc_format(uint32_t format)
-{
-	switch (format) {
-	case DRM_FORMAT_XBGR8888:
-		return WIN_COLOR_DEPTH_R8G8B8A8;
-
-	case DRM_FORMAT_XRGB8888:
-		return WIN_COLOR_DEPTH_B8G8R8A8;
-
-	case DRM_FORMAT_RGB565:
-		return WIN_COLOR_DEPTH_B5G6R5;
-
-	case DRM_FORMAT_UYVY:
-		return WIN_COLOR_DEPTH_YCbCr422;
-
-	case DRM_FORMAT_YUV420:
-		return WIN_COLOR_DEPTH_YCbCr420P;
-
-	case DRM_FORMAT_YUV422:
-		return WIN_COLOR_DEPTH_YCbCr422P;
-
-	default:
-		break;
-	}
-
-	WARN(1, "unsupported pixel format %u, using default\n", format);
-	return WIN_COLOR_DEPTH_B8G8R8A8;
-}
-
 static int tegra_crtc_mode_set(struct drm_crtc *crtc,
 			       struct drm_display_mode *mode,
 			       struct drm_display_mode *adjusted,
@@ -648,12 +768,12 @@ static int tegra_crtc_mode_set(struct drm_crtc *crtc,
 	struct tegra_bo *bo = tegra_fb_get_plane(crtc->primary->fb, 0);
 	struct tegra_dc *dc = to_tegra_dc(crtc);
 	struct tegra_dc_window window;
-	unsigned long div, value;
+	u32 value;
 	int err;
 
 	drm_vblank_pre_modeset(crtc->dev, dc->pipe);
 
-	err = tegra_crtc_setup_clk(crtc, mode, &div);
+	err = tegra_crtc_setup_clk(crtc, mode);
 	if (err) {
 		dev_err(dc->dev, "failed to setup clock for CRTC: %d\n", err);
 		return err;
@@ -669,9 +789,6 @@ static int tegra_crtc_mode_set(struct drm_crtc *crtc,
 		tegra_dc_writel(dc, value, DC_DISP_INTERLACE_CONTROL);
 	}
 
-	value = SHIFT_CLK_DIVIDER(div) | PIXEL_CLK_DIVIDER_PCD1;
-	tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL);
-
 	/* setup window parameters */
 	memset(&window, 0, sizeof(window));
 	window.src.x = 0;
@@ -682,7 +799,8 @@ static int tegra_crtc_mode_set(struct drm_crtc *crtc,
 	window.dst.y = 0;
 	window.dst.w = mode->hdisplay;
 	window.dst.h = mode->vdisplay;
-	window.format = tegra_dc_format(crtc->primary->fb->pixel_format);
+	window.format = tegra_dc_format(crtc->primary->fb->pixel_format,
+					&window.swap);
 	window.bits_per_pixel = crtc->primary->fb->bits_per_pixel;
 	window.stride[0] = crtc->primary->fb->pitches[0];
 	window.base[0] = bo->paddr;
@@ -728,10 +846,6 @@ static void tegra_crtc_prepare(struct drm_crtc *crtc)
 		WIN_A_OF_INT | WIN_B_OF_INT | WIN_C_OF_INT;
 	tegra_dc_writel(dc, value, DC_CMD_INT_POLARITY);
 
-	value = PW0_ENABLE | PW1_ENABLE | PW2_ENABLE | PW3_ENABLE |
-		PW4_ENABLE | PM0_ENABLE | PM1_ENABLE;
-	tegra_dc_writel(dc, value, DC_CMD_DISPLAY_POWER_CONTROL);
-
 	/* initialize timer */
 	value = CURSOR_THRESHOLD(0) | WINDOW_A_THRESHOLD(0x20) |
 		WINDOW_B_THRESHOLD(0x20) | WINDOW_C_THRESHOLD(0x20);
@@ -991,6 +1105,8 @@ static int tegra_dc_show_regs(struct seq_file *s, void *data)
 	DUMP_REG(DC_DISP_SD_BL_CONTROL);
 	DUMP_REG(DC_DISP_SD_HW_K_VALUES);
 	DUMP_REG(DC_DISP_SD_MAN_K_VALUES);
+	DUMP_REG(DC_DISP_CURSOR_START_ADDR_HI);
+	DUMP_REG(DC_DISP_BLEND_CURSOR_CONTROL);
 	DUMP_REG(DC_WIN_WIN_OPTIONS);
 	DUMP_REG(DC_WIN_BYTE_SWAP);
 	DUMP_REG(DC_WIN_BUFFER_CONTROL);
@@ -1096,26 +1212,26 @@ static int tegra_dc_debugfs_exit(struct tegra_dc *dc)
 
 static int tegra_dc_init(struct host1x_client *client)
 {
-	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->parent);
 	struct tegra_dc *dc = host1x_client_to_dc(client);
 	int err;
 
-	drm_crtc_init(tegra->drm, &dc->base, &tegra_crtc_funcs);
+	drm_crtc_init(drm, &dc->base, &tegra_crtc_funcs);
 	drm_mode_crtc_set_gamma_size(&dc->base, 256);
 	drm_crtc_helper_add(&dc->base, &tegra_crtc_helper_funcs);
 
-	err = tegra_dc_rgb_init(tegra->drm, dc);
+	err = tegra_dc_rgb_init(drm, dc);
 	if (err < 0 && err != -ENODEV) {
 		dev_err(dc->dev, "failed to initialize RGB output: %d\n", err);
 		return err;
 	}
 
-	err = tegra_dc_add_planes(tegra->drm, dc);
+	err = tegra_dc_add_planes(drm, dc);
 	if (err < 0)
 		return err;
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
-		err = tegra_dc_debugfs_init(dc, tegra->drm->primary);
+		err = tegra_dc_debugfs_init(dc, drm->primary);
 		if (err < 0)
 			dev_err(dc->dev, "debugfs setup failed: %d\n", err);
 	}
@@ -1160,14 +1276,17 @@ static const struct host1x_client_ops dc_client_ops = {
 
 static const struct tegra_dc_soc_info tegra20_dc_soc_info = {
 	.supports_interlacing = false,
+	.supports_cursor = false,
 };
 
 static const struct tegra_dc_soc_info tegra30_dc_soc_info = {
 	.supports_interlacing = false,
+	.supports_cursor = false,
 };
 
 static const struct tegra_dc_soc_info tegra124_dc_soc_info = {
 	.supports_interlacing = true,
+	.supports_cursor = true,
 };
 
 static const struct of_device_id tegra_dc_of_match[] = {
diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h
index c9410149482..78c5feff95d 100644
--- a/drivers/gpu/drm/tegra/dc.h
+++ b/drivers/gpu/drm/tegra/dc.h
@@ -67,10 +67,12 @@
 #define WIN_A_ACT_REQ   (1 <<  1)
 #define WIN_B_ACT_REQ   (1 <<  2)
 #define WIN_C_ACT_REQ   (1 <<  3)
+#define CURSOR_ACT_REQ  (1 <<  7)
 #define GENERAL_UPDATE  (1 <<  8)
 #define WIN_A_UPDATE    (1 <<  9)
 #define WIN_B_UPDATE    (1 << 10)
 #define WIN_C_UPDATE    (1 << 11)
+#define CURSOR_UPDATE   (1 << 15)
 #define NC_HOST_TRIG    (1 << 24)
 
 #define DC_CMD_DISPLAY_WINDOW_HEADER		0x042
@@ -116,9 +118,10 @@
 #define DC_DISP_DISP_SIGNAL_OPTIONS1		0x401
 
 #define DC_DISP_DISP_WIN_OPTIONS		0x402
-#define HDMI_ENABLE (1 << 30)
-#define DSI_ENABLE  (1 << 29)
-#define SOR_ENABLE  (1 << 25)
+#define HDMI_ENABLE	(1 << 30)
+#define DSI_ENABLE	(1 << 29)
+#define SOR_ENABLE	(1 << 25)
+#define CURSOR_ENABLE	(1 << 16)
 
 #define DC_DISP_DISP_MEM_HIGH_PRIORITY		0x403
 #define CURSOR_THRESHOLD(x)   (((x) & 0x03) << 24)
@@ -266,6 +269,14 @@
 #define DC_DISP_CURSOR_BACKGROUND		0x43d
 
 #define DC_DISP_CURSOR_START_ADDR		0x43e
+#define CURSOR_CLIP_DISPLAY	(0 << 28)
+#define CURSOR_CLIP_WIN_A	(1 << 28)
+#define CURSOR_CLIP_WIN_B	(2 << 28)
+#define CURSOR_CLIP_WIN_C	(3 << 28)
+#define CURSOR_SIZE_32x32	(0 << 24)
+#define CURSOR_SIZE_64x64	(1 << 24)
+#define CURSOR_SIZE_128x128	(2 << 24)
+#define CURSOR_SIZE_256x256	(3 << 24)
 #define DC_DISP_CURSOR_START_ADDR_NS		0x43f
 
 #define DC_DISP_CURSOR_POSITION			0x440
@@ -302,6 +313,19 @@
 #define  INTERLACE_START  (1 << 1)
 #define  INTERLACE_ENABLE (1 << 0)
 
+#define DC_DISP_CURSOR_START_ADDR_HI		0x4ec
+#define DC_DISP_BLEND_CURSOR_CONTROL		0x4f1
+#define CURSOR_MODE_LEGACY			(0 << 24)
+#define CURSOR_MODE_NORMAL			(1 << 24)
+#define CURSOR_DST_BLEND_ZERO			(0 << 16)
+#define CURSOR_DST_BLEND_K1			(1 << 16)
+#define CURSOR_DST_BLEND_NEG_K1_TIMES_SRC	(2 << 16)
+#define CURSOR_DST_BLEND_MASK			(3 << 16)
+#define CURSOR_SRC_BLEND_K1			(0 << 8)
+#define CURSOR_SRC_BLEND_K1_TIMES_SRC		(1 << 8)
+#define CURSOR_SRC_BLEND_MASK			(3 << 8)
+#define CURSOR_ALPHA				0xff
+
 #define DC_WIN_CSC_YOF				0x611
 #define DC_WIN_CSC_KYRGB			0x612
 #define DC_WIN_CSC_KUR				0x613
@@ -312,7 +336,8 @@
 #define DC_WIN_CSC_KVB				0x618
 
 #define DC_WIN_WIN_OPTIONS			0x700
-#define INVERT_V     (1 <<  2)
+#define H_DIRECTION  (1 <<  0)
+#define V_DIRECTION  (1 <<  2)
 #define COLOR_EXPAND (1 <<  6)
 #define CSC_ENABLE   (1 << 18)
 #define WIN_ENABLE   (1 << 30)
diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c
index 005c19bd92d..3f132e356e9 100644
--- a/drivers/gpu/drm/tegra/dpaux.c
+++ b/drivers/gpu/drm/tegra/dpaux.c
@@ -15,6 +15,7 @@
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/regulator/consumer.h>
+#include <linux/workqueue.h>
 
 #include <drm/drm_dp_helper.h>
 #include <drm/drm_panel.h>
@@ -41,6 +42,7 @@ struct tegra_dpaux {
 	struct regulator *vdd;
 
 	struct completion complete;
+	struct work_struct work;
 	struct list_head list;
 };
 
@@ -49,6 +51,11 @@ static inline struct tegra_dpaux *to_dpaux(struct drm_dp_aux *aux)
 	return container_of(aux, struct tegra_dpaux, aux);
 }
 
+static inline struct tegra_dpaux *work_to_dpaux(struct work_struct *work)
+{
+	return container_of(work, struct tegra_dpaux, work);
+}
+
 static inline unsigned long tegra_dpaux_readl(struct tegra_dpaux *dpaux,
 					      unsigned long offset)
 {
@@ -231,6 +238,14 @@ static ssize_t tegra_dpaux_transfer(struct drm_dp_aux *aux,
 	return ret;
 }
 
+static void tegra_dpaux_hotplug(struct work_struct *work)
+{
+	struct tegra_dpaux *dpaux = work_to_dpaux(work);
+
+	if (dpaux->output)
+		drm_helper_hpd_irq_event(dpaux->output->connector.dev);
+}
+
 static irqreturn_t tegra_dpaux_irq(int irq, void *data)
 {
 	struct tegra_dpaux *dpaux = data;
@@ -241,16 +256,8 @@ static irqreturn_t tegra_dpaux_irq(int irq, void *data)
 	value = tegra_dpaux_readl(dpaux, DPAUX_INTR_AUX);
 	tegra_dpaux_writel(dpaux, value, DPAUX_INTR_AUX);
 
-	if (value & DPAUX_INTR_PLUG_EVENT) {
-		if (dpaux->output) {
-			drm_helper_hpd_irq_event(dpaux->output->connector.dev);
-		}
-	}
-
-	if (value & DPAUX_INTR_UNPLUG_EVENT) {
-		if (dpaux->output)
-			drm_helper_hpd_irq_event(dpaux->output->connector.dev);
-	}
+	if (value & (DPAUX_INTR_PLUG_EVENT | DPAUX_INTR_UNPLUG_EVENT))
+		schedule_work(&dpaux->work);
 
 	if (value & DPAUX_INTR_IRQ_EVENT) {
 		/* TODO: handle this */
@@ -273,6 +280,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev)
 	if (!dpaux)
 		return -ENOMEM;
 
+	INIT_WORK(&dpaux->work, tegra_dpaux_hotplug);
 	init_completion(&dpaux->complete);
 	INIT_LIST_HEAD(&dpaux->list);
 	dpaux->dev = &pdev->dev;
@@ -332,7 +340,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev)
 	dpaux->aux.transfer = tegra_dpaux_transfer;
 	dpaux->aux.dev = &pdev->dev;
 
-	err = drm_dp_aux_register_i2c_bus(&dpaux->aux);
+	err = drm_dp_aux_register(&dpaux->aux);
 	if (err < 0)
 		return err;
 
@@ -355,12 +363,14 @@ static int tegra_dpaux_remove(struct platform_device *pdev)
 {
 	struct tegra_dpaux *dpaux = platform_get_drvdata(pdev);
 
-	drm_dp_aux_unregister_i2c_bus(&dpaux->aux);
+	drm_dp_aux_unregister(&dpaux->aux);
 
 	mutex_lock(&dpaux_lock);
 	list_del(&dpaux->list);
 	mutex_unlock(&dpaux_lock);
 
+	cancel_work_sync(&dpaux->work);
+
 	clk_disable_unprepare(dpaux->clk_parent);
 	reset_control_assert(dpaux->rst);
 	clk_disable_unprepare(dpaux->clk);
@@ -404,6 +414,7 @@ int tegra_dpaux_attach(struct tegra_dpaux *dpaux, struct tegra_output *output)
 	unsigned long timeout;
 	int err;
 
+	output->connector.polled = DRM_CONNECTOR_POLL_HPD;
 	dpaux->output = output;
 
 	err = regulator_enable(dpaux->vdd);
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 6f5b6e2f552..3396f9f6a9f 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -33,7 +33,6 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 	if (!tegra)
 		return -ENOMEM;
 
-	dev_set_drvdata(drm->dev, tegra);
 	mutex_init(&tegra->clients_lock);
 	INIT_LIST_HEAD(&tegra->clients);
 	drm->dev_private = tegra;
@@ -640,14 +639,40 @@ int tegra_drm_unregister_client(struct tegra_drm *tegra,
 	return 0;
 }
 
-static int host1x_drm_probe(struct host1x_device *device)
+static int host1x_drm_probe(struct host1x_device *dev)
 {
-	return drm_host1x_init(&tegra_drm_driver, device);
+	struct drm_driver *driver = &tegra_drm_driver;
+	struct drm_device *drm;
+	int err;
+
+	drm = drm_dev_alloc(driver, &dev->dev);
+	if (!drm)
+		return -ENOMEM;
+
+	drm_dev_set_unique(drm, dev_name(&dev->dev));
+	dev_set_drvdata(&dev->dev, drm);
+
+	err = drm_dev_register(drm, 0);
+	if (err < 0)
+		goto unref;
+
+	DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n", driver->name,
+		 driver->major, driver->minor, driver->patchlevel,
+		 driver->date, drm->primary->index);
+
+	return 0;
+
+unref:
+	drm_dev_unref(drm);
+	return err;
 }
 
-static int host1x_drm_remove(struct host1x_device *device)
+static int host1x_drm_remove(struct host1x_device *dev)
 {
-	drm_host1x_exit(&tegra_drm_driver, device);
+	struct drm_device *drm = dev_get_drvdata(&dev->dev);
+
+	drm_dev_unregister(drm);
+	drm_dev_unref(drm);
 
 	return 0;
 }
@@ -666,6 +691,7 @@ static const struct of_device_id host1x_drm_subdevs[] = {
 	{ .compatible = "nvidia,tegra114-gr3d", },
 	{ .compatible = "nvidia,tegra124-dc", },
 	{ .compatible = "nvidia,tegra124-sor", },
+	{ .compatible = "nvidia,tegra124-hdmi", },
 	{ /* sentinel */ }
 };
 
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index 126332c3ecb..6b8fe9d86ed 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -80,13 +80,13 @@ host1x_to_drm_client(struct host1x_client *client)
 	return container_of(client, struct tegra_drm_client, base);
 }
 
-extern int tegra_drm_register_client(struct tegra_drm *tegra,
-				     struct tegra_drm_client *client);
-extern int tegra_drm_unregister_client(struct tegra_drm *tegra,
-				       struct tegra_drm_client *client);
+int tegra_drm_register_client(struct tegra_drm *tegra,
+			      struct tegra_drm_client *client);
+int tegra_drm_unregister_client(struct tegra_drm *tegra,
+				struct tegra_drm_client *client);
 
-extern int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm);
-extern int tegra_drm_exit(struct tegra_drm *tegra);
+int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm);
+int tegra_drm_exit(struct tegra_drm *tegra);
 
 struct tegra_dc_soc_info;
 struct tegra_output;
@@ -156,6 +156,7 @@ struct tegra_dc_window {
 	} dst;
 	unsigned int bits_per_pixel;
 	unsigned int format;
+	unsigned int swap;
 	unsigned int stride[2];
 	unsigned long base[3];
 	bool bottom_up;
@@ -163,19 +164,15 @@ struct tegra_dc_window {
 };
 
 /* from dc.c */
-extern unsigned int tegra_dc_format(uint32_t format);
-extern int tegra_dc_setup_window(struct tegra_dc *dc, unsigned int index,
-				 const struct tegra_dc_window *window);
-extern void tegra_dc_enable_vblank(struct tegra_dc *dc);
-extern void tegra_dc_disable_vblank(struct tegra_dc *dc);
-extern void tegra_dc_cancel_page_flip(struct drm_crtc *crtc,
-				      struct drm_file *file);
+void tegra_dc_enable_vblank(struct tegra_dc *dc);
+void tegra_dc_disable_vblank(struct tegra_dc *dc);
+void tegra_dc_cancel_page_flip(struct drm_crtc *crtc, struct drm_file *file);
 
 struct tegra_output_ops {
 	int (*enable)(struct tegra_output *output);
 	int (*disable)(struct tegra_output *output);
 	int (*setup_clock)(struct tegra_output *output, struct clk *clk,
-			   unsigned long pclk);
+			   unsigned long pclk, unsigned int *div);
 	int (*check_mode)(struct tegra_output *output,
 			  struct drm_display_mode *mode,
 			  enum drm_mode_status *status);
@@ -233,10 +230,11 @@ static inline int tegra_output_disable(struct tegra_output *output)
 }
 
 static inline int tegra_output_setup_clock(struct tegra_output *output,
-					   struct clk *clk, unsigned long pclk)
+					   struct clk *clk, unsigned long pclk,
+					   unsigned int *div)
 {
 	if (output && output->ops && output->ops->setup_clock)
-		return output->ops->setup_clock(output, clk, pclk);
+		return output->ops->setup_clock(output, clk, pclk, div);
 
 	return output ? -ENOSYS : -EINVAL;
 }
@@ -251,27 +249,21 @@ static inline int tegra_output_check_mode(struct tegra_output *output,
 	return output ? -ENOSYS : -EINVAL;
 }
 
-/* from bus.c */
-int drm_host1x_init(struct drm_driver *driver, struct host1x_device *device);
-void drm_host1x_exit(struct drm_driver *driver, struct host1x_device *device);
-
 /* from rgb.c */
-extern int tegra_dc_rgb_probe(struct tegra_dc *dc);
-extern int tegra_dc_rgb_remove(struct tegra_dc *dc);
-extern int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc);
-extern int tegra_dc_rgb_exit(struct tegra_dc *dc);
+int tegra_dc_rgb_probe(struct tegra_dc *dc);
+int tegra_dc_rgb_remove(struct tegra_dc *dc);
+int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc);
+int tegra_dc_rgb_exit(struct tegra_dc *dc);
 
 /* from output.c */
-extern int tegra_output_probe(struct tegra_output *output);
-extern int tegra_output_remove(struct tegra_output *output);
-extern int tegra_output_init(struct drm_device *drm, struct tegra_output *output);
-extern int tegra_output_exit(struct tegra_output *output);
+int tegra_output_probe(struct tegra_output *output);
+int tegra_output_remove(struct tegra_output *output);
+int tegra_output_init(struct drm_device *drm, struct tegra_output *output);
+int tegra_output_exit(struct tegra_output *output);
 
 /* from dpaux.c */
-
 struct tegra_dpaux;
 struct drm_dp_link;
-struct drm_dp_aux;
 
 struct tegra_dpaux *tegra_dpaux_find_by_of_node(struct device_node *np);
 enum drm_connector_status tegra_dpaux_detect(struct tegra_dpaux *dpaux);
@@ -288,10 +280,10 @@ struct tegra_bo *tegra_fb_get_plane(struct drm_framebuffer *framebuffer,
 				    unsigned int index);
 bool tegra_fb_is_bottom_up(struct drm_framebuffer *framebuffer);
 bool tegra_fb_is_tiled(struct drm_framebuffer *framebuffer);
-extern int tegra_drm_fb_init(struct drm_device *drm);
-extern void tegra_drm_fb_exit(struct drm_device *drm);
+int tegra_drm_fb_init(struct drm_device *drm);
+void tegra_drm_fb_exit(struct drm_device *drm);
 #ifdef CONFIG_DRM_TEGRA_FBDEV
-extern void tegra_fbdev_restore_mode(struct tegra_fbdev *fbdev);
+void tegra_fbdev_restore_mode(struct tegra_fbdev *fbdev);
 #endif
 
 extern struct platform_driver tegra_dc_driver;
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 0e599f0417c..bd56f2affa7 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -14,6 +14,8 @@
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 
+#include <linux/regulator/consumer.h>
+
 #include <drm/drm_mipi_dsi.h>
 #include <drm/drm_panel.h>
 
@@ -43,11 +45,15 @@ struct tegra_dsi {
 	struct drm_minor *minor;
 	struct dentry *debugfs;
 
+	unsigned long flags;
 	enum mipi_dsi_pixel_format format;
 	unsigned int lanes;
 
 	struct tegra_mipi_device *mipi;
 	struct mipi_dsi_host host;
+
+	struct regulator *vdd;
+	bool enabled;
 };
 
 static inline struct tegra_dsi *
@@ -244,8 +250,10 @@ static int tegra_dsi_debugfs_exit(struct tegra_dsi *dsi)
 #define PKT_LP		(1 << 30)
 #define NUM_PKT_SEQ	12
 
-/* non-burst mode with sync-end */
-static const u32 pkt_seq_vnb_syne[NUM_PKT_SEQ] = {
+/*
+ * non-burst mode with sync pulses
+ */
+static const u32 pkt_seq_video_non_burst_sync_pulses[NUM_PKT_SEQ] = {
 	[ 0] = PKT_ID0(MIPI_DSI_V_SYNC_START) | PKT_LEN0(0) |
 	       PKT_ID1(MIPI_DSI_BLANKING_PACKET) | PKT_LEN1(1) |
 	       PKT_ID2(MIPI_DSI_H_SYNC_END) | PKT_LEN2(0) |
@@ -280,6 +288,36 @@ static const u32 pkt_seq_vnb_syne[NUM_PKT_SEQ] = {
 	       PKT_ID2(MIPI_DSI_BLANKING_PACKET) | PKT_LEN2(4),
 };
 
+/*
+ * non-burst mode with sync events
+ */
+static const u32 pkt_seq_video_non_burst_sync_events[NUM_PKT_SEQ] = {
+	[ 0] = PKT_ID0(MIPI_DSI_V_SYNC_START) | PKT_LEN0(0) |
+	       PKT_ID1(MIPI_DSI_END_OF_TRANSMISSION) | PKT_LEN1(7) |
+	       PKT_LP,
+	[ 1] = 0,
+	[ 2] = PKT_ID0(MIPI_DSI_H_SYNC_START) | PKT_LEN0(0) |
+	       PKT_ID1(MIPI_DSI_END_OF_TRANSMISSION) | PKT_LEN1(7) |
+	       PKT_LP,
+	[ 3] = 0,
+	[ 4] = PKT_ID0(MIPI_DSI_H_SYNC_START) | PKT_LEN0(0) |
+	       PKT_ID1(MIPI_DSI_END_OF_TRANSMISSION) | PKT_LEN1(7) |
+	       PKT_LP,
+	[ 5] = 0,
+	[ 6] = PKT_ID0(MIPI_DSI_H_SYNC_START) | PKT_LEN0(0) |
+	       PKT_ID1(MIPI_DSI_BLANKING_PACKET) | PKT_LEN1(2) |
+	       PKT_ID2(MIPI_DSI_PACKED_PIXEL_STREAM_24) | PKT_LEN2(3),
+	[ 7] = PKT_ID0(MIPI_DSI_BLANKING_PACKET) | PKT_LEN0(4),
+	[ 8] = PKT_ID0(MIPI_DSI_H_SYNC_START) | PKT_LEN0(0) |
+	       PKT_ID1(MIPI_DSI_END_OF_TRANSMISSION) | PKT_LEN1(7) |
+	       PKT_LP,
+	[ 9] = 0,
+	[10] = PKT_ID0(MIPI_DSI_H_SYNC_START) | PKT_LEN0(0) |
+	       PKT_ID1(MIPI_DSI_BLANKING_PACKET) | PKT_LEN1(2) |
+	       PKT_ID2(MIPI_DSI_PACKED_PIXEL_STREAM_24) | PKT_LEN2(3),
+	[11] = PKT_ID0(MIPI_DSI_BLANKING_PACKET) | PKT_LEN0(4),
+};
+
 static int tegra_dsi_set_phy_timing(struct tegra_dsi *dsi)
 {
 	struct mipi_dphy_timing timing;
@@ -361,28 +399,70 @@ static int tegra_dsi_get_muldiv(enum mipi_dsi_pixel_format format,
 	return 0;
 }
 
+static int tegra_dsi_get_format(enum mipi_dsi_pixel_format format,
+				enum tegra_dsi_format *fmt)
+{
+	switch (format) {
+	case MIPI_DSI_FMT_RGB888:
+		*fmt = TEGRA_DSI_FORMAT_24P;
+		break;
+
+	case MIPI_DSI_FMT_RGB666:
+		*fmt = TEGRA_DSI_FORMAT_18NP;
+		break;
+
+	case MIPI_DSI_FMT_RGB666_PACKED:
+		*fmt = TEGRA_DSI_FORMAT_18P;
+		break;
+
+	case MIPI_DSI_FMT_RGB565:
+		*fmt = TEGRA_DSI_FORMAT_16P;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int tegra_output_dsi_enable(struct tegra_output *output)
 {
 	struct tegra_dc *dc = to_tegra_dc(output->encoder.crtc);
 	struct drm_display_mode *mode = &dc->base.mode;
 	unsigned int hact, hsw, hbp, hfp, i, mul, div;
 	struct tegra_dsi *dsi = to_dsi(output);
-	/* FIXME: don't hardcode this */
-	const u32 *pkt_seq = pkt_seq_vnb_syne;
+	enum tegra_dsi_format format;
 	unsigned long value;
+	const u32 *pkt_seq;
 	int err;
 
+	if (dsi->enabled)
+		return 0;
+
+	if (dsi->flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) {
+		DRM_DEBUG_KMS("Non-burst video mode with sync pulses\n");
+		pkt_seq = pkt_seq_video_non_burst_sync_pulses;
+	} else {
+		DRM_DEBUG_KMS("Non-burst video mode with sync events\n");
+		pkt_seq = pkt_seq_video_non_burst_sync_events;
+	}
+
 	err = tegra_dsi_get_muldiv(dsi->format, &mul, &div);
 	if (err < 0)
 		return err;
 
+	err = tegra_dsi_get_format(dsi->format, &format);
+	if (err < 0)
+		return err;
+
 	err = clk_enable(dsi->clk);
 	if (err < 0)
 		return err;
 
 	reset_control_deassert(dsi->rst);
 
-	value = DSI_CONTROL_CHANNEL(0) | DSI_CONTROL_FORMAT(dsi->format) |
+	value = DSI_CONTROL_CHANNEL(0) | DSI_CONTROL_FORMAT(format) |
 		DSI_CONTROL_LANES(dsi->lanes - 1) |
 		DSI_CONTROL_SOURCE(dc->pipe);
 	tegra_dsi_writel(dsi, value, DSI_CONTROL);
@@ -454,6 +534,8 @@ static int tegra_output_dsi_enable(struct tegra_output *output)
 	value |= DSI_POWER_CONTROL_ENABLE;
 	tegra_dsi_writel(dsi, value, DSI_POWER_CONTROL);
 
+	dsi->enabled = true;
+
 	return 0;
 }
 
@@ -463,9 +545,12 @@ static int tegra_output_dsi_disable(struct tegra_output *output)
 	struct tegra_dsi *dsi = to_dsi(output);
 	unsigned long value;
 
+	if (!dsi->enabled)
+		return 0;
+
 	/* disable DSI controller */
 	value = tegra_dsi_readl(dsi, DSI_POWER_CONTROL);
-	value &= DSI_POWER_CONTROL_ENABLE;
+	value &= ~DSI_POWER_CONTROL_ENABLE;
 	tegra_dsi_writel(dsi, value, DSI_POWER_CONTROL);
 
 	/*
@@ -492,30 +577,44 @@ static int tegra_output_dsi_disable(struct tegra_output *output)
 
 	clk_disable(dsi->clk);
 
+	dsi->enabled = false;
+
 	return 0;
 }
 
 static int tegra_output_dsi_setup_clock(struct tegra_output *output,
-					struct clk *clk, unsigned long pclk)
+					struct clk *clk, unsigned long pclk,
+					unsigned int *divp)
 {
 	struct tegra_dc *dc = to_tegra_dc(output->encoder.crtc);
 	struct drm_display_mode *mode = &dc->base.mode;
 	unsigned int timeout, mul, div, vrefresh;
 	struct tegra_dsi *dsi = to_dsi(output);
 	unsigned long bclk, plld, value;
-	struct clk *base;
 	int err;
 
 	err = tegra_dsi_get_muldiv(dsi->format, &mul, &div);
 	if (err < 0)
 		return err;
 
+	DRM_DEBUG_KMS("mul: %u, div: %u, lanes: %u\n", mul, div, dsi->lanes);
 	vrefresh = drm_mode_vrefresh(mode);
+	DRM_DEBUG_KMS("vrefresh: %u\n", vrefresh);
 
-	pclk = mode->htotal * mode->vtotal * vrefresh;
+	/* compute byte clock */
 	bclk = (pclk * mul) / (div * dsi->lanes);
-	plld = DIV_ROUND_UP(bclk * 8, 1000000);
-	pclk = (plld * 1000000) / 2;
+
+	/*
+	 * Compute bit clock and round up to the next MHz.
+	 */
+	plld = DIV_ROUND_UP(bclk * 8, 1000000) * 1000000;
+
+	/*
+	 * We divide the frequency by two here, but we make up for that by
+	 * setting the shift clock divider (further below) to half of the
+	 * correct value.
+	 */
+	plld /= 2;
 
 	err = clk_set_parent(clk, dsi->clk_parent);
 	if (err < 0) {
@@ -523,20 +622,26 @@ static int tegra_output_dsi_setup_clock(struct tegra_output *output,
 		return err;
 	}
 
-	base = clk_get_parent(dsi->clk_parent);
-
-	/*
-	 * This assumes that the parent clock is pll_d_out0 or pll_d2_out
-	 * respectively, each of which divides the base pll_d by 2.
-	 */
-	err = clk_set_rate(base, pclk * 2);
+	err = clk_set_rate(dsi->clk_parent, plld);
 	if (err < 0) {
 		dev_err(dsi->dev, "failed to set base clock rate to %lu Hz\n",
-			pclk * 2);
+			plld);
 		return err;
 	}
 
 	/*
+	 * Derive pixel clock from bit clock using the shift clock divider.
+	 * Note that this is only half of what we would expect, but we need
+	 * that to make up for the fact that we divided the bit clock by a
+	 * factor of two above.
+	 *
+	 * It's not clear exactly why this is necessary, but the display is
+	 * not working properly otherwise. Perhaps the PLLs cannot generate
+	 * frequencies sufficiently high.
+	 */
+	*divp = ((8 * mul) / (div * dsi->lanes)) - 2;
+
+	/*
 	 * XXX: Move the below somewhere else so that we don't need to have
 	 * access to the vrefresh in this function?
 	 */
@@ -610,61 +715,32 @@ static int tegra_dsi_pad_calibrate(struct tegra_dsi *dsi)
 
 static int tegra_dsi_init(struct host1x_client *client)
 {
-	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->parent);
 	struct tegra_dsi *dsi = host1x_client_to_dsi(client);
-	unsigned long value, i;
 	int err;
 
 	dsi->output.type = TEGRA_OUTPUT_DSI;
 	dsi->output.dev = client->dev;
 	dsi->output.ops = &dsi_ops;
 
-	err = tegra_output_init(tegra->drm, &dsi->output);
+	err = tegra_output_init(drm, &dsi->output);
 	if (err < 0) {
 		dev_err(client->dev, "output setup failed: %d\n", err);
 		return err;
 	}
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
-		err = tegra_dsi_debugfs_init(dsi, tegra->drm->primary);
+		err = tegra_dsi_debugfs_init(dsi, drm->primary);
 		if (err < 0)
 			dev_err(dsi->dev, "debugfs setup failed: %d\n", err);
 	}
 
-	/*
-	 * enable high-speed mode, checksum generation, ECC generation and
-	 * disable raw mode
-	 */
-	value = tegra_dsi_readl(dsi, DSI_HOST_CONTROL);
-	value |= DSI_HOST_CONTROL_ECC | DSI_HOST_CONTROL_CS |
-		 DSI_HOST_CONTROL_HS;
-	value &= ~DSI_HOST_CONTROL_RAW;
-	tegra_dsi_writel(dsi, value, DSI_HOST_CONTROL);
-
-	tegra_dsi_writel(dsi, 0, DSI_SOL_DELAY);
-	tegra_dsi_writel(dsi, 0, DSI_MAX_THRESHOLD);
-
-	tegra_dsi_writel(dsi, 0, DSI_INIT_SEQ_CONTROL);
-
-	for (i = 0; i < 8; i++) {
-		tegra_dsi_writel(dsi, 0, DSI_INIT_SEQ_DATA_0 + i);
-		tegra_dsi_writel(dsi, 0, DSI_INIT_SEQ_DATA_8 + i);
-	}
-
-	for (i = 0; i < 12; i++)
-		tegra_dsi_writel(dsi, 0, DSI_PKT_SEQ_0_LO + i);
-
-	tegra_dsi_writel(dsi, 0, DSI_DCS_CMDS);
-
 	err = tegra_dsi_pad_calibrate(dsi);
 	if (err < 0) {
 		dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
 		return err;
 	}
 
-	tegra_dsi_writel(dsi, DSI_POWER_CONTROL_ENABLE, DSI_POWER_CONTROL);
-	usleep_range(300, 1000);
-
 	return 0;
 }
 
@@ -715,66 +791,13 @@ static int tegra_dsi_setup_clocks(struct tegra_dsi *dsi)
 	return 0;
 }
 
-static void tegra_dsi_initialize(struct tegra_dsi *dsi)
-{
-	unsigned int i;
-
-	tegra_dsi_writel(dsi, 0, DSI_POWER_CONTROL);
-
-	tegra_dsi_writel(dsi, 0, DSI_INT_ENABLE);
-	tegra_dsi_writel(dsi, 0, DSI_INT_STATUS);
-	tegra_dsi_writel(dsi, 0, DSI_INT_MASK);
-
-	tegra_dsi_writel(dsi, 0, DSI_HOST_CONTROL);
-	tegra_dsi_writel(dsi, 0, DSI_CONTROL);
-
-	tegra_dsi_writel(dsi, 0, DSI_SOL_DELAY);
-	tegra_dsi_writel(dsi, 0, DSI_MAX_THRESHOLD);
-
-	tegra_dsi_writel(dsi, 0, DSI_INIT_SEQ_CONTROL);
-
-	for (i = 0; i < 8; i++) {
-		tegra_dsi_writel(dsi, 0, DSI_INIT_SEQ_DATA_0 + i);
-		tegra_dsi_writel(dsi, 0, DSI_INIT_SEQ_DATA_8 + i);
-	}
-
-	for (i = 0; i < 12; i++)
-		tegra_dsi_writel(dsi, 0, DSI_PKT_SEQ_0_LO + i);
-
-	tegra_dsi_writel(dsi, 0, DSI_DCS_CMDS);
-
-	for (i = 0; i < 4; i++)
-		tegra_dsi_writel(dsi, 0, DSI_PKT_LEN_0_1 + i);
-
-	tegra_dsi_writel(dsi, 0x00000000, DSI_PHY_TIMING_0);
-	tegra_dsi_writel(dsi, 0x00000000, DSI_PHY_TIMING_1);
-	tegra_dsi_writel(dsi, 0x000000ff, DSI_PHY_TIMING_2);
-	tegra_dsi_writel(dsi, 0x00000000, DSI_BTA_TIMING);
-
-	tegra_dsi_writel(dsi, 0, DSI_TIMEOUT_0);
-	tegra_dsi_writel(dsi, 0, DSI_TIMEOUT_1);
-	tegra_dsi_writel(dsi, 0, DSI_TO_TALLY);
-
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_0);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_CD);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CD_STATUS);
-	tegra_dsi_writel(dsi, 0, DSI_VIDEO_MODE_CONTROL);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_1);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_2);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_3);
-	tegra_dsi_writel(dsi, 0, DSI_PAD_CONTROL_4);
-
-	tegra_dsi_writel(dsi, 0, DSI_GANGED_MODE_CONTROL);
-	tegra_dsi_writel(dsi, 0, DSI_GANGED_MODE_START);
-	tegra_dsi_writel(dsi, 0, DSI_GANGED_MODE_SIZE);
-}
-
 static int tegra_dsi_host_attach(struct mipi_dsi_host *host,
 				 struct mipi_dsi_device *device)
 {
 	struct tegra_dsi *dsi = host_to_tegra(host);
 	struct tegra_output *output = &dsi->output;
 
+	dsi->flags = device->mode_flags;
 	dsi->format = device->format;
 	dsi->lanes = device->lanes;
 
@@ -829,6 +852,7 @@ static int tegra_dsi_probe(struct platform_device *pdev)
 	 * attaches to the DSI host, the parameters will be taken from
 	 * the attached device.
 	 */
+	dsi->flags = MIPI_DSI_MODE_VIDEO;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->lanes = 4;
 
@@ -872,6 +896,18 @@ static int tegra_dsi_probe(struct platform_device *pdev)
 		return err;
 	}
 
+	dsi->vdd = devm_regulator_get(&pdev->dev, "avdd-dsi-csi");
+	if (IS_ERR(dsi->vdd)) {
+		dev_err(&pdev->dev, "cannot get VDD supply\n");
+		return PTR_ERR(dsi->vdd);
+	}
+
+	err = regulator_enable(dsi->vdd);
+	if (err < 0) {
+		dev_err(&pdev->dev, "cannot enable VDD supply\n");
+		return err;
+	}
+
 	err = tegra_dsi_setup_clocks(dsi);
 	if (err < 0) {
 		dev_err(&pdev->dev, "cannot setup clocks\n");
@@ -883,8 +919,6 @@ static int tegra_dsi_probe(struct platform_device *pdev)
 	if (IS_ERR(dsi->regs))
 		return PTR_ERR(dsi->regs);
 
-	tegra_dsi_initialize(dsi);
-
 	dsi->mipi = tegra_mipi_request(&pdev->dev);
 	if (IS_ERR(dsi->mipi))
 		return PTR_ERR(dsi->mipi);
@@ -929,9 +963,11 @@ static int tegra_dsi_remove(struct platform_device *pdev)
 	mipi_dsi_host_unregister(&dsi->host);
 	tegra_mipi_free(dsi->mipi);
 
+	regulator_disable(dsi->vdd);
 	clk_disable_unprepare(dsi->clk_parent);
 	clk_disable_unprepare(dsi->clk_lp);
 	clk_disable_unprepare(dsi->clk);
+	reset_control_assert(dsi->rst);
 
 	err = tegra_output_remove(&dsi->output);
 	if (err < 0) {
diff --git a/drivers/gpu/drm/tegra/dsi.h b/drivers/gpu/drm/tegra/dsi.h
index 1db5cc24ea9..5ce610d08d7 100644
--- a/drivers/gpu/drm/tegra/dsi.h
+++ b/drivers/gpu/drm/tegra/dsi.h
@@ -117,4 +117,14 @@
 #define DSI_INIT_SEQ_DATA_14		0x5e
 #define DSI_INIT_SEQ_DATA_15		0x5f
 
+/*
+ * pixel format as used in the DSI_CONTROL_FORMAT field
+ */
+enum tegra_dsi_format {
+	TEGRA_DSI_FORMAT_16P,
+	TEGRA_DSI_FORMAT_18NP,
+	TEGRA_DSI_FORMAT_18P,
+	TEGRA_DSI_FORMAT_24P,
+};
+
 #endif
diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c
index f7fca09d492..9798a708032 100644
--- a/drivers/gpu/drm/tegra/fb.c
+++ b/drivers/gpu/drm/tegra/fb.c
@@ -346,11 +346,8 @@ static void tegra_fbdev_free(struct tegra_fbdev *fbdev)
 
 void tegra_fbdev_restore_mode(struct tegra_fbdev *fbdev)
 {
-	if (fbdev) {
-		drm_modeset_lock_all(fbdev->base.dev);
-		drm_fb_helper_restore_fbdev_mode(&fbdev->base);
-		drm_modeset_unlock_all(fbdev->base.dev);
-	}
+	if (fbdev)
+		drm_fb_helper_restore_fbdev_mode_unlocked(&fbdev->base);
 }
 
 static void tegra_fb_output_poll_changed(struct drm_device *drm)
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index bcf9895cef9..aa85b7b26f1 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -169,7 +169,8 @@ err:
 	return ERR_PTR(ret);
 }
 
-struct tegra_bo *tegra_bo_import(struct drm_device *drm, struct dma_buf *buf)
+static struct tegra_bo *tegra_bo_import(struct drm_device *drm,
+					struct dma_buf *buf)
 {
 	struct dma_buf_attachment *attach;
 	struct tegra_bo *bo;
diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c
index 2c7ca748edf..7c53941f2a9 100644
--- a/drivers/gpu/drm/tegra/gr2d.c
+++ b/drivers/gpu/drm/tegra/gr2d.c
@@ -28,7 +28,7 @@ static inline struct gr2d *to_gr2d(struct tegra_drm_client *client)
 static int gr2d_init(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->parent);
 	unsigned long flags = HOST1X_SYNCPT_HAS_BASE;
 	struct gr2d *gr2d = to_gr2d(drm);
 
@@ -42,17 +42,17 @@ static int gr2d_init(struct host1x_client *client)
 		return -ENOMEM;
 	}
 
-	return tegra_drm_register_client(tegra, drm);
+	return tegra_drm_register_client(dev->dev_private, drm);
 }
 
 static int gr2d_exit(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->parent);
 	struct gr2d *gr2d = to_gr2d(drm);
 	int err;
 
-	err = tegra_drm_unregister_client(tegra, drm);
+	err = tegra_drm_unregister_client(dev->dev_private, drm);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c
index 0cbb24b1ae0..30f5ba9bd6d 100644
--- a/drivers/gpu/drm/tegra/gr3d.c
+++ b/drivers/gpu/drm/tegra/gr3d.c
@@ -37,7 +37,7 @@ static inline struct gr3d *to_gr3d(struct tegra_drm_client *client)
 static int gr3d_init(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->parent);
 	unsigned long flags = HOST1X_SYNCPT_HAS_BASE;
 	struct gr3d *gr3d = to_gr3d(drm);
 
@@ -51,17 +51,17 @@ static int gr3d_init(struct host1x_client *client)
 		return -ENOMEM;
 	}
 
-	return tegra_drm_register_client(tegra, drm);
+	return tegra_drm_register_client(dev->dev_private, drm);
 }
 
 static int gr3d_exit(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->parent);
 	struct gr3d *gr3d = to_gr3d(drm);
 	int err;
 
-	err = tegra_drm_unregister_client(tegra, drm);
+	err = tegra_drm_unregister_client(dev->dev_private, drm);
 	if (err < 0)
 		return err;
 
diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c
index 6928015d11a..ba067bb767e 100644
--- a/drivers/gpu/drm/tegra/hdmi.c
+++ b/drivers/gpu/drm/tegra/hdmi.c
@@ -42,8 +42,9 @@ struct tegra_hdmi {
 	struct device *dev;
 	bool enabled;
 
-	struct regulator *vdd;
+	struct regulator *hdmi;
 	struct regulator *pll;
+	struct regulator *vdd;
 
 	void __iomem *regs;
 	unsigned int irq;
@@ -317,6 +318,85 @@ static const struct tmds_config tegra114_tmds_config[] = {
 	},
 };
 
+static const struct tmds_config tegra124_tmds_config[] = {
+	{ /* 480p/576p / 25.2MHz/27MHz modes */
+		.pclk = 27000000,
+		.pll0 = SOR_PLL_ICHPMP(1) | SOR_PLL_BG_V17_S(3) |
+			SOR_PLL_VCOCAP(0) | SOR_PLL_RESISTORSEL,
+		.pll1 = SOR_PLL_LOADADJ(3) | SOR_PLL_TMDS_TERMADJ(0),
+		.pe_current = PE_CURRENT0(PE_CURRENT_0_mA_T114) |
+			PE_CURRENT1(PE_CURRENT_0_mA_T114) |
+			PE_CURRENT2(PE_CURRENT_0_mA_T114) |
+			PE_CURRENT3(PE_CURRENT_0_mA_T114),
+		.drive_current =
+			DRIVE_CURRENT_LANE0_T114(DRIVE_CURRENT_10_400_mA_T114) |
+			DRIVE_CURRENT_LANE1_T114(DRIVE_CURRENT_10_400_mA_T114) |
+			DRIVE_CURRENT_LANE2_T114(DRIVE_CURRENT_10_400_mA_T114) |
+			DRIVE_CURRENT_LANE3_T114(DRIVE_CURRENT_10_400_mA_T114),
+		.peak_current = PEAK_CURRENT_LANE0(PEAK_CURRENT_0_000_mA) |
+			PEAK_CURRENT_LANE1(PEAK_CURRENT_0_000_mA) |
+			PEAK_CURRENT_LANE2(PEAK_CURRENT_0_000_mA) |
+			PEAK_CURRENT_LANE3(PEAK_CURRENT_0_000_mA),
+	}, { /* 720p / 74.25MHz modes */
+		.pclk = 74250000,
+		.pll0 = SOR_PLL_ICHPMP(1) | SOR_PLL_BG_V17_S(3) |
+			SOR_PLL_VCOCAP(1) | SOR_PLL_RESISTORSEL,
+		.pll1 = SOR_PLL_PE_EN | SOR_PLL_LOADADJ(3) |
+			SOR_PLL_TMDS_TERMADJ(0),
+		.pe_current = PE_CURRENT0(PE_CURRENT_15_mA_T114) |
+			PE_CURRENT1(PE_CURRENT_15_mA_T114) |
+			PE_CURRENT2(PE_CURRENT_15_mA_T114) |
+			PE_CURRENT3(PE_CURRENT_15_mA_T114),
+		.drive_current =
+			DRIVE_CURRENT_LANE0_T114(DRIVE_CURRENT_10_400_mA_T114) |
+			DRIVE_CURRENT_LANE1_T114(DRIVE_CURRENT_10_400_mA_T114) |
+			DRIVE_CURRENT_LANE2_T114(DRIVE_CURRENT_10_400_mA_T114) |
+			DRIVE_CURRENT_LANE3_T114(DRIVE_CURRENT_10_400_mA_T114),
+		.peak_current = PEAK_CURRENT_LANE0(PEAK_CURRENT_0_000_mA) |
+			PEAK_CURRENT_LANE1(PEAK_CURRENT_0_000_mA) |
+			PEAK_CURRENT_LANE2(PEAK_CURRENT_0_000_mA) |
+			PEAK_CURRENT_LANE3(PEAK_CURRENT_0_000_mA),
+	}, { /* 1080p / 148.5MHz modes */
+		.pclk = 148500000,
+		.pll0 = SOR_PLL_ICHPMP(1) | SOR_PLL_BG_V17_S(3) |
+			SOR_PLL_VCOCAP(3) | SOR_PLL_RESISTORSEL,
+		.pll1 = SOR_PLL_PE_EN | SOR_PLL_LOADADJ(3) |
+			SOR_PLL_TMDS_TERMADJ(0),
+		.pe_current = PE_CURRENT0(PE_CURRENT_10_mA_T114) |
+			PE_CURRENT1(PE_CURRENT_10_mA_T114) |
+			PE_CURRENT2(PE_CURRENT_10_mA_T114) |
+			PE_CURRENT3(PE_CURRENT_10_mA_T114),
+		.drive_current =
+			DRIVE_CURRENT_LANE0_T114(DRIVE_CURRENT_12_400_mA_T114) |
+			DRIVE_CURRENT_LANE1_T114(DRIVE_CURRENT_12_400_mA_T114) |
+			DRIVE_CURRENT_LANE2_T114(DRIVE_CURRENT_12_400_mA_T114) |
+			DRIVE_CURRENT_LANE3_T114(DRIVE_CURRENT_12_400_mA_T114),
+		.peak_current = PEAK_CURRENT_LANE0(PEAK_CURRENT_0_000_mA) |
+			PEAK_CURRENT_LANE1(PEAK_CURRENT_0_000_mA) |
+			PEAK_CURRENT_LANE2(PEAK_CURRENT_0_000_mA) |
+			PEAK_CURRENT_LANE3(PEAK_CURRENT_0_000_mA),
+	}, { /* 225/297MHz modes */
+		.pclk = UINT_MAX,
+		.pll0 = SOR_PLL_ICHPMP(1) | SOR_PLL_BG_V17_S(3) |
+			SOR_PLL_VCOCAP(0xf) | SOR_PLL_RESISTORSEL,
+		.pll1 = SOR_PLL_LOADADJ(3) | SOR_PLL_TMDS_TERMADJ(7)
+			| SOR_PLL_TMDS_TERM_ENABLE,
+		.pe_current = PE_CURRENT0(PE_CURRENT_0_mA_T114) |
+			PE_CURRENT1(PE_CURRENT_0_mA_T114) |
+			PE_CURRENT2(PE_CURRENT_0_mA_T114) |
+			PE_CURRENT3(PE_CURRENT_0_mA_T114),
+		.drive_current =
+			DRIVE_CURRENT_LANE0_T114(DRIVE_CURRENT_25_200_mA_T114) |
+			DRIVE_CURRENT_LANE1_T114(DRIVE_CURRENT_25_200_mA_T114) |
+			DRIVE_CURRENT_LANE2_T114(DRIVE_CURRENT_25_200_mA_T114) |
+			DRIVE_CURRENT_LANE3_T114(DRIVE_CURRENT_19_200_mA_T114),
+		.peak_current = PEAK_CURRENT_LANE0(PEAK_CURRENT_3_000_mA) |
+			PEAK_CURRENT_LANE1(PEAK_CURRENT_3_000_mA) |
+			PEAK_CURRENT_LANE2(PEAK_CURRENT_3_000_mA) |
+			PEAK_CURRENT_LANE3(PEAK_CURRENT_0_800_mA),
+	},
+};
+
 static const struct tegra_hdmi_audio_config *
 tegra_hdmi_get_audio_config(unsigned int audio_freq, unsigned int pclk)
 {
@@ -716,13 +796,9 @@ static int tegra_output_hdmi_enable(struct tegra_output *output)
 		return err;
 	}
 
-	/*
-	 * This assumes that the display controller will divide its parent
-	 * clock by 2 to generate the pixel clock.
-	 */
-	err = tegra_output_setup_clock(output, hdmi->clk, pclk * 2);
+	err = regulator_enable(hdmi->vdd);
 	if (err < 0) {
-		dev_err(hdmi->dev, "failed to setup clock: %d\n", err);
+		dev_err(hdmi->dev, "failed to enable VDD regulator: %d\n", err);
 		return err;
 	}
 
@@ -730,7 +806,7 @@ static int tegra_output_hdmi_enable(struct tegra_output *output)
 	if (err < 0)
 		return err;
 
-	err = clk_enable(hdmi->clk);
+	err = clk_prepare_enable(hdmi->clk);
 	if (err < 0) {
 		dev_err(hdmi->dev, "failed to enable clock: %d\n", err);
 		return err;
@@ -740,6 +816,17 @@ static int tegra_output_hdmi_enable(struct tegra_output *output)
 	usleep_range(1000, 2000);
 	reset_control_deassert(hdmi->rst);
 
+	/* power up sequence */
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_SOR_PLL0);
+	value &= ~SOR_PLL_PDBG;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_SOR_PLL0);
+
+	usleep_range(10, 20);
+
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_SOR_PLL0);
+	value &= ~SOR_PLL_PWR;
+	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_SOR_PLL0);
+
 	tegra_dc_writel(dc, VSYNC_H_POSITION(1),
 			DC_DISP_DISP_TIMING_OPTIONS);
 	tegra_dc_writel(dc, DITHER_CONTROL_DISABLE | BASE_COLOR_SIZE888,
@@ -838,9 +925,13 @@ static int tegra_output_hdmi_enable(struct tegra_output *output)
 	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_SOR_SEQ_INST(0));
 	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_SOR_SEQ_INST(8));
 
-	value = 0x1c800;
+	value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_SOR_CSTM);
 	value &= ~SOR_CSTM_ROTCLK(~0);
 	value |= SOR_CSTM_ROTCLK(2);
+	value |= SOR_CSTM_PLLDIV;
+	value &= ~SOR_CSTM_LVDS_ENABLE;
+	value &= ~SOR_CSTM_MODE_MASK;
+	value |= SOR_CSTM_MODE_TMDS;
 	tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_SOR_CSTM);
 
 	/* start SOR */
@@ -930,10 +1021,18 @@ static int tegra_output_hdmi_disable(struct tegra_output *output)
 	 * sure it's only executed when the output is attached to one.
 	 */
 	if (dc) {
+		/*
+		 * XXX: We can't do this here because it causes HDMI to go
+		 * into an erroneous state with the result that HDMI won't
+		 * properly work once disabled. See also a similar symptom
+		 * for the SOR output.
+		 */
+		/*
 		value = tegra_dc_readl(dc, DC_CMD_DISPLAY_POWER_CONTROL);
 		value &= ~(PW0_ENABLE | PW1_ENABLE | PW2_ENABLE | PW3_ENABLE |
 			   PW4_ENABLE | PM0_ENABLE | PM1_ENABLE);
 		tegra_dc_writel(dc, value, DC_CMD_DISPLAY_POWER_CONTROL);
+		*/
 
 		value = tegra_dc_readl(dc, DC_CMD_DISPLAY_COMMAND);
 		value &= ~DISP_CTRL_MODE_MASK;
@@ -947,8 +1046,9 @@ static int tegra_output_hdmi_disable(struct tegra_output *output)
 		tegra_dc_writel(dc, GENERAL_ACT_REQ, DC_CMD_STATE_CONTROL);
 	}
 
+	clk_disable_unprepare(hdmi->clk);
 	reset_control_assert(hdmi->rst);
-	clk_disable(hdmi->clk);
+	regulator_disable(hdmi->vdd);
 	regulator_disable(hdmi->pll);
 
 	hdmi->enabled = false;
@@ -957,10 +1057,10 @@ static int tegra_output_hdmi_disable(struct tegra_output *output)
 }
 
 static int tegra_output_hdmi_setup_clock(struct tegra_output *output,
-					 struct clk *clk, unsigned long pclk)
+					 struct clk *clk, unsigned long pclk,
+					 unsigned int *div)
 {
 	struct tegra_hdmi *hdmi = to_hdmi(output);
-	struct clk *base;
 	int err;
 
 	err = clk_set_parent(clk, hdmi->clk_parent);
@@ -969,17 +1069,12 @@ static int tegra_output_hdmi_setup_clock(struct tegra_output *output,
 		return err;
 	}
 
-	base = clk_get_parent(hdmi->clk_parent);
-
-	/*
-	 * This assumes that the parent clock is pll_d_out0 or pll_d2_out
-	 * respectively, each of which divides the base pll_d by 2.
-	 */
-	err = clk_set_rate(base, pclk * 2);
+	err = clk_set_rate(hdmi->clk_parent, pclk);
 	if (err < 0)
-		dev_err(output->dev,
-			"failed to set base clock rate to %lu Hz\n",
-			pclk * 2);
+		dev_err(output->dev, "failed to set clock rate to %lu Hz\n",
+			pclk);
+
+	*div = 0;
 
 	return 0;
 }
@@ -1017,7 +1112,7 @@ static int tegra_hdmi_show_regs(struct seq_file *s, void *data)
 	struct tegra_hdmi *hdmi = node->info_ent->data;
 	int err;
 
-	err = clk_enable(hdmi->clk);
+	err = clk_prepare_enable(hdmi->clk);
 	if (err)
 		return err;
 
@@ -1186,7 +1281,7 @@ static int tegra_hdmi_show_regs(struct seq_file *s, void *data)
 
 #undef DUMP_REG
 
-	clk_disable(hdmi->clk);
+	clk_disable_unprepare(hdmi->clk);
 
 	return 0;
 }
@@ -1252,33 +1347,33 @@ static int tegra_hdmi_debugfs_exit(struct tegra_hdmi *hdmi)
 
 static int tegra_hdmi_init(struct host1x_client *client)
 {
-	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->parent);
 	struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client);
 	int err;
 
-	err = regulator_enable(hdmi->vdd);
-	if (err < 0) {
-		dev_err(client->dev, "failed to enable VDD regulator: %d\n",
-			err);
-		return err;
-	}
-
 	hdmi->output.type = TEGRA_OUTPUT_HDMI;
 	hdmi->output.dev = client->dev;
 	hdmi->output.ops = &hdmi_ops;
 
-	err = tegra_output_init(tegra->drm, &hdmi->output);
+	err = tegra_output_init(drm, &hdmi->output);
 	if (err < 0) {
 		dev_err(client->dev, "output setup failed: %d\n", err);
 		return err;
 	}
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
-		err = tegra_hdmi_debugfs_init(hdmi, tegra->drm->primary);
+		err = tegra_hdmi_debugfs_init(hdmi, drm->primary);
 		if (err < 0)
 			dev_err(client->dev, "debugfs setup failed: %d\n", err);
 	}
 
+	err = regulator_enable(hdmi->hdmi);
+	if (err < 0) {
+		dev_err(client->dev, "failed to enable HDMI regulator: %d\n",
+			err);
+		return err;
+	}
+
 	return 0;
 }
 
@@ -1287,6 +1382,8 @@ static int tegra_hdmi_exit(struct host1x_client *client)
 	struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client);
 	int err;
 
+	regulator_disable(hdmi->hdmi);
+
 	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
 		err = tegra_hdmi_debugfs_exit(hdmi);
 		if (err < 0)
@@ -1306,8 +1403,6 @@ static int tegra_hdmi_exit(struct host1x_client *client)
 		return err;
 	}
 
-	regulator_disable(hdmi->vdd);
-
 	return 0;
 }
 
@@ -1340,7 +1435,16 @@ static const struct tegra_hdmi_config tegra114_hdmi_config = {
 	.has_sor_io_peak_current = true,
 };
 
+static const struct tegra_hdmi_config tegra124_hdmi_config = {
+	.tmds = tegra124_tmds_config,
+	.num_tmds = ARRAY_SIZE(tegra124_tmds_config),
+	.fuse_override_offset = HDMI_NV_PDISP_SOR_PAD_CTLS0,
+	.fuse_override_value = 1 << 31,
+	.has_sor_io_peak_current = true,
+};
+
 static const struct of_device_id tegra_hdmi_of_match[] = {
+	{ .compatible = "nvidia,tegra124-hdmi", .data = &tegra124_hdmi_config },
 	{ .compatible = "nvidia,tegra114-hdmi", .data = &tegra114_hdmi_config },
 	{ .compatible = "nvidia,tegra30-hdmi", .data = &tegra30_hdmi_config },
 	{ .compatible = "nvidia,tegra20-hdmi", .data = &tegra20_hdmi_config },
@@ -1381,28 +1485,20 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 		return PTR_ERR(hdmi->rst);
 	}
 
-	err = clk_prepare(hdmi->clk);
-	if (err < 0)
-		return err;
-
 	hdmi->clk_parent = devm_clk_get(&pdev->dev, "parent");
 	if (IS_ERR(hdmi->clk_parent))
 		return PTR_ERR(hdmi->clk_parent);
 
-	err = clk_prepare(hdmi->clk_parent);
-	if (err < 0)
-		return err;
-
 	err = clk_set_parent(hdmi->clk, hdmi->clk_parent);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to setup clocks: %d\n", err);
 		return err;
 	}
 
-	hdmi->vdd = devm_regulator_get(&pdev->dev, "vdd");
-	if (IS_ERR(hdmi->vdd)) {
-		dev_err(&pdev->dev, "failed to get VDD regulator\n");
-		return PTR_ERR(hdmi->vdd);
+	hdmi->hdmi = devm_regulator_get(&pdev->dev, "hdmi");
+	if (IS_ERR(hdmi->hdmi)) {
+		dev_err(&pdev->dev, "failed to get HDMI regulator\n");
+		return PTR_ERR(hdmi->hdmi);
 	}
 
 	hdmi->pll = devm_regulator_get(&pdev->dev, "pll");
@@ -1411,6 +1507,12 @@ static int tegra_hdmi_probe(struct platform_device *pdev)
 		return PTR_ERR(hdmi->pll);
 	}
 
+	hdmi->vdd = devm_regulator_get(&pdev->dev, "vdd");
+	if (IS_ERR(hdmi->vdd)) {
+		dev_err(&pdev->dev, "failed to get VDD regulator\n");
+		return PTR_ERR(hdmi->vdd);
+	}
+
 	hdmi->output.dev = &pdev->dev;
 
 	err = tegra_output_probe(&hdmi->output);
@@ -1462,8 +1564,8 @@ static int tegra_hdmi_remove(struct platform_device *pdev)
 		return err;
 	}
 
-	clk_unprepare(hdmi->clk_parent);
-	clk_unprepare(hdmi->clk);
+	clk_disable_unprepare(hdmi->clk_parent);
+	clk_disable_unprepare(hdmi->clk);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/tegra/hdmi.h b/drivers/gpu/drm/tegra/hdmi.h
index 0aebc485f7f..919a19df4e1 100644
--- a/drivers/gpu/drm/tegra/hdmi.h
+++ b/drivers/gpu/drm/tegra/hdmi.h
@@ -190,6 +190,11 @@
 
 #define HDMI_NV_PDISP_SOR_CSTM					0x5a
 #define SOR_CSTM_ROTCLK(x) (((x) & 0xf) << 24)
+#define SOR_CSTM_PLLDIV (1 << 21)
+#define SOR_CSTM_LVDS_ENABLE (1 << 16)
+#define SOR_CSTM_MODE_LVDS (0 << 12)
+#define SOR_CSTM_MODE_TMDS (1 << 12)
+#define SOR_CSTM_MODE_MASK (3 << 12)
 
 #define HDMI_NV_PDISP_SOR_LVDS					0x5b
 #define HDMI_NV_PDISP_SOR_CRCA					0x5c
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index 0266fb40479..d6af9be48f4 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -159,11 +159,38 @@ static int tegra_output_rgb_disable(struct tegra_output *output)
 }
 
 static int tegra_output_rgb_setup_clock(struct tegra_output *output,
-					struct clk *clk, unsigned long pclk)
+					struct clk *clk, unsigned long pclk,
+					unsigned int *div)
 {
 	struct tegra_rgb *rgb = to_rgb(output);
+	int err;
+
+	err = clk_set_parent(clk, rgb->clk_parent);
+	if (err < 0) {
+		dev_err(output->dev, "failed to set parent: %d\n", err);
+		return err;
+	}
 
-	return clk_set_parent(clk, rgb->clk_parent);
+	/*
+	 * We may not want to change the frequency of the parent clock, since
+	 * it may be a parent for other peripherals. This is due to the fact
+	 * that on Tegra20 there's only a single clock dedicated to display
+	 * (pll_d_out0), whereas later generations have a second one that can
+	 * be used to independently drive a second output (pll_d2_out0).
+	 *
+	 * As a way to support multiple outputs on Tegra20 as well, pll_p is
+	 * typically used as the parent clock for the display controllers.
+	 * But this comes at a cost: pll_p is the parent of several other
+	 * peripherals, so its frequency shouldn't change out of the blue.
+	 *
+	 * The best we can do at this point is to use the shift clock divider
+	 * and hope that the desired frequency can be matched (or at least
+	 * matched sufficiently close that the panel will still work).
+	 */
+
+	*div = ((clk_get_rate(clk) * 2) / pclk) - 2;
+
+	return 0;
 }
 
 static int tegra_output_rgb_check_mode(struct tegra_output *output,
diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c
index 49ef5729f43..27c979b5011 100644
--- a/drivers/gpu/drm/tegra/sor.c
+++ b/drivers/gpu/drm/tegra/sor.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/debugfs.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
@@ -33,7 +34,23 @@ struct tegra_sor {
 
 	struct tegra_dpaux *dpaux;
 
+	struct mutex lock;
 	bool enabled;
+
+	struct dentry *debugfs;
+};
+
+struct tegra_sor_config {
+	u32 bits_per_pixel;
+
+	u32 active_polarity;
+	u32 active_count;
+	u32 tu_size;
+	u32 active_frac;
+	u32 watermark;
+
+	u32 hblank_symbols;
+	u32 vblank_symbols;
 };
 
 static inline struct tegra_sor *
@@ -289,34 +306,232 @@ static int tegra_sor_power_up(struct tegra_sor *sor, unsigned long timeout)
 	return -ETIMEDOUT;
 }
 
+struct tegra_sor_params {
+	/* number of link clocks per line */
+	unsigned int num_clocks;
+	/* ratio between input and output */
+	u64 ratio;
+	/* precision factor */
+	u64 precision;
+
+	unsigned int active_polarity;
+	unsigned int active_count;
+	unsigned int active_frac;
+	unsigned int tu_size;
+	unsigned int error;
+};
+
+static int tegra_sor_compute_params(struct tegra_sor *sor,
+				    struct tegra_sor_params *params,
+				    unsigned int tu_size)
+{
+	u64 active_sym, active_count, frac, approx;
+	u32 active_polarity, active_frac = 0;
+	const u64 f = params->precision;
+	s64 error;
+
+	active_sym = params->ratio * tu_size;
+	active_count = div_u64(active_sym, f) * f;
+	frac = active_sym - active_count;
+
+	/* fraction < 0.5 */
+	if (frac >= (f / 2)) {
+		active_polarity = 1;
+		frac = f - frac;
+	} else {
+		active_polarity = 0;
+	}
+
+	if (frac != 0) {
+		frac = div_u64(f * f,  frac); /* 1/fraction */
+		if (frac <= (15 * f)) {
+			active_frac = div_u64(frac, f);
+
+			/* round up */
+			if (active_polarity)
+				active_frac++;
+		} else {
+			active_frac = active_polarity ? 1 : 15;
+		}
+	}
+
+	if (active_frac == 1)
+		active_polarity = 0;
+
+	if (active_polarity == 1) {
+		if (active_frac) {
+			approx = active_count + (active_frac * (f - 1)) * f;
+			approx = div_u64(approx, active_frac * f);
+		} else {
+			approx = active_count + f;
+		}
+	} else {
+		if (active_frac)
+			approx = active_count + div_u64(f, active_frac);
+		else
+			approx = active_count;
+	}
+
+	error = div_s64(active_sym - approx, tu_size);
+	error *= params->num_clocks;
+
+	if (error <= 0 && abs64(error) < params->error) {
+		params->active_count = div_u64(active_count, f);
+		params->active_polarity = active_polarity;
+		params->active_frac = active_frac;
+		params->error = abs64(error);
+		params->tu_size = tu_size;
+
+		if (error == 0)
+			return true;
+	}
+
+	return false;
+}
+
+static int tegra_sor_calc_config(struct tegra_sor *sor,
+				 struct drm_display_mode *mode,
+				 struct tegra_sor_config *config,
+				 struct drm_dp_link *link)
+{
+	const u64 f = 100000, link_rate = link->rate * 1000;
+	const u64 pclk = mode->clock * 1000;
+	u64 input, output, watermark, num;
+	struct tegra_sor_params params;
+	u32 num_syms_per_line;
+	unsigned int i;
+
+	if (!link_rate || !link->num_lanes || !pclk || !config->bits_per_pixel)
+		return -EINVAL;
+
+	output = link_rate * 8 * link->num_lanes;
+	input = pclk * config->bits_per_pixel;
+
+	if (input >= output)
+		return -ERANGE;
+
+	memset(&params, 0, sizeof(params));
+	params.ratio = div64_u64(input * f, output);
+	params.num_clocks = div_u64(link_rate * mode->hdisplay, pclk);
+	params.precision = f;
+	params.error = 64 * f;
+	params.tu_size = 64;
+
+	for (i = params.tu_size; i >= 32; i--)
+		if (tegra_sor_compute_params(sor, &params, i))
+			break;
+
+	if (params.active_frac == 0) {
+		config->active_polarity = 0;
+		config->active_count = params.active_count;
+
+		if (!params.active_polarity)
+			config->active_count--;
+
+		config->tu_size = params.tu_size;
+		config->active_frac = 1;
+	} else {
+		config->active_polarity = params.active_polarity;
+		config->active_count = params.active_count;
+		config->active_frac = params.active_frac;
+		config->tu_size = params.tu_size;
+	}
+
+	dev_dbg(sor->dev,
+		"polarity: %d active count: %d tu size: %d active frac: %d\n",
+		config->active_polarity, config->active_count,
+		config->tu_size, config->active_frac);
+
+	watermark = params.ratio * config->tu_size * (f - params.ratio);
+	watermark = div_u64(watermark, f);
+
+	watermark = div_u64(watermark + params.error, f);
+	config->watermark = watermark + (config->bits_per_pixel / 8) + 2;
+	num_syms_per_line = (mode->hdisplay * config->bits_per_pixel) *
+			    (link->num_lanes * 8);
+
+	if (config->watermark > 30) {
+		config->watermark = 30;
+		dev_err(sor->dev,
+			"unable to compute TU size, forcing watermark to %u\n",
+			config->watermark);
+	} else if (config->watermark > num_syms_per_line) {
+		config->watermark = num_syms_per_line;
+		dev_err(sor->dev, "watermark too high, forcing to %u\n",
+			config->watermark);
+	}
+
+	/* compute the number of symbols per horizontal blanking interval */
+	num = ((mode->htotal - mode->hdisplay) - 7) * link_rate;
+	config->hblank_symbols = div_u64(num, pclk);
+
+	if (link->capabilities & DP_LINK_CAP_ENHANCED_FRAMING)
+		config->hblank_symbols -= 3;
+
+	config->hblank_symbols -= 12 / link->num_lanes;
+
+	/* compute the number of symbols per vertical blanking interval */
+	num = (mode->hdisplay - 25) * link_rate;
+	config->vblank_symbols = div_u64(num, pclk);
+	config->vblank_symbols -= 36 / link->num_lanes + 4;
+
+	dev_dbg(sor->dev, "blank symbols: H:%u V:%u\n", config->hblank_symbols,
+		config->vblank_symbols);
+
+	return 0;
+}
+
 static int tegra_output_sor_enable(struct tegra_output *output)
 {
 	struct tegra_dc *dc = to_tegra_dc(output->encoder.crtc);
 	struct drm_display_mode *mode = &dc->base.mode;
 	unsigned int vbe, vse, hbe, hse, vbs, hbs, i;
 	struct tegra_sor *sor = to_sor(output);
+	struct tegra_sor_config config;
+	struct drm_dp_link link;
+	struct drm_dp_aux *aux;
 	unsigned long value;
-	int err;
+	int err = 0;
+
+	mutex_lock(&sor->lock);
 
 	if (sor->enabled)
-		return 0;
+		goto unlock;
 
 	err = clk_prepare_enable(sor->clk);
 	if (err < 0)
-		return err;
+		goto unlock;
 
 	reset_control_deassert(sor->rst);
 
+	/* FIXME: properly convert to struct drm_dp_aux */
+	aux = (struct drm_dp_aux *)sor->dpaux;
+
 	if (sor->dpaux) {
 		err = tegra_dpaux_enable(sor->dpaux);
 		if (err < 0)
 			dev_err(sor->dev, "failed to enable DP: %d\n", err);
+
+		err = drm_dp_link_probe(aux, &link);
+		if (err < 0) {
+			dev_err(sor->dev, "failed to probe eDP link: %d\n",
+				err);
+			return err;
+		}
 	}
 
 	err = clk_set_parent(sor->clk, sor->clk_safe);
 	if (err < 0)
 		dev_err(sor->dev, "failed to set safe parent clock: %d\n", err);
 
+	memset(&config, 0, sizeof(config));
+	config.bits_per_pixel = 24; /* XXX: don't hardcode? */
+
+	err = tegra_sor_calc_config(sor, mode, &config, &link);
+	if (err < 0)
+		dev_err(sor->dev, "failed to compute link configuration: %d\n",
+			err);
+
 	value = tegra_sor_readl(sor, SOR_CLK_CNTRL);
 	value &= ~SOR_CLK_CNTRL_DP_CLK_SEL_MASK;
 	value |= SOR_CLK_CNTRL_DP_CLK_SEL_SINGLE_DPCLK;
@@ -385,7 +600,7 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 	err = tegra_io_rail_power_on(TEGRA_IO_RAIL_LVDS);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to power on I/O rail: %d\n", err);
-		return err;
+		goto unlock;
 	}
 
 	usleep_range(5, 100);
@@ -419,15 +634,29 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 	if (err < 0)
 		dev_err(sor->dev, "failed to set DP parent clock: %d\n", err);
 
-	/* power dplanes (XXX parameterize based on link?) */
+	/* power DP lanes */
 	value = tegra_sor_readl(sor, SOR_DP_PADCTL_0);
-	value |= SOR_DP_PADCTL_PD_TXD_3 | SOR_DP_PADCTL_PD_TXD_0 |
-		 SOR_DP_PADCTL_PD_TXD_1 | SOR_DP_PADCTL_PD_TXD_2;
+
+	if (link.num_lanes <= 2)
+		value &= ~(SOR_DP_PADCTL_PD_TXD_3 | SOR_DP_PADCTL_PD_TXD_2);
+	else
+		value |= SOR_DP_PADCTL_PD_TXD_3 | SOR_DP_PADCTL_PD_TXD_2;
+
+	if (link.num_lanes <= 1)
+		value &= ~SOR_DP_PADCTL_PD_TXD_1;
+	else
+		value |= SOR_DP_PADCTL_PD_TXD_1;
+
+	if (link.num_lanes == 0)
+		value &= ~SOR_DP_PADCTL_PD_TXD_0;
+	else
+		value |= SOR_DP_PADCTL_PD_TXD_0;
+
 	tegra_sor_writel(sor, value, SOR_DP_PADCTL_0);
 
 	value = tegra_sor_readl(sor, SOR_DP_LINKCTL_0);
 	value &= ~SOR_DP_LINKCTL_LANE_COUNT_MASK;
-	value |= SOR_DP_LINKCTL_LANE_COUNT(4);
+	value |= SOR_DP_LINKCTL_LANE_COUNT(link.num_lanes);
 	tegra_sor_writel(sor, value, SOR_DP_LINKCTL_0);
 
 	/* start lane sequencer */
@@ -443,10 +672,10 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 		usleep_range(250, 1000);
 	}
 
-	/* set link bandwidth (2.7 GHz, XXX: parameterize based on link?) */
+	/* set link bandwidth */
 	value = tegra_sor_readl(sor, SOR_CLK_CNTRL);
 	value &= ~SOR_CLK_CNTRL_DP_LINK_SPEED_MASK;
-	value |= SOR_CLK_CNTRL_DP_LINK_SPEED_G2_70;
+	value |= drm_dp_link_rate_to_bw_code(link.rate) << 2;
 	tegra_sor_writel(sor, value, SOR_CLK_CNTRL);
 
 	/* set linkctl */
@@ -454,7 +683,7 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 	value |= SOR_DP_LINKCTL_ENABLE;
 
 	value &= ~SOR_DP_LINKCTL_TU_SIZE_MASK;
-	value |= SOR_DP_LINKCTL_TU_SIZE(59); /* XXX: don't hardcode? */
+	value |= SOR_DP_LINKCTL_TU_SIZE(config.tu_size);
 
 	value |= SOR_DP_LINKCTL_ENHANCED_FRAME;
 	tegra_sor_writel(sor, value, SOR_DP_LINKCTL_0);
@@ -470,28 +699,31 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 
 	value = tegra_sor_readl(sor, SOR_DP_CONFIG_0);
 	value &= ~SOR_DP_CONFIG_WATERMARK_MASK;
-	value |= SOR_DP_CONFIG_WATERMARK(14); /* XXX: don't hardcode? */
+	value |= SOR_DP_CONFIG_WATERMARK(config.watermark);
 
 	value &= ~SOR_DP_CONFIG_ACTIVE_SYM_COUNT_MASK;
-	value |= SOR_DP_CONFIG_ACTIVE_SYM_COUNT(47); /* XXX: don't hardcode? */
+	value |= SOR_DP_CONFIG_ACTIVE_SYM_COUNT(config.active_count);
 
 	value &= ~SOR_DP_CONFIG_ACTIVE_SYM_FRAC_MASK;
-	value |= SOR_DP_CONFIG_ACTIVE_SYM_FRAC(9); /* XXX: don't hardcode? */
+	value |= SOR_DP_CONFIG_ACTIVE_SYM_FRAC(config.active_frac);
 
-	value &= ~SOR_DP_CONFIG_ACTIVE_SYM_POLARITY; /* XXX: don't hardcode? */
+	if (config.active_polarity)
+		value |= SOR_DP_CONFIG_ACTIVE_SYM_POLARITY;
+	else
+		value &= ~SOR_DP_CONFIG_ACTIVE_SYM_POLARITY;
 
 	value |= SOR_DP_CONFIG_ACTIVE_SYM_ENABLE;
-	value |= SOR_DP_CONFIG_DISPARITY_NEGATIVE; /* XXX: don't hardcode? */
+	value |= SOR_DP_CONFIG_DISPARITY_NEGATIVE;
 	tegra_sor_writel(sor, value, SOR_DP_CONFIG_0);
 
 	value = tegra_sor_readl(sor, SOR_DP_AUDIO_HBLANK_SYMBOLS);
 	value &= ~SOR_DP_AUDIO_HBLANK_SYMBOLS_MASK;
-	value |= 137; /* XXX: don't hardcode? */
+	value |= config.hblank_symbols & 0xffff;
 	tegra_sor_writel(sor, value, SOR_DP_AUDIO_HBLANK_SYMBOLS);
 
 	value = tegra_sor_readl(sor, SOR_DP_AUDIO_VBLANK_SYMBOLS);
 	value &= ~SOR_DP_AUDIO_VBLANK_SYMBOLS_MASK;
-	value |= 2368; /* XXX: don't hardcode? */
+	value |= config.vblank_symbols & 0xffff;
 	tegra_sor_writel(sor, value, SOR_DP_AUDIO_VBLANK_SYMBOLS);
 
 	/* enable pad calibration logic */
@@ -500,30 +732,27 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 	tegra_sor_writel(sor, value, SOR_DP_PADCTL_0);
 
 	if (sor->dpaux) {
-		/* FIXME: properly convert to struct drm_dp_aux */
-		struct drm_dp_aux *aux = (struct drm_dp_aux *)sor->dpaux;
-		struct drm_dp_link link;
 		u8 rate, lanes;
 
 		err = drm_dp_link_probe(aux, &link);
 		if (err < 0) {
 			dev_err(sor->dev, "failed to probe eDP link: %d\n",
 				err);
-			return err;
+			goto unlock;
 		}
 
 		err = drm_dp_link_power_up(aux, &link);
 		if (err < 0) {
 			dev_err(sor->dev, "failed to power up eDP link: %d\n",
 				err);
-			return err;
+			goto unlock;
 		}
 
 		err = drm_dp_link_configure(aux, &link);
 		if (err < 0) {
 			dev_err(sor->dev, "failed to configure eDP link: %d\n",
 				err);
-			return err;
+			goto unlock;
 		}
 
 		rate = drm_dp_link_rate_to_bw_code(link.rate);
@@ -558,7 +787,7 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 		if (err < 0) {
 			dev_err(sor->dev, "DP fast link training failed: %d\n",
 				err);
-			return err;
+			goto unlock;
 		}
 
 		dev_dbg(sor->dev, "fast link training succeeded\n");
@@ -567,7 +796,7 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 	err = tegra_sor_power_up(sor, 250);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to power up SOR: %d\n", err);
-		return err;
+		goto unlock;
 	}
 
 	/* start display controller in continuous mode */
@@ -586,12 +815,26 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 	 * configure panel (24bpp, vsync-, hsync-, DP-A protocol, complete
 	 * raster, associate with display controller)
 	 */
-	value = SOR_STATE_ASY_PIXELDEPTH_BPP_24_444 |
-		SOR_STATE_ASY_VSYNCPOL |
+	value = SOR_STATE_ASY_VSYNCPOL |
 		SOR_STATE_ASY_HSYNCPOL |
 		SOR_STATE_ASY_PROTOCOL_DP_A |
 		SOR_STATE_ASY_CRC_MODE_COMPLETE |
 		SOR_STATE_ASY_OWNER(dc->pipe + 1);
+
+	switch (config.bits_per_pixel) {
+	case 24:
+		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_24_444;
+		break;
+
+	case 18:
+		value |= SOR_STATE_ASY_PIXELDEPTH_BPP_18_444;
+		break;
+
+	default:
+		BUG();
+		break;
+	}
+
 	tegra_sor_writel(sor, value, SOR_STATE_1);
 
 	/*
@@ -620,11 +863,8 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 	value = ((vbs & 0x7fff) << 16) | (hbs & 0x7fff);
 	tegra_sor_writel(sor, value, SOR_HEAD_STATE_4(0));
 
-	/* XXX interlaced mode */
-	tegra_sor_writel(sor, 0x00000001, SOR_HEAD_STATE_5(0));
-
 	/* CSTM (LVDS, link A/B, upper) */
-	value = SOR_CSTM_LVDS | SOR_CSTM_LINK_ACT_B | SOR_CSTM_LINK_ACT_B |
+	value = SOR_CSTM_LVDS | SOR_CSTM_LINK_ACT_A | SOR_CSTM_LINK_ACT_B |
 		SOR_CSTM_UPPER;
 	tegra_sor_writel(sor, value, SOR_CSTM);
 
@@ -632,7 +872,7 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 	err = tegra_sor_setup_pwm(sor, 250);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to setup PWM: %d\n", err);
-		return err;
+		goto unlock;
 	}
 
 	value = tegra_dc_readl(dc, DC_DISP_DISP_WIN_OPTIONS);
@@ -644,18 +884,20 @@ static int tegra_output_sor_enable(struct tegra_output *output)
 	err = tegra_sor_attach(sor);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to attach SOR: %d\n", err);
-		return err;
+		goto unlock;
 	}
 
 	err = tegra_sor_wakeup(sor);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to enable DC: %d\n", err);
-		return err;
+		goto unlock;
 	}
 
 	sor->enabled = true;
 
-	return 0;
+unlock:
+	mutex_unlock(&sor->lock);
+	return err;
 }
 
 static int tegra_sor_detach(struct tegra_sor *sor)
@@ -740,7 +982,7 @@ static int tegra_sor_power_down(struct tegra_sor *sor)
 	tegra_sor_writel(sor, value, SOR_DP_PADCTL_0);
 
 	/* stop lane sequencer */
-	value = SOR_LANE_SEQ_CTL_TRIGGER | SOR_LANE_SEQ_CTL_SEQUENCE_DOWN |
+	value = SOR_LANE_SEQ_CTL_TRIGGER | SOR_LANE_SEQ_CTL_SEQUENCE_UP |
 		SOR_LANE_SEQ_CTL_POWER_STATE_DOWN;
 	tegra_sor_writel(sor, value, SOR_LANE_SEQ_CTL);
 
@@ -783,15 +1025,17 @@ static int tegra_output_sor_disable(struct tegra_output *output)
 	struct tegra_dc *dc = to_tegra_dc(output->encoder.crtc);
 	struct tegra_sor *sor = to_sor(output);
 	unsigned long value;
-	int err;
+	int err = 0;
+
+	mutex_lock(&sor->lock);
 
 	if (!sor->enabled)
-		return 0;
+		goto unlock;
 
 	err = tegra_sor_detach(sor);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to detach SOR: %d\n", err);
-		return err;
+		goto unlock;
 	}
 
 	tegra_sor_writel(sor, 0, SOR_STATE_1);
@@ -832,21 +1076,21 @@ static int tegra_output_sor_disable(struct tegra_output *output)
 	err = tegra_sor_power_down(sor);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to power down SOR: %d\n", err);
-		return err;
+		goto unlock;
 	}
 
 	if (sor->dpaux) {
 		err = tegra_dpaux_disable(sor->dpaux);
 		if (err < 0) {
 			dev_err(sor->dev, "failed to disable DP: %d\n", err);
-			return err;
+			goto unlock;
 		}
 	}
 
 	err = tegra_io_rail_power_off(TEGRA_IO_RAIL_LVDS);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to power off I/O rail: %d\n", err);
-		return err;
+		goto unlock;
 	}
 
 	reset_control_assert(sor->rst);
@@ -854,18 +1098,18 @@ static int tegra_output_sor_disable(struct tegra_output *output)
 
 	sor->enabled = false;
 
-	return 0;
+unlock:
+	mutex_unlock(&sor->lock);
+	return err;
 }
 
 static int tegra_output_sor_setup_clock(struct tegra_output *output,
-					struct clk *clk, unsigned long pclk)
+					struct clk *clk, unsigned long pclk,
+					unsigned int *div)
 {
 	struct tegra_sor *sor = to_sor(output);
 	int err;
 
-	/* round to next MHz */
-	pclk = DIV_ROUND_UP(pclk / 2, 1000000) * 1000000;
-
 	err = clk_set_parent(clk, sor->clk_parent);
 	if (err < 0) {
 		dev_err(sor->dev, "failed to set parent clock: %d\n", err);
@@ -874,11 +1118,12 @@ static int tegra_output_sor_setup_clock(struct tegra_output *output,
 
 	err = clk_set_rate(sor->clk_parent, pclk);
 	if (err < 0) {
-		dev_err(sor->dev, "failed to set base clock rate to %lu Hz\n",
-			pclk * 2);
+		dev_err(sor->dev, "failed to set clock rate to %lu Hz\n", pclk);
 		return err;
 	}
 
+	*div = 0;
+
 	return 0;
 }
 
@@ -914,9 +1159,124 @@ static const struct tegra_output_ops sor_ops = {
 	.detect = tegra_output_sor_detect,
 };
 
+static int tegra_sor_crc_open(struct inode *inode, struct file *file)
+{
+	file->private_data = inode->i_private;
+
+	return 0;
+}
+
+static int tegra_sor_crc_release(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+
+static int tegra_sor_crc_wait(struct tegra_sor *sor, unsigned long timeout)
+{
+	u32 value;
+
+	timeout = jiffies + msecs_to_jiffies(timeout);
+
+	while (time_before(jiffies, timeout)) {
+		value = tegra_sor_readl(sor, SOR_CRC_A);
+		if (value & SOR_CRC_A_VALID)
+			return 0;
+
+		usleep_range(100, 200);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static ssize_t tegra_sor_crc_read(struct file *file, char __user *buffer,
+				  size_t size, loff_t *ppos)
+{
+	struct tegra_sor *sor = file->private_data;
+	ssize_t num, err;
+	char buf[10];
+	u32 value;
+
+	mutex_lock(&sor->lock);
+
+	if (!sor->enabled) {
+		err = -EAGAIN;
+		goto unlock;
+	}
+
+	value = tegra_sor_readl(sor, SOR_STATE_1);
+	value &= ~SOR_STATE_ASY_CRC_MODE_MASK;
+	tegra_sor_writel(sor, value, SOR_STATE_1);
+
+	value = tegra_sor_readl(sor, SOR_CRC_CNTRL);
+	value |= SOR_CRC_CNTRL_ENABLE;
+	tegra_sor_writel(sor, value, SOR_CRC_CNTRL);
+
+	value = tegra_sor_readl(sor, SOR_TEST);
+	value &= ~SOR_TEST_CRC_POST_SERIALIZE;
+	tegra_sor_writel(sor, value, SOR_TEST);
+
+	err = tegra_sor_crc_wait(sor, 100);
+	if (err < 0)
+		goto unlock;
+
+	tegra_sor_writel(sor, SOR_CRC_A_RESET, SOR_CRC_A);
+	value = tegra_sor_readl(sor, SOR_CRC_B);
+
+	num = scnprintf(buf, sizeof(buf), "%08x\n", value);
+
+	err = simple_read_from_buffer(buffer, size, ppos, buf, num);
+
+unlock:
+	mutex_unlock(&sor->lock);
+	return err;
+}
+
+static const struct file_operations tegra_sor_crc_fops = {
+	.owner = THIS_MODULE,
+	.open = tegra_sor_crc_open,
+	.read = tegra_sor_crc_read,
+	.release = tegra_sor_crc_release,
+};
+
+static int tegra_sor_debugfs_init(struct tegra_sor *sor,
+				  struct drm_minor *minor)
+{
+	struct dentry *entry;
+	int err = 0;
+
+	sor->debugfs = debugfs_create_dir("sor", minor->debugfs_root);
+	if (!sor->debugfs)
+		return -ENOMEM;
+
+	entry = debugfs_create_file("crc", 0644, sor->debugfs, sor,
+				    &tegra_sor_crc_fops);
+	if (!entry) {
+		dev_err(sor->dev,
+			"cannot create /sys/kernel/debug/dri/%s/sor/crc\n",
+			minor->debugfs_root->d_name.name);
+		err = -ENOMEM;
+		goto remove;
+	}
+
+	return err;
+
+remove:
+	debugfs_remove(sor->debugfs);
+	sor->debugfs = NULL;
+	return err;
+}
+
+static int tegra_sor_debugfs_exit(struct tegra_sor *sor)
+{
+	debugfs_remove_recursive(sor->debugfs);
+	sor->debugfs = NULL;
+
+	return 0;
+}
+
 static int tegra_sor_init(struct host1x_client *client)
 {
-	struct tegra_drm *tegra = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->parent);
 	struct tegra_sor *sor = host1x_client_to_sor(client);
 	int err;
 
@@ -928,12 +1288,18 @@ static int tegra_sor_init(struct host1x_client *client)
 	sor->output.dev = sor->dev;
 	sor->output.ops = &sor_ops;
 
-	err = tegra_output_init(tegra->drm, &sor->output);
+	err = tegra_output_init(drm, &sor->output);
 	if (err < 0) {
 		dev_err(sor->dev, "output setup failed: %d\n", err);
 		return err;
 	}
 
+	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
+		err = tegra_sor_debugfs_init(sor, drm->primary);
+		if (err < 0)
+			dev_err(sor->dev, "debugfs setup failed: %d\n", err);
+	}
+
 	if (sor->dpaux) {
 		err = tegra_dpaux_attach(sor->dpaux, &sor->output);
 		if (err < 0) {
@@ -964,6 +1330,12 @@ static int tegra_sor_exit(struct host1x_client *client)
 		}
 	}
 
+	if (IS_ENABLED(CONFIG_DEBUG_FS)) {
+		err = tegra_sor_debugfs_exit(sor);
+		if (err < 0)
+			dev_err(sor->dev, "debugfs cleanup failed: %d\n", err);
+	}
+
 	err = tegra_output_exit(&sor->output);
 	if (err < 0) {
 		dev_err(sor->dev, "output cleanup failed: %d\n", err);
@@ -1045,6 +1417,8 @@ static int tegra_sor_probe(struct platform_device *pdev)
 	sor->client.ops = &sor_client_ops;
 	sor->client.dev = &pdev->dev;
 
+	mutex_init(&sor->lock);
+
 	err = host1x_client_register(&sor->client);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register host1x client: %d\n",
diff --git a/drivers/gpu/drm/tegra/sor.h b/drivers/gpu/drm/tegra/sor.h
index f4156d54cd0..a5f8853fedb 100644
--- a/drivers/gpu/drm/tegra/sor.h
+++ b/drivers/gpu/drm/tegra/sor.h
@@ -47,6 +47,7 @@
 #define SOR_HEAD_STATE_4(x) (0x0d + (x))
 #define SOR_HEAD_STATE_5(x) (0x0f + (x))
 #define SOR_CRC_CNTRL 0x11
+#define  SOR_CRC_CNTRL_ENABLE			(1 << 0)
 #define SOR_DP_DEBUG_MVID 0x12
 
 #define SOR_CLK_CNTRL 0x13
@@ -69,6 +70,7 @@
 #define  SOR_PWR_NORMAL_STATE_PU		(1 << 0)
 
 #define SOR_TEST 0x16
+#define  SOR_TEST_CRC_POST_SERIALIZE		(1 << 23)
 #define  SOR_TEST_ATTACHED			(1 << 10)
 #define  SOR_TEST_HEAD_MODE_MASK		(3 << 8)
 #define  SOR_TEST_HEAD_MODE_AWAKE		(2 << 8)
@@ -115,6 +117,8 @@
 
 #define SOR_LVDS 0x1c
 #define SOR_CRC_A 0x1d
+#define  SOR_CRC_A_VALID			(1 << 0)
+#define  SOR_CRC_A_RESET			(1 << 0)
 #define SOR_CRC_B 0x1e
 #define SOR_BLANK 0x1f
 #define SOR_SEQ_CTL 0x20
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index 171a8203892..b20b69488dc 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -268,7 +268,7 @@ static int tilcdc_load(struct drm_device *dev, unsigned long flags)
 	}
 
 	pm_runtime_get_sync(dev->dev);
-	ret = drm_irq_install(dev);
+	ret = drm_irq_install(dev, platform_get_irq(dev->platformdev, 0));
 	pm_runtime_put_sync(dev->dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to install IRQ handler\n");
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index afdf383f630..7094b92d1ec 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -294,6 +294,7 @@ int udl_driver_load(struct drm_device *dev, unsigned long flags)
 	dev->dev_private = udl;
 
 	if (!udl_parse_vendor_descriptor(dev, dev->usbdev)) {
+		ret = -ENODEV;
 		DRM_ERROR("firmware not recognized. Assume incompatible device\n");
 		goto err;
 	}
diff --git a/drivers/gpu/drm/via/via_dma.c b/drivers/gpu/drm/via/via_dma.c
index a18479c6b6d..6fc0648dd37 100644
--- a/drivers/gpu/drm/via/via_dma.c
+++ b/drivers/gpu/drm/via/via_dma.c
@@ -737,4 +737,4 @@ const struct drm_ioctl_desc via_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(VIA_BLIT_SYNC, via_dma_blit_sync, DRM_AUTH)
 };
 
-int via_max_ioctl = DRM_ARRAY_SIZE(via_ioctls);
+int via_max_ioctl = ARRAY_SIZE(via_ioctls);
diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c
index 92788910548..d70b1e1544b 100644
--- a/drivers/gpu/drm/via/via_mm.c
+++ b/drivers/gpu/drm/via/via_mm.c
@@ -79,7 +79,7 @@ int via_final_context(struct drm_device *dev, int context)
 
 	/* Linux specific until context tracking code gets ported to BSD */
 	/* Last context, perform cleanup */
-	if (list_is_singular(&dev->ctxlist) && dev->dev_private) {
+	if (list_is_singular(&dev->ctxlist)) {
 		DRM_DEBUG("Last Context\n");
 		drm_irq_uninstall(dev);
 		via_cleanup_futex(dev_priv);
diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig
index b71bcd0bfbb..67720f70fe2 100644
--- a/drivers/gpu/drm/vmwgfx/Kconfig
+++ b/drivers/gpu/drm/vmwgfx/Kconfig
@@ -1,11 +1,14 @@
 config DRM_VMWGFX
 	tristate "DRM driver for VMware Virtual GPU"
-	depends on DRM && PCI && FB
+	depends on DRM && PCI
 	select FB_DEFERRED_IO
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
 	select DRM_TTM
+	# Only needed for the transitional use of drm_crtc_init - can be removed
+	# again once vmwgfx sets up the primary plane itself.
+	select DRM_KMS_HELPER
 	help
 	  Choose this option if you would like to run 3D acceleration
 	  in a VMware virtual machine.
@@ -14,7 +17,7 @@ config DRM_VMWGFX
 	  The compiled module will be called "vmwgfx.ko".
 
 config DRM_VMWGFX_FBCON
-	depends on DRM_VMWGFX
+	depends on DRM_VMWGFX && FB
 	bool "Enable framebuffer console under vmwgfx by default"
 	help
 	   Choose this option if you are shipping a new vmwgfx
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 4a223bbea3b..246a62bab37 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -806,7 +806,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	}
 
 	if (dev_priv->capabilities & SVGA_CAP_IRQMASK) {
-		ret = drm_irq_install(dev);
+		ret = drm_irq_install(dev, dev->pdev->irq);
 		if (ret != 0) {
 			DRM_ERROR("Failed installing irq: %d\n", ret);
 			goto out_no_irq;
@@ -1417,7 +1417,7 @@ static struct drm_driver driver = {
 	.enable_vblank = vmw_enable_vblank,
 	.disable_vblank = vmw_disable_vblank,
 	.ioctls = vmw_ioctls,
-	.num_ioctls = DRM_ARRAY_SIZE(vmw_ioctls),
+	.num_ioctls = ARRAY_SIZE(vmw_ioctls),
 	.master_create = vmw_master_create,
 	.master_destroy = vmw_master_destroy,
 	.master_set = vmw_master_set,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index a89ad938eac..b031b48dbb3 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -179,7 +179,6 @@ static int vmw_fb_set_par(struct fb_info *info)
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_POSITION_Y, info->var.yoffset);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_WIDTH, info->var.xres);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_HEIGHT, info->var.yres);
-		vmw_write(vmw_priv, SVGA_REG_BYTES_PER_LINE, info->fix.line_length);
 		vmw_write(vmw_priv, SVGA_REG_DISPLAY_ID, SVGA_ID_INVALID);
 	}
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index a2dde5ad813..8f3edc4710f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -187,7 +187,7 @@ int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
 	 * can do this since the caller in the drm core doesn't check anything
 	 * which is protected by any looks.
 	 */
-	mutex_unlock(&crtc->mutex);
+	drm_modeset_unlock(&crtc->mutex);
 	drm_modeset_lock_all(dev_priv->dev);
 
 	/* A lot of the code assumes this */
@@ -252,7 +252,7 @@ int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
 	ret = 0;
 out:
 	drm_modeset_unlock_all(dev_priv->dev);
-	mutex_lock(&crtc->mutex);
+	drm_modeset_lock(&crtc->mutex, NULL);
 
 	return ret;
 }
@@ -273,7 +273,7 @@ int vmw_du_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	 * can do this since the caller in the drm core doesn't check anything
 	 * which is protected by any looks.
 	 */
-	mutex_unlock(&crtc->mutex);
+	drm_modeset_unlock(&crtc->mutex);
 	drm_modeset_lock_all(dev_priv->dev);
 
 	vmw_cursor_update_position(dev_priv, shown,
@@ -281,7 +281,7 @@ int vmw_du_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 				   du->cursor_y + du->hotspot_y);
 
 	drm_modeset_unlock_all(dev_priv->dev);
-	mutex_lock(&crtc->mutex);
+	drm_modeset_lock(&crtc->mutex, NULL);
 
 	return 0;
 }
@@ -2001,7 +2001,7 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector,
 	if (du->pref_mode)
 		list_move(&du->pref_mode->head, &connector->probed_modes);
 
-	drm_mode_connector_list_update(connector);
+	drm_mode_connector_list_update(connector, true);
 
 	return 1;
 }
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index ccdd2e6da5e..aaf54859adb 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -216,8 +216,8 @@ int host1x_device_exit(struct host1x_device *device)
 }
 EXPORT_SYMBOL(host1x_device_exit);
 
-static int host1x_register_client(struct host1x *host1x,
-				  struct host1x_client *client)
+static int host1x_add_client(struct host1x *host1x,
+			     struct host1x_client *client)
 {
 	struct host1x_device *device;
 	struct host1x_subdev *subdev;
@@ -238,8 +238,8 @@ static int host1x_register_client(struct host1x *host1x,
 	return -ENODEV;
 }
 
-static int host1x_unregister_client(struct host1x *host1x,
-				    struct host1x_client *client)
+static int host1x_del_client(struct host1x *host1x,
+			     struct host1x_client *client)
 {
 	struct host1x_device *device, *dt;
 	struct host1x_subdev *subdev;
@@ -503,7 +503,7 @@ int host1x_client_register(struct host1x_client *client)
 	mutex_lock(&devices_lock);
 
 	list_for_each_entry(host1x, &devices, list) {
-		err = host1x_register_client(host1x, client);
+		err = host1x_add_client(host1x, client);
 		if (!err) {
 			mutex_unlock(&devices_lock);
 			return 0;
@@ -529,7 +529,7 @@ int host1x_client_unregister(struct host1x_client *client)
 	mutex_lock(&devices_lock);
 
 	list_for_each_entry(host1x, &devices, list) {
-		err = host1x_unregister_client(host1x, client);
+		err = host1x_del_client(host1x, client);
 		if (!err) {
 			mutex_unlock(&devices_lock);
 			return 0;
diff --git a/drivers/gpu/ipu-v3/Kconfig b/drivers/gpu/ipu-v3/Kconfig
new file mode 100644
index 00000000000..2f228a2f2a4
--- /dev/null
+++ b/drivers/gpu/ipu-v3/Kconfig
@@ -0,0 +1,7 @@
+config IMX_IPUV3_CORE
+	tristate "IPUv3 core support"
+	depends on SOC_IMX5 || SOC_IMX6Q || SOC_IMX6SL || ARCH_MULTIPLATFORM
+	depends on RESET_CONTROLLER
+	help
+	  Choose this if you have a i.MX5/6 system and want to use the Image
+	  Processing Unit. This option only enables IPU base support.
diff --git a/drivers/staging/imx-drm/ipu-v3/Makefile b/drivers/gpu/ipu-v3/Makefile
index 28ed72e98a9..1887972b4ac 100644
--- a/drivers/staging/imx-drm/ipu-v3/Makefile
+++ b/drivers/gpu/ipu-v3/Makefile
@@ -1,3 +1,3 @@
-obj-$(CONFIG_DRM_IMX_IPUV3_CORE) += imx-ipu-v3.o
+obj-$(CONFIG_IMX_IPUV3_CORE) += imx-ipu-v3.o
 
-imx-ipu-v3-objs := ipu-common.o ipu-dc.o ipu-di.o ipu-dp.o ipu-dmfc.o
+imx-ipu-v3-objs := ipu-common.o ipu-dc.o ipu-di.o ipu-dp.o ipu-dmfc.o ipu-smfc.o
diff --git a/drivers/staging/imx-drm/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index a1f7b2001c8..04e7b2eafbd 100644
--- a/drivers/staging/imx-drm/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -31,7 +31,7 @@
 
 #include <drm/drm_fourcc.h>
 
-#include "imx-ipu-v3.h"
+#include <video/imx-ipu-v3.h>
 #include "ipu-prv.h"
 
 static inline u32 ipu_cm_read(struct ipu_soc *ipu, unsigned offset)
@@ -661,6 +661,39 @@ int ipu_module_disable(struct ipu_soc *ipu, u32 mask)
 }
 EXPORT_SYMBOL_GPL(ipu_module_disable);
 
+int ipu_csi_enable(struct ipu_soc *ipu, int csi)
+{
+	return ipu_module_enable(ipu, csi ? IPU_CONF_CSI1_EN : IPU_CONF_CSI0_EN);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_enable);
+
+int ipu_csi_disable(struct ipu_soc *ipu, int csi)
+{
+	return ipu_module_disable(ipu, csi ? IPU_CONF_CSI1_EN : IPU_CONF_CSI0_EN);
+}
+EXPORT_SYMBOL_GPL(ipu_csi_disable);
+
+int ipu_smfc_enable(struct ipu_soc *ipu)
+{
+	return ipu_module_enable(ipu, IPU_CONF_SMFC_EN);
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_enable);
+
+int ipu_smfc_disable(struct ipu_soc *ipu)
+{
+	return ipu_module_disable(ipu, IPU_CONF_SMFC_EN);
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_disable);
+
+int ipu_idmac_get_current_buffer(struct ipuv3_channel *channel)
+{
+	struct ipu_soc *ipu = channel->ipu;
+	unsigned int chno = channel->num;
+
+	return (ipu_cm_read(ipu, IPU_CHA_CUR_BUF(chno)) & idma_mask(chno)) ? 1 : 0;
+}
+EXPORT_SYMBOL_GPL(ipu_idmac_get_current_buffer);
+
 void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num)
 {
 	struct ipu_soc *ipu = channel->ipu;
@@ -896,8 +929,17 @@ static int ipu_submodules_init(struct ipu_soc *ipu,
 		goto err_dp;
 	}
 
+	ret = ipu_smfc_init(ipu, dev, ipu_base +
+			devtype->cm_ofs + IPU_CM_SMFC_REG_OFS);
+	if (ret) {
+		unit = "smfc";
+		goto err_smfc;
+	}
+
 	return 0;
 
+err_smfc:
+	ipu_dp_exit(ipu);
 err_dp:
 	ipu_dmfc_exit(ipu);
 err_dmfc:
@@ -977,6 +1019,7 @@ EXPORT_SYMBOL_GPL(ipu_idmac_channel_irq);
 
 static void ipu_submodules_exit(struct ipu_soc *ipu)
 {
+	ipu_smfc_exit(ipu);
 	ipu_dp_exit(ipu);
 	ipu_dmfc_exit(ipu);
 	ipu_dc_exit(ipu);
@@ -1001,6 +1044,7 @@ static void platform_device_unregister_children(struct platform_device *pdev)
 struct ipu_platform_reg {
 	struct ipu_client_platformdata pdata;
 	const char *name;
+	int reg_offset;
 };
 
 static const struct ipu_platform_reg client_reg[] = {
@@ -1022,13 +1066,29 @@ static const struct ipu_platform_reg client_reg[] = {
 			.dma[1] = -EINVAL,
 		},
 		.name = "imx-ipuv3-crtc",
+	}, {
+		.pdata = {
+			.csi = 0,
+			.dma[0] = IPUV3_CHANNEL_CSI0,
+			.dma[1] = -EINVAL,
+		},
+		.reg_offset = IPU_CM_CSI0_REG_OFS,
+		.name = "imx-ipuv3-camera",
+	}, {
+		.pdata = {
+			.csi = 1,
+			.dma[0] = IPUV3_CHANNEL_CSI1,
+			.dma[1] = -EINVAL,
+		},
+		.reg_offset = IPU_CM_CSI1_REG_OFS,
+		.name = "imx-ipuv3-camera",
 	},
 };
 
 static DEFINE_MUTEX(ipu_client_id_mutex);
 static int ipu_client_id;
 
-static int ipu_add_client_devices(struct ipu_soc *ipu)
+static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base)
 {
 	struct device *dev = ipu->dev;
 	unsigned i;
@@ -1042,9 +1102,19 @@ static int ipu_add_client_devices(struct ipu_soc *ipu)
 	for (i = 0; i < ARRAY_SIZE(client_reg); i++) {
 		const struct ipu_platform_reg *reg = &client_reg[i];
 		struct platform_device *pdev;
-
-		pdev = platform_device_register_data(dev, reg->name,
-			id++, &reg->pdata, sizeof(reg->pdata));
+		struct resource res;
+
+		if (reg->reg_offset) {
+			memset(&res, 0, sizeof(res));
+			res.flags = IORESOURCE_MEM;
+			res.start = ipu_base + ipu->devtype->cm_ofs + reg->reg_offset;
+			res.end = res.start + PAGE_SIZE - 1;
+			pdev = platform_device_register_resndata(dev, reg->name,
+				id++, &res, 1, &reg->pdata, sizeof(reg->pdata));
+		} else {
+			pdev = platform_device_register_data(dev, reg->name,
+				id++, &reg->pdata, sizeof(reg->pdata));
+		}
 
 		if (IS_ERR(pdev))
 			goto err_register;
@@ -1241,7 +1311,7 @@ static int ipu_probe(struct platform_device *pdev)
 	if (ret)
 		goto failed_submodules_init;
 
-	ret = ipu_add_client_devices(ipu);
+	ret = ipu_add_client_devices(ipu, ipu_base);
 	if (ret) {
 		dev_err(&pdev->dev, "adding client devices failed with %d\n",
 				ret);
diff --git a/drivers/staging/imx-drm/ipu-v3/ipu-dc.c b/drivers/gpu/ipu-v3/ipu-dc.c
index 784a4a13eac..2326c752d89 100644
--- a/drivers/staging/imx-drm/ipu-v3/ipu-dc.c
+++ b/drivers/gpu/ipu-v3/ipu-dc.c
@@ -21,8 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 
-#include "../imx-drm.h"
-#include "imx-ipu-v3.h"
+#include <video/imx-ipu-v3.h>
 #include "ipu-prv.h"
 
 #define DC_MAP_CONF_PTR(n)	(0x108 + ((n) & ~0x1) * 2)
diff --git a/drivers/staging/imx-drm/ipu-v3/ipu-di.c b/drivers/gpu/ipu-v3/ipu-di.c
index 849b3e120ef..c490ba4384f 100644
--- a/drivers/staging/imx-drm/ipu-v3/ipu-di.c
+++ b/drivers/gpu/ipu-v3/ipu-di.c
@@ -20,7 +20,7 @@
 #include <linux/err.h>
 #include <linux/platform_device.h>
 
-#include "imx-ipu-v3.h"
+#include <video/imx-ipu-v3.h>
 #include "ipu-prv.h"
 
 struct ipu_di {
diff --git a/drivers/staging/imx-drm/ipu-v3/ipu-dmfc.c b/drivers/gpu/ipu-v3/ipu-dmfc.c
index 59f182b28fc..042c3958e2a 100644
--- a/drivers/staging/imx-drm/ipu-v3/ipu-dmfc.c
+++ b/drivers/gpu/ipu-v3/ipu-dmfc.c
@@ -17,7 +17,7 @@
 #include <linux/errno.h>
 #include <linux/io.h>
 
-#include "imx-ipu-v3.h"
+#include <video/imx-ipu-v3.h>
 #include "ipu-prv.h"
 
 #define DMFC_RD_CHAN		0x0000
diff --git a/drivers/staging/imx-drm/ipu-v3/ipu-dp.c b/drivers/gpu/ipu-v3/ipu-dp.c
index d90f82a87d1..98686edbcdb 100644
--- a/drivers/staging/imx-drm/ipu-v3/ipu-dp.c
+++ b/drivers/gpu/ipu-v3/ipu-dp.c
@@ -19,7 +19,7 @@
 #include <linux/io.h>
 #include <linux/err.h>
 
-#include "imx-ipu-v3.h"
+#include <video/imx-ipu-v3.h>
 #include "ipu-prv.h"
 
 #define DP_SYNC 0
diff --git a/drivers/staging/imx-drm/ipu-v3/ipu-prv.h b/drivers/gpu/ipu-v3/ipu-prv.h
index bfc1b336648..c93f50ec04f 100644
--- a/drivers/staging/imx-drm/ipu-v3/ipu-prv.h
+++ b/drivers/gpu/ipu-v3/ipu-prv.h
@@ -22,7 +22,7 @@ struct ipu_soc;
 #include <linux/clk.h>
 #include <linux/platform_device.h>
 
-#include "imx-ipu-v3.h"
+#include <video/imx-ipu-v3.h>
 
 #define IPUV3_CHANNEL_CSI0			 0
 #define IPUV3_CHANNEL_CSI1			 1
@@ -151,6 +151,8 @@ struct ipuv3_channel {
 struct ipu_dc_priv;
 struct ipu_dmfc_priv;
 struct ipu_di;
+struct ipu_smfc_priv;
+
 struct ipu_devtype;
 
 struct ipu_soc {
@@ -178,6 +180,7 @@ struct ipu_soc {
 	struct ipu_dp_priv	*dp_priv;
 	struct ipu_dmfc_priv	*dmfc_priv;
 	struct ipu_di		*di_priv[2];
+	struct ipu_smfc_priv	*smfc_priv;
 };
 
 void ipu_srm_dp_sync_update(struct ipu_soc *ipu);
@@ -206,4 +209,7 @@ void ipu_dc_exit(struct ipu_soc *ipu);
 int ipu_cpmem_init(struct ipu_soc *ipu, struct device *dev, unsigned long base);
 void ipu_cpmem_exit(struct ipu_soc *ipu);
 
+int ipu_smfc_init(struct ipu_soc *ipu, struct device *dev, unsigned long base);
+void ipu_smfc_exit(struct ipu_soc *ipu);
+
 #endif				/* __IPU_PRV_H__ */
diff --git a/drivers/gpu/ipu-v3/ipu-smfc.c b/drivers/gpu/ipu-v3/ipu-smfc.c
new file mode 100644
index 00000000000..e4f85ad286f
--- /dev/null
+++ b/drivers/gpu/ipu-v3/ipu-smfc.c
@@ -0,0 +1,97 @@
+/*
+ * Copyright 2008-2010 Freescale Semiconductor, Inc. All Rights Reserved.
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+#define DEBUG
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/clk.h>
+#include <video/imx-ipu-v3.h>
+
+#include "ipu-prv.h"
+
+struct ipu_smfc_priv {
+	void __iomem *base;
+	spinlock_t lock;
+};
+
+/*SMFC Registers */
+#define SMFC_MAP	0x0000
+#define SMFC_WMC	0x0004
+#define SMFC_BS		0x0008
+
+int ipu_smfc_set_burstsize(struct ipu_soc *ipu, int channel, int burstsize)
+{
+	struct ipu_smfc_priv *smfc = ipu->smfc_priv;
+	unsigned long flags;
+	u32 val, shift;
+
+	spin_lock_irqsave(&smfc->lock, flags);
+
+	shift = channel * 4;
+	val = readl(smfc->base + SMFC_BS);
+	val &= ~(0xf << shift);
+	val |= burstsize << shift;
+	writel(val, smfc->base + SMFC_BS);
+
+	spin_unlock_irqrestore(&smfc->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_set_burstsize);
+
+int ipu_smfc_map_channel(struct ipu_soc *ipu, int channel, int csi_id, int mipi_id)
+{
+	struct ipu_smfc_priv *smfc = ipu->smfc_priv;
+	unsigned long flags;
+	u32 val, shift;
+
+	spin_lock_irqsave(&smfc->lock, flags);
+
+	shift = channel * 3;
+	val = readl(smfc->base + SMFC_MAP);
+	val &= ~(0x7 << shift);
+	val |= ((csi_id << 2) | mipi_id) << shift;
+	writel(val, smfc->base + SMFC_MAP);
+
+	spin_unlock_irqrestore(&smfc->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ipu_smfc_map_channel);
+
+int ipu_smfc_init(struct ipu_soc *ipu, struct device *dev,
+		  unsigned long base)
+{
+	struct ipu_smfc_priv *smfc;
+
+	smfc = devm_kzalloc(dev, sizeof(*smfc), GFP_KERNEL);
+	if (!smfc)
+		return -ENOMEM;
+
+	ipu->smfc_priv = smfc;
+	spin_lock_init(&smfc->lock);
+
+	smfc->base = devm_ioremap(dev, base, PAGE_SIZE);
+	if (!smfc->base)
+		return -ENOMEM;
+
+	pr_debug("%s: ioremap 0x%08lx -> %p\n", __func__, base, smfc->base);
+
+	return 0;
+}
+
+void ipu_smfc_exit(struct ipu_soc *ipu)
+{
+}
diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index ec0ae2d1686..6866448083b 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -623,7 +623,8 @@ static int vga_switcheroo_runtime_suspend(struct device *dev)
 	ret = dev->bus->pm->runtime_suspend(dev);
 	if (ret)
 		return ret;
-
+	if (vgasr_priv.handler->switchto)
+		vgasr_priv.handler->switchto(VGA_SWITCHEROO_IGD);
 	vga_switcheroo_power_switch(pdev, VGA_SWITCHEROO_OFF);
 	return 0;
 }
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 800c8b60f7a..5e79c6ad914 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -810,7 +810,7 @@ config HID_ZYDACRON
 
 config HID_SENSOR_HUB
 	tristate "HID Sensors framework support"
-	depends on HID
+	depends on HID && HAS_IOMEM
 	select MFD_CORE
 	default n
 	---help---
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 6d00bb9366f..48b66bbffc9 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -323,6 +323,7 @@
 
 #define USB_VENDOR_ID_ETURBOTOUCH	0x22b9
 #define USB_DEVICE_ID_ETURBOTOUCH	0x0006
+#define USB_DEVICE_ID_ETURBOTOUCH_2968	0x2968
 
 #define USB_VENDOR_ID_EZKEY		0x0518
 #define USB_DEVICE_ID_BTC_8193		0x0002
@@ -715,6 +716,8 @@
 
 #define USB_VENDOR_ID_PENMOUNT		0x14e1
 #define USB_DEVICE_ID_PENMOUNT_PCI	0x3500
+#define USB_DEVICE_ID_PENMOUNT_1610	0x1610
+#define USB_DEVICE_ID_PENMOUNT_1640	0x1640
 
 #define USB_VENDOR_ID_PETALYNX		0x18b1
 #define USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE	0x0037
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index 24883b4d1a4..cc2bd202219 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -52,7 +52,7 @@ static void hid_lg4ff_set_range_g25(struct hid_device *hid, u16 range);
 static ssize_t lg4ff_range_show(struct device *dev, struct device_attribute *attr, char *buf);
 static ssize_t lg4ff_range_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count);
 
-static DEVICE_ATTR(range, S_IRWXU | S_IRWXG | S_IRWXO, lg4ff_range_show, lg4ff_range_store);
+static DEVICE_ATTR(range, S_IRWXU | S_IRWXG | S_IROTH, lg4ff_range_show, lg4ff_range_store);
 
 struct lg4ff_device_entry {
 	__u32 product_id;
diff --git a/drivers/hid/hid-picolcd_fb.c b/drivers/hid/hid-picolcd_fb.c
index c930ab8554e..7f965e23143 100644
--- a/drivers/hid/hid-picolcd_fb.c
+++ b/drivers/hid/hid-picolcd_fb.c
@@ -501,7 +501,7 @@ static ssize_t picolcd_fb_update_rate_store(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(fb_update_rate, 0666, picolcd_fb_update_rate_show,
+static DEVICE_ATTR(fb_update_rate, 0664, picolcd_fb_update_rate_show,
 		picolcd_fb_update_rate_store);
 
 /* initialize Framebuffer device */
diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c
index 2451c7e5feb..578bbe65902 100644
--- a/drivers/hid/hid-rmi.c
+++ b/drivers/hid/hid-rmi.c
@@ -428,6 +428,7 @@ static int rmi_raw_event(struct hid_device *hdev,
 	return 0;
 }
 
+#ifdef CONFIG_PM
 static int rmi_post_reset(struct hid_device *hdev)
 {
 	return rmi_set_mode(hdev, RMI_MODE_ATTN_REPORTS);
@@ -437,6 +438,7 @@ static int rmi_post_resume(struct hid_device *hdev)
 {
 	return rmi_set_mode(hdev, RMI_MODE_ATTN_REPORTS);
 }
+#endif /* CONFIG_PM */
 
 #define RMI4_MAX_PAGE 0xff
 #define RMI4_PAGE_SIZE 0x0100
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index a8d5c8faf8c..e244e449cbb 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -159,17 +159,18 @@ int sensor_hub_register_callback(struct hid_sensor_hub_device *hsdev,
 {
 	struct hid_sensor_hub_callbacks_list *callback;
 	struct sensor_hub_data *pdata = hid_get_drvdata(hsdev->hdev);
+	unsigned long flags;
 
-	spin_lock(&pdata->dyn_callback_lock);
+	spin_lock_irqsave(&pdata->dyn_callback_lock, flags);
 	list_for_each_entry(callback, &pdata->dyn_callback_list, list)
 		if (callback->usage_id == usage_id &&
 						callback->hsdev == hsdev) {
-			spin_unlock(&pdata->dyn_callback_lock);
+			spin_unlock_irqrestore(&pdata->dyn_callback_lock, flags);
 			return -EINVAL;
 		}
 	callback = kzalloc(sizeof(*callback), GFP_ATOMIC);
 	if (!callback) {
-		spin_unlock(&pdata->dyn_callback_lock);
+		spin_unlock_irqrestore(&pdata->dyn_callback_lock, flags);
 		return -ENOMEM;
 	}
 	callback->hsdev = hsdev;
@@ -177,7 +178,7 @@ int sensor_hub_register_callback(struct hid_sensor_hub_device *hsdev,
 	callback->usage_id = usage_id;
 	callback->priv = NULL;
 	list_add_tail(&callback->list, &pdata->dyn_callback_list);
-	spin_unlock(&pdata->dyn_callback_lock);
+	spin_unlock_irqrestore(&pdata->dyn_callback_lock, flags);
 
 	return 0;
 }
@@ -188,8 +189,9 @@ int sensor_hub_remove_callback(struct hid_sensor_hub_device *hsdev,
 {
 	struct hid_sensor_hub_callbacks_list *callback;
 	struct sensor_hub_data *pdata = hid_get_drvdata(hsdev->hdev);
+	unsigned long flags;
 
-	spin_lock(&pdata->dyn_callback_lock);
+	spin_lock_irqsave(&pdata->dyn_callback_lock, flags);
 	list_for_each_entry(callback, &pdata->dyn_callback_list, list)
 		if (callback->usage_id == usage_id &&
 						callback->hsdev == hsdev) {
@@ -197,7 +199,7 @@ int sensor_hub_remove_callback(struct hid_sensor_hub_device *hsdev,
 			kfree(callback);
 			break;
 		}
-	spin_unlock(&pdata->dyn_callback_lock);
+	spin_unlock_irqrestore(&pdata->dyn_callback_lock, flags);
 
 	return 0;
 }
@@ -378,15 +380,16 @@ static int sensor_hub_suspend(struct hid_device *hdev, pm_message_t message)
 {
 	struct sensor_hub_data *pdata = hid_get_drvdata(hdev);
 	struct hid_sensor_hub_callbacks_list *callback;
+	unsigned long flags;
 
 	hid_dbg(hdev, " sensor_hub_suspend\n");
-	spin_lock(&pdata->dyn_callback_lock);
+	spin_lock_irqsave(&pdata->dyn_callback_lock, flags);
 	list_for_each_entry(callback, &pdata->dyn_callback_list, list) {
 		if (callback->usage_callback->suspend)
 			callback->usage_callback->suspend(
 					callback->hsdev, callback->priv);
 	}
-	spin_unlock(&pdata->dyn_callback_lock);
+	spin_unlock_irqrestore(&pdata->dyn_callback_lock, flags);
 
 	return 0;
 }
@@ -395,15 +398,16 @@ static int sensor_hub_resume(struct hid_device *hdev)
 {
 	struct sensor_hub_data *pdata = hid_get_drvdata(hdev);
 	struct hid_sensor_hub_callbacks_list *callback;
+	unsigned long flags;
 
 	hid_dbg(hdev, " sensor_hub_resume\n");
-	spin_lock(&pdata->dyn_callback_lock);
+	spin_lock_irqsave(&pdata->dyn_callback_lock, flags);
 	list_for_each_entry(callback, &pdata->dyn_callback_list, list) {
 		if (callback->usage_callback->resume)
 			callback->usage_callback->resume(
 					callback->hsdev, callback->priv);
 	}
-	spin_unlock(&pdata->dyn_callback_lock);
+	spin_unlock_irqrestore(&pdata->dyn_callback_lock, flags);
 
 	return 0;
 }
@@ -632,6 +636,7 @@ static int sensor_hub_probe(struct hid_device *hdev,
 			if (name == NULL) {
 				hid_err(hdev, "Failed MFD device name\n");
 					ret = -ENOMEM;
+					kfree(hsdev);
 					goto err_no_mem;
 			}
 			sd->hid_sensor_hub_client_devs[
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 59badc10a08..31e6727cd00 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -49,6 +49,7 @@ static const struct hid_blacklist {
 
 	{ USB_VENDOR_ID_EMS, USB_DEVICE_ID_EMS_TRIO_LINKER_PLUS_II, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_ETURBOTOUCH, USB_DEVICE_ID_ETURBOTOUCH, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_ETURBOTOUCH, USB_DEVICE_ID_ETURBOTOUCH_2968, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_GREENASIA, USB_DEVICE_ID_GREENASIA_DUAL_USB_JOYPAD, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_PANTHERLORD, USB_DEVICE_ID_PANTHERLORD_TWIN_USB_JOYSTICK, HID_QUIRK_MULTI_INPUT | HID_QUIRK_SKIP_OUTPUT_REPORTS },
 	{ USB_VENDOR_ID_PLAYDOTCOM, USB_DEVICE_ID_PLAYDOTCOM_EMS_USBII, HID_QUIRK_MULTI_INPUT },
@@ -76,6 +77,8 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GX680R_LED_PANEL, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_NEXIO, USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_MOUSE, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_PENMOUNT, USB_DEVICE_ID_PENMOUNT_1610, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_PENMOUNT, USB_DEVICE_ID_PENMOUNT_1640, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN1, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN2, HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hsi/clients/Kconfig b/drivers/hsi/clients/Kconfig
index 71b9f9ab86e..bc60dec3f58 100644
--- a/drivers/hsi/clients/Kconfig
+++ b/drivers/hsi/clients/Kconfig
@@ -15,7 +15,7 @@ config NOKIA_MODEM
 
 config SSI_PROTOCOL
 	tristate "SSI protocol"
-	depends on HSI && PHONET && (OMAP_SSI=y || OMAP_SSI=m)
+	depends on HSI && PHONET && OMAP_SSI
 	help
 	If you say Y here, you will enable the SSI protocol aka McSAAB.
 
diff --git a/drivers/hsi/controllers/omap_ssi_port.c b/drivers/hsi/controllers/omap_ssi_port.c
index b8693f0b27f..29aea0b9336 100644
--- a/drivers/hsi/controllers/omap_ssi_port.c
+++ b/drivers/hsi/controllers/omap_ssi_port.c
@@ -1116,8 +1116,7 @@ static int __init ssi_port_probe(struct platform_device *pd)
 
 	dev_dbg(&pd->dev, "init ssi port...\n");
 
-	err = ref_module(THIS_MODULE, ssi->owner);
-	if (err) {
+	if (!try_module_get(ssi->owner)) {
 		dev_err(&pd->dev, "could not increment parent module refcount (err=%d)\n",
 			err);
 		return -ENODEV;
@@ -1254,6 +1253,7 @@ static int __exit ssi_port_remove(struct platform_device *pd)
 
 	omap_ssi->port[omap_port->port_id] = NULL;
 	platform_set_drvdata(pd, NULL);
+	module_put(ssi->owner);
 	pm_runtime_disable(&pd->dev);
 
 	return 0;
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 6c8b032cacb..ed9350d4276 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -404,7 +404,7 @@ static u32  next_vp;
  * performance critical channels (IDE, SCSI and Network) will be uniformly
  * distributed across all available CPUs.
  */
-static void init_vp_index(struct vmbus_channel *channel, uuid_le *type_guid)
+static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_guid)
 {
 	u32 cur_cpu;
 	int i;
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index e84f4526eb3..ae22e3c1fc4 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -339,9 +339,13 @@ static void process_chn_event(u32 relid)
 		 */
 
 		do {
-			hv_begin_read(&channel->inbound);
+			if (read_state)
+				hv_begin_read(&channel->inbound);
 			channel->onchannel_callback(arg);
-			bytes_to_read = hv_end_read(&channel->inbound);
+			if (read_state)
+				bytes_to_read = hv_end_read(&channel->inbound);
+			else
+				bytes_to_read = 0;
 		} while (read_state && (bytes_to_read != 0));
 	} else {
 		pr_err("no channel callback for relid - %u\n", relid);
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index eaaa3d843b8..23b2ce294c4 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -246,8 +246,8 @@ void hv_fcopy_onchannelcallback(void *context)
 		/*
 		 * Send the information to the user-level daemon.
 		 */
-		fcopy_send_data();
 		schedule_delayed_work(&fcopy_work, 5*HZ);
+		fcopy_send_data();
 		return;
 	}
 	icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index ea852537307..521c14625b3 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -127,6 +127,17 @@ kvp_work_func(struct work_struct *dummy)
 	kvp_respond_to_host(NULL, HV_E_FAIL);
 }
 
+static void poll_channel(struct vmbus_channel *channel)
+{
+	if (channel->target_cpu != smp_processor_id())
+		smp_call_function_single(channel->target_cpu,
+					 hv_kvp_onchannelcallback,
+					 channel, true);
+	else
+		hv_kvp_onchannelcallback(channel);
+}
+
+
 static int kvp_handle_handshake(struct hv_kvp_msg *msg)
 {
 	int ret = 1;
@@ -155,7 +166,7 @@ static int kvp_handle_handshake(struct hv_kvp_msg *msg)
 		kvp_register(dm_reg_value);
 		kvp_transaction.active = false;
 		if (kvp_transaction.kvp_context)
-			hv_kvp_onchannelcallback(kvp_transaction.kvp_context);
+			poll_channel(kvp_transaction.kvp_context);
 	}
 	return ret;
 }
@@ -568,7 +579,7 @@ response_done:
 
 	vmbus_sendpacket(channel, recv_buffer, buf_len, req_id,
 				VM_PKT_DATA_INBAND, 0);
-
+	poll_channel(channel);
 }
 
 /*
@@ -603,7 +614,7 @@ void hv_kvp_onchannelcallback(void *context)
 		return;
 	}
 
-	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
+	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 4, &recvlen,
 			 &requestid);
 
 	if (recvlen > 0) {
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index dd761806f0e..3b9c9ef0deb 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -319,7 +319,7 @@ static int util_probe(struct hv_device *dev,
 		(struct hv_util_service *)dev_id->driver_data;
 	int ret;
 
-	srv->recv_buffer = kmalloc(PAGE_SIZE * 2, GFP_KERNEL);
+	srv->recv_buffer = kmalloc(PAGE_SIZE * 4, GFP_KERNEL);
 	if (!srv->recv_buffer)
 		return -ENOMEM;
 	if (srv->util_init) {
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 18d1a8404cb..22b750749a3 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -649,9 +649,9 @@ extern struct vmbus_connection vmbus_connection;
 
 /* General vmbus interface */
 
-struct hv_device *vmbus_device_create(uuid_le *type,
-					 uuid_le *instance,
-					 struct vmbus_channel *channel);
+struct hv_device *vmbus_device_create(const uuid_le *type,
+				      const uuid_le *instance,
+				      struct vmbus_channel *channel);
 
 int vmbus_device_register(struct hv_device *child_device_obj);
 void vmbus_device_unregister(struct hv_device *device_obj);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 8e53a3c2607..4d6b26979fb 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -435,7 +435,7 @@ static int vmbus_uevent(struct device *device, struct kobj_uevent_env *env)
 	return ret;
 }
 
-static uuid_le null_guid;
+static const uuid_le null_guid;
 
 static inline bool is_null_guid(const __u8 *guid)
 {
@@ -450,7 +450,7 @@ static inline bool is_null_guid(const __u8 *guid)
  */
 static const struct hv_vmbus_device_id *hv_vmbus_get_id(
 					const struct hv_vmbus_device_id *id,
-					__u8 *guid)
+					const __u8 *guid)
 {
 	for (; !is_null_guid(id->guid); id++)
 		if (!memcmp(&id->guid, guid, sizeof(uuid_le)))
@@ -779,9 +779,9 @@ EXPORT_SYMBOL_GPL(vmbus_driver_unregister);
  * vmbus_device_create - Creates and registers a new child device
  * on the vmbus.
  */
-struct hv_device *vmbus_device_create(uuid_le *type,
-					    uuid_le *instance,
-					    struct vmbus_channel *channel)
+struct hv_device *vmbus_device_create(const uuid_le *type,
+				      const uuid_le *instance,
+				      struct vmbus_channel *channel)
 {
 	struct hv_device *child_device_obj;
 
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 00343166feb..02d3d85829f 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1052,7 +1052,7 @@ config SENSORS_PC87427
 	  will be called pc87427.
 
 config SENSORS_NTC_THERMISTOR
-	tristate "NTC thermistor support"
+	tristate "NTC thermistor support from Murata"
 	depends on !OF || IIO=n || IIO
 	help
 	  This driver supports NTC thermistors sensor reading and its
@@ -1060,7 +1060,8 @@ config SENSORS_NTC_THERMISTOR
 	  send notifications about the temperature.
 
 	  Currently, this driver supports
-	  NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, and NCP15WL333.
+	  NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473, and NCP15WL333
+	  from Murata.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called ntc-thermistor.
@@ -1124,6 +1125,16 @@ config SENSORS_SHT21
 	  This driver can also be built as a module.  If so, the module
 	  will be called sht21.
 
+config SENSORS_SHTC1
+	tristate "Sensiron humidity and temperature sensors. SHTC1 and compat."
+	depends on I2C
+	help
+	  If you say yes here you get support for the Sensiron SHTC1 and SHTW1
+	  humidity and temperature sensors.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called shtc1.
+
 config SENSORS_S3C
 	tristate "Samsung built-in ADC"
 	depends on S3C_ADC
@@ -1166,6 +1177,7 @@ config SENSORS_DME1737
 config SENSORS_EMC1403
 	tristate "SMSC EMC1403/23 thermal sensor"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	  If you say yes here you get support for the SMSC EMC1403/23
 	  temperature monitoring chip.
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index 11798ad7e80..3dc0f02f71d 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -126,6 +126,7 @@ obj-$(CONFIG_SENSORS_SCH5627)	+= sch5627.o
 obj-$(CONFIG_SENSORS_SCH5636)	+= sch5636.o
 obj-$(CONFIG_SENSORS_SHT15)	+= sht15.o
 obj-$(CONFIG_SENSORS_SHT21)	+= sht21.o
+obj-$(CONFIG_SENSORS_SHTC1)	+= shtc1.o
 obj-$(CONFIG_SENSORS_SIS5595)	+= sis5595.o
 obj-$(CONFIG_SENSORS_SMM665)	+= smm665.o
 obj-$(CONFIG_SENSORS_SMSC47B397)+= smsc47b397.o
diff --git a/drivers/hwmon/adc128d818.c b/drivers/hwmon/adc128d818.c
index 5ffd81f19d0..0625e50d7a6 100644
--- a/drivers/hwmon/adc128d818.c
+++ b/drivers/hwmon/adc128d818.c
@@ -239,50 +239,50 @@ static ssize_t adc128_show_alarm(struct device *dev,
 	return sprintf(buf, "%u\n", !!(alarms & mask));
 }
 
-static SENSOR_DEVICE_ATTR_2(in0_input, S_IWUSR | S_IRUGO,
-			    adc128_show_in, adc128_set_in, 0, 0);
+static SENSOR_DEVICE_ATTR_2(in0_input, S_IRUGO,
+			    adc128_show_in, NULL, 0, 0);
 static SENSOR_DEVICE_ATTR_2(in0_min, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 0, 1);
 static SENSOR_DEVICE_ATTR_2(in0_max, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 0, 2);
 
-static SENSOR_DEVICE_ATTR_2(in1_input, S_IWUSR | S_IRUGO,
-			    adc128_show_in, adc128_set_in, 1, 0);
+static SENSOR_DEVICE_ATTR_2(in1_input, S_IRUGO,
+			    adc128_show_in, NULL, 1, 0);
 static SENSOR_DEVICE_ATTR_2(in1_min, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 1, 1);
 static SENSOR_DEVICE_ATTR_2(in1_max, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 1, 2);
 
-static SENSOR_DEVICE_ATTR_2(in2_input, S_IWUSR | S_IRUGO,
-			    adc128_show_in, adc128_set_in, 2, 0);
+static SENSOR_DEVICE_ATTR_2(in2_input, S_IRUGO,
+			    adc128_show_in, NULL, 2, 0);
 static SENSOR_DEVICE_ATTR_2(in2_min, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 2, 1);
 static SENSOR_DEVICE_ATTR_2(in2_max, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 2, 2);
 
-static SENSOR_DEVICE_ATTR_2(in3_input, S_IWUSR | S_IRUGO,
-			    adc128_show_in, adc128_set_in, 3, 0);
+static SENSOR_DEVICE_ATTR_2(in3_input, S_IRUGO,
+			    adc128_show_in, NULL, 3, 0);
 static SENSOR_DEVICE_ATTR_2(in3_min, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 3, 1);
 static SENSOR_DEVICE_ATTR_2(in3_max, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 3, 2);
 
-static SENSOR_DEVICE_ATTR_2(in4_input, S_IWUSR | S_IRUGO,
-			    adc128_show_in, adc128_set_in, 4, 0);
+static SENSOR_DEVICE_ATTR_2(in4_input, S_IRUGO,
+			    adc128_show_in, NULL, 4, 0);
 static SENSOR_DEVICE_ATTR_2(in4_min, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 4, 1);
 static SENSOR_DEVICE_ATTR_2(in4_max, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 4, 2);
 
-static SENSOR_DEVICE_ATTR_2(in5_input, S_IWUSR | S_IRUGO,
-			    adc128_show_in, adc128_set_in, 5, 0);
+static SENSOR_DEVICE_ATTR_2(in5_input, S_IRUGO,
+			    adc128_show_in, NULL, 5, 0);
 static SENSOR_DEVICE_ATTR_2(in5_min, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 5, 1);
 static SENSOR_DEVICE_ATTR_2(in5_max, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 5, 2);
 
-static SENSOR_DEVICE_ATTR_2(in6_input, S_IWUSR | S_IRUGO,
-			    adc128_show_in, adc128_set_in, 6, 0);
+static SENSOR_DEVICE_ATTR_2(in6_input, S_IRUGO,
+			    adc128_show_in, NULL, 6, 0);
 static SENSOR_DEVICE_ATTR_2(in6_min, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 6, 1);
 static SENSOR_DEVICE_ATTR_2(in6_max, S_IWUSR | S_IRUGO,
diff --git a/drivers/hwmon/adm1021.c b/drivers/hwmon/adm1021.c
index 3eb4281689b..d74241bb278 100644
--- a/drivers/hwmon/adm1021.c
+++ b/drivers/hwmon/adm1021.c
@@ -185,7 +185,7 @@ static ssize_t set_temp_max(struct device *dev,
 	struct adm1021_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
 	long temp;
-	int err;
+	int reg_val, err;
 
 	err = kstrtol(buf, 10, &temp);
 	if (err)
@@ -193,10 +193,11 @@ static ssize_t set_temp_max(struct device *dev,
 	temp /= 1000;
 
 	mutex_lock(&data->update_lock);
-	data->temp_max[index] = clamp_val(temp, -128, 127);
+	reg_val = clamp_val(temp, -128, 127);
+	data->temp_max[index] = reg_val * 1000;
 	if (!read_only)
 		i2c_smbus_write_byte_data(client, ADM1021_REG_TOS_W(index),
-					  data->temp_max[index]);
+					  reg_val);
 	mutex_unlock(&data->update_lock);
 
 	return count;
@@ -210,7 +211,7 @@ static ssize_t set_temp_min(struct device *dev,
 	struct adm1021_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
 	long temp;
-	int err;
+	int reg_val, err;
 
 	err = kstrtol(buf, 10, &temp);
 	if (err)
@@ -218,10 +219,11 @@ static ssize_t set_temp_min(struct device *dev,
 	temp /= 1000;
 
 	mutex_lock(&data->update_lock);
-	data->temp_min[index] = clamp_val(temp, -128, 127);
+	reg_val = clamp_val(temp, -128, 127);
+	data->temp_min[index] = reg_val * 1000;
 	if (!read_only)
 		i2c_smbus_write_byte_data(client, ADM1021_REG_THYST_W(index),
-					  data->temp_min[index]);
+					  reg_val);
 	mutex_unlock(&data->update_lock);
 
 	return count;
diff --git a/drivers/hwmon/adm1029.c b/drivers/hwmon/adm1029.c
index 78339e880bd..2804571b269 100644
--- a/drivers/hwmon/adm1029.c
+++ b/drivers/hwmon/adm1029.c
@@ -232,6 +232,9 @@ static ssize_t set_fan_div(struct device *dev,
 	/* Update the value */
 	reg = (reg & 0x3F) | (val << 6);
 
+	/* Update the cache */
+	data->fan_div[attr->index] = reg;
+
 	/* Write value */
 	i2c_smbus_write_byte_data(client,
 				  ADM1029_REG_FAN_DIV[attr->index], reg);
diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c
index a8a540ca8c3..51c1a5a165a 100644
--- a/drivers/hwmon/adm1031.c
+++ b/drivers/hwmon/adm1031.c
@@ -365,6 +365,7 @@ set_auto_temp_min(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
+	val = clamp_val(val, 0, 127000);
 	mutex_lock(&data->update_lock);
 	data->auto_temp[nr] = AUTO_TEMP_MIN_TO_REG(val, data->auto_temp[nr]);
 	adm1031_write_value(client, ADM1031_REG_AUTO_TEMP(nr),
@@ -394,6 +395,7 @@ set_auto_temp_max(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
+	val = clamp_val(val, 0, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_max[nr] = AUTO_TEMP_MAX_TO_REG(val, data->auto_temp[nr],
 						  data->pwm[nr]);
@@ -696,7 +698,7 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+	val = clamp_val(val, -55000, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_min[nr] = TEMP_TO_REG(val);
 	adm1031_write_value(client, ADM1031_REG_TEMP_MIN(nr),
@@ -717,7 +719,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+	val = clamp_val(val, -55000, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_max[nr] = TEMP_TO_REG(val);
 	adm1031_write_value(client, ADM1031_REG_TEMP_MAX(nr),
@@ -738,7 +740,7 @@ static ssize_t set_temp_crit(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		return ret;
 
-	val = clamp_val(val, -55000, nr == 0 ? 127750 : 127875);
+	val = clamp_val(val, -55000, 127000);
 	mutex_lock(&data->update_lock);
 	data->temp_crit[nr] = TEMP_TO_REG(val);
 	adm1031_write_value(client, ADM1031_REG_TEMP_CRIT(nr),
diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c
index 0f4dea5ccf1..9ee3913850d 100644
--- a/drivers/hwmon/adt7470.c
+++ b/drivers/hwmon/adt7470.c
@@ -515,7 +515,7 @@ static ssize_t set_temp_min(struct device *dev,
 		return -EINVAL;
 
 	temp = DIV_ROUND_CLOSEST(temp, 1000);
-	temp = clamp_val(temp, 0, 255);
+	temp = clamp_val(temp, -128, 127);
 
 	mutex_lock(&data->lock);
 	data->temp_min[attr->index] = temp;
@@ -549,7 +549,7 @@ static ssize_t set_temp_max(struct device *dev,
 		return -EINVAL;
 
 	temp = DIV_ROUND_CLOSEST(temp, 1000);
-	temp = clamp_val(temp, 0, 255);
+	temp = clamp_val(temp, -128, 127);
 
 	mutex_lock(&data->lock);
 	data->temp_max[attr->index] = temp;
@@ -826,7 +826,7 @@ static ssize_t set_pwm_tmin(struct device *dev,
 		return -EINVAL;
 
 	temp = DIV_ROUND_CLOSEST(temp, 1000);
-	temp = clamp_val(temp, 0, 255);
+	temp = clamp_val(temp, -128, 127);
 
 	mutex_lock(&data->lock);
 	data->pwm_tmin[attr->index] = temp;
diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index eea81729651..9f2be3dd28f 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -704,7 +704,7 @@ static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO,
 	get_temp_alarm, NULL, IDX_TEMP1_MAX);
 static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO,
 	get_temp_alarm, NULL, IDX_TEMP1_CRIT);
-static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO,
 	get_temp, NULL, IDX_TEMP2_INPUT);
 static SENSOR_DEVICE_ATTR(temp2_min, S_IRUGO | S_IWUSR, get_temp,
 	set_temp, IDX_TEMP2_MIN);
diff --git a/drivers/hwmon/atxp1.c b/drivers/hwmon/atxp1.c
index 6edce42c61d..2ae8a304b5e 100644
--- a/drivers/hwmon/atxp1.c
+++ b/drivers/hwmon/atxp1.c
@@ -45,30 +45,6 @@ MODULE_AUTHOR("Sebastian Witt <se.witt@gmx.net>");
 
 static const unsigned short normal_i2c[] = { 0x37, 0x4e, I2C_CLIENT_END };
 
-static int atxp1_probe(struct i2c_client *client,
-		       const struct i2c_device_id *id);
-static int atxp1_remove(struct i2c_client *client);
-static struct atxp1_data *atxp1_update_device(struct device *dev);
-static int atxp1_detect(struct i2c_client *client, struct i2c_board_info *info);
-
-static const struct i2c_device_id atxp1_id[] = {
-	{ "atxp1", 0 },
-	{ }
-};
-MODULE_DEVICE_TABLE(i2c, atxp1_id);
-
-static struct i2c_driver atxp1_driver = {
-	.class		= I2C_CLASS_HWMON,
-	.driver = {
-		.name	= "atxp1",
-	},
-	.probe		= atxp1_probe,
-	.remove		= atxp1_remove,
-	.id_table	= atxp1_id,
-	.detect		= atxp1_detect,
-	.address_list	= normal_i2c,
-};
-
 struct atxp1_data {
 	struct device *hwmon_dev;
 	struct mutex update_lock;
@@ -386,4 +362,22 @@ static int atxp1_remove(struct i2c_client *client)
 	return 0;
 };
 
+static const struct i2c_device_id atxp1_id[] = {
+	{ "atxp1", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, atxp1_id);
+
+static struct i2c_driver atxp1_driver = {
+	.class		= I2C_CLASS_HWMON,
+	.driver = {
+		.name	= "atxp1",
+	},
+	.probe		= atxp1_probe,
+	.remove		= atxp1_remove,
+	.id_table	= atxp1_id,
+	.detect		= atxp1_detect,
+	.address_list	= normal_i2c,
+};
+
 module_i2c_driver(atxp1_driver);
diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c
index afd31042b45..d14ab3c45da 100644
--- a/drivers/hwmon/da9052-hwmon.c
+++ b/drivers/hwmon/da9052-hwmon.c
@@ -194,7 +194,7 @@ static ssize_t da9052_hwmon_show_name(struct device *dev,
 				      struct device_attribute *devattr,
 				      char *buf)
 {
-	return sprintf(buf, "da9052-hwmon\n");
+	return sprintf(buf, "da9052\n");
 }
 
 static ssize_t show_label(struct device *dev,
diff --git a/drivers/hwmon/da9055-hwmon.c b/drivers/hwmon/da9055-hwmon.c
index 73b3865f120..35eb7738d71 100644
--- a/drivers/hwmon/da9055-hwmon.c
+++ b/drivers/hwmon/da9055-hwmon.c
@@ -204,7 +204,7 @@ static ssize_t da9055_hwmon_show_name(struct device *dev,
 				      struct device_attribute *devattr,
 				      char *buf)
 {
-	return sprintf(buf, "da9055-hwmon\n");
+	return sprintf(buf, "da9055\n");
 }
 
 static ssize_t show_label(struct device *dev,
diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c
index fd892dd48e4..78002de46cb 100644
--- a/drivers/hwmon/emc2103.c
+++ b/drivers/hwmon/emc2103.c
@@ -250,9 +250,7 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *da,
 	if (result < 0)
 		return result;
 
-	val = DIV_ROUND_CLOSEST(val, 1000);
-	if ((val < -63) || (val > 127))
-		return -EINVAL;
+	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), -63, 127);
 
 	mutex_lock(&data->update_lock);
 	data->temp_min[nr] = val;
@@ -274,9 +272,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *da,
 	if (result < 0)
 		return result;
 
-	val = DIV_ROUND_CLOSEST(val, 1000);
-	if ((val < -63) || (val > 127))
-		return -EINVAL;
+	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), -63, 127);
 
 	mutex_lock(&data->update_lock);
 	data->temp_max[nr] = val;
@@ -390,15 +386,14 @@ static ssize_t set_fan_target(struct device *dev, struct device_attribute *da,
 {
 	struct emc2103_data *data = emc2103_update_device(dev);
 	struct i2c_client *client = to_i2c_client(dev);
-	long rpm_target;
+	unsigned long rpm_target;
 
-	int result = kstrtol(buf, 10, &rpm_target);
+	int result = kstrtoul(buf, 10, &rpm_target);
 	if (result < 0)
 		return result;
 
 	/* Datasheet states 16384 as maximum RPM target (table 3.2) */
-	if ((rpm_target < 0) || (rpm_target > 16384))
-		return -EINVAL;
+	rpm_target = clamp_val(rpm_target, 0, 16384);
 
 	mutex_lock(&data->update_lock);
 
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index ba35e4d530b..2566c43dd1e 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -538,7 +538,7 @@ static int gpio_fan_probe(struct platform_device *pdev)
 
 	/* Make this driver part of hwmon class. */
 	fan_data->hwmon_dev = hwmon_device_register_with_groups(&pdev->dev,
-						"gpio-fan", fan_data,
+						"gpio_fan", fan_data,
 						gpio_fan_groups);
 	if (IS_ERR(fan_data->hwmon_dev))
 		return PTR_ERR(fan_data->hwmon_dev);
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 93d26e8af3e..bfd3f3eeabc 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -148,7 +148,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg)
 
 	switch (reg) {
 	case INA2XX_SHUNT_VOLTAGE:
-		val = DIV_ROUND_CLOSEST(data->regs[reg],
+		/* signed register */
+		val = DIV_ROUND_CLOSEST((s16)data->regs[reg],
 					data->config->shunt_div);
 		break;
 	case INA2XX_BUS_VOLTAGE:
@@ -160,8 +161,8 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg)
 		val = data->regs[reg] * data->config->power_lsb;
 		break;
 	case INA2XX_CURRENT:
-		/* LSB=1mA (selected). Is in mA */
-		val = data->regs[reg];
+		/* signed register, LSB=1mA (selected), in mA */
+		val = (s16)data->regs[reg];
 		break;
 	default:
 		/* programmer goofed */
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index bed4af35830..b0129a54e1a 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -5,7 +5,7 @@
  * Copyright (c) 2002, 2003  Philip Pokorny <ppokorny@penguincomputing.com>
  * Copyright (c) 2003        Margit Schubert-While <margitsw@t-online.de>
  * Copyright (c) 2004        Justin Thiessen <jthiessen@penguincomputing.com>
- * Copyright (C) 2007--2009  Jean Delvare <jdelvare@suse.de>
+ * Copyright (C) 2007--2014  Jean Delvare <jdelvare@suse.de>
  *
  * Chip details at	      <http://www.national.com/ds/LM/LM85.pdf>
  *
@@ -39,7 +39,7 @@
 static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, I2C_CLIENT_END };
 
 enum chips {
-	any_chip, lm85b, lm85c,
+	lm85,
 	adm1027, adt7463, adt7468,
 	emc6d100, emc6d102, emc6d103, emc6d103s
 };
@@ -75,9 +75,6 @@ enum chips {
 #define LM85_COMPANY_NATIONAL		0x01
 #define LM85_COMPANY_ANALOG_DEV		0x41
 #define LM85_COMPANY_SMSC		0x5c
-#define LM85_VERSTEP_VMASK              0xf0
-#define LM85_VERSTEP_GENERIC		0x60
-#define LM85_VERSTEP_GENERIC2		0x70
 #define LM85_VERSTEP_LM85C		0x60
 #define LM85_VERSTEP_LM85B		0x62
 #define LM85_VERSTEP_LM96000_1		0x68
@@ -351,9 +348,9 @@ static const struct i2c_device_id lm85_id[] = {
 	{ "adm1027", adm1027 },
 	{ "adt7463", adt7463 },
 	{ "adt7468", adt7468 },
-	{ "lm85", any_chip },
-	{ "lm85b", lm85b },
-	{ "lm85c", lm85c },
+	{ "lm85", lm85 },
+	{ "lm85b", lm85 },
+	{ "lm85c", lm85 },
 	{ "emc6d100", emc6d100 },
 	{ "emc6d101", emc6d100 },
 	{ "emc6d102", emc6d102 },
@@ -1281,7 +1278,7 @@ static int lm85_detect(struct i2c_client *client, struct i2c_board_info *info)
 {
 	struct i2c_adapter *adapter = client->adapter;
 	int address = client->addr;
-	const char *type_name;
+	const char *type_name = NULL;
 	int company, verstep;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
@@ -1297,16 +1294,6 @@ static int lm85_detect(struct i2c_client *client, struct i2c_board_info *info)
 		"Detecting device at 0x%02x with COMPANY: 0x%02x and VERSTEP: 0x%02x\n",
 		address, company, verstep);
 
-	/* All supported chips have the version in common */
-	if ((verstep & LM85_VERSTEP_VMASK) != LM85_VERSTEP_GENERIC &&
-	    (verstep & LM85_VERSTEP_VMASK) != LM85_VERSTEP_GENERIC2) {
-		dev_dbg(&adapter->dev,
-			"Autodetection failed: unsupported version\n");
-		return -ENODEV;
-	}
-	type_name = "lm85";
-
-	/* Now, refine the detection */
 	if (company == LM85_COMPANY_NATIONAL) {
 		switch (verstep) {
 		case LM85_VERSTEP_LM85C:
@@ -1323,6 +1310,7 @@ static int lm85_detect(struct i2c_client *client, struct i2c_board_info *info)
 					"Found Winbond WPCD377I, ignoring\n");
 				return -ENODEV;
 			}
+			type_name = "lm85";
 			break;
 		}
 	} else if (company == LM85_COMPANY_ANALOG_DEV) {
@@ -1357,12 +1345,11 @@ static int lm85_detect(struct i2c_client *client, struct i2c_board_info *info)
 			type_name = "emc6d103s";
 			break;
 		}
-	} else {
-		dev_dbg(&adapter->dev,
-			"Autodetection failed: unknown vendor\n");
-		return -ENODEV;
 	}
 
+	if (!type_name)
+		return -ENODEV;
+
 	strlcpy(info->type, type_name, I2C_NAME_SIZE);
 
 	return 0;
diff --git a/drivers/hwmon/ltc4151.c b/drivers/hwmon/ltc4151.c
index af81be1237c..c86a1840249 100644
--- a/drivers/hwmon/ltc4151.c
+++ b/drivers/hwmon/ltc4151.c
@@ -47,7 +47,7 @@
 #define LTC4151_ADIN_L	0x05
 
 struct ltc4151_data {
-	struct device *hwmon_dev;
+	struct i2c_client *client;
 
 	struct mutex update_lock;
 	bool valid;
@@ -59,8 +59,8 @@ struct ltc4151_data {
 
 static struct ltc4151_data *ltc4151_update_device(struct device *dev)
 {
-	struct i2c_client *client = to_i2c_client(dev);
-	struct ltc4151_data *data = i2c_get_clientdata(client);
+	struct ltc4151_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
 	struct ltc4151_data *ret = data;
 
 	mutex_lock(&data->update_lock);
@@ -159,7 +159,7 @@ static SENSOR_DEVICE_ATTR(curr1_input, S_IRUGO, ltc4151_show_value, NULL,
  * Finally, construct an array of pointers to members of the above objects,
  * as required for sysfs_create_group()
  */
-static struct attribute *ltc4151_attributes[] = {
+static struct attribute *ltc4151_attrs[] = {
 	&sensor_dev_attr_in1_input.dev_attr.attr,
 	&sensor_dev_attr_in2_input.dev_attr.attr,
 
@@ -167,54 +167,30 @@ static struct attribute *ltc4151_attributes[] = {
 
 	NULL,
 };
-
-static const struct attribute_group ltc4151_group = {
-	.attrs = ltc4151_attributes,
-};
+ATTRIBUTE_GROUPS(ltc4151);
 
 static int ltc4151_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
 	struct i2c_adapter *adapter = client->adapter;
+	struct device *dev = &client->dev;
 	struct ltc4151_data *data;
-	int ret;
+	struct device *hwmon_dev;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
 		return -ENODEV;
 
-	data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL);
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	i2c_set_clientdata(client, data);
+	data->client = client;
 	mutex_init(&data->update_lock);
 
-	/* Register sysfs hooks */
-	ret = sysfs_create_group(&client->dev.kobj, &ltc4151_group);
-	if (ret)
-		return ret;
-
-	data->hwmon_dev = hwmon_device_register(&client->dev);
-	if (IS_ERR(data->hwmon_dev)) {
-		ret = PTR_ERR(data->hwmon_dev);
-		goto out_hwmon_device_register;
-	}
-
-	return 0;
-
-out_hwmon_device_register:
-	sysfs_remove_group(&client->dev.kobj, &ltc4151_group);
-	return ret;
-}
-
-static int ltc4151_remove(struct i2c_client *client)
-{
-	struct ltc4151_data *data = i2c_get_clientdata(client);
-
-	hwmon_device_unregister(data->hwmon_dev);
-	sysfs_remove_group(&client->dev.kobj, &ltc4151_group);
-
-	return 0;
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name,
+							   data,
+							   ltc4151_groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static const struct i2c_device_id ltc4151_id[] = {
@@ -229,7 +205,6 @@ static struct i2c_driver ltc4151_driver = {
 		.name	= "ltc4151",
 	},
 	.probe		= ltc4151_probe,
-	.remove		= ltc4151_remove,
 	.id_table	= ltc4151_id,
 };
 
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index e76feb86a1d..ae66f42c4d6 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -163,6 +163,18 @@ static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 }
 
 static const struct of_device_id ntc_match[] = {
+	{ .compatible = "murata,ncp15wb473",
+		.data = &ntc_thermistor_id[0] },
+	{ .compatible = "murata,ncp18wb473",
+		.data = &ntc_thermistor_id[1] },
+	{ .compatible = "murata,ncp21wb473",
+		.data = &ntc_thermistor_id[2] },
+	{ .compatible = "murata,ncp03wb473",
+		.data = &ntc_thermistor_id[3] },
+	{ .compatible = "murata,ncp15wl333",
+		.data = &ntc_thermistor_id[4] },
+
+	/* Usage of vendor name "ntc" is deprecated */
 	{ .compatible = "ntc,ncp15wb473",
 		.data = &ntc_thermistor_id[0] },
 	{ .compatible = "ntc,ncp18wb473",
@@ -500,7 +512,7 @@ static int ntc_thermistor_probe(struct platform_device *pdev)
 	}
 
 	dev_info(&pdev->dev, "Thermistor type: %s successfully probed.\n",
-								pdev->name);
+								pdev_id->name);
 
 	return 0;
 err_after_sysfs:
@@ -534,7 +546,7 @@ static struct platform_driver ntc_thermistor_driver = {
 
 module_platform_driver(ntc_thermistor_driver);
 
-MODULE_DESCRIPTION("NTC Thermistor Driver");
+MODULE_DESCRIPTION("NTC Thermistor Driver from Murata");
 MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:ntc-thermistor");
diff --git a/drivers/hwmon/shtc1.c b/drivers/hwmon/shtc1.c
new file mode 100644
index 00000000000..decd7df995a
--- /dev/null
+++ b/drivers/hwmon/shtc1.c
@@ -0,0 +1,251 @@
+/* Sensirion SHTC1 humidity and temperature sensor driver
+ *
+ * Copyright (C) 2014 Sensirion AG, Switzerland
+ * Author: Johannes Winkelmann <johannes.winkelmann@sensirion.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/platform_data/shtc1.h>
+
+/* commands (high precision mode) */
+static const unsigned char shtc1_cmd_measure_blocking_hpm[]    = { 0x7C, 0xA2 };
+static const unsigned char shtc1_cmd_measure_nonblocking_hpm[] = { 0x78, 0x66 };
+
+/* commands (low precision mode) */
+static const unsigned char shtc1_cmd_measure_blocking_lpm[]    = { 0x64, 0x58 };
+static const unsigned char shtc1_cmd_measure_nonblocking_lpm[] = { 0x60, 0x9c };
+
+/* command for reading the ID register */
+static const unsigned char shtc1_cmd_read_id_reg[]	       = { 0xef, 0xc8 };
+
+/* constants for reading the ID register */
+#define SHTC1_ID	  0x07
+#define SHTC1_ID_REG_MASK 0x1f
+
+/* delays for non-blocking i2c commands, both in us */
+#define SHTC1_NONBLOCKING_WAIT_TIME_HPM  14400
+#define SHTC1_NONBLOCKING_WAIT_TIME_LPM   1000
+
+#define SHTC1_CMD_LENGTH      2
+#define SHTC1_RESPONSE_LENGTH 6
+
+struct shtc1_data {
+	struct i2c_client *client;
+	struct mutex update_lock;
+	bool valid;
+	unsigned long last_updated; /* in jiffies */
+
+	const unsigned char *command;
+	unsigned int nonblocking_wait_time; /* in us */
+
+	struct shtc1_platform_data setup;
+
+	int temperature; /* 1000 * temperature in dgr C */
+	int humidity; /* 1000 * relative humidity in %RH */
+};
+
+static int shtc1_update_values(struct i2c_client *client,
+			       struct shtc1_data *data,
+			       char *buf, int bufsize)
+{
+	int ret = i2c_master_send(client, data->command, SHTC1_CMD_LENGTH);
+	if (ret != SHTC1_CMD_LENGTH) {
+		dev_err(&client->dev, "failed to send command: %d\n", ret);
+		return ret < 0 ? ret : -EIO;
+	}
+
+	/*
+	 * In blocking mode (clock stretching mode) the I2C bus
+	 * is blocked for other traffic, thus the call to i2c_master_recv()
+	 * will wait until the data is ready. For non blocking mode, we
+	 * have to wait ourselves.
+	 */
+	if (!data->setup.blocking_io)
+		usleep_range(data->nonblocking_wait_time,
+			     data->nonblocking_wait_time + 1000);
+
+	ret = i2c_master_recv(client, buf, bufsize);
+	if (ret != bufsize) {
+		dev_err(&client->dev, "failed to read values: %d\n", ret);
+		return ret < 0 ? ret : -EIO;
+	}
+
+	return 0;
+}
+
+/* sysfs attributes */
+static struct shtc1_data *shtc1_update_client(struct device *dev)
+{
+	struct shtc1_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	unsigned char buf[SHTC1_RESPONSE_LENGTH];
+	int val;
+	int ret = 0;
+
+	mutex_lock(&data->update_lock);
+
+	if (time_after(jiffies, data->last_updated + HZ / 10) || !data->valid) {
+		ret = shtc1_update_values(client, data, buf, sizeof(buf));
+		if (ret)
+			goto out;
+
+		/*
+		 * From datasheet:
+		 * T = -45 + 175 * ST / 2^16
+		 * RH = 100 * SRH / 2^16
+		 *
+		 * Adapted for integer fixed point (3 digit) arithmetic.
+		 */
+		val = be16_to_cpup((__be16 *)buf);
+		data->temperature = ((21875 * val) >> 13) - 45000;
+		val = be16_to_cpup((__be16 *)(buf + 3));
+		data->humidity = ((12500 * val) >> 13);
+
+		data->last_updated = jiffies;
+		data->valid = true;
+	}
+
+out:
+	mutex_unlock(&data->update_lock);
+
+	return ret == 0 ? data : ERR_PTR(ret);
+}
+
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr,
+				char *buf)
+{
+	struct shtc1_data *data = shtc1_update_client(dev);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	return sprintf(buf, "%d\n", data->temperature);
+}
+
+static ssize_t humidity1_input_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct shtc1_data *data = shtc1_update_client(dev);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	return sprintf(buf, "%d\n", data->humidity);
+}
+
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RO(humidity1_input);
+
+static struct attribute *shtc1_attrs[] = {
+	&dev_attr_temp1_input.attr,
+	&dev_attr_humidity1_input.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(shtc1);
+
+static void shtc1_select_command(struct shtc1_data *data)
+{
+	if (data->setup.high_precision) {
+		data->command = data->setup.blocking_io ?
+				shtc1_cmd_measure_blocking_hpm :
+				shtc1_cmd_measure_nonblocking_hpm;
+		data->nonblocking_wait_time = SHTC1_NONBLOCKING_WAIT_TIME_HPM;
+
+	} else {
+		data->command = data->setup.blocking_io ?
+				shtc1_cmd_measure_blocking_lpm :
+				shtc1_cmd_measure_nonblocking_lpm;
+		data->nonblocking_wait_time = SHTC1_NONBLOCKING_WAIT_TIME_LPM;
+	}
+}
+
+static int shtc1_probe(struct i2c_client *client,
+		       const struct i2c_device_id *id)
+{
+	int ret;
+	char id_reg[2];
+	struct shtc1_data *data;
+	struct device *hwmon_dev;
+	struct i2c_adapter *adap = client->adapter;
+	struct device *dev = &client->dev;
+
+	if (!i2c_check_functionality(adap, I2C_FUNC_I2C)) {
+		dev_err(dev, "plain i2c transactions not supported\n");
+		return -ENODEV;
+	}
+
+	ret = i2c_master_send(client, shtc1_cmd_read_id_reg, SHTC1_CMD_LENGTH);
+	if (ret != SHTC1_CMD_LENGTH) {
+		dev_err(dev, "could not send read_id_reg command: %d\n", ret);
+		return ret < 0 ? ret : -ENODEV;
+	}
+	ret = i2c_master_recv(client, id_reg, sizeof(id_reg));
+	if (ret != sizeof(id_reg)) {
+		dev_err(dev, "could not read ID register: %d\n", ret);
+		return -ENODEV;
+	}
+	if ((id_reg[1] & SHTC1_ID_REG_MASK) != SHTC1_ID) {
+		dev_err(dev, "ID register doesn't match\n");
+		return -ENODEV;
+	}
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->setup.blocking_io = false;
+	data->setup.high_precision = true;
+	data->client = client;
+
+	if (client->dev.platform_data)
+		data->setup = *(struct shtc1_platform_data *)dev->platform_data;
+	shtc1_select_command(data);
+	mutex_init(&data->update_lock);
+
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev,
+							   client->name,
+							   data,
+							   shtc1_groups);
+	if (IS_ERR(hwmon_dev))
+		dev_dbg(dev, "unable to register hwmon device\n");
+
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+/* device ID table */
+static const struct i2c_device_id shtc1_id[] = {
+	{ "shtc1", 0 },
+	{ "shtw1", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, shtc1_id);
+
+static struct i2c_driver shtc1_i2c_driver = {
+	.driver.name  = "shtc1",
+	.probe        = shtc1_probe,
+	.id_table     = shtc1_id,
+};
+
+module_i2c_driver(shtc1_i2c_driver);
+
+MODULE_AUTHOR("Johannes Winkelmann <johannes.winkelmann@sensirion.com>");
+MODULE_DESCRIPTION("Sensirion SHTC1 humidity and temperature sensor driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c
index efee4c59239..34b9a601ad0 100644
--- a/drivers/hwmon/smsc47m192.c
+++ b/drivers/hwmon/smsc47m192.c
@@ -86,7 +86,7 @@ static inline u8 IN_TO_REG(unsigned long val, int n)
  */
 static inline s8 TEMP_TO_REG(int val)
 {
-	return clamp_val(SCALE(val, 1, 1000), -128000, 127000);
+	return SCALE(clamp_val(val, -128000, 127000), 1, 1000);
 }
 
 static inline int TEMP_FROM_REG(s8 val)
@@ -384,6 +384,8 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 	err = kstrtoul(buf, 10, &val);
 	if (err)
 		return err;
+	if (val > 255)
+		return -EINVAL;
 
 	data->vrm = val;
 	return count;
diff --git a/drivers/hwmon/vexpress.c b/drivers/hwmon/vexpress.c
index 611f34c7333..c53619086f3 100644
--- a/drivers/hwmon/vexpress.c
+++ b/drivers/hwmon/vexpress.c
@@ -27,17 +27,8 @@
 struct vexpress_hwmon_data {
 	struct device *hwmon_dev;
 	struct regmap *reg;
-	const char *name;
 };
 
-static ssize_t vexpress_hwmon_name_show(struct device *dev,
-		struct device_attribute *dev_attr, char *buffer)
-{
-	struct vexpress_hwmon_data *data = dev_get_drvdata(dev);
-
-	return sprintf(buffer, "%s\n", data->name);
-}
-
 static ssize_t vexpress_hwmon_label_show(struct device *dev,
 		struct device_attribute *dev_attr, char *buffer)
 {
@@ -95,16 +86,6 @@ static umode_t vexpress_hwmon_attr_is_visible(struct kobject *kobj,
 	return attr->mode;
 }
 
-static DEVICE_ATTR(name, S_IRUGO, vexpress_hwmon_name_show, NULL);
-
-#define VEXPRESS_HWMON_ATTRS(_name, _label_attr, _input_attr)	\
-struct attribute *vexpress_hwmon_attrs_##_name[] = {		\
-	&dev_attr_name.attr,					\
-	&dev_attr_##_label_attr.attr,				\
-	&sensor_dev_attr_##_input_attr.dev_attr.attr,		\
-	NULL							\
-}
-
 struct vexpress_hwmon_type {
 	const char *name;
 	const struct attribute_group **attr_groups;
@@ -114,7 +95,11 @@ struct vexpress_hwmon_type {
 static DEVICE_ATTR(in1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(in1_input, S_IRUGO, vexpress_hwmon_u32_show,
 		NULL, 1000);
-static VEXPRESS_HWMON_ATTRS(volt, in1_label, in1_input);
+static struct attribute *vexpress_hwmon_attrs_volt[] = {
+	&dev_attr_in1_label.attr,
+	&sensor_dev_attr_in1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_volt = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_volt,
@@ -131,7 +116,11 @@ static struct vexpress_hwmon_type vexpress_hwmon_volt = {
 static DEVICE_ATTR(curr1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(curr1_input, S_IRUGO, vexpress_hwmon_u32_show,
 		NULL, 1000);
-static VEXPRESS_HWMON_ATTRS(amp, curr1_label, curr1_input);
+static struct attribute *vexpress_hwmon_attrs_amp[] = {
+	&dev_attr_curr1_label.attr,
+	&sensor_dev_attr_curr1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_amp = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_amp,
@@ -147,7 +136,11 @@ static struct vexpress_hwmon_type vexpress_hwmon_amp = {
 static DEVICE_ATTR(temp1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, vexpress_hwmon_u32_show,
 		NULL, 1000);
-static VEXPRESS_HWMON_ATTRS(temp, temp1_label, temp1_input);
+static struct attribute *vexpress_hwmon_attrs_temp[] = {
+	&dev_attr_temp1_label.attr,
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_temp = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_temp,
@@ -163,7 +156,11 @@ static struct vexpress_hwmon_type vexpress_hwmon_temp = {
 static DEVICE_ATTR(power1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(power1_input, S_IRUGO, vexpress_hwmon_u32_show,
 		NULL, 1);
-static VEXPRESS_HWMON_ATTRS(power, power1_label, power1_input);
+static struct attribute *vexpress_hwmon_attrs_power[] = {
+	&dev_attr_power1_label.attr,
+	&sensor_dev_attr_power1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_power = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_power,
@@ -179,7 +176,11 @@ static struct vexpress_hwmon_type vexpress_hwmon_power = {
 static DEVICE_ATTR(energy1_label, S_IRUGO, vexpress_hwmon_label_show, NULL);
 static SENSOR_DEVICE_ATTR(energy1_input, S_IRUGO, vexpress_hwmon_u64_show,
 		NULL, 1);
-static VEXPRESS_HWMON_ATTRS(energy, energy1_label, energy1_input);
+static struct attribute *vexpress_hwmon_attrs_energy[] = {
+	&dev_attr_energy1_label.attr,
+	&sensor_dev_attr_energy1_input.dev_attr.attr,
+	NULL
+};
 static struct attribute_group vexpress_hwmon_group_energy = {
 	.is_visible = vexpress_hwmon_attr_is_visible,
 	.attrs = vexpress_hwmon_attrs_energy,
@@ -218,7 +219,6 @@ MODULE_DEVICE_TABLE(of, vexpress_hwmon_of_match);
 
 static int vexpress_hwmon_probe(struct platform_device *pdev)
 {
-	int err;
 	const struct of_device_id *match;
 	struct vexpress_hwmon_data *data;
 	const struct vexpress_hwmon_type *type;
@@ -232,45 +232,19 @@ static int vexpress_hwmon_probe(struct platform_device *pdev)
 	if (!match)
 		return -ENODEV;
 	type = match->data;
-	data->name = type->name;
 
 	data->reg = devm_regmap_init_vexpress_config(&pdev->dev);
 	if (IS_ERR(data->reg))
 		return PTR_ERR(data->reg);
 
-	err = sysfs_create_groups(&pdev->dev.kobj, type->attr_groups);
-	if (err)
-		goto error;
-
-	data->hwmon_dev = hwmon_device_register(&pdev->dev);
-	if (IS_ERR(data->hwmon_dev)) {
-		err = PTR_ERR(data->hwmon_dev);
-		goto error;
-	}
-
-	return 0;
-
-error:
-	sysfs_remove_group(&pdev->dev.kobj, match->data);
-	return err;
-}
-
-static int vexpress_hwmon_remove(struct platform_device *pdev)
-{
-	struct vexpress_hwmon_data *data = platform_get_drvdata(pdev);
-	const struct of_device_id *match;
-
-	hwmon_device_unregister(data->hwmon_dev);
-
-	match = of_match_device(vexpress_hwmon_of_match, &pdev->dev);
-	sysfs_remove_group(&pdev->dev.kobj, match->data);
+	data->hwmon_dev = devm_hwmon_device_register_with_groups(&pdev->dev,
+			type->name, data, type->attr_groups);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(data->hwmon_dev);
 }
 
 static struct platform_driver vexpress_hwmon_driver = {
 	.probe = vexpress_hwmon_probe,
-	.remove = vexpress_hwmon_remove,
 	.driver	= {
 		.name = DRVNAME,
 		.owner = THIS_MODULE,
diff --git a/drivers/hwmon/w83l786ng.c b/drivers/hwmon/w83l786ng.c
index 6ed76ceb927..32487c19cbf 100644
--- a/drivers/hwmon/w83l786ng.c
+++ b/drivers/hwmon/w83l786ng.c
@@ -249,7 +249,7 @@ static ssize_t show_##reg(struct device *dev, struct device_attribute *attr, \
 	int nr = to_sensor_dev_attr(attr)->index; \
 	struct w83l786ng_data *data = w83l786ng_update_device(dev); \
 	return sprintf(buf, "%d\n", \
-		FAN_FROM_REG(data->fan[nr], DIV_FROM_REG(data->fan_div[nr]))); \
+		FAN_FROM_REG(data->reg[nr], DIV_FROM_REG(data->fan_div[nr]))); \
 }
 
 show_fan_reg(fan);
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 620d1004a1e..9f7d5859cf6 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -676,6 +676,16 @@ config I2C_RIIC
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-riic.
 
+config I2C_RK3X
+	tristate "Rockchip RK3xxx I2C adapter"
+	depends on OF
+	help
+	  Say Y here to include support for the I2C adapter in Rockchip RK3xxx
+	  SoCs.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called i2c-rk3x.
+
 config HAVE_S3C2410_I2C
 	bool
 	help
@@ -764,6 +774,19 @@ config I2C_STU300
 	  This driver can also be built as a module. If so, the module
 	  will be called i2c-stu300.
 
+config I2C_SUN6I_P2WI
+	tristate "Allwinner sun6i internal P2WI controller"
+	depends on RESET_CONTROLLER
+	depends on MACH_SUN6I || COMPILE_TEST
+	help
+	  If you say yes to this option, support will be included for the
+	  P2WI (Push/Pull 2 Wire Interface) controller embedded in some sunxi
+	  SOCs.
+	  The P2WI looks like an SMBus controller (which supports only byte
+	  accesses), except that it only supports one slave device.
+	  This interface is used to connect to specific PMIC devices (like the
+	  AXP221).
+
 config I2C_TEGRA
 	tristate "NVIDIA Tegra internal I2C controller"
 	depends on ARCH_TEGRA
diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile
index 298692cc600..dd9a7f8e873 100644
--- a/drivers/i2c/busses/Makefile
+++ b/drivers/i2c/busses/Makefile
@@ -66,6 +66,7 @@ obj-$(CONFIG_I2C_PXA)		+= i2c-pxa.o
 obj-$(CONFIG_I2C_PXA_PCI)	+= i2c-pxa-pci.o
 obj-$(CONFIG_I2C_QUP)		+= i2c-qup.o
 obj-$(CONFIG_I2C_RIIC)		+= i2c-riic.o
+obj-$(CONFIG_I2C_RK3X)		+= i2c-rk3x.o
 obj-$(CONFIG_I2C_S3C2410)	+= i2c-s3c2410.o
 obj-$(CONFIG_I2C_S6000)		+= i2c-s6000.o
 obj-$(CONFIG_I2C_SH7760)	+= i2c-sh7760.o
@@ -74,6 +75,7 @@ obj-$(CONFIG_I2C_SIMTEC)	+= i2c-simtec.o
 obj-$(CONFIG_I2C_SIRF)		+= i2c-sirf.o
 obj-$(CONFIG_I2C_ST)		+= i2c-st.o
 obj-$(CONFIG_I2C_STU300)	+= i2c-stu300.o
+obj-$(CONFIG_I2C_SUN6I_P2WI)	+= i2c-sun6i-p2wi.o
 obj-$(CONFIG_I2C_TEGRA)		+= i2c-tegra.o
 obj-$(CONFIG_I2C_VERSATILE)	+= i2c-versatile.o
 obj-$(CONFIG_I2C_WMT)		+= i2c-wmt.o
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
new file mode 100644
index 00000000000..a9791509966
--- /dev/null
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -0,0 +1,763 @@
+/*
+ * Driver for I2C adapter in Rockchip RK3xxx SoC
+ *
+ * Max Schwarz <max.schwarz@online.de>
+ * based on the patches by Rockchip Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+#include <linux/wait.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+
+
+/* Register Map */
+#define REG_CON        0x00 /* control register */
+#define REG_CLKDIV     0x04 /* clock divisor register */
+#define REG_MRXADDR    0x08 /* slave address for REGISTER_TX */
+#define REG_MRXRADDR   0x0c /* slave register address for REGISTER_TX */
+#define REG_MTXCNT     0x10 /* number of bytes to be transmitted */
+#define REG_MRXCNT     0x14 /* number of bytes to be received */
+#define REG_IEN        0x18 /* interrupt enable */
+#define REG_IPD        0x1c /* interrupt pending */
+#define REG_FCNT       0x20 /* finished count */
+
+/* Data buffer offsets */
+#define TXBUFFER_BASE 0x100
+#define RXBUFFER_BASE 0x200
+
+/* REG_CON bits */
+#define REG_CON_EN        BIT(0)
+enum {
+	REG_CON_MOD_TX = 0,      /* transmit data */
+	REG_CON_MOD_REGISTER_TX, /* select register and restart */
+	REG_CON_MOD_RX,          /* receive data */
+	REG_CON_MOD_REGISTER_RX, /* broken: transmits read addr AND writes
+				  * register addr */
+};
+#define REG_CON_MOD(mod)  ((mod) << 1)
+#define REG_CON_MOD_MASK  (BIT(1) | BIT(2))
+#define REG_CON_START     BIT(3)
+#define REG_CON_STOP      BIT(4)
+#define REG_CON_LASTACK   BIT(5) /* 1: send NACK after last received byte */
+#define REG_CON_ACTACK    BIT(6) /* 1: stop if NACK is received */
+
+/* REG_MRXADDR bits */
+#define REG_MRXADDR_VALID(x) BIT(24 + (x)) /* [x*8+7:x*8] of MRX[R]ADDR valid */
+
+/* REG_IEN/REG_IPD bits */
+#define REG_INT_BTF       BIT(0) /* a byte was transmitted */
+#define REG_INT_BRF       BIT(1) /* a byte was received */
+#define REG_INT_MBTF      BIT(2) /* master data transmit finished */
+#define REG_INT_MBRF      BIT(3) /* master data receive finished */
+#define REG_INT_START     BIT(4) /* START condition generated */
+#define REG_INT_STOP      BIT(5) /* STOP condition generated */
+#define REG_INT_NAKRCV    BIT(6) /* NACK received */
+#define REG_INT_ALL       0x7f
+
+/* Constants */
+#define WAIT_TIMEOUT      200 /* ms */
+#define DEFAULT_SCL_RATE  (100 * 1000) /* Hz */
+
+enum rk3x_i2c_state {
+	STATE_IDLE,
+	STATE_START,
+	STATE_READ,
+	STATE_WRITE,
+	STATE_STOP
+};
+
+/**
+ * @grf_offset: offset inside the grf regmap for setting the i2c type
+ */
+struct rk3x_i2c_soc_data {
+	int grf_offset;
+};
+
+struct rk3x_i2c {
+	struct i2c_adapter adap;
+	struct device *dev;
+	struct rk3x_i2c_soc_data *soc_data;
+
+	/* Hardware resources */
+	void __iomem *regs;
+	struct clk *clk;
+
+	/* Settings */
+	unsigned int scl_frequency;
+
+	/* Synchronization & notification */
+	spinlock_t lock;
+	wait_queue_head_t wait;
+	bool busy;
+
+	/* Current message */
+	struct i2c_msg *msg;
+	u8 addr;
+	unsigned int mode;
+	bool is_last_msg;
+
+	/* I2C state machine */
+	enum rk3x_i2c_state state;
+	unsigned int processed; /* sent/received bytes */
+	int error;
+};
+
+static inline void i2c_writel(struct rk3x_i2c *i2c, u32 value,
+			      unsigned int offset)
+{
+	writel(value, i2c->regs + offset);
+}
+
+static inline u32 i2c_readl(struct rk3x_i2c *i2c, unsigned int offset)
+{
+	return readl(i2c->regs + offset);
+}
+
+/* Reset all interrupt pending bits */
+static inline void rk3x_i2c_clean_ipd(struct rk3x_i2c *i2c)
+{
+	i2c_writel(i2c, REG_INT_ALL, REG_IPD);
+}
+
+/**
+ * Generate a START condition, which triggers a REG_INT_START interrupt.
+ */
+static void rk3x_i2c_start(struct rk3x_i2c *i2c)
+{
+	u32 val;
+
+	rk3x_i2c_clean_ipd(i2c);
+	i2c_writel(i2c, REG_INT_START, REG_IEN);
+
+	/* enable adapter with correct mode, send START condition */
+	val = REG_CON_EN | REG_CON_MOD(i2c->mode) | REG_CON_START;
+
+	/* if we want to react to NACK, set ACTACK bit */
+	if (!(i2c->msg->flags & I2C_M_IGNORE_NAK))
+		val |= REG_CON_ACTACK;
+
+	i2c_writel(i2c, val, REG_CON);
+}
+
+/**
+ * Generate a STOP condition, which triggers a REG_INT_STOP interrupt.
+ *
+ * @error: Error code to return in rk3x_i2c_xfer
+ */
+static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error)
+{
+	unsigned int ctrl;
+
+	i2c->processed = 0;
+	i2c->msg = NULL;
+	i2c->error = error;
+
+	if (i2c->is_last_msg) {
+		/* Enable stop interrupt */
+		i2c_writel(i2c, REG_INT_STOP, REG_IEN);
+
+		i2c->state = STATE_STOP;
+
+		ctrl = i2c_readl(i2c, REG_CON);
+		ctrl |= REG_CON_STOP;
+		i2c_writel(i2c, ctrl, REG_CON);
+	} else {
+		/* Signal rk3x_i2c_xfer to start the next message. */
+		i2c->busy = false;
+		i2c->state = STATE_IDLE;
+
+		/*
+		 * The HW is actually not capable of REPEATED START. But we can
+		 * get the intended effect by resetting its internal state
+		 * and issuing an ordinary START.
+		 */
+		i2c_writel(i2c, 0, REG_CON);
+
+		/* signal that we are finished with the current msg */
+		wake_up(&i2c->wait);
+	}
+}
+
+/**
+ * Setup a read according to i2c->msg
+ */
+static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c)
+{
+	unsigned int len = i2c->msg->len - i2c->processed;
+	u32 con;
+
+	con = i2c_readl(i2c, REG_CON);
+
+	/*
+	 * The hw can read up to 32 bytes at a time. If we need more than one
+	 * chunk, send an ACK after the last byte of the current chunk.
+	 */
+	if (unlikely(len > 32)) {
+		len = 32;
+		con &= ~REG_CON_LASTACK;
+	} else {
+		con |= REG_CON_LASTACK;
+	}
+
+	/* make sure we are in plain RX mode if we read a second chunk */
+	if (i2c->processed != 0) {
+		con &= ~REG_CON_MOD_MASK;
+		con |= REG_CON_MOD(REG_CON_MOD_RX);
+	}
+
+	i2c_writel(i2c, con, REG_CON);
+	i2c_writel(i2c, len, REG_MRXCNT);
+}
+
+/**
+ * Fill the transmit buffer with data from i2c->msg
+ */
+static void rk3x_i2c_fill_transmit_buf(struct rk3x_i2c *i2c)
+{
+	unsigned int i, j;
+	u32 cnt = 0;
+	u32 val;
+	u8 byte;
+
+	for (i = 0; i < 8; ++i) {
+		val = 0;
+		for (j = 0; j < 4; ++j) {
+			if (i2c->processed == i2c->msg->len)
+				break;
+
+			if (i2c->processed == 0 && cnt == 0)
+				byte = (i2c->addr & 0x7f) << 1;
+			else
+				byte = i2c->msg->buf[i2c->processed++];
+
+			val |= byte << (j * 8);
+			cnt++;
+		}
+
+		i2c_writel(i2c, val, TXBUFFER_BASE + 4 * i);
+
+		if (i2c->processed == i2c->msg->len)
+			break;
+	}
+
+	i2c_writel(i2c, cnt, REG_MTXCNT);
+}
+
+
+/* IRQ handlers for individual states */
+
+static void rk3x_i2c_handle_start(struct rk3x_i2c *i2c, unsigned int ipd)
+{
+	if (!(ipd & REG_INT_START)) {
+		rk3x_i2c_stop(i2c, -EIO);
+		dev_warn(i2c->dev, "unexpected irq in START: 0x%x\n", ipd);
+		rk3x_i2c_clean_ipd(i2c);
+		return;
+	}
+
+	/* ack interrupt */
+	i2c_writel(i2c, REG_INT_START, REG_IPD);
+
+	/* disable start bit */
+	i2c_writel(i2c, i2c_readl(i2c, REG_CON) & ~REG_CON_START, REG_CON);
+
+	/* enable appropriate interrupts and transition */
+	if (i2c->mode == REG_CON_MOD_TX) {
+		i2c_writel(i2c, REG_INT_MBTF | REG_INT_NAKRCV, REG_IEN);
+		i2c->state = STATE_WRITE;
+		rk3x_i2c_fill_transmit_buf(i2c);
+	} else {
+		/* in any other case, we are going to be reading. */
+		i2c_writel(i2c, REG_INT_MBRF | REG_INT_NAKRCV, REG_IEN);
+		i2c->state = STATE_READ;
+		rk3x_i2c_prepare_read(i2c);
+	}
+}
+
+static void rk3x_i2c_handle_write(struct rk3x_i2c *i2c, unsigned int ipd)
+{
+	if (!(ipd & REG_INT_MBTF)) {
+		rk3x_i2c_stop(i2c, -EIO);
+		dev_err(i2c->dev, "unexpected irq in WRITE: 0x%x\n", ipd);
+		rk3x_i2c_clean_ipd(i2c);
+		return;
+	}
+
+	/* ack interrupt */
+	i2c_writel(i2c, REG_INT_MBTF, REG_IPD);
+
+	/* are we finished? */
+	if (i2c->processed == i2c->msg->len)
+		rk3x_i2c_stop(i2c, i2c->error);
+	else
+		rk3x_i2c_fill_transmit_buf(i2c);
+}
+
+static void rk3x_i2c_handle_read(struct rk3x_i2c *i2c, unsigned int ipd)
+{
+	unsigned int i;
+	unsigned int len = i2c->msg->len - i2c->processed;
+	u32 uninitialized_var(val);
+	u8 byte;
+
+	/* we only care for MBRF here. */
+	if (!(ipd & REG_INT_MBRF))
+		return;
+
+	/* ack interrupt */
+	i2c_writel(i2c, REG_INT_MBRF, REG_IPD);
+
+	/* read the data from receive buffer */
+	for (i = 0; i < len; ++i) {
+		if (i % 4 == 0)
+			val = i2c_readl(i2c, RXBUFFER_BASE + (i / 4) * 4);
+
+		byte = (val >> ((i % 4) * 8)) & 0xff;
+		i2c->msg->buf[i2c->processed++] = byte;
+	}
+
+	/* are we finished? */
+	if (i2c->processed == i2c->msg->len)
+		rk3x_i2c_stop(i2c, i2c->error);
+	else
+		rk3x_i2c_prepare_read(i2c);
+}
+
+static void rk3x_i2c_handle_stop(struct rk3x_i2c *i2c, unsigned int ipd)
+{
+	unsigned int con;
+
+	if (!(ipd & REG_INT_STOP)) {
+		rk3x_i2c_stop(i2c, -EIO);
+		dev_err(i2c->dev, "unexpected irq in STOP: 0x%x\n", ipd);
+		rk3x_i2c_clean_ipd(i2c);
+		return;
+	}
+
+	/* ack interrupt */
+	i2c_writel(i2c, REG_INT_STOP, REG_IPD);
+
+	/* disable STOP bit */
+	con = i2c_readl(i2c, REG_CON);
+	con &= ~REG_CON_STOP;
+	i2c_writel(i2c, con, REG_CON);
+
+	i2c->busy = false;
+	i2c->state = STATE_IDLE;
+
+	/* signal rk3x_i2c_xfer that we are finished */
+	wake_up(&i2c->wait);
+}
+
+static irqreturn_t rk3x_i2c_irq(int irqno, void *dev_id)
+{
+	struct rk3x_i2c *i2c = dev_id;
+	unsigned int ipd;
+
+	spin_lock(&i2c->lock);
+
+	ipd = i2c_readl(i2c, REG_IPD);
+	if (i2c->state == STATE_IDLE) {
+		dev_warn(i2c->dev, "irq in STATE_IDLE, ipd = 0x%x\n", ipd);
+		rk3x_i2c_clean_ipd(i2c);
+		goto out;
+	}
+
+	dev_dbg(i2c->dev, "IRQ: state %d, ipd: %x\n", i2c->state, ipd);
+
+	/* Clean interrupt bits we don't care about */
+	ipd &= ~(REG_INT_BRF | REG_INT_BTF);
+
+	if (ipd & REG_INT_NAKRCV) {
+		/*
+		 * We got a NACK in the last operation. Depending on whether
+		 * IGNORE_NAK is set, we have to stop the operation and report
+		 * an error.
+		 */
+		i2c_writel(i2c, REG_INT_NAKRCV, REG_IPD);
+
+		ipd &= ~REG_INT_NAKRCV;
+
+		if (!(i2c->msg->flags & I2C_M_IGNORE_NAK))
+			rk3x_i2c_stop(i2c, -ENXIO);
+	}
+
+	/* is there anything left to handle? */
+	if (unlikely(ipd == 0))
+		goto out;
+
+	switch (i2c->state) {
+	case STATE_START:
+		rk3x_i2c_handle_start(i2c, ipd);
+		break;
+	case STATE_WRITE:
+		rk3x_i2c_handle_write(i2c, ipd);
+		break;
+	case STATE_READ:
+		rk3x_i2c_handle_read(i2c, ipd);
+		break;
+	case STATE_STOP:
+		rk3x_i2c_handle_stop(i2c, ipd);
+		break;
+	case STATE_IDLE:
+		break;
+	}
+
+out:
+	spin_unlock(&i2c->lock);
+	return IRQ_HANDLED;
+}
+
+static void rk3x_i2c_set_scl_rate(struct rk3x_i2c *i2c, unsigned long scl_rate)
+{
+	unsigned long i2c_rate = clk_get_rate(i2c->clk);
+	unsigned int div;
+
+	/* SCL rate = (clk rate) / (8 * DIV) */
+	div = DIV_ROUND_UP(i2c_rate, scl_rate * 8);
+
+	/* The lower and upper half of the CLKDIV reg describe the length of
+	 * SCL low & high periods. */
+	div = DIV_ROUND_UP(div, 2);
+
+	i2c_writel(i2c, (div << 16) | (div & 0xffff), REG_CLKDIV);
+}
+
+/**
+ * Setup I2C registers for an I2C operation specified by msgs, num.
+ *
+ * Must be called with i2c->lock held.
+ *
+ * @msgs: I2C msgs to process
+ * @num: Number of msgs
+ *
+ * returns: Number of I2C msgs processed or negative in case of error
+ */
+static int rk3x_i2c_setup(struct rk3x_i2c *i2c, struct i2c_msg *msgs, int num)
+{
+	u32 addr = (msgs[0].addr & 0x7f) << 1;
+	int ret = 0;
+
+	/*
+	 * The I2C adapter can issue a small (len < 4) write packet before
+	 * reading. This speeds up SMBus-style register reads.
+	 * The MRXADDR/MRXRADDR hold the slave address and the slave register
+	 * address in this case.
+	 */
+
+	if (num >= 2 && msgs[0].len < 4 &&
+	    !(msgs[0].flags & I2C_M_RD) && (msgs[1].flags & I2C_M_RD)) {
+		u32 reg_addr = 0;
+		int i;
+
+		dev_dbg(i2c->dev, "Combined write/read from addr 0x%x\n",
+			addr >> 1);
+
+		/* Fill MRXRADDR with the register address(es) */
+		for (i = 0; i < msgs[0].len; ++i) {
+			reg_addr |= msgs[0].buf[i] << (i * 8);
+			reg_addr |= REG_MRXADDR_VALID(i);
+		}
+
+		/* msgs[0] is handled by hw. */
+		i2c->msg = &msgs[1];
+
+		i2c->mode = REG_CON_MOD_REGISTER_TX;
+
+		i2c_writel(i2c, addr | REG_MRXADDR_VALID(0), REG_MRXADDR);
+		i2c_writel(i2c, reg_addr, REG_MRXRADDR);
+
+		ret = 2;
+	} else {
+		/*
+		 * We'll have to do it the boring way and process the msgs
+		 * one-by-one.
+		 */
+
+		if (msgs[0].flags & I2C_M_RD) {
+			addr |= 1; /* set read bit */
+
+			/*
+			 * We have to transmit the slave addr first. Use
+			 * MOD_REGISTER_TX for that purpose.
+			 */
+			i2c->mode = REG_CON_MOD_REGISTER_TX;
+			i2c_writel(i2c, addr | REG_MRXADDR_VALID(0),
+				   REG_MRXADDR);
+			i2c_writel(i2c, 0, REG_MRXRADDR);
+		} else {
+			i2c->mode = REG_CON_MOD_TX;
+		}
+
+		i2c->msg = &msgs[0];
+
+		ret = 1;
+	}
+
+	i2c->addr = msgs[0].addr;
+	i2c->busy = true;
+	i2c->state = STATE_START;
+	i2c->processed = 0;
+	i2c->error = 0;
+
+	rk3x_i2c_clean_ipd(i2c);
+
+	return ret;
+}
+
+static int rk3x_i2c_xfer(struct i2c_adapter *adap,
+			 struct i2c_msg *msgs, int num)
+{
+	struct rk3x_i2c *i2c = (struct rk3x_i2c *)adap->algo_data;
+	unsigned long timeout, flags;
+	int ret = 0;
+	int i;
+
+	spin_lock_irqsave(&i2c->lock, flags);
+
+	clk_enable(i2c->clk);
+
+	/* The clock rate might have changed, so setup the divider again */
+	rk3x_i2c_set_scl_rate(i2c, i2c->scl_frequency);
+
+	i2c->is_last_msg = false;
+
+	/*
+	 * Process msgs. We can handle more than one message at once (see
+	 * rk3x_i2c_setup()).
+	 */
+	for (i = 0; i < num; i += ret) {
+		ret = rk3x_i2c_setup(i2c, msgs + i, num - i);
+
+		if (ret < 0) {
+			dev_err(i2c->dev, "rk3x_i2c_setup() failed\n");
+			break;
+		}
+
+		if (i + ret >= num)
+			i2c->is_last_msg = true;
+
+		spin_unlock_irqrestore(&i2c->lock, flags);
+
+		rk3x_i2c_start(i2c);
+
+		timeout = wait_event_timeout(i2c->wait, !i2c->busy,
+					     msecs_to_jiffies(WAIT_TIMEOUT));
+
+		spin_lock_irqsave(&i2c->lock, flags);
+
+		if (timeout == 0) {
+			dev_err(i2c->dev, "timeout, ipd: 0x%02x, state: %d\n",
+				i2c_readl(i2c, REG_IPD), i2c->state);
+
+			/* Force a STOP condition without interrupt */
+			i2c_writel(i2c, 0, REG_IEN);
+			i2c_writel(i2c, REG_CON_EN | REG_CON_STOP, REG_CON);
+
+			i2c->state = STATE_IDLE;
+
+			ret = -ETIMEDOUT;
+			break;
+		}
+
+		if (i2c->error) {
+			ret = i2c->error;
+			break;
+		}
+	}
+
+	clk_disable(i2c->clk);
+	spin_unlock_irqrestore(&i2c->lock, flags);
+
+	return ret;
+}
+
+static u32 rk3x_i2c_func(struct i2c_adapter *adap)
+{
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_PROTOCOL_MANGLING;
+}
+
+static const struct i2c_algorithm rk3x_i2c_algorithm = {
+	.master_xfer		= rk3x_i2c_xfer,
+	.functionality		= rk3x_i2c_func,
+};
+
+static struct rk3x_i2c_soc_data soc_data[3] = {
+	{ .grf_offset = 0x154 }, /* rk3066 */
+	{ .grf_offset = 0x0a4 }, /* rk3188 */
+	{ .grf_offset = -1 },    /* no I2C switching needed */
+};
+
+static const struct of_device_id rk3x_i2c_match[] = {
+	{ .compatible = "rockchip,rk3066-i2c", .data = (void *)&soc_data[0] },
+	{ .compatible = "rockchip,rk3188-i2c", .data = (void *)&soc_data[1] },
+	{ .compatible = "rockchip,rk3288-i2c", .data = (void *)&soc_data[2] },
+	{},
+};
+
+static int rk3x_i2c_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const struct of_device_id *match;
+	struct rk3x_i2c *i2c;
+	struct resource *mem;
+	int ret = 0;
+	int bus_nr;
+	u32 value;
+	int irq;
+
+	i2c = devm_kzalloc(&pdev->dev, sizeof(struct rk3x_i2c), GFP_KERNEL);
+	if (!i2c)
+		return -ENOMEM;
+
+	match = of_match_node(rk3x_i2c_match, np);
+	i2c->soc_data = (struct rk3x_i2c_soc_data *)match->data;
+
+	if (of_property_read_u32(pdev->dev.of_node, "clock-frequency",
+				 &i2c->scl_frequency)) {
+		dev_info(&pdev->dev, "using default SCL frequency: %d\n",
+			 DEFAULT_SCL_RATE);
+		i2c->scl_frequency = DEFAULT_SCL_RATE;
+	}
+
+	if (i2c->scl_frequency == 0 || i2c->scl_frequency > 400 * 1000) {
+		dev_warn(&pdev->dev, "invalid SCL frequency specified.\n");
+		dev_warn(&pdev->dev, "using default SCL frequency: %d\n",
+			 DEFAULT_SCL_RATE);
+		i2c->scl_frequency = DEFAULT_SCL_RATE;
+	}
+
+	strlcpy(i2c->adap.name, "rk3x-i2c", sizeof(i2c->adap.name));
+	i2c->adap.owner = THIS_MODULE;
+	i2c->adap.algo = &rk3x_i2c_algorithm;
+	i2c->adap.retries = 3;
+	i2c->adap.dev.of_node = np;
+	i2c->adap.algo_data = i2c;
+	i2c->adap.dev.parent = &pdev->dev;
+
+	i2c->dev = &pdev->dev;
+
+	spin_lock_init(&i2c->lock);
+	init_waitqueue_head(&i2c->wait);
+
+	i2c->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(i2c->clk)) {
+		dev_err(&pdev->dev, "cannot get clock\n");
+		return PTR_ERR(i2c->clk);
+	}
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	i2c->regs = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(i2c->regs))
+		return PTR_ERR(i2c->regs);
+
+	/* Try to set the I2C adapter number from dt */
+	bus_nr = of_alias_get_id(np, "i2c");
+
+	/*
+	 * Switch to new interface if the SoC also offers the old one.
+	 * The control bit is located in the GRF register space.
+	 */
+	if (i2c->soc_data->grf_offset >= 0) {
+		struct regmap *grf;
+
+		grf = syscon_regmap_lookup_by_phandle(np, "rockchip,grf");
+		if (IS_ERR(grf)) {
+			dev_err(&pdev->dev,
+				"rk3x-i2c needs 'rockchip,grf' property\n");
+			return PTR_ERR(grf);
+		}
+
+		if (bus_nr < 0) {
+			dev_err(&pdev->dev, "rk3x-i2c needs i2cX alias");
+			return -EINVAL;
+		}
+
+		/* 27+i: write mask, 11+i: value */
+		value = BIT(27 + bus_nr) | BIT(11 + bus_nr);
+
+		ret = regmap_write(grf, i2c->soc_data->grf_offset, value);
+		if (ret != 0) {
+			dev_err(i2c->dev, "Could not write to GRF: %d\n", ret);
+			return ret;
+		}
+	}
+
+	/* IRQ setup */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "cannot find rk3x IRQ\n");
+		return irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, rk3x_i2c_irq,
+			       0, dev_name(&pdev->dev), i2c);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "cannot request IRQ\n");
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, i2c);
+
+	ret = clk_prepare(i2c->clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Could not prepare clock\n");
+		return ret;
+	}
+
+	ret = i2c_add_adapter(&i2c->adap);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Could not register adapter\n");
+		goto err_clk;
+	}
+
+	dev_info(&pdev->dev, "Initialized RK3xxx I2C bus at %p\n", i2c->regs);
+
+	return 0;
+
+err_clk:
+	clk_unprepare(i2c->clk);
+	return ret;
+}
+
+static int rk3x_i2c_remove(struct platform_device *pdev)
+{
+	struct rk3x_i2c *i2c = platform_get_drvdata(pdev);
+
+	i2c_del_adapter(&i2c->adap);
+	clk_unprepare(i2c->clk);
+
+	return 0;
+}
+
+static struct platform_driver rk3x_i2c_driver = {
+	.probe   = rk3x_i2c_probe,
+	.remove  = rk3x_i2c_remove,
+	.driver  = {
+		.owner = THIS_MODULE,
+		.name  = "rk3x-i2c",
+		.of_match_table = rk3x_i2c_match,
+	},
+};
+
+module_platform_driver(rk3x_i2c_driver);
+
+MODULE_DESCRIPTION("Rockchip RK3xxx I2C Bus driver");
+MODULE_AUTHOR("Max Schwarz <max.schwarz@online.de>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/i2c/busses/i2c-sun6i-p2wi.c b/drivers/i2c/busses/i2c-sun6i-p2wi.c
new file mode 100644
index 00000000000..4d75d475970
--- /dev/null
+++ b/drivers/i2c/busses/i2c-sun6i-p2wi.c
@@ -0,0 +1,344 @@
+/*
+ * P2WI (Push-Pull Two Wire Interface) bus driver.
+ *
+ * Author: Boris BREZILLON <boris.brezillon@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ *
+ * The P2WI controller looks like an SMBus controller which only supports byte
+ * data transfers. But, it differs from standard SMBus protocol on several
+ * aspects:
+ * - it supports only one slave device, and thus drop the address field
+ * - it adds a parity bit every 8bits of data
+ * - only one read access is required to read a byte (instead of a write
+ *   followed by a read access in standard SMBus protocol)
+ * - there's no Ack bit after each byte transfer
+ *
+ * This means this bus cannot be used to interface with standard SMBus
+ * devices (the only known device to support this interface is the AXP221
+ * PMIC).
+ *
+ */
+#include <linux/clk.h>
+#include <linux/i2c.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+
+/* P2WI registers */
+#define P2WI_CTRL		0x0
+#define P2WI_CCR		0x4
+#define P2WI_INTE		0x8
+#define P2WI_INTS		0xc
+#define P2WI_DADDR0		0x10
+#define P2WI_DADDR1		0x14
+#define P2WI_DLEN		0x18
+#define P2WI_DATA0		0x1c
+#define P2WI_DATA1		0x20
+#define P2WI_LCR		0x24
+#define P2WI_PMCR		0x28
+
+/* CTRL fields */
+#define P2WI_CTRL_START_TRANS		BIT(7)
+#define P2WI_CTRL_ABORT_TRANS		BIT(6)
+#define P2WI_CTRL_GLOBAL_INT_ENB	BIT(1)
+#define P2WI_CTRL_SOFT_RST		BIT(0)
+
+/* CLK CTRL fields */
+#define P2WI_CCR_SDA_OUT_DELAY(v)	(((v) & 0x7) << 8)
+#define P2WI_CCR_MAX_CLK_DIV		0xff
+#define P2WI_CCR_CLK_DIV(v)		((v) & P2WI_CCR_MAX_CLK_DIV)
+
+/* STATUS fields */
+#define P2WI_INTS_TRANS_ERR_ID(v)	(((v) >> 8) & 0xff)
+#define P2WI_INTS_LOAD_BSY		BIT(2)
+#define P2WI_INTS_TRANS_ERR		BIT(1)
+#define P2WI_INTS_TRANS_OVER		BIT(0)
+
+/* DATA LENGTH fields*/
+#define P2WI_DLEN_READ			BIT(4)
+#define P2WI_DLEN_DATA_LENGTH(v)	((v - 1) & 0x7)
+
+/* LINE CTRL fields*/
+#define P2WI_LCR_SCL_STATE		BIT(5)
+#define P2WI_LCR_SDA_STATE		BIT(4)
+#define P2WI_LCR_SCL_CTL		BIT(3)
+#define P2WI_LCR_SCL_CTL_EN		BIT(2)
+#define P2WI_LCR_SDA_CTL		BIT(1)
+#define P2WI_LCR_SDA_CTL_EN		BIT(0)
+
+/* PMU MODE CTRL fields */
+#define P2WI_PMCR_PMU_INIT_SEND		BIT(31)
+#define P2WI_PMCR_PMU_INIT_DATA(v)	(((v) & 0xff) << 16)
+#define P2WI_PMCR_PMU_MODE_REG(v)	(((v) & 0xff) << 8)
+#define P2WI_PMCR_PMU_DEV_ADDR(v)	((v) & 0xff)
+
+#define P2WI_MAX_FREQ			6000000
+
+struct p2wi {
+	struct i2c_adapter adapter;
+	struct completion complete;
+	unsigned int status;
+	void __iomem *regs;
+	struct clk *clk;
+	struct reset_control *rstc;
+	int slave_addr;
+};
+
+static irqreturn_t p2wi_interrupt(int irq, void *dev_id)
+{
+	struct p2wi *p2wi = dev_id;
+	unsigned long status;
+
+	status = readl(p2wi->regs + P2WI_INTS);
+	p2wi->status = status;
+
+	/* Clear interrupts */
+	status &= (P2WI_INTS_LOAD_BSY | P2WI_INTS_TRANS_ERR |
+		   P2WI_INTS_TRANS_OVER);
+	writel(status, p2wi->regs + P2WI_INTS);
+
+	complete(&p2wi->complete);
+
+	return IRQ_HANDLED;
+}
+
+static u32 p2wi_functionality(struct i2c_adapter *adap)
+{
+	return I2C_FUNC_SMBUS_BYTE_DATA;
+}
+
+static int p2wi_smbus_xfer(struct i2c_adapter *adap, u16 addr,
+			   unsigned short flags, char read_write,
+			   u8 command, int size, union i2c_smbus_data *data)
+{
+	struct p2wi *p2wi = i2c_get_adapdata(adap);
+	unsigned long dlen = P2WI_DLEN_DATA_LENGTH(1);
+
+	if (p2wi->slave_addr >= 0 && addr != p2wi->slave_addr) {
+		dev_err(&adap->dev, "invalid P2WI address\n");
+		return -EINVAL;
+	}
+
+	if (!data)
+		return -EINVAL;
+
+	writel(command, p2wi->regs + P2WI_DADDR0);
+
+	if (read_write == I2C_SMBUS_READ)
+		dlen |= P2WI_DLEN_READ;
+	else
+		writel(data->byte, p2wi->regs + P2WI_DATA0);
+
+	writel(dlen, p2wi->regs + P2WI_DLEN);
+
+	if (readl(p2wi->regs + P2WI_CTRL) & P2WI_CTRL_START_TRANS) {
+		dev_err(&adap->dev, "P2WI bus busy\n");
+		return -EBUSY;
+	}
+
+	reinit_completion(&p2wi->complete);
+
+	writel(P2WI_INTS_LOAD_BSY | P2WI_INTS_TRANS_ERR | P2WI_INTS_TRANS_OVER,
+	       p2wi->regs + P2WI_INTE);
+
+	writel(P2WI_CTRL_START_TRANS | P2WI_CTRL_GLOBAL_INT_ENB,
+	       p2wi->regs + P2WI_CTRL);
+
+	wait_for_completion(&p2wi->complete);
+
+	if (p2wi->status & P2WI_INTS_LOAD_BSY) {
+		dev_err(&adap->dev, "P2WI bus busy\n");
+		return -EBUSY;
+	}
+
+	if (p2wi->status & P2WI_INTS_TRANS_ERR) {
+		dev_err(&adap->dev, "P2WI bus xfer error\n");
+		return -ENXIO;
+	}
+
+	if (read_write == I2C_SMBUS_READ)
+		data->byte = readl(p2wi->regs + P2WI_DATA0);
+
+	return 0;
+}
+
+static const struct i2c_algorithm p2wi_algo = {
+	.smbus_xfer = p2wi_smbus_xfer,
+	.functionality = p2wi_functionality,
+};
+
+static const struct of_device_id p2wi_of_match_table[] = {
+	{ .compatible = "allwinner,sun6i-a31-p2wi" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, p2wi_of_match_table);
+
+static int p2wi_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct device_node *childnp;
+	unsigned long parent_clk_freq;
+	u32 clk_freq = 100000;
+	struct resource *r;
+	struct p2wi *p2wi;
+	u32 slave_addr;
+	int clk_div;
+	int irq;
+	int ret;
+
+	of_property_read_u32(np, "clock-frequency", &clk_freq);
+	if (clk_freq > P2WI_MAX_FREQ) {
+		dev_err(dev,
+			"required clock-frequency (%u Hz) is too high (max = 6MHz)",
+			clk_freq);
+		return -EINVAL;
+	}
+
+	if (of_get_child_count(np) > 1) {
+		dev_err(dev, "P2WI only supports one slave device\n");
+		return -EINVAL;
+	}
+
+	p2wi = devm_kzalloc(dev, sizeof(struct p2wi), GFP_KERNEL);
+	if (!p2wi)
+		return -ENOMEM;
+
+	p2wi->slave_addr = -1;
+
+	/*
+	 * Authorize a p2wi node without any children to be able to use an
+	 * i2c-dev from userpace.
+	 * In this case the slave_addr is set to -1 and won't be checked when
+	 * launching a P2WI transfer.
+	 */
+	childnp = of_get_next_available_child(np, NULL);
+	if (childnp) {
+		ret = of_property_read_u32(childnp, "reg", &slave_addr);
+		if (ret) {
+			dev_err(dev, "invalid slave address on node %s\n",
+				childnp->full_name);
+			return -EINVAL;
+		}
+
+		p2wi->slave_addr = slave_addr;
+	}
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	p2wi->regs = devm_ioremap_resource(dev, r);
+	if (IS_ERR(p2wi->regs))
+		return PTR_ERR(p2wi->regs);
+
+	strlcpy(p2wi->adapter.name, pdev->name, sizeof(p2wi->adapter.name));
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "failed to retrieve irq: %d\n", irq);
+		return irq;
+	}
+
+	p2wi->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(p2wi->clk)) {
+		ret = PTR_ERR(p2wi->clk);
+		dev_err(dev, "failed to retrieve clk: %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_prepare_enable(p2wi->clk);
+	if (ret) {
+		dev_err(dev, "failed to enable clk: %d\n", ret);
+		return ret;
+	}
+
+	parent_clk_freq = clk_get_rate(p2wi->clk);
+
+	p2wi->rstc = devm_reset_control_get(dev, NULL);
+	if (IS_ERR(p2wi->rstc)) {
+		ret = PTR_ERR(p2wi->rstc);
+		dev_err(dev, "failed to retrieve reset controller: %d\n", ret);
+		goto err_clk_disable;
+	}
+
+	ret = reset_control_deassert(p2wi->rstc);
+	if (ret) {
+		dev_err(dev, "failed to deassert reset line: %d\n", ret);
+		goto err_clk_disable;
+	}
+
+	init_completion(&p2wi->complete);
+	p2wi->adapter.dev.parent = dev;
+	p2wi->adapter.algo = &p2wi_algo;
+	p2wi->adapter.owner = THIS_MODULE;
+	p2wi->adapter.dev.of_node = pdev->dev.of_node;
+	platform_set_drvdata(pdev, p2wi);
+	i2c_set_adapdata(&p2wi->adapter, p2wi);
+
+	ret = devm_request_irq(dev, irq, p2wi_interrupt, 0, pdev->name, p2wi);
+	if (ret) {
+		dev_err(dev, "can't register interrupt handler irq%d: %d\n",
+			irq, ret);
+		goto err_reset_assert;
+	}
+
+	writel(P2WI_CTRL_SOFT_RST, p2wi->regs + P2WI_CTRL);
+
+	clk_div = parent_clk_freq / clk_freq;
+	if (!clk_div) {
+		dev_warn(dev,
+			 "clock-frequency is too high, setting it to %lu Hz\n",
+			 parent_clk_freq);
+		clk_div = 1;
+	} else if (clk_div > P2WI_CCR_MAX_CLK_DIV) {
+		dev_warn(dev,
+			 "clock-frequency is too low, setting it to %lu Hz\n",
+			 parent_clk_freq / P2WI_CCR_MAX_CLK_DIV);
+		clk_div = P2WI_CCR_MAX_CLK_DIV;
+	}
+
+	writel(P2WI_CCR_SDA_OUT_DELAY(1) | P2WI_CCR_CLK_DIV(clk_div),
+	       p2wi->regs + P2WI_CCR);
+
+	ret = i2c_add_adapter(&p2wi->adapter);
+	if (!ret)
+		return 0;
+
+err_reset_assert:
+	reset_control_assert(p2wi->rstc);
+
+err_clk_disable:
+	clk_disable_unprepare(p2wi->clk);
+
+	return ret;
+}
+
+static int p2wi_remove(struct platform_device *dev)
+{
+	struct p2wi *p2wi = platform_get_drvdata(dev);
+
+	reset_control_assert(p2wi->rstc);
+	clk_disable_unprepare(p2wi->clk);
+	i2c_del_adapter(&p2wi->adapter);
+
+	return 0;
+}
+
+static struct platform_driver p2wi_driver = {
+	.probe	= p2wi_probe,
+	.remove	= p2wi_remove,
+	.driver	= {
+		.owner = THIS_MODULE,
+		.name = "i2c-sunxi-p2wi",
+		.of_match_table = p2wi_of_match_table,
+	},
+};
+module_platform_driver(p2wi_driver);
+
+MODULE_AUTHOR("Boris BREZILLON <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner P2WI driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 7c7f4b856ba..66aa83b9938 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -42,6 +42,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
+#include <linux/clk/clk-conf.h>
 #include <linux/completion.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
@@ -274,6 +275,10 @@ static int i2c_device_probe(struct device *dev)
 					client->flags & I2C_CLIENT_WAKE);
 	dev_dbg(dev, "probe\n");
 
+	status = of_clk_set_defaults(dev->of_node, false);
+	if (status < 0)
+		return status;
+
 	acpi_dev_pm_attach(&client->dev, true);
 	status = driver->probe(client, i2c_match_id(driver->id_table, client));
 	if (status)
diff --git a/drivers/i2c/muxes/Kconfig b/drivers/i2c/muxes/Kconfig
index f7f9865b8b8..f6d313e528d 100644
--- a/drivers/i2c/muxes/Kconfig
+++ b/drivers/i2c/muxes/Kconfig
@@ -40,6 +40,7 @@ config I2C_MUX_PCA9541
 
 config I2C_MUX_PCA954x
 	tristate "Philips PCA954x I2C Mux/switches"
+	depends on GPIOLIB
 	help
 	  If you say yes here you get support for the Philips PCA954x
 	  I2C mux/switch devices.
diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig
index 8fb46aab2d8..a04c49f2a01 100644
--- a/drivers/ide/Kconfig
+++ b/drivers/ide/Kconfig
@@ -416,6 +416,7 @@ config BLK_DEV_CY82C693
 
 config BLK_DEV_CS5520
 	tristate "Cyrix CS5510/20 MediaGX chipset support (VERY EXPERIMENTAL)"
+	depends on X86_32 || COMPILE_TEST
 	select BLK_DEV_IDEDMA_PCI
 	help
 	  Include support for PIO tuning and virtual DMA on the Cyrix MediaGX
@@ -426,6 +427,7 @@ config BLK_DEV_CS5520
 
 config BLK_DEV_CS5530
 	tristate "Cyrix/National Semiconductor CS5530 MediaGX chipset support"
+	depends on X86_32 || COMPILE_TEST
 	select BLK_DEV_IDEDMA_PCI
 	help
 	  Include support for UDMA on the Cyrix MediaGX 5530 chipset. This
@@ -435,7 +437,7 @@ config BLK_DEV_CS5530
 
 config BLK_DEV_CS5535
 	tristate "AMD CS5535 chipset support"
-	depends on X86 && !X86_64
+	depends on X86_32
 	select BLK_DEV_IDEDMA_PCI
 	help
 	  Include support for UDMA on the NSC/AMD CS5535 companion chipset.
@@ -486,6 +488,7 @@ config BLK_DEV_JMICRON
 
 config BLK_DEV_SC1200
 	tristate "National SCx200 chipset support"
+	depends on X86_32 || COMPILE_TEST
 	select BLK_DEV_IDEDMA_PCI
 	help
 	  This driver adds support for the on-board IDE controller on the
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 2a744a91370..a3d3b1733c4 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -853,8 +853,9 @@ static int init_irq (ide_hwif_t *hwif)
 	if (irq_handler == NULL)
 		irq_handler = ide_intr;
 
-	if (request_irq(hwif->irq, irq_handler, sa, hwif->name, hwif))
-		goto out_up;
+	if (!host->get_lock)
+		if (request_irq(hwif->irq, irq_handler, sa, hwif->name, hwif))
+			goto out_up;
 
 #if !defined(__mc68000__)
 	printk(KERN_INFO "%s at 0x%03lx-0x%03lx,0x%03lx on irq %d", hwif->name,
@@ -1533,7 +1534,8 @@ static void ide_unregister(ide_hwif_t *hwif)
 
 	ide_proc_unregister_port(hwif);
 
-	free_irq(hwif->irq, hwif);
+	if (!hwif->host->get_lock)
+		free_irq(hwif->irq, hwif);
 
 	device_unregister(hwif->portdev);
 	device_unregister(&hwif->gendev);
diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c
index a7e68c81f89..a077cc86421 100644
--- a/drivers/iio/accel/bma180.c
+++ b/drivers/iio/accel/bma180.c
@@ -68,13 +68,13 @@
 /* Defaults values */
 #define BMA180_DEF_PMODE	0
 #define BMA180_DEF_BW		20
-#define BMA180_DEF_SCALE	250
+#define BMA180_DEF_SCALE	2452
 
 /* Available values for sysfs */
 #define BMA180_FLP_FREQ_AVAILABLE \
 	"10 20 40 75 150 300"
 #define BMA180_SCALE_AVAILABLE \
-	"0.000130 0.000190 0.000250 0.000380 0.000500 0.000990 0.001980"
+	"0.001275 0.001863 0.002452 0.003727 0.004903 0.009709 0.019417"
 
 struct bma180_data {
 	struct i2c_client *client;
@@ -94,7 +94,7 @@ enum bma180_axis {
 };
 
 static int bw_table[] = { 10, 20, 40, 75, 150, 300 }; /* Hz */
-static int scale_table[] = { 130, 190, 250, 380, 500, 990, 1980 };
+static int scale_table[] = { 1275, 1863, 2452, 3727, 4903, 9709, 19417 };
 
 static int bma180_get_acc_reg(struct bma180_data *data, enum bma180_axis axis)
 {
@@ -376,6 +376,8 @@ static int bma180_write_raw(struct iio_dev *indio_dev,
 		mutex_unlock(&data->mutex);
 		return ret;
 	case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
+		if (val2)
+			return -EINVAL;
 		mutex_lock(&data->mutex);
 		ret = bma180_set_bw(data, val);
 		mutex_unlock(&data->mutex);
diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c
index 69abf9163df..54e464e4bb7 100644
--- a/drivers/iio/accel/hid-sensor-accel-3d.c
+++ b/drivers/iio/accel/hid-sensor-accel-3d.c
@@ -110,7 +110,6 @@ static int accel_3d_read_raw(struct iio_dev *indio_dev,
 	struct accel_3d_state *accel_state = iio_priv(indio_dev);
 	int report_id = -1;
 	u32 address;
-	int ret;
 	int ret_type;
 	s32 poll_value;
 
@@ -151,14 +150,12 @@ static int accel_3d_read_raw(struct iio_dev *indio_dev,
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		ret = hid_sensor_read_samp_freq_value(
+		ret_type = hid_sensor_read_samp_freq_value(
 			&accel_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	case IIO_CHAN_INFO_HYSTERESIS:
-		ret = hid_sensor_read_raw_hyst_value(
+		ret_type = hid_sensor_read_raw_hyst_value(
 			&accel_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	default:
 		ret_type = -EINVAL;
diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c
index 17aeea17056..2a5fa9a436e 100644
--- a/drivers/iio/accel/mma8452.c
+++ b/drivers/iio/accel/mma8452.c
@@ -111,8 +111,14 @@ static const int mma8452_samp_freq[8][2] = {
 	{6, 250000}, {1, 560000}
 };
 
+/* 
+ * Hardware has fullscale of -2G, -4G, -8G corresponding to raw value -2048
+ * The userspace interface uses m/s^2 and we declare micro units
+ * So scale factor is given by:
+ * 	g * N * 1000000 / 2048 for N = 2, 4, 8 and g=9.80665
+ */
 static const int mma8452_scales[3][2] = {
-	{0, 977}, {0, 1953}, {0, 3906}
+	{0, 9577}, {0, 19154}, {0, 38307}
 };
 
 static ssize_t mma8452_show_samp_freq_avail(struct device *dev,
diff --git a/drivers/iio/adc/ad799x.c b/drivers/iio/adc/ad799x.c
index 39b4cb48d73..6eba301ee03 100644
--- a/drivers/iio/adc/ad799x.c
+++ b/drivers/iio/adc/ad799x.c
@@ -427,9 +427,12 @@ static int ad799x_write_event_value(struct iio_dev *indio_dev,
 	int ret;
 	struct ad799x_state *st = iio_priv(indio_dev);
 
+	if (val < 0 || val > RES_MASK(chan->scan_type.realbits))
+		return -EINVAL;
+
 	mutex_lock(&indio_dev->mlock);
 	ret = ad799x_i2c_write16(st, ad799x_threshold_reg(chan, dir, info),
-		val);
+		val << chan->scan_type.shift);
 	mutex_unlock(&indio_dev->mlock);
 
 	return ret;
@@ -452,7 +455,8 @@ static int ad799x_read_event_value(struct iio_dev *indio_dev,
 	mutex_unlock(&indio_dev->mlock);
 	if (ret < 0)
 		return ret;
-	*val = valin;
+	*val = (valin >> chan->scan_type.shift) &
+		RES_MASK(chan->scan_type.realbits);
 
 	return IIO_VAL_INT;
 }
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index 3b5bacd4d8d..2b6a9ce9927 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -510,12 +510,11 @@ static int at91_adc_channel_init(struct iio_dev *idev)
 	return idev->num_channels;
 }
 
-static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
+static int at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
 					     struct at91_adc_trigger *triggers,
 					     const char *trigger_name)
 {
 	struct at91_adc_state *st = iio_priv(idev);
-	u8 value = 0;
 	int i;
 
 	for (i = 0; i < st->trigger_number; i++) {
@@ -528,15 +527,16 @@ static u8 at91_adc_get_trigger_value_by_name(struct iio_dev *idev,
 			return -ENOMEM;
 
 		if (strcmp(trigger_name, name) == 0) {
-			value = triggers[i].value;
 			kfree(name);
-			break;
+			if (triggers[i].value == 0)
+				return -EINVAL;
+			return triggers[i].value;
 		}
 
 		kfree(name);
 	}
 
-	return value;
+	return -EINVAL;
 }
 
 static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
@@ -546,14 +546,14 @@ static int at91_adc_configure_trigger(struct iio_trigger *trig, bool state)
 	struct iio_buffer *buffer = idev->buffer;
 	struct at91_adc_reg_desc *reg = st->registers;
 	u32 status = at91_adc_readl(st, reg->trigger_register);
-	u8 value;
+	int value;
 	u8 bit;
 
 	value = at91_adc_get_trigger_value_by_name(idev,
 						   st->trigger_list,
 						   idev->trig->name);
-	if (value == 0)
-		return -EINVAL;
+	if (value < 0)
+		return value;
 
 	if (state) {
 		st->buffer = kmalloc(idev->scan_bytes, GFP_KERNEL);
diff --git a/drivers/iio/adc/men_z188_adc.c b/drivers/iio/adc/men_z188_adc.c
index 6989c16aec2..b58d6302521 100644
--- a/drivers/iio/adc/men_z188_adc.c
+++ b/drivers/iio/adc/men_z188_adc.c
@@ -121,8 +121,8 @@ static int men_z188_probe(struct mcb_device *dev,
 	indio_dev->num_channels = ARRAY_SIZE(z188_adc_iio_channels);
 
 	mem = mcb_request_mem(dev, "z188-adc");
-	if (!mem)
-		return -ENOMEM;
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
 
 	adc->base = ioremap(mem->start, resource_size(mem));
 	if (adc->base == NULL)
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index a4db3026bec..d5dc4c6ce86 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -374,7 +374,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev,
 			return -EAGAIN;
 		}
 	}
-	map_val = chan->channel + TOTAL_CHANNELS;
+	map_val = adc_dev->channel_step[chan->scan_index];
 
 	/*
 	 * We check the complete FIFO. We programmed just one entry but in case
diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c
index 7de1c4c8794..eb86786e698 100644
--- a/drivers/iio/adc/twl4030-madc.c
+++ b/drivers/iio/adc/twl4030-madc.c
@@ -645,6 +645,7 @@ int twl4030_get_madc_conversion(int channel_no)
 	req.channels = (1 << channel_no);
 	req.method = TWL4030_MADC_SW2;
 	req.active = 0;
+	req.raw = 0;
 	req.func_cb = NULL;
 	ret = twl4030_madc_conversion(&req);
 	if (ret < 0)
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index 73282cee0c8..a3109a6f4d8 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -75,6 +75,9 @@ int hid_sensor_power_state(struct hid_sensor_common *st, bool state)
 					(s32)report_val);
 	}
 
+	sensor_hub_get_feature(st->hsdev, st->power_state.report_id,
+					st->power_state.index,
+					&state_val);
 	return 0;
 }
 EXPORT_SYMBOL(hid_sensor_power_state);
diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c
index 40f4e4935d0..fa034a3dad7 100644
--- a/drivers/iio/gyro/hid-sensor-gyro-3d.c
+++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c
@@ -110,7 +110,6 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev,
 	struct gyro_3d_state *gyro_state = iio_priv(indio_dev);
 	int report_id = -1;
 	u32 address;
-	int ret;
 	int ret_type;
 	s32 poll_value;
 
@@ -151,14 +150,12 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev,
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		ret = hid_sensor_read_samp_freq_value(
+		ret_type = hid_sensor_read_samp_freq_value(
 			&gyro_state->common_attributes, val, val2);
-			ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	case IIO_CHAN_INFO_HYSTERESIS:
-		ret = hid_sensor_read_raw_hyst_value(
+		ret_type = hid_sensor_read_raw_hyst_value(
 			&gyro_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	default:
 		ret_type = -EINVAL;
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index 36b1ae92e23..9f1a1400990 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -966,7 +966,7 @@ static int iio_buffer_update_demux(struct iio_dev *indio_dev,
 
 	/* Now we have the two masks, work from least sig and build up sizes */
 	for_each_set_bit(out_ind,
-			 indio_dev->active_scan_mask,
+			 buffer->scan_mask,
 			 indio_dev->masklength) {
 		in_ind = find_next_bit(indio_dev->active_scan_mask,
 				       indio_dev->masklength,
diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
index 258a973a1fb..bfbf4d419f4 100644
--- a/drivers/iio/industrialio-event.c
+++ b/drivers/iio/industrialio-event.c
@@ -345,6 +345,9 @@ static int iio_device_add_event(struct iio_dev *indio_dev,
 			&indio_dev->event_interface->dev_attr_list);
 		kfree(postfix);
 
+		if ((ret == -EBUSY) && (shared_by != IIO_SEPARATE))
+			continue;
+
 		if (ret)
 			return ret;
 
diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
index d833d55052e..c7497009d60 100644
--- a/drivers/iio/inkern.c
+++ b/drivers/iio/inkern.c
@@ -183,7 +183,7 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np,
 		else if (name && index >= 0) {
 			pr_err("ERROR: could not get IIO channel %s:%s(%i)\n",
 				np->full_name, name ? name : "", index);
-			return chan;
+			return NULL;
 		}
 
 		/*
@@ -193,8 +193,9 @@ static struct iio_channel *of_iio_channel_get_by_name(struct device_node *np,
 		 */
 		np = np->parent;
 		if (np && !of_get_property(np, "io-channel-ranges", NULL))
-			break;
+			return NULL;
 	}
+
 	return chan;
 }
 
@@ -317,6 +318,7 @@ struct iio_channel *iio_channel_get(struct device *dev,
 		if (channel != NULL)
 			return channel;
 	}
+
 	return iio_channel_get_sys(name, channel_name);
 }
 EXPORT_SYMBOL_GPL(iio_channel_get);
diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c
index f34c94380b4..96e71e103ea 100644
--- a/drivers/iio/light/hid-sensor-als.c
+++ b/drivers/iio/light/hid-sensor-als.c
@@ -79,7 +79,6 @@ static int als_read_raw(struct iio_dev *indio_dev,
 	struct als_state *als_state = iio_priv(indio_dev);
 	int report_id = -1;
 	u32 address;
-	int ret;
 	int ret_type;
 	s32 poll_value;
 
@@ -129,14 +128,12 @@ static int als_read_raw(struct iio_dev *indio_dev,
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		ret = hid_sensor_read_samp_freq_value(
+		ret_type = hid_sensor_read_samp_freq_value(
 				&als_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	case IIO_CHAN_INFO_HYSTERESIS:
-		ret = hid_sensor_read_raw_hyst_value(
+		ret_type = hid_sensor_read_raw_hyst_value(
 				&als_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	default:
 		ret_type = -EINVAL;
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index d203ef4d892..412bae86d6a 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -74,7 +74,6 @@ static int prox_read_raw(struct iio_dev *indio_dev,
 	struct prox_state *prox_state = iio_priv(indio_dev);
 	int report_id = -1;
 	u32 address;
-	int ret;
 	int ret_type;
 	s32 poll_value;
 
@@ -125,14 +124,12 @@ static int prox_read_raw(struct iio_dev *indio_dev,
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		ret = hid_sensor_read_samp_freq_value(
+		ret_type = hid_sensor_read_samp_freq_value(
 				&prox_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	case IIO_CHAN_INFO_HYSTERESIS:
-		ret = hid_sensor_read_raw_hyst_value(
+		ret_type = hid_sensor_read_raw_hyst_value(
 				&prox_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	default:
 		ret_type = -EINVAL;
diff --git a/drivers/iio/light/tcs3472.c b/drivers/iio/light/tcs3472.c
index fe063a0a21c..752569985d1 100644
--- a/drivers/iio/light/tcs3472.c
+++ b/drivers/iio/light/tcs3472.c
@@ -52,6 +52,7 @@
 
 struct tcs3472_data {
 	struct i2c_client *client;
+	struct mutex lock;
 	u8 enable;
 	u8 control;
 	u8 atime;
@@ -116,10 +117,17 @@ static int tcs3472_read_raw(struct iio_dev *indio_dev,
 
 	switch (mask) {
 	case IIO_CHAN_INFO_RAW:
+		if (iio_buffer_enabled(indio_dev))
+			return -EBUSY;
+
+		mutex_lock(&data->lock);
 		ret = tcs3472_req_data(data);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&data->lock);
 			return ret;
+		}
 		ret = i2c_smbus_read_word_data(data->client, chan->address);
+		mutex_unlock(&data->lock);
 		if (ret < 0)
 			return ret;
 		*val = ret;
@@ -255,6 +263,7 @@ static int tcs3472_probe(struct i2c_client *client,
 	data = iio_priv(indio_dev);
 	i2c_set_clientdata(client, indio_dev);
 	data->client = client;
+	mutex_init(&data->lock);
 
 	indio_dev->dev.parent = &client->dev;
 	indio_dev->info = &tcs3472_info;
diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
index 09ea5c481f4..ea08313af0d 100644
--- a/drivers/iio/magnetometer/ak8975.c
+++ b/drivers/iio/magnetometer/ak8975.c
@@ -373,8 +373,6 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val)
 {
 	struct ak8975_data *data = iio_priv(indio_dev);
 	struct i2c_client *client = data->client;
-	u16 meas_reg;
-	s16 raw;
 	int ret;
 
 	mutex_lock(&data->lock);
@@ -422,16 +420,11 @@ static int ak8975_read_axis(struct iio_dev *indio_dev, int index, int *val)
 		dev_err(&client->dev, "Read axis data fails\n");
 		goto exit;
 	}
-	meas_reg = ret;
 
 	mutex_unlock(&data->lock);
 
-	/* Endian conversion of the measured values. */
-	raw = (s16) (le16_to_cpu(meas_reg));
-
 	/* Clamp to valid range. */
-	raw = clamp_t(s16, raw, -4096, 4095);
-	*val = raw;
+	*val = clamp_t(s16, ret, -4096, 4095);
 	return IIO_VAL_INT;
 
 exit:
diff --git a/drivers/iio/magnetometer/hid-sensor-magn-3d.c b/drivers/iio/magnetometer/hid-sensor-magn-3d.c
index 41cf29e2a37..b2b0937d513 100644
--- a/drivers/iio/magnetometer/hid-sensor-magn-3d.c
+++ b/drivers/iio/magnetometer/hid-sensor-magn-3d.c
@@ -110,7 +110,6 @@ static int magn_3d_read_raw(struct iio_dev *indio_dev,
 	struct magn_3d_state *magn_state = iio_priv(indio_dev);
 	int report_id = -1;
 	u32 address;
-	int ret;
 	int ret_type;
 	s32 poll_value;
 
@@ -153,14 +152,12 @@ static int magn_3d_read_raw(struct iio_dev *indio_dev,
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		ret = hid_sensor_read_samp_freq_value(
+		ret_type = hid_sensor_read_samp_freq_value(
 			&magn_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	case IIO_CHAN_INFO_HYSTERESIS:
-		ret = hid_sensor_read_raw_hyst_value(
+		ret_type = hid_sensor_read_raw_hyst_value(
 			&magn_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	default:
 		ret_type = -EINVAL;
diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c
index 1cd190c7378..2c0d2a4fed8 100644
--- a/drivers/iio/pressure/hid-sensor-press.c
+++ b/drivers/iio/pressure/hid-sensor-press.c
@@ -78,7 +78,6 @@ static int press_read_raw(struct iio_dev *indio_dev,
 	struct press_state *press_state = iio_priv(indio_dev);
 	int report_id = -1;
 	u32 address;
-	int ret;
 	int ret_type;
 	s32 poll_value;
 
@@ -128,14 +127,12 @@ static int press_read_raw(struct iio_dev *indio_dev,
 		ret_type = IIO_VAL_INT;
 		break;
 	case IIO_CHAN_INFO_SAMP_FREQ:
-		ret = hid_sensor_read_samp_freq_value(
+		ret_type = hid_sensor_read_samp_freq_value(
 				&press_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	case IIO_CHAN_INFO_HYSTERESIS:
-		ret = hid_sensor_read_raw_hyst_value(
+		ret_type = hid_sensor_read_raw_hyst_value(
 				&press_state->common_attributes, val, val2);
-		ret_type = IIO_VAL_INT_PLUS_MICRO;
 		break;
 	default:
 		ret_type = -EINVAL;
diff --git a/drivers/iio/pressure/mpl3115.c b/drivers/iio/pressure/mpl3115.c
index ba6d0c520e6..01b2e0b1887 100644
--- a/drivers/iio/pressure/mpl3115.c
+++ b/drivers/iio/pressure/mpl3115.c
@@ -98,7 +98,7 @@ static int mpl3115_read_raw(struct iio_dev *indio_dev,
 			mutex_unlock(&data->lock);
 			if (ret < 0)
 				return ret;
-			*val = sign_extend32(be32_to_cpu(tmp) >> 12, 23);
+			*val = be32_to_cpu(tmp) >> 12;
 			return IIO_VAL_INT;
 		case IIO_TEMP: /* in 0.0625 celsius / LSB */
 			mutex_lock(&data->lock);
@@ -112,7 +112,7 @@ static int mpl3115_read_raw(struct iio_dev *indio_dev,
 			mutex_unlock(&data->lock);
 			if (ret < 0)
 				return ret;
-			*val = sign_extend32(be32_to_cpu(tmp) >> 20, 15);
+			*val = sign_extend32(be32_to_cpu(tmp) >> 20, 11);
 			return IIO_VAL_INT;
 		default:
 			return -EINVAL;
@@ -185,7 +185,7 @@ static const struct iio_chan_spec mpl3115_channels[] = {
 			BIT(IIO_CHAN_INFO_SCALE),
 		.scan_index = 0,
 		.scan_type = {
-			.sign = 's',
+			.sign = 'u',
 			.realbits = 20,
 			.storagebits = 32,
 			.shift = 12,
diff --git a/drivers/infiniband/Makefile b/drivers/infiniband/Makefile
index bf508b5550c..dc21836b5a8 100644
--- a/drivers/infiniband/Makefile
+++ b/drivers/infiniband/Makefile
@@ -1,18 +1,3 @@
 obj-$(CONFIG_INFINIBAND)		+= core/
-obj-$(CONFIG_INFINIBAND_MTHCA)		+= hw/mthca/
-obj-$(CONFIG_INFINIBAND_IPATH)		+= hw/ipath/
-obj-$(CONFIG_INFINIBAND_QIB)		+= hw/qib/
-obj-$(CONFIG_INFINIBAND_EHCA)		+= hw/ehca/
-obj-$(CONFIG_INFINIBAND_AMSO1100)	+= hw/amso1100/
-obj-$(CONFIG_INFINIBAND_CXGB3)		+= hw/cxgb3/
-obj-$(CONFIG_INFINIBAND_CXGB4)		+= hw/cxgb4/
-obj-$(CONFIG_MLX4_INFINIBAND)		+= hw/mlx4/
-obj-$(CONFIG_MLX5_INFINIBAND)		+= hw/mlx5/
-obj-$(CONFIG_INFINIBAND_NES)		+= hw/nes/
-obj-$(CONFIG_INFINIBAND_OCRDMA)		+= hw/ocrdma/
-obj-$(CONFIG_INFINIBAND_USNIC)		+= hw/usnic/
-obj-$(CONFIG_INFINIBAND_IPOIB)		+= ulp/ipoib/
-obj-$(CONFIG_INFINIBAND_SRP)		+= ulp/srp/
-obj-$(CONFIG_INFINIBAND_SRPT)		+= ulp/srpt/
-obj-$(CONFIG_INFINIBAND_ISER)		+= ulp/iser/
-obj-$(CONFIG_INFINIBAND_ISERT)		+= ulp/isert/
+obj-$(CONFIG_INFINIBAND)		+= hw/
+obj-$(CONFIG_INFINIBAND)		+= ulp/
diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 3ab3865544b..ffd0af6734a 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -18,7 +18,7 @@ ib_sa-y :=			sa_query.o multicast.o
 
 ib_cm-y :=			cm.o
 
-iw_cm-y :=			iwcm.o
+iw_cm-y :=			iwcm.o iwpm_util.o iwpm_msg.o
 
 rdma_cm-y :=			cma.o
 
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 42c3058e6e9..d570030d899 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -3607,7 +3607,8 @@ static int cma_get_id_stats(struct sk_buff *skb, struct netlink_callback *cb)
 
 			id_stats = ibnl_put_msg(skb, &nlh, cb->nlh->nlmsg_seq,
 						sizeof *id_stats, RDMA_NL_RDMA_CM,
-						RDMA_NL_RDMA_CM_ID_STATS);
+						RDMA_NL_RDMA_CM_ID_STATS,
+						NLM_F_MULTI);
 			if (!id_stats)
 				goto out;
 
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
new file mode 100644
index 00000000000..b85ddbc979e
--- /dev/null
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -0,0 +1,685 @@
+/*
+ * Copyright (c) 2014 Intel Corporation. All rights reserved.
+ * Copyright (c) 2014 Chelsio, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "iwpm_util.h"
+
+static const char iwpm_ulib_name[] = "iWarpPortMapperUser";
+static int iwpm_ulib_version = 3;
+static int iwpm_user_pid = IWPM_PID_UNDEFINED;
+static atomic_t echo_nlmsg_seq;
+
+int iwpm_valid_pid(void)
+{
+	return iwpm_user_pid > 0;
+}
+EXPORT_SYMBOL(iwpm_valid_pid);
+
+/*
+ * iwpm_register_pid - Send a netlink query to user space
+ *                     for the iwarp port mapper pid
+ *
+ * nlmsg attributes:
+ *	[IWPM_NLA_REG_PID_SEQ]
+ *	[IWPM_NLA_REG_IF_NAME]
+ *	[IWPM_NLA_REG_IBDEV_NAME]
+ *	[IWPM_NLA_REG_ULIB_NAME]
+ */
+int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
+{
+	struct sk_buff *skb = NULL;
+	struct iwpm_nlmsg_request *nlmsg_request = NULL;
+	struct nlmsghdr *nlh;
+	u32 msg_seq;
+	const char *err_str = "";
+	int ret = -EINVAL;
+
+	if (!iwpm_valid_client(nl_client)) {
+		err_str = "Invalid port mapper client";
+		goto pid_query_error;
+	}
+	if (iwpm_registered_client(nl_client))
+		return 0;
+	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REG_PID, &nlh, nl_client);
+	if (!skb) {
+		err_str = "Unable to create a nlmsg";
+		goto pid_query_error;
+	}
+	nlh->nlmsg_seq = iwpm_get_nlmsg_seq();
+	nlmsg_request = iwpm_get_nlmsg_request(nlh->nlmsg_seq, nl_client, GFP_KERNEL);
+	if (!nlmsg_request) {
+		err_str = "Unable to allocate netlink request";
+		goto pid_query_error;
+	}
+	msg_seq = atomic_read(&echo_nlmsg_seq);
+
+	/* fill in the pid request message */
+	err_str = "Unable to put attribute of the nlmsg";
+	ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_REG_PID_SEQ);
+	if (ret)
+		goto pid_query_error;
+	ret = ibnl_put_attr(skb, nlh, IWPM_IFNAME_SIZE,
+				pm_msg->if_name, IWPM_NLA_REG_IF_NAME);
+	if (ret)
+		goto pid_query_error;
+	ret = ibnl_put_attr(skb, nlh, IWPM_DEVNAME_SIZE,
+				pm_msg->dev_name, IWPM_NLA_REG_IBDEV_NAME);
+	if (ret)
+		goto pid_query_error;
+	ret = ibnl_put_attr(skb, nlh, IWPM_ULIBNAME_SIZE,
+				(char *)iwpm_ulib_name, IWPM_NLA_REG_ULIB_NAME);
+	if (ret)
+		goto pid_query_error;
+
+	pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n",
+		__func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name);
+
+	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
+	if (ret) {
+		skb = NULL; /* skb is freed in the netlink send-op handling */
+		iwpm_set_registered(nl_client, 1);
+		iwpm_user_pid = IWPM_PID_UNAVAILABLE;
+		err_str = "Unable to send a nlmsg";
+		goto pid_query_error;
+	}
+	nlmsg_request->req_buffer = pm_msg;
+	ret = iwpm_wait_complete_req(nlmsg_request);
+	return ret;
+pid_query_error:
+	pr_info("%s: %s (client = %d)\n", __func__, err_str, nl_client);
+	if (skb)
+		dev_kfree_skb(skb);
+	if (nlmsg_request)
+		iwpm_free_nlmsg_request(&nlmsg_request->kref);
+	return ret;
+}
+EXPORT_SYMBOL(iwpm_register_pid);
+
+/*
+ * iwpm_add_mapping - Send a netlink add mapping message
+ *                    to the port mapper
+ * nlmsg attributes:
+ *	[IWPM_NLA_MANAGE_MAPPING_SEQ]
+ *	[IWPM_NLA_MANAGE_ADDR]
+ */
+int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
+{
+	struct sk_buff *skb = NULL;
+	struct iwpm_nlmsg_request *nlmsg_request = NULL;
+	struct nlmsghdr *nlh;
+	u32 msg_seq;
+	const char *err_str = "";
+	int ret = -EINVAL;
+
+	if (!iwpm_valid_client(nl_client)) {
+		err_str = "Invalid port mapper client";
+		goto add_mapping_error;
+	}
+	if (!iwpm_registered_client(nl_client)) {
+		err_str = "Unregistered port mapper client";
+		goto add_mapping_error;
+	}
+	if (!iwpm_valid_pid())
+		return 0;
+	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_ADD_MAPPING, &nlh, nl_client);
+	if (!skb) {
+		err_str = "Unable to create a nlmsg";
+		goto add_mapping_error;
+	}
+	nlh->nlmsg_seq = iwpm_get_nlmsg_seq();
+	nlmsg_request = iwpm_get_nlmsg_request(nlh->nlmsg_seq, nl_client, GFP_KERNEL);
+	if (!nlmsg_request) {
+		err_str = "Unable to allocate netlink request";
+		goto add_mapping_error;
+	}
+	msg_seq = atomic_read(&echo_nlmsg_seq);
+	/* fill in the add mapping message */
+	err_str = "Unable to put attribute of the nlmsg";
+	ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq,
+				IWPM_NLA_MANAGE_MAPPING_SEQ);
+	if (ret)
+		goto add_mapping_error;
+	ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage),
+				&pm_msg->loc_addr, IWPM_NLA_MANAGE_ADDR);
+	if (ret)
+		goto add_mapping_error;
+	nlmsg_request->req_buffer = pm_msg;
+
+	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	if (ret) {
+		skb = NULL; /* skb is freed in the netlink send-op handling */
+		iwpm_user_pid = IWPM_PID_UNDEFINED;
+		err_str = "Unable to send a nlmsg";
+		goto add_mapping_error;
+	}
+	ret = iwpm_wait_complete_req(nlmsg_request);
+	return ret;
+add_mapping_error:
+	pr_info("%s: %s (client = %d)\n", __func__, err_str, nl_client);
+	if (skb)
+		dev_kfree_skb(skb);
+	if (nlmsg_request)
+		iwpm_free_nlmsg_request(&nlmsg_request->kref);
+	return ret;
+}
+EXPORT_SYMBOL(iwpm_add_mapping);
+
+/*
+ * iwpm_add_and_query_mapping - Send a netlink add and query
+ *                              mapping message to the port mapper
+ * nlmsg attributes:
+ *	[IWPM_NLA_QUERY_MAPPING_SEQ]
+ *	[IWPM_NLA_QUERY_LOCAL_ADDR]
+ *	[IWPM_NLA_QUERY_REMOTE_ADDR]
+ */
+int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
+{
+	struct sk_buff *skb = NULL;
+	struct iwpm_nlmsg_request *nlmsg_request = NULL;
+	struct nlmsghdr *nlh;
+	u32 msg_seq;
+	const char *err_str = "";
+	int ret = -EINVAL;
+
+	if (!iwpm_valid_client(nl_client)) {
+		err_str = "Invalid port mapper client";
+		goto query_mapping_error;
+	}
+	if (!iwpm_registered_client(nl_client)) {
+		err_str = "Unregistered port mapper client";
+		goto query_mapping_error;
+	}
+	if (!iwpm_valid_pid())
+		return 0;
+	ret = -ENOMEM;
+	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_QUERY_MAPPING, &nlh, nl_client);
+	if (!skb) {
+		err_str = "Unable to create a nlmsg";
+		goto query_mapping_error;
+	}
+	nlh->nlmsg_seq = iwpm_get_nlmsg_seq();
+	nlmsg_request = iwpm_get_nlmsg_request(nlh->nlmsg_seq,
+				nl_client, GFP_KERNEL);
+	if (!nlmsg_request) {
+		err_str = "Unable to allocate netlink request";
+		goto query_mapping_error;
+	}
+	msg_seq = atomic_read(&echo_nlmsg_seq);
+
+	/* fill in the query message */
+	err_str = "Unable to put attribute of the nlmsg";
+	ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq,
+				IWPM_NLA_QUERY_MAPPING_SEQ);
+	if (ret)
+		goto query_mapping_error;
+	ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage),
+				&pm_msg->loc_addr, IWPM_NLA_QUERY_LOCAL_ADDR);
+	if (ret)
+		goto query_mapping_error;
+	ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage),
+				&pm_msg->rem_addr, IWPM_NLA_QUERY_REMOTE_ADDR);
+	if (ret)
+		goto query_mapping_error;
+	nlmsg_request->req_buffer = pm_msg;
+
+	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	if (ret) {
+		skb = NULL; /* skb is freed in the netlink send-op handling */
+		err_str = "Unable to send a nlmsg";
+		goto query_mapping_error;
+	}
+	ret = iwpm_wait_complete_req(nlmsg_request);
+	return ret;
+query_mapping_error:
+	pr_info("%s: %s (client = %d)\n", __func__, err_str, nl_client);
+	if (skb)
+		dev_kfree_skb(skb);
+	if (nlmsg_request)
+		iwpm_free_nlmsg_request(&nlmsg_request->kref);
+	return ret;
+}
+EXPORT_SYMBOL(iwpm_add_and_query_mapping);
+
+/*
+ * iwpm_remove_mapping - Send a netlink remove mapping message
+ *                       to the port mapper
+ * nlmsg attributes:
+ *	[IWPM_NLA_MANAGE_MAPPING_SEQ]
+ *	[IWPM_NLA_MANAGE_ADDR]
+ */
+int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
+{
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	u32 msg_seq;
+	const char *err_str = "";
+	int ret = -EINVAL;
+
+	if (!iwpm_valid_client(nl_client)) {
+		err_str = "Invalid port mapper client";
+		goto remove_mapping_error;
+	}
+	if (!iwpm_registered_client(nl_client)) {
+		err_str = "Unregistered port mapper client";
+		goto remove_mapping_error;
+	}
+	if (!iwpm_valid_pid())
+		return 0;
+	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REMOVE_MAPPING, &nlh, nl_client);
+	if (!skb) {
+		ret = -ENOMEM;
+		err_str = "Unable to create a nlmsg";
+		goto remove_mapping_error;
+	}
+	msg_seq = atomic_read(&echo_nlmsg_seq);
+	nlh->nlmsg_seq = iwpm_get_nlmsg_seq();
+	err_str = "Unable to put attribute of the nlmsg";
+	ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq,
+				IWPM_NLA_MANAGE_MAPPING_SEQ);
+	if (ret)
+		goto remove_mapping_error;
+	ret = ibnl_put_attr(skb, nlh, sizeof(struct sockaddr_storage),
+				local_addr, IWPM_NLA_MANAGE_ADDR);
+	if (ret)
+		goto remove_mapping_error;
+
+	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	if (ret) {
+		skb = NULL; /* skb is freed in the netlink send-op handling */
+		iwpm_user_pid = IWPM_PID_UNDEFINED;
+		err_str = "Unable to send a nlmsg";
+		goto remove_mapping_error;
+	}
+	iwpm_print_sockaddr(local_addr,
+			"remove_mapping: Local sockaddr:");
+	return 0;
+remove_mapping_error:
+	pr_info("%s: %s (client = %d)\n", __func__, err_str, nl_client);
+	if (skb)
+		dev_kfree_skb_any(skb);
+	return ret;
+}
+EXPORT_SYMBOL(iwpm_remove_mapping);
+
+/* netlink attribute policy for the received response to register pid request */
+static const struct nla_policy resp_reg_policy[IWPM_NLA_RREG_PID_MAX] = {
+	[IWPM_NLA_RREG_PID_SEQ]     = { .type = NLA_U32 },
+	[IWPM_NLA_RREG_IBDEV_NAME]  = { .type = NLA_STRING,
+					.len = IWPM_DEVNAME_SIZE - 1 },
+	[IWPM_NLA_RREG_ULIB_NAME]   = { .type = NLA_STRING,
+					.len = IWPM_ULIBNAME_SIZE - 1 },
+	[IWPM_NLA_RREG_ULIB_VER]    = { .type = NLA_U16 },
+	[IWPM_NLA_RREG_PID_ERR]     = { .type = NLA_U16 }
+};
+
+/*
+ * iwpm_register_pid_cb - Process a port mapper response to
+ *                        iwpm_register_pid()
+ */
+int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct iwpm_nlmsg_request *nlmsg_request = NULL;
+	struct nlattr *nltb[IWPM_NLA_RREG_PID_MAX];
+	struct iwpm_dev_data *pm_msg;
+	char *dev_name, *iwpm_name;
+	u32 msg_seq;
+	u8 nl_client;
+	u16 iwpm_version;
+	const char *msg_type = "Register Pid response";
+
+	if (iwpm_parse_nlmsg(cb, IWPM_NLA_RREG_PID_MAX,
+				resp_reg_policy, nltb, msg_type))
+		return -EINVAL;
+
+	msg_seq = nla_get_u32(nltb[IWPM_NLA_RREG_PID_SEQ]);
+	nlmsg_request = iwpm_find_nlmsg_request(msg_seq);
+	if (!nlmsg_request) {
+		pr_info("%s: Could not find a matching request (seq = %u)\n",
+				 __func__, msg_seq);
+		return -EINVAL;
+	}
+	pm_msg = nlmsg_request->req_buffer;
+	nl_client = nlmsg_request->nl_client;
+	dev_name = (char *)nla_data(nltb[IWPM_NLA_RREG_IBDEV_NAME]);
+	iwpm_name = (char *)nla_data(nltb[IWPM_NLA_RREG_ULIB_NAME]);
+	iwpm_version = nla_get_u16(nltb[IWPM_NLA_RREG_ULIB_VER]);
+
+	/* check device name, ulib name and version */
+	if (strcmp(pm_msg->dev_name, dev_name) ||
+			strcmp(iwpm_ulib_name, iwpm_name) ||
+			iwpm_version != iwpm_ulib_version) {
+
+		pr_info("%s: Incorrect info (dev = %s name = %s version = %d)\n",
+				__func__, dev_name, iwpm_name, iwpm_version);
+		nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR;
+		goto register_pid_response_exit;
+	}
+	iwpm_user_pid = cb->nlh->nlmsg_pid;
+	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+	pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n",
+			__func__, iwpm_user_pid);
+	if (iwpm_valid_client(nl_client))
+		iwpm_set_registered(nl_client, 1);
+register_pid_response_exit:
+	nlmsg_request->request_done = 1;
+	/* always for found nlmsg_request */
+	kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request);
+	barrier();
+	wake_up(&nlmsg_request->waitq);
+	return 0;
+}
+EXPORT_SYMBOL(iwpm_register_pid_cb);
+
+/* netlink attribute policy for the received response to add mapping request */
+static const struct nla_policy resp_add_policy[IWPM_NLA_RMANAGE_MAPPING_MAX] = {
+	[IWPM_NLA_MANAGE_MAPPING_SEQ]     = { .type = NLA_U32 },
+	[IWPM_NLA_MANAGE_ADDR]            = { .len = sizeof(struct sockaddr_storage) },
+	[IWPM_NLA_MANAGE_MAPPED_LOC_ADDR] = { .len = sizeof(struct sockaddr_storage) },
+	[IWPM_NLA_RMANAGE_MAPPING_ERR]	  = { .type = NLA_U16 }
+};
+
+/*
+ * iwpm_add_mapping_cb - Process a port mapper response to
+ *                       iwpm_add_mapping()
+ */
+int iwpm_add_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct iwpm_sa_data *pm_msg;
+	struct iwpm_nlmsg_request *nlmsg_request = NULL;
+	struct nlattr *nltb[IWPM_NLA_RMANAGE_MAPPING_MAX];
+	struct sockaddr_storage *local_sockaddr;
+	struct sockaddr_storage *mapped_sockaddr;
+	const char *msg_type;
+	u32 msg_seq;
+
+	msg_type = "Add Mapping response";
+	if (iwpm_parse_nlmsg(cb, IWPM_NLA_RMANAGE_MAPPING_MAX,
+				resp_add_policy, nltb, msg_type))
+		return -EINVAL;
+
+	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+
+	msg_seq = nla_get_u32(nltb[IWPM_NLA_MANAGE_MAPPING_SEQ]);
+	nlmsg_request = iwpm_find_nlmsg_request(msg_seq);
+	if (!nlmsg_request) {
+		pr_info("%s: Could not find a matching request (seq = %u)\n",
+				 __func__, msg_seq);
+		return -EINVAL;
+	}
+	pm_msg = nlmsg_request->req_buffer;
+	local_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_MANAGE_ADDR]);
+	mapped_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_MANAGE_MAPPED_LOC_ADDR]);
+
+	if (iwpm_compare_sockaddr(local_sockaddr, &pm_msg->loc_addr)) {
+		nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR;
+		goto add_mapping_response_exit;
+	}
+	if (mapped_sockaddr->ss_family != local_sockaddr->ss_family) {
+		pr_info("%s: Sockaddr family doesn't match the requested one\n",
+				__func__);
+		nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR;
+		goto add_mapping_response_exit;
+	}
+	memcpy(&pm_msg->mapped_loc_addr, mapped_sockaddr,
+			sizeof(*mapped_sockaddr));
+	iwpm_print_sockaddr(&pm_msg->loc_addr,
+			"add_mapping: Local sockaddr:");
+	iwpm_print_sockaddr(&pm_msg->mapped_loc_addr,
+			"add_mapping: Mapped local sockaddr:");
+
+add_mapping_response_exit:
+	nlmsg_request->request_done = 1;
+	/* always for found request */
+	kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request);
+	barrier();
+	wake_up(&nlmsg_request->waitq);
+	return 0;
+}
+EXPORT_SYMBOL(iwpm_add_mapping_cb);
+
+/* netlink attribute policy for the response to add and query mapping request */
+static const struct nla_policy resp_query_policy[IWPM_NLA_RQUERY_MAPPING_MAX] = {
+	[IWPM_NLA_QUERY_MAPPING_SEQ]      = { .type = NLA_U32 },
+	[IWPM_NLA_QUERY_LOCAL_ADDR]       = { .len = sizeof(struct sockaddr_storage) },
+	[IWPM_NLA_QUERY_REMOTE_ADDR]      = { .len = sizeof(struct sockaddr_storage) },
+	[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR] = { .len = sizeof(struct sockaddr_storage) },
+	[IWPM_NLA_RQUERY_MAPPED_REM_ADDR] = { .len = sizeof(struct sockaddr_storage) },
+	[IWPM_NLA_RQUERY_MAPPING_ERR]	  = { .type = NLA_U16 }
+};
+
+/*
+ * iwpm_add_and_query_mapping_cb - Process a port mapper response to
+ *                                 iwpm_add_and_query_mapping()
+ */
+int iwpm_add_and_query_mapping_cb(struct sk_buff *skb,
+				struct netlink_callback *cb)
+{
+	struct iwpm_sa_data *pm_msg;
+	struct iwpm_nlmsg_request *nlmsg_request = NULL;
+	struct nlattr *nltb[IWPM_NLA_RQUERY_MAPPING_MAX];
+	struct sockaddr_storage *local_sockaddr, *remote_sockaddr;
+	struct sockaddr_storage *mapped_loc_sockaddr, *mapped_rem_sockaddr;
+	const char *msg_type;
+	u32 msg_seq;
+	u16 err_code;
+
+	msg_type = "Query Mapping response";
+	if (iwpm_parse_nlmsg(cb, IWPM_NLA_RQUERY_MAPPING_MAX,
+				resp_query_policy, nltb, msg_type))
+		return -EINVAL;
+	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+
+	msg_seq = nla_get_u32(nltb[IWPM_NLA_QUERY_MAPPING_SEQ]);
+	nlmsg_request = iwpm_find_nlmsg_request(msg_seq);
+	if (!nlmsg_request) {
+		pr_info("%s: Could not find a matching request (seq = %u)\n",
+				 __func__, msg_seq);
+			return -EINVAL;
+	}
+	pm_msg = nlmsg_request->req_buffer;
+	local_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_QUERY_LOCAL_ADDR]);
+	remote_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_QUERY_REMOTE_ADDR]);
+	mapped_loc_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_LOC_ADDR]);
+	mapped_rem_sockaddr = (struct sockaddr_storage *)
+			nla_data(nltb[IWPM_NLA_RQUERY_MAPPED_REM_ADDR]);
+
+	err_code = nla_get_u16(nltb[IWPM_NLA_RQUERY_MAPPING_ERR]);
+	if (err_code == IWPM_REMOTE_QUERY_REJECT) {
+		pr_info("%s: Received a Reject (pid = %u, echo seq = %u)\n",
+			__func__, cb->nlh->nlmsg_pid, msg_seq);
+		nlmsg_request->err_code = IWPM_REMOTE_QUERY_REJECT;
+	}
+	if (iwpm_compare_sockaddr(local_sockaddr, &pm_msg->loc_addr) ||
+		iwpm_compare_sockaddr(remote_sockaddr, &pm_msg->rem_addr)) {
+		pr_info("%s: Incorrect local sockaddr\n", __func__);
+		nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR;
+		goto query_mapping_response_exit;
+	}
+	if (mapped_loc_sockaddr->ss_family != local_sockaddr->ss_family ||
+		mapped_rem_sockaddr->ss_family != remote_sockaddr->ss_family) {
+		pr_info("%s: Sockaddr family doesn't match the requested one\n",
+				__func__);
+		nlmsg_request->err_code = IWPM_USER_LIB_INFO_ERR;
+		goto query_mapping_response_exit;
+	}
+	memcpy(&pm_msg->mapped_loc_addr, mapped_loc_sockaddr,
+			sizeof(*mapped_loc_sockaddr));
+	memcpy(&pm_msg->mapped_rem_addr, mapped_rem_sockaddr,
+			sizeof(*mapped_rem_sockaddr));
+
+	iwpm_print_sockaddr(&pm_msg->loc_addr,
+			"query_mapping: Local sockaddr:");
+	iwpm_print_sockaddr(&pm_msg->mapped_loc_addr,
+			"query_mapping: Mapped local sockaddr:");
+	iwpm_print_sockaddr(&pm_msg->rem_addr,
+			"query_mapping: Remote sockaddr:");
+	iwpm_print_sockaddr(&pm_msg->mapped_rem_addr,
+			"query_mapping: Mapped remote sockaddr:");
+query_mapping_response_exit:
+	nlmsg_request->request_done = 1;
+	/* always for found request */
+	kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request);
+	barrier();
+	wake_up(&nlmsg_request->waitq);
+	return 0;
+}
+EXPORT_SYMBOL(iwpm_add_and_query_mapping_cb);
+
+/* netlink attribute policy for the received request for mapping info */
+static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = {
+	[IWPM_NLA_MAPINFO_ULIB_NAME] = { .type = NLA_STRING,
+					.len = IWPM_ULIBNAME_SIZE - 1 },
+	[IWPM_NLA_MAPINFO_ULIB_VER]  = { .type = NLA_U16 }
+};
+
+/*
+ * iwpm_mapping_info_cb - Process a port mapper request for mapping info
+ */
+int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct nlattr *nltb[IWPM_NLA_MAPINFO_REQ_MAX];
+	const char *msg_type = "Mapping Info response";
+	int iwpm_pid;
+	u8 nl_client;
+	char *iwpm_name;
+	u16 iwpm_version;
+	int ret = -EINVAL;
+
+	if (iwpm_parse_nlmsg(cb, IWPM_NLA_MAPINFO_REQ_MAX,
+				resp_mapinfo_policy, nltb, msg_type)) {
+		pr_info("%s: Unable to parse nlmsg\n", __func__);
+		return ret;
+	}
+	iwpm_name = (char *)nla_data(nltb[IWPM_NLA_MAPINFO_ULIB_NAME]);
+	iwpm_version = nla_get_u16(nltb[IWPM_NLA_MAPINFO_ULIB_VER]);
+	if (strcmp(iwpm_ulib_name, iwpm_name) ||
+			iwpm_version != iwpm_ulib_version) {
+		pr_info("%s: Invalid port mapper name = %s version = %d\n",
+				__func__, iwpm_name, iwpm_version);
+		return ret;
+	}
+	nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type);
+	if (!iwpm_valid_client(nl_client)) {
+		pr_info("%s: Invalid port mapper client = %d\n",
+				__func__, nl_client);
+		return ret;
+	}
+	iwpm_set_registered(nl_client, 0);
+	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+	if (!iwpm_mapinfo_available())
+		return 0;
+	iwpm_pid = cb->nlh->nlmsg_pid;
+	pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n",
+		 __func__, iwpm_pid);
+	ret = iwpm_send_mapinfo(nl_client, iwpm_pid);
+	return ret;
+}
+EXPORT_SYMBOL(iwpm_mapping_info_cb);
+
+/* netlink attribute policy for the received mapping info ack */
+static const struct nla_policy ack_mapinfo_policy[IWPM_NLA_MAPINFO_NUM_MAX] = {
+	[IWPM_NLA_MAPINFO_SEQ]    =   { .type = NLA_U32 },
+	[IWPM_NLA_MAPINFO_SEND_NUM] = { .type = NLA_U32 },
+	[IWPM_NLA_MAPINFO_ACK_NUM] =  { .type = NLA_U32 }
+};
+
+/*
+ * iwpm_ack_mapping_info_cb - Process a port mapper ack for
+ *                            the provided mapping info records
+ */
+int iwpm_ack_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct nlattr *nltb[IWPM_NLA_MAPINFO_NUM_MAX];
+	u32 mapinfo_send, mapinfo_ack;
+	const char *msg_type = "Mapping Info Ack";
+
+	if (iwpm_parse_nlmsg(cb, IWPM_NLA_MAPINFO_NUM_MAX,
+				ack_mapinfo_policy, nltb, msg_type))
+		return -EINVAL;
+	mapinfo_send = nla_get_u32(nltb[IWPM_NLA_MAPINFO_SEND_NUM]);
+	mapinfo_ack = nla_get_u32(nltb[IWPM_NLA_MAPINFO_ACK_NUM]);
+	if (mapinfo_ack != mapinfo_send)
+		pr_info("%s: Invalid mapinfo number (sent = %u ack-ed = %u)\n",
+			__func__, mapinfo_send, mapinfo_ack);
+	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+	return 0;
+}
+EXPORT_SYMBOL(iwpm_ack_mapping_info_cb);
+
+/* netlink attribute policy for the received port mapper error message */
+static const struct nla_policy map_error_policy[IWPM_NLA_ERR_MAX] = {
+	[IWPM_NLA_ERR_SEQ]        = { .type = NLA_U32 },
+	[IWPM_NLA_ERR_CODE]       = { .type = NLA_U16 },
+};
+
+/*
+ * iwpm_mapping_error_cb - Process a port mapper error message
+ */
+int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct iwpm_nlmsg_request *nlmsg_request = NULL;
+	int nl_client = RDMA_NL_GET_CLIENT(cb->nlh->nlmsg_type);
+	struct nlattr *nltb[IWPM_NLA_ERR_MAX];
+	u32 msg_seq;
+	u16 err_code;
+	const char *msg_type = "Mapping Error Msg";
+
+	if (iwpm_parse_nlmsg(cb, IWPM_NLA_ERR_MAX,
+				map_error_policy, nltb, msg_type))
+		return -EINVAL;
+
+	msg_seq = nla_get_u32(nltb[IWPM_NLA_ERR_SEQ]);
+	err_code = nla_get_u16(nltb[IWPM_NLA_ERR_CODE]);
+	pr_info("%s: Received msg seq = %u err code = %u client = %d\n",
+				__func__, msg_seq, err_code, nl_client);
+	/* look for nlmsg_request */
+	nlmsg_request = iwpm_find_nlmsg_request(msg_seq);
+	if (!nlmsg_request) {
+		/* not all errors have associated requests */
+		pr_debug("Could not find matching req (seq = %u)\n", msg_seq);
+		return 0;
+	}
+	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+	nlmsg_request->err_code = err_code;
+	nlmsg_request->request_done = 1;
+	/* always for found request */
+	kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request);
+	barrier();
+	wake_up(&nlmsg_request->waitq);
+	return 0;
+}
+EXPORT_SYMBOL(iwpm_mapping_error_cb);
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
new file mode 100644
index 00000000000..69e9f84c160
--- /dev/null
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -0,0 +1,607 @@
+/*
+ * Copyright (c) 2014 Chelsio, Inc. All rights reserved.
+ * Copyright (c) 2014 Intel Corporation. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *	  copyright notice, this list of conditions and the following
+ *	  disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *	  copyright notice, this list of conditions and the following
+ *	  disclaimer in the documentation and/or other materials
+ *	  provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "iwpm_util.h"
+
+#define IWPM_HASH_BUCKET_SIZE	512
+#define IWPM_HASH_BUCKET_MASK	(IWPM_HASH_BUCKET_SIZE - 1)
+
+static LIST_HEAD(iwpm_nlmsg_req_list);
+static DEFINE_SPINLOCK(iwpm_nlmsg_req_lock);
+
+static struct hlist_head *iwpm_hash_bucket;
+static DEFINE_SPINLOCK(iwpm_mapinfo_lock);
+
+static DEFINE_MUTEX(iwpm_admin_lock);
+static struct iwpm_admin_data iwpm_admin;
+
+int iwpm_init(u8 nl_client)
+{
+	if (iwpm_valid_client(nl_client))
+		return -EINVAL;
+	mutex_lock(&iwpm_admin_lock);
+	if (atomic_read(&iwpm_admin.refcount) == 0) {
+		iwpm_hash_bucket = kzalloc(IWPM_HASH_BUCKET_SIZE *
+					sizeof(struct hlist_head), GFP_KERNEL);
+		if (!iwpm_hash_bucket) {
+			mutex_unlock(&iwpm_admin_lock);
+			pr_err("%s Unable to create mapinfo hash table\n", __func__);
+			return -ENOMEM;
+		}
+	}
+	atomic_inc(&iwpm_admin.refcount);
+	mutex_unlock(&iwpm_admin_lock);
+	iwpm_set_valid(nl_client, 1);
+	return 0;
+}
+EXPORT_SYMBOL(iwpm_init);
+
+static void free_hash_bucket(void);
+
+int iwpm_exit(u8 nl_client)
+{
+
+	if (!iwpm_valid_client(nl_client))
+		return -EINVAL;
+	mutex_lock(&iwpm_admin_lock);
+	if (atomic_read(&iwpm_admin.refcount) == 0) {
+		mutex_unlock(&iwpm_admin_lock);
+		pr_err("%s Incorrect usage - negative refcount\n", __func__);
+		return -EINVAL;
+	}
+	if (atomic_dec_and_test(&iwpm_admin.refcount)) {
+		free_hash_bucket();
+		pr_debug("%s: Mapinfo hash table is destroyed\n", __func__);
+	}
+	mutex_unlock(&iwpm_admin_lock);
+	iwpm_set_valid(nl_client, 0);
+	return 0;
+}
+EXPORT_SYMBOL(iwpm_exit);
+
+static struct hlist_head *get_hash_bucket_head(struct sockaddr_storage *,
+					       struct sockaddr_storage *);
+
+int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
+			struct sockaddr_storage *mapped_sockaddr,
+			u8 nl_client)
+{
+	struct hlist_head *hash_bucket_head;
+	struct iwpm_mapping_info *map_info;
+	unsigned long flags;
+
+	if (!iwpm_valid_client(nl_client))
+		return -EINVAL;
+	map_info = kzalloc(sizeof(struct iwpm_mapping_info), GFP_KERNEL);
+	if (!map_info) {
+		pr_err("%s: Unable to allocate a mapping info\n", __func__);
+		return -ENOMEM;
+	}
+	memcpy(&map_info->local_sockaddr, local_sockaddr,
+	       sizeof(struct sockaddr_storage));
+	memcpy(&map_info->mapped_sockaddr, mapped_sockaddr,
+	       sizeof(struct sockaddr_storage));
+	map_info->nl_client = nl_client;
+
+	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
+	if (iwpm_hash_bucket) {
+		hash_bucket_head = get_hash_bucket_head(
+					&map_info->local_sockaddr,
+					&map_info->mapped_sockaddr);
+		hlist_add_head(&map_info->hlist_node, hash_bucket_head);
+	}
+	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(iwpm_create_mapinfo);
+
+int iwpm_remove_mapinfo(struct sockaddr_storage *local_sockaddr,
+			struct sockaddr_storage *mapped_local_addr)
+{
+	struct hlist_node *tmp_hlist_node;
+	struct hlist_head *hash_bucket_head;
+	struct iwpm_mapping_info *map_info = NULL;
+	unsigned long flags;
+	int ret = -EINVAL;
+
+	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
+	if (iwpm_hash_bucket) {
+		hash_bucket_head = get_hash_bucket_head(
+					local_sockaddr,
+					mapped_local_addr);
+		hlist_for_each_entry_safe(map_info, tmp_hlist_node,
+					hash_bucket_head, hlist_node) {
+
+			if (!iwpm_compare_sockaddr(&map_info->mapped_sockaddr,
+						mapped_local_addr)) {
+
+				hlist_del_init(&map_info->hlist_node);
+				kfree(map_info);
+				ret = 0;
+				break;
+			}
+		}
+	}
+	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(iwpm_remove_mapinfo);
+
+static void free_hash_bucket(void)
+{
+	struct hlist_node *tmp_hlist_node;
+	struct iwpm_mapping_info *map_info;
+	unsigned long flags;
+	int i;
+
+	/* remove all the mapinfo data from the list */
+	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
+	for (i = 0; i < IWPM_HASH_BUCKET_SIZE; i++) {
+		hlist_for_each_entry_safe(map_info, tmp_hlist_node,
+			&iwpm_hash_bucket[i], hlist_node) {
+
+				hlist_del_init(&map_info->hlist_node);
+				kfree(map_info);
+			}
+	}
+	/* free the hash list */
+	kfree(iwpm_hash_bucket);
+	iwpm_hash_bucket = NULL;
+	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
+}
+
+struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
+					u8 nl_client, gfp_t gfp)
+{
+	struct iwpm_nlmsg_request *nlmsg_request = NULL;
+	unsigned long flags;
+
+	nlmsg_request = kzalloc(sizeof(struct iwpm_nlmsg_request), gfp);
+	if (!nlmsg_request) {
+		pr_err("%s Unable to allocate a nlmsg_request\n", __func__);
+		return NULL;
+	}
+	spin_lock_irqsave(&iwpm_nlmsg_req_lock, flags);
+	list_add_tail(&nlmsg_request->inprocess_list, &iwpm_nlmsg_req_list);
+	spin_unlock_irqrestore(&iwpm_nlmsg_req_lock, flags);
+
+	kref_init(&nlmsg_request->kref);
+	kref_get(&nlmsg_request->kref);
+	nlmsg_request->nlmsg_seq = nlmsg_seq;
+	nlmsg_request->nl_client = nl_client;
+	nlmsg_request->request_done = 0;
+	nlmsg_request->err_code = 0;
+	return nlmsg_request;
+}
+
+void iwpm_free_nlmsg_request(struct kref *kref)
+{
+	struct iwpm_nlmsg_request *nlmsg_request;
+	unsigned long flags;
+
+	nlmsg_request = container_of(kref, struct iwpm_nlmsg_request, kref);
+
+	spin_lock_irqsave(&iwpm_nlmsg_req_lock, flags);
+	list_del_init(&nlmsg_request->inprocess_list);
+	spin_unlock_irqrestore(&iwpm_nlmsg_req_lock, flags);
+
+	if (!nlmsg_request->request_done)
+		pr_debug("%s Freeing incomplete nlmsg request (seq = %u).\n",
+			__func__, nlmsg_request->nlmsg_seq);
+	kfree(nlmsg_request);
+}
+
+struct iwpm_nlmsg_request *iwpm_find_nlmsg_request(__u32 echo_seq)
+{
+	struct iwpm_nlmsg_request *nlmsg_request;
+	struct iwpm_nlmsg_request *found_request = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iwpm_nlmsg_req_lock, flags);
+	list_for_each_entry(nlmsg_request, &iwpm_nlmsg_req_list,
+			    inprocess_list) {
+		if (nlmsg_request->nlmsg_seq == echo_seq) {
+			found_request = nlmsg_request;
+			kref_get(&nlmsg_request->kref);
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&iwpm_nlmsg_req_lock, flags);
+	return found_request;
+}
+
+int iwpm_wait_complete_req(struct iwpm_nlmsg_request *nlmsg_request)
+{
+	int ret;
+	init_waitqueue_head(&nlmsg_request->waitq);
+
+	ret = wait_event_timeout(nlmsg_request->waitq,
+			(nlmsg_request->request_done != 0), IWPM_NL_TIMEOUT);
+	if (!ret) {
+		ret = -EINVAL;
+		pr_info("%s: Timeout %d sec for netlink request (seq = %u)\n",
+			__func__, (IWPM_NL_TIMEOUT/HZ), nlmsg_request->nlmsg_seq);
+	} else {
+		ret = nlmsg_request->err_code;
+	}
+	kref_put(&nlmsg_request->kref, iwpm_free_nlmsg_request);
+	return ret;
+}
+
+int iwpm_get_nlmsg_seq(void)
+{
+	return atomic_inc_return(&iwpm_admin.nlmsg_seq);
+}
+
+int iwpm_valid_client(u8 nl_client)
+{
+	if (nl_client >= RDMA_NL_NUM_CLIENTS)
+		return 0;
+	return iwpm_admin.client_list[nl_client];
+}
+
+void iwpm_set_valid(u8 nl_client, int valid)
+{
+	if (nl_client >= RDMA_NL_NUM_CLIENTS)
+		return;
+	iwpm_admin.client_list[nl_client] = valid;
+}
+
+/* valid client */
+int iwpm_registered_client(u8 nl_client)
+{
+	return iwpm_admin.reg_list[nl_client];
+}
+
+/* valid client */
+void iwpm_set_registered(u8 nl_client, int reg)
+{
+	iwpm_admin.reg_list[nl_client] = reg;
+}
+
+int iwpm_compare_sockaddr(struct sockaddr_storage *a_sockaddr,
+				struct sockaddr_storage *b_sockaddr)
+{
+	if (a_sockaddr->ss_family != b_sockaddr->ss_family)
+		return 1;
+	if (a_sockaddr->ss_family == AF_INET) {
+		struct sockaddr_in *a4_sockaddr =
+			(struct sockaddr_in *)a_sockaddr;
+		struct sockaddr_in *b4_sockaddr =
+			(struct sockaddr_in *)b_sockaddr;
+		if (!memcmp(&a4_sockaddr->sin_addr,
+			&b4_sockaddr->sin_addr, sizeof(struct in_addr))
+			&& a4_sockaddr->sin_port == b4_sockaddr->sin_port)
+				return 0;
+
+	} else if (a_sockaddr->ss_family == AF_INET6) {
+		struct sockaddr_in6 *a6_sockaddr =
+			(struct sockaddr_in6 *)a_sockaddr;
+		struct sockaddr_in6 *b6_sockaddr =
+			(struct sockaddr_in6 *)b_sockaddr;
+		if (!memcmp(&a6_sockaddr->sin6_addr,
+			&b6_sockaddr->sin6_addr, sizeof(struct in6_addr))
+			&& a6_sockaddr->sin6_port == b6_sockaddr->sin6_port)
+				return 0;
+
+	} else {
+		pr_err("%s: Invalid sockaddr family\n", __func__);
+	}
+	return 1;
+}
+
+struct sk_buff *iwpm_create_nlmsg(u32 nl_op, struct nlmsghdr **nlh,
+						int nl_client)
+{
+	struct sk_buff *skb = NULL;
+
+	skb = dev_alloc_skb(NLMSG_GOODSIZE);
+	if (!skb) {
+		pr_err("%s Unable to allocate skb\n", __func__);
+		goto create_nlmsg_exit;
+	}
+	if (!(ibnl_put_msg(skb, nlh, 0, 0, nl_client, nl_op,
+			   NLM_F_REQUEST))) {
+		pr_warn("%s: Unable to put the nlmsg header\n", __func__);
+		dev_kfree_skb(skb);
+		skb = NULL;
+	}
+create_nlmsg_exit:
+	return skb;
+}
+
+int iwpm_parse_nlmsg(struct netlink_callback *cb, int policy_max,
+				   const struct nla_policy *nlmsg_policy,
+				   struct nlattr *nltb[], const char *msg_type)
+{
+	int nlh_len = 0;
+	int ret;
+	const char *err_str = "";
+
+	ret = nlmsg_validate(cb->nlh, nlh_len, policy_max-1, nlmsg_policy);
+	if (ret) {
+		err_str = "Invalid attribute";
+		goto parse_nlmsg_error;
+	}
+	ret = nlmsg_parse(cb->nlh, nlh_len, nltb, policy_max-1, nlmsg_policy);
+	if (ret) {
+		err_str = "Unable to parse the nlmsg";
+		goto parse_nlmsg_error;
+	}
+	ret = iwpm_validate_nlmsg_attr(nltb, policy_max);
+	if (ret) {
+		err_str = "Invalid NULL attribute";
+		goto parse_nlmsg_error;
+	}
+	return 0;
+parse_nlmsg_error:
+	pr_warn("%s: %s (msg type %s ret = %d)\n",
+			__func__, err_str, msg_type, ret);
+	return ret;
+}
+
+void iwpm_print_sockaddr(struct sockaddr_storage *sockaddr, char *msg)
+{
+	struct sockaddr_in6 *sockaddr_v6;
+	struct sockaddr_in *sockaddr_v4;
+
+	switch (sockaddr->ss_family) {
+	case AF_INET:
+		sockaddr_v4 = (struct sockaddr_in *)sockaddr;
+		pr_debug("%s IPV4 %pI4: %u(0x%04X)\n",
+			msg, &sockaddr_v4->sin_addr,
+			ntohs(sockaddr_v4->sin_port),
+			ntohs(sockaddr_v4->sin_port));
+		break;
+	case AF_INET6:
+		sockaddr_v6 = (struct sockaddr_in6 *)sockaddr;
+		pr_debug("%s IPV6 %pI6: %u(0x%04X)\n",
+			msg, &sockaddr_v6->sin6_addr,
+			ntohs(sockaddr_v6->sin6_port),
+			ntohs(sockaddr_v6->sin6_port));
+		break;
+	default:
+		break;
+	}
+}
+
+static u32 iwpm_ipv6_jhash(struct sockaddr_in6 *ipv6_sockaddr)
+{
+	u32 ipv6_hash = jhash(&ipv6_sockaddr->sin6_addr, sizeof(struct in6_addr), 0);
+	u32 hash = jhash_2words(ipv6_hash, (__force u32) ipv6_sockaddr->sin6_port, 0);
+	return hash;
+}
+
+static u32 iwpm_ipv4_jhash(struct sockaddr_in *ipv4_sockaddr)
+{
+	u32 ipv4_hash = jhash(&ipv4_sockaddr->sin_addr, sizeof(struct in_addr), 0);
+	u32 hash = jhash_2words(ipv4_hash, (__force u32) ipv4_sockaddr->sin_port, 0);
+	return hash;
+}
+
+static struct hlist_head *get_hash_bucket_head(struct sockaddr_storage
+					       *local_sockaddr,
+					       struct sockaddr_storage
+					       *mapped_sockaddr)
+{
+	u32 local_hash, mapped_hash, hash;
+
+	if (local_sockaddr->ss_family == AF_INET) {
+		local_hash = iwpm_ipv4_jhash((struct sockaddr_in *) local_sockaddr);
+		mapped_hash = iwpm_ipv4_jhash((struct sockaddr_in *) mapped_sockaddr);
+
+	} else if (local_sockaddr->ss_family == AF_INET6) {
+		local_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) local_sockaddr);
+		mapped_hash = iwpm_ipv6_jhash((struct sockaddr_in6 *) mapped_sockaddr);
+	} else {
+		pr_err("%s: Invalid sockaddr family\n", __func__);
+		return NULL;
+	}
+
+	if (local_hash == mapped_hash) /* if port mapper isn't available */
+		hash = local_hash;
+	else
+		hash = jhash_2words(local_hash, mapped_hash, 0);
+
+	return &iwpm_hash_bucket[hash & IWPM_HASH_BUCKET_MASK];
+}
+
+static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
+{
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	u32 msg_seq;
+	const char *err_str = "";
+	int ret = -EINVAL;
+
+	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_MAPINFO_NUM, &nlh, nl_client);
+	if (!skb) {
+		err_str = "Unable to create a nlmsg";
+		goto mapinfo_num_error;
+	}
+	nlh->nlmsg_seq = iwpm_get_nlmsg_seq();
+	msg_seq = 0;
+	err_str = "Unable to put attribute of mapinfo number nlmsg";
+	ret = ibnl_put_attr(skb, nlh, sizeof(u32), &msg_seq, IWPM_NLA_MAPINFO_SEQ);
+	if (ret)
+		goto mapinfo_num_error;
+	ret = ibnl_put_attr(skb, nlh, sizeof(u32),
+				&mapping_num, IWPM_NLA_MAPINFO_SEND_NUM);
+	if (ret)
+		goto mapinfo_num_error;
+	ret = ibnl_unicast(skb, nlh, iwpm_pid);
+	if (ret) {
+		skb = NULL;
+		err_str = "Unable to send a nlmsg";
+		goto mapinfo_num_error;
+	}
+	pr_debug("%s: Sent mapping number = %d\n", __func__, mapping_num);
+	return 0;
+mapinfo_num_error:
+	pr_info("%s: %s\n", __func__, err_str);
+	if (skb)
+		dev_kfree_skb(skb);
+	return ret;
+}
+
+static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid)
+{
+	struct nlmsghdr *nlh = NULL;
+	int ret = 0;
+
+	if (!skb)
+		return ret;
+	if (!(ibnl_put_msg(skb, &nlh, 0, 0, nl_client,
+			   RDMA_NL_IWPM_MAPINFO, NLM_F_MULTI))) {
+		pr_warn("%s Unable to put NLMSG_DONE\n", __func__);
+		return -ENOMEM;
+	}
+	nlh->nlmsg_type = NLMSG_DONE;
+	ret = ibnl_unicast(skb, (struct nlmsghdr *)skb->data, iwpm_pid);
+	if (ret)
+		pr_warn("%s Unable to send a nlmsg\n", __func__);
+	return ret;
+}
+
+int iwpm_send_mapinfo(u8 nl_client, int iwpm_pid)
+{
+	struct iwpm_mapping_info *map_info;
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	int skb_num = 0, mapping_num = 0;
+	int i = 0, nlmsg_bytes = 0;
+	unsigned long flags;
+	const char *err_str = "";
+	int ret;
+
+	skb = dev_alloc_skb(NLMSG_GOODSIZE);
+	if (!skb) {
+		ret = -ENOMEM;
+		err_str = "Unable to allocate skb";
+		goto send_mapping_info_exit;
+	}
+	skb_num++;
+	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
+	for (i = 0; i < IWPM_HASH_BUCKET_SIZE; i++) {
+		hlist_for_each_entry(map_info, &iwpm_hash_bucket[i],
+				     hlist_node) {
+			if (map_info->nl_client != nl_client)
+				continue;
+			nlh = NULL;
+			if (!(ibnl_put_msg(skb, &nlh, 0, 0, nl_client,
+					RDMA_NL_IWPM_MAPINFO, NLM_F_MULTI))) {
+				ret = -ENOMEM;
+				err_str = "Unable to put the nlmsg header";
+				goto send_mapping_info_unlock;
+			}
+			err_str = "Unable to put attribute of the nlmsg";
+			ret = ibnl_put_attr(skb, nlh,
+					sizeof(struct sockaddr_storage),
+					&map_info->local_sockaddr,
+					IWPM_NLA_MAPINFO_LOCAL_ADDR);
+			if (ret)
+				goto send_mapping_info_unlock;
+
+			ret = ibnl_put_attr(skb, nlh,
+					sizeof(struct sockaddr_storage),
+					&map_info->mapped_sockaddr,
+					IWPM_NLA_MAPINFO_MAPPED_ADDR);
+			if (ret)
+				goto send_mapping_info_unlock;
+
+			iwpm_print_sockaddr(&map_info->local_sockaddr,
+				"send_mapping_info: Local sockaddr:");
+			iwpm_print_sockaddr(&map_info->mapped_sockaddr,
+				"send_mapping_info: Mapped local sockaddr:");
+			mapping_num++;
+			nlmsg_bytes += nlh->nlmsg_len;
+
+			/* check if all mappings can fit in one skb */
+			if (NLMSG_GOODSIZE - nlmsg_bytes < nlh->nlmsg_len * 2) {
+				/* and leave room for NLMSG_DONE */
+				nlmsg_bytes = 0;
+				skb_num++;
+				spin_unlock_irqrestore(&iwpm_mapinfo_lock,
+						       flags);
+				/* send the skb */
+				ret = send_nlmsg_done(skb, nl_client, iwpm_pid);
+				skb = NULL;
+				if (ret) {
+					err_str = "Unable to send map info";
+					goto send_mapping_info_exit;
+				}
+				if (skb_num == IWPM_MAPINFO_SKB_COUNT) {
+					ret = -ENOMEM;
+					err_str = "Insufficient skbs for map info";
+					goto send_mapping_info_exit;
+				}
+				skb = dev_alloc_skb(NLMSG_GOODSIZE);
+				if (!skb) {
+					ret = -ENOMEM;
+					err_str = "Unable to allocate skb";
+					goto send_mapping_info_exit;
+				}
+				spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
+			}
+		}
+	}
+send_mapping_info_unlock:
+	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
+send_mapping_info_exit:
+	if (ret) {
+		pr_warn("%s: %s (ret = %d)\n", __func__, err_str, ret);
+		if (skb)
+			dev_kfree_skb(skb);
+		return ret;
+	}
+	send_nlmsg_done(skb, nl_client, iwpm_pid);
+	return send_mapinfo_num(mapping_num, nl_client, iwpm_pid);
+}
+
+int iwpm_mapinfo_available(void)
+{
+	unsigned long flags;
+	int full_bucket = 0, i = 0;
+
+	spin_lock_irqsave(&iwpm_mapinfo_lock, flags);
+	if (iwpm_hash_bucket) {
+		for (i = 0; i < IWPM_HASH_BUCKET_SIZE; i++) {
+			if (!hlist_empty(&iwpm_hash_bucket[i])) {
+				full_bucket = 1;
+				break;
+			}
+		}
+	}
+	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
+	return full_bucket;
+}
diff --git a/drivers/infiniband/core/iwpm_util.h b/drivers/infiniband/core/iwpm_util.h
new file mode 100644
index 00000000000..9777c869a14
--- /dev/null
+++ b/drivers/infiniband/core/iwpm_util.h
@@ -0,0 +1,238 @@
+/*
+ * Copyright (c) 2014 Intel Corporation. All rights reserved.
+ * Copyright (c) 2014 Chelsio, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *	  copyright notice, this list of conditions and the following
+ *	  disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *	  copyright notice, this list of conditions and the following
+ *	  disclaimer in the documentation and/or other materials
+ *	  provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef _IWPM_UTIL_H
+#define _IWPM_UTIL_H
+
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/spinlock.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/delay.h>
+#include <linux/workqueue.h>
+#include <linux/mutex.h>
+#include <linux/jhash.h>
+#include <linux/kref.h>
+#include <net/netlink.h>
+#include <linux/errno.h>
+#include <rdma/iw_portmap.h>
+#include <rdma/rdma_netlink.h>
+
+
+#define IWPM_NL_RETRANS		3
+#define IWPM_NL_TIMEOUT		(10*HZ)
+#define IWPM_MAPINFO_SKB_COUNT	20
+
+#define IWPM_PID_UNDEFINED     -1
+#define IWPM_PID_UNAVAILABLE   -2
+
+struct iwpm_nlmsg_request {
+	struct list_head    inprocess_list;
+	__u32               nlmsg_seq;
+	void                *req_buffer;
+	u8	            nl_client;
+	u8                  request_done;
+	u16                 err_code;
+	wait_queue_head_t   waitq;
+	struct kref         kref;
+};
+
+struct iwpm_mapping_info {
+	struct hlist_node hlist_node;
+	struct sockaddr_storage local_sockaddr;
+	struct sockaddr_storage mapped_sockaddr;
+	u8     nl_client;
+};
+
+struct iwpm_admin_data {
+	atomic_t refcount;
+	atomic_t nlmsg_seq;
+	int      client_list[RDMA_NL_NUM_CLIENTS];
+	int      reg_list[RDMA_NL_NUM_CLIENTS];
+};
+
+/**
+ * iwpm_get_nlmsg_request - Allocate and initialize netlink message request
+ * @nlmsg_seq: Sequence number of the netlink message
+ * @nl_client: The index of the netlink client
+ * @gfp: Indicates how the memory for the request should be allocated
+ *
+ * Returns the newly allocated netlink request object if successful,
+ * otherwise returns NULL
+ */
+struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
+						u8 nl_client, gfp_t gfp);
+
+/**
+ * iwpm_free_nlmsg_request - Deallocate netlink message request
+ * @kref: Holds reference of netlink message request
+ */
+void iwpm_free_nlmsg_request(struct kref *kref);
+
+/**
+ * iwpm_find_nlmsg_request - Find netlink message request in the request list
+ * @echo_seq: Sequence number of the netlink request to find
+ *
+ * Returns the found netlink message request,
+ * if not found, returns NULL
+ */
+struct iwpm_nlmsg_request *iwpm_find_nlmsg_request(__u32 echo_seq);
+
+/**
+ * iwpm_wait_complete_req - Block while servicing the netlink request
+ * @nlmsg_request: Netlink message request to service
+ *
+ * Wakes up, after the request is completed or expired
+ * Returns 0 if the request is complete without error
+ */
+int iwpm_wait_complete_req(struct iwpm_nlmsg_request *nlmsg_request);
+
+/**
+ * iwpm_get_nlmsg_seq - Get the sequence number for a netlink
+ *			message to send to the port mapper
+ *
+ * Returns the sequence number for the netlink message.
+ */
+int iwpm_get_nlmsg_seq(void);
+
+/**
+ * iwpm_valid_client - Check if the port mapper client is valid
+ * @nl_client: The index of the netlink client
+ *
+ * Valid clients need to call iwpm_init() before using
+ * the port mapper
+ */
+int iwpm_valid_client(u8 nl_client);
+
+/**
+ * iwpm_set_valid - Set the port mapper client to valid or not
+ * @nl_client: The index of the netlink client
+ * @valid: 1 if valid or 0 if invalid
+ */
+void iwpm_set_valid(u8 nl_client, int valid);
+
+/**
+ * iwpm_registered_client - Check if the port mapper client is registered
+ * @nl_client: The index of the netlink client
+ *
+ * Call iwpm_register_pid() to register a client
+ */
+int iwpm_registered_client(u8 nl_client);
+
+/**
+ * iwpm_set_registered - Set the port mapper client to registered or not
+ * @nl_client: The index of the netlink client
+ * @reg: 1 if registered or 0 if not
+ */
+void iwpm_set_registered(u8 nl_client, int reg);
+
+/**
+ * iwpm_send_mapinfo - Send local and mapped IPv4/IPv6 address info of
+ *                     a client to the user space port mapper
+ * @nl_client: The index of the netlink client
+ * @iwpm_pid: The pid of the user space port mapper
+ *
+ * If successful, returns the number of sent mapping info records
+ */
+int iwpm_send_mapinfo(u8 nl_client, int iwpm_pid);
+
+/**
+ * iwpm_mapinfo_available - Check if any mapping info records is available
+ *		            in the hash table
+ *
+ * Returns 1 if mapping information is available, otherwise returns 0
+ */
+int iwpm_mapinfo_available(void);
+
+/**
+ * iwpm_compare_sockaddr - Compare two sockaddr storage structs
+ *
+ * Returns 0 if they are holding the same ip/tcp address info,
+ * otherwise returns 1
+ */
+int iwpm_compare_sockaddr(struct sockaddr_storage *a_sockaddr,
+			struct sockaddr_storage *b_sockaddr);
+
+/**
+ * iwpm_validate_nlmsg_attr - Check for NULL netlink attributes
+ * @nltb: Holds address of each netlink message attributes
+ * @nla_count: Number of netlink message attributes
+ *
+ * Returns error if any of the nla_count attributes is NULL
+ */
+static inline int iwpm_validate_nlmsg_attr(struct nlattr *nltb[],
+					   int nla_count)
+{
+	int i;
+	for (i = 1; i < nla_count; i++) {
+		if (!nltb[i])
+			return -EINVAL;
+	}
+	return 0;
+}
+
+/**
+ * iwpm_create_nlmsg - Allocate skb and form a netlink message
+ * @nl_op: Netlink message opcode
+ * @nlh: Holds address of the netlink message header in skb
+ * @nl_client: The index of the netlink client
+ *
+ * Returns the newly allcated skb, or NULL if the tailroom of the skb
+ * is insufficient to store the message header and payload
+ */
+struct sk_buff *iwpm_create_nlmsg(u32 nl_op, struct nlmsghdr **nlh,
+					int nl_client);
+
+/**
+ * iwpm_parse_nlmsg - Validate and parse the received netlink message
+ * @cb: Netlink callback structure
+ * @policy_max: Maximum attribute type to be expected
+ * @nlmsg_policy: Validation policy
+ * @nltb: Array to store policy_max parsed elements
+ * @msg_type: Type of netlink message
+ *
+ * Returns 0 on success or a negative error code
+ */
+int iwpm_parse_nlmsg(struct netlink_callback *cb, int policy_max,
+				const struct nla_policy *nlmsg_policy,
+				struct nlattr *nltb[], const char *msg_type);
+
+/**
+ * iwpm_print_sockaddr - Print IPv4/IPv6 address and TCP port
+ * @sockaddr: Socket address to print
+ * @msg: Message to print
+ */
+void iwpm_print_sockaddr(struct sockaddr_storage *sockaddr, char *msg);
+#endif
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index a1e9cba8494..23dd5a5c759 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -103,13 +103,13 @@ int ibnl_remove_client(int index)
 EXPORT_SYMBOL(ibnl_remove_client);
 
 void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
-		   int len, int client, int op)
+		   int len, int client, int op, int flags)
 {
 	unsigned char *prev_tail;
 
 	prev_tail = skb_tail_pointer(skb);
 	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op),
-			 len, NLM_F_MULTI);
+			 len, flags);
 	if (!*nlh)
 		goto out_nlmsg_trim;
 	(*nlh)->nlmsg_len = skb_tail_pointer(skb) - prev_tail;
@@ -172,6 +172,20 @@ static void ibnl_rcv(struct sk_buff *skb)
 	mutex_unlock(&ibnl_mutex);
 }
 
+int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
+			__u32 pid)
+{
+	return nlmsg_unicast(nls, skb, pid);
+}
+EXPORT_SYMBOL(ibnl_unicast);
+
+int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
+			unsigned int group, gfp_t flags)
+{
+	return nlmsg_multicast(nls, skb, 0, group, flags);
+}
+EXPORT_SYMBOL(ibnl_multicast);
+
 int __init ibnl_init(void)
 {
 	struct netlink_kernel_cfg cfg = {
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index f820958e404..233eaf541f5 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -618,7 +618,7 @@ static void init_mad(struct ib_sa_mad *mad, struct ib_mad_agent *agent)
 
 static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
 {
-	bool preload = gfp_mask & __GFP_WAIT;
+	bool preload = !!(gfp_mask & __GFP_WAIT);
 	unsigned long flags;
 	int ret, id;
 
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 7d3292c7b4b..cbd0383f622 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -429,15 +429,19 @@ static void ib_port_release(struct kobject *kobj)
 	struct attribute *a;
 	int i;
 
-	for (i = 0; (a = p->gid_group.attrs[i]); ++i)
-		kfree(a);
+	if (p->gid_group.attrs) {
+		for (i = 0; (a = p->gid_group.attrs[i]); ++i)
+			kfree(a);
 
-	kfree(p->gid_group.attrs);
+		kfree(p->gid_group.attrs);
+	}
 
-	for (i = 0; (a = p->pkey_group.attrs[i]); ++i)
-		kfree(a);
+	if (p->pkey_group.attrs) {
+		for (i = 0; (a = p->pkey_group.attrs[i]); ++i)
+			kfree(a);
 
-	kfree(p->pkey_group.attrs);
+		kfree(p->pkey_group.attrs);
+	}
 
 	kfree(p);
 }
@@ -534,10 +538,12 @@ static int add_port(struct ib_device *device, int port_num,
 	p->port_num   = port_num;
 
 	ret = kobject_init_and_add(&p->kobj, &port_type,
-				   kobject_get(device->ports_parent),
+				   device->ports_parent,
 				   "%d", port_num);
-	if (ret)
-		goto err_put;
+	if (ret) {
+		kfree(p);
+		return ret;
+	}
 
 	ret = sysfs_create_group(&p->kobj, &pma_group);
 	if (ret)
@@ -585,6 +591,7 @@ err_free_pkey:
 		kfree(p->pkey_group.attrs[i]);
 
 	kfree(p->pkey_group.attrs);
+	p->pkey_group.attrs = NULL;
 
 err_remove_gid:
 	sysfs_remove_group(&p->kobj, &p->gid_group);
@@ -594,13 +601,13 @@ err_free_gid:
 		kfree(p->gid_group.attrs[i]);
 
 	kfree(p->gid_group.attrs);
+	p->gid_group.attrs = NULL;
 
 err_remove_pma:
 	sysfs_remove_group(&p->kobj, &pma_group);
 
 err_put:
-	kobject_put(device->ports_parent);
-	kfree(p);
+	kobject_put(&p->kobj);
 	return ret;
 }
 
@@ -809,6 +816,22 @@ static struct attribute_group iw_stats_group = {
 	.attrs	= iw_proto_stats_attrs,
 };
 
+static void free_port_list_attributes(struct ib_device *device)
+{
+	struct kobject *p, *t;
+
+	list_for_each_entry_safe(p, t, &device->port_list, entry) {
+		struct ib_port *port = container_of(p, struct ib_port, kobj);
+		list_del(&p->entry);
+		sysfs_remove_group(p, &pma_group);
+		sysfs_remove_group(p, &port->pkey_group);
+		sysfs_remove_group(p, &port->gid_group);
+		kobject_put(p);
+	}
+
+	kobject_put(device->ports_parent);
+}
+
 int ib_device_register_sysfs(struct ib_device *device,
 			     int (*port_callback)(struct ib_device *,
 						  u8, struct kobject *))
@@ -835,7 +858,7 @@ int ib_device_register_sysfs(struct ib_device *device,
 	}
 
 	device->ports_parent = kobject_create_and_add("ports",
-					kobject_get(&class_dev->kobj));
+						      &class_dev->kobj);
 	if (!device->ports_parent) {
 		ret = -ENOMEM;
 		goto err_put;
@@ -862,21 +885,7 @@ int ib_device_register_sysfs(struct ib_device *device,
 	return 0;
 
 err_put:
-	{
-		struct kobject *p, *t;
-		struct ib_port *port;
-
-		list_for_each_entry_safe(p, t, &device->port_list, entry) {
-			list_del(&p->entry);
-			port = container_of(p, struct ib_port, kobj);
-			sysfs_remove_group(p, &pma_group);
-			sysfs_remove_group(p, &port->pkey_group);
-			sysfs_remove_group(p, &port->gid_group);
-			kobject_put(p);
-		}
-	}
-
-	kobject_put(&class_dev->kobj);
+	free_port_list_attributes(device);
 
 err_unregister:
 	device_unregister(class_dev);
@@ -887,22 +896,18 @@ err:
 
 void ib_device_unregister_sysfs(struct ib_device *device)
 {
-	struct kobject *p, *t;
-	struct ib_port *port;
-
 	/* Hold kobject until ib_dealloc_device() */
-	kobject_get(&device->dev.kobj);
+	struct kobject *kobj_dev = kobject_get(&device->dev.kobj);
+	int i;
 
-	list_for_each_entry_safe(p, t, &device->port_list, entry) {
-		list_del(&p->entry);
-		port = container_of(p, struct ib_port, kobj);
-		sysfs_remove_group(p, &pma_group);
-		sysfs_remove_group(p, &port->pkey_group);
-		sysfs_remove_group(p, &port->gid_group);
-		kobject_put(p);
-	}
+	if (device->node_type == RDMA_NODE_RNIC && device->get_protocol_stats)
+		sysfs_remove_group(kobj_dev, &iw_stats_group);
+
+	free_port_list_attributes(device);
+
+	for (i = 0; i < ARRAY_SIZE(ib_class_attributes); ++i)
+		device_remove_file(&device->dev, ib_class_attributes[i]);
 
-	kobject_put(device->ports_parent);
 	device_unregister(&device->dev);
 }
 
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index f0d588f8859..1acb9910055 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -98,7 +98,7 @@ struct ib_umad_port {
 
 struct ib_umad_device {
 	int                  start_port, end_port;
-	struct kref          ref;
+	struct kobject       kobj;
 	struct ib_umad_port  port[0];
 };
 
@@ -134,14 +134,18 @@ static DECLARE_BITMAP(dev_map, IB_UMAD_MAX_PORTS);
 static void ib_umad_add_one(struct ib_device *device);
 static void ib_umad_remove_one(struct ib_device *device);
 
-static void ib_umad_release_dev(struct kref *ref)
+static void ib_umad_release_dev(struct kobject *kobj)
 {
 	struct ib_umad_device *dev =
-		container_of(ref, struct ib_umad_device, ref);
+		container_of(kobj, struct ib_umad_device, kobj);
 
 	kfree(dev);
 }
 
+static struct kobj_type ib_umad_dev_ktype = {
+	.release = ib_umad_release_dev,
+};
+
 static int hdr_size(struct ib_umad_file *file)
 {
 	return file->use_pkey_index ? sizeof (struct ib_user_mad_hdr) :
@@ -780,27 +784,19 @@ static int ib_umad_open(struct inode *inode, struct file *filp)
 {
 	struct ib_umad_port *port;
 	struct ib_umad_file *file;
-	int ret;
+	int ret = -ENXIO;
 
 	port = container_of(inode->i_cdev, struct ib_umad_port, cdev);
-	if (port)
-		kref_get(&port->umad_dev->ref);
-	else
-		return -ENXIO;
 
 	mutex_lock(&port->file_mutex);
 
-	if (!port->ib_dev) {
-		ret = -ENXIO;
+	if (!port->ib_dev)
 		goto out;
-	}
 
+	ret = -ENOMEM;
 	file = kzalloc(sizeof *file, GFP_KERNEL);
-	if (!file) {
-		kref_put(&port->umad_dev->ref, ib_umad_release_dev);
-		ret = -ENOMEM;
+	if (!file)
 		goto out;
-	}
 
 	mutex_init(&file->mutex);
 	spin_lock_init(&file->send_lock);
@@ -814,6 +810,13 @@ static int ib_umad_open(struct inode *inode, struct file *filp)
 	list_add_tail(&file->port_list, &port->file_list);
 
 	ret = nonseekable_open(inode, filp);
+	if (ret) {
+		list_del(&file->port_list);
+		kfree(file);
+		goto out;
+	}
+
+	kobject_get(&port->umad_dev->kobj);
 
 out:
 	mutex_unlock(&port->file_mutex);
@@ -852,7 +855,7 @@ static int ib_umad_close(struct inode *inode, struct file *filp)
 	mutex_unlock(&file->port->file_mutex);
 
 	kfree(file);
-	kref_put(&dev->ref, ib_umad_release_dev);
+	kobject_put(&dev->kobj);
 
 	return 0;
 }
@@ -880,10 +883,6 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
 	int ret;
 
 	port = container_of(inode->i_cdev, struct ib_umad_port, sm_cdev);
-	if (port)
-		kref_get(&port->umad_dev->ref);
-	else
-		return -ENXIO;
 
 	if (filp->f_flags & O_NONBLOCK) {
 		if (down_trylock(&port->sm_sem)) {
@@ -898,17 +897,27 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp)
 	}
 
 	ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props);
-	if (ret) {
-		up(&port->sm_sem);
-		goto fail;
-	}
+	if (ret)
+		goto err_up_sem;
 
 	filp->private_data = port;
 
-	return nonseekable_open(inode, filp);
+	ret = nonseekable_open(inode, filp);
+	if (ret)
+		goto err_clr_sm_cap;
+
+	kobject_get(&port->umad_dev->kobj);
+
+	return 0;
+
+err_clr_sm_cap:
+	swap(props.set_port_cap_mask, props.clr_port_cap_mask);
+	ib_modify_port(port->ib_dev, port->port_num, 0, &props);
+
+err_up_sem:
+	up(&port->sm_sem);
 
 fail:
-	kref_put(&port->umad_dev->ref, ib_umad_release_dev);
 	return ret;
 }
 
@@ -927,7 +936,7 @@ static int ib_umad_sm_close(struct inode *inode, struct file *filp)
 
 	up(&port->sm_sem);
 
-	kref_put(&port->umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&port->umad_dev->kobj);
 
 	return ret;
 }
@@ -995,6 +1004,7 @@ static int find_overflow_devnum(void)
 }
 
 static int ib_umad_init_port(struct ib_device *device, int port_num,
+			     struct ib_umad_device *umad_dev,
 			     struct ib_umad_port *port)
 {
 	int devnum;
@@ -1027,6 +1037,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 
 	cdev_init(&port->cdev, &umad_fops);
 	port->cdev.owner = THIS_MODULE;
+	port->cdev.kobj.parent = &umad_dev->kobj;
 	kobject_set_name(&port->cdev.kobj, "umad%d", port->dev_num);
 	if (cdev_add(&port->cdev, base, 1))
 		goto err_cdev;
@@ -1045,6 +1056,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 	base += IB_UMAD_MAX_PORTS;
 	cdev_init(&port->sm_cdev, &umad_sm_fops);
 	port->sm_cdev.owner = THIS_MODULE;
+	port->sm_cdev.kobj.parent = &umad_dev->kobj;
 	kobject_set_name(&port->sm_cdev.kobj, "issm%d", port->dev_num);
 	if (cdev_add(&port->sm_cdev, base, 1))
 		goto err_sm_cdev;
@@ -1138,7 +1150,7 @@ static void ib_umad_add_one(struct ib_device *device)
 	if (!umad_dev)
 		return;
 
-	kref_init(&umad_dev->ref);
+	kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype);
 
 	umad_dev->start_port = s;
 	umad_dev->end_port   = e;
@@ -1146,7 +1158,8 @@ static void ib_umad_add_one(struct ib_device *device)
 	for (i = s; i <= e; ++i) {
 		umad_dev->port[i - s].umad_dev = umad_dev;
 
-		if (ib_umad_init_port(device, i, &umad_dev->port[i - s]))
+		if (ib_umad_init_port(device, i, umad_dev,
+				      &umad_dev->port[i - s]))
 			goto err;
 	}
 
@@ -1158,7 +1171,7 @@ err:
 	while (--i >= s)
 		ib_umad_kill_port(&umad_dev->port[i - s]);
 
-	kref_put(&umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&umad_dev->kobj);
 }
 
 static void ib_umad_remove_one(struct ib_device *device)
@@ -1172,7 +1185,7 @@ static void ib_umad_remove_one(struct ib_device *device)
 	for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i)
 		ib_umad_kill_port(&umad_dev->port[i]);
 
-	kref_put(&umad_dev->ref, ib_umad_release_dev);
+	kobject_put(&umad_dev->kobj);
 }
 
 static char *umad_devnode(struct device *dev, umode_t *mode)
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 92525f855d8..c2b89cc5dbc 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -48,7 +48,7 @@
 
 #include "core_priv.h"
 
-int ib_rate_to_mult(enum ib_rate rate)
+__attribute_const__ int ib_rate_to_mult(enum ib_rate rate)
 {
 	switch (rate) {
 	case IB_RATE_2_5_GBPS: return  1;
@@ -65,7 +65,7 @@ int ib_rate_to_mult(enum ib_rate rate)
 }
 EXPORT_SYMBOL(ib_rate_to_mult);
 
-enum ib_rate mult_to_ib_rate(int mult)
+__attribute_const__ enum ib_rate mult_to_ib_rate(int mult)
 {
 	switch (mult) {
 	case 1:  return IB_RATE_2_5_GBPS;
@@ -82,7 +82,7 @@ enum ib_rate mult_to_ib_rate(int mult)
 }
 EXPORT_SYMBOL(mult_to_ib_rate);
 
-int ib_rate_to_mbps(enum ib_rate rate)
+__attribute_const__ int ib_rate_to_mbps(enum ib_rate rate)
 {
 	switch (rate) {
 	case IB_RATE_2_5_GBPS: return 2500;
@@ -107,7 +107,7 @@ int ib_rate_to_mbps(enum ib_rate rate)
 }
 EXPORT_SYMBOL(ib_rate_to_mbps);
 
-enum rdma_transport_type
+__attribute_const__ enum rdma_transport_type
 rdma_node_get_transport(enum rdma_node_type node_type)
 {
 	switch (node_type) {
diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile
new file mode 100644
index 00000000000..e900b03531a
--- /dev/null
+++ b/drivers/infiniband/hw/Makefile
@@ -0,0 +1,12 @@
+obj-$(CONFIG_INFINIBAND_MTHCA)		+= mthca/
+obj-$(CONFIG_INFINIBAND_IPATH)		+= ipath/
+obj-$(CONFIG_INFINIBAND_QIB)		+= qib/
+obj-$(CONFIG_INFINIBAND_EHCA)		+= ehca/
+obj-$(CONFIG_INFINIBAND_AMSO1100)	+= amso1100/
+obj-$(CONFIG_INFINIBAND_CXGB3)		+= cxgb3/
+obj-$(CONFIG_INFINIBAND_CXGB4)		+= cxgb4/
+obj-$(CONFIG_MLX4_INFINIBAND)		+= mlx4/
+obj-$(CONFIG_MLX5_INFINIBAND)		+= mlx5/
+obj-$(CONFIG_INFINIBAND_NES)		+= nes/
+obj-$(CONFIG_INFINIBAND_OCRDMA)		+= ocrdma/
+obj-$(CONFIG_INFINIBAND_USNIC)		+= usnic/
diff --git a/drivers/infiniband/hw/cxgb3/cxio_hal.c b/drivers/infiniband/hw/cxgb3/cxio_hal.c
index c3f5aca4ef0..de1c61b417d 100644
--- a/drivers/infiniband/hw/cxgb3/cxio_hal.c
+++ b/drivers/infiniband/hw/cxgb3/cxio_hal.c
@@ -735,14 +735,12 @@ static int __cxio_tpt_op(struct cxio_rdev *rdev_p, u32 reset_tpt_entry,
 			((perm & TPT_MW_BIND) ? F_TPT_MW_BIND_ENABLE : 0) |
 			V_TPT_ADDR_TYPE((zbva ? TPT_ZBTO : TPT_VATO)) |
 			V_TPT_PAGE_SIZE(page_size));
-		tpt.rsvd_pbl_addr = reset_tpt_entry ? 0 :
-				    cpu_to_be32(V_TPT_PBL_ADDR(PBL_OFF(rdev_p, pbl_addr)>>3));
+		tpt.rsvd_pbl_addr = cpu_to_be32(V_TPT_PBL_ADDR(PBL_OFF(rdev_p, pbl_addr)>>3));
 		tpt.len = cpu_to_be32(len);
 		tpt.va_hi = cpu_to_be32((u32) (to >> 32));
 		tpt.va_low_or_fbo = cpu_to_be32((u32) (to & 0xFFFFFFFFULL));
 		tpt.rsvd_bind_cnt_or_pstag = 0;
-		tpt.rsvd_pbl_size = reset_tpt_entry ? 0 :
-				  cpu_to_be32(V_TPT_PBL_SIZE(pbl_size >> 2));
+		tpt.rsvd_pbl_size = cpu_to_be32(V_TPT_PBL_SIZE(pbl_size >> 2));
 	}
 	err = cxio_hal_ctrl_qp_write_mem(rdev_p,
 				       stag_idx +
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index 095bb046e2c..cb78b1e9bcd 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -418,6 +418,7 @@ static int send_abort(struct iwch_ep *ep, struct sk_buff *skb, gfp_t gfp)
 	skb->priority = CPL_PRIORITY_DATA;
 	set_arp_failure_handler(skb, abort_arp_failure);
 	req = (struct cpl_abort_req *) skb_put(skb, sizeof(*req));
+	memset(req, 0, sizeof(*req));
 	req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_HOST_ABORT_CON_REQ));
 	req->wr.wr_lo = htonl(V_WR_TID(ep->hwtid));
 	OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ABORT_REQ, ep->hwtid));
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 1f863a96a48..768a0fb67dd 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2009-2010 Chelsio, Inc. All rights reserved.
+ * Copyright (c) 2009-2014 Chelsio, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -47,6 +47,8 @@
 #include <net/ip6_route.h>
 #include <net/addrconf.h>
 
+#include <rdma/ib_addr.h>
+
 #include "iw_cxgb4.h"
 
 static char *states[] = {
@@ -232,12 +234,16 @@ static void release_tid(struct c4iw_rdev *rdev, u32 hwtid, struct sk_buff *skb)
 
 static void set_emss(struct c4iw_ep *ep, u16 opt)
 {
-	ep->emss = ep->com.dev->rdev.lldi.mtus[GET_TCPOPT_MSS(opt)] - 40;
+	ep->emss = ep->com.dev->rdev.lldi.mtus[GET_TCPOPT_MSS(opt)] -
+		   sizeof(struct iphdr) - sizeof(struct tcphdr);
 	ep->mss = ep->emss;
 	if (GET_TCPOPT_TSTAMP(opt))
 		ep->emss -= 12;
 	if (ep->emss < 128)
 		ep->emss = 128;
+	if (ep->emss & 7)
+		PDBG("Warning: misaligned mtu idx %u mss %u emss=%u\n",
+		     GET_TCPOPT_MSS(opt), ep->mss, ep->emss);
 	PDBG("%s mss_idx %u mss %u emss=%u\n", __func__, GET_TCPOPT_MSS(opt),
 	     ep->mss, ep->emss);
 }
@@ -294,6 +300,12 @@ void _c4iw_free_ep(struct kref *kref)
 		dst_release(ep->dst);
 		cxgb4_l2t_release(ep->l2t);
 	}
+	if (test_bit(RELEASE_MAPINFO, &ep->com.flags)) {
+		print_addr(&ep->com, __func__, "remove_mapinfo/mapping");
+		iwpm_remove_mapinfo(&ep->com.local_addr,
+				    &ep->com.mapped_local_addr);
+		iwpm_remove_mapping(&ep->com.local_addr, RDMA_NL_C4IW);
+	}
 	kfree(ep);
 }
 
@@ -341,10 +353,7 @@ static struct sk_buff *get_skb(struct sk_buff *skb, int len, gfp_t gfp)
 
 static struct net_device *get_real_dev(struct net_device *egress_dev)
 {
-	struct net_device *phys_dev = egress_dev;
-	if (egress_dev->priv_flags & IFF_802_1Q_VLAN)
-		phys_dev = vlan_dev_real_dev(egress_dev);
-	return phys_dev;
+	return rdma_vlan_dev_real_dev(egress_dev) ? : egress_dev;
 }
 
 static int our_interface(struct c4iw_dev *dev, struct net_device *egress_dev)
@@ -423,8 +432,17 @@ static void arp_failure_discard(void *handle, struct sk_buff *skb)
  */
 static void act_open_req_arp_failure(void *handle, struct sk_buff *skb)
 {
+	struct c4iw_ep *ep = handle;
+
 	printk(KERN_ERR MOD "ARP failure duing connect\n");
 	kfree_skb(skb);
+	connect_reply_upcall(ep, -EHOSTUNREACH);
+	state_set(&ep->com, DEAD);
+	remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
+	cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
+	dst_release(ep->dst);
+	cxgb4_l2t_release(ep->l2t);
+	c4iw_put_ep(&ep->com);
 }
 
 /*
@@ -468,7 +486,7 @@ static void send_flowc(struct c4iw_ep *ep, struct sk_buff *skb)
 	flowc->mnemval[5].mnemonic = FW_FLOWC_MNEM_RCVNXT;
 	flowc->mnemval[5].val = cpu_to_be32(ep->rcv_seq);
 	flowc->mnemval[6].mnemonic = FW_FLOWC_MNEM_SNDBUF;
-	flowc->mnemval[6].val = cpu_to_be32(snd_win);
+	flowc->mnemval[6].val = cpu_to_be32(ep->snd_win);
 	flowc->mnemval[7].mnemonic = FW_FLOWC_MNEM_MSS;
 	flowc->mnemval[7].val = cpu_to_be32(ep->emss);
 	/* Pad WR to 16 byte boundary */
@@ -528,6 +546,49 @@ static int send_abort(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp)
 	return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
 }
 
+/*
+ * c4iw_form_pm_msg - Form a port mapper message with mapping info
+ */
+static void c4iw_form_pm_msg(struct c4iw_ep *ep,
+				struct iwpm_sa_data *pm_msg)
+{
+	memcpy(&pm_msg->loc_addr, &ep->com.local_addr,
+		sizeof(ep->com.local_addr));
+	memcpy(&pm_msg->rem_addr, &ep->com.remote_addr,
+		sizeof(ep->com.remote_addr));
+}
+
+/*
+ * c4iw_form_reg_msg - Form a port mapper message with dev info
+ */
+static void c4iw_form_reg_msg(struct c4iw_dev *dev,
+				struct iwpm_dev_data *pm_msg)
+{
+	memcpy(pm_msg->dev_name, dev->ibdev.name, IWPM_DEVNAME_SIZE);
+	memcpy(pm_msg->if_name, dev->rdev.lldi.ports[0]->name,
+				IWPM_IFNAME_SIZE);
+}
+
+static void c4iw_record_pm_msg(struct c4iw_ep *ep,
+			struct iwpm_sa_data *pm_msg)
+{
+	memcpy(&ep->com.mapped_local_addr, &pm_msg->mapped_loc_addr,
+		sizeof(ep->com.mapped_local_addr));
+	memcpy(&ep->com.mapped_remote_addr, &pm_msg->mapped_rem_addr,
+		sizeof(ep->com.mapped_remote_addr));
+}
+
+static void best_mtu(const unsigned short *mtus, unsigned short mtu,
+		     unsigned int *idx, int use_ts)
+{
+	unsigned short hdr_size = sizeof(struct iphdr) +
+				  sizeof(struct tcphdr) +
+				  (use_ts ? 12 : 0);
+	unsigned short data_size = mtu - hdr_size;
+
+	cxgb4_best_aligned_mtu(mtus, hdr_size, data_size, 8, idx);
+}
+
 static int send_connect(struct c4iw_ep *ep)
 {
 	struct cpl_act_open_req *req;
@@ -546,10 +607,15 @@ static int send_connect(struct c4iw_ep *ep)
 	int sizev6 = is_t4(ep->com.dev->rdev.lldi.adapter_type) ?
 				sizeof(struct cpl_act_open_req6) :
 				sizeof(struct cpl_t5_act_open_req6);
-	struct sockaddr_in *la = (struct sockaddr_in *)&ep->com.local_addr;
-	struct sockaddr_in *ra = (struct sockaddr_in *)&ep->com.remote_addr;
-	struct sockaddr_in6 *la6 = (struct sockaddr_in6 *)&ep->com.local_addr;
-	struct sockaddr_in6 *ra6 = (struct sockaddr_in6 *)&ep->com.remote_addr;
+	struct sockaddr_in *la = (struct sockaddr_in *)
+				 &ep->com.mapped_local_addr;
+	struct sockaddr_in *ra = (struct sockaddr_in *)
+				 &ep->com.mapped_remote_addr;
+	struct sockaddr_in6 *la6 = (struct sockaddr_in6 *)
+				   &ep->com.mapped_local_addr;
+	struct sockaddr_in6 *ra6 = (struct sockaddr_in6 *)
+				   &ep->com.mapped_remote_addr;
+	int win;
 
 	wrlen = (ep->com.remote_addr.ss_family == AF_INET) ?
 			roundup(sizev4, 16) :
@@ -565,8 +631,18 @@ static int send_connect(struct c4iw_ep *ep)
 	}
 	set_wr_txq(skb, CPL_PRIORITY_SETUP, ep->ctrlq_idx);
 
-	cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
+	best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
+		 enable_tcp_timestamps);
 	wscale = compute_wscale(rcv_win);
+
+	/*
+	 * Specify the largest window that will fit in opt0. The
+	 * remainder will be specified in the rx_data_ack.
+	 */
+	win = ep->rcv_win >> 10;
+	if (win > RCV_BUFSIZ_MASK)
+		win = RCV_BUFSIZ_MASK;
+
 	opt0 = (nocong ? NO_CONG(1) : 0) |
 	       KEEP_ALIVE(1) |
 	       DELACK(1) |
@@ -577,7 +653,7 @@ static int send_connect(struct c4iw_ep *ep)
 	       SMAC_SEL(ep->smac_idx) |
 	       DSCP(ep->tos) |
 	       ULP_MODE(ULP_MODE_TCPDDP) |
-	       RCV_BUFSIZ(rcv_win>>10);
+	       RCV_BUFSIZ(win);
 	opt2 = RX_CHANNEL(0) |
 	       CCTRL_ECN(enable_ecn) |
 	       RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid);
@@ -591,7 +667,7 @@ static int send_connect(struct c4iw_ep *ep)
 		opt2 |= T5_OPT_2_VALID;
 		opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE);
 	}
-	t4_set_arp_err_handler(skb, NULL, act_open_req_arp_failure);
+	t4_set_arp_err_handler(skb, ep, act_open_req_arp_failure);
 
 	if (is_t4(ep->com.dev->rdev.lldi.adapter_type)) {
 		if (ep->com.remote_addr.ss_family == AF_INET) {
@@ -633,6 +709,13 @@ static int send_connect(struct c4iw_ep *ep)
 			req6->opt2 = cpu_to_be32(opt2);
 		}
 	} else {
+		u32 isn = (prandom_u32() & ~7UL) - 1;
+
+		opt2 |= T5_OPT_2_VALID;
+		opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+		if (peer2peer)
+			isn += 4;
+
 		if (ep->com.remote_addr.ss_family == AF_INET) {
 			t5_req = (struct cpl_t5_act_open_req *)
 				 skb_put(skb, wrlen);
@@ -649,6 +732,9 @@ static int send_connect(struct c4iw_ep *ep)
 						     cxgb4_select_ntuple(
 					     ep->com.dev->rdev.lldi.ports[0],
 					     ep->l2t)));
+			t5_req->rsvd = cpu_to_be32(isn);
+			PDBG("%s snd_isn %u\n", __func__,
+			     be32_to_cpu(t5_req->rsvd));
 			t5_req->opt2 = cpu_to_be32(opt2);
 		} else {
 			t5_req6 = (struct cpl_t5_act_open_req6 *)
@@ -672,6 +758,9 @@ static int send_connect(struct c4iw_ep *ep)
 							cxgb4_select_ntuple(
 						ep->com.dev->rdev.lldi.ports[0],
 						ep->l2t));
+			t5_req6->rsvd = cpu_to_be32(isn);
+			PDBG("%s snd_isn %u\n", __func__,
+			     be32_to_cpu(t5_req6->rsvd));
 			t5_req6->opt2 = cpu_to_be32(opt2);
 		}
 	}
@@ -1145,6 +1234,14 @@ static int update_rx_credits(struct c4iw_ep *ep, u32 credits)
 		return 0;
 	}
 
+	/*
+	 * If we couldn't specify the entire rcv window at connection setup
+	 * due to the limit in the number of bits in the RCV_BUFSIZ field,
+	 * then add the overage in to the credits returned.
+	 */
+	if (ep->rcv_win > RCV_BUFSIZ_MASK * 1024)
+		credits += ep->rcv_win - RCV_BUFSIZ_MASK * 1024;
+
 	req = (struct cpl_rx_data_ack *) skb_put(skb, wrlen);
 	memset(req, 0, wrlen);
 	INIT_TP_WR(req, ep->hwtid);
@@ -1618,6 +1715,7 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
 	unsigned int mtu_idx;
 	int wscale;
 	struct sockaddr_in *sin;
+	int win;
 
 	skb = get_skb(NULL, sizeof(*req), GFP_KERNEL);
 	req = (struct fw_ofld_connection_wr *)__skb_put(skb, sizeof(*req));
@@ -1627,10 +1725,10 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
 	req->le.filter = cpu_to_be32(cxgb4_select_ntuple(
 				     ep->com.dev->rdev.lldi.ports[0],
 				     ep->l2t));
-	sin = (struct sockaddr_in *)&ep->com.local_addr;
+	sin = (struct sockaddr_in *)&ep->com.mapped_local_addr;
 	req->le.lport = sin->sin_port;
 	req->le.u.ipv4.lip = sin->sin_addr.s_addr;
-	sin = (struct sockaddr_in *)&ep->com.remote_addr;
+	sin = (struct sockaddr_in *)&ep->com.mapped_remote_addr;
 	req->le.pport = sin->sin_port;
 	req->le.u.ipv4.pip = sin->sin_addr.s_addr;
 	req->tcb.t_state_to_astid =
@@ -1640,8 +1738,18 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
 			htons(F_FW_OFLD_CONNECTION_WR_CPLRXDATAACK);
 	req->tcb.tx_max = (__force __be32) jiffies;
 	req->tcb.rcv_adv = htons(1);
-	cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
+	best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
+		 enable_tcp_timestamps);
 	wscale = compute_wscale(rcv_win);
+
+	/*
+	 * Specify the largest window that will fit in opt0. The
+	 * remainder will be specified in the rx_data_ack.
+	 */
+	win = ep->rcv_win >> 10;
+	if (win > RCV_BUFSIZ_MASK)
+		win = RCV_BUFSIZ_MASK;
+
 	req->tcb.opt0 = (__force __be64) (TCAM_BYPASS(1) |
 		(nocong ? NO_CONG(1) : 0) |
 		KEEP_ALIVE(1) |
@@ -1653,7 +1761,7 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
 		SMAC_SEL(ep->smac_idx) |
 		DSCP(ep->tos) |
 		ULP_MODE(ULP_MODE_TCPDDP) |
-		RCV_BUFSIZ(rcv_win >> 10));
+		RCV_BUFSIZ(win));
 	req->tcb.opt2 = (__force __be32) (PACE(1) |
 		TX_QUEUE(ep->com.dev->rdev.lldi.tx_modq[ep->tx_chan]) |
 		RX_CHANNEL(0) |
@@ -1690,6 +1798,13 @@ static int is_neg_adv(unsigned int status)
 	       status == CPL_ERR_KEEPALV_NEG_ADVICE;
 }
 
+static void set_tcp_window(struct c4iw_ep *ep, struct port_info *pi)
+{
+	ep->snd_win = snd_win;
+	ep->rcv_win = rcv_win;
+	PDBG("%s snd_win %d rcv_win %d\n", __func__, ep->snd_win, ep->rcv_win);
+}
+
 #define ACT_OPEN_RETRY_COUNT 2
 
 static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
@@ -1738,6 +1853,7 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
 		ep->ctrlq_idx = cxgb4_port_idx(pdev);
 		ep->rss_qid = cdev->rdev.lldi.rxq_ids[
 			cxgb4_port_idx(pdev) * step];
+		set_tcp_window(ep, (struct port_info *)netdev_priv(pdev));
 		dev_put(pdev);
 	} else {
 		pdev = get_real_dev(n->dev);
@@ -1746,16 +1862,17 @@ static int import_ep(struct c4iw_ep *ep, int iptype, __u8 *peer_ip,
 		if (!ep->l2t)
 			goto out;
 		ep->mtu = dst_mtu(dst);
-		ep->tx_chan = cxgb4_port_chan(n->dev);
-		ep->smac_idx = (cxgb4_port_viid(n->dev) & 0x7F) << 1;
+		ep->tx_chan = cxgb4_port_chan(pdev);
+		ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
 		step = cdev->rdev.lldi.ntxq /
 			cdev->rdev.lldi.nchan;
-		ep->txq_idx = cxgb4_port_idx(n->dev) * step;
-		ep->ctrlq_idx = cxgb4_port_idx(n->dev);
+		ep->txq_idx = cxgb4_port_idx(pdev) * step;
+		ep->ctrlq_idx = cxgb4_port_idx(pdev);
 		step = cdev->rdev.lldi.nrxq /
 			cdev->rdev.lldi.nchan;
 		ep->rss_qid = cdev->rdev.lldi.rxq_ids[
-			cxgb4_port_idx(n->dev) * step];
+			cxgb4_port_idx(pdev) * step];
+		set_tcp_window(ep, (struct port_info *)netdev_priv(pdev));
 
 		if (clear_mpa_v1) {
 			ep->retry_with_mpa_v1 = 0;
@@ -1870,10 +1987,10 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct sockaddr_in6 *ra6;
 
 	ep = lookup_atid(t, atid);
-	la = (struct sockaddr_in *)&ep->com.local_addr;
-	ra = (struct sockaddr_in *)&ep->com.remote_addr;
-	la6 = (struct sockaddr_in6 *)&ep->com.local_addr;
-	ra6 = (struct sockaddr_in6 *)&ep->com.remote_addr;
+	la = (struct sockaddr_in *)&ep->com.mapped_local_addr;
+	ra = (struct sockaddr_in *)&ep->com.mapped_remote_addr;
+	la6 = (struct sockaddr_in6 *)&ep->com.mapped_local_addr;
+	ra6 = (struct sockaddr_in6 *)&ep->com.mapped_remote_addr;
 
 	PDBG("%s ep %p atid %u status %u errno %d\n", __func__, ep, atid,
 	     status, status2errno(status));
@@ -1986,13 +2103,36 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 	u64 opt0;
 	u32 opt2;
 	int wscale;
+	struct cpl_t5_pass_accept_rpl *rpl5 = NULL;
+	int win;
 
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
 	BUG_ON(skb_cloned(skb));
-	skb_trim(skb, sizeof(*rpl));
+
 	skb_get(skb);
-	cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
+	rpl = cplhdr(skb);
+	if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
+		skb_trim(skb, roundup(sizeof(*rpl5), 16));
+		rpl5 = (void *)rpl;
+		INIT_TP_WR(rpl5, ep->hwtid);
+	} else {
+		skb_trim(skb, sizeof(*rpl));
+		INIT_TP_WR(rpl, ep->hwtid);
+	}
+	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
+						    ep->hwtid));
+
+	best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
+		 enable_tcp_timestamps && req->tcpopt.tstamp);
 	wscale = compute_wscale(rcv_win);
+
+	/*
+	 * Specify the largest window that will fit in opt0. The
+	 * remainder will be specified in the rx_data_ack.
+	 */
+	win = ep->rcv_win >> 10;
+	if (win > RCV_BUFSIZ_MASK)
+		win = RCV_BUFSIZ_MASK;
 	opt0 = (nocong ? NO_CONG(1) : 0) |
 	       KEEP_ALIVE(1) |
 	       DELACK(1) |
@@ -2003,7 +2143,7 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 	       SMAC_SEL(ep->smac_idx) |
 	       DSCP(ep->tos >> 2) |
 	       ULP_MODE(ULP_MODE_TCPDDP) |
-	       RCV_BUFSIZ(rcv_win>>10);
+	       RCV_BUFSIZ(win);
 	opt2 = RX_CHANNEL(0) |
 	       RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid);
 
@@ -2023,14 +2163,18 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 			opt2 |= CCTRL_ECN(1);
 	}
 	if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
+		u32 isn = (prandom_u32() & ~7UL) - 1;
 		opt2 |= T5_OPT_2_VALID;
 		opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE);
+		opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+		rpl5 = (void *)rpl;
+		memset(&rpl5->iss, 0, roundup(sizeof(*rpl5)-sizeof(*rpl), 16));
+		if (peer2peer)
+			isn += 4;
+		rpl5->iss = cpu_to_be32(isn);
+		PDBG("%s iss %u\n", __func__, be32_to_cpu(rpl5->iss));
 	}
 
-	rpl = cplhdr(skb);
-	INIT_TP_WR(rpl, ep->hwtid);
-	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
-				      ep->hwtid));
 	rpl->opt0 = cpu_to_be64(opt0);
 	rpl->opt2 = cpu_to_be32(opt2);
 	set_wr_txq(skb, CPL_PRIORITY_SETUP, ep->ctrlq_idx);
@@ -2045,7 +2189,6 @@ static void reject_cr(struct c4iw_dev *dev, u32 hwtid, struct sk_buff *skb)
 	PDBG("%s c4iw_dev %p tid %u\n", __func__, dev, hwtid);
 	BUG_ON(skb_cloned(skb));
 	skb_trim(skb, sizeof(struct cpl_tid_release));
-	skb_get(skb);
 	release_tid(&dev->rdev, hwtid, skb);
 	return;
 }
@@ -2095,6 +2238,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 	int err;
 	u16 peer_mss = ntohs(req->tcpopt.mss);
 	int iptype;
+	unsigned short hdrs;
 
 	parent_ep = lookup_stid(t, stid);
 	if (!parent_ep) {
@@ -2152,8 +2296,10 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 		goto reject;
 	}
 
-	if (peer_mss && child_ep->mtu > (peer_mss + 40))
-		child_ep->mtu = peer_mss + 40;
+	hdrs = sizeof(struct iphdr) + sizeof(struct tcphdr) +
+	       ((enable_tcp_timestamps && req->tcpopt.tstamp) ? 12 : 0);
+	if (peer_mss && child_ep->mtu > (peer_mss + hdrs))
+		child_ep->mtu = peer_mss + hdrs;
 
 	state_set(&child_ep->com, CONNECTING);
 	child_ep->com.dev = dev;
@@ -2730,13 +2876,15 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	struct c4iw_dev *dev = to_c4iw_dev(cm_id->device);
 	struct c4iw_ep *ep;
 	int err = 0;
-	struct sockaddr_in *laddr = (struct sockaddr_in *)&cm_id->local_addr;
-	struct sockaddr_in *raddr = (struct sockaddr_in *)&cm_id->remote_addr;
-	struct sockaddr_in6 *laddr6 = (struct sockaddr_in6 *)&cm_id->local_addr;
-	struct sockaddr_in6 *raddr6 = (struct sockaddr_in6 *)
-				      &cm_id->remote_addr;
+	struct sockaddr_in *laddr;
+	struct sockaddr_in *raddr;
+	struct sockaddr_in6 *laddr6;
+	struct sockaddr_in6 *raddr6;
+	struct iwpm_dev_data pm_reg_msg;
+	struct iwpm_sa_data pm_msg;
 	__u8 *ra;
 	int iptype;
+	int iwpm_err = 0;
 
 	if ((conn_param->ord > c4iw_max_read_depth) ||
 	    (conn_param->ird > c4iw_max_read_depth)) {
@@ -2767,7 +2915,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	if (!ep->com.qp) {
 		PDBG("%s qpn 0x%x not found!\n", __func__, conn_param->qpn);
 		err = -EINVAL;
-		goto fail2;
+		goto fail1;
 	}
 	ref_qp(ep);
 	PDBG("%s qpn 0x%x qp %p cm_id %p\n", __func__, conn_param->qpn,
@@ -2780,10 +2928,50 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	if (ep->atid == -1) {
 		printk(KERN_ERR MOD "%s - cannot alloc atid.\n", __func__);
 		err = -ENOMEM;
-		goto fail2;
+		goto fail1;
 	}
 	insert_handle(dev, &dev->atid_idr, ep, ep->atid);
 
+	memcpy(&ep->com.local_addr, &cm_id->local_addr,
+	       sizeof(ep->com.local_addr));
+	memcpy(&ep->com.remote_addr, &cm_id->remote_addr,
+	       sizeof(ep->com.remote_addr));
+
+	/* No port mapper available, go with the specified peer information */
+	memcpy(&ep->com.mapped_local_addr, &cm_id->local_addr,
+	       sizeof(ep->com.mapped_local_addr));
+	memcpy(&ep->com.mapped_remote_addr, &cm_id->remote_addr,
+	       sizeof(ep->com.mapped_remote_addr));
+
+	c4iw_form_reg_msg(dev, &pm_reg_msg);
+	iwpm_err = iwpm_register_pid(&pm_reg_msg, RDMA_NL_C4IW);
+	if (iwpm_err) {
+		PDBG("%s: Port Mapper reg pid fail (err = %d).\n",
+			__func__, iwpm_err);
+	}
+	if (iwpm_valid_pid() && !iwpm_err) {
+		c4iw_form_pm_msg(ep, &pm_msg);
+		iwpm_err = iwpm_add_and_query_mapping(&pm_msg, RDMA_NL_C4IW);
+		if (iwpm_err)
+			PDBG("%s: Port Mapper query fail (err = %d).\n",
+				__func__, iwpm_err);
+		else
+			c4iw_record_pm_msg(ep, &pm_msg);
+	}
+	if (iwpm_create_mapinfo(&ep->com.local_addr,
+				&ep->com.mapped_local_addr, RDMA_NL_C4IW)) {
+		iwpm_remove_mapping(&ep->com.local_addr, RDMA_NL_C4IW);
+		err = -ENOMEM;
+		goto fail1;
+	}
+	print_addr(&ep->com, __func__, "add_query/create_mapinfo");
+	set_bit(RELEASE_MAPINFO, &ep->com.flags);
+
+	laddr = (struct sockaddr_in *)&ep->com.mapped_local_addr;
+	raddr = (struct sockaddr_in *)&ep->com.mapped_remote_addr;
+	laddr6 = (struct sockaddr_in6 *)&ep->com.mapped_local_addr;
+	raddr6 = (struct sockaddr_in6 *) &ep->com.mapped_remote_addr;
+
 	if (cm_id->remote_addr.ss_family == AF_INET) {
 		iptype = 4;
 		ra = (__u8 *)&raddr->sin_addr;
@@ -2794,7 +2982,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		if ((__force int)raddr->sin_addr.s_addr == INADDR_ANY) {
 			err = pick_local_ipaddrs(dev, cm_id);
 			if (err)
-				goto fail2;
+				goto fail1;
 		}
 
 		/* find a route */
@@ -2814,7 +3002,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		if (ipv6_addr_type(&raddr6->sin6_addr) == IPV6_ADDR_ANY) {
 			err = pick_local_ip6addrs(dev, cm_id);
 			if (err)
-				goto fail2;
+				goto fail1;
 		}
 
 		/* find a route */
@@ -2830,13 +3018,13 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	if (!ep->dst) {
 		printk(KERN_ERR MOD "%s - cannot find route.\n", __func__);
 		err = -EHOSTUNREACH;
-		goto fail3;
+		goto fail2;
 	}
 
 	err = import_ep(ep, iptype, ra, ep->dst, ep->com.dev, true);
 	if (err) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
-		goto fail4;
+		goto fail3;
 	}
 
 	PDBG("%s txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n",
@@ -2845,10 +3033,6 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 
 	state_set(&ep->com, CONNECTING);
 	ep->tos = 0;
-	memcpy(&ep->com.local_addr, &cm_id->local_addr,
-	       sizeof(ep->com.local_addr));
-	memcpy(&ep->com.remote_addr, &cm_id->remote_addr,
-	       sizeof(ep->com.remote_addr));
 
 	/* send connect request to rnic */
 	err = send_connect(ep);
@@ -2856,12 +3040,12 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		goto out;
 
 	cxgb4_l2t_release(ep->l2t);
-fail4:
-	dst_release(ep->dst);
 fail3:
+	dst_release(ep->dst);
+fail2:
 	remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
 	cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
-fail2:
+fail1:
 	cm_id->rem_ref(cm_id);
 	c4iw_put_ep(&ep->com);
 out:
@@ -2871,7 +3055,8 @@ out:
 static int create_server6(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
 {
 	int err;
-	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&ep->com.local_addr;
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
+				    &ep->com.mapped_local_addr;
 
 	c4iw_init_wr_wait(&ep->com.wr_wait);
 	err = cxgb4_create_server6(ep->com.dev->rdev.lldi.ports[0],
@@ -2892,7 +3077,8 @@ static int create_server6(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
 static int create_server4(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
 {
 	int err;
-	struct sockaddr_in *sin = (struct sockaddr_in *)&ep->com.local_addr;
+	struct sockaddr_in *sin = (struct sockaddr_in *)
+				  &ep->com.mapped_local_addr;
 
 	if (dev->rdev.lldi.enable_fw_ofld_conn) {
 		do {
@@ -2927,6 +3113,9 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 	int err = 0;
 	struct c4iw_dev *dev = to_c4iw_dev(cm_id->device);
 	struct c4iw_listen_ep *ep;
+	struct iwpm_dev_data pm_reg_msg;
+	struct iwpm_sa_data pm_msg;
+	int iwpm_err = 0;
 
 	might_sleep();
 
@@ -2961,6 +3150,37 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 		goto fail2;
 	}
 	insert_handle(dev, &dev->stid_idr, ep, ep->stid);
+
+	/* No port mapper available, go with the specified info */
+	memcpy(&ep->com.mapped_local_addr, &cm_id->local_addr,
+	       sizeof(ep->com.mapped_local_addr));
+
+	c4iw_form_reg_msg(dev, &pm_reg_msg);
+	iwpm_err = iwpm_register_pid(&pm_reg_msg, RDMA_NL_C4IW);
+	if (iwpm_err) {
+		PDBG("%s: Port Mapper reg pid fail (err = %d).\n",
+			__func__, iwpm_err);
+	}
+	if (iwpm_valid_pid() && !iwpm_err) {
+		memcpy(&pm_msg.loc_addr, &ep->com.local_addr,
+				sizeof(ep->com.local_addr));
+		iwpm_err = iwpm_add_mapping(&pm_msg, RDMA_NL_C4IW);
+		if (iwpm_err)
+			PDBG("%s: Port Mapper query fail (err = %d).\n",
+				__func__, iwpm_err);
+		else
+			memcpy(&ep->com.mapped_local_addr,
+				&pm_msg.mapped_loc_addr,
+				sizeof(ep->com.mapped_local_addr));
+	}
+	if (iwpm_create_mapinfo(&ep->com.local_addr,
+				&ep->com.mapped_local_addr, RDMA_NL_C4IW)) {
+		err = -ENOMEM;
+		goto fail3;
+	}
+	print_addr(&ep->com, __func__, "add_mapping/create_mapinfo");
+
+	set_bit(RELEASE_MAPINFO, &ep->com.flags);
 	state_set(&ep->com, LISTEN);
 	if (ep->com.local_addr.ss_family == AF_INET)
 		err = create_server4(dev, ep);
@@ -2970,6 +3190,8 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 		cm_id->provider_data = ep;
 		goto out;
 	}
+
+fail3:
 	cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid,
 			ep->com.local_addr.ss_family);
 fail2:
@@ -3703,7 +3925,7 @@ int __init c4iw_cm_init(void)
 	return 0;
 }
 
-void __exit c4iw_cm_term(void)
+void c4iw_cm_term(void)
 {
 	WARN_ON(!list_empty(&timeout_list));
 	flush_workqueue(workq);
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index cfaa56ada18..c04292c950f 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -134,7 +134,8 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 			V_FW_RI_RES_WR_IQANUS(0) |
 			V_FW_RI_RES_WR_IQANUD(1) |
 			F_FW_RI_RES_WR_IQANDST |
-			V_FW_RI_RES_WR_IQANDSTINDEX(*rdev->lldi.rxq_ids));
+			V_FW_RI_RES_WR_IQANDSTINDEX(
+				rdev->lldi.ciq_ids[cq->vector]));
 	res->u.cq.iqdroprss_to_iqesize = cpu_to_be16(
 			F_FW_RI_RES_WR_IQDROPRSS |
 			V_FW_RI_RES_WR_IQPCIECH(2) |
@@ -870,6 +871,9 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 
 	rhp = to_c4iw_dev(ibdev);
 
+	if (vector >= rhp->rdev.lldi.nciq)
+		return ERR_PTR(-EINVAL);
+
 	chp = kzalloc(sizeof(*chp), GFP_KERNEL);
 	if (!chp)
 		return ERR_PTR(-ENOMEM);
@@ -915,6 +919,7 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 	}
 	chp->cq.size = hwentries;
 	chp->cq.memsize = memsize;
+	chp->cq.vector = vector;
 
 	ret = create_cq(&rhp->rdev, &chp->cq,
 			ucontext ? &ucontext->uctx : &rhp->rdev.uctx);
@@ -940,7 +945,6 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 		if (!mm2)
 			goto err4;
 
-		memset(&uresp, 0, sizeof(uresp));
 		uresp.qid_mask = rhp->rdev.cqmask;
 		uresp.cqid = chp->cq.cqid;
 		uresp.size = chp->cq.size;
@@ -951,7 +955,8 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 		uresp.gts_key = ucontext->key;
 		ucontext->key += PAGE_SIZE;
 		spin_unlock(&ucontext->mmap_lock);
-		ret = ib_copy_to_udata(udata, &uresp, sizeof uresp);
+		ret = ib_copy_to_udata(udata, &uresp,
+				       sizeof(uresp) - sizeof(uresp.reserved));
 		if (ret)
 			goto err5;
 
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index f4fa50a609e..7db82b24302 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -77,6 +77,16 @@ struct c4iw_debugfs_data {
 	int pos;
 };
 
+/* registered cxgb4 netlink callbacks */
+static struct ibnl_client_cbs c4iw_nl_cb_table[] = {
+	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
+	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
+	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
+	[RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb},
+	[RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb},
+	[RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}
+};
+
 static int count_idrs(int id, void *p, void *data)
 {
 	int *countp = data;
@@ -113,35 +123,49 @@ static int dump_qp(int id, void *p, void *data)
 				&qp->ep->com.local_addr;
 			struct sockaddr_in *rsin = (struct sockaddr_in *)
 				&qp->ep->com.remote_addr;
+			struct sockaddr_in *mapped_lsin = (struct sockaddr_in *)
+				&qp->ep->com.mapped_local_addr;
+			struct sockaddr_in *mapped_rsin = (struct sockaddr_in *)
+				&qp->ep->com.mapped_remote_addr;
 
 			cc = snprintf(qpd->buf + qpd->pos, space,
 				      "rc qp sq id %u rq id %u state %u "
 				      "onchip %u ep tid %u state %u "
-				      "%pI4:%u->%pI4:%u\n",
+				      "%pI4:%u/%u->%pI4:%u/%u\n",
 				      qp->wq.sq.qid, qp->wq.rq.qid,
 				      (int)qp->attr.state,
 				      qp->wq.sq.flags & T4_SQ_ONCHIP,
 				      qp->ep->hwtid, (int)qp->ep->com.state,
 				      &lsin->sin_addr, ntohs(lsin->sin_port),
-				      &rsin->sin_addr, ntohs(rsin->sin_port));
+				      ntohs(mapped_lsin->sin_port),
+				      &rsin->sin_addr, ntohs(rsin->sin_port),
+				      ntohs(mapped_rsin->sin_port));
 		} else {
 			struct sockaddr_in6 *lsin6 = (struct sockaddr_in6 *)
 				&qp->ep->com.local_addr;
 			struct sockaddr_in6 *rsin6 = (struct sockaddr_in6 *)
 				&qp->ep->com.remote_addr;
+			struct sockaddr_in6 *mapped_lsin6 =
+				(struct sockaddr_in6 *)
+				&qp->ep->com.mapped_local_addr;
+			struct sockaddr_in6 *mapped_rsin6 =
+				(struct sockaddr_in6 *)
+				&qp->ep->com.mapped_remote_addr;
 
 			cc = snprintf(qpd->buf + qpd->pos, space,
 				      "rc qp sq id %u rq id %u state %u "
 				      "onchip %u ep tid %u state %u "
-				      "%pI6:%u->%pI6:%u\n",
+				      "%pI6:%u/%u->%pI6:%u/%u\n",
 				      qp->wq.sq.qid, qp->wq.rq.qid,
 				      (int)qp->attr.state,
 				      qp->wq.sq.flags & T4_SQ_ONCHIP,
 				      qp->ep->hwtid, (int)qp->ep->com.state,
 				      &lsin6->sin6_addr,
 				      ntohs(lsin6->sin6_port),
+				      ntohs(mapped_lsin6->sin6_port),
 				      &rsin6->sin6_addr,
-				      ntohs(rsin6->sin6_port));
+				      ntohs(rsin6->sin6_port),
+				      ntohs(mapped_rsin6->sin6_port));
 		}
 	} else
 		cc = snprintf(qpd->buf + qpd->pos, space,
@@ -386,31 +410,43 @@ static int dump_ep(int id, void *p, void *data)
 			&ep->com.local_addr;
 		struct sockaddr_in *rsin = (struct sockaddr_in *)
 			&ep->com.remote_addr;
+		struct sockaddr_in *mapped_lsin = (struct sockaddr_in *)
+			&ep->com.mapped_local_addr;
+		struct sockaddr_in *mapped_rsin = (struct sockaddr_in *)
+			&ep->com.mapped_remote_addr;
 
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p qp %p state %d flags 0x%lx "
 			      "history 0x%lx hwtid %d atid %d "
-			      "%pI4:%d <-> %pI4:%d\n",
+			      "%pI4:%d/%d <-> %pI4:%d/%d\n",
 			      ep, ep->com.cm_id, ep->com.qp,
 			      (int)ep->com.state, ep->com.flags,
 			      ep->com.history, ep->hwtid, ep->atid,
 			      &lsin->sin_addr, ntohs(lsin->sin_port),
-			      &rsin->sin_addr, ntohs(rsin->sin_port));
+			      ntohs(mapped_lsin->sin_port),
+			      &rsin->sin_addr, ntohs(rsin->sin_port),
+			      ntohs(mapped_rsin->sin_port));
 	} else {
 		struct sockaddr_in6 *lsin6 = (struct sockaddr_in6 *)
 			&ep->com.local_addr;
 		struct sockaddr_in6 *rsin6 = (struct sockaddr_in6 *)
 			&ep->com.remote_addr;
+		struct sockaddr_in6 *mapped_lsin6 = (struct sockaddr_in6 *)
+			&ep->com.mapped_local_addr;
+		struct sockaddr_in6 *mapped_rsin6 = (struct sockaddr_in6 *)
+			&ep->com.mapped_remote_addr;
 
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p qp %p state %d flags 0x%lx "
 			      "history 0x%lx hwtid %d atid %d "
-			      "%pI6:%d <-> %pI6:%d\n",
+			      "%pI6:%d/%d <-> %pI6:%d/%d\n",
 			      ep, ep->com.cm_id, ep->com.qp,
 			      (int)ep->com.state, ep->com.flags,
 			      ep->com.history, ep->hwtid, ep->atid,
 			      &lsin6->sin6_addr, ntohs(lsin6->sin6_port),
-			      &rsin6->sin6_addr, ntohs(rsin6->sin6_port));
+			      ntohs(mapped_lsin6->sin6_port),
+			      &rsin6->sin6_addr, ntohs(rsin6->sin6_port),
+			      ntohs(mapped_rsin6->sin6_port));
 	}
 	if (cc < space)
 		epd->pos += cc;
@@ -431,23 +467,29 @@ static int dump_listen_ep(int id, void *p, void *data)
 	if (ep->com.local_addr.ss_family == AF_INET) {
 		struct sockaddr_in *lsin = (struct sockaddr_in *)
 			&ep->com.local_addr;
+		struct sockaddr_in *mapped_lsin = (struct sockaddr_in *)
+			&ep->com.mapped_local_addr;
 
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p state %d flags 0x%lx stid %d "
-			      "backlog %d %pI4:%d\n",
+			      "backlog %d %pI4:%d/%d\n",
 			      ep, ep->com.cm_id, (int)ep->com.state,
 			      ep->com.flags, ep->stid, ep->backlog,
-			      &lsin->sin_addr, ntohs(lsin->sin_port));
+			      &lsin->sin_addr, ntohs(lsin->sin_port),
+			      ntohs(mapped_lsin->sin_port));
 	} else {
 		struct sockaddr_in6 *lsin6 = (struct sockaddr_in6 *)
 			&ep->com.local_addr;
+		struct sockaddr_in6 *mapped_lsin6 = (struct sockaddr_in6 *)
+			&ep->com.mapped_local_addr;
 
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p state %d flags 0x%lx stid %d "
-			      "backlog %d %pI6:%d\n",
+			      "backlog %d %pI6:%d/%d\n",
 			      ep, ep->com.cm_id, (int)ep->com.state,
 			      ep->com.flags, ep->stid, ep->backlog,
-			      &lsin6->sin6_addr, ntohs(lsin6->sin6_port));
+			      &lsin6->sin6_addr, ntohs(lsin6->sin6_port),
+			      ntohs(mapped_lsin6->sin6_port));
 	}
 	if (cc < space)
 		epd->pos += cc;
@@ -654,6 +696,7 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 		pr_err(MOD "error allocating status page\n");
 		goto err4;
 	}
+	rdev->status_page->db_off = 0;
 	return 0;
 err4:
 	c4iw_rqtpool_destroy(rdev);
@@ -736,6 +779,7 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
 			pci_resource_len(devp->rdev.lldi.pdev, 2));
 		if (!devp->rdev.bar2_kva) {
 			pr_err(MOD "Unable to ioremap BAR2\n");
+			ib_dealloc_device(&devp->ibdev);
 			return ERR_PTR(-EINVAL);
 		}
 	} else if (ocqp_supported(infop)) {
@@ -747,6 +791,7 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
 			devp->rdev.lldi.vr->ocq.size);
 		if (!devp->rdev.oc_mw_kva) {
 			pr_err(MOD "Unable to ioremap onchip mem\n");
+			ib_dealloc_device(&devp->ibdev);
 			return ERR_PTR(-EINVAL);
 		}
 	}
@@ -780,6 +825,8 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
 					c4iw_debugfs_root);
 		setup_debugfs(devp);
 	}
+
+
 	return devp;
 }
 
@@ -1274,6 +1321,20 @@ static int __init c4iw_init_module(void)
 		printk(KERN_WARNING MOD
 		       "could not create debugfs entry, continuing\n");
 
+	if (ibnl_add_client(RDMA_NL_C4IW, RDMA_NL_IWPM_NUM_OPS,
+			    c4iw_nl_cb_table))
+		pr_err("%s[%u]: Failed to add netlink callback\n"
+		       , __func__, __LINE__);
+
+	err = iwpm_init(RDMA_NL_C4IW);
+	if (err) {
+		pr_err("port mapper initialization failed with %d\n", err);
+		ibnl_remove_client(RDMA_NL_C4IW);
+		c4iw_cm_term();
+		debugfs_remove_recursive(c4iw_debugfs_root);
+		return err;
+	}
+
 	cxgb4_register_uld(CXGB4_ULD_RDMA, &c4iw_uld_info);
 
 	return 0;
@@ -1291,6 +1352,8 @@ static void __exit c4iw_exit_module(void)
 	}
 	mutex_unlock(&dev_mutex);
 	cxgb4_unregister_uld(CXGB4_ULD_RDMA);
+	iwpm_exit(RDMA_NL_C4IW);
+	ibnl_remove_client(RDMA_NL_C4IW);
 	c4iw_cm_term();
 	debugfs_remove_recursive(c4iw_debugfs_root);
 }
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 7474b490760..361fff7a074 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -52,6 +52,8 @@
 
 #include <rdma/ib_verbs.h>
 #include <rdma/iw_cm.h>
+#include <rdma/rdma_netlink.h>
+#include <rdma/iw_portmap.h>
 
 #include "cxgb4.h"
 #include "cxgb4_uld.h"
@@ -728,6 +730,7 @@ enum c4iw_ep_flags {
 	CLOSE_SENT		= 3,
 	TIMEOUT                 = 4,
 	QP_REFERENCED           = 5,
+	RELEASE_MAPINFO		= 6,
 };
 
 enum c4iw_ep_history {
@@ -764,6 +767,8 @@ struct c4iw_ep_common {
 	struct mutex mutex;
 	struct sockaddr_storage local_addr;
 	struct sockaddr_storage remote_addr;
+	struct sockaddr_storage mapped_local_addr;
+	struct sockaddr_storage mapped_remote_addr;
 	struct c4iw_wr_wait wr_wait;
 	unsigned long flags;
 	unsigned long history;
@@ -805,7 +810,48 @@ struct c4iw_ep {
 	u8 retry_with_mpa_v1;
 	u8 tried_with_mpa_v1;
 	unsigned int retry_count;
-};
+	int snd_win;
+	int rcv_win;
+};
+
+static inline void print_addr(struct c4iw_ep_common *epc, const char *func,
+			      const char *msg)
+{
+
+#define SINA(a) (&(((struct sockaddr_in *)(a))->sin_addr.s_addr))
+#define SINP(a) ntohs(((struct sockaddr_in *)(a))->sin_port)
+#define SIN6A(a) (&(((struct sockaddr_in6 *)(a))->sin6_addr))
+#define SIN6P(a) ntohs(((struct sockaddr_in6 *)(a))->sin6_port)
+
+	if (c4iw_debug) {
+		switch (epc->local_addr.ss_family) {
+		case AF_INET:
+			PDBG("%s %s %pI4:%u/%u <-> %pI4:%u/%u\n",
+			     func, msg, SINA(&epc->local_addr),
+			     SINP(&epc->local_addr),
+			     SINP(&epc->mapped_local_addr),
+			     SINA(&epc->remote_addr),
+			     SINP(&epc->remote_addr),
+			     SINP(&epc->mapped_remote_addr));
+			break;
+		case AF_INET6:
+			PDBG("%s %s %pI6:%u/%u <-> %pI6:%u/%u\n",
+			     func, msg, SIN6A(&epc->local_addr),
+			     SIN6P(&epc->local_addr),
+			     SIN6P(&epc->mapped_local_addr),
+			     SIN6A(&epc->remote_addr),
+			     SIN6P(&epc->remote_addr),
+			     SIN6P(&epc->mapped_remote_addr));
+			break;
+		default:
+			break;
+		}
+	}
+#undef SINA
+#undef SINP
+#undef SIN6A
+#undef SIN6P
+}
 
 static inline struct c4iw_ep *to_ep(struct iw_cm_id *cm_id)
 {
@@ -862,7 +908,7 @@ int c4iw_destroy_ctrl_qp(struct c4iw_rdev *rdev);
 int c4iw_register_device(struct c4iw_dev *dev);
 void c4iw_unregister_device(struct c4iw_dev *dev);
 int __init c4iw_cm_init(void);
-void __exit c4iw_cm_term(void);
+void c4iw_cm_term(void);
 void c4iw_release_dev_ucontext(struct c4iw_rdev *rdev,
 			       struct c4iw_dev_ucontext *uctx);
 void c4iw_init_dev_ucontext(struct c4iw_rdev *rdev,
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index a94a3e12c34..b1d305338de 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -122,7 +122,7 @@ static struct ib_ucontext *c4iw_alloc_ucontext(struct ib_device *ibdev,
 	INIT_LIST_HEAD(&context->mmaps);
 	spin_lock_init(&context->mmap_lock);
 
-	if (udata->outlen < sizeof(uresp)) {
+	if (udata->outlen < sizeof(uresp) - sizeof(uresp.reserved)) {
 		if (!warned++)
 			pr_err(MOD "Warning - downlevel libcxgb4 (non-fatal), device status page disabled.");
 		rhp->rdev.flags |= T4_STATUS_PAGE_DISABLED;
@@ -140,7 +140,8 @@ static struct ib_ucontext *c4iw_alloc_ucontext(struct ib_device *ibdev,
 		context->key += PAGE_SIZE;
 		spin_unlock(&context->mmap_lock);
 
-		ret = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
+		ret = ib_copy_to_udata(udata, &uresp,
+				       sizeof(uresp) - sizeof(uresp.reserved));
 		if (ret)
 			goto err_mm;
 
@@ -499,7 +500,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.node_type = RDMA_NODE_RNIC;
 	memcpy(dev->ibdev.node_desc, C4IW_NODE_DESC, sizeof(C4IW_NODE_DESC));
 	dev->ibdev.phys_port_cnt = dev->rdev.lldi.nports;
-	dev->ibdev.num_comp_vectors = 1;
+	dev->ibdev.num_comp_vectors =  dev->rdev.lldi.nciq;
 	dev->ibdev.dma_device = &(dev->rdev.lldi.pdev->dev);
 	dev->ibdev.query_device = c4iw_query_device;
 	dev->ibdev.query_port = c4iw_query_port;
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index 2178f319841..68b0a6bf4eb 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -542,6 +542,7 @@ struct t4_cq {
 	size_t memsize;
 	__be64 bits_type_ts;
 	u32 cqid;
+	int vector;
 	u16 size; /* including status page */
 	u16 cidx;
 	u16 sw_pidx;
diff --git a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
index 6121ca08fe5..91289a051af 100644
--- a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
+++ b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
@@ -848,6 +848,7 @@ enum {                     /* TCP congestion control algorithms */
 #define V_CONG_CNTRL(x) ((x) << S_CONG_CNTRL)
 #define G_CONG_CNTRL(x) (((x) >> S_CONG_CNTRL) & M_CONG_CNTRL)
 
+#define CONG_CNTRL_VALID   (1 << 18)
 #define T5_OPT_2_VALID       (1 << 31)
 
 #endif /* _T4FW_RI_API_H_ */
diff --git a/drivers/infiniband/hw/cxgb4/user.h b/drivers/infiniband/hw/cxgb4/user.h
index 11ccd276e5d..cbd0ce17072 100644
--- a/drivers/infiniband/hw/cxgb4/user.h
+++ b/drivers/infiniband/hw/cxgb4/user.h
@@ -48,6 +48,7 @@ struct c4iw_create_cq_resp {
 	__u32 cqid;
 	__u32 size;
 	__u32 qid_mask;
+	__u32 reserved; /* explicit padding (optional for i386) */
 };
 
 
@@ -74,5 +75,6 @@ struct c4iw_create_qp_resp {
 struct c4iw_alloc_ucontext_resp {
 	__u64 status_page_key;
 	__u32 status_page_size;
+	__u32 reserved; /* explicit padding (optional for i386) */
 };
 #endif
diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c
index e2f9a51f4a3..45802e97332 100644
--- a/drivers/infiniband/hw/ipath/ipath_diag.c
+++ b/drivers/infiniband/hw/ipath/ipath_diag.c
@@ -346,6 +346,10 @@ static ssize_t ipath_diagpkt_write(struct file *fp,
 			ret = -EFAULT;
 			goto bail;
 		}
+		dp.len = odp.len;
+		dp.unit = odp.unit;
+		dp.data = odp.data;
+		dp.pbc_wd = 0;
 	} else {
 		ret = -EINVAL;
 		goto bail;
diff --git a/drivers/infiniband/hw/ipath/ipath_intr.c b/drivers/infiniband/hw/ipath/ipath_intr.c
index 26dfbc8ee0f..01ba792791a 100644
--- a/drivers/infiniband/hw/ipath/ipath_intr.c
+++ b/drivers/infiniband/hw/ipath/ipath_intr.c
@@ -70,7 +70,7 @@ void ipath_disarm_senderrbufs(struct ipath_devdata *dd)
 	if (sbuf[0] || sbuf[1] || (piobcnt > 128 && (sbuf[2] || sbuf[3]))) {
 		int i;
 		if (ipath_debug & (__IPATH_PKTDBG|__IPATH_DBG) &&
-			dd->ipath_lastcancel > jiffies) {
+			time_after(dd->ipath_lastcancel, jiffies)) {
 			__IPATH_DBG_WHICH(__IPATH_PKTDBG|__IPATH_DBG,
 					  "SendbufErrs %lx %lx", sbuf[0],
 					  sbuf[1]);
@@ -755,7 +755,7 @@ static int handle_errors(struct ipath_devdata *dd, ipath_err_t errs)
 
 	/* likely due to cancel; so suppress message unless verbose */
 	if ((errs & (INFINIPATH_E_SPKTLEN | INFINIPATH_E_SPIOARMLAUNCH)) &&
-		dd->ipath_lastcancel > jiffies) {
+		time_after(dd->ipath_lastcancel, jiffies)) {
 		/* armlaunch takes precedence; it often causes both. */
 		ipath_cdbg(VERBOSE,
 			"Suppressed %s error (%llx) after sendbuf cancel\n",
diff --git a/drivers/infiniband/hw/ipath/ipath_sdma.c b/drivers/infiniband/hw/ipath/ipath_sdma.c
index 98ac18ec977..17a517766ad 100644
--- a/drivers/infiniband/hw/ipath/ipath_sdma.c
+++ b/drivers/infiniband/hw/ipath/ipath_sdma.c
@@ -247,7 +247,7 @@ static void sdma_abort_task(unsigned long opaque)
 
 	/* ipath_sdma_abort() is done, waiting for interrupt */
 	if (status == IPATH_SDMA_ABORT_DISARMED) {
-		if (jiffies < dd->ipath_sdma_abort_intr_timeout)
+		if (time_before(jiffies, dd->ipath_sdma_abort_intr_timeout))
 			goto resched_noprint;
 		/* give up, intr got lost somewhere */
 		ipath_dbg("give up waiting for SDMADISABLED intr\n");
@@ -341,7 +341,7 @@ resched:
 	 * JAG - this is bad to just have default be a loop without
 	 * state change
 	 */
-	if (jiffies > dd->ipath_sdma_abort_jiffies) {
+	if (time_after(jiffies, dd->ipath_sdma_abort_jiffies)) {
 		ipath_dbg("looping with status 0x%08lx\n",
 			  dd->ipath_sdma_status);
 		dd->ipath_sdma_abort_jiffies = jiffies + 5 * HZ;
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 170dca60804..2d8c3397774 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -73,7 +73,7 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 {
 	struct mlx4_ib_dev *ibdev = to_mdev(pd->device);
 	struct mlx4_dev *dev = ibdev->dev;
-	int is_mcast;
+	int is_mcast = 0;
 	struct in6_addr in6;
 	u16 vlan_tag;
 
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 5f640814cc8..1066eec854a 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -102,7 +102,7 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *
 	int err;
 
 	err = mlx4_buf_alloc(dev->dev, nent * dev->dev->caps.cqe_size,
-			     PAGE_SIZE * 2, &buf->buf);
+			     PAGE_SIZE * 2, &buf->buf, GFP_KERNEL);
 
 	if (err)
 		goto out;
@@ -113,7 +113,7 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *
 	if (err)
 		goto err_buf;
 
-	err = mlx4_buf_write_mtt(dev->dev, &buf->mtt, &buf->buf);
+	err = mlx4_buf_write_mtt(dev->dev, &buf->mtt, &buf->buf, GFP_KERNEL);
 	if (err)
 		goto err_mtt;
 
@@ -209,7 +209,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 
 		uar = &to_mucontext(context)->uar;
 	} else {
-		err = mlx4_db_alloc(dev->dev, &cq->db, 1);
+		err = mlx4_db_alloc(dev->dev, &cq->db, 1, GFP_KERNEL);
 		if (err)
 			goto err_cq;
 
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index fd36ec67263..287ad0564ac 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -478,10 +478,6 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 	if (!tun_ctx || tun_ctx->state != DEMUX_PV_STATE_ACTIVE)
 		return -EAGAIN;
 
-	/* QP0 forwarding only for Dom0 */
-	if (!dest_qpt && (mlx4_master_func_num(dev->dev) != slave))
-		return -EINVAL;
-
 	if (!dest_qpt)
 		tun_qp = &tun_ctx->qp[0];
 	else
@@ -667,6 +663,21 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
 	}
 	/* Class-specific handling */
 	switch (mad->mad_hdr.mgmt_class) {
+	case IB_MGMT_CLASS_SUBN_LID_ROUTED:
+	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
+		/* 255 indicates the dom0 */
+		if (slave != 255 && slave != mlx4_master_func_num(dev->dev)) {
+			if (!mlx4_vf_smi_enabled(dev->dev, slave, port))
+				return -EPERM;
+			/* for a VF. drop unsolicited MADs */
+			if (!(mad->mad_hdr.method & IB_MGMT_METHOD_RESP)) {
+				mlx4_ib_warn(ibdev, "demux QP0. rejecting unsolicited mad for slave %d class 0x%x, method 0x%x\n",
+					     slave, mad->mad_hdr.mgmt_class,
+					     mad->mad_hdr.method);
+				return -EINVAL;
+			}
+		}
+		break;
 	case IB_MGMT_CLASS_SUBN_ADM:
 		if (mlx4_ib_demux_sa_handler(ibdev, port, slave,
 					     (struct ib_sa_mad *) mad))
@@ -1165,10 +1176,6 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
 	if (!sqp_ctx || sqp_ctx->state != DEMUX_PV_STATE_ACTIVE)
 		return -EAGAIN;
 
-	/* QP0 forwarding only for Dom0 */
-	if (dest_qpt == IB_QPT_SMI && (mlx4_master_func_num(dev->dev) != slave))
-		return -EINVAL;
-
 	if (dest_qpt == IB_QPT_SMI) {
 		src_qpnum = 0;
 		sqp = &sqp_ctx->qp[0];
@@ -1285,11 +1292,6 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
 			     "belongs to another slave\n", wc->src_qp);
 		return;
 	}
-	if (slave != mlx4_master_func_num(dev->dev) && !(wc->src_qp & 0x2)) {
-		mlx4_ib_warn(ctx->ib_dev, "can't multiplex bad sqp:%d: "
-			     "non-master trying to send QP0 packets\n", wc->src_qp);
-		return;
-	}
 
 	/* Map transaction ID */
 	ib_dma_sync_single_for_cpu(ctx->ib_dev, tun_qp->ring[wr_ix].map,
@@ -1317,6 +1319,12 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
 
 	/* Class-specific handling */
 	switch (tunnel->mad.mad_hdr.mgmt_class) {
+	case IB_MGMT_CLASS_SUBN_LID_ROUTED:
+	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
+		if (slave != mlx4_master_func_num(dev->dev) &&
+		    !mlx4_vf_smi_enabled(dev->dev, slave, ctx->port))
+			return;
+		break;
 	case IB_MGMT_CLASS_SUBN_ADM:
 		if (mlx4_ib_multiplex_sa_handler(ctx->ib_dev, ctx->port, slave,
 			      (struct ib_sa_mad *) &tunnel->mad))
@@ -1749,9 +1757,9 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
 		return -EEXIST;
 
 	ctx->state = DEMUX_PV_STATE_STARTING;
-	/* have QP0 only on port owner, and only if link layer is IB */
-	if (ctx->slave == mlx4_master_func_num(to_mdev(ctx->ib_dev)->dev) &&
-	    rdma_port_get_link_layer(ibdev, ctx->port) == IB_LINK_LAYER_INFINIBAND)
+	/* have QP0 only if link layer is IB */
+	if (rdma_port_get_link_layer(ibdev, ctx->port) ==
+	    IB_LINK_LAYER_INFINIBAND)
 		ctx->has_smi = 1;
 
 	if (ctx->has_smi) {
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 199c7896f08..0f7027e7db1 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -545,12 +545,11 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
 	return 0;
 }
 
-static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
-			 u32 cap_mask)
+static int mlx4_ib_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
+			    u32 cap_mask)
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	int err;
-	u8 is_eth = dev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev->dev);
 	if (IS_ERR(mailbox))
@@ -564,8 +563,8 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
 		((__be32 *) mailbox->buf)[1] = cpu_to_be32(cap_mask);
 	}
 
-	err = mlx4_cmd(dev->dev, mailbox->dma, port, is_eth, MLX4_CMD_SET_PORT,
-		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+	err = mlx4_cmd(dev->dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT,
+		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
 
 	mlx4_free_cmd_mailbox(dev->dev, mailbox);
 	return err;
@@ -574,11 +573,20 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
 static int mlx4_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
 			       struct ib_port_modify *props)
 {
+	struct mlx4_ib_dev *mdev = to_mdev(ibdev);
+	u8 is_eth = mdev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
 	struct ib_port_attr attr;
 	u32 cap_mask;
 	int err;
 
-	mutex_lock(&to_mdev(ibdev)->cap_mask_mutex);
+	/* return OK if this is RoCE. CM calls ib_modify_port() regardless
+	 * of whether port link layer is ETH or IB. For ETH ports, qkey
+	 * violations and port capabilities are not meaningful.
+	 */
+	if (is_eth)
+		return 0;
+
+	mutex_lock(&mdev->cap_mask_mutex);
 
 	err = mlx4_ib_query_port(ibdev, port, &attr);
 	if (err)
@@ -587,9 +595,9 @@ static int mlx4_ib_modify_port(struct ib_device *ibdev, u8 port, int mask,
 	cap_mask = (attr.port_cap_flags | props->set_port_cap_mask) &
 		~props->clr_port_cap_mask;
 
-	err = mlx4_SET_PORT(to_mdev(ibdev), port,
-			    !!(mask & IB_PORT_RESET_QKEY_CNTR),
-			    cap_mask);
+	err = mlx4_ib_SET_PORT(mdev, port,
+			       !!(mask & IB_PORT_RESET_QKEY_CNTR),
+			       cap_mask);
 
 out:
 	mutex_unlock(&to_mdev(ibdev)->cap_mask_mutex);
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 66b0b7dbd9f..369da3ca5d6 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -156,6 +156,7 @@ enum mlx4_ib_qp_flags {
 	MLX4_IB_QP_LSO = IB_QP_CREATE_IPOIB_UD_LSO,
 	MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK = IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
 	MLX4_IB_QP_NETIF = IB_QP_CREATE_NETIF_QP,
+	MLX4_IB_QP_CREATE_USE_GFP_NOIO = IB_QP_CREATE_USE_GFP_NOIO,
 	MLX4_IB_SRIOV_TUNNEL_QP = 1 << 30,
 	MLX4_IB_SRIOV_SQP = 1 << 31,
 };
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index dc57482ae7a..67780452f0c 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -608,9 +608,20 @@ static int qp_has_rq(struct ib_qp_init_attr *attr)
 	return !attr->srq;
 }
 
+static int qp0_enabled_vf(struct mlx4_dev *dev, int qpn)
+{
+	int i;
+	for (i = 0; i < dev->caps.num_ports; i++) {
+		if (qpn == dev->caps.qp0_proxy[i])
+			return !!dev->caps.qp0_qkey[i];
+	}
+	return 0;
+}
+
 static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			    struct ib_qp_init_attr *init_attr,
-			    struct ib_udata *udata, int sqpn, struct mlx4_ib_qp **caller_qp)
+			    struct ib_udata *udata, int sqpn, struct mlx4_ib_qp **caller_qp,
+			    gfp_t gfp)
 {
 	int qpn;
 	int err;
@@ -625,10 +636,13 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		     !(init_attr->create_flags & MLX4_IB_SRIOV_SQP))) {
 			if (init_attr->qp_type == IB_QPT_GSI)
 				qp_type = MLX4_IB_QPT_PROXY_GSI;
-			else if (mlx4_is_master(dev->dev))
-				qp_type = MLX4_IB_QPT_PROXY_SMI_OWNER;
-			else
-				qp_type = MLX4_IB_QPT_PROXY_SMI;
+			else {
+				if (mlx4_is_master(dev->dev) ||
+				    qp0_enabled_vf(dev->dev, sqpn))
+					qp_type = MLX4_IB_QPT_PROXY_SMI_OWNER;
+				else
+					qp_type = MLX4_IB_QPT_PROXY_SMI;
+			}
 		}
 		qpn = sqpn;
 		/* add extra sg entry for tunneling */
@@ -643,7 +657,9 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			return -EINVAL;
 		if (tnl_init->proxy_qp_type == IB_QPT_GSI)
 			qp_type = MLX4_IB_QPT_TUN_GSI;
-		else if (tnl_init->slave == mlx4_master_func_num(dev->dev))
+		else if (tnl_init->slave == mlx4_master_func_num(dev->dev) ||
+			 mlx4_vf_smi_enabled(dev->dev, tnl_init->slave,
+					     tnl_init->port))
 			qp_type = MLX4_IB_QPT_TUN_SMI_OWNER;
 		else
 			qp_type = MLX4_IB_QPT_TUN_SMI;
@@ -658,14 +674,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		if (qp_type == MLX4_IB_QPT_SMI || qp_type == MLX4_IB_QPT_GSI ||
 		    (qp_type & (MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_SMI_OWNER |
 				MLX4_IB_QPT_PROXY_GSI | MLX4_IB_QPT_TUN_SMI_OWNER))) {
-			sqp = kzalloc(sizeof (struct mlx4_ib_sqp), GFP_KERNEL);
+			sqp = kzalloc(sizeof (struct mlx4_ib_sqp), gfp);
 			if (!sqp)
 				return -ENOMEM;
 			qp = &sqp->qp;
 			qp->pri.vid = 0xFFFF;
 			qp->alt.vid = 0xFFFF;
 		} else {
-			qp = kzalloc(sizeof (struct mlx4_ib_qp), GFP_KERNEL);
+			qp = kzalloc(sizeof (struct mlx4_ib_qp), gfp);
 			if (!qp)
 				return -ENOMEM;
 			qp->pri.vid = 0xFFFF;
@@ -748,14 +764,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			goto err;
 
 		if (qp_has_rq(init_attr)) {
-			err = mlx4_db_alloc(dev->dev, &qp->db, 0);
+			err = mlx4_db_alloc(dev->dev, &qp->db, 0, gfp);
 			if (err)
 				goto err;
 
 			*qp->db.db = 0;
 		}
 
-		if (mlx4_buf_alloc(dev->dev, qp->buf_size, PAGE_SIZE * 2, &qp->buf)) {
+		if (mlx4_buf_alloc(dev->dev, qp->buf_size, PAGE_SIZE * 2, &qp->buf, gfp)) {
 			err = -ENOMEM;
 			goto err_db;
 		}
@@ -765,13 +781,12 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		if (err)
 			goto err_buf;
 
-		err = mlx4_buf_write_mtt(dev->dev, &qp->mtt, &qp->buf);
+		err = mlx4_buf_write_mtt(dev->dev, &qp->mtt, &qp->buf, gfp);
 		if (err)
 			goto err_mtt;
 
-		qp->sq.wrid  = kmalloc(qp->sq.wqe_cnt * sizeof (u64), GFP_KERNEL);
-		qp->rq.wrid  = kmalloc(qp->rq.wqe_cnt * sizeof (u64), GFP_KERNEL);
-
+		qp->sq.wrid  = kmalloc(qp->sq.wqe_cnt * sizeof (u64), gfp);
+		qp->rq.wrid  = kmalloc(qp->rq.wqe_cnt * sizeof (u64), gfp);
 		if (!qp->sq.wrid || !qp->rq.wrid) {
 			err = -ENOMEM;
 			goto err_wrid;
@@ -801,7 +816,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			goto err_proxy;
 	}
 
-	err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp);
+	err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp, gfp);
 	if (err)
 		goto err_qpn;
 
@@ -1040,7 +1055,10 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
 	struct mlx4_ib_qp *qp = NULL;
 	int err;
 	u16 xrcdn = 0;
+	gfp_t gfp;
 
+	gfp = (init_attr->create_flags & MLX4_IB_QP_CREATE_USE_GFP_NOIO) ?
+		GFP_NOIO : GFP_KERNEL;
 	/*
 	 * We only support LSO, vendor flag1, and multicast loopback blocking,
 	 * and only for kernel UD QPs.
@@ -1049,7 +1067,8 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
 					MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK |
 					MLX4_IB_SRIOV_TUNNEL_QP |
 					MLX4_IB_SRIOV_SQP |
-					MLX4_IB_QP_NETIF))
+					MLX4_IB_QP_NETIF |
+					MLX4_IB_QP_CREATE_USE_GFP_NOIO))
 		return ERR_PTR(-EINVAL);
 
 	if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) {
@@ -1059,7 +1078,7 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
 
 	if (init_attr->create_flags &&
 	    (udata ||
-	     ((init_attr->create_flags & ~MLX4_IB_SRIOV_SQP) &&
+	     ((init_attr->create_flags & ~(MLX4_IB_SRIOV_SQP | MLX4_IB_QP_CREATE_USE_GFP_NOIO)) &&
 	      init_attr->qp_type != IB_QPT_UD) ||
 	     ((init_attr->create_flags & MLX4_IB_SRIOV_SQP) &&
 	      init_attr->qp_type > IB_QPT_GSI)))
@@ -1079,7 +1098,7 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
 	case IB_QPT_RC:
 	case IB_QPT_UC:
 	case IB_QPT_RAW_PACKET:
-		qp = kzalloc(sizeof *qp, GFP_KERNEL);
+		qp = kzalloc(sizeof *qp, gfp);
 		if (!qp)
 			return ERR_PTR(-ENOMEM);
 		qp->pri.vid = 0xFFFF;
@@ -1088,7 +1107,7 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
 	case IB_QPT_UD:
 	{
 		err = create_qp_common(to_mdev(pd->device), pd, init_attr,
-				       udata, 0, &qp);
+				       udata, 0, &qp, gfp);
 		if (err)
 			return ERR_PTR(err);
 
@@ -1106,7 +1125,7 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
 
 		err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata,
 				       get_sqp_num(to_mdev(pd->device), init_attr),
-				       &qp);
+				       &qp, gfp);
 		if (err)
 			return ERR_PTR(err);
 
@@ -1938,6 +1957,19 @@ out:
 	return err;
 }
 
+static int vf_get_qp0_qkey(struct mlx4_dev *dev, int qpn, u32 *qkey)
+{
+	int i;
+	for (i = 0; i < dev->caps.num_ports; i++) {
+		if (qpn == dev->caps.qp0_proxy[i] ||
+		    qpn == dev->caps.qp0_tunnel[i]) {
+			*qkey = dev->caps.qp0_qkey[i];
+			return 0;
+		}
+	}
+	return -EINVAL;
+}
+
 static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
 				  struct ib_send_wr *wr,
 				  void *wqe, unsigned *mlx_seg_len)
@@ -1995,8 +2027,13 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
 			cpu_to_be32(mdev->dev->caps.qp0_tunnel[sqp->qp.port - 1]);
 
 	sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1));
-	if (mlx4_get_parav_qkey(mdev->dev, sqp->qp.mqp.qpn, &qkey))
-		return -EINVAL;
+	if (mlx4_is_master(mdev->dev)) {
+		if (mlx4_get_parav_qkey(mdev->dev, sqp->qp.mqp.qpn, &qkey))
+			return -EINVAL;
+	} else {
+		if (vf_get_qp0_qkey(mdev->dev, sqp->qp.mqp.qpn, &qkey))
+			return -EINVAL;
+	}
 	sqp->ud_header.deth.qkey = cpu_to_be32(qkey);
 	sqp->ud_header.deth.source_qpn = cpu_to_be32(sqp->qp.mqp.qpn);
 
@@ -2378,7 +2415,8 @@ static void set_datagram_seg(struct mlx4_wqe_datagram_seg *dseg,
 
 static void set_tunnel_datagram_seg(struct mlx4_ib_dev *dev,
 				    struct mlx4_wqe_datagram_seg *dseg,
-				    struct ib_send_wr *wr, enum ib_qp_type qpt)
+				    struct ib_send_wr *wr,
+				    enum mlx4_ib_qp_type qpt)
 {
 	union mlx4_ext_av *av = &to_mah(wr->wr.ud.ah)->av;
 	struct mlx4_av sqp_av = {0};
@@ -2391,8 +2429,10 @@ static void set_tunnel_datagram_seg(struct mlx4_ib_dev *dev,
 			cpu_to_be32(0xf0000000);
 
 	memcpy(dseg->av, &sqp_av, sizeof (struct mlx4_av));
-	/* This function used only for sending on QP1 proxies */
-	dseg->dqpn = cpu_to_be32(dev->dev->caps.qp1_tunnel[port - 1]);
+	if (qpt == MLX4_IB_QPT_PROXY_GSI)
+		dseg->dqpn = cpu_to_be32(dev->dev->caps.qp1_tunnel[port - 1]);
+	else
+		dseg->dqpn = cpu_to_be32(dev->dev->caps.qp0_tunnel[port - 1]);
 	/* Use QKEY from the QP context, which is set by master */
 	dseg->qkey = cpu_to_be32(IB_QP_SET_QKEY);
 }
@@ -2687,11 +2727,6 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			break;
 
 		case MLX4_IB_QPT_PROXY_SMI_OWNER:
-			if (unlikely(!mlx4_is_master(to_mdev(ibqp->device)->dev))) {
-				err = -ENOSYS;
-				*bad_wr = wr;
-				goto out;
-			}
 			err = build_sriov_qp0_header(to_msqp(qp), wr, ctrl, &seglen);
 			if (unlikely(err)) {
 				*bad_wr = wr;
@@ -2708,16 +2743,13 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			size += seglen / 16;
 			break;
 		case MLX4_IB_QPT_PROXY_SMI:
-			/* don't allow QP0 sends on guests */
-			err = -ENOSYS;
-			*bad_wr = wr;
-			goto out;
 		case MLX4_IB_QPT_PROXY_GSI:
 			/* If we are tunneling special qps, this is a UD qp.
 			 * In this case we first add a UD segment targeting
 			 * the tunnel qp, and then add a header with address
 			 * information */
-			set_tunnel_datagram_seg(to_mdev(ibqp->device), wqe, wr, ibqp->qp_type);
+			set_tunnel_datagram_seg(to_mdev(ibqp->device), wqe, wr,
+						qp->mlx4_ib_qp_type);
 			wqe  += sizeof (struct mlx4_wqe_datagram_seg);
 			size += sizeof (struct mlx4_wqe_datagram_seg) / 16;
 			build_tunnel_header(wr, wqe, &seglen);
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index 60c5fb025fc..62d9285300a 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -134,13 +134,14 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 		if (err)
 			goto err_mtt;
 	} else {
-		err = mlx4_db_alloc(dev->dev, &srq->db, 0);
+		err = mlx4_db_alloc(dev->dev, &srq->db, 0, GFP_KERNEL);
 		if (err)
 			goto err_srq;
 
 		*srq->db.db = 0;
 
-		if (mlx4_buf_alloc(dev->dev, buf_size, PAGE_SIZE * 2, &srq->buf)) {
+		if (mlx4_buf_alloc(dev->dev, buf_size, PAGE_SIZE * 2, &srq->buf,
+				   GFP_KERNEL)) {
 			err = -ENOMEM;
 			goto err_db;
 		}
@@ -165,7 +166,7 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 		if (err)
 			goto err_buf;
 
-		err = mlx4_buf_write_mtt(dev->dev, &srq->mtt, &srq->buf);
+		err = mlx4_buf_write_mtt(dev->dev, &srq->mtt, &srq->buf, GFP_KERNEL);
 		if (err)
 			goto err_mtt;
 
diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c
index 5a38e43eca6..cb4c66e723b 100644
--- a/drivers/infiniband/hw/mlx4/sysfs.c
+++ b/drivers/infiniband/hw/mlx4/sysfs.c
@@ -389,8 +389,10 @@ struct mlx4_port {
 	struct mlx4_ib_dev    *dev;
 	struct attribute_group pkey_group;
 	struct attribute_group gid_group;
-	u8                     port_num;
+	struct device_attribute	enable_smi_admin;
+	struct device_attribute	smi_enabled;
 	int		       slave;
+	u8                     port_num;
 };
 
 
@@ -558,6 +560,101 @@ err:
 	return NULL;
 }
 
+static ssize_t sysfs_show_smi_enabled(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct mlx4_port *p =
+		container_of(attr, struct mlx4_port, smi_enabled);
+	ssize_t len = 0;
+
+	if (mlx4_vf_smi_enabled(p->dev->dev, p->slave, p->port_num))
+		len = sprintf(buf, "%d\n", 1);
+	else
+		len = sprintf(buf, "%d\n", 0);
+
+	return len;
+}
+
+static ssize_t sysfs_show_enable_smi_admin(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct mlx4_port *p =
+		container_of(attr, struct mlx4_port, enable_smi_admin);
+	ssize_t len = 0;
+
+	if (mlx4_vf_get_enable_smi_admin(p->dev->dev, p->slave, p->port_num))
+		len = sprintf(buf, "%d\n", 1);
+	else
+		len = sprintf(buf, "%d\n", 0);
+
+	return len;
+}
+
+static ssize_t sysfs_store_enable_smi_admin(struct device *dev,
+					    struct device_attribute *attr,
+					    const char *buf, size_t count)
+{
+	struct mlx4_port *p =
+		container_of(attr, struct mlx4_port, enable_smi_admin);
+	int enable;
+
+	if (sscanf(buf, "%i", &enable) != 1 ||
+	    enable < 0 || enable > 1)
+		return -EINVAL;
+
+	if (mlx4_vf_set_enable_smi_admin(p->dev->dev, p->slave, p->port_num, enable))
+		return -EINVAL;
+	return count;
+}
+
+static int add_vf_smi_entries(struct mlx4_port *p)
+{
+	int is_eth = rdma_port_get_link_layer(&p->dev->ib_dev, p->port_num) ==
+			IB_LINK_LAYER_ETHERNET;
+	int ret;
+
+	/* do not display entries if eth transport, or if master */
+	if (is_eth || p->slave == mlx4_master_func_num(p->dev->dev))
+		return 0;
+
+	sysfs_attr_init(&p->smi_enabled.attr);
+	p->smi_enabled.show = sysfs_show_smi_enabled;
+	p->smi_enabled.store = NULL;
+	p->smi_enabled.attr.name = "smi_enabled";
+	p->smi_enabled.attr.mode = 0444;
+	ret = sysfs_create_file(&p->kobj, &p->smi_enabled.attr);
+	if (ret) {
+		pr_err("failed to create smi_enabled\n");
+		return ret;
+	}
+
+	sysfs_attr_init(&p->enable_smi_admin.attr);
+	p->enable_smi_admin.show = sysfs_show_enable_smi_admin;
+	p->enable_smi_admin.store = sysfs_store_enable_smi_admin;
+	p->enable_smi_admin.attr.name = "enable_smi_admin";
+	p->enable_smi_admin.attr.mode = 0644;
+	ret = sysfs_create_file(&p->kobj, &p->enable_smi_admin.attr);
+	if (ret) {
+		pr_err("failed to create enable_smi_admin\n");
+		sysfs_remove_file(&p->kobj, &p->smi_enabled.attr);
+		return ret;
+	}
+	return 0;
+}
+
+static void remove_vf_smi_entries(struct mlx4_port *p)
+{
+	int is_eth = rdma_port_get_link_layer(&p->dev->ib_dev, p->port_num) ==
+			IB_LINK_LAYER_ETHERNET;
+
+	if (is_eth || p->slave == mlx4_master_func_num(p->dev->dev))
+		return;
+
+	sysfs_remove_file(&p->kobj, &p->smi_enabled.attr);
+	sysfs_remove_file(&p->kobj, &p->enable_smi_admin.attr);
+}
+
 static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave)
 {
 	struct mlx4_port *p;
@@ -602,6 +699,10 @@ static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave)
 	if (ret)
 		goto err_free_gid;
 
+	ret = add_vf_smi_entries(p);
+	if (ret)
+		goto err_free_gid;
+
 	list_add_tail(&p->kobj.entry, &dev->pkeys.pkey_port_list[slave]);
 	return 0;
 
@@ -669,6 +770,7 @@ err_add:
 		mport = container_of(p, struct mlx4_port, kobj);
 		sysfs_remove_group(p, &mport->pkey_group);
 		sysfs_remove_group(p, &mport->gid_group);
+		remove_vf_smi_entries(mport);
 		kobject_put(p);
 	}
 	kobject_put(dev->dev_ports_parent[slave]);
@@ -713,6 +815,7 @@ static void unregister_pkey_tree(struct mlx4_ib_dev *device)
 			port = container_of(p, struct mlx4_port, kobj);
 			sysfs_remove_group(p, &port->pkey_group);
 			sysfs_remove_group(p, &port->gid_group);
+			remove_vf_smi_entries(port);
 			kobject_put(p);
 			kobject_put(device->dev_ports_parent[slave]);
 		}
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 62bb6b49dc1..8ae4f896cb4 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -32,6 +32,7 @@
 
 #include <linux/kref.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_user_verbs.h>
 #include "mlx5_ib.h"
 #include "user.h"
 
@@ -602,14 +603,24 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			  int *cqe_size, int *index, int *inlen)
 {
 	struct mlx5_ib_create_cq ucmd;
+	size_t ucmdlen;
 	int page_shift;
 	int npages;
 	int ncont;
 	int err;
 
-	if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)))
+	ucmdlen =
+		(udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
+		 sizeof(ucmd)) ? (sizeof(ucmd) -
+				  sizeof(ucmd.reserved)) : sizeof(ucmd);
+
+	if (ib_copy_from_udata(&ucmd, udata, ucmdlen))
 		return -EFAULT;
 
+	if (ucmdlen == sizeof(ucmd) &&
+	    ucmd.reserved != 0)
+		return -EINVAL;
+
 	if (ucmd.cqe_size != 64 && ucmd.cqe_size != 128)
 		return -EINVAL;
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 50541586e0a..f2ccf1a5a29 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -264,8 +264,6 @@ struct mlx5_ib_mr {
 	__be64			*pas;
 	dma_addr_t		dma;
 	int			npages;
-	struct completion	done;
-	enum ib_wc_status	status;
 	struct mlx5_ib_dev     *dev;
 	struct mlx5_create_mkey_mbox_out out;
 	struct mlx5_core_sig_ctx    *sig;
@@ -277,6 +275,17 @@ struct mlx5_ib_fast_reg_page_list {
 	dma_addr_t			map;
 };
 
+struct mlx5_ib_umr_context {
+	enum ib_wc_status	status;
+	struct completion	done;
+};
+
+static inline void mlx5_ib_init_umr_context(struct mlx5_ib_umr_context *context)
+{
+	context->status = -1;
+	init_completion(&context->done);
+}
+
 struct umr_common {
 	struct ib_pd	*pd;
 	struct ib_cq	*cq;
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 81392b26d07..afa873bd028 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -73,6 +73,8 @@ static void reg_mr_callback(int status, void *context)
 	struct mlx5_cache_ent *ent = &cache->ent[c];
 	u8 key;
 	unsigned long flags;
+	struct mlx5_mr_table *table = &dev->mdev.priv.mr_table;
+	int err;
 
 	spin_lock_irqsave(&ent->lock, flags);
 	ent->pending--;
@@ -107,6 +109,13 @@ static void reg_mr_callback(int status, void *context)
 	ent->cur++;
 	ent->size++;
 	spin_unlock_irqrestore(&ent->lock, flags);
+
+	write_lock_irqsave(&table->lock, flags);
+	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->mmr.key),
+				&mr->mmr);
+	if (err)
+		pr_err("Error inserting to mr tree. 0x%x\n", -err);
+	write_unlock_irqrestore(&table->lock, flags);
 }
 
 static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
@@ -699,7 +708,7 @@ static void prep_umr_unreg_wqe(struct mlx5_ib_dev *dev,
 
 void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context)
 {
-	struct mlx5_ib_mr *mr;
+	struct mlx5_ib_umr_context *context;
 	struct ib_wc wc;
 	int err;
 
@@ -712,9 +721,9 @@ void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context)
 		if (err == 0)
 			break;
 
-		mr = (struct mlx5_ib_mr *)(unsigned long)wc.wr_id;
-		mr->status = wc.status;
-		complete(&mr->done);
+		context = (struct mlx5_ib_umr_context *) (unsigned long) wc.wr_id;
+		context->status = wc.status;
+		complete(&context->done);
 	}
 	ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
 }
@@ -726,11 +735,12 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct device *ddev = dev->ib_dev.dma_device;
 	struct umr_common *umrc = &dev->umrc;
+	struct mlx5_ib_umr_context umr_context;
 	struct ib_send_wr wr, *bad;
 	struct mlx5_ib_mr *mr;
 	struct ib_sge sg;
 	int size = sizeof(u64) * npages;
-	int err;
+	int err = 0;
 	int i;
 
 	for (i = 0; i < 1; i++) {
@@ -751,7 +761,7 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 	mr->pas = kmalloc(size + MLX5_UMR_ALIGN - 1, GFP_KERNEL);
 	if (!mr->pas) {
 		err = -ENOMEM;
-		goto error;
+		goto free_mr;
 	}
 
 	mlx5_ib_populate_pas(dev, umem, page_shift,
@@ -760,44 +770,46 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
 	mr->dma = dma_map_single(ddev, mr_align(mr->pas, MLX5_UMR_ALIGN), size,
 				 DMA_TO_DEVICE);
 	if (dma_mapping_error(ddev, mr->dma)) {
-		kfree(mr->pas);
 		err = -ENOMEM;
-		goto error;
+		goto free_pas;
 	}
 
 	memset(&wr, 0, sizeof(wr));
-	wr.wr_id = (u64)(unsigned long)mr;
+	wr.wr_id = (u64)(unsigned long)&umr_context;
 	prep_umr_reg_wqe(pd, &wr, &sg, mr->dma, npages, mr->mmr.key, page_shift, virt_addr, len, access_flags);
 
-	/* We serialize polls so one process does not kidnap another's
-	 * completion. This is not a problem since wr is completed in
-	 * around 1 usec
-	 */
+	mlx5_ib_init_umr_context(&umr_context);
 	down(&umrc->sem);
-	init_completion(&mr->done);
 	err = ib_post_send(umrc->qp, &wr, &bad);
 	if (err) {
 		mlx5_ib_warn(dev, "post send failed, err %d\n", err);
-		up(&umrc->sem);
-		goto error;
+		goto unmap_dma;
+	} else {
+		wait_for_completion(&umr_context.done);
+		if (umr_context.status != IB_WC_SUCCESS) {
+			mlx5_ib_warn(dev, "reg umr failed\n");
+			err = -EFAULT;
+		}
 	}
-	wait_for_completion(&mr->done);
-	up(&umrc->sem);
 
+	mr->mmr.iova = virt_addr;
+	mr->mmr.size = len;
+	mr->mmr.pd = to_mpd(pd)->pdn;
+
+unmap_dma:
+	up(&umrc->sem);
 	dma_unmap_single(ddev, mr->dma, size, DMA_TO_DEVICE);
+
+free_pas:
 	kfree(mr->pas);
 
-	if (mr->status != IB_WC_SUCCESS) {
-		mlx5_ib_warn(dev, "reg umr failed\n");
-		err = -EFAULT;
-		goto error;
+free_mr:
+	if (err) {
+		free_cached_mr(dev, mr);
+		return ERR_PTR(err);
 	}
 
 	return mr;
-
-error:
-	free_cached_mr(dev, mr);
-	return ERR_PTR(err);
 }
 
 static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr,
@@ -926,24 +938,26 @@ error:
 static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
 	struct umr_common *umrc = &dev->umrc;
+	struct mlx5_ib_umr_context umr_context;
 	struct ib_send_wr wr, *bad;
 	int err;
 
 	memset(&wr, 0, sizeof(wr));
-	wr.wr_id = (u64)(unsigned long)mr;
+	wr.wr_id = (u64)(unsigned long)&umr_context;
 	prep_umr_unreg_wqe(dev, &wr, mr->mmr.key);
 
+	mlx5_ib_init_umr_context(&umr_context);
 	down(&umrc->sem);
-	init_completion(&mr->done);
 	err = ib_post_send(umrc->qp, &wr, &bad);
 	if (err) {
 		up(&umrc->sem);
 		mlx5_ib_dbg(dev, "err %d\n", err);
 		goto error;
+	} else {
+		wait_for_completion(&umr_context.done);
+		up(&umrc->sem);
 	}
-	wait_for_completion(&mr->done);
-	up(&umrc->sem);
-	if (mr->status != IB_WC_SUCCESS) {
+	if (umr_context.status != IB_WC_SUCCESS) {
 		mlx5_ib_warn(dev, "unreg umr failed\n");
 		err = -EFAULT;
 		goto error;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index dc930ed21ec..bbbcf389272 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -574,6 +574,10 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	uar_index = uuarn_to_uar_index(&context->uuari, uuarn);
 	mlx5_ib_dbg(dev, "uuarn 0x%x, uar_index 0x%x\n", uuarn, uar_index);
 
+	qp->rq.offset = 0;
+	qp->sq.wqe_shift = ilog2(MLX5_SEND_WQE_BB);
+	qp->sq.offset = qp->rq.wqe_cnt << qp->rq.wqe_shift;
+
 	err = set_user_buf_size(dev, qp, &ucmd);
 	if (err)
 		goto err_uuar;
@@ -671,7 +675,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	int err;
 
 	uuari = &dev->mdev.priv.uuari;
-	if (init_attr->create_flags & ~IB_QP_CREATE_SIGNATURE_EN)
+	if (init_attr->create_flags & ~(IB_QP_CREATE_SIGNATURE_EN | IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK))
 		return -EINVAL;
 
 	if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR)
@@ -2078,6 +2082,7 @@ static int mlx5_set_bsf(struct ib_mr *sig_mr,
 	struct ib_sig_domain *wire = &sig_attrs->wire;
 	int ret, selector;
 
+	memset(bsf, 0, sizeof(*bsf));
 	switch (sig_attrs->mem.sig_type) {
 	case IB_SIG_TYPE_T10_DIF:
 		if (sig_attrs->wire.sig_type != IB_SIG_TYPE_T10_DIF)
@@ -2090,9 +2095,11 @@ static int mlx5_set_bsf(struct ib_mr *sig_mr,
 			/* Same block structure */
 			basic->bsf_size_sbs = 1 << 4;
 			if (mem->sig.dif.bg_type == wire->sig.dif.bg_type)
-				basic->wire.copy_byte_mask = 0xff;
-			else
-				basic->wire.copy_byte_mask = 0x3f;
+				basic->wire.copy_byte_mask |= 0xc0;
+			if (mem->sig.dif.app_tag == wire->sig.dif.app_tag)
+				basic->wire.copy_byte_mask |= 0x30;
+			if (mem->sig.dif.ref_tag == wire->sig.dif.ref_tag)
+				basic->wire.copy_byte_mask |= 0x0f;
 		} else
 			basic->wire.bs_selector = bs_selector(wire->sig.dif.pi_interval);
 
@@ -2131,9 +2138,13 @@ static int set_sig_data_segment(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
 	int ret;
 	int wqe_size;
 
-	if (!wr->wr.sig_handover.prot) {
+	if (!wr->wr.sig_handover.prot ||
+	    (data_key == wr->wr.sig_handover.prot->lkey &&
+	     data_va == wr->wr.sig_handover.prot->addr &&
+	     data_len == wr->wr.sig_handover.prot->length)) {
 		/**
 		 * Source domain doesn't contain signature information
+		 * or data and protection are interleaved in memory.
 		 * So need construct:
 		 *                  ------------------
 		 *                 |     data_klm     |
@@ -2187,23 +2198,13 @@ static int set_sig_data_segment(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
 		data_sentry->bcount = cpu_to_be16(block_size);
 		data_sentry->key = cpu_to_be32(data_key);
 		data_sentry->va = cpu_to_be64(data_va);
+		data_sentry->stride = cpu_to_be16(block_size);
+
 		prot_sentry->bcount = cpu_to_be16(prot_size);
 		prot_sentry->key = cpu_to_be32(prot_key);
+		prot_sentry->va = cpu_to_be64(prot_va);
+		prot_sentry->stride = cpu_to_be16(prot_size);
 
-		if (prot_key == data_key && prot_va == data_va) {
-			/**
-			 * The data and protection are interleaved
-			 * in a single memory region
-			 **/
-			prot_sentry->va = cpu_to_be64(data_va + block_size);
-			prot_sentry->stride = cpu_to_be16(block_size + prot_size);
-			data_sentry->stride = prot_sentry->stride;
-		} else {
-			/* The data and protection are two different buffers */
-			prot_sentry->va = cpu_to_be64(prot_va);
-			data_sentry->stride = cpu_to_be16(block_size);
-			prot_sentry->stride = cpu_to_be16(prot_size);
-		}
 		wqe_size = ALIGN(sizeof(*sblock_ctrl) + sizeof(*data_sentry) +
 				 sizeof(*prot_sentry), 64);
 	}
@@ -2275,7 +2276,10 @@ static int set_sig_umr_wr(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
 
 	/* length of the protected region, data + protection */
 	region_len = wr->sg_list->length;
-	if (wr->wr.sig_handover.prot)
+	if (wr->wr.sig_handover.prot &&
+	    (wr->wr.sig_handover.prot->lkey != wr->sg_list->lkey  ||
+	     wr->wr.sig_handover.prot->addr != wr->sg_list->addr  ||
+	     wr->wr.sig_handover.prot->length != wr->sg_list->length))
 		region_len += wr->wr.sig_handover.prot->length;
 
 	/**
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 210b3eaf188..384af6dec5e 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -35,6 +35,7 @@
 #include <linux/mlx5/srq.h>
 #include <linux/slab.h>
 #include <rdma/ib_umem.h>
+#include <rdma/ib_user_verbs.h>
 
 #include "mlx5_ib.h"
 #include "user.h"
@@ -78,16 +79,27 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct mlx5_ib_create_srq ucmd;
+	size_t ucmdlen;
 	int err;
 	int npages;
 	int page_shift;
 	int ncont;
 	u32 offset;
 
-	if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
+	ucmdlen =
+		(udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
+		 sizeof(ucmd)) ? (sizeof(ucmd) -
+				  sizeof(ucmd.reserved)) : sizeof(ucmd);
+
+	if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) {
 		mlx5_ib_dbg(dev, "failed copy udata\n");
 		return -EFAULT;
 	}
+
+	if (ucmdlen == sizeof(ucmd) &&
+	    ucmd.reserved != 0)
+		return -EINVAL;
+
 	srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE);
 
 	srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, buf_size,
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index 0f4f8e42a17..d0ba264ac1e 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -91,6 +91,7 @@ struct mlx5_ib_create_cq {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u32	cqe_size;
+	__u32	reserved; /* explicit padding (optional on i386) */
 };
 
 struct mlx5_ib_create_cq_resp {
@@ -109,6 +110,7 @@ struct mlx5_ib_create_srq {
 	__u64	buf_addr;
 	__u64	db_addr;
 	__u32	flags;
+	__u32	reserved; /* explicit padding (optional on i386) */
 };
 
 struct mlx5_ib_create_srq_resp {
diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c
index 353c7b05a90..3b2a6dc8ea9 100644
--- a/drivers/infiniband/hw/nes/nes.c
+++ b/drivers/infiniband/hw/nes/nes.c
@@ -68,7 +68,6 @@ MODULE_VERSION(DRV_VERSION);
 int max_mtu = 9000;
 int interrupt_mod_interval = 0;
 
-
 /* Interoperability */
 int mpa_version = 1;
 module_param(mpa_version, int, 0644);
@@ -112,6 +111,16 @@ static struct pci_device_id nes_pci_table[] = {
 
 MODULE_DEVICE_TABLE(pci, nes_pci_table);
 
+/* registered nes netlink callbacks */
+static struct ibnl_client_cbs nes_nl_cb_table[] = {
+	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
+	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
+	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
+	[RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb},
+	[RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb},
+	[RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}
+};
+
 static int nes_inetaddr_event(struct notifier_block *, unsigned long, void *);
 static int nes_net_event(struct notifier_block *, unsigned long, void *);
 static int nes_notifiers_registered;
@@ -672,6 +681,17 @@ static int nes_probe(struct pci_dev *pcidev, const struct pci_device_id *ent)
 	}
 	nes_notifiers_registered++;
 
+	if (ibnl_add_client(RDMA_NL_NES, RDMA_NL_IWPM_NUM_OPS, nes_nl_cb_table))
+		printk(KERN_ERR PFX "%s[%u]: Failed to add netlink callback\n",
+			__func__, __LINE__);
+
+	ret = iwpm_init(RDMA_NL_NES);
+	if (ret) {
+		printk(KERN_ERR PFX "%s: port mapper initialization failed\n",
+				pci_name(pcidev));
+		goto bail7;
+	}
+
 	INIT_DELAYED_WORK(&nesdev->work, nes_recheck_link_status);
 
 	/* Initialize network devices */
@@ -710,6 +730,7 @@ static int nes_probe(struct pci_dev *pcidev, const struct pci_device_id *ent)
 
 	nes_debug(NES_DBG_INIT, "netdev_count=%d, nesadapter->netdev_count=%d\n",
 			nesdev->netdev_count, nesdev->nesadapter->netdev_count);
+	ibnl_remove_client(RDMA_NL_NES);
 
 	nes_notifiers_registered--;
 	if (nes_notifiers_registered == 0) {
@@ -773,6 +794,8 @@ static void nes_remove(struct pci_dev *pcidev)
 				nesdev->nesadapter->netdev_count--;
 			}
 		}
+	ibnl_remove_client(RDMA_NL_NES);
+	iwpm_exit(RDMA_NL_NES);
 
 	nes_notifiers_registered--;
 	if (nes_notifiers_registered == 0) {
diff --git a/drivers/infiniband/hw/nes/nes.h b/drivers/infiniband/hw/nes/nes.h
index 33cc58941a3..bd9d132f11c 100644
--- a/drivers/infiniband/hw/nes/nes.h
+++ b/drivers/infiniband/hw/nes/nes.h
@@ -51,6 +51,8 @@
 #include <rdma/ib_pack.h>
 #include <rdma/rdma_cm.h>
 #include <rdma/iw_cm.h>
+#include <rdma/rdma_netlink.h>
+#include <rdma/iw_portmap.h>
 
 #define NES_SEND_FIRST_WRITE
 
@@ -130,6 +132,7 @@
 #define NES_DBG_IW_TX       0x00040000
 #define NES_DBG_SHUTDOWN    0x00080000
 #define NES_DBG_PAU         0x00100000
+#define NES_DBG_NLMSG       0x00200000
 #define NES_DBG_RSVD1       0x10000000
 #define NES_DBG_RSVD2       0x20000000
 #define NES_DBG_RSVD3       0x40000000
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index dfa9df48450..6f09a72e78d 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2014 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -59,6 +59,7 @@
 #include <net/route.h>
 #include <net/ip_fib.h>
 #include <net/tcp.h>
+#include <linux/fcntl.h>
 
 #include "nes.h"
 
@@ -166,7 +167,6 @@ int nes_rem_ref_cm_node(struct nes_cm_node *cm_node)
 {
 	return rem_ref_cm_node(cm_node->cm_core, cm_node);
 }
-
 /**
  * create_event
  */
@@ -482,11 +482,11 @@ static void form_cm_frame(struct sk_buff *skb,
 	iph->ttl = 0x40;
 	iph->protocol = 0x06;   /* IPPROTO_TCP */
 
-	iph->saddr = htonl(cm_node->loc_addr);
-	iph->daddr = htonl(cm_node->rem_addr);
+	iph->saddr = htonl(cm_node->mapped_loc_addr);
+	iph->daddr = htonl(cm_node->mapped_rem_addr);
 
-	tcph->source = htons(cm_node->loc_port);
-	tcph->dest = htons(cm_node->rem_port);
+	tcph->source = htons(cm_node->mapped_loc_port);
+	tcph->dest = htons(cm_node->mapped_rem_port);
 	tcph->seq = htonl(cm_node->tcp_cntxt.loc_seq_num);
 
 	if (flags & SET_ACK) {
@@ -525,6 +525,100 @@ static void form_cm_frame(struct sk_buff *skb,
 	cm_packets_created++;
 }
 
+/*
+ * nes_create_sockaddr - Record ip addr and tcp port in a sockaddr struct
+ */
+static void nes_create_sockaddr(__be32 ip_addr, __be16 port,
+				struct sockaddr_storage *addr)
+{
+	struct sockaddr_in *nes_sockaddr = (struct sockaddr_in *)addr;
+	nes_sockaddr->sin_family = AF_INET;
+	memcpy(&nes_sockaddr->sin_addr.s_addr, &ip_addr, sizeof(__be32));
+	nes_sockaddr->sin_port = port;
+}
+
+/*
+ * nes_create_mapinfo - Create a mapinfo object in the port mapper data base
+ */
+static int nes_create_mapinfo(struct nes_cm_info *cm_info)
+{
+	struct sockaddr_storage local_sockaddr;
+	struct sockaddr_storage mapped_sockaddr;
+
+	nes_create_sockaddr(htonl(cm_info->loc_addr), htons(cm_info->loc_port),
+				&local_sockaddr);
+	nes_create_sockaddr(htonl(cm_info->mapped_loc_addr),
+			htons(cm_info->mapped_loc_port), &mapped_sockaddr);
+
+	return iwpm_create_mapinfo(&local_sockaddr,
+				&mapped_sockaddr, RDMA_NL_NES);
+}
+
+/*
+ * nes_remove_mapinfo - Remove a mapinfo object from the port mapper data base
+ *                      and send a remove mapping op message to
+ *                      the userspace port mapper
+ */
+static int nes_remove_mapinfo(u32 loc_addr, u16 loc_port,
+			u32 mapped_loc_addr, u16 mapped_loc_port)
+{
+	struct sockaddr_storage local_sockaddr;
+	struct sockaddr_storage mapped_sockaddr;
+
+	nes_create_sockaddr(htonl(loc_addr), htons(loc_port), &local_sockaddr);
+	nes_create_sockaddr(htonl(mapped_loc_addr), htons(mapped_loc_port),
+				&mapped_sockaddr);
+
+	iwpm_remove_mapinfo(&local_sockaddr, &mapped_sockaddr);
+	return iwpm_remove_mapping(&local_sockaddr, RDMA_NL_NES);
+}
+
+/*
+ * nes_form_pm_msg - Form a port mapper message with mapping info
+ */
+static void nes_form_pm_msg(struct nes_cm_info *cm_info,
+				struct iwpm_sa_data *pm_msg)
+{
+	nes_create_sockaddr(htonl(cm_info->loc_addr), htons(cm_info->loc_port),
+				&pm_msg->loc_addr);
+	nes_create_sockaddr(htonl(cm_info->rem_addr), htons(cm_info->rem_port),
+				&pm_msg->rem_addr);
+}
+
+/*
+ * nes_form_reg_msg - Form a port mapper message with dev info
+ */
+static void nes_form_reg_msg(struct nes_vnic *nesvnic,
+			struct iwpm_dev_data *pm_msg)
+{
+	memcpy(pm_msg->dev_name, nesvnic->nesibdev->ibdev.name,
+				IWPM_DEVNAME_SIZE);
+	memcpy(pm_msg->if_name, nesvnic->netdev->name, IWPM_IFNAME_SIZE);
+}
+
+/*
+ * nes_record_pm_msg - Save the received mapping info
+ */
+static void nes_record_pm_msg(struct nes_cm_info *cm_info,
+			struct iwpm_sa_data *pm_msg)
+{
+	struct sockaddr_in *mapped_loc_addr =
+			(struct sockaddr_in *)&pm_msg->mapped_loc_addr;
+	struct sockaddr_in *mapped_rem_addr =
+			(struct sockaddr_in *)&pm_msg->mapped_rem_addr;
+
+	if (mapped_loc_addr->sin_family == AF_INET) {
+		cm_info->mapped_loc_addr =
+			ntohl(mapped_loc_addr->sin_addr.s_addr);
+		cm_info->mapped_loc_port = ntohs(mapped_loc_addr->sin_port);
+	}
+	if (mapped_rem_addr->sin_family == AF_INET) {
+		cm_info->mapped_rem_addr =
+			ntohl(mapped_rem_addr->sin_addr.s_addr);
+		cm_info->mapped_rem_port = ntohs(mapped_rem_addr->sin_port);
+	}
+}
+
 /**
  * print_core - dump a cm core
  */
@@ -1147,8 +1241,11 @@ static struct nes_cm_node *find_node(struct nes_cm_core *cm_core,
 			  loc_addr, loc_port,
 			  cm_node->rem_addr, cm_node->rem_port,
 			  rem_addr, rem_port);
-		if ((cm_node->loc_addr == loc_addr) && (cm_node->loc_port == loc_port) &&
-		    (cm_node->rem_addr == rem_addr) && (cm_node->rem_port == rem_port)) {
+		if ((cm_node->mapped_loc_addr == loc_addr) &&
+			(cm_node->mapped_loc_port == loc_port) &&
+			(cm_node->mapped_rem_addr == rem_addr) &&
+			(cm_node->mapped_rem_port == rem_port)) {
+
 			add_ref_cm_node(cm_node);
 			spin_unlock_irqrestore(&cm_core->ht_lock, flags);
 			return cm_node;
@@ -1165,18 +1262,28 @@ static struct nes_cm_node *find_node(struct nes_cm_core *cm_core,
  * find_listener - find a cm node listening on this addr-port pair
  */
 static struct nes_cm_listener *find_listener(struct nes_cm_core *cm_core,
-					     nes_addr_t dst_addr, u16 dst_port, enum nes_cm_listener_state listener_state)
+					nes_addr_t dst_addr, u16 dst_port,
+					enum nes_cm_listener_state listener_state, int local)
 {
 	unsigned long flags;
 	struct nes_cm_listener *listen_node;
+	nes_addr_t listen_addr;
+	u16 listen_port;
 
 	/* walk list and find cm_node associated with this session ID */
 	spin_lock_irqsave(&cm_core->listen_list_lock, flags);
 	list_for_each_entry(listen_node, &cm_core->listen_list.list, list) {
+		if (local) {
+			listen_addr = listen_node->loc_addr;
+			listen_port = listen_node->loc_port;
+		} else {
+			listen_addr = listen_node->mapped_loc_addr;
+			listen_port = listen_node->mapped_loc_port;
+		}
 		/* compare node pair, return node handle if a match */
-		if (((listen_node->loc_addr == dst_addr) ||
-		     listen_node->loc_addr == 0x00000000) &&
-		    (listen_node->loc_port == dst_port) &&
+		if (((listen_addr == dst_addr) ||
+		     listen_addr == 0x00000000) &&
+		    (listen_port == dst_port) &&
 		    (listener_state & listen_node->listener_state)) {
 			atomic_inc(&listen_node->ref_count);
 			spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
@@ -1189,7 +1296,6 @@ static struct nes_cm_listener *find_listener(struct nes_cm_core *cm_core,
 	return NULL;
 }
 
-
 /**
  * add_hte_node - add a cm node to the hash table
  */
@@ -1310,9 +1416,20 @@ static int mini_cm_dec_refcnt_listen(struct nes_cm_core *cm_core,
 
 		spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
 
-		if (listener->nesvnic)
-			nes_manage_apbvt(listener->nesvnic, listener->loc_port,
-					 PCI_FUNC(listener->nesvnic->nesdev->pcidev->devfn), NES_MANAGE_APBVT_DEL);
+		if (listener->nesvnic) {
+			nes_manage_apbvt(listener->nesvnic,
+				listener->mapped_loc_port,
+				PCI_FUNC(listener->nesvnic->nesdev->pcidev->devfn),
+				NES_MANAGE_APBVT_DEL);
+
+			nes_remove_mapinfo(listener->loc_addr,
+					listener->loc_port,
+					listener->mapped_loc_addr,
+					listener->mapped_loc_port);
+			nes_debug(NES_DBG_NLMSG,
+					"Delete APBVT mapped_loc_port = %04X\n",
+					listener->mapped_loc_port);
+		}
 
 		nes_debug(NES_DBG_CM, "destroying listener (%p)\n", listener);
 
@@ -1454,6 +1571,11 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 	cm_node->loc_port = cm_info->loc_port;
 	cm_node->rem_port = cm_info->rem_port;
 
+	cm_node->mapped_loc_addr = cm_info->mapped_loc_addr;
+	cm_node->mapped_rem_addr = cm_info->mapped_rem_addr;
+	cm_node->mapped_loc_port = cm_info->mapped_loc_port;
+	cm_node->mapped_rem_port = cm_info->mapped_rem_port;
+
 	cm_node->mpa_frame_rev = mpa_version;
 	cm_node->send_rdma0_op = SEND_RDMA_READ_ZERO;
 	cm_node->mpav2_ird_ord = 0;
@@ -1500,8 +1622,10 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 	cm_node->loopbackpartner = NULL;
 
 	/* get the mac addr for the remote node */
-	oldarpindex = nes_arp_table(nesdev, cm_node->rem_addr, NULL, NES_ARP_RESOLVE);
-	arpindex = nes_addr_resolve_neigh(nesvnic, cm_info->rem_addr, oldarpindex);
+	oldarpindex = nes_arp_table(nesdev, cm_node->mapped_rem_addr,
+				NULL, NES_ARP_RESOLVE);
+	arpindex = nes_addr_resolve_neigh(nesvnic,
+				cm_node->mapped_rem_addr, oldarpindex);
 	if (arpindex < 0) {
 		kfree(cm_node);
 		return NULL;
@@ -1563,11 +1687,14 @@ static int rem_ref_cm_node(struct nes_cm_core *cm_core,
 		mini_cm_dec_refcnt_listen(cm_core, cm_node->listener, 0);
 	} else {
 		if (cm_node->apbvt_set && cm_node->nesvnic) {
-			nes_manage_apbvt(cm_node->nesvnic, cm_node->loc_port,
-					 PCI_FUNC(
-						 cm_node->nesvnic->nesdev->pcidev->devfn),
+			nes_manage_apbvt(cm_node->nesvnic, cm_node->mapped_loc_port,
+					 PCI_FUNC(cm_node->nesvnic->nesdev->pcidev->devfn),
 					 NES_MANAGE_APBVT_DEL);
 		}
+		nes_debug(NES_DBG_NLMSG, "Delete APBVT mapped_loc_port = %04X\n",
+					cm_node->mapped_loc_port);
+		nes_remove_mapinfo(cm_node->loc_addr, cm_node->loc_port,
+			cm_node->mapped_loc_addr, cm_node->mapped_loc_port);
 	}
 
 	atomic_dec(&cm_core->node_cnt);
@@ -2235,17 +2362,21 @@ static void process_packet(struct nes_cm_node *cm_node, struct sk_buff *skb,
  * mini_cm_listen - create a listen node with params
  */
 static struct nes_cm_listener *mini_cm_listen(struct nes_cm_core *cm_core,
-					      struct nes_vnic *nesvnic, struct nes_cm_info *cm_info)
+			struct nes_vnic *nesvnic, struct nes_cm_info *cm_info)
 {
 	struct nes_cm_listener *listener;
+	struct iwpm_dev_data pm_reg_msg;
+	struct iwpm_sa_data pm_msg;
 	unsigned long flags;
+	int iwpm_err = 0;
 
 	nes_debug(NES_DBG_CM, "Search for 0x%08x : 0x%04x\n",
 		  cm_info->loc_addr, cm_info->loc_port);
 
 	/* cannot have multiple matching listeners */
-	listener = find_listener(cm_core, htonl(cm_info->loc_addr),
-				 htons(cm_info->loc_port), NES_CM_LISTENER_EITHER_STATE);
+	listener = find_listener(cm_core, cm_info->loc_addr, cm_info->loc_port,
+				NES_CM_LISTENER_EITHER_STATE, 1);
+
 	if (listener && listener->listener_state == NES_CM_LISTENER_ACTIVE_STATE) {
 		/* find automatically incs ref count ??? */
 		atomic_dec(&listener->ref_count);
@@ -2254,6 +2385,22 @@ static struct nes_cm_listener *mini_cm_listen(struct nes_cm_core *cm_core,
 	}
 
 	if (!listener) {
+		nes_form_reg_msg(nesvnic, &pm_reg_msg);
+		iwpm_err = iwpm_register_pid(&pm_reg_msg, RDMA_NL_NES);
+		if (iwpm_err) {
+			nes_debug(NES_DBG_NLMSG,
+			"Port Mapper reg pid fail (err = %d).\n", iwpm_err);
+		}
+		if (iwpm_valid_pid() && !iwpm_err) {
+			nes_form_pm_msg(cm_info, &pm_msg);
+			iwpm_err = iwpm_add_mapping(&pm_msg, RDMA_NL_NES);
+			if (iwpm_err)
+				nes_debug(NES_DBG_NLMSG,
+				"Port Mapper query fail (err = %d).\n", iwpm_err);
+			else
+				nes_record_pm_msg(cm_info, &pm_msg);
+		}
+
 		/* create a CM listen node (1/2 node to compare incoming traffic to) */
 		listener = kzalloc(sizeof(*listener), GFP_ATOMIC);
 		if (!listener) {
@@ -2261,8 +2408,10 @@ static struct nes_cm_listener *mini_cm_listen(struct nes_cm_core *cm_core,
 			return NULL;
 		}
 
-		listener->loc_addr = htonl(cm_info->loc_addr);
-		listener->loc_port = htons(cm_info->loc_port);
+		listener->loc_addr = cm_info->loc_addr;
+		listener->loc_port = cm_info->loc_port;
+		listener->mapped_loc_addr = cm_info->mapped_loc_addr;
+		listener->mapped_loc_port = cm_info->mapped_loc_port;
 		listener->reused_node = 0;
 
 		atomic_set(&listener->ref_count, 1);
@@ -2324,14 +2473,18 @@ static struct nes_cm_node *mini_cm_connect(struct nes_cm_core *cm_core,
 
 	if (cm_info->loc_addr == cm_info->rem_addr) {
 		loopbackremotelistener = find_listener(cm_core,
-						       ntohl(nesvnic->local_ipaddr), cm_node->rem_port,
-						       NES_CM_LISTENER_ACTIVE_STATE);
+			cm_node->mapped_loc_addr, cm_node->mapped_rem_port,
+			NES_CM_LISTENER_ACTIVE_STATE, 0);
 		if (loopbackremotelistener == NULL) {
 			create_event(cm_node, NES_CM_EVENT_ABORTED);
 		} else {
 			loopback_cm_info = *cm_info;
 			loopback_cm_info.loc_port = cm_info->rem_port;
 			loopback_cm_info.rem_port = cm_info->loc_port;
+			loopback_cm_info.mapped_loc_port =
+				cm_info->mapped_rem_port;
+			loopback_cm_info.mapped_rem_port =
+				cm_info->mapped_loc_port;
 			loopback_cm_info.cm_id = loopbackremotelistener->cm_id;
 			loopbackremotenode = make_cm_node(cm_core, nesvnic,
 							  &loopback_cm_info, loopbackremotelistener);
@@ -2560,6 +2713,12 @@ static int mini_cm_recv_pkt(struct nes_cm_core *cm_core,
 	nfo.rem_addr = ntohl(iph->saddr);
 	nfo.rem_port = ntohs(tcph->source);
 
+	/* If port mapper is available these should be mapped address info */
+	nfo.mapped_loc_addr = ntohl(iph->daddr);
+	nfo.mapped_loc_port = ntohs(tcph->dest);
+	nfo.mapped_rem_addr = ntohl(iph->saddr);
+	nfo.mapped_rem_port = ntohs(tcph->source);
+
 	tmp_daddr = cpu_to_be32(iph->daddr);
 	tmp_saddr = cpu_to_be32(iph->saddr);
 
@@ -2568,8 +2727,8 @@ static int mini_cm_recv_pkt(struct nes_cm_core *cm_core,
 
 	do {
 		cm_node = find_node(cm_core,
-				    nfo.rem_port, nfo.rem_addr,
-				    nfo.loc_port, nfo.loc_addr);
+				    nfo.mapped_rem_port, nfo.mapped_rem_addr,
+				    nfo.mapped_loc_port, nfo.mapped_loc_addr);
 
 		if (!cm_node) {
 			/* Only type of packet accepted are for */
@@ -2578,9 +2737,9 @@ static int mini_cm_recv_pkt(struct nes_cm_core *cm_core,
 				skb_handled = 0;
 				break;
 			}
-			listener = find_listener(cm_core, nfo.loc_addr,
-						 nfo.loc_port,
-						 NES_CM_LISTENER_ACTIVE_STATE);
+			listener = find_listener(cm_core, nfo.mapped_loc_addr,
+					nfo.mapped_loc_port,
+					NES_CM_LISTENER_ACTIVE_STATE, 0);
 			if (!listener) {
 				nfo.cm_id = NULL;
 				nfo.conn_type = 0;
@@ -3184,10 +3343,12 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 
 	nes_cm_init_tsa_conn(nesqp, cm_node);
 
-	nesqp->nesqp_context->tcpPorts[0] = cpu_to_le16(ntohs(laddr->sin_port));
-	nesqp->nesqp_context->tcpPorts[1] = cpu_to_le16(ntohs(raddr->sin_port));
+	nesqp->nesqp_context->tcpPorts[0] =
+				cpu_to_le16(cm_node->mapped_loc_port);
+	nesqp->nesqp_context->tcpPorts[1] =
+				cpu_to_le16(cm_node->mapped_rem_port);
 
-	nesqp->nesqp_context->ip0 = cpu_to_le32(ntohl(raddr->sin_addr.s_addr));
+	nesqp->nesqp_context->ip0 = cpu_to_le32(cm_node->mapped_rem_addr);
 
 	nesqp->nesqp_context->misc2 |= cpu_to_le32(
 		(u32)PCI_FUNC(nesdev->pcidev->devfn) <<
@@ -3211,9 +3372,9 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	memset(&nes_quad, 0, sizeof(nes_quad));
 	nes_quad.DstIpAdrIndex =
 		cpu_to_le32((u32)PCI_FUNC(nesdev->pcidev->devfn) << 24);
-	nes_quad.SrcIpadr = raddr->sin_addr.s_addr;
-	nes_quad.TcpPorts[0] = raddr->sin_port;
-	nes_quad.TcpPorts[1] = laddr->sin_port;
+	nes_quad.SrcIpadr = htonl(cm_node->mapped_rem_addr);
+	nes_quad.TcpPorts[0] = htons(cm_node->mapped_rem_port);
+	nes_quad.TcpPorts[1] = htons(cm_node->mapped_loc_port);
 
 	/* Produce hash key */
 	crc_value = get_crc_value(&nes_quad);
@@ -3315,6 +3476,9 @@ int nes_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	int apbvt_set = 0;
 	struct sockaddr_in *laddr = (struct sockaddr_in *)&cm_id->local_addr;
 	struct sockaddr_in *raddr = (struct sockaddr_in *)&cm_id->remote_addr;
+	struct iwpm_dev_data pm_reg_msg;
+	struct iwpm_sa_data pm_msg;
+	int iwpm_err = 0;
 
 	if (cm_id->remote_addr.ss_family != AF_INET)
 		return -ENOSYS;
@@ -3352,20 +3516,44 @@ int nes_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	nes_debug(NES_DBG_CM, "mpa private data len =%u\n",
 		  conn_param->private_data_len);
 
+	/* set up the connection params for the node */
+	cm_info.loc_addr = ntohl(laddr->sin_addr.s_addr);
+	cm_info.loc_port = ntohs(laddr->sin_port);
+	cm_info.rem_addr = ntohl(raddr->sin_addr.s_addr);
+	cm_info.rem_port = ntohs(raddr->sin_port);
+	cm_info.cm_id = cm_id;
+	cm_info.conn_type = NES_CM_IWARP_CONN_TYPE;
+
+	/* No port mapper available, go with the specified peer information */
+	cm_info.mapped_loc_addr = cm_info.loc_addr;
+	cm_info.mapped_loc_port = cm_info.loc_port;
+	cm_info.mapped_rem_addr = cm_info.rem_addr;
+	cm_info.mapped_rem_port = cm_info.rem_port;
+
+	nes_form_reg_msg(nesvnic, &pm_reg_msg);
+	iwpm_err = iwpm_register_pid(&pm_reg_msg, RDMA_NL_NES);
+	if (iwpm_err) {
+		nes_debug(NES_DBG_NLMSG,
+			"Port Mapper reg pid fail (err = %d).\n", iwpm_err);
+	}
+	if (iwpm_valid_pid() && !iwpm_err) {
+		nes_form_pm_msg(&cm_info, &pm_msg);
+		iwpm_err = iwpm_add_and_query_mapping(&pm_msg, RDMA_NL_NES);
+		if (iwpm_err)
+			nes_debug(NES_DBG_NLMSG,
+			"Port Mapper query fail (err = %d).\n", iwpm_err);
+		else
+			nes_record_pm_msg(&cm_info, &pm_msg);
+	}
+
 	if (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr) {
-		nes_manage_apbvt(nesvnic, ntohs(laddr->sin_port),
-				 PCI_FUNC(nesdev->pcidev->devfn),
-				 NES_MANAGE_APBVT_ADD);
+		nes_manage_apbvt(nesvnic, cm_info.mapped_loc_port,
+			PCI_FUNC(nesdev->pcidev->devfn), NES_MANAGE_APBVT_ADD);
 		apbvt_set = 1;
 	}
 
-	/* set up the connection params for the node */
-	cm_info.loc_addr = htonl(laddr->sin_addr.s_addr);
-	cm_info.loc_port = htons(laddr->sin_port);
-	cm_info.rem_addr = htonl(raddr->sin_addr.s_addr);
-	cm_info.rem_port = htons(raddr->sin_port);
-	cm_info.cm_id = cm_id;
-	cm_info.conn_type = NES_CM_IWARP_CONN_TYPE;
+	if (nes_create_mapinfo(&cm_info))
+		return -ENOMEM;
 
 	cm_id->add_ref(cm_id);
 
@@ -3375,10 +3563,14 @@ int nes_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 					  &cm_info);
 	if (!cm_node) {
 		if (apbvt_set)
-			nes_manage_apbvt(nesvnic, ntohs(laddr->sin_port),
+			nes_manage_apbvt(nesvnic, cm_info.mapped_loc_port,
 					 PCI_FUNC(nesdev->pcidev->devfn),
 					 NES_MANAGE_APBVT_DEL);
 
+		nes_debug(NES_DBG_NLMSG, "Delete mapped_loc_port = %04X\n",
+				cm_info.mapped_loc_port);
+		nes_remove_mapinfo(cm_info.loc_addr, cm_info.loc_port,
+			cm_info.mapped_loc_addr, cm_info.mapped_loc_port);
 		cm_id->rem_ref(cm_id);
 		return -ENOMEM;
 	}
@@ -3424,13 +3616,16 @@ int nes_create_listen(struct iw_cm_id *cm_id, int backlog)
 			nesvnic->local_ipaddr, laddr->sin_addr.s_addr);
 
 	/* setup listen params in our api call struct */
-	cm_info.loc_addr = nesvnic->local_ipaddr;
-	cm_info.loc_port = laddr->sin_port;
+	cm_info.loc_addr = ntohl(nesvnic->local_ipaddr);
+	cm_info.loc_port = ntohs(laddr->sin_port);
 	cm_info.backlog = backlog;
 	cm_info.cm_id = cm_id;
 
 	cm_info.conn_type = NES_CM_IWARP_CONN_TYPE;
 
+	/* No port mapper available, go with the specified info */
+	cm_info.mapped_loc_addr = cm_info.loc_addr;
+	cm_info.mapped_loc_port = cm_info.loc_port;
 
 	cm_node = g_cm_core->api->listen(g_cm_core, nesvnic, &cm_info);
 	if (!cm_node) {
@@ -3442,7 +3637,10 @@ int nes_create_listen(struct iw_cm_id *cm_id, int backlog)
 	cm_id->provider_data = cm_node;
 
 	if (!cm_node->reused_node) {
-		err = nes_manage_apbvt(nesvnic, ntohs(laddr->sin_port),
+		if (nes_create_mapinfo(&cm_info))
+			return -ENOMEM;
+
+		err = nes_manage_apbvt(nesvnic, cm_node->mapped_loc_port,
 				       PCI_FUNC(nesvnic->nesdev->pcidev->devfn),
 				       NES_MANAGE_APBVT_ADD);
 		if (err) {
@@ -3567,9 +3765,11 @@ static void cm_event_connected(struct nes_cm_event *event)
 	nes_cm_init_tsa_conn(nesqp, cm_node);
 
 	/* set the QP tsa context */
-	nesqp->nesqp_context->tcpPorts[0] = cpu_to_le16(ntohs(laddr->sin_port));
-	nesqp->nesqp_context->tcpPorts[1] = cpu_to_le16(ntohs(raddr->sin_port));
-	nesqp->nesqp_context->ip0 = cpu_to_le32(ntohl(raddr->sin_addr.s_addr));
+	nesqp->nesqp_context->tcpPorts[0] =
+			cpu_to_le16(cm_node->mapped_loc_port);
+	nesqp->nesqp_context->tcpPorts[1] =
+			cpu_to_le16(cm_node->mapped_rem_port);
+	nesqp->nesqp_context->ip0 = cpu_to_le32(cm_node->mapped_rem_addr);
 
 	nesqp->nesqp_context->misc2 |= cpu_to_le32(
 			(u32)PCI_FUNC(nesdev->pcidev->devfn) <<
@@ -3599,9 +3799,9 @@ static void cm_event_connected(struct nes_cm_event *event)
 
 	nes_quad.DstIpAdrIndex =
 		cpu_to_le32((u32)PCI_FUNC(nesdev->pcidev->devfn) << 24);
-	nes_quad.SrcIpadr = raddr->sin_addr.s_addr;
-	nes_quad.TcpPorts[0] = raddr->sin_port;
-	nes_quad.TcpPorts[1] = laddr->sin_port;
+	nes_quad.SrcIpadr = htonl(cm_node->mapped_rem_addr);
+	nes_quad.TcpPorts[0] = htons(cm_node->mapped_rem_port);
+	nes_quad.TcpPorts[1] = htons(cm_node->mapped_loc_port);
 
 	/* Produce hash key */
 	crc_value = get_crc_value(&nes_quad);
@@ -3629,7 +3829,7 @@ static void cm_event_connected(struct nes_cm_event *event)
 	cm_event.ird = cm_node->ird_size;
 	cm_event.ord = cm_node->ord_size;
 
-	cm_event_laddr->sin_addr.s_addr = event->cm_info.rem_addr;
+	cm_event_laddr->sin_addr.s_addr = htonl(event->cm_info.rem_addr);
 	ret = cm_id->event_handler(cm_id, &cm_event);
 	nes_debug(NES_DBG_CM, "OFA CM event_handler returned, ret=%d\n", ret);
 
diff --git a/drivers/infiniband/hw/nes/nes_cm.h b/drivers/infiniband/hw/nes/nes_cm.h
index 522c99cd07c..f522cf63978 100644
--- a/drivers/infiniband/hw/nes/nes_cm.h
+++ b/drivers/infiniband/hw/nes/nes_cm.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 - 2011 Intel Corporation.  All rights reserved.
+ * Copyright (c) 2006 - 2014 Intel Corporation.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -293,8 +293,8 @@ struct nes_cm_listener {
 	struct list_head           list;
 	struct nes_cm_core         *cm_core;
 	u8                         loc_mac[ETH_ALEN];
-	nes_addr_t                 loc_addr;
-	u16                        loc_port;
+	nes_addr_t                 loc_addr, mapped_loc_addr;
+	u16                        loc_port, mapped_loc_port;
 	struct iw_cm_id            *cm_id;
 	enum nes_cm_conn_type      conn_type;
 	atomic_t                   ref_count;
@@ -308,7 +308,9 @@ struct nes_cm_listener {
 /* per connection node and node state information */
 struct nes_cm_node {
 	nes_addr_t                loc_addr, rem_addr;
+	nes_addr_t                mapped_loc_addr, mapped_rem_addr;
 	u16                       loc_port, rem_port;
+	u16                       mapped_loc_port, mapped_rem_port;
 
 	u8                        loc_mac[ETH_ALEN];
 	u8                        rem_mac[ETH_ALEN];
@@ -364,6 +366,10 @@ struct nes_cm_info {
 	u16 rem_port;
 	nes_addr_t loc_addr;
 	nes_addr_t rem_addr;
+	u16 mapped_loc_port;
+	u16 mapped_rem_port;
+	nes_addr_t mapped_loc_addr;
+	nes_addr_t mapped_rem_addr;
 
 	enum nes_cm_conn_type  conn_type;
 	int backlog;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 6c54106f5e6..41a9aec9998 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -510,16 +510,9 @@ exit:
 	return status;
 }
 
-static int ocrdma_debugfs_open(struct inode *inode, struct file *file)
-{
-	if (inode->i_private)
-		file->private_data = inode->i_private;
-	return 0;
-}
-
 static const struct file_operations ocrdma_dbg_ops = {
 	.owner = THIS_MODULE,
-	.open = ocrdma_debugfs_open,
+	.open = simple_open,
 	.read = ocrdma_dbgfs_ops_read,
 };
 
diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c
index 5b7aeb224a3..8d3c78ddc90 100644
--- a/drivers/infiniband/hw/qib/qib_init.c
+++ b/drivers/infiniband/hw/qib/qib_init.c
@@ -1272,7 +1272,7 @@ static int qib_notify_dca(struct notifier_block *nb, unsigned long event,
  * Do all the generic driver unit- and chip-independent memory
  * allocation and initialization.
  */
-static int __init qlogic_ib_init(void)
+static int __init qib_ib_init(void)
 {
 	int ret;
 
@@ -1316,12 +1316,12 @@ bail:
 	return ret;
 }
 
-module_init(qlogic_ib_init);
+module_init(qib_ib_init);
 
 /*
  * Do the non-unit driver cleanup, memory free, etc. at unload.
  */
-static void __exit qlogic_ib_cleanup(void)
+static void __exit qib_ib_cleanup(void)
 {
 	int ret;
 
@@ -1346,7 +1346,7 @@ static void __exit qlogic_ib_cleanup(void)
 	qib_dev_cleanup();
 }
 
-module_exit(qlogic_ib_cleanup);
+module_exit(qib_ib_cleanup);
 
 /* this can only be called after a successful initialization */
 static void cleanup_device_data(struct qib_devdata *dd)
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index edad991d60e..22c720e5740 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -1028,7 +1028,7 @@ static int set_pkeys(struct qib_devdata *dd, u8 port, u16 *pkeys)
 
 		event.event = IB_EVENT_PKEY_CHANGE;
 		event.device = &dd->verbs_dev.ibdev;
-		event.element.port_num = 1;
+		event.element.port_num = port;
 		ib_dispatch_event(&event);
 	}
 	return 0;
diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c
index 0cad0c40d74..7fcc150d603 100644
--- a/drivers/infiniband/hw/qib/qib_qp.c
+++ b/drivers/infiniband/hw/qib/qib_qp.c
@@ -985,7 +985,8 @@ struct ib_qp *qib_create_qp(struct ib_pd *ibpd,
 	struct ib_qp *ret;
 
 	if (init_attr->cap.max_send_sge > ib_qib_max_sges ||
-	    init_attr->cap.max_send_wr > ib_qib_max_qp_wrs) {
+	    init_attr->cap.max_send_wr > ib_qib_max_qp_wrs ||
+	    init_attr->create_flags) {
 		ret = ERR_PTR(-EINVAL);
 		goto bail;
 	}
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index d48d2c0a2e3..53bd6a2d9cd 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -466,6 +466,9 @@ struct ib_qp *usnic_ib_create_qp(struct ib_pd *pd,
 	ucontext = to_uucontext(pd->uobject->context);
 	us_ibdev = to_usdev(pd->device);
 
+	if (init_attr->create_flags)
+		return ERR_PTR(-EINVAL);
+
 	err = ib_copy_from_udata(&cmd, udata, sizeof(cmd));
 	if (err) {
 		usnic_err("%s: cannot copy udata for create_qp\n",
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c
index d135ad90d91..3a4288e0fba 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c
@@ -1,3 +1,21 @@
+/*
+ * Copyright (c) 2014, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/slab.h>
diff --git a/drivers/infiniband/ulp/Makefile b/drivers/infiniband/ulp/Makefile
new file mode 100644
index 00000000000..f3c7dcf0309
--- /dev/null
+++ b/drivers/infiniband/ulp/Makefile
@@ -0,0 +1,5 @@
+obj-$(CONFIG_INFINIBAND_IPOIB)		+= ipoib/
+obj-$(CONFIG_INFINIBAND_SRP)		+= srp/
+obj-$(CONFIG_INFINIBAND_SRPT)		+= srpt/
+obj-$(CONFIG_INFINIBAND_ISER)		+= iser/
+obj-$(CONFIG_INFINIBAND_ISERT)		+= isert/
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 1377f85911c..933efcea0d0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1030,10 +1030,20 @@ static struct ib_qp *ipoib_cm_create_tx_qp(struct net_device *dev, struct ipoib_
 		.cap.max_send_sge	= 1,
 		.sq_sig_type		= IB_SIGNAL_ALL_WR,
 		.qp_type		= IB_QPT_RC,
-		.qp_context		= tx
+		.qp_context		= tx,
+		.create_flags		= IB_QP_CREATE_USE_GFP_NOIO
 	};
 
-	return ib_create_qp(priv->pd, &attr);
+	struct ib_qp *tx_qp;
+
+	tx_qp = ib_create_qp(priv->pd, &attr);
+	if (PTR_ERR(tx_qp) == -EINVAL) {
+		ipoib_warn(priv, "can't use GFP_NOIO for QPs on device %s, using GFP_KERNEL\n",
+			   priv->ca->name);
+		attr.create_flags &= ~IB_QP_CREATE_USE_GFP_NOIO;
+		tx_qp = ib_create_qp(priv->pd, &attr);
+	}
+	return tx_qp;
 }
 
 static int ipoib_cm_send_req(struct net_device *dev,
@@ -1104,12 +1114,14 @@ static int ipoib_cm_tx_init(struct ipoib_cm_tx *p, u32 qpn,
 	struct ipoib_dev_priv *priv = netdev_priv(p->dev);
 	int ret;
 
-	p->tx_ring = vzalloc(ipoib_sendq_size * sizeof *p->tx_ring);
+	p->tx_ring = __vmalloc(ipoib_sendq_size * sizeof *p->tx_ring,
+			       GFP_NOIO, PAGE_KERNEL);
 	if (!p->tx_ring) {
 		ipoib_warn(priv, "failed to allocate tx ring\n");
 		ret = -ENOMEM;
 		goto err_tx;
 	}
+	memset(p->tx_ring, 0, ipoib_sendq_size * sizeof *p->tx_ring);
 
 	p->qp = ipoib_cm_create_tx_qp(p->dev, p);
 	if (IS_ERR(p->qp)) {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
index c4b3940845e..078cadd6c79 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
@@ -105,5 +105,5 @@ static const struct ethtool_ops ipoib_ethtool_ops = {
 
 void ipoib_set_ethtool_ops(struct net_device *dev)
 {
-	SET_ETHTOOL_OPS(dev, &ipoib_ethtool_ops);
+	dev->ethtool_ops = &ipoib_ethtool_ops;
 }
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 25f195ef44b..eb7973957a6 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -99,6 +99,7 @@ MODULE_PARM_DESC(pi_enable, "Enable T10-PI offload support (default:disabled)");
 module_param_named(pi_guard, iser_pi_guard, int, 0644);
 MODULE_PARM_DESC(pi_guard, "T10-PI guard_type, 0:CRC|1:IP_CSUM (default:CRC)");
 
+static struct workqueue_struct *release_wq;
 struct iser_global ig;
 
 void
@@ -337,24 +338,6 @@ iscsi_iser_conn_create(struct iscsi_cls_session *cls_session, uint32_t conn_idx)
 	return cls_conn;
 }
 
-static void
-iscsi_iser_conn_destroy(struct iscsi_cls_conn *cls_conn)
-{
-	struct iscsi_conn *conn = cls_conn->dd_data;
-	struct iser_conn *ib_conn = conn->dd_data;
-
-	iscsi_conn_teardown(cls_conn);
-	/*
-	 * Userspace will normally call the stop callback and
-	 * already have freed the ib_conn, but if it goofed up then
-	 * we free it here.
-	 */
-	if (ib_conn) {
-		ib_conn->iscsi_conn = NULL;
-		iser_conn_put(ib_conn, 1); /* deref iscsi/ib conn unbinding */
-	}
-}
-
 static int
 iscsi_iser_conn_bind(struct iscsi_cls_session *cls_session,
 		     struct iscsi_cls_conn *cls_conn, uint64_t transport_eph,
@@ -392,29 +375,39 @@ iscsi_iser_conn_bind(struct iscsi_cls_session *cls_session,
 	conn->dd_data = ib_conn;
 	ib_conn->iscsi_conn = conn;
 
-	iser_conn_get(ib_conn); /* ref iscsi/ib conn binding */
 	return 0;
 }
 
+static int
+iscsi_iser_conn_start(struct iscsi_cls_conn *cls_conn)
+{
+	struct iscsi_conn *iscsi_conn;
+	struct iser_conn *ib_conn;
+
+	iscsi_conn = cls_conn->dd_data;
+	ib_conn = iscsi_conn->dd_data;
+	reinit_completion(&ib_conn->stop_completion);
+
+	return iscsi_conn_start(cls_conn);
+}
+
 static void
 iscsi_iser_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
 {
 	struct iscsi_conn *conn = cls_conn->dd_data;
 	struct iser_conn *ib_conn = conn->dd_data;
 
+	iser_dbg("stopping iscsi_conn: %p, ib_conn: %p\n", conn, ib_conn);
+	iscsi_conn_stop(cls_conn, flag);
+
 	/*
 	 * Userspace may have goofed up and not bound the connection or
 	 * might have only partially setup the connection.
 	 */
 	if (ib_conn) {
-		iscsi_conn_stop(cls_conn, flag);
-		/*
-		 * There is no unbind event so the stop callback
-		 * must release the ref from the bind.
-		 */
-		iser_conn_put(ib_conn, 1); /* deref iscsi/ib conn unbinding */
+		conn->dd_data = NULL;
+		complete(&ib_conn->stop_completion);
 	}
-	conn->dd_data = NULL;
 }
 
 static void iscsi_iser_session_destroy(struct iscsi_cls_session *cls_session)
@@ -515,28 +508,28 @@ iscsi_iser_set_param(struct iscsi_cls_conn *cls_conn,
 	case ISCSI_PARAM_HDRDGST_EN:
 		sscanf(buf, "%d", &value);
 		if (value) {
-			iser_err("DataDigest wasn't negotiated to None");
+			iser_err("DataDigest wasn't negotiated to None\n");
 			return -EPROTO;
 		}
 		break;
 	case ISCSI_PARAM_DATADGST_EN:
 		sscanf(buf, "%d", &value);
 		if (value) {
-			iser_err("DataDigest wasn't negotiated to None");
+			iser_err("DataDigest wasn't negotiated to None\n");
 			return -EPROTO;
 		}
 		break;
 	case ISCSI_PARAM_IFMARKER_EN:
 		sscanf(buf, "%d", &value);
 		if (value) {
-			iser_err("IFMarker wasn't negotiated to No");
+			iser_err("IFMarker wasn't negotiated to No\n");
 			return -EPROTO;
 		}
 		break;
 	case ISCSI_PARAM_OFMARKER_EN:
 		sscanf(buf, "%d", &value);
 		if (value) {
-			iser_err("OFMarker wasn't negotiated to No");
+			iser_err("OFMarker wasn't negotiated to No\n");
 			return -EPROTO;
 		}
 		break;
@@ -652,19 +645,20 @@ iscsi_iser_ep_disconnect(struct iscsi_endpoint *ep)
 	struct iser_conn *ib_conn;
 
 	ib_conn = ep->dd_data;
-	if (ib_conn->iscsi_conn)
-		/*
-		 * Must suspend xmit path if the ep is bound to the
-		 * iscsi_conn, so we know we are not accessing the ib_conn
-		 * when we free it.
-		 *
-		 * This may not be bound if the ep poll failed.
-		 */
-		iscsi_suspend_tx(ib_conn->iscsi_conn);
-
-
-	iser_info("ib conn %p state %d\n", ib_conn, ib_conn->state);
+	iser_info("ep %p ib conn %p state %d\n", ep, ib_conn, ib_conn->state);
 	iser_conn_terminate(ib_conn);
+
+	/*
+	 * if iser_conn and iscsi_conn are bound, we must wait iscsi_conn_stop
+	 * call and ISER_CONN_DOWN state before freeing the iser resources.
+	 * otherwise we are safe to free resources immediately.
+	 */
+	if (ib_conn->iscsi_conn) {
+		INIT_WORK(&ib_conn->release_work, iser_release_work);
+		queue_work(release_wq, &ib_conn->release_work);
+	} else {
+		iser_conn_release(ib_conn);
+	}
 }
 
 static umode_t iser_attr_is_visible(int param_type, int param)
@@ -748,13 +742,13 @@ static struct iscsi_transport iscsi_iser_transport = {
 	/* connection management */
 	.create_conn            = iscsi_iser_conn_create,
 	.bind_conn              = iscsi_iser_conn_bind,
-	.destroy_conn           = iscsi_iser_conn_destroy,
+	.destroy_conn           = iscsi_conn_teardown,
 	.attr_is_visible	= iser_attr_is_visible,
 	.set_param              = iscsi_iser_set_param,
 	.get_conn_param		= iscsi_conn_get_param,
 	.get_ep_param		= iscsi_iser_get_ep_param,
 	.get_session_param	= iscsi_session_get_param,
-	.start_conn             = iscsi_conn_start,
+	.start_conn             = iscsi_iser_conn_start,
 	.stop_conn              = iscsi_iser_conn_stop,
 	/* iscsi host params */
 	.get_host_param		= iscsi_host_get_param,
@@ -801,6 +795,12 @@ static int __init iser_init(void)
 	mutex_init(&ig.connlist_mutex);
 	INIT_LIST_HEAD(&ig.connlist);
 
+	release_wq = alloc_workqueue("release workqueue", 0, 0);
+	if (!release_wq) {
+		iser_err("failed to allocate release workqueue\n");
+		return -ENOMEM;
+	}
+
 	iscsi_iser_scsi_transport = iscsi_register_transport(
 							&iscsi_iser_transport);
 	if (!iscsi_iser_scsi_transport) {
@@ -819,7 +819,24 @@ register_transport_failure:
 
 static void __exit iser_exit(void)
 {
+	struct iser_conn *ib_conn, *n;
+	int connlist_empty;
+
 	iser_dbg("Removing iSER datamover...\n");
+	destroy_workqueue(release_wq);
+
+	mutex_lock(&ig.connlist_mutex);
+	connlist_empty = list_empty(&ig.connlist);
+	mutex_unlock(&ig.connlist_mutex);
+
+	if (!connlist_empty) {
+		iser_err("Error cleanup stage completed but we still have iser "
+			 "connections, destroying them anyway.\n");
+		list_for_each_entry_safe(ib_conn, n, &ig.connlist, conn_list) {
+			iser_conn_release(ib_conn);
+		}
+	}
+
 	iscsi_unregister_transport(&iscsi_iser_transport);
 	kmem_cache_destroy(ig.desc_cache);
 }
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 324129f80d4..97cd385bf7f 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -69,7 +69,7 @@
 
 #define DRV_NAME	"iser"
 #define PFX		DRV_NAME ": "
-#define DRV_VER		"1.3"
+#define DRV_VER		"1.4"
 
 #define iser_dbg(fmt, arg...)				\
 	do {						\
@@ -333,6 +333,8 @@ struct iser_conn {
 	int                          post_recv_buf_count; /* posted rx count  */
 	atomic_t                     post_send_buf_count; /* posted tx count   */
 	char 			     name[ISER_OBJECT_NAME_SIZE];
+	struct work_struct	     release_work;
+	struct completion	     stop_completion;
 	struct list_head	     conn_list;       /* entry in ig conn list */
 
 	char  			     *login_buf;
@@ -417,12 +419,12 @@ void iscsi_iser_recv(struct iscsi_conn *conn,
 
 void iser_conn_init(struct iser_conn *ib_conn);
 
-void iser_conn_get(struct iser_conn *ib_conn);
-
-int iser_conn_put(struct iser_conn *ib_conn, int destroy_cma_id_allowed);
+void iser_conn_release(struct iser_conn *ib_conn);
 
 void iser_conn_terminate(struct iser_conn *ib_conn);
 
+void iser_release_work(struct work_struct *work);
+
 void iser_rcv_completion(struct iser_rx_desc *desc,
 			 unsigned long    dto_xfer_len,
 			struct iser_conn *ib_conn);
diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c
index 2e2d903db83..8d44a406063 100644
--- a/drivers/infiniband/ulp/iser/iser_initiator.c
+++ b/drivers/infiniband/ulp/iser/iser_initiator.c
@@ -41,11 +41,11 @@
 #include "iscsi_iser.h"
 
 /* Register user buffer memory and initialize passive rdma
- *  dto descriptor. Total data size is stored in
- *  iser_task->data[ISER_DIR_IN].data_len
+ *  dto descriptor. Data size is stored in
+ *  task->data[ISER_DIR_IN].data_len, Protection size
+ *  os stored in task->prot[ISER_DIR_IN].data_len
  */
-static int iser_prepare_read_cmd(struct iscsi_task *task,
-				 unsigned int edtl)
+static int iser_prepare_read_cmd(struct iscsi_task *task)
 
 {
 	struct iscsi_iser_task *iser_task = task->dd_data;
@@ -73,14 +73,6 @@ static int iser_prepare_read_cmd(struct iscsi_task *task,
 			return err;
 	}
 
-	if (edtl > iser_task->data[ISER_DIR_IN].data_len) {
-		iser_err("Total data length: %ld, less than EDTL: "
-			 "%d, in READ cmd BHS itt: %d, conn: 0x%p\n",
-			 iser_task->data[ISER_DIR_IN].data_len, edtl,
-			 task->itt, iser_task->ib_conn);
-		return -EINVAL;
-	}
-
 	err = device->iser_reg_rdma_mem(iser_task, ISER_DIR_IN);
 	if (err) {
 		iser_err("Failed to set up Data-IN RDMA\n");
@@ -100,8 +92,9 @@ static int iser_prepare_read_cmd(struct iscsi_task *task,
 }
 
 /* Register user buffer memory and initialize passive rdma
- *  dto descriptor. Total data size is stored in
- *  task->data[ISER_DIR_OUT].data_len
+ *  dto descriptor. Data size is stored in
+ *  task->data[ISER_DIR_OUT].data_len, Protection size
+ *  is stored at task->prot[ISER_DIR_OUT].data_len
  */
 static int
 iser_prepare_write_cmd(struct iscsi_task *task,
@@ -135,14 +128,6 @@ iser_prepare_write_cmd(struct iscsi_task *task,
 			return err;
 	}
 
-	if (edtl > iser_task->data[ISER_DIR_OUT].data_len) {
-		iser_err("Total data length: %ld, less than EDTL: %d, "
-			 "in WRITE cmd BHS itt: %d, conn: 0x%p\n",
-			 iser_task->data[ISER_DIR_OUT].data_len,
-			 edtl, task->itt, task->conn);
-		return -EINVAL;
-	}
-
 	err = device->iser_reg_rdma_mem(iser_task, ISER_DIR_OUT);
 	if (err != 0) {
 		iser_err("Failed to register write cmd RDMA mem\n");
@@ -417,11 +402,12 @@ int iser_send_command(struct iscsi_conn *conn,
 	if (scsi_prot_sg_count(sc)) {
 		prot_buf->buf  = scsi_prot_sglist(sc);
 		prot_buf->size = scsi_prot_sg_count(sc);
-		prot_buf->data_len = sc->prot_sdb->length;
+		prot_buf->data_len = data_buf->data_len >>
+				     ilog2(sc->device->sector_size) * 8;
 	}
 
 	if (hdr->flags & ISCSI_FLAG_CMD_READ) {
-		err = iser_prepare_read_cmd(task, edtl);
+		err = iser_prepare_read_cmd(task);
 		if (err)
 			goto send_command_error;
 	}
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 32849f2becd..ea01075f9f9 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -581,14 +581,30 @@ static int iser_conn_state_comp_exch(struct iser_conn *ib_conn,
 	return ret;
 }
 
+void iser_release_work(struct work_struct *work)
+{
+	struct iser_conn *ib_conn;
+
+	ib_conn = container_of(work, struct iser_conn, release_work);
+
+	/* wait for .conn_stop callback */
+	wait_for_completion(&ib_conn->stop_completion);
+
+	/* wait for the qp`s post send and post receive buffers to empty */
+	wait_event_interruptible(ib_conn->wait,
+				 ib_conn->state == ISER_CONN_DOWN);
+
+	iser_conn_release(ib_conn);
+}
+
 /**
  * Frees all conn objects and deallocs conn descriptor
  */
-static void iser_conn_release(struct iser_conn *ib_conn, int can_destroy_id)
+void iser_conn_release(struct iser_conn *ib_conn)
 {
 	struct iser_device  *device = ib_conn->device;
 
-	BUG_ON(ib_conn->state != ISER_CONN_DOWN);
+	BUG_ON(ib_conn->state == ISER_CONN_UP);
 
 	mutex_lock(&ig.connlist_mutex);
 	list_del(&ib_conn->conn_list);
@@ -600,27 +616,13 @@ static void iser_conn_release(struct iser_conn *ib_conn, int can_destroy_id)
 	if (device != NULL)
 		iser_device_try_release(device);
 	/* if cma handler context, the caller actually destroy the id */
-	if (ib_conn->cma_id != NULL && can_destroy_id) {
+	if (ib_conn->cma_id != NULL) {
 		rdma_destroy_id(ib_conn->cma_id);
 		ib_conn->cma_id = NULL;
 	}
 	iscsi_destroy_endpoint(ib_conn->ep);
 }
 
-void iser_conn_get(struct iser_conn *ib_conn)
-{
-	atomic_inc(&ib_conn->refcount);
-}
-
-int iser_conn_put(struct iser_conn *ib_conn, int can_destroy_id)
-{
-	if (atomic_dec_and_test(&ib_conn->refcount)) {
-		iser_conn_release(ib_conn, can_destroy_id);
-		return 1;
-	}
-	return 0;
-}
-
 /**
  * triggers start of the disconnect procedures and wait for them to be done
  */
@@ -638,24 +640,19 @@ void iser_conn_terminate(struct iser_conn *ib_conn)
 	if (err)
 		iser_err("Failed to disconnect, conn: 0x%p err %d\n",
 			 ib_conn,err);
-
-	wait_event_interruptible(ib_conn->wait,
-				 ib_conn->state == ISER_CONN_DOWN);
-
-	iser_conn_put(ib_conn, 1); /* deref ib conn deallocate */
 }
 
-static int iser_connect_error(struct rdma_cm_id *cma_id)
+static void iser_connect_error(struct rdma_cm_id *cma_id)
 {
 	struct iser_conn *ib_conn;
+
 	ib_conn = (struct iser_conn *)cma_id->context;
 
 	ib_conn->state = ISER_CONN_DOWN;
 	wake_up_interruptible(&ib_conn->wait);
-	return iser_conn_put(ib_conn, 0); /* deref ib conn's cma id */
 }
 
-static int iser_addr_handler(struct rdma_cm_id *cma_id)
+static void iser_addr_handler(struct rdma_cm_id *cma_id)
 {
 	struct iser_device *device;
 	struct iser_conn   *ib_conn;
@@ -664,7 +661,8 @@ static int iser_addr_handler(struct rdma_cm_id *cma_id)
 	device = iser_device_find_by_ib_device(cma_id);
 	if (!device) {
 		iser_err("device lookup/creation failed\n");
-		return iser_connect_error(cma_id);
+		iser_connect_error(cma_id);
+		return;
 	}
 
 	ib_conn = (struct iser_conn *)cma_id->context;
@@ -686,13 +684,12 @@ static int iser_addr_handler(struct rdma_cm_id *cma_id)
 	ret = rdma_resolve_route(cma_id, 1000);
 	if (ret) {
 		iser_err("resolve route failed: %d\n", ret);
-		return iser_connect_error(cma_id);
+		iser_connect_error(cma_id);
+		return;
 	}
-
-	return 0;
 }
 
-static int iser_route_handler(struct rdma_cm_id *cma_id)
+static void iser_route_handler(struct rdma_cm_id *cma_id)
 {
 	struct rdma_conn_param conn_param;
 	int    ret;
@@ -720,9 +717,9 @@ static int iser_route_handler(struct rdma_cm_id *cma_id)
 		goto failure;
 	}
 
-	return 0;
+	return;
 failure:
-	return iser_connect_error(cma_id);
+	iser_connect_error(cma_id);
 }
 
 static void iser_connected_handler(struct rdma_cm_id *cma_id)
@@ -735,14 +732,13 @@ static void iser_connected_handler(struct rdma_cm_id *cma_id)
 	iser_info("remote qpn:%x my qpn:%x\n", attr.dest_qp_num, cma_id->qp->qp_num);
 
 	ib_conn = (struct iser_conn *)cma_id->context;
-	ib_conn->state = ISER_CONN_UP;
-	wake_up_interruptible(&ib_conn->wait);
+	if (iser_conn_state_comp_exch(ib_conn, ISER_CONN_PENDING, ISER_CONN_UP))
+		wake_up_interruptible(&ib_conn->wait);
 }
 
-static int iser_disconnected_handler(struct rdma_cm_id *cma_id)
+static void iser_disconnected_handler(struct rdma_cm_id *cma_id)
 {
 	struct iser_conn *ib_conn;
-	int ret;
 
 	ib_conn = (struct iser_conn *)cma_id->context;
 
@@ -762,24 +758,19 @@ static int iser_disconnected_handler(struct rdma_cm_id *cma_id)
 		ib_conn->state = ISER_CONN_DOWN;
 		wake_up_interruptible(&ib_conn->wait);
 	}
-
-	ret = iser_conn_put(ib_conn, 0); /* deref ib conn's cma id */
-	return ret;
 }
 
 static int iser_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
-	int ret = 0;
-
 	iser_info("event %d status %d conn %p id %p\n",
 		  event->event, event->status, cma_id->context, cma_id);
 
 	switch (event->event) {
 	case RDMA_CM_EVENT_ADDR_RESOLVED:
-		ret = iser_addr_handler(cma_id);
+		iser_addr_handler(cma_id);
 		break;
 	case RDMA_CM_EVENT_ROUTE_RESOLVED:
-		ret = iser_route_handler(cma_id);
+		iser_route_handler(cma_id);
 		break;
 	case RDMA_CM_EVENT_ESTABLISHED:
 		iser_connected_handler(cma_id);
@@ -789,18 +780,18 @@ static int iser_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *eve
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	case RDMA_CM_EVENT_UNREACHABLE:
 	case RDMA_CM_EVENT_REJECTED:
-		ret = iser_connect_error(cma_id);
+		iser_connect_error(cma_id);
 		break;
 	case RDMA_CM_EVENT_DISCONNECTED:
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
 	case RDMA_CM_EVENT_ADDR_CHANGE:
-		ret = iser_disconnected_handler(cma_id);
+		iser_disconnected_handler(cma_id);
 		break;
 	default:
 		iser_err("Unexpected RDMA CM event (%d)\n", event->event);
 		break;
 	}
-	return ret;
+	return 0;
 }
 
 void iser_conn_init(struct iser_conn *ib_conn)
@@ -809,7 +800,7 @@ void iser_conn_init(struct iser_conn *ib_conn)
 	init_waitqueue_head(&ib_conn->wait);
 	ib_conn->post_recv_buf_count = 0;
 	atomic_set(&ib_conn->post_send_buf_count, 0);
-	atomic_set(&ib_conn->refcount, 1); /* ref ib conn allocation */
+	init_completion(&ib_conn->stop_completion);
 	INIT_LIST_HEAD(&ib_conn->conn_list);
 	spin_lock_init(&ib_conn->lock);
 }
@@ -837,7 +828,6 @@ int iser_connect(struct iser_conn   *ib_conn,
 
 	ib_conn->state = ISER_CONN_PENDING;
 
-	iser_conn_get(ib_conn); /* ref ib conn's cma id */
 	ib_conn->cma_id = rdma_create_id(iser_cma_handler,
 					     (void *)ib_conn,
 					     RDMA_PS_TCP, IB_QPT_RC);
@@ -874,9 +864,8 @@ id_failure:
 	ib_conn->cma_id = NULL;
 addr_failure:
 	ib_conn->state = ISER_CONN_DOWN;
-	iser_conn_put(ib_conn, 1); /* deref ib conn's cma id */
 connect_failure:
-	iser_conn_put(ib_conn, 1); /* deref ib conn deallocate */
+	iser_conn_release(ib_conn);
 	return err;
 }
 
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index b9d647468b9..d4c7928a0f3 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -663,8 +663,9 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 
 	pi_support = np->tpg_np->tpg->tpg_attrib.t10_pi;
 	if (pi_support && !device->pi_capable) {
-		pr_err("Protection information requested but not supported\n");
-		ret = -EINVAL;
+		pr_err("Protection information requested but not supported, "
+		       "rejecting connect request\n");
+		ret = rdma_reject(cma_id, NULL, 0);
 		goto out_mr;
 	}
 
@@ -787,14 +788,12 @@ isert_disconnect_work(struct work_struct *work)
 		isert_put_conn(isert_conn);
 		return;
 	}
-	if (!isert_conn->logout_posted) {
-		pr_debug("Calling rdma_disconnect for !logout_posted from"
-			 " isert_disconnect_work\n");
+
+	if (isert_conn->disconnect) {
+		/* Send DREQ/DREP towards our initiator */
 		rdma_disconnect(isert_conn->conn_cm_id);
-		mutex_unlock(&isert_conn->conn_mutex);
-		iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
-		goto wake_up;
 	}
+
 	mutex_unlock(&isert_conn->conn_mutex);
 
 wake_up:
@@ -803,10 +802,11 @@ wake_up:
 }
 
 static void
-isert_disconnected_handler(struct rdma_cm_id *cma_id)
+isert_disconnected_handler(struct rdma_cm_id *cma_id, bool disconnect)
 {
 	struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context;
 
+	isert_conn->disconnect = disconnect;
 	INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work);
 	schedule_work(&isert_conn->conn_logout_work);
 }
@@ -815,29 +815,28 @@ static int
 isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	int ret = 0;
+	bool disconnect = false;
 
 	pr_debug("isert_cma_handler: event %d status %d conn %p id %p\n",
 		 event->event, event->status, cma_id->context, cma_id);
 
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
-		pr_debug("RDMA_CM_EVENT_CONNECT_REQUEST: >>>>>>>>>>>>>>>\n");
 		ret = isert_connect_request(cma_id, event);
 		break;
 	case RDMA_CM_EVENT_ESTABLISHED:
-		pr_debug("RDMA_CM_EVENT_ESTABLISHED >>>>>>>>>>>>>>\n");
 		isert_connected_handler(cma_id);
 		break;
-	case RDMA_CM_EVENT_DISCONNECTED:
-		pr_debug("RDMA_CM_EVENT_DISCONNECTED: >>>>>>>>>>>>>>\n");
-		isert_disconnected_handler(cma_id);
-		break;
-	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_ADDR_CHANGE:    /* FALLTHRU */
+	case RDMA_CM_EVENT_DISCONNECTED:   /* FALLTHRU */
+	case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
+		disconnect = true;
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:  /* FALLTHRU */
+		isert_disconnected_handler(cma_id, disconnect);
 		break;
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	default:
-		pr_err("Unknown RDMA CMA event: %d\n", event->event);
+		pr_err("Unhandled RDMA CMA event: %d\n", event->event);
 		break;
 	}
 
@@ -1054,7 +1053,9 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
 	}
 	if (!login->login_failed) {
 		if (login->login_complete) {
-			if (isert_conn->conn_device->use_fastreg) {
+			if (!conn->sess->sess_ops->SessionType &&
+			    isert_conn->conn_device->use_fastreg) {
+				/* Normal Session and fastreg is used */
 				u8 pi_support = login->np->tpg_np->tpg->tpg_attrib.t10_pi;
 
 				ret = isert_conn_create_fastreg_pool(isert_conn,
@@ -1824,11 +1825,8 @@ isert_do_control_comp(struct work_struct *work)
 		break;
 	case ISTATE_SEND_LOGOUTRSP:
 		pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n");
-		/*
-		 * Call atomic_dec(&isert_conn->post_send_buf_count)
-		 * from isert_wait_conn()
-		 */
-		isert_conn->logout_posted = true;
+
+		atomic_dec(&isert_conn->post_send_buf_count);
 		iscsit_logout_post_handler(cmd, cmd->conn);
 		break;
 	case ISTATE_SEND_TEXTRSP:
@@ -2034,6 +2032,8 @@ isert_cq_rx_comp_err(struct isert_conn *isert_conn)
 	isert_conn->state = ISER_CONN_DOWN;
 	mutex_unlock(&isert_conn->conn_mutex);
 
+	iscsit_cause_connection_reinstatement(isert_conn->conn, 0);
+
 	complete(&isert_conn->conn_wait_comp_err);
 }
 
@@ -2320,7 +2320,7 @@ isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn)
 	int rc;
 
 	isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc);
-	rc = iscsit_build_text_rsp(cmd, conn, hdr);
+	rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_INFINIBAND);
 	if (rc < 0)
 		return rc;
 
@@ -3156,9 +3156,14 @@ accept_wait:
 		return -ENODEV;
 
 	spin_lock_bh(&np->np_thread_lock);
-	if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
+	if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) {
 		spin_unlock_bh(&np->np_thread_lock);
-		pr_debug("ISCSI_NP_THREAD_RESET for isert_accept_np\n");
+		pr_debug("np_thread_state %d for isert_accept_np\n",
+			 np->np_thread_state);
+		/**
+		 * No point in stalling here when np_thread
+		 * is in state RESET/SHUTDOWN/EXIT - bail
+		 **/
 		return -ENODEV;
 	}
 	spin_unlock_bh(&np->np_thread_lock);
@@ -3208,15 +3213,9 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	struct isert_conn *isert_conn = conn->context;
 
 	pr_debug("isert_wait_conn: Starting \n");
-	/*
-	 * Decrement post_send_buf_count for special case when called
-	 * from isert_do_control_comp() -> iscsit_logout_post_handler()
-	 */
-	mutex_lock(&isert_conn->conn_mutex);
-	if (isert_conn->logout_posted)
-		atomic_dec(&isert_conn->post_send_buf_count);
 
-	if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) {
+	mutex_lock(&isert_conn->conn_mutex);
+	if (isert_conn->conn_cm_id) {
 		pr_debug("Calling rdma_disconnect from isert_wait_conn\n");
 		rdma_disconnect(isert_conn->conn_cm_id);
 	}
@@ -3293,6 +3292,7 @@ destroy_rx_wq:
 
 static void __exit isert_exit(void)
 {
+	flush_scheduled_work();
 	destroy_workqueue(isert_comp_wq);
 	destroy_workqueue(isert_rx_wq);
 	iscsit_unregister_transport(&iser_target_transport);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index da6612e6800..04f51f7bf61 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -116,7 +116,6 @@ struct isert_device;
 
 struct isert_conn {
 	enum iser_conn_state	state;
-	bool			logout_posted;
 	int			post_recv_buf_count;
 	atomic_t		post_send_buf_count;
 	u32			responder_resources;
@@ -151,6 +150,7 @@ struct isert_conn {
 #define ISERT_COMP_BATCH_COUNT	8
 	int			conn_comp_batch;
 	struct llist_head	conn_comp_llist;
+	bool                    disconnect;
 };
 
 #define ISERT_MAX_CQ 64
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 66a908bf3fb..e3c2c5b4297 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -30,7 +30,7 @@
  * SOFTWARE.
  */
 
-#define pr_fmt(fmt) PFX fmt
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/module.h>
 #include <linux/init.h>
@@ -66,6 +66,8 @@ static unsigned int srp_sg_tablesize;
 static unsigned int cmd_sg_entries;
 static unsigned int indirect_sg_entries;
 static bool allow_ext_sg;
+static bool prefer_fr;
+static bool register_always;
 static int topspin_workarounds = 1;
 
 module_param(srp_sg_tablesize, uint, 0444);
@@ -87,6 +89,14 @@ module_param(topspin_workarounds, int, 0444);
 MODULE_PARM_DESC(topspin_workarounds,
 		 "Enable workarounds for Topspin/Cisco SRP target bugs if != 0");
 
+module_param(prefer_fr, bool, 0444);
+MODULE_PARM_DESC(prefer_fr,
+"Whether to use fast registration if both FMR and fast registration are supported");
+
+module_param(register_always, bool, 0444);
+MODULE_PARM_DESC(register_always,
+		 "Use memory registration even for contiguous memory regions");
+
 static struct kernel_param_ops srp_tmo_ops;
 
 static int srp_reconnect_delay = 10;
@@ -288,28 +298,174 @@ static int srp_new_cm_id(struct srp_target_port *target)
 	return 0;
 }
 
+static struct ib_fmr_pool *srp_alloc_fmr_pool(struct srp_target_port *target)
+{
+	struct srp_device *dev = target->srp_host->srp_dev;
+	struct ib_fmr_pool_param fmr_param;
+
+	memset(&fmr_param, 0, sizeof(fmr_param));
+	fmr_param.pool_size	    = target->scsi_host->can_queue;
+	fmr_param.dirty_watermark   = fmr_param.pool_size / 4;
+	fmr_param.cache		    = 1;
+	fmr_param.max_pages_per_fmr = dev->max_pages_per_mr;
+	fmr_param.page_shift	    = ilog2(dev->mr_page_size);
+	fmr_param.access	    = (IB_ACCESS_LOCAL_WRITE |
+				       IB_ACCESS_REMOTE_WRITE |
+				       IB_ACCESS_REMOTE_READ);
+
+	return ib_create_fmr_pool(dev->pd, &fmr_param);
+}
+
+/**
+ * srp_destroy_fr_pool() - free the resources owned by a pool
+ * @pool: Fast registration pool to be destroyed.
+ */
+static void srp_destroy_fr_pool(struct srp_fr_pool *pool)
+{
+	int i;
+	struct srp_fr_desc *d;
+
+	if (!pool)
+		return;
+
+	for (i = 0, d = &pool->desc[0]; i < pool->size; i++, d++) {
+		if (d->frpl)
+			ib_free_fast_reg_page_list(d->frpl);
+		if (d->mr)
+			ib_dereg_mr(d->mr);
+	}
+	kfree(pool);
+}
+
+/**
+ * srp_create_fr_pool() - allocate and initialize a pool for fast registration
+ * @device:            IB device to allocate fast registration descriptors for.
+ * @pd:                Protection domain associated with the FR descriptors.
+ * @pool_size:         Number of descriptors to allocate.
+ * @max_page_list_len: Maximum fast registration work request page list length.
+ */
+static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device,
+					      struct ib_pd *pd, int pool_size,
+					      int max_page_list_len)
+{
+	struct srp_fr_pool *pool;
+	struct srp_fr_desc *d;
+	struct ib_mr *mr;
+	struct ib_fast_reg_page_list *frpl;
+	int i, ret = -EINVAL;
+
+	if (pool_size <= 0)
+		goto err;
+	ret = -ENOMEM;
+	pool = kzalloc(sizeof(struct srp_fr_pool) +
+		       pool_size * sizeof(struct srp_fr_desc), GFP_KERNEL);
+	if (!pool)
+		goto err;
+	pool->size = pool_size;
+	pool->max_page_list_len = max_page_list_len;
+	spin_lock_init(&pool->lock);
+	INIT_LIST_HEAD(&pool->free_list);
+
+	for (i = 0, d = &pool->desc[0]; i < pool->size; i++, d++) {
+		mr = ib_alloc_fast_reg_mr(pd, max_page_list_len);
+		if (IS_ERR(mr)) {
+			ret = PTR_ERR(mr);
+			goto destroy_pool;
+		}
+		d->mr = mr;
+		frpl = ib_alloc_fast_reg_page_list(device, max_page_list_len);
+		if (IS_ERR(frpl)) {
+			ret = PTR_ERR(frpl);
+			goto destroy_pool;
+		}
+		d->frpl = frpl;
+		list_add_tail(&d->entry, &pool->free_list);
+	}
+
+out:
+	return pool;
+
+destroy_pool:
+	srp_destroy_fr_pool(pool);
+
+err:
+	pool = ERR_PTR(ret);
+	goto out;
+}
+
+/**
+ * srp_fr_pool_get() - obtain a descriptor suitable for fast registration
+ * @pool: Pool to obtain descriptor from.
+ */
+static struct srp_fr_desc *srp_fr_pool_get(struct srp_fr_pool *pool)
+{
+	struct srp_fr_desc *d = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	if (!list_empty(&pool->free_list)) {
+		d = list_first_entry(&pool->free_list, typeof(*d), entry);
+		list_del(&d->entry);
+	}
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	return d;
+}
+
+/**
+ * srp_fr_pool_put() - put an FR descriptor back in the free list
+ * @pool: Pool the descriptor was allocated from.
+ * @desc: Pointer to an array of fast registration descriptor pointers.
+ * @n:    Number of descriptors to put back.
+ *
+ * Note: The caller must already have queued an invalidation request for
+ * desc->mr->rkey before calling this function.
+ */
+static void srp_fr_pool_put(struct srp_fr_pool *pool, struct srp_fr_desc **desc,
+			    int n)
+{
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	for (i = 0; i < n; i++)
+		list_add(&desc[i]->entry, &pool->free_list);
+	spin_unlock_irqrestore(&pool->lock, flags);
+}
+
+static struct srp_fr_pool *srp_alloc_fr_pool(struct srp_target_port *target)
+{
+	struct srp_device *dev = target->srp_host->srp_dev;
+
+	return srp_create_fr_pool(dev->dev, dev->pd,
+				  target->scsi_host->can_queue,
+				  dev->max_pages_per_mr);
+}
+
 static int srp_create_target_ib(struct srp_target_port *target)
 {
+	struct srp_device *dev = target->srp_host->srp_dev;
 	struct ib_qp_init_attr *init_attr;
 	struct ib_cq *recv_cq, *send_cq;
 	struct ib_qp *qp;
+	struct ib_fmr_pool *fmr_pool = NULL;
+	struct srp_fr_pool *fr_pool = NULL;
+	const int m = 1 + dev->use_fast_reg;
 	int ret;
 
 	init_attr = kzalloc(sizeof *init_attr, GFP_KERNEL);
 	if (!init_attr)
 		return -ENOMEM;
 
-	recv_cq = ib_create_cq(target->srp_host->srp_dev->dev,
-			       srp_recv_completion, NULL, target,
+	recv_cq = ib_create_cq(dev->dev, srp_recv_completion, NULL, target,
 			       target->queue_size, target->comp_vector);
 	if (IS_ERR(recv_cq)) {
 		ret = PTR_ERR(recv_cq);
 		goto err;
 	}
 
-	send_cq = ib_create_cq(target->srp_host->srp_dev->dev,
-			       srp_send_completion, NULL, target,
-			       target->queue_size, target->comp_vector);
+	send_cq = ib_create_cq(dev->dev, srp_send_completion, NULL, target,
+			       m * target->queue_size, target->comp_vector);
 	if (IS_ERR(send_cq)) {
 		ret = PTR_ERR(send_cq);
 		goto err_recv_cq;
@@ -318,16 +474,16 @@ static int srp_create_target_ib(struct srp_target_port *target)
 	ib_req_notify_cq(recv_cq, IB_CQ_NEXT_COMP);
 
 	init_attr->event_handler       = srp_qp_event;
-	init_attr->cap.max_send_wr     = target->queue_size;
+	init_attr->cap.max_send_wr     = m * target->queue_size;
 	init_attr->cap.max_recv_wr     = target->queue_size;
 	init_attr->cap.max_recv_sge    = 1;
 	init_attr->cap.max_send_sge    = 1;
-	init_attr->sq_sig_type         = IB_SIGNAL_ALL_WR;
+	init_attr->sq_sig_type         = IB_SIGNAL_REQ_WR;
 	init_attr->qp_type             = IB_QPT_RC;
 	init_attr->send_cq             = send_cq;
 	init_attr->recv_cq             = recv_cq;
 
-	qp = ib_create_qp(target->srp_host->srp_dev->pd, init_attr);
+	qp = ib_create_qp(dev->pd, init_attr);
 	if (IS_ERR(qp)) {
 		ret = PTR_ERR(qp);
 		goto err_send_cq;
@@ -337,6 +493,30 @@ static int srp_create_target_ib(struct srp_target_port *target)
 	if (ret)
 		goto err_qp;
 
+	if (dev->use_fast_reg && dev->has_fr) {
+		fr_pool = srp_alloc_fr_pool(target);
+		if (IS_ERR(fr_pool)) {
+			ret = PTR_ERR(fr_pool);
+			shost_printk(KERN_WARNING, target->scsi_host, PFX
+				     "FR pool allocation failed (%d)\n", ret);
+			goto err_qp;
+		}
+		if (target->fr_pool)
+			srp_destroy_fr_pool(target->fr_pool);
+		target->fr_pool = fr_pool;
+	} else if (!dev->use_fast_reg && dev->has_fmr) {
+		fmr_pool = srp_alloc_fmr_pool(target);
+		if (IS_ERR(fmr_pool)) {
+			ret = PTR_ERR(fmr_pool);
+			shost_printk(KERN_WARNING, target->scsi_host, PFX
+				     "FMR pool allocation failed (%d)\n", ret);
+			goto err_qp;
+		}
+		if (target->fmr_pool)
+			ib_destroy_fmr_pool(target->fmr_pool);
+		target->fmr_pool = fmr_pool;
+	}
+
 	if (target->qp)
 		ib_destroy_qp(target->qp);
 	if (target->recv_cq)
@@ -371,8 +551,16 @@ err:
  */
 static void srp_free_target_ib(struct srp_target_port *target)
 {
+	struct srp_device *dev = target->srp_host->srp_dev;
 	int i;
 
+	if (dev->use_fast_reg) {
+		if (target->fr_pool)
+			srp_destroy_fr_pool(target->fr_pool);
+	} else {
+		if (target->fmr_pool)
+			ib_destroy_fmr_pool(target->fmr_pool);
+	}
 	ib_destroy_qp(target->qp);
 	ib_destroy_cq(target->send_cq);
 	ib_destroy_cq(target->recv_cq);
@@ -577,7 +765,8 @@ static void srp_disconnect_target(struct srp_target_port *target)
 
 static void srp_free_req_data(struct srp_target_port *target)
 {
-	struct ib_device *ibdev = target->srp_host->srp_dev->dev;
+	struct srp_device *dev = target->srp_host->srp_dev;
+	struct ib_device *ibdev = dev->dev;
 	struct srp_request *req;
 	int i;
 
@@ -586,7 +775,10 @@ static void srp_free_req_data(struct srp_target_port *target)
 
 	for (i = 0; i < target->req_ring_size; ++i) {
 		req = &target->req_ring[i];
-		kfree(req->fmr_list);
+		if (dev->use_fast_reg)
+			kfree(req->fr_list);
+		else
+			kfree(req->fmr_list);
 		kfree(req->map_page);
 		if (req->indirect_dma_addr) {
 			ib_dma_unmap_single(ibdev, req->indirect_dma_addr,
@@ -605,6 +797,7 @@ static int srp_alloc_req_data(struct srp_target_port *target)
 	struct srp_device *srp_dev = target->srp_host->srp_dev;
 	struct ib_device *ibdev = srp_dev->dev;
 	struct srp_request *req;
+	void *mr_list;
 	dma_addr_t dma_addr;
 	int i, ret = -ENOMEM;
 
@@ -617,12 +810,20 @@ static int srp_alloc_req_data(struct srp_target_port *target)
 
 	for (i = 0; i < target->req_ring_size; ++i) {
 		req = &target->req_ring[i];
-		req->fmr_list = kmalloc(target->cmd_sg_cnt * sizeof(void *),
-					GFP_KERNEL);
-		req->map_page = kmalloc(SRP_FMR_SIZE * sizeof(void *),
-					GFP_KERNEL);
+		mr_list = kmalloc(target->cmd_sg_cnt * sizeof(void *),
+				  GFP_KERNEL);
+		if (!mr_list)
+			goto out;
+		if (srp_dev->use_fast_reg)
+			req->fr_list = mr_list;
+		else
+			req->fmr_list = mr_list;
+		req->map_page = kmalloc(srp_dev->max_pages_per_mr *
+					sizeof(void *), GFP_KERNEL);
+		if (!req->map_page)
+			goto out;
 		req->indirect_desc = kmalloc(target->indirect_size, GFP_KERNEL);
-		if (!req->fmr_list || !req->map_page || !req->indirect_desc)
+		if (!req->indirect_desc)
 			goto out;
 
 		dma_addr = ib_dma_map_single(ibdev, req->indirect_desc,
@@ -759,21 +960,56 @@ static int srp_connect_target(struct srp_target_port *target)
 	}
 }
 
+static int srp_inv_rkey(struct srp_target_port *target, u32 rkey)
+{
+	struct ib_send_wr *bad_wr;
+	struct ib_send_wr wr = {
+		.opcode		    = IB_WR_LOCAL_INV,
+		.wr_id		    = LOCAL_INV_WR_ID_MASK,
+		.next		    = NULL,
+		.num_sge	    = 0,
+		.send_flags	    = 0,
+		.ex.invalidate_rkey = rkey,
+	};
+
+	return ib_post_send(target->qp, &wr, &bad_wr);
+}
+
 static void srp_unmap_data(struct scsi_cmnd *scmnd,
 			   struct srp_target_port *target,
 			   struct srp_request *req)
 {
-	struct ib_device *ibdev = target->srp_host->srp_dev->dev;
-	struct ib_pool_fmr **pfmr;
+	struct srp_device *dev = target->srp_host->srp_dev;
+	struct ib_device *ibdev = dev->dev;
+	int i, res;
 
 	if (!scsi_sglist(scmnd) ||
 	    (scmnd->sc_data_direction != DMA_TO_DEVICE &&
 	     scmnd->sc_data_direction != DMA_FROM_DEVICE))
 		return;
 
-	pfmr = req->fmr_list;
-	while (req->nfmr--)
-		ib_fmr_pool_unmap(*pfmr++);
+	if (dev->use_fast_reg) {
+		struct srp_fr_desc **pfr;
+
+		for (i = req->nmdesc, pfr = req->fr_list; i > 0; i--, pfr++) {
+			res = srp_inv_rkey(target, (*pfr)->mr->rkey);
+			if (res < 0) {
+				shost_printk(KERN_ERR, target->scsi_host, PFX
+				  "Queueing INV WR for rkey %#x failed (%d)\n",
+				  (*pfr)->mr->rkey, res);
+				queue_work(system_long_wq,
+					   &target->tl_err_work);
+			}
+		}
+		if (req->nmdesc)
+			srp_fr_pool_put(target->fr_pool, req->fr_list,
+					req->nmdesc);
+	} else {
+		struct ib_pool_fmr **pfmr;
+
+		for (i = req->nmdesc, pfmr = req->fmr_list; i > 0; i--, pfmr++)
+			ib_fmr_pool_unmap(*pfmr);
+	}
 
 	ib_dma_unmap_sg(ibdev, scsi_sglist(scmnd), scsi_sg_count(scmnd),
 			scmnd->sc_data_direction);
@@ -813,6 +1049,10 @@ static struct scsi_cmnd *srp_claim_req(struct srp_target_port *target,
 
 /**
  * srp_free_req() - Unmap data and add request to the free request list.
+ * @target: SRP target port.
+ * @req:    Request to be freed.
+ * @scmnd:  SCSI command associated with @req.
+ * @req_lim_delta: Amount to be added to @target->req_lim.
  */
 static void srp_free_req(struct srp_target_port *target,
 			 struct srp_request *req, struct scsi_cmnd *scmnd,
@@ -882,21 +1122,19 @@ static int srp_rport_reconnect(struct srp_rport *rport)
 	 * callbacks will have finished before a new QP is allocated.
 	 */
 	ret = srp_new_cm_id(target);
-	/*
-	 * Whether or not creating a new CM ID succeeded, create a new
-	 * QP. This guarantees that all completion callback function
-	 * invocations have finished before request resetting starts.
-	 */
-	if (ret == 0)
-		ret = srp_create_target_ib(target);
-	else
-		srp_create_target_ib(target);
 
 	for (i = 0; i < target->req_ring_size; ++i) {
 		struct srp_request *req = &target->req_ring[i];
 		srp_finish_req(target, req, NULL, DID_RESET << 16);
 	}
 
+	/*
+	 * Whether or not creating a new CM ID succeeded, create a new
+	 * QP. This guarantees that all callback functions for the old QP have
+	 * finished before any send requests are posted on the new QP.
+	 */
+	ret += srp_create_target_ib(target);
+
 	INIT_LIST_HEAD(&target->free_tx);
 	for (i = 0; i < target->queue_size; ++i)
 		list_add(&target->tx_ring[i]->list, &target->free_tx);
@@ -928,33 +1166,87 @@ static void srp_map_desc(struct srp_map_state *state, dma_addr_t dma_addr,
 static int srp_map_finish_fmr(struct srp_map_state *state,
 			      struct srp_target_port *target)
 {
-	struct srp_device *dev = target->srp_host->srp_dev;
 	struct ib_pool_fmr *fmr;
 	u64 io_addr = 0;
 
-	if (!state->npages)
-		return 0;
-
-	if (state->npages == 1) {
-		srp_map_desc(state, state->base_dma_addr, state->fmr_len,
-			     target->rkey);
-		state->npages = state->fmr_len = 0;
-		return 0;
-	}
-
-	fmr = ib_fmr_pool_map_phys(dev->fmr_pool, state->pages,
+	fmr = ib_fmr_pool_map_phys(target->fmr_pool, state->pages,
 				   state->npages, io_addr);
 	if (IS_ERR(fmr))
 		return PTR_ERR(fmr);
 
 	*state->next_fmr++ = fmr;
-	state->nfmr++;
+	state->nmdesc++;
+
+	srp_map_desc(state, 0, state->dma_len, fmr->fmr->rkey);
 
-	srp_map_desc(state, 0, state->fmr_len, fmr->fmr->rkey);
-	state->npages = state->fmr_len = 0;
 	return 0;
 }
 
+static int srp_map_finish_fr(struct srp_map_state *state,
+			     struct srp_target_port *target)
+{
+	struct srp_device *dev = target->srp_host->srp_dev;
+	struct ib_send_wr *bad_wr;
+	struct ib_send_wr wr;
+	struct srp_fr_desc *desc;
+	u32 rkey;
+
+	desc = srp_fr_pool_get(target->fr_pool);
+	if (!desc)
+		return -ENOMEM;
+
+	rkey = ib_inc_rkey(desc->mr->rkey);
+	ib_update_fast_reg_key(desc->mr, rkey);
+
+	memcpy(desc->frpl->page_list, state->pages,
+	       sizeof(state->pages[0]) * state->npages);
+
+	memset(&wr, 0, sizeof(wr));
+	wr.opcode = IB_WR_FAST_REG_MR;
+	wr.wr_id = FAST_REG_WR_ID_MASK;
+	wr.wr.fast_reg.iova_start = state->base_dma_addr;
+	wr.wr.fast_reg.page_list = desc->frpl;
+	wr.wr.fast_reg.page_list_len = state->npages;
+	wr.wr.fast_reg.page_shift = ilog2(dev->mr_page_size);
+	wr.wr.fast_reg.length = state->dma_len;
+	wr.wr.fast_reg.access_flags = (IB_ACCESS_LOCAL_WRITE |
+				       IB_ACCESS_REMOTE_READ |
+				       IB_ACCESS_REMOTE_WRITE);
+	wr.wr.fast_reg.rkey = desc->mr->lkey;
+
+	*state->next_fr++ = desc;
+	state->nmdesc++;
+
+	srp_map_desc(state, state->base_dma_addr, state->dma_len,
+		     desc->mr->rkey);
+
+	return ib_post_send(target->qp, &wr, &bad_wr);
+}
+
+static int srp_finish_mapping(struct srp_map_state *state,
+			      struct srp_target_port *target)
+{
+	int ret = 0;
+
+	if (state->npages == 0)
+		return 0;
+
+	if (state->npages == 1 && !register_always)
+		srp_map_desc(state, state->base_dma_addr, state->dma_len,
+			     target->rkey);
+	else
+		ret = target->srp_host->srp_dev->use_fast_reg ?
+			srp_map_finish_fr(state, target) :
+			srp_map_finish_fmr(state, target);
+
+	if (ret == 0) {
+		state->npages = 0;
+		state->dma_len = 0;
+	}
+
+	return ret;
+}
+
 static void srp_map_update_start(struct srp_map_state *state,
 				 struct scatterlist *sg, int sg_index,
 				 dma_addr_t dma_addr)
@@ -967,7 +1259,7 @@ static void srp_map_update_start(struct srp_map_state *state,
 static int srp_map_sg_entry(struct srp_map_state *state,
 			    struct srp_target_port *target,
 			    struct scatterlist *sg, int sg_index,
-			    int use_fmr)
+			    bool use_mr)
 {
 	struct srp_device *dev = target->srp_host->srp_dev;
 	struct ib_device *ibdev = dev->dev;
@@ -979,23 +1271,25 @@ static int srp_map_sg_entry(struct srp_map_state *state,
 	if (!dma_len)
 		return 0;
 
-	if (use_fmr == SRP_MAP_NO_FMR) {
-		/* Once we're in direct map mode for a request, we don't
-		 * go back to FMR mode, so no need to update anything
+	if (!use_mr) {
+		/*
+		 * Once we're in direct map mode for a request, we don't
+		 * go back to FMR or FR mode, so no need to update anything
 		 * other than the descriptor.
 		 */
 		srp_map_desc(state, dma_addr, dma_len, target->rkey);
 		return 0;
 	}
 
-	/* If we start at an offset into the FMR page, don't merge into
-	 * the current FMR. Finish it out, and use the kernel's MR for this
-	 * sg entry. This is to avoid potential bugs on some SRP targets
-	 * that were never quite defined, but went away when the initiator
-	 * avoided using FMR on such page fragments.
+	/*
+	 * Since not all RDMA HW drivers support non-zero page offsets for
+	 * FMR, if we start at an offset into a page, don't merge into the
+	 * current FMR mapping. Finish it out, and use the kernel's MR for
+	 * this sg entry.
 	 */
-	if (dma_addr & ~dev->fmr_page_mask || dma_len > dev->fmr_max_size) {
-		ret = srp_map_finish_fmr(state, target);
+	if ((!dev->use_fast_reg && dma_addr & ~dev->mr_page_mask) ||
+	    dma_len > dev->mr_max_size) {
+		ret = srp_finish_mapping(state, target);
 		if (ret)
 			return ret;
 
@@ -1004,52 +1298,106 @@ static int srp_map_sg_entry(struct srp_map_state *state,
 		return 0;
 	}
 
-	/* If this is the first sg to go into the FMR, save our position.
-	 * We need to know the first unmapped entry, its index, and the
-	 * first unmapped address within that entry to be able to restart
-	 * mapping after an error.
+	/*
+	 * If this is the first sg that will be mapped via FMR or via FR, save
+	 * our position. We need to know the first unmapped entry, its index,
+	 * and the first unmapped address within that entry to be able to
+	 * restart mapping after an error.
 	 */
 	if (!state->unmapped_sg)
 		srp_map_update_start(state, sg, sg_index, dma_addr);
 
 	while (dma_len) {
-		if (state->npages == SRP_FMR_SIZE) {
-			ret = srp_map_finish_fmr(state, target);
+		unsigned offset = dma_addr & ~dev->mr_page_mask;
+		if (state->npages == dev->max_pages_per_mr || offset != 0) {
+			ret = srp_finish_mapping(state, target);
 			if (ret)
 				return ret;
 
 			srp_map_update_start(state, sg, sg_index, dma_addr);
 		}
 
-		len = min_t(unsigned int, dma_len, dev->fmr_page_size);
+		len = min_t(unsigned int, dma_len, dev->mr_page_size - offset);
 
 		if (!state->npages)
 			state->base_dma_addr = dma_addr;
-		state->pages[state->npages++] = dma_addr;
-		state->fmr_len += len;
+		state->pages[state->npages++] = dma_addr & dev->mr_page_mask;
+		state->dma_len += len;
 		dma_addr += len;
 		dma_len -= len;
 	}
 
-	/* If the last entry of the FMR wasn't a full page, then we need to
+	/*
+	 * If the last entry of the MR wasn't a full page, then we need to
 	 * close it out and start a new one -- we can only merge at page
 	 * boundries.
 	 */
 	ret = 0;
-	if (len != dev->fmr_page_size) {
-		ret = srp_map_finish_fmr(state, target);
+	if (len != dev->mr_page_size) {
+		ret = srp_finish_mapping(state, target);
 		if (!ret)
 			srp_map_update_start(state, NULL, 0, 0);
 	}
 	return ret;
 }
 
+static int srp_map_sg(struct srp_map_state *state,
+		      struct srp_target_port *target, struct srp_request *req,
+		      struct scatterlist *scat, int count)
+{
+	struct srp_device *dev = target->srp_host->srp_dev;
+	struct ib_device *ibdev = dev->dev;
+	struct scatterlist *sg;
+	int i;
+	bool use_mr;
+
+	state->desc	= req->indirect_desc;
+	state->pages	= req->map_page;
+	if (dev->use_fast_reg) {
+		state->next_fr = req->fr_list;
+		use_mr = !!target->fr_pool;
+	} else {
+		state->next_fmr = req->fmr_list;
+		use_mr = !!target->fmr_pool;
+	}
+
+	for_each_sg(scat, sg, count, i) {
+		if (srp_map_sg_entry(state, target, sg, i, use_mr)) {
+			/*
+			 * Memory registration failed, so backtrack to the
+			 * first unmapped entry and continue on without using
+			 * memory registration.
+			 */
+			dma_addr_t dma_addr;
+			unsigned int dma_len;
+
+backtrack:
+			sg = state->unmapped_sg;
+			i = state->unmapped_index;
+
+			dma_addr = ib_sg_dma_address(ibdev, sg);
+			dma_len = ib_sg_dma_len(ibdev, sg);
+			dma_len -= (state->unmapped_addr - dma_addr);
+			dma_addr = state->unmapped_addr;
+			use_mr = false;
+			srp_map_desc(state, dma_addr, dma_len, target->rkey);
+		}
+	}
+
+	if (use_mr && srp_finish_mapping(state, target))
+		goto backtrack;
+
+	req->nmdesc = state->nmdesc;
+
+	return 0;
+}
+
 static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target,
 			struct srp_request *req)
 {
-	struct scatterlist *scat, *sg;
+	struct scatterlist *scat;
 	struct srp_cmd *cmd = req->cmd->buf;
-	int i, len, nents, count, use_fmr;
+	int len, nents, count;
 	struct srp_device *dev;
 	struct ib_device *ibdev;
 	struct srp_map_state state;
@@ -1081,7 +1429,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target,
 	fmt = SRP_DATA_DESC_DIRECT;
 	len = sizeof (struct srp_cmd) +	sizeof (struct srp_direct_buf);
 
-	if (count == 1) {
+	if (count == 1 && !register_always) {
 		/*
 		 * The midlayer only generated a single gather/scatter
 		 * entry, or DMA mapping coalesced everything to a
@@ -1094,13 +1442,13 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target,
 		buf->key = cpu_to_be32(target->rkey);
 		buf->len = cpu_to_be32(ib_sg_dma_len(ibdev, scat));
 
-		req->nfmr = 0;
+		req->nmdesc = 0;
 		goto map_complete;
 	}
 
-	/* We have more than one scatter/gather entry, so build our indirect
-	 * descriptor table, trying to merge as many entries with FMR as we
-	 * can.
+	/*
+	 * We have more than one scatter/gather entry, so build our indirect
+	 * descriptor table, trying to merge as many entries as we can.
 	 */
 	indirect_hdr = (void *) cmd->add_data;
 
@@ -1108,35 +1456,7 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target,
 				   target->indirect_size, DMA_TO_DEVICE);
 
 	memset(&state, 0, sizeof(state));
-	state.desc	= req->indirect_desc;
-	state.pages	= req->map_page;
-	state.next_fmr	= req->fmr_list;
-
-	use_fmr = dev->fmr_pool ? SRP_MAP_ALLOW_FMR : SRP_MAP_NO_FMR;
-
-	for_each_sg(scat, sg, count, i) {
-		if (srp_map_sg_entry(&state, target, sg, i, use_fmr)) {
-			/* FMR mapping failed, so backtrack to the first
-			 * unmapped entry and continue on without using FMR.
-			 */
-			dma_addr_t dma_addr;
-			unsigned int dma_len;
-
-backtrack:
-			sg = state.unmapped_sg;
-			i = state.unmapped_index;
-
-			dma_addr = ib_sg_dma_address(ibdev, sg);
-			dma_len = ib_sg_dma_len(ibdev, sg);
-			dma_len -= (state.unmapped_addr - dma_addr);
-			dma_addr = state.unmapped_addr;
-			use_fmr = SRP_MAP_NO_FMR;
-			srp_map_desc(&state, dma_addr, dma_len, target->rkey);
-		}
-	}
-
-	if (use_fmr == SRP_MAP_ALLOW_FMR && srp_map_finish_fmr(&state, target))
-		goto backtrack;
+	srp_map_sg(&state, target, req, scat, count);
 
 	/* We've mapped the request, now pull as much of the indirect
 	 * descriptor table as we can into the command buffer. If this
@@ -1144,9 +1464,9 @@ backtrack:
 	 * guaranteed to fit into the command, as the SCSI layer won't
 	 * give us more S/G entries than we allow.
 	 */
-	req->nfmr = state.nfmr;
 	if (state.ndesc == 1) {
-		/* FMR mapping was able to collapse this to one entry,
+		/*
+		 * Memory registration collapsed the sg-list into one entry,
 		 * so use a direct descriptor.
 		 */
 		struct srp_direct_buf *buf = (void *) cmd->add_data;
@@ -1455,6 +1775,7 @@ static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc)
 
 /**
  * srp_tl_err_work() - handle a transport layer error
+ * @work: Work structure embedded in an SRP target port.
  *
  * Note: This function may get invoked before the rport has been created,
  * hence the target->rport test.
@@ -1468,14 +1789,24 @@ static void srp_tl_err_work(struct work_struct *work)
 		srp_start_tl_fail_timers(target->rport);
 }
 
-static void srp_handle_qp_err(enum ib_wc_status wc_status, bool send_err,
-			      struct srp_target_port *target)
+static void srp_handle_qp_err(u64 wr_id, enum ib_wc_status wc_status,
+			      bool send_err, struct srp_target_port *target)
 {
 	if (target->connected && !target->qp_in_error) {
-		shost_printk(KERN_ERR, target->scsi_host,
-			     PFX "failed %s status %d\n",
-			     send_err ? "send" : "receive",
-			     wc_status);
+		if (wr_id & LOCAL_INV_WR_ID_MASK) {
+			shost_printk(KERN_ERR, target->scsi_host, PFX
+				     "LOCAL_INV failed with status %d\n",
+				     wc_status);
+		} else if (wr_id & FAST_REG_WR_ID_MASK) {
+			shost_printk(KERN_ERR, target->scsi_host, PFX
+				     "FAST_REG_MR failed status %d\n",
+				     wc_status);
+		} else {
+			shost_printk(KERN_ERR, target->scsi_host,
+				     PFX "failed %s status %d for iu %p\n",
+				     send_err ? "send" : "receive",
+				     wc_status, (void *)(uintptr_t)wr_id);
+		}
 		queue_work(system_long_wq, &target->tl_err_work);
 	}
 	target->qp_in_error = true;
@@ -1491,7 +1822,7 @@ static void srp_recv_completion(struct ib_cq *cq, void *target_ptr)
 		if (likely(wc.status == IB_WC_SUCCESS)) {
 			srp_handle_recv(target, &wc);
 		} else {
-			srp_handle_qp_err(wc.status, false, target);
+			srp_handle_qp_err(wc.wr_id, wc.status, false, target);
 		}
 	}
 }
@@ -1507,7 +1838,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr)
 			iu = (struct srp_iu *) (uintptr_t) wc.wr_id;
 			list_add(&iu->list, &target->free_tx);
 		} else {
-			srp_handle_qp_err(wc.status, true, target);
+			srp_handle_qp_err(wc.wr_id, wc.status, true, target);
 		}
 	}
 }
@@ -1521,7 +1852,7 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 	struct srp_cmd *cmd;
 	struct ib_device *dev;
 	unsigned long flags;
-	int len, result;
+	int len, ret;
 	const bool in_scsi_eh = !in_interrupt() && current == shost->ehandler;
 
 	/*
@@ -1533,12 +1864,9 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 	if (in_scsi_eh)
 		mutex_lock(&rport->mutex);
 
-	result = srp_chkready(target->rport);
-	if (unlikely(result)) {
-		scmnd->result = result;
-		scmnd->scsi_done(scmnd);
-		goto unlock_rport;
-	}
+	scmnd->result = srp_chkready(target->rport);
+	if (unlikely(scmnd->result))
+		goto err;
 
 	spin_lock_irqsave(&target->lock, flags);
 	iu = __srp_get_tx_iu(target, SRP_IU_CMD);
@@ -1553,7 +1881,6 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 	ib_dma_sync_single_for_cpu(dev, iu->dma, target->max_iu_len,
 				   DMA_TO_DEVICE);
 
-	scmnd->result        = 0;
 	scmnd->host_scribble = (void *) req;
 
 	cmd = iu->buf;
@@ -1570,7 +1897,15 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 	len = srp_map_data(scmnd, target, req);
 	if (len < 0) {
 		shost_printk(KERN_ERR, target->scsi_host,
-			     PFX "Failed to map data\n");
+			     PFX "Failed to map data (%d)\n", len);
+		/*
+		 * If we ran out of memory descriptors (-ENOMEM) because an
+		 * application is queuing many requests with more than
+		 * max_pages_per_mr sg-list elements, tell the SCSI mid-layer
+		 * to reduce queue depth temporarily.
+		 */
+		scmnd->result = len == -ENOMEM ?
+			DID_OK << 16 | QUEUE_FULL << 1 : DID_ERROR << 16;
 		goto err_iu;
 	}
 
@@ -1582,11 +1917,13 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 		goto err_unmap;
 	}
 
+	ret = 0;
+
 unlock_rport:
 	if (in_scsi_eh)
 		mutex_unlock(&rport->mutex);
 
-	return 0;
+	return ret;
 
 err_unmap:
 	srp_unmap_data(scmnd, target, req);
@@ -1594,16 +1931,27 @@ err_unmap:
 err_iu:
 	srp_put_tx_iu(target, iu, SRP_IU_CMD);
 
+	/*
+	 * Avoid that the loops that iterate over the request ring can
+	 * encounter a dangling SCSI command pointer.
+	 */
+	req->scmnd = NULL;
+
 	spin_lock_irqsave(&target->lock, flags);
 	list_add(&req->list, &target->free_reqs);
 
 err_unlock:
 	spin_unlock_irqrestore(&target->lock, flags);
 
-	if (in_scsi_eh)
-		mutex_unlock(&rport->mutex);
+err:
+	if (scmnd->result) {
+		scmnd->scsi_done(scmnd);
+		ret = 0;
+	} else {
+		ret = SCSI_MLQUEUE_HOST_BUSY;
+	}
 
-	return SCSI_MLQUEUE_HOST_BUSY;
+	goto unlock_rport;
 }
 
 /*
@@ -2310,6 +2658,8 @@ static struct class srp_class = {
 
 /**
  * srp_conn_unique() - check whether the connection to a target is unique
+ * @host:   SRP host.
+ * @target: SRP target port.
  */
 static bool srp_conn_unique(struct srp_host *host,
 			    struct srp_target_port *target)
@@ -2605,7 +2955,8 @@ static ssize_t srp_create_target(struct device *dev,
 		container_of(dev, struct srp_host, dev);
 	struct Scsi_Host *target_host;
 	struct srp_target_port *target;
-	struct ib_device *ibdev = host->srp_dev->dev;
+	struct srp_device *srp_dev = host->srp_dev;
+	struct ib_device *ibdev = srp_dev->dev;
 	int ret;
 
 	target_host = scsi_host_alloc(&srp_template,
@@ -2650,9 +3001,9 @@ static ssize_t srp_create_target(struct device *dev,
 		goto err;
 	}
 
-	if (!host->srp_dev->fmr_pool && !target->allow_ext_sg &&
-				target->cmd_sg_cnt < target->sg_tablesize) {
-		pr_warn("No FMR pool and no external indirect descriptors, limiting sg_tablesize to cmd_sg_cnt\n");
+	if (!srp_dev->has_fmr && !srp_dev->has_fr && !target->allow_ext_sg &&
+	    target->cmd_sg_cnt < target->sg_tablesize) {
+		pr_warn("No MR pool and no external indirect descriptors, limiting sg_tablesize to cmd_sg_cnt\n");
 		target->sg_tablesize = target->cmd_sg_cnt;
 	}
 
@@ -2790,9 +3141,9 @@ static void srp_add_one(struct ib_device *device)
 {
 	struct srp_device *srp_dev;
 	struct ib_device_attr *dev_attr;
-	struct ib_fmr_pool_param fmr_param;
 	struct srp_host *host;
-	int max_pages_per_fmr, fmr_page_shift, s, e, p;
+	int mr_page_shift, s, e, p;
+	u64 max_pages_per_mr;
 
 	dev_attr = kmalloc(sizeof *dev_attr, GFP_KERNEL);
 	if (!dev_attr)
@@ -2807,15 +3158,39 @@ static void srp_add_one(struct ib_device *device)
 	if (!srp_dev)
 		goto free_attr;
 
+	srp_dev->has_fmr = (device->alloc_fmr && device->dealloc_fmr &&
+			    device->map_phys_fmr && device->unmap_fmr);
+	srp_dev->has_fr = (dev_attr->device_cap_flags &
+			   IB_DEVICE_MEM_MGT_EXTENSIONS);
+	if (!srp_dev->has_fmr && !srp_dev->has_fr)
+		dev_warn(&device->dev, "neither FMR nor FR is supported\n");
+
+	srp_dev->use_fast_reg = (srp_dev->has_fr &&
+				 (!srp_dev->has_fmr || prefer_fr));
+
 	/*
 	 * Use the smallest page size supported by the HCA, down to a
 	 * minimum of 4096 bytes. We're unlikely to build large sglists
 	 * out of smaller entries.
 	 */
-	fmr_page_shift		= max(12, ffs(dev_attr->page_size_cap) - 1);
-	srp_dev->fmr_page_size	= 1 << fmr_page_shift;
-	srp_dev->fmr_page_mask	= ~((u64) srp_dev->fmr_page_size - 1);
-	srp_dev->fmr_max_size	= srp_dev->fmr_page_size * SRP_FMR_SIZE;
+	mr_page_shift		= max(12, ffs(dev_attr->page_size_cap) - 1);
+	srp_dev->mr_page_size	= 1 << mr_page_shift;
+	srp_dev->mr_page_mask	= ~((u64) srp_dev->mr_page_size - 1);
+	max_pages_per_mr	= dev_attr->max_mr_size;
+	do_div(max_pages_per_mr, srp_dev->mr_page_size);
+	srp_dev->max_pages_per_mr = min_t(u64, SRP_MAX_PAGES_PER_MR,
+					  max_pages_per_mr);
+	if (srp_dev->use_fast_reg) {
+		srp_dev->max_pages_per_mr =
+			min_t(u32, srp_dev->max_pages_per_mr,
+			      dev_attr->max_fast_reg_page_list_len);
+	}
+	srp_dev->mr_max_size	= srp_dev->mr_page_size *
+				   srp_dev->max_pages_per_mr;
+	pr_debug("%s: mr_page_shift = %d, dev_attr->max_mr_size = %#llx, dev_attr->max_fast_reg_page_list_len = %u, max_pages_per_mr = %d, mr_max_size = %#x\n",
+		 device->name, mr_page_shift, dev_attr->max_mr_size,
+		 dev_attr->max_fast_reg_page_list_len,
+		 srp_dev->max_pages_per_mr, srp_dev->mr_max_size);
 
 	INIT_LIST_HEAD(&srp_dev->dev_list);
 
@@ -2831,27 +3206,6 @@ static void srp_add_one(struct ib_device *device)
 	if (IS_ERR(srp_dev->mr))
 		goto err_pd;
 
-	for (max_pages_per_fmr = SRP_FMR_SIZE;
-			max_pages_per_fmr >= SRP_FMR_MIN_SIZE;
-			max_pages_per_fmr /= 2, srp_dev->fmr_max_size /= 2) {
-		memset(&fmr_param, 0, sizeof fmr_param);
-		fmr_param.pool_size	    = SRP_FMR_POOL_SIZE;
-		fmr_param.dirty_watermark   = SRP_FMR_DIRTY_SIZE;
-		fmr_param.cache		    = 1;
-		fmr_param.max_pages_per_fmr = max_pages_per_fmr;
-		fmr_param.page_shift	    = fmr_page_shift;
-		fmr_param.access	    = (IB_ACCESS_LOCAL_WRITE |
-					       IB_ACCESS_REMOTE_WRITE |
-					       IB_ACCESS_REMOTE_READ);
-
-		srp_dev->fmr_pool = ib_create_fmr_pool(srp_dev->pd, &fmr_param);
-		if (!IS_ERR(srp_dev->fmr_pool))
-			break;
-	}
-
-	if (IS_ERR(srp_dev->fmr_pool))
-		srp_dev->fmr_pool = NULL;
-
 	if (device->node_type == RDMA_NODE_IB_SWITCH) {
 		s = 0;
 		e = 0;
@@ -2914,8 +3268,6 @@ static void srp_remove_one(struct ib_device *device)
 		kfree(host);
 	}
 
-	if (srp_dev->fmr_pool)
-		ib_destroy_fmr_pool(srp_dev->fmr_pool);
 	ib_dereg_mr(srp_dev->mr);
 	ib_dealloc_pd(srp_dev->pd);
 
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index aad27b7b4a4..e46ecb15aa0 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -66,13 +66,10 @@ enum {
 	SRP_TAG_NO_REQ		= ~0U,
 	SRP_TAG_TSK_MGMT	= 1U << 31,
 
-	SRP_FMR_SIZE		= 512,
-	SRP_FMR_MIN_SIZE	= 128,
-	SRP_FMR_POOL_SIZE	= 1024,
-	SRP_FMR_DIRTY_SIZE	= SRP_FMR_POOL_SIZE / 4,
+	SRP_MAX_PAGES_PER_MR	= 512,
 
-	SRP_MAP_ALLOW_FMR	= 0,
-	SRP_MAP_NO_FMR		= 1,
+	LOCAL_INV_WR_ID_MASK	= 1,
+	FAST_REG_WR_ID_MASK	= 2,
 };
 
 enum srp_target_state {
@@ -86,15 +83,24 @@ enum srp_iu_type {
 	SRP_IU_RSP,
 };
 
+/*
+ * @mr_page_mask: HCA memory registration page mask.
+ * @mr_page_size: HCA memory registration page size.
+ * @mr_max_size: Maximum size in bytes of a single FMR / FR registration
+ *   request.
+ */
 struct srp_device {
 	struct list_head	dev_list;
 	struct ib_device       *dev;
 	struct ib_pd	       *pd;
 	struct ib_mr	       *mr;
-	struct ib_fmr_pool     *fmr_pool;
-	u64			fmr_page_mask;
-	int			fmr_page_size;
-	int			fmr_max_size;
+	u64			mr_page_mask;
+	int			mr_page_size;
+	int			mr_max_size;
+	int			max_pages_per_mr;
+	bool			has_fmr;
+	bool			has_fr;
+	bool			use_fast_reg;
 };
 
 struct srp_host {
@@ -112,11 +118,14 @@ struct srp_request {
 	struct list_head	list;
 	struct scsi_cmnd       *scmnd;
 	struct srp_iu	       *cmd;
-	struct ib_pool_fmr    **fmr_list;
+	union {
+		struct ib_pool_fmr **fmr_list;
+		struct srp_fr_desc **fr_list;
+	};
 	u64		       *map_page;
 	struct srp_direct_buf  *indirect_desc;
 	dma_addr_t		indirect_dma_addr;
-	short			nfmr;
+	short			nmdesc;
 	short			index;
 };
 
@@ -131,6 +140,10 @@ struct srp_target_port {
 	struct ib_cq	       *send_cq ____cacheline_aligned_in_smp;
 	struct ib_cq	       *recv_cq;
 	struct ib_qp	       *qp;
+	union {
+		struct ib_fmr_pool     *fmr_pool;
+		struct srp_fr_pool     *fr_pool;
+	};
 	u32			lkey;
 	u32			rkey;
 	enum srp_target_state	state;
@@ -197,15 +210,66 @@ struct srp_iu {
 	enum dma_data_direction	direction;
 };
 
+/**
+ * struct srp_fr_desc - fast registration work request arguments
+ * @entry: Entry in srp_fr_pool.free_list.
+ * @mr:    Memory region.
+ * @frpl:  Fast registration page list.
+ */
+struct srp_fr_desc {
+	struct list_head		entry;
+	struct ib_mr			*mr;
+	struct ib_fast_reg_page_list	*frpl;
+};
+
+/**
+ * struct srp_fr_pool - pool of fast registration descriptors
+ *
+ * An entry is available for allocation if and only if it occurs in @free_list.
+ *
+ * @size:      Number of descriptors in this pool.
+ * @max_page_list_len: Maximum fast registration work request page list length.
+ * @lock:      Protects free_list.
+ * @free_list: List of free descriptors.
+ * @desc:      Fast registration descriptor pool.
+ */
+struct srp_fr_pool {
+	int			size;
+	int			max_page_list_len;
+	spinlock_t		lock;
+	struct list_head	free_list;
+	struct srp_fr_desc	desc[0];
+};
+
+/**
+ * struct srp_map_state - per-request DMA memory mapping state
+ * @desc:	    Pointer to the element of the SRP buffer descriptor array
+ *		    that is being filled in.
+ * @pages:	    Array with DMA addresses of pages being considered for
+ *		    memory registration.
+ * @base_dma_addr:  DMA address of the first page that has not yet been mapped.
+ * @dma_len:	    Number of bytes that will be registered with the next
+ *		    FMR or FR memory registration call.
+ * @total_len:	    Total number of bytes in the sg-list being mapped.
+ * @npages:	    Number of page addresses in the pages[] array.
+ * @nmdesc:	    Number of FMR or FR memory descriptors used for mapping.
+ * @ndesc:	    Number of SRP buffer descriptors that have been filled in.
+ * @unmapped_sg:    First element of the sg-list that is mapped via FMR or FR.
+ * @unmapped_index: Index of the first element mapped via FMR or FR.
+ * @unmapped_addr:  DMA address of the first element mapped via FMR or FR.
+ */
 struct srp_map_state {
-	struct ib_pool_fmr    **next_fmr;
+	union {
+		struct ib_pool_fmr **next_fmr;
+		struct srp_fr_desc **next_fr;
+	};
 	struct srp_direct_buf  *desc;
 	u64		       *pages;
 	dma_addr_t		base_dma_addr;
-	u32			fmr_len;
+	u32			dma_len;
 	u32			total_len;
 	unsigned int		npages;
-	unsigned int		nfmr;
+	unsigned int		nmdesc;
 	unsigned int		ndesc;
 	struct scatterlist     *unmapped_sg;
 	int			unmapped_index;
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index ce953d895f5..fd325ec9f06 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -629,12 +629,10 @@ static int str_to_user(const char *str, unsigned int maxlen, void __user *p)
 	return copy_to_user(p, str, len) ? -EFAULT : len;
 }
 
-#define OLD_KEY_MAX	0x1ff
 static int handle_eviocgbit(struct input_dev *dev,
 			    unsigned int type, unsigned int size,
 			    void __user *p, int compat_mode)
 {
-	static unsigned long keymax_warn_time;
 	unsigned long *bits;
 	int len;
 
@@ -652,24 +650,8 @@ static int handle_eviocgbit(struct input_dev *dev,
 	default: return -EINVAL;
 	}
 
-	/*
-	 * Work around bugs in userspace programs that like to do
-	 * EVIOCGBIT(EV_KEY, KEY_MAX) and not realize that 'len'
-	 * should be in bytes, not in bits.
-	 */
-	if (type == EV_KEY && size == OLD_KEY_MAX) {
-		len = OLD_KEY_MAX;
-		if (printk_timed_ratelimit(&keymax_warn_time, 10 * 1000))
-			pr_warning("(EVIOCGBIT): Suspicious buffer size %u, "
-				   "limiting output to %zu bytes. See "
-				   "http://userweb.kernel.org/~dtor/eviocgbit-bug.html\n",
-				   OLD_KEY_MAX,
-				   BITS_TO_LONGS(OLD_KEY_MAX) * sizeof(long));
-	}
-
 	return bits_to_user(bits, len, size, p, compat_mode);
 }
-#undef OLD_KEY_MAX
 
 static int evdev_handle_get_keycode(struct input_dev *dev, void __user *p)
 {
diff --git a/drivers/input/input-polldev.c b/drivers/input/input-polldev.c
index 7f161d93203..3664f81655c 100644
--- a/drivers/input/input-polldev.c
+++ b/drivers/input/input-polldev.c
@@ -147,6 +147,11 @@ static struct attribute_group input_polldev_attribute_group = {
 	.attrs = sysfs_attrs
 };
 
+static const struct attribute_group *input_polldev_attribute_groups[] = {
+	&input_polldev_attribute_group,
+	NULL
+};
+
 /**
  * input_allocate_polled_device - allocate memory for polled device
  *
@@ -171,6 +176,91 @@ struct input_polled_dev *input_allocate_polled_device(void)
 }
 EXPORT_SYMBOL(input_allocate_polled_device);
 
+struct input_polled_devres {
+	struct input_polled_dev *polldev;
+};
+
+static int devm_input_polldev_match(struct device *dev, void *res, void *data)
+{
+	struct input_polled_devres *devres = res;
+
+	return devres->polldev == data;
+}
+
+static void devm_input_polldev_release(struct device *dev, void *res)
+{
+	struct input_polled_devres *devres = res;
+	struct input_polled_dev *polldev = devres->polldev;
+
+	dev_dbg(dev, "%s: dropping reference/freeing %s\n",
+		__func__, dev_name(&polldev->input->dev));
+
+	input_put_device(polldev->input);
+	kfree(polldev);
+}
+
+static void devm_input_polldev_unregister(struct device *dev, void *res)
+{
+	struct input_polled_devres *devres = res;
+	struct input_polled_dev *polldev = devres->polldev;
+
+	dev_dbg(dev, "%s: unregistering device %s\n",
+		__func__, dev_name(&polldev->input->dev));
+	input_unregister_device(polldev->input);
+
+	/*
+	 * Note that we are still holding extra reference to the input
+	 * device so it will stick around until devm_input_polldev_release()
+	 * is called.
+	 */
+}
+
+/**
+ * devm_input_allocate_polled_device - allocate managed polled device
+ * @dev: device owning the polled device being created
+ *
+ * Returns prepared &struct input_polled_dev or %NULL.
+ *
+ * Managed polled input devices do not need to be explicitly unregistered
+ * or freed as it will be done automatically when owner device unbinds
+ * from * its driver (or binding fails). Once such managed polled device
+ * is allocated, it is ready to be set up and registered in the same
+ * fashion as regular polled input devices (using
+ * input_register_polled_device() function).
+ *
+ * If you want to manually unregister and free such managed polled devices,
+ * it can be still done by calling input_unregister_polled_device() and
+ * input_free_polled_device(), although it is rarely needed.
+ *
+ * NOTE: the owner device is set up as parent of input device and users
+ * should not override it.
+ */
+struct input_polled_dev *devm_input_allocate_polled_device(struct device *dev)
+{
+	struct input_polled_dev *polldev;
+	struct input_polled_devres *devres;
+
+	devres = devres_alloc(devm_input_polldev_release, sizeof(*devres),
+			      GFP_KERNEL);
+	if (!devres)
+		return NULL;
+
+	polldev = input_allocate_polled_device();
+	if (!polldev) {
+		devres_free(devres);
+		return NULL;
+	}
+
+	polldev->input->dev.parent = dev;
+	polldev->devres_managed = true;
+
+	devres->polldev = polldev;
+	devres_add(dev, devres);
+
+	return polldev;
+}
+EXPORT_SYMBOL(devm_input_allocate_polled_device);
+
 /**
  * input_free_polled_device - free memory allocated for polled device
  * @dev: device to free
@@ -181,7 +271,12 @@ EXPORT_SYMBOL(input_allocate_polled_device);
 void input_free_polled_device(struct input_polled_dev *dev)
 {
 	if (dev) {
-		input_free_device(dev->input);
+		if (dev->devres_managed)
+			WARN_ON(devres_destroy(dev->input->dev.parent,
+						devm_input_polldev_release,
+						devm_input_polldev_match,
+						dev));
+		input_put_device(dev->input);
 		kfree(dev);
 	}
 }
@@ -199,26 +294,35 @@ EXPORT_SYMBOL(input_free_polled_device);
  */
 int input_register_polled_device(struct input_polled_dev *dev)
 {
+	struct input_polled_devres *devres = NULL;
 	struct input_dev *input = dev->input;
 	int error;
 
+	if (dev->devres_managed) {
+		devres = devres_alloc(devm_input_polldev_unregister,
+				      sizeof(*devres), GFP_KERNEL);
+		if (!devres)
+			return -ENOMEM;
+
+		devres->polldev = dev;
+	}
+
 	input_set_drvdata(input, dev);
 	INIT_DELAYED_WORK(&dev->work, input_polled_device_work);
+
 	if (!dev->poll_interval)
 		dev->poll_interval = 500;
 	if (!dev->poll_interval_max)
 		dev->poll_interval_max = dev->poll_interval;
+
 	input->open = input_open_polled_device;
 	input->close = input_close_polled_device;
 
-	error = input_register_device(input);
-	if (error)
-		return error;
+	input->dev.groups = input_polldev_attribute_groups;
 
-	error = sysfs_create_group(&input->dev.kobj,
-				   &input_polldev_attribute_group);
+	error = input_register_device(input);
 	if (error) {
-		input_unregister_device(input);
+		devres_free(devres);
 		return error;
 	}
 
@@ -231,6 +335,12 @@ int input_register_polled_device(struct input_polled_dev *dev)
 	 */
 	input_get_device(input);
 
+	if (dev->devres_managed) {
+		dev_dbg(input->dev.parent, "%s: registering %s with devres.\n",
+			__func__, dev_name(&input->dev));
+		devres_add(input->dev.parent, devres);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL(input_register_polled_device);
@@ -245,8 +355,11 @@ EXPORT_SYMBOL(input_register_polled_device);
  */
 void input_unregister_polled_device(struct input_polled_dev *dev)
 {
-	sysfs_remove_group(&dev->input->dev.kobj,
-			   &input_polldev_attribute_group);
+	if (dev->devres_managed)
+		WARN_ON(devres_destroy(dev->input->dev.parent,
+					devm_input_polldev_unregister,
+					devm_input_polldev_match,
+					dev));
 
 	input_unregister_device(dev->input);
 }
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 1c4c0db0555..29ca0bb4f56 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -257,9 +257,10 @@ static int input_handle_abs_event(struct input_dev *dev,
 }
 
 static int input_get_disposition(struct input_dev *dev,
-			  unsigned int type, unsigned int code, int value)
+			  unsigned int type, unsigned int code, int *pval)
 {
 	int disposition = INPUT_IGNORE_EVENT;
+	int value = *pval;
 
 	switch (type) {
 
@@ -357,6 +358,7 @@ static int input_get_disposition(struct input_dev *dev,
 		break;
 	}
 
+	*pval = value;
 	return disposition;
 }
 
@@ -365,7 +367,7 @@ static void input_handle_event(struct input_dev *dev,
 {
 	int disposition;
 
-	disposition = input_get_disposition(dev, type, code, value);
+	disposition = input_get_disposition(dev, type, code, &value);
 
 	if ((disposition & INPUT_PASS_TO_DEVICE) && dev->event)
 		dev->event(dev, type, code, value);
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index ffc7ad3a2c8..f7e79b48134 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -524,6 +524,17 @@ config KEYBOARD_STOWAWAY
 	  To compile this driver as a module, choose M here: the
 	  module will be called stowaway.
 
+config KEYBOARD_ST_KEYSCAN
+	tristate "STMicroelectronics keyscan support"
+	depends on ARCH_STI || COMPILE_TEST
+	select INPUT_MATRIXKMAP
+	help
+	  Say Y here if you want to use a keypad attached to the keyscan block
+	  on some STMicroelectronics SoC devices.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called st-keyscan.
+
 config KEYBOARD_SUNKBD
 	tristate "Sun Type 4 and Type 5 keyboard"
 	select SERIO
@@ -578,7 +589,7 @@ config KEYBOARD_OMAP
 
 config KEYBOARD_OMAP4
 	tristate "TI OMAP4+ keypad support"
-	depends on ARCH_OMAP2PLUS
+	depends on OF || ARCH_OMAP2PLUS
 	select INPUT_MATRIXKMAP
 	help
 	  Say Y here if you want to use the OMAP4+ keypad.
diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile
index 11cff7b84b4..7504ae19049 100644
--- a/drivers/input/keyboard/Makefile
+++ b/drivers/input/keyboard/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_KEYBOARD_SH_KEYSC)		+= sh_keysc.o
 obj-$(CONFIG_KEYBOARD_SPEAR)		+= spear-keyboard.o
 obj-$(CONFIG_KEYBOARD_STMPE)		+= stmpe-keypad.o
 obj-$(CONFIG_KEYBOARD_STOWAWAY)		+= stowaway.o
+obj-$(CONFIG_KEYBOARD_ST_KEYSCAN)	+= st-keyscan.o
 obj-$(CONFIG_KEYBOARD_SUNKBD)		+= sunkbd.o
 obj-$(CONFIG_KEYBOARD_TC3589X)		+= tc3589x-keypad.o
 obj-$(CONFIG_KEYBOARD_TEGRA)		+= tegra-kbc.o
diff --git a/drivers/input/keyboard/adp5520-keys.c b/drivers/input/keyboard/adp5520-keys.c
index 4cc14c2fa7d..7f4a8b58efc 100644
--- a/drivers/input/keyboard/adp5520-keys.c
+++ b/drivers/input/keyboard/adp5520-keys.c
@@ -12,6 +12,7 @@
 #include <linux/input.h>
 #include <linux/mfd/adp5520.h>
 #include <linux/slab.h>
+#include <linux/device.h>
 
 struct adp5520_keys {
 	struct input_dev *input;
@@ -81,7 +82,7 @@ static int adp5520_keys_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	if (pdata == NULL) {
+	if (!pdata) {
 		dev_err(&pdev->dev, "missing platform data\n");
 		return -EINVAL;
 	}
@@ -89,17 +90,15 @@ static int adp5520_keys_probe(struct platform_device *pdev)
 	if (!(pdata->rows_en_mask && pdata->cols_en_mask))
 		return -EINVAL;
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (dev == NULL) {
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev) {
 		dev_err(&pdev->dev, "failed to alloc memory\n");
 		return -ENOMEM;
 	}
 
-	input = input_allocate_device();
-	if (!input) {
-		ret = -ENOMEM;
-		goto err;
-	}
+	input = devm_input_allocate_device(&pdev->dev);
+	if (!input)
+		return -ENOMEM;
 
 	dev->master = pdev->dev.parent;
 	dev->input = input;
@@ -135,7 +134,7 @@ static int adp5520_keys_probe(struct platform_device *pdev)
 	ret = input_register_device(input);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to register input device\n");
-		goto err;
+		return ret;
 	}
 
 	en_mask = pdata->rows_en_mask | pdata->cols_en_mask;
@@ -157,8 +156,7 @@ static int adp5520_keys_probe(struct platform_device *pdev)
 
 	if (ret) {
 		dev_err(&pdev->dev, "failed to write\n");
-		ret = -EIO;
-		goto err1;
+		return -EIO;
 	}
 
 	dev->notifier.notifier_call = adp5520_keys_notifier;
@@ -166,19 +164,11 @@ static int adp5520_keys_probe(struct platform_device *pdev)
 			ADP5520_KP_IEN | ADP5520_KR_IEN);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to register notifier\n");
-		goto err1;
+		return ret;
 	}
 
 	platform_set_drvdata(pdev, dev);
 	return 0;
-
-err1:
-	input_unregister_device(input);
-	input = NULL;
-err:
-	input_free_device(input);
-	kfree(dev);
-	return ret;
 }
 
 static int adp5520_keys_remove(struct platform_device *pdev)
@@ -188,8 +178,6 @@ static int adp5520_keys_remove(struct platform_device *pdev)
 	adp5520_unregister_notifier(dev->master, &dev->notifier,
 				ADP5520_KP_IEN | ADP5520_KR_IEN);
 
-	input_unregister_device(dev->input);
-	kfree(dev);
 	return 0;
 }
 
diff --git a/drivers/input/keyboard/clps711x-keypad.c b/drivers/input/keyboard/clps711x-keypad.c
index 3955aecee44..552b65c6e6b 100644
--- a/drivers/input/keyboard/clps711x-keypad.c
+++ b/drivers/input/keyboard/clps711x-keypad.c
@@ -185,7 +185,7 @@ static int clps711x_keypad_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id clps711x_keypad_of_match[] = {
+static const struct of_device_id clps711x_keypad_of_match[] = {
 	{ .compatible = "cirrus,clps711x-keypad", },
 	{ }
 };
diff --git a/drivers/input/keyboard/gpio_keys.c b/drivers/input/keyboard/gpio_keys.c
index 2db13246eb8..8c98e97f8e4 100644
--- a/drivers/input/keyboard/gpio_keys.c
+++ b/drivers/input/keyboard/gpio_keys.c
@@ -424,6 +424,16 @@ out:
 	return IRQ_HANDLED;
 }
 
+static void gpio_keys_quiesce_key(void *data)
+{
+	struct gpio_button_data *bdata = data;
+
+	if (bdata->timer_debounce)
+		del_timer_sync(&bdata->timer);
+
+	cancel_work_sync(&bdata->work);
+}
+
 static int gpio_keys_setup_key(struct platform_device *pdev,
 				struct input_dev *input,
 				struct gpio_button_data *bdata,
@@ -433,7 +443,8 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 	struct device *dev = &pdev->dev;
 	irq_handler_t isr;
 	unsigned long irqflags;
-	int irq, error;
+	int irq;
+	int error;
 
 	bdata->input = input;
 	bdata->button = button;
@@ -441,7 +452,8 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 
 	if (gpio_is_valid(button->gpio)) {
 
-		error = gpio_request_one(button->gpio, GPIOF_IN, desc);
+		error = devm_gpio_request_one(&pdev->dev, button->gpio,
+					      GPIOF_IN, desc);
 		if (error < 0) {
 			dev_err(dev, "Failed to request GPIO %d, error %d\n",
 				button->gpio, error);
@@ -463,7 +475,7 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 			dev_err(dev,
 				"Unable to get irq number for GPIO %d, error %d\n",
 				button->gpio, error);
-			goto fail;
+			return error;
 		}
 		bdata->irq = irq;
 
@@ -497,26 +509,33 @@ static int gpio_keys_setup_key(struct platform_device *pdev,
 	input_set_capability(input, button->type ?: EV_KEY, button->code);
 
 	/*
+	 * Install custom action to cancel debounce timer and
+	 * workqueue item.
+	 */
+	error = devm_add_action(&pdev->dev, gpio_keys_quiesce_key, bdata);
+	if (error) {
+		dev_err(&pdev->dev,
+			"failed to register quiesce action, error: %d\n",
+			error);
+		return error;
+	}
+
+	/*
 	 * If platform has specified that the button can be disabled,
 	 * we don't want it to share the interrupt line.
 	 */
 	if (!button->can_disable)
 		irqflags |= IRQF_SHARED;
 
-	error = request_any_context_irq(bdata->irq, isr, irqflags, desc, bdata);
+	error = devm_request_any_context_irq(&pdev->dev, bdata->irq,
+					     isr, irqflags, desc, bdata);
 	if (error < 0) {
 		dev_err(dev, "Unable to claim irq %d; error %d\n",
 			bdata->irq, error);
-		goto fail;
+		return error;
 	}
 
 	return 0;
-
-fail:
-	if (gpio_is_valid(button->gpio))
-		gpio_free(button->gpio);
-
-	return error;
 }
 
 static void gpio_keys_report_state(struct gpio_keys_drvdata *ddata)
@@ -578,23 +597,18 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 	int i;
 
 	node = dev->of_node;
-	if (!node) {
-		error = -ENODEV;
-		goto err_out;
-	}
+	if (!node)
+		return ERR_PTR(-ENODEV);
 
 	nbuttons = of_get_child_count(node);
-	if (nbuttons == 0) {
-		error = -ENODEV;
-		goto err_out;
-	}
+	if (nbuttons == 0)
+		return ERR_PTR(-ENODEV);
 
-	pdata = kzalloc(sizeof(*pdata) + nbuttons * (sizeof *button),
-			GFP_KERNEL);
-	if (!pdata) {
-		error = -ENOMEM;
-		goto err_out;
-	}
+	pdata = devm_kzalloc(dev,
+			     sizeof(*pdata) + nbuttons * sizeof(*button),
+			     GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
 
 	pdata->buttons = (struct gpio_keys_button *)(pdata + 1);
 	pdata->nbuttons = nbuttons;
@@ -619,7 +633,7 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 				dev_err(dev,
 					"Failed to get gpio flags, error: %d\n",
 					error);
-			goto err_free_pdata;
+			return ERR_PTR(error);
 		}
 
 		button = &pdata->buttons[i++];
@@ -630,8 +644,7 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 		if (of_property_read_u32(pp, "linux,code", &button->code)) {
 			dev_err(dev, "Button without keycode: 0x%x\n",
 				button->gpio);
-			error = -EINVAL;
-			goto err_free_pdata;
+			return ERR_PTR(-EINVAL);
 		}
 
 		button->desc = of_get_property(pp, "label", NULL);
@@ -646,20 +659,13 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 			button->debounce_interval = 5;
 	}
 
-	if (pdata->nbuttons == 0) {
-		error = -EINVAL;
-		goto err_free_pdata;
-	}
+	if (pdata->nbuttons == 0)
+		return ERR_PTR(-EINVAL);
 
 	return pdata;
-
-err_free_pdata:
-	kfree(pdata);
-err_out:
-	return ERR_PTR(error);
 }
 
-static struct of_device_id gpio_keys_of_match[] = {
+static const struct of_device_id gpio_keys_of_match[] = {
 	{ .compatible = "gpio-keys", },
 	{ },
 };
@@ -675,22 +681,13 @@ gpio_keys_get_devtree_pdata(struct device *dev)
 
 #endif
 
-static void gpio_remove_key(struct gpio_button_data *bdata)
-{
-	free_irq(bdata->irq, bdata);
-	if (bdata->timer_debounce)
-		del_timer_sync(&bdata->timer);
-	cancel_work_sync(&bdata->work);
-	if (gpio_is_valid(bdata->button->gpio))
-		gpio_free(bdata->button->gpio);
-}
-
 static int gpio_keys_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	const struct gpio_keys_platform_data *pdata = dev_get_platdata(dev);
 	struct gpio_keys_drvdata *ddata;
 	struct input_dev *input;
+	size_t size;
 	int i, error;
 	int wakeup = 0;
 
@@ -700,14 +697,18 @@ static int gpio_keys_probe(struct platform_device *pdev)
 			return PTR_ERR(pdata);
 	}
 
-	ddata = kzalloc(sizeof(struct gpio_keys_drvdata) +
-			pdata->nbuttons * sizeof(struct gpio_button_data),
-			GFP_KERNEL);
-	input = input_allocate_device();
-	if (!ddata || !input) {
+	size = sizeof(struct gpio_keys_drvdata) +
+			pdata->nbuttons * sizeof(struct gpio_button_data);
+	ddata = devm_kzalloc(dev, size, GFP_KERNEL);
+	if (!ddata) {
 		dev_err(dev, "failed to allocate state\n");
-		error = -ENOMEM;
-		goto fail1;
+		return -ENOMEM;
+	}
+
+	input = devm_input_allocate_device(dev);
+	if (!input) {
+		dev_err(dev, "failed to allocate input device\n");
+		return -ENOMEM;
 	}
 
 	ddata->pdata = pdata;
@@ -738,7 +739,7 @@ static int gpio_keys_probe(struct platform_device *pdev)
 
 		error = gpio_keys_setup_key(pdev, input, bdata, button);
 		if (error)
-			goto fail2;
+			return error;
 
 		if (button->wakeup)
 			wakeup = 1;
@@ -748,57 +749,31 @@ static int gpio_keys_probe(struct platform_device *pdev)
 	if (error) {
 		dev_err(dev, "Unable to export keys/switches, error: %d\n",
 			error);
-		goto fail2;
+		return error;
 	}
 
 	error = input_register_device(input);
 	if (error) {
 		dev_err(dev, "Unable to register input device, error: %d\n",
 			error);
-		goto fail3;
+		goto err_remove_group;
 	}
 
 	device_init_wakeup(&pdev->dev, wakeup);
 
 	return 0;
 
- fail3:
+err_remove_group:
 	sysfs_remove_group(&pdev->dev.kobj, &gpio_keys_attr_group);
- fail2:
-	while (--i >= 0)
-		gpio_remove_key(&ddata->data[i]);
-
- fail1:
-	input_free_device(input);
-	kfree(ddata);
-	/* If we have no platform data, we allocated pdata dynamically. */
-	if (!dev_get_platdata(&pdev->dev))
-		kfree(pdata);
-
 	return error;
 }
 
 static int gpio_keys_remove(struct platform_device *pdev)
 {
-	struct gpio_keys_drvdata *ddata = platform_get_drvdata(pdev);
-	struct input_dev *input = ddata->input;
-	int i;
-
 	sysfs_remove_group(&pdev->dev.kobj, &gpio_keys_attr_group);
 
 	device_init_wakeup(&pdev->dev, 0);
 
-	for (i = 0; i < ddata->pdata->nbuttons; i++)
-		gpio_remove_key(&ddata->data[i]);
-
-	input_unregister_device(input);
-
-	/* If we have no platform data, we allocated pdata dynamically. */
-	if (!dev_get_platdata(&pdev->dev))
-		kfree(ddata->pdata);
-
-	kfree(ddata);
-
 	return 0;
 }
 
diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c
index e571e194ff8..432d36395f3 100644
--- a/drivers/input/keyboard/gpio_keys_polled.c
+++ b/drivers/input/keyboard/gpio_keys_polled.c
@@ -120,12 +120,10 @@ static struct gpio_keys_platform_data *gpio_keys_polled_get_devtree_pdata(struct
 	if (nbuttons == 0)
 		return NULL;
 
-	pdata = kzalloc(sizeof(*pdata) + nbuttons * (sizeof *button),
-			GFP_KERNEL);
-	if (!pdata) {
-		error = -ENOMEM;
-		goto err_out;
-	}
+	pdata = devm_kzalloc(dev, sizeof(*pdata) + nbuttons * sizeof(*button),
+			     GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
 
 	pdata->buttons = (struct gpio_keys_button *)(pdata + 1);
 	pdata->nbuttons = nbuttons;
@@ -151,7 +149,7 @@ static struct gpio_keys_platform_data *gpio_keys_polled_get_devtree_pdata(struct
 				dev_err(dev,
 					"Failed to get gpio flags, error: %d\n",
 					error);
-			goto err_free_pdata;
+			return ERR_PTR(error);
 		}
 
 		button = &pdata->buttons[i++];
@@ -162,8 +160,7 @@ static struct gpio_keys_platform_data *gpio_keys_polled_get_devtree_pdata(struct
 		if (of_property_read_u32(pp, "linux,code", &button->code)) {
 			dev_err(dev, "Button without keycode: 0x%x\n",
 				button->gpio);
-			error = -EINVAL;
-			goto err_free_pdata;
+			return ERR_PTR(-EINVAL);
 		}
 
 		button->desc = of_get_property(pp, "label", NULL);
@@ -178,20 +175,13 @@ static struct gpio_keys_platform_data *gpio_keys_polled_get_devtree_pdata(struct
 			button->debounce_interval = 5;
 	}
 
-	if (pdata->nbuttons == 0) {
-		error = -EINVAL;
-		goto err_free_pdata;
-	}
+	if (pdata->nbuttons == 0)
+		return ERR_PTR(-EINVAL);
 
 	return pdata;
-
-err_free_pdata:
-	kfree(pdata);
-err_out:
-	return ERR_PTR(error);
 }
 
-static struct of_device_id gpio_keys_polled_of_match[] = {
+static const struct of_device_id gpio_keys_polled_of_match[] = {
 	{ .compatible = "gpio-keys-polled", },
 	{ },
 };
@@ -213,6 +203,7 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 	struct gpio_keys_polled_dev *bdev;
 	struct input_polled_dev *poll_dev;
 	struct input_dev *input;
+	size_t size;
 	int error;
 	int i;
 
@@ -228,24 +219,21 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 
 	if (!pdata->poll_interval) {
 		dev_err(dev, "missing poll_interval value\n");
-		error = -EINVAL;
-		goto err_free_pdata;
+		return -EINVAL;
 	}
 
-	bdev = kzalloc(sizeof(struct gpio_keys_polled_dev) +
-		       pdata->nbuttons * sizeof(struct gpio_keys_button_data),
-		       GFP_KERNEL);
+	size = sizeof(struct gpio_keys_polled_dev) +
+			pdata->nbuttons * sizeof(struct gpio_keys_button_data);
+	bdev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
 	if (!bdev) {
 		dev_err(dev, "no memory for private data\n");
-		error = -ENOMEM;
-		goto err_free_pdata;
+		return -ENOMEM;
 	}
 
-	poll_dev = input_allocate_polled_device();
+	poll_dev = devm_input_allocate_polled_device(&pdev->dev);
 	if (!poll_dev) {
 		dev_err(dev, "no memory for polled device\n");
-		error = -ENOMEM;
-		goto err_free_bdev;
+		return -ENOMEM;
 	}
 
 	poll_dev->private = bdev;
@@ -258,7 +246,6 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 
 	input->name = pdev->name;
 	input->phys = DRV_NAME"/input0";
-	input->dev.parent = &pdev->dev;
 
 	input->id.bustype = BUS_HOST;
 	input->id.vendor = 0x0001;
@@ -277,16 +264,15 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 
 		if (button->wakeup) {
 			dev_err(dev, DRV_NAME " does not support wakeup\n");
-			error = -EINVAL;
-			goto err_free_gpio;
+			return -EINVAL;
 		}
 
-		error = gpio_request_one(gpio, GPIOF_IN,
-					 button->desc ?: DRV_NAME);
+		error = devm_gpio_request_one(&pdev->dev, gpio, GPIOF_IN,
+					      button->desc ? : DRV_NAME);
 		if (error) {
 			dev_err(dev, "unable to claim gpio %u, err=%d\n",
 				gpio, error);
-			goto err_free_gpio;
+			return error;
 		}
 
 		bdata->can_sleep = gpio_cansleep(gpio);
@@ -306,7 +292,7 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 	if (error) {
 		dev_err(dev, "unable to register polled device, err=%d\n",
 			error);
-		goto err_free_gpio;
+		return error;
 	}
 
 	/* report initial state of the buttons */
@@ -315,52 +301,10 @@ static int gpio_keys_polled_probe(struct platform_device *pdev)
 					     &bdev->data[i]);
 
 	return 0;
-
-err_free_gpio:
-	while (--i >= 0)
-		gpio_free(pdata->buttons[i].gpio);
-
-	input_free_polled_device(poll_dev);
-
-err_free_bdev:
-	kfree(bdev);
-
-err_free_pdata:
-	/* If we have no platform_data, we allocated pdata dynamically.  */
-	if (!dev_get_platdata(&pdev->dev))
-		kfree(pdata);
-
-	return error;
-}
-
-static int gpio_keys_polled_remove(struct platform_device *pdev)
-{
-	struct gpio_keys_polled_dev *bdev = platform_get_drvdata(pdev);
-	const struct gpio_keys_platform_data *pdata = bdev->pdata;
-	int i;
-
-	input_unregister_polled_device(bdev->poll_dev);
-
-	for (i = 0; i < pdata->nbuttons; i++)
-		gpio_free(pdata->buttons[i].gpio);
-
-	input_free_polled_device(bdev->poll_dev);
-
-	/*
-	 * If we had no platform_data, we allocated pdata dynamically and
-	 * must free it here.
-	 */
-	if (!dev_get_platdata(&pdev->dev))
-		kfree(pdata);
-
-	kfree(bdev);
-
-	return 0;
 }
 
 static struct platform_driver gpio_keys_polled_driver = {
 	.probe	= gpio_keys_polled_probe,
-	.remove	= gpio_keys_polled_remove,
 	.driver	= {
 		.name	= DRV_NAME,
 		.owner	= THIS_MODULE,
diff --git a/drivers/input/keyboard/imx_keypad.c b/drivers/input/keyboard/imx_keypad.c
index 97ec33572e5..8280cb16260 100644
--- a/drivers/input/keyboard/imx_keypad.c
+++ b/drivers/input/keyboard/imx_keypad.c
@@ -415,7 +415,7 @@ open_err:
 }
 
 #ifdef CONFIG_OF
-static struct of_device_id imx_keypad_of_match[] = {
+static const struct of_device_id imx_keypad_of_match[] = {
 	{ .compatible = "fsl,imx21-kpp", },
 	{ /* sentinel */ }
 };
diff --git a/drivers/input/keyboard/jornada680_kbd.c b/drivers/input/keyboard/jornada680_kbd.c
index 69b1f002ff5..0ba4428da24 100644
--- a/drivers/input/keyboard/jornada680_kbd.c
+++ b/drivers/input/keyboard/jornada680_kbd.c
@@ -16,6 +16,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/device.h>
 #include <linux/input.h>
 #include <linux/input-polldev.h>
 #include <linux/interrupt.h>
@@ -185,14 +186,15 @@ static int jornada680kbd_probe(struct platform_device *pdev)
 	struct input_dev *input_dev;
 	int i, error;
 
-	jornadakbd = kzalloc(sizeof(struct jornadakbd), GFP_KERNEL);
+	jornadakbd = devm_kzalloc(&pdev->dev, sizeof(struct jornadakbd),
+				  GFP_KERNEL);
 	if (!jornadakbd)
 		return -ENOMEM;
 
-	poll_dev = input_allocate_polled_device();
+	poll_dev = devm_input_allocate_polled_device(&pdev->dev);
 	if (!poll_dev) {
-		error = -ENOMEM;
-		goto failed;
+		dev_err(&pdev->dev, "failed to allocate polled input device\n");
+		return -ENOMEM;
 	}
 
 	platform_set_drvdata(pdev, jornadakbd);
@@ -224,27 +226,10 @@ static int jornada680kbd_probe(struct platform_device *pdev)
 	input_set_capability(input_dev, EV_MSC, MSC_SCAN);
 
 	error = input_register_polled_device(jornadakbd->poll_dev);
-	if (error)
-		goto failed;
-
-	return 0;
-
- failed:
-	printk(KERN_ERR "Jornadakbd: failed to register driver, error: %d\n",
-		error);
-	input_free_polled_device(poll_dev);
-	kfree(jornadakbd);
-	return error;
-
-}
-
-static int jornada680kbd_remove(struct platform_device *pdev)
-{
-	struct jornadakbd *jornadakbd = platform_get_drvdata(pdev);
-
-	input_unregister_polled_device(jornadakbd->poll_dev);
-	input_free_polled_device(jornadakbd->poll_dev);
-	kfree(jornadakbd);
+	if (error) {
+		dev_err(&pdev->dev, "failed to register polled input device\n");
+		return error;
+	}
 
 	return 0;
 }
@@ -255,7 +240,6 @@ static struct platform_driver jornada680kbd_driver = {
 		.owner	= THIS_MODULE,
 	},
 	.probe	= jornada680kbd_probe,
-	.remove	= jornada680kbd_remove,
 };
 module_platform_driver(jornada680kbd_driver);
 
diff --git a/drivers/input/keyboard/mcs_touchkey.c b/drivers/input/keyboard/mcs_touchkey.c
index 1da8e0b44b5..375b05ca8e2 100644
--- a/drivers/input/keyboard/mcs_touchkey.c
+++ b/drivers/input/keyboard/mcs_touchkey.c
@@ -147,7 +147,7 @@ static int mcs_touchkey_probe(struct i2c_client *client,
 	}
 	dev_info(&client->dev, "Firmware version: %d\n", fw_ver);
 
-	input_dev->name = "MELPAS MCS Touchkey";
+	input_dev->name = "MELFAS MCS Touchkey";
 	input_dev->id.bustype = BUS_I2C;
 	input_dev->dev.parent = &client->dev;
 	input_dev->evbit[0] = BIT_MASK(EV_KEY);
diff --git a/drivers/input/keyboard/omap4-keypad.c b/drivers/input/keyboard/omap4-keypad.c
index 0400b3f2b4b..024b7bdffe5 100644
--- a/drivers/input/keyboard/omap4-keypad.c
+++ b/drivers/input/keyboard/omap4-keypad.c
@@ -28,11 +28,10 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/input.h>
+#include <linux/input/matrix_keypad.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
 
-#include <linux/platform_data/omap4-keypad.h>
-
 /* OMAP4 registers */
 #define OMAP4_KBD_REVISION		0x00
 #define OMAP4_KBD_SYSCONFIG		0x10
@@ -218,7 +217,6 @@ static void omap4_keypad_close(struct input_dev *input)
 	pm_runtime_put_sync(input->dev.parent);
 }
 
-#ifdef CONFIG_OF
 static int omap4_keypad_parse_dt(struct device *dev,
 				 struct omap4_keypad *keypad_data)
 {
@@ -235,20 +233,9 @@ static int omap4_keypad_parse_dt(struct device *dev,
 
 	return 0;
 }
-#else
-static inline int omap4_keypad_parse_dt(struct device *dev,
-					struct omap4_keypad *keypad_data)
-{
-	return -ENOSYS;
-}
-#endif
 
 static int omap4_keypad_probe(struct platform_device *pdev)
 {
-	const struct omap4_keypad_platform_data *pdata =
-				dev_get_platdata(&pdev->dev);
-	const struct matrix_keymap_data *keymap_data =
-				pdata ? pdata->keymap_data : NULL;
 	struct omap4_keypad *keypad_data;
 	struct input_dev *input_dev;
 	struct resource *res;
@@ -277,14 +264,9 @@ static int omap4_keypad_probe(struct platform_device *pdev)
 
 	keypad_data->irq = irq;
 
-	if (pdata) {
-		keypad_data->rows = pdata->rows;
-		keypad_data->cols = pdata->cols;
-	} else {
-		error = omap4_keypad_parse_dt(&pdev->dev, keypad_data);
-		if (error)
-			return error;
-	}
+	error = omap4_keypad_parse_dt(&pdev->dev, keypad_data);
+	if (error)
+		return error;
 
 	res = request_mem_region(res->start, resource_size(res), pdev->name);
 	if (!res) {
@@ -363,7 +345,7 @@ static int omap4_keypad_probe(struct platform_device *pdev)
 		goto err_free_input;
 	}
 
-	error = matrix_keypad_build_keymap(keymap_data, NULL,
+	error = matrix_keypad_build_keymap(NULL, NULL,
 					   keypad_data->rows, keypad_data->cols,
 					   keypad_data->keymap, input_dev);
 	if (error) {
@@ -434,13 +416,11 @@ static int omap4_keypad_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_OF
 static const struct of_device_id omap_keypad_dt_match[] = {
 	{ .compatible = "ti,omap4-keypad" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, omap_keypad_dt_match);
-#endif
 
 #ifdef CONFIG_PM_SLEEP
 static int omap4_keypad_suspend(struct device *dev)
@@ -482,7 +462,7 @@ static struct platform_driver omap4_keypad_driver = {
 		.name	= "omap4-keypad",
 		.owner	= THIS_MODULE,
 		.pm	= &omap4_keypad_pm_ops,
-		.of_match_table = of_match_ptr(omap_keypad_dt_match),
+		.of_match_table = omap_keypad_dt_match,
 	},
 };
 module_platform_driver(omap4_keypad_driver);
diff --git a/drivers/input/keyboard/st-keyscan.c b/drivers/input/keyboard/st-keyscan.c
new file mode 100644
index 00000000000..de7be4f03d9
--- /dev/null
+++ b/drivers/input/keyboard/st-keyscan.c
@@ -0,0 +1,276 @@
+/*
+ * STMicroelectronics Key Scanning driver
+ *
+ * Copyright (c) 2014 STMicroelectonics Ltd.
+ * Author: Stuart Menefy <stuart.menefy@st.com>
+ *
+ * Based on sh_keysc.c, copyright 2008 Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/input/matrix_keypad.h>
+
+#define ST_KEYSCAN_MAXKEYS 16
+
+#define KEYSCAN_CONFIG_OFF		0x0
+#define KEYSCAN_CONFIG_ENABLE		0x1
+#define KEYSCAN_DEBOUNCE_TIME_OFF	0x4
+#define KEYSCAN_MATRIX_STATE_OFF	0x8
+#define KEYSCAN_MATRIX_DIM_OFF		0xc
+#define KEYSCAN_MATRIX_DIM_X_SHIFT	0x0
+#define KEYSCAN_MATRIX_DIM_Y_SHIFT	0x2
+
+struct st_keyscan {
+	void __iomem *base;
+	int irq;
+	struct clk *clk;
+	struct input_dev *input_dev;
+	unsigned long last_state;
+	unsigned int n_rows;
+	unsigned int n_cols;
+	unsigned int debounce_us;
+};
+
+static irqreturn_t keyscan_isr(int irq, void *dev_id)
+{
+	struct st_keyscan *keypad = dev_id;
+	unsigned short *keycode = keypad->input_dev->keycode;
+	unsigned long state, change;
+	int bit_nr;
+
+	state = readl(keypad->base + KEYSCAN_MATRIX_STATE_OFF) & 0xffff;
+	change = keypad->last_state ^ state;
+	keypad->last_state = state;
+
+	for_each_set_bit(bit_nr, &change, BITS_PER_LONG)
+		input_report_key(keypad->input_dev,
+				 keycode[bit_nr], state & BIT(bit_nr));
+
+	input_sync(keypad->input_dev);
+
+	return IRQ_HANDLED;
+}
+
+static int keyscan_start(struct st_keyscan *keypad)
+{
+	int error;
+
+	error = clk_enable(keypad->clk);
+	if (error)
+		return error;
+
+	writel(keypad->debounce_us * (clk_get_rate(keypad->clk) / 1000000),
+	       keypad->base + KEYSCAN_DEBOUNCE_TIME_OFF);
+
+	writel(((keypad->n_cols - 1) << KEYSCAN_MATRIX_DIM_X_SHIFT) |
+	       ((keypad->n_rows - 1) << KEYSCAN_MATRIX_DIM_Y_SHIFT),
+	       keypad->base + KEYSCAN_MATRIX_DIM_OFF);
+
+	writel(KEYSCAN_CONFIG_ENABLE, keypad->base + KEYSCAN_CONFIG_OFF);
+
+	return 0;
+}
+
+static void keyscan_stop(struct st_keyscan *keypad)
+{
+	writel(0, keypad->base + KEYSCAN_CONFIG_OFF);
+
+	clk_disable(keypad->clk);
+}
+
+static int keyscan_open(struct input_dev *dev)
+{
+	struct st_keyscan *keypad = input_get_drvdata(dev);
+
+	return keyscan_start(keypad);
+}
+
+static void keyscan_close(struct input_dev *dev)
+{
+	struct st_keyscan *keypad = input_get_drvdata(dev);
+
+	keyscan_stop(keypad);
+}
+
+static int keypad_matrix_key_parse_dt(struct st_keyscan *keypad_data)
+{
+	struct device *dev = keypad_data->input_dev->dev.parent;
+	struct device_node *np = dev->of_node;
+	int error;
+
+	error = matrix_keypad_parse_of_params(dev, &keypad_data->n_rows,
+					      &keypad_data->n_cols);
+	if (error) {
+		dev_err(dev, "failed to parse keypad params\n");
+		return error;
+	}
+
+	of_property_read_u32(np, "st,debounce-us", &keypad_data->debounce_us);
+
+	dev_dbg(dev, "n_rows=%d n_col=%d debounce=%d\n",
+		keypad_data->n_rows, keypad_data->n_cols,
+		keypad_data->debounce_us);
+
+	return 0;
+}
+
+static int keyscan_probe(struct platform_device *pdev)
+{
+	struct st_keyscan *keypad_data;
+	struct input_dev *input_dev;
+	struct resource *res;
+	int error;
+
+	if (!pdev->dev.of_node) {
+		dev_err(&pdev->dev, "no DT data present\n");
+		return -EINVAL;
+	}
+
+	keypad_data = devm_kzalloc(&pdev->dev, sizeof(*keypad_data),
+				   GFP_KERNEL);
+	if (!keypad_data)
+		return -ENOMEM;
+
+	input_dev = devm_input_allocate_device(&pdev->dev);
+	if (!input_dev) {
+		dev_err(&pdev->dev, "failed to allocate the input device\n");
+		return -ENOMEM;
+	}
+
+	input_dev->name = pdev->name;
+	input_dev->phys = "keyscan-keys/input0";
+	input_dev->dev.parent = &pdev->dev;
+	input_dev->open = keyscan_open;
+	input_dev->close = keyscan_close;
+
+	input_dev->id.bustype = BUS_HOST;
+
+	error = keypad_matrix_key_parse_dt(keypad_data);
+	if (error)
+		return error;
+
+	error = matrix_keypad_build_keymap(NULL, NULL,
+					   keypad_data->n_rows,
+					   keypad_data->n_cols,
+					   NULL, input_dev);
+	if (error) {
+		dev_err(&pdev->dev, "failed to build keymap\n");
+		return error;
+	}
+
+	input_set_drvdata(input_dev, keypad_data);
+
+	keypad_data->input_dev = input_dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	keypad_data->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(keypad_data->base))
+		return PTR_ERR(keypad_data->base);
+
+	keypad_data->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(keypad_data->clk)) {
+		dev_err(&pdev->dev, "cannot get clock\n");
+		return PTR_ERR(keypad_data->clk);
+	}
+
+	error = clk_enable(keypad_data->clk);
+	if (error) {
+		dev_err(&pdev->dev, "failed to enable clock\n");
+		return error;
+	}
+
+	keyscan_stop(keypad_data);
+
+	keypad_data->irq = platform_get_irq(pdev, 0);
+	if (keypad_data->irq < 0) {
+		dev_err(&pdev->dev, "no IRQ specified\n");
+		return -EINVAL;
+	}
+
+	error = devm_request_irq(&pdev->dev, keypad_data->irq, keyscan_isr, 0,
+				 pdev->name, keypad_data);
+	if (error) {
+		dev_err(&pdev->dev, "failed to request IRQ\n");
+		return error;
+	}
+
+	error = input_register_device(input_dev);
+	if (error) {
+		dev_err(&pdev->dev, "failed to register input device\n");
+		return error;
+	}
+
+	platform_set_drvdata(pdev, keypad_data);
+
+	device_set_wakeup_capable(&pdev->dev, 1);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int keyscan_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct st_keyscan *keypad = platform_get_drvdata(pdev);
+	struct input_dev *input = keypad->input_dev;
+
+	mutex_lock(&input->mutex);
+
+	if (device_may_wakeup(dev))
+		enable_irq_wake(keypad->irq);
+	else if (input->users)
+		keyscan_stop(keypad);
+
+	mutex_unlock(&input->mutex);
+	return 0;
+}
+
+static int keyscan_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct st_keyscan *keypad = platform_get_drvdata(pdev);
+	struct input_dev *input = keypad->input_dev;
+	int retval = 0;
+
+	mutex_lock(&input->mutex);
+
+	if (device_may_wakeup(dev))
+		disable_irq_wake(keypad->irq);
+	else if (input->users)
+		retval = keyscan_start(keypad);
+
+	mutex_unlock(&input->mutex);
+	return retval;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(keyscan_dev_pm_ops, keyscan_suspend, keyscan_resume);
+
+static const struct of_device_id keyscan_of_match[] = {
+	{ .compatible = "st,sti-keyscan" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, keyscan_of_match);
+
+static struct platform_driver keyscan_device_driver = {
+	.probe		= keyscan_probe,
+	.driver		= {
+		.name	= "st-keyscan",
+		.pm	= &keyscan_dev_pm_ops,
+		.of_match_table = of_match_ptr(keyscan_of_match),
+	}
+};
+
+module_platform_driver(keyscan_device_driver);
+
+MODULE_AUTHOR("Stuart Menefy <stuart.menefy@st.com>");
+MODULE_DESCRIPTION("STMicroelectronics keyscan device driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/input/keyboard/tc3589x-keypad.c b/drivers/input/keyboard/tc3589x-keypad.c
index 74494a35752..ad7abae6907 100644
--- a/drivers/input/keyboard/tc3589x-keypad.c
+++ b/drivers/input/keyboard/tc3589x-keypad.c
@@ -296,6 +296,65 @@ static void tc3589x_keypad_close(struct input_dev *input)
 	tc3589x_keypad_disable(keypad);
 }
 
+#ifdef CONFIG_OF
+static const struct tc3589x_keypad_platform_data *
+tc3589x_keypad_of_probe(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct tc3589x_keypad_platform_data *plat;
+	u32 cols, rows;
+	u32 debounce_ms;
+	int proplen;
+
+	if (!np)
+		return ERR_PTR(-ENODEV);
+
+	plat = devm_kzalloc(dev, sizeof(*plat), GFP_KERNEL);
+	if (!plat)
+		return ERR_PTR(-ENOMEM);
+
+	of_property_read_u32(np, "keypad,num-columns", &cols);
+	of_property_read_u32(np, "keypad,num-rows", &rows);
+	plat->kcol = (u8) cols;
+	plat->krow = (u8) rows;
+	if (!plat->krow || !plat->kcol ||
+	     plat->krow > TC_KPD_ROWS || plat->kcol > TC_KPD_COLUMNS) {
+		dev_err(dev,
+			"keypad columns/rows not properly specified (%ux%u)\n",
+			plat->kcol, plat->krow);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!of_get_property(np, "linux,keymap", &proplen)) {
+		dev_err(dev, "property linux,keymap not found\n");
+		return ERR_PTR(-ENOENT);
+	}
+
+	plat->no_autorepeat = of_property_read_bool(np, "linux,no-autorepeat");
+	plat->enable_wakeup = of_property_read_bool(np, "linux,wakeup");
+
+	/* The custom delay format is ms/16 */
+	of_property_read_u32(np, "debounce-delay-ms", &debounce_ms);
+	if (debounce_ms)
+		plat->debounce_period = debounce_ms * 16;
+	else
+		plat->debounce_period = TC_KPD_DEBOUNCE_PERIOD;
+
+	plat->settle_time = TC_KPD_SETTLE_TIME;
+	/* FIXME: should be property of the IRQ resource? */
+	plat->irqtype = IRQF_TRIGGER_FALLING;
+
+	return plat;
+}
+#else
+static inline const struct tc3589x_keypad_platform_data *
+tc3589x_keypad_of_probe(struct device *dev)
+{
+	return ERR_PTR(-ENODEV);
+}
+#endif
+
+
 static int tc3589x_keypad_probe(struct platform_device *pdev)
 {
 	struct tc3589x *tc3589x = dev_get_drvdata(pdev->dev.parent);
@@ -306,8 +365,11 @@ static int tc3589x_keypad_probe(struct platform_device *pdev)
 
 	plat = tc3589x->pdata->keypad;
 	if (!plat) {
-		dev_err(&pdev->dev, "invalid keypad platform data\n");
-		return -EINVAL;
+		plat = tc3589x_keypad_of_probe(&pdev->dev);
+		if (IS_ERR(plat)) {
+			dev_err(&pdev->dev, "invalid keypad platform data\n");
+			return PTR_ERR(plat);
+		}
 	}
 
 	irq = platform_get_irq(pdev, 0);
diff --git a/drivers/input/misc/88pm860x_onkey.c b/drivers/input/misc/88pm860x_onkey.c
index abd8453e521..220ce0fa15d 100644
--- a/drivers/input/misc/88pm860x_onkey.c
+++ b/drivers/input/misc/88pm860x_onkey.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/mfd/88pm860x.h>
 #include <linux/slab.h>
+#include <linux/device.h>
 
 #define PM8607_WAKEUP		0x0b
 
@@ -68,7 +69,8 @@ static int pm860x_onkey_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	info = kzalloc(sizeof(struct pm860x_onkey_info), GFP_KERNEL);
+	info = devm_kzalloc(&pdev->dev, sizeof(struct pm860x_onkey_info),
+			    GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 	info->chip = chip;
@@ -76,11 +78,10 @@ static int pm860x_onkey_probe(struct platform_device *pdev)
 	info->dev = &pdev->dev;
 	info->irq = irq;
 
-	info->idev = input_allocate_device();
+	info->idev = devm_input_allocate_device(&pdev->dev);
 	if (!info->idev) {
 		dev_err(chip->dev, "Failed to allocate input dev\n");
-		ret = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
 
 	info->idev->name = "88pm860x_on";
@@ -93,42 +94,22 @@ static int pm860x_onkey_probe(struct platform_device *pdev)
 	ret = input_register_device(info->idev);
 	if (ret) {
 		dev_err(chip->dev, "Can't register input device: %d\n", ret);
-		goto out_reg;
+		return ret;
 	}
 
-	ret = request_threaded_irq(info->irq, NULL, pm860x_onkey_handler,
-				   IRQF_ONESHOT, "onkey", info);
+	ret = devm_request_threaded_irq(&pdev->dev, info->irq, NULL,
+					pm860x_onkey_handler, IRQF_ONESHOT,
+					"onkey", info);
 	if (ret < 0) {
 		dev_err(chip->dev, "Failed to request IRQ: #%d: %d\n",
 			info->irq, ret);
-		goto out_irq;
+		return ret;
 	}
 
 	platform_set_drvdata(pdev, info);
 	device_init_wakeup(&pdev->dev, 1);
 
 	return 0;
-
-out_irq:
-	input_unregister_device(info->idev);
-	kfree(info);
-	return ret;
-
-out_reg:
-	input_free_device(info->idev);
-out:
-	kfree(info);
-	return ret;
-}
-
-static int pm860x_onkey_remove(struct platform_device *pdev)
-{
-	struct pm860x_onkey_info *info = platform_get_drvdata(pdev);
-
-	free_irq(info->irq, info);
-	input_unregister_device(info->idev);
-	kfree(info);
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -161,7 +142,6 @@ static struct platform_driver pm860x_onkey_driver = {
 		.pm	= &pm860x_onkey_pm_ops,
 	},
 	.probe		= pm860x_onkey_probe,
-	.remove		= pm860x_onkey_remove,
 };
 module_platform_driver(pm860x_onkey_driver);
 
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 5928ea71dd6..2ff4425a893 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -224,7 +224,7 @@ config INPUT_GP2A
 
 config INPUT_GPIO_BEEPER
 	tristate "Generic GPIO Beeper support"
-	depends on OF_GPIO
+	depends on GPIOLIB
 	help
 	  Say Y here if you have a beeper connected to a GPIO pin.
 
diff --git a/drivers/input/misc/ab8500-ponkey.c b/drivers/input/misc/ab8500-ponkey.c
index f2fbdd88ed2..95ef7dd6442 100644
--- a/drivers/input/misc/ab8500-ponkey.c
+++ b/drivers/input/misc/ab8500-ponkey.c
@@ -7,6 +7,7 @@
  * AB8500 Power-On Key handler
  */
 
+#include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -65,12 +66,14 @@ static int ab8500_ponkey_probe(struct platform_device *pdev)
 		return irq_dbr;
 	}
 
-	ponkey = kzalloc(sizeof(struct ab8500_ponkey), GFP_KERNEL);
-	input = input_allocate_device();
-	if (!ponkey || !input) {
-		error = -ENOMEM;
-		goto err_free_mem;
-	}
+	ponkey = devm_kzalloc(&pdev->dev, sizeof(struct ab8500_ponkey),
+			      GFP_KERNEL);
+	if (!ponkey)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(&pdev->dev);
+	if (!input)
+		return -ENOMEM;
 
 	ponkey->idev = input;
 	ponkey->ab8500 = ab8500;
@@ -82,52 +85,32 @@ static int ab8500_ponkey_probe(struct platform_device *pdev)
 
 	input_set_capability(input, EV_KEY, KEY_POWER);
 
-	error = request_any_context_irq(ponkey->irq_dbf, ab8500_ponkey_handler,
-					0, "ab8500-ponkey-dbf", ponkey);
+	error = devm_request_any_context_irq(&pdev->dev, ponkey->irq_dbf,
+					     ab8500_ponkey_handler, 0,
+					     "ab8500-ponkey-dbf", ponkey);
 	if (error < 0) {
 		dev_err(ab8500->dev, "Failed to request dbf IRQ#%d: %d\n",
 			ponkey->irq_dbf, error);
-		goto err_free_mem;
+		return error;
 	}
 
-	error = request_any_context_irq(ponkey->irq_dbr, ab8500_ponkey_handler,
-					0, "ab8500-ponkey-dbr", ponkey);
+	error = devm_request_any_context_irq(&pdev->dev, ponkey->irq_dbr,
+					     ab8500_ponkey_handler, 0,
+					     "ab8500-ponkey-dbr", ponkey);
 	if (error < 0) {
 		dev_err(ab8500->dev, "Failed to request dbr IRQ#%d: %d\n",
 			ponkey->irq_dbr, error);
-		goto err_free_dbf_irq;
+		return error;
 	}
 
 	error = input_register_device(ponkey->idev);
 	if (error) {
 		dev_err(ab8500->dev, "Can't register input device: %d\n", error);
-		goto err_free_dbr_irq;
+		return error;
 	}
 
 	platform_set_drvdata(pdev, ponkey);
 	return 0;
-
-err_free_dbr_irq:
-	free_irq(ponkey->irq_dbr, ponkey);
-err_free_dbf_irq:
-	free_irq(ponkey->irq_dbf, ponkey);
-err_free_mem:
-	input_free_device(input);
-	kfree(ponkey);
-
-	return error;
-}
-
-static int ab8500_ponkey_remove(struct platform_device *pdev)
-{
-	struct ab8500_ponkey *ponkey = platform_get_drvdata(pdev);
-
-	free_irq(ponkey->irq_dbf, ponkey);
-	free_irq(ponkey->irq_dbr, ponkey);
-	input_unregister_device(ponkey->idev);
-	kfree(ponkey);
-
-	return 0;
 }
 
 #ifdef CONFIG_OF
@@ -144,7 +127,6 @@ static struct platform_driver ab8500_ponkey_driver = {
 		.of_match_table = of_match_ptr(ab8500_ponkey_match),
 	},
 	.probe		= ab8500_ponkey_probe,
-	.remove		= ab8500_ponkey_remove,
 };
 module_platform_driver(ab8500_ponkey_driver);
 
diff --git a/drivers/input/misc/gpio-beeper.c b/drivers/input/misc/gpio-beeper.c
index b757435e2b3..8886af63eae 100644
--- a/drivers/input/misc/gpio-beeper.c
+++ b/drivers/input/misc/gpio-beeper.c
@@ -1,7 +1,7 @@
 /*
  * Generic GPIO beeper driver
  *
- * Copyright (C) 2013 Alexander Shiyan <shc_work@mail.ru>
+ * Copyright (C) 2013-2014 Alexander Shiyan <shc_work@mail.ru>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -11,7 +11,8 @@
 
 #include <linux/input.h>
 #include <linux/module.h>
-#include <linux/of_gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of.h>
 #include <linux/workqueue.h>
 #include <linux/platform_device.h>
 
@@ -19,14 +20,13 @@
 
 struct gpio_beeper {
 	struct work_struct	work;
-	int			gpio;
-	bool			active_low;
+	struct gpio_desc	*desc;
 	bool			beeping;
 };
 
 static void gpio_beeper_toggle(struct gpio_beeper *beep, bool on)
 {
-	gpio_set_value_cansleep(beep->gpio, on ^ beep->active_low);
+	gpiod_set_value_cansleep(beep->desc, on);
 }
 
 static void gpio_beeper_work(struct work_struct *work)
@@ -65,18 +65,16 @@ static void gpio_beeper_close(struct input_dev *input)
 static int gpio_beeper_probe(struct platform_device *pdev)
 {
 	struct gpio_beeper *beep;
-	enum of_gpio_flags flags;
 	struct input_dev *input;
-	unsigned long gflags;
 	int err;
 
 	beep = devm_kzalloc(&pdev->dev, sizeof(*beep), GFP_KERNEL);
 	if (!beep)
 		return -ENOMEM;
 
-	beep->gpio = of_get_gpio_flags(pdev->dev.of_node, 0, &flags);
-	if (!gpio_is_valid(beep->gpio))
-		return beep->gpio;
+	beep->desc = devm_gpiod_get(&pdev->dev, NULL);
+	if (IS_ERR(beep->desc))
+		return PTR_ERR(beep->desc);
 
 	input = devm_input_allocate_device(&pdev->dev);
 	if (!input)
@@ -94,10 +92,7 @@ static int gpio_beeper_probe(struct platform_device *pdev)
 
 	input_set_capability(input, EV_SND, SND_BELL);
 
-	beep->active_low = flags & OF_GPIO_ACTIVE_LOW;
-	gflags = beep->active_low ? GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW;
-
-	err = devm_gpio_request_one(&pdev->dev, beep->gpio, gflags, pdev->name);
+	err = gpiod_direction_output(beep->desc, 0);
 	if (err)
 		return err;
 
@@ -106,17 +101,19 @@ static int gpio_beeper_probe(struct platform_device *pdev)
 	return input_register_device(input);
 }
 
-static struct of_device_id gpio_beeper_of_match[] = {
+#ifdef CONFIG_OF
+static const struct of_device_id gpio_beeper_of_match[] = {
 	{ .compatible = BEEPER_MODNAME, },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, gpio_beeper_of_match);
+#endif
 
 static struct platform_driver gpio_beeper_platform_driver = {
 	.driver	= {
 		.name		= BEEPER_MODNAME,
 		.owner		= THIS_MODULE,
-		.of_match_table	= gpio_beeper_of_match,
+		.of_match_table	= of_match_ptr(gpio_beeper_of_match),
 	},
 	.probe	= gpio_beeper_probe,
 };
diff --git a/drivers/input/misc/ims-pcu.c b/drivers/input/misc/ims-pcu.c
index 5a736397d9c..719410feb84 100644
--- a/drivers/input/misc/ims-pcu.c
+++ b/drivers/input/misc/ims-pcu.c
@@ -1566,6 +1566,7 @@ static int ims_pcu_buffers_alloc(struct ims_pcu *pcu)
 	if (!pcu->urb_ctrl_buf) {
 		dev_err(pcu->dev,
 			"Failed to allocate memory for read buffer\n");
+		error = -ENOMEM;
 		goto err_free_urb_out_buf;
 	}
 
diff --git a/drivers/input/misc/max8925_onkey.c b/drivers/input/misc/max8925_onkey.c
index eef41cfc054..3809618e6a5 100644
--- a/drivers/input/misc/max8925_onkey.c
+++ b/drivers/input/misc/max8925_onkey.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/mfd/max8925.h>
 #include <linux/slab.h>
+#include <linux/device.h>
 
 #define SW_INPUT		(1 << 7)	/* 0/1 -- up/down */
 #define HARDRESET_EN		(1 << 7)
@@ -81,12 +82,14 @@ static int max8925_onkey_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	info = kzalloc(sizeof(struct max8925_onkey_info), GFP_KERNEL);
-	input = input_allocate_device();
-	if (!info || !input) {
-		error = -ENOMEM;
-		goto err_free_mem;
-	}
+	info = devm_kzalloc(&pdev->dev, sizeof(struct max8925_onkey_info),
+			    GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(&pdev->dev);
+	if (!input)
+		return -ENOMEM;
 
 	info->idev = input;
 	info->i2c = chip->i2c;
@@ -100,55 +103,34 @@ static int max8925_onkey_probe(struct platform_device *pdev)
 	input->dev.parent = &pdev->dev;
 	input_set_capability(input, EV_KEY, KEY_POWER);
 
-	error = request_threaded_irq(irq[0], NULL, max8925_onkey_handler,
-				     IRQF_ONESHOT, "onkey-down", info);
+	error = devm_request_threaded_irq(&pdev->dev, irq[0], NULL,
+					  max8925_onkey_handler, IRQF_ONESHOT,
+					  "onkey-down", info);
 	if (error < 0) {
 		dev_err(chip->dev, "Failed to request IRQ: #%d: %d\n",
 			irq[0], error);
-		goto err_free_mem;
+		return error;
 	}
 
-	error = request_threaded_irq(irq[1], NULL, max8925_onkey_handler,
-				     IRQF_ONESHOT, "onkey-up", info);
+	error = devm_request_threaded_irq(&pdev->dev, irq[1], NULL,
+					  max8925_onkey_handler, IRQF_ONESHOT,
+					  "onkey-up", info);
 	if (error < 0) {
 		dev_err(chip->dev, "Failed to request IRQ: #%d: %d\n",
 			irq[1], error);
-		goto err_free_irq0;
+		return error;
 	}
 
 	error = input_register_device(info->idev);
 	if (error) {
 		dev_err(chip->dev, "Can't register input device: %d\n", error);
-		goto err_free_irq1;
+		return error;
 	}
 
 	platform_set_drvdata(pdev, info);
 	device_init_wakeup(&pdev->dev, 1);
 
 	return 0;
-
-err_free_irq1:
-	free_irq(irq[1], info);
-err_free_irq0:
-	free_irq(irq[0], info);
-err_free_mem:
-	input_free_device(input);
-	kfree(info);
-
-	return error;
-}
-
-static int max8925_onkey_remove(struct platform_device *pdev)
-{
-	struct max8925_onkey_info *info = platform_get_drvdata(pdev);
-	struct max8925_chip *chip = dev_get_drvdata(pdev->dev.parent);
-
-	free_irq(info->irq[0] + chip->irq_base, info);
-	free_irq(info->irq[1] + chip->irq_base, info);
-	input_unregister_device(info->idev);
-	kfree(info);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -190,7 +172,6 @@ static struct platform_driver max8925_onkey_driver = {
 		.pm	= &max8925_onkey_pm_ops,
 	},
 	.probe		= max8925_onkey_probe,
-	.remove		= max8925_onkey_remove,
 };
 module_platform_driver(max8925_onkey_driver);
 
diff --git a/drivers/input/misc/max8997_haptic.c b/drivers/input/misc/max8997_haptic.c
index 1fea5484941..a363ebbd9cc 100644
--- a/drivers/input/misc/max8997_haptic.c
+++ b/drivers/input/misc/max8997_haptic.c
@@ -181,11 +181,21 @@ static void max8997_haptic_enable(struct max8997_haptic *chip)
 	}
 
 	if (!chip->enabled) {
-		chip->enabled = true;
-		regulator_enable(chip->regulator);
+		error = regulator_enable(chip->regulator);
+		if (error) {
+			dev_err(chip->dev, "Failed to enable regulator\n");
+			goto out;
+		}
 		max8997_haptic_configure(chip);
-		if (chip->mode == MAX8997_EXTERNAL_MODE)
-			pwm_enable(chip->pwm);
+		if (chip->mode == MAX8997_EXTERNAL_MODE) {
+			error = pwm_enable(chip->pwm);
+			if (error) {
+				dev_err(chip->dev, "Failed to enable PWM\n");
+				regulator_disable(chip->regulator);
+				goto out;
+			}
+		}
+		chip->enabled = true;
 	}
 
 out:
diff --git a/drivers/input/misc/pmic8xxx-pwrkey.c b/drivers/input/misc/pmic8xxx-pwrkey.c
index 1cb8fda7a16..c91e3d33aea 100644
--- a/drivers/input/misc/pmic8xxx-pwrkey.c
+++ b/drivers/input/misc/pmic8xxx-pwrkey.c
@@ -92,15 +92,15 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev)
 	bool pull_up;
 
 	if (of_property_read_u32(pdev->dev.of_node, "debounce", &kpd_delay))
-		kpd_delay = 0;
+		kpd_delay = 15625;
 
-	pull_up = of_property_read_bool(pdev->dev.of_node, "pull-up");
-
-	if (kpd_delay > 62500) {
+	if (kpd_delay > 62500 || kpd_delay == 0) {
 		dev_err(&pdev->dev, "invalid power key trigger delay\n");
 		return -EINVAL;
 	}
 
+	pull_up = of_property_read_bool(pdev->dev.of_node, "pull-up");
+
 	regmap = dev_get_regmap(pdev->dev.parent, NULL);
 	if (!regmap) {
 		dev_err(&pdev->dev, "failed to locate regmap for the device\n");
diff --git a/drivers/input/misc/rotary_encoder.c b/drivers/input/misc/rotary_encoder.c
index 99b9e42aa74..93558a1c7f7 100644
--- a/drivers/input/misc/rotary_encoder.c
+++ b/drivers/input/misc/rotary_encoder.c
@@ -143,7 +143,7 @@ static irqreturn_t rotary_encoder_half_period_irq(int irq, void *dev_id)
 }
 
 #ifdef CONFIG_OF
-static struct of_device_id rotary_encoder_of_match[] = {
+static const struct of_device_id rotary_encoder_of_match[] = {
 	{ .compatible = "rotary-encoder", },
 	{ },
 };
diff --git a/drivers/input/misc/sirfsoc-onkey.c b/drivers/input/misc/sirfsoc-onkey.c
index e4104f9b2e6..fed5102e180 100644
--- a/drivers/input/misc/sirfsoc-onkey.c
+++ b/drivers/input/misc/sirfsoc-onkey.c
@@ -213,7 +213,7 @@ static struct platform_driver sirfsoc_pwrc_driver = {
 
 module_platform_driver(sirfsoc_pwrc_driver);
 
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Binghua Duan <Binghua.Duan@csr.com>, Xianglong Du <Xianglong.Du@csr.com>");
 MODULE_DESCRIPTION("CSR Prima2 PWRC Driver");
 MODULE_ALIAS("platform:sirfsoc-pwrc");
diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c
index 20c80f543d5..5a6334be30b 100644
--- a/drivers/input/misc/soc_button_array.c
+++ b/drivers/input/misc/soc_button_array.c
@@ -17,7 +17,6 @@
 #include <linux/acpi.h>
 #include <linux/gpio/consumer.h>
 #include <linux/gpio_keys.h>
-#include <linux/input.h>
 #include <linux/platform_device.h>
 #include <linux/pnp.h>
 
diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c
index 77dc23b94eb..6d26eecc278 100644
--- a/drivers/input/misc/twl6040-vibra.c
+++ b/drivers/input/misc/twl6040-vibra.c
@@ -262,7 +262,7 @@ static int twl6040_vibra_probe(struct platform_device *pdev)
 	struct vibra_info *info;
 	int vddvibl_uV = 0;
 	int vddvibr_uV = 0;
-	int ret;
+	int error;
 
 	twl6040_core_node = of_find_node_by_name(twl6040_core_dev->of_node,
 						 "vibra");
@@ -309,12 +309,12 @@ static int twl6040_vibra_probe(struct platform_device *pdev)
 
 	mutex_init(&info->mutex);
 
-	ret = devm_request_threaded_irq(&pdev->dev, info->irq, NULL,
-					twl6040_vib_irq_handler, 0,
-					"twl6040_irq_vib", info);
-	if (ret) {
-		dev_err(info->dev, "VIB IRQ request failed: %d\n", ret);
-		return ret;
+	error = devm_request_threaded_irq(&pdev->dev, info->irq, NULL,
+					  twl6040_vib_irq_handler, 0,
+					  "twl6040_irq_vib", info);
+	if (error) {
+		dev_err(info->dev, "VIB IRQ request failed: %d\n", error);
+		return error;
 	}
 
 	info->supplies[0].supply = "vddvibl";
@@ -323,40 +323,40 @@ static int twl6040_vibra_probe(struct platform_device *pdev)
 	 * When booted with Device tree the regulators are attached to the
 	 * parent device (twl6040 MFD core)
 	 */
-	ret = regulator_bulk_get(twl6040_core_dev, ARRAY_SIZE(info->supplies),
-				 info->supplies);
-	if (ret) {
-		dev_err(info->dev, "couldn't get regulators %d\n", ret);
-		return ret;
+	error = devm_regulator_bulk_get(twl6040_core_dev,
+					ARRAY_SIZE(info->supplies),
+					info->supplies);
+	if (error) {
+		dev_err(info->dev, "couldn't get regulators %d\n", error);
+		return error;
 	}
 
 	if (vddvibl_uV) {
-		ret = regulator_set_voltage(info->supplies[0].consumer,
-					    vddvibl_uV, vddvibl_uV);
-		if (ret) {
+		error = regulator_set_voltage(info->supplies[0].consumer,
+					      vddvibl_uV, vddvibl_uV);
+		if (error) {
 			dev_err(info->dev, "failed to set VDDVIBL volt %d\n",
-				ret);
-			goto err_regulator;
+				error);
+			return error;
 		}
 	}
 
 	if (vddvibr_uV) {
-		ret = regulator_set_voltage(info->supplies[1].consumer,
-					    vddvibr_uV, vddvibr_uV);
-		if (ret) {
+		error = regulator_set_voltage(info->supplies[1].consumer,
+					      vddvibr_uV, vddvibr_uV);
+		if (error) {
 			dev_err(info->dev, "failed to set VDDVIBR volt %d\n",
-				ret);
-			goto err_regulator;
+				error);
+			return error;
 		}
 	}
 
 	INIT_WORK(&info->play_work, vibra_play_work);
 
-	info->input_dev = input_allocate_device();
-	if (info->input_dev == NULL) {
+	info->input_dev = devm_input_allocate_device(&pdev->dev);
+	if (!info->input_dev) {
 		dev_err(info->dev, "couldn't allocate input device\n");
-		ret = -ENOMEM;
-		goto err_regulator;
+		return -ENOMEM;
 	}
 
 	input_set_drvdata(info->input_dev, info);
@@ -367,44 +367,25 @@ static int twl6040_vibra_probe(struct platform_device *pdev)
 	info->input_dev->close = twl6040_vibra_close;
 	__set_bit(FF_RUMBLE, info->input_dev->ffbit);
 
-	ret = input_ff_create_memless(info->input_dev, NULL, vibra_play);
-	if (ret < 0) {
+	error = input_ff_create_memless(info->input_dev, NULL, vibra_play);
+	if (error) {
 		dev_err(info->dev, "couldn't register vibrator to FF\n");
-		goto err_ialloc;
+		return error;
 	}
 
-	ret = input_register_device(info->input_dev);
-	if (ret < 0) {
+	error = input_register_device(info->input_dev);
+	if (error) {
 		dev_err(info->dev, "couldn't register input device\n");
-		goto err_iff;
+		return error;
 	}
 
 	platform_set_drvdata(pdev, info);
 
 	return 0;
-
-err_iff:
-	input_ff_destroy(info->input_dev);
-err_ialloc:
-	input_free_device(info->input_dev);
-err_regulator:
-	regulator_bulk_free(ARRAY_SIZE(info->supplies), info->supplies);
-	return ret;
-}
-
-static int twl6040_vibra_remove(struct platform_device *pdev)
-{
-	struct vibra_info *info = platform_get_drvdata(pdev);
-
-	input_unregister_device(info->input_dev);
-	regulator_bulk_free(ARRAY_SIZE(info->supplies), info->supplies);
-
-	return 0;
 }
 
 static struct platform_driver twl6040_vibra_driver = {
 	.probe		= twl6040_vibra_probe,
-	.remove		= twl6040_vibra_remove,
 	.driver		= {
 		.name	= "twl6040-vibra",
 		.owner	= THIS_MODULE,
diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig
index 6b8441f7bc3..366fc7ad5eb 100644
--- a/drivers/input/mouse/Kconfig
+++ b/drivers/input/mouse/Kconfig
@@ -53,7 +53,7 @@ config MOUSE_PS2_LOGIPS2PP
 	default y
 	depends on MOUSE_PS2
 	help
-	  Say Y here if you have a Logictech PS/2++ mouse connected to
+	  Say Y here if you have a Logitech PS/2++ mouse connected to
 	  your system.
 
 	  If unsure, say Y.
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index b96e978a37b..ee2a04d90d2 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -473,8 +473,15 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse,
 	input_report_key(dev, BTN_TOOL_FINGER, fingers == 1);
 	input_report_key(dev, BTN_TOOL_DOUBLETAP, fingers == 2);
 	input_report_key(dev, BTN_TOOL_TRIPLETAP, fingers == 3);
-	input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
-	input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+
+	/* For clickpads map both buttons to BTN_LEFT */
+	if (etd->fw_version & 0x001000) {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+	} else {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+		input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	}
+
 	input_report_abs(dev, ABS_PRESSURE, pres);
 	input_report_abs(dev, ABS_TOOL_WIDTH, width);
 
@@ -484,10 +491,17 @@ static void elantech_report_absolute_v3(struct psmouse *psmouse,
 static void elantech_input_sync_v4(struct psmouse *psmouse)
 {
 	struct input_dev *dev = psmouse->dev;
+	struct elantech_data *etd = psmouse->private;
 	unsigned char *packet = psmouse->packet;
 
-	input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
-	input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	/* For clickpads map both buttons to BTN_LEFT */
+	if (etd->fw_version & 0x001000) {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x03);
+	} else {
+		input_report_key(dev, BTN_LEFT, packet[0] & 0x01);
+		input_report_key(dev, BTN_RIGHT, packet[0] & 0x02);
+	}
+
 	input_mt_report_pointer_emulation(dev, true);
 	input_sync(dev);
 }
@@ -835,7 +849,7 @@ static int elantech_set_absolute_mode(struct psmouse *psmouse)
 		if (etd->set_hw_resolution)
 			etd->reg_10 = 0x0b;
 		else
-			etd->reg_10 = 0x03;
+			etd->reg_10 = 0x01;
 
 		if (elantech_write_reg(psmouse, 0x10, etd->reg_10))
 			rc = -1;
@@ -1336,7 +1350,8 @@ static int elantech_reconnect(struct psmouse *psmouse)
 }
 
 /*
- * Some hw_version 3 models go into error state when we try to set bit 3 of r10
+ * Some hw_version 3 models go into error state when we try to set
+ * bit 3 and/or bit 1 of r10.
  */
 static const struct dmi_system_id no_hw_res_dmi_table[] = {
 #if defined(CONFIG_DMI) && defined(CONFIG_X86)
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index c5ec703c727..ef9e0b8a9aa 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -132,7 +132,8 @@ static const struct min_max_quirk min_max_pnpid_table[] = {
 		1232, 5710, 1156, 4696
 	},
 	{
-		(const char * const []){"LEN0034", "LEN0036", "LEN2004", NULL},
+		(const char * const []){"LEN0034", "LEN0036", "LEN2002",
+					"LEN2004", NULL},
 		1024, 5112, 2024, 4832
 	},
 	{
@@ -168,7 +169,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
 	"LEN0049",
 	"LEN2000",
 	"LEN2001", /* Edge E431 */
-	"LEN2002",
+	"LEN2002", /* Edge E531 */
 	"LEN2003",
 	"LEN2004", /* L440 */
 	"LEN2005",
@@ -347,15 +348,6 @@ static int synaptics_resolution(struct psmouse *psmouse)
 	unsigned char resp[3];
 	int i;
 
-	for (i = 0; min_max_pnpid_table[i].pnp_ids; i++)
-		if (matches_pnp_id(psmouse, min_max_pnpid_table[i].pnp_ids)) {
-			priv->x_min = min_max_pnpid_table[i].x_min;
-			priv->x_max = min_max_pnpid_table[i].x_max;
-			priv->y_min = min_max_pnpid_table[i].y_min;
-			priv->y_max = min_max_pnpid_table[i].y_max;
-			return 0;
-		}
-
 	if (SYN_ID_MAJOR(priv->identity) < 4)
 		return 0;
 
@@ -366,6 +358,16 @@ static int synaptics_resolution(struct psmouse *psmouse)
 		}
 	}
 
+	for (i = 0; min_max_pnpid_table[i].pnp_ids; i++) {
+		if (matches_pnp_id(psmouse, min_max_pnpid_table[i].pnp_ids)) {
+			priv->x_min = min_max_pnpid_table[i].x_min;
+			priv->x_max = min_max_pnpid_table[i].x_max;
+			priv->y_min = min_max_pnpid_table[i].y_min;
+			priv->y_max = min_max_pnpid_table[i].y_max;
+			return 0;
+		}
+	}
+
 	if (SYN_EXT_CAP_REQUESTS(priv->capabilities) >= 5 &&
 	    SYN_CAP_MAX_DIMENSIONS(priv->ext_cap_0c)) {
 		if (synaptics_send_cmd(psmouse, SYN_QUE_EXT_MAX_COORDS, resp)) {
diff --git a/drivers/input/serio/apbps2.c b/drivers/input/serio/apbps2.c
index 17e01a807dd..98be824544a 100644
--- a/drivers/input/serio/apbps2.c
+++ b/drivers/input/serio/apbps2.c
@@ -203,7 +203,7 @@ static int apbps2_of_remove(struct platform_device *of_dev)
 	return 0;
 }
 
-static struct of_device_id apbps2_of_match[] = {
+static const struct of_device_id apbps2_of_match[] = {
 	{ .name = "GAISLER_APBPS2", },
 	{ .name = "01_060", },
 	{}
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index 381b20d4c56..136b7b204f5 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -402,6 +402,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 		},
 	},
 	{
+		/* Acer Aspire 5710 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5710"),
+		},
+	},
+	{
 		/* Gericom Bellagio */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Gericom"),
diff --git a/drivers/input/serio/olpc_apsp.c b/drivers/input/serio/olpc_apsp.c
index 5d2fe7ece7c..d906f3ebc8c 100644
--- a/drivers/input/serio/olpc_apsp.c
+++ b/drivers/input/serio/olpc_apsp.c
@@ -262,7 +262,7 @@ static int olpc_apsp_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id olpc_apsp_dt_ids[] = {
+static const struct of_device_id olpc_apsp_dt_ids[] = {
 	{ .compatible = "olpc,ap-sp", },
 	{}
 };
diff --git a/drivers/input/tablet/wacom_sys.c b/drivers/input/tablet/wacom_sys.c
index 611fc3905d0..2c613cd41dd 100644
--- a/drivers/input/tablet/wacom_sys.c
+++ b/drivers/input/tablet/wacom_sys.c
@@ -349,6 +349,7 @@ static int wacom_parse_hid(struct usb_interface *intf,
 						break;
 
 					case MTTPC:
+					case MTTPC_B:
 						features->pktlen = WACOM_PKGLEN_MTTPC;
 						break;
 
@@ -380,6 +381,16 @@ static int wacom_parse_hid(struct usb_interface *intf,
 						i += 12;
 						break;
 
+					case MTTPC_B:
+						features->x_max =
+							get_unaligned_le16(&report[i + 3]);
+						features->x_phy =
+							get_unaligned_le16(&report[i + 6]);
+						features->unit = report[i - 5];
+						features->unitExpo = report[i - 3];
+						i += 9;
+						break;
+
 					default:
 						features->x_max =
 							get_unaligned_le16(&report[i + 3]);
@@ -430,6 +441,14 @@ static int wacom_parse_hid(struct usb_interface *intf,
 						i += 12;
 						break;
 
+					case MTTPC_B:
+						features->y_max =
+							get_unaligned_le16(&report[i + 3]);
+						features->y_phy =
+							get_unaligned_le16(&report[i + 6]);
+						i += 9;
+						break;
+
 					default:
 						features->y_max =
 							features->x_max;
diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c
index 4822c57a375..e73cf2c71f3 100644
--- a/drivers/input/tablet/wacom_wac.c
+++ b/drivers/input/tablet/wacom_wac.c
@@ -484,6 +484,8 @@ static int wacom_intuos_inout(struct wacom_wac *wacom)
 		input_report_key(input, BTN_TOUCH, 0);
 		input_report_abs(input, ABS_PRESSURE, 0);
 		input_report_abs(input, ABS_DISTANCE, wacom->features.distance_max);
+		if (features->quirks & WACOM_QUIRK_MULTI_INPUT)
+			wacom->shared->stylus_in_proximity = true;
 	}
 
 	/* Exit report */
@@ -928,12 +930,12 @@ static int wacom_24hdt_irq(struct wacom_wac *wacom)
 		input_mt_report_slot_state(input, MT_TOOL_FINGER, touch);
 
 		if (touch) {
-			int t_x = le16_to_cpup((__le16 *)&data[offset + 2]);
-			int c_x = le16_to_cpup((__le16 *)&data[offset + 4]);
-			int t_y = le16_to_cpup((__le16 *)&data[offset + 6]);
-			int c_y = le16_to_cpup((__le16 *)&data[offset + 8]);
-			int w = le16_to_cpup((__le16 *)&data[offset + 10]);
-			int h = le16_to_cpup((__le16 *)&data[offset + 12]);
+			int t_x = get_unaligned_le16(&data[offset + 2]);
+			int c_x = get_unaligned_le16(&data[offset + 4]);
+			int t_y = get_unaligned_le16(&data[offset + 6]);
+			int c_y = get_unaligned_le16(&data[offset + 8]);
+			int w = get_unaligned_le16(&data[offset + 10]);
+			int h = get_unaligned_le16(&data[offset + 12]);
 
 			input_report_abs(input, ABS_MT_POSITION_X, t_x);
 			input_report_abs(input, ABS_MT_POSITION_Y, t_y);
@@ -962,7 +964,7 @@ static int wacom_mt_touch(struct wacom_wac *wacom)
 	int x_offset = 0;
 
 	/* MTTPC does not support Height and Width */
-	if (wacom->features.type == MTTPC)
+	if (wacom->features.type == MTTPC || wacom->features.type == MTTPC_B)
 		x_offset = -4;
 
 	/*
@@ -978,7 +980,7 @@ static int wacom_mt_touch(struct wacom_wac *wacom)
 	for (i = 0; i < contacts_to_send; i++) {
 		int offset = (WACOM_BYTES_PER_MT_PACKET + x_offset) * i + 3;
 		bool touch = data[offset] & 0x1;
-		int id = le16_to_cpup((__le16 *)&data[offset + 1]);
+		int id = get_unaligned_le16(&data[offset + 1]);
 		int slot = input_mt_get_slot_by_key(input, id);
 
 		if (slot < 0)
@@ -987,8 +989,8 @@ static int wacom_mt_touch(struct wacom_wac *wacom)
 		input_mt_slot(input, slot);
 		input_mt_report_slot_state(input, MT_TOOL_FINGER, touch);
 		if (touch) {
-			int x = le16_to_cpup((__le16 *)&data[offset + x_offset + 7]);
-			int y = le16_to_cpup((__le16 *)&data[offset + x_offset + 9]);
+			int x = get_unaligned_le16(&data[offset + x_offset + 7]);
+			int y = get_unaligned_le16(&data[offset + x_offset + 9]);
 			input_report_abs(input, ABS_MT_POSITION_X, x);
 			input_report_abs(input, ABS_MT_POSITION_Y, y);
 		}
@@ -1047,6 +1049,10 @@ static int wacom_tpc_single_touch(struct wacom_wac *wacom, size_t len)
 			prox = data[0] & 0x01;
 			x = get_unaligned_le16(&data[1]);
 			y = get_unaligned_le16(&data[3]);
+		} else if (len == WACOM_PKGLEN_TPC1FG_B) {
+			prox = data[2] & 0x01;
+			x = get_unaligned_le16(&data[3]);
+			y = get_unaligned_le16(&data[5]);
 		} else {
 			prox = data[1] & 0x01;
 			x = le16_to_cpup((__le16 *)&data[2]);
@@ -1110,6 +1116,9 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 	case WACOM_PKGLEN_TPC2FG:
 		return wacom_tpc_mt_touch(wacom);
 
+	case WACOM_PKGLEN_PENABLED:
+		return wacom_tpc_pen(wacom);
+
 	default:
 		switch (data[0]) {
 		case WACOM_REPORT_TPC1FG:
@@ -1119,6 +1128,7 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 			return wacom_tpc_single_touch(wacom, len);
 
 		case WACOM_REPORT_TPCMT:
+		case WACOM_REPORT_TPCMT2:
 			return wacom_mt_touch(wacom);
 
 		case WACOM_REPORT_PENABLED:
@@ -1207,9 +1217,9 @@ static void wacom_bpt3_touch_msg(struct wacom_wac *wacom, unsigned char *data)
 			 * a=(pi*r^2)/C.
 			 */
 			int a = data[5];
-			int x_res  = input_abs_get_res(input, ABS_X);
-			int y_res  = input_abs_get_res(input, ABS_Y);
-			width  = 2 * int_sqrt(a * WACOM_CONTACT_AREA_SCALE);
+			int x_res = input_abs_get_res(input, ABS_MT_POSITION_X);
+			int y_res = input_abs_get_res(input, ABS_MT_POSITION_Y);
+			width = 2 * int_sqrt(a * WACOM_CONTACT_AREA_SCALE);
 			height = width * y_res / x_res;
 		}
 
@@ -1461,6 +1471,7 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 	case TABLETPC2FG:
 	case MTSCREEN:
 	case MTTPC:
+	case MTTPC_B:
 		sync = wacom_tpc_irq(wacom_wac, len);
 		break;
 
@@ -1565,10 +1576,10 @@ static void wacom_abs_set_axis(struct input_dev *input_dev,
 	struct wacom_features *features = &wacom_wac->features;
 
 	if (features->device_type == BTN_TOOL_PEN) {
-		input_set_abs_params(input_dev, ABS_X, 0, features->x_max,
-				     features->x_fuzz, 0);
-		input_set_abs_params(input_dev, ABS_Y, 0, features->y_max,
-				     features->y_fuzz, 0);
+		input_set_abs_params(input_dev, ABS_X, features->x_min,
+				     features->x_max, features->x_fuzz, 0);
+		input_set_abs_params(input_dev, ABS_Y, features->y_min,
+				     features->y_max, features->y_fuzz, 0);
 		input_set_abs_params(input_dev, ABS_PRESSURE, 0,
 			features->pressure_max, features->pressure_fuzz, 0);
 
@@ -1576,7 +1587,7 @@ static void wacom_abs_set_axis(struct input_dev *input_dev,
 		input_abs_set_res(input_dev, ABS_X, features->x_resolution);
 		input_abs_set_res(input_dev, ABS_Y, features->y_resolution);
 	} else {
-		if (features->touch_max <= 2) {
+		if (features->touch_max == 1) {
 			input_set_abs_params(input_dev, ABS_X, 0,
 				features->x_max, features->x_fuzz, 0);
 			input_set_abs_params(input_dev, ABS_Y, 0,
@@ -1802,15 +1813,10 @@ int wacom_setup_input_capabilities(struct input_dev *input_dev,
 
 	case MTSCREEN:
 	case MTTPC:
+	case MTTPC_B:
 	case TABLETPC2FG:
-		if (features->device_type == BTN_TOOL_FINGER) {
-			unsigned int flags = INPUT_MT_DIRECT;
-
-			if (wacom_wac->features.type == TABLETPC2FG)
-				flags = 0;
-
-			input_mt_init_slots(input_dev, features->touch_max, flags);
-		}
+		if (features->device_type == BTN_TOOL_FINGER && features->touch_max > 1)
+			input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_DIRECT);
 		/* fall through */
 
 	case TABLETPC:
@@ -1871,10 +1877,6 @@ int wacom_setup_input_capabilities(struct input_dev *input_dev,
 			__set_bit(BTN_RIGHT, input_dev->keybit);
 
 			if (features->touch_max) {
-				/* touch interface */
-				unsigned int flags = INPUT_MT_POINTER;
-
-				__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
 				if (features->pktlen == WACOM_PKGLEN_BBTOUCH3) {
 					input_set_abs_params(input_dev,
 						     ABS_MT_TOUCH_MAJOR,
@@ -1882,12 +1884,8 @@ int wacom_setup_input_capabilities(struct input_dev *input_dev,
 					input_set_abs_params(input_dev,
 						     ABS_MT_TOUCH_MINOR,
 						     0, features->y_max, 0, 0);
-				} else {
-					__set_bit(BTN_TOOL_FINGER, input_dev->keybit);
-					__set_bit(BTN_TOOL_DOUBLETAP, input_dev->keybit);
-					flags = 0;
 				}
-				input_mt_init_slots(input_dev, features->touch_max, flags);
+				input_mt_init_slots(input_dev, features->touch_max, INPUT_MT_POINTER);
 			} else {
 				/* buttons/keys only interface */
 				__clear_bit(ABS_X, input_dev->absbit);
@@ -2123,11 +2121,11 @@ static const struct wacom_features wacom_features_0x317 =
 	  63, INTUOSPL, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES,
 	  .touch_max = 16 };
 static const struct wacom_features wacom_features_0xF4 =
-	{ "Wacom Cintiq 24HD",       WACOM_PKGLEN_INTUOS,   104480, 65600, 2047,
-	  63, WACOM_24HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES };
+	{ "Wacom Cintiq 24HD",       WACOM_PKGLEN_INTUOS,   104280, 65400, 2047,
+	  63, WACOM_24HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 200, 200 };
 static const struct wacom_features wacom_features_0xF8 =
-	{ "Wacom Cintiq 24HD touch", WACOM_PKGLEN_INTUOS,   104480, 65600, 2047, /* Pen */
-	  63, WACOM_24HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES,
+	{ "Wacom Cintiq 24HD touch", WACOM_PKGLEN_INTUOS,   104280, 65400, 2047, /* Pen */
+	  63, WACOM_24HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 200, 200,
 	  .oVid = USB_VENDOR_ID_WACOM, .oPid = 0xf6 };
 static const struct wacom_features wacom_features_0xF6 =
 	{ "Wacom Cintiq 24HD touch", .type = WACOM_24HDT, /* Touch */
@@ -2142,8 +2140,8 @@ static const struct wacom_features wacom_features_0xC6 =
 	{ "Wacom Cintiq 12WX",    WACOM_PKGLEN_INTUOS,    53020, 33440, 1023,
 	  63, WACOM_BEE, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES };
 static const struct wacom_features wacom_features_0x304 =
-	{ "Wacom Cintiq 13HD",    WACOM_PKGLEN_INTUOS,    59552, 33848, 1023,
-	  63, WACOM_13HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES };
+	{ "Wacom Cintiq 13HD",    WACOM_PKGLEN_INTUOS,    59352, 33648, 1023,
+	  63, WACOM_13HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 200, 200 };
 static const struct wacom_features wacom_features_0xC7 =
 	{ "Wacom DTU1931",        WACOM_PKGLEN_GRAPHIRE,  37832, 30305,  511,
 	  0, PL, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
@@ -2157,24 +2155,24 @@ static const struct wacom_features wacom_features_0xFB =
 	{ "Wacom DTU1031",        WACOM_PKGLEN_DTUS,      22096, 13960,  511,
 	  0, DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x57 =
-	{ "Wacom DTK2241",        WACOM_PKGLEN_INTUOS,    95840, 54260, 2047,
-	  63, DTK, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES};
+	{ "Wacom DTK2241",        WACOM_PKGLEN_INTUOS,    95640, 54060, 2047,
+	  63, DTK, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 200, 200 };
 static const struct wacom_features wacom_features_0x59 = /* Pen */
-	{ "Wacom DTH2242",        WACOM_PKGLEN_INTUOS,    95840, 54260, 2047,
-	  63, DTK, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES,
+	{ "Wacom DTH2242",        WACOM_PKGLEN_INTUOS,    95640, 54060, 2047,
+	  63, DTK, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 200, 200,
 	  .oVid = USB_VENDOR_ID_WACOM, .oPid = 0x5D };
 static const struct wacom_features wacom_features_0x5D = /* Touch */
 	{ "Wacom DTH2242",       .type = WACOM_24HDT,
 	  .oVid = USB_VENDOR_ID_WACOM, .oPid = 0x59, .touch_max = 10 };
 static const struct wacom_features wacom_features_0xCC =
-	{ "Wacom Cintiq 21UX2",   WACOM_PKGLEN_INTUOS,    87200, 65600, 2047,
-	  63, WACOM_21UX2, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES };
+	{ "Wacom Cintiq 21UX2",   WACOM_PKGLEN_INTUOS,    87000, 65400, 2047,
+	  63, WACOM_21UX2, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 200, 200 };
 static const struct wacom_features wacom_features_0xFA =
-	{ "Wacom Cintiq 22HD",    WACOM_PKGLEN_INTUOS,    95840, 54260, 2047,
-	  63, WACOM_22HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES };
+	{ "Wacom Cintiq 22HD",    WACOM_PKGLEN_INTUOS,    95640, 54060, 2047,
+	  63, WACOM_22HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 200, 200 };
 static const struct wacom_features wacom_features_0x5B =
-	{ "Wacom Cintiq 22HDT", WACOM_PKGLEN_INTUOS,      95840, 54260, 2047,
-	  63, WACOM_22HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES,
+	{ "Wacom Cintiq 22HDT", WACOM_PKGLEN_INTUOS,      95640, 54060, 2047,
+	  63, WACOM_22HD, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 200, 200,
 	  .oVid = USB_VENDOR_ID_WACOM, .oPid = 0x5e };
 static const struct wacom_features wacom_features_0x5E =
 	{ "Wacom Cintiq 22HDT", .type = WACOM_24HDT,
@@ -2233,9 +2231,21 @@ static const struct wacom_features wacom_features_0x10E =
 static const struct wacom_features wacom_features_0x10F =
 	{ "Wacom ISDv4 10F",      WACOM_PKGLEN_MTTPC,     27760, 15694,  255,
 	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0x116 =
+	{ "Wacom ISDv4 116",      WACOM_PKGLEN_GRAPHIRE,  26202, 16325,  255,
+	  0, TABLETPCE, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x4001 =
 	{ "Wacom ISDv4 4001",      WACOM_PKGLEN_MTTPC,     26202, 16325,  255,
 	  0, MTTPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0x4004 =
+	{ "Wacom ISDv4 4004",      WACOM_PKGLEN_MTTPC,     11060, 6220,  255,
+	  0, MTTPC_B, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0x5000 =
+	{ "Wacom ISDv4 5000",      WACOM_PKGLEN_MTTPC,     27848, 15752,  1023,
+	  0, MTTPC_B, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
+static const struct wacom_features wacom_features_0x5002 =
+	{ "Wacom ISDv4 5002",      WACOM_PKGLEN_MTTPC,     29576, 16724,  1023,
+	  0, MTTPC_B, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x47 =
 	{ "Wacom Intuos2 6x8",    WACOM_PKGLEN_INTUOS,    20320, 16240, 1023,
 	  31, INTUOS, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
@@ -2316,8 +2326,8 @@ static const struct wacom_features wacom_features_0x6004 =
 	{ "ISD-V4",               WACOM_PKGLEN_GRAPHIRE,  12800,  8000,  255,
 	  0, TABLETPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES };
 static const struct wacom_features wacom_features_0x0307 =
-	{ "Wacom ISDv5 307", WACOM_PKGLEN_INTUOS,  59552,  33848, 2047,
-	  63, CINTIQ_HYBRID, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES,
+	{ "Wacom ISDv5 307", WACOM_PKGLEN_INTUOS,  59352,  33648, 2047,
+	  63, CINTIQ_HYBRID, WACOM_INTUOS3_RES, WACOM_INTUOS3_RES, 200, 200,
 	  .oVid = USB_VENDOR_ID_WACOM, .oPid = 0x309 };
 static const struct wacom_features wacom_features_0x0309 =
 	{ "Wacom ISDv5 309", .type = WACOM_24HDT, /* Touch */
@@ -2447,6 +2457,7 @@ const struct usb_device_id wacom_ids[] = {
 	{ USB_DEVICE_WACOM(0x10D) },
 	{ USB_DEVICE_WACOM(0x10E) },
 	{ USB_DEVICE_WACOM(0x10F) },
+	{ USB_DEVICE_WACOM(0x116) },
 	{ USB_DEVICE_WACOM(0x300) },
 	{ USB_DEVICE_WACOM(0x301) },
 	{ USB_DEVICE_DETAILED(0x302, USB_CLASS_HID, 0, 0) },
@@ -2457,6 +2468,9 @@ const struct usb_device_id wacom_ids[] = {
 	{ USB_DEVICE_DETAILED(0x315, USB_CLASS_HID, 0, 0) },
 	{ USB_DEVICE_DETAILED(0x317, USB_CLASS_HID, 0, 0) },
 	{ USB_DEVICE_WACOM(0x4001) },
+	{ USB_DEVICE_WACOM(0x4004) },
+	{ USB_DEVICE_WACOM(0x5000) },
+	{ USB_DEVICE_WACOM(0x5002) },
 	{ USB_DEVICE_WACOM(0x47) },
 	{ USB_DEVICE_WACOM(0xF4) },
 	{ USB_DEVICE_WACOM(0xF8) },
diff --git a/drivers/input/tablet/wacom_wac.h b/drivers/input/tablet/wacom_wac.h
index f69c0ebe7fa..b2c9a9c1b55 100644
--- a/drivers/input/tablet/wacom_wac.h
+++ b/drivers/input/tablet/wacom_wac.h
@@ -22,6 +22,7 @@
 #define WACOM_PKGLEN_BBFUN	 9
 #define WACOM_PKGLEN_INTUOS	10
 #define WACOM_PKGLEN_TPC1FG	 5
+#define WACOM_PKGLEN_TPC1FG_B	10
 #define WACOM_PKGLEN_TPC2FG	14
 #define WACOM_PKGLEN_BBTOUCH	20
 #define WACOM_PKGLEN_BBTOUCH3	64
@@ -30,6 +31,7 @@
 #define WACOM_PKGLEN_MTOUCH	62
 #define WACOM_PKGLEN_MTTPC	40
 #define WACOM_PKGLEN_DTUS	68
+#define WACOM_PKGLEN_PENABLED	 8
 
 /* wacom data size per MT contact */
 #define WACOM_BYTES_PER_MT_PACKET	11
@@ -52,6 +54,7 @@
 #define WACOM_REPORT_TPC1FG		6
 #define WACOM_REPORT_TPC2FG		13
 #define WACOM_REPORT_TPCMT		13
+#define WACOM_REPORT_TPCMT2		3
 #define WACOM_REPORT_TPCHID		15
 #define WACOM_REPORT_TPCST		16
 #define WACOM_REPORT_DTUS		17
@@ -105,6 +108,7 @@ enum {
 	TABLETPC2FG,
 	MTSCREEN,
 	MTTPC,
+	MTTPC_B,
 	MAX_TYPE
 };
 
@@ -118,6 +122,8 @@ struct wacom_features {
 	int type;
 	int x_resolution;
 	int y_resolution;
+	int x_min;
+	int y_min;
 	int device_type;
 	int x_phy;
 	int y_phy;
diff --git a/drivers/input/touchscreen/88pm860x-ts.c b/drivers/input/touchscreen/88pm860x-ts.c
index 544e20c551f..0d4a9fad4a7 100644
--- a/drivers/input/touchscreen/88pm860x-ts.c
+++ b/drivers/input/touchscreen/88pm860x-ts.c
@@ -16,6 +16,7 @@
 #include <linux/input.h>
 #include <linux/mfd/88pm860x.h>
 #include <linux/slab.h>
+#include <linux/device.h>
 
 #define MEAS_LEN		(8)
 #define ACCURATE_BIT		(12)
@@ -234,16 +235,17 @@ static int pm860x_touch_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	touch = kzalloc(sizeof(struct pm860x_touch), GFP_KERNEL);
-	if (touch == NULL)
+	touch = devm_kzalloc(&pdev->dev, sizeof(struct pm860x_touch),
+			     GFP_KERNEL);
+	if (!touch)
 		return -ENOMEM;
+
 	platform_set_drvdata(pdev, touch);
 
-	touch->idev = input_allocate_device();
-	if (touch->idev == NULL) {
+	touch->idev = devm_input_allocate_device(&pdev->dev);
+	if (!touch->idev) {
 		dev_err(&pdev->dev, "Failed to allocate input device!\n");
-		ret = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
 
 	touch->idev->name = "88pm860x-touch";
@@ -258,10 +260,11 @@ static int pm860x_touch_probe(struct platform_device *pdev)
 	touch->res_x = res_x;
 	input_set_drvdata(touch->idev, touch);
 
-	ret = request_threaded_irq(touch->irq, NULL, pm860x_touch_handler,
-				   IRQF_ONESHOT, "touch", touch);
+	ret = devm_request_threaded_irq(&pdev->dev, touch->irq, NULL,
+					pm860x_touch_handler, IRQF_ONESHOT,
+					"touch", touch);
 	if (ret < 0)
-		goto out_irq;
+		return ret;
 
 	__set_bit(EV_ABS, touch->idev->evbit);
 	__set_bit(ABS_X, touch->idev->absbit);
@@ -279,28 +282,11 @@ static int pm860x_touch_probe(struct platform_device *pdev)
 	ret = input_register_device(touch->idev);
 	if (ret < 0) {
 		dev_err(chip->dev, "Failed to register touch!\n");
-		goto out_rg;
+		return ret;
 	}
 
 	platform_set_drvdata(pdev, touch);
 	return 0;
-out_rg:
-	free_irq(touch->irq, touch);
-out_irq:
-	input_free_device(touch->idev);
-out:
-	kfree(touch);
-	return ret;
-}
-
-static int pm860x_touch_remove(struct platform_device *pdev)
-{
-	struct pm860x_touch *touch = platform_get_drvdata(pdev);
-
-	input_unregister_device(touch->idev);
-	free_irq(touch->irq, touch);
-	kfree(touch);
-	return 0;
 }
 
 static struct platform_driver pm860x_touch_driver = {
@@ -309,7 +295,6 @@ static struct platform_driver pm860x_touch_driver = {
 		.owner	= THIS_MODULE,
 	},
 	.probe	= pm860x_touch_probe,
-	.remove	= pm860x_touch_remove,
 };
 module_platform_driver(pm860x_touch_driver);
 
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index d4e5ab57909..a23a94bb4bc 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -11,6 +11,10 @@ menuconfig INPUT_TOUCHSCREEN
 
 if INPUT_TOUCHSCREEN
 
+config OF_TOUCHSCREEN
+	def_tristate INPUT
+	depends on INPUT && OF
+
 config TOUCHSCREEN_88PM860X
 	tristate "Marvell 88PM860x touchscreen"
 	depends on MFD_88PM860X
@@ -89,6 +93,7 @@ config TOUCHSCREEN_AD7879_SPI
 config TOUCHSCREEN_ATMEL_MXT
 	tristate "Atmel mXT I2C Touchscreen"
 	depends on I2C
+	select FW_LOADER
 	help
 	  Say Y here if you have Atmel mXT series I2C touchscreen,
 	  such as AT42QT602240/ATMXT224, connected to your system.
@@ -846,7 +851,7 @@ config TOUCHSCREEN_TSC2007
 
 config TOUCHSCREEN_W90X900
 	tristate "W90P910 touchscreen driver"
-	depends on HAVE_CLK
+	depends on ARCH_W90X900
 	help
 	  Say Y here if you have a W90P910 based touchscreen.
 
@@ -885,6 +890,17 @@ config TOUCHSCREEN_STMPE
 	  To compile this driver as a module, choose M here: the
 	  module will be called stmpe-ts.
 
+config TOUCHSCREEN_SUN4I
+	tristate "Allwinner sun4i resistive touchscreen controller support"
+	depends on ARCH_SUNXI || COMPILE_TEST
+	depends on HWMON
+	help
+	  This selects support for the resistive touchscreen controller
+	  found on Allwinner sunxi SoCs.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called sun4i-ts.
+
 config TOUCHSCREEN_SUR40
 	tristate "Samsung SUR40 (Surface 2.0/PixelSense) touchscreen"
 	depends on USB
diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile
index 03f12a1f221..126479d8c29 100644
--- a/drivers/input/touchscreen/Makefile
+++ b/drivers/input/touchscreen/Makefile
@@ -6,6 +6,7 @@
 
 wm97xx-ts-y := wm97xx-core.o
 
+obj-$(CONFIG_OF_TOUCHSCREEN)		+= of_touchscreen.o
 obj-$(CONFIG_TOUCHSCREEN_88PM860X)	+= 88pm860x-ts.o
 obj-$(CONFIG_TOUCHSCREEN_AD7877)	+= ad7877.o
 obj-$(CONFIG_TOUCHSCREEN_AD7879)	+= ad7879.o
@@ -53,6 +54,7 @@ obj-$(CONFIG_TOUCHSCREEN_PIXCIR)	+= pixcir_i2c_ts.o
 obj-$(CONFIG_TOUCHSCREEN_S3C2410)	+= s3c2410_ts.o
 obj-$(CONFIG_TOUCHSCREEN_ST1232)	+= st1232.o
 obj-$(CONFIG_TOUCHSCREEN_STMPE)		+= stmpe-ts.o
+obj-$(CONFIG_TOUCHSCREEN_SUN4I)		+= sun4i-ts.o
 obj-$(CONFIG_TOUCHSCREEN_SUR40)		+= sur40.o
 obj-$(CONFIG_TOUCHSCREEN_TI_AM335X_TSC)	+= ti_am335x_tsc.o
 obj-$(CONFIG_TOUCHSCREEN_TOUCHIT213)	+= touchit213.o
diff --git a/drivers/input/touchscreen/ad7877.c b/drivers/input/touchscreen/ad7877.c
index 6793c85903a..523865daa1d 100644
--- a/drivers/input/touchscreen/ad7877.c
+++ b/drivers/input/touchscreen/ad7877.c
@@ -210,11 +210,6 @@ static bool gpio3;
 module_param(gpio3, bool, 0);
 MODULE_PARM_DESC(gpio3, "If gpio3 is set to 1 AUX3 acts as GPIO3");
 
-/*
- * ad7877_read/write are only used for initial setup and for sysfs controls.
- * The main traffic is done using spi_async() in the interrupt handler.
- */
-
 static int ad7877_read(struct spi_device *spi, u16 reg)
 {
 	struct ser_req *req;
diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index 7f8aa981500..da201b8e37d 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -706,7 +706,7 @@ static void ads7846_read_state(struct ads7846 *ts)
 		m = &ts->msg[msg_idx];
 		error = spi_sync(ts->spi, m);
 		if (error) {
-			dev_err(&ts->spi->dev, "spi_async --> %d\n", error);
+			dev_err(&ts->spi->dev, "spi_sync --> %d\n", error);
 			packet->tc.ignore = true;
 			return;
 		}
diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c
index a70400754e9..6e0b4a2120d 100644
--- a/drivers/input/touchscreen/atmel_mxt_ts.c
+++ b/drivers/input/touchscreen/atmel_mxt_ts.c
@@ -2,6 +2,8 @@
  * Atmel maXTouch Touchscreen driver
  *
  * Copyright (C) 2010 Samsung Electronics Co.Ltd
+ * Copyright (C) 2012 Google, Inc.
+ *
  * Author: Joonyoung Shim <jy0922.shim@samsung.com>
  *
  * This program is free software; you can redistribute  it and/or modify it
@@ -12,6 +14,8 @@
  */
 
 #include <linux/module.h>
+#include <linux/init.h>
+#include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/firmware.h>
 #include <linux/i2c.h>
@@ -25,12 +29,6 @@
 #define MXT_VER_21		21
 #define MXT_VER_22		22
 
-/* Slave addresses */
-#define MXT_APP_LOW		0x4a
-#define MXT_APP_HIGH		0x4b
-#define MXT_BOOT_LOW		0x24
-#define MXT_BOOT_HIGH		0x25
-
 /* Firmware */
 #define MXT_FW_NAME		"maxtouch.fw"
 
@@ -83,6 +81,9 @@
 #define MXT_COMMAND_REPORTALL	3
 #define MXT_COMMAND_DIAGNOSTIC	5
 
+/* Define for T6 status byte */
+#define MXT_T6_STATUS_RESET	(1 << 7)
+
 /* MXT_GEN_POWER_T7 field */
 #define MXT_POWER_IDLEACQINT	0
 #define MXT_POWER_ACTVACQINT	1
@@ -99,33 +100,26 @@
 
 /* MXT_TOUCH_MULTI_T9 field */
 #define MXT_TOUCH_CTRL		0
-#define MXT_TOUCH_XORIGIN	1
-#define MXT_TOUCH_YORIGIN	2
-#define MXT_TOUCH_XSIZE		3
-#define MXT_TOUCH_YSIZE		4
-#define MXT_TOUCH_BLEN		6
-#define MXT_TOUCH_TCHTHR	7
-#define MXT_TOUCH_TCHDI		8
-#define MXT_TOUCH_ORIENT	9
-#define MXT_TOUCH_MOVHYSTI	11
-#define MXT_TOUCH_MOVHYSTN	12
-#define MXT_TOUCH_NUMTOUCH	14
-#define MXT_TOUCH_MRGHYST	15
-#define MXT_TOUCH_MRGTHR	16
-#define MXT_TOUCH_AMPHYST	17
-#define MXT_TOUCH_XRANGE_LSB	18
-#define MXT_TOUCH_XRANGE_MSB	19
-#define MXT_TOUCH_YRANGE_LSB	20
-#define MXT_TOUCH_YRANGE_MSB	21
-#define MXT_TOUCH_XLOCLIP	22
-#define MXT_TOUCH_XHICLIP	23
-#define MXT_TOUCH_YLOCLIP	24
-#define MXT_TOUCH_YHICLIP	25
-#define MXT_TOUCH_XEDGECTRL	26
-#define MXT_TOUCH_XEDGEDIST	27
-#define MXT_TOUCH_YEDGECTRL	28
-#define MXT_TOUCH_YEDGEDIST	29
-#define MXT_TOUCH_JUMPLIMIT	30
+#define MXT_T9_ORIENT		9
+#define MXT_T9_RANGE		18
+
+/* MXT_TOUCH_MULTI_T9 status */
+#define MXT_T9_UNGRIP		(1 << 0)
+#define MXT_T9_SUPPRESS		(1 << 1)
+#define MXT_T9_AMP		(1 << 2)
+#define MXT_T9_VECTOR		(1 << 3)
+#define MXT_T9_MOVE		(1 << 4)
+#define MXT_T9_RELEASE		(1 << 5)
+#define MXT_T9_PRESS		(1 << 6)
+#define MXT_T9_DETECT		(1 << 7)
+
+struct t9_range {
+	u16 x;
+	u16 y;
+} __packed;
+
+/* MXT_TOUCH_MULTI_T9 orient */
+#define MXT_T9_ORIENT_SWITCH	(1 << 0)
 
 /* MXT_PROCI_GRIPFACE_T20 field */
 #define MXT_GRIPFACE_CTRL	0
@@ -174,17 +168,16 @@
 
 /* Define for MXT_GEN_COMMAND_T6 */
 #define MXT_BOOT_VALUE		0xa5
+#define MXT_RESET_VALUE		0x01
 #define MXT_BACKUP_VALUE	0x55
+
+/* Delay times */
 #define MXT_BACKUP_TIME		50	/* msec */
 #define MXT_RESET_TIME		200	/* msec */
-
-#define MXT_FWRESET_TIME	175	/* msec */
-
-/* MXT_SPT_GPIOPWM_T19 field */
-#define MXT_GPIO0_MASK		0x04
-#define MXT_GPIO1_MASK		0x08
-#define MXT_GPIO2_MASK		0x10
-#define MXT_GPIO3_MASK		0x20
+#define MXT_RESET_TIMEOUT	3000	/* msec */
+#define MXT_CRC_TIMEOUT		1000	/* msec */
+#define MXT_FW_RESET_TIME	3000	/* msec */
+#define MXT_FW_CHG_TIMEOUT	300	/* msec */
 
 /* Command to unlock bootloader */
 #define MXT_UNLOCK_CMD_MSB	0xaa
@@ -198,21 +191,8 @@
 #define MXT_FRAME_CRC_PASS	0x04
 #define MXT_APP_CRC_FAIL	0x40	/* valid 7 8 bit only */
 #define MXT_BOOT_STATUS_MASK	0x3f
-
-/* Touch status */
-#define MXT_UNGRIP		(1 << 0)
-#define MXT_SUPPRESS		(1 << 1)
-#define MXT_AMP			(1 << 2)
-#define MXT_VECTOR		(1 << 3)
-#define MXT_MOVE		(1 << 4)
-#define MXT_RELEASE		(1 << 5)
-#define MXT_PRESS		(1 << 6)
-#define MXT_DETECT		(1 << 7)
-
-/* Touch orient bits */
-#define MXT_XY_SWITCH		(1 << 0)
-#define MXT_X_INVERT		(1 << 1)
-#define MXT_Y_INVERT		(1 << 2)
+#define MXT_BOOT_EXTENDED_ID	(1 << 5)
+#define MXT_BOOT_ID_MASK	0x1f
 
 /* Touchscreen absolute values */
 #define MXT_MAX_AREA		0xff
@@ -232,8 +212,8 @@ struct mxt_info {
 struct mxt_object {
 	u8 type;
 	u16 start_address;
-	u8 size;		/* Size of each instance - 1 */
-	u8 instances;		/* Number of instances - 1 */
+	u8 size_minus_one;
+	u8 instances_minus_one;
 	u8 num_report_ids;
 } __packed;
 
@@ -250,19 +230,40 @@ struct mxt_data {
 	const struct mxt_platform_data *pdata;
 	struct mxt_object *object_table;
 	struct mxt_info info;
-	bool is_tp;
-
 	unsigned int irq;
 	unsigned int max_x;
 	unsigned int max_y;
+	bool in_bootloader;
+	u32 config_crc;
+	u8 bootloader_addr;
 
 	/* Cached parameters from object table */
 	u8 T6_reportid;
+	u16 T6_address;
 	u8 T9_reportid_min;
 	u8 T9_reportid_max;
 	u8 T19_reportid;
+
+	/* for fw update in bootloader */
+	struct completion bl_completion;
+
+	/* for reset handling */
+	struct completion reset_completion;
+
+	/* for config update handling */
+	struct completion crc_completion;
 };
 
+static size_t mxt_obj_size(const struct mxt_object *obj)
+{
+	return obj->size_minus_one + 1;
+}
+
+static size_t mxt_obj_instances(const struct mxt_object *obj)
+{
+	return obj->instances_minus_one + 1;
+}
+
 static bool mxt_object_readable(unsigned int type)
 {
 	switch (type) {
@@ -334,60 +335,190 @@ static void mxt_dump_message(struct device *dev,
 		message->reportid, 7, message->message);
 }
 
-static int mxt_check_bootloader(struct i2c_client *client,
-				     unsigned int state)
+static int mxt_wait_for_completion(struct mxt_data *data,
+				   struct completion *comp,
+				   unsigned int timeout_ms)
+{
+	struct device *dev = &data->client->dev;
+	unsigned long timeout = msecs_to_jiffies(timeout_ms);
+	long ret;
+
+	ret = wait_for_completion_interruptible_timeout(comp, timeout);
+	if (ret < 0) {
+		return ret;
+	} else if (ret == 0) {
+		dev_err(dev, "Wait for completion timed out.\n");
+		return -ETIMEDOUT;
+	}
+	return 0;
+}
+
+static int mxt_bootloader_read(struct mxt_data *data,
+			       u8 *val, unsigned int count)
+{
+	int ret;
+	struct i2c_msg msg;
+
+	msg.addr = data->bootloader_addr;
+	msg.flags = data->client->flags & I2C_M_TEN;
+	msg.flags |= I2C_M_RD;
+	msg.len = count;
+	msg.buf = val;
+
+	ret = i2c_transfer(data->client->adapter, &msg, 1);
+
+	if (ret == 1) {
+		ret = 0;
+	} else {
+		ret = ret < 0 ? ret : -EIO;
+		dev_err(&data->client->dev, "%s: i2c recv failed (%d)\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
+static int mxt_bootloader_write(struct mxt_data *data,
+				const u8 * const val, unsigned int count)
+{
+	int ret;
+	struct i2c_msg msg;
+
+	msg.addr = data->bootloader_addr;
+	msg.flags = data->client->flags & I2C_M_TEN;
+	msg.len = count;
+	msg.buf = (u8 *)val;
+
+	ret = i2c_transfer(data->client->adapter, &msg, 1);
+	if (ret == 1) {
+		ret = 0;
+	} else {
+		ret = ret < 0 ? ret : -EIO;
+		dev_err(&data->client->dev, "%s: i2c send failed (%d)\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
+static int mxt_lookup_bootloader_address(struct mxt_data *data)
+{
+	u8 appmode = data->client->addr;
+	u8 bootloader;
+
+	switch (appmode) {
+	case 0x4a:
+	case 0x4b:
+	case 0x4c:
+	case 0x4d:
+	case 0x5a:
+	case 0x5b:
+		bootloader = appmode - 0x26;
+		break;
+	default:
+		dev_err(&data->client->dev,
+			"Appmode i2c address 0x%02x not found\n",
+			appmode);
+		return -EINVAL;
+	}
+
+	data->bootloader_addr = bootloader;
+	return 0;
+}
+
+static u8 mxt_get_bootloader_version(struct mxt_data *data, u8 val)
+{
+	struct device *dev = &data->client->dev;
+	u8 buf[3];
+
+	if (val & MXT_BOOT_EXTENDED_ID) {
+		if (mxt_bootloader_read(data, &buf[0], 3) != 0) {
+			dev_err(dev, "%s: i2c failure\n", __func__);
+			return val;
+		}
+
+		dev_dbg(dev, "Bootloader ID:%d Version:%d\n", buf[1], buf[2]);
+
+		return buf[0];
+	} else {
+		dev_dbg(dev, "Bootloader ID:%d\n", val & MXT_BOOT_ID_MASK);
+
+		return val;
+	}
+}
+
+static int mxt_check_bootloader(struct mxt_data *data, unsigned int state)
 {
+	struct device *dev = &data->client->dev;
 	u8 val;
+	int ret;
 
 recheck:
-	if (i2c_master_recv(client, &val, 1) != 1) {
-		dev_err(&client->dev, "%s: i2c recv failed\n", __func__);
-		return -EIO;
+	if (state != MXT_WAITING_BOOTLOAD_CMD) {
+		/*
+		 * In application update mode, the interrupt
+		 * line signals state transitions. We must wait for the
+		 * CHG assertion before reading the status byte.
+		 * Once the status byte has been read, the line is deasserted.
+		 */
+		ret = mxt_wait_for_completion(data, &data->bl_completion,
+					      MXT_FW_CHG_TIMEOUT);
+		if (ret) {
+			/*
+			 * TODO: handle -ERESTARTSYS better by terminating
+			 * fw update process before returning to userspace
+			 * by writing length 0x000 to device (iff we are in
+			 * WAITING_FRAME_DATA state).
+			 */
+			dev_err(dev, "Update wait error %d\n", ret);
+			return ret;
+		}
 	}
 
+	ret = mxt_bootloader_read(data, &val, 1);
+	if (ret)
+		return ret;
+
+	if (state == MXT_WAITING_BOOTLOAD_CMD)
+		val = mxt_get_bootloader_version(data, val);
+
 	switch (state) {
 	case MXT_WAITING_BOOTLOAD_CMD:
 	case MXT_WAITING_FRAME_DATA:
 		val &= ~MXT_BOOT_STATUS_MASK;
 		break;
 	case MXT_FRAME_CRC_PASS:
-		if (val == MXT_FRAME_CRC_CHECK)
+		if (val == MXT_FRAME_CRC_CHECK) {
 			goto recheck;
+		} else if (val == MXT_FRAME_CRC_FAIL) {
+			dev_err(dev, "Bootloader CRC fail\n");
+			return -EINVAL;
+		}
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	if (val != state) {
-		dev_err(&client->dev, "Unvalid bootloader mode state\n");
+		dev_err(dev, "Invalid bootloader state %02X != %02X\n",
+			val, state);
 		return -EINVAL;
 	}
 
 	return 0;
 }
 
-static int mxt_unlock_bootloader(struct i2c_client *client)
+static int mxt_unlock_bootloader(struct mxt_data *data)
 {
+	int ret;
 	u8 buf[2];
 
 	buf[0] = MXT_UNLOCK_CMD_LSB;
 	buf[1] = MXT_UNLOCK_CMD_MSB;
 
-	if (i2c_master_send(client, buf, 2) != 2) {
-		dev_err(&client->dev, "%s: i2c send failed\n", __func__);
-		return -EIO;
-	}
-
-	return 0;
-}
-
-static int mxt_fw_write(struct i2c_client *client,
-			     const u8 *data, unsigned int frame_size)
-{
-	if (i2c_master_send(client, data, frame_size) != frame_size) {
-		dev_err(&client->dev, "%s: i2c send failed\n", __func__);
-		return -EIO;
-	}
+	ret = mxt_bootloader_write(data, buf, 2);
+	if (ret)
+		return ret;
 
 	return 0;
 }
@@ -427,11 +558,6 @@ static int __mxt_read_reg(struct i2c_client *client,
 	return ret;
 }
 
-static int mxt_read_reg(struct i2c_client *client, u16 reg, u8 *val)
-{
-	return __mxt_read_reg(client, reg, 1, val);
-}
-
 static int __mxt_write_reg(struct i2c_client *client, u16 reg, u16 len,
 			   const void *val)
 {
@@ -479,7 +605,7 @@ mxt_get_object(struct mxt_data *data, u8 type)
 			return object;
 	}
 
-	dev_err(&data->client->dev, "Invalid object type\n");
+	dev_err(&data->client->dev, "Invalid object type T%u\n", type);
 	return NULL;
 }
 
@@ -505,7 +631,7 @@ static int mxt_write_object(struct mxt_data *data,
 	u16 reg;
 
 	object = mxt_get_object(data, type);
-	if (!object || offset >= object->size + 1)
+	if (!object || offset >= mxt_obj_size(object))
 		return -EINVAL;
 
 	reg = object->start_address;
@@ -515,18 +641,25 @@ static int mxt_write_object(struct mxt_data *data,
 static void mxt_input_button(struct mxt_data *data, struct mxt_message *message)
 {
 	struct input_dev *input = data->input_dev;
+	const struct mxt_platform_data *pdata = data->pdata;
 	bool button;
 	int i;
 
 	/* Active-low switch */
-	for (i = 0; i < MXT_NUM_GPIO; i++) {
-		if (data->pdata->key_map[i] == KEY_RESERVED)
+	for (i = 0; i < pdata->t19_num_keys; i++) {
+		if (pdata->t19_keymap[i] == KEY_RESERVED)
 			continue;
-		button = !(message->message[0] & MXT_GPIO0_MASK << i);
-		input_report_key(input, data->pdata->key_map[i], button);
+		button = !(message->message[0] & (1 << i));
+		input_report_key(input, pdata->t19_keymap[i], button);
 	}
 }
 
+static void mxt_input_sync(struct input_dev *input_dev)
+{
+	input_mt_report_pointer_emulation(input_dev, false);
+	input_sync(input_dev);
+}
+
 static void mxt_input_touchevent(struct mxt_data *data,
 				      struct mxt_message *message, int id)
 {
@@ -536,44 +669,60 @@ static void mxt_input_touchevent(struct mxt_data *data,
 	int x;
 	int y;
 	int area;
-	int pressure;
+	int amplitude;
 
 	x = (message->message[1] << 4) | ((message->message[3] >> 4) & 0xf);
 	y = (message->message[2] << 4) | ((message->message[3] & 0xf));
+
+	/* Handle 10/12 bit switching */
 	if (data->max_x < 1024)
-		x = x >> 2;
+		x >>= 2;
 	if (data->max_y < 1024)
-		y = y >> 2;
+		y >>= 2;
 
 	area = message->message[4];
-	pressure = message->message[5];
+	amplitude = message->message[5];
 
 	dev_dbg(dev,
 		"[%u] %c%c%c%c%c%c%c%c x: %5u y: %5u area: %3u amp: %3u\n",
 		id,
-		(status & MXT_DETECT) ? 'D' : '.',
-		(status & MXT_PRESS) ? 'P' : '.',
-		(status & MXT_RELEASE) ? 'R' : '.',
-		(status & MXT_MOVE) ? 'M' : '.',
-		(status & MXT_VECTOR) ? 'V' : '.',
-		(status & MXT_AMP) ? 'A' : '.',
-		(status & MXT_SUPPRESS) ? 'S' : '.',
-		(status & MXT_UNGRIP) ? 'U' : '.',
-		x, y, area, pressure);
+		(status & MXT_T9_DETECT) ? 'D' : '.',
+		(status & MXT_T9_PRESS) ? 'P' : '.',
+		(status & MXT_T9_RELEASE) ? 'R' : '.',
+		(status & MXT_T9_MOVE) ? 'M' : '.',
+		(status & MXT_T9_VECTOR) ? 'V' : '.',
+		(status & MXT_T9_AMP) ? 'A' : '.',
+		(status & MXT_T9_SUPPRESS) ? 'S' : '.',
+		(status & MXT_T9_UNGRIP) ? 'U' : '.',
+		x, y, area, amplitude);
 
 	input_mt_slot(input_dev, id);
-	input_mt_report_slot_state(input_dev, MT_TOOL_FINGER,
-				   status & MXT_DETECT);
 
-	if (status & MXT_DETECT) {
+	if (status & MXT_T9_DETECT) {
+		/*
+		 * Multiple bits may be set if the host is slow to read
+		 * the status messages, indicating all the events that
+		 * have happened.
+		 */
+		if (status & MXT_T9_RELEASE) {
+			input_mt_report_slot_state(input_dev,
+						   MT_TOOL_FINGER, 0);
+			mxt_input_sync(input_dev);
+		}
+
+		/* Touch active */
+		input_mt_report_slot_state(input_dev, MT_TOOL_FINGER, 1);
 		input_report_abs(input_dev, ABS_MT_POSITION_X, x);
 		input_report_abs(input_dev, ABS_MT_POSITION_Y, y);
-		input_report_abs(input_dev, ABS_MT_PRESSURE, pressure);
+		input_report_abs(input_dev, ABS_MT_PRESSURE, amplitude);
 		input_report_abs(input_dev, ABS_MT_TOUCH_MAJOR, area);
+	} else {
+		/* Touch no longer active, close out slot */
+		input_mt_report_slot_state(input_dev, MT_TOOL_FINGER, 0);
 	}
 }
 
-static unsigned mxt_extract_T6_csum(const u8 *csum)
+static u16 mxt_extract_T6_csum(const u8 *csum)
 {
 	return csum[0] | (csum[1] << 8) | (csum[2] << 16);
 }
@@ -584,28 +733,37 @@ static bool mxt_is_T9_message(struct mxt_data *data, struct mxt_message *msg)
 	return (id >= data->T9_reportid_min && id <= data->T9_reportid_max);
 }
 
-static irqreturn_t mxt_interrupt(int irq, void *dev_id)
+static irqreturn_t mxt_process_messages_until_invalid(struct mxt_data *data)
 {
-	struct mxt_data *data = dev_id;
 	struct mxt_message message;
 	const u8 *payload = &message.message[0];
 	struct device *dev = &data->client->dev;
 	u8 reportid;
 	bool update_input = false;
+	u32 crc;
 
 	do {
 		if (mxt_read_message(data, &message)) {
 			dev_err(dev, "Failed to read message\n");
-			goto end;
+			return IRQ_NONE;
 		}
 
 		reportid = message.reportid;
 
 		if (reportid == data->T6_reportid) {
 			u8 status = payload[0];
-			unsigned csum = mxt_extract_T6_csum(&payload[1]);
+
+			crc = mxt_extract_T6_csum(&payload[1]);
+			if (crc != data->config_crc) {
+				data->config_crc = crc;
+				complete(&data->crc_completion);
+			}
+
 			dev_dbg(dev, "Status: %02x Config Checksum: %06x\n",
-				status, csum);
+				status, data->config_crc);
+
+			if (status & MXT_T6_STATUS_RESET)
+				complete(&data->reset_completion);
 		} else if (mxt_is_T9_message(data, &message)) {
 			int id = reportid - data->T9_reportid_min;
 			mxt_input_touchevent(data, &message, id);
@@ -618,15 +776,96 @@ static irqreturn_t mxt_interrupt(int irq, void *dev_id)
 		}
 	} while (reportid != 0xff);
 
-	if (update_input) {
-		input_mt_report_pointer_emulation(data->input_dev, false);
-		input_sync(data->input_dev);
-	}
+	if (update_input)
+		mxt_input_sync(data->input_dev);
 
-end:
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t mxt_interrupt(int irq, void *dev_id)
+{
+	struct mxt_data *data = dev_id;
+
+	if (data->in_bootloader) {
+		/* bootloader state transition completion */
+		complete(&data->bl_completion);
+		return IRQ_HANDLED;
+	}
+
+	return mxt_process_messages_until_invalid(data);
+}
+
+static int mxt_t6_command(struct mxt_data *data, u16 cmd_offset,
+			  u8 value, bool wait)
+{
+	u16 reg;
+	u8 command_register;
+	int timeout_counter = 0;
+	int ret;
+
+	reg = data->T6_address + cmd_offset;
+
+	ret = mxt_write_reg(data->client, reg, value);
+	if (ret)
+		return ret;
+
+	if (!wait)
+		return 0;
+
+	do {
+		msleep(20);
+		ret = __mxt_read_reg(data->client, reg, 1, &command_register);
+		if (ret)
+			return ret;
+	} while (command_register != 0 && timeout_counter++ <= 100);
+
+	if (timeout_counter > 100) {
+		dev_err(&data->client->dev, "Command failed!\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int mxt_soft_reset(struct mxt_data *data)
+{
+	struct device *dev = &data->client->dev;
+	int ret = 0;
+
+	dev_info(dev, "Resetting chip\n");
+
+	reinit_completion(&data->reset_completion);
+
+	ret = mxt_t6_command(data, MXT_COMMAND_RESET, MXT_RESET_VALUE, false);
+	if (ret)
+		return ret;
+
+	ret = mxt_wait_for_completion(data, &data->reset_completion,
+				      MXT_RESET_TIMEOUT);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void mxt_update_crc(struct mxt_data *data, u8 cmd, u8 value)
+{
+	/*
+	 * On failure, CRC is set to 0 and config will always be
+	 * downloaded.
+	 */
+	data->config_crc = 0;
+	reinit_completion(&data->crc_completion);
+
+	mxt_t6_command(data, cmd, value, true);
+
+	/*
+	 * Wait for crc message. On failure, CRC is set to 0 and config will
+	 * always be downloaded.
+	 */
+	mxt_wait_for_completion(data, &data->crc_completion, MXT_CRC_TIMEOUT);
+}
+
 static int mxt_check_reg_init(struct mxt_data *data)
 {
 	const struct mxt_platform_data *pdata = data->pdata;
@@ -641,13 +880,23 @@ static int mxt_check_reg_init(struct mxt_data *data)
 		return 0;
 	}
 
+	mxt_update_crc(data, MXT_COMMAND_REPORTALL, 1);
+
+	if (data->config_crc == pdata->config_crc) {
+		dev_info(dev, "Config CRC 0x%06X: OK\n", data->config_crc);
+		return 0;
+	}
+
+	dev_info(dev, "Config CRC 0x%06X: does not match 0x%06X\n",
+		 data->config_crc, pdata->config_crc);
+
 	for (i = 0; i < data->info.object_num; i++) {
 		object = data->object_table + i;
 
 		if (!mxt_object_writable(object->type))
 			continue;
 
-		size = (object->size + 1) * (object->instances + 1);
+		size = mxt_obj_size(object) * mxt_obj_instances(object);
 		if (index + size > pdata->config_length) {
 			dev_err(dev, "Not enough config data!\n");
 			return -EINVAL;
@@ -660,6 +909,14 @@ static int mxt_check_reg_init(struct mxt_data *data)
 		index += size;
 	}
 
+	mxt_update_crc(data, MXT_COMMAND_BACKUPNV, MXT_BACKUP_VALUE);
+
+	ret = mxt_soft_reset(data);
+	if (ret)
+		return ret;
+
+	dev_info(dev, "Config successfully updated\n");
+
 	return 0;
 }
 
@@ -685,54 +942,6 @@ static int mxt_make_highchg(struct mxt_data *data)
 	return 0;
 }
 
-static void mxt_handle_pdata(struct mxt_data *data)
-{
-	const struct mxt_platform_data *pdata = data->pdata;
-	u8 voltage;
-
-	/* Set touchscreen lines */
-	mxt_write_object(data, MXT_TOUCH_MULTI_T9, MXT_TOUCH_XSIZE,
-			pdata->x_line);
-	mxt_write_object(data, MXT_TOUCH_MULTI_T9, MXT_TOUCH_YSIZE,
-			pdata->y_line);
-
-	/* Set touchscreen orient */
-	mxt_write_object(data, MXT_TOUCH_MULTI_T9, MXT_TOUCH_ORIENT,
-			pdata->orient);
-
-	/* Set touchscreen burst length */
-	mxt_write_object(data, MXT_TOUCH_MULTI_T9,
-			MXT_TOUCH_BLEN, pdata->blen);
-
-	/* Set touchscreen threshold */
-	mxt_write_object(data, MXT_TOUCH_MULTI_T9,
-			MXT_TOUCH_TCHTHR, pdata->threshold);
-
-	/* Set touchscreen resolution */
-	mxt_write_object(data, MXT_TOUCH_MULTI_T9,
-			MXT_TOUCH_XRANGE_LSB, (pdata->x_size - 1) & 0xff);
-	mxt_write_object(data, MXT_TOUCH_MULTI_T9,
-			MXT_TOUCH_XRANGE_MSB, (pdata->x_size - 1) >> 8);
-	mxt_write_object(data, MXT_TOUCH_MULTI_T9,
-			MXT_TOUCH_YRANGE_LSB, (pdata->y_size - 1) & 0xff);
-	mxt_write_object(data, MXT_TOUCH_MULTI_T9,
-			MXT_TOUCH_YRANGE_MSB, (pdata->y_size - 1) >> 8);
-
-	/* Set touchscreen voltage */
-	if (pdata->voltage) {
-		if (pdata->voltage < MXT_VOLTAGE_DEFAULT) {
-			voltage = (MXT_VOLTAGE_DEFAULT - pdata->voltage) /
-				MXT_VOLTAGE_STEP;
-			voltage = 0xff - voltage + 1;
-		} else
-			voltage = (pdata->voltage - MXT_VOLTAGE_DEFAULT) /
-				MXT_VOLTAGE_STEP;
-
-		mxt_write_object(data, MXT_SPT_CTECONFIG_T28,
-				MXT_CTE_VOLTAGE, voltage);
-	}
-}
-
 static int mxt_get_info(struct mxt_data *data)
 {
 	struct i2c_client *client = data->client;
@@ -772,7 +981,7 @@ static int mxt_get_object_table(struct mxt_data *data)
 		if (object->num_report_ids) {
 			min_id = reportid;
 			reportid += object->num_report_ids *
-					(object->instances + 1);
+					mxt_obj_instances(object);
 			max_id = reportid - 1;
 		} else {
 			min_id = 0;
@@ -780,13 +989,15 @@ static int mxt_get_object_table(struct mxt_data *data)
 		}
 
 		dev_dbg(&data->client->dev,
-			"Type %2d Start %3d Size %3d Instances %2d ReportIDs %3u : %3u\n",
-			object->type, object->start_address, object->size + 1,
-			object->instances + 1, min_id, max_id);
+			"T%u Start:%u Size:%zu Instances:%zu Report IDs:%u-%u\n",
+			object->type, object->start_address,
+			mxt_obj_size(object), mxt_obj_instances(object),
+			min_id, max_id);
 
 		switch (object->type) {
 		case MXT_GEN_COMMAND_T6:
 			data->T6_reportid = min_id;
+			data->T6_address = object->start_address;
 			break;
 		case MXT_TOUCH_MULTI_T9:
 			data->T9_reportid_min = min_id;
@@ -811,12 +1022,59 @@ static void mxt_free_object_table(struct mxt_data *data)
 	data->T19_reportid = 0;
 }
 
+static int mxt_read_t9_resolution(struct mxt_data *data)
+{
+	struct i2c_client *client = data->client;
+	int error;
+	struct t9_range range;
+	unsigned char orient;
+	struct mxt_object *object;
+
+	object = mxt_get_object(data, MXT_TOUCH_MULTI_T9);
+	if (!object)
+		return -EINVAL;
+
+	error = __mxt_read_reg(client,
+			       object->start_address + MXT_T9_RANGE,
+			       sizeof(range), &range);
+	if (error)
+		return error;
+
+	le16_to_cpus(&range.x);
+	le16_to_cpus(&range.y);
+
+	error =  __mxt_read_reg(client,
+				object->start_address + MXT_T9_ORIENT,
+				1, &orient);
+	if (error)
+		return error;
+
+	/* Handle default values */
+	if (range.x == 0)
+		range.x = 1023;
+
+	if (range.y == 0)
+		range.y = 1023;
+
+	if (orient & MXT_T9_ORIENT_SWITCH) {
+		data->max_x = range.y;
+		data->max_y = range.x;
+	} else {
+		data->max_x = range.x;
+		data->max_y = range.y;
+	}
+
+	dev_dbg(&client->dev,
+		"Touchscreen size X%uY%u\n", data->max_x, data->max_y);
+
+	return 0;
+}
+
 static int mxt_initialize(struct mxt_data *data)
 {
 	struct i2c_client *client = data->client;
 	struct mxt_info *info = &data->info;
 	int error;
-	u8 val;
 
 	error = mxt_get_info(data);
 	if (error)
@@ -832,47 +1090,29 @@ static int mxt_initialize(struct mxt_data *data)
 
 	/* Get object table information */
 	error = mxt_get_object_table(data);
-	if (error)
+	if (error) {
+		dev_err(&client->dev, "Error %d reading object table\n", error);
 		goto err_free_object_table;
+	}
 
 	/* Check register init values */
 	error = mxt_check_reg_init(data);
-	if (error)
-		goto err_free_object_table;
-
-	mxt_handle_pdata(data);
-
-	/* Backup to memory */
-	mxt_write_object(data, MXT_GEN_COMMAND_T6,
-			MXT_COMMAND_BACKUPNV,
-			MXT_BACKUP_VALUE);
-	msleep(MXT_BACKUP_TIME);
-
-	/* Soft reset */
-	mxt_write_object(data, MXT_GEN_COMMAND_T6,
-			MXT_COMMAND_RESET, 1);
-	msleep(MXT_RESET_TIME);
-
-	/* Update matrix size at info struct */
-	error = mxt_read_reg(client, MXT_MATRIX_X_SIZE, &val);
-	if (error)
+	if (error) {
+		dev_err(&client->dev, "Error %d initializing configuration\n",
+			error);
 		goto err_free_object_table;
-	info->matrix_xsize = val;
+	}
 
-	error = mxt_read_reg(client, MXT_MATRIX_Y_SIZE, &val);
-	if (error)
+	error = mxt_read_t9_resolution(data);
+	if (error) {
+		dev_err(&client->dev, "Failed to initialize T9 resolution\n");
 		goto err_free_object_table;
-	info->matrix_ysize = val;
-
-	dev_info(&client->dev,
-			"Family ID: %u Variant ID: %u Major.Minor.Build: %u.%u.%02X\n",
-			info->family_id, info->variant_id, info->version >> 4,
-			info->version & 0xf, info->build);
+	}
 
 	dev_info(&client->dev,
-			"Matrix X Size: %u Matrix Y Size: %u Object Num: %u\n",
-			info->matrix_xsize, info->matrix_ysize,
-			info->object_num);
+		 "Family: %u Variant: %u Firmware V%u.%u.%02X Objects: %u\n",
+		 info->family_id, info->variant_id, info->version >> 4,
+		 info->version & 0xf, info->build, info->object_num);
 
 	return 0;
 
@@ -881,20 +1121,6 @@ err_free_object_table:
 	return error;
 }
 
-static void mxt_calc_resolution(struct mxt_data *data)
-{
-	unsigned int max_x = data->pdata->x_size - 1;
-	unsigned int max_y = data->pdata->y_size - 1;
-
-	if (data->pdata->orient & MXT_XY_SWITCH) {
-		data->max_x = max_y;
-		data->max_y = max_x;
-	} else {
-		data->max_x = max_x;
-		data->max_y = max_y;
-	}
-}
-
 /* Firmware Version is returned as Major.Minor.Build */
 static ssize_t mxt_fw_version_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
@@ -921,11 +1147,11 @@ static ssize_t mxt_show_instance(char *buf, int count,
 {
 	int i;
 
-	if (object->instances > 0)
+	if (mxt_obj_instances(object) > 1)
 		count += scnprintf(buf + count, PAGE_SIZE - count,
 				   "Instance %u\n", instance);
 
-	for (i = 0; i < object->size + 1; i++)
+	for (i = 0; i < mxt_obj_size(object); i++)
 		count += scnprintf(buf + count, PAGE_SIZE - count,
 				"\t[%2u]: %02x (%d)\n", i, val[i], val[i]);
 	count += scnprintf(buf + count, PAGE_SIZE - count, "\n");
@@ -958,8 +1184,8 @@ static ssize_t mxt_object_show(struct device *dev,
 		count += scnprintf(buf + count, PAGE_SIZE - count,
 				"T%u:\n", object->type);
 
-		for (j = 0; j < object->instances + 1; j++) {
-			u16 size = object->size + 1;
+		for (j = 0; j < mxt_obj_instances(object); j++) {
+			u16 size = mxt_obj_size(object);
 			u16 addr = object->start_address + j * size;
 
 			error = __mxt_read_reg(data->client, addr, size, obuf);
@@ -975,13 +1201,38 @@ done:
 	return error ?: count;
 }
 
+static int mxt_check_firmware_format(struct device *dev,
+				     const struct firmware *fw)
+{
+	unsigned int pos = 0;
+	char c;
+
+	while (pos < fw->size) {
+		c = *(fw->data + pos);
+
+		if (c < '0' || (c > '9' && c < 'A') || c > 'F')
+			return 0;
+
+		pos++;
+	}
+
+	/*
+	 * To convert file try:
+	 * xxd -r -p mXTXXX__APP_VX-X-XX.enc > maxtouch.fw
+	 */
+	dev_err(dev, "Aborting: firmware file must be in binary format\n");
+
+	return -EINVAL;
+}
+
 static int mxt_load_fw(struct device *dev, const char *fn)
 {
 	struct mxt_data *data = dev_get_drvdata(dev);
-	struct i2c_client *client = data->client;
 	const struct firmware *fw = NULL;
 	unsigned int frame_size;
 	unsigned int pos = 0;
+	unsigned int retry = 0;
+	unsigned int frame = 0;
 	int ret;
 
 	ret = request_firmware(&fw, fn, dev);
@@ -990,59 +1241,91 @@ static int mxt_load_fw(struct device *dev, const char *fn)
 		return ret;
 	}
 
+	/* Check for incorrect enc file */
+	ret = mxt_check_firmware_format(dev, fw);
+	if (ret)
+		goto release_firmware;
+
+	ret = mxt_lookup_bootloader_address(data);
+	if (ret)
+		goto release_firmware;
+
 	/* Change to the bootloader mode */
-	mxt_write_object(data, MXT_GEN_COMMAND_T6,
-			MXT_COMMAND_RESET, MXT_BOOT_VALUE);
+	data->in_bootloader = true;
+
+	ret = mxt_t6_command(data, MXT_COMMAND_RESET, MXT_BOOT_VALUE, false);
+	if (ret)
+		goto release_firmware;
+
 	msleep(MXT_RESET_TIME);
 
-	/* Change to slave address of bootloader */
-	if (client->addr == MXT_APP_LOW)
-		client->addr = MXT_BOOT_LOW;
-	else
-		client->addr = MXT_BOOT_HIGH;
+	reinit_completion(&data->bl_completion);
 
-	ret = mxt_check_bootloader(client, MXT_WAITING_BOOTLOAD_CMD);
+	ret = mxt_check_bootloader(data, MXT_WAITING_BOOTLOAD_CMD);
 	if (ret)
-		goto out;
+		goto disable_irq;
 
 	/* Unlock bootloader */
-	mxt_unlock_bootloader(client);
+	mxt_unlock_bootloader(data);
 
 	while (pos < fw->size) {
-		ret = mxt_check_bootloader(client,
-						MXT_WAITING_FRAME_DATA);
+		ret = mxt_check_bootloader(data, MXT_WAITING_FRAME_DATA);
 		if (ret)
-			goto out;
+			goto disable_irq;
 
 		frame_size = ((*(fw->data + pos) << 8) | *(fw->data + pos + 1));
 
-		/* We should add 2 at frame size as the the firmware data is not
-		 * included the CRC bytes.
-		 */
+		/* Take account of CRC bytes */
 		frame_size += 2;
 
 		/* Write one frame to device */
-		mxt_fw_write(client, fw->data + pos, frame_size);
-
-		ret = mxt_check_bootloader(client,
-						MXT_FRAME_CRC_PASS);
+		ret = mxt_bootloader_write(data, fw->data + pos, frame_size);
 		if (ret)
-			goto out;
+			goto disable_irq;
 
-		pos += frame_size;
+		ret = mxt_check_bootloader(data, MXT_FRAME_CRC_PASS);
+		if (ret) {
+			retry++;
 
-		dev_dbg(dev, "Updated %d bytes / %zd bytes\n", pos, fw->size);
+			/* Back off by 20ms per retry */
+			msleep(retry * 20);
+
+			if (retry > 20) {
+				dev_err(dev, "Retry count exceeded\n");
+				goto disable_irq;
+			}
+		} else {
+			retry = 0;
+			pos += frame_size;
+			frame++;
+		}
+
+		if (frame % 50 == 0)
+			dev_dbg(dev, "Sent %d frames, %d/%zd bytes\n",
+				frame, pos, fw->size);
 	}
 
-out:
-	release_firmware(fw);
+	/* Wait for flash. */
+	ret = mxt_wait_for_completion(data, &data->bl_completion,
+				      MXT_FW_RESET_TIME);
+	if (ret)
+		goto disable_irq;
 
-	/* Change to slave address of application */
-	if (client->addr == MXT_BOOT_LOW)
-		client->addr = MXT_APP_LOW;
-	else
-		client->addr = MXT_APP_HIGH;
+	dev_dbg(dev, "Sent %d frames, %d bytes\n", frame, pos);
 
+	/*
+	 * Wait for device to reset. Some bootloader versions do not assert
+	 * the CHG line after bootloading has finished, so ignore potential
+	 * errors.
+	 */
+	mxt_wait_for_completion(data, &data->bl_completion, MXT_FW_RESET_TIME);
+
+	data->in_bootloader = false;
+
+disable_irq:
+	disable_irq(data->irq);
+release_firmware:
+	release_firmware(fw);
 	return ret;
 }
 
@@ -1053,28 +1336,23 @@ static ssize_t mxt_update_fw_store(struct device *dev,
 	struct mxt_data *data = dev_get_drvdata(dev);
 	int error;
 
-	disable_irq(data->irq);
-
 	error = mxt_load_fw(dev, MXT_FW_NAME);
 	if (error) {
 		dev_err(dev, "The firmware update failed(%d)\n", error);
 		count = error;
 	} else {
-		dev_dbg(dev, "The firmware update succeeded\n");
-
-		/* Wait for reset */
-		msleep(MXT_FWRESET_TIME);
+		dev_info(dev, "The firmware update succeeded\n");
 
 		mxt_free_object_table(data);
 
 		mxt_initialize(data);
-	}
 
-	enable_irq(data->irq);
+		enable_irq(data->irq);
 
-	error = mxt_make_highchg(data);
-	if (error)
-		return error;
+		error = mxt_make_highchg(data);
+		if (error)
+			return error;
+	}
 
 	return count;
 }
@@ -1134,6 +1412,8 @@ static int mxt_probe(struct i2c_client *client,
 	struct input_dev *input_dev;
 	int error;
 	unsigned int num_mt_slots;
+	unsigned int mt_flags = 0;
+	int i;
 
 	if (!pdata)
 		return -EINVAL;
@@ -1146,10 +1426,7 @@ static int mxt_probe(struct i2c_client *client,
 		goto err_free_mem;
 	}
 
-	data->is_tp = pdata && pdata->is_tp;
-
-	input_dev->name = (data->is_tp) ? "Atmel maXTouch Touchpad" :
-					  "Atmel maXTouch Touchscreen";
+	input_dev->name = "Atmel maXTouch Touchscreen";
 	snprintf(data->phys, sizeof(data->phys), "i2c-%u-%04x/input0",
 		 client->adapter->nr, client->addr);
 
@@ -1165,7 +1442,9 @@ static int mxt_probe(struct i2c_client *client,
 	data->pdata = pdata;
 	data->irq = client->irq;
 
-	mxt_calc_resolution(data);
+	init_completion(&data->bl_completion);
+	init_completion(&data->reset_completion);
+	init_completion(&data->crc_completion);
 
 	error = mxt_initialize(data);
 	if (error)
@@ -1175,20 +1454,15 @@ static int mxt_probe(struct i2c_client *client,
 	__set_bit(EV_KEY, input_dev->evbit);
 	__set_bit(BTN_TOUCH, input_dev->keybit);
 
-	if (data->is_tp) {
-		int i;
-		__set_bit(INPUT_PROP_POINTER, input_dev->propbit);
+	if (pdata->t19_num_keys) {
 		__set_bit(INPUT_PROP_BUTTONPAD, input_dev->propbit);
 
-		for (i = 0; i < MXT_NUM_GPIO; i++)
-			if (pdata->key_map[i] != KEY_RESERVED)
-				__set_bit(pdata->key_map[i], input_dev->keybit);
+		for (i = 0; i < pdata->t19_num_keys; i++)
+			if (pdata->t19_keymap[i] != KEY_RESERVED)
+				input_set_capability(input_dev, EV_KEY,
+						     pdata->t19_keymap[i]);
 
-		__set_bit(BTN_TOOL_FINGER, input_dev->keybit);
-		__set_bit(BTN_TOOL_DOUBLETAP, input_dev->keybit);
-		__set_bit(BTN_TOOL_TRIPLETAP, input_dev->keybit);
-		__set_bit(BTN_TOOL_QUADTAP, input_dev->keybit);
-		__set_bit(BTN_TOOL_QUINTTAP, input_dev->keybit);
+		mt_flags |= INPUT_MT_POINTER;
 
 		input_abs_set_res(input_dev, ABS_X, MXT_PIXELS_PER_MM);
 		input_abs_set_res(input_dev, ABS_Y, MXT_PIXELS_PER_MM);
@@ -1196,6 +1470,8 @@ static int mxt_probe(struct i2c_client *client,
 				  MXT_PIXELS_PER_MM);
 		input_abs_set_res(input_dev, ABS_MT_POSITION_Y,
 				  MXT_PIXELS_PER_MM);
+
+		input_dev->name = "Atmel maXTouch Touchpad";
 	}
 
 	/* For single touch */
@@ -1208,7 +1484,7 @@ static int mxt_probe(struct i2c_client *client,
 
 	/* For multi touch */
 	num_mt_slots = data->T9_reportid_max - data->T9_reportid_min + 1;
-	error = input_mt_init_slots(input_dev, num_mt_slots, 0);
+	error = input_mt_init_slots(input_dev, num_mt_slots, mt_flags);
 	if (error)
 		goto err_free_object;
 	input_set_abs_params(input_dev, ABS_MT_TOUCH_MAJOR,
@@ -1236,12 +1512,18 @@ static int mxt_probe(struct i2c_client *client,
 		goto err_free_irq;
 
 	error = input_register_device(input_dev);
-	if (error)
+	if (error) {
+		dev_err(&client->dev, "Error %d registering input device\n",
+			error);
 		goto err_free_irq;
+	}
 
 	error = sysfs_create_group(&client->dev.kobj, &mxt_attr_group);
-	if (error)
+	if (error) {
+		dev_err(&client->dev, "Failure %d creating sysfs group\n",
+			error);
 		goto err_unregister_device;
+	}
 
 	return 0;
 
@@ -1294,11 +1576,7 @@ static int mxt_resume(struct device *dev)
 	struct mxt_data *data = i2c_get_clientdata(client);
 	struct input_dev *input_dev = data->input_dev;
 
-	/* Soft reset */
-	mxt_write_object(data, MXT_GEN_COMMAND_T6,
-			MXT_COMMAND_RESET, 1);
-
-	msleep(MXT_RESET_TIME);
+	mxt_soft_reset(data);
 
 	mutex_lock(&input_dev->mutex);
 
diff --git a/drivers/input/touchscreen/auo-pixcir-ts.c b/drivers/input/touchscreen/auo-pixcir-ts.c
index d3f9f6b0f9b..7f3c9478778 100644
--- a/drivers/input/touchscreen/auo-pixcir-ts.c
+++ b/drivers/input/touchscreen/auo-pixcir-ts.c
@@ -679,7 +679,7 @@ static const struct i2c_device_id auo_pixcir_idtable[] = {
 MODULE_DEVICE_TABLE(i2c, auo_pixcir_idtable);
 
 #ifdef CONFIG_OF
-static struct of_device_id auo_pixcir_ts_dt_idtable[] = {
+static const struct of_device_id auo_pixcir_ts_dt_idtable[] = {
 	{ .compatible = "auo,auo_pixcir_ts" },
 	{},
 };
diff --git a/drivers/input/touchscreen/da9034-ts.c b/drivers/input/touchscreen/da9034-ts.c
index 8ccf7bb4028..cf6f4b31db4 100644
--- a/drivers/input/touchscreen/da9034-ts.c
+++ b/drivers/input/touchscreen/da9034-ts.c
@@ -301,10 +301,11 @@ static int da9034_touch_probe(struct platform_device *pdev)
 	struct da9034_touch_pdata *pdata = dev_get_platdata(&pdev->dev);
 	struct da9034_touch *touch;
 	struct input_dev *input_dev;
-	int ret;
+	int error;
 
-	touch = kzalloc(sizeof(struct da9034_touch), GFP_KERNEL);
-	if (touch == NULL) {
+	touch = devm_kzalloc(&pdev->dev, sizeof(struct da9034_touch),
+			     GFP_KERNEL);
+	if (!touch) {
 		dev_err(&pdev->dev, "failed to allocate driver data\n");
 		return -ENOMEM;
 	}
@@ -315,18 +316,18 @@ static int da9034_touch_probe(struct platform_device *pdev)
 		touch->interval_ms	= pdata->interval_ms;
 		touch->x_inverted	= pdata->x_inverted;
 		touch->y_inverted	= pdata->y_inverted;
-	} else
+	} else {
 		/* fallback into default */
 		touch->interval_ms	= 10;
+	}
 
 	INIT_DELAYED_WORK(&touch->tsi_work, da9034_tsi_work);
 	touch->notifier.notifier_call = da9034_touch_notifier;
 
-	input_dev = input_allocate_device();
+	input_dev = devm_input_allocate_device(&pdev->dev);
 	if (!input_dev) {
 		dev_err(&pdev->dev, "failed to allocate input device\n");
-		ret = -ENOMEM;
-		goto err_free_touch;
+		return -ENOMEM;
 	}
 
 	input_dev->name		= pdev->name;
@@ -346,26 +347,9 @@ static int da9034_touch_probe(struct platform_device *pdev)
 	touch->input_dev = input_dev;
 	input_set_drvdata(input_dev, touch);
 
-	ret = input_register_device(input_dev);
-	if (ret)
-		goto err_free_input;
-
-	platform_set_drvdata(pdev, touch);
-	return 0;
-
-err_free_input:
-	input_free_device(input_dev);
-err_free_touch:
-	kfree(touch);
-	return ret;
-}
-
-static int da9034_touch_remove(struct platform_device *pdev)
-{
-	struct da9034_touch *touch = platform_get_drvdata(pdev);
-
-	input_unregister_device(touch->input_dev);
-	kfree(touch);
+	error = input_register_device(input_dev);
+	if (error)
+		return error;
 
 	return 0;
 }
@@ -376,7 +360,6 @@ static struct platform_driver da9034_touch_driver = {
 		.owner	= THIS_MODULE,
 	},
 	.probe		= da9034_touch_probe,
-	.remove		= da9034_touch_remove,
 };
 module_platform_driver(da9034_touch_driver);
 
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index f8815bebc9e..d4f33992ad8 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -271,7 +271,7 @@ static int edt_ft5x06_register_write(struct edt_ft5x06_ts_data *tsdata,
 		wrbuf[0] = addr;
 		wrbuf[1] = value;
 
-		return edt_ft5x06_ts_readwrite(tsdata->client, 3,
+		return edt_ft5x06_ts_readwrite(tsdata->client, 2,
 					wrbuf, 0, NULL);
 
 	default:
diff --git a/drivers/input/touchscreen/egalax_ts.c b/drivers/input/touchscreen/egalax_ts.c
index e6bcb13680b..c8057847d71 100644
--- a/drivers/input/touchscreen/egalax_ts.c
+++ b/drivers/input/touchscreen/egalax_ts.c
@@ -262,7 +262,7 @@ static int egalax_ts_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(egalax_ts_pm_ops, egalax_ts_suspend, egalax_ts_resume);
 
-static struct of_device_id egalax_ts_dt_ids[] = {
+static const struct of_device_id egalax_ts_dt_ids[] = {
 	{ .compatible = "eeti,egalax_ts" },
 	{ /* sentinel */ }
 };
diff --git a/drivers/input/touchscreen/intel-mid-touch.c b/drivers/input/touchscreen/intel-mid-touch.c
index 4f6b156144e..c38ca4a7e38 100644
--- a/drivers/input/touchscreen/intel-mid-touch.c
+++ b/drivers/input/touchscreen/intel-mid-touch.c
@@ -36,6 +36,7 @@
 #include <linux/irq.h>
 #include <linux/delay.h>
 #include <asm/intel_scu_ipc.h>
+#include <linux/device.h>
 
 /* PMIC Interrupt registers */
 #define PMIC_REG_ID1		0x00 /* PMIC ID1 register */
@@ -580,12 +581,17 @@ static int mrstouch_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	tsdev = kzalloc(sizeof(struct mrstouch_dev), GFP_KERNEL);
-	input = input_allocate_device();
-	if (!tsdev || !input) {
+	tsdev = devm_kzalloc(&pdev->dev, sizeof(struct mrstouch_dev),
+			     GFP_KERNEL);
+	if (!tsdev) {
 		dev_err(&pdev->dev, "unable to allocate memory\n");
-		err = -ENOMEM;
-		goto err_free_mem;
+		return -ENOMEM;
+	}
+
+	input = devm_input_allocate_device(&pdev->dev);
+	if (!input) {
+		dev_err(&pdev->dev, "unable to allocate input device\n");
+		return -ENOMEM;
 	}
 
 	tsdev->dev = &pdev->dev;
@@ -598,7 +604,7 @@ static int mrstouch_probe(struct platform_device *pdev)
 	err = mrstouch_adc_init(tsdev);
 	if (err) {
 		dev_err(&pdev->dev, "ADC initialization failed\n");
-		goto err_free_mem;
+		return err;
 	}
 
 	input->name = "mrst_touchscreen";
@@ -618,38 +624,20 @@ static int mrstouch_probe(struct platform_device *pdev)
 	input_set_abs_params(tsdev->input, ABS_PRESSURE,
 			     MRST_PRESSURE_MIN, MRST_PRESSURE_MAX, 0, 0);
 
-	err = request_threaded_irq(tsdev->irq, NULL, mrstouch_pendet_irq,
-				   IRQF_ONESHOT, "mrstouch", tsdev);
+	err = devm_request_threaded_irq(&pdev->dev, tsdev->irq, NULL,
+					mrstouch_pendet_irq, IRQF_ONESHOT,
+					"mrstouch", tsdev);
 	if (err) {
 		dev_err(tsdev->dev, "unable to allocate irq\n");
-		goto err_free_mem;
+		return err;
 	}
 
 	err = input_register_device(tsdev->input);
 	if (err) {
 		dev_err(tsdev->dev, "unable to register input device\n");
-		goto err_free_irq;
+		return err;
 	}
 
-	platform_set_drvdata(pdev, tsdev);
-	return 0;
-
-err_free_irq:
-	free_irq(tsdev->irq, tsdev);
-err_free_mem:
-	input_free_device(input);
-	kfree(tsdev);
-	return err;
-}
-
-static int mrstouch_remove(struct platform_device *pdev)
-{
-	struct mrstouch_dev *tsdev = platform_get_drvdata(pdev);
-
-	free_irq(tsdev->irq, tsdev);
-	input_unregister_device(tsdev->input);
-	kfree(tsdev);
-
 	return 0;
 }
 
@@ -659,7 +647,6 @@ static struct platform_driver mrstouch_driver = {
 		.owner	= THIS_MODULE,
 	},
 	.probe		= mrstouch_probe,
-	.remove		= mrstouch_remove,
 };
 module_platform_driver(mrstouch_driver);
 
diff --git a/drivers/input/touchscreen/lpc32xx_ts.c b/drivers/input/touchscreen/lpc32xx_ts.c
index 2058253b55d..bb47d3442a3 100644
--- a/drivers/input/touchscreen/lpc32xx_ts.c
+++ b/drivers/input/touchscreen/lpc32xx_ts.c
@@ -384,7 +384,7 @@ static const struct dev_pm_ops lpc32xx_ts_pm_ops = {
 #endif
 
 #ifdef CONFIG_OF
-static struct of_device_id lpc32xx_tsc_of_match[] = {
+static const struct of_device_id lpc32xx_tsc_of_match[] = {
 	{ .compatible = "nxp,lpc3220-tsc", },
 	{ },
 };
diff --git a/drivers/input/touchscreen/mcs5000_ts.c b/drivers/input/touchscreen/mcs5000_ts.c
index 647e36f5930..00510a9836b 100644
--- a/drivers/input/touchscreen/mcs5000_ts.c
+++ b/drivers/input/touchscreen/mcs5000_ts.c
@@ -161,10 +161,9 @@ static irqreturn_t mcs5000_ts_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void mcs5000_ts_phys_init(struct mcs5000_ts_data *data)
+static void mcs5000_ts_phys_init(struct mcs5000_ts_data *data,
+				 const struct mcs_platform_data *platform_data)
 {
-	const struct mcs_platform_data *platform_data =
-		data->platform_data;
 	struct i2c_client *client = data->client;
 
 	/* Touch reset & sleep mode */
@@ -187,28 +186,32 @@ static void mcs5000_ts_phys_init(struct mcs5000_ts_data *data)
 }
 
 static int mcs5000_ts_probe(struct i2c_client *client,
-		const struct i2c_device_id *id)
+			    const struct i2c_device_id *id)
 {
+	const struct mcs_platform_data *pdata;
 	struct mcs5000_ts_data *data;
 	struct input_dev *input_dev;
-	int ret;
+	int error;
 
-	if (!dev_get_platdata(&client->dev))
+	pdata = dev_get_platdata(&client->dev);
+	if (!pdata)
 		return -EINVAL;
 
-	data = kzalloc(sizeof(struct mcs5000_ts_data), GFP_KERNEL);
-	input_dev = input_allocate_device();
-	if (!data || !input_dev) {
+	data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL);
+	if (!data) {
 		dev_err(&client->dev, "Failed to allocate memory\n");
-		ret = -ENOMEM;
-		goto err_free_mem;
+		return -ENOMEM;
 	}
 
 	data->client = client;
-	data->input_dev = input_dev;
-	data->platform_data = dev_get_platdata(&client->dev);
 
-	input_dev->name = "MELPAS MCS-5000 Touchscreen";
+	input_dev = devm_input_allocate_device(&client->dev);
+	if (!input_dev) {
+		dev_err(&client->dev, "Failed to allocate input device\n");
+		return -ENOMEM;
+	}
+
+	input_dev->name = "MELFAS MCS-5000 Touchscreen";
 	input_dev->id.bustype = BUS_I2C;
 	input_dev->dev.parent = &client->dev;
 
@@ -219,44 +222,30 @@ static int mcs5000_ts_probe(struct i2c_client *client,
 	input_set_abs_params(input_dev, ABS_Y, 0, MCS5000_MAX_YC, 0, 0);
 
 	input_set_drvdata(input_dev, data);
+	data->input_dev = input_dev;
 
-	if (data->platform_data->cfg_pin)
-		data->platform_data->cfg_pin();
-
-	ret = request_threaded_irq(client->irq, NULL, mcs5000_ts_interrupt,
-			IRQF_TRIGGER_LOW | IRQF_ONESHOT, "mcs5000_ts", data);
+	if (pdata->cfg_pin)
+		pdata->cfg_pin();
 
-	if (ret < 0) {
+	error = devm_request_threaded_irq(&client->dev, client->irq,
+					  NULL, mcs5000_ts_interrupt,
+					  IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+					  "mcs5000_ts", data);
+	if (error) {
 		dev_err(&client->dev, "Failed to register interrupt\n");
-		goto err_free_mem;
+		return error;
 	}
 
-	ret = input_register_device(data->input_dev);
-	if (ret < 0)
-		goto err_free_irq;
+	error = input_register_device(data->input_dev);
+	if (error) {
+		dev_err(&client->dev, "Failed to register input device\n");
+		return error;
+	}
 
-	mcs5000_ts_phys_init(data);
+	mcs5000_ts_phys_init(data, pdata);
 	i2c_set_clientdata(client, data);
 
 	return 0;
-
-err_free_irq:
-	free_irq(client->irq, data);
-err_free_mem:
-	input_free_device(input_dev);
-	kfree(data);
-	return ret;
-}
-
-static int mcs5000_ts_remove(struct i2c_client *client)
-{
-	struct mcs5000_ts_data *data = i2c_get_clientdata(client);
-
-	free_irq(client->irq, data);
-	input_unregister_device(data->input_dev);
-	kfree(data);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM
@@ -274,14 +263,15 @@ static int mcs5000_ts_resume(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct mcs5000_ts_data *data = i2c_get_clientdata(client);
+	const struct mcs_platform_data *pdata = dev_get_platdata(dev);
 
-	mcs5000_ts_phys_init(data);
+	mcs5000_ts_phys_init(data, pdata);
 
 	return 0;
 }
+#endif
 
 static SIMPLE_DEV_PM_OPS(mcs5000_ts_pm, mcs5000_ts_suspend, mcs5000_ts_resume);
-#endif
 
 static const struct i2c_device_id mcs5000_ts_id[] = {
 	{ "mcs5000_ts", 0 },
@@ -291,12 +281,9 @@ MODULE_DEVICE_TABLE(i2c, mcs5000_ts_id);
 
 static struct i2c_driver mcs5000_ts_driver = {
 	.probe		= mcs5000_ts_probe,
-	.remove		= mcs5000_ts_remove,
 	.driver = {
 		.name = "mcs5000_ts",
-#ifdef CONFIG_PM
 		.pm   = &mcs5000_ts_pm,
-#endif
 	},
 	.id_table	= mcs5000_ts_id,
 };
diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c
index 8a598c06539..372bbf7658f 100644
--- a/drivers/input/touchscreen/mms114.c
+++ b/drivers/input/touchscreen/mms114.c
@@ -456,7 +456,7 @@ static int mms114_probe(struct i2c_client *client,
 	data->input_dev = input_dev;
 	data->pdata = pdata;
 
-	input_dev->name = "MELPAS MMS114 Touchscreen";
+	input_dev->name = "MELFAS MMS114 Touchscreen";
 	input_dev->id.bustype = BUS_I2C;
 	input_dev->dev.parent = &client->dev;
 	input_dev->open = mms114_input_open;
@@ -570,7 +570,7 @@ static const struct i2c_device_id mms114_id[] = {
 MODULE_DEVICE_TABLE(i2c, mms114_id);
 
 #ifdef CONFIG_OF
-static struct of_device_id mms114_dt_match[] = {
+static const struct of_device_id mms114_dt_match[] = {
 	{ .compatible = "melfas,mms114" },
 	{ }
 };
diff --git a/drivers/input/touchscreen/of_touchscreen.c b/drivers/input/touchscreen/of_touchscreen.c
new file mode 100644
index 00000000000..f8f9b84230b
--- /dev/null
+++ b/drivers/input/touchscreen/of_touchscreen.c
@@ -0,0 +1,45 @@
+/*
+ *  Generic DT helper functions for touchscreen devices
+ *
+ *  Copyright (c) 2014 Sebastian Reichel <sre@kernel.org>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/of.h>
+#include <linux/input.h>
+#include <linux/input/touchscreen.h>
+
+/**
+ * touchscreen_parse_of_params - parse common touchscreen DT properties
+ * @dev: device that should be parsed
+ *
+ * This function parses common DT properties for touchscreens and setups the
+ * input device accordingly. The function keeps previously setuped default
+ * values if no value is specified via DT.
+ */
+void touchscreen_parse_of_params(struct input_dev *dev)
+{
+	struct device_node *np = dev->dev.parent->of_node;
+	struct input_absinfo *absinfo;
+
+	input_alloc_absinfo(dev);
+	if (!dev->absinfo)
+		return;
+
+	absinfo = &dev->absinfo[ABS_X];
+	of_property_read_u32(np, "touchscreen-size-x", &absinfo->maximum);
+	of_property_read_u32(np, "touchscreen-fuzz-x", &absinfo->fuzz);
+
+	absinfo = &dev->absinfo[ABS_Y];
+	of_property_read_u32(np, "touchscreen-size-y", &absinfo->maximum);
+	of_property_read_u32(np, "touchscreen-fuzz-y", &absinfo->fuzz);
+
+	absinfo = &dev->absinfo[ABS_PRESSURE];
+	of_property_read_u32(np, "touchscreen-max-pressure", &absinfo->maximum);
+	of_property_read_u32(np, "touchscreen-fuzz-pressure", &absinfo->fuzz);
+}
+EXPORT_SYMBOL(touchscreen_parse_of_params);
diff --git a/drivers/input/touchscreen/pixcir_i2c_ts.c b/drivers/input/touchscreen/pixcir_i2c_ts.c
index 02392d2061d..19c6c0fdc94 100644
--- a/drivers/input/touchscreen/pixcir_i2c_ts.c
+++ b/drivers/input/touchscreen/pixcir_i2c_ts.c
@@ -24,12 +24,13 @@
 #include <linux/i2c.h>
 #include <linux/input.h>
 #include <linux/input/pixcir_ts.h>
+#include <linux/gpio.h>
 
 struct pixcir_i2c_ts_data {
 	struct i2c_client *client;
 	struct input_dev *input;
 	const struct pixcir_ts_platform_data *chip;
-	bool exiting;
+	bool running;
 };
 
 static void pixcir_ts_poscheck(struct pixcir_i2c_ts_data *data)
@@ -87,11 +88,12 @@ static void pixcir_ts_poscheck(struct pixcir_i2c_ts_data *data)
 static irqreturn_t pixcir_ts_isr(int irq, void *dev_id)
 {
 	struct pixcir_i2c_ts_data *tsdata = dev_id;
+	const struct pixcir_ts_platform_data *pdata = tsdata->chip;
 
-	while (!tsdata->exiting) {
+	while (tsdata->running) {
 		pixcir_ts_poscheck(tsdata);
 
-		if (tsdata->chip->attb_read_val())
+		if (gpio_get_value(pdata->gpio_attb))
 			break;
 
 		msleep(20);
@@ -100,25 +102,221 @@ static irqreturn_t pixcir_ts_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static int pixcir_set_power_mode(struct pixcir_i2c_ts_data *ts,
+				 enum pixcir_power_mode mode)
+{
+	struct device *dev = &ts->client->dev;
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(ts->client, PIXCIR_REG_POWER_MODE);
+	if (ret < 0) {
+		dev_err(dev, "%s: can't read reg 0x%x : %d\n",
+			__func__, PIXCIR_REG_POWER_MODE, ret);
+		return ret;
+	}
+
+	ret &= ~PIXCIR_POWER_MODE_MASK;
+	ret |= mode;
+
+	/* Always AUTO_IDLE */
+	ret |= PIXCIR_POWER_ALLOW_IDLE;
+
+	ret = i2c_smbus_write_byte_data(ts->client, PIXCIR_REG_POWER_MODE, ret);
+	if (ret < 0) {
+		dev_err(dev, "%s: can't write reg 0x%x : %d\n",
+			__func__, PIXCIR_REG_POWER_MODE, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Set the interrupt mode for the device i.e. ATTB line behaviour
+ *
+ * @polarity : 1 for active high, 0 for active low.
+ */
+static int pixcir_set_int_mode(struct pixcir_i2c_ts_data *ts,
+			       enum pixcir_int_mode mode, bool polarity)
+{
+	struct device *dev = &ts->client->dev;
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(ts->client, PIXCIR_REG_INT_MODE);
+	if (ret < 0) {
+		dev_err(dev, "%s: can't read reg 0x%x : %d\n",
+			__func__, PIXCIR_REG_INT_MODE, ret);
+		return ret;
+	}
+
+	ret &= ~PIXCIR_INT_MODE_MASK;
+	ret |= mode;
+
+	if (polarity)
+		ret |= PIXCIR_INT_POL_HIGH;
+	else
+		ret &= ~PIXCIR_INT_POL_HIGH;
+
+	ret = i2c_smbus_write_byte_data(ts->client, PIXCIR_REG_INT_MODE, ret);
+	if (ret < 0) {
+		dev_err(dev, "%s: can't write reg 0x%x : %d\n",
+			__func__, PIXCIR_REG_INT_MODE, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Enable/disable interrupt generation
+ */
+static int pixcir_int_enable(struct pixcir_i2c_ts_data *ts, bool enable)
+{
+	struct device *dev = &ts->client->dev;
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(ts->client, PIXCIR_REG_INT_MODE);
+	if (ret < 0) {
+		dev_err(dev, "%s: can't read reg 0x%x : %d\n",
+			__func__, PIXCIR_REG_INT_MODE, ret);
+		return ret;
+	}
+
+	if (enable)
+		ret |= PIXCIR_INT_ENABLE;
+	else
+		ret &= ~PIXCIR_INT_ENABLE;
+
+	ret = i2c_smbus_write_byte_data(ts->client, PIXCIR_REG_INT_MODE, ret);
+	if (ret < 0) {
+		dev_err(dev, "%s: can't write reg 0x%x : %d\n",
+			__func__, PIXCIR_REG_INT_MODE, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int pixcir_start(struct pixcir_i2c_ts_data *ts)
+{
+	struct device *dev = &ts->client->dev;
+	int error;
+
+	/* LEVEL_TOUCH interrupt with active low polarity */
+	error = pixcir_set_int_mode(ts, PIXCIR_INT_LEVEL_TOUCH, 0);
+	if (error) {
+		dev_err(dev, "Failed to set interrupt mode: %d\n", error);
+		return error;
+	}
+
+	ts->running = true;
+	mb();	/* Update status before IRQ can fire */
+
+	/* enable interrupt generation */
+	error = pixcir_int_enable(ts, true);
+	if (error) {
+		dev_err(dev, "Failed to enable interrupt generation: %d\n",
+			error);
+		return error;
+	}
+
+	return 0;
+}
+
+static int pixcir_stop(struct pixcir_i2c_ts_data *ts)
+{
+	int error;
+
+	/* Disable interrupt generation */
+	error = pixcir_int_enable(ts, false);
+	if (error) {
+		dev_err(&ts->client->dev,
+			"Failed to disable interrupt generation: %d\n",
+			error);
+		return error;
+	}
+
+	/* Exit ISR if running, no more report parsing */
+	ts->running = false;
+	mb();	/* update status before we synchronize irq */
+
+	/* Wait till running ISR is complete */
+	synchronize_irq(ts->client->irq);
+
+	return 0;
+}
+
+static int pixcir_input_open(struct input_dev *dev)
+{
+	struct pixcir_i2c_ts_data *ts = input_get_drvdata(dev);
+
+	return pixcir_start(ts);
+}
+
+static void pixcir_input_close(struct input_dev *dev)
+{
+	struct pixcir_i2c_ts_data *ts = input_get_drvdata(dev);
+
+	pixcir_stop(ts);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int pixcir_i2c_ts_suspend(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
+	struct pixcir_i2c_ts_data *ts = i2c_get_clientdata(client);
+	struct input_dev *input = ts->input;
+	int ret = 0;
+
+	mutex_lock(&input->mutex);
+
+	if (device_may_wakeup(&client->dev)) {
+		if (!input->users) {
+			ret = pixcir_start(ts);
+			if (ret) {
+				dev_err(dev, "Failed to start\n");
+				goto unlock;
+			}
+		}
 
-	if (device_may_wakeup(&client->dev))
 		enable_irq_wake(client->irq);
+	} else if (input->users) {
+		ret = pixcir_stop(ts);
+	}
 
-	return 0;
+unlock:
+	mutex_unlock(&input->mutex);
+
+	return ret;
 }
 
 static int pixcir_i2c_ts_resume(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
+	struct pixcir_i2c_ts_data *ts = i2c_get_clientdata(client);
+	struct input_dev *input = ts->input;
+	int ret = 0;
+
+	mutex_lock(&input->mutex);
 
-	if (device_may_wakeup(&client->dev))
+	if (device_may_wakeup(&client->dev)) {
 		disable_irq_wake(client->irq);
 
-	return 0;
+		if (!input->users) {
+			ret = pixcir_stop(ts);
+			if (ret) {
+				dev_err(dev, "Failed to stop\n");
+				goto unlock;
+			}
+		}
+	} else if (input->users) {
+		ret = pixcir_start(ts);
+	}
+
+unlock:
+	mutex_unlock(&input->mutex);
+
+	return ret;
 }
 #endif
 
@@ -130,6 +328,7 @@ static int pixcir_i2c_ts_probe(struct i2c_client *client,
 {
 	const struct pixcir_ts_platform_data *pdata =
 			dev_get_platdata(&client->dev);
+	struct device *dev = &client->dev;
 	struct pixcir_i2c_ts_data *tsdata;
 	struct input_dev *input;
 	int error;
@@ -139,12 +338,19 @@ static int pixcir_i2c_ts_probe(struct i2c_client *client,
 		return -EINVAL;
 	}
 
-	tsdata = kzalloc(sizeof(*tsdata), GFP_KERNEL);
-	input = input_allocate_device();
-	if (!tsdata || !input) {
-		dev_err(&client->dev, "Failed to allocate driver data!\n");
-		error = -ENOMEM;
-		goto err_free_mem;
+	if (!gpio_is_valid(pdata->gpio_attb)) {
+		dev_err(dev, "Invalid gpio_attb in pdata\n");
+		return -EINVAL;
+	}
+
+	tsdata = devm_kzalloc(dev, sizeof(*tsdata), GFP_KERNEL);
+	if (!tsdata)
+		return -ENOMEM;
+
+	input = devm_input_allocate_device(dev);
+	if (!input) {
+		dev_err(dev, "Failed to allocate input device\n");
+		return -ENOMEM;
 	}
 
 	tsdata->client = client;
@@ -153,6 +359,8 @@ static int pixcir_i2c_ts_probe(struct i2c_client *client,
 
 	input->name = client->name;
 	input->id.bustype = BUS_I2C;
+	input->open = pixcir_input_open;
+	input->close = pixcir_input_close;
 	input->dev.parent = &client->dev;
 
 	__set_bit(EV_KEY, input->evbit);
@@ -165,44 +373,47 @@ static int pixcir_i2c_ts_probe(struct i2c_client *client,
 
 	input_set_drvdata(input, tsdata);
 
-	error = request_threaded_irq(client->irq, NULL, pixcir_ts_isr,
-				     IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
-				     client->name, tsdata);
+	error = devm_gpio_request_one(dev, pdata->gpio_attb,
+				      GPIOF_DIR_IN, "pixcir_i2c_attb");
 	if (error) {
-		dev_err(&client->dev, "Unable to request touchscreen IRQ.\n");
-		goto err_free_mem;
+		dev_err(dev, "Failed to request ATTB gpio\n");
+		return error;
 	}
 
+	error = devm_request_threaded_irq(dev, client->irq, NULL, pixcir_ts_isr,
+					  IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					  client->name, tsdata);
+	if (error) {
+		dev_err(dev, "failed to request irq %d\n", client->irq);
+		return error;
+	}
+
+	/* Always be in IDLE mode to save power, device supports auto wake */
+	error = pixcir_set_power_mode(tsdata, PIXCIR_POWER_IDLE);
+	if (error) {
+		dev_err(dev, "Failed to set IDLE mode\n");
+		return error;
+	}
+
+	/* Stop device till opened */
+	error = pixcir_stop(tsdata);
+	if (error)
+		return error;
+
 	error = input_register_device(input);
 	if (error)
-		goto err_free_irq;
+		return error;
 
 	i2c_set_clientdata(client, tsdata);
 	device_init_wakeup(&client->dev, 1);
 
 	return 0;
-
-err_free_irq:
-	free_irq(client->irq, tsdata);
-err_free_mem:
-	input_free_device(input);
-	kfree(tsdata);
-	return error;
 }
 
 static int pixcir_i2c_ts_remove(struct i2c_client *client)
 {
-	struct pixcir_i2c_ts_data *tsdata = i2c_get_clientdata(client);
-
 	device_init_wakeup(&client->dev, 0);
 
-	tsdata->exiting = true;
-	mb();
-	free_irq(client->irq, tsdata);
-
-	input_unregister_device(tsdata->input);
-	kfree(tsdata);
-
 	return 0;
 }
 
diff --git a/drivers/input/touchscreen/sun4i-ts.c b/drivers/input/touchscreen/sun4i-ts.c
new file mode 100644
index 00000000000..2ba82602495
--- /dev/null
+++ b/drivers/input/touchscreen/sun4i-ts.c
@@ -0,0 +1,339 @@
+/*
+ * Allwinner sunxi resistive touchscreen controller driver
+ *
+ * Copyright (C) 2013 - 2014 Hans de Goede <hdegoede@redhat.com>
+ *
+ * The hwmon parts are based on work by Corentin LABBE which is:
+ * Copyright (C) 2013 Corentin LABBE <clabbe.montjoie@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * The sun4i-ts controller is capable of detecting a second touch, but when a
+ * second touch is present then the accuracy becomes so bad the reported touch
+ * location is not useable.
+ *
+ * The original android driver contains some complicated heuristics using the
+ * aprox. distance between the 2 touches to see if the user is making a pinch
+ * open / close movement, and then reports emulated multi-touch events around
+ * the last touch coordinate (as the dual-touch coordinates are worthless).
+ *
+ * These kinds of heuristics are just asking for trouble (and don't belong
+ * in the kernel). So this driver offers straight forward, reliable single
+ * touch functionality only.
+ */
+
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/init.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#define TP_CTRL0		0x00
+#define TP_CTRL1		0x04
+#define TP_CTRL2		0x08
+#define TP_CTRL3		0x0c
+#define TP_INT_FIFOC		0x10
+#define TP_INT_FIFOS		0x14
+#define TP_TPR			0x18
+#define TP_CDAT			0x1c
+#define TEMP_DATA		0x20
+#define TP_DATA			0x24
+
+/* TP_CTRL0 bits */
+#define ADC_FIRST_DLY(x)	((x) << 24) /* 8 bits */
+#define ADC_FIRST_DLY_MODE(x)	((x) << 23)
+#define ADC_CLK_SEL(x)		((x) << 22)
+#define ADC_CLK_DIV(x)		((x) << 20) /* 3 bits */
+#define FS_DIV(x)		((x) << 16) /* 4 bits */
+#define T_ACQ(x)		((x) << 0) /* 16 bits */
+
+/* TP_CTRL1 bits */
+#define STYLUS_UP_DEBOUN(x)	((x) << 12) /* 8 bits */
+#define STYLUS_UP_DEBOUN_EN(x)	((x) << 9)
+#define TOUCH_PAN_CALI_EN(x)	((x) << 6)
+#define TP_DUAL_EN(x)		((x) << 5)
+#define TP_MODE_EN(x)		((x) << 4)
+#define TP_ADC_SELECT(x)	((x) << 3)
+#define ADC_CHAN_SELECT(x)	((x) << 0)  /* 3 bits */
+
+/* TP_CTRL2 bits */
+#define TP_SENSITIVE_ADJUST(x)	((x) << 28) /* 4 bits */
+#define TP_MODE_SELECT(x)	((x) << 26) /* 2 bits */
+#define PRE_MEA_EN(x)		((x) << 24)
+#define PRE_MEA_THRE_CNT(x)	((x) << 0) /* 24 bits */
+
+/* TP_CTRL3 bits */
+#define FILTER_EN(x)		((x) << 2)
+#define FILTER_TYPE(x)		((x) << 0)  /* 2 bits */
+
+/* TP_INT_FIFOC irq and fifo mask / control bits */
+#define TEMP_IRQ_EN(x)		((x) << 18)
+#define OVERRUN_IRQ_EN(x)	((x) << 17)
+#define DATA_IRQ_EN(x)		((x) << 16)
+#define TP_DATA_XY_CHANGE(x)	((x) << 13)
+#define FIFO_TRIG(x)		((x) << 8)  /* 5 bits */
+#define DATA_DRQ_EN(x)		((x) << 7)
+#define FIFO_FLUSH(x)		((x) << 4)
+#define TP_UP_IRQ_EN(x)		((x) << 1)
+#define TP_DOWN_IRQ_EN(x)	((x) << 0)
+
+/* TP_INT_FIFOS irq and fifo status bits */
+#define TEMP_DATA_PENDING	BIT(18)
+#define FIFO_OVERRUN_PENDING	BIT(17)
+#define FIFO_DATA_PENDING	BIT(16)
+#define TP_IDLE_FLG		BIT(2)
+#define TP_UP_PENDING		BIT(1)
+#define TP_DOWN_PENDING		BIT(0)
+
+/* TP_TPR bits */
+#define TEMP_ENABLE(x)		((x) << 16)
+#define TEMP_PERIOD(x)		((x) << 0)  /* t = x * 256 * 16 / clkin */
+
+struct sun4i_ts_data {
+	struct device *dev;
+	struct input_dev *input;
+	void __iomem *base;
+	unsigned int irq;
+	bool ignore_fifo_data;
+	int temp_data;
+};
+
+static void sun4i_ts_irq_handle_input(struct sun4i_ts_data *ts, u32 reg_val)
+{
+	u32 x, y;
+
+	if (reg_val & FIFO_DATA_PENDING) {
+		x = readl(ts->base + TP_DATA);
+		y = readl(ts->base + TP_DATA);
+		/* The 1st location reported after an up event is unreliable */
+		if (!ts->ignore_fifo_data) {
+			input_report_abs(ts->input, ABS_X, x);
+			input_report_abs(ts->input, ABS_Y, y);
+			/*
+			 * The hardware has a separate down status bit, but
+			 * that gets set before we get the first location,
+			 * resulting in reporting a click on the old location.
+			 */
+			input_report_key(ts->input, BTN_TOUCH, 1);
+			input_sync(ts->input);
+		} else {
+			ts->ignore_fifo_data = false;
+		}
+	}
+
+	if (reg_val & TP_UP_PENDING) {
+		ts->ignore_fifo_data = true;
+		input_report_key(ts->input, BTN_TOUCH, 0);
+		input_sync(ts->input);
+	}
+}
+
+static irqreturn_t sun4i_ts_irq(int irq, void *dev_id)
+{
+	struct sun4i_ts_data *ts = dev_id;
+	u32 reg_val;
+
+	reg_val  = readl(ts->base + TP_INT_FIFOS);
+
+	if (reg_val & TEMP_DATA_PENDING)
+		ts->temp_data = readl(ts->base + TEMP_DATA);
+
+	if (ts->input)
+		sun4i_ts_irq_handle_input(ts, reg_val);
+
+	writel(reg_val, ts->base + TP_INT_FIFOS);
+
+	return IRQ_HANDLED;
+}
+
+static int sun4i_ts_open(struct input_dev *dev)
+{
+	struct sun4i_ts_data *ts = input_get_drvdata(dev);
+
+	/* Flush, set trig level to 1, enable temp, data and up irqs */
+	writel(TEMP_IRQ_EN(1) | DATA_IRQ_EN(1) | FIFO_TRIG(1) | FIFO_FLUSH(1) |
+		TP_UP_IRQ_EN(1), ts->base + TP_INT_FIFOC);
+
+	return 0;
+}
+
+static void sun4i_ts_close(struct input_dev *dev)
+{
+	struct sun4i_ts_data *ts = input_get_drvdata(dev);
+
+	/* Deactivate all input IRQs */
+	writel(TEMP_IRQ_EN(1), ts->base + TP_INT_FIFOC);
+}
+
+static ssize_t show_temp(struct device *dev, struct device_attribute *devattr,
+			 char *buf)
+{
+	struct sun4i_ts_data *ts = dev_get_drvdata(dev);
+
+	/* No temp_data until the first irq */
+	if (ts->temp_data == -1)
+		return -EAGAIN;
+
+	return sprintf(buf, "%d\n", (ts->temp_data - 1447) * 100);
+}
+
+static ssize_t show_temp_label(struct device *dev,
+			      struct device_attribute *devattr, char *buf)
+{
+	return sprintf(buf, "SoC temperature\n");
+}
+
+static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
+static DEVICE_ATTR(temp1_label, S_IRUGO, show_temp_label, NULL);
+
+static struct attribute *sun4i_ts_attrs[] = {
+	&dev_attr_temp1_input.attr,
+	&dev_attr_temp1_label.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(sun4i_ts);
+
+static int sun4i_ts_probe(struct platform_device *pdev)
+{
+	struct sun4i_ts_data *ts;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct device *hwmon;
+	int error;
+	bool ts_attached;
+
+	ts = devm_kzalloc(dev, sizeof(struct sun4i_ts_data), GFP_KERNEL);
+	if (!ts)
+		return -ENOMEM;
+
+	ts->dev = dev;
+	ts->ignore_fifo_data = true;
+	ts->temp_data = -1;
+
+	ts_attached = of_property_read_bool(np, "allwinner,ts-attached");
+	if (ts_attached) {
+		ts->input = devm_input_allocate_device(dev);
+		if (!ts->input)
+			return -ENOMEM;
+
+		ts->input->name = pdev->name;
+		ts->input->phys = "sun4i_ts/input0";
+		ts->input->open = sun4i_ts_open;
+		ts->input->close = sun4i_ts_close;
+		ts->input->id.bustype = BUS_HOST;
+		ts->input->id.vendor = 0x0001;
+		ts->input->id.product = 0x0001;
+		ts->input->id.version = 0x0100;
+		ts->input->evbit[0] =  BIT(EV_SYN) | BIT(EV_KEY) | BIT(EV_ABS);
+		__set_bit(BTN_TOUCH, ts->input->keybit);
+		input_set_abs_params(ts->input, ABS_X, 0, 4095, 0, 0);
+		input_set_abs_params(ts->input, ABS_Y, 0, 4095, 0, 0);
+		input_set_drvdata(ts->input, ts);
+	}
+
+	ts->base = devm_ioremap_resource(dev,
+			      platform_get_resource(pdev, IORESOURCE_MEM, 0));
+	if (IS_ERR(ts->base))
+		return PTR_ERR(ts->base);
+
+	ts->irq = platform_get_irq(pdev, 0);
+	error = devm_request_irq(dev, ts->irq, sun4i_ts_irq, 0, "sun4i-ts", ts);
+	if (error)
+		return error;
+
+	/*
+	 * Select HOSC clk, clkin = clk / 6, adc samplefreq = clkin / 8192,
+	 * t_acq = clkin / (16 * 64)
+	 */
+	writel(ADC_CLK_SEL(0) | ADC_CLK_DIV(2) | FS_DIV(7) | T_ACQ(63),
+	       ts->base + TP_CTRL0);
+
+	/*
+	 * sensitive_adjust = 15 : max, which is not all that sensitive,
+	 * tp_mode = 0 : only x and y coordinates, as we don't use dual touch
+	 */
+	writel(TP_SENSITIVE_ADJUST(15) | TP_MODE_SELECT(0),
+	       ts->base + TP_CTRL2);
+
+	/* Enable median filter, type 1 : 5/3 */
+	writel(FILTER_EN(1) | FILTER_TYPE(1), ts->base + TP_CTRL3);
+
+	/* Enable temperature measurement, period 1953 (2 seconds) */
+	writel(TEMP_ENABLE(1) | TEMP_PERIOD(1953), ts->base + TP_TPR);
+
+	/*
+	 * Set stylus up debounce to aprox 10 ms, enable debounce, and
+	 * finally enable tp mode.
+	 */
+	writel(STYLUS_UP_DEBOUN(5) | STYLUS_UP_DEBOUN_EN(1) | TP_MODE_EN(1),
+	       ts->base + TP_CTRL1);
+
+	hwmon = devm_hwmon_device_register_with_groups(ts->dev, "sun4i_ts",
+						       ts, sun4i_ts_groups);
+	if (IS_ERR(hwmon))
+		return PTR_ERR(hwmon);
+
+	writel(TEMP_IRQ_EN(1), ts->base + TP_INT_FIFOC);
+
+	if (ts_attached) {
+		error = input_register_device(ts->input);
+		if (error) {
+			writel(0, ts->base + TP_INT_FIFOC);
+			return error;
+		}
+	}
+
+	platform_set_drvdata(pdev, ts);
+	return 0;
+}
+
+static int sun4i_ts_remove(struct platform_device *pdev)
+{
+	struct sun4i_ts_data *ts = platform_get_drvdata(pdev);
+
+	/* Explicit unregister to avoid open/close changing the imask later */
+	if (ts->input)
+		input_unregister_device(ts->input);
+
+	/* Deactivate all IRQs */
+	writel(0, ts->base + TP_INT_FIFOC);
+
+	return 0;
+}
+
+static const struct of_device_id sun4i_ts_of_match[] = {
+	{ .compatible = "allwinner,sun4i-a10-ts", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sun4i_ts_of_match);
+
+static struct platform_driver sun4i_ts_driver = {
+	.driver = {
+		.owner	= THIS_MODULE,
+		.name	= "sun4i-ts",
+		.of_match_table = of_match_ptr(sun4i_ts_of_match),
+	},
+	.probe	= sun4i_ts_probe,
+	.remove	= sun4i_ts_remove,
+};
+
+module_platform_driver(sun4i_ts_driver);
+
+MODULE_DESCRIPTION("Allwinner sun4i resistive touchscreen controller driver");
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/input/touchscreen/ti_am335x_tsc.c b/drivers/input/touchscreen/ti_am335x_tsc.c
index 4e793a17361..2ce649520fe 100644
--- a/drivers/input/touchscreen/ti_am335x_tsc.c
+++ b/drivers/input/touchscreen/ti_am335x_tsc.c
@@ -359,9 +359,12 @@ static int titsc_parse_dt(struct platform_device *pdev,
 	 */
 	err = of_property_read_u32(node, "ti,coordinate-readouts",
 			&ts_dev->coordinate_readouts);
-	if (err < 0)
+	if (err < 0) {
+		dev_warn(&pdev->dev, "please use 'ti,coordinate-readouts' instead\n");
 		err = of_property_read_u32(node, "ti,coordiante-readouts",
 				&ts_dev->coordinate_readouts);
+	}
+
 	if (err < 0)
 		return err;
 
diff --git a/drivers/input/touchscreen/tsc2005.c b/drivers/input/touchscreen/tsc2005.c
index 550adcbbfc2..52380b68ebd 100644
--- a/drivers/input/touchscreen/tsc2005.c
+++ b/drivers/input/touchscreen/tsc2005.c
@@ -25,11 +25,15 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/input.h>
+#include <linux/input/touchscreen.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/pm.h>
+#include <linux/of.h>
+#include <linux/of_gpio.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/tsc2005.h>
+#include <linux/regulator/consumer.h>
 
 /*
  * The touchscreen interface operates as follows:
@@ -100,6 +104,11 @@
 					 TSC2005_CFR2_AVG_7)
 
 #define MAX_12BIT			0xfff
+#define TSC2005_DEF_X_FUZZ		4
+#define TSC2005_DEF_Y_FUZZ		8
+#define TSC2005_DEF_P_FUZZ		2
+#define TSC2005_DEF_RESISTOR		280
+
 #define TSC2005_SPI_MAX_SPEED_HZ	10000000
 #define TSC2005_PENUP_TIME_MS		40
 
@@ -143,6 +152,9 @@ struct tsc2005 {
 
 	bool			pen_down;
 
+	struct regulator	*vio;
+
+	int			reset_gpio;
 	void			(*set_reset)(bool enable);
 };
 
@@ -337,6 +349,14 @@ static void tsc2005_stop_scan(struct tsc2005 *ts)
 	tsc2005_cmd(ts, TSC2005_CMD_STOP);
 }
 
+static void tsc2005_set_reset(struct tsc2005 *ts, bool enable)
+{
+	if (ts->reset_gpio >= 0)
+		gpio_set_value(ts->reset_gpio, enable);
+	else if (ts->set_reset)
+		ts->set_reset(enable);
+}
+
 /* must be called with ts->mutex held */
 static void __tsc2005_disable(struct tsc2005 *ts)
 {
@@ -355,7 +375,7 @@ static void __tsc2005_enable(struct tsc2005 *ts)
 {
 	tsc2005_start_scan(ts);
 
-	if (ts->esd_timeout && ts->set_reset) {
+	if (ts->esd_timeout && (ts->set_reset || ts->reset_gpio)) {
 		ts->last_valid_interrupt = jiffies;
 		schedule_delayed_work(&ts->esd_work,
 				round_jiffies_relative(
@@ -414,9 +434,9 @@ static ssize_t tsc2005_selftest_show(struct device *dev,
 	}
 
 	/* hardware reset */
-	ts->set_reset(false);
+	tsc2005_set_reset(ts, false);
 	usleep_range(100, 500); /* only 10us required */
-	ts->set_reset(true);
+	tsc2005_set_reset(ts, true);
 
 	if (!success)
 		goto out;
@@ -459,7 +479,7 @@ static umode_t tsc2005_attr_is_visible(struct kobject *kobj,
 	umode_t mode = attr->mode;
 
 	if (attr == &dev_attr_selftest.attr) {
-		if (!ts->set_reset)
+		if (!ts->set_reset && !ts->reset_gpio)
 			mode = 0;
 	}
 
@@ -509,9 +529,9 @@ static void tsc2005_esd_work(struct work_struct *work)
 
 	tsc2005_update_pen_state(ts, 0, 0, 0);
 
-	ts->set_reset(false);
+	tsc2005_set_reset(ts, false);
 	usleep_range(100, 500); /* only 10us required */
-	ts->set_reset(true);
+	tsc2005_set_reset(ts, true);
 
 	enable_irq(ts->spi->irq);
 	tsc2005_start_scan(ts);
@@ -572,29 +592,47 @@ static void tsc2005_setup_spi_xfer(struct tsc2005 *ts)
 static int tsc2005_probe(struct spi_device *spi)
 {
 	const struct tsc2005_platform_data *pdata = dev_get_platdata(&spi->dev);
+	struct device_node *np = spi->dev.of_node;
+
 	struct tsc2005 *ts;
 	struct input_dev *input_dev;
-	unsigned int max_x, max_y, max_p;
-	unsigned int fudge_x, fudge_y, fudge_p;
+	unsigned int max_x = MAX_12BIT;
+	unsigned int max_y = MAX_12BIT;
+	unsigned int max_p = MAX_12BIT;
+	unsigned int fudge_x = TSC2005_DEF_X_FUZZ;
+	unsigned int fudge_y = TSC2005_DEF_Y_FUZZ;
+	unsigned int fudge_p = TSC2005_DEF_P_FUZZ;
+	unsigned int x_plate_ohm = TSC2005_DEF_RESISTOR;
+	unsigned int esd_timeout;
 	int error;
 
-	if (!pdata) {
-		dev_dbg(&spi->dev, "no platform data\n");
+	if (!np && !pdata) {
+		dev_err(&spi->dev, "no platform data\n");
 		return -ENODEV;
 	}
 
-	fudge_x	= pdata->ts_x_fudge	   ? : 4;
-	fudge_y	= pdata->ts_y_fudge	   ? : 8;
-	fudge_p	= pdata->ts_pressure_fudge ? : 2;
-	max_x	= pdata->ts_x_max	   ? : MAX_12BIT;
-	max_y	= pdata->ts_y_max	   ? : MAX_12BIT;
-	max_p	= pdata->ts_pressure_max   ? : MAX_12BIT;
-
 	if (spi->irq <= 0) {
-		dev_dbg(&spi->dev, "no irq\n");
+		dev_err(&spi->dev, "no irq\n");
 		return -ENODEV;
 	}
 
+	if (pdata) {
+		fudge_x	= pdata->ts_x_fudge;
+		fudge_y	= pdata->ts_y_fudge;
+		fudge_p	= pdata->ts_pressure_fudge;
+		max_x	= pdata->ts_x_max;
+		max_y	= pdata->ts_y_max;
+		max_p	= pdata->ts_pressure_max;
+		x_plate_ohm = pdata->ts_x_plate_ohm;
+		esd_timeout = pdata->esd_timeout_ms;
+	} else {
+		x_plate_ohm = TSC2005_DEF_RESISTOR;
+		of_property_read_u32(np, "ti,x-plate-ohms", &x_plate_ohm);
+		esd_timeout = 0;
+		of_property_read_u32(np, "ti,esd-recovery-timeout-ms",
+								&esd_timeout);
+	}
+
 	spi->mode = SPI_MODE_0;
 	spi->bits_per_word = 8;
 	if (!spi->max_speed_hz)
@@ -604,19 +642,48 @@ static int tsc2005_probe(struct spi_device *spi)
 	if (error)
 		return error;
 
-	ts = kzalloc(sizeof(*ts), GFP_KERNEL);
-	input_dev = input_allocate_device();
-	if (!ts || !input_dev) {
-		error = -ENOMEM;
-		goto err_free_mem;
-	}
+	ts = devm_kzalloc(&spi->dev, sizeof(*ts), GFP_KERNEL);
+	if (!ts)
+		return -ENOMEM;
+
+	input_dev = devm_input_allocate_device(&spi->dev);
+	if (!input_dev)
+		return -ENOMEM;
 
 	ts->spi = spi;
 	ts->idev = input_dev;
 
-	ts->x_plate_ohm	= pdata->ts_x_plate_ohm	? : 280;
-	ts->esd_timeout	= pdata->esd_timeout_ms;
-	ts->set_reset	= pdata->set_reset;
+	ts->x_plate_ohm = x_plate_ohm;
+	ts->esd_timeout = esd_timeout;
+
+	if (np) {
+		ts->reset_gpio = of_get_named_gpio(np, "reset-gpios", 0);
+		if (ts->reset_gpio == -EPROBE_DEFER)
+			return ts->reset_gpio;
+		if (ts->reset_gpio < 0) {
+			dev_err(&spi->dev, "error acquiring reset gpio: %d\n",
+				ts->reset_gpio);
+			return ts->reset_gpio;
+		}
+
+		error = devm_gpio_request_one(&spi->dev, ts->reset_gpio, 0,
+					      "reset-gpios");
+		if (error) {
+			dev_err(&spi->dev, "error requesting reset gpio: %d\n",
+				error);
+			return error;
+		}
+
+		ts->vio = devm_regulator_get(&spi->dev, "vio");
+		if (IS_ERR(ts->vio)) {
+			error = PTR_ERR(ts->vio);
+			dev_err(&spi->dev, "vio regulator missing (%d)", error);
+			return error;
+		}
+	} else {
+		ts->reset_gpio = -1;
+		ts->set_reset = pdata->set_reset;
+	}
 
 	mutex_init(&ts->mutex);
 
@@ -641,6 +708,9 @@ static int tsc2005_probe(struct spi_device *spi)
 	input_set_abs_params(input_dev, ABS_Y, 0, max_y, fudge_y, 0);
 	input_set_abs_params(input_dev, ABS_PRESSURE, 0, max_p, fudge_p, 0);
 
+	if (np)
+		touchscreen_parse_of_params(input_dev);
+
 	input_dev->open = tsc2005_open;
 	input_dev->close = tsc2005_close;
 
@@ -649,12 +719,20 @@ static int tsc2005_probe(struct spi_device *spi)
 	/* Ensure the touchscreen is off */
 	tsc2005_stop_scan(ts);
 
-	error = request_threaded_irq(spi->irq, NULL, tsc2005_irq_thread,
-				     IRQF_TRIGGER_RISING | IRQF_ONESHOT,
-				     "tsc2005", ts);
+	error = devm_request_threaded_irq(&spi->dev, spi->irq, NULL,
+					  tsc2005_irq_thread,
+					  IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+					  "tsc2005", ts);
 	if (error) {
 		dev_err(&spi->dev, "Failed to request irq, err: %d\n", error);
-		goto err_free_mem;
+		return error;
+	}
+
+	/* enable regulator for DT */
+	if (ts->vio) {
+		error = regulator_enable(ts->vio);
+		if (error)
+			return error;
 	}
 
 	spi_set_drvdata(spi, ts);
@@ -662,7 +740,7 @@ static int tsc2005_probe(struct spi_device *spi)
 	if (error) {
 		dev_err(&spi->dev,
 			"Failed to create sysfs attributes, err: %d\n", error);
-		goto err_clear_drvdata;
+		goto disable_regulator;
 	}
 
 	error = input_register_device(ts->idev);
@@ -677,11 +755,9 @@ static int tsc2005_probe(struct spi_device *spi)
 
 err_remove_sysfs:
 	sysfs_remove_group(&spi->dev.kobj, &tsc2005_attr_group);
-err_clear_drvdata:
-	free_irq(spi->irq, ts);
-err_free_mem:
-	input_free_device(input_dev);
-	kfree(ts);
+disable_regulator:
+	if (ts->vio)
+		regulator_disable(ts->vio);
 	return error;
 }
 
@@ -689,11 +765,10 @@ static int tsc2005_remove(struct spi_device *spi)
 {
 	struct tsc2005 *ts = spi_get_drvdata(spi);
 
-	sysfs_remove_group(&ts->spi->dev.kobj, &tsc2005_attr_group);
+	sysfs_remove_group(&spi->dev.kobj, &tsc2005_attr_group);
 
-	free_irq(ts->spi->irq, ts);
-	input_unregister_device(ts->idev);
-	kfree(ts);
+	if (ts->vio)
+		regulator_disable(ts->vio);
 
 	return 0;
 }
diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 01d30cedde4..feea85b52fa 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -880,7 +880,7 @@ static struct i2c_device_id zforce_idtable[] = {
 MODULE_DEVICE_TABLE(i2c, zforce_idtable);
 
 #ifdef CONFIG_OF
-static struct of_device_id zforce_dt_idtable[] = {
+static const struct of_device_id zforce_dt_idtable[] = {
 	{ .compatible = "neonode,zforce" },
 	{},
 };
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index d4daa05efe6..499b4366a98 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -45,7 +45,7 @@ struct pri_queue {
 struct pasid_state {
 	struct list_head list;			/* For global state-list */
 	atomic_t count;				/* Reference count */
-	atomic_t mmu_notifier_count;		/* Counting nested mmu_notifier
+	unsigned mmu_notifier_count;		/* Counting nested mmu_notifier
 						   calls */
 	struct task_struct *task;		/* Task bound to this PASID */
 	struct mm_struct *mm;			/* mm_struct for the faults */
@@ -53,7 +53,8 @@ struct pasid_state {
 	struct pri_queue pri[PRI_QUEUE_SIZE];	/* PRI tag states */
 	struct device_state *device_state;	/* Link to our device_state */
 	int pasid;				/* PASID index */
-	spinlock_t lock;			/* Protect pri_queues */
+	spinlock_t lock;			/* Protect pri_queues and
+						   mmu_notifer_count */
 	wait_queue_head_t wq;			/* To wait for count == 0 */
 };
 
@@ -431,15 +432,19 @@ static void mn_invalidate_range_start(struct mmu_notifier *mn,
 {
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
+	unsigned long flags;
 
 	pasid_state = mn_to_state(mn);
 	dev_state   = pasid_state->device_state;
 
-	if (atomic_add_return(1, &pasid_state->mmu_notifier_count) == 1) {
+	spin_lock_irqsave(&pasid_state->lock, flags);
+	if (pasid_state->mmu_notifier_count == 0) {
 		amd_iommu_domain_set_gcr3(dev_state->domain,
 					  pasid_state->pasid,
 					  __pa(empty_page_table));
 	}
+	pasid_state->mmu_notifier_count += 1;
+	spin_unlock_irqrestore(&pasid_state->lock, flags);
 }
 
 static void mn_invalidate_range_end(struct mmu_notifier *mn,
@@ -448,15 +453,19 @@ static void mn_invalidate_range_end(struct mmu_notifier *mn,
 {
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
+	unsigned long flags;
 
 	pasid_state = mn_to_state(mn);
 	dev_state   = pasid_state->device_state;
 
-	if (atomic_dec_and_test(&pasid_state->mmu_notifier_count)) {
+	spin_lock_irqsave(&pasid_state->lock, flags);
+	pasid_state->mmu_notifier_count -= 1;
+	if (pasid_state->mmu_notifier_count == 0) {
 		amd_iommu_domain_set_gcr3(dev_state->domain,
 					  pasid_state->pasid,
 					  __pa(pasid_state->mm->pgd));
 	}
+	spin_unlock_irqrestore(&pasid_state->lock, flags);
 }
 
 static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -650,7 +659,6 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
 		goto out;
 
 	atomic_set(&pasid_state->count, 1);
-	atomic_set(&pasid_state->mmu_notifier_count, 0);
 	init_waitqueue_head(&pasid_state->wq);
 	spin_lock_init(&pasid_state->lock);
 
diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
index b99dd88e31b..bb446d742a2 100644
--- a/drivers/iommu/fsl_pamu.c
+++ b/drivers/iommu/fsl_pamu.c
@@ -170,10 +170,10 @@ int pamu_disable_liodn(int liodn)
 static unsigned int map_addrspace_size_to_wse(phys_addr_t addrspace_size)
 {
 	/* Bug if not a power of 2 */
-	BUG_ON(!is_power_of_2(addrspace_size));
+	BUG_ON((addrspace_size & (addrspace_size - 1)));
 
 	/* window size is 2^(WSE+1) bytes */
-	return __ffs(addrspace_size) - 1;
+	return fls64(addrspace_size) - 2;
 }
 
 /* Derive the PAACE window count encoding for the subwindow count */
@@ -351,7 +351,7 @@ int pamu_config_ppaace(int liodn, phys_addr_t win_addr, phys_addr_t win_size,
 	struct paace *ppaace;
 	unsigned long fspi;
 
-	if (!is_power_of_2(win_size) || win_size < PAMU_PAGE_SIZE) {
+	if ((win_size & (win_size - 1)) || win_size < PAMU_PAGE_SIZE) {
 		pr_debug("window size too small or not a power of two %llx\n", win_size);
 		return -EINVAL;
 	}
@@ -464,7 +464,7 @@ int pamu_config_spaace(int liodn, u32 subwin_cnt, u32 subwin,
 		return -ENOENT;
 	}
 
-	if (!is_power_of_2(subwin_size) || subwin_size < PAMU_PAGE_SIZE) {
+	if ((subwin_size & (subwin_size - 1)) || subwin_size < PAMU_PAGE_SIZE) {
 		pr_debug("subwindow size out of range, or not a power of 2\n");
 		return -EINVAL;
 	}
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index 93072ba44b1..af47648301a 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -301,7 +301,7 @@ static int check_size(u64 size, dma_addr_t iova)
 	 * Size must be a power of two and at least be equal
 	 * to PAMU page size.
 	 */
-	if (!is_power_of_2(size) || size < PAMU_PAGE_SIZE) {
+	if ((size & (size - 1)) || size < PAMU_PAGE_SIZE) {
 		pr_debug("%s: size too small or not a power of two\n", __func__);
 		return -EINVAL;
 	}
@@ -335,11 +335,6 @@ static struct fsl_dma_domain *iommu_alloc_dma_domain(void)
 	return domain;
 }
 
-static inline struct device_domain_info *find_domain(struct device *dev)
-{
-	return dev->archdata.iommu_domain;
-}
-
 static void remove_device_ref(struct device_domain_info *info, u32 win_cnt)
 {
 	unsigned long flags;
@@ -380,7 +375,7 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d
 	 * Check here if the device is already attached to domain or not.
 	 * If the device is already attached to a domain detach it.
 	 */
-	old_domain_info = find_domain(dev);
+	old_domain_info = dev->archdata.iommu_domain;
 	if (old_domain_info && old_domain_info->domain != dma_domain) {
 		spin_unlock_irqrestore(&device_domain_lock, flags);
 		detach_device(dev, old_domain_info->domain);
@@ -399,7 +394,7 @@ static void attach_device(struct fsl_dma_domain *dma_domain, int liodn, struct d
 	 * the info for the first LIODN as all
 	 * LIODNs share the same domain
 	 */
-	if (!old_domain_info)
+	if (!dev->archdata.iommu_domain)
 		dev->archdata.iommu_domain = info;
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 
@@ -1042,12 +1037,15 @@ root_bus:
 			group = get_shared_pci_device_group(pdev);
 	}
 
+	if (!group)
+		group = ERR_PTR(-ENODEV);
+
 	return group;
 }
 
 static int fsl_pamu_add_device(struct device *dev)
 {
-	struct iommu_group *group = NULL;
+	struct iommu_group *group = ERR_PTR(-ENODEV);
 	struct pci_dev *pdev;
 	const u32 *prop;
 	int ret, len;
@@ -1070,7 +1068,7 @@ static int fsl_pamu_add_device(struct device *dev)
 			group = get_device_iommu_group(dev);
 	}
 
-	if (!group || IS_ERR(group))
+	if (IS_ERR(group))
 		return PTR_ERR(group);
 
 	ret = iommu_group_add_device(group, dev);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 6bb32773c3a..51b6b77dc3e 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3816,14 +3816,11 @@ int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 				((void *)rmrr) + rmrr->header.length,
 				rmrr->segment, rmrru->devices,
 				rmrru->devices_cnt);
-			if (ret > 0)
-				break;
-			else if(ret < 0)
+			if(ret < 0)
 				return ret;
 		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
-			if (dmar_remove_dev_scope(info, rmrr->segment,
-				rmrru->devices, rmrru->devices_cnt))
-				break;
+			dmar_remove_dev_scope(info, rmrr->segment,
+				rmrru->devices, rmrru->devices_cnt);
 		}
 	}
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index bbb746e3550..7f0c2a30267 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -10,6 +10,11 @@ config ARM_GIC
 config GIC_NON_BANKED
 	bool
 
+config ARM_GIC_V3
+	bool
+	select IRQ_DOMAIN
+	select MULTI_IRQ_HANDLER
+
 config ARM_NVIC
 	bool
 	select IRQ_DOMAIN
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 62a13e5ef98..c57e642700d 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -15,7 +15,8 @@ obj-$(CONFIG_ORION_IRQCHIP)		+= irq-orion.o
 obj-$(CONFIG_ARCH_SUNXI)		+= irq-sun4i.o
 obj-$(CONFIG_ARCH_SUNXI)		+= irq-sunxi-nmi.o
 obj-$(CONFIG_ARCH_SPEAR3XX)		+= spear-shirq.o
-obj-$(CONFIG_ARM_GIC)			+= irq-gic.o
+obj-$(CONFIG_ARM_GIC)			+= irq-gic.o irq-gic-common.o
+obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-common.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
 obj-$(CONFIG_IMGPDC_IRQ)		+= irq-imgpdc.o
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index c887e6eebc4..574aba0eba4 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -334,6 +334,15 @@ static void armada_mpic_send_doorbell(const struct cpumask *mask,
 
 static void armada_xp_mpic_smp_cpu_init(void)
 {
+	u32 control;
+	int nr_irqs, i;
+
+	control = readl(main_int_base + ARMADA_370_XP_INT_CONTROL);
+	nr_irqs = (control >> 2) & 0x3ff;
+
+	for (i = 0; i < nr_irqs; i++)
+		writel(i, per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS);
+
 	/* Clear pending IPIs */
 	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
 
@@ -474,7 +483,7 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 					     struct device_node *parent)
 {
 	struct resource main_int_res, per_cpu_int_res;
-	int parent_irq;
+	int parent_irq, nr_irqs, i;
 	u32 control;
 
 	BUG_ON(of_address_to_resource(node, 0, &main_int_res));
@@ -496,9 +505,13 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 	BUG_ON(!per_cpu_int_base);
 
 	control = readl(main_int_base + ARMADA_370_XP_INT_CONTROL);
+	nr_irqs = (control >> 2) & 0x3ff;
+
+	for (i = 0; i < nr_irqs; i++)
+		writel(i, main_int_base + ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS);
 
 	armada_370_xp_mpic_domain =
-		irq_domain_add_linear(node, (control >> 2) & 0x3ff,
+		irq_domain_add_linear(node, nr_irqs,
 				&armada_370_xp_mpic_irq_ops, NULL);
 
 	BUG_ON(!armada_370_xp_mpic_domain);
diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c
index 8ee2a36d584..c15c840987d 100644
--- a/drivers/irqchip/irq-brcmstb-l2.c
+++ b/drivers/irqchip/irq-brcmstb-l2.c
@@ -150,7 +150,7 @@ int __init brcmstb_l2_intc_of_init(struct device_node *np,
 
 	/* Allocate a single Generic IRQ chip for this node */
 	ret = irq_alloc_domain_generic_chips(data->domain, 32, 1,
-				np->full_name, handle_level_irq, clr, 0, 0);
+				np->full_name, handle_edge_irq, clr, 0, 0);
 	if (ret) {
 		pr_err("failed to allocate generic irq chip\n");
 		goto out_free_domain;
diff --git a/drivers/irqchip/irq-gic-common.c b/drivers/irqchip/irq-gic-common.c
new file mode 100644
index 00000000000..60ac704d209
--- /dev/null
+++ b/drivers/irqchip/irq-gic-common.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip/arm-gic.h>
+
+#include "irq-gic-common.h"
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+		       void __iomem *base, void (*sync_access)(void))
+{
+	u32 enablemask = 1 << (irq % 32);
+	u32 enableoff = (irq / 32) * 4;
+	u32 confmask = 0x2 << ((irq % 16) * 2);
+	u32 confoff = (irq / 16) * 4;
+	bool enabled = false;
+	u32 val;
+
+	/*
+	 * Read current configuration register, and insert the config
+	 * for "irq", depending on "type".
+	 */
+	val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
+	if (type == IRQ_TYPE_LEVEL_HIGH)
+		val &= ~confmask;
+	else if (type == IRQ_TYPE_EDGE_RISING)
+		val |= confmask;
+
+	/*
+	 * As recommended by the spec, disable the interrupt before changing
+	 * the configuration
+	 */
+	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
+		if (sync_access)
+			sync_access();
+		enabled = true;
+	}
+
+	/*
+	 * Write back the new configuration, and possibly re-enable
+	 * the interrupt.
+	 */
+	writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
+
+	if (enabled)
+		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+
+	if (sync_access)
+		sync_access();
+}
+
+void __init gic_dist_config(void __iomem *base, int gic_irqs,
+			    void (*sync_access)(void))
+{
+	unsigned int i;
+
+	/*
+	 * Set all global interrupts to be level triggered, active low.
+	 */
+	for (i = 32; i < gic_irqs; i += 16)
+		writel_relaxed(0, base + GIC_DIST_CONFIG + i / 4);
+
+	/*
+	 * Set priority on all global interrupts.
+	 */
+	for (i = 32; i < gic_irqs; i += 4)
+		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i);
+
+	/*
+	 * Disable all interrupts.  Leave the PPI and SGIs alone
+	 * as they are enabled by redistributor registers.
+	 */
+	for (i = 32; i < gic_irqs; i += 32)
+		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i / 8);
+
+	if (sync_access)
+		sync_access();
+}
+
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void))
+{
+	int i;
+
+	/*
+	 * Deal with the banked PPI and SGI interrupts - disable all
+	 * PPI interrupts, ensure all SGI interrupts are enabled.
+	 */
+	writel_relaxed(0xffff0000, base + GIC_DIST_ENABLE_CLEAR);
+	writel_relaxed(0x0000ffff, base + GIC_DIST_ENABLE_SET);
+
+	/*
+	 * Set priority on PPI and SGI interrupts
+	 */
+	for (i = 0; i < 32; i += 4)
+		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
+
+	if (sync_access)
+		sync_access();
+}
diff --git a/drivers/irqchip/irq-gic-common.h b/drivers/irqchip/irq-gic-common.h
new file mode 100644
index 00000000000..b41f02481c3
--- /dev/null
+++ b/drivers/irqchip/irq-gic-common.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2002 ARM Limited, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _IRQ_GIC_COMMON_H
+#define _IRQ_GIC_COMMON_H
+
+#include <linux/of.h>
+#include <linux/irqdomain.h>
+
+void gic_configure_irq(unsigned int irq, unsigned int type,
+                       void __iomem *base, void (*sync_access)(void));
+void gic_dist_config(void __iomem *base, int gic_irqs,
+		     void (*sync_access)(void));
+void gic_cpu_config(void __iomem *base, void (*sync_access)(void));
+
+#endif /* _IRQ_GIC_COMMON_H */
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
new file mode 100644
index 00000000000..57eaa5a0b1e
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -0,0 +1,692 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/cpu.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/cputype.h>
+#include <asm/exception.h>
+#include <asm/smp_plat.h>
+
+#include "irq-gic-common.h"
+#include "irqchip.h"
+
+struct gic_chip_data {
+	void __iomem		*dist_base;
+	void __iomem		**redist_base;
+	void __percpu __iomem	**rdist;
+	struct irq_domain	*domain;
+	u64			redist_stride;
+	u32			redist_regions;
+	unsigned int		irq_nr;
+};
+
+static struct gic_chip_data gic_data __read_mostly;
+
+#define gic_data_rdist()		(this_cpu_ptr(gic_data.rdist))
+#define gic_data_rdist_rd_base()	(*gic_data_rdist())
+#define gic_data_rdist_sgi_base()	(gic_data_rdist_rd_base() + SZ_64K)
+
+/* Our default, arbitrary priority value. Linux only uses one anyway. */
+#define DEFAULT_PMR_VALUE	0xf0
+
+static inline unsigned int gic_irq(struct irq_data *d)
+{
+	return d->hwirq;
+}
+
+static inline int gic_irq_in_rdist(struct irq_data *d)
+{
+	return gic_irq(d) < 32;
+}
+
+static inline void __iomem *gic_dist_base(struct irq_data *d)
+{
+	if (gic_irq_in_rdist(d))	/* SGI+PPI -> SGI_base for this CPU */
+		return gic_data_rdist_sgi_base();
+
+	if (d->hwirq <= 1023)		/* SPI -> dist_base */
+		return gic_data.dist_base;
+
+	if (d->hwirq >= 8192)
+		BUG();		/* LPI Detected!!! */
+
+	return NULL;
+}
+
+static void gic_do_wait_for_rwp(void __iomem *base)
+{
+	u32 count = 1000000;	/* 1s! */
+
+	while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("RWP timeout, gone fishing\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	};
+}
+
+/* Wait for completion of a distributor change */
+static void gic_dist_wait_for_rwp(void)
+{
+	gic_do_wait_for_rwp(gic_data.dist_base);
+}
+
+/* Wait for completion of a redistributor change */
+static void gic_redist_wait_for_rwp(void)
+{
+	gic_do_wait_for_rwp(gic_data_rdist_rd_base());
+}
+
+/* Low level accessors */
+static u64 gic_read_iar(void)
+{
+	u64 irqstat;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat));
+	return irqstat;
+}
+
+static void gic_write_pmr(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_write_ctlr(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_CTLR_EL1) ", %0" : : "r" (val));
+	isb();
+}
+
+static void gic_write_grpen1(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_GRPEN1_EL1) ", %0" : : "r" (val));
+	isb();
+}
+
+static void gic_write_sgi1r(u64 val)
+{
+	asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val));
+}
+
+static void gic_enable_sre(void)
+{
+	u64 val;
+
+	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+	val |= ICC_SRE_EL1_SRE;
+	asm volatile("msr_s " __stringify(ICC_SRE_EL1) ", %0" : : "r" (val));
+	isb();
+
+	/*
+	 * Need to check that the SRE bit has actually been set. If
+	 * not, it means that SRE is disabled at EL2. We're going to
+	 * die painfully, and there is nothing we can do about it.
+	 *
+	 * Kindly inform the luser.
+	 */
+	asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val));
+	if (!(val & ICC_SRE_EL1_SRE))
+		pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n");
+}
+
+static void gic_enable_redist(void)
+{
+	void __iomem *rbase;
+	u32 count = 1000000;	/* 1s! */
+	u32 val;
+
+	rbase = gic_data_rdist_rd_base();
+
+	/* Wake up this CPU redistributor */
+	val = readl_relaxed(rbase + GICR_WAKER);
+	val &= ~GICR_WAKER_ProcessorSleep;
+	writel_relaxed(val, rbase + GICR_WAKER);
+
+	while (readl_relaxed(rbase + GICR_WAKER) & GICR_WAKER_ChildrenAsleep) {
+		count--;
+		if (!count) {
+			pr_err_ratelimited("redist didn't wake up...\n");
+			return;
+		}
+		cpu_relax();
+		udelay(1);
+	};
+}
+
+/*
+ * Routines to disable, enable, EOI and route interrupts
+ */
+static void gic_poke_irq(struct irq_data *d, u32 offset)
+{
+	u32 mask = 1 << (gic_irq(d) % 32);
+	void (*rwp_wait)(void);
+	void __iomem *base;
+
+	if (gic_irq_in_rdist(d)) {
+		base = gic_data_rdist_sgi_base();
+		rwp_wait = gic_redist_wait_for_rwp;
+	} else {
+		base = gic_data.dist_base;
+		rwp_wait = gic_dist_wait_for_rwp;
+	}
+
+	writel_relaxed(mask, base + offset + (gic_irq(d) / 32) * 4);
+	rwp_wait();
+}
+
+static int gic_peek_irq(struct irq_data *d, u32 offset)
+{
+	u32 mask = 1 << (gic_irq(d) % 32);
+	void __iomem *base;
+
+	if (gic_irq_in_rdist(d))
+		base = gic_data_rdist_sgi_base();
+	else
+		base = gic_data.dist_base;
+
+	return !!(readl_relaxed(base + offset + (gic_irq(d) / 32) * 4) & mask);
+}
+
+static void gic_mask_irq(struct irq_data *d)
+{
+	gic_poke_irq(d, GICD_ICENABLER);
+}
+
+static void gic_unmask_irq(struct irq_data *d)
+{
+	gic_poke_irq(d, GICD_ISENABLER);
+}
+
+static void gic_eoi_irq(struct irq_data *d)
+{
+	gic_write_eoir(gic_irq(d));
+}
+
+static int gic_set_type(struct irq_data *d, unsigned int type)
+{
+	unsigned int irq = gic_irq(d);
+	void (*rwp_wait)(void);
+	void __iomem *base;
+
+	/* Interrupt configuration for SGIs can't be changed */
+	if (irq < 16)
+		return -EINVAL;
+
+	if (type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING)
+		return -EINVAL;
+
+	if (gic_irq_in_rdist(d)) {
+		base = gic_data_rdist_sgi_base();
+		rwp_wait = gic_redist_wait_for_rwp;
+	} else {
+		base = gic_data.dist_base;
+		rwp_wait = gic_dist_wait_for_rwp;
+	}
+
+	gic_configure_irq(irq, type, base, rwp_wait);
+
+	return 0;
+}
+
+static u64 gic_mpidr_to_affinity(u64 mpidr)
+{
+	u64 aff;
+
+	aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8  |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+	return aff;
+}
+
+static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
+{
+	u64 irqnr;
+
+	do {
+		irqnr = gic_read_iar();
+
+		if (likely(irqnr > 15 && irqnr < 1020)) {
+			u64 irq = irq_find_mapping(gic_data.domain, irqnr);
+			if (likely(irq)) {
+				handle_IRQ(irq, regs);
+				continue;
+			}
+
+			WARN_ONCE(true, "Unexpected SPI received!\n");
+			gic_write_eoir(irqnr);
+		}
+		if (irqnr < 16) {
+			gic_write_eoir(irqnr);
+#ifdef CONFIG_SMP
+			handle_IPI(irqnr, regs);
+#else
+			WARN_ONCE(true, "Unexpected SGI received!\n");
+#endif
+			continue;
+		}
+	} while (irqnr != ICC_IAR1_EL1_SPURIOUS);
+}
+
+static void __init gic_dist_init(void)
+{
+	unsigned int i;
+	u64 affinity;
+	void __iomem *base = gic_data.dist_base;
+
+	/* Disable the distributor */
+	writel_relaxed(0, base + GICD_CTLR);
+	gic_dist_wait_for_rwp();
+
+	gic_dist_config(base, gic_data.irq_nr, gic_dist_wait_for_rwp);
+
+	/* Enable distributor with ARE, Group1 */
+	writel_relaxed(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1,
+		       base + GICD_CTLR);
+
+	/*
+	 * Set all global interrupts to the boot CPU only. ARE must be
+	 * enabled.
+	 */
+	affinity = gic_mpidr_to_affinity(cpu_logical_map(smp_processor_id()));
+	for (i = 32; i < gic_data.irq_nr; i++)
+		writeq_relaxed(affinity, base + GICD_IROUTER + i * 8);
+}
+
+static int gic_populate_rdist(void)
+{
+	u64 mpidr = cpu_logical_map(smp_processor_id());
+	u64 typer;
+	u32 aff;
+	int i;
+
+	/*
+	 * Convert affinity to a 32bit value that can be matched to
+	 * GICR_TYPER bits [63:32].
+	 */
+	aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 |
+	       MPIDR_AFFINITY_LEVEL(mpidr, 0));
+
+	for (i = 0; i < gic_data.redist_regions; i++) {
+		void __iomem *ptr = gic_data.redist_base[i];
+		u32 reg;
+
+		reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK;
+		if (reg != GIC_PIDR2_ARCH_GICv3 &&
+		    reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */
+			pr_warn("No redistributor present @%p\n", ptr);
+			break;
+		}
+
+		do {
+			typer = readq_relaxed(ptr + GICR_TYPER);
+			if ((typer >> 32) == aff) {
+				gic_data_rdist_rd_base() = ptr;
+				pr_info("CPU%d: found redistributor %llx @%p\n",
+					smp_processor_id(),
+					(unsigned long long)mpidr, ptr);
+				return 0;
+			}
+
+			if (gic_data.redist_stride) {
+				ptr += gic_data.redist_stride;
+			} else {
+				ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */
+				if (typer & GICR_TYPER_VLPIS)
+					ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */
+			}
+		} while (!(typer & GICR_TYPER_LAST));
+	}
+
+	/* We couldn't even deal with ourselves... */
+	WARN(true, "CPU%d: mpidr %llx has no re-distributor!\n",
+	     smp_processor_id(), (unsigned long long)mpidr);
+	return -ENODEV;
+}
+
+static void gic_cpu_init(void)
+{
+	void __iomem *rbase;
+
+	/* Register ourselves with the rest of the world */
+	if (gic_populate_rdist())
+		return;
+
+	gic_enable_redist();
+
+	rbase = gic_data_rdist_sgi_base();
+
+	gic_cpu_config(rbase, gic_redist_wait_for_rwp);
+
+	/* Enable system registers */
+	gic_enable_sre();
+
+	/* Set priority mask register */
+	gic_write_pmr(DEFAULT_PMR_VALUE);
+
+	/* EOI deactivates interrupt too (mode 0) */
+	gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir);
+
+	/* ... and let's hit the road... */
+	gic_write_grpen1(1);
+}
+
+#ifdef CONFIG_SMP
+static int gic_secondary_init(struct notifier_block *nfb,
+			      unsigned long action, void *hcpu)
+{
+	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
+		gic_cpu_init();
+	return NOTIFY_OK;
+}
+
+/*
+ * Notifier for enabling the GIC CPU interface. Set an arbitrarily high
+ * priority because the GIC needs to be up before the ARM generic timers.
+ */
+static struct notifier_block gic_cpu_notifier = {
+	.notifier_call = gic_secondary_init,
+	.priority = 100,
+};
+
+static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
+				   u64 cluster_id)
+{
+	int cpu = *base_cpu;
+	u64 mpidr = cpu_logical_map(cpu);
+	u16 tlist = 0;
+
+	while (cpu < nr_cpu_ids) {
+		/*
+		 * If we ever get a cluster of more than 16 CPUs, just
+		 * scream and skip that CPU.
+		 */
+		if (WARN_ON((mpidr & 0xff) >= 16))
+			goto out;
+
+		tlist |= 1 << (mpidr & 0xf);
+
+		cpu = cpumask_next(cpu, mask);
+		if (cpu == nr_cpu_ids)
+			goto out;
+
+		mpidr = cpu_logical_map(cpu);
+
+		if (cluster_id != (mpidr & ~0xffUL)) {
+			cpu--;
+			goto out;
+		}
+	}
+out:
+	*base_cpu = cpu;
+	return tlist;
+}
+
+static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
+{
+	u64 val;
+
+	val = (MPIDR_AFFINITY_LEVEL(cluster_id, 3) << 48	|
+	       MPIDR_AFFINITY_LEVEL(cluster_id, 2) << 32	|
+	       irq << 24			    		|
+	       MPIDR_AFFINITY_LEVEL(cluster_id, 1) << 16	|
+	       tlist);
+
+	pr_debug("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val);
+	gic_write_sgi1r(val);
+}
+
+static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+{
+	int cpu;
+
+	if (WARN_ON(irq >= 16))
+		return;
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	smp_wmb();
+
+	for_each_cpu_mask(cpu, *mask) {
+		u64 cluster_id = cpu_logical_map(cpu) & ~0xffUL;
+		u16 tlist;
+
+		tlist = gic_compute_target_list(&cpu, mask, cluster_id);
+		gic_send_sgi(cluster_id, tlist, irq);
+	}
+
+	/* Force the above writes to ICC_SGI1R_EL1 to be executed */
+	isb();
+}
+
+static void gic_smp_init(void)
+{
+	set_smp_cross_call(gic_raise_softirq);
+	register_cpu_notifier(&gic_cpu_notifier);
+}
+
+static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
+			    bool force)
+{
+	unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	void __iomem *reg;
+	int enabled;
+	u64 val;
+
+	if (gic_irq_in_rdist(d))
+		return -EINVAL;
+
+	/* If interrupt was enabled, disable it first */
+	enabled = gic_peek_irq(d, GICD_ISENABLER);
+	if (enabled)
+		gic_mask_irq(d);
+
+	reg = gic_dist_base(d) + GICD_IROUTER + (gic_irq(d) * 8);
+	val = gic_mpidr_to_affinity(cpu_logical_map(cpu));
+
+	writeq_relaxed(val, reg);
+
+	/*
+	 * If the interrupt was enabled, enabled it again. Otherwise,
+	 * just wait for the distributor to have digested our changes.
+	 */
+	if (enabled)
+		gic_unmask_irq(d);
+	else
+		gic_dist_wait_for_rwp();
+
+	return IRQ_SET_MASK_OK;
+}
+#else
+#define gic_set_affinity	NULL
+#define gic_smp_init()		do { } while(0)
+#endif
+
+static struct irq_chip gic_chip = {
+	.name			= "GICv3",
+	.irq_mask		= gic_mask_irq,
+	.irq_unmask		= gic_unmask_irq,
+	.irq_eoi		= gic_eoi_irq,
+	.irq_set_type		= gic_set_type,
+	.irq_set_affinity	= gic_set_affinity,
+};
+
+static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	/* SGIs are private to the core kernel */
+	if (hw < 16)
+		return -EPERM;
+	/* PPIs */
+	if (hw < 32) {
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &gic_chip,
+					 handle_percpu_devid_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+	}
+	/* SPIs */
+	if (hw >= 32 && hw < gic_data.irq_nr) {
+		irq_set_chip_and_handler(irq, &gic_chip,
+					 handle_fasteoi_irq);
+		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	}
+	irq_set_chip_data(irq, d->host_data);
+	return 0;
+}
+
+static int gic_irq_domain_xlate(struct irq_domain *d,
+				struct device_node *controller,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (d->of_node != controller)
+		return -EINVAL;
+	if (intsize < 3)
+		return -EINVAL;
+
+	switch(intspec[0]) {
+	case 0:			/* SPI */
+		*out_hwirq = intspec[1] + 32;
+		break;
+	case 1:			/* PPI */
+		*out_hwirq = intspec[1] + 16;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
+	return 0;
+}
+
+static const struct irq_domain_ops gic_irq_domain_ops = {
+	.map = gic_irq_domain_map,
+	.xlate = gic_irq_domain_xlate,
+};
+
+static int __init gic_of_init(struct device_node *node, struct device_node *parent)
+{
+	void __iomem *dist_base;
+	void __iomem **redist_base;
+	u64 redist_stride;
+	u32 redist_regions;
+	u32 reg;
+	int gic_irqs;
+	int err;
+	int i;
+
+	dist_base = of_iomap(node, 0);
+	if (!dist_base) {
+		pr_err("%s: unable to map gic dist registers\n",
+			node->full_name);
+		return -ENXIO;
+	}
+
+	reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK;
+	if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) {
+		pr_err("%s: no distributor detected, giving up\n",
+			node->full_name);
+		err = -ENODEV;
+		goto out_unmap_dist;
+	}
+
+	if (of_property_read_u32(node, "#redistributor-regions", &redist_regions))
+		redist_regions = 1;
+
+	redist_base = kzalloc(sizeof(*redist_base) * redist_regions, GFP_KERNEL);
+	if (!redist_base) {
+		err = -ENOMEM;
+		goto out_unmap_dist;
+	}
+
+	for (i = 0; i < redist_regions; i++) {
+		redist_base[i] = of_iomap(node, 1 + i);
+		if (!redist_base[i]) {
+			pr_err("%s: couldn't map region %d\n",
+			       node->full_name, i);
+			err = -ENODEV;
+			goto out_unmap_rdist;
+		}
+	}
+
+	if (of_property_read_u64(node, "redistributor-stride", &redist_stride))
+		redist_stride = 0;
+
+	gic_data.dist_base = dist_base;
+	gic_data.redist_base = redist_base;
+	gic_data.redist_regions = redist_regions;
+	gic_data.redist_stride = redist_stride;
+
+	/*
+	 * Find out how many interrupts are supported.
+	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
+	 */
+	gic_irqs = readl_relaxed(gic_data.dist_base + GICD_TYPER) & 0x1f;
+	gic_irqs = (gic_irqs + 1) * 32;
+	if (gic_irqs > 1020)
+		gic_irqs = 1020;
+	gic_data.irq_nr = gic_irqs;
+
+	gic_data.domain = irq_domain_add_tree(node, &gic_irq_domain_ops,
+					      &gic_data);
+	gic_data.rdist = alloc_percpu(typeof(*gic_data.rdist));
+
+	if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdist)) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	set_handle_irq(gic_handle_irq);
+
+	gic_smp_init();
+	gic_dist_init();
+	gic_cpu_init();
+
+	return 0;
+
+out_free:
+	if (gic_data.domain)
+		irq_domain_remove(gic_data.domain);
+	free_percpu(gic_data.rdist);
+out_unmap_rdist:
+	for (i = 0; i < redist_regions; i++)
+		if (redist_base[i])
+			iounmap(redist_base[i]);
+	kfree(redist_base);
+out_unmap_dist:
+	iounmap(dist_base);
+	return err;
+}
+
+IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 7e11c9d6ae8..9c1f883fc5a 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -42,10 +42,12 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/arm-gic.h>
 
+#include <asm/cputype.h>
 #include <asm/irq.h>
 #include <asm/exception.h>
 #include <asm/smp_plat.h>
 
+#include "irq-gic-common.h"
 #include "irqchip.h"
 
 union gic_base {
@@ -188,12 +190,6 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 {
 	void __iomem *base = gic_dist_base(d);
 	unsigned int gicirq = gic_irq(d);
-	u32 enablemask = 1 << (gicirq % 32);
-	u32 enableoff = (gicirq / 32) * 4;
-	u32 confmask = 0x2 << ((gicirq % 16) * 2);
-	u32 confoff = (gicirq / 16) * 4;
-	bool enabled = false;
-	u32 val;
 
 	/* Interrupt configuration for SGIs can't be changed */
 	if (gicirq < 16)
@@ -207,25 +203,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 	if (gic_arch_extn.irq_set_type)
 		gic_arch_extn.irq_set_type(d, type);
 
-	val = readl_relaxed(base + GIC_DIST_CONFIG + confoff);
-	if (type == IRQ_TYPE_LEVEL_HIGH)
-		val &= ~confmask;
-	else if (type == IRQ_TYPE_EDGE_RISING)
-		val |= confmask;
-
-	/*
-	 * As recommended by the spec, disable the interrupt before changing
-	 * the configuration
-	 */
-	if (readl_relaxed(base + GIC_DIST_ENABLE_SET + enableoff) & enablemask) {
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_CLEAR + enableoff);
-		enabled = true;
-	}
-
-	writel_relaxed(val, base + GIC_DIST_CONFIG + confoff);
-
-	if (enabled)
-		writel_relaxed(enablemask, base + GIC_DIST_ENABLE_SET + enableoff);
+	gic_configure_irq(gicirq, type, base, NULL);
 
 	raw_spin_unlock(&irq_controller_lock);
 
@@ -387,12 +365,6 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	writel_relaxed(0, base + GIC_DIST_CTRL);
 
 	/*
-	 * Set all global interrupts to be level triggered, active low.
-	 */
-	for (i = 32; i < gic_irqs; i += 16)
-		writel_relaxed(0, base + GIC_DIST_CONFIG + i * 4 / 16);
-
-	/*
 	 * Set all global interrupts to this CPU only.
 	 */
 	cpumask = gic_get_cpumask(gic);
@@ -401,18 +373,7 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	for (i = 32; i < gic_irqs; i += 4)
 		writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
-	/*
-	 * Set priority on all global interrupts.
-	 */
-	for (i = 32; i < gic_irqs; i += 4)
-		writel_relaxed(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
-
-	/*
-	 * Disable all interrupts.  Leave the PPI and SGIs alone
-	 * as these enables are banked registers.
-	 */
-	for (i = 32; i < gic_irqs; i += 32)
-		writel_relaxed(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
+	gic_dist_config(base, gic_irqs, NULL);
 
 	writel_relaxed(1, base + GIC_DIST_CTRL);
 }
@@ -439,18 +400,7 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 		if (i != cpu)
 			gic_cpu_map[i] &= ~cpu_mask;
 
-	/*
-	 * Deal with the banked PPI and SGI interrupts - disable all
-	 * PPI interrupts, ensure all SGI interrupts are enabled.
-	 */
-	writel_relaxed(0xffff0000, dist_base + GIC_DIST_ENABLE_CLEAR);
-	writel_relaxed(0x0000ffff, dist_base + GIC_DIST_ENABLE_SET);
-
-	/*
-	 * Set priority on PPI and SGI interrupts
-	 */
-	for (i = 0; i < 32; i += 4)
-		writel_relaxed(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4 / 4);
+	gic_cpu_config(dist_base, NULL);
 
 	writel_relaxed(0xf0, base + GIC_CPU_PRIMASK);
 	writel_relaxed(1, base + GIC_CPU_CTRL);
@@ -954,7 +904,9 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 		}
 
 		for_each_possible_cpu(cpu) {
-			unsigned long offset = percpu_offset * cpu_logical_map(cpu);
+			u32 mpidr = cpu_logical_map(cpu);
+			u32 core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+			unsigned long offset = percpu_offset * core_id;
 			*per_cpu_ptr(gic->dist_base.percpu_base, cpu) = dist_base + offset;
 			*per_cpu_ptr(gic->cpu_base.percpu_base, cpu) = cpu_base + offset;
 		}
@@ -1071,8 +1023,10 @@ gic_of_init(struct device_node *node, struct device_node *parent)
 	gic_cnt++;
 	return 0;
 }
+IRQCHIP_DECLARE(gic_400, "arm,gic-400", gic_of_init);
 IRQCHIP_DECLARE(cortex_a15_gic, "arm,cortex-a15-gic", gic_of_init);
 IRQCHIP_DECLARE(cortex_a9_gic, "arm,cortex-a9-gic", gic_of_init);
+IRQCHIP_DECLARE(cortex_a7_gic, "arm,cortex-a7-gic", gic_of_init);
 IRQCHIP_DECLARE(msm_8660_qgic, "qcom,msm-8660-qgic", gic_of_init);
 IRQCHIP_DECLARE(msm_qgic2, "qcom,msm-qgic2", gic_of_init);
 
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
index 3fdda3a4026..6ce6bd3441b 100644
--- a/drivers/irqchip/spear-shirq.c
+++ b/drivers/irqchip/spear-shirq.c
@@ -125,7 +125,7 @@ static struct spear_shirq spear320_shirq_ras2 = {
 };
 
 static struct spear_shirq spear320_shirq_ras3 = {
-	.irq_nr = 3,
+	.irq_nr = 7,
 	.irq_bit_off = 0,
 	.invalid_irq = 1,
 	.regs = {
diff --git a/drivers/isdn/capi/Kconfig b/drivers/isdn/capi/Kconfig
index 9816c51eb5c..7641b3096ea 100644
--- a/drivers/isdn/capi/Kconfig
+++ b/drivers/isdn/capi/Kconfig
@@ -1,11 +1,3 @@
-config ISDN_DRV_AVMB1_VERBOSE_REASON
-	bool "Verbose reason code reporting"
-	default y
-	help
-	  If you say Y here, the CAPI drivers will give verbose reasons for
-	  disconnecting. This will increase the size of the kernel by 7 KB. If
-	  unsure, say Y.
-
 config CAPI_TRACE
 	bool "CAPI trace support"
 	default y
@@ -17,7 +9,7 @@ config CAPI_TRACE
 	  If unsure, say Y.
 
 config ISDN_CAPI_CAPI20
-	tristate "CAPI2.0 /dev/capi support"
+	tristate "CAPI2.0 /dev/capi20 support"
 	help
 	  This option will provide the CAPI 2.0 interface to userspace
 	  applications via /dev/capi20. Applications should use the
@@ -42,3 +34,11 @@ config ISDN_CAPI_CAPIDRV
 	  the legacy isdn4linux link layer.  If you have a card which is
 	  supported by a CAPI driver, but still want to use old features like
 	  ippp interfaces or ttyI emulation, say Y/M here.
+
+config ISDN_CAPI_CAPIDRV_VERBOSE
+	bool "Verbose reason code reporting"
+	depends on ISDN_CAPI_CAPIDRV
+	help
+	  If you say Y here, the capidrv interface will give verbose reasons
+	  for disconnecting. This will increase the size of the kernel by 7 KB.
+	  If unsure, say N.
diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index ac6f72b455d..f9a87ed2392 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -1271,7 +1271,7 @@ static int __init capinc_tty_init(void)
 		return -ENOMEM;
 	}
 	drv->driver_name = "capi_nc";
-	drv->name = "capi";
+	drv->name = "capi!";
 	drv->major = 0;
 	drv->minor_start = 0;
 	drv->type = TTY_DRIVER_TYPE_SERIAL;
@@ -1417,7 +1417,7 @@ static int __init capi_init(void)
 		return PTR_ERR(capi_class);
 	}
 
-	device_create(capi_class, NULL, MKDEV(capi_major, 0), NULL, "capi");
+	device_create(capi_class, NULL, MKDEV(capi_major, 0), NULL, "capi20");
 
 	if (capinc_tty_init() < 0) {
 		device_destroy(capi_class, MKDEV(capi_major, 0));
diff --git a/drivers/isdn/capi/capidrv.c b/drivers/isdn/capi/capidrv.c
index cc9f1927a32..fd6d28f3fc3 100644
--- a/drivers/isdn/capi/capidrv.c
+++ b/drivers/isdn/capi/capidrv.c
@@ -763,6 +763,201 @@ static inline int new_bchan(capidrv_contr *card)
 }
 
 /* ------------------------------------------------------------------- */
+static char *capi_info2str(u16 reason)
+{
+#ifndef CONFIG_ISDN_CAPI_CAPIDRV_VERBOSE
+	return "..";
+#else
+	switch (reason) {
+
+/*-- informative values (corresponding message was processed) -----*/
+	case 0x0001:
+		return "NCPI not supported by current protocol, NCPI ignored";
+	case 0x0002:
+		return "Flags not supported by current protocol, flags ignored";
+	case 0x0003:
+		return "Alert already sent by another application";
+
+/*-- error information concerning CAPI_REGISTER -----*/
+	case 0x1001:
+		return "Too many applications";
+	case 0x1002:
+		return "Logical block size too small, must be at least 128 Bytes";
+	case 0x1003:
+		return "Buffer exceeds 64 kByte";
+	case 0x1004:
+		return "Message buffer size too small, must be at least 1024 Bytes";
+	case 0x1005:
+		return "Max. number of logical connections not supported";
+	case 0x1006:
+		return "Reserved";
+	case 0x1007:
+		return "The message could not be accepted because of an internal busy condition";
+	case 0x1008:
+		return "OS resource error (no memory ?)";
+	case 0x1009:
+		return "CAPI not installed";
+	case 0x100A:
+		return "Controller does not support external equipment";
+	case 0x100B:
+		return "Controller does only support external equipment";
+
+/*-- error information concerning message exchange functions -----*/
+	case 0x1101:
+		return "Illegal application number";
+	case 0x1102:
+		return "Illegal command or subcommand or message length less than 12 bytes";
+	case 0x1103:
+		return "The message could not be accepted because of a queue full condition !! The error code does not imply that CAPI cannot receive messages directed to another controller, PLCI or NCCI";
+	case 0x1104:
+		return "Queue is empty";
+	case 0x1105:
+		return "Queue overflow, a message was lost !! This indicates a configuration error. The only recovery from this error is to perform a CAPI_RELEASE";
+	case 0x1106:
+		return "Unknown notification parameter";
+	case 0x1107:
+		return "The Message could not be accepted because of an internal busy condition";
+	case 0x1108:
+		return "OS Resource error (no memory ?)";
+	case 0x1109:
+		return "CAPI not installed";
+	case 0x110A:
+		return "Controller does not support external equipment";
+	case 0x110B:
+		return "Controller does only support external equipment";
+
+/*-- error information concerning resource / coding problems -----*/
+	case 0x2001:
+		return "Message not supported in current state";
+	case 0x2002:
+		return "Illegal Controller / PLCI / NCCI";
+	case 0x2003:
+		return "Out of PLCI";
+	case 0x2004:
+		return "Out of NCCI";
+	case 0x2005:
+		return "Out of LISTEN";
+	case 0x2006:
+		return "Out of FAX resources (protocol T.30)";
+	case 0x2007:
+		return "Illegal message parameter coding";
+
+/*-- error information concerning requested services  -----*/
+	case 0x3001:
+		return "B1 protocol not supported";
+	case 0x3002:
+		return "B2 protocol not supported";
+	case 0x3003:
+		return "B3 protocol not supported";
+	case 0x3004:
+		return "B1 protocol parameter not supported";
+	case 0x3005:
+		return "B2 protocol parameter not supported";
+	case 0x3006:
+		return "B3 protocol parameter not supported";
+	case 0x3007:
+		return "B protocol combination not supported";
+	case 0x3008:
+		return "NCPI not supported";
+	case 0x3009:
+		return "CIP Value unknown";
+	case 0x300A:
+		return "Flags not supported (reserved bits)";
+	case 0x300B:
+		return "Facility not supported";
+	case 0x300C:
+		return "Data length not supported by current protocol";
+	case 0x300D:
+		return "Reset procedure not supported by current protocol";
+
+/*-- informations about the clearing of a physical connection -----*/
+	case 0x3301:
+		return "Protocol error layer 1 (broken line or B-channel removed by signalling protocol)";
+	case 0x3302:
+		return "Protocol error layer 2";
+	case 0x3303:
+		return "Protocol error layer 3";
+	case 0x3304:
+		return "Another application got that call";
+/*-- T.30 specific reasons -----*/
+	case 0x3311:
+		return "Connecting not successful (remote station is no FAX G3 machine)";
+	case 0x3312:
+		return "Connecting not successful (training error)";
+	case 0x3313:
+		return "Disconnected before transfer (remote station does not support transfer mode, e.g. resolution)";
+	case 0x3314:
+		return "Disconnected during transfer (remote abort)";
+	case 0x3315:
+		return "Disconnected during transfer (remote procedure error, e.g. unsuccessful repetition of T.30 commands)";
+	case 0x3316:
+		return "Disconnected during transfer (local tx data underrun)";
+	case 0x3317:
+		return "Disconnected during transfer (local rx data overflow)";
+	case 0x3318:
+		return "Disconnected during transfer (local abort)";
+	case 0x3319:
+		return "Illegal parameter coding (e.g. SFF coding error)";
+
+/*-- disconnect causes from the network according to ETS 300 102-1/Q.931 -----*/
+	case 0x3481: return "Unallocated (unassigned) number";
+	case 0x3482: return "No route to specified transit network";
+	case 0x3483: return "No route to destination";
+	case 0x3486: return "Channel unacceptable";
+	case 0x3487:
+		return "Call awarded and being delivered in an established channel";
+	case 0x3490: return "Normal call clearing";
+	case 0x3491: return "User busy";
+	case 0x3492: return "No user responding";
+	case 0x3493: return "No answer from user (user alerted)";
+	case 0x3495: return "Call rejected";
+	case 0x3496: return "Number changed";
+	case 0x349A: return "Non-selected user clearing";
+	case 0x349B: return "Destination out of order";
+	case 0x349C: return "Invalid number format";
+	case 0x349D: return "Facility rejected";
+	case 0x349E: return "Response to STATUS ENQUIRY";
+	case 0x349F: return "Normal, unspecified";
+	case 0x34A2: return "No circuit / channel available";
+	case 0x34A6: return "Network out of order";
+	case 0x34A9: return "Temporary failure";
+	case 0x34AA: return "Switching equipment congestion";
+	case 0x34AB: return "Access information discarded";
+	case 0x34AC: return "Requested circuit / channel not available";
+	case 0x34AF: return "Resources unavailable, unspecified";
+	case 0x34B1: return "Quality of service unavailable";
+	case 0x34B2: return "Requested facility not subscribed";
+	case 0x34B9: return "Bearer capability not authorized";
+	case 0x34BA: return "Bearer capability not presently available";
+	case 0x34BF: return "Service or option not available, unspecified";
+	case 0x34C1: return "Bearer capability not implemented";
+	case 0x34C2: return "Channel type not implemented";
+	case 0x34C5: return "Requested facility not implemented";
+	case 0x34C6: return "Only restricted digital information bearer capability is available";
+	case 0x34CF: return "Service or option not implemented, unspecified";
+	case 0x34D1: return "Invalid call reference value";
+	case 0x34D2: return "Identified channel does not exist";
+	case 0x34D3: return "A suspended call exists, but this call identity does not";
+	case 0x34D4: return "Call identity in use";
+	case 0x34D5: return "No call suspended";
+	case 0x34D6: return "Call having the requested call identity has been cleared";
+	case 0x34D8: return "Incompatible destination";
+	case 0x34DB: return "Invalid transit network selection";
+	case 0x34DF: return "Invalid message, unspecified";
+	case 0x34E0: return "Mandatory information element is missing";
+	case 0x34E1: return "Message type non-existent or not implemented";
+	case 0x34E2: return "Message not compatible with call state or message type non-existent or not implemented";
+	case 0x34E3: return "Information element non-existent or not implemented";
+	case 0x34E4: return "Invalid information element contents";
+	case 0x34E5: return "Message not compatible with call state";
+	case 0x34E6: return "Recovery on timer expiry";
+	case 0x34EF: return "Protocol error, unspecified";
+	case 0x34FF: return "Interworking, unspecified";
+
+	default: return "No additional information";
+	}
+#endif
+}
 
 static void handle_controller(_cmsg *cmsg)
 {
diff --git a/drivers/isdn/capi/capiutil.c b/drivers/isdn/capi/capiutil.c
index d26f17033b6..6e797e502cf 100644
--- a/drivers/isdn/capi/capiutil.c
+++ b/drivers/isdn/capi/capiutil.c
@@ -22,205 +22,6 @@
 
 /* from CAPI2.0 DDK AVM Berlin GmbH */
 
-#ifndef CONFIG_ISDN_DRV_AVMB1_VERBOSE_REASON
-char *capi_info2str(u16 reason)
-{
-	return "..";
-}
-#else
-char *capi_info2str(u16 reason)
-{
-	switch (reason) {
-
-/*-- informative values (corresponding message was processed) -----*/
-	case 0x0001:
-		return "NCPI not supported by current protocol, NCPI ignored";
-	case 0x0002:
-		return "Flags not supported by current protocol, flags ignored";
-	case 0x0003:
-		return "Alert already sent by another application";
-
-/*-- error information concerning CAPI_REGISTER -----*/
-	case 0x1001:
-		return "Too many applications";
-	case 0x1002:
-		return "Logical block size too small, must be at least 128 Bytes";
-	case 0x1003:
-		return "Buffer exceeds 64 kByte";
-	case 0x1004:
-		return "Message buffer size too small, must be at least 1024 Bytes";
-	case 0x1005:
-		return "Max. number of logical connections not supported";
-	case 0x1006:
-		return "Reserved";
-	case 0x1007:
-		return "The message could not be accepted because of an internal busy condition";
-	case 0x1008:
-		return "OS resource error (no memory ?)";
-	case 0x1009:
-		return "CAPI not installed";
-	case 0x100A:
-		return "Controller does not support external equipment";
-	case 0x100B:
-		return "Controller does only support external equipment";
-
-/*-- error information concerning message exchange functions -----*/
-	case 0x1101:
-		return "Illegal application number";
-	case 0x1102:
-		return "Illegal command or subcommand or message length less than 12 bytes";
-	case 0x1103:
-		return "The message could not be accepted because of a queue full condition !! The error code does not imply that CAPI cannot receive messages directed to another controller, PLCI or NCCI";
-	case 0x1104:
-		return "Queue is empty";
-	case 0x1105:
-		return "Queue overflow, a message was lost !! This indicates a configuration error. The only recovery from this error is to perform a CAPI_RELEASE";
-	case 0x1106:
-		return "Unknown notification parameter";
-	case 0x1107:
-		return "The Message could not be accepted because of an internal busy condition";
-	case 0x1108:
-		return "OS Resource error (no memory ?)";
-	case 0x1109:
-		return "CAPI not installed";
-	case 0x110A:
-		return "Controller does not support external equipment";
-	case 0x110B:
-		return "Controller does only support external equipment";
-
-/*-- error information concerning resource / coding problems -----*/
-	case 0x2001:
-		return "Message not supported in current state";
-	case 0x2002:
-		return "Illegal Controller / PLCI / NCCI";
-	case 0x2003:
-		return "Out of PLCI";
-	case 0x2004:
-		return "Out of NCCI";
-	case 0x2005:
-		return "Out of LISTEN";
-	case 0x2006:
-		return "Out of FAX resources (protocol T.30)";
-	case 0x2007:
-		return "Illegal message parameter coding";
-
-/*-- error information concerning requested services  -----*/
-	case 0x3001:
-		return "B1 protocol not supported";
-	case 0x3002:
-		return "B2 protocol not supported";
-	case 0x3003:
-		return "B3 protocol not supported";
-	case 0x3004:
-		return "B1 protocol parameter not supported";
-	case 0x3005:
-		return "B2 protocol parameter not supported";
-	case 0x3006:
-		return "B3 protocol parameter not supported";
-	case 0x3007:
-		return "B protocol combination not supported";
-	case 0x3008:
-		return "NCPI not supported";
-	case 0x3009:
-		return "CIP Value unknown";
-	case 0x300A:
-		return "Flags not supported (reserved bits)";
-	case 0x300B:
-		return "Facility not supported";
-	case 0x300C:
-		return "Data length not supported by current protocol";
-	case 0x300D:
-		return "Reset procedure not supported by current protocol";
-
-/*-- informations about the clearing of a physical connection -----*/
-	case 0x3301:
-		return "Protocol error layer 1 (broken line or B-channel removed by signalling protocol)";
-	case 0x3302:
-		return "Protocol error layer 2";
-	case 0x3303:
-		return "Protocol error layer 3";
-	case 0x3304:
-		return "Another application got that call";
-/*-- T.30 specific reasons -----*/
-	case 0x3311:
-		return "Connecting not successful (remote station is no FAX G3 machine)";
-	case 0x3312:
-		return "Connecting not successful (training error)";
-	case 0x3313:
-		return "Disconnected before transfer (remote station does not support transfer mode, e.g. resolution)";
-	case 0x3314:
-		return "Disconnected during transfer (remote abort)";
-	case 0x3315:
-		return "Disconnected during transfer (remote procedure error, e.g. unsuccessful repetition of T.30 commands)";
-	case 0x3316:
-		return "Disconnected during transfer (local tx data underrun)";
-	case 0x3317:
-		return "Disconnected during transfer (local rx data overflow)";
-	case 0x3318:
-		return "Disconnected during transfer (local abort)";
-	case 0x3319:
-		return "Illegal parameter coding (e.g. SFF coding error)";
-
-/*-- disconnect causes from the network according to ETS 300 102-1/Q.931 -----*/
-	case 0x3481: return "Unallocated (unassigned) number";
-	case 0x3482: return "No route to specified transit network";
-	case 0x3483: return "No route to destination";
-	case 0x3486: return "Channel unacceptable";
-	case 0x3487:
-		return "Call awarded and being delivered in an established channel";
-	case 0x3490: return "Normal call clearing";
-	case 0x3491: return "User busy";
-	case 0x3492: return "No user responding";
-	case 0x3493: return "No answer from user (user alerted)";
-	case 0x3495: return "Call rejected";
-	case 0x3496: return "Number changed";
-	case 0x349A: return "Non-selected user clearing";
-	case 0x349B: return "Destination out of order";
-	case 0x349C: return "Invalid number format";
-	case 0x349D: return "Facility rejected";
-	case 0x349E: return "Response to STATUS ENQUIRY";
-	case 0x349F: return "Normal, unspecified";
-	case 0x34A2: return "No circuit / channel available";
-	case 0x34A6: return "Network out of order";
-	case 0x34A9: return "Temporary failure";
-	case 0x34AA: return "Switching equipment congestion";
-	case 0x34AB: return "Access information discarded";
-	case 0x34AC: return "Requested circuit / channel not available";
-	case 0x34AF: return "Resources unavailable, unspecified";
-	case 0x34B1: return "Quality of service unavailable";
-	case 0x34B2: return "Requested facility not subscribed";
-	case 0x34B9: return "Bearer capability not authorized";
-	case 0x34BA: return "Bearer capability not presently available";
-	case 0x34BF: return "Service or option not available, unspecified";
-	case 0x34C1: return "Bearer capability not implemented";
-	case 0x34C2: return "Channel type not implemented";
-	case 0x34C5: return "Requested facility not implemented";
-	case 0x34C6: return "Only restricted digital information bearer capability is available";
-	case 0x34CF: return "Service or option not implemented, unspecified";
-	case 0x34D1: return "Invalid call reference value";
-	case 0x34D2: return "Identified channel does not exist";
-	case 0x34D3: return "A suspended call exists, but this call identity does not";
-	case 0x34D4: return "Call identity in use";
-	case 0x34D5: return "No call suspended";
-	case 0x34D6: return "Call having the requested call identity has been cleared";
-	case 0x34D8: return "Incompatible destination";
-	case 0x34DB: return "Invalid transit network selection";
-	case 0x34DF: return "Invalid message, unspecified";
-	case 0x34E0: return "Mandatory information element is missing";
-	case 0x34E1: return "Message type non-existent or not implemented";
-	case 0x34E2: return "Message not compatible with call state or message type non-existent or not implemented";
-	case 0x34E3: return "Information element non-existent or not implemented";
-	case 0x34E4: return "Invalid information element contents";
-	case 0x34E5: return "Message not compatible with call state";
-	case 0x34E6: return "Recovery on timer expiry";
-	case 0x34EF: return "Protocol error, unspecified";
-	case 0x34FF: return "Interworking, unspecified";
-
-	default: return "No additional information";
-	}
-}
-#endif
-
 typedef struct {
 	int typ;
 	size_t off;
@@ -1073,4 +874,3 @@ EXPORT_SYMBOL(capi_cmsg_header);
 EXPORT_SYMBOL(capi_cmd2str);
 EXPORT_SYMBOL(capi_cmsg2str);
 EXPORT_SYMBOL(capi_message2str);
-EXPORT_SYMBOL(capi_info2str);
diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index c44950d3eb7..b7ae0a0dd5b 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -2400,6 +2400,7 @@ allocerr:
 error:
 	freeurbs(cs);
 	usb_set_intfdata(interface, NULL);
+	usb_put_dev(udev);
 	gigaset_freecs(cs);
 	return rc;
 }
diff --git a/drivers/isdn/hisax/Kconfig b/drivers/isdn/hisax/Kconfig
index d9edcc94c2a..97465ac5a2d 100644
--- a/drivers/isdn/hisax/Kconfig
+++ b/drivers/isdn/hisax/Kconfig
@@ -16,7 +16,7 @@ config ISDN_DRV_HISAX
 	  also to the configuration option of the driver for your particular
 	  card, below.
 
-if ISDN_DRV_HISAX!=n
+if ISDN_DRV_HISAX
 
 comment "D-channel protocol features"
 
@@ -348,10 +348,6 @@ config HISAX_ENTERNOW_PCI
 	  This enables HiSax support for the Formula-n enter:now PCI
 	  ISDN card.
 
-endif
-
-if ISDN_DRV_HISAX
-
 config HISAX_DEBUG
 	bool "HiSax debugging"
 	help
@@ -420,11 +416,6 @@ config HISAX_FRITZ_PCIPNP
 	  (the latter also needs you to select "ISA Plug and Play support"
 	  from the menu "Plug and Play configuration")
 
-config HISAX_AVM_A1_PCMCIA
-	bool
-	depends on HISAX_AVM_A1_CS
-	default y
-
 endif
 
 endmenu
diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c
index 414dbf6da89..fc9f9d03fa1 100644
--- a/drivers/isdn/hisax/hfc4s8s_l1.c
+++ b/drivers/isdn/hisax/hfc4s8s_l1.c
@@ -197,25 +197,6 @@ typedef struct _hfc4s8s_hw {
 
 
 
-/***************************/
-/* inline function defines */
-/***************************/
-#ifdef HISAX_HFC4S8S_PCIMEM	/* inline functions memory mapped */
-
-/* memory write and dummy IO read to avoid PCI byte merge problems */
-#define Write_hfc8(a, b, c) {(*((volatile u_char *)(a->membase + b)) = c); inb(a->iobase + 4);}
-/* memory write without dummy IO access for fifo data access */
-#define fWrite_hfc8(a, b, c) (*((volatile u_char *)(a->membase + b)) = c)
-#define Read_hfc8(a, b) (*((volatile u_char *)(a->membase + b)))
-#define Write_hfc16(a, b, c) (*((volatile unsigned short *)(a->membase + b)) = c)
-#define Read_hfc16(a, b) (*((volatile unsigned short *)(a->membase + b)))
-#define Write_hfc32(a, b, c) (*((volatile unsigned long *)(a->membase + b)) = c)
-#define Read_hfc32(a, b) (*((volatile unsigned long *)(a->membase + b)))
-#define wait_busy(a) {while ((Read_hfc8(a, R_STATUS) & M_BUSY));}
-#define PCI_ENA_MEMIO	0x03
-
-#else
-
 /* inline functions io mapped */
 static inline void
 SetRegAddr(hfc4s8s_hw *a, u_char b)
@@ -306,8 +287,6 @@ wait_busy(hfc4s8s_hw *a)
 
 #define PCI_ENA_REGIO	0x01
 
-#endif				/* HISAX_HFC4S8S_PCIMEM */
-
 /******************************************************/
 /* function to read critical counter registers that   */
 /* may be updated by the chip during read             */
@@ -724,26 +703,15 @@ rx_d_frame(struct hfc4s8s_l1 *l1p, int ech)
 				return;
 			} else {
 				/* read errornous D frame */
-
-#ifndef HISAX_HFC4S8S_PCIMEM
 				SetRegAddr(l1p->hw, A_FIFO_DATA0);
-#endif
 
 				while (z1 >= 4) {
-#ifdef HISAX_HFC4S8S_PCIMEM
-					Read_hfc32(l1p->hw, A_FIFO_DATA0);
-#else
 					fRead_hfc32(l1p->hw);
-#endif
 					z1 -= 4;
 				}
 
 				while (z1--)
-#ifdef HISAX_HFC4S8S_PCIMEM
-					Read_hfc8(l1p->hw, A_FIFO_DATA0);
-#else
-				fRead_hfc8(l1p->hw);
-#endif
+					fRead_hfc8(l1p->hw);
 
 				Write_hfc8(l1p->hw, A_INC_RES_FIFO, 1);
 				wait_busy(l1p->hw);
@@ -753,27 +721,16 @@ rx_d_frame(struct hfc4s8s_l1 *l1p, int ech)
 
 		cp = skb->data;
 
-#ifndef HISAX_HFC4S8S_PCIMEM
 		SetRegAddr(l1p->hw, A_FIFO_DATA0);
-#endif
 
 		while (z1 >= 4) {
-#ifdef HISAX_HFC4S8S_PCIMEM
-			*((unsigned long *) cp) =
-				Read_hfc32(l1p->hw, A_FIFO_DATA0);
-#else
 			*((unsigned long *) cp) = fRead_hfc32(l1p->hw);
-#endif
 			cp += 4;
 			z1 -= 4;
 		}
 
 		while (z1--)
-#ifdef HISAX_HFC4S8S_PCIMEM
-			*cp++ = Read_hfc8(l1p->hw, A_FIFO_DATA0);
-#else
-		*cp++ = fRead_hfc8(l1p->hw);
-#endif
+			*cp++ = fRead_hfc8(l1p->hw);
 
 		Write_hfc8(l1p->hw, A_INC_RES_FIFO, 1);	/* increment f counter */
 		wait_busy(l1p->hw);
@@ -859,28 +816,17 @@ rx_b_frame(struct hfc4s8s_btype *bch)
 			wait_busy(l1->hw);
 			return;
 		}
-#ifndef HISAX_HFC4S8S_PCIMEM
 		SetRegAddr(l1->hw, A_FIFO_DATA0);
-#endif
 
 		while (z1 >= 4) {
-#ifdef HISAX_HFC4S8S_PCIMEM
-			*((unsigned long *) bch->rx_ptr) =
-				Read_hfc32(l1->hw, A_FIFO_DATA0);
-#else
 			*((unsigned long *) bch->rx_ptr) =
 				fRead_hfc32(l1->hw);
-#endif
 			bch->rx_ptr += 4;
 			z1 -= 4;
 		}
 
 		while (z1--)
-#ifdef HISAX_HFC4S8S_PCIMEM
-			*(bch->rx_ptr++) = Read_hfc8(l1->hw, A_FIFO_DATA0);
-#else
-		*(bch->rx_ptr++) = fRead_hfc8(l1->hw);
-#endif
+			*(bch->rx_ptr++) = fRead_hfc8(l1->hw);
 
 		if (hdlc_complete) {
 			/* increment f counter */
@@ -940,29 +886,17 @@ tx_d_frame(struct hfc4s8s_l1 *l1p)
 	if ((skb = skb_dequeue(&l1p->d_tx_queue))) {
 		cp = skb->data;
 		cnt = skb->len;
-#ifndef HISAX_HFC4S8S_PCIMEM
 		SetRegAddr(l1p->hw, A_FIFO_DATA0);
-#endif
 
 		while (cnt >= 4) {
-#ifdef HISAX_HFC4S8S_PCIMEM
-			fWrite_hfc32(l1p->hw, A_FIFO_DATA0,
-				     *(unsigned long *) cp);
-#else
 			SetRegAddr(l1p->hw, A_FIFO_DATA0);
 			fWrite_hfc32(l1p->hw, *(unsigned long *) cp);
-#endif
 			cp += 4;
 			cnt -= 4;
 		}
 
-#ifdef HISAX_HFC4S8S_PCIMEM
-		while (cnt--)
-			fWrite_hfc8(l1p->hw, A_FIFO_DATA0, *cp++);
-#else
 		while (cnt--)
 			fWrite_hfc8(l1p->hw, *cp++);
-#endif
 
 		l1p->tx_cnt = skb->truesize;
 		Write_hfc8(l1p->hw, A_INC_RES_FIFO, 1);	/* increment f counter */
@@ -1037,26 +971,15 @@ tx_b_frame(struct hfc4s8s_btype *bch)
 		cp = skb->data + bch->tx_cnt;
 		bch->tx_cnt += cnt;
 
-#ifndef HISAX_HFC4S8S_PCIMEM
 		SetRegAddr(l1->hw, A_FIFO_DATA0);
-#endif
 		while (cnt >= 4) {
-#ifdef HISAX_HFC4S8S_PCIMEM
-			fWrite_hfc32(l1->hw, A_FIFO_DATA0,
-				     *(unsigned long *) cp);
-#else
 			fWrite_hfc32(l1->hw, *(unsigned long *) cp);
-#endif
 			cp += 4;
 			cnt -= 4;
 		}
 
 		while (cnt--)
-#ifdef HISAX_HFC4S8S_PCIMEM
-			fWrite_hfc8(l1->hw, A_FIFO_DATA0, *cp++);
-#else
-		fWrite_hfc8(l1->hw, *cp++);
-#endif
+			fWrite_hfc8(l1->hw, *cp++);
 
 		if (bch->tx_cnt >= skb->len) {
 			if (bch->mode == L1_MODE_HDLC) {
@@ -1281,10 +1204,8 @@ hfc4s8s_interrupt(int intno, void *dev_id)
 	if (!hw || !(hw->mr.r_irq_ctrl & M_GLOB_IRQ_EN))
 		return IRQ_NONE;
 
-#ifndef	HISAX_HFC4S8S_PCIMEM
 	/* read current selected regsister */
 	old_ioreg = GetRegAddr(hw);
-#endif
 
 	/* Layer 1 State change */
 	hw->mr.r_irq_statech |=
@@ -1292,9 +1213,7 @@ hfc4s8s_interrupt(int intno, void *dev_id)
 	if (!
 	    (b = (Read_hfc8(hw, R_STATUS) & (M_MISC_IRQSTA | M_FR_IRQSTA)))
 	    && !hw->mr.r_irq_statech) {
-#ifndef	HISAX_HFC4S8S_PCIMEM
 		SetRegAddr(hw, old_ioreg);
-#endif
 		return IRQ_NONE;
 	}
 
@@ -1322,9 +1241,7 @@ hfc4s8s_interrupt(int intno, void *dev_id)
 	/* queue the request to allow other cards to interrupt */
 	schedule_work(&hw->tqueue);
 
-#ifndef	HISAX_HFC4S8S_PCIMEM
 	SetRegAddr(hw, old_ioreg);
-#endif
 	return IRQ_HANDLED;
 }				/* hfc4s8s_interrupt */
 
@@ -1471,13 +1388,8 @@ static void
 release_pci_ports(hfc4s8s_hw *hw)
 {
 	pci_write_config_word(hw->pdev, PCI_COMMAND, 0);
-#ifdef HISAX_HFC4S8S_PCIMEM
-	if (hw->membase)
-		iounmap((void *) hw->membase);
-#else
 	if (hw->iobase)
 		release_region(hw->iobase, 8);
-#endif
 }
 
 /*****************************************/
@@ -1486,11 +1398,7 @@ release_pci_ports(hfc4s8s_hw *hw)
 static void
 enable_pci_ports(hfc4s8s_hw *hw)
 {
-#ifdef HISAX_HFC4S8S_PCIMEM
-	pci_write_config_word(hw->pdev, PCI_COMMAND, PCI_ENA_MEMIO);
-#else
 	pci_write_config_word(hw->pdev, PCI_COMMAND, PCI_ENA_REGIO);
-#endif
 }
 
 /*************************************/
@@ -1561,15 +1469,9 @@ setup_instance(hfc4s8s_hw *hw)
 		       hw->irq);
 		goto out;
 	}
-#ifdef HISAX_HFC4S8S_PCIMEM
-	printk(KERN_INFO
-	       "HFC-4S/8S: found PCI card at membase 0x%p, irq %d\n",
-	       hw->hw_membase, hw->irq);
-#else
 	printk(KERN_INFO
 	       "HFC-4S/8S: found PCI card at iobase 0x%x, irq %d\n",
 	       hw->iobase, hw->irq);
-#endif
 
 	hfc_hardware_enable(hw, 1, 0);
 
@@ -1614,17 +1516,12 @@ hfc4s8s_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hw->irq = pdev->irq;
 	hw->iobase = pci_resource_start(pdev, 0);
 
-#ifdef HISAX_HFC4S8S_PCIMEM
-	hw->hw_membase = (u_char *) pci_resource_start(pdev, 1);
-	hw->membase = ioremap((ulong) hw->hw_membase, 256);
-#else
 	if (!request_region(hw->iobase, 8, hw->card_name)) {
 		printk(KERN_INFO
 		       "HFC-4S/8S: failed to request address space at 0x%04x\n",
 		       hw->iobase);
 		goto out;
 	}
-#endif
 
 	pci_set_drvdata(pdev, hw);
 	err = setup_instance(hw);
diff --git a/drivers/isdn/hisax/l3ni1.c b/drivers/isdn/hisax/l3ni1.c
index 0df6691d045..8dc791bfaa6 100644
--- a/drivers/isdn/hisax/l3ni1.c
+++ b/drivers/isdn/hisax/l3ni1.c
@@ -2059,13 +2059,17 @@ static int l3ni1_cmd_global(struct PStack *st, isdn_ctrl *ic)
 			memcpy(p, ic->parm.ni1_io.data, ic->parm.ni1_io.datalen); /* copy data */
 			l = (p - temp) + ic->parm.ni1_io.datalen; /* total length */
 
-			if (ic->parm.ni1_io.timeout > 0)
-				if (!(pc = ni1_new_l3_process(st, -1)))
-				{ free_invoke_id(st, id);
+			if (ic->parm.ni1_io.timeout > 0) {
+				pc = ni1_new_l3_process(st, -1);
+				if (!pc) {
+					free_invoke_id(st, id);
 					return (-2);
 				}
-			pc->prot.ni1.ll_id = ic->parm.ni1_io.ll_id; /* remember id */
-			pc->prot.ni1.proc = ic->parm.ni1_io.proc; /* and procedure */
+				/* remember id */
+				pc->prot.ni1.ll_id = ic->parm.ni1_io.ll_id;
+				/* and procedure */
+				pc->prot.ni1.proc = ic->parm.ni1_io.proc;
+			}
 
 			if (!(skb = l3_alloc_skb(l)))
 			{ free_invoke_id(st, id);
diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index a5da511e3c9..62f0688d45a 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -442,7 +442,7 @@ static int get_filter(void __user *arg, struct sock_filter **p)
 {
 	struct sock_fprog uprog;
 	struct sock_filter *code = NULL;
-	int len, err;
+	int len;
 
 	if (copy_from_user(&uprog, arg, sizeof(uprog)))
 		return -EFAULT;
@@ -458,12 +458,6 @@ static int get_filter(void __user *arg, struct sock_filter **p)
 	if (IS_ERR(code))
 		return PTR_ERR(code);
 
-	err = sk_chk_filter(code, uprog.len);
-	if (err) {
-		kfree(code);
-		return err;
-	}
-
 	*p = code;
 	return uprog.len;
 }
@@ -634,7 +628,7 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg)
 #ifdef CONFIG_IPPP_FILTER
 	case PPPIOCSPASS:
 	{
-		struct sock_fprog fprog;
+		struct sock_fprog_kern fprog;
 		struct sock_filter *code;
 		int err, len = get_filter(argp, &code);
 
@@ -644,16 +638,22 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg)
 		fprog.len = len;
 		fprog.filter = code;
 
-		if (is->pass_filter)
+		if (is->pass_filter) {
 			sk_unattached_filter_destroy(is->pass_filter);
-		err = sk_unattached_filter_create(&is->pass_filter, &fprog);
+			is->pass_filter = NULL;
+		}
+		if (fprog.filter != NULL)
+			err = sk_unattached_filter_create(&is->pass_filter,
+							  &fprog);
+		else
+			err = 0;
 		kfree(code);
 
 		return err;
 	}
 	case PPPIOCSACTIVE:
 	{
-		struct sock_fprog fprog;
+		struct sock_fprog_kern fprog;
 		struct sock_filter *code;
 		int err, len = get_filter(argp, &code);
 
@@ -663,9 +663,15 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg)
 		fprog.len = len;
 		fprog.filter = code;
 
-		if (is->active_filter)
+		if (is->active_filter) {
 			sk_unattached_filter_destroy(is->active_filter);
-		err = sk_unattached_filter_create(&is->active_filter, &fprog);
+			is->active_filter = NULL;
+		}
+		if (fprog.filter != NULL)
+			err = sk_unattached_filter_create(&is->active_filter,
+							  &fprog);
+		else
+			err = 0;
 		kfree(code);
 
 		return err;
diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c
index 2c0d2c2bf94..9f454d76cc0 100644
--- a/drivers/isdn/mISDN/l1oip_core.c
+++ b/drivers/isdn/mISDN/l1oip_core.c
@@ -287,11 +287,9 @@ l1oip_socket_send(struct l1oip *hc, u8 localcodec, u8 channel, u32 chanmask,
 	p = frame;
 
 	/* restart timer */
-	if ((int)(hc->keep_tl.expires-jiffies) < 5 * HZ) {
-		del_timer(&hc->keep_tl);
-		hc->keep_tl.expires = jiffies + L1OIP_KEEPALIVE * HZ;
-		add_timer(&hc->keep_tl);
-	} else
+	if (time_before(hc->keep_tl.expires, jiffies + 5 * HZ))
+		mod_timer(&hc->keep_tl, jiffies + L1OIP_KEEPALIVE * HZ);
+	else
 		hc->keep_tl.expires = jiffies + L1OIP_KEEPALIVE * HZ;
 
 	if (debug & DEBUG_L1OIP_MSG)
@@ -621,11 +619,9 @@ multiframe:
 		goto multiframe;
 
 	/* restart timer */
-	if ((int)(hc->timeout_tl.expires-jiffies) < 5 * HZ || !hc->timeout_on) {
+	if (time_before(hc->timeout_tl.expires, jiffies + 5 * HZ) || !hc->timeout_on) {
 		hc->timeout_on = 1;
-		del_timer(&hc->timeout_tl);
-		hc->timeout_tl.expires = jiffies + L1OIP_TIMEOUT * HZ;
-		add_timer(&hc->timeout_tl);
+		mod_timer(&hc->timeout_tl, jiffies + L1OIP_TIMEOUT * HZ);
 	} else /* only adjust timer */
 		hc->timeout_tl.expires = jiffies + L1OIP_TIMEOUT * HZ;
 
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 089841ca180..a1b044e7eaa 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -300,16 +300,6 @@ config LEDS_PCA963X
 	  LED driver chip accessed via the I2C bus. Supported
 	  devices include PCA9633 and PCA9634
 
-config LEDS_PCA9685
-	tristate "LED support for PCA9685 I2C chip"
-	depends on LEDS_CLASS
-	depends on I2C
-	help
-	  This option enables support for LEDs connected to the PCA9685
-	  LED driver chip accessed via the I2C bus.
-	  The PCA9685 offers 12-bit PWM (4095 levels of brightness) on
-	  16 individual channels.
-
 config LEDS_WM831X_STATUS
 	tristate "LED support for status LEDs on WM831x PMICs"
 	depends on LEDS_CLASS
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 8b4c956e11b..79c5155199a 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -36,7 +36,6 @@ obj-$(CONFIG_LEDS_OT200)		+= leds-ot200.o
 obj-$(CONFIG_LEDS_FSG)			+= leds-fsg.o
 obj-$(CONFIG_LEDS_PCA955X)		+= leds-pca955x.o
 obj-$(CONFIG_LEDS_PCA963X)		+= leds-pca963x.o
-obj-$(CONFIG_LEDS_PCA9685)		+= leds-pca9685.o
 obj-$(CONFIG_LEDS_DA903X)		+= leds-da903x.o
 obj-$(CONFIG_LEDS_DA9052)		+= leds-da9052.o
 obj-$(CONFIG_LEDS_WM831X_STATUS)	+= leds-wm831x-status.o
diff --git a/drivers/leds/dell-led.c b/drivers/leds/dell-led.c
index e5c57389efd..c36acaf566a 100644
--- a/drivers/leds/dell-led.c
+++ b/drivers/leds/dell-led.c
@@ -15,12 +15,15 @@
 #include <linux/leds.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/dmi.h>
+#include <linux/dell-led.h>
 
 MODULE_AUTHOR("Louis Davis/Jim Dailey");
 MODULE_DESCRIPTION("Dell LED Control Driver");
 MODULE_LICENSE("GPL");
 
 #define DELL_LED_BIOS_GUID "F6E4FE6E-909D-47cb-8BAB-C9F6F2F8D396"
+#define DELL_APP_GUID "A80593CE-A997-11DA-B012-B622A1EF5492"
 MODULE_ALIAS("wmi:" DELL_LED_BIOS_GUID);
 
 /* Error Result Codes: */
@@ -39,6 +42,149 @@ MODULE_ALIAS("wmi:" DELL_LED_BIOS_GUID);
 #define CMD_LED_OFF	17
 #define CMD_LED_BLINK	18
 
+struct app_wmi_args {
+	u16 class;
+	u16 selector;
+	u32 arg1;
+	u32 arg2;
+	u32 arg3;
+	u32 arg4;
+	u32 res1;
+	u32 res2;
+	u32 res3;
+	u32 res4;
+	char dummy[92];
+};
+
+#define GLOBAL_MIC_MUTE_ENABLE	0x364
+#define GLOBAL_MIC_MUTE_DISABLE	0x365
+
+struct dell_bios_data_token {
+	u16 tokenid;
+	u16 location;
+	u16 value;
+};
+
+struct __attribute__ ((__packed__)) dell_bios_calling_interface {
+	struct	dmi_header header;
+	u16	cmd_io_addr;
+	u8	cmd_io_code;
+	u32	supported_cmds;
+	struct	dell_bios_data_token damap[];
+};
+
+static struct dell_bios_data_token dell_mic_tokens[2];
+
+static int dell_wmi_perform_query(struct app_wmi_args *args)
+{
+	struct app_wmi_args *bios_return;
+	union acpi_object *obj;
+	struct acpi_buffer input;
+	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
+	acpi_status status;
+	u32 rc = -EINVAL;
+
+	input.length = 128;
+	input.pointer = args;
+
+	status = wmi_evaluate_method(DELL_APP_GUID, 0, 1, &input, &output);
+	if (!ACPI_SUCCESS(status))
+		goto err_out0;
+
+	obj = output.pointer;
+	if (!obj)
+		goto err_out0;
+
+	if (obj->type != ACPI_TYPE_BUFFER)
+		goto err_out1;
+
+	bios_return = (struct app_wmi_args *)obj->buffer.pointer;
+	rc = bios_return->res1;
+	if (rc)
+		goto err_out1;
+
+	memcpy(args, bios_return, sizeof(struct app_wmi_args));
+	rc = 0;
+
+ err_out1:
+	kfree(obj);
+ err_out0:
+	return rc;
+}
+
+static void __init find_micmute_tokens(const struct dmi_header *dm, void *dummy)
+{
+	struct dell_bios_calling_interface *calling_interface;
+	struct dell_bios_data_token *token;
+	int token_size = sizeof(struct dell_bios_data_token);
+	int i = 0;
+
+	if (dm->type == 0xda && dm->length > 17) {
+		calling_interface = container_of(dm,
+				struct dell_bios_calling_interface, header);
+
+		token = &calling_interface->damap[i];
+		while (token->tokenid != 0xffff) {
+			if (token->tokenid == GLOBAL_MIC_MUTE_DISABLE)
+				memcpy(&dell_mic_tokens[0], token, token_size);
+			else if (token->tokenid == GLOBAL_MIC_MUTE_ENABLE)
+				memcpy(&dell_mic_tokens[1], token, token_size);
+
+			i++;
+			token = &calling_interface->damap[i];
+		}
+	}
+}
+
+static int dell_micmute_led_set(int state)
+{
+	struct app_wmi_args args;
+	struct dell_bios_data_token *token;
+
+	if (!wmi_has_guid(DELL_APP_GUID))
+		return -ENODEV;
+
+	if (state == 0 || state == 1)
+		token = &dell_mic_tokens[state];
+	else
+		return -EINVAL;
+
+	memset(&args, 0, sizeof(struct app_wmi_args));
+
+	args.class = 1;
+	args.arg1 = token->location;
+	args.arg2 = token->value;
+
+	dell_wmi_perform_query(&args);
+
+	return state;
+}
+
+int dell_app_wmi_led_set(int whichled, int on)
+{
+	int state = 0;
+
+	switch (whichled) {
+	case DELL_LED_MICMUTE:
+		state = dell_micmute_led_set(on);
+		break;
+	default:
+		pr_warn("led type %x is not supported\n", whichled);
+		break;
+	}
+
+	return state;
+}
+EXPORT_SYMBOL_GPL(dell_app_wmi_led_set);
+
+static int __init dell_micmute_led_init(void)
+{
+	memset(dell_mic_tokens, 0, sizeof(struct dell_bios_data_token) * 2);
+	dmi_walk(find_micmute_tokens, NULL);
+
+	return 0;
+}
+
 struct bios_args {
 	unsigned char length;
 	unsigned char result_code;
@@ -181,21 +327,32 @@ static int __init dell_led_init(void)
 {
 	int error = 0;
 
-	if (!wmi_has_guid(DELL_LED_BIOS_GUID))
+	if (!wmi_has_guid(DELL_LED_BIOS_GUID) && !wmi_has_guid(DELL_APP_GUID))
 		return -ENODEV;
 
-	error = led_off();
-	if (error != 0)
-		return -ENODEV;
+	if (wmi_has_guid(DELL_APP_GUID))
+		error = dell_micmute_led_init();
 
-	return led_classdev_register(NULL, &dell_led);
+	if (wmi_has_guid(DELL_LED_BIOS_GUID)) {
+		error = led_off();
+		if (error != 0)
+			return -ENODEV;
+
+		error = led_classdev_register(NULL, &dell_led);
+	}
+
+	return error;
 }
 
 static void __exit dell_led_exit(void)
 {
-	led_classdev_unregister(&dell_led);
+	int error = 0;
 
-	led_off();
+	if (wmi_has_guid(DELL_LED_BIOS_GUID)) {
+		error = led_off();
+		if (error == 0)
+			led_classdev_unregister(&dell_led);
+	}
 }
 
 module_init(dell_led_init);
diff --git a/drivers/leds/leds-88pm860x.c b/drivers/leds/leds-88pm860x.c
index d1e1bca90d1..c2def5551ce 100644
--- a/drivers/leds/leds-88pm860x.c
+++ b/drivers/leds/leds-88pm860x.c
@@ -130,10 +130,9 @@ static int pm860x_led_dt_init(struct platform_device *pdev,
 	struct device_node *nproot, *np;
 	int iset = 0;
 
-	nproot = of_node_get(pdev->dev.parent->of_node);
-	if (!nproot)
+	if (!pdev->dev.parent->of_node)
 		return -ENODEV;
-	nproot = of_find_node_by_name(nproot, "leds");
+	nproot = of_get_child_by_name(pdev->dev.parent->of_node, "leds");
 	if (!nproot) {
 		dev_err(&pdev->dev, "failed to find leds node\n");
 		return -ENODEV;
diff --git a/drivers/leds/leds-adp5520.c b/drivers/leds/leds-adp5520.c
index 86b5bdb0c77..5036d7b4f82 100644
--- a/drivers/leds/leds-adp5520.c
+++ b/drivers/leds/leds-adp5520.c
@@ -120,13 +120,10 @@ static int adp5520_led_probe(struct platform_device *pdev)
 
 	led = devm_kzalloc(&pdev->dev, sizeof(*led) * pdata->num_leds,
 				GFP_KERNEL);
-	if (led == NULL) {
-		dev_err(&pdev->dev, "failed to alloc memory\n");
+	if (!led)
 		return -ENOMEM;
-	}
 
 	ret = adp5520_led_prepare(pdev);
-
 	if (ret) {
 		dev_err(&pdev->dev, "failed to write\n");
 		return ret;
diff --git a/drivers/leds/leds-bd2802.c b/drivers/leds/leds-bd2802.c
index fb5a3472d61..6078c15d345 100644
--- a/drivers/leds/leds-bd2802.c
+++ b/drivers/leds/leds-bd2802.c
@@ -678,10 +678,8 @@ static int bd2802_probe(struct i2c_client *client,
 	int ret, i;
 
 	led = devm_kzalloc(&client->dev, sizeof(struct bd2802_led), GFP_KERNEL);
-	if (!led) {
-		dev_err(&client->dev, "failed to allocate driver data\n");
+	if (!led)
 		return -ENOMEM;
-	}
 
 	led->client = client;
 	pdata = led->pdata = dev_get_platdata(&client->dev);
diff --git a/drivers/leds/leds-da903x.c b/drivers/leds/leds-da903x.c
index 35dffb10038..54b8b5216b8 100644
--- a/drivers/leds/leds-da903x.c
+++ b/drivers/leds/leds-da903x.c
@@ -108,10 +108,8 @@ static int da903x_led_probe(struct platform_device *pdev)
 	}
 
 	led = devm_kzalloc(&pdev->dev, sizeof(struct da903x_led), GFP_KERNEL);
-	if (led == NULL) {
-		dev_err(&pdev->dev, "failed to alloc memory for LED%d\n", id);
+	if (!led)
 		return -ENOMEM;
-	}
 
 	led->cdev.name = pdata->name;
 	led->cdev.default_trigger = pdata->default_trigger;
diff --git a/drivers/leds/leds-da9052.c b/drivers/leds/leds-da9052.c
index 01486adc7f8..e4da1f460ac 100644
--- a/drivers/leds/leds-da9052.c
+++ b/drivers/leds/leds-da9052.c
@@ -126,8 +126,7 @@ static int da9052_led_probe(struct platform_device *pdev)
 	led = devm_kzalloc(&pdev->dev,
 			   sizeof(struct da9052_led) * pled->num_leds,
 			   GFP_KERNEL);
-	if (led == NULL) {
-		dev_err(&pdev->dev, "Failed to alloc memory\n");
+	if (!led) {
 		error = -ENOMEM;
 		goto err;
 	}
diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c
index cb5ed82994b..9e1716f8098 100644
--- a/drivers/leds/leds-lp5523.c
+++ b/drivers/leds/leds-lp5523.c
@@ -1,5 +1,5 @@
 /*
- * lp5523.c - LP5523 LED Driver
+ * lp5523.c - LP5523, LP55231 LED Driver
  *
  * Copyright (C) 2010 Nokia Corporation
  * Copyright (C) 2012 Texas Instruments
@@ -814,6 +814,7 @@ MODULE_DEVICE_TABLE(i2c, lp5523_id);
 #ifdef CONFIG_OF
 static const struct of_device_id of_lp5523_leds_match[] = {
 	{ .compatible = "national,lp5523", },
+	{ .compatible = "ti,lp55231", },
 	{},
 };
 
diff --git a/drivers/leds/leds-pca9685.c b/drivers/leds/leds-pca9685.c
deleted file mode 100644
index 6e1ef3a9d6e..00000000000
--- a/drivers/leds/leds-pca9685.c
+++ /dev/null
@@ -1,213 +0,0 @@
-/*
- * Copyright 2013 Maximilian Güntner <maximilian.guentner@gmail.com>
- *
- * This file is subject to the terms and conditions of version 2 of
- * the GNU General Public License.  See the file COPYING in the main
- * directory of this archive for more details.
- *
- * Based on leds-pca963x.c driver by
- * Peter Meerwald <p.meerwald@bct-electronic.com>
- *
- * Driver for the NXP PCA9685 12-Bit PWM LED driver chip.
- *
- */
-
-#include <linux/ctype.h>
-#include <linux/delay.h>
-#include <linux/err.h>
-#include <linux/i2c.h>
-#include <linux/leds.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/workqueue.h>
-
-#include <linux/platform_data/leds-pca9685.h>
-
-/* Register Addresses */
-#define PCA9685_MODE1 0x00
-#define PCA9685_MODE2 0x01
-#define PCA9685_LED0_ON_L 0x06
-#define PCA9685_ALL_LED_ON_L 0xFA
-
-/* MODE1 Register */
-#define PCA9685_ALLCALL 0x00
-#define PCA9685_SLEEP   0x04
-#define PCA9685_AI      0x05
-
-/* MODE2 Register */
-#define PCA9685_INVRT   0x04
-#define PCA9685_OUTDRV  0x02
-
-static const struct i2c_device_id pca9685_id[] = {
-	{ "pca9685", 0 },
-	{ }
-};
-MODULE_DEVICE_TABLE(i2c, pca9685_id);
-
-struct pca9685_led {
-	struct i2c_client *client;
-	struct work_struct work;
-	u16 brightness;
-	struct led_classdev led_cdev;
-	int led_num; /* 0-15 */
-	char name[32];
-};
-
-static void pca9685_write_msg(struct i2c_client *client, u8 *buf, u8 len)
-{
-	struct i2c_msg msg = {
-		.addr = client->addr,
-		.flags = 0x00,
-		.len = len,
-		.buf = buf
-	};
-	i2c_transfer(client->adapter, &msg, 1);
-}
-
-static void pca9685_all_off(struct i2c_client *client)
-{
-	u8 i2c_buffer[5] = {PCA9685_ALL_LED_ON_L, 0x00, 0x00, 0x00, 0x10};
-	pca9685_write_msg(client, i2c_buffer, 5);
-}
-
-static void pca9685_led_work(struct work_struct *work)
-{
-	struct pca9685_led *pca9685;
-	u8 i2c_buffer[5];
-
-	pca9685 = container_of(work, struct pca9685_led, work);
-	i2c_buffer[0] = PCA9685_LED0_ON_L + 4 * pca9685->led_num;
-	/*
-	 * 4095 is the maximum brightness, so we set the ON time to 0x1000
-	 * which disables the PWM generator for that LED
-	 */
-	if (pca9685->brightness == 4095)
-		*((__le16 *)(i2c_buffer+1)) = cpu_to_le16(0x1000);
-	else
-		*((__le16 *)(i2c_buffer+1)) = 0x0000;
-
-	if (pca9685->brightness == 0)
-		*((__le16 *)(i2c_buffer+3)) = cpu_to_le16(0x1000);
-	else if (pca9685->brightness == 4095)
-		*((__le16 *)(i2c_buffer+3)) = 0x0000;
-	else
-		*((__le16 *)(i2c_buffer+3)) = cpu_to_le16(pca9685->brightness);
-
-	pca9685_write_msg(pca9685->client, i2c_buffer, 5);
-}
-
-static void pca9685_led_set(struct led_classdev *led_cdev,
-		enum led_brightness value)
-{
-	struct pca9685_led *pca9685;
-	pca9685 = container_of(led_cdev, struct pca9685_led, led_cdev);
-	pca9685->brightness = value;
-
-	schedule_work(&pca9685->work);
-}
-
-static int pca9685_probe(struct i2c_client *client,
-		const struct i2c_device_id *id)
-{
-	struct pca9685_led *pca9685;
-	struct pca9685_platform_data *pdata;
-	int err;
-	u8 i;
-
-	pdata = dev_get_platdata(&client->dev);
-	if (pdata) {
-		if (pdata->leds.num_leds < 1 || pdata->leds.num_leds > 15) {
-			dev_err(&client->dev, "board info must claim 1-16 LEDs");
-			return -EINVAL;
-		}
-	}
-
-	pca9685 = devm_kzalloc(&client->dev, 16 * sizeof(*pca9685), GFP_KERNEL);
-	if (!pca9685)
-		return -ENOMEM;
-
-	i2c_set_clientdata(client, pca9685);
-	pca9685_all_off(client);
-
-	for (i = 0; i < 16; i++) {
-		pca9685[i].client = client;
-		pca9685[i].led_num = i;
-		pca9685[i].name[0] = '\0';
-		if (pdata && i < pdata->leds.num_leds) {
-			if (pdata->leds.leds[i].name)
-				strncpy(pca9685[i].name,
-					pdata->leds.leds[i].name,
-					sizeof(pca9685[i].name)-1);
-			if (pdata->leds.leds[i].default_trigger)
-				pca9685[i].led_cdev.default_trigger =
-					pdata->leds.leds[i].default_trigger;
-		}
-		if (strlen(pca9685[i].name) == 0) {
-			/*
-			 * Write adapter and address to the name as well.
-			 * Otherwise multiple chips attached to one host would
-			 * not work.
-			 */
-			snprintf(pca9685[i].name, sizeof(pca9685[i].name),
-					"pca9685:%d:x%.2x:%d",
-					client->adapter->nr, client->addr, i);
-		}
-		pca9685[i].led_cdev.name = pca9685[i].name;
-		pca9685[i].led_cdev.max_brightness = 0xfff;
-		pca9685[i].led_cdev.brightness_set = pca9685_led_set;
-
-		INIT_WORK(&pca9685[i].work, pca9685_led_work);
-		err = led_classdev_register(&client->dev, &pca9685[i].led_cdev);
-		if (err < 0)
-			goto exit;
-	}
-
-	if (pdata)
-		i2c_smbus_write_byte_data(client, PCA9685_MODE2,
-			pdata->outdrv << PCA9685_OUTDRV |
-			pdata->inverted << PCA9685_INVRT);
-	else
-		i2c_smbus_write_byte_data(client, PCA9685_MODE2,
-			PCA9685_TOTEM_POLE << PCA9685_OUTDRV);
-	/* Enable Auto-Increment, enable oscillator, ALLCALL/SUBADDR disabled */
-	i2c_smbus_write_byte_data(client, PCA9685_MODE1, BIT(PCA9685_AI));
-
-	return 0;
-
-exit:
-	while (i--) {
-		led_classdev_unregister(&pca9685[i].led_cdev);
-		cancel_work_sync(&pca9685[i].work);
-	}
-	return err;
-}
-
-static int pca9685_remove(struct i2c_client *client)
-{
-	struct pca9685_led *pca9685 = i2c_get_clientdata(client);
-	u8 i;
-
-	for (i = 0; i < 16; i++) {
-		led_classdev_unregister(&pca9685[i].led_cdev);
-		cancel_work_sync(&pca9685[i].work);
-	}
-	pca9685_all_off(client);
-	return 0;
-}
-
-static struct i2c_driver pca9685_driver = {
-	.driver = {
-		.name = "leds-pca9685",
-		.owner = THIS_MODULE,
-	},
-	.probe = pca9685_probe,
-	.remove = pca9685_remove,
-	.id_table = pca9685_id,
-};
-
-module_i2c_driver(pca9685_driver);
-
-MODULE_AUTHOR("Maximilian Güntner <maximilian.guentner@gmail.com>");
-MODULE_DESCRIPTION("PCA9685 LED Driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/leds-pwm.c b/drivers/leds/leds-pwm.c
index 7d0aaed1e23..d672bb4480f 100644
--- a/drivers/leds/leds-pwm.c
+++ b/drivers/leds/leds-pwm.c
@@ -69,6 +69,10 @@ static void led_pwm_set(struct led_classdev *led_cdev,
 
 	duty *= brightness;
 	do_div(duty, max);
+
+	if (led_dat->active_low)
+		duty = led_dat->period - duty;
+
 	led_dat->duty = duty;
 
 	if (led_dat->can_sleep)
@@ -92,55 +96,78 @@ static void led_pwm_cleanup(struct led_pwm_priv *priv)
 	}
 }
 
-static int led_pwm_create_of(struct platform_device *pdev,
-			     struct led_pwm_priv *priv)
+static int led_pwm_add(struct device *dev, struct led_pwm_priv *priv,
+		       struct led_pwm *led, struct device_node *child)
 {
-	struct device_node *child;
+	struct led_pwm_data *led_data = &priv->leds[priv->num_leds];
 	int ret;
 
-	for_each_child_of_node(pdev->dev.of_node, child) {
-		struct led_pwm_data *led_dat = &priv->leds[priv->num_leds];
+	led_data->active_low = led->active_low;
+	led_data->cdev.name = led->name;
+	led_data->cdev.default_trigger = led->default_trigger;
+	led_data->cdev.brightness_set = led_pwm_set;
+	led_data->cdev.brightness = LED_OFF;
+	led_data->cdev.max_brightness = led->max_brightness;
+	led_data->cdev.flags = LED_CORE_SUSPENDRESUME;
 
-		led_dat->cdev.name = of_get_property(child, "label",
-						     NULL) ? : child->name;
+	if (child)
+		led_data->pwm = devm_of_pwm_get(dev, child, NULL);
+	else
+		led_data->pwm = devm_pwm_get(dev, led->name);
+	if (IS_ERR(led_data->pwm)) {
+		ret = PTR_ERR(led_data->pwm);
+		dev_err(dev, "unable to request PWM for %s: %d\n",
+			led->name, ret);
+		return ret;
+	}
 
-		led_dat->pwm = devm_of_pwm_get(&pdev->dev, child, NULL);
-		if (IS_ERR(led_dat->pwm)) {
-			dev_err(&pdev->dev, "unable to request PWM for %s\n",
-				led_dat->cdev.name);
-			ret = PTR_ERR(led_dat->pwm);
-			goto err;
-		}
-		/* Get the period from PWM core when n*/
-		led_dat->period = pwm_get_period(led_dat->pwm);
+	if (child)
+		led_data->period = pwm_get_period(led_data->pwm);
 
-		led_dat->cdev.default_trigger = of_get_property(child,
-						"linux,default-trigger", NULL);
-		of_property_read_u32(child, "max-brightness",
-				     &led_dat->cdev.max_brightness);
+	led_data->can_sleep = pwm_can_sleep(led_data->pwm);
+	if (led_data->can_sleep)
+		INIT_WORK(&led_data->work, led_pwm_work);
 
-		led_dat->cdev.brightness_set = led_pwm_set;
-		led_dat->cdev.brightness = LED_OFF;
-		led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
+	led_data->period = pwm_get_period(led_data->pwm);
+	if (!led_data->period && (led->pwm_period_ns > 0))
+		led_data->period = led->pwm_period_ns;
 
-		led_dat->can_sleep = pwm_can_sleep(led_dat->pwm);
-		if (led_dat->can_sleep)
-			INIT_WORK(&led_dat->work, led_pwm_work);
+	ret = led_classdev_register(dev, &led_data->cdev);
+	if (ret == 0) {
+		priv->num_leds++;
+	} else {
+		dev_err(dev, "failed to register PWM led for %s: %d\n",
+			led->name, ret);
+	}
+
+	return ret;
+}
 
-		ret = led_classdev_register(&pdev->dev, &led_dat->cdev);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "failed to register for %s\n",
-				led_dat->cdev.name);
+static int led_pwm_create_of(struct device *dev, struct led_pwm_priv *priv)
+{
+	struct device_node *child;
+	struct led_pwm led;
+	int ret = 0;
+
+	memset(&led, 0, sizeof(led));
+
+	for_each_child_of_node(dev->of_node, child) {
+		led.name = of_get_property(child, "label", NULL) ? :
+			   child->name;
+
+		led.default_trigger = of_get_property(child,
+						"linux,default-trigger", NULL);
+		led.active_low = of_property_read_bool(child, "active-low");
+		of_property_read_u32(child, "max-brightness",
+				     &led.max_brightness);
+
+		ret = led_pwm_add(dev, priv, &led, child);
+		if (ret) {
 			of_node_put(child);
-			goto err;
+			break;
 		}
-		priv->num_leds++;
 	}
 
-	return 0;
-err:
-	led_pwm_cleanup(priv);
-
 	return ret;
 }
 
@@ -166,51 +193,23 @@ static int led_pwm_probe(struct platform_device *pdev)
 
 	if (pdata) {
 		for (i = 0; i < count; i++) {
-			struct led_pwm *cur_led = &pdata->leds[i];
-			struct led_pwm_data *led_dat = &priv->leds[i];
-
-			led_dat->pwm = devm_pwm_get(&pdev->dev, cur_led->name);
-			if (IS_ERR(led_dat->pwm)) {
-				ret = PTR_ERR(led_dat->pwm);
-				dev_err(&pdev->dev,
-					"unable to request PWM for %s\n",
-					cur_led->name);
-				goto err;
-			}
-
-			led_dat->cdev.name = cur_led->name;
-			led_dat->cdev.default_trigger = cur_led->default_trigger;
-			led_dat->active_low = cur_led->active_low;
-			led_dat->period = cur_led->pwm_period_ns;
-			led_dat->cdev.brightness_set = led_pwm_set;
-			led_dat->cdev.brightness = LED_OFF;
-			led_dat->cdev.max_brightness = cur_led->max_brightness;
-			led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
-
-			led_dat->can_sleep = pwm_can_sleep(led_dat->pwm);
-			if (led_dat->can_sleep)
-				INIT_WORK(&led_dat->work, led_pwm_work);
-
-			ret = led_classdev_register(&pdev->dev, &led_dat->cdev);
-			if (ret < 0)
-				goto err;
+			ret = led_pwm_add(&pdev->dev, priv, &pdata->leds[i],
+					  NULL);
+			if (ret)
+				break;
 		}
-		priv->num_leds = count;
 	} else {
-		ret = led_pwm_create_of(pdev, priv);
-		if (ret)
-			return ret;
+		ret = led_pwm_create_of(&pdev->dev, priv);
+	}
+
+	if (ret) {
+		led_pwm_cleanup(priv);
+		return ret;
 	}
 
 	platform_set_drvdata(pdev, priv);
 
 	return 0;
-
-err:
-	priv->num_leds = i;
-	led_pwm_cleanup(priv);
-
-	return ret;
 }
 
 static int led_pwm_remove(struct platform_device *pdev)
diff --git a/drivers/leds/leds-s3c24xx.c b/drivers/leds/leds-s3c24xx.c
index 28988b7b4fa..785eb53a87f 100644
--- a/drivers/leds/leds-s3c24xx.c
+++ b/drivers/leds/leds-s3c24xx.c
@@ -76,10 +76,8 @@ static int s3c24xx_led_probe(struct platform_device *dev)
 
 	led = devm_kzalloc(&dev->dev, sizeof(struct s3c24xx_gpio_led),
 			   GFP_KERNEL);
-	if (led == NULL) {
-		dev_err(&dev->dev, "No memory for device\n");
+	if (!led)
 		return -ENOMEM;
-	}
 
 	platform_set_drvdata(dev, led);
 
diff --git a/drivers/leds/leds-sunfire.c b/drivers/leds/leds-sunfire.c
index 388632d23d4..0b8cc4a021a 100644
--- a/drivers/leds/leds-sunfire.c
+++ b/drivers/leds/leds-sunfire.c
@@ -135,10 +135,8 @@ static int sunfire_led_generic_probe(struct platform_device *pdev,
 	}
 
 	p = devm_kzalloc(&pdev->dev, sizeof(*p), GFP_KERNEL);
-	if (!p) {
-		dev_err(&pdev->dev, "Could not allocate struct sunfire_drvdata\n");
+	if (!p)
 		return -ENOMEM;
-	}
 
 	for (i = 0; i < NUM_LEDS_PER_BOARD; i++) {
 		struct led_classdev *lp = &p->leds[i].led_cdev;
diff --git a/drivers/leds/trigger/ledtrig-cpu.c b/drivers/leds/trigger/ledtrig-cpu.c
index 1c3ee9fcaf3..aec0f02b6b3 100644
--- a/drivers/leds/trigger/ledtrig-cpu.c
+++ b/drivers/leds/trigger/ledtrig-cpu.c
@@ -47,7 +47,7 @@ static DEFINE_PER_CPU(struct led_trigger_cpu, cpu_trig);
  */
 void ledtrig_cpu(enum cpu_led_event ledevt)
 {
-	struct led_trigger_cpu *trig = &__get_cpu_var(cpu_trig);
+	struct led_trigger_cpu *trig = this_cpu_ptr(&cpu_trig);
 
 	/* Locate the correct CPU LED */
 	switch (ledevt) {
diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c
index 23b4a3b28db..4eab93aa570 100644
--- a/drivers/macintosh/smu.c
+++ b/drivers/macintosh/smu.c
@@ -1257,7 +1257,8 @@ static unsigned int smu_fpoll(struct file *file, poll_table *wait)
 		if (pp->busy && pp->cmd.status != 1)
 			mask |= POLLIN;
 		spin_unlock_irqrestore(&pp->lock, flags);
-	} if (pp->mode == smu_file_events) {
+	}
+	if (pp->mode == smu_file_events) {
 		/* Not yet implemented */
 	}
 	return mask;
diff --git a/drivers/macintosh/windfarm_pm121.c b/drivers/macintosh/windfarm_pm121.c
index 7fe58b0ae8b..b350fb86ff0 100644
--- a/drivers/macintosh/windfarm_pm121.c
+++ b/drivers/macintosh/windfarm_pm121.c
@@ -555,8 +555,18 @@ static void pm121_create_sys_fans(int loop_id)
 	pid_param.interval	= PM121_SYS_INTERVAL;
 	pid_param.history_len	= PM121_SYS_HISTORY_SIZE;
 	pid_param.itarget	= param->itarget;
-	pid_param.min		= control->ops->get_min(control);
-	pid_param.max		= control->ops->get_max(control);
+	if(control)
+	{
+		pid_param.min		= control->ops->get_min(control);
+		pid_param.max		= control->ops->get_max(control);
+	} else {
+		/*
+		 * This is probably not the right!?
+		 * Perhaps goto fail  if control == NULL  above?
+		 */
+		pid_param.min		= 0;
+		pid_param.max		= 0;
+	}
 
 	wf_pid_init(&pm121_sys_state[loop_id]->pid, &pid_param);
 
@@ -571,7 +581,7 @@ static void pm121_create_sys_fans(int loop_id)
 	   control the same control */
 	printk(KERN_WARNING "pm121: failed to set up %s loop "
 	       "setting \"%s\" to max speed.\n",
-	       loop_names[loop_id], control->name);
+	       loop_names[loop_id], control ? control->name : "uninitialized value");
 
 	if (control)
 		wf_control_set_max(control);
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 9a8e66ae04f..67f8b31e205 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -669,17 +669,13 @@ static inline unsigned long file_page_offset(struct bitmap_storage *store,
 /*
  * return a pointer to the page in the filemap that contains the given bit
  *
- * this lookup is complicated by the fact that the bitmap sb might be exactly
- * 1 page (e.g., x86) or less than 1 page -- so the bitmap might start on page
- * 0 or page 1
  */
 static inline struct page *filemap_get_page(struct bitmap_storage *store,
 					    unsigned long chunk)
 {
 	if (file_page_index(store, chunk) >= store->file_pages)
 		return NULL;
-	return store->filemap[file_page_index(store, chunk)
-			      - file_page_index(store, 0)];
+	return store->filemap[file_page_index(store, chunk)];
 }
 
 static int bitmap_storage_alloc(struct bitmap_storage *store,
diff --git a/drivers/md/dm-bio-prison.c b/drivers/md/dm-bio-prison.c
index 85f0b707425..f752d12081f 100644
--- a/drivers/md/dm-bio-prison.c
+++ b/drivers/md/dm-bio-prison.c
@@ -14,13 +14,17 @@
 
 /*----------------------------------------------------------------*/
 
-struct dm_bio_prison {
+struct bucket {
 	spinlock_t lock;
+	struct hlist_head cells;
+};
+
+struct dm_bio_prison {
 	mempool_t *cell_pool;
 
 	unsigned nr_buckets;
 	unsigned hash_mask;
-	struct hlist_head *cells;
+	struct bucket *buckets;
 };
 
 /*----------------------------------------------------------------*/
@@ -40,6 +44,12 @@ static uint32_t calc_nr_buckets(unsigned nr_cells)
 
 static struct kmem_cache *_cell_cache;
 
+static void init_bucket(struct bucket *b)
+{
+	spin_lock_init(&b->lock);
+	INIT_HLIST_HEAD(&b->cells);
+}
+
 /*
  * @nr_cells should be the number of cells you want in use _concurrently_.
  * Don't confuse it with the number of distinct keys.
@@ -49,13 +59,12 @@ struct dm_bio_prison *dm_bio_prison_create(unsigned nr_cells)
 	unsigned i;
 	uint32_t nr_buckets = calc_nr_buckets(nr_cells);
 	size_t len = sizeof(struct dm_bio_prison) +
-		(sizeof(struct hlist_head) * nr_buckets);
+		(sizeof(struct bucket) * nr_buckets);
 	struct dm_bio_prison *prison = kmalloc(len, GFP_KERNEL);
 
 	if (!prison)
 		return NULL;
 
-	spin_lock_init(&prison->lock);
 	prison->cell_pool = mempool_create_slab_pool(nr_cells, _cell_cache);
 	if (!prison->cell_pool) {
 		kfree(prison);
@@ -64,9 +73,9 @@ struct dm_bio_prison *dm_bio_prison_create(unsigned nr_cells)
 
 	prison->nr_buckets = nr_buckets;
 	prison->hash_mask = nr_buckets - 1;
-	prison->cells = (struct hlist_head *) (prison + 1);
+	prison->buckets = (struct bucket *) (prison + 1);
 	for (i = 0; i < nr_buckets; i++)
-		INIT_HLIST_HEAD(prison->cells + i);
+		init_bucket(prison->buckets + i);
 
 	return prison;
 }
@@ -107,40 +116,44 @@ static int keys_equal(struct dm_cell_key *lhs, struct dm_cell_key *rhs)
 		       (lhs->block == rhs->block);
 }
 
-static struct dm_bio_prison_cell *__search_bucket(struct hlist_head *bucket,
+static struct bucket *get_bucket(struct dm_bio_prison *prison,
+				 struct dm_cell_key *key)
+{
+	return prison->buckets + hash_key(prison, key);
+}
+
+static struct dm_bio_prison_cell *__search_bucket(struct bucket *b,
 						  struct dm_cell_key *key)
 {
 	struct dm_bio_prison_cell *cell;
 
-	hlist_for_each_entry(cell, bucket, list)
+	hlist_for_each_entry(cell, &b->cells, list)
 		if (keys_equal(&cell->key, key))
 			return cell;
 
 	return NULL;
 }
 
-static void __setup_new_cell(struct dm_bio_prison *prison,
+static void __setup_new_cell(struct bucket *b,
 			     struct dm_cell_key *key,
 			     struct bio *holder,
-			     uint32_t hash,
 			     struct dm_bio_prison_cell *cell)
 {
 	memcpy(&cell->key, key, sizeof(cell->key));
 	cell->holder = holder;
 	bio_list_init(&cell->bios);
-	hlist_add_head(&cell->list, prison->cells + hash);
+	hlist_add_head(&cell->list, &b->cells);
 }
 
-static int __bio_detain(struct dm_bio_prison *prison,
+static int __bio_detain(struct bucket *b,
 			struct dm_cell_key *key,
 			struct bio *inmate,
 			struct dm_bio_prison_cell *cell_prealloc,
 			struct dm_bio_prison_cell **cell_result)
 {
-	uint32_t hash = hash_key(prison, key);
 	struct dm_bio_prison_cell *cell;
 
-	cell = __search_bucket(prison->cells + hash, key);
+	cell = __search_bucket(b, key);
 	if (cell) {
 		if (inmate)
 			bio_list_add(&cell->bios, inmate);
@@ -148,7 +161,7 @@ static int __bio_detain(struct dm_bio_prison *prison,
 		return 1;
 	}
 
-	__setup_new_cell(prison, key, inmate, hash, cell_prealloc);
+	__setup_new_cell(b, key, inmate, cell_prealloc);
 	*cell_result = cell_prealloc;
 	return 0;
 }
@@ -161,10 +174,11 @@ static int bio_detain(struct dm_bio_prison *prison,
 {
 	int r;
 	unsigned long flags;
+	struct bucket *b = get_bucket(prison, key);
 
-	spin_lock_irqsave(&prison->lock, flags);
-	r = __bio_detain(prison, key, inmate, cell_prealloc, cell_result);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_lock_irqsave(&b->lock, flags);
+	r = __bio_detain(b, key, inmate, cell_prealloc, cell_result);
+	spin_unlock_irqrestore(&b->lock, flags);
 
 	return r;
 }
@@ -208,10 +222,11 @@ void dm_cell_release(struct dm_bio_prison *prison,
 		     struct bio_list *bios)
 {
 	unsigned long flags;
+	struct bucket *b = get_bucket(prison, &cell->key);
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irqsave(&b->lock, flags);
 	__cell_release(cell, bios);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irqrestore(&b->lock, flags);
 }
 EXPORT_SYMBOL_GPL(dm_cell_release);
 
@@ -230,28 +245,25 @@ void dm_cell_release_no_holder(struct dm_bio_prison *prison,
 			       struct bio_list *inmates)
 {
 	unsigned long flags;
+	struct bucket *b = get_bucket(prison, &cell->key);
 
-	spin_lock_irqsave(&prison->lock, flags);
+	spin_lock_irqsave(&b->lock, flags);
 	__cell_release_no_holder(cell, inmates);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	spin_unlock_irqrestore(&b->lock, flags);
 }
 EXPORT_SYMBOL_GPL(dm_cell_release_no_holder);
 
 void dm_cell_error(struct dm_bio_prison *prison,
-		   struct dm_bio_prison_cell *cell)
+		   struct dm_bio_prison_cell *cell, int error)
 {
 	struct bio_list bios;
 	struct bio *bio;
-	unsigned long flags;
 
 	bio_list_init(&bios);
-
-	spin_lock_irqsave(&prison->lock, flags);
-	__cell_release(cell, &bios);
-	spin_unlock_irqrestore(&prison->lock, flags);
+	dm_cell_release(prison, cell, &bios);
 
 	while ((bio = bio_list_pop(&bios)))
-		bio_io_error(bio);
+		bio_endio(bio, error);
 }
 EXPORT_SYMBOL_GPL(dm_cell_error);
 
diff --git a/drivers/md/dm-bio-prison.h b/drivers/md/dm-bio-prison.h
index 3f833190ead..6805a142b75 100644
--- a/drivers/md/dm-bio-prison.h
+++ b/drivers/md/dm-bio-prison.h
@@ -85,7 +85,7 @@ void dm_cell_release_no_holder(struct dm_bio_prison *prison,
 			       struct dm_bio_prison_cell *cell,
 			       struct bio_list *inmates);
 void dm_cell_error(struct dm_bio_prison *prison,
-		   struct dm_bio_prison_cell *cell);
+		   struct dm_bio_prison_cell *cell, int error);
 
 /*----------------------------------------------------------------*/
 
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 4e84095833d..ab472c557d1 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -615,16 +615,6 @@ static void write_endio(struct bio *bio, int error)
 }
 
 /*
- * This function is called when wait_on_bit is actually waiting.
- */
-static int do_io_schedule(void *word)
-{
-	io_schedule();
-
-	return 0;
-}
-
-/*
  * Initiate a write on a dirty buffer, but don't wait for it.
  *
  * - If the buffer is not dirty, exit.
@@ -640,8 +630,7 @@ static void __write_dirty_buffer(struct dm_buffer *b,
 		return;
 
 	clear_bit(B_DIRTY, &b->state);
-	wait_on_bit_lock(&b->state, B_WRITING,
-			 do_io_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_lock_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE);
 
 	if (!write_list)
 		submit_io(b, WRITE, b->block, write_endio);
@@ -675,9 +664,9 @@ static void __make_buffer_clean(struct dm_buffer *b)
 	if (!b->state)	/* fast case */
 		return;
 
-	wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
 	__write_dirty_buffer(b, NULL);
-	wait_on_bit(&b->state, B_WRITING, do_io_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&b->state, B_WRITING, TASK_UNINTERRUPTIBLE);
 }
 
 /*
@@ -1030,7 +1019,7 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
 	if (need_submit)
 		submit_io(b, READ, b->block, read_endio);
 
-	wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
 
 	if (b->read_error) {
 		int error = b->read_error;
@@ -1209,15 +1198,13 @@ again:
 				dropped_lock = 1;
 				b->hold_count++;
 				dm_bufio_unlock(c);
-				wait_on_bit(&b->state, B_WRITING,
-					    do_io_schedule,
-					    TASK_UNINTERRUPTIBLE);
+				wait_on_bit_io(&b->state, B_WRITING,
+					       TASK_UNINTERRUPTIBLE);
 				dm_bufio_lock(c);
 				b->hold_count--;
 			} else
-				wait_on_bit(&b->state, B_WRITING,
-					    do_io_schedule,
-					    TASK_UNINTERRUPTIBLE);
+				wait_on_bit_io(&b->state, B_WRITING,
+					       TASK_UNINTERRUPTIBLE);
 		}
 
 		if (!test_bit(B_DIRTY, &b->state) &&
@@ -1321,15 +1308,15 @@ retry:
 
 	__write_dirty_buffer(b, NULL);
 	if (b->hold_count == 1) {
-		wait_on_bit(&b->state, B_WRITING,
-			    do_io_schedule, TASK_UNINTERRUPTIBLE);
+		wait_on_bit_io(&b->state, B_WRITING,
+			       TASK_UNINTERRUPTIBLE);
 		set_bit(B_DIRTY, &b->state);
 		__unlink_buffer(b);
 		__link_buffer(b, new_block, LIST_DIRTY);
 	} else {
 		sector_t old_block;
-		wait_on_bit_lock(&b->state, B_WRITING,
-				 do_io_schedule, TASK_UNINTERRUPTIBLE);
+		wait_on_bit_lock_io(&b->state, B_WRITING,
+				    TASK_UNINTERRUPTIBLE);
 		/*
 		 * Relink buffer to "new_block" so that write_callback
 		 * sees "new_block" as a block number.
@@ -1341,8 +1328,8 @@ retry:
 		__unlink_buffer(b);
 		__link_buffer(b, new_block, b->list_mode);
 		submit_io(b, WRITE, new_block, write_endio);
-		wait_on_bit(&b->state, B_WRITING,
-			    do_io_schedule, TASK_UNINTERRUPTIBLE);
+		wait_on_bit_io(&b->state, B_WRITING,
+			       TASK_UNINTERRUPTIBLE);
 		__unlink_buffer(b);
 		__link_buffer(b, old_block, b->list_mode);
 	}
@@ -1541,7 +1528,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign
 	BUG_ON(block_size < 1 << SECTOR_SHIFT ||
 	       (block_size & (block_size - 1)));
 
-	c = kmalloc(sizeof(*c), GFP_KERNEL);
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c) {
 		r = -ENOMEM;
 		goto bad_client;
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 4ead4ba6065..d2899e7eb3a 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -425,6 +425,15 @@ static int __open_metadata(struct dm_cache_metadata *cmd)
 
 	disk_super = dm_block_data(sblock);
 
+	/* Verify the data block size hasn't changed */
+	if (le32_to_cpu(disk_super->data_block_size) != cmd->data_block_size) {
+		DMERR("changing the data block size (from %u to %llu) is not supported",
+		      le32_to_cpu(disk_super->data_block_size),
+		      (unsigned long long)cmd->data_block_size);
+		r = -EINVAL;
+		goto bad;
+	}
+
 	r = __check_incompat_features(disk_super, cmd);
 	if (r < 0)
 		goto bad;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 5f054c44b48..2c63326638b 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -231,7 +231,7 @@ struct cache {
 	/*
 	 * cache_size entries, dirty if set
 	 */
-	dm_cblock_t nr_dirty;
+	atomic_t nr_dirty;
 	unsigned long *dirty_bitset;
 
 	/*
@@ -492,7 +492,7 @@ static bool is_dirty(struct cache *cache, dm_cblock_t b)
 static void set_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock)
 {
 	if (!test_and_set_bit(from_cblock(cblock), cache->dirty_bitset)) {
-		cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) + 1);
+		atomic_inc(&cache->nr_dirty);
 		policy_set_dirty(cache->policy, oblock);
 	}
 }
@@ -501,8 +501,7 @@ static void clear_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cbl
 {
 	if (test_and_clear_bit(from_cblock(cblock), cache->dirty_bitset)) {
 		policy_clear_dirty(cache->policy, oblock);
-		cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) - 1);
-		if (!from_cblock(cache->nr_dirty))
+		if (atomic_dec_return(&cache->nr_dirty) == 0)
 			dm_table_event(cache->ti->table);
 	}
 }
@@ -2269,7 +2268,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	atomic_set(&cache->quiescing_ack, 0);
 
 	r = -ENOMEM;
-	cache->nr_dirty = 0;
+	atomic_set(&cache->nr_dirty, 0);
 	cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size));
 	if (!cache->dirty_bitset) {
 		*error = "could not allocate dirty bitset";
@@ -2808,7 +2807,7 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 
 		residency = policy_residency(cache->policy);
 
-		DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %llu ",
+		DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ",
 		       (unsigned)(DM_CACHE_METADATA_BLOCK_SIZE >> SECTOR_SHIFT),
 		       (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
 		       (unsigned long long)nr_blocks_metadata,
@@ -2821,7 +2820,7 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 		       (unsigned) atomic_read(&cache->stats.write_miss),
 		       (unsigned) atomic_read(&cache->stats.demotion),
 		       (unsigned) atomic_read(&cache->stats.promotion),
-		       (unsigned long long) from_cblock(cache->nr_dirty));
+		       (unsigned long) atomic_read(&cache->nr_dirty));
 
 		if (writethrough_mode(&cache->features))
 			DMEMIT("1 writethrough ");
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 53b213226c0..4cba2d808af 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2003 Christophe Saout <christophe@saout.de>
+ * Copyright (C) 2003 Jana Saout <jana@saout.de>
  * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org>
  * Copyright (C) 2006-2009 Red Hat, Inc. All rights reserved.
  * Copyright (C) 2013 Milan Broz <gmazyland@gmail.com>
@@ -1996,6 +1996,6 @@ static void __exit dm_crypt_exit(void)
 module_init(dm_crypt_init);
 module_exit(dm_crypt_exit);
 
-MODULE_AUTHOR("Christophe Saout <christophe@saout.de>");
+MODULE_AUTHOR("Jana Saout <jana@saout.de>");
 MODULE_DESCRIPTION(DM_NAME " target for transparent encryption / decryption");
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 414dad4cb49..ad913cd4ade 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1391,7 +1391,8 @@ static int era_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
 
 static void era_destroy(struct era *era)
 {
-	metadata_close(era->md);
+	if (era->md)
+		metadata_close(era->md);
 
 	if (era->wq)
 		destroy_workqueue(era->wq);
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 3842ac738f9..db404a0f7e2 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -10,6 +10,7 @@
 #include <linux/device-mapper.h>
 
 #include <linux/bio.h>
+#include <linux/completion.h>
 #include <linux/mempool.h>
 #include <linux/module.h>
 #include <linux/sched.h>
@@ -32,7 +33,7 @@ struct dm_io_client {
 struct io {
 	unsigned long error_bits;
 	atomic_t count;
-	struct task_struct *sleeper;
+	struct completion *wait;
 	struct dm_io_client *client;
 	io_notify_fn callback;
 	void *context;
@@ -121,8 +122,8 @@ static void dec_count(struct io *io, unsigned int region, int error)
 			invalidate_kernel_vmap_range(io->vma_invalidate_address,
 						     io->vma_invalidate_size);
 
-		if (io->sleeper)
-			wake_up_process(io->sleeper);
+		if (io->wait)
+			complete(io->wait);
 
 		else {
 			unsigned long r = io->error_bits;
@@ -387,6 +388,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 	 */
 	volatile char io_[sizeof(struct io) + __alignof__(struct io) - 1];
 	struct io *io = (struct io *)PTR_ALIGN(&io_, __alignof__(struct io));
+	DECLARE_COMPLETION_ONSTACK(wait);
 
 	if (num_regions > 1 && (rw & RW_MASK) != WRITE) {
 		WARN_ON(1);
@@ -395,7 +397,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 
 	io->error_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
-	io->sleeper = current;
+	io->wait = &wait;
 	io->client = client;
 
 	io->vma_invalidate_address = dp->vma_invalidate_address;
@@ -403,15 +405,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 
 	dispatch_io(rw, num_regions, where, dp, io, 1);
 
-	while (1) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-
-		if (!atomic_read(&io->count))
-			break;
-
-		io_schedule();
-	}
-	set_current_state(TASK_RUNNING);
+	wait_for_completion_io(&wait);
 
 	if (error_bits)
 		*error_bits = io->error_bits;
@@ -434,7 +428,7 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 	io = mempool_alloc(client->pool, GFP_NOIO);
 	io->error_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
-	io->sleeper = NULL;
+	io->wait = NULL;
 	io->client = client;
 	io->callback = fn;
 	io->context = context;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index ebfa411d1a7..f4167b013d9 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1242,17 +1242,8 @@ static int do_end_io(struct multipath *m, struct request *clone,
 	if (!error && !clone->errors)
 		return 0;	/* I/O complete */
 
-	if (noretry_error(error)) {
-		if ((clone->cmd_flags & REQ_WRITE_SAME) &&
-		    !clone->q->limits.max_write_same_sectors) {
-			struct queue_limits *limits;
-
-			/* device doesn't really support WRITE SAME, disable it */
-			limits = dm_get_queue_limits(dm_table_get_md(m->ti->table));
-			limits->max_write_same_sectors = 0;
-		}
+	if (noretry_error(error))
 		return error;
-	}
 
 	if (mpio->pgpath)
 		fail_path(mpio->pgpath);
@@ -1620,8 +1611,9 @@ static int multipath_busy(struct dm_target *ti)
 
 	spin_lock_irqsave(&m->lock, flags);
 
-	/* pg_init in progress, requeue until done */
-	if (!pg_ready(m)) {
+	/* pg_init in progress or no paths available */
+	if (m->pg_init_in_progress ||
+	    (!m->nr_valid_paths && m->queue_if_no_path)) {
 		busy = 1;
 		goto out;
 	}
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 8e0caed0bf7..864b03f4772 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1032,21 +1032,13 @@ static void start_merge(struct dm_snapshot *s)
 		snapshot_merge_next_chunks(s);
 }
 
-static int wait_schedule(void *ptr)
-{
-	schedule();
-
-	return 0;
-}
-
 /*
  * Stop the merging process and wait until it finishes.
  */
 static void stop_merge(struct dm_snapshot *s)
 {
 	set_bit(SHUTDOWN_MERGE, &s->state_bits);
-	wait_on_bit(&s->state_bits, RUNNING_MERGE, wait_schedule,
-		    TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&s->state_bits, RUNNING_MERGE, TASK_UNINTERRUPTIBLE);
 	clear_bit(SHUTDOWN_MERGE, &s->state_bits);
 }
 
@@ -2141,6 +2133,11 @@ static int origin_write_extent(struct dm_snapshot *merging_snap,
  * Origin: maps a linear range of a device, with hooks for snapshotting.
  */
 
+struct dm_origin {
+	struct dm_dev *dev;
+	unsigned split_boundary;
+};
+
 /*
  * Construct an origin mapping: <dev_path>
  * The context for an origin is merely a 'struct dm_dev *'
@@ -2149,41 +2146,65 @@ static int origin_write_extent(struct dm_snapshot *merging_snap,
 static int origin_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	int r;
-	struct dm_dev *dev;
+	struct dm_origin *o;
 
 	if (argc != 1) {
 		ti->error = "origin: incorrect number of arguments";
 		return -EINVAL;
 	}
 
-	r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &dev);
+	o = kmalloc(sizeof(struct dm_origin), GFP_KERNEL);
+	if (!o) {
+		ti->error = "Cannot allocate private origin structure";
+		r = -ENOMEM;
+		goto bad_alloc;
+	}
+
+	r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &o->dev);
 	if (r) {
 		ti->error = "Cannot get target device";
-		return r;
+		goto bad_open;
 	}
 
-	ti->private = dev;
+	ti->private = o;
 	ti->num_flush_bios = 1;
 
 	return 0;
+
+bad_open:
+	kfree(o);
+bad_alloc:
+	return r;
 }
 
 static void origin_dtr(struct dm_target *ti)
 {
-	struct dm_dev *dev = ti->private;
-	dm_put_device(ti, dev);
+	struct dm_origin *o = ti->private;
+	dm_put_device(ti, o->dev);
+	kfree(o);
 }
 
 static int origin_map(struct dm_target *ti, struct bio *bio)
 {
-	struct dm_dev *dev = ti->private;
-	bio->bi_bdev = dev->bdev;
+	struct dm_origin *o = ti->private;
+	unsigned available_sectors;
 
-	if (bio->bi_rw & REQ_FLUSH)
+	bio->bi_bdev = o->dev->bdev;
+
+	if (unlikely(bio->bi_rw & REQ_FLUSH))
+		return DM_MAPIO_REMAPPED;
+
+	if (bio_rw(bio) != WRITE)
 		return DM_MAPIO_REMAPPED;
 
+	available_sectors = o->split_boundary -
+		((unsigned)bio->bi_iter.bi_sector & (o->split_boundary - 1));
+
+	if (bio_sectors(bio) > available_sectors)
+		dm_accept_partial_bio(bio, available_sectors);
+
 	/* Only tell snapshots if this is a write */
-	return (bio_rw(bio) == WRITE) ? do_origin(dev, bio) : DM_MAPIO_REMAPPED;
+	return do_origin(o->dev, bio);
 }
 
 /*
@@ -2192,15 +2213,15 @@ static int origin_map(struct dm_target *ti, struct bio *bio)
  */
 static void origin_resume(struct dm_target *ti)
 {
-	struct dm_dev *dev = ti->private;
+	struct dm_origin *o = ti->private;
 
-	ti->max_io_len = get_origin_minimum_chunksize(dev->bdev);
+	o->split_boundary = get_origin_minimum_chunksize(o->dev->bdev);
 }
 
 static void origin_status(struct dm_target *ti, status_type_t type,
 			  unsigned status_flags, char *result, unsigned maxlen)
 {
-	struct dm_dev *dev = ti->private;
+	struct dm_origin *o = ti->private;
 
 	switch (type) {
 	case STATUSTYPE_INFO:
@@ -2208,7 +2229,7 @@ static void origin_status(struct dm_target *ti, status_type_t type,
 		break;
 
 	case STATUSTYPE_TABLE:
-		snprintf(result, maxlen, "%s", dev->name);
+		snprintf(result, maxlen, "%s", o->dev->name);
 		break;
 	}
 }
@@ -2216,13 +2237,13 @@ static void origin_status(struct dm_target *ti, status_type_t type,
 static int origin_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
 			struct bio_vec *biovec, int max_size)
 {
-	struct dm_dev *dev = ti->private;
-	struct request_queue *q = bdev_get_queue(dev->bdev);
+	struct dm_origin *o = ti->private;
+	struct request_queue *q = bdev_get_queue(o->dev->bdev);
 
 	if (!q->merge_bvec_fn)
 		return max_size;
 
-	bvm->bi_bdev = dev->bdev;
+	bvm->bi_bdev = o->dev->bdev;
 
 	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
 }
@@ -2230,9 +2251,9 @@ static int origin_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
 static int origin_iterate_devices(struct dm_target *ti,
 				  iterate_devices_callout_fn fn, void *data)
 {
-	struct dm_dev *dev = ti->private;
+	struct dm_origin *o = ti->private;
 
-	return fn(ti, dev, 0, ti->len, data);
+	return fn(ti, o->dev, 0, ti->len, data);
 }
 
 static struct target_type origin_target = {
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 50601ec7017..5f59f1e3e5b 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -465,8 +465,8 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 }
 EXPORT_SYMBOL(dm_get_device);
 
-int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
-			 sector_t start, sector_t len, void *data)
+static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
+				sector_t start, sector_t len, void *data)
 {
 	struct queue_limits *limits = data;
 	struct block_device *bdev = dev->bdev;
@@ -499,7 +499,6 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 					  (unsigned int) (PAGE_SIZE >> 9));
 	return 0;
 }
-EXPORT_SYMBOL_GPL(dm_set_device_limits);
 
 /*
  * Decrement a device's use count and remove it if necessary.
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index b086a945edc..e9d33ad59df 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -613,6 +613,15 @@ static int __open_metadata(struct dm_pool_metadata *pmd)
 
 	disk_super = dm_block_data(sblock);
 
+	/* Verify the data block size hasn't changed */
+	if (le32_to_cpu(disk_super->data_block_size) != pmd->data_block_size) {
+		DMERR("changing the data block size (from %u to %llu) is not supported",
+		      le32_to_cpu(disk_super->data_block_size),
+		      (unsigned long long)pmd->data_block_size);
+		r = -EINVAL;
+		goto bad_unlock_sblock;
+	}
+
 	r = __check_incompat_features(disk_super, pmd);
 	if (r < 0)
 		goto bad_unlock_sblock;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 242ac2ea5f2..fc9c848a60c 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -310,13 +310,18 @@ static void cell_defer_no_holder_no_free(struct thin_c *tc,
 	wake_worker(pool);
 }
 
-static void cell_error(struct pool *pool,
-		       struct dm_bio_prison_cell *cell)
+static void cell_error_with_code(struct pool *pool,
+				 struct dm_bio_prison_cell *cell, int error_code)
 {
-	dm_cell_error(pool->prison, cell);
+	dm_cell_error(pool->prison, cell, error_code);
 	dm_bio_prison_free_cell(pool->prison, cell);
 }
 
+static void cell_error(struct pool *pool, struct dm_bio_prison_cell *cell)
+{
+	cell_error_with_code(pool, cell, -EIO);
+}
+
 /*----------------------------------------------------------------*/
 
 /*
@@ -1027,7 +1032,7 @@ static void retry_on_resume(struct bio *bio)
 	spin_unlock_irqrestore(&tc->lock, flags);
 }
 
-static bool should_error_unserviceable_bio(struct pool *pool)
+static int should_error_unserviceable_bio(struct pool *pool)
 {
 	enum pool_mode m = get_pool_mode(pool);
 
@@ -1035,25 +1040,27 @@ static bool should_error_unserviceable_bio(struct pool *pool)
 	case PM_WRITE:
 		/* Shouldn't get here */
 		DMERR_LIMIT("bio unserviceable, yet pool is in PM_WRITE mode");
-		return true;
+		return -EIO;
 
 	case PM_OUT_OF_DATA_SPACE:
-		return pool->pf.error_if_no_space;
+		return pool->pf.error_if_no_space ? -ENOSPC : 0;
 
 	case PM_READ_ONLY:
 	case PM_FAIL:
-		return true;
+		return -EIO;
 	default:
 		/* Shouldn't get here */
 		DMERR_LIMIT("bio unserviceable, yet pool has an unknown mode");
-		return true;
+		return -EIO;
 	}
 }
 
 static void handle_unserviceable_bio(struct pool *pool, struct bio *bio)
 {
-	if (should_error_unserviceable_bio(pool))
-		bio_io_error(bio);
+	int error = should_error_unserviceable_bio(pool);
+
+	if (error)
+		bio_endio(bio, error);
 	else
 		retry_on_resume(bio);
 }
@@ -1062,18 +1069,21 @@ static void retry_bios_on_resume(struct pool *pool, struct dm_bio_prison_cell *c
 {
 	struct bio *bio;
 	struct bio_list bios;
+	int error;
 
-	if (should_error_unserviceable_bio(pool)) {
-		cell_error(pool, cell);
+	error = should_error_unserviceable_bio(pool);
+	if (error) {
+		cell_error_with_code(pool, cell, error);
 		return;
 	}
 
 	bio_list_init(&bios);
 	cell_release(pool, cell, &bios);
 
-	if (should_error_unserviceable_bio(pool))
+	error = should_error_unserviceable_bio(pool);
+	if (error)
 		while ((bio = bio_list_pop(&bios)))
-			bio_io_error(bio);
+			bio_endio(bio, error);
 	else
 		while ((bio = bio_list_pop(&bios)))
 			retry_on_resume(bio);
@@ -1610,47 +1620,63 @@ static void do_no_space_timeout(struct work_struct *ws)
 
 /*----------------------------------------------------------------*/
 
-struct noflush_work {
+struct pool_work {
 	struct work_struct worker;
-	struct thin_c *tc;
+	struct completion complete;
+};
+
+static struct pool_work *to_pool_work(struct work_struct *ws)
+{
+	return container_of(ws, struct pool_work, worker);
+}
 
-	atomic_t complete;
-	wait_queue_head_t wait;
+static void pool_work_complete(struct pool_work *pw)
+{
+	complete(&pw->complete);
+}
+
+static void pool_work_wait(struct pool_work *pw, struct pool *pool,
+			   void (*fn)(struct work_struct *))
+{
+	INIT_WORK_ONSTACK(&pw->worker, fn);
+	init_completion(&pw->complete);
+	queue_work(pool->wq, &pw->worker);
+	wait_for_completion(&pw->complete);
+}
+
+/*----------------------------------------------------------------*/
+
+struct noflush_work {
+	struct pool_work pw;
+	struct thin_c *tc;
 };
 
-static void complete_noflush_work(struct noflush_work *w)
+static struct noflush_work *to_noflush(struct work_struct *ws)
 {
-	atomic_set(&w->complete, 1);
-	wake_up(&w->wait);
+	return container_of(to_pool_work(ws), struct noflush_work, pw);
 }
 
 static void do_noflush_start(struct work_struct *ws)
 {
-	struct noflush_work *w = container_of(ws, struct noflush_work, worker);
+	struct noflush_work *w = to_noflush(ws);
 	w->tc->requeue_mode = true;
 	requeue_io(w->tc);
-	complete_noflush_work(w);
+	pool_work_complete(&w->pw);
 }
 
 static void do_noflush_stop(struct work_struct *ws)
 {
-	struct noflush_work *w = container_of(ws, struct noflush_work, worker);
+	struct noflush_work *w = to_noflush(ws);
 	w->tc->requeue_mode = false;
-	complete_noflush_work(w);
+	pool_work_complete(&w->pw);
 }
 
 static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *))
 {
 	struct noflush_work w;
 
-	INIT_WORK_ONSTACK(&w.worker, fn);
 	w.tc = tc;
-	atomic_set(&w.complete, 0);
-	init_waitqueue_head(&w.wait);
-
-	queue_work(tc->pool->wq, &w.worker);
-
-	wait_event(w.wait, atomic_read(&w.complete));
+	pool_work_wait(&w.pw, tc->pool, fn);
 }
 
 /*----------------------------------------------------------------*/
@@ -3068,7 +3094,8 @@ static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits)
 	 */
 	if (pt->adjusted_pf.discard_passdown) {
 		data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits;
-		limits->discard_granularity = data_limits->discard_granularity;
+		limits->discard_granularity = max(data_limits->discard_granularity,
+						  pool->sectors_per_block << SECTOR_SHIFT);
 	} else
 		limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 }
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index c99003e0d47..b9a64bbce30 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2003 Christophe Saout <christophe@saout.de>
+ * Copyright (C) 2003 Jana Saout <jana@saout.de>
  *
  * This file is released under the GPL.
  */
@@ -79,6 +79,6 @@ static void __exit dm_zero_exit(void)
 module_init(dm_zero_init)
 module_exit(dm_zero_exit)
 
-MODULE_AUTHOR("Christophe Saout <christophe@saout.de>");
+MODULE_AUTHOR("Jana Saout <jana@saout.de>");
 MODULE_DESCRIPTION(DM_NAME " dummy target returning zeros");
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index aa9e093343d..32b958dbc49 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -54,6 +54,8 @@ static void do_deferred_remove(struct work_struct *w);
 
 static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
 
+static struct workqueue_struct *deferred_remove_workqueue;
+
 /*
  * For bio-based dm.
  * One of these is allocated per bio.
@@ -276,16 +278,24 @@ static int __init local_init(void)
 	if (r)
 		goto out_free_rq_tio_cache;
 
+	deferred_remove_workqueue = alloc_workqueue("kdmremove", WQ_UNBOUND, 1);
+	if (!deferred_remove_workqueue) {
+		r = -ENOMEM;
+		goto out_uevent_exit;
+	}
+
 	_major = major;
 	r = register_blkdev(_major, _name);
 	if (r < 0)
-		goto out_uevent_exit;
+		goto out_free_workqueue;
 
 	if (!_major)
 		_major = r;
 
 	return 0;
 
+out_free_workqueue:
+	destroy_workqueue(deferred_remove_workqueue);
 out_uevent_exit:
 	dm_uevent_exit();
 out_free_rq_tio_cache:
@@ -299,6 +309,7 @@ out_free_io_cache:
 static void local_exit(void)
 {
 	flush_scheduled_work();
+	destroy_workqueue(deferred_remove_workqueue);
 
 	kmem_cache_destroy(_rq_tio_cache);
 	kmem_cache_destroy(_io_cache);
@@ -407,7 +418,7 @@ static void dm_blk_close(struct gendisk *disk, fmode_t mode)
 
 	if (atomic_dec_and_test(&md->open_count) &&
 	    (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
-		schedule_work(&deferred_remove_work);
+		queue_work(deferred_remove_workqueue, &deferred_remove_work);
 
 	dm_put(md);
 
@@ -755,6 +766,14 @@ static void dec_pending(struct dm_io *io, int error)
 	}
 }
 
+static void disable_write_same(struct mapped_device *md)
+{
+	struct queue_limits *limits = dm_get_queue_limits(md);
+
+	/* device doesn't really support WRITE SAME, disable it */
+	limits->max_write_same_sectors = 0;
+}
+
 static void clone_endio(struct bio *bio, int error)
 {
 	int r = 0;
@@ -783,6 +802,10 @@ static void clone_endio(struct bio *bio, int error)
 		}
 	}
 
+	if (unlikely(r == -EREMOTEIO && (bio->bi_rw & REQ_WRITE_SAME) &&
+		     !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors))
+		disable_write_same(md);
+
 	free_tio(md, tio);
 	dec_pending(io, error);
 }
@@ -977,6 +1000,10 @@ static void dm_done(struct request *clone, int error, bool mapped)
 			r = rq_end_io(tio->ti, clone, error, &tio->info);
 	}
 
+	if (unlikely(r == -EREMOTEIO && (clone->cmd_flags & REQ_WRITE_SAME) &&
+		     !clone->q->limits.max_write_same_sectors))
+		disable_write_same(tio->md);
+
 	if (r <= 0)
 		/* The target wants to complete the I/O */
 		dm_end_request(clone, r);
@@ -1110,6 +1137,46 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
 }
 EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
 
+/*
+ * A target may call dm_accept_partial_bio only from the map routine.  It is
+ * allowed for all bio types except REQ_FLUSH.
+ *
+ * dm_accept_partial_bio informs the dm that the target only wants to process
+ * additional n_sectors sectors of the bio and the rest of the data should be
+ * sent in a next bio.
+ *
+ * A diagram that explains the arithmetics:
+ * +--------------------+---------------+-------+
+ * |         1          |       2       |   3   |
+ * +--------------------+---------------+-------+
+ *
+ * <-------------- *tio->len_ptr --------------->
+ *                      <------- bi_size ------->
+ *                      <-- n_sectors -->
+ *
+ * Region 1 was already iterated over with bio_advance or similar function.
+ *	(it may be empty if the target doesn't use bio_advance)
+ * Region 2 is the remaining bio size that the target wants to process.
+ *	(it may be empty if region 1 is non-empty, although there is no reason
+ *	 to make it empty)
+ * The target requires that region 3 is to be sent in the next bio.
+ *
+ * If the target wants to receive multiple copies of the bio (via num_*bios, etc),
+ * the partially processed part (the sum of regions 1+2) must be the same for all
+ * copies of the bio.
+ */
+void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
+{
+	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
+	unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT;
+	BUG_ON(bio->bi_rw & REQ_FLUSH);
+	BUG_ON(bi_size > *tio->len_ptr);
+	BUG_ON(n_sectors > bi_size);
+	*tio->len_ptr -= bi_size - n_sectors;
+	bio->bi_iter.bi_size = n_sectors << SECTOR_SHIFT;
+}
+EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
+
 static void __map_bio(struct dm_target_io *tio)
 {
 	int r;
@@ -1152,10 +1219,10 @@ struct clone_info {
 	struct bio *bio;
 	struct dm_io *io;
 	sector_t sector;
-	sector_t sector_count;
+	unsigned sector_count;
 };
 
-static void bio_setup_sector(struct bio *bio, sector_t sector, sector_t len)
+static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len)
 {
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_iter.bi_size = to_bytes(len);
@@ -1200,11 +1267,13 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci,
 
 static void __clone_and_map_simple_bio(struct clone_info *ci,
 				       struct dm_target *ti,
-				       unsigned target_bio_nr, sector_t len)
+				       unsigned target_bio_nr, unsigned *len)
 {
 	struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs, target_bio_nr);
 	struct bio *clone = &tio->clone;
 
+	tio->len_ptr = len;
+
 	/*
 	 * Discard requests require the bio's inline iovecs be initialized.
 	 * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
@@ -1212,13 +1281,13 @@ static void __clone_and_map_simple_bio(struct clone_info *ci,
 	 */
 	 __bio_clone_fast(clone, ci->bio);
 	if (len)
-		bio_setup_sector(clone, ci->sector, len);
+		bio_setup_sector(clone, ci->sector, *len);
 
 	__map_bio(tio);
 }
 
 static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
-				  unsigned num_bios, sector_t len)
+				  unsigned num_bios, unsigned *len)
 {
 	unsigned target_bio_nr;
 
@@ -1233,13 +1302,13 @@ static int __send_empty_flush(struct clone_info *ci)
 
 	BUG_ON(bio_has_data(ci->bio));
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
-		__send_duplicate_bios(ci, ti, ti->num_flush_bios, 0);
+		__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
 
 	return 0;
 }
 
 static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
-				     sector_t sector, unsigned len)
+				     sector_t sector, unsigned *len)
 {
 	struct bio *bio = ci->bio;
 	struct dm_target_io *tio;
@@ -1254,7 +1323,8 @@ static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti
 
 	for (target_bio_nr = 0; target_bio_nr < num_target_bios; target_bio_nr++) {
 		tio = alloc_tio(ci, ti, 0, target_bio_nr);
-		clone_bio(tio, bio, sector, len);
+		tio->len_ptr = len;
+		clone_bio(tio, bio, sector, *len);
 		__map_bio(tio);
 	}
 }
@@ -1283,7 +1353,7 @@ static int __send_changing_extent_only(struct clone_info *ci,
 				       is_split_required_fn is_split_required)
 {
 	struct dm_target *ti;
-	sector_t len;
+	unsigned len;
 	unsigned num_bios;
 
 	do {
@@ -1302,11 +1372,11 @@ static int __send_changing_extent_only(struct clone_info *ci,
 			return -EOPNOTSUPP;
 
 		if (is_split_required && !is_split_required(ti))
-			len = min(ci->sector_count, max_io_len_target_boundary(ci->sector, ti));
+			len = min((sector_t)ci->sector_count, max_io_len_target_boundary(ci->sector, ti));
 		else
-			len = min(ci->sector_count, max_io_len(ci->sector, ti));
+			len = min((sector_t)ci->sector_count, max_io_len(ci->sector, ti));
 
-		__send_duplicate_bios(ci, ti, num_bios, len);
+		__send_duplicate_bios(ci, ti, num_bios, &len);
 
 		ci->sector += len;
 	} while (ci->sector_count -= len);
@@ -1345,7 +1415,7 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 
 	len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
 
-	__clone_and_map_data_bio(ci, ti, ci->sector, len);
+	__clone_and_map_data_bio(ci, ti, ci->sector, &len);
 
 	ci->sector += len;
 	ci->sector_count -= len;
@@ -1439,7 +1509,6 @@ static int dm_merge_bvec(struct request_queue *q,
 	 * just one page.
 	 */
 	else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9)
-
 		max_size = 0;
 
 out:
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 2382cfc9bb3..32fc19c540d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3448,6 +3448,8 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 		mddev->level = LEVEL_NONE;
 		return rv;
 	}
+	if (mddev->ro)
+		return  -EROFS;
 
 	/* request to change the personality.  Need to ensure:
 	 *  - array is not engaged in resync/recovery/reshape
@@ -3634,6 +3636,8 @@ layout_store(struct mddev *mddev, const char *buf, size_t len)
 		int err;
 		if (mddev->pers->check_reshape == NULL)
 			return -EBUSY;
+		if (mddev->ro)
+			return -EROFS;
 		mddev->new_layout = n;
 		err = mddev->pers->check_reshape(mddev);
 		if (err) {
@@ -3723,6 +3727,8 @@ chunk_size_store(struct mddev *mddev, const char *buf, size_t len)
 		int err;
 		if (mddev->pers->check_reshape == NULL)
 			return -EBUSY;
+		if (mddev->ro)
+			return -EROFS;
 		mddev->new_chunk_sectors = n >> 9;
 		err = mddev->pers->check_reshape(mddev);
 		if (err) {
@@ -5593,7 +5599,7 @@ static int get_array_info(struct mddev * mddev, void __user * arg)
 	if (mddev->in_sync)
 		info.state = (1<<MD_SB_CLEAN);
 	if (mddev->bitmap && mddev->bitmap_info.offset)
-		info.state = (1<<MD_SB_BITMAP_PRESENT);
+		info.state |= (1<<MD_SB_BITMAP_PRESENT);
 	info.active_disks  = insync;
 	info.working_disks = working;
 	info.failed_disks  = failed;
@@ -6135,6 +6141,8 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
 	 */
 	if (mddev->sync_thread)
 		return -EBUSY;
+	if (mddev->ro)
+		return -EROFS;
 
 	rdev_for_each(rdev, mddev) {
 		sector_t avail = rdev->sectors;
@@ -6157,6 +6165,8 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks)
 	/* change the number of raid disks */
 	if (mddev->pers->check_reshape == NULL)
 		return -EINVAL;
+	if (mddev->ro)
+		return -EROFS;
 	if (raid_disks <= 0 ||
 	    (mddev->max_disks && raid_disks >= mddev->max_disks))
 		return -EINVAL;
@@ -7491,6 +7501,19 @@ void md_do_sync(struct md_thread *thread)
 			    rdev->recovery_offset < j)
 				j = rdev->recovery_offset;
 		rcu_read_unlock();
+
+		/* If there is a bitmap, we need to make sure all
+		 * writes that started before we added a spare
+		 * complete before we start doing a recovery.
+		 * Otherwise the write might complete and (via
+		 * bitmap_endwrite) set a bit in the bitmap after the
+		 * recovery has checked that bit and skipped that
+		 * region.
+		 */
+		if (mddev->bitmap) {
+			mddev->pers->quiesce(mddev, 1);
+			mddev->pers->quiesce(mddev, 0);
+		}
 	}
 
 	printk(KERN_INFO "md: %s of RAID array %s\n", desc, mdname(mddev));
@@ -8333,7 +8356,7 @@ static int md_clear_badblocks(struct badblocks *bb, sector_t s, int sectors)
 			if (a < s) {
 				/* we need to split this range */
 				if (bb->count >= MD_MAX_BADBLOCKS) {
-					rv = 0;
+					rv = -ENOSPC;
 					goto out;
 				}
 				memmove(p+lo+1, p+lo, (bb->count - lo) * 8);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2afef4ec931..6234b2e8458 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -292,9 +292,12 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 	BUG_ON(atomic_read(&conf->active_stripes)==0);
 	if (test_bit(STRIPE_HANDLE, &sh->state)) {
 		if (test_bit(STRIPE_DELAYED, &sh->state) &&
-		    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+		    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
 			list_add_tail(&sh->lru, &conf->delayed_list);
-		else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
+			if (atomic_read(&conf->preread_active_stripes)
+			    < IO_THRESHOLD)
+				md_wakeup_thread(conf->mddev->thread);
+		} else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
 			   sh->bm_seq - conf->seq_write > 0)
 			list_add_tail(&sh->lru, &conf->bitmap_list);
 		else {
@@ -413,6 +416,11 @@ static void release_stripe(struct stripe_head *sh)
 	int hash;
 	bool wakeup;
 
+	/* Avoid release_list until the last reference.
+	 */
+	if (atomic_add_unless(&sh->count, -1, 1))
+		return;
+
 	if (unlikely(!conf->mddev->thread) ||
 		test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state))
 		goto slow_path;
@@ -479,6 +487,7 @@ static void shrink_buffers(struct stripe_head *sh)
 	int num = sh->raid_conf->pool_size;
 
 	for (i = 0; i < num ; i++) {
+		WARN_ON(sh->dev[i].page != sh->dev[i].orig_page);
 		p = sh->dev[i].page;
 		if (!p)
 			continue;
@@ -499,6 +508,7 @@ static int grow_buffers(struct stripe_head *sh)
 			return 1;
 		}
 		sh->dev[i].page = page;
+		sh->dev[i].orig_page = page;
 	}
 	return 0;
 }
@@ -855,6 +865,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
 				bi->bi_rw |= REQ_NOMERGE;
 
+			if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
+				WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+			sh->dev[i].vec.bv_page = sh->dev[i].page;
 			bi->bi_vcnt = 1;
 			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			bi->bi_io_vec[0].bv_offset = 0;
@@ -899,6 +912,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			else
 				rbi->bi_iter.bi_sector = (sh->sector
 						  + rrdev->data_offset);
+			if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
+				WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+			sh->dev[i].rvec.bv_page = sh->dev[i].page;
 			rbi->bi_vcnt = 1;
 			rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			rbi->bi_io_vec[0].bv_offset = 0;
@@ -927,8 +943,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 }
 
 static struct dma_async_tx_descriptor *
-async_copy_data(int frombio, struct bio *bio, struct page *page,
-	sector_t sector, struct dma_async_tx_descriptor *tx)
+async_copy_data(int frombio, struct bio *bio, struct page **page,
+	sector_t sector, struct dma_async_tx_descriptor *tx,
+	struct stripe_head *sh)
 {
 	struct bio_vec bvl;
 	struct bvec_iter iter;
@@ -965,11 +982,16 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
 		if (clen > 0) {
 			b_offset += bvl.bv_offset;
 			bio_page = bvl.bv_page;
-			if (frombio)
-				tx = async_memcpy(page, bio_page, page_offset,
+			if (frombio) {
+				if (sh->raid_conf->skip_copy &&
+				    b_offset == 0 && page_offset == 0 &&
+				    clen == STRIPE_SIZE)
+					*page = bio_page;
+				else
+					tx = async_memcpy(*page, bio_page, page_offset,
 						  b_offset, clen, &submit);
-			else
-				tx = async_memcpy(bio_page, page, b_offset,
+			} else
+				tx = async_memcpy(bio_page, *page, b_offset,
 						  page_offset, clen, &submit);
 		}
 		/* chain the operations */
@@ -1045,8 +1067,8 @@ static void ops_run_biofill(struct stripe_head *sh)
 			spin_unlock_irq(&sh->stripe_lock);
 			while (rbi && rbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
-				tx = async_copy_data(0, rbi, dev->page,
-					dev->sector, tx);
+				tx = async_copy_data(0, rbi, &dev->page,
+					dev->sector, tx, sh);
 				rbi = r5_next_bio(rbi, dev->sector);
 			}
 		}
@@ -1384,6 +1406,7 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 			BUG_ON(dev->written);
 			wbi = dev->written = chosen;
 			spin_unlock_irq(&sh->stripe_lock);
+			WARN_ON(dev->page != dev->orig_page);
 
 			while (wbi && wbi->bi_iter.bi_sector <
 				dev->sector + STRIPE_SECTORS) {
@@ -1393,9 +1416,15 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 					set_bit(R5_SyncIO, &dev->flags);
 				if (wbi->bi_rw & REQ_DISCARD)
 					set_bit(R5_Discard, &dev->flags);
-				else
-					tx = async_copy_data(1, wbi, dev->page,
-						dev->sector, tx);
+				else {
+					tx = async_copy_data(1, wbi, &dev->page,
+						dev->sector, tx, sh);
+					if (dev->page != dev->orig_page) {
+						set_bit(R5_SkipCopy, &dev->flags);
+						clear_bit(R5_UPTODATE, &dev->flags);
+						clear_bit(R5_OVERWRITE, &dev->flags);
+					}
+				}
 				wbi = r5_next_bio(wbi, dev->sector);
 			}
 		}
@@ -1426,7 +1455,7 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
 		struct r5dev *dev = &sh->dev[i];
 
 		if (dev->written || i == pd_idx || i == qd_idx) {
-			if (!discard)
+			if (!discard && !test_bit(R5_SkipCopy, &dev->flags))
 				set_bit(R5_UPTODATE, &dev->flags);
 			if (fua)
 				set_bit(R5_WantFUA, &dev->flags);
@@ -1839,8 +1868,10 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 		osh = get_free_stripe(conf, hash);
 		unlock_device_hash_lock(conf, hash);
 		atomic_set(&nsh->count, 1);
-		for(i=0; i<conf->pool_size; i++)
+		for(i=0; i<conf->pool_size; i++) {
 			nsh->dev[i].page = osh->dev[i].page;
+			nsh->dev[i].orig_page = osh->dev[i].page;
+		}
 		for( ; i<newsize; i++)
 			nsh->dev[i].page = NULL;
 		nsh->hash_lock_index = hash;
@@ -1896,6 +1927,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 			if (nsh->dev[i].page == NULL) {
 				struct page *p = alloc_page(GFP_NOIO);
 				nsh->dev[i].page = p;
+				nsh->dev[i].orig_page = p;
 				if (!p)
 					err = -ENOMEM;
 			}
@@ -2133,24 +2165,20 @@ static void raid5_end_write_request(struct bio *bi, int error)
 }
 
 static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous);
-	
+
 static void raid5_build_block(struct stripe_head *sh, int i, int previous)
 {
 	struct r5dev *dev = &sh->dev[i];
 
 	bio_init(&dev->req);
 	dev->req.bi_io_vec = &dev->vec;
-	dev->req.bi_vcnt++;
-	dev->req.bi_max_vecs++;
+	dev->req.bi_max_vecs = 1;
 	dev->req.bi_private = sh;
-	dev->vec.bv_page = dev->page;
 
 	bio_init(&dev->rreq);
 	dev->rreq.bi_io_vec = &dev->rvec;
-	dev->rreq.bi_vcnt++;
-	dev->rreq.bi_max_vecs++;
+	dev->rreq.bi_max_vecs = 1;
 	dev->rreq.bi_private = sh;
-	dev->rvec.bv_page = dev->page;
 
 	dev->flags = 0;
 	dev->sector = compute_blocknr(sh, i, previous);
@@ -2750,6 +2778,11 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		/* and fail all 'written' */
 		bi = sh->dev[i].written;
 		sh->dev[i].written = NULL;
+		if (test_and_clear_bit(R5_SkipCopy, &sh->dev[i].flags)) {
+			WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+			sh->dev[i].page = sh->dev[i].orig_page;
+		}
+
 		if (bi) bitmap_end = 1;
 		while (bi && bi->bi_iter.bi_sector <
 		       sh->dev[i].sector + STRIPE_SECTORS) {
@@ -2886,8 +2919,11 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
 	     (s->failed >= 1 && fdev[0]->toread) ||
 	     (s->failed >= 2 && fdev[1]->toread) ||
 	     (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
+	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) &&
 	      !test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
-	     (sh->raid_conf->level == 6 && s->failed && s->to_write))) {
+	     (sh->raid_conf->level == 6 && s->failed && s->to_write &&
+	      s->to_write < sh->raid_conf->raid_disks - 2 &&
+	      (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) {
 		/* we would like to get this block, possibly by computing it,
 		 * otherwise read it if the backing disk is insync
 		 */
@@ -2991,12 +3027,17 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 			dev = &sh->dev[i];
 			if (!test_bit(R5_LOCKED, &dev->flags) &&
 			    (test_bit(R5_UPTODATE, &dev->flags) ||
-			     test_bit(R5_Discard, &dev->flags))) {
+			     test_bit(R5_Discard, &dev->flags) ||
+			     test_bit(R5_SkipCopy, &dev->flags))) {
 				/* We can return any write requests */
 				struct bio *wbi, *wbi2;
 				pr_debug("Return write for disc %d\n", i);
 				if (test_and_clear_bit(R5_Discard, &dev->flags))
 					clear_bit(R5_UPTODATE, &dev->flags);
+				if (test_and_clear_bit(R5_SkipCopy, &dev->flags)) {
+					WARN_ON(test_bit(R5_UPTODATE, &dev->flags));
+					dev->page = dev->orig_page;
+				}
 				wbi = dev->written;
 				dev->written = NULL;
 				while (wbi && wbi->bi_iter.bi_sector <
@@ -3015,6 +3056,8 @@ static void handle_stripe_clean_event(struct r5conf *conf,
 						0);
 			} else if (test_bit(R5_Discard, &dev->flags))
 				discard_pending = 1;
+			WARN_ON(test_bit(R5_SkipCopy, &dev->flags));
+			WARN_ON(dev->page != dev->orig_page);
 		}
 	if (!discard_pending &&
 	    test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
@@ -3086,7 +3129,8 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 		    !test_bit(R5_LOCKED, &dev->flags) &&
 		    !(test_bit(R5_UPTODATE, &dev->flags) ||
 		    test_bit(R5_Wantcompute, &dev->flags))) {
-			if (test_bit(R5_Insync, &dev->flags)) rcw++;
+			if (test_bit(R5_Insync, &dev->flags))
+				rcw++;
 			else
 				rcw += 2*disks;
 		}
@@ -3107,10 +3151,10 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 			    !(test_bit(R5_UPTODATE, &dev->flags) ||
 			    test_bit(R5_Wantcompute, &dev->flags)) &&
 			    test_bit(R5_Insync, &dev->flags)) {
-				if (
-				  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
-					pr_debug("Read_old block "
-						 "%d for r-m-w\n", i);
+				if (test_bit(STRIPE_PREREAD_ACTIVE,
+					     &sh->state)) {
+					pr_debug("Read_old block %d for r-m-w\n",
+						 i);
 					set_bit(R5_LOCKED, &dev->flags);
 					set_bit(R5_Wantread, &dev->flags);
 					s->locked++;
@@ -3133,10 +3177,9 @@ static void handle_stripe_dirtying(struct r5conf *conf,
 			    !(test_bit(R5_UPTODATE, &dev->flags) ||
 			      test_bit(R5_Wantcompute, &dev->flags))) {
 				rcw++;
-				if (!test_bit(R5_Insync, &dev->flags))
-					continue; /* it's a failed drive */
-				if (
-				  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+				if (test_bit(R5_Insync, &dev->flags) &&
+				    test_bit(STRIPE_PREREAD_ACTIVE,
+					     &sh->state)) {
 					pr_debug("Read_old block "
 						"%d for Reconstruct\n", i);
 					set_bit(R5_LOCKED, &dev->flags);
@@ -5031,8 +5074,8 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int
 	bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
 
 	set_bit(STRIPE_SYNC_REQUESTED, &sh->state);
+	set_bit(STRIPE_HANDLE, &sh->state);
 
-	handle_stripe(sh);
 	release_stripe(sh);
 
 	return STRIPE_SECTORS;
@@ -5072,7 +5115,7 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 			/* already done this stripe */
 			continue;
 
-		sh = get_active_stripe(conf, sector, 0, 1, 0);
+		sh = get_active_stripe(conf, sector, 0, 1, 1);
 
 		if (!sh) {
 			/* failed to get a stripe - must wait */
@@ -5355,6 +5398,50 @@ raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
 					raid5_store_preread_threshold);
 
 static ssize_t
+raid5_show_skip_copy(struct mddev *mddev, char *page)
+{
+	struct r5conf *conf = mddev->private;
+	if (conf)
+		return sprintf(page, "%d\n", conf->skip_copy);
+	else
+		return 0;
+}
+
+static ssize_t
+raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
+{
+	struct r5conf *conf = mddev->private;
+	unsigned long new;
+	if (len >= PAGE_SIZE)
+		return -EINVAL;
+	if (!conf)
+		return -ENODEV;
+
+	if (kstrtoul(page, 10, &new))
+		return -EINVAL;
+	new = !!new;
+	if (new == conf->skip_copy)
+		return len;
+
+	mddev_suspend(mddev);
+	conf->skip_copy = new;
+	if (new)
+		mddev->queue->backing_dev_info.capabilities |=
+						BDI_CAP_STABLE_WRITES;
+	else
+		mddev->queue->backing_dev_info.capabilities &=
+						~BDI_CAP_STABLE_WRITES;
+	mddev_resume(mddev);
+	return len;
+}
+
+static struct md_sysfs_entry
+raid5_skip_copy = __ATTR(skip_copy, S_IRUGO | S_IWUSR,
+					raid5_show_skip_copy,
+					raid5_store_skip_copy);
+
+
+static ssize_t
 stripe_cache_active_show(struct mddev *mddev, char *page)
 {
 	struct r5conf *conf = mddev->private;
@@ -5439,6 +5526,7 @@ static struct attribute *raid5_attrs[] =  {
 	&raid5_stripecache_active.attr,
 	&raid5_preread_bypass_threshold.attr,
 	&raid5_group_thread_cnt.attr,
+	&raid5_skip_copy.attr,
 	NULL,
 };
 static struct attribute_group raid5_attrs_group = {
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 01ad8ae8f57..bc72cd4be5f 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -232,7 +232,7 @@ struct stripe_head {
 		 */
 		struct bio	req, rreq;
 		struct bio_vec	vec, rvec;
-		struct page	*page;
+		struct page	*page, *orig_page;
 		struct bio	*toread, *read, *towrite, *written;
 		sector_t	sector;			/* sector of this page */
 		unsigned long	flags;
@@ -299,6 +299,7 @@ enum r5dev_flags {
 			 * data in, and now is a good time to write it out.
 			 */
 	R5_Discard,	/* Discard the stripe */
+	R5_SkipCopy,	/* Don't copy data from bio to stripe cache */
 };
 
 /*
@@ -436,6 +437,7 @@ struct r5conf {
 	atomic_t		pending_full_writes; /* full write backlog */
 	int			bypass_count; /* bypassed prereads */
 	int			bypass_threshold; /* preread nice */
+	int			skip_copy; /* Don't copy data from bio to stripe cache */
 	struct list_head	*last_hold; /* detect hold_list promotions */
 
 	atomic_t		reshape_stripes; /* stripes with pending writes for reshape */
diff --git a/drivers/media/dvb-frontends/si2168.c b/drivers/media/dvb-frontends/si2168.c
index 8637d2ed762..2e3cdcfa0a6 100644
--- a/drivers/media/dvb-frontends/si2168.c
+++ b/drivers/media/dvb-frontends/si2168.c
@@ -60,7 +60,7 @@ static int si2168_cmd_execute(struct si2168 *s, struct si2168_cmd *cmd)
 				jiffies_to_msecs(jiffies) -
 				(jiffies_to_msecs(timeout) - TIMEOUT));
 
-		if (!(cmd->args[0] >> 7) & 0x01) {
+		if (!((cmd->args[0] >> 7) & 0x01)) {
 			ret = -ETIMEDOUT;
 			goto err_mutex_unlock;
 		}
@@ -485,20 +485,6 @@ static int si2168_init(struct dvb_frontend *fe)
 	if (ret)
 		goto err;
 
-	cmd.args[0] = 0x05;
-	cmd.args[1] = 0x00;
-	cmd.args[2] = 0xaa;
-	cmd.args[3] = 0x4d;
-	cmd.args[4] = 0x56;
-	cmd.args[5] = 0x40;
-	cmd.args[6] = 0x00;
-	cmd.args[7] = 0x00;
-	cmd.wlen = 8;
-	cmd.rlen = 1;
-	ret = si2168_cmd_execute(s, &cmd);
-	if (ret)
-		goto err;
-
 	/* cold state - try to download firmware */
 	dev_info(&s->client->dev, "%s: found a '%s' in cold state\n",
 			KBUILD_MODNAME, si2168_ops.info.name);
diff --git a/drivers/media/dvb-frontends/si2168_priv.h b/drivers/media/dvb-frontends/si2168_priv.h
index 2a343e896f4..53f7f06ae34 100644
--- a/drivers/media/dvb-frontends/si2168_priv.h
+++ b/drivers/media/dvb-frontends/si2168_priv.h
@@ -22,7 +22,7 @@
 #include <linux/firmware.h>
 #include <linux/i2c-mux.h>
 
-#define SI2168_FIRMWARE "dvb-demod-si2168-01.fw"
+#define SI2168_FIRMWARE "dvb-demod-si2168-02.fw"
 
 /* state struct */
 struct si2168 {
diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c
index 522fe00f5ee..9619be5d482 100644
--- a/drivers/media/dvb-frontends/tda10071.c
+++ b/drivers/media/dvb-frontends/tda10071.c
@@ -668,6 +668,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 	int ret, i;
 	u8 mode, rolloff, pilot, inversion, div;
+	fe_modulation_t modulation;
 
 	dev_dbg(&priv->i2c->dev,
 			"%s: delivery_system=%d modulation=%d frequency=%d symbol_rate=%d inversion=%d pilot=%d rolloff=%d\n",
@@ -702,10 +703,13 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 
 	switch (c->delivery_system) {
 	case SYS_DVBS:
+		modulation = QPSK;
 		rolloff = 0;
 		pilot = 2;
 		break;
 	case SYS_DVBS2:
+		modulation = c->modulation;
+
 		switch (c->rolloff) {
 		case ROLLOFF_20:
 			rolloff = 2;
@@ -750,7 +754,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 
 	for (i = 0, mode = 0xff; i < ARRAY_SIZE(TDA10071_MODCOD); i++) {
 		if (c->delivery_system == TDA10071_MODCOD[i].delivery_system &&
-			c->modulation == TDA10071_MODCOD[i].modulation &&
+			modulation == TDA10071_MODCOD[i].modulation &&
 			c->fec_inner == TDA10071_MODCOD[i].fec) {
 			mode = TDA10071_MODCOD[i].val;
 			dev_dbg(&priv->i2c->dev, "%s: mode found=%02x\n",
@@ -834,10 +838,10 @@ static int tda10071_get_frontend(struct dvb_frontend *fe)
 
 	switch ((buf[1] >> 0) & 0x01) {
 	case 0:
-		c->inversion = INVERSION_OFF;
+		c->inversion = INVERSION_ON;
 		break;
 	case 1:
-		c->inversion = INVERSION_ON;
+		c->inversion = INVERSION_OFF;
 		break;
 	}
 
@@ -856,7 +860,7 @@ static int tda10071_get_frontend(struct dvb_frontend *fe)
 	if (ret)
 		goto error;
 
-	c->symbol_rate = (buf[0] << 16) | (buf[1] << 8) | (buf[2] << 0);
+	c->symbol_rate = ((buf[0] << 16) | (buf[1] << 8) | (buf[2] << 0)) * 1000;
 
 	return ret;
 error:
diff --git a/drivers/media/dvb-frontends/tda10071_priv.h b/drivers/media/dvb-frontends/tda10071_priv.h
index 4baf14bfb65..42048619273 100644
--- a/drivers/media/dvb-frontends/tda10071_priv.h
+++ b/drivers/media/dvb-frontends/tda10071_priv.h
@@ -55,6 +55,7 @@ static struct tda10071_modcod {
 	{ SYS_DVBS2, QPSK,  FEC_8_9,  0x0a },
 	{ SYS_DVBS2, QPSK,  FEC_9_10, 0x0b },
 	/* 8PSK */
+	{ SYS_DVBS2, PSK_8, FEC_AUTO, 0x00 },
 	{ SYS_DVBS2, PSK_8, FEC_3_5,  0x0c },
 	{ SYS_DVBS2, PSK_8, FEC_2_3,  0x0d },
 	{ SYS_DVBS2, PSK_8, FEC_3_4,  0x0e },
diff --git a/drivers/media/pci/saa7134/saa7134-empress.c b/drivers/media/pci/saa7134/saa7134-empress.c
index e65c760e4e8..0006d6bf8c1 100644
--- a/drivers/media/pci/saa7134/saa7134-empress.c
+++ b/drivers/media/pci/saa7134/saa7134-empress.c
@@ -179,7 +179,7 @@ static const struct v4l2_file_operations ts_fops =
 	.read	  = vb2_fop_read,
 	.poll	  = vb2_fop_poll,
 	.mmap	  = vb2_fop_mmap,
-	.ioctl	  = video_ioctl2,
+	.unlocked_ioctl = video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops ts_ioctl_ops = {
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 20f1655e6d7..8108c698b54 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -93,7 +93,9 @@ config VIDEO_M32R_AR_M64278
 
 config VIDEO_OMAP3
 	tristate "OMAP 3 Camera support"
-	depends on OMAP_IOVMM && VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API && ARCH_OMAP3
+	depends on VIDEO_V4L2 && I2C && VIDEO_V4L2_SUBDEV_API && ARCH_OMAP3
+	select ARM_DMA_USE_IOMMU
+	select OMAP_IOMMU
 	---help---
 	  Driver for an OMAP 3 camera controller.
 
diff --git a/drivers/media/platform/davinci/vpif_capture.c b/drivers/media/platform/davinci/vpif_capture.c
index a7ed1649790..1e4ec697fb1 100644
--- a/drivers/media/platform/davinci/vpif_capture.c
+++ b/drivers/media/platform/davinci/vpif_capture.c
@@ -269,6 +269,7 @@ err:
 		list_del(&buf->list);
 		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
 	}
+	spin_unlock_irqrestore(&common->irqlock, flags);
 
 	return ret;
 }
diff --git a/drivers/media/platform/davinci/vpif_display.c b/drivers/media/platform/davinci/vpif_display.c
index 5bb085b19bc..b431b58f39e 100644
--- a/drivers/media/platform/davinci/vpif_display.c
+++ b/drivers/media/platform/davinci/vpif_display.c
@@ -233,6 +233,7 @@ err:
 		list_del(&buf->list);
 		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_QUEUED);
 	}
+	spin_unlock_irqrestore(&common->irqlock, flags);
 
 	return ret;
 }
diff --git a/drivers/media/platform/omap3isp/Makefile b/drivers/media/platform/omap3isp/Makefile
index e8847e79e31..254975a9174 100644
--- a/drivers/media/platform/omap3isp/Makefile
+++ b/drivers/media/platform/omap3isp/Makefile
@@ -3,7 +3,7 @@
 ccflags-$(CONFIG_VIDEO_OMAP3_DEBUG) += -DDEBUG
 
 omap3-isp-objs += \
-	isp.o ispqueue.o ispvideo.o \
+	isp.o ispvideo.o \
 	ispcsiphy.o ispccp2.o ispcsi2.o \
 	ispccdc.o isppreview.o ispresizer.o \
 	ispstat.o isph3a_aewb.o isph3a_af.o isphist.o
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 06a0df43424..2c7aa672056 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -69,6 +69,8 @@
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
 
+#include <asm/dma-iommu.h>
+
 #include <media/v4l2-common.h>
 #include <media/v4l2-device.h>
 
@@ -1397,14 +1399,14 @@ int omap3isp_module_sync_idle(struct media_entity *me, wait_queue_head_t *wait,
 	if (isp_pipeline_is_last(me)) {
 		struct isp_video *video = pipe->output;
 		unsigned long flags;
-		spin_lock_irqsave(&video->queue->irqlock, flags);
+		spin_lock_irqsave(&video->irqlock, flags);
 		if (video->dmaqueue_flags & ISP_VIDEO_DMAQUEUE_UNDERRUN) {
-			spin_unlock_irqrestore(&video->queue->irqlock, flags);
+			spin_unlock_irqrestore(&video->irqlock, flags);
 			atomic_set(stopping, 0);
 			smp_mb();
 			return 0;
 		}
-		spin_unlock_irqrestore(&video->queue->irqlock, flags);
+		spin_unlock_irqrestore(&video->irqlock, flags);
 		if (!wait_event_timeout(*wait, !atomic_read(stopping),
 					msecs_to_jiffies(1000))) {
 			atomic_set(stopping, 0);
@@ -1625,7 +1627,7 @@ struct isp_device *omap3isp_get(struct isp_device *isp)
  * Decrement the reference count on the ISP. If the last reference is released,
  * power-down all submodules, disable clocks and free temporary buffers.
  */
-void omap3isp_put(struct isp_device *isp)
+static void __omap3isp_put(struct isp_device *isp, bool save_ctx)
 {
 	if (isp == NULL)
 		return;
@@ -1634,7 +1636,7 @@ void omap3isp_put(struct isp_device *isp)
 	BUG_ON(isp->ref_count == 0);
 	if (--isp->ref_count == 0) {
 		isp_disable_interrupts(isp);
-		if (isp->domain) {
+		if (save_ctx) {
 			isp_save_ctx(isp);
 			isp->has_context = 1;
 		}
@@ -1648,6 +1650,11 @@ void omap3isp_put(struct isp_device *isp)
 	mutex_unlock(&isp->isp_mutex);
 }
 
+void omap3isp_put(struct isp_device *isp)
+{
+	__omap3isp_put(isp, true);
+}
+
 /* --------------------------------------------------------------------------
  * Platform device driver
  */
@@ -2120,6 +2127,61 @@ error_csiphy:
 	return ret;
 }
 
+static void isp_detach_iommu(struct isp_device *isp)
+{
+	arm_iommu_release_mapping(isp->mapping);
+	isp->mapping = NULL;
+	iommu_group_remove_device(isp->dev);
+}
+
+static int isp_attach_iommu(struct isp_device *isp)
+{
+	struct dma_iommu_mapping *mapping;
+	struct iommu_group *group;
+	int ret;
+
+	/* Create a device group and add the device to it. */
+	group = iommu_group_alloc();
+	if (IS_ERR(group)) {
+		dev_err(isp->dev, "failed to allocate IOMMU group\n");
+		return PTR_ERR(group);
+	}
+
+	ret = iommu_group_add_device(group, isp->dev);
+	iommu_group_put(group);
+
+	if (ret < 0) {
+		dev_err(isp->dev, "failed to add device to IPMMU group\n");
+		return ret;
+	}
+
+	/*
+	 * Create the ARM mapping, used by the ARM DMA mapping core to allocate
+	 * VAs. This will allocate a corresponding IOMMU domain.
+	 */
+	mapping = arm_iommu_create_mapping(&platform_bus_type, SZ_1G, SZ_2G);
+	if (IS_ERR(mapping)) {
+		dev_err(isp->dev, "failed to create ARM IOMMU mapping\n");
+		ret = PTR_ERR(mapping);
+		goto error;
+	}
+
+	isp->mapping = mapping;
+
+	/* Attach the ARM VA mapping to the device. */
+	ret = arm_iommu_attach_device(isp->dev, mapping);
+	if (ret < 0) {
+		dev_err(isp->dev, "failed to attach device to VA mapping\n");
+		goto error;
+	}
+
+	return 0;
+
+error:
+	isp_detach_iommu(isp);
+	return ret;
+}
+
 /*
  * isp_remove - Remove ISP platform device
  * @pdev: Pointer to ISP platform device
@@ -2135,10 +2197,8 @@ static int isp_remove(struct platform_device *pdev)
 	isp_xclk_cleanup(isp);
 
 	__omap3isp_get(isp, false);
-	iommu_detach_device(isp->domain, &pdev->dev);
-	iommu_domain_free(isp->domain);
-	isp->domain = NULL;
-	omap3isp_put(isp);
+	isp_detach_iommu(isp);
+	__omap3isp_put(isp, false);
 
 	return 0;
 }
@@ -2265,39 +2325,32 @@ static int isp_probe(struct platform_device *pdev)
 		}
 	}
 
-	isp->domain = iommu_domain_alloc(pdev->dev.bus);
-	if (!isp->domain) {
-		dev_err(isp->dev, "can't alloc iommu domain\n");
-		ret = -ENOMEM;
+	/* IOMMU */
+	ret = isp_attach_iommu(isp);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "unable to attach to IOMMU\n");
 		goto error_isp;
 	}
 
-	ret = iommu_attach_device(isp->domain, &pdev->dev);
-	if (ret) {
-		dev_err(&pdev->dev, "can't attach iommu device: %d\n", ret);
-		ret = -EPROBE_DEFER;
-		goto free_domain;
-	}
-
 	/* Interrupt */
 	isp->irq_num = platform_get_irq(pdev, 0);
 	if (isp->irq_num <= 0) {
 		dev_err(isp->dev, "No IRQ resource\n");
 		ret = -ENODEV;
-		goto detach_dev;
+		goto error_iommu;
 	}
 
 	if (devm_request_irq(isp->dev, isp->irq_num, isp_isr, IRQF_SHARED,
 			     "OMAP3 ISP", isp)) {
 		dev_err(isp->dev, "Unable to request IRQ\n");
 		ret = -EINVAL;
-		goto detach_dev;
+		goto error_iommu;
 	}
 
 	/* Entities */
 	ret = isp_initialize_modules(isp);
 	if (ret < 0)
-		goto detach_dev;
+		goto error_iommu;
 
 	ret = isp_register_entities(isp);
 	if (ret < 0)
@@ -2310,14 +2363,11 @@ static int isp_probe(struct platform_device *pdev)
 
 error_modules:
 	isp_cleanup_modules(isp);
-detach_dev:
-	iommu_detach_device(isp->domain, &pdev->dev);
-free_domain:
-	iommu_domain_free(isp->domain);
-	isp->domain = NULL;
+error_iommu:
+	isp_detach_iommu(isp);
 error_isp:
 	isp_xclk_cleanup(isp);
-	omap3isp_put(isp);
+	__omap3isp_put(isp, false);
 error:
 	mutex_destroy(&isp->isp_mutex);
 
diff --git a/drivers/media/platform/omap3isp/isp.h b/drivers/media/platform/omap3isp/isp.h
index 6d5e6971190..2c314eea125 100644
--- a/drivers/media/platform/omap3isp/isp.h
+++ b/drivers/media/platform/omap3isp/isp.h
@@ -45,8 +45,6 @@
 #include "ispcsi2.h"
 #include "ispccp2.h"
 
-#define IOMMU_FLAG (IOVMF_ENDIAN_LITTLE | IOVMF_ELSZ_8)
-
 #define ISP_TOK_TERM		0xFFFFFFFF	/*
 						 * terminating token for ISP
 						 * modules reg list
@@ -152,6 +150,7 @@ struct isp_xclk {
  *             regions.
  * @mmio_base_phys: Array with physical L4 bus addresses for ISP register
  *                  regions.
+ * @mapping: IOMMU mapping
  * @stat_lock: Spinlock for handling statistics
  * @isp_mutex: Mutex for serializing requests to ISP.
  * @stop_failure: Indicates that an entity failed to stop.
@@ -171,7 +170,6 @@ struct isp_xclk {
  * @isp_res: Pointer to current settings for ISP Resizer.
  * @isp_prev: Pointer to current settings for ISP Preview.
  * @isp_ccdc: Pointer to current settings for ISP CCDC.
- * @iommu: Pointer to requested IOMMU instance for ISP.
  * @platform_cb: ISP driver callback function pointers for platform code
  *
  * This structure is used to store the OMAP ISP Information.
@@ -189,6 +187,8 @@ struct isp_device {
 	void __iomem *mmio_base[OMAP3_ISP_IOMEM_LAST];
 	unsigned long mmio_base_phys[OMAP3_ISP_IOMEM_LAST];
 
+	struct dma_iommu_mapping *mapping;
+
 	/* ISP Obj */
 	spinlock_t stat_lock;	/* common lock for statistic drivers */
 	struct mutex isp_mutex;	/* For handling ref_count field */
@@ -219,8 +219,6 @@ struct isp_device {
 
 	unsigned int sbl_resources;
 	unsigned int subclk_resources;
-
-	struct iommu_domain *domain;
 };
 
 #define v4l2_dev_to_isp_device(dev) \
diff --git a/drivers/media/platform/omap3isp/ispccdc.c b/drivers/media/platform/omap3isp/ispccdc.c
index 4d920c800ff..9f727d20f06 100644
--- a/drivers/media/platform/omap3isp/ispccdc.c
+++ b/drivers/media/platform/omap3isp/ispccdc.c
@@ -30,7 +30,6 @@
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/mm.h>
-#include <linux/omap-iommu.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <media/v4l2-event.h>
@@ -206,7 +205,8 @@ static int ccdc_lsc_validate_config(struct isp_ccdc_device *ccdc,
  * ccdc_lsc_program_table - Program Lens Shading Compensation table address.
  * @ccdc: Pointer to ISP CCDC device.
  */
-static void ccdc_lsc_program_table(struct isp_ccdc_device *ccdc, u32 addr)
+static void ccdc_lsc_program_table(struct isp_ccdc_device *ccdc,
+				   dma_addr_t addr)
 {
 	isp_reg_writel(to_isp_device(ccdc), addr,
 		       OMAP3_ISP_IOMEM_CCDC, ISPCCDC_LSC_TABLE_BASE);
@@ -333,7 +333,7 @@ static int __ccdc_lsc_configure(struct isp_ccdc_device *ccdc,
 		return -EBUSY;
 
 	ccdc_lsc_setup_regs(ccdc, &req->config);
-	ccdc_lsc_program_table(ccdc, req->table);
+	ccdc_lsc_program_table(ccdc, req->table.dma);
 	return 0;
 }
 
@@ -368,11 +368,12 @@ static void ccdc_lsc_free_request(struct isp_ccdc_device *ccdc,
 	if (req == NULL)
 		return;
 
-	if (req->iovm)
-		dma_unmap_sg(isp->dev, req->iovm->sgt->sgl,
-			     req->iovm->sgt->nents, DMA_TO_DEVICE);
-	if (req->table)
-		omap_iommu_vfree(isp->domain, isp->dev, req->table);
+	if (req->table.addr) {
+		sg_free_table(&req->table.sgt);
+		dma_free_coherent(isp->dev, req->config.size, req->table.addr,
+				  req->table.dma);
+	}
+
 	kfree(req);
 }
 
@@ -416,7 +417,6 @@ static int ccdc_lsc_config(struct isp_ccdc_device *ccdc,
 	struct isp_device *isp = to_isp_device(ccdc);
 	struct ispccdc_lsc_config_req *req;
 	unsigned long flags;
-	void *table;
 	u16 update;
 	int ret;
 
@@ -444,38 +444,31 @@ static int ccdc_lsc_config(struct isp_ccdc_device *ccdc,
 
 		req->enable = 1;
 
-		req->table = omap_iommu_vmalloc(isp->domain, isp->dev, 0,
-					req->config.size, IOMMU_FLAG);
-		if (IS_ERR_VALUE(req->table)) {
-			req->table = 0;
-			ret = -ENOMEM;
-			goto done;
-		}
-
-		req->iovm = omap_find_iovm_area(isp->dev, req->table);
-		if (req->iovm == NULL) {
+		req->table.addr = dma_alloc_coherent(isp->dev, req->config.size,
+						     &req->table.dma,
+						     GFP_KERNEL);
+		if (req->table.addr == NULL) {
 			ret = -ENOMEM;
 			goto done;
 		}
 
-		if (!dma_map_sg(isp->dev, req->iovm->sgt->sgl,
-				req->iovm->sgt->nents, DMA_TO_DEVICE)) {
-			ret = -ENOMEM;
-			req->iovm = NULL;
+		ret = dma_get_sgtable(isp->dev, &req->table.sgt,
+				      req->table.addr, req->table.dma,
+				      req->config.size);
+		if (ret < 0)
 			goto done;
-		}
 
-		dma_sync_sg_for_cpu(isp->dev, req->iovm->sgt->sgl,
-				    req->iovm->sgt->nents, DMA_TO_DEVICE);
+		dma_sync_sg_for_cpu(isp->dev, req->table.sgt.sgl,
+				    req->table.sgt.nents, DMA_TO_DEVICE);
 
-		table = omap_da_to_va(isp->dev, req->table);
-		if (copy_from_user(table, config->lsc, req->config.size)) {
+		if (copy_from_user(req->table.addr, config->lsc,
+				   req->config.size)) {
 			ret = -EFAULT;
 			goto done;
 		}
 
-		dma_sync_sg_for_device(isp->dev, req->iovm->sgt->sgl,
-				       req->iovm->sgt->nents, DMA_TO_DEVICE);
+		dma_sync_sg_for_device(isp->dev, req->table.sgt.sgl,
+				       req->table.sgt.nents, DMA_TO_DEVICE);
 	}
 
 	spin_lock_irqsave(&ccdc->lsc.req_lock, flags);
@@ -584,7 +577,7 @@ static void ccdc_configure_fpc(struct isp_ccdc_device *ccdc)
 	if (!ccdc->fpc_en)
 		return;
 
-	isp_reg_writel(isp, ccdc->fpc.fpcaddr, OMAP3_ISP_IOMEM_CCDC,
+	isp_reg_writel(isp, ccdc->fpc.dma, OMAP3_ISP_IOMEM_CCDC,
 		       ISPCCDC_FPC_ADDR);
 	/* The FPNUM field must be set before enabling FPC. */
 	isp_reg_writel(isp, (ccdc->fpc.fpnum << ISPCCDC_FPC_FPNUM_SHIFT),
@@ -724,8 +717,9 @@ static int ccdc_config(struct isp_ccdc_device *ccdc,
 	ccdc->shadow_update = 0;
 
 	if (OMAP3ISP_CCDC_FPC & ccdc_struct->update) {
-		u32 table_old = 0;
-		u32 table_new;
+		struct omap3isp_ccdc_fpc fpc;
+		struct ispccdc_fpc fpc_old = { .addr = NULL, };
+		struct ispccdc_fpc fpc_new;
 		u32 size;
 
 		if (ccdc->state != ISP_PIPELINE_STREAM_STOPPED)
@@ -734,35 +728,39 @@ static int ccdc_config(struct isp_ccdc_device *ccdc,
 		ccdc->fpc_en = !!(OMAP3ISP_CCDC_FPC & ccdc_struct->flag);
 
 		if (ccdc->fpc_en) {
-			if (copy_from_user(&ccdc->fpc, ccdc_struct->fpc,
-					   sizeof(ccdc->fpc)))
+			if (copy_from_user(&fpc, ccdc_struct->fpc, sizeof(fpc)))
 				return -EFAULT;
 
+			size = fpc.fpnum * 4;
+
 			/*
-			 * table_new must be 64-bytes aligned, but it's
-			 * already done by omap_iommu_vmalloc().
+			 * The table address must be 64-bytes aligned, which is
+			 * guaranteed by dma_alloc_coherent().
 			 */
-			size = ccdc->fpc.fpnum * 4;
-			table_new = omap_iommu_vmalloc(isp->domain, isp->dev,
-							0, size, IOMMU_FLAG);
-			if (IS_ERR_VALUE(table_new))
+			fpc_new.fpnum = fpc.fpnum;
+			fpc_new.addr = dma_alloc_coherent(isp->dev, size,
+							  &fpc_new.dma,
+							  GFP_KERNEL);
+			if (fpc_new.addr == NULL)
 				return -ENOMEM;
 
-			if (copy_from_user(omap_da_to_va(isp->dev, table_new),
-					   (__force void __user *)
-					   ccdc->fpc.fpcaddr, size)) {
-				omap_iommu_vfree(isp->domain, isp->dev,
-								table_new);
+			if (copy_from_user(fpc_new.addr,
+					   (__force void __user *)fpc.fpcaddr,
+					   size)) {
+				dma_free_coherent(isp->dev, size, fpc_new.addr,
+						  fpc_new.dma);
 				return -EFAULT;
 			}
 
-			table_old = ccdc->fpc.fpcaddr;
-			ccdc->fpc.fpcaddr = table_new;
+			fpc_old = ccdc->fpc;
+			ccdc->fpc = fpc_new;
 		}
 
 		ccdc_configure_fpc(ccdc);
-		if (table_old != 0)
-			omap_iommu_vfree(isp->domain, isp->dev, table_old);
+
+		if (fpc_old.addr != NULL)
+			dma_free_coherent(isp->dev, fpc_old.fpnum * 4,
+					  fpc_old.addr, fpc_old.dma);
 	}
 
 	return ccdc_lsc_config(ccdc, ccdc_struct);
@@ -1523,7 +1521,7 @@ static int ccdc_isr_buffer(struct isp_ccdc_device *ccdc)
 
 	buffer = omap3isp_video_buffer_next(&ccdc->video_out);
 	if (buffer != NULL) {
-		ccdc_set_outaddr(ccdc, buffer->isp_addr);
+		ccdc_set_outaddr(ccdc, buffer->dma);
 		restart = 1;
 	}
 
@@ -1662,7 +1660,7 @@ static int ccdc_video_queue(struct isp_video *video, struct isp_buffer *buffer)
 	if (!(ccdc->output & CCDC_OUTPUT_MEMORY))
 		return -ENODEV;
 
-	ccdc_set_outaddr(ccdc, buffer->isp_addr);
+	ccdc_set_outaddr(ccdc, buffer->dma);
 
 	/* We now have a buffer queued on the output, restart the pipeline
 	 * on the next CCDC interrupt if running in continuous mode (or when
@@ -2580,8 +2578,9 @@ void omap3isp_ccdc_cleanup(struct isp_device *isp)
 	cancel_work_sync(&ccdc->lsc.table_work);
 	ccdc_lsc_free_queue(ccdc, &ccdc->lsc.free_queue);
 
-	if (ccdc->fpc.fpcaddr != 0)
-		omap_iommu_vfree(isp->domain, isp->dev, ccdc->fpc.fpcaddr);
+	if (ccdc->fpc.addr != NULL)
+		dma_free_coherent(isp->dev, ccdc->fpc.fpnum * 4, ccdc->fpc.addr,
+				  ccdc->fpc.dma);
 
 	mutex_destroy(&ccdc->ioctl_lock);
 }
diff --git a/drivers/media/platform/omap3isp/ispccdc.h b/drivers/media/platform/omap3isp/ispccdc.h
index 9d24e410786..f65061602c7 100644
--- a/drivers/media/platform/omap3isp/ispccdc.h
+++ b/drivers/media/platform/omap3isp/ispccdc.h
@@ -46,6 +46,12 @@ enum ccdc_input_entity {
 
 #define	OMAP3ISP_CCDC_NEVENTS	16
 
+struct ispccdc_fpc {
+	void *addr;
+	dma_addr_t dma;
+	unsigned int fpnum;
+};
+
 enum ispccdc_lsc_state {
 	LSC_STATE_STOPPED = 0,
 	LSC_STATE_STOPPING = 1,
@@ -57,8 +63,12 @@ struct ispccdc_lsc_config_req {
 	struct list_head list;
 	struct omap3isp_ccdc_lsc_config config;
 	unsigned char enable;
-	u32 table;
-	struct iovm_struct *iovm;
+
+	struct {
+		void *addr;
+		dma_addr_t dma;
+		struct sg_table sgt;
+	} table;
 };
 
 /*
@@ -136,7 +146,7 @@ struct isp_ccdc_device {
 		     fpc_en:1;
 	struct omap3isp_ccdc_blcomp blcomp;
 	struct omap3isp_ccdc_bclamp clamp;
-	struct omap3isp_ccdc_fpc fpc;
+	struct ispccdc_fpc fpc;
 	struct ispccdc_lsc lsc;
 	unsigned int update;
 	unsigned int shadow_update;
diff --git a/drivers/media/platform/omap3isp/ispccp2.c b/drivers/media/platform/omap3isp/ispccp2.c
index b30b67d22a5..f3801db9095 100644
--- a/drivers/media/platform/omap3isp/ispccp2.c
+++ b/drivers/media/platform/omap3isp/ispccp2.c
@@ -549,7 +549,7 @@ static void ccp2_isr_buffer(struct isp_ccp2_device *ccp2)
 
 	buffer = omap3isp_video_buffer_next(&ccp2->video_in);
 	if (buffer != NULL)
-		ccp2_set_inaddr(ccp2, buffer->isp_addr);
+		ccp2_set_inaddr(ccp2, buffer->dma);
 
 	pipe->state |= ISP_PIPELINE_IDLE_INPUT;
 
@@ -940,7 +940,7 @@ static int ccp2_video_queue(struct isp_video *video, struct isp_buffer *buffer)
 {
 	struct isp_ccp2_device *ccp2 = &video->isp->isp_ccp2;
 
-	ccp2_set_inaddr(ccp2, buffer->isp_addr);
+	ccp2_set_inaddr(ccp2, buffer->dma);
 	return 0;
 }
 
diff --git a/drivers/media/platform/omap3isp/ispcsi2.c b/drivers/media/platform/omap3isp/ispcsi2.c
index 620560828a4..5a2e47e58b8 100644
--- a/drivers/media/platform/omap3isp/ispcsi2.c
+++ b/drivers/media/platform/omap3isp/ispcsi2.c
@@ -695,7 +695,7 @@ static void csi2_isr_buffer(struct isp_csi2_device *csi2)
 	if (buffer == NULL)
 		return;
 
-	csi2_set_outaddr(csi2, buffer->isp_addr);
+	csi2_set_outaddr(csi2, buffer->dma);
 	csi2_ctx_enable(isp, csi2, 0, 1);
 }
 
@@ -812,7 +812,7 @@ static int csi2_queue(struct isp_video *video, struct isp_buffer *buffer)
 	struct isp_device *isp = video->isp;
 	struct isp_csi2_device *csi2 = &isp->isp_csi2a;
 
-	csi2_set_outaddr(csi2, buffer->isp_addr);
+	csi2_set_outaddr(csi2, buffer->dma);
 
 	/*
 	 * If streaming was enabled before there was a buffer queued
diff --git a/drivers/media/platform/omap3isp/isph3a_aewb.c b/drivers/media/platform/omap3isp/isph3a_aewb.c
index 75fd82b152b..d6811ce263e 100644
--- a/drivers/media/platform/omap3isp/isph3a_aewb.c
+++ b/drivers/media/platform/omap3isp/isph3a_aewb.c
@@ -47,7 +47,7 @@ static void h3a_aewb_setup_regs(struct ispstat *aewb, void *priv)
 	if (aewb->state == ISPSTAT_DISABLED)
 		return;
 
-	isp_reg_writel(aewb->isp, aewb->active_buf->iommu_addr,
+	isp_reg_writel(aewb->isp, aewb->active_buf->dma_addr,
 		       OMAP3_ISP_IOMEM_H3A, ISPH3A_AEWBUFST);
 
 	if (!aewb->update)
diff --git a/drivers/media/platform/omap3isp/isph3a_af.c b/drivers/media/platform/omap3isp/isph3a_af.c
index a0bf5af3243..6fc960cd30f 100644
--- a/drivers/media/platform/omap3isp/isph3a_af.c
+++ b/drivers/media/platform/omap3isp/isph3a_af.c
@@ -51,7 +51,7 @@ static void h3a_af_setup_regs(struct ispstat *af, void *priv)
 	if (af->state == ISPSTAT_DISABLED)
 		return;
 
-	isp_reg_writel(af->isp, af->active_buf->iommu_addr, OMAP3_ISP_IOMEM_H3A,
+	isp_reg_writel(af->isp, af->active_buf->dma_addr, OMAP3_ISP_IOMEM_H3A,
 		       ISPH3A_AFBUFST);
 
 	if (!af->update)
diff --git a/drivers/media/platform/omap3isp/isppreview.c b/drivers/media/platform/omap3isp/isppreview.c
index 395b2b068c7..720809b07e7 100644
--- a/drivers/media/platform/omap3isp/isppreview.c
+++ b/drivers/media/platform/omap3isp/isppreview.c
@@ -1499,14 +1499,14 @@ static void preview_isr_buffer(struct isp_prev_device *prev)
 	if (prev->input == PREVIEW_INPUT_MEMORY) {
 		buffer = omap3isp_video_buffer_next(&prev->video_in);
 		if (buffer != NULL)
-			preview_set_inaddr(prev, buffer->isp_addr);
+			preview_set_inaddr(prev, buffer->dma);
 		pipe->state |= ISP_PIPELINE_IDLE_INPUT;
 	}
 
 	if (prev->output & PREVIEW_OUTPUT_MEMORY) {
 		buffer = omap3isp_video_buffer_next(&prev->video_out);
 		if (buffer != NULL) {
-			preview_set_outaddr(prev, buffer->isp_addr);
+			preview_set_outaddr(prev, buffer->dma);
 			restart = 1;
 		}
 		pipe->state |= ISP_PIPELINE_IDLE_OUTPUT;
@@ -1577,10 +1577,10 @@ static int preview_video_queue(struct isp_video *video,
 	struct isp_prev_device *prev = &video->isp->isp_prev;
 
 	if (video->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
-		preview_set_inaddr(prev, buffer->isp_addr);
+		preview_set_inaddr(prev, buffer->dma);
 
 	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		preview_set_outaddr(prev, buffer->isp_addr);
+		preview_set_outaddr(prev, buffer->dma);
 
 	return 0;
 }
diff --git a/drivers/media/platform/omap3isp/ispqueue.c b/drivers/media/platform/omap3isp/ispqueue.c
deleted file mode 100644
index a5e65858e79..00000000000
--- a/drivers/media/platform/omap3isp/ispqueue.c
+++ /dev/null
@@ -1,1161 +0,0 @@
-/*
- * ispqueue.c
- *
- * TI OMAP3 ISP - Video buffers queue handling
- *
- * Copyright (C) 2010 Nokia Corporation
- *
- * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
- *	     Sakari Ailus <sakari.ailus@iki.fi>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- */
-
-#include <asm/cacheflush.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/poll.h>
-#include <linux/scatterlist.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-
-#include "ispqueue.h"
-
-/* -----------------------------------------------------------------------------
- * Video buffers management
- */
-
-/*
- * isp_video_buffer_cache_sync - Keep the buffers coherent between CPU and ISP
- *
- * The typical operation required here is Cache Invalidation across
- * the (user space) buffer address range. And this _must_ be done
- * at QBUF stage (and *only* at QBUF).
- *
- * We try to use optimal cache invalidation function:
- * - dmac_map_area:
- *    - used when the number of pages are _low_.
- *    - it becomes quite slow as the number of pages increase.
- *       - for 648x492 viewfinder (150 pages) it takes 1.3 ms.
- *       - for 5 Mpix buffer (2491 pages) it takes between 25-50 ms.
- *
- * - flush_cache_all:
- *    - used when the number of pages are _high_.
- *    - time taken in the range of 500-900 us.
- *    - has a higher penalty but, as whole dcache + icache is invalidated
- */
-/*
- * FIXME: dmac_inv_range crashes randomly on the user space buffer
- *        address. Fall back to flush_cache_all for now.
- */
-#define ISP_CACHE_FLUSH_PAGES_MAX       0
-
-static void isp_video_buffer_cache_sync(struct isp_video_buffer *buf)
-{
-	if (buf->skip_cache)
-		return;
-
-	if (buf->vbuf.m.userptr == 0 || buf->npages == 0 ||
-	    buf->npages > ISP_CACHE_FLUSH_PAGES_MAX)
-		flush_cache_all();
-	else {
-		dmac_map_area((void *)buf->vbuf.m.userptr, buf->vbuf.length,
-			      DMA_FROM_DEVICE);
-		outer_inv_range(buf->vbuf.m.userptr,
-				buf->vbuf.m.userptr + buf->vbuf.length);
-	}
-}
-
-/*
- * isp_video_buffer_lock_vma - Prevent VMAs from being unmapped
- *
- * Lock the VMAs underlying the given buffer into memory. This avoids the
- * userspace buffer mapping from being swapped out, making VIPT cache handling
- * easier.
- *
- * Note that the pages will not be freed as the buffers have been locked to
- * memory using by a call to get_user_pages(), but the userspace mapping could
- * still disappear if the VMAs are not locked. This is caused by the memory
- * management code trying to be as lock-less as possible, which results in the
- * userspace mapping manager not finding out that the pages are locked under
- * some conditions.
- */
-static int isp_video_buffer_lock_vma(struct isp_video_buffer *buf, int lock)
-{
-	struct vm_area_struct *vma;
-	unsigned long start;
-	unsigned long end;
-	int ret = 0;
-
-	if (buf->vbuf.memory == V4L2_MEMORY_MMAP)
-		return 0;
-
-	/* We can be called from workqueue context if the current task dies to
-	 * unlock the VMAs. In that case there's no current memory management
-	 * context so unlocking can't be performed, but the VMAs have been or
-	 * are getting destroyed anyway so it doesn't really matter.
-	 */
-	if (!current || !current->mm)
-		return lock ? -EINVAL : 0;
-
-	start = buf->vbuf.m.userptr;
-	end = buf->vbuf.m.userptr + buf->vbuf.length - 1;
-
-	down_write(&current->mm->mmap_sem);
-	spin_lock(&current->mm->page_table_lock);
-
-	do {
-		vma = find_vma(current->mm, start);
-		if (vma == NULL) {
-			ret = -EFAULT;
-			goto out;
-		}
-
-		if (lock)
-			vma->vm_flags |= VM_LOCKED;
-		else
-			vma->vm_flags &= ~VM_LOCKED;
-
-		start = vma->vm_end + 1;
-	} while (vma->vm_end < end);
-
-	if (lock)
-		buf->vm_flags |= VM_LOCKED;
-	else
-		buf->vm_flags &= ~VM_LOCKED;
-
-out:
-	spin_unlock(&current->mm->page_table_lock);
-	up_write(&current->mm->mmap_sem);
-	return ret;
-}
-
-/*
- * isp_video_buffer_sglist_kernel - Build a scatter list for a vmalloc'ed buffer
- *
- * Iterate over the vmalloc'ed area and create a scatter list entry for every
- * page.
- */
-static int isp_video_buffer_sglist_kernel(struct isp_video_buffer *buf)
-{
-	struct scatterlist *sglist;
-	unsigned int npages;
-	unsigned int i;
-	void *addr;
-
-	addr = buf->vaddr;
-	npages = PAGE_ALIGN(buf->vbuf.length) >> PAGE_SHIFT;
-
-	sglist = vmalloc(npages * sizeof(*sglist));
-	if (sglist == NULL)
-		return -ENOMEM;
-
-	sg_init_table(sglist, npages);
-
-	for (i = 0; i < npages; ++i, addr += PAGE_SIZE) {
-		struct page *page = vmalloc_to_page(addr);
-
-		if (page == NULL || PageHighMem(page)) {
-			vfree(sglist);
-			return -EINVAL;
-		}
-
-		sg_set_page(&sglist[i], page, PAGE_SIZE, 0);
-	}
-
-	buf->sglen = npages;
-	buf->sglist = sglist;
-
-	return 0;
-}
-
-/*
- * isp_video_buffer_sglist_user - Build a scatter list for a userspace buffer
- *
- * Walk the buffer pages list and create a 1:1 mapping to a scatter list.
- */
-static int isp_video_buffer_sglist_user(struct isp_video_buffer *buf)
-{
-	struct scatterlist *sglist;
-	unsigned int offset = buf->offset;
-	unsigned int i;
-
-	sglist = vmalloc(buf->npages * sizeof(*sglist));
-	if (sglist == NULL)
-		return -ENOMEM;
-
-	sg_init_table(sglist, buf->npages);
-
-	for (i = 0; i < buf->npages; ++i) {
-		if (PageHighMem(buf->pages[i])) {
-			vfree(sglist);
-			return -EINVAL;
-		}
-
-		sg_set_page(&sglist[i], buf->pages[i], PAGE_SIZE - offset,
-			    offset);
-		offset = 0;
-	}
-
-	buf->sglen = buf->npages;
-	buf->sglist = sglist;
-
-	return 0;
-}
-
-/*
- * isp_video_buffer_sglist_pfnmap - Build a scatter list for a VM_PFNMAP buffer
- *
- * Create a scatter list of physically contiguous pages starting at the buffer
- * memory physical address.
- */
-static int isp_video_buffer_sglist_pfnmap(struct isp_video_buffer *buf)
-{
-	struct scatterlist *sglist;
-	unsigned int offset = buf->offset;
-	unsigned long pfn = buf->paddr >> PAGE_SHIFT;
-	unsigned int i;
-
-	sglist = vmalloc(buf->npages * sizeof(*sglist));
-	if (sglist == NULL)
-		return -ENOMEM;
-
-	sg_init_table(sglist, buf->npages);
-
-	for (i = 0; i < buf->npages; ++i, ++pfn) {
-		sg_set_page(&sglist[i], pfn_to_page(pfn), PAGE_SIZE - offset,
-			    offset);
-		/* PFNMAP buffers will not get DMA-mapped, set the DMA address
-		 * manually.
-		 */
-		sg_dma_address(&sglist[i]) = (pfn << PAGE_SHIFT) + offset;
-		offset = 0;
-	}
-
-	buf->sglen = buf->npages;
-	buf->sglist = sglist;
-
-	return 0;
-}
-
-/*
- * isp_video_buffer_cleanup - Release pages for a userspace VMA.
- *
- * Release pages locked by a call isp_video_buffer_prepare_user and free the
- * pages table.
- */
-static void isp_video_buffer_cleanup(struct isp_video_buffer *buf)
-{
-	enum dma_data_direction direction;
-	unsigned int i;
-
-	if (buf->queue->ops->buffer_cleanup)
-		buf->queue->ops->buffer_cleanup(buf);
-
-	if (!(buf->vm_flags & VM_PFNMAP)) {
-		direction = buf->vbuf.type == V4L2_BUF_TYPE_VIDEO_CAPTURE
-			  ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-		dma_unmap_sg(buf->queue->dev, buf->sglist, buf->sglen,
-			     direction);
-	}
-
-	vfree(buf->sglist);
-	buf->sglist = NULL;
-	buf->sglen = 0;
-
-	if (buf->pages != NULL) {
-		isp_video_buffer_lock_vma(buf, 0);
-
-		for (i = 0; i < buf->npages; ++i)
-			page_cache_release(buf->pages[i]);
-
-		vfree(buf->pages);
-		buf->pages = NULL;
-	}
-
-	buf->npages = 0;
-	buf->skip_cache = false;
-}
-
-/*
- * isp_video_buffer_prepare_user - Pin userspace VMA pages to memory.
- *
- * This function creates a list of pages for a userspace VMA. The number of
- * pages is first computed based on the buffer size, and pages are then
- * retrieved by a call to get_user_pages.
- *
- * Pages are pinned to memory by get_user_pages, making them available for DMA
- * transfers. However, due to memory management optimization, it seems the
- * get_user_pages doesn't guarantee that the pinned pages will not be written
- * to swap and removed from the userspace mapping(s). When this happens, a page
- * fault can be generated when accessing those unmapped pages.
- *
- * If the fault is triggered by a page table walk caused by VIPT cache
- * management operations, the page fault handler might oops if the MM semaphore
- * is held, as it can't handle kernel page faults in that case. To fix that, a
- * fixup entry needs to be added to the cache management code, or the userspace
- * VMA must be locked to avoid removing pages from the userspace mapping in the
- * first place.
- *
- * If the number of pages retrieved is smaller than the number required by the
- * buffer size, the function returns -EFAULT.
- */
-static int isp_video_buffer_prepare_user(struct isp_video_buffer *buf)
-{
-	unsigned long data;
-	unsigned int first;
-	unsigned int last;
-	int ret;
-
-	data = buf->vbuf.m.userptr;
-	first = (data & PAGE_MASK) >> PAGE_SHIFT;
-	last = ((data + buf->vbuf.length - 1) & PAGE_MASK) >> PAGE_SHIFT;
-
-	buf->offset = data & ~PAGE_MASK;
-	buf->npages = last - first + 1;
-	buf->pages = vmalloc(buf->npages * sizeof(buf->pages[0]));
-	if (buf->pages == NULL)
-		return -ENOMEM;
-
-	down_read(&current->mm->mmap_sem);
-	ret = get_user_pages(current, current->mm, data & PAGE_MASK,
-			     buf->npages,
-			     buf->vbuf.type == V4L2_BUF_TYPE_VIDEO_CAPTURE, 0,
-			     buf->pages, NULL);
-	up_read(&current->mm->mmap_sem);
-
-	if (ret != buf->npages) {
-		buf->npages = ret < 0 ? 0 : ret;
-		isp_video_buffer_cleanup(buf);
-		return -EFAULT;
-	}
-
-	ret = isp_video_buffer_lock_vma(buf, 1);
-	if (ret < 0)
-		isp_video_buffer_cleanup(buf);
-
-	return ret;
-}
-
-/*
- * isp_video_buffer_prepare_pfnmap - Validate a VM_PFNMAP userspace buffer
- *
- * Userspace VM_PFNMAP buffers are supported only if they are contiguous in
- * memory and if they span a single VMA.
- *
- * Return 0 if the buffer is valid, or -EFAULT otherwise.
- */
-static int isp_video_buffer_prepare_pfnmap(struct isp_video_buffer *buf)
-{
-	struct vm_area_struct *vma;
-	unsigned long prev_pfn;
-	unsigned long this_pfn;
-	unsigned long start;
-	unsigned long end;
-	dma_addr_t pa = 0;
-	int ret = -EFAULT;
-
-	start = buf->vbuf.m.userptr;
-	end = buf->vbuf.m.userptr + buf->vbuf.length - 1;
-
-	buf->offset = start & ~PAGE_MASK;
-	buf->npages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
-	buf->pages = NULL;
-
-	down_read(&current->mm->mmap_sem);
-	vma = find_vma(current->mm, start);
-	if (vma == NULL || vma->vm_end < end)
-		goto done;
-
-	for (prev_pfn = 0; start <= end; start += PAGE_SIZE) {
-		ret = follow_pfn(vma, start, &this_pfn);
-		if (ret)
-			goto done;
-
-		if (prev_pfn == 0)
-			pa = this_pfn << PAGE_SHIFT;
-		else if (this_pfn != prev_pfn + 1) {
-			ret = -EFAULT;
-			goto done;
-		}
-
-		prev_pfn = this_pfn;
-	}
-
-	buf->paddr = pa + buf->offset;
-	ret = 0;
-
-done:
-	up_read(&current->mm->mmap_sem);
-	return ret;
-}
-
-/*
- * isp_video_buffer_prepare_vm_flags - Get VMA flags for a userspace address
- *
- * This function locates the VMAs for the buffer's userspace address and checks
- * that their flags match. The only flag that we need to care for at the moment
- * is VM_PFNMAP.
- *
- * The buffer vm_flags field is set to the first VMA flags.
- *
- * Return -EFAULT if no VMA can be found for part of the buffer, or if the VMAs
- * have incompatible flags.
- */
-static int isp_video_buffer_prepare_vm_flags(struct isp_video_buffer *buf)
-{
-	struct vm_area_struct *vma;
-	pgprot_t uninitialized_var(vm_page_prot);
-	unsigned long start;
-	unsigned long end;
-	int ret = -EFAULT;
-
-	start = buf->vbuf.m.userptr;
-	end = buf->vbuf.m.userptr + buf->vbuf.length - 1;
-
-	down_read(&current->mm->mmap_sem);
-
-	do {
-		vma = find_vma(current->mm, start);
-		if (vma == NULL)
-			goto done;
-
-		if (start == buf->vbuf.m.userptr) {
-			buf->vm_flags = vma->vm_flags;
-			vm_page_prot = vma->vm_page_prot;
-		}
-
-		if ((buf->vm_flags ^ vma->vm_flags) & VM_PFNMAP)
-			goto done;
-
-		if (vm_page_prot != vma->vm_page_prot)
-			goto done;
-
-		start = vma->vm_end + 1;
-	} while (vma->vm_end < end);
-
-	/* Skip cache management to enhance performances for non-cached or
-	 * write-combining buffers.
-	 */
-	if (vm_page_prot == pgprot_noncached(vm_page_prot) ||
-	    vm_page_prot == pgprot_writecombine(vm_page_prot))
-		buf->skip_cache = true;
-
-	ret = 0;
-
-done:
-	up_read(&current->mm->mmap_sem);
-	return ret;
-}
-
-/*
- * isp_video_buffer_prepare - Make a buffer ready for operation
- *
- * Preparing a buffer involves:
- *
- * - validating VMAs (userspace buffers only)
- * - locking pages and VMAs into memory (userspace buffers only)
- * - building page and scatter-gather lists
- * - mapping buffers for DMA operation
- * - performing driver-specific preparation
- *
- * The function must be called in userspace context with a valid mm context
- * (this excludes cleanup paths such as sys_close when the userspace process
- * segfaults).
- */
-static int isp_video_buffer_prepare(struct isp_video_buffer *buf)
-{
-	enum dma_data_direction direction;
-	int ret;
-
-	switch (buf->vbuf.memory) {
-	case V4L2_MEMORY_MMAP:
-		ret = isp_video_buffer_sglist_kernel(buf);
-		break;
-
-	case V4L2_MEMORY_USERPTR:
-		ret = isp_video_buffer_prepare_vm_flags(buf);
-		if (ret < 0)
-			return ret;
-
-		if (buf->vm_flags & VM_PFNMAP) {
-			ret = isp_video_buffer_prepare_pfnmap(buf);
-			if (ret < 0)
-				return ret;
-
-			ret = isp_video_buffer_sglist_pfnmap(buf);
-		} else {
-			ret = isp_video_buffer_prepare_user(buf);
-			if (ret < 0)
-				return ret;
-
-			ret = isp_video_buffer_sglist_user(buf);
-		}
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	if (ret < 0)
-		goto done;
-
-	if (!(buf->vm_flags & VM_PFNMAP)) {
-		direction = buf->vbuf.type == V4L2_BUF_TYPE_VIDEO_CAPTURE
-			  ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-		ret = dma_map_sg(buf->queue->dev, buf->sglist, buf->sglen,
-				 direction);
-		if (ret != buf->sglen) {
-			ret = -EFAULT;
-			goto done;
-		}
-	}
-
-	if (buf->queue->ops->buffer_prepare)
-		ret = buf->queue->ops->buffer_prepare(buf);
-
-done:
-	if (ret < 0) {
-		isp_video_buffer_cleanup(buf);
-		return ret;
-	}
-
-	return ret;
-}
-
-/*
- * isp_video_queue_query - Query the status of a given buffer
- *
- * Locking: must be called with the queue lock held.
- */
-static void isp_video_buffer_query(struct isp_video_buffer *buf,
-				   struct v4l2_buffer *vbuf)
-{
-	memcpy(vbuf, &buf->vbuf, sizeof(*vbuf));
-
-	if (buf->vma_use_count)
-		vbuf->flags |= V4L2_BUF_FLAG_MAPPED;
-
-	switch (buf->state) {
-	case ISP_BUF_STATE_ERROR:
-		vbuf->flags |= V4L2_BUF_FLAG_ERROR;
-		/* Fallthrough */
-	case ISP_BUF_STATE_DONE:
-		vbuf->flags |= V4L2_BUF_FLAG_DONE;
-		break;
-	case ISP_BUF_STATE_QUEUED:
-	case ISP_BUF_STATE_ACTIVE:
-		vbuf->flags |= V4L2_BUF_FLAG_QUEUED;
-		break;
-	case ISP_BUF_STATE_IDLE:
-	default:
-		break;
-	}
-}
-
-/*
- * isp_video_buffer_wait - Wait for a buffer to be ready
- *
- * In non-blocking mode, return immediately with 0 if the buffer is ready or
- * -EAGAIN if the buffer is in the QUEUED or ACTIVE state.
- *
- * In blocking mode, wait (interruptibly but with no timeout) on the buffer wait
- * queue using the same condition.
- */
-static int isp_video_buffer_wait(struct isp_video_buffer *buf, int nonblocking)
-{
-	if (nonblocking) {
-		return (buf->state != ISP_BUF_STATE_QUEUED &&
-			buf->state != ISP_BUF_STATE_ACTIVE)
-			? 0 : -EAGAIN;
-	}
-
-	return wait_event_interruptible(buf->wait,
-		buf->state != ISP_BUF_STATE_QUEUED &&
-		buf->state != ISP_BUF_STATE_ACTIVE);
-}
-
-/* -----------------------------------------------------------------------------
- * Queue management
- */
-
-/*
- * isp_video_queue_free - Free video buffers memory
- *
- * Buffers can only be freed if the queue isn't streaming and if no buffer is
- * mapped to userspace. Return -EBUSY if those conditions aren't satisfied.
- *
- * This function must be called with the queue lock held.
- */
-static int isp_video_queue_free(struct isp_video_queue *queue)
-{
-	unsigned int i;
-
-	if (queue->streaming)
-		return -EBUSY;
-
-	for (i = 0; i < queue->count; ++i) {
-		if (queue->buffers[i]->vma_use_count != 0)
-			return -EBUSY;
-	}
-
-	for (i = 0; i < queue->count; ++i) {
-		struct isp_video_buffer *buf = queue->buffers[i];
-
-		isp_video_buffer_cleanup(buf);
-
-		vfree(buf->vaddr);
-		buf->vaddr = NULL;
-
-		kfree(buf);
-		queue->buffers[i] = NULL;
-	}
-
-	INIT_LIST_HEAD(&queue->queue);
-	queue->count = 0;
-	return 0;
-}
-
-/*
- * isp_video_queue_alloc - Allocate video buffers memory
- *
- * This function must be called with the queue lock held.
- */
-static int isp_video_queue_alloc(struct isp_video_queue *queue,
-				 unsigned int nbuffers,
-				 unsigned int size, enum v4l2_memory memory)
-{
-	struct isp_video_buffer *buf;
-	unsigned int i;
-	void *mem;
-	int ret;
-
-	/* Start by freeing the buffers. */
-	ret = isp_video_queue_free(queue);
-	if (ret < 0)
-		return ret;
-
-	/* Bail out if no buffers should be allocated. */
-	if (nbuffers == 0)
-		return 0;
-
-	/* Initialize the allocated buffers. */
-	for (i = 0; i < nbuffers; ++i) {
-		buf = kzalloc(queue->bufsize, GFP_KERNEL);
-		if (buf == NULL)
-			break;
-
-		if (memory == V4L2_MEMORY_MMAP) {
-			/* Allocate video buffers memory for mmap mode. Align
-			 * the size to the page size.
-			 */
-			mem = vmalloc_32_user(PAGE_ALIGN(size));
-			if (mem == NULL) {
-				kfree(buf);
-				break;
-			}
-
-			buf->vbuf.m.offset = i * PAGE_ALIGN(size);
-			buf->vaddr = mem;
-		}
-
-		buf->vbuf.index = i;
-		buf->vbuf.length = size;
-		buf->vbuf.type = queue->type;
-		buf->vbuf.flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-		buf->vbuf.field = V4L2_FIELD_NONE;
-		buf->vbuf.memory = memory;
-
-		buf->queue = queue;
-		init_waitqueue_head(&buf->wait);
-
-		queue->buffers[i] = buf;
-	}
-
-	if (i == 0)
-		return -ENOMEM;
-
-	queue->count = i;
-	return nbuffers;
-}
-
-/**
- * omap3isp_video_queue_cleanup - Clean up the video buffers queue
- * @queue: Video buffers queue
- *
- * Free all allocated resources and clean up the video buffers queue. The queue
- * must not be busy (no ongoing video stream) and buffers must have been
- * unmapped.
- *
- * Return 0 on success or -EBUSY if the queue is busy or buffers haven't been
- * unmapped.
- */
-int omap3isp_video_queue_cleanup(struct isp_video_queue *queue)
-{
-	return isp_video_queue_free(queue);
-}
-
-/**
- * omap3isp_video_queue_init - Initialize the video buffers queue
- * @queue: Video buffers queue
- * @type: V4L2 buffer type (capture or output)
- * @ops: Driver-specific queue operations
- * @dev: Device used for DMA operations
- * @bufsize: Size of the driver-specific buffer structure
- *
- * Initialize the video buffers queue with the supplied parameters.
- *
- * The queue type must be one of V4L2_BUF_TYPE_VIDEO_CAPTURE or
- * V4L2_BUF_TYPE_VIDEO_OUTPUT. Other buffer types are not supported yet.
- *
- * Buffer objects will be allocated using the given buffer size to allow room
- * for driver-specific fields. Driver-specific buffer structures must start
- * with a struct isp_video_buffer field. Drivers with no driver-specific buffer
- * structure must pass the size of the isp_video_buffer structure in the bufsize
- * parameter.
- *
- * Return 0 on success.
- */
-int omap3isp_video_queue_init(struct isp_video_queue *queue,
-			      enum v4l2_buf_type type,
-			      const struct isp_video_queue_operations *ops,
-			      struct device *dev, unsigned int bufsize)
-{
-	INIT_LIST_HEAD(&queue->queue);
-	mutex_init(&queue->lock);
-	spin_lock_init(&queue->irqlock);
-
-	queue->type = type;
-	queue->ops = ops;
-	queue->dev = dev;
-	queue->bufsize = bufsize;
-
-	return 0;
-}
-
-/* -----------------------------------------------------------------------------
- * V4L2 operations
- */
-
-/**
- * omap3isp_video_queue_reqbufs - Allocate video buffers memory
- *
- * This function is intended to be used as a VIDIOC_REQBUFS ioctl handler. It
- * allocated video buffer objects and, for MMAP buffers, buffer memory.
- *
- * If the number of buffers is 0, all buffers are freed and the function returns
- * without performing any allocation.
- *
- * If the number of buffers is not 0, currently allocated buffers (if any) are
- * freed and the requested number of buffers are allocated. Depending on
- * driver-specific requirements and on memory availability, a number of buffer
- * smaller or bigger than requested can be allocated. This isn't considered as
- * an error.
- *
- * Return 0 on success or one of the following error codes:
- *
- * -EINVAL if the buffer type or index are invalid
- * -EBUSY if the queue is busy (streaming or buffers mapped)
- * -ENOMEM if the buffers can't be allocated due to an out-of-memory condition
- */
-int omap3isp_video_queue_reqbufs(struct isp_video_queue *queue,
-				 struct v4l2_requestbuffers *rb)
-{
-	unsigned int nbuffers = rb->count;
-	unsigned int size;
-	int ret;
-
-	if (rb->type != queue->type)
-		return -EINVAL;
-
-	queue->ops->queue_prepare(queue, &nbuffers, &size);
-	if (size == 0)
-		return -EINVAL;
-
-	nbuffers = min_t(unsigned int, nbuffers, ISP_VIDEO_MAX_BUFFERS);
-
-	mutex_lock(&queue->lock);
-
-	ret = isp_video_queue_alloc(queue, nbuffers, size, rb->memory);
-	if (ret < 0)
-		goto done;
-
-	rb->count = ret;
-	ret = 0;
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_querybuf - Query the status of a buffer in a queue
- *
- * This function is intended to be used as a VIDIOC_QUERYBUF ioctl handler. It
- * returns the status of a given video buffer.
- *
- * Return 0 on success or -EINVAL if the buffer type or index are invalid.
- */
-int omap3isp_video_queue_querybuf(struct isp_video_queue *queue,
-				  struct v4l2_buffer *vbuf)
-{
-	struct isp_video_buffer *buf;
-	int ret = 0;
-
-	if (vbuf->type != queue->type)
-		return -EINVAL;
-
-	mutex_lock(&queue->lock);
-
-	if (vbuf->index >= queue->count) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	buf = queue->buffers[vbuf->index];
-	isp_video_buffer_query(buf, vbuf);
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_qbuf - Queue a buffer
- *
- * This function is intended to be used as a VIDIOC_QBUF ioctl handler.
- *
- * The v4l2_buffer structure passed from userspace is first sanity tested. If
- * sane, the buffer is then processed and added to the main queue and, if the
- * queue is streaming, to the IRQ queue.
- *
- * Before being enqueued, USERPTR buffers are checked for address changes. If
- * the buffer has a different userspace address, the old memory area is unlocked
- * and the new memory area is locked.
- */
-int omap3isp_video_queue_qbuf(struct isp_video_queue *queue,
-			      struct v4l2_buffer *vbuf)
-{
-	struct isp_video_buffer *buf;
-	unsigned long flags;
-	int ret = -EINVAL;
-
-	if (vbuf->type != queue->type)
-		goto done;
-
-	mutex_lock(&queue->lock);
-
-	if (vbuf->index >= queue->count)
-		goto done;
-
-	buf = queue->buffers[vbuf->index];
-
-	if (vbuf->memory != buf->vbuf.memory)
-		goto done;
-
-	if (buf->state != ISP_BUF_STATE_IDLE)
-		goto done;
-
-	if (vbuf->memory == V4L2_MEMORY_USERPTR &&
-	    vbuf->length < buf->vbuf.length)
-		goto done;
-
-	if (vbuf->memory == V4L2_MEMORY_USERPTR &&
-	    vbuf->m.userptr != buf->vbuf.m.userptr) {
-		isp_video_buffer_cleanup(buf);
-		buf->vbuf.m.userptr = vbuf->m.userptr;
-		buf->prepared = 0;
-	}
-
-	if (!buf->prepared) {
-		ret = isp_video_buffer_prepare(buf);
-		if (ret < 0)
-			goto done;
-		buf->prepared = 1;
-	}
-
-	isp_video_buffer_cache_sync(buf);
-
-	buf->state = ISP_BUF_STATE_QUEUED;
-	list_add_tail(&buf->stream, &queue->queue);
-
-	if (queue->streaming) {
-		spin_lock_irqsave(&queue->irqlock, flags);
-		queue->ops->buffer_queue(buf);
-		spin_unlock_irqrestore(&queue->irqlock, flags);
-	}
-
-	ret = 0;
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_dqbuf - Dequeue a buffer
- *
- * This function is intended to be used as a VIDIOC_DQBUF ioctl handler.
- *
- * Wait until a buffer is ready to be dequeued, remove it from the queue and
- * copy its information to the v4l2_buffer structure.
- *
- * If the nonblocking argument is not zero and no buffer is ready, return
- * -EAGAIN immediately instead of waiting.
- *
- * If no buffer has been enqueued, or if the requested buffer type doesn't match
- * the queue type, return -EINVAL.
- */
-int omap3isp_video_queue_dqbuf(struct isp_video_queue *queue,
-			       struct v4l2_buffer *vbuf, int nonblocking)
-{
-	struct isp_video_buffer *buf;
-	int ret;
-
-	if (vbuf->type != queue->type)
-		return -EINVAL;
-
-	mutex_lock(&queue->lock);
-
-	if (list_empty(&queue->queue)) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	buf = list_first_entry(&queue->queue, struct isp_video_buffer, stream);
-	ret = isp_video_buffer_wait(buf, nonblocking);
-	if (ret < 0)
-		goto done;
-
-	list_del(&buf->stream);
-
-	isp_video_buffer_query(buf, vbuf);
-	buf->state = ISP_BUF_STATE_IDLE;
-	vbuf->flags &= ~V4L2_BUF_FLAG_QUEUED;
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_streamon - Start streaming
- *
- * This function is intended to be used as a VIDIOC_STREAMON ioctl handler. It
- * starts streaming on the queue and calls the buffer_queue operation for all
- * queued buffers.
- *
- * Return 0 on success.
- */
-int omap3isp_video_queue_streamon(struct isp_video_queue *queue)
-{
-	struct isp_video_buffer *buf;
-	unsigned long flags;
-
-	mutex_lock(&queue->lock);
-
-	if (queue->streaming)
-		goto done;
-
-	queue->streaming = 1;
-
-	spin_lock_irqsave(&queue->irqlock, flags);
-	list_for_each_entry(buf, &queue->queue, stream)
-		queue->ops->buffer_queue(buf);
-	spin_unlock_irqrestore(&queue->irqlock, flags);
-
-done:
-	mutex_unlock(&queue->lock);
-	return 0;
-}
-
-/**
- * omap3isp_video_queue_streamoff - Stop streaming
- *
- * This function is intended to be used as a VIDIOC_STREAMOFF ioctl handler. It
- * stops streaming on the queue and wakes up all the buffers.
- *
- * Drivers must stop the hardware and synchronize with interrupt handlers and/or
- * delayed works before calling this function to make sure no buffer will be
- * touched by the driver and/or hardware.
- */
-void omap3isp_video_queue_streamoff(struct isp_video_queue *queue)
-{
-	struct isp_video_buffer *buf;
-	unsigned long flags;
-	unsigned int i;
-
-	mutex_lock(&queue->lock);
-
-	if (!queue->streaming)
-		goto done;
-
-	queue->streaming = 0;
-
-	spin_lock_irqsave(&queue->irqlock, flags);
-	for (i = 0; i < queue->count; ++i) {
-		buf = queue->buffers[i];
-
-		if (buf->state == ISP_BUF_STATE_ACTIVE)
-			wake_up(&buf->wait);
-
-		buf->state = ISP_BUF_STATE_IDLE;
-	}
-	spin_unlock_irqrestore(&queue->irqlock, flags);
-
-	INIT_LIST_HEAD(&queue->queue);
-
-done:
-	mutex_unlock(&queue->lock);
-}
-
-/**
- * omap3isp_video_queue_discard_done - Discard all buffers marked as DONE
- *
- * This function is intended to be used with suspend/resume operations. It
- * discards all 'done' buffers as they would be too old to be requested after
- * resume.
- *
- * Drivers must stop the hardware and synchronize with interrupt handlers and/or
- * delayed works before calling this function to make sure no buffer will be
- * touched by the driver and/or hardware.
- */
-void omap3isp_video_queue_discard_done(struct isp_video_queue *queue)
-{
-	struct isp_video_buffer *buf;
-	unsigned int i;
-
-	mutex_lock(&queue->lock);
-
-	if (!queue->streaming)
-		goto done;
-
-	for (i = 0; i < queue->count; ++i) {
-		buf = queue->buffers[i];
-
-		if (buf->state == ISP_BUF_STATE_DONE)
-			buf->state = ISP_BUF_STATE_ERROR;
-	}
-
-done:
-	mutex_unlock(&queue->lock);
-}
-
-static void isp_video_queue_vm_open(struct vm_area_struct *vma)
-{
-	struct isp_video_buffer *buf = vma->vm_private_data;
-
-	buf->vma_use_count++;
-}
-
-static void isp_video_queue_vm_close(struct vm_area_struct *vma)
-{
-	struct isp_video_buffer *buf = vma->vm_private_data;
-
-	buf->vma_use_count--;
-}
-
-static const struct vm_operations_struct isp_video_queue_vm_ops = {
-	.open = isp_video_queue_vm_open,
-	.close = isp_video_queue_vm_close,
-};
-
-/**
- * omap3isp_video_queue_mmap - Map buffers to userspace
- *
- * This function is intended to be used as an mmap() file operation handler. It
- * maps a buffer to userspace based on the VMA offset.
- *
- * Only buffers of memory type MMAP are supported.
- */
-int omap3isp_video_queue_mmap(struct isp_video_queue *queue,
-			 struct vm_area_struct *vma)
-{
-	struct isp_video_buffer *uninitialized_var(buf);
-	unsigned long size;
-	unsigned int i;
-	int ret = 0;
-
-	mutex_lock(&queue->lock);
-
-	for (i = 0; i < queue->count; ++i) {
-		buf = queue->buffers[i];
-		if ((buf->vbuf.m.offset >> PAGE_SHIFT) == vma->vm_pgoff)
-			break;
-	}
-
-	if (i == queue->count) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	size = vma->vm_end - vma->vm_start;
-
-	if (buf->vbuf.memory != V4L2_MEMORY_MMAP ||
-	    size != PAGE_ALIGN(buf->vbuf.length)) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	ret = remap_vmalloc_range(vma, buf->vaddr, 0);
-	if (ret < 0)
-		goto done;
-
-	vma->vm_ops = &isp_video_queue_vm_ops;
-	vma->vm_private_data = buf;
-	isp_video_queue_vm_open(vma);
-
-done:
-	mutex_unlock(&queue->lock);
-	return ret;
-}
-
-/**
- * omap3isp_video_queue_poll - Poll video queue state
- *
- * This function is intended to be used as a poll() file operation handler. It
- * polls the state of the video buffer at the front of the queue and returns an
- * events mask.
- *
- * If no buffer is present at the front of the queue, POLLERR is returned.
- */
-unsigned int omap3isp_video_queue_poll(struct isp_video_queue *queue,
-				       struct file *file, poll_table *wait)
-{
-	struct isp_video_buffer *buf;
-	unsigned int mask = 0;
-
-	mutex_lock(&queue->lock);
-	if (list_empty(&queue->queue)) {
-		mask |= POLLERR;
-		goto done;
-	}
-	buf = list_first_entry(&queue->queue, struct isp_video_buffer, stream);
-
-	poll_wait(file, &buf->wait, wait);
-	if (buf->state == ISP_BUF_STATE_DONE ||
-	    buf->state == ISP_BUF_STATE_ERROR) {
-		if (queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-			mask |= POLLIN | POLLRDNORM;
-		else
-			mask |= POLLOUT | POLLWRNORM;
-	}
-
-done:
-	mutex_unlock(&queue->lock);
-	return mask;
-}
diff --git a/drivers/media/platform/omap3isp/ispqueue.h b/drivers/media/platform/omap3isp/ispqueue.h
deleted file mode 100644
index 3e048ad6564..00000000000
--- a/drivers/media/platform/omap3isp/ispqueue.h
+++ /dev/null
@@ -1,188 +0,0 @@
-/*
- * ispqueue.h
- *
- * TI OMAP3 ISP - Video buffers queue handling
- *
- * Copyright (C) 2010 Nokia Corporation
- *
- * Contacts: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
- *	     Sakari Ailus <sakari.ailus@iki.fi>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- */
-
-#ifndef OMAP3_ISP_QUEUE_H
-#define OMAP3_ISP_QUEUE_H
-
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/mm_types.h>
-#include <linux/mutex.h>
-#include <linux/videodev2.h>
-#include <linux/wait.h>
-
-struct isp_video_queue;
-struct page;
-struct scatterlist;
-
-#define ISP_VIDEO_MAX_BUFFERS		16
-
-/**
- * enum isp_video_buffer_state - ISP video buffer state
- * @ISP_BUF_STATE_IDLE:	The buffer is under userspace control (dequeued
- *	or not queued yet).
- * @ISP_BUF_STATE_QUEUED: The buffer has been queued but isn't used by the
- *	device yet.
- * @ISP_BUF_STATE_ACTIVE: The buffer is in use for an active video transfer.
- * @ISP_BUF_STATE_ERROR: The device is done with the buffer and an error
- *	occurred. For capture device the buffer likely contains corrupted data or
- *	no data at all.
- * @ISP_BUF_STATE_DONE: The device is done with the buffer and no error occurred.
- *	For capture devices the buffer contains valid data.
- */
-enum isp_video_buffer_state {
-	ISP_BUF_STATE_IDLE,
-	ISP_BUF_STATE_QUEUED,
-	ISP_BUF_STATE_ACTIVE,
-	ISP_BUF_STATE_ERROR,
-	ISP_BUF_STATE_DONE,
-};
-
-/**
- * struct isp_video_buffer - ISP video buffer
- * @vma_use_count: Number of times the buffer is mmap'ed to userspace
- * @stream: List head for insertion into main queue
- * @queue: ISP buffers queue this buffer belongs to
- * @prepared: Whether the buffer has been prepared
- * @skip_cache: Whether to skip cache management operations for this buffer
- * @vaddr: Memory virtual address (for kernel buffers)
- * @vm_flags: Buffer VMA flags (for userspace buffers)
- * @offset: Offset inside the first page (for userspace buffers)
- * @npages: Number of pages (for userspace buffers)
- * @pages: Pages table (for userspace non-VM_PFNMAP buffers)
- * @paddr: Memory physical address (for userspace VM_PFNMAP buffers)
- * @sglen: Number of elements in the scatter list (for non-VM_PFNMAP buffers)
- * @sglist: Scatter list (for non-VM_PFNMAP buffers)
- * @vbuf: V4L2 buffer
- * @irqlist: List head for insertion into IRQ queue
- * @state: Current buffer state
- * @wait: Wait queue to signal buffer completion
- */
-struct isp_video_buffer {
-	unsigned long vma_use_count;
-	struct list_head stream;
-	struct isp_video_queue *queue;
-	unsigned int prepared:1;
-	bool skip_cache;
-
-	/* For kernel buffers. */
-	void *vaddr;
-
-	/* For userspace buffers. */
-	vm_flags_t vm_flags;
-	unsigned long offset;
-	unsigned int npages;
-	struct page **pages;
-	dma_addr_t paddr;
-
-	/* For all buffers except VM_PFNMAP. */
-	unsigned int sglen;
-	struct scatterlist *sglist;
-
-	/* Touched by the interrupt handler. */
-	struct v4l2_buffer vbuf;
-	struct list_head irqlist;
-	enum isp_video_buffer_state state;
-	wait_queue_head_t wait;
-};
-
-#define to_isp_video_buffer(vb)	container_of(vb, struct isp_video_buffer, vb)
-
-/**
- * struct isp_video_queue_operations - Driver-specific operations
- * @queue_prepare: Called before allocating buffers. Drivers should clamp the
- *	number of buffers according to their requirements, and must return the
- *	buffer size in bytes.
- * @buffer_prepare: Called the first time a buffer is queued, or after changing
- *	the userspace memory address for a USERPTR buffer, with the queue lock
- *	held. Drivers should perform device-specific buffer preparation (such as
- *	mapping the buffer memory in an IOMMU). This operation is optional.
- * @buffer_queue: Called when a buffer is being added to the queue with the
- *	queue irqlock spinlock held.
- * @buffer_cleanup: Called before freeing buffers, or before changing the
- *	userspace memory address for a USERPTR buffer, with the queue lock held.
- *	Drivers must perform cleanup operations required to undo the
- *	buffer_prepare call. This operation is optional.
- */
-struct isp_video_queue_operations {
-	void (*queue_prepare)(struct isp_video_queue *queue,
-			      unsigned int *nbuffers, unsigned int *size);
-	int  (*buffer_prepare)(struct isp_video_buffer *buf);
-	void (*buffer_queue)(struct isp_video_buffer *buf);
-	void (*buffer_cleanup)(struct isp_video_buffer *buf);
-};
-
-/**
- * struct isp_video_queue - ISP video buffers queue
- * @type: Type of video buffers handled by this queue
- * @ops: Queue operations
- * @dev: Device used for DMA operations
- * @bufsize: Size of a driver-specific buffer object
- * @count: Number of currently allocated buffers
- * @buffers: ISP video buffers
- * @lock: Mutex to protect access to the buffers, main queue and state
- * @irqlock: Spinlock to protect access to the IRQ queue
- * @streaming: Queue state, indicates whether the queue is streaming
- * @queue: List of all queued buffers
- */
-struct isp_video_queue {
-	enum v4l2_buf_type type;
-	const struct isp_video_queue_operations *ops;
-	struct device *dev;
-	unsigned int bufsize;
-
-	unsigned int count;
-	struct isp_video_buffer *buffers[ISP_VIDEO_MAX_BUFFERS];
-	struct mutex lock;
-	spinlock_t irqlock;
-
-	unsigned int streaming:1;
-
-	struct list_head queue;
-};
-
-int omap3isp_video_queue_cleanup(struct isp_video_queue *queue);
-int omap3isp_video_queue_init(struct isp_video_queue *queue,
-			      enum v4l2_buf_type type,
-			      const struct isp_video_queue_operations *ops,
-			      struct device *dev, unsigned int bufsize);
-
-int omap3isp_video_queue_reqbufs(struct isp_video_queue *queue,
-				 struct v4l2_requestbuffers *rb);
-int omap3isp_video_queue_querybuf(struct isp_video_queue *queue,
-				  struct v4l2_buffer *vbuf);
-int omap3isp_video_queue_qbuf(struct isp_video_queue *queue,
-			      struct v4l2_buffer *vbuf);
-int omap3isp_video_queue_dqbuf(struct isp_video_queue *queue,
-			       struct v4l2_buffer *vbuf, int nonblocking);
-int omap3isp_video_queue_streamon(struct isp_video_queue *queue);
-void omap3isp_video_queue_streamoff(struct isp_video_queue *queue);
-void omap3isp_video_queue_discard_done(struct isp_video_queue *queue);
-int omap3isp_video_queue_mmap(struct isp_video_queue *queue,
-			      struct vm_area_struct *vma);
-unsigned int omap3isp_video_queue_poll(struct isp_video_queue *queue,
-				       struct file *file, poll_table *wait);
-
-#endif /* OMAP3_ISP_QUEUE_H */
diff --git a/drivers/media/platform/omap3isp/ispresizer.c b/drivers/media/platform/omap3isp/ispresizer.c
index 86369df81d7..6f077c2377d 100644
--- a/drivers/media/platform/omap3isp/ispresizer.c
+++ b/drivers/media/platform/omap3isp/ispresizer.c
@@ -1040,7 +1040,7 @@ static void resizer_isr_buffer(struct isp_res_device *res)
 	 */
 	buffer = omap3isp_video_buffer_next(&res->video_out);
 	if (buffer != NULL) {
-		resizer_set_outaddr(res, buffer->isp_addr);
+		resizer_set_outaddr(res, buffer->dma);
 		restart = 1;
 	}
 
@@ -1049,7 +1049,7 @@ static void resizer_isr_buffer(struct isp_res_device *res)
 	if (res->input == RESIZER_INPUT_MEMORY) {
 		buffer = omap3isp_video_buffer_next(&res->video_in);
 		if (buffer != NULL)
-			resizer_set_inaddr(res, buffer->isp_addr);
+			resizer_set_inaddr(res, buffer->dma);
 		pipe->state |= ISP_PIPELINE_IDLE_INPUT;
 	}
 
@@ -1101,7 +1101,7 @@ static int resizer_video_queue(struct isp_video *video,
 	struct isp_res_device *res = &video->isp->isp_res;
 
 	if (video->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
-		resizer_set_inaddr(res, buffer->isp_addr);
+		resizer_set_inaddr(res, buffer->dma);
 
 	/*
 	 * We now have a buffer queued on the output. Despite what the
@@ -1116,7 +1116,7 @@ static int resizer_video_queue(struct isp_video *video,
 	 * continuous mode or when starting the stream.
 	 */
 	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		resizer_set_outaddr(res, buffer->isp_addr);
+		resizer_set_outaddr(res, buffer->dma);
 
 	return 0;
 }
diff --git a/drivers/media/platform/omap3isp/ispstat.c b/drivers/media/platform/omap3isp/ispstat.c
index 5707f85c4cc..e6cbc1eaf4c 100644
--- a/drivers/media/platform/omap3isp/ispstat.c
+++ b/drivers/media/platform/omap3isp/ispstat.c
@@ -26,13 +26,12 @@
  */
 
 #include <linux/dma-mapping.h>
-#include <linux/omap-iommu.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
 #include "isp.h"
 
-#define IS_COHERENT_BUF(stat)	((stat)->dma_ch >= 0)
+#define ISP_STAT_USES_DMAENGINE(stat)	((stat)->dma_ch >= 0)
 
 /*
  * MAGIC_SIZE must always be the greatest common divisor of
@@ -77,21 +76,10 @@ static void __isp_stat_buf_sync_magic(struct ispstat *stat,
 					dma_addr_t, unsigned long, size_t,
 					enum dma_data_direction))
 {
-	struct device *dev = stat->isp->dev;
-	struct page *pg;
-	dma_addr_t dma_addr;
-	u32 offset;
-
-	/* Initial magic words */
-	pg = vmalloc_to_page(buf->virt_addr);
-	dma_addr = pfn_to_dma(dev, page_to_pfn(pg));
-	dma_sync(dev, dma_addr, 0, MAGIC_SIZE, dir);
-
-	/* Final magic words */
-	pg = vmalloc_to_page(buf->virt_addr + buf_size);
-	dma_addr = pfn_to_dma(dev, page_to_pfn(pg));
-	offset = ((u32)buf->virt_addr + buf_size) & ~PAGE_MASK;
-	dma_sync(dev, dma_addr, offset, MAGIC_SIZE, dir);
+	/* Sync the initial and final magic words. */
+	dma_sync(stat->isp->dev, buf->dma_addr, 0, MAGIC_SIZE, dir);
+	dma_sync(stat->isp->dev, buf->dma_addr + (buf_size & PAGE_MASK),
+		 buf_size & ~PAGE_MASK, MAGIC_SIZE, dir);
 }
 
 static void isp_stat_buf_sync_magic_for_device(struct ispstat *stat,
@@ -99,7 +87,7 @@ static void isp_stat_buf_sync_magic_for_device(struct ispstat *stat,
 					       u32 buf_size,
 					       enum dma_data_direction dir)
 {
-	if (IS_COHERENT_BUF(stat))
+	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
 	__isp_stat_buf_sync_magic(stat, buf, buf_size, dir,
@@ -111,7 +99,7 @@ static void isp_stat_buf_sync_magic_for_cpu(struct ispstat *stat,
 					    u32 buf_size,
 					    enum dma_data_direction dir)
 {
-	if (IS_COHERENT_BUF(stat))
+	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
 	__isp_stat_buf_sync_magic(stat, buf, buf_size, dir,
@@ -180,21 +168,21 @@ static void isp_stat_buf_insert_magic(struct ispstat *stat,
 static void isp_stat_buf_sync_for_device(struct ispstat *stat,
 					 struct ispstat_buffer *buf)
 {
-	if (IS_COHERENT_BUF(stat))
+	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
-	dma_sync_sg_for_device(stat->isp->dev, buf->iovm->sgt->sgl,
-			       buf->iovm->sgt->nents, DMA_FROM_DEVICE);
+	dma_sync_sg_for_device(stat->isp->dev, buf->sgt.sgl,
+			       buf->sgt.nents, DMA_FROM_DEVICE);
 }
 
 static void isp_stat_buf_sync_for_cpu(struct ispstat *stat,
 				      struct ispstat_buffer *buf)
 {
-	if (IS_COHERENT_BUF(stat))
+	if (ISP_STAT_USES_DMAENGINE(stat))
 		return;
 
-	dma_sync_sg_for_cpu(stat->isp->dev, buf->iovm->sgt->sgl,
-			    buf->iovm->sgt->nents, DMA_FROM_DEVICE);
+	dma_sync_sg_for_cpu(stat->isp->dev, buf->sgt.sgl,
+			    buf->sgt.nents, DMA_FROM_DEVICE);
 }
 
 static void isp_stat_buf_clear(struct ispstat *stat)
@@ -354,29 +342,21 @@ static struct ispstat_buffer *isp_stat_buf_get(struct ispstat *stat,
 
 static void isp_stat_bufs_free(struct ispstat *stat)
 {
-	struct isp_device *isp = stat->isp;
-	int i;
+	struct device *dev = ISP_STAT_USES_DMAENGINE(stat)
+			   ? NULL : stat->isp->dev;
+	unsigned int i;
 
 	for (i = 0; i < STAT_MAX_BUFS; i++) {
 		struct ispstat_buffer *buf = &stat->buf[i];
 
-		if (!IS_COHERENT_BUF(stat)) {
-			if (IS_ERR_OR_NULL((void *)buf->iommu_addr))
-				continue;
-			if (buf->iovm)
-				dma_unmap_sg(isp->dev, buf->iovm->sgt->sgl,
-					     buf->iovm->sgt->nents,
-					     DMA_FROM_DEVICE);
-			omap_iommu_vfree(isp->domain, isp->dev,
-							buf->iommu_addr);
-		} else {
-			if (!buf->virt_addr)
-				continue;
-			dma_free_coherent(stat->isp->dev, stat->buf_alloc_size,
-					  buf->virt_addr, buf->dma_addr);
-		}
-		buf->iommu_addr = 0;
-		buf->iovm = NULL;
+		if (!buf->virt_addr)
+			continue;
+
+		sg_free_table(&buf->sgt);
+
+		dma_free_coherent(dev, stat->buf_alloc_size, buf->virt_addr,
+				  buf->dma_addr);
+
 		buf->dma_addr = 0;
 		buf->virt_addr = NULL;
 		buf->empty = 1;
@@ -389,83 +369,51 @@ static void isp_stat_bufs_free(struct ispstat *stat)
 	stat->active_buf = NULL;
 }
 
-static int isp_stat_bufs_alloc_iommu(struct ispstat *stat, unsigned int size)
-{
-	struct isp_device *isp = stat->isp;
-	int i;
-
-	stat->buf_alloc_size = size;
-
-	for (i = 0; i < STAT_MAX_BUFS; i++) {
-		struct ispstat_buffer *buf = &stat->buf[i];
-		struct iovm_struct *iovm;
-
-		WARN_ON(buf->dma_addr);
-		buf->iommu_addr = omap_iommu_vmalloc(isp->domain, isp->dev, 0,
-							size, IOMMU_FLAG);
-		if (IS_ERR((void *)buf->iommu_addr)) {
-			dev_err(stat->isp->dev,
-				 "%s: Can't acquire memory for "
-				 "buffer %d\n", stat->subdev.name, i);
-			isp_stat_bufs_free(stat);
-			return -ENOMEM;
-		}
-
-		iovm = omap_find_iovm_area(isp->dev, buf->iommu_addr);
-		if (!iovm ||
-		    !dma_map_sg(isp->dev, iovm->sgt->sgl, iovm->sgt->nents,
-				DMA_FROM_DEVICE)) {
-			isp_stat_bufs_free(stat);
-			return -ENOMEM;
-		}
-		buf->iovm = iovm;
-
-		buf->virt_addr = omap_da_to_va(stat->isp->dev,
-					  (u32)buf->iommu_addr);
-		buf->empty = 1;
-		dev_dbg(stat->isp->dev, "%s: buffer[%d] allocated."
-			"iommu_addr=0x%08lx virt_addr=0x%08lx",
-			stat->subdev.name, i, buf->iommu_addr,
-			(unsigned long)buf->virt_addr);
-	}
-
-	return 0;
-}
-
-static int isp_stat_bufs_alloc_dma(struct ispstat *stat, unsigned int size)
+static int isp_stat_bufs_alloc_one(struct device *dev,
+				   struct ispstat_buffer *buf,
+				   unsigned int size)
 {
-	int i;
-
-	stat->buf_alloc_size = size;
-
-	for (i = 0; i < STAT_MAX_BUFS; i++) {
-		struct ispstat_buffer *buf = &stat->buf[i];
-
-		WARN_ON(buf->iommu_addr);
-		buf->virt_addr = dma_alloc_coherent(stat->isp->dev, size,
-					&buf->dma_addr, GFP_KERNEL | GFP_DMA);
+	int ret;
 
-		if (!buf->virt_addr || !buf->dma_addr) {
-			dev_info(stat->isp->dev,
-				 "%s: Can't acquire memory for "
-				 "DMA buffer %d\n", stat->subdev.name, i);
-			isp_stat_bufs_free(stat);
-			return -ENOMEM;
-		}
-		buf->empty = 1;
+	buf->virt_addr = dma_alloc_coherent(dev, size, &buf->dma_addr,
+					    GFP_KERNEL | GFP_DMA);
+	if (!buf->virt_addr)
+		return -ENOMEM;
 
-		dev_dbg(stat->isp->dev, "%s: buffer[%d] allocated."
-			"dma_addr=0x%08lx virt_addr=0x%08lx\n",
-			stat->subdev.name, i, (unsigned long)buf->dma_addr,
-			(unsigned long)buf->virt_addr);
+	ret = dma_get_sgtable(dev, &buf->sgt, buf->virt_addr, buf->dma_addr,
+			      size);
+	if (ret < 0) {
+		dma_free_coherent(dev, size, buf->virt_addr, buf->dma_addr);
+		buf->virt_addr = NULL;
+		buf->dma_addr = 0;
+		return ret;
 	}
 
 	return 0;
 }
 
+/*
+ * The device passed to the DMA API depends on whether the statistics block uses
+ * ISP DMA, external DMA or PIO to transfer data.
+ *
+ * The first case (for the AEWB and AF engines) passes the ISP device, resulting
+ * in the DMA buffers being mapped through the ISP IOMMU.
+ *
+ * The second case (for the histogram engine) should pass the DMA engine device.
+ * As that device isn't accessible through the OMAP DMA engine API the driver
+ * passes NULL instead, resulting in the buffers being mapped directly as
+ * physical pages.
+ *
+ * The third case (for the histogram engine) doesn't require any mapping. The
+ * buffers could be allocated with kmalloc/vmalloc, but we still use
+ * dma_alloc_coherent() for consistency purpose.
+ */
 static int isp_stat_bufs_alloc(struct ispstat *stat, u32 size)
 {
+	struct device *dev = ISP_STAT_USES_DMAENGINE(stat)
+			   ? NULL : stat->isp->dev;
 	unsigned long flags;
+	unsigned int i;
 
 	spin_lock_irqsave(&stat->isp->stat_lock, flags);
 
@@ -489,10 +437,31 @@ static int isp_stat_bufs_alloc(struct ispstat *stat, u32 size)
 
 	isp_stat_bufs_free(stat);
 
-	if (IS_COHERENT_BUF(stat))
-		return isp_stat_bufs_alloc_dma(stat, size);
-	else
-		return isp_stat_bufs_alloc_iommu(stat, size);
+	stat->buf_alloc_size = size;
+
+	for (i = 0; i < STAT_MAX_BUFS; i++) {
+		struct ispstat_buffer *buf = &stat->buf[i];
+		int ret;
+
+		ret = isp_stat_bufs_alloc_one(dev, buf, size);
+		if (ret < 0) {
+			dev_err(stat->isp->dev,
+				"%s: Failed to allocate DMA buffer %u\n",
+				stat->subdev.name, i);
+			isp_stat_bufs_free(stat);
+			return ret;
+		}
+
+		buf->empty = 1;
+
+		dev_dbg(stat->isp->dev,
+			"%s: buffer[%u] allocated. dma=0x%08lx virt=0x%08lx",
+			stat->subdev.name, i,
+			(unsigned long)buf->dma_addr,
+			(unsigned long)buf->virt_addr);
+	}
+
+	return 0;
 }
 
 static void isp_stat_queue_event(struct ispstat *stat, int err)
diff --git a/drivers/media/platform/omap3isp/ispstat.h b/drivers/media/platform/omap3isp/ispstat.h
index 9a047c929b9..58d6ac7cb66 100644
--- a/drivers/media/platform/omap3isp/ispstat.h
+++ b/drivers/media/platform/omap3isp/ispstat.h
@@ -46,8 +46,7 @@
 struct ispstat;
 
 struct ispstat_buffer {
-	unsigned long iommu_addr;
-	struct iovm_struct *iovm;
+	struct sg_table sgt;
 	void *virt_addr;
 	dma_addr_t dma_addr;
 	struct timespec ts;
diff --git a/drivers/media/platform/omap3isp/ispvideo.c b/drivers/media/platform/omap3isp/ispvideo.c
index 85b4036ba5e..e36bac26476 100644
--- a/drivers/media/platform/omap3isp/ispvideo.c
+++ b/drivers/media/platform/omap3isp/ispvideo.c
@@ -27,7 +27,6 @@
 #include <linux/clk.h>
 #include <linux/mm.h>
 #include <linux/module.h>
-#include <linux/omap-iommu.h>
 #include <linux/pagemap.h>
 #include <linux/scatterlist.h>
 #include <linux/sched.h>
@@ -35,6 +34,7 @@
 #include <linux/vmalloc.h>
 #include <media/v4l2-dev.h>
 #include <media/v4l2-ioctl.h>
+#include <media/videobuf2-dma-contig.h>
 
 #include "ispvideo.h"
 #include "isp.h"
@@ -326,90 +326,36 @@ isp_video_check_format(struct isp_video *video, struct isp_video_fh *vfh)
 }
 
 /* -----------------------------------------------------------------------------
- * IOMMU management
- */
-
-#define IOMMU_FLAG	(IOVMF_ENDIAN_LITTLE | IOVMF_ELSZ_8)
-
-/*
- * ispmmu_vmap - Wrapper for Virtual memory mapping of a scatter gather list
- * @isp: Device pointer specific to the OMAP3 ISP.
- * @sglist: Pointer to source Scatter gather list to allocate.
- * @sglen: Number of elements of the scatter-gatter list.
- *
- * Returns a resulting mapped device address by the ISP MMU, or -ENOMEM if
- * we ran out of memory.
- */
-static dma_addr_t
-ispmmu_vmap(struct isp_device *isp, const struct scatterlist *sglist, int sglen)
-{
-	struct sg_table *sgt;
-	u32 da;
-
-	sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
-	if (sgt == NULL)
-		return -ENOMEM;
-
-	sgt->sgl = (struct scatterlist *)sglist;
-	sgt->nents = sglen;
-	sgt->orig_nents = sglen;
-
-	da = omap_iommu_vmap(isp->domain, isp->dev, 0, sgt, IOMMU_FLAG);
-	if (IS_ERR_VALUE(da))
-		kfree(sgt);
-
-	return da;
-}
-
-/*
- * ispmmu_vunmap - Unmap a device address from the ISP MMU
- * @isp: Device pointer specific to the OMAP3 ISP.
- * @da: Device address generated from a ispmmu_vmap call.
- */
-static void ispmmu_vunmap(struct isp_device *isp, dma_addr_t da)
-{
-	struct sg_table *sgt;
-
-	sgt = omap_iommu_vunmap(isp->domain, isp->dev, (u32)da);
-	kfree(sgt);
-}
-
-/* -----------------------------------------------------------------------------
  * Video queue operations
  */
 
-static void isp_video_queue_prepare(struct isp_video_queue *queue,
-				    unsigned int *nbuffers, unsigned int *size)
+static int isp_video_queue_setup(struct vb2_queue *queue,
+				 const struct v4l2_format *fmt,
+				 unsigned int *count, unsigned int *num_planes,
+				 unsigned int sizes[], void *alloc_ctxs[])
 {
-	struct isp_video_fh *vfh =
-		container_of(queue, struct isp_video_fh, queue);
+	struct isp_video_fh *vfh = vb2_get_drv_priv(queue);
 	struct isp_video *video = vfh->video;
 
-	*size = vfh->format.fmt.pix.sizeimage;
-	if (*size == 0)
-		return;
+	*num_planes = 1;
 
-	*nbuffers = min(*nbuffers, video->capture_mem / PAGE_ALIGN(*size));
-}
+	sizes[0] = vfh->format.fmt.pix.sizeimage;
+	if (sizes[0] == 0)
+		return -EINVAL;
 
-static void isp_video_buffer_cleanup(struct isp_video_buffer *buf)
-{
-	struct isp_video_fh *vfh = isp_video_queue_to_isp_video_fh(buf->queue);
-	struct isp_buffer *buffer = to_isp_buffer(buf);
-	struct isp_video *video = vfh->video;
+	alloc_ctxs[0] = video->alloc_ctx;
 
-	if (buffer->isp_addr) {
-		ispmmu_vunmap(video->isp, buffer->isp_addr);
-		buffer->isp_addr = 0;
-	}
+	*count = min(*count, video->capture_mem / PAGE_ALIGN(sizes[0]));
+
+	return 0;
 }
 
-static int isp_video_buffer_prepare(struct isp_video_buffer *buf)
+static int isp_video_buffer_prepare(struct vb2_buffer *buf)
 {
-	struct isp_video_fh *vfh = isp_video_queue_to_isp_video_fh(buf->queue);
+	struct isp_video_fh *vfh = vb2_get_drv_priv(buf->vb2_queue);
 	struct isp_buffer *buffer = to_isp_buffer(buf);
 	struct isp_video *video = vfh->video;
-	unsigned long addr;
+	dma_addr_t addr;
 
 	/* Refuse to prepare the buffer is the video node has registered an
 	 * error. We don't need to take any lock here as the operation is
@@ -420,19 +366,16 @@ static int isp_video_buffer_prepare(struct isp_video_buffer *buf)
 	if (unlikely(video->error))
 		return -EIO;
 
-	addr = ispmmu_vmap(video->isp, buf->sglist, buf->sglen);
-	if (IS_ERR_VALUE(addr))
-		return -EIO;
-
+	addr = vb2_dma_contig_plane_dma_addr(buf, 0);
 	if (!IS_ALIGNED(addr, 32)) {
-		dev_dbg(video->isp->dev, "Buffer address must be "
-			"aligned to 32 bytes boundary.\n");
-		ispmmu_vunmap(video->isp, buffer->isp_addr);
+		dev_dbg(video->isp->dev,
+			"Buffer address must be aligned to 32 bytes boundary.\n");
 		return -EINVAL;
 	}
 
-	buf->vbuf.bytesused = vfh->format.fmt.pix.sizeimage;
-	buffer->isp_addr = addr;
+	vb2_set_plane_payload(&buffer->vb, 0, vfh->format.fmt.pix.sizeimage);
+	buffer->dma = addr;
+
 	return 0;
 }
 
@@ -445,9 +388,9 @@ static int isp_video_buffer_prepare(struct isp_video_buffer *buf)
  * If the pipeline is busy, it will be restarted in the output module interrupt
  * handler.
  */
-static void isp_video_buffer_queue(struct isp_video_buffer *buf)
+static void isp_video_buffer_queue(struct vb2_buffer *buf)
 {
-	struct isp_video_fh *vfh = isp_video_queue_to_isp_video_fh(buf->queue);
+	struct isp_video_fh *vfh = vb2_get_drv_priv(buf->vb2_queue);
 	struct isp_buffer *buffer = to_isp_buffer(buf);
 	struct isp_video *video = vfh->video;
 	struct isp_pipeline *pipe = to_isp_pipeline(&video->video.entity);
@@ -456,14 +399,18 @@ static void isp_video_buffer_queue(struct isp_video_buffer *buf)
 	unsigned int empty;
 	unsigned int start;
 
+	spin_lock_irqsave(&video->irqlock, flags);
+
 	if (unlikely(video->error)) {
-		buf->state = ISP_BUF_STATE_ERROR;
-		wake_up(&buf->wait);
+		vb2_buffer_done(&buffer->vb, VB2_BUF_STATE_ERROR);
+		spin_unlock_irqrestore(&video->irqlock, flags);
 		return;
 	}
 
 	empty = list_empty(&video->dmaqueue);
-	list_add_tail(&buffer->buffer.irqlist, &video->dmaqueue);
+	list_add_tail(&buffer->irqlist, &video->dmaqueue);
+
+	spin_unlock_irqrestore(&video->irqlock, flags);
 
 	if (empty) {
 		if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
@@ -487,23 +434,22 @@ static void isp_video_buffer_queue(struct isp_video_buffer *buf)
 	}
 }
 
-static const struct isp_video_queue_operations isp_video_queue_ops = {
-	.queue_prepare = &isp_video_queue_prepare,
-	.buffer_prepare = &isp_video_buffer_prepare,
-	.buffer_queue = &isp_video_buffer_queue,
-	.buffer_cleanup = &isp_video_buffer_cleanup,
+static const struct vb2_ops isp_video_queue_ops = {
+	.queue_setup = isp_video_queue_setup,
+	.buf_prepare = isp_video_buffer_prepare,
+	.buf_queue = isp_video_buffer_queue,
 };
 
 /*
  * omap3isp_video_buffer_next - Complete the current buffer and return the next
  * @video: ISP video object
  *
- * Remove the current video buffer from the DMA queue and fill its timestamp,
- * field count and state fields before waking up its completion handler.
+ * Remove the current video buffer from the DMA queue and fill its timestamp and
+ * field count before handing it back to videobuf2.
  *
- * For capture video nodes the buffer state is set to ISP_BUF_STATE_DONE if no
- * error has been flagged in the pipeline, or to ISP_BUF_STATE_ERROR otherwise.
- * For video output nodes the buffer state is always set to ISP_BUF_STATE_DONE.
+ * For capture video nodes the buffer state is set to VB2_BUF_STATE_DONE if no
+ * error has been flagged in the pipeline, or to VB2_BUF_STATE_ERROR otherwise.
+ * For video output nodes the buffer state is always set to VB2_BUF_STATE_DONE.
  *
  * The DMA queue is expected to contain at least one buffer.
  *
@@ -513,26 +459,25 @@ static const struct isp_video_queue_operations isp_video_queue_ops = {
 struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
 {
 	struct isp_pipeline *pipe = to_isp_pipeline(&video->video.entity);
-	struct isp_video_queue *queue = video->queue;
 	enum isp_pipeline_state state;
-	struct isp_video_buffer *buf;
+	struct isp_buffer *buf;
 	unsigned long flags;
 	struct timespec ts;
 
-	spin_lock_irqsave(&queue->irqlock, flags);
+	spin_lock_irqsave(&video->irqlock, flags);
 	if (WARN_ON(list_empty(&video->dmaqueue))) {
-		spin_unlock_irqrestore(&queue->irqlock, flags);
+		spin_unlock_irqrestore(&video->irqlock, flags);
 		return NULL;
 	}
 
-	buf = list_first_entry(&video->dmaqueue, struct isp_video_buffer,
+	buf = list_first_entry(&video->dmaqueue, struct isp_buffer,
 			       irqlist);
 	list_del(&buf->irqlist);
-	spin_unlock_irqrestore(&queue->irqlock, flags);
+	spin_unlock_irqrestore(&video->irqlock, flags);
 
 	ktime_get_ts(&ts);
-	buf->vbuf.timestamp.tv_sec = ts.tv_sec;
-	buf->vbuf.timestamp.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+	buf->vb.v4l2_buf.timestamp.tv_sec = ts.tv_sec;
+	buf->vb.v4l2_buf.timestamp.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
 
 	/* Do frame number propagation only if this is the output video node.
 	 * Frame number either comes from the CSI receivers or it gets
@@ -541,22 +486,27 @@ struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
 	 * first, so the input number might lag behind by 1 in some cases.
 	 */
 	if (video == pipe->output && !pipe->do_propagation)
-		buf->vbuf.sequence = atomic_inc_return(&pipe->frame_number);
+		buf->vb.v4l2_buf.sequence =
+			atomic_inc_return(&pipe->frame_number);
 	else
-		buf->vbuf.sequence = atomic_read(&pipe->frame_number);
+		buf->vb.v4l2_buf.sequence = atomic_read(&pipe->frame_number);
 
 	/* Report pipeline errors to userspace on the capture device side. */
-	if (queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->error) {
-		buf->state = ISP_BUF_STATE_ERROR;
+	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->error) {
+		state = VB2_BUF_STATE_ERROR;
 		pipe->error = false;
 	} else {
-		buf->state = ISP_BUF_STATE_DONE;
+		state = VB2_BUF_STATE_DONE;
 	}
 
-	wake_up(&buf->wait);
+	vb2_buffer_done(&buf->vb, state);
+
+	spin_lock_irqsave(&video->irqlock, flags);
 
 	if (list_empty(&video->dmaqueue)) {
-		if (queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		spin_unlock_irqrestore(&video->irqlock, flags);
+
+		if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
 			state = ISP_PIPELINE_QUEUE_OUTPUT
 			      | ISP_PIPELINE_STREAM;
 		else
@@ -571,16 +521,19 @@ struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
 		return NULL;
 	}
 
-	if (queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->input != NULL) {
-		spin_lock_irqsave(&pipe->lock, flags);
+	if (video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE && pipe->input != NULL) {
+		spin_lock(&pipe->lock);
 		pipe->state &= ~ISP_PIPELINE_STREAM;
-		spin_unlock_irqrestore(&pipe->lock, flags);
+		spin_unlock(&pipe->lock);
 	}
 
-	buf = list_first_entry(&video->dmaqueue, struct isp_video_buffer,
+	buf = list_first_entry(&video->dmaqueue, struct isp_buffer,
 			       irqlist);
-	buf->state = ISP_BUF_STATE_ACTIVE;
-	return to_isp_buffer(buf);
+	buf->vb.state = VB2_BUF_STATE_ACTIVE;
+
+	spin_unlock_irqrestore(&video->irqlock, flags);
+
+	return buf;
 }
 
 /*
@@ -592,25 +545,22 @@ struct isp_buffer *omap3isp_video_buffer_next(struct isp_video *video)
  */
 void omap3isp_video_cancel_stream(struct isp_video *video)
 {
-	struct isp_video_queue *queue = video->queue;
 	unsigned long flags;
 
-	spin_lock_irqsave(&queue->irqlock, flags);
+	spin_lock_irqsave(&video->irqlock, flags);
 
 	while (!list_empty(&video->dmaqueue)) {
-		struct isp_video_buffer *buf;
+		struct isp_buffer *buf;
 
 		buf = list_first_entry(&video->dmaqueue,
-				       struct isp_video_buffer, irqlist);
+				       struct isp_buffer, irqlist);
 		list_del(&buf->irqlist);
-
-		buf->state = ISP_BUF_STATE_ERROR;
-		wake_up(&buf->wait);
+		vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR);
 	}
 
 	video->error = true;
 
-	spin_unlock_irqrestore(&queue->irqlock, flags);
+	spin_unlock_irqrestore(&video->irqlock, flags);
 }
 
 /*
@@ -627,12 +577,15 @@ void omap3isp_video_resume(struct isp_video *video, int continuous)
 {
 	struct isp_buffer *buf = NULL;
 
-	if (continuous && video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
-		omap3isp_video_queue_discard_done(video->queue);
+	if (continuous && video->type == V4L2_BUF_TYPE_VIDEO_CAPTURE) {
+		mutex_lock(&video->queue_lock);
+		vb2_discard_done(video->queue);
+		mutex_unlock(&video->queue_lock);
+	}
 
 	if (!list_empty(&video->dmaqueue)) {
 		buf = list_first_entry(&video->dmaqueue,
-				       struct isp_buffer, buffer.irqlist);
+				       struct isp_buffer, irqlist);
 		video->ops->queue(video, buf);
 		video->dmaqueue_flags |= ISP_VIDEO_DMAQUEUE_QUEUED;
 	} else {
@@ -840,33 +793,56 @@ static int
 isp_video_reqbufs(struct file *file, void *fh, struct v4l2_requestbuffers *rb)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(fh);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
 
-	return omap3isp_video_queue_reqbufs(&vfh->queue, rb);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_reqbufs(&vfh->queue, rb);
+	mutex_unlock(&video->queue_lock);
+
+	return ret;
 }
 
 static int
 isp_video_querybuf(struct file *file, void *fh, struct v4l2_buffer *b)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(fh);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
+
+	mutex_lock(&video->queue_lock);
+	ret = vb2_querybuf(&vfh->queue, b);
+	mutex_unlock(&video->queue_lock);
 
-	return omap3isp_video_queue_querybuf(&vfh->queue, b);
+	return ret;
 }
 
 static int
 isp_video_qbuf(struct file *file, void *fh, struct v4l2_buffer *b)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(fh);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
 
-	return omap3isp_video_queue_qbuf(&vfh->queue, b);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_qbuf(&vfh->queue, b);
+	mutex_unlock(&video->queue_lock);
+
+	return ret;
 }
 
 static int
 isp_video_dqbuf(struct file *file, void *fh, struct v4l2_buffer *b)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(fh);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
+
+	mutex_lock(&video->queue_lock);
+	ret = vb2_dqbuf(&vfh->queue, b, file->f_flags & O_NONBLOCK);
+	mutex_unlock(&video->queue_lock);
 
-	return omap3isp_video_queue_dqbuf(&vfh->queue, b,
-					  file->f_flags & O_NONBLOCK);
+	return ret;
 }
 
 static int isp_video_check_external_subdevs(struct isp_video *video,
@@ -1006,11 +982,6 @@ isp_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 
 	mutex_lock(&video->stream_lock);
 
-	if (video->streaming) {
-		mutex_unlock(&video->stream_lock);
-		return -EBUSY;
-	}
-
 	/* Start streaming on the pipeline. No link touching an entity in the
 	 * pipeline can be activated or deactivated once streaming is started.
 	 */
@@ -1069,7 +1040,9 @@ isp_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 	INIT_LIST_HEAD(&video->dmaqueue);
 	atomic_set(&pipe->frame_number, -1);
 
-	ret = omap3isp_video_queue_streamon(&vfh->queue);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_streamon(&vfh->queue, type);
+	mutex_unlock(&video->queue_lock);
 	if (ret < 0)
 		goto err_check_format;
 
@@ -1082,19 +1055,19 @@ isp_video_streamon(struct file *file, void *fh, enum v4l2_buf_type type)
 					      ISP_PIPELINE_STREAM_CONTINUOUS);
 		if (ret < 0)
 			goto err_set_stream;
-		spin_lock_irqsave(&video->queue->irqlock, flags);
+		spin_lock_irqsave(&video->irqlock, flags);
 		if (list_empty(&video->dmaqueue))
 			video->dmaqueue_flags |= ISP_VIDEO_DMAQUEUE_UNDERRUN;
-		spin_unlock_irqrestore(&video->queue->irqlock, flags);
+		spin_unlock_irqrestore(&video->irqlock, flags);
 	}
 
-	video->streaming = 1;
-
 	mutex_unlock(&video->stream_lock);
 	return 0;
 
 err_set_stream:
-	omap3isp_video_queue_streamoff(&vfh->queue);
+	mutex_lock(&video->queue_lock);
+	vb2_streamoff(&vfh->queue, type);
+	mutex_unlock(&video->queue_lock);
 err_check_format:
 	media_entity_pipeline_stop(&video->video.entity);
 err_pipeline_start:
@@ -1130,9 +1103,9 @@ isp_video_streamoff(struct file *file, void *fh, enum v4l2_buf_type type)
 	mutex_lock(&video->stream_lock);
 
 	/* Make sure we're not streaming yet. */
-	mutex_lock(&vfh->queue.lock);
-	streaming = vfh->queue.streaming;
-	mutex_unlock(&vfh->queue.lock);
+	mutex_lock(&video->queue_lock);
+	streaming = vb2_is_streaming(&vfh->queue);
+	mutex_unlock(&video->queue_lock);
 
 	if (!streaming)
 		goto done;
@@ -1151,9 +1124,12 @@ isp_video_streamoff(struct file *file, void *fh, enum v4l2_buf_type type)
 
 	/* Stop the stream. */
 	omap3isp_pipeline_set_stream(pipe, ISP_PIPELINE_STREAM_STOPPED);
-	omap3isp_video_queue_streamoff(&vfh->queue);
+	omap3isp_video_cancel_stream(video);
+
+	mutex_lock(&video->queue_lock);
+	vb2_streamoff(&vfh->queue, type);
+	mutex_unlock(&video->queue_lock);
 	video->queue = NULL;
-	video->streaming = 0;
 	video->error = false;
 
 	if (video->isp->pdata->set_constraints)
@@ -1223,6 +1199,7 @@ static int isp_video_open(struct file *file)
 {
 	struct isp_video *video = video_drvdata(file);
 	struct isp_video_fh *handle;
+	struct vb2_queue *queue;
 	int ret = 0;
 
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
@@ -1244,9 +1221,20 @@ static int isp_video_open(struct file *file)
 		goto done;
 	}
 
-	omap3isp_video_queue_init(&handle->queue, video->type,
-				  &isp_video_queue_ops, video->isp->dev,
-				  sizeof(struct isp_buffer));
+	queue = &handle->queue;
+	queue->type = video->type;
+	queue->io_modes = VB2_MMAP | VB2_USERPTR;
+	queue->drv_priv = handle;
+	queue->ops = &isp_video_queue_ops;
+	queue->mem_ops = &vb2_dma_contig_memops;
+	queue->buf_struct_size = sizeof(struct isp_buffer);
+	queue->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+
+	ret = vb2_queue_init(&handle->queue);
+	if (ret < 0) {
+		omap3isp_put(video->isp);
+		goto done;
+	}
 
 	memset(&handle->format, 0, sizeof(handle->format));
 	handle->format.type = video->type;
@@ -1273,9 +1261,9 @@ static int isp_video_release(struct file *file)
 	/* Disable streaming and free the buffers queue resources. */
 	isp_video_streamoff(file, vfh, video->type);
 
-	mutex_lock(&handle->queue.lock);
-	omap3isp_video_queue_cleanup(&handle->queue);
-	mutex_unlock(&handle->queue.lock);
+	mutex_lock(&video->queue_lock);
+	vb2_queue_release(&handle->queue);
+	mutex_unlock(&video->queue_lock);
 
 	omap3isp_pipeline_pm_use(&video->video.entity, 0);
 
@@ -1292,16 +1280,27 @@ static int isp_video_release(struct file *file)
 static unsigned int isp_video_poll(struct file *file, poll_table *wait)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(file->private_data);
-	struct isp_video_queue *queue = &vfh->queue;
+	struct isp_video *video = video_drvdata(file);
+	int ret;
 
-	return omap3isp_video_queue_poll(queue, file, wait);
+	mutex_lock(&video->queue_lock);
+	ret = vb2_poll(&vfh->queue, file, wait);
+	mutex_unlock(&video->queue_lock);
+
+	return ret;
 }
 
 static int isp_video_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct isp_video_fh *vfh = to_isp_video_fh(file->private_data);
+	struct isp_video *video = video_drvdata(file);
+	int ret;
+
+	mutex_lock(&video->queue_lock);
+	ret = vb2_mmap(&vfh->queue, vma);
+	mutex_unlock(&video->queue_lock);
 
-	return omap3isp_video_queue_mmap(&vfh->queue, vma);
+	return ret;
 }
 
 static struct v4l2_file_operations isp_video_fops = {
@@ -1342,15 +1341,23 @@ int omap3isp_video_init(struct isp_video *video, const char *name)
 		return -EINVAL;
 	}
 
+	video->alloc_ctx = vb2_dma_contig_init_ctx(video->isp->dev);
+	if (IS_ERR(video->alloc_ctx))
+		return PTR_ERR(video->alloc_ctx);
+
 	ret = media_entity_init(&video->video.entity, 1, &video->pad, 0);
-	if (ret < 0)
+	if (ret < 0) {
+		vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
 		return ret;
+	}
 
 	mutex_init(&video->mutex);
 	atomic_set(&video->active, 0);
 
 	spin_lock_init(&video->pipe.lock);
 	mutex_init(&video->stream_lock);
+	mutex_init(&video->queue_lock);
+	spin_lock_init(&video->irqlock);
 
 	/* Initialize the video device. */
 	if (video->ops == NULL)
@@ -1371,7 +1378,9 @@ int omap3isp_video_init(struct isp_video *video, const char *name)
 
 void omap3isp_video_cleanup(struct isp_video *video)
 {
+	vb2_dma_contig_cleanup_ctx(video->alloc_ctx);
 	media_entity_cleanup(&video->video.entity);
+	mutex_destroy(&video->queue_lock);
 	mutex_destroy(&video->stream_lock);
 	mutex_destroy(&video->mutex);
 }
diff --git a/drivers/media/platform/omap3isp/ispvideo.h b/drivers/media/platform/omap3isp/ispvideo.h
index 4e194076cc6..7d2e82122ec 100644
--- a/drivers/media/platform/omap3isp/ispvideo.h
+++ b/drivers/media/platform/omap3isp/ispvideo.h
@@ -30,8 +30,7 @@
 #include <media/media-entity.h>
 #include <media/v4l2-dev.h>
 #include <media/v4l2-fh.h>
-
-#include "ispqueue.h"
+#include <media/videobuf2-core.h>
 
 #define ISP_VIDEO_DRIVER_NAME		"ispvideo"
 #define ISP_VIDEO_DRIVER_VERSION	"0.0.2"
@@ -124,17 +123,19 @@ static inline int isp_pipeline_ready(struct isp_pipeline *pipe)
 			       ISP_PIPELINE_IDLE_OUTPUT);
 }
 
-/*
- * struct isp_buffer - ISP buffer
- * @buffer: ISP video buffer
- * @isp_addr: MMU mapped address (a.k.a. device address) of the buffer.
+/**
+ * struct isp_buffer - ISP video buffer
+ * @vb: videobuf2 buffer
+ * @irqlist: List head for insertion into IRQ queue
+ * @dma: DMA address
  */
 struct isp_buffer {
-	struct isp_video_buffer buffer;
-	dma_addr_t isp_addr;
+	struct vb2_buffer vb;
+	struct list_head irqlist;
+	dma_addr_t dma;
 };
 
-#define to_isp_buffer(buf)	container_of(buf, struct isp_buffer, buffer)
+#define to_isp_buffer(buf)	container_of(buf, struct isp_buffer, vb)
 
 enum isp_video_dmaqueue_flags {
 	/* Set if DMA queue becomes empty when ISP_PIPELINE_STREAM_CONTINUOUS */
@@ -172,16 +173,16 @@ struct isp_video {
 	unsigned int bpl_value;		/* bytes per line value */
 	unsigned int bpl_padding;	/* padding at end of line */
 
-	/* Entity video node streaming */
-	unsigned int streaming:1;
-
 	/* Pipeline state */
 	struct isp_pipeline pipe;
 	struct mutex stream_lock;	/* pipeline and stream states */
 	bool error;
 
 	/* Video buffers queue */
-	struct isp_video_queue *queue;
+	void *alloc_ctx;
+	struct vb2_queue *queue;
+	struct mutex queue_lock;	/* protects the queue */
+	spinlock_t irqlock;		/* protects dmaqueue */
 	struct list_head dmaqueue;
 	enum isp_video_dmaqueue_flags dmaqueue_flags;
 
@@ -193,7 +194,7 @@ struct isp_video {
 struct isp_video_fh {
 	struct v4l2_fh vfh;
 	struct isp_video *video;
-	struct isp_video_queue queue;
+	struct vb2_queue queue;
 	struct v4l2_format format;
 	struct v4l2_fract timeperframe;
 };
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index 271a752cee5..fa4cc7b880a 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -57,7 +57,7 @@ static int si2157_cmd_execute(struct si2157 *s, struct si2157_cmd *cmd)
 			jiffies_to_msecs(jiffies) -
 			(jiffies_to_msecs(timeout) - TIMEOUT));
 
-	if (!(buf[0] >> 7) & 0x01) {
+	if (!((buf[0] >> 7) & 0x01)) {
 		ret = -ETIMEDOUT;
 		goto err_mutex_unlock;
 	} else {
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index 021e4d35e4d..7b9b75f6077 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -704,15 +704,41 @@ static int af9035_read_config(struct dvb_usb_device *d)
 		if (ret < 0)
 			goto err;
 
-		if (tmp == 0x00)
-			dev_dbg(&d->udev->dev,
-					"%s: [%d]tuner not set, using default\n",
-					__func__, i);
-		else
+		dev_dbg(&d->udev->dev, "%s: [%d]tuner=%02x\n",
+				__func__, i, tmp);
+
+		/* tuner sanity check */
+		if (state->chip_type == 0x9135) {
+			if (state->chip_version == 0x02) {
+				/* IT9135 BX (v2) */
+				switch (tmp) {
+				case AF9033_TUNER_IT9135_60:
+				case AF9033_TUNER_IT9135_61:
+				case AF9033_TUNER_IT9135_62:
+					state->af9033_config[i].tuner = tmp;
+					break;
+				}
+			} else {
+				/* IT9135 AX (v1) */
+				switch (tmp) {
+				case AF9033_TUNER_IT9135_38:
+				case AF9033_TUNER_IT9135_51:
+				case AF9033_TUNER_IT9135_52:
+					state->af9033_config[i].tuner = tmp;
+					break;
+				}
+			}
+		} else {
+			/* AF9035 */
 			state->af9033_config[i].tuner = tmp;
+		}
 
-		dev_dbg(&d->udev->dev, "%s: [%d]tuner=%02x\n",
-				__func__, i, state->af9033_config[i].tuner);
+		if (state->af9033_config[i].tuner != tmp) {
+			dev_info(&d->udev->dev,
+					"%s: [%d] overriding tuner from %02x to %02x\n",
+					KBUILD_MODNAME, i, tmp,
+					state->af9033_config[i].tuner);
+		}
 
 		switch (state->af9033_config[i].tuner) {
 		case AF9033_TUNER_TUA9001:
diff --git a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
index e3558061893..f296394bb7c 100644
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
@@ -253,13 +253,6 @@ static int dvb_usbv2_adapter_stream_exit(struct dvb_usb_adapter *adap)
 	return usb_urb_exitv2(&adap->stream);
 }
 
-static int wait_schedule(void *ptr)
-{
-	schedule();
-
-	return 0;
-}
-
 static int dvb_usb_start_feed(struct dvb_demux_feed *dvbdmxfeed)
 {
 	struct dvb_usb_adapter *adap = dvbdmxfeed->demux->priv;
@@ -273,8 +266,7 @@ static int dvb_usb_start_feed(struct dvb_demux_feed *dvbdmxfeed)
 			dvbdmxfeed->pid, dvbdmxfeed->index);
 
 	/* wait init is done */
-	wait_on_bit(&adap->state_bits, ADAP_INIT, wait_schedule,
-			TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&adap->state_bits, ADAP_INIT, TASK_UNINTERRUPTIBLE);
 
 	if (adap->active_fe == -1)
 		return -EINVAL;
@@ -568,7 +560,7 @@ static int dvb_usb_fe_sleep(struct dvb_frontend *fe)
 
 	if (!adap->suspend_resume_active) {
 		set_bit(ADAP_SLEEP, &adap->state_bits);
-		wait_on_bit(&adap->state_bits, ADAP_STREAMING, wait_schedule,
+		wait_on_bit(&adap->state_bits, ADAP_STREAMING,
 				TASK_UNINTERRUPTIBLE);
 	}
 
diff --git a/drivers/media/usb/gspca/pac7302.c b/drivers/media/usb/gspca/pac7302.c
index 2fd1c5e31a0..339adce7c7a 100644
--- a/drivers/media/usb/gspca/pac7302.c
+++ b/drivers/media/usb/gspca/pac7302.c
@@ -928,6 +928,7 @@ static const struct usb_device_id device_table[] = {
 	{USB_DEVICE(0x093a, 0x2620)},
 	{USB_DEVICE(0x093a, 0x2621)},
 	{USB_DEVICE(0x093a, 0x2622), .driver_info = FL_VFLIP},
+	{USB_DEVICE(0x093a, 0x2623), .driver_info = FL_VFLIP},
 	{USB_DEVICE(0x093a, 0x2624), .driver_info = FL_VFLIP},
 	{USB_DEVICE(0x093a, 0x2625)},
 	{USB_DEVICE(0x093a, 0x2626)},
diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c
index 0500c4175d5..6bce01a674f 100644
--- a/drivers/media/usb/hdpvr/hdpvr-video.c
+++ b/drivers/media/usb/hdpvr/hdpvr-video.c
@@ -82,7 +82,7 @@ static void hdpvr_read_bulk_callback(struct urb *urb)
 }
 
 /*=========================================================================*/
-/* bufffer bits */
+/* buffer bits */
 
 /* function expects dev->io_mutex to be hold by caller */
 int hdpvr_cancel_queue(struct hdpvr_device *dev)
@@ -926,7 +926,7 @@ static int hdpvr_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_MPEG_AUDIO_ENCODING:
 		if (dev->flags & HDPVR_FLAG_AC3_CAP) {
 			opt->audio_codec = ctrl->val;
-			return hdpvr_set_audio(dev, opt->audio_input,
+			return hdpvr_set_audio(dev, opt->audio_input + 1,
 					      opt->audio_codec);
 		}
 		return 0;
@@ -1198,7 +1198,7 @@ int hdpvr_register_videodev(struct hdpvr_device *dev, struct device *parent,
 	v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops,
 		V4L2_CID_MPEG_AUDIO_ENCODING,
 		ac3 ? V4L2_MPEG_AUDIO_ENCODING_AC3 : V4L2_MPEG_AUDIO_ENCODING_AAC,
-		0x7, V4L2_MPEG_AUDIO_ENCODING_AAC);
+		0x7, ac3 ? dev->options.audio_codec : V4L2_MPEG_AUDIO_ENCODING_AAC);
 	v4l2_ctrl_new_std_menu(hdl, &hdpvr_ctrl_ops,
 		V4L2_CID_MPEG_VIDEO_ENCODING,
 		V4L2_MPEG_VIDEO_ENCODING_MPEG_4_AVC, 0x3,
diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c
index 4ae54caadd0..ce1c9f5d9de 100644
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -610,10 +610,10 @@ struct v4l2_fract v4l2_calc_aspect_ratio(u8 hor_landscape, u8 vert_portrait)
 		aspect.denominator = 9;
 	} else if (ratio == 34) {
 		aspect.numerator = 4;
-		aspect.numerator = 3;
+		aspect.denominator = 3;
 	} else if (ratio == 68) {
 		aspect.numerator = 15;
-		aspect.numerator = 9;
+		aspect.denominator = 9;
 	} else {
 		aspect.numerator = hor_landscape + 99;
 		aspect.denominator = 100;
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 349e659d75f..7c4489c4236 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -1200,6 +1200,30 @@ void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state)
 EXPORT_SYMBOL_GPL(vb2_buffer_done);
 
 /**
+ * vb2_discard_done() - discard all buffers marked as DONE
+ * @q:		videobuf2 queue
+ *
+ * This function is intended to be used with suspend/resume operations. It
+ * discards all 'done' buffers as they would be too old to be requested after
+ * resume.
+ *
+ * Drivers must stop the hardware and synchronize with interrupt handlers and/or
+ * delayed works before calling this function to make sure no buffer will be
+ * touched by the driver and/or hardware.
+ */
+void vb2_discard_done(struct vb2_queue *q)
+{
+	struct vb2_buffer *vb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->done_lock, flags);
+	list_for_each_entry(vb, &q->done_list, done_entry)
+		vb->state = VB2_BUF_STATE_ERROR;
+	spin_unlock_irqrestore(&q->done_lock, flags);
+}
+EXPORT_SYMBOL_GPL(vb2_discard_done);
+
+/**
  * __fill_vb2_buffer() - fill a vb2_buffer with information provided in a
  * v4l2_buffer by the userspace. The caller has already verified that struct
  * v4l2_buffer has a valid number of planes.
diff --git a/drivers/memstick/host/rtsx_pci_ms.c b/drivers/memstick/host/rtsx_pci_ms.c
index 2a635b6fdaf..c880ba68575 100644
--- a/drivers/memstick/host/rtsx_pci_ms.c
+++ b/drivers/memstick/host/rtsx_pci_ms.c
@@ -601,6 +601,7 @@ static int rtsx_pci_ms_drv_remove(struct platform_device *pdev)
 	pcr->slots[RTSX_MS_CARD].card_event = NULL;
 	msh = host->msh;
 	host->eject = true;
+	cancel_work_sync(&host->handle_req);
 
 	mutex_lock(&host->host_mutex);
 	if (host->req) {
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index 570b18a113f..ebc0af7d769 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -1037,7 +1037,7 @@ mpt_free_msg_frame(MPT_ADAPTER *ioc, MPT_FRAME_HDR *mf)
 		goto out;
 	/* signature to know if this mf is freed */
 	mf->u.frame.linkage.arg1 = cpu_to_le32(0xdeadbeaf);
-	list_add_tail(&mf->u.frame.linkage.list, &ioc->FreeQ);
+	list_add(&mf->u.frame.linkage.list, &ioc->FreeQ);
 #ifdef MFCNT
 	ioc->mfcnt--;
 #endif
diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c
index dcc8385adeb..8a050e88568 100644
--- a/drivers/message/fusion/mptctl.c
+++ b/drivers/message/fusion/mptctl.c
@@ -2432,9 +2432,9 @@ mptctl_hp_hostinfo(unsigned long arg, unsigned int data_size)
 	int			rc, cim_rev;
 	ToolboxIstwiReadWriteRequest_t	*IstwiRWRequest;
 	MPT_FRAME_HDR		*mf = NULL;
-	MPIHeader_t		*mpi_hdr;
 	unsigned long		timeleft;
 	int			retval;
+	u32			msgcontext;
 
 	/* Reset long to int. Should affect IA64 and SPARC only
 	 */
@@ -2581,11 +2581,11 @@ mptctl_hp_hostinfo(unsigned long arg, unsigned int data_size)
 	}
 
 	IstwiRWRequest = (ToolboxIstwiReadWriteRequest_t *)mf;
-	mpi_hdr = (MPIHeader_t *) mf;
+	msgcontext = IstwiRWRequest->MsgContext;
 	memset(IstwiRWRequest,0,sizeof(ToolboxIstwiReadWriteRequest_t));
+	IstwiRWRequest->MsgContext = msgcontext;
 	IstwiRWRequest->Function = MPI_FUNCTION_TOOLBOX;
 	IstwiRWRequest->Tool = MPI_TOOLBOX_ISTWI_READ_WRITE_TOOL;
-	IstwiRWRequest->MsgContext = mpi_hdr->MsgContext;
 	IstwiRWRequest->Flags = MPI_TB_ISTWI_FLAGS_READ;
 	IstwiRWRequest->NumAddressBytes = 0x01;
 	IstwiRWRequest->DataLength = cpu_to_le16(0x04);
diff --git a/drivers/message/fusion/mptfc.c b/drivers/message/fusion/mptfc.c
index fd75108c355..02a3eefd693 100644
--- a/drivers/message/fusion/mptfc.c
+++ b/drivers/message/fusion/mptfc.c
@@ -649,7 +649,7 @@ mptfc_slave_alloc(struct scsi_device *sdev)
 }
 
 static int
-mptfc_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+mptfc_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *SCpnt)
 {
 	struct mptfc_rport_info	*ri;
 	struct fc_rport	*rport = starget_to_rport(scsi_target(SCpnt->device));
@@ -658,14 +658,14 @@ mptfc_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 
 	if (!vdevice || !vdevice->vtarget) {
 		SCpnt->result = DID_NO_CONNECT << 16;
-		done(SCpnt);
+		SCpnt->scsi_done(SCpnt);
 		return 0;
 	}
 
 	err = fc_remote_port_chkready(rport);
 	if (unlikely(err)) {
 		SCpnt->result = err;
-		done(SCpnt);
+		SCpnt->scsi_done(SCpnt);
 		return 0;
 	}
 
@@ -673,15 +673,13 @@ mptfc_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 	ri = *((struct mptfc_rport_info **)rport->dd_data);
 	if (unlikely(!ri)) {
 		SCpnt->result = DID_IMM_RETRY << 16;
-		done(SCpnt);
+		SCpnt->scsi_done(SCpnt);
 		return 0;
 	}
 
-	return mptscsih_qcmd(SCpnt,done);
+	return mptscsih_qcmd(SCpnt);
 }
 
-static DEF_SCSI_QCMD(mptfc_qcmd)
-
 /*
  *	mptfc_display_port_link_speed - displaying link speed
  *	@ioc: Pointer to MPT_ADAPTER structure
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 00d339c361f..711fcb5cec8 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -1896,7 +1896,7 @@ mptsas_slave_alloc(struct scsi_device *sdev)
 }
 
 static int
-mptsas_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+mptsas_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *SCpnt)
 {
 	MPT_SCSI_HOST	*hd;
 	MPT_ADAPTER	*ioc;
@@ -1904,11 +1904,11 @@ mptsas_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 
 	if (!vdevice || !vdevice->vtarget || vdevice->vtarget->deleted) {
 		SCpnt->result = DID_NO_CONNECT << 16;
-		done(SCpnt);
+		SCpnt->scsi_done(SCpnt);
 		return 0;
 	}
 
-	hd = shost_priv(SCpnt->device->host);
+	hd = shost_priv(shost);
 	ioc = hd->ioc;
 
 	if (ioc->sas_discovery_quiesce_io)
@@ -1917,11 +1917,9 @@ mptsas_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 	if (ioc->debug_level & MPT_DEBUG_SCSI)
 		scsi_print_command(SCpnt);
 
-	return mptscsih_qcmd(SCpnt,done);
+	return mptscsih_qcmd(SCpnt);
 }
 
-static DEF_SCSI_QCMD(mptsas_qcmd)
-
 /**
  *	mptsas_mptsas_eh_timed_out - resets the scsi_cmnd timeout
  *		if the device under question is currently in the
diff --git a/drivers/message/fusion/mptscsih.c b/drivers/message/fusion/mptscsih.c
index 727819cc703..2a1c6f21af2 100644
--- a/drivers/message/fusion/mptscsih.c
+++ b/drivers/message/fusion/mptscsih.c
@@ -1304,7 +1304,6 @@ int mptscsih_show_info(struct seq_file *m, struct Scsi_Host *host)
 /**
  *	mptscsih_qcmd - Primary Fusion MPT SCSI initiator IO start routine.
  *	@SCpnt: Pointer to scsi_cmnd structure
- *	@done: Pointer SCSI mid-layer IO completion function
  *
  *	(linux scsi_host_template.queuecommand routine)
  *	This is the primary SCSI IO start routine.  Create a MPI SCSIIORequest
@@ -1313,7 +1312,7 @@ int mptscsih_show_info(struct seq_file *m, struct Scsi_Host *host)
  *	Returns 0. (rtn value discarded by linux scsi mid-layer)
  */
 int
-mptscsih_qcmd(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+mptscsih_qcmd(struct scsi_cmnd *SCpnt)
 {
 	MPT_SCSI_HOST		*hd;
 	MPT_FRAME_HDR		*mf;
@@ -1329,10 +1328,9 @@ mptscsih_qcmd(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
 
 	hd = shost_priv(SCpnt->device->host);
 	ioc = hd->ioc;
-	SCpnt->scsi_done = done;
 
-	dmfprintk(ioc, printk(MYIOC_s_DEBUG_FMT "qcmd: SCpnt=%p, done()=%p\n",
-		ioc->name, SCpnt, done));
+	dmfprintk(ioc, printk(MYIOC_s_DEBUG_FMT "qcmd: SCpnt=%p\n",
+		ioc->name, SCpnt));
 
 	if (ioc->taskmgmt_quiesce_io)
 		return SCSI_MLQUEUE_HOST_BUSY;
diff --git a/drivers/message/fusion/mptscsih.h b/drivers/message/fusion/mptscsih.h
index 83f503162f7..99e3390807f 100644
--- a/drivers/message/fusion/mptscsih.h
+++ b/drivers/message/fusion/mptscsih.h
@@ -113,7 +113,7 @@ extern int mptscsih_resume(struct pci_dev *pdev);
 #endif
 extern int mptscsih_show_info(struct seq_file *, struct Scsi_Host *);
 extern const char * mptscsih_info(struct Scsi_Host *SChost);
-extern int mptscsih_qcmd(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *));
+extern int mptscsih_qcmd(struct scsi_cmnd *SCpnt);
 extern int mptscsih_IssueTaskMgmt(MPT_SCSI_HOST *hd, u8 type, u8 channel,
 	u8 id, int lun, int ctx2abort, ulong timeout);
 extern void mptscsih_slave_destroy(struct scsi_device *device);
diff --git a/drivers/message/fusion/mptspi.c b/drivers/message/fusion/mptspi.c
index 5653e505f91..49d11338294 100644
--- a/drivers/message/fusion/mptspi.c
+++ b/drivers/message/fusion/mptspi.c
@@ -780,33 +780,31 @@ static int mptspi_slave_configure(struct scsi_device *sdev)
 }
 
 static int
-mptspi_qcmd_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_cmnd *))
+mptspi_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *SCpnt)
 {
-	struct _MPT_SCSI_HOST *hd = shost_priv(SCpnt->device->host);
+	struct _MPT_SCSI_HOST *hd = shost_priv(shost);
 	VirtDevice	*vdevice = SCpnt->device->hostdata;
 	MPT_ADAPTER *ioc = hd->ioc;
 
 	if (!vdevice || !vdevice->vtarget) {
 		SCpnt->result = DID_NO_CONNECT << 16;
-		done(SCpnt);
+		SCpnt->scsi_done(SCpnt);
 		return 0;
 	}
 
 	if (SCpnt->device->channel == 1 &&
 		mptscsih_is_phys_disk(ioc, 0, SCpnt->device->id) == 0) {
 		SCpnt->result = DID_NO_CONNECT << 16;
-		done(SCpnt);
+		SCpnt->scsi_done(SCpnt);
 		return 0;
 	}
 
 	if (spi_dv_pending(scsi_target(SCpnt->device)))
 		ddvprintk(ioc, scsi_print_command(SCpnt));
 
-	return mptscsih_qcmd(SCpnt,done);
+	return mptscsih_qcmd(SCpnt);
 }
 
-static DEF_SCSI_QCMD(mptspi_qcmd)
-
 static void mptspi_slave_destroy(struct scsi_device *sdev)
 {
 	struct scsi_target *starget = scsi_target(sdev);
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index ee8204cc31e..6cc4b6acc22 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -760,6 +760,7 @@ config MFD_SYSCON
 config MFD_DAVINCI_VOICECODEC
 	tristate
 	select MFD_CORE
+	select REGMAP_MMIO
 
 config MFD_TI_AM335X_TSCADC
 	tristate "TI ADC / Touch Screen chip support"
@@ -1225,7 +1226,7 @@ config MFD_WM8994
 	  functionaltiy of the device other drivers must be enabled.
 
 config MFD_STW481X
-	bool "Support for ST Microelectronics STw481x"
+	tristate "Support for ST Microelectronics STw481x"
 	depends on I2C && ARCH_NOMADIK
 	select REGMAP_I2C
 	select MFD_CORE
@@ -1248,7 +1249,7 @@ config MCP_SA11X0
 
 # Chip drivers
 config MCP_UCB1200
-	bool "Support for UCB1200 / UCB1300"
+	tristate "Support for UCB1200 / UCB1300"
 	depends on MCP_SA11X0
 	select MCP
 
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index a8ee4a36a1d..cf2e6a198c6 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -591,7 +591,7 @@ static int ab8500_irq_init(struct ab8500 *ab8500, struct device_node *np)
 		num_irqs = AB8500_NR_IRQS;
 
 	/* If ->irq_base is zero this will give a linear mapping */
-	ab8500->domain = irq_domain_add_simple(NULL,
+	ab8500->domain = irq_domain_add_simple(ab8500->dev->of_node,
 			num_irqs, 0,
 			&ab8500_irq_ops, ab8500);
 
diff --git a/drivers/mfd/twl4030-power.c b/drivers/mfd/twl4030-power.c
index 96162b62f3c..3bc969a5916 100644
--- a/drivers/mfd/twl4030-power.c
+++ b/drivers/mfd/twl4030-power.c
@@ -29,13 +29,21 @@
 #include <linux/i2c/twl.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 
 #include <asm/mach-types.h>
 
 static u8 twl4030_start_script_address = 0x2b;
 
-#define PWR_P1_SW_EVENTS	0x10
-#define PWR_DEVOFF		(1 << 0)
+/* Register bits for P1, P2 and P3_SW_EVENTS */
+#define PWR_STOPON_PRWON	BIT(6)
+#define PWR_STOPON_SYSEN	BIT(5)
+#define PWR_ENABLE_WARMRESET	BIT(4)
+#define PWR_LVL_WAKEUP		BIT(3)
+#define PWR_DEVACT		BIT(2)
+#define PWR_DEVSLP		BIT(1)
+#define PWR_DEVOFF		BIT(0)
+
 #define SEQ_OFFSYNC		(1 << 0)
 
 #define PHY_TO_OFF_PM_MASTER(p)		(p - 0x36)
@@ -52,10 +60,6 @@ static u8 twl4030_start_script_address = 0x2b;
 #define R_CFG_P2_TRANSITION	PHY_TO_OFF_PM_MASTER(0x37)
 #define R_CFG_P3_TRANSITION	PHY_TO_OFF_PM_MASTER(0x38)
 
-#define LVL_WAKEUP	0x08
-
-#define ENABLE_WARMRESET (1<<4)
-
 #define END_OF_SCRIPT		0x3f
 
 #define R_SEQ_ADD_A2S		PHY_TO_OFF_PM_MASTER(0x55)
@@ -125,6 +129,53 @@ static u8 res_config_addrs[] = {
 	[RES_MAIN_REF]	= 0x94,
 };
 
+/*
+ * Usable values for .remap_sleep and .remap_off
+ * Based on table "5.3.3 Resource Operating modes"
+ */
+enum {
+	TWL_REMAP_OFF = 0,
+	TWL_REMAP_SLEEP = 8,
+	TWL_REMAP_ACTIVE = 9,
+};
+
+/*
+ * Macros to configure the PM register states for various resources.
+ * Note that we can make MSG_SINGULAR etc private to this driver once
+ * omap3 has been made DT only.
+ */
+#define TWL_DFLT_DELAY		2	/* typically 2 32 KiHz cycles */
+#define TWL_DEV_GRP_P123	(DEV_GRP_P1 | DEV_GRP_P2 | DEV_GRP_P3)
+#define TWL_RESOURCE_SET(res, state)					\
+	{ MSG_SINGULAR(DEV_GRP_NULL, (res), (state)), TWL_DFLT_DELAY }
+#define TWL_RESOURCE_ON(res)	TWL_RESOURCE_SET(res, RES_STATE_ACTIVE)
+#define TWL_RESOURCE_OFF(res)	TWL_RESOURCE_SET(res, RES_STATE_OFF)
+#define TWL_RESOURCE_RESET(res)	TWL_RESOURCE_SET(res, RES_STATE_WRST)
+/*
+ * It seems that type1 and type2 is just the resource init order
+ * number for the type1 and type2 group.
+ */
+#define TWL_RESOURCE_SET_ACTIVE(res, state)			       	\
+	{ MSG_SINGULAR(DEV_GRP_NULL, (res), RES_STATE_ACTIVE), (state) }
+#define TWL_RESOURCE_GROUP_RESET(group, type1, type2)			\
+	{ MSG_BROADCAST(DEV_GRP_NULL, (group), (type1), (type2),	\
+		RES_STATE_WRST), TWL_DFLT_DELAY }
+#define TWL_RESOURCE_GROUP_SLEEP(group, type, type2)			\
+	{ MSG_BROADCAST(DEV_GRP_NULL, (group), (type), (type2),		\
+		RES_STATE_SLEEP), TWL_DFLT_DELAY }
+#define TWL_RESOURCE_GROUP_ACTIVE(group, type, type2)			\
+	{ MSG_BROADCAST(DEV_GRP_NULL, (group), (type), (type2),		\
+		RES_STATE_ACTIVE), TWL_DFLT_DELAY }
+#define TWL_REMAP_SLEEP(res, devgrp, typ, typ2)				\
+	{ .resource = (res), .devgroup = (devgrp),			\
+	  .type = (typ), .type2 = (typ2),				\
+	  .remap_off = TWL_REMAP_OFF,					\
+	  .remap_sleep = TWL_REMAP_SLEEP, }
+#define TWL_REMAP_OFF(res, devgrp, typ, typ2)				\
+	{ .resource = (res), .devgroup = (devgrp),			\
+	  .type = (typ), .type2 = (typ2),				\
+	  .remap_off = TWL_REMAP_OFF, .remap_sleep = TWL_REMAP_OFF, }
+
 static int twl4030_write_script_byte(u8 address, u8 byte)
 {
 	int err;
@@ -196,7 +247,7 @@ static int twl4030_config_wakeup3_sequence(u8 address)
 	err = twl_i2c_read_u8(TWL_MODULE_PM_MASTER, &data, R_P3_SW_EVENTS);
 	if (err)
 		goto out;
-	data |= LVL_WAKEUP;
+	data |= PWR_LVL_WAKEUP;
 	err = twl_i2c_write_u8(TWL_MODULE_PM_MASTER, data, R_P3_SW_EVENTS);
 out:
 	if (err)
@@ -219,7 +270,7 @@ static int twl4030_config_wakeup12_sequence(u8 address)
 	if (err)
 		goto out;
 
-	data |= LVL_WAKEUP;
+	data |= PWR_LVL_WAKEUP;
 	err = twl_i2c_write_u8(TWL_MODULE_PM_MASTER, data, R_P1_SW_EVENTS);
 	if (err)
 		goto out;
@@ -228,7 +279,7 @@ static int twl4030_config_wakeup12_sequence(u8 address)
 	if (err)
 		goto out;
 
-	data |= LVL_WAKEUP;
+	data |= PWR_LVL_WAKEUP;
 	err = twl_i2c_write_u8(TWL_MODULE_PM_MASTER, data, R_P2_SW_EVENTS);
 	if (err)
 		goto out;
@@ -281,7 +332,7 @@ static int twl4030_config_warmreset_sequence(u8 address)
 	if (err)
 		goto out;
 
-	rd_data |= ENABLE_WARMRESET;
+	rd_data |= PWR_ENABLE_WARMRESET;
 	err = twl_i2c_write_u8(TWL_MODULE_PM_MASTER, rd_data, R_P1_SW_EVENTS);
 	if (err)
 		goto out;
@@ -290,7 +341,7 @@ static int twl4030_config_warmreset_sequence(u8 address)
 	if (err)
 		goto out;
 
-	rd_data |= ENABLE_WARMRESET;
+	rd_data |= PWR_ENABLE_WARMRESET;
 	err = twl_i2c_write_u8(TWL_MODULE_PM_MASTER, rd_data, R_P2_SW_EVENTS);
 	if (err)
 		goto out;
@@ -299,7 +350,7 @@ static int twl4030_config_warmreset_sequence(u8 address)
 	if (err)
 		goto out;
 
-	rd_data |= ENABLE_WARMRESET;
+	rd_data |= PWR_ENABLE_WARMRESET;
 	err = twl_i2c_write_u8(TWL_MODULE_PM_MASTER, rd_data, R_P3_SW_EVENTS);
 out:
 	if (err)
@@ -421,6 +472,12 @@ static int load_twl4030_script(struct twl4030_script *tscript,
 			goto out;
 	}
 	if (tscript->flags & TWL4030_WAKEUP12_SCRIPT) {
+		/* Reset any existing sleep script to avoid hangs on reboot */
+		err = twl_i2c_write_u8(TWL_MODULE_PM_MASTER, END_OF_SCRIPT,
+				       R_SEQ_ADD_A2S);
+		if (err)
+			goto out;
+
 		err = twl4030_config_wakeup12_sequence(address);
 		if (err)
 			goto out;
@@ -493,7 +550,8 @@ int twl4030_remove_script(u8 flags)
 	return err;
 }
 
-static int twl4030_power_configure_scripts(struct twl4030_power_data *pdata)
+static int
+twl4030_power_configure_scripts(const struct twl4030_power_data *pdata)
 {
 	int err;
 	int i;
@@ -509,12 +567,34 @@ static int twl4030_power_configure_scripts(struct twl4030_power_data *pdata)
 	return 0;
 }
 
-static int twl4030_power_configure_resources(struct twl4030_power_data *pdata)
+static void twl4030_patch_rconfig(struct twl4030_resconfig *common,
+				  struct twl4030_resconfig *board)
+{
+	while (common->resource) {
+		struct twl4030_resconfig *b = board;
+
+		while (b->resource) {
+			if (b->resource == common->resource) {
+				*common = *b;
+				break;
+			}
+			b++;
+		}
+		common++;
+	}
+}
+
+static int
+twl4030_power_configure_resources(const struct twl4030_power_data *pdata)
 {
 	struct twl4030_resconfig *resconfig = pdata->resource_config;
+	struct twl4030_resconfig *boardconf = pdata->board_config;
 	int err;
 
 	if (resconfig) {
+		if (boardconf)
+			twl4030_patch_rconfig(resconfig, boardconf);
+
 		while (resconfig->resource) {
 			err = twl4030_configure_resource(resconfig);
 			if (err)
@@ -541,7 +621,7 @@ void twl4030_power_off(void)
 		pr_err("TWL4030 Unable to power off\n");
 }
 
-static bool twl4030_power_use_poweroff(struct twl4030_power_data *pdata,
+static bool twl4030_power_use_poweroff(const struct twl4030_power_data *pdata,
 					struct device_node *node)
 {
 	if (pdata && pdata->use_poweroff)
@@ -553,10 +633,170 @@ static bool twl4030_power_use_poweroff(struct twl4030_power_data *pdata,
 	return false;
 }
 
+#ifdef CONFIG_OF
+
+/* Generic warm reset configuration for omap3 */
+
+static struct twl4030_ins omap3_wrst_seq[] = {
+	TWL_RESOURCE_OFF(RES_NRES_PWRON),
+	TWL_RESOURCE_OFF(RES_RESET),
+	TWL_RESOURCE_RESET(RES_MAIN_REF),
+	TWL_RESOURCE_GROUP_RESET(RES_GRP_ALL, RES_TYPE_R0, RES_TYPE2_R2),
+	TWL_RESOURCE_RESET(RES_VUSB_3V1),
+	TWL_RESOURCE_GROUP_RESET(RES_GRP_ALL, RES_TYPE_R0, RES_TYPE2_R1),
+	TWL_RESOURCE_GROUP_RESET(RES_GRP_RC, RES_TYPE_ALL, RES_TYPE2_R0),
+	TWL_RESOURCE_ON(RES_RESET),
+	TWL_RESOURCE_ON(RES_NRES_PWRON),
+};
+
+static struct twl4030_script omap3_wrst_script = {
+	.script	= omap3_wrst_seq,
+	.size	= ARRAY_SIZE(omap3_wrst_seq),
+	.flags	= TWL4030_WRST_SCRIPT,
+};
+
+static struct twl4030_script *omap3_reset_scripts[] = {
+	&omap3_wrst_script,
+};
+
+static struct twl4030_resconfig omap3_rconfig[] = {
+	TWL_REMAP_SLEEP(RES_HFCLKOUT, DEV_GRP_P3, -1, -1),
+	TWL_REMAP_SLEEP(RES_VDD1, DEV_GRP_P1, -1, -1),
+	TWL_REMAP_SLEEP(RES_VDD2, DEV_GRP_P1, -1, -1),
+	{ 0, 0 },
+};
+
+static struct twl4030_power_data omap3_reset = {
+	.scripts		= omap3_reset_scripts,
+	.num			= ARRAY_SIZE(omap3_reset_scripts),
+	.resource_config	= omap3_rconfig,
+};
+
+/* Recommended generic default idle configuration for off-idle */
+
+/* Broadcast message to put res to sleep */
+static struct twl4030_ins omap3_idle_sleep_on_seq[] = {
+	TWL_RESOURCE_GROUP_SLEEP(RES_GRP_ALL, RES_TYPE_ALL, 0),
+};
+
+static struct twl4030_script omap3_idle_sleep_on_script = {
+	.script	= omap3_idle_sleep_on_seq,
+	.size	= ARRAY_SIZE(omap3_idle_sleep_on_seq),
+	.flags	= TWL4030_SLEEP_SCRIPT,
+};
+
+/* Broadcast message to put res to active */
+static struct twl4030_ins omap3_idle_wakeup_p12_seq[] = {
+	TWL_RESOURCE_GROUP_ACTIVE(RES_GRP_ALL, RES_TYPE_ALL, 0),
+};
+
+static struct twl4030_script omap3_idle_wakeup_p12_script = {
+	.script	= omap3_idle_wakeup_p12_seq,
+	.size	= ARRAY_SIZE(omap3_idle_wakeup_p12_seq),
+	.flags	= TWL4030_WAKEUP12_SCRIPT,
+};
+
+/* Broadcast message to put res to active */
+static struct twl4030_ins omap3_idle_wakeup_p3_seq[] = {
+	TWL_RESOURCE_SET_ACTIVE(RES_CLKEN, 0x37),
+	TWL_RESOURCE_GROUP_ACTIVE(RES_GRP_ALL, RES_TYPE_ALL, 0),
+};
+
+static struct twl4030_script omap3_idle_wakeup_p3_script = {
+	.script	= omap3_idle_wakeup_p3_seq,
+	.size	= ARRAY_SIZE(omap3_idle_wakeup_p3_seq),
+	.flags	= TWL4030_WAKEUP3_SCRIPT,
+};
+
+static struct twl4030_script *omap3_idle_scripts[] = {
+	&omap3_idle_wakeup_p12_script,
+	&omap3_idle_wakeup_p3_script,
+	&omap3_wrst_script,
+	&omap3_idle_sleep_on_script,
+};
+
+/*
+ * Recommended configuration based on "Recommended Sleep
+ * Sequences for the Zoom Platform":
+ * http://omappedia.com/wiki/File:Recommended_Sleep_Sequences_Zoom.pdf
+ * Note that the type1 and type2 seem to be just the init order number
+ * for type1 and type2 groups as specified in the document mentioned
+ * above.
+ */
+static struct twl4030_resconfig omap3_idle_rconfig[] = {
+	TWL_REMAP_SLEEP(RES_VAUX1, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VAUX2, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VAUX3, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VAUX4, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VMMC1, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VMMC2, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_OFF(RES_VPLL1, DEV_GRP_P1, 3, 1),
+	TWL_REMAP_SLEEP(RES_VPLL2, DEV_GRP_P1, 0, 0),
+	TWL_REMAP_SLEEP(RES_VSIM, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VDAC, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VINTANA1, TWL_DEV_GRP_P123, 1, 2),
+	TWL_REMAP_SLEEP(RES_VINTANA2, TWL_DEV_GRP_P123, 0, 2),
+	TWL_REMAP_SLEEP(RES_VINTDIG, TWL_DEV_GRP_P123, 1, 2),
+	TWL_REMAP_SLEEP(RES_VIO, TWL_DEV_GRP_P123, 2, 2),
+	TWL_REMAP_OFF(RES_VDD1, DEV_GRP_P1, 4, 1),
+	TWL_REMAP_OFF(RES_VDD2, DEV_GRP_P1, 3, 1),
+	TWL_REMAP_SLEEP(RES_VUSB_1V5, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VUSB_1V8, DEV_GRP_NULL, 0, 0),
+	TWL_REMAP_SLEEP(RES_VUSB_3V1, TWL_DEV_GRP_P123, 0, 0),
+	/* Resource #20 USB charge pump skipped */
+	TWL_REMAP_SLEEP(RES_REGEN, TWL_DEV_GRP_P123, 2, 1),
+	TWL_REMAP_SLEEP(RES_NRES_PWRON, TWL_DEV_GRP_P123, 0, 1),
+	TWL_REMAP_SLEEP(RES_CLKEN, TWL_DEV_GRP_P123, 3, 2),
+	TWL_REMAP_SLEEP(RES_SYSEN, TWL_DEV_GRP_P123, 6, 1),
+	TWL_REMAP_SLEEP(RES_HFCLKOUT, DEV_GRP_P3, 0, 2),
+	TWL_REMAP_SLEEP(RES_32KCLKOUT, TWL_DEV_GRP_P123, 0, 0),
+	TWL_REMAP_SLEEP(RES_RESET, TWL_DEV_GRP_P123, 6, 0),
+	TWL_REMAP_SLEEP(RES_MAIN_REF, TWL_DEV_GRP_P123, 0, 0),
+	{ /* Terminator */ },
+};
+
+static struct twl4030_power_data omap3_idle = {
+	.scripts		= omap3_idle_scripts,
+	.num			= ARRAY_SIZE(omap3_idle_scripts),
+	.resource_config	= omap3_idle_rconfig,
+};
+
+/* Disable 32 KiHz oscillator during idle */
+static struct twl4030_resconfig osc_off_rconfig[] = {
+	TWL_REMAP_OFF(RES_CLKEN, DEV_GRP_P1 | DEV_GRP_P3, 3, 2),
+	{ /* Terminator */ },
+};
+
+static struct twl4030_power_data osc_off_idle = {
+	.scripts		= omap3_idle_scripts,
+	.num			= ARRAY_SIZE(omap3_idle_scripts),
+	.resource_config	= omap3_idle_rconfig,
+	.board_config		= osc_off_rconfig,
+};
+
+static struct of_device_id twl4030_power_of_match[] = {
+	{
+		.compatible = "ti,twl4030-power-reset",
+		.data = &omap3_reset,
+	},
+	{
+		.compatible = "ti,twl4030-power-idle",
+		.data = &omap3_idle,
+	},
+	{
+		.compatible = "ti,twl4030-power-idle-osc-off",
+		.data = &osc_off_idle,
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, twl4030_power_of_match);
+#endif	/* CONFIG_OF */
+
 static int twl4030_power_probe(struct platform_device *pdev)
 {
-	struct twl4030_power_data *pdata = dev_get_platdata(&pdev->dev);
+	const struct twl4030_power_data *pdata = dev_get_platdata(&pdev->dev);
 	struct device_node *node = pdev->dev.of_node;
+	const struct of_device_id *match;
 	int err = 0;
 	int err2 = 0;
 	u8 val;
@@ -577,8 +817,12 @@ static int twl4030_power_probe(struct platform_device *pdev)
 		return err;
 	}
 
+	match = of_match_device(of_match_ptr(twl4030_power_of_match),
+				&pdev->dev);
+	if (match && match->data)
+		pdata = match->data;
+
 	if (pdata) {
-		/* TODO: convert to device tree */
 		err = twl4030_power_configure_scripts(pdata);
 		if (err) {
 			pr_err("TWL4030 failed to load scripts\n");
@@ -628,14 +872,6 @@ static int twl4030_power_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_OF
-static const struct of_device_id twl4030_power_of_match[] = {
-	{.compatible = "ti,twl4030-power", },
-	{ },
-};
-MODULE_DEVICE_TABLE(of, twl4030_power_of_match);
-#endif
-
 static struct platform_driver twl4030_power_driver = {
 	.driver = {
 		.name	= "twl4030_power",
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index a43d0c46727..ee9402324a2 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -54,7 +54,7 @@ config AD525X_DPOT_SPI
 config ATMEL_PWM
 	tristate "Atmel AT32/AT91 PWM support"
 	depends on HAVE_CLK
-	depends on AVR32 || AT91SAM9263 || AT91SAM9RL || AT91SAM9G45
+	depends on AVR32 || ARCH_AT91SAM9263 || ARCH_AT91SAM9RL || ARCH_AT91SAM9G45
 	help
 	  This option enables device driver support for the PWM channels
 	  on certain Atmel processors.  Pulse Width Modulation is used for
diff --git a/drivers/misc/vexpress-syscfg.c b/drivers/misc/vexpress-syscfg.c
index 73068e50e56..3250fc1df0a 100644
--- a/drivers/misc/vexpress-syscfg.c
+++ b/drivers/misc/vexpress-syscfg.c
@@ -199,7 +199,7 @@ static struct regmap *vexpress_syscfg_regmap_init(struct device *dev,
 	func = kzalloc(sizeof(*func) + sizeof(*func->template) * num,
 			GFP_KERNEL);
 	if (!func)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	func->syscfg = syscfg;
 	func->num_templates = num;
@@ -231,10 +231,14 @@ static struct regmap *vexpress_syscfg_regmap_init(struct device *dev,
 	func->regmap = regmap_init(dev, NULL, func,
 			&vexpress_syscfg_regmap_config);
 
-	if (IS_ERR(func->regmap))
+	if (IS_ERR(func->regmap)) {
+		void *err = func->regmap;
+
 		kfree(func);
-	else
-		list_add(&func->list, &syscfg->funcs);
+		return err;
+	}
+
+	list_add(&func->list, &syscfg->funcs);
 
 	return func->regmap;
 }
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index 2421835d5da..19161749218 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -17,7 +17,8 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
  *
- * Maintained by: Dmitry Torokhov <dtor@vmware.com>
+ * Maintained by:	Xavier Deguillard <xdeguillard@vmware.com>
+ *			Philip Moltmann <moltmann@vmware.com>
  */
 
 /*
diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index 824644875d4..d2dbf02022b 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -341,16 +341,17 @@ int mmc_add_card(struct mmc_card *card)
 	if (mmc_host_is_spi(card->host)) {
 		pr_info("%s: new %s%s%s card on SPI\n",
 			mmc_hostname(card->host),
-			mmc_card_highspeed(card) ? "high speed " : "",
-			mmc_card_ddr_mode(card) ? "DDR " : "",
+			mmc_card_hs(card) ? "high speed " : "",
+			mmc_card_ddr52(card) ? "DDR " : "",
 			type);
 	} else {
 		pr_info("%s: new %s%s%s%s%s card at address %04x\n",
 			mmc_hostname(card->host),
 			mmc_card_uhs(card) ? "ultra high speed " :
-			(mmc_card_highspeed(card) ? "high speed " : ""),
+			(mmc_card_hs(card) ? "high speed " : ""),
+			mmc_card_hs400(card) ? "HS400 " :
 			(mmc_card_hs200(card) ? "HS200 " : ""),
-			mmc_card_ddr_mode(card) ? "DDR " : "",
+			mmc_card_ddr52(card) ? "DDR " : "",
 			uhs_bus_speed_mode, type, card->rca);
 	}
 
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index acbc3f2aaaf..7dc0c85fdb6 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -800,6 +800,10 @@ void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card)
 			data->timeout_ns = limit_us * 1000;
 			data->timeout_clks = 0;
 		}
+
+		/* assign limit value if invalid */
+		if (timeout_us == 0)
+			data->timeout_ns = limit_us * 1000;
 	}
 
 	/*
@@ -1310,31 +1314,38 @@ int mmc_regulator_set_ocr(struct mmc_host *mmc,
 }
 EXPORT_SYMBOL_GPL(mmc_regulator_set_ocr);
 
+#endif /* CONFIG_REGULATOR */
+
 int mmc_regulator_get_supply(struct mmc_host *mmc)
 {
 	struct device *dev = mmc_dev(mmc);
-	struct regulator *supply;
 	int ret;
 
-	supply = devm_regulator_get(dev, "vmmc");
-	mmc->supply.vmmc = supply;
+	mmc->supply.vmmc = devm_regulator_get_optional(dev, "vmmc");
 	mmc->supply.vqmmc = devm_regulator_get_optional(dev, "vqmmc");
 
-	if (IS_ERR(supply))
-		return PTR_ERR(supply);
+	if (IS_ERR(mmc->supply.vmmc)) {
+		if (PTR_ERR(mmc->supply.vmmc) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		dev_info(dev, "No vmmc regulator found\n");
+	} else {
+		ret = mmc_regulator_get_ocrmask(mmc->supply.vmmc);
+		if (ret > 0)
+			mmc->ocr_avail = ret;
+		else
+			dev_warn(dev, "Failed getting OCR mask: %d\n", ret);
+	}
 
-	ret = mmc_regulator_get_ocrmask(supply);
-	if (ret > 0)
-		mmc->ocr_avail = ret;
-	else
-		dev_warn(mmc_dev(mmc), "Failed getting OCR mask: %d\n", ret);
+	if (IS_ERR(mmc->supply.vqmmc)) {
+		if (PTR_ERR(mmc->supply.vqmmc) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		dev_info(dev, "No vqmmc regulator found\n");
+	}
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mmc_regulator_get_supply);
 
-#endif /* CONFIG_REGULATOR */
-
 /*
  * Mask off any voltages we don't support and select
  * the lowest voltage
@@ -1533,8 +1544,13 @@ void mmc_power_up(struct mmc_host *host, u32 ocr)
 	host->ios.timing = MMC_TIMING_LEGACY;
 	mmc_set_ios(host);
 
-	/* Set signal voltage to 3.3V */
-	__mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330);
+	/* Try to set signal voltage to 3.3V but fall back to 1.8v or 1.2v */
+	if (__mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330) == 0)
+		dev_dbg(mmc_dev(host), "Initial signal voltage of 3.3v\n");
+	else if (__mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180) == 0)
+		dev_dbg(mmc_dev(host), "Initial signal voltage of 1.8v\n");
+	else if (__mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120) == 0)
+		dev_dbg(mmc_dev(host), "Initial signal voltage of 1.2v\n");
 
 	/*
 	 * This delay should be sufficient to allow the power supply
@@ -2183,7 +2199,7 @@ int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen)
 {
 	struct mmc_command cmd = {0};
 
-	if (mmc_card_blockaddr(card) || mmc_card_ddr_mode(card))
+	if (mmc_card_blockaddr(card) || mmc_card_ddr52(card))
 		return 0;
 
 	cmd.opcode = MMC_SET_BLOCKLEN;
@@ -2263,7 +2279,6 @@ static int mmc_do_hw_reset(struct mmc_host *host, int check)
 		}
 	}
 
-	host->card->state &= ~(MMC_STATE_HIGHSPEED | MMC_STATE_HIGHSPEED_DDR);
 	if (mmc_host_is_spi(host)) {
 		host->ios.chip_select = MMC_CS_HIGH;
 		host->ios.bus_mode = MMC_BUSMODE_PUSHPULL;
@@ -2403,6 +2418,11 @@ void mmc_rescan(struct work_struct *work)
 		container_of(work, struct mmc_host, detect.work);
 	int i;
 
+	if (host->trigger_card_event && host->ops->card_event) {
+		host->ops->card_event(host);
+		host->trigger_card_event = false;
+	}
+
 	if (host->rescan_disable)
 		return;
 
diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c
index 54829c0ed00..91eb1622324 100644
--- a/drivers/mmc/core/debugfs.c
+++ b/drivers/mmc/core/debugfs.c
@@ -135,8 +135,14 @@ static int mmc_ios_show(struct seq_file *s, void *data)
 	case MMC_TIMING_UHS_DDR50:
 		str = "sd uhs DDR50";
 		break;
+	case MMC_TIMING_MMC_DDR52:
+		str = "mmc DDR52";
+		break;
 	case MMC_TIMING_MMC_HS200:
-		str = "mmc high-speed SDR200";
+		str = "mmc HS200";
+		break;
+	case MMC_TIMING_MMC_HS400:
+		str = "mmc HS400";
 		break;
 	default:
 		str = "invalid";
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index fdea825dbb2..95cceae9694 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -447,6 +447,10 @@ int mmc_of_parse(struct mmc_host *host)
 		host->caps2 |= MMC_CAP2_HS200_1_8V_SDR;
 	if (of_find_property(np, "mmc-hs200-1_2v", &len))
 		host->caps2 |= MMC_CAP2_HS200_1_2V_SDR;
+	if (of_find_property(np, "mmc-hs400-1_8v", &len))
+		host->caps2 |= MMC_CAP2_HS400_1_8V | MMC_CAP2_HS200_1_8V_SDR;
+	if (of_find_property(np, "mmc-hs400-1_2v", &len))
+		host->caps2 |= MMC_CAP2_HS400_1_2V | MMC_CAP2_HS200_1_2V_SDR;
 
 	return 0;
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 1ab5f3a0af5..793c6f7ddb0 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -240,31 +240,62 @@ static int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd)
 static void mmc_select_card_type(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
-	u8 card_type = card->ext_csd.raw_card_type & EXT_CSD_CARD_TYPE_MASK;
+	u8 card_type = card->ext_csd.raw_card_type;
 	u32 caps = host->caps, caps2 = host->caps2;
-	unsigned int hs_max_dtr = 0;
+	unsigned int hs_max_dtr = 0, hs200_max_dtr = 0;
+	unsigned int avail_type = 0;
 
-	if (card_type & EXT_CSD_CARD_TYPE_26)
+	if (caps & MMC_CAP_MMC_HIGHSPEED &&
+	    card_type & EXT_CSD_CARD_TYPE_HS_26) {
 		hs_max_dtr = MMC_HIGH_26_MAX_DTR;
+		avail_type |= EXT_CSD_CARD_TYPE_HS_26;
+	}
 
 	if (caps & MMC_CAP_MMC_HIGHSPEED &&
-			card_type & EXT_CSD_CARD_TYPE_52)
+	    card_type & EXT_CSD_CARD_TYPE_HS_52) {
 		hs_max_dtr = MMC_HIGH_52_MAX_DTR;
+		avail_type |= EXT_CSD_CARD_TYPE_HS_52;
+	}
+
+	if (caps & MMC_CAP_1_8V_DDR &&
+	    card_type & EXT_CSD_CARD_TYPE_DDR_1_8V) {
+		hs_max_dtr = MMC_HIGH_DDR_MAX_DTR;
+		avail_type |= EXT_CSD_CARD_TYPE_DDR_1_8V;
+	}
 
-	if ((caps & MMC_CAP_1_8V_DDR &&
-			card_type & EXT_CSD_CARD_TYPE_DDR_1_8V) ||
-	    (caps & MMC_CAP_1_2V_DDR &&
-			card_type & EXT_CSD_CARD_TYPE_DDR_1_2V))
+	if (caps & MMC_CAP_1_2V_DDR &&
+	    card_type & EXT_CSD_CARD_TYPE_DDR_1_2V) {
 		hs_max_dtr = MMC_HIGH_DDR_MAX_DTR;
+		avail_type |= EXT_CSD_CARD_TYPE_DDR_1_2V;
+	}
+
+	if (caps2 & MMC_CAP2_HS200_1_8V_SDR &&
+	    card_type & EXT_CSD_CARD_TYPE_HS200_1_8V) {
+		hs200_max_dtr = MMC_HS200_MAX_DTR;
+		avail_type |= EXT_CSD_CARD_TYPE_HS200_1_8V;
+	}
+
+	if (caps2 & MMC_CAP2_HS200_1_2V_SDR &&
+	    card_type & EXT_CSD_CARD_TYPE_HS200_1_2V) {
+		hs200_max_dtr = MMC_HS200_MAX_DTR;
+		avail_type |= EXT_CSD_CARD_TYPE_HS200_1_2V;
+	}
+
+	if (caps2 & MMC_CAP2_HS400_1_8V &&
+	    card_type & EXT_CSD_CARD_TYPE_HS400_1_8V) {
+		hs200_max_dtr = MMC_HS200_MAX_DTR;
+		avail_type |= EXT_CSD_CARD_TYPE_HS400_1_8V;
+	}
 
-	if ((caps2 & MMC_CAP2_HS200_1_8V_SDR &&
-			card_type & EXT_CSD_CARD_TYPE_SDR_1_8V) ||
-	    (caps2 & MMC_CAP2_HS200_1_2V_SDR &&
-			card_type & EXT_CSD_CARD_TYPE_SDR_1_2V))
-		hs_max_dtr = MMC_HS200_MAX_DTR;
+	if (caps2 & MMC_CAP2_HS400_1_2V &&
+	    card_type & EXT_CSD_CARD_TYPE_HS400_1_2V) {
+		hs200_max_dtr = MMC_HS200_MAX_DTR;
+		avail_type |= EXT_CSD_CARD_TYPE_HS400_1_2V;
+	}
 
 	card->ext_csd.hs_max_dtr = hs_max_dtr;
-	card->ext_csd.card_type = card_type;
+	card->ext_csd.hs200_max_dtr = hs200_max_dtr;
+	card->mmc_avail_type = avail_type;
 }
 
 /*
@@ -480,6 +511,8 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd)
 			ext_csd[EXT_CSD_PWR_CL_DDR_52_195];
 		card->ext_csd.raw_pwr_cl_ddr_52_360 =
 			ext_csd[EXT_CSD_PWR_CL_DDR_52_360];
+		card->ext_csd.raw_pwr_cl_ddr_200_360 =
+			ext_csd[EXT_CSD_PWR_CL_DDR_200_360];
 	}
 
 	if (card->ext_csd.rev >= 5) {
@@ -646,7 +679,10 @@ static int mmc_compare_ext_csds(struct mmc_card *card, unsigned bus_width)
 		(card->ext_csd.raw_pwr_cl_ddr_52_195 ==
 			bw_ext_csd[EXT_CSD_PWR_CL_DDR_52_195]) &&
 		(card->ext_csd.raw_pwr_cl_ddr_52_360 ==
-			bw_ext_csd[EXT_CSD_PWR_CL_DDR_52_360]));
+			bw_ext_csd[EXT_CSD_PWR_CL_DDR_52_360]) &&
+		(card->ext_csd.raw_pwr_cl_ddr_200_360 ==
+			bw_ext_csd[EXT_CSD_PWR_CL_DDR_200_360]));
+
 	if (err)
 		err = -EINVAL;
 
@@ -694,18 +730,10 @@ static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_rel_sectors.attr,
 	NULL,
 };
-
-static struct attribute_group mmc_std_attr_group = {
-	.attrs = mmc_std_attrs,
-};
-
-static const struct attribute_group *mmc_attr_groups[] = {
-	&mmc_std_attr_group,
-	NULL,
-};
+ATTRIBUTE_GROUPS(mmc_std);
 
 static struct device_type mmc_type = {
-	.groups = mmc_attr_groups,
+	.groups = mmc_std_groups,
 };
 
 /*
@@ -714,17 +742,13 @@ static struct device_type mmc_type = {
  * extended CSD register, select it by executing the
  * mmc_switch command.
  */
-static int mmc_select_powerclass(struct mmc_card *card,
-		unsigned int bus_width)
+static int __mmc_select_powerclass(struct mmc_card *card,
+				   unsigned int bus_width)
 {
-	int err = 0;
+	struct mmc_host *host = card->host;
+	struct mmc_ext_csd *ext_csd = &card->ext_csd;
 	unsigned int pwrclass_val = 0;
-	struct mmc_host *host;
-
-	BUG_ON(!card);
-
-	host = card->host;
-	BUG_ON(!host);
+	int err = 0;
 
 	/* Power class selection is supported for versions >= 4.0 */
 	if (card->csd.mmca_vsn < CSD_SPEC_VER_4)
@@ -736,14 +760,14 @@ static int mmc_select_powerclass(struct mmc_card *card,
 
 	switch (1 << host->ios.vdd) {
 	case MMC_VDD_165_195:
-		if (host->ios.clock <= 26000000)
-			pwrclass_val = card->ext_csd.raw_pwr_cl_26_195;
-		else if	(host->ios.clock <= 52000000)
+		if (host->ios.clock <= MMC_HIGH_26_MAX_DTR)
+			pwrclass_val = ext_csd->raw_pwr_cl_26_195;
+		else if (host->ios.clock <= MMC_HIGH_52_MAX_DTR)
 			pwrclass_val = (bus_width <= EXT_CSD_BUS_WIDTH_8) ?
-				card->ext_csd.raw_pwr_cl_52_195 :
-				card->ext_csd.raw_pwr_cl_ddr_52_195;
-		else if (host->ios.clock <= 200000000)
-			pwrclass_val = card->ext_csd.raw_pwr_cl_200_195;
+				ext_csd->raw_pwr_cl_52_195 :
+				ext_csd->raw_pwr_cl_ddr_52_195;
+		else if (host->ios.clock <= MMC_HS200_MAX_DTR)
+			pwrclass_val = ext_csd->raw_pwr_cl_200_195;
 		break;
 	case MMC_VDD_27_28:
 	case MMC_VDD_28_29:
@@ -754,14 +778,16 @@ static int mmc_select_powerclass(struct mmc_card *card,
 	case MMC_VDD_33_34:
 	case MMC_VDD_34_35:
 	case MMC_VDD_35_36:
-		if (host->ios.clock <= 26000000)
-			pwrclass_val = card->ext_csd.raw_pwr_cl_26_360;
-		else if	(host->ios.clock <= 52000000)
+		if (host->ios.clock <= MMC_HIGH_26_MAX_DTR)
+			pwrclass_val = ext_csd->raw_pwr_cl_26_360;
+		else if (host->ios.clock <= MMC_HIGH_52_MAX_DTR)
 			pwrclass_val = (bus_width <= EXT_CSD_BUS_WIDTH_8) ?
-				card->ext_csd.raw_pwr_cl_52_360 :
-				card->ext_csd.raw_pwr_cl_ddr_52_360;
-		else if (host->ios.clock <= 200000000)
-			pwrclass_val = card->ext_csd.raw_pwr_cl_200_360;
+				ext_csd->raw_pwr_cl_52_360 :
+				ext_csd->raw_pwr_cl_ddr_52_360;
+		else if (host->ios.clock <= MMC_HS200_MAX_DTR)
+			pwrclass_val = (bus_width == EXT_CSD_DDR_BUS_WIDTH_8) ?
+				ext_csd->raw_pwr_cl_ddr_200_360 :
+				ext_csd->raw_pwr_cl_200_360;
 		break;
 	default:
 		pr_warning("%s: Voltage range not supported "
@@ -787,40 +813,79 @@ static int mmc_select_powerclass(struct mmc_card *card,
 	return err;
 }
 
+static int mmc_select_powerclass(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	u32 bus_width, ext_csd_bits;
+	int err, ddr;
+
+	/* Power class selection is supported for versions >= 4.0 */
+	if (card->csd.mmca_vsn < CSD_SPEC_VER_4)
+		return 0;
+
+	bus_width = host->ios.bus_width;
+	/* Power class values are defined only for 4/8 bit bus */
+	if (bus_width == MMC_BUS_WIDTH_1)
+		return 0;
+
+	ddr = card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_52;
+	if (ddr)
+		ext_csd_bits = (bus_width == MMC_BUS_WIDTH_8) ?
+			EXT_CSD_DDR_BUS_WIDTH_8 : EXT_CSD_DDR_BUS_WIDTH_4;
+	else
+		ext_csd_bits = (bus_width == MMC_BUS_WIDTH_8) ?
+			EXT_CSD_BUS_WIDTH_8 :  EXT_CSD_BUS_WIDTH_4;
+
+	err = __mmc_select_powerclass(card, ext_csd_bits);
+	if (err)
+		pr_warn("%s: power class selection to bus width %d ddr %d failed\n",
+			mmc_hostname(host), 1 << bus_width, ddr);
+
+	return err;
+}
+
 /*
- * Selects the desired buswidth and switch to the HS200 mode
- * if bus width set without error
+ * Set the bus speed for the selected speed mode.
  */
-static int mmc_select_hs200(struct mmc_card *card)
+static void mmc_set_bus_speed(struct mmc_card *card)
+{
+	unsigned int max_dtr = (unsigned int)-1;
+
+	if ((mmc_card_hs200(card) || mmc_card_hs400(card)) &&
+	     max_dtr > card->ext_csd.hs200_max_dtr)
+		max_dtr = card->ext_csd.hs200_max_dtr;
+	else if (mmc_card_hs(card) && max_dtr > card->ext_csd.hs_max_dtr)
+		max_dtr = card->ext_csd.hs_max_dtr;
+	else if (max_dtr > card->csd.max_dtr)
+		max_dtr = card->csd.max_dtr;
+
+	mmc_set_clock(card->host, max_dtr);
+}
+
+/*
+ * Select the bus width amoung 4-bit and 8-bit(SDR).
+ * If the bus width is changed successfully, return the selected width value.
+ * Zero is returned instead of error value if the wide width is not supported.
+ */
+static int mmc_select_bus_width(struct mmc_card *card)
 {
-	int idx, err = -EINVAL;
-	struct mmc_host *host;
 	static unsigned ext_csd_bits[] = {
-		EXT_CSD_BUS_WIDTH_4,
 		EXT_CSD_BUS_WIDTH_8,
+		EXT_CSD_BUS_WIDTH_4,
 	};
 	static unsigned bus_widths[] = {
-		MMC_BUS_WIDTH_4,
 		MMC_BUS_WIDTH_8,
+		MMC_BUS_WIDTH_4,
 	};
+	struct mmc_host *host = card->host;
+	unsigned idx, bus_width = 0;
+	int err = 0;
 
-	BUG_ON(!card);
-
-	host = card->host;
-
-	if (card->ext_csd.card_type & EXT_CSD_CARD_TYPE_SDR_1_2V &&
-			host->caps2 & MMC_CAP2_HS200_1_2V_SDR)
-		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
-
-	if (err && card->ext_csd.card_type & EXT_CSD_CARD_TYPE_SDR_1_8V &&
-			host->caps2 & MMC_CAP2_HS200_1_8V_SDR)
-		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
-
-	/* If fails try again during next card power cycle */
-	if (err)
-		goto err;
+	if ((card->csd.mmca_vsn < CSD_SPEC_VER_4) &&
+	    !(host->caps & (MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA)))
+		return 0;
 
-	idx = (host->caps & MMC_CAP_8_BIT_DATA) ? 1 : 0;
+	idx = (host->caps & MMC_CAP_8_BIT_DATA) ? 0 : 1;
 
 	/*
 	 * Unlike SD, MMC cards dont have a configuration register to notify
@@ -828,8 +893,7 @@ static int mmc_select_hs200(struct mmc_card *card)
 	 * the supported bus width or compare the ext csd values of current
 	 * bus width and ext csd values of 1 bit mode read earlier.
 	 */
-	for (; idx >= 0; idx--) {
-
+	for (; idx < ARRAY_SIZE(bus_widths); idx++) {
 		/*
 		 * Host is capable of 8bit transfer, then switch
 		 * the device to work in 8bit transfer mode. If the
@@ -844,27 +908,266 @@ static int mmc_select_hs200(struct mmc_card *card)
 		if (err)
 			continue;
 
-		mmc_set_bus_width(card->host, bus_widths[idx]);
+		bus_width = bus_widths[idx];
+		mmc_set_bus_width(host, bus_width);
 
+		/*
+		 * If controller can't handle bus width test,
+		 * compare ext_csd previously read in 1 bit mode
+		 * against ext_csd at new bus width
+		 */
 		if (!(host->caps & MMC_CAP_BUS_WIDTH_TEST))
-			err = mmc_compare_ext_csds(card, bus_widths[idx]);
+			err = mmc_compare_ext_csds(card, bus_width);
 		else
-			err = mmc_bus_test(card, bus_widths[idx]);
-		if (!err)
+			err = mmc_bus_test(card, bus_width);
+
+		if (!err) {
+			err = bus_width;
 			break;
+		} else {
+			pr_warn("%s: switch to bus width %d failed\n",
+				mmc_hostname(host), ext_csd_bits[idx]);
+		}
 	}
 
-	/* switch to HS200 mode if bus width set successfully */
+	return err;
+}
+
+/*
+ * Switch to the high-speed mode
+ */
+static int mmc_select_hs(struct mmc_card *card)
+{
+	int err;
+
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS,
+			   card->ext_csd.generic_cmd6_time,
+			   true, true, true);
 	if (!err)
+		mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
+
+	return err;
+}
+
+/*
+ * Activate wide bus and DDR if supported.
+ */
+static int mmc_select_hs_ddr(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	u32 bus_width, ext_csd_bits;
+	int err = 0;
+
+	if (!(card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_52))
+		return 0;
+
+	bus_width = host->ios.bus_width;
+	if (bus_width == MMC_BUS_WIDTH_1)
+		return 0;
+
+	ext_csd_bits = (bus_width == MMC_BUS_WIDTH_8) ?
+		EXT_CSD_DDR_BUS_WIDTH_8 : EXT_CSD_DDR_BUS_WIDTH_4;
+
+	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			EXT_CSD_BUS_WIDTH,
+			ext_csd_bits,
+			card->ext_csd.generic_cmd6_time);
+	if (err) {
+		pr_warn("%s: switch to bus width %d ddr failed\n",
+			mmc_hostname(host), 1 << bus_width);
+		return err;
+	}
+
+	/*
+	 * eMMC cards can support 3.3V to 1.2V i/o (vccq)
+	 * signaling.
+	 *
+	 * EXT_CSD_CARD_TYPE_DDR_1_8V means 3.3V or 1.8V vccq.
+	 *
+	 * 1.8V vccq at 3.3V core voltage (vcc) is not required
+	 * in the JEDEC spec for DDR.
+	 *
+	 * Do not force change in vccq since we are obviously
+	 * working and no change to vccq is needed.
+	 *
+	 * WARNING: eMMC rules are NOT the same as SD DDR
+	 */
+	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_1_2V) {
+		err = __mmc_set_signal_voltage(host,
+				MMC_SIGNAL_VOLTAGE_120);
+		if (err)
+			return err;
+	}
+
+	mmc_set_timing(host, MMC_TIMING_MMC_DDR52);
+
+	return err;
+}
+
+static int mmc_select_hs400(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	int err = 0;
+
+	/*
+	 * HS400 mode requires 8-bit bus width
+	 */
+	if (!(card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400 &&
+	      host->ios.bus_width == MMC_BUS_WIDTH_8))
+		return 0;
+
+	/*
+	 * Before switching to dual data rate operation for HS400,
+	 * it is required to convert from HS200 mode to HS mode.
+	 */
+	mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
+	mmc_set_bus_speed(card);
+
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS,
+			   card->ext_csd.generic_cmd6_time,
+			   true, true, true);
+	if (err) {
+		pr_warn("%s: switch to high-speed from hs200 failed, err:%d\n",
+			mmc_hostname(host), err);
+		return err;
+	}
+
+	err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			 EXT_CSD_BUS_WIDTH,
+			 EXT_CSD_DDR_BUS_WIDTH_8,
+			 card->ext_csd.generic_cmd6_time);
+	if (err) {
+		pr_warn("%s: switch to bus width for hs400 failed, err:%d\n",
+			mmc_hostname(host), err);
+		return err;
+	}
+
+	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+			   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS400,
+			   card->ext_csd.generic_cmd6_time,
+			   true, true, true);
+	if (err) {
+		pr_warn("%s: switch to hs400 failed, err:%d\n",
+			 mmc_hostname(host), err);
+		return err;
+	}
+
+	mmc_set_timing(host, MMC_TIMING_MMC_HS400);
+	mmc_set_bus_speed(card);
+
+	return 0;
+}
+
+/*
+ * For device supporting HS200 mode, the following sequence
+ * should be done before executing the tuning process.
+ * 1. set the desired bus width(4-bit or 8-bit, 1-bit is not supported)
+ * 2. switch to HS200 mode
+ * 3. set the clock to > 52Mhz and <=200MHz
+ */
+static int mmc_select_hs200(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	int err = -EINVAL;
+
+	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS200_1_2V)
+		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
+
+	if (err && card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS200_1_8V)
+		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
+
+	/* If fails try again during next card power cycle */
+	if (err)
+		goto err;
+
+	/*
+	 * Set the bus width(4 or 8) with host's support and
+	 * switch to HS200 mode if bus width is set successfully.
+	 */
+	err = mmc_select_bus_width(card);
+	if (!IS_ERR_VALUE(err)) {
 		err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-				EXT_CSD_HS_TIMING, 2,
-				card->ext_csd.generic_cmd6_time,
-				true, true, true);
+				   EXT_CSD_HS_TIMING, EXT_CSD_TIMING_HS200,
+				   card->ext_csd.generic_cmd6_time,
+				   true, true, true);
+		if (!err)
+			mmc_set_timing(host, MMC_TIMING_MMC_HS200);
+	}
 err:
 	return err;
 }
 
 /*
+ * Activate High Speed or HS200 mode if supported.
+ */
+static int mmc_select_timing(struct mmc_card *card)
+{
+	int err = 0;
+
+	if ((card->csd.mmca_vsn < CSD_SPEC_VER_4 &&
+	     card->ext_csd.hs_max_dtr == 0))
+		goto bus_speed;
+
+	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS200)
+		err = mmc_select_hs200(card);
+	else if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS)
+		err = mmc_select_hs(card);
+
+	if (err && err != -EBADMSG)
+		return err;
+
+	if (err) {
+		pr_warn("%s: switch to %s failed\n",
+			mmc_card_hs(card) ? "high-speed" :
+			(mmc_card_hs200(card) ? "hs200" : ""),
+			mmc_hostname(card->host));
+		err = 0;
+	}
+
+bus_speed:
+	/*
+	 * Set the bus speed to the selected bus timing.
+	 * If timing is not selected, backward compatible is the default.
+	 */
+	mmc_set_bus_speed(card);
+	return err;
+}
+
+/*
+ * Execute tuning sequence to seek the proper bus operating
+ * conditions for HS200 and HS400, which sends CMD21 to the device.
+ */
+static int mmc_hs200_tuning(struct mmc_card *card)
+{
+	struct mmc_host *host = card->host;
+	int err = 0;
+
+	/*
+	 * Timing should be adjusted to the HS400 target
+	 * operation frequency for tuning process
+	 */
+	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400 &&
+	    host->ios.bus_width == MMC_BUS_WIDTH_8)
+		if (host->ops->prepare_hs400_tuning)
+			host->ops->prepare_hs400_tuning(host, &host->ios);
+
+	if (host->ops->execute_tuning) {
+		mmc_host_clk_hold(host);
+		err = host->ops->execute_tuning(host,
+				MMC_SEND_TUNING_BLOCK_HS200);
+		mmc_host_clk_release(host);
+
+		if (err)
+			pr_warn("%s: tuning execution failed\n",
+				mmc_hostname(host));
+	}
+
+	return err;
+}
+
+/*
  * Handle the detection and initialisation of a card.
  *
  * In the case of a resume, "oldcard" will contain the card
@@ -874,9 +1177,8 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	struct mmc_card *oldcard)
 {
 	struct mmc_card *card;
-	int err, ddr = 0;
+	int err;
 	u32 cid[4];
-	unsigned int max_dtr;
 	u32 rocr;
 	u8 *ext_csd = NULL;
 
@@ -1068,206 +1370,34 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	}
 
 	/*
-	 * Activate high speed (if supported)
-	 */
-	if (card->ext_csd.hs_max_dtr != 0) {
-		err = 0;
-		if (card->ext_csd.hs_max_dtr > 52000000 &&
-		    host->caps2 & MMC_CAP2_HS200)
-			err = mmc_select_hs200(card);
-		else if	(host->caps & MMC_CAP_MMC_HIGHSPEED)
-			err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-					EXT_CSD_HS_TIMING, 1,
-					card->ext_csd.generic_cmd6_time,
-					true, true, true);
-
-		if (err && err != -EBADMSG)
-			goto free_card;
-
-		if (err) {
-			pr_warning("%s: switch to highspeed failed\n",
-			       mmc_hostname(card->host));
-			err = 0;
-		} else {
-			if (card->ext_csd.hs_max_dtr > 52000000 &&
-			    host->caps2 & MMC_CAP2_HS200) {
-				mmc_card_set_hs200(card);
-				mmc_set_timing(card->host,
-					       MMC_TIMING_MMC_HS200);
-			} else {
-				mmc_card_set_highspeed(card);
-				mmc_set_timing(card->host, MMC_TIMING_MMC_HS);
-			}
-		}
-	}
-
-	/*
-	 * Compute bus speed.
-	 */
-	max_dtr = (unsigned int)-1;
-
-	if (mmc_card_highspeed(card) || mmc_card_hs200(card)) {
-		if (max_dtr > card->ext_csd.hs_max_dtr)
-			max_dtr = card->ext_csd.hs_max_dtr;
-		if (mmc_card_highspeed(card) && (max_dtr > 52000000))
-			max_dtr = 52000000;
-	} else if (max_dtr > card->csd.max_dtr) {
-		max_dtr = card->csd.max_dtr;
-	}
-
-	mmc_set_clock(host, max_dtr);
-
-	/*
-	 * Indicate DDR mode (if supported).
+	 * Select timing interface
 	 */
-	if (mmc_card_highspeed(card)) {
-		if ((card->ext_csd.card_type & EXT_CSD_CARD_TYPE_DDR_1_8V)
-			&& (host->caps & MMC_CAP_1_8V_DDR))
-				ddr = MMC_1_8V_DDR_MODE;
-		else if ((card->ext_csd.card_type & EXT_CSD_CARD_TYPE_DDR_1_2V)
-			&& (host->caps & MMC_CAP_1_2V_DDR))
-				ddr = MMC_1_2V_DDR_MODE;
-	}
+	err = mmc_select_timing(card);
+	if (err)
+		goto free_card;
 
-	/*
-	 * Indicate HS200 SDR mode (if supported).
-	 */
 	if (mmc_card_hs200(card)) {
-		u32 ext_csd_bits;
-		u32 bus_width = card->host->ios.bus_width;
-
-		/*
-		 * For devices supporting HS200 mode, the bus width has
-		 * to be set before executing the tuning function. If
-		 * set before tuning, then device will respond with CRC
-		 * errors for responses on CMD line. So for HS200 the
-		 * sequence will be
-		 * 1. set bus width 4bit / 8 bit (1 bit not supported)
-		 * 2. switch to HS200 mode
-		 * 3. set the clock to > 52Mhz <=200MHz and
-		 * 4. execute tuning for HS200
-		 */
-		if ((host->caps2 & MMC_CAP2_HS200) &&
-		    card->host->ops->execute_tuning) {
-			mmc_host_clk_hold(card->host);
-			err = card->host->ops->execute_tuning(card->host,
-				MMC_SEND_TUNING_BLOCK_HS200);
-			mmc_host_clk_release(card->host);
-		}
-		if (err) {
-			pr_warning("%s: tuning execution failed\n",
-				   mmc_hostname(card->host));
+		err = mmc_hs200_tuning(card);
+		if (err)
 			goto err;
-		}
 
-		ext_csd_bits = (bus_width == MMC_BUS_WIDTH_8) ?
-				EXT_CSD_BUS_WIDTH_8 : EXT_CSD_BUS_WIDTH_4;
-		err = mmc_select_powerclass(card, ext_csd_bits);
+		err = mmc_select_hs400(card);
 		if (err)
-			pr_warning("%s: power class selection to bus width %d"
-				   " failed\n", mmc_hostname(card->host),
-				   1 << bus_width);
+			goto err;
+	} else if (mmc_card_hs(card)) {
+		/* Select the desired bus width optionally */
+		err = mmc_select_bus_width(card);
+		if (!IS_ERR_VALUE(err)) {
+			err = mmc_select_hs_ddr(card);
+			if (err)
+				goto err;
+		}
 	}
 
 	/*
-	 * Activate wide bus and DDR (if supported).
+	 * Choose the power class with selected bus interface
 	 */
-	if (!mmc_card_hs200(card) &&
-	    (card->csd.mmca_vsn >= CSD_SPEC_VER_4) &&
-	    (host->caps & (MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA))) {
-		static unsigned ext_csd_bits[][2] = {
-			{ EXT_CSD_BUS_WIDTH_8, EXT_CSD_DDR_BUS_WIDTH_8 },
-			{ EXT_CSD_BUS_WIDTH_4, EXT_CSD_DDR_BUS_WIDTH_4 },
-			{ EXT_CSD_BUS_WIDTH_1, EXT_CSD_BUS_WIDTH_1 },
-		};
-		static unsigned bus_widths[] = {
-			MMC_BUS_WIDTH_8,
-			MMC_BUS_WIDTH_4,
-			MMC_BUS_WIDTH_1
-		};
-		unsigned idx, bus_width = 0;
-
-		if (host->caps & MMC_CAP_8_BIT_DATA)
-			idx = 0;
-		else
-			idx = 1;
-		for (; idx < ARRAY_SIZE(bus_widths); idx++) {
-			bus_width = bus_widths[idx];
-			if (bus_width == MMC_BUS_WIDTH_1)
-				ddr = 0; /* no DDR for 1-bit width */
-			err = mmc_select_powerclass(card, ext_csd_bits[idx][0]);
-			if (err)
-				pr_warning("%s: power class selection to "
-					   "bus width %d failed\n",
-					   mmc_hostname(card->host),
-					   1 << bus_width);
-
-			err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-					 EXT_CSD_BUS_WIDTH,
-					 ext_csd_bits[idx][0],
-					 card->ext_csd.generic_cmd6_time);
-			if (!err) {
-				mmc_set_bus_width(card->host, bus_width);
-
-				/*
-				 * If controller can't handle bus width test,
-				 * compare ext_csd previously read in 1 bit mode
-				 * against ext_csd at new bus width
-				 */
-				if (!(host->caps & MMC_CAP_BUS_WIDTH_TEST))
-					err = mmc_compare_ext_csds(card,
-						bus_width);
-				else
-					err = mmc_bus_test(card, bus_width);
-				if (!err)
-					break;
-			}
-		}
-
-		if (!err && ddr) {
-			err = mmc_select_powerclass(card, ext_csd_bits[idx][1]);
-			if (err)
-				pr_warning("%s: power class selection to "
-					   "bus width %d ddr %d failed\n",
-					   mmc_hostname(card->host),
-					   1 << bus_width, ddr);
-
-			err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-					 EXT_CSD_BUS_WIDTH,
-					 ext_csd_bits[idx][1],
-					 card->ext_csd.generic_cmd6_time);
-		}
-		if (err) {
-			pr_warning("%s: switch to bus width %d ddr %d "
-				"failed\n", mmc_hostname(card->host),
-				1 << bus_width, ddr);
-			goto free_card;
-		} else if (ddr) {
-			/*
-			 * eMMC cards can support 3.3V to 1.2V i/o (vccq)
-			 * signaling.
-			 *
-			 * EXT_CSD_CARD_TYPE_DDR_1_8V means 3.3V or 1.8V vccq.
-			 *
-			 * 1.8V vccq at 3.3V core voltage (vcc) is not required
-			 * in the JEDEC spec for DDR.
-			 *
-			 * Do not force change in vccq since we are obviously
-			 * working and no change to vccq is needed.
-			 *
-			 * WARNING: eMMC rules are NOT the same as SD DDR
-			 */
-			if (ddr == MMC_1_2V_DDR_MODE) {
-				err = __mmc_set_signal_voltage(host,
-					MMC_SIGNAL_VOLTAGE_120);
-				if (err)
-					goto err;
-			}
-			mmc_card_set_ddr_mode(card);
-			mmc_set_timing(card->host, MMC_TIMING_UHS_DDR50);
-			mmc_set_bus_width(card->host, bus_width);
-		}
-	}
+	mmc_select_powerclass(card);
 
 	/*
 	 * Enable HPI feature (if supported)
@@ -1507,7 +1637,6 @@ static int _mmc_suspend(struct mmc_host *host, bool is_suspend)
 		err = mmc_sleep(host);
 	else if (!mmc_host_is_spi(host))
 		err = mmc_deselect_cards(host);
-	host->card->state &= ~(MMC_STATE_HIGHSPEED | MMC_STATE_HIGHSPEED_200);
 
 	if (!err) {
 		mmc_power_off(host);
@@ -1637,7 +1766,6 @@ static int mmc_power_restore(struct mmc_host *host)
 {
 	int ret;
 
-	host->card->state &= ~(MMC_STATE_HIGHSPEED | MMC_STATE_HIGHSPEED_200);
 	mmc_claim_host(host);
 	ret = mmc_init_card(host, host->card->ocr, host->card);
 	mmc_release_host(host);
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 2dd359d2242..0c44510bf71 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -707,18 +707,10 @@ static struct attribute *sd_std_attrs[] = {
 	&dev_attr_serial.attr,
 	NULL,
 };
-
-static struct attribute_group sd_std_attr_group = {
-	.attrs = sd_std_attrs,
-};
-
-static const struct attribute_group *sd_attr_groups[] = {
-	&sd_std_attr_group,
-	NULL,
-};
+ATTRIBUTE_GROUPS(sd_std);
 
 struct device_type sd_type = {
-	.groups = sd_attr_groups,
+	.groups = sd_std_groups,
 };
 
 /*
@@ -895,7 +887,7 @@ unsigned mmc_sd_get_max_clock(struct mmc_card *card)
 {
 	unsigned max_dtr = (unsigned int)-1;
 
-	if (mmc_card_highspeed(card)) {
+	if (mmc_card_hs(card)) {
 		if (max_dtr > card->sw_caps.hs_max_dtr)
 			max_dtr = card->sw_caps.hs_max_dtr;
 	} else if (max_dtr > card->csd.max_dtr) {
@@ -905,12 +897,6 @@ unsigned mmc_sd_get_max_clock(struct mmc_card *card)
 	return max_dtr;
 }
 
-void mmc_sd_go_highspeed(struct mmc_card *card)
-{
-	mmc_card_set_highspeed(card);
-	mmc_set_timing(card->host, MMC_TIMING_SD_HS);
-}
-
 /*
  * Handle the detection and initialisation of a card.
  *
@@ -985,16 +971,13 @@ static int mmc_sd_init_card(struct mmc_host *host, u32 ocr,
 		err = mmc_sd_init_uhs_card(card);
 		if (err)
 			goto free_card;
-
-		/* Card is an ultra-high-speed card */
-		mmc_card_set_uhs(card);
 	} else {
 		/*
 		 * Attempt to change to high-speed (if supported)
 		 */
 		err = mmc_sd_switch_hs(card);
 		if (err > 0)
-			mmc_sd_go_highspeed(card);
+			mmc_set_timing(card->host, MMC_TIMING_SD_HS);
 		else if (err)
 			goto free_card;
 
@@ -1089,7 +1072,7 @@ static int _mmc_sd_suspend(struct mmc_host *host)
 
 	if (!mmc_host_is_spi(host))
 		err = mmc_deselect_cards(host);
-	host->card->state &= ~MMC_STATE_HIGHSPEED;
+
 	if (!err) {
 		mmc_power_off(host);
 		mmc_card_set_suspended(host->card);
@@ -1198,7 +1181,6 @@ static int mmc_sd_power_restore(struct mmc_host *host)
 {
 	int ret;
 
-	host->card->state &= ~MMC_STATE_HIGHSPEED;
 	mmc_claim_host(host);
 	ret = mmc_sd_init_card(host, host->card->ocr, host->card);
 	mmc_release_host(host);
diff --git a/drivers/mmc/core/sd.h b/drivers/mmc/core/sd.h
index 4b34b24f3f7..aab824a9a7f 100644
--- a/drivers/mmc/core/sd.h
+++ b/drivers/mmc/core/sd.h
@@ -12,6 +12,5 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card,
 	bool reinit);
 unsigned mmc_sd_get_max_clock(struct mmc_card *card);
 int mmc_sd_switch_hs(struct mmc_card *card);
-void mmc_sd_go_highspeed(struct mmc_card *card);
 
 #endif
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index 4d721c6e2af..e636d9e99e4 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -363,7 +363,7 @@ static unsigned mmc_sdio_get_max_clock(struct mmc_card *card)
 {
 	unsigned max_dtr;
 
-	if (mmc_card_highspeed(card)) {
+	if (mmc_card_hs(card)) {
 		/*
 		 * The SDIO specification doesn't mention how
 		 * the CIS transfer speed register relates to
@@ -733,7 +733,6 @@ try_again:
 		mmc_set_clock(host, card->cis.max_dtr);
 
 		if (card->cccr.high_speed) {
-			mmc_card_set_highspeed(card);
 			mmc_set_timing(card->host, MMC_TIMING_SD_HS);
 		}
 
@@ -792,16 +791,13 @@ try_again:
 		err = mmc_sdio_init_uhs_card(card);
 		if (err)
 			goto remove;
-
-		/* Card is an ultra-high-speed card */
-		mmc_card_set_uhs(card);
 	} else {
 		/*
 		 * Switch to high-speed (if supported).
 		 */
 		err = sdio_enable_hs(card);
 		if (err > 0)
-			mmc_sd_go_highspeed(card);
+			mmc_set_timing(card->host, MMC_TIMING_SD_HS);
 		else if (err)
 			goto remove;
 
@@ -943,40 +939,21 @@ static int mmc_sdio_pre_suspend(struct mmc_host *host)
  */
 static int mmc_sdio_suspend(struct mmc_host *host)
 {
-	int i, err = 0;
-
-	for (i = 0; i < host->card->sdio_funcs; i++) {
-		struct sdio_func *func = host->card->sdio_func[i];
-		if (func && sdio_func_present(func) && func->dev.driver) {
-			const struct dev_pm_ops *pmops = func->dev.driver->pm;
-			err = pmops->suspend(&func->dev);
-			if (err)
-				break;
-		}
-	}
-	while (err && --i >= 0) {
-		struct sdio_func *func = host->card->sdio_func[i];
-		if (func && sdio_func_present(func) && func->dev.driver) {
-			const struct dev_pm_ops *pmops = func->dev.driver->pm;
-			pmops->resume(&func->dev);
-		}
-	}
-
-	if (!err && mmc_card_keep_power(host) && mmc_card_wake_sdio_irq(host)) {
+	if (mmc_card_keep_power(host) && mmc_card_wake_sdio_irq(host)) {
 		mmc_claim_host(host);
 		sdio_disable_wide(host->card);
 		mmc_release_host(host);
 	}
 
-	if (!err && !mmc_card_keep_power(host))
+	if (!mmc_card_keep_power(host))
 		mmc_power_off(host);
 
-	return err;
+	return 0;
 }
 
 static int mmc_sdio_resume(struct mmc_host *host)
 {
-	int i, err = 0;
+	int err = 0;
 
 	BUG_ON(!host);
 	BUG_ON(!host->card);
@@ -1019,24 +996,6 @@ static int mmc_sdio_resume(struct mmc_host *host)
 		wake_up_process(host->sdio_irq_thread);
 	mmc_release_host(host);
 
-	/*
-	 * If the card looked to be the same as before suspending, then
-	 * we proceed to resume all card functions.  If one of them returns
-	 * an error then we simply return that error to the core and the
-	 * card will be redetected as new.  It is the responsibility of
-	 * the function driver to perform further tests with the extra
-	 * knowledge it has of the card to confirm the card is indeed the
-	 * same as before suspending (same MAC address for network cards,
-	 * etc.) and return an error otherwise.
-	 */
-	for (i = 0; !err && i < host->card->sdio_funcs; i++) {
-		struct sdio_func *func = host->card->sdio_func[i];
-		if (func && sdio_func_present(func) && func->dev.driver) {
-			const struct dev_pm_ops *pmops = func->dev.driver->pm;
-			err = pmops->resume(&func->dev);
-		}
-	}
-
 	host->pm_flags &= ~MMC_PM_KEEP_POWER;
 	return err;
 }
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 92d1ba8e815..4fa8fef9147 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -197,20 +197,8 @@ static int sdio_bus_remove(struct device *dev)
 
 #ifdef CONFIG_PM
 
-#ifdef CONFIG_PM_SLEEP
-static int pm_no_operation(struct device *dev)
-{
-	/*
-	 * Prevent the PM core from calling SDIO device drivers' suspend
-	 * callback routines, which it is not supposed to do, by using this
-	 * empty function as the bus type suspend callaback for SDIO.
-	 */
-	return 0;
-}
-#endif
-
 static const struct dev_pm_ops sdio_bus_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(pm_no_operation, pm_no_operation)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_generic_suspend, pm_generic_resume)
 	SET_RUNTIME_PM_OPS(
 		pm_generic_runtime_suspend,
 		pm_generic_runtime_resume,
diff --git a/drivers/mmc/core/sdio_irq.c b/drivers/mmc/core/sdio_irq.c
index aaa90460ed2..5cc13c8d35b 100644
--- a/drivers/mmc/core/sdio_irq.c
+++ b/drivers/mmc/core/sdio_irq.c
@@ -90,6 +90,15 @@ static int process_sdio_pending_irqs(struct mmc_host *host)
 	return ret;
 }
 
+void sdio_run_irqs(struct mmc_host *host)
+{
+	mmc_claim_host(host);
+	host->sdio_irq_pending = true;
+	process_sdio_pending_irqs(host);
+	mmc_release_host(host);
+}
+EXPORT_SYMBOL_GPL(sdio_run_irqs);
+
 static int sdio_irq_thread(void *_host)
 {
 	struct mmc_host *host = _host;
@@ -189,14 +198,20 @@ static int sdio_card_irq_get(struct mmc_card *card)
 	WARN_ON(!host->claimed);
 
 	if (!host->sdio_irqs++) {
-		atomic_set(&host->sdio_irq_thread_abort, 0);
-		host->sdio_irq_thread =
-			kthread_run(sdio_irq_thread, host, "ksdioirqd/%s",
-				mmc_hostname(host));
-		if (IS_ERR(host->sdio_irq_thread)) {
-			int err = PTR_ERR(host->sdio_irq_thread);
-			host->sdio_irqs--;
-			return err;
+		if (!(host->caps2 & MMC_CAP2_SDIO_IRQ_NOTHREAD)) {
+			atomic_set(&host->sdio_irq_thread_abort, 0);
+			host->sdio_irq_thread =
+				kthread_run(sdio_irq_thread, host,
+					    "ksdioirqd/%s", mmc_hostname(host));
+			if (IS_ERR(host->sdio_irq_thread)) {
+				int err = PTR_ERR(host->sdio_irq_thread);
+				host->sdio_irqs--;
+				return err;
+			}
+		} else {
+			mmc_host_clk_hold(host);
+			host->ops->enable_sdio_irq(host, 1);
+			mmc_host_clk_release(host);
 		}
 	}
 
@@ -211,8 +226,14 @@ static int sdio_card_irq_put(struct mmc_card *card)
 	BUG_ON(host->sdio_irqs < 1);
 
 	if (!--host->sdio_irqs) {
-		atomic_set(&host->sdio_irq_thread_abort, 1);
-		kthread_stop(host->sdio_irq_thread);
+		if (!(host->caps2 & MMC_CAP2_SDIO_IRQ_NOTHREAD)) {
+			atomic_set(&host->sdio_irq_thread_abort, 1);
+			kthread_stop(host->sdio_irq_thread);
+		} else {
+			mmc_host_clk_hold(host);
+			host->ops->enable_sdio_irq(host, 0);
+			mmc_host_clk_release(host);
+		}
 	}
 
 	return 0;
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index f7650b899e3..5f89cb83d5f 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -32,9 +32,7 @@ static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id)
 	/* Schedule a card detection after a debounce timeout */
 	struct mmc_host *host = dev_id;
 
-	if (host->ops->card_event)
-		host->ops->card_event(host);
-
+	host->trigger_card_event = true;
 	mmc_detect_change(host, msecs_to_jiffies(200));
 
 	return IRQ_HANDLED;
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 779368b683d..a5652548230 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -168,7 +168,7 @@ config MMC_SDHCI_ESDHC_IMX
 
 config MMC_SDHCI_DOVE
 	tristate "SDHCI support on Marvell's Dove SoC"
-	depends on ARCH_DOVE
+	depends on ARCH_DOVE || MACH_DOVE
 	depends on MMC_SDHCI_PLTFM
 	select MMC_SDHCI_IO_ACCESSORS
 	help
@@ -216,8 +216,7 @@ config MMC_SDHCI_SIRF
 config MMC_SDHCI_PXAV3
 	tristate "Marvell MMP2 SD Host Controller support (PXAV3)"
 	depends on CLKDEV_LOOKUP
-	select MMC_SDHCI
-	select MMC_SDHCI_PLTFM
+	depends on MMC_SDHCI_PLTFM
 	default CPU_MMP2
 	help
 	  This selects the Marvell(R) PXAV3 SD Host Controller.
@@ -229,8 +228,7 @@ config MMC_SDHCI_PXAV3
 config MMC_SDHCI_PXAV2
 	tristate "Marvell PXA9XX SD Host Controller support (PXAV2)"
 	depends on CLKDEV_LOOKUP
-	select MMC_SDHCI
-	select MMC_SDHCI_PLTFM
+	depends on MMC_SDHCI_PLTFM
 	default CPU_PXA910
 	help
 	  This selects the Marvell(R) PXAV2 SD Host Controller.
@@ -264,7 +262,7 @@ config MMC_SDHCI_S3C_DMA
 config MMC_SDHCI_BCM_KONA
 	tristate "SDHCI support on Broadcom KONA platform"
 	depends on ARCH_BCM_MOBILE
-	select MMC_SDHCI_PLTFM
+	depends on MMC_SDHCI_PLTFM
 	help
 	  This selects the Broadcom Kona Secure Digital Host Controller
 	  Interface(SDHCI) support.
@@ -283,10 +281,19 @@ config MMC_SDHCI_BCM2835
 
 	  If unsure, say N.
 
+config MMC_MOXART
+	tristate "MOXART SD/MMC Host Controller support"
+	depends on ARCH_MOXART && MMC
+	help
+	  This selects support for the MOXART SD/MMC Host Controller.
+	  MOXA provides one multi-functional card reader which can
+	  be found on some embedded hardware such as UC-7112-LX.
+	  If you have a controller with this interface, say Y here.
+
 config MMC_OMAP
 	tristate "TI OMAP Multimedia Card Interface support"
 	depends on ARCH_OMAP
-	select TPS65010 if MACH_OMAP_H2
+	depends on TPS65010 || !MACH_OMAP_H2
 	help
 	  This selects the TI OMAP Multimedia card Interface.
 	  If you have an OMAP board with a Multimedia Card slot,
@@ -688,6 +695,12 @@ config MMC_WMT
 	  To compile this driver as a module, choose M here: the
 	  module will be called wmt-sdmmc.
 
+config MMC_USDHI6ROL0
+	tristate "Renesas USDHI6ROL0 SD/SDIO Host Controller support"
+	help
+	  This selects support for the Renesas USDHI6ROL0 SD/SDIO
+	  Host Controller
+
 config MMC_REALTEK_PCI
 	tristate "Realtek PCI-E SD/MMC Card Interface Driver"
 	depends on MFD_RTSX_PCI
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index 61cbc241935..7f81ddf1dd2 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -50,7 +50,9 @@ obj-$(CONFIG_MMC_JZ4740)	+= jz4740_mmc.o
 obj-$(CONFIG_MMC_VUB300)	+= vub300.o
 obj-$(CONFIG_MMC_USHC)		+= ushc.o
 obj-$(CONFIG_MMC_WMT)		+= wmt-sdmmc.o
+obj-$(CONFIG_MMC_MOXART)	+= moxart-mmc.o
 obj-$(CONFIG_MMC_SUNXI)		+= sunxi-mmc.o
+obj-$(CONFIG_MMC_USDHI6ROL0)	+= usdhi6rol0.o
 
 obj-$(CONFIG_MMC_REALTEK_PCI)	+= rtsx_pci_sdmmc.o
 obj-$(CONFIG_MMC_REALTEK_USB)	+= rtsx_usb_sdmmc.o
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index 42706ea0ba8..bb585d94090 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -37,6 +37,7 @@
 #include <linux/atmel-mci.h>
 #include <linux/atmel_pdc.h>
 
+#include <asm/cacheflush.h>
 #include <asm/io.h>
 #include <asm/unaligned.h>
 
@@ -820,16 +821,9 @@ static void atmci_pdc_complete(struct atmel_mci *host)
 
 	atmci_pdc_cleanup(host);
 
-	/*
-	 * If the card was removed, data will be NULL. No point trying
-	 * to send the stop command or waiting for NBUSY in this case.
-	 */
-	if (host->data) {
-		dev_dbg(&host->pdev->dev,
-		        "(%s) set pending xfer complete\n", __func__);
-		atmci_set_pending(host, EVENT_XFER_COMPLETE);
-		tasklet_schedule(&host->tasklet);
-	}
+	dev_dbg(&host->pdev->dev, "(%s) set pending xfer complete\n", __func__);
+	atmci_set_pending(host, EVENT_XFER_COMPLETE);
+	tasklet_schedule(&host->tasklet);
 }
 
 static void atmci_dma_cleanup(struct atmel_mci *host)
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index 3423c5ed50c..0fbc53ac7ea 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -187,7 +187,7 @@ static void dw_mci_exynos_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 	unsigned long actual;
 	u8 div = priv->ciu_div + 1;
 
-	if (ios->timing == MMC_TIMING_UHS_DDR50) {
+	if (ios->timing == MMC_TIMING_MMC_DDR52) {
 		mci_writel(host, CLKSEL, priv->ddr_timing);
 		/* Should be double rate for DDR mode */
 		if (ios->bus_width == MMC_BUS_WIDTH_8)
@@ -386,8 +386,7 @@ static int dw_mci_exynos_execute_tuning(struct dw_mci_slot *slot, u32 opcode,
 
 /* Common capabilities of Exynos4/Exynos5 SoC */
 static unsigned long exynos_dwmmc_caps[4] = {
-	MMC_CAP_UHS_DDR50 | MMC_CAP_1_8V_DDR |
-		MMC_CAP_8_BIT_DATA | MMC_CAP_CMD23,
+	MMC_CAP_1_8V_DDR | MMC_CAP_8_BIT_DATA | MMC_CAP_CMD23,
 	MMC_CAP_CMD23,
 	MMC_CAP_CMD23,
 	MMC_CAP_CMD23,
@@ -426,7 +425,7 @@ static int dw_mci_exynos_probe(struct platform_device *pdev)
 	return dw_mci_pltfm_register(pdev, drv_data);
 }
 
-const struct dev_pm_ops dw_mci_exynos_pmops = {
+static const struct dev_pm_ops dw_mci_exynos_pmops = {
 	SET_SYSTEM_SLEEP_PM_OPS(dw_mci_exynos_suspend, dw_mci_exynos_resume)
 	.resume_noirq = dw_mci_exynos_resume_noirq,
 	.thaw_noirq = dw_mci_exynos_resume_noirq,
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index cced599d5ae..1ac227c603b 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -235,12 +235,6 @@ err:
 }
 #endif /* defined(CONFIG_DEBUG_FS) */
 
-static void dw_mci_set_timeout(struct dw_mci *host)
-{
-	/* timeout (maximum) */
-	mci_writel(host, TMOUT, 0xffffffff);
-}
-
 static u32 dw_mci_prepare_command(struct mmc_host *mmc, struct mmc_command *cmd)
 {
 	struct mmc_data	*data;
@@ -257,9 +251,8 @@ static u32 dw_mci_prepare_command(struct mmc_host *mmc, struct mmc_command *cmd)
 	    (cmd->opcode == SD_IO_RW_DIRECT &&
 	     ((cmd->arg >> 9) & 0x1FFFF) == SDIO_CCCR_ABORT))
 		cmdr |= SDMMC_CMD_STOP;
-	else
-		if (cmd->opcode != MMC_SEND_STATUS && cmd->data)
-			cmdr |= SDMMC_CMD_PRV_DAT_WAIT;
+	else if (cmd->opcode != MMC_SEND_STATUS && cmd->data)
+		cmdr |= SDMMC_CMD_PRV_DAT_WAIT;
 
 	if (cmd->flags & MMC_RSP_PRESENT) {
 		/* We expect a response, so set this bit */
@@ -850,8 +843,6 @@ static void __dw_mci_start_request(struct dw_mci *host,
 	u32 cmdflags;
 
 	mrq = slot->mrq;
-	if (host->pdata->select_slot)
-		host->pdata->select_slot(slot->id);
 
 	host->cur_slot = slot;
 	host->mrq = mrq;
@@ -864,7 +855,7 @@ static void __dw_mci_start_request(struct dw_mci *host,
 
 	data = cmd->data;
 	if (data) {
-		dw_mci_set_timeout(host);
+		mci_writel(host, TMOUT, 0xFFFFFFFF);
 		mci_writel(host, BYTCNT, data->blksz*data->blocks);
 		mci_writel(host, BLKSIZ, data->blksz);
 	}
@@ -962,7 +953,7 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	regs = mci_readl(slot->host, UHS_REG);
 
 	/* DDR mode set */
-	if (ios->timing == MMC_TIMING_UHS_DDR50)
+	if (ios->timing == MMC_TIMING_MMC_DDR52)
 		regs |= ((0x1 << slot->id) << 16);
 	else
 		regs &= ~((0x1 << slot->id) << 16);
@@ -985,17 +976,11 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	switch (ios->power_mode) {
 	case MMC_POWER_UP:
 		set_bit(DW_MMC_CARD_NEED_INIT, &slot->flags);
-		/* Power up slot */
-		if (slot->host->pdata->setpower)
-			slot->host->pdata->setpower(slot->id, mmc->ocr_avail);
 		regs = mci_readl(slot->host, PWREN);
 		regs |= (1 << slot->id);
 		mci_writel(slot->host, PWREN, regs);
 		break;
 	case MMC_POWER_OFF:
-		/* Power down slot */
-		if (slot->host->pdata->setpower)
-			slot->host->pdata->setpower(slot->id, 0);
 		regs = mci_readl(slot->host, PWREN);
 		regs &= ~(1 << slot->id);
 		mci_writel(slot->host, PWREN, regs);
@@ -1009,15 +994,13 @@ static int dw_mci_get_ro(struct mmc_host *mmc)
 {
 	int read_only;
 	struct dw_mci_slot *slot = mmc_priv(mmc);
-	struct dw_mci_board *brd = slot->host->pdata;
+	int gpio_ro = mmc_gpio_get_ro(mmc);
 
 	/* Use platform get_ro function, else try on board write protect */
 	if (slot->quirks & DW_MCI_SLOT_QUIRK_NO_WRITE_PROTECT)
 		read_only = 0;
-	else if (brd->get_ro)
-		read_only = brd->get_ro(slot->id);
-	else if (gpio_is_valid(slot->wp_gpio))
-		read_only = gpio_get_value(slot->wp_gpio);
+	else if (!IS_ERR_VALUE(gpio_ro))
+		read_only = gpio_ro;
 	else
 		read_only =
 			mci_readl(slot->host, WRTPRT) & (1 << slot->id) ? 1 : 0;
@@ -1039,8 +1022,6 @@ static int dw_mci_get_cd(struct mmc_host *mmc)
 	/* Use platform get_cd function, else try onboard card detect */
 	if (brd->quirks & DW_MCI_QUIRK_BROKEN_CARD_DETECTION)
 		present = 1;
-	else if (brd->get_cd)
-		present = !brd->get_cd(slot->id);
 	else if (!IS_ERR_VALUE(gpio_cd))
 		present = gpio_cd;
 	else
@@ -1248,7 +1229,7 @@ static int dw_mci_data_complete(struct dw_mci *host, struct mmc_data *data)
 			data->error = -EIO;
 		}
 
-		dev_err(host->dev, "data error, status 0x%08x\n", status);
+		dev_dbg(host->dev, "data error, status 0x%08x\n", status);
 
 		/*
 		 * After an error, there may be data lingering
@@ -2045,86 +2026,15 @@ static int dw_mci_of_get_slot_quirks(struct device *dev, u8 slot)
 
 	return quirks;
 }
-
-/* find out bus-width for a given slot */
-static u32 dw_mci_of_get_bus_wd(struct device *dev, u8 slot)
-{
-	struct device_node *np = dw_mci_of_find_slot_node(dev, slot);
-	u32 bus_wd = 1;
-
-	if (!np)
-		return 1;
-
-	if (of_property_read_u32(np, "bus-width", &bus_wd))
-		dev_err(dev, "bus-width property not found, assuming width"
-			       " as 1\n");
-	return bus_wd;
-}
-
-/* find the write protect gpio for a given slot; or -1 if none specified */
-static int dw_mci_of_get_wp_gpio(struct device *dev, u8 slot)
-{
-	struct device_node *np = dw_mci_of_find_slot_node(dev, slot);
-	int gpio;
-
-	if (!np)
-		return -EINVAL;
-
-	gpio = of_get_named_gpio(np, "wp-gpios", 0);
-
-	/* Having a missing entry is valid; return silently */
-	if (!gpio_is_valid(gpio))
-		return -EINVAL;
-
-	if (devm_gpio_request(dev, gpio, "dw-mci-wp")) {
-		dev_warn(dev, "gpio [%d] request failed\n", gpio);
-		return -EINVAL;
-	}
-
-	return gpio;
-}
-
-/* find the cd gpio for a given slot */
-static void dw_mci_of_get_cd_gpio(struct device *dev, u8 slot,
-					struct mmc_host *mmc)
-{
-	struct device_node *np = dw_mci_of_find_slot_node(dev, slot);
-	int gpio;
-
-	if (!np)
-		return;
-
-	gpio = of_get_named_gpio(np, "cd-gpios", 0);
-
-	/* Having a missing entry is valid; return silently */
-	if (!gpio_is_valid(gpio))
-		return;
-
-	if (mmc_gpio_request_cd(mmc, gpio, 0))
-		dev_warn(dev, "gpio [%d] request failed\n", gpio);
-}
 #else /* CONFIG_OF */
 static int dw_mci_of_get_slot_quirks(struct device *dev, u8 slot)
 {
 	return 0;
 }
-static u32 dw_mci_of_get_bus_wd(struct device *dev, u8 slot)
-{
-	return 1;
-}
 static struct device_node *dw_mci_of_find_slot_node(struct device *dev, u8 slot)
 {
 	return NULL;
 }
-static int dw_mci_of_get_wp_gpio(struct device *dev, u8 slot)
-{
-	return -EINVAL;
-}
-static void dw_mci_of_get_cd_gpio(struct device *dev, u8 slot,
-					struct mmc_host *mmc)
-{
-	return;
-}
 #endif /* CONFIG_OF */
 
 static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
@@ -2134,7 +2044,6 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	const struct dw_mci_drv_data *drv_data = host->drv_data;
 	int ctrl_id, ret;
 	u32 freq[2];
-	u8 bus_width;
 
 	mmc = mmc_alloc_host(sizeof(struct dw_mci_slot), host->dev);
 	if (!mmc)
@@ -2158,17 +2067,7 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 		mmc->f_max = freq[1];
 	}
 
-	if (host->pdata->get_ocr)
-		mmc->ocr_avail = host->pdata->get_ocr(id);
-	else
-		mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
-
-	/*
-	 * Start with slot power disabled, it will be enabled when a card
-	 * is detected.
-	 */
-	if (host->pdata->setpower)
-		host->pdata->setpower(id, 0);
+	mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
 
 	if (host->pdata->caps)
 		mmc->caps = host->pdata->caps;
@@ -2189,19 +2088,7 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 	if (host->pdata->caps2)
 		mmc->caps2 = host->pdata->caps2;
 
-	if (host->pdata->get_bus_wd)
-		bus_width = host->pdata->get_bus_wd(slot->id);
-	else if (host->dev->of_node)
-		bus_width = dw_mci_of_get_bus_wd(host->dev, slot->id);
-	else
-		bus_width = 1;
-
-	switch (bus_width) {
-	case 8:
-		mmc->caps |= MMC_CAP_8_BIT_DATA;
-	case 4:
-		mmc->caps |= MMC_CAP_4_BIT_DATA;
-	}
+	mmc_of_parse(mmc);
 
 	if (host->pdata->blk_settings) {
 		mmc->max_segs = host->pdata->blk_settings->max_segs;
@@ -2226,8 +2113,10 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 #endif /* CONFIG_MMC_DW_IDMAC */
 	}
 
-	slot->wp_gpio = dw_mci_of_get_wp_gpio(host->dev, slot->id);
-	dw_mci_of_get_cd_gpio(host->dev, slot->id, mmc);
+	if (dw_mci_get_cd(mmc))
+		set_bit(DW_MMC_CARD_PRESENT, &slot->flags);
+	else
+		clear_bit(DW_MMC_CARD_PRESENT, &slot->flags);
 
 	ret = mmc_add_host(mmc);
 	if (ret)
@@ -2249,10 +2138,6 @@ err_setup_bus:
 
 static void dw_mci_cleanup_slot(struct dw_mci_slot *slot, unsigned int id)
 {
-	/* Shutdown detect IRQ */
-	if (slot->host->pdata->exit)
-		slot->host->pdata->exit(id);
-
 	/* Debugfs stuff is cleaned up by mmc core */
 	mmc_remove_host(slot->mmc);
 	slot->host->slot[id] = NULL;
@@ -2399,24 +2284,9 @@ static struct dw_mci_board *dw_mci_parse_dt(struct dw_mci *host)
 			return ERR_PTR(ret);
 	}
 
-	if (of_find_property(np, "keep-power-in-suspend", NULL))
-		pdata->pm_caps |= MMC_PM_KEEP_POWER;
-
-	if (of_find_property(np, "enable-sdio-wakeup", NULL))
-		pdata->pm_caps |= MMC_PM_WAKE_SDIO_IRQ;
-
 	if (of_find_property(np, "supports-highspeed", NULL))
 		pdata->caps |= MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED;
 
-	if (of_find_property(np, "caps2-mmc-hs200-1_8v", NULL))
-		pdata->caps2 |= MMC_CAP2_HS200_1_8V_SDR;
-
-	if (of_find_property(np, "caps2-mmc-hs200-1_2v", NULL))
-		pdata->caps2 |= MMC_CAP2_HS200_1_2V_SDR;
-
-	if (of_get_property(np, "cd-inverted", NULL))
-		pdata->caps2 |= MMC_CAP2_CD_ACTIVE_HIGH;
-
 	return pdata;
 }
 
@@ -2442,9 +2312,9 @@ int dw_mci_probe(struct dw_mci *host)
 		}
 	}
 
-	if (!host->pdata->select_slot && host->pdata->num_slots > 1) {
+	if (host->pdata->num_slots > 1) {
 		dev_err(host->dev,
-			"Platform data must supply select_slot function\n");
+			"Platform data must supply num_slots.\n");
 		return -ENODEV;
 	}
 
@@ -2474,12 +2344,19 @@ int dw_mci_probe(struct dw_mci *host)
 			ret = clk_set_rate(host->ciu_clk, host->pdata->bus_hz);
 			if (ret)
 				dev_warn(host->dev,
-					 "Unable to set bus rate to %ul\n",
+					 "Unable to set bus rate to %uHz\n",
 					 host->pdata->bus_hz);
 		}
 		host->bus_hz = clk_get_rate(host->ciu_clk);
 	}
 
+	if (!host->bus_hz) {
+		dev_err(host->dev,
+			"Platform data must supply bus speed\n");
+		ret = -ENODEV;
+		goto err_clk_ciu;
+	}
+
 	if (drv_data && drv_data->init) {
 		ret = drv_data->init(host);
 		if (ret) {
@@ -2516,13 +2393,6 @@ int dw_mci_probe(struct dw_mci *host)
 		}
 	}
 
-	if (!host->bus_hz) {
-		dev_err(host->dev,
-			"Platform data must supply bus speed\n");
-		ret = -ENODEV;
-		goto err_regulator;
-	}
-
 	host->quirks = host->pdata->quirks;
 
 	spin_lock_init(&host->lock);
@@ -2666,8 +2536,6 @@ err_workqueue:
 err_dmaunmap:
 	if (host->use_dma && host->dma_ops->exit)
 		host->dma_ops->exit(host);
-
-err_regulator:
 	if (host->vmmc)
 		regulator_disable(host->vmmc);
 
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 68349779c39..738fa241d05 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -195,7 +195,6 @@ extern int dw_mci_resume(struct dw_mci *host);
  * @mmc: The mmc_host representing this slot.
  * @host: The MMC controller this slot is using.
  * @quirks: Slot-level quirks (DW_MCI_SLOT_QUIRK_XXX)
- * @wp_gpio: If gpio_is_valid() we'll use this to read write protect.
  * @ctype: Card type for this slot.
  * @mrq: mmc_request currently being processed or waiting to be
  *	processed, or NULL when the slot is idle.
@@ -214,7 +213,6 @@ struct dw_mci_slot {
 	struct dw_mci		*host;
 
 	int			quirks;
-	int			wp_gpio;
 
 	u32			ctype;
 
diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c
index de2139cf344..537d6c7a5ae 100644
--- a/drivers/mmc/host/jz4740_mmc.c
+++ b/drivers/mmc/host/jz4740_mmc.c
@@ -515,10 +515,13 @@ static irqreturn_t jz_mmc_irq_worker(int irq, void *devid)
 
 		jz4740_mmc_send_command(host, req->stop);
 
-		timeout = jz4740_mmc_poll_irq(host, JZ_MMC_IRQ_PRG_DONE);
-		if (timeout) {
-			host->state = JZ4740_MMC_STATE_DONE;
-			break;
+		if (mmc_resp_type(req->stop) & MMC_RSP_BUSY) {
+			timeout = jz4740_mmc_poll_irq(host,
+						      JZ_MMC_IRQ_PRG_DONE);
+			if (timeout) {
+				host->state = JZ4740_MMC_STATE_DONE;
+				break;
+			}
 		}
 	case JZ4740_MMC_STATE_DONE:
 		break;
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 0a87e569134..cc8d4a6099c 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -448,7 +448,6 @@ mmc_spi_command_send(struct mmc_spi_host *host,
 {
 	struct scratch		*data = host->data;
 	u8			*cp = data->status;
-	u32			arg = cmd->arg;
 	int			status;
 	struct spi_transfer	*t;
 
@@ -465,14 +464,12 @@ mmc_spi_command_send(struct mmc_spi_host *host,
 	 * We init the whole buffer to all-ones, which is what we need
 	 * to write while we're reading (later) response data.
 	 */
-	memset(cp++, 0xff, sizeof(data->status));
+	memset(cp, 0xff, sizeof(data->status));
 
-	*cp++ = 0x40 | cmd->opcode;
-	*cp++ = (u8)(arg >> 24);
-	*cp++ = (u8)(arg >> 16);
-	*cp++ = (u8)(arg >> 8);
-	*cp++ = (u8)arg;
-	*cp++ = (crc7(0, &data->status[1], 5) << 1) | 0x01;
+	cp[1] = 0x40 | cmd->opcode;
+	put_unaligned_be32(cmd->arg, cp+2);
+	cp[6] = crc7_be(0, cp+1, 5) | 0x01;
+	cp += 7;
 
 	/* Then, read up to 13 bytes (while writing all-ones):
 	 *  - N(CR) (== 1..8) bytes of all-ones
@@ -711,10 +708,7 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	 * so we have to cope with this situation and check the response
 	 * bit-by-bit. Arggh!!!
 	 */
-	pattern  = scratch->status[0] << 24;
-	pattern |= scratch->status[1] << 16;
-	pattern |= scratch->status[2] << 8;
-	pattern |= scratch->status[3];
+	pattern = get_unaligned_be32(scratch->status);
 
 	/* First 3 bit of pattern are undefined */
 	pattern |= 0xE0000000;
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index a084edd37af..7ad463e9741 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -301,7 +301,8 @@ static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_8)
 		clk |= MCI_ST_8BIT_BUS;
 
-	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50)
+	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50 ||
+	    host->mmc->ios.timing == MMC_TIMING_MMC_DDR52)
 		clk |= MCI_ST_UX500_NEG_EDGE;
 
 	mmci_write_clkreg(host, clk);
@@ -764,7 +765,8 @@ static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 			mmci_write_clkreg(host, clk);
 		}
 
-	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50)
+	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50 ||
+	    host->mmc->ios.timing == MMC_TIMING_MMC_DDR52)
 		datactrl |= MCI_ST_DPSM_DDRMODE;
 
 	/*
diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c
new file mode 100644
index 00000000000..74924a04026
--- /dev/null
+++ b/drivers/mmc/host/moxart-mmc.c
@@ -0,0 +1,730 @@
+/*
+ * MOXA ART MMC host driver.
+ *
+ * Copyright (C) 2014 Jonas Jensen
+ *
+ * Jonas Jensen <jonas.jensen@gmail.com>
+ *
+ * Based on code from
+ * Moxa Technologies Co., Ltd. <www.moxa.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/version.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/blkdev.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/sd.h>
+#include <linux/sched.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/clk.h>
+#include <linux/bitops.h>
+#include <linux/of_dma.h>
+#include <linux/spinlock.h>
+
+#define REG_COMMAND		0
+#define REG_ARGUMENT		4
+#define REG_RESPONSE0		8
+#define REG_RESPONSE1		12
+#define REG_RESPONSE2		16
+#define REG_RESPONSE3		20
+#define REG_RESPONSE_COMMAND	24
+#define REG_DATA_CONTROL	28
+#define REG_DATA_TIMER		32
+#define REG_DATA_LENGTH		36
+#define REG_STATUS		40
+#define REG_CLEAR		44
+#define REG_INTERRUPT_MASK	48
+#define REG_POWER_CONTROL	52
+#define REG_CLOCK_CONTROL	56
+#define REG_BUS_WIDTH		60
+#define REG_DATA_WINDOW		64
+#define REG_FEATURE		68
+#define REG_REVISION		72
+
+/* REG_COMMAND */
+#define CMD_SDC_RESET		BIT(10)
+#define CMD_EN			BIT(9)
+#define CMD_APP_CMD		BIT(8)
+#define CMD_LONG_RSP		BIT(7)
+#define CMD_NEED_RSP		BIT(6)
+#define CMD_IDX_MASK		0x3f
+
+/* REG_RESPONSE_COMMAND */
+#define RSP_CMD_APP		BIT(6)
+#define RSP_CMD_IDX_MASK	0x3f
+
+/* REG_DATA_CONTROL */
+#define DCR_DATA_FIFO_RESET     BIT(8)
+#define DCR_DATA_THRES          BIT(7)
+#define DCR_DATA_EN		BIT(6)
+#define DCR_DMA_EN		BIT(5)
+#define DCR_DATA_WRITE		BIT(4)
+#define DCR_BLK_SIZE		0x0f
+
+/* REG_DATA_LENGTH */
+#define DATA_LEN_MASK		0xffffff
+
+/* REG_STATUS */
+#define WRITE_PROT		BIT(12)
+#define CARD_DETECT		BIT(11)
+/* 1-10 below can be sent to either registers, interrupt or clear. */
+#define CARD_CHANGE		BIT(10)
+#define FIFO_ORUN		BIT(9)
+#define FIFO_URUN		BIT(8)
+#define DATA_END		BIT(7)
+#define CMD_SENT		BIT(6)
+#define DATA_CRC_OK		BIT(5)
+#define RSP_CRC_OK		BIT(4)
+#define DATA_TIMEOUT		BIT(3)
+#define RSP_TIMEOUT		BIT(2)
+#define DATA_CRC_FAIL		BIT(1)
+#define RSP_CRC_FAIL		BIT(0)
+
+#define MASK_RSP		(RSP_TIMEOUT | RSP_CRC_FAIL | \
+				 RSP_CRC_OK  | CARD_DETECT  | CMD_SENT)
+
+#define MASK_DATA		(DATA_CRC_OK   | DATA_END | \
+				 DATA_CRC_FAIL | DATA_TIMEOUT)
+
+#define MASK_INTR_PIO		(FIFO_URUN | FIFO_ORUN | CARD_CHANGE)
+
+/* REG_POWER_CONTROL */
+#define SD_POWER_ON		BIT(4)
+#define SD_POWER_MASK		0x0f
+
+/* REG_CLOCK_CONTROL */
+#define CLK_HISPD		BIT(9)
+#define CLK_OFF			BIT(8)
+#define CLK_SD			BIT(7)
+#define CLK_DIV_MASK		0x7f
+
+/* REG_BUS_WIDTH */
+#define BUS_WIDTH_8		BIT(2)
+#define BUS_WIDTH_4		BIT(1)
+#define BUS_WIDTH_1		BIT(0)
+
+#define MMC_VDD_360		23
+#define MIN_POWER		(MMC_VDD_360 - SD_POWER_MASK)
+#define MAX_RETRIES		500000
+
+struct moxart_host {
+	spinlock_t			lock;
+
+	void __iomem			*base;
+
+	phys_addr_t			reg_phys;
+
+	struct dma_chan			*dma_chan_tx;
+	struct dma_chan                 *dma_chan_rx;
+	struct dma_async_tx_descriptor	*tx_desc;
+	struct mmc_host			*mmc;
+	struct mmc_request		*mrq;
+	struct scatterlist		*cur_sg;
+	struct completion		dma_complete;
+	struct completion		pio_complete;
+
+	u32				num_sg;
+	u32				data_remain;
+	u32				data_len;
+	u32				fifo_width;
+	u32				timeout;
+	u32				rate;
+
+	long				sysclk;
+
+	bool				have_dma;
+	bool				is_removed;
+};
+
+static inline void moxart_init_sg(struct moxart_host *host,
+				  struct mmc_data *data)
+{
+	host->cur_sg = data->sg;
+	host->num_sg = data->sg_len;
+	host->data_remain = host->cur_sg->length;
+
+	if (host->data_remain > host->data_len)
+		host->data_remain = host->data_len;
+}
+
+static inline int moxart_next_sg(struct moxart_host *host)
+{
+	int remain;
+	struct mmc_data *data = host->mrq->cmd->data;
+
+	host->cur_sg++;
+	host->num_sg--;
+
+	if (host->num_sg > 0) {
+		host->data_remain = host->cur_sg->length;
+		remain = host->data_len - data->bytes_xfered;
+		if (remain > 0 && remain < host->data_remain)
+			host->data_remain = remain;
+	}
+
+	return host->num_sg;
+}
+
+static int moxart_wait_for_status(struct moxart_host *host,
+				  u32 mask, u32 *status)
+{
+	int ret = -ETIMEDOUT;
+	u32 i;
+
+	for (i = 0; i < MAX_RETRIES; i++) {
+		*status = readl(host->base + REG_STATUS);
+		if (!(*status & mask)) {
+			udelay(5);
+			continue;
+		}
+		writel(*status & mask, host->base + REG_CLEAR);
+		ret = 0;
+		break;
+	}
+
+	if (ret)
+		dev_err(mmc_dev(host->mmc), "timed out waiting for status\n");
+
+	return ret;
+}
+
+
+static void moxart_send_command(struct moxart_host *host,
+	struct mmc_command *cmd)
+{
+	u32 status, cmdctrl;
+
+	writel(RSP_TIMEOUT  | RSP_CRC_OK |
+	       RSP_CRC_FAIL | CMD_SENT, host->base + REG_CLEAR);
+	writel(cmd->arg, host->base + REG_ARGUMENT);
+
+	cmdctrl = cmd->opcode & CMD_IDX_MASK;
+	if (cmdctrl == SD_APP_SET_BUS_WIDTH    || cmdctrl == SD_APP_OP_COND   ||
+	    cmdctrl == SD_APP_SEND_SCR         || cmdctrl == SD_APP_SD_STATUS ||
+	    cmdctrl == SD_APP_SEND_NUM_WR_BLKS)
+		cmdctrl |= CMD_APP_CMD;
+
+	if (cmd->flags & MMC_RSP_PRESENT)
+		cmdctrl |= CMD_NEED_RSP;
+
+	if (cmd->flags & MMC_RSP_136)
+		cmdctrl |= CMD_LONG_RSP;
+
+	writel(cmdctrl | CMD_EN, host->base + REG_COMMAND);
+
+	if (moxart_wait_for_status(host, MASK_RSP, &status) == -ETIMEDOUT)
+		cmd->error = -ETIMEDOUT;
+
+	if (status & RSP_TIMEOUT) {
+		cmd->error = -ETIMEDOUT;
+		return;
+	}
+	if (status & RSP_CRC_FAIL) {
+		cmd->error = -EIO;
+		return;
+	}
+	if (status & RSP_CRC_OK) {
+		if (cmd->flags & MMC_RSP_136) {
+			cmd->resp[3] = readl(host->base + REG_RESPONSE0);
+			cmd->resp[2] = readl(host->base + REG_RESPONSE1);
+			cmd->resp[1] = readl(host->base + REG_RESPONSE2);
+			cmd->resp[0] = readl(host->base + REG_RESPONSE3);
+		} else {
+			cmd->resp[0] = readl(host->base + REG_RESPONSE0);
+		}
+	}
+}
+
+static void moxart_dma_complete(void *param)
+{
+	struct moxart_host *host = param;
+
+	complete(&host->dma_complete);
+}
+
+static void moxart_transfer_dma(struct mmc_data *data, struct moxart_host *host)
+{
+	u32 len, dir_data, dir_slave;
+	unsigned long dma_time;
+	struct dma_async_tx_descriptor *desc = NULL;
+	struct dma_chan *dma_chan;
+
+	if (host->data_len == data->bytes_xfered)
+		return;
+
+	if (data->flags & MMC_DATA_WRITE) {
+		dma_chan = host->dma_chan_tx;
+		dir_data = DMA_TO_DEVICE;
+		dir_slave = DMA_MEM_TO_DEV;
+	} else {
+		dma_chan = host->dma_chan_rx;
+		dir_data = DMA_FROM_DEVICE;
+		dir_slave = DMA_DEV_TO_MEM;
+	}
+
+	len = dma_map_sg(dma_chan->device->dev, data->sg,
+			 data->sg_len, dir_data);
+
+	if (len > 0) {
+		desc = dmaengine_prep_slave_sg(dma_chan, data->sg,
+					       len, dir_slave,
+					       DMA_PREP_INTERRUPT |
+					       DMA_CTRL_ACK);
+	} else {
+		dev_err(mmc_dev(host->mmc), "dma_map_sg returned zero length\n");
+	}
+
+	if (desc) {
+		host->tx_desc = desc;
+		desc->callback = moxart_dma_complete;
+		desc->callback_param = host;
+		dmaengine_submit(desc);
+		dma_async_issue_pending(dma_chan);
+	}
+
+	data->bytes_xfered += host->data_remain;
+
+	dma_time = wait_for_completion_interruptible_timeout(
+		   &host->dma_complete, host->timeout);
+
+	dma_unmap_sg(dma_chan->device->dev,
+		     data->sg, data->sg_len,
+		     dir_data);
+}
+
+
+static void moxart_transfer_pio(struct moxart_host *host)
+{
+	struct mmc_data *data = host->mrq->cmd->data;
+	u32 *sgp, len = 0, remain, status;
+
+	if (host->data_len == data->bytes_xfered)
+		return;
+
+	sgp = sg_virt(host->cur_sg);
+	remain = host->data_remain;
+
+	if (data->flags & MMC_DATA_WRITE) {
+		while (remain > 0) {
+			if (moxart_wait_for_status(host, FIFO_URUN, &status)
+			     == -ETIMEDOUT) {
+				data->error = -ETIMEDOUT;
+				complete(&host->pio_complete);
+				return;
+			}
+			for (len = 0; len < remain && len < host->fifo_width;) {
+				iowrite32(*sgp, host->base + REG_DATA_WINDOW);
+				sgp++;
+				len += 4;
+			}
+			remain -= len;
+		}
+
+	} else {
+		while (remain > 0) {
+			if (moxart_wait_for_status(host, FIFO_ORUN, &status)
+			    == -ETIMEDOUT) {
+				data->error = -ETIMEDOUT;
+				complete(&host->pio_complete);
+				return;
+			}
+			for (len = 0; len < remain && len < host->fifo_width;) {
+				/* SCR data must be read in big endian. */
+				if (data->mrq->cmd->opcode == SD_APP_SEND_SCR)
+					*sgp = ioread32be(host->base +
+							  REG_DATA_WINDOW);
+				else
+					*sgp = ioread32(host->base +
+							REG_DATA_WINDOW);
+				sgp++;
+				len += 4;
+			}
+			remain -= len;
+		}
+	}
+
+	data->bytes_xfered += host->data_remain - remain;
+	host->data_remain = remain;
+
+	if (host->data_len != data->bytes_xfered)
+		moxart_next_sg(host);
+	else
+		complete(&host->pio_complete);
+}
+
+static void moxart_prepare_data(struct moxart_host *host)
+{
+	struct mmc_data *data = host->mrq->cmd->data;
+	u32 datactrl;
+	int blksz_bits;
+
+	if (!data)
+		return;
+
+	host->data_len = data->blocks * data->blksz;
+	blksz_bits = ffs(data->blksz) - 1;
+	BUG_ON(1 << blksz_bits != data->blksz);
+
+	moxart_init_sg(host, data);
+
+	datactrl = DCR_DATA_EN | (blksz_bits & DCR_BLK_SIZE);
+
+	if (data->flags & MMC_DATA_WRITE)
+		datactrl |= DCR_DATA_WRITE;
+
+	if ((host->data_len > host->fifo_width) && host->have_dma)
+		datactrl |= DCR_DMA_EN;
+
+	writel(DCR_DATA_FIFO_RESET, host->base + REG_DATA_CONTROL);
+	writel(MASK_DATA | FIFO_URUN | FIFO_ORUN, host->base + REG_CLEAR);
+	writel(host->rate, host->base + REG_DATA_TIMER);
+	writel(host->data_len, host->base + REG_DATA_LENGTH);
+	writel(datactrl, host->base + REG_DATA_CONTROL);
+}
+
+static void moxart_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct moxart_host *host = mmc_priv(mmc);
+	unsigned long pio_time, flags;
+	u32 status;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	init_completion(&host->dma_complete);
+	init_completion(&host->pio_complete);
+
+	host->mrq = mrq;
+
+	if (readl(host->base + REG_STATUS) & CARD_DETECT) {
+		mrq->cmd->error = -ETIMEDOUT;
+		goto request_done;
+	}
+
+	moxart_prepare_data(host);
+	moxart_send_command(host, host->mrq->cmd);
+
+	if (mrq->cmd->data) {
+		if ((host->data_len > host->fifo_width) && host->have_dma) {
+
+			writel(CARD_CHANGE, host->base + REG_INTERRUPT_MASK);
+
+			spin_unlock_irqrestore(&host->lock, flags);
+
+			moxart_transfer_dma(mrq->cmd->data, host);
+
+			spin_lock_irqsave(&host->lock, flags);
+		} else {
+
+			writel(MASK_INTR_PIO, host->base + REG_INTERRUPT_MASK);
+
+			spin_unlock_irqrestore(&host->lock, flags);
+
+			/* PIO transfers start from interrupt. */
+			pio_time = wait_for_completion_interruptible_timeout(
+				   &host->pio_complete, host->timeout);
+
+			spin_lock_irqsave(&host->lock, flags);
+		}
+
+		if (host->is_removed) {
+			dev_err(mmc_dev(host->mmc), "card removed\n");
+			mrq->cmd->error = -ETIMEDOUT;
+			goto request_done;
+		}
+
+		if (moxart_wait_for_status(host, MASK_DATA, &status)
+		    == -ETIMEDOUT) {
+			mrq->cmd->data->error = -ETIMEDOUT;
+			goto request_done;
+		}
+
+		if (status & DATA_CRC_FAIL)
+			mrq->cmd->data->error = -ETIMEDOUT;
+
+		if (mrq->cmd->data->stop)
+			moxart_send_command(host, mrq->cmd->data->stop);
+	}
+
+request_done:
+	spin_unlock_irqrestore(&host->lock, flags);
+	mmc_request_done(host->mmc, mrq);
+}
+
+static irqreturn_t moxart_irq(int irq, void *devid)
+{
+	struct moxart_host *host = (struct moxart_host *)devid;
+	u32 status;
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	status = readl(host->base + REG_STATUS);
+	if (status & CARD_CHANGE) {
+		host->is_removed = status & CARD_DETECT;
+		if (host->is_removed && host->have_dma) {
+			dmaengine_terminate_all(host->dma_chan_tx);
+			dmaengine_terminate_all(host->dma_chan_rx);
+		}
+		host->mrq = NULL;
+		writel(MASK_INTR_PIO, host->base + REG_CLEAR);
+		writel(CARD_CHANGE, host->base + REG_INTERRUPT_MASK);
+		mmc_detect_change(host->mmc, 0);
+	}
+	if (status & (FIFO_ORUN | FIFO_URUN) && host->mrq)
+		moxart_transfer_pio(host);
+
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+static void moxart_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct moxart_host *host = mmc_priv(mmc);
+	unsigned long flags;
+	u8 power, div;
+	u32 ctrl;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (ios->clock) {
+		for (div = 0; div < CLK_DIV_MASK; ++div) {
+			if (ios->clock >= host->sysclk / (2 * (div + 1)))
+				break;
+		}
+		ctrl = CLK_SD | div;
+		host->rate = host->sysclk / (2 * (div + 1));
+		if (host->rate > host->sysclk)
+			ctrl |= CLK_HISPD;
+		writel(ctrl, host->base + REG_CLOCK_CONTROL);
+	}
+
+	if (ios->power_mode == MMC_POWER_OFF) {
+		writel(readl(host->base + REG_POWER_CONTROL) & ~SD_POWER_ON,
+		       host->base + REG_POWER_CONTROL);
+	} else {
+		if (ios->vdd < MIN_POWER)
+			power = 0;
+		else
+			power = ios->vdd - MIN_POWER;
+
+		writel(SD_POWER_ON | (u32) power,
+		       host->base + REG_POWER_CONTROL);
+	}
+
+	switch (ios->bus_width) {
+	case MMC_BUS_WIDTH_4:
+		writel(BUS_WIDTH_4, host->base + REG_BUS_WIDTH);
+		break;
+	case MMC_BUS_WIDTH_8:
+		writel(BUS_WIDTH_8, host->base + REG_BUS_WIDTH);
+		break;
+	default:
+		writel(BUS_WIDTH_1, host->base + REG_BUS_WIDTH);
+		break;
+	}
+
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
+
+static int moxart_get_ro(struct mmc_host *mmc)
+{
+	struct moxart_host *host = mmc_priv(mmc);
+
+	return !!(readl(host->base + REG_STATUS) & WRITE_PROT);
+}
+
+static struct mmc_host_ops moxart_ops = {
+	.request = moxart_request,
+	.set_ios = moxart_set_ios,
+	.get_ro = moxart_get_ro,
+};
+
+static int moxart_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *node = dev->of_node;
+	struct resource res_mmc;
+	struct mmc_host *mmc;
+	struct moxart_host *host = NULL;
+	struct dma_slave_config cfg;
+	struct clk *clk;
+	void __iomem *reg_mmc;
+	dma_cap_mask_t mask;
+	int irq, ret;
+	u32 i;
+
+	mmc = mmc_alloc_host(sizeof(struct moxart_host), dev);
+	if (!mmc) {
+		dev_err(dev, "mmc_alloc_host failed\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = of_address_to_resource(node, 0, &res_mmc);
+	if (ret) {
+		dev_err(dev, "of_address_to_resource failed\n");
+		goto out;
+	}
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (irq <= 0) {
+		dev_err(dev, "irq_of_parse_and_map failed\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	clk = of_clk_get(node, 0);
+	if (IS_ERR(clk)) {
+		dev_err(dev, "of_clk_get failed\n");
+		ret = PTR_ERR(clk);
+		goto out;
+	}
+
+	reg_mmc = devm_ioremap_resource(dev, &res_mmc);
+	if (IS_ERR(reg_mmc)) {
+		ret = PTR_ERR(reg_mmc);
+		goto out;
+	}
+
+	mmc_of_parse(mmc);
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	host = mmc_priv(mmc);
+	host->mmc = mmc;
+	host->base = reg_mmc;
+	host->reg_phys = res_mmc.start;
+	host->timeout = msecs_to_jiffies(1000);
+	host->sysclk = clk_get_rate(clk);
+	host->fifo_width = readl(host->base + REG_FEATURE) << 2;
+	host->dma_chan_tx = of_dma_request_slave_channel(node, "tx");
+	host->dma_chan_rx = of_dma_request_slave_channel(node, "rx");
+
+	spin_lock_init(&host->lock);
+
+	mmc->ops = &moxart_ops;
+	mmc->f_max = DIV_ROUND_CLOSEST(host->sysclk, 2);
+	mmc->f_min = DIV_ROUND_CLOSEST(host->sysclk, CLK_DIV_MASK * 2);
+	mmc->ocr_avail = 0xffff00;	/* Support 2.0v - 3.6v power. */
+
+	if (IS_ERR(host->dma_chan_tx) || IS_ERR(host->dma_chan_rx)) {
+		dev_dbg(dev, "PIO mode transfer enabled\n");
+		host->have_dma = false;
+	} else {
+		dev_dbg(dev, "DMA channels found (%p,%p)\n",
+			 host->dma_chan_tx, host->dma_chan_rx);
+		host->have_dma = true;
+
+		cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+
+		cfg.direction = DMA_MEM_TO_DEV;
+		cfg.src_addr = 0;
+		cfg.dst_addr = host->reg_phys + REG_DATA_WINDOW;
+		dmaengine_slave_config(host->dma_chan_tx, &cfg);
+
+		cfg.direction = DMA_DEV_TO_MEM;
+		cfg.src_addr = host->reg_phys + REG_DATA_WINDOW;
+		cfg.dst_addr = 0;
+		dmaengine_slave_config(host->dma_chan_rx, &cfg);
+	}
+
+	switch ((readl(host->base + REG_BUS_WIDTH) >> 3) & 3) {
+	case 1:
+		mmc->caps |= MMC_CAP_4_BIT_DATA;
+		break;
+	case 2:
+		mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA;
+		break;
+	default:
+		break;
+	}
+
+	writel(0, host->base + REG_INTERRUPT_MASK);
+
+	writel(CMD_SDC_RESET, host->base + REG_COMMAND);
+	for (i = 0; i < MAX_RETRIES; i++) {
+		if (!(readl(host->base + REG_COMMAND) & CMD_SDC_RESET))
+			break;
+		udelay(5);
+	}
+
+	ret = devm_request_irq(dev, irq, moxart_irq, 0, "moxart-mmc", host);
+	if (ret)
+		goto out;
+
+	dev_set_drvdata(dev, mmc);
+	mmc_add_host(mmc);
+
+	dev_dbg(dev, "IRQ=%d, FIFO is %d bytes\n", irq, host->fifo_width);
+
+	return 0;
+
+out:
+	if (mmc)
+		mmc_free_host(mmc);
+	return ret;
+}
+
+static int moxart_remove(struct platform_device *pdev)
+{
+	struct mmc_host *mmc = dev_get_drvdata(&pdev->dev);
+	struct moxart_host *host = mmc_priv(mmc);
+
+	dev_set_drvdata(&pdev->dev, NULL);
+
+	if (mmc) {
+		if (!IS_ERR(host->dma_chan_tx))
+			dma_release_channel(host->dma_chan_tx);
+		if (!IS_ERR(host->dma_chan_rx))
+			dma_release_channel(host->dma_chan_rx);
+		mmc_remove_host(mmc);
+		mmc_free_host(mmc);
+
+		writel(0, host->base + REG_INTERRUPT_MASK);
+		writel(0, host->base + REG_POWER_CONTROL);
+		writel(readl(host->base + REG_CLOCK_CONTROL) | CLK_OFF,
+		       host->base + REG_CLOCK_CONTROL);
+	}
+
+	kfree(host);
+
+	return 0;
+}
+
+static const struct of_device_id moxart_mmc_match[] = {
+	{ .compatible = "moxa,moxart-mmc" },
+	{ .compatible = "faraday,ftsdc010" },
+	{ }
+};
+
+static struct platform_driver moxart_mmc_driver = {
+	.probe      = moxart_probe,
+	.remove     = moxart_remove,
+	.driver     = {
+		.name		= "mmc-moxart",
+		.owner		= THIS_MODULE,
+		.of_match_table	= moxart_mmc_match,
+	},
+};
+module_platform_driver(moxart_mmc_driver);
+
+MODULE_ALIAS("platform:mmc-moxart");
+MODULE_DESCRIPTION("MOXA ART MMC driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jonas Jensen <jonas.jensen@gmail.com>");
diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c
index 45aa2206741..6b4c5ad3b39 100644
--- a/drivers/mmc/host/mvsdio.c
+++ b/drivers/mmc/host/mvsdio.c
@@ -79,11 +79,11 @@ static int mvsd_setup_data(struct mvsd_host *host, struct mmc_data *data)
 		unsigned long t = jiffies + HZ;
 		unsigned int hw_state,  count = 0;
 		do {
+			hw_state = mvsd_read(MVSD_HW_STATE);
 			if (time_after(jiffies, t)) {
 				dev_warn(host->dev, "FIFO_EMPTY bit missing\n");
 				break;
 			}
-			hw_state = mvsd_read(MVSD_HW_STATE);
 			count++;
 		} while (!(hw_state & (1 << 13)));
 		dev_dbg(host->dev, "*** wait for FIFO_EMPTY bit "
@@ -354,6 +354,20 @@ static irqreturn_t mvsd_irq(int irq, void *dev)
 		intr_status, mvsd_read(MVSD_NOR_INTR_EN),
 		mvsd_read(MVSD_HW_STATE));
 
+	/*
+	 * It looks like, SDIO IP can issue one late, spurious irq
+	 * although all irqs should be disabled. To work around this,
+	 * bail out early, if we didn't expect any irqs to occur.
+	 */
+	if (!mvsd_read(MVSD_NOR_INTR_EN) && !mvsd_read(MVSD_ERR_INTR_EN)) {
+		dev_dbg(host->dev, "spurious irq detected intr 0x%04x intr_en 0x%04x erri 0x%04x erri_en 0x%04x\n",
+			mvsd_read(MVSD_NOR_INTR_STATUS),
+			mvsd_read(MVSD_NOR_INTR_EN),
+			mvsd_read(MVSD_ERR_INTR_STATUS),
+			mvsd_read(MVSD_ERR_INTR_EN));
+		return IRQ_HANDLED;
+	}
+
 	spin_lock(&host->lock);
 
 	/* PIO handling, if needed. Messy business... */
@@ -801,10 +815,10 @@ static int mvsd_probe(struct platform_device *pdev)
 		goto out;
 
 	if (!(mmc->caps & MMC_CAP_NEEDS_POLL))
-		dev_notice(&pdev->dev, "using GPIO for card detection\n");
+		dev_dbg(&pdev->dev, "using GPIO for card detection\n");
 	else
-		dev_notice(&pdev->dev,
-			   "lacking card detect (fall back to polling)\n");
+		dev_dbg(&pdev->dev, "lacking card detect (fall back to polling)\n");
+
 	return 0;
 
 out:
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index f7199c83f5c..ed1cb93c378 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -124,9 +124,8 @@ enum mxcmci_type {
 
 struct mxcmci_host {
 	struct mmc_host		*mmc;
-	struct resource		*res;
 	void __iomem		*base;
-	int			irq;
+	dma_addr_t		phys_base;
 	int			detect_irq;
 	struct dma_chan		*dma;
 	struct dma_async_tx_descriptor *desc;
@@ -154,8 +153,6 @@ struct mxcmci_host {
 	struct work_struct	datawork;
 	spinlock_t		lock;
 
-	struct regulator	*vcc;
-
 	int			burstlen;
 	int			dmareq;
 	struct dma_slave_config dma_slave_config;
@@ -241,37 +238,15 @@ static inline void mxcmci_writew(struct mxcmci_host *host, u16 val, int reg)
 
 static void mxcmci_set_clk_rate(struct mxcmci_host *host, unsigned int clk_ios);
 
-static inline void mxcmci_init_ocr(struct mxcmci_host *host)
-{
-	host->vcc = regulator_get(mmc_dev(host->mmc), "vmmc");
-
-	if (IS_ERR(host->vcc)) {
-		host->vcc = NULL;
-	} else {
-		host->mmc->ocr_avail = mmc_regulator_get_ocrmask(host->vcc);
-		if (host->pdata && host->pdata->ocr_avail)
-			dev_warn(mmc_dev(host->mmc),
-				"pdata->ocr_avail will not be used\n");
-	}
-
-	if (host->vcc == NULL) {
-		/* fall-back to platform data */
-		if (host->pdata && host->pdata->ocr_avail)
-			host->mmc->ocr_avail = host->pdata->ocr_avail;
-		else
-			host->mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
-	}
-}
-
-static inline void mxcmci_set_power(struct mxcmci_host *host,
-				    unsigned char power_mode,
-				    unsigned int vdd)
+static void mxcmci_set_power(struct mxcmci_host *host, unsigned int vdd)
 {
-	if (host->vcc) {
-		if (power_mode == MMC_POWER_UP)
-			mmc_regulator_set_ocr(host->mmc, host->vcc, vdd);
-		else if (power_mode == MMC_POWER_OFF)
-			mmc_regulator_set_ocr(host->mmc, host->vcc, 0);
+	if (!IS_ERR(host->mmc->supply.vmmc)) {
+		if (host->power_mode == MMC_POWER_UP)
+			mmc_regulator_set_ocr(host->mmc,
+					      host->mmc->supply.vmmc, vdd);
+		else if (host->power_mode == MMC_POWER_OFF)
+			mmc_regulator_set_ocr(host->mmc,
+					      host->mmc->supply.vmmc, 0);
 	}
 
 	if (host->pdata && host->pdata->setpower)
@@ -299,7 +274,6 @@ static void mxcmci_softreset(struct mxcmci_host *host)
 
 	mxcmci_writew(host, 0xff, MMC_REG_RES_TO);
 }
-static int mxcmci_setup_dma(struct mmc_host *mmc);
 
 #if IS_ENABLED(CONFIG_PPC_MPC512x)
 static inline void buffer_swap32(u32 *buf, int len)
@@ -868,8 +842,8 @@ static int mxcmci_setup_dma(struct mmc_host *mmc)
 	struct mxcmci_host *host = mmc_priv(mmc);
 	struct dma_slave_config *config = &host->dma_slave_config;
 
-	config->dst_addr = host->res->start + MMC_REG_BUFFER_ACCESS;
-	config->src_addr = host->res->start + MMC_REG_BUFFER_ACCESS;
+	config->dst_addr = host->phys_base + MMC_REG_BUFFER_ACCESS;
+	config->src_addr = host->phys_base + MMC_REG_BUFFER_ACCESS;
 	config->dst_addr_width = 4;
 	config->src_addr_width = 4;
 	config->dst_maxburst = host->burstlen;
@@ -911,8 +885,8 @@ static void mxcmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		host->cmdat &= ~CMD_DAT_CONT_BUS_WIDTH_4;
 
 	if (host->power_mode != ios->power_mode) {
-		mxcmci_set_power(host, ios->power_mode, ios->vdd);
 		host->power_mode = ios->power_mode;
+		mxcmci_set_power(host, ios->vdd);
 
 		if (ios->power_mode == MMC_POWER_ON)
 			host->cmdat |= CMD_DAT_CONT_INIT;
@@ -1040,8 +1014,8 @@ static const struct mmc_host_ops mxcmci_ops = {
 static int mxcmci_probe(struct platform_device *pdev)
 {
 	struct mmc_host *mmc;
-	struct mxcmci_host *host = NULL;
-	struct resource *iores, *r;
+	struct mxcmci_host *host;
+	struct resource *res;
 	int ret = 0, irq;
 	bool dat3_card_detect = false;
 	dma_cap_mask_t mask;
@@ -1052,21 +1026,25 @@ static int mxcmci_probe(struct platform_device *pdev)
 
 	of_id = of_match_device(mxcmci_of_match, &pdev->dev);
 
-	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	irq = platform_get_irq(pdev, 0);
-	if (!iores || irq < 0)
+	if (irq < 0)
 		return -EINVAL;
 
-	r = request_mem_region(iores->start, resource_size(iores), pdev->name);
-	if (!r)
-		return -EBUSY;
+	mmc = mmc_alloc_host(sizeof(*host), &pdev->dev);
+	if (!mmc)
+		return -ENOMEM;
+
+	host = mmc_priv(mmc);
 
-	mmc = mmc_alloc_host(sizeof(struct mxcmci_host), &pdev->dev);
-	if (!mmc) {
-		ret = -ENOMEM;
-		goto out_release_mem;
+	host->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(host->base)) {
+		ret = PTR_ERR(host->base);
+		goto out_free;
 	}
 
+	host->phys_base = res->start;
+
 	ret = mmc_of_parse(mmc);
 	if (ret)
 		goto out_free;
@@ -1084,13 +1062,6 @@ static int mxcmci_probe(struct platform_device *pdev)
 	mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count;
 	mmc->max_seg_size = mmc->max_req_size;
 
-	host = mmc_priv(mmc);
-	host->base = ioremap(r->start, resource_size(r));
-	if (!host->base) {
-		ret = -ENOMEM;
-		goto out_free;
-	}
-
 	if (of_id) {
 		const struct platform_device_id *id_entry = of_id->data;
 		host->devtype = id_entry->driver_data;
@@ -1112,7 +1083,14 @@ static int mxcmci_probe(struct platform_device *pdev)
 			&& !of_property_read_bool(pdev->dev.of_node, "cd-gpios"))
 		dat3_card_detect = true;
 
-	mxcmci_init_ocr(host);
+	ret = mmc_regulator_get_supply(mmc);
+	if (ret) {
+		if (pdata && ret != -EPROBE_DEFER)
+			mmc->ocr_avail = pdata->ocr_avail ? :
+				MMC_VDD_32_33 | MMC_VDD_33_34;
+		else
+			goto out_free;
+	}
 
 	if (dat3_card_detect)
 		host->default_irq_mask =
@@ -1120,19 +1098,16 @@ static int mxcmci_probe(struct platform_device *pdev)
 	else
 		host->default_irq_mask = 0;
 
-	host->res = r;
-	host->irq = irq;
-
 	host->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
 	if (IS_ERR(host->clk_ipg)) {
 		ret = PTR_ERR(host->clk_ipg);
-		goto out_iounmap;
+		goto out_free;
 	}
 
 	host->clk_per = devm_clk_get(&pdev->dev, "per");
 	if (IS_ERR(host->clk_per)) {
 		ret = PTR_ERR(host->clk_per);
-		goto out_iounmap;
+		goto out_free;
 	}
 
 	clk_prepare_enable(host->clk_per);
@@ -1159,9 +1134,9 @@ static int mxcmci_probe(struct platform_device *pdev)
 	if (!host->pdata) {
 		host->dma = dma_request_slave_channel(&pdev->dev, "rx-tx");
 	} else {
-		r = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-		if (r) {
-			host->dmareq = r->start;
+		res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
+		if (res) {
+			host->dmareq = res->start;
 			host->dma_data.peripheral_type = IMX_DMATYPE_SDHC;
 			host->dma_data.priority = DMA_PRIO_LOW;
 			host->dma_data.dma_request = host->dmareq;
@@ -1178,7 +1153,8 @@ static int mxcmci_probe(struct platform_device *pdev)
 
 	INIT_WORK(&host->datawork, mxcmci_datawork);
 
-	ret = request_irq(host->irq, mxcmci_irq, 0, DRIVER_NAME, host);
+	ret = devm_request_irq(&pdev->dev, irq, mxcmci_irq, 0,
+			       dev_name(&pdev->dev), host);
 	if (ret)
 		goto out_free_dma;
 
@@ -1188,7 +1164,7 @@ static int mxcmci_probe(struct platform_device *pdev)
 		ret = host->pdata->init(&pdev->dev, mxcmci_detect_irq,
 				host->mmc);
 		if (ret)
-			goto out_free_irq;
+			goto out_free_dma;
 	}
 
 	init_timer(&host->watchdog);
@@ -1199,20 +1175,17 @@ static int mxcmci_probe(struct platform_device *pdev)
 
 	return 0;
 
-out_free_irq:
-	free_irq(host->irq, host);
 out_free_dma:
 	if (host->dma)
 		dma_release_channel(host->dma);
+
 out_clk_put:
 	clk_disable_unprepare(host->clk_per);
 	clk_disable_unprepare(host->clk_ipg);
-out_iounmap:
-	iounmap(host->base);
+
 out_free:
 	mmc_free_host(mmc);
-out_release_mem:
-	release_mem_region(iores->start, resource_size(iores));
+
 	return ret;
 }
 
@@ -1223,30 +1196,21 @@ static int mxcmci_remove(struct platform_device *pdev)
 
 	mmc_remove_host(mmc);
 
-	if (host->vcc)
-		regulator_put(host->vcc);
-
 	if (host->pdata && host->pdata->exit)
 		host->pdata->exit(&pdev->dev, mmc);
 
-	free_irq(host->irq, host);
-	iounmap(host->base);
-
 	if (host->dma)
 		dma_release_channel(host->dma);
 
 	clk_disable_unprepare(host->clk_per);
 	clk_disable_unprepare(host->clk_ipg);
 
-	release_mem_region(host->res->start, resource_size(host->res));
-
 	mmc_free_host(mmc);
 
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int mxcmci_suspend(struct device *dev)
+static int __maybe_unused mxcmci_suspend(struct device *dev)
 {
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct mxcmci_host *host = mmc_priv(mmc);
@@ -1256,7 +1220,7 @@ static int mxcmci_suspend(struct device *dev)
 	return 0;
 }
 
-static int mxcmci_resume(struct device *dev)
+static int __maybe_unused mxcmci_resume(struct device *dev)
 {
 	struct mmc_host *mmc = dev_get_drvdata(dev);
 	struct mxcmci_host *host = mmc_priv(mmc);
@@ -1266,11 +1230,7 @@ static int mxcmci_resume(struct device *dev)
 	return 0;
 }
 
-static const struct dev_pm_ops mxcmci_pm_ops = {
-	.suspend	= mxcmci_suspend,
-	.resume		= mxcmci_resume,
-};
-#endif
+static SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume);
 
 static struct platform_driver mxcmci_driver = {
 	.probe		= mxcmci_probe,
@@ -1279,9 +1239,7 @@ static struct platform_driver mxcmci_driver = {
 	.driver		= {
 		.name		= DRIVER_NAME,
 		.owner		= THIS_MODULE,
-#ifdef CONFIG_PM
 		.pm	= &mxcmci_pm_ops,
-#endif
 		.of_match_table	= mxcmci_of_match,
 	}
 };
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index 073e871a0fc..babfea03ba8 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -70,6 +70,7 @@ struct mxs_mmc_host {
 	unsigned char			bus_width;
 	spinlock_t			lock;
 	int				sdio_irq_en;
+	bool				broken_cd;
 };
 
 static int mxs_mmc_get_cd(struct mmc_host *mmc)
@@ -78,6 +79,9 @@ static int mxs_mmc_get_cd(struct mmc_host *mmc)
 	struct mxs_ssp *ssp = &host->ssp;
 	int present, ret;
 
+	if (host->broken_cd)
+		return -ENOSYS;
+
 	ret = mmc_gpio_get_cd(mmc);
 	if (ret >= 0)
 		return ret;
@@ -568,6 +572,7 @@ static int mxs_mmc_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id =
 			of_match_device(mxs_mmc_dt_ids, &pdev->dev);
+	struct device_node *np = pdev->dev.of_node;
 	struct mxs_mmc_host *host;
 	struct mmc_host *mmc;
 	struct resource *iores;
@@ -634,6 +639,8 @@ static int mxs_mmc_probe(struct platform_device *pdev)
 	mmc->caps = MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED |
 		    MMC_CAP_SDIO_IRQ | MMC_CAP_NEEDS_POLL;
 
+	host->broken_cd = of_property_read_bool(np, "broken-cd");
+
 	mmc->f_min = 400000;
 	mmc->f_max = 288000000;
 
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index 5c2e58b2930..81974ecdfcb 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -177,7 +177,7 @@ static void mmc_omap_fclk_offdelay(struct mmc_omap_slot *slot)
 	unsigned long tick_ns;
 
 	if (slot != NULL && slot->host->fclk_enabled && slot->fclk_freq > 0) {
-		tick_ns = (1000000000 + slot->fclk_freq - 1) / slot->fclk_freq;
+		tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, slot->fclk_freq);
 		ndelay(8 * tick_ns);
 	}
 }
@@ -435,7 +435,7 @@ static void mmc_omap_send_stop_work(struct work_struct *work)
 	struct mmc_data *data = host->stop_data;
 	unsigned long tick_ns;
 
-	tick_ns = (1000000000 + slot->fclk_freq - 1)/slot->fclk_freq;
+	tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, slot->fclk_freq);
 	ndelay(8*tick_ns);
 
 	mmc_omap_start_command(host, data->stop);
@@ -477,7 +477,7 @@ mmc_omap_send_abort(struct mmc_omap_host *host, int maxloops)
 	u16 stat = 0;
 
 	/* Sending abort takes 80 clocks. Have some extra and round up */
-	timeout = (120*1000000 + slot->fclk_freq - 1)/slot->fclk_freq;
+	timeout = DIV_ROUND_UP(120 * USEC_PER_SEC, slot->fclk_freq);
 	restarts = 0;
 	while (restarts < maxloops) {
 		OMAP_MMC_WRITE(host, STAT, 0xFFFF);
@@ -677,8 +677,8 @@ mmc_omap_xfer_data(struct mmc_omap_host *host, int write)
 	if (n > host->buffer_bytes_left)
 		n = host->buffer_bytes_left;
 
-	nwords = n / 2;
-	nwords += n & 1; /* handle odd number of bytes to transfer */
+	/* Round up to handle odd number of bytes to transfer */
+	nwords = DIV_ROUND_UP(n, 2);
 
 	host->buffer_bytes_left -= n;
 	host->total_bytes_left -= n;
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index e91ee21549d..6b7b7558592 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -31,7 +31,7 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/of_device.h>
-#include <linux/omap-dma.h>
+#include <linux/omap-dmaengine.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/core.h>
 #include <linux/mmc/mmc.h>
@@ -582,7 +582,7 @@ static void omap_hsmmc_set_clock(struct omap_hsmmc_host *host)
 	 *	- MMC/SD clock coming out of controller > 25MHz
 	 */
 	if ((mmc_slot(host).features & HSMMC_HAS_HSPE_SUPPORT) &&
-	    (ios->timing != MMC_TIMING_UHS_DDR50) &&
+	    (ios->timing != MMC_TIMING_MMC_DDR52) &&
 	    ((OMAP_HSMMC_READ(host->base, CAPA) & HSS) == HSS)) {
 		regval = OMAP_HSMMC_READ(host->base, HCTL);
 		if (clkdiv && (clk_get_rate(host->fclk)/clkdiv) > 25000000)
@@ -602,7 +602,7 @@ static void omap_hsmmc_set_bus_width(struct omap_hsmmc_host *host)
 	u32 con;
 
 	con = OMAP_HSMMC_READ(host->base, CON);
-	if (ios->timing == MMC_TIMING_UHS_DDR50)
+	if (ios->timing == MMC_TIMING_MMC_DDR52)
 		con |= DDR;	/* configure in DDR mode */
 	else
 		con &= ~DDR;
@@ -920,16 +920,17 @@ omap_hsmmc_xfer_done(struct omap_hsmmc_host *host, struct mmc_data *data)
 static void
 omap_hsmmc_cmd_done(struct omap_hsmmc_host *host, struct mmc_command *cmd)
 {
-	host->cmd = NULL;
-
 	if (host->mrq->sbc && (host->cmd == host->mrq->sbc) &&
 	    !host->mrq->sbc->error && !(host->flags & AUTO_CMD23)) {
+		host->cmd = NULL;
 		omap_hsmmc_start_dma_transfer(host);
 		omap_hsmmc_start_command(host, host->mrq->cmd,
 						host->mrq->data);
 		return;
 	}
 
+	host->cmd = NULL;
+
 	if (cmd->flags & MMC_RSP_PRESENT) {
 		if (cmd->flags & MMC_RSP_136) {
 			/* response type 2 */
@@ -1851,6 +1852,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 	unsigned tx_req, rx_req;
 	struct pinctrl *pinctrl;
 	const struct omap_mmc_of_data *data;
+	void __iomem *base;
 
 	match = of_match_device(of_match_ptr(omap_mmc_of_match), &pdev->dev);
 	if (match) {
@@ -1881,9 +1883,9 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 	if (res == NULL || irq < 0)
 		return -ENXIO;
 
-	res = request_mem_region(res->start, resource_size(res), pdev->name);
-	if (res == NULL)
-		return -EBUSY;
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	ret = omap_hsmmc_gpio_init(pdata);
 	if (ret)
@@ -1904,7 +1906,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 	host->irq	= irq;
 	host->slot_id	= 0;
 	host->mapbase	= res->start + pdata->reg_offset;
-	host->base	= ioremap(host->mapbase, SZ_4K);
+	host->base	= base + pdata->reg_offset;
 	host->power_mode = MMC_POWER_OFF;
 	host->next_data.cookie = 1;
 	host->pbias_enabled = 0;
@@ -1922,7 +1924,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 
 	spin_lock_init(&host->irq_lock);
 
-	host->fclk = clk_get(&pdev->dev, "fck");
+	host->fclk = devm_clk_get(&pdev->dev, "fck");
 	if (IS_ERR(host->fclk)) {
 		ret = PTR_ERR(host->fclk);
 		host->fclk = NULL;
@@ -1941,7 +1943,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 
 	omap_hsmmc_context_save(host);
 
-	host->dbclk = clk_get(&pdev->dev, "mmchsdb_fck");
+	host->dbclk = devm_clk_get(&pdev->dev, "mmchsdb_fck");
 	/*
 	 * MMC can still work without debounce clock.
 	 */
@@ -1949,7 +1951,6 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 		host->dbclk = NULL;
 	} else if (clk_prepare_enable(host->dbclk) != 0) {
 		dev_warn(mmc_dev(host->mmc), "Failed to enable debounce clk\n");
-		clk_put(host->dbclk);
 		host->dbclk = NULL;
 	}
 
@@ -2018,7 +2019,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 	}
 
 	/* Request IRQ for MMC operations */
-	ret = request_irq(host->irq, omap_hsmmc_irq, 0,
+	ret = devm_request_irq(&pdev->dev, host->irq, omap_hsmmc_irq, 0,
 			mmc_hostname(mmc), host);
 	if (ret) {
 		dev_err(mmc_dev(host->mmc), "Unable to grab HSMMC IRQ\n");
@@ -2029,7 +2030,7 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 		if (pdata->init(&pdev->dev) != 0) {
 			dev_err(mmc_dev(host->mmc),
 				"Unable to configure MMC IRQs\n");
-			goto err_irq_cd_init;
+			goto err_irq;
 		}
 	}
 
@@ -2044,9 +2045,9 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 
 	/* Request IRQ for card detect */
 	if ((mmc_slot(host).card_detect_irq)) {
-		ret = request_threaded_irq(mmc_slot(host).card_detect_irq,
-					   NULL,
-					   omap_hsmmc_detect,
+		ret = devm_request_threaded_irq(&pdev->dev,
+						mmc_slot(host).card_detect_irq,
+						NULL, omap_hsmmc_detect,
 					   IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 					   mmc_hostname(mmc), host);
 		if (ret) {
@@ -2089,15 +2090,12 @@ static int omap_hsmmc_probe(struct platform_device *pdev)
 
 err_slot_name:
 	mmc_remove_host(mmc);
-	free_irq(mmc_slot(host).card_detect_irq, host);
 err_irq_cd:
 	if (host->use_reg)
 		omap_hsmmc_reg_put(host);
 err_reg:
 	if (host->pdata->cleanup)
 		host->pdata->cleanup(&pdev->dev);
-err_irq_cd_init:
-	free_irq(host->irq, host);
 err_irq:
 	if (host->tx_chan)
 		dma_release_channel(host->tx_chan);
@@ -2105,27 +2103,19 @@ err_irq:
 		dma_release_channel(host->rx_chan);
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
-	clk_put(host->fclk);
-	if (host->dbclk) {
+	if (host->dbclk)
 		clk_disable_unprepare(host->dbclk);
-		clk_put(host->dbclk);
-	}
 err1:
-	iounmap(host->base);
 	mmc_free_host(mmc);
 err_alloc:
 	omap_hsmmc_gpio_free(pdata);
 err:
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res)
-		release_mem_region(res->start, resource_size(res));
 	return ret;
 }
 
 static int omap_hsmmc_remove(struct platform_device *pdev)
 {
 	struct omap_hsmmc_host *host = platform_get_drvdata(pdev);
-	struct resource *res;
 
 	pm_runtime_get_sync(host->dev);
 	mmc_remove_host(host->mmc);
@@ -2133,9 +2123,6 @@ static int omap_hsmmc_remove(struct platform_device *pdev)
 		omap_hsmmc_reg_put(host);
 	if (host->pdata->cleanup)
 		host->pdata->cleanup(&pdev->dev);
-	free_irq(host->irq, host);
-	if (mmc_slot(host).card_detect_irq)
-		free_irq(mmc_slot(host).card_detect_irq, host);
 
 	if (host->tx_chan)
 		dma_release_channel(host->tx_chan);
@@ -2144,20 +2131,12 @@ static int omap_hsmmc_remove(struct platform_device *pdev)
 
 	pm_runtime_put_sync(host->dev);
 	pm_runtime_disable(host->dev);
-	clk_put(host->fclk);
-	if (host->dbclk) {
+	if (host->dbclk)
 		clk_disable_unprepare(host->dbclk);
-		clk_put(host->dbclk);
-	}
 
 	omap_hsmmc_gpio_free(host->pdata);
-	iounmap(host->base);
 	mmc_free_host(host->mmc);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (res)
-		release_mem_region(res->start, resource_size(res));
-
 	return 0;
 }
 
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 0b9ded13a3a..0d519649b57 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -236,6 +236,9 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 	case MMC_RSP_R1:
 		rsp_type = SD_RSP_TYPE_R1;
 		break;
+	case MMC_RSP_R1 & ~MMC_RSP_CRC:
+		rsp_type = SD_RSP_TYPE_R1 | SD_NO_CHECK_CRC7;
+		break;
 	case MMC_RSP_R1B:
 		rsp_type = SD_RSP_TYPE_R1b;
 		break;
@@ -816,6 +819,7 @@ static int sd_set_timing(struct realtek_pci_sdmmc *host, unsigned char timing)
 		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, CLK_CTL, CLK_LOW_FREQ, 0);
 		break;
 
+	case MMC_TIMING_MMC_DDR52:
 	case MMC_TIMING_UHS_DDR50:
 		rtsx_pci_add_cmd(pcr, WRITE_REG_CMD, SD_CFG1,
 				0x0C | SD_ASYNC_FIFO_NOT_RST,
@@ -896,6 +900,7 @@ static void sdmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		host->vpclk = true;
 		host->double_clk = false;
 		break;
+	case MMC_TIMING_MMC_DDR52:
 	case MMC_TIMING_UHS_DDR50:
 	case MMC_TIMING_UHS_SDR25:
 		host->ssc_depth = RTSX_SSC_DEPTH_1M;
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index e11fafa6fc6..5d3766e792f 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -34,7 +34,8 @@
 #include <linux/mfd/rtsx_usb.h>
 #include <asm/unaligned.h>
 
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#if defined(CONFIG_LEDS_CLASS) || (defined(CONFIG_LEDS_CLASS_MODULE) && \
+		defined(CONFIG_MMC_REALTEK_USB_MODULE))
 #include <linux/leds.h>
 #include <linux/workqueue.h>
 #define RTSX_USB_USE_LEDS_CLASS
@@ -59,7 +60,7 @@ struct rtsx_usb_sdmmc {
 
 	unsigned char		power_mode;
 
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#ifdef RTSX_USB_USE_LEDS_CLASS
 	struct led_classdev	led;
 	char			led_name[32];
 	struct work_struct	led_work;
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index ebb3f392b58..8ce3c28cb76 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -102,11 +102,19 @@ static void sdhci_acpi_int_hw_reset(struct sdhci_host *host)
 }
 
 static const struct sdhci_ops sdhci_acpi_ops_dflt = {
+	.set_clock = sdhci_set_clock,
 	.enable_dma = sdhci_acpi_enable_dma,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 static const struct sdhci_ops sdhci_acpi_ops_int = {
+	.set_clock = sdhci_set_clock,
 	.enable_dma = sdhci_acpi_enable_dma,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 	.hw_reset   = sdhci_acpi_int_hw_reset,
 };
 
diff --git a/drivers/mmc/host/sdhci-bcm-kona.c b/drivers/mmc/host/sdhci-bcm-kona.c
index 6f166e63b81..dd780c315a6 100644
--- a/drivers/mmc/host/sdhci-bcm-kona.c
+++ b/drivers/mmc/host/sdhci-bcm-kona.c
@@ -206,9 +206,13 @@ static void sdhci_bcm_kona_init_74_clocks(struct sdhci_host *host,
 }
 
 static struct sdhci_ops sdhci_bcm_kona_ops = {
+	.set_clock = sdhci_set_clock,
 	.get_max_clock = sdhci_bcm_kona_get_max_clk,
 	.get_timeout_clock = sdhci_bcm_kona_get_timeout_clock,
 	.platform_send_init_74_clocks = sdhci_bcm_kona_init_74_clocks,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 	.card_event = sdhci_bcm_kona_card_event,
 };
 
diff --git a/drivers/mmc/host/sdhci-bcm2835.c b/drivers/mmc/host/sdhci-bcm2835.c
index f6d8d67c545..46af9a439d7 100644
--- a/drivers/mmc/host/sdhci-bcm2835.c
+++ b/drivers/mmc/host/sdhci-bcm2835.c
@@ -131,8 +131,12 @@ static const struct sdhci_ops bcm2835_sdhci_ops = {
 	.read_l = bcm2835_sdhci_readl,
 	.read_w = bcm2835_sdhci_readw,
 	.read_b = bcm2835_sdhci_readb,
+	.set_clock = sdhci_set_clock,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
 	.get_min_clock = bcm2835_sdhci_get_min_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 static const struct sdhci_pltfm_data bcm2835_sdhci_pdata = {
diff --git a/drivers/mmc/host/sdhci-cns3xxx.c b/drivers/mmc/host/sdhci-cns3xxx.c
index f2cc26633cb..14b74075589 100644
--- a/drivers/mmc/host/sdhci-cns3xxx.c
+++ b/drivers/mmc/host/sdhci-cns3xxx.c
@@ -30,13 +30,12 @@ static void sdhci_cns3xxx_set_clock(struct sdhci_host *host, unsigned int clock)
 	u16 clk;
 	unsigned long timeout;
 
-	if (clock == host->clock)
-		return;
+	host->mmc->actual_clock = 0;
 
 	sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL);
 
 	if (clock == 0)
-		goto out;
+		return;
 
 	while (host->max_clk / div > clock) {
 		/*
@@ -75,13 +74,14 @@ static void sdhci_cns3xxx_set_clock(struct sdhci_host *host, unsigned int clock)
 
 	clk |= SDHCI_CLOCK_CARD_EN;
 	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
-out:
-	host->clock = clock;
 }
 
 static const struct sdhci_ops sdhci_cns3xxx_ops = {
 	.get_max_clock	= sdhci_cns3xxx_get_max_clk,
 	.set_clock	= sdhci_cns3xxx_set_clock,
+	.set_bus_width	= sdhci_set_bus_width,
+	.reset          = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 static const struct sdhci_pltfm_data sdhci_cns3xxx_pdata = {
@@ -90,8 +90,7 @@ static const struct sdhci_pltfm_data sdhci_cns3xxx_pdata = {
 		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
 		  SDHCI_QUIRK_INVERTED_WRITE_PROTECT |
 		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN |
-		  SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
-		  SDHCI_QUIRK_NONSTANDARD_CLOCK,
+		  SDHCI_QUIRK_BROKEN_TIMEOUT_VAL,
 };
 
 static int sdhci_cns3xxx_probe(struct platform_device *pdev)
diff --git a/drivers/mmc/host/sdhci-dove.c b/drivers/mmc/host/sdhci-dove.c
index 736d7a2eb7e..e6278ec007d 100644
--- a/drivers/mmc/host/sdhci-dove.c
+++ b/drivers/mmc/host/sdhci-dove.c
@@ -21,28 +21,17 @@
 
 #include <linux/clk.h>
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/io.h>
 #include <linux/mmc/host.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 
 #include "sdhci-pltfm.h"
 
 struct sdhci_dove_priv {
 	struct clk *clk;
-	int gpio_cd;
 };
 
-static irqreturn_t sdhci_dove_carddetect_irq(int irq, void *data)
-{
-	struct sdhci_host *host = data;
-
-	tasklet_schedule(&host->card_tasklet);
-	return IRQ_HANDLED;
-}
-
 static u16 sdhci_dove_readw(struct sdhci_host *host, int reg)
 {
 	u16 ret;
@@ -60,8 +49,6 @@ static u16 sdhci_dove_readw(struct sdhci_host *host, int reg)
 
 static u32 sdhci_dove_readl(struct sdhci_host *host, int reg)
 {
-	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	struct sdhci_dove_priv *priv = pltfm_host->priv;
 	u32 ret;
 
 	ret = readl(host->ioaddr + reg);
@@ -71,14 +58,6 @@ static u32 sdhci_dove_readl(struct sdhci_host *host, int reg)
 		/* Mask the support for 3.0V */
 		ret &= ~SDHCI_CAN_VDD_300;
 		break;
-	case SDHCI_PRESENT_STATE:
-		if (gpio_is_valid(priv->gpio_cd)) {
-			if (gpio_get_value(priv->gpio_cd) == 0)
-				ret |= SDHCI_CARD_PRESENT;
-			else
-				ret &= ~SDHCI_CARD_PRESENT;
-		}
-		break;
 	}
 	return ret;
 }
@@ -86,6 +65,10 @@ static u32 sdhci_dove_readl(struct sdhci_host *host, int reg)
 static const struct sdhci_ops sdhci_dove_ops = {
 	.read_w	= sdhci_dove_readw,
 	.read_l	= sdhci_dove_readl,
+	.set_clock = sdhci_set_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 static const struct sdhci_pltfm_data sdhci_dove_pdata = {
@@ -113,28 +96,9 @@ static int sdhci_dove_probe(struct platform_device *pdev)
 
 	priv->clk = devm_clk_get(&pdev->dev, NULL);
 
-	if (pdev->dev.of_node) {
-		priv->gpio_cd = of_get_named_gpio(pdev->dev.of_node,
-						  "cd-gpios", 0);
-	} else {
-		priv->gpio_cd = -EINVAL;
-	}
-
-	if (gpio_is_valid(priv->gpio_cd)) {
-		ret = gpio_request(priv->gpio_cd, "sdhci-cd");
-		if (ret) {
-			dev_err(&pdev->dev, "card detect gpio request failed: %d\n",
-				ret);
-			return ret;
-		}
-		gpio_direction_input(priv->gpio_cd);
-	}
-
 	host = sdhci_pltfm_init(pdev, &sdhci_dove_pdata, 0);
-	if (IS_ERR(host)) {
-		ret = PTR_ERR(host);
-		goto err_sdhci_pltfm_init;
-	}
+	if (IS_ERR(host))
+		return PTR_ERR(host);
 
 	pltfm_host = sdhci_priv(host);
 	pltfm_host->priv = priv;
@@ -142,39 +106,20 @@ static int sdhci_dove_probe(struct platform_device *pdev)
 	if (!IS_ERR(priv->clk))
 		clk_prepare_enable(priv->clk);
 
-	sdhci_get_of_property(pdev);
+	ret = mmc_of_parse(host->mmc);
+	if (ret)
+		goto err_sdhci_add;
 
 	ret = sdhci_add_host(host);
 	if (ret)
 		goto err_sdhci_add;
 
-	/*
-	 * We must request the IRQ after sdhci_add_host(), as the tasklet only
-	 * gets setup in sdhci_add_host() and we oops.
-	 */
-	if (gpio_is_valid(priv->gpio_cd)) {
-		ret = request_irq(gpio_to_irq(priv->gpio_cd),
-				  sdhci_dove_carddetect_irq,
-				  IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
-				  mmc_hostname(host->mmc), host);
-		if (ret) {
-			dev_err(&pdev->dev, "card detect irq request failed: %d\n",
-				ret);
-			goto err_request_irq;
-		}
-	}
-
 	return 0;
 
-err_request_irq:
-	sdhci_remove_host(host, 0);
 err_sdhci_add:
 	if (!IS_ERR(priv->clk))
 		clk_disable_unprepare(priv->clk);
 	sdhci_pltfm_free(pdev);
-err_sdhci_pltfm_init:
-	if (gpio_is_valid(priv->gpio_cd))
-		gpio_free(priv->gpio_cd);
 	return ret;
 }
 
@@ -186,11 +131,6 @@ static int sdhci_dove_remove(struct platform_device *pdev)
 
 	sdhci_pltfm_unregister(pdev);
 
-	if (gpio_is_valid(priv->gpio_cd)) {
-		free_irq(gpio_to_irq(priv->gpio_cd), host);
-		gpio_free(priv->gpio_cd);
-	}
-
 	if (!IS_ERR(priv->clk))
 		clk_disable_unprepare(priv->clk);
 
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index b841bb7cd37..ccec0e32590 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -160,7 +160,6 @@ struct pltfm_imx_data {
 		MULTIBLK_IN_PROCESS, /* exact multiblock cmd in process */
 		WAIT_FOR_INT,        /* sent CMD12, waiting for response INT */
 	} multiblock_status;
-	u32 uhs_mode;
 	u32 is_ddr;
 };
 
@@ -382,7 +381,6 @@ static u16 esdhc_readw_le(struct sdhci_host *host, int reg)
 		if (val & ESDHC_MIX_CTRL_SMPCLK_SEL)
 			ret |= SDHCI_CTRL_TUNED_CLK;
 
-		ret |= (imx_data->uhs_mode & SDHCI_CTRL_UHS_MASK);
 		ret &= ~SDHCI_CTRL_PRESET_VAL_ENABLE;
 
 		return ret;
@@ -429,7 +427,6 @@ static void esdhc_writew_le(struct sdhci_host *host, u16 val, int reg)
 		else
 			new_val &= ~ESDHC_VENDOR_SPEC_VSELECT;
 		writel(new_val, host->ioaddr + ESDHC_VENDOR_SPEC);
-		imx_data->uhs_mode = val & SDHCI_CTRL_UHS_MASK;
 		if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) {
 			new_val = readl(host->ioaddr + ESDHC_MIX_CTRL);
 			if (val & SDHCI_CTRL_TUNED_CLK)
@@ -600,12 +597,14 @@ static inline void esdhc_pltfm_set_clock(struct sdhci_host *host,
 	u32 temp, val;
 
 	if (clock == 0) {
+		host->mmc->actual_clock = 0;
+
 		if (esdhc_is_usdhc(imx_data)) {
 			val = readl(host->ioaddr + ESDHC_VENDOR_SPEC);
 			writel(val & ~ESDHC_VENDOR_SPEC_FRC_SDCLK_ON,
 					host->ioaddr + ESDHC_VENDOR_SPEC);
 		}
-		goto out;
+		return;
 	}
 
 	if (esdhc_is_usdhc(imx_data) && !imx_data->is_ddr)
@@ -645,8 +644,6 @@ static inline void esdhc_pltfm_set_clock(struct sdhci_host *host,
 	}
 
 	mdelay(1);
-out:
-	host->clock = clock;
 }
 
 static unsigned int esdhc_pltfm_get_ro(struct sdhci_host *host)
@@ -668,7 +665,7 @@ static unsigned int esdhc_pltfm_get_ro(struct sdhci_host *host)
 	return -ENOSYS;
 }
 
-static int esdhc_pltfm_bus_width(struct sdhci_host *host, int width)
+static void esdhc_pltfm_set_bus_width(struct sdhci_host *host, int width)
 {
 	u32 ctrl;
 
@@ -686,8 +683,6 @@ static int esdhc_pltfm_bus_width(struct sdhci_host *host, int width)
 
 	esdhc_clrset_le(host, ESDHC_CTRL_BUSWIDTH_MASK, ctrl,
 			SDHCI_HOST_CONTROL);
-
-	return 0;
 }
 
 static void esdhc_prepare_tuning(struct sdhci_host *host, u32 val)
@@ -697,6 +692,7 @@ static void esdhc_prepare_tuning(struct sdhci_host *host, u32 val)
 	/* FIXME: delay a bit for card to be ready for next tuning due to errors */
 	mdelay(1);
 
+	/* This is balanced by the runtime put in sdhci_tasklet_finish */
 	pm_runtime_get_sync(host->mmc->parent);
 	reg = readl(host->ioaddr + ESDHC_MIX_CTRL);
 	reg |= ESDHC_MIX_CTRL_EXE_TUNE | ESDHC_MIX_CTRL_SMPCLK_SEL |
@@ -713,13 +709,12 @@ static void esdhc_request_done(struct mmc_request *mrq)
 	complete(&mrq->completion);
 }
 
-static int esdhc_send_tuning_cmd(struct sdhci_host *host, u32 opcode)
+static int esdhc_send_tuning_cmd(struct sdhci_host *host, u32 opcode,
+				 struct scatterlist *sg)
 {
 	struct mmc_command cmd = {0};
 	struct mmc_request mrq = {NULL};
 	struct mmc_data data = {0};
-	struct scatterlist sg;
-	char tuning_pattern[ESDHC_TUNING_BLOCK_PATTERN_LEN];
 
 	cmd.opcode = opcode;
 	cmd.arg = 0;
@@ -728,11 +723,9 @@ static int esdhc_send_tuning_cmd(struct sdhci_host *host, u32 opcode)
 	data.blksz = ESDHC_TUNING_BLOCK_PATTERN_LEN;
 	data.blocks = 1;
 	data.flags = MMC_DATA_READ;
-	data.sg = &sg;
+	data.sg = sg;
 	data.sg_len = 1;
 
-	sg_init_one(&sg, tuning_pattern, sizeof(tuning_pattern));
-
 	mrq.cmd = &cmd;
 	mrq.cmd->mrq = &mrq;
 	mrq.data = &data;
@@ -742,14 +735,12 @@ static int esdhc_send_tuning_cmd(struct sdhci_host *host, u32 opcode)
 	mrq.done = esdhc_request_done;
 	init_completion(&(mrq.completion));
 
-	disable_irq(host->irq);
-	spin_lock(&host->lock);
+	spin_lock_irq(&host->lock);
 	host->mrq = &mrq;
 
 	sdhci_send_command(host, mrq.cmd);
 
-	spin_unlock(&host->lock);
-	enable_irq(host->irq);
+	spin_unlock_irq(&host->lock);
 
 	wait_for_completion(&mrq.completion);
 
@@ -772,13 +763,21 @@ static void esdhc_post_tuning(struct sdhci_host *host)
 
 static int esdhc_executing_tuning(struct sdhci_host *host, u32 opcode)
 {
+	struct scatterlist sg;
+	char *tuning_pattern;
 	int min, max, avg, ret;
 
+	tuning_pattern = kmalloc(ESDHC_TUNING_BLOCK_PATTERN_LEN, GFP_KERNEL);
+	if (!tuning_pattern)
+		return -ENOMEM;
+
+	sg_init_one(&sg, tuning_pattern, ESDHC_TUNING_BLOCK_PATTERN_LEN);
+
 	/* find the mininum delay first which can pass tuning */
 	min = ESDHC_TUNE_CTRL_MIN;
 	while (min < ESDHC_TUNE_CTRL_MAX) {
 		esdhc_prepare_tuning(host, min);
-		if (!esdhc_send_tuning_cmd(host, opcode))
+		if (!esdhc_send_tuning_cmd(host, opcode, &sg))
 			break;
 		min += ESDHC_TUNE_CTRL_STEP;
 	}
@@ -787,7 +786,7 @@ static int esdhc_executing_tuning(struct sdhci_host *host, u32 opcode)
 	max = min + ESDHC_TUNE_CTRL_STEP;
 	while (max < ESDHC_TUNE_CTRL_MAX) {
 		esdhc_prepare_tuning(host, max);
-		if (esdhc_send_tuning_cmd(host, opcode)) {
+		if (esdhc_send_tuning_cmd(host, opcode, &sg)) {
 			max -= ESDHC_TUNE_CTRL_STEP;
 			break;
 		}
@@ -797,9 +796,11 @@ static int esdhc_executing_tuning(struct sdhci_host *host, u32 opcode)
 	/* use average delay to get the best timing */
 	avg = (min + max) / 2;
 	esdhc_prepare_tuning(host, avg);
-	ret = esdhc_send_tuning_cmd(host, opcode);
+	ret = esdhc_send_tuning_cmd(host, opcode, &sg);
 	esdhc_post_tuning(host);
 
+	kfree(tuning_pattern);
+
 	dev_dbg(mmc_dev(host->mmc), "tunning %s at 0x%x ret %d\n",
 		ret ? "failed" : "passed", avg, ret);
 
@@ -837,28 +838,21 @@ static int esdhc_change_pinstate(struct sdhci_host *host,
 	return pinctrl_select_state(imx_data->pinctrl, pinctrl);
 }
 
-static int esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
+static void esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned timing)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct pltfm_imx_data *imx_data = pltfm_host->priv;
 	struct esdhc_platform_data *boarddata = &imx_data->boarddata;
 
-	switch (uhs) {
+	switch (timing) {
 	case MMC_TIMING_UHS_SDR12:
-		imx_data->uhs_mode = SDHCI_CTRL_UHS_SDR12;
-		break;
 	case MMC_TIMING_UHS_SDR25:
-		imx_data->uhs_mode = SDHCI_CTRL_UHS_SDR25;
-		break;
 	case MMC_TIMING_UHS_SDR50:
-		imx_data->uhs_mode = SDHCI_CTRL_UHS_SDR50;
-		break;
 	case MMC_TIMING_UHS_SDR104:
 	case MMC_TIMING_MMC_HS200:
-		imx_data->uhs_mode = SDHCI_CTRL_UHS_SDR104;
 		break;
 	case MMC_TIMING_UHS_DDR50:
-		imx_data->uhs_mode = SDHCI_CTRL_UHS_DDR50;
+	case MMC_TIMING_MMC_DDR52:
 		writel(readl(host->ioaddr + ESDHC_MIX_CTRL) |
 				ESDHC_MIX_CTRL_DDREN,
 				host->ioaddr + ESDHC_MIX_CTRL);
@@ -875,7 +869,15 @@ static int esdhc_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
 		break;
 	}
 
-	return esdhc_change_pinstate(host, uhs);
+	esdhc_change_pinstate(host, timing);
+}
+
+static void esdhc_reset(struct sdhci_host *host, u8 mask)
+{
+	sdhci_reset(host, mask);
+
+	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
 static struct sdhci_ops sdhci_esdhc_ops = {
@@ -888,8 +890,9 @@ static struct sdhci_ops sdhci_esdhc_ops = {
 	.get_max_clock = esdhc_pltfm_get_max_clock,
 	.get_min_clock = esdhc_pltfm_get_min_clock,
 	.get_ro = esdhc_pltfm_get_ro,
-	.platform_bus_width = esdhc_pltfm_bus_width,
+	.set_bus_width = esdhc_pltfm_set_bus_width,
 	.set_uhs_signaling = esdhc_set_uhs_signaling,
+	.reset = esdhc_reset,
 };
 
 static const struct sdhci_pltfm_data sdhci_esdhc_imx_pdata = {
@@ -1170,8 +1173,10 @@ static int sdhci_esdhc_runtime_suspend(struct device *dev)
 
 	ret = sdhci_runtime_suspend_host(host);
 
-	clk_disable_unprepare(imx_data->clk_per);
-	clk_disable_unprepare(imx_data->clk_ipg);
+	if (!sdhci_sdio_irq_enabled(host)) {
+		clk_disable_unprepare(imx_data->clk_per);
+		clk_disable_unprepare(imx_data->clk_ipg);
+	}
 	clk_disable_unprepare(imx_data->clk_ahb);
 
 	return ret;
@@ -1183,8 +1188,10 @@ static int sdhci_esdhc_runtime_resume(struct device *dev)
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct pltfm_imx_data *imx_data = pltfm_host->priv;
 
-	clk_prepare_enable(imx_data->clk_per);
-	clk_prepare_enable(imx_data->clk_ipg);
+	if (!sdhci_sdio_irq_enabled(host)) {
+		clk_prepare_enable(imx_data->clk_per);
+		clk_prepare_enable(imx_data->clk_ipg);
+	}
 	clk_prepare_enable(imx_data->clk_ahb);
 
 	return sdhci_runtime_resume_host(host);
diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h
index a7d9f95a7b0..3497cfaf683 100644
--- a/drivers/mmc/host/sdhci-esdhc.h
+++ b/drivers/mmc/host/sdhci-esdhc.h
@@ -20,10 +20,8 @@
 
 #define ESDHC_DEFAULT_QUIRKS	(SDHCI_QUIRK_FORCE_BLK_SZ_2048 | \
 				SDHCI_QUIRK_NO_BUSY_IRQ | \
-				SDHCI_QUIRK_NONSTANDARD_CLOCK | \
 				SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | \
-				SDHCI_QUIRK_PIO_NEEDS_DELAY | \
-				SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET)
+				SDHCI_QUIRK_PIO_NEEDS_DELAY)
 
 #define ESDHC_SYSTEM_CONTROL	0x2c
 #define ESDHC_CLOCK_MASK	0x0000fff0
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index acb0e9eb55f..40573a58486 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -468,6 +468,10 @@ MODULE_DEVICE_TABLE(of, sdhci_msm_dt_match);
 
 static struct sdhci_ops sdhci_msm_ops = {
 	.platform_execute_tuning = sdhci_msm_execute_tuning,
+	.reset = sdhci_reset,
+	.set_clock = sdhci_set_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 static int sdhci_msm_probe(struct platform_device *pdev)
diff --git a/drivers/mmc/host/sdhci-of-arasan.c b/drivers/mmc/host/sdhci-of-arasan.c
index f7c7cf62437..5bd1092310f 100644
--- a/drivers/mmc/host/sdhci-of-arasan.c
+++ b/drivers/mmc/host/sdhci-of-arasan.c
@@ -52,8 +52,12 @@ static unsigned int sdhci_arasan_get_timeout_clock(struct sdhci_host *host)
 }
 
 static struct sdhci_ops sdhci_arasan_ops = {
+	.set_clock = sdhci_set_clock,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
 	.get_timeout_clock = sdhci_arasan_get_timeout_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 static struct sdhci_pltfm_data sdhci_arasan_pdata = {
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 0b249970b11..8be4dcfb49a 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -199,13 +199,14 @@ static unsigned int esdhc_of_get_min_clock(struct sdhci_host *host)
 
 static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 {
-
 	int pre_div = 2;
 	int div = 1;
 	u32 temp;
 
+	host->mmc->actual_clock = 0;
+
 	if (clock == 0)
-		goto out;
+		return;
 
 	/* Workaround to reduce the clock frequency for p1010 esdhc */
 	if (of_find_compatible_node(NULL, NULL, "fsl,p1010-esdhc")) {
@@ -238,24 +239,8 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 		| (pre_div << ESDHC_PREDIV_SHIFT));
 	sdhci_writel(host, temp, ESDHC_SYSTEM_CONTROL);
 	mdelay(1);
-out:
-	host->clock = clock;
-}
-
-#ifdef CONFIG_PM
-static u32 esdhc_proctl;
-static void esdhc_of_suspend(struct sdhci_host *host)
-{
-	esdhc_proctl = sdhci_be32bs_readl(host, SDHCI_HOST_CONTROL);
 }
 
-static void esdhc_of_resume(struct sdhci_host *host)
-{
-	esdhc_of_enable_dma(host);
-	sdhci_be32bs_writel(host, esdhc_proctl, SDHCI_HOST_CONTROL);
-}
-#endif
-
 static void esdhc_of_platform_init(struct sdhci_host *host)
 {
 	u32 vvn;
@@ -269,7 +254,7 @@ static void esdhc_of_platform_init(struct sdhci_host *host)
 		host->quirks &= ~SDHCI_QUIRK_NO_BUSY_IRQ;
 }
 
-static int esdhc_pltfm_bus_width(struct sdhci_host *host, int width)
+static void esdhc_pltfm_set_bus_width(struct sdhci_host *host, int width)
 {
 	u32 ctrl;
 
@@ -289,8 +274,6 @@ static int esdhc_pltfm_bus_width(struct sdhci_host *host, int width)
 
 	clrsetbits_be32(host->ioaddr + SDHCI_HOST_CONTROL,
 			ESDHC_CTRL_BUSWIDTH_MASK, ctrl);
-
-	return 0;
 }
 
 static const struct sdhci_ops sdhci_esdhc_ops = {
@@ -305,13 +288,46 @@ static const struct sdhci_ops sdhci_esdhc_ops = {
 	.get_max_clock = esdhc_of_get_max_clock,
 	.get_min_clock = esdhc_of_get_min_clock,
 	.platform_init = esdhc_of_platform_init,
-#ifdef CONFIG_PM
-	.platform_suspend = esdhc_of_suspend,
-	.platform_resume = esdhc_of_resume,
-#endif
 	.adma_workaround = esdhci_of_adma_workaround,
-	.platform_bus_width = esdhc_pltfm_bus_width,
+	.set_bus_width = esdhc_pltfm_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
+};
+
+#ifdef CONFIG_PM
+
+static u32 esdhc_proctl;
+static int esdhc_of_suspend(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
+
+	esdhc_proctl = sdhci_be32bs_readl(host, SDHCI_HOST_CONTROL);
+
+	return sdhci_suspend_host(host);
+}
+
+static int esdhc_of_resume(struct device *dev)
+{
+	struct sdhci_host *host = dev_get_drvdata(dev);
+	int ret = sdhci_resume_host(host);
+
+	if (ret == 0) {
+		/* Isn't this already done by sdhci_resume_host() ? --rmk */
+		esdhc_of_enable_dma(host);
+		sdhci_be32bs_writel(host, esdhc_proctl, SDHCI_HOST_CONTROL);
+	}
+
+	return ret;
+}
+
+static const struct dev_pm_ops esdhc_pmops = {
+	.suspend	= esdhc_of_suspend,
+	.resume		= esdhc_of_resume,
 };
+#define ESDHC_PMOPS (&esdhc_pmops)
+#else
+#define ESDHC_PMOPS NULL
+#endif
 
 static const struct sdhci_pltfm_data sdhci_esdhc_pdata = {
 	/*
@@ -374,7 +390,7 @@ static struct platform_driver sdhci_esdhc_driver = {
 		.name = "sdhci-esdhc",
 		.owner = THIS_MODULE,
 		.of_match_table = sdhci_esdhc_of_match,
-		.pm = SDHCI_PLTFM_PMOPS,
+		.pm = ESDHC_PMOPS,
 	},
 	.probe = sdhci_esdhc_probe,
 	.remove = sdhci_esdhc_remove,
diff --git a/drivers/mmc/host/sdhci-of-hlwd.c b/drivers/mmc/host/sdhci-of-hlwd.c
index 57c514a81ca..b341661369a 100644
--- a/drivers/mmc/host/sdhci-of-hlwd.c
+++ b/drivers/mmc/host/sdhci-of-hlwd.c
@@ -58,6 +58,10 @@ static const struct sdhci_ops sdhci_hlwd_ops = {
 	.write_l = sdhci_hlwd_writel,
 	.write_w = sdhci_hlwd_writew,
 	.write_b = sdhci_hlwd_writeb,
+	.set_clock = sdhci_set_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 static const struct sdhci_pltfm_data sdhci_hlwd_pdata = {
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index f49666bcc52..5670e381b0c 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -21,6 +21,45 @@
 #include "sdhci-pci.h"
 #include "sdhci-pci-o2micro.h"
 
+static void o2_pci_set_baseclk(struct sdhci_pci_chip *chip, u32 value)
+{
+	u32 scratch_32;
+	pci_read_config_dword(chip->pdev,
+			      O2_SD_PLL_SETTING, &scratch_32);
+
+	scratch_32 &= 0x0000FFFF;
+	scratch_32 |= value;
+
+	pci_write_config_dword(chip->pdev,
+			       O2_SD_PLL_SETTING, scratch_32);
+}
+
+static void o2_pci_led_enable(struct sdhci_pci_chip *chip)
+{
+	int ret;
+	u32 scratch_32;
+
+	/* Set led of SD host function enable */
+	ret = pci_read_config_dword(chip->pdev,
+				    O2_SD_FUNC_REG0, &scratch_32);
+	if (ret)
+		return;
+
+	scratch_32 &= ~O2_SD_FREG0_LEDOFF;
+	pci_write_config_dword(chip->pdev,
+			       O2_SD_FUNC_REG0, scratch_32);
+
+	ret = pci_read_config_dword(chip->pdev,
+				    O2_SD_TEST_REG, &scratch_32);
+	if (ret)
+		return;
+
+	scratch_32 |= O2_SD_LED_ENABLE;
+	pci_write_config_dword(chip->pdev,
+			       O2_SD_TEST_REG, scratch_32);
+
+}
+
 void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip)
 {
 	u32 scratch_32;
@@ -216,6 +255,40 @@ int sdhci_pci_o2_probe(struct sdhci_pci_chip *chip)
 		scratch &= 0x7f;
 		pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch);
 
+		/* DevId=8520 subId= 0x11 or 0x12  Type Chip support */
+		if (chip->pdev->device == PCI_DEVICE_ID_O2_FUJIN2) {
+			ret = pci_read_config_dword(chip->pdev,
+						    O2_SD_FUNC_REG0,
+						    &scratch_32);
+			scratch_32 = ((scratch_32 & 0xFF000000) >> 24);
+
+			/* Check Whether subId is 0x11 or 0x12 */
+			if ((scratch_32 == 0x11) || (scratch_32 == 0x12)) {
+				scratch_32 = 0x2c280000;
+
+				/* Set Base Clock to 208MZ */
+				o2_pci_set_baseclk(chip, scratch_32);
+				ret = pci_read_config_dword(chip->pdev,
+							    O2_SD_FUNC_REG4,
+							    &scratch_32);
+
+				/* Enable Base Clk setting change */
+				scratch_32 |= O2_SD_FREG4_ENABLE_CLK_SET;
+				pci_write_config_dword(chip->pdev,
+						       O2_SD_FUNC_REG4,
+						       scratch_32);
+
+				/* Set Tuning Window to 4 */
+				pci_write_config_byte(chip->pdev,
+						      O2_SD_TUNING_CTRL, 0x44);
+
+				break;
+			}
+		}
+
+		/* Enable 8520 led function */
+		o2_pci_led_enable(chip);
+
 		/* Set timeout CLK */
 		ret = pci_read_config_dword(chip->pdev,
 					    O2_SD_CLK_SETTING, &scratch_32);
@@ -276,7 +349,7 @@ int sdhci_pci_o2_probe(struct sdhci_pci_chip *chip)
 		pci_write_config_byte(chip->pdev, O2_SD_LOCK_WP, scratch);
 
 		ret = pci_read_config_dword(chip->pdev,
-					    O2_SD_FUNC_REG0, &scratch_32);
+					    O2_SD_PLL_SETTING, &scratch_32);
 
 		if ((scratch_32 & 0xff000000) == 0x01000000) {
 			scratch_32 &= 0x0000FFFF;
@@ -299,6 +372,9 @@ int sdhci_pci_o2_probe(struct sdhci_pci_chip *chip)
 					       O2_SD_FUNC_REG4, scratch_32);
 		}
 
+		/* Set Tuning Windows to 5 */
+		pci_write_config_byte(chip->pdev,
+				O2_SD_TUNING_CTRL, 0x55);
 		/* Lock WP */
 		ret = pci_read_config_byte(chip->pdev,
 					   O2_SD_LOCK_WP, &scratch);
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.h b/drivers/mmc/host/sdhci-pci-o2micro.h
index dbec4c93348..f7ffc908d9a 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.h
+++ b/drivers/mmc/host/sdhci-pci-o2micro.h
@@ -57,6 +57,9 @@
 #define O2_SD_UHS2_L1_CTRL	0x35C
 #define O2_SD_FUNC_REG3		0x3E0
 #define O2_SD_FUNC_REG4		0x3E4
+#define O2_SD_LED_ENABLE	BIT(6)
+#define O2_SD_FREG0_LEDOFF	BIT(13)
+#define O2_SD_FREG4_ENABLE_CLK_SET	BIT(22)
 
 #define O2_SD_VENDOR_SETTING	0x110
 #define O2_SD_VENDOR_SETTING2	0x1C8
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index fdc61212036..52c42fcc284 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -1031,7 +1031,7 @@ static int sdhci_pci_enable_dma(struct sdhci_host *host)
 	return 0;
 }
 
-static int sdhci_pci_bus_width(struct sdhci_host *host, int width)
+static void sdhci_pci_set_bus_width(struct sdhci_host *host, int width)
 {
 	u8 ctrl;
 
@@ -1052,8 +1052,6 @@ static int sdhci_pci_bus_width(struct sdhci_host *host, int width)
 	}
 
 	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
-
-	return 0;
 }
 
 static void sdhci_pci_gpio_hw_reset(struct sdhci_host *host)
@@ -1080,8 +1078,11 @@ static void sdhci_pci_hw_reset(struct sdhci_host *host)
 }
 
 static const struct sdhci_ops sdhci_pci_ops = {
+	.set_clock	= sdhci_set_clock,
 	.enable_dma	= sdhci_pci_enable_dma,
-	.platform_bus_width	= sdhci_pci_bus_width,
+	.set_bus_width	= sdhci_pci_set_bus_width,
+	.reset		= sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 	.hw_reset		= sdhci_pci_hw_reset,
 };
 
diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c
index bef250e9541..7e834fb78f4 100644
--- a/drivers/mmc/host/sdhci-pltfm.c
+++ b/drivers/mmc/host/sdhci-pltfm.c
@@ -45,6 +45,10 @@ unsigned int sdhci_pltfm_clk_get_max_clock(struct sdhci_host *host)
 EXPORT_SYMBOL_GPL(sdhci_pltfm_clk_get_max_clock);
 
 static const struct sdhci_ops sdhci_pltfm_ops = {
+	.set_clock = sdhci_set_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 #ifdef CONFIG_OF
diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c
index d51e061ec57..3c0f3c0a1cc 100644
--- a/drivers/mmc/host/sdhci-pxav2.c
+++ b/drivers/mmc/host/sdhci-pxav2.c
@@ -51,11 +51,13 @@
 #define MMC_CARD		0x1000
 #define MMC_WIDTH		0x0100
 
-static void pxav2_set_private_registers(struct sdhci_host *host, u8 mask)
+static void pxav2_reset(struct sdhci_host *host, u8 mask)
 {
 	struct platform_device *pdev = to_platform_device(mmc_dev(host->mmc));
 	struct sdhci_pxa_platdata *pdata = pdev->dev.platform_data;
 
+	sdhci_reset(host, mask);
+
 	if (mask == SDHCI_RESET_ALL) {
 		u16 tmp = 0;
 
@@ -88,7 +90,7 @@ static void pxav2_set_private_registers(struct sdhci_host *host, u8 mask)
 	}
 }
 
-static int pxav2_mmc_set_width(struct sdhci_host *host, int width)
+static void pxav2_mmc_set_bus_width(struct sdhci_host *host, int width)
 {
 	u8 ctrl;
 	u16 tmp;
@@ -107,14 +109,14 @@ static int pxav2_mmc_set_width(struct sdhci_host *host, int width)
 	}
 	writew(tmp, host->ioaddr + SD_CE_ATA_2);
 	writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL);
-
-	return 0;
 }
 
 static const struct sdhci_ops pxav2_sdhci_ops = {
+	.set_clock     = sdhci_set_clock,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
-	.platform_reset_exit = pxav2_set_private_registers,
-	.platform_bus_width = pxav2_mmc_set_width,
+	.set_bus_width = pxav2_mmc_set_bus_width,
+	.reset         = pxav2_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 #ifdef CONFIG_OF
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 2fd73b38c30..f4f12894756 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -112,11 +112,13 @@ static int mv_conf_mbus_windows(struct platform_device *pdev,
 	return 0;
 }
 
-static void pxav3_set_private_registers(struct sdhci_host *host, u8 mask)
+static void pxav3_reset(struct sdhci_host *host, u8 mask)
 {
 	struct platform_device *pdev = to_platform_device(mmc_dev(host->mmc));
 	struct sdhci_pxa_platdata *pdata = pdev->dev.platform_data;
 
+	sdhci_reset(host, mask);
+
 	if (mask == SDHCI_RESET_ALL) {
 		/*
 		 * tune timing of read data/command when crc error happen
@@ -184,7 +186,7 @@ static void pxav3_gen_init_74_clocks(struct sdhci_host *host, u8 power_mode)
 	pxa->power_mode = power_mode;
 }
 
-static int pxav3_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
+static void pxav3_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
 {
 	u16 ctrl_2;
 
@@ -218,15 +220,16 @@ static int pxav3_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
 	dev_dbg(mmc_dev(host->mmc),
 		"%s uhs = %d, ctrl_2 = %04X\n",
 		__func__, uhs, ctrl_2);
-
-	return 0;
 }
 
 static const struct sdhci_ops pxav3_sdhci_ops = {
-	.platform_reset_exit = pxav3_set_private_registers,
+	.set_clock = sdhci_set_clock,
 	.set_uhs_signaling = pxav3_set_uhs_signaling,
 	.platform_send_init_74_clocks = pxav3_gen_init_74_clocks,
 	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = pxav3_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 static struct sdhci_pltfm_data sdhci_pxav3_pdata = {
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index d61eb5a7083..fa5954a0544 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -33,9 +33,6 @@
 
 #define MAX_BUS_CLK	(4)
 
-/* Number of gpio's used is max data bus width + command and clock lines */
-#define NUM_GPIOS(x)	(x + 2)
-
 /**
  * struct sdhci_s3c - S3C SDHCI instance
  * @host: The SDHCI host created
@@ -58,6 +55,8 @@ struct sdhci_s3c {
 	struct clk		*clk_io;
 	struct clk		*clk_bus[MAX_BUS_CLK];
 	unsigned long		clk_rates[MAX_BUS_CLK];
+
+	bool			no_divider;
 };
 
 /**
@@ -70,6 +69,7 @@ struct sdhci_s3c {
  */
 struct sdhci_s3c_drv_data {
 	unsigned int	sdhci_quirks;
+	bool		no_divider;
 };
 
 static inline struct sdhci_s3c *to_s3c(struct sdhci_host *host)
@@ -119,7 +119,7 @@ static unsigned int sdhci_s3c_consider_clock(struct sdhci_s3c *ourhost,
 	 * If controller uses a non-standard clock division, find the best clock
 	 * speed possible with selected clock source and skip the division.
 	 */
-	if (ourhost->host->quirks & SDHCI_QUIRK_NONSTANDARD_CLOCK) {
+	if (ourhost->no_divider) {
 		rate = clk_round_rate(clksrc, wanted);
 		return wanted - rate;
 	}
@@ -161,9 +161,13 @@ static void sdhci_s3c_set_clock(struct sdhci_host *host, unsigned int clock)
 	int src;
 	u32 ctrl;
 
+	host->mmc->actual_clock = 0;
+
 	/* don't bother if the clock is going off. */
-	if (clock == 0)
+	if (clock == 0) {
+		sdhci_set_clock(host, clock);
 		return;
+	}
 
 	for (src = 0; src < MAX_BUS_CLK; src++) {
 		delta = sdhci_s3c_consider_clock(ourhost, src, clock);
@@ -215,6 +219,8 @@ static void sdhci_s3c_set_clock(struct sdhci_host *host, unsigned int clock)
 	if (clock < 25 * 1000000)
 		ctrl |= (S3C_SDHCI_CTRL3_FCSEL3 | S3C_SDHCI_CTRL3_FCSEL2);
 	writel(ctrl, host->ioaddr + S3C_SDHCI_CONTROL3);
+
+	sdhci_set_clock(host, clock);
 }
 
 /**
@@ -295,10 +301,11 @@ static void sdhci_cmu_set_clock(struct sdhci_host *host, unsigned int clock)
 	unsigned long timeout;
 	u16 clk = 0;
 
+	host->mmc->actual_clock = 0;
+
 	/* If the clock is going off, set to 0 at clock control register */
 	if (clock == 0) {
 		sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL);
-		host->clock = clock;
 		return;
 	}
 
@@ -306,8 +313,6 @@ static void sdhci_cmu_set_clock(struct sdhci_host *host, unsigned int clock)
 
 	clk_set_rate(ourhost->clk_bus[ourhost->cur_clk], clock);
 
-	host->clock = clock;
-
 	clk = SDHCI_CLOCK_INT_EN;
 	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
 
@@ -329,14 +334,14 @@ static void sdhci_cmu_set_clock(struct sdhci_host *host, unsigned int clock)
 }
 
 /**
- * sdhci_s3c_platform_bus_width - support 8bit buswidth
+ * sdhci_s3c_set_bus_width - support 8bit buswidth
  * @host: The SDHCI host being queried
  * @width: MMC_BUS_WIDTH_ macro for the bus width being requested
  *
  * We have 8-bit width support but is not a v3 controller.
  * So we add platform_bus_width() and support 8bit width.
  */
-static int sdhci_s3c_platform_bus_width(struct sdhci_host *host, int width)
+static void sdhci_s3c_set_bus_width(struct sdhci_host *host, int width)
 {
 	u8 ctrl;
 
@@ -358,93 +363,23 @@ static int sdhci_s3c_platform_bus_width(struct sdhci_host *host, int width)
 	}
 
 	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
-
-	return 0;
 }
 
 static struct sdhci_ops sdhci_s3c_ops = {
 	.get_max_clock		= sdhci_s3c_get_max_clk,
 	.set_clock		= sdhci_s3c_set_clock,
 	.get_min_clock		= sdhci_s3c_get_min_clock,
-	.platform_bus_width	= sdhci_s3c_platform_bus_width,
+	.set_bus_width		= sdhci_s3c_set_bus_width,
+	.reset			= sdhci_reset,
+	.set_uhs_signaling	= sdhci_set_uhs_signaling,
 };
 
-static void sdhci_s3c_notify_change(struct platform_device *dev, int state)
-{
-	struct sdhci_host *host = platform_get_drvdata(dev);
-#ifdef CONFIG_PM_RUNTIME
-	struct sdhci_s3c *sc = sdhci_priv(host);
-#endif
-	unsigned long flags;
-
-	if (host) {
-		spin_lock_irqsave(&host->lock, flags);
-		if (state) {
-			dev_dbg(&dev->dev, "card inserted.\n");
-#ifdef CONFIG_PM_RUNTIME
-			clk_prepare_enable(sc->clk_io);
-#endif
-			host->flags &= ~SDHCI_DEVICE_DEAD;
-			host->quirks |= SDHCI_QUIRK_BROKEN_CARD_DETECTION;
-		} else {
-			dev_dbg(&dev->dev, "card removed.\n");
-			host->flags |= SDHCI_DEVICE_DEAD;
-			host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
-#ifdef CONFIG_PM_RUNTIME
-			clk_disable_unprepare(sc->clk_io);
-#endif
-		}
-		tasklet_schedule(&host->card_tasklet);
-		spin_unlock_irqrestore(&host->lock, flags);
-	}
-}
-
-static irqreturn_t sdhci_s3c_gpio_card_detect_thread(int irq, void *dev_id)
-{
-	struct sdhci_s3c *sc = dev_id;
-	int status = gpio_get_value(sc->ext_cd_gpio);
-	if (sc->pdata->ext_cd_gpio_invert)
-		status = !status;
-	sdhci_s3c_notify_change(sc->pdev, status);
-	return IRQ_HANDLED;
-}
-
-static void sdhci_s3c_setup_card_detect_gpio(struct sdhci_s3c *sc)
-{
-	struct s3c_sdhci_platdata *pdata = sc->pdata;
-	struct device *dev = &sc->pdev->dev;
-
-	if (devm_gpio_request(dev, pdata->ext_cd_gpio, "SDHCI EXT CD") == 0) {
-		sc->ext_cd_gpio = pdata->ext_cd_gpio;
-		sc->ext_cd_irq = gpio_to_irq(pdata->ext_cd_gpio);
-		if (sc->ext_cd_irq &&
-		    request_threaded_irq(sc->ext_cd_irq, NULL,
-					 sdhci_s3c_gpio_card_detect_thread,
-					 IRQF_TRIGGER_RISING |
-					 IRQF_TRIGGER_FALLING |
-					 IRQF_ONESHOT,
-					 dev_name(dev), sc) == 0) {
-			int status = gpio_get_value(sc->ext_cd_gpio);
-			if (pdata->ext_cd_gpio_invert)
-				status = !status;
-			sdhci_s3c_notify_change(sc->pdev, status);
-		} else {
-			dev_warn(dev, "cannot request irq for card detect\n");
-			sc->ext_cd_irq = 0;
-		}
-	} else {
-		dev_err(dev, "cannot request gpio for card detect\n");
-	}
-}
-
 #ifdef CONFIG_OF
 static int sdhci_s3c_parse_dt(struct device *dev,
 		struct sdhci_host *host, struct s3c_sdhci_platdata *pdata)
 {
 	struct device_node *node = dev->of_node;
-	struct sdhci_s3c *ourhost = to_s3c(host);
 	u32 max_width;
-	int gpio;
 
 	/* if the bus-width property is not specified, assume width as 1 */
 	if (of_property_read_u32(node, "bus-width", &max_width))
@@ -462,18 +397,8 @@ static int sdhci_s3c_parse_dt(struct device *dev,
 		return 0;
 	}
 
-	gpio = of_get_named_gpio(node, "cd-gpios", 0);
-	if (gpio_is_valid(gpio)) {
-		pdata->cd_type = S3C_SDHCI_CD_GPIO;
-		pdata->ext_cd_gpio = gpio;
-		ourhost->ext_cd_gpio = -1;
-		if (of_get_property(node, "cd-inverted", NULL))
-			pdata->ext_cd_gpio_invert = 1;
+	if (of_get_named_gpio(node, "cd-gpios", 0))
 		return 0;
-	} else if (gpio != -ENOENT) {
-		dev_err(dev, "invalid card detect gpio specified\n");
-		return -EINVAL;
-	}
 
 	/* assuming internal card detect that will be configured by pinctrl */
 	pdata->cd_type = S3C_SDHCI_CD_INTERNAL;
@@ -606,8 +531,10 @@ static int sdhci_s3c_probe(struct platform_device *pdev)
 	/* Setup quirks for the controller */
 	host->quirks |= SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC;
 	host->quirks |= SDHCI_QUIRK_NO_HISPD_BIT;
-	if (drv_data)
+	if (drv_data) {
 		host->quirks |= drv_data->sdhci_quirks;
+		sc->no_divider = drv_data->no_divider;
+	}
 
 #ifndef CONFIG_MMC_SDHCI_S3C_DMA
 
@@ -656,7 +583,7 @@ static int sdhci_s3c_probe(struct platform_device *pdev)
 	 * If controller does not have internal clock divider,
 	 * we can use overriding functions instead of default.
 	 */
-	if (host->quirks & SDHCI_QUIRK_NONSTANDARD_CLOCK) {
+	if (sc->no_divider) {
 		sdhci_s3c_ops.set_clock = sdhci_cmu_set_clock;
 		sdhci_s3c_ops.get_min_clock = sdhci_cmu_get_min_clock;
 		sdhci_s3c_ops.get_max_clock = sdhci_cmu_get_max_clock;
@@ -674,6 +601,8 @@ static int sdhci_s3c_probe(struct platform_device *pdev)
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_suspend_ignore_children(&pdev->dev, 1);
 
+	mmc_of_parse(host->mmc);
+
 	ret = sdhci_add_host(host);
 	if (ret) {
 		dev_err(dev, "sdhci_add_host() failed\n");
@@ -682,15 +611,6 @@ static int sdhci_s3c_probe(struct platform_device *pdev)
 		goto err_req_regs;
 	}
 
-	/* The following two methods of card detection might call
-	   sdhci_s3c_notify_change() immediately, so they can be called
-	   only after sdhci_add_host(). Setup errors are ignored. */
-	if (pdata->cd_type == S3C_SDHCI_CD_EXTERNAL && pdata->ext_cd_init)
-		pdata->ext_cd_init(&sdhci_s3c_notify_change);
-	if (pdata->cd_type == S3C_SDHCI_CD_GPIO &&
-	    gpio_is_valid(pdata->ext_cd_gpio))
-		sdhci_s3c_setup_card_detect_gpio(sc);
-
 #ifdef CONFIG_PM_RUNTIME
 	if (pdata->cd_type != S3C_SDHCI_CD_INTERNAL)
 		clk_disable_unprepare(sc->clk_io);
@@ -711,16 +631,12 @@ static int sdhci_s3c_remove(struct platform_device *pdev)
 {
 	struct sdhci_host *host =  platform_get_drvdata(pdev);
 	struct sdhci_s3c *sc = sdhci_priv(host);
-	struct s3c_sdhci_platdata *pdata = sc->pdata;
-
-	if (pdata->cd_type == S3C_SDHCI_CD_EXTERNAL && pdata->ext_cd_cleanup)
-		pdata->ext_cd_cleanup(&sdhci_s3c_notify_change);
 
 	if (sc->ext_cd_irq)
 		free_irq(sc->ext_cd_irq, sc);
 
 #ifdef CONFIG_PM_RUNTIME
-	if (pdata->cd_type != S3C_SDHCI_CD_INTERNAL)
+	if (sc->pdata->cd_type != S3C_SDHCI_CD_INTERNAL)
 		clk_prepare_enable(sc->clk_io);
 #endif
 	sdhci_remove_host(host, 1);
@@ -797,7 +713,7 @@ static const struct dev_pm_ops sdhci_s3c_pmops = {
 
 #if defined(CONFIG_CPU_EXYNOS4210) || defined(CONFIG_SOC_EXYNOS4212)
 static struct sdhci_s3c_drv_data exynos4_sdhci_drv_data = {
-	.sdhci_quirks = SDHCI_QUIRK_NONSTANDARD_CLOCK,
+	.no_divider = true,
 };
 #define EXYNOS4_SDHCI_DRV_DATA ((kernel_ulong_t)&exynos4_sdhci_drv_data)
 #else
diff --git a/drivers/mmc/host/sdhci-sirf.c b/drivers/mmc/host/sdhci-sirf.c
index 696122c1b46..17004531d08 100644
--- a/drivers/mmc/host/sdhci-sirf.c
+++ b/drivers/mmc/host/sdhci-sirf.c
@@ -28,7 +28,11 @@ static unsigned int sdhci_sirf_get_max_clk(struct sdhci_host *host)
 }
 
 static struct sdhci_ops sdhci_sirf_ops = {
+	.set_clock = sdhci_set_clock,
 	.get_max_clock	= sdhci_sirf_get_max_clk,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 static struct sdhci_pltfm_data sdhci_sirf_pdata = {
diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c
index 0316dec3f00..9d535c7336e 100644
--- a/drivers/mmc/host/sdhci-spear.c
+++ b/drivers/mmc/host/sdhci-spear.c
@@ -38,7 +38,10 @@ struct spear_sdhci {
 
 /* sdhci ops */
 static const struct sdhci_ops sdhci_pltfm_ops = {
-	/* Nothing to do for now. */
+	.set_clock = sdhci_set_clock,
+	.set_bus_width = sdhci_set_bus_width,
+	.reset = sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
 };
 
 #ifdef CONFIG_OF
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index a835898a68d..d93a063a36f 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -32,11 +32,17 @@
 
 /* Tegra SDHOST controller vendor register definitions */
 #define SDHCI_TEGRA_VENDOR_MISC_CTRL		0x120
+#define SDHCI_MISC_CTRL_ENABLE_SDR104		0x8
+#define SDHCI_MISC_CTRL_ENABLE_SDR50		0x10
 #define SDHCI_MISC_CTRL_ENABLE_SDHCI_SPEC_300	0x20
+#define SDHCI_MISC_CTRL_ENABLE_DDR50		0x200
 
 #define NVQUIRK_FORCE_SDHCI_SPEC_200	BIT(0)
 #define NVQUIRK_ENABLE_BLOCK_GAP_DET	BIT(1)
 #define NVQUIRK_ENABLE_SDHCI_SPEC_300	BIT(2)
+#define NVQUIRK_DISABLE_SDR50		BIT(3)
+#define NVQUIRK_DISABLE_SDR104		BIT(4)
+#define NVQUIRK_DISABLE_DDR50		BIT(5)
 
 struct sdhci_tegra_soc_data {
 	const struct sdhci_pltfm_data *pdata;
@@ -48,19 +54,6 @@ struct sdhci_tegra {
 	int power_gpio;
 };
 
-static u32 tegra_sdhci_readl(struct sdhci_host *host, int reg)
-{
-	u32 val;
-
-	if (unlikely(reg == SDHCI_PRESENT_STATE)) {
-		/* Use wp_gpio here instead? */
-		val = readl(host->ioaddr + reg);
-		return val | SDHCI_WRITE_PROTECT;
-	}
-
-	return readl(host->ioaddr + reg);
-}
-
 static u16 tegra_sdhci_readw(struct sdhci_host *host, int reg)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -108,26 +101,33 @@ static unsigned int tegra_sdhci_get_ro(struct sdhci_host *host)
 	return mmc_gpio_get_ro(host->mmc);
 }
 
-static void tegra_sdhci_reset_exit(struct sdhci_host *host, u8 mask)
+static void tegra_sdhci_reset(struct sdhci_host *host, u8 mask)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_tegra *tegra_host = pltfm_host->priv;
 	const struct sdhci_tegra_soc_data *soc_data = tegra_host->soc_data;
+	u32 misc_ctrl;
+
+	sdhci_reset(host, mask);
 
 	if (!(mask & SDHCI_RESET_ALL))
 		return;
 
+	misc_ctrl = sdhci_readw(host, SDHCI_TEGRA_VENDOR_MISC_CTRL);
 	/* Erratum: Enable SDHCI spec v3.00 support */
-	if (soc_data->nvquirks & NVQUIRK_ENABLE_SDHCI_SPEC_300) {
-		u32 misc_ctrl;
-
-		misc_ctrl = sdhci_readb(host, SDHCI_TEGRA_VENDOR_MISC_CTRL);
+	if (soc_data->nvquirks & NVQUIRK_ENABLE_SDHCI_SPEC_300)
 		misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDHCI_SPEC_300;
-		sdhci_writeb(host, misc_ctrl, SDHCI_TEGRA_VENDOR_MISC_CTRL);
-	}
+	/* Don't advertise UHS modes which aren't supported yet */
+	if (soc_data->nvquirks & NVQUIRK_DISABLE_SDR50)
+		misc_ctrl &= ~SDHCI_MISC_CTRL_ENABLE_SDR50;
+	if (soc_data->nvquirks & NVQUIRK_DISABLE_DDR50)
+		misc_ctrl &= ~SDHCI_MISC_CTRL_ENABLE_DDR50;
+	if (soc_data->nvquirks & NVQUIRK_DISABLE_SDR104)
+		misc_ctrl &= ~SDHCI_MISC_CTRL_ENABLE_SDR104;
+	sdhci_writew(host, misc_ctrl, SDHCI_TEGRA_VENDOR_MISC_CTRL);
 }
 
-static int tegra_sdhci_buswidth(struct sdhci_host *host, int bus_width)
+static void tegra_sdhci_set_bus_width(struct sdhci_host *host, int bus_width)
 {
 	u32 ctrl;
 
@@ -144,23 +144,25 @@ static int tegra_sdhci_buswidth(struct sdhci_host *host, int bus_width)
 			ctrl &= ~SDHCI_CTRL_4BITBUS;
 	}
 	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
-	return 0;
 }
 
 static const struct sdhci_ops tegra_sdhci_ops = {
 	.get_ro     = tegra_sdhci_get_ro,
-	.read_l     = tegra_sdhci_readl,
 	.read_w     = tegra_sdhci_readw,
 	.write_l    = tegra_sdhci_writel,
-	.platform_bus_width = tegra_sdhci_buswidth,
-	.platform_reset_exit = tegra_sdhci_reset_exit,
+	.set_clock  = sdhci_set_clock,
+	.set_bus_width = tegra_sdhci_set_bus_width,
+	.reset      = tegra_sdhci_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
+	.get_max_clock = sdhci_pltfm_clk_get_max_clock,
 };
 
 static const struct sdhci_pltfm_data sdhci_tegra20_pdata = {
 	.quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
 		  SDHCI_QUIRK_NO_HISPD_BIT |
-		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC,
+		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
+		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
 	.ops  = &tegra_sdhci_ops,
 };
 
@@ -175,13 +177,16 @@ static const struct sdhci_pltfm_data sdhci_tegra30_pdata = {
 		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
 		  SDHCI_QUIRK_NO_HISPD_BIT |
-		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC,
+		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
+		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
 	.ops  = &tegra_sdhci_ops,
 };
 
 static struct sdhci_tegra_soc_data soc_data_tegra30 = {
 	.pdata = &sdhci_tegra30_pdata,
-	.nvquirks = NVQUIRK_ENABLE_SDHCI_SPEC_300,
+	.nvquirks = NVQUIRK_ENABLE_SDHCI_SPEC_300 |
+		    NVQUIRK_DISABLE_SDR50 |
+		    NVQUIRK_DISABLE_SDR104,
 };
 
 static const struct sdhci_pltfm_data sdhci_tegra114_pdata = {
@@ -189,12 +194,16 @@ static const struct sdhci_pltfm_data sdhci_tegra114_pdata = {
 		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
 		  SDHCI_QUIRK_SINGLE_POWER_WRITE |
 		  SDHCI_QUIRK_NO_HISPD_BIT |
-		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC,
+		  SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC |
+		  SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN,
 	.ops  = &tegra_sdhci_ops,
 };
 
 static struct sdhci_tegra_soc_data soc_data_tegra114 = {
 	.pdata = &sdhci_tegra114_pdata,
+	.nvquirks = NVQUIRK_DISABLE_SDR50 |
+		    NVQUIRK_DISABLE_DDR50 |
+		    NVQUIRK_DISABLE_SDR104,
 };
 
 static const struct of_device_id sdhci_tegra_dt_match[] = {
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 9a79fc4b60c..47055f3f01b 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -44,6 +44,8 @@
 
 #define MAX_TUNING_LOOP 40
 
+#define ADMA_SIZE	((128 * 2 + 1) * 4)
+
 static unsigned int debug_quirks = 0;
 static unsigned int debug_quirks2;
 
@@ -131,43 +133,26 @@ static void sdhci_dumpregs(struct sdhci_host *host)
  *                                                                           *
 \*****************************************************************************/
 
-static void sdhci_clear_set_irqs(struct sdhci_host *host, u32 clear, u32 set)
-{
-	u32 ier;
-
-	ier = sdhci_readl(host, SDHCI_INT_ENABLE);
-	ier &= ~clear;
-	ier |= set;
-	sdhci_writel(host, ier, SDHCI_INT_ENABLE);
-	sdhci_writel(host, ier, SDHCI_SIGNAL_ENABLE);
-}
-
-static void sdhci_unmask_irqs(struct sdhci_host *host, u32 irqs)
-{
-	sdhci_clear_set_irqs(host, 0, irqs);
-}
-
-static void sdhci_mask_irqs(struct sdhci_host *host, u32 irqs)
-{
-	sdhci_clear_set_irqs(host, irqs, 0);
-}
-
 static void sdhci_set_card_detection(struct sdhci_host *host, bool enable)
 {
-	u32 present, irqs;
+	u32 present;
 
 	if ((host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) ||
 	    (host->mmc->caps & MMC_CAP_NONREMOVABLE))
 		return;
 
-	present = sdhci_readl(host, SDHCI_PRESENT_STATE) &
-			      SDHCI_CARD_PRESENT;
-	irqs = present ? SDHCI_INT_CARD_REMOVE : SDHCI_INT_CARD_INSERT;
+	if (enable) {
+		present = sdhci_readl(host, SDHCI_PRESENT_STATE) &
+				      SDHCI_CARD_PRESENT;
 
-	if (enable)
-		sdhci_unmask_irqs(host, irqs);
-	else
-		sdhci_mask_irqs(host, irqs);
+		host->ier |= present ? SDHCI_INT_CARD_REMOVE :
+				       SDHCI_INT_CARD_INSERT;
+	} else {
+		host->ier &= ~(SDHCI_INT_CARD_REMOVE | SDHCI_INT_CARD_INSERT);
+	}
+
+	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
 static void sdhci_enable_card_detection(struct sdhci_host *host)
@@ -180,22 +165,9 @@ static void sdhci_disable_card_detection(struct sdhci_host *host)
 	sdhci_set_card_detection(host, false);
 }
 
-static void sdhci_reset(struct sdhci_host *host, u8 mask)
+void sdhci_reset(struct sdhci_host *host, u8 mask)
 {
 	unsigned long timeout;
-	u32 uninitialized_var(ier);
-
-	if (host->quirks & SDHCI_QUIRK_NO_CARD_NO_RESET) {
-		if (!(sdhci_readl(host, SDHCI_PRESENT_STATE) &
-			SDHCI_CARD_PRESENT))
-			return;
-	}
-
-	if (host->quirks & SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET)
-		ier = sdhci_readl(host, SDHCI_INT_ENABLE);
-
-	if (host->ops->platform_reset_enter)
-		host->ops->platform_reset_enter(host, mask);
 
 	sdhci_writeb(host, mask, SDHCI_SOFTWARE_RESET);
 
@@ -220,16 +192,27 @@ static void sdhci_reset(struct sdhci_host *host, u8 mask)
 		timeout--;
 		mdelay(1);
 	}
+}
+EXPORT_SYMBOL_GPL(sdhci_reset);
+
+static void sdhci_do_reset(struct sdhci_host *host, u8 mask)
+{
+	if (host->quirks & SDHCI_QUIRK_NO_CARD_NO_RESET) {
+		if (!(sdhci_readl(host, SDHCI_PRESENT_STATE) &
+			SDHCI_CARD_PRESENT))
+			return;
+	}
 
-	if (host->ops->platform_reset_exit)
-		host->ops->platform_reset_exit(host, mask);
+	host->ops->reset(host, mask);
 
-	if (host->quirks & SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET)
-		sdhci_clear_set_irqs(host, SDHCI_INT_ALL_MASK, ier);
+	if (mask & SDHCI_RESET_ALL) {
+		if (host->flags & (SDHCI_USE_SDMA | SDHCI_USE_ADMA)) {
+			if (host->ops->enable_dma)
+				host->ops->enable_dma(host);
+		}
 
-	if (host->flags & (SDHCI_USE_SDMA | SDHCI_USE_ADMA)) {
-		if ((host->ops->enable_dma) && (mask & SDHCI_RESET_ALL))
-			host->ops->enable_dma(host);
+		/* Resetting the controller clears many */
+		host->preset_enabled = false;
 	}
 }
 
@@ -238,15 +221,18 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios);
 static void sdhci_init(struct sdhci_host *host, int soft)
 {
 	if (soft)
-		sdhci_reset(host, SDHCI_RESET_CMD|SDHCI_RESET_DATA);
+		sdhci_do_reset(host, SDHCI_RESET_CMD|SDHCI_RESET_DATA);
 	else
-		sdhci_reset(host, SDHCI_RESET_ALL);
+		sdhci_do_reset(host, SDHCI_RESET_ALL);
 
-	sdhci_clear_set_irqs(host, SDHCI_INT_ALL_MASK,
-		SDHCI_INT_BUS_POWER | SDHCI_INT_DATA_END_BIT |
-		SDHCI_INT_DATA_CRC | SDHCI_INT_DATA_TIMEOUT | SDHCI_INT_INDEX |
-		SDHCI_INT_END_BIT | SDHCI_INT_CRC | SDHCI_INT_TIMEOUT |
-		SDHCI_INT_DATA_END | SDHCI_INT_RESPONSE);
+	host->ier = SDHCI_INT_BUS_POWER | SDHCI_INT_DATA_END_BIT |
+		    SDHCI_INT_DATA_CRC | SDHCI_INT_DATA_TIMEOUT |
+		    SDHCI_INT_INDEX | SDHCI_INT_END_BIT | SDHCI_INT_CRC |
+		    SDHCI_INT_TIMEOUT | SDHCI_INT_DATA_END |
+		    SDHCI_INT_RESPONSE;
+
+	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 
 	if (soft) {
 		/* force clock reconfiguration */
@@ -502,11 +488,6 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 	else
 		direction = DMA_TO_DEVICE;
 
-	/*
-	 * The ADMA descriptor table is mapped further down as we
-	 * need to fill it with data first.
-	 */
-
 	host->align_addr = dma_map_single(mmc_dev(host->mmc),
 		host->align_buffer, 128 * 4, direction);
 	if (dma_mapping_error(mmc_dev(host->mmc), host->align_addr))
@@ -567,7 +548,7 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 		 * If this triggers then we have a calculation bug
 		 * somewhere. :/
 		 */
-		WARN_ON((desc - host->adma_desc) > (128 * 2 + 1) * 4);
+		WARN_ON((desc - host->adma_desc) > ADMA_SIZE);
 	}
 
 	if (host->quirks & SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC) {
@@ -595,17 +576,8 @@ static int sdhci_adma_table_pre(struct sdhci_host *host,
 			host->align_addr, 128 * 4, direction);
 	}
 
-	host->adma_addr = dma_map_single(mmc_dev(host->mmc),
-		host->adma_desc, (128 * 2 + 1) * 4, DMA_TO_DEVICE);
-	if (dma_mapping_error(mmc_dev(host->mmc), host->adma_addr))
-		goto unmap_entries;
-	BUG_ON(host->adma_addr & 0x3);
-
 	return 0;
 
-unmap_entries:
-	dma_unmap_sg(mmc_dev(host->mmc), data->sg,
-		data->sg_len, direction);
 unmap_align:
 	dma_unmap_single(mmc_dev(host->mmc), host->align_addr,
 		128 * 4, direction);
@@ -623,19 +595,25 @@ static void sdhci_adma_table_post(struct sdhci_host *host,
 	u8 *align;
 	char *buffer;
 	unsigned long flags;
+	bool has_unaligned;
 
 	if (data->flags & MMC_DATA_READ)
 		direction = DMA_FROM_DEVICE;
 	else
 		direction = DMA_TO_DEVICE;
 
-	dma_unmap_single(mmc_dev(host->mmc), host->adma_addr,
-		(128 * 2 + 1) * 4, DMA_TO_DEVICE);
-
 	dma_unmap_single(mmc_dev(host->mmc), host->align_addr,
 		128 * 4, direction);
 
-	if (data->flags & MMC_DATA_READ) {
+	/* Do a quick scan of the SG list for any unaligned mappings */
+	has_unaligned = false;
+	for_each_sg(data->sg, sg, host->sg_count, i)
+		if (sg_dma_address(sg) & 3) {
+			has_unaligned = true;
+			break;
+		}
+
+	if (has_unaligned && data->flags & MMC_DATA_READ) {
 		dma_sync_sg_for_cpu(mmc_dev(host->mmc), data->sg,
 			data->sg_len, direction);
 
@@ -721,9 +699,12 @@ static void sdhci_set_transfer_irqs(struct sdhci_host *host)
 	u32 dma_irqs = SDHCI_INT_DMA_END | SDHCI_INT_ADMA_ERROR;
 
 	if (host->flags & SDHCI_REQ_USE_DMA)
-		sdhci_clear_set_irqs(host, pio_irqs, dma_irqs);
+		host->ier = (host->ier & ~pio_irqs) | dma_irqs;
 	else
-		sdhci_clear_set_irqs(host, dma_irqs, pio_irqs);
+		host->ier = (host->ier & ~dma_irqs) | pio_irqs;
+
+	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
 static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_command *cmd)
@@ -976,8 +957,8 @@ static void sdhci_finish_data(struct sdhci_host *host)
 		 * upon error conditions.
 		 */
 		if (data->error) {
-			sdhci_reset(host, SDHCI_RESET_CMD);
-			sdhci_reset(host, SDHCI_RESET_DATA);
+			sdhci_do_reset(host, SDHCI_RESET_CMD);
+			sdhci_do_reset(host, SDHCI_RESET_DATA);
 		}
 
 		sdhci_send_command(host, data->stop);
@@ -1107,24 +1088,23 @@ static void sdhci_finish_command(struct sdhci_host *host)
 
 static u16 sdhci_get_preset_value(struct sdhci_host *host)
 {
-	u16 ctrl, preset = 0;
-
-	ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+	u16 preset = 0;
 
-	switch (ctrl & SDHCI_CTRL_UHS_MASK) {
-	case SDHCI_CTRL_UHS_SDR12:
+	switch (host->timing) {
+	case MMC_TIMING_UHS_SDR12:
 		preset = sdhci_readw(host, SDHCI_PRESET_FOR_SDR12);
 		break;
-	case SDHCI_CTRL_UHS_SDR25:
+	case MMC_TIMING_UHS_SDR25:
 		preset = sdhci_readw(host, SDHCI_PRESET_FOR_SDR25);
 		break;
-	case SDHCI_CTRL_UHS_SDR50:
+	case MMC_TIMING_UHS_SDR50:
 		preset = sdhci_readw(host, SDHCI_PRESET_FOR_SDR50);
 		break;
-	case SDHCI_CTRL_UHS_SDR104:
+	case MMC_TIMING_UHS_SDR104:
+	case MMC_TIMING_MMC_HS200:
 		preset = sdhci_readw(host, SDHCI_PRESET_FOR_SDR104);
 		break;
-	case SDHCI_CTRL_UHS_DDR50:
+	case MMC_TIMING_UHS_DDR50:
 		preset = sdhci_readw(host, SDHCI_PRESET_FOR_DDR50);
 		break;
 	default:
@@ -1136,32 +1116,22 @@ static u16 sdhci_get_preset_value(struct sdhci_host *host)
 	return preset;
 }
 
-static void sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
+void sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
 {
 	int div = 0; /* Initialized for compiler warning */
 	int real_div = div, clk_mul = 1;
 	u16 clk = 0;
 	unsigned long timeout;
 
-	if (clock && clock == host->clock)
-		return;
-
 	host->mmc->actual_clock = 0;
 
-	if (host->ops->set_clock) {
-		host->ops->set_clock(host, clock);
-		if (host->quirks & SDHCI_QUIRK_NONSTANDARD_CLOCK)
-			return;
-	}
-
 	sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL);
 
 	if (clock == 0)
-		goto out;
+		return;
 
 	if (host->version >= SDHCI_SPEC_300) {
-		if (sdhci_readw(host, SDHCI_HOST_CONTROL2) &
-			SDHCI_CTRL_PRESET_VAL_ENABLE) {
+		if (host->preset_enabled) {
 			u16 pre_val;
 
 			clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
@@ -1247,26 +1217,16 @@ clock_set:
 
 	clk |= SDHCI_CLOCK_CARD_EN;
 	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
-
-out:
-	host->clock = clock;
 }
+EXPORT_SYMBOL_GPL(sdhci_set_clock);
 
-static inline void sdhci_update_clock(struct sdhci_host *host)
-{
-	unsigned int clock;
-
-	clock = host->clock;
-	host->clock = 0;
-	sdhci_set_clock(host, clock);
-}
-
-static int sdhci_set_power(struct sdhci_host *host, unsigned short power)
+static void sdhci_set_power(struct sdhci_host *host, unsigned char mode,
+			    unsigned short vdd)
 {
 	u8 pwr = 0;
 
-	if (power != (unsigned short)-1) {
-		switch (1 << power) {
+	if (mode != MMC_POWER_OFF) {
+		switch (1 << vdd) {
 		case MMC_VDD_165_195:
 			pwr = SDHCI_POWER_180;
 			break;
@@ -1284,7 +1244,7 @@ static int sdhci_set_power(struct sdhci_host *host, unsigned short power)
 	}
 
 	if (host->pwr == pwr)
-		return -1;
+		return;
 
 	host->pwr = pwr;
 
@@ -1292,38 +1252,43 @@ static int sdhci_set_power(struct sdhci_host *host, unsigned short power)
 		sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
 		if (host->quirks2 & SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON)
 			sdhci_runtime_pm_bus_off(host);
-		return 0;
-	}
-
-	/*
-	 * Spec says that we should clear the power reg before setting
-	 * a new value. Some controllers don't seem to like this though.
-	 */
-	if (!(host->quirks & SDHCI_QUIRK_SINGLE_POWER_WRITE))
-		sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
+		vdd = 0;
+	} else {
+		/*
+		 * Spec says that we should clear the power reg before setting
+		 * a new value. Some controllers don't seem to like this though.
+		 */
+		if (!(host->quirks & SDHCI_QUIRK_SINGLE_POWER_WRITE))
+			sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
 
-	/*
-	 * At least the Marvell CaFe chip gets confused if we set the voltage
-	 * and set turn on power at the same time, so set the voltage first.
-	 */
-	if (host->quirks & SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER)
-		sdhci_writeb(host, pwr, SDHCI_POWER_CONTROL);
+		/*
+		 * At least the Marvell CaFe chip gets confused if we set the
+		 * voltage and set turn on power at the same time, so set the
+		 * voltage first.
+		 */
+		if (host->quirks & SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER)
+			sdhci_writeb(host, pwr, SDHCI_POWER_CONTROL);
 
-	pwr |= SDHCI_POWER_ON;
+		pwr |= SDHCI_POWER_ON;
 
-	sdhci_writeb(host, pwr, SDHCI_POWER_CONTROL);
+		sdhci_writeb(host, pwr, SDHCI_POWER_CONTROL);
 
-	if (host->quirks2 & SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON)
-		sdhci_runtime_pm_bus_on(host);
+		if (host->quirks2 & SDHCI_QUIRK2_CARD_ON_NEEDS_BUS_ON)
+			sdhci_runtime_pm_bus_on(host);
 
-	/*
-	 * Some controllers need an extra 10ms delay of 10ms before they
-	 * can apply clock after applying power
-	 */
-	if (host->quirks & SDHCI_QUIRK_DELAY_AFTER_POWER)
-		mdelay(10);
+		/*
+		 * Some controllers need an extra 10ms delay of 10ms before
+		 * they can apply clock after applying power
+		 */
+		if (host->quirks & SDHCI_QUIRK_DELAY_AFTER_POWER)
+			mdelay(10);
+	}
 
-	return power;
+	if (host->vmmc) {
+		spin_unlock_irq(&host->lock);
+		mmc_regulator_set_ocr(host->mmc, host->vmmc, vdd);
+		spin_lock_irq(&host->lock);
+	}
 }
 
 /*****************************************************************************\
@@ -1427,10 +1392,53 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
+void sdhci_set_bus_width(struct sdhci_host *host, int width)
+{
+	u8 ctrl;
+
+	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
+	if (width == MMC_BUS_WIDTH_8) {
+		ctrl &= ~SDHCI_CTRL_4BITBUS;
+		if (host->version >= SDHCI_SPEC_300)
+			ctrl |= SDHCI_CTRL_8BITBUS;
+	} else {
+		if (host->version >= SDHCI_SPEC_300)
+			ctrl &= ~SDHCI_CTRL_8BITBUS;
+		if (width == MMC_BUS_WIDTH_4)
+			ctrl |= SDHCI_CTRL_4BITBUS;
+		else
+			ctrl &= ~SDHCI_CTRL_4BITBUS;
+	}
+	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
+}
+EXPORT_SYMBOL_GPL(sdhci_set_bus_width);
+
+void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing)
+{
+	u16 ctrl_2;
+
+	ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+	/* Select Bus Speed Mode for host */
+	ctrl_2 &= ~SDHCI_CTRL_UHS_MASK;
+	if ((timing == MMC_TIMING_MMC_HS200) ||
+	    (timing == MMC_TIMING_UHS_SDR104))
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR104;
+	else if (timing == MMC_TIMING_UHS_SDR12)
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR12;
+	else if (timing == MMC_TIMING_UHS_SDR25)
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR25;
+	else if (timing == MMC_TIMING_UHS_SDR50)
+		ctrl_2 |= SDHCI_CTRL_UHS_SDR50;
+	else if ((timing == MMC_TIMING_UHS_DDR50) ||
+		 (timing == MMC_TIMING_MMC_DDR52))
+		ctrl_2 |= SDHCI_CTRL_UHS_DDR50;
+	sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
+}
+EXPORT_SYMBOL_GPL(sdhci_set_uhs_signaling);
+
 static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 {
 	unsigned long flags;
-	int vdd_bit = -1;
 	u8 ctrl;
 
 	spin_lock_irqsave(&host->lock, flags);
@@ -1456,45 +1464,17 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 		!(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN))
 		sdhci_enable_preset_value(host, false);
 
-	sdhci_set_clock(host, ios->clock);
-
-	if (ios->power_mode == MMC_POWER_OFF)
-		vdd_bit = sdhci_set_power(host, -1);
-	else
-		vdd_bit = sdhci_set_power(host, ios->vdd);
-
-	if (host->vmmc && vdd_bit != -1) {
-		spin_unlock_irqrestore(&host->lock, flags);
-		mmc_regulator_set_ocr(host->mmc, host->vmmc, vdd_bit);
-		spin_lock_irqsave(&host->lock, flags);
+	if (!ios->clock || ios->clock != host->clock) {
+		host->ops->set_clock(host, ios->clock);
+		host->clock = ios->clock;
 	}
 
+	sdhci_set_power(host, ios->power_mode, ios->vdd);
+
 	if (host->ops->platform_send_init_74_clocks)
 		host->ops->platform_send_init_74_clocks(host, ios->power_mode);
 
-	/*
-	 * If your platform has 8-bit width support but is not a v3 controller,
-	 * or if it requires special setup code, you should implement that in
-	 * platform_bus_width().
-	 */
-	if (host->ops->platform_bus_width) {
-		host->ops->platform_bus_width(host, ios->bus_width);
-	} else {
-		ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
-		if (ios->bus_width == MMC_BUS_WIDTH_8) {
-			ctrl &= ~SDHCI_CTRL_4BITBUS;
-			if (host->version >= SDHCI_SPEC_300)
-				ctrl |= SDHCI_CTRL_8BITBUS;
-		} else {
-			if (host->version >= SDHCI_SPEC_300)
-				ctrl &= ~SDHCI_CTRL_8BITBUS;
-			if (ios->bus_width == MMC_BUS_WIDTH_4)
-				ctrl |= SDHCI_CTRL_4BITBUS;
-			else
-				ctrl &= ~SDHCI_CTRL_4BITBUS;
-		}
-		sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
-	}
+	host->ops->set_bus_width(host, ios->bus_width);
 
 	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
 
@@ -1510,19 +1490,20 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 
 		/* In case of UHS-I modes, set High Speed Enable */
 		if ((ios->timing == MMC_TIMING_MMC_HS200) ||
+		    (ios->timing == MMC_TIMING_MMC_DDR52) ||
 		    (ios->timing == MMC_TIMING_UHS_SDR50) ||
 		    (ios->timing == MMC_TIMING_UHS_SDR104) ||
 		    (ios->timing == MMC_TIMING_UHS_DDR50) ||
 		    (ios->timing == MMC_TIMING_UHS_SDR25))
 			ctrl |= SDHCI_CTRL_HISPD;
 
-		ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
-		if (!(ctrl_2 & SDHCI_CTRL_PRESET_VAL_ENABLE)) {
+		if (!host->preset_enabled) {
 			sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 			/*
 			 * We only need to set Driver Strength if the
 			 * preset value enable is not set.
 			 */
+			ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
 			ctrl_2 &= ~SDHCI_CTRL_DRV_TYPE_MASK;
 			if (ios->drv_type == MMC_SET_DRIVER_TYPE_A)
 				ctrl_2 |= SDHCI_CTRL_DRV_TYPE_A;
@@ -1546,7 +1527,7 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 			sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 
 			/* Re-enable SD Clock */
-			sdhci_update_clock(host);
+			host->ops->set_clock(host, host->clock);
 		}
 
 
@@ -1555,25 +1536,8 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 		clk &= ~SDHCI_CLOCK_CARD_EN;
 		sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
 
-		if (host->ops->set_uhs_signaling)
-			host->ops->set_uhs_signaling(host, ios->timing);
-		else {
-			ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
-			/* Select Bus Speed Mode for host */
-			ctrl_2 &= ~SDHCI_CTRL_UHS_MASK;
-			if ((ios->timing == MMC_TIMING_MMC_HS200) ||
-			    (ios->timing == MMC_TIMING_UHS_SDR104))
-				ctrl_2 |= SDHCI_CTRL_UHS_SDR104;
-			else if (ios->timing == MMC_TIMING_UHS_SDR12)
-				ctrl_2 |= SDHCI_CTRL_UHS_SDR12;
-			else if (ios->timing == MMC_TIMING_UHS_SDR25)
-				ctrl_2 |= SDHCI_CTRL_UHS_SDR25;
-			else if (ios->timing == MMC_TIMING_UHS_SDR50)
-				ctrl_2 |= SDHCI_CTRL_UHS_SDR50;
-			else if (ios->timing == MMC_TIMING_UHS_DDR50)
-				ctrl_2 |= SDHCI_CTRL_UHS_DDR50;
-			sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
-		}
+		host->ops->set_uhs_signaling(host, ios->timing);
+		host->timing = ios->timing;
 
 		if (!(host->quirks2 & SDHCI_QUIRK2_PRESET_VALUE_BROKEN) &&
 				((ios->timing == MMC_TIMING_UHS_SDR12) ||
@@ -1590,7 +1554,7 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 		}
 
 		/* Re-enable SD Clock */
-		sdhci_update_clock(host);
+		host->ops->set_clock(host, host->clock);
 	} else
 		sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 
@@ -1600,7 +1564,7 @@ static void sdhci_do_set_ios(struct sdhci_host *host, struct mmc_ios *ios)
 	 * it on each ios seems to solve the problem.
 	 */
 	if(host->quirks & SDHCI_QUIRK_RESET_CMD_DATA_ON_IOS)
-		sdhci_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA);
+		sdhci_do_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA);
 
 	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
@@ -1709,24 +1673,16 @@ static int sdhci_get_ro(struct mmc_host *mmc)
 
 static void sdhci_enable_sdio_irq_nolock(struct sdhci_host *host, int enable)
 {
-	if (host->flags & SDHCI_DEVICE_DEAD)
-		goto out;
-
-	if (enable)
-		host->flags |= SDHCI_SDIO_IRQ_ENABLED;
-	else
-		host->flags &= ~SDHCI_SDIO_IRQ_ENABLED;
-
-	/* SDIO IRQ will be enabled as appropriate in runtime resume */
-	if (host->runtime_suspended)
-		goto out;
+	if (!(host->flags & SDHCI_DEVICE_DEAD)) {
+		if (enable)
+			host->ier |= SDHCI_INT_CARD_INT;
+		else
+			host->ier &= ~SDHCI_INT_CARD_INT;
 
-	if (enable)
-		sdhci_unmask_irqs(host, SDHCI_INT_CARD_INT);
-	else
-		sdhci_mask_irqs(host, SDHCI_INT_CARD_INT);
-out:
-	mmiowb();
+		sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+		sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+		mmiowb();
+	}
 }
 
 static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
@@ -1734,9 +1690,18 @@ static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
 	struct sdhci_host *host = mmc_priv(mmc);
 	unsigned long flags;
 
+	sdhci_runtime_pm_get(host);
+
 	spin_lock_irqsave(&host->lock, flags);
+	if (enable)
+		host->flags |= SDHCI_SDIO_IRQ_ENABLED;
+	else
+		host->flags &= ~SDHCI_SDIO_IRQ_ENABLED;
+
 	sdhci_enable_sdio_irq_nolock(host, enable);
 	spin_unlock_irqrestore(&host->lock, flags);
+
+	sdhci_runtime_pm_put(host);
 }
 
 static int sdhci_do_start_signal_voltage_switch(struct sdhci_host *host,
@@ -1855,22 +1820,15 @@ static int sdhci_card_busy(struct mmc_host *mmc)
 
 static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
-	struct sdhci_host *host;
+	struct sdhci_host *host = mmc_priv(mmc);
 	u16 ctrl;
-	u32 ier;
 	int tuning_loop_counter = MAX_TUNING_LOOP;
-	unsigned long timeout;
 	int err = 0;
-	bool requires_tuning_nonuhs = false;
 	unsigned long flags;
 
-	host = mmc_priv(mmc);
-
 	sdhci_runtime_pm_get(host);
 	spin_lock_irqsave(&host->lock, flags);
 
-	ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
-
 	/*
 	 * The Host Controller needs tuning only in case of SDR104 mode
 	 * and for SDR50 mode when Use Tuning for SDR50 is set in the
@@ -1878,15 +1836,18 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	 * If the Host Controller supports the HS200 mode then the
 	 * tuning function has to be executed.
 	 */
-	if (((ctrl & SDHCI_CTRL_UHS_MASK) == SDHCI_CTRL_UHS_SDR50) &&
-	    (host->flags & SDHCI_SDR50_NEEDS_TUNING ||
-	     host->flags & SDHCI_SDR104_NEEDS_TUNING))
-		requires_tuning_nonuhs = true;
-
-	if (((ctrl & SDHCI_CTRL_UHS_MASK) == SDHCI_CTRL_UHS_SDR104) ||
-	    requires_tuning_nonuhs)
-		ctrl |= SDHCI_CTRL_EXEC_TUNING;
-	else {
+	switch (host->timing) {
+	case MMC_TIMING_MMC_HS200:
+	case MMC_TIMING_UHS_SDR104:
+		break;
+
+	case MMC_TIMING_UHS_SDR50:
+		if (host->flags & SDHCI_SDR50_NEEDS_TUNING ||
+		    host->flags & SDHCI_SDR104_NEEDS_TUNING)
+			break;
+		/* FALLTHROUGH */
+
+	default:
 		spin_unlock_irqrestore(&host->lock, flags);
 		sdhci_runtime_pm_put(host);
 		return 0;
@@ -1899,6 +1860,8 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		return err;
 	}
 
+	ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+	ctrl |= SDHCI_CTRL_EXEC_TUNING;
 	sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2);
 
 	/*
@@ -1911,21 +1874,17 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	 * to make sure we don't hit a controller bug, we _only_
 	 * enable Buffer Read Ready interrupt here.
 	 */
-	ier = sdhci_readl(host, SDHCI_INT_ENABLE);
-	sdhci_clear_set_irqs(host, ier, SDHCI_INT_DATA_AVAIL);
+	sdhci_writel(host, SDHCI_INT_DATA_AVAIL, SDHCI_INT_ENABLE);
+	sdhci_writel(host, SDHCI_INT_DATA_AVAIL, SDHCI_SIGNAL_ENABLE);
 
 	/*
 	 * Issue CMD19 repeatedly till Execute Tuning is set to 0 or the number
 	 * of loops reaches 40 times or a timeout of 150ms occurs.
 	 */
-	timeout = 150;
 	do {
 		struct mmc_command cmd = {0};
 		struct mmc_request mrq = {NULL};
 
-		if (!tuning_loop_counter && !timeout)
-			break;
-
 		cmd.opcode = opcode;
 		cmd.arg = 0;
 		cmd.flags = MMC_RSP_R1 | MMC_CMD_ADTC;
@@ -1933,6 +1892,9 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		cmd.data = NULL;
 		cmd.error = 0;
 
+		if (tuning_loop_counter-- == 0)
+			break;
+
 		mrq.cmd = &cmd;
 		host->mrq = &mrq;
 
@@ -1990,26 +1952,25 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		host->tuning_done = 0;
 
 		ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
-		tuning_loop_counter--;
-		timeout--;
-		mdelay(1);
+
+		/* eMMC spec does not require a delay between tuning cycles */
+		if (opcode == MMC_SEND_TUNING_BLOCK)
+			mdelay(1);
 	} while (ctrl & SDHCI_CTRL_EXEC_TUNING);
 
 	/*
 	 * The Host Driver has exhausted the maximum number of loops allowed,
 	 * so use fixed sampling frequency.
 	 */
-	if (!tuning_loop_counter || !timeout) {
+	if (tuning_loop_counter < 0) {
 		ctrl &= ~SDHCI_CTRL_TUNED_CLK;
 		sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2);
+	}
+	if (!(ctrl & SDHCI_CTRL_TUNED_CLK)) {
+		pr_info(DRIVER_NAME ": Tuning procedure"
+			" failed, falling back to fixed sampling"
+			" clock\n");
 		err = -EIO;
-	} else {
-		if (!(ctrl & SDHCI_CTRL_TUNED_CLK)) {
-			pr_info(DRIVER_NAME ": Tuning procedure"
-				" failed, falling back to fixed sampling"
-				" clock\n");
-			err = -EIO;
-		}
 	}
 
 out:
@@ -2044,7 +2005,8 @@ out:
 	if (err && (host->flags & SDHCI_USING_RETUNING_TIMER))
 		err = 0;
 
-	sdhci_clear_set_irqs(host, SDHCI_INT_DATA_AVAIL, ier);
+	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 	spin_unlock_irqrestore(&host->lock, flags);
 	sdhci_runtime_pm_put(host);
 
@@ -2054,26 +2016,30 @@ out:
 
 static void sdhci_enable_preset_value(struct sdhci_host *host, bool enable)
 {
-	u16 ctrl;
-
 	/* Host Controller v3.00 defines preset value registers */
 	if (host->version < SDHCI_SPEC_300)
 		return;
 
-	ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
-
 	/*
 	 * We only enable or disable Preset Value if they are not already
 	 * enabled or disabled respectively. Otherwise, we bail out.
 	 */
-	if (enable && !(ctrl & SDHCI_CTRL_PRESET_VAL_ENABLE)) {
-		ctrl |= SDHCI_CTRL_PRESET_VAL_ENABLE;
-		sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2);
-		host->flags |= SDHCI_PV_ENABLED;
-	} else if (!enable && (ctrl & SDHCI_CTRL_PRESET_VAL_ENABLE)) {
-		ctrl &= ~SDHCI_CTRL_PRESET_VAL_ENABLE;
+	if (host->preset_enabled != enable) {
+		u16 ctrl = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+
+		if (enable)
+			ctrl |= SDHCI_CTRL_PRESET_VAL_ENABLE;
+		else
+			ctrl &= ~SDHCI_CTRL_PRESET_VAL_ENABLE;
+
 		sdhci_writew(host, ctrl, SDHCI_HOST_CONTROL2);
-		host->flags &= ~SDHCI_PV_ENABLED;
+
+		if (enable)
+			host->flags |= SDHCI_PV_ENABLED;
+		else
+			host->flags &= ~SDHCI_PV_ENABLED;
+
+		host->preset_enabled = enable;
 	}
 }
 
@@ -2095,8 +2061,8 @@ static void sdhci_card_event(struct mmc_host *mmc)
 		pr_err("%s: Resetting controller.\n",
 			mmc_hostname(host->mmc));
 
-		sdhci_reset(host, SDHCI_RESET_CMD);
-		sdhci_reset(host, SDHCI_RESET_DATA);
+		sdhci_do_reset(host, SDHCI_RESET_CMD);
+		sdhci_do_reset(host, SDHCI_RESET_DATA);
 
 		host->mrq->cmd->error = -ENOMEDIUM;
 		tasklet_schedule(&host->finish_tasklet);
@@ -2124,15 +2090,6 @@ static const struct mmc_host_ops sdhci_ops = {
  *                                                                           *
 \*****************************************************************************/
 
-static void sdhci_tasklet_card(unsigned long param)
-{
-	struct sdhci_host *host = (struct sdhci_host*)param;
-
-	sdhci_card_event(host->mmc);
-
-	mmc_detect_change(host->mmc, msecs_to_jiffies(200));
-}
-
 static void sdhci_tasklet_finish(unsigned long param)
 {
 	struct sdhci_host *host;
@@ -2169,12 +2126,12 @@ static void sdhci_tasklet_finish(unsigned long param)
 		/* Some controllers need this kick or reset won't work here */
 		if (host->quirks & SDHCI_QUIRK_CLOCK_BEFORE_RESET)
 			/* This is to force an update */
-			sdhci_update_clock(host);
+			host->ops->set_clock(host, host->clock);
 
 		/* Spec says we should do both at the same time, but Ricoh
 		   controllers do not like that. */
-		sdhci_reset(host, SDHCI_RESET_CMD);
-		sdhci_reset(host, SDHCI_RESET_DATA);
+		sdhci_do_reset(host, SDHCI_RESET_CMD);
+		sdhci_do_reset(host, SDHCI_RESET_DATA);
 	}
 
 	host->mrq = NULL;
@@ -2424,101 +2381,94 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 
 static irqreturn_t sdhci_irq(int irq, void *dev_id)
 {
-	irqreturn_t result;
+	irqreturn_t result = IRQ_NONE;
 	struct sdhci_host *host = dev_id;
-	u32 intmask, unexpected = 0;
-	int cardint = 0, max_loops = 16;
+	u32 intmask, mask, unexpected = 0;
+	int max_loops = 16;
 
 	spin_lock(&host->lock);
 
-	if (host->runtime_suspended) {
+	if (host->runtime_suspended && !sdhci_sdio_irq_enabled(host)) {
 		spin_unlock(&host->lock);
 		return IRQ_NONE;
 	}
 
 	intmask = sdhci_readl(host, SDHCI_INT_STATUS);
-
 	if (!intmask || intmask == 0xffffffff) {
 		result = IRQ_NONE;
 		goto out;
 	}
 
-again:
-	DBG("*** %s got interrupt: 0x%08x\n",
-		mmc_hostname(host->mmc), intmask);
-
-	if (intmask & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE)) {
-		u32 present = sdhci_readl(host, SDHCI_PRESENT_STATE) &
-			      SDHCI_CARD_PRESENT;
-
-		/*
-		 * There is a observation on i.mx esdhc.  INSERT bit will be
-		 * immediately set again when it gets cleared, if a card is
-		 * inserted.  We have to mask the irq to prevent interrupt
-		 * storm which will freeze the system.  And the REMOVE gets
-		 * the same situation.
-		 *
-		 * More testing are needed here to ensure it works for other
-		 * platforms though.
-		 */
-		sdhci_mask_irqs(host, present ? SDHCI_INT_CARD_INSERT :
-						SDHCI_INT_CARD_REMOVE);
-		sdhci_unmask_irqs(host, present ? SDHCI_INT_CARD_REMOVE :
-						  SDHCI_INT_CARD_INSERT);
-
-		sdhci_writel(host, intmask & (SDHCI_INT_CARD_INSERT |
-			     SDHCI_INT_CARD_REMOVE), SDHCI_INT_STATUS);
-		intmask &= ~(SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE);
-		tasklet_schedule(&host->card_tasklet);
-	}
-
-	if (intmask & SDHCI_INT_CMD_MASK) {
-		sdhci_writel(host, intmask & SDHCI_INT_CMD_MASK,
-			SDHCI_INT_STATUS);
-		sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK);
-	}
+	do {
+		/* Clear selected interrupts. */
+		mask = intmask & (SDHCI_INT_CMD_MASK | SDHCI_INT_DATA_MASK |
+				  SDHCI_INT_BUS_POWER);
+		sdhci_writel(host, mask, SDHCI_INT_STATUS);
 
-	if (intmask & SDHCI_INT_DATA_MASK) {
-		sdhci_writel(host, intmask & SDHCI_INT_DATA_MASK,
-			SDHCI_INT_STATUS);
-		sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK);
-	}
+		DBG("*** %s got interrupt: 0x%08x\n",
+			mmc_hostname(host->mmc), intmask);
 
-	intmask &= ~(SDHCI_INT_CMD_MASK | SDHCI_INT_DATA_MASK);
+		if (intmask & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE)) {
+			u32 present = sdhci_readl(host, SDHCI_PRESENT_STATE) &
+				      SDHCI_CARD_PRESENT;
 
-	intmask &= ~SDHCI_INT_ERROR;
+			/*
+			 * There is a observation on i.mx esdhc.  INSERT
+			 * bit will be immediately set again when it gets
+			 * cleared, if a card is inserted.  We have to mask
+			 * the irq to prevent interrupt storm which will
+			 * freeze the system.  And the REMOVE gets the
+			 * same situation.
+			 *
+			 * More testing are needed here to ensure it works
+			 * for other platforms though.
+			 */
+			host->ier &= ~(SDHCI_INT_CARD_INSERT |
+				       SDHCI_INT_CARD_REMOVE);
+			host->ier |= present ? SDHCI_INT_CARD_REMOVE :
+					       SDHCI_INT_CARD_INSERT;
+			sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+			sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+
+			sdhci_writel(host, intmask & (SDHCI_INT_CARD_INSERT |
+				     SDHCI_INT_CARD_REMOVE), SDHCI_INT_STATUS);
+
+			host->thread_isr |= intmask & (SDHCI_INT_CARD_INSERT |
+						       SDHCI_INT_CARD_REMOVE);
+			result = IRQ_WAKE_THREAD;
+		}
 
-	if (intmask & SDHCI_INT_BUS_POWER) {
-		pr_err("%s: Card is consuming too much power!\n",
-			mmc_hostname(host->mmc));
-		sdhci_writel(host, SDHCI_INT_BUS_POWER, SDHCI_INT_STATUS);
-	}
+		if (intmask & SDHCI_INT_CMD_MASK)
+			sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK);
 
-	intmask &= ~SDHCI_INT_BUS_POWER;
+		if (intmask & SDHCI_INT_DATA_MASK)
+			sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK);
 
-	if (intmask & SDHCI_INT_CARD_INT)
-		cardint = 1;
+		if (intmask & SDHCI_INT_BUS_POWER)
+			pr_err("%s: Card is consuming too much power!\n",
+				mmc_hostname(host->mmc));
 
-	intmask &= ~SDHCI_INT_CARD_INT;
+		if (intmask & SDHCI_INT_CARD_INT) {
+			sdhci_enable_sdio_irq_nolock(host, false);
+			host->thread_isr |= SDHCI_INT_CARD_INT;
+			result = IRQ_WAKE_THREAD;
+		}
 
-	if (intmask) {
-		unexpected |= intmask;
-		sdhci_writel(host, intmask, SDHCI_INT_STATUS);
-	}
+		intmask &= ~(SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE |
+			     SDHCI_INT_CMD_MASK | SDHCI_INT_DATA_MASK |
+			     SDHCI_INT_ERROR | SDHCI_INT_BUS_POWER |
+			     SDHCI_INT_CARD_INT);
 
-	result = IRQ_HANDLED;
+		if (intmask) {
+			unexpected |= intmask;
+			sdhci_writel(host, intmask, SDHCI_INT_STATUS);
+		}
 
-	intmask = sdhci_readl(host, SDHCI_INT_STATUS);
+		if (result == IRQ_NONE)
+			result = IRQ_HANDLED;
 
-	/*
-	 * If we know we'll call the driver to signal SDIO IRQ, disregard
-	 * further indications of Card Interrupt in the status to avoid a
-	 * needless loop.
-	 */
-	if (cardint)
-		intmask &= ~SDHCI_INT_CARD_INT;
-	if (intmask && --max_loops)
-		goto again;
+		intmask = sdhci_readl(host, SDHCI_INT_STATUS);
+	} while (intmask && --max_loops);
 out:
 	spin_unlock(&host->lock);
 
@@ -2527,15 +2477,38 @@ out:
 			   mmc_hostname(host->mmc), unexpected);
 		sdhci_dumpregs(host);
 	}
-	/*
-	 * We have to delay this as it calls back into the driver.
-	 */
-	if (cardint)
-		mmc_signal_sdio_irq(host->mmc);
 
 	return result;
 }
 
+static irqreturn_t sdhci_thread_irq(int irq, void *dev_id)
+{
+	struct sdhci_host *host = dev_id;
+	unsigned long flags;
+	u32 isr;
+
+	spin_lock_irqsave(&host->lock, flags);
+	isr = host->thread_isr;
+	host->thread_isr = 0;
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (isr & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE)) {
+		sdhci_card_event(host->mmc);
+		mmc_detect_change(host->mmc, msecs_to_jiffies(200));
+	}
+
+	if (isr & SDHCI_INT_CARD_INT) {
+		sdio_run_irqs(host->mmc);
+
+		spin_lock_irqsave(&host->lock, flags);
+		if (host->flags & SDHCI_SDIO_IRQ_ENABLED)
+			sdhci_enable_sdio_irq_nolock(host, true);
+		spin_unlock_irqrestore(&host->lock, flags);
+	}
+
+	return isr ? IRQ_HANDLED : IRQ_NONE;
+}
+
 /*****************************************************************************\
  *                                                                           *
  * Suspend/resume                                                            *
@@ -2572,9 +2545,6 @@ EXPORT_SYMBOL_GPL(sdhci_disable_irq_wakeups);
 
 int sdhci_suspend_host(struct sdhci_host *host)
 {
-	if (host->ops->platform_suspend)
-		host->ops->platform_suspend(host);
-
 	sdhci_disable_card_detection(host);
 
 	/* Disable tuning since we are suspending */
@@ -2584,7 +2554,9 @@ int sdhci_suspend_host(struct sdhci_host *host)
 	}
 
 	if (!device_may_wakeup(mmc_dev(host->mmc))) {
-		sdhci_mask_irqs(host, SDHCI_INT_ALL_MASK);
+		host->ier = 0;
+		sdhci_writel(host, 0, SDHCI_INT_ENABLE);
+		sdhci_writel(host, 0, SDHCI_SIGNAL_ENABLE);
 		free_irq(host->irq, host);
 	} else {
 		sdhci_enable_irq_wakeups(host);
@@ -2605,8 +2577,9 @@ int sdhci_resume_host(struct sdhci_host *host)
 	}
 
 	if (!device_may_wakeup(mmc_dev(host->mmc))) {
-		ret = request_irq(host->irq, sdhci_irq, IRQF_SHARED,
-				  mmc_hostname(host->mmc), host);
+		ret = request_threaded_irq(host->irq, sdhci_irq,
+					   sdhci_thread_irq, IRQF_SHARED,
+					   mmc_hostname(host->mmc), host);
 		if (ret)
 			return ret;
 	} else {
@@ -2628,9 +2601,6 @@ int sdhci_resume_host(struct sdhci_host *host)
 
 	sdhci_enable_card_detection(host);
 
-	if (host->ops->platform_resume)
-		host->ops->platform_resume(host);
-
 	/* Set the re-tuning expiration flag */
 	if (host->flags & SDHCI_USING_RETUNING_TIMER)
 		host->flags |= SDHCI_NEEDS_RETUNING;
@@ -2682,10 +2652,12 @@ int sdhci_runtime_suspend_host(struct sdhci_host *host)
 	}
 
 	spin_lock_irqsave(&host->lock, flags);
-	sdhci_mask_irqs(host, SDHCI_INT_ALL_MASK);
+	host->ier &= SDHCI_INT_CARD_INT;
+	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 	spin_unlock_irqrestore(&host->lock, flags);
 
-	synchronize_irq(host->irq);
+	synchronize_hardirq(host->irq);
 
 	spin_lock_irqsave(&host->lock, flags);
 	host->runtime_suspended = true;
@@ -2729,7 +2701,7 @@ int sdhci_runtime_resume_host(struct sdhci_host *host)
 	host->runtime_suspended = false;
 
 	/* Enable SDIO IRQ */
-	if ((host->flags & SDHCI_SDIO_IRQ_ENABLED))
+	if (host->flags & SDHCI_SDIO_IRQ_ENABLED)
 		sdhci_enable_sdio_irq_nolock(host, true);
 
 	/* Enable Card Detection */
@@ -2788,7 +2760,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	if (debug_quirks2)
 		host->quirks2 = debug_quirks2;
 
-	sdhci_reset(host, SDHCI_RESET_ALL);
+	sdhci_do_reset(host, SDHCI_RESET_ALL);
 
 	host->version = sdhci_readw(host, SDHCI_HOST_VERSION);
 	host->version = (host->version & SDHCI_SPEC_VER_MASK)
@@ -2848,15 +2820,29 @@ int sdhci_add_host(struct sdhci_host *host)
 		 * (128) and potentially one alignment transfer for
 		 * each of those entries.
 		 */
-		host->adma_desc = kmalloc((128 * 2 + 1) * 4, GFP_KERNEL);
+		host->adma_desc = dma_alloc_coherent(mmc_dev(host->mmc),
+						     ADMA_SIZE, &host->adma_addr,
+						     GFP_KERNEL);
 		host->align_buffer = kmalloc(128 * 4, GFP_KERNEL);
 		if (!host->adma_desc || !host->align_buffer) {
-			kfree(host->adma_desc);
+			dma_free_coherent(mmc_dev(host->mmc), ADMA_SIZE,
+					  host->adma_desc, host->adma_addr);
 			kfree(host->align_buffer);
 			pr_warning("%s: Unable to allocate ADMA "
 				"buffers. Falling back to standard DMA.\n",
 				mmc_hostname(mmc));
 			host->flags &= ~SDHCI_USE_ADMA;
+			host->adma_desc = NULL;
+			host->align_buffer = NULL;
+		} else if (host->adma_addr & 3) {
+			pr_warning("%s: unable to allocate aligned ADMA descriptor\n",
+				   mmc_hostname(mmc));
+			host->flags &= ~SDHCI_USE_ADMA;
+			dma_free_coherent(mmc_dev(host->mmc), ADMA_SIZE,
+					  host->adma_desc, host->adma_addr);
+			kfree(host->align_buffer);
+			host->adma_desc = NULL;
+			host->align_buffer = NULL;
 		}
 	}
 
@@ -2941,6 +2927,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	mmc->max_busy_timeout = (1 << 27) / host->timeout_clk;
 
 	mmc->caps |= MMC_CAP_SDIO_IRQ | MMC_CAP_ERASE | MMC_CAP_CMD23;
+	mmc->caps2 |= MMC_CAP2_SDIO_IRQ_NOTHREAD;
 
 	if (host->quirks & SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12)
 		host->flags |= SDHCI_AUTO_CMD12;
@@ -3212,8 +3199,6 @@ int sdhci_add_host(struct sdhci_host *host)
 	/*
 	 * Init tasklets.
 	 */
-	tasklet_init(&host->card_tasklet,
-		sdhci_tasklet_card, (unsigned long)host);
 	tasklet_init(&host->finish_tasklet,
 		sdhci_tasklet_finish, (unsigned long)host);
 
@@ -3230,8 +3215,8 @@ int sdhci_add_host(struct sdhci_host *host)
 
 	sdhci_init(host, 0);
 
-	ret = request_irq(host->irq, sdhci_irq, IRQF_SHARED,
-		mmc_hostname(mmc), host);
+	ret = request_threaded_irq(host->irq, sdhci_irq, sdhci_thread_irq,
+				   IRQF_SHARED,	mmc_hostname(mmc), host);
 	if (ret) {
 		pr_err("%s: Failed to request IRQ %d: %d\n",
 		       mmc_hostname(mmc), host->irq, ret);
@@ -3273,12 +3258,12 @@ int sdhci_add_host(struct sdhci_host *host)
 
 #ifdef SDHCI_USE_LEDS_CLASS
 reset:
-	sdhci_reset(host, SDHCI_RESET_ALL);
-	sdhci_mask_irqs(host, SDHCI_INT_ALL_MASK);
+	sdhci_do_reset(host, SDHCI_RESET_ALL);
+	sdhci_writel(host, 0, SDHCI_INT_ENABLE);
+	sdhci_writel(host, 0, SDHCI_SIGNAL_ENABLE);
 	free_irq(host->irq, host);
 #endif
 untasklet:
-	tasklet_kill(&host->card_tasklet);
 	tasklet_kill(&host->finish_tasklet);
 
 	return ret;
@@ -3315,14 +3300,14 @@ void sdhci_remove_host(struct sdhci_host *host, int dead)
 #endif
 
 	if (!dead)
-		sdhci_reset(host, SDHCI_RESET_ALL);
+		sdhci_do_reset(host, SDHCI_RESET_ALL);
 
-	sdhci_mask_irqs(host, SDHCI_INT_ALL_MASK);
+	sdhci_writel(host, 0, SDHCI_INT_ENABLE);
+	sdhci_writel(host, 0, SDHCI_SIGNAL_ENABLE);
 	free_irq(host->irq, host);
 
 	del_timer_sync(&host->timer);
 
-	tasklet_kill(&host->card_tasklet);
 	tasklet_kill(&host->finish_tasklet);
 
 	if (host->vmmc) {
@@ -3335,7 +3320,9 @@ void sdhci_remove_host(struct sdhci_host *host, int dead)
 		regulator_put(host->vqmmc);
 	}
 
-	kfree(host->adma_desc);
+	if (host->adma_desc)
+		dma_free_coherent(mmc_dev(host->mmc), ADMA_SIZE,
+				  host->adma_desc, host->adma_addr);
 	kfree(host->align_buffer);
 
 	host->adma_desc = NULL;
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 0a3ed01887d..4a5cd5e3fa3 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -281,18 +281,14 @@ struct sdhci_ops {
 	unsigned int	(*get_max_clock)(struct sdhci_host *host);
 	unsigned int	(*get_min_clock)(struct sdhci_host *host);
 	unsigned int	(*get_timeout_clock)(struct sdhci_host *host);
-	int		(*platform_bus_width)(struct sdhci_host *host,
-					       int width);
+	void		(*set_bus_width)(struct sdhci_host *host, int width);
 	void (*platform_send_init_74_clocks)(struct sdhci_host *host,
 					     u8 power_mode);
 	unsigned int    (*get_ro)(struct sdhci_host *host);
-	void	(*platform_reset_enter)(struct sdhci_host *host, u8 mask);
-	void	(*platform_reset_exit)(struct sdhci_host *host, u8 mask);
+	void		(*reset)(struct sdhci_host *host, u8 mask);
 	int	(*platform_execute_tuning)(struct sdhci_host *host, u32 opcode);
-	int	(*set_uhs_signaling)(struct sdhci_host *host, unsigned int uhs);
+	void	(*set_uhs_signaling)(struct sdhci_host *host, unsigned int uhs);
 	void	(*hw_reset)(struct sdhci_host *host);
-	void	(*platform_suspend)(struct sdhci_host *host);
-	void	(*platform_resume)(struct sdhci_host *host);
 	void    (*adma_workaround)(struct sdhci_host *host, u32 intmask);
 	void	(*platform_init)(struct sdhci_host *host);
 	void    (*card_event)(struct sdhci_host *host);
@@ -397,6 +393,16 @@ extern void sdhci_remove_host(struct sdhci_host *host, int dead);
 extern void sdhci_send_command(struct sdhci_host *host,
 				struct mmc_command *cmd);
 
+static inline bool sdhci_sdio_irq_enabled(struct sdhci_host *host)
+{
+	return !!(host->flags & SDHCI_SDIO_IRQ_ENABLED);
+}
+
+void sdhci_set_clock(struct sdhci_host *host, unsigned int clock);
+void sdhci_set_bus_width(struct sdhci_host *host, int width);
+void sdhci_reset(struct sdhci_host *host, u8 mask);
+void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing);
+
 #ifdef CONFIG_PM
 extern int sdhci_suspend_host(struct sdhci_host *host);
 extern int sdhci_resume_host(struct sdhci_host *host);
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 54730f4aac8..656fbba4c42 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -803,12 +803,13 @@ static u32 sh_mmcif_set_cmd(struct sh_mmcif_host *host,
 			break;
 		}
 		switch (host->timing) {
-		case MMC_TIMING_UHS_DDR50:
+		case MMC_TIMING_MMC_DDR52:
 			/*
 			 * MMC core will only set this timing, if the host
-			 * advertises the MMC_CAP_UHS_DDR50 capability. MMCIF
-			 * implementations with this capability, e.g. sh73a0,
-			 * will have to set it in their platform data.
+			 * advertises the MMC_CAP_1_8V_DDR/MMC_CAP_1_2V_DDR
+			 * capability. MMCIF implementations with this
+			 * capability, e.g. sh73a0, will have to set it
+			 * in their platform data.
 			 */
 			tmp |= CMD_SET_DARS;
 			break;
diff --git a/drivers/mmc/host/usdhi6rol0.c b/drivers/mmc/host/usdhi6rol0.c
new file mode 100644
index 00000000000..f0a39eb049a
--- /dev/null
+++ b/drivers/mmc/host/usdhi6rol0.c
@@ -0,0 +1,1847 @@
+/*
+ * Copyright (C) 2013-2014 Renesas Electronics Europe Ltd.
+ * Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/highmem.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/log2.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
+#include <linux/mmc/sd.h>
+#include <linux/mmc/sdio.h>
+#include <linux/module.h>
+#include <linux/pagemap.h>
+#include <linux/platform_device.h>
+#include <linux/scatterlist.h>
+#include <linux/string.h>
+#include <linux/time.h>
+#include <linux/virtio.h>
+#include <linux/workqueue.h>
+
+#define USDHI6_SD_CMD		0x0000
+#define USDHI6_SD_PORT_SEL	0x0004
+#define USDHI6_SD_ARG		0x0008
+#define USDHI6_SD_STOP		0x0010
+#define USDHI6_SD_SECCNT	0x0014
+#define USDHI6_SD_RSP10		0x0018
+#define USDHI6_SD_RSP32		0x0020
+#define USDHI6_SD_RSP54		0x0028
+#define USDHI6_SD_RSP76		0x0030
+#define USDHI6_SD_INFO1		0x0038
+#define USDHI6_SD_INFO2		0x003c
+#define USDHI6_SD_INFO1_MASK	0x0040
+#define USDHI6_SD_INFO2_MASK	0x0044
+#define USDHI6_SD_CLK_CTRL	0x0048
+#define USDHI6_SD_SIZE		0x004c
+#define USDHI6_SD_OPTION	0x0050
+#define USDHI6_SD_ERR_STS1	0x0058
+#define USDHI6_SD_ERR_STS2	0x005c
+#define USDHI6_SD_BUF0		0x0060
+#define USDHI6_SDIO_MODE	0x0068
+#define USDHI6_SDIO_INFO1	0x006c
+#define USDHI6_SDIO_INFO1_MASK	0x0070
+#define USDHI6_CC_EXT_MODE	0x01b0
+#define USDHI6_SOFT_RST		0x01c0
+#define USDHI6_VERSION		0x01c4
+#define USDHI6_HOST_MODE	0x01c8
+#define USDHI6_SDIF_MODE	0x01cc
+
+#define USDHI6_SD_CMD_APP		0x0040
+#define USDHI6_SD_CMD_MODE_RSP_AUTO	0x0000
+#define USDHI6_SD_CMD_MODE_RSP_NONE	0x0300
+#define USDHI6_SD_CMD_MODE_RSP_R1	0x0400	/* Also R5, R6, R7 */
+#define USDHI6_SD_CMD_MODE_RSP_R1B	0x0500	/* R1b */
+#define USDHI6_SD_CMD_MODE_RSP_R2	0x0600
+#define USDHI6_SD_CMD_MODE_RSP_R3	0x0700	/* Also R4 */
+#define USDHI6_SD_CMD_DATA		0x0800
+#define USDHI6_SD_CMD_READ		0x1000
+#define USDHI6_SD_CMD_MULTI		0x2000
+#define USDHI6_SD_CMD_CMD12_AUTO_OFF	0x4000
+
+#define USDHI6_CC_EXT_MODE_SDRW		BIT(1)
+
+#define USDHI6_SD_INFO1_RSP_END		BIT(0)
+#define USDHI6_SD_INFO1_ACCESS_END	BIT(2)
+#define USDHI6_SD_INFO1_CARD_OUT	BIT(3)
+#define USDHI6_SD_INFO1_CARD_IN		BIT(4)
+#define USDHI6_SD_INFO1_CD		BIT(5)
+#define USDHI6_SD_INFO1_WP		BIT(7)
+#define USDHI6_SD_INFO1_D3_CARD_OUT	BIT(8)
+#define USDHI6_SD_INFO1_D3_CARD_IN	BIT(9)
+
+#define USDHI6_SD_INFO2_CMD_ERR		BIT(0)
+#define USDHI6_SD_INFO2_CRC_ERR		BIT(1)
+#define USDHI6_SD_INFO2_END_ERR		BIT(2)
+#define USDHI6_SD_INFO2_TOUT		BIT(3)
+#define USDHI6_SD_INFO2_IWA_ERR		BIT(4)
+#define USDHI6_SD_INFO2_IRA_ERR		BIT(5)
+#define USDHI6_SD_INFO2_RSP_TOUT	BIT(6)
+#define USDHI6_SD_INFO2_SDDAT0		BIT(7)
+#define USDHI6_SD_INFO2_BRE		BIT(8)
+#define USDHI6_SD_INFO2_BWE		BIT(9)
+#define USDHI6_SD_INFO2_SCLKDIVEN	BIT(13)
+#define USDHI6_SD_INFO2_CBSY		BIT(14)
+#define USDHI6_SD_INFO2_ILA		BIT(15)
+
+#define USDHI6_SD_INFO1_CARD_INSERT (USDHI6_SD_INFO1_CARD_IN | USDHI6_SD_INFO1_D3_CARD_IN)
+#define USDHI6_SD_INFO1_CARD_EJECT (USDHI6_SD_INFO1_CARD_OUT | USDHI6_SD_INFO1_D3_CARD_OUT)
+#define USDHI6_SD_INFO1_CARD (USDHI6_SD_INFO1_CARD_INSERT | USDHI6_SD_INFO1_CARD_EJECT)
+#define USDHI6_SD_INFO1_CARD_CD (USDHI6_SD_INFO1_CARD_IN | USDHI6_SD_INFO1_CARD_OUT)
+
+#define USDHI6_SD_INFO2_ERR	(USDHI6_SD_INFO2_CMD_ERR |	\
+	USDHI6_SD_INFO2_CRC_ERR | USDHI6_SD_INFO2_END_ERR |	\
+	USDHI6_SD_INFO2_TOUT | USDHI6_SD_INFO2_IWA_ERR |	\
+	USDHI6_SD_INFO2_IRA_ERR | USDHI6_SD_INFO2_RSP_TOUT |	\
+	USDHI6_SD_INFO2_ILA)
+
+#define USDHI6_SD_INFO1_IRQ	(USDHI6_SD_INFO1_RSP_END | USDHI6_SD_INFO1_ACCESS_END | \
+				 USDHI6_SD_INFO1_CARD)
+
+#define USDHI6_SD_INFO2_IRQ	(USDHI6_SD_INFO2_ERR | USDHI6_SD_INFO2_BRE | \
+				 USDHI6_SD_INFO2_BWE | 0x0800 | USDHI6_SD_INFO2_ILA)
+
+#define USDHI6_SD_CLK_CTRL_SCLKEN	BIT(8)
+
+#define USDHI6_SD_STOP_STP		BIT(0)
+#define USDHI6_SD_STOP_SEC		BIT(8)
+
+#define USDHI6_SDIO_INFO1_IOIRQ		BIT(0)
+#define USDHI6_SDIO_INFO1_EXPUB52	BIT(14)
+#define USDHI6_SDIO_INFO1_EXWT		BIT(15)
+
+#define USDHI6_SD_ERR_STS1_CRC_NO_ERROR	BIT(13)
+
+#define USDHI6_SOFT_RST_RESERVED	(BIT(1) | BIT(2))
+#define USDHI6_SOFT_RST_RESET		BIT(0)
+
+#define USDHI6_SD_OPTION_TIMEOUT_SHIFT	4
+#define USDHI6_SD_OPTION_TIMEOUT_MASK	(0xf << USDHI6_SD_OPTION_TIMEOUT_SHIFT)
+#define USDHI6_SD_OPTION_WIDTH_1	BIT(15)
+
+#define USDHI6_SD_PORT_SEL_PORTS_SHIFT	8
+
+#define USDHI6_SD_CLK_CTRL_DIV_MASK	0xff
+
+#define USDHI6_SDIO_INFO1_IRQ	(USDHI6_SDIO_INFO1_IOIRQ | 3 | \
+				 USDHI6_SDIO_INFO1_EXPUB52 | USDHI6_SDIO_INFO1_EXWT)
+
+#define USDHI6_MIN_DMA 64
+
+enum usdhi6_wait_for {
+	USDHI6_WAIT_FOR_REQUEST,
+	USDHI6_WAIT_FOR_CMD,
+	USDHI6_WAIT_FOR_MREAD,
+	USDHI6_WAIT_FOR_MWRITE,
+	USDHI6_WAIT_FOR_READ,
+	USDHI6_WAIT_FOR_WRITE,
+	USDHI6_WAIT_FOR_DATA_END,
+	USDHI6_WAIT_FOR_STOP,
+	USDHI6_WAIT_FOR_DMA,
+};
+
+struct usdhi6_page {
+	struct page *page;
+	void *mapped;		/* mapped page */
+};
+
+struct usdhi6_host {
+	struct mmc_host *mmc;
+	struct mmc_request *mrq;
+	void __iomem *base;
+	struct clk *clk;
+
+	/* SG memory handling */
+
+	/* Common for multiple and single block requests */
+	struct usdhi6_page pg;	/* current page from an SG */
+	void *blk_page;		/* either a mapped page, or the bounce buffer */
+	size_t offset;		/* offset within a page, including sg->offset */
+
+	/* Blocks, crossing a page boundary */
+	size_t head_len;
+	struct usdhi6_page head_pg;
+
+	/* A bounce buffer for unaligned blocks or blocks, crossing a page boundary */
+	struct scatterlist bounce_sg;
+	u8 bounce_buf[512];
+
+	/* Multiple block requests only */
+	struct scatterlist *sg;	/* current SG segment */
+	int page_idx;		/* page index within an SG segment */
+
+	enum usdhi6_wait_for wait;
+	u32 status_mask;
+	u32 status2_mask;
+	u32 sdio_mask;
+	u32 io_error;
+	u32 irq_status;
+	unsigned long imclk;
+	unsigned long rate;
+	bool app_cmd;
+
+	/* Timeout handling */
+	struct delayed_work timeout_work;
+	unsigned long timeout;
+
+	/* DMA support */
+	struct dma_chan *chan_rx;
+	struct dma_chan *chan_tx;
+	bool dma_active;
+};
+
+/*			I/O primitives					*/
+
+static void usdhi6_write(struct usdhi6_host *host, u32 reg, u32 data)
+{
+	iowrite32(data, host->base + reg);
+	dev_vdbg(mmc_dev(host->mmc), "%s(0x%p + 0x%x) = 0x%x\n", __func__,
+		host->base, reg, data);
+}
+
+static void usdhi6_write16(struct usdhi6_host *host, u32 reg, u16 data)
+{
+	iowrite16(data, host->base + reg);
+	dev_vdbg(mmc_dev(host->mmc), "%s(0x%p + 0x%x) = 0x%x\n", __func__,
+		host->base, reg, data);
+}
+
+static u32 usdhi6_read(struct usdhi6_host *host, u32 reg)
+{
+	u32 data = ioread32(host->base + reg);
+	dev_vdbg(mmc_dev(host->mmc), "%s(0x%p + 0x%x) = 0x%x\n", __func__,
+		host->base, reg, data);
+	return data;
+}
+
+static u16 usdhi6_read16(struct usdhi6_host *host, u32 reg)
+{
+	u16 data = ioread16(host->base + reg);
+	dev_vdbg(mmc_dev(host->mmc), "%s(0x%p + 0x%x) = 0x%x\n", __func__,
+		host->base, reg, data);
+	return data;
+}
+
+static void usdhi6_irq_enable(struct usdhi6_host *host, u32 info1, u32 info2)
+{
+	host->status_mask = USDHI6_SD_INFO1_IRQ & ~info1;
+	host->status2_mask = USDHI6_SD_INFO2_IRQ & ~info2;
+	usdhi6_write(host, USDHI6_SD_INFO1_MASK, host->status_mask);
+	usdhi6_write(host, USDHI6_SD_INFO2_MASK, host->status2_mask);
+}
+
+static void usdhi6_wait_for_resp(struct usdhi6_host *host)
+{
+	usdhi6_irq_enable(host, USDHI6_SD_INFO1_RSP_END |
+			  USDHI6_SD_INFO1_ACCESS_END | USDHI6_SD_INFO1_CARD_CD,
+			  USDHI6_SD_INFO2_ERR);
+}
+
+static void usdhi6_wait_for_brwe(struct usdhi6_host *host, bool read)
+{
+	usdhi6_irq_enable(host, USDHI6_SD_INFO1_ACCESS_END |
+			  USDHI6_SD_INFO1_CARD_CD, USDHI6_SD_INFO2_ERR |
+			  (read ? USDHI6_SD_INFO2_BRE : USDHI6_SD_INFO2_BWE));
+}
+
+static void usdhi6_only_cd(struct usdhi6_host *host)
+{
+	/* Mask all except card hotplug */
+	usdhi6_irq_enable(host, USDHI6_SD_INFO1_CARD_CD, 0);
+}
+
+static void usdhi6_mask_all(struct usdhi6_host *host)
+{
+	usdhi6_irq_enable(host, 0, 0);
+}
+
+static int usdhi6_error_code(struct usdhi6_host *host)
+{
+	u32 err;
+
+	usdhi6_write(host, USDHI6_SD_STOP, USDHI6_SD_STOP_STP);
+
+	if (host->io_error &
+	    (USDHI6_SD_INFO2_RSP_TOUT | USDHI6_SD_INFO2_TOUT)) {
+		u32 rsp54 = usdhi6_read(host, USDHI6_SD_RSP54);
+		int opc = host->mrq ? host->mrq->cmd->opcode : -1;
+
+		err = usdhi6_read(host, USDHI6_SD_ERR_STS2);
+		/* Response timeout is often normal, don't spam the log */
+		if (host->wait == USDHI6_WAIT_FOR_CMD)
+			dev_dbg(mmc_dev(host->mmc),
+				"T-out sts 0x%x, resp 0x%x, state %u, CMD%d\n",
+				err, rsp54, host->wait, opc);
+		else
+			dev_warn(mmc_dev(host->mmc),
+				 "T-out sts 0x%x, resp 0x%x, state %u, CMD%d\n",
+				 err, rsp54, host->wait, opc);
+		return -ETIMEDOUT;
+	}
+
+	err = usdhi6_read(host, USDHI6_SD_ERR_STS1);
+	if (err != USDHI6_SD_ERR_STS1_CRC_NO_ERROR)
+		dev_warn(mmc_dev(host->mmc), "Err sts 0x%x, state %u, CMD%d\n",
+			 err, host->wait, host->mrq ? host->mrq->cmd->opcode : -1);
+	if (host->io_error & USDHI6_SD_INFO2_ILA)
+		return -EILSEQ;
+
+	return -EIO;
+}
+
+/*			Scatter-Gather management			*/
+
+/*
+ * In PIO mode we have to map each page separately, using kmap(). That way
+ * adjacent pages are mapped to non-adjacent virtual addresses. That's why we
+ * have to use a bounce buffer for blocks, crossing page boundaries. Such blocks
+ * have been observed with an SDIO WiFi card (b43 driver).
+ */
+static void usdhi6_blk_bounce(struct usdhi6_host *host,
+			      struct scatterlist *sg)
+{
+	struct mmc_data *data = host->mrq->data;
+	size_t blk_head = host->head_len;
+
+	dev_dbg(mmc_dev(host->mmc), "%s(): CMD%u of %u SG: %ux%u @ 0x%x\n",
+		__func__, host->mrq->cmd->opcode, data->sg_len,
+		data->blksz, data->blocks, sg->offset);
+
+	host->head_pg.page	= host->pg.page;
+	host->head_pg.mapped	= host->pg.mapped;
+	host->pg.page		= nth_page(host->pg.page, 1);
+	host->pg.mapped		= kmap(host->pg.page);
+
+	host->blk_page = host->bounce_buf;
+	host->offset = 0;
+
+	if (data->flags & MMC_DATA_READ)
+		return;
+
+	memcpy(host->bounce_buf, host->head_pg.mapped + PAGE_SIZE - blk_head,
+	       blk_head);
+	memcpy(host->bounce_buf + blk_head, host->pg.mapped,
+	       data->blksz - blk_head);
+}
+
+/* Only called for multiple block IO */
+static void usdhi6_sg_prep(struct usdhi6_host *host)
+{
+	struct mmc_request *mrq = host->mrq;
+	struct mmc_data *data = mrq->data;
+
+	usdhi6_write(host, USDHI6_SD_SECCNT, data->blocks);
+
+	host->sg = data->sg;
+	/* TODO: if we always map, this is redundant */
+	host->offset = host->sg->offset;
+}
+
+/* Map the first page in an SG segment: common for multiple and single block IO */
+static void *usdhi6_sg_map(struct usdhi6_host *host)
+{
+	struct mmc_data *data = host->mrq->data;
+	struct scatterlist *sg = data->sg_len > 1 ? host->sg : data->sg;
+	size_t head = PAGE_SIZE - sg->offset;
+	size_t blk_head = head % data->blksz;
+
+	WARN(host->pg.page, "%p not properly unmapped!\n", host->pg.page);
+	if (WARN(sg_dma_len(sg) % data->blksz,
+		 "SG size %u isn't a multiple of block size %u\n",
+		 sg_dma_len(sg), data->blksz))
+		return NULL;
+
+	host->pg.page = sg_page(sg);
+	host->pg.mapped = kmap(host->pg.page);
+	host->offset = sg->offset;
+
+	/*
+	 * Block size must be a power of 2 for multi-block transfers,
+	 * therefore blk_head is equal for all pages in this SG
+	 */
+	host->head_len = blk_head;
+
+	if (head < data->blksz)
+		/*
+		 * The first block in the SG crosses a page boundary.
+		 * Max blksz = 512, so blocks can only span 2 pages
+		 */
+		usdhi6_blk_bounce(host, sg);
+	else
+		host->blk_page = host->pg.mapped;
+
+	dev_dbg(mmc_dev(host->mmc), "Mapped %p (%lx) at %p + %u for CMD%u @ 0x%p\n",
+		host->pg.page, page_to_pfn(host->pg.page), host->pg.mapped,
+		sg->offset, host->mrq->cmd->opcode, host->mrq);
+
+	return host->blk_page + host->offset;
+}
+
+/* Unmap the current page: common for multiple and single block IO */
+static void usdhi6_sg_unmap(struct usdhi6_host *host, bool force)
+{
+	struct mmc_data *data = host->mrq->data;
+	struct page *page = host->head_pg.page;
+
+	if (page) {
+		/* Previous block was cross-page boundary */
+		struct scatterlist *sg = data->sg_len > 1 ?
+			host->sg : data->sg;
+		size_t blk_head = host->head_len;
+
+		if (!data->error && data->flags & MMC_DATA_READ) {
+			memcpy(host->head_pg.mapped + PAGE_SIZE - blk_head,
+			       host->bounce_buf, blk_head);
+			memcpy(host->pg.mapped, host->bounce_buf + blk_head,
+			       data->blksz - blk_head);
+		}
+
+		flush_dcache_page(page);
+		kunmap(page);
+
+		host->head_pg.page = NULL;
+
+		if (!force && sg_dma_len(sg) + sg->offset >
+		    (host->page_idx << PAGE_SHIFT) + data->blksz - blk_head)
+			/* More blocks in this SG, don't unmap the next page */
+			return;
+	}
+
+	page = host->pg.page;
+	if (!page)
+		return;
+
+	flush_dcache_page(page);
+	kunmap(page);
+
+	host->pg.page = NULL;
+}
+
+/* Called from MMC_WRITE_MULTIPLE_BLOCK or MMC_READ_MULTIPLE_BLOCK */
+static void usdhi6_sg_advance(struct usdhi6_host *host)
+{
+	struct mmc_data *data = host->mrq->data;
+	size_t done, total;
+
+	/* New offset: set at the end of the previous block */
+	if (host->head_pg.page) {
+		/* Finished a cross-page block, jump to the new page */
+		host->page_idx++;
+		host->offset = data->blksz - host->head_len;
+		host->blk_page = host->pg.mapped;
+		usdhi6_sg_unmap(host, false);
+	} else {
+		host->offset += data->blksz;
+		/* The completed block didn't cross a page boundary */
+		if (host->offset == PAGE_SIZE) {
+			/* If required, we'll map the page below */
+			host->offset = 0;
+			host->page_idx++;
+		}
+	}
+
+	/*
+	 * Now host->blk_page + host->offset point at the end of our last block
+	 * and host->page_idx is the index of the page, in which our new block
+	 * is located, if any
+	 */
+
+	done = (host->page_idx << PAGE_SHIFT) + host->offset;
+	total = host->sg->offset + sg_dma_len(host->sg);
+
+	dev_dbg(mmc_dev(host->mmc), "%s(): %zu of %zu @ %zu\n", __func__,
+		done, total, host->offset);
+
+	if (done < total && host->offset) {
+		/* More blocks in this page */
+		if (host->offset + data->blksz > PAGE_SIZE)
+			/* We approached at a block, that spans 2 pages */
+			usdhi6_blk_bounce(host, host->sg);
+
+		return;
+	}
+
+	/* Finished current page or an SG segment */
+	usdhi6_sg_unmap(host, false);
+
+	if (done == total) {
+		/*
+		 * End of an SG segment or the complete SG: jump to the next
+		 * segment, we'll map it later in usdhi6_blk_read() or
+		 * usdhi6_blk_write()
+		 */
+		struct scatterlist *next = sg_next(host->sg);
+
+		host->page_idx = 0;
+
+		if (!next)
+			host->wait = USDHI6_WAIT_FOR_DATA_END;
+		host->sg = next;
+
+		if (WARN(next && sg_dma_len(next) % data->blksz,
+			 "SG size %u isn't a multiple of block size %u\n",
+			 sg_dma_len(next), data->blksz))
+			data->error = -EINVAL;
+
+		return;
+	}
+
+	/* We cannot get here after crossing a page border */
+
+	/* Next page in the same SG */
+	host->pg.page = nth_page(sg_page(host->sg), host->page_idx);
+	host->pg.mapped = kmap(host->pg.page);
+	host->blk_page = host->pg.mapped;
+
+	dev_dbg(mmc_dev(host->mmc), "Mapped %p (%lx) at %p for CMD%u @ 0x%p\n",
+		host->pg.page, page_to_pfn(host->pg.page), host->pg.mapped,
+		host->mrq->cmd->opcode, host->mrq);
+}
+
+/*			DMA handling					*/
+
+static void usdhi6_dma_release(struct usdhi6_host *host)
+{
+	host->dma_active = false;
+	if (host->chan_tx) {
+		struct dma_chan *chan = host->chan_tx;
+		host->chan_tx = NULL;
+		dma_release_channel(chan);
+	}
+	if (host->chan_rx) {
+		struct dma_chan *chan = host->chan_rx;
+		host->chan_rx = NULL;
+		dma_release_channel(chan);
+	}
+}
+
+static void usdhi6_dma_stop_unmap(struct usdhi6_host *host)
+{
+	struct mmc_data *data = host->mrq->data;
+
+	if (!host->dma_active)
+		return;
+
+	usdhi6_write(host, USDHI6_CC_EXT_MODE, 0);
+	host->dma_active = false;
+
+	if (data->flags & MMC_DATA_READ)
+		dma_unmap_sg(host->chan_rx->device->dev, data->sg,
+			     data->sg_len, DMA_FROM_DEVICE);
+	else
+		dma_unmap_sg(host->chan_tx->device->dev, data->sg,
+			     data->sg_len, DMA_TO_DEVICE);
+}
+
+static void usdhi6_dma_complete(void *arg)
+{
+	struct usdhi6_host *host = arg;
+	struct mmc_request *mrq = host->mrq;
+
+	if (WARN(!mrq || !mrq->data, "%s: NULL data in DMA completion for %p!\n",
+		 dev_name(mmc_dev(host->mmc)), mrq))
+		return;
+
+	dev_dbg(mmc_dev(host->mmc), "%s(): CMD%u DMA completed\n", __func__,
+		mrq->cmd->opcode);
+
+	usdhi6_dma_stop_unmap(host);
+	usdhi6_wait_for_brwe(host, mrq->data->flags & MMC_DATA_READ);
+}
+
+static int usdhi6_dma_setup(struct usdhi6_host *host, struct dma_chan *chan,
+			    enum dma_transfer_direction dir)
+{
+	struct mmc_data *data = host->mrq->data;
+	struct scatterlist *sg = data->sg;
+	struct dma_async_tx_descriptor *desc = NULL;
+	dma_cookie_t cookie = -EINVAL;
+	enum dma_data_direction data_dir;
+	int ret;
+
+	switch (dir) {
+	case DMA_MEM_TO_DEV:
+		data_dir = DMA_TO_DEVICE;
+		break;
+	case DMA_DEV_TO_MEM:
+		data_dir = DMA_FROM_DEVICE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = dma_map_sg(chan->device->dev, sg, data->sg_len, data_dir);
+	if (ret > 0) {
+		host->dma_active = true;
+		desc = dmaengine_prep_slave_sg(chan, sg, ret, dir,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	}
+
+	if (desc) {
+		desc->callback = usdhi6_dma_complete;
+		desc->callback_param = host;
+		cookie = dmaengine_submit(desc);
+	}
+
+	dev_dbg(mmc_dev(host->mmc), "%s(): mapped %d -> %d, cookie %d @ %p\n",
+		__func__, data->sg_len, ret, cookie, desc);
+
+	if (cookie < 0) {
+		/* DMA failed, fall back to PIO */
+		if (ret >= 0)
+			ret = cookie;
+		usdhi6_dma_release(host);
+		dev_warn(mmc_dev(host->mmc),
+			 "DMA failed: %d, falling back to PIO\n", ret);
+	}
+
+	return cookie;
+}
+
+static int usdhi6_dma_start(struct usdhi6_host *host)
+{
+	if (!host->chan_rx || !host->chan_tx)
+		return -ENODEV;
+
+	if (host->mrq->data->flags & MMC_DATA_READ)
+		return usdhi6_dma_setup(host, host->chan_rx, DMA_DEV_TO_MEM);
+
+	return usdhi6_dma_setup(host, host->chan_tx, DMA_MEM_TO_DEV);
+}
+
+static void usdhi6_dma_kill(struct usdhi6_host *host)
+{
+	struct mmc_data *data = host->mrq->data;
+
+	dev_dbg(mmc_dev(host->mmc), "%s(): SG of %u: %ux%u\n",
+		__func__, data->sg_len, data->blocks, data->blksz);
+	/* Abort DMA */
+	if (data->flags & MMC_DATA_READ)
+		dmaengine_terminate_all(host->chan_rx);
+	else
+		dmaengine_terminate_all(host->chan_tx);
+}
+
+static void usdhi6_dma_check_error(struct usdhi6_host *host)
+{
+	struct mmc_data *data = host->mrq->data;
+
+	dev_dbg(mmc_dev(host->mmc), "%s(): IO error %d, status 0x%x\n",
+		__func__, host->io_error, usdhi6_read(host, USDHI6_SD_INFO1));
+
+	if (host->io_error) {
+		data->error = usdhi6_error_code(host);
+		data->bytes_xfered = 0;
+		usdhi6_dma_kill(host);
+		usdhi6_dma_release(host);
+		dev_warn(mmc_dev(host->mmc),
+			 "DMA failed: %d, falling back to PIO\n", data->error);
+		return;
+	}
+
+	/*
+	 * The datasheet tells us to check a response from the card, whereas
+	 * responses only come after the command phase, not after the data
+	 * phase. Let's check anyway.
+	 */
+	if (host->irq_status & USDHI6_SD_INFO1_RSP_END)
+		dev_warn(mmc_dev(host->mmc), "Unexpected response received!\n");
+}
+
+static void usdhi6_dma_kick(struct usdhi6_host *host)
+{
+	if (host->mrq->data->flags & MMC_DATA_READ)
+		dma_async_issue_pending(host->chan_rx);
+	else
+		dma_async_issue_pending(host->chan_tx);
+}
+
+static void usdhi6_dma_request(struct usdhi6_host *host, phys_addr_t start)
+{
+	struct dma_slave_config cfg = {
+		.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+		.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+	};
+	int ret;
+
+	host->chan_tx = dma_request_slave_channel(mmc_dev(host->mmc), "tx");
+	dev_dbg(mmc_dev(host->mmc), "%s: TX: got channel %p\n", __func__,
+		host->chan_tx);
+
+	if (!host->chan_tx)
+		return;
+
+	cfg.direction = DMA_MEM_TO_DEV;
+	cfg.dst_addr = start + USDHI6_SD_BUF0;
+	cfg.dst_maxburst = 128;	/* 128 words * 4 bytes = 512 bytes */
+	cfg.src_addr = 0;
+	ret = dmaengine_slave_config(host->chan_tx, &cfg);
+	if (ret < 0)
+		goto e_release_tx;
+
+	host->chan_rx = dma_request_slave_channel(mmc_dev(host->mmc), "rx");
+	dev_dbg(mmc_dev(host->mmc), "%s: RX: got channel %p\n", __func__,
+		host->chan_rx);
+
+	if (!host->chan_rx)
+		goto e_release_tx;
+
+	cfg.direction = DMA_DEV_TO_MEM;
+	cfg.src_addr = cfg.dst_addr;
+	cfg.src_maxburst = 128;	/* 128 words * 4 bytes = 512 bytes */
+	cfg.dst_addr = 0;
+	ret = dmaengine_slave_config(host->chan_rx, &cfg);
+	if (ret < 0)
+		goto e_release_rx;
+
+	return;
+
+e_release_rx:
+	dma_release_channel(host->chan_rx);
+	host->chan_rx = NULL;
+e_release_tx:
+	dma_release_channel(host->chan_tx);
+	host->chan_tx = NULL;
+}
+
+/*			API helpers					*/
+
+static void usdhi6_clk_set(struct usdhi6_host *host, struct mmc_ios *ios)
+{
+	unsigned long rate = ios->clock;
+	u32 val;
+	unsigned int i;
+
+	for (i = 1000; i; i--) {
+		if (usdhi6_read(host, USDHI6_SD_INFO2) & USDHI6_SD_INFO2_SCLKDIVEN)
+			break;
+		usleep_range(10, 100);
+	}
+
+	if (!i) {
+		dev_err(mmc_dev(host->mmc), "SD bus busy, clock set aborted\n");
+		return;
+	}
+
+	val = usdhi6_read(host, USDHI6_SD_CLK_CTRL) & ~USDHI6_SD_CLK_CTRL_DIV_MASK;
+
+	if (rate) {
+		unsigned long new_rate;
+
+		if (host->imclk <= rate) {
+			if (ios->timing != MMC_TIMING_UHS_DDR50) {
+				/* Cannot have 1-to-1 clock in DDR mode */
+				new_rate = host->imclk;
+				val |= 0xff;
+			} else {
+				new_rate = host->imclk / 2;
+			}
+		} else {
+			unsigned long div =
+				roundup_pow_of_two(DIV_ROUND_UP(host->imclk, rate));
+			val |= div >> 2;
+			new_rate = host->imclk / div;
+		}
+
+		if (host->rate == new_rate)
+			return;
+
+		host->rate = new_rate;
+
+		dev_dbg(mmc_dev(host->mmc), "target %lu, div %u, set %lu\n",
+			rate, (val & 0xff) << 2, new_rate);
+	}
+
+	/*
+	 * if old or new rate is equal to input rate, have to switch the clock
+	 * off before changing and on after
+	 */
+	if (host->imclk == rate || host->imclk == host->rate || !rate)
+		usdhi6_write(host, USDHI6_SD_CLK_CTRL,
+			     val & ~USDHI6_SD_CLK_CTRL_SCLKEN);
+
+	if (!rate) {
+		host->rate = 0;
+		return;
+	}
+
+	usdhi6_write(host, USDHI6_SD_CLK_CTRL, val);
+
+	if (host->imclk == rate || host->imclk == host->rate ||
+	    !(val & USDHI6_SD_CLK_CTRL_SCLKEN))
+		usdhi6_write(host, USDHI6_SD_CLK_CTRL,
+			     val | USDHI6_SD_CLK_CTRL_SCLKEN);
+}
+
+static void usdhi6_set_power(struct usdhi6_host *host, struct mmc_ios *ios)
+{
+	struct mmc_host *mmc = host->mmc;
+
+	if (!IS_ERR(mmc->supply.vmmc))
+		/* Errors ignored... */
+		mmc_regulator_set_ocr(mmc, mmc->supply.vmmc,
+				      ios->power_mode ? ios->vdd : 0);
+}
+
+static int usdhi6_reset(struct usdhi6_host *host)
+{
+	int i;
+
+	usdhi6_write(host, USDHI6_SOFT_RST, USDHI6_SOFT_RST_RESERVED);
+	cpu_relax();
+	usdhi6_write(host, USDHI6_SOFT_RST, USDHI6_SOFT_RST_RESERVED | USDHI6_SOFT_RST_RESET);
+	for (i = 1000; i; i--)
+		if (usdhi6_read(host, USDHI6_SOFT_RST) & USDHI6_SOFT_RST_RESET)
+			break;
+
+	return i ? 0 : -ETIMEDOUT;
+}
+
+static void usdhi6_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct usdhi6_host *host = mmc_priv(mmc);
+	u32 option, mode;
+	int ret;
+
+	dev_dbg(mmc_dev(mmc), "%uHz, OCR: %u, power %u, bus-width %u, timing %u\n",
+		ios->clock, ios->vdd, ios->power_mode, ios->bus_width, ios->timing);
+
+	switch (ios->power_mode) {
+	case MMC_POWER_OFF:
+		usdhi6_set_power(host, ios);
+		usdhi6_only_cd(host);
+		break;
+	case MMC_POWER_UP:
+		/*
+		 * We only also touch USDHI6_SD_OPTION from .request(), which
+		 * cannot race with MMC_POWER_UP
+		 */
+		ret = usdhi6_reset(host);
+		if (ret < 0) {
+			dev_err(mmc_dev(mmc), "Cannot reset the interface!\n");
+		} else {
+			usdhi6_set_power(host, ios);
+			usdhi6_only_cd(host);
+		}
+		break;
+	case MMC_POWER_ON:
+		option = usdhi6_read(host, USDHI6_SD_OPTION);
+		/*
+		 * The eMMC standard only allows 4 or 8 bits in the DDR mode,
+		 * the same probably holds for SD cards. We check here anyway,
+		 * since the datasheet explicitly requires 4 bits for DDR.
+		 */
+		if (ios->bus_width == MMC_BUS_WIDTH_1) {
+			if (ios->timing == MMC_TIMING_UHS_DDR50)
+				dev_err(mmc_dev(mmc),
+					"4 bits are required for DDR\n");
+			option |= USDHI6_SD_OPTION_WIDTH_1;
+			mode = 0;
+		} else {
+			option &= ~USDHI6_SD_OPTION_WIDTH_1;
+			mode = ios->timing == MMC_TIMING_UHS_DDR50;
+		}
+		usdhi6_write(host, USDHI6_SD_OPTION, option);
+		usdhi6_write(host, USDHI6_SDIF_MODE, mode);
+		break;
+	}
+
+	if (host->rate != ios->clock)
+		usdhi6_clk_set(host, ios);
+}
+
+/* This is data timeout. Response timeout is fixed to 640 clock cycles */
+static void usdhi6_timeout_set(struct usdhi6_host *host)
+{
+	struct mmc_request *mrq = host->mrq;
+	u32 val;
+	unsigned long ticks;
+
+	if (!mrq->data)
+		ticks = host->rate / 1000 * mrq->cmd->busy_timeout;
+	else
+		ticks = host->rate / 1000000 * (mrq->data->timeout_ns / 1000) +
+			mrq->data->timeout_clks;
+
+	if (!ticks || ticks > 1 << 27)
+		/* Max timeout */
+		val = 14;
+	else if (ticks < 1 << 13)
+		/* Min timeout */
+		val = 0;
+	else
+		val = order_base_2(ticks) - 13;
+
+	dev_dbg(mmc_dev(host->mmc), "Set %s timeout %lu ticks @ %lu Hz\n",
+		mrq->data ? "data" : "cmd", ticks, host->rate);
+
+	/* Timeout Counter mask: 0xf0 */
+	usdhi6_write(host, USDHI6_SD_OPTION, (val << USDHI6_SD_OPTION_TIMEOUT_SHIFT) |
+		     (usdhi6_read(host, USDHI6_SD_OPTION) & ~USDHI6_SD_OPTION_TIMEOUT_MASK));
+}
+
+static void usdhi6_request_done(struct usdhi6_host *host)
+{
+	struct mmc_request *mrq = host->mrq;
+	struct mmc_data *data = mrq->data;
+
+	if (WARN(host->pg.page || host->head_pg.page,
+		 "Page %p or %p not unmapped: wait %u, CMD%d(%c) @ +0x%zx %ux%u in SG%u!\n",
+		 host->pg.page, host->head_pg.page, host->wait, mrq->cmd->opcode,
+		 data ? (data->flags & MMC_DATA_READ ? 'R' : 'W') : '-',
+		 data ? host->offset : 0, data ? data->blocks : 0,
+		 data ? data->blksz : 0, data ? data->sg_len : 0))
+		usdhi6_sg_unmap(host, true);
+
+	if (mrq->cmd->error ||
+	    (data && data->error) ||
+	    (mrq->stop && mrq->stop->error))
+		dev_dbg(mmc_dev(host->mmc), "%s(CMD%d: %ux%u): err %d %d %d\n",
+			__func__, mrq->cmd->opcode, data ? data->blocks : 0,
+			data ? data->blksz : 0,
+			mrq->cmd->error,
+			data ? data->error : 1,
+			mrq->stop ? mrq->stop->error : 1);
+
+	/* Disable DMA */
+	usdhi6_write(host, USDHI6_CC_EXT_MODE, 0);
+	host->wait = USDHI6_WAIT_FOR_REQUEST;
+	host->mrq = NULL;
+
+	mmc_request_done(host->mmc, mrq);
+}
+
+static int usdhi6_cmd_flags(struct usdhi6_host *host)
+{
+	struct mmc_request *mrq = host->mrq;
+	struct mmc_command *cmd = mrq->cmd;
+	u16 opc = cmd->opcode;
+
+	if (host->app_cmd) {
+		host->app_cmd = false;
+		opc |= USDHI6_SD_CMD_APP;
+	}
+
+	if (mrq->data) {
+		opc |= USDHI6_SD_CMD_DATA;
+
+		if (mrq->data->flags & MMC_DATA_READ)
+			opc |= USDHI6_SD_CMD_READ;
+
+		if (cmd->opcode == MMC_READ_MULTIPLE_BLOCK ||
+		    cmd->opcode == MMC_WRITE_MULTIPLE_BLOCK ||
+		    (cmd->opcode == SD_IO_RW_EXTENDED &&
+		     mrq->data->blocks > 1)) {
+			opc |= USDHI6_SD_CMD_MULTI;
+			if (!mrq->stop)
+				opc |= USDHI6_SD_CMD_CMD12_AUTO_OFF;
+		}
+
+		switch (mmc_resp_type(cmd)) {
+		case MMC_RSP_NONE:
+			opc |= USDHI6_SD_CMD_MODE_RSP_NONE;
+			break;
+		case MMC_RSP_R1:
+			opc |= USDHI6_SD_CMD_MODE_RSP_R1;
+			break;
+		case MMC_RSP_R1B:
+			opc |= USDHI6_SD_CMD_MODE_RSP_R1B;
+			break;
+		case MMC_RSP_R2:
+			opc |= USDHI6_SD_CMD_MODE_RSP_R2;
+			break;
+		case MMC_RSP_R3:
+			opc |= USDHI6_SD_CMD_MODE_RSP_R3;
+			break;
+		default:
+			dev_warn(mmc_dev(host->mmc),
+				 "Unknown response type %d\n",
+				 mmc_resp_type(cmd));
+			return -EINVAL;
+		}
+	}
+
+	return opc;
+}
+
+static int usdhi6_rq_start(struct usdhi6_host *host)
+{
+	struct mmc_request *mrq = host->mrq;
+	struct mmc_command *cmd = mrq->cmd;
+	struct mmc_data *data = mrq->data;
+	int opc = usdhi6_cmd_flags(host);
+	int i;
+
+	if (opc < 0)
+		return opc;
+
+	for (i = 1000; i; i--) {
+		if (!(usdhi6_read(host, USDHI6_SD_INFO2) & USDHI6_SD_INFO2_CBSY))
+			break;
+		usleep_range(10, 100);
+	}
+
+	if (!i) {
+		dev_dbg(mmc_dev(host->mmc), "Command active, request aborted\n");
+		return -EAGAIN;
+	}
+
+	if (data) {
+		bool use_dma;
+		int ret = 0;
+
+		host->page_idx = 0;
+
+		if (cmd->opcode == SD_IO_RW_EXTENDED && data->blocks > 1) {
+			switch (data->blksz) {
+			case 512:
+				break;
+			case 32:
+			case 64:
+			case 128:
+			case 256:
+				if (mrq->stop)
+					ret = -EINVAL;
+				break;
+			default:
+				ret = -EINVAL;
+			}
+		} else if ((cmd->opcode == MMC_READ_MULTIPLE_BLOCK ||
+			    cmd->opcode == MMC_WRITE_MULTIPLE_BLOCK) &&
+			   data->blksz != 512) {
+			ret = -EINVAL;
+		}
+
+		if (ret < 0) {
+			dev_warn(mmc_dev(host->mmc), "%s(): %u blocks of %u bytes\n",
+				 __func__, data->blocks, data->blksz);
+			return -EINVAL;
+		}
+
+		if (cmd->opcode == MMC_READ_MULTIPLE_BLOCK ||
+		    cmd->opcode == MMC_WRITE_MULTIPLE_BLOCK ||
+		    (cmd->opcode == SD_IO_RW_EXTENDED &&
+		     data->blocks > 1))
+			usdhi6_sg_prep(host);
+
+		usdhi6_write(host, USDHI6_SD_SIZE, data->blksz);
+
+		if ((data->blksz >= USDHI6_MIN_DMA ||
+		     data->blocks > 1) &&
+		    (data->blksz % 4 ||
+		     data->sg->offset % 4))
+			dev_dbg(mmc_dev(host->mmc),
+				"Bad SG of %u: %ux%u @ %u\n", data->sg_len,
+				data->blksz, data->blocks, data->sg->offset);
+
+		/* Enable DMA for USDHI6_MIN_DMA bytes or more */
+		use_dma = data->blksz >= USDHI6_MIN_DMA &&
+			!(data->blksz % 4) &&
+			usdhi6_dma_start(host) >= DMA_MIN_COOKIE;
+
+		if (use_dma)
+			usdhi6_write(host, USDHI6_CC_EXT_MODE, USDHI6_CC_EXT_MODE_SDRW);
+
+		dev_dbg(mmc_dev(host->mmc),
+			"%s(): request opcode %u, %u blocks of %u bytes in %u segments, %s %s @+0x%x%s\n",
+			__func__, cmd->opcode, data->blocks, data->blksz,
+			data->sg_len, use_dma ? "DMA" : "PIO",
+			data->flags & MMC_DATA_READ ? "read" : "write",
+			data->sg->offset, mrq->stop ? " + stop" : "");
+	} else {
+		dev_dbg(mmc_dev(host->mmc), "%s(): request opcode %u\n",
+			__func__, cmd->opcode);
+	}
+
+	/* We have to get a command completion interrupt with DMA too */
+	usdhi6_wait_for_resp(host);
+
+	host->wait = USDHI6_WAIT_FOR_CMD;
+	schedule_delayed_work(&host->timeout_work, host->timeout);
+
+	/* SEC bit is required to enable block counting by the core */
+	usdhi6_write(host, USDHI6_SD_STOP,
+		     data && data->blocks > 1 ? USDHI6_SD_STOP_SEC : 0);
+	usdhi6_write(host, USDHI6_SD_ARG, cmd->arg);
+
+	/* Kick command execution */
+	usdhi6_write(host, USDHI6_SD_CMD, opc);
+
+	return 0;
+}
+
+static void usdhi6_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct usdhi6_host *host = mmc_priv(mmc);
+	int ret;
+
+	cancel_delayed_work_sync(&host->timeout_work);
+
+	host->mrq = mrq;
+	host->sg = NULL;
+
+	usdhi6_timeout_set(host);
+	ret = usdhi6_rq_start(host);
+	if (ret < 0) {
+		mrq->cmd->error = ret;
+		usdhi6_request_done(host);
+	}
+}
+
+static int usdhi6_get_cd(struct mmc_host *mmc)
+{
+	struct usdhi6_host *host = mmc_priv(mmc);
+	/* Read is atomic, no need to lock */
+	u32 status = usdhi6_read(host, USDHI6_SD_INFO1) & USDHI6_SD_INFO1_CD;
+
+/*
+ *	level	status.CD	CD_ACTIVE_HIGH	card present
+ *	1	0		0		0
+ *	1	0		1		1
+ *	0	1		0		1
+ *	0	1		1		0
+ */
+	return !status ^ !(mmc->caps2 & MMC_CAP2_CD_ACTIVE_HIGH);
+}
+
+static int usdhi6_get_ro(struct mmc_host *mmc)
+{
+	struct usdhi6_host *host = mmc_priv(mmc);
+	/* No locking as above */
+	u32 status = usdhi6_read(host, USDHI6_SD_INFO1) & USDHI6_SD_INFO1_WP;
+
+/*
+ *	level	status.WP	RO_ACTIVE_HIGH	card read-only
+ *	1	0		0		0
+ *	1	0		1		1
+ *	0	1		0		1
+ *	0	1		1		0
+ */
+	return !status ^ !(mmc->caps2 & MMC_CAP2_RO_ACTIVE_HIGH);
+}
+
+static void usdhi6_enable_sdio_irq(struct mmc_host *mmc, int enable)
+{
+	struct usdhi6_host *host = mmc_priv(mmc);
+
+	dev_dbg(mmc_dev(mmc), "%s(): %sable\n", __func__, enable ? "en" : "dis");
+
+	if (enable) {
+		host->sdio_mask = USDHI6_SDIO_INFO1_IRQ & ~USDHI6_SDIO_INFO1_IOIRQ;
+		usdhi6_write(host, USDHI6_SDIO_INFO1_MASK, host->sdio_mask);
+		usdhi6_write(host, USDHI6_SDIO_MODE, 1);
+	} else {
+		usdhi6_write(host, USDHI6_SDIO_MODE, 0);
+		usdhi6_write(host, USDHI6_SDIO_INFO1_MASK, USDHI6_SDIO_INFO1_IRQ);
+		host->sdio_mask = USDHI6_SDIO_INFO1_IRQ;
+	}
+}
+
+static struct mmc_host_ops usdhi6_ops = {
+	.request	= usdhi6_request,
+	.set_ios	= usdhi6_set_ios,
+	.get_cd		= usdhi6_get_cd,
+	.get_ro		= usdhi6_get_ro,
+	.enable_sdio_irq = usdhi6_enable_sdio_irq,
+};
+
+/*			State machine handlers				*/
+
+static void usdhi6_resp_cmd12(struct usdhi6_host *host)
+{
+	struct mmc_command *cmd = host->mrq->stop;
+	cmd->resp[0] = usdhi6_read(host, USDHI6_SD_RSP10);
+}
+
+static void usdhi6_resp_read(struct usdhi6_host *host)
+{
+	struct mmc_command *cmd = host->mrq->cmd;
+	u32 *rsp = cmd->resp, tmp = 0;
+	int i;
+
+/*
+ * RSP10	39-8
+ * RSP32	71-40
+ * RSP54	103-72
+ * RSP76	127-104
+ * R2-type response:
+ * resp[0]	= r[127..96]
+ * resp[1]	= r[95..64]
+ * resp[2]	= r[63..32]
+ * resp[3]	= r[31..0]
+ * Other responses:
+ * resp[0]	= r[39..8]
+ */
+
+	if (mmc_resp_type(cmd) == MMC_RSP_NONE)
+		return;
+
+	if (!(host->irq_status & USDHI6_SD_INFO1_RSP_END)) {
+		dev_err(mmc_dev(host->mmc),
+			"CMD%d: response expected but is missing!\n", cmd->opcode);
+		return;
+	}
+
+	if (mmc_resp_type(cmd) & MMC_RSP_136)
+		for (i = 0; i < 4; i++) {
+			if (i)
+				rsp[3 - i] = tmp >> 24;
+			tmp = usdhi6_read(host, USDHI6_SD_RSP10 + i * 8);
+			rsp[3 - i] |= tmp << 8;
+		}
+	else if (cmd->opcode == MMC_READ_MULTIPLE_BLOCK ||
+		 cmd->opcode == MMC_WRITE_MULTIPLE_BLOCK)
+		/* Read RSP54 to avoid conflict with auto CMD12 */
+		rsp[0] = usdhi6_read(host, USDHI6_SD_RSP54);
+	else
+		rsp[0] = usdhi6_read(host, USDHI6_SD_RSP10);
+
+	dev_dbg(mmc_dev(host->mmc), "Response 0x%x\n", rsp[0]);
+}
+
+static int usdhi6_blk_read(struct usdhi6_host *host)
+{
+	struct mmc_data *data = host->mrq->data;
+	u32 *p;
+	int i, rest;
+
+	if (host->io_error) {
+		data->error = usdhi6_error_code(host);
+		goto error;
+	}
+
+	if (host->pg.page) {
+		p = host->blk_page + host->offset;
+	} else {
+		p = usdhi6_sg_map(host);
+		if (!p) {
+			data->error = -ENOMEM;
+			goto error;
+		}
+	}
+
+	for (i = 0; i < data->blksz / 4; i++, p++)
+		*p = usdhi6_read(host, USDHI6_SD_BUF0);
+
+	rest = data->blksz % 4;
+	for (i = 0; i < (rest + 1) / 2; i++) {
+		u16 d = usdhi6_read16(host, USDHI6_SD_BUF0);
+		((u8 *)p)[2 * i] = ((u8 *)&d)[0];
+		if (rest > 1 && !i)
+			((u8 *)p)[2 * i + 1] = ((u8 *)&d)[1];
+	}
+
+	return 0;
+
+error:
+	dev_dbg(mmc_dev(host->mmc), "%s(): %d\n", __func__, data->error);
+	host->wait = USDHI6_WAIT_FOR_REQUEST;
+	return data->error;
+}
+
+static int usdhi6_blk_write(struct usdhi6_host *host)
+{
+	struct mmc_data *data = host->mrq->data;
+	u32 *p;
+	int i, rest;
+
+	if (host->io_error) {
+		data->error = usdhi6_error_code(host);
+		goto error;
+	}
+
+	if (host->pg.page) {
+		p = host->blk_page + host->offset;
+	} else {
+		p = usdhi6_sg_map(host);
+		if (!p) {
+			data->error = -ENOMEM;
+			goto error;
+		}
+	}
+
+	for (i = 0; i < data->blksz / 4; i++, p++)
+		usdhi6_write(host, USDHI6_SD_BUF0, *p);
+
+	rest = data->blksz % 4;
+	for (i = 0; i < (rest + 1) / 2; i++) {
+		u16 d;
+		((u8 *)&d)[0] = ((u8 *)p)[2 * i];
+		if (rest > 1 && !i)
+			((u8 *)&d)[1] = ((u8 *)p)[2 * i + 1];
+		else
+			((u8 *)&d)[1] = 0;
+		usdhi6_write16(host, USDHI6_SD_BUF0, d);
+	}
+
+	return 0;
+
+error:
+	dev_dbg(mmc_dev(host->mmc), "%s(): %d\n", __func__, data->error);
+	host->wait = USDHI6_WAIT_FOR_REQUEST;
+	return data->error;
+}
+
+static int usdhi6_stop_cmd(struct usdhi6_host *host)
+{
+	struct mmc_request *mrq = host->mrq;
+
+	switch (mrq->cmd->opcode) {
+	case MMC_READ_MULTIPLE_BLOCK:
+	case MMC_WRITE_MULTIPLE_BLOCK:
+		if (mrq->stop->opcode == MMC_STOP_TRANSMISSION) {
+			host->wait = USDHI6_WAIT_FOR_STOP;
+			return 0;
+		}
+		/* Unsupported STOP command */
+	default:
+		dev_err(mmc_dev(host->mmc),
+			"unsupported stop CMD%d for CMD%d\n",
+			mrq->stop->opcode, mrq->cmd->opcode);
+		mrq->stop->error = -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static bool usdhi6_end_cmd(struct usdhi6_host *host)
+{
+	struct mmc_request *mrq = host->mrq;
+	struct mmc_command *cmd = mrq->cmd;
+
+	if (host->io_error) {
+		cmd->error = usdhi6_error_code(host);
+		return false;
+	}
+
+	usdhi6_resp_read(host);
+
+	if (!mrq->data)
+		return false;
+
+	if (host->dma_active) {
+		usdhi6_dma_kick(host);
+		if (!mrq->stop)
+			host->wait = USDHI6_WAIT_FOR_DMA;
+		else if (usdhi6_stop_cmd(host) < 0)
+			return false;
+	} else if (mrq->data->flags & MMC_DATA_READ) {
+		if (cmd->opcode == MMC_READ_MULTIPLE_BLOCK ||
+		    (cmd->opcode == SD_IO_RW_EXTENDED &&
+		     mrq->data->blocks > 1))
+			host->wait = USDHI6_WAIT_FOR_MREAD;
+		else
+			host->wait = USDHI6_WAIT_FOR_READ;
+	} else {
+		if (cmd->opcode == MMC_WRITE_MULTIPLE_BLOCK ||
+		    (cmd->opcode == SD_IO_RW_EXTENDED &&
+		     mrq->data->blocks > 1))
+			host->wait = USDHI6_WAIT_FOR_MWRITE;
+		else
+			host->wait = USDHI6_WAIT_FOR_WRITE;
+	}
+
+	return true;
+}
+
+static bool usdhi6_read_block(struct usdhi6_host *host)
+{
+	/* ACCESS_END IRQ is already unmasked */
+	int ret = usdhi6_blk_read(host);
+
+	/*
+	 * Have to force unmapping both pages: the single block could have been
+	 * cross-page, in which case for single-block IO host->page_idx == 0.
+	 * So, if we don't force, the second page won't be unmapped.
+	 */
+	usdhi6_sg_unmap(host, true);
+
+	if (ret < 0)
+		return false;
+
+	host->wait = USDHI6_WAIT_FOR_DATA_END;
+	return true;
+}
+
+static bool usdhi6_mread_block(struct usdhi6_host *host)
+{
+	int ret = usdhi6_blk_read(host);
+
+	if (ret < 0)
+		return false;
+
+	usdhi6_sg_advance(host);
+
+	return !host->mrq->data->error &&
+		(host->wait != USDHI6_WAIT_FOR_DATA_END || !host->mrq->stop);
+}
+
+static bool usdhi6_write_block(struct usdhi6_host *host)
+{
+	int ret = usdhi6_blk_write(host);
+
+	/* See comment in usdhi6_read_block() */
+	usdhi6_sg_unmap(host, true);
+
+	if (ret < 0)
+		return false;
+
+	host->wait = USDHI6_WAIT_FOR_DATA_END;
+	return true;
+}
+
+static bool usdhi6_mwrite_block(struct usdhi6_host *host)
+{
+	int ret = usdhi6_blk_write(host);
+
+	if (ret < 0)
+		return false;
+
+	usdhi6_sg_advance(host);
+
+	return !host->mrq->data->error &&
+		(host->wait != USDHI6_WAIT_FOR_DATA_END || !host->mrq->stop);
+}
+
+/*			Interrupt & timeout handlers			*/
+
+static irqreturn_t usdhi6_sd_bh(int irq, void *dev_id)
+{
+	struct usdhi6_host *host = dev_id;
+	struct mmc_request *mrq;
+	struct mmc_command *cmd;
+	struct mmc_data *data;
+	bool io_wait = false;
+
+	cancel_delayed_work_sync(&host->timeout_work);
+
+	mrq = host->mrq;
+	if (!mrq)
+		return IRQ_HANDLED;
+
+	cmd = mrq->cmd;
+	data = mrq->data;
+
+	switch (host->wait) {
+	case USDHI6_WAIT_FOR_REQUEST:
+		/* We're too late, the timeout has already kicked in */
+		return IRQ_HANDLED;
+	case USDHI6_WAIT_FOR_CMD:
+		/* Wait for data? */
+		io_wait = usdhi6_end_cmd(host);
+		break;
+	case USDHI6_WAIT_FOR_MREAD:
+		/* Wait for more data? */
+		io_wait = usdhi6_mread_block(host);
+		break;
+	case USDHI6_WAIT_FOR_READ:
+		/* Wait for data end? */
+		io_wait = usdhi6_read_block(host);
+		break;
+	case USDHI6_WAIT_FOR_MWRITE:
+		/* Wait data to write? */
+		io_wait = usdhi6_mwrite_block(host);
+		break;
+	case USDHI6_WAIT_FOR_WRITE:
+		/* Wait for data end? */
+		io_wait = usdhi6_write_block(host);
+		break;
+	case USDHI6_WAIT_FOR_DMA:
+		usdhi6_dma_check_error(host);
+		break;
+	case USDHI6_WAIT_FOR_STOP:
+		usdhi6_write(host, USDHI6_SD_STOP, 0);
+		if (host->io_error) {
+			int ret = usdhi6_error_code(host);
+			if (mrq->stop)
+				mrq->stop->error = ret;
+			else
+				mrq->data->error = ret;
+			dev_warn(mmc_dev(host->mmc), "%s(): %d\n", __func__, ret);
+			break;
+		}
+		usdhi6_resp_cmd12(host);
+		mrq->stop->error = 0;
+		break;
+	case USDHI6_WAIT_FOR_DATA_END:
+		if (host->io_error) {
+			mrq->data->error = usdhi6_error_code(host);
+			dev_warn(mmc_dev(host->mmc), "%s(): %d\n", __func__,
+				 mrq->data->error);
+		}
+		break;
+	default:
+		cmd->error = -EFAULT;
+		dev_err(mmc_dev(host->mmc), "Invalid state %u\n", host->wait);
+		usdhi6_request_done(host);
+		return IRQ_HANDLED;
+	}
+
+	if (io_wait) {
+		schedule_delayed_work(&host->timeout_work, host->timeout);
+		/* Wait for more data or ACCESS_END */
+		if (!host->dma_active)
+			usdhi6_wait_for_brwe(host, mrq->data->flags & MMC_DATA_READ);
+		return IRQ_HANDLED;
+	}
+
+	if (!cmd->error) {
+		if (data) {
+			if (!data->error) {
+				if (host->wait != USDHI6_WAIT_FOR_STOP &&
+				    host->mrq->stop &&
+				    !host->mrq->stop->error &&
+				    !usdhi6_stop_cmd(host)) {
+					/* Sending STOP */
+					usdhi6_wait_for_resp(host);
+
+					schedule_delayed_work(&host->timeout_work,
+							      host->timeout);
+
+					return IRQ_HANDLED;
+				}
+
+				data->bytes_xfered = data->blocks * data->blksz;
+			} else {
+				/* Data error: might need to unmap the last page */
+				dev_warn(mmc_dev(host->mmc), "%s(): data error %d\n",
+					 __func__, data->error);
+				usdhi6_sg_unmap(host, true);
+			}
+		} else if (cmd->opcode == MMC_APP_CMD) {
+			host->app_cmd = true;
+		}
+	}
+
+	usdhi6_request_done(host);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t usdhi6_sd(int irq, void *dev_id)
+{
+	struct usdhi6_host *host = dev_id;
+	u16 status, status2, error;
+
+	status = usdhi6_read(host, USDHI6_SD_INFO1) & ~host->status_mask &
+		~USDHI6_SD_INFO1_CARD;
+	status2 = usdhi6_read(host, USDHI6_SD_INFO2) & ~host->status2_mask;
+
+	usdhi6_only_cd(host);
+
+	dev_dbg(mmc_dev(host->mmc),
+		"IRQ status = 0x%08x, status2 = 0x%08x\n", status, status2);
+
+	if (!status && !status2)
+		return IRQ_NONE;
+
+	error = status2 & USDHI6_SD_INFO2_ERR;
+
+	/* Ack / clear interrupts */
+	if (USDHI6_SD_INFO1_IRQ & status)
+		usdhi6_write(host, USDHI6_SD_INFO1,
+			     0xffff & ~(USDHI6_SD_INFO1_IRQ & status));
+
+	if (USDHI6_SD_INFO2_IRQ & status2) {
+		if (error)
+			/* In error cases BWE and BRE aren't cleared automatically */
+			status2 |= USDHI6_SD_INFO2_BWE | USDHI6_SD_INFO2_BRE;
+
+		usdhi6_write(host, USDHI6_SD_INFO2,
+			     0xffff & ~(USDHI6_SD_INFO2_IRQ & status2));
+	}
+
+	host->io_error = error;
+	host->irq_status = status;
+
+	if (error) {
+		/* Don't pollute the log with unsupported command timeouts */
+		if (host->wait != USDHI6_WAIT_FOR_CMD ||
+		    error != USDHI6_SD_INFO2_RSP_TOUT)
+			dev_warn(mmc_dev(host->mmc),
+				 "%s(): INFO2 error bits 0x%08x\n",
+				 __func__, error);
+		else
+			dev_dbg(mmc_dev(host->mmc),
+				"%s(): INFO2 error bits 0x%08x\n",
+				__func__, error);
+	}
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t usdhi6_sdio(int irq, void *dev_id)
+{
+	struct usdhi6_host *host = dev_id;
+	u32 status = usdhi6_read(host, USDHI6_SDIO_INFO1) & ~host->sdio_mask;
+
+	dev_dbg(mmc_dev(host->mmc), "%s(): status 0x%x\n", __func__, status);
+
+	if (!status)
+		return IRQ_NONE;
+
+	usdhi6_write(host, USDHI6_SDIO_INFO1, ~status);
+
+	mmc_signal_sdio_irq(host->mmc);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t usdhi6_cd(int irq, void *dev_id)
+{
+	struct usdhi6_host *host = dev_id;
+	struct mmc_host *mmc = host->mmc;
+	u16 status;
+
+	/* We're only interested in hotplug events here */
+	status = usdhi6_read(host, USDHI6_SD_INFO1) & ~host->status_mask &
+		USDHI6_SD_INFO1_CARD;
+
+	if (!status)
+		return IRQ_NONE;
+
+	/* Ack */
+	usdhi6_write(host, USDHI6_SD_INFO1, !status);
+
+	if (!work_pending(&mmc->detect.work) &&
+	    (((status & USDHI6_SD_INFO1_CARD_INSERT) &&
+	      !mmc->card) ||
+	     ((status & USDHI6_SD_INFO1_CARD_EJECT) &&
+	      mmc->card)))
+		mmc_detect_change(mmc, msecs_to_jiffies(100));
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * Actually this should not be needed, if the built-in timeout works reliably in
+ * the both PIO cases and DMA never fails. But if DMA does fail, a timeout
+ * handler might be the only way to catch the error.
+ */
+static void usdhi6_timeout_work(struct work_struct *work)
+{
+	struct delayed_work *d = container_of(work, struct delayed_work, work);
+	struct usdhi6_host *host = container_of(d, struct usdhi6_host, timeout_work);
+	struct mmc_request *mrq = host->mrq;
+	struct mmc_data *data = mrq ? mrq->data : NULL;
+
+	dev_warn(mmc_dev(host->mmc),
+		 "%s timeout wait %u CMD%d: IRQ 0x%08x:0x%08x, last IRQ 0x%08x\n",
+		 host->dma_active ? "DMA" : "PIO",
+		 host->wait, mrq ? mrq->cmd->opcode : -1,
+		 usdhi6_read(host, USDHI6_SD_INFO1),
+		 usdhi6_read(host, USDHI6_SD_INFO2), host->irq_status);
+
+	if (host->dma_active) {
+		usdhi6_dma_kill(host);
+		usdhi6_dma_stop_unmap(host);
+	}
+
+	switch (host->wait) {
+	default:
+		dev_err(mmc_dev(host->mmc), "Invalid state %u\n", host->wait);
+		/* mrq can be NULL in this actually impossible case */
+	case USDHI6_WAIT_FOR_CMD:
+		usdhi6_error_code(host);
+		if (mrq)
+			mrq->cmd->error = -ETIMEDOUT;
+		break;
+	case USDHI6_WAIT_FOR_STOP:
+		usdhi6_error_code(host);
+		mrq->stop->error = -ETIMEDOUT;
+		break;
+	case USDHI6_WAIT_FOR_DMA:
+	case USDHI6_WAIT_FOR_MREAD:
+	case USDHI6_WAIT_FOR_MWRITE:
+	case USDHI6_WAIT_FOR_READ:
+	case USDHI6_WAIT_FOR_WRITE:
+		dev_dbg(mmc_dev(host->mmc),
+			"%c: page #%u @ +0x%zx %ux%u in SG%u. Current SG %u bytes @ %u\n",
+			data->flags & MMC_DATA_READ ? 'R' : 'W', host->page_idx,
+			host->offset, data->blocks, data->blksz, data->sg_len,
+			sg_dma_len(host->sg), host->sg->offset);
+		usdhi6_sg_unmap(host, true);
+		/*
+		 * If USDHI6_WAIT_FOR_DATA_END times out, we have already unmapped
+		 * the page
+		 */
+	case USDHI6_WAIT_FOR_DATA_END:
+		usdhi6_error_code(host);
+		data->error = -ETIMEDOUT;
+	}
+
+	if (mrq)
+		usdhi6_request_done(host);
+}
+
+/*			 Probe / release				*/
+
+static const struct of_device_id usdhi6_of_match[] = {
+	{.compatible = "renesas,usdhi6rol0"},
+	{}
+};
+MODULE_DEVICE_TABLE(of, usdhi6_of_match);
+
+static int usdhi6_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mmc_host *mmc;
+	struct usdhi6_host *host;
+	struct resource *res;
+	int irq_cd, irq_sd, irq_sdio;
+	u32 version;
+	int ret;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	irq_cd = platform_get_irq_byname(pdev, "card detect");
+	irq_sd = platform_get_irq_byname(pdev, "data");
+	irq_sdio = platform_get_irq_byname(pdev, "SDIO");
+	if (irq_sd < 0 || irq_sdio < 0)
+		return -ENODEV;
+
+	mmc = mmc_alloc_host(sizeof(struct usdhi6_host), dev);
+	if (!mmc)
+		return -ENOMEM;
+
+	ret = mmc_of_parse(mmc);
+	if (ret < 0)
+		goto e_free_mmc;
+
+	mmc_regulator_get_supply(mmc);
+
+	host		= mmc_priv(mmc);
+	host->mmc	= mmc;
+	host->wait	= USDHI6_WAIT_FOR_REQUEST;
+	host->timeout	= msecs_to_jiffies(4000);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	host->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(host->base)) {
+		ret = PTR_ERR(host->base);
+		goto e_free_mmc;
+	}
+
+	host->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(host->clk))
+		goto e_free_mmc;
+
+	host->imclk = clk_get_rate(host->clk);
+
+	ret = clk_prepare_enable(host->clk);
+	if (ret < 0)
+		goto e_free_mmc;
+
+	version = usdhi6_read(host, USDHI6_VERSION);
+	if ((version & 0xfff) != 0xa0d) {
+		dev_err(dev, "Version not recognized %x\n", version);
+		goto e_clk_off;
+	}
+
+	dev_info(dev, "A USDHI6ROL0 SD host detected with %d ports\n",
+		 usdhi6_read(host, USDHI6_SD_PORT_SEL) >> USDHI6_SD_PORT_SEL_PORTS_SHIFT);
+
+	usdhi6_mask_all(host);
+
+	if (irq_cd >= 0) {
+		ret = devm_request_irq(dev, irq_cd, usdhi6_cd, 0,
+				       dev_name(dev), host);
+		if (ret < 0)
+			goto e_clk_off;
+	} else {
+		mmc->caps |= MMC_CAP_NEEDS_POLL;
+	}
+
+	ret = devm_request_threaded_irq(dev, irq_sd, usdhi6_sd, usdhi6_sd_bh, 0,
+			       dev_name(dev), host);
+	if (ret < 0)
+		goto e_clk_off;
+
+	ret = devm_request_irq(dev, irq_sdio, usdhi6_sdio, 0,
+			       dev_name(dev), host);
+	if (ret < 0)
+		goto e_clk_off;
+
+	INIT_DELAYED_WORK(&host->timeout_work, usdhi6_timeout_work);
+
+	usdhi6_dma_request(host, res->start);
+
+	mmc->ops = &usdhi6_ops;
+	mmc->caps |= MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED |
+		MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_DDR50 | MMC_CAP_SDIO_IRQ;
+	/* Set .max_segs to some random number. Feel free to adjust. */
+	mmc->max_segs = 32;
+	mmc->max_blk_size = 512;
+	mmc->max_req_size = PAGE_CACHE_SIZE * mmc->max_segs;
+	mmc->max_blk_count = mmc->max_req_size / mmc->max_blk_size;
+	/*
+	 * Setting .max_seg_size to 1 page would simplify our page-mapping code,
+	 * But OTOH, having large segments makes DMA more efficient. We could
+	 * check, whether we managed to get DMA and fall back to 1 page
+	 * segments, but if we do manage to obtain DMA and then it fails at
+	 * run-time and we fall back to PIO, we will continue getting large
+	 * segments. So, we wouldn't be able to get rid of the code anyway.
+	 */
+	mmc->max_seg_size = mmc->max_req_size;
+	if (!mmc->f_max)
+		mmc->f_max = host->imclk;
+	mmc->f_min = host->imclk / 512;
+
+	platform_set_drvdata(pdev, host);
+
+	ret = mmc_add_host(mmc);
+	if (ret < 0)
+		goto e_clk_off;
+
+	return 0;
+
+e_clk_off:
+	clk_disable_unprepare(host->clk);
+e_free_mmc:
+	mmc_free_host(mmc);
+
+	return ret;
+}
+
+static int usdhi6_remove(struct platform_device *pdev)
+{
+	struct usdhi6_host *host = platform_get_drvdata(pdev);
+
+	mmc_remove_host(host->mmc);
+
+	usdhi6_mask_all(host);
+	cancel_delayed_work_sync(&host->timeout_work);
+	usdhi6_dma_release(host);
+	clk_disable_unprepare(host->clk);
+	mmc_free_host(host->mmc);
+
+	return 0;
+}
+
+static struct platform_driver usdhi6_driver = {
+	.probe		= usdhi6_probe,
+	.remove		= usdhi6_remove,
+	.driver		= {
+		.name	= "usdhi6rol0",
+		.owner	= THIS_MODULE,
+		.of_match_table = usdhi6_of_match,
+	},
+};
+
+module_platform_driver(usdhi6_driver);
+
+MODULE_DESCRIPTION("Renesas usdhi6rol0 SD/SDIO host driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:usdhi6rol0");
+MODULE_AUTHOR("Guennadi Liakhovetski <g.liakhovetski@gmx.de>");
diff --git a/drivers/mmc/host/wmt-sdmmc.c b/drivers/mmc/host/wmt-sdmmc.c
index 498d1f79908..282891a8e45 100644
--- a/drivers/mmc/host/wmt-sdmmc.c
+++ b/drivers/mmc/host/wmt-sdmmc.c
@@ -840,7 +840,7 @@ static int wmt_mci_probe(struct platform_device *pdev)
 	priv->dma_desc_buffer = dma_alloc_coherent(&pdev->dev,
 						   mmc->max_blk_count * 16,
 						   &priv->dma_desc_device_addr,
-						   208);
+						   GFP_KERNEL);
 	if (!priv->dma_desc_buffer) {
 		dev_err(&pdev->dev, "DMA alloc fail\n");
 		ret = -EPERM;
diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index 5d49a212961..94b821042d9 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -321,6 +321,8 @@ source "drivers/mtd/onenand/Kconfig"
 
 source "drivers/mtd/lpddr/Kconfig"
 
+source "drivers/mtd/spi-nor/Kconfig"
+
 source "drivers/mtd/ubi/Kconfig"
 
 endif # MTD
diff --git a/drivers/mtd/Makefile b/drivers/mtd/Makefile
index 4cfb31e6c96..99bb9a1f6e1 100644
--- a/drivers/mtd/Makefile
+++ b/drivers/mtd/Makefile
@@ -32,4 +32,5 @@ inftl-objs		:= inftlcore.o inftlmount.o
 
 obj-y		+= chips/ lpddr/ maps/ devices/ nand/ onenand/ tests/
 
+obj-$(CONFIG_MTD_SPI_NOR)	+= spi-nor/
 obj-$(CONFIG_MTD_UBI)		+= ubi/
diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig
index e4696b37f3d..9f02c28c020 100644
--- a/drivers/mtd/chips/Kconfig
+++ b/drivers/mtd/chips/Kconfig
@@ -169,33 +169,33 @@ config MTD_OTP
 	  in the programming of OTP bits will waste them.
 
 config MTD_CFI_INTELEXT
-	tristate "Support for Intel/Sharp flash chips"
+	tristate "Support for CFI command set 0001 (Intel/Sharp chips)"
 	depends on MTD_GEN_PROBE
 	select MTD_CFI_UTIL
 	help
 	  The Common Flash Interface defines a number of different command
 	  sets which a CFI-compliant chip may claim to implement. This code
-	  provides support for one of those command sets, used on Intel
-	  StrataFlash and other parts.
+	  provides support for command set 0001, used on Intel StrataFlash
+	  and other parts.
 
 config MTD_CFI_AMDSTD
-	tristate "Support for AMD/Fujitsu/Spansion flash chips"
+	tristate "Support for CFI command set 0002 (AMD/Fujitsu/Spansion chips)"
 	depends on MTD_GEN_PROBE
 	select MTD_CFI_UTIL
 	help
 	  The Common Flash Interface defines a number of different command
 	  sets which a CFI-compliant chip may claim to implement. This code
-	  provides support for one of those command sets, used on chips
-	  including the AMD Am29LV320.
+	  provides support for command set 0002, used on chips including
+	  the AMD Am29LV320.
 
 config MTD_CFI_STAA
-	tristate "Support for ST (Advanced Architecture) flash chips"
+	tristate "Support for CFI command set 0020 (ST (Advanced Architecture) chips)"
 	depends on MTD_GEN_PROBE
 	select MTD_CFI_UTIL
 	help
 	  The Common Flash Interface defines a number of different command
 	  sets which a CFI-compliant chip may claim to implement. This code
-	  provides support for one of those command sets.
+	  provides support for command set 0020.
 
 config MTD_CFI_UTIL
 	tristate
diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index e4ec355704a..a7543ba3e19 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -52,6 +52,11 @@
 /* Atmel chips */
 #define AT49BV640D	0x02de
 #define AT49BV640DT	0x02db
+/* Sharp chips */
+#define LH28F640BFHE_PTTL90	0x00b0
+#define LH28F640BFHE_PBTL90	0x00b1
+#define LH28F640BFHE_PTTL70A	0x00b2
+#define LH28F640BFHE_PBTL70A	0x00b3
 
 static int cfi_intelext_read (struct mtd_info *, loff_t, size_t, size_t *, u_char *);
 static int cfi_intelext_write_words(struct mtd_info *, loff_t, size_t, size_t *, const u_char *);
@@ -258,6 +263,36 @@ static void fixup_st_m28w320cb(struct mtd_info *mtd)
 		(cfi->cfiq->EraseRegionInfo[1] & 0xffff0000) | 0x3e;
 };
 
+static int is_LH28F640BF(struct cfi_private *cfi)
+{
+	/* Sharp LH28F640BF Family */
+	if (cfi->mfr == CFI_MFR_SHARP && (
+	    cfi->id == LH28F640BFHE_PTTL90 || cfi->id == LH28F640BFHE_PBTL90 ||
+	    cfi->id == LH28F640BFHE_PTTL70A || cfi->id == LH28F640BFHE_PBTL70A))
+		return 1;
+	return 0;
+}
+
+static void fixup_LH28F640BF(struct mtd_info *mtd)
+{
+	struct map_info *map = mtd->priv;
+	struct cfi_private *cfi = map->fldrv_priv;
+	struct cfi_pri_intelext *extp = cfi->cmdset_priv;
+
+	/* Reset the Partition Configuration Register on LH28F640BF
+	 * to a single partition (PCR = 0x000): PCR is embedded into A0-A15. */
+	if (is_LH28F640BF(cfi)) {
+		printk(KERN_INFO "Reset Partition Config. Register: 1 Partition of 4 planes\n");
+		map_write(map, CMD(0x60), 0);
+		map_write(map, CMD(0x04), 0);
+
+		/* We have set one single partition thus
+		 * Simultaneous Operations are not allowed */
+		printk(KERN_INFO "cfi_cmdset_0001: Simultaneous Operations disabled\n");
+		extp->FeatureSupport &= ~512;
+	}
+}
+
 static void fixup_use_point(struct mtd_info *mtd)
 {
 	struct map_info *map = mtd->priv;
@@ -309,6 +344,8 @@ static struct cfi_fixup cfi_fixup_table[] = {
 	{ CFI_MFR_ST, 0x00ba, /* M28W320CT */ fixup_st_m28w320ct },
 	{ CFI_MFR_ST, 0x00bb, /* M28W320CB */ fixup_st_m28w320cb },
 	{ CFI_MFR_INTEL, CFI_ID_ANY, fixup_unlock_powerup_lock },
+	{ CFI_MFR_SHARP, CFI_ID_ANY, fixup_unlock_powerup_lock },
+	{ CFI_MFR_SHARP, CFI_ID_ANY, fixup_LH28F640BF },
 	{ 0, 0, NULL }
 };
 
@@ -1649,6 +1686,12 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 	initial_adr = adr;
 	cmd_adr = adr & ~(wbufsize-1);
 
+	/* Sharp LH28F640BF chips need the first address for the
+	 * Page Buffer Program command. See Table 5 of
+	 * LH28F320BF, LH28F640BF, LH28F128BF Series (Appendix FUM00701) */
+	if (is_LH28F640BF(cfi))
+		cmd_adr = adr;
+
 	/* Let's determine this according to the interleave only once */
 	write_cmd = (cfi->cfiq->P_ID != P_ID_INTEL_PERFORMANCE) ? CMD(0xe8) : CMD(0xe9);
 
diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c
index 6293855fb5e..423666b51ef 100644
--- a/drivers/mtd/chips/cfi_cmdset_0020.c
+++ b/drivers/mtd/chips/cfi_cmdset_0020.c
@@ -961,7 +961,7 @@ static int cfi_staa_erase_varsize(struct mtd_info *mtd,
 			chipnum++;
 
 			if (chipnum >= cfi->numchips)
-			break;
+				break;
 		}
 	}
 
@@ -1170,7 +1170,7 @@ static int cfi_staa_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 			chipnum++;
 
 			if (chipnum >= cfi->numchips)
-			break;
+				break;
 		}
 	}
 	return 0;
diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c
index 08049f6eea6..09c79bd0b4f 100644
--- a/drivers/mtd/chips/cfi_util.c
+++ b/drivers/mtd/chips/cfi_util.c
@@ -239,7 +239,7 @@ int cfi_varsize_frob(struct mtd_info *mtd, varsize_frob_t frob,
 			chipnum++;
 
 			if (chipnum >= cfi->numchips)
-			break;
+				break;
 		}
 	}
 
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 1210bc2923b..c49d0b127fe 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -80,7 +80,7 @@ config MTD_DATAFLASH_OTP
 
 config MTD_M25P80
 	tristate "Support most SPI Flash chips (AT26DF, M25P, W25X, ...)"
-	depends on SPI_MASTER
+	depends on SPI_MASTER && MTD_SPI_NOR
 	help
 	  This enables access to most modern SPI flash chips, used for
 	  program and data storage.   Series supported include Atmel AT26DF,
@@ -212,7 +212,7 @@ config MTD_DOCG3
 
 config MTD_ST_SPI_FSM
 	tristate "ST Microelectronics SPI FSM Serial Flash Controller"
-	depends on ARM || SH
+	depends on ARCH_STI
 	help
 	  This provides an MTD device driver for the ST Microelectronics
 	  SPI Fast Sequence Mode (FSM) Serial Flash Controller and support
diff --git a/drivers/mtd/devices/docg3.c b/drivers/mtd/devices/docg3.c
index dd5e1018d37..91a169c44b3 100644
--- a/drivers/mtd/devices/docg3.c
+++ b/drivers/mtd/devices/docg3.c
@@ -1608,8 +1608,8 @@ static ssize_t dps1_insert_key(struct device *dev,
 #define FLOOR_SYSFS(id) { \
 	__ATTR(f##id##_dps0_is_keylocked, S_IRUGO, dps0_is_key_locked, NULL), \
 	__ATTR(f##id##_dps1_is_keylocked, S_IRUGO, dps1_is_key_locked, NULL), \
-	__ATTR(f##id##_dps0_protection_key, S_IWUGO, NULL, dps0_insert_key), \
-	__ATTR(f##id##_dps1_protection_key, S_IWUGO, NULL, dps1_insert_key), \
+	__ATTR(f##id##_dps0_protection_key, S_IWUSR|S_IWGRP, NULL, dps0_insert_key), \
+	__ATTR(f##id##_dps1_protection_key, S_IWUSR|S_IWGRP, NULL, dps1_insert_key), \
 }
 
 static struct device_attribute doc_sys_attrs[DOC_MAX_NBFLOORS][4] = {
diff --git a/drivers/mtd/devices/elm.c b/drivers/mtd/devices/elm.c
index 1fd4a0f7796..b4f61c7fc16 100644
--- a/drivers/mtd/devices/elm.c
+++ b/drivers/mtd/devices/elm.c
@@ -213,6 +213,28 @@ static void elm_load_syndrome(struct elm_info *info,
 				val = cpu_to_be32(*(u32 *) &ecc[0]) >> 12;
 				elm_write_reg(info, offset, val);
 				break;
+			case BCH16_ECC:
+				val = cpu_to_be32(*(u32 *) &ecc[22]);
+				elm_write_reg(info, offset, val);
+				offset += 4;
+				val = cpu_to_be32(*(u32 *) &ecc[18]);
+				elm_write_reg(info, offset, val);
+				offset += 4;
+				val = cpu_to_be32(*(u32 *) &ecc[14]);
+				elm_write_reg(info, offset, val);
+				offset += 4;
+				val = cpu_to_be32(*(u32 *) &ecc[10]);
+				elm_write_reg(info, offset, val);
+				offset += 4;
+				val = cpu_to_be32(*(u32 *) &ecc[6]);
+				elm_write_reg(info, offset, val);
+				offset += 4;
+				val = cpu_to_be32(*(u32 *) &ecc[2]);
+				elm_write_reg(info, offset, val);
+				offset += 4;
+				val = cpu_to_be32(*(u32 *) &ecc[0]) >> 16;
+				elm_write_reg(info, offset, val);
+				break;
 			default:
 				pr_err("invalid config bch_type\n");
 			}
@@ -418,6 +440,7 @@ static int elm_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
 /**
  * elm_context_save
  * saves ELM configurations to preserve them across Hardware powered-down
@@ -435,6 +458,13 @@ static int elm_context_save(struct elm_info *info)
 	for (i = 0; i < ERROR_VECTOR_MAX; i++) {
 		offset = i * SYNDROME_FRAGMENT_REG_SIZE;
 		switch (bch_type) {
+		case BCH16_ECC:
+			regs->elm_syndrome_fragment_6[i] = elm_read_reg(info,
+					ELM_SYNDROME_FRAGMENT_6 + offset);
+			regs->elm_syndrome_fragment_5[i] = elm_read_reg(info,
+					ELM_SYNDROME_FRAGMENT_5 + offset);
+			regs->elm_syndrome_fragment_4[i] = elm_read_reg(info,
+					ELM_SYNDROME_FRAGMENT_4 + offset);
 		case BCH8_ECC:
 			regs->elm_syndrome_fragment_3[i] = elm_read_reg(info,
 					ELM_SYNDROME_FRAGMENT_3 + offset);
@@ -445,6 +475,7 @@ static int elm_context_save(struct elm_info *info)
 					ELM_SYNDROME_FRAGMENT_1 + offset);
 			regs->elm_syndrome_fragment_0[i] = elm_read_reg(info,
 					ELM_SYNDROME_FRAGMENT_0 + offset);
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -473,6 +504,13 @@ static int elm_context_restore(struct elm_info *info)
 	for (i = 0; i < ERROR_VECTOR_MAX; i++) {
 		offset = i * SYNDROME_FRAGMENT_REG_SIZE;
 		switch (bch_type) {
+		case BCH16_ECC:
+			elm_write_reg(info, ELM_SYNDROME_FRAGMENT_6 + offset,
+					regs->elm_syndrome_fragment_6[i]);
+			elm_write_reg(info, ELM_SYNDROME_FRAGMENT_5 + offset,
+					regs->elm_syndrome_fragment_5[i]);
+			elm_write_reg(info, ELM_SYNDROME_FRAGMENT_4 + offset,
+					regs->elm_syndrome_fragment_4[i]);
 		case BCH8_ECC:
 			elm_write_reg(info, ELM_SYNDROME_FRAGMENT_3 + offset,
 					regs->elm_syndrome_fragment_3[i]);
@@ -483,6 +521,7 @@ static int elm_context_restore(struct elm_info *info)
 					regs->elm_syndrome_fragment_1[i]);
 			elm_write_reg(info, ELM_SYNDROME_FRAGMENT_0 + offset,
 					regs->elm_syndrome_fragment_0[i]);
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -509,6 +548,7 @@ static int elm_resume(struct device *dev)
 	elm_context_restore(info);
 	return 0;
 }
+#endif
 
 static SIMPLE_DEV_PM_OPS(elm_pm_ops, elm_suspend, elm_resume);
 
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 524dab3ac93..ed7e0a1bed3 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -19,485 +19,98 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/device.h>
-#include <linux/interrupt.h>
-#include <linux/mutex.h>
-#include <linux/math64.h>
-#include <linux/slab.h>
-#include <linux/sched.h>
-#include <linux/mod_devicetable.h>
 
-#include <linux/mtd/cfi.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
-#include <linux/of_platform.h>
 
 #include <linux/spi/spi.h>
 #include <linux/spi/flash.h>
+#include <linux/mtd/spi-nor.h>
 
-/* Flash opcodes. */
-#define	OPCODE_WREN		0x06	/* Write enable */
-#define	OPCODE_RDSR		0x05	/* Read status register */
-#define	OPCODE_WRSR		0x01	/* Write status register 1 byte */
-#define	OPCODE_NORM_READ	0x03	/* Read data bytes (low frequency) */
-#define	OPCODE_FAST_READ	0x0b	/* Read data bytes (high frequency) */
-#define	OPCODE_DUAL_READ        0x3b    /* Read data bytes (Dual SPI) */
-#define	OPCODE_QUAD_READ        0x6b    /* Read data bytes (Quad SPI) */
-#define	OPCODE_PP		0x02	/* Page program (up to 256 bytes) */
-#define	OPCODE_BE_4K		0x20	/* Erase 4KiB block */
-#define	OPCODE_BE_4K_PMC	0xd7	/* Erase 4KiB block on PMC chips */
-#define	OPCODE_BE_32K		0x52	/* Erase 32KiB block */
-#define	OPCODE_CHIP_ERASE	0xc7	/* Erase whole flash chip */
-#define	OPCODE_SE		0xd8	/* Sector erase (usually 64KiB) */
-#define	OPCODE_RDID		0x9f	/* Read JEDEC ID */
-#define	OPCODE_RDCR             0x35    /* Read configuration register */
-
-/* 4-byte address opcodes - used on Spansion and some Macronix flashes. */
-#define	OPCODE_NORM_READ_4B	0x13	/* Read data bytes (low frequency) */
-#define	OPCODE_FAST_READ_4B	0x0c	/* Read data bytes (high frequency) */
-#define	OPCODE_DUAL_READ_4B	0x3c    /* Read data bytes (Dual SPI) */
-#define	OPCODE_QUAD_READ_4B	0x6c    /* Read data bytes (Quad SPI) */
-#define	OPCODE_PP_4B		0x12	/* Page program (up to 256 bytes) */
-#define	OPCODE_SE_4B		0xdc	/* Sector erase (usually 64KiB) */
-
-/* Used for SST flashes only. */
-#define	OPCODE_BP		0x02	/* Byte program */
-#define	OPCODE_WRDI		0x04	/* Write disable */
-#define	OPCODE_AAI_WP		0xad	/* Auto address increment word program */
-
-/* Used for Macronix and Winbond flashes. */
-#define	OPCODE_EN4B		0xb7	/* Enter 4-byte mode */
-#define	OPCODE_EX4B		0xe9	/* Exit 4-byte mode */
-
-/* Used for Spansion flashes only. */
-#define	OPCODE_BRWR		0x17	/* Bank register write */
-
-/* Status Register bits. */
-#define	SR_WIP			1	/* Write in progress */
-#define	SR_WEL			2	/* Write enable latch */
-/* meaning of other SR_* bits may differ between vendors */
-#define	SR_BP0			4	/* Block protect 0 */
-#define	SR_BP1			8	/* Block protect 1 */
-#define	SR_BP2			0x10	/* Block protect 2 */
-#define	SR_SRWD			0x80	/* SR write protect */
-
-#define SR_QUAD_EN_MX           0x40    /* Macronix Quad I/O */
-
-/* Configuration Register bits. */
-#define CR_QUAD_EN_SPAN		0x2     /* Spansion Quad I/O */
-
-/* Define max times to check status register before we give up. */
-#define	MAX_READY_WAIT_JIFFIES	(40 * HZ)	/* M25P16 specs 40s max chip erase */
 #define	MAX_CMD_SIZE		6
-
-#define JEDEC_MFR(_jedec_id)	((_jedec_id) >> 16)
-
-/****************************************************************************/
-
-enum read_type {
-	M25P80_NORMAL = 0,
-	M25P80_FAST,
-	M25P80_DUAL,
-	M25P80_QUAD,
-};
-
 struct m25p {
 	struct spi_device	*spi;
-	struct mutex		lock;
+	struct spi_nor		spi_nor;
 	struct mtd_info		mtd;
-	u16			page_size;
-	u16			addr_width;
-	u8			erase_opcode;
-	u8			read_opcode;
-	u8			program_opcode;
-	u8			*command;
-	enum read_type		flash_read;
+	u8			command[MAX_CMD_SIZE];
 };
 
-static inline struct m25p *mtd_to_m25p(struct mtd_info *mtd)
-{
-	return container_of(mtd, struct m25p, mtd);
-}
-
-/****************************************************************************/
-
-/*
- * Internal helper functions
- */
-
-/*
- * Read the status register, returning its value in the location
- * Return the status register value.
- * Returns negative if error occurred.
- */
-static int read_sr(struct m25p *flash)
-{
-	ssize_t retval;
-	u8 code = OPCODE_RDSR;
-	u8 val;
-
-	retval = spi_write_then_read(flash->spi, &code, 1, &val, 1);
-
-	if (retval < 0) {
-		dev_err(&flash->spi->dev, "error %d reading SR\n",
-				(int) retval);
-		return retval;
-	}
-
-	return val;
-}
-
-/*
- * Read configuration register, returning its value in the
- * location. Return the configuration register value.
- * Returns negative if error occured.
- */
-static int read_cr(struct m25p *flash)
-{
-	u8 code = OPCODE_RDCR;
-	int ret;
-	u8 val;
-
-	ret = spi_write_then_read(flash->spi, &code, 1, &val, 1);
-	if (ret < 0) {
-		dev_err(&flash->spi->dev, "error %d reading CR\n", ret);
-		return ret;
-	}
-
-	return val;
-}
-
-/*
- * Write status register 1 byte
- * Returns negative if error occurred.
- */
-static int write_sr(struct m25p *flash, u8 val)
-{
-	flash->command[0] = OPCODE_WRSR;
-	flash->command[1] = val;
-
-	return spi_write(flash->spi, flash->command, 2);
-}
-
-/*
- * Set write enable latch with Write Enable command.
- * Returns negative if error occurred.
- */
-static inline int write_enable(struct m25p *flash)
-{
-	u8	code = OPCODE_WREN;
-
-	return spi_write_then_read(flash->spi, &code, 1, NULL, 0);
-}
-
-/*
- * Send write disble instruction to the chip.
- */
-static inline int write_disable(struct m25p *flash)
-{
-	u8	code = OPCODE_WRDI;
-
-	return spi_write_then_read(flash->spi, &code, 1, NULL, 0);
-}
-
-/*
- * Enable/disable 4-byte addressing mode.
- */
-static inline int set_4byte(struct m25p *flash, u32 jedec_id, int enable)
-{
-	int status;
-	bool need_wren = false;
-
-	switch (JEDEC_MFR(jedec_id)) {
-	case CFI_MFR_ST: /* Micron, actually */
-		/* Some Micron need WREN command; all will accept it */
-		need_wren = true;
-	case CFI_MFR_MACRONIX:
-	case 0xEF /* winbond */:
-		if (need_wren)
-			write_enable(flash);
-
-		flash->command[0] = enable ? OPCODE_EN4B : OPCODE_EX4B;
-		status = spi_write(flash->spi, flash->command, 1);
-
-		if (need_wren)
-			write_disable(flash);
-
-		return status;
-	default:
-		/* Spansion style */
-		flash->command[0] = OPCODE_BRWR;
-		flash->command[1] = enable << 7;
-		return spi_write(flash->spi, flash->command, 2);
-	}
-}
-
-/*
- * Service routine to read status register until ready, or timeout occurs.
- * Returns non-zero if error.
- */
-static int wait_till_ready(struct m25p *flash)
-{
-	unsigned long deadline;
-	int sr;
-
-	deadline = jiffies + MAX_READY_WAIT_JIFFIES;
-
-	do {
-		if ((sr = read_sr(flash)) < 0)
-			break;
-		else if (!(sr & SR_WIP))
-			return 0;
-
-		cond_resched();
-
-	} while (!time_after_eq(jiffies, deadline));
-
-	return 1;
-}
-
-/*
- * Write status Register and configuration register with 2 bytes
- * The first byte will be written to the status register, while the
- * second byte will be written to the configuration register.
- * Return negative if error occured.
- */
-static int write_sr_cr(struct m25p *flash, u16 val)
-{
-	flash->command[0] = OPCODE_WRSR;
-	flash->command[1] = val & 0xff;
-	flash->command[2] = (val >> 8);
-
-	return spi_write(flash->spi, flash->command, 3);
-}
-
-static int macronix_quad_enable(struct m25p *flash)
-{
-	int ret, val;
-	u8 cmd[2];
-	cmd[0] = OPCODE_WRSR;
-
-	val = read_sr(flash);
-	cmd[1] = val | SR_QUAD_EN_MX;
-	write_enable(flash);
-
-	spi_write(flash->spi, &cmd, 2);
-
-	if (wait_till_ready(flash))
-		return 1;
-
-	ret = read_sr(flash);
-	if (!(ret > 0 && (ret & SR_QUAD_EN_MX))) {
-		dev_err(&flash->spi->dev, "Macronix Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int spansion_quad_enable(struct m25p *flash)
+static int m25p80_read_reg(struct spi_nor *nor, u8 code, u8 *val, int len)
 {
+	struct m25p *flash = nor->priv;
+	struct spi_device *spi = flash->spi;
 	int ret;
-	int quad_en = CR_QUAD_EN_SPAN << 8;
-
-	write_enable(flash);
 
-	ret = write_sr_cr(flash, quad_en);
-	if (ret < 0) {
-		dev_err(&flash->spi->dev,
-			"error while writing configuration register\n");
-		return -EINVAL;
-	}
-
-	/* read back and check it */
-	ret = read_cr(flash);
-	if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) {
-		dev_err(&flash->spi->dev, "Spansion Quad bit not set\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int set_quad_mode(struct m25p *flash, u32 jedec_id)
-{
-	int status;
-
-	switch (JEDEC_MFR(jedec_id)) {
-	case CFI_MFR_MACRONIX:
-		status = macronix_quad_enable(flash);
-		if (status) {
-			dev_err(&flash->spi->dev,
-				"Macronix quad-read not enabled\n");
-			return -EINVAL;
-		}
-		return status;
-	default:
-		status = spansion_quad_enable(flash);
-		if (status) {
-			dev_err(&flash->spi->dev,
-				"Spansion quad-read not enabled\n");
-			return -EINVAL;
-		}
-		return status;
-	}
-}
-
-/*
- * Erase the whole flash memory
- *
- * Returns 0 if successful, non-zero otherwise.
- */
-static int erase_chip(struct m25p *flash)
-{
-	pr_debug("%s: %s %lldKiB\n", dev_name(&flash->spi->dev), __func__,
-			(long long)(flash->mtd.size >> 10));
+	ret = spi_write_then_read(spi, &code, 1, val, len);
+	if (ret < 0)
+		dev_err(&spi->dev, "error %d reading %x\n", ret, code);
 
-	/* Wait until finished previous write command. */
-	if (wait_till_ready(flash))
-		return 1;
-
-	/* Send write enable, then erase commands. */
-	write_enable(flash);
-
-	/* Set up command buffer. */
-	flash->command[0] = OPCODE_CHIP_ERASE;
-
-	spi_write(flash->spi, flash->command, 1);
-
-	return 0;
+	return ret;
 }
 
-static void m25p_addr2cmd(struct m25p *flash, unsigned int addr, u8 *cmd)
+static void m25p_addr2cmd(struct spi_nor *nor, unsigned int addr, u8 *cmd)
 {
 	/* opcode is in cmd[0] */
-	cmd[1] = addr >> (flash->addr_width * 8 -  8);
-	cmd[2] = addr >> (flash->addr_width * 8 - 16);
-	cmd[3] = addr >> (flash->addr_width * 8 - 24);
-	cmd[4] = addr >> (flash->addr_width * 8 - 32);
+	cmd[1] = addr >> (nor->addr_width * 8 -  8);
+	cmd[2] = addr >> (nor->addr_width * 8 - 16);
+	cmd[3] = addr >> (nor->addr_width * 8 - 24);
+	cmd[4] = addr >> (nor->addr_width * 8 - 32);
 }
 
-static int m25p_cmdsz(struct m25p *flash)
+static int m25p_cmdsz(struct spi_nor *nor)
 {
-	return 1 + flash->addr_width;
+	return 1 + nor->addr_width;
 }
 
-/*
- * Erase one sector of flash memory at offset ``offset'' which is any
- * address within the sector which should be erased.
- *
- * Returns 0 if successful, non-zero otherwise.
- */
-static int erase_sector(struct m25p *flash, u32 offset)
+static int m25p80_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len,
+			int wr_en)
 {
-	pr_debug("%s: %s %dKiB at 0x%08x\n", dev_name(&flash->spi->dev),
-			__func__, flash->mtd.erasesize / 1024, offset);
-
-	/* Wait until finished previous write command. */
-	if (wait_till_ready(flash))
-		return 1;
+	struct m25p *flash = nor->priv;
+	struct spi_device *spi = flash->spi;
 
-	/* Send write enable, then erase commands. */
-	write_enable(flash);
-
-	/* Set up command buffer. */
-	flash->command[0] = flash->erase_opcode;
-	m25p_addr2cmd(flash, offset, flash->command);
-
-	spi_write(flash->spi, flash->command, m25p_cmdsz(flash));
+	flash->command[0] = opcode;
+	if (buf)
+		memcpy(&flash->command[1], buf, len);
 
-	return 0;
+	return spi_write(spi, flash->command, len + 1);
 }
 
-/****************************************************************************/
-
-/*
- * MTD implementation
- */
-
-/*
- * Erase an address range on the flash chip.  The address range may extend
- * one or more erase sectors.  Return an error is there is a problem erasing.
- */
-static int m25p80_erase(struct mtd_info *mtd, struct erase_info *instr)
+static void m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
+			size_t *retlen, const u_char *buf)
 {
-	struct m25p *flash = mtd_to_m25p(mtd);
-	u32 addr,len;
-	uint32_t rem;
-
-	pr_debug("%s: %s at 0x%llx, len %lld\n", dev_name(&flash->spi->dev),
-			__func__, (long long)instr->addr,
-			(long long)instr->len);
-
-	div_u64_rem(instr->len, mtd->erasesize, &rem);
-	if (rem)
-		return -EINVAL;
-
-	addr = instr->addr;
-	len = instr->len;
-
-	mutex_lock(&flash->lock);
-
-	/* whole-chip erase? */
-	if (len == flash->mtd.size) {
-		if (erase_chip(flash)) {
-			instr->state = MTD_ERASE_FAILED;
-			mutex_unlock(&flash->lock);
-			return -EIO;
-		}
+	struct m25p *flash = nor->priv;
+	struct spi_device *spi = flash->spi;
+	struct spi_transfer t[2] = {};
+	struct spi_message m;
+	int cmd_sz = m25p_cmdsz(nor);
 
-	/* REVISIT in some cases we could speed up erasing large regions
-	 * by using OPCODE_SE instead of OPCODE_BE_4K.  We may have set up
-	 * to use "small sector erase", but that's not always optimal.
-	 */
+	spi_message_init(&m);
 
-	/* "sector"-at-a-time erase */
-	} else {
-		while (len) {
-			if (erase_sector(flash, addr)) {
-				instr->state = MTD_ERASE_FAILED;
-				mutex_unlock(&flash->lock);
-				return -EIO;
-			}
+	if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
+		cmd_sz = 1;
 
-			addr += mtd->erasesize;
-			len -= mtd->erasesize;
-		}
-	}
+	flash->command[0] = nor->program_opcode;
+	m25p_addr2cmd(nor, to, flash->command);
 
-	mutex_unlock(&flash->lock);
+	t[0].tx_buf = flash->command;
+	t[0].len = cmd_sz;
+	spi_message_add_tail(&t[0], &m);
 
-	instr->state = MTD_ERASE_DONE;
-	mtd_erase_callback(instr);
+	t[1].tx_buf = buf;
+	t[1].len = len;
+	spi_message_add_tail(&t[1], &m);
 
-	return 0;
-}
+	spi_sync(spi, &m);
 
-/*
- * Dummy Cycle calculation for different type of read.
- * It can be used to support more commands with
- * different dummy cycle requirements.
- */
-static inline int m25p80_dummy_cycles_read(struct m25p *flash)
-{
-	switch (flash->flash_read) {
-	case M25P80_FAST:
-	case M25P80_DUAL:
-	case M25P80_QUAD:
-		return 1;
-	case M25P80_NORMAL:
-		return 0;
-	default:
-		dev_err(&flash->spi->dev, "No valid read type supported\n");
-		return -1;
-	}
+	*retlen += m.actual_length - cmd_sz;
 }
 
-static inline unsigned int m25p80_rx_nbits(const struct m25p *flash)
+static inline unsigned int m25p80_rx_nbits(struct spi_nor *nor)
 {
-	switch (flash->flash_read) {
-	case M25P80_DUAL:
+	switch (nor->flash_read) {
+	case SPI_NOR_DUAL:
 		return 2;
-	case M25P80_QUAD:
+	case SPI_NOR_QUAD:
 		return 4;
 	default:
 		return 0;
@@ -505,590 +118,72 @@ static inline unsigned int m25p80_rx_nbits(const struct m25p *flash)
 }
 
 /*
- * Read an address range from the flash chip.  The address range
+ * Read an address range from the nor chip.  The address range
  * may be any size provided it is within the physical boundaries.
  */
-static int m25p80_read(struct mtd_info *mtd, loff_t from, size_t len,
-	size_t *retlen, u_char *buf)
+static int m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
+			size_t *retlen, u_char *buf)
 {
-	struct m25p *flash = mtd_to_m25p(mtd);
+	struct m25p *flash = nor->priv;
+	struct spi_device *spi = flash->spi;
 	struct spi_transfer t[2];
 	struct spi_message m;
-	uint8_t opcode;
-	int dummy;
+	int dummy = nor->read_dummy;
+	int ret;
 
-	pr_debug("%s: %s from 0x%08x, len %zd\n", dev_name(&flash->spi->dev),
-			__func__, (u32)from, len);
+	/* Wait till previous write/erase is done. */
+	ret = nor->wait_till_ready(nor);
+	if (ret)
+		return ret;
 
 	spi_message_init(&m);
 	memset(t, 0, (sizeof t));
 
-	dummy =  m25p80_dummy_cycles_read(flash);
-	if (dummy < 0) {
-		dev_err(&flash->spi->dev, "No valid read command supported\n");
-		return -EINVAL;
-	}
+	flash->command[0] = nor->read_opcode;
+	m25p_addr2cmd(nor, from, flash->command);
 
 	t[0].tx_buf = flash->command;
-	t[0].len = m25p_cmdsz(flash) + dummy;
+	t[0].len = m25p_cmdsz(nor) + dummy;
 	spi_message_add_tail(&t[0], &m);
 
 	t[1].rx_buf = buf;
-	t[1].rx_nbits = m25p80_rx_nbits(flash);
+	t[1].rx_nbits = m25p80_rx_nbits(nor);
 	t[1].len = len;
 	spi_message_add_tail(&t[1], &m);
 
-	mutex_lock(&flash->lock);
-
-	/* Wait till previous write/erase is done. */
-	if (wait_till_ready(flash)) {
-		/* REVISIT status return?? */
-		mutex_unlock(&flash->lock);
-		return 1;
-	}
-
-	/* Set up the write data buffer. */
-	opcode = flash->read_opcode;
-	flash->command[0] = opcode;
-	m25p_addr2cmd(flash, from, flash->command);
-
-	spi_sync(flash->spi, &m);
-
-	*retlen = m.actual_length - m25p_cmdsz(flash) - dummy;
-
-	mutex_unlock(&flash->lock);
+	spi_sync(spi, &m);
 
+	*retlen = m.actual_length - m25p_cmdsz(nor) - dummy;
 	return 0;
 }
 
-/*
- * Write an address range to the flash chip.  Data must be written in
- * FLASH_PAGESIZE chunks.  The address range may be any size provided
- * it is within the physical boundaries.
- */
-static int m25p80_write(struct mtd_info *mtd, loff_t to, size_t len,
-	size_t *retlen, const u_char *buf)
+static int m25p80_erase(struct spi_nor *nor, loff_t offset)
 {
-	struct m25p *flash = mtd_to_m25p(mtd);
-	u32 page_offset, page_size;
-	struct spi_transfer t[2];
-	struct spi_message m;
-
-	pr_debug("%s: %s to 0x%08x, len %zd\n", dev_name(&flash->spi->dev),
-			__func__, (u32)to, len);
-
-	spi_message_init(&m);
-	memset(t, 0, (sizeof t));
-
-	t[0].tx_buf = flash->command;
-	t[0].len = m25p_cmdsz(flash);
-	spi_message_add_tail(&t[0], &m);
-
-	t[1].tx_buf = buf;
-	spi_message_add_tail(&t[1], &m);
-
-	mutex_lock(&flash->lock);
-
-	/* Wait until finished previous write command. */
-	if (wait_till_ready(flash)) {
-		mutex_unlock(&flash->lock);
-		return 1;
-	}
-
-	write_enable(flash);
-
-	/* Set up the opcode in the write buffer. */
-	flash->command[0] = flash->program_opcode;
-	m25p_addr2cmd(flash, to, flash->command);
-
-	page_offset = to & (flash->page_size - 1);
-
-	/* do all the bytes fit onto one page? */
-	if (page_offset + len <= flash->page_size) {
-		t[1].len = len;
-
-		spi_sync(flash->spi, &m);
-
-		*retlen = m.actual_length - m25p_cmdsz(flash);
-	} else {
-		u32 i;
-
-		/* the size of data remaining on the first page */
-		page_size = flash->page_size - page_offset;
-
-		t[1].len = page_size;
-		spi_sync(flash->spi, &m);
-
-		*retlen = m.actual_length - m25p_cmdsz(flash);
-
-		/* write everything in flash->page_size chunks */
-		for (i = page_size; i < len; i += page_size) {
-			page_size = len - i;
-			if (page_size > flash->page_size)
-				page_size = flash->page_size;
-
-			/* write the next page to flash */
-			m25p_addr2cmd(flash, to + i, flash->command);
-
-			t[1].tx_buf = buf + i;
-			t[1].len = page_size;
-
-			wait_till_ready(flash);
-
-			write_enable(flash);
-
-			spi_sync(flash->spi, &m);
-
-			*retlen += m.actual_length - m25p_cmdsz(flash);
-		}
-	}
-
-	mutex_unlock(&flash->lock);
-
-	return 0;
-}
-
-static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
-		size_t *retlen, const u_char *buf)
-{
-	struct m25p *flash = mtd_to_m25p(mtd);
-	struct spi_transfer t[2];
-	struct spi_message m;
-	size_t actual;
-	int cmd_sz, ret;
-
-	pr_debug("%s: %s to 0x%08x, len %zd\n", dev_name(&flash->spi->dev),
-			__func__, (u32)to, len);
-
-	spi_message_init(&m);
-	memset(t, 0, (sizeof t));
-
-	t[0].tx_buf = flash->command;
-	t[0].len = m25p_cmdsz(flash);
-	spi_message_add_tail(&t[0], &m);
-
-	t[1].tx_buf = buf;
-	spi_message_add_tail(&t[1], &m);
+	struct m25p *flash = nor->priv;
+	int ret;
 
-	mutex_lock(&flash->lock);
+	dev_dbg(nor->dev, "%dKiB at 0x%08x\n",
+		flash->mtd.erasesize / 1024, (u32)offset);
 
 	/* Wait until finished previous write command. */
-	ret = wait_till_ready(flash);
+	ret = nor->wait_till_ready(nor);
 	if (ret)
-		goto time_out;
-
-	write_enable(flash);
-
-	actual = to % 2;
-	/* Start write from odd address. */
-	if (actual) {
-		flash->command[0] = OPCODE_BP;
-		m25p_addr2cmd(flash, to, flash->command);
-
-		/* write one byte. */
-		t[1].len = 1;
-		spi_sync(flash->spi, &m);
-		ret = wait_till_ready(flash);
-		if (ret)
-			goto time_out;
-		*retlen += m.actual_length - m25p_cmdsz(flash);
-	}
-	to += actual;
-
-	flash->command[0] = OPCODE_AAI_WP;
-	m25p_addr2cmd(flash, to, flash->command);
-
-	/* Write out most of the data here. */
-	cmd_sz = m25p_cmdsz(flash);
-	for (; actual < len - 1; actual += 2) {
-		t[0].len = cmd_sz;
-		/* write two bytes. */
-		t[1].len = 2;
-		t[1].tx_buf = buf + actual;
+		return ret;
 
-		spi_sync(flash->spi, &m);
-		ret = wait_till_ready(flash);
-		if (ret)
-			goto time_out;
-		*retlen += m.actual_length - cmd_sz;
-		cmd_sz = 1;
-		to += 2;
-	}
-	write_disable(flash);
-	ret = wait_till_ready(flash);
+	/* Send write enable, then erase commands. */
+	ret = nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0, 0);
 	if (ret)
-		goto time_out;
-
-	/* Write out trailing byte if it exists. */
-	if (actual != len) {
-		write_enable(flash);
-		flash->command[0] = OPCODE_BP;
-		m25p_addr2cmd(flash, to, flash->command);
-		t[0].len = m25p_cmdsz(flash);
-		t[1].len = 1;
-		t[1].tx_buf = buf + actual;
-
-		spi_sync(flash->spi, &m);
-		ret = wait_till_ready(flash);
-		if (ret)
-			goto time_out;
-		*retlen += m.actual_length - m25p_cmdsz(flash);
-		write_disable(flash);
-	}
-
-time_out:
-	mutex_unlock(&flash->lock);
-	return ret;
-}
-
-static int m25p80_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
-{
-	struct m25p *flash = mtd_to_m25p(mtd);
-	uint32_t offset = ofs;
-	uint8_t status_old, status_new;
-	int res = 0;
-
-	mutex_lock(&flash->lock);
-	/* Wait until finished previous command */
-	if (wait_till_ready(flash)) {
-		res = 1;
-		goto err;
-	}
-
-	status_old = read_sr(flash);
-
-	if (offset < flash->mtd.size-(flash->mtd.size/2))
-		status_new = status_old | SR_BP2 | SR_BP1 | SR_BP0;
-	else if (offset < flash->mtd.size-(flash->mtd.size/4))
-		status_new = (status_old & ~SR_BP0) | SR_BP2 | SR_BP1;
-	else if (offset < flash->mtd.size-(flash->mtd.size/8))
-		status_new = (status_old & ~SR_BP1) | SR_BP2 | SR_BP0;
-	else if (offset < flash->mtd.size-(flash->mtd.size/16))
-		status_new = (status_old & ~(SR_BP0|SR_BP1)) | SR_BP2;
-	else if (offset < flash->mtd.size-(flash->mtd.size/32))
-		status_new = (status_old & ~SR_BP2) | SR_BP1 | SR_BP0;
-	else if (offset < flash->mtd.size-(flash->mtd.size/64))
-		status_new = (status_old & ~(SR_BP2|SR_BP0)) | SR_BP1;
-	else
-		status_new = (status_old & ~(SR_BP2|SR_BP1)) | SR_BP0;
-
-	/* Only modify protection if it will not unlock other areas */
-	if ((status_new&(SR_BP2|SR_BP1|SR_BP0)) >
-					(status_old&(SR_BP2|SR_BP1|SR_BP0))) {
-		write_enable(flash);
-		if (write_sr(flash, status_new) < 0) {
-			res = 1;
-			goto err;
-		}
-	}
-
-err:	mutex_unlock(&flash->lock);
-	return res;
-}
-
-static int m25p80_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
-{
-	struct m25p *flash = mtd_to_m25p(mtd);
-	uint32_t offset = ofs;
-	uint8_t status_old, status_new;
-	int res = 0;
-
-	mutex_lock(&flash->lock);
-	/* Wait until finished previous command */
-	if (wait_till_ready(flash)) {
-		res = 1;
-		goto err;
-	}
-
-	status_old = read_sr(flash);
-
-	if (offset+len > flash->mtd.size-(flash->mtd.size/64))
-		status_new = status_old & ~(SR_BP2|SR_BP1|SR_BP0);
-	else if (offset+len > flash->mtd.size-(flash->mtd.size/32))
-		status_new = (status_old & ~(SR_BP2|SR_BP1)) | SR_BP0;
-	else if (offset+len > flash->mtd.size-(flash->mtd.size/16))
-		status_new = (status_old & ~(SR_BP2|SR_BP0)) | SR_BP1;
-	else if (offset+len > flash->mtd.size-(flash->mtd.size/8))
-		status_new = (status_old & ~SR_BP2) | SR_BP1 | SR_BP0;
-	else if (offset+len > flash->mtd.size-(flash->mtd.size/4))
-		status_new = (status_old & ~(SR_BP0|SR_BP1)) | SR_BP2;
-	else if (offset+len > flash->mtd.size-(flash->mtd.size/2))
-		status_new = (status_old & ~SR_BP1) | SR_BP2 | SR_BP0;
-	else
-		status_new = (status_old & ~SR_BP0) | SR_BP2 | SR_BP1;
-
-	/* Only modify protection if it will not lock other areas */
-	if ((status_new&(SR_BP2|SR_BP1|SR_BP0)) <
-					(status_old&(SR_BP2|SR_BP1|SR_BP0))) {
-		write_enable(flash);
-		if (write_sr(flash, status_new) < 0) {
-			res = 1;
-			goto err;
-		}
-	}
-
-err:	mutex_unlock(&flash->lock);
-	return res;
-}
-
-/****************************************************************************/
-
-/*
- * SPI device driver setup and teardown
- */
-
-struct flash_info {
-	/* JEDEC id zero means "no ID" (most older chips); otherwise it has
-	 * a high byte of zero plus three data bytes: the manufacturer id,
-	 * then a two byte device id.
-	 */
-	u32		jedec_id;
-	u16             ext_id;
-
-	/* The size listed here is what works with OPCODE_SE, which isn't
-	 * necessarily called a "sector" by the vendor.
-	 */
-	unsigned	sector_size;
-	u16		n_sectors;
-
-	u16		page_size;
-	u16		addr_width;
-
-	u16		flags;
-#define	SECT_4K		0x01		/* OPCODE_BE_4K works uniformly */
-#define	M25P_NO_ERASE	0x02		/* No erase command needed */
-#define	SST_WRITE	0x04		/* use SST byte programming */
-#define	M25P_NO_FR	0x08		/* Can't do fastread */
-#define	SECT_4K_PMC	0x10		/* OPCODE_BE_4K_PMC works uniformly */
-#define	M25P80_DUAL_READ	0x20    /* Flash supports Dual Read */
-#define	M25P80_QUAD_READ	0x40    /* Flash supports Quad Read */
-};
-
-#define INFO(_jedec_id, _ext_id, _sector_size, _n_sectors, _flags)	\
-	((kernel_ulong_t)&(struct flash_info) {				\
-		.jedec_id = (_jedec_id),				\
-		.ext_id = (_ext_id),					\
-		.sector_size = (_sector_size),				\
-		.n_sectors = (_n_sectors),				\
-		.page_size = 256,					\
-		.flags = (_flags),					\
-	})
-
-#define CAT25_INFO(_sector_size, _n_sectors, _page_size, _addr_width, _flags)	\
-	((kernel_ulong_t)&(struct flash_info) {				\
-		.sector_size = (_sector_size),				\
-		.n_sectors = (_n_sectors),				\
-		.page_size = (_page_size),				\
-		.addr_width = (_addr_width),				\
-		.flags = (_flags),					\
-	})
-
-/* NOTE: double check command sets and memory organization when you add
- * more flash chips.  This current list focusses on newer chips, which
- * have been converging on command sets which including JEDEC ID.
- */
-static const struct spi_device_id m25p_ids[] = {
-	/* Atmel -- some are (confusingly) marketed as "DataFlash" */
-	{ "at25fs010",  INFO(0x1f6601, 0, 32 * 1024,   4, SECT_4K) },
-	{ "at25fs040",  INFO(0x1f6604, 0, 64 * 1024,   8, SECT_4K) },
-
-	{ "at25df041a", INFO(0x1f4401, 0, 64 * 1024,   8, SECT_4K) },
-	{ "at25df321a", INFO(0x1f4701, 0, 64 * 1024,  64, SECT_4K) },
-	{ "at25df641",  INFO(0x1f4800, 0, 64 * 1024, 128, SECT_4K) },
-
-	{ "at26f004",   INFO(0x1f0400, 0, 64 * 1024,  8, SECT_4K) },
-	{ "at26df081a", INFO(0x1f4501, 0, 64 * 1024, 16, SECT_4K) },
-	{ "at26df161a", INFO(0x1f4601, 0, 64 * 1024, 32, SECT_4K) },
-	{ "at26df321",  INFO(0x1f4700, 0, 64 * 1024, 64, SECT_4K) },
-
-	{ "at45db081d", INFO(0x1f2500, 0, 64 * 1024, 16, SECT_4K) },
-
-	/* EON -- en25xxx */
-	{ "en25f32",    INFO(0x1c3116, 0, 64 * 1024,   64, SECT_4K) },
-	{ "en25p32",    INFO(0x1c2016, 0, 64 * 1024,   64, 0) },
-	{ "en25q32b",   INFO(0x1c3016, 0, 64 * 1024,   64, 0) },
-	{ "en25p64",    INFO(0x1c2017, 0, 64 * 1024,  128, 0) },
-	{ "en25q64",    INFO(0x1c3017, 0, 64 * 1024,  128, SECT_4K) },
-	{ "en25qh256",  INFO(0x1c7019, 0, 64 * 1024,  512, 0) },
-
-	/* ESMT */
-	{ "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K) },
-
-	/* Everspin */
-	{ "mr25h256", CAT25_INFO( 32 * 1024, 1, 256, 2, M25P_NO_ERASE | M25P_NO_FR) },
-	{ "mr25h10",  CAT25_INFO(128 * 1024, 1, 256, 3, M25P_NO_ERASE | M25P_NO_FR) },
-
-	/* GigaDevice */
-	{ "gd25q32", INFO(0xc84016, 0, 64 * 1024,  64, SECT_4K) },
-	{ "gd25q64", INFO(0xc84017, 0, 64 * 1024, 128, SECT_4K) },
-
-	/* Intel/Numonyx -- xxxs33b */
-	{ "160s33b",  INFO(0x898911, 0, 64 * 1024,  32, 0) },
-	{ "320s33b",  INFO(0x898912, 0, 64 * 1024,  64, 0) },
-	{ "640s33b",  INFO(0x898913, 0, 64 * 1024, 128, 0) },
-
-	/* Macronix */
-	{ "mx25l2005a",  INFO(0xc22012, 0, 64 * 1024,   4, SECT_4K) },
-	{ "mx25l4005a",  INFO(0xc22013, 0, 64 * 1024,   8, SECT_4K) },
-	{ "mx25l8005",   INFO(0xc22014, 0, 64 * 1024,  16, 0) },
-	{ "mx25l1606e",  INFO(0xc22015, 0, 64 * 1024,  32, SECT_4K) },
-	{ "mx25l3205d",  INFO(0xc22016, 0, 64 * 1024,  64, 0) },
-	{ "mx25l3255e",  INFO(0xc29e16, 0, 64 * 1024,  64, SECT_4K) },
-	{ "mx25l6405d",  INFO(0xc22017, 0, 64 * 1024, 128, 0) },
-	{ "mx25l12805d", INFO(0xc22018, 0, 64 * 1024, 256, 0) },
-	{ "mx25l12855e", INFO(0xc22618, 0, 64 * 1024, 256, 0) },
-	{ "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512, 0) },
-	{ "mx25l25655e", INFO(0xc22619, 0, 64 * 1024, 512, 0) },
-	{ "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, M25P80_QUAD_READ) },
-	{ "mx66l1g55g",  INFO(0xc2261b, 0, 64 * 1024, 2048, M25P80_QUAD_READ) },
-
-	/* Micron */
-	{ "n25q064",     INFO(0x20ba17, 0, 64 * 1024,  128, 0) },
-	{ "n25q128a11",  INFO(0x20bb18, 0, 64 * 1024,  256, 0) },
-	{ "n25q128a13",  INFO(0x20ba18, 0, 64 * 1024,  256, 0) },
-	{ "n25q256a",    INFO(0x20ba19, 0, 64 * 1024,  512, SECT_4K) },
-	{ "n25q512a",    INFO(0x20bb20, 0, 64 * 1024, 1024, SECT_4K) },
-
-	/* PMC */
-	{ "pm25lv512",   INFO(0,        0, 32 * 1024,    2, SECT_4K_PMC) },
-	{ "pm25lv010",   INFO(0,        0, 32 * 1024,    4, SECT_4K_PMC) },
-	{ "pm25lq032",   INFO(0x7f9d46, 0, 64 * 1024,   64, SECT_4K) },
-
-	/* Spansion -- single (large) sector size only, at least
-	 * for the chips listed here (without boot sectors).
-	 */
-	{ "s25sl032p",  INFO(0x010215, 0x4d00,  64 * 1024,  64, 0) },
-	{ "s25sl064p",  INFO(0x010216, 0x4d00,  64 * 1024, 128, 0) },
-	{ "s25fl256s0", INFO(0x010219, 0x4d00, 256 * 1024, 128, 0) },
-	{ "s25fl256s1", INFO(0x010219, 0x4d01,  64 * 1024, 512, M25P80_DUAL_READ | M25P80_QUAD_READ) },
-	{ "s25fl512s",  INFO(0x010220, 0x4d00, 256 * 1024, 256, M25P80_DUAL_READ | M25P80_QUAD_READ) },
-	{ "s70fl01gs",  INFO(0x010221, 0x4d00, 256 * 1024, 256, 0) },
-	{ "s25sl12800", INFO(0x012018, 0x0300, 256 * 1024,  64, 0) },
-	{ "s25sl12801", INFO(0x012018, 0x0301,  64 * 1024, 256, 0) },
-	{ "s25fl129p0", INFO(0x012018, 0x4d00, 256 * 1024,  64, 0) },
-	{ "s25fl129p1", INFO(0x012018, 0x4d01,  64 * 1024, 256, 0) },
-	{ "s25sl004a",  INFO(0x010212,      0,  64 * 1024,   8, 0) },
-	{ "s25sl008a",  INFO(0x010213,      0,  64 * 1024,  16, 0) },
-	{ "s25sl016a",  INFO(0x010214,      0,  64 * 1024,  32, 0) },
-	{ "s25sl032a",  INFO(0x010215,      0,  64 * 1024,  64, 0) },
-	{ "s25sl064a",  INFO(0x010216,      0,  64 * 1024, 128, 0) },
-	{ "s25fl008k",  INFO(0xef4014,      0,  64 * 1024,  16, SECT_4K) },
-	{ "s25fl016k",  INFO(0xef4015,      0,  64 * 1024,  32, SECT_4K) },
-	{ "s25fl064k",  INFO(0xef4017,      0,  64 * 1024, 128, SECT_4K) },
-
-	/* SST -- large erase sizes are "overlays", "sectors" are 4K */
-	{ "sst25vf040b", INFO(0xbf258d, 0, 64 * 1024,  8, SECT_4K | SST_WRITE) },
-	{ "sst25vf080b", INFO(0xbf258e, 0, 64 * 1024, 16, SECT_4K | SST_WRITE) },
-	{ "sst25vf016b", INFO(0xbf2541, 0, 64 * 1024, 32, SECT_4K | SST_WRITE) },
-	{ "sst25vf032b", INFO(0xbf254a, 0, 64 * 1024, 64, SECT_4K | SST_WRITE) },
-	{ "sst25vf064c", INFO(0xbf254b, 0, 64 * 1024, 128, SECT_4K) },
-	{ "sst25wf512",  INFO(0xbf2501, 0, 64 * 1024,  1, SECT_4K | SST_WRITE) },
-	{ "sst25wf010",  INFO(0xbf2502, 0, 64 * 1024,  2, SECT_4K | SST_WRITE) },
-	{ "sst25wf020",  INFO(0xbf2503, 0, 64 * 1024,  4, SECT_4K | SST_WRITE) },
-	{ "sst25wf040",  INFO(0xbf2504, 0, 64 * 1024,  8, SECT_4K | SST_WRITE) },
-
-	/* ST Microelectronics -- newer production may have feature updates */
-	{ "m25p05",  INFO(0x202010,  0,  32 * 1024,   2, 0) },
-	{ "m25p10",  INFO(0x202011,  0,  32 * 1024,   4, 0) },
-	{ "m25p20",  INFO(0x202012,  0,  64 * 1024,   4, 0) },
-	{ "m25p40",  INFO(0x202013,  0,  64 * 1024,   8, 0) },
-	{ "m25p80",  INFO(0x202014,  0,  64 * 1024,  16, 0) },
-	{ "m25p16",  INFO(0x202015,  0,  64 * 1024,  32, 0) },
-	{ "m25p32",  INFO(0x202016,  0,  64 * 1024,  64, 0) },
-	{ "m25p64",  INFO(0x202017,  0,  64 * 1024, 128, 0) },
-	{ "m25p128", INFO(0x202018,  0, 256 * 1024,  64, 0) },
-	{ "n25q032", INFO(0x20ba16,  0,  64 * 1024,  64, 0) },
-
-	{ "m25p05-nonjedec",  INFO(0, 0,  32 * 1024,   2, 0) },
-	{ "m25p10-nonjedec",  INFO(0, 0,  32 * 1024,   4, 0) },
-	{ "m25p20-nonjedec",  INFO(0, 0,  64 * 1024,   4, 0) },
-	{ "m25p40-nonjedec",  INFO(0, 0,  64 * 1024,   8, 0) },
-	{ "m25p80-nonjedec",  INFO(0, 0,  64 * 1024,  16, 0) },
-	{ "m25p16-nonjedec",  INFO(0, 0,  64 * 1024,  32, 0) },
-	{ "m25p32-nonjedec",  INFO(0, 0,  64 * 1024,  64, 0) },
-	{ "m25p64-nonjedec",  INFO(0, 0,  64 * 1024, 128, 0) },
-	{ "m25p128-nonjedec", INFO(0, 0, 256 * 1024,  64, 0) },
-
-	{ "m45pe10", INFO(0x204011,  0, 64 * 1024,    2, 0) },
-	{ "m45pe80", INFO(0x204014,  0, 64 * 1024,   16, 0) },
-	{ "m45pe16", INFO(0x204015,  0, 64 * 1024,   32, 0) },
-
-	{ "m25pe20", INFO(0x208012,  0, 64 * 1024,  4,       0) },
-	{ "m25pe80", INFO(0x208014,  0, 64 * 1024, 16,       0) },
-	{ "m25pe16", INFO(0x208015,  0, 64 * 1024, 32, SECT_4K) },
-
-	{ "m25px16",    INFO(0x207115,  0, 64 * 1024, 32, SECT_4K) },
-	{ "m25px32",    INFO(0x207116,  0, 64 * 1024, 64, SECT_4K) },
-	{ "m25px32-s0", INFO(0x207316,  0, 64 * 1024, 64, SECT_4K) },
-	{ "m25px32-s1", INFO(0x206316,  0, 64 * 1024, 64, SECT_4K) },
-	{ "m25px64",    INFO(0x207117,  0, 64 * 1024, 128, 0) },
-
-	/* Winbond -- w25x "blocks" are 64K, "sectors" are 4KiB */
-	{ "w25x10", INFO(0xef3011, 0, 64 * 1024,  2,  SECT_4K) },
-	{ "w25x20", INFO(0xef3012, 0, 64 * 1024,  4,  SECT_4K) },
-	{ "w25x40", INFO(0xef3013, 0, 64 * 1024,  8,  SECT_4K) },
-	{ "w25x80", INFO(0xef3014, 0, 64 * 1024,  16, SECT_4K) },
-	{ "w25x16", INFO(0xef3015, 0, 64 * 1024,  32, SECT_4K) },
-	{ "w25x32", INFO(0xef3016, 0, 64 * 1024,  64, SECT_4K) },
-	{ "w25q32", INFO(0xef4016, 0, 64 * 1024,  64, SECT_4K) },
-	{ "w25q32dw", INFO(0xef6016, 0, 64 * 1024,  64, SECT_4K) },
-	{ "w25x64", INFO(0xef3017, 0, 64 * 1024, 128, SECT_4K) },
-	{ "w25q64", INFO(0xef4017, 0, 64 * 1024, 128, SECT_4K) },
-	{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
-	{ "w25q80", INFO(0xef5014, 0, 64 * 1024,  16, SECT_4K) },
-	{ "w25q80bl", INFO(0xef4014, 0, 64 * 1024,  16, SECT_4K) },
-	{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
-	{ "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K) },
-
-	/* Catalyst / On Semiconductor -- non-JEDEC */
-	{ "cat25c11", CAT25_INFO(  16, 8, 16, 1, M25P_NO_ERASE | M25P_NO_FR) },
-	{ "cat25c03", CAT25_INFO(  32, 8, 16, 2, M25P_NO_ERASE | M25P_NO_FR) },
-	{ "cat25c09", CAT25_INFO( 128, 8, 32, 2, M25P_NO_ERASE | M25P_NO_FR) },
-	{ "cat25c17", CAT25_INFO( 256, 8, 32, 2, M25P_NO_ERASE | M25P_NO_FR) },
-	{ "cat25128", CAT25_INFO(2048, 8, 64, 2, M25P_NO_ERASE | M25P_NO_FR) },
-	{ },
-};
-MODULE_DEVICE_TABLE(spi, m25p_ids);
-
-static const struct spi_device_id *jedec_probe(struct spi_device *spi)
-{
-	int			tmp;
-	u8			code = OPCODE_RDID;
-	u8			id[5];
-	u32			jedec;
-	u16                     ext_jedec;
-	struct flash_info	*info;
+		return ret;
 
-	/* JEDEC also defines an optional "extended device information"
-	 * string for after vendor-specific data, after the three bytes
-	 * we use here.  Supporting some chips might require using it.
-	 */
-	tmp = spi_write_then_read(spi, &code, 1, id, 5);
-	if (tmp < 0) {
-		pr_debug("%s: error %d reading JEDEC ID\n",
-				dev_name(&spi->dev), tmp);
-		return ERR_PTR(tmp);
-	}
-	jedec = id[0];
-	jedec = jedec << 8;
-	jedec |= id[1];
-	jedec = jedec << 8;
-	jedec |= id[2];
+	/* Set up command buffer. */
+	flash->command[0] = nor->erase_opcode;
+	m25p_addr2cmd(nor, offset, flash->command);
 
-	ext_jedec = id[3] << 8 | id[4];
+	spi_write(flash->spi, flash->command, m25p_cmdsz(nor));
 
-	for (tmp = 0; tmp < ARRAY_SIZE(m25p_ids) - 1; tmp++) {
-		info = (void *)m25p_ids[tmp].driver_data;
-		if (info->jedec_id == jedec) {
-			if (info->ext_id == 0 || info->ext_id == ext_jedec)
-				return &m25p_ids[tmp];
-		}
-	}
-	dev_err(&spi->dev, "unrecognized JEDEC id %06x\n", jedec);
-	return ERR_PTR(-ENODEV);
+	return 0;
 }
 
-
 /*
  * board specific setup should have ensured the SPI clock used here
  * matches what the READ command supports, at least until this driver
@@ -1096,231 +191,45 @@ static const struct spi_device_id *jedec_probe(struct spi_device *spi)
  */
 static int m25p_probe(struct spi_device *spi)
 {
-	const struct spi_device_id	*id = spi_get_device_id(spi);
-	struct flash_platform_data	*data;
-	struct m25p			*flash;
-	struct flash_info		*info;
-	unsigned			i;
 	struct mtd_part_parser_data	ppdata;
-	struct device_node *np = spi->dev.of_node;
+	struct flash_platform_data	*data;
+	struct m25p *flash;
+	struct spi_nor *nor;
+	enum read_mode mode = SPI_NOR_NORMAL;
 	int ret;
 
-	/* Platform data helps sort out which chip type we have, as
-	 * well as how this board partitions it.  If we don't have
-	 * a chip ID, try the JEDEC id commands; they'll work for most
-	 * newer chips, even if we don't recognize the particular chip.
-	 */
-	data = dev_get_platdata(&spi->dev);
-	if (data && data->type) {
-		const struct spi_device_id *plat_id;
-
-		for (i = 0; i < ARRAY_SIZE(m25p_ids) - 1; i++) {
-			plat_id = &m25p_ids[i];
-			if (strcmp(data->type, plat_id->name))
-				continue;
-			break;
-		}
-
-		if (i < ARRAY_SIZE(m25p_ids) - 1)
-			id = plat_id;
-		else
-			dev_warn(&spi->dev, "unrecognized id %s\n", data->type);
-	}
-
-	info = (void *)id->driver_data;
-
-	if (info->jedec_id) {
-		const struct spi_device_id *jid;
-
-		jid = jedec_probe(spi);
-		if (IS_ERR(jid)) {
-			return PTR_ERR(jid);
-		} else if (jid != id) {
-			/*
-			 * JEDEC knows better, so overwrite platform ID. We
-			 * can't trust partitions any longer, but we'll let
-			 * mtd apply them anyway, since some partitions may be
-			 * marked read-only, and we don't want to lose that
-			 * information, even if it's not 100% accurate.
-			 */
-			dev_warn(&spi->dev, "found %s, expected %s\n",
-				 jid->name, id->name);
-			id = jid;
-			info = (void *)jid->driver_data;
-		}
-	}
-
 	flash = devm_kzalloc(&spi->dev, sizeof(*flash), GFP_KERNEL);
 	if (!flash)
 		return -ENOMEM;
 
-	flash->command = devm_kzalloc(&spi->dev, MAX_CMD_SIZE, GFP_KERNEL);
-	if (!flash->command)
-		return -ENOMEM;
-
-	flash->spi = spi;
-	mutex_init(&flash->lock);
-	spi_set_drvdata(spi, flash);
-
-	/*
-	 * Atmel, SST and Intel/Numonyx serial flash tend to power
-	 * up with the software protection bits set
-	 */
+	nor = &flash->spi_nor;
 
-	if (JEDEC_MFR(info->jedec_id) == CFI_MFR_ATMEL ||
-	    JEDEC_MFR(info->jedec_id) == CFI_MFR_INTEL ||
-	    JEDEC_MFR(info->jedec_id) == CFI_MFR_SST) {
-		write_enable(flash);
-		write_sr(flash, 0);
-	}
-
-	if (data && data->name)
-		flash->mtd.name = data->name;
-	else
-		flash->mtd.name = dev_name(&spi->dev);
-
-	flash->mtd.type = MTD_NORFLASH;
-	flash->mtd.writesize = 1;
-	flash->mtd.flags = MTD_CAP_NORFLASH;
-	flash->mtd.size = info->sector_size * info->n_sectors;
-	flash->mtd._erase = m25p80_erase;
-	flash->mtd._read = m25p80_read;
-
-	/* flash protection support for STmicro chips */
-	if (JEDEC_MFR(info->jedec_id) == CFI_MFR_ST) {
-		flash->mtd._lock = m25p80_lock;
-		flash->mtd._unlock = m25p80_unlock;
-	}
+	/* install the hooks */
+	nor->read = m25p80_read;
+	nor->write = m25p80_write;
+	nor->erase = m25p80_erase;
+	nor->write_reg = m25p80_write_reg;
+	nor->read_reg = m25p80_read_reg;
 
-	/* sst flash chips use AAI word program */
-	if (info->flags & SST_WRITE)
-		flash->mtd._write = sst_write;
-	else
-		flash->mtd._write = m25p80_write;
+	nor->dev = &spi->dev;
+	nor->mtd = &flash->mtd;
+	nor->priv = flash;
 
-	/* prefer "small sector" erase if possible */
-	if (info->flags & SECT_4K) {
-		flash->erase_opcode = OPCODE_BE_4K;
-		flash->mtd.erasesize = 4096;
-	} else if (info->flags & SECT_4K_PMC) {
-		flash->erase_opcode = OPCODE_BE_4K_PMC;
-		flash->mtd.erasesize = 4096;
-	} else {
-		flash->erase_opcode = OPCODE_SE;
-		flash->mtd.erasesize = info->sector_size;
-	}
+	spi_set_drvdata(spi, flash);
+	flash->mtd.priv = nor;
+	flash->spi = spi;
 
-	if (info->flags & M25P_NO_ERASE)
-		flash->mtd.flags |= MTD_NO_ERASE;
+	if (spi->mode & SPI_RX_QUAD)
+		mode = SPI_NOR_QUAD;
+	else if (spi->mode & SPI_RX_DUAL)
+		mode = SPI_NOR_DUAL;
+	ret = spi_nor_scan(nor, spi_get_device_id(spi), mode);
+	if (ret)
+		return ret;
 
+	data = dev_get_platdata(&spi->dev);
 	ppdata.of_node = spi->dev.of_node;
-	flash->mtd.dev.parent = &spi->dev;
-	flash->page_size = info->page_size;
-	flash->mtd.writebufsize = flash->page_size;
-
-	if (np) {
-		/* If we were instantiated by DT, use it */
-		if (of_property_read_bool(np, "m25p,fast-read"))
-			flash->flash_read = M25P80_FAST;
-		else
-			flash->flash_read = M25P80_NORMAL;
-	} else {
-		/* If we weren't instantiated by DT, default to fast-read */
-		flash->flash_read = M25P80_FAST;
-	}
-
-	/* Some devices cannot do fast-read, no matter what DT tells us */
-	if (info->flags & M25P_NO_FR)
-		flash->flash_read = M25P80_NORMAL;
-
-	/* Quad/Dual-read mode takes precedence over fast/normal */
-	if (spi->mode & SPI_RX_QUAD && info->flags & M25P80_QUAD_READ) {
-		ret = set_quad_mode(flash, info->jedec_id);
-		if (ret) {
-			dev_err(&flash->spi->dev, "quad mode not supported\n");
-			return ret;
-		}
-		flash->flash_read = M25P80_QUAD;
-	} else if (spi->mode & SPI_RX_DUAL && info->flags & M25P80_DUAL_READ) {
-		flash->flash_read = M25P80_DUAL;
-	}
 
-	/* Default commands */
-	switch (flash->flash_read) {
-	case M25P80_QUAD:
-		flash->read_opcode = OPCODE_QUAD_READ;
-		break;
-	case M25P80_DUAL:
-		flash->read_opcode = OPCODE_DUAL_READ;
-		break;
-	case M25P80_FAST:
-		flash->read_opcode = OPCODE_FAST_READ;
-		break;
-	case M25P80_NORMAL:
-		flash->read_opcode = OPCODE_NORM_READ;
-		break;
-	default:
-		dev_err(&flash->spi->dev, "No Read opcode defined\n");
-		return -EINVAL;
-	}
-
-	flash->program_opcode = OPCODE_PP;
-
-	if (info->addr_width)
-		flash->addr_width = info->addr_width;
-	else if (flash->mtd.size > 0x1000000) {
-		/* enable 4-byte addressing if the device exceeds 16MiB */
-		flash->addr_width = 4;
-		if (JEDEC_MFR(info->jedec_id) == CFI_MFR_AMD) {
-			/* Dedicated 4-byte command set */
-			switch (flash->flash_read) {
-			case M25P80_QUAD:
-				flash->read_opcode = OPCODE_QUAD_READ_4B;
-				break;
-			case M25P80_DUAL:
-				flash->read_opcode = OPCODE_DUAL_READ_4B;
-				break;
-			case M25P80_FAST:
-				flash->read_opcode = OPCODE_FAST_READ_4B;
-				break;
-			case M25P80_NORMAL:
-				flash->read_opcode = OPCODE_NORM_READ_4B;
-				break;
-			}
-			flash->program_opcode = OPCODE_PP_4B;
-			/* No small sector erase for 4-byte command set */
-			flash->erase_opcode = OPCODE_SE_4B;
-			flash->mtd.erasesize = info->sector_size;
-		} else
-			set_4byte(flash, info->jedec_id, 1);
-	} else {
-		flash->addr_width = 3;
-	}
-
-	dev_info(&spi->dev, "%s (%lld Kbytes)\n", id->name,
-			(long long)flash->mtd.size >> 10);
-
-	pr_debug("mtd .name = %s, .size = 0x%llx (%lldMiB) "
-			".erasesize = 0x%.8x (%uKiB) .numeraseregions = %d\n",
-		flash->mtd.name,
-		(long long)flash->mtd.size, (long long)(flash->mtd.size >> 20),
-		flash->mtd.erasesize, flash->mtd.erasesize / 1024,
-		flash->mtd.numeraseregions);
-
-	if (flash->mtd.numeraseregions)
-		for (i = 0; i < flash->mtd.numeraseregions; i++)
-			pr_debug("mtd.eraseregions[%d] = { .offset = 0x%llx, "
-				".erasesize = 0x%.8x (%uKiB), "
-				".numblocks = %d }\n",
-				i, (long long)flash->mtd.eraseregions[i].offset,
-				flash->mtd.eraseregions[i].erasesize,
-				flash->mtd.eraseregions[i].erasesize / 1024,
-				flash->mtd.eraseregions[i].numblocks);
-
-
-	/* partitions should match sector boundaries; and it may be good to
-	 * use readonly partitions for writeprotected sectors (BP2..BP0).
-	 */
 	return mtd_device_parse_register(&flash->mtd, NULL, &ppdata,
 			data ? data->parts : NULL,
 			data ? data->nr_parts : 0);
@@ -1341,7 +250,7 @@ static struct spi_driver m25p80_driver = {
 		.name	= "m25p80",
 		.owner	= THIS_MODULE,
 	},
-	.id_table	= m25p_ids,
+	.id_table	= spi_nor_ids,
 	.probe	= m25p_probe,
 	.remove	= m25p_remove,
 
diff --git a/drivers/mtd/devices/serial_flash_cmds.h b/drivers/mtd/devices/serial_flash_cmds.h
index 4f0c2c7c898..f59a125295d 100644
--- a/drivers/mtd/devices/serial_flash_cmds.h
+++ b/drivers/mtd/devices/serial_flash_cmds.h
@@ -13,43 +13,23 @@
 #define _MTD_SERIAL_FLASH_CMDS_H
 
 /* Generic Flash Commands/OPCODEs */
-#define FLASH_CMD_WREN		0x06
-#define FLASH_CMD_WRDI		0x04
-#define FLASH_CMD_RDID		0x9f
-#define FLASH_CMD_RDSR		0x05
-#define FLASH_CMD_RDSR2		0x35
-#define FLASH_CMD_WRSR		0x01
-#define FLASH_CMD_SE_4K		0x20
-#define FLASH_CMD_SE_32K	0x52
-#define FLASH_CMD_SE		0xd8
-#define FLASH_CMD_CHIPERASE	0xc7
-#define FLASH_CMD_WRVCR		0x81
-#define FLASH_CMD_RDVCR		0x85
+#define SPINOR_OP_RDSR2		0x35
+#define SPINOR_OP_WRVCR		0x81
+#define SPINOR_OP_RDVCR		0x85
 
 /* JEDEC Standard - Serial Flash Discoverable Parmeters (SFDP) Commands */
-#define FLASH_CMD_READ		0x03	/* READ */
-#define FLASH_CMD_READ_FAST	0x0b	/* FAST READ */
-#define FLASH_CMD_READ_1_1_2	0x3b	/* DUAL OUTPUT READ */
-#define FLASH_CMD_READ_1_2_2	0xbb	/* DUAL I/O READ */
-#define FLASH_CMD_READ_1_1_4	0x6b	/* QUAD OUTPUT READ */
-#define FLASH_CMD_READ_1_4_4	0xeb	/* QUAD I/O READ */
+#define SPINOR_OP_READ_1_2_2	0xbb	/* DUAL I/O READ */
+#define SPINOR_OP_READ_1_4_4	0xeb	/* QUAD I/O READ */
 
-#define FLASH_CMD_WRITE		0x02	/* PAGE PROGRAM */
-#define FLASH_CMD_WRITE_1_1_2	0xa2	/* DUAL INPUT PROGRAM */
-#define FLASH_CMD_WRITE_1_2_2	0xd2	/* DUAL INPUT EXT PROGRAM */
-#define FLASH_CMD_WRITE_1_1_4	0x32	/* QUAD INPUT PROGRAM */
-#define FLASH_CMD_WRITE_1_4_4	0x12	/* QUAD INPUT EXT PROGRAM */
-
-#define FLASH_CMD_EN4B_ADDR	0xb7	/* Enter 4-byte address mode */
-#define FLASH_CMD_EX4B_ADDR	0xe9	/* Exit 4-byte address mode */
+#define SPINOR_OP_WRITE		0x02	/* PAGE PROGRAM */
+#define SPINOR_OP_WRITE_1_1_2	0xa2	/* DUAL INPUT PROGRAM */
+#define SPINOR_OP_WRITE_1_2_2	0xd2	/* DUAL INPUT EXT PROGRAM */
+#define SPINOR_OP_WRITE_1_1_4	0x32	/* QUAD INPUT PROGRAM */
+#define SPINOR_OP_WRITE_1_4_4	0x12	/* QUAD INPUT EXT PROGRAM */
 
 /* READ commands with 32-bit addressing */
-#define FLASH_CMD_READ4		0x13
-#define FLASH_CMD_READ4_FAST	0x0c
-#define FLASH_CMD_READ4_1_1_2	0x3c
-#define FLASH_CMD_READ4_1_2_2	0xbc
-#define FLASH_CMD_READ4_1_1_4	0x6c
-#define FLASH_CMD_READ4_1_4_4	0xec
+#define SPINOR_OP_READ4_1_2_2	0xbc
+#define SPINOR_OP_READ4_1_4_4	0xec
 
 /* Configuration flags */
 #define FLASH_FLAG_SINGLE	0x000000ff
diff --git a/drivers/mtd/devices/slram.c b/drivers/mtd/devices/slram.c
index 5a5cd2ace4a..2fc4957cbe7 100644
--- a/drivers/mtd/devices/slram.c
+++ b/drivers/mtd/devices/slram.c
@@ -280,14 +280,11 @@ __setup("slram=", mtd_slram_setup);
 static int __init init_slram(void)
 {
 	char *devname;
-	int i;
 
 #ifndef MODULE
 	char *devstart;
 	char *devlength;
 
-	i = 0;
-
 	if (!map) {
 		E("slram: not enough parameters.\n");
 		return(-EINVAL);
@@ -314,6 +311,7 @@ static int __init init_slram(void)
 	}
 #else
 	int count;
+	int i;
 
 	for (count = 0; count < SLRAM_MAX_DEVICES_PARAMS && map[count];
 			count++) {
diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c
index 1957d7c8e18..d252514d3e9 100644
--- a/drivers/mtd/devices/st_spi_fsm.c
+++ b/drivers/mtd/devices/st_spi_fsm.c
@@ -19,6 +19,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -201,44 +202,6 @@
 
 #define STFSM_MAX_WAIT_SEQ_MS  1000     /* FSM execution time */
 
-/* Flash Commands */
-#define FLASH_CMD_WREN         0x06
-#define FLASH_CMD_WRDI         0x04
-#define FLASH_CMD_RDID         0x9f
-#define FLASH_CMD_RDSR         0x05
-#define FLASH_CMD_RDSR2                0x35
-#define FLASH_CMD_WRSR         0x01
-#define FLASH_CMD_SE_4K                0x20
-#define FLASH_CMD_SE_32K       0x52
-#define FLASH_CMD_SE           0xd8
-#define FLASH_CMD_CHIPERASE    0xc7
-#define FLASH_CMD_WRVCR                0x81
-#define FLASH_CMD_RDVCR                0x85
-
-#define FLASH_CMD_READ         0x03    /* READ */
-#define FLASH_CMD_READ_FAST    0x0b    /* FAST READ */
-#define FLASH_CMD_READ_1_1_2   0x3b    /* DUAL OUTPUT READ */
-#define FLASH_CMD_READ_1_2_2   0xbb    /* DUAL I/O READ */
-#define FLASH_CMD_READ_1_1_4   0x6b    /* QUAD OUTPUT READ */
-#define FLASH_CMD_READ_1_4_4   0xeb    /* QUAD I/O READ */
-
-#define FLASH_CMD_WRITE                0x02    /* PAGE PROGRAM */
-#define FLASH_CMD_WRITE_1_1_2  0xa2    /* DUAL INPUT PROGRAM */
-#define FLASH_CMD_WRITE_1_2_2  0xd2    /* DUAL INPUT EXT PROGRAM */
-#define FLASH_CMD_WRITE_1_1_4  0x32    /* QUAD INPUT PROGRAM */
-#define FLASH_CMD_WRITE_1_4_4  0x12    /* QUAD INPUT EXT PROGRAM */
-
-#define FLASH_CMD_EN4B_ADDR    0xb7    /* Enter 4-byte address mode */
-#define FLASH_CMD_EX4B_ADDR    0xe9    /* Exit 4-byte address mode */
-
-/* READ commands with 32-bit addressing (N25Q256 and S25FLxxxS) */
-#define FLASH_CMD_READ4                0x13
-#define FLASH_CMD_READ4_FAST   0x0c
-#define FLASH_CMD_READ4_1_1_2  0x3c
-#define FLASH_CMD_READ4_1_2_2  0xbc
-#define FLASH_CMD_READ4_1_1_4  0x6c
-#define FLASH_CMD_READ4_1_4_4  0xec
-
 /* S25FLxxxS commands */
 #define S25FL_CMD_WRITE4_1_1_4 0x34
 #define S25FL_CMD_SE4          0xdc
@@ -246,7 +209,7 @@
 #define S25FL_CMD_DYBWR                0xe1
 #define S25FL_CMD_DYBRD                0xe0
 #define S25FL_CMD_WRITE4       0x12    /* Note, opcode clashes with
-					* 'FLASH_CMD_WRITE_1_4_4'
+					* 'SPINOR_OP_WRITE_1_4_4'
 					* as found on N25Qxxx devices! */
 
 /* Status register */
@@ -261,6 +224,12 @@
 #define S25FL_STATUS_E_ERR     0x20
 #define S25FL_STATUS_P_ERR     0x40
 
+#define N25Q_CMD_WRVCR         0x81
+#define N25Q_CMD_RDVCR         0x85
+#define N25Q_CMD_RDVECR        0x65
+#define N25Q_CMD_RDNVCR        0xb5
+#define N25Q_CMD_WRNVCR        0xb1
+
 #define FLASH_PAGESIZE         256			/* In Bytes    */
 #define FLASH_PAGESIZE_32      (FLASH_PAGESIZE / 4)	/* In uint32_t */
 #define FLASH_MAX_BUSY_WAIT    (300 * HZ)	/* Maximum 'CHIPERASE' time */
@@ -270,7 +239,6 @@
  */
 #define CFG_READ_TOGGLE_32BIT_ADDR     0x00000001
 #define CFG_WRITE_TOGGLE_32BIT_ADDR    0x00000002
-#define CFG_WRITE_EX_32BIT_ADDR_DELAY  0x00000004
 #define CFG_ERASESEC_TOGGLE_32BIT_ADDR 0x00000008
 #define CFG_S25FL_CHECK_ERROR_FLAGS    0x00000010
 
@@ -329,7 +297,7 @@ struct flash_info {
 	u32             jedec_id;
 	u16             ext_id;
 	/*
-	 * The size listed here is what works with FLASH_CMD_SE, which isn't
+	 * The size listed here is what works with SPINOR_OP_SE, which isn't
 	 * necessarily called a "sector" by the vendor.
 	 */
 	unsigned        sector_size;
@@ -369,17 +337,26 @@ static struct flash_info flash_types[] = {
 	{ "m25px32", 0x207116, 0,  64 * 1024,  64, M25PX_FLAG, 75, NULL },
 	{ "m25px64", 0x207117, 0,  64 * 1024, 128, M25PX_FLAG, 75, NULL },
 
+	/* Macronix MX25xxx
+	 *     - Support for 'FLASH_FLAG_WRITE_1_4_4' is omitted for devices
+	 *       where operating frequency must be reduced.
+	 */
 #define MX25_FLAG (FLASH_FLAG_READ_WRITE       |	\
 		   FLASH_FLAG_READ_FAST         |	\
 		   FLASH_FLAG_READ_1_1_2        |	\
 		   FLASH_FLAG_READ_1_2_2        |	\
 		   FLASH_FLAG_READ_1_1_4        |	\
-		   FLASH_FLAG_READ_1_4_4        |	\
 		   FLASH_FLAG_SE_4K             |	\
 		   FLASH_FLAG_SE_32K)
+	{ "mx25l3255e",  0xc29e16, 0, 64 * 1024, 64,
+	  (MX25_FLAG | FLASH_FLAG_WRITE_1_4_4), 86,
+	  stfsm_mx25_config},
 	{ "mx25l25635e", 0xc22019, 0, 64*1024, 512,
 	  (MX25_FLAG | FLASH_FLAG_32BIT_ADDR | FLASH_FLAG_RESET), 70,
 	  stfsm_mx25_config },
+	{ "mx25l25655e", 0xc22619, 0, 64*1024, 512,
+	  (MX25_FLAG | FLASH_FLAG_32BIT_ADDR | FLASH_FLAG_RESET), 70,
+	  stfsm_mx25_config},
 
 #define N25Q_FLAG (FLASH_FLAG_READ_WRITE       |	\
 		   FLASH_FLAG_READ_FAST         |	\
@@ -407,6 +384,8 @@ static struct flash_info flash_types[] = {
 			FLASH_FLAG_READ_1_4_4   |	\
 			FLASH_FLAG_WRITE_1_1_4  |	\
 			FLASH_FLAG_READ_FAST)
+	{ "s25fl032p",  0x010215, 0x4d00,  64 * 1024,  64, S25FLXXXP_FLAG, 80,
+	  stfsm_s25fl_config},
 	{ "s25fl129p0", 0x012018, 0x4d00, 256 * 1024,  64, S25FLXXXP_FLAG, 80,
 	  stfsm_s25fl_config },
 	{ "s25fl129p1", 0x012018, 0x4d01,  64 * 1024, 256, S25FLXXXP_FLAG, 80,
@@ -473,22 +452,22 @@ static struct flash_info flash_types[] = {
 
 /* Default READ configurations, in order of preference */
 static struct seq_rw_config default_read_configs[] = {
-	{FLASH_FLAG_READ_1_4_4, FLASH_CMD_READ_1_4_4,	0, 4, 4, 0x00, 2, 4},
-	{FLASH_FLAG_READ_1_1_4, FLASH_CMD_READ_1_1_4,	0, 1, 4, 0x00, 4, 0},
-	{FLASH_FLAG_READ_1_2_2, FLASH_CMD_READ_1_2_2,	0, 2, 2, 0x00, 4, 0},
-	{FLASH_FLAG_READ_1_1_2, FLASH_CMD_READ_1_1_2,	0, 1, 2, 0x00, 0, 8},
-	{FLASH_FLAG_READ_FAST,	FLASH_CMD_READ_FAST,	0, 1, 1, 0x00, 0, 8},
-	{FLASH_FLAG_READ_WRITE, FLASH_CMD_READ,		0, 1, 1, 0x00, 0, 0},
+	{FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ_1_4_4,	0, 4, 4, 0x00, 2, 4},
+	{FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ_1_1_4,	0, 1, 4, 0x00, 4, 0},
+	{FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ_1_2_2,	0, 2, 2, 0x00, 4, 0},
+	{FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ_1_1_2,	0, 1, 2, 0x00, 0, 8},
+	{FLASH_FLAG_READ_FAST,	SPINOR_OP_READ_FAST,	0, 1, 1, 0x00, 0, 8},
+	{FLASH_FLAG_READ_WRITE, SPINOR_OP_READ,		0, 1, 1, 0x00, 0, 0},
 	{0x00,			0,			0, 0, 0, 0x00, 0, 0},
 };
 
 /* Default WRITE configurations */
 static struct seq_rw_config default_write_configs[] = {
-	{FLASH_FLAG_WRITE_1_4_4, FLASH_CMD_WRITE_1_4_4, 1, 4, 4, 0x00, 0, 0},
-	{FLASH_FLAG_WRITE_1_1_4, FLASH_CMD_WRITE_1_1_4, 1, 1, 4, 0x00, 0, 0},
-	{FLASH_FLAG_WRITE_1_2_2, FLASH_CMD_WRITE_1_2_2, 1, 2, 2, 0x00, 0, 0},
-	{FLASH_FLAG_WRITE_1_1_2, FLASH_CMD_WRITE_1_1_2, 1, 1, 2, 0x00, 0, 0},
-	{FLASH_FLAG_READ_WRITE,  FLASH_CMD_WRITE,       1, 1, 1, 0x00, 0, 0},
+	{FLASH_FLAG_WRITE_1_4_4, SPINOR_OP_WRITE_1_4_4, 1, 4, 4, 0x00, 0, 0},
+	{FLASH_FLAG_WRITE_1_1_4, SPINOR_OP_WRITE_1_1_4, 1, 1, 4, 0x00, 0, 0},
+	{FLASH_FLAG_WRITE_1_2_2, SPINOR_OP_WRITE_1_2_2, 1, 2, 2, 0x00, 0, 0},
+	{FLASH_FLAG_WRITE_1_1_2, SPINOR_OP_WRITE_1_1_2, 1, 1, 2, 0x00, 0, 0},
+	{FLASH_FLAG_READ_WRITE,  SPINOR_OP_WRITE,       1, 1, 1, 0x00, 0, 0},
 	{0x00,			 0,			0, 0, 0, 0x00, 0, 0},
 };
 
@@ -511,12 +490,12 @@ static struct seq_rw_config default_write_configs[] = {
  * cycles.
  */
 static struct seq_rw_config n25q_read3_configs[] = {
-	{FLASH_FLAG_READ_1_4_4, FLASH_CMD_READ_1_4_4,	0, 4, 4, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_1_4, FLASH_CMD_READ_1_1_4,	0, 1, 4, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_2_2, FLASH_CMD_READ_1_2_2,	0, 2, 2, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_1_2, FLASH_CMD_READ_1_1_2,	0, 1, 2, 0x00, 0, 8},
-	{FLASH_FLAG_READ_FAST,	FLASH_CMD_READ_FAST,	0, 1, 1, 0x00, 0, 8},
-	{FLASH_FLAG_READ_WRITE, FLASH_CMD_READ,	        0, 1, 1, 0x00, 0, 0},
+	{FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ_1_4_4,	0, 4, 4, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ_1_1_4,	0, 1, 4, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ_1_2_2,	0, 2, 2, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ_1_1_2,	0, 1, 2, 0x00, 0, 8},
+	{FLASH_FLAG_READ_FAST,	SPINOR_OP_READ_FAST,	0, 1, 1, 0x00, 0, 8},
+	{FLASH_FLAG_READ_WRITE, SPINOR_OP_READ,	        0, 1, 1, 0x00, 0, 0},
 	{0x00,			0,			0, 0, 0, 0x00, 0, 0},
 };
 
@@ -526,12 +505,12 @@ static struct seq_rw_config n25q_read3_configs[] = {
  *	- 'FAST' variants configured for 8 dummy cycles (see note above.)
  */
 static struct seq_rw_config n25q_read4_configs[] = {
-	{FLASH_FLAG_READ_1_4_4, FLASH_CMD_READ4_1_4_4,	0, 4, 4, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_1_4, FLASH_CMD_READ4_1_1_4,	0, 1, 4, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_2_2, FLASH_CMD_READ4_1_2_2,	0, 2, 2, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_1_2, FLASH_CMD_READ4_1_1_2,	0, 1, 2, 0x00, 0, 8},
-	{FLASH_FLAG_READ_FAST,	FLASH_CMD_READ4_FAST,	0, 1, 1, 0x00, 0, 8},
-	{FLASH_FLAG_READ_WRITE, FLASH_CMD_READ4,	0, 1, 1, 0x00, 0, 0},
+	{FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ4_1_4_4,	0, 4, 4, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ4_1_1_4,	0, 1, 4, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ4_1_2_2,	0, 2, 2, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ4_1_1_2,	0, 1, 2, 0x00, 0, 8},
+	{FLASH_FLAG_READ_FAST,	SPINOR_OP_READ4_FAST,	0, 1, 1, 0x00, 0, 8},
+	{FLASH_FLAG_READ_WRITE, SPINOR_OP_READ4,	0, 1, 1, 0x00, 0, 0},
 	{0x00,			0,			0, 0, 0, 0x00, 0, 0},
 };
 
@@ -544,7 +523,7 @@ static int stfsm_mx25_en_32bit_addr_seq(struct stfsm_seq *seq)
 {
 	seq->seq_opc[0] = (SEQ_OPC_PADS_1 |
 			   SEQ_OPC_CYCLES(8) |
-			   SEQ_OPC_OPCODE(FLASH_CMD_EN4B_ADDR) |
+			   SEQ_OPC_OPCODE(SPINOR_OP_EN4B) |
 			   SEQ_OPC_CSDEASSERT);
 
 	seq->seq[0] = STFSM_INST_CMD1;
@@ -572,12 +551,12 @@ static int stfsm_mx25_en_32bit_addr_seq(struct stfsm_seq *seq)
  * entering a state that is incompatible with the SPIBoot Controller.
  */
 static struct seq_rw_config stfsm_s25fl_read4_configs[] = {
-	{FLASH_FLAG_READ_1_4_4,  FLASH_CMD_READ4_1_4_4,  0, 4, 4, 0x00, 2, 4},
-	{FLASH_FLAG_READ_1_1_4,  FLASH_CMD_READ4_1_1_4,  0, 1, 4, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_2_2,  FLASH_CMD_READ4_1_2_2,  0, 2, 2, 0x00, 4, 0},
-	{FLASH_FLAG_READ_1_1_2,  FLASH_CMD_READ4_1_1_2,  0, 1, 2, 0x00, 0, 8},
-	{FLASH_FLAG_READ_FAST,   FLASH_CMD_READ4_FAST,   0, 1, 1, 0x00, 0, 8},
-	{FLASH_FLAG_READ_WRITE,  FLASH_CMD_READ4,        0, 1, 1, 0x00, 0, 0},
+	{FLASH_FLAG_READ_1_4_4,  SPINOR_OP_READ4_1_4_4,  0, 4, 4, 0x00, 2, 4},
+	{FLASH_FLAG_READ_1_1_4,  SPINOR_OP_READ4_1_1_4,  0, 1, 4, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_2_2,  SPINOR_OP_READ4_1_2_2,  0, 2, 2, 0x00, 4, 0},
+	{FLASH_FLAG_READ_1_1_2,  SPINOR_OP_READ4_1_1_2,  0, 1, 2, 0x00, 0, 8},
+	{FLASH_FLAG_READ_FAST,   SPINOR_OP_READ4_FAST,   0, 1, 1, 0x00, 0, 8},
+	{FLASH_FLAG_READ_WRITE,  SPINOR_OP_READ4,        0, 1, 1, 0x00, 0, 0},
 	{0x00,                   0,                      0, 0, 0, 0x00, 0, 0},
 };
 
@@ -590,13 +569,13 @@ static struct seq_rw_config stfsm_s25fl_write4_configs[] = {
 /*
  * [W25Qxxx] Configuration
  */
-#define W25Q_STATUS_QE			(0x1 << 9)
+#define W25Q_STATUS_QE			(0x1 << 1)
 
 static struct stfsm_seq stfsm_seq_read_jedec = {
 	.data_size = TRANSFER_SIZE(8),
 	.seq_opc[0] = (SEQ_OPC_PADS_1 |
 		       SEQ_OPC_CYCLES(8) |
-		       SEQ_OPC_OPCODE(FLASH_CMD_RDID)),
+		       SEQ_OPC_OPCODE(SPINOR_OP_RDID)),
 	.seq = {
 		STFSM_INST_CMD1,
 		STFSM_INST_DATA_READ,
@@ -612,7 +591,7 @@ static struct stfsm_seq stfsm_seq_read_status_fifo = {
 	.data_size = TRANSFER_SIZE(4),
 	.seq_opc[0] = (SEQ_OPC_PADS_1 |
 		       SEQ_OPC_CYCLES(8) |
-		       SEQ_OPC_OPCODE(FLASH_CMD_RDSR)),
+		       SEQ_OPC_OPCODE(SPINOR_OP_RDSR)),
 	.seq = {
 		STFSM_INST_CMD1,
 		STFSM_INST_DATA_READ,
@@ -628,10 +607,10 @@ static struct stfsm_seq stfsm_seq_erase_sector = {
 	/* 'addr_cfg' configured during initialisation */
 	.seq_opc = {
 		(SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-		 SEQ_OPC_OPCODE(FLASH_CMD_WREN) | SEQ_OPC_CSDEASSERT),
+		 SEQ_OPC_OPCODE(SPINOR_OP_WREN) | SEQ_OPC_CSDEASSERT),
 
 		(SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-		 SEQ_OPC_OPCODE(FLASH_CMD_SE)),
+		 SEQ_OPC_OPCODE(SPINOR_OP_SE)),
 	},
 	.seq = {
 		STFSM_INST_CMD1,
@@ -649,10 +628,10 @@ static struct stfsm_seq stfsm_seq_erase_sector = {
 static struct stfsm_seq stfsm_seq_erase_chip = {
 	.seq_opc = {
 		(SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-		 SEQ_OPC_OPCODE(FLASH_CMD_WREN) | SEQ_OPC_CSDEASSERT),
+		 SEQ_OPC_OPCODE(SPINOR_OP_WREN) | SEQ_OPC_CSDEASSERT),
 
 		(SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-		 SEQ_OPC_OPCODE(FLASH_CMD_CHIPERASE) | SEQ_OPC_CSDEASSERT),
+		 SEQ_OPC_OPCODE(SPINOR_OP_CHIP_ERASE) | SEQ_OPC_CSDEASSERT),
 	},
 	.seq = {
 		STFSM_INST_CMD1,
@@ -669,26 +648,9 @@ static struct stfsm_seq stfsm_seq_erase_chip = {
 
 static struct stfsm_seq stfsm_seq_write_status = {
 	.seq_opc[0] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-		       SEQ_OPC_OPCODE(FLASH_CMD_WREN) | SEQ_OPC_CSDEASSERT),
-	.seq_opc[1] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-		       SEQ_OPC_OPCODE(FLASH_CMD_WRSR)),
-	.seq = {
-		STFSM_INST_CMD1,
-		STFSM_INST_CMD2,
-		STFSM_INST_STA_WR1,
-		STFSM_INST_STOP,
-	},
-	.seq_cfg = (SEQ_CFG_PADS_1 |
-		    SEQ_CFG_READNOTWRITE |
-		    SEQ_CFG_CSDEASSERT |
-		    SEQ_CFG_STARTSEQ),
-};
-
-static struct stfsm_seq stfsm_seq_wrvcr = {
-	.seq_opc[0] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-		       SEQ_OPC_OPCODE(FLASH_CMD_WREN) | SEQ_OPC_CSDEASSERT),
+		       SEQ_OPC_OPCODE(SPINOR_OP_WREN) | SEQ_OPC_CSDEASSERT),
 	.seq_opc[1] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-		       SEQ_OPC_OPCODE(FLASH_CMD_WRVCR)),
+		       SEQ_OPC_OPCODE(SPINOR_OP_WRSR)),
 	.seq = {
 		STFSM_INST_CMD1,
 		STFSM_INST_CMD2,
@@ -704,9 +666,9 @@ static struct stfsm_seq stfsm_seq_wrvcr = {
 static int stfsm_n25q_en_32bit_addr_seq(struct stfsm_seq *seq)
 {
 	seq->seq_opc[0] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-			   SEQ_OPC_OPCODE(FLASH_CMD_EN4B_ADDR));
+			   SEQ_OPC_OPCODE(SPINOR_OP_EN4B));
 	seq->seq_opc[1] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-			   SEQ_OPC_OPCODE(FLASH_CMD_WREN) |
+			   SEQ_OPC_OPCODE(SPINOR_OP_WREN) |
 			   SEQ_OPC_CSDEASSERT);
 
 	seq->seq[0] = STFSM_INST_CMD2;
@@ -793,7 +755,7 @@ static void stfsm_read_fifo(struct stfsm *fsm, uint32_t *buf, uint32_t size)
 
 	dev_dbg(fsm->dev, "Reading %d bytes from FIFO\n", size);
 
-	BUG_ON((((uint32_t)buf) & 0x3) || (size & 0x3));
+	BUG_ON((((uintptr_t)buf) & 0x3) || (size & 0x3));
 
 	while (remaining) {
 		for (;;) {
@@ -817,7 +779,7 @@ static int stfsm_write_fifo(struct stfsm *fsm, const uint32_t *buf,
 
 	dev_dbg(fsm->dev, "writing %d bytes to FIFO\n", size);
 
-	BUG_ON((((uint32_t)buf) & 0x3) || (size & 0x3));
+	BUG_ON((((uintptr_t)buf) & 0x3) || (size & 0x3));
 
 	writesl(fsm->base + SPI_FAST_SEQ_DATA_REG, buf, words);
 
@@ -827,7 +789,7 @@ static int stfsm_write_fifo(struct stfsm *fsm, const uint32_t *buf,
 static int stfsm_enter_32bit_addr(struct stfsm *fsm, int enter)
 {
 	struct stfsm_seq *seq = &fsm->stfsm_seq_en_32bit_addr;
-	uint32_t cmd = enter ? FLASH_CMD_EN4B_ADDR : FLASH_CMD_EX4B_ADDR;
+	uint32_t cmd = enter ? SPINOR_OP_EN4B : SPINOR_OP_EX4B;
 
 	seq->seq_opc[0] = (SEQ_OPC_PADS_1 |
 			   SEQ_OPC_CYCLES(8) |
@@ -851,7 +813,7 @@ static uint8_t stfsm_wait_busy(struct stfsm *fsm)
 	/* Use RDRS1 */
 	seq->seq_opc[0] = (SEQ_OPC_PADS_1 |
 			   SEQ_OPC_CYCLES(8) |
-			   SEQ_OPC_OPCODE(FLASH_CMD_RDSR));
+			   SEQ_OPC_OPCODE(SPINOR_OP_RDSR));
 
 	/* Load read_status sequence */
 	stfsm_load_seq(fsm, seq);
@@ -889,60 +851,57 @@ static uint8_t stfsm_wait_busy(struct stfsm *fsm)
 }
 
 static int stfsm_read_status(struct stfsm *fsm, uint8_t cmd,
-			   uint8_t *status)
+			     uint8_t *data, int bytes)
 {
 	struct stfsm_seq *seq = &stfsm_seq_read_status_fifo;
 	uint32_t tmp;
+	uint8_t *t = (uint8_t *)&tmp;
+	int i;
 
-	dev_dbg(fsm->dev, "reading STA[%s]\n",
-		(cmd == FLASH_CMD_RDSR) ? "1" : "2");
+	dev_dbg(fsm->dev, "read 'status' register [0x%02x], %d byte(s)\n",
+		cmd, bytes);
 
-	seq->seq_opc[0] = (SEQ_OPC_PADS_1 |
-			   SEQ_OPC_CYCLES(8) |
+	BUG_ON(bytes != 1 && bytes != 2);
+
+	seq->seq_opc[0] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
 			   SEQ_OPC_OPCODE(cmd)),
 
 	stfsm_load_seq(fsm, seq);
 
 	stfsm_read_fifo(fsm, &tmp, 4);
 
-	*status = (uint8_t)(tmp >> 24);
+	for (i = 0; i < bytes; i++)
+		data[i] = t[i];
 
 	stfsm_wait_seq(fsm);
 
 	return 0;
 }
 
-static int stfsm_write_status(struct stfsm *fsm, uint16_t status,
-			       int sta_bytes)
+static int stfsm_write_status(struct stfsm *fsm, uint8_t cmd,
+			    uint16_t data, int bytes, int wait_busy)
 {
 	struct stfsm_seq *seq = &stfsm_seq_write_status;
 
-	dev_dbg(fsm->dev, "writing STA[%s] 0x%04x\n",
-		(sta_bytes == 1) ? "1" : "1+2", status);
-
-	seq->status = (uint32_t)status | STA_PADS_1 | STA_CSDEASSERT;
-	seq->seq[2] = (sta_bytes == 1) ?
-		STFSM_INST_STA_WR1 : STFSM_INST_STA_WR1_2;
-
-	stfsm_load_seq(fsm, seq);
-
-	stfsm_wait_seq(fsm);
+	dev_dbg(fsm->dev,
+		"write 'status' register [0x%02x], %d byte(s), 0x%04x\n"
+		" %s wait-busy\n", cmd, bytes, data, wait_busy ? "with" : "no");
 
-	return 0;
-};
+	BUG_ON(bytes != 1 && bytes != 2);
 
-static int stfsm_wrvcr(struct stfsm *fsm, uint8_t data)
-{
-	struct stfsm_seq *seq = &stfsm_seq_wrvcr;
-
-	dev_dbg(fsm->dev, "writing VCR 0x%02x\n", data);
+	seq->seq_opc[1] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
+			   SEQ_OPC_OPCODE(cmd));
 
-	seq->status = (STA_DATA_BYTE1(data) | STA_PADS_1 | STA_CSDEASSERT);
+	seq->status = (uint32_t)data | STA_PADS_1 | STA_CSDEASSERT;
+	seq->seq[2] = (bytes == 1) ? STFSM_INST_STA_WR1 : STFSM_INST_STA_WR1_2;
 
 	stfsm_load_seq(fsm, seq);
 
 	stfsm_wait_seq(fsm);
 
+	if (wait_busy)
+		stfsm_wait_busy(fsm);
+
 	return 0;
 }
 
@@ -1027,7 +986,7 @@ static void stfsm_prepare_rw_seq(struct stfsm *fsm,
 	if (cfg->write)
 		seq->seq_opc[i++] = (SEQ_OPC_PADS_1 |
 				     SEQ_OPC_CYCLES(8) |
-				     SEQ_OPC_OPCODE(FLASH_CMD_WREN) |
+				     SEQ_OPC_OPCODE(SPINOR_OP_WREN) |
 				     SEQ_OPC_CSDEASSERT);
 
 	/* Address configuration (24 or 32-bit addresses) */
@@ -1149,31 +1108,36 @@ static int stfsm_mx25_config(struct stfsm *fsm)
 		stfsm_mx25_en_32bit_addr_seq(&fsm->stfsm_seq_en_32bit_addr);
 
 		soc_reset = stfsm_can_handle_soc_reset(fsm);
-		if (soc_reset || !fsm->booted_from_spi) {
+		if (soc_reset || !fsm->booted_from_spi)
 			/* If we can handle SoC resets, we enable 32-bit address
 			 * mode pervasively */
 			stfsm_enter_32bit_addr(fsm, 1);
 
-		} else {
+		else
 			/* Else, enable/disable 32-bit addressing before/after
 			 * each operation */
 			fsm->configuration = (CFG_READ_TOGGLE_32BIT_ADDR |
 					      CFG_WRITE_TOGGLE_32BIT_ADDR |
 					      CFG_ERASESEC_TOGGLE_32BIT_ADDR);
-			/* It seems a small delay is required after exiting
-			 * 32-bit mode following a write operation.  The issue
-			 * is under investigation.
-			 */
-			fsm->configuration |= CFG_WRITE_EX_32BIT_ADDR_DELAY;
-		}
 	}
 
-	/* For QUAD mode, set 'QE' STATUS bit */
+	/* Check status of 'QE' bit, update if required. */
+	stfsm_read_status(fsm, SPINOR_OP_RDSR, &sta, 1);
 	data_pads = ((fsm->stfsm_seq_read.seq_cfg >> 16) & 0x3) + 1;
 	if (data_pads == 4) {
-		stfsm_read_status(fsm, FLASH_CMD_RDSR, &sta);
-		sta |= MX25_STATUS_QE;
-		stfsm_write_status(fsm, sta, 1);
+		if (!(sta & MX25_STATUS_QE)) {
+			/* Set 'QE' */
+			sta |= MX25_STATUS_QE;
+
+			stfsm_write_status(fsm, SPINOR_OP_WRSR, sta, 1, 1);
+		}
+	} else {
+		if (sta & MX25_STATUS_QE) {
+			/* Clear 'QE' */
+			sta &= ~MX25_STATUS_QE;
+
+			stfsm_write_status(fsm, SPINOR_OP_WRSR, sta, 1, 1);
+		}
 	}
 
 	return 0;
@@ -1239,7 +1203,7 @@ static int stfsm_n25q_config(struct stfsm *fsm)
 	 */
 	vcr = (N25Q_VCR_DUMMY_CYCLES(8) | N25Q_VCR_XIP_DISABLED |
 	       N25Q_VCR_WRAP_CONT);
-	stfsm_wrvcr(fsm, vcr);
+	stfsm_write_status(fsm, N25Q_CMD_WRVCR, vcr, 1, 0);
 
 	return 0;
 }
@@ -1297,7 +1261,7 @@ static void stfsm_s25fl_write_dyb(struct stfsm *fsm, uint32_t offs, uint8_t dby)
 {
 	struct stfsm_seq seq = {
 		.seq_opc[0] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
-			       SEQ_OPC_OPCODE(FLASH_CMD_WREN) |
+			       SEQ_OPC_OPCODE(SPINOR_OP_WREN) |
 			       SEQ_OPC_CSDEASSERT),
 		.seq_opc[1] = (SEQ_OPC_PADS_1 | SEQ_OPC_CYCLES(8) |
 			       SEQ_OPC_OPCODE(S25FL_CMD_DYBWR)),
@@ -1337,7 +1301,7 @@ static int stfsm_s25fl_clear_status_reg(struct stfsm *fsm)
 			       SEQ_OPC_CSDEASSERT),
 		.seq_opc[1] = (SEQ_OPC_PADS_1 |
 			       SEQ_OPC_CYCLES(8) |
-			       SEQ_OPC_OPCODE(FLASH_CMD_WRDI) |
+			       SEQ_OPC_OPCODE(SPINOR_OP_WRDI) |
 			       SEQ_OPC_CSDEASSERT),
 		.seq = {
 			STFSM_INST_CMD1,
@@ -1367,6 +1331,7 @@ static int stfsm_s25fl_config(struct stfsm *fsm)
 	uint32_t offs;
 	uint16_t sta_wr;
 	uint8_t sr1, cr1, dyb;
+	int update_sr = 0;
 	int ret;
 
 	if (flags & FLASH_FLAG_32BIT_ADDR) {
@@ -1414,34 +1379,28 @@ static int stfsm_s25fl_config(struct stfsm *fsm)
 		}
 	}
 
-	/* Check status of 'QE' bit */
+	/* Check status of 'QE' bit, update if required. */
+	stfsm_read_status(fsm, SPINOR_OP_RDSR2, &cr1, 1);
 	data_pads = ((fsm->stfsm_seq_read.seq_cfg >> 16) & 0x3) + 1;
-	stfsm_read_status(fsm, FLASH_CMD_RDSR2, &cr1);
 	if (data_pads == 4) {
 		if (!(cr1 & STFSM_S25FL_CONFIG_QE)) {
 			/* Set 'QE' */
 			cr1 |= STFSM_S25FL_CONFIG_QE;
 
-			stfsm_read_status(fsm, FLASH_CMD_RDSR, &sr1);
-			sta_wr = ((uint16_t)cr1  << 8) | sr1;
-
-			stfsm_write_status(fsm, sta_wr, 2);
-
-			stfsm_wait_busy(fsm);
+			update_sr = 1;
 		}
 	} else {
-		if ((cr1 & STFSM_S25FL_CONFIG_QE)) {
+		if (cr1 & STFSM_S25FL_CONFIG_QE) {
 			/* Clear 'QE' */
 			cr1 &= ~STFSM_S25FL_CONFIG_QE;
 
-			stfsm_read_status(fsm, FLASH_CMD_RDSR, &sr1);
-			sta_wr = ((uint16_t)cr1  << 8) | sr1;
-
-			stfsm_write_status(fsm, sta_wr, 2);
-
-			stfsm_wait_busy(fsm);
+			update_sr = 1;
 		}
-
+	}
+	if (update_sr) {
+		stfsm_read_status(fsm, SPINOR_OP_RDSR, &sr1, 1);
+		sta_wr = ((uint16_t)cr1  << 8) | sr1;
+		stfsm_write_status(fsm, SPINOR_OP_WRSR, sta_wr, 2, 1);
 	}
 
 	/*
@@ -1456,27 +1415,36 @@ static int stfsm_s25fl_config(struct stfsm *fsm)
 static int stfsm_w25q_config(struct stfsm *fsm)
 {
 	uint32_t data_pads;
-	uint16_t sta_wr;
-	uint8_t sta1, sta2;
+	uint8_t sr1, sr2;
+	uint16_t sr_wr;
+	int update_sr = 0;
 	int ret;
 
 	ret = stfsm_prepare_rwe_seqs_default(fsm);
 	if (ret)
 		return ret;
 
-	/* If using QUAD mode, set QE STATUS bit */
+	/* Check status of 'QE' bit, update if required. */
+	stfsm_read_status(fsm, SPINOR_OP_RDSR2, &sr2, 1);
 	data_pads = ((fsm->stfsm_seq_read.seq_cfg >> 16) & 0x3) + 1;
 	if (data_pads == 4) {
-		stfsm_read_status(fsm, FLASH_CMD_RDSR, &sta1);
-		stfsm_read_status(fsm, FLASH_CMD_RDSR2, &sta2);
-
-		sta_wr = ((uint16_t)sta2 << 8) | sta1;
-
-		sta_wr |= W25Q_STATUS_QE;
-
-		stfsm_write_status(fsm, sta_wr, 2);
-
-		stfsm_wait_busy(fsm);
+		if (!(sr2 & W25Q_STATUS_QE)) {
+			/* Set 'QE' */
+			sr2 |= W25Q_STATUS_QE;
+			update_sr = 1;
+		}
+	} else {
+		if (sr2 & W25Q_STATUS_QE) {
+			/* Clear 'QE' */
+			sr2 &= ~W25Q_STATUS_QE;
+			update_sr = 1;
+		}
+	}
+	if (update_sr) {
+		/* Write status register */
+		stfsm_read_status(fsm, SPINOR_OP_RDSR, &sr1, 1);
+		sr_wr = ((uint16_t)sr2 << 8) | sr1;
+		stfsm_write_status(fsm, SPINOR_OP_WRSR, sr_wr, 2, 1);
 	}
 
 	return 0;
@@ -1506,7 +1474,7 @@ static int stfsm_read(struct stfsm *fsm, uint8_t *buf, uint32_t size,
 	read_mask = (data_pads << 2) - 1;
 
 	/* Handle non-aligned buf */
-	p = ((uint32_t)buf & 0x3) ? (uint8_t *)page_buf : buf;
+	p = ((uintptr_t)buf & 0x3) ? (uint8_t *)page_buf : buf;
 
 	/* Handle non-aligned size */
 	size_ub = (size + read_mask) & ~read_mask;
@@ -1528,7 +1496,7 @@ static int stfsm_read(struct stfsm *fsm, uint8_t *buf, uint32_t size,
 	}
 
 	/* Handle non-aligned buf */
-	if ((uint32_t)buf & 0x3)
+	if ((uintptr_t)buf & 0x3)
 		memcpy(buf, page_buf, size);
 
 	/* Wait for sequence to finish */
@@ -1570,7 +1538,7 @@ static int stfsm_write(struct stfsm *fsm, const uint8_t *buf,
 	write_mask = (data_pads << 2) - 1;
 
 	/* Handle non-aligned buf */
-	if ((uint32_t)buf & 0x3) {
+	if ((uintptr_t)buf & 0x3) {
 		memcpy(page_buf, buf, size);
 		p = (uint8_t *)page_buf;
 	} else {
@@ -1628,11 +1596,8 @@ static int stfsm_write(struct stfsm *fsm, const uint8_t *buf,
 		stfsm_s25fl_clear_status_reg(fsm);
 
 	/* Exit 32-bit address mode, if required */
-	if (fsm->configuration & CFG_WRITE_TOGGLE_32BIT_ADDR) {
+	if (fsm->configuration & CFG_WRITE_TOGGLE_32BIT_ADDR)
 		stfsm_enter_32bit_addr(fsm, 0);
-		if (fsm->configuration & CFG_WRITE_EX_32BIT_ADDR_DELAY)
-			udelay(1);
-	}
 
 	return 0;
 }
@@ -1736,7 +1701,7 @@ static int stfsm_mtd_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 	while (len) {
 		/* Write up to page boundary */
-		bytes = min(FLASH_PAGESIZE - page_offs, len);
+		bytes = min_t(size_t, FLASH_PAGESIZE - page_offs, len);
 
 		ret = stfsm_write(fsm, b, bytes, to);
 		if (ret)
@@ -1935,6 +1900,13 @@ static int stfsm_init(struct stfsm *fsm)
 	       fsm->base + SPI_CONFIGDATA);
 	writel(STFSM_DEFAULT_WR_TIME, fsm->base + SPI_STATUS_WR_TIME_REG);
 
+	/*
+	 * Set the FSM 'WAIT' delay to the minimum workable value.  Note, for
+	 * our purposes, the WAIT instruction is used purely to achieve
+	 * "sequence validity" rather than actually implement a delay.
+	 */
+	writel(0x00000001, fsm->base + SPI_PROGRAM_ERASE_TIME);
+
 	/* Clear FIFO, just in case */
 	stfsm_clear_fifo(fsm);
 
@@ -2086,7 +2058,7 @@ static int stfsm_remove(struct platform_device *pdev)
 	return mtd_device_unregister(&fsm->mtd);
 }
 
-static struct of_device_id stfsm_match[] = {
+static const struct of_device_id stfsm_match[] = {
 	{ .compatible = "st,spi-fsm", },
 	{},
 };
diff --git a/drivers/mtd/lpddr/Kconfig b/drivers/mtd/lpddr/Kconfig
index 265f969817e..3a19cbee24d 100644
--- a/drivers/mtd/lpddr/Kconfig
+++ b/drivers/mtd/lpddr/Kconfig
@@ -1,5 +1,5 @@
-menu "LPDDR flash memory drivers"
-	depends on MTD!=n
+menu "LPDDR & LPDDR2 PCM memory drivers"
+	depends on MTD
 
 config MTD_LPDDR
 	tristate "Support for LPDDR flash chips"
@@ -17,4 +17,13 @@ config MTD_QINFO_PROBE
 	    Window QINFO interface, permits software to be used for entire
 	    families of devices. This serves similar purpose of CFI on legacy
 	    Flash products
+
+config MTD_LPDDR2_NVM
+	# ARM dependency is only for writel_relaxed()
+	depends on MTD && ARM
+	tristate "Support for LPDDR2-NVM flash chips"
+	help
+	  This option enables support of PCM memories with a LPDDR2-NVM
+	  (Low power double data rate 2) interface.
+
 endmenu
diff --git a/drivers/mtd/lpddr/Makefile b/drivers/mtd/lpddr/Makefile
index da48e46b581..881d440d483 100644
--- a/drivers/mtd/lpddr/Makefile
+++ b/drivers/mtd/lpddr/Makefile
@@ -4,3 +4,4 @@
 
 obj-$(CONFIG_MTD_QINFO_PROBE)	+= qinfo_probe.o
 obj-$(CONFIG_MTD_LPDDR)	+= lpddr_cmds.o
+obj-$(CONFIG_MTD_LPDDR2_NVM) += lpddr2_nvm.o
diff --git a/drivers/mtd/lpddr/lpddr2_nvm.c b/drivers/mtd/lpddr/lpddr2_nvm.c
new file mode 100644
index 00000000000..063cec40d0a
--- /dev/null
+++ b/drivers/mtd/lpddr/lpddr2_nvm.c
@@ -0,0 +1,507 @@
+/*
+ * LPDDR2-NVM MTD driver. This module provides read, write, erase, lock/unlock
+ * support for LPDDR2-NVM PCM memories
+ *
+ * Copyright © 2012 Micron Technology, Inc.
+ *
+ * Vincenzo Aliberti <vincenzo.aliberti@gmail.com>
+ * Domenico Manna <domenico.manna@gmail.com>
+ * Many thanks to Andrea Vigilante for initial enabling
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": %s: " fmt, __func__
+
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/mtd/map.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/ioport.h>
+#include <linux/err.h>
+
+/* Parameters */
+#define ERASE_BLOCKSIZE			(0x00020000/2)	/* in Word */
+#define WRITE_BUFFSIZE			(0x00000400/2)	/* in Word */
+#define OW_BASE_ADDRESS			0x00000000	/* OW offset */
+#define BUS_WIDTH			0x00000020	/* x32 devices */
+
+/* PFOW symbols address offset */
+#define PFOW_QUERY_STRING_P		(0x0000/2)	/* in Word */
+#define PFOW_QUERY_STRING_F		(0x0002/2)	/* in Word */
+#define PFOW_QUERY_STRING_O		(0x0004/2)	/* in Word */
+#define PFOW_QUERY_STRING_W		(0x0006/2)	/* in Word */
+
+/* OW registers address */
+#define CMD_CODE_OFS			(0x0080/2)	/* in Word */
+#define CMD_DATA_OFS			(0x0084/2)	/* in Word */
+#define CMD_ADD_L_OFS			(0x0088/2)	/* in Word */
+#define CMD_ADD_H_OFS			(0x008A/2)	/* in Word */
+#define MPR_L_OFS			(0x0090/2)	/* in Word */
+#define MPR_H_OFS			(0x0092/2)	/* in Word */
+#define CMD_EXEC_OFS			(0x00C0/2)	/* in Word */
+#define STATUS_REG_OFS			(0x00CC/2)	/* in Word */
+#define PRG_BUFFER_OFS			(0x0010/2)	/* in Word */
+
+/* Datamask */
+#define MR_CFGMASK			0x8000
+#define SR_OK_DATAMASK			0x0080
+
+/* LPDDR2-NVM Commands */
+#define LPDDR2_NVM_LOCK			0x0061
+#define LPDDR2_NVM_UNLOCK		0x0062
+#define LPDDR2_NVM_SW_PROGRAM		0x0041
+#define LPDDR2_NVM_SW_OVERWRITE		0x0042
+#define LPDDR2_NVM_BUF_PROGRAM		0x00E9
+#define LPDDR2_NVM_BUF_OVERWRITE	0x00EA
+#define LPDDR2_NVM_ERASE		0x0020
+
+/* LPDDR2-NVM Registers offset */
+#define LPDDR2_MODE_REG_DATA		0x0040
+#define LPDDR2_MODE_REG_CFG		0x0050
+
+/*
+ * Internal Type Definitions
+ * pcm_int_data contains memory controller details:
+ * @reg_data : LPDDR2_MODE_REG_DATA register address after remapping
+ * @reg_cfg  : LPDDR2_MODE_REG_CFG register address after remapping
+ * &bus_width: memory bus-width (eg: x16 2 Bytes, x32 4 Bytes)
+ */
+struct pcm_int_data {
+	void __iomem *ctl_regs;
+	int bus_width;
+};
+
+static DEFINE_MUTEX(lpdd2_nvm_mutex);
+
+/*
+ * Build a map_word starting from an u_long
+ */
+static inline map_word build_map_word(u_long myword)
+{
+	map_word val = { {0} };
+	val.x[0] = myword;
+	return val;
+}
+
+/*
+ * Build Mode Register Configuration DataMask based on device bus-width
+ */
+static inline u_int build_mr_cfgmask(u_int bus_width)
+{
+	u_int val = MR_CFGMASK;
+
+	if (bus_width == 0x0004)		/* x32 device */
+		val = val << 16;
+
+	return val;
+}
+
+/*
+ * Build Status Register OK DataMask based on device bus-width
+ */
+static inline u_int build_sr_ok_datamask(u_int bus_width)
+{
+	u_int val = SR_OK_DATAMASK;
+
+	if (bus_width == 0x0004)		/* x32 device */
+		val = (val << 16)+val;
+
+	return val;
+}
+
+/*
+ * Evaluates Overlay Window Control Registers address
+ */
+static inline u_long ow_reg_add(struct map_info *map, u_long offset)
+{
+	u_long val = 0;
+	struct pcm_int_data *pcm_data = map->fldrv_priv;
+
+	val = map->pfow_base + offset*pcm_data->bus_width;
+
+	return val;
+}
+
+/*
+ * Enable lpddr2-nvm Overlay Window
+ * Overlay Window is a memory mapped area containing all LPDDR2-NVM registers
+ * used by device commands as well as uservisible resources like Device Status
+ * Register, Device ID, etc
+ */
+static inline void ow_enable(struct map_info *map)
+{
+	struct pcm_int_data *pcm_data = map->fldrv_priv;
+
+	writel_relaxed(build_mr_cfgmask(pcm_data->bus_width) | 0x18,
+		pcm_data->ctl_regs + LPDDR2_MODE_REG_CFG);
+	writel_relaxed(0x01, pcm_data->ctl_regs + LPDDR2_MODE_REG_DATA);
+}
+
+/*
+ * Disable lpddr2-nvm Overlay Window
+ * Overlay Window is a memory mapped area containing all LPDDR2-NVM registers
+ * used by device commands as well as uservisible resources like Device Status
+ * Register, Device ID, etc
+ */
+static inline void ow_disable(struct map_info *map)
+{
+	struct pcm_int_data *pcm_data = map->fldrv_priv;
+
+	writel_relaxed(build_mr_cfgmask(pcm_data->bus_width) | 0x18,
+		pcm_data->ctl_regs + LPDDR2_MODE_REG_CFG);
+	writel_relaxed(0x02, pcm_data->ctl_regs + LPDDR2_MODE_REG_DATA);
+}
+
+/*
+ * Execute lpddr2-nvm operations
+ */
+static int lpddr2_nvm_do_op(struct map_info *map, u_long cmd_code,
+	u_long cmd_data, u_long cmd_add, u_long cmd_mpr, u_char *buf)
+{
+	map_word add_l = { {0} }, add_h = { {0} }, mpr_l = { {0} },
+		mpr_h = { {0} }, data_l = { {0} }, cmd = { {0} },
+		exec_cmd = { {0} }, sr;
+	map_word data_h = { {0} };	/* only for 2x x16 devices stacked */
+	u_long i, status_reg, prg_buff_ofs;
+	struct pcm_int_data *pcm_data = map->fldrv_priv;
+	u_int sr_ok_datamask = build_sr_ok_datamask(pcm_data->bus_width);
+
+	/* Builds low and high words for OW Control Registers */
+	add_l.x[0]	= cmd_add & 0x0000FFFF;
+	add_h.x[0]	= (cmd_add >> 16) & 0x0000FFFF;
+	mpr_l.x[0]	= cmd_mpr & 0x0000FFFF;
+	mpr_h.x[0]	= (cmd_mpr >> 16) & 0x0000FFFF;
+	cmd.x[0]	= cmd_code & 0x0000FFFF;
+	exec_cmd.x[0]	= 0x0001;
+	data_l.x[0]	= cmd_data & 0x0000FFFF;
+	data_h.x[0]	= (cmd_data >> 16) & 0x0000FFFF; /* only for 2x x16 */
+
+	/* Set Overlay Window Control Registers */
+	map_write(map, cmd, ow_reg_add(map, CMD_CODE_OFS));
+	map_write(map, data_l, ow_reg_add(map, CMD_DATA_OFS));
+	map_write(map, add_l, ow_reg_add(map, CMD_ADD_L_OFS));
+	map_write(map, add_h, ow_reg_add(map, CMD_ADD_H_OFS));
+	map_write(map, mpr_l, ow_reg_add(map, MPR_L_OFS));
+	map_write(map, mpr_h, ow_reg_add(map, MPR_H_OFS));
+	if (pcm_data->bus_width == 0x0004) {	/* 2x16 devices stacked */
+		map_write(map, cmd, ow_reg_add(map, CMD_CODE_OFS) + 2);
+		map_write(map, data_h, ow_reg_add(map, CMD_DATA_OFS) + 2);
+		map_write(map, add_l, ow_reg_add(map, CMD_ADD_L_OFS) + 2);
+		map_write(map, add_h, ow_reg_add(map, CMD_ADD_H_OFS) + 2);
+		map_write(map, mpr_l, ow_reg_add(map, MPR_L_OFS) + 2);
+		map_write(map, mpr_h, ow_reg_add(map, MPR_H_OFS) + 2);
+	}
+
+	/* Fill Program Buffer */
+	if ((cmd_code == LPDDR2_NVM_BUF_PROGRAM) ||
+		(cmd_code == LPDDR2_NVM_BUF_OVERWRITE)) {
+		prg_buff_ofs = (map_read(map,
+			ow_reg_add(map, PRG_BUFFER_OFS))).x[0];
+		for (i = 0; i < cmd_mpr; i++) {
+			map_write(map, build_map_word(buf[i]), map->pfow_base +
+			prg_buff_ofs + i);
+		}
+	}
+
+	/* Command Execute */
+	map_write(map, exec_cmd, ow_reg_add(map, CMD_EXEC_OFS));
+	if (pcm_data->bus_width == 0x0004)	/* 2x16 devices stacked */
+		map_write(map, exec_cmd, ow_reg_add(map, CMD_EXEC_OFS) + 2);
+
+	/* Status Register Check */
+	do {
+		sr = map_read(map, ow_reg_add(map, STATUS_REG_OFS));
+		status_reg = sr.x[0];
+		if (pcm_data->bus_width == 0x0004) {/* 2x16 devices stacked */
+			sr = map_read(map, ow_reg_add(map,
+				STATUS_REG_OFS) + 2);
+			status_reg += sr.x[0] << 16;
+		}
+	} while ((status_reg & sr_ok_datamask) != sr_ok_datamask);
+
+	return (((status_reg & sr_ok_datamask) == sr_ok_datamask) ? 0 : -EIO);
+}
+
+/*
+ * Execute lpddr2-nvm operations @ block level
+ */
+static int lpddr2_nvm_do_block_op(struct mtd_info *mtd, loff_t start_add,
+	uint64_t len, u_char block_op)
+{
+	struct map_info *map = mtd->priv;
+	u_long add, end_add;
+	int ret = 0;
+
+	mutex_lock(&lpdd2_nvm_mutex);
+
+	ow_enable(map);
+
+	add = start_add;
+	end_add = add + len;
+
+	do {
+		ret = lpddr2_nvm_do_op(map, block_op, 0x00, add, add, NULL);
+		if (ret)
+			goto out;
+		add += mtd->erasesize;
+	} while (add < end_add);
+
+out:
+	ow_disable(map);
+	mutex_unlock(&lpdd2_nvm_mutex);
+	return ret;
+}
+
+/*
+ * verify presence of PFOW string
+ */
+static int lpddr2_nvm_pfow_present(struct map_info *map)
+{
+	map_word pfow_val[4];
+	unsigned int found = 1;
+
+	mutex_lock(&lpdd2_nvm_mutex);
+
+	ow_enable(map);
+
+	/* Load string from array */
+	pfow_val[0] = map_read(map, ow_reg_add(map, PFOW_QUERY_STRING_P));
+	pfow_val[1] = map_read(map, ow_reg_add(map, PFOW_QUERY_STRING_F));
+	pfow_val[2] = map_read(map, ow_reg_add(map, PFOW_QUERY_STRING_O));
+	pfow_val[3] = map_read(map, ow_reg_add(map, PFOW_QUERY_STRING_W));
+
+	/* Verify the string loaded vs expected */
+	if (!map_word_equal(map, build_map_word('P'), pfow_val[0]))
+		found = 0;
+	if (!map_word_equal(map, build_map_word('F'), pfow_val[1]))
+		found = 0;
+	if (!map_word_equal(map, build_map_word('O'), pfow_val[2]))
+		found = 0;
+	if (!map_word_equal(map, build_map_word('W'), pfow_val[3]))
+		found = 0;
+
+	ow_disable(map);
+
+	mutex_unlock(&lpdd2_nvm_mutex);
+
+	return found;
+}
+
+/*
+ * lpddr2_nvm driver read method
+ */
+static int lpddr2_nvm_read(struct mtd_info *mtd, loff_t start_add,
+				size_t len, size_t *retlen, u_char *buf)
+{
+	struct map_info *map = mtd->priv;
+
+	mutex_lock(&lpdd2_nvm_mutex);
+
+	*retlen = len;
+
+	map_copy_from(map, buf, start_add, *retlen);
+
+	mutex_unlock(&lpdd2_nvm_mutex);
+	return 0;
+}
+
+/*
+ * lpddr2_nvm driver write method
+ */
+static int lpddr2_nvm_write(struct mtd_info *mtd, loff_t start_add,
+				size_t len, size_t *retlen, const u_char *buf)
+{
+	struct map_info *map = mtd->priv;
+	struct pcm_int_data *pcm_data = map->fldrv_priv;
+	u_long add, current_len, tot_len, target_len, my_data;
+	u_char *write_buf = (u_char *)buf;
+	int ret = 0;
+
+	mutex_lock(&lpdd2_nvm_mutex);
+
+	ow_enable(map);
+
+	/* Set start value for the variables */
+	add = start_add;
+	target_len = len;
+	tot_len = 0;
+
+	while (tot_len < target_len) {
+		if (!(IS_ALIGNED(add, mtd->writesize))) { /* do sw program */
+			my_data = write_buf[tot_len];
+			my_data += (write_buf[tot_len+1]) << 8;
+			if (pcm_data->bus_width == 0x0004) {/* 2x16 devices */
+				my_data += (write_buf[tot_len+2]) << 16;
+				my_data += (write_buf[tot_len+3]) << 24;
+			}
+			ret = lpddr2_nvm_do_op(map, LPDDR2_NVM_SW_OVERWRITE,
+				my_data, add, 0x00, NULL);
+			if (ret)
+				goto out;
+
+			add += pcm_data->bus_width;
+			tot_len += pcm_data->bus_width;
+		} else {		/* do buffer program */
+			current_len = min(target_len - tot_len,
+				(u_long) mtd->writesize);
+			ret = lpddr2_nvm_do_op(map, LPDDR2_NVM_BUF_OVERWRITE,
+				0x00, add, current_len, write_buf + tot_len);
+			if (ret)
+				goto out;
+
+			add += current_len;
+			tot_len += current_len;
+		}
+	}
+
+out:
+	*retlen = tot_len;
+	ow_disable(map);
+	mutex_unlock(&lpdd2_nvm_mutex);
+	return ret;
+}
+
+/*
+ * lpddr2_nvm driver erase method
+ */
+static int lpddr2_nvm_erase(struct mtd_info *mtd, struct erase_info *instr)
+{
+	int ret = lpddr2_nvm_do_block_op(mtd, instr->addr, instr->len,
+		LPDDR2_NVM_ERASE);
+	if (!ret) {
+		instr->state = MTD_ERASE_DONE;
+		mtd_erase_callback(instr);
+	}
+
+	return ret;
+}
+
+/*
+ * lpddr2_nvm driver unlock method
+ */
+static int lpddr2_nvm_unlock(struct mtd_info *mtd, loff_t start_add,
+	uint64_t len)
+{
+	return lpddr2_nvm_do_block_op(mtd, start_add, len, LPDDR2_NVM_UNLOCK);
+}
+
+/*
+ * lpddr2_nvm driver lock method
+ */
+static int lpddr2_nvm_lock(struct mtd_info *mtd, loff_t start_add,
+	uint64_t len)
+{
+	return lpddr2_nvm_do_block_op(mtd, start_add, len, LPDDR2_NVM_LOCK);
+}
+
+/*
+ * lpddr2_nvm driver probe method
+ */
+static int lpddr2_nvm_probe(struct platform_device *pdev)
+{
+	struct map_info *map;
+	struct mtd_info *mtd;
+	struct resource *add_range;
+	struct resource *control_regs;
+	struct pcm_int_data *pcm_data;
+
+	/* Allocate memory control_regs data structures */
+	pcm_data = devm_kzalloc(&pdev->dev, sizeof(*pcm_data), GFP_KERNEL);
+	if (!pcm_data)
+		return -ENOMEM;
+
+	pcm_data->bus_width = BUS_WIDTH;
+
+	/* Allocate memory for map_info & mtd_info data structures */
+	map = devm_kzalloc(&pdev->dev, sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+
+	mtd = devm_kzalloc(&pdev->dev, sizeof(*mtd), GFP_KERNEL);
+	if (!mtd)
+		return -ENOMEM;
+
+	/* lpddr2_nvm address range */
+	add_range = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	/* Populate map_info data structure */
+	*map = (struct map_info) {
+		.virt		= devm_ioremap_resource(&pdev->dev, add_range),
+		.name		= pdev->dev.init_name,
+		.phys		= add_range->start,
+		.size		= resource_size(add_range),
+		.bankwidth	= pcm_data->bus_width / 2,
+		.pfow_base	= OW_BASE_ADDRESS,
+		.fldrv_priv	= pcm_data,
+	};
+	if (IS_ERR(map->virt))
+		return PTR_ERR(map->virt);
+
+	simple_map_init(map);	/* fill with default methods */
+
+	control_regs = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	pcm_data->ctl_regs = devm_ioremap_resource(&pdev->dev, control_regs);
+	if (IS_ERR(pcm_data->ctl_regs))
+		return PTR_ERR(pcm_data->ctl_regs);
+
+	/* Populate mtd_info data structure */
+	*mtd = (struct mtd_info) {
+		.name		= pdev->dev.init_name,
+		.type		= MTD_RAM,
+		.priv		= map,
+		.size		= resource_size(add_range),
+		.erasesize	= ERASE_BLOCKSIZE * pcm_data->bus_width,
+		.writesize	= 1,
+		.writebufsize	= WRITE_BUFFSIZE * pcm_data->bus_width,
+		.flags		= (MTD_CAP_NVRAM | MTD_POWERUP_LOCK),
+		._read		= lpddr2_nvm_read,
+		._write		= lpddr2_nvm_write,
+		._erase		= lpddr2_nvm_erase,
+		._unlock	= lpddr2_nvm_unlock,
+		._lock		= lpddr2_nvm_lock,
+	};
+
+	/* Verify the presence of the device looking for PFOW string */
+	if (!lpddr2_nvm_pfow_present(map)) {
+		pr_err("device not recognized\n");
+		return -EINVAL;
+	}
+	/* Parse partitions and register the MTD device */
+	return mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+}
+
+/*
+ * lpddr2_nvm driver remove method
+ */
+static int lpddr2_nvm_remove(struct platform_device *pdev)
+{
+	return mtd_device_unregister(dev_get_drvdata(&pdev->dev));
+}
+
+/* Initialize platform_driver data structure for lpddr2_nvm */
+static struct platform_driver lpddr2_nvm_drv = {
+	.driver		= {
+		.name	= "lpddr2_nvm",
+	},
+	.probe		= lpddr2_nvm_probe,
+	.remove		= lpddr2_nvm_remove,
+};
+
+module_platform_driver(lpddr2_nvm_drv);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vincenzo Aliberti <vincenzo.aliberti@gmail.com>");
+MODULE_DESCRIPTION("MTD driver for LPDDR2-NVM PCM memories");
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index fce23fe043f..21b2874a303 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -108,7 +108,7 @@ config MTD_SUN_UFLASH
 
 config MTD_SC520CDP
 	tristate "CFI Flash device mapped on AMD SC520 CDP"
-	depends on X86 && MTD_CFI
+	depends on (MELAN || COMPILE_TEST) && MTD_CFI
 	help
 	  The SC520 CDP board has two banks of CFI-compliant chips and one
 	  Dual-in-line JEDEC chip. This 'mapping' driver supports that
@@ -116,7 +116,7 @@ config MTD_SC520CDP
 
 config MTD_NETSC520
 	tristate "CFI Flash device mapped on AMD NetSc520"
-	depends on X86 && MTD_CFI
+	depends on (MELAN || COMPILE_TEST) && MTD_CFI
 	help
 	  This enables access routines for the flash chips on the AMD NetSc520
 	  demonstration board. If you have one of these boards and would like
diff --git a/drivers/mtd/maps/sc520cdp.c b/drivers/mtd/maps/sc520cdp.c
index 8fead8e46bc..093edd51bdc 100644
--- a/drivers/mtd/maps/sc520cdp.c
+++ b/drivers/mtd/maps/sc520cdp.c
@@ -183,7 +183,7 @@ static const struct sc520_par_table par_table[NUM_FLASH_BANKS] =
 
 static void sc520cdp_setup_par(void)
 {
-	volatile unsigned long __iomem *mmcr;
+	unsigned long __iomem *mmcr;
 	unsigned long mmcr_val;
 	int i, j;
 
@@ -203,11 +203,11 @@ static void sc520cdp_setup_par(void)
 	*/
 	for(i = 0; i < NUM_FLASH_BANKS; i++) {		/* for each par_table entry  */
 		for(j = 0; j < NUM_SC520_PAR; j++) {	/* for each PAR register     */
-			mmcr_val = mmcr[SC520_PAR(j)];
+			mmcr_val = readl(&mmcr[SC520_PAR(j)]);
 			/* if target device field matches, reprogram the PAR */
 			if((mmcr_val & SC520_PAR_TRGDEV) == par_table[i].trgdev)
 			{
-				mmcr[SC520_PAR(j)] = par_table[i].new_par;
+				writel(par_table[i].new_par, &mmcr[SC520_PAR(j)]);
 				break;
 			}
 		}
diff --git a/drivers/mtd/maps/solutionengine.c b/drivers/mtd/maps/solutionengine.c
index 83a7a709156..bb580bc1644 100644
--- a/drivers/mtd/maps/solutionengine.c
+++ b/drivers/mtd/maps/solutionengine.c
@@ -33,28 +33,6 @@ struct map_info soleng_flash_map = {
 
 static const char * const probes[] = { "RedBoot", "cmdlinepart", NULL };
 
-#ifdef CONFIG_MTD_SUPERH_RESERVE
-static struct mtd_partition superh_se_partitions[] = {
-	/* Reserved for boot code, read-only */
-	{
-		.name = "flash_boot",
-		.offset = 0x00000000,
-		.size = CONFIG_MTD_SUPERH_RESERVE,
-		.mask_flags = MTD_WRITEABLE,
-	},
-	/* All else is writable (e.g. JFFS) */
-	{
-		.name = "Flash FS",
-		.offset = MTDPART_OFS_NXTBLK,
-		.size = MTDPART_SIZ_FULL,
-	}
-};
-#define NUM_PARTITIONS ARRAY_SIZE(superh_se_partitions)
-#else
-#define superh_se_partitions NULL
-#define NUM_PARTITIONS 0
-#endif /* CONFIG_MTD_SUPERH_RESERVE */
-
 static int __init init_soleng_maps(void)
 {
 	/* First probe at offset 0 */
@@ -92,8 +70,7 @@ static int __init init_soleng_maps(void)
 		mtd_device_register(eprom_mtd, NULL, 0);
 	}
 
-	mtd_device_parse_register(flash_mtd, probes, NULL,
-				  superh_se_partitions, NUM_PARTITIONS);
+	mtd_device_parse_register(flash_mtd, probes, NULL, NULL, 0);
 
 	return 0;
 }
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 4dbfaee9aa9..43e30992a36 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -87,6 +87,9 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 	if (req->cmd_type != REQ_TYPE_FS)
 		return -EIO;
 
+	if (req->cmd_flags & REQ_FLUSH)
+		return tr->flush(dev);
+
 	if (blk_rq_pos(req) + blk_rq_cur_sectors(req) >
 	    get_capacity(req->rq_disk))
 		return -EIO;
@@ -407,6 +410,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
 	if (!new->rq)
 		goto error3;
 
+	if (tr->flush)
+		blk_queue_flush(new->rq, REQ_FLUSH);
+
 	new->rq->queuedata = new;
 	blk_queue_logical_block_size(new->rq, tr->blksize);
 
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 7d4e7b9da3a..a0f54e80670 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -568,13 +568,18 @@ static int mtdchar_write_ioctl(struct mtd_info *mtd,
 {
 	struct mtd_write_req req;
 	struct mtd_oob_ops ops;
-	void __user *usr_data, *usr_oob;
+	const void __user *usr_data, *usr_oob;
 	int ret;
 
-	if (copy_from_user(&req, argp, sizeof(req)) ||
-			!access_ok(VERIFY_READ, req.usr_data, req.len) ||
-			!access_ok(VERIFY_READ, req.usr_oob, req.ooblen))
+	if (copy_from_user(&req, argp, sizeof(req)))
 		return -EFAULT;
+
+	usr_data = (const void __user *)(uintptr_t)req.usr_data;
+	usr_oob = (const void __user *)(uintptr_t)req.usr_oob;
+	if (!access_ok(VERIFY_READ, usr_data, req.len) ||
+	    !access_ok(VERIFY_READ, usr_oob, req.ooblen))
+		return -EFAULT;
+
 	if (!mtd->_write_oob)
 		return -EOPNOTSUPP;
 
@@ -583,10 +588,7 @@ static int mtdchar_write_ioctl(struct mtd_info *mtd,
 	ops.ooblen = (size_t)req.ooblen;
 	ops.ooboffs = 0;
 
-	usr_data = (void __user *)(uintptr_t)req.usr_data;
-	usr_oob = (void __user *)(uintptr_t)req.usr_oob;
-
-	if (req.usr_data) {
+	if (usr_data) {
 		ops.datbuf = memdup_user(usr_data, ops.len);
 		if (IS_ERR(ops.datbuf))
 			return PTR_ERR(ops.datbuf);
@@ -594,7 +596,7 @@ static int mtdchar_write_ioctl(struct mtd_info *mtd,
 		ops.datbuf = NULL;
 	}
 
-	if (req.usr_oob) {
+	if (usr_oob) {
 		ops.oobbuf = memdup_user(usr_oob, ops.ooblen);
 		if (IS_ERR(ops.oobbuf)) {
 			kfree(ops.datbuf);
diff --git a/drivers/mtd/nand/bf5xx_nand.c b/drivers/mtd/nand/bf5xx_nand.c
index b7a24946ca2..722898aea7a 100644
--- a/drivers/mtd/nand/bf5xx_nand.c
+++ b/drivers/mtd/nand/bf5xx_nand.c
@@ -679,9 +679,6 @@ static int bf5xx_nand_remove(struct platform_device *pdev)
 	peripheral_free_list(bfin_nfc_pin_req);
 	bf5xx_nand_dma_remove(info);
 
-	/* free the common resources */
-	kfree(info);
-
 	return 0;
 }
 
@@ -742,10 +739,10 @@ static int bf5xx_nand_probe(struct platform_device *pdev)
 		return -EFAULT;
 	}
 
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
 	if (info == NULL) {
 		err = -ENOMEM;
-		goto out_err_kzalloc;
+		goto out_err;
 	}
 
 	platform_set_drvdata(pdev, info);
@@ -790,7 +787,7 @@ static int bf5xx_nand_probe(struct platform_device *pdev)
 	/* initialise the hardware */
 	err = bf5xx_nand_hw_init(info);
 	if (err)
-		goto out_err_hw_init;
+		goto out_err;
 
 	/* setup hardware ECC data struct */
 	if (hardware_ecc) {
@@ -827,9 +824,7 @@ static int bf5xx_nand_probe(struct platform_device *pdev)
 
 out_err_nand_scan:
 	bf5xx_nand_dma_remove(info);
-out_err_hw_init:
-	kfree(info);
-out_err_kzalloc:
+out_err:
 	peripheral_free_list(bfin_nfc_pin_req);
 
 	return err;
diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c
index c07cd573ad3..9f2012a3e76 100644
--- a/drivers/mtd/nand/denali.c
+++ b/drivers/mtd/nand/denali.c
@@ -1233,7 +1233,7 @@ static int denali_waitfunc(struct mtd_info *mtd, struct nand_chip *chip)
 	return status;
 }
 
-static void denali_erase(struct mtd_info *mtd, int page)
+static int denali_erase(struct mtd_info *mtd, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
 
@@ -1250,8 +1250,7 @@ static void denali_erase(struct mtd_info *mtd, int page)
 	irq_status = wait_for_irq(denali, INTR_STATUS__ERASE_COMP |
 					INTR_STATUS__ERASE_FAIL);
 
-	denali->status = (irq_status & INTR_STATUS__ERASE_FAIL) ?
-						NAND_STATUS_FAIL : PASS;
+	return (irq_status & INTR_STATUS__ERASE_FAIL) ? NAND_STATUS_FAIL : PASS;
 }
 
 static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col,
@@ -1584,7 +1583,7 @@ int denali_init(struct denali_nand_info *denali)
 	denali->nand.ecc.write_page_raw = denali_write_page_raw;
 	denali->nand.ecc.read_oob = denali_read_oob;
 	denali->nand.ecc.write_oob = denali_write_oob;
-	denali->nand.erase_cmd = denali_erase;
+	denali->nand.erase = denali_erase;
 
 	if (nand_scan_tail(&denali->mtd)) {
 		ret = -ENXIO;
diff --git a/drivers/mtd/nand/docg4.c b/drivers/mtd/nand/docg4.c
index 1b0265e85a0..ce24637e14f 100644
--- a/drivers/mtd/nand/docg4.c
+++ b/drivers/mtd/nand/docg4.c
@@ -872,7 +872,7 @@ static int docg4_read_oob(struct mtd_info *mtd, struct nand_chip *nand,
 	return 0;
 }
 
-static void docg4_erase_block(struct mtd_info *mtd, int page)
+static int docg4_erase_block(struct mtd_info *mtd, int page)
 {
 	struct nand_chip *nand = mtd->priv;
 	struct docg4_priv *doc = nand->priv;
@@ -916,6 +916,8 @@ static void docg4_erase_block(struct mtd_info *mtd, int page)
 	write_nop(docptr);
 	poll_status(doc);
 	write_nop(docptr);
+
+	return nand->waitfunc(mtd, nand);
 }
 
 static int write_page(struct mtd_info *mtd, struct nand_chip *nand,
@@ -1236,7 +1238,7 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	nand->block_markbad = docg4_block_markbad;
 	nand->read_buf = docg4_read_buf;
 	nand->write_buf = docg4_write_buf16;
-	nand->erase_cmd = docg4_erase_block;
+	nand->erase = docg4_erase_block;
 	nand->ecc.read_page = docg4_read_page;
 	nand->ecc.write_page = docg4_write_page;
 	nand->ecc.read_page_raw = docg4_read_page_raw;
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index ec549cd9849..545a5c002f0 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -723,6 +723,19 @@ static int fsl_elbc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return 0;
 }
 
+/* ECC will be calculated automatically, and errors will be detected in
+ * waitfunc.
+ */
+static int fsl_elbc_write_subpage(struct mtd_info *mtd, struct nand_chip *chip,
+				uint32_t offset, uint32_t data_len,
+				const uint8_t *buf, int oob_required)
+{
+	fsl_elbc_write_buf(mtd, buf, mtd->writesize);
+	fsl_elbc_write_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+	return 0;
+}
+
 static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 {
 	struct fsl_lbc_ctrl *ctrl = priv->ctrl;
@@ -761,6 +774,7 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 
 	chip->ecc.read_page = fsl_elbc_read_page;
 	chip->ecc.write_page = fsl_elbc_write_page;
+	chip->ecc.write_subpage = fsl_elbc_write_subpage;
 
 	/* If CS Base Register selects full hardware ECC then use it */
 	if ((in_be32(&lbc->bank[priv->bank].br) & BR_DECC) ==
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index cb45d2f8e20..2338124dd05 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -56,7 +56,7 @@ struct fsl_ifc_nand_ctrl {
 	struct nand_hw_control controller;
 	struct fsl_ifc_mtd *chips[FSL_IFC_BANK_COUNT];
 
-	u8 __iomem *addr;	/* Address of assigned IFC buffer	*/
+	void __iomem *addr;	/* Address of assigned IFC buffer	*/
 	unsigned int page;	/* Last page written to / read from	*/
 	unsigned int read_bytes;/* Number of bytes read during command	*/
 	unsigned int column;	/* Saved column from SEQIN		*/
@@ -591,7 +591,10 @@ static void fsl_ifc_cmdfunc(struct mtd_info *mtd, unsigned int command,
 		 * The chip always seems to report that it is
 		 * write-protected, even when it is not.
 		 */
-		setbits8(ifc_nand_ctrl->addr, NAND_STATUS_WP);
+		if (chip->options & NAND_BUSWIDTH_16)
+			setbits16(ifc_nand_ctrl->addr, NAND_STATUS_WP);
+		else
+			setbits8(ifc_nand_ctrl->addr, NAND_STATUS_WP);
 		return;
 
 	case NAND_CMD_RESET:
@@ -636,7 +639,7 @@ static void fsl_ifc_write_buf(struct mtd_info *mtd, const u8 *buf, int len)
 		len = bufsize - ifc_nand_ctrl->index;
 	}
 
-	memcpy_toio(&ifc_nand_ctrl->addr[ifc_nand_ctrl->index], buf, len);
+	memcpy_toio(ifc_nand_ctrl->addr + ifc_nand_ctrl->index, buf, len);
 	ifc_nand_ctrl->index += len;
 }
 
@@ -648,13 +651,16 @@ static uint8_t fsl_ifc_read_byte(struct mtd_info *mtd)
 {
 	struct nand_chip *chip = mtd->priv;
 	struct fsl_ifc_mtd *priv = chip->priv;
+	unsigned int offset;
 
 	/*
 	 * If there are still bytes in the IFC buffer, then use the
 	 * next byte.
 	 */
-	if (ifc_nand_ctrl->index < ifc_nand_ctrl->read_bytes)
-		return in_8(&ifc_nand_ctrl->addr[ifc_nand_ctrl->index++]);
+	if (ifc_nand_ctrl->index < ifc_nand_ctrl->read_bytes) {
+		offset = ifc_nand_ctrl->index++;
+		return in_8(ifc_nand_ctrl->addr + offset);
+	}
 
 	dev_err(priv->dev, "%s: beyond end of buffer\n", __func__);
 	return ERR_BYTE;
@@ -675,8 +681,7 @@ static uint8_t fsl_ifc_read_byte16(struct mtd_info *mtd)
 	 * next byte.
 	 */
 	if (ifc_nand_ctrl->index < ifc_nand_ctrl->read_bytes) {
-		data = in_be16((uint16_t __iomem *)&ifc_nand_ctrl->
-			       addr[ifc_nand_ctrl->index]);
+		data = in_be16(ifc_nand_ctrl->addr + ifc_nand_ctrl->index);
 		ifc_nand_ctrl->index += 2;
 		return (uint8_t) data;
 	}
@@ -701,7 +706,7 @@ static void fsl_ifc_read_buf(struct mtd_info *mtd, u8 *buf, int len)
 
 	avail = min((unsigned int)len,
 			ifc_nand_ctrl->read_bytes - ifc_nand_ctrl->index);
-	memcpy_fromio(buf, &ifc_nand_ctrl->addr[ifc_nand_ctrl->index], avail);
+	memcpy_fromio(buf, ifc_nand_ctrl->addr + ifc_nand_ctrl->index, avail);
 	ifc_nand_ctrl->index += avail;
 
 	if (len > avail)
diff --git a/drivers/mtd/nand/gpmi-nand/bch-regs.h b/drivers/mtd/nand/gpmi-nand/bch-regs.h
index 588f5374047..05bb91f2f4c 100644
--- a/drivers/mtd/nand/gpmi-nand/bch-regs.h
+++ b/drivers/mtd/nand/gpmi-nand/bch-regs.h
@@ -54,7 +54,7 @@
 #define MX6Q_BP_BCH_FLASH0LAYOUT0_ECC0		11
 #define MX6Q_BM_BCH_FLASH0LAYOUT0_ECC0	(0x1f << MX6Q_BP_BCH_FLASH0LAYOUT0_ECC0)
 #define BF_BCH_FLASH0LAYOUT0_ECC0(v, x)				\
-	(GPMI_IS_MX6Q(x)					\
+	(GPMI_IS_MX6(x)					\
 		? (((v) << MX6Q_BP_BCH_FLASH0LAYOUT0_ECC0)	\
 			& MX6Q_BM_BCH_FLASH0LAYOUT0_ECC0)	\
 		: (((v) << BP_BCH_FLASH0LAYOUT0_ECC0)		\
@@ -65,7 +65,7 @@
 #define MX6Q_BM_BCH_FLASH0LAYOUT0_GF_13_14			\
 				(0x1 << MX6Q_BP_BCH_FLASH0LAYOUT0_GF_13_14)
 #define BF_BCH_FLASH0LAYOUT0_GF(v, x)				\
-	((GPMI_IS_MX6Q(x) && ((v) == 14))			\
+	((GPMI_IS_MX6(x) && ((v) == 14))			\
 		? (((1) << MX6Q_BP_BCH_FLASH0LAYOUT0_GF_13_14)	\
 			& MX6Q_BM_BCH_FLASH0LAYOUT0_GF_13_14)	\
 		: 0						\
@@ -77,7 +77,7 @@
 #define MX6Q_BM_BCH_FLASH0LAYOUT0_DATA0_SIZE	\
 			(0x3ff << BP_BCH_FLASH0LAYOUT0_DATA0_SIZE)
 #define BF_BCH_FLASH0LAYOUT0_DATA0_SIZE(v, x)				\
-	(GPMI_IS_MX6Q(x)						\
+	(GPMI_IS_MX6(x)						\
 		? (((v) >> 2) & MX6Q_BM_BCH_FLASH0LAYOUT0_DATA0_SIZE)	\
 		: ((v) & BM_BCH_FLASH0LAYOUT0_DATA0_SIZE)		\
 	)
@@ -96,7 +96,7 @@
 #define MX6Q_BP_BCH_FLASH0LAYOUT1_ECCN		11
 #define MX6Q_BM_BCH_FLASH0LAYOUT1_ECCN	(0x1f << MX6Q_BP_BCH_FLASH0LAYOUT1_ECCN)
 #define BF_BCH_FLASH0LAYOUT1_ECCN(v, x)				\
-	(GPMI_IS_MX6Q(x)					\
+	(GPMI_IS_MX6(x)					\
 		? (((v) << MX6Q_BP_BCH_FLASH0LAYOUT1_ECCN)	\
 			& MX6Q_BM_BCH_FLASH0LAYOUT1_ECCN)	\
 		: (((v) << BP_BCH_FLASH0LAYOUT1_ECCN)		\
@@ -107,7 +107,7 @@
 #define MX6Q_BM_BCH_FLASH0LAYOUT1_GF_13_14			\
 				(0x1 << MX6Q_BP_BCH_FLASH0LAYOUT1_GF_13_14)
 #define BF_BCH_FLASH0LAYOUT1_GF(v, x)				\
-	((GPMI_IS_MX6Q(x) && ((v) == 14))			\
+	((GPMI_IS_MX6(x) && ((v) == 14))			\
 		? (((1) << MX6Q_BP_BCH_FLASH0LAYOUT1_GF_13_14)	\
 			& MX6Q_BM_BCH_FLASH0LAYOUT1_GF_13_14)	\
 		: 0						\
@@ -119,7 +119,7 @@
 #define MX6Q_BM_BCH_FLASH0LAYOUT1_DATAN_SIZE	\
 			(0x3ff << BP_BCH_FLASH0LAYOUT1_DATAN_SIZE)
 #define BF_BCH_FLASH0LAYOUT1_DATAN_SIZE(v, x)				\
-	(GPMI_IS_MX6Q(x)						\
+	(GPMI_IS_MX6(x)						\
 		? (((v) >> 2) & MX6Q_BM_BCH_FLASH0LAYOUT1_DATAN_SIZE)	\
 		: ((v) & BM_BCH_FLASH0LAYOUT1_DATAN_SIZE)		\
 	)
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
index dd1df605a1d..87e658ce23e 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
@@ -861,7 +861,7 @@ static void gpmi_compute_edo_timing(struct gpmi_nand_data *this,
 	struct resources *r = &this->resources;
 	unsigned long rate = clk_get_rate(r->clock[0]);
 	int mode = this->timing_mode;
-	int dll_threshold = 16; /* in ns */
+	int dll_threshold = this->devdata->max_chain_delay;
 	unsigned long delay;
 	unsigned long clk_period;
 	int t_rea;
@@ -886,9 +886,6 @@ static void gpmi_compute_edo_timing(struct gpmi_nand_data *this,
 	/* [3] for GPMI_HW_GPMI_CTRL1 */
 	hw->wrn_dly_sel = BV_GPMI_CTRL1_WRN_DLY_SEL_NO_DELAY;
 
-	if (GPMI_IS_MX6Q(this))
-		dll_threshold = 12;
-
 	/*
 	 * Enlarge 10 times for the numerator and denominator in {3}.
 	 * This make us to get more accurate result.
@@ -974,7 +971,7 @@ int gpmi_extra_init(struct gpmi_nand_data *this)
 	struct nand_chip *chip = &this->nand;
 
 	/* Enable the asynchronous EDO feature. */
-	if (GPMI_IS_MX6Q(this) && chip->onfi_version) {
+	if (GPMI_IS_MX6(this) && chip->onfi_version) {
 		int mode = onfi_get_async_timing_mode(chip);
 
 		/* We only support the timing mode 4 and mode 5. */
@@ -1096,12 +1093,12 @@ int gpmi_is_ready(struct gpmi_nand_data *this, unsigned chip)
 	if (GPMI_IS_MX23(this)) {
 		mask = MX23_BM_GPMI_DEBUG_READY0 << chip;
 		reg = readl(r->gpmi_regs + HW_GPMI_DEBUG);
-	} else if (GPMI_IS_MX28(this) || GPMI_IS_MX6Q(this)) {
+	} else if (GPMI_IS_MX28(this) || GPMI_IS_MX6(this)) {
 		/*
 		 * In the imx6, all the ready/busy pins are bound
 		 * together. So we only need to check chip 0.
 		 */
-		if (GPMI_IS_MX6Q(this))
+		if (GPMI_IS_MX6(this))
 			chip = 0;
 
 		/* MX28 shares the same R/B register as MX6Q. */
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index bb77f750e75..f638cd8077c 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -53,6 +53,30 @@ static struct nand_ecclayout gpmi_hw_ecclayout = {
 	.oobfree = { {.offset = 0, .length = 0} }
 };
 
+static const struct gpmi_devdata gpmi_devdata_imx23 = {
+	.type = IS_MX23,
+	.bch_max_ecc_strength = 20,
+	.max_chain_delay = 16,
+};
+
+static const struct gpmi_devdata gpmi_devdata_imx28 = {
+	.type = IS_MX28,
+	.bch_max_ecc_strength = 20,
+	.max_chain_delay = 16,
+};
+
+static const struct gpmi_devdata gpmi_devdata_imx6q = {
+	.type = IS_MX6Q,
+	.bch_max_ecc_strength = 40,
+	.max_chain_delay = 12,
+};
+
+static const struct gpmi_devdata gpmi_devdata_imx6sx = {
+	.type = IS_MX6SX,
+	.bch_max_ecc_strength = 62,
+	.max_chain_delay = 12,
+};
+
 static irqreturn_t bch_irq(int irq, void *cookie)
 {
 	struct gpmi_nand_data *this = cookie;
@@ -102,14 +126,8 @@ static inline bool gpmi_check_ecc(struct gpmi_nand_data *this)
 		/* The mx23/mx28 only support the GF13. */
 		if (geo->gf_len == 14)
 			return false;
-
-		if (geo->ecc_strength > MXS_ECC_STRENGTH_MAX)
-			return false;
-	} else if (GPMI_IS_MX6Q(this)) {
-		if (geo->ecc_strength > MX6_ECC_STRENGTH_MAX)
-			return false;
 	}
-	return true;
+	return geo->ecc_strength <= this->devdata->bch_max_ecc_strength;
 }
 
 /*
@@ -270,8 +288,7 @@ static int legacy_set_geometry(struct gpmi_nand_data *this)
 			"We can not support this nand chip."
 			" Its required ecc strength(%d) is beyond our"
 			" capability(%d).\n", geo->ecc_strength,
-			(GPMI_IS_MX6Q(this) ? MX6_ECC_STRENGTH_MAX
-					: MXS_ECC_STRENGTH_MAX));
+			this->devdata->bch_max_ecc_strength);
 		return -EINVAL;
 	}
 
@@ -572,7 +589,7 @@ static int gpmi_get_clks(struct gpmi_nand_data *this)
 	}
 
 	/* Get extra clocks */
-	if (GPMI_IS_MX6Q(this))
+	if (GPMI_IS_MX6(this))
 		extra_clks = extra_clks_for_mx6q;
 	if (!extra_clks)
 		return 0;
@@ -590,9 +607,9 @@ static int gpmi_get_clks(struct gpmi_nand_data *this)
 		r->clock[i] = clk;
 	}
 
-	if (GPMI_IS_MX6Q(this))
+	if (GPMI_IS_MX6(this))
 		/*
-		 * Set the default value for the gpmi clock in mx6q:
+		 * Set the default value for the gpmi clock.
 		 *
 		 * If you want to use the ONFI nand which is in the
 		 * Synchronous Mode, you should change the clock as you need.
@@ -1655,7 +1672,7 @@ static int gpmi_init_last(struct gpmi_nand_data *this)
 	 *  (1) the chip is imx6, and
 	 *  (2) the size of the ECC parity is byte aligned.
 	 */
-	if (GPMI_IS_MX6Q(this) &&
+	if (GPMI_IS_MX6(this) &&
 		((bch_geo->gf_len * bch_geo->ecc_strength) % 8) == 0) {
 		ecc->read_subpage = gpmi_ecc_read_subpage;
 		chip->options |= NAND_SUBPAGE_READ;
@@ -1711,7 +1728,7 @@ static int gpmi_nand_init(struct gpmi_nand_data *this)
 	if (ret)
 		goto err_out;
 
-	ret = nand_scan_ident(mtd, GPMI_IS_MX6Q(this) ? 2 : 1, NULL);
+	ret = nand_scan_ident(mtd, GPMI_IS_MX6(this) ? 2 : 1, NULL);
 	if (ret)
 		goto err_out;
 
@@ -1740,23 +1757,19 @@ err_out:
 	return ret;
 }
 
-static const struct platform_device_id gpmi_ids[] = {
-	{ .name = "imx23-gpmi-nand", .driver_data = IS_MX23, },
-	{ .name = "imx28-gpmi-nand", .driver_data = IS_MX28, },
-	{ .name = "imx6q-gpmi-nand", .driver_data = IS_MX6Q, },
-	{}
-};
-
 static const struct of_device_id gpmi_nand_id_table[] = {
 	{
 		.compatible = "fsl,imx23-gpmi-nand",
-		.data = (void *)&gpmi_ids[IS_MX23],
+		.data = (void *)&gpmi_devdata_imx23,
 	}, {
 		.compatible = "fsl,imx28-gpmi-nand",
-		.data = (void *)&gpmi_ids[IS_MX28],
+		.data = (void *)&gpmi_devdata_imx28,
 	}, {
 		.compatible = "fsl,imx6q-gpmi-nand",
-		.data = (void *)&gpmi_ids[IS_MX6Q],
+		.data = (void *)&gpmi_devdata_imx6q,
+	}, {
+		.compatible = "fsl,imx6sx-gpmi-nand",
+		.data = (void *)&gpmi_devdata_imx6sx,
 	}, {}
 };
 MODULE_DEVICE_TABLE(of, gpmi_nand_id_table);
@@ -1767,18 +1780,18 @@ static int gpmi_nand_probe(struct platform_device *pdev)
 	const struct of_device_id *of_id;
 	int ret;
 
+	this = devm_kzalloc(&pdev->dev, sizeof(*this), GFP_KERNEL);
+	if (!this)
+		return -ENOMEM;
+
 	of_id = of_match_device(gpmi_nand_id_table, &pdev->dev);
 	if (of_id) {
-		pdev->id_entry = of_id->data;
+		this->devdata = of_id->data;
 	} else {
 		dev_err(&pdev->dev, "Failed to find the right device id.\n");
 		return -ENODEV;
 	}
 
-	this = devm_kzalloc(&pdev->dev, sizeof(*this), GFP_KERNEL);
-	if (!this)
-		return -ENOMEM;
-
 	platform_set_drvdata(pdev, this);
 	this->pdev  = pdev;
 	this->dev   = &pdev->dev;
@@ -1823,7 +1836,6 @@ static struct platform_driver gpmi_nand_driver = {
 	},
 	.probe   = gpmi_nand_probe,
 	.remove  = gpmi_nand_remove,
-	.id_table = gpmi_ids,
 };
 module_platform_driver(gpmi_nand_driver);
 
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
index 4c801fa1872..32c6ba49f98 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
@@ -119,11 +119,25 @@ struct nand_timing {
 	int8_t  tRHOH_in_ns;
 };
 
+enum gpmi_type {
+	IS_MX23,
+	IS_MX28,
+	IS_MX6Q,
+	IS_MX6SX
+};
+
+struct gpmi_devdata {
+	enum gpmi_type type;
+	int bch_max_ecc_strength;
+	int max_chain_delay; /* See the async EDO mode */
+};
+
 struct gpmi_nand_data {
 	/* flags */
 #define GPMI_ASYNC_EDO_ENABLED	(1 << 0)
 #define GPMI_TIMING_INIT_OK	(1 << 1)
 	int			flags;
+	const struct gpmi_devdata *devdata;
 
 	/* System Interface */
 	struct device		*dev;
@@ -281,15 +295,11 @@ extern int gpmi_read_page(struct gpmi_nand_data *,
 #define STATUS_ERASED		0xff
 #define STATUS_UNCORRECTABLE	0xfe
 
-/* BCH's bit correction capability. */
-#define MXS_ECC_STRENGTH_MAX	20	/* mx23 and mx28 */
-#define MX6_ECC_STRENGTH_MAX	40
-
-/* Use the platform_id to distinguish different Archs. */
-#define IS_MX23			0x0
-#define IS_MX28			0x1
-#define IS_MX6Q			0x2
-#define GPMI_IS_MX23(x)		((x)->pdev->id_entry->driver_data == IS_MX23)
-#define GPMI_IS_MX28(x)		((x)->pdev->id_entry->driver_data == IS_MX28)
-#define GPMI_IS_MX6Q(x)		((x)->pdev->id_entry->driver_data == IS_MX6Q)
+/* Use the devdata to distinguish different Archs. */
+#define GPMI_IS_MX23(x)		((x)->devdata->type == IS_MX23)
+#define GPMI_IS_MX28(x)		((x)->devdata->type == IS_MX28)
+#define GPMI_IS_MX6Q(x)		((x)->devdata->type == IS_MX6Q)
+#define GPMI_IS_MX6SX(x)	((x)->devdata->type == IS_MX6SX)
+
+#define GPMI_IS_MX6(x)		(GPMI_IS_MX6Q(x) || GPMI_IS_MX6SX(x))
 #endif
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 9d01c4df838..4f3e80c68a2 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -37,6 +37,7 @@
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 #include <linux/types.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
@@ -1204,8 +1205,7 @@ static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip,
 	 * ecc.pos. Let's make sure that there are no gaps in ECC positions.
 	 */
 	for (i = 0; i < eccfrag_len - 1; i++) {
-		if (eccpos[i + start_step * chip->ecc.bytes] + 1 !=
-			eccpos[i + start_step * chip->ecc.bytes + 1]) {
+		if (eccpos[i + index] + 1 != eccpos[i + index + 1]) {
 			gaps = 1;
 			break;
 		}
@@ -1501,6 +1501,7 @@ static int nand_do_read_ops(struct mtd_info *mtd, loff_t from,
 		mtd->oobavail : mtd->oobsize;
 
 	uint8_t *bufpoi, *oob, *buf;
+	int use_bufpoi;
 	unsigned int max_bitflips = 0;
 	int retry_mode = 0;
 	bool ecc_fail = false;
@@ -1523,9 +1524,20 @@ static int nand_do_read_ops(struct mtd_info *mtd, loff_t from,
 		bytes = min(mtd->writesize - col, readlen);
 		aligned = (bytes == mtd->writesize);
 
+		if (!aligned)
+			use_bufpoi = 1;
+		else if (chip->options & NAND_USE_BOUNCE_BUFFER)
+			use_bufpoi = !virt_addr_valid(buf);
+		else
+			use_bufpoi = 0;
+
 		/* Is the current page in the buffer? */
 		if (realpage != chip->pagebuf || oob) {
-			bufpoi = aligned ? buf : chip->buffers->databuf;
+			bufpoi = use_bufpoi ? chip->buffers->databuf : buf;
+
+			if (use_bufpoi && aligned)
+				pr_debug("%s: using read bounce buffer for buf@%p\n",
+						 __func__, buf);
 
 read_retry:
 			chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page);
@@ -1547,7 +1559,7 @@ read_retry:
 				ret = chip->ecc.read_page(mtd, chip, bufpoi,
 							  oob_required, page);
 			if (ret < 0) {
-				if (!aligned)
+				if (use_bufpoi)
 					/* Invalidate page cache */
 					chip->pagebuf = -1;
 				break;
@@ -1556,7 +1568,7 @@ read_retry:
 			max_bitflips = max_t(unsigned int, max_bitflips, ret);
 
 			/* Transfer not aligned data */
-			if (!aligned) {
+			if (use_bufpoi) {
 				if (!NAND_HAS_SUBPAGE_READ(chip) && !oob &&
 				    !(mtd->ecc_stats.failed - ecc_failures) &&
 				    (ops->mode != MTD_OPS_RAW)) {
@@ -2376,11 +2388,23 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 		int bytes = mtd->writesize;
 		int cached = writelen > bytes && page != blockmask;
 		uint8_t *wbuf = buf;
+		int use_bufpoi;
+		int part_pagewr = (column || writelen < (mtd->writesize - 1));
+
+		if (part_pagewr)
+			use_bufpoi = 1;
+		else if (chip->options & NAND_USE_BOUNCE_BUFFER)
+			use_bufpoi = !virt_addr_valid(buf);
+		else
+			use_bufpoi = 0;
 
-		/* Partial page write? */
-		if (unlikely(column || writelen < (mtd->writesize - 1))) {
+		/* Partial page write?, or need to use bounce buffer */
+		if (use_bufpoi) {
+			pr_debug("%s: using write bounce buffer for buf@%p\n",
+					 __func__, buf);
 			cached = 0;
-			bytes = min_t(int, bytes - column, (int) writelen);
+			if (part_pagewr)
+				bytes = min_t(int, bytes - column, writelen);
 			chip->pagebuf = -1;
 			memset(chip->buffers->databuf, 0xff, mtd->writesize);
 			memcpy(&chip->buffers->databuf[column], buf, bytes);
@@ -2618,18 +2642,20 @@ out:
 }
 
 /**
- * single_erase_cmd - [GENERIC] NAND standard block erase command function
+ * single_erase - [GENERIC] NAND standard block erase command function
  * @mtd: MTD device structure
  * @page: the page address of the block which will be erased
  *
- * Standard erase command for NAND chips.
+ * Standard erase command for NAND chips. Returns NAND status.
  */
-static void single_erase_cmd(struct mtd_info *mtd, int page)
+static int single_erase(struct mtd_info *mtd, int page)
 {
 	struct nand_chip *chip = mtd->priv;
 	/* Send commands to erase a block */
 	chip->cmdfunc(mtd, NAND_CMD_ERASE1, -1, page);
 	chip->cmdfunc(mtd, NAND_CMD_ERASE2, -1, -1);
+
+	return chip->waitfunc(mtd, chip);
 }
 
 /**
@@ -2710,9 +2736,7 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 		    (page + pages_per_block))
 			chip->pagebuf = -1;
 
-		chip->erase_cmd(mtd, page & chip->pagemask);
-
-		status = chip->waitfunc(mtd, chip);
+		status = chip->erase(mtd, page & chip->pagemask);
 
 		/*
 		 * See if operation failed and additional status checks are
@@ -3607,7 +3631,7 @@ static struct nand_flash_dev *nand_get_flash_type(struct mtd_info *mtd,
 
 	chip->onfi_version = 0;
 	if (!type->name || !type->pagesize) {
-		/* Check is chip is ONFI compliant */
+		/* Check if the chip is ONFI compliant */
 		if (nand_flash_detect_onfi(mtd, chip, &busw))
 			goto ident_done;
 
@@ -3685,7 +3709,7 @@ ident_done:
 	}
 
 	chip->badblockbits = 8;
-	chip->erase_cmd = single_erase_cmd;
+	chip->erase = single_erase;
 
 	/* Do not replace user supplied command function! */
 	if (mtd->writesize > 512 && chip->cmdfunc == nand_command)
@@ -3770,6 +3794,39 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 }
 EXPORT_SYMBOL(nand_scan_ident);
 
+/*
+ * Check if the chip configuration meet the datasheet requirements.
+
+ * If our configuration corrects A bits per B bytes and the minimum
+ * required correction level is X bits per Y bytes, then we must ensure
+ * both of the following are true:
+ *
+ * (1) A / B >= X / Y
+ * (2) A >= X
+ *
+ * Requirement (1) ensures we can correct for the required bitflip density.
+ * Requirement (2) ensures we can correct even when all bitflips are clumped
+ * in the same sector.
+ */
+static bool nand_ecc_strength_good(struct mtd_info *mtd)
+{
+	struct nand_chip *chip = mtd->priv;
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	int corr, ds_corr;
+
+	if (ecc->size == 0 || chip->ecc_step_ds == 0)
+		/* Not enough information */
+		return true;
+
+	/*
+	 * We get the number of corrected bits per page to compare
+	 * the correction density.
+	 */
+	corr = (mtd->writesize * ecc->strength) / ecc->size;
+	ds_corr = (mtd->writesize * chip->ecc_strength_ds) / chip->ecc_step_ds;
+
+	return corr >= ds_corr && ecc->strength >= chip->ecc_strength_ds;
+}
 
 /**
  * nand_scan_tail - [NAND Interface] Scan for the NAND device
@@ -3990,6 +4047,11 @@ int nand_scan_tail(struct mtd_info *mtd)
 		ecc->layout->oobavail += ecc->layout->oobfree[i].length;
 	mtd->oobavail = ecc->layout->oobavail;
 
+	/* ECC sanity check: warn if it's too weak */
+	if (!nand_ecc_strength_good(mtd))
+		pr_warn("WARNING: %s: the ECC used on your system is too weak compared to the one required by the NAND chip\n",
+			mtd->name);
+
 	/*
 	 * Set the number of read / write steps for one page depending on ECC
 	 * mode.
@@ -4023,8 +4085,16 @@ int nand_scan_tail(struct mtd_info *mtd)
 	chip->pagebuf = -1;
 
 	/* Large page NAND with SOFT_ECC should support subpage reads */
-	if ((ecc->mode == NAND_ECC_SOFT) && (chip->page_shift > 9))
-		chip->options |= NAND_SUBPAGE_READ;
+	switch (ecc->mode) {
+	case NAND_ECC_SOFT:
+	case NAND_ECC_SOFT_BCH:
+		if (chip->page_shift > 9)
+			chip->options |= NAND_SUBPAGE_READ;
+		break;
+
+	default:
+		break;
+	}
 
 	/* Fill in remaining MTD driver data */
 	mtd->type = nand_is_slc(chip) ? MTD_NANDFLASH : MTD_MLCNANDFLASH;
diff --git a/drivers/mtd/nand/nand_bbt.c b/drivers/mtd/nand/nand_bbt.c
index c0615d1526f..7f0c3b4c2a4 100644
--- a/drivers/mtd/nand/nand_bbt.c
+++ b/drivers/mtd/nand/nand_bbt.c
@@ -528,7 +528,7 @@ static int search_bbt(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr
 {
 	struct nand_chip *this = mtd->priv;
 	int i, chips;
-	int bits, startblock, block, dir;
+	int startblock, block, dir;
 	int scanlen = mtd->writesize + mtd->oobsize;
 	int bbtblocks;
 	int blocktopage = this->bbt_erase_shift - this->page_shift;
@@ -552,9 +552,6 @@ static int search_bbt(struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr
 		bbtblocks = mtd->size >> this->bbt_erase_shift;
 	}
 
-	/* Number of bits for each erase block in the bbt */
-	bits = td->options & NAND_BBT_NRBITS_MSK;
-
 	for (i = 0; i < chips; i++) {
 		/* Reset version information */
 		td->version[i] = 0;
@@ -1285,6 +1282,7 @@ static int nand_create_badblock_pattern(struct nand_chip *this)
 int nand_default_bbt(struct mtd_info *mtd)
 {
 	struct nand_chip *this = mtd->priv;
+	int ret;
 
 	/* Is a flash based bad block table requested? */
 	if (this->bbt_options & NAND_BBT_USE_FLASH) {
@@ -1303,8 +1301,11 @@ int nand_default_bbt(struct mtd_info *mtd)
 		this->bbt_md = NULL;
 	}
 
-	if (!this->badblock_pattern)
-		nand_create_badblock_pattern(this);
+	if (!this->badblock_pattern) {
+		ret = nand_create_badblock_pattern(this);
+		if (ret)
+			return ret;
+	}
 
 	return nand_scan_bbt(mtd, this->badblock_pattern);
 }
diff --git a/drivers/mtd/nand/nand_ecc.c b/drivers/mtd/nand/nand_ecc.c
index 053c9a2d47c..97c4c0216c9 100644
--- a/drivers/mtd/nand/nand_ecc.c
+++ b/drivers/mtd/nand/nand_ecc.c
@@ -506,7 +506,7 @@ int __nand_correct_data(unsigned char *buf,
 	if ((bitsperbyte[b0] + bitsperbyte[b1] + bitsperbyte[b2]) == 1)
 		return 1;	/* error in ECC data; no action needed */
 
-	pr_err("%s: uncorrectable ECC error", __func__);
+	pr_err("%s: uncorrectable ECC error\n", __func__);
 	return -1;
 }
 EXPORT_SYMBOL(__nand_correct_data);
diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c
index 42e8a770e63..4f0d83648e5 100644
--- a/drivers/mtd/nand/nandsim.c
+++ b/drivers/mtd/nand/nandsim.c
@@ -575,12 +575,12 @@ static int alloc_device(struct nandsim *ns)
 		cfile = filp_open(cache_file, O_CREAT | O_RDWR | O_LARGEFILE, 0600);
 		if (IS_ERR(cfile))
 			return PTR_ERR(cfile);
-		if (!cfile->f_op->read && !cfile->f_op->aio_read) {
+		if (!(cfile->f_mode & FMODE_CAN_READ)) {
 			NS_ERR("alloc_device: cache file not readable\n");
 			err = -EINVAL;
 			goto err_close;
 		}
-		if (!cfile->f_op->write && !cfile->f_op->aio_write) {
+		if (!(cfile->f_mode & FMODE_CAN_WRITE)) {
 			NS_ERR("alloc_device: cache file not writeable\n");
 			err = -EINVAL;
 			goto err_close;
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index 1ff49b80bda..f0ed92e210a 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -137,6 +137,10 @@
 #define BADBLOCK_MARKER_LENGTH		2
 
 #ifdef CONFIG_MTD_NAND_OMAP_BCH
+static u_char bch16_vector[] = {0xf5, 0x24, 0x1c, 0xd0, 0x61, 0xb3, 0xf1, 0x55,
+				0x2e, 0x2c, 0x86, 0xa3, 0xed, 0x36, 0x1b, 0x78,
+				0x48, 0x76, 0xa9, 0x3b, 0x97, 0xd1, 0x7a, 0x93,
+				0x07, 0x0e};
 static u_char bch8_vector[] = {0xf3, 0xdb, 0x14, 0x16, 0x8b, 0xd2, 0xbe, 0xcc,
 	0xac, 0x6b, 0xff, 0x99, 0x7b};
 static u_char bch4_vector[] = {0x00, 0x6b, 0x31, 0xdd, 0x41, 0xbc, 0x10};
@@ -1114,6 +1118,19 @@ static void __maybe_unused omap_enable_hwecc_bch(struct mtd_info *mtd, int mode)
 			ecc_size1 = BCH_ECC_SIZE1;
 		}
 		break;
+	case OMAP_ECC_BCH16_CODE_HW:
+		bch_type = 0x2;
+		nsectors = chip->ecc.steps;
+		if (mode == NAND_ECC_READ) {
+			wr_mode	  = 0x01;
+			ecc_size0 = 52; /* ECC bits in nibbles per sector */
+			ecc_size1 = 0;  /* non-ECC bits in nibbles per sector */
+		} else {
+			wr_mode	  = 0x01;
+			ecc_size0 = 0;  /* extra bits in nibbles per sector */
+			ecc_size1 = 52; /* OOB bits in nibbles per sector */
+		}
+		break;
 	default:
 		return;
 	}
@@ -1162,7 +1179,8 @@ static int __maybe_unused omap_calculate_ecc_bch(struct mtd_info *mtd,
 	struct gpmc_nand_regs	*gpmc_regs = &info->reg;
 	u8 *ecc_code;
 	unsigned long nsectors, bch_val1, bch_val2, bch_val3, bch_val4;
-	int i;
+	u32 val;
+	int i, j;
 
 	nsectors = ((readl(info->reg.gpmc_ecc_config) >> 4) & 0x7) + 1;
 	for (i = 0; i < nsectors; i++) {
@@ -1201,6 +1219,41 @@ static int __maybe_unused omap_calculate_ecc_bch(struct mtd_info *mtd,
 			*ecc_code++ = ((bch_val1 >> 4) & 0xFF);
 			*ecc_code++ = ((bch_val1 & 0xF) << 4);
 			break;
+		case OMAP_ECC_BCH16_CODE_HW:
+			val = readl(gpmc_regs->gpmc_bch_result6[i]);
+			ecc_code[0]  = ((val >>  8) & 0xFF);
+			ecc_code[1]  = ((val >>  0) & 0xFF);
+			val = readl(gpmc_regs->gpmc_bch_result5[i]);
+			ecc_code[2]  = ((val >> 24) & 0xFF);
+			ecc_code[3]  = ((val >> 16) & 0xFF);
+			ecc_code[4]  = ((val >>  8) & 0xFF);
+			ecc_code[5]  = ((val >>  0) & 0xFF);
+			val = readl(gpmc_regs->gpmc_bch_result4[i]);
+			ecc_code[6]  = ((val >> 24) & 0xFF);
+			ecc_code[7]  = ((val >> 16) & 0xFF);
+			ecc_code[8]  = ((val >>  8) & 0xFF);
+			ecc_code[9]  = ((val >>  0) & 0xFF);
+			val = readl(gpmc_regs->gpmc_bch_result3[i]);
+			ecc_code[10] = ((val >> 24) & 0xFF);
+			ecc_code[11] = ((val >> 16) & 0xFF);
+			ecc_code[12] = ((val >>  8) & 0xFF);
+			ecc_code[13] = ((val >>  0) & 0xFF);
+			val = readl(gpmc_regs->gpmc_bch_result2[i]);
+			ecc_code[14] = ((val >> 24) & 0xFF);
+			ecc_code[15] = ((val >> 16) & 0xFF);
+			ecc_code[16] = ((val >>  8) & 0xFF);
+			ecc_code[17] = ((val >>  0) & 0xFF);
+			val = readl(gpmc_regs->gpmc_bch_result1[i]);
+			ecc_code[18] = ((val >> 24) & 0xFF);
+			ecc_code[19] = ((val >> 16) & 0xFF);
+			ecc_code[20] = ((val >>  8) & 0xFF);
+			ecc_code[21] = ((val >>  0) & 0xFF);
+			val = readl(gpmc_regs->gpmc_bch_result0[i]);
+			ecc_code[22] = ((val >> 24) & 0xFF);
+			ecc_code[23] = ((val >> 16) & 0xFF);
+			ecc_code[24] = ((val >>  8) & 0xFF);
+			ecc_code[25] = ((val >>  0) & 0xFF);
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -1210,8 +1263,8 @@ static int __maybe_unused omap_calculate_ecc_bch(struct mtd_info *mtd,
 		case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
 			/* Add constant polynomial to remainder, so that
 			 * ECC of blank pages results in 0x0 on reading back */
-			for (i = 0; i < eccbytes; i++)
-				ecc_calc[i] ^= bch4_polynomial[i];
+			for (j = 0; j < eccbytes; j++)
+				ecc_calc[j] ^= bch4_polynomial[j];
 			break;
 		case OMAP_ECC_BCH4_CODE_HW:
 			/* Set  8th ECC byte as 0x0 for ROM compatibility */
@@ -1220,13 +1273,15 @@ static int __maybe_unused omap_calculate_ecc_bch(struct mtd_info *mtd,
 		case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
 			/* Add constant polynomial to remainder, so that
 			 * ECC of blank pages results in 0x0 on reading back */
-			for (i = 0; i < eccbytes; i++)
-				ecc_calc[i] ^= bch8_polynomial[i];
+			for (j = 0; j < eccbytes; j++)
+				ecc_calc[j] ^= bch8_polynomial[j];
 			break;
 		case OMAP_ECC_BCH8_CODE_HW:
 			/* Set 14th ECC byte as 0x0 for ROM compatibility */
 			ecc_calc[eccbytes - 1] = 0x0;
 			break;
+		case OMAP_ECC_BCH16_CODE_HW:
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -1237,6 +1292,7 @@ static int __maybe_unused omap_calculate_ecc_bch(struct mtd_info *mtd,
 	return 0;
 }
 
+#ifdef CONFIG_MTD_NAND_OMAP_BCH
 /**
  * erased_sector_bitflips - count bit flips
  * @data:	data sector buffer
@@ -1276,7 +1332,6 @@ static int erased_sector_bitflips(u_char *data, u_char *oob,
 	return flip_bits;
 }
 
-#ifdef CONFIG_MTD_NAND_OMAP_BCH
 /**
  * omap_elm_correct_data - corrects page data area in case error reported
  * @mtd:	MTD device structure
@@ -1318,6 +1373,10 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
 		actual_eccbytes = ecc->bytes - 1;
 		erased_ecc_vec = bch8_vector;
 		break;
+	case OMAP_ECC_BCH16_CODE_HW:
+		actual_eccbytes = ecc->bytes;
+		erased_ecc_vec = bch16_vector;
+		break;
 	default:
 		pr_err("invalid driver configuration\n");
 		return -EINVAL;
@@ -1382,7 +1441,7 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
 
 	/* Check if any error reported */
 	if (!is_error_reported)
-		return 0;
+		return stat;
 
 	/* Decode BCH error using ELM module */
 	elm_decode_bch_error_page(info->elm_dev, ecc_vec, err_vec);
@@ -1401,6 +1460,7 @@ static int omap_elm_correct_data(struct mtd_info *mtd, u_char *data,
 						BCH4_BIT_PAD;
 					break;
 				case OMAP_ECC_BCH8_CODE_HW:
+				case OMAP_ECC_BCH16_CODE_HW:
 					pos = err_vec[i].error_loc[j];
 					break;
 				default:
@@ -1912,6 +1972,40 @@ static int omap_nand_probe(struct platform_device *pdev)
 		goto return_error;
 #endif
 
+	case OMAP_ECC_BCH16_CODE_HW:
+#ifdef CONFIG_MTD_NAND_OMAP_BCH
+		pr_info("using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
+		nand_chip->ecc.mode		= NAND_ECC_HW;
+		nand_chip->ecc.size		= 512;
+		nand_chip->ecc.bytes		= 26;
+		nand_chip->ecc.strength		= 16;
+		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		nand_chip->ecc.correct		= omap_elm_correct_data;
+		nand_chip->ecc.calculate	= omap_calculate_ecc_bch;
+		nand_chip->ecc.read_page	= omap_read_page_bch;
+		nand_chip->ecc.write_page	= omap_write_page_bch;
+		/* This ECC scheme requires ELM H/W block */
+		err = is_elm_present(info, pdata->elm_of_node, BCH16_ECC);
+		if (err < 0) {
+			pr_err("ELM is required for this ECC scheme\n");
+			goto return_error;
+		}
+		/* define ECC layout */
+		ecclayout->eccbytes		= nand_chip->ecc.bytes *
+							(mtd->writesize /
+							nand_chip->ecc.size);
+		oob_index			= BADBLOCK_MARKER_LENGTH;
+		for (i = 0; i < ecclayout->eccbytes; i++, oob_index++)
+			ecclayout->eccpos[i]	= oob_index;
+		/* reserved marker already included in ecclayout->eccbytes */
+		ecclayout->oobfree->offset	=
+				ecclayout->eccpos[ecclayout->eccbytes - 1] + 1;
+		break;
+#else
+		pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n");
+		err = -EINVAL;
+		goto return_error;
+#endif
 	default:
 		pr_err("nand: error: invalid or unsupported ECC scheme\n");
 		err = -EINVAL;
diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c
index dd7fe817eaf..471b4df3a5a 100644
--- a/drivers/mtd/nand/orion_nand.c
+++ b/drivers/mtd/nand/orion_nand.c
@@ -214,7 +214,7 @@ static int orion_nand_remove(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_OF
-static struct of_device_id orion_nand_of_match_table[] = {
+static const struct of_device_id orion_nand_of_match_table[] = {
 	{ .compatible = "marvell,orion-nand", },
 	{},
 };
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 7588fe2c127..96b0b1d27df 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -127,10 +127,10 @@
 
 /* macros for registers read/write */
 #define nand_writel(info, off, val)	\
-	__raw_writel((val), (info)->mmio_base + (off))
+	writel_relaxed((val), (info)->mmio_base + (off))
 
 #define nand_readl(info, off)		\
-	__raw_readl((info)->mmio_base + (off))
+	readl_relaxed((info)->mmio_base + (off))
 
 /* error code and state */
 enum {
@@ -337,7 +337,7 @@ static struct nand_ecclayout ecc_layout_4KB_bch8bit = {
 /* convert nano-seconds to nand flash controller clock cycles */
 #define ns2cycle(ns, clk)	(int)((ns) * (clk / 1000000) / 1000)
 
-static struct of_device_id pxa3xx_nand_dt_ids[] = {
+static const struct of_device_id pxa3xx_nand_dt_ids[] = {
 	{
 		.compatible = "marvell,pxa3xx-nand",
 		.data       = (void *)PXA3XX_NAND_VARIANT_PXA,
@@ -1354,7 +1354,6 @@ static int pxa_ecc_init(struct pxa3xx_nand_info *info,
 		ecc->mode = NAND_ECC_HW;
 		ecc->size = 512;
 		ecc->strength = 1;
-		return 1;
 
 	} else if (strength == 1 && ecc_stepsize == 512 && page_size == 512) {
 		info->chunk_size = 512;
@@ -1363,7 +1362,6 @@ static int pxa_ecc_init(struct pxa3xx_nand_info *info,
 		ecc->mode = NAND_ECC_HW;
 		ecc->size = 512;
 		ecc->strength = 1;
-		return 1;
 
 	/*
 	 * Required ECC: 4-bit correction per 512 bytes
@@ -1378,7 +1376,6 @@ static int pxa_ecc_init(struct pxa3xx_nand_info *info,
 		ecc->size = info->chunk_size;
 		ecc->layout = &ecc_layout_2KB_bch4bit;
 		ecc->strength = 16;
-		return 1;
 
 	} else if (strength == 4 && ecc_stepsize == 512 && page_size == 4096) {
 		info->ecc_bch = 1;
@@ -1389,7 +1386,6 @@ static int pxa_ecc_init(struct pxa3xx_nand_info *info,
 		ecc->size = info->chunk_size;
 		ecc->layout = &ecc_layout_4KB_bch4bit;
 		ecc->strength = 16;
-		return 1;
 
 	/*
 	 * Required ECC: 8-bit correction per 512 bytes
@@ -1404,8 +1400,15 @@ static int pxa_ecc_init(struct pxa3xx_nand_info *info,
 		ecc->size = info->chunk_size;
 		ecc->layout = &ecc_layout_4KB_bch8bit;
 		ecc->strength = 16;
-		return 1;
+	} else {
+		dev_err(&info->pdev->dev,
+			"ECC strength %d at page size %d is not supported\n",
+			strength, page_size);
+		return -ENODEV;
 	}
+
+	dev_info(&info->pdev->dev, "ECC strength %d, ECC step size %d\n",
+		 ecc->strength, ecc->size);
 	return 0;
 }
 
@@ -1516,8 +1519,13 @@ KEEP_CONFIG:
 		}
 	}
 
-	ecc_strength = chip->ecc_strength_ds;
-	ecc_step = chip->ecc_step_ds;
+	if (pdata->ecc_strength && pdata->ecc_step_size) {
+		ecc_strength = pdata->ecc_strength;
+		ecc_step = pdata->ecc_step_size;
+	} else {
+		ecc_strength = chip->ecc_strength_ds;
+		ecc_step = chip->ecc_step_ds;
+	}
 
 	/* Set default ECC strength requirements on non-ONFI devices */
 	if (ecc_strength < 1 && ecc_step < 1) {
@@ -1527,12 +1535,8 @@ KEEP_CONFIG:
 
 	ret = pxa_ecc_init(info, &chip->ecc, ecc_strength,
 			   ecc_step, mtd->writesize);
-	if (!ret) {
-		dev_err(&info->pdev->dev,
-			"ECC strength %d at page size %d is not supported\n",
-			ecc_strength, mtd->writesize);
-		return -ENODEV;
-	}
+	if (ret)
+		return ret;
 
 	/* calculate addressing information */
 	if (mtd->writesize >= 2048)
@@ -1730,6 +1734,14 @@ static int pxa3xx_nand_probe_dt(struct platform_device *pdev)
 	of_property_read_u32(np, "num-cs", &pdata->num_cs);
 	pdata->flash_bbt = of_get_nand_on_flash_bbt(np);
 
+	pdata->ecc_strength = of_get_nand_ecc_strength(np);
+	if (pdata->ecc_strength < 0)
+		pdata->ecc_strength = 0;
+
+	pdata->ecc_step_size = of_get_nand_ecc_step_size(np);
+	if (pdata->ecc_step_size < 0)
+		pdata->ecc_step_size = 0;
+
 	pdev->dev.platform_data = pdata;
 
 	return 0;
diff --git a/drivers/mtd/nand/r852.c b/drivers/mtd/nand/r852.c
index 325930db3f0..baea83f4dea 100644
--- a/drivers/mtd/nand/r852.c
+++ b/drivers/mtd/nand/r852.c
@@ -245,7 +245,7 @@ static void r852_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	}
 
 	/* write DWORD chinks - faster */
-	while (len) {
+	while (len >= 4) {
 		reg = buf[0] | buf[1] << 8 | buf[2] << 16 | buf[3] << 24;
 		r852_write_reg_dword(dev, R852_DATALINE, reg);
 		buf += 4;
@@ -254,8 +254,10 @@ static void r852_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	}
 
 	/* write rest */
-	while (len)
+	while (len > 0) {
 		r852_write_reg(dev, R852_DATALINE, *buf++);
+		len--;
+	}
 }
 
 /*
diff --git a/drivers/mtd/onenand/samsung.c b/drivers/mtd/onenand/samsung.c
index b1a792fd1c2..efb819c3df2 100644
--- a/drivers/mtd/onenand/samsung.c
+++ b/drivers/mtd/onenand/samsung.c
@@ -537,9 +537,9 @@ static int onenand_write_bufferram(struct mtd_info *mtd, int area,
 	return 0;
 }
 
-static int (*s5pc110_dma_ops)(void *dst, void *src, size_t count, int direction);
+static int (*s5pc110_dma_ops)(dma_addr_t dst, dma_addr_t src, size_t count, int direction);
 
-static int s5pc110_dma_poll(void *dst, void *src, size_t count, int direction)
+static int s5pc110_dma_poll(dma_addr_t dst, dma_addr_t src, size_t count, int direction)
 {
 	void __iomem *base = onenand->dma_addr;
 	int status;
@@ -605,7 +605,7 @@ static irqreturn_t s5pc110_onenand_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int s5pc110_dma_irq(void *dst, void *src, size_t count, int direction)
+static int s5pc110_dma_irq(dma_addr_t dst, dma_addr_t src, size_t count, int direction)
 {
 	void __iomem *base = onenand->dma_addr;
 	int status;
@@ -686,7 +686,7 @@ static int s5pc110_read_bufferram(struct mtd_info *mtd, int area,
 		dev_err(dev, "Couldn't map a %d byte buffer for DMA\n", count);
 		goto normal;
 	}
-	err = s5pc110_dma_ops((void *) dma_dst, (void *) dma_src,
+	err = s5pc110_dma_ops(dma_dst, dma_src,
 			count, S5PC110_DMA_DIR_READ);
 
 	if (page_dma)
diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
new file mode 100644
index 00000000000..f8acfa4310e
--- /dev/null
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -0,0 +1,17 @@
+menuconfig MTD_SPI_NOR
+	tristate "SPI-NOR device support"
+	depends on MTD
+	help
+	  This is the framework for the SPI NOR which can be used by the SPI
+	  device drivers and the SPI-NOR device driver.
+
+if MTD_SPI_NOR
+
+config SPI_FSL_QUADSPI
+	tristate "Freescale Quad SPI controller"
+	depends on ARCH_MXC
+	help
+	  This enables support for the Quad SPI controller in master mode.
+	  We only connect the NOR to this controller now.
+
+endif # MTD_SPI_NOR
diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile
new file mode 100644
index 00000000000..6a7ce146224
--- /dev/null
+++ b/drivers/mtd/spi-nor/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_MTD_SPI_NOR)	+= spi-nor.o
+obj-$(CONFIG_SPI_FSL_QUADSPI)	+= fsl-quadspi.o
diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c
new file mode 100644
index 00000000000..8d659a2888d
--- /dev/null
+++ b/drivers/mtd/spi-nor/fsl-quadspi.c
@@ -0,0 +1,1009 @@
+/*
+ * Freescale QuadSPI driver.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/timer.h>
+#include <linux/jiffies.h>
+#include <linux/completion.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+
+/* The registers */
+#define QUADSPI_MCR			0x00
+#define QUADSPI_MCR_RESERVED_SHIFT	16
+#define QUADSPI_MCR_RESERVED_MASK	(0xF << QUADSPI_MCR_RESERVED_SHIFT)
+#define QUADSPI_MCR_MDIS_SHIFT		14
+#define QUADSPI_MCR_MDIS_MASK		(1 << QUADSPI_MCR_MDIS_SHIFT)
+#define QUADSPI_MCR_CLR_TXF_SHIFT	11
+#define QUADSPI_MCR_CLR_TXF_MASK	(1 << QUADSPI_MCR_CLR_TXF_SHIFT)
+#define QUADSPI_MCR_CLR_RXF_SHIFT	10
+#define QUADSPI_MCR_CLR_RXF_MASK	(1 << QUADSPI_MCR_CLR_RXF_SHIFT)
+#define QUADSPI_MCR_DDR_EN_SHIFT	7
+#define QUADSPI_MCR_DDR_EN_MASK		(1 << QUADSPI_MCR_DDR_EN_SHIFT)
+#define QUADSPI_MCR_END_CFG_SHIFT	2
+#define QUADSPI_MCR_END_CFG_MASK	(3 << QUADSPI_MCR_END_CFG_SHIFT)
+#define QUADSPI_MCR_SWRSTHD_SHIFT	1
+#define QUADSPI_MCR_SWRSTHD_MASK	(1 << QUADSPI_MCR_SWRSTHD_SHIFT)
+#define QUADSPI_MCR_SWRSTSD_SHIFT	0
+#define QUADSPI_MCR_SWRSTSD_MASK	(1 << QUADSPI_MCR_SWRSTSD_SHIFT)
+
+#define QUADSPI_IPCR			0x08
+#define QUADSPI_IPCR_SEQID_SHIFT	24
+#define QUADSPI_IPCR_SEQID_MASK		(0xF << QUADSPI_IPCR_SEQID_SHIFT)
+
+#define QUADSPI_BUF0CR			0x10
+#define QUADSPI_BUF1CR			0x14
+#define QUADSPI_BUF2CR			0x18
+#define QUADSPI_BUFXCR_INVALID_MSTRID	0xe
+
+#define QUADSPI_BUF3CR			0x1c
+#define QUADSPI_BUF3CR_ALLMST_SHIFT	31
+#define QUADSPI_BUF3CR_ALLMST		(1 << QUADSPI_BUF3CR_ALLMST_SHIFT)
+
+#define QUADSPI_BFGENCR			0x20
+#define QUADSPI_BFGENCR_PAR_EN_SHIFT	16
+#define QUADSPI_BFGENCR_PAR_EN_MASK	(1 << (QUADSPI_BFGENCR_PAR_EN_SHIFT))
+#define QUADSPI_BFGENCR_SEQID_SHIFT	12
+#define QUADSPI_BFGENCR_SEQID_MASK	(0xF << QUADSPI_BFGENCR_SEQID_SHIFT)
+
+#define QUADSPI_BUF0IND			0x30
+#define QUADSPI_BUF1IND			0x34
+#define QUADSPI_BUF2IND			0x38
+#define QUADSPI_SFAR			0x100
+
+#define QUADSPI_SMPR			0x108
+#define QUADSPI_SMPR_DDRSMP_SHIFT	16
+#define QUADSPI_SMPR_DDRSMP_MASK	(7 << QUADSPI_SMPR_DDRSMP_SHIFT)
+#define QUADSPI_SMPR_FSDLY_SHIFT	6
+#define QUADSPI_SMPR_FSDLY_MASK		(1 << QUADSPI_SMPR_FSDLY_SHIFT)
+#define QUADSPI_SMPR_FSPHS_SHIFT	5
+#define QUADSPI_SMPR_FSPHS_MASK		(1 << QUADSPI_SMPR_FSPHS_SHIFT)
+#define QUADSPI_SMPR_HSENA_SHIFT	0
+#define QUADSPI_SMPR_HSENA_MASK		(1 << QUADSPI_SMPR_HSENA_SHIFT)
+
+#define QUADSPI_RBSR			0x10c
+#define QUADSPI_RBSR_RDBFL_SHIFT	8
+#define QUADSPI_RBSR_RDBFL_MASK		(0x3F << QUADSPI_RBSR_RDBFL_SHIFT)
+
+#define QUADSPI_RBCT			0x110
+#define QUADSPI_RBCT_WMRK_MASK		0x1F
+#define QUADSPI_RBCT_RXBRD_SHIFT	8
+#define QUADSPI_RBCT_RXBRD_USEIPS	(0x1 << QUADSPI_RBCT_RXBRD_SHIFT)
+
+#define QUADSPI_TBSR			0x150
+#define QUADSPI_TBDR			0x154
+#define QUADSPI_SR			0x15c
+#define QUADSPI_SR_IP_ACC_SHIFT		1
+#define QUADSPI_SR_IP_ACC_MASK		(0x1 << QUADSPI_SR_IP_ACC_SHIFT)
+#define QUADSPI_SR_AHB_ACC_SHIFT	2
+#define QUADSPI_SR_AHB_ACC_MASK		(0x1 << QUADSPI_SR_AHB_ACC_SHIFT)
+
+#define QUADSPI_FR			0x160
+#define QUADSPI_FR_TFF_MASK		0x1
+
+#define QUADSPI_SFA1AD			0x180
+#define QUADSPI_SFA2AD			0x184
+#define QUADSPI_SFB1AD			0x188
+#define QUADSPI_SFB2AD			0x18c
+#define QUADSPI_RBDR			0x200
+
+#define QUADSPI_LUTKEY			0x300
+#define QUADSPI_LUTKEY_VALUE		0x5AF05AF0
+
+#define QUADSPI_LCKCR			0x304
+#define QUADSPI_LCKER_LOCK		0x1
+#define QUADSPI_LCKER_UNLOCK		0x2
+
+#define QUADSPI_RSER			0x164
+#define QUADSPI_RSER_TFIE		(0x1 << 0)
+
+#define QUADSPI_LUT_BASE		0x310
+
+/*
+ * The definition of the LUT register shows below:
+ *
+ *  ---------------------------------------------------
+ *  | INSTR1 | PAD1 | OPRND1 | INSTR0 | PAD0 | OPRND0 |
+ *  ---------------------------------------------------
+ */
+#define OPRND0_SHIFT		0
+#define PAD0_SHIFT		8
+#define INSTR0_SHIFT		10
+#define OPRND1_SHIFT		16
+
+/* Instruction set for the LUT register. */
+#define LUT_STOP		0
+#define LUT_CMD			1
+#define LUT_ADDR		2
+#define LUT_DUMMY		3
+#define LUT_MODE		4
+#define LUT_MODE2		5
+#define LUT_MODE4		6
+#define LUT_READ		7
+#define LUT_WRITE		8
+#define LUT_JMP_ON_CS		9
+#define LUT_ADDR_DDR		10
+#define LUT_MODE_DDR		11
+#define LUT_MODE2_DDR		12
+#define LUT_MODE4_DDR		13
+#define LUT_READ_DDR		14
+#define LUT_WRITE_DDR		15
+#define LUT_DATA_LEARN		16
+
+/*
+ * The PAD definitions for LUT register.
+ *
+ * The pad stands for the lines number of IO[0:3].
+ * For example, the Quad read need four IO lines, so you should
+ * set LUT_PAD4 which means we use four IO lines.
+ */
+#define LUT_PAD1		0
+#define LUT_PAD2		1
+#define LUT_PAD4		2
+
+/* Oprands for the LUT register. */
+#define ADDR24BIT		0x18
+#define ADDR32BIT		0x20
+
+/* Macros for constructing the LUT register. */
+#define LUT0(ins, pad, opr)						\
+		(((opr) << OPRND0_SHIFT) | ((LUT_##pad) << PAD0_SHIFT) | \
+		((LUT_##ins) << INSTR0_SHIFT))
+
+#define LUT1(ins, pad, opr)	(LUT0(ins, pad, opr) << OPRND1_SHIFT)
+
+/* other macros for LUT register. */
+#define QUADSPI_LUT(x)          (QUADSPI_LUT_BASE + (x) * 4)
+#define QUADSPI_LUT_NUM		64
+
+/* SEQID -- we can have 16 seqids at most. */
+#define SEQID_QUAD_READ		0
+#define SEQID_WREN		1
+#define SEQID_WRDI		2
+#define SEQID_RDSR		3
+#define SEQID_SE		4
+#define SEQID_CHIP_ERASE	5
+#define SEQID_PP		6
+#define SEQID_RDID		7
+#define SEQID_WRSR		8
+#define SEQID_RDCR		9
+#define SEQID_EN4B		10
+#define SEQID_BRWR		11
+
+enum fsl_qspi_devtype {
+	FSL_QUADSPI_VYBRID,
+	FSL_QUADSPI_IMX6SX,
+};
+
+struct fsl_qspi_devtype_data {
+	enum fsl_qspi_devtype devtype;
+	int rxfifo;
+	int txfifo;
+};
+
+static struct fsl_qspi_devtype_data vybrid_data = {
+	.devtype = FSL_QUADSPI_VYBRID,
+	.rxfifo = 128,
+	.txfifo = 64
+};
+
+static struct fsl_qspi_devtype_data imx6sx_data = {
+	.devtype = FSL_QUADSPI_IMX6SX,
+	.rxfifo = 128,
+	.txfifo = 512
+};
+
+#define FSL_QSPI_MAX_CHIP	4
+struct fsl_qspi {
+	struct mtd_info mtd[FSL_QSPI_MAX_CHIP];
+	struct spi_nor nor[FSL_QSPI_MAX_CHIP];
+	void __iomem *iobase;
+	void __iomem *ahb_base; /* Used when read from AHB bus */
+	u32 memmap_phy;
+	struct clk *clk, *clk_en;
+	struct device *dev;
+	struct completion c;
+	struct fsl_qspi_devtype_data *devtype_data;
+	u32 nor_size;
+	u32 nor_num;
+	u32 clk_rate;
+	unsigned int chip_base_addr; /* We may support two chips. */
+};
+
+static inline int is_vybrid_qspi(struct fsl_qspi *q)
+{
+	return q->devtype_data->devtype == FSL_QUADSPI_VYBRID;
+}
+
+static inline int is_imx6sx_qspi(struct fsl_qspi *q)
+{
+	return q->devtype_data->devtype == FSL_QUADSPI_IMX6SX;
+}
+
+/*
+ * An IC bug makes us to re-arrange the 32-bit data.
+ * The following chips, such as IMX6SLX, have fixed this bug.
+ */
+static inline u32 fsl_qspi_endian_xchg(struct fsl_qspi *q, u32 a)
+{
+	return is_vybrid_qspi(q) ? __swab32(a) : a;
+}
+
+static inline void fsl_qspi_unlock_lut(struct fsl_qspi *q)
+{
+	writel(QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
+	writel(QUADSPI_LCKER_UNLOCK, q->iobase + QUADSPI_LCKCR);
+}
+
+static inline void fsl_qspi_lock_lut(struct fsl_qspi *q)
+{
+	writel(QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
+	writel(QUADSPI_LCKER_LOCK, q->iobase + QUADSPI_LCKCR);
+}
+
+static irqreturn_t fsl_qspi_irq_handler(int irq, void *dev_id)
+{
+	struct fsl_qspi *q = dev_id;
+	u32 reg;
+
+	/* clear interrupt */
+	reg = readl(q->iobase + QUADSPI_FR);
+	writel(reg, q->iobase + QUADSPI_FR);
+
+	if (reg & QUADSPI_FR_TFF_MASK)
+		complete(&q->c);
+
+	dev_dbg(q->dev, "QUADSPI_FR : 0x%.8x:0x%.8x\n", q->chip_base_addr, reg);
+	return IRQ_HANDLED;
+}
+
+static void fsl_qspi_init_lut(struct fsl_qspi *q)
+{
+	void __iomem *base = q->iobase;
+	int rxfifo = q->devtype_data->rxfifo;
+	u32 lut_base;
+	u8 cmd, addrlen, dummy;
+	int i;
+
+	fsl_qspi_unlock_lut(q);
+
+	/* Clear all the LUT table */
+	for (i = 0; i < QUADSPI_LUT_NUM; i++)
+		writel(0, base + QUADSPI_LUT_BASE + i * 4);
+
+	/* Quad Read */
+	lut_base = SEQID_QUAD_READ * 4;
+
+	if (q->nor_size <= SZ_16M) {
+		cmd = SPINOR_OP_READ_1_1_4;
+		addrlen = ADDR24BIT;
+		dummy = 8;
+	} else {
+		/* use the 4-byte address */
+		cmd = SPINOR_OP_READ_1_1_4;
+		addrlen = ADDR32BIT;
+		dummy = 8;
+	}
+
+	writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+			base + QUADSPI_LUT(lut_base));
+	writel(LUT0(DUMMY, PAD1, dummy) | LUT1(READ, PAD4, rxfifo),
+			base + QUADSPI_LUT(lut_base + 1));
+
+	/* Write enable */
+	lut_base = SEQID_WREN * 4;
+	writel(LUT0(CMD, PAD1, SPINOR_OP_WREN), base + QUADSPI_LUT(lut_base));
+
+	/* Page Program */
+	lut_base = SEQID_PP * 4;
+
+	if (q->nor_size <= SZ_16M) {
+		cmd = SPINOR_OP_PP;
+		addrlen = ADDR24BIT;
+	} else {
+		/* use the 4-byte address */
+		cmd = SPINOR_OP_PP;
+		addrlen = ADDR32BIT;
+	}
+
+	writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+			base + QUADSPI_LUT(lut_base));
+	writel(LUT0(WRITE, PAD1, 0), base + QUADSPI_LUT(lut_base + 1));
+
+	/* Read Status */
+	lut_base = SEQID_RDSR * 4;
+	writel(LUT0(CMD, PAD1, SPINOR_OP_RDSR) | LUT1(READ, PAD1, 0x1),
+			base + QUADSPI_LUT(lut_base));
+
+	/* Erase a sector */
+	lut_base = SEQID_SE * 4;
+
+	if (q->nor_size <= SZ_16M) {
+		cmd = SPINOR_OP_SE;
+		addrlen = ADDR24BIT;
+	} else {
+		/* use the 4-byte address */
+		cmd = SPINOR_OP_SE;
+		addrlen = ADDR32BIT;
+	}
+
+	writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+			base + QUADSPI_LUT(lut_base));
+
+	/* Erase the whole chip */
+	lut_base = SEQID_CHIP_ERASE * 4;
+	writel(LUT0(CMD, PAD1, SPINOR_OP_CHIP_ERASE),
+			base + QUADSPI_LUT(lut_base));
+
+	/* READ ID */
+	lut_base = SEQID_RDID * 4;
+	writel(LUT0(CMD, PAD1, SPINOR_OP_RDID) | LUT1(READ, PAD1, 0x8),
+			base + QUADSPI_LUT(lut_base));
+
+	/* Write Register */
+	lut_base = SEQID_WRSR * 4;
+	writel(LUT0(CMD, PAD1, SPINOR_OP_WRSR) | LUT1(WRITE, PAD1, 0x2),
+			base + QUADSPI_LUT(lut_base));
+
+	/* Read Configuration Register */
+	lut_base = SEQID_RDCR * 4;
+	writel(LUT0(CMD, PAD1, SPINOR_OP_RDCR) | LUT1(READ, PAD1, 0x1),
+			base + QUADSPI_LUT(lut_base));
+
+	/* Write disable */
+	lut_base = SEQID_WRDI * 4;
+	writel(LUT0(CMD, PAD1, SPINOR_OP_WRDI), base + QUADSPI_LUT(lut_base));
+
+	/* Enter 4 Byte Mode (Micron) */
+	lut_base = SEQID_EN4B * 4;
+	writel(LUT0(CMD, PAD1, SPINOR_OP_EN4B), base + QUADSPI_LUT(lut_base));
+
+	/* Enter 4 Byte Mode (Spansion) */
+	lut_base = SEQID_BRWR * 4;
+	writel(LUT0(CMD, PAD1, SPINOR_OP_BRWR), base + QUADSPI_LUT(lut_base));
+
+	fsl_qspi_lock_lut(q);
+}
+
+/* Get the SEQID for the command */
+static int fsl_qspi_get_seqid(struct fsl_qspi *q, u8 cmd)
+{
+	switch (cmd) {
+	case SPINOR_OP_READ_1_1_4:
+		return SEQID_QUAD_READ;
+	case SPINOR_OP_WREN:
+		return SEQID_WREN;
+	case SPINOR_OP_WRDI:
+		return SEQID_WRDI;
+	case SPINOR_OP_RDSR:
+		return SEQID_RDSR;
+	case SPINOR_OP_SE:
+		return SEQID_SE;
+	case SPINOR_OP_CHIP_ERASE:
+		return SEQID_CHIP_ERASE;
+	case SPINOR_OP_PP:
+		return SEQID_PP;
+	case SPINOR_OP_RDID:
+		return SEQID_RDID;
+	case SPINOR_OP_WRSR:
+		return SEQID_WRSR;
+	case SPINOR_OP_RDCR:
+		return SEQID_RDCR;
+	case SPINOR_OP_EN4B:
+		return SEQID_EN4B;
+	case SPINOR_OP_BRWR:
+		return SEQID_BRWR;
+	default:
+		dev_err(q->dev, "Unsupported cmd 0x%.2x\n", cmd);
+		break;
+	}
+	return -EINVAL;
+}
+
+static int
+fsl_qspi_runcmd(struct fsl_qspi *q, u8 cmd, unsigned int addr, int len)
+{
+	void __iomem *base = q->iobase;
+	int seqid;
+	u32 reg, reg2;
+	int err;
+
+	init_completion(&q->c);
+	dev_dbg(q->dev, "to 0x%.8x:0x%.8x, len:%d, cmd:%.2x\n",
+			q->chip_base_addr, addr, len, cmd);
+
+	/* save the reg */
+	reg = readl(base + QUADSPI_MCR);
+
+	writel(q->memmap_phy + q->chip_base_addr + addr, base + QUADSPI_SFAR);
+	writel(QUADSPI_RBCT_WMRK_MASK | QUADSPI_RBCT_RXBRD_USEIPS,
+			base + QUADSPI_RBCT);
+	writel(reg | QUADSPI_MCR_CLR_RXF_MASK, base + QUADSPI_MCR);
+
+	do {
+		reg2 = readl(base + QUADSPI_SR);
+		if (reg2 & (QUADSPI_SR_IP_ACC_MASK | QUADSPI_SR_AHB_ACC_MASK)) {
+			udelay(1);
+			dev_dbg(q->dev, "The controller is busy, 0x%x\n", reg2);
+			continue;
+		}
+		break;
+	} while (1);
+
+	/* trigger the LUT now */
+	seqid = fsl_qspi_get_seqid(q, cmd);
+	writel((seqid << QUADSPI_IPCR_SEQID_SHIFT) | len, base + QUADSPI_IPCR);
+
+	/* Wait for the interrupt. */
+	err = wait_for_completion_timeout(&q->c, msecs_to_jiffies(1000));
+	if (!err) {
+		dev_err(q->dev,
+			"cmd 0x%.2x timeout, addr@%.8x, FR:0x%.8x, SR:0x%.8x\n",
+			cmd, addr, readl(base + QUADSPI_FR),
+			readl(base + QUADSPI_SR));
+		err = -ETIMEDOUT;
+	} else {
+		err = 0;
+	}
+
+	/* restore the MCR */
+	writel(reg, base + QUADSPI_MCR);
+
+	return err;
+}
+
+/* Read out the data from the QUADSPI_RBDR buffer registers. */
+static void fsl_qspi_read_data(struct fsl_qspi *q, int len, u8 *rxbuf)
+{
+	u32 tmp;
+	int i = 0;
+
+	while (len > 0) {
+		tmp = readl(q->iobase + QUADSPI_RBDR + i * 4);
+		tmp = fsl_qspi_endian_xchg(q, tmp);
+		dev_dbg(q->dev, "chip addr:0x%.8x, rcv:0x%.8x\n",
+				q->chip_base_addr, tmp);
+
+		if (len >= 4) {
+			*((u32 *)rxbuf) = tmp;
+			rxbuf += 4;
+		} else {
+			memcpy(rxbuf, &tmp, len);
+			break;
+		}
+
+		len -= 4;
+		i++;
+	}
+}
+
+/*
+ * If we have changed the content of the flash by writing or erasing,
+ * we need to invalidate the AHB buffer. If we do not do so, we may read out
+ * the wrong data. The spec tells us reset the AHB domain and Serial Flash
+ * domain at the same time.
+ */
+static inline void fsl_qspi_invalid(struct fsl_qspi *q)
+{
+	u32 reg;
+
+	reg = readl(q->iobase + QUADSPI_MCR);
+	reg |= QUADSPI_MCR_SWRSTHD_MASK | QUADSPI_MCR_SWRSTSD_MASK;
+	writel(reg, q->iobase + QUADSPI_MCR);
+
+	/*
+	 * The minimum delay : 1 AHB + 2 SFCK clocks.
+	 * Delay 1 us is enough.
+	 */
+	udelay(1);
+
+	reg &= ~(QUADSPI_MCR_SWRSTHD_MASK | QUADSPI_MCR_SWRSTSD_MASK);
+	writel(reg, q->iobase + QUADSPI_MCR);
+}
+
+static int fsl_qspi_nor_write(struct fsl_qspi *q, struct spi_nor *nor,
+				u8 opcode, unsigned int to, u32 *txbuf,
+				unsigned count, size_t *retlen)
+{
+	int ret, i, j;
+	u32 tmp;
+
+	dev_dbg(q->dev, "to 0x%.8x:0x%.8x, len : %d\n",
+		q->chip_base_addr, to, count);
+
+	/* clear the TX FIFO. */
+	tmp = readl(q->iobase + QUADSPI_MCR);
+	writel(tmp | QUADSPI_MCR_CLR_RXF_MASK, q->iobase + QUADSPI_MCR);
+
+	/* fill the TX data to the FIFO */
+	for (j = 0, i = ((count + 3) / 4); j < i; j++) {
+		tmp = fsl_qspi_endian_xchg(q, *txbuf);
+		writel(tmp, q->iobase + QUADSPI_TBDR);
+		txbuf++;
+	}
+
+	/* Trigger it */
+	ret = fsl_qspi_runcmd(q, opcode, to, count);
+
+	if (ret == 0 && retlen)
+		*retlen += count;
+
+	return ret;
+}
+
+static void fsl_qspi_set_map_addr(struct fsl_qspi *q)
+{
+	int nor_size = q->nor_size;
+	void __iomem *base = q->iobase;
+
+	writel(nor_size + q->memmap_phy, base + QUADSPI_SFA1AD);
+	writel(nor_size * 2 + q->memmap_phy, base + QUADSPI_SFA2AD);
+	writel(nor_size * 3 + q->memmap_phy, base + QUADSPI_SFB1AD);
+	writel(nor_size * 4 + q->memmap_phy, base + QUADSPI_SFB2AD);
+}
+
+/*
+ * There are two different ways to read out the data from the flash:
+ *  the "IP Command Read" and the "AHB Command Read".
+ *
+ * The IC guy suggests we use the "AHB Command Read" which is faster
+ * then the "IP Command Read". (What's more is that there is a bug in
+ * the "IP Command Read" in the Vybrid.)
+ *
+ * After we set up the registers for the "AHB Command Read", we can use
+ * the memcpy to read the data directly. A "missed" access to the buffer
+ * causes the controller to clear the buffer, and use the sequence pointed
+ * by the QUADSPI_BFGENCR[SEQID] to initiate a read from the flash.
+ */
+static void fsl_qspi_init_abh_read(struct fsl_qspi *q)
+{
+	void __iomem *base = q->iobase;
+	int seqid;
+
+	/* AHB configuration for access buffer 0/1/2 .*/
+	writel(QUADSPI_BUFXCR_INVALID_MSTRID, base + QUADSPI_BUF0CR);
+	writel(QUADSPI_BUFXCR_INVALID_MSTRID, base + QUADSPI_BUF1CR);
+	writel(QUADSPI_BUFXCR_INVALID_MSTRID, base + QUADSPI_BUF2CR);
+	writel(QUADSPI_BUF3CR_ALLMST, base + QUADSPI_BUF3CR);
+
+	/* We only use the buffer3 */
+	writel(0, base + QUADSPI_BUF0IND);
+	writel(0, base + QUADSPI_BUF1IND);
+	writel(0, base + QUADSPI_BUF2IND);
+
+	/* Set the default lut sequence for AHB Read. */
+	seqid = fsl_qspi_get_seqid(q, q->nor[0].read_opcode);
+	writel(seqid << QUADSPI_BFGENCR_SEQID_SHIFT,
+		q->iobase + QUADSPI_BFGENCR);
+}
+
+/* We use this function to do some basic init for spi_nor_scan(). */
+static int fsl_qspi_nor_setup(struct fsl_qspi *q)
+{
+	void __iomem *base = q->iobase;
+	u32 reg;
+	int ret;
+
+	/* the default frequency, we will change it in the future.*/
+	ret = clk_set_rate(q->clk, 66000000);
+	if (ret)
+		return ret;
+
+	/* Init the LUT table. */
+	fsl_qspi_init_lut(q);
+
+	/* Disable the module */
+	writel(QUADSPI_MCR_MDIS_MASK | QUADSPI_MCR_RESERVED_MASK,
+			base + QUADSPI_MCR);
+
+	reg = readl(base + QUADSPI_SMPR);
+	writel(reg & ~(QUADSPI_SMPR_FSDLY_MASK
+			| QUADSPI_SMPR_FSPHS_MASK
+			| QUADSPI_SMPR_HSENA_MASK
+			| QUADSPI_SMPR_DDRSMP_MASK), base + QUADSPI_SMPR);
+
+	/* Enable the module */
+	writel(QUADSPI_MCR_RESERVED_MASK | QUADSPI_MCR_END_CFG_MASK,
+			base + QUADSPI_MCR);
+
+	/* enable the interrupt */
+	writel(QUADSPI_RSER_TFIE, q->iobase + QUADSPI_RSER);
+
+	return 0;
+}
+
+static int fsl_qspi_nor_setup_last(struct fsl_qspi *q)
+{
+	unsigned long rate = q->clk_rate;
+	int ret;
+
+	if (is_imx6sx_qspi(q))
+		rate *= 4;
+
+	ret = clk_set_rate(q->clk, rate);
+	if (ret)
+		return ret;
+
+	/* Init the LUT table again. */
+	fsl_qspi_init_lut(q);
+
+	/* Init for AHB read */
+	fsl_qspi_init_abh_read(q);
+
+	return 0;
+}
+
+static struct of_device_id fsl_qspi_dt_ids[] = {
+	{ .compatible = "fsl,vf610-qspi", .data = (void *)&vybrid_data, },
+	{ .compatible = "fsl,imx6sx-qspi", .data = (void *)&imx6sx_data, },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, fsl_qspi_dt_ids);
+
+static void fsl_qspi_set_base_addr(struct fsl_qspi *q, struct spi_nor *nor)
+{
+	q->chip_base_addr = q->nor_size * (nor - q->nor);
+}
+
+static int fsl_qspi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+	int ret;
+	struct fsl_qspi *q = nor->priv;
+
+	ret = fsl_qspi_runcmd(q, opcode, 0, len);
+	if (ret)
+		return ret;
+
+	fsl_qspi_read_data(q, len, buf);
+	return 0;
+}
+
+static int fsl_qspi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len,
+			int write_enable)
+{
+	struct fsl_qspi *q = nor->priv;
+	int ret;
+
+	if (!buf) {
+		ret = fsl_qspi_runcmd(q, opcode, 0, 1);
+		if (ret)
+			return ret;
+
+		if (opcode == SPINOR_OP_CHIP_ERASE)
+			fsl_qspi_invalid(q);
+
+	} else if (len > 0) {
+		ret = fsl_qspi_nor_write(q, nor, opcode, 0,
+					(u32 *)buf, len, NULL);
+	} else {
+		dev_err(q->dev, "invalid cmd %d\n", opcode);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static void fsl_qspi_write(struct spi_nor *nor, loff_t to,
+		size_t len, size_t *retlen, const u_char *buf)
+{
+	struct fsl_qspi *q = nor->priv;
+
+	fsl_qspi_nor_write(q, nor, nor->program_opcode, to,
+				(u32 *)buf, len, retlen);
+
+	/* invalid the data in the AHB buffer. */
+	fsl_qspi_invalid(q);
+}
+
+static int fsl_qspi_read(struct spi_nor *nor, loff_t from,
+		size_t len, size_t *retlen, u_char *buf)
+{
+	struct fsl_qspi *q = nor->priv;
+	u8 cmd = nor->read_opcode;
+	int ret;
+
+	dev_dbg(q->dev, "cmd [%x],read from (0x%p, 0x%.8x, 0x%.8x),len:%d\n",
+		cmd, q->ahb_base, q->chip_base_addr, (unsigned int)from, len);
+
+	/* Wait until the previous command is finished. */
+	ret = nor->wait_till_ready(nor);
+	if (ret)
+		return ret;
+
+	/* Read out the data directly from the AHB buffer.*/
+	memcpy(buf, q->ahb_base + q->chip_base_addr + from, len);
+
+	*retlen += len;
+	return 0;
+}
+
+static int fsl_qspi_erase(struct spi_nor *nor, loff_t offs)
+{
+	struct fsl_qspi *q = nor->priv;
+	int ret;
+
+	dev_dbg(nor->dev, "%dKiB at 0x%08x:0x%08x\n",
+		nor->mtd->erasesize / 1024, q->chip_base_addr, (u32)offs);
+
+	/* Wait until finished previous write command. */
+	ret = nor->wait_till_ready(nor);
+	if (ret)
+		return ret;
+
+	/* Send write enable, then erase commands. */
+	ret = nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0, 0);
+	if (ret)
+		return ret;
+
+	ret = fsl_qspi_runcmd(q, nor->erase_opcode, offs, 0);
+	if (ret)
+		return ret;
+
+	fsl_qspi_invalid(q);
+	return 0;
+}
+
+static int fsl_qspi_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct fsl_qspi *q = nor->priv;
+	int ret;
+
+	ret = clk_enable(q->clk_en);
+	if (ret)
+		return ret;
+
+	ret = clk_enable(q->clk);
+	if (ret) {
+		clk_disable(q->clk_en);
+		return ret;
+	}
+
+	fsl_qspi_set_base_addr(q, nor);
+	return 0;
+}
+
+static void fsl_qspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct fsl_qspi *q = nor->priv;
+
+	clk_disable(q->clk);
+	clk_disable(q->clk_en);
+}
+
+static int fsl_qspi_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct mtd_part_parser_data ppdata;
+	struct device *dev = &pdev->dev;
+	struct fsl_qspi *q;
+	struct resource *res;
+	struct spi_nor *nor;
+	struct mtd_info *mtd;
+	int ret, i = 0;
+	bool has_second_chip = false;
+	const struct of_device_id *of_id =
+			of_match_device(fsl_qspi_dt_ids, &pdev->dev);
+
+	q = devm_kzalloc(dev, sizeof(*q), GFP_KERNEL);
+	if (!q)
+		return -ENOMEM;
+
+	q->nor_num = of_get_child_count(dev->of_node);
+	if (!q->nor_num || q->nor_num > FSL_QSPI_MAX_CHIP)
+		return -ENODEV;
+
+	/* find the resources */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "QuadSPI");
+	q->iobase = devm_ioremap_resource(dev, res);
+	if (IS_ERR(q->iobase)) {
+		ret = PTR_ERR(q->iobase);
+		goto map_failed;
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+					"QuadSPI-memory");
+	q->ahb_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(q->ahb_base)) {
+		ret = PTR_ERR(q->ahb_base);
+		goto map_failed;
+	}
+	q->memmap_phy = res->start;
+
+	/* find the clocks */
+	q->clk_en = devm_clk_get(dev, "qspi_en");
+	if (IS_ERR(q->clk_en)) {
+		ret = PTR_ERR(q->clk_en);
+		goto map_failed;
+	}
+
+	q->clk = devm_clk_get(dev, "qspi");
+	if (IS_ERR(q->clk)) {
+		ret = PTR_ERR(q->clk);
+		goto map_failed;
+	}
+
+	ret = clk_prepare_enable(q->clk_en);
+	if (ret) {
+		dev_err(dev, "can not enable the qspi_en clock\n");
+		goto map_failed;
+	}
+
+	ret = clk_prepare_enable(q->clk);
+	if (ret) {
+		clk_disable_unprepare(q->clk_en);
+		dev_err(dev, "can not enable the qspi clock\n");
+		goto map_failed;
+	}
+
+	/* find the irq */
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0) {
+		dev_err(dev, "failed to get the irq\n");
+		goto irq_failed;
+	}
+
+	ret = devm_request_irq(dev, ret,
+			fsl_qspi_irq_handler, 0, pdev->name, q);
+	if (ret) {
+		dev_err(dev, "failed to request irq.\n");
+		goto irq_failed;
+	}
+
+	q->dev = dev;
+	q->devtype_data = (struct fsl_qspi_devtype_data *)of_id->data;
+	platform_set_drvdata(pdev, q);
+
+	ret = fsl_qspi_nor_setup(q);
+	if (ret)
+		goto irq_failed;
+
+	if (of_get_property(np, "fsl,qspi-has-second-chip", NULL))
+		has_second_chip = true;
+
+	/* iterate the subnodes. */
+	for_each_available_child_of_node(dev->of_node, np) {
+		const struct spi_device_id *id;
+		char modalias[40];
+
+		/* skip the holes */
+		if (!has_second_chip)
+			i *= 2;
+
+		nor = &q->nor[i];
+		mtd = &q->mtd[i];
+
+		nor->mtd = mtd;
+		nor->dev = dev;
+		nor->priv = q;
+		mtd->priv = nor;
+
+		/* fill the hooks */
+		nor->read_reg = fsl_qspi_read_reg;
+		nor->write_reg = fsl_qspi_write_reg;
+		nor->read = fsl_qspi_read;
+		nor->write = fsl_qspi_write;
+		nor->erase = fsl_qspi_erase;
+
+		nor->prepare = fsl_qspi_prep;
+		nor->unprepare = fsl_qspi_unprep;
+
+		if (of_modalias_node(np, modalias, sizeof(modalias)) < 0)
+			goto map_failed;
+
+		id = spi_nor_match_id(modalias);
+		if (!id)
+			goto map_failed;
+
+		ret = of_property_read_u32(np, "spi-max-frequency",
+				&q->clk_rate);
+		if (ret < 0)
+			goto map_failed;
+
+		/* set the chip address for READID */
+		fsl_qspi_set_base_addr(q, nor);
+
+		ret = spi_nor_scan(nor, id, SPI_NOR_QUAD);
+		if (ret)
+			goto map_failed;
+
+		ppdata.of_node = np;
+		ret = mtd_device_parse_register(mtd, NULL, &ppdata, NULL, 0);
+		if (ret)
+			goto map_failed;
+
+		/* Set the correct NOR size now. */
+		if (q->nor_size == 0) {
+			q->nor_size = mtd->size;
+
+			/* Map the SPI NOR to accessiable address */
+			fsl_qspi_set_map_addr(q);
+		}
+
+		/*
+		 * The TX FIFO is 64 bytes in the Vybrid, but the Page Program
+		 * may writes 265 bytes per time. The write is working in the
+		 * unit of the TX FIFO, not in the unit of the SPI NOR's page
+		 * size.
+		 *
+		 * So shrink the spi_nor->page_size if it is larger then the
+		 * TX FIFO.
+		 */
+		if (nor->page_size > q->devtype_data->txfifo)
+			nor->page_size = q->devtype_data->txfifo;
+
+		i++;
+	}
+
+	/* finish the rest init. */
+	ret = fsl_qspi_nor_setup_last(q);
+	if (ret)
+		goto last_init_failed;
+
+	clk_disable(q->clk);
+	clk_disable(q->clk_en);
+	dev_info(dev, "QuadSPI SPI NOR flash driver\n");
+	return 0;
+
+last_init_failed:
+	for (i = 0; i < q->nor_num; i++)
+		mtd_device_unregister(&q->mtd[i]);
+
+irq_failed:
+	clk_disable_unprepare(q->clk);
+	clk_disable_unprepare(q->clk_en);
+map_failed:
+	dev_err(dev, "Freescale QuadSPI probe failed\n");
+	return ret;
+}
+
+static int fsl_qspi_remove(struct platform_device *pdev)
+{
+	struct fsl_qspi *q = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < q->nor_num; i++)
+		mtd_device_unregister(&q->mtd[i]);
+
+	/* disable the hardware */
+	writel(QUADSPI_MCR_MDIS_MASK, q->iobase + QUADSPI_MCR);
+	writel(0x0, q->iobase + QUADSPI_RSER);
+
+	clk_unprepare(q->clk);
+	clk_unprepare(q->clk_en);
+	return 0;
+}
+
+static struct platform_driver fsl_qspi_driver = {
+	.driver = {
+		.name	= "fsl-quadspi",
+		.bus	= &platform_bus_type,
+		.owner	= THIS_MODULE,
+		.of_match_table = fsl_qspi_dt_ids,
+	},
+	.probe          = fsl_qspi_probe,
+	.remove		= fsl_qspi_remove,
+};
+module_platform_driver(fsl_qspi_driver);
+
+MODULE_DESCRIPTION("Freescale QuadSPI Controller Driver");
+MODULE_AUTHOR("Freescale Semiconductor Inc.");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
new file mode 100644
index 00000000000..c713c865671
--- /dev/null
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -0,0 +1,1107 @@
+/*
+ * Based on m25p80.c, by Mike Lavender (mike@steroidmicros.com), with
+ * influence from lart.c (Abraham Van Der Merwe) and mtd_dataflash.c
+ *
+ * Copyright (C) 2005, Intec Automation Inc.
+ * Copyright (C) 2014, Freescale Semiconductor, Inc.
+ *
+ * This code is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/math64.h>
+
+#include <linux/mtd/cfi.h>
+#include <linux/mtd/mtd.h>
+#include <linux/of_platform.h>
+#include <linux/spi/flash.h>
+#include <linux/mtd/spi-nor.h>
+
+/* Define max times to check status register before we give up. */
+#define	MAX_READY_WAIT_JIFFIES	(40 * HZ) /* M25P16 specs 40s max chip erase */
+
+#define JEDEC_MFR(_jedec_id)	((_jedec_id) >> 16)
+
+/*
+ * Read the status register, returning its value in the location
+ * Return the status register value.
+ * Returns negative if error occurred.
+ */
+static int read_sr(struct spi_nor *nor)
+{
+	int ret;
+	u8 val;
+
+	ret = nor->read_reg(nor, SPINOR_OP_RDSR, &val, 1);
+	if (ret < 0) {
+		pr_err("error %d reading SR\n", (int) ret);
+		return ret;
+	}
+
+	return val;
+}
+
+/*
+ * Read configuration register, returning its value in the
+ * location. Return the configuration register value.
+ * Returns negative if error occured.
+ */
+static int read_cr(struct spi_nor *nor)
+{
+	int ret;
+	u8 val;
+
+	ret = nor->read_reg(nor, SPINOR_OP_RDCR, &val, 1);
+	if (ret < 0) {
+		dev_err(nor->dev, "error %d reading CR\n", ret);
+		return ret;
+	}
+
+	return val;
+}
+
+/*
+ * Dummy Cycle calculation for different type of read.
+ * It can be used to support more commands with
+ * different dummy cycle requirements.
+ */
+static inline int spi_nor_read_dummy_cycles(struct spi_nor *nor)
+{
+	switch (nor->flash_read) {
+	case SPI_NOR_FAST:
+	case SPI_NOR_DUAL:
+	case SPI_NOR_QUAD:
+		return 1;
+	case SPI_NOR_NORMAL:
+		return 0;
+	}
+	return 0;
+}
+
+/*
+ * Write status register 1 byte
+ * Returns negative if error occurred.
+ */
+static inline int write_sr(struct spi_nor *nor, u8 val)
+{
+	nor->cmd_buf[0] = val;
+	return nor->write_reg(nor, SPINOR_OP_WRSR, nor->cmd_buf, 1, 0);
+}
+
+/*
+ * Set write enable latch with Write Enable command.
+ * Returns negative if error occurred.
+ */
+static inline int write_enable(struct spi_nor *nor)
+{
+	return nor->write_reg(nor, SPINOR_OP_WREN, NULL, 0, 0);
+}
+
+/*
+ * Send write disble instruction to the chip.
+ */
+static inline int write_disable(struct spi_nor *nor)
+{
+	return nor->write_reg(nor, SPINOR_OP_WRDI, NULL, 0, 0);
+}
+
+static inline struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd)
+{
+	return mtd->priv;
+}
+
+/* Enable/disable 4-byte addressing mode. */
+static inline int set_4byte(struct spi_nor *nor, u32 jedec_id, int enable)
+{
+	int status;
+	bool need_wren = false;
+	u8 cmd;
+
+	switch (JEDEC_MFR(jedec_id)) {
+	case CFI_MFR_ST: /* Micron, actually */
+		/* Some Micron need WREN command; all will accept it */
+		need_wren = true;
+	case CFI_MFR_MACRONIX:
+	case 0xEF /* winbond */:
+		if (need_wren)
+			write_enable(nor);
+
+		cmd = enable ? SPINOR_OP_EN4B : SPINOR_OP_EX4B;
+		status = nor->write_reg(nor, cmd, NULL, 0, 0);
+		if (need_wren)
+			write_disable(nor);
+
+		return status;
+	default:
+		/* Spansion style */
+		nor->cmd_buf[0] = enable << 7;
+		return nor->write_reg(nor, SPINOR_OP_BRWR, nor->cmd_buf, 1, 0);
+	}
+}
+
+static int spi_nor_wait_till_ready(struct spi_nor *nor)
+{
+	unsigned long deadline;
+	int sr;
+
+	deadline = jiffies + MAX_READY_WAIT_JIFFIES;
+
+	do {
+		cond_resched();
+
+		sr = read_sr(nor);
+		if (sr < 0)
+			break;
+		else if (!(sr & SR_WIP))
+			return 0;
+	} while (!time_after_eq(jiffies, deadline));
+
+	return -ETIMEDOUT;
+}
+
+/*
+ * Service routine to read status register until ready, or timeout occurs.
+ * Returns non-zero if error.
+ */
+static int wait_till_ready(struct spi_nor *nor)
+{
+	return nor->wait_till_ready(nor);
+}
+
+/*
+ * Erase the whole flash memory
+ *
+ * Returns 0 if successful, non-zero otherwise.
+ */
+static int erase_chip(struct spi_nor *nor)
+{
+	int ret;
+
+	dev_dbg(nor->dev, " %lldKiB\n", (long long)(nor->mtd->size >> 10));
+
+	/* Wait until finished previous write command. */
+	ret = wait_till_ready(nor);
+	if (ret)
+		return ret;
+
+	/* Send write enable, then erase commands. */
+	write_enable(nor);
+
+	return nor->write_reg(nor, SPINOR_OP_CHIP_ERASE, NULL, 0, 0);
+}
+
+static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	int ret = 0;
+
+	mutex_lock(&nor->lock);
+
+	if (nor->prepare) {
+		ret = nor->prepare(nor, ops);
+		if (ret) {
+			dev_err(nor->dev, "failed in the preparation.\n");
+			mutex_unlock(&nor->lock);
+			return ret;
+		}
+	}
+	return ret;
+}
+
+static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	if (nor->unprepare)
+		nor->unprepare(nor, ops);
+	mutex_unlock(&nor->lock);
+}
+
+/*
+ * Erase an address range on the nor chip.  The address range may extend
+ * one or more erase sectors.  Return an error is there is a problem erasing.
+ */
+static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
+{
+	struct spi_nor *nor = mtd_to_spi_nor(mtd);
+	u32 addr, len;
+	uint32_t rem;
+	int ret;
+
+	dev_dbg(nor->dev, "at 0x%llx, len %lld\n", (long long)instr->addr,
+			(long long)instr->len);
+
+	div_u64_rem(instr->len, mtd->erasesize, &rem);
+	if (rem)
+		return -EINVAL;
+
+	addr = instr->addr;
+	len = instr->len;
+
+	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_ERASE);
+	if (ret)
+		return ret;
+
+	/* whole-chip erase? */
+	if (len == mtd->size) {
+		if (erase_chip(nor)) {
+			ret = -EIO;
+			goto erase_err;
+		}
+
+	/* REVISIT in some cases we could speed up erasing large regions
+	 * by using SPINOR_OP_SE instead of SPINOR_OP_BE_4K.  We may have set up
+	 * to use "small sector erase", but that's not always optimal.
+	 */
+
+	/* "sector"-at-a-time erase */
+	} else {
+		while (len) {
+			if (nor->erase(nor, addr)) {
+				ret = -EIO;
+				goto erase_err;
+			}
+
+			addr += mtd->erasesize;
+			len -= mtd->erasesize;
+		}
+	}
+
+	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_ERASE);
+
+	instr->state = MTD_ERASE_DONE;
+	mtd_erase_callback(instr);
+
+	return ret;
+
+erase_err:
+	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_ERASE);
+	instr->state = MTD_ERASE_FAILED;
+	return ret;
+}
+
+static int spi_nor_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
+{
+	struct spi_nor *nor = mtd_to_spi_nor(mtd);
+	uint32_t offset = ofs;
+	uint8_t status_old, status_new;
+	int ret = 0;
+
+	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_LOCK);
+	if (ret)
+		return ret;
+
+	/* Wait until finished previous command */
+	ret = wait_till_ready(nor);
+	if (ret)
+		goto err;
+
+	status_old = read_sr(nor);
+
+	if (offset < mtd->size - (mtd->size / 2))
+		status_new = status_old | SR_BP2 | SR_BP1 | SR_BP0;
+	else if (offset < mtd->size - (mtd->size / 4))
+		status_new = (status_old & ~SR_BP0) | SR_BP2 | SR_BP1;
+	else if (offset < mtd->size - (mtd->size / 8))
+		status_new = (status_old & ~SR_BP1) | SR_BP2 | SR_BP0;
+	else if (offset < mtd->size - (mtd->size / 16))
+		status_new = (status_old & ~(SR_BP0 | SR_BP1)) | SR_BP2;
+	else if (offset < mtd->size - (mtd->size / 32))
+		status_new = (status_old & ~SR_BP2) | SR_BP1 | SR_BP0;
+	else if (offset < mtd->size - (mtd->size / 64))
+		status_new = (status_old & ~(SR_BP2 | SR_BP0)) | SR_BP1;
+	else
+		status_new = (status_old & ~(SR_BP2 | SR_BP1)) | SR_BP0;
+
+	/* Only modify protection if it will not unlock other areas */
+	if ((status_new & (SR_BP2 | SR_BP1 | SR_BP0)) >
+				(status_old & (SR_BP2 | SR_BP1 | SR_BP0))) {
+		write_enable(nor);
+		ret = write_sr(nor, status_new);
+		if (ret)
+			goto err;
+	}
+
+err:
+	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_LOCK);
+	return ret;
+}
+
+static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
+{
+	struct spi_nor *nor = mtd_to_spi_nor(mtd);
+	uint32_t offset = ofs;
+	uint8_t status_old, status_new;
+	int ret = 0;
+
+	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_UNLOCK);
+	if (ret)
+		return ret;
+
+	/* Wait until finished previous command */
+	ret = wait_till_ready(nor);
+	if (ret)
+		goto err;
+
+	status_old = read_sr(nor);
+
+	if (offset+len > mtd->size - (mtd->size / 64))
+		status_new = status_old & ~(SR_BP2 | SR_BP1 | SR_BP0);
+	else if (offset+len > mtd->size - (mtd->size / 32))
+		status_new = (status_old & ~(SR_BP2 | SR_BP1)) | SR_BP0;
+	else if (offset+len > mtd->size - (mtd->size / 16))
+		status_new = (status_old & ~(SR_BP2 | SR_BP0)) | SR_BP1;
+	else if (offset+len > mtd->size - (mtd->size / 8))
+		status_new = (status_old & ~SR_BP2) | SR_BP1 | SR_BP0;
+	else if (offset+len > mtd->size - (mtd->size / 4))
+		status_new = (status_old & ~(SR_BP0 | SR_BP1)) | SR_BP2;
+	else if (offset+len > mtd->size - (mtd->size / 2))
+		status_new = (status_old & ~SR_BP1) | SR_BP2 | SR_BP0;
+	else
+		status_new = (status_old & ~SR_BP0) | SR_BP2 | SR_BP1;
+
+	/* Only modify protection if it will not lock other areas */
+	if ((status_new & (SR_BP2 | SR_BP1 | SR_BP0)) <
+				(status_old & (SR_BP2 | SR_BP1 | SR_BP0))) {
+		write_enable(nor);
+		ret = write_sr(nor, status_new);
+		if (ret)
+			goto err;
+	}
+
+err:
+	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_UNLOCK);
+	return ret;
+}
+
+struct flash_info {
+	/* JEDEC id zero means "no ID" (most older chips); otherwise it has
+	 * a high byte of zero plus three data bytes: the manufacturer id,
+	 * then a two byte device id.
+	 */
+	u32		jedec_id;
+	u16             ext_id;
+
+	/* The size listed here is what works with SPINOR_OP_SE, which isn't
+	 * necessarily called a "sector" by the vendor.
+	 */
+	unsigned	sector_size;
+	u16		n_sectors;
+
+	u16		page_size;
+	u16		addr_width;
+
+	u16		flags;
+#define	SECT_4K			0x01	/* SPINOR_OP_BE_4K works uniformly */
+#define	SPI_NOR_NO_ERASE	0x02	/* No erase command needed */
+#define	SST_WRITE		0x04	/* use SST byte programming */
+#define	SPI_NOR_NO_FR		0x08	/* Can't do fastread */
+#define	SECT_4K_PMC		0x10	/* SPINOR_OP_BE_4K_PMC works uniformly */
+#define	SPI_NOR_DUAL_READ	0x20    /* Flash supports Dual Read */
+#define	SPI_NOR_QUAD_READ	0x40    /* Flash supports Quad Read */
+};
+
+#define INFO(_jedec_id, _ext_id, _sector_size, _n_sectors, _flags)	\
+	((kernel_ulong_t)&(struct flash_info) {				\
+		.jedec_id = (_jedec_id),				\
+		.ext_id = (_ext_id),					\
+		.sector_size = (_sector_size),				\
+		.n_sectors = (_n_sectors),				\
+		.page_size = 256,					\
+		.flags = (_flags),					\
+	})
+
+#define CAT25_INFO(_sector_size, _n_sectors, _page_size, _addr_width, _flags)	\
+	((kernel_ulong_t)&(struct flash_info) {				\
+		.sector_size = (_sector_size),				\
+		.n_sectors = (_n_sectors),				\
+		.page_size = (_page_size),				\
+		.addr_width = (_addr_width),				\
+		.flags = (_flags),					\
+	})
+
+/* NOTE: double check command sets and memory organization when you add
+ * more nor chips.  This current list focusses on newer chips, which
+ * have been converging on command sets which including JEDEC ID.
+ */
+const struct spi_device_id spi_nor_ids[] = {
+	/* Atmel -- some are (confusingly) marketed as "DataFlash" */
+	{ "at25fs010",  INFO(0x1f6601, 0, 32 * 1024,   4, SECT_4K) },
+	{ "at25fs040",  INFO(0x1f6604, 0, 64 * 1024,   8, SECT_4K) },
+
+	{ "at25df041a", INFO(0x1f4401, 0, 64 * 1024,   8, SECT_4K) },
+	{ "at25df321a", INFO(0x1f4701, 0, 64 * 1024,  64, SECT_4K) },
+	{ "at25df641",  INFO(0x1f4800, 0, 64 * 1024, 128, SECT_4K) },
+
+	{ "at26f004",   INFO(0x1f0400, 0, 64 * 1024,  8, SECT_4K) },
+	{ "at26df081a", INFO(0x1f4501, 0, 64 * 1024, 16, SECT_4K) },
+	{ "at26df161a", INFO(0x1f4601, 0, 64 * 1024, 32, SECT_4K) },
+	{ "at26df321",  INFO(0x1f4700, 0, 64 * 1024, 64, SECT_4K) },
+
+	{ "at45db081d", INFO(0x1f2500, 0, 64 * 1024, 16, SECT_4K) },
+
+	/* EON -- en25xxx */
+	{ "en25f32",    INFO(0x1c3116, 0, 64 * 1024,   64, SECT_4K) },
+	{ "en25p32",    INFO(0x1c2016, 0, 64 * 1024,   64, 0) },
+	{ "en25q32b",   INFO(0x1c3016, 0, 64 * 1024,   64, 0) },
+	{ "en25p64",    INFO(0x1c2017, 0, 64 * 1024,  128, 0) },
+	{ "en25q64",    INFO(0x1c3017, 0, 64 * 1024,  128, SECT_4K) },
+	{ "en25qh256",  INFO(0x1c7019, 0, 64 * 1024,  512, 0) },
+
+	/* ESMT */
+	{ "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K) },
+
+	/* Everspin */
+	{ "mr25h256", CAT25_INFO( 32 * 1024, 1, 256, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+	{ "mr25h10",  CAT25_INFO(128 * 1024, 1, 256, 3, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+
+	/* GigaDevice */
+	{ "gd25q32", INFO(0xc84016, 0, 64 * 1024,  64, SECT_4K) },
+	{ "gd25q64", INFO(0xc84017, 0, 64 * 1024, 128, SECT_4K) },
+
+	/* Intel/Numonyx -- xxxs33b */
+	{ "160s33b",  INFO(0x898911, 0, 64 * 1024,  32, 0) },
+	{ "320s33b",  INFO(0x898912, 0, 64 * 1024,  64, 0) },
+	{ "640s33b",  INFO(0x898913, 0, 64 * 1024, 128, 0) },
+
+	/* Macronix */
+	{ "mx25l2005a",  INFO(0xc22012, 0, 64 * 1024,   4, SECT_4K) },
+	{ "mx25l4005a",  INFO(0xc22013, 0, 64 * 1024,   8, SECT_4K) },
+	{ "mx25l8005",   INFO(0xc22014, 0, 64 * 1024,  16, 0) },
+	{ "mx25l1606e",  INFO(0xc22015, 0, 64 * 1024,  32, SECT_4K) },
+	{ "mx25l3205d",  INFO(0xc22016, 0, 64 * 1024,  64, 0) },
+	{ "mx25l3255e",  INFO(0xc29e16, 0, 64 * 1024,  64, SECT_4K) },
+	{ "mx25l6405d",  INFO(0xc22017, 0, 64 * 1024, 128, 0) },
+	{ "mx25l12805d", INFO(0xc22018, 0, 64 * 1024, 256, 0) },
+	{ "mx25l12855e", INFO(0xc22618, 0, 64 * 1024, 256, 0) },
+	{ "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512, 0) },
+	{ "mx25l25655e", INFO(0xc22619, 0, 64 * 1024, 512, 0) },
+	{ "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_QUAD_READ) },
+	{ "mx66l1g55g",  INFO(0xc2261b, 0, 64 * 1024, 2048, SPI_NOR_QUAD_READ) },
+
+	/* Micron */
+	{ "n25q064",     INFO(0x20ba17, 0, 64 * 1024,  128, 0) },
+	{ "n25q128a11",  INFO(0x20bb18, 0, 64 * 1024,  256, 0) },
+	{ "n25q128a13",  INFO(0x20ba18, 0, 64 * 1024,  256, 0) },
+	{ "n25q256a",    INFO(0x20ba19, 0, 64 * 1024,  512, SECT_4K) },
+	{ "n25q512a",    INFO(0x20bb20, 0, 64 * 1024, 1024, SECT_4K) },
+
+	/* PMC */
+	{ "pm25lv512",   INFO(0,        0, 32 * 1024,    2, SECT_4K_PMC) },
+	{ "pm25lv010",   INFO(0,        0, 32 * 1024,    4, SECT_4K_PMC) },
+	{ "pm25lq032",   INFO(0x7f9d46, 0, 64 * 1024,   64, SECT_4K) },
+
+	/* Spansion -- single (large) sector size only, at least
+	 * for the chips listed here (without boot sectors).
+	 */
+	{ "s25sl032p",  INFO(0x010215, 0x4d00,  64 * 1024,  64, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "s25sl064p",  INFO(0x010216, 0x4d00,  64 * 1024, 128, 0) },
+	{ "s25fl256s0", INFO(0x010219, 0x4d00, 256 * 1024, 128, 0) },
+	{ "s25fl256s1", INFO(0x010219, 0x4d01,  64 * 1024, 512, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "s25fl512s",  INFO(0x010220, 0x4d00, 256 * 1024, 256, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "s70fl01gs",  INFO(0x010221, 0x4d00, 256 * 1024, 256, 0) },
+	{ "s25sl12800", INFO(0x012018, 0x0300, 256 * 1024,  64, 0) },
+	{ "s25sl12801", INFO(0x012018, 0x0301,  64 * 1024, 256, 0) },
+	{ "s25fl129p0", INFO(0x012018, 0x4d00, 256 * 1024,  64, 0) },
+	{ "s25fl129p1", INFO(0x012018, 0x4d01,  64 * 1024, 256, 0) },
+	{ "s25sl004a",  INFO(0x010212,      0,  64 * 1024,   8, 0) },
+	{ "s25sl008a",  INFO(0x010213,      0,  64 * 1024,  16, 0) },
+	{ "s25sl016a",  INFO(0x010214,      0,  64 * 1024,  32, 0) },
+	{ "s25sl032a",  INFO(0x010215,      0,  64 * 1024,  64, 0) },
+	{ "s25sl064a",  INFO(0x010216,      0,  64 * 1024, 128, 0) },
+	{ "s25fl008k",  INFO(0xef4014,      0,  64 * 1024,  16, SECT_4K) },
+	{ "s25fl016k",  INFO(0xef4015,      0,  64 * 1024,  32, SECT_4K) },
+	{ "s25fl064k",  INFO(0xef4017,      0,  64 * 1024, 128, SECT_4K) },
+
+	/* SST -- large erase sizes are "overlays", "sectors" are 4K */
+	{ "sst25vf040b", INFO(0xbf258d, 0, 64 * 1024,  8, SECT_4K | SST_WRITE) },
+	{ "sst25vf080b", INFO(0xbf258e, 0, 64 * 1024, 16, SECT_4K | SST_WRITE) },
+	{ "sst25vf016b", INFO(0xbf2541, 0, 64 * 1024, 32, SECT_4K | SST_WRITE) },
+	{ "sst25vf032b", INFO(0xbf254a, 0, 64 * 1024, 64, SECT_4K | SST_WRITE) },
+	{ "sst25vf064c", INFO(0xbf254b, 0, 64 * 1024, 128, SECT_4K) },
+	{ "sst25wf512",  INFO(0xbf2501, 0, 64 * 1024,  1, SECT_4K | SST_WRITE) },
+	{ "sst25wf010",  INFO(0xbf2502, 0, 64 * 1024,  2, SECT_4K | SST_WRITE) },
+	{ "sst25wf020",  INFO(0xbf2503, 0, 64 * 1024,  4, SECT_4K | SST_WRITE) },
+	{ "sst25wf040",  INFO(0xbf2504, 0, 64 * 1024,  8, SECT_4K | SST_WRITE) },
+
+	/* ST Microelectronics -- newer production may have feature updates */
+	{ "m25p05",  INFO(0x202010,  0,  32 * 1024,   2, 0) },
+	{ "m25p10",  INFO(0x202011,  0,  32 * 1024,   4, 0) },
+	{ "m25p20",  INFO(0x202012,  0,  64 * 1024,   4, 0) },
+	{ "m25p40",  INFO(0x202013,  0,  64 * 1024,   8, 0) },
+	{ "m25p80",  INFO(0x202014,  0,  64 * 1024,  16, 0) },
+	{ "m25p16",  INFO(0x202015,  0,  64 * 1024,  32, 0) },
+	{ "m25p32",  INFO(0x202016,  0,  64 * 1024,  64, 0) },
+	{ "m25p64",  INFO(0x202017,  0,  64 * 1024, 128, 0) },
+	{ "m25p128", INFO(0x202018,  0, 256 * 1024,  64, 0) },
+	{ "n25q032", INFO(0x20ba16,  0,  64 * 1024,  64, 0) },
+
+	{ "m25p05-nonjedec",  INFO(0, 0,  32 * 1024,   2, 0) },
+	{ "m25p10-nonjedec",  INFO(0, 0,  32 * 1024,   4, 0) },
+	{ "m25p20-nonjedec",  INFO(0, 0,  64 * 1024,   4, 0) },
+	{ "m25p40-nonjedec",  INFO(0, 0,  64 * 1024,   8, 0) },
+	{ "m25p80-nonjedec",  INFO(0, 0,  64 * 1024,  16, 0) },
+	{ "m25p16-nonjedec",  INFO(0, 0,  64 * 1024,  32, 0) },
+	{ "m25p32-nonjedec",  INFO(0, 0,  64 * 1024,  64, 0) },
+	{ "m25p64-nonjedec",  INFO(0, 0,  64 * 1024, 128, 0) },
+	{ "m25p128-nonjedec", INFO(0, 0, 256 * 1024,  64, 0) },
+
+	{ "m45pe10", INFO(0x204011,  0, 64 * 1024,    2, 0) },
+	{ "m45pe80", INFO(0x204014,  0, 64 * 1024,   16, 0) },
+	{ "m45pe16", INFO(0x204015,  0, 64 * 1024,   32, 0) },
+
+	{ "m25pe20", INFO(0x208012,  0, 64 * 1024,  4,       0) },
+	{ "m25pe80", INFO(0x208014,  0, 64 * 1024, 16,       0) },
+	{ "m25pe16", INFO(0x208015,  0, 64 * 1024, 32, SECT_4K) },
+
+	{ "m25px16",    INFO(0x207115,  0, 64 * 1024, 32, SECT_4K) },
+	{ "m25px32",    INFO(0x207116,  0, 64 * 1024, 64, SECT_4K) },
+	{ "m25px32-s0", INFO(0x207316,  0, 64 * 1024, 64, SECT_4K) },
+	{ "m25px32-s1", INFO(0x206316,  0, 64 * 1024, 64, SECT_4K) },
+	{ "m25px64",    INFO(0x207117,  0, 64 * 1024, 128, 0) },
+
+	/* Winbond -- w25x "blocks" are 64K, "sectors" are 4KiB */
+	{ "w25x10", INFO(0xef3011, 0, 64 * 1024,  2,  SECT_4K) },
+	{ "w25x20", INFO(0xef3012, 0, 64 * 1024,  4,  SECT_4K) },
+	{ "w25x40", INFO(0xef3013, 0, 64 * 1024,  8,  SECT_4K) },
+	{ "w25x80", INFO(0xef3014, 0, 64 * 1024,  16, SECT_4K) },
+	{ "w25x16", INFO(0xef3015, 0, 64 * 1024,  32, SECT_4K) },
+	{ "w25x32", INFO(0xef3016, 0, 64 * 1024,  64, SECT_4K) },
+	{ "w25q32", INFO(0xef4016, 0, 64 * 1024,  64, SECT_4K) },
+	{ "w25q32dw", INFO(0xef6016, 0, 64 * 1024,  64, SECT_4K) },
+	{ "w25x64", INFO(0xef3017, 0, 64 * 1024, 128, SECT_4K) },
+	{ "w25q64", INFO(0xef4017, 0, 64 * 1024, 128, SECT_4K) },
+	{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
+	{ "w25q80", INFO(0xef5014, 0, 64 * 1024,  16, SECT_4K) },
+	{ "w25q80bl", INFO(0xef4014, 0, 64 * 1024,  16, SECT_4K) },
+	{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
+	{ "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K) },
+
+	/* Catalyst / On Semiconductor -- non-JEDEC */
+	{ "cat25c11", CAT25_INFO(  16, 8, 16, 1, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+	{ "cat25c03", CAT25_INFO(  32, 8, 16, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+	{ "cat25c09", CAT25_INFO( 128, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+	{ "cat25c17", CAT25_INFO( 256, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+	{ "cat25128", CAT25_INFO(2048, 8, 64, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+	{ },
+};
+EXPORT_SYMBOL_GPL(spi_nor_ids);
+
+static const struct spi_device_id *spi_nor_read_id(struct spi_nor *nor)
+{
+	int			tmp;
+	u8			id[5];
+	u32			jedec;
+	u16                     ext_jedec;
+	struct flash_info	*info;
+
+	tmp = nor->read_reg(nor, SPINOR_OP_RDID, id, 5);
+	if (tmp < 0) {
+		dev_dbg(nor->dev, " error %d reading JEDEC ID\n", tmp);
+		return ERR_PTR(tmp);
+	}
+	jedec = id[0];
+	jedec = jedec << 8;
+	jedec |= id[1];
+	jedec = jedec << 8;
+	jedec |= id[2];
+
+	ext_jedec = id[3] << 8 | id[4];
+
+	for (tmp = 0; tmp < ARRAY_SIZE(spi_nor_ids) - 1; tmp++) {
+		info = (void *)spi_nor_ids[tmp].driver_data;
+		if (info->jedec_id == jedec) {
+			if (info->ext_id == 0 || info->ext_id == ext_jedec)
+				return &spi_nor_ids[tmp];
+		}
+	}
+	dev_err(nor->dev, "unrecognized JEDEC id %06x\n", jedec);
+	return ERR_PTR(-ENODEV);
+}
+
+static const struct spi_device_id *jedec_probe(struct spi_nor *nor)
+{
+	return nor->read_id(nor);
+}
+
+static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
+			size_t *retlen, u_char *buf)
+{
+	struct spi_nor *nor = mtd_to_spi_nor(mtd);
+	int ret;
+
+	dev_dbg(nor->dev, "from 0x%08x, len %zd\n", (u32)from, len);
+
+	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_READ);
+	if (ret)
+		return ret;
+
+	ret = nor->read(nor, from, len, retlen, buf);
+
+	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_READ);
+	return ret;
+}
+
+static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
+		size_t *retlen, const u_char *buf)
+{
+	struct spi_nor *nor = mtd_to_spi_nor(mtd);
+	size_t actual;
+	int ret;
+
+	dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len);
+
+	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_WRITE);
+	if (ret)
+		return ret;
+
+	/* Wait until finished previous write command. */
+	ret = wait_till_ready(nor);
+	if (ret)
+		goto time_out;
+
+	write_enable(nor);
+
+	nor->sst_write_second = false;
+
+	actual = to % 2;
+	/* Start write from odd address. */
+	if (actual) {
+		nor->program_opcode = SPINOR_OP_BP;
+
+		/* write one byte. */
+		nor->write(nor, to, 1, retlen, buf);
+		ret = wait_till_ready(nor);
+		if (ret)
+			goto time_out;
+	}
+	to += actual;
+
+	/* Write out most of the data here. */
+	for (; actual < len - 1; actual += 2) {
+		nor->program_opcode = SPINOR_OP_AAI_WP;
+
+		/* write two bytes. */
+		nor->write(nor, to, 2, retlen, buf + actual);
+		ret = wait_till_ready(nor);
+		if (ret)
+			goto time_out;
+		to += 2;
+		nor->sst_write_second = true;
+	}
+	nor->sst_write_second = false;
+
+	write_disable(nor);
+	ret = wait_till_ready(nor);
+	if (ret)
+		goto time_out;
+
+	/* Write out trailing byte if it exists. */
+	if (actual != len) {
+		write_enable(nor);
+
+		nor->program_opcode = SPINOR_OP_BP;
+		nor->write(nor, to, 1, retlen, buf + actual);
+
+		ret = wait_till_ready(nor);
+		if (ret)
+			goto time_out;
+		write_disable(nor);
+	}
+time_out:
+	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
+	return ret;
+}
+
+/*
+ * Write an address range to the nor chip.  Data must be written in
+ * FLASH_PAGESIZE chunks.  The address range may be any size provided
+ * it is within the physical boundaries.
+ */
+static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
+	size_t *retlen, const u_char *buf)
+{
+	struct spi_nor *nor = mtd_to_spi_nor(mtd);
+	u32 page_offset, page_size, i;
+	int ret;
+
+	dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len);
+
+	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_WRITE);
+	if (ret)
+		return ret;
+
+	/* Wait until finished previous write command. */
+	ret = wait_till_ready(nor);
+	if (ret)
+		goto write_err;
+
+	write_enable(nor);
+
+	page_offset = to & (nor->page_size - 1);
+
+	/* do all the bytes fit onto one page? */
+	if (page_offset + len <= nor->page_size) {
+		nor->write(nor, to, len, retlen, buf);
+	} else {
+		/* the size of data remaining on the first page */
+		page_size = nor->page_size - page_offset;
+		nor->write(nor, to, page_size, retlen, buf);
+
+		/* write everything in nor->page_size chunks */
+		for (i = page_size; i < len; i += page_size) {
+			page_size = len - i;
+			if (page_size > nor->page_size)
+				page_size = nor->page_size;
+
+			wait_till_ready(nor);
+			write_enable(nor);
+
+			nor->write(nor, to + i, page_size, retlen, buf + i);
+		}
+	}
+
+write_err:
+	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
+	return 0;
+}
+
+static int macronix_quad_enable(struct spi_nor *nor)
+{
+	int ret, val;
+
+	val = read_sr(nor);
+	write_enable(nor);
+
+	nor->cmd_buf[0] = val | SR_QUAD_EN_MX;
+	nor->write_reg(nor, SPINOR_OP_WRSR, nor->cmd_buf, 1, 0);
+
+	if (wait_till_ready(nor))
+		return 1;
+
+	ret = read_sr(nor);
+	if (!(ret > 0 && (ret & SR_QUAD_EN_MX))) {
+		dev_err(nor->dev, "Macronix Quad bit not set\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Write status Register and configuration register with 2 bytes
+ * The first byte will be written to the status register, while the
+ * second byte will be written to the configuration register.
+ * Return negative if error occured.
+ */
+static int write_sr_cr(struct spi_nor *nor, u16 val)
+{
+	nor->cmd_buf[0] = val & 0xff;
+	nor->cmd_buf[1] = (val >> 8);
+
+	return nor->write_reg(nor, SPINOR_OP_WRSR, nor->cmd_buf, 2, 0);
+}
+
+static int spansion_quad_enable(struct spi_nor *nor)
+{
+	int ret;
+	int quad_en = CR_QUAD_EN_SPAN << 8;
+
+	write_enable(nor);
+
+	ret = write_sr_cr(nor, quad_en);
+	if (ret < 0) {
+		dev_err(nor->dev,
+			"error while writing configuration register\n");
+		return -EINVAL;
+	}
+
+	/* read back and check it */
+	ret = read_cr(nor);
+	if (!(ret > 0 && (ret & CR_QUAD_EN_SPAN))) {
+		dev_err(nor->dev, "Spansion Quad bit not set\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int set_quad_mode(struct spi_nor *nor, u32 jedec_id)
+{
+	int status;
+
+	switch (JEDEC_MFR(jedec_id)) {
+	case CFI_MFR_MACRONIX:
+		status = macronix_quad_enable(nor);
+		if (status) {
+			dev_err(nor->dev, "Macronix quad-read not enabled\n");
+			return -EINVAL;
+		}
+		return status;
+	default:
+		status = spansion_quad_enable(nor);
+		if (status) {
+			dev_err(nor->dev, "Spansion quad-read not enabled\n");
+			return -EINVAL;
+		}
+		return status;
+	}
+}
+
+static int spi_nor_check(struct spi_nor *nor)
+{
+	if (!nor->dev || !nor->read || !nor->write ||
+		!nor->read_reg || !nor->write_reg || !nor->erase) {
+		pr_err("spi-nor: please fill all the necessary fields!\n");
+		return -EINVAL;
+	}
+
+	if (!nor->read_id)
+		nor->read_id = spi_nor_read_id;
+	if (!nor->wait_till_ready)
+		nor->wait_till_ready = spi_nor_wait_till_ready;
+
+	return 0;
+}
+
+int spi_nor_scan(struct spi_nor *nor, const struct spi_device_id *id,
+			enum read_mode mode)
+{
+	struct flash_info		*info;
+	struct flash_platform_data	*data;
+	struct device *dev = nor->dev;
+	struct mtd_info *mtd = nor->mtd;
+	struct device_node *np = dev->of_node;
+	int ret;
+	int i;
+
+	ret = spi_nor_check(nor);
+	if (ret)
+		return ret;
+
+	/* Platform data helps sort out which chip type we have, as
+	 * well as how this board partitions it.  If we don't have
+	 * a chip ID, try the JEDEC id commands; they'll work for most
+	 * newer chips, even if we don't recognize the particular chip.
+	 */
+	data = dev_get_platdata(dev);
+	if (data && data->type) {
+		const struct spi_device_id *plat_id;
+
+		for (i = 0; i < ARRAY_SIZE(spi_nor_ids) - 1; i++) {
+			plat_id = &spi_nor_ids[i];
+			if (strcmp(data->type, plat_id->name))
+				continue;
+			break;
+		}
+
+		if (i < ARRAY_SIZE(spi_nor_ids) - 1)
+			id = plat_id;
+		else
+			dev_warn(dev, "unrecognized id %s\n", data->type);
+	}
+
+	info = (void *)id->driver_data;
+
+	if (info->jedec_id) {
+		const struct spi_device_id *jid;
+
+		jid = jedec_probe(nor);
+		if (IS_ERR(jid)) {
+			return PTR_ERR(jid);
+		} else if (jid != id) {
+			/*
+			 * JEDEC knows better, so overwrite platform ID. We
+			 * can't trust partitions any longer, but we'll let
+			 * mtd apply them anyway, since some partitions may be
+			 * marked read-only, and we don't want to lose that
+			 * information, even if it's not 100% accurate.
+			 */
+			dev_warn(dev, "found %s, expected %s\n",
+				 jid->name, id->name);
+			id = jid;
+			info = (void *)jid->driver_data;
+		}
+	}
+
+	mutex_init(&nor->lock);
+
+	/*
+	 * Atmel, SST and Intel/Numonyx serial nor tend to power
+	 * up with the software protection bits set
+	 */
+
+	if (JEDEC_MFR(info->jedec_id) == CFI_MFR_ATMEL ||
+	    JEDEC_MFR(info->jedec_id) == CFI_MFR_INTEL ||
+	    JEDEC_MFR(info->jedec_id) == CFI_MFR_SST) {
+		write_enable(nor);
+		write_sr(nor, 0);
+	}
+
+	if (data && data->name)
+		mtd->name = data->name;
+	else
+		mtd->name = dev_name(dev);
+
+	mtd->type = MTD_NORFLASH;
+	mtd->writesize = 1;
+	mtd->flags = MTD_CAP_NORFLASH;
+	mtd->size = info->sector_size * info->n_sectors;
+	mtd->_erase = spi_nor_erase;
+	mtd->_read = spi_nor_read;
+
+	/* nor protection support for STmicro chips */
+	if (JEDEC_MFR(info->jedec_id) == CFI_MFR_ST) {
+		mtd->_lock = spi_nor_lock;
+		mtd->_unlock = spi_nor_unlock;
+	}
+
+	/* sst nor chips use AAI word program */
+	if (info->flags & SST_WRITE)
+		mtd->_write = sst_write;
+	else
+		mtd->_write = spi_nor_write;
+
+	/* prefer "small sector" erase if possible */
+	if (info->flags & SECT_4K) {
+		nor->erase_opcode = SPINOR_OP_BE_4K;
+		mtd->erasesize = 4096;
+	} else if (info->flags & SECT_4K_PMC) {
+		nor->erase_opcode = SPINOR_OP_BE_4K_PMC;
+		mtd->erasesize = 4096;
+	} else {
+		nor->erase_opcode = SPINOR_OP_SE;
+		mtd->erasesize = info->sector_size;
+	}
+
+	if (info->flags & SPI_NOR_NO_ERASE)
+		mtd->flags |= MTD_NO_ERASE;
+
+	mtd->dev.parent = dev;
+	nor->page_size = info->page_size;
+	mtd->writebufsize = nor->page_size;
+
+	if (np) {
+		/* If we were instantiated by DT, use it */
+		if (of_property_read_bool(np, "m25p,fast-read"))
+			nor->flash_read = SPI_NOR_FAST;
+		else
+			nor->flash_read = SPI_NOR_NORMAL;
+	} else {
+		/* If we weren't instantiated by DT, default to fast-read */
+		nor->flash_read = SPI_NOR_FAST;
+	}
+
+	/* Some devices cannot do fast-read, no matter what DT tells us */
+	if (info->flags & SPI_NOR_NO_FR)
+		nor->flash_read = SPI_NOR_NORMAL;
+
+	/* Quad/Dual-read mode takes precedence over fast/normal */
+	if (mode == SPI_NOR_QUAD && info->flags & SPI_NOR_QUAD_READ) {
+		ret = set_quad_mode(nor, info->jedec_id);
+		if (ret) {
+			dev_err(dev, "quad mode not supported\n");
+			return ret;
+		}
+		nor->flash_read = SPI_NOR_QUAD;
+	} else if (mode == SPI_NOR_DUAL && info->flags & SPI_NOR_DUAL_READ) {
+		nor->flash_read = SPI_NOR_DUAL;
+	}
+
+	/* Default commands */
+	switch (nor->flash_read) {
+	case SPI_NOR_QUAD:
+		nor->read_opcode = SPINOR_OP_READ_1_1_4;
+		break;
+	case SPI_NOR_DUAL:
+		nor->read_opcode = SPINOR_OP_READ_1_1_2;
+		break;
+	case SPI_NOR_FAST:
+		nor->read_opcode = SPINOR_OP_READ_FAST;
+		break;
+	case SPI_NOR_NORMAL:
+		nor->read_opcode = SPINOR_OP_READ;
+		break;
+	default:
+		dev_err(dev, "No Read opcode defined\n");
+		return -EINVAL;
+	}
+
+	nor->program_opcode = SPINOR_OP_PP;
+
+	if (info->addr_width)
+		nor->addr_width = info->addr_width;
+	else if (mtd->size > 0x1000000) {
+		/* enable 4-byte addressing if the device exceeds 16MiB */
+		nor->addr_width = 4;
+		if (JEDEC_MFR(info->jedec_id) == CFI_MFR_AMD) {
+			/* Dedicated 4-byte command set */
+			switch (nor->flash_read) {
+			case SPI_NOR_QUAD:
+				nor->read_opcode = SPINOR_OP_READ4_1_1_4;
+				break;
+			case SPI_NOR_DUAL:
+				nor->read_opcode = SPINOR_OP_READ4_1_1_2;
+				break;
+			case SPI_NOR_FAST:
+				nor->read_opcode = SPINOR_OP_READ4_FAST;
+				break;
+			case SPI_NOR_NORMAL:
+				nor->read_opcode = SPINOR_OP_READ4;
+				break;
+			}
+			nor->program_opcode = SPINOR_OP_PP_4B;
+			/* No small sector erase for 4-byte command set */
+			nor->erase_opcode = SPINOR_OP_SE_4B;
+			mtd->erasesize = info->sector_size;
+		} else
+			set_4byte(nor, info->jedec_id, 1);
+	} else {
+		nor->addr_width = 3;
+	}
+
+	nor->read_dummy = spi_nor_read_dummy_cycles(nor);
+
+	dev_info(dev, "%s (%lld Kbytes)\n", id->name,
+			(long long)mtd->size >> 10);
+
+	dev_dbg(dev,
+		"mtd .name = %s, .size = 0x%llx (%lldMiB), "
+		".erasesize = 0x%.8x (%uKiB) .numeraseregions = %d\n",
+		mtd->name, (long long)mtd->size, (long long)(mtd->size >> 20),
+		mtd->erasesize, mtd->erasesize / 1024, mtd->numeraseregions);
+
+	if (mtd->numeraseregions)
+		for (i = 0; i < mtd->numeraseregions; i++)
+			dev_dbg(dev,
+				"mtd.eraseregions[%d] = { .offset = 0x%llx, "
+				".erasesize = 0x%.8x (%uKiB), "
+				".numblocks = %d }\n",
+				i, (long long)mtd->eraseregions[i].offset,
+				mtd->eraseregions[i].erasesize,
+				mtd->eraseregions[i].erasesize / 1024,
+				mtd->eraseregions[i].numblocks);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(spi_nor_scan);
+
+const struct spi_device_id *spi_nor_match_id(char *name)
+{
+	const struct spi_device_id *id = spi_nor_ids;
+
+	while (id->name[0]) {
+		if (!strcmp(name, id->name))
+			return id;
+		id++;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(spi_nor_match_id);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Huang Shijie <shijie8@gmail.com>");
+MODULE_AUTHOR("Mike Lavender");
+MODULE_DESCRIPTION("framework for SPI NOR");
diff --git a/drivers/mtd/tests/oobtest.c b/drivers/mtd/tests/oobtest.c
index 2e9e2d11f20..f19ab1acde1 100644
--- a/drivers/mtd/tests/oobtest.c
+++ b/drivers/mtd/tests/oobtest.c
@@ -69,8 +69,8 @@ static int write_eraseblock(int ebnum)
 	int err = 0;
 	loff_t addr = ebnum * mtd->erasesize;
 
+	prandom_bytes_state(&rnd_state, writebuf, use_len_max * pgcnt);
 	for (i = 0; i < pgcnt; ++i, addr += mtd->writesize) {
-		prandom_bytes_state(&rnd_state, writebuf, use_len);
 		ops.mode      = MTD_OPS_AUTO_OOB;
 		ops.len       = 0;
 		ops.retlen    = 0;
@@ -78,7 +78,7 @@ static int write_eraseblock(int ebnum)
 		ops.oobretlen = 0;
 		ops.ooboffs   = use_offset;
 		ops.datbuf    = NULL;
-		ops.oobbuf    = writebuf;
+		ops.oobbuf    = writebuf + (use_len_max * i) + use_offset;
 		err = mtd_write_oob(mtd, addr, &ops);
 		if (err || ops.oobretlen != use_len) {
 			pr_err("error: writeoob failed at %#llx\n",
@@ -122,8 +122,8 @@ static int verify_eraseblock(int ebnum)
 	int err = 0;
 	loff_t addr = ebnum * mtd->erasesize;
 
+	prandom_bytes_state(&rnd_state, writebuf, use_len_max * pgcnt);
 	for (i = 0; i < pgcnt; ++i, addr += mtd->writesize) {
-		prandom_bytes_state(&rnd_state, writebuf, use_len);
 		ops.mode      = MTD_OPS_AUTO_OOB;
 		ops.len       = 0;
 		ops.retlen    = 0;
@@ -139,7 +139,8 @@ static int verify_eraseblock(int ebnum)
 			errcnt += 1;
 			return err ? err : -1;
 		}
-		if (memcmp(readbuf, writebuf, use_len)) {
+		if (memcmp(readbuf, writebuf + (use_len_max * i) + use_offset,
+			   use_len)) {
 			pr_err("error: verify failed at %#llx\n",
 			       (long long)addr);
 			errcnt += 1;
@@ -166,7 +167,9 @@ static int verify_eraseblock(int ebnum)
 				errcnt += 1;
 				return err ? err : -1;
 			}
-			if (memcmp(readbuf + use_offset, writebuf, use_len)) {
+			if (memcmp(readbuf + use_offset,
+				   writebuf + (use_len_max * i) + use_offset,
+				   use_len)) {
 				pr_err("error: verify failed at %#llx\n",
 						(long long)addr);
 				errcnt += 1;
@@ -566,8 +569,8 @@ static int __init mtd_oobtest_init(void)
 		if (bbt[i] || bbt[i + 1])
 			continue;
 		addr = (i + 1) * mtd->erasesize - mtd->writesize;
+		prandom_bytes_state(&rnd_state, writebuf, sz * cnt);
 		for (pg = 0; pg < cnt; ++pg) {
-			prandom_bytes_state(&rnd_state, writebuf, sz);
 			ops.mode      = MTD_OPS_AUTO_OOB;
 			ops.len       = 0;
 			ops.retlen    = 0;
@@ -575,7 +578,7 @@ static int __init mtd_oobtest_init(void)
 			ops.oobretlen = 0;
 			ops.ooboffs   = 0;
 			ops.datbuf    = NULL;
-			ops.oobbuf    = writebuf;
+			ops.oobbuf    = writebuf + pg * sz;
 			err = mtd_write_oob(mtd, addr, &ops);
 			if (err)
 				goto out;
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index 20a667c95da..8457df7ec5a 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -432,8 +432,10 @@ int ubiblock_create(struct ubi_volume_info *vi)
 	 * Rembember workqueues are cheap, they're not threads.
 	 */
 	dev->wq = alloc_workqueue("%s", 0, 0, gd->disk_name);
-	if (!dev->wq)
+	if (!dev->wq) {
+		ret = -ENOMEM;
 		goto out_free_queue;
+	}
 	INIT_WORK(&dev->work, ubiblock_do_work);
 
 	mutex_lock(&devices_mutex);
diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c
index f54562a5998..7646220ca6e 100644
--- a/drivers/mtd/ubi/cdev.c
+++ b/drivers/mtd/ubi/cdev.c
@@ -731,7 +731,7 @@ static int rename_volumes(struct ubi_device *ubi,
 			goto out_free;
 		}
 
-		re->desc = ubi_open_volume(ubi->ubi_num, vol_id, UBI_EXCLUSIVE);
+		re->desc = ubi_open_volume(ubi->ubi_num, vol_id, UBI_READWRITE);
 		if (IS_ERR(re->desc)) {
 			err = PTR_ERR(re->desc);
 			ubi_err("cannot open volume %d, error %d", vol_id, err);
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index c5dad652614..0431b46d9fd 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -127,7 +127,7 @@ static struct ubi_ainf_volume *add_vol(struct ubi_attach_info *ai, int vol_id,
 
 		if (vol_id > av->vol_id)
 			p = &(*p)->rb_left;
-		else if (vol_id > av->vol_id)
+		else
 			p = &(*p)->rb_right;
 	}
 
@@ -423,7 +423,7 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai,
 				pnum, err);
 			ret = err > 0 ? UBI_BAD_FASTMAP : err;
 			goto out;
-		} else if (ret == UBI_IO_BITFLIPS)
+		} else if (err == UBI_IO_BITFLIPS)
 			scrub = 1;
 
 		/*
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index b667a51ed21..0dfeaf5da3f 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -157,7 +157,7 @@ static inline struct aggregator *__get_first_agg(struct port *port)
 
 	rcu_read_lock();
 	first_slave = bond_first_slave_rcu(bond);
-	agg = first_slave ? &(SLAVE_AD_INFO(first_slave).aggregator) : NULL;
+	agg = first_slave ? &(SLAVE_AD_INFO(first_slave)->aggregator) : NULL;
 	rcu_read_unlock();
 
 	return agg;
@@ -192,7 +192,7 @@ static inline void __enable_port(struct port *port)
 {
 	struct slave *slave = port->slave;
 
-	if ((slave->link == BOND_LINK_UP) && IS_UP(slave->dev))
+	if ((slave->link == BOND_LINK_UP) && bond_slave_is_up(slave))
 		bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_LATER);
 }
 
@@ -241,7 +241,7 @@ static inline int __check_agg_selection_timer(struct port *port)
  */
 static inline void __get_state_machine_lock(struct port *port)
 {
-	spin_lock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock));
+	spin_lock_bh(&(SLAVE_AD_INFO(port->slave)->state_machine_lock));
 }
 
 /**
@@ -250,7 +250,7 @@ static inline void __get_state_machine_lock(struct port *port)
  */
 static inline void __release_state_machine_lock(struct port *port)
 {
-	spin_unlock_bh(&(SLAVE_AD_INFO(port->slave).state_machine_lock));
+	spin_unlock_bh(&(SLAVE_AD_INFO(port->slave)->state_machine_lock));
 }
 
 /**
@@ -350,7 +350,7 @@ static u8 __get_duplex(struct port *port)
 static inline void __initialize_port_locks(struct slave *slave)
 {
 	/* make sure it isn't called twice */
-	spin_lock_init(&(SLAVE_AD_INFO(slave).state_machine_lock));
+	spin_lock_init(&(SLAVE_AD_INFO(slave)->state_machine_lock));
 }
 
 /* Conversions */
@@ -688,8 +688,8 @@ static struct aggregator *__get_active_agg(struct aggregator *aggregator)
 	struct slave *slave;
 
 	bond_for_each_slave_rcu(bond, slave, iter)
-		if (SLAVE_AD_INFO(slave).aggregator.is_active)
-			return &(SLAVE_AD_INFO(slave).aggregator);
+		if (SLAVE_AD_INFO(slave)->aggregator.is_active)
+			return &(SLAVE_AD_INFO(slave)->aggregator);
 
 	return NULL;
 }
@@ -1293,7 +1293,7 @@ static void ad_port_selection_logic(struct port *port)
 	}
 	/* search on all aggregators for a suitable aggregator for this port */
 	bond_for_each_slave(bond, slave, iter) {
-		aggregator = &(SLAVE_AD_INFO(slave).aggregator);
+		aggregator = &(SLAVE_AD_INFO(slave)->aggregator);
 
 		/* keep a free aggregator for later use(if needed) */
 		if (!aggregator->lag_ports) {
@@ -1504,7 +1504,7 @@ static void ad_agg_selection_logic(struct aggregator *agg)
 	best = (active && agg_device_up(active)) ? active : NULL;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		agg = &(SLAVE_AD_INFO(slave).aggregator);
+		agg = &(SLAVE_AD_INFO(slave)->aggregator);
 
 		agg->is_active = 0;
 
@@ -1549,7 +1549,7 @@ static void ad_agg_selection_logic(struct aggregator *agg)
 			 best->slave ? best->slave->dev->name : "NULL");
 
 		bond_for_each_slave_rcu(bond, slave, iter) {
-			agg = &(SLAVE_AD_INFO(slave).aggregator);
+			agg = &(SLAVE_AD_INFO(slave)->aggregator);
 
 			pr_debug("Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n",
 				 agg->aggregator_identifier, agg->num_of_ports,
@@ -1840,16 +1840,16 @@ void bond_3ad_bind_slave(struct slave *slave)
 	struct aggregator *aggregator;
 
 	/* check that the slave has not been initialized yet. */
-	if (SLAVE_AD_INFO(slave).port.slave != slave) {
+	if (SLAVE_AD_INFO(slave)->port.slave != slave) {
 
 		/* port initialization */
-		port = &(SLAVE_AD_INFO(slave).port);
+		port = &(SLAVE_AD_INFO(slave)->port);
 
 		ad_initialize_port(port, bond->params.lacp_fast);
 
 		__initialize_port_locks(slave);
 		port->slave = slave;
-		port->actor_port_number = SLAVE_AD_INFO(slave).id;
+		port->actor_port_number = SLAVE_AD_INFO(slave)->id;
 		/* key is determined according to the link speed, duplex and user key(which
 		 * is yet not supported)
 		 */
@@ -1874,7 +1874,7 @@ void bond_3ad_bind_slave(struct slave *slave)
 		__disable_port(port);
 
 		/* aggregator initialization */
-		aggregator = &(SLAVE_AD_INFO(slave).aggregator);
+		aggregator = &(SLAVE_AD_INFO(slave)->aggregator);
 
 		ad_initialize_agg(aggregator);
 
@@ -1903,8 +1903,8 @@ void bond_3ad_unbind_slave(struct slave *slave)
 	struct slave *slave_iter;
 	struct list_head *iter;
 
-	aggregator = &(SLAVE_AD_INFO(slave).aggregator);
-	port = &(SLAVE_AD_INFO(slave).port);
+	aggregator = &(SLAVE_AD_INFO(slave)->aggregator);
+	port = &(SLAVE_AD_INFO(slave)->port);
 
 	/* if slave is null, the whole port is not initialized */
 	if (!port->slave) {
@@ -1932,7 +1932,7 @@ void bond_3ad_unbind_slave(struct slave *slave)
 		    (aggregator->lag_ports->next_port_in_aggregator)) {
 			/* find new aggregator for the related port(s) */
 			bond_for_each_slave(bond, slave_iter, iter) {
-				new_aggregator = &(SLAVE_AD_INFO(slave_iter).aggregator);
+				new_aggregator = &(SLAVE_AD_INFO(slave_iter)->aggregator);
 				/* if the new aggregator is empty, or it is
 				 * connected to our port only
 				 */
@@ -2010,7 +2010,7 @@ void bond_3ad_unbind_slave(struct slave *slave)
 
 	/* find the aggregator that this port is connected to */
 	bond_for_each_slave(bond, slave_iter, iter) {
-		temp_aggregator = &(SLAVE_AD_INFO(slave_iter).aggregator);
+		temp_aggregator = &(SLAVE_AD_INFO(slave_iter)->aggregator);
 		prev_port = NULL;
 		/* search the port in the aggregator's related ports */
 		for (temp_port = temp_aggregator->lag_ports; temp_port;
@@ -2076,7 +2076,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 	if (BOND_AD_INFO(bond).agg_select_timer &&
 	    !(--BOND_AD_INFO(bond).agg_select_timer)) {
 		slave = bond_first_slave_rcu(bond);
-		port = slave ? &(SLAVE_AD_INFO(slave).port) : NULL;
+		port = slave ? &(SLAVE_AD_INFO(slave)->port) : NULL;
 
 		/* select the active aggregator for the bond */
 		if (port) {
@@ -2094,7 +2094,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 
 	/* for each port run the state machines */
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		port = &(SLAVE_AD_INFO(slave).port);
+		port = &(SLAVE_AD_INFO(slave)->port);
 		if (!port->slave) {
 			pr_warn_ratelimited("%s: Warning: Found an uninitialized port\n",
 					    bond->dev->name);
@@ -2155,7 +2155,7 @@ static int bond_3ad_rx_indication(struct lacpdu *lacpdu, struct slave *slave,
 
 	if (length >= sizeof(struct lacpdu)) {
 
-		port = &(SLAVE_AD_INFO(slave).port);
+		port = &(SLAVE_AD_INFO(slave)->port);
 
 		if (!port->slave) {
 			pr_warn_ratelimited("%s: Warning: port of slave %s is uninitialized\n",
@@ -2212,7 +2212,7 @@ void bond_3ad_adapter_speed_changed(struct slave *slave)
 {
 	struct port *port;
 
-	port = &(SLAVE_AD_INFO(slave).port);
+	port = &(SLAVE_AD_INFO(slave)->port);
 
 	/* if slave is null, the whole port is not initialized */
 	if (!port->slave) {
@@ -2245,7 +2245,7 @@ void bond_3ad_adapter_duplex_changed(struct slave *slave)
 {
 	struct port *port;
 
-	port = &(SLAVE_AD_INFO(slave).port);
+	port = &(SLAVE_AD_INFO(slave)->port);
 
 	/* if slave is null, the whole port is not initialized */
 	if (!port->slave) {
@@ -2279,7 +2279,7 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 {
 	struct port *port;
 
-	port = &(SLAVE_AD_INFO(slave).port);
+	port = &(SLAVE_AD_INFO(slave)->port);
 
 	/* if slave is null, the whole port is not initialized */
 	if (!port->slave) {
@@ -2347,7 +2347,7 @@ int bond_3ad_set_carrier(struct bonding *bond)
 		ret = 0;
 		goto out;
 	}
-	active = __get_active_agg(&(SLAVE_AD_INFO(first_slave).aggregator));
+	active = __get_active_agg(&(SLAVE_AD_INFO(first_slave)->aggregator));
 	if (active) {
 		/* are enough slaves available to consider link up? */
 		if (active->num_of_ports < bond->params.min_links) {
@@ -2384,7 +2384,7 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond,
 	struct port *port;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		port = &(SLAVE_AD_INFO(slave).port);
+		port = &(SLAVE_AD_INFO(slave)->port);
 		if (port->aggregator && port->aggregator->is_active) {
 			aggregator = port->aggregator;
 			break;
@@ -2440,22 +2440,22 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev)
 		goto err_free;
 	}
 
-	slave_agg_no = bond_xmit_hash(bond, skb, slaves_in_agg);
+	slave_agg_no = bond_xmit_hash(bond, skb) % slaves_in_agg;
 	first_ok_slave = NULL;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		agg = SLAVE_AD_INFO(slave).port.aggregator;
+		agg = SLAVE_AD_INFO(slave)->port.aggregator;
 		if (!agg || agg->aggregator_identifier != agg_id)
 			continue;
 
 		if (slave_agg_no >= 0) {
-			if (!first_ok_slave && SLAVE_IS_OK(slave))
+			if (!first_ok_slave && bond_slave_can_tx(slave))
 				first_ok_slave = slave;
 			slave_agg_no--;
 			continue;
 		}
 
-		if (SLAVE_IS_OK(slave)) {
+		if (bond_slave_can_tx(slave)) {
 			bond_dev_queue_xmit(bond, skb, slave->dev);
 			goto out;
 		}
@@ -2522,7 +2522,7 @@ void bond_3ad_update_lacp_rate(struct bonding *bond)
 
 	lacp_fast = bond->params.lacp_fast;
 	bond_for_each_slave(bond, slave, iter) {
-		port = &(SLAVE_AD_INFO(slave).port);
+		port = &(SLAVE_AD_INFO(slave)->port);
 		__get_state_machine_lock(port);
 		if (lacp_fast)
 			port->actor_oper_port_state |= AD_STATE_LACP_TIMEOUT;
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 93580a47cc5..76c0dade233 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -229,7 +229,7 @@ static struct slave *tlb_get_least_loaded_slave(struct bonding *bond)
 
 	/* Find the slave with the largest gap */
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		if (SLAVE_IS_OK(slave)) {
+		if (bond_slave_can_tx(slave)) {
 			long long gap = compute_gap(slave);
 
 			if (max_gap < gap) {
@@ -384,7 +384,7 @@ static struct slave *rlb_next_rx_slave(struct bonding *bond)
 	bool found = false;
 
 	bond_for_each_slave(bond, slave, iter) {
-		if (!SLAVE_IS_OK(slave))
+		if (!bond_slave_can_tx(slave))
 			continue;
 		if (!found) {
 			if (!before || before->speed < slave->speed)
@@ -417,7 +417,7 @@ static struct slave *__rlb_next_rx_slave(struct bonding *bond)
 	bool found = false;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		if (!SLAVE_IS_OK(slave))
+		if (!bond_slave_can_tx(slave))
 			continue;
 		if (!found) {
 			if (!before || before->speed < slave->speed)
@@ -755,7 +755,7 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
 	/* Don't modify or load balance ARPs that do not originate locally
 	 * (e.g.,arrive via a bridge).
 	 */
-	if (!bond_slave_has_mac_rcu(bond, arp->mac_src))
+	if (!bond_slave_has_mac_rx(bond, arp->mac_src))
 		return NULL;
 
 	if (arp->op_code == htons(ARPOP_REPLY)) {
@@ -1039,11 +1039,14 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 	struct bonding *bond = bond_get_bond_by_slave(slave);
 	struct net_device *upper;
 	struct list_head *iter;
+	struct bond_vlan_tag tags[BOND_MAX_VLAN_ENCAP];
 
 	/* send untagged */
 	alb_send_lp_vid(slave, mac_addr, 0, 0);
 
-	/* loop through vlans and send one packet for each */
+	/* loop through all devices and see if we need to send a packet
+	 * for that device.
+	 */
 	rcu_read_lock();
 	netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
 		if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
@@ -1059,6 +1062,16 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
 						vlan_dev_vlan_id(upper));
 			}
 		}
+
+		/* If this is a macvlan device, then only send updates
+		 * when strict_match is turned off.
+		 */
+		if (netif_is_macvlan(upper) && !strict_match) {
+			memset(tags, 0, sizeof(tags));
+			bond_verify_device_path(bond->dev, upper, tags);
+			alb_send_lp_vid(slave, upper->dev_addr,
+					tags[0].vlan_proto, tags[0].vlan_id);
+		}
 	}
 	rcu_read_unlock();
 }
@@ -1068,7 +1081,7 @@ static int alb_set_slave_mac_addr(struct slave *slave, u8 addr[])
 	struct net_device *dev = slave->dev;
 	struct sockaddr s_addr;
 
-	if (slave->bond->params.mode == BOND_MODE_TLB) {
+	if (BOND_MODE(slave->bond) == BOND_MODE_TLB) {
 		memcpy(dev->dev_addr, addr, dev->addr_len);
 		return 0;
 	}
@@ -1111,13 +1124,13 @@ static void alb_swap_mac_addr(struct slave *slave1, struct slave *slave2)
 static void alb_fasten_mac_swap(struct bonding *bond, struct slave *slave1,
 				struct slave *slave2)
 {
-	int slaves_state_differ = (SLAVE_IS_OK(slave1) != SLAVE_IS_OK(slave2));
+	int slaves_state_differ = (bond_slave_can_tx(slave1) != bond_slave_can_tx(slave2));
 	struct slave *disabled_slave = NULL;
 
 	ASSERT_RTNL();
 
 	/* fasten the change in the switch */
-	if (SLAVE_IS_OK(slave1)) {
+	if (bond_slave_can_tx(slave1)) {
 		alb_send_learning_packets(slave1, slave1->dev->dev_addr, false);
 		if (bond->alb_info.rlb_enabled) {
 			/* inform the clients that the mac address
@@ -1129,7 +1142,7 @@ static void alb_fasten_mac_swap(struct bonding *bond, struct slave *slave1,
 		disabled_slave = slave1;
 	}
 
-	if (SLAVE_IS_OK(slave2)) {
+	if (bond_slave_can_tx(slave2)) {
 		alb_send_learning_packets(slave2, slave2->dev->dev_addr, false);
 		if (bond->alb_info.rlb_enabled) {
 			/* inform the clients that the mac address
@@ -1358,6 +1371,77 @@ void bond_alb_deinitialize(struct bonding *bond)
 		rlb_deinitialize(bond);
 }
 
+static int bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
+		struct slave *tx_slave)
+{
+	struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond));
+	struct ethhdr *eth_data = eth_hdr(skb);
+
+	if (!tx_slave) {
+		/* unbalanced or unassigned, send through primary */
+		tx_slave = rcu_dereference(bond->curr_active_slave);
+		if (bond->params.tlb_dynamic_lb)
+			bond_info->unbalanced_load += skb->len;
+	}
+
+	if (tx_slave && bond_slave_can_tx(tx_slave)) {
+		if (tx_slave != rcu_dereference(bond->curr_active_slave)) {
+			ether_addr_copy(eth_data->h_source,
+					tx_slave->dev->dev_addr);
+		}
+
+		bond_dev_queue_xmit(bond, skb, tx_slave->dev);
+		goto out;
+	}
+
+	if (tx_slave && bond->params.tlb_dynamic_lb) {
+		_lock_tx_hashtbl(bond);
+		__tlb_clear_slave(bond, tx_slave, 0);
+		_unlock_tx_hashtbl(bond);
+	}
+
+	/* no suitable interface, frame not sent */
+	dev_kfree_skb_any(skb);
+out:
+	return NETDEV_TX_OK;
+}
+
+int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	struct ethhdr *eth_data;
+	struct slave *tx_slave = NULL;
+	u32 hash_index;
+
+	skb_reset_mac_header(skb);
+	eth_data = eth_hdr(skb);
+
+	/* Do not TX balance any multicast or broadcast */
+	if (!is_multicast_ether_addr(eth_data->h_dest)) {
+		switch (skb->protocol) {
+		case htons(ETH_P_IP):
+		case htons(ETH_P_IPX):
+		    /* In case of IPX, it will falback to L2 hash */
+		case htons(ETH_P_IPV6):
+			hash_index = bond_xmit_hash(bond, skb);
+			if (bond->params.tlb_dynamic_lb) {
+				tx_slave = tlb_choose_channel(bond,
+							      hash_index & 0xFF,
+							      skb->len);
+			} else {
+				struct list_head *iter;
+				int idx = hash_index % bond->slave_cnt;
+
+				bond_for_each_slave_rcu(bond, tx_slave, iter)
+					if (--idx < 0)
+						break;
+			}
+			break;
+		}
+	}
+	return bond_do_alb_xmit(skb, bond, tx_slave);
+}
+
 int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
@@ -1366,7 +1450,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	struct slave *tx_slave = NULL;
 	static const __be32 ip_bcast = htonl(0xffffffff);
 	int hash_size = 0;
-	int do_tx_balance = 1;
+	bool do_tx_balance = true;
 	u32 hash_index = 0;
 	const u8 *hash_start = NULL;
 	struct ipv6hdr *ip6hdr;
@@ -1381,7 +1465,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 		if (ether_addr_equal_64bits(eth_data->h_dest, mac_bcast) ||
 		    (iph->daddr == ip_bcast) ||
 		    (iph->protocol == IPPROTO_IGMP)) {
-			do_tx_balance = 0;
+			do_tx_balance = false;
 			break;
 		}
 		hash_start = (char *)&(iph->daddr);
@@ -1393,7 +1477,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 		 * that here just in case.
 		 */
 		if (ether_addr_equal_64bits(eth_data->h_dest, mac_bcast)) {
-			do_tx_balance = 0;
+			do_tx_balance = false;
 			break;
 		}
 
@@ -1401,7 +1485,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 		 * broadcasts in IPv4.
 		 */
 		if (ether_addr_equal_64bits(eth_data->h_dest, mac_v6_allmcast)) {
-			do_tx_balance = 0;
+			do_tx_balance = false;
 			break;
 		}
 
@@ -1411,7 +1495,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 		 */
 		ip6hdr = ipv6_hdr(skb);
 		if (ipv6_addr_any(&ip6hdr->saddr)) {
-			do_tx_balance = 0;
+			do_tx_balance = false;
 			break;
 		}
 
@@ -1421,7 +1505,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 	case ETH_P_IPX:
 		if (ipx_hdr(skb)->ipx_checksum != IPX_NO_CHECKSUM) {
 			/* something is wrong with this packet */
-			do_tx_balance = 0;
+			do_tx_balance = false;
 			break;
 		}
 
@@ -1430,7 +1514,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 			 * this family since it has an "ARP" like
 			 * mechanism
 			 */
-			do_tx_balance = 0;
+			do_tx_balance = false;
 			break;
 		}
 
@@ -1438,12 +1522,12 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 		hash_size = ETH_ALEN;
 		break;
 	case ETH_P_ARP:
-		do_tx_balance = 0;
+		do_tx_balance = false;
 		if (bond_info->rlb_enabled)
 			tx_slave = rlb_arp_xmit(skb, bond);
 		break;
 	default:
-		do_tx_balance = 0;
+		do_tx_balance = false;
 		break;
 	}
 
@@ -1452,32 +1536,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
 		tx_slave = tlb_choose_channel(bond, hash_index, skb->len);
 	}
 
-	if (!tx_slave) {
-		/* unbalanced or unassigned, send through primary */
-		tx_slave = rcu_dereference(bond->curr_active_slave);
-		bond_info->unbalanced_load += skb->len;
-	}
-
-	if (tx_slave && SLAVE_IS_OK(tx_slave)) {
-		if (tx_slave != rcu_dereference(bond->curr_active_slave)) {
-			ether_addr_copy(eth_data->h_source,
-					tx_slave->dev->dev_addr);
-		}
-
-		bond_dev_queue_xmit(bond, skb, tx_slave->dev);
-		goto out;
-	}
-
-	if (tx_slave) {
-		_lock_tx_hashtbl(bond);
-		__tlb_clear_slave(bond, tx_slave, 0);
-		_unlock_tx_hashtbl(bond);
-	}
-
-	/* no suitable interface, frame not sent */
-	dev_kfree_skb_any(skb);
-out:
-	return NETDEV_TX_OK;
+	return bond_do_alb_xmit(skb, bond, tx_slave);
 }
 
 void bond_alb_monitor(struct work_struct *work)
@@ -1514,8 +1573,10 @@ void bond_alb_monitor(struct work_struct *work)
 			/* If updating current_active, use all currently
 			 * user mac addreses (!strict_match).  Otherwise, only
 			 * use mac of the slave device.
+			 * In RLB mode, we always use strict matches.
 			 */
-			strict_match = (slave != bond->curr_active_slave);
+			strict_match = (slave != bond->curr_active_slave ||
+					bond_info->rlb_enabled);
 			alb_send_learning_packets(slave, slave->dev->dev_addr,
 						  strict_match);
 		}
@@ -1719,7 +1780,7 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 	/* in TLB mode, the slave might flip down/up with the old dev_addr,
 	 * and thus filter bond->dev_addr's packets, so force bond's mac
 	 */
-	if (bond->params.mode == BOND_MODE_TLB) {
+	if (BOND_MODE(bond) == BOND_MODE_TLB) {
 		struct sockaddr sa;
 		u8 tmp_addr[ETH_ALEN];
 
diff --git a/drivers/net/bonding/bond_alb.h b/drivers/net/bonding/bond_alb.h
index e09dd4bfaff..5fc76c01636 100644
--- a/drivers/net/bonding/bond_alb.h
+++ b/drivers/net/bonding/bond_alb.h
@@ -175,6 +175,7 @@ void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave);
 void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char link);
 void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave);
 int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
+int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev);
 void bond_alb_monitor(struct work_struct *);
 int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr);
 void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id);
diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c
index 2d3f7fa541f..658e761c456 100644
--- a/drivers/net/bonding/bond_debugfs.c
+++ b/drivers/net/bonding/bond_debugfs.c
@@ -23,7 +23,7 @@ static int bond_debug_rlb_hash_show(struct seq_file *m, void *v)
 	struct rlb_client_info *client_info;
 	u32 hash_index;
 
-	if (bond->params.mode != BOND_MODE_ALB)
+	if (BOND_MODE(bond) != BOND_MODE_ALB)
 		return 0;
 
 	seq_printf(m, "SourceIP        DestinationIP   "
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d3a67896d43..701f86cd599 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -343,7 +343,7 @@ static int bond_set_carrier(struct bonding *bond)
 	if (!bond_has_slaves(bond))
 		goto down;
 
-	if (bond->params.mode == BOND_MODE_8023AD)
+	if (BOND_MODE(bond) == BOND_MODE_8023AD)
 		return bond_3ad_set_carrier(bond);
 
 	bond_for_each_slave(bond, slave, iter) {
@@ -497,7 +497,7 @@ static int bond_set_promiscuity(struct bonding *bond, int inc)
 	struct list_head *iter;
 	int err = 0;
 
-	if (USES_PRIMARY(bond->params.mode)) {
+	if (bond_uses_primary(bond)) {
 		/* write lock already acquired */
 		if (bond->curr_active_slave) {
 			err = dev_set_promiscuity(bond->curr_active_slave->dev,
@@ -523,7 +523,7 @@ static int bond_set_allmulti(struct bonding *bond, int inc)
 	struct list_head *iter;
 	int err = 0;
 
-	if (USES_PRIMARY(bond->params.mode)) {
+	if (bond_uses_primary(bond)) {
 		/* write lock already acquired */
 		if (bond->curr_active_slave) {
 			err = dev_set_allmulti(bond->curr_active_slave->dev,
@@ -574,7 +574,7 @@ static void bond_hw_addr_flush(struct net_device *bond_dev,
 	dev_uc_unsync(slave_dev, bond_dev);
 	dev_mc_unsync(slave_dev, bond_dev);
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		/* del lacpdu mc addr from mc list */
 		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
 
@@ -585,8 +585,8 @@ static void bond_hw_addr_flush(struct net_device *bond_dev,
 /*--------------------------- Active slave change ---------------------------*/
 
 /* Update the hardware address list and promisc/allmulti for the new and
- * old active slaves (if any).  Modes that are !USES_PRIMARY keep all
- * slaves up date at all times; only the USES_PRIMARY modes need to call
+ * old active slaves (if any).  Modes that are not using primary keep all
+ * slaves up date at all times; only the modes that use primary need to call
  * this function to swap these settings during a failover.
  */
 static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active,
@@ -747,7 +747,7 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
 	bond_for_each_slave(bond, slave, iter) {
 		if (slave->link == BOND_LINK_UP)
 			return slave;
-		if (slave->link == BOND_LINK_BACK && IS_UP(slave->dev) &&
+		if (slave->link == BOND_LINK_BACK && bond_slave_is_up(slave) &&
 		    slave->delay < mintime) {
 			mintime = slave->delay;
 			bestslave = slave;
@@ -801,7 +801,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 		new_active->last_link_up = jiffies;
 
 		if (new_active->link == BOND_LINK_BACK) {
-			if (USES_PRIMARY(bond->params.mode)) {
+			if (bond_uses_primary(bond)) {
 				pr_info("%s: making interface %s the new active one %d ms earlier\n",
 					bond->dev->name, new_active->dev->name,
 					(bond->params.updelay - new_active->delay) * bond->params.miimon);
@@ -810,20 +810,20 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 			new_active->delay = 0;
 			new_active->link = BOND_LINK_UP;
 
-			if (bond->params.mode == BOND_MODE_8023AD)
+			if (BOND_MODE(bond) == BOND_MODE_8023AD)
 				bond_3ad_handle_link_change(new_active, BOND_LINK_UP);
 
 			if (bond_is_lb(bond))
 				bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP);
 		} else {
-			if (USES_PRIMARY(bond->params.mode)) {
+			if (bond_uses_primary(bond)) {
 				pr_info("%s: making interface %s the new active one\n",
 					bond->dev->name, new_active->dev->name);
 			}
 		}
 	}
 
-	if (USES_PRIMARY(bond->params.mode))
+	if (bond_uses_primary(bond))
 		bond_hw_addr_swap(bond, new_active, old_active);
 
 	if (bond_is_lb(bond)) {
@@ -838,7 +838,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 		rcu_assign_pointer(bond->curr_active_slave, new_active);
 	}
 
-	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
+	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) {
 		if (old_active)
 			bond_set_slave_inactive_flags(old_active,
 						      BOND_SLAVE_NOTIFY_NOW);
@@ -876,8 +876,8 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 	 * resend only if bond is brought up with the affected
 	 * bonding modes and the retransmission is enabled */
 	if (netif_running(bond->dev) && (bond->params.resend_igmp > 0) &&
-	    ((USES_PRIMARY(bond->params.mode) && new_active) ||
-	     bond->params.mode == BOND_MODE_ROUNDROBIN)) {
+	    ((bond_uses_primary(bond) && new_active) ||
+	     BOND_MODE(bond) == BOND_MODE_ROUNDROBIN)) {
 		bond->igmp_retrans = bond->params.resend_igmp;
 		queue_delayed_work(bond->wq, &bond->mcast_work, 1);
 	}
@@ -958,7 +958,7 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev)
 	struct slave *slave;
 
 	bond_for_each_slave(bond, slave, iter)
-		if (IS_UP(slave->dev))
+		if (bond_slave_is_up(slave))
 			slave_disable_netpoll(slave);
 }
 
@@ -1025,10 +1025,14 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
 				 NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
 				 NETIF_F_HIGHDMA | NETIF_F_LRO)
 
+#define BOND_ENC_FEATURES	(NETIF_F_ALL_CSUM | NETIF_F_SG | NETIF_F_RXCSUM |\
+				 NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL)
+
 static void bond_compute_features(struct bonding *bond)
 {
 	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
 	netdev_features_t vlan_features = BOND_VLAN_FEATURES;
+	netdev_features_t enc_features  = BOND_ENC_FEATURES;
 	struct net_device *bond_dev = bond->dev;
 	struct list_head *iter;
 	struct slave *slave;
@@ -1038,11 +1042,15 @@ static void bond_compute_features(struct bonding *bond)
 
 	if (!bond_has_slaves(bond))
 		goto done;
+	vlan_features &= NETIF_F_ALL_FOR_ALL;
 
 	bond_for_each_slave(bond, slave, iter) {
 		vlan_features = netdev_increment_features(vlan_features,
 			slave->dev->vlan_features, BOND_VLAN_FEATURES);
 
+		enc_features = netdev_increment_features(enc_features,
+							 slave->dev->hw_enc_features,
+							 BOND_ENC_FEATURES);
 		dst_release_flag &= slave->dev->priv_flags;
 		if (slave->dev->hard_header_len > max_hard_header_len)
 			max_hard_header_len = slave->dev->hard_header_len;
@@ -1053,6 +1061,7 @@ static void bond_compute_features(struct bonding *bond)
 
 done:
 	bond_dev->vlan_features = vlan_features;
+	bond_dev->hw_enc_features = enc_features;
 	bond_dev->hard_header_len = max_hard_header_len;
 	bond_dev->gso_max_segs = gso_max_segs;
 	netif_set_gso_max_size(bond_dev, gso_max_size);
@@ -1084,7 +1093,7 @@ static bool bond_should_deliver_exact_match(struct sk_buff *skb,
 					    struct bonding *bond)
 {
 	if (bond_is_slave_inactive(slave)) {
-		if (bond->params.mode == BOND_MODE_ALB &&
+		if (BOND_MODE(bond) == BOND_MODE_ALB &&
 		    skb->pkt_type != PACKET_BROADCAST &&
 		    skb->pkt_type != PACKET_MULTICAST)
 			return false;
@@ -1126,7 +1135,7 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 
 	skb->dev = bond->dev;
 
-	if (bond->params.mode == BOND_MODE_ALB &&
+	if (BOND_MODE(bond) == BOND_MODE_ALB &&
 	    bond->dev->priv_flags & IFF_BRIDGE_PORT &&
 	    skb->pkt_type == PACKET_HOST) {
 
@@ -1163,6 +1172,35 @@ static void bond_upper_dev_unlink(struct net_device *bond_dev,
 	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
 }
 
+static struct slave *bond_alloc_slave(struct bonding *bond)
+{
+	struct slave *slave = NULL;
+
+	slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
+	if (!slave)
+		return NULL;
+
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
+		SLAVE_AD_INFO(slave) = kzalloc(sizeof(struct ad_slave_info),
+					       GFP_KERNEL);
+		if (!SLAVE_AD_INFO(slave)) {
+			kfree(slave);
+			return NULL;
+		}
+	}
+	return slave;
+}
+
+static void bond_free_slave(struct slave *slave)
+{
+	struct bonding *bond = bond_get_bond_by_slave(slave);
+
+	if (BOND_MODE(bond) == BOND_MODE_8023AD)
+		kfree(SLAVE_AD_INFO(slave));
+
+	kfree(slave);
+}
+
 /* enslave device <slave> to bond device <master> */
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 {
@@ -1269,7 +1307,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		if (!bond_has_slaves(bond)) {
 			pr_warn("%s: Warning: The first slave device specified does not support setting the MAC address\n",
 				bond_dev->name);
-			if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) {
+			if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) {
 				bond->params.fail_over_mac = BOND_FOM_ACTIVE;
 				pr_warn("%s: Setting fail_over_mac to active for active-backup mode\n",
 					bond_dev->name);
@@ -1290,11 +1328,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	    bond->dev->addr_assign_type == NET_ADDR_RANDOM)
 		bond_set_dev_addr(bond->dev, slave_dev);
 
-	new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
+	new_slave = bond_alloc_slave(bond);
 	if (!new_slave) {
 		res = -ENOMEM;
 		goto err_undo_flags;
 	}
+
+	new_slave->bond = bond;
+	new_slave->dev = slave_dev;
 	/*
 	 * Set the new_slave's queue_id to be zero.  Queue ID mapping
 	 * is set via sysfs or module option if desired.
@@ -1317,7 +1358,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr);
 
 	if (!bond->params.fail_over_mac ||
-	    bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
+	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/*
 		 * Set slave to master's mac address.  The application already
 		 * set the master's mac address to that of the first slave
@@ -1338,8 +1379,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		goto err_restore_mac;
 	}
 
-	new_slave->bond = bond;
-	new_slave->dev = slave_dev;
 	slave_dev->priv_flags |= IFF_BONDING;
 
 	if (bond_is_lb(bond)) {
@@ -1351,10 +1390,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 			goto err_close;
 	}
 
-	/* If the mode USES_PRIMARY, then the following is handled by
+	/* If the mode uses primary, then the following is handled by
 	 * bond_change_active_slave().
 	 */
-	if (!USES_PRIMARY(bond->params.mode)) {
+	if (!bond_uses_primary(bond)) {
 		/* set promiscuity level to new slave */
 		if (bond_dev->flags & IFF_PROMISC) {
 			res = dev_set_promiscuity(slave_dev, 1);
@@ -1377,7 +1416,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		netif_addr_unlock_bh(bond_dev);
 	}
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		/* add lacpdu mc addr to mc list */
 		u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR;
 
@@ -1450,7 +1489,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		 new_slave->link == BOND_LINK_DOWN ? "DOWN" :
 		 (new_slave->link == BOND_LINK_UP ? "UP" : "BACK"));
 
-	if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) {
+	if (bond_uses_primary(bond) && bond->params.primary[0]) {
 		/* if there is a primary slave, remember it */
 		if (strcmp(bond->params.primary, new_slave->dev->name) == 0) {
 			bond->primary_slave = new_slave;
@@ -1458,7 +1497,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		}
 	}
 
-	switch (bond->params.mode) {
+	switch (BOND_MODE(bond)) {
 	case BOND_MODE_ACTIVEBACKUP:
 		bond_set_slave_inactive_flags(new_slave,
 					      BOND_SLAVE_NOTIFY_NOW);
@@ -1471,14 +1510,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW);
 		/* if this is the first slave */
 		if (!prev_slave) {
-			SLAVE_AD_INFO(new_slave).id = 1;
+			SLAVE_AD_INFO(new_slave)->id = 1;
 			/* Initialize AD with the number of times that the AD timer is called in 1 second
 			 * can be called only after the mac address of the bond is set
 			 */
 			bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL);
 		} else {
-			SLAVE_AD_INFO(new_slave).id =
-				SLAVE_AD_INFO(prev_slave).id + 1;
+			SLAVE_AD_INFO(new_slave)->id =
+				SLAVE_AD_INFO(prev_slave)->id + 1;
 		}
 
 		bond_3ad_bind_slave(new_slave);
@@ -1539,7 +1578,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 	bond_compute_features(bond);
 	bond_set_carrier(bond);
 
-	if (USES_PRIMARY(bond->params.mode)) {
+	if (bond_uses_primary(bond)) {
 		block_netpoll_tx();
 		write_lock_bh(&bond->curr_slave_lock);
 		bond_select_active_slave(bond);
@@ -1563,7 +1602,7 @@ err_unregister:
 	netdev_rx_handler_unregister(slave_dev);
 
 err_detach:
-	if (!USES_PRIMARY(bond->params.mode))
+	if (!bond_uses_primary(bond))
 		bond_hw_addr_flush(bond_dev, slave_dev);
 
 	vlan_vids_del_by_dev(slave_dev, bond_dev);
@@ -1585,7 +1624,7 @@ err_close:
 
 err_restore_mac:
 	if (!bond->params.fail_over_mac ||
-	    bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
+	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* XXX TODO - fom follow mode needs to change master's
 		 * MAC if this slave's MAC is in use by the bond, or at
 		 * least print a warning.
@@ -1599,7 +1638,7 @@ err_restore_mtu:
 	dev_set_mtu(slave_dev, new_slave->original_mtu);
 
 err_free:
-	kfree(new_slave);
+	bond_free_slave(new_slave);
 
 err_undo_flags:
 	/* Enslave of first slave has failed and we need to fix master's mac */
@@ -1661,7 +1700,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 	write_lock_bh(&bond->lock);
 
 	/* Inform AD package of unbinding of slave. */
-	if (bond->params.mode == BOND_MODE_8023AD)
+	if (BOND_MODE(bond) == BOND_MODE_8023AD)
 		bond_3ad_unbind_slave(slave);
 
 	write_unlock_bh(&bond->lock);
@@ -1676,7 +1715,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 	bond->current_arp_slave = NULL;
 
 	if (!all && (!bond->params.fail_over_mac ||
-		     bond->params.mode != BOND_MODE_ACTIVEBACKUP)) {
+		     BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) {
 		if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
 		    bond_has_slaves(bond))
 			pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s - set the HWaddr of %s to a different address to avoid conflicts\n",
@@ -1748,10 +1787,10 @@ static int __bond_release_one(struct net_device *bond_dev,
 	/* must do this from outside any spinlocks */
 	vlan_vids_del_by_dev(slave_dev, bond_dev);
 
-	/* If the mode USES_PRIMARY, then this cases was handled above by
+	/* If the mode uses primary, then this cases was handled above by
 	 * bond_change_active_slave(..., NULL)
 	 */
-	if (!USES_PRIMARY(bond->params.mode)) {
+	if (!bond_uses_primary(bond)) {
 		/* unset promiscuity level from slave
 		 * NOTE: The NETDEV_CHANGEADDR call above may change the value
 		 * of the IFF_PROMISC flag in the bond_dev, but we need the
@@ -1775,7 +1814,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 	dev_close(slave_dev);
 
 	if (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
-	    bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
+	    BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 		/* restore original ("permanent") mac address */
 		ether_addr_copy(addr.sa_data, slave->perm_hwaddr);
 		addr.sa_family = slave_dev->type;
@@ -1786,7 +1825,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 
 	slave_dev->priv_flags &= ~IFF_BONDING;
 
-	kfree(slave);
+	bond_free_slave(slave);
 
 	return 0;  /* deletion OK */
 }
@@ -1821,7 +1860,7 @@ static int bond_info_query(struct net_device *bond_dev, struct ifbond *info)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 
-	info->bond_mode = bond->params.mode;
+	info->bond_mode = BOND_MODE(bond);
 	info->miimon = bond->params.miimon;
 
 	info->num_slaves = bond->slave_cnt;
@@ -1877,7 +1916,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (slave->delay) {
 				pr_info("%s: link status down for %sinterface %s, disabling it in %d ms\n",
 					bond->dev->name,
-					(bond->params.mode ==
+					(BOND_MODE(bond) ==
 					 BOND_MODE_ACTIVEBACKUP) ?
 					(bond_is_active_slave(slave) ?
 					 "active " : "backup ") : "",
@@ -1968,10 +2007,10 @@ static void bond_miimon_commit(struct bonding *bond)
 			slave->link = BOND_LINK_UP;
 			slave->last_link_up = jiffies;
 
-			if (bond->params.mode == BOND_MODE_8023AD) {
+			if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 				/* prevent it from being the active one */
 				bond_set_backup_slave(slave);
-			} else if (bond->params.mode != BOND_MODE_ACTIVEBACKUP) {
+			} else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 				/* make it immediately active */
 				bond_set_active_slave(slave);
 			} else if (slave != bond->primary_slave) {
@@ -1985,7 +2024,7 @@ static void bond_miimon_commit(struct bonding *bond)
 				slave->duplex ? "full" : "half");
 
 			/* notify ad that the link status has changed */
-			if (bond->params.mode == BOND_MODE_8023AD)
+			if (BOND_MODE(bond) == BOND_MODE_8023AD)
 				bond_3ad_handle_link_change(slave, BOND_LINK_UP);
 
 			if (bond_is_lb(bond))
@@ -2004,15 +2043,15 @@ static void bond_miimon_commit(struct bonding *bond)
 
 			slave->link = BOND_LINK_DOWN;
 
-			if (bond->params.mode == BOND_MODE_ACTIVEBACKUP ||
-			    bond->params.mode == BOND_MODE_8023AD)
+			if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
+			    BOND_MODE(bond) == BOND_MODE_8023AD)
 				bond_set_slave_inactive_flags(slave,
 							      BOND_SLAVE_NOTIFY_NOW);
 
 			pr_info("%s: link status definitely down for interface %s, disabling it\n",
 				bond->dev->name, slave->dev->name);
 
-			if (bond->params.mode == BOND_MODE_8023AD)
+			if (BOND_MODE(bond) == BOND_MODE_8023AD)
 				bond_3ad_handle_link_change(slave,
 							    BOND_LINK_DOWN);
 
@@ -2175,9 +2214,9 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
  * When the path is validated, collect any vlan information in the
  * path.
  */
-static bool bond_verify_device_path(struct net_device *start_dev,
-				    struct net_device *end_dev,
-				    struct bond_vlan_tag *tags)
+bool bond_verify_device_path(struct net_device *start_dev,
+			     struct net_device *end_dev,
+			     struct bond_vlan_tag *tags)
 {
 	struct net_device *upper;
 	struct list_head  *iter;
@@ -2287,8 +2326,8 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond,
 	int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP);
 
 	if (!slave_do_arp_validate(bond, slave)) {
-		if ((slave_do_arp_validate_only(bond, slave) && is_arp) ||
-		    !slave_do_arp_validate_only(bond, slave))
+		if ((slave_do_arp_validate_only(bond) && is_arp) ||
+		    !slave_do_arp_validate_only(bond))
 			slave->last_rx = jiffies;
 		return RX_HANDLER_ANOTHER;
 	} else if (!is_arp) {
@@ -2456,7 +2495,7 @@ static void bond_loadbalance_arp_mon(struct work_struct *work)
 		 * do - all replies will be rx'ed on same link causing slaves
 		 * to be unstable during low/no traffic periods
 		 */
-		if (IS_UP(slave->dev))
+		if (bond_slave_is_up(slave))
 			bond_arp_send_all(bond, slave);
 	}
 
@@ -2678,10 +2717,10 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 	bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER);
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		if (!found && !before && IS_UP(slave->dev))
+		if (!found && !before && bond_slave_is_up(slave))
 			before = slave;
 
-		if (found && !new_slave && IS_UP(slave->dev))
+		if (found && !new_slave && bond_slave_is_up(slave))
 			new_slave = slave;
 		/* if the link state is up at this point, we
 		 * mark it down - this can happen if we have
@@ -2690,7 +2729,7 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 		 * one the current slave so it is still marked
 		 * up when it is actually down
 		 */
-		if (!IS_UP(slave->dev) && slave->link == BOND_LINK_UP) {
+		if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) {
 			slave->link = BOND_LINK_DOWN;
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
@@ -2853,7 +2892,7 @@ static int bond_slave_netdev_event(unsigned long event,
 
 		bond_update_speed_duplex(slave);
 
-		if (bond->params.mode == BOND_MODE_8023AD) {
+		if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 			if (old_speed != slave->speed)
 				bond_3ad_adapter_speed_changed(slave);
 			if (old_duplex != slave->duplex)
@@ -2881,7 +2920,7 @@ static int bond_slave_netdev_event(unsigned long event,
 		break;
 	case NETDEV_CHANGENAME:
 		/* we don't care if we don't have primary set */
-		if (!USES_PRIMARY(bond->params.mode) ||
+		if (!bond_uses_primary(bond) ||
 		    !bond->params.primary[0])
 			break;
 
@@ -3011,20 +3050,18 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
  * bond_xmit_hash - generate a hash value based on the xmit policy
  * @bond: bonding device
  * @skb: buffer to use for headers
- * @count: modulo value
  *
  * This function will extract the necessary headers from the skb buffer and use
  * them to generate a hash based on the xmit_policy set in the bonding device
- * which will be reduced modulo count before returning.
  */
-int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count)
+u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 {
 	struct flow_keys flow;
 	u32 hash;
 
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 ||
 	    !bond_flow_dissect(bond, skb, &flow))
-		return bond_eth_hash(skb) % count;
+		return bond_eth_hash(skb);
 
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
 	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23)
@@ -3035,7 +3072,7 @@ int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count)
 	hash ^= (hash >> 16);
 	hash ^= (hash >> 8);
 
-	return hash % count;
+	return hash;
 }
 
 /*-------------------------- Device entry points ----------------------------*/
@@ -3046,7 +3083,7 @@ static void bond_work_init_all(struct bonding *bond)
 			  bond_resend_igmp_join_requests_delayed);
 	INIT_DELAYED_WORK(&bond->alb_work, bond_alb_monitor);
 	INIT_DELAYED_WORK(&bond->mii_work, bond_mii_monitor);
-	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP)
+	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
 		INIT_DELAYED_WORK(&bond->arp_work, bond_activebackup_arp_mon);
 	else
 		INIT_DELAYED_WORK(&bond->arp_work, bond_loadbalance_arp_mon);
@@ -3073,7 +3110,7 @@ static int bond_open(struct net_device *bond_dev)
 	if (bond_has_slaves(bond)) {
 		read_lock(&bond->curr_slave_lock);
 		bond_for_each_slave(bond, slave, iter) {
-			if (USES_PRIMARY(bond->params.mode)
+			if (bond_uses_primary(bond)
 				&& (slave != bond->curr_active_slave)) {
 				bond_set_slave_inactive_flags(slave,
 							      BOND_SLAVE_NOTIFY_NOW);
@@ -3092,9 +3129,10 @@ static int bond_open(struct net_device *bond_dev)
 		/* bond_alb_initialize must be called before the timer
 		 * is started.
 		 */
-		if (bond_alb_initialize(bond, (bond->params.mode == BOND_MODE_ALB)))
+		if (bond_alb_initialize(bond, (BOND_MODE(bond) == BOND_MODE_ALB)))
 			return -ENOMEM;
-		queue_delayed_work(bond->wq, &bond->alb_work, 0);
+		if (bond->params.tlb_dynamic_lb)
+			queue_delayed_work(bond->wq, &bond->alb_work, 0);
 	}
 
 	if (bond->params.miimon)  /* link check interval, in milliseconds. */
@@ -3105,7 +3143,7 @@ static int bond_open(struct net_device *bond_dev)
 		bond->recv_probe = bond_arp_rcv;
 	}
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		queue_delayed_work(bond->wq, &bond->ad_work, 0);
 		/* register to receive LACPDUs */
 		bond->recv_probe = bond_3ad_lacpdu_recv;
@@ -3310,7 +3348,7 @@ static void bond_set_rx_mode(struct net_device *bond_dev)
 
 
 	rcu_read_lock();
-	if (USES_PRIMARY(bond->params.mode)) {
+	if (bond_uses_primary(bond)) {
 		slave = rcu_dereference(bond->curr_active_slave);
 		if (slave) {
 			dev_uc_sync(slave->dev, bond_dev);
@@ -3464,7 +3502,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	struct list_head *iter;
 	int res = 0;
 
-	if (bond->params.mode == BOND_MODE_ALB)
+	if (BOND_MODE(bond) == BOND_MODE_ALB)
 		return bond_alb_set_mac_address(bond_dev, addr);
 
 
@@ -3475,7 +3513,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr)
 	 * Returning an error causes ifenslave to fail.
 	 */
 	if (bond->params.fail_over_mac &&
-	    bond->params.mode == BOND_MODE_ACTIVEBACKUP)
+	    BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP)
 		return 0;
 
 	if (!is_valid_ether_addr(sa->sa_data))
@@ -3555,7 +3593,7 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl
 	/* Here we start from the slave with slave_id */
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (--i < 0) {
-			if (slave_can_tx(slave)) {
+			if (bond_slave_can_tx(slave)) {
 				bond_dev_queue_xmit(bond, skb, slave->dev);
 				return;
 			}
@@ -3567,7 +3605,7 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (--i < 0)
 			break;
-		if (slave_can_tx(slave)) {
+		if (bond_slave_can_tx(slave)) {
 			bond_dev_queue_xmit(bond, skb, slave->dev);
 			return;
 		}
@@ -3624,7 +3662,7 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev
 	 */
 	if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) {
 		slave = rcu_dereference(bond->curr_active_slave);
-		if (slave && slave_can_tx(slave))
+		if (slave && bond_slave_can_tx(slave))
 			bond_dev_queue_xmit(bond, skb, slave->dev);
 		else
 			bond_xmit_slave_id(bond, skb, 0);
@@ -3662,7 +3700,7 @@ static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 
-	bond_xmit_slave_id(bond, skb, bond_xmit_hash(bond, skb, bond->slave_cnt));
+	bond_xmit_slave_id(bond, skb, bond_xmit_hash(bond, skb) % bond->slave_cnt);
 
 	return NETDEV_TX_OK;
 }
@@ -3677,7 +3715,7 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev)
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (bond_is_last_slave(bond, slave))
 			break;
-		if (IS_UP(slave->dev) && slave->link == BOND_LINK_UP) {
+		if (bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) {
 			struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
 
 			if (!skb2) {
@@ -3689,7 +3727,7 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev)
 			bond_dev_queue_xmit(bond, skb2, slave->dev);
 		}
 	}
-	if (slave && IS_UP(slave->dev) && slave->link == BOND_LINK_UP)
+	if (slave && bond_slave_is_up(slave) && slave->link == BOND_LINK_UP)
 		bond_dev_queue_xmit(bond, skb, slave->dev);
 	else
 		dev_kfree_skb_any(skb);
@@ -3714,7 +3752,7 @@ static inline int bond_slave_override(struct bonding *bond,
 	/* Find out if any slaves have the same mapping as this skb. */
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		if (slave->queue_id == skb->queue_mapping) {
-			if (slave_can_tx(slave)) {
+			if (bond_slave_can_tx(slave)) {
 				bond_dev_queue_xmit(bond, skb, slave->dev);
 				return 0;
 			}
@@ -3755,12 +3793,11 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev
 {
 	struct bonding *bond = netdev_priv(dev);
 
-	if (TX_QUEUE_OVERRIDE(bond->params.mode)) {
-		if (!bond_slave_override(bond, skb))
-			return NETDEV_TX_OK;
-	}
+	if (bond_should_override_tx_queue(bond) &&
+	    !bond_slave_override(bond, skb))
+		return NETDEV_TX_OK;
 
-	switch (bond->params.mode) {
+	switch (BOND_MODE(bond)) {
 	case BOND_MODE_ROUNDROBIN:
 		return bond_xmit_roundrobin(skb, dev);
 	case BOND_MODE_ACTIVEBACKUP:
@@ -3772,12 +3809,13 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev
 	case BOND_MODE_8023AD:
 		return bond_3ad_xmit_xor(skb, dev);
 	case BOND_MODE_ALB:
-	case BOND_MODE_TLB:
 		return bond_alb_xmit(skb, dev);
+	case BOND_MODE_TLB:
+		return bond_tlb_xmit(skb, dev);
 	default:
 		/* Should never happen, mode already checked */
 		pr_err("%s: Error: Unknown bonding mode %d\n",
-		       dev->name, bond->params.mode);
+		       dev->name, BOND_MODE(bond));
 		WARN_ON_ONCE(1);
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
@@ -3817,14 +3855,14 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev,
 	ecmd->duplex = DUPLEX_UNKNOWN;
 	ecmd->port = PORT_OTHER;
 
-	/* Since SLAVE_IS_OK returns false for all inactive or down slaves, we
+	/* Since bond_slave_can_tx returns false for all inactive or down slaves, we
 	 * do not need to check mode.  Though link speed might not represent
 	 * the true receive or transmit bandwidth (not all modes are symmetric)
 	 * this is an accurate maximum.
 	 */
 	read_lock(&bond->lock);
 	bond_for_each_slave(bond, slave, iter) {
-		if (SLAVE_IS_OK(slave)) {
+		if (bond_slave_can_tx(slave)) {
 			if (slave->speed != SPEED_UNKNOWN)
 				speed += slave->speed;
 			if (ecmd->duplex == DUPLEX_UNKNOWN &&
@@ -3915,7 +3953,7 @@ void bond_setup(struct net_device *bond_dev)
 	/* Initialize the device options */
 	bond_dev->tx_queue_len = 0;
 	bond_dev->flags |= IFF_MASTER|IFF_MULTICAST;
-	bond_dev->priv_flags |= IFF_BONDING;
+	bond_dev->priv_flags |= IFF_BONDING | IFF_UNICAST_FLT;
 	bond_dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
 
 	/* At first, we block adding VLANs. That's the only way to
@@ -3945,6 +3983,7 @@ void bond_setup(struct net_device *bond_dev)
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM);
+	bond_dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
 	bond_dev->features |= bond_dev->hw_features;
 }
 
@@ -3994,7 +4033,8 @@ static int bond_check_params(struct bond_params *params)
 
 	if (xmit_hash_policy) {
 		if ((bond_mode != BOND_MODE_XOR) &&
-		    (bond_mode != BOND_MODE_8023AD)) {
+		    (bond_mode != BOND_MODE_8023AD) &&
+		    (bond_mode != BOND_MODE_TLB)) {
 			pr_info("xmit_hash_policy param is irrelevant in mode %s\n",
 				bond_mode_name(bond_mode));
 		} else {
@@ -4028,7 +4068,7 @@ static int bond_check_params(struct bond_params *params)
 	}
 
 	if (ad_select) {
-		bond_opt_initstr(&newval, lacp_rate);
+		bond_opt_initstr(&newval, ad_select);
 		valptr = bond_opt_parse(bond_opt_get(BOND_OPT_AD_SELECT),
 					&newval);
 		if (!valptr) {
@@ -4079,7 +4119,7 @@ static int bond_check_params(struct bond_params *params)
 	}
 
 	/* reset values for 802.3ad/TLB/ALB */
-	if (BOND_NO_USES_ARP(bond_mode)) {
+	if (!bond_mode_uses_arp(bond_mode)) {
 		if (!miimon) {
 			pr_warn("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n");
 			pr_warn("Forcing miimon to 100msec\n");
@@ -4161,7 +4201,7 @@ static int bond_check_params(struct bond_params *params)
 		   catch mistakes */
 		__be32 ip;
 		if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) ||
-		    IS_IP_TARGET_UNUSABLE_ADDRESS(ip)) {
+		    !bond_is_ip_target_ok(ip)) {
 			pr_warn("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n",
 				arp_ip_target[i]);
 			arp_interval = 0;
@@ -4234,7 +4274,7 @@ static int bond_check_params(struct bond_params *params)
 		pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details\n");
 	}
 
-	if (primary && !USES_PRIMARY(bond_mode)) {
+	if (primary && !bond_mode_uses_primary(bond_mode)) {
 		/* currently, using a primary only makes sense
 		 * in active backup, TLB or ALB modes
 		 */
@@ -4300,6 +4340,7 @@ static int bond_check_params(struct bond_params *params)
 	params->min_links = min_links;
 	params->lp_interval = lp_interval;
 	params->packets_per_slave = packets_per_slave;
+	params->tlb_dynamic_lb = 1; /* Default value */
 	if (packets_per_slave > 0) {
 		params->reciprocal_packets_per_slave =
 			reciprocal_value(packets_per_slave);
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index f847e165d25..5ab3c1847e6 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -56,10 +56,10 @@ static int bond_fill_slave_info(struct sk_buff *skb,
 	if (nla_put_u16(skb, IFLA_BOND_SLAVE_QUEUE_ID, slave->queue_id))
 		goto nla_put_failure;
 
-	if (slave->bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) {
 		const struct aggregator *agg;
 
-		agg = SLAVE_AD_INFO(slave).port.aggregator;
+		agg = SLAVE_AD_INFO(slave)->port.aggregator;
 		if (agg)
 			if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID,
 					agg->aggregator_identifier))
@@ -407,7 +407,7 @@ static int bond_fill_info(struct sk_buff *skb,
 	unsigned int packets_per_slave;
 	int i, targets_added;
 
-	if (nla_put_u8(skb, IFLA_BOND_MODE, bond->params.mode))
+	if (nla_put_u8(skb, IFLA_BOND_MODE, BOND_MODE(bond)))
 		goto nla_put_failure;
 
 	if (slave_dev &&
@@ -505,7 +505,7 @@ static int bond_fill_info(struct sk_buff *skb,
 		       bond->params.ad_select))
 		goto nla_put_failure;
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info info;
 
 		if (!bond_3ad_get_active_agg_info(bond, &info)) {
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 83207029844..540e0167bf2 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -70,6 +70,8 @@ static int bond_option_mode_set(struct bonding *bond,
 				const struct bond_opt_value *newval);
 static int bond_option_slaves_set(struct bonding *bond,
 				  const struct bond_opt_value *newval);
+static int bond_option_tlb_dynamic_lb_set(struct bonding *bond,
+				  const struct bond_opt_value *newval);
 
 
 static const struct bond_opt_value bond_mode_tbl[] = {
@@ -180,6 +182,12 @@ static const struct bond_opt_value bond_lp_interval_tbl[] = {
 	{ NULL,      -1,      0},
 };
 
+static const struct bond_opt_value bond_tlb_dynamic_lb_tbl[] = {
+	{ "off", 0,  0},
+	{ "on",  1,  BOND_VALFLAG_DEFAULT},
+	{ NULL,  -1, 0}
+};
+
 static const struct bond_option bond_opts[] = {
 	[BOND_OPT_MODE] = {
 		.id = BOND_OPT_MODE,
@@ -200,7 +208,7 @@ static const struct bond_option bond_opts[] = {
 	[BOND_OPT_XMIT_HASH] = {
 		.id = BOND_OPT_XMIT_HASH,
 		.name = "xmit_hash_policy",
-		.desc = "balance-xor and 802.3ad hashing method",
+		.desc = "balance-xor, 802.3ad, and tlb hashing method",
 		.values = bond_xmit_hashtype_tbl,
 		.set = bond_option_xmit_hash_policy_set
 	},
@@ -365,9 +373,33 @@ static const struct bond_option bond_opts[] = {
 		.flags = BOND_OPTFLAG_RAWVAL,
 		.set = bond_option_slaves_set
 	},
+	[BOND_OPT_TLB_DYNAMIC_LB] = {
+		.id = BOND_OPT_TLB_DYNAMIC_LB,
+		.name = "tlb_dynamic_lb",
+		.desc = "Enable dynamic flow shuffling",
+		.unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_TLB)),
+		.values = bond_tlb_dynamic_lb_tbl,
+		.flags = BOND_OPTFLAG_IFDOWN,
+		.set = bond_option_tlb_dynamic_lb_set,
+	},
 	{ }
 };
 
+/* Searches for an option by name */
+const struct bond_option *bond_opt_get_by_name(const char *name)
+{
+	const struct bond_option *opt;
+	int option;
+
+	for (option = 0; option < BOND_OPT_LAST; option++) {
+		opt = bond_opt_get(option);
+		if (opt && !strcmp(opt->name, name))
+			return opt;
+	}
+
+	return NULL;
+}
+
 /* Searches for a value in opt's values[] table */
 const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val)
 {
@@ -641,7 +673,7 @@ const struct bond_option *bond_opt_get(unsigned int option)
 
 int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval)
 {
-	if (BOND_NO_USES_ARP(newval->value) && bond->params.arp_interval) {
+	if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) {
 		pr_info("%s: %s mode is incompatible with arp monitoring, start mii monitoring\n",
 			bond->dev->name, newval->string);
 		/* disable arp monitoring */
@@ -662,7 +694,7 @@ int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newv
 static struct net_device *__bond_option_active_slave_get(struct bonding *bond,
 							 struct slave *slave)
 {
-	return USES_PRIMARY(bond->params.mode) && slave ? slave->dev : NULL;
+	return bond_uses_primary(bond) && slave ? slave->dev : NULL;
 }
 
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond)
@@ -727,7 +759,7 @@ static int bond_option_active_slave_set(struct bonding *bond,
 				bond->dev->name, new_active->dev->name);
 		} else {
 			if (old_active && (new_active->link == BOND_LINK_UP) &&
-			    IS_UP(new_active->dev)) {
+			    bond_slave_is_up(new_active)) {
 				pr_info("%s: Setting %s as active slave\n",
 					bond->dev->name, new_active->dev->name);
 				bond_change_active_slave(bond, new_active);
@@ -746,6 +778,10 @@ static int bond_option_active_slave_set(struct bonding *bond,
 	return ret;
 }
 
+/* There are two tricky bits here.  First, if MII monitoring is activated, then
+ * we must disable ARP monitoring.  Second, if the timer isn't running, we must
+ * start it.
+ */
 static int bond_option_miimon_set(struct bonding *bond,
 				  const struct bond_opt_value *newval)
 {
@@ -784,6 +820,10 @@ static int bond_option_miimon_set(struct bonding *bond,
 	return 0;
 }
 
+/* Set up and down delays. These must be multiples of the
+ * MII monitoring value, and are stored internally as the multiplier.
+ * Thus, we must translate to MS for the real world.
+ */
 static int bond_option_updelay_set(struct bonding *bond,
 				   const struct bond_opt_value *newval)
 {
@@ -842,6 +882,10 @@ static int bond_option_use_carrier_set(struct bonding *bond,
 	return 0;
 }
 
+/* There are two tricky bits here.  First, if ARP monitoring is activated, then
+ * we must disable MII monitoring.  Second, if the ARP timer isn't running,
+ * we must start it.
+ */
 static int bond_option_arp_interval_set(struct bonding *bond,
 					const struct bond_opt_value *newval)
 {
@@ -899,7 +943,7 @@ static int _bond_option_arp_ip_target_add(struct bonding *bond, __be32 target)
 	__be32 *targets = bond->params.arp_targets;
 	int ind;
 
-	if (IS_IP_TARGET_UNUSABLE_ADDRESS(target)) {
+	if (!bond_is_ip_target_ok(target)) {
 		pr_err("%s: invalid ARP target %pI4 specified for addition\n",
 		       bond->dev->name, &target);
 		return -EINVAL;
@@ -944,7 +988,7 @@ static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target)
 	unsigned long *targets_rx;
 	int ind, i;
 
-	if (IS_IP_TARGET_UNUSABLE_ADDRESS(target)) {
+	if (!bond_is_ip_target_ok(target)) {
 		pr_err("%s: invalid ARP target %pI4 specified for removal\n",
 		       bond->dev->name, &target);
 		return -EINVAL;
@@ -1338,3 +1382,13 @@ err_no_cmd:
 	ret = -EPERM;
 	goto out;
 }
+
+static int bond_option_tlb_dynamic_lb_set(struct bonding *bond,
+					  const struct bond_opt_value *newval)
+{
+	pr_info("%s: Setting dynamic-lb to %s (%llu)\n",
+		bond->dev->name, newval->string, newval->value);
+	bond->params.tlb_dynamic_lb = newval->value;
+
+	return 0;
+}
diff --git a/drivers/net/bonding/bond_options.h b/drivers/net/bonding/bond_options.h
index 12be9e1bfb0..17ded5b2917 100644
--- a/drivers/net/bonding/bond_options.h
+++ b/drivers/net/bonding/bond_options.h
@@ -62,6 +62,7 @@ enum {
 	BOND_OPT_RESEND_IGMP,
 	BOND_OPT_LP_INTERVAL,
 	BOND_OPT_SLAVES,
+	BOND_OPT_TLB_DYNAMIC_LB,
 	BOND_OPT_LAST
 };
 
@@ -104,6 +105,7 @@ int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf);
 const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt,
 					    struct bond_opt_value *val);
 const struct bond_option *bond_opt_get(unsigned int option);
+const struct bond_option *bond_opt_get_by_name(const char *name);
 const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val);
 
 /* This helper is used to initialize a bond_opt_value structure for parameter
diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c
index 013fdd0f45e..b215b479bb3 100644
--- a/drivers/net/bonding/bond_procfs.c
+++ b/drivers/net/bonding/bond_procfs.c
@@ -72,9 +72,9 @@ static void bond_info_show_master(struct seq_file *seq)
 	curr = rcu_dereference(bond->curr_active_slave);
 
 	seq_printf(seq, "Bonding Mode: %s",
-		   bond_mode_name(bond->params.mode));
+		   bond_mode_name(BOND_MODE(bond)));
 
-	if (bond->params.mode == BOND_MODE_ACTIVEBACKUP &&
+	if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP &&
 	    bond->params.fail_over_mac) {
 		optval = bond_opt_get_val(BOND_OPT_FAIL_OVER_MAC,
 					  bond->params.fail_over_mac);
@@ -83,15 +83,15 @@ static void bond_info_show_master(struct seq_file *seq)
 
 	seq_printf(seq, "\n");
 
-	if (bond->params.mode == BOND_MODE_XOR ||
-		bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_XOR ||
+		BOND_MODE(bond) == BOND_MODE_8023AD) {
 		optval = bond_opt_get_val(BOND_OPT_XMIT_HASH,
 					  bond->params.xmit_policy);
 		seq_printf(seq, "Transmit Hash Policy: %s (%d)\n",
 			   optval->string, bond->params.xmit_policy);
 	}
 
-	if (USES_PRIMARY(bond->params.mode)) {
+	if (bond_uses_primary(bond)) {
 		seq_printf(seq, "Primary Slave: %s",
 			   (bond->primary_slave) ?
 			   bond->primary_slave->dev->name : "None");
@@ -134,7 +134,7 @@ static void bond_info_show_master(struct seq_file *seq)
 		seq_printf(seq, "\n");
 	}
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info ad_info;
 
 		seq_puts(seq, "\n802.3ad info\n");
@@ -188,9 +188,9 @@ static void bond_info_show_slave(struct seq_file *seq,
 
 	seq_printf(seq, "Permanent HW addr: %pM\n", slave->perm_hwaddr);
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		const struct aggregator *agg
-			= SLAVE_AD_INFO(slave).port.aggregator;
+			= SLAVE_AD_INFO(slave)->port.aggregator;
 
 		if (agg)
 			seq_printf(seq, "Aggregator ID: %d\n",
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 5f6babcfc26..daed52f68ce 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -45,8 +45,7 @@
 #define to_dev(obj)	container_of(obj, struct device, kobj)
 #define to_bond(cd)	((struct bonding *)(netdev_priv(to_net_dev(cd))))
 
-/*
- * "show" function for the bond_masters attribute.
+/* "show" function for the bond_masters attribute.
  * The class parameter is ignored.
  */
 static ssize_t bonding_show_bonds(struct class *cls,
@@ -88,14 +87,12 @@ static struct net_device *bond_get_by_name(struct bond_net *bn, const char *ifna
 	return NULL;
 }
 
-/*
- * "store" function for the bond_masters attribute.  This is what
+/* "store" function for the bond_masters attribute.  This is what
  * creates and deletes entire bonds.
  *
  * The class parameter is ignored.
  *
  */
-
 static ssize_t bonding_store_bonds(struct class *cls,
 				   struct class_attribute *attr,
 				   const char *buffer, size_t count)
@@ -158,9 +155,26 @@ static const struct class_attribute class_attr_bonding_masters = {
 	.store = bonding_store_bonds,
 };
 
-/*
- * Show the slaves in the current bond.
- */
+/* Generic "store" method for bonding sysfs option setting */
+static ssize_t bonding_sysfs_store_option(struct device *d,
+					  struct device_attribute *attr,
+					  const char *buffer, size_t count)
+{
+	struct bonding *bond = to_bond(d);
+	const struct bond_option *opt;
+	int ret;
+
+	opt = bond_opt_get_by_name(attr->attr.name);
+	if (WARN_ON(!opt))
+		return -ENOENT;
+	ret = bond_opt_tryset_rtnl(bond, opt->id, (char *)buffer);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+
+/* Show the slaves in the current bond. */
 static ssize_t bonding_show_slaves(struct device *d,
 				   struct device_attribute *attr, char *buf)
 {
@@ -190,62 +204,24 @@ static ssize_t bonding_show_slaves(struct device *d,
 
 	return res;
 }
-
-/*
- * Set the slaves in the current bond.
- * This is supposed to be only thin wrapper for bond_enslave and bond_release.
- * All hard work should be done there.
- */
-static ssize_t bonding_store_slaves(struct device *d,
-				    struct device_attribute *attr,
-				    const char *buffer, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_SLAVES, (char *)buffer);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(slaves, S_IRUGO | S_IWUSR, bonding_show_slaves,
-		   bonding_store_slaves);
+		   bonding_sysfs_store_option);
 
-/*
- * Show and set the bonding mode.  The bond interface must be down to
- * change the mode.
- */
+/* Show the bonding mode. */
 static ssize_t bonding_show_mode(struct device *d,
 				 struct device_attribute *attr, char *buf)
 {
 	struct bonding *bond = to_bond(d);
 	const struct bond_opt_value *val;
 
-	val = bond_opt_get_val(BOND_OPT_MODE, bond->params.mode);
+	val = bond_opt_get_val(BOND_OPT_MODE, BOND_MODE(bond));
 
-	return sprintf(buf, "%s %d\n", val->string, bond->params.mode);
-}
-
-static ssize_t bonding_store_mode(struct device *d,
-				  struct device_attribute *attr,
-				  const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_MODE, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
+	return sprintf(buf, "%s %d\n", val->string, BOND_MODE(bond));
 }
 static DEVICE_ATTR(mode, S_IRUGO | S_IWUSR,
-		   bonding_show_mode, bonding_store_mode);
+		   bonding_show_mode, bonding_sysfs_store_option);
 
-/*
- * Show and set the bonding transmit hash method.
- */
+/* Show the bonding transmit hash method. */
 static ssize_t bonding_show_xmit_hash(struct device *d,
 				      struct device_attribute *attr,
 				      char *buf)
@@ -257,26 +233,10 @@ static ssize_t bonding_show_xmit_hash(struct device *d,
 
 	return sprintf(buf, "%s %d\n", val->string, bond->params.xmit_policy);
 }
-
-static ssize_t bonding_store_xmit_hash(struct device *d,
-				       struct device_attribute *attr,
-				       const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_XMIT_HASH, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(xmit_hash_policy, S_IRUGO | S_IWUSR,
-		   bonding_show_xmit_hash, bonding_store_xmit_hash);
+		   bonding_show_xmit_hash, bonding_sysfs_store_option);
 
-/*
- * Show and set arp_validate.
- */
+/* Show arp_validate. */
 static ssize_t bonding_show_arp_validate(struct device *d,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -289,26 +249,10 @@ static ssize_t bonding_show_arp_validate(struct device *d,
 
 	return sprintf(buf, "%s %d\n", val->string, bond->params.arp_validate);
 }
-
-static ssize_t bonding_store_arp_validate(struct device *d,
-					  struct device_attribute *attr,
-					  const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_ARP_VALIDATE, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
-
 static DEVICE_ATTR(arp_validate, S_IRUGO | S_IWUSR, bonding_show_arp_validate,
-		   bonding_store_arp_validate);
-/*
- * Show and set arp_all_targets.
- */
+		   bonding_sysfs_store_option);
+
+/* Show arp_all_targets. */
 static ssize_t bonding_show_arp_all_targets(struct device *d,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -321,28 +265,10 @@ static ssize_t bonding_show_arp_all_targets(struct device *d,
 	return sprintf(buf, "%s %d\n",
 		       val->string, bond->params.arp_all_targets);
 }
-
-static ssize_t bonding_store_arp_all_targets(struct device *d,
-					  struct device_attribute *attr,
-					  const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_ARP_ALL_TARGETS, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
-
 static DEVICE_ATTR(arp_all_targets, S_IRUGO | S_IWUSR,
-		   bonding_show_arp_all_targets, bonding_store_arp_all_targets);
+		   bonding_show_arp_all_targets, bonding_sysfs_store_option);
 
-/*
- * Show and store fail_over_mac.  User only allowed to change the
- * value when there are no slaves.
- */
+/* Show fail_over_mac. */
 static ssize_t bonding_show_fail_over_mac(struct device *d,
 					  struct device_attribute *attr,
 					  char *buf)
@@ -355,30 +281,10 @@ static ssize_t bonding_show_fail_over_mac(struct device *d,
 
 	return sprintf(buf, "%s %d\n", val->string, bond->params.fail_over_mac);
 }
-
-static ssize_t bonding_store_fail_over_mac(struct device *d,
-					   struct device_attribute *attr,
-					   const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_FAIL_OVER_MAC, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
-
 static DEVICE_ATTR(fail_over_mac, S_IRUGO | S_IWUSR,
-		   bonding_show_fail_over_mac, bonding_store_fail_over_mac);
+		   bonding_show_fail_over_mac, bonding_sysfs_store_option);
 
-/*
- * Show and set the arp timer interval.  There are two tricky bits
- * here.  First, if ARP monitoring is activated, then we must disable
- * MII monitoring.  Second, if the ARP timer isn't running, we must
- * start it.
- */
+/* Show the arp timer interval. */
 static ssize_t bonding_show_arp_interval(struct device *d,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -387,26 +293,10 @@ static ssize_t bonding_show_arp_interval(struct device *d,
 
 	return sprintf(buf, "%d\n", bond->params.arp_interval);
 }
-
-static ssize_t bonding_store_arp_interval(struct device *d,
-					  struct device_attribute *attr,
-					  const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_ARP_INTERVAL, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(arp_interval, S_IRUGO | S_IWUSR,
-		   bonding_show_arp_interval, bonding_store_arp_interval);
+		   bonding_show_arp_interval, bonding_sysfs_store_option);
 
-/*
- * Show and set the arp targets.
- */
+/* Show the arp targets. */
 static ssize_t bonding_show_arp_targets(struct device *d,
 					struct device_attribute *attr,
 					char *buf)
@@ -424,27 +314,10 @@ static ssize_t bonding_show_arp_targets(struct device *d,
 
 	return res;
 }
+static DEVICE_ATTR(arp_ip_target, S_IRUGO | S_IWUSR,
+		   bonding_show_arp_targets, bonding_sysfs_store_option);
 
-static ssize_t bonding_store_arp_targets(struct device *d,
-					 struct device_attribute *attr,
-					 const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_ARP_TARGETS, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
-static DEVICE_ATTR(arp_ip_target, S_IRUGO | S_IWUSR , bonding_show_arp_targets, bonding_store_arp_targets);
-
-/*
- * Show and set the up and down delays.  These must be multiples of the
- * MII monitoring value, and are stored internally as the multiplier.
- * Thus, we must translate to MS for the real world.
- */
+/* Show the up and down delays. */
 static ssize_t bonding_show_downdelay(struct device *d,
 				      struct device_attribute *attr,
 				      char *buf)
@@ -453,22 +326,8 @@ static ssize_t bonding_show_downdelay(struct device *d,
 
 	return sprintf(buf, "%d\n", bond->params.downdelay * bond->params.miimon);
 }
-
-static ssize_t bonding_store_downdelay(struct device *d,
-				       struct device_attribute *attr,
-				       const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_DOWNDELAY, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(downdelay, S_IRUGO | S_IWUSR,
-		   bonding_show_downdelay, bonding_store_downdelay);
+		   bonding_show_downdelay, bonding_sysfs_store_option);
 
 static ssize_t bonding_show_updelay(struct device *d,
 				    struct device_attribute *attr,
@@ -479,27 +338,10 @@ static ssize_t bonding_show_updelay(struct device *d,
 	return sprintf(buf, "%d\n", bond->params.updelay * bond->params.miimon);
 
 }
-
-static ssize_t bonding_store_updelay(struct device *d,
-				     struct device_attribute *attr,
-				     const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_UPDELAY, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(updelay, S_IRUGO | S_IWUSR,
-		   bonding_show_updelay, bonding_store_updelay);
+		   bonding_show_updelay, bonding_sysfs_store_option);
 
-/*
- * Show and set the LACP interval.  Interface must be down, and the mode
- * must be set to 802.3ad mode.
- */
+/* Show the LACP interval. */
 static ssize_t bonding_show_lacp(struct device *d,
 				 struct device_attribute *attr,
 				 char *buf)
@@ -511,22 +353,8 @@ static ssize_t bonding_show_lacp(struct device *d,
 
 	return sprintf(buf, "%s %d\n", val->string, bond->params.lacp_fast);
 }
-
-static ssize_t bonding_store_lacp(struct device *d,
-				  struct device_attribute *attr,
-				  const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_LACP_RATE, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR,
-		   bonding_show_lacp, bonding_store_lacp);
+		   bonding_show_lacp, bonding_sysfs_store_option);
 
 static ssize_t bonding_show_min_links(struct device *d,
 				      struct device_attribute *attr,
@@ -536,22 +364,8 @@ static ssize_t bonding_show_min_links(struct device *d,
 
 	return sprintf(buf, "%u\n", bond->params.min_links);
 }
-
-static ssize_t bonding_store_min_links(struct device *d,
-				       struct device_attribute *attr,
-				       const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_MINLINKS, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(min_links, S_IRUGO | S_IWUSR,
-		   bonding_show_min_links, bonding_store_min_links);
+		   bonding_show_min_links, bonding_sysfs_store_option);
 
 static ssize_t bonding_show_ad_select(struct device *d,
 				      struct device_attribute *attr,
@@ -564,27 +378,10 @@ static ssize_t bonding_show_ad_select(struct device *d,
 
 	return sprintf(buf, "%s %d\n", val->string, bond->params.ad_select);
 }
-
-
-static ssize_t bonding_store_ad_select(struct device *d,
-				       struct device_attribute *attr,
-				       const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_AD_SELECT, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR,
-		   bonding_show_ad_select, bonding_store_ad_select);
+		   bonding_show_ad_select, bonding_sysfs_store_option);
 
-/*
- * Show and set the number of peer notifications to send after a failover event.
- */
+/* Show and set the number of peer notifications to send after a failover event. */
 static ssize_t bonding_show_num_peer_notif(struct device *d,
 					   struct device_attribute *attr,
 					   char *buf)
@@ -611,12 +408,7 @@ static DEVICE_ATTR(num_grat_arp, S_IRUGO | S_IWUSR,
 static DEVICE_ATTR(num_unsol_na, S_IRUGO | S_IWUSR,
 		   bonding_show_num_peer_notif, bonding_store_num_peer_notif);
 
-/*
- * Show and set the MII monitor interval.  There are two tricky bits
- * here.  First, if MII monitoring is activated, then we must disable
- * ARP monitoring.  Second, if the timer isn't running, we must
- * start it.
- */
+/* Show the MII monitor interval. */
 static ssize_t bonding_show_miimon(struct device *d,
 				   struct device_attribute *attr,
 				   char *buf)
@@ -625,30 +417,10 @@ static ssize_t bonding_show_miimon(struct device *d,
 
 	return sprintf(buf, "%d\n", bond->params.miimon);
 }
-
-static ssize_t bonding_store_miimon(struct device *d,
-				    struct device_attribute *attr,
-				    const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_MIIMON, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(miimon, S_IRUGO | S_IWUSR,
-		   bonding_show_miimon, bonding_store_miimon);
+		   bonding_show_miimon, bonding_sysfs_store_option);
 
-/*
- * Show and set the primary slave.  The store function is much
- * simpler than bonding_store_slaves function because it only needs to
- * handle one interface name.
- * The bond must be a mode that supports a primary for this be
- * set.
- */
+/* Show the primary slave. */
 static ssize_t bonding_show_primary(struct device *d,
 				    struct device_attribute *attr,
 				    char *buf)
@@ -661,26 +433,10 @@ static ssize_t bonding_show_primary(struct device *d,
 
 	return count;
 }
-
-static ssize_t bonding_store_primary(struct device *d,
-				     struct device_attribute *attr,
-				     const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_PRIMARY, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(primary, S_IRUGO | S_IWUSR,
-		   bonding_show_primary, bonding_store_primary);
+		   bonding_show_primary, bonding_sysfs_store_option);
 
-/*
- * Show and set the primary_reselect flag.
- */
+/* Show the primary_reselect flag. */
 static ssize_t bonding_show_primary_reselect(struct device *d,
 					     struct device_attribute *attr,
 					     char *buf)
@@ -694,28 +450,10 @@ static ssize_t bonding_show_primary_reselect(struct device *d,
 	return sprintf(buf, "%s %d\n",
 		       val->string, bond->params.primary_reselect);
 }
-
-static ssize_t bonding_store_primary_reselect(struct device *d,
-					      struct device_attribute *attr,
-					      const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_PRIMARY_RESELECT,
-				   (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(primary_reselect, S_IRUGO | S_IWUSR,
-		   bonding_show_primary_reselect,
-		   bonding_store_primary_reselect);
+		   bonding_show_primary_reselect, bonding_sysfs_store_option);
 
-/*
- * Show and set the use_carrier flag.
- */
+/* Show the use_carrier flag. */
 static ssize_t bonding_show_carrier(struct device *d,
 				    struct device_attribute *attr,
 				    char *buf)
@@ -724,27 +462,11 @@ static ssize_t bonding_show_carrier(struct device *d,
 
 	return sprintf(buf, "%d\n", bond->params.use_carrier);
 }
-
-static ssize_t bonding_store_carrier(struct device *d,
-				     struct device_attribute *attr,
-				     const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_USE_CARRIER, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(use_carrier, S_IRUGO | S_IWUSR,
-		   bonding_show_carrier, bonding_store_carrier);
+		   bonding_show_carrier, bonding_sysfs_store_option);
 
 
-/*
- * Show and set currently active_slave.
- */
+/* Show currently active_slave. */
 static ssize_t bonding_show_active_slave(struct device *d,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -761,27 +483,10 @@ static ssize_t bonding_show_active_slave(struct device *d,
 
 	return count;
 }
-
-static ssize_t bonding_store_active_slave(struct device *d,
-					  struct device_attribute *attr,
-					  const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_ACTIVE_SLAVE, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(active_slave, S_IRUGO | S_IWUSR,
-		   bonding_show_active_slave, bonding_store_active_slave);
-
+		   bonding_show_active_slave, bonding_sysfs_store_option);
 
-/*
- * Show link status of the bond interface.
- */
+/* Show link status of the bond interface. */
 static ssize_t bonding_show_mii_status(struct device *d,
 				       struct device_attribute *attr,
 				       char *buf)
@@ -792,9 +497,7 @@ static ssize_t bonding_show_mii_status(struct device *d,
 }
 static DEVICE_ATTR(mii_status, S_IRUGO, bonding_show_mii_status, NULL);
 
-/*
- * Show current 802.3ad aggregator ID.
- */
+/* Show current 802.3ad aggregator ID. */
 static ssize_t bonding_show_ad_aggregator(struct device *d,
 					  struct device_attribute *attr,
 					  char *buf)
@@ -802,7 +505,7 @@ static ssize_t bonding_show_ad_aggregator(struct device *d,
 	int count = 0;
 	struct bonding *bond = to_bond(d);
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info ad_info;
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
@@ -814,9 +517,7 @@ static ssize_t bonding_show_ad_aggregator(struct device *d,
 static DEVICE_ATTR(ad_aggregator, S_IRUGO, bonding_show_ad_aggregator, NULL);
 
 
-/*
- * Show number of active 802.3ad ports.
- */
+/* Show number of active 802.3ad ports. */
 static ssize_t bonding_show_ad_num_ports(struct device *d,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -824,7 +525,7 @@ static ssize_t bonding_show_ad_num_ports(struct device *d,
 	int count = 0;
 	struct bonding *bond = to_bond(d);
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info ad_info;
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
@@ -836,9 +537,7 @@ static ssize_t bonding_show_ad_num_ports(struct device *d,
 static DEVICE_ATTR(ad_num_ports, S_IRUGO, bonding_show_ad_num_ports, NULL);
 
 
-/*
- * Show current 802.3ad actor key.
- */
+/* Show current 802.3ad actor key. */
 static ssize_t bonding_show_ad_actor_key(struct device *d,
 					 struct device_attribute *attr,
 					 char *buf)
@@ -846,7 +545,7 @@ static ssize_t bonding_show_ad_actor_key(struct device *d,
 	int count = 0;
 	struct bonding *bond = to_bond(d);
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info ad_info;
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
@@ -858,9 +557,7 @@ static ssize_t bonding_show_ad_actor_key(struct device *d,
 static DEVICE_ATTR(ad_actor_key, S_IRUGO, bonding_show_ad_actor_key, NULL);
 
 
-/*
- * Show current 802.3ad partner key.
- */
+/* Show current 802.3ad partner key. */
 static ssize_t bonding_show_ad_partner_key(struct device *d,
 					   struct device_attribute *attr,
 					   char *buf)
@@ -868,7 +565,7 @@ static ssize_t bonding_show_ad_partner_key(struct device *d,
 	int count = 0;
 	struct bonding *bond = to_bond(d);
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info ad_info;
 		count = sprintf(buf, "%d\n",
 				bond_3ad_get_active_agg_info(bond, &ad_info)
@@ -880,9 +577,7 @@ static ssize_t bonding_show_ad_partner_key(struct device *d,
 static DEVICE_ATTR(ad_partner_key, S_IRUGO, bonding_show_ad_partner_key, NULL);
 
 
-/*
- * Show current 802.3ad partner mac.
- */
+/* Show current 802.3ad partner mac. */
 static ssize_t bonding_show_ad_partner_mac(struct device *d,
 					   struct device_attribute *attr,
 					   char *buf)
@@ -890,7 +585,7 @@ static ssize_t bonding_show_ad_partner_mac(struct device *d,
 	int count = 0;
 	struct bonding *bond = to_bond(d);
 
-	if (bond->params.mode == BOND_MODE_8023AD) {
+	if (BOND_MODE(bond) == BOND_MODE_8023AD) {
 		struct ad_info ad_info;
 		if (!bond_3ad_get_active_agg_info(bond, &ad_info))
 			count = sprintf(buf, "%pM\n", ad_info.partner_system);
@@ -900,9 +595,7 @@ static ssize_t bonding_show_ad_partner_mac(struct device *d,
 }
 static DEVICE_ATTR(ad_partner_mac, S_IRUGO, bonding_show_ad_partner_mac, NULL);
 
-/*
- * Show the queue_ids of the slaves in the current bond.
- */
+/* Show the queue_ids of the slaves in the current bond. */
 static ssize_t bonding_show_queue_id(struct device *d,
 				     struct device_attribute *attr,
 				     char *buf)
@@ -933,31 +626,11 @@ static ssize_t bonding_show_queue_id(struct device *d,
 
 	return res;
 }
-
-/*
- * Set the queue_ids of the  slaves in the current bond.  The bond
- * interface must be enslaved for this to work.
- */
-static ssize_t bonding_store_queue_id(struct device *d,
-				      struct device_attribute *attr,
-				      const char *buffer, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_QUEUE_ID, (char *)buffer);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(queue_id, S_IRUGO | S_IWUSR, bonding_show_queue_id,
-		   bonding_store_queue_id);
+		   bonding_sysfs_store_option);
 
 
-/*
- * Show and set the all_slaves_active flag.
- */
+/* Show the all_slaves_active flag. */
 static ssize_t bonding_show_slaves_active(struct device *d,
 					  struct device_attribute *attr,
 					  char *buf)
@@ -966,27 +639,10 @@ static ssize_t bonding_show_slaves_active(struct device *d,
 
 	return sprintf(buf, "%d\n", bond->params.all_slaves_active);
 }
-
-static ssize_t bonding_store_slaves_active(struct device *d,
-					   struct device_attribute *attr,
-					   const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_ALL_SLAVES_ACTIVE,
-				   (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
 static DEVICE_ATTR(all_slaves_active, S_IRUGO | S_IWUSR,
-		   bonding_show_slaves_active, bonding_store_slaves_active);
+		   bonding_show_slaves_active, bonding_sysfs_store_option);
 
-/*
- * Show and set the number of IGMP membership reports to send on link failure
- */
+/* Show the number of IGMP membership reports to send on link failure */
 static ssize_t bonding_show_resend_igmp(struct device *d,
 					struct device_attribute *attr,
 					char *buf)
@@ -995,23 +651,8 @@ static ssize_t bonding_show_resend_igmp(struct device *d,
 
 	return sprintf(buf, "%d\n", bond->params.resend_igmp);
 }
-
-static ssize_t bonding_store_resend_igmp(struct device *d,
-					 struct device_attribute *attr,
-					 const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_RESEND_IGMP, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
-}
-
 static DEVICE_ATTR(resend_igmp, S_IRUGO | S_IWUSR,
-		   bonding_show_resend_igmp, bonding_store_resend_igmp);
+		   bonding_show_resend_igmp, bonding_sysfs_store_option);
 
 
 static ssize_t bonding_show_lp_interval(struct device *d,
@@ -1019,25 +660,21 @@ static ssize_t bonding_show_lp_interval(struct device *d,
 					char *buf)
 {
 	struct bonding *bond = to_bond(d);
+
 	return sprintf(buf, "%d\n", bond->params.lp_interval);
 }
+static DEVICE_ATTR(lp_interval, S_IRUGO | S_IWUSR,
+		   bonding_show_lp_interval, bonding_sysfs_store_option);
 
-static ssize_t bonding_store_lp_interval(struct device *d,
-					 struct device_attribute *attr,
-					 const char *buf, size_t count)
+static ssize_t bonding_show_tlb_dynamic_lb(struct device *d,
+					   struct device_attribute *attr,
+					   char *buf)
 {
 	struct bonding *bond = to_bond(d);
-	int ret;
-
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_LP_INTERVAL, (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
+	return sprintf(buf, "%d\n", bond->params.tlb_dynamic_lb);
 }
-
-static DEVICE_ATTR(lp_interval, S_IRUGO | S_IWUSR,
-		   bonding_show_lp_interval, bonding_store_lp_interval);
+static DEVICE_ATTR(tlb_dynamic_lb, S_IRUGO | S_IWUSR,
+		   bonding_show_tlb_dynamic_lb, bonding_sysfs_store_option);
 
 static ssize_t bonding_show_packets_per_slave(struct device *d,
 					      struct device_attribute *attr,
@@ -1045,27 +682,11 @@ static ssize_t bonding_show_packets_per_slave(struct device *d,
 {
 	struct bonding *bond = to_bond(d);
 	unsigned int packets_per_slave = bond->params.packets_per_slave;
-	return sprintf(buf, "%u\n", packets_per_slave);
-}
-
-static ssize_t bonding_store_packets_per_slave(struct device *d,
-					       struct device_attribute *attr,
-					       const char *buf, size_t count)
-{
-	struct bonding *bond = to_bond(d);
-	int ret;
 
-	ret = bond_opt_tryset_rtnl(bond, BOND_OPT_PACKETS_PER_SLAVE,
-				   (char *)buf);
-	if (!ret)
-		ret = count;
-
-	return ret;
+	return sprintf(buf, "%u\n", packets_per_slave);
 }
-
 static DEVICE_ATTR(packets_per_slave, S_IRUGO | S_IWUSR,
-		   bonding_show_packets_per_slave,
-		   bonding_store_packets_per_slave);
+		   bonding_show_packets_per_slave, bonding_sysfs_store_option);
 
 static struct attribute *per_bond_attrs[] = {
 	&dev_attr_slaves.attr,
@@ -1099,6 +720,7 @@ static struct attribute *per_bond_attrs[] = {
 	&dev_attr_min_links.attr,
 	&dev_attr_lp_interval.attr,
 	&dev_attr_packets_per_slave.attr,
+	&dev_attr_tlb_dynamic_lb.attr,
 	NULL,
 };
 
@@ -1107,8 +729,7 @@ static struct attribute_group bonding_group = {
 	.attrs = per_bond_attrs,
 };
 
-/*
- * Initialize sysfs.  This sets up the bonding_masters file in
+/* Initialize sysfs.  This sets up the bonding_masters file in
  * /sys/class/net.
  */
 int bond_create_sysfs(struct bond_net *bn)
@@ -1120,8 +741,7 @@ int bond_create_sysfs(struct bond_net *bn)
 
 	ret = netdev_class_create_file_ns(&bn->class_attr_bonding_masters,
 					  bn->net);
-	/*
-	 * Permit multiple loads of the module by ignoring failures to
+	/* Permit multiple loads of the module by ignoring failures to
 	 * create the bonding_masters sysfs file.  Bonding devices
 	 * created by second or subsequent loads of the module will
 	 * not be listed in, or controllable by, bonding_masters, but
@@ -1144,16 +764,13 @@ int bond_create_sysfs(struct bond_net *bn)
 
 }
 
-/*
- * Remove /sys/class/net/bonding_masters.
- */
+/* Remove /sys/class/net/bonding_masters. */
 void bond_destroy_sysfs(struct bond_net *bn)
 {
 	netdev_class_remove_file_ns(&bn->class_attr_bonding_masters, bn->net);
 }
 
-/*
- * Initialize sysfs for each bond.  This sets up and registers
+/* Initialize sysfs for each bond.  This sets up and registers
  * the 'bondctl' directory for each individual bond under /sys/class/net.
  */
 void bond_prepare_sysfs_group(struct bonding *bond)
diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c
index 2e4eec5450c..198677f58ce 100644
--- a/drivers/net/bonding/bond_sysfs_slave.c
+++ b/drivers/net/bonding/bond_sysfs_slave.c
@@ -69,8 +69,8 @@ static ssize_t ad_aggregator_id_show(struct slave *slave, char *buf)
 {
 	const struct aggregator *agg;
 
-	if (slave->bond->params.mode == BOND_MODE_8023AD) {
-		agg = SLAVE_AD_INFO(slave).port.aggregator;
+	if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) {
+		agg = SLAVE_AD_INFO(slave)->port.aggregator;
 		if (agg)
 			return sprintf(buf, "%d\n",
 				       agg->aggregator_identifier);
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index 00bea320e3b..0b4d9cde0b0 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -41,42 +41,6 @@
 
 #define BOND_DEFAULT_MIIMON	100
 
-#define IS_UP(dev)					   \
-	      ((((dev)->flags & IFF_UP) == IFF_UP)	&& \
-	       netif_running(dev)			&& \
-	       netif_carrier_ok(dev))
-
-/*
- * Checks whether slave is ready for transmit.
- */
-#define SLAVE_IS_OK(slave)			        \
-		    (((slave)->dev->flags & IFF_UP)  && \
-		     netif_running((slave)->dev)     && \
-		     ((slave)->link == BOND_LINK_UP) && \
-		     bond_is_active_slave(slave))
-
-
-#define USES_PRIMARY(mode)				\
-		(((mode) == BOND_MODE_ACTIVEBACKUP) ||	\
-		 ((mode) == BOND_MODE_TLB)          ||	\
-		 ((mode) == BOND_MODE_ALB))
-
-#define BOND_NO_USES_ARP(mode)				\
-		(((mode) == BOND_MODE_8023AD)	||	\
-		 ((mode) == BOND_MODE_TLB)	||	\
-		 ((mode) == BOND_MODE_ALB))
-
-#define TX_QUEUE_OVERRIDE(mode)				\
-			(((mode) == BOND_MODE_ACTIVEBACKUP) ||	\
-			 ((mode) == BOND_MODE_ROUNDROBIN))
-
-#define BOND_MODE_IS_LB(mode)			\
-		(((mode) == BOND_MODE_TLB) ||	\
-		 ((mode) == BOND_MODE_ALB))
-
-#define IS_IP_TARGET_UNUSABLE_ADDRESS(a)	\
-	((htonl(INADDR_BROADCAST) == a) ||	\
-	 ipv4_is_zeronet(a))
 /*
  * Less bad way to call ioctl from within the kernel; this needs to be
  * done some other way to get the call out of interrupt context.
@@ -90,6 +54,8 @@
 	set_fs(fs);			\
 	res; })
 
+#define BOND_MODE(bond) ((bond)->params.mode)
+
 /* slave list primitives */
 #define bond_slave_list(bond) (&(bond)->dev->adj_list.lower)
 
@@ -175,6 +141,7 @@ struct bond_params {
 	int resend_igmp;
 	int lp_interval;
 	int packets_per_slave;
+	int tlb_dynamic_lb;
 	struct reciprocal_value reciprocal_packets_per_slave;
 };
 
@@ -183,8 +150,6 @@ struct bond_parm_tbl {
 	int mode;
 };
 
-#define BOND_MAX_MODENAME_LEN 20
-
 struct slave {
 	struct net_device *dev; /* first - useful for panic debug */
 	struct bonding *bond; /* our master */
@@ -205,7 +170,7 @@ struct slave {
 	u32    speed;
 	u16    queue_id;
 	u8     perm_hwaddr[ETH_ALEN];
-	struct ad_slave_info ad_info; /* HUGE - better to dynamically alloc */
+	struct ad_slave_info *ad_info;
 	struct tlb_slave_info tlb_info;
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll *np;
@@ -285,14 +250,41 @@ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond,
 
 static inline struct bonding *bond_get_bond_by_slave(struct slave *slave)
 {
-	if (!slave || !slave->bond)
-		return NULL;
 	return slave->bond;
 }
 
+static inline bool bond_should_override_tx_queue(struct bonding *bond)
+{
+	return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
+	       BOND_MODE(bond) == BOND_MODE_ROUNDROBIN;
+}
+
 static inline bool bond_is_lb(const struct bonding *bond)
 {
-	return BOND_MODE_IS_LB(bond->params.mode);
+	return BOND_MODE(bond) == BOND_MODE_TLB ||
+	       BOND_MODE(bond) == BOND_MODE_ALB;
+}
+
+static inline bool bond_mode_uses_arp(int mode)
+{
+	return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB &&
+	       mode != BOND_MODE_ALB;
+}
+
+static inline bool bond_mode_uses_primary(int mode)
+{
+	return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB ||
+	       mode == BOND_MODE_ALB;
+}
+
+static inline bool bond_uses_primary(struct bonding *bond)
+{
+	return bond_mode_uses_primary(BOND_MODE(bond));
+}
+
+static inline bool bond_slave_is_up(struct slave *slave)
+{
+	return netif_running(slave->dev) && netif_carrier_ok(slave->dev);
 }
 
 static inline void bond_set_active_slave(struct slave *slave)
@@ -365,6 +357,12 @@ static inline bool bond_is_active_slave(struct slave *slave)
 	return !bond_slave_state(slave);
 }
 
+static inline bool bond_slave_can_tx(struct slave *slave)
+{
+	return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP &&
+	       bond_is_active_slave(slave);
+}
+
 #define BOND_PRI_RESELECT_ALWAYS	0
 #define BOND_PRI_RESELECT_BETTER	1
 #define BOND_PRI_RESELECT_FAILURE	2
@@ -396,12 +394,16 @@ static inline int slave_do_arp_validate(struct bonding *bond,
 	return bond->params.arp_validate & (1 << bond_slave_state(slave));
 }
 
-static inline int slave_do_arp_validate_only(struct bonding *bond,
-					     struct slave *slave)
+static inline int slave_do_arp_validate_only(struct bonding *bond)
 {
 	return bond->params.arp_validate & BOND_ARP_FILTER;
 }
 
+static inline int bond_is_ip_target_ok(__be32 addr)
+{
+	return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr);
+}
+
 /* Get the oldest arp which we've received on this slave for bond's
  * arp_targets.
  */
@@ -479,16 +481,14 @@ static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be3
 	return addr;
 }
 
-static inline bool slave_can_tx(struct slave *slave)
-{
-	if (IS_UP(slave->dev) && slave->link == BOND_LINK_UP &&
-	    bond_is_active_slave(slave))
-		return true;
-	else
-		return false;
-}
-
-struct bond_net;
+struct bond_net {
+	struct net		*net;	/* Associated network namespace */
+	struct list_head	dev_list;
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry	*proc_dir;
+#endif
+	struct class_attribute	class_attr_bonding_masters;
+};
 
 int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave);
 void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev);
@@ -500,7 +500,7 @@ int bond_sysfs_slave_add(struct slave *slave);
 void bond_sysfs_slave_del(struct slave *slave);
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev);
 int bond_release(struct net_device *bond_dev, struct net_device *slave_dev);
-int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count);
+u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb);
 void bond_select_active_slave(struct bonding *bond);
 void bond_change_active_slave(struct bonding *bond, struct slave *new_active);
 void bond_create_debugfs(void);
@@ -516,15 +516,9 @@ void bond_netlink_fini(void);
 struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond);
 struct net_device *bond_option_active_slave_get(struct bonding *bond);
 const char *bond_slave_link_status(s8 link);
-
-struct bond_net {
-	struct net *		net;	/* Associated network namespace */
-	struct list_head	dev_list;
-#ifdef CONFIG_PROC_FS
-	struct proc_dir_entry *	proc_dir;
-#endif
-	struct class_attribute	class_attr_bonding_masters;
-};
+bool bond_verify_device_path(struct net_device *start_dev,
+			     struct net_device *end_dev,
+			     struct bond_vlan_tag *tags);
 
 #ifdef CONFIG_PROC_FS
 void bond_create_proc_entry(struct bonding *bond);
@@ -576,6 +570,27 @@ static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond,
 	return NULL;
 }
 
+/* Caller must hold rcu_read_lock() for read */
+static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+	struct netdev_hw_addr *ha;
+
+	bond_for_each_slave_rcu(bond, tmp, iter)
+		if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
+			return true;
+
+	if (netdev_uc_empty(bond->dev))
+		return false;
+
+	netdev_for_each_uc_addr(ha, bond->dev)
+		if (ether_addr_equal_64bits(mac, ha->addr))
+			return true;
+
+	return false;
+}
+
 /* Check if the ip is present in arp ip list, or first free slot if ip == 0
  * Returns -1 if not found, index if found
  */
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 9e7d95dae2c..41688229c57 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -65,7 +65,7 @@ config CAN_LEDS
 
 config CAN_AT91
 	tristate "Atmel AT91 onchip CAN controller"
-	depends on ARM
+	depends on ARCH_AT91 || COMPILE_TEST
 	---help---
 	  This is a driver for the SoC CAN controller in Atmel's AT91SAM9263
 	  and AT91SAM9X5 processors.
@@ -77,12 +77,6 @@ config CAN_TI_HECC
 	  Driver for TI HECC (High End CAN Controller) module found on many
 	  TI devices. The device specifications are available from www.ti.com
 
-config CAN_MCP251X
-	tristate "Microchip MCP251x SPI CAN controllers"
-	depends on SPI && HAS_DMA
-	---help---
-	  Driver for the Microchip MCP251x SPI CAN controllers.
-
 config CAN_BFIN
 	depends on BF534 || BF536 || BF537 || BF538 || BF539 || BF54x
 	tristate "Analog Devices Blackfin on-chip CAN"
@@ -110,7 +104,7 @@ config CAN_FLEXCAN
 
 config PCH_CAN
 	tristate "Intel EG20T PCH CAN controller"
-	depends on PCI
+	depends on PCI && (X86_32 || COMPILE_TEST)
 	---help---
 	  This driver is for PCH CAN of Topcliff (Intel EG20T PCH) which
 	  is an IOH for x86 embedded processor (Intel Atom E6xx series).
@@ -125,6 +119,24 @@ config CAN_GRCAN
 	  endian syntheses of the cores would need some modifications on
 	  the hardware level to work.
 
+config CAN_RCAR
+	tristate "Renesas R-Car CAN controller"
+	depends on ARM
+	---help---
+	  Say Y here if you want to use CAN controller found on Renesas R-Car
+	  SoCs.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called rcar_can.
+
+config CAN_XILINXCAN
+	tristate "Xilinx CAN"
+	depends on ARCH_ZYNQ || MICROBLAZE || COMPILE_TEST
+	depends on COMMON_CLK && HAS_IOMEM
+	---help---
+	  Xilinx CAN driver. This driver supports both soft AXI CAN IP and
+	  Zynq CANPS IP.
+
 source "drivers/net/can/mscan/Kconfig"
 
 source "drivers/net/can/sja1000/Kconfig"
@@ -133,6 +145,8 @@ source "drivers/net/can/c_can/Kconfig"
 
 source "drivers/net/can/cc770/Kconfig"
 
+source "drivers/net/can/spi/Kconfig"
+
 source "drivers/net/can/usb/Kconfig"
 
 source "drivers/net/can/softing/Kconfig"
diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile
index c7440392adb..1697f22353a 100644
--- a/drivers/net/can/Makefile
+++ b/drivers/net/can/Makefile
@@ -10,6 +10,7 @@ can-dev-y			:= dev.o
 
 can-dev-$(CONFIG_CAN_LEDS)	+= led.o
 
+obj-y				+= spi/
 obj-y				+= usb/
 obj-y				+= softing/
 
@@ -19,11 +20,12 @@ obj-$(CONFIG_CAN_C_CAN)		+= c_can/
 obj-$(CONFIG_CAN_CC770)		+= cc770/
 obj-$(CONFIG_CAN_AT91)		+= at91_can.o
 obj-$(CONFIG_CAN_TI_HECC)	+= ti_hecc.o
-obj-$(CONFIG_CAN_MCP251X)	+= mcp251x.o
 obj-$(CONFIG_CAN_BFIN)		+= bfin_can.o
 obj-$(CONFIG_CAN_JANZ_ICAN3)	+= janz-ican3.o
 obj-$(CONFIG_CAN_FLEXCAN)	+= flexcan.o
 obj-$(CONFIG_PCH_CAN)		+= pch_can.o
 obj-$(CONFIG_CAN_GRCAN)		+= grcan.o
+obj-$(CONFIG_CAN_RCAR)		+= rcar_can.o
+obj-$(CONFIG_CAN_XILINXCAN)	+= xilinx_can.o
 
 ccflags-$(CONFIG_CAN_DEBUG_DEVICES) := -DDEBUG
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 95e04e2002d..8e78bb48f5a 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -252,8 +252,7 @@ static void c_can_obj_update(struct net_device *dev, int iface, u32 cmd, u32 obj
 	struct c_can_priv *priv = netdev_priv(dev);
 	int cnt, reg = C_CAN_IFACE(COMREQ_REG, iface);
 
-	priv->write_reg(priv, reg + 1, cmd);
-	priv->write_reg(priv, reg, obj);
+	priv->write_reg32(priv, reg, (cmd << 16) | obj);
 
 	for (cnt = MIN_TIMEOUT_VALUE; cnt; cnt--) {
 		if (!(priv->read_reg(priv, reg) & IF_COMR_BUSY))
@@ -328,8 +327,7 @@ static void c_can_setup_tx_object(struct net_device *dev, int iface,
 		change_bit(idx, &priv->tx_dir);
 	}
 
-	priv->write_reg(priv, C_CAN_IFACE(ARB1_REG, iface), arb);
-	priv->write_reg(priv, C_CAN_IFACE(ARB2_REG, iface), arb >> 16);
+	priv->write_reg32(priv, C_CAN_IFACE(ARB1_REG, iface), arb);
 
 	priv->write_reg(priv, C_CAN_IFACE(MSGCTRL_REG, iface), ctrl);
 
@@ -391,8 +389,7 @@ static int c_can_read_msg_object(struct net_device *dev, int iface, u32 ctrl)
 
 	frame->can_dlc = get_can_dlc(ctrl & 0x0F);
 
-	arb = priv->read_reg(priv, C_CAN_IFACE(ARB1_REG, iface));
-	arb |= priv->read_reg(priv, C_CAN_IFACE(ARB2_REG, iface)) << 16;
+	arb = priv->read_reg32(priv, C_CAN_IFACE(ARB1_REG, iface));
 
 	if (arb & IF_ARB_MSGXTD)
 		frame->can_id = (arb & CAN_EFF_MASK) | CAN_EFF_FLAG;
@@ -424,12 +421,10 @@ static void c_can_setup_receive_object(struct net_device *dev, int iface,
 	struct c_can_priv *priv = netdev_priv(dev);
 
 	mask |= BIT(29);
-	priv->write_reg(priv, C_CAN_IFACE(MASK1_REG, iface), mask);
-	priv->write_reg(priv, C_CAN_IFACE(MASK2_REG, iface), mask >> 16);
+	priv->write_reg32(priv, C_CAN_IFACE(MASK1_REG, iface), mask);
 
 	id |= IF_ARB_MSGVAL;
-	priv->write_reg(priv, C_CAN_IFACE(ARB1_REG, iface), id);
-	priv->write_reg(priv, C_CAN_IFACE(ARB2_REG, iface), id >> 16);
+	priv->write_reg32(priv, C_CAN_IFACE(ARB1_REG, iface), id);
 
 	priv->write_reg(priv, C_CAN_IFACE(MSGCTRL_REG, iface), mcont);
 	c_can_object_put(dev, iface, obj, IF_COMM_RCV_SETUP);
diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h
index c56f1b1c11c..99ad1aa576b 100644
--- a/drivers/net/can/c_can/c_can.h
+++ b/drivers/net/can/c_can/c_can.h
@@ -78,6 +78,7 @@ enum reg {
 	C_CAN_INTPND2_REG,
 	C_CAN_MSGVAL1_REG,
 	C_CAN_MSGVAL2_REG,
+	C_CAN_FUNCTION_REG,
 };
 
 static const u16 reg_map_c_can[] = {
@@ -129,6 +130,7 @@ static const u16 reg_map_d_can[] = {
 	[C_CAN_BRPEXT_REG]	= 0x0E,
 	[C_CAN_INT_REG]		= 0x10,
 	[C_CAN_TEST_REG]	= 0x14,
+	[C_CAN_FUNCTION_REG]	= 0x18,
 	[C_CAN_TXRQST1_REG]	= 0x88,
 	[C_CAN_TXRQST2_REG]	= 0x8A,
 	[C_CAN_NEWDAT1_REG]	= 0x9C,
@@ -176,8 +178,10 @@ struct c_can_priv {
 	atomic_t tx_active;
 	unsigned long tx_dir;
 	int last_status;
-	u16 (*read_reg) (struct c_can_priv *priv, enum reg index);
-	void (*write_reg) (struct c_can_priv *priv, enum reg index, u16 val);
+	u16 (*read_reg) (const struct c_can_priv *priv, enum reg index);
+	void (*write_reg) (const struct c_can_priv *priv, enum reg index, u16 val);
+	u32 (*read_reg32) (const struct c_can_priv *priv, enum reg index);
+	void (*write_reg32) (const struct c_can_priv *priv, enum reg index, u32 val);
 	void __iomem *base;
 	const u16 *regs;
 	void *priv;		/* for board-specific data */
diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c
index fe5f6303b58..5d11e0e4225 100644
--- a/drivers/net/can/c_can/c_can_pci.c
+++ b/drivers/net/can/c_can/c_can_pci.c
@@ -19,9 +19,13 @@
 
 #include "c_can.h"
 
+#define PCI_DEVICE_ID_PCH_CAN	0x8818
+#define PCH_PCI_SOFT_RESET	0x01fc
+
 enum c_can_pci_reg_align {
 	C_CAN_REG_ALIGN_16,
 	C_CAN_REG_ALIGN_32,
+	C_CAN_REG_32,
 };
 
 struct c_can_pci_data {
@@ -31,6 +35,10 @@ struct c_can_pci_data {
 	enum c_can_pci_reg_align reg_align;
 	/* Set the frequency */
 	unsigned int freq;
+	/* PCI bar number */
+	int bar;
+	/* Callback for reset */
+	void (*init)(const struct c_can_priv *priv, bool enable);
 };
 
 /*
@@ -39,30 +47,70 @@ struct c_can_pci_data {
  * registers can be aligned to a 16-bit boundary or 32-bit boundary etc.
  * Handle the same by providing a common read/write interface.
  */
-static u16 c_can_pci_read_reg_aligned_to_16bit(struct c_can_priv *priv,
+static u16 c_can_pci_read_reg_aligned_to_16bit(const struct c_can_priv *priv,
 						enum reg index)
 {
 	return readw(priv->base + priv->regs[index]);
 }
 
-static void c_can_pci_write_reg_aligned_to_16bit(struct c_can_priv *priv,
+static void c_can_pci_write_reg_aligned_to_16bit(const struct c_can_priv *priv,
 						enum reg index, u16 val)
 {
 	writew(val, priv->base + priv->regs[index]);
 }
 
-static u16 c_can_pci_read_reg_aligned_to_32bit(struct c_can_priv *priv,
+static u16 c_can_pci_read_reg_aligned_to_32bit(const struct c_can_priv *priv,
 						enum reg index)
 {
 	return readw(priv->base + 2 * priv->regs[index]);
 }
 
-static void c_can_pci_write_reg_aligned_to_32bit(struct c_can_priv *priv,
+static void c_can_pci_write_reg_aligned_to_32bit(const struct c_can_priv *priv,
 						enum reg index, u16 val)
 {
 	writew(val, priv->base + 2 * priv->regs[index]);
 }
 
+static u16 c_can_pci_read_reg_32bit(const struct c_can_priv *priv,
+				    enum reg index)
+{
+	return (u16)ioread32(priv->base + 2 * priv->regs[index]);
+}
+
+static void c_can_pci_write_reg_32bit(const struct c_can_priv *priv,
+				      enum reg index, u16 val)
+{
+	iowrite32((u32)val, priv->base + 2 * priv->regs[index]);
+}
+
+static u32 c_can_pci_read_reg32(const struct c_can_priv *priv, enum reg index)
+{
+	u32 val;
+
+	val = priv->read_reg(priv, index);
+	val |= ((u32) priv->read_reg(priv, index + 1)) << 16;
+
+	return val;
+}
+
+static void c_can_pci_write_reg32(const struct c_can_priv *priv, enum reg index,
+		u32 val)
+{
+	priv->write_reg(priv, index + 1, val >> 16);
+	priv->write_reg(priv, index, val);
+}
+
+static void c_can_pci_reset_pch(const struct c_can_priv *priv, bool enable)
+{
+	if (enable) {
+		u32 __iomem *addr = priv->base + PCH_PCI_SOFT_RESET;
+
+		/* write to sw reset register */
+		iowrite32(1, addr);
+		iowrite32(0, addr);
+	}
+}
+
 static int c_can_pci_probe(struct pci_dev *pdev,
 			   const struct pci_device_id *ent)
 {
@@ -90,7 +138,8 @@ static int c_can_pci_probe(struct pci_dev *pdev,
 		pci_set_master(pdev);
 	}
 
-	addr = pci_iomap(pdev, 0, pci_resource_len(pdev, 0));
+	addr = pci_iomap(pdev, c_can_pci_data->bar,
+			 pci_resource_len(pdev, c_can_pci_data->bar));
 	if (!addr) {
 		dev_err(&pdev->dev,
 			"device has no PCI memory resources, "
@@ -147,10 +196,18 @@ static int c_can_pci_probe(struct pci_dev *pdev,
 		priv->read_reg = c_can_pci_read_reg_aligned_to_16bit;
 		priv->write_reg = c_can_pci_write_reg_aligned_to_16bit;
 		break;
+	case C_CAN_REG_32:
+		priv->read_reg = c_can_pci_read_reg_32bit;
+		priv->write_reg = c_can_pci_write_reg_32bit;
+		break;
 	default:
 		ret = -EINVAL;
 		goto out_free_c_can;
 	}
+	priv->read_reg32 = c_can_pci_read_reg32;
+	priv->write_reg32 = c_can_pci_write_reg32;
+
+	priv->raminit = c_can_pci_data->init;
 
 	ret = register_c_can_dev(dev);
 	if (ret) {
@@ -198,6 +255,15 @@ static struct c_can_pci_data c_can_sta2x11= {
 	.type = BOSCH_C_CAN,
 	.reg_align = C_CAN_REG_ALIGN_32,
 	.freq = 52000000, /* 52 Mhz */
+	.bar = 0,
+};
+
+static struct c_can_pci_data c_can_pch = {
+	.type = BOSCH_C_CAN,
+	.reg_align = C_CAN_REG_32,
+	.freq = 50000000, /* 50 MHz */
+	.init = c_can_pci_reset_pch,
+	.bar = 1,
 };
 
 #define C_CAN_ID(_vend, _dev, _driverdata) {		\
@@ -207,6 +273,8 @@ static struct c_can_pci_data c_can_sta2x11= {
 static DEFINE_PCI_DEVICE_TABLE(c_can_pci_tbl) = {
 	C_CAN_ID(PCI_VENDOR_ID_STMICRO, PCI_DEVICE_ID_STMICRO_CAN,
 		 c_can_sta2x11),
+	C_CAN_ID(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PCH_CAN,
+		 c_can_pch),
 	{},
 };
 static struct pci_driver c_can_pci_driver = {
diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 1df0b322d1e..12430be6448 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -40,6 +40,7 @@
 #define CAN_RAMINIT_START_MASK(i)	(0x001 << (i))
 #define CAN_RAMINIT_DONE_MASK(i)	(0x100 << (i))
 #define CAN_RAMINIT_ALL_MASK(i)		(0x101 << (i))
+#define DCAN_RAM_INIT_BIT		(1 << 3)
 static DEFINE_SPINLOCK(raminit_lock);
 /*
  * 16-bit c_can registers can be arranged differently in the memory
@@ -47,31 +48,31 @@ static DEFINE_SPINLOCK(raminit_lock);
  * registers can be aligned to a 16-bit boundary or 32-bit boundary etc.
  * Handle the same by providing a common read/write interface.
  */
-static u16 c_can_plat_read_reg_aligned_to_16bit(struct c_can_priv *priv,
+static u16 c_can_plat_read_reg_aligned_to_16bit(const struct c_can_priv *priv,
 						enum reg index)
 {
 	return readw(priv->base + priv->regs[index]);
 }
 
-static void c_can_plat_write_reg_aligned_to_16bit(struct c_can_priv *priv,
+static void c_can_plat_write_reg_aligned_to_16bit(const struct c_can_priv *priv,
 						enum reg index, u16 val)
 {
 	writew(val, priv->base + priv->regs[index]);
 }
 
-static u16 c_can_plat_read_reg_aligned_to_32bit(struct c_can_priv *priv,
+static u16 c_can_plat_read_reg_aligned_to_32bit(const struct c_can_priv *priv,
 						enum reg index)
 {
 	return readw(priv->base + 2 * priv->regs[index]);
 }
 
-static void c_can_plat_write_reg_aligned_to_32bit(struct c_can_priv *priv,
+static void c_can_plat_write_reg_aligned_to_32bit(const struct c_can_priv *priv,
 						enum reg index, u16 val)
 {
 	writew(val, priv->base + 2 * priv->regs[index]);
 }
 
-static void c_can_hw_raminit_wait(const struct c_can_priv *priv, u32 mask,
+static void c_can_hw_raminit_wait_ti(const struct c_can_priv *priv, u32 mask,
 				  u32 val)
 {
 	/* We look only at the bits of our instance. */
@@ -80,7 +81,7 @@ static void c_can_hw_raminit_wait(const struct c_can_priv *priv, u32 mask,
 		udelay(1);
 }
 
-static void c_can_hw_raminit(const struct c_can_priv *priv, bool enable)
+static void c_can_hw_raminit_ti(const struct c_can_priv *priv, bool enable)
 {
 	u32 mask = CAN_RAMINIT_ALL_MASK(priv->instance);
 	u32 ctrl;
@@ -96,18 +97,68 @@ static void c_can_hw_raminit(const struct c_can_priv *priv, bool enable)
 	ctrl |= CAN_RAMINIT_DONE_MASK(priv->instance);
 	writel(ctrl, priv->raminit_ctrlreg);
 	ctrl &= ~CAN_RAMINIT_DONE_MASK(priv->instance);
-	c_can_hw_raminit_wait(priv, ctrl, mask);
+	c_can_hw_raminit_wait_ti(priv, ctrl, mask);
 
 	if (enable) {
 		/* Set start bit and wait for the done bit. */
 		ctrl |= CAN_RAMINIT_START_MASK(priv->instance);
 		writel(ctrl, priv->raminit_ctrlreg);
 		ctrl |= CAN_RAMINIT_DONE_MASK(priv->instance);
-		c_can_hw_raminit_wait(priv, ctrl, mask);
+		c_can_hw_raminit_wait_ti(priv, ctrl, mask);
 	}
 	spin_unlock(&raminit_lock);
 }
 
+static u32 c_can_plat_read_reg32(const struct c_can_priv *priv, enum reg index)
+{
+	u32 val;
+
+	val = priv->read_reg(priv, index);
+	val |= ((u32) priv->read_reg(priv, index + 1)) << 16;
+
+	return val;
+}
+
+static void c_can_plat_write_reg32(const struct c_can_priv *priv, enum reg index,
+		u32 val)
+{
+	priv->write_reg(priv, index + 1, val >> 16);
+	priv->write_reg(priv, index, val);
+}
+
+static u32 d_can_plat_read_reg32(const struct c_can_priv *priv, enum reg index)
+{
+	return readl(priv->base + priv->regs[index]);
+}
+
+static void d_can_plat_write_reg32(const struct c_can_priv *priv, enum reg index,
+		u32 val)
+{
+	writel(val, priv->base + priv->regs[index]);
+}
+
+static void c_can_hw_raminit_wait(const struct c_can_priv *priv, u32 mask)
+{
+	while (priv->read_reg32(priv, C_CAN_FUNCTION_REG) & mask)
+		udelay(1);
+}
+
+static void c_can_hw_raminit(const struct c_can_priv *priv, bool enable)
+{
+	u32 ctrl;
+
+	ctrl = priv->read_reg32(priv, C_CAN_FUNCTION_REG);
+	ctrl &= ~DCAN_RAM_INIT_BIT;
+	priv->write_reg32(priv, C_CAN_FUNCTION_REG, ctrl);
+	c_can_hw_raminit_wait(priv, ctrl);
+
+	if (enable) {
+		ctrl |= DCAN_RAM_INIT_BIT;
+		priv->write_reg32(priv, C_CAN_FUNCTION_REG, ctrl);
+		c_can_hw_raminit_wait(priv, ctrl);
+	}
+}
+
 static struct platform_device_id c_can_id_table[] = {
 	[BOSCH_C_CAN_PLATFORM] = {
 		.name = KBUILD_MODNAME,
@@ -201,11 +252,15 @@ static int c_can_plat_probe(struct platform_device *pdev)
 		case IORESOURCE_MEM_32BIT:
 			priv->read_reg = c_can_plat_read_reg_aligned_to_32bit;
 			priv->write_reg = c_can_plat_write_reg_aligned_to_32bit;
+			priv->read_reg32 = c_can_plat_read_reg32;
+			priv->write_reg32 = c_can_plat_write_reg32;
 			break;
 		case IORESOURCE_MEM_16BIT:
 		default:
 			priv->read_reg = c_can_plat_read_reg_aligned_to_16bit;
 			priv->write_reg = c_can_plat_write_reg_aligned_to_16bit;
+			priv->read_reg32 = c_can_plat_read_reg32;
+			priv->write_reg32 = c_can_plat_write_reg32;
 			break;
 		}
 		break;
@@ -214,6 +269,8 @@ static int c_can_plat_probe(struct platform_device *pdev)
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
 		priv->read_reg = c_can_plat_read_reg_aligned_to_16bit;
 		priv->write_reg = c_can_plat_write_reg_aligned_to_16bit;
+		priv->read_reg32 = d_can_plat_read_reg32;
+		priv->write_reg32 = d_can_plat_write_reg32;
 
 		if (pdev->dev.of_node)
 			priv->instance = of_alias_get_id(pdev->dev.of_node, "d_can");
@@ -221,11 +278,21 @@ static int c_can_plat_probe(struct platform_device *pdev)
 			priv->instance = pdev->id;
 
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-		priv->raminit_ctrlreg = devm_ioremap_resource(&pdev->dev, res);
+		/* Not all D_CAN modules have a separate register for the D_CAN
+		 * RAM initialization. Use default RAM init bit in D_CAN module
+		 * if not specified in DT.
+		 */
+		if (!res) {
+			priv->raminit = c_can_hw_raminit;
+			break;
+		}
+
+		priv->raminit_ctrlreg = devm_ioremap(&pdev->dev, res->start,
+						     resource_size(res));
 		if (IS_ERR(priv->raminit_ctrlreg) || priv->instance < 0)
 			dev_info(&pdev->dev, "control memory is not used for raminit\n");
 		else
-			priv->raminit = c_can_hw_raminit;
+			priv->raminit = c_can_hw_raminit_ti;
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/drivers/net/can/mscan/Kconfig b/drivers/net/can/mscan/Kconfig
index f19be5269e7..81c71171949 100644
--- a/drivers/net/can/mscan/Kconfig
+++ b/drivers/net/can/mscan/Kconfig
@@ -1,5 +1,5 @@
 config CAN_MSCAN
-	depends on PPC || M68K
+	depends on PPC
 	tristate "Support for Freescale MSCAN based chips"
 	---help---
 	  The Motorola Scalable Controller Area Network (MSCAN) definition
diff --git a/drivers/net/can/rcar_can.c b/drivers/net/can/rcar_can.c
new file mode 100644
index 00000000000..5268d216ecf
--- /dev/null
+++ b/drivers/net/can/rcar_can.c
@@ -0,0 +1,876 @@
+/* Renesas R-Car CAN device driver
+ *
+ * Copyright (C) 2013 Cogent Embedded, Inc. <source@cogentembedded.com>
+ * Copyright (C) 2013 Renesas Solutions Corp.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/platform_device.h>
+#include <linux/can/led.h>
+#include <linux/can/dev.h>
+#include <linux/clk.h>
+#include <linux/can/platform/rcar_can.h>
+
+#define RCAR_CAN_DRV_NAME	"rcar_can"
+
+/* Mailbox configuration:
+ * mailbox 60 - 63 - Rx FIFO mailboxes
+ * mailbox 56 - 59 - Tx FIFO mailboxes
+ * non-FIFO mailboxes are not used
+ */
+#define RCAR_CAN_N_MBX		64 /* Number of mailboxes in non-FIFO mode */
+#define RCAR_CAN_RX_FIFO_MBX	60 /* Mailbox - window to Rx FIFO */
+#define RCAR_CAN_TX_FIFO_MBX	56 /* Mailbox - window to Tx FIFO */
+#define RCAR_CAN_FIFO_DEPTH	4
+
+/* Mailbox registers structure */
+struct rcar_can_mbox_regs {
+	u32 id;		/* IDE and RTR bits, SID and EID */
+	u8 stub;	/* Not used */
+	u8 dlc;		/* Data Length Code - bits [0..3] */
+	u8 data[8];	/* Data Bytes */
+	u8 tsh;		/* Time Stamp Higher Byte */
+	u8 tsl;		/* Time Stamp Lower Byte */
+};
+
+struct rcar_can_regs {
+	struct rcar_can_mbox_regs mb[RCAR_CAN_N_MBX]; /* Mailbox registers */
+	u32 mkr_2_9[8];	/* Mask Registers 2-9 */
+	u32 fidcr[2];	/* FIFO Received ID Compare Register */
+	u32 mkivlr1;	/* Mask Invalid Register 1 */
+	u32 mier1;	/* Mailbox Interrupt Enable Register 1 */
+	u32 mkr_0_1[2];	/* Mask Registers 0-1 */
+	u32 mkivlr0;    /* Mask Invalid Register 0*/
+	u32 mier0;      /* Mailbox Interrupt Enable Register 0 */
+	u8 pad_440[0x3c0];
+	u8 mctl[64];	/* Message Control Registers */
+	u16 ctlr;	/* Control Register */
+	u16 str;	/* Status register */
+	u8 bcr[3];	/* Bit Configuration Register */
+	u8 clkr;	/* Clock Select Register */
+	u8 rfcr;	/* Receive FIFO Control Register */
+	u8 rfpcr;	/* Receive FIFO Pointer Control Register */
+	u8 tfcr;	/* Transmit FIFO Control Register */
+	u8 tfpcr;       /* Transmit FIFO Pointer Control Register */
+	u8 eier;	/* Error Interrupt Enable Register */
+	u8 eifr;	/* Error Interrupt Factor Judge Register */
+	u8 recr;	/* Receive Error Count Register */
+	u8 tecr;        /* Transmit Error Count Register */
+	u8 ecsr;	/* Error Code Store Register */
+	u8 cssr;	/* Channel Search Support Register */
+	u8 mssr;	/* Mailbox Search Status Register */
+	u8 msmr;	/* Mailbox Search Mode Register */
+	u16 tsr;	/* Time Stamp Register */
+	u8 afsr;	/* Acceptance Filter Support Register */
+	u8 pad_857;
+	u8 tcr;		/* Test Control Register */
+	u8 pad_859[7];
+	u8 ier;		/* Interrupt Enable Register */
+	u8 isr;		/* Interrupt Status Register */
+	u8 pad_862;
+	u8 mbsmr;	/* Mailbox Search Mask Register */
+};
+
+struct rcar_can_priv {
+	struct can_priv can;	/* Must be the first member! */
+	struct net_device *ndev;
+	struct napi_struct napi;
+	struct rcar_can_regs __iomem *regs;
+	struct clk *clk;
+	u8 tx_dlc[RCAR_CAN_FIFO_DEPTH];
+	u32 tx_head;
+	u32 tx_tail;
+	u8 clock_select;
+	u8 ier;
+};
+
+static const struct can_bittiming_const rcar_can_bittiming_const = {
+	.name = RCAR_CAN_DRV_NAME,
+	.tseg1_min = 4,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 1024,
+	.brp_inc = 1,
+};
+
+/* Control Register bits */
+#define RCAR_CAN_CTLR_BOM	(3 << 11) /* Bus-Off Recovery Mode Bits */
+#define RCAR_CAN_CTLR_BOM_ENT	(1 << 11) /* Entry to halt mode */
+					/* at bus-off entry */
+#define RCAR_CAN_CTLR_SLPM	(1 << 10)
+#define RCAR_CAN_CTLR_CANM	(3 << 8) /* Operating Mode Select Bit */
+#define RCAR_CAN_CTLR_CANM_HALT	(1 << 9)
+#define RCAR_CAN_CTLR_CANM_RESET (1 << 8)
+#define RCAR_CAN_CTLR_CANM_FORCE_RESET (3 << 8)
+#define RCAR_CAN_CTLR_MLM	(1 << 3) /* Message Lost Mode Select */
+#define RCAR_CAN_CTLR_IDFM	(3 << 1) /* ID Format Mode Select Bits */
+#define RCAR_CAN_CTLR_IDFM_MIXED (1 << 2) /* Mixed ID mode */
+#define RCAR_CAN_CTLR_MBM	(1 << 0) /* Mailbox Mode select */
+
+/* Status Register bits */
+#define RCAR_CAN_STR_RSTST	(1 << 8) /* Reset Status Bit */
+
+/* FIFO Received ID Compare Registers 0 and 1 bits */
+#define RCAR_CAN_FIDCR_IDE	(1 << 31) /* ID Extension Bit */
+#define RCAR_CAN_FIDCR_RTR	(1 << 30) /* Remote Transmission Request Bit */
+
+/* Receive FIFO Control Register bits */
+#define RCAR_CAN_RFCR_RFEST	(1 << 7) /* Receive FIFO Empty Status Flag */
+#define RCAR_CAN_RFCR_RFE	(1 << 0) /* Receive FIFO Enable */
+
+/* Transmit FIFO Control Register bits */
+#define RCAR_CAN_TFCR_TFUST	(7 << 1) /* Transmit FIFO Unsent Message */
+					/* Number Status Bits */
+#define RCAR_CAN_TFCR_TFUST_SHIFT 1	/* Offset of Transmit FIFO Unsent */
+					/* Message Number Status Bits */
+#define RCAR_CAN_TFCR_TFE	(1 << 0) /* Transmit FIFO Enable */
+
+#define RCAR_CAN_N_RX_MKREGS1	2	/* Number of mask registers */
+					/* for Rx mailboxes 0-31 */
+#define RCAR_CAN_N_RX_MKREGS2	8
+
+/* Bit Configuration Register settings */
+#define RCAR_CAN_BCR_TSEG1(x)	(((x) & 0x0f) << 20)
+#define RCAR_CAN_BCR_BPR(x)	(((x) & 0x3ff) << 8)
+#define RCAR_CAN_BCR_SJW(x)	(((x) & 0x3) << 4)
+#define RCAR_CAN_BCR_TSEG2(x)	((x) & 0x07)
+
+/* Mailbox and Mask Registers bits */
+#define RCAR_CAN_IDE		(1 << 31)
+#define RCAR_CAN_RTR		(1 << 30)
+#define RCAR_CAN_SID_SHIFT	18
+
+/* Mailbox Interrupt Enable Register 1 bits */
+#define RCAR_CAN_MIER1_RXFIE	(1 << 28) /* Receive  FIFO Interrupt Enable */
+#define RCAR_CAN_MIER1_TXFIE	(1 << 24) /* Transmit FIFO Interrupt Enable */
+
+/* Interrupt Enable Register bits */
+#define RCAR_CAN_IER_ERSIE	(1 << 5) /* Error (ERS) Interrupt Enable Bit */
+#define RCAR_CAN_IER_RXFIE	(1 << 4) /* Reception FIFO Interrupt */
+					/* Enable Bit */
+#define RCAR_CAN_IER_TXFIE	(1 << 3) /* Transmission FIFO Interrupt */
+					/* Enable Bit */
+/* Interrupt Status Register bits */
+#define RCAR_CAN_ISR_ERSF	(1 << 5) /* Error (ERS) Interrupt Status Bit */
+#define RCAR_CAN_ISR_RXFF	(1 << 4) /* Reception FIFO Interrupt */
+					/* Status Bit */
+#define RCAR_CAN_ISR_TXFF	(1 << 3) /* Transmission FIFO Interrupt */
+					/* Status Bit */
+
+/* Error Interrupt Enable Register bits */
+#define RCAR_CAN_EIER_BLIE	(1 << 7) /* Bus Lock Interrupt Enable */
+#define RCAR_CAN_EIER_OLIE	(1 << 6) /* Overload Frame Transmit */
+					/* Interrupt Enable */
+#define RCAR_CAN_EIER_ORIE	(1 << 5) /* Receive Overrun  Interrupt Enable */
+#define RCAR_CAN_EIER_BORIE	(1 << 4) /* Bus-Off Recovery Interrupt Enable */
+#define RCAR_CAN_EIER_BOEIE	(1 << 3) /* Bus-Off Entry Interrupt Enable */
+#define RCAR_CAN_EIER_EPIE	(1 << 2) /* Error Passive Interrupt Enable */
+#define RCAR_CAN_EIER_EWIE	(1 << 1) /* Error Warning Interrupt Enable */
+#define RCAR_CAN_EIER_BEIE	(1 << 0) /* Bus Error Interrupt Enable */
+
+/* Error Interrupt Factor Judge Register bits */
+#define RCAR_CAN_EIFR_BLIF	(1 << 7) /* Bus Lock Detect Flag */
+#define RCAR_CAN_EIFR_OLIF	(1 << 6) /* Overload Frame Transmission */
+					 /* Detect Flag */
+#define RCAR_CAN_EIFR_ORIF	(1 << 5) /* Receive Overrun Detect Flag */
+#define RCAR_CAN_EIFR_BORIF	(1 << 4) /* Bus-Off Recovery Detect Flag */
+#define RCAR_CAN_EIFR_BOEIF	(1 << 3) /* Bus-Off Entry Detect Flag */
+#define RCAR_CAN_EIFR_EPIF	(1 << 2) /* Error Passive Detect Flag */
+#define RCAR_CAN_EIFR_EWIF	(1 << 1) /* Error Warning Detect Flag */
+#define RCAR_CAN_EIFR_BEIF	(1 << 0) /* Bus Error Detect Flag */
+
+/* Error Code Store Register bits */
+#define RCAR_CAN_ECSR_EDPM	(1 << 7) /* Error Display Mode Select Bit */
+#define RCAR_CAN_ECSR_ADEF	(1 << 6) /* ACK Delimiter Error Flag */
+#define RCAR_CAN_ECSR_BE0F	(1 << 5) /* Bit Error (dominant) Flag */
+#define RCAR_CAN_ECSR_BE1F	(1 << 4) /* Bit Error (recessive) Flag */
+#define RCAR_CAN_ECSR_CEF	(1 << 3) /* CRC Error Flag */
+#define RCAR_CAN_ECSR_AEF	(1 << 2) /* ACK Error Flag */
+#define RCAR_CAN_ECSR_FEF	(1 << 1) /* Form Error Flag */
+#define RCAR_CAN_ECSR_SEF	(1 << 0) /* Stuff Error Flag */
+
+#define RCAR_CAN_NAPI_WEIGHT	4
+#define MAX_STR_READS		0x100
+
+static void tx_failure_cleanup(struct net_device *ndev)
+{
+	int i;
+
+	for (i = 0; i < RCAR_CAN_FIFO_DEPTH; i++)
+		can_free_echo_skb(ndev, i);
+}
+
+static void rcar_can_error(struct net_device *ndev)
+{
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u8 eifr, txerr = 0, rxerr = 0;
+
+	/* Propagate the error condition to the CAN stack */
+	skb = alloc_can_err_skb(ndev, &cf);
+
+	eifr = readb(&priv->regs->eifr);
+	if (eifr & (RCAR_CAN_EIFR_EWIF | RCAR_CAN_EIFR_EPIF)) {
+		txerr = readb(&priv->regs->tecr);
+		rxerr = readb(&priv->regs->recr);
+		if (skb) {
+			cf->can_id |= CAN_ERR_CRTL;
+			cf->data[6] = txerr;
+			cf->data[7] = rxerr;
+		}
+	}
+	if (eifr & RCAR_CAN_EIFR_BEIF) {
+		int rx_errors = 0, tx_errors = 0;
+		u8 ecsr;
+
+		netdev_dbg(priv->ndev, "Bus error interrupt:\n");
+		if (skb) {
+			cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
+			cf->data[2] = CAN_ERR_PROT_UNSPEC;
+		}
+		ecsr = readb(&priv->regs->ecsr);
+		if (ecsr & RCAR_CAN_ECSR_ADEF) {
+			netdev_dbg(priv->ndev, "ACK Delimiter Error\n");
+			tx_errors++;
+			writeb(~RCAR_CAN_ECSR_ADEF, &priv->regs->ecsr);
+			if (skb)
+				cf->data[3] |= CAN_ERR_PROT_LOC_ACK_DEL;
+		}
+		if (ecsr & RCAR_CAN_ECSR_BE0F) {
+			netdev_dbg(priv->ndev, "Bit Error (dominant)\n");
+			tx_errors++;
+			writeb(~RCAR_CAN_ECSR_BE0F, &priv->regs->ecsr);
+			if (skb)
+				cf->data[2] |= CAN_ERR_PROT_BIT0;
+		}
+		if (ecsr & RCAR_CAN_ECSR_BE1F) {
+			netdev_dbg(priv->ndev, "Bit Error (recessive)\n");
+			tx_errors++;
+			writeb(~RCAR_CAN_ECSR_BE1F, &priv->regs->ecsr);
+			if (skb)
+				cf->data[2] |= CAN_ERR_PROT_BIT1;
+		}
+		if (ecsr & RCAR_CAN_ECSR_CEF) {
+			netdev_dbg(priv->ndev, "CRC Error\n");
+			rx_errors++;
+			writeb(~RCAR_CAN_ECSR_CEF, &priv->regs->ecsr);
+			if (skb)
+				cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+		}
+		if (ecsr & RCAR_CAN_ECSR_AEF) {
+			netdev_dbg(priv->ndev, "ACK Error\n");
+			tx_errors++;
+			writeb(~RCAR_CAN_ECSR_AEF, &priv->regs->ecsr);
+			if (skb) {
+				cf->can_id |= CAN_ERR_ACK;
+				cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+			}
+		}
+		if (ecsr & RCAR_CAN_ECSR_FEF) {
+			netdev_dbg(priv->ndev, "Form Error\n");
+			rx_errors++;
+			writeb(~RCAR_CAN_ECSR_FEF, &priv->regs->ecsr);
+			if (skb)
+				cf->data[2] |= CAN_ERR_PROT_FORM;
+		}
+		if (ecsr & RCAR_CAN_ECSR_SEF) {
+			netdev_dbg(priv->ndev, "Stuff Error\n");
+			rx_errors++;
+			writeb(~RCAR_CAN_ECSR_SEF, &priv->regs->ecsr);
+			if (skb)
+				cf->data[2] |= CAN_ERR_PROT_STUFF;
+		}
+
+		priv->can.can_stats.bus_error++;
+		ndev->stats.rx_errors += rx_errors;
+		ndev->stats.tx_errors += tx_errors;
+		writeb(~RCAR_CAN_EIFR_BEIF, &priv->regs->eifr);
+	}
+	if (eifr & RCAR_CAN_EIFR_EWIF) {
+		netdev_dbg(priv->ndev, "Error warning interrupt\n");
+		priv->can.state = CAN_STATE_ERROR_WARNING;
+		priv->can.can_stats.error_warning++;
+		/* Clear interrupt condition */
+		writeb(~RCAR_CAN_EIFR_EWIF, &priv->regs->eifr);
+		if (skb)
+			cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_WARNING :
+					      CAN_ERR_CRTL_RX_WARNING;
+	}
+	if (eifr & RCAR_CAN_EIFR_EPIF) {
+		netdev_dbg(priv->ndev, "Error passive interrupt\n");
+		priv->can.state = CAN_STATE_ERROR_PASSIVE;
+		priv->can.can_stats.error_passive++;
+		/* Clear interrupt condition */
+		writeb(~RCAR_CAN_EIFR_EPIF, &priv->regs->eifr);
+		if (skb)
+			cf->data[1] = txerr > rxerr ? CAN_ERR_CRTL_TX_PASSIVE :
+					      CAN_ERR_CRTL_RX_PASSIVE;
+	}
+	if (eifr & RCAR_CAN_EIFR_BOEIF) {
+		netdev_dbg(priv->ndev, "Bus-off entry interrupt\n");
+		tx_failure_cleanup(ndev);
+		priv->ier = RCAR_CAN_IER_ERSIE;
+		writeb(priv->ier, &priv->regs->ier);
+		priv->can.state = CAN_STATE_BUS_OFF;
+		/* Clear interrupt condition */
+		writeb(~RCAR_CAN_EIFR_BOEIF, &priv->regs->eifr);
+		can_bus_off(ndev);
+		if (skb)
+			cf->can_id |= CAN_ERR_BUSOFF;
+	}
+	if (eifr & RCAR_CAN_EIFR_ORIF) {
+		netdev_dbg(priv->ndev, "Receive overrun error interrupt\n");
+		ndev->stats.rx_over_errors++;
+		ndev->stats.rx_errors++;
+		writeb(~RCAR_CAN_EIFR_ORIF, &priv->regs->eifr);
+		if (skb) {
+			cf->can_id |= CAN_ERR_CRTL;
+			cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
+		}
+	}
+	if (eifr & RCAR_CAN_EIFR_OLIF) {
+		netdev_dbg(priv->ndev,
+			   "Overload Frame Transmission error interrupt\n");
+		ndev->stats.rx_over_errors++;
+		ndev->stats.rx_errors++;
+		writeb(~RCAR_CAN_EIFR_OLIF, &priv->regs->eifr);
+		if (skb) {
+			cf->can_id |= CAN_ERR_PROT;
+			cf->data[2] |= CAN_ERR_PROT_OVERLOAD;
+		}
+	}
+
+	if (skb) {
+		stats->rx_packets++;
+		stats->rx_bytes += cf->can_dlc;
+		netif_rx(skb);
+	}
+}
+
+static void rcar_can_tx_done(struct net_device *ndev)
+{
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	u8 isr;
+
+	while (1) {
+		u8 unsent = readb(&priv->regs->tfcr);
+
+		unsent = (unsent & RCAR_CAN_TFCR_TFUST) >>
+			  RCAR_CAN_TFCR_TFUST_SHIFT;
+		if (priv->tx_head - priv->tx_tail <= unsent)
+			break;
+		stats->tx_packets++;
+		stats->tx_bytes += priv->tx_dlc[priv->tx_tail %
+						RCAR_CAN_FIFO_DEPTH];
+		priv->tx_dlc[priv->tx_tail % RCAR_CAN_FIFO_DEPTH] = 0;
+		can_get_echo_skb(ndev, priv->tx_tail % RCAR_CAN_FIFO_DEPTH);
+		priv->tx_tail++;
+		netif_wake_queue(ndev);
+	}
+	/* Clear interrupt */
+	isr = readb(&priv->regs->isr);
+	writeb(isr & ~RCAR_CAN_ISR_TXFF, &priv->regs->isr);
+	can_led_event(ndev, CAN_LED_EVENT_TX);
+}
+
+static irqreturn_t rcar_can_interrupt(int irq, void *dev_id)
+{
+	struct net_device *ndev = dev_id;
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+	u8 isr;
+
+	isr = readb(&priv->regs->isr);
+	if (!(isr & priv->ier))
+		return IRQ_NONE;
+
+	if (isr & RCAR_CAN_ISR_ERSF)
+		rcar_can_error(ndev);
+
+	if (isr & RCAR_CAN_ISR_TXFF)
+		rcar_can_tx_done(ndev);
+
+	if (isr & RCAR_CAN_ISR_RXFF) {
+		if (napi_schedule_prep(&priv->napi)) {
+			/* Disable Rx FIFO interrupts */
+			priv->ier &= ~RCAR_CAN_IER_RXFIE;
+			writeb(priv->ier, &priv->regs->ier);
+			__napi_schedule(&priv->napi);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void rcar_can_set_bittiming(struct net_device *dev)
+{
+	struct rcar_can_priv *priv = netdev_priv(dev);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	u32 bcr;
+
+	bcr = RCAR_CAN_BCR_TSEG1(bt->phase_seg1 + bt->prop_seg - 1) |
+	      RCAR_CAN_BCR_BPR(bt->brp - 1) | RCAR_CAN_BCR_SJW(bt->sjw - 1) |
+	      RCAR_CAN_BCR_TSEG2(bt->phase_seg2 - 1);
+	/* Don't overwrite CLKR with 32-bit BCR access; CLKR has 8-bit access.
+	 * All the registers are big-endian but they get byte-swapped on 32-bit
+	 * read/write (but not on 8-bit, contrary to the manuals)...
+	 */
+	writel((bcr << 8) | priv->clock_select, &priv->regs->bcr);
+}
+
+static void rcar_can_start(struct net_device *ndev)
+{
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+	u16 ctlr;
+	int i;
+
+	/* Set controller to known mode:
+	 * - FIFO mailbox mode
+	 * - accept all messages
+	 * - overrun mode
+	 * CAN is in sleep mode after MCU hardware or software reset.
+	 */
+	ctlr = readw(&priv->regs->ctlr);
+	ctlr &= ~RCAR_CAN_CTLR_SLPM;
+	writew(ctlr, &priv->regs->ctlr);
+	/* Go to reset mode */
+	ctlr |= RCAR_CAN_CTLR_CANM_FORCE_RESET;
+	writew(ctlr, &priv->regs->ctlr);
+	for (i = 0; i < MAX_STR_READS; i++) {
+		if (readw(&priv->regs->str) & RCAR_CAN_STR_RSTST)
+			break;
+	}
+	rcar_can_set_bittiming(ndev);
+	ctlr |= RCAR_CAN_CTLR_IDFM_MIXED; /* Select mixed ID mode */
+	ctlr |= RCAR_CAN_CTLR_BOM_ENT;	/* Entry to halt mode automatically */
+					/* at bus-off */
+	ctlr |= RCAR_CAN_CTLR_MBM;	/* Select FIFO mailbox mode */
+	ctlr |= RCAR_CAN_CTLR_MLM;	/* Overrun mode */
+	writew(ctlr, &priv->regs->ctlr);
+
+	/* Accept all SID and EID */
+	writel(0, &priv->regs->mkr_2_9[6]);
+	writel(0, &priv->regs->mkr_2_9[7]);
+	/* In FIFO mailbox mode, write "0" to bits 24 to 31 */
+	writel(0, &priv->regs->mkivlr1);
+	/* Accept all frames */
+	writel(0, &priv->regs->fidcr[0]);
+	writel(RCAR_CAN_FIDCR_IDE | RCAR_CAN_FIDCR_RTR, &priv->regs->fidcr[1]);
+	/* Enable and configure FIFO mailbox interrupts */
+	writel(RCAR_CAN_MIER1_RXFIE | RCAR_CAN_MIER1_TXFIE, &priv->regs->mier1);
+
+	priv->ier = RCAR_CAN_IER_ERSIE | RCAR_CAN_IER_RXFIE |
+		    RCAR_CAN_IER_TXFIE;
+	writeb(priv->ier, &priv->regs->ier);
+
+	/* Accumulate error codes */
+	writeb(RCAR_CAN_ECSR_EDPM, &priv->regs->ecsr);
+	/* Enable error interrupts */
+	writeb(RCAR_CAN_EIER_EWIE | RCAR_CAN_EIER_EPIE | RCAR_CAN_EIER_BOEIE |
+	       (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING ?
+	       RCAR_CAN_EIER_BEIE : 0) | RCAR_CAN_EIER_ORIE |
+	       RCAR_CAN_EIER_OLIE, &priv->regs->eier);
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	/* Go to operation mode */
+	writew(ctlr & ~RCAR_CAN_CTLR_CANM, &priv->regs->ctlr);
+	for (i = 0; i < MAX_STR_READS; i++) {
+		if (!(readw(&priv->regs->str) & RCAR_CAN_STR_RSTST))
+			break;
+	}
+	/* Enable Rx and Tx FIFO */
+	writeb(RCAR_CAN_RFCR_RFE, &priv->regs->rfcr);
+	writeb(RCAR_CAN_TFCR_TFE, &priv->regs->tfcr);
+}
+
+static int rcar_can_open(struct net_device *ndev)
+{
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+	int err;
+
+	err = clk_prepare_enable(priv->clk);
+	if (err) {
+		netdev_err(ndev, "clk_prepare_enable() failed, error %d\n",
+			   err);
+		goto out;
+	}
+	err = open_candev(ndev);
+	if (err) {
+		netdev_err(ndev, "open_candev() failed, error %d\n", err);
+		goto out_clock;
+	}
+	napi_enable(&priv->napi);
+	err = request_irq(ndev->irq, rcar_can_interrupt, 0, ndev->name, ndev);
+	if (err) {
+		netdev_err(ndev, "error requesting interrupt %x\n", ndev->irq);
+		goto out_close;
+	}
+	can_led_event(ndev, CAN_LED_EVENT_OPEN);
+	rcar_can_start(ndev);
+	netif_start_queue(ndev);
+	return 0;
+out_close:
+	napi_disable(&priv->napi);
+	close_candev(ndev);
+out_clock:
+	clk_disable_unprepare(priv->clk);
+out:
+	return err;
+}
+
+static void rcar_can_stop(struct net_device *ndev)
+{
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+	u16 ctlr;
+	int i;
+
+	/* Go to (force) reset mode */
+	ctlr = readw(&priv->regs->ctlr);
+	ctlr |= RCAR_CAN_CTLR_CANM_FORCE_RESET;
+	writew(ctlr, &priv->regs->ctlr);
+	for (i = 0; i < MAX_STR_READS; i++) {
+		if (readw(&priv->regs->str) & RCAR_CAN_STR_RSTST)
+			break;
+	}
+	writel(0, &priv->regs->mier0);
+	writel(0, &priv->regs->mier1);
+	writeb(0, &priv->regs->ier);
+	writeb(0, &priv->regs->eier);
+	/* Go to sleep mode */
+	ctlr |= RCAR_CAN_CTLR_SLPM;
+	writew(ctlr, &priv->regs->ctlr);
+	priv->can.state = CAN_STATE_STOPPED;
+}
+
+static int rcar_can_close(struct net_device *ndev)
+{
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	rcar_can_stop(ndev);
+	free_irq(ndev->irq, ndev);
+	napi_disable(&priv->napi);
+	clk_disable_unprepare(priv->clk);
+	close_candev(ndev);
+	can_led_event(ndev, CAN_LED_EVENT_STOP);
+	return 0;
+}
+
+static netdev_tx_t rcar_can_start_xmit(struct sk_buff *skb,
+				       struct net_device *ndev)
+{
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+	struct can_frame *cf = (struct can_frame *)skb->data;
+	u32 data, i;
+
+	if (can_dropped_invalid_skb(ndev, skb))
+		return NETDEV_TX_OK;
+
+	if (cf->can_id & CAN_EFF_FLAG)	/* Extended frame format */
+		data = (cf->can_id & CAN_EFF_MASK) | RCAR_CAN_IDE;
+	else				/* Standard frame format */
+		data = (cf->can_id & CAN_SFF_MASK) << RCAR_CAN_SID_SHIFT;
+
+	if (cf->can_id & CAN_RTR_FLAG) { /* Remote transmission request */
+		data |= RCAR_CAN_RTR;
+	} else {
+		for (i = 0; i < cf->can_dlc; i++)
+			writeb(cf->data[i],
+			       &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].data[i]);
+	}
+
+	writel(data, &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].id);
+
+	writeb(cf->can_dlc, &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].dlc);
+
+	priv->tx_dlc[priv->tx_head % RCAR_CAN_FIFO_DEPTH] = cf->can_dlc;
+	can_put_echo_skb(skb, ndev, priv->tx_head % RCAR_CAN_FIFO_DEPTH);
+	priv->tx_head++;
+	/* Start Tx: write 0xff to the TFPCR register to increment
+	 * the CPU-side pointer for the transmit FIFO to the next
+	 * mailbox location
+	 */
+	writeb(0xff, &priv->regs->tfpcr);
+	/* Stop the queue if we've filled all FIFO entries */
+	if (priv->tx_head - priv->tx_tail >= RCAR_CAN_FIFO_DEPTH)
+		netif_stop_queue(ndev);
+
+	return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops rcar_can_netdev_ops = {
+	.ndo_open = rcar_can_open,
+	.ndo_stop = rcar_can_close,
+	.ndo_start_xmit = rcar_can_start_xmit,
+};
+
+static void rcar_can_rx_pkt(struct rcar_can_priv *priv)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u32 data;
+	u8 dlc;
+
+	skb = alloc_can_skb(priv->ndev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	data = readl(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].id);
+	if (data & RCAR_CAN_IDE)
+		cf->can_id = (data & CAN_EFF_MASK) | CAN_EFF_FLAG;
+	else
+		cf->can_id = (data >> RCAR_CAN_SID_SHIFT) & CAN_SFF_MASK;
+
+	dlc = readb(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].dlc);
+	cf->can_dlc = get_can_dlc(dlc);
+	if (data & RCAR_CAN_RTR) {
+		cf->can_id |= CAN_RTR_FLAG;
+	} else {
+		for (dlc = 0; dlc < cf->can_dlc; dlc++)
+			cf->data[dlc] =
+			readb(&priv->regs->mb[RCAR_CAN_RX_FIFO_MBX].data[dlc]);
+	}
+
+	can_led_event(priv->ndev, CAN_LED_EVENT_RX);
+
+	stats->rx_bytes += cf->can_dlc;
+	stats->rx_packets++;
+	netif_receive_skb(skb);
+}
+
+static int rcar_can_rx_poll(struct napi_struct *napi, int quota)
+{
+	struct rcar_can_priv *priv = container_of(napi,
+						  struct rcar_can_priv, napi);
+	int num_pkts;
+
+	for (num_pkts = 0; num_pkts < quota; num_pkts++) {
+		u8 rfcr, isr;
+
+		isr = readb(&priv->regs->isr);
+		/* Clear interrupt bit */
+		if (isr & RCAR_CAN_ISR_RXFF)
+			writeb(isr & ~RCAR_CAN_ISR_RXFF, &priv->regs->isr);
+		rfcr = readb(&priv->regs->rfcr);
+		if (rfcr & RCAR_CAN_RFCR_RFEST)
+			break;
+		rcar_can_rx_pkt(priv);
+		/* Write 0xff to the RFPCR register to increment
+		 * the CPU-side pointer for the receive FIFO
+		 * to the next mailbox location
+		 */
+		writeb(0xff, &priv->regs->rfpcr);
+	}
+	/* All packets processed */
+	if (num_pkts < quota) {
+		napi_complete(napi);
+		priv->ier |= RCAR_CAN_IER_RXFIE;
+		writeb(priv->ier, &priv->regs->ier);
+	}
+	return num_pkts;
+}
+
+static int rcar_can_do_set_mode(struct net_device *ndev, enum can_mode mode)
+{
+	switch (mode) {
+	case CAN_MODE_START:
+		rcar_can_start(ndev);
+		netif_wake_queue(ndev);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int rcar_can_get_berr_counter(const struct net_device *dev,
+				     struct can_berr_counter *bec)
+{
+	struct rcar_can_priv *priv = netdev_priv(dev);
+	int err;
+
+	err = clk_prepare_enable(priv->clk);
+	if (err)
+		return err;
+	bec->txerr = readb(&priv->regs->tecr);
+	bec->rxerr = readb(&priv->regs->recr);
+	clk_disable_unprepare(priv->clk);
+	return 0;
+}
+
+static int rcar_can_probe(struct platform_device *pdev)
+{
+	struct rcar_can_platform_data *pdata;
+	struct rcar_can_priv *priv;
+	struct net_device *ndev;
+	struct resource *mem;
+	void __iomem *addr;
+	int err = -ENODEV;
+	int irq;
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata) {
+		dev_err(&pdev->dev, "No platform data provided!\n");
+		goto fail;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (!irq) {
+		dev_err(&pdev->dev, "No IRQ resource\n");
+		goto fail;
+	}
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	addr = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(addr)) {
+		err = PTR_ERR(addr);
+		goto fail;
+	}
+
+	ndev = alloc_candev(sizeof(struct rcar_can_priv), RCAR_CAN_FIFO_DEPTH);
+	if (!ndev) {
+		dev_err(&pdev->dev, "alloc_candev() failed\n");
+		err = -ENOMEM;
+		goto fail;
+	}
+
+	priv = netdev_priv(ndev);
+
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		err = PTR_ERR(priv->clk);
+		dev_err(&pdev->dev, "cannot get clock: %d\n", err);
+		goto fail_clk;
+	}
+
+	ndev->netdev_ops = &rcar_can_netdev_ops;
+	ndev->irq = irq;
+	ndev->flags |= IFF_ECHO;
+	priv->ndev = ndev;
+	priv->regs = addr;
+	priv->clock_select = pdata->clock_select;
+	priv->can.clock.freq = clk_get_rate(priv->clk);
+	priv->can.bittiming_const = &rcar_can_bittiming_const;
+	priv->can.do_set_mode = rcar_can_do_set_mode;
+	priv->can.do_get_berr_counter = rcar_can_get_berr_counter;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING;
+	platform_set_drvdata(pdev, ndev);
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+
+	netif_napi_add(ndev, &priv->napi, rcar_can_rx_poll,
+		       RCAR_CAN_NAPI_WEIGHT);
+	err = register_candev(ndev);
+	if (err) {
+		dev_err(&pdev->dev, "register_candev() failed, error %d\n",
+			err);
+		goto fail_candev;
+	}
+
+	devm_can_led_init(ndev);
+
+	dev_info(&pdev->dev, "device registered (reg_base=%p, irq=%u)\n",
+		 priv->regs, ndev->irq);
+
+	return 0;
+fail_candev:
+	netif_napi_del(&priv->napi);
+fail_clk:
+	free_candev(ndev);
+fail:
+	return err;
+}
+
+static int rcar_can_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+
+	unregister_candev(ndev);
+	netif_napi_del(&priv->napi);
+	free_candev(ndev);
+	return 0;
+}
+
+static int __maybe_unused rcar_can_suspend(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+	u16 ctlr;
+
+	if (netif_running(ndev)) {
+		netif_stop_queue(ndev);
+		netif_device_detach(ndev);
+	}
+	ctlr = readw(&priv->regs->ctlr);
+	ctlr |= RCAR_CAN_CTLR_CANM_HALT;
+	writew(ctlr, &priv->regs->ctlr);
+	ctlr |= RCAR_CAN_CTLR_SLPM;
+	writew(ctlr, &priv->regs->ctlr);
+	priv->can.state = CAN_STATE_SLEEPING;
+
+	clk_disable(priv->clk);
+	return 0;
+}
+
+static int __maybe_unused rcar_can_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct rcar_can_priv *priv = netdev_priv(ndev);
+	u16 ctlr;
+	int err;
+
+	err = clk_enable(priv->clk);
+	if (err) {
+		netdev_err(ndev, "clk_enable() failed, error %d\n", err);
+		return err;
+	}
+
+	ctlr = readw(&priv->regs->ctlr);
+	ctlr &= ~RCAR_CAN_CTLR_SLPM;
+	writew(ctlr, &priv->regs->ctlr);
+	ctlr &= ~RCAR_CAN_CTLR_CANM;
+	writew(ctlr, &priv->regs->ctlr);
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	if (netif_running(ndev)) {
+		netif_device_attach(ndev);
+		netif_start_queue(ndev);
+	}
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(rcar_can_pm_ops, rcar_can_suspend, rcar_can_resume);
+
+static struct platform_driver rcar_can_driver = {
+	.driver = {
+		.name = RCAR_CAN_DRV_NAME,
+		.owner = THIS_MODULE,
+		.pm = &rcar_can_pm_ops,
+	},
+	.probe = rcar_can_probe,
+	.remove = rcar_can_remove,
+};
+
+module_platform_driver(rcar_can_driver);
+
+MODULE_AUTHOR("Cogent Embedded, Inc.");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("CAN driver for Renesas R-Car SoC");
+MODULE_ALIAS("platform:" RCAR_CAN_DRV_NAME);
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index dcf9196f631..ea4d4f1a641 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -52,6 +52,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/workqueue.h>
 #include <linux/can.h>
 #include <linux/can/skb.h>
 
@@ -85,6 +86,7 @@ struct slcan {
 	struct tty_struct	*tty;		/* ptr to TTY structure	     */
 	struct net_device	*dev;		/* easy for intr handling    */
 	spinlock_t		lock;
+	struct work_struct	tx_work;	/* Flushes transmit buffer   */
 
 	/* These are pointers to the malloc()ed frame buffers. */
 	unsigned char		rbuff[SLC_MTU];	/* receiver buffer	     */
@@ -309,36 +311,46 @@ static void slc_encaps(struct slcan *sl, struct can_frame *cf)
 	sl->dev->stats.tx_bytes += cf->can_dlc;
 }
 
-/*
- * Called by the driver when there's room for more data.  If we have
- * more packets to send, we send them here.
- */
-static void slcan_write_wakeup(struct tty_struct *tty)
+/* Write out any remaining transmit buffer. Scheduled when tty is writable */
+static void slcan_transmit(struct work_struct *work)
 {
+	struct slcan *sl = container_of(work, struct slcan, tx_work);
 	int actual;
-	struct slcan *sl = (struct slcan *) tty->disc_data;
 
+	spin_lock_bh(&sl->lock);
 	/* First make sure we're connected. */
-	if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev))
+	if (!sl->tty || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev)) {
+		spin_unlock_bh(&sl->lock);
 		return;
+	}
 
-	spin_lock_bh(&sl->lock);
 	if (sl->xleft <= 0)  {
 		/* Now serial buffer is almost free & we can start
 		 * transmission of another packet */
 		sl->dev->stats.tx_packets++;
-		clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
+		clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags);
 		spin_unlock_bh(&sl->lock);
 		netif_wake_queue(sl->dev);
 		return;
 	}
 
-	actual = tty->ops->write(tty, sl->xhead, sl->xleft);
+	actual = sl->tty->ops->write(sl->tty, sl->xhead, sl->xleft);
 	sl->xleft -= actual;
 	sl->xhead += actual;
 	spin_unlock_bh(&sl->lock);
 }
 
+/*
+ * Called by the driver when there's room for more data.
+ * Schedule the transmit.
+ */
+static void slcan_write_wakeup(struct tty_struct *tty)
+{
+	struct slcan *sl = tty->disc_data;
+
+	schedule_work(&sl->tx_work);
+}
+
 /* Send a can_frame to a TTY queue. */
 static netdev_tx_t slc_xmit(struct sk_buff *skb, struct net_device *dev)
 {
@@ -528,6 +540,7 @@ static struct slcan *slc_alloc(dev_t line)
 	sl->magic = SLCAN_MAGIC;
 	sl->dev	= dev;
 	spin_lock_init(&sl->lock);
+	INIT_WORK(&sl->tx_work, slcan_transmit);
 	slcan_devs[i] = dev;
 
 	return sl;
@@ -626,8 +639,12 @@ static void slcan_close(struct tty_struct *tty)
 	if (!sl || sl->magic != SLCAN_MAGIC || sl->tty != tty)
 		return;
 
+	spin_lock_bh(&sl->lock);
 	tty->disc_data = NULL;
 	sl->tty = NULL;
+	spin_unlock_bh(&sl->lock);
+
+	flush_work(&sl->tx_work);
 
 	/* Flush network side */
 	unregister_netdev(sl->dev);
diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c
index 7d8c8f3672d..bacd236ce30 100644
--- a/drivers/net/can/softing/softing_main.c
+++ b/drivers/net/can/softing/softing_main.c
@@ -556,15 +556,6 @@ failed:
 /*
  * netdev sysfs
  */
-static ssize_t show_channel(struct device *dev, struct device_attribute *attr,
-		char *buf)
-{
-	struct net_device *ndev = to_net_dev(dev);
-	struct softing_priv *priv = netdev2softing(ndev);
-
-	return sprintf(buf, "%i\n", priv->index);
-}
-
 static ssize_t show_chip(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
@@ -609,12 +600,10 @@ static ssize_t store_output(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static const DEVICE_ATTR(channel, S_IRUGO, show_channel, NULL);
 static const DEVICE_ATTR(chip, S_IRUGO, show_chip, NULL);
 static const DEVICE_ATTR(output, S_IRUGO | S_IWUSR, show_output, store_output);
 
 static const struct attribute *const netdev_sysfs_attrs[] = {
-	&dev_attr_channel.attr,
 	&dev_attr_chip.attr,
 	&dev_attr_output.attr,
 	NULL,
@@ -679,17 +668,20 @@ static int softing_netdev_register(struct net_device *netdev)
 {
 	int ret;
 
-	netdev->sysfs_groups[0] = &netdev_sysfs_group;
 	ret = register_candev(netdev);
 	if (ret) {
 		dev_alert(&netdev->dev, "register failed\n");
 		return ret;
 	}
+	if (sysfs_create_group(&netdev->dev.kobj, &netdev_sysfs_group) < 0)
+		netdev_alert(netdev, "sysfs group failed\n");
+
 	return 0;
 }
 
 static void softing_netdev_cleanup(struct net_device *netdev)
 {
+	sysfs_remove_group(&netdev->dev.kobj, &netdev_sysfs_group);
 	unregister_candev(netdev);
 	free_candev(netdev);
 }
@@ -721,8 +713,6 @@ DEV_ATTR_RO(firmware_version, id.fw_version);
 DEV_ATTR_RO_STR(hardware, pdat->name);
 DEV_ATTR_RO(hardware_version, id.hw_version);
 DEV_ATTR_RO(license, id.license);
-DEV_ATTR_RO(frequency, id.freq);
-DEV_ATTR_RO(txpending, tx.pending);
 
 static struct attribute *softing_pdev_attrs[] = {
 	&dev_attr_serial.attr,
@@ -731,8 +721,6 @@ static struct attribute *softing_pdev_attrs[] = {
 	&dev_attr_hardware.attr,
 	&dev_attr_hardware_version.attr,
 	&dev_attr_license.attr,
-	&dev_attr_frequency.attr,
-	&dev_attr_txpending.attr,
 	NULL,
 };
 
diff --git a/drivers/net/can/spi/Kconfig b/drivers/net/can/spi/Kconfig
new file mode 100644
index 00000000000..148cae5871a
--- /dev/null
+++ b/drivers/net/can/spi/Kconfig
@@ -0,0 +1,10 @@
+menu "CAN SPI interfaces"
+	depends on SPI
+
+config CAN_MCP251X
+	tristate "Microchip MCP251x SPI CAN controllers"
+	depends on HAS_DMA
+	---help---
+	  Driver for the Microchip MCP251x SPI CAN controllers.
+
+endmenu
diff --git a/drivers/net/can/spi/Makefile b/drivers/net/can/spi/Makefile
new file mode 100644
index 00000000000..90bcacffbc6
--- /dev/null
+++ b/drivers/net/can/spi/Makefile
@@ -0,0 +1,8 @@
+#
+#  Makefile for the Linux Controller Area Network SPI drivers.
+#
+
+
+obj-$(CONFIG_CAN_MCP251X)	+= mcp251x.o
+
+ccflags-$(CONFIG_CAN_DEBUG_DEVICES) := -DDEBUG
diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index 28c11f81524..5df239e6881 100644
--- a/drivers/net/can/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -214,6 +214,8 @@
 
 #define TX_ECHO_SKB_MAX	1
 
+#define MCP251X_OST_DELAY_MS	(5)
+
 #define DEVICE_NAME "mcp251x"
 
 static int mcp251x_enable_dma; /* Enable SPI DMA. Default: 0 (Off) */
@@ -624,50 +626,45 @@ static int mcp251x_setup(struct net_device *net, struct mcp251x_priv *priv,
 static int mcp251x_hw_reset(struct spi_device *spi)
 {
 	struct mcp251x_priv *priv = spi_get_drvdata(spi);
+	u8 reg;
 	int ret;
-	unsigned long timeout;
+
+	/* Wait for oscillator startup timer after power up */
+	mdelay(MCP251X_OST_DELAY_MS);
 
 	priv->spi_tx_buf[0] = INSTRUCTION_RESET;
-	ret = spi_write(spi, priv->spi_tx_buf, 1);
-	if (ret) {
-		dev_err(&spi->dev, "reset failed: ret = %d\n", ret);
-		return -EIO;
-	}
+	ret = mcp251x_spi_trans(spi, 1);
+	if (ret)
+		return ret;
+
+	/* Wait for oscillator startup timer after reset */
+	mdelay(MCP251X_OST_DELAY_MS);
+	
+	reg = mcp251x_read_reg(spi, CANSTAT);
+	if ((reg & CANCTRL_REQOP_MASK) != CANCTRL_REQOP_CONF)
+		return -ENODEV;
 
-	/* Wait for reset to finish */
-	timeout = jiffies + HZ;
-	mdelay(10);
-	while ((mcp251x_read_reg(spi, CANSTAT) & CANCTRL_REQOP_MASK)
-	       != CANCTRL_REQOP_CONF) {
-		schedule();
-		if (time_after(jiffies, timeout)) {
-			dev_err(&spi->dev, "MCP251x didn't"
-				" enter in conf mode after reset\n");
-			return -EBUSY;
-		}
-	}
 	return 0;
 }
 
 static int mcp251x_hw_probe(struct spi_device *spi)
 {
-	int st1, st2;
+	u8 ctrl;
+	int ret;
 
-	mcp251x_hw_reset(spi);
+	ret = mcp251x_hw_reset(spi);
+	if (ret)
+		return ret;
 
-	/*
-	 * Please note that these are "magic values" based on after
-	 * reset defaults taken from data sheet which allows us to see
-	 * if we really have a chip on the bus (we avoid common all
-	 * zeroes or all ones situations)
-	 */
-	st1 = mcp251x_read_reg(spi, CANSTAT) & 0xEE;
-	st2 = mcp251x_read_reg(spi, CANCTRL) & 0x17;
+	ctrl = mcp251x_read_reg(spi, CANCTRL);
+
+	dev_dbg(&spi->dev, "CANCTRL 0x%02x\n", ctrl);
 
-	dev_dbg(&spi->dev, "CANSTAT 0x%02x CANCTRL 0x%02x\n", st1, st2);
+	/* Check for power up default value */
+	if ((ctrl & 0x17) != 0x07)
+		return -ENODEV;
 
-	/* Check for power up default values */
-	return (st1 == 0x80 && st2 == 0x07) ? 1 : 0;
+	return 0;
 }
 
 static int mcp251x_power_enable(struct regulator *reg, int enable)
@@ -776,7 +773,6 @@ static void mcp251x_restart_work_handler(struct work_struct *ws)
 
 	mutex_lock(&priv->mcp_lock);
 	if (priv->after_suspend) {
-		mdelay(10);
 		mcp251x_hw_reset(spi);
 		mcp251x_setup(net, priv, spi);
 		if (priv->after_suspend & AFTER_SUSPEND_RESTART) {
@@ -955,7 +951,7 @@ static int mcp251x_open(struct net_device *net)
 	priv->tx_len = 0;
 
 	ret = request_threaded_irq(spi->irq, NULL, mcp251x_can_ist,
-				   flags, DEVICE_NAME, priv);
+				   flags | IRQF_ONESHOT, DEVICE_NAME, priv);
 	if (ret) {
 		dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq);
 		mcp251x_power_enable(priv->transceiver, 0);
@@ -1032,8 +1028,8 @@ static int mcp251x_can_probe(struct spi_device *spi)
 	struct mcp251x_platform_data *pdata = dev_get_platdata(&spi->dev);
 	struct net_device *net;
 	struct mcp251x_priv *priv;
-	int freq, ret = -ENODEV;
 	struct clk *clk;
+	int freq, ret;
 
 	clk = devm_clk_get(&spi->dev, NULL);
 	if (IS_ERR(clk)) {
@@ -1076,6 +1072,18 @@ static int mcp251x_can_probe(struct spi_device *spi)
 	priv->net = net;
 	priv->clk = clk;
 
+	spi_set_drvdata(spi, priv);
+
+	/* Configure the SPI bus */
+	spi->bits_per_word = 8;
+	if (mcp251x_is_2510(spi))
+		spi->max_speed_hz = spi->max_speed_hz ? : 5 * 1000 * 1000;
+	else
+		spi->max_speed_hz = spi->max_speed_hz ? : 10 * 1000 * 1000;
+	ret = spi_setup(spi);
+	if (ret)
+		goto out_clk;
+
 	priv->power = devm_regulator_get(&spi->dev, "vdd");
 	priv->transceiver = devm_regulator_get(&spi->dev, "xceiver");
 	if ((PTR_ERR(priv->power) == -EPROBE_DEFER) ||
@@ -1088,8 +1096,6 @@ static int mcp251x_can_probe(struct spi_device *spi)
 	if (ret)
 		goto out_clk;
 
-	spi_set_drvdata(spi, priv);
-
 	priv->spi = spi;
 	mutex_init(&priv->mcp_lock);
 
@@ -1134,20 +1140,11 @@ static int mcp251x_can_probe(struct spi_device *spi)
 
 	SET_NETDEV_DEV(net, &spi->dev);
 
-	/* Configure the SPI bus */
-	spi->mode = spi->mode ? : SPI_MODE_0;
-	if (mcp251x_is_2510(spi))
-		spi->max_speed_hz = spi->max_speed_hz ? : 5 * 1000 * 1000;
-	else
-		spi->max_speed_hz = spi->max_speed_hz ? : 10 * 1000 * 1000;
-	spi->bits_per_word = 8;
-	spi_setup(spi);
-
 	/* Here is OK to not lock the MCP, no one knows about it yet */
-	if (!mcp251x_hw_probe(spi)) {
-		ret = -ENODEV;
+	ret = mcp251x_hw_probe(spi);
+	if (ret)
 		goto error_probe;
-	}
+
 	mcp251x_hw_sleep(spi);
 
 	ret = register_candev(net);
@@ -1156,7 +1153,7 @@ static int mcp251x_can_probe(struct spi_device *spi)
 
 	devm_can_led_init(net);
 
-	return ret;
+	return 0;
 
 error_probe:
 	if (mcp251x_enable_dma)
diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index fc96a3d83eb..a77db919363 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -13,13 +13,21 @@ config CAN_ESD_USB2
           This driver supports the CAN-USB/2 interface
           from esd electronic system design gmbh (http://www.esd.eu).
 
+config CAN_GS_USB
+	tristate "Geschwister Schneider UG interfaces"
+	---help---
+	  This driver supports the Geschwister Schneider USB/CAN devices.
+	  If unsure choose N,
+	  choose Y for built in support,
+	  M to compile as module (module will be named: gs_usb).
+
 config CAN_KVASER_USB
 	tristate "Kvaser CAN/USB interface"
 	---help---
 	  This driver adds support for Kvaser CAN/USB devices like Kvaser
 	  Leaf Light.
 
-	  The driver gives support for the following devices:
+	  The driver provides support for the following devices:
 	    - Kvaser Leaf Light
 	    - Kvaser Leaf Professional HS
 	    - Kvaser Leaf SemiPro HS
@@ -36,6 +44,8 @@ config CAN_KVASER_USB
 	    - Kvaser Leaf Light "China"
 	    - Kvaser BlackBird SemiPro
 	    - Kvaser USBcan R
+	    - Kvaser Leaf Light v2
+	    - Kvaser Mini PCI Express HS
 
 	  If unsure, say N.
 
diff --git a/drivers/net/can/usb/Makefile b/drivers/net/can/usb/Makefile
index becef460a91..7b9a393b1ac 100644
--- a/drivers/net/can/usb/Makefile
+++ b/drivers/net/can/usb/Makefile
@@ -4,6 +4,7 @@
 
 obj-$(CONFIG_CAN_EMS_USB) += ems_usb.o
 obj-$(CONFIG_CAN_ESD_USB2) += esd_usb2.o
+obj-$(CONFIG_CAN_GS_USB) += gs_usb.o
 obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
 obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/
 obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
new file mode 100644
index 00000000000..04b0f84612f
--- /dev/null
+++ b/drivers/net/can/usb/gs_usb.c
@@ -0,0 +1,971 @@
+/* CAN driver for Geschwister Schneider USB/CAN devices.
+ *
+ * Copyright (C) 2013 Geschwister Schneider Technologie-,
+ * Entwicklungs- und Vertriebs UG (Haftungsbeschränkt).
+ *
+ * Many thanks to all socketcan devs!
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/signal.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+
+/* Device specific constants */
+#define USB_GSUSB_1_VENDOR_ID      0x1d50
+#define USB_GSUSB_1_PRODUCT_ID     0x606f
+
+#define GSUSB_ENDPOINT_IN          1
+#define GSUSB_ENDPOINT_OUT         2
+
+/* Device specific constants */
+enum gs_usb_breq {
+	GS_USB_BREQ_HOST_FORMAT = 0,
+	GS_USB_BREQ_BITTIMING,
+	GS_USB_BREQ_MODE,
+	GS_USB_BREQ_BERR,
+	GS_USB_BREQ_BT_CONST,
+	GS_USB_BREQ_DEVICE_CONFIG
+};
+
+enum gs_can_mode {
+	/* reset a channel. turns it off */
+	GS_CAN_MODE_RESET = 0,
+	/* starts a channel */
+	GS_CAN_MODE_START
+};
+
+enum gs_can_state {
+	GS_CAN_STATE_ERROR_ACTIVE = 0,
+	GS_CAN_STATE_ERROR_WARNING,
+	GS_CAN_STATE_ERROR_PASSIVE,
+	GS_CAN_STATE_BUS_OFF,
+	GS_CAN_STATE_STOPPED,
+	GS_CAN_STATE_SLEEPING
+};
+
+/* data types passed between host and device */
+struct gs_host_config {
+	u32 byte_order;
+} __packed;
+/* All data exchanged between host and device is exchanged in host byte order,
+ * thanks to the struct gs_host_config byte_order member, which is sent first
+ * to indicate the desired byte order.
+ */
+
+struct gs_device_config {
+	u8 reserved1;
+	u8 reserved2;
+	u8 reserved3;
+	u8 icount;
+	u32 sw_version;
+	u32 hw_version;
+} __packed;
+
+#define GS_CAN_MODE_NORMAL               0
+#define GS_CAN_MODE_LISTEN_ONLY          (1<<0)
+#define GS_CAN_MODE_LOOP_BACK            (1<<1)
+#define GS_CAN_MODE_TRIPLE_SAMPLE        (1<<2)
+#define GS_CAN_MODE_ONE_SHOT             (1<<3)
+
+struct gs_device_mode {
+	u32 mode;
+	u32 flags;
+} __packed;
+
+struct gs_device_state {
+	u32 state;
+	u32 rxerr;
+	u32 txerr;
+} __packed;
+
+struct gs_device_bittiming {
+	u32 prop_seg;
+	u32 phase_seg1;
+	u32 phase_seg2;
+	u32 sjw;
+	u32 brp;
+} __packed;
+
+#define GS_CAN_FEATURE_LISTEN_ONLY      (1<<0)
+#define GS_CAN_FEATURE_LOOP_BACK        (1<<1)
+#define GS_CAN_FEATURE_TRIPLE_SAMPLE    (1<<2)
+#define GS_CAN_FEATURE_ONE_SHOT         (1<<3)
+
+struct gs_device_bt_const {
+	u32 feature;
+	u32 fclk_can;
+	u32 tseg1_min;
+	u32 tseg1_max;
+	u32 tseg2_min;
+	u32 tseg2_max;
+	u32 sjw_max;
+	u32 brp_min;
+	u32 brp_max;
+	u32 brp_inc;
+} __packed;
+
+#define GS_CAN_FLAG_OVERFLOW 1
+
+struct gs_host_frame {
+	u32 echo_id;
+	u32 can_id;
+
+	u8 can_dlc;
+	u8 channel;
+	u8 flags;
+	u8 reserved;
+
+	u8 data[8];
+} __packed;
+/* The GS USB devices make use of the same flags and masks as in
+ * linux/can.h and linux/can/error.h, and no additional mapping is necessary.
+ */
+
+/* Only send a max of GS_MAX_TX_URBS frames per channel at a time. */
+#define GS_MAX_TX_URBS 10
+/* Only launch a max of GS_MAX_RX_URBS usb requests at a time. */
+#define GS_MAX_RX_URBS 30
+/* Maximum number of interfaces the driver supports per device.
+ * Current hardware only supports 2 interfaces. The future may vary.
+ */
+#define GS_MAX_INTF 2
+
+struct gs_tx_context {
+	struct gs_can *dev;
+	unsigned int echo_id;
+};
+
+struct gs_can {
+	struct can_priv can; /* must be the first member */
+
+	struct gs_usb *parent;
+
+	struct net_device *netdev;
+	struct usb_device *udev;
+	struct usb_interface *iface;
+
+	struct can_bittiming_const bt_const;
+	unsigned int channel;	/* channel number */
+
+	/* This lock prevents a race condition between xmit and recieve. */
+	spinlock_t tx_ctx_lock;
+	struct gs_tx_context tx_context[GS_MAX_TX_URBS];
+
+	struct usb_anchor tx_submitted;
+	atomic_t active_tx_urbs;
+};
+
+/* usb interface struct */
+struct gs_usb {
+	struct gs_can *canch[GS_MAX_INTF];
+	struct usb_anchor rx_submitted;
+	atomic_t active_channels;
+	struct usb_device *udev;
+};
+
+/* 'allocate' a tx context.
+ * returns a valid tx context or NULL if there is no space.
+ */
+static struct gs_tx_context *gs_alloc_tx_context(struct gs_can *dev)
+{
+	int i = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->tx_ctx_lock, flags);
+
+	for (; i < GS_MAX_TX_URBS; i++) {
+		if (dev->tx_context[i].echo_id == GS_MAX_TX_URBS) {
+			dev->tx_context[i].echo_id = i;
+			spin_unlock_irqrestore(&dev->tx_ctx_lock, flags);
+			return &dev->tx_context[i];
+		}
+	}
+
+	spin_unlock_irqrestore(&dev->tx_ctx_lock, flags);
+	return NULL;
+}
+
+/* releases a tx context
+ */
+static void gs_free_tx_context(struct gs_tx_context *txc)
+{
+	txc->echo_id = GS_MAX_TX_URBS;
+}
+
+/* Get a tx context by id.
+ */
+static struct gs_tx_context *gs_get_tx_context(struct gs_can *dev, unsigned int id)
+{
+	unsigned long flags;
+
+	if (id < GS_MAX_TX_URBS) {
+		spin_lock_irqsave(&dev->tx_ctx_lock, flags);
+		if (dev->tx_context[id].echo_id == id) {
+			spin_unlock_irqrestore(&dev->tx_ctx_lock, flags);
+			return &dev->tx_context[id];
+		}
+		spin_unlock_irqrestore(&dev->tx_ctx_lock, flags);
+	}
+	return NULL;
+}
+
+static int gs_cmd_reset(struct gs_usb *gsusb, struct gs_can *gsdev)
+{
+	struct gs_device_mode *dm;
+	struct usb_interface *intf = gsdev->iface;
+	int rc;
+
+	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
+	if (!dm)
+		return -ENOMEM;
+
+	dm->mode = GS_CAN_MODE_RESET;
+
+	rc = usb_control_msg(interface_to_usbdev(intf),
+			     usb_sndctrlpipe(interface_to_usbdev(intf), 0),
+			     GS_USB_BREQ_MODE,
+			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     gsdev->channel,
+			     0,
+			     dm,
+			     sizeof(*dm),
+			     1000);
+
+	return rc;
+}
+
+static void gs_update_state(struct gs_can *dev, struct can_frame *cf)
+{
+	struct can_device_stats *can_stats = &dev->can.can_stats;
+
+	if (cf->can_id & CAN_ERR_RESTARTED) {
+		dev->can.state = CAN_STATE_ERROR_ACTIVE;
+		can_stats->restarts++;
+	} else if (cf->can_id & CAN_ERR_BUSOFF) {
+		dev->can.state = CAN_STATE_BUS_OFF;
+		can_stats->bus_off++;
+	} else if (cf->can_id & CAN_ERR_CRTL) {
+		if ((cf->data[1] & CAN_ERR_CRTL_TX_WARNING) ||
+		    (cf->data[1] & CAN_ERR_CRTL_RX_WARNING)) {
+			dev->can.state = CAN_STATE_ERROR_WARNING;
+			can_stats->error_warning++;
+		} else if ((cf->data[1] & CAN_ERR_CRTL_TX_PASSIVE) ||
+			   (cf->data[1] & CAN_ERR_CRTL_RX_PASSIVE)) {
+			dev->can.state = CAN_STATE_ERROR_PASSIVE;
+			can_stats->error_passive++;
+		} else {
+			dev->can.state = CAN_STATE_ERROR_ACTIVE;
+		}
+	}
+}
+
+static void gs_usb_recieve_bulk_callback(struct urb *urb)
+{
+	struct gs_usb *usbcan = urb->context;
+	struct gs_can *dev;
+	struct net_device *netdev;
+	int rc;
+	struct net_device_stats *stats;
+	struct gs_host_frame *hf = urb->transfer_buffer;
+	struct gs_tx_context *txc;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+
+	BUG_ON(!usbcan);
+
+	switch (urb->status) {
+	case 0: /* success */
+		break;
+	case -ENOENT:
+	case -ESHUTDOWN:
+		return;
+	default:
+		/* do not resubmit aborted urbs. eg: when device goes down */
+		return;
+	}
+
+	/* device reports out of range channel id */
+	if (hf->channel >= GS_MAX_INTF)
+		goto resubmit_urb;
+
+	dev = usbcan->canch[hf->channel];
+
+	netdev = dev->netdev;
+	stats = &netdev->stats;
+
+	if (!netif_device_present(netdev))
+		return;
+
+	if (hf->echo_id == -1) { /* normal rx */
+		skb = alloc_can_skb(dev->netdev, &cf);
+		if (!skb)
+			return;
+
+		cf->can_id = hf->can_id;
+
+		cf->can_dlc = get_can_dlc(hf->can_dlc);
+		memcpy(cf->data, hf->data, 8);
+
+		/* ERROR frames tell us information about the controller */
+		if (hf->can_id & CAN_ERR_FLAG)
+			gs_update_state(dev, cf);
+
+		netdev->stats.rx_packets++;
+		netdev->stats.rx_bytes += hf->can_dlc;
+
+		netif_rx(skb);
+	} else { /* echo_id == hf->echo_id */
+		if (hf->echo_id >= GS_MAX_TX_URBS) {
+			netdev_err(netdev,
+				   "Unexpected out of range echo id %d\n",
+				   hf->echo_id);
+			goto resubmit_urb;
+		}
+
+		netdev->stats.tx_packets++;
+		netdev->stats.tx_bytes += hf->can_dlc;
+
+		txc = gs_get_tx_context(dev, hf->echo_id);
+
+		/* bad devices send bad echo_ids. */
+		if (!txc) {
+			netdev_err(netdev,
+				   "Unexpected unused echo id %d\n",
+				   hf->echo_id);
+			goto resubmit_urb;
+		}
+
+		can_get_echo_skb(netdev, hf->echo_id);
+
+		gs_free_tx_context(txc);
+
+		netif_wake_queue(netdev);
+	}
+
+	if (hf->flags & GS_CAN_FLAG_OVERFLOW) {
+		skb = alloc_can_err_skb(netdev, &cf);
+		if (!skb)
+			goto resubmit_urb;
+
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->can_dlc = CAN_ERR_DLC;
+		cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
+		stats->rx_over_errors++;
+		stats->rx_errors++;
+		netif_rx(skb);
+	}
+
+ resubmit_urb:
+	usb_fill_bulk_urb(urb,
+			  usbcan->udev,
+			  usb_rcvbulkpipe(usbcan->udev, GSUSB_ENDPOINT_IN),
+			  hf,
+			  sizeof(struct gs_host_frame),
+			  gs_usb_recieve_bulk_callback,
+			  usbcan
+			  );
+
+	rc = usb_submit_urb(urb, GFP_ATOMIC);
+
+	/* USB failure take down all interfaces */
+	if (rc == -ENODEV) {
+		for (rc = 0; rc < GS_MAX_INTF; rc++) {
+			if (usbcan->canch[rc])
+				netif_device_detach(usbcan->canch[rc]->netdev);
+		}
+	}
+}
+
+static int gs_usb_set_bittiming(struct net_device *netdev)
+{
+	struct gs_can *dev = netdev_priv(netdev);
+	struct can_bittiming *bt = &dev->can.bittiming;
+	struct usb_interface *intf = dev->iface;
+	int rc;
+	struct gs_device_bittiming *dbt;
+
+	dbt = kmalloc(sizeof(*dbt), GFP_KERNEL);
+	if (!dbt)
+		return -ENOMEM;
+
+	dbt->prop_seg = bt->prop_seg;
+	dbt->phase_seg1 = bt->phase_seg1;
+	dbt->phase_seg2 = bt->phase_seg2;
+	dbt->sjw = bt->sjw;
+	dbt->brp = bt->brp;
+
+	/* request bit timings */
+	rc = usb_control_msg(interface_to_usbdev(intf),
+			     usb_sndctrlpipe(interface_to_usbdev(intf), 0),
+			     GS_USB_BREQ_BITTIMING,
+			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     dev->channel,
+			     0,
+			     dbt,
+			     sizeof(*dbt),
+			     1000);
+
+	kfree(dbt);
+
+	if (rc < 0)
+		dev_err(netdev->dev.parent, "Couldn't set bittimings (err=%d)",
+			rc);
+
+	return rc;
+}
+
+static void gs_usb_xmit_callback(struct urb *urb)
+{
+	struct gs_tx_context *txc = urb->context;
+	struct gs_can *dev = txc->dev;
+	struct net_device *netdev = dev->netdev;
+
+	if (urb->status)
+		netdev_info(netdev, "usb xmit fail %d\n", txc->echo_id);
+
+	usb_free_coherent(urb->dev,
+			  urb->transfer_buffer_length,
+			  urb->transfer_buffer,
+			  urb->transfer_dma);
+
+	atomic_dec(&dev->active_tx_urbs);
+
+	if (!netif_device_present(netdev))
+		return;
+
+	if (netif_queue_stopped(netdev))
+		netif_wake_queue(netdev);
+}
+
+static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct gs_can *dev = netdev_priv(netdev);
+	struct net_device_stats *stats = &dev->netdev->stats;
+	struct urb *urb;
+	struct gs_host_frame *hf;
+	struct can_frame *cf;
+	int rc;
+	unsigned int idx;
+	struct gs_tx_context *txc;
+
+	if (can_dropped_invalid_skb(netdev, skb))
+		return NETDEV_TX_OK;
+
+	/* find an empty context to keep track of transmission */
+	txc = gs_alloc_tx_context(dev);
+	if (!txc)
+		return NETDEV_TX_BUSY;
+
+	/* create a URB, and a buffer for it */
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb) {
+		netdev_err(netdev, "No memory left for URB\n");
+		goto nomem_urb;
+	}
+
+	hf = usb_alloc_coherent(dev->udev, sizeof(*hf), GFP_ATOMIC,
+				&urb->transfer_dma);
+	if (!hf) {
+		netdev_err(netdev, "No memory left for USB buffer\n");
+		goto nomem_hf;
+	}
+
+	idx = txc->echo_id;
+
+	if (idx >= GS_MAX_TX_URBS) {
+		netdev_err(netdev, "Invalid tx context %d\n", idx);
+		goto badidx;
+	}
+
+	hf->echo_id = idx;
+	hf->channel = dev->channel;
+
+	cf = (struct can_frame *)skb->data;
+
+	hf->can_id = cf->can_id;
+	hf->can_dlc = cf->can_dlc;
+	memcpy(hf->data, cf->data, cf->can_dlc);
+
+	usb_fill_bulk_urb(urb, dev->udev,
+			  usb_sndbulkpipe(dev->udev, GSUSB_ENDPOINT_OUT),
+			  hf,
+			  sizeof(*hf),
+			  gs_usb_xmit_callback,
+			  txc);
+
+	urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+	usb_anchor_urb(urb, &dev->tx_submitted);
+
+	can_put_echo_skb(skb, netdev, idx);
+
+	atomic_inc(&dev->active_tx_urbs);
+
+	rc = usb_submit_urb(urb, GFP_ATOMIC);
+	if (unlikely(rc)) {			/* usb send failed */
+		atomic_dec(&dev->active_tx_urbs);
+
+		can_free_echo_skb(netdev, idx);
+		gs_free_tx_context(txc);
+
+		usb_unanchor_urb(urb);
+		usb_free_coherent(dev->udev,
+				  sizeof(*hf),
+				  hf,
+				  urb->transfer_dma);
+
+
+		if (rc == -ENODEV) {
+			netif_device_detach(netdev);
+		} else {
+			netdev_err(netdev, "usb_submit failed (err=%d)\n", rc);
+			stats->tx_dropped++;
+		}
+	} else {
+		/* Slow down tx path */
+		if (atomic_read(&dev->active_tx_urbs) >= GS_MAX_TX_URBS)
+			netif_stop_queue(netdev);
+	}
+
+	/* let usb core take care of this urb */
+	usb_free_urb(urb);
+
+	return NETDEV_TX_OK;
+
+ badidx:
+	usb_free_coherent(dev->udev,
+			  sizeof(*hf),
+			  hf,
+			  urb->transfer_dma);
+ nomem_hf:
+	usb_free_urb(urb);
+
+ nomem_urb:
+	gs_free_tx_context(txc);
+	dev_kfree_skb(skb);
+	stats->tx_dropped++;
+	return NETDEV_TX_OK;
+}
+
+static int gs_can_open(struct net_device *netdev)
+{
+	struct gs_can *dev = netdev_priv(netdev);
+	struct gs_usb *parent = dev->parent;
+	int rc, i;
+	struct gs_device_mode *dm;
+	u32 ctrlmode;
+
+	rc = open_candev(netdev);
+	if (rc)
+		return rc;
+
+	if (atomic_add_return(1, &parent->active_channels) == 1) {
+		for (i = 0; i < GS_MAX_RX_URBS; i++) {
+			struct urb *urb;
+			u8 *buf;
+
+			/* alloc rx urb */
+			urb = usb_alloc_urb(0, GFP_KERNEL);
+			if (!urb) {
+				netdev_err(netdev,
+					   "No memory left for URB\n");
+				return -ENOMEM;
+			}
+
+			/* alloc rx buffer */
+			buf = usb_alloc_coherent(dev->udev,
+						 sizeof(struct gs_host_frame),
+						 GFP_KERNEL,
+						 &urb->transfer_dma);
+			if (!buf) {
+				netdev_err(netdev,
+					   "No memory left for USB buffer\n");
+				usb_free_urb(urb);
+				return -ENOMEM;
+			}
+
+			/* fill, anchor, and submit rx urb */
+			usb_fill_bulk_urb(urb,
+					  dev->udev,
+					  usb_rcvbulkpipe(dev->udev,
+							  GSUSB_ENDPOINT_IN),
+					  buf,
+					  sizeof(struct gs_host_frame),
+					  gs_usb_recieve_bulk_callback,
+					  parent);
+			urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+
+			usb_anchor_urb(urb, &parent->rx_submitted);
+
+			rc = usb_submit_urb(urb, GFP_KERNEL);
+			if (rc) {
+				if (rc == -ENODEV)
+					netif_device_detach(dev->netdev);
+
+				netdev_err(netdev,
+					   "usb_submit failed (err=%d)\n",
+					   rc);
+
+				usb_unanchor_urb(urb);
+				break;
+			}
+
+			/* Drop reference,
+			 * USB core will take care of freeing it
+			 */
+			usb_free_urb(urb);
+		}
+	}
+
+	dm = kmalloc(sizeof(*dm), GFP_KERNEL);
+	if (!dm)
+		return -ENOMEM;
+
+	/* flags */
+	ctrlmode = dev->can.ctrlmode;
+	dm->flags = 0;
+
+	if (ctrlmode & CAN_CTRLMODE_LOOPBACK)
+		dm->flags |= GS_CAN_MODE_LOOP_BACK;
+	else if (ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		dm->flags |= GS_CAN_MODE_LISTEN_ONLY;
+
+	/* Controller is not allowed to retry TX
+	 * this mode is unavailable on atmels uc3c hardware
+	 */
+	if (ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+		dm->flags |= GS_CAN_MODE_ONE_SHOT;
+
+	if (ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+		dm->flags |= GS_CAN_MODE_TRIPLE_SAMPLE;
+
+	/* finally start device */
+	dm->mode = GS_CAN_MODE_START;
+	rc = usb_control_msg(interface_to_usbdev(dev->iface),
+			     usb_sndctrlpipe(interface_to_usbdev(dev->iface), 0),
+			     GS_USB_BREQ_MODE,
+			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     dev->channel,
+			     0,
+			     dm,
+			     sizeof(*dm),
+			     1000);
+
+	if (rc < 0) {
+		netdev_err(netdev, "Couldn't start device (err=%d)\n", rc);
+		kfree(dm);
+		return rc;
+	}
+
+	kfree(dm);
+
+	dev->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	if (!(dev->can.ctrlmode & CAN_CTRLMODE_LISTENONLY))
+		netif_start_queue(netdev);
+
+	return 0;
+}
+
+static int gs_can_close(struct net_device *netdev)
+{
+	int rc;
+	struct gs_can *dev = netdev_priv(netdev);
+	struct gs_usb *parent = dev->parent;
+
+	netif_stop_queue(netdev);
+
+	/* Stop polling */
+	if (atomic_dec_and_test(&parent->active_channels))
+		usb_kill_anchored_urbs(&parent->rx_submitted);
+
+	/* Stop sending URBs */
+	usb_kill_anchored_urbs(&dev->tx_submitted);
+	atomic_set(&dev->active_tx_urbs, 0);
+
+	/* reset the device */
+	rc = gs_cmd_reset(parent, dev);
+	if (rc < 0)
+		netdev_warn(netdev, "Couldn't shutdown device (err=%d)", rc);
+
+	/* reset tx contexts */
+	for (rc = 0; rc < GS_MAX_TX_URBS; rc++) {
+		dev->tx_context[rc].dev = dev;
+		dev->tx_context[rc].echo_id = GS_MAX_TX_URBS;
+	}
+
+	/* close the netdev */
+	close_candev(netdev);
+
+	return 0;
+}
+
+static const struct net_device_ops gs_usb_netdev_ops = {
+	.ndo_open = gs_can_open,
+	.ndo_stop = gs_can_close,
+	.ndo_start_xmit = gs_can_start_xmit,
+};
+
+static struct gs_can *gs_make_candev(unsigned int channel, struct usb_interface *intf)
+{
+	struct gs_can *dev;
+	struct net_device *netdev;
+	int rc;
+	struct gs_device_bt_const *bt_const;
+
+	bt_const = kmalloc(sizeof(*bt_const), GFP_KERNEL);
+	if (!bt_const)
+		return ERR_PTR(-ENOMEM);
+
+	/* fetch bit timing constants */
+	rc = usb_control_msg(interface_to_usbdev(intf),
+			     usb_rcvctrlpipe(interface_to_usbdev(intf), 0),
+			     GS_USB_BREQ_BT_CONST,
+			     USB_DIR_IN|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     channel,
+			     0,
+			     bt_const,
+			     sizeof(*bt_const),
+			     1000);
+
+	if (rc < 0) {
+		dev_err(&intf->dev,
+			"Couldn't get bit timing const for channel (err=%d)\n",
+			rc);
+		kfree(bt_const);
+		return ERR_PTR(rc);
+	}
+
+	/* create netdev */
+	netdev = alloc_candev(sizeof(struct gs_can), GS_MAX_TX_URBS);
+	if (!netdev) {
+		dev_err(&intf->dev, "Couldn't allocate candev\n");
+		kfree(bt_const);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	dev = netdev_priv(netdev);
+
+	netdev->netdev_ops = &gs_usb_netdev_ops;
+
+	netdev->flags |= IFF_ECHO; /* we support full roundtrip echo */
+
+	/* dev settup */
+	strcpy(dev->bt_const.name, "gs_usb");
+	dev->bt_const.tseg1_min = bt_const->tseg1_min;
+	dev->bt_const.tseg1_max = bt_const->tseg1_max;
+	dev->bt_const.tseg2_min = bt_const->tseg2_min;
+	dev->bt_const.tseg2_max = bt_const->tseg2_max;
+	dev->bt_const.sjw_max = bt_const->sjw_max;
+	dev->bt_const.brp_min = bt_const->brp_min;
+	dev->bt_const.brp_max = bt_const->brp_max;
+	dev->bt_const.brp_inc = bt_const->brp_inc;
+
+	dev->udev = interface_to_usbdev(intf);
+	dev->iface = intf;
+	dev->netdev = netdev;
+	dev->channel = channel;
+
+	init_usb_anchor(&dev->tx_submitted);
+	atomic_set(&dev->active_tx_urbs, 0);
+	spin_lock_init(&dev->tx_ctx_lock);
+	for (rc = 0; rc < GS_MAX_TX_URBS; rc++) {
+		dev->tx_context[rc].dev = dev;
+		dev->tx_context[rc].echo_id = GS_MAX_TX_URBS;
+	}
+
+	/* can settup */
+	dev->can.state = CAN_STATE_STOPPED;
+	dev->can.clock.freq = bt_const->fclk_can;
+	dev->can.bittiming_const = &dev->bt_const;
+	dev->can.do_set_bittiming = gs_usb_set_bittiming;
+
+	dev->can.ctrlmode_supported = 0;
+
+	if (bt_const->feature & GS_CAN_FEATURE_LISTEN_ONLY)
+		dev->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
+
+	if (bt_const->feature & GS_CAN_FEATURE_LOOP_BACK)
+		dev->can.ctrlmode_supported |= CAN_CTRLMODE_LOOPBACK;
+
+	if (bt_const->feature & GS_CAN_FEATURE_TRIPLE_SAMPLE)
+		dev->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
+
+	if (bt_const->feature & GS_CAN_FEATURE_ONE_SHOT)
+		dev->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT;
+
+	kfree(bt_const);
+
+	SET_NETDEV_DEV(netdev, &intf->dev);
+
+	rc = register_candev(dev->netdev);
+	if (rc) {
+		free_candev(dev->netdev);
+		dev_err(&intf->dev, "Couldn't register candev (err=%d)\n", rc);
+		return ERR_PTR(rc);
+	}
+
+	return dev;
+}
+
+static void gs_destroy_candev(struct gs_can *dev)
+{
+	unregister_candev(dev->netdev);
+	free_candev(dev->netdev);
+	usb_kill_anchored_urbs(&dev->tx_submitted);
+	kfree(dev);
+}
+
+static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
+{
+	struct gs_usb *dev;
+	int rc = -ENOMEM;
+	unsigned int icount, i;
+	struct gs_host_config *hconf;
+	struct gs_device_config *dconf;
+
+	hconf = kmalloc(sizeof(*hconf), GFP_KERNEL);
+	if (!hconf)
+		return -ENOMEM;
+
+	hconf->byte_order = 0x0000beef;
+
+	/* send host config */
+	rc = usb_control_msg(interface_to_usbdev(intf),
+			     usb_sndctrlpipe(interface_to_usbdev(intf), 0),
+			     GS_USB_BREQ_HOST_FORMAT,
+			     USB_DIR_OUT|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     1,
+			     intf->altsetting[0].desc.bInterfaceNumber,
+			     hconf,
+			     sizeof(*hconf),
+			     1000);
+
+	kfree(hconf);
+
+	if (rc < 0) {
+		dev_err(&intf->dev, "Couldn't send data format (err=%d)\n",
+			rc);
+		return rc;
+	}
+
+	dconf = kmalloc(sizeof(*dconf), GFP_KERNEL);
+	if (!dconf)
+		return -ENOMEM;
+
+	/* read device config */
+	rc = usb_control_msg(interface_to_usbdev(intf),
+			     usb_rcvctrlpipe(interface_to_usbdev(intf), 0),
+			     GS_USB_BREQ_DEVICE_CONFIG,
+			     USB_DIR_IN|USB_TYPE_VENDOR|USB_RECIP_INTERFACE,
+			     1,
+			     intf->altsetting[0].desc.bInterfaceNumber,
+			     dconf,
+			     sizeof(*dconf),
+			     1000);
+	if (rc < 0) {
+		dev_err(&intf->dev, "Couldn't get device config: (err=%d)\n",
+			rc);
+
+		kfree(dconf);
+
+		return rc;
+	}
+
+	icount = dconf->icount+1;
+
+	kfree(dconf);
+
+	dev_info(&intf->dev, "Configuring for %d interfaces\n", icount);
+
+	if (icount > GS_MAX_INTF) {
+		dev_err(&intf->dev,
+			"Driver cannot handle more that %d CAN interfaces\n",
+			GS_MAX_INTF);
+		return -EINVAL;
+	}
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	init_usb_anchor(&dev->rx_submitted);
+
+	atomic_set(&dev->active_channels, 0);
+
+	usb_set_intfdata(intf, dev);
+	dev->udev = interface_to_usbdev(intf);
+
+	for (i = 0; i < icount; i++) {
+		dev->canch[i] = gs_make_candev(i, intf);
+		if (IS_ERR_OR_NULL(dev->canch[i])) {
+			/* on failure destroy previously created candevs */
+			icount = i;
+			for (i = 0; i < icount; i++) {
+				gs_destroy_candev(dev->canch[i]);
+				dev->canch[i] = NULL;
+			}
+			kfree(dev);
+			return rc;
+		}
+		dev->canch[i]->parent = dev;
+	}
+
+	return 0;
+}
+
+static void gs_usb_disconnect(struct usb_interface *intf)
+{
+	unsigned i;
+	struct gs_usb *dev = usb_get_intfdata(intf);
+	usb_set_intfdata(intf, NULL);
+
+	if (!dev) {
+		dev_err(&intf->dev, "Disconnect (nodata)\n");
+		return;
+	}
+
+	for (i = 0; i < GS_MAX_INTF; i++) {
+		struct gs_can *can = dev->canch[i];
+
+		if (!can)
+			continue;
+
+		gs_destroy_candev(can);
+	}
+
+	usb_kill_anchored_urbs(&dev->rx_submitted);
+}
+
+static const struct usb_device_id gs_usb_table[] = {
+	{USB_DEVICE(USB_GSUSB_1_VENDOR_ID, USB_GSUSB_1_PRODUCT_ID)},
+	{} /* Terminating entry */
+};
+
+MODULE_DEVICE_TABLE(usb, gs_usb_table);
+
+static struct usb_driver gs_usb_driver = {
+	.name       = "gs_usb",
+	.probe      = gs_usb_probe,
+	.disconnect = gs_usb_disconnect,
+	.id_table   = gs_usb_table,
+};
+
+module_usb_driver(gs_usb_driver);
+
+MODULE_AUTHOR("Maximilian Schneider <mws@schneidersoft.net>");
+MODULE_DESCRIPTION(
+"Socket CAN device driver for Geschwister Schneider Technologie-, "
+"Entwicklungs- und Vertriebs UG. USB2.0 to CAN interfaces.");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 4ca46edc061..541fb7a0562 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -53,6 +53,8 @@
 #define USB_OEM_MERCURY_PRODUCT_ID	34
 #define USB_OEM_LEAF_PRODUCT_ID		35
 #define USB_CAN_R_PRODUCT_ID		39
+#define USB_LEAF_LITE_V2_PRODUCT_ID	288
+#define USB_MINI_PCIE_HS_PRODUCT_ID	289
 
 /* USB devices features */
 #define KVASER_HAS_SILENT_MODE		BIT(0)
@@ -356,6 +358,8 @@ static const struct usb_device_id kvaser_usb_table[] = {
 		.driver_info = KVASER_HAS_TXRX_ERRORS },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_CAN_R_PRODUCT_ID),
 		.driver_info = KVASER_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
@@ -379,38 +383,43 @@ static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id,
 	void *buf;
 	int actual_len;
 	int err;
-	int pos = 0;
+	int pos;
+	unsigned long to = jiffies + msecs_to_jiffies(USB_RECV_TIMEOUT);
 
 	buf = kzalloc(RX_BUFFER_SIZE, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	err = usb_bulk_msg(dev->udev,
-			   usb_rcvbulkpipe(dev->udev,
-					   dev->bulk_in->bEndpointAddress),
-			   buf, RX_BUFFER_SIZE, &actual_len,
-			   USB_RECV_TIMEOUT);
-	if (err < 0)
-		goto end;
+	do {
+		err = usb_bulk_msg(dev->udev,
+				   usb_rcvbulkpipe(dev->udev,
+					dev->bulk_in->bEndpointAddress),
+				   buf, RX_BUFFER_SIZE, &actual_len,
+				   USB_RECV_TIMEOUT);
+		if (err < 0)
+			goto end;
 
-	while (pos <= actual_len - MSG_HEADER_LEN) {
-		tmp = buf + pos;
+		pos = 0;
+		while (pos <= actual_len - MSG_HEADER_LEN) {
+			tmp = buf + pos;
 
-		if (!tmp->len)
-			break;
+			if (!tmp->len)
+				break;
 
-		if (pos + tmp->len > actual_len) {
-			dev_err(dev->udev->dev.parent, "Format error\n");
-			break;
-		}
+			if (pos + tmp->len > actual_len) {
+				dev_err(dev->udev->dev.parent,
+					"Format error\n");
+				break;
+			}
 
-		if (tmp->id == id) {
-			memcpy(msg, tmp, tmp->len);
-			goto end;
-		}
+			if (tmp->id == id) {
+				memcpy(msg, tmp, tmp->len);
+				goto end;
+			}
 
-		pos += tmp->len;
-	}
+			pos += tmp->len;
+		}
+	} while (time_before(jiffies, to));
 
 	err = -EINVAL;
 
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
new file mode 100644
index 00000000000..5e8b5609c06
--- /dev/null
+++ b/drivers/net/can/xilinx_can.c
@@ -0,0 +1,1208 @@
+/* Xilinx CAN device driver
+ *
+ * Copyright (C) 2012 - 2014 Xilinx, Inc.
+ * Copyright (C) 2009 PetaLogix. All rights reserved.
+ *
+ * Description:
+ * This driver is developed for Axi CAN IP and for Zynq CANPS Controller.
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/skbuff.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/led.h>
+
+#define DRIVER_NAME	"xilinx_can"
+
+/* CAN registers set */
+enum xcan_reg {
+	XCAN_SRR_OFFSET		= 0x00, /* Software reset */
+	XCAN_MSR_OFFSET		= 0x04, /* Mode select */
+	XCAN_BRPR_OFFSET	= 0x08, /* Baud rate prescaler */
+	XCAN_BTR_OFFSET		= 0x0C, /* Bit timing */
+	XCAN_ECR_OFFSET		= 0x10, /* Error counter */
+	XCAN_ESR_OFFSET		= 0x14, /* Error status */
+	XCAN_SR_OFFSET		= 0x18, /* Status */
+	XCAN_ISR_OFFSET		= 0x1C, /* Interrupt status */
+	XCAN_IER_OFFSET		= 0x20, /* Interrupt enable */
+	XCAN_ICR_OFFSET		= 0x24, /* Interrupt clear */
+	XCAN_TXFIFO_ID_OFFSET	= 0x30,/* TX FIFO ID */
+	XCAN_TXFIFO_DLC_OFFSET	= 0x34, /* TX FIFO DLC */
+	XCAN_TXFIFO_DW1_OFFSET	= 0x38, /* TX FIFO Data Word 1 */
+	XCAN_TXFIFO_DW2_OFFSET	= 0x3C, /* TX FIFO Data Word 2 */
+	XCAN_RXFIFO_ID_OFFSET	= 0x50, /* RX FIFO ID */
+	XCAN_RXFIFO_DLC_OFFSET	= 0x54, /* RX FIFO DLC */
+	XCAN_RXFIFO_DW1_OFFSET	= 0x58, /* RX FIFO Data Word 1 */
+	XCAN_RXFIFO_DW2_OFFSET	= 0x5C, /* RX FIFO Data Word 2 */
+};
+
+/* CAN register bit masks - XCAN_<REG>_<BIT>_MASK */
+#define XCAN_SRR_CEN_MASK		0x00000002 /* CAN enable */
+#define XCAN_SRR_RESET_MASK		0x00000001 /* Soft Reset the CAN core */
+#define XCAN_MSR_LBACK_MASK		0x00000002 /* Loop back mode select */
+#define XCAN_MSR_SLEEP_MASK		0x00000001 /* Sleep mode select */
+#define XCAN_BRPR_BRP_MASK		0x000000FF /* Baud rate prescaler */
+#define XCAN_BTR_SJW_MASK		0x00000180 /* Synchronous jump width */
+#define XCAN_BTR_TS2_MASK		0x00000070 /* Time segment 2 */
+#define XCAN_BTR_TS1_MASK		0x0000000F /* Time segment 1 */
+#define XCAN_ECR_REC_MASK		0x0000FF00 /* Receive error counter */
+#define XCAN_ECR_TEC_MASK		0x000000FF /* Transmit error counter */
+#define XCAN_ESR_ACKER_MASK		0x00000010 /* ACK error */
+#define XCAN_ESR_BERR_MASK		0x00000008 /* Bit error */
+#define XCAN_ESR_STER_MASK		0x00000004 /* Stuff error */
+#define XCAN_ESR_FMER_MASK		0x00000002 /* Form error */
+#define XCAN_ESR_CRCER_MASK		0x00000001 /* CRC error */
+#define XCAN_SR_TXFLL_MASK		0x00000400 /* TX FIFO is full */
+#define XCAN_SR_ESTAT_MASK		0x00000180 /* Error status */
+#define XCAN_SR_ERRWRN_MASK		0x00000040 /* Error warning */
+#define XCAN_SR_NORMAL_MASK		0x00000008 /* Normal mode */
+#define XCAN_SR_LBACK_MASK		0x00000002 /* Loop back mode */
+#define XCAN_SR_CONFIG_MASK		0x00000001 /* Configuration mode */
+#define XCAN_IXR_TXFEMP_MASK		0x00004000 /* TX FIFO Empty */
+#define XCAN_IXR_WKUP_MASK		0x00000800 /* Wake up interrupt */
+#define XCAN_IXR_SLP_MASK		0x00000400 /* Sleep interrupt */
+#define XCAN_IXR_BSOFF_MASK		0x00000200 /* Bus off interrupt */
+#define XCAN_IXR_ERROR_MASK		0x00000100 /* Error interrupt */
+#define XCAN_IXR_RXNEMP_MASK		0x00000080 /* RX FIFO NotEmpty intr */
+#define XCAN_IXR_RXOFLW_MASK		0x00000040 /* RX FIFO Overflow intr */
+#define XCAN_IXR_RXOK_MASK		0x00000010 /* Message received intr */
+#define XCAN_IXR_TXFLL_MASK		0x00000004 /* Tx FIFO Full intr */
+#define XCAN_IXR_TXOK_MASK		0x00000002 /* TX successful intr */
+#define XCAN_IXR_ARBLST_MASK		0x00000001 /* Arbitration lost intr */
+#define XCAN_IDR_ID1_MASK		0xFFE00000 /* Standard msg identifier */
+#define XCAN_IDR_SRR_MASK		0x00100000 /* Substitute remote TXreq */
+#define XCAN_IDR_IDE_MASK		0x00080000 /* Identifier extension */
+#define XCAN_IDR_ID2_MASK		0x0007FFFE /* Extended message ident */
+#define XCAN_IDR_RTR_MASK		0x00000001 /* Remote TX request */
+#define XCAN_DLCR_DLC_MASK		0xF0000000 /* Data length code */
+
+#define XCAN_INTR_ALL		(XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\
+				 XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \
+				 XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \
+				 XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK)
+
+/* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */
+#define XCAN_BTR_SJW_SHIFT		7  /* Synchronous jump width */
+#define XCAN_BTR_TS2_SHIFT		4  /* Time segment 2 */
+#define XCAN_IDR_ID1_SHIFT		21 /* Standard Messg Identifier */
+#define XCAN_IDR_ID2_SHIFT		1  /* Extended Message Identifier */
+#define XCAN_DLCR_DLC_SHIFT		28 /* Data length code */
+#define XCAN_ESR_REC_SHIFT		8  /* Rx Error Count */
+
+/* CAN frame length constants */
+#define XCAN_FRAME_MAX_DATA_LEN		8
+#define XCAN_TIMEOUT			(1 * HZ)
+
+/**
+ * struct xcan_priv - This definition define CAN driver instance
+ * @can:			CAN private data structure.
+ * @tx_head:			Tx CAN packets ready to send on the queue
+ * @tx_tail:			Tx CAN packets successfully sended on the queue
+ * @tx_max:			Maximum number packets the driver can send
+ * @napi:			NAPI structure
+ * @read_reg:			For reading data from CAN registers
+ * @write_reg:			For writing data to CAN registers
+ * @dev:			Network device data structure
+ * @reg_base:			Ioremapped address to registers
+ * @irq_flags:			For request_irq()
+ * @bus_clk:			Pointer to struct clk
+ * @can_clk:			Pointer to struct clk
+ */
+struct xcan_priv {
+	struct can_priv can;
+	unsigned int tx_head;
+	unsigned int tx_tail;
+	unsigned int tx_max;
+	struct napi_struct napi;
+	u32 (*read_reg)(const struct xcan_priv *priv, enum xcan_reg reg);
+	void (*write_reg)(const struct xcan_priv *priv, enum xcan_reg reg,
+			u32 val);
+	struct net_device *dev;
+	void __iomem *reg_base;
+	unsigned long irq_flags;
+	struct clk *bus_clk;
+	struct clk *can_clk;
+};
+
+/* CAN Bittiming constants as per Xilinx CAN specs */
+static const struct can_bittiming_const xcan_bittiming_const = {
+	.name = DRIVER_NAME,
+	.tseg1_min = 1,
+	.tseg1_max = 16,
+	.tseg2_min = 1,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
+};
+
+/**
+ * xcan_write_reg_le - Write a value to the device register little endian
+ * @priv:	Driver private data structure
+ * @reg:	Register offset
+ * @val:	Value to write at the Register offset
+ *
+ * Write data to the paricular CAN register
+ */
+static void xcan_write_reg_le(const struct xcan_priv *priv, enum xcan_reg reg,
+			u32 val)
+{
+	iowrite32(val, priv->reg_base + reg);
+}
+
+/**
+ * xcan_read_reg_le - Read a value from the device register little endian
+ * @priv:	Driver private data structure
+ * @reg:	Register offset
+ *
+ * Read data from the particular CAN register
+ * Return: value read from the CAN register
+ */
+static u32 xcan_read_reg_le(const struct xcan_priv *priv, enum xcan_reg reg)
+{
+	return ioread32(priv->reg_base + reg);
+}
+
+/**
+ * xcan_write_reg_be - Write a value to the device register big endian
+ * @priv:	Driver private data structure
+ * @reg:	Register offset
+ * @val:	Value to write at the Register offset
+ *
+ * Write data to the paricular CAN register
+ */
+static void xcan_write_reg_be(const struct xcan_priv *priv, enum xcan_reg reg,
+			u32 val)
+{
+	iowrite32be(val, priv->reg_base + reg);
+}
+
+/**
+ * xcan_read_reg_be - Read a value from the device register big endian
+ * @priv:	Driver private data structure
+ * @reg:	Register offset
+ *
+ * Read data from the particular CAN register
+ * Return: value read from the CAN register
+ */
+static u32 xcan_read_reg_be(const struct xcan_priv *priv, enum xcan_reg reg)
+{
+	return ioread32be(priv->reg_base + reg);
+}
+
+/**
+ * set_reset_mode - Resets the CAN device mode
+ * @ndev:	Pointer to net_device structure
+ *
+ * This is the driver reset mode routine.The driver
+ * enters into configuration mode.
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int set_reset_mode(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	unsigned long timeout;
+
+	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
+
+	timeout = jiffies + XCAN_TIMEOUT;
+	while (!(priv->read_reg(priv, XCAN_SR_OFFSET) & XCAN_SR_CONFIG_MASK)) {
+		if (time_after(jiffies, timeout)) {
+			netdev_warn(ndev, "timed out for config mode\n");
+			return -ETIMEDOUT;
+		}
+		usleep_range(500, 10000);
+	}
+
+	return 0;
+}
+
+/**
+ * xcan_set_bittiming - CAN set bit timing routine
+ * @ndev:	Pointer to net_device structure
+ *
+ * This is the driver set bittiming  routine.
+ * Return: 0 on success and failure value on error
+ */
+static int xcan_set_bittiming(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	u32 btr0, btr1;
+	u32 is_config_mode;
+
+	/* Check whether Xilinx CAN is in configuration mode.
+	 * It cannot set bit timing if Xilinx CAN is not in configuration mode.
+	 */
+	is_config_mode = priv->read_reg(priv, XCAN_SR_OFFSET) &
+				XCAN_SR_CONFIG_MASK;
+	if (!is_config_mode) {
+		netdev_alert(ndev,
+		     "BUG! Cannot set bittiming - CAN is not in config mode\n");
+		return -EPERM;
+	}
+
+	/* Setting Baud Rate prescalar value in BRPR Register */
+	btr0 = (bt->brp - 1);
+
+	/* Setting Time Segment 1 in BTR Register */
+	btr1 = (bt->prop_seg + bt->phase_seg1 - 1);
+
+	/* Setting Time Segment 2 in BTR Register */
+	btr1 |= (bt->phase_seg2 - 1) << XCAN_BTR_TS2_SHIFT;
+
+	/* Setting Synchronous jump width in BTR Register */
+	btr1 |= (bt->sjw - 1) << XCAN_BTR_SJW_SHIFT;
+
+	priv->write_reg(priv, XCAN_BRPR_OFFSET, btr0);
+	priv->write_reg(priv, XCAN_BTR_OFFSET, btr1);
+
+	netdev_dbg(ndev, "BRPR=0x%08x, BTR=0x%08x\n",
+			priv->read_reg(priv, XCAN_BRPR_OFFSET),
+			priv->read_reg(priv, XCAN_BTR_OFFSET));
+
+	return 0;
+}
+
+/**
+ * xcan_chip_start - This the drivers start routine
+ * @ndev:	Pointer to net_device structure
+ *
+ * This is the drivers start routine.
+ * Based on the State of the CAN device it puts
+ * the CAN device into a proper mode.
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int xcan_chip_start(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 err, reg_msr, reg_sr_mask;
+	unsigned long timeout;
+
+	/* Check if it is in reset mode */
+	err = set_reset_mode(ndev);
+	if (err < 0)
+		return err;
+
+	err = xcan_set_bittiming(ndev);
+	if (err < 0)
+		return err;
+
+	/* Enable interrupts */
+	priv->write_reg(priv, XCAN_IER_OFFSET, XCAN_INTR_ALL);
+
+	/* Check whether it is loopback mode or normal mode  */
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) {
+		reg_msr = XCAN_MSR_LBACK_MASK;
+		reg_sr_mask = XCAN_SR_LBACK_MASK;
+	} else {
+		reg_msr = 0x0;
+		reg_sr_mask = XCAN_SR_NORMAL_MASK;
+	}
+
+	priv->write_reg(priv, XCAN_MSR_OFFSET, reg_msr);
+	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_CEN_MASK);
+
+	timeout = jiffies + XCAN_TIMEOUT;
+	while (!(priv->read_reg(priv, XCAN_SR_OFFSET) & reg_sr_mask)) {
+		if (time_after(jiffies, timeout)) {
+			netdev_warn(ndev,
+				"timed out for correct mode\n");
+			return -ETIMEDOUT;
+		}
+	}
+	netdev_dbg(ndev, "status:#x%08x\n",
+			priv->read_reg(priv, XCAN_SR_OFFSET));
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	return 0;
+}
+
+/**
+ * xcan_do_set_mode - This sets the mode of the driver
+ * @ndev:	Pointer to net_device structure
+ * @mode:	Tells the mode of the driver
+ *
+ * This check the drivers state and calls the
+ * the corresponding modes to set.
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int xcan_do_set_mode(struct net_device *ndev, enum can_mode mode)
+{
+	int ret;
+
+	switch (mode) {
+	case CAN_MODE_START:
+		ret = xcan_chip_start(ndev);
+		if (ret < 0) {
+			netdev_err(ndev, "xcan_chip_start failed!\n");
+			return ret;
+		}
+		netif_wake_queue(ndev);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
+
+/**
+ * xcan_start_xmit - Starts the transmission
+ * @skb:	sk_buff pointer that contains data to be Txed
+ * @ndev:	Pointer to net_device structure
+ *
+ * This function is invoked from upper layers to initiate transmission. This
+ * function uses the next available free txbuff and populates their fields to
+ * start the transmission.
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	struct can_frame *cf = (struct can_frame *)skb->data;
+	u32 id, dlc, data[2] = {0, 0};
+
+	if (can_dropped_invalid_skb(ndev, skb))
+		return NETDEV_TX_OK;
+
+	/* Check if the TX buffer is full */
+	if (unlikely(priv->read_reg(priv, XCAN_SR_OFFSET) &
+			XCAN_SR_TXFLL_MASK)) {
+		netif_stop_queue(ndev);
+		netdev_err(ndev, "BUG!, TX FIFO full when queue awake!\n");
+		return NETDEV_TX_BUSY;
+	}
+
+	/* Watch carefully on the bit sequence */
+	if (cf->can_id & CAN_EFF_FLAG) {
+		/* Extended CAN ID format */
+		id = ((cf->can_id & CAN_EFF_MASK) << XCAN_IDR_ID2_SHIFT) &
+			XCAN_IDR_ID2_MASK;
+		id |= (((cf->can_id & CAN_EFF_MASK) >>
+			(CAN_EFF_ID_BITS-CAN_SFF_ID_BITS)) <<
+			XCAN_IDR_ID1_SHIFT) & XCAN_IDR_ID1_MASK;
+
+		/* The substibute remote TX request bit should be "1"
+		 * for extended frames as in the Xilinx CAN datasheet
+		 */
+		id |= XCAN_IDR_IDE_MASK | XCAN_IDR_SRR_MASK;
+
+		if (cf->can_id & CAN_RTR_FLAG)
+			/* Extended frames remote TX request */
+			id |= XCAN_IDR_RTR_MASK;
+	} else {
+		/* Standard CAN ID format */
+		id = ((cf->can_id & CAN_SFF_MASK) << XCAN_IDR_ID1_SHIFT) &
+			XCAN_IDR_ID1_MASK;
+
+		if (cf->can_id & CAN_RTR_FLAG)
+			/* Standard frames remote TX request */
+			id |= XCAN_IDR_SRR_MASK;
+	}
+
+	dlc = cf->can_dlc << XCAN_DLCR_DLC_SHIFT;
+
+	if (cf->can_dlc > 0)
+		data[0] = be32_to_cpup((__be32 *)(cf->data + 0));
+	if (cf->can_dlc > 4)
+		data[1] = be32_to_cpup((__be32 *)(cf->data + 4));
+
+	can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max);
+	priv->tx_head++;
+
+	/* Write the Frame to Xilinx CAN TX FIFO */
+	priv->write_reg(priv, XCAN_TXFIFO_ID_OFFSET, id);
+	/* If the CAN frame is RTR frame this write triggers tranmission */
+	priv->write_reg(priv, XCAN_TXFIFO_DLC_OFFSET, dlc);
+	if (!(cf->can_id & CAN_RTR_FLAG)) {
+		priv->write_reg(priv, XCAN_TXFIFO_DW1_OFFSET, data[0]);
+		/* If the CAN frame is Standard/Extended frame this
+		 * write triggers tranmission
+		 */
+		priv->write_reg(priv, XCAN_TXFIFO_DW2_OFFSET, data[1]);
+		stats->tx_bytes += cf->can_dlc;
+	}
+
+	/* Check if the TX buffer is full */
+	if ((priv->tx_head - priv->tx_tail) == priv->tx_max)
+		netif_stop_queue(ndev);
+
+	return NETDEV_TX_OK;
+}
+
+/**
+ * xcan_rx -  Is called from CAN isr to complete the received
+ *		frame  processing
+ * @ndev:	Pointer to net_device structure
+ *
+ * This function is invoked from the CAN isr(poll) to process the Rx frames. It
+ * does minimal processing and invokes "netif_receive_skb" to complete further
+ * processing.
+ * Return: 1 on success and 0 on failure.
+ */
+static int xcan_rx(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u32 id_xcan, dlc, data[2] = {0, 0};
+
+	skb = alloc_can_skb(ndev, &cf);
+	if (unlikely(!skb)) {
+		stats->rx_dropped++;
+		return 0;
+	}
+
+	/* Read a frame from Xilinx zynq CANPS */
+	id_xcan = priv->read_reg(priv, XCAN_RXFIFO_ID_OFFSET);
+	dlc = priv->read_reg(priv, XCAN_RXFIFO_DLC_OFFSET) >>
+				XCAN_DLCR_DLC_SHIFT;
+
+	/* Change Xilinx CAN data length format to socketCAN data format */
+	cf->can_dlc = get_can_dlc(dlc);
+
+	/* Change Xilinx CAN ID format to socketCAN ID format */
+	if (id_xcan & XCAN_IDR_IDE_MASK) {
+		/* The received frame is an Extended format frame */
+		cf->can_id = (id_xcan & XCAN_IDR_ID1_MASK) >> 3;
+		cf->can_id |= (id_xcan & XCAN_IDR_ID2_MASK) >>
+				XCAN_IDR_ID2_SHIFT;
+		cf->can_id |= CAN_EFF_FLAG;
+		if (id_xcan & XCAN_IDR_RTR_MASK)
+			cf->can_id |= CAN_RTR_FLAG;
+	} else {
+		/* The received frame is a standard format frame */
+		cf->can_id = (id_xcan & XCAN_IDR_ID1_MASK) >>
+				XCAN_IDR_ID1_SHIFT;
+		if (id_xcan & XCAN_IDR_SRR_MASK)
+			cf->can_id |= CAN_RTR_FLAG;
+	}
+
+	if (!(id_xcan & XCAN_IDR_SRR_MASK)) {
+		data[0] = priv->read_reg(priv, XCAN_RXFIFO_DW1_OFFSET);
+		data[1] = priv->read_reg(priv, XCAN_RXFIFO_DW2_OFFSET);
+
+		/* Change Xilinx CAN data format to socketCAN data format */
+		if (cf->can_dlc > 0)
+			*(__be32 *)(cf->data) = cpu_to_be32(data[0]);
+		if (cf->can_dlc > 4)
+			*(__be32 *)(cf->data + 4) = cpu_to_be32(data[1]);
+	}
+
+	stats->rx_bytes += cf->can_dlc;
+	stats->rx_packets++;
+	netif_receive_skb(skb);
+
+	return 1;
+}
+
+/**
+ * xcan_err_interrupt - error frame Isr
+ * @ndev:	net_device pointer
+ * @isr:	interrupt status register value
+ *
+ * This is the CAN error interrupt and it will
+ * check the the type of error and forward the error
+ * frame to upper layers.
+ */
+static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u32 err_status, status, txerr = 0, rxerr = 0;
+
+	skb = alloc_can_err_skb(ndev, &cf);
+
+	err_status = priv->read_reg(priv, XCAN_ESR_OFFSET);
+	priv->write_reg(priv, XCAN_ESR_OFFSET, err_status);
+	txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK;
+	rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) &
+			XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT);
+	status = priv->read_reg(priv, XCAN_SR_OFFSET);
+
+	if (isr & XCAN_IXR_BSOFF_MASK) {
+		priv->can.state = CAN_STATE_BUS_OFF;
+		priv->can.can_stats.bus_off++;
+		/* Leave device in Config Mode in bus-off state */
+		priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
+		can_bus_off(ndev);
+		if (skb)
+			cf->can_id |= CAN_ERR_BUSOFF;
+	} else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) {
+		priv->can.state = CAN_STATE_ERROR_PASSIVE;
+		priv->can.can_stats.error_passive++;
+		if (skb) {
+			cf->can_id |= CAN_ERR_CRTL;
+			cf->data[1] = (rxerr > 127) ?
+					CAN_ERR_CRTL_RX_PASSIVE :
+					CAN_ERR_CRTL_TX_PASSIVE;
+			cf->data[6] = txerr;
+			cf->data[7] = rxerr;
+		}
+	} else if (status & XCAN_SR_ERRWRN_MASK) {
+		priv->can.state = CAN_STATE_ERROR_WARNING;
+		priv->can.can_stats.error_warning++;
+		if (skb) {
+			cf->can_id |= CAN_ERR_CRTL;
+			cf->data[1] |= (txerr > rxerr) ?
+					CAN_ERR_CRTL_TX_WARNING :
+					CAN_ERR_CRTL_RX_WARNING;
+			cf->data[6] = txerr;
+			cf->data[7] = rxerr;
+		}
+	}
+
+	/* Check for Arbitration lost interrupt */
+	if (isr & XCAN_IXR_ARBLST_MASK) {
+		priv->can.can_stats.arbitration_lost++;
+		if (skb) {
+			cf->can_id |= CAN_ERR_LOSTARB;
+			cf->data[0] = CAN_ERR_LOSTARB_UNSPEC;
+		}
+	}
+
+	/* Check for RX FIFO Overflow interrupt */
+	if (isr & XCAN_IXR_RXOFLW_MASK) {
+		stats->rx_over_errors++;
+		stats->rx_errors++;
+		priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
+		if (skb) {
+			cf->can_id |= CAN_ERR_CRTL;
+			cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW;
+		}
+	}
+
+	/* Check for error interrupt */
+	if (isr & XCAN_IXR_ERROR_MASK) {
+		if (skb) {
+			cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR;
+			cf->data[2] |= CAN_ERR_PROT_UNSPEC;
+		}
+
+		/* Check for Ack error interrupt */
+		if (err_status & XCAN_ESR_ACKER_MASK) {
+			stats->tx_errors++;
+			if (skb) {
+				cf->can_id |= CAN_ERR_ACK;
+				cf->data[3] |= CAN_ERR_PROT_LOC_ACK;
+			}
+		}
+
+		/* Check for Bit error interrupt */
+		if (err_status & XCAN_ESR_BERR_MASK) {
+			stats->tx_errors++;
+			if (skb) {
+				cf->can_id |= CAN_ERR_PROT;
+				cf->data[2] = CAN_ERR_PROT_BIT;
+			}
+		}
+
+		/* Check for Stuff error interrupt */
+		if (err_status & XCAN_ESR_STER_MASK) {
+			stats->rx_errors++;
+			if (skb) {
+				cf->can_id |= CAN_ERR_PROT;
+				cf->data[2] = CAN_ERR_PROT_STUFF;
+			}
+		}
+
+		/* Check for Form error interrupt */
+		if (err_status & XCAN_ESR_FMER_MASK) {
+			stats->rx_errors++;
+			if (skb) {
+				cf->can_id |= CAN_ERR_PROT;
+				cf->data[2] = CAN_ERR_PROT_FORM;
+			}
+		}
+
+		/* Check for CRC error interrupt */
+		if (err_status & XCAN_ESR_CRCER_MASK) {
+			stats->rx_errors++;
+			if (skb) {
+				cf->can_id |= CAN_ERR_PROT;
+				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ |
+						CAN_ERR_PROT_LOC_CRC_DEL;
+			}
+		}
+			priv->can.can_stats.bus_error++;
+	}
+
+	if (skb) {
+		stats->rx_packets++;
+		stats->rx_bytes += cf->can_dlc;
+		netif_rx(skb);
+	}
+
+	netdev_dbg(ndev, "%s: error status register:0x%x\n",
+			__func__, priv->read_reg(priv, XCAN_ESR_OFFSET));
+}
+
+/**
+ * xcan_state_interrupt - It will check the state of the CAN device
+ * @ndev:	net_device pointer
+ * @isr:	interrupt status register value
+ *
+ * This will checks the state of the CAN device
+ * and puts the device into appropriate state.
+ */
+static void xcan_state_interrupt(struct net_device *ndev, u32 isr)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+
+	/* Check for Sleep interrupt if set put CAN device in sleep state */
+	if (isr & XCAN_IXR_SLP_MASK)
+		priv->can.state = CAN_STATE_SLEEPING;
+
+	/* Check for Wake up interrupt if set put CAN device in Active state */
+	if (isr & XCAN_IXR_WKUP_MASK)
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+}
+
+/**
+ * xcan_rx_poll - Poll routine for rx packets (NAPI)
+ * @napi:	napi structure pointer
+ * @quota:	Max number of rx packets to be processed.
+ *
+ * This is the poll routine for rx part.
+ * It will process the packets maximux quota value.
+ *
+ * Return: number of packets received
+ */
+static int xcan_rx_poll(struct napi_struct *napi, int quota)
+{
+	struct net_device *ndev = napi->dev;
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 isr, ier;
+	int work_done = 0;
+
+	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+	while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) {
+		if (isr & XCAN_IXR_RXOK_MASK) {
+			priv->write_reg(priv, XCAN_ICR_OFFSET,
+				XCAN_IXR_RXOK_MASK);
+			work_done += xcan_rx(ndev);
+		} else {
+			priv->write_reg(priv, XCAN_ICR_OFFSET,
+				XCAN_IXR_RXNEMP_MASK);
+			break;
+		}
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK);
+		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+	}
+
+	if (work_done)
+		can_led_event(ndev, CAN_LED_EVENT_RX);
+
+	if (work_done < quota) {
+		napi_complete(napi);
+		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
+		ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK);
+		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
+	}
+	return work_done;
+}
+
+/**
+ * xcan_tx_interrupt - Tx Done Isr
+ * @ndev:	net_device pointer
+ * @isr:	Interrupt status register value
+ */
+static void xcan_tx_interrupt(struct net_device *ndev, u32 isr)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+
+	while ((priv->tx_head - priv->tx_tail > 0) &&
+			(isr & XCAN_IXR_TXOK_MASK)) {
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+		can_get_echo_skb(ndev, priv->tx_tail %
+					priv->tx_max);
+		priv->tx_tail++;
+		stats->tx_packets++;
+		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+	}
+	can_led_event(ndev, CAN_LED_EVENT_TX);
+	netif_wake_queue(ndev);
+}
+
+/**
+ * xcan_interrupt - CAN Isr
+ * @irq:	irq number
+ * @dev_id:	device id poniter
+ *
+ * This is the xilinx CAN Isr. It checks for the type of interrupt
+ * and invokes the corresponding ISR.
+ *
+ * Return:
+ * IRQ_NONE - If CAN device is in sleep mode, IRQ_HANDLED otherwise
+ */
+static irqreturn_t xcan_interrupt(int irq, void *dev_id)
+{
+	struct net_device *ndev = (struct net_device *)dev_id;
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 isr, ier;
+
+	/* Get the interrupt status from Xilinx CAN */
+	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+	if (!isr)
+		return IRQ_NONE;
+
+	/* Check for the type of interrupt and Processing it */
+	if (isr & (XCAN_IXR_SLP_MASK | XCAN_IXR_WKUP_MASK)) {
+		priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_SLP_MASK |
+				XCAN_IXR_WKUP_MASK));
+		xcan_state_interrupt(ndev, isr);
+	}
+
+	/* Check for Tx interrupt and Processing it */
+	if (isr & XCAN_IXR_TXOK_MASK)
+		xcan_tx_interrupt(ndev, isr);
+
+	/* Check for the type of error interrupt and Processing it */
+	if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
+			XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) {
+		priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK |
+				XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK |
+				XCAN_IXR_ARBLST_MASK));
+		xcan_err_interrupt(ndev, isr);
+	}
+
+	/* Check for the type of receive interrupt and Processing it */
+	if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) {
+		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
+		ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK);
+		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
+		napi_schedule(&priv->napi);
+	}
+	return IRQ_HANDLED;
+}
+
+/**
+ * xcan_chip_stop - Driver stop routine
+ * @ndev:	Pointer to net_device structure
+ *
+ * This is the drivers stop routine. It will disable the
+ * interrupts and put the device into configuration mode.
+ */
+static void xcan_chip_stop(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 ier;
+
+	/* Disable interrupts and leave the can in configuration mode */
+	ier = priv->read_reg(priv, XCAN_IER_OFFSET);
+	ier &= ~XCAN_INTR_ALL;
+	priv->write_reg(priv, XCAN_IER_OFFSET, ier);
+	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
+	priv->can.state = CAN_STATE_STOPPED;
+}
+
+/**
+ * xcan_open - Driver open routine
+ * @ndev:	Pointer to net_device structure
+ *
+ * This is the driver open routine.
+ * Return: 0 on success and failure value on error
+ */
+static int xcan_open(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	ret = request_irq(ndev->irq, xcan_interrupt, priv->irq_flags,
+			ndev->name, ndev);
+	if (ret < 0) {
+		netdev_err(ndev, "irq allocation for CAN failed\n");
+		goto err;
+	}
+
+	ret = clk_prepare_enable(priv->can_clk);
+	if (ret) {
+		netdev_err(ndev, "unable to enable device clock\n");
+		goto err_irq;
+	}
+
+	ret = clk_prepare_enable(priv->bus_clk);
+	if (ret) {
+		netdev_err(ndev, "unable to enable bus clock\n");
+		goto err_can_clk;
+	}
+
+	/* Set chip into reset mode */
+	ret = set_reset_mode(ndev);
+	if (ret < 0) {
+		netdev_err(ndev, "mode resetting failed!\n");
+		goto err_bus_clk;
+	}
+
+	/* Common open */
+	ret = open_candev(ndev);
+	if (ret)
+		goto err_bus_clk;
+
+	ret = xcan_chip_start(ndev);
+	if (ret < 0) {
+		netdev_err(ndev, "xcan_chip_start failed!\n");
+		goto err_candev;
+	}
+
+	can_led_event(ndev, CAN_LED_EVENT_OPEN);
+	napi_enable(&priv->napi);
+	netif_start_queue(ndev);
+
+	return 0;
+
+err_candev:
+	close_candev(ndev);
+err_bus_clk:
+	clk_disable_unprepare(priv->bus_clk);
+err_can_clk:
+	clk_disable_unprepare(priv->can_clk);
+err_irq:
+	free_irq(ndev->irq, ndev);
+err:
+	return ret;
+}
+
+/**
+ * xcan_close - Driver close routine
+ * @ndev:	Pointer to net_device structure
+ *
+ * Return: 0 always
+ */
+static int xcan_close(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+	napi_disable(&priv->napi);
+	xcan_chip_stop(ndev);
+	clk_disable_unprepare(priv->bus_clk);
+	clk_disable_unprepare(priv->can_clk);
+	free_irq(ndev->irq, ndev);
+	close_candev(ndev);
+
+	can_led_event(ndev, CAN_LED_EVENT_STOP);
+
+	return 0;
+}
+
+/**
+ * xcan_get_berr_counter - error counter routine
+ * @ndev:	Pointer to net_device structure
+ * @bec:	Pointer to can_berr_counter structure
+ *
+ * This is the driver error counter routine.
+ * Return: 0 on success and failure value on error
+ */
+static int xcan_get_berr_counter(const struct net_device *ndev,
+					struct can_berr_counter *bec)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	ret = clk_prepare_enable(priv->can_clk);
+	if (ret)
+		goto err;
+
+	ret = clk_prepare_enable(priv->bus_clk);
+	if (ret)
+		goto err_clk;
+
+	bec->txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK;
+	bec->rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) &
+			XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT);
+
+	clk_disable_unprepare(priv->bus_clk);
+	clk_disable_unprepare(priv->can_clk);
+
+	return 0;
+
+err_clk:
+	clk_disable_unprepare(priv->can_clk);
+err:
+	return ret;
+}
+
+
+static const struct net_device_ops xcan_netdev_ops = {
+	.ndo_open	= xcan_open,
+	.ndo_stop	= xcan_close,
+	.ndo_start_xmit	= xcan_start_xmit,
+};
+
+/**
+ * xcan_suspend - Suspend method for the driver
+ * @dev:	Address of the platform_device structure
+ *
+ * Put the driver into low power mode.
+ * Return: 0 always
+ */
+static int __maybe_unused xcan_suspend(struct device *dev)
+{
+	struct platform_device *pdev = dev_get_drvdata(dev);
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct xcan_priv *priv = netdev_priv(ndev);
+
+	if (netif_running(ndev)) {
+		netif_stop_queue(ndev);
+		netif_device_detach(ndev);
+	}
+
+	priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK);
+	priv->can.state = CAN_STATE_SLEEPING;
+
+	clk_disable(priv->bus_clk);
+	clk_disable(priv->can_clk);
+
+	return 0;
+}
+
+/**
+ * xcan_resume - Resume from suspend
+ * @dev:	Address of the platformdevice structure
+ *
+ * Resume operation after suspend.
+ * Return: 0 on success and failure value on error
+ */
+static int __maybe_unused xcan_resume(struct device *dev)
+{
+	struct platform_device *pdev = dev_get_drvdata(dev);
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct xcan_priv *priv = netdev_priv(ndev);
+	int ret;
+
+	ret = clk_enable(priv->bus_clk);
+	if (ret) {
+		dev_err(dev, "Cannot enable clock.\n");
+		return ret;
+	}
+	ret = clk_enable(priv->can_clk);
+	if (ret) {
+		dev_err(dev, "Cannot enable clock.\n");
+		clk_disable_unprepare(priv->bus_clk);
+		return ret;
+	}
+
+	priv->write_reg(priv, XCAN_MSR_OFFSET, 0);
+	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_CEN_MASK);
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	if (netif_running(ndev)) {
+		netif_device_attach(ndev);
+		netif_start_queue(ndev);
+	}
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(xcan_dev_pm_ops, xcan_suspend, xcan_resume);
+
+/**
+ * xcan_probe - Platform registration call
+ * @pdev:	Handle to the platform device structure
+ *
+ * This function does all the memory allocation and registration for the CAN
+ * device.
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int xcan_probe(struct platform_device *pdev)
+{
+	struct resource *res; /* IO mem resources */
+	struct net_device *ndev;
+	struct xcan_priv *priv;
+	void __iomem *addr;
+	int ret, rx_max, tx_max;
+
+	/* Get the virtual base address for the device */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	addr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(addr)) {
+		ret = PTR_ERR(addr);
+		goto err;
+	}
+
+	ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max);
+	if (ret < 0)
+		goto err;
+
+	ret = of_property_read_u32(pdev->dev.of_node, "rx-fifo-depth", &rx_max);
+	if (ret < 0)
+		goto err;
+
+	/* Create a CAN device instance */
+	ndev = alloc_candev(sizeof(struct xcan_priv), tx_max);
+	if (!ndev)
+		return -ENOMEM;
+
+	priv = netdev_priv(ndev);
+	priv->dev = ndev;
+	priv->can.bittiming_const = &xcan_bittiming_const;
+	priv->can.do_set_mode = xcan_do_set_mode;
+	priv->can.do_get_berr_counter = xcan_get_berr_counter;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
+					CAN_CTRLMODE_BERR_REPORTING;
+	priv->reg_base = addr;
+	priv->tx_max = tx_max;
+
+	/* Get IRQ for the device */
+	ndev->irq = platform_get_irq(pdev, 0);
+	ndev->flags |= IFF_ECHO;	/* We support local echo */
+
+	platform_set_drvdata(pdev, ndev);
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+	ndev->netdev_ops = &xcan_netdev_ops;
+
+	/* Getting the CAN can_clk info */
+	priv->can_clk = devm_clk_get(&pdev->dev, "can_clk");
+	if (IS_ERR(priv->can_clk)) {
+		dev_err(&pdev->dev, "Device clock not found.\n");
+		ret = PTR_ERR(priv->can_clk);
+		goto err_free;
+	}
+	/* Check for type of CAN device */
+	if (of_device_is_compatible(pdev->dev.of_node,
+				    "xlnx,zynq-can-1.0")) {
+		priv->bus_clk = devm_clk_get(&pdev->dev, "pclk");
+		if (IS_ERR(priv->bus_clk)) {
+			dev_err(&pdev->dev, "bus clock not found\n");
+			ret = PTR_ERR(priv->bus_clk);
+			goto err_free;
+		}
+	} else {
+		priv->bus_clk = devm_clk_get(&pdev->dev, "s_axi_aclk");
+		if (IS_ERR(priv->bus_clk)) {
+			dev_err(&pdev->dev, "bus clock not found\n");
+			ret = PTR_ERR(priv->bus_clk);
+			goto err_free;
+		}
+	}
+
+	ret = clk_prepare_enable(priv->can_clk);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to enable device clock\n");
+		goto err_free;
+	}
+
+	ret = clk_prepare_enable(priv->bus_clk);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to enable bus clock\n");
+		goto err_unprepare_disable_dev;
+	}
+
+	priv->write_reg = xcan_write_reg_le;
+	priv->read_reg = xcan_read_reg_le;
+
+	if (priv->read_reg(priv, XCAN_SR_OFFSET) != XCAN_SR_CONFIG_MASK) {
+		priv->write_reg = xcan_write_reg_be;
+		priv->read_reg = xcan_read_reg_be;
+	}
+
+	priv->can.clock.freq = clk_get_rate(priv->can_clk);
+
+	netif_napi_add(ndev, &priv->napi, xcan_rx_poll, rx_max);
+
+	ret = register_candev(ndev);
+	if (ret) {
+		dev_err(&pdev->dev, "fail to register failed (err=%d)\n", ret);
+		goto err_unprepare_disable_busclk;
+	}
+
+	devm_can_led_init(ndev);
+	clk_disable_unprepare(priv->bus_clk);
+	clk_disable_unprepare(priv->can_clk);
+	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n",
+			priv->reg_base, ndev->irq, priv->can.clock.freq,
+			priv->tx_max);
+
+	return 0;
+
+err_unprepare_disable_busclk:
+	clk_disable_unprepare(priv->bus_clk);
+err_unprepare_disable_dev:
+	clk_disable_unprepare(priv->can_clk);
+err_free:
+	free_candev(ndev);
+err:
+	return ret;
+}
+
+/**
+ * xcan_remove - Unregister the device after releasing the resources
+ * @pdev:	Handle to the platform device structure
+ *
+ * This function frees all the resources allocated to the device.
+ * Return: 0 always
+ */
+static int xcan_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct xcan_priv *priv = netdev_priv(ndev);
+
+	if (set_reset_mode(ndev) < 0)
+		netdev_err(ndev, "mode resetting failed!\n");
+
+	unregister_candev(ndev);
+	netif_napi_del(&priv->napi);
+	free_candev(ndev);
+
+	return 0;
+}
+
+/* Match table for OF platform binding */
+static struct of_device_id xcan_of_match[] = {
+	{ .compatible = "xlnx,zynq-can-1.0", },
+	{ .compatible = "xlnx,axi-can-1.00.a", },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, xcan_of_match);
+
+static struct platform_driver xcan_driver = {
+	.probe = xcan_probe,
+	.remove	= xcan_remove,
+	.driver	= {
+		.owner = THIS_MODULE,
+		.name = DRIVER_NAME,
+		.pm = &xcan_dev_pm_ops,
+		.of_match_table	= xcan_of_match,
+	},
+};
+
+module_platform_driver(xcan_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Xilinx Inc");
+MODULE_DESCRIPTION("Xilinx CAN interface");
diff --git a/drivers/net/dsa/mv88e6123_61_65.c b/drivers/net/dsa/mv88e6123_61_65.c
index 41ee5b6ae91..69c42513dd7 100644
--- a/drivers/net/dsa/mv88e6123_61_65.c
+++ b/drivers/net/dsa/mv88e6123_61_65.c
@@ -289,7 +289,7 @@ static int mv88e6123_61_65_setup_port(struct dsa_switch *ds, int p)
 
 static int mv88e6123_61_65_setup(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)(ds + 1);
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int i;
 	int ret;
 
diff --git a/drivers/net/dsa/mv88e6131.c b/drivers/net/dsa/mv88e6131.c
index dadfafba64e..953bc6a49e5 100644
--- a/drivers/net/dsa/mv88e6131.c
+++ b/drivers/net/dsa/mv88e6131.c
@@ -155,7 +155,7 @@ static int mv88e6131_setup_global(struct dsa_switch *ds)
 
 static int mv88e6131_setup_port(struct dsa_switch *ds, int p)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)(ds + 1);
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int addr = REG_PORT(p);
 	u16 val;
 
@@ -274,7 +274,7 @@ static int mv88e6131_setup_port(struct dsa_switch *ds, int p)
 
 static int mv88e6131_setup(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)(ds + 1);
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int i;
 	int ret;
 
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index 17314ed9456..9ce2146346b 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -74,7 +74,7 @@ int __mv88e6xxx_reg_read(struct mii_bus *bus, int sw_addr, int addr, int reg)
 
 int mv88e6xxx_reg_read(struct dsa_switch *ds, int addr, int reg)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)(ds + 1);
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret;
 
 	mutex_lock(&ps->smi_mutex);
@@ -118,7 +118,7 @@ int __mv88e6xxx_reg_write(struct mii_bus *bus, int sw_addr, int addr,
 
 int mv88e6xxx_reg_write(struct dsa_switch *ds, int addr, int reg, u16 val)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)(ds + 1);
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret;
 
 	mutex_lock(&ps->smi_mutex);
@@ -256,7 +256,7 @@ static void mv88e6xxx_ppu_reenable_timer(unsigned long _ps)
 
 static int mv88e6xxx_ppu_access_get(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)(ds + 1);
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret;
 
 	mutex_lock(&ps->ppu_mutex);
@@ -283,7 +283,7 @@ static int mv88e6xxx_ppu_access_get(struct dsa_switch *ds)
 
 static void mv88e6xxx_ppu_access_put(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)(ds + 1);
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 
 	/* Schedule a timer to re-enable the PHY polling unit. */
 	mod_timer(&ps->ppu_timer, jiffies + msecs_to_jiffies(10));
@@ -292,7 +292,7 @@ static void mv88e6xxx_ppu_access_put(struct dsa_switch *ds)
 
 void mv88e6xxx_ppu_state_init(struct dsa_switch *ds)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)(ds + 1);
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 
 	mutex_init(&ps->ppu_mutex);
 	INIT_WORK(&ps->ppu_work, mv88e6xxx_ppu_reenable_work);
@@ -463,7 +463,7 @@ void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds,
 				 int nr_stats, struct mv88e6xxx_hw_stat *stats,
 				 int port, uint64_t *data)
 {
-	struct mv88e6xxx_priv_state *ps = (void *)(ds + 1);
+	struct mv88e6xxx_priv_state *ps = ds_to_priv(ds);
 	int ret;
 	int i;
 
diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c
index 35df0b9e684..a968654b631 100644
--- a/drivers/net/ethernet/3com/3c509.c
+++ b/drivers/net/ethernet/3com/3c509.c
@@ -534,7 +534,7 @@ static int el3_common_init(struct net_device *dev)
 	/* The EL3-specific entries in the device structure. */
 	dev->netdev_ops = &netdev_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
-	SET_ETHTOOL_OPS(dev, &ethtool_ops);
+	dev->ethtool_ops = &ethtool_ops;
 
 	err = register_netdev(dev);
 	if (err) {
diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c
index 063557e037f..f18647c2355 100644
--- a/drivers/net/ethernet/3com/3c589_cs.c
+++ b/drivers/net/ethernet/3com/3c589_cs.c
@@ -218,7 +218,7 @@ static int tc589_probe(struct pcmcia_device *link)
 	dev->netdev_ops = &el3_netdev_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
 
-	SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops);
+	dev->ethtool_ops = &netdev_ethtool_ops;
 
 	return tc589_config(link);
 }
diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c
index 465cc7108d8..e13b04624de 100644
--- a/drivers/net/ethernet/3com/typhoon.c
+++ b/drivers/net/ethernet/3com/typhoon.c
@@ -2435,7 +2435,7 @@ typhoon_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netif_napi_add(dev, &tp->napi, typhoon_poll, 16);
 	dev->watchdog_timeo	= TX_TIMEOUT;
 
-	SET_ETHTOOL_OPS(dev, &typhoon_ethtool_ops);
+	dev->ethtool_ops = &typhoon_ethtool_ops;
 
 	/* We can handle scatter gather, up to 16 entries, and
 	 * we can do IP checksumming (only version 4, doh...)
diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c
index 455d4c399b5..1d162ccb473 100644
--- a/drivers/net/ethernet/8390/ax88796.c
+++ b/drivers/net/ethernet/8390/ax88796.c
@@ -157,7 +157,7 @@ static void ax_reset_8390(struct net_device *dev)
 
 	/* This check _should_not_ be necessary, omit eventually. */
 	while ((ei_inb(addr + EN0_ISR) & ENISR_RESET) == 0) {
-		if (jiffies - reset_start_time > 2 * HZ / 100) {
+		if (time_after(jiffies, reset_start_time + 2 * HZ / 100)) {
 			netdev_warn(dev, "%s: did not complete.\n", __func__);
 			break;
 		}
@@ -293,7 +293,7 @@ static void ax_block_output(struct net_device *dev, int count,
 	dma_start = jiffies;
 
 	while ((ei_inb(nic_base + EN0_ISR) & ENISR_RDC) == 0) {
-		if (jiffies - dma_start > 2 * HZ / 100) {		/* 20ms */
+		if (time_after(jiffies, dma_start + 2 * HZ / 100)) { /* 20ms */
 			netdev_warn(dev, "timeout waiting for Tx RDC.\n");
 			ax_reset_8390(dev);
 			ax_NS8390_init(dev, 1);
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 05134945846..edb71866185 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -68,6 +68,7 @@ source "drivers/net/ethernet/neterion/Kconfig"
 source "drivers/net/ethernet/faraday/Kconfig"
 source "drivers/net/ethernet/freescale/Kconfig"
 source "drivers/net/ethernet/fujitsu/Kconfig"
+source "drivers/net/ethernet/hisilicon/Kconfig"
 source "drivers/net/ethernet/hp/Kconfig"
 source "drivers/net/ethernet/ibm/Kconfig"
 source "drivers/net/ethernet/intel/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 35190e36c45..58de3339ab3 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_NET_VENDOR_EXAR) += neterion/
 obj-$(CONFIG_NET_VENDOR_FARADAY) += faraday/
 obj-$(CONFIG_NET_VENDOR_FREESCALE) += freescale/
 obj-$(CONFIG_NET_VENDOR_FUJITSU) += fujitsu/
+obj-$(CONFIG_NET_VENDOR_HISILICON) += hisilicon/
 obj-$(CONFIG_NET_VENDOR_HP) += hp/
 obj-$(CONFIG_NET_VENDOR_IBM) += ibm/
 obj-$(CONFIG_NET_VENDOR_INTEL) += intel/
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 171d73c1d3c..40dbbf74033 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -784,7 +784,7 @@ static int starfire_init_one(struct pci_dev *pdev,
 
 	dev->netdev_ops = &netdev_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
-	SET_ETHTOOL_OPS(dev, &ethtool_ops);
+	dev->ethtool_ops = &ethtool_ops;
 
 	netif_napi_add(dev, &np->napi, netdev_poll, max_interrupt_work);
 
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 28460676b8c..d81e7167a8b 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -736,6 +736,7 @@ static int emac_open(struct net_device *dev)
 
 	ret = emac_mdio_probe(dev);
 	if (ret < 0) {
+		free_irq(dev->irq, dev);
 		netdev_err(dev, "cannot probe MDIO bus\n");
 		return ret;
 	}
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 1517e9df5ba..9a6991be974 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -476,7 +476,7 @@ static int acenic_probe_one(struct pci_dev *pdev,
 	dev->watchdog_timeo = 5*HZ;
 
 	dev->netdev_ops = &ace_netdev_ops;
-	SET_ETHTOOL_OPS(dev, &ace_ethtool_ops);
+	dev->ethtool_ops = &ace_ethtool_ops;
 
 	/* we only display this string ONCE */
 	if (!boards_found)
diff --git a/drivers/net/ethernet/altera/altera_sgdma.c b/drivers/net/ethernet/altera/altera_sgdma.c
index 99cc56f451c..580553d42d3 100644
--- a/drivers/net/ethernet/altera/altera_sgdma.c
+++ b/drivers/net/ethernet/altera/altera_sgdma.c
@@ -353,7 +353,6 @@ static int sgdma_async_read(struct altera_tse_private *priv)
 
 	struct sgdma_descrip __iomem *cdesc = &descbase[0];
 	struct sgdma_descrip __iomem *ndesc = &descbase[1];
-
 	struct tse_buffer *rxbuffer = NULL;
 
 	if (!sgdma_rxbusy(priv)) {
diff --git a/drivers/net/ethernet/altera/altera_tse_ethtool.c b/drivers/net/ethernet/altera/altera_tse_ethtool.c
index 54c25eff795..be72e1e6452 100644
--- a/drivers/net/ethernet/altera/altera_tse_ethtool.c
+++ b/drivers/net/ethernet/altera/altera_tse_ethtool.c
@@ -271,5 +271,5 @@ static const struct ethtool_ops tse_ethtool_ops = {
 
 void altera_tse_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &tse_ethtool_ops);
+	netdev->ethtool_ops = &tse_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index 562df46e0a8..bbaf36d9f5e 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -7,7 +7,7 @@ config NET_VENDOR_AMD
 	default y
 	depends on DIO || MACH_DECSTATION || MVME147 || ATARI || SUN3 || \
 		   SUN3X || SBUS || PCI || ZORRO || (ISA && ISA_DMA_API) || \
-		   (ARM && ARCH_EBSA110) || ISA || EISA || PCMCIA
+		   (ARM && ARCH_EBSA110) || ISA || EISA || PCMCIA || ARM64
 	---help---
 	  If you have a network (Ethernet) chipset belonging to this class,
 	  say Y.
@@ -177,4 +177,16 @@ config SUNLANCE
 	  To compile this driver as a module, choose M here: the module
 	  will be called sunlance.
 
+config AMD_XGBE
+	tristate "AMD 10GbE Ethernet driver"
+	depends on OF_NET
+	select PHYLIB
+	select AMD_XGBE_PHY
+	---help---
+	  This driver supports the AMD 10GbE Ethernet device found on an
+	  AMD SoC.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called amd-xgbe.
+
 endif # NET_VENDOR_AMD
diff --git a/drivers/net/ethernet/amd/Makefile b/drivers/net/ethernet/amd/Makefile
index cdd4301a973..a38a2dce3eb 100644
--- a/drivers/net/ethernet/amd/Makefile
+++ b/drivers/net/ethernet/amd/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_NI65) += ni65.o
 obj-$(CONFIG_PCNET32) += pcnet32.o
 obj-$(CONFIG_SUN3LANCE) += sun3lance.o
 obj-$(CONFIG_SUNLANCE) += sunlance.o
+obj-$(CONFIG_AMD_XGBE) += xgbe/
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index 26efaaa5e73..068dc7cad5f 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -1900,7 +1900,7 @@ static int amd8111e_probe_one(struct pci_dev *pdev,
 
 	/* Initialize driver entry points */
 	dev->netdev_ops = &amd8111e_netdev_ops;
-	SET_ETHTOOL_OPS(dev, &ops);
+	dev->ethtool_ops = &ops;
 	dev->irq =pdev->irq;
 	dev->watchdog_timeo = AMD8111E_TX_TIMEOUT;
 	netif_napi_add(dev, &lp->napi, amd8111e_rx_poll, 32);
diff --git a/drivers/net/ethernet/amd/ariadne.c b/drivers/net/ethernet/amd/ariadne.c
index b08101b31b8..968b7bfac8f 100644
--- a/drivers/net/ethernet/amd/ariadne.c
+++ b/drivers/net/ethernet/amd/ariadne.c
@@ -718,7 +718,6 @@ static int ariadne_init_one(struct zorro_dev *z,
 	unsigned long mem_start = board + ARIADNE_RAM;
 	struct resource *r1, *r2;
 	struct net_device *dev;
-	struct ariadne_private *priv;
 	u32 serial;
 	int err;
 
@@ -738,8 +737,6 @@ static int ariadne_init_one(struct zorro_dev *z,
 		return -ENOMEM;
 	}
 
-	priv = netdev_priv(dev);
-
 	r1->name = dev->name;
 	r2->name = dev->name;
 
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index a2bd91e3d30..a78e4c13695 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -1229,7 +1229,7 @@ static int au1000_probe(struct platform_device *pdev)
 	dev->base_addr = base->start;
 	dev->irq = irq;
 	dev->netdev_ops = &au1000_netdev_ops;
-	SET_ETHTOOL_OPS(dev, &au1000_ethtool_ops);
+	dev->ethtool_ops = &au1000_ethtool_ops;
 	dev->watchdog_timeo = ETH_TX_TIMEOUT;
 
 	/*
diff --git a/drivers/net/ethernet/amd/hplance.c b/drivers/net/ethernet/amd/hplance.c
index 47ce57c2c89..6c9de117ffc 100644
--- a/drivers/net/ethernet/amd/hplance.c
+++ b/drivers/net/ethernet/amd/hplance.c
@@ -27,9 +27,9 @@
 
 #include "hplance.h"
 
-/* We have 16834 bytes of RAM for the init block and buffers. This places
+/* We have 16392 bytes of RAM for the init block and buffers. This places
  * an upper limit on the number of buffers we can use. NetBSD uses 8 Rx
- * buffers and 2 Tx buffers.
+ * buffers and 2 Tx buffers, it takes (8 + 2) * 1544 bytes.
  */
 #define LANCE_LOG_TX_BUFFERS 1
 #define LANCE_LOG_RX_BUFFERS 3
diff --git a/drivers/net/ethernet/amd/mvme147.c b/drivers/net/ethernet/amd/mvme147.c
index 0e8399dec05..0660ac5846b 100644
--- a/drivers/net/ethernet/amd/mvme147.c
+++ b/drivers/net/ethernet/amd/mvme147.c
@@ -26,9 +26,9 @@
 #include <asm/pgtable.h>
 #include <asm/mvme147hw.h>
 
-/* We have 16834 bytes of RAM for the init block and buffers. This places
+/* We have 32K of RAM for the init block and buffers. This places
  * an upper limit on the number of buffers we can use. NetBSD uses 8 Rx
- * buffers and 2 Tx buffers.
+ * buffers and 2 Tx buffers, it takes (8 + 2) * 1544 bytes.
  */
 #define LANCE_LOG_TX_BUFFERS 1
 #define LANCE_LOG_RX_BUFFERS 3
@@ -111,7 +111,7 @@ struct net_device * __init mvme147lance_probe(int unit)
 	       dev->dev_addr);
 
 	lp = netdev_priv(dev);
-	lp->ram = __get_dma_pages(GFP_ATOMIC, 3);	/* 16K */
+	lp->ram = __get_dma_pages(GFP_ATOMIC, 3);	/* 32K */
 	if (!lp->ram) {
 		printk("%s: No memory for LANCE buffers\n", dev->name);
 		free_netdev(dev);
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index 08569fe2b18..abf3b1581c8 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -457,7 +457,7 @@ static int nmclan_probe(struct pcmcia_device *link)
     lp->tx_free_frames=AM2150_MAX_TX_FRAMES;
 
     dev->netdev_ops = &mace_netdev_ops;
-    SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops);
+    dev->ethtool_ops = &netdev_ethtool_ops;
     dev->watchdog_timeo = TX_TIMEOUT;
 
     return nmclan_config(link);
diff --git a/drivers/net/ethernet/amd/xgbe/Makefile b/drivers/net/ethernet/amd/xgbe/Makefile
new file mode 100644
index 00000000000..26cf9af1642
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/Makefile
@@ -0,0 +1,6 @@
+obj-$(CONFIG_AMD_XGBE) += amd-xgbe.o
+
+amd-xgbe-objs := xgbe-main.o xgbe-drv.o xgbe-dev.o \
+		 xgbe-desc.o xgbe-ethtool.o xgbe-mdio.o
+
+amd-xgbe-$(CONFIG_DEBUG_FS) += xgbe-debugfs.o
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
new file mode 100644
index 00000000000..bf462ee86f5
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -0,0 +1,1007 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __XGBE_COMMON_H__
+#define __XGBE_COMMON_H__
+
+/* DMA register offsets */
+#define DMA_MR				0x3000
+#define DMA_SBMR			0x3004
+#define DMA_ISR				0x3008
+#define DMA_AXIARCR			0x3010
+#define DMA_AXIAWCR			0x3018
+#define DMA_DSR0			0x3020
+#define DMA_DSR1			0x3024
+#define DMA_DSR2			0x3028
+#define DMA_DSR3			0x302c
+#define DMA_DSR4			0x3030
+
+/* DMA register entry bit positions and sizes */
+#define DMA_AXIARCR_DRC_INDEX		0
+#define DMA_AXIARCR_DRC_WIDTH		4
+#define DMA_AXIARCR_DRD_INDEX		4
+#define DMA_AXIARCR_DRD_WIDTH		2
+#define DMA_AXIARCR_TEC_INDEX		8
+#define DMA_AXIARCR_TEC_WIDTH		4
+#define DMA_AXIARCR_TED_INDEX		12
+#define DMA_AXIARCR_TED_WIDTH		2
+#define DMA_AXIARCR_THC_INDEX		16
+#define DMA_AXIARCR_THC_WIDTH		4
+#define DMA_AXIARCR_THD_INDEX		20
+#define DMA_AXIARCR_THD_WIDTH		2
+#define DMA_AXIAWCR_DWC_INDEX		0
+#define DMA_AXIAWCR_DWC_WIDTH		4
+#define DMA_AXIAWCR_DWD_INDEX		4
+#define DMA_AXIAWCR_DWD_WIDTH		2
+#define DMA_AXIAWCR_RPC_INDEX		8
+#define DMA_AXIAWCR_RPC_WIDTH		4
+#define DMA_AXIAWCR_RPD_INDEX		12
+#define DMA_AXIAWCR_RPD_WIDTH		2
+#define DMA_AXIAWCR_RHC_INDEX		16
+#define DMA_AXIAWCR_RHC_WIDTH		4
+#define DMA_AXIAWCR_RHD_INDEX		20
+#define DMA_AXIAWCR_RHD_WIDTH		2
+#define DMA_AXIAWCR_TDC_INDEX		24
+#define DMA_AXIAWCR_TDC_WIDTH		4
+#define DMA_AXIAWCR_TDD_INDEX		28
+#define DMA_AXIAWCR_TDD_WIDTH		2
+#define DMA_DSR0_RPS_INDEX		8
+#define DMA_DSR0_RPS_WIDTH		4
+#define DMA_DSR0_TPS_INDEX		12
+#define DMA_DSR0_TPS_WIDTH		4
+#define DMA_ISR_MACIS_INDEX		17
+#define DMA_ISR_MACIS_WIDTH		1
+#define DMA_ISR_MTLIS_INDEX		16
+#define DMA_ISR_MTLIS_WIDTH		1
+#define DMA_MR_SWR_INDEX		0
+#define DMA_MR_SWR_WIDTH		1
+#define DMA_SBMR_EAME_INDEX		11
+#define DMA_SBMR_EAME_WIDTH		1
+#define DMA_SBMR_UNDEF_INDEX		0
+#define DMA_SBMR_UNDEF_WIDTH		1
+
+/* DMA channel register offsets
+ *   Multiple channels can be active.  The first channel has registers
+ *   that begin at 0x3100.  Each subsequent channel has registers that
+ *   are accessed using an offset of 0x80 from the previous channel.
+ */
+#define DMA_CH_BASE			0x3100
+#define DMA_CH_INC			0x80
+
+#define DMA_CH_CR			0x00
+#define DMA_CH_TCR			0x04
+#define DMA_CH_RCR			0x08
+#define DMA_CH_TDLR_HI			0x10
+#define DMA_CH_TDLR_LO			0x14
+#define DMA_CH_RDLR_HI			0x18
+#define DMA_CH_RDLR_LO			0x1c
+#define DMA_CH_TDTR_LO			0x24
+#define DMA_CH_RDTR_LO			0x2c
+#define DMA_CH_TDRLR			0x30
+#define DMA_CH_RDRLR			0x34
+#define DMA_CH_IER			0x38
+#define DMA_CH_RIWT			0x3c
+#define DMA_CH_CATDR_LO			0x44
+#define DMA_CH_CARDR_LO			0x4c
+#define DMA_CH_CATBR_HI			0x50
+#define DMA_CH_CATBR_LO			0x54
+#define DMA_CH_CARBR_HI			0x58
+#define DMA_CH_CARBR_LO			0x5c
+#define DMA_CH_SR			0x60
+
+/* DMA channel register entry bit positions and sizes */
+#define DMA_CH_CR_PBLX8_INDEX		16
+#define DMA_CH_CR_PBLX8_WIDTH		1
+#define DMA_CH_IER_AIE_INDEX		15
+#define DMA_CH_IER_AIE_WIDTH		1
+#define DMA_CH_IER_FBEE_INDEX		12
+#define DMA_CH_IER_FBEE_WIDTH		1
+#define DMA_CH_IER_NIE_INDEX		16
+#define DMA_CH_IER_NIE_WIDTH		1
+#define DMA_CH_IER_RBUE_INDEX		7
+#define DMA_CH_IER_RBUE_WIDTH		1
+#define DMA_CH_IER_RIE_INDEX		6
+#define DMA_CH_IER_RIE_WIDTH		1
+#define DMA_CH_IER_RSE_INDEX		8
+#define DMA_CH_IER_RSE_WIDTH		1
+#define DMA_CH_IER_TBUE_INDEX		2
+#define DMA_CH_IER_TBUE_WIDTH		1
+#define DMA_CH_IER_TIE_INDEX		0
+#define DMA_CH_IER_TIE_WIDTH		1
+#define DMA_CH_IER_TXSE_INDEX		1
+#define DMA_CH_IER_TXSE_WIDTH		1
+#define DMA_CH_RCR_PBL_INDEX		16
+#define DMA_CH_RCR_PBL_WIDTH		6
+#define DMA_CH_RCR_RBSZ_INDEX		1
+#define DMA_CH_RCR_RBSZ_WIDTH		14
+#define DMA_CH_RCR_SR_INDEX		0
+#define DMA_CH_RCR_SR_WIDTH		1
+#define DMA_CH_RIWT_RWT_INDEX		0
+#define DMA_CH_RIWT_RWT_WIDTH		8
+#define DMA_CH_SR_FBE_INDEX		12
+#define DMA_CH_SR_FBE_WIDTH		1
+#define DMA_CH_SR_RBU_INDEX		7
+#define DMA_CH_SR_RBU_WIDTH		1
+#define DMA_CH_SR_RI_INDEX		6
+#define DMA_CH_SR_RI_WIDTH		1
+#define DMA_CH_SR_RPS_INDEX		8
+#define DMA_CH_SR_RPS_WIDTH		1
+#define DMA_CH_SR_TBU_INDEX		2
+#define DMA_CH_SR_TBU_WIDTH		1
+#define DMA_CH_SR_TI_INDEX		0
+#define DMA_CH_SR_TI_WIDTH		1
+#define DMA_CH_SR_TPS_INDEX		1
+#define DMA_CH_SR_TPS_WIDTH		1
+#define DMA_CH_TCR_OSP_INDEX		4
+#define DMA_CH_TCR_OSP_WIDTH		1
+#define DMA_CH_TCR_PBL_INDEX		16
+#define DMA_CH_TCR_PBL_WIDTH		6
+#define DMA_CH_TCR_ST_INDEX		0
+#define DMA_CH_TCR_ST_WIDTH		1
+#define DMA_CH_TCR_TSE_INDEX		12
+#define DMA_CH_TCR_TSE_WIDTH		1
+
+/* DMA channel register values */
+#define DMA_OSP_DISABLE			0x00
+#define DMA_OSP_ENABLE			0x01
+#define DMA_PBL_1			1
+#define DMA_PBL_2			2
+#define DMA_PBL_4			4
+#define DMA_PBL_8			8
+#define DMA_PBL_16			16
+#define DMA_PBL_32			32
+#define DMA_PBL_64			64      /* 8 x 8 */
+#define DMA_PBL_128			128     /* 8 x 16 */
+#define DMA_PBL_256			256     /* 8 x 32 */
+#define DMA_PBL_X8_DISABLE		0x00
+#define DMA_PBL_X8_ENABLE		0x01
+
+
+/* MAC register offsets */
+#define MAC_TCR				0x0000
+#define MAC_RCR				0x0004
+#define MAC_PFR				0x0008
+#define MAC_WTR				0x000c
+#define MAC_HTR0			0x0010
+#define MAC_HTR1			0x0014
+#define MAC_HTR2			0x0018
+#define MAC_HTR3			0x001c
+#define MAC_HTR4			0x0020
+#define MAC_HTR5			0x0024
+#define MAC_HTR6			0x0028
+#define MAC_HTR7			0x002c
+#define MAC_VLANTR			0x0050
+#define MAC_VLANHTR			0x0058
+#define MAC_VLANIR			0x0060
+#define MAC_IVLANIR			0x0064
+#define MAC_RETMR			0x006c
+#define MAC_Q0TFCR			0x0070
+#define MAC_RFCR			0x0090
+#define MAC_RQC0R			0x00a0
+#define MAC_RQC1R			0x00a4
+#define MAC_RQC2R			0x00a8
+#define MAC_RQC3R			0x00ac
+#define MAC_ISR				0x00b0
+#define MAC_IER				0x00b4
+#define MAC_RTSR			0x00b8
+#define MAC_PMTCSR			0x00c0
+#define MAC_RWKPFR			0x00c4
+#define MAC_LPICSR			0x00d0
+#define MAC_LPITCR			0x00d4
+#define MAC_VR				0x0110
+#define MAC_DR				0x0114
+#define MAC_HWF0R			0x011c
+#define MAC_HWF1R			0x0120
+#define MAC_HWF2R			0x0124
+#define MAC_GPIOCR			0x0278
+#define MAC_GPIOSR			0x027c
+#define MAC_MACA0HR			0x0300
+#define MAC_MACA0LR			0x0304
+#define MAC_MACA1HR			0x0308
+#define MAC_MACA1LR			0x030c
+
+#define MAC_QTFCR_INC			4
+#define MAC_MACA_INC			4
+
+/* MAC register entry bit positions and sizes */
+#define MAC_HWF0R_ADDMACADRSEL_INDEX	18
+#define MAC_HWF0R_ADDMACADRSEL_WIDTH	5
+#define MAC_HWF0R_ARPOFFSEL_INDEX	9
+#define MAC_HWF0R_ARPOFFSEL_WIDTH	1
+#define MAC_HWF0R_EEESEL_INDEX		13
+#define MAC_HWF0R_EEESEL_WIDTH		1
+#define MAC_HWF0R_GMIISEL_INDEX		1
+#define MAC_HWF0R_GMIISEL_WIDTH		1
+#define MAC_HWF0R_MGKSEL_INDEX		7
+#define MAC_HWF0R_MGKSEL_WIDTH		1
+#define MAC_HWF0R_MMCSEL_INDEX		8
+#define MAC_HWF0R_MMCSEL_WIDTH		1
+#define MAC_HWF0R_RWKSEL_INDEX		6
+#define MAC_HWF0R_RWKSEL_WIDTH		1
+#define MAC_HWF0R_RXCOESEL_INDEX	16
+#define MAC_HWF0R_RXCOESEL_WIDTH	1
+#define MAC_HWF0R_SAVLANINS_INDEX	27
+#define MAC_HWF0R_SAVLANINS_WIDTH	1
+#define MAC_HWF0R_SMASEL_INDEX		5
+#define MAC_HWF0R_SMASEL_WIDTH		1
+#define MAC_HWF0R_TSSEL_INDEX		12
+#define MAC_HWF0R_TSSEL_WIDTH		1
+#define MAC_HWF0R_TSSTSSEL_INDEX	25
+#define MAC_HWF0R_TSSTSSEL_WIDTH	2
+#define MAC_HWF0R_TXCOESEL_INDEX	14
+#define MAC_HWF0R_TXCOESEL_WIDTH	1
+#define MAC_HWF0R_VLHASH_INDEX		4
+#define MAC_HWF0R_VLHASH_WIDTH		1
+#define MAC_HWF1R_ADVTHWORD_INDEX	13
+#define MAC_HWF1R_ADVTHWORD_WIDTH	1
+#define MAC_HWF1R_DBGMEMA_INDEX		19
+#define MAC_HWF1R_DBGMEMA_WIDTH		1
+#define MAC_HWF1R_DCBEN_INDEX		16
+#define MAC_HWF1R_DCBEN_WIDTH		1
+#define MAC_HWF1R_HASHTBLSZ_INDEX	24
+#define MAC_HWF1R_HASHTBLSZ_WIDTH	3
+#define MAC_HWF1R_L3L4FNUM_INDEX	27
+#define MAC_HWF1R_L3L4FNUM_WIDTH	4
+#define MAC_HWF1R_RSSEN_INDEX		20
+#define MAC_HWF1R_RSSEN_WIDTH		1
+#define MAC_HWF1R_RXFIFOSIZE_INDEX	0
+#define MAC_HWF1R_RXFIFOSIZE_WIDTH	5
+#define MAC_HWF1R_SPHEN_INDEX		17
+#define MAC_HWF1R_SPHEN_WIDTH		1
+#define MAC_HWF1R_TSOEN_INDEX		18
+#define MAC_HWF1R_TSOEN_WIDTH		1
+#define MAC_HWF1R_TXFIFOSIZE_INDEX	6
+#define MAC_HWF1R_TXFIFOSIZE_WIDTH	5
+#define MAC_HWF2R_AUXSNAPNUM_INDEX	28
+#define MAC_HWF2R_AUXSNAPNUM_WIDTH	3
+#define MAC_HWF2R_PPSOUTNUM_INDEX	24
+#define MAC_HWF2R_PPSOUTNUM_WIDTH	3
+#define MAC_HWF2R_RXCHCNT_INDEX		12
+#define MAC_HWF2R_RXCHCNT_WIDTH		4
+#define MAC_HWF2R_RXQCNT_INDEX		0
+#define MAC_HWF2R_RXQCNT_WIDTH		4
+#define MAC_HWF2R_TXCHCNT_INDEX		18
+#define MAC_HWF2R_TXCHCNT_WIDTH		4
+#define MAC_HWF2R_TXQCNT_INDEX		6
+#define MAC_HWF2R_TXQCNT_WIDTH		4
+#define MAC_ISR_MMCRXIS_INDEX		9
+#define MAC_ISR_MMCRXIS_WIDTH		1
+#define MAC_ISR_MMCTXIS_INDEX		10
+#define MAC_ISR_MMCTXIS_WIDTH		1
+#define MAC_ISR_PMTIS_INDEX		4
+#define MAC_ISR_PMTIS_WIDTH		1
+#define MAC_MACA1HR_AE_INDEX		31
+#define MAC_MACA1HR_AE_WIDTH		1
+#define MAC_PFR_HMC_INDEX		2
+#define MAC_PFR_HMC_WIDTH		1
+#define MAC_PFR_HUC_INDEX		1
+#define MAC_PFR_HUC_WIDTH		1
+#define MAC_PFR_PM_INDEX		4
+#define MAC_PFR_PM_WIDTH		1
+#define MAC_PFR_PR_INDEX		0
+#define MAC_PFR_PR_WIDTH		1
+#define MAC_PMTCSR_MGKPKTEN_INDEX	1
+#define MAC_PMTCSR_MGKPKTEN_WIDTH	1
+#define MAC_PMTCSR_PWRDWN_INDEX		0
+#define MAC_PMTCSR_PWRDWN_WIDTH		1
+#define MAC_PMTCSR_RWKFILTRST_INDEX	31
+#define MAC_PMTCSR_RWKFILTRST_WIDTH	1
+#define MAC_PMTCSR_RWKPKTEN_INDEX	2
+#define MAC_PMTCSR_RWKPKTEN_WIDTH	1
+#define MAC_Q0TFCR_PT_INDEX		16
+#define MAC_Q0TFCR_PT_WIDTH		16
+#define MAC_Q0TFCR_TFE_INDEX		1
+#define MAC_Q0TFCR_TFE_WIDTH		1
+#define MAC_RCR_ACS_INDEX		1
+#define MAC_RCR_ACS_WIDTH		1
+#define MAC_RCR_CST_INDEX		2
+#define MAC_RCR_CST_WIDTH		1
+#define MAC_RCR_DCRCC_INDEX		3
+#define MAC_RCR_DCRCC_WIDTH		1
+#define MAC_RCR_IPC_INDEX		9
+#define MAC_RCR_IPC_WIDTH		1
+#define MAC_RCR_JE_INDEX		8
+#define MAC_RCR_JE_WIDTH		1
+#define MAC_RCR_LM_INDEX		10
+#define MAC_RCR_LM_WIDTH		1
+#define MAC_RCR_RE_INDEX		0
+#define MAC_RCR_RE_WIDTH		1
+#define MAC_RFCR_RFE_INDEX		0
+#define MAC_RFCR_RFE_WIDTH		1
+#define MAC_RQC0R_RXQ0EN_INDEX		0
+#define MAC_RQC0R_RXQ0EN_WIDTH		2
+#define MAC_TCR_SS_INDEX		29
+#define MAC_TCR_SS_WIDTH		2
+#define MAC_TCR_TE_INDEX		0
+#define MAC_TCR_TE_WIDTH		1
+#define MAC_VLANTR_DOVLTC_INDEX		20
+#define MAC_VLANTR_DOVLTC_WIDTH		1
+#define MAC_VLANTR_ERSVLM_INDEX		19
+#define MAC_VLANTR_ERSVLM_WIDTH		1
+#define MAC_VLANTR_ESVL_INDEX		18
+#define MAC_VLANTR_ESVL_WIDTH		1
+#define MAC_VLANTR_EVLS_INDEX		21
+#define MAC_VLANTR_EVLS_WIDTH		2
+#define MAC_VLANTR_EVLRXS_INDEX		24
+#define MAC_VLANTR_EVLRXS_WIDTH		1
+#define MAC_VR_DEVID_INDEX		8
+#define MAC_VR_DEVID_WIDTH		8
+#define MAC_VR_SNPSVER_INDEX		0
+#define MAC_VR_SNPSVER_WIDTH		8
+#define MAC_VR_USERVER_INDEX		16
+#define MAC_VR_USERVER_WIDTH		8
+
+/* MMC register offsets */
+#define MMC_CR				0x0800
+#define MMC_RISR			0x0804
+#define MMC_TISR			0x0808
+#define MMC_RIER			0x080c
+#define MMC_TIER			0x0810
+#define MMC_TXOCTETCOUNT_GB_LO		0x0814
+#define MMC_TXOCTETCOUNT_GB_HI		0x0818
+#define MMC_TXFRAMECOUNT_GB_LO		0x081c
+#define MMC_TXFRAMECOUNT_GB_HI		0x0820
+#define MMC_TXBROADCASTFRAMES_G_LO	0x0824
+#define MMC_TXBROADCASTFRAMES_G_HI	0x0828
+#define MMC_TXMULTICASTFRAMES_G_LO	0x082c
+#define MMC_TXMULTICASTFRAMES_G_HI	0x0830
+#define MMC_TX64OCTETS_GB_LO		0x0834
+#define MMC_TX64OCTETS_GB_HI		0x0838
+#define MMC_TX65TO127OCTETS_GB_LO	0x083c
+#define MMC_TX65TO127OCTETS_GB_HI	0x0840
+#define MMC_TX128TO255OCTETS_GB_LO	0x0844
+#define MMC_TX128TO255OCTETS_GB_HI	0x0848
+#define MMC_TX256TO511OCTETS_GB_LO	0x084c
+#define MMC_TX256TO511OCTETS_GB_HI	0x0850
+#define MMC_TX512TO1023OCTETS_GB_LO	0x0854
+#define MMC_TX512TO1023OCTETS_GB_HI	0x0858
+#define MMC_TX1024TOMAXOCTETS_GB_LO	0x085c
+#define MMC_TX1024TOMAXOCTETS_GB_HI	0x0860
+#define MMC_TXUNICASTFRAMES_GB_LO	0x0864
+#define MMC_TXUNICASTFRAMES_GB_HI	0x0868
+#define MMC_TXMULTICASTFRAMES_GB_LO	0x086c
+#define MMC_TXMULTICASTFRAMES_GB_HI	0x0870
+#define MMC_TXBROADCASTFRAMES_GB_LO	0x0874
+#define MMC_TXBROADCASTFRAMES_GB_HI	0x0878
+#define MMC_TXUNDERFLOWERROR_LO		0x087c
+#define MMC_TXUNDERFLOWERROR_HI		0x0880
+#define MMC_TXOCTETCOUNT_G_LO		0x0884
+#define MMC_TXOCTETCOUNT_G_HI		0x0888
+#define MMC_TXFRAMECOUNT_G_LO		0x088c
+#define MMC_TXFRAMECOUNT_G_HI		0x0890
+#define MMC_TXPAUSEFRAMES_LO		0x0894
+#define MMC_TXPAUSEFRAMES_HI		0x0898
+#define MMC_TXVLANFRAMES_G_LO		0x089c
+#define MMC_TXVLANFRAMES_G_HI		0x08a0
+#define MMC_RXFRAMECOUNT_GB_LO		0x0900
+#define MMC_RXFRAMECOUNT_GB_HI		0x0904
+#define MMC_RXOCTETCOUNT_GB_LO		0x0908
+#define MMC_RXOCTETCOUNT_GB_HI		0x090c
+#define MMC_RXOCTETCOUNT_G_LO		0x0910
+#define MMC_RXOCTETCOUNT_G_HI		0x0914
+#define MMC_RXBROADCASTFRAMES_G_LO	0x0918
+#define MMC_RXBROADCASTFRAMES_G_HI	0x091c
+#define MMC_RXMULTICASTFRAMES_G_LO	0x0920
+#define MMC_RXMULTICASTFRAMES_G_HI	0x0924
+#define MMC_RXCRCERROR_LO		0x0928
+#define MMC_RXCRCERROR_HI		0x092c
+#define MMC_RXRUNTERROR			0x0930
+#define MMC_RXJABBERERROR		0x0934
+#define MMC_RXUNDERSIZE_G		0x0938
+#define MMC_RXOVERSIZE_G		0x093c
+#define MMC_RX64OCTETS_GB_LO		0x0940
+#define MMC_RX64OCTETS_GB_HI		0x0944
+#define MMC_RX65TO127OCTETS_GB_LO	0x0948
+#define MMC_RX65TO127OCTETS_GB_HI	0x094c
+#define MMC_RX128TO255OCTETS_GB_LO	0x0950
+#define MMC_RX128TO255OCTETS_GB_HI	0x0954
+#define MMC_RX256TO511OCTETS_GB_LO	0x0958
+#define MMC_RX256TO511OCTETS_GB_HI	0x095c
+#define MMC_RX512TO1023OCTETS_GB_LO	0x0960
+#define MMC_RX512TO1023OCTETS_GB_HI	0x0964
+#define MMC_RX1024TOMAXOCTETS_GB_LO	0x0968
+#define MMC_RX1024TOMAXOCTETS_GB_HI	0x096c
+#define MMC_RXUNICASTFRAMES_G_LO	0x0970
+#define MMC_RXUNICASTFRAMES_G_HI	0x0974
+#define MMC_RXLENGTHERROR_LO		0x0978
+#define MMC_RXLENGTHERROR_HI		0x097c
+#define MMC_RXOUTOFRANGETYPE_LO		0x0980
+#define MMC_RXOUTOFRANGETYPE_HI		0x0984
+#define MMC_RXPAUSEFRAMES_LO		0x0988
+#define MMC_RXPAUSEFRAMES_HI		0x098c
+#define MMC_RXFIFOOVERFLOW_LO		0x0990
+#define MMC_RXFIFOOVERFLOW_HI		0x0994
+#define MMC_RXVLANFRAMES_GB_LO		0x0998
+#define MMC_RXVLANFRAMES_GB_HI		0x099c
+#define MMC_RXWATCHDOGERROR		0x09a0
+
+/* MMC register entry bit positions and sizes */
+#define MMC_CR_CR_INDEX				0
+#define MMC_CR_CR_WIDTH				1
+#define MMC_CR_CSR_INDEX			1
+#define MMC_CR_CSR_WIDTH			1
+#define MMC_CR_ROR_INDEX			2
+#define MMC_CR_ROR_WIDTH			1
+#define MMC_CR_MCF_INDEX			3
+#define MMC_CR_MCF_WIDTH			1
+#define MMC_CR_MCT_INDEX			4
+#define MMC_CR_MCT_WIDTH			2
+#define MMC_RIER_ALL_INTERRUPTS_INDEX		0
+#define MMC_RIER_ALL_INTERRUPTS_WIDTH		23
+#define MMC_RISR_RXFRAMECOUNT_GB_INDEX		0
+#define MMC_RISR_RXFRAMECOUNT_GB_WIDTH		1
+#define MMC_RISR_RXOCTETCOUNT_GB_INDEX		1
+#define MMC_RISR_RXOCTETCOUNT_GB_WIDTH		1
+#define MMC_RISR_RXOCTETCOUNT_G_INDEX		2
+#define MMC_RISR_RXOCTETCOUNT_G_WIDTH		1
+#define MMC_RISR_RXBROADCASTFRAMES_G_INDEX	3
+#define MMC_RISR_RXBROADCASTFRAMES_G_WIDTH	1
+#define MMC_RISR_RXMULTICASTFRAMES_G_INDEX	4
+#define MMC_RISR_RXMULTICASTFRAMES_G_WIDTH	1
+#define MMC_RISR_RXCRCERROR_INDEX		5
+#define MMC_RISR_RXCRCERROR_WIDTH		1
+#define MMC_RISR_RXRUNTERROR_INDEX		6
+#define MMC_RISR_RXRUNTERROR_WIDTH		1
+#define MMC_RISR_RXJABBERERROR_INDEX		7
+#define MMC_RISR_RXJABBERERROR_WIDTH		1
+#define MMC_RISR_RXUNDERSIZE_G_INDEX		8
+#define MMC_RISR_RXUNDERSIZE_G_WIDTH		1
+#define MMC_RISR_RXOVERSIZE_G_INDEX		9
+#define MMC_RISR_RXOVERSIZE_G_WIDTH		1
+#define MMC_RISR_RX64OCTETS_GB_INDEX		10
+#define MMC_RISR_RX64OCTETS_GB_WIDTH		1
+#define MMC_RISR_RX65TO127OCTETS_GB_INDEX	11
+#define MMC_RISR_RX65TO127OCTETS_GB_WIDTH	1
+#define MMC_RISR_RX128TO255OCTETS_GB_INDEX	12
+#define MMC_RISR_RX128TO255OCTETS_GB_WIDTH	1
+#define MMC_RISR_RX256TO511OCTETS_GB_INDEX	13
+#define MMC_RISR_RX256TO511OCTETS_GB_WIDTH	1
+#define MMC_RISR_RX512TO1023OCTETS_GB_INDEX	14
+#define MMC_RISR_RX512TO1023OCTETS_GB_WIDTH	1
+#define MMC_RISR_RX1024TOMAXOCTETS_GB_INDEX	15
+#define MMC_RISR_RX1024TOMAXOCTETS_GB_WIDTH	1
+#define MMC_RISR_RXUNICASTFRAMES_G_INDEX	16
+#define MMC_RISR_RXUNICASTFRAMES_G_WIDTH	1
+#define MMC_RISR_RXLENGTHERROR_INDEX		17
+#define MMC_RISR_RXLENGTHERROR_WIDTH		1
+#define MMC_RISR_RXOUTOFRANGETYPE_INDEX		18
+#define MMC_RISR_RXOUTOFRANGETYPE_WIDTH		1
+#define MMC_RISR_RXPAUSEFRAMES_INDEX		19
+#define MMC_RISR_RXPAUSEFRAMES_WIDTH		1
+#define MMC_RISR_RXFIFOOVERFLOW_INDEX		20
+#define MMC_RISR_RXFIFOOVERFLOW_WIDTH		1
+#define MMC_RISR_RXVLANFRAMES_GB_INDEX		21
+#define MMC_RISR_RXVLANFRAMES_GB_WIDTH		1
+#define MMC_RISR_RXWATCHDOGERROR_INDEX		22
+#define MMC_RISR_RXWATCHDOGERROR_WIDTH		1
+#define MMC_TIER_ALL_INTERRUPTS_INDEX		0
+#define MMC_TIER_ALL_INTERRUPTS_WIDTH		18
+#define MMC_TISR_TXOCTETCOUNT_GB_INDEX		0
+#define MMC_TISR_TXOCTETCOUNT_GB_WIDTH		1
+#define MMC_TISR_TXFRAMECOUNT_GB_INDEX		1
+#define MMC_TISR_TXFRAMECOUNT_GB_WIDTH		1
+#define MMC_TISR_TXBROADCASTFRAMES_G_INDEX	2
+#define MMC_TISR_TXBROADCASTFRAMES_G_WIDTH	1
+#define MMC_TISR_TXMULTICASTFRAMES_G_INDEX	3
+#define MMC_TISR_TXMULTICASTFRAMES_G_WIDTH	1
+#define MMC_TISR_TX64OCTETS_GB_INDEX		4
+#define MMC_TISR_TX64OCTETS_GB_WIDTH		1
+#define MMC_TISR_TX65TO127OCTETS_GB_INDEX	5
+#define MMC_TISR_TX65TO127OCTETS_GB_WIDTH	1
+#define MMC_TISR_TX128TO255OCTETS_GB_INDEX	6
+#define MMC_TISR_TX128TO255OCTETS_GB_WIDTH	1
+#define MMC_TISR_TX256TO511OCTETS_GB_INDEX	7
+#define MMC_TISR_TX256TO511OCTETS_GB_WIDTH	1
+#define MMC_TISR_TX512TO1023OCTETS_GB_INDEX	8
+#define MMC_TISR_TX512TO1023OCTETS_GB_WIDTH	1
+#define MMC_TISR_TX1024TOMAXOCTETS_GB_INDEX	9
+#define MMC_TISR_TX1024TOMAXOCTETS_GB_WIDTH	1
+#define MMC_TISR_TXUNICASTFRAMES_GB_INDEX	10
+#define MMC_TISR_TXUNICASTFRAMES_GB_WIDTH	1
+#define MMC_TISR_TXMULTICASTFRAMES_GB_INDEX	11
+#define MMC_TISR_TXMULTICASTFRAMES_GB_WIDTH	1
+#define MMC_TISR_TXBROADCASTFRAMES_GB_INDEX	12
+#define MMC_TISR_TXBROADCASTFRAMES_GB_WIDTH	1
+#define MMC_TISR_TXUNDERFLOWERROR_INDEX		13
+#define MMC_TISR_TXUNDERFLOWERROR_WIDTH		1
+#define MMC_TISR_TXOCTETCOUNT_G_INDEX		14
+#define MMC_TISR_TXOCTETCOUNT_G_WIDTH		1
+#define MMC_TISR_TXFRAMECOUNT_G_INDEX		15
+#define MMC_TISR_TXFRAMECOUNT_G_WIDTH		1
+#define MMC_TISR_TXPAUSEFRAMES_INDEX		16
+#define MMC_TISR_TXPAUSEFRAMES_WIDTH		1
+#define MMC_TISR_TXVLANFRAMES_G_INDEX		17
+#define MMC_TISR_TXVLANFRAMES_G_WIDTH		1
+
+/* MTL register offsets */
+#define MTL_OMR				0x1000
+#define MTL_FDCR			0x1008
+#define MTL_FDSR			0x100c
+#define MTL_FDDR			0x1010
+#define MTL_ISR				0x1020
+#define MTL_RQDCM0R			0x1030
+#define MTL_TCPM0R			0x1040
+#define MTL_TCPM1R			0x1044
+
+#define MTL_RQDCM_INC			4
+#define MTL_RQDCM_Q_PER_REG		4
+
+/* MTL register entry bit positions and sizes */
+#define MTL_OMR_ETSALG_INDEX		5
+#define MTL_OMR_ETSALG_WIDTH		2
+#define MTL_OMR_RAA_INDEX		2
+#define MTL_OMR_RAA_WIDTH		1
+
+/* MTL queue register offsets
+ *   Multiple queues can be active.  The first queue has registers
+ *   that begin at 0x1100.  Each subsequent queue has registers that
+ *   are accessed using an offset of 0x80 from the previous queue.
+ */
+#define MTL_Q_BASE			0x1100
+#define MTL_Q_INC			0x80
+
+#define MTL_Q_TQOMR			0x00
+#define MTL_Q_TQUR			0x04
+#define MTL_Q_TQDR			0x08
+#define MTL_Q_TCECR			0x10
+#define MTL_Q_TCESR			0x14
+#define MTL_Q_TCQWR			0x18
+#define MTL_Q_RQOMR			0x40
+#define MTL_Q_RQMPOCR			0x44
+#define MTL_Q_RQDR			0x4c
+#define MTL_Q_IER			0x70
+#define MTL_Q_ISR			0x74
+
+/* MTL queue register entry bit positions and sizes */
+#define MTL_Q_TCQWR_QW_INDEX		0
+#define MTL_Q_TCQWR_QW_WIDTH		21
+#define MTL_Q_RQOMR_EHFC_INDEX		7
+#define MTL_Q_RQOMR_EHFC_WIDTH		1
+#define MTL_Q_RQOMR_RFA_INDEX		8
+#define MTL_Q_RQOMR_RFA_WIDTH		3
+#define MTL_Q_RQOMR_RFD_INDEX		13
+#define MTL_Q_RQOMR_RFD_WIDTH		3
+#define MTL_Q_RQOMR_RQS_INDEX		16
+#define MTL_Q_RQOMR_RQS_WIDTH		9
+#define MTL_Q_RQOMR_RSF_INDEX		5
+#define MTL_Q_RQOMR_RSF_WIDTH		1
+#define MTL_Q_RQOMR_RTC_INDEX		0
+#define MTL_Q_RQOMR_RTC_WIDTH		2
+#define MTL_Q_TQOMR_FTQ_INDEX		0
+#define MTL_Q_TQOMR_FTQ_WIDTH		1
+#define MTL_Q_TQOMR_TQS_INDEX		16
+#define MTL_Q_TQOMR_TQS_WIDTH		10
+#define MTL_Q_TQOMR_TSF_INDEX		1
+#define MTL_Q_TQOMR_TSF_WIDTH		1
+#define MTL_Q_TQOMR_TTC_INDEX		4
+#define MTL_Q_TQOMR_TTC_WIDTH		3
+#define MTL_Q_TQOMR_TXQEN_INDEX		2
+#define MTL_Q_TQOMR_TXQEN_WIDTH		2
+
+/* MTL queue register value */
+#define MTL_RSF_DISABLE			0x00
+#define MTL_RSF_ENABLE			0x01
+#define MTL_TSF_DISABLE			0x00
+#define MTL_TSF_ENABLE			0x01
+
+#define MTL_RX_THRESHOLD_64		0x00
+#define MTL_RX_THRESHOLD_96		0x02
+#define MTL_RX_THRESHOLD_128		0x03
+#define MTL_TX_THRESHOLD_32		0x01
+#define MTL_TX_THRESHOLD_64		0x00
+#define MTL_TX_THRESHOLD_96		0x02
+#define MTL_TX_THRESHOLD_128		0x03
+#define MTL_TX_THRESHOLD_192		0x04
+#define MTL_TX_THRESHOLD_256		0x05
+#define MTL_TX_THRESHOLD_384		0x06
+#define MTL_TX_THRESHOLD_512		0x07
+
+#define MTL_ETSALG_WRR			0x00
+#define MTL_ETSALG_WFQ			0x01
+#define MTL_ETSALG_DWRR			0x02
+#define MTL_RAA_SP			0x00
+#define MTL_RAA_WSP			0x01
+
+#define MTL_Q_DISABLED			0x00
+#define MTL_Q_ENABLED			0x02
+
+
+/* MTL traffic class register offsets
+ *   Multiple traffic classes can be active.  The first class has registers
+ *   that begin at 0x1100.  Each subsequent queue has registers that
+ *   are accessed using an offset of 0x80 from the previous queue.
+ */
+#define MTL_TC_BASE			MTL_Q_BASE
+#define MTL_TC_INC			MTL_Q_INC
+
+#define MTL_TC_ETSCR			0x10
+
+/* MTL traffic class register entry bit positions and sizes */
+#define MTL_TC_ETSCR_TSA_INDEX		0
+#define MTL_TC_ETSCR_TSA_WIDTH		2
+
+/* MTL traffic class register value */
+#define MTL_TSA_SP			0x00
+#define MTL_TSA_ETS			0x02
+
+
+/* PCS MMD select register offset
+ *  The MMD select register is used for accessing PCS registers
+ *  when the underlying APB3 interface is using indirect addressing.
+ *  Indirect addressing requires accessing registers in two phases,
+ *  an address phase and a data phase.  The address phases requires
+ *  writing an address selection value to the MMD select regiesters.
+ */
+#define PCS_MMD_SELECT			0xff
+
+
+/* Descriptor/Packet entry bit positions and sizes */
+#define RX_PACKET_ERRORS_CRC_INDEX		2
+#define RX_PACKET_ERRORS_CRC_WIDTH		1
+#define RX_PACKET_ERRORS_FRAME_INDEX		3
+#define RX_PACKET_ERRORS_FRAME_WIDTH		1
+#define RX_PACKET_ERRORS_LENGTH_INDEX		0
+#define RX_PACKET_ERRORS_LENGTH_WIDTH		1
+#define RX_PACKET_ERRORS_OVERRUN_INDEX		1
+#define RX_PACKET_ERRORS_OVERRUN_WIDTH		1
+
+#define RX_PACKET_ATTRIBUTES_CSUM_DONE_INDEX	0
+#define RX_PACKET_ATTRIBUTES_CSUM_DONE_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_INDEX	1
+#define RX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH	1
+#define RX_PACKET_ATTRIBUTES_INCOMPLETE_INDEX	2
+#define RX_PACKET_ATTRIBUTES_INCOMPLETE_WIDTH	1
+
+#define RX_NORMAL_DESC0_OVT_INDEX		0
+#define RX_NORMAL_DESC0_OVT_WIDTH		16
+#define RX_NORMAL_DESC3_ES_INDEX		15
+#define RX_NORMAL_DESC3_ES_WIDTH		1
+#define RX_NORMAL_DESC3_ETLT_INDEX		16
+#define RX_NORMAL_DESC3_ETLT_WIDTH		4
+#define RX_NORMAL_DESC3_INTE_INDEX		30
+#define RX_NORMAL_DESC3_INTE_WIDTH		1
+#define RX_NORMAL_DESC3_LD_INDEX		28
+#define RX_NORMAL_DESC3_LD_WIDTH		1
+#define RX_NORMAL_DESC3_OWN_INDEX		31
+#define RX_NORMAL_DESC3_OWN_WIDTH		1
+#define RX_NORMAL_DESC3_PL_INDEX		0
+#define RX_NORMAL_DESC3_PL_WIDTH		14
+
+#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_INDEX	0
+#define TX_PACKET_ATTRIBUTES_CSUM_ENABLE_WIDTH	1
+#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_INDEX	1
+#define TX_PACKET_ATTRIBUTES_TSO_ENABLE_WIDTH	1
+#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_INDEX	2
+#define TX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH	1
+
+#define TX_CONTEXT_DESC2_MSS_INDEX		0
+#define TX_CONTEXT_DESC2_MSS_WIDTH		15
+#define TX_CONTEXT_DESC3_CTXT_INDEX		30
+#define TX_CONTEXT_DESC3_CTXT_WIDTH		1
+#define TX_CONTEXT_DESC3_TCMSSV_INDEX		26
+#define TX_CONTEXT_DESC3_TCMSSV_WIDTH		1
+#define TX_CONTEXT_DESC3_VLTV_INDEX		16
+#define TX_CONTEXT_DESC3_VLTV_WIDTH		1
+#define TX_CONTEXT_DESC3_VT_INDEX		0
+#define TX_CONTEXT_DESC3_VT_WIDTH		16
+
+#define TX_NORMAL_DESC2_HL_B1L_INDEX		0
+#define TX_NORMAL_DESC2_HL_B1L_WIDTH		14
+#define TX_NORMAL_DESC2_IC_INDEX		31
+#define TX_NORMAL_DESC2_IC_WIDTH		1
+#define TX_NORMAL_DESC2_VTIR_INDEX		14
+#define TX_NORMAL_DESC2_VTIR_WIDTH		2
+#define TX_NORMAL_DESC3_CIC_INDEX		16
+#define TX_NORMAL_DESC3_CIC_WIDTH		2
+#define TX_NORMAL_DESC3_CPC_INDEX		26
+#define TX_NORMAL_DESC3_CPC_WIDTH		2
+#define TX_NORMAL_DESC3_CTXT_INDEX		30
+#define TX_NORMAL_DESC3_CTXT_WIDTH		1
+#define TX_NORMAL_DESC3_FD_INDEX		29
+#define TX_NORMAL_DESC3_FD_WIDTH		1
+#define TX_NORMAL_DESC3_FL_INDEX		0
+#define TX_NORMAL_DESC3_FL_WIDTH		15
+#define TX_NORMAL_DESC3_LD_INDEX		28
+#define TX_NORMAL_DESC3_LD_WIDTH		1
+#define TX_NORMAL_DESC3_OWN_INDEX		31
+#define TX_NORMAL_DESC3_OWN_WIDTH		1
+#define TX_NORMAL_DESC3_TCPHDRLEN_INDEX		19
+#define TX_NORMAL_DESC3_TCPHDRLEN_WIDTH		4
+#define TX_NORMAL_DESC3_TCPPL_INDEX		0
+#define TX_NORMAL_DESC3_TCPPL_WIDTH		18
+#define TX_NORMAL_DESC3_TSE_INDEX		18
+#define TX_NORMAL_DESC3_TSE_WIDTH		1
+
+#define TX_NORMAL_DESC2_VLAN_INSERT		0x2
+
+/* MDIO undefined or vendor specific registers */
+#ifndef MDIO_AN_COMP_STAT
+#define MDIO_AN_COMP_STAT		0x0030
+#endif
+
+
+/* Bit setting and getting macros
+ *  The get macro will extract the current bit field value from within
+ *  the variable
+ *
+ *  The set macro will clear the current bit field value within the
+ *  variable and then set the bit field of the variable to the
+ *  specified value
+ */
+#define GET_BITS(_var, _index, _width)					\
+	(((_var) >> (_index)) & ((0x1 << (_width)) - 1))
+
+#define SET_BITS(_var, _index, _width, _val)				\
+do {									\
+	(_var) &= ~(((0x1 << (_width)) - 1) << (_index));		\
+	(_var) |= (((_val) & ((0x1 << (_width)) - 1)) << (_index));	\
+} while (0)
+
+#define GET_BITS_LE(_var, _index, _width)				\
+	((le32_to_cpu((_var)) >> (_index)) & ((0x1 << (_width)) - 1))
+
+#define SET_BITS_LE(_var, _index, _width, _val)				\
+do {									\
+	(_var) &= cpu_to_le32(~(((0x1 << (_width)) - 1) << (_index)));	\
+	(_var) |= cpu_to_le32((((_val) &				\
+			      ((0x1 << (_width)) - 1)) << (_index)));	\
+} while (0)
+
+
+/* Bit setting and getting macros based on register fields
+ *  The get macro uses the bit field definitions formed using the input
+ *  names to extract the current bit field value from within the
+ *  variable
+ *
+ *  The set macro uses the bit field definitions formed using the input
+ *  names to set the bit field of the variable to the specified value
+ */
+#define XGMAC_GET_BITS(_var, _prefix, _field)				\
+	GET_BITS((_var),						\
+		 _prefix##_##_field##_INDEX,				\
+		 _prefix##_##_field##_WIDTH)
+
+#define XGMAC_SET_BITS(_var, _prefix, _field, _val)			\
+	SET_BITS((_var),						\
+		 _prefix##_##_field##_INDEX,				\
+		 _prefix##_##_field##_WIDTH, (_val))
+
+#define XGMAC_GET_BITS_LE(_var, _prefix, _field)			\
+	GET_BITS_LE((_var),						\
+		 _prefix##_##_field##_INDEX,				\
+		 _prefix##_##_field##_WIDTH)
+
+#define XGMAC_SET_BITS_LE(_var, _prefix, _field, _val)			\
+	SET_BITS_LE((_var),						\
+		 _prefix##_##_field##_INDEX,				\
+		 _prefix##_##_field##_WIDTH, (_val))
+
+
+/* Macros for reading or writing registers
+ *  The ioread macros will get bit fields or full values using the
+ *  register definitions formed using the input names
+ *
+ *  The iowrite macros will set bit fields or full values using the
+ *  register definitions formed using the input names
+ */
+#define XGMAC_IOREAD(_pdata, _reg)					\
+	ioread32((_pdata)->xgmac_regs + _reg)
+
+#define XGMAC_IOREAD_BITS(_pdata, _reg, _field)				\
+	GET_BITS(XGMAC_IOREAD((_pdata), _reg),				\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH)
+
+#define XGMAC_IOWRITE(_pdata, _reg, _val)				\
+	iowrite32((_val), (_pdata)->xgmac_regs + _reg)
+
+#define XGMAC_IOWRITE_BITS(_pdata, _reg, _field, _val)			\
+do {									\
+	u32 reg_val = XGMAC_IOREAD((_pdata), _reg);			\
+	SET_BITS(reg_val,						\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH, (_val));			\
+	XGMAC_IOWRITE((_pdata), _reg, reg_val);				\
+} while (0)
+
+
+/* Macros for reading or writing MTL queue or traffic class registers
+ *  Similar to the standard read and write macros except that the
+ *  base register value is calculated by the queue or traffic class number
+ */
+#define XGMAC_MTL_IOREAD(_pdata, _n, _reg)				\
+	ioread32((_pdata)->xgmac_regs +					\
+		 MTL_Q_BASE + ((_n) * MTL_Q_INC) + _reg)
+
+#define XGMAC_MTL_IOREAD_BITS(_pdata, _n, _reg, _field)			\
+	GET_BITS(XGMAC_MTL_IOREAD((_pdata), (_n), _reg),		\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH)
+
+#define XGMAC_MTL_IOWRITE(_pdata, _n, _reg, _val)			\
+	iowrite32((_val), (_pdata)->xgmac_regs +			\
+		  MTL_Q_BASE + ((_n) * MTL_Q_INC) + _reg)
+
+#define XGMAC_MTL_IOWRITE_BITS(_pdata, _n, _reg, _field, _val)		\
+do {									\
+	u32 reg_val = XGMAC_MTL_IOREAD((_pdata), (_n), _reg);		\
+	SET_BITS(reg_val,						\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH, (_val));			\
+	XGMAC_MTL_IOWRITE((_pdata), (_n), _reg, reg_val);		\
+} while (0)
+
+
+/* Macros for reading or writing DMA channel registers
+ *  Similar to the standard read and write macros except that the
+ *  base register value is obtained from the ring
+ */
+#define XGMAC_DMA_IOREAD(_channel, _reg)				\
+	ioread32((_channel)->dma_regs + _reg)
+
+#define XGMAC_DMA_IOREAD_BITS(_channel, _reg, _field)			\
+	GET_BITS(XGMAC_DMA_IOREAD((_channel), _reg),			\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH)
+
+#define XGMAC_DMA_IOWRITE(_channel, _reg, _val)				\
+	iowrite32((_val), (_channel)->dma_regs + _reg)
+
+#define XGMAC_DMA_IOWRITE_BITS(_channel, _reg, _field, _val)		\
+do {									\
+	u32 reg_val = XGMAC_DMA_IOREAD((_channel), _reg);		\
+	SET_BITS(reg_val,						\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH, (_val));			\
+	XGMAC_DMA_IOWRITE((_channel), _reg, reg_val);			\
+} while (0)
+
+
+/* Macros for building, reading or writing register values or bits
+ * within the register values of XPCS registers.
+ */
+#define XPCS_IOWRITE(_pdata, _off, _val)				\
+	iowrite32(_val, (_pdata)->xpcs_regs + (_off))
+
+#define XPCS_IOREAD(_pdata, _off)					\
+	ioread32((_pdata)->xpcs_regs + (_off))
+
+
+/* Macros for building, reading or writing register values or bits
+ * using MDIO.  Different from above because of the use of standardized
+ * Linux include values.  No shifting is performed with the bit
+ * operations, everything works on mask values.
+ */
+#define XMDIO_READ(_pdata, _mmd, _reg)					\
+	((_pdata)->hw_if.read_mmd_regs((_pdata), 0,			\
+		MII_ADDR_C45 | (_mmd << 16) | ((_reg) & 0xffff)))
+
+#define XMDIO_READ_BITS(_pdata, _mmd, _reg, _mask)			\
+	(XMDIO_READ((_pdata), _mmd, _reg) & _mask)
+
+#define XMDIO_WRITE(_pdata, _mmd, _reg, _val)				\
+	((_pdata)->hw_if.write_mmd_regs((_pdata), 0,			\
+		MII_ADDR_C45 | (_mmd << 16) | ((_reg) & 0xffff), (_val)))
+
+#define XMDIO_WRITE_BITS(_pdata, _mmd, _reg, _mask, _val)		\
+do {									\
+	u32 mmd_val = XMDIO_READ((_pdata), _mmd, _reg);			\
+	mmd_val &= ~_mask;						\
+	mmd_val |= (_val);						\
+	XMDIO_WRITE((_pdata), _mmd, _reg, mmd_val);			\
+} while (0)
+
+#endif
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
new file mode 100644
index 00000000000..6bb76d5c817
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c
@@ -0,0 +1,375 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+
+static ssize_t xgbe_common_read(char __user *buffer, size_t count,
+				loff_t *ppos, unsigned int value)
+{
+	char *buf;
+	ssize_t len;
+
+	if (*ppos != 0)
+		return 0;
+
+	buf = kasprintf(GFP_KERNEL, "0x%08x\n", value);
+	if (!buf)
+		return -ENOMEM;
+
+	if (count < strlen(buf)) {
+		kfree(buf);
+		return -ENOSPC;
+	}
+
+	len = simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+	kfree(buf);
+
+	return len;
+}
+
+static ssize_t xgbe_common_write(const char __user *buffer, size_t count,
+				 loff_t *ppos, unsigned int *value)
+{
+	char workarea[32];
+	ssize_t len;
+	unsigned int scan_value;
+
+	if (*ppos != 0)
+		return 0;
+
+	if (count >= sizeof(workarea))
+		return -ENOSPC;
+
+	len = simple_write_to_buffer(workarea, sizeof(workarea) - 1, ppos,
+				     buffer, count);
+	if (len < 0)
+		return len;
+
+	workarea[len] = '\0';
+	if (sscanf(workarea, "%x", &scan_value) == 1)
+		*value = scan_value;
+	else
+		return -EIO;
+
+	return len;
+}
+
+static ssize_t xgmac_reg_addr_read(struct file *filp, char __user *buffer,
+				   size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+
+	return xgbe_common_read(buffer, count, ppos, pdata->debugfs_xgmac_reg);
+}
+
+static ssize_t xgmac_reg_addr_write(struct file *filp,
+				    const char __user *buffer,
+				    size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+
+	return xgbe_common_write(buffer, count, ppos,
+				 &pdata->debugfs_xgmac_reg);
+}
+
+static ssize_t xgmac_reg_value_read(struct file *filp, char __user *buffer,
+				    size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+	unsigned int value;
+
+	value = XGMAC_IOREAD(pdata, pdata->debugfs_xgmac_reg);
+
+	return xgbe_common_read(buffer, count, ppos, value);
+}
+
+static ssize_t xgmac_reg_value_write(struct file *filp,
+				     const char __user *buffer,
+				     size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+	unsigned int value;
+	ssize_t len;
+
+	len = xgbe_common_write(buffer, count, ppos, &value);
+	if (len < 0)
+		return len;
+
+	XGMAC_IOWRITE(pdata, pdata->debugfs_xgmac_reg, value);
+
+	return len;
+}
+
+static const struct file_operations xgmac_reg_addr_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read =  xgmac_reg_addr_read,
+	.write = xgmac_reg_addr_write,
+};
+
+static const struct file_operations xgmac_reg_value_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read =  xgmac_reg_value_read,
+	.write = xgmac_reg_value_write,
+};
+
+static ssize_t xpcs_mmd_read(struct file *filp, char __user *buffer,
+			     size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+
+	return xgbe_common_read(buffer, count, ppos, pdata->debugfs_xpcs_mmd);
+}
+
+static ssize_t xpcs_mmd_write(struct file *filp, const char __user *buffer,
+			      size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+
+	return xgbe_common_write(buffer, count, ppos,
+				 &pdata->debugfs_xpcs_mmd);
+}
+
+static ssize_t xpcs_reg_addr_read(struct file *filp, char __user *buffer,
+				  size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+
+	return xgbe_common_read(buffer, count, ppos, pdata->debugfs_xpcs_reg);
+}
+
+static ssize_t xpcs_reg_addr_write(struct file *filp, const char __user *buffer,
+				   size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+
+	return xgbe_common_write(buffer, count, ppos,
+				 &pdata->debugfs_xpcs_reg);
+}
+
+static ssize_t xpcs_reg_value_read(struct file *filp, char __user *buffer,
+				   size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+	unsigned int value;
+
+	value = pdata->hw_if.read_mmd_regs(pdata, pdata->debugfs_xpcs_mmd,
+					   pdata->debugfs_xpcs_reg);
+
+	return xgbe_common_read(buffer, count, ppos, value);
+}
+
+static ssize_t xpcs_reg_value_write(struct file *filp,
+				    const char __user *buffer,
+				    size_t count, loff_t *ppos)
+{
+	struct xgbe_prv_data *pdata = filp->private_data;
+	unsigned int value;
+	ssize_t len;
+
+	len = xgbe_common_write(buffer, count, ppos, &value);
+	if (len < 0)
+		return len;
+
+	pdata->hw_if.write_mmd_regs(pdata, pdata->debugfs_xpcs_mmd,
+				    pdata->debugfs_xpcs_reg, value);
+
+	return len;
+}
+
+static const struct file_operations xpcs_mmd_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read =  xpcs_mmd_read,
+	.write = xpcs_mmd_write,
+};
+
+static const struct file_operations xpcs_reg_addr_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read =  xpcs_reg_addr_read,
+	.write = xpcs_reg_addr_write,
+};
+
+static const struct file_operations xpcs_reg_value_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read =  xpcs_reg_value_read,
+	.write = xpcs_reg_value_write,
+};
+
+void xgbe_debugfs_init(struct xgbe_prv_data *pdata)
+{
+	struct dentry *pfile;
+	char *buf;
+
+	/* Set defaults */
+	pdata->debugfs_xgmac_reg = 0;
+	pdata->debugfs_xpcs_mmd = 1;
+	pdata->debugfs_xpcs_reg = 0;
+
+	buf = kasprintf(GFP_KERNEL, "amd-xgbe-%s", pdata->netdev->name);
+	pdata->xgbe_debugfs = debugfs_create_dir(buf, NULL);
+	if (pdata->xgbe_debugfs == NULL) {
+		netdev_err(pdata->netdev, "debugfs_create_dir failed\n");
+		return;
+	}
+
+	pfile = debugfs_create_file("xgmac_register", 0600,
+				    pdata->xgbe_debugfs, pdata,
+				    &xgmac_reg_addr_fops);
+	if (!pfile)
+		netdev_err(pdata->netdev, "debugfs_create_file failed\n");
+
+	pfile = debugfs_create_file("xgmac_register_value", 0600,
+				    pdata->xgbe_debugfs, pdata,
+				    &xgmac_reg_value_fops);
+	if (!pfile)
+		netdev_err(pdata->netdev, "debugfs_create_file failed\n");
+
+	pfile = debugfs_create_file("xpcs_mmd", 0600,
+				    pdata->xgbe_debugfs, pdata,
+				    &xpcs_mmd_fops);
+	if (!pfile)
+		netdev_err(pdata->netdev, "debugfs_create_file failed\n");
+
+	pfile = debugfs_create_file("xpcs_register", 0600,
+				    pdata->xgbe_debugfs, pdata,
+				    &xpcs_reg_addr_fops);
+	if (!pfile)
+		netdev_err(pdata->netdev, "debugfs_create_file failed\n");
+
+	pfile = debugfs_create_file("xpcs_register_value", 0600,
+				    pdata->xgbe_debugfs, pdata,
+				    &xpcs_reg_value_fops);
+	if (!pfile)
+		netdev_err(pdata->netdev, "debugfs_create_file failed\n");
+
+	kfree(buf);
+}
+
+void xgbe_debugfs_exit(struct xgbe_prv_data *pdata)
+{
+	debugfs_remove_recursive(pdata->xgbe_debugfs);
+	pdata->xgbe_debugfs = NULL;
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
new file mode 100644
index 00000000000..6f1c85956d5
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -0,0 +1,556 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+
+static void xgbe_unmap_skb(struct xgbe_prv_data *, struct xgbe_ring_data *);
+
+static void xgbe_free_ring(struct xgbe_prv_data *pdata,
+			   struct xgbe_ring *ring)
+{
+	struct xgbe_ring_data *rdata;
+	unsigned int i;
+
+	if (!ring)
+		return;
+
+	if (ring->rdata) {
+		for (i = 0; i < ring->rdesc_count; i++) {
+			rdata = GET_DESC_DATA(ring, i);
+			xgbe_unmap_skb(pdata, rdata);
+		}
+
+		kfree(ring->rdata);
+		ring->rdata = NULL;
+	}
+
+	if (ring->rdesc) {
+		dma_free_coherent(pdata->dev,
+				  (sizeof(struct xgbe_ring_desc) *
+				   ring->rdesc_count),
+				  ring->rdesc, ring->rdesc_dma);
+		ring->rdesc = NULL;
+	}
+}
+
+static void xgbe_free_ring_resources(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	DBGPR("-->xgbe_free_ring_resources\n");
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		xgbe_free_ring(pdata, channel->tx_ring);
+		xgbe_free_ring(pdata, channel->rx_ring);
+	}
+
+	DBGPR("<--xgbe_free_ring_resources\n");
+}
+
+static int xgbe_init_ring(struct xgbe_prv_data *pdata,
+			  struct xgbe_ring *ring, unsigned int rdesc_count)
+{
+	DBGPR("-->xgbe_init_ring\n");
+
+	if (!ring)
+		return 0;
+
+	/* Descriptors */
+	ring->rdesc_count = rdesc_count;
+	ring->rdesc = dma_alloc_coherent(pdata->dev,
+					 (sizeof(struct xgbe_ring_desc) *
+					  rdesc_count), &ring->rdesc_dma,
+					 GFP_KERNEL);
+	if (!ring->rdesc)
+		return -ENOMEM;
+
+	/* Descriptor information */
+	ring->rdata = kcalloc(rdesc_count, sizeof(struct xgbe_ring_data),
+			      GFP_KERNEL);
+	if (!ring->rdata)
+		return -ENOMEM;
+
+	DBGPR("    rdesc=0x%p, rdesc_dma=0x%llx, rdata=0x%p\n",
+	      ring->rdesc, ring->rdesc_dma, ring->rdata);
+
+	DBGPR("<--xgbe_init_ring\n");
+
+	return 0;
+}
+
+static int xgbe_alloc_ring_resources(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+	int ret;
+
+	DBGPR("-->xgbe_alloc_ring_resources\n");
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		DBGPR("  %s - tx_ring:\n", channel->name);
+		ret = xgbe_init_ring(pdata, channel->tx_ring,
+				     pdata->tx_desc_count);
+		if (ret) {
+			netdev_alert(pdata->netdev,
+				     "error initializing Tx ring\n");
+			goto err_ring;
+		}
+
+		DBGPR("  %s - rx_ring:\n", channel->name);
+		ret = xgbe_init_ring(pdata, channel->rx_ring,
+				     pdata->rx_desc_count);
+		if (ret) {
+			netdev_alert(pdata->netdev,
+				     "error initializing Tx ring\n");
+			goto err_ring;
+		}
+	}
+
+	DBGPR("<--xgbe_alloc_ring_resources\n");
+
+	return 0;
+
+err_ring:
+	xgbe_free_ring_resources(pdata);
+
+	return ret;
+}
+
+static void xgbe_wrapper_tx_descriptor_init(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_channel *channel;
+	struct xgbe_ring *ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_ring_desc *rdesc;
+	dma_addr_t rdesc_dma;
+	unsigned int i, j;
+
+	DBGPR("-->xgbe_wrapper_tx_descriptor_init\n");
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->tx_ring;
+		if (!ring)
+			break;
+
+		rdesc = ring->rdesc;
+		rdesc_dma = ring->rdesc_dma;
+
+		for (j = 0; j < ring->rdesc_count; j++) {
+			rdata = GET_DESC_DATA(ring, j);
+
+			rdata->rdesc = rdesc;
+			rdata->rdesc_dma = rdesc_dma;
+
+			rdesc++;
+			rdesc_dma += sizeof(struct xgbe_ring_desc);
+		}
+
+		ring->cur = 0;
+		ring->dirty = 0;
+		ring->tx.queue_stopped = 0;
+
+		hw_if->tx_desc_init(channel);
+	}
+
+	DBGPR("<--xgbe_wrapper_tx_descriptor_init\n");
+}
+
+static void xgbe_wrapper_rx_descriptor_init(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_channel *channel;
+	struct xgbe_ring *ring;
+	struct xgbe_ring_desc *rdesc;
+	struct xgbe_ring_data *rdata;
+	dma_addr_t rdesc_dma, skb_dma;
+	struct sk_buff *skb = NULL;
+	unsigned int i, j;
+
+	DBGPR("-->xgbe_wrapper_rx_descriptor_init\n");
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->rx_ring;
+		if (!ring)
+			break;
+
+		rdesc = ring->rdesc;
+		rdesc_dma = ring->rdesc_dma;
+
+		for (j = 0; j < ring->rdesc_count; j++) {
+			rdata = GET_DESC_DATA(ring, j);
+
+			rdata->rdesc = rdesc;
+			rdata->rdesc_dma = rdesc_dma;
+
+			/* Allocate skb & assign to each rdesc */
+			skb = dev_alloc_skb(pdata->rx_buf_size);
+			if (skb == NULL)
+				break;
+			skb_dma = dma_map_single(pdata->dev, skb->data,
+						 pdata->rx_buf_size,
+						 DMA_FROM_DEVICE);
+			if (dma_mapping_error(pdata->dev, skb_dma)) {
+				netdev_alert(pdata->netdev,
+					     "failed to do the dma map\n");
+				dev_kfree_skb_any(skb);
+				break;
+			}
+			rdata->skb = skb;
+			rdata->skb_dma = skb_dma;
+			rdata->skb_dma_len = pdata->rx_buf_size;
+
+			rdesc++;
+			rdesc_dma += sizeof(struct xgbe_ring_desc);
+		}
+
+		ring->cur = 0;
+		ring->dirty = 0;
+		ring->rx.realloc_index = 0;
+		ring->rx.realloc_threshold = 0;
+
+		hw_if->rx_desc_init(channel);
+	}
+
+	DBGPR("<--xgbe_wrapper_rx_descriptor_init\n");
+}
+
+static void xgbe_unmap_skb(struct xgbe_prv_data *pdata,
+			   struct xgbe_ring_data *rdata)
+{
+	if (rdata->skb_dma) {
+		if (rdata->mapped_as_page) {
+			dma_unmap_page(pdata->dev, rdata->skb_dma,
+				       rdata->skb_dma_len, DMA_TO_DEVICE);
+		} else {
+			dma_unmap_single(pdata->dev, rdata->skb_dma,
+					 rdata->skb_dma_len, DMA_TO_DEVICE);
+		}
+		rdata->skb_dma = 0;
+		rdata->skb_dma_len = 0;
+	}
+
+	if (rdata->skb) {
+		dev_kfree_skb_any(rdata->skb);
+		rdata->skb = NULL;
+	}
+
+	rdata->tso_header = 0;
+	rdata->len = 0;
+	rdata->interrupt = 0;
+	rdata->mapped_as_page = 0;
+}
+
+static int xgbe_map_tx_skb(struct xgbe_channel *channel, struct sk_buff *skb)
+{
+	struct xgbe_prv_data *pdata = channel->pdata;
+	struct xgbe_ring *ring = channel->tx_ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_packet_data *packet;
+	struct skb_frag_struct *frag;
+	dma_addr_t skb_dma;
+	unsigned int start_index, cur_index;
+	unsigned int offset, tso, vlan, datalen, len;
+	unsigned int i;
+
+	DBGPR("-->xgbe_map_tx_skb: cur = %d\n", ring->cur);
+
+	offset = 0;
+	start_index = ring->cur;
+	cur_index = ring->cur;
+
+	packet = &ring->packet_data;
+	packet->rdesc_count = 0;
+	packet->length = 0;
+
+	tso = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			     TSO_ENABLE);
+	vlan = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			      VLAN_CTAG);
+
+	/* Save space for a context descriptor if needed */
+	if ((tso && (packet->mss != ring->tx.cur_mss)) ||
+	    (vlan && (packet->vlan_ctag != ring->tx.cur_vlan_ctag)))
+		cur_index++;
+	rdata = GET_DESC_DATA(ring, cur_index);
+
+	if (tso) {
+		DBGPR("  TSO packet\n");
+
+		/* Map the TSO header */
+		skb_dma = dma_map_single(pdata->dev, skb->data,
+					 packet->header_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(pdata->dev, skb_dma)) {
+			netdev_alert(pdata->netdev, "dma_map_single failed\n");
+			goto err_out;
+		}
+		rdata->skb_dma = skb_dma;
+		rdata->skb_dma_len = packet->header_len;
+		rdata->tso_header = 1;
+
+		offset = packet->header_len;
+
+		packet->length += packet->header_len;
+
+		cur_index++;
+		rdata = GET_DESC_DATA(ring, cur_index);
+	}
+
+	/* Map the (remainder of the) packet */
+	for (datalen = skb_headlen(skb) - offset; datalen; ) {
+		len = min_t(unsigned int, datalen, TX_MAX_BUF_SIZE);
+
+		skb_dma = dma_map_single(pdata->dev, skb->data + offset, len,
+					 DMA_TO_DEVICE);
+		if (dma_mapping_error(pdata->dev, skb_dma)) {
+			netdev_alert(pdata->netdev, "dma_map_single failed\n");
+			goto err_out;
+		}
+		rdata->skb_dma = skb_dma;
+		rdata->skb_dma_len = len;
+		DBGPR("  skb data: index=%u, dma=0x%llx, len=%u\n",
+		      cur_index, skb_dma, len);
+
+		datalen -= len;
+		offset += len;
+
+		packet->length += len;
+
+		cur_index++;
+		rdata = GET_DESC_DATA(ring, cur_index);
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		DBGPR("  mapping frag %u\n", i);
+
+		frag = &skb_shinfo(skb)->frags[i];
+		offset = 0;
+
+		for (datalen = skb_frag_size(frag); datalen; ) {
+			len = min_t(unsigned int, datalen, TX_MAX_BUF_SIZE);
+
+			skb_dma = skb_frag_dma_map(pdata->dev, frag, offset,
+						   len, DMA_TO_DEVICE);
+			if (dma_mapping_error(pdata->dev, skb_dma)) {
+				netdev_alert(pdata->netdev,
+					     "skb_frag_dma_map failed\n");
+				goto err_out;
+			}
+			rdata->skb_dma = skb_dma;
+			rdata->skb_dma_len = len;
+			rdata->mapped_as_page = 1;
+			DBGPR("  skb data: index=%u, dma=0x%llx, len=%u\n",
+			      cur_index, skb_dma, len);
+
+			datalen -= len;
+			offset += len;
+
+			packet->length += len;
+
+			cur_index++;
+			rdata = GET_DESC_DATA(ring, cur_index);
+		}
+	}
+
+	/* Save the skb address in the last entry */
+	rdata->skb = skb;
+
+	/* Save the number of descriptor entries used */
+	packet->rdesc_count = cur_index - start_index;
+
+	DBGPR("<--xgbe_map_tx_skb: count=%u\n", packet->rdesc_count);
+
+	return packet->rdesc_count;
+
+err_out:
+	while (start_index < cur_index) {
+		rdata = GET_DESC_DATA(ring, start_index++);
+		xgbe_unmap_skb(pdata, rdata);
+	}
+
+	DBGPR("<--xgbe_map_tx_skb: count=0\n");
+
+	return 0;
+}
+
+static void xgbe_realloc_skb(struct xgbe_channel *channel)
+{
+	struct xgbe_prv_data *pdata = channel->pdata;
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_ring *ring = channel->rx_ring;
+	struct xgbe_ring_data *rdata;
+	struct sk_buff *skb = NULL;
+	dma_addr_t skb_dma;
+	int i;
+
+	DBGPR("-->xgbe_realloc_skb: rx_ring->rx.realloc_index = %u\n",
+	      ring->rx.realloc_index);
+
+	for (i = 0; i < ring->dirty; i++) {
+		rdata = GET_DESC_DATA(ring, ring->rx.realloc_index);
+
+		/* Reset rdata values */
+		xgbe_unmap_skb(pdata, rdata);
+
+		/* Allocate skb & assign to each rdesc */
+		skb = dev_alloc_skb(pdata->rx_buf_size);
+		if (skb == NULL) {
+			netdev_alert(pdata->netdev,
+				     "failed to allocate skb\n");
+			break;
+		}
+		skb_dma = dma_map_single(pdata->dev, skb->data,
+					 pdata->rx_buf_size, DMA_FROM_DEVICE);
+		if (dma_mapping_error(pdata->dev, skb_dma)) {
+			netdev_alert(pdata->netdev,
+				     "failed to do the dma map\n");
+			dev_kfree_skb_any(skb);
+			break;
+		}
+		rdata->skb = skb;
+		rdata->skb_dma = skb_dma;
+		rdata->skb_dma_len = pdata->rx_buf_size;
+
+		hw_if->rx_desc_reset(rdata);
+
+		ring->rx.realloc_index++;
+	}
+	ring->dirty = 0;
+
+	DBGPR("<--xgbe_realloc_skb\n");
+}
+
+void xgbe_init_function_ptrs_desc(struct xgbe_desc_if *desc_if)
+{
+	DBGPR("-->xgbe_init_function_ptrs_desc\n");
+
+	desc_if->alloc_ring_resources = xgbe_alloc_ring_resources;
+	desc_if->free_ring_resources = xgbe_free_ring_resources;
+	desc_if->map_tx_skb = xgbe_map_tx_skb;
+	desc_if->realloc_skb = xgbe_realloc_skb;
+	desc_if->unmap_skb = xgbe_unmap_skb;
+	desc_if->wrapper_tx_desc_init = xgbe_wrapper_tx_descriptor_init;
+	desc_if->wrapper_rx_desc_init = xgbe_wrapper_rx_descriptor_init;
+
+	DBGPR("<--xgbe_init_function_ptrs_desc\n");
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
new file mode 100644
index 00000000000..002293b0819
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -0,0 +1,2182 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/phy.h>
+#include <linux/clk.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+
+static unsigned int xgbe_usec_to_riwt(struct xgbe_prv_data *pdata,
+				      unsigned int usec)
+{
+	unsigned long rate;
+	unsigned int ret;
+
+	DBGPR("-->xgbe_usec_to_riwt\n");
+
+	rate = clk_get_rate(pdata->sysclock);
+
+	/*
+	 * Convert the input usec value to the watchdog timer value. Each
+	 * watchdog timer value is equivalent to 256 clock cycles.
+	 * Calculate the required value as:
+	 *   ( usec * ( system_clock_mhz / 10^6 ) / 256
+	 */
+	ret = (usec * (rate / 1000000)) / 256;
+
+	DBGPR("<--xgbe_usec_to_riwt\n");
+
+	return ret;
+}
+
+static unsigned int xgbe_riwt_to_usec(struct xgbe_prv_data *pdata,
+				      unsigned int riwt)
+{
+	unsigned long rate;
+	unsigned int ret;
+
+	DBGPR("-->xgbe_riwt_to_usec\n");
+
+	rate = clk_get_rate(pdata->sysclock);
+
+	/*
+	 * Convert the input watchdog timer value to the usec value. Each
+	 * watchdog timer value is equivalent to 256 clock cycles.
+	 * Calculate the required value as:
+	 *   ( riwt * 256 ) / ( system_clock_mhz / 10^6 )
+	 */
+	ret = (riwt * 256) / (rate / 1000000);
+
+	DBGPR("<--xgbe_riwt_to_usec\n");
+
+	return ret;
+}
+
+static int xgbe_config_pblx8(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++)
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_CR, PBLX8,
+				       pdata->pblx8);
+
+	return 0;
+}
+
+static int xgbe_get_tx_pbl_val(struct xgbe_prv_data *pdata)
+{
+	return XGMAC_DMA_IOREAD_BITS(pdata->channel, DMA_CH_TCR, PBL);
+}
+
+static int xgbe_config_tx_pbl_val(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_TCR, PBL,
+				       pdata->tx_pbl);
+	}
+
+	return 0;
+}
+
+static int xgbe_get_rx_pbl_val(struct xgbe_prv_data *pdata)
+{
+	return XGMAC_DMA_IOREAD_BITS(pdata->channel, DMA_CH_RCR, PBL);
+}
+
+static int xgbe_config_rx_pbl_val(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_RCR, PBL,
+				       pdata->rx_pbl);
+	}
+
+	return 0;
+}
+
+static int xgbe_config_osp_mode(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_TCR, OSP,
+				       pdata->tx_osp_mode);
+	}
+
+	return 0;
+}
+
+static int xgbe_config_rsf_mode(struct xgbe_prv_data *pdata, unsigned int val)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->hw_feat.rx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RSF, val);
+
+	return 0;
+}
+
+static int xgbe_config_tsf_mode(struct xgbe_prv_data *pdata, unsigned int val)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->hw_feat.tx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, TSF, val);
+
+	return 0;
+}
+
+static int xgbe_config_rx_threshold(struct xgbe_prv_data *pdata,
+				    unsigned int val)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->hw_feat.rx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RTC, val);
+
+	return 0;
+}
+
+static int xgbe_config_tx_threshold(struct xgbe_prv_data *pdata,
+				    unsigned int val)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->hw_feat.tx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, TTC, val);
+
+	return 0;
+}
+
+static int xgbe_config_rx_coalesce(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_RIWT, RWT,
+				       pdata->rx_riwt);
+	}
+
+	return 0;
+}
+
+static int xgbe_config_tx_coalesce(struct xgbe_prv_data *pdata)
+{
+	return 0;
+}
+
+static void xgbe_config_rx_buffer_size(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_RCR, RBSZ,
+				       pdata->rx_buf_size);
+	}
+}
+
+static void xgbe_config_tso_mode(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_TCR, TSE, 1);
+	}
+}
+
+static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata)
+{
+	unsigned int max_q_count, q_count;
+	unsigned int reg, reg_val;
+	unsigned int i;
+
+	/* Clear MTL flow control */
+	for (i = 0; i < pdata->hw_feat.rx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, EHFC, 0);
+
+	/* Clear MAC flow control */
+	max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES;
+	q_count = min_t(unsigned int, pdata->hw_feat.rx_q_cnt, max_q_count);
+	reg = MAC_Q0TFCR;
+	for (i = 0; i < q_count; i++) {
+		reg_val = XGMAC_IOREAD(pdata, reg);
+		XGMAC_SET_BITS(reg_val, MAC_Q0TFCR, TFE, 0);
+		XGMAC_IOWRITE(pdata, reg, reg_val);
+
+		reg += MAC_QTFCR_INC;
+	}
+
+	return 0;
+}
+
+static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata)
+{
+	unsigned int max_q_count, q_count;
+	unsigned int reg, reg_val;
+	unsigned int i;
+
+	/* Set MTL flow control */
+	for (i = 0; i < pdata->hw_feat.rx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, EHFC, 1);
+
+	/* Set MAC flow control */
+	max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES;
+	q_count = min_t(unsigned int, pdata->hw_feat.rx_q_cnt, max_q_count);
+	reg = MAC_Q0TFCR;
+	for (i = 0; i < q_count; i++) {
+		reg_val = XGMAC_IOREAD(pdata, reg);
+
+		/* Enable transmit flow control */
+		XGMAC_SET_BITS(reg_val, MAC_Q0TFCR, TFE, 1);
+		/* Set pause time */
+		XGMAC_SET_BITS(reg_val, MAC_Q0TFCR, PT, 0xffff);
+
+		XGMAC_IOWRITE(pdata, reg, reg_val);
+
+		reg += MAC_QTFCR_INC;
+	}
+
+	return 0;
+}
+
+static int xgbe_disable_rx_flow_control(struct xgbe_prv_data *pdata)
+{
+	XGMAC_IOWRITE_BITS(pdata, MAC_RFCR, RFE, 0);
+
+	return 0;
+}
+
+static int xgbe_enable_rx_flow_control(struct xgbe_prv_data *pdata)
+{
+	XGMAC_IOWRITE_BITS(pdata, MAC_RFCR, RFE, 1);
+
+	return 0;
+}
+
+static int xgbe_config_tx_flow_control(struct xgbe_prv_data *pdata)
+{
+	if (pdata->tx_pause)
+		xgbe_enable_tx_flow_control(pdata);
+	else
+		xgbe_disable_tx_flow_control(pdata);
+
+	return 0;
+}
+
+static int xgbe_config_rx_flow_control(struct xgbe_prv_data *pdata)
+{
+	if (pdata->rx_pause)
+		xgbe_enable_rx_flow_control(pdata);
+	else
+		xgbe_disable_rx_flow_control(pdata);
+
+	return 0;
+}
+
+static void xgbe_config_flow_control(struct xgbe_prv_data *pdata)
+{
+	xgbe_config_tx_flow_control(pdata);
+	xgbe_config_rx_flow_control(pdata);
+}
+
+static void xgbe_enable_dma_interrupts(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int dma_ch_isr, dma_ch_ier;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		/* Clear all the interrupts which are set */
+		dma_ch_isr = XGMAC_DMA_IOREAD(channel, DMA_CH_SR);
+		XGMAC_DMA_IOWRITE(channel, DMA_CH_SR, dma_ch_isr);
+
+		/* Clear all interrupt enable bits */
+		dma_ch_ier = 0;
+
+		/* Enable following interrupts
+		 *   NIE  - Normal Interrupt Summary Enable
+		 *   AIE  - Abnormal Interrupt Summary Enable
+		 *   FBEE - Fatal Bus Error Enable
+		 */
+		XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, NIE, 1);
+		XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, AIE, 1);
+		XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, FBEE, 1);
+
+		if (channel->tx_ring) {
+			/* Enable the following Tx interrupts
+			 *   TIE  - Transmit Interrupt Enable (unless polling)
+			 */
+			XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TIE, 1);
+		}
+		if (channel->rx_ring) {
+			/* Enable following Rx interrupts
+			 *   RBUE - Receive Buffer Unavailable Enable
+			 *   RIE  - Receive Interrupt Enable
+			 */
+			XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RBUE, 1);
+			XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RIE, 1);
+		}
+
+		XGMAC_DMA_IOWRITE(channel, DMA_CH_IER, dma_ch_ier);
+	}
+}
+
+static void xgbe_enable_mtl_interrupts(struct xgbe_prv_data *pdata)
+{
+	unsigned int mtl_q_isr;
+	unsigned int q_count, i;
+
+	q_count = max(pdata->hw_feat.tx_q_cnt, pdata->hw_feat.rx_q_cnt);
+	for (i = 0; i < q_count; i++) {
+		/* Clear all the interrupts which are set */
+		mtl_q_isr = XGMAC_MTL_IOREAD(pdata, i, MTL_Q_ISR);
+		XGMAC_MTL_IOWRITE(pdata, i, MTL_Q_ISR, mtl_q_isr);
+
+		/* No MTL interrupts to be enabled */
+		XGMAC_MTL_IOWRITE(pdata, i, MTL_Q_ISR, 0);
+	}
+}
+
+static void xgbe_enable_mac_interrupts(struct xgbe_prv_data *pdata)
+{
+	/* No MAC interrupts to be enabled */
+	XGMAC_IOWRITE(pdata, MAC_IER, 0);
+
+	/* Enable all counter interrupts */
+	XGMAC_IOWRITE_BITS(pdata, MMC_RIER, ALL_INTERRUPTS, 0xff);
+	XGMAC_IOWRITE_BITS(pdata, MMC_TIER, ALL_INTERRUPTS, 0xff);
+}
+
+static int xgbe_set_gmii_speed(struct xgbe_prv_data *pdata)
+{
+	XGMAC_IOWRITE_BITS(pdata, MAC_TCR, SS, 0x3);
+
+	return 0;
+}
+
+static int xgbe_set_gmii_2500_speed(struct xgbe_prv_data *pdata)
+{
+	XGMAC_IOWRITE_BITS(pdata, MAC_TCR, SS, 0x2);
+
+	return 0;
+}
+
+static int xgbe_set_xgmii_speed(struct xgbe_prv_data *pdata)
+{
+	XGMAC_IOWRITE_BITS(pdata, MAC_TCR, SS, 0);
+
+	return 0;
+}
+
+static int xgbe_set_promiscuous_mode(struct xgbe_prv_data *pdata,
+				     unsigned int enable)
+{
+	unsigned int val = enable ? 1 : 0;
+
+	if (XGMAC_IOREAD_BITS(pdata, MAC_PFR, PR) == val)
+		return 0;
+
+	DBGPR("  %s promiscuous mode\n", enable ? "entering" : "leaving");
+	XGMAC_IOWRITE_BITS(pdata, MAC_PFR, PR, val);
+
+	return 0;
+}
+
+static int xgbe_set_all_multicast_mode(struct xgbe_prv_data *pdata,
+				       unsigned int enable)
+{
+	unsigned int val = enable ? 1 : 0;
+
+	if (XGMAC_IOREAD_BITS(pdata, MAC_PFR, PM) == val)
+		return 0;
+
+	DBGPR("  %s allmulti mode\n", enable ? "entering" : "leaving");
+	XGMAC_IOWRITE_BITS(pdata, MAC_PFR, PM, val);
+
+	return 0;
+}
+
+static int xgbe_set_addn_mac_addrs(struct xgbe_prv_data *pdata,
+				   unsigned int am_mode)
+{
+	struct netdev_hw_addr *ha;
+	unsigned int mac_reg;
+	unsigned int mac_addr_hi, mac_addr_lo;
+	u8 *mac_addr;
+	unsigned int i;
+
+	XGMAC_IOWRITE_BITS(pdata, MAC_PFR, HUC, 0);
+	XGMAC_IOWRITE_BITS(pdata, MAC_PFR, HMC, 0);
+
+	i = 0;
+	mac_reg = MAC_MACA1HR;
+
+	netdev_for_each_uc_addr(ha, pdata->netdev) {
+		mac_addr_lo = 0;
+		mac_addr_hi = 0;
+		mac_addr = (u8 *)&mac_addr_lo;
+		mac_addr[0] = ha->addr[0];
+		mac_addr[1] = ha->addr[1];
+		mac_addr[2] = ha->addr[2];
+		mac_addr[3] = ha->addr[3];
+		mac_addr = (u8 *)&mac_addr_hi;
+		mac_addr[0] = ha->addr[4];
+		mac_addr[1] = ha->addr[5];
+
+		DBGPR("  adding unicast address %pM at 0x%04x\n",
+		      ha->addr, mac_reg);
+
+		XGMAC_SET_BITS(mac_addr_hi, MAC_MACA1HR, AE, 1);
+
+		XGMAC_IOWRITE(pdata, mac_reg, mac_addr_hi);
+		mac_reg += MAC_MACA_INC;
+		XGMAC_IOWRITE(pdata, mac_reg, mac_addr_lo);
+		mac_reg += MAC_MACA_INC;
+
+		i++;
+	}
+
+	if (!am_mode) {
+		netdev_for_each_mc_addr(ha, pdata->netdev) {
+			mac_addr_lo = 0;
+			mac_addr_hi = 0;
+			mac_addr = (u8 *)&mac_addr_lo;
+			mac_addr[0] = ha->addr[0];
+			mac_addr[1] = ha->addr[1];
+			mac_addr[2] = ha->addr[2];
+			mac_addr[3] = ha->addr[3];
+			mac_addr = (u8 *)&mac_addr_hi;
+			mac_addr[0] = ha->addr[4];
+			mac_addr[1] = ha->addr[5];
+
+			DBGPR("  adding multicast address %pM at 0x%04x\n",
+			      ha->addr, mac_reg);
+
+			XGMAC_SET_BITS(mac_addr_hi, MAC_MACA1HR, AE, 1);
+
+			XGMAC_IOWRITE(pdata, mac_reg, mac_addr_hi);
+			mac_reg += MAC_MACA_INC;
+			XGMAC_IOWRITE(pdata, mac_reg, mac_addr_lo);
+			mac_reg += MAC_MACA_INC;
+
+			i++;
+		}
+	}
+
+	/* Clear remaining additional MAC address entries */
+	for (; i < pdata->hw_feat.addn_mac; i++) {
+		XGMAC_IOWRITE(pdata, mac_reg, 0);
+		mac_reg += MAC_MACA_INC;
+		XGMAC_IOWRITE(pdata, mac_reg, 0);
+		mac_reg += MAC_MACA_INC;
+	}
+
+	return 0;
+}
+
+static int xgbe_set_mac_address(struct xgbe_prv_data *pdata, u8 *addr)
+{
+	unsigned int mac_addr_hi, mac_addr_lo;
+
+	mac_addr_hi = (addr[5] <<  8) | (addr[4] <<  0);
+	mac_addr_lo = (addr[3] << 24) | (addr[2] << 16) |
+		      (addr[1] <<  8) | (addr[0] <<  0);
+
+	XGMAC_IOWRITE(pdata, MAC_MACA0HR, mac_addr_hi);
+	XGMAC_IOWRITE(pdata, MAC_MACA0LR, mac_addr_lo);
+
+	return 0;
+}
+
+static int xgbe_read_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
+			      int mmd_reg)
+{
+	unsigned int mmd_address;
+	int mmd_data;
+
+	if (mmd_reg & MII_ADDR_C45)
+		mmd_address = mmd_reg & ~MII_ADDR_C45;
+	else
+		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+
+	/* The PCS registers are accessed using mmio. The underlying APB3
+	 * management interface uses indirect addressing to access the MMD
+	 * register sets. This requires accessing of the PCS register in two
+	 * phases, an address phase and a data phase.
+	 *
+	 * The mmio interface is based on 32-bit offsets and values. All
+	 * register offsets must therefore be adjusted by left shifting the
+	 * offset 2 bits and reading 32 bits of data.
+	 */
+	mutex_lock(&pdata->xpcs_mutex);
+	XPCS_IOWRITE(pdata, PCS_MMD_SELECT << 2, mmd_address >> 8);
+	mmd_data = XPCS_IOREAD(pdata, (mmd_address & 0xff) << 2);
+	mutex_unlock(&pdata->xpcs_mutex);
+
+	return mmd_data;
+}
+
+static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
+				int mmd_reg, int mmd_data)
+{
+	unsigned int mmd_address;
+
+	if (mmd_reg & MII_ADDR_C45)
+		mmd_address = mmd_reg & ~MII_ADDR_C45;
+	else
+		mmd_address = (pdata->mdio_mmd << 16) | (mmd_reg & 0xffff);
+
+	/* The PCS registers are accessed using mmio. The underlying APB3
+	 * management interface uses indirect addressing to access the MMD
+	 * register sets. This requires accessing of the PCS register in two
+	 * phases, an address phase and a data phase.
+	 *
+	 * The mmio interface is based on 32-bit offsets and values. All
+	 * register offsets must therefore be adjusted by left shifting the
+	 * offset 2 bits and reading 32 bits of data.
+	 */
+	mutex_lock(&pdata->xpcs_mutex);
+	XPCS_IOWRITE(pdata, PCS_MMD_SELECT << 2, mmd_address >> 8);
+	XPCS_IOWRITE(pdata, (mmd_address & 0xff) << 2, mmd_data);
+	mutex_unlock(&pdata->xpcs_mutex);
+}
+
+static int xgbe_tx_complete(struct xgbe_ring_desc *rdesc)
+{
+	return !XGMAC_GET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, OWN);
+}
+
+static int xgbe_disable_rx_csum(struct xgbe_prv_data *pdata)
+{
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, IPC, 0);
+
+	return 0;
+}
+
+static int xgbe_enable_rx_csum(struct xgbe_prv_data *pdata)
+{
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, IPC, 1);
+
+	return 0;
+}
+
+static int xgbe_enable_rx_vlan_stripping(struct xgbe_prv_data *pdata)
+{
+	/* Put the VLAN tag in the Rx descriptor */
+	XGMAC_IOWRITE_BITS(pdata, MAC_VLANTR, EVLRXS, 1);
+
+	/* Don't check the VLAN type */
+	XGMAC_IOWRITE_BITS(pdata, MAC_VLANTR, DOVLTC, 1);
+
+	/* Check only C-TAG (0x8100) packets */
+	XGMAC_IOWRITE_BITS(pdata, MAC_VLANTR, ERSVLM, 0);
+
+	/* Don't consider an S-TAG (0x88A8) packet as a VLAN packet */
+	XGMAC_IOWRITE_BITS(pdata, MAC_VLANTR, ESVL, 0);
+
+	/* Enable VLAN tag stripping */
+	XGMAC_IOWRITE_BITS(pdata, MAC_VLANTR, EVLS, 0x3);
+
+	return 0;
+}
+
+static int xgbe_disable_rx_vlan_stripping(struct xgbe_prv_data *pdata)
+{
+	XGMAC_IOWRITE_BITS(pdata, MAC_VLANTR, EVLS, 0);
+
+	return 0;
+}
+
+static void xgbe_tx_desc_reset(struct xgbe_ring_data *rdata)
+{
+	struct xgbe_ring_desc *rdesc = rdata->rdesc;
+
+	/* Reset the Tx descriptor
+	 *   Set buffer 1 (lo) address to zero
+	 *   Set buffer 1 (hi) address to zero
+	 *   Reset all other control bits (IC, TTSE, B2L & B1L)
+	 *   Reset all other control bits (OWN, CTXT, FD, LD, CPC, CIC, etc)
+	 */
+	rdesc->desc0 = 0;
+	rdesc->desc1 = 0;
+	rdesc->desc2 = 0;
+	rdesc->desc3 = 0;
+}
+
+static void xgbe_tx_desc_init(struct xgbe_channel *channel)
+{
+	struct xgbe_ring *ring = channel->tx_ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_ring_desc *rdesc;
+	int i;
+	int start_index = ring->cur;
+
+	DBGPR("-->tx_desc_init\n");
+
+	/* Initialze all descriptors */
+	for (i = 0; i < ring->rdesc_count; i++) {
+		rdata = GET_DESC_DATA(ring, i);
+		rdesc = rdata->rdesc;
+
+		/* Initialize Tx descriptor
+		 *   Set buffer 1 (lo) address to zero
+		 *   Set buffer 1 (hi) address to zero
+		 *   Reset all other control bits (IC, TTSE, B2L & B1L)
+		 *   Reset all other control bits (OWN, CTXT, FD, LD, CPC, CIC,
+		 *     etc)
+		 */
+		rdesc->desc0 = 0;
+		rdesc->desc1 = 0;
+		rdesc->desc2 = 0;
+		rdesc->desc3 = 0;
+	}
+
+	/* Make sure everything is written to the descriptor(s) before
+	 * telling the device about them
+	 */
+	wmb();
+
+	/* Update the total number of Tx descriptors */
+	XGMAC_DMA_IOWRITE(channel, DMA_CH_TDRLR, ring->rdesc_count - 1);
+
+	/* Update the starting address of descriptor ring */
+	rdata = GET_DESC_DATA(ring, start_index);
+	XGMAC_DMA_IOWRITE(channel, DMA_CH_TDLR_HI,
+			  upper_32_bits(rdata->rdesc_dma));
+	XGMAC_DMA_IOWRITE(channel, DMA_CH_TDLR_LO,
+			  lower_32_bits(rdata->rdesc_dma));
+
+	DBGPR("<--tx_desc_init\n");
+}
+
+static void xgbe_rx_desc_reset(struct xgbe_ring_data *rdata)
+{
+	struct xgbe_ring_desc *rdesc = rdata->rdesc;
+
+	/* Reset the Rx descriptor
+	 *   Set buffer 1 (lo) address to dma address (lo)
+	 *   Set buffer 1 (hi) address to dma address (hi)
+	 *   Set buffer 2 (lo) address to zero
+	 *   Set buffer 2 (hi) address to zero and set control bits
+	 *     OWN and INTE
+	 */
+	rdesc->desc0 = cpu_to_le32(lower_32_bits(rdata->skb_dma));
+	rdesc->desc1 = cpu_to_le32(upper_32_bits(rdata->skb_dma));
+	rdesc->desc2 = 0;
+
+	rdesc->desc3 = 0;
+	if (rdata->interrupt)
+		XGMAC_SET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, INTE, 1);
+
+	/* Since the Rx DMA engine is likely running, make sure everything
+	 * is written to the descriptor(s) before setting the OWN bit
+	 * for the descriptor
+	 */
+	wmb();
+
+	XGMAC_SET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, OWN, 1);
+
+	/* Make sure ownership is written to the descriptor */
+	wmb();
+}
+
+static void xgbe_rx_desc_init(struct xgbe_channel *channel)
+{
+	struct xgbe_prv_data *pdata = channel->pdata;
+	struct xgbe_ring *ring = channel->rx_ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_ring_desc *rdesc;
+	unsigned int start_index = ring->cur;
+	unsigned int rx_coalesce, rx_frames;
+	unsigned int i;
+
+	DBGPR("-->rx_desc_init\n");
+
+	rx_coalesce = (pdata->rx_riwt || pdata->rx_frames) ? 1 : 0;
+	rx_frames = pdata->rx_frames;
+
+	/* Initialize all descriptors */
+	for (i = 0; i < ring->rdesc_count; i++) {
+		rdata = GET_DESC_DATA(ring, i);
+		rdesc = rdata->rdesc;
+
+		/* Initialize Rx descriptor
+		 *   Set buffer 1 (lo) address to dma address (lo)
+		 *   Set buffer 1 (hi) address to dma address (hi)
+		 *   Set buffer 2 (lo) address to zero
+		 *   Set buffer 2 (hi) address to zero and set control
+		 *     bits OWN and INTE appropriateley
+		 */
+		rdesc->desc0 = cpu_to_le32(lower_32_bits(rdata->skb_dma));
+		rdesc->desc1 = cpu_to_le32(upper_32_bits(rdata->skb_dma));
+		rdesc->desc2 = 0;
+		rdesc->desc3 = 0;
+		XGMAC_SET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, OWN, 1);
+		XGMAC_SET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, INTE, 1);
+		rdata->interrupt = 1;
+		if (rx_coalesce && (!rx_frames || ((i + 1) % rx_frames))) {
+			/* Clear interrupt on completion bit */
+			XGMAC_SET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, INTE,
+					  0);
+			rdata->interrupt = 0;
+		}
+	}
+
+	/* Make sure everything is written to the descriptors before
+	 * telling the device about them
+	 */
+	wmb();
+
+	/* Update the total number of Rx descriptors */
+	XGMAC_DMA_IOWRITE(channel, DMA_CH_RDRLR, ring->rdesc_count - 1);
+
+	/* Update the starting address of descriptor ring */
+	rdata = GET_DESC_DATA(ring, start_index);
+	XGMAC_DMA_IOWRITE(channel, DMA_CH_RDLR_HI,
+			  upper_32_bits(rdata->rdesc_dma));
+	XGMAC_DMA_IOWRITE(channel, DMA_CH_RDLR_LO,
+			  lower_32_bits(rdata->rdesc_dma));
+
+	/* Update the Rx Descriptor Tail Pointer */
+	rdata = GET_DESC_DATA(ring, start_index + ring->rdesc_count - 1);
+	XGMAC_DMA_IOWRITE(channel, DMA_CH_RDTR_LO,
+			  lower_32_bits(rdata->rdesc_dma));
+
+	DBGPR("<--rx_desc_init\n");
+}
+
+static void xgbe_pre_xmit(struct xgbe_channel *channel)
+{
+	struct xgbe_prv_data *pdata = channel->pdata;
+	struct xgbe_ring *ring = channel->tx_ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_ring_desc *rdesc;
+	struct xgbe_packet_data *packet = &ring->packet_data;
+	unsigned int csum, tso, vlan;
+	unsigned int tso_context, vlan_context;
+	unsigned int tx_coalesce, tx_frames;
+	int start_index = ring->cur;
+	int i;
+
+	DBGPR("-->xgbe_pre_xmit\n");
+
+	csum = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			      CSUM_ENABLE);
+	tso = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			     TSO_ENABLE);
+	vlan = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			      VLAN_CTAG);
+
+	if (tso && (packet->mss != ring->tx.cur_mss))
+		tso_context = 1;
+	else
+		tso_context = 0;
+
+	if (vlan && (packet->vlan_ctag != ring->tx.cur_vlan_ctag))
+		vlan_context = 1;
+	else
+		vlan_context = 0;
+
+	tx_coalesce = (pdata->tx_usecs || pdata->tx_frames) ? 1 : 0;
+	tx_frames = pdata->tx_frames;
+	if (tx_coalesce && !channel->tx_timer_active)
+		ring->coalesce_count = 0;
+
+	rdata = GET_DESC_DATA(ring, ring->cur);
+	rdesc = rdata->rdesc;
+
+	/* Create a context descriptor if this is a TSO packet */
+	if (tso_context || vlan_context) {
+		if (tso_context) {
+			DBGPR("  TSO context descriptor, mss=%u\n",
+			      packet->mss);
+
+			/* Set the MSS size */
+			XGMAC_SET_BITS_LE(rdesc->desc2, TX_CONTEXT_DESC2,
+					  MSS, packet->mss);
+
+			/* Mark it as a CONTEXT descriptor */
+			XGMAC_SET_BITS_LE(rdesc->desc3, TX_CONTEXT_DESC3,
+					  CTXT, 1);
+
+			/* Indicate this descriptor contains the MSS */
+			XGMAC_SET_BITS_LE(rdesc->desc3, TX_CONTEXT_DESC3,
+					  TCMSSV, 1);
+
+			ring->tx.cur_mss = packet->mss;
+		}
+
+		if (vlan_context) {
+			DBGPR("  VLAN context descriptor, ctag=%u\n",
+			      packet->vlan_ctag);
+
+			/* Mark it as a CONTEXT descriptor */
+			XGMAC_SET_BITS_LE(rdesc->desc3, TX_CONTEXT_DESC3,
+					  CTXT, 1);
+
+			/* Set the VLAN tag */
+			XGMAC_SET_BITS_LE(rdesc->desc3, TX_CONTEXT_DESC3,
+					  VT, packet->vlan_ctag);
+
+			/* Indicate this descriptor contains the VLAN tag */
+			XGMAC_SET_BITS_LE(rdesc->desc3, TX_CONTEXT_DESC3,
+					  VLTV, 1);
+
+			ring->tx.cur_vlan_ctag = packet->vlan_ctag;
+		}
+
+		ring->cur++;
+		rdata = GET_DESC_DATA(ring, ring->cur);
+		rdesc = rdata->rdesc;
+	}
+
+	/* Update buffer address (for TSO this is the header) */
+	rdesc->desc0 =  cpu_to_le32(lower_32_bits(rdata->skb_dma));
+	rdesc->desc1 =  cpu_to_le32(upper_32_bits(rdata->skb_dma));
+
+	/* Update the buffer length */
+	XGMAC_SET_BITS_LE(rdesc->desc2, TX_NORMAL_DESC2, HL_B1L,
+			  rdata->skb_dma_len);
+
+	/* VLAN tag insertion check */
+	if (vlan)
+		XGMAC_SET_BITS_LE(rdesc->desc2, TX_NORMAL_DESC2, VTIR,
+				  TX_NORMAL_DESC2_VLAN_INSERT);
+
+	/* Set IC bit based on Tx coalescing settings */
+	XGMAC_SET_BITS_LE(rdesc->desc2, TX_NORMAL_DESC2, IC, 1);
+	if (tx_coalesce && (!tx_frames ||
+			    (++ring->coalesce_count % tx_frames)))
+		/* Clear IC bit */
+		XGMAC_SET_BITS_LE(rdesc->desc2, TX_NORMAL_DESC2, IC, 0);
+
+	/* Mark it as First Descriptor */
+	XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, FD, 1);
+
+	/* Mark it as a NORMAL descriptor */
+	XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, CTXT, 0);
+
+	/* Set OWN bit if not the first descriptor */
+	if (ring->cur != start_index)
+		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, OWN, 1);
+
+	if (tso) {
+		/* Enable TSO */
+		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, TSE, 1);
+		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, TCPPL,
+				  packet->tcp_payload_len);
+		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, TCPHDRLEN,
+				  packet->tcp_header_len / 4);
+	} else {
+		/* Enable CRC and Pad Insertion */
+		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, CPC, 0);
+
+		/* Enable HW CSUM */
+		if (csum)
+			XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3,
+					  CIC, 0x3);
+
+		/* Set the total length to be transmitted */
+		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, FL,
+				  packet->length);
+	}
+
+	for (i = ring->cur - start_index + 1; i < packet->rdesc_count; i++) {
+		ring->cur++;
+		rdata = GET_DESC_DATA(ring, ring->cur);
+		rdesc = rdata->rdesc;
+
+		/* Update buffer address */
+		rdesc->desc0 = cpu_to_le32(lower_32_bits(rdata->skb_dma));
+		rdesc->desc1 = cpu_to_le32(upper_32_bits(rdata->skb_dma));
+
+		/* Update the buffer length */
+		XGMAC_SET_BITS_LE(rdesc->desc2, TX_NORMAL_DESC2, HL_B1L,
+				  rdata->skb_dma_len);
+
+		/* Set IC bit based on Tx coalescing settings */
+		XGMAC_SET_BITS_LE(rdesc->desc2, TX_NORMAL_DESC2, IC, 1);
+		if (tx_coalesce && (!tx_frames ||
+				    (++ring->coalesce_count % tx_frames)))
+			/* Clear IC bit */
+			XGMAC_SET_BITS_LE(rdesc->desc2, TX_NORMAL_DESC2, IC, 0);
+
+		/* Set OWN bit */
+		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, OWN, 1);
+
+		/* Mark it as NORMAL descriptor */
+		XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, CTXT, 0);
+
+		/* Enable HW CSUM */
+		if (csum)
+			XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3,
+					  CIC, 0x3);
+	}
+
+	/* Set LAST bit for the last descriptor */
+	XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, LD, 1);
+
+	/* In case the Tx DMA engine is running, make sure everything
+	 * is written to the descriptor(s) before setting the OWN bit
+	 * for the first descriptor
+	 */
+	wmb();
+
+	/* Set OWN bit for the first descriptor */
+	rdata = GET_DESC_DATA(ring, start_index);
+	rdesc = rdata->rdesc;
+	XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, OWN, 1);
+
+#ifdef XGMAC_ENABLE_TX_DESC_DUMP
+	xgbe_dump_tx_desc(ring, start_index, packet->rdesc_count, 1);
+#endif
+
+	/* Make sure ownership is written to the descriptor */
+	wmb();
+
+	/* Issue a poll command to Tx DMA by writing address
+	 * of next immediate free descriptor */
+	ring->cur++;
+	rdata = GET_DESC_DATA(ring, ring->cur);
+	XGMAC_DMA_IOWRITE(channel, DMA_CH_TDTR_LO,
+			  lower_32_bits(rdata->rdesc_dma));
+
+	/* Start the Tx coalescing timer */
+	if (tx_coalesce && !channel->tx_timer_active) {
+		channel->tx_timer_active = 1;
+		hrtimer_start(&channel->tx_timer,
+			      ktime_set(0, pdata->tx_usecs * NSEC_PER_USEC),
+			      HRTIMER_MODE_REL);
+	}
+
+	DBGPR("  %s: descriptors %u to %u written\n",
+	      channel->name, start_index & (ring->rdesc_count - 1),
+	      (ring->cur - 1) & (ring->rdesc_count - 1));
+
+	DBGPR("<--xgbe_pre_xmit\n");
+}
+
+static int xgbe_dev_read(struct xgbe_channel *channel)
+{
+	struct xgbe_ring *ring = channel->rx_ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_ring_desc *rdesc;
+	struct xgbe_packet_data *packet = &ring->packet_data;
+	unsigned int err, etlt;
+
+	DBGPR("-->xgbe_dev_read: cur = %d\n", ring->cur);
+
+	rdata = GET_DESC_DATA(ring, ring->cur);
+	rdesc = rdata->rdesc;
+
+	/* Check for data availability */
+	if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, OWN))
+		return 1;
+
+#ifdef XGMAC_ENABLE_RX_DESC_DUMP
+	xgbe_dump_rx_desc(ring, rdesc, ring->cur);
+#endif
+
+	/* Get the packet length */
+	rdata->len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL);
+
+	if (!XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, LD)) {
+		/* Not all the data has been transferred for this packet */
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       INCOMPLETE, 1);
+		return 0;
+	}
+
+	/* This is the last of the data for this packet */
+	XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+		       INCOMPLETE, 0);
+
+	/* Set checksum done indicator as appropriate */
+	if (channel->pdata->netdev->features & NETIF_F_RXCSUM)
+		XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+			       CSUM_DONE, 1);
+
+	/* Check for errors (only valid in last descriptor) */
+	err = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, ES);
+	etlt = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, ETLT);
+	DBGPR("  err=%u, etlt=%#x\n", err, etlt);
+
+	if (!err || (err && !etlt)) {
+		if (etlt == 0x09) {
+			XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+				       VLAN_CTAG, 1);
+			packet->vlan_ctag = XGMAC_GET_BITS_LE(rdesc->desc0,
+							      RX_NORMAL_DESC0,
+							      OVT);
+			DBGPR("  vlan-ctag=0x%04x\n", packet->vlan_ctag);
+		}
+	} else {
+		if ((etlt == 0x05) || (etlt == 0x06))
+			XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES,
+				       CSUM_DONE, 0);
+		else
+			XGMAC_SET_BITS(packet->errors, RX_PACKET_ERRORS,
+				       FRAME, 1);
+	}
+
+	DBGPR("<--xgbe_dev_read: %s - descriptor=%u (cur=%d)\n", channel->name,
+	      ring->cur & (ring->rdesc_count - 1), ring->cur);
+
+	return 0;
+}
+
+static int xgbe_is_context_desc(struct xgbe_ring_desc *rdesc)
+{
+	/* Rx and Tx share CTXT bit, so check TDES3.CTXT bit */
+	return XGMAC_GET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, CTXT);
+}
+
+static int xgbe_is_last_desc(struct xgbe_ring_desc *rdesc)
+{
+	/* Rx and Tx share LD bit, so check TDES3.LD bit */
+	return XGMAC_GET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, LD);
+}
+
+static void xgbe_save_interrupt_status(struct xgbe_channel *channel,
+				       enum xgbe_int_state int_state)
+{
+	unsigned int dma_ch_ier;
+
+	if (int_state == XGMAC_INT_STATE_SAVE) {
+		channel->saved_ier = XGMAC_DMA_IOREAD(channel, DMA_CH_IER);
+		channel->saved_ier &= DMA_INTERRUPT_MASK;
+	} else {
+		dma_ch_ier = XGMAC_DMA_IOREAD(channel, DMA_CH_IER);
+		dma_ch_ier |= channel->saved_ier;
+		XGMAC_DMA_IOWRITE(channel, DMA_CH_IER, dma_ch_ier);
+	}
+}
+
+static int xgbe_enable_int(struct xgbe_channel *channel,
+			   enum xgbe_int int_id)
+{
+	switch (int_id) {
+	case XGMAC_INT_DMA_ISR_DC0IS:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, TIE, 1);
+		break;
+	case XGMAC_INT_DMA_CH_SR_TI:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, TIE, 1);
+		break;
+	case XGMAC_INT_DMA_CH_SR_TPS:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, TXSE, 1);
+		break;
+	case XGMAC_INT_DMA_CH_SR_TBU:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, TBUE, 1);
+		break;
+	case XGMAC_INT_DMA_CH_SR_RI:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, RIE, 1);
+		break;
+	case XGMAC_INT_DMA_CH_SR_RBU:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, RBUE, 1);
+		break;
+	case XGMAC_INT_DMA_CH_SR_RPS:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, RSE, 1);
+		break;
+	case XGMAC_INT_DMA_CH_SR_FBE:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, FBEE, 1);
+		break;
+	case XGMAC_INT_DMA_ALL:
+		xgbe_save_interrupt_status(channel, XGMAC_INT_STATE_RESTORE);
+		break;
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+
+static int xgbe_disable_int(struct xgbe_channel *channel,
+			    enum xgbe_int int_id)
+{
+	unsigned int dma_ch_ier;
+
+	switch (int_id) {
+	case XGMAC_INT_DMA_ISR_DC0IS:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, TIE, 0);
+		break;
+	case XGMAC_INT_DMA_CH_SR_TI:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, TIE, 0);
+		break;
+	case XGMAC_INT_DMA_CH_SR_TPS:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, TXSE, 0);
+		break;
+	case XGMAC_INT_DMA_CH_SR_TBU:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, TBUE, 0);
+		break;
+	case XGMAC_INT_DMA_CH_SR_RI:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, RIE, 0);
+		break;
+	case XGMAC_INT_DMA_CH_SR_RBU:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, RBUE, 0);
+		break;
+	case XGMAC_INT_DMA_CH_SR_RPS:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, RSE, 0);
+		break;
+	case XGMAC_INT_DMA_CH_SR_FBE:
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_IER, FBEE, 0);
+		break;
+	case XGMAC_INT_DMA_ALL:
+		xgbe_save_interrupt_status(channel, XGMAC_INT_STATE_SAVE);
+
+		dma_ch_ier = XGMAC_DMA_IOREAD(channel, DMA_CH_IER);
+		dma_ch_ier &= ~DMA_INTERRUPT_MASK;
+		XGMAC_DMA_IOWRITE(channel, DMA_CH_IER, dma_ch_ier);
+		break;
+	default:
+		return -1;
+	}
+
+	return 0;
+}
+
+static int xgbe_exit(struct xgbe_prv_data *pdata)
+{
+	unsigned int count = 2000;
+
+	DBGPR("-->xgbe_exit\n");
+
+	/* Issue a software reset */
+	XGMAC_IOWRITE_BITS(pdata, DMA_MR, SWR, 1);
+	usleep_range(10, 15);
+
+	/* Poll Until Poll Condition */
+	while (count-- && XGMAC_IOREAD_BITS(pdata, DMA_MR, SWR))
+		usleep_range(500, 600);
+
+	if (!count)
+		return -EBUSY;
+
+	DBGPR("<--xgbe_exit\n");
+
+	return 0;
+}
+
+static int xgbe_flush_tx_queues(struct xgbe_prv_data *pdata)
+{
+	unsigned int i, count;
+
+	for (i = 0; i < pdata->hw_feat.tx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, FTQ, 1);
+
+	/* Poll Until Poll Condition */
+	for (i = 0; i < pdata->hw_feat.tx_q_cnt; i++) {
+		count = 2000;
+		while (count-- && XGMAC_MTL_IOREAD_BITS(pdata, i,
+							MTL_Q_TQOMR, FTQ))
+			usleep_range(500, 600);
+
+		if (!count)
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+static void xgbe_config_dma_bus(struct xgbe_prv_data *pdata)
+{
+	/* Set enhanced addressing mode */
+	XGMAC_IOWRITE_BITS(pdata, DMA_SBMR, EAME, 1);
+
+	/* Set the System Bus mode */
+	XGMAC_IOWRITE_BITS(pdata, DMA_SBMR, UNDEF, 1);
+}
+
+static void xgbe_config_dma_cache(struct xgbe_prv_data *pdata)
+{
+	unsigned int arcache, awcache;
+
+	arcache = 0;
+	XGMAC_SET_BITS(arcache, DMA_AXIARCR, DRC, DMA_ARCACHE_SETTING);
+	XGMAC_SET_BITS(arcache, DMA_AXIARCR, DRD, DMA_ARDOMAIN_SETTING);
+	XGMAC_SET_BITS(arcache, DMA_AXIARCR, TEC, DMA_ARCACHE_SETTING);
+	XGMAC_SET_BITS(arcache, DMA_AXIARCR, TED, DMA_ARDOMAIN_SETTING);
+	XGMAC_SET_BITS(arcache, DMA_AXIARCR, THC, DMA_ARCACHE_SETTING);
+	XGMAC_SET_BITS(arcache, DMA_AXIARCR, THD, DMA_ARDOMAIN_SETTING);
+	XGMAC_IOWRITE(pdata, DMA_AXIARCR, arcache);
+
+	awcache = 0;
+	XGMAC_SET_BITS(awcache, DMA_AXIAWCR, DWC, DMA_AWCACHE_SETTING);
+	XGMAC_SET_BITS(awcache, DMA_AXIAWCR, DWD, DMA_AWDOMAIN_SETTING);
+	XGMAC_SET_BITS(awcache, DMA_AXIAWCR, RPC, DMA_AWCACHE_SETTING);
+	XGMAC_SET_BITS(awcache, DMA_AXIAWCR, RPD, DMA_AWDOMAIN_SETTING);
+	XGMAC_SET_BITS(awcache, DMA_AXIAWCR, RHC, DMA_AWCACHE_SETTING);
+	XGMAC_SET_BITS(awcache, DMA_AXIAWCR, RHD, DMA_AWDOMAIN_SETTING);
+	XGMAC_SET_BITS(awcache, DMA_AXIAWCR, TDC, DMA_AWCACHE_SETTING);
+	XGMAC_SET_BITS(awcache, DMA_AXIAWCR, TDD, DMA_AWDOMAIN_SETTING);
+	XGMAC_IOWRITE(pdata, DMA_AXIAWCR, awcache);
+}
+
+static void xgbe_config_mtl_mode(struct xgbe_prv_data *pdata)
+{
+	unsigned int i;
+
+	/* Set Tx to weighted round robin scheduling algorithm (when
+	 * traffic class is using ETS algorithm)
+	 */
+	XGMAC_IOWRITE_BITS(pdata, MTL_OMR, ETSALG, MTL_ETSALG_WRR);
+
+	/* Set Tx traffic classes to strict priority algorithm */
+	for (i = 0; i < XGBE_TC_CNT; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_TC_ETSCR, TSA, MTL_TSA_SP);
+
+	/* Set Rx to strict priority algorithm */
+	XGMAC_IOWRITE_BITS(pdata, MTL_OMR, RAA, MTL_RAA_SP);
+}
+
+static unsigned int xgbe_calculate_per_queue_fifo(unsigned long fifo_size,
+						  unsigned char queue_count)
+{
+	unsigned int q_fifo_size = 0;
+	enum xgbe_mtl_fifo_size p_fifo = XGMAC_MTL_FIFO_SIZE_256;
+
+	/* Calculate Tx/Rx fifo share per queue */
+	switch (fifo_size) {
+	case 0:
+		q_fifo_size = FIFO_SIZE_B(128);
+		break;
+	case 1:
+		q_fifo_size = FIFO_SIZE_B(256);
+		break;
+	case 2:
+		q_fifo_size = FIFO_SIZE_B(512);
+		break;
+	case 3:
+		q_fifo_size = FIFO_SIZE_KB(1);
+		break;
+	case 4:
+		q_fifo_size = FIFO_SIZE_KB(2);
+		break;
+	case 5:
+		q_fifo_size = FIFO_SIZE_KB(4);
+		break;
+	case 6:
+		q_fifo_size = FIFO_SIZE_KB(8);
+		break;
+	case 7:
+		q_fifo_size = FIFO_SIZE_KB(16);
+		break;
+	case 8:
+		q_fifo_size = FIFO_SIZE_KB(32);
+		break;
+	case 9:
+		q_fifo_size = FIFO_SIZE_KB(64);
+		break;
+	case 10:
+		q_fifo_size = FIFO_SIZE_KB(128);
+		break;
+	case 11:
+		q_fifo_size = FIFO_SIZE_KB(256);
+		break;
+	}
+	q_fifo_size = q_fifo_size / queue_count;
+
+	/* Set the queue fifo size programmable value */
+	if (q_fifo_size >= FIFO_SIZE_KB(256))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_256K;
+	else if (q_fifo_size >= FIFO_SIZE_KB(128))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_128K;
+	else if (q_fifo_size >= FIFO_SIZE_KB(64))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_64K;
+	else if (q_fifo_size >= FIFO_SIZE_KB(32))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_32K;
+	else if (q_fifo_size >= FIFO_SIZE_KB(16))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_16K;
+	else if (q_fifo_size >= FIFO_SIZE_KB(8))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_8K;
+	else if (q_fifo_size >= FIFO_SIZE_KB(4))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_4K;
+	else if (q_fifo_size >= FIFO_SIZE_KB(2))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_2K;
+	else if (q_fifo_size >= FIFO_SIZE_KB(1))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_1K;
+	else if (q_fifo_size >= FIFO_SIZE_B(512))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_512;
+	else if (q_fifo_size >= FIFO_SIZE_B(256))
+		p_fifo = XGMAC_MTL_FIFO_SIZE_256;
+
+	return p_fifo;
+}
+
+static void xgbe_config_tx_fifo_size(struct xgbe_prv_data *pdata)
+{
+	enum xgbe_mtl_fifo_size fifo_size;
+	unsigned int i;
+
+	fifo_size = xgbe_calculate_per_queue_fifo(pdata->hw_feat.tx_fifo_size,
+						  pdata->hw_feat.tx_q_cnt);
+
+	for (i = 0; i < pdata->hw_feat.tx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, TQS, fifo_size);
+
+	netdev_notice(pdata->netdev, "%d Tx queues, %d byte fifo per queue\n",
+		      pdata->hw_feat.tx_q_cnt, ((fifo_size + 1) * 256));
+}
+
+static void xgbe_config_rx_fifo_size(struct xgbe_prv_data *pdata)
+{
+	enum xgbe_mtl_fifo_size fifo_size;
+	unsigned int i;
+
+	fifo_size = xgbe_calculate_per_queue_fifo(pdata->hw_feat.rx_fifo_size,
+						  pdata->hw_feat.rx_q_cnt);
+
+	for (i = 0; i < pdata->hw_feat.rx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RQS, fifo_size);
+
+	netdev_notice(pdata->netdev, "%d Rx queues, %d byte fifo per queue\n",
+		      pdata->hw_feat.rx_q_cnt, ((fifo_size + 1) * 256));
+}
+
+static void xgbe_config_rx_queue_mapping(struct xgbe_prv_data *pdata)
+{
+	unsigned int i, reg, reg_val;
+	unsigned int q_count = pdata->hw_feat.rx_q_cnt;
+
+	/* Select dynamic mapping of MTL Rx queue to DMA Rx channel */
+	reg = MTL_RQDCM0R;
+	reg_val = 0;
+	for (i = 0; i < q_count;) {
+		reg_val |= (0x80 << ((i++ % MTL_RQDCM_Q_PER_REG) << 3));
+
+		if ((i % MTL_RQDCM_Q_PER_REG) && (i != q_count))
+			continue;
+
+		XGMAC_IOWRITE(pdata, reg, reg_val);
+
+		reg += MTL_RQDCM_INC;
+		reg_val = 0;
+	}
+}
+
+static void xgbe_config_flow_control_threshold(struct xgbe_prv_data *pdata)
+{
+	unsigned int i;
+
+	for (i = 0; i < pdata->hw_feat.rx_q_cnt; i++) {
+		/* Activate flow control when less than 4k left in fifo */
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RFA, 2);
+
+		/* De-activate flow control when more than 6k left in fifo */
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, RFD, 4);
+	}
+}
+
+static void xgbe_config_mac_address(struct xgbe_prv_data *pdata)
+{
+	xgbe_set_mac_address(pdata, pdata->netdev->dev_addr);
+}
+
+static void xgbe_config_jumbo_enable(struct xgbe_prv_data *pdata)
+{
+	unsigned int val;
+
+	val = (pdata->netdev->mtu > XGMAC_STD_PACKET_MTU) ? 1 : 0;
+
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, JE, val);
+}
+
+static void xgbe_config_checksum_offload(struct xgbe_prv_data *pdata)
+{
+	if (pdata->netdev->features & NETIF_F_RXCSUM)
+		xgbe_enable_rx_csum(pdata);
+	else
+		xgbe_disable_rx_csum(pdata);
+}
+
+static void xgbe_config_vlan_support(struct xgbe_prv_data *pdata)
+{
+	if (pdata->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		xgbe_enable_rx_vlan_stripping(pdata);
+	else
+		xgbe_disable_rx_vlan_stripping(pdata);
+}
+
+static void xgbe_tx_mmc_int(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_mmc_stats *stats = &pdata->mmc_stats;
+	unsigned int mmc_isr = XGMAC_IOREAD(pdata, MMC_TISR);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXOCTETCOUNT_GB))
+		stats->txoctetcount_gb +=
+			XGMAC_IOREAD(pdata, MMC_TXOCTETCOUNT_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXFRAMECOUNT_GB))
+		stats->txframecount_gb +=
+			XGMAC_IOREAD(pdata, MMC_TXFRAMECOUNT_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXBROADCASTFRAMES_G))
+		stats->txbroadcastframes_g +=
+			XGMAC_IOREAD(pdata, MMC_TXBROADCASTFRAMES_G_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXMULTICASTFRAMES_G))
+		stats->txmulticastframes_g +=
+			XGMAC_IOREAD(pdata, MMC_TXMULTICASTFRAMES_G_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX64OCTETS_GB))
+		stats->tx64octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_TX64OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX65TO127OCTETS_GB))
+		stats->tx65to127octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_TX65TO127OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX128TO255OCTETS_GB))
+		stats->tx128to255octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_TX128TO255OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX256TO511OCTETS_GB))
+		stats->tx256to511octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_TX256TO511OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX512TO1023OCTETS_GB))
+		stats->tx512to1023octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_TX512TO1023OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TX1024TOMAXOCTETS_GB))
+		stats->tx1024tomaxoctets_gb +=
+			XGMAC_IOREAD(pdata, MMC_TX1024TOMAXOCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXUNICASTFRAMES_GB))
+		stats->txunicastframes_gb +=
+			XGMAC_IOREAD(pdata, MMC_TXUNICASTFRAMES_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXMULTICASTFRAMES_GB))
+		stats->txmulticastframes_gb +=
+			XGMAC_IOREAD(pdata, MMC_TXMULTICASTFRAMES_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXBROADCASTFRAMES_GB))
+		stats->txbroadcastframes_g +=
+			XGMAC_IOREAD(pdata, MMC_TXBROADCASTFRAMES_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXUNDERFLOWERROR))
+		stats->txunderflowerror +=
+			XGMAC_IOREAD(pdata, MMC_TXUNDERFLOWERROR_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXOCTETCOUNT_G))
+		stats->txoctetcount_g +=
+			XGMAC_IOREAD(pdata, MMC_TXOCTETCOUNT_G_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXFRAMECOUNT_G))
+		stats->txframecount_g +=
+			XGMAC_IOREAD(pdata, MMC_TXFRAMECOUNT_G_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXPAUSEFRAMES))
+		stats->txpauseframes +=
+			XGMAC_IOREAD(pdata, MMC_TXPAUSEFRAMES_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_TISR, TXVLANFRAMES_G))
+		stats->txvlanframes_g +=
+			XGMAC_IOREAD(pdata, MMC_TXVLANFRAMES_G_LO);
+}
+
+static void xgbe_rx_mmc_int(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_mmc_stats *stats = &pdata->mmc_stats;
+	unsigned int mmc_isr = XGMAC_IOREAD(pdata, MMC_RISR);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXFRAMECOUNT_GB))
+		stats->rxframecount_gb +=
+			XGMAC_IOREAD(pdata, MMC_RXFRAMECOUNT_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXOCTETCOUNT_GB))
+		stats->rxoctetcount_gb +=
+			XGMAC_IOREAD(pdata, MMC_RXOCTETCOUNT_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXOCTETCOUNT_G))
+		stats->rxoctetcount_g +=
+			XGMAC_IOREAD(pdata, MMC_RXOCTETCOUNT_G_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXBROADCASTFRAMES_G))
+		stats->rxbroadcastframes_g +=
+			XGMAC_IOREAD(pdata, MMC_RXBROADCASTFRAMES_G_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXMULTICASTFRAMES_G))
+		stats->rxmulticastframes_g +=
+			XGMAC_IOREAD(pdata, MMC_RXMULTICASTFRAMES_G_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXCRCERROR))
+		stats->rxcrcerror +=
+			XGMAC_IOREAD(pdata, MMC_RXCRCERROR_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXRUNTERROR))
+		stats->rxrunterror +=
+			XGMAC_IOREAD(pdata, MMC_RXRUNTERROR);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXJABBERERROR))
+		stats->rxjabbererror +=
+			XGMAC_IOREAD(pdata, MMC_RXJABBERERROR);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXUNDERSIZE_G))
+		stats->rxundersize_g +=
+			XGMAC_IOREAD(pdata, MMC_RXUNDERSIZE_G);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXOVERSIZE_G))
+		stats->rxoversize_g +=
+			XGMAC_IOREAD(pdata, MMC_RXOVERSIZE_G);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX64OCTETS_GB))
+		stats->rx64octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_RX64OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX65TO127OCTETS_GB))
+		stats->rx65to127octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_RX65TO127OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX128TO255OCTETS_GB))
+		stats->rx128to255octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_RX128TO255OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX256TO511OCTETS_GB))
+		stats->rx256to511octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_RX256TO511OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX512TO1023OCTETS_GB))
+		stats->rx512to1023octets_gb +=
+			XGMAC_IOREAD(pdata, MMC_RX512TO1023OCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RX1024TOMAXOCTETS_GB))
+		stats->rx1024tomaxoctets_gb +=
+			XGMAC_IOREAD(pdata, MMC_RX1024TOMAXOCTETS_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXUNICASTFRAMES_G))
+		stats->rxunicastframes_g +=
+			XGMAC_IOREAD(pdata, MMC_RXUNICASTFRAMES_G_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXLENGTHERROR))
+		stats->rxlengtherror +=
+			XGMAC_IOREAD(pdata, MMC_RXLENGTHERROR_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXOUTOFRANGETYPE))
+		stats->rxoutofrangetype +=
+			XGMAC_IOREAD(pdata, MMC_RXOUTOFRANGETYPE_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXPAUSEFRAMES))
+		stats->rxpauseframes +=
+			XGMAC_IOREAD(pdata, MMC_RXPAUSEFRAMES_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXFIFOOVERFLOW))
+		stats->rxfifooverflow +=
+			XGMAC_IOREAD(pdata, MMC_RXFIFOOVERFLOW_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXVLANFRAMES_GB))
+		stats->rxvlanframes_gb +=
+			XGMAC_IOREAD(pdata, MMC_RXVLANFRAMES_GB_LO);
+
+	if (XGMAC_GET_BITS(mmc_isr, MMC_RISR, RXWATCHDOGERROR))
+		stats->rxwatchdogerror +=
+			XGMAC_IOREAD(pdata, MMC_RXWATCHDOGERROR);
+}
+
+static void xgbe_read_mmc_stats(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_mmc_stats *stats = &pdata->mmc_stats;
+
+	/* Freeze counters */
+	XGMAC_IOWRITE_BITS(pdata, MMC_CR, MCF, 1);
+
+	stats->txoctetcount_gb +=
+		XGMAC_IOREAD(pdata, MMC_TXOCTETCOUNT_GB_LO);
+
+	stats->txframecount_gb +=
+		XGMAC_IOREAD(pdata, MMC_TXFRAMECOUNT_GB_LO);
+
+	stats->txbroadcastframes_g +=
+		XGMAC_IOREAD(pdata, MMC_TXBROADCASTFRAMES_G_LO);
+
+	stats->txmulticastframes_g +=
+		XGMAC_IOREAD(pdata, MMC_TXMULTICASTFRAMES_G_LO);
+
+	stats->tx64octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_TX64OCTETS_GB_LO);
+
+	stats->tx65to127octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_TX65TO127OCTETS_GB_LO);
+
+	stats->tx128to255octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_TX128TO255OCTETS_GB_LO);
+
+	stats->tx256to511octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_TX256TO511OCTETS_GB_LO);
+
+	stats->tx512to1023octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_TX512TO1023OCTETS_GB_LO);
+
+	stats->tx1024tomaxoctets_gb +=
+		XGMAC_IOREAD(pdata, MMC_TX1024TOMAXOCTETS_GB_LO);
+
+	stats->txunicastframes_gb +=
+		XGMAC_IOREAD(pdata, MMC_TXUNICASTFRAMES_GB_LO);
+
+	stats->txmulticastframes_gb +=
+		XGMAC_IOREAD(pdata, MMC_TXMULTICASTFRAMES_GB_LO);
+
+	stats->txbroadcastframes_g +=
+		XGMAC_IOREAD(pdata, MMC_TXBROADCASTFRAMES_GB_LO);
+
+	stats->txunderflowerror +=
+		XGMAC_IOREAD(pdata, MMC_TXUNDERFLOWERROR_LO);
+
+	stats->txoctetcount_g +=
+		XGMAC_IOREAD(pdata, MMC_TXOCTETCOUNT_G_LO);
+
+	stats->txframecount_g +=
+		XGMAC_IOREAD(pdata, MMC_TXFRAMECOUNT_G_LO);
+
+	stats->txpauseframes +=
+		XGMAC_IOREAD(pdata, MMC_TXPAUSEFRAMES_LO);
+
+	stats->txvlanframes_g +=
+		XGMAC_IOREAD(pdata, MMC_TXVLANFRAMES_G_LO);
+
+	stats->rxframecount_gb +=
+		XGMAC_IOREAD(pdata, MMC_RXFRAMECOUNT_GB_LO);
+
+	stats->rxoctetcount_gb +=
+		XGMAC_IOREAD(pdata, MMC_RXOCTETCOUNT_GB_LO);
+
+	stats->rxoctetcount_g +=
+		XGMAC_IOREAD(pdata, MMC_RXOCTETCOUNT_G_LO);
+
+	stats->rxbroadcastframes_g +=
+		XGMAC_IOREAD(pdata, MMC_RXBROADCASTFRAMES_G_LO);
+
+	stats->rxmulticastframes_g +=
+		XGMAC_IOREAD(pdata, MMC_RXMULTICASTFRAMES_G_LO);
+
+	stats->rxcrcerror +=
+		XGMAC_IOREAD(pdata, MMC_RXCRCERROR_LO);
+
+	stats->rxrunterror +=
+		XGMAC_IOREAD(pdata, MMC_RXRUNTERROR);
+
+	stats->rxjabbererror +=
+		XGMAC_IOREAD(pdata, MMC_RXJABBERERROR);
+
+	stats->rxundersize_g +=
+		XGMAC_IOREAD(pdata, MMC_RXUNDERSIZE_G);
+
+	stats->rxoversize_g +=
+		XGMAC_IOREAD(pdata, MMC_RXOVERSIZE_G);
+
+	stats->rx64octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_RX64OCTETS_GB_LO);
+
+	stats->rx65to127octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_RX65TO127OCTETS_GB_LO);
+
+	stats->rx128to255octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_RX128TO255OCTETS_GB_LO);
+
+	stats->rx256to511octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_RX256TO511OCTETS_GB_LO);
+
+	stats->rx512to1023octets_gb +=
+		XGMAC_IOREAD(pdata, MMC_RX512TO1023OCTETS_GB_LO);
+
+	stats->rx1024tomaxoctets_gb +=
+		XGMAC_IOREAD(pdata, MMC_RX1024TOMAXOCTETS_GB_LO);
+
+	stats->rxunicastframes_g +=
+		XGMAC_IOREAD(pdata, MMC_RXUNICASTFRAMES_G_LO);
+
+	stats->rxlengtherror +=
+		XGMAC_IOREAD(pdata, MMC_RXLENGTHERROR_LO);
+
+	stats->rxoutofrangetype +=
+		XGMAC_IOREAD(pdata, MMC_RXOUTOFRANGETYPE_LO);
+
+	stats->rxpauseframes +=
+		XGMAC_IOREAD(pdata, MMC_RXPAUSEFRAMES_LO);
+
+	stats->rxfifooverflow +=
+		XGMAC_IOREAD(pdata, MMC_RXFIFOOVERFLOW_LO);
+
+	stats->rxvlanframes_gb +=
+		XGMAC_IOREAD(pdata, MMC_RXVLANFRAMES_GB_LO);
+
+	stats->rxwatchdogerror +=
+		XGMAC_IOREAD(pdata, MMC_RXWATCHDOGERROR);
+
+	/* Un-freeze counters */
+	XGMAC_IOWRITE_BITS(pdata, MMC_CR, MCF, 0);
+}
+
+static void xgbe_config_mmc(struct xgbe_prv_data *pdata)
+{
+	/* Set counters to reset on read */
+	XGMAC_IOWRITE_BITS(pdata, MMC_CR, ROR, 1);
+
+	/* Reset the counters */
+	XGMAC_IOWRITE_BITS(pdata, MMC_CR, CR, 1);
+}
+
+static void xgbe_enable_tx(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	/* Enable each Tx DMA channel */
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_TCR, ST, 1);
+	}
+
+	/* Enable each Tx queue */
+	for (i = 0; i < pdata->hw_feat.tx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, TXQEN,
+				       MTL_Q_ENABLED);
+
+	/* Enable MAC Tx */
+	XGMAC_IOWRITE_BITS(pdata, MAC_TCR, TE, 1);
+}
+
+static void xgbe_disable_tx(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	/* Disable MAC Tx */
+	XGMAC_IOWRITE_BITS(pdata, MAC_TCR, TE, 0);
+
+	/* Disable each Tx queue */
+	for (i = 0; i < pdata->hw_feat.tx_q_cnt; i++)
+		XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_TQOMR, TXQEN, 0);
+
+	/* Disable each Tx DMA channel */
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_TCR, ST, 0);
+	}
+}
+
+static void xgbe_enable_rx(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int reg_val, i;
+
+	/* Enable each Rx DMA channel */
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_RCR, SR, 1);
+	}
+
+	/* Enable each Rx queue */
+	reg_val = 0;
+	for (i = 0; i < pdata->hw_feat.rx_q_cnt; i++)
+		reg_val |= (0x02 << (i << 1));
+	XGMAC_IOWRITE(pdata, MAC_RQC0R, reg_val);
+
+	/* Enable MAC Rx */
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 1);
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 1);
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 1);
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 1);
+}
+
+static void xgbe_disable_rx(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	/* Disable MAC Rx */
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, DCRCC, 0);
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, CST, 0);
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, ACS, 0);
+	XGMAC_IOWRITE_BITS(pdata, MAC_RCR, RE, 0);
+
+	/* Disable each Rx queue */
+	XGMAC_IOWRITE(pdata, MAC_RQC0R, 0);
+
+	/* Disable each Rx DMA channel */
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_RCR, SR, 0);
+	}
+}
+
+static void xgbe_powerup_tx(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	/* Enable each Tx DMA channel */
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_TCR, ST, 1);
+	}
+
+	/* Enable MAC Tx */
+	XGMAC_IOWRITE_BITS(pdata, MAC_TCR, TE, 1);
+}
+
+static void xgbe_powerdown_tx(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	/* Disable MAC Tx */
+	XGMAC_IOWRITE_BITS(pdata, MAC_TCR, TE, 0);
+
+	/* Disable each Tx DMA channel */
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_TCR, ST, 0);
+	}
+}
+
+static void xgbe_powerup_rx(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	/* Enable each Rx DMA channel */
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_RCR, SR, 1);
+	}
+}
+
+static void xgbe_powerdown_rx(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	/* Disable each Rx DMA channel */
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->rx_ring)
+			break;
+
+		XGMAC_DMA_IOWRITE_BITS(channel, DMA_CH_RCR, SR, 0);
+	}
+}
+
+static int xgbe_init(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_desc_if *desc_if = &pdata->desc_if;
+	int ret;
+
+	DBGPR("-->xgbe_init\n");
+
+	/* Flush Tx queues */
+	ret = xgbe_flush_tx_queues(pdata);
+	if (ret)
+		return ret;
+
+	/*
+	 * Initialize DMA related features
+	 */
+	xgbe_config_dma_bus(pdata);
+	xgbe_config_dma_cache(pdata);
+	xgbe_config_osp_mode(pdata);
+	xgbe_config_pblx8(pdata);
+	xgbe_config_tx_pbl_val(pdata);
+	xgbe_config_rx_pbl_val(pdata);
+	xgbe_config_rx_coalesce(pdata);
+	xgbe_config_tx_coalesce(pdata);
+	xgbe_config_rx_buffer_size(pdata);
+	xgbe_config_tso_mode(pdata);
+	desc_if->wrapper_tx_desc_init(pdata);
+	desc_if->wrapper_rx_desc_init(pdata);
+	xgbe_enable_dma_interrupts(pdata);
+
+	/*
+	 * Initialize MTL related features
+	 */
+	xgbe_config_mtl_mode(pdata);
+	xgbe_config_rx_queue_mapping(pdata);
+	/*TODO: Program the priorities mapped to the Selected Traffic Classes
+		in MTL_TC_Prty_Map0-3 registers */
+	xgbe_config_tsf_mode(pdata, pdata->tx_sf_mode);
+	xgbe_config_rsf_mode(pdata, pdata->rx_sf_mode);
+	xgbe_config_tx_threshold(pdata, pdata->tx_threshold);
+	xgbe_config_rx_threshold(pdata, pdata->rx_threshold);
+	xgbe_config_tx_fifo_size(pdata);
+	xgbe_config_rx_fifo_size(pdata);
+	xgbe_config_flow_control_threshold(pdata);
+	/*TODO: Queue to Traffic Class Mapping (Q2TCMAP) */
+	/*TODO: Error Packet and undersized good Packet forwarding enable
+		(FEP and FUP)
+	 */
+	xgbe_enable_mtl_interrupts(pdata);
+
+	/* Transmit Class Weight */
+	XGMAC_IOWRITE_BITS(pdata, MTL_Q_TCQWR, QW, 0x10);
+
+	/*
+	 * Initialize MAC related features
+	 */
+	xgbe_config_mac_address(pdata);
+	xgbe_config_jumbo_enable(pdata);
+	xgbe_config_flow_control(pdata);
+	xgbe_config_checksum_offload(pdata);
+	xgbe_config_vlan_support(pdata);
+	xgbe_config_mmc(pdata);
+	xgbe_enable_mac_interrupts(pdata);
+
+	DBGPR("<--xgbe_init\n");
+
+	return 0;
+}
+
+void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if)
+{
+	DBGPR("-->xgbe_init_function_ptrs\n");
+
+	hw_if->tx_complete = xgbe_tx_complete;
+
+	hw_if->set_promiscuous_mode = xgbe_set_promiscuous_mode;
+	hw_if->set_all_multicast_mode = xgbe_set_all_multicast_mode;
+	hw_if->set_addn_mac_addrs = xgbe_set_addn_mac_addrs;
+	hw_if->set_mac_address = xgbe_set_mac_address;
+
+	hw_if->enable_rx_csum = xgbe_enable_rx_csum;
+	hw_if->disable_rx_csum = xgbe_disable_rx_csum;
+
+	hw_if->enable_rx_vlan_stripping = xgbe_enable_rx_vlan_stripping;
+	hw_if->disable_rx_vlan_stripping = xgbe_disable_rx_vlan_stripping;
+
+	hw_if->read_mmd_regs = xgbe_read_mmd_regs;
+	hw_if->write_mmd_regs = xgbe_write_mmd_regs;
+
+	hw_if->set_gmii_speed = xgbe_set_gmii_speed;
+	hw_if->set_gmii_2500_speed = xgbe_set_gmii_2500_speed;
+	hw_if->set_xgmii_speed = xgbe_set_xgmii_speed;
+
+	hw_if->enable_tx = xgbe_enable_tx;
+	hw_if->disable_tx = xgbe_disable_tx;
+	hw_if->enable_rx = xgbe_enable_rx;
+	hw_if->disable_rx = xgbe_disable_rx;
+
+	hw_if->powerup_tx = xgbe_powerup_tx;
+	hw_if->powerdown_tx = xgbe_powerdown_tx;
+	hw_if->powerup_rx = xgbe_powerup_rx;
+	hw_if->powerdown_rx = xgbe_powerdown_rx;
+
+	hw_if->pre_xmit = xgbe_pre_xmit;
+	hw_if->dev_read = xgbe_dev_read;
+	hw_if->enable_int = xgbe_enable_int;
+	hw_if->disable_int = xgbe_disable_int;
+	hw_if->init = xgbe_init;
+	hw_if->exit = xgbe_exit;
+
+	/* Descriptor related Sequences have to be initialized here */
+	hw_if->tx_desc_init = xgbe_tx_desc_init;
+	hw_if->rx_desc_init = xgbe_rx_desc_init;
+	hw_if->tx_desc_reset = xgbe_tx_desc_reset;
+	hw_if->rx_desc_reset = xgbe_rx_desc_reset;
+	hw_if->is_last_desc = xgbe_is_last_desc;
+	hw_if->is_context_desc = xgbe_is_context_desc;
+
+	/* For FLOW ctrl */
+	hw_if->config_tx_flow_control = xgbe_config_tx_flow_control;
+	hw_if->config_rx_flow_control = xgbe_config_rx_flow_control;
+
+	/* For RX coalescing */
+	hw_if->config_rx_coalesce = xgbe_config_rx_coalesce;
+	hw_if->config_tx_coalesce = xgbe_config_tx_coalesce;
+	hw_if->usec_to_riwt = xgbe_usec_to_riwt;
+	hw_if->riwt_to_usec = xgbe_riwt_to_usec;
+
+	/* For RX and TX threshold config */
+	hw_if->config_rx_threshold = xgbe_config_rx_threshold;
+	hw_if->config_tx_threshold = xgbe_config_tx_threshold;
+
+	/* For RX and TX Store and Forward Mode config */
+	hw_if->config_rsf_mode = xgbe_config_rsf_mode;
+	hw_if->config_tsf_mode = xgbe_config_tsf_mode;
+
+	/* For TX DMA Operating on Second Frame config */
+	hw_if->config_osp_mode = xgbe_config_osp_mode;
+
+	/* For RX and TX PBL config */
+	hw_if->config_rx_pbl_val = xgbe_config_rx_pbl_val;
+	hw_if->get_rx_pbl_val = xgbe_get_rx_pbl_val;
+	hw_if->config_tx_pbl_val = xgbe_config_tx_pbl_val;
+	hw_if->get_tx_pbl_val = xgbe_get_tx_pbl_val;
+	hw_if->config_pblx8 = xgbe_config_pblx8;
+
+	/* For MMC statistics support */
+	hw_if->tx_mmc_int = xgbe_tx_mmc_int;
+	hw_if->rx_mmc_int = xgbe_rx_mmc_int;
+	hw_if->read_mmc_stats = xgbe_read_mmc_stats;
+
+	DBGPR("<--xgbe_init_function_ptrs\n");
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
new file mode 100644
index 00000000000..cfe3d93b5f5
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -0,0 +1,1351 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/tcp.h>
+#include <linux/if_vlan.h>
+#include <linux/phy.h>
+#include <net/busy_poll.h>
+#include <linux/clk.h>
+#include <linux/if_ether.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+
+static int xgbe_poll(struct napi_struct *, int);
+static void xgbe_set_rx_mode(struct net_device *);
+
+static inline unsigned int xgbe_tx_avail_desc(struct xgbe_ring *ring)
+{
+	return (ring->rdesc_count - (ring->cur - ring->dirty));
+}
+
+static int xgbe_calc_rx_buf_size(struct net_device *netdev, unsigned int mtu)
+{
+	unsigned int rx_buf_size;
+
+	if (mtu > XGMAC_JUMBO_PACKET_MTU) {
+		netdev_alert(netdev, "MTU exceeds maximum supported value\n");
+		return -EINVAL;
+	}
+
+	rx_buf_size = mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+	if (rx_buf_size < RX_MIN_BUF_SIZE)
+		rx_buf_size = RX_MIN_BUF_SIZE;
+	rx_buf_size = (rx_buf_size + RX_BUF_ALIGN - 1) & ~(RX_BUF_ALIGN - 1);
+
+	return rx_buf_size;
+}
+
+static void xgbe_enable_rx_tx_ints(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (channel->tx_ring)
+			hw_if->enable_int(channel,
+					  XGMAC_INT_DMA_CH_SR_TI);
+		if (channel->rx_ring)
+			hw_if->enable_int(channel,
+					  XGMAC_INT_DMA_CH_SR_RI);
+	}
+}
+
+static void xgbe_disable_rx_tx_ints(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (channel->tx_ring)
+			hw_if->disable_int(channel,
+					   XGMAC_INT_DMA_CH_SR_TI);
+		if (channel->rx_ring)
+			hw_if->disable_int(channel,
+					   XGMAC_INT_DMA_CH_SR_RI);
+	}
+}
+
+static irqreturn_t xgbe_isr(int irq, void *data)
+{
+	struct xgbe_prv_data *pdata = data;
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_channel *channel;
+	unsigned int dma_isr, dma_ch_isr;
+	unsigned int mac_isr;
+	unsigned int i;
+
+	/* The DMA interrupt status register also reports MAC and MTL
+	 * interrupts. So for polling mode, we just need to check for
+	 * this register to be non-zero
+	 */
+	dma_isr = XGMAC_IOREAD(pdata, DMA_ISR);
+	if (!dma_isr)
+		goto isr_done;
+
+	DBGPR("-->xgbe_isr\n");
+
+	DBGPR("  DMA_ISR = %08x\n", dma_isr);
+	DBGPR("  DMA_DS0 = %08x\n", XGMAC_IOREAD(pdata, DMA_DSR0));
+	DBGPR("  DMA_DS1 = %08x\n", XGMAC_IOREAD(pdata, DMA_DSR1));
+
+	for (i = 0; i < pdata->channel_count; i++) {
+		if (!(dma_isr & (1 << i)))
+			continue;
+
+		channel = pdata->channel + i;
+
+		dma_ch_isr = XGMAC_DMA_IOREAD(channel, DMA_CH_SR);
+		DBGPR("  DMA_CH%u_ISR = %08x\n", i, dma_ch_isr);
+
+		if (XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, TI) ||
+		    XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, RI)) {
+			if (napi_schedule_prep(&pdata->napi)) {
+				/* Disable Tx and Rx interrupts */
+				xgbe_disable_rx_tx_ints(pdata);
+
+				/* Turn on polling */
+				__napi_schedule(&pdata->napi);
+			}
+		}
+
+		/* Restart the device on a Fatal Bus Error */
+		if (XGMAC_GET_BITS(dma_ch_isr, DMA_CH_SR, FBE))
+			schedule_work(&pdata->restart_work);
+
+		/* Clear all interrupt signals */
+		XGMAC_DMA_IOWRITE(channel, DMA_CH_SR, dma_ch_isr);
+	}
+
+	if (XGMAC_GET_BITS(dma_isr, DMA_ISR, MACIS)) {
+		mac_isr = XGMAC_IOREAD(pdata, MAC_ISR);
+
+		if (XGMAC_GET_BITS(mac_isr, MAC_ISR, MMCTXIS))
+			hw_if->tx_mmc_int(pdata);
+
+		if (XGMAC_GET_BITS(mac_isr, MAC_ISR, MMCRXIS))
+			hw_if->rx_mmc_int(pdata);
+	}
+
+	DBGPR("  DMA_ISR = %08x\n", XGMAC_IOREAD(pdata, DMA_ISR));
+
+	DBGPR("<--xgbe_isr\n");
+
+isr_done:
+	return IRQ_HANDLED;
+}
+
+static enum hrtimer_restart xgbe_tx_timer(struct hrtimer *timer)
+{
+	struct xgbe_channel *channel = container_of(timer,
+						    struct xgbe_channel,
+						    tx_timer);
+	struct xgbe_ring *ring = channel->tx_ring;
+	struct xgbe_prv_data *pdata = channel->pdata;
+	unsigned long flags;
+
+	DBGPR("-->xgbe_tx_timer\n");
+
+	spin_lock_irqsave(&ring->lock, flags);
+
+	if (napi_schedule_prep(&pdata->napi)) {
+		/* Disable Tx and Rx interrupts */
+		xgbe_disable_rx_tx_ints(pdata);
+
+		/* Turn on polling */
+		__napi_schedule(&pdata->napi);
+	}
+
+	channel->tx_timer_active = 0;
+
+	spin_unlock_irqrestore(&ring->lock, flags);
+
+	DBGPR("<--xgbe_tx_timer\n");
+
+	return HRTIMER_NORESTART;
+}
+
+static void xgbe_init_tx_timers(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	DBGPR("-->xgbe_init_tx_timers\n");
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		DBGPR("  %s adding tx timer\n", channel->name);
+		hrtimer_init(&channel->tx_timer, CLOCK_MONOTONIC,
+			     HRTIMER_MODE_REL);
+		channel->tx_timer.function = xgbe_tx_timer;
+	}
+
+	DBGPR("<--xgbe_init_tx_timers\n");
+}
+
+static void xgbe_stop_tx_timers(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel;
+	unsigned int i;
+
+	DBGPR("-->xgbe_stop_tx_timers\n");
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		if (!channel->tx_ring)
+			break;
+
+		DBGPR("  %s deleting tx timer\n", channel->name);
+		channel->tx_timer_active = 0;
+		hrtimer_cancel(&channel->tx_timer);
+	}
+
+	DBGPR("<--xgbe_stop_tx_timers\n");
+}
+
+void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata)
+{
+	unsigned int mac_hfr0, mac_hfr1, mac_hfr2;
+	struct xgbe_hw_features *hw_feat = &pdata->hw_feat;
+
+	DBGPR("-->xgbe_get_all_hw_features\n");
+
+	mac_hfr0 = XGMAC_IOREAD(pdata, MAC_HWF0R);
+	mac_hfr1 = XGMAC_IOREAD(pdata, MAC_HWF1R);
+	mac_hfr2 = XGMAC_IOREAD(pdata, MAC_HWF2R);
+
+	memset(hw_feat, 0, sizeof(*hw_feat));
+
+	/* Hardware feature register 0 */
+	hw_feat->gmii        = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, GMIISEL);
+	hw_feat->vlhash      = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, VLHASH);
+	hw_feat->sma         = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, SMASEL);
+	hw_feat->rwk         = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, RWKSEL);
+	hw_feat->mgk         = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, MGKSEL);
+	hw_feat->mmc         = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, MMCSEL);
+	hw_feat->aoe         = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, ARPOFFSEL);
+	hw_feat->ts          = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, TSSEL);
+	hw_feat->eee         = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, EEESEL);
+	hw_feat->tx_coe      = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, TXCOESEL);
+	hw_feat->rx_coe      = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, RXCOESEL);
+	hw_feat->addn_mac    = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R,
+					      ADDMACADRSEL);
+	hw_feat->ts_src      = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, TSSTSSEL);
+	hw_feat->sa_vlan_ins = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, SAVLANINS);
+
+	/* Hardware feature register 1 */
+	hw_feat->rx_fifo_size  = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R,
+						RXFIFOSIZE);
+	hw_feat->tx_fifo_size  = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R,
+						TXFIFOSIZE);
+	hw_feat->dcb           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, DCBEN);
+	hw_feat->sph           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, SPHEN);
+	hw_feat->tso           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, TSOEN);
+	hw_feat->dma_debug     = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, DBGMEMA);
+	hw_feat->hash_table_size = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R,
+						  HASHTBLSZ);
+	hw_feat->l3l4_filter_num = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R,
+						  L3L4FNUM);
+
+	/* Hardware feature register 2 */
+	hw_feat->rx_q_cnt     = XGMAC_GET_BITS(mac_hfr2, MAC_HWF2R, RXQCNT);
+	hw_feat->tx_q_cnt     = XGMAC_GET_BITS(mac_hfr2, MAC_HWF2R, TXQCNT);
+	hw_feat->rx_ch_cnt    = XGMAC_GET_BITS(mac_hfr2, MAC_HWF2R, RXCHCNT);
+	hw_feat->tx_ch_cnt    = XGMAC_GET_BITS(mac_hfr2, MAC_HWF2R, TXCHCNT);
+	hw_feat->pps_out_num  = XGMAC_GET_BITS(mac_hfr2, MAC_HWF2R, PPSOUTNUM);
+	hw_feat->aux_snap_num = XGMAC_GET_BITS(mac_hfr2, MAC_HWF2R, AUXSNAPNUM);
+
+	/* The Queue and Channel counts are zero based so increment them
+	 * to get the actual number
+	 */
+	hw_feat->rx_q_cnt++;
+	hw_feat->tx_q_cnt++;
+	hw_feat->rx_ch_cnt++;
+	hw_feat->tx_ch_cnt++;
+
+	DBGPR("<--xgbe_get_all_hw_features\n");
+}
+
+static void xgbe_napi_enable(struct xgbe_prv_data *pdata, unsigned int add)
+{
+	if (add)
+		netif_napi_add(pdata->netdev, &pdata->napi, xgbe_poll,
+			       NAPI_POLL_WEIGHT);
+	napi_enable(&pdata->napi);
+}
+
+static void xgbe_napi_disable(struct xgbe_prv_data *pdata)
+{
+	napi_disable(&pdata->napi);
+}
+
+void xgbe_init_tx_coalesce(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+
+	DBGPR("-->xgbe_init_tx_coalesce\n");
+
+	pdata->tx_usecs = XGMAC_INIT_DMA_TX_USECS;
+	pdata->tx_frames = XGMAC_INIT_DMA_TX_FRAMES;
+
+	hw_if->config_tx_coalesce(pdata);
+
+	DBGPR("<--xgbe_init_tx_coalesce\n");
+}
+
+void xgbe_init_rx_coalesce(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+
+	DBGPR("-->xgbe_init_rx_coalesce\n");
+
+	pdata->rx_riwt = hw_if->usec_to_riwt(pdata, XGMAC_INIT_DMA_RX_USECS);
+	pdata->rx_frames = XGMAC_INIT_DMA_RX_FRAMES;
+
+	hw_if->config_rx_coalesce(pdata);
+
+	DBGPR("<--xgbe_init_rx_coalesce\n");
+}
+
+static void xgbe_free_tx_skbuff(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_desc_if *desc_if = &pdata->desc_if;
+	struct xgbe_channel *channel;
+	struct xgbe_ring *ring;
+	struct xgbe_ring_data *rdata;
+	unsigned int i, j;
+
+	DBGPR("-->xgbe_free_tx_skbuff\n");
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->tx_ring;
+		if (!ring)
+			break;
+
+		for (j = 0; j < ring->rdesc_count; j++) {
+			rdata = GET_DESC_DATA(ring, j);
+			desc_if->unmap_skb(pdata, rdata);
+		}
+	}
+
+	DBGPR("<--xgbe_free_tx_skbuff\n");
+}
+
+static void xgbe_free_rx_skbuff(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_desc_if *desc_if = &pdata->desc_if;
+	struct xgbe_channel *channel;
+	struct xgbe_ring *ring;
+	struct xgbe_ring_data *rdata;
+	unsigned int i, j;
+
+	DBGPR("-->xgbe_free_rx_skbuff\n");
+
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++) {
+		ring = channel->rx_ring;
+		if (!ring)
+			break;
+
+		for (j = 0; j < ring->rdesc_count; j++) {
+			rdata = GET_DESC_DATA(ring, j);
+			desc_if->unmap_skb(pdata, rdata);
+		}
+	}
+
+	DBGPR("<--xgbe_free_rx_skbuff\n");
+}
+
+int xgbe_powerdown(struct net_device *netdev, unsigned int caller)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	unsigned long flags;
+
+	DBGPR("-->xgbe_powerdown\n");
+
+	if (!netif_running(netdev) ||
+	    (caller == XGMAC_IOCTL_CONTEXT && pdata->power_down)) {
+		netdev_alert(netdev, "Device is already powered down\n");
+		DBGPR("<--xgbe_powerdown\n");
+		return -EINVAL;
+	}
+
+	phy_stop(pdata->phydev);
+
+	spin_lock_irqsave(&pdata->lock, flags);
+
+	if (caller == XGMAC_DRIVER_CONTEXT)
+		netif_device_detach(netdev);
+
+	netif_tx_stop_all_queues(netdev);
+	xgbe_napi_disable(pdata);
+
+	/* Powerdown Tx/Rx */
+	hw_if->powerdown_tx(pdata);
+	hw_if->powerdown_rx(pdata);
+
+	pdata->power_down = 1;
+
+	spin_unlock_irqrestore(&pdata->lock, flags);
+
+	DBGPR("<--xgbe_powerdown\n");
+
+	return 0;
+}
+
+int xgbe_powerup(struct net_device *netdev, unsigned int caller)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	unsigned long flags;
+
+	DBGPR("-->xgbe_powerup\n");
+
+	if (!netif_running(netdev) ||
+	    (caller == XGMAC_IOCTL_CONTEXT && !pdata->power_down)) {
+		netdev_alert(netdev, "Device is already powered up\n");
+		DBGPR("<--xgbe_powerup\n");
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&pdata->lock, flags);
+
+	pdata->power_down = 0;
+
+	phy_start(pdata->phydev);
+
+	/* Enable Tx/Rx */
+	hw_if->powerup_tx(pdata);
+	hw_if->powerup_rx(pdata);
+
+	if (caller == XGMAC_DRIVER_CONTEXT)
+		netif_device_attach(netdev);
+
+	xgbe_napi_enable(pdata, 0);
+	netif_tx_start_all_queues(netdev);
+
+	spin_unlock_irqrestore(&pdata->lock, flags);
+
+	DBGPR("<--xgbe_powerup\n");
+
+	return 0;
+}
+
+static int xgbe_start(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct net_device *netdev = pdata->netdev;
+
+	DBGPR("-->xgbe_start\n");
+
+	xgbe_set_rx_mode(netdev);
+
+	hw_if->init(pdata);
+
+	phy_start(pdata->phydev);
+
+	hw_if->enable_tx(pdata);
+	hw_if->enable_rx(pdata);
+
+	xgbe_init_tx_timers(pdata);
+
+	xgbe_napi_enable(pdata, 1);
+	netif_tx_start_all_queues(netdev);
+
+	DBGPR("<--xgbe_start\n");
+
+	return 0;
+}
+
+static void xgbe_stop(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct net_device *netdev = pdata->netdev;
+
+	DBGPR("-->xgbe_stop\n");
+
+	phy_stop(pdata->phydev);
+
+	netif_tx_stop_all_queues(netdev);
+	xgbe_napi_disable(pdata);
+
+	xgbe_stop_tx_timers(pdata);
+
+	hw_if->disable_tx(pdata);
+	hw_if->disable_rx(pdata);
+
+	DBGPR("<--xgbe_stop\n");
+}
+
+static void xgbe_restart_dev(struct xgbe_prv_data *pdata, unsigned int reset)
+{
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+
+	DBGPR("-->xgbe_restart_dev\n");
+
+	/* If not running, "restart" will happen on open */
+	if (!netif_running(pdata->netdev))
+		return;
+
+	xgbe_stop(pdata);
+	synchronize_irq(pdata->irq_number);
+
+	xgbe_free_tx_skbuff(pdata);
+	xgbe_free_rx_skbuff(pdata);
+
+	/* Issue software reset to device if requested */
+	if (reset)
+		hw_if->exit(pdata);
+
+	xgbe_start(pdata);
+
+	DBGPR("<--xgbe_restart_dev\n");
+}
+
+static void xgbe_restart(struct work_struct *work)
+{
+	struct xgbe_prv_data *pdata = container_of(work,
+						   struct xgbe_prv_data,
+						   restart_work);
+
+	rtnl_lock();
+
+	xgbe_restart_dev(pdata, 1);
+
+	rtnl_unlock();
+}
+
+static void xgbe_prep_vlan(struct sk_buff *skb, struct xgbe_packet_data *packet)
+{
+	if (vlan_tx_tag_present(skb))
+		packet->vlan_ctag = vlan_tx_tag_get(skb);
+}
+
+static int xgbe_prep_tso(struct sk_buff *skb, struct xgbe_packet_data *packet)
+{
+	int ret;
+
+	if (!XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			    TSO_ENABLE))
+		return 0;
+
+	ret = skb_cow_head(skb, 0);
+	if (ret)
+		return ret;
+
+	packet->header_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	packet->tcp_header_len = tcp_hdrlen(skb);
+	packet->tcp_payload_len = skb->len - packet->header_len;
+	packet->mss = skb_shinfo(skb)->gso_size;
+	DBGPR("  packet->header_len=%u\n", packet->header_len);
+	DBGPR("  packet->tcp_header_len=%u, packet->tcp_payload_len=%u\n",
+	      packet->tcp_header_len, packet->tcp_payload_len);
+	DBGPR("  packet->mss=%u\n", packet->mss);
+
+	return 0;
+}
+
+static int xgbe_is_tso(struct sk_buff *skb)
+{
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (!skb_is_gso(skb))
+		return 0;
+
+	DBGPR("  TSO packet to be processed\n");
+
+	return 1;
+}
+
+static void xgbe_packet_info(struct xgbe_ring *ring, struct sk_buff *skb,
+			     struct xgbe_packet_data *packet)
+{
+	struct skb_frag_struct *frag;
+	unsigned int context_desc;
+	unsigned int len;
+	unsigned int i;
+
+	context_desc = 0;
+	packet->rdesc_count = 0;
+
+	if (xgbe_is_tso(skb)) {
+		/* TSO requires an extra desriptor if mss is different */
+		if (skb_shinfo(skb)->gso_size != ring->tx.cur_mss) {
+			context_desc = 1;
+			packet->rdesc_count++;
+		}
+
+		/* TSO requires an extra desriptor for TSO header */
+		packet->rdesc_count++;
+
+		XGMAC_SET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			       TSO_ENABLE, 1);
+		XGMAC_SET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			       CSUM_ENABLE, 1);
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL)
+		XGMAC_SET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			       CSUM_ENABLE, 1);
+
+	if (vlan_tx_tag_present(skb)) {
+		/* VLAN requires an extra descriptor if tag is different */
+		if (vlan_tx_tag_get(skb) != ring->tx.cur_vlan_ctag)
+			/* We can share with the TSO context descriptor */
+			if (!context_desc) {
+				context_desc = 1;
+				packet->rdesc_count++;
+			}
+
+		XGMAC_SET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES,
+			       VLAN_CTAG, 1);
+	}
+
+	for (len = skb_headlen(skb); len;) {
+		packet->rdesc_count++;
+		len -= min_t(unsigned int, len, TX_MAX_BUF_SIZE);
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		frag = &skb_shinfo(skb)->frags[i];
+		for (len = skb_frag_size(frag); len; ) {
+			packet->rdesc_count++;
+			len -= min_t(unsigned int, len, TX_MAX_BUF_SIZE);
+		}
+	}
+}
+
+static int xgbe_open(struct net_device *netdev)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_desc_if *desc_if = &pdata->desc_if;
+	int ret;
+
+	DBGPR("-->xgbe_open\n");
+
+	/* Enable the clock */
+	ret = clk_prepare_enable(pdata->sysclock);
+	if (ret) {
+		netdev_alert(netdev, "clk_prepare_enable failed\n");
+		return ret;
+	}
+
+	/* Calculate the Rx buffer size before allocating rings */
+	ret = xgbe_calc_rx_buf_size(netdev, netdev->mtu);
+	if (ret < 0)
+		goto err_clk;
+	pdata->rx_buf_size = ret;
+
+	/* Allocate the ring descriptors and buffers */
+	ret = desc_if->alloc_ring_resources(pdata);
+	if (ret)
+		goto err_clk;
+
+	/* Initialize the device restart work struct */
+	INIT_WORK(&pdata->restart_work, xgbe_restart);
+
+	/* Request interrupts */
+	ret = devm_request_irq(pdata->dev, netdev->irq, xgbe_isr, 0,
+			       netdev->name, pdata);
+	if (ret) {
+		netdev_alert(netdev, "error requesting irq %d\n",
+			     pdata->irq_number);
+		goto err_irq;
+	}
+	pdata->irq_number = netdev->irq;
+
+	ret = xgbe_start(pdata);
+	if (ret)
+		goto err_start;
+
+	DBGPR("<--xgbe_open\n");
+
+	return 0;
+
+err_start:
+	hw_if->exit(pdata);
+
+	devm_free_irq(pdata->dev, pdata->irq_number, pdata);
+	pdata->irq_number = 0;
+
+err_irq:
+	desc_if->free_ring_resources(pdata);
+
+err_clk:
+	clk_disable_unprepare(pdata->sysclock);
+
+	return ret;
+}
+
+static int xgbe_close(struct net_device *netdev)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_desc_if *desc_if = &pdata->desc_if;
+
+	DBGPR("-->xgbe_close\n");
+
+	/* Stop the device */
+	xgbe_stop(pdata);
+
+	/* Issue software reset to device */
+	hw_if->exit(pdata);
+
+	/* Free all the ring data */
+	desc_if->free_ring_resources(pdata);
+
+	/* Release the interrupt */
+	if (pdata->irq_number != 0) {
+		devm_free_irq(pdata->dev, pdata->irq_number, pdata);
+		pdata->irq_number = 0;
+	}
+
+	/* Disable the clock */
+	clk_disable_unprepare(pdata->sysclock);
+
+	DBGPR("<--xgbe_close\n");
+
+	return 0;
+}
+
+static int xgbe_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_desc_if *desc_if = &pdata->desc_if;
+	struct xgbe_channel *channel;
+	struct xgbe_ring *ring;
+	struct xgbe_packet_data *packet;
+	unsigned long flags;
+	int ret;
+
+	DBGPR("-->xgbe_xmit: skb->len = %d\n", skb->len);
+
+	channel = pdata->channel + skb->queue_mapping;
+	ring = channel->tx_ring;
+	packet = &ring->packet_data;
+
+	ret = NETDEV_TX_OK;
+
+	spin_lock_irqsave(&ring->lock, flags);
+
+	if (skb->len == 0) {
+		netdev_err(netdev, "empty skb received from stack\n");
+		dev_kfree_skb_any(skb);
+		goto tx_netdev_return;
+	}
+
+	/* Calculate preliminary packet info */
+	memset(packet, 0, sizeof(*packet));
+	xgbe_packet_info(ring, skb, packet);
+
+	/* Check that there are enough descriptors available */
+	if (packet->rdesc_count > xgbe_tx_avail_desc(ring)) {
+		DBGPR("  Tx queue stopped, not enough descriptors available\n");
+		netif_stop_subqueue(netdev, channel->queue_index);
+		ring->tx.queue_stopped = 1;
+		ret = NETDEV_TX_BUSY;
+		goto tx_netdev_return;
+	}
+
+	ret = xgbe_prep_tso(skb, packet);
+	if (ret) {
+		netdev_err(netdev, "error processing TSO packet\n");
+		dev_kfree_skb_any(skb);
+		goto tx_netdev_return;
+	}
+	xgbe_prep_vlan(skb, packet);
+
+	if (!desc_if->map_tx_skb(channel, skb)) {
+		dev_kfree_skb_any(skb);
+		goto tx_netdev_return;
+	}
+
+	/* Configure required descriptor fields for transmission */
+	hw_if->pre_xmit(channel);
+
+#ifdef XGMAC_ENABLE_TX_PKT_DUMP
+	xgbe_print_pkt(netdev, skb, true);
+#endif
+
+tx_netdev_return:
+	spin_unlock_irqrestore(&ring->lock, flags);
+
+	DBGPR("<--xgbe_xmit\n");
+
+	return ret;
+}
+
+static void xgbe_set_rx_mode(struct net_device *netdev)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	unsigned int pr_mode, am_mode;
+
+	DBGPR("-->xgbe_set_rx_mode\n");
+
+	pr_mode = ((netdev->flags & IFF_PROMISC) != 0);
+	am_mode = ((netdev->flags & IFF_ALLMULTI) != 0);
+
+	if (netdev_uc_count(netdev) > pdata->hw_feat.addn_mac)
+		pr_mode = 1;
+	if (netdev_mc_count(netdev) > pdata->hw_feat.addn_mac)
+		am_mode = 1;
+	if ((netdev_uc_count(netdev) + netdev_mc_count(netdev)) >
+	     pdata->hw_feat.addn_mac)
+		pr_mode = 1;
+
+	hw_if->set_promiscuous_mode(pdata, pr_mode);
+	hw_if->set_all_multicast_mode(pdata, am_mode);
+	if (!pr_mode)
+		hw_if->set_addn_mac_addrs(pdata, am_mode);
+
+	DBGPR("<--xgbe_set_rx_mode\n");
+}
+
+static int xgbe_set_mac_address(struct net_device *netdev, void *addr)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct sockaddr *saddr = addr;
+
+	DBGPR("-->xgbe_set_mac_address\n");
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(netdev->dev_addr, saddr->sa_data, netdev->addr_len);
+
+	hw_if->set_mac_address(pdata, netdev->dev_addr);
+
+	DBGPR("<--xgbe_set_mac_address\n");
+
+	return 0;
+}
+
+static int xgbe_change_mtu(struct net_device *netdev, int mtu)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	int ret;
+
+	DBGPR("-->xgbe_change_mtu\n");
+
+	ret = xgbe_calc_rx_buf_size(netdev, mtu);
+	if (ret < 0)
+		return ret;
+
+	pdata->rx_buf_size = ret;
+	netdev->mtu = mtu;
+
+	xgbe_restart_dev(pdata, 0);
+
+	DBGPR("<--xgbe_change_mtu\n");
+
+	return 0;
+}
+
+static struct rtnl_link_stats64 *xgbe_get_stats64(struct net_device *netdev,
+						  struct rtnl_link_stats64 *s)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_mmc_stats *pstats = &pdata->mmc_stats;
+
+	DBGPR("-->%s\n", __func__);
+
+	pdata->hw_if.read_mmc_stats(pdata);
+
+	s->rx_packets = pstats->rxframecount_gb;
+	s->rx_bytes = pstats->rxoctetcount_gb;
+	s->rx_errors = pstats->rxframecount_gb -
+		       pstats->rxbroadcastframes_g -
+		       pstats->rxmulticastframes_g -
+		       pstats->rxunicastframes_g;
+	s->multicast = pstats->rxmulticastframes_g;
+	s->rx_length_errors = pstats->rxlengtherror;
+	s->rx_crc_errors = pstats->rxcrcerror;
+	s->rx_fifo_errors = pstats->rxfifooverflow;
+
+	s->tx_packets = pstats->txframecount_gb;
+	s->tx_bytes = pstats->txoctetcount_gb;
+	s->tx_errors = pstats->txframecount_gb - pstats->txframecount_g;
+	s->tx_dropped = netdev->stats.tx_dropped;
+
+	DBGPR("<--%s\n", __func__);
+
+	return s;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void xgbe_poll_controller(struct net_device *netdev)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+
+	DBGPR("-->xgbe_poll_controller\n");
+
+	disable_irq(pdata->irq_number);
+
+	xgbe_isr(pdata->irq_number, pdata);
+
+	enable_irq(pdata->irq_number);
+
+	DBGPR("<--xgbe_poll_controller\n");
+}
+#endif /* End CONFIG_NET_POLL_CONTROLLER */
+
+static int xgbe_set_features(struct net_device *netdev,
+			     netdev_features_t features)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	unsigned int rxcsum_enabled, rxvlan_enabled;
+
+	rxcsum_enabled = !!(pdata->netdev_features & NETIF_F_RXCSUM);
+	rxvlan_enabled = !!(pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_RX);
+
+	if ((features & NETIF_F_RXCSUM) && !rxcsum_enabled) {
+		hw_if->enable_rx_csum(pdata);
+		netdev_alert(netdev, "state change - rxcsum enabled\n");
+	} else if (!(features & NETIF_F_RXCSUM) && rxcsum_enabled) {
+		hw_if->disable_rx_csum(pdata);
+		netdev_alert(netdev, "state change - rxcsum disabled\n");
+	}
+
+	if ((features & NETIF_F_HW_VLAN_CTAG_RX) && !rxvlan_enabled) {
+		hw_if->enable_rx_vlan_stripping(pdata);
+		netdev_alert(netdev, "state change - rxvlan enabled\n");
+	} else if (!(features & NETIF_F_HW_VLAN_CTAG_RX) && rxvlan_enabled) {
+		hw_if->disable_rx_vlan_stripping(pdata);
+		netdev_alert(netdev, "state change - rxvlan disabled\n");
+	}
+
+	pdata->netdev_features = features;
+
+	DBGPR("<--xgbe_set_features\n");
+
+	return 0;
+}
+
+static const struct net_device_ops xgbe_netdev_ops = {
+	.ndo_open		= xgbe_open,
+	.ndo_stop		= xgbe_close,
+	.ndo_start_xmit		= xgbe_xmit,
+	.ndo_set_rx_mode	= xgbe_set_rx_mode,
+	.ndo_set_mac_address	= xgbe_set_mac_address,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_mtu		= xgbe_change_mtu,
+	.ndo_get_stats64	= xgbe_get_stats64,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= xgbe_poll_controller,
+#endif
+	.ndo_set_features	= xgbe_set_features,
+};
+
+struct net_device_ops *xgbe_get_netdev_ops(void)
+{
+	return (struct net_device_ops *)&xgbe_netdev_ops;
+}
+
+static int xgbe_tx_poll(struct xgbe_channel *channel)
+{
+	struct xgbe_prv_data *pdata = channel->pdata;
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_desc_if *desc_if = &pdata->desc_if;
+	struct xgbe_ring *ring = channel->tx_ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_ring_desc *rdesc;
+	struct net_device *netdev = pdata->netdev;
+	unsigned long flags;
+	int processed = 0;
+
+	DBGPR("-->xgbe_tx_poll\n");
+
+	/* Nothing to do if there isn't a Tx ring for this channel */
+	if (!ring)
+		return 0;
+
+	spin_lock_irqsave(&ring->lock, flags);
+
+	while ((processed < TX_DESC_MAX_PROC) && (ring->dirty < ring->cur)) {
+		rdata = GET_DESC_DATA(ring, ring->dirty);
+		rdesc = rdata->rdesc;
+
+		if (!hw_if->tx_complete(rdesc))
+			break;
+
+#ifdef XGMAC_ENABLE_TX_DESC_DUMP
+		xgbe_dump_tx_desc(ring, ring->dirty, 1, 0);
+#endif
+
+		/* Free the SKB and reset the descriptor for re-use */
+		desc_if->unmap_skb(pdata, rdata);
+		hw_if->tx_desc_reset(rdata);
+
+		processed++;
+		ring->dirty++;
+	}
+
+	if ((ring->tx.queue_stopped == 1) &&
+	    (xgbe_tx_avail_desc(ring) > TX_DESC_MIN_FREE)) {
+		ring->tx.queue_stopped = 0;
+		netif_wake_subqueue(netdev, channel->queue_index);
+	}
+
+	DBGPR("<--xgbe_tx_poll: processed=%d\n", processed);
+
+	spin_unlock_irqrestore(&ring->lock, flags);
+
+	return processed;
+}
+
+static int xgbe_rx_poll(struct xgbe_channel *channel, int budget)
+{
+	struct xgbe_prv_data *pdata = channel->pdata;
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct xgbe_desc_if *desc_if = &pdata->desc_if;
+	struct xgbe_ring *ring = channel->rx_ring;
+	struct xgbe_ring_data *rdata;
+	struct xgbe_packet_data *packet;
+	struct net_device *netdev = pdata->netdev;
+	struct sk_buff *skb;
+	unsigned int incomplete, error;
+	unsigned int cur_len, put_len, max_len;
+	int received = 0;
+
+	DBGPR("-->xgbe_rx_poll: budget=%d\n", budget);
+
+	/* Nothing to do if there isn't a Rx ring for this channel */
+	if (!ring)
+		return 0;
+
+	packet = &ring->packet_data;
+	while (received < budget) {
+		DBGPR("  cur = %d\n", ring->cur);
+
+		/* Clear the packet data information */
+		memset(packet, 0, sizeof(*packet));
+		skb = NULL;
+		error = 0;
+		cur_len = 0;
+
+read_again:
+		rdata = GET_DESC_DATA(ring, ring->cur);
+
+		if (hw_if->dev_read(channel))
+			break;
+
+		received++;
+		ring->cur++;
+		ring->dirty++;
+
+		dma_unmap_single(pdata->dev, rdata->skb_dma,
+				 rdata->skb_dma_len, DMA_FROM_DEVICE);
+		rdata->skb_dma = 0;
+
+		incomplete = XGMAC_GET_BITS(packet->attributes,
+					    RX_PACKET_ATTRIBUTES,
+					    INCOMPLETE);
+
+		/* Earlier error, just drain the remaining data */
+		if (incomplete && error)
+			goto read_again;
+
+		if (error || packet->errors) {
+			if (packet->errors)
+				DBGPR("Error in received packet\n");
+			dev_kfree_skb(skb);
+			continue;
+		}
+
+		put_len = rdata->len - cur_len;
+		if (skb) {
+			if (pskb_expand_head(skb, 0, put_len, GFP_ATOMIC)) {
+				DBGPR("pskb_expand_head error\n");
+				if (incomplete) {
+					error = 1;
+					goto read_again;
+				}
+
+				dev_kfree_skb(skb);
+				continue;
+			}
+			memcpy(skb_tail_pointer(skb), rdata->skb->data,
+			       put_len);
+		} else {
+			skb = rdata->skb;
+			rdata->skb = NULL;
+		}
+		skb_put(skb, put_len);
+		cur_len += put_len;
+
+		if (incomplete)
+			goto read_again;
+
+		/* Be sure we don't exceed the configured MTU */
+		max_len = netdev->mtu + ETH_HLEN;
+		if (!(netdev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+		    (skb->protocol == htons(ETH_P_8021Q)))
+			max_len += VLAN_HLEN;
+
+		if (skb->len > max_len) {
+			DBGPR("packet length exceeds configured MTU\n");
+			dev_kfree_skb(skb);
+			continue;
+		}
+
+#ifdef XGMAC_ENABLE_RX_PKT_DUMP
+		xgbe_print_pkt(netdev, skb, false);
+#endif
+
+		skb_checksum_none_assert(skb);
+		if (XGMAC_GET_BITS(packet->attributes,
+				   RX_PACKET_ATTRIBUTES, CSUM_DONE))
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		if (XGMAC_GET_BITS(packet->attributes,
+				   RX_PACKET_ATTRIBUTES, VLAN_CTAG))
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+					       packet->vlan_ctag);
+
+		skb->dev = netdev;
+		skb->protocol = eth_type_trans(skb, netdev);
+		skb_record_rx_queue(skb, channel->queue_index);
+		skb_mark_napi_id(skb, &pdata->napi);
+
+		netdev->last_rx = jiffies;
+		napi_gro_receive(&pdata->napi, skb);
+	}
+
+	if (received) {
+		desc_if->realloc_skb(channel);
+
+		/* Update the Rx Tail Pointer Register with address of
+		 * the last cleaned entry */
+		rdata = GET_DESC_DATA(ring, ring->rx.realloc_index - 1);
+		XGMAC_DMA_IOWRITE(channel, DMA_CH_RDTR_LO,
+				  lower_32_bits(rdata->rdesc_dma));
+	}
+
+	DBGPR("<--xgbe_rx_poll: received = %d\n", received);
+
+	return received;
+}
+
+static int xgbe_poll(struct napi_struct *napi, int budget)
+{
+	struct xgbe_prv_data *pdata = container_of(napi, struct xgbe_prv_data,
+						   napi);
+	struct xgbe_channel *channel;
+	int processed;
+	unsigned int i;
+
+	DBGPR("-->xgbe_poll: budget=%d\n", budget);
+
+	/* Cleanup Tx ring first */
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++)
+		xgbe_tx_poll(channel);
+
+	/* Process Rx ring next */
+	processed = 0;
+	channel = pdata->channel;
+	for (i = 0; i < pdata->channel_count; i++, channel++)
+		processed += xgbe_rx_poll(channel, budget - processed);
+
+	/* If we processed everything, we are done */
+	if (processed < budget) {
+		/* Turn off polling */
+		napi_complete(napi);
+
+		/* Enable Tx and Rx interrupts */
+		xgbe_enable_rx_tx_ints(pdata);
+	}
+
+	DBGPR("<--xgbe_poll: received = %d\n", processed);
+
+	return processed;
+}
+
+void xgbe_dump_tx_desc(struct xgbe_ring *ring, unsigned int idx,
+		       unsigned int count, unsigned int flag)
+{
+	struct xgbe_ring_data *rdata;
+	struct xgbe_ring_desc *rdesc;
+
+	while (count--) {
+		rdata = GET_DESC_DATA(ring, idx);
+		rdesc = rdata->rdesc;
+		DBGPR("TX_NORMAL_DESC[%d %s] = %08x:%08x:%08x:%08x\n", idx,
+		      (flag == 1) ? "QUEUED FOR TX" : "TX BY DEVICE",
+		      le32_to_cpu(rdesc->desc0), le32_to_cpu(rdesc->desc1),
+		      le32_to_cpu(rdesc->desc2), le32_to_cpu(rdesc->desc3));
+		idx++;
+	}
+}
+
+void xgbe_dump_rx_desc(struct xgbe_ring *ring, struct xgbe_ring_desc *desc,
+		       unsigned int idx)
+{
+	DBGPR("RX_NORMAL_DESC[%d RX BY DEVICE] = %08x:%08x:%08x:%08x\n", idx,
+	      le32_to_cpu(desc->desc0), le32_to_cpu(desc->desc1),
+	      le32_to_cpu(desc->desc2), le32_to_cpu(desc->desc3));
+}
+
+void xgbe_print_pkt(struct net_device *netdev, struct sk_buff *skb, bool tx_rx)
+{
+	struct ethhdr *eth = (struct ethhdr *)skb->data;
+	unsigned char *buf = skb->data;
+	unsigned char buffer[128];
+	unsigned int i, j;
+
+	netdev_alert(netdev, "\n************** SKB dump ****************\n");
+
+	netdev_alert(netdev, "%s packet of %d bytes\n",
+		     (tx_rx ? "TX" : "RX"), skb->len);
+
+	netdev_alert(netdev, "Dst MAC addr: %pM\n", eth->h_dest);
+	netdev_alert(netdev, "Src MAC addr: %pM\n", eth->h_source);
+	netdev_alert(netdev, "Protocol: 0x%04hx\n", ntohs(eth->h_proto));
+
+	for (i = 0, j = 0; i < skb->len;) {
+		j += snprintf(buffer + j, sizeof(buffer) - j, "%02hhx",
+			      buf[i++]);
+
+		if ((i % 32) == 0) {
+			netdev_alert(netdev, "  0x%04x: %s\n", i - 32, buffer);
+			j = 0;
+		} else if ((i % 16) == 0) {
+			buffer[j++] = ' ';
+			buffer[j++] = ' ';
+		} else if ((i % 4) == 0) {
+			buffer[j++] = ' ';
+		}
+	}
+	if (i % 32)
+		netdev_alert(netdev, "  0x%04x: %s\n", i - (i % 32), buffer);
+
+	netdev_alert(netdev, "\n************** SKB dump ****************\n");
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
new file mode 100644
index 00000000000..8909f2b51af
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -0,0 +1,510 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/phy.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+
+struct xgbe_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int stat_size;
+	int stat_offset;
+};
+
+#define XGMAC_MMC_STAT(_string, _var)				\
+	{ _string,						\
+	  FIELD_SIZEOF(struct xgbe_mmc_stats, _var),		\
+	  offsetof(struct xgbe_prv_data, mmc_stats._var),	\
+	}
+
+static const struct xgbe_stats xgbe_gstring_stats[] = {
+	XGMAC_MMC_STAT("tx_bytes", txoctetcount_gb),
+	XGMAC_MMC_STAT("tx_packets", txframecount_gb),
+	XGMAC_MMC_STAT("tx_unicast_packets", txunicastframes_gb),
+	XGMAC_MMC_STAT("tx_broadcast_packets", txbroadcastframes_gb),
+	XGMAC_MMC_STAT("tx_multicast_packets", txmulticastframes_gb),
+	XGMAC_MMC_STAT("tx_vlan_packets", txvlanframes_g),
+	XGMAC_MMC_STAT("tx_64_byte_packets", tx64octets_gb),
+	XGMAC_MMC_STAT("tx_65_to_127_byte_packets", tx65to127octets_gb),
+	XGMAC_MMC_STAT("tx_128_to_255_byte_packets", tx128to255octets_gb),
+	XGMAC_MMC_STAT("tx_256_to_511_byte_packets", tx256to511octets_gb),
+	XGMAC_MMC_STAT("tx_512_to_1023_byte_packets", tx512to1023octets_gb),
+	XGMAC_MMC_STAT("tx_1024_to_max_byte_packets", tx1024tomaxoctets_gb),
+	XGMAC_MMC_STAT("tx_underflow_errors", txunderflowerror),
+	XGMAC_MMC_STAT("tx_pause_frames", txpauseframes),
+
+	XGMAC_MMC_STAT("rx_bytes", rxoctetcount_gb),
+	XGMAC_MMC_STAT("rx_packets", rxframecount_gb),
+	XGMAC_MMC_STAT("rx_unicast_packets", rxunicastframes_g),
+	XGMAC_MMC_STAT("rx_broadcast_packets", rxbroadcastframes_g),
+	XGMAC_MMC_STAT("rx_multicast_packets", rxmulticastframes_g),
+	XGMAC_MMC_STAT("rx_vlan_packets", rxvlanframes_gb),
+	XGMAC_MMC_STAT("rx_64_byte_packets", rx64octets_gb),
+	XGMAC_MMC_STAT("rx_65_to_127_byte_packets", rx65to127octets_gb),
+	XGMAC_MMC_STAT("rx_128_to_255_byte_packets", rx128to255octets_gb),
+	XGMAC_MMC_STAT("rx_256_to_511_byte_packets", rx256to511octets_gb),
+	XGMAC_MMC_STAT("rx_512_to_1023_byte_packets", rx512to1023octets_gb),
+	XGMAC_MMC_STAT("rx_1024_to_max_byte_packets", rx1024tomaxoctets_gb),
+	XGMAC_MMC_STAT("rx_undersize_packets", rxundersize_g),
+	XGMAC_MMC_STAT("rx_oversize_packets", rxoversize_g),
+	XGMAC_MMC_STAT("rx_crc_errors", rxcrcerror),
+	XGMAC_MMC_STAT("rx_crc_errors_small_packets", rxrunterror),
+	XGMAC_MMC_STAT("rx_crc_errors_giant_packets", rxjabbererror),
+	XGMAC_MMC_STAT("rx_length_errors", rxlengtherror),
+	XGMAC_MMC_STAT("rx_out_of_range_errors", rxoutofrangetype),
+	XGMAC_MMC_STAT("rx_fifo_overflow_errors", rxfifooverflow),
+	XGMAC_MMC_STAT("rx_watchdog_errors", rxwatchdogerror),
+	XGMAC_MMC_STAT("rx_pause_frames", rxpauseframes),
+};
+#define XGBE_STATS_COUNT	ARRAY_SIZE(xgbe_gstring_stats)
+
+static void xgbe_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+{
+	int i;
+
+	DBGPR("-->%s\n", __func__);
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < XGBE_STATS_COUNT; i++) {
+			memcpy(data, xgbe_gstring_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			data += ETH_GSTRING_LEN;
+		}
+		break;
+	}
+
+	DBGPR("<--%s\n", __func__);
+}
+
+static void xgbe_get_ethtool_stats(struct net_device *netdev,
+				   struct ethtool_stats *stats, u64 *data)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	u8 *stat;
+	int i;
+
+	DBGPR("-->%s\n", __func__);
+
+	pdata->hw_if.read_mmc_stats(pdata);
+	for (i = 0; i < XGBE_STATS_COUNT; i++) {
+		stat = (u8 *)pdata + xgbe_gstring_stats[i].stat_offset;
+		*data++ = *(u64 *)stat;
+	}
+
+	DBGPR("<--%s\n", __func__);
+}
+
+static int xgbe_get_sset_count(struct net_device *netdev, int stringset)
+{
+	int ret;
+
+	DBGPR("-->%s\n", __func__);
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		ret = XGBE_STATS_COUNT;
+		break;
+
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+	DBGPR("<--%s\n", __func__);
+
+	return ret;
+}
+
+static void xgbe_get_pauseparam(struct net_device *netdev,
+				struct ethtool_pauseparam *pause)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+
+	DBGPR("-->xgbe_get_pauseparam\n");
+
+	pause->autoneg = pdata->pause_autoneg;
+	pause->tx_pause = pdata->tx_pause;
+	pause->rx_pause = pdata->rx_pause;
+
+	DBGPR("<--xgbe_get_pauseparam\n");
+}
+
+static int xgbe_set_pauseparam(struct net_device *netdev,
+			       struct ethtool_pauseparam *pause)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct phy_device *phydev = pdata->phydev;
+	int ret = 0;
+
+	DBGPR("-->xgbe_set_pauseparam\n");
+
+	DBGPR("  autoneg = %d, tx_pause = %d, rx_pause = %d\n",
+	      pause->autoneg, pause->tx_pause, pause->rx_pause);
+
+	pdata->pause_autoneg = pause->autoneg;
+	if (pause->autoneg) {
+		phydev->advertising |= ADVERTISED_Pause;
+		phydev->advertising |= ADVERTISED_Asym_Pause;
+
+	} else {
+		phydev->advertising &= ~ADVERTISED_Pause;
+		phydev->advertising &= ~ADVERTISED_Asym_Pause;
+
+		pdata->tx_pause = pause->tx_pause;
+		pdata->rx_pause = pause->rx_pause;
+	}
+
+	if (netif_running(netdev))
+		ret = phy_start_aneg(phydev);
+
+	DBGPR("<--xgbe_set_pauseparam\n");
+
+	return ret;
+}
+
+static int xgbe_get_settings(struct net_device *netdev,
+			     struct ethtool_cmd *cmd)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	int ret;
+
+	DBGPR("-->xgbe_get_settings\n");
+
+	if (!pdata->phydev)
+		return -ENODEV;
+
+	spin_lock_irq(&pdata->lock);
+
+	ret = phy_ethtool_gset(pdata->phydev, cmd);
+	cmd->transceiver = XCVR_EXTERNAL;
+
+	spin_unlock_irq(&pdata->lock);
+
+	DBGPR("<--xgbe_get_settings\n");
+
+	return ret;
+}
+
+static int xgbe_set_settings(struct net_device *netdev,
+			     struct ethtool_cmd *cmd)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct phy_device *phydev = pdata->phydev;
+	u32 speed;
+	int ret;
+
+	DBGPR("-->xgbe_set_settings\n");
+
+	if (!pdata->phydev)
+		return -ENODEV;
+
+	spin_lock_irq(&pdata->lock);
+
+	speed = ethtool_cmd_speed(cmd);
+
+	ret = -EINVAL;
+	if (cmd->phy_address != phydev->addr)
+		goto unlock;
+
+	if ((cmd->autoneg != AUTONEG_ENABLE) &&
+	    (cmd->autoneg != AUTONEG_DISABLE))
+		goto unlock;
+
+	if ((cmd->autoneg == AUTONEG_DISABLE) &&
+	    (((speed != SPEED_10000) && (speed != SPEED_1000)) ||
+	     (cmd->duplex != DUPLEX_FULL)))
+		goto unlock;
+
+	if (cmd->autoneg == AUTONEG_ENABLE) {
+		/* Clear settings needed to force speeds */
+		phydev->supported &= ~SUPPORTED_1000baseT_Full;
+		phydev->supported &= ~SUPPORTED_10000baseT_Full;
+	} else {
+		/* Add settings needed to force speed */
+		phydev->supported |= SUPPORTED_1000baseT_Full;
+		phydev->supported |= SUPPORTED_10000baseT_Full;
+	}
+
+	cmd->advertising &= phydev->supported;
+	if ((cmd->autoneg == AUTONEG_ENABLE) && !cmd->advertising)
+		goto unlock;
+
+	ret = 0;
+	phydev->autoneg = cmd->autoneg;
+	phydev->speed = speed;
+	phydev->duplex = cmd->duplex;
+	phydev->advertising = cmd->advertising;
+
+	if (cmd->autoneg == AUTONEG_ENABLE)
+		phydev->advertising |= ADVERTISED_Autoneg;
+	else
+		phydev->advertising &= ~ADVERTISED_Autoneg;
+
+	if (netif_running(netdev))
+		ret = phy_start_aneg(phydev);
+
+unlock:
+	spin_unlock_irq(&pdata->lock);
+
+	DBGPR("<--xgbe_set_settings\n");
+
+	return ret;
+}
+
+static void xgbe_get_drvinfo(struct net_device *netdev,
+			     struct ethtool_drvinfo *drvinfo)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+
+	strlcpy(drvinfo->driver, XGBE_DRV_NAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, XGBE_DRV_VERSION, sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, dev_name(pdata->dev),
+		sizeof(drvinfo->bus_info));
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%d",
+		 XGMAC_IOREAD_BITS(pdata, MAC_VR, USERVER),
+		 XGMAC_IOREAD_BITS(pdata, MAC_VR, DEVID),
+		 XGMAC_IOREAD_BITS(pdata, MAC_VR, SNPSVER));
+	drvinfo->n_stats = XGBE_STATS_COUNT;
+}
+
+static int xgbe_get_coalesce(struct net_device *netdev,
+			     struct ethtool_coalesce *ec)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	unsigned int riwt;
+
+	DBGPR("-->xgbe_get_coalesce\n");
+
+	memset(ec, 0, sizeof(struct ethtool_coalesce));
+
+	riwt = pdata->rx_riwt;
+	ec->rx_coalesce_usecs = hw_if->riwt_to_usec(pdata, riwt);
+	ec->rx_max_coalesced_frames = pdata->rx_frames;
+
+	ec->tx_coalesce_usecs = pdata->tx_usecs;
+	ec->tx_max_coalesced_frames = pdata->tx_frames;
+
+	DBGPR("<--xgbe_get_coalesce\n");
+
+	return 0;
+}
+
+static int xgbe_set_coalesce(struct net_device *netdev,
+			     struct ethtool_coalesce *ec)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	unsigned int rx_frames, rx_riwt, rx_usecs;
+	unsigned int tx_frames, tx_usecs;
+
+	DBGPR("-->xgbe_set_coalesce\n");
+
+	/* Check for not supported parameters  */
+	if ((ec->rx_coalesce_usecs_irq) ||
+	    (ec->rx_max_coalesced_frames_irq) ||
+	    (ec->tx_coalesce_usecs_irq) ||
+	    (ec->tx_max_coalesced_frames_irq) ||
+	    (ec->stats_block_coalesce_usecs) ||
+	    (ec->use_adaptive_rx_coalesce) ||
+	    (ec->use_adaptive_tx_coalesce) ||
+	    (ec->pkt_rate_low) ||
+	    (ec->rx_coalesce_usecs_low) ||
+	    (ec->rx_max_coalesced_frames_low) ||
+	    (ec->tx_coalesce_usecs_low) ||
+	    (ec->tx_max_coalesced_frames_low) ||
+	    (ec->pkt_rate_high) ||
+	    (ec->rx_coalesce_usecs_high) ||
+	    (ec->rx_max_coalesced_frames_high) ||
+	    (ec->tx_coalesce_usecs_high) ||
+	    (ec->tx_max_coalesced_frames_high) ||
+	    (ec->rate_sample_interval))
+		return -EOPNOTSUPP;
+
+	/* Can only change rx-frames when interface is down (see
+	 * rx_descriptor_init in xgbe-dev.c)
+	 */
+	rx_frames = pdata->rx_frames;
+	if (rx_frames != ec->rx_max_coalesced_frames && netif_running(netdev)) {
+		netdev_alert(netdev,
+			     "interface must be down to change rx-frames\n");
+		return -EINVAL;
+	}
+
+	rx_riwt = hw_if->usec_to_riwt(pdata, ec->rx_coalesce_usecs);
+	rx_frames = ec->rx_max_coalesced_frames;
+
+	/* Use smallest possible value if conversion resulted in zero */
+	if (ec->rx_coalesce_usecs && !rx_riwt)
+		rx_riwt = 1;
+
+	/* Check the bounds of values for Rx */
+	if (rx_riwt > XGMAC_MAX_DMA_RIWT) {
+		rx_usecs = hw_if->riwt_to_usec(pdata, XGMAC_MAX_DMA_RIWT);
+		netdev_alert(netdev, "rx-usec is limited to %d usecs\n",
+			     rx_usecs);
+		return -EINVAL;
+	}
+	if (rx_frames > pdata->channel->rx_ring->rdesc_count) {
+		netdev_alert(netdev, "rx-frames is limited to %d frames\n",
+			     pdata->channel->rx_ring->rdesc_count);
+		return -EINVAL;
+	}
+
+	tx_usecs = ec->tx_coalesce_usecs;
+	tx_frames = ec->tx_max_coalesced_frames;
+
+	/* Check the bounds of values for Tx */
+	if (tx_frames > pdata->channel->tx_ring->rdesc_count) {
+		netdev_alert(netdev, "tx-frames is limited to %d frames\n",
+			     pdata->channel->tx_ring->rdesc_count);
+		return -EINVAL;
+	}
+
+	pdata->rx_riwt = rx_riwt;
+	pdata->rx_frames = rx_frames;
+	hw_if->config_rx_coalesce(pdata);
+
+	pdata->tx_usecs = tx_usecs;
+	pdata->tx_frames = tx_frames;
+	hw_if->config_tx_coalesce(pdata);
+
+	DBGPR("<--xgbe_set_coalesce\n");
+
+	return 0;
+}
+
+static const struct ethtool_ops xgbe_ethtool_ops = {
+	.get_settings = xgbe_get_settings,
+	.set_settings = xgbe_set_settings,
+	.get_drvinfo = xgbe_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+	.get_coalesce = xgbe_get_coalesce,
+	.set_coalesce = xgbe_set_coalesce,
+	.get_pauseparam = xgbe_get_pauseparam,
+	.set_pauseparam = xgbe_set_pauseparam,
+	.get_strings = xgbe_get_strings,
+	.get_ethtool_stats = xgbe_get_ethtool_stats,
+	.get_sset_count = xgbe_get_sset_count,
+};
+
+struct ethtool_ops *xgbe_get_ethtool_ops(void)
+{
+	return (struct ethtool_ops *)&xgbe_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
new file mode 100644
index 00000000000..5a1891faba8
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c
@@ -0,0 +1,513 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/clk.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+
+MODULE_AUTHOR("Tom Lendacky <thomas.lendacky@amd.com>");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(XGBE_DRV_VERSION);
+MODULE_DESCRIPTION(XGBE_DRV_DESC);
+
+static struct xgbe_channel *xgbe_alloc_rings(struct xgbe_prv_data *pdata)
+{
+	struct xgbe_channel *channel_mem, *channel;
+	struct xgbe_ring *tx_ring, *rx_ring;
+	unsigned int count, i;
+
+	DBGPR("-->xgbe_alloc_rings\n");
+
+	count = max_t(unsigned int, pdata->tx_ring_count, pdata->rx_ring_count);
+
+	channel_mem = devm_kcalloc(pdata->dev, count,
+				   sizeof(struct xgbe_channel), GFP_KERNEL);
+	if (!channel_mem)
+		return NULL;
+
+	tx_ring = devm_kcalloc(pdata->dev, pdata->tx_ring_count,
+			       sizeof(struct xgbe_ring), GFP_KERNEL);
+	if (!tx_ring)
+		return NULL;
+
+	rx_ring = devm_kcalloc(pdata->dev, pdata->rx_ring_count,
+			       sizeof(struct xgbe_ring), GFP_KERNEL);
+	if (!rx_ring)
+		return NULL;
+
+	for (i = 0, channel = channel_mem; i < count; i++, channel++) {
+		snprintf(channel->name, sizeof(channel->name), "channel-%d", i);
+		channel->pdata = pdata;
+		channel->queue_index = i;
+		channel->dma_regs = pdata->xgmac_regs + DMA_CH_BASE +
+				    (DMA_CH_INC * i);
+
+		if (i < pdata->tx_ring_count) {
+			spin_lock_init(&tx_ring->lock);
+			channel->tx_ring = tx_ring++;
+		}
+
+		if (i < pdata->rx_ring_count) {
+			spin_lock_init(&tx_ring->lock);
+			channel->rx_ring = rx_ring++;
+		}
+
+		DBGPR("  %s - queue_index=%u, dma_regs=%p, tx=%p, rx=%p\n",
+		      channel->name, channel->queue_index, channel->dma_regs,
+		      channel->tx_ring, channel->rx_ring);
+	}
+
+	pdata->channel_count = count;
+
+	DBGPR("<--xgbe_alloc_rings\n");
+
+	return channel_mem;
+}
+
+static void xgbe_default_config(struct xgbe_prv_data *pdata)
+{
+	DBGPR("-->xgbe_default_config\n");
+
+	pdata->pblx8 = DMA_PBL_X8_ENABLE;
+	pdata->tx_sf_mode = MTL_TSF_ENABLE;
+	pdata->tx_threshold = MTL_TX_THRESHOLD_64;
+	pdata->tx_pbl = DMA_PBL_16;
+	pdata->tx_osp_mode = DMA_OSP_ENABLE;
+	pdata->rx_sf_mode = MTL_RSF_DISABLE;
+	pdata->rx_threshold = MTL_RX_THRESHOLD_64;
+	pdata->rx_pbl = DMA_PBL_16;
+	pdata->pause_autoneg = 1;
+	pdata->tx_pause = 1;
+	pdata->rx_pause = 1;
+	pdata->power_down = 0;
+	pdata->default_autoneg = AUTONEG_ENABLE;
+	pdata->default_speed = SPEED_10000;
+
+	DBGPR("<--xgbe_default_config\n");
+}
+
+static void xgbe_init_all_fptrs(struct xgbe_prv_data *pdata)
+{
+	xgbe_init_function_ptrs_dev(&pdata->hw_if);
+	xgbe_init_function_ptrs_desc(&pdata->desc_if);
+}
+
+static int xgbe_probe(struct platform_device *pdev)
+{
+	struct xgbe_prv_data *pdata;
+	struct xgbe_hw_if *hw_if;
+	struct xgbe_desc_if *desc_if;
+	struct net_device *netdev;
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	const u8 *mac_addr;
+	int ret;
+
+	DBGPR("--> xgbe_probe\n");
+
+	netdev = alloc_etherdev_mq(sizeof(struct xgbe_prv_data),
+				   XGBE_MAX_DMA_CHANNELS);
+	if (!netdev) {
+		dev_err(dev, "alloc_etherdev failed\n");
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+	SET_NETDEV_DEV(netdev, dev);
+	pdata = netdev_priv(netdev);
+	pdata->netdev = netdev;
+	pdata->pdev = pdev;
+	pdata->dev = dev;
+	platform_set_drvdata(pdev, netdev);
+
+	spin_lock_init(&pdata->lock);
+	mutex_init(&pdata->xpcs_mutex);
+
+	/* Set and validate the number of descriptors for a ring */
+	BUILD_BUG_ON_NOT_POWER_OF_2(TX_DESC_CNT);
+	pdata->tx_desc_count = TX_DESC_CNT;
+	if (pdata->tx_desc_count & (pdata->tx_desc_count - 1)) {
+		dev_err(dev, "tx descriptor count (%d) is not valid\n",
+			pdata->tx_desc_count);
+		ret = -EINVAL;
+		goto err_io;
+	}
+	BUILD_BUG_ON_NOT_POWER_OF_2(RX_DESC_CNT);
+	pdata->rx_desc_count = RX_DESC_CNT;
+	if (pdata->rx_desc_count & (pdata->rx_desc_count - 1)) {
+		dev_err(dev, "rx descriptor count (%d) is not valid\n",
+			pdata->rx_desc_count);
+		ret = -EINVAL;
+		goto err_io;
+	}
+
+	/* Obtain the system clock setting */
+	pdata->sysclock = devm_clk_get(dev, NULL);
+	if (IS_ERR(pdata->sysclock)) {
+		dev_err(dev, "devm_clk_get failed\n");
+		ret = PTR_ERR(pdata->sysclock);
+		goto err_io;
+	}
+
+	/* Obtain the mmio areas for the device */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	pdata->xgmac_regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(pdata->xgmac_regs)) {
+		dev_err(dev, "xgmac ioremap failed\n");
+		ret = PTR_ERR(pdata->xgmac_regs);
+		goto err_io;
+	}
+	DBGPR("  xgmac_regs = %p\n", pdata->xgmac_regs);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	pdata->xpcs_regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(pdata->xpcs_regs)) {
+		dev_err(dev, "xpcs ioremap failed\n");
+		ret = PTR_ERR(pdata->xpcs_regs);
+		goto err_io;
+	}
+	DBGPR("  xpcs_regs  = %p\n", pdata->xpcs_regs);
+
+	/* Set the DMA mask */
+	if (!dev->dma_mask)
+		dev->dma_mask = &dev->coherent_dma_mask;
+	*(dev->dma_mask) = DMA_BIT_MASK(40);
+	dev->coherent_dma_mask = DMA_BIT_MASK(40);
+
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0) {
+		dev_err(dev, "platform_get_irq failed\n");
+		goto err_io;
+	}
+	netdev->irq = ret;
+	netdev->base_addr = (unsigned long)pdata->xgmac_regs;
+
+	/* Set all the function pointers */
+	xgbe_init_all_fptrs(pdata);
+	hw_if = &pdata->hw_if;
+	desc_if = &pdata->desc_if;
+
+	/* Issue software reset to device */
+	hw_if->exit(pdata);
+
+	/* Populate the hardware features */
+	xgbe_get_all_hw_features(pdata);
+
+	/* Retrieve the MAC address */
+	mac_addr = of_get_mac_address(dev->of_node);
+	if (!mac_addr) {
+		dev_err(dev, "invalid mac address for this device\n");
+		ret = -EINVAL;
+		goto err_io;
+	}
+	memcpy(netdev->dev_addr, mac_addr, netdev->addr_len);
+
+	/* Retrieve the PHY mode - it must be "xgmii" */
+	pdata->phy_mode = of_get_phy_mode(dev->of_node);
+	if (pdata->phy_mode != PHY_INTERFACE_MODE_XGMII) {
+		dev_err(dev, "invalid phy-mode specified for this device\n");
+		ret = -EINVAL;
+		goto err_io;
+	}
+
+	/* Set default configuration data */
+	xgbe_default_config(pdata);
+
+	/* Calculate the number of Tx and Rx rings to be created */
+	pdata->tx_ring_count = min_t(unsigned int, num_online_cpus(),
+				     pdata->hw_feat.tx_ch_cnt);
+	ret = netif_set_real_num_tx_queues(netdev, pdata->tx_ring_count);
+	if (ret) {
+		dev_err(dev, "error setting real tx queue count\n");
+		goto err_io;
+	}
+
+	pdata->rx_ring_count = min_t(unsigned int,
+				     netif_get_num_default_rss_queues(),
+				     pdata->hw_feat.rx_ch_cnt);
+	ret = netif_set_real_num_rx_queues(netdev, pdata->rx_ring_count);
+	if (ret) {
+		dev_err(dev, "error setting real rx queue count\n");
+		goto err_io;
+	}
+
+	/* Allocate the rings for the DMA channels */
+	pdata->channel = xgbe_alloc_rings(pdata);
+	if (!pdata->channel) {
+		dev_err(dev, "ring allocation failed\n");
+		ret = -ENOMEM;
+		goto err_io;
+	}
+
+	/* Prepare to regsiter with MDIO */
+	pdata->mii_bus_id = kasprintf(GFP_KERNEL, "%s", pdev->name);
+	if (!pdata->mii_bus_id) {
+		dev_err(dev, "failed to allocate mii bus id\n");
+		ret = -ENOMEM;
+		goto err_io;
+	}
+	ret = xgbe_mdio_register(pdata);
+	if (ret)
+		goto err_bus_id;
+
+	/* Set network and ethtool operations */
+	netdev->netdev_ops = xgbe_get_netdev_ops();
+	netdev->ethtool_ops = xgbe_get_ethtool_ops();
+
+	/* Set device features */
+	netdev->hw_features = NETIF_F_SG |
+			      NETIF_F_IP_CSUM |
+			      NETIF_F_IPV6_CSUM |
+			      NETIF_F_RXCSUM |
+			      NETIF_F_TSO |
+			      NETIF_F_TSO6 |
+			      NETIF_F_GRO |
+			      NETIF_F_HW_VLAN_CTAG_RX |
+			      NETIF_F_HW_VLAN_CTAG_TX;
+
+	netdev->vlan_features |= NETIF_F_SG |
+				 NETIF_F_IP_CSUM |
+				 NETIF_F_IPV6_CSUM |
+				 NETIF_F_TSO |
+				 NETIF_F_TSO6;
+
+	netdev->features |= netdev->hw_features;
+	pdata->netdev_features = netdev->features;
+
+	xgbe_init_rx_coalesce(pdata);
+	xgbe_init_tx_coalesce(pdata);
+
+	netif_carrier_off(netdev);
+	ret = register_netdev(netdev);
+	if (ret) {
+		dev_err(dev, "net device registration failed\n");
+		goto err_reg_netdev;
+	}
+
+	xgbe_debugfs_init(pdata);
+
+	netdev_notice(netdev, "net device enabled\n");
+
+	DBGPR("<-- xgbe_probe\n");
+
+	return 0;
+
+err_reg_netdev:
+	xgbe_mdio_unregister(pdata);
+
+err_bus_id:
+	kfree(pdata->mii_bus_id);
+
+err_io:
+	free_netdev(netdev);
+
+err_alloc:
+	dev_notice(dev, "net device not enabled\n");
+
+	return ret;
+}
+
+static int xgbe_remove(struct platform_device *pdev)
+{
+	struct net_device *netdev = platform_get_drvdata(pdev);
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+
+	DBGPR("-->xgbe_remove\n");
+
+	xgbe_debugfs_exit(pdata);
+
+	unregister_netdev(netdev);
+
+	xgbe_mdio_unregister(pdata);
+
+	kfree(pdata->mii_bus_id);
+
+	free_netdev(netdev);
+
+	DBGPR("<--xgbe_remove\n");
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int xgbe_suspend(struct device *dev)
+{
+	struct net_device *netdev = dev_get_drvdata(dev);
+	int ret;
+
+	DBGPR("-->xgbe_suspend\n");
+
+	if (!netif_running(netdev)) {
+		DBGPR("<--xgbe_dev_suspend\n");
+		return -EINVAL;
+	}
+
+	ret = xgbe_powerdown(netdev, XGMAC_DRIVER_CONTEXT);
+
+	DBGPR("<--xgbe_suspend\n");
+
+	return ret;
+}
+
+static int xgbe_resume(struct device *dev)
+{
+	struct net_device *netdev = dev_get_drvdata(dev);
+	int ret;
+
+	DBGPR("-->xgbe_resume\n");
+
+	if (!netif_running(netdev)) {
+		DBGPR("<--xgbe_dev_resume\n");
+		return -EINVAL;
+	}
+
+	ret = xgbe_powerup(netdev, XGMAC_DRIVER_CONTEXT);
+
+	DBGPR("<--xgbe_resume\n");
+
+	return ret;
+}
+#endif /* CONFIG_PM */
+
+static const struct of_device_id xgbe_of_match[] = {
+	{ .compatible = "amd,xgbe-seattle-v1a", },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, xgbe_of_match);
+static SIMPLE_DEV_PM_OPS(xgbe_pm_ops, xgbe_suspend, xgbe_resume);
+
+static struct platform_driver xgbe_driver = {
+	.driver = {
+		.name = "amd-xgbe",
+		.of_match_table = xgbe_of_match,
+		.pm = &xgbe_pm_ops,
+	},
+	.probe = xgbe_probe,
+	.remove = xgbe_remove,
+};
+
+module_platform_driver(xgbe_driver);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
new file mode 100644
index 00000000000..ea7a5d6750e
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -0,0 +1,433 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/kmod.h>
+#include <linux/spinlock.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
+#include <linux/of.h>
+
+#include "xgbe.h"
+#include "xgbe-common.h"
+
+
+static int xgbe_mdio_read(struct mii_bus *mii, int prtad, int mmd_reg)
+{
+	struct xgbe_prv_data *pdata = mii->priv;
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	int mmd_data;
+
+	DBGPR_MDIO("-->xgbe_mdio_read: prtad=%#x mmd_reg=%#x\n",
+		   prtad, mmd_reg);
+
+	mmd_data = hw_if->read_mmd_regs(pdata, prtad, mmd_reg);
+
+	DBGPR_MDIO("<--xgbe_mdio_read: mmd_data=%#x\n", mmd_data);
+
+	return mmd_data;
+}
+
+static int xgbe_mdio_write(struct mii_bus *mii, int prtad, int mmd_reg,
+			   u16 mmd_val)
+{
+	struct xgbe_prv_data *pdata = mii->priv;
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	int mmd_data = mmd_val;
+
+	DBGPR_MDIO("-->xgbe_mdio_write: prtad=%#x mmd_reg=%#x mmd_data=%#x\n",
+		   prtad, mmd_reg, mmd_data);
+
+	hw_if->write_mmd_regs(pdata, prtad, mmd_reg, mmd_data);
+
+	DBGPR_MDIO("<--xgbe_mdio_write\n");
+
+	return 0;
+}
+
+static void xgbe_adjust_link(struct net_device *netdev)
+{
+	struct xgbe_prv_data *pdata = netdev_priv(netdev);
+	struct xgbe_hw_if *hw_if = &pdata->hw_if;
+	struct phy_device *phydev = pdata->phydev;
+	unsigned long flags;
+	int new_state = 0;
+
+	if (phydev == NULL)
+		return;
+
+	DBGPR_MDIO("-->xgbe_adjust_link: address=%d, newlink=%d, curlink=%d\n",
+		   phydev->addr, phydev->link, pdata->phy_link);
+
+	spin_lock_irqsave(&pdata->lock, flags);
+
+	if (phydev->link) {
+		/* Flow control support */
+		if (pdata->pause_autoneg) {
+			if (phydev->pause || phydev->asym_pause) {
+				pdata->tx_pause = 1;
+				pdata->rx_pause = 1;
+			} else {
+				pdata->tx_pause = 0;
+				pdata->rx_pause = 0;
+			}
+		}
+
+		if (pdata->tx_pause != pdata->phy_tx_pause) {
+			hw_if->config_tx_flow_control(pdata);
+			pdata->phy_tx_pause = pdata->tx_pause;
+		}
+
+		if (pdata->rx_pause != pdata->phy_rx_pause) {
+			hw_if->config_rx_flow_control(pdata);
+			pdata->phy_rx_pause = pdata->rx_pause;
+		}
+
+		/* Speed support */
+		if (phydev->speed != pdata->phy_speed) {
+			new_state = 1;
+
+			switch (phydev->speed) {
+			case SPEED_10000:
+				hw_if->set_xgmii_speed(pdata);
+				break;
+
+			case SPEED_2500:
+				hw_if->set_gmii_2500_speed(pdata);
+				break;
+
+			case SPEED_1000:
+				hw_if->set_gmii_speed(pdata);
+				break;
+			}
+			pdata->phy_speed = phydev->speed;
+		}
+
+		if (phydev->link != pdata->phy_link) {
+			new_state = 1;
+			pdata->phy_link = 1;
+		}
+	} else if (pdata->phy_link) {
+		new_state = 1;
+		pdata->phy_link = 0;
+		pdata->phy_speed = SPEED_UNKNOWN;
+	}
+
+	if (new_state)
+		phy_print_status(phydev);
+
+	spin_unlock_irqrestore(&pdata->lock, flags);
+
+	DBGPR_MDIO("<--xgbe_adjust_link\n");
+}
+
+void xgbe_dump_phy_registers(struct xgbe_prv_data *pdata)
+{
+	struct device *dev = pdata->dev;
+	struct phy_device *phydev = pdata->mii->phy_map[XGBE_PRTAD];
+	int i;
+
+	dev_alert(dev, "\n************* PHY Reg dump **********************\n");
+
+	dev_alert(dev, "PCS Control Reg (%#04x) = %#04x\n", MDIO_CTRL1,
+		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_CTRL1));
+	dev_alert(dev, "PCS Status Reg (%#04x) = %#04x\n", MDIO_STAT1,
+		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1));
+	dev_alert(dev, "Phy Id (PHYS ID 1 %#04x)= %#04x\n", MDIO_DEVID1,
+		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVID1));
+	dev_alert(dev, "Phy Id (PHYS ID 2 %#04x)= %#04x\n", MDIO_DEVID2,
+		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVID2));
+	dev_alert(dev, "Devices in Package (%#04x)= %#04x\n", MDIO_DEVS1,
+		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVS1));
+	dev_alert(dev, "Devices in Package (%#04x)= %#04x\n", MDIO_DEVS2,
+		  XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_DEVS2));
+
+	dev_alert(dev, "Auto-Neg Control Reg (%#04x) = %#04x\n", MDIO_CTRL1,
+		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1));
+	dev_alert(dev, "Auto-Neg Status Reg (%#04x) = %#04x\n", MDIO_STAT1,
+		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_STAT1));
+	dev_alert(dev, "Auto-Neg Ad Reg 1 (%#04x) = %#04x\n",
+		  MDIO_AN_ADVERTISE,
+		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE));
+	dev_alert(dev, "Auto-Neg Ad Reg 2 (%#04x) = %#04x\n",
+		  MDIO_AN_ADVERTISE + 1,
+		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1));
+	dev_alert(dev, "Auto-Neg Ad Reg 3 (%#04x) = %#04x\n",
+		  MDIO_AN_ADVERTISE + 2,
+		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2));
+	dev_alert(dev, "Auto-Neg Completion Reg (%#04x) = %#04x\n",
+		  MDIO_AN_COMP_STAT,
+		  XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_COMP_STAT));
+
+	dev_alert(dev, "MMD Device Mask = %#x\n",
+		  phydev->c45_ids.devices_in_package);
+	for (i = 0; i < ARRAY_SIZE(phydev->c45_ids.device_ids); i++)
+		dev_alert(dev, "  MMD %d: ID = %#08x\n", i,
+			  phydev->c45_ids.device_ids[i]);
+
+	dev_alert(dev, "\n*************************************************\n");
+}
+
+int xgbe_mdio_register(struct xgbe_prv_data *pdata)
+{
+	struct net_device *netdev = pdata->netdev;
+	struct device_node *phy_node;
+	struct mii_bus *mii;
+	struct phy_device *phydev;
+	int ret = 0;
+
+	DBGPR("-->xgbe_mdio_register\n");
+
+	/* Retrieve the phy-handle */
+	phy_node = of_parse_phandle(pdata->dev->of_node, "phy-handle", 0);
+	if (!phy_node) {
+		dev_err(pdata->dev, "unable to parse phy-handle\n");
+		return -EINVAL;
+	}
+
+	/* Register with the MDIO bus */
+	mii = mdiobus_alloc();
+	if (mii == NULL) {
+		dev_err(pdata->dev, "mdiobus_alloc failed\n");
+		ret = -ENOMEM;
+		goto err_node_get;
+	}
+
+	/* Register on the MDIO bus (don't probe any PHYs) */
+	mii->name = XGBE_PHY_NAME;
+	mii->read = xgbe_mdio_read;
+	mii->write = xgbe_mdio_write;
+	snprintf(mii->id, sizeof(mii->id), "%s", pdata->mii_bus_id);
+	mii->priv = pdata;
+	mii->phy_mask = ~0;
+	mii->parent = pdata->dev;
+	ret = mdiobus_register(mii);
+	if (ret) {
+		dev_err(pdata->dev, "mdiobus_register failed\n");
+		goto err_mdiobus_alloc;
+	}
+	DBGPR("  mdiobus_register succeeded for %s\n", pdata->mii_bus_id);
+
+	/* Probe the PCS using Clause 45 */
+	phydev = get_phy_device(mii, XGBE_PRTAD, true);
+	if (IS_ERR(phydev) || !phydev ||
+	    !phydev->c45_ids.device_ids[MDIO_MMD_PCS]) {
+		dev_err(pdata->dev, "get_phy_device failed\n");
+		ret = phydev ? PTR_ERR(phydev) : -ENOLINK;
+		goto err_mdiobus_register;
+	}
+	request_module(MDIO_MODULE_PREFIX MDIO_ID_FMT,
+		       MDIO_ID_ARGS(phydev->c45_ids.device_ids[MDIO_MMD_PCS]));
+
+	of_node_get(phy_node);
+	phydev->dev.of_node = phy_node;
+	ret = phy_device_register(phydev);
+	if (ret) {
+		dev_err(pdata->dev, "phy_device_register failed\n");
+		of_node_put(phy_node);
+		goto err_phy_device;
+	}
+
+	/* Add a reference to the PHY driver so it can't be unloaded */
+	pdata->phy_module = phydev->dev.driver ?
+			    phydev->dev.driver->owner : NULL;
+	if (!try_module_get(pdata->phy_module)) {
+		dev_err(pdata->dev, "try_module_get failed\n");
+		ret = -EIO;
+		goto err_phy_device;
+	}
+
+	pdata->mii = mii;
+	pdata->mdio_mmd = MDIO_MMD_PCS;
+
+	pdata->phy_link = -1;
+	pdata->phy_speed = SPEED_UNKNOWN;
+	pdata->phy_tx_pause = pdata->tx_pause;
+	pdata->phy_rx_pause = pdata->rx_pause;
+
+	ret = phy_connect_direct(netdev, phydev, &xgbe_adjust_link,
+				 pdata->phy_mode);
+	if (ret) {
+		netdev_err(netdev, "phy_connect_direct failed\n");
+		goto err_phy_device;
+	}
+
+	if (!phydev->drv || (phydev->drv->phy_id == 0)) {
+		netdev_err(netdev, "phy_id not valid\n");
+		ret = -ENODEV;
+		goto err_phy_connect;
+	}
+	DBGPR("  phy_connect_direct succeeded for PHY %s, link=%d\n",
+	      dev_name(&phydev->dev), phydev->link);
+
+	phydev->autoneg = pdata->default_autoneg;
+	if (phydev->autoneg == AUTONEG_DISABLE) {
+		/* Add settings needed to force speed */
+		phydev->supported |= SUPPORTED_1000baseT_Full;
+		phydev->supported |= SUPPORTED_10000baseT_Full;
+
+		phydev->speed = pdata->default_speed;
+		phydev->duplex = DUPLEX_FULL;
+
+		phydev->advertising &= ~ADVERTISED_Autoneg;
+	}
+
+	pdata->phydev = phydev;
+
+	of_node_put(phy_node);
+
+	DBGPHY_REGS(pdata);
+
+	DBGPR("<--xgbe_mdio_register\n");
+
+	return 0;
+
+err_phy_connect:
+	phy_disconnect(phydev);
+
+err_phy_device:
+	phy_device_free(phydev);
+
+err_mdiobus_register:
+	mdiobus_unregister(mii);
+
+err_mdiobus_alloc:
+	mdiobus_free(mii);
+
+err_node_get:
+	of_node_put(phy_node);
+
+	return ret;
+}
+
+void xgbe_mdio_unregister(struct xgbe_prv_data *pdata)
+{
+	DBGPR("-->xgbe_mdio_unregister\n");
+
+	phy_disconnect(pdata->phydev);
+	pdata->phydev = NULL;
+
+	module_put(pdata->phy_module);
+	pdata->phy_module = NULL;
+
+	mdiobus_unregister(pdata->mii);
+	pdata->mii->priv = NULL;
+
+	mdiobus_free(pdata->mii);
+	pdata->mii = NULL;
+
+	DBGPR("<--xgbe_mdio_unregister\n");
+}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
new file mode 100644
index 00000000000..ab0627162c0
--- /dev/null
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -0,0 +1,676 @@
+/*
+ * AMD 10Gb Ethernet driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * This file incorporates work covered by the following copyright and
+ * permission notice:
+ *     The Synopsys DWC ETHER XGMAC Software Driver and documentation
+ *     (hereinafter "Software") is an unsupported proprietary work of Synopsys,
+ *     Inc. unless otherwise expressly agreed to in writing between Synopsys
+ *     and you.
+ *
+ *     The Software IS NOT an item of Licensed Software or Licensed Product
+ *     under any End User Software License Agreement or Agreement for Licensed
+ *     Product with Synopsys or any supplement thereto.  Permission is hereby
+ *     granted, free of charge, to any person obtaining a copy of this software
+ *     annotated with this license and the Software, to deal in the Software
+ *     without restriction, including without limitation the rights to use,
+ *     copy, modify, merge, publish, distribute, sublicense, and/or sell copies
+ *     of the Software, and to permit persons to whom the Software is furnished
+ *     to do so, subject to the following conditions:
+ *
+ *     The above copyright notice and this permission notice shall be included
+ *     in all copies or substantial portions of the Software.
+ *
+ *     THIS SOFTWARE IS BEING DISTRIBUTED BY SYNOPSYS SOLELY ON AN "AS IS"
+ *     BASIS AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
+ *     TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ *     PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. IN NO EVENT SHALL SYNOPSYS
+ *     BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *     CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *     SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ *     INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ *     CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ *     ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+ *     THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __XGBE_H__
+#define __XGBE_H__
+
+#include <linux/dma-mapping.h>
+#include <linux/netdevice.h>
+#include <linux/workqueue.h>
+#include <linux/phy.h>
+
+
+#define XGBE_DRV_NAME		"amd-xgbe"
+#define XGBE_DRV_VERSION	"1.0.0-a"
+#define XGBE_DRV_DESC		"AMD 10 Gigabit Ethernet Driver"
+
+/* Descriptor related defines */
+#define TX_DESC_CNT		512
+#define TX_DESC_MIN_FREE	(TX_DESC_CNT >> 3)
+#define TX_DESC_MAX_PROC	(TX_DESC_CNT >> 1)
+#define RX_DESC_CNT		512
+
+#define TX_MAX_BUF_SIZE		(0x3fff & ~(64 - 1))
+
+#define RX_MIN_BUF_SIZE		(ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN)
+#define RX_BUF_ALIGN		64
+
+#define XGBE_MAX_DMA_CHANNELS	16
+#define DMA_ARDOMAIN_SETTING	0x2
+#define DMA_ARCACHE_SETTING	0xb
+#define DMA_AWDOMAIN_SETTING	0x2
+#define DMA_AWCACHE_SETTING	0x7
+#define DMA_INTERRUPT_MASK	0x31c7
+
+#define XGMAC_MIN_PACKET	60
+#define XGMAC_STD_PACKET_MTU	1500
+#define XGMAC_MAX_STD_PACKET	1518
+#define XGMAC_JUMBO_PACKET_MTU	9000
+#define XGMAC_MAX_JUMBO_PACKET	9018
+
+#define MAX_MULTICAST_LIST	14
+#define TX_FLAGS_IP_PKT		0x00000001
+#define TX_FLAGS_TCP_PKT	0x00000002
+
+/* MDIO bus phy name */
+#define XGBE_PHY_NAME		"amd_xgbe_phy"
+#define XGBE_PRTAD		0
+
+/* Driver PMT macros */
+#define XGMAC_DRIVER_CONTEXT	1
+#define XGMAC_IOCTL_CONTEXT	2
+
+#define FIFO_SIZE_B(x)		(x)
+#define FIFO_SIZE_KB(x)		(x * 1024)
+
+#define XGBE_TC_CNT		2
+
+/* Helper macro for descriptor handling
+ *  Always use GET_DESC_DATA to access the descriptor data
+ *  since the index is free-running and needs to be and-ed
+ *  with the descriptor count value of the ring to index to
+ *  the proper descriptor data.
+ */
+#define GET_DESC_DATA(_ring, _idx)				\
+	((_ring)->rdata +					\
+	 ((_idx) & ((_ring)->rdesc_count - 1)))
+
+
+/* Default coalescing parameters */
+#define XGMAC_INIT_DMA_TX_USECS		100
+#define XGMAC_INIT_DMA_TX_FRAMES	16
+
+#define XGMAC_MAX_DMA_RIWT		0xff
+#define XGMAC_INIT_DMA_RX_USECS		100
+#define XGMAC_INIT_DMA_RX_FRAMES	16
+
+/* Flow control queue count */
+#define XGMAC_MAX_FLOW_CONTROL_QUEUES	8
+
+
+struct xgbe_prv_data;
+
+struct xgbe_packet_data {
+	unsigned int attributes;
+
+	unsigned int errors;
+
+	unsigned int rdesc_count;
+	unsigned int length;
+
+	unsigned int header_len;
+	unsigned int tcp_header_len;
+	unsigned int tcp_payload_len;
+	unsigned short mss;
+
+	unsigned short vlan_ctag;
+};
+
+/* Common Rx and Tx descriptor mapping */
+struct xgbe_ring_desc {
+	unsigned int desc0;
+	unsigned int desc1;
+	unsigned int desc2;
+	unsigned int desc3;
+};
+
+/* Structure used to hold information related to the descriptor
+ * and the packet associated with the descriptor (always use
+ * use the GET_DESC_DATA macro to access this data from the ring)
+ */
+struct xgbe_ring_data {
+	struct xgbe_ring_desc *rdesc;	/* Virtual address of descriptor */
+	dma_addr_t rdesc_dma;		/* DMA address of descriptor */
+
+	struct sk_buff *skb;		/* Virtual address of SKB */
+	dma_addr_t skb_dma;		/* DMA address of SKB data */
+	unsigned int skb_dma_len;	/* Length of SKB DMA area */
+	unsigned int tso_header;        /* TSO header indicator */
+
+	unsigned short len;		/* Length of received Rx packet */
+
+	unsigned int interrupt;		/* Interrupt indicator */
+
+	unsigned int mapped_as_page;
+};
+
+struct xgbe_ring {
+	/* Ring lock - used just for TX rings at the moment */
+	spinlock_t lock;
+
+	/* Per packet related information */
+	struct xgbe_packet_data packet_data;
+
+	/* Virtual/DMA addresses and count of allocated descriptor memory */
+	struct xgbe_ring_desc *rdesc;
+	dma_addr_t rdesc_dma;
+	unsigned int rdesc_count;
+
+	/* Array of descriptor data corresponding the descriptor memory
+	 * (always use the GET_DESC_DATA macro to access this data)
+	 */
+	struct xgbe_ring_data *rdata;
+
+	/* Ring index values
+	 *  cur   - Tx: index of descriptor to be used for current transfer
+	 *          Rx: index of descriptor to check for packet availability
+	 *  dirty - Tx: index of descriptor to check for transfer complete
+	 *          Rx: count of descriptors in which a packet has been received
+	 *              (used with skb_realloc_index to refresh the ring)
+	 */
+	unsigned int cur;
+	unsigned int dirty;
+
+	/* Coalesce frame count used for interrupt bit setting */
+	unsigned int coalesce_count;
+
+	union {
+		struct {
+			unsigned int queue_stopped;
+			unsigned short cur_mss;
+			unsigned short cur_vlan_ctag;
+		} tx;
+
+		struct {
+			unsigned int realloc_index;
+			unsigned int realloc_threshold;
+		} rx;
+	};
+} ____cacheline_aligned;
+
+/* Structure used to describe the descriptor rings associated with
+ * a DMA channel.
+ */
+struct xgbe_channel {
+	char name[16];
+
+	/* Address of private data area for device */
+	struct xgbe_prv_data *pdata;
+
+	/* Queue index and base address of queue's DMA registers */
+	unsigned int queue_index;
+	void __iomem *dma_regs;
+
+	unsigned int saved_ier;
+
+	unsigned int tx_timer_active;
+	struct hrtimer tx_timer;
+
+	struct xgbe_ring *tx_ring;
+	struct xgbe_ring *rx_ring;
+} ____cacheline_aligned;
+
+enum xgbe_int {
+	XGMAC_INT_DMA_ISR_DC0IS,
+	XGMAC_INT_DMA_CH_SR_TI,
+	XGMAC_INT_DMA_CH_SR_TPS,
+	XGMAC_INT_DMA_CH_SR_TBU,
+	XGMAC_INT_DMA_CH_SR_RI,
+	XGMAC_INT_DMA_CH_SR_RBU,
+	XGMAC_INT_DMA_CH_SR_RPS,
+	XGMAC_INT_DMA_CH_SR_FBE,
+	XGMAC_INT_DMA_ALL,
+};
+
+enum xgbe_int_state {
+	XGMAC_INT_STATE_SAVE,
+	XGMAC_INT_STATE_RESTORE,
+};
+
+enum xgbe_mtl_fifo_size {
+	XGMAC_MTL_FIFO_SIZE_256  = 0x00,
+	XGMAC_MTL_FIFO_SIZE_512  = 0x01,
+	XGMAC_MTL_FIFO_SIZE_1K   = 0x03,
+	XGMAC_MTL_FIFO_SIZE_2K   = 0x07,
+	XGMAC_MTL_FIFO_SIZE_4K   = 0x0f,
+	XGMAC_MTL_FIFO_SIZE_8K   = 0x1f,
+	XGMAC_MTL_FIFO_SIZE_16K  = 0x3f,
+	XGMAC_MTL_FIFO_SIZE_32K  = 0x7f,
+	XGMAC_MTL_FIFO_SIZE_64K  = 0xff,
+	XGMAC_MTL_FIFO_SIZE_128K = 0x1ff,
+	XGMAC_MTL_FIFO_SIZE_256K = 0x3ff,
+};
+
+struct xgbe_mmc_stats {
+	/* Tx Stats */
+	u64 txoctetcount_gb;
+	u64 txframecount_gb;
+	u64 txbroadcastframes_g;
+	u64 txmulticastframes_g;
+	u64 tx64octets_gb;
+	u64 tx65to127octets_gb;
+	u64 tx128to255octets_gb;
+	u64 tx256to511octets_gb;
+	u64 tx512to1023octets_gb;
+	u64 tx1024tomaxoctets_gb;
+	u64 txunicastframes_gb;
+	u64 txmulticastframes_gb;
+	u64 txbroadcastframes_gb;
+	u64 txunderflowerror;
+	u64 txoctetcount_g;
+	u64 txframecount_g;
+	u64 txpauseframes;
+	u64 txvlanframes_g;
+
+	/* Rx Stats */
+	u64 rxframecount_gb;
+	u64 rxoctetcount_gb;
+	u64 rxoctetcount_g;
+	u64 rxbroadcastframes_g;
+	u64 rxmulticastframes_g;
+	u64 rxcrcerror;
+	u64 rxrunterror;
+	u64 rxjabbererror;
+	u64 rxundersize_g;
+	u64 rxoversize_g;
+	u64 rx64octets_gb;
+	u64 rx65to127octets_gb;
+	u64 rx128to255octets_gb;
+	u64 rx256to511octets_gb;
+	u64 rx512to1023octets_gb;
+	u64 rx1024tomaxoctets_gb;
+	u64 rxunicastframes_g;
+	u64 rxlengtherror;
+	u64 rxoutofrangetype;
+	u64 rxpauseframes;
+	u64 rxfifooverflow;
+	u64 rxvlanframes_gb;
+	u64 rxwatchdogerror;
+};
+
+struct xgbe_hw_if {
+	int (*tx_complete)(struct xgbe_ring_desc *);
+
+	int (*set_promiscuous_mode)(struct xgbe_prv_data *, unsigned int);
+	int (*set_all_multicast_mode)(struct xgbe_prv_data *, unsigned int);
+	int (*set_addn_mac_addrs)(struct xgbe_prv_data *, unsigned int);
+	int (*set_mac_address)(struct xgbe_prv_data *, u8 *addr);
+
+	int (*enable_rx_csum)(struct xgbe_prv_data *);
+	int (*disable_rx_csum)(struct xgbe_prv_data *);
+
+	int (*enable_rx_vlan_stripping)(struct xgbe_prv_data *);
+	int (*disable_rx_vlan_stripping)(struct xgbe_prv_data *);
+
+	int (*read_mmd_regs)(struct xgbe_prv_data *, int, int);
+	void (*write_mmd_regs)(struct xgbe_prv_data *, int, int, int);
+	int (*set_gmii_speed)(struct xgbe_prv_data *);
+	int (*set_gmii_2500_speed)(struct xgbe_prv_data *);
+	int (*set_xgmii_speed)(struct xgbe_prv_data *);
+
+	void (*enable_tx)(struct xgbe_prv_data *);
+	void (*disable_tx)(struct xgbe_prv_data *);
+	void (*enable_rx)(struct xgbe_prv_data *);
+	void (*disable_rx)(struct xgbe_prv_data *);
+
+	void (*powerup_tx)(struct xgbe_prv_data *);
+	void (*powerdown_tx)(struct xgbe_prv_data *);
+	void (*powerup_rx)(struct xgbe_prv_data *);
+	void (*powerdown_rx)(struct xgbe_prv_data *);
+
+	int (*init)(struct xgbe_prv_data *);
+	int (*exit)(struct xgbe_prv_data *);
+
+	int (*enable_int)(struct xgbe_channel *, enum xgbe_int);
+	int (*disable_int)(struct xgbe_channel *, enum xgbe_int);
+	void (*pre_xmit)(struct xgbe_channel *);
+	int (*dev_read)(struct xgbe_channel *);
+	void (*tx_desc_init)(struct xgbe_channel *);
+	void (*rx_desc_init)(struct xgbe_channel *);
+	void (*rx_desc_reset)(struct xgbe_ring_data *);
+	void (*tx_desc_reset)(struct xgbe_ring_data *);
+	int (*is_last_desc)(struct xgbe_ring_desc *);
+	int (*is_context_desc)(struct xgbe_ring_desc *);
+
+	/* For FLOW ctrl */
+	int (*config_tx_flow_control)(struct xgbe_prv_data *);
+	int (*config_rx_flow_control)(struct xgbe_prv_data *);
+
+	/* For RX coalescing */
+	int (*config_rx_coalesce)(struct xgbe_prv_data *);
+	int (*config_tx_coalesce)(struct xgbe_prv_data *);
+	unsigned int (*usec_to_riwt)(struct xgbe_prv_data *, unsigned int);
+	unsigned int (*riwt_to_usec)(struct xgbe_prv_data *, unsigned int);
+
+	/* For RX and TX threshold config */
+	int (*config_rx_threshold)(struct xgbe_prv_data *, unsigned int);
+	int (*config_tx_threshold)(struct xgbe_prv_data *, unsigned int);
+
+	/* For RX and TX Store and Forward Mode config */
+	int (*config_rsf_mode)(struct xgbe_prv_data *, unsigned int);
+	int (*config_tsf_mode)(struct xgbe_prv_data *, unsigned int);
+
+	/* For TX DMA Operate on Second Frame config */
+	int (*config_osp_mode)(struct xgbe_prv_data *);
+
+	/* For RX and TX PBL config */
+	int (*config_rx_pbl_val)(struct xgbe_prv_data *);
+	int (*get_rx_pbl_val)(struct xgbe_prv_data *);
+	int (*config_tx_pbl_val)(struct xgbe_prv_data *);
+	int (*get_tx_pbl_val)(struct xgbe_prv_data *);
+	int (*config_pblx8)(struct xgbe_prv_data *);
+
+	/* For MMC statistics */
+	void (*rx_mmc_int)(struct xgbe_prv_data *);
+	void (*tx_mmc_int)(struct xgbe_prv_data *);
+	void (*read_mmc_stats)(struct xgbe_prv_data *);
+};
+
+struct xgbe_desc_if {
+	int (*alloc_ring_resources)(struct xgbe_prv_data *);
+	void (*free_ring_resources)(struct xgbe_prv_data *);
+	int (*map_tx_skb)(struct xgbe_channel *, struct sk_buff *);
+	void (*realloc_skb)(struct xgbe_channel *);
+	void (*unmap_skb)(struct xgbe_prv_data *, struct xgbe_ring_data *);
+	void (*wrapper_tx_desc_init)(struct xgbe_prv_data *);
+	void (*wrapper_rx_desc_init)(struct xgbe_prv_data *);
+};
+
+/* This structure contains flags that indicate what hardware features
+ * or configurations are present in the device.
+ */
+struct xgbe_hw_features {
+	/* HW Feature Register0 */
+	unsigned int gmii;		/* 1000 Mbps support */
+	unsigned int vlhash;		/* VLAN Hash Filter */
+	unsigned int sma;		/* SMA(MDIO) Interface */
+	unsigned int rwk;		/* PMT remote wake-up packet */
+	unsigned int mgk;		/* PMT magic packet */
+	unsigned int mmc;		/* RMON module */
+	unsigned int aoe;		/* ARP Offload */
+	unsigned int ts;		/* IEEE 1588-2008 Adavanced Timestamp */
+	unsigned int eee;		/* Energy Efficient Ethernet */
+	unsigned int tx_coe;		/* Tx Checksum Offload */
+	unsigned int rx_coe;		/* Rx Checksum Offload */
+	unsigned int addn_mac;		/* Additional MAC Addresses */
+	unsigned int ts_src;		/* Timestamp Source */
+	unsigned int sa_vlan_ins;	/* Source Address or VLAN Insertion */
+
+	/* HW Feature Register1 */
+	unsigned int rx_fifo_size;	/* MTL Receive FIFO Size */
+	unsigned int tx_fifo_size;	/* MTL Transmit FIFO Size */
+	unsigned int adv_ts_hi;		/* Advance Timestamping High Word */
+	unsigned int dcb;		/* DCB Feature */
+	unsigned int sph;		/* Split Header Feature */
+	unsigned int tso;		/* TCP Segmentation Offload */
+	unsigned int dma_debug;		/* DMA Debug Registers */
+	unsigned int rss;		/* Receive Side Scaling */
+	unsigned int hash_table_size;	/* Hash Table Size */
+	unsigned int l3l4_filter_num;	/* Number of L3-L4 Filters */
+
+	/* HW Feature Register2 */
+	unsigned int rx_q_cnt;		/* Number of MTL Receive Queues */
+	unsigned int tx_q_cnt;		/* Number of MTL Transmit Queues */
+	unsigned int rx_ch_cnt;		/* Number of DMA Receive Channels */
+	unsigned int tx_ch_cnt;		/* Number of DMA Transmit Channels */
+	unsigned int pps_out_num;	/* Number of PPS outputs */
+	unsigned int aux_snap_num;	/* Number of Aux snapshot inputs */
+};
+
+struct xgbe_prv_data {
+	struct net_device *netdev;
+	struct platform_device *pdev;
+	struct device *dev;
+
+	/* XGMAC/XPCS related mmio registers */
+	void __iomem *xgmac_regs;	/* XGMAC CSRs */
+	void __iomem *xpcs_regs;	/* XPCS MMD registers */
+
+	/* Overall device lock */
+	spinlock_t lock;
+
+	/* XPCS indirect addressing mutex */
+	struct mutex xpcs_mutex;
+
+	int irq_number;
+
+	struct xgbe_hw_if hw_if;
+	struct xgbe_desc_if desc_if;
+
+	/* Rings for Tx/Rx on a DMA channel */
+	struct xgbe_channel *channel;
+	unsigned int channel_count;
+	unsigned int tx_ring_count;
+	unsigned int tx_desc_count;
+	unsigned int rx_ring_count;
+	unsigned int rx_desc_count;
+
+	/* Tx/Rx common settings */
+	unsigned int pblx8;
+
+	/* Tx settings */
+	unsigned int tx_sf_mode;
+	unsigned int tx_threshold;
+	unsigned int tx_pbl;
+	unsigned int tx_osp_mode;
+
+	/* Rx settings */
+	unsigned int rx_sf_mode;
+	unsigned int rx_threshold;
+	unsigned int rx_pbl;
+
+	/* Tx coalescing settings */
+	unsigned int tx_usecs;
+	unsigned int tx_frames;
+
+	/* Rx coalescing settings */
+	unsigned int rx_riwt;
+	unsigned int rx_frames;
+
+	/* Current MTU */
+	unsigned int rx_buf_size;
+
+	/* Flow control settings */
+	unsigned int pause_autoneg;
+	unsigned int tx_pause;
+	unsigned int rx_pause;
+
+	/* MDIO settings */
+	struct module *phy_module;
+	char *mii_bus_id;
+	struct mii_bus *mii;
+	int mdio_mmd;
+	struct phy_device *phydev;
+	int default_autoneg;
+	int default_speed;
+
+	/* Current PHY settings */
+	phy_interface_t phy_mode;
+	int phy_link;
+	int phy_speed;
+	unsigned int phy_tx_pause;
+	unsigned int phy_rx_pause;
+
+	/* Netdev related settings */
+	netdev_features_t netdev_features;
+	struct napi_struct napi;
+	struct xgbe_mmc_stats mmc_stats;
+
+	/* System clock value used for Rx watchdog */
+	struct clk *sysclock;
+
+	/* Hardware features of the device */
+	struct xgbe_hw_features hw_feat;
+
+	/* Device restart work structure */
+	struct work_struct restart_work;
+
+	/* Keeps track of power mode */
+	unsigned int power_down;
+
+#ifdef CONFIG_DEBUG_FS
+	struct dentry *xgbe_debugfs;
+
+	unsigned int debugfs_xgmac_reg;
+
+	unsigned int debugfs_xpcs_mmd;
+	unsigned int debugfs_xpcs_reg;
+#endif
+};
+
+/* Function prototypes*/
+
+void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *);
+void xgbe_init_function_ptrs_desc(struct xgbe_desc_if *);
+struct net_device_ops *xgbe_get_netdev_ops(void);
+struct ethtool_ops *xgbe_get_ethtool_ops(void);
+
+int xgbe_mdio_register(struct xgbe_prv_data *);
+void xgbe_mdio_unregister(struct xgbe_prv_data *);
+void xgbe_dump_phy_registers(struct xgbe_prv_data *);
+void xgbe_dump_tx_desc(struct xgbe_ring *, unsigned int, unsigned int,
+		       unsigned int);
+void xgbe_dump_rx_desc(struct xgbe_ring *, struct xgbe_ring_desc *,
+		       unsigned int);
+void xgbe_print_pkt(struct net_device *, struct sk_buff *, bool);
+void xgbe_get_all_hw_features(struct xgbe_prv_data *);
+int xgbe_powerup(struct net_device *, unsigned int);
+int xgbe_powerdown(struct net_device *, unsigned int);
+void xgbe_init_rx_coalesce(struct xgbe_prv_data *);
+void xgbe_init_tx_coalesce(struct xgbe_prv_data *);
+
+#ifdef CONFIG_DEBUG_FS
+void xgbe_debugfs_init(struct xgbe_prv_data *);
+void xgbe_debugfs_exit(struct xgbe_prv_data *);
+#else
+static inline void xgbe_debugfs_init(struct xgbe_prv_data *pdata) {}
+static inline void xgbe_debugfs_exit(struct xgbe_prv_data *pdata) {}
+#endif /* CONFIG_DEBUG_FS */
+
+/* NOTE: Uncomment for TX and RX DESCRIPTOR DUMP in KERNEL LOG */
+#if 0
+#define XGMAC_ENABLE_TX_DESC_DUMP
+#define XGMAC_ENABLE_RX_DESC_DUMP
+#endif
+
+/* NOTE: Uncomment for TX and RX PACKET DUMP in KERNEL LOG */
+#if 0
+#define XGMAC_ENABLE_TX_PKT_DUMP
+#define XGMAC_ENABLE_RX_PKT_DUMP
+#endif
+
+/* NOTE: Uncomment for function trace log messages in KERNEL LOG */
+#if 0
+#define YDEBUG
+#define YDEBUG_MDIO
+#endif
+
+/* For debug prints */
+#ifdef YDEBUG
+#define DBGPR(x...) pr_alert(x)
+#define DBGPHY_REGS(x...) xgbe_dump_phy_registers(x)
+#else
+#define DBGPR(x...) do { } while (0)
+#define DBGPHY_REGS(x...) do { } while (0)
+#endif
+
+#ifdef YDEBUG_MDIO
+#define DBGPR_MDIO(x...) pr_alert(x)
+#else
+#define DBGPR_MDIO(x...) do { } while (0)
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index d647a7d115a..18e2faccebb 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -13,6 +13,7 @@
  *		Vineet Gupta
  */
 
+#include <linux/crc32.h>
 #include <linux/etherdevice.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -362,6 +363,15 @@ static irqreturn_t arc_emac_intr(int irq, void *dev_instance)
 	return IRQ_HANDLED;
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void arc_emac_poll_controller(struct net_device *dev)
+{
+	disable_irq(dev->irq);
+	arc_emac_intr(dev->irq, dev);
+	enable_irq(dev->irq);
+}
+#endif
+
 /**
  * arc_emac_open - Open the network device.
  * @ndev:	Pointer to the network device.
@@ -451,6 +461,41 @@ static int arc_emac_open(struct net_device *ndev)
 }
 
 /**
+ * arc_emac_set_rx_mode - Change the receive filtering mode.
+ * @ndev:	Pointer to the network device.
+ *
+ * This function enables/disables promiscuous or all-multicast mode
+ * and updates the multicast filtering list of the network device.
+ */
+static void arc_emac_set_rx_mode(struct net_device *ndev)
+{
+	struct arc_emac_priv *priv = netdev_priv(ndev);
+
+	if (ndev->flags & IFF_PROMISC) {
+		arc_reg_or(priv, R_CTRL, PROM_MASK);
+	} else {
+		arc_reg_clr(priv, R_CTRL, PROM_MASK);
+
+		if (ndev->flags & IFF_ALLMULTI) {
+			arc_reg_set(priv, R_LAFL, ~0);
+			arc_reg_set(priv, R_LAFH, ~0);
+		} else {
+			struct netdev_hw_addr *ha;
+			unsigned int filter[2] = { 0, 0 };
+			int bit;
+
+			netdev_for_each_mc_addr(ha, ndev) {
+				bit = ether_crc_le(ETH_ALEN, ha->addr) >> 26;
+				filter[bit >> 5] |= 1 << (bit & 31);
+			}
+
+			arc_reg_set(priv, R_LAFL, filter[0]);
+			arc_reg_set(priv, R_LAFH, filter[1]);
+		}
+	}
+}
+
+/**
  * arc_emac_stop - Close the network device.
  * @ndev:	Pointer to the network device.
  *
@@ -620,6 +665,10 @@ static const struct net_device_ops arc_emac_netdev_ops = {
 	.ndo_start_xmit		= arc_emac_tx,
 	.ndo_set_mac_address	= arc_emac_set_address,
 	.ndo_get_stats		= arc_emac_stats,
+	.ndo_set_rx_mode	= arc_emac_set_rx_mode,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= arc_emac_poll_controller,
+#endif
 };
 
 static int arc_emac_probe(struct platform_device *pdev)
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 17bb9ce9626..49faa97a30c 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1302,7 +1302,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	netdev->netdev_ops = &alx_netdev_ops;
-	SET_ETHTOOL_OPS(netdev, &alx_ethtool_ops);
+	netdev->ethtool_ops = &alx_ethtool_ops;
 	netdev->irq = pdev->irq;
 	netdev->watchdog_timeo = ALX_WATCHDOG_TIME;
 
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
index 859ea844ba0..48694c239d5 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
@@ -56,8 +56,8 @@ static int atl1c_get_settings(struct net_device *netdev,
 		else
 			ecmd->duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	ecmd->autoneg = AUTONEG_ENABLE;
@@ -305,5 +305,5 @@ static const struct ethtool_ops atl1c_ethtool_ops = {
 
 void atl1c_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &atl1c_ethtool_ops);
+	netdev->ethtool_ops = &atl1c_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
index 82b23861bf5..1be072f4afc 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
@@ -57,8 +57,8 @@ static int atl1e_get_settings(struct net_device *netdev,
 		else
 			ecmd->duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	ecmd->autoneg = AUTONEG_ENABLE;
@@ -388,5 +388,5 @@ static const struct ethtool_ops atl1e_ethtool_ops = {
 
 void atl1e_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &atl1e_ethtool_ops);
+	netdev->ethtool_ops = &atl1e_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index dfd0e91fa72..b460db7919a 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -3258,8 +3258,8 @@ static int atl1_get_settings(struct net_device *netdev,
 		else
 			ecmd->duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 	if (hw->media_type == MEDIA_TYPE_AUTO_SENSOR ||
 	    hw->media_type == MEDIA_TYPE_1000M_FULL)
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 78befb522a5..6746bd71714 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -1396,7 +1396,7 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	atl2_setup_pcicmd(pdev);
 
 	netdev->netdev_ops = &atl2_netdev_ops;
-	SET_ETHTOOL_OPS(netdev, &atl2_ethtool_ops);
+	netdev->ethtool_ops = &atl2_ethtool_ops;
 	netdev->watchdog_timeo = 5 * HZ;
 	strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1);
 
@@ -1769,8 +1769,8 @@ static int atl2_get_settings(struct net_device *netdev,
 		else
 			ecmd->duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	ecmd->autoneg = AUTONEG_ENABLE;
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 85dbddd0372..3e488094b07 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -150,4 +150,15 @@ config BGMAC
 	  In case of using this driver on BCM4706 it's also requires to enable
 	  BCMA_DRIVER_GMAC_CMN to make it work.
 
+config SYSTEMPORT
+	tristate "Broadcom SYSTEMPORT internal MAC support"
+	depends on OF
+	select MII
+	select PHYLIB
+	select FIXED_PHY if SYSTEMPORT=y
+	help
+	  This driver supports the built-in Ethernet MACs found in the
+	  Broadcom BCM7xxx Set Top Box family chipset using an internal
+	  Ethernet switch.
+
 endif # NET_VENDOR_BROADCOM
diff --git a/drivers/net/ethernet/broadcom/Makefile b/drivers/net/ethernet/broadcom/Makefile
index fd639a0d4c7..e2a958a657e 100644
--- a/drivers/net/ethernet/broadcom/Makefile
+++ b/drivers/net/ethernet/broadcom/Makefile
@@ -11,3 +11,4 @@ obj-$(CONFIG_BNX2X) += bnx2x/
 obj-$(CONFIG_SB1250_MAC) += sb1250-mac.o
 obj-$(CONFIG_TIGON3) += tg3.o
 obj-$(CONFIG_BGMAC) += bgmac.o
+obj-$(CONFIG_SYSTEMPORT) += bcmsysport.o
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 05ba6258901..ca5a20a48b1 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -2380,7 +2380,7 @@ static int b44_init_one(struct ssb_device *sdev,
 	netif_napi_add(dev, &bp->napi, b44_poll, 64);
 	dev->watchdog_timeo = B44_TX_TIMEOUT;
 	dev->irq = sdev->irq;
-	SET_ETHTOOL_OPS(dev, &b44_ethtool_ops);
+	dev->ethtool_ops = &b44_ethtool_ops;
 
 	err = ssb_bus_powerup(sdev->bus, 0);
 	if (err) {
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index a7d11f5565d..3e8d1a88ed3 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -1315,8 +1315,7 @@ static const struct bcm_enet_stats bcm_enet_gstrings_stats[] = {
 
 };
 
-#define BCM_ENET_STATS_LEN	\
-	(sizeof(bcm_enet_gstrings_stats) / sizeof(struct bcm_enet_stats))
+#define BCM_ENET_STATS_LEN	ARRAY_SIZE(bcm_enet_gstrings_stats)
 
 static const u32 unused_mib_regs[] = {
 	ETH_MIB_TX_ALL_OCTETS,
@@ -1898,7 +1897,7 @@ static int bcm_enet_probe(struct platform_device *pdev)
 	dev->netdev_ops = &bcm_enet_ops;
 	netif_napi_add(dev, &priv->napi, bcm_enet_poll, 16);
 
-	SET_ETHTOOL_OPS(dev, &bcm_enet_ethtool_ops);
+	dev->ethtool_ops = &bcm_enet_ethtool_ops;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	ret = register_netdev(dev);
@@ -2784,7 +2783,7 @@ static int bcm_enetsw_probe(struct platform_device *pdev)
 	/* register netdevice */
 	dev->netdev_ops = &bcm_enetsw_ops;
 	netif_napi_add(dev, &priv->napi, bcm_enet_poll, 16);
-	SET_ETHTOOL_OPS(dev, &bcm_enetsw_ethtool_ops);
+	dev->ethtool_ops = &bcm_enetsw_ethtool_ops;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	spin_lock_init(&priv->enetsw_mdio_lock);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
new file mode 100644
index 00000000000..5776e503e4c
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -0,0 +1,1633 @@
+/*
+ * Broadcom BCM7xxx System Port Ethernet MAC driver
+ *
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+#include <linux/phy.h>
+#include <linux/phy_fixed.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+
+#include "bcmsysport.h"
+
+/* I/O accessors register helpers */
+#define BCM_SYSPORT_IO_MACRO(name, offset) \
+static inline u32 name##_readl(struct bcm_sysport_priv *priv, u32 off)	\
+{									\
+	u32 reg = __raw_readl(priv->base + offset + off);		\
+	return reg;							\
+}									\
+static inline void name##_writel(struct bcm_sysport_priv *priv,		\
+				  u32 val, u32 off)			\
+{									\
+	__raw_writel(val, priv->base + offset + off);			\
+}									\
+
+BCM_SYSPORT_IO_MACRO(intrl2_0, SYS_PORT_INTRL2_0_OFFSET);
+BCM_SYSPORT_IO_MACRO(intrl2_1, SYS_PORT_INTRL2_1_OFFSET);
+BCM_SYSPORT_IO_MACRO(umac, SYS_PORT_UMAC_OFFSET);
+BCM_SYSPORT_IO_MACRO(tdma, SYS_PORT_TDMA_OFFSET);
+BCM_SYSPORT_IO_MACRO(rdma, SYS_PORT_RDMA_OFFSET);
+BCM_SYSPORT_IO_MACRO(rxchk, SYS_PORT_RXCHK_OFFSET);
+BCM_SYSPORT_IO_MACRO(txchk, SYS_PORT_TXCHK_OFFSET);
+BCM_SYSPORT_IO_MACRO(rbuf, SYS_PORT_RBUF_OFFSET);
+BCM_SYSPORT_IO_MACRO(tbuf, SYS_PORT_TBUF_OFFSET);
+BCM_SYSPORT_IO_MACRO(topctrl, SYS_PORT_TOPCTRL_OFFSET);
+
+/* L2-interrupt masking/unmasking helpers, does automatic saving of the applied
+ * mask in a software copy to avoid CPU_MASK_STATUS reads in hot-paths.
+  */
+#define BCM_SYSPORT_INTR_L2(which)	\
+static inline void intrl2_##which##_mask_clear(struct bcm_sysport_priv *priv, \
+						u32 mask)		\
+{									\
+	intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR);	\
+	priv->irq##which##_mask &= ~(mask);				\
+}									\
+static inline void intrl2_##which##_mask_set(struct bcm_sysport_priv *priv, \
+						u32 mask)		\
+{									\
+	intrl2_## which##_writel(priv, mask, INTRL2_CPU_MASK_SET);	\
+	priv->irq##which##_mask |= (mask);				\
+}									\
+
+BCM_SYSPORT_INTR_L2(0)
+BCM_SYSPORT_INTR_L2(1)
+
+/* Register accesses to GISB/RBUS registers are expensive (few hundred
+ * nanoseconds), so keep the check for 64-bits explicit here to save
+ * one register write per-packet on 32-bits platforms.
+ */
+static inline void dma_desc_set_addr(struct bcm_sysport_priv *priv,
+				     void __iomem *d,
+				     dma_addr_t addr)
+{
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	__raw_writel(upper_32_bits(addr) & DESC_ADDR_HI_MASK,
+			d + DESC_ADDR_HI_STATUS_LEN);
+#endif
+	__raw_writel(lower_32_bits(addr), d + DESC_ADDR_LO);
+}
+
+static inline void tdma_port_write_desc_addr(struct bcm_sysport_priv *priv,
+						struct dma_desc *desc,
+						unsigned int port)
+{
+	/* Ports are latched, so write upper address first */
+	tdma_writel(priv, desc->addr_status_len, TDMA_WRITE_PORT_HI(port));
+	tdma_writel(priv, desc->addr_lo, TDMA_WRITE_PORT_LO(port));
+}
+
+/* Ethtool operations */
+static int bcm_sysport_set_settings(struct net_device *dev,
+				    struct ethtool_cmd *cmd)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	return phy_ethtool_sset(priv->phydev, cmd);
+}
+
+static int bcm_sysport_get_settings(struct net_device *dev,
+					struct ethtool_cmd *cmd)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	return phy_ethtool_gset(priv->phydev, cmd);
+}
+
+static int bcm_sysport_set_rx_csum(struct net_device *dev,
+					netdev_features_t wanted)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	u32 reg;
+
+	priv->rx_csum_en = !!(wanted & NETIF_F_RXCSUM);
+	reg = rxchk_readl(priv, RXCHK_CONTROL);
+	if (priv->rx_csum_en)
+		reg |= RXCHK_EN;
+	else
+		reg &= ~RXCHK_EN;
+
+	/* If UniMAC forwards CRC, we need to skip over it to get
+	 * a valid CHK bit to be set in the per-packet status word
+	 */
+	if (priv->rx_csum_en && priv->crc_fwd)
+		reg |= RXCHK_SKIP_FCS;
+	else
+		reg &= ~RXCHK_SKIP_FCS;
+
+	rxchk_writel(priv, reg, RXCHK_CONTROL);
+
+	return 0;
+}
+
+static int bcm_sysport_set_tx_csum(struct net_device *dev,
+					netdev_features_t wanted)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	u32 reg;
+
+	/* Hardware transmit checksum requires us to enable the Transmit status
+	 * block prepended to the packet contents
+	 */
+	priv->tsb_en = !!(wanted & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM));
+	reg = tdma_readl(priv, TDMA_CONTROL);
+	if (priv->tsb_en)
+		reg |= TSB_EN;
+	else
+		reg &= ~TSB_EN;
+	tdma_writel(priv, reg, TDMA_CONTROL);
+
+	return 0;
+}
+
+static int bcm_sysport_set_features(struct net_device *dev,
+					netdev_features_t features)
+{
+	netdev_features_t changed = features ^ dev->features;
+	netdev_features_t wanted = dev->wanted_features;
+	int ret = 0;
+
+	if (changed & NETIF_F_RXCSUM)
+		ret = bcm_sysport_set_rx_csum(dev, wanted);
+	if (changed & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))
+		ret = bcm_sysport_set_tx_csum(dev, wanted);
+
+	return ret;
+}
+
+/* Hardware counters must be kept in sync because the order/offset
+ * is important here (order in structure declaration = order in hardware)
+ */
+static const struct bcm_sysport_stats bcm_sysport_gstrings_stats[] = {
+	/* general stats */
+	STAT_NETDEV(rx_packets),
+	STAT_NETDEV(tx_packets),
+	STAT_NETDEV(rx_bytes),
+	STAT_NETDEV(tx_bytes),
+	STAT_NETDEV(rx_errors),
+	STAT_NETDEV(tx_errors),
+	STAT_NETDEV(rx_dropped),
+	STAT_NETDEV(tx_dropped),
+	STAT_NETDEV(multicast),
+	/* UniMAC RSV counters */
+	STAT_MIB_RX("rx_64_octets", mib.rx.pkt_cnt.cnt_64),
+	STAT_MIB_RX("rx_65_127_oct", mib.rx.pkt_cnt.cnt_127),
+	STAT_MIB_RX("rx_128_255_oct", mib.rx.pkt_cnt.cnt_255),
+	STAT_MIB_RX("rx_256_511_oct", mib.rx.pkt_cnt.cnt_511),
+	STAT_MIB_RX("rx_512_1023_oct", mib.rx.pkt_cnt.cnt_1023),
+	STAT_MIB_RX("rx_1024_1518_oct", mib.rx.pkt_cnt.cnt_1518),
+	STAT_MIB_RX("rx_vlan_1519_1522_oct", mib.rx.pkt_cnt.cnt_mgv),
+	STAT_MIB_RX("rx_1522_2047_oct", mib.rx.pkt_cnt.cnt_2047),
+	STAT_MIB_RX("rx_2048_4095_oct", mib.rx.pkt_cnt.cnt_4095),
+	STAT_MIB_RX("rx_4096_9216_oct", mib.rx.pkt_cnt.cnt_9216),
+	STAT_MIB_RX("rx_pkts", mib.rx.pkt),
+	STAT_MIB_RX("rx_bytes", mib.rx.bytes),
+	STAT_MIB_RX("rx_multicast", mib.rx.mca),
+	STAT_MIB_RX("rx_broadcast", mib.rx.bca),
+	STAT_MIB_RX("rx_fcs", mib.rx.fcs),
+	STAT_MIB_RX("rx_control", mib.rx.cf),
+	STAT_MIB_RX("rx_pause", mib.rx.pf),
+	STAT_MIB_RX("rx_unknown", mib.rx.uo),
+	STAT_MIB_RX("rx_align", mib.rx.aln),
+	STAT_MIB_RX("rx_outrange", mib.rx.flr),
+	STAT_MIB_RX("rx_code", mib.rx.cde),
+	STAT_MIB_RX("rx_carrier", mib.rx.fcr),
+	STAT_MIB_RX("rx_oversize", mib.rx.ovr),
+	STAT_MIB_RX("rx_jabber", mib.rx.jbr),
+	STAT_MIB_RX("rx_mtu_err", mib.rx.mtue),
+	STAT_MIB_RX("rx_good_pkts", mib.rx.pok),
+	STAT_MIB_RX("rx_unicast", mib.rx.uc),
+	STAT_MIB_RX("rx_ppp", mib.rx.ppp),
+	STAT_MIB_RX("rx_crc", mib.rx.rcrc),
+	/* UniMAC TSV counters */
+	STAT_MIB_TX("tx_64_octets", mib.tx.pkt_cnt.cnt_64),
+	STAT_MIB_TX("tx_65_127_oct", mib.tx.pkt_cnt.cnt_127),
+	STAT_MIB_TX("tx_128_255_oct", mib.tx.pkt_cnt.cnt_255),
+	STAT_MIB_TX("tx_256_511_oct", mib.tx.pkt_cnt.cnt_511),
+	STAT_MIB_TX("tx_512_1023_oct", mib.tx.pkt_cnt.cnt_1023),
+	STAT_MIB_TX("tx_1024_1518_oct", mib.tx.pkt_cnt.cnt_1518),
+	STAT_MIB_TX("tx_vlan_1519_1522_oct", mib.tx.pkt_cnt.cnt_mgv),
+	STAT_MIB_TX("tx_1522_2047_oct", mib.tx.pkt_cnt.cnt_2047),
+	STAT_MIB_TX("tx_2048_4095_oct", mib.tx.pkt_cnt.cnt_4095),
+	STAT_MIB_TX("tx_4096_9216_oct", mib.tx.pkt_cnt.cnt_9216),
+	STAT_MIB_TX("tx_pkts", mib.tx.pkts),
+	STAT_MIB_TX("tx_multicast", mib.tx.mca),
+	STAT_MIB_TX("tx_broadcast", mib.tx.bca),
+	STAT_MIB_TX("tx_pause", mib.tx.pf),
+	STAT_MIB_TX("tx_control", mib.tx.cf),
+	STAT_MIB_TX("tx_fcs_err", mib.tx.fcs),
+	STAT_MIB_TX("tx_oversize", mib.tx.ovr),
+	STAT_MIB_TX("tx_defer", mib.tx.drf),
+	STAT_MIB_TX("tx_excess_defer", mib.tx.edf),
+	STAT_MIB_TX("tx_single_col", mib.tx.scl),
+	STAT_MIB_TX("tx_multi_col", mib.tx.mcl),
+	STAT_MIB_TX("tx_late_col", mib.tx.lcl),
+	STAT_MIB_TX("tx_excess_col", mib.tx.ecl),
+	STAT_MIB_TX("tx_frags", mib.tx.frg),
+	STAT_MIB_TX("tx_total_col", mib.tx.ncl),
+	STAT_MIB_TX("tx_jabber", mib.tx.jbr),
+	STAT_MIB_TX("tx_bytes", mib.tx.bytes),
+	STAT_MIB_TX("tx_good_pkts", mib.tx.pok),
+	STAT_MIB_TX("tx_unicast", mib.tx.uc),
+	/* UniMAC RUNT counters */
+	STAT_RUNT("rx_runt_pkts", mib.rx_runt_cnt),
+	STAT_RUNT("rx_runt_valid_fcs", mib.rx_runt_fcs),
+	STAT_RUNT("rx_runt_inval_fcs_align", mib.rx_runt_fcs_align),
+	STAT_RUNT("rx_runt_bytes", mib.rx_runt_bytes),
+	/* RXCHK misc statistics */
+	STAT_RXCHK("rxchk_bad_csum", mib.rxchk_bad_csum, RXCHK_BAD_CSUM_CNTR),
+	STAT_RXCHK("rxchk_other_pkt_disc", mib.rxchk_other_pkt_disc,
+			RXCHK_OTHER_DISC_CNTR),
+	/* RBUF misc statistics */
+	STAT_RBUF("rbuf_ovflow_cnt", mib.rbuf_ovflow_cnt, RBUF_OVFL_DISC_CNTR),
+	STAT_RBUF("rbuf_err_cnt", mib.rbuf_err_cnt, RBUF_ERR_PKT_CNTR),
+};
+
+#define BCM_SYSPORT_STATS_LEN	ARRAY_SIZE(bcm_sysport_gstrings_stats)
+
+static void bcm_sysport_get_drvinfo(struct net_device *dev,
+					struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+	strlcpy(info->version, "0.1", sizeof(info->version));
+	strlcpy(info->bus_info, "platform", sizeof(info->bus_info));
+	info->n_stats = BCM_SYSPORT_STATS_LEN;
+}
+
+static u32 bcm_sysport_get_msglvl(struct net_device *dev)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+
+	return priv->msg_enable;
+}
+
+static void bcm_sysport_set_msglvl(struct net_device *dev, u32 enable)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+
+	priv->msg_enable = enable;
+}
+
+static int bcm_sysport_get_sset_count(struct net_device *dev, int string_set)
+{
+	switch (string_set) {
+	case ETH_SS_STATS:
+		return BCM_SYSPORT_STATS_LEN;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void bcm_sysport_get_strings(struct net_device *dev,
+					u32 stringset, u8 *data)
+{
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < BCM_SYSPORT_STATS_LEN; i++) {
+			memcpy(data + i * ETH_GSTRING_LEN,
+				bcm_sysport_gstrings_stats[i].stat_string,
+				ETH_GSTRING_LEN);
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void bcm_sysport_update_mib_counters(struct bcm_sysport_priv *priv)
+{
+	int i, j = 0;
+
+	for (i = 0; i < BCM_SYSPORT_STATS_LEN; i++) {
+		const struct bcm_sysport_stats *s;
+		u8 offset = 0;
+		u32 val = 0;
+		char *p;
+
+		s = &bcm_sysport_gstrings_stats[i];
+		switch (s->type) {
+		case BCM_SYSPORT_STAT_NETDEV:
+			continue;
+		case BCM_SYSPORT_STAT_MIB_RX:
+		case BCM_SYSPORT_STAT_MIB_TX:
+		case BCM_SYSPORT_STAT_RUNT:
+			if (s->type != BCM_SYSPORT_STAT_MIB_RX)
+				offset = UMAC_MIB_STAT_OFFSET;
+			val = umac_readl(priv, UMAC_MIB_START + j + offset);
+			break;
+		case BCM_SYSPORT_STAT_RXCHK:
+			val = rxchk_readl(priv, s->reg_offset);
+			if (val == ~0)
+				rxchk_writel(priv, 0, s->reg_offset);
+			break;
+		case BCM_SYSPORT_STAT_RBUF:
+			val = rbuf_readl(priv, s->reg_offset);
+			if (val == ~0)
+				rbuf_writel(priv, 0, s->reg_offset);
+			break;
+		}
+
+		j += s->stat_sizeof;
+		p = (char *)priv + s->stat_offset;
+		*(u32 *)p = val;
+	}
+
+	netif_dbg(priv, hw, priv->netdev, "updated MIB counters\n");
+}
+
+static void bcm_sysport_get_stats(struct net_device *dev,
+					struct ethtool_stats *stats, u64 *data)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	int i;
+
+	if (netif_running(dev))
+		bcm_sysport_update_mib_counters(priv);
+
+	for (i =  0; i < BCM_SYSPORT_STATS_LEN; i++) {
+		const struct bcm_sysport_stats *s;
+		char *p;
+
+		s = &bcm_sysport_gstrings_stats[i];
+		if (s->type == BCM_SYSPORT_STAT_NETDEV)
+			p = (char *)&dev->stats;
+		else
+			p = (char *)priv;
+		p += s->stat_offset;
+		data[i] = *(u32 *)p;
+	}
+}
+
+static void bcm_sysport_free_cb(struct bcm_sysport_cb *cb)
+{
+	dev_kfree_skb_any(cb->skb);
+	cb->skb = NULL;
+	dma_unmap_addr_set(cb, dma_addr, 0);
+}
+
+static int bcm_sysport_rx_refill(struct bcm_sysport_priv *priv,
+				 struct bcm_sysport_cb *cb)
+{
+	struct device *kdev = &priv->pdev->dev;
+	struct net_device *ndev = priv->netdev;
+	dma_addr_t mapping;
+	int ret;
+
+	cb->skb = netdev_alloc_skb(priv->netdev, RX_BUF_LENGTH);
+	if (!cb->skb) {
+		netif_err(priv, rx_err, ndev, "SKB alloc failed\n");
+		return -ENOMEM;
+	}
+
+	mapping = dma_map_single(kdev, cb->skb->data,
+				RX_BUF_LENGTH, DMA_FROM_DEVICE);
+	ret = dma_mapping_error(kdev, mapping);
+	if (ret) {
+		bcm_sysport_free_cb(cb);
+		netif_err(priv, rx_err, ndev, "DMA mapping failure\n");
+		return ret;
+	}
+
+	dma_unmap_addr_set(cb, dma_addr, mapping);
+	dma_desc_set_addr(priv, priv->rx_bd_assign_ptr, mapping);
+
+	priv->rx_bd_assign_index++;
+	priv->rx_bd_assign_index &= (priv->num_rx_bds - 1);
+	priv->rx_bd_assign_ptr = priv->rx_bds +
+		(priv->rx_bd_assign_index * DESC_SIZE);
+
+	netif_dbg(priv, rx_status, ndev, "RX refill\n");
+
+	return 0;
+}
+
+static int bcm_sysport_alloc_rx_bufs(struct bcm_sysport_priv *priv)
+{
+	struct bcm_sysport_cb *cb;
+	int ret = 0;
+	unsigned int i;
+
+	for (i = 0; i < priv->num_rx_bds; i++) {
+		cb = &priv->rx_cbs[priv->rx_bd_assign_index];
+		if (cb->skb)
+			continue;
+
+		ret = bcm_sysport_rx_refill(priv, cb);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+/* Poll the hardware for up to budget packets to process */
+static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv,
+					unsigned int budget)
+{
+	struct device *kdev = &priv->pdev->dev;
+	struct net_device *ndev = priv->netdev;
+	unsigned int processed = 0, to_process;
+	struct bcm_sysport_cb *cb;
+	struct sk_buff *skb;
+	unsigned int p_index;
+	u16 len, status;
+	struct bcm_rsb *rsb;
+
+	/* Determine how much we should process since last call */
+	p_index = rdma_readl(priv, RDMA_PROD_INDEX);
+	p_index &= RDMA_PROD_INDEX_MASK;
+
+	if (p_index < priv->rx_c_index)
+		to_process = (RDMA_CONS_INDEX_MASK + 1) -
+			priv->rx_c_index + p_index;
+	else
+		to_process = p_index - priv->rx_c_index;
+
+	netif_dbg(priv, rx_status, ndev,
+			"p_index=%d rx_c_index=%d to_process=%d\n",
+			p_index, priv->rx_c_index, to_process);
+
+	while ((processed < to_process) &&
+		(processed < budget)) {
+
+		cb = &priv->rx_cbs[priv->rx_read_ptr];
+		skb = cb->skb;
+		dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
+				RX_BUF_LENGTH, DMA_FROM_DEVICE);
+
+		/* Extract the Receive Status Block prepended */
+		rsb = (struct bcm_rsb *)skb->data;
+		len = (rsb->rx_status_len >> DESC_LEN_SHIFT) & DESC_LEN_MASK;
+		status = (rsb->rx_status_len >> DESC_STATUS_SHIFT) &
+			DESC_STATUS_MASK;
+
+		processed++;
+		priv->rx_read_ptr++;
+		if (priv->rx_read_ptr == priv->num_rx_bds)
+			priv->rx_read_ptr = 0;
+
+		netif_dbg(priv, rx_status, ndev,
+				"p=%d, c=%d, rd_ptr=%d, len=%d, flag=0x%04x\n",
+				p_index, priv->rx_c_index, priv->rx_read_ptr,
+				len, status);
+
+		if (unlikely(!skb)) {
+			netif_err(priv, rx_err, ndev, "out of memory!\n");
+			ndev->stats.rx_dropped++;
+			ndev->stats.rx_errors++;
+			goto refill;
+		}
+
+		if (unlikely(!(status & DESC_EOP) || !(status & DESC_SOP))) {
+			netif_err(priv, rx_status, ndev, "fragmented packet!\n");
+			ndev->stats.rx_dropped++;
+			ndev->stats.rx_errors++;
+			bcm_sysport_free_cb(cb);
+			goto refill;
+		}
+
+		if (unlikely(status & (RX_STATUS_ERR | RX_STATUS_OVFLOW))) {
+			netif_err(priv, rx_err, ndev, "error packet\n");
+			if (status & RX_STATUS_OVFLOW)
+				ndev->stats.rx_over_errors++;
+			ndev->stats.rx_dropped++;
+			ndev->stats.rx_errors++;
+			bcm_sysport_free_cb(cb);
+			goto refill;
+		}
+
+		skb_put(skb, len);
+
+		/* Hardware validated our checksum */
+		if (likely(status & DESC_L4_CSUM))
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+		/* Hardware pre-pends packets with 2bytes before Ethernet
+		 * header plus we have the Receive Status Block, strip off all
+		 * of this from the SKB.
+		 */
+		skb_pull(skb, sizeof(*rsb) + 2);
+		len -= (sizeof(*rsb) + 2);
+
+		/* UniMAC may forward CRC */
+		if (priv->crc_fwd) {
+			skb_trim(skb, len - ETH_FCS_LEN);
+			len -= ETH_FCS_LEN;
+		}
+
+		skb->protocol = eth_type_trans(skb, ndev);
+		ndev->stats.rx_packets++;
+		ndev->stats.rx_bytes += len;
+
+		napi_gro_receive(&priv->napi, skb);
+refill:
+		bcm_sysport_rx_refill(priv, cb);
+	}
+
+	return processed;
+}
+
+static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_priv *priv,
+					struct bcm_sysport_cb *cb,
+					unsigned int *bytes_compl,
+					unsigned int *pkts_compl)
+{
+	struct device *kdev = &priv->pdev->dev;
+	struct net_device *ndev = priv->netdev;
+
+	if (cb->skb) {
+		ndev->stats.tx_bytes += cb->skb->len;
+		*bytes_compl += cb->skb->len;
+		dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr),
+				dma_unmap_len(cb, dma_len),
+				DMA_TO_DEVICE);
+		ndev->stats.tx_packets++;
+		(*pkts_compl)++;
+		bcm_sysport_free_cb(cb);
+	/* SKB fragment */
+	} else if (dma_unmap_addr(cb, dma_addr)) {
+		ndev->stats.tx_bytes += dma_unmap_len(cb, dma_len);
+		dma_unmap_page(kdev, dma_unmap_addr(cb, dma_addr),
+				dma_unmap_len(cb, dma_len), DMA_TO_DEVICE);
+		dma_unmap_addr_set(cb, dma_addr, 0);
+	}
+}
+
+/* Reclaim queued SKBs for transmission completion, lockless version */
+static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
+					     struct bcm_sysport_tx_ring *ring)
+{
+	struct net_device *ndev = priv->netdev;
+	unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs;
+	unsigned int pkts_compl = 0, bytes_compl = 0;
+	struct bcm_sysport_cb *cb;
+	struct netdev_queue *txq;
+	u32 hw_ind;
+
+	txq = netdev_get_tx_queue(ndev, ring->index);
+
+	/* Compute how many descriptors have been processed since last call */
+	hw_ind = tdma_readl(priv, TDMA_DESC_RING_PROD_CONS_INDEX(ring->index));
+	c_index = (hw_ind >> RING_CONS_INDEX_SHIFT) & RING_CONS_INDEX_MASK;
+	ring->p_index = (hw_ind & RING_PROD_INDEX_MASK);
+
+	last_c_index = ring->c_index;
+	num_tx_cbs = ring->size;
+
+	c_index &= (num_tx_cbs - 1);
+
+	if (c_index >= last_c_index)
+		last_tx_cn = c_index - last_c_index;
+	else
+		last_tx_cn = num_tx_cbs - last_c_index + c_index;
+
+	netif_dbg(priv, tx_done, ndev,
+			"ring=%d c_index=%d last_tx_cn=%d last_c_index=%d\n",
+			ring->index, c_index, last_tx_cn, last_c_index);
+
+	while (last_tx_cn-- > 0) {
+		cb = ring->cbs + last_c_index;
+		bcm_sysport_tx_reclaim_one(priv, cb, &bytes_compl, &pkts_compl);
+
+		ring->desc_count++;
+		last_c_index++;
+		last_c_index &= (num_tx_cbs - 1);
+	}
+
+	ring->c_index = c_index;
+
+	if (netif_tx_queue_stopped(txq) && pkts_compl)
+		netif_tx_wake_queue(txq);
+
+	netif_dbg(priv, tx_done, ndev,
+			"ring=%d c_index=%d pkts_compl=%d, bytes_compl=%d\n",
+			ring->index, ring->c_index, pkts_compl, bytes_compl);
+
+	return pkts_compl;
+}
+
+/* Locked version of the per-ring TX reclaim routine */
+static unsigned int bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv,
+					   struct bcm_sysport_tx_ring *ring)
+{
+	unsigned int released;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	released = __bcm_sysport_tx_reclaim(priv, ring);
+	spin_unlock_irqrestore(&ring->lock, flags);
+
+	return released;
+}
+
+static int bcm_sysport_tx_poll(struct napi_struct *napi, int budget)
+{
+	struct bcm_sysport_tx_ring *ring =
+		container_of(napi, struct bcm_sysport_tx_ring, napi);
+	unsigned int work_done = 0;
+
+	work_done = bcm_sysport_tx_reclaim(ring->priv, ring);
+
+	if (work_done == 0) {
+		napi_complete(napi);
+		/* re-enable TX interrupt */
+		intrl2_1_mask_clear(ring->priv, BIT(ring->index));
+	}
+
+	return 0;
+}
+
+static void bcm_sysport_tx_reclaim_all(struct bcm_sysport_priv *priv)
+{
+	unsigned int q;
+
+	for (q = 0; q < priv->netdev->num_tx_queues; q++)
+		bcm_sysport_tx_reclaim(priv, &priv->tx_rings[q]);
+}
+
+static int bcm_sysport_poll(struct napi_struct *napi, int budget)
+{
+	struct bcm_sysport_priv *priv =
+		container_of(napi, struct bcm_sysport_priv, napi);
+	unsigned int work_done = 0;
+
+	work_done = bcm_sysport_desc_rx(priv, budget);
+
+	priv->rx_c_index += work_done;
+	priv->rx_c_index &= RDMA_CONS_INDEX_MASK;
+	rdma_writel(priv, priv->rx_c_index, RDMA_CONS_INDEX);
+
+	if (work_done < budget) {
+		napi_complete(napi);
+		/* re-enable RX interrupts */
+		intrl2_0_mask_clear(priv, INTRL2_0_RDMA_MBDONE);
+	}
+
+	return work_done;
+}
+
+
+/* RX and misc interrupt routine */
+static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id)
+{
+	struct net_device *dev = dev_id;
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+
+	priv->irq0_stat = intrl2_0_readl(priv, INTRL2_CPU_STATUS) &
+			  ~intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
+	intrl2_0_writel(priv, priv->irq0_stat, INTRL2_CPU_CLEAR);
+
+	if (unlikely(priv->irq0_stat == 0)) {
+		netdev_warn(priv->netdev, "spurious RX interrupt\n");
+		return IRQ_NONE;
+	}
+
+	if (priv->irq0_stat & INTRL2_0_RDMA_MBDONE) {
+		if (likely(napi_schedule_prep(&priv->napi))) {
+			/* disable RX interrupts */
+			intrl2_0_mask_set(priv, INTRL2_0_RDMA_MBDONE);
+			__napi_schedule(&priv->napi);
+		}
+	}
+
+	/* TX ring is full, perform a full reclaim since we do not know
+	 * which one would trigger this interrupt
+	 */
+	if (priv->irq0_stat & INTRL2_0_TX_RING_FULL)
+		bcm_sysport_tx_reclaim_all(priv);
+
+	return IRQ_HANDLED;
+}
+
+/* TX interrupt service routine */
+static irqreturn_t bcm_sysport_tx_isr(int irq, void *dev_id)
+{
+	struct net_device *dev = dev_id;
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct bcm_sysport_tx_ring *txr;
+	unsigned int ring;
+
+	priv->irq1_stat = intrl2_1_readl(priv, INTRL2_CPU_STATUS) &
+				~intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
+	intrl2_1_writel(priv, 0xffffffff, INTRL2_CPU_CLEAR);
+
+	if (unlikely(priv->irq1_stat == 0)) {
+		netdev_warn(priv->netdev, "spurious TX interrupt\n");
+		return IRQ_NONE;
+	}
+
+	for (ring = 0; ring < dev->num_tx_queues; ring++) {
+		if (!(priv->irq1_stat & BIT(ring)))
+			continue;
+
+		txr = &priv->tx_rings[ring];
+
+		if (likely(napi_schedule_prep(&txr->napi))) {
+			intrl2_1_mask_set(priv, BIT(ring));
+			__napi_schedule(&txr->napi);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int bcm_sysport_insert_tsb(struct sk_buff *skb, struct net_device *dev)
+{
+	struct sk_buff *nskb;
+	struct bcm_tsb *tsb;
+	u32 csum_info;
+	u8 ip_proto;
+	u16 csum_start;
+	u16 ip_ver;
+
+	/* Re-allocate SKB if needed */
+	if (unlikely(skb_headroom(skb) < sizeof(*tsb))) {
+		nskb = skb_realloc_headroom(skb, sizeof(*tsb));
+		dev_kfree_skb(skb);
+		if (!nskb) {
+			dev->stats.tx_errors++;
+			dev->stats.tx_dropped++;
+			return -ENOMEM;
+		}
+		skb = nskb;
+	}
+
+	tsb = (struct bcm_tsb *)skb_push(skb, sizeof(*tsb));
+	/* Zero-out TSB by default */
+	memset(tsb, 0, sizeof(*tsb));
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		ip_ver = htons(skb->protocol);
+		switch (ip_ver) {
+		case ETH_P_IP:
+			ip_proto = ip_hdr(skb)->protocol;
+			break;
+		case ETH_P_IPV6:
+			ip_proto = ipv6_hdr(skb)->nexthdr;
+			break;
+		default:
+			return 0;
+		}
+
+		/* Get the checksum offset and the L4 (transport) offset */
+		csum_start = skb_checksum_start_offset(skb) - sizeof(*tsb);
+		csum_info = (csum_start + skb->csum_offset) & L4_CSUM_PTR_MASK;
+		csum_info |= (csum_start << L4_PTR_SHIFT);
+
+		if (ip_proto == IPPROTO_TCP || ip_proto == IPPROTO_UDP) {
+			csum_info |= L4_LENGTH_VALID;
+			if (ip_proto == IPPROTO_UDP && ip_ver == ETH_P_IP)
+				csum_info |= L4_UDP;
+		} else
+			csum_info = 0;
+
+		tsb->l4_ptr_dest_map = csum_info;
+	}
+
+	return 0;
+}
+
+static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb,
+				    struct net_device *dev)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct device *kdev = &priv->pdev->dev;
+	struct bcm_sysport_tx_ring *ring;
+	struct bcm_sysport_cb *cb;
+	struct netdev_queue *txq;
+	struct dma_desc *desc;
+	unsigned int skb_len;
+	unsigned long flags;
+	dma_addr_t mapping;
+	u32 len_status;
+	u16 queue;
+	int ret;
+
+	queue = skb_get_queue_mapping(skb);
+	txq = netdev_get_tx_queue(dev, queue);
+	ring = &priv->tx_rings[queue];
+
+	/* lock against tx reclaim in BH context and TX ring full interrupt */
+	spin_lock_irqsave(&ring->lock, flags);
+	if (unlikely(ring->desc_count == 0)) {
+		netif_tx_stop_queue(txq);
+		netdev_err(dev, "queue %d awake and ring full!\n", queue);
+		ret = NETDEV_TX_BUSY;
+		goto out;
+	}
+
+	/* Insert TSB and checksum infos */
+	if (priv->tsb_en) {
+		ret = bcm_sysport_insert_tsb(skb, dev);
+		if (ret) {
+			ret = NETDEV_TX_OK;
+			goto out;
+		}
+	}
+
+	/* The Ethernet switch we are interfaced with needs packets to be at
+	 * least 64 bytes (including FCS) otherwise they will be discarded when
+	 * they enter the switch port logic. When Broadcom tags are enabled, we
+	 * need to make sure that packets are at least 68 bytes
+	 * (including FCS and tag) because the length verification is done after
+	 * the Broadcom tag is stripped off the ingress packet.
+	 */
+	if (skb_padto(skb, ETH_ZLEN + ENET_BRCM_TAG_LEN)) {
+		ret = NETDEV_TX_OK;
+		goto out;
+	}
+
+	skb_len = skb->len < ETH_ZLEN + ENET_BRCM_TAG_LEN ?
+			ETH_ZLEN + ENET_BRCM_TAG_LEN : skb->len;
+
+	mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE);
+	if (dma_mapping_error(kdev, mapping)) {
+		netif_err(priv, tx_err, dev, "DMA map failed at %p (len=%d)\n",
+				skb->data, skb_len);
+		ret = NETDEV_TX_OK;
+		goto out;
+	}
+
+	/* Remember the SKB for future freeing */
+	cb = &ring->cbs[ring->curr_desc];
+	cb->skb = skb;
+	dma_unmap_addr_set(cb, dma_addr, mapping);
+	dma_unmap_len_set(cb, dma_len, skb_len);
+
+	/* Fetch a descriptor entry from our pool */
+	desc = ring->desc_cpu;
+
+	desc->addr_lo = lower_32_bits(mapping);
+	len_status = upper_32_bits(mapping) & DESC_ADDR_HI_MASK;
+	len_status |= (skb_len << DESC_LEN_SHIFT);
+	len_status |= (DESC_SOP | DESC_EOP | TX_STATUS_APP_CRC) <<
+			DESC_STATUS_SHIFT;
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		len_status |= (DESC_L4_CSUM << DESC_STATUS_SHIFT);
+
+	ring->curr_desc++;
+	if (ring->curr_desc == ring->size)
+		ring->curr_desc = 0;
+	ring->desc_count--;
+
+	/* Ensure write completion of the descriptor status/length
+	 * in DRAM before the System Port WRITE_PORT register latches
+	 * the value
+	 */
+	wmb();
+	desc->addr_status_len = len_status;
+	wmb();
+
+	/* Write this descriptor address to the RING write port */
+	tdma_port_write_desc_addr(priv, desc, ring->index);
+
+	/* Check ring space and update SW control flow */
+	if (ring->desc_count == 0)
+		netif_tx_stop_queue(txq);
+
+	netif_dbg(priv, tx_queued, dev, "ring=%d desc_count=%d, curr_desc=%d\n",
+			ring->index, ring->desc_count, ring->curr_desc);
+
+	ret = NETDEV_TX_OK;
+out:
+	spin_unlock_irqrestore(&ring->lock, flags);
+	return ret;
+}
+
+static void bcm_sysport_tx_timeout(struct net_device *dev)
+{
+	netdev_warn(dev, "transmit timeout!\n");
+
+	dev->trans_start = jiffies;
+	dev->stats.tx_errors++;
+
+	netif_tx_wake_all_queues(dev);
+}
+
+/* phylib adjust link callback */
+static void bcm_sysport_adj_link(struct net_device *dev)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	struct phy_device *phydev = priv->phydev;
+	unsigned int changed = 0;
+	u32 cmd_bits = 0, reg;
+
+	if (priv->old_link != phydev->link) {
+		changed = 1;
+		priv->old_link = phydev->link;
+	}
+
+	if (priv->old_duplex != phydev->duplex) {
+		changed = 1;
+		priv->old_duplex = phydev->duplex;
+	}
+
+	switch (phydev->speed) {
+	case SPEED_2500:
+		cmd_bits = CMD_SPEED_2500;
+		break;
+	case SPEED_1000:
+		cmd_bits = CMD_SPEED_1000;
+		break;
+	case SPEED_100:
+		cmd_bits = CMD_SPEED_100;
+		break;
+	case SPEED_10:
+		cmd_bits = CMD_SPEED_10;
+		break;
+	default:
+		break;
+	}
+	cmd_bits <<= CMD_SPEED_SHIFT;
+
+	if (phydev->duplex == DUPLEX_HALF)
+		cmd_bits |= CMD_HD_EN;
+
+	if (priv->old_pause != phydev->pause) {
+		changed = 1;
+		priv->old_pause = phydev->pause;
+	}
+
+	if (!phydev->pause)
+		cmd_bits |= CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE;
+
+	if (changed) {
+		reg = umac_readl(priv, UMAC_CMD);
+		reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) |
+			CMD_HD_EN | CMD_RX_PAUSE_IGNORE |
+			CMD_TX_PAUSE_IGNORE);
+		reg |= cmd_bits;
+		umac_writel(priv, reg, UMAC_CMD);
+
+		phy_print_status(priv->phydev);
+	}
+}
+
+static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
+				    unsigned int index)
+{
+	struct bcm_sysport_tx_ring *ring = &priv->tx_rings[index];
+	struct device *kdev = &priv->pdev->dev;
+	size_t size;
+	void *p;
+	u32 reg;
+
+	/* Simple descriptors partitioning for now */
+	size = 256;
+
+	/* We just need one DMA descriptor which is DMA-able, since writing to
+	 * the port will allocate a new descriptor in its internal linked-list
+	 */
+	p = dma_zalloc_coherent(kdev, 1, &ring->desc_dma, GFP_KERNEL);
+	if (!p) {
+		netif_err(priv, hw, priv->netdev, "DMA alloc failed\n");
+		return -ENOMEM;
+	}
+
+	ring->cbs = kzalloc(sizeof(struct bcm_sysport_cb) * size, GFP_KERNEL);
+	if (!ring->cbs) {
+		netif_err(priv, hw, priv->netdev, "CB allocation failed\n");
+		return -ENOMEM;
+	}
+
+	/* Initialize SW view of the ring */
+	spin_lock_init(&ring->lock);
+	ring->priv = priv;
+	netif_napi_add(priv->netdev, &ring->napi, bcm_sysport_tx_poll, 64);
+	ring->index = index;
+	ring->size = size;
+	ring->alloc_size = ring->size;
+	ring->desc_cpu = p;
+	ring->desc_count = ring->size;
+	ring->curr_desc = 0;
+
+	/* Initialize HW ring */
+	tdma_writel(priv, RING_EN, TDMA_DESC_RING_HEAD_TAIL_PTR(index));
+	tdma_writel(priv, 0, TDMA_DESC_RING_COUNT(index));
+	tdma_writel(priv, 1, TDMA_DESC_RING_INTR_CONTROL(index));
+	tdma_writel(priv, 0, TDMA_DESC_RING_PROD_CONS_INDEX(index));
+	tdma_writel(priv, RING_IGNORE_STATUS, TDMA_DESC_RING_MAPPING(index));
+	tdma_writel(priv, 0, TDMA_DESC_RING_PCP_DEI_VID(index));
+
+	/* Program the number of descriptors as MAX_THRESHOLD and half of
+	 * its size for the hysteresis trigger
+	 */
+	tdma_writel(priv, ring->size |
+			1 << RING_HYST_THRESH_SHIFT,
+			TDMA_DESC_RING_MAX_HYST(index));
+
+	/* Enable the ring queue in the arbiter */
+	reg = tdma_readl(priv, TDMA_TIER1_ARB_0_QUEUE_EN);
+	reg |= (1 << index);
+	tdma_writel(priv, reg, TDMA_TIER1_ARB_0_QUEUE_EN);
+
+	napi_enable(&ring->napi);
+
+	netif_dbg(priv, hw, priv->netdev,
+			"TDMA cfg, size=%d, desc_cpu=%p\n",
+			ring->size, ring->desc_cpu);
+
+	return 0;
+}
+
+static void bcm_sysport_fini_tx_ring(struct bcm_sysport_priv *priv,
+					unsigned int index)
+{
+	struct bcm_sysport_tx_ring *ring = &priv->tx_rings[index];
+	struct device *kdev = &priv->pdev->dev;
+	u32 reg;
+
+	/* Caller should stop the TDMA engine */
+	reg = tdma_readl(priv, TDMA_STATUS);
+	if (!(reg & TDMA_DISABLED))
+		netdev_warn(priv->netdev, "TDMA not stopped!\n");
+
+	napi_disable(&ring->napi);
+	netif_napi_del(&ring->napi);
+
+	bcm_sysport_tx_reclaim(priv, ring);
+
+	kfree(ring->cbs);
+	ring->cbs = NULL;
+
+	if (ring->desc_dma) {
+		dma_free_coherent(kdev, 1, ring->desc_cpu, ring->desc_dma);
+		ring->desc_dma = 0;
+	}
+	ring->size = 0;
+	ring->alloc_size = 0;
+
+	netif_dbg(priv, hw, priv->netdev, "TDMA fini done\n");
+}
+
+/* RDMA helper */
+static inline int rdma_enable_set(struct bcm_sysport_priv *priv,
+					unsigned int enable)
+{
+	unsigned int timeout = 1000;
+	u32 reg;
+
+	reg = rdma_readl(priv, RDMA_CONTROL);
+	if (enable)
+		reg |= RDMA_EN;
+	else
+		reg &= ~RDMA_EN;
+	rdma_writel(priv, reg, RDMA_CONTROL);
+
+	/* Poll for RMDA disabling completion */
+	do {
+		reg = rdma_readl(priv, RDMA_STATUS);
+		if (!!(reg & RDMA_DISABLED) == !enable)
+			return 0;
+		usleep_range(1000, 2000);
+	} while (timeout-- > 0);
+
+	netdev_err(priv->netdev, "timeout waiting for RDMA to finish\n");
+
+	return -ETIMEDOUT;
+}
+
+/* TDMA helper */
+static inline int tdma_enable_set(struct bcm_sysport_priv *priv,
+					unsigned int enable)
+{
+	unsigned int timeout = 1000;
+	u32 reg;
+
+	reg = tdma_readl(priv, TDMA_CONTROL);
+	if (enable)
+		reg |= TDMA_EN;
+	else
+		reg &= ~TDMA_EN;
+	tdma_writel(priv, reg, TDMA_CONTROL);
+
+	/* Poll for TMDA disabling completion */
+	do {
+		reg = tdma_readl(priv, TDMA_STATUS);
+		if (!!(reg & TDMA_DISABLED) == !enable)
+			return 0;
+
+		usleep_range(1000, 2000);
+	} while (timeout-- > 0);
+
+	netdev_err(priv->netdev, "timeout waiting for TDMA to finish\n");
+
+	return -ETIMEDOUT;
+}
+
+static int bcm_sysport_init_rx_ring(struct bcm_sysport_priv *priv)
+{
+	u32 reg;
+	int ret;
+
+	/* Initialize SW view of the RX ring */
+	priv->num_rx_bds = NUM_RX_DESC;
+	priv->rx_bds = priv->base + SYS_PORT_RDMA_OFFSET;
+	priv->rx_bd_assign_ptr = priv->rx_bds;
+	priv->rx_bd_assign_index = 0;
+	priv->rx_c_index = 0;
+	priv->rx_read_ptr = 0;
+	priv->rx_cbs = kzalloc(priv->num_rx_bds *
+				sizeof(struct bcm_sysport_cb), GFP_KERNEL);
+	if (!priv->rx_cbs) {
+		netif_err(priv, hw, priv->netdev, "CB allocation failed\n");
+		return -ENOMEM;
+	}
+
+	ret = bcm_sysport_alloc_rx_bufs(priv);
+	if (ret) {
+		netif_err(priv, hw, priv->netdev, "SKB allocation failed\n");
+		return ret;
+	}
+
+	/* Initialize HW, ensure RDMA is disabled */
+	reg = rdma_readl(priv, RDMA_STATUS);
+	if (!(reg & RDMA_DISABLED))
+		rdma_enable_set(priv, 0);
+
+	rdma_writel(priv, 0, RDMA_WRITE_PTR_LO);
+	rdma_writel(priv, 0, RDMA_WRITE_PTR_HI);
+	rdma_writel(priv, 0, RDMA_PROD_INDEX);
+	rdma_writel(priv, 0, RDMA_CONS_INDEX);
+	rdma_writel(priv, priv->num_rx_bds << RDMA_RING_SIZE_SHIFT |
+			  RX_BUF_LENGTH, RDMA_RING_BUF_SIZE);
+	/* Operate the queue in ring mode */
+	rdma_writel(priv, 0, RDMA_START_ADDR_HI);
+	rdma_writel(priv, 0, RDMA_START_ADDR_LO);
+	rdma_writel(priv, 0, RDMA_END_ADDR_HI);
+	rdma_writel(priv, NUM_HW_RX_DESC_WORDS - 1, RDMA_END_ADDR_LO);
+
+	rdma_writel(priv, 1, RDMA_MBDONE_INTR);
+
+	netif_dbg(priv, hw, priv->netdev,
+			"RDMA cfg, num_rx_bds=%d, rx_bds=%p\n",
+			priv->num_rx_bds, priv->rx_bds);
+
+	return 0;
+}
+
+static void bcm_sysport_fini_rx_ring(struct bcm_sysport_priv *priv)
+{
+	struct bcm_sysport_cb *cb;
+	unsigned int i;
+	u32 reg;
+
+	/* Caller should ensure RDMA is disabled */
+	reg = rdma_readl(priv, RDMA_STATUS);
+	if (!(reg & RDMA_DISABLED))
+		netdev_warn(priv->netdev, "RDMA not stopped!\n");
+
+	for (i = 0; i < priv->num_rx_bds; i++) {
+		cb = &priv->rx_cbs[i];
+		if (dma_unmap_addr(cb, dma_addr))
+			dma_unmap_single(&priv->pdev->dev,
+					dma_unmap_addr(cb, dma_addr),
+					RX_BUF_LENGTH, DMA_FROM_DEVICE);
+		bcm_sysport_free_cb(cb);
+	}
+
+	kfree(priv->rx_cbs);
+	priv->rx_cbs = NULL;
+
+	netif_dbg(priv, hw, priv->netdev, "RDMA fini done\n");
+}
+
+static void bcm_sysport_set_rx_mode(struct net_device *dev)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	u32 reg;
+
+	reg = umac_readl(priv, UMAC_CMD);
+	if (dev->flags & IFF_PROMISC)
+		reg |= CMD_PROMISC;
+	else
+		reg &= ~CMD_PROMISC;
+	umac_writel(priv, reg, UMAC_CMD);
+
+	/* No support for ALLMULTI */
+	if (dev->flags & IFF_ALLMULTI)
+		return;
+}
+
+static inline void umac_enable_set(struct bcm_sysport_priv *priv,
+					unsigned int enable)
+{
+	u32 reg;
+
+	reg = umac_readl(priv, UMAC_CMD);
+	if (enable)
+		reg |= CMD_RX_EN | CMD_TX_EN;
+	else
+		reg &= ~(CMD_RX_EN | CMD_TX_EN);
+	umac_writel(priv, reg, UMAC_CMD);
+
+	/* UniMAC stops on a packet boundary, wait for a full-sized packet
+	 * to be processed (1 msec).
+	 */
+	if (enable == 0)
+		usleep_range(1000, 2000);
+}
+
+static inline void umac_reset(struct bcm_sysport_priv *priv)
+{
+	u32 reg;
+
+	reg = umac_readl(priv, UMAC_CMD);
+	reg |= CMD_SW_RESET;
+	umac_writel(priv, reg, UMAC_CMD);
+	udelay(10);
+	reg = umac_readl(priv, UMAC_CMD);
+	reg &= ~CMD_SW_RESET;
+	umac_writel(priv, reg, UMAC_CMD);
+}
+
+static void umac_set_hw_addr(struct bcm_sysport_priv *priv,
+				unsigned char *addr)
+{
+	umac_writel(priv, (addr[0] << 24) | (addr[1] << 16) |
+			(addr[2] << 8) | addr[3], UMAC_MAC0);
+	umac_writel(priv, (addr[4] << 8) | addr[5], UMAC_MAC1);
+}
+
+static void topctrl_flush(struct bcm_sysport_priv *priv)
+{
+	topctrl_writel(priv, RX_FLUSH, RX_FLUSH_CNTL);
+	topctrl_writel(priv, TX_FLUSH, TX_FLUSH_CNTL);
+	mdelay(1);
+	topctrl_writel(priv, 0, RX_FLUSH_CNTL);
+	topctrl_writel(priv, 0, TX_FLUSH_CNTL);
+}
+
+static int bcm_sysport_open(struct net_device *dev)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	unsigned int i;
+	u32 reg;
+	int ret;
+
+	/* Reset UniMAC */
+	umac_reset(priv);
+
+	/* Flush TX and RX FIFOs at TOPCTRL level */
+	topctrl_flush(priv);
+
+	/* Disable the UniMAC RX/TX */
+	umac_enable_set(priv, 0);
+
+	/* Enable RBUF 2bytes alignment and Receive Status Block */
+	reg = rbuf_readl(priv, RBUF_CONTROL);
+	reg |= RBUF_4B_ALGN | RBUF_RSB_EN;
+	rbuf_writel(priv, reg, RBUF_CONTROL);
+
+	/* Set maximum frame length */
+	umac_writel(priv, UMAC_MAX_MTU_SIZE, UMAC_MAX_FRAME_LEN);
+
+	/* Set MAC address */
+	umac_set_hw_addr(priv, dev->dev_addr);
+
+	/* Read CRC forward */
+	priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD);
+
+	priv->phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
+					0, priv->phy_interface);
+	if (!priv->phydev) {
+		netdev_err(dev, "could not attach to PHY\n");
+		return -ENODEV;
+	}
+
+	/* Reset house keeping link status */
+	priv->old_duplex = -1;
+	priv->old_link = -1;
+	priv->old_pause = -1;
+
+	/* mask all interrupts and request them */
+	intrl2_0_writel(priv, 0xffffffff, INTRL2_CPU_MASK_SET);
+	intrl2_0_writel(priv, 0xffffffff, INTRL2_CPU_CLEAR);
+	intrl2_0_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
+	intrl2_1_writel(priv, 0xffffffff, INTRL2_CPU_MASK_SET);
+	intrl2_1_writel(priv, 0xffffffff, INTRL2_CPU_CLEAR);
+	intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
+
+	ret = request_irq(priv->irq0, bcm_sysport_rx_isr, 0, dev->name, dev);
+	if (ret) {
+		netdev_err(dev, "failed to request RX interrupt\n");
+		goto out_phy_disconnect;
+	}
+
+	ret = request_irq(priv->irq1, bcm_sysport_tx_isr, 0, dev->name, dev);
+	if (ret) {
+		netdev_err(dev, "failed to request TX interrupt\n");
+		goto out_free_irq0;
+	}
+
+	/* Initialize both hardware and software ring */
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		ret = bcm_sysport_init_tx_ring(priv, i);
+		if (ret) {
+			netdev_err(dev, "failed to initialize TX ring %d\n",
+					i);
+			goto out_free_tx_ring;
+		}
+	}
+
+	/* Initialize linked-list */
+	tdma_writel(priv, TDMA_LL_RAM_INIT_BUSY, TDMA_STATUS);
+
+	/* Initialize RX ring */
+	ret = bcm_sysport_init_rx_ring(priv);
+	if (ret) {
+		netdev_err(dev, "failed to initialize RX ring\n");
+		goto out_free_rx_ring;
+	}
+
+	/* Turn on RDMA */
+	ret = rdma_enable_set(priv, 1);
+	if (ret)
+		goto out_free_rx_ring;
+
+	/* Enable RX interrupt and TX ring full interrupt */
+	intrl2_0_mask_clear(priv, INTRL2_0_RDMA_MBDONE | INTRL2_0_TX_RING_FULL);
+
+	/* Turn on TDMA */
+	ret = tdma_enable_set(priv, 1);
+	if (ret)
+		goto out_clear_rx_int;
+
+	/* Enable NAPI */
+	napi_enable(&priv->napi);
+
+	/* Turn on UniMAC TX/RX */
+	umac_enable_set(priv, 1);
+
+	phy_start(priv->phydev);
+
+	/* Enable TX interrupts for the 32 TXQs */
+	intrl2_1_mask_clear(priv, 0xffffffff);
+
+	/* Last call before we start the real business */
+	netif_tx_start_all_queues(dev);
+
+	return 0;
+
+out_clear_rx_int:
+	intrl2_0_mask_set(priv, INTRL2_0_RDMA_MBDONE | INTRL2_0_TX_RING_FULL);
+out_free_rx_ring:
+	bcm_sysport_fini_rx_ring(priv);
+out_free_tx_ring:
+	for (i = 0; i < dev->num_tx_queues; i++)
+		bcm_sysport_fini_tx_ring(priv, i);
+	free_irq(priv->irq1, dev);
+out_free_irq0:
+	free_irq(priv->irq0, dev);
+out_phy_disconnect:
+	phy_disconnect(priv->phydev);
+	return ret;
+}
+
+static int bcm_sysport_stop(struct net_device *dev)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	unsigned int i;
+	u32 reg;
+	int ret;
+
+	/* stop all software from updating hardware */
+	netif_tx_stop_all_queues(dev);
+	napi_disable(&priv->napi);
+	phy_stop(priv->phydev);
+
+	/* mask all interrupts */
+	intrl2_0_mask_set(priv, 0xffffffff);
+	intrl2_0_writel(priv, 0xffffffff, INTRL2_CPU_CLEAR);
+	intrl2_1_mask_set(priv, 0xffffffff);
+	intrl2_1_writel(priv, 0xffffffff, INTRL2_CPU_CLEAR);
+
+	/* Disable UniMAC RX */
+	reg = umac_readl(priv, UMAC_CMD);
+	reg &= ~CMD_RX_EN;
+	umac_writel(priv, reg, UMAC_CMD);
+
+	ret = tdma_enable_set(priv, 0);
+	if (ret) {
+		netdev_err(dev, "timeout disabling RDMA\n");
+		return ret;
+	}
+
+	/* Wait for a maximum packet size to be drained */
+	usleep_range(2000, 3000);
+
+	ret = rdma_enable_set(priv, 0);
+	if (ret) {
+		netdev_err(dev, "timeout disabling TDMA\n");
+		return ret;
+	}
+
+	/* Disable UniMAC TX */
+	reg = umac_readl(priv, UMAC_CMD);
+	reg &= ~CMD_TX_EN;
+	umac_writel(priv, reg, UMAC_CMD);
+
+	/* Free RX/TX rings SW structures */
+	for (i = 0; i < dev->num_tx_queues; i++)
+		bcm_sysport_fini_tx_ring(priv, i);
+	bcm_sysport_fini_rx_ring(priv);
+
+	free_irq(priv->irq0, dev);
+	free_irq(priv->irq1, dev);
+
+	/* Disconnect from PHY */
+	phy_disconnect(priv->phydev);
+
+	return 0;
+}
+
+static struct ethtool_ops bcm_sysport_ethtool_ops = {
+	.get_settings		= bcm_sysport_get_settings,
+	.set_settings		= bcm_sysport_set_settings,
+	.get_drvinfo		= bcm_sysport_get_drvinfo,
+	.get_msglevel		= bcm_sysport_get_msglvl,
+	.set_msglevel		= bcm_sysport_set_msglvl,
+	.get_link		= ethtool_op_get_link,
+	.get_strings		= bcm_sysport_get_strings,
+	.get_ethtool_stats	= bcm_sysport_get_stats,
+	.get_sset_count		= bcm_sysport_get_sset_count,
+};
+
+static const struct net_device_ops bcm_sysport_netdev_ops = {
+	.ndo_start_xmit		= bcm_sysport_xmit,
+	.ndo_tx_timeout		= bcm_sysport_tx_timeout,
+	.ndo_open		= bcm_sysport_open,
+	.ndo_stop		= bcm_sysport_stop,
+	.ndo_set_features	= bcm_sysport_set_features,
+	.ndo_set_rx_mode	= bcm_sysport_set_rx_mode,
+};
+
+#define REV_FMT	"v%2x.%02x"
+
+static int bcm_sysport_probe(struct platform_device *pdev)
+{
+	struct bcm_sysport_priv *priv;
+	struct device_node *dn;
+	struct net_device *dev;
+	const void *macaddr;
+	struct resource *r;
+	u32 txq, rxq;
+	int ret;
+
+	dn = pdev->dev.of_node;
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	/* Read the Transmit/Receive Queue properties */
+	if (of_property_read_u32(dn, "systemport,num-txq", &txq))
+		txq = TDMA_NUM_RINGS;
+	if (of_property_read_u32(dn, "systemport,num-rxq", &rxq))
+		rxq = 1;
+
+	dev = alloc_etherdev_mqs(sizeof(*priv), txq, rxq);
+	if (!dev)
+		return -ENOMEM;
+
+	/* Initialize private members */
+	priv = netdev_priv(dev);
+
+	priv->irq0 = platform_get_irq(pdev, 0);
+	priv->irq1 = platform_get_irq(pdev, 1);
+	if (priv->irq0 <= 0 || priv->irq1 <= 0) {
+		dev_err(&pdev->dev, "invalid interrupts\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	priv->base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(priv->base)) {
+		ret = PTR_ERR(priv->base);
+		goto err;
+	}
+
+	priv->netdev = dev;
+	priv->pdev = pdev;
+
+	priv->phy_interface = of_get_phy_mode(dn);
+	/* Default to GMII interface mode */
+	if (priv->phy_interface < 0)
+		priv->phy_interface = PHY_INTERFACE_MODE_GMII;
+
+	/* In the case of a fixed PHY, the DT node associated
+	 * to the PHY is the Ethernet MAC DT node.
+	 */
+	if (of_phy_is_fixed_link(dn)) {
+		ret = of_phy_register_fixed_link(dn);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to register fixed PHY\n");
+			goto err;
+		}
+
+		priv->phy_dn = dn;
+	}
+
+	/* Initialize netdevice members */
+	macaddr = of_get_mac_address(dn);
+	if (!macaddr || !is_valid_ether_addr(macaddr)) {
+		dev_warn(&pdev->dev, "using random Ethernet MAC\n");
+		random_ether_addr(dev->dev_addr);
+	} else {
+		ether_addr_copy(dev->dev_addr, macaddr);
+	}
+
+	SET_NETDEV_DEV(dev, &pdev->dev);
+	dev_set_drvdata(&pdev->dev, dev);
+	dev->ethtool_ops = &bcm_sysport_ethtool_ops;
+	dev->netdev_ops = &bcm_sysport_netdev_ops;
+	netif_napi_add(dev, &priv->napi, bcm_sysport_poll, 64);
+
+	/* HW supported features, none enabled by default */
+	dev->hw_features |= NETIF_F_RXCSUM | NETIF_F_HIGHDMA |
+				NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+
+	/* Set the needed headroom once and for all */
+	BUILD_BUG_ON(sizeof(struct bcm_tsb) != 8);
+	dev->needed_headroom += sizeof(struct bcm_tsb);
+
+	/* libphy will adjust the link state accordingly */
+	netif_carrier_off(dev);
+
+	ret = register_netdev(dev);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register net_device\n");
+		goto err;
+	}
+
+	priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK;
+	dev_info(&pdev->dev,
+		"Broadcom SYSTEMPORT" REV_FMT
+		" at 0x%p (irqs: %d, %d, TXQs: %d, RXQs: %d)\n",
+		(priv->rev >> 8) & 0xff, priv->rev & 0xff,
+		priv->base, priv->irq0, priv->irq1, txq, rxq);
+
+	return 0;
+err:
+	free_netdev(dev);
+	return ret;
+}
+
+static int bcm_sysport_remove(struct platform_device *pdev)
+{
+	struct net_device *dev = dev_get_drvdata(&pdev->dev);
+
+	/* Not much to do, ndo_close has been called
+	 * and we use managed allocations
+	 */
+	unregister_netdev(dev);
+	free_netdev(dev);
+	dev_set_drvdata(&pdev->dev, NULL);
+
+	return 0;
+}
+
+static const struct of_device_id bcm_sysport_of_match[] = {
+	{ .compatible = "brcm,systemport-v1.00" },
+	{ .compatible = "brcm,systemport" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver bcm_sysport_driver = {
+	.probe	= bcm_sysport_probe,
+	.remove	= bcm_sysport_remove,
+	.driver =  {
+		.name = "brcm-systemport",
+		.owner = THIS_MODULE,
+		.of_match_table = bcm_sysport_of_match,
+	},
+};
+module_platform_driver(bcm_sysport_driver);
+
+MODULE_AUTHOR("Broadcom Corporation");
+MODULE_DESCRIPTION("Broadcom System Port Ethernet MAC driver");
+MODULE_ALIAS("platform:brcm-systemport");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
new file mode 100644
index 00000000000..281c0824603
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -0,0 +1,678 @@
+/*
+ * Broadcom BCM7xxx System Port Ethernet MAC driver
+ *
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __BCM_SYSPORT_H
+#define __BCM_SYSPORT_H
+
+#include <linux/if_vlan.h>
+
+/* Receive/transmit descriptor format */
+#define DESC_ADDR_HI_STATUS_LEN	0x00
+#define  DESC_ADDR_HI_SHIFT	0
+#define  DESC_ADDR_HI_MASK	0xff
+#define  DESC_STATUS_SHIFT	8
+#define  DESC_STATUS_MASK	0x3ff
+#define  DESC_LEN_SHIFT		18
+#define  DESC_LEN_MASK		0x7fff
+#define DESC_ADDR_LO		0x04
+
+/* HW supports 40-bit addressing hence the */
+#define DESC_SIZE		(WORDS_PER_DESC * sizeof(u32))
+
+/* Default RX buffer allocation size */
+#define RX_BUF_LENGTH		2048
+
+/* Body(1500) + EH_SIZE(14) + VLANTAG(4) + BRCMTAG(4) + FCS(4) = 1526.
+ * 1536 is multiple of 256 bytes
+ */
+#define ENET_BRCM_TAG_LEN	4
+#define ENET_PAD		10
+#define UMAC_MAX_MTU_SIZE	(ETH_DATA_LEN + ETH_HLEN + VLAN_HLEN + \
+				 ENET_BRCM_TAG_LEN + ETH_FCS_LEN + ENET_PAD)
+
+/* Transmit status block */
+struct bcm_tsb {
+	u32 pcp_dei_vid;
+#define PCP_DEI_MASK		0xf
+#define VID_SHIFT		4
+#define VID_MASK		0xfff
+	u32 l4_ptr_dest_map;
+#define L4_CSUM_PTR_MASK	0x1ff
+#define L4_PTR_SHIFT		9
+#define L4_PTR_MASK		0x1ff
+#define L4_UDP			(1 << 18)
+#define L4_LENGTH_VALID		(1 << 19)
+#define DEST_MAP_SHIFT		20
+#define DEST_MAP_MASK		0x1ff
+};
+
+/* Receive status block uses the same
+ * definitions as the DMA descriptor
+ */
+struct bcm_rsb {
+	u32 rx_status_len;
+	u32 brcm_egress_tag;
+};
+
+/* Common Receive/Transmit status bits */
+#define DESC_L4_CSUM		(1 << 7)
+#define DESC_SOP		(1 << 8)
+#define DESC_EOP		(1 << 9)
+
+/* Receive Status bits */
+#define RX_STATUS_UCAST			0
+#define RX_STATUS_BCAST			0x04
+#define RX_STATUS_MCAST			0x08
+#define RX_STATUS_L2_MCAST		0x0c
+#define RX_STATUS_ERR			(1 << 4)
+#define RX_STATUS_OVFLOW		(1 << 5)
+#define RX_STATUS_PARSE_FAIL		(1 << 6)
+
+/* Transmit Status bits */
+#define TX_STATUS_VLAN_NO_ACT		0x00
+#define TX_STATUS_VLAN_PCP_TSB		0x01
+#define TX_STATUS_VLAN_QUEUE		0x02
+#define TX_STATUS_VLAN_VID_TSB		0x03
+#define TX_STATUS_OWR_CRC		(1 << 2)
+#define TX_STATUS_APP_CRC		(1 << 3)
+#define TX_STATUS_BRCM_TAG_NO_ACT	0
+#define TX_STATUS_BRCM_TAG_ZERO		0x10
+#define TX_STATUS_BRCM_TAG_ONE_QUEUE	0x20
+#define TX_STATUS_BRCM_TAG_ONE_TSB	0x30
+#define TX_STATUS_SKIP_BYTES		(1 << 6)
+
+/* Specific register definitions */
+#define SYS_PORT_TOPCTRL_OFFSET		0
+#define REV_CNTL			0x00
+#define  REV_MASK			0xffff
+
+#define RX_FLUSH_CNTL			0x04
+#define  RX_FLUSH			(1 << 0)
+
+#define TX_FLUSH_CNTL			0x08
+#define  TX_FLUSH			(1 << 0)
+
+#define MISC_CNTL			0x0c
+#define  SYS_CLK_SEL			(1 << 0)
+#define  TDMA_EOP_SEL			(1 << 1)
+
+/* Level-2 Interrupt controller offsets and defines */
+#define SYS_PORT_INTRL2_0_OFFSET	0x200
+#define SYS_PORT_INTRL2_1_OFFSET	0x240
+#define INTRL2_CPU_STATUS		0x00
+#define INTRL2_CPU_SET			0x04
+#define INTRL2_CPU_CLEAR		0x08
+#define INTRL2_CPU_MASK_STATUS		0x0c
+#define INTRL2_CPU_MASK_SET		0x10
+#define INTRL2_CPU_MASK_CLEAR		0x14
+
+/* Level-2 instance 0 interrupt bits */
+#define INTRL2_0_GISB_ERR		(1 << 0)
+#define INTRL2_0_RBUF_OVFLOW		(1 << 1)
+#define INTRL2_0_TBUF_UNDFLOW		(1 << 2)
+#define INTRL2_0_MPD			(1 << 3)
+#define INTRL2_0_BRCM_MATCH_TAG		(1 << 4)
+#define INTRL2_0_RDMA_MBDONE		(1 << 5)
+#define INTRL2_0_OVER_MAX_THRESH	(1 << 6)
+#define INTRL2_0_BELOW_HYST_THRESH	(1 << 7)
+#define INTRL2_0_FREE_LIST_EMPTY	(1 << 8)
+#define INTRL2_0_TX_RING_FULL		(1 << 9)
+#define INTRL2_0_DESC_ALLOC_ERR		(1 << 10)
+#define INTRL2_0_UNEXP_PKTSIZE_ACK	(1 << 11)
+
+/* RXCHK offset and defines */
+#define SYS_PORT_RXCHK_OFFSET		0x300
+
+#define RXCHK_CONTROL			0x00
+#define  RXCHK_EN			(1 << 0)
+#define  RXCHK_SKIP_FCS			(1 << 1)
+#define  RXCHK_BAD_CSUM_DIS		(1 << 2)
+#define  RXCHK_BRCM_TAG_EN		(1 << 3)
+#define  RXCHK_BRCM_TAG_MATCH_SHIFT	4
+#define  RXCHK_BRCM_TAG_MATCH_MASK	0xff
+#define  RXCHK_PARSE_TNL		(1 << 12)
+#define  RXCHK_VIOL_EN			(1 << 13)
+#define  RXCHK_VIOL_DIS			(1 << 14)
+#define  RXCHK_INCOM_PKT		(1 << 15)
+#define  RXCHK_V6_DUPEXT_EN		(1 << 16)
+#define  RXCHK_V6_DUPEXT_DIS		(1 << 17)
+#define  RXCHK_ETHERTYPE_DIS		(1 << 18)
+#define  RXCHK_L2_HDR_DIS		(1 << 19)
+#define  RXCHK_L3_HDR_DIS		(1 << 20)
+#define  RXCHK_MAC_RX_ERR_DIS		(1 << 21)
+#define  RXCHK_PARSE_AUTH		(1 << 22)
+
+#define RXCHK_BRCM_TAG0			0x04
+#define RXCHK_BRCM_TAG(i)		((i) * RXCHK_BRCM_TAG0)
+#define RXCHK_BRCM_TAG0_MASK		0x24
+#define RXCHK_BRCM_TAG_MASK(i)		((i) * RXCHK_BRCM_TAG0_MASK)
+#define RXCHK_BRCM_TAG_MATCH_STATUS	0x44
+#define RXCHK_ETHERTYPE			0x48
+#define RXCHK_BAD_CSUM_CNTR		0x4C
+#define RXCHK_OTHER_DISC_CNTR		0x50
+
+/* TXCHCK offsets and defines */
+#define SYS_PORT_TXCHK_OFFSET		0x380
+#define TXCHK_PKT_RDY_THRESH		0x00
+
+/* Receive buffer offset and defines */
+#define SYS_PORT_RBUF_OFFSET		0x400
+
+#define RBUF_CONTROL			0x00
+#define  RBUF_RSB_EN			(1 << 0)
+#define  RBUF_4B_ALGN			(1 << 1)
+#define  RBUF_BRCM_TAG_STRIP		(1 << 2)
+#define  RBUF_BAD_PKT_DISC		(1 << 3)
+#define  RBUF_RESUME_THRESH_SHIFT	4
+#define  RBUF_RESUME_THRESH_MASK	0xff
+#define  RBUF_OK_TO_SEND_SHIFT		12
+#define  RBUF_OK_TO_SEND_MASK		0xff
+#define  RBUF_CRC_REPLACE		(1 << 20)
+#define  RBUF_OK_TO_SEND_MODE		(1 << 21)
+#define  RBUF_RSB_SWAP			(1 << 22)
+#define  RBUF_ACPI_EN			(1 << 23)
+
+#define RBUF_PKT_RDY_THRESH		0x04
+
+#define RBUF_STATUS			0x08
+#define  RBUF_WOL_MODE			(1 << 0)
+#define  RBUF_MPD			(1 << 1)
+#define  RBUF_ACPI			(1 << 2)
+
+#define RBUF_OVFL_DISC_CNTR		0x0c
+#define RBUF_ERR_PKT_CNTR		0x10
+
+/* Transmit buffer offset and defines */
+#define SYS_PORT_TBUF_OFFSET		0x600
+
+#define TBUF_CONTROL			0x00
+#define  TBUF_BP_EN			(1 << 0)
+#define  TBUF_MAX_PKT_THRESH_SHIFT	1
+#define  TBUF_MAX_PKT_THRESH_MASK	0x1f
+#define  TBUF_FULL_THRESH_SHIFT		8
+#define  TBUF_FULL_THRESH_MASK		0x1f
+
+/* UniMAC offset and defines */
+#define SYS_PORT_UMAC_OFFSET		0x800
+
+#define UMAC_CMD			0x008
+#define  CMD_TX_EN			(1 << 0)
+#define  CMD_RX_EN			(1 << 1)
+#define  CMD_SPEED_SHIFT		2
+#define  CMD_SPEED_10			0
+#define  CMD_SPEED_100			1
+#define  CMD_SPEED_1000			2
+#define  CMD_SPEED_2500			3
+#define  CMD_SPEED_MASK			3
+#define  CMD_PROMISC			(1 << 4)
+#define  CMD_PAD_EN			(1 << 5)
+#define  CMD_CRC_FWD			(1 << 6)
+#define  CMD_PAUSE_FWD			(1 << 7)
+#define  CMD_RX_PAUSE_IGNORE		(1 << 8)
+#define  CMD_TX_ADDR_INS		(1 << 9)
+#define  CMD_HD_EN			(1 << 10)
+#define  CMD_SW_RESET			(1 << 13)
+#define  CMD_LCL_LOOP_EN		(1 << 15)
+#define  CMD_AUTO_CONFIG		(1 << 22)
+#define  CMD_CNTL_FRM_EN		(1 << 23)
+#define  CMD_NO_LEN_CHK			(1 << 24)
+#define  CMD_RMT_LOOP_EN		(1 << 25)
+#define  CMD_PRBL_EN			(1 << 27)
+#define  CMD_TX_PAUSE_IGNORE		(1 << 28)
+#define  CMD_TX_RX_EN			(1 << 29)
+#define  CMD_RUNT_FILTER_DIS		(1 << 30)
+
+#define UMAC_MAC0			0x00c
+#define UMAC_MAC1			0x010
+#define UMAC_MAX_FRAME_LEN		0x014
+
+#define UMAC_TX_FLUSH			0x334
+
+#define UMAC_MIB_START			0x400
+
+/* There is a 0xC gap between the end of RX and beginning of TX stats and then
+ * between the end of TX stats and the beginning of the RX RUNT
+ */
+#define UMAC_MIB_STAT_OFFSET		0xc
+
+#define UMAC_MIB_CTRL			0x580
+#define  MIB_RX_CNT_RST			(1 << 0)
+#define  MIB_RUNT_CNT_RST		(1 << 1)
+#define  MIB_TX_CNT_RST			(1 << 2)
+#define UMAC_MDF_CTRL			0x650
+#define UMAC_MDF_ADDR			0x654
+
+/* Receive DMA offset and defines */
+#define SYS_PORT_RDMA_OFFSET		0x2000
+
+#define RDMA_CONTROL			0x1000
+#define  RDMA_EN			(1 << 0)
+#define  RDMA_RING_CFG			(1 << 1)
+#define  RDMA_DISC_EN			(1 << 2)
+#define  RDMA_BUF_DATA_OFFSET_SHIFT	4
+#define  RDMA_BUF_DATA_OFFSET_MASK	0x3ff
+
+#define RDMA_STATUS			0x1004
+#define  RDMA_DISABLED			(1 << 0)
+#define  RDMA_DESC_RAM_INIT_BUSY	(1 << 1)
+#define  RDMA_BP_STATUS			(1 << 2)
+
+#define RDMA_SCB_BURST_SIZE		0x1008
+
+#define RDMA_RING_BUF_SIZE		0x100c
+#define  RDMA_RING_SIZE_SHIFT		16
+
+#define RDMA_WRITE_PTR_HI		0x1010
+#define RDMA_WRITE_PTR_LO		0x1014
+#define RDMA_PROD_INDEX			0x1018
+#define  RDMA_PROD_INDEX_MASK		0xffff
+
+#define RDMA_CONS_INDEX			0x101c
+#define  RDMA_CONS_INDEX_MASK		0xffff
+
+#define RDMA_START_ADDR_HI		0x1020
+#define RDMA_START_ADDR_LO		0x1024
+#define RDMA_END_ADDR_HI		0x1028
+#define RDMA_END_ADDR_LO		0x102c
+
+#define RDMA_MBDONE_INTR		0x1030
+#define  RDMA_INTR_THRESH_MASK		0xff
+#define  RDMA_TIMEOUT_SHIFT		16
+#define  RDMA_TIMEOUT_MASK		0xffff
+
+#define RDMA_XON_XOFF_THRESH		0x1034
+#define  RDMA_XON_XOFF_THRESH_MASK	0xffff
+#define  RDMA_XOFF_THRESH_SHIFT		16
+
+#define RDMA_READ_PTR_HI		0x1038
+#define RDMA_READ_PTR_LO		0x103c
+
+#define RDMA_OVERRIDE			0x1040
+#define  RDMA_LE_MODE			(1 << 0)
+#define  RDMA_REG_MODE			(1 << 1)
+
+#define RDMA_TEST			0x1044
+#define  RDMA_TP_OUT_SEL		(1 << 0)
+#define  RDMA_MEM_SEL			(1 << 1)
+
+#define RDMA_DEBUG			0x1048
+
+/* Transmit DMA offset and defines */
+#define TDMA_NUM_RINGS			32	/* rings = queues */
+#define TDMA_PORT_SIZE			DESC_SIZE /* two 32-bits words */
+
+#define SYS_PORT_TDMA_OFFSET		0x4000
+#define TDMA_WRITE_PORT_OFFSET		0x0000
+#define TDMA_WRITE_PORT_HI(i)		(TDMA_WRITE_PORT_OFFSET + \
+					(i) * TDMA_PORT_SIZE)
+#define TDMA_WRITE_PORT_LO(i)		(TDMA_WRITE_PORT_OFFSET + \
+					sizeof(u32) + (i) * TDMA_PORT_SIZE)
+
+#define TDMA_READ_PORT_OFFSET		(TDMA_WRITE_PORT_OFFSET + \
+					(TDMA_NUM_RINGS * TDMA_PORT_SIZE))
+#define TDMA_READ_PORT_HI(i)		(TDMA_READ_PORT_OFFSET + \
+					(i) * TDMA_PORT_SIZE)
+#define TDMA_READ_PORT_LO(i)		(TDMA_READ_PORT_OFFSET + \
+					sizeof(u32) + (i) * TDMA_PORT_SIZE)
+
+#define TDMA_READ_PORT_CMD_OFFSET	(TDMA_READ_PORT_OFFSET + \
+					(TDMA_NUM_RINGS * TDMA_PORT_SIZE))
+#define TDMA_READ_PORT_CMD(i)		(TDMA_READ_PORT_CMD_OFFSET + \
+					(i) * sizeof(u32))
+
+#define TDMA_DESC_RING_00_BASE		(TDMA_READ_PORT_CMD_OFFSET + \
+					(TDMA_NUM_RINGS * sizeof(u32)))
+
+/* Register offsets and defines relatives to a specific ring number */
+#define RING_HEAD_TAIL_PTR		0x00
+#define  RING_HEAD_MASK			0x7ff
+#define  RING_TAIL_SHIFT		11
+#define  RING_TAIL_MASK			0x7ff
+#define  RING_FLUSH			(1 << 24)
+#define  RING_EN			(1 << 25)
+
+#define RING_COUNT			0x04
+#define  RING_COUNT_MASK		0x7ff
+#define  RING_BUFF_DONE_SHIFT		11
+#define  RING_BUFF_DONE_MASK		0x7ff
+
+#define RING_MAX_HYST			0x08
+#define  RING_MAX_THRESH_MASK		0x7ff
+#define  RING_HYST_THRESH_SHIFT		11
+#define  RING_HYST_THRESH_MASK		0x7ff
+
+#define RING_INTR_CONTROL		0x0c
+#define  RING_INTR_THRESH_MASK		0x7ff
+#define  RING_EMPTY_INTR_EN		(1 << 15)
+#define  RING_TIMEOUT_SHIFT		16
+#define  RING_TIMEOUT_MASK		0xffff
+
+#define RING_PROD_CONS_INDEX		0x10
+#define  RING_PROD_INDEX_MASK		0xffff
+#define  RING_CONS_INDEX_SHIFT		16
+#define  RING_CONS_INDEX_MASK		0xffff
+
+#define RING_MAPPING			0x14
+#define  RING_QID_MASK			0x3
+#define  RING_PORT_ID_SHIFT		3
+#define  RING_PORT_ID_MASK		0x7
+#define  RING_IGNORE_STATUS		(1 << 6)
+#define  RING_FAILOVER_EN		(1 << 7)
+#define  RING_CREDIT_SHIFT		8
+#define  RING_CREDIT_MASK		0xffff
+
+#define RING_PCP_DEI_VID		0x18
+#define  RING_VID_MASK			0x7ff
+#define  RING_DEI			(1 << 12)
+#define  RING_PCP_SHIFT			13
+#define  RING_PCP_MASK			0x7
+#define  RING_PKT_SIZE_ADJ_SHIFT	16
+#define  RING_PKT_SIZE_ADJ_MASK		0xf
+
+#define TDMA_DESC_RING_SIZE		28
+
+/* Defininition for a given TX ring base address */
+#define TDMA_DESC_RING_BASE(i)		(TDMA_DESC_RING_00_BASE + \
+					((i) * TDMA_DESC_RING_SIZE))
+
+/* Ring indexed register addreses */
+#define TDMA_DESC_RING_HEAD_TAIL_PTR(i)	(TDMA_DESC_RING_BASE(i) + \
+					RING_HEAD_TAIL_PTR)
+#define TDMA_DESC_RING_COUNT(i)		(TDMA_DESC_RING_BASE(i) + \
+					RING_COUNT)
+#define TDMA_DESC_RING_MAX_HYST(i)	(TDMA_DESC_RING_BASE(i) + \
+					RING_MAX_HYST)
+#define TDMA_DESC_RING_INTR_CONTROL(i)	(TDMA_DESC_RING_BASE(i) + \
+					RING_INTR_CONTROL)
+#define TDMA_DESC_RING_PROD_CONS_INDEX(i) \
+					(TDMA_DESC_RING_BASE(i) + \
+					RING_PROD_CONS_INDEX)
+#define TDMA_DESC_RING_MAPPING(i)	(TDMA_DESC_RING_BASE(i) + \
+					RING_MAPPING)
+#define TDMA_DESC_RING_PCP_DEI_VID(i)	(TDMA_DESC_RING_BASE(i) + \
+					RING_PCP_DEI_VID)
+
+#define TDMA_CONTROL			0x600
+#define  TDMA_EN			(1 << 0)
+#define  TSB_EN				(1 << 1)
+#define  TSB_SWAP			(1 << 2)
+#define  ACB_ALGO			(1 << 3)
+#define  BUF_DATA_OFFSET_SHIFT		4
+#define  BUF_DATA_OFFSET_MASK		0x3ff
+#define  VLAN_EN			(1 << 14)
+#define  SW_BRCM_TAG			(1 << 15)
+#define  WNC_KPT_SIZE_UPDATE		(1 << 16)
+#define  SYNC_PKT_SIZE			(1 << 17)
+#define  ACH_TXDONE_DELAY_SHIFT		18
+#define  ACH_TXDONE_DELAY_MASK		0xff
+
+#define TDMA_STATUS			0x604
+#define  TDMA_DISABLED			(1 << 0)
+#define  TDMA_LL_RAM_INIT_BUSY		(1 << 1)
+
+#define TDMA_SCB_BURST_SIZE		0x608
+#define TDMA_OVER_MAX_THRESH_STATUS	0x60c
+#define TDMA_OVER_HYST_THRESH_STATUS	0x610
+#define TDMA_TPID			0x614
+
+#define TDMA_FREE_LIST_HEAD_TAIL_PTR	0x618
+#define  TDMA_FREE_HEAD_MASK		0x7ff
+#define  TDMA_FREE_TAIL_SHIFT		11
+#define  TDMA_FREE_TAIL_MASK		0x7ff
+
+#define TDMA_FREE_LIST_COUNT		0x61c
+#define  TDMA_FREE_LIST_COUNT_MASK	0x7ff
+
+#define TDMA_TIER2_ARB_CTRL		0x620
+#define  TDMA_ARB_MODE_RR		0
+#define  TDMA_ARB_MODE_WEIGHT_RR	0x1
+#define  TDMA_ARB_MODE_STRICT		0x2
+#define  TDMA_ARB_MODE_DEFICIT_RR	0x3
+#define  TDMA_CREDIT_SHIFT		4
+#define  TDMA_CREDIT_MASK		0xffff
+
+#define TDMA_TIER1_ARB_0_CTRL		0x624
+#define  TDMA_ARB_EN			(1 << 0)
+
+#define TDMA_TIER1_ARB_0_QUEUE_EN	0x628
+#define TDMA_TIER1_ARB_1_CTRL		0x62c
+#define TDMA_TIER1_ARB_1_QUEUE_EN	0x630
+#define TDMA_TIER1_ARB_2_CTRL		0x634
+#define TDMA_TIER1_ARB_2_QUEUE_EN	0x638
+#define TDMA_TIER1_ARB_3_CTRL		0x63c
+#define TDMA_TIER1_ARB_3_QUEUE_EN	0x640
+
+#define TDMA_SCB_ENDIAN_OVERRIDE	0x644
+#define  TDMA_LE_MODE			(1 << 0)
+#define  TDMA_REG_MODE			(1 << 1)
+
+#define TDMA_TEST			0x648
+#define  TDMA_TP_OUT_SEL		(1 << 0)
+#define  TDMA_MEM_TM			(1 << 1)
+
+#define TDMA_DEBUG			0x64c
+
+/* Transmit/Receive descriptor */
+struct dma_desc {
+	u32	addr_status_len;
+	u32	addr_lo;
+};
+
+/* Number of Receive hardware descriptor words */
+#define NUM_HW_RX_DESC_WORDS		1024
+/* Real number of usable descriptors */
+#define NUM_RX_DESC			(NUM_HW_RX_DESC_WORDS / WORDS_PER_DESC)
+
+/* Internal linked-list RAM has up to 1536 entries */
+#define NUM_TX_DESC			1536
+
+#define WORDS_PER_DESC			(sizeof(struct dma_desc) / sizeof(u32))
+
+/* Rx/Tx common counter group.*/
+struct bcm_sysport_pkt_counters {
+	u32	cnt_64;		/* RO Received/Transmited 64 bytes packet */
+	u32	cnt_127;	/* RO Rx/Tx 127 bytes packet */
+	u32	cnt_255;	/* RO Rx/Tx 65-255 bytes packet */
+	u32	cnt_511;	/* RO Rx/Tx 256-511 bytes packet */
+	u32	cnt_1023;	/* RO Rx/Tx 512-1023 bytes packet */
+	u32	cnt_1518;	/* RO Rx/Tx 1024-1518 bytes packet */
+	u32	cnt_mgv;	/* RO Rx/Tx 1519-1522 good VLAN packet */
+	u32	cnt_2047;	/* RO Rx/Tx 1522-2047 bytes packet*/
+	u32	cnt_4095;	/* RO Rx/Tx 2048-4095 bytes packet*/
+	u32	cnt_9216;	/* RO Rx/Tx 4096-9216 bytes packet*/
+};
+
+/* RSV, Receive Status Vector */
+struct bcm_sysport_rx_counters {
+	struct  bcm_sysport_pkt_counters pkt_cnt;
+	u32	pkt;		/* RO (0x428) Received pkt count*/
+	u32	bytes;		/* RO Received byte count */
+	u32	mca;		/* RO # of Received multicast pkt */
+	u32	bca;		/* RO # of Receive broadcast pkt */
+	u32	fcs;		/* RO # of Received FCS error  */
+	u32	cf;		/* RO # of Received control frame pkt*/
+	u32	pf;		/* RO # of Received pause frame pkt */
+	u32	uo;		/* RO # of unknown op code pkt */
+	u32	aln;		/* RO # of alignment error count */
+	u32	flr;		/* RO # of frame length out of range count */
+	u32	cde;		/* RO # of code error pkt */
+	u32	fcr;		/* RO # of carrier sense error pkt */
+	u32	ovr;		/* RO # of oversize pkt*/
+	u32	jbr;		/* RO # of jabber count */
+	u32	mtue;		/* RO # of MTU error pkt*/
+	u32	pok;		/* RO # of Received good pkt */
+	u32	uc;		/* RO # of unicast pkt */
+	u32	ppp;		/* RO # of PPP pkt */
+	u32	rcrc;		/* RO (0x470),# of CRC match pkt */
+};
+
+/* TSV, Transmit Status Vector */
+struct bcm_sysport_tx_counters {
+	struct bcm_sysport_pkt_counters pkt_cnt;
+	u32	pkts;		/* RO (0x4a8) Transmited pkt */
+	u32	mca;		/* RO # of xmited multicast pkt */
+	u32	bca;		/* RO # of xmited broadcast pkt */
+	u32	pf;		/* RO # of xmited pause frame count */
+	u32	cf;		/* RO # of xmited control frame count */
+	u32	fcs;		/* RO # of xmited FCS error count */
+	u32	ovr;		/* RO # of xmited oversize pkt */
+	u32	drf;		/* RO # of xmited deferral pkt */
+	u32	edf;		/* RO # of xmited Excessive deferral pkt*/
+	u32	scl;		/* RO # of xmited single collision pkt */
+	u32	mcl;		/* RO # of xmited multiple collision pkt*/
+	u32	lcl;		/* RO # of xmited late collision pkt */
+	u32	ecl;		/* RO # of xmited excessive collision pkt*/
+	u32	frg;		/* RO # of xmited fragments pkt*/
+	u32	ncl;		/* RO # of xmited total collision count */
+	u32	jbr;		/* RO # of xmited jabber count*/
+	u32	bytes;		/* RO # of xmited byte count */
+	u32	pok;		/* RO # of xmited good pkt */
+	u32	uc;		/* RO (0x0x4f0)# of xmited unitcast pkt */
+};
+
+struct bcm_sysport_mib {
+	struct bcm_sysport_rx_counters rx;
+	struct bcm_sysport_tx_counters tx;
+	u32 rx_runt_cnt;
+	u32 rx_runt_fcs;
+	u32 rx_runt_fcs_align;
+	u32 rx_runt_bytes;
+	u32 rxchk_bad_csum;
+	u32 rxchk_other_pkt_disc;
+	u32 rbuf_ovflow_cnt;
+	u32 rbuf_err_cnt;
+};
+
+/* HW maintains a large list of counters */
+enum bcm_sysport_stat_type {
+	BCM_SYSPORT_STAT_NETDEV = -1,
+	BCM_SYSPORT_STAT_MIB_RX,
+	BCM_SYSPORT_STAT_MIB_TX,
+	BCM_SYSPORT_STAT_RUNT,
+	BCM_SYSPORT_STAT_RXCHK,
+	BCM_SYSPORT_STAT_RBUF,
+};
+
+/* Macros to help define ethtool statistics */
+#define STAT_NETDEV(m) { \
+	.stat_string = __stringify(m), \
+	.stat_sizeof = sizeof(((struct net_device_stats *)0)->m), \
+	.stat_offset = offsetof(struct net_device_stats, m), \
+	.type = BCM_SYSPORT_STAT_NETDEV, \
+}
+
+#define STAT_MIB(str, m, _type) { \
+	.stat_string = str, \
+	.stat_sizeof = sizeof(((struct bcm_sysport_priv *)0)->m), \
+	.stat_offset = offsetof(struct bcm_sysport_priv, m), \
+	.type = _type, \
+}
+
+#define STAT_MIB_RX(str, m) STAT_MIB(str, m, BCM_SYSPORT_STAT_MIB_RX)
+#define STAT_MIB_TX(str, m) STAT_MIB(str, m, BCM_SYSPORT_STAT_MIB_TX)
+#define STAT_RUNT(str, m) STAT_MIB(str, m, BCM_SYSPORT_STAT_RUNT)
+
+#define STAT_RXCHK(str, m, ofs) { \
+	.stat_string = str, \
+	.stat_sizeof = sizeof(((struct bcm_sysport_priv *)0)->m), \
+	.stat_offset = offsetof(struct bcm_sysport_priv, m), \
+	.type = BCM_SYSPORT_STAT_RXCHK, \
+	.reg_offset = ofs, \
+}
+
+#define STAT_RBUF(str, m, ofs) { \
+	.stat_string = str, \
+	.stat_sizeof = sizeof(((struct bcm_sysport_priv *)0)->m), \
+	.stat_offset = offsetof(struct bcm_sysport_priv, m), \
+	.type = BCM_SYSPORT_STAT_RBUF, \
+	.reg_offset = ofs, \
+}
+
+struct bcm_sysport_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int stat_sizeof;
+	int stat_offset;
+	enum bcm_sysport_stat_type type;
+	/* reg offset from UMAC base for misc counters */
+	u16 reg_offset;
+};
+
+/* Software house keeping helper structure */
+struct bcm_sysport_cb {
+	struct sk_buff	*skb;		/* SKB for RX packets */
+	void __iomem	*bd_addr;	/* Buffer descriptor PHYS addr */
+
+	DEFINE_DMA_UNMAP_ADDR(dma_addr);
+	DEFINE_DMA_UNMAP_LEN(dma_len);
+};
+
+/* Software view of the TX ring */
+struct bcm_sysport_tx_ring {
+	spinlock_t	lock;		/* Ring lock for tx reclaim/xmit */
+	struct napi_struct napi;	/* NAPI per tx queue */
+	dma_addr_t	desc_dma;	/* DMA cookie */
+	unsigned int	index;		/* Ring index */
+	unsigned int	size;		/* Ring current size */
+	unsigned int	alloc_size;	/* Ring one-time allocated size */
+	unsigned int	desc_count;	/* Number of descriptors */
+	unsigned int	curr_desc;	/* Current descriptor */
+	unsigned int	c_index;	/* Last consumer index */
+	unsigned int	p_index;	/* Current producer index */
+	struct bcm_sysport_cb *cbs;	/* Transmit control blocks */
+	struct dma_desc	*desc_cpu;	/* CPU view of the descriptor */
+	struct bcm_sysport_priv *priv;	/* private context backpointer */
+};
+
+/* Driver private structure */
+struct bcm_sysport_priv {
+	void __iomem		*base;
+	u32			irq0_stat;
+	u32			irq0_mask;
+	u32			irq1_stat;
+	u32			irq1_mask;
+	struct napi_struct	napi ____cacheline_aligned;
+	struct net_device	*netdev;
+	struct platform_device	*pdev;
+	int			irq0;
+	int			irq1;
+
+	/* Transmit rings */
+	struct bcm_sysport_tx_ring tx_rings[TDMA_NUM_RINGS];
+
+	/* Receive queue */
+	void __iomem		*rx_bds;
+	void __iomem		*rx_bd_assign_ptr;
+	unsigned int		rx_bd_assign_index;
+	struct bcm_sysport_cb	*rx_cbs;
+	unsigned int		num_rx_bds;
+	unsigned int		rx_read_ptr;
+	unsigned int		rx_c_index;
+
+	/* PHY device */
+	struct device_node	*phy_dn;
+	struct phy_device	*phydev;
+	phy_interface_t		phy_interface;
+	int			old_pause;
+	int			old_link;
+	int			old_duplex;
+
+	/* Misc fields */
+	unsigned int		rx_csum_en:1;
+	unsigned int		tsb_en:1;
+	unsigned int		crc_fwd:1;
+	u16			rev;
+
+	/* MIB related fields */
+	struct bcm_sysport_mib	mib;
+
+	/* Ethtool */
+	u32			msg_enable;
+};
+#endif /* __BCM_SYSPORT_H */
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 0297a79a38e..05c6af6c418 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1436,7 +1436,7 @@ static int bgmac_probe(struct bcma_device *core)
 		return -ENOMEM;
 	net_dev->netdev_ops = &bgmac_netdev_ops;
 	net_dev->irq = core->irq;
-	SET_ETHTOOL_OPS(net_dev, &bgmac_ethtool_ops);
+	net_dev->ethtool_ops = &bgmac_ethtool_ops;
 	bgmac = netdev_priv(net_dev);
 	bgmac->net_dev = net_dev;
 	bgmac->core = core;
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 0ab83708b6a..67d2b004737 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -6916,8 +6916,8 @@ bnx2_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		}
 	}
 	else {
-		ethtool_cmd_speed_set(cmd, -1);
-		cmd->duplex = -1;
+		ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
+		cmd->duplex = DUPLEX_UNKNOWN;
 	}
 	spin_unlock_bh(&bp->phy_lock);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 4d8f8aba0ea..8206a293e6b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -6,7 +6,7 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Eliezer Tamir
  * Based on code from Michael Chan's bnx2 driver
  */
@@ -346,6 +346,7 @@ struct sw_tx_bd {
 	u8		flags;
 /* Set on the first BD descriptor when there is a split BD */
 #define BNX2X_TSO_SPLIT_BD		(1<<0)
+#define BNX2X_HAS_SECOND_PBD		(1<<1)
 };
 
 struct sw_rx_page {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index dd57c7c5a3d..c43e7238de2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -6,7 +6,7 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Eliezer Tamir
  * Based on code from Michael Chan's bnx2 driver
  * UDP CSUM errata workaround by Arik Gendelman
@@ -227,6 +227,12 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 	--nbd;
 	bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
 
+	if (tx_buf->flags & BNX2X_HAS_SECOND_PBD) {
+		/* Skip second parse bd... */
+		--nbd;
+		bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
+	}
+
 	/* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */
 	if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) {
 		tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd;
@@ -797,7 +803,8 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 
 		return;
 	}
-	bnx2x_frag_free(fp, new_data);
+	if (new_data)
+		bnx2x_frag_free(fp, new_data);
 drop:
 	/* drop the packet and keep the buffer in the bin */
 	DP(NETIF_MSG_RX_STATUS,
@@ -906,6 +913,18 @@ static int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
 		bd_prod = RX_BD(bd_prod);
 		bd_cons = RX_BD(bd_cons);
 
+		/* A rmb() is required to ensure that the CQE is not read
+		 * before it is written by the adapter DMA.  PCI ordering
+		 * rules will make sure the other fields are written before
+		 * the marker at the end of struct eth_fast_path_rx_cqe
+		 * but without rmb() a weakly ordered processor can process
+		 * stale data.  Without the barrier TPA state-machine might
+		 * enter inconsistent state and kernel stack might be
+		 * provided with incorrect packet description - these lead
+		 * to various kernel crashed.
+		 */
+		rmb();
+
 		cqe_fp_flags = cqe_fp->type_error_flags;
 		cqe_fp_type = cqe_fp_flags & ETH_FAST_PATH_RX_CQE_TYPE;
 
@@ -3876,6 +3895,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			/* set encapsulation flag in start BD */
 			SET_FLAG(tx_start_bd->general_data,
 				 ETH_TX_START_BD_TUNNEL_EXIST, 1);
+
+			tx_buf->flags |= BNX2X_HAS_SECOND_PBD;
+
 			nbd++;
 		} else if (xmit_type & XMIT_CSUM) {
 			/* Set PBD in checksum offload case w/o encapsulation */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 3448cc033ca..571427c7226 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -6,7 +6,7 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Eliezer Tamir
  * Based on code from Michael Chan's bnx2 driver
  * UDP CSUM errata workaround by Arik Gendelman
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
index 97ea5421dd9..51a952c51cb 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
@@ -12,7 +12,7 @@
  * license other than the GPL, without Broadcom's express prior written
  * consent.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Dmitry Kravkov
  *
  */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h
index 804b8f64463..c6939ecb02c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h
@@ -12,7 +12,7 @@
  * license other than the GPL, without Broadcom's express prior written
  * consent.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Dmitry Kravkov
  *
  */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index b6de05e3149..25eddd90f48 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -6,7 +6,7 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Eliezer Tamir
  * Based on code from Michael Chan's bnx2 driver
  * UDP CSUM errata workaround by Arik Gendelman
@@ -379,6 +379,7 @@ static int bnx2x_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 			break;
 		case PORT_FIBRE:
 		case PORT_DA:
+		case PORT_NONE:
 			if (!(bp->port.supported[0] & SUPPORTED_FIBRE ||
 			      bp->port.supported[1] & SUPPORTED_FIBRE)) {
 				DP(BNX2X_MSG_ETHTOOL,
@@ -3316,7 +3317,7 @@ static u32 bnx2x_get_rxfh_indir_size(struct net_device *dev)
 	return T_ETH_INDIRECTION_TABLE_SIZE;
 }
 
-static int bnx2x_get_rxfh_indir(struct net_device *dev, u32 *indir)
+static int bnx2x_get_rxfh(struct net_device *dev, u32 *indir, u8 *key)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
@@ -3340,14 +3341,15 @@ static int bnx2x_get_rxfh_indir(struct net_device *dev, u32 *indir)
 	return 0;
 }
 
-static int bnx2x_set_rxfh_indir(struct net_device *dev, const u32 *indir)
+static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
+			  const u8 *key)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	size_t i;
 
 	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++) {
 		/*
-		 * The same as in bnx2x_get_rxfh_indir: we can't use a memcpy()
+		 * The same as in bnx2x_get_rxfh: we can't use a memcpy()
 		 * as an internal storage of an indirection table is a u8 array
 		 * while indir->ring_index points to an array of u32.
 		 *
@@ -3471,8 +3473,8 @@ static const struct ethtool_ops bnx2x_ethtool_ops = {
 	.get_rxnfc		= bnx2x_get_rxnfc,
 	.set_rxnfc		= bnx2x_set_rxnfc,
 	.get_rxfh_indir_size	= bnx2x_get_rxfh_indir_size,
-	.get_rxfh_indir		= bnx2x_get_rxfh_indir,
-	.set_rxfh_indir		= bnx2x_set_rxfh_indir,
+	.get_rxfh		= bnx2x_get_rxfh,
+	.set_rxfh		= bnx2x_set_rxfh,
 	.get_channels		= bnx2x_get_channels,
 	.set_channels		= bnx2x_set_channels,
 	.get_module_info	= bnx2x_get_module_info,
@@ -3498,16 +3500,14 @@ static const struct ethtool_ops bnx2x_vf_ethtool_ops = {
 	.get_rxnfc		= bnx2x_get_rxnfc,
 	.set_rxnfc		= bnx2x_set_rxnfc,
 	.get_rxfh_indir_size	= bnx2x_get_rxfh_indir_size,
-	.get_rxfh_indir		= bnx2x_get_rxfh_indir,
-	.set_rxfh_indir		= bnx2x_set_rxfh_indir,
+	.get_rxfh		= bnx2x_get_rxfh,
+	.set_rxfh		= bnx2x_set_rxfh,
 	.get_channels		= bnx2x_get_channels,
 	.set_channels		= bnx2x_set_channels,
 };
 
 void bnx2x_set_ethtool_ops(struct bnx2x *bp, struct net_device *netdev)
 {
-	if (IS_PF(bp))
-		SET_ETHTOOL_OPS(netdev, &bnx2x_ethtool_ops);
-	else /* vf */
-		SET_ETHTOOL_OPS(netdev, &bnx2x_vf_ethtool_ops);
+	netdev->ethtool_ops = (IS_PF(bp)) ?
+		&bnx2x_ethtool_ops : &bnx2x_vf_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_file_hdr.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_file_hdr.h
index f572ae164fc..8aafd9b5d6a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_file_hdr.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_file_hdr.h
@@ -6,8 +6,8 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
- * Written by: Vladislav Zolotarov <vladz@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
+ * Written by: Vladislav Zolotarov
  * Based on the original idea of John Wright <john.wright@hp.com>.
  */
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
index c2dfea7968f..bd90e50bd8e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
@@ -7,9 +7,9 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Eliezer Tamir
- * Modified by: Vladislav Zolotarov <vladz@broadcom.com>
+ * Modified by: Vladislav Zolotarov
  */
 
 #ifndef BNX2X_INIT_H
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h
index 8ab0dd90096..5669ed2e87d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h
@@ -8,8 +8,8 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
- * Written by: Vladislav Zolotarov <vladz@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
+ * Written by: Vladislav Zolotarov
  */
 
 #ifndef BNX2X_INIT_OPS_H
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 9b6b3d7304b..53fb4fa61b4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -2218,7 +2218,6 @@ int bnx2x_update_pfc(struct link_params *params,
 	 */
 	u32 val;
 	struct bnx2x *bp = params->bp;
-	int bnx2x_status = 0;
 	u8 bmac_loopback = (params->loopback_mode == LOOPBACK_BMAC);
 
 	if (params->feature_config_flags & FEATURE_CONFIG_PFC_ENABLED)
@@ -2232,7 +2231,7 @@ int bnx2x_update_pfc(struct link_params *params,
 	bnx2x_update_pfc_nig(params, vars, pfc_params);
 
 	if (!vars->link_up)
-		return bnx2x_status;
+		return 0;
 
 	DP(NETIF_MSG_LINK, "About to update PFC in BMAC\n");
 
@@ -2246,7 +2245,7 @@ int bnx2x_update_pfc(struct link_params *params,
 		    == 0) {
 			DP(NETIF_MSG_LINK, "About to update PFC in EMAC\n");
 			bnx2x_emac_enable(params, vars, 0);
-			return bnx2x_status;
+			return 0;
 		}
 		if (CHIP_IS_E2(bp))
 			bnx2x_update_pfc_bmac2(params, vars, bmac_loopback);
@@ -2260,7 +2259,7 @@ int bnx2x_update_pfc(struct link_params *params,
 			val = 1;
 		REG_WR(bp, NIG_REG_BMAC0_PAUSE_OUT_EN + params->port*4, val);
 	}
-	return bnx2x_status;
+	return 0;
 }
 
 static int bnx2x_bmac1_enable(struct link_params *params,
@@ -3703,7 +3702,8 @@ static void bnx2x_warpcore_restart_AN_KR(struct bnx2x_phy *phy,
 static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
 					struct link_params *params,
 					struct link_vars *vars) {
-	u16 lane, i, cl72_ctrl, an_adv = 0;
+	u16 lane, i, cl72_ctrl, an_adv = 0, val;
+	u32 wc_lane_config;
 	struct bnx2x *bp = params->bp;
 	static struct bnx2x_reg_set reg_set[] = {
 		{MDIO_WC_DEVAD, MDIO_WC_REG_SERDESDIGITAL_CONTROL1000X2, 0x7},
@@ -3822,15 +3822,27 @@ static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
 		/* Enable Auto-Detect to support 1G over CL37 as well */
 		bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
 				 MDIO_WC_REG_SERDESDIGITAL_CONTROL1000X1, 0x10);
-
+		wc_lane_config = REG_RD(bp, params->shmem_base +
+					offsetof(struct shmem_region, dev_info.
+					shared_hw_config.wc_lane_config));
+		bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
+				MDIO_WC_REG_RX0_PCI_CTRL + (lane << 4), &val);
 		/* Force cl48 sync_status LOW to avoid getting stuck in CL73
 		 * parallel-detect loop when CL73 and CL37 are enabled.
 		 */
-		CL22_WR_OVER_CL45(bp, phy, MDIO_REG_BANK_AER_BLOCK,
-				  MDIO_AER_BLOCK_AER_REG, 0);
+		val |= 1 << 11;
+
+		/* Restore Polarity settings in case it was run over by
+		 * previous link owner
+		 */
+		if (wc_lane_config &
+		    (SHARED_HW_CFG_RX_LANE0_POL_FLIP_ENABLED << lane))
+			val |= 3 << 2;
+		else
+			val &= ~(3 << 2);
 		bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
-				 MDIO_WC_REG_RXB_ANA_RX_CONTROL_PCI, 0x0800);
-		bnx2x_set_aer_mmd(params, phy);
+				 MDIO_WC_REG_RX0_PCI_CTRL + (lane << 4),
+				 val);
 
 		bnx2x_disable_kr2(params, vars, phy);
 	}
@@ -6473,7 +6485,6 @@ int bnx2x_test_link(struct link_params *params, struct link_vars *vars,
 static int bnx2x_link_initialize(struct link_params *params,
 				 struct link_vars *vars)
 {
-	int rc = 0;
 	u8 phy_index, non_ext_phy;
 	struct bnx2x *bp = params->bp;
 	/* In case of external phy existence, the line speed would be the
@@ -6546,7 +6557,7 @@ static int bnx2x_link_initialize(struct link_params *params,
 			NIG_STATUS_XGXS0_LINK_STATUS |
 			NIG_STATUS_SERDES0_LINK_STATUS |
 			NIG_MASK_MI_INT));
-	return rc;
+	return 0;
 }
 
 static void bnx2x_int_link_reset(struct bnx2x_phy *phy,
@@ -12461,6 +12472,7 @@ static int bnx2x_avoid_link_flap(struct link_params *params,
 	u32 dont_clear_stat, lfa_sts;
 	struct bnx2x *bp = params->bp;
 
+	bnx2x_set_mdio_emac_per_phy(bp, params);
 	/* Sync the link parameters */
 	bnx2x_link_status_update(params, vars);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 3a8e51ed5be..6a8b1453a1b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -6,7 +6,7 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Eliezer Tamir
  * Based on code from Michael Chan's bnx2 driver
  * UDP CSUM errata workaround by Arik Gendelman
@@ -10053,6 +10053,24 @@ static void bnx2x_prev_unload_close_mac(struct bnx2x *bp,
 #define BCM_5710_UNDI_FW_MF_VERS	(0x05)
 #define BNX2X_PREV_UNDI_MF_PORT(p) (BAR_TSTRORM_INTMEM + 0x150c + ((p) << 4))
 #define BNX2X_PREV_UNDI_MF_FUNC(f) (BAR_TSTRORM_INTMEM + 0x184c + ((f) << 4))
+
+static bool bnx2x_prev_is_after_undi(struct bnx2x *bp)
+{
+	/* UNDI marks its presence in DORQ -
+	 * it initializes CID offset for normal bell to 0x7
+	 */
+	if (!(REG_RD(bp, MISC_REG_RESET_REG_1) &
+	    MISC_REGISTERS_RESET_REG_1_RST_DORQ))
+		return false;
+
+	if (REG_RD(bp, DORQ_REG_NORM_CID_OFST) == 0x7) {
+		BNX2X_DEV_INFO("UNDI previously loaded\n");
+		return true;
+	}
+
+	return false;
+}
+
 static bool bnx2x_prev_unload_undi_fw_supports_mf(struct bnx2x *bp)
 {
 	u8 major, minor, version;
@@ -10302,6 +10320,10 @@ static int bnx2x_prev_unload_uncommon(struct bnx2x *bp)
 
 	BNX2X_DEV_INFO("Path is unmarked\n");
 
+	/* Cannot proceed with FLR if UNDI is loaded, since FW does not match */
+	if (bnx2x_prev_is_after_undi(bp))
+		goto out;
+
 	/* If function has FLR capabilities, and existing FW version matches
 	 * the one required, then FLR will be sufficient to clean any residue
 	 * left by previous driver
@@ -10322,6 +10344,7 @@ static int bnx2x_prev_unload_uncommon(struct bnx2x *bp)
 
 	BNX2X_DEV_INFO("Could not FLR\n");
 
+out:
 	/* Close the MCP request, return failure*/
 	rc = bnx2x_prev_mcp_done(bp);
 	if (!rc)
@@ -10360,19 +10383,13 @@ static int bnx2x_prev_unload_common(struct bnx2x *bp)
 		/* close LLH filters towards the BRB */
 		bnx2x_set_rx_filter(&bp->link_params, 0);
 
-		/* Check if the UNDI driver was previously loaded
-		 * UNDI driver initializes CID offset for normal bell to 0x7
-		 */
-		if (reset_reg & MISC_REGISTERS_RESET_REG_1_RST_DORQ) {
-			tmp_reg = REG_RD(bp, DORQ_REG_NORM_CID_OFST);
-			if (tmp_reg == 0x7) {
-				BNX2X_DEV_INFO("UNDI previously loaded\n");
-				prev_undi = true;
-				/* clear the UNDI indication */
-				REG_WR(bp, DORQ_REG_NORM_CID_OFST, 0);
-				/* clear possible idle check errors */
-				REG_RD(bp, NIG_REG_NIG_INT_STS_CLR_0);
-			}
+		/* Check if the UNDI driver was previously loaded */
+		if (bnx2x_prev_is_after_undi(bp)) {
+			prev_undi = true;
+			/* clear the UNDI indication */
+			REG_WR(bp, DORQ_REG_NORM_CID_OFST, 0);
+			/* clear possible idle check errors */
+			REG_RD(bp, NIG_REG_NIG_INT_STS_CLR_0);
 		}
 		if (!CHIP_IS_E1x(bp))
 			/* block FW from writing to host */
@@ -12920,7 +12937,7 @@ static int bnx2x_get_num_non_def_sbs(struct pci_dev *pdev, int cnic_cnt)
 	 * without the default SB.
 	 * For VFs there is no default SB, then we return (index+1).
 	 */
-	pci_read_config_word(pdev, pdev->msix_cap + PCI_MSI_FLAGS, &control);
+	pci_read_config_word(pdev, pdev->msix_cap + PCI_MSIX_FLAGS, &control);
 
 	index = control & PCI_MSIX_FLAGS_QSIZE;
 
@@ -13283,8 +13300,8 @@ static int bnx2x_eeh_nic_unload(struct bnx2x *bp)
 	netdev_reset_tc(bp->dev);
 
 	del_timer_sync(&bp->timer);
-	cancel_delayed_work(&bp->sp_task);
-	cancel_delayed_work(&bp->period_task);
+	cancel_delayed_work_sync(&bp->sp_task);
+	cancel_delayed_work_sync(&bp->period_task);
 
 	spin_lock_bh(&bp->stats_lock);
 	bp->stats_state = STATS_STATE_DISABLED;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index d725317c427..b1936044767 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -12,7 +12,7 @@
  * license other than the GPL, without Broadcom's express prior written
  * consent.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Vladislav Zolotarov
  *
  */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
index 80f6c790ed8..718ecd29466 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
@@ -12,7 +12,7 @@
  * license other than the GPL, without Broadcom's express prior written
  * consent.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Vladislav Zolotarov
  *
  */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index faf01488d26..eda8583f6fc 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -12,9 +12,9 @@
  * license other than the GPL, without Broadcom's express prior written
  * consent.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
- * Written by: Shmulik Ravid <shmulikr@broadcom.com>
- *	       Ariel Elior <ariele@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
+ * Written by: Shmulik Ravid
+ *	       Ariel Elior <ariel.elior@qlogic.com>
  *
  */
 #include "bnx2x.h"
@@ -1071,8 +1071,10 @@ void bnx2x_iov_init_dq(struct bnx2x *bp)
 	REG_WR(bp, DORQ_REG_VF_TYPE_MIN_MCID_0, 0);
 	REG_WR(bp, DORQ_REG_VF_TYPE_MAX_MCID_0, 0x1ffff);
 
-	/* set the VF doorbell threshold */
-	REG_WR(bp, DORQ_REG_VF_USAGE_CT_LIMIT, 4);
+	/* set the VF doorbell threshold. This threshold represents the amount
+	 * of doorbells allowed in the main DORQ fifo for a specific VF.
+	 */
+	REG_WR(bp, DORQ_REG_VF_USAGE_CT_LIMIT, 64);
 }
 
 void bnx2x_iov_init_dmae(struct bnx2x *bp)
@@ -2576,7 +2578,8 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx,
 
 	ivi->vf = vfidx;
 	ivi->qos = 0;
-	ivi->tx_rate = 10000; /* always 10G. TBA take from link struct */
+	ivi->max_tx_rate = 10000; /* always 10G. TBA take from link struct */
+	ivi->min_tx_rate = 0;
 	ivi->spoofchk = 1; /*always enabled */
 	if (vf->state == VF_ENABLED) {
 		/* mac and vlan are in vlan_mac objects */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 6929adba52f..96c575e147a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -12,9 +12,9 @@
  * license other than the GPL, without Broadcom's express prior written
  * consent.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
- * Written by: Shmulik Ravid <shmulikr@broadcom.com>
- *	       Ariel Elior <ariele@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
+ * Written by: Shmulik Ravid
+ *	       Ariel Elior <ariel.elior@qlogic.com>
  */
 #ifndef BNX2X_SRIOV_H
 #define BNX2X_SRIOV_H
@@ -571,7 +571,7 @@ static inline void __iomem *bnx2x_vf_doorbells(struct bnx2x *bp)
 	return NULL;
 }
 
-static inline void bnx2x_vf_pci_dealloc(struct bnx2 *bp) {return 0; }
+static inline void bnx2x_vf_pci_dealloc(struct bnx2x *bp) {}
 static inline int bnx2x_vf_pci_alloc(struct bnx2x *bp) {return 0; }
 static inline void bnx2x_pf_set_vfs_vlan(struct bnx2x *bp) {}
 static inline int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs) {return 0; }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
index 3b75070411a..ca47665f94b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
@@ -6,7 +6,7 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Eliezer Tamir
  * Based on code from Michael Chan's bnx2 driver
  * UDP CSUM errata workaround by Arik Gendelman
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
index f35845006cd..2beceaefdee 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
@@ -6,7 +6,7 @@
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
  * Written by: Eliezer Tamir
  * Based on code from Michael Chan's bnx2 driver
  * UDP CSUM errata workaround by Arik Gendelman
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 784c7155b98..d712d0ddd71 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -12,9 +12,9 @@
  * license other than the GPL, without Broadcom's express prior written
  * consent.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
- * Written by: Shmulik Ravid <shmulikr@broadcom.com>
- *	       Ariel Elior <ariele@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
+ * Written by: Shmulik Ravid
+ *	       Ariel Elior <ariel.elior@qlogic.com>
  */
 
 #include "bnx2x.h"
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
index c922b81170e..e21e706762c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
@@ -12,8 +12,8 @@
  * license other than the GPL, without Broadcom's express prior written
  * consent.
  *
- * Maintained by: Eilon Greenstein <eilong@broadcom.com>
- * Written by: Ariel Elior <ariele@broadcom.com>
+ * Maintained by: Ariel Elior <ariel.elior@qlogic.com>
+ * Written by: Ariel Elior <ariel.elior@qlogic.com>
  */
 #ifndef VF_PF_IF_H
 #define VF_PF_IF_H
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 4dd48d2fa80..8244e2b14bb 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -608,6 +608,10 @@ static int cnic_unregister_device(struct cnic_dev *dev, int ulp_type)
 		pr_err("%s: Bad type %d\n", __func__, ulp_type);
 		return -EINVAL;
 	}
+
+	if (ulp_type == CNIC_ULP_ISCSI)
+		cnic_send_nlmsg(cp, ISCSI_KEVENT_IF_DOWN, NULL);
+
 	mutex_lock(&cnic_lock);
 	if (rcu_dereference(cp->ulp_ops[ulp_type])) {
 		RCU_INIT_POINTER(cp->ulp_ops[ulp_type], NULL);
@@ -620,9 +624,7 @@ static int cnic_unregister_device(struct cnic_dev *dev, int ulp_type)
 	}
 	mutex_unlock(&cnic_lock);
 
-	if (ulp_type == CNIC_ULP_ISCSI)
-		cnic_send_nlmsg(cp, ISCSI_KEVENT_IF_DOWN, NULL);
-	else if (ulp_type == CNIC_ULP_FCOE)
+	if (ulp_type == CNIC_ULP_FCOE)
 		dev->fcoe_cap = NULL;
 
 	synchronize_rcu();
@@ -1039,21 +1041,17 @@ static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages)
 	struct cnic_local *cp = dev->cnic_priv;
 	struct cnic_uio_dev *udev;
 
-	read_lock(&cnic_dev_lock);
 	list_for_each_entry(udev, &cnic_udev_list, list) {
 		if (udev->pdev == dev->pcidev) {
 			udev->dev = dev;
 			if (__cnic_alloc_uio_rings(udev, pages)) {
 				udev->dev = NULL;
-				read_unlock(&cnic_dev_lock);
 				return -ENOMEM;
 			}
 			cp->udev = udev;
-			read_unlock(&cnic_dev_lock);
 			return 0;
 		}
 	}
-	read_unlock(&cnic_dev_lock);
 
 	udev = kzalloc(sizeof(struct cnic_uio_dev), GFP_ATOMIC);
 	if (!udev)
@@ -1067,9 +1065,7 @@ static int cnic_alloc_uio_rings(struct cnic_dev *dev, int pages)
 	if (__cnic_alloc_uio_rings(udev, pages))
 		goto err_udev;
 
-	write_lock(&cnic_dev_lock);
 	list_add(&udev->list, &cnic_udev_list);
-	write_unlock(&cnic_dev_lock);
 
 	pci_dev_get(udev->pdev);
 
@@ -5624,20 +5620,27 @@ static void cnic_rcv_netevent(struct cnic_local *cp, unsigned long event,
 {
 	int if_type;
 
-	rcu_read_lock();
 	for (if_type = 0; if_type < MAX_CNIC_ULP_TYPE; if_type++) {
 		struct cnic_ulp_ops *ulp_ops;
 		void *ctx;
 
-		ulp_ops = rcu_dereference(cp->ulp_ops[if_type]);
-		if (!ulp_ops || !ulp_ops->indicate_netevent)
+		mutex_lock(&cnic_lock);
+		ulp_ops = rcu_dereference_protected(cp->ulp_ops[if_type],
+						lockdep_is_held(&cnic_lock));
+		if (!ulp_ops || !ulp_ops->indicate_netevent) {
+			mutex_unlock(&cnic_lock);
 			continue;
+		}
 
 		ctx = cp->ulp_handle[if_type];
 
+		set_bit(ULP_F_CALL_PENDING, &cp->ulp_flags[if_type]);
+		mutex_unlock(&cnic_lock);
+
 		ulp_ops->indicate_netevent(ctx, event, vlan_id);
+
+		clear_bit(ULP_F_CALL_PENDING, &cp->ulp_flags[if_type]);
 	}
-	rcu_read_unlock();
 }
 
 /* netdev event handler */
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 0966bd04375..4e615debe47 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1149,6 +1149,11 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto out;
 	}
 
+	if (skb_padto(skb, ETH_ZLEN)) {
+		ret = NETDEV_TX_OK;
+		goto out;
+	}
+
 	/* set the SKB transmit checksum */
 	if (priv->desc_64b_en) {
 		ret = bcmgenet_put_tx_csum(dev, skb);
@@ -1408,13 +1413,6 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv)
 		if (cb->skb)
 			continue;
 
-		/* set the DMA descriptor length once and for all
-		 * it will only change if we support dynamically sizing
-		 * priv->rx_buf_len, but we do not
-		 */
-		dmadesc_set_length_status(priv, priv->rx_bd_assign_ptr,
-				priv->rx_buf_len << DMA_BUFLENGTH_SHIFT);
-
 		ret = bcmgenet_rx_refill(priv, cb);
 		if (ret)
 			break;
@@ -2481,7 +2479,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	dev_set_drvdata(&pdev->dev, dev);
 	ether_addr_copy(dev->dev_addr, macaddr);
 	dev->watchdog_timeo = 2 * HZ;
-	SET_ETHTOOL_OPS(dev, &bcmgenet_ethtool_ops);
+	dev->ethtool_ops = &bcmgenet_ethtool_ops;
 	dev->netdev_ops = &bcmgenet_netdev_ops;
 	netif_napi_add(dev, &priv->napi, bcmgenet_poll, 64);
 
@@ -2535,14 +2533,17 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	netif_set_real_num_tx_queues(priv->dev, priv->hw_params->tx_queues + 1);
 	netif_set_real_num_rx_queues(priv->dev, priv->hw_params->rx_queues + 1);
 
-	err = register_netdev(dev);
-	if (err)
-		goto err_clk_disable;
+	/* libphy will determine the link state */
+	netif_carrier_off(dev);
 
 	/* Turn off the main clock, WOL clock is handled separately */
 	if (!IS_ERR(priv->clk))
 		clk_disable_unprepare(priv->clk);
 
+	err = register_netdev(dev);
+	if (err)
+		goto err;
+
 	return err;
 
 err_clk_disable:
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 0f117105fed..e23c993b136 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -331,9 +331,9 @@ struct bcmgenet_mib_counters {
 #define  EXT_ENERGY_DET_MASK		(1 << 12)
 
 #define EXT_RGMII_OOB_CTRL		0x0C
-#define  RGMII_MODE_EN			(1 << 0)
 #define  RGMII_LINK			(1 << 4)
 #define  OOB_DISABLE			(1 << 5)
+#define  RGMII_MODE_EN			(1 << 6)
 #define  ID_MODE_DIS			(1 << 16)
 
 #define EXT_GPHY_CTRL			0x1C
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 4608673beaf..add8d859608 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -298,6 +298,7 @@ int bcmgenet_mii_config(struct net_device *dev)
 static int bcmgenet_mii_probe(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device_node *dn = priv->pdev->dev.of_node;
 	struct phy_device *phydev;
 	unsigned int phy_flags;
 	int ret;
@@ -307,15 +308,19 @@ static int bcmgenet_mii_probe(struct net_device *dev)
 		return 0;
 	}
 
-	if (priv->phy_dn)
-		phydev = of_phy_connect(dev, priv->phy_dn,
-					bcmgenet_mii_setup, 0,
-					priv->phy_interface);
-	else
-		phydev = of_phy_connect_fixed_link(dev,
-					bcmgenet_mii_setup,
-					priv->phy_interface);
+	/* In the case of a fixed PHY, the DT node associated
+	 * to the PHY is the Ethernet MAC DT node.
+	 */
+	if (of_phy_is_fixed_link(dn)) {
+		ret = of_phy_register_fixed_link(dn);
+		if (ret)
+			return ret;
+
+		priv->phy_dn = dn;
+	}
 
+	phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup, 0,
+				priv->phy_interface);
 	if (!phydev) {
 		pr_err("could not attach to PHY\n");
 		return -ENODEV;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index e5d95c5ce1a..8afa579e7c4 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -4,7 +4,7 @@
  * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com)
  * Copyright (C) 2001, 2002, 2003 Jeff Garzik (jgarzik@pobox.com)
  * Copyright (C) 2004 Sun Microsystems Inc.
- * Copyright (C) 2005-2013 Broadcom Corporation.
+ * Copyright (C) 2005-2014 Broadcom Corporation.
  *
  * Firmware is:
  *	Derived from proprietary unpublished source code,
@@ -94,10 +94,10 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits)
 
 #define DRV_MODULE_NAME		"tg3"
 #define TG3_MAJ_NUM			3
-#define TG3_MIN_NUM			136
+#define TG3_MIN_NUM			137
 #define DRV_MODULE_VERSION	\
 	__stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM)
-#define DRV_MODULE_RELDATE	"Jan 03, 2014"
+#define DRV_MODULE_RELDATE	"May 11, 2014"
 
 #define RESET_KIND_SHUTDOWN	0
 #define RESET_KIND_INIT		1
@@ -3224,7 +3224,7 @@ static int tg3_nvram_read_using_eeprom(struct tg3 *tp,
 	return 0;
 }
 
-#define NVRAM_CMD_TIMEOUT 10000
+#define NVRAM_CMD_TIMEOUT 5000
 
 static int tg3_nvram_exec_cmd(struct tg3 *tp, u32 nvram_cmd)
 {
@@ -3232,7 +3232,7 @@ static int tg3_nvram_exec_cmd(struct tg3 *tp, u32 nvram_cmd)
 
 	tw32(NVRAM_CMD, nvram_cmd);
 	for (i = 0; i < NVRAM_CMD_TIMEOUT; i++) {
-		udelay(10);
+		usleep_range(10, 40);
 		if (tr32(NVRAM_CMD) & NVRAM_CMD_DONE) {
 			udelay(10);
 			break;
@@ -7854,8 +7854,8 @@ static int tg3_tso_bug(struct tg3 *tp, struct sk_buff *skb)
 		netif_wake_queue(tp->dev);
 	}
 
-	segs = skb_gso_segment(skb, tp->dev->features & ~NETIF_F_TSO);
-	if (IS_ERR(segs))
+	segs = skb_gso_segment(skb, tp->dev->features & ~(NETIF_F_TSO | NETIF_F_TSO6));
+	if (IS_ERR(segs) || !segs)
 		goto tg3_tso_bug_end;
 
 	do {
@@ -7871,9 +7871,7 @@ tg3_tso_bug_end:
 	return NETDEV_TX_OK;
 }
 
-/* hard_start_xmit for devices that have the 4G bug and/or 40-bit bug and
- * support TG3_FLAG_HW_TSO_1 or firmware TSO only.
- */
+/* hard_start_xmit for all devices */
 static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct tg3 *tp = netdev_priv(dev);
@@ -7884,6 +7882,10 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct tg3_napi *tnapi;
 	struct netdev_queue *txq;
 	unsigned int last;
+	struct iphdr *iph = NULL;
+	struct tcphdr *tcph = NULL;
+	__sum16 tcp_csum = 0, ip_csum = 0;
+	__be16 ip_tot_len = 0;
 
 	txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
 	tnapi = &tp->napi[skb_get_queue_mapping(skb)];
@@ -7915,7 +7917,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (mss) {
-		struct iphdr *iph;
 		u32 tcp_opt_len, hdr_len;
 
 		if (skb_cow_head(skb, 0))
@@ -7927,27 +7928,31 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb) - ETH_HLEN;
 
 		if (!skb_is_gso_v6(skb)) {
+			if (unlikely((ETH_HLEN + hdr_len) > 80) &&
+			    tg3_flag(tp, TSO_BUG))
+				return tg3_tso_bug(tp, skb);
+
+			ip_csum = iph->check;
+			ip_tot_len = iph->tot_len;
 			iph->check = 0;
 			iph->tot_len = htons(mss + hdr_len);
 		}
 
-		if (unlikely((ETH_HLEN + hdr_len) > 80) &&
-		    tg3_flag(tp, TSO_BUG))
-			return tg3_tso_bug(tp, skb);
-
 		base_flags |= (TXD_FLAG_CPU_PRE_DMA |
 			       TXD_FLAG_CPU_POST_DMA);
 
+		tcph = tcp_hdr(skb);
+		tcp_csum = tcph->check;
+
 		if (tg3_flag(tp, HW_TSO_1) ||
 		    tg3_flag(tp, HW_TSO_2) ||
 		    tg3_flag(tp, HW_TSO_3)) {
-			tcp_hdr(skb)->check = 0;
+			tcph->check = 0;
 			base_flags &= ~TXD_FLAG_TCPUDP_CSUM;
-		} else
-			tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr,
-								 iph->daddr, 0,
-								 IPPROTO_TCP,
-								 0);
+		} else {
+			tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+							 0, IPPROTO_TCP, 0);
+		}
 
 		if (tg3_flag(tp, HW_TSO_3)) {
 			mss |= (hdr_len & 0xc) << 12;
@@ -8047,6 +8052,18 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (would_hit_hwbug) {
 		tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i);
 
+		if (mss) {
+			/* If it's a TSO packet, do GSO instead of
+			 * allocating and copying to a large linear SKB
+			 */
+			if (ip_tot_len) {
+				iph->check = ip_csum;
+				iph->tot_len = ip_tot_len;
+			}
+			tcph->check = tcp_csum;
+			return tg3_tso_bug(tp, skb);
+		}
+
 		/* If the workaround fails due to memory/mapping
 		 * failure, silently drop this packet.
 		 */
@@ -11876,9 +11893,9 @@ static int tg3_get_eeprom_len(struct net_device *dev)
 static int tg3_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data)
 {
 	struct tg3 *tp = netdev_priv(dev);
-	int ret;
+	int ret, cpmu_restore = 0;
 	u8  *pd;
-	u32 i, offset, len, b_offset, b_count;
+	u32 i, offset, len, b_offset, b_count, cpmu_val = 0;
 	__be32 val;
 
 	if (tg3_flag(tp, NO_NVRAM))
@@ -11890,6 +11907,19 @@ static int tg3_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 
 	eeprom->magic = TG3_EEPROM_MAGIC;
 
+	/* Override clock, link aware and link idle modes */
+	if (tg3_flag(tp, CPMU_PRESENT)) {
+		cpmu_val = tr32(TG3_CPMU_CTRL);
+		if (cpmu_val & (CPMU_CTRL_LINK_AWARE_MODE |
+				CPMU_CTRL_LINK_IDLE_MODE)) {
+			tw32(TG3_CPMU_CTRL, cpmu_val &
+					    ~(CPMU_CTRL_LINK_AWARE_MODE |
+					     CPMU_CTRL_LINK_IDLE_MODE));
+			cpmu_restore = 1;
+		}
+	}
+	tg3_override_clk(tp);
+
 	if (offset & 3) {
 		/* adjustments to start on required 4 byte boundary */
 		b_offset = offset & 3;
@@ -11900,7 +11930,7 @@ static int tg3_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 		}
 		ret = tg3_nvram_read_be32(tp, offset-b_offset, &val);
 		if (ret)
-			return ret;
+			goto eeprom_done;
 		memcpy(data, ((char *)&val) + b_offset, b_count);
 		len -= b_count;
 		offset += b_count;
@@ -11912,10 +11942,20 @@ static int tg3_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 	for (i = 0; i < (len - (len & 3)); i += 4) {
 		ret = tg3_nvram_read_be32(tp, offset + i, &val);
 		if (ret) {
+			if (i)
+				i -= 4;
 			eeprom->len += i;
-			return ret;
+			goto eeprom_done;
 		}
 		memcpy(pd + i, &val, 4);
+		if (need_resched()) {
+			if (signal_pending(current)) {
+				eeprom->len += i;
+				ret = -EINTR;
+				goto eeprom_done;
+			}
+			cond_resched();
+		}
 	}
 	eeprom->len += i;
 
@@ -11926,11 +11966,19 @@ static int tg3_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom,
 		b_offset = offset + len - b_count;
 		ret = tg3_nvram_read_be32(tp, b_offset, &val);
 		if (ret)
-			return ret;
+			goto eeprom_done;
 		memcpy(pd, &val, b_count);
 		eeprom->len += b_count;
 	}
-	return 0;
+	ret = 0;
+
+eeprom_done:
+	/* Restore clock, link aware and link idle modes */
+	tg3_restore_clk(tp);
+	if (cpmu_restore)
+		tw32(TG3_CPMU_CTRL, cpmu_val);
+
+	return ret;
 }
 
 static int tg3_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data)
@@ -12484,7 +12532,7 @@ static u32 tg3_get_rxfh_indir_size(struct net_device *dev)
 	return size;
 }
 
-static int tg3_get_rxfh_indir(struct net_device *dev, u32 *indir)
+static int tg3_get_rxfh(struct net_device *dev, u32 *indir, u8 *key)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	int i;
@@ -12495,7 +12543,7 @@ static int tg3_get_rxfh_indir(struct net_device *dev, u32 *indir)
 	return 0;
 }
 
-static int tg3_set_rxfh_indir(struct net_device *dev, const u32 *indir)
+static int tg3_set_rxfh(struct net_device *dev, const u32 *indir, const u8 *key)
 {
 	struct tg3 *tp = netdev_priv(dev);
 	size_t i;
@@ -14027,8 +14075,8 @@ static const struct ethtool_ops tg3_ethtool_ops = {
 	.get_sset_count		= tg3_get_sset_count,
 	.get_rxnfc		= tg3_get_rxnfc,
 	.get_rxfh_indir_size    = tg3_get_rxfh_indir_size,
-	.get_rxfh_indir		= tg3_get_rxfh_indir,
-	.set_rxfh_indir		= tg3_set_rxfh_indir,
+	.get_rxfh		= tg3_get_rxfh,
+	.set_rxfh		= tg3_set_rxfh,
 	.get_channels		= tg3_get_channels,
 	.set_channels		= tg3_set_channels,
 	.get_ts_info		= tg3_get_ts_info,
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index 04321e5a356..461accaf0aa 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -4,7 +4,7 @@
  * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com)
  * Copyright (C) 2001 Jeff Garzik (jgarzik@pobox.com)
  * Copyright (C) 2004 Sun Microsystems Inc.
- * Copyright (C) 2007-2013 Broadcom Corporation.
+ * Copyright (C) 2007-2014 Broadcom Corporation.
  */
 
 #ifndef _T3_H
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index f9e150825bb..882cad71ad6 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -266,8 +266,8 @@ bnad_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
 		ethtool_cmd_speed_set(cmd, SPEED_10000);
 		cmd->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(cmd, -1);
-		cmd->duplex = -1;
+		ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
+		cmd->duplex = DUPLEX_UNKNOWN;
 	}
 	cmd->transceiver = XCVR_EXTERNAL;
 	cmd->maxtxpkt = 0;
@@ -1137,5 +1137,5 @@ static const struct ethtool_ops bnad_ethtool_ops = {
 void
 bnad_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &bnad_ethtool_ops);
+	netdev->ethtool_ops = &bnad_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index 521dfea44b8..25d6b2a10e4 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -1737,7 +1737,7 @@ static int xgmac_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ndev);
 	ether_setup(ndev);
 	ndev->netdev_ops = &xgmac_netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &xgmac_ethtool_ops);
+	ndev->ethtool_ops = &xgmac_ethtool_ops;
 	spin_lock_init(&priv->stats_lock);
 	INIT_WORK(&priv->tx_timeout_work, xgmac_tx_timeout_work);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index 05613a85ce6..186566bfdbc 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -580,8 +580,8 @@ static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		ethtool_cmd_speed_set(cmd, p->link_config.speed);
 		cmd->duplex = p->link_config.duplex;
 	} else {
-		ethtool_cmd_speed_set(cmd, -1);
-		cmd->duplex = -1;
+		ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
+		cmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	cmd->port = (cmd->supported & SUPPORTED_TP) ? PORT_TP : PORT_FIBRE;
@@ -1100,7 +1100,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 		netif_napi_add(netdev, &adapter->napi, t1_poll, 64);
 
-		SET_ETHTOOL_OPS(netdev, &t1_ethtool_ops);
+		netdev->ethtool_ops = &t1_ethtool_ops;
 	}
 
 	if (t1_init_sw_modules(adapter, bi) < 0) {
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 07bbb711b7e..5d9cce053cc 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -1809,8 +1809,8 @@ static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		ethtool_cmd_speed_set(cmd, p->link_config.speed);
 		cmd->duplex = p->link_config.duplex;
 	} else {
-		ethtool_cmd_speed_set(cmd, -1);
-		cmd->duplex = -1;
+		ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
+		cmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	cmd->port = (cmd->supported & SUPPORTED_TP) ? PORT_TP : PORT_FIBRE;
@@ -3291,7 +3291,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			netdev->features |= NETIF_F_HIGHDMA;
 
 		netdev->netdev_ops = &cxgb_netdev_ops;
-		SET_ETHTOOL_OPS(netdev, &cxgb_ethtool_ops);
+		netdev->ethtool_ops = &cxgb_ethtool_ops;
 	}
 
 	pci_set_drvdata(pdev, adapter);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
index c0a9dd55f4e..b0cbb2b7fd4 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
@@ -185,7 +185,7 @@ static struct net_device *get_iff_from_mac(struct adapter *adapter,
 		if (ether_addr_equal(dev->dev_addr, mac)) {
 			rcu_read_lock();
 			if (vlan && vlan != VLAN_VID_MASK) {
-				dev = __vlan_find_dev_deep(dev, htons(ETH_P_8021Q), vlan);
+				dev = __vlan_find_dev_deep_rcu(dev, htons(ETH_P_8021Q), vlan);
 			} else if (netif_is_bond_slave(dev)) {
 				struct net_device *upper_dev;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 32db3770926..f503dce4ab1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -357,11 +357,17 @@ enum {
 	MAX_OFLD_QSETS = 16,          /* # of offload Tx/Rx queue sets */
 	MAX_CTRL_QUEUES = NCHAN,      /* # of control Tx queues */
 	MAX_RDMA_QUEUES = NCHAN,      /* # of streaming RDMA Rx queues */
+	MAX_RDMA_CIQS = NCHAN,        /* # of  RDMA concentrator IQs */
+	MAX_ISCSI_QUEUES = NCHAN,     /* # of streaming iSCSI Rx queues */
 };
 
 enum {
-	MAX_EGRQ = 128,         /* max # of egress queues, including FLs */
-	MAX_INGQ = 64           /* max # of interrupt-capable ingress queues */
+	INGQ_EXTRAS = 2,        /* firmware event queue and */
+				/*   forwarded interrupts */
+	MAX_EGRQ = MAX_ETH_QSETS*2 + MAX_OFLD_QSETS*2
+		   + MAX_CTRL_QUEUES + MAX_RDMA_QUEUES + MAX_ISCSI_QUEUES,
+	MAX_INGQ = MAX_ETH_QSETS + MAX_OFLD_QSETS + MAX_RDMA_QUEUES
+		   + MAX_RDMA_CIQS + MAX_ISCSI_QUEUES + INGQ_EXTRAS,
 };
 
 struct adapter;
@@ -538,6 +544,7 @@ struct sge {
 	struct sge_eth_rxq ethrxq[MAX_ETH_QSETS];
 	struct sge_ofld_rxq ofldrxq[MAX_OFLD_QSETS];
 	struct sge_ofld_rxq rdmarxq[MAX_RDMA_QUEUES];
+	struct sge_ofld_rxq rdmaciq[MAX_RDMA_CIQS];
 	struct sge_rspq fw_evtq ____cacheline_aligned_in_smp;
 
 	struct sge_rspq intrq ____cacheline_aligned_in_smp;
@@ -548,8 +555,10 @@ struct sge {
 	u16 ethtxq_rover;           /* Tx queue to clean up next */
 	u16 ofldqsets;              /* # of active offload queue sets */
 	u16 rdmaqs;                 /* # of available RDMA Rx queues */
+	u16 rdmaciqs;               /* # of available RDMA concentrator IQs */
 	u16 ofld_rxq[MAX_OFLD_QSETS];
 	u16 rdma_rxq[NCHAN];
+	u16 rdma_ciq[NCHAN];
 	u16 timer_val[SGE_NTIMERS];
 	u8 counter_val[SGE_NCOUNTERS];
 	u32 fl_pg_order;            /* large page allocation size */
@@ -577,6 +586,7 @@ struct sge {
 #define for_each_ethrxq(sge, i) for (i = 0; i < (sge)->ethqsets; i++)
 #define for_each_ofldrxq(sge, i) for (i = 0; i < (sge)->ofldqsets; i++)
 #define for_each_rdmarxq(sge, i) for (i = 0; i < (sge)->rdmaqs; i++)
+#define for_each_rdmaciq(sge, i) for (i = 0; i < (sge)->rdmaciqs; i++)
 
 struct l2t_data;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 24e16e3301e..a83271cf17c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -818,12 +818,17 @@ static void name_msix_vecs(struct adapter *adap)
 	for_each_rdmarxq(&adap->sge, i)
 		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-rdma%d",
 			 adap->port[0]->name, i);
+
+	for_each_rdmaciq(&adap->sge, i)
+		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-rdma-ciq%d",
+			 adap->port[0]->name, i);
 }
 
 static int request_msix_queue_irqs(struct adapter *adap)
 {
 	struct sge *s = &adap->sge;
-	int err, ethqidx, ofldqidx = 0, rdmaqidx = 0, msi_index = 2;
+	int err, ethqidx, ofldqidx = 0, rdmaqidx = 0, rdmaciqqidx = 0;
+	int msi_index = 2;
 
 	err = request_irq(adap->msix_info[1].vec, t4_sge_intr_msix, 0,
 			  adap->msix_info[1].desc, &s->fw_evtq);
@@ -857,9 +862,21 @@ static int request_msix_queue_irqs(struct adapter *adap)
 			goto unwind;
 		msi_index++;
 	}
+	for_each_rdmaciq(s, rdmaciqqidx) {
+		err = request_irq(adap->msix_info[msi_index].vec,
+				  t4_sge_intr_msix, 0,
+				  adap->msix_info[msi_index].desc,
+				  &s->rdmaciq[rdmaciqqidx].rspq);
+		if (err)
+			goto unwind;
+		msi_index++;
+	}
 	return 0;
 
 unwind:
+	while (--rdmaciqqidx >= 0)
+		free_irq(adap->msix_info[--msi_index].vec,
+			 &s->rdmaciq[rdmaciqqidx].rspq);
 	while (--rdmaqidx >= 0)
 		free_irq(adap->msix_info[--msi_index].vec,
 			 &s->rdmarxq[rdmaqidx].rspq);
@@ -885,6 +902,8 @@ static void free_msix_queue_irqs(struct adapter *adap)
 		free_irq(adap->msix_info[msi_index++].vec, &s->ofldrxq[i].rspq);
 	for_each_rdmarxq(s, i)
 		free_irq(adap->msix_info[msi_index++].vec, &s->rdmarxq[i].rspq);
+	for_each_rdmaciq(s, i)
+		free_irq(adap->msix_info[msi_index++].vec, &s->rdmaciq[i].rspq);
 }
 
 /**
@@ -1047,7 +1066,8 @@ freeout:	t4_free_sge_resources(adap);
 		if (msi_idx > 0)
 			msi_idx++;
 		err = t4_sge_alloc_rxq(adap, &q->rspq, false, dev, msi_idx,
-				       &q->fl, uldrx_handler);
+				       q->fl.size ? &q->fl : NULL,
+				       uldrx_handler);
 		if (err)
 			goto freeout;
 		memset(&q->stats, 0, sizeof(q->stats));
@@ -1064,13 +1084,28 @@ freeout:	t4_free_sge_resources(adap);
 		if (msi_idx > 0)
 			msi_idx++;
 		err = t4_sge_alloc_rxq(adap, &q->rspq, false, adap->port[i],
-				       msi_idx, &q->fl, uldrx_handler);
+				       msi_idx, q->fl.size ? &q->fl : NULL,
+				       uldrx_handler);
 		if (err)
 			goto freeout;
 		memset(&q->stats, 0, sizeof(q->stats));
 		s->rdma_rxq[i] = q->rspq.abs_id;
 	}
 
+	for_each_rdmaciq(s, i) {
+		struct sge_ofld_rxq *q = &s->rdmaciq[i];
+
+		if (msi_idx > 0)
+			msi_idx++;
+		err = t4_sge_alloc_rxq(adap, &q->rspq, false, adap->port[i],
+				       msi_idx, q->fl.size ? &q->fl : NULL,
+				       uldrx_handler);
+		if (err)
+			goto freeout;
+		memset(&q->stats, 0, sizeof(q->stats));
+		s->rdma_ciq[i] = q->rspq.abs_id;
+	}
+
 	for_each_port(adap, i) {
 		/*
 		 * Note that ->rdmarxq[i].rspq.cntxt_id below is 0 if we don't
@@ -2252,12 +2287,19 @@ static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	else if (p->port_type == FW_PORT_TYPE_FIBER_XFI ||
 		 p->port_type == FW_PORT_TYPE_FIBER_XAUI)
 		cmd->port = PORT_FIBRE;
-	else if (p->port_type == FW_PORT_TYPE_SFP) {
-		if (p->mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE ||
-		    p->mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE)
+	else if (p->port_type == FW_PORT_TYPE_SFP ||
+		 p->port_type == FW_PORT_TYPE_QSFP_10G ||
+		 p->port_type == FW_PORT_TYPE_QSFP) {
+		if (p->mod_type == FW_PORT_MOD_TYPE_LR ||
+		    p->mod_type == FW_PORT_MOD_TYPE_SR ||
+		    p->mod_type == FW_PORT_MOD_TYPE_ER ||
+		    p->mod_type == FW_PORT_MOD_TYPE_LRM)
+			cmd->port = PORT_FIBRE;
+		else if (p->mod_type == FW_PORT_MOD_TYPE_TWINAX_PASSIVE ||
+			 p->mod_type == FW_PORT_MOD_TYPE_TWINAX_ACTIVE)
 			cmd->port = PORT_DA;
 		else
-			cmd->port = PORT_FIBRE;
+			cmd->port = PORT_OTHER;
 	} else
 		cmd->port = PORT_OTHER;
 
@@ -2461,8 +2503,7 @@ static unsigned int qtimer_val(const struct adapter *adap,
 }
 
 /**
- *	set_rxq_intr_params - set a queue's interrupt holdoff parameters
- *	@adap: the adapter
+ *	set_rspq_intr_params - set a queue's interrupt holdoff parameters
  *	@q: the Rx queue
  *	@us: the hold-off time in us, or 0 to disable timer
  *	@cnt: the hold-off packet count, or 0 to disable counter
@@ -2470,9 +2511,11 @@ static unsigned int qtimer_val(const struct adapter *adap,
  *	Sets an Rx queue's interrupt hold-off time and packet count.  At least
  *	one of the two needs to be enabled for the queue to generate interrupts.
  */
-static int set_rxq_intr_params(struct adapter *adap, struct sge_rspq *q,
-			       unsigned int us, unsigned int cnt)
+static int set_rspq_intr_params(struct sge_rspq *q,
+				unsigned int us, unsigned int cnt)
 {
+	struct adapter *adap = q->adap;
+
 	if ((us | cnt) == 0)
 		cnt = 1;
 
@@ -2499,24 +2542,34 @@ static int set_rxq_intr_params(struct adapter *adap, struct sge_rspq *q,
 	return 0;
 }
 
-static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
+/**
+ * set_rx_intr_params - set a net devices's RX interrupt holdoff paramete!
+ * @dev: the network device
+ * @us: the hold-off time in us, or 0 to disable timer
+ * @cnt: the hold-off packet count, or 0 to disable counter
+ *
+ * Set the RX interrupt hold-off parameters for a network device.
+ */
+static int set_rx_intr_params(struct net_device *dev,
+			      unsigned int us, unsigned int cnt)
 {
-	const struct port_info *pi = netdev_priv(dev);
+	int i, err;
+	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adap = pi->adapter;
-	struct sge_rspq *q;
-	int i;
-	int r = 0;
-
-	for (i = pi->first_qset; i < pi->first_qset + pi->nqsets; i++) {
-		q = &adap->sge.ethrxq[i].rspq;
-		r = set_rxq_intr_params(adap, q, c->rx_coalesce_usecs,
-			c->rx_max_coalesced_frames);
-		if (r) {
-			dev_err(&dev->dev, "failed to set coalesce %d\n", r);
-			break;
-		}
+	struct sge_eth_rxq *q = &adap->sge.ethrxq[pi->first_qset];
+
+	for (i = 0; i < pi->nqsets; i++, q++) {
+		err = set_rspq_intr_params(&q->rspq, us, cnt);
+		if (err)
+			return err;
 	}
-	return r;
+	return 0;
+}
+
+static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
+{
+	return set_rx_intr_params(dev, c->rx_coalesce_usecs,
+				  c->rx_max_coalesced_frames);
 }
 
 static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
@@ -2732,7 +2785,7 @@ static u32 get_rss_table_size(struct net_device *dev)
 	return pi->rss_size;
 }
 
-static int get_rss_table(struct net_device *dev, u32 *p)
+static int get_rss_table(struct net_device *dev, u32 *p, u8 *key)
 {
 	const struct port_info *pi = netdev_priv(dev);
 	unsigned int n = pi->rss_size;
@@ -2742,7 +2795,7 @@ static int get_rss_table(struct net_device *dev, u32 *p)
 	return 0;
 }
 
-static int set_rss_table(struct net_device *dev, const u32 *p)
+static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key)
 {
 	unsigned int i;
 	struct port_info *pi = netdev_priv(dev);
@@ -2844,8 +2897,8 @@ static const struct ethtool_ops cxgb_ethtool_ops = {
 	.set_wol           = set_wol,
 	.get_rxnfc         = get_rxnfc,
 	.get_rxfh_indir_size = get_rss_table_size,
-	.get_rxfh_indir    = get_rss_table,
-	.set_rxfh_indir    = set_rss_table,
+	.get_rxfh	   = get_rss_table,
+	.set_rxfh	   = set_rss_table,
 	.flash_device      = set_flash,
 };
 
@@ -3386,6 +3439,77 @@ unsigned int cxgb4_best_mtu(const unsigned short *mtus, unsigned short mtu,
 EXPORT_SYMBOL(cxgb4_best_mtu);
 
 /**
+ *     cxgb4_best_aligned_mtu - find best MTU, [hopefully] data size aligned
+ *     @mtus: the HW MTU table
+ *     @header_size: Header Size
+ *     @data_size_max: maximum Data Segment Size
+ *     @data_size_align: desired Data Segment Size Alignment (2^N)
+ *     @mtu_idxp: HW MTU Table Index return value pointer (possibly NULL)
+ *
+ *     Similar to cxgb4_best_mtu() but instead of searching the Hardware
+ *     MTU Table based solely on a Maximum MTU parameter, we break that
+ *     parameter up into a Header Size and Maximum Data Segment Size, and
+ *     provide a desired Data Segment Size Alignment.  If we find an MTU in
+ *     the Hardware MTU Table which will result in a Data Segment Size with
+ *     the requested alignment _and_ that MTU isn't "too far" from the
+ *     closest MTU, then we'll return that rather than the closest MTU.
+ */
+unsigned int cxgb4_best_aligned_mtu(const unsigned short *mtus,
+				    unsigned short header_size,
+				    unsigned short data_size_max,
+				    unsigned short data_size_align,
+				    unsigned int *mtu_idxp)
+{
+	unsigned short max_mtu = header_size + data_size_max;
+	unsigned short data_size_align_mask = data_size_align - 1;
+	int mtu_idx, aligned_mtu_idx;
+
+	/* Scan the MTU Table till we find an MTU which is larger than our
+	 * Maximum MTU or we reach the end of the table.  Along the way,
+	 * record the last MTU found, if any, which will result in a Data
+	 * Segment Length matching the requested alignment.
+	 */
+	for (mtu_idx = 0, aligned_mtu_idx = -1; mtu_idx < NMTUS; mtu_idx++) {
+		unsigned short data_size = mtus[mtu_idx] - header_size;
+
+		/* If this MTU minus the Header Size would result in a
+		 * Data Segment Size of the desired alignment, remember it.
+		 */
+		if ((data_size & data_size_align_mask) == 0)
+			aligned_mtu_idx = mtu_idx;
+
+		/* If we're not at the end of the Hardware MTU Table and the
+		 * next element is larger than our Maximum MTU, drop out of
+		 * the loop.
+		 */
+		if (mtu_idx+1 < NMTUS && mtus[mtu_idx+1] > max_mtu)
+			break;
+	}
+
+	/* If we fell out of the loop because we ran to the end of the table,
+	 * then we just have to use the last [largest] entry.
+	 */
+	if (mtu_idx == NMTUS)
+		mtu_idx--;
+
+	/* If we found an MTU which resulted in the requested Data Segment
+	 * Length alignment and that's "not far" from the largest MTU which is
+	 * less than or equal to the maximum MTU, then use that.
+	 */
+	if (aligned_mtu_idx >= 0 &&
+	    mtu_idx - aligned_mtu_idx <= 1)
+		mtu_idx = aligned_mtu_idx;
+
+	/* If the caller has passed in an MTU Index pointer, pass the
+	 * MTU Index back.  Return the MTU value.
+	 */
+	if (mtu_idxp)
+		*mtu_idxp = mtu_idx;
+	return mtus[mtu_idx];
+}
+EXPORT_SYMBOL(cxgb4_best_aligned_mtu);
+
+/**
  *	cxgb4_port_chan - get the HW channel of a port
  *	@dev: the net device for the port
  *
@@ -3782,7 +3906,9 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	lli.mtus = adap->params.mtus;
 	if (uld == CXGB4_ULD_RDMA) {
 		lli.rxq_ids = adap->sge.rdma_rxq;
+		lli.ciq_ids = adap->sge.rdma_ciq;
 		lli.nrxq = adap->sge.rdmaqs;
+		lli.nciq = adap->sge.rdmaciqs;
 	} else if (uld == CXGB4_ULD_ISCSI) {
 		lli.rxq_ids = adap->sge.ofld_rxq;
 		lli.nrxq = adap->sge.ofldqsets;
@@ -3931,22 +4057,19 @@ int cxgb4_unregister_uld(enum cxgb4_uld type)
 EXPORT_SYMBOL(cxgb4_unregister_uld);
 
 /* Check if netdev on which event is occured belongs to us or not. Return
- * suceess (1) if it belongs otherwise failure (0).
+ * success (true) if it belongs otherwise failure (false).
+ * Called with rcu_read_lock() held.
  */
-static int cxgb4_netdev(struct net_device *netdev)
+static bool cxgb4_netdev(const struct net_device *netdev)
 {
 	struct adapter *adap;
 	int i;
 
-	spin_lock(&adap_rcu_lock);
 	list_for_each_entry_rcu(adap, &adap_rcu_list, rcu_node)
 		for (i = 0; i < MAX_NPORTS; i++)
-			if (adap->port[i] == netdev) {
-				spin_unlock(&adap_rcu_lock);
-				return 1;
-			}
-	spin_unlock(&adap_rcu_lock);
-	return 0;
+			if (adap->port[i] == netdev)
+				return true;
+	return false;
 }
 
 static int clip_add(struct net_device *event_dev, struct inet6_ifaddr *ifa,
@@ -4061,7 +4184,7 @@ static int update_root_dev_clip(struct net_device *dev)
 
 	/* Parse all bond and vlan devices layered on top of the physical dev */
 	for (i = 0; i < VLAN_N_VID; i++) {
-		root_dev = __vlan_find_dev_deep(dev, htons(ETH_P_8021Q), i);
+		root_dev = __vlan_find_dev_deep_rcu(dev, htons(ETH_P_8021Q), i);
 		if (!root_dev)
 			continue;
 
@@ -5528,13 +5651,41 @@ static int adap_init0(struct adapter *adap)
 #undef FW_PARAM_PFVF
 #undef FW_PARAM_DEV
 
-	/*
-	 * These are finalized by FW initialization, load their values now.
+	/* The MTU/MSS Table is initialized by now, so load their values.  If
+	 * we're initializing the adapter, then we'll make any modifications
+	 * we want to the MTU/MSS Table and also initialize the congestion
+	 * parameters.
 	 */
 	t4_read_mtu_tbl(adap, adap->params.mtus, NULL);
-	t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
-		     adap->params.b_wnd);
+	if (state != DEV_STATE_INIT) {
+		int i;
 
+		/* The default MTU Table contains values 1492 and 1500.
+		 * However, for TCP, it's better to have two values which are
+		 * a multiple of 8 +/- 4 bytes apart near this popular MTU.
+		 * This allows us to have a TCP Data Payload which is a
+		 * multiple of 8 regardless of what combination of TCP Options
+		 * are in use (always a multiple of 4 bytes) which is
+		 * important for performance reasons.  For instance, if no
+		 * options are in use, then we have a 20-byte IP header and a
+		 * 20-byte TCP header.  In this case, a 1500-byte MSS would
+		 * result in a TCP Data Payload of 1500 - 40 == 1460 bytes
+		 * which is not a multiple of 8.  So using an MSS of 1488 in
+		 * this case results in a TCP Data Payload of 1448 bytes which
+		 * is a multiple of 8.  On the other hand, if 12-byte TCP Time
+		 * Stamps have been negotiated, then an MTU of 1500 bytes
+		 * results in a TCP Data Payload of 1448 bytes which, as
+		 * above, is a multiple of 8 bytes ...
+		 */
+		for (i = 0; i < NMTUS; i++)
+			if (adap->params.mtus[i] == 1492) {
+				adap->params.mtus[i] = 1488;
+				break;
+			}
+
+		t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
+			     adap->params.b_wnd);
+	}
 	t4_init_tp_params(adap);
 	adap->flags |= FW_OK;
 	return 0;
@@ -5669,12 +5820,12 @@ static inline bool is_x_10g_port(const struct link_config *lc)
 	       (lc->supported & FW_PORT_CAP_SPEED_40G) != 0;
 }
 
-static inline void init_rspq(struct sge_rspq *q, u8 timer_idx, u8 pkt_cnt_idx,
+static inline void init_rspq(struct adapter *adap, struct sge_rspq *q,
+			     unsigned int us, unsigned int cnt,
 			     unsigned int size, unsigned int iqe_size)
 {
-	q->intr_params = QINTR_TIMER_IDX(timer_idx) |
-			 (pkt_cnt_idx < SGE_NCOUNTERS ? QINTR_CNT_EN : 0);
-	q->pktcnt_idx = pkt_cnt_idx < SGE_NCOUNTERS ? pkt_cnt_idx : 0;
+	q->adap = adap;
+	set_rspq_intr_params(q, us, cnt);
 	q->iqe_len = iqe_size;
 	q->size = size;
 }
@@ -5688,6 +5839,7 @@ static void cfg_queues(struct adapter *adap)
 {
 	struct sge *s = &adap->sge;
 	int i, q10g = 0, n10g = 0, qidx = 0;
+	int ciq_size;
 
 	for_each_port(adap, i)
 		n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
@@ -5726,12 +5878,13 @@ static void cfg_queues(struct adapter *adap)
 			s->ofldqsets = adap->params.nports;
 		/* For RDMA one Rx queue per channel suffices */
 		s->rdmaqs = adap->params.nports;
+		s->rdmaciqs = adap->params.nports;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(s->ethrxq); i++) {
 		struct sge_eth_rxq *r = &s->ethrxq[i];
 
-		init_rspq(&r->rspq, 0, 0, 1024, 64);
+		init_rspq(adap, &r->rspq, 5, 10, 1024, 64);
 		r->fl.size = 72;
 	}
 
@@ -5747,7 +5900,7 @@ static void cfg_queues(struct adapter *adap)
 	for (i = 0; i < ARRAY_SIZE(s->ofldrxq); i++) {
 		struct sge_ofld_rxq *r = &s->ofldrxq[i];
 
-		init_rspq(&r->rspq, 0, 0, 1024, 64);
+		init_rspq(adap, &r->rspq, 5, 1, 1024, 64);
 		r->rspq.uld = CXGB4_ULD_ISCSI;
 		r->fl.size = 72;
 	}
@@ -5755,13 +5908,26 @@ static void cfg_queues(struct adapter *adap)
 	for (i = 0; i < ARRAY_SIZE(s->rdmarxq); i++) {
 		struct sge_ofld_rxq *r = &s->rdmarxq[i];
 
-		init_rspq(&r->rspq, 0, 0, 511, 64);
+		init_rspq(adap, &r->rspq, 5, 1, 511, 64);
 		r->rspq.uld = CXGB4_ULD_RDMA;
 		r->fl.size = 72;
 	}
 
-	init_rspq(&s->fw_evtq, 6, 0, 512, 64);
-	init_rspq(&s->intrq, 6, 0, 2 * MAX_INGQ, 64);
+	ciq_size = 64 + adap->vres.cq.size + adap->tids.nftids;
+	if (ciq_size > SGE_MAX_IQ_SIZE) {
+		CH_WARN(adap, "CIQ size too small for available IQs\n");
+		ciq_size = SGE_MAX_IQ_SIZE;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(s->rdmaciq); i++) {
+		struct sge_ofld_rxq *r = &s->rdmaciq[i];
+
+		init_rspq(adap, &r->rspq, 5, 1, ciq_size, 64);
+		r->rspq.uld = CXGB4_ULD_RDMA;
+	}
+
+	init_rspq(adap, &s->fw_evtq, 0, 1, 1024, 64);
+	init_rspq(adap, &s->intrq, 0, 1, 2 * MAX_INGQ, 64);
 }
 
 /*
@@ -5808,9 +5974,9 @@ static int enable_msix(struct adapter *adap)
 
 	want = s->max_ethqsets + EXTRA_VECS;
 	if (is_offload(adap)) {
-		want += s->rdmaqs + s->ofldqsets;
+		want += s->rdmaqs + s->rdmaciqs + s->ofldqsets;
 		/* need nchan for each possible ULD */
-		ofld_need = 2 * nchan;
+		ofld_need = 3 * nchan;
 	}
 	need = adap->params.nports + EXTRA_VECS + ofld_need;
 
@@ -6076,7 +6242,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		netdev->priv_flags |= IFF_UNICAST_FLT;
 
 		netdev->netdev_ops = &cxgb4_netdev_ops;
-		SET_ETHTOOL_OPS(netdev, &cxgb_ethtool_ops);
+		netdev->ethtool_ops = &cxgb_ethtool_ops;
 	}
 
 	pci_set_drvdata(pdev, adapter);
@@ -6227,6 +6393,7 @@ static void remove_one(struct pci_dev *pdev)
 			adapter->flags &= ~DEV_ENABLED;
 		}
 		pci_release_regions(pdev);
+		synchronize_rcu();
 		kfree(adapter);
 	} else
 		pci_release_regions(pdev);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index e274a047528..55e9daf7f9d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -232,8 +232,10 @@ struct cxgb4_lld_info {
 	const struct cxgb4_virt_res *vr;     /* assorted HW resources */
 	const unsigned short *mtus;          /* MTU table */
 	const unsigned short *rxq_ids;       /* the ULD's Rx queue ids */
+	const unsigned short *ciq_ids;       /* the ULD's concentrator IQ ids */
 	unsigned short nrxq;                 /* # of Rx queues */
 	unsigned short ntxq;                 /* # of Tx queues */
+	unsigned short nciq;		     /* # of concentrator IQ */
 	unsigned char nchan:4;               /* # of channels */
 	unsigned char nports:4;              /* # of ports */
 	unsigned char wr_cred;               /* WR 16-byte credits */
@@ -274,6 +276,11 @@ unsigned int cxgb4_port_viid(const struct net_device *dev);
 unsigned int cxgb4_port_idx(const struct net_device *dev);
 unsigned int cxgb4_best_mtu(const unsigned short *mtus, unsigned short mtu,
 			    unsigned int *idx);
+unsigned int cxgb4_best_aligned_mtu(const unsigned short *mtus,
+				    unsigned short header_size,
+				    unsigned short data_size_max,
+				    unsigned short data_size_align,
+				    unsigned int *mtu_idxp);
 void cxgb4_get_tcp_stats(struct pci_dev *pdev, struct tp_tcp_stats *v4,
 			 struct tp_tcp_stats *v6);
 void cxgb4_iscsi_init(struct net_device *dev, unsigned int tag_mask,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index e249528c8e6..dd4355d248e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1697,7 +1697,8 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp,
 		return handle_trace_pkt(q->adap, si);
 
 	pkt = (const struct cpl_rx_pkt *)rsp;
-	csum_ok = pkt->csum_calc && !pkt->err_vec;
+	csum_ok = pkt->csum_calc && !pkt->err_vec &&
+		  (q->netdev->features & NETIF_F_RXCSUM);
 	if ((pkt->l2info & htonl(RXF_TCP)) &&
 	    (q->netdev->features & NETIF_F_GRO) && csum_ok && !pkt->ip_frag) {
 		do_gro(rxq, si, pkt);
@@ -1720,8 +1721,7 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp,
 
 	rxq->stats.pkts++;
 
-	if (csum_ok && (q->netdev->features & NETIF_F_RXCSUM) &&
-	    (pkt->l2info & htonl(RXF_UDP | RXF_TCP))) {
+	if (csum_ok && (pkt->l2info & htonl(RXF_UDP | RXF_TCP))) {
 		if (!pkt->ip_frag) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			rxq->stats.rx_cso++;
@@ -2215,7 +2215,6 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	iq->cntxt_id = ntohs(c.iqid);
 	iq->abs_id = ntohs(c.physiqid);
 	iq->size--;                           /* subtract status entry */
-	iq->adap = adap;
 	iq->netdev = dev;
 	iq->handler = hnd;
 
@@ -2515,6 +2514,10 @@ void t4_free_sge_resources(struct adapter *adap)
 		if (oq->rspq.desc)
 			free_rspq_fl(adap, &oq->rspq, &oq->fl);
 	}
+	for (i = 0, oq = adap->sge.rdmaciq; i < adap->sge.rdmaciqs; i++, oq++) {
+		if (oq->rspq.desc)
+			free_rspq_fl(adap, &oq->rspq, &oq->fl);
+	}
 
 	/* clean up offload Tx queues */
 	for (i = 0; i < ARRAY_SIZE(adap->sge.ofldtxq); i++) {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index bba67681aea..931478e7bd2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3962,6 +3962,7 @@ int t4_port_init(struct adapter *adap, int mbox, int pf, int vf)
 		p->lport = j;
 		p->rss_size = rss_size;
 		memcpy(adap->port[i]->dev_addr, addr, ETH_ALEN);
+		adap->port[i]->dev_port = j;
 
 		ret = ntohl(c.u.info.lstatus_to_modtype);
 		p->mdio_addr = (ret & FW_PORT_CMD_MDIOCAP) ?
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
index 1d1623be9f1..71b799b5b0f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
@@ -68,6 +68,7 @@ enum {
 	SGE_MAX_WR_LEN = 512,     /* max WR size in bytes */
 	SGE_NTIMERS = 6,          /* # of interrupt holdoff timer values */
 	SGE_NCOUNTERS = 4,        /* # of interrupt packet counter values */
+	SGE_MAX_IQ_SIZE = 65520,
 
 	SGE_TIMER_RSTRT_CNTR = 6, /* restart RX packet threshold counter */
 	SGE_TIMER_UPD_CIDX = 7,   /* update cidx only */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index f2738c71078..973eb11aa98 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -227,6 +227,7 @@ struct cpl_pass_open_req {
 #define DELACK(x)     ((x) << 5)
 #define ULP_MODE(x)   ((x) << 8)
 #define RCV_BUFSIZ(x) ((x) << 12)
+#define RCV_BUFSIZ_MASK 0x3FFU
 #define DSCP(x)       ((x) << 22)
 #define SMAC_SEL(x)   ((u64)(x) << 28)
 #define L2T_IDX(x)    ((u64)(x) << 36)
@@ -278,6 +279,15 @@ struct cpl_pass_accept_rpl {
 	__be64 opt0;
 };
 
+struct cpl_t5_pass_accept_rpl {
+	WR_HDR;
+	union opcode_tid ot;
+	__be32 opt2;
+	__be64 opt0;
+	__be32 iss;
+	__be32 rsvd;
+};
+
 struct cpl_act_open_req {
 	WR_HDR;
 	union opcode_tid ot;
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 52859288de7..ff1cdd1788b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -2664,7 +2664,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 		netdev->priv_flags |= IFF_UNICAST_FLT;
 
 		netdev->netdev_ops = &cxgb4vf_netdev_ops;
-		SET_ETHTOOL_OPS(netdev, &cxgb4vf_ethtool_ops);
+		netdev->ethtool_ops = &cxgb4vf_ethtool_ops;
 
 		/*
 		 * Initialize the hardware/software state for the port.
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 9d88c1d50b4..bdfa80ca5e3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -1510,7 +1510,8 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
 {
 	struct sk_buff *skb;
 	const struct cpl_rx_pkt *pkt = (void *)rsp;
-	bool csum_ok = pkt->csum_calc && !pkt->err_vec;
+	bool csum_ok = pkt->csum_calc && !pkt->err_vec &&
+		       (rspq->netdev->features & NETIF_F_RXCSUM);
 	struct sge_eth_rxq *rxq = container_of(rspq, struct sge_eth_rxq, rspq);
 
 	/*
@@ -1538,8 +1539,8 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp,
 	skb_record_rx_queue(skb, rspq->idx);
 	rxq->stats.pkts++;
 
-	if (csum_ok && (rspq->netdev->features & NETIF_F_RXCSUM) &&
-	    !pkt->err_vec && (be32_to_cpu(pkt->l2info) & (RXF_UDP|RXF_TCP))) {
+	if (csum_ok && !pkt->err_vec &&
+	    (be32_to_cpu(pkt->l2info) & (RXF_UDP|RXF_TCP))) {
 		if (!pkt->ip_frag)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		else {
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index e35c8e0202a..14f465f239d 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -43,6 +43,8 @@
 #define ENIC_CQ_MAX		(ENIC_WQ_MAX + ENIC_RQ_MAX)
 #define ENIC_INTR_MAX		(ENIC_CQ_MAX + 2)
 
+#define ENIC_AIC_LARGE_PKT_DIFF	3
+
 struct enic_msix_entry {
 	int requested;
 	char devname[IFNAMSIZ];
@@ -50,6 +52,33 @@ struct enic_msix_entry {
 	void *devid;
 };
 
+/* Store only the lower range.  Higher range is given by fw. */
+struct enic_intr_mod_range {
+	u32 small_pkt_range_start;
+	u32 large_pkt_range_start;
+};
+
+struct enic_intr_mod_table {
+	u32 rx_rate;
+	u32 range_percent;
+};
+
+#define ENIC_MAX_LINK_SPEEDS		3
+#define ENIC_LINK_SPEED_10G		10000
+#define ENIC_LINK_SPEED_4G		4000
+#define ENIC_LINK_40G_INDEX		2
+#define ENIC_LINK_10G_INDEX		1
+#define ENIC_LINK_4G_INDEX		0
+#define ENIC_RX_COALESCE_RANGE_END	125
+#define ENIC_AIC_TS_BREAK		100
+
+struct enic_rx_coal {
+	u32 small_pkt_range_start;
+	u32 large_pkt_range_start;
+	u32 range_end;
+	u32 use_adaptive_rx_coalesce;
+};
+
 /* priv_flags */
 #define ENIC_SRIOV_ENABLED		(1 << 0)
 
@@ -85,13 +114,12 @@ struct enic {
 	u32 msg_enable;
 	spinlock_t devcmd_lock;
 	u8 mac_addr[ETH_ALEN];
-	u8 mc_addr[ENIC_MULTICAST_PERFECT_FILTERS][ETH_ALEN];
-	u8 uc_addr[ENIC_UNICAST_PERFECT_FILTERS][ETH_ALEN];
 	unsigned int flags;
 	unsigned int priv_flags;
 	unsigned int mc_count;
 	unsigned int uc_count;
 	u32 port_mtu;
+	struct enic_rx_coal rx_coalesce_setting;
 	u32 rx_coalesce_usecs;
 	u32 tx_coalesce_usecs;
 #ifdef CONFIG_PCI_IOV
diff --git a/drivers/net/ethernet/cisco/enic/enic_dev.c b/drivers/net/ethernet/cisco/enic/enic_dev.c
index 4b6e5695b26..3e27df52284 100644
--- a/drivers/net/ethernet/cisco/enic/enic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/enic_dev.c
@@ -88,7 +88,7 @@ int enic_dev_packet_filter(struct enic *enic, int directed, int multicast,
 	return err;
 }
 
-int enic_dev_add_addr(struct enic *enic, u8 *addr)
+int enic_dev_add_addr(struct enic *enic, const u8 *addr)
 {
 	int err;
 
@@ -99,7 +99,7 @@ int enic_dev_add_addr(struct enic *enic, u8 *addr)
 	return err;
 }
 
-int enic_dev_del_addr(struct enic *enic, u8 *addr)
+int enic_dev_del_addr(struct enic *enic, const u8 *addr)
 {
 	int err;
 
diff --git a/drivers/net/ethernet/cisco/enic/enic_dev.h b/drivers/net/ethernet/cisco/enic/enic_dev.h
index 129b14a4efb..36ea1ab25f6 100644
--- a/drivers/net/ethernet/cisco/enic/enic_dev.h
+++ b/drivers/net/ethernet/cisco/enic/enic_dev.h
@@ -45,8 +45,8 @@ int enic_dev_add_station_addr(struct enic *enic);
 int enic_dev_del_station_addr(struct enic *enic);
 int enic_dev_packet_filter(struct enic *enic, int directed, int multicast,
 	int broadcast, int promisc, int allmulti);
-int enic_dev_add_addr(struct enic *enic, u8 *addr);
-int enic_dev_del_addr(struct enic *enic, u8 *addr);
+int enic_dev_add_addr(struct enic *enic, const u8 *addr);
+int enic_dev_del_addr(struct enic *enic, const u8 *addr);
 int enic_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid);
 int enic_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid);
 int enic_dev_notify_unset(struct enic *enic);
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index 47e3562f486..2e50b5489d2 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -79,6 +79,17 @@ static const struct enic_stat enic_rx_stats[] = {
 static const unsigned int enic_n_tx_stats = ARRAY_SIZE(enic_tx_stats);
 static const unsigned int enic_n_rx_stats = ARRAY_SIZE(enic_rx_stats);
 
+void enic_intr_coal_set_rx(struct enic *enic, u32 timer)
+{
+	int i;
+	int intr;
+
+	for (i = 0; i < enic->rq_count; i++) {
+		intr = enic_msix_rq_intr(enic, i);
+		vnic_intr_coalescing_timer_set(&enic->intr[intr], timer);
+	}
+}
+
 static int enic_get_settings(struct net_device *netdev,
 	struct ethtool_cmd *ecmd)
 {
@@ -93,8 +104,8 @@ static int enic_get_settings(struct net_device *netdev,
 		ethtool_cmd_speed_set(ecmd, vnic_dev_port_speed(enic->vdev));
 		ecmd->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	ecmd->autoneg = AUTONEG_DISABLE;
@@ -178,9 +189,14 @@ static int enic_get_coalesce(struct net_device *netdev,
 	struct ethtool_coalesce *ecmd)
 {
 	struct enic *enic = netdev_priv(netdev);
+	struct enic_rx_coal *rxcoal = &enic->rx_coalesce_setting;
 
 	ecmd->tx_coalesce_usecs = enic->tx_coalesce_usecs;
 	ecmd->rx_coalesce_usecs = enic->rx_coalesce_usecs;
+	if (rxcoal->use_adaptive_rx_coalesce)
+		ecmd->use_adaptive_rx_coalesce = 1;
+	ecmd->rx_coalesce_usecs_low = rxcoal->small_pkt_range_start;
+	ecmd->rx_coalesce_usecs_high = rxcoal->range_end;
 
 	return 0;
 }
@@ -191,17 +207,31 @@ static int enic_set_coalesce(struct net_device *netdev,
 	struct enic *enic = netdev_priv(netdev);
 	u32 tx_coalesce_usecs;
 	u32 rx_coalesce_usecs;
+	u32 rx_coalesce_usecs_low;
+	u32 rx_coalesce_usecs_high;
+	u32 coalesce_usecs_max;
 	unsigned int i, intr;
+	struct enic_rx_coal *rxcoal = &enic->rx_coalesce_setting;
 
+	coalesce_usecs_max = vnic_dev_get_intr_coal_timer_max(enic->vdev);
 	tx_coalesce_usecs = min_t(u32, ecmd->tx_coalesce_usecs,
-		vnic_dev_get_intr_coal_timer_max(enic->vdev));
+				  coalesce_usecs_max);
 	rx_coalesce_usecs = min_t(u32, ecmd->rx_coalesce_usecs,
-		vnic_dev_get_intr_coal_timer_max(enic->vdev));
+				  coalesce_usecs_max);
+
+	rx_coalesce_usecs_low = min_t(u32, ecmd->rx_coalesce_usecs_low,
+				      coalesce_usecs_max);
+	rx_coalesce_usecs_high = min_t(u32, ecmd->rx_coalesce_usecs_high,
+				       coalesce_usecs_max);
 
 	switch (vnic_dev_get_intr_mode(enic->vdev)) {
 	case VNIC_DEV_INTR_MODE_INTX:
 		if (tx_coalesce_usecs != rx_coalesce_usecs)
 			return -EINVAL;
+		if (ecmd->use_adaptive_rx_coalesce	||
+		    ecmd->rx_coalesce_usecs_low		||
+		    ecmd->rx_coalesce_usecs_high)
+			return -EOPNOTSUPP;
 
 		intr = enic_legacy_io_intr();
 		vnic_intr_coalescing_timer_set(&enic->intr[intr],
@@ -210,6 +240,10 @@ static int enic_set_coalesce(struct net_device *netdev,
 	case VNIC_DEV_INTR_MODE_MSI:
 		if (tx_coalesce_usecs != rx_coalesce_usecs)
 			return -EINVAL;
+		if (ecmd->use_adaptive_rx_coalesce	||
+		    ecmd->rx_coalesce_usecs_low		||
+		    ecmd->rx_coalesce_usecs_high)
+			return -EOPNOTSUPP;
 
 		vnic_intr_coalescing_timer_set(&enic->intr[0],
 			tx_coalesce_usecs);
@@ -221,12 +255,27 @@ static int enic_set_coalesce(struct net_device *netdev,
 				tx_coalesce_usecs);
 		}
 
-		for (i = 0; i < enic->rq_count; i++) {
-			intr = enic_msix_rq_intr(enic, i);
-			vnic_intr_coalescing_timer_set(&enic->intr[intr],
-				rx_coalesce_usecs);
+		if (rxcoal->use_adaptive_rx_coalesce) {
+			if (!ecmd->use_adaptive_rx_coalesce) {
+				rxcoal->use_adaptive_rx_coalesce = 0;
+				enic_intr_coal_set_rx(enic, rx_coalesce_usecs);
+			}
+		} else {
+			if (ecmd->use_adaptive_rx_coalesce)
+				rxcoal->use_adaptive_rx_coalesce = 1;
+			else
+				enic_intr_coal_set_rx(enic, rx_coalesce_usecs);
 		}
 
+		if (ecmd->rx_coalesce_usecs_high) {
+			if (rx_coalesce_usecs_high <
+			    (rx_coalesce_usecs_low + ENIC_AIC_LARGE_PKT_DIFF))
+				return -EINVAL;
+			rxcoal->range_end = rx_coalesce_usecs_high;
+			rxcoal->small_pkt_range_start = rx_coalesce_usecs_low;
+			rxcoal->large_pkt_range_start = rx_coalesce_usecs_low +
+							ENIC_AIC_LARGE_PKT_DIFF;
+		}
 		break;
 	default:
 		break;
@@ -253,5 +302,5 @@ static const struct ethtool_ops enic_ethtool_ops = {
 
 void enic_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &enic_ethtool_ops);
+	netdev->ethtool_ops = &enic_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 2945718ce80..f32f828b7f3 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -38,6 +38,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/prefetch.h>
 #include <net/ip6_checksum.h>
+#include <linux/ktime.h>
 
 #include "cq_enet_desc.h"
 #include "vnic_dev.h"
@@ -72,6 +73,35 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, enic_id_table);
 
+#define ENIC_LARGE_PKT_THRESHOLD		1000
+#define ENIC_MAX_COALESCE_TIMERS		10
+/*  Interrupt moderation table, which will be used to decide the
+ *  coalescing timer values
+ *  {rx_rate in Mbps, mapping percentage of the range}
+ */
+struct enic_intr_mod_table mod_table[ENIC_MAX_COALESCE_TIMERS + 1] = {
+	{4000,  0},
+	{4400, 10},
+	{5060, 20},
+	{5230, 30},
+	{5540, 40},
+	{5820, 50},
+	{6120, 60},
+	{6435, 70},
+	{6745, 80},
+	{7000, 90},
+	{0xFFFFFFFF, 100}
+};
+
+/* This table helps the driver to pick different ranges for rx coalescing
+ * timer depending on the link speed.
+ */
+struct enic_intr_mod_range mod_range[ENIC_MAX_LINK_SPEEDS] = {
+	{0,  0}, /* 0  - 4  Gbps */
+	{0,  3}, /* 4  - 10 Gbps */
+	{3,  6}, /* 10 - 40 Gbps */
+};
+
 int enic_is_dynamic(struct enic *enic)
 {
 	return enic->pdev->device == PCI_DEVICE_ID_CISCO_VIC_ENET_DYN;
@@ -586,8 +616,71 @@ static struct rtnl_link_stats64 *enic_get_stats(struct net_device *netdev,
 	return net_stats;
 }
 
+static int enic_mc_sync(struct net_device *netdev, const u8 *mc_addr)
+{
+	struct enic *enic = netdev_priv(netdev);
+
+	if (enic->mc_count == ENIC_MULTICAST_PERFECT_FILTERS) {
+		unsigned int mc_count = netdev_mc_count(netdev);
+
+		netdev_warn(netdev, "Registering only %d out of %d multicast addresses\n",
+			    ENIC_MULTICAST_PERFECT_FILTERS, mc_count);
+
+		return -ENOSPC;
+	}
+
+	enic_dev_add_addr(enic, mc_addr);
+	enic->mc_count++;
+
+	return 0;
+}
+
+static int enic_mc_unsync(struct net_device *netdev, const u8 *mc_addr)
+{
+	struct enic *enic = netdev_priv(netdev);
+
+	enic_dev_del_addr(enic, mc_addr);
+	enic->mc_count--;
+
+	return 0;
+}
+
+static int enic_uc_sync(struct net_device *netdev, const u8 *uc_addr)
+{
+	struct enic *enic = netdev_priv(netdev);
+
+	if (enic->uc_count == ENIC_UNICAST_PERFECT_FILTERS) {
+		unsigned int uc_count = netdev_uc_count(netdev);
+
+		netdev_warn(netdev, "Registering only %d out of %d unicast addresses\n",
+			    ENIC_UNICAST_PERFECT_FILTERS, uc_count);
+
+		return -ENOSPC;
+	}
+
+	enic_dev_add_addr(enic, uc_addr);
+	enic->uc_count++;
+
+	return 0;
+}
+
+static int enic_uc_unsync(struct net_device *netdev, const u8 *uc_addr)
+{
+	struct enic *enic = netdev_priv(netdev);
+
+	enic_dev_del_addr(enic, uc_addr);
+	enic->uc_count--;
+
+	return 0;
+}
+
 void enic_reset_addr_lists(struct enic *enic)
 {
+	struct net_device *netdev = enic->netdev;
+
+	__dev_uc_unsync(netdev, NULL);
+	__dev_mc_unsync(netdev, NULL);
+
 	enic->mc_count = 0;
 	enic->uc_count = 0;
 	enic->flags = 0;
@@ -654,112 +747,6 @@ static int enic_set_mac_address(struct net_device *netdev, void *p)
 	return enic_dev_add_station_addr(enic);
 }
 
-static void enic_update_multicast_addr_list(struct enic *enic)
-{
-	struct net_device *netdev = enic->netdev;
-	struct netdev_hw_addr *ha;
-	unsigned int mc_count = netdev_mc_count(netdev);
-	u8 mc_addr[ENIC_MULTICAST_PERFECT_FILTERS][ETH_ALEN];
-	unsigned int i, j;
-
-	if (mc_count > ENIC_MULTICAST_PERFECT_FILTERS) {
-		netdev_warn(netdev, "Registering only %d out of %d "
-			"multicast addresses\n",
-			ENIC_MULTICAST_PERFECT_FILTERS, mc_count);
-		mc_count = ENIC_MULTICAST_PERFECT_FILTERS;
-	}
-
-	/* Is there an easier way?  Trying to minimize to
-	 * calls to add/del multicast addrs.  We keep the
-	 * addrs from the last call in enic->mc_addr and
-	 * look for changes to add/del.
-	 */
-
-	i = 0;
-	netdev_for_each_mc_addr(ha, netdev) {
-		if (i == mc_count)
-			break;
-		memcpy(mc_addr[i++], ha->addr, ETH_ALEN);
-	}
-
-	for (i = 0; i < enic->mc_count; i++) {
-		for (j = 0; j < mc_count; j++)
-			if (ether_addr_equal(enic->mc_addr[i], mc_addr[j]))
-				break;
-		if (j == mc_count)
-			enic_dev_del_addr(enic, enic->mc_addr[i]);
-	}
-
-	for (i = 0; i < mc_count; i++) {
-		for (j = 0; j < enic->mc_count; j++)
-			if (ether_addr_equal(mc_addr[i], enic->mc_addr[j]))
-				break;
-		if (j == enic->mc_count)
-			enic_dev_add_addr(enic, mc_addr[i]);
-	}
-
-	/* Save the list to compare against next time
-	 */
-
-	for (i = 0; i < mc_count; i++)
-		memcpy(enic->mc_addr[i], mc_addr[i], ETH_ALEN);
-
-	enic->mc_count = mc_count;
-}
-
-static void enic_update_unicast_addr_list(struct enic *enic)
-{
-	struct net_device *netdev = enic->netdev;
-	struct netdev_hw_addr *ha;
-	unsigned int uc_count = netdev_uc_count(netdev);
-	u8 uc_addr[ENIC_UNICAST_PERFECT_FILTERS][ETH_ALEN];
-	unsigned int i, j;
-
-	if (uc_count > ENIC_UNICAST_PERFECT_FILTERS) {
-		netdev_warn(netdev, "Registering only %d out of %d "
-			"unicast addresses\n",
-			ENIC_UNICAST_PERFECT_FILTERS, uc_count);
-		uc_count = ENIC_UNICAST_PERFECT_FILTERS;
-	}
-
-	/* Is there an easier way?  Trying to minimize to
-	 * calls to add/del unicast addrs.  We keep the
-	 * addrs from the last call in enic->uc_addr and
-	 * look for changes to add/del.
-	 */
-
-	i = 0;
-	netdev_for_each_uc_addr(ha, netdev) {
-		if (i == uc_count)
-			break;
-		memcpy(uc_addr[i++], ha->addr, ETH_ALEN);
-	}
-
-	for (i = 0; i < enic->uc_count; i++) {
-		for (j = 0; j < uc_count; j++)
-			if (ether_addr_equal(enic->uc_addr[i], uc_addr[j]))
-				break;
-		if (j == uc_count)
-			enic_dev_del_addr(enic, enic->uc_addr[i]);
-	}
-
-	for (i = 0; i < uc_count; i++) {
-		for (j = 0; j < enic->uc_count; j++)
-			if (ether_addr_equal(uc_addr[i], enic->uc_addr[j]))
-				break;
-		if (j == enic->uc_count)
-			enic_dev_add_addr(enic, uc_addr[i]);
-	}
-
-	/* Save the list to compare against next time
-	 */
-
-	for (i = 0; i < uc_count; i++)
-		memcpy(enic->uc_addr[i], uc_addr[i], ETH_ALEN);
-
-	enic->uc_count = uc_count;
-}
-
 /* netif_tx_lock held, BHs disabled */
 static void enic_set_rx_mode(struct net_device *netdev)
 {
@@ -782,9 +769,9 @@ static void enic_set_rx_mode(struct net_device *netdev)
 	}
 
 	if (!promisc) {
-		enic_update_unicast_addr_list(enic);
+		__dev_uc_sync(netdev, enic_uc_sync, enic_uc_unsync);
 		if (!allmulti)
-			enic_update_multicast_addr_list(enic);
+			__dev_mc_sync(netdev, enic_mc_sync, enic_mc_unsync);
 	}
 }
 
@@ -979,6 +966,15 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq)
 	return 0;
 }
 
+static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
+				      u32 pkt_len)
+{
+	if (ENIC_LARGE_PKT_THRESHOLD <= pkt_len)
+		pkt_size->large_pkt_bytes_cnt += pkt_len;
+	else
+		pkt_size->small_pkt_bytes_cnt += pkt_len;
+}
+
 static void enic_rq_indicate_buf(struct vnic_rq *rq,
 	struct cq_desc *cq_desc, struct vnic_rq_buf *buf,
 	int skipped, void *opaque)
@@ -986,6 +982,7 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 	struct enic *enic = vnic_dev_priv(rq->vdev);
 	struct net_device *netdev = enic->netdev;
 	struct sk_buff *skb;
+	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
 
 	u8 type, color, eop, sop, ingress_port, vlan_stripped;
 	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
@@ -1056,6 +1053,9 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 			napi_gro_receive(&enic->napi[q_number], skb);
 		else
 			netif_receive_skb(skb);
+		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
+			enic_intr_update_pkt_size(&cq->pkt_size_counter,
+						  bytes_written);
 	} else {
 
 		/* Buffer overflow
@@ -1134,6 +1134,64 @@ static int enic_poll(struct napi_struct *napi, int budget)
 	return rq_work_done;
 }
 
+static void enic_set_int_moderation(struct enic *enic, struct vnic_rq *rq)
+{
+	unsigned int intr = enic_msix_rq_intr(enic, rq->index);
+	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
+	u32 timer = cq->tobe_rx_coal_timeval;
+
+	if (cq->tobe_rx_coal_timeval != cq->cur_rx_coal_timeval) {
+		vnic_intr_coalescing_timer_set(&enic->intr[intr], timer);
+		cq->cur_rx_coal_timeval = cq->tobe_rx_coal_timeval;
+	}
+}
+
+static void enic_calc_int_moderation(struct enic *enic, struct vnic_rq *rq)
+{
+	struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting;
+	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
+	struct vnic_rx_bytes_counter *pkt_size_counter = &cq->pkt_size_counter;
+	int index;
+	u32 timer;
+	u32 range_start;
+	u32 traffic;
+	u64 delta;
+	ktime_t now = ktime_get();
+
+	delta = ktime_us_delta(now, cq->prev_ts);
+	if (delta < ENIC_AIC_TS_BREAK)
+		return;
+	cq->prev_ts = now;
+
+	traffic = pkt_size_counter->large_pkt_bytes_cnt +
+		  pkt_size_counter->small_pkt_bytes_cnt;
+	/* The table takes Mbps
+	 * traffic *= 8    => bits
+	 * traffic *= (10^6 / delta)    => bps
+	 * traffic /= 10^6     => Mbps
+	 *
+	 * Combining, traffic *= (8 / delta)
+	 */
+
+	traffic <<= 3;
+	traffic = delta > UINT_MAX ? 0 : traffic / (u32)delta;
+
+	for (index = 0; index < ENIC_MAX_COALESCE_TIMERS; index++)
+		if (traffic < mod_table[index].rx_rate)
+			break;
+	range_start = (pkt_size_counter->small_pkt_bytes_cnt >
+		       pkt_size_counter->large_pkt_bytes_cnt << 1) ?
+		      rx_coal->small_pkt_range_start :
+		      rx_coal->large_pkt_range_start;
+	timer = range_start + ((rx_coal->range_end - range_start) *
+			       mod_table[index].range_percent / 100);
+	/* Damping */
+	cq->tobe_rx_coal_timeval = (timer + cq->tobe_rx_coal_timeval) >> 1;
+
+	pkt_size_counter->large_pkt_bytes_cnt = 0;
+	pkt_size_counter->small_pkt_bytes_cnt = 0;
+}
+
 static int enic_poll_msix(struct napi_struct *napi, int budget)
 {
 	struct net_device *netdev = napi->dev;
@@ -1171,6 +1229,13 @@ static int enic_poll_msix(struct napi_struct *napi, int budget)
 
 	if (err)
 		work_done = work_to_do;
+	if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
+		/* Call the function which refreshes
+		 * the intr coalescing timer value based on
+		 * the traffic.  This is supported only in
+		 * the case of MSI-x mode
+		 */
+		enic_calc_int_moderation(enic, &enic->rq[rq]);
 
 	if (work_done < work_to_do) {
 
@@ -1179,6 +1244,8 @@ static int enic_poll_msix(struct napi_struct *napi, int budget)
 		 */
 
 		napi_complete(napi);
+		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
+			enic_set_int_moderation(enic, &enic->rq[rq]);
 		vnic_intr_unmask(&enic->intr[intr]);
 	}
 
@@ -1314,6 +1381,42 @@ static void enic_synchronize_irqs(struct enic *enic)
 	}
 }
 
+static void enic_set_rx_coal_setting(struct enic *enic)
+{
+	unsigned int speed;
+	int index = -1;
+	struct enic_rx_coal *rx_coal = &enic->rx_coalesce_setting;
+
+	/* If intr mode is not MSIX, do not do adaptive coalescing */
+	if (VNIC_DEV_INTR_MODE_MSIX != vnic_dev_get_intr_mode(enic->vdev)) {
+		netdev_info(enic->netdev, "INTR mode is not MSIX, Not initializing adaptive coalescing");
+		return;
+	}
+
+	/* 1. Read the link speed from fw
+	 * 2. Pick the default range for the speed
+	 * 3. Update it in enic->rx_coalesce_setting
+	 */
+	speed = vnic_dev_port_speed(enic->vdev);
+	if (ENIC_LINK_SPEED_10G < speed)
+		index = ENIC_LINK_40G_INDEX;
+	else if (ENIC_LINK_SPEED_4G < speed)
+		index = ENIC_LINK_10G_INDEX;
+	else
+		index = ENIC_LINK_4G_INDEX;
+
+	rx_coal->small_pkt_range_start = mod_range[index].small_pkt_range_start;
+	rx_coal->large_pkt_range_start = mod_range[index].large_pkt_range_start;
+	rx_coal->range_end = ENIC_RX_COALESCE_RANGE_END;
+
+	/* Start with the value provided by UCSM */
+	for (index = 0; index < enic->rq_count; index++)
+		enic->cq[index].cur_rx_coal_timeval =
+				enic->config.intr_timer_usec;
+
+	rx_coal->use_adaptive_rx_coalesce = 1;
+}
+
 static int enic_dev_notify_set(struct enic *enic)
 {
 	int err;
@@ -2231,6 +2334,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	enic->notify_timer.function = enic_notify_timer;
 	enic->notify_timer.data = (unsigned long)enic;
 
+	enic_set_rx_coal_setting(enic);
 	INIT_WORK(&enic->reset, enic_reset);
 	INIT_WORK(&enic->change_mtu_work, enic_change_mtu_work);
 
@@ -2250,6 +2354,9 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	enic->tx_coalesce_usecs = enic->config.intr_timer_usec;
+	/* rx coalesce time already got initialized. This gets used
+	 * if adaptive coal is turned off
+	 */
 	enic->rx_coalesce_usecs = enic->tx_coalesce_usecs;
 
 	if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic))
diff --git a/drivers/net/ethernet/cisco/enic/vnic_cq.h b/drivers/net/ethernet/cisco/enic/vnic_cq.h
index 579315cbe80..4e6aa65857f 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_cq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_cq.h
@@ -50,6 +50,11 @@ struct vnic_cq_ctrl {
 	u32 pad10;
 };
 
+struct vnic_rx_bytes_counter {
+	unsigned int small_pkt_bytes_cnt;
+	unsigned int large_pkt_bytes_cnt;
+};
+
 struct vnic_cq {
 	unsigned int index;
 	struct vnic_dev *vdev;
@@ -58,6 +63,10 @@ struct vnic_cq {
 	unsigned int to_clean;
 	unsigned int last_color;
 	unsigned int interrupt_offset;
+	struct vnic_rx_bytes_counter pkt_size_counter;
+	unsigned int cur_rx_coal_timeval;
+	unsigned int tobe_rx_coal_timeval;
+	ktime_t prev_ts;
 };
 
 static inline unsigned int vnic_cq_service(struct vnic_cq *cq,
diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c
index 69dd92598b7..e86a45cb9e6 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c
@@ -657,7 +657,7 @@ int vnic_dev_packet_filter(struct vnic_dev *vdev, int directed, int multicast,
 	return err;
 }
 
-int vnic_dev_add_addr(struct vnic_dev *vdev, u8 *addr)
+int vnic_dev_add_addr(struct vnic_dev *vdev, const u8 *addr)
 {
 	u64 a0 = 0, a1 = 0;
 	int wait = 1000;
@@ -674,7 +674,7 @@ int vnic_dev_add_addr(struct vnic_dev *vdev, u8 *addr)
 	return err;
 }
 
-int vnic_dev_del_addr(struct vnic_dev *vdev, u8 *addr)
+int vnic_dev_del_addr(struct vnic_dev *vdev, const u8 *addr)
 {
 	u64 a0 = 0, a1 = 0;
 	int wait = 1000;
diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.h b/drivers/net/ethernet/cisco/enic/vnic_dev.h
index e670029862a..1f3b301f822 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.h
@@ -95,8 +95,8 @@ int vnic_dev_stats_dump(struct vnic_dev *vdev, struct vnic_stats **stats);
 int vnic_dev_hang_notify(struct vnic_dev *vdev);
 int vnic_dev_packet_filter(struct vnic_dev *vdev, int directed, int multicast,
 	int broadcast, int promisc, int allmulti);
-int vnic_dev_add_addr(struct vnic_dev *vdev, u8 *addr);
-int vnic_dev_del_addr(struct vnic_dev *vdev, u8 *addr);
+int vnic_dev_add_addr(struct vnic_dev *vdev, const u8 *addr);
+int vnic_dev_del_addr(struct vnic_dev *vdev, const u8 *addr);
 int vnic_dev_get_mac_addr(struct vnic_dev *vdev, u8 *mac_addr);
 int vnic_dev_notify_set(struct vnic_dev *vdev, u16 intr);
 int vnic_dev_notify_unset(struct vnic_dev *vdev);
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 8c4b93be333..13723c96d1a 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -109,6 +109,7 @@ typedef struct board_info {
 	u8		imr_all;
 
 	unsigned int	flags;
+	unsigned int	in_timeout:1;
 	unsigned int	in_suspend:1;
 	unsigned int	wake_supported:1;
 
@@ -187,13 +188,13 @@ dm9000_reset(board_info_t *db)
 	 * The essential point is that we have to do a double reset, and the
 	 * instruction is to set LBK into MAC internal loopback mode.
 	 */
-	iow(db, DM9000_NCR, 0x03);
+	iow(db, DM9000_NCR, NCR_RST | NCR_MAC_LBK);
 	udelay(100); /* Application note says at least 20 us */
 	if (ior(db, DM9000_NCR) & 1)
 		dev_err(db->dev, "dm9000 did not respond to first reset\n");
 
 	iow(db, DM9000_NCR, 0);
-	iow(db, DM9000_NCR, 0x03);
+	iow(db, DM9000_NCR, NCR_RST | NCR_MAC_LBK);
 	udelay(100);
 	if (ior(db, DM9000_NCR) & 1)
 		dev_err(db->dev, "dm9000 did not respond to second reset\n");
@@ -273,7 +274,7 @@ static void dm9000_dumpblk_32bit(void __iomem *reg, int count)
  */
 static void dm9000_msleep(board_info_t *db, unsigned int ms)
 {
-	if (db->in_suspend)
+	if (db->in_suspend || db->in_timeout)
 		mdelay(ms);
 	else
 		msleep(ms);
@@ -334,7 +335,8 @@ dm9000_phy_write(struct net_device *dev,
 	unsigned long reg_save;
 
 	dm9000_dbg(db, 5, "phy_write[%02x] = %04x\n", reg, value);
-	mutex_lock(&db->addr_lock);
+	if (!db->in_timeout)
+		mutex_lock(&db->addr_lock);
 
 	spin_lock_irqsave(&db->lock, flags);
 
@@ -365,7 +367,8 @@ dm9000_phy_write(struct net_device *dev,
 	writeb(reg_save, db->io_addr);
 
 	spin_unlock_irqrestore(&db->lock, flags);
-	mutex_unlock(&db->addr_lock);
+	if (!db->in_timeout)
+		mutex_unlock(&db->addr_lock);
 }
 
 /* dm9000_set_io
@@ -882,6 +885,18 @@ dm9000_hash_table(struct net_device *dev)
 	spin_unlock_irqrestore(&db->lock, flags);
 }
 
+static void
+dm9000_mask_interrupts(board_info_t *db)
+{
+	iow(db, DM9000_IMR, IMR_PAR);
+}
+
+static void
+dm9000_unmask_interrupts(board_info_t *db)
+{
+	iow(db, DM9000_IMR, db->imr_all);
+}
+
 /*
  * Initialize dm9000 board
  */
@@ -894,6 +909,9 @@ dm9000_init_dm9000(struct net_device *dev)
 
 	dm9000_dbg(db, 1, "entering %s\n", __func__);
 
+	dm9000_reset(db);
+	dm9000_mask_interrupts(db);
+
 	/* I/O mode */
 	db->io_mode = ior(db, DM9000_ISR) >> 6;	/* ISR bit7:6 keeps I/O mode */
 
@@ -941,9 +959,6 @@ dm9000_init_dm9000(struct net_device *dev)
 
 	db->imr_all = imr;
 
-	/* Enable TX/RX interrupt mask */
-	iow(db, DM9000_IMR, imr);
-
 	/* Init Driver variable */
 	db->tx_pkt_cnt = 0;
 	db->queue_pkt_len = 0;
@@ -959,17 +974,19 @@ static void dm9000_timeout(struct net_device *dev)
 
 	/* Save previous register address */
 	spin_lock_irqsave(&db->lock, flags);
+	db->in_timeout = 1;
 	reg_save = readb(db->io_addr);
 
 	netif_stop_queue(dev);
-	dm9000_reset(db);
 	dm9000_init_dm9000(dev);
+	dm9000_unmask_interrupts(db);
 	/* We can accept TX packets again */
 	dev->trans_start = jiffies; /* prevent tx timeout */
 	netif_wake_queue(dev);
 
 	/* Restore previous register address */
 	writeb(reg_save, db->io_addr);
+	db->in_timeout = 0;
 	spin_unlock_irqrestore(&db->lock, flags);
 }
 
@@ -1093,7 +1110,6 @@ dm9000_rx(struct net_device *dev)
 		if (rxbyte & DM9000_PKT_ERR) {
 			dev_warn(db->dev, "status check fail: %d\n", rxbyte);
 			iow(db, DM9000_RCR, 0x00);	/* Stop Device */
-			iow(db, DM9000_ISR, IMR_PAR);	/* Stop INT request */
 			return;
 		}
 
@@ -1193,9 +1209,7 @@ static irqreturn_t dm9000_interrupt(int irq, void *dev_id)
 	/* Save previous register address */
 	reg_save = readb(db->io_addr);
 
-	/* Disable all interrupts */
-	iow(db, DM9000_IMR, IMR_PAR);
-
+	dm9000_mask_interrupts(db);
 	/* Got DM9000 interrupt status */
 	int_status = ior(db, DM9000_ISR);	/* Got ISR */
 	iow(db, DM9000_ISR, int_status);	/* Clear ISR status */
@@ -1218,9 +1232,7 @@ static irqreturn_t dm9000_interrupt(int irq, void *dev_id)
 		}
 	}
 
-	/* Re-enable interrupt mask */
-	iow(db, DM9000_IMR, db->imr_all);
-
+	dm9000_unmask_interrupts(db);
 	/* Restore previous register address */
 	writeb(reg_save, db->io_addr);
 
@@ -1292,6 +1304,9 @@ dm9000_open(struct net_device *dev)
 	 * may work, and tell the user that this is a problem */
 
 	if (irqflags == IRQF_TRIGGER_NONE)
+		irqflags = irq_get_trigger_type(dev->irq);
+
+	if (irqflags == IRQF_TRIGGER_NONE)
 		dev_warn(db->dev, "WARNING: no IRQ resource flags set.\n");
 
 	irqflags |= IRQF_SHARED;
@@ -1301,11 +1316,14 @@ dm9000_open(struct net_device *dev)
 	mdelay(1); /* delay needs by DM9000B */
 
 	/* Initialize DM9000 board */
-	dm9000_reset(db);
 	dm9000_init_dm9000(dev);
 
 	if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
 		return -EAGAIN;
+	/* Now that we have an interrupt handler hooked up we can unmask
+	 * our interrupts
+	 */
+	dm9000_unmask_interrupts(db);
 
 	/* Init driver variable */
 	db->dbug_cnt = 0;
@@ -1313,7 +1331,8 @@ dm9000_open(struct net_device *dev)
 	mii_check_media(&db->mii, netif_msg_link(db), 1);
 	netif_start_queue(dev);
 
-	dm9000_schedule_poll(db);
+	/* Poll initial link status */
+	schedule_delayed_work(&db->phy_poll, 1);
 
 	return 0;
 }
@@ -1326,7 +1345,7 @@ dm9000_shutdown(struct net_device *dev)
 	/* RESET device */
 	dm9000_phy_write(dev, 0, MII_BMCR, BMCR_RESET);	/* PHY RESET */
 	iow(db, DM9000_GPR, 0x01);	/* Power-Down PHY */
-	iow(db, DM9000_IMR, IMR_PAR);	/* Disable all interrupt */
+	dm9000_mask_interrupts(db);
 	iow(db, DM9000_RCR, 0x00);	/* Disable RX */
 }
 
@@ -1547,12 +1566,7 @@ dm9000_probe(struct platform_device *pdev)
 	db->flags |= DM9000_PLATF_SIMPLE_PHY;
 #endif
 
-	/* Fixing bug on dm9000_probe, takeover dm9000_reset(db),
-	 * Need 'NCR_MAC_LBK' bit to indeed stable our DM9000 fifo
-	 * while probe stage.
-	 */
-
-	iow(db, DM9000_NCR, NCR_MAC_LBK | NCR_RST);
+	dm9000_reset(db);
 
 	/* try multiple times, DM9000 sometimes gets the read wrong */
 	for (i = 0; i < 8; i++) {
@@ -1695,8 +1709,8 @@ dm9000_drv_resume(struct device *dev)
 			/* reset if we were not in wake mode to ensure if
 			 * the device was powered off it is in a known state */
 			if (!db->wake_state) {
-				dm9000_reset(db);
 				dm9000_init_dm9000(ndev);
+				dm9000_unmask_interrupts(db);
 			}
 
 			netif_device_attach(ndev);
diff --git a/drivers/net/ethernet/dec/tulip/timer.c b/drivers/net/ethernet/dec/tulip/timer.c
index 768379b8aee..523d9dde50a 100644
--- a/drivers/net/ethernet/dec/tulip/timer.c
+++ b/drivers/net/ethernet/dec/tulip/timer.c
@@ -158,7 +158,7 @@ void comet_timer(unsigned long data)
 {
 	struct net_device *dev = (struct net_device *)data;
 	struct tulip_private *tp = netdev_priv(dev);
-	int next_tick = 60*HZ;
+	int next_tick = 2*HZ;
 
 	if (tulip_debug > 1)
 		netdev_dbg(dev, "Comet link status %04x partner capability %04x\n",
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 1642de78aac..861660841ce 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -1703,7 +1703,7 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 #ifdef CONFIG_TULIP_NAPI
 	netif_napi_add(dev, &tp->napi, tulip_poll, 16);
 #endif
-	SET_ETHTOOL_OPS(dev, &ops);
+	dev->ethtool_ops = &ops;
 
 	if (register_netdev(dev))
 		goto err_out_free_ring;
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index aa801a6af7b..80afec335a1 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -962,8 +962,8 @@ ULi_ethtool_gset(struct uli526x_board_info *db, struct ethtool_cmd *ecmd)
 	}
 	if(db->link_failed)
 	{
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	if (db->media_mode & ULI526X_AUTO)
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index 4fb756d219f..1274b6fdac8 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -227,7 +227,7 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	dev->netdev_ops = &netdev_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
-	SET_ETHTOOL_OPS(dev, &ethtool_ops);
+	dev->ethtool_ops = &ethtool_ops;
 #if 0
 	dev->features = NETIF_F_IP_CSUM;
 #endif
@@ -1185,8 +1185,8 @@ static int rio_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		ethtool_cmd_speed_set(cmd, np->speed);
 		cmd->duplex = np->full_duplex ? DUPLEX_FULL : DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(cmd, -1);
-		cmd->duplex = -1;
+		ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
+		cmd->duplex = DUPLEX_UNKNOWN;
 	}
 	if ( np->an_enable)
 		cmd->autoneg = AUTONEG_ENABLE;
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index d9e5ca0d48c..433c1e18544 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -577,7 +577,7 @@ static int sundance_probe1(struct pci_dev *pdev,
 
 	/* The chip-specific entries in the device structure. */
 	dev->netdev_ops = &netdev_ops;
-	SET_ETHTOOL_OPS(dev, &ethtool_ops);
+	dev->ethtool_ops = &ethtool_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
 
 	pci_set_drvdata(pdev, dev);
diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
index 4884205e56e..056b44b9347 100644
--- a/drivers/net/ethernet/ec_bhf.c
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -134,17 +134,17 @@ struct ec_bhf_priv {
 
 	struct pci_dev *dev;
 
-	void * __iomem io;
-	void * __iomem dma_io;
+	void __iomem *io;
+	void __iomem *dma_io;
 
 	struct hrtimer hrtimer;
 
 	int tx_dma_chan;
 	int rx_dma_chan;
-	void * __iomem ec_io;
-	void * __iomem fifo_io;
-	void * __iomem mii_io;
-	void * __iomem mac_io;
+	void __iomem *ec_io;
+	void __iomem *fifo_io;
+	void __iomem *mii_io;
+	void __iomem *mac_io;
 
 	struct bhf_dma rx_buf;
 	struct rx_desc *rx_descs;
@@ -297,7 +297,7 @@ static int ec_bhf_setup_offsets(struct ec_bhf_priv *priv)
 {
 	struct device *dev = PRIV_TO_DEV(priv);
 	unsigned block_count, i;
-	void * __iomem ec_info;
+	void __iomem *ec_info;
 
 	dev_dbg(dev, "Info block:\n");
 	dev_dbg(dev, "Type of function: %x\n", (unsigned)ioread16(priv->io));
@@ -569,8 +569,8 @@ static int ec_bhf_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	struct net_device *net_dev;
 	struct ec_bhf_priv *priv;
-	void * __iomem dma_io;
-	void * __iomem io;
+	void __iomem *dma_io;
+	void __iomem *io;
 	int err = 0;
 
 	err = pci_enable_device(dev);
@@ -615,7 +615,7 @@ static int ec_bhf_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	}
 
 	net_dev = alloc_etherdev(sizeof(struct ec_bhf_priv));
-	if (net_dev == 0) {
+	if (net_dev == NULL) {
 		err = -ENOMEM;
 		goto err_unmap_dma_io;
 	}
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 97db5a7179d..c2f5d2d3b93 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -120,6 +120,9 @@ static inline char *nic_name(struct pci_dev *pdev)
 #define MAX_VFS			30 /* Max VFs supported by BE3 FW */
 #define FW_VER_LEN		32
 
+#define	RSS_INDIR_TABLE_LEN	128
+#define RSS_HASH_KEY_LEN	40
+
 struct be_dma_mem {
 	void *va;
 	dma_addr_t dma;
@@ -371,6 +374,7 @@ enum vf_state {
 #define BE_FLAGS_LINK_STATUS_INIT		1
 #define BE_FLAGS_WORKER_SCHEDULED		(1 << 3)
 #define BE_FLAGS_VLAN_PROMISC			(1 << 4)
+#define BE_FLAGS_MCAST_PROMISC			(1 << 5)
 #define BE_FLAGS_NAPI_ENABLED			(1 << 9)
 #define BE_FLAGS_QNQ_ASYNC_EVT_RCVD		(1 << 11)
 #define BE_FLAGS_VXLAN_OFFLOADS			(1 << 12)
@@ -409,6 +413,13 @@ struct be_resources {
 	u32 if_cap_flags;
 };
 
+struct rss_info {
+	u64 rss_flags;
+	u8 rsstable[RSS_INDIR_TABLE_LEN];
+	u8 rss_queue[RSS_INDIR_TABLE_LEN];
+	u8 rss_hkey[RSS_HASH_KEY_LEN];
+};
+
 struct be_adapter {
 	struct pci_dev *pdev;
 	struct net_device *netdev;
@@ -445,7 +456,7 @@ struct be_adapter {
 	struct be_drv_stats drv_stats;
 	struct be_aic_obj aic_obj[MAX_EVT_QS];
 	u16 vlans_added;
-	u8 vlan_tag[VLAN_N_VID];
+	unsigned long vids[BITS_TO_LONGS(VLAN_N_VID)];
 	u8 vlan_prio_bmap;	/* Available Priority BitMap */
 	u16 recommended_prio;	/* Recommended Priority */
 	struct be_dma_mem rx_filter; /* Cmd DMA mem for rx-filter */
@@ -507,7 +518,7 @@ struct be_adapter {
 	u32 msg_enable;
 	int be_get_temp_freq;
 	u8 pf_number;
-	u64 rss_flags;
+	struct rss_info rss_info;
 };
 
 #define be_physfn(adapter)		(!adapter->virtfn)
@@ -546,9 +557,7 @@ static inline u16 be_max_qs(struct be_adapter *adapter)
 #define be_pvid_tagging_enabled(adapter)	(adapter->pvid)
 
 /* Is BE in QNQ multi-channel mode */
-#define be_is_qnq_mode(adapter)		(adapter->mc_type == FLEX10 ||  \
-					 adapter->mc_type == vNIC1 ||	\
-					 adapter->mc_type == UFP)
+#define be_is_qnq_mode(adapter)		(adapter->function_mode & QNQ_MODE)
 
 #define lancer_chip(adapter)	(adapter->pdev->device == OC_DEVICE_ID3 || \
 				 adapter->pdev->device == OC_DEVICE_ID4)
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index d1ec15af0d2..f4ea3490f44 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -52,8 +52,7 @@ static struct be_cmd_priv_map cmd_priv_map[] = {
 	}
 };
 
-static bool be_cmd_allowed(struct be_adapter *adapter, u8 opcode,
-			   u8 subsystem)
+static bool be_cmd_allowed(struct be_adapter *adapter, u8 opcode, u8 subsystem)
 {
 	int i;
 	int num_entries = sizeof(cmd_priv_map)/sizeof(struct be_cmd_priv_map);
@@ -120,21 +119,28 @@ static struct be_cmd_resp_hdr *be_decode_resp_hdr(u32 tag0, u32 tag1)
 	return (void *)addr;
 }
 
-static int be_mcc_compl_process(struct be_adapter *adapter,
-				struct be_mcc_compl *compl)
+static bool be_skip_err_log(u8 opcode, u16 base_status, u16 addl_status)
 {
-	u16 compl_status, extd_status;
-	struct be_cmd_resp_hdr *resp_hdr;
-	u8 opcode = 0, subsystem = 0;
-
-	/* Just swap the status to host endian; mcc tag is opaquely copied
-	 * from mcc_wrb */
-	be_dws_le_to_cpu(compl, 4);
-
-	compl_status = (compl->status >> CQE_STATUS_COMPL_SHIFT) &
-				CQE_STATUS_COMPL_MASK;
+	if (base_status == MCC_STATUS_NOT_SUPPORTED ||
+	    base_status == MCC_STATUS_ILLEGAL_REQUEST ||
+	    addl_status == MCC_ADDL_STATUS_TOO_MANY_INTERFACES ||
+	    (opcode == OPCODE_COMMON_WRITE_FLASHROM &&
+	    (base_status == MCC_STATUS_ILLEGAL_FIELD ||
+	     addl_status == MCC_ADDL_STATUS_FLASH_IMAGE_CRC_MISMATCH)))
+		return true;
+	else
+		return false;
+}
 
-	resp_hdr = be_decode_resp_hdr(compl->tag0, compl->tag1);
+/* Place holder for all the async MCC cmds wherein the caller is not in a busy
+ * loop (has not issued be_mcc_notify_wait())
+ */
+static void be_async_cmd_process(struct be_adapter *adapter,
+				 struct be_mcc_compl *compl,
+				 struct be_cmd_resp_hdr *resp_hdr)
+{
+	enum mcc_base_status base_status = base_status(compl->status);
+	u8 opcode = 0, subsystem = 0;
 
 	if (resp_hdr) {
 		opcode = resp_hdr->opcode;
@@ -144,61 +150,86 @@ static int be_mcc_compl_process(struct be_adapter *adapter,
 	if (opcode == OPCODE_LOWLEVEL_LOOPBACK_TEST &&
 	    subsystem == CMD_SUBSYSTEM_LOWLEVEL) {
 		complete(&adapter->et_cmd_compl);
-		return 0;
+		return;
 	}
 
-	if (((opcode == OPCODE_COMMON_WRITE_FLASHROM) ||
-	     (opcode == OPCODE_COMMON_WRITE_OBJECT)) &&
-	    (subsystem == CMD_SUBSYSTEM_COMMON)) {
-		adapter->flash_status = compl_status;
+	if ((opcode == OPCODE_COMMON_WRITE_FLASHROM ||
+	     opcode == OPCODE_COMMON_WRITE_OBJECT) &&
+	    subsystem == CMD_SUBSYSTEM_COMMON) {
+		adapter->flash_status = compl->status;
 		complete(&adapter->et_cmd_compl);
+		return;
 	}
 
-	if (compl_status == MCC_STATUS_SUCCESS) {
-		if (((opcode == OPCODE_ETH_GET_STATISTICS) ||
-		     (opcode == OPCODE_ETH_GET_PPORT_STATS)) &&
-		    (subsystem == CMD_SUBSYSTEM_ETH)) {
-			be_parse_stats(adapter);
-			adapter->stats_cmd_sent = false;
-		}
-		if (opcode == OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES &&
-		    subsystem == CMD_SUBSYSTEM_COMMON) {
+	if ((opcode == OPCODE_ETH_GET_STATISTICS ||
+	     opcode == OPCODE_ETH_GET_PPORT_STATS) &&
+	    subsystem == CMD_SUBSYSTEM_ETH &&
+	    base_status == MCC_STATUS_SUCCESS) {
+		be_parse_stats(adapter);
+		adapter->stats_cmd_sent = false;
+		return;
+	}
+
+	if (opcode == OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES &&
+	    subsystem == CMD_SUBSYSTEM_COMMON) {
+		if (base_status == MCC_STATUS_SUCCESS) {
 			struct be_cmd_resp_get_cntl_addnl_attribs *resp =
-				(void *)resp_hdr;
+							(void *)resp_hdr;
 			adapter->drv_stats.be_on_die_temperature =
-				resp->on_die_temperature;
-		}
-	} else {
-		if (opcode == OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES)
+						resp->on_die_temperature;
+		} else {
 			adapter->be_get_temp_freq = 0;
+		}
+		return;
+	}
+}
+
+static int be_mcc_compl_process(struct be_adapter *adapter,
+				struct be_mcc_compl *compl)
+{
+	enum mcc_base_status base_status;
+	enum mcc_addl_status addl_status;
+	struct be_cmd_resp_hdr *resp_hdr;
+	u8 opcode = 0, subsystem = 0;
+
+	/* Just swap the status to host endian; mcc tag is opaquely copied
+	 * from mcc_wrb */
+	be_dws_le_to_cpu(compl, 4);
+
+	base_status = base_status(compl->status);
+	addl_status = addl_status(compl->status);
+
+	resp_hdr = be_decode_resp_hdr(compl->tag0, compl->tag1);
+	if (resp_hdr) {
+		opcode = resp_hdr->opcode;
+		subsystem = resp_hdr->subsystem;
+	}
+
+	be_async_cmd_process(adapter, compl, resp_hdr);
 
-		if (compl_status == MCC_STATUS_NOT_SUPPORTED ||
-			compl_status == MCC_STATUS_ILLEGAL_REQUEST)
-			goto done;
+	if (base_status != MCC_STATUS_SUCCESS &&
+	    !be_skip_err_log(opcode, base_status, addl_status)) {
 
-		if (compl_status == MCC_STATUS_UNAUTHORIZED_REQUEST) {
+		if (base_status == MCC_STATUS_UNAUTHORIZED_REQUEST) {
 			dev_warn(&adapter->pdev->dev,
 				 "VF is not privileged to issue opcode %d-%d\n",
 				 opcode, subsystem);
 		} else {
-			extd_status = (compl->status >> CQE_STATUS_EXTD_SHIFT) &
-					CQE_STATUS_EXTD_MASK;
 			dev_err(&adapter->pdev->dev,
 				"opcode %d-%d failed:status %d-%d\n",
-				opcode, subsystem, compl_status, extd_status);
-
-			if (extd_status == MCC_ADDL_STS_INSUFFICIENT_RESOURCES)
-				return extd_status;
+				opcode, subsystem, base_status, addl_status);
 		}
 	}
-done:
-	return compl_status;
+	return compl->status;
 }
 
 /* Link state evt is a string of bytes; no need for endian swapping */
 static void be_async_link_state_process(struct be_adapter *adapter,
-		struct be_async_event_link_state *evt)
+					struct be_mcc_compl *compl)
 {
+	struct be_async_event_link_state *evt =
+			(struct be_async_event_link_state *)compl;
+
 	/* When link status changes, link speed must be re-queried from FW */
 	adapter->phy.link_speed = -1;
 
@@ -221,8 +252,11 @@ static void be_async_link_state_process(struct be_adapter *adapter,
 
 /* Grp5 CoS Priority evt */
 static void be_async_grp5_cos_priority_process(struct be_adapter *adapter,
-		struct be_async_event_grp5_cos_priority *evt)
+					       struct be_mcc_compl *compl)
 {
+	struct be_async_event_grp5_cos_priority *evt =
+			(struct be_async_event_grp5_cos_priority *)compl;
+
 	if (evt->valid) {
 		adapter->vlan_prio_bmap = evt->available_priority_bmap;
 		adapter->recommended_prio &= ~VLAN_PRIO_MASK;
@@ -233,8 +267,11 @@ static void be_async_grp5_cos_priority_process(struct be_adapter *adapter,
 
 /* Grp5 QOS Speed evt: qos_link_speed is in units of 10 Mbps */
 static void be_async_grp5_qos_speed_process(struct be_adapter *adapter,
-		struct be_async_event_grp5_qos_link_speed *evt)
+					    struct be_mcc_compl *compl)
 {
+	struct be_async_event_grp5_qos_link_speed *evt =
+			(struct be_async_event_grp5_qos_link_speed *)compl;
+
 	if (adapter->phy.link_speed >= 0 &&
 	    evt->physical_port == adapter->port_num)
 		adapter->phy.link_speed = le16_to_cpu(evt->qos_link_speed) * 10;
@@ -242,8 +279,11 @@ static void be_async_grp5_qos_speed_process(struct be_adapter *adapter,
 
 /*Grp5 PVID evt*/
 static void be_async_grp5_pvid_state_process(struct be_adapter *adapter,
-		struct be_async_event_grp5_pvid_state *evt)
+					     struct be_mcc_compl *compl)
 {
+	struct be_async_event_grp5_pvid_state *evt =
+			(struct be_async_event_grp5_pvid_state *)compl;
+
 	if (evt->enabled) {
 		adapter->pvid = le16_to_cpu(evt->tag) & VLAN_VID_MASK;
 		dev_info(&adapter->pdev->dev, "LPVID: %d\n", adapter->pvid);
@@ -253,26 +293,21 @@ static void be_async_grp5_pvid_state_process(struct be_adapter *adapter,
 }
 
 static void be_async_grp5_evt_process(struct be_adapter *adapter,
-		u32 trailer, struct be_mcc_compl *evt)
+				      struct be_mcc_compl *compl)
 {
-	u8 event_type = 0;
-
-	event_type = (trailer >> ASYNC_TRAILER_EVENT_TYPE_SHIFT) &
-		ASYNC_TRAILER_EVENT_TYPE_MASK;
+	u8 event_type = (compl->flags >> ASYNC_EVENT_TYPE_SHIFT) &
+				ASYNC_EVENT_TYPE_MASK;
 
 	switch (event_type) {
 	case ASYNC_EVENT_COS_PRIORITY:
-		be_async_grp5_cos_priority_process(adapter,
-		(struct be_async_event_grp5_cos_priority *)evt);
-	break;
+		be_async_grp5_cos_priority_process(adapter, compl);
+		break;
 	case ASYNC_EVENT_QOS_SPEED:
-		be_async_grp5_qos_speed_process(adapter,
-		(struct be_async_event_grp5_qos_link_speed *)evt);
-	break;
+		be_async_grp5_qos_speed_process(adapter, compl);
+		break;
 	case ASYNC_EVENT_PVID_STATE:
-		be_async_grp5_pvid_state_process(adapter,
-		(struct be_async_event_grp5_pvid_state *)evt);
-	break;
+		be_async_grp5_pvid_state_process(adapter, compl);
+		break;
 	default:
 		dev_warn(&adapter->pdev->dev, "Unknown grp5 event 0x%x!\n",
 			 event_type);
@@ -281,13 +316,13 @@ static void be_async_grp5_evt_process(struct be_adapter *adapter,
 }
 
 static void be_async_dbg_evt_process(struct be_adapter *adapter,
-		u32 trailer, struct be_mcc_compl *cmp)
+				     struct be_mcc_compl *cmp)
 {
 	u8 event_type = 0;
 	struct be_async_event_qnq *evt = (struct be_async_event_qnq *) cmp;
 
-	event_type = (trailer >> ASYNC_TRAILER_EVENT_TYPE_SHIFT) &
-		ASYNC_TRAILER_EVENT_TYPE_MASK;
+	event_type = (cmp->flags >> ASYNC_EVENT_TYPE_SHIFT) &
+			ASYNC_EVENT_TYPE_MASK;
 
 	switch (event_type) {
 	case ASYNC_DEBUG_EVENT_TYPE_QNQ:
@@ -302,25 +337,33 @@ static void be_async_dbg_evt_process(struct be_adapter *adapter,
 	}
 }
 
-static inline bool is_link_state_evt(u32 trailer)
+static inline bool is_link_state_evt(u32 flags)
 {
-	return ((trailer >> ASYNC_TRAILER_EVENT_CODE_SHIFT) &
-		ASYNC_TRAILER_EVENT_CODE_MASK) ==
-				ASYNC_EVENT_CODE_LINK_STATE;
+	return ((flags >> ASYNC_EVENT_CODE_SHIFT) & ASYNC_EVENT_CODE_MASK) ==
+			ASYNC_EVENT_CODE_LINK_STATE;
 }
 
-static inline bool is_grp5_evt(u32 trailer)
+static inline bool is_grp5_evt(u32 flags)
 {
-	return (((trailer >> ASYNC_TRAILER_EVENT_CODE_SHIFT) &
-		ASYNC_TRAILER_EVENT_CODE_MASK) ==
-				ASYNC_EVENT_CODE_GRP_5);
+	return ((flags >> ASYNC_EVENT_CODE_SHIFT) & ASYNC_EVENT_CODE_MASK) ==
+			ASYNC_EVENT_CODE_GRP_5;
 }
 
-static inline bool is_dbg_evt(u32 trailer)
+static inline bool is_dbg_evt(u32 flags)
 {
-	return (((trailer >> ASYNC_TRAILER_EVENT_CODE_SHIFT) &
-		ASYNC_TRAILER_EVENT_CODE_MASK) ==
-				ASYNC_EVENT_CODE_QNQ);
+	return ((flags >> ASYNC_EVENT_CODE_SHIFT) & ASYNC_EVENT_CODE_MASK) ==
+			ASYNC_EVENT_CODE_QNQ;
+}
+
+static void be_mcc_event_process(struct be_adapter *adapter,
+				 struct be_mcc_compl *compl)
+{
+	if (is_link_state_evt(compl->flags))
+		be_async_link_state_process(adapter, compl);
+	else if (is_grp5_evt(compl->flags))
+		be_async_grp5_evt_process(adapter, compl);
+	else if (is_dbg_evt(compl->flags))
+		be_async_dbg_evt_process(adapter, compl);
 }
 
 static struct be_mcc_compl *be_mcc_compl_get(struct be_adapter *adapter)
@@ -362,21 +405,13 @@ int be_process_mcc(struct be_adapter *adapter)
 	struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 
 	spin_lock(&adapter->mcc_cq_lock);
+
 	while ((compl = be_mcc_compl_get(adapter))) {
 		if (compl->flags & CQE_FLAGS_ASYNC_MASK) {
-			/* Interpret flags as an async trailer */
-			if (is_link_state_evt(compl->flags))
-				be_async_link_state_process(adapter,
-				(struct be_async_event_link_state *) compl);
-			else if (is_grp5_evt(compl->flags))
-				be_async_grp5_evt_process(adapter,
-				compl->flags, compl);
-			else if (is_dbg_evt(compl->flags))
-				be_async_dbg_evt_process(adapter,
-				compl->flags, compl);
+			be_mcc_event_process(adapter, compl);
 		} else if (compl->flags & CQE_FLAGS_COMPLETED_MASK) {
-				status = be_mcc_compl_process(adapter, compl);
-				atomic_dec(&mcc_obj->q.used);
+			status = be_mcc_compl_process(adapter, compl);
+			atomic_dec(&mcc_obj->q.used);
 		}
 		be_mcc_compl_use(compl);
 		num++;
@@ -436,7 +471,9 @@ static int be_mcc_notify_wait(struct be_adapter *adapter)
 	if (status == -EIO)
 		goto out;
 
-	status = resp->status;
+	status = (resp->base_status |
+		  ((resp->addl_status & CQE_ADDL_STATUS_MASK) <<
+		   CQE_ADDL_STATUS_SHIFT));
 out:
 	return status;
 }
@@ -560,10 +597,8 @@ static bool lancer_provisioning_error(struct be_adapter *adapter)
 	u32 sliport_status = 0, sliport_err1 = 0, sliport_err2 = 0;
 	sliport_status = ioread32(adapter->db + SLIPORT_STATUS_OFFSET);
 	if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
-		sliport_err1 = ioread32(adapter->db +
-					SLIPORT_ERROR1_OFFSET);
-		sliport_err2 = ioread32(adapter->db +
-					SLIPORT_ERROR2_OFFSET);
+		sliport_err1 = ioread32(adapter->db + SLIPORT_ERROR1_OFFSET);
+		sliport_err2 = ioread32(adapter->db + SLIPORT_ERROR2_OFFSET);
 
 		if (sliport_err1 == SLIPORT_ERROR_NO_RESOURCE1 &&
 		    sliport_err2 == SLIPORT_ERROR_NO_RESOURCE2)
@@ -630,8 +665,7 @@ int be_fw_wait_ready(struct be_adapter *adapter)
 		if (stage == POST_STAGE_ARMFW_RDY)
 			return 0;
 
-		dev_info(dev, "Waiting for POST, %ds elapsed\n",
-			 timeout);
+		dev_info(dev, "Waiting for POST, %ds elapsed\n", timeout);
 		if (msleep_interruptible(2000)) {
 			dev_err(dev, "Waiting for POST aborted\n");
 			return -EINTR;
@@ -649,8 +683,7 @@ static inline struct be_sge *nonembedded_sgl(struct be_mcc_wrb *wrb)
 	return &wrb->payload.sgl[0];
 }
 
-static inline void fill_wrb_tags(struct be_mcc_wrb *wrb,
-				 unsigned long addr)
+static inline void fill_wrb_tags(struct be_mcc_wrb *wrb, unsigned long addr)
 {
 	wrb->tag0 = addr & 0xFFFFFFFF;
 	wrb->tag1 = upper_32_bits(addr);
@@ -659,8 +692,9 @@ static inline void fill_wrb_tags(struct be_mcc_wrb *wrb,
 /* Don't touch the hdr after it's prepared */
 /* mem will be NULL for embedded commands */
 static void be_wrb_cmd_hdr_prepare(struct be_cmd_req_hdr *req_hdr,
-				u8 subsystem, u8 opcode, int cmd_len,
-				struct be_mcc_wrb *wrb, struct be_dma_mem *mem)
+				   u8 subsystem, u8 opcode, int cmd_len,
+				   struct be_mcc_wrb *wrb,
+				   struct be_dma_mem *mem)
 {
 	struct be_sge *sge;
 
@@ -683,7 +717,7 @@ static void be_wrb_cmd_hdr_prepare(struct be_cmd_req_hdr *req_hdr,
 }
 
 static void be_cmd_page_addrs_prepare(struct phys_addr *pages, u32 max_pages,
-			struct be_dma_mem *mem)
+				      struct be_dma_mem *mem)
 {
 	int i, buf_pages = min(PAGES_4K_SPANNED(mem->va, mem->size), max_pages);
 	u64 dma = (u64)mem->dma;
@@ -868,7 +902,8 @@ int be_cmd_eq_create(struct be_adapter *adapter, struct be_eq_obj *eqo)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_EQ_CREATE, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_EQ_CREATE, sizeof(*req), wrb,
+			       NULL);
 
 	/* Support for EQ_CREATEv2 available only SH-R onwards */
 	if (!(BEx_chip(adapter) || lancer_chip(adapter)))
@@ -917,7 +952,8 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_NTWK_MAC_QUERY, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_NTWK_MAC_QUERY, sizeof(*req), wrb,
+			       NULL);
 	req->type = MAC_ADDRESS_TYPE_NETWORK;
 	if (permanent) {
 		req->permanent = 1;
@@ -940,7 +976,7 @@ err:
 
 /* Uses synchronous MCCQ */
 int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr,
-		u32 if_id, u32 *pmac_id, u32 domain)
+		    u32 if_id, u32 *pmac_id, u32 domain)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_pmac_add *req;
@@ -956,7 +992,8 @@ int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_NTWK_PMAC_ADD, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_NTWK_PMAC_ADD, sizeof(*req), wrb,
+			       NULL);
 
 	req->hdr.domain = domain;
 	req->if_id = cpu_to_le32(if_id);
@@ -1012,7 +1049,7 @@ err:
 
 /* Uses Mbox */
 int be_cmd_cq_create(struct be_adapter *adapter, struct be_queue_info *cq,
-		struct be_queue_info *eq, bool no_delay, int coalesce_wm)
+		     struct be_queue_info *eq, bool no_delay, int coalesce_wm)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_cq_create *req;
@@ -1028,17 +1065,18 @@ int be_cmd_cq_create(struct be_adapter *adapter, struct be_queue_info *cq,
 	ctxt = &req->context;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_CQ_CREATE, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_CQ_CREATE, sizeof(*req), wrb,
+			       NULL);
 
 	req->num_pages =  cpu_to_le16(PAGES_4K_SPANNED(q_mem->va, q_mem->size));
 
 	if (BEx_chip(adapter)) {
 		AMAP_SET_BITS(struct amap_cq_context_be, coalescwm, ctxt,
-								coalesce_wm);
+			      coalesce_wm);
 		AMAP_SET_BITS(struct amap_cq_context_be, nodelay,
-								ctxt, no_delay);
+			      ctxt, no_delay);
 		AMAP_SET_BITS(struct amap_cq_context_be, count, ctxt,
-						__ilog2_u32(cq->len/256));
+			      __ilog2_u32(cq->len / 256));
 		AMAP_SET_BITS(struct amap_cq_context_be, valid, ctxt, 1);
 		AMAP_SET_BITS(struct amap_cq_context_be, eventable, ctxt, 1);
 		AMAP_SET_BITS(struct amap_cq_context_be, eqid, ctxt, eq->id);
@@ -1053,14 +1091,12 @@ int be_cmd_cq_create(struct be_adapter *adapter, struct be_queue_info *cq,
 			AMAP_SET_BITS(struct amap_cq_context_v2, coalescwm,
 				      ctxt, coalesce_wm);
 		AMAP_SET_BITS(struct amap_cq_context_v2, nodelay, ctxt,
-								no_delay);
+			      no_delay);
 		AMAP_SET_BITS(struct amap_cq_context_v2, count, ctxt,
-						__ilog2_u32(cq->len/256));
+			      __ilog2_u32(cq->len / 256));
 		AMAP_SET_BITS(struct amap_cq_context_v2, valid, ctxt, 1);
-		AMAP_SET_BITS(struct amap_cq_context_v2, eventable,
-								ctxt, 1);
-		AMAP_SET_BITS(struct amap_cq_context_v2, eqid,
-								ctxt, eq->id);
+		AMAP_SET_BITS(struct amap_cq_context_v2, eventable, ctxt, 1);
+		AMAP_SET_BITS(struct amap_cq_context_v2, eqid, ctxt, eq->id);
 	}
 
 	be_dws_cpu_to_le(ctxt, sizeof(req->context));
@@ -1088,8 +1124,8 @@ static u32 be_encoded_q_len(int q_len)
 }
 
 static int be_cmd_mccq_ext_create(struct be_adapter *adapter,
-				struct be_queue_info *mccq,
-				struct be_queue_info *cq)
+				  struct be_queue_info *mccq,
+				  struct be_queue_info *cq)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_mcc_ext_create *req;
@@ -1105,13 +1141,14 @@ static int be_cmd_mccq_ext_create(struct be_adapter *adapter,
 	ctxt = &req->context;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_MCC_CREATE_EXT, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_MCC_CREATE_EXT, sizeof(*req), wrb,
+			       NULL);
 
 	req->num_pages = cpu_to_le16(PAGES_4K_SPANNED(q_mem->va, q_mem->size));
 	if (BEx_chip(adapter)) {
 		AMAP_SET_BITS(struct amap_mcc_context_be, valid, ctxt, 1);
 		AMAP_SET_BITS(struct amap_mcc_context_be, ring_size, ctxt,
-						be_encoded_q_len(mccq->len));
+			      be_encoded_q_len(mccq->len));
 		AMAP_SET_BITS(struct amap_mcc_context_be, cq_id, ctxt, cq->id);
 	} else {
 		req->hdr.version = 1;
@@ -1145,8 +1182,8 @@ static int be_cmd_mccq_ext_create(struct be_adapter *adapter,
 }
 
 static int be_cmd_mccq_org_create(struct be_adapter *adapter,
-				struct be_queue_info *mccq,
-				struct be_queue_info *cq)
+				  struct be_queue_info *mccq,
+				  struct be_queue_info *cq)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_mcc_create *req;
@@ -1162,13 +1199,14 @@ static int be_cmd_mccq_org_create(struct be_adapter *adapter,
 	ctxt = &req->context;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_MCC_CREATE, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_MCC_CREATE, sizeof(*req), wrb,
+			       NULL);
 
 	req->num_pages = cpu_to_le16(PAGES_4K_SPANNED(q_mem->va, q_mem->size));
 
 	AMAP_SET_BITS(struct amap_mcc_context_be, valid, ctxt, 1);
 	AMAP_SET_BITS(struct amap_mcc_context_be, ring_size, ctxt,
-			be_encoded_q_len(mccq->len));
+		      be_encoded_q_len(mccq->len));
 	AMAP_SET_BITS(struct amap_mcc_context_be, cq_id, ctxt, cq->id);
 
 	be_dws_cpu_to_le(ctxt, sizeof(req->context));
@@ -1187,8 +1225,7 @@ static int be_cmd_mccq_org_create(struct be_adapter *adapter,
 }
 
 int be_cmd_mccq_create(struct be_adapter *adapter,
-			struct be_queue_info *mccq,
-			struct be_queue_info *cq)
+		       struct be_queue_info *mccq, struct be_queue_info *cq)
 {
 	int status;
 
@@ -1213,7 +1250,7 @@ int be_cmd_txq_create(struct be_adapter *adapter, struct be_tx_obj *txo)
 
 	req = embedded_payload(&wrb);
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH,
-				OPCODE_ETH_TX_CREATE, sizeof(*req), &wrb, NULL);
+			       OPCODE_ETH_TX_CREATE, sizeof(*req), &wrb, NULL);
 
 	if (lancer_chip(adapter)) {
 		req->hdr.version = 1;
@@ -1250,8 +1287,8 @@ int be_cmd_txq_create(struct be_adapter *adapter, struct be_tx_obj *txo)
 
 /* Uses MCC */
 int be_cmd_rxq_create(struct be_adapter *adapter,
-		struct be_queue_info *rxq, u16 cq_id, u16 frag_size,
-		u32 if_id, u32 rss, u8 *rss_id)
+		      struct be_queue_info *rxq, u16 cq_id, u16 frag_size,
+		      u32 if_id, u32 rss, u8 *rss_id)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_eth_rx_create *req;
@@ -1268,7 +1305,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH,
-				OPCODE_ETH_RX_CREATE, sizeof(*req), wrb, NULL);
+			       OPCODE_ETH_RX_CREATE, sizeof(*req), wrb, NULL);
 
 	req->cq_id = cpu_to_le16(cq_id);
 	req->frag_size = fls(frag_size) - 1;
@@ -1295,7 +1332,7 @@ err:
  * Uses Mbox
  */
 int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q,
-		int queue_type)
+		     int queue_type)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_q_destroy *req;
@@ -1334,7 +1371,7 @@ int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q,
 	}
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, subsys, opcode, sizeof(*req), wrb,
-				NULL);
+			       NULL);
 	req->id = cpu_to_le16(q->id);
 
 	status = be_mbox_notify_wait(adapter);
@@ -1361,7 +1398,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH,
-			OPCODE_ETH_RX_DESTROY, sizeof(*req), wrb, NULL);
+			       OPCODE_ETH_RX_DESTROY, sizeof(*req), wrb, NULL);
 	req->id = cpu_to_le16(q->id);
 
 	status = be_mcc_notify_wait(adapter);
@@ -1384,7 +1421,8 @@ int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags, u32 en_flags,
 
 	req = embedded_payload(&wrb);
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_NTWK_INTERFACE_CREATE, sizeof(*req), &wrb, NULL);
+			       OPCODE_COMMON_NTWK_INTERFACE_CREATE,
+			       sizeof(*req), &wrb, NULL);
 	req->hdr.domain = domain;
 	req->capability_flags = cpu_to_le32(cap_flags);
 	req->enable_flags = cpu_to_le32(en_flags);
@@ -1422,7 +1460,8 @@ int be_cmd_if_destroy(struct be_adapter *adapter, int interface_id, u32 domain)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_NTWK_INTERFACE_DESTROY, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_NTWK_INTERFACE_DESTROY,
+			       sizeof(*req), wrb, NULL);
 	req->hdr.domain = domain;
 	req->interface_id = cpu_to_le32(interface_id);
 
@@ -1452,7 +1491,8 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	hdr = nonemb_cmd->va;
 
 	be_wrb_cmd_hdr_prepare(hdr, CMD_SUBSYSTEM_ETH,
-		OPCODE_ETH_GET_STATISTICS, nonemb_cmd->size, wrb, nonemb_cmd);
+			       OPCODE_ETH_GET_STATISTICS, nonemb_cmd->size, wrb,
+			       nonemb_cmd);
 
 	/* version 1 of the cmd is not supported only by BE2 */
 	if (BE2_chip(adapter))
@@ -1472,7 +1512,7 @@ err:
 
 /* Lancer Stats */
 int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
-				struct be_dma_mem *nonemb_cmd)
+			       struct be_dma_mem *nonemb_cmd)
 {
 
 	struct be_mcc_wrb *wrb;
@@ -1493,8 +1533,8 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 	req = nonemb_cmd->va;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH,
-			OPCODE_ETH_GET_PPORT_STATS, nonemb_cmd->size, wrb,
-			nonemb_cmd);
+			       OPCODE_ETH_GET_PPORT_STATS, nonemb_cmd->size,
+			       wrb, nonemb_cmd);
 
 	req->cmd_params.params.pport_num = cpu_to_le16(adapter->hba_port_num);
 	req->cmd_params.params.reset_stats = 0;
@@ -1553,7 +1593,8 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_NTWK_LINK_STATUS_QUERY, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_NTWK_LINK_STATUS_QUERY,
+			       sizeof(*req), wrb, NULL);
 
 	/* version 1 of the cmd is not supported only by BE2 */
 	if (!BE2_chip(adapter))
@@ -1598,8 +1639,8 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES, sizeof(*req),
-		wrb, NULL);
+			       OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES,
+			       sizeof(*req), wrb, NULL);
 
 	be_mcc_notify(adapter);
 
@@ -1625,7 +1666,8 @@ int be_cmd_get_reg_len(struct be_adapter *adapter, u32 *log_size)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_MANAGE_FAT, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_MANAGE_FAT, sizeof(*req), wrb,
+			       NULL);
 	req->fat_operation = cpu_to_le32(QUERY_FAT);
 	status = be_mcc_notify_wait(adapter);
 	if (!status) {
@@ -1655,8 +1697,8 @@ void be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 
 	get_fat_cmd.size = sizeof(struct be_cmd_req_get_fat) + 60*1024;
 	get_fat_cmd.va = pci_alloc_consistent(adapter->pdev,
-			get_fat_cmd.size,
-			&get_fat_cmd.dma);
+					      get_fat_cmd.size,
+					      &get_fat_cmd.dma);
 	if (!get_fat_cmd.va) {
 		status = -ENOMEM;
 		dev_err(&adapter->pdev->dev,
@@ -1679,8 +1721,8 @@ void be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 
 		payload_len = sizeof(struct be_cmd_req_get_fat) + buf_size;
 		be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-				OPCODE_COMMON_MANAGE_FAT, payload_len, wrb,
-				&get_fat_cmd);
+				       OPCODE_COMMON_MANAGE_FAT, payload_len,
+				       wrb, &get_fat_cmd);
 
 		req->fat_operation = cpu_to_le32(RETRIEVE_FAT);
 		req->read_log_offset = cpu_to_le32(log_offset);
@@ -1691,8 +1733,8 @@ void be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 		if (!status) {
 			struct be_cmd_resp_get_fat *resp = get_fat_cmd.va;
 			memcpy(buf + offset,
-				resp->data_buffer,
-				le32_to_cpu(resp->read_log_length));
+			       resp->data_buffer,
+			       le32_to_cpu(resp->read_log_length));
 		} else {
 			dev_err(&adapter->pdev->dev, "FAT Table Retrieve error\n");
 			goto err;
@@ -1702,14 +1744,13 @@ void be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf)
 	}
 err:
 	pci_free_consistent(adapter->pdev, get_fat_cmd.size,
-			get_fat_cmd.va,
-			get_fat_cmd.dma);
+			    get_fat_cmd.va, get_fat_cmd.dma);
 	spin_unlock_bh(&adapter->mcc_lock);
 }
 
 /* Uses synchronous mcc */
 int be_cmd_get_fw_ver(struct be_adapter *adapter, char *fw_ver,
-			char *fw_on_flash)
+		      char *fw_on_flash)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_get_fw_version *req;
@@ -1726,7 +1767,8 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter, char *fw_ver,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_GET_FW_VERSION, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_GET_FW_VERSION, sizeof(*req), wrb,
+			       NULL);
 	status = be_mcc_notify_wait(adapter);
 	if (!status) {
 		struct be_cmd_resp_get_fw_version *resp = embedded_payload(wrb);
@@ -1759,7 +1801,8 @@ int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *set_eqd,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_MODIFY_EQ_DELAY, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_MODIFY_EQ_DELAY, sizeof(*req), wrb,
+			       NULL);
 
 	req->num_eq = cpu_to_le32(num);
 	for (i = 0; i < num; i++) {
@@ -1777,7 +1820,7 @@ err:
 
 /* Uses sycnhronous mcc */
 int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
-		       u32 num, bool promiscuous)
+		       u32 num)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_vlan_config *req;
@@ -1793,19 +1836,16 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_NTWK_VLAN_CONFIG, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_NTWK_VLAN_CONFIG, sizeof(*req),
+			       wrb, NULL);
 
 	req->interface_id = if_id;
-	req->promiscuous = promiscuous;
 	req->untagged = BE_IF_FLAGS_UNTAGGED & be_if_cap_flags(adapter) ? 1 : 0;
 	req->num_vlan = num;
-	if (!promiscuous) {
-		memcpy(req->normal_vlan, vtag_array,
-			req->num_vlan * sizeof(vtag_array[0]));
-	}
+	memcpy(req->normal_vlan, vtag_array,
+	       req->num_vlan * sizeof(vtag_array[0]));
 
 	status = be_mcc_notify_wait(adapter);
-
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
@@ -1827,18 +1867,19 @@ int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 	}
 	memset(req, 0, sizeof(*req));
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-				OPCODE_COMMON_NTWK_RX_FILTER, sizeof(*req),
-				wrb, mem);
+			       OPCODE_COMMON_NTWK_RX_FILTER, sizeof(*req),
+			       wrb, mem);
 
 	req->if_id = cpu_to_le32(adapter->if_handle);
 	if (flags & IFF_PROMISC) {
 		req->if_flags_mask = cpu_to_le32(BE_IF_FLAGS_PROMISCUOUS |
-					BE_IF_FLAGS_VLAN_PROMISCUOUS |
-					BE_IF_FLAGS_MCAST_PROMISCUOUS);
+						 BE_IF_FLAGS_VLAN_PROMISCUOUS |
+						 BE_IF_FLAGS_MCAST_PROMISCUOUS);
 		if (value == ON)
-			req->if_flags = cpu_to_le32(BE_IF_FLAGS_PROMISCUOUS |
-						BE_IF_FLAGS_VLAN_PROMISCUOUS |
-						BE_IF_FLAGS_MCAST_PROMISCUOUS);
+			req->if_flags =
+				cpu_to_le32(BE_IF_FLAGS_PROMISCUOUS |
+					    BE_IF_FLAGS_VLAN_PROMISCUOUS |
+					    BE_IF_FLAGS_MCAST_PROMISCUOUS);
 	} else if (flags & IFF_ALLMULTI) {
 		req->if_flags_mask = req->if_flags =
 				cpu_to_le32(BE_IF_FLAGS_MCAST_PROMISCUOUS);
@@ -1867,7 +1908,7 @@ int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 	}
 
 	if ((req->if_flags_mask & cpu_to_le32(be_if_cap_flags(adapter))) !=
-	     req->if_flags_mask) {
+	    req->if_flags_mask) {
 		dev_warn(&adapter->pdev->dev,
 			 "Cannot set rx filter flags 0x%x\n",
 			 req->if_flags_mask);
@@ -1905,7 +1946,8 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_SET_FLOW_CONTROL, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_SET_FLOW_CONTROL, sizeof(*req),
+			       wrb, NULL);
 
 	req->tx_flow_control = cpu_to_le16((u16)tx_fc);
 	req->rx_flow_control = cpu_to_le16((u16)rx_fc);
@@ -1938,7 +1980,8 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_GET_FLOW_CONTROL, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_GET_FLOW_CONTROL, sizeof(*req),
+			       wrb, NULL);
 
 	status = be_mcc_notify_wait(adapter);
 	if (!status) {
@@ -1968,7 +2011,8 @@ int be_cmd_query_fw_cfg(struct be_adapter *adapter, u32 *port_num,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_QUERY_FIRMWARE_CONFIG, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_QUERY_FIRMWARE_CONFIG,
+			       sizeof(*req), wrb, NULL);
 
 	status = be_mbox_notify_wait(adapter);
 	if (!status) {
@@ -2011,7 +2055,8 @@ int be_cmd_reset_function(struct be_adapter *adapter)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(req, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_FUNCTION_RESET, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_FUNCTION_RESET, sizeof(*req), wrb,
+			       NULL);
 
 	status = be_mbox_notify_wait(adapter);
 
@@ -2020,47 +2065,47 @@ int be_cmd_reset_function(struct be_adapter *adapter)
 }
 
 int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
-			u32 rss_hash_opts, u16 table_size)
+		      u32 rss_hash_opts, u16 table_size, const u8 *rss_hkey)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_rss_config *req;
-	u32 myhash[10] = {0x15d43fa5, 0x2534685a, 0x5f87693a, 0x5668494e,
-			0x33cf6a53, 0x383334c6, 0x76ac4257, 0x59b242b2,
-			0x3ea83c02, 0x4a110304};
 	int status;
 
 	if (!(be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS))
 		return 0;
 
-	if (mutex_lock_interruptible(&adapter->mbox_lock))
-		return -1;
+	spin_lock_bh(&adapter->mcc_lock);
 
-	wrb = wrb_from_mbox(adapter);
+	wrb = wrb_from_mccq(adapter);
+	if (!wrb) {
+		status = -EBUSY;
+		goto err;
+	}
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH,
-		OPCODE_ETH_RSS_CONFIG, sizeof(*req), wrb, NULL);
+			       OPCODE_ETH_RSS_CONFIG, sizeof(*req), wrb, NULL);
 
 	req->if_id = cpu_to_le32(adapter->if_handle);
 	req->enable_rss = cpu_to_le16(rss_hash_opts);
 	req->cpu_table_size_log2 = cpu_to_le16(fls(table_size) - 1);
 
-	if (lancer_chip(adapter) || skyhawk_chip(adapter))
+	if (!BEx_chip(adapter))
 		req->hdr.version = 1;
 
 	memcpy(req->cpu_table, rsstable, table_size);
-	memcpy(req->hash, myhash, sizeof(myhash));
+	memcpy(req->hash, rss_hkey, RSS_HASH_KEY_LEN);
 	be_dws_cpu_to_le(req->hash, sizeof(req->hash));
 
-	status = be_mbox_notify_wait(adapter);
-
-	mutex_unlock(&adapter->mbox_lock);
+	status = be_mcc_notify_wait(adapter);
+err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
 /* Uses sync mcc */
 int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
-			u8 bcn, u8 sts, u8 state)
+			    u8 bcn, u8 sts, u8 state)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_enable_disable_beacon *req;
@@ -2076,7 +2121,8 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_ENABLE_DISABLE_BEACON, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_ENABLE_DISABLE_BEACON,
+			       sizeof(*req), wrb, NULL);
 
 	req->port_num = port_num;
 	req->beacon_state = state;
@@ -2107,7 +2153,8 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_GET_BEACON_STATE, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_GET_BEACON_STATE, sizeof(*req),
+			       wrb, NULL);
 
 	req->port_num = port_num;
 
@@ -2146,20 +2193,20 @@ int lancer_cmd_write_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-				OPCODE_COMMON_WRITE_OBJECT,
-				sizeof(struct lancer_cmd_req_write_object), wrb,
-				NULL);
+			       OPCODE_COMMON_WRITE_OBJECT,
+			       sizeof(struct lancer_cmd_req_write_object), wrb,
+			       NULL);
 
 	ctxt = &req->context;
 	AMAP_SET_BITS(struct amap_lancer_write_obj_context,
-			write_length, ctxt, data_size);
+		      write_length, ctxt, data_size);
 
 	if (data_size == 0)
 		AMAP_SET_BITS(struct amap_lancer_write_obj_context,
-				eof, ctxt, 1);
+			      eof, ctxt, 1);
 	else
 		AMAP_SET_BITS(struct amap_lancer_write_obj_context,
-				eof, ctxt, 0);
+			      eof, ctxt, 0);
 
 	be_dws_cpu_to_le(ctxt, sizeof(req->context));
 	req->write_offset = cpu_to_le32(data_offset);
@@ -2167,8 +2214,8 @@ int lancer_cmd_write_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	req->descriptor_count = cpu_to_le32(1);
 	req->buf_len = cpu_to_le32(data_size);
 	req->addr_low = cpu_to_le32((cmd->dma +
-				sizeof(struct lancer_cmd_req_write_object))
-				& 0xFFFFFFFF);
+				     sizeof(struct lancer_cmd_req_write_object))
+				    & 0xFFFFFFFF);
 	req->addr_high = cpu_to_le32(upper_32_bits(cmd->dma +
 				sizeof(struct lancer_cmd_req_write_object)));
 
@@ -2197,8 +2244,8 @@ err_unlock:
 }
 
 int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
-		u32 data_size, u32 data_offset, const char *obj_name,
-		u32 *data_read, u32 *eof, u8 *addn_status)
+			   u32 data_size, u32 data_offset, const char *obj_name,
+			   u32 *data_read, u32 *eof, u8 *addn_status)
 {
 	struct be_mcc_wrb *wrb;
 	struct lancer_cmd_req_read_object *req;
@@ -2216,9 +2263,9 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_READ_OBJECT,
-			sizeof(struct lancer_cmd_req_read_object), wrb,
-			NULL);
+			       OPCODE_COMMON_READ_OBJECT,
+			       sizeof(struct lancer_cmd_req_read_object), wrb,
+			       NULL);
 
 	req->desired_read_len = cpu_to_le32(data_size);
 	req->read_offset = cpu_to_le32(data_offset);
@@ -2244,7 +2291,7 @@ err_unlock:
 }
 
 int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd,
-			u32 flash_type, u32 flash_opcode, u32 buf_size)
+			  u32 flash_type, u32 flash_opcode, u32 buf_size)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_write_flashrom *req;
@@ -2261,7 +2308,8 @@ int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	req = cmd->va;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_WRITE_FLASHROM, cmd->size, wrb, cmd);
+			       OPCODE_COMMON_WRITE_FLASHROM, cmd->size, wrb,
+			       cmd);
 
 	req->params.op_type = cpu_to_le32(flash_type);
 	req->params.op_code = cpu_to_le32(flash_opcode);
@@ -2284,7 +2332,7 @@ err_unlock:
 }
 
 int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
-			 int offset)
+			  u16 optype, int offset)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_read_flash_crc *req;
@@ -2303,7 +2351,7 @@ int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 			       OPCODE_COMMON_READ_FLASHROM, sizeof(*req),
 			       wrb, NULL);
 
-	req->params.op_type = cpu_to_le32(OPTYPE_REDBOOT);
+	req->params.op_type = cpu_to_le32(optype);
 	req->params.op_code = cpu_to_le32(FLASHROM_OPER_REPORT);
 	req->params.offset = cpu_to_le32(offset);
 	req->params.data_buf_size = cpu_to_le32(0x4);
@@ -2318,7 +2366,7 @@ err:
 }
 
 int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
-				struct be_dma_mem *nonemb_cmd)
+			    struct be_dma_mem *nonemb_cmd)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_acpi_wol_magic_config *req;
@@ -2334,8 +2382,8 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	req = nonemb_cmd->va;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ETH,
-		OPCODE_ETH_ACPI_WOL_MAGIC_CONFIG, sizeof(*req), wrb,
-		nonemb_cmd);
+			       OPCODE_ETH_ACPI_WOL_MAGIC_CONFIG, sizeof(*req),
+			       wrb, nonemb_cmd);
 	memcpy(req->magic_mac, mac, ETH_ALEN);
 
 	status = be_mcc_notify_wait(adapter);
@@ -2363,8 +2411,8 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_LOWLEVEL,
-			OPCODE_LOWLEVEL_SET_LOOPBACK_MODE, sizeof(*req), wrb,
-			NULL);
+			       OPCODE_LOWLEVEL_SET_LOOPBACK_MODE, sizeof(*req),
+			       wrb, NULL);
 
 	req->src_port = port_num;
 	req->dest_port = port_num;
@@ -2378,7 +2426,8 @@ err:
 }
 
 int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
-		u32 loopback_type, u32 pkt_size, u32 num_pkts, u64 pattern)
+			 u32 loopback_type, u32 pkt_size, u32 num_pkts,
+			 u64 pattern)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_loopback_test *req;
@@ -2396,7 +2445,8 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_LOWLEVEL,
-			OPCODE_LOWLEVEL_LOOPBACK_TEST, sizeof(*req), wrb, NULL);
+			       OPCODE_LOWLEVEL_LOOPBACK_TEST, sizeof(*req), wrb,
+			       NULL);
 
 	req->hdr.timeout = cpu_to_le32(15);
 	req->pattern = cpu_to_le64(pattern);
@@ -2421,7 +2471,7 @@ err:
 }
 
 int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
-				u32 byte_cnt, struct be_dma_mem *cmd)
+			u32 byte_cnt, struct be_dma_mem *cmd)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_ddrdma_test *req;
@@ -2437,7 +2487,8 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 	}
 	req = cmd->va;
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_LOWLEVEL,
-			OPCODE_LOWLEVEL_HOST_DDR_DMA, cmd->size, wrb, cmd);
+			       OPCODE_LOWLEVEL_HOST_DDR_DMA, cmd->size, wrb,
+			       cmd);
 
 	req->pattern = cpu_to_le64(pattern);
 	req->byte_count = cpu_to_le32(byte_cnt);
@@ -2465,7 +2516,7 @@ err:
 }
 
 int be_cmd_get_seeprom_data(struct be_adapter *adapter,
-				struct be_dma_mem *nonemb_cmd)
+			    struct be_dma_mem *nonemb_cmd)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_seeprom_read *req;
@@ -2481,8 +2532,8 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	req = nonemb_cmd->va;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_SEEPROM_READ, sizeof(*req), wrb,
-			nonemb_cmd);
+			       OPCODE_COMMON_SEEPROM_READ, sizeof(*req), wrb,
+			       nonemb_cmd);
 
 	status = be_mcc_notify_wait(adapter);
 
@@ -2510,8 +2561,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 		goto err;
 	}
 	cmd.size = sizeof(struct be_cmd_req_get_phy_info);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size,
-					&cmd.dma);
+	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -2521,8 +2571,8 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 	req = cmd.va;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_GET_PHY_DETAILS, sizeof(*req),
-			wrb, &cmd);
+			       OPCODE_COMMON_GET_PHY_DETAILS, sizeof(*req),
+			       wrb, &cmd);
 
 	status = be_mcc_notify_wait(adapter);
 	if (!status) {
@@ -2544,8 +2594,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 				BE_SUPPORTED_SPEED_1GBPS;
 		}
 	}
-	pci_free_consistent(adapter->pdev, cmd.size,
-				cmd.va, cmd.dma);
+	pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
@@ -2568,7 +2617,7 @@ int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_SET_QOS, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_SET_QOS, sizeof(*req), wrb, NULL);
 
 	req->hdr.domain = domain;
 	req->valid_bits = cpu_to_le32(BE_QOS_BITS_NIC);
@@ -2597,10 +2646,9 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 	memset(&attribs_cmd, 0, sizeof(struct be_dma_mem));
 	attribs_cmd.size = sizeof(struct be_cmd_resp_cntl_attribs);
 	attribs_cmd.va = pci_alloc_consistent(adapter->pdev, attribs_cmd.size,
-						&attribs_cmd.dma);
+					      &attribs_cmd.dma);
 	if (!attribs_cmd.va) {
-		dev_err(&adapter->pdev->dev,
-				"Memory allocation failure\n");
+		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
 		goto err;
 	}
@@ -2613,8 +2661,8 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 	req = attribs_cmd.va;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			 OPCODE_COMMON_GET_CNTL_ATTRIBUTES, payload_len, wrb,
-			&attribs_cmd);
+			       OPCODE_COMMON_GET_CNTL_ATTRIBUTES, payload_len,
+			       wrb, &attribs_cmd);
 
 	status = be_mbox_notify_wait(adapter);
 	if (!status) {
@@ -2649,7 +2697,8 @@ int be_cmd_req_native_mode(struct be_adapter *adapter)
 	req = embedded_payload(wrb);
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-		OPCODE_COMMON_SET_DRIVER_FUNCTION_CAP, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_SET_DRIVER_FUNCTION_CAP,
+			       sizeof(*req), wrb, NULL);
 
 	req->valid_cap_flags = cpu_to_le32(CAPABILITY_SW_TIMESTAMPS |
 				CAPABILITY_BE3_NATIVE_ERX_API);
@@ -2762,12 +2811,12 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 	memset(&get_mac_list_cmd, 0, sizeof(struct be_dma_mem));
 	get_mac_list_cmd.size = sizeof(struct be_cmd_resp_get_mac_list);
 	get_mac_list_cmd.va = pci_alloc_consistent(adapter->pdev,
-			get_mac_list_cmd.size,
-			&get_mac_list_cmd.dma);
+						   get_mac_list_cmd.size,
+						   &get_mac_list_cmd.dma);
 
 	if (!get_mac_list_cmd.va) {
 		dev_err(&adapter->pdev->dev,
-				"Memory allocation failure during GET_MAC_LIST\n");
+			"Memory allocation failure during GET_MAC_LIST\n");
 		return -ENOMEM;
 	}
 
@@ -2831,18 +2880,18 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 		/* If no active mac_id found, return first mac addr */
 		*pmac_id_valid = false;
 		memcpy(mac, resp->macaddr_list[0].mac_addr_id.macaddr,
-								ETH_ALEN);
+		       ETH_ALEN);
 	}
 
 out:
 	spin_unlock_bh(&adapter->mcc_lock);
 	pci_free_consistent(adapter->pdev, get_mac_list_cmd.size,
-			get_mac_list_cmd.va, get_mac_list_cmd.dma);
+			    get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
 }
 
-int be_cmd_get_active_mac(struct be_adapter *adapter, u32 curr_pmac_id, u8 *mac,
-			  u32 if_handle, bool active, u32 domain)
+int be_cmd_get_active_mac(struct be_adapter *adapter, u32 curr_pmac_id,
+			  u8 *mac, u32 if_handle, bool active, u32 domain)
 {
 
 	if (!active)
@@ -2892,7 +2941,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_mac_list);
 	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size,
-			&cmd.dma, GFP_KERNEL);
+				    &cmd.dma, GFP_KERNEL);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -2906,8 +2955,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 
 	req = cmd.va;
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-				OPCODE_COMMON_SET_MAC_LIST, sizeof(*req),
-				wrb, &cmd);
+			       OPCODE_COMMON_SET_MAC_LIST, sizeof(*req),
+			       wrb, &cmd);
 
 	req->hdr.domain = domain;
 	req->mac_count = mac_count;
@@ -2917,8 +2966,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	dma_free_coherent(&adapter->pdev->dev, cmd.size,
-				cmd.va, cmd.dma);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
@@ -2963,7 +3011,8 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 	ctxt = &req->context;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_SET_HSW_CONFIG, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_SET_HSW_CONFIG, sizeof(*req), wrb,
+			       NULL);
 
 	req->hdr.domain = domain;
 	AMAP_SET_BITS(struct amap_set_hsw_context, interface_id, ctxt, intf_id);
@@ -3009,7 +3058,8 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	ctxt = &req->context;
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
-			OPCODE_COMMON_GET_HSW_CONFIG, sizeof(*req), wrb, NULL);
+			       OPCODE_COMMON_GET_HSW_CONFIG, sizeof(*req), wrb,
+			       NULL);
 
 	req->hdr.domain = domain;
 	AMAP_SET_BITS(struct amap_get_hsw_req_context, interface_id,
@@ -3027,10 +3077,9 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	if (!status) {
 		struct be_cmd_resp_get_hsw_config *resp =
 						embedded_payload(wrb);
-		be_dws_le_to_cpu(&resp->context,
-						sizeof(resp->context));
+		be_dws_le_to_cpu(&resp->context, sizeof(resp->context));
 		vid = AMAP_GET_BITS(struct amap_get_hsw_resp_context,
-							pvid, &resp->context);
+				    pvid, &resp->context);
 		if (pvid)
 			*pvid = le16_to_cpu(vid);
 		if (mode)
@@ -3062,11 +3111,9 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_acpi_wol_magic_config_v1);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size,
-					       &cmd.dma);
+	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
 	if (!cmd.va) {
-		dev_err(&adapter->pdev->dev,
-				"Memory allocation failure\n");
+		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
 		goto err;
 	}
@@ -3349,8 +3396,7 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_func_config);
-	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size,
-				      &cmd.dma);
+	cmd.va = pci_alloc_consistent(adapter->pdev, cmd.size, &cmd.dma);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -3396,7 +3442,7 @@ err:
 
 /* Uses mbox */
 static int be_cmd_get_profile_config_mbox(struct be_adapter *adapter,
-					u8 domain, struct be_dma_mem *cmd)
+					  u8 domain, struct be_dma_mem *cmd)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_get_profile_config *req;
@@ -3424,7 +3470,7 @@ static int be_cmd_get_profile_config_mbox(struct be_adapter *adapter,
 
 /* Uses sync mcc */
 static int be_cmd_get_profile_config_mccq(struct be_adapter *adapter,
-					u8 domain, struct be_dma_mem *cmd)
+					  u8 domain, struct be_dma_mem *cmd)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_get_profile_config *req;
@@ -3484,8 +3530,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 	resp = cmd.va;
 	desc_count = le32_to_cpu(resp->desc_count);
 
-	pcie =  be_get_pcie_desc(adapter->pdev->devfn, resp->func_param,
-				 desc_count);
+	pcie = be_get_pcie_desc(adapter->pdev->devfn, resp->func_param,
+				desc_count);
 	if (pcie)
 		res->max_vfs = le16_to_cpu(pcie->num_vfs);
 
@@ -3548,33 +3594,47 @@ void be_reset_nic_desc(struct be_nic_res_desc *nic)
 	nic->cq_count = 0xFFFF;
 	nic->toe_conn_count = 0xFFFF;
 	nic->eq_count = 0xFFFF;
+	nic->iface_count = 0xFFFF;
 	nic->link_param = 0xFF;
+	nic->channel_id_param = cpu_to_le16(0xF000);
 	nic->acpi_params = 0xFF;
 	nic->wol_param = 0x0F;
-	nic->bw_min = 0xFFFFFFFF;
+	nic->tunnel_iface_count = 0xFFFF;
+	nic->direct_tenant_iface_count = 0xFFFF;
 	nic->bw_max = 0xFFFFFFFF;
 }
 
-int be_cmd_config_qos(struct be_adapter *adapter, u32 bps, u8 domain)
+int be_cmd_config_qos(struct be_adapter *adapter, u32 max_rate, u16 link_speed,
+		      u8 domain)
 {
-	if (lancer_chip(adapter)) {
-		struct be_nic_res_desc nic_desc;
+	struct be_nic_res_desc nic_desc;
+	u32 bw_percent;
+	u16 version = 0;
+
+	if (BE3_chip(adapter))
+		return be_cmd_set_qos(adapter, max_rate / 10, domain);
 
-		be_reset_nic_desc(&nic_desc);
+	be_reset_nic_desc(&nic_desc);
+	nic_desc.pf_num = adapter->pf_number;
+	nic_desc.vf_num = domain;
+	if (lancer_chip(adapter)) {
 		nic_desc.hdr.desc_type = NIC_RESOURCE_DESC_TYPE_V0;
 		nic_desc.hdr.desc_len = RESOURCE_DESC_SIZE_V0;
 		nic_desc.flags = (1 << QUN_SHIFT) | (1 << IMM_SHIFT) |
 					(1 << NOSV_SHIFT);
-		nic_desc.pf_num = adapter->pf_number;
-		nic_desc.vf_num = domain;
-		nic_desc.bw_max = cpu_to_le32(bps);
-
-		return be_cmd_set_profile_config(adapter, &nic_desc,
-						 RESOURCE_DESC_SIZE_V0,
-						 0, domain);
+		nic_desc.bw_max = cpu_to_le32(max_rate / 10);
 	} else {
-		return be_cmd_set_qos(adapter, bps, domain);
+		version = 1;
+		nic_desc.hdr.desc_type = NIC_RESOURCE_DESC_TYPE_V1;
+		nic_desc.hdr.desc_len = RESOURCE_DESC_SIZE_V1;
+		nic_desc.flags = (1 << IMM_SHIFT) | (1 << NOSV_SHIFT);
+		bw_percent = max_rate ? (max_rate * 100) / link_speed : 100;
+		nic_desc.bw_max = cpu_to_le32(bw_percent);
 	}
+
+	return be_cmd_set_profile_config(adapter, &nic_desc,
+					 nic_desc.hdr.desc_len,
+					 version, domain);
 }
 
 int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
@@ -3859,7 +3919,7 @@ err:
 }
 
 int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
-			int wrb_payload_size, u16 *cmd_status, u16 *ext_status)
+		    int wrb_payload_size, u16 *cmd_status, u16 *ext_status)
 {
 	struct be_adapter *adapter = netdev_priv(netdev_handle);
 	struct be_mcc_wrb *wrb;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index b60e4d53c1c..59b3c056f32 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -50,7 +50,7 @@ struct be_mcc_wrb {
 #define CQE_FLAGS_CONSUMED_MASK 	(1 << 27)
 
 /* Completion Status */
-enum {
+enum mcc_base_status {
 	MCC_STATUS_SUCCESS = 0,
 	MCC_STATUS_FAILED = 1,
 	MCC_STATUS_ILLEGAL_REQUEST = 2,
@@ -60,12 +60,25 @@ enum {
 	MCC_STATUS_NOT_SUPPORTED = 66
 };
 
-#define MCC_ADDL_STS_INSUFFICIENT_RESOURCES	0x16
+/* Additional status */
+enum mcc_addl_status {
+	MCC_ADDL_STATUS_INSUFFICIENT_RESOURCES = 0x16,
+	MCC_ADDL_STATUS_FLASH_IMAGE_CRC_MISMATCH = 0x4d,
+	MCC_ADDL_STATUS_TOO_MANY_INTERFACES = 0x4a
+};
+
+#define CQE_BASE_STATUS_MASK		0xFFFF
+#define CQE_BASE_STATUS_SHIFT		0	/* bits 0 - 15 */
+#define CQE_ADDL_STATUS_MASK		0xFF
+#define CQE_ADDL_STATUS_SHIFT		16	/* bits 16 - 31 */
 
-#define CQE_STATUS_COMPL_MASK		0xFFFF
-#define CQE_STATUS_COMPL_SHIFT		0	/* bits 0 - 15 */
-#define CQE_STATUS_EXTD_MASK		0xFFFF
-#define CQE_STATUS_EXTD_SHIFT		16	/* bits 16 - 31 */
+#define base_status(status)		\
+		((enum mcc_base_status)	\
+			(status > 0 ? (status & CQE_BASE_STATUS_MASK) : 0))
+#define addl_status(status)		\
+		((enum mcc_addl_status)	\
+			(status > 0 ? (status >> CQE_ADDL_STATUS_SHIFT) & \
+					CQE_ADDL_STATUS_MASK : 0))
 
 struct be_mcc_compl {
 	u32 status;		/* dword 0 */
@@ -74,13 +87,13 @@ struct be_mcc_compl {
 	u32 flags;		/* dword 3 */
 };
 
-/* When the async bit of mcc_compl is set, the last 4 bytes of
- * mcc_compl is interpreted as follows:
+/* When the async bit of mcc_compl flags is set, flags
+ * is interpreted as follows:
  */
-#define ASYNC_TRAILER_EVENT_CODE_SHIFT	8	/* bits 8 - 15 */
-#define ASYNC_TRAILER_EVENT_CODE_MASK	0xFF
-#define ASYNC_TRAILER_EVENT_TYPE_SHIFT	16
-#define ASYNC_TRAILER_EVENT_TYPE_MASK	0xFF
+#define ASYNC_EVENT_CODE_SHIFT		8	/* bits 8 - 15 */
+#define ASYNC_EVENT_CODE_MASK		0xFF
+#define ASYNC_EVENT_TYPE_SHIFT		16
+#define ASYNC_EVENT_TYPE_MASK		0xFF
 #define ASYNC_EVENT_CODE_LINK_STATE	0x1
 #define ASYNC_EVENT_CODE_GRP_5		0x5
 #define ASYNC_EVENT_QOS_SPEED		0x1
@@ -89,10 +102,6 @@ struct be_mcc_compl {
 #define ASYNC_EVENT_CODE_QNQ		0x6
 #define ASYNC_DEBUG_EVENT_TYPE_QNQ	1
 
-struct be_async_event_trailer {
-	u32 code;
-};
-
 enum {
 	LINK_DOWN	= 0x0,
 	LINK_UP		= 0x1
@@ -100,7 +109,7 @@ enum {
 #define LINK_STATUS_MASK			0x1
 #define LOGICAL_LINK_STATUS_MASK		0x2
 
-/* When the event code of an async trailer is link-state, the mcc_compl
+/* When the event code of compl->flags is link-state, the mcc_compl
  * must be interpreted as follows
  */
 struct be_async_event_link_state {
@@ -110,10 +119,10 @@ struct be_async_event_link_state {
 	u8 port_speed;
 	u8 port_fault;
 	u8 rsvd0[7];
-	struct be_async_event_trailer trailer;
+	u32 flags;
 } __packed;
 
-/* When the event code of an async trailer is GRP-5 and event_type is QOS_SPEED
+/* When the event code of compl->flags is GRP-5 and event_type is QOS_SPEED
  * the mcc_compl must be interpreted as follows
  */
 struct be_async_event_grp5_qos_link_speed {
@@ -121,10 +130,10 @@ struct be_async_event_grp5_qos_link_speed {
 	u8 rsvd[5];
 	u16 qos_link_speed;
 	u32 event_tag;
-	struct be_async_event_trailer trailer;
+	u32 flags;
 } __packed;
 
-/* When the event code of an async trailer is GRP5 and event type is
+/* When the event code of compl->flags is GRP5 and event type is
  * CoS-Priority, the mcc_compl must be interpreted as follows
  */
 struct be_async_event_grp5_cos_priority {
@@ -134,10 +143,10 @@ struct be_async_event_grp5_cos_priority {
 	u8 valid;
 	u8 rsvd0;
 	u8 event_tag;
-	struct be_async_event_trailer trailer;
+	u32 flags;
 } __packed;
 
-/* When the event code of an async trailer is GRP5 and event type is
+/* When the event code of compl->flags is GRP5 and event type is
  * PVID state, the mcc_compl must be interpreted as follows
  */
 struct be_async_event_grp5_pvid_state {
@@ -146,7 +155,7 @@ struct be_async_event_grp5_pvid_state {
 	u16 tag;
 	u32 event_tag;
 	u32 rsvd1;
-	struct be_async_event_trailer trailer;
+	u32 flags;
 } __packed;
 
 /* async event indicating outer VLAN tag in QnQ */
@@ -156,7 +165,7 @@ struct be_async_event_qnq {
 	u16 vlan_tag;
 	u32 event_tag;
 	u8 rsvd1[4];
-	struct be_async_event_trailer trailer;
+	u32 flags;
 } __packed;
 
 struct be_mcc_mailbox {
@@ -258,8 +267,8 @@ struct be_cmd_resp_hdr {
 	u8 opcode;		/* dword 0 */
 	u8 subsystem;		/* dword 0 */
 	u8 rsvd[2];		/* dword 0 */
-	u8 status;		/* dword 1 */
-	u8 add_status;		/* dword 1 */
+	u8 base_status;		/* dword 1 */
+	u8 addl_status;		/* dword 1 */
 	u8 rsvd1[2];		/* dword 1 */
 	u32 response_length;	/* dword 2 */
 	u32 actual_resp_len;	/* dword 3 */
@@ -1082,7 +1091,7 @@ struct be_cmd_resp_modify_eq_delay {
  * based on the skew/IPL.
  */
 #define RDMA_ENABLED				0x4
-#define FLEX10_MODE				0x400
+#define QNQ_MODE				0x400
 #define VNIC_MODE				0x20000
 #define UMC_ENABLED				0x1000000
 struct be_cmd_req_query_fw_cfg {
@@ -1186,7 +1195,8 @@ struct be_cmd_read_flash_crc {
 	struct flashrom_params params;
 	u8 crc[4];
 	u8 rsvd[4];
-};
+} __packed;
+
 /**************** Lancer Firmware Flash ************/
 struct amap_lancer_write_obj_context {
 	u8 write_length[24];
@@ -1891,16 +1901,20 @@ struct be_nic_res_desc {
 	u16 cq_count;
 	u16 toe_conn_count;
 	u16 eq_count;
-	u32 rsvd5;
+	u16 vlan_id;
+	u16 iface_count;
 	u32 cap_flags;
 	u8 link_param;
-	u8 rsvd6[3];
+	u8 rsvd6;
+	u16 channel_id_param;
 	u32 bw_min;
 	u32 bw_max;
 	u8 acpi_params;
 	u8 wol_param;
 	u16 rsvd7;
-	u32 rsvd8[7];
+	u16 tunnel_iface_count;
+	u16 direct_tenant_iface_count;
+	u32 rsvd8[6];
 } __packed;
 
 /************ Multi-Channel type ***********/
@@ -2060,7 +2074,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter, char *fw_ver,
 		      char *fw_on_flash);
 int be_cmd_modify_eqd(struct be_adapter *adapter, struct be_set_eqd *, int num);
 int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
-		       u32 num, bool promiscuous);
+		       u32 num);
 int be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 status);
 int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc);
 int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc);
@@ -2068,7 +2082,7 @@ int be_cmd_query_fw_cfg(struct be_adapter *adapter, u32 *port_num,
 			u32 *function_mode, u32 *function_caps, u16 *asic_rev);
 int be_cmd_reset_function(struct be_adapter *adapter);
 int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
-		      u32 rss_hash_opts, u16 table_size);
+		      u32 rss_hash_opts, u16 table_size, const u8 *rss_hkey);
 int be_process_mcc(struct be_adapter *adapter);
 int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num, u8 beacon,
 			    u8 status, u8 state);
@@ -2084,7 +2098,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 			   u32 data_size, u32 data_offset, const char *obj_name,
 			   u32 *data_read, u32 *eof, u8 *addn_status);
 int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
-			 int offset);
+			  u16 optype, int offset);
 int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 			    struct be_dma_mem *nonemb_cmd);
 int be_cmd_fw_init(struct be_adapter *adapter);
@@ -2101,7 +2115,8 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 			u8 loopback_type, u8 enable);
 int be_cmd_get_phy_info(struct be_adapter *adapter);
-int be_cmd_config_qos(struct be_adapter *adapter, u32 bps, u8 domain);
+int be_cmd_config_qos(struct be_adapter *adapter, u32 max_rate,
+		      u16 link_speed, u8 domain);
 void be_detect_error(struct be_adapter *adapter);
 int be_cmd_get_die_temperature(struct be_adapter *adapter);
 int be_cmd_get_cntl_attributes(struct be_adapter *adapter);
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 15ba96cba65..e2da4d20dd3 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -132,6 +132,7 @@ static const struct be_ethtool_stat et_rx_stats[] = {
 	{DRVSTAT_RX_INFO(rx_bytes)},/* If moving this member see above note */
 	{DRVSTAT_RX_INFO(rx_pkts)}, /* If moving this member see above note */
 	{DRVSTAT_RX_INFO(rx_compl)},
+	{DRVSTAT_RX_INFO(rx_compl_err)},
 	{DRVSTAT_RX_INFO(rx_mcast_pkts)},
 	/* Number of page allocation failures while posting receive buffers
 	 * to HW.
@@ -181,7 +182,7 @@ static const char et_self_tests[][ETH_GSTRING_LEN] = {
 #define BE_NO_LOOPBACK 0xff
 
 static void be_get_drvinfo(struct net_device *netdev,
-				struct ethtool_drvinfo *drvinfo)
+			   struct ethtool_drvinfo *drvinfo)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
@@ -201,8 +202,7 @@ static void be_get_drvinfo(struct net_device *netdev,
 	drvinfo->eedump_len = 0;
 }
 
-static u32
-lancer_cmd_get_file_len(struct be_adapter *adapter, u8 *file_name)
+static u32 lancer_cmd_get_file_len(struct be_adapter *adapter, u8 *file_name)
 {
 	u32 data_read = 0, eof;
 	u8 addn_status;
@@ -212,14 +212,14 @@ lancer_cmd_get_file_len(struct be_adapter *adapter, u8 *file_name)
 	memset(&data_len_cmd, 0, sizeof(data_len_cmd));
 	/* data_offset and data_size should be 0 to get reg len */
 	status = lancer_cmd_read_object(adapter, &data_len_cmd, 0, 0,
-				file_name, &data_read, &eof, &addn_status);
+					file_name, &data_read, &eof,
+					&addn_status);
 
 	return data_read;
 }
 
-static int
-lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
-		u32 buf_len, void *buf)
+static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
+				u32 buf_len, void *buf)
 {
 	struct be_dma_mem read_cmd;
 	u32 read_len = 0, total_read_len = 0, chunk_size;
@@ -229,11 +229,11 @@ lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 
 	read_cmd.size = LANCER_READ_FILE_CHUNK;
 	read_cmd.va = pci_alloc_consistent(adapter->pdev, read_cmd.size,
-			&read_cmd.dma);
+					   &read_cmd.dma);
 
 	if (!read_cmd.va) {
 		dev_err(&adapter->pdev->dev,
-				"Memory allocation failure while reading dump\n");
+			"Memory allocation failure while reading dump\n");
 		return -ENOMEM;
 	}
 
@@ -242,8 +242,8 @@ lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 				LANCER_READ_FILE_CHUNK);
 		chunk_size = ALIGN(chunk_size, 4);
 		status = lancer_cmd_read_object(adapter, &read_cmd, chunk_size,
-				total_read_len, file_name, &read_len,
-				&eof, &addn_status);
+						total_read_len, file_name,
+						&read_len, &eof, &addn_status);
 		if (!status) {
 			memcpy(buf + total_read_len, read_cmd.va, read_len);
 			total_read_len += read_len;
@@ -254,13 +254,12 @@ lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 		}
 	}
 	pci_free_consistent(adapter->pdev, read_cmd.size, read_cmd.va,
-			read_cmd.dma);
+			    read_cmd.dma);
 
 	return status;
 }
 
-static int
-be_get_reg_len(struct net_device *netdev)
+static int be_get_reg_len(struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	u32 log_size = 0;
@@ -271,7 +270,7 @@ be_get_reg_len(struct net_device *netdev)
 	if (be_physfn(adapter)) {
 		if (lancer_chip(adapter))
 			log_size = lancer_cmd_get_file_len(adapter,
-					LANCER_FW_DUMP_FILE);
+							   LANCER_FW_DUMP_FILE);
 		else
 			be_cmd_get_reg_len(adapter, &log_size);
 	}
@@ -287,7 +286,7 @@ be_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *buf)
 		memset(buf, 0, regs->len);
 		if (lancer_chip(adapter))
 			lancer_cmd_read_file(adapter, LANCER_FW_DUMP_FILE,
-					regs->len, buf);
+					     regs->len, buf);
 		else
 			be_cmd_get_regs(adapter, regs->len, buf);
 	}
@@ -337,9 +336,8 @@ static int be_set_coalesce(struct net_device *netdev,
 	return 0;
 }
 
-static void
-be_get_ethtool_stats(struct net_device *netdev,
-		struct ethtool_stats *stats, uint64_t *data)
+static void be_get_ethtool_stats(struct net_device *netdev,
+				 struct ethtool_stats *stats, uint64_t *data)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_rx_obj *rxo;
@@ -390,9 +388,8 @@ be_get_ethtool_stats(struct net_device *netdev,
 	}
 }
 
-static void
-be_get_stat_strings(struct net_device *netdev, uint32_t stringset,
-		uint8_t *data)
+static void be_get_stat_strings(struct net_device *netdev, uint32_t stringset,
+				uint8_t *data)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int i, j;
@@ -642,16 +639,15 @@ be_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *ecmd)
 	adapter->rx_fc = ecmd->rx_pause;
 
 	status = be_cmd_set_flow_control(adapter,
-					adapter->tx_fc, adapter->rx_fc);
+					 adapter->tx_fc, adapter->rx_fc);
 	if (status)
 		dev_warn(&adapter->pdev->dev, "Pause param set failed.\n");
 
 	return status;
 }
 
-static int
-be_set_phys_id(struct net_device *netdev,
-	       enum ethtool_phys_id_state state)
+static int be_set_phys_id(struct net_device *netdev,
+			  enum ethtool_phys_id_state state)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
@@ -708,8 +704,7 @@ static int be_set_dump(struct net_device *netdev, struct ethtool_dump *dump)
 	return status;
 }
 
-static void
-be_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
+static void be_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
@@ -723,8 +718,7 @@ be_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	memset(&wol->sopass, 0, sizeof(wol->sopass));
 }
 
-static int
-be_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
+static int be_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
@@ -744,8 +738,7 @@ be_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	return 0;
 }
 
-static int
-be_test_ddr_dma(struct be_adapter *adapter)
+static int be_test_ddr_dma(struct be_adapter *adapter)
 {
 	int ret, i;
 	struct be_dma_mem ddrdma_cmd;
@@ -761,7 +754,7 @@ be_test_ddr_dma(struct be_adapter *adapter)
 
 	for (i = 0; i < 2; i++) {
 		ret = be_cmd_ddr_dma_test(adapter, pattern[i],
-					4096, &ddrdma_cmd);
+					  4096, &ddrdma_cmd);
 		if (ret != 0)
 			goto err;
 	}
@@ -773,20 +766,17 @@ err:
 }
 
 static u64 be_loopback_test(struct be_adapter *adapter, u8 loopback_type,
-				u64 *status)
+			    u64 *status)
 {
-	be_cmd_set_loopback(adapter, adapter->hba_port_num,
-				loopback_type, 1);
+	be_cmd_set_loopback(adapter, adapter->hba_port_num, loopback_type, 1);
 	*status = be_cmd_loopback_test(adapter, adapter->hba_port_num,
-				loopback_type, 1500,
-				2, 0xabc);
-	be_cmd_set_loopback(adapter, adapter->hba_port_num,
-				BE_NO_LOOPBACK, 1);
+				       loopback_type, 1500, 2, 0xabc);
+	be_cmd_set_loopback(adapter, adapter->hba_port_num, BE_NO_LOOPBACK, 1);
 	return *status;
 }
 
-static void
-be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data)
+static void be_self_test(struct net_device *netdev, struct ethtool_test *test,
+			 u64 *data)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int status;
@@ -801,12 +791,10 @@ be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data)
 	memset(data, 0, sizeof(u64) * ETHTOOL_TESTS_NUM);
 
 	if (test->flags & ETH_TEST_FL_OFFLINE) {
-		if (be_loopback_test(adapter, BE_MAC_LOOPBACK,
-				     &data[0]) != 0)
+		if (be_loopback_test(adapter, BE_MAC_LOOPBACK, &data[0]) != 0)
 			test->flags |= ETH_TEST_FL_FAILED;
 
-		if (be_loopback_test(adapter, BE_PHY_LOOPBACK,
-				     &data[1]) != 0)
+		if (be_loopback_test(adapter, BE_PHY_LOOPBACK, &data[1]) != 0)
 			test->flags |= ETH_TEST_FL_FAILED;
 
 		if (test->flags & ETH_TEST_FL_EXTERNAL_LB) {
@@ -832,16 +820,14 @@ be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data)
 	}
 }
 
-static int
-be_do_flash(struct net_device *netdev, struct ethtool_flash *efl)
+static int be_do_flash(struct net_device *netdev, struct ethtool_flash *efl)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
 	return be_load_fw(adapter, efl->data);
 }
 
-static int
-be_get_eeprom_len(struct net_device *netdev)
+static int be_get_eeprom_len(struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
@@ -851,18 +837,17 @@ be_get_eeprom_len(struct net_device *netdev)
 	if (lancer_chip(adapter)) {
 		if (be_physfn(adapter))
 			return lancer_cmd_get_file_len(adapter,
-					LANCER_VPD_PF_FILE);
+						       LANCER_VPD_PF_FILE);
 		else
 			return lancer_cmd_get_file_len(adapter,
-					LANCER_VPD_VF_FILE);
+						       LANCER_VPD_VF_FILE);
 	} else {
 		return BE_READ_SEEPROM_LEN;
 	}
 }
 
-static int
-be_read_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
-			uint8_t *data)
+static int be_read_eeprom(struct net_device *netdev,
+			  struct ethtool_eeprom *eeprom, uint8_t *data)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_dma_mem eeprom_cmd;
@@ -875,10 +860,10 @@ be_read_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 	if (lancer_chip(adapter)) {
 		if (be_physfn(adapter))
 			return lancer_cmd_read_file(adapter, LANCER_VPD_PF_FILE,
-					eeprom->len, data);
+						    eeprom->len, data);
 		else
 			return lancer_cmd_read_file(adapter, LANCER_VPD_VF_FILE,
-					eeprom->len, data);
+						    eeprom->len, data);
 	}
 
 	eeprom->magic = BE_VENDOR_ID | (adapter->pdev->device<<16);
@@ -933,27 +918,27 @@ static u64 be_get_rss_hash_opts(struct be_adapter *adapter, u64 flow_type)
 
 	switch (flow_type) {
 	case TCP_V4_FLOW:
-		if (adapter->rss_flags & RSS_ENABLE_IPV4)
+		if (adapter->rss_info.rss_flags & RSS_ENABLE_IPV4)
 			data |= RXH_IP_DST | RXH_IP_SRC;
-		if (adapter->rss_flags & RSS_ENABLE_TCP_IPV4)
+		if (adapter->rss_info.rss_flags & RSS_ENABLE_TCP_IPV4)
 			data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		break;
 	case UDP_V4_FLOW:
-		if (adapter->rss_flags & RSS_ENABLE_IPV4)
+		if (adapter->rss_info.rss_flags & RSS_ENABLE_IPV4)
 			data |= RXH_IP_DST | RXH_IP_SRC;
-		if (adapter->rss_flags & RSS_ENABLE_UDP_IPV4)
+		if (adapter->rss_info.rss_flags & RSS_ENABLE_UDP_IPV4)
 			data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		break;
 	case TCP_V6_FLOW:
-		if (adapter->rss_flags & RSS_ENABLE_IPV6)
+		if (adapter->rss_info.rss_flags & RSS_ENABLE_IPV6)
 			data |= RXH_IP_DST | RXH_IP_SRC;
-		if (adapter->rss_flags & RSS_ENABLE_TCP_IPV6)
+		if (adapter->rss_info.rss_flags & RSS_ENABLE_TCP_IPV6)
 			data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		break;
 	case UDP_V6_FLOW:
-		if (adapter->rss_flags & RSS_ENABLE_IPV6)
+		if (adapter->rss_info.rss_flags & RSS_ENABLE_IPV6)
 			data |= RXH_IP_DST | RXH_IP_SRC;
-		if (adapter->rss_flags & RSS_ENABLE_UDP_IPV6)
+		if (adapter->rss_info.rss_flags & RSS_ENABLE_UDP_IPV6)
 			data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		break;
 	}
@@ -962,7 +947,7 @@ static u64 be_get_rss_hash_opts(struct be_adapter *adapter, u64 flow_type)
 }
 
 static int be_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
-		      u32 *rule_locs)
+			u32 *rule_locs)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
@@ -992,7 +977,7 @@ static int be_set_rss_hash_opts(struct be_adapter *adapter,
 	struct be_rx_obj *rxo;
 	int status = 0, i, j;
 	u8 rsstable[128];
-	u32 rss_flags = adapter->rss_flags;
+	u32 rss_flags = adapter->rss_info.rss_flags;
 
 	if (cmd->data != L3_RSS_FLAGS &&
 	    cmd->data != (L3_RSS_FLAGS | L4_RSS_FLAGS))
@@ -1039,7 +1024,7 @@ static int be_set_rss_hash_opts(struct be_adapter *adapter,
 		return -EINVAL;
 	}
 
-	if (rss_flags == adapter->rss_flags)
+	if (rss_flags == adapter->rss_info.rss_flags)
 		return status;
 
 	if (be_multi_rxq(adapter)) {
@@ -1051,9 +1036,11 @@ static int be_set_rss_hash_opts(struct be_adapter *adapter,
 			}
 		}
 	}
-	status = be_cmd_rss_config(adapter, rsstable, rss_flags, 128);
+
+	status = be_cmd_rss_config(adapter, adapter->rss_info.rsstable,
+				   rss_flags, 128, adapter->rss_info.rss_hkey);
 	if (!status)
-		adapter->rss_flags = rss_flags;
+		adapter->rss_info.rss_flags = rss_flags;
 
 	return status;
 }
@@ -1103,6 +1090,69 @@ static int be_set_channels(struct net_device  *netdev,
 	return be_update_queues(adapter);
 }
 
+static u32 be_get_rxfh_indir_size(struct net_device *netdev)
+{
+	return RSS_INDIR_TABLE_LEN;
+}
+
+static u32 be_get_rxfh_key_size(struct net_device *netdev)
+{
+	return RSS_HASH_KEY_LEN;
+}
+
+static int be_get_rxfh(struct net_device *netdev, u32 *indir, u8 *hkey)
+{
+	struct be_adapter *adapter = netdev_priv(netdev);
+	int i;
+	struct rss_info *rss = &adapter->rss_info;
+
+	if (indir) {
+		for (i = 0; i < RSS_INDIR_TABLE_LEN; i++)
+			indir[i] = rss->rss_queue[i];
+	}
+
+	if (hkey)
+		memcpy(hkey, rss->rss_hkey, RSS_HASH_KEY_LEN);
+
+	return 0;
+}
+
+static int be_set_rxfh(struct net_device *netdev, const u32 *indir,
+		       const u8 *hkey)
+{
+	int rc = 0, i, j;
+	struct be_adapter *adapter = netdev_priv(netdev);
+	u8 rsstable[RSS_INDIR_TABLE_LEN];
+
+	if (indir) {
+		struct be_rx_obj *rxo;
+		for (i = 0; i < RSS_INDIR_TABLE_LEN; i++) {
+			j = indir[i];
+			rxo = &adapter->rx_obj[j];
+			rsstable[i] = rxo->rss_id;
+			adapter->rss_info.rss_queue[i] = j;
+		}
+	} else {
+		memcpy(rsstable, adapter->rss_info.rsstable,
+		       RSS_INDIR_TABLE_LEN);
+	}
+
+	if (!hkey)
+		hkey =  adapter->rss_info.rss_hkey;
+
+	rc = be_cmd_rss_config(adapter, rsstable,
+			adapter->rss_info.rss_flags,
+			RSS_INDIR_TABLE_LEN, hkey);
+	if (rc) {
+		adapter->rss_info.rss_flags = RSS_ENABLE_NONE;
+		return -EIO;
+	}
+	memcpy(adapter->rss_info.rss_hkey, hkey, RSS_HASH_KEY_LEN);
+	memcpy(adapter->rss_info.rsstable, rsstable,
+	       RSS_INDIR_TABLE_LEN);
+	return 0;
+}
+
 const struct ethtool_ops be_ethtool_ops = {
 	.get_settings = be_get_settings,
 	.get_drvinfo = be_get_drvinfo,
@@ -1129,6 +1179,10 @@ const struct ethtool_ops be_ethtool_ops = {
 	.self_test = be_self_test,
 	.get_rxnfc = be_get_rxnfc,
 	.set_rxnfc = be_set_rxnfc,
+	.get_rxfh_indir_size = be_get_rxfh_indir_size,
+	.get_rxfh_key_size = be_get_rxfh_key_size,
+	.get_rxfh = be_get_rxfh,
+	.set_rxfh = be_set_rxfh,
 	.get_channels = be_get_channels,
 	.set_channels = be_set_channels
 };
diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h
index 3bd198550ed..8840c64aaec 100644
--- a/drivers/net/ethernet/emulex/benet/be_hw.h
+++ b/drivers/net/ethernet/emulex/benet/be_hw.h
@@ -188,10 +188,14 @@
 #define OPTYPE_FCOE_FW_ACTIVE		10
 #define OPTYPE_FCOE_FW_BACKUP		11
 #define OPTYPE_NCSI_FW			13
+#define OPTYPE_REDBOOT_DIR		18
+#define OPTYPE_REDBOOT_CONFIG		19
+#define OPTYPE_SH_PHY_FW		21
+#define OPTYPE_FLASHISM_JUMPVECTOR	22
+#define OPTYPE_UFI_DIR			23
 #define OPTYPE_PHY_FW			99
 #define TN_8022				13
 
-#define ILLEGAL_IOCTL_REQ		2
 #define FLASHROM_OPER_PHY_FLASH		9
 #define FLASHROM_OPER_PHY_SAVE		10
 #define FLASHROM_OPER_FLASH		1
@@ -250,6 +254,9 @@
 #define IMAGE_FIRMWARE_BACKUP_FCoE	178
 #define IMAGE_FIRMWARE_BACKUP_COMP_FCoE 179
 #define IMAGE_FIRMWARE_PHY		192
+#define IMAGE_REDBOOT_DIR		208
+#define IMAGE_REDBOOT_CONFIG		209
+#define IMAGE_UFI_DIR			210
 #define IMAGE_BOOT_CODE			224
 
 /************* Rx Packet Type Encoding **************/
@@ -534,7 +541,8 @@ struct flash_section_entry {
 	u32 image_size;
 	u32 cksum;
 	u32 entry_point;
-	u32 rsvd0;
+	u16 optype;
+	u16 rsvd0;
 	u32 rsvd1;
 	u8 ver_data[32];
 } __packed;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index dc19bc5dec7..1e187fb760f 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -134,7 +134,7 @@ static void be_queue_free(struct be_adapter *adapter, struct be_queue_info *q)
 }
 
 static int be_queue_alloc(struct be_adapter *adapter, struct be_queue_info *q,
-		u16 len, u16 entry_size)
+			  u16 len, u16 entry_size)
 {
 	struct be_dma_mem *mem = &q->dma_mem;
 
@@ -154,7 +154,7 @@ static void be_reg_intr_set(struct be_adapter *adapter, bool enable)
 	u32 reg, enabled;
 
 	pci_read_config_dword(adapter->pdev, PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET,
-				&reg);
+			      &reg);
 	enabled = reg & MEMBAR_CTRL_INT_CTRL_HOSTINTR_MASK;
 
 	if (!enabled && enable)
@@ -165,7 +165,7 @@ static void be_reg_intr_set(struct be_adapter *adapter, bool enable)
 		return;
 
 	pci_write_config_dword(adapter->pdev,
-			PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET, reg);
+			       PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET, reg);
 }
 
 static void be_intr_set(struct be_adapter *adapter, bool enable)
@@ -206,12 +206,11 @@ static void be_txq_notify(struct be_adapter *adapter, struct be_tx_obj *txo,
 }
 
 static void be_eq_notify(struct be_adapter *adapter, u16 qid,
-		bool arm, bool clear_int, u16 num_popped)
+			 bool arm, bool clear_int, u16 num_popped)
 {
 	u32 val = 0;
 	val |= qid & DB_EQ_RING_ID_MASK;
-	val |= ((qid & DB_EQ_RING_ID_EXT_MASK) <<
-			DB_EQ_RING_ID_EXT_MASK_SHIFT);
+	val |= ((qid & DB_EQ_RING_ID_EXT_MASK) << DB_EQ_RING_ID_EXT_MASK_SHIFT);
 
 	if (adapter->eeh_error)
 		return;
@@ -477,7 +476,7 @@ static void populate_be_v2_stats(struct be_adapter *adapter)
 	drvs->rx_drops_no_tpre_descr = rxf_stats->rx_drops_no_tpre_descr;
 	drvs->rx_drops_too_many_frags = rxf_stats->rx_drops_too_many_frags;
 	adapter->drv_stats.eth_red_drops = pmem_sts->eth_red_drops;
-	if (be_roce_supported(adapter))  {
+	if (be_roce_supported(adapter)) {
 		drvs->rx_roce_bytes_lsd = port_stats->roce_bytes_received_lsd;
 		drvs->rx_roce_bytes_msd = port_stats->roce_bytes_received_msd;
 		drvs->rx_roce_frames = port_stats->roce_frames_received;
@@ -491,8 +490,7 @@ static void populate_lancer_stats(struct be_adapter *adapter)
 {
 
 	struct be_drv_stats *drvs = &adapter->drv_stats;
-	struct lancer_pport_stats *pport_stats =
-					pport_stats_from_cmd(adapter);
+	struct lancer_pport_stats *pport_stats = pport_stats_from_cmd(adapter);
 
 	be_dws_le_to_cpu(pport_stats, sizeof(*pport_stats));
 	drvs->rx_pause_frames = pport_stats->rx_pause_frames_lo;
@@ -539,8 +537,7 @@ static void accumulate_16bit_val(u32 *acc, u16 val)
 }
 
 static void populate_erx_stats(struct be_adapter *adapter,
-			struct be_rx_obj *rxo,
-			u32 erx_stat)
+			       struct be_rx_obj *rxo, u32 erx_stat)
 {
 	if (!BEx_chip(adapter))
 		rx_stats(rxo)->rx_drops_no_frags = erx_stat;
@@ -579,7 +576,7 @@ void be_parse_stats(struct be_adapter *adapter)
 }
 
 static struct rtnl_link_stats64 *be_get_stats64(struct net_device *netdev,
-					struct rtnl_link_stats64 *stats)
+						struct rtnl_link_stats64 *stats)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_drv_stats *drvs = &adapter->drv_stats;
@@ -660,7 +657,8 @@ void be_link_status_update(struct be_adapter *adapter, u8 link_status)
 }
 
 static void be_tx_stats_update(struct be_tx_obj *txo,
-			u32 wrb_cnt, u32 copied, u32 gso_segs, bool stopped)
+			       u32 wrb_cnt, u32 copied, u32 gso_segs,
+			       bool stopped)
 {
 	struct be_tx_stats *stats = tx_stats(txo);
 
@@ -676,7 +674,7 @@ static void be_tx_stats_update(struct be_tx_obj *txo,
 
 /* Determine number of WRB entries needed to xmit data in an skb */
 static u32 wrb_cnt_for_skb(struct be_adapter *adapter, struct sk_buff *skb,
-								bool *dummy)
+			   bool *dummy)
 {
 	int cnt = (skb->len > skb->data_len);
 
@@ -704,7 +702,7 @@ static inline void wrb_fill(struct be_eth_wrb *wrb, u64 addr, int len)
 }
 
 static inline u16 be_get_tx_vlan_tag(struct be_adapter *adapter,
-					struct sk_buff *skb)
+				     struct sk_buff *skb)
 {
 	u8 vlan_prio;
 	u16 vlan_tag;
@@ -733,7 +731,8 @@ static u16 skb_ip_proto(struct sk_buff *skb)
 }
 
 static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
-		struct sk_buff *skb, u32 wrb_cnt, u32 len, bool skip_hw_vlan)
+			 struct sk_buff *skb, u32 wrb_cnt, u32 len,
+			 bool skip_hw_vlan)
 {
 	u16 vlan_tag, proto;
 
@@ -774,7 +773,7 @@ static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
 }
 
 static void unmap_tx_frag(struct device *dev, struct be_eth_wrb *wrb,
-		bool unmap_single)
+			  bool unmap_single)
 {
 	dma_addr_t dma;
 
@@ -791,8 +790,8 @@ static void unmap_tx_frag(struct device *dev, struct be_eth_wrb *wrb,
 }
 
 static int make_tx_wrbs(struct be_adapter *adapter, struct be_queue_info *txq,
-		struct sk_buff *skb, u32 wrb_cnt, bool dummy_wrb,
-		bool skip_hw_vlan)
+			struct sk_buff *skb, u32 wrb_cnt, bool dummy_wrb,
+			bool skip_hw_vlan)
 {
 	dma_addr_t busaddr;
 	int i, copied = 0;
@@ -821,8 +820,7 @@ static int make_tx_wrbs(struct be_adapter *adapter, struct be_queue_info *txq,
 	}
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-		const struct skb_frag_struct *frag =
-			&skb_shinfo(skb)->frags[i];
+		const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
 		busaddr = skb_frag_dma_map(dev, frag, 0,
 					   skb_frag_size(frag), DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, busaddr))
@@ -927,8 +925,7 @@ static int be_vlan_tag_tx_chk(struct be_adapter *adapter, struct sk_buff *skb)
 	return vlan_tx_tag_present(skb) || adapter->pvid || adapter->qnq_vid;
 }
 
-static int be_ipv6_tx_stall_chk(struct be_adapter *adapter,
-				struct sk_buff *skb)
+static int be_ipv6_tx_stall_chk(struct be_adapter *adapter, struct sk_buff *skb)
 {
 	return BE3_chip(adapter) && be_ipv6_exthdr_check(skb);
 }
@@ -959,7 +956,7 @@ static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter,
 	 */
 	if (be_pvid_tagging_enabled(adapter) &&
 	    veh->h_vlan_proto == htons(ETH_P_8021Q))
-			*skip_hw_vlan = true;
+		*skip_hw_vlan = true;
 
 	/* HW has a bug wherein it will calculate CSUM for VLAN
 	 * pkts even though it is disabled.
@@ -1077,16 +1074,15 @@ static int be_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	if (new_mtu < BE_MIN_MTU ||
-			new_mtu > (BE_MAX_JUMBO_FRAME_SIZE -
-					(ETH_HLEN + ETH_FCS_LEN))) {
+	    new_mtu > (BE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN))) {
 		dev_info(&adapter->pdev->dev,
-			"MTU must be between %d and %d bytes\n",
-			BE_MIN_MTU,
-			(BE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN)));
+			 "MTU must be between %d and %d bytes\n",
+			 BE_MIN_MTU,
+			 (BE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN)));
 		return -EINVAL;
 	}
 	dev_info(&adapter->pdev->dev, "MTU changed from %d to %d bytes\n",
-			netdev->mtu, new_mtu);
+		 netdev->mtu, new_mtu);
 	netdev->mtu = new_mtu;
 	return 0;
 }
@@ -1098,7 +1094,7 @@ static int be_change_mtu(struct net_device *netdev, int new_mtu)
 static int be_vid_config(struct be_adapter *adapter)
 {
 	u16 vids[BE_NUM_VLANS_SUPPORTED];
-	u16 num = 0, i;
+	u16 num = 0, i = 0;
 	int status = 0;
 
 	/* No need to further configure vids if in promiscuous mode */
@@ -1109,16 +1105,14 @@ static int be_vid_config(struct be_adapter *adapter)
 		goto set_vlan_promisc;
 
 	/* Construct VLAN Table to give to HW */
-	for (i = 0; i < VLAN_N_VID; i++)
-		if (adapter->vlan_tag[i])
-			vids[num++] = cpu_to_le16(i);
-
-	status = be_cmd_vlan_config(adapter, adapter->if_handle,
-				    vids, num, 0);
+	for_each_set_bit(i, adapter->vids, VLAN_N_VID)
+		vids[num++] = cpu_to_le16(i);
 
+	status = be_cmd_vlan_config(adapter, adapter->if_handle, vids, num);
 	if (status) {
 		/* Set to VLAN promisc mode as setting VLAN filter failed */
-		if (status == MCC_ADDL_STS_INSUFFICIENT_RESOURCES)
+		if (addl_status(status) ==
+				MCC_ADDL_STATUS_INSUFFICIENT_RESOURCES)
 			goto set_vlan_promisc;
 		dev_err(&adapter->pdev->dev,
 			"Setting HW VLAN filtering failed.\n");
@@ -1160,16 +1154,16 @@ static int be_vlan_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	if (lancer_chip(adapter) && vid == 0)
 		return status;
 
-	if (adapter->vlan_tag[vid])
+	if (test_bit(vid, adapter->vids))
 		return status;
 
-	adapter->vlan_tag[vid] = 1;
+	set_bit(vid, adapter->vids);
 	adapter->vlans_added++;
 
 	status = be_vid_config(adapter);
 	if (status) {
 		adapter->vlans_added--;
-		adapter->vlan_tag[vid] = 0;
+		clear_bit(vid, adapter->vids);
 	}
 
 	return status;
@@ -1184,12 +1178,12 @@ static int be_vlan_rem_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	if (lancer_chip(adapter) && vid == 0)
 		goto ret;
 
-	adapter->vlan_tag[vid] = 0;
+	clear_bit(vid, adapter->vids);
 	status = be_vid_config(adapter);
 	if (!status)
 		adapter->vlans_added--;
 	else
-		adapter->vlan_tag[vid] = 1;
+		set_bit(vid, adapter->vids);
 ret:
 	return status;
 }
@@ -1197,7 +1191,7 @@ ret:
 static void be_clear_promisc(struct be_adapter *adapter)
 {
 	adapter->promiscuous = false;
-	adapter->flags &= ~BE_FLAGS_VLAN_PROMISC;
+	adapter->flags &= ~(BE_FLAGS_VLAN_PROMISC | BE_FLAGS_MCAST_PROMISC);
 
 	be_cmd_rx_filter(adapter, IFF_PROMISC, OFF);
 }
@@ -1222,10 +1216,8 @@ static void be_set_rx_mode(struct net_device *netdev)
 
 	/* Enable multicast promisc if num configured exceeds what we support */
 	if (netdev->flags & IFF_ALLMULTI ||
-	    netdev_mc_count(netdev) > be_max_mc(adapter)) {
-		be_cmd_rx_filter(adapter, IFF_ALLMULTI, ON);
-		goto done;
-	}
+	    netdev_mc_count(netdev) > be_max_mc(adapter))
+		goto set_mcast_promisc;
 
 	if (netdev_uc_count(netdev) != adapter->uc_macs) {
 		struct netdev_hw_addr *ha;
@@ -1251,13 +1243,22 @@ static void be_set_rx_mode(struct net_device *netdev)
 	}
 
 	status = be_cmd_rx_filter(adapter, IFF_MULTICAST, ON);
-
-	/* Set to MCAST promisc mode if setting MULTICAST address fails */
-	if (status) {
-		dev_info(&adapter->pdev->dev, "Exhausted multicast HW filters.\n");
-		dev_info(&adapter->pdev->dev, "Disabling HW multicast filtering.\n");
-		be_cmd_rx_filter(adapter, IFF_ALLMULTI, ON);
+	if (!status) {
+		if (adapter->flags & BE_FLAGS_MCAST_PROMISC)
+			adapter->flags &= ~BE_FLAGS_MCAST_PROMISC;
+		goto done;
 	}
+
+set_mcast_promisc:
+	if (adapter->flags & BE_FLAGS_MCAST_PROMISC)
+		return;
+
+	/* Set to MCAST promisc mode if setting MULTICAST address fails
+	 * or if num configured exceeds what we support
+	 */
+	status = be_cmd_rx_filter(adapter, IFF_ALLMULTI, ON);
+	if (!status)
+		adapter->flags |= BE_FLAGS_MCAST_PROMISC;
 done:
 	return;
 }
@@ -1287,7 +1288,7 @@ static int be_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 
 	if (status)
 		dev_err(&adapter->pdev->dev, "MAC %pM set on VF %d Failed\n",
-				mac, vf);
+			mac, vf);
 	else
 		memcpy(vf_cfg->mac_addr, mac, ETH_ALEN);
 
@@ -1295,7 +1296,7 @@ static int be_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 }
 
 static int be_get_vf_config(struct net_device *netdev, int vf,
-			struct ifla_vf_info *vi)
+			    struct ifla_vf_info *vi)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
@@ -1307,7 +1308,8 @@ static int be_get_vf_config(struct net_device *netdev, int vf,
 		return -EINVAL;
 
 	vi->vf = vf;
-	vi->tx_rate = vf_cfg->tx_rate;
+	vi->max_tx_rate = vf_cfg->tx_rate;
+	vi->min_tx_rate = 0;
 	vi->vlan = vf_cfg->vlan_tag & VLAN_VID_MASK;
 	vi->qos = vf_cfg->vlan_tag >> VLAN_PRIO_SHIFT;
 	memcpy(&vi->mac, vf_cfg->mac_addr, ETH_ALEN);
@@ -1316,8 +1318,7 @@ static int be_get_vf_config(struct net_device *netdev, int vf,
 	return 0;
 }
 
-static int be_set_vf_vlan(struct net_device *netdev,
-			int vf, u16 vlan, u8 qos)
+static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
@@ -1348,11 +1349,14 @@ static int be_set_vf_vlan(struct net_device *netdev,
 	return status;
 }
 
-static int be_set_vf_tx_rate(struct net_device *netdev,
-			int vf, int rate)
+static int be_set_vf_tx_rate(struct net_device *netdev, int vf,
+			     int min_tx_rate, int max_tx_rate)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
-	int status = 0;
+	struct device *dev = &adapter->pdev->dev;
+	int percent_rate, status = 0;
+	u16 link_speed = 0;
+	u8 link_status;
 
 	if (!sriov_enabled(adapter))
 		return -EPERM;
@@ -1360,18 +1364,50 @@ static int be_set_vf_tx_rate(struct net_device *netdev,
 	if (vf >= adapter->num_vfs)
 		return -EINVAL;
 
-	if (rate < 100 || rate > 10000) {
-		dev_err(&adapter->pdev->dev,
-			"tx rate must be between 100 and 10000 Mbps\n");
+	if (min_tx_rate)
 		return -EINVAL;
+
+	if (!max_tx_rate)
+		goto config_qos;
+
+	status = be_cmd_link_status_query(adapter, &link_speed,
+					  &link_status, 0);
+	if (status)
+		goto err;
+
+	if (!link_status) {
+		dev_err(dev, "TX-rate setting not allowed when link is down\n");
+		status = -EPERM;
+		goto err;
+	}
+
+	if (max_tx_rate < 100 || max_tx_rate > link_speed) {
+		dev_err(dev, "TX-rate must be between 100 and %d Mbps\n",
+			link_speed);
+		status = -EINVAL;
+		goto err;
+	}
+
+	/* On Skyhawk the QOS setting must be done only as a % value */
+	percent_rate = link_speed / 100;
+	if (skyhawk_chip(adapter) && (max_tx_rate % percent_rate)) {
+		dev_err(dev, "TX-rate must be a multiple of %d Mbps\n",
+			percent_rate);
+		status = -EINVAL;
+		goto err;
 	}
 
-	status = be_cmd_config_qos(adapter, rate / 10, vf + 1);
+config_qos:
+	status = be_cmd_config_qos(adapter, max_tx_rate, link_speed, vf + 1);
 	if (status)
-		dev_err(&adapter->pdev->dev,
-				"tx rate %d on VF %d failed\n", rate, vf);
-	else
-		adapter->vf_cfg[vf].tx_rate = rate;
+		goto err;
+
+	adapter->vf_cfg[vf].tx_rate = max_tx_rate;
+	return 0;
+
+err:
+	dev_err(dev, "TX-rate setting of %dMbps on VF%d failed\n",
+		max_tx_rate, vf);
 	return status;
 }
 static int be_set_vf_link_state(struct net_device *netdev, int vf,
@@ -1469,7 +1505,7 @@ modify_eqd:
 }
 
 static void be_rx_stats_update(struct be_rx_obj *rxo,
-		struct be_rx_compl_info *rxcp)
+			       struct be_rx_compl_info *rxcp)
 {
 	struct be_rx_stats *stats = rx_stats(rxo);
 
@@ -1566,7 +1602,8 @@ static void skb_fill_rx_data(struct be_rx_obj *rxo, struct sk_buff *skb,
 		skb_frag_set_page(skb, 0, page_info->page);
 		skb_shinfo(skb)->frags[0].page_offset =
 					page_info->page_offset + hdr_len;
-		skb_frag_size_set(&skb_shinfo(skb)->frags[0], curr_frag_len - hdr_len);
+		skb_frag_size_set(&skb_shinfo(skb)->frags[0],
+				  curr_frag_len - hdr_len);
 		skb->data_len = curr_frag_len - hdr_len;
 		skb->truesize += rx_frag_size;
 		skb->tail += hdr_len;
@@ -1725,8 +1762,8 @@ static void be_parse_rx_compl_v1(struct be_eth_rx_compl *compl,
 	if (rxcp->vlanf) {
 		rxcp->qnq = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, qnq,
 					  compl);
-		rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vlan_tag,
-					       compl);
+		rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v1,
+					       vlan_tag, compl);
 	}
 	rxcp->port = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, port, compl);
 	rxcp->tunneled =
@@ -1757,8 +1794,8 @@ static void be_parse_rx_compl_v0(struct be_eth_rx_compl *compl,
 	if (rxcp->vlanf) {
 		rxcp->qnq = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, qnq,
 					  compl);
-		rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vlan_tag,
-					       compl);
+		rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v0,
+					       vlan_tag, compl);
 	}
 	rxcp->port = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, port, compl);
 	rxcp->ip_frag = AMAP_GET_BITS(struct amap_eth_rx_compl_v0,
@@ -1799,7 +1836,7 @@ static struct be_rx_compl_info *be_rx_compl_get(struct be_rx_obj *rxo)
 			rxcp->vlan_tag = swab16(rxcp->vlan_tag);
 
 		if (adapter->pvid == (rxcp->vlan_tag & VLAN_VID_MASK) &&
-		    !adapter->vlan_tag[rxcp->vlan_tag])
+		    !test_bit(rxcp->vlan_tag, adapter->vids))
 			rxcp->vlanf = 0;
 	}
 
@@ -1915,7 +1952,7 @@ static struct be_eth_tx_compl *be_tx_compl_get(struct be_queue_info *tx_cq)
 }
 
 static u16 be_tx_compl_process(struct be_adapter *adapter,
-		struct be_tx_obj *txo, u16 last_index)
+			       struct be_tx_obj *txo, u16 last_index)
 {
 	struct be_queue_info *txq = &txo->q;
 	struct be_eth_wrb *wrb;
@@ -2122,7 +2159,7 @@ static int be_evt_queues_create(struct be_adapter *adapter)
 
 		eq = &eqo->q;
 		rc = be_queue_alloc(adapter, eq, EVNT_Q_LEN,
-					sizeof(struct be_eq_entry));
+				    sizeof(struct be_eq_entry));
 		if (rc)
 			return rc;
 
@@ -2155,7 +2192,7 @@ static int be_mcc_queues_create(struct be_adapter *adapter)
 
 	cq = &adapter->mcc_obj.cq;
 	if (be_queue_alloc(adapter, cq, MCC_CQ_LEN,
-			sizeof(struct be_mcc_compl)))
+			   sizeof(struct be_mcc_compl)))
 		goto err;
 
 	/* Use the default EQ for MCC completions */
@@ -2275,7 +2312,7 @@ static int be_rx_cqs_create(struct be_adapter *adapter)
 		rxo->adapter = adapter;
 		cq = &rxo->cq;
 		rc = be_queue_alloc(adapter, cq, RX_CQ_LEN,
-				sizeof(struct be_eth_rx_compl));
+				    sizeof(struct be_eth_rx_compl));
 		if (rc)
 			return rc;
 
@@ -2339,7 +2376,7 @@ static inline bool do_gro(struct be_rx_compl_info *rxcp)
 }
 
 static int be_process_rx(struct be_rx_obj *rxo, struct napi_struct *napi,
-			int budget, int polling)
+			 int budget, int polling)
 {
 	struct be_adapter *adapter = rxo->adapter;
 	struct be_queue_info *rx_cq = &rxo->cq;
@@ -2365,7 +2402,7 @@ static int be_process_rx(struct be_rx_obj *rxo, struct napi_struct *napi,
 		 * promiscuous mode on some skews
 		 */
 		if (unlikely(rxcp->port != adapter->port_num &&
-				!lancer_chip(adapter))) {
+			     !lancer_chip(adapter))) {
 			be_rx_compl_discard(rxo, rxcp);
 			goto loop_continue;
 		}
@@ -2405,8 +2442,9 @@ static bool be_process_tx(struct be_adapter *adapter, struct be_tx_obj *txo,
 		if (!txcp)
 			break;
 		num_wrbs += be_tx_compl_process(adapter, txo,
-				AMAP_GET_BITS(struct amap_eth_tx_compl,
-					wrb_index, txcp));
+						AMAP_GET_BITS(struct
+							      amap_eth_tx_compl,
+							      wrb_index, txcp));
 	}
 
 	if (work_done) {
@@ -2416,7 +2454,7 @@ static bool be_process_tx(struct be_adapter *adapter, struct be_tx_obj *txo,
 		/* As Tx wrbs have been freed up, wake up netdev queue
 		 * if it was stopped due to lack of tx wrbs.  */
 		if (__netif_subqueue_stopped(adapter->netdev, idx) &&
-			atomic_read(&txo->q.used) < txo->q.len / 2) {
+		    atomic_read(&txo->q.used) < txo->q.len / 2) {
 			netif_wake_subqueue(adapter->netdev, idx);
 		}
 
@@ -2510,9 +2548,9 @@ void be_detect_error(struct be_adapter *adapter)
 		sliport_status = ioread32(adapter->db + SLIPORT_STATUS_OFFSET);
 		if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
 			sliport_err1 = ioread32(adapter->db +
-					SLIPORT_ERROR1_OFFSET);
+						SLIPORT_ERROR1_OFFSET);
 			sliport_err2 = ioread32(adapter->db +
-					SLIPORT_ERROR2_OFFSET);
+						SLIPORT_ERROR2_OFFSET);
 			adapter->hw_error = true;
 			/* Do not log error messages if its a FW reset */
 			if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 &&
@@ -2531,13 +2569,13 @@ void be_detect_error(struct be_adapter *adapter)
 		}
 	} else {
 		pci_read_config_dword(adapter->pdev,
-				PCICFG_UE_STATUS_LOW, &ue_lo);
+				      PCICFG_UE_STATUS_LOW, &ue_lo);
 		pci_read_config_dword(adapter->pdev,
-				PCICFG_UE_STATUS_HIGH, &ue_hi);
+				      PCICFG_UE_STATUS_HIGH, &ue_hi);
 		pci_read_config_dword(adapter->pdev,
-				PCICFG_UE_STATUS_LOW_MASK, &ue_lo_mask);
+				      PCICFG_UE_STATUS_LOW_MASK, &ue_lo_mask);
 		pci_read_config_dword(adapter->pdev,
-				PCICFG_UE_STATUS_HI_MASK, &ue_hi_mask);
+				      PCICFG_UE_STATUS_HI_MASK, &ue_hi_mask);
 
 		ue_lo = (ue_lo & ~ue_lo_mask);
 		ue_hi = (ue_hi & ~ue_hi_mask);
@@ -2624,7 +2662,7 @@ fail:
 }
 
 static inline int be_msix_vec_get(struct be_adapter *adapter,
-				struct be_eq_obj *eqo)
+				  struct be_eq_obj *eqo)
 {
 	return adapter->msix_entries[eqo->msix_idx].vector;
 }
@@ -2648,7 +2686,7 @@ err_msix:
 	for (i--, eqo = &adapter->eq_obj[i]; i >= 0; i--, eqo--)
 		free_irq(be_msix_vec_get(adapter, eqo), eqo);
 	dev_warn(&adapter->pdev->dev, "MSIX Request IRQ failed - err %d\n",
-		status);
+		 status);
 	be_msix_disable(adapter);
 	return status;
 }
@@ -2774,7 +2812,8 @@ static int be_rx_qs_create(struct be_adapter *adapter)
 {
 	struct be_rx_obj *rxo;
 	int rc, i, j;
-	u8 rsstable[128];
+	u8 rss_hkey[RSS_HASH_KEY_LEN];
+	struct rss_info *rss = &adapter->rss_info;
 
 	for_all_rx_queues(adapter, rxo, i) {
 		rc = be_queue_alloc(adapter, &rxo->q, RX_Q_LEN,
@@ -2799,31 +2838,36 @@ static int be_rx_qs_create(struct be_adapter *adapter)
 	}
 
 	if (be_multi_rxq(adapter)) {
-		for (j = 0; j < 128; j += adapter->num_rx_qs - 1) {
+		for (j = 0; j < RSS_INDIR_TABLE_LEN;
+			j += adapter->num_rx_qs - 1) {
 			for_all_rss_queues(adapter, rxo, i) {
-				if ((j + i) >= 128)
+				if ((j + i) >= RSS_INDIR_TABLE_LEN)
 					break;
-				rsstable[j + i] = rxo->rss_id;
+				rss->rsstable[j + i] = rxo->rss_id;
+				rss->rss_queue[j + i] = i;
 			}
 		}
-		adapter->rss_flags = RSS_ENABLE_TCP_IPV4 | RSS_ENABLE_IPV4 |
-					RSS_ENABLE_TCP_IPV6 | RSS_ENABLE_IPV6;
+		rss->rss_flags = RSS_ENABLE_TCP_IPV4 | RSS_ENABLE_IPV4 |
+			RSS_ENABLE_TCP_IPV6 | RSS_ENABLE_IPV6;
 
 		if (!BEx_chip(adapter))
-			adapter->rss_flags |= RSS_ENABLE_UDP_IPV4 |
-						RSS_ENABLE_UDP_IPV6;
+			rss->rss_flags |= RSS_ENABLE_UDP_IPV4 |
+				RSS_ENABLE_UDP_IPV6;
 	} else {
 		/* Disable RSS, if only default RX Q is created */
-		adapter->rss_flags = RSS_ENABLE_NONE;
+		rss->rss_flags = RSS_ENABLE_NONE;
 	}
 
-	rc = be_cmd_rss_config(adapter, rsstable, adapter->rss_flags,
-			       128);
+	get_random_bytes(rss_hkey, RSS_HASH_KEY_LEN);
+	rc = be_cmd_rss_config(adapter, rss->rsstable, rss->rss_flags,
+			       128, rss_hkey);
 	if (rc) {
-		adapter->rss_flags = RSS_ENABLE_NONE;
+		rss->rss_flags = RSS_ENABLE_NONE;
 		return rc;
 	}
 
+	memcpy(rss->rss_hkey, rss_hkey, RSS_HASH_KEY_LEN);
+
 	/* First time posting */
 	for_all_rx_queues(adapter, rxo, i)
 		be_post_rx_frags(rxo, GFP_KERNEL);
@@ -2858,7 +2902,7 @@ static int be_open(struct net_device *netdev)
 	for_all_evt_queues(adapter, eqo, i) {
 		napi_enable(&eqo->napi);
 		be_enable_busy_poll(eqo);
-		be_eq_notify(adapter, eqo->q.id, true, false, 0);
+		be_eq_notify(adapter, eqo->q.id, true, true, 0);
 	}
 	adapter->flags |= BE_FLAGS_NAPI_ENABLED;
 
@@ -2896,7 +2940,8 @@ static int be_setup_wol(struct be_adapter *adapter, bool enable)
 
 	if (enable) {
 		status = pci_write_config_dword(adapter->pdev,
-			PCICFG_PM_CONTROL_OFFSET, PCICFG_PM_CONTROL_MASK);
+						PCICFG_PM_CONTROL_OFFSET,
+						PCICFG_PM_CONTROL_MASK);
 		if (status) {
 			dev_err(&adapter->pdev->dev,
 				"Could not enable Wake-on-lan\n");
@@ -2905,7 +2950,8 @@ static int be_setup_wol(struct be_adapter *adapter, bool enable)
 			return status;
 		}
 		status = be_cmd_enable_magic_wol(adapter,
-				adapter->netdev->dev_addr, &cmd);
+						 adapter->netdev->dev_addr,
+						 &cmd);
 		pci_enable_wake(adapter->pdev, PCI_D3hot, 1);
 		pci_enable_wake(adapter->pdev, PCI_D3cold, 1);
 	} else {
@@ -2944,7 +2990,8 @@ static int be_vf_eth_addr_config(struct be_adapter *adapter)
 
 		if (status)
 			dev_err(&adapter->pdev->dev,
-			"Mac address assignment failed for VF %d\n", vf);
+				"Mac address assignment failed for VF %d\n",
+				vf);
 		else
 			memcpy(vf_cfg->mac_addr, mac, ETH_ALEN);
 
@@ -3086,9 +3133,11 @@ static int be_vfs_if_create(struct be_adapter *adapter)
 
 		/* If a FW profile exists, then cap_flags are updated */
 		en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED |
-			   BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_MULTICAST);
-		status = be_cmd_if_create(adapter, cap_flags, en_flags,
-					  &vf_cfg->if_handle, vf + 1);
+					BE_IF_FLAGS_BROADCAST |
+					BE_IF_FLAGS_MULTICAST);
+		status =
+		    be_cmd_if_create(adapter, cap_flags, en_flags,
+				     &vf_cfg->if_handle, vf + 1);
 		if (status)
 			goto err;
 	}
@@ -3119,7 +3168,6 @@ static int be_vf_setup(struct be_adapter *adapter)
 	struct be_vf_cfg *vf_cfg;
 	int status, old_vfs, vf;
 	u32 privileges;
-	u16 lnk_speed;
 
 	old_vfs = pci_num_vf(adapter->pdev);
 	if (old_vfs) {
@@ -3175,16 +3223,9 @@ static int be_vf_setup(struct be_adapter *adapter)
 					 vf);
 		}
 
-		/* BE3 FW, by default, caps VF TX-rate to 100mbps.
-		 * Allow full available bandwidth
-		 */
-		if (BE3_chip(adapter) && !old_vfs)
-			be_cmd_config_qos(adapter, 1000, vf + 1);
-
-		status = be_cmd_link_status_query(adapter, &lnk_speed,
-						  NULL, vf + 1);
-		if (!status)
-			vf_cfg->tx_rate = lnk_speed;
+		/* Allow full available bandwidth */
+		if (!old_vfs)
+			be_cmd_config_qos(adapter, 0, 0, vf + 1);
 
 		if (!old_vfs) {
 			be_cmd_enable_vf(adapter, vf + 1);
@@ -3213,9 +3254,9 @@ err:
 
 static u8 be_convert_mc_type(u32 function_mode)
 {
-	if (function_mode & VNIC_MODE && function_mode & FLEX10_MODE)
+	if (function_mode & VNIC_MODE && function_mode & QNQ_MODE)
 		return vNIC1;
-	else if (function_mode & FLEX10_MODE)
+	else if (function_mode & QNQ_MODE)
 		return FLEX10;
 	else if (function_mode & VNIC_MODE)
 		return vNIC2;
@@ -3590,35 +3631,7 @@ static void be_netpoll(struct net_device *netdev)
 }
 #endif
 
-#define FW_FILE_HDR_SIGN 	"ServerEngines Corp. "
-static char flash_cookie[2][16] =      {"*** SE FLAS", "H DIRECTORY *** "};
-
-static bool be_flash_redboot(struct be_adapter *adapter,
-			const u8 *p, u32 img_start, int image_size,
-			int hdr_size)
-{
-	u32 crc_offset;
-	u8 flashed_crc[4];
-	int status;
-
-	crc_offset = hdr_size + img_start + image_size - 4;
-
-	p += crc_offset;
-
-	status = be_cmd_get_flash_crc(adapter, flashed_crc,
-			(image_size - 4));
-	if (status) {
-		dev_err(&adapter->pdev->dev,
-		"could not get crc from flash, not flashing redboot\n");
-		return false;
-	}
-
-	/*update redboot only if crc does not match*/
-	if (!memcmp(flashed_crc, p, 4))
-		return false;
-	else
-		return true;
-}
+static char flash_cookie[2][16] = {"*** SE FLAS", "H DIRECTORY *** "};
 
 static bool phy_flashing_required(struct be_adapter *adapter)
 {
@@ -3649,8 +3662,8 @@ static bool is_comp_in_ufi(struct be_adapter *adapter,
 }
 
 static struct flash_section_info *get_fsec_info(struct be_adapter *adapter,
-					 int header_size,
-					 const struct firmware *fw)
+						int header_size,
+						const struct firmware *fw)
 {
 	struct flash_section_info *fsec = NULL;
 	const u8 *p = fw->data;
@@ -3665,12 +3678,35 @@ static struct flash_section_info *get_fsec_info(struct be_adapter *adapter,
 	return NULL;
 }
 
+static int be_check_flash_crc(struct be_adapter *adapter, const u8 *p,
+			      u32 img_offset, u32 img_size, int hdr_size,
+			      u16 img_optype, bool *crc_match)
+{
+	u32 crc_offset;
+	int status;
+	u8 crc[4];
+
+	status = be_cmd_get_flash_crc(adapter, crc, img_optype, img_size - 4);
+	if (status)
+		return status;
+
+	crc_offset = hdr_size + img_offset + img_size - 4;
+
+	/* Skip flashing, if crc of flashed region matches */
+	if (!memcmp(crc, p + crc_offset, 4))
+		*crc_match = true;
+	else
+		*crc_match = false;
+
+	return status;
+}
+
 static int be_flash(struct be_adapter *adapter, const u8 *img,
-		struct be_dma_mem *flash_cmd, int optype, int img_size)
+		    struct be_dma_mem *flash_cmd, int optype, int img_size)
 {
-	u32 total_bytes = 0, flash_op, num_bytes = 0;
-	int status = 0;
 	struct be_cmd_write_flashrom *req = flash_cmd->va;
+	u32 total_bytes, flash_op, num_bytes;
+	int status;
 
 	total_bytes = img_size;
 	while (total_bytes) {
@@ -3693,32 +3729,28 @@ static int be_flash(struct be_adapter *adapter, const u8 *img,
 		memcpy(req->data_buf, img, num_bytes);
 		img += num_bytes;
 		status = be_cmd_write_flashrom(adapter, flash_cmd, optype,
-						flash_op, num_bytes);
-		if (status) {
-			if (status == ILLEGAL_IOCTL_REQ &&
-			    optype == OPTYPE_PHY_FW)
-				break;
-			dev_err(&adapter->pdev->dev,
-				"cmd to write to flash rom failed.\n");
+					       flash_op, num_bytes);
+		if (base_status(status) == MCC_STATUS_ILLEGAL_REQUEST &&
+		    optype == OPTYPE_PHY_FW)
+			break;
+		else if (status)
 			return status;
-		}
 	}
 	return 0;
 }
 
 /* For BE2, BE3 and BE3-R */
 static int be_flash_BEx(struct be_adapter *adapter,
-			 const struct firmware *fw,
-			 struct be_dma_mem *flash_cmd,
-			 int num_of_images)
-
+			const struct firmware *fw,
+			struct be_dma_mem *flash_cmd, int num_of_images)
 {
-	int status = 0, i, filehdr_size = 0;
 	int img_hdrs_size = (num_of_images * sizeof(struct image_hdr));
-	const u8 *p = fw->data;
-	const struct flash_comp *pflashcomp;
-	int num_comp, redboot;
+	struct device *dev = &adapter->pdev->dev;
 	struct flash_section_info *fsec = NULL;
+	int status, i, filehdr_size, num_comp;
+	const struct flash_comp *pflashcomp;
+	bool crc_match;
+	const u8 *p;
 
 	struct flash_comp gen3_flash_types[] = {
 		{ FLASH_iSCSI_PRIMARY_IMAGE_START_g3, OPTYPE_ISCSI_ACTIVE,
@@ -3775,8 +3807,7 @@ static int be_flash_BEx(struct be_adapter *adapter,
 	/* Get flash section info*/
 	fsec = get_fsec_info(adapter, filehdr_size + img_hdrs_size, fw);
 	if (!fsec) {
-		dev_err(&adapter->pdev->dev,
-			"Invalid Cookie. UFI corrupted ?\n");
+		dev_err(dev, "Invalid Cookie. FW image may be corrupted\n");
 		return -1;
 	}
 	for (i = 0; i < num_comp; i++) {
@@ -3792,23 +3823,32 @@ static int be_flash_BEx(struct be_adapter *adapter,
 				continue;
 
 		if (pflashcomp[i].optype == OPTYPE_REDBOOT) {
-			redboot = be_flash_redboot(adapter, fw->data,
-				pflashcomp[i].offset, pflashcomp[i].size,
-				filehdr_size + img_hdrs_size);
-			if (!redboot)
+			status = be_check_flash_crc(adapter, fw->data,
+						    pflashcomp[i].offset,
+						    pflashcomp[i].size,
+						    filehdr_size +
+						    img_hdrs_size,
+						    OPTYPE_REDBOOT, &crc_match);
+			if (status) {
+				dev_err(dev,
+					"Could not get CRC for 0x%x region\n",
+					pflashcomp[i].optype);
+				continue;
+			}
+
+			if (crc_match)
 				continue;
 		}
 
-		p = fw->data;
-		p += filehdr_size + pflashcomp[i].offset + img_hdrs_size;
+		p = fw->data + filehdr_size + pflashcomp[i].offset +
+			img_hdrs_size;
 		if (p + pflashcomp[i].size > fw->data + fw->size)
 			return -1;
 
 		status = be_flash(adapter, p, flash_cmd, pflashcomp[i].optype,
-					pflashcomp[i].size);
+				  pflashcomp[i].size);
 		if (status) {
-			dev_err(&adapter->pdev->dev,
-				"Flashing section type %d failed.\n",
+			dev_err(dev, "Flashing section type 0x%x failed\n",
 				pflashcomp[i].img_type);
 			return status;
 		}
@@ -3816,80 +3856,142 @@ static int be_flash_BEx(struct be_adapter *adapter,
 	return 0;
 }
 
+static u16 be_get_img_optype(struct flash_section_entry fsec_entry)
+{
+	u32 img_type = le32_to_cpu(fsec_entry.type);
+	u16 img_optype = le16_to_cpu(fsec_entry.optype);
+
+	if (img_optype != 0xFFFF)
+		return img_optype;
+
+	switch (img_type) {
+	case IMAGE_FIRMWARE_iSCSI:
+		img_optype = OPTYPE_ISCSI_ACTIVE;
+		break;
+	case IMAGE_BOOT_CODE:
+		img_optype = OPTYPE_REDBOOT;
+		break;
+	case IMAGE_OPTION_ROM_ISCSI:
+		img_optype = OPTYPE_BIOS;
+		break;
+	case IMAGE_OPTION_ROM_PXE:
+		img_optype = OPTYPE_PXE_BIOS;
+		break;
+	case IMAGE_OPTION_ROM_FCoE:
+		img_optype = OPTYPE_FCOE_BIOS;
+		break;
+	case IMAGE_FIRMWARE_BACKUP_iSCSI:
+		img_optype = OPTYPE_ISCSI_BACKUP;
+		break;
+	case IMAGE_NCSI:
+		img_optype = OPTYPE_NCSI_FW;
+		break;
+	case IMAGE_FLASHISM_JUMPVECTOR:
+		img_optype = OPTYPE_FLASHISM_JUMPVECTOR;
+		break;
+	case IMAGE_FIRMWARE_PHY:
+		img_optype = OPTYPE_SH_PHY_FW;
+		break;
+	case IMAGE_REDBOOT_DIR:
+		img_optype = OPTYPE_REDBOOT_DIR;
+		break;
+	case IMAGE_REDBOOT_CONFIG:
+		img_optype = OPTYPE_REDBOOT_CONFIG;
+		break;
+	case IMAGE_UFI_DIR:
+		img_optype = OPTYPE_UFI_DIR;
+		break;
+	default:
+		break;
+	}
+
+	return img_optype;
+}
+
 static int be_flash_skyhawk(struct be_adapter *adapter,
-		const struct firmware *fw,
-		struct be_dma_mem *flash_cmd, int num_of_images)
+			    const struct firmware *fw,
+			    struct be_dma_mem *flash_cmd, int num_of_images)
 {
-	int status = 0, i, filehdr_size = 0;
-	int img_offset, img_size, img_optype, redboot;
 	int img_hdrs_size = num_of_images * sizeof(struct image_hdr);
-	const u8 *p = fw->data;
+	struct device *dev = &adapter->pdev->dev;
 	struct flash_section_info *fsec = NULL;
+	u32 img_offset, img_size, img_type;
+	int status, i, filehdr_size;
+	bool crc_match, old_fw_img;
+	u16 img_optype;
+	const u8 *p;
 
 	filehdr_size = sizeof(struct flash_file_hdr_g3);
 	fsec = get_fsec_info(adapter, filehdr_size + img_hdrs_size, fw);
 	if (!fsec) {
-		dev_err(&adapter->pdev->dev,
-			"Invalid Cookie. UFI corrupted ?\n");
+		dev_err(dev, "Invalid Cookie. FW image may be corrupted\n");
 		return -1;
 	}
 
 	for (i = 0; i < le32_to_cpu(fsec->fsec_hdr.num_images); i++) {
 		img_offset = le32_to_cpu(fsec->fsec_entry[i].offset);
 		img_size   = le32_to_cpu(fsec->fsec_entry[i].pad_size);
+		img_type   = le32_to_cpu(fsec->fsec_entry[i].type);
+		img_optype = be_get_img_optype(fsec->fsec_entry[i]);
+		old_fw_img = fsec->fsec_entry[i].optype == 0xFFFF;
 
-		switch (le32_to_cpu(fsec->fsec_entry[i].type)) {
-		case IMAGE_FIRMWARE_iSCSI:
-			img_optype = OPTYPE_ISCSI_ACTIVE;
-			break;
-		case IMAGE_BOOT_CODE:
-			img_optype = OPTYPE_REDBOOT;
-			break;
-		case IMAGE_OPTION_ROM_ISCSI:
-			img_optype = OPTYPE_BIOS;
-			break;
-		case IMAGE_OPTION_ROM_PXE:
-			img_optype = OPTYPE_PXE_BIOS;
-			break;
-		case IMAGE_OPTION_ROM_FCoE:
-			img_optype = OPTYPE_FCOE_BIOS;
-			break;
-		case IMAGE_FIRMWARE_BACKUP_iSCSI:
-			img_optype = OPTYPE_ISCSI_BACKUP;
-			break;
-		case IMAGE_NCSI:
-			img_optype = OPTYPE_NCSI_FW;
-			break;
-		default:
+		if (img_optype == 0xFFFF)
 			continue;
+		/* Don't bother verifying CRC if an old FW image is being
+		 * flashed
+		 */
+		if (old_fw_img)
+			goto flash;
+
+		status = be_check_flash_crc(adapter, fw->data, img_offset,
+					    img_size, filehdr_size +
+					    img_hdrs_size, img_optype,
+					    &crc_match);
+		/* The current FW image on the card does not recognize the new
+		 * FLASH op_type. The FW download is partially complete.
+		 * Reboot the server now to enable FW image to recognize the
+		 * new FLASH op_type. To complete the remaining process,
+		 * download the same FW again after the reboot.
+		 */
+		if (base_status(status) == MCC_STATUS_ILLEGAL_REQUEST ||
+		    base_status(status) == MCC_STATUS_ILLEGAL_FIELD) {
+			dev_err(dev, "Flash incomplete. Reset the server\n");
+			dev_err(dev, "Download FW image again after reset\n");
+			return -EAGAIN;
+		} else if (status) {
+			dev_err(dev, "Could not get CRC for 0x%x region\n",
+				img_optype);
+			return -EFAULT;
 		}
 
-		if (img_optype == OPTYPE_REDBOOT) {
-			redboot = be_flash_redboot(adapter, fw->data,
-					img_offset, img_size,
-					filehdr_size + img_hdrs_size);
-			if (!redboot)
-				continue;
-		}
+		if (crc_match)
+			continue;
 
-		p = fw->data;
-		p += filehdr_size + img_offset + img_hdrs_size;
+flash:
+		p = fw->data + filehdr_size + img_offset + img_hdrs_size;
 		if (p + img_size > fw->data + fw->size)
 			return -1;
 
 		status = be_flash(adapter, p, flash_cmd, img_optype, img_size);
-		if (status) {
-			dev_err(&adapter->pdev->dev,
-				"Flashing section type %d failed.\n",
-				fsec->fsec_entry[i].type);
-			return status;
+		/* For old FW images ignore ILLEGAL_FIELD error or errors on
+		 * UFI_DIR region
+		 */
+		if (old_fw_img &&
+		    (base_status(status) == MCC_STATUS_ILLEGAL_FIELD ||
+		     (img_optype == OPTYPE_UFI_DIR &&
+		      base_status(status) == MCC_STATUS_FAILED))) {
+			continue;
+		} else if (status) {
+			dev_err(dev, "Flashing section type 0x%x failed\n",
+				img_type);
+			return -EFAULT;
 		}
 	}
 	return 0;
 }
 
 static int lancer_fw_download(struct be_adapter *adapter,
-				const struct firmware *fw)
+			      const struct firmware *fw)
 {
 #define LANCER_FW_DOWNLOAD_CHUNK      (32 * 1024)
 #define LANCER_FW_DOWNLOAD_LOCATION   "/prg"
@@ -3955,7 +4057,7 @@ static int lancer_fw_download(struct be_adapter *adapter,
 	}
 
 	dma_free_coherent(&adapter->pdev->dev, flash_cmd.size, flash_cmd.va,
-				flash_cmd.dma);
+			  flash_cmd.dma);
 	if (status) {
 		dev_err(&adapter->pdev->dev,
 			"Firmware load error. "
@@ -3976,9 +4078,8 @@ static int lancer_fw_download(struct be_adapter *adapter,
 			goto lancer_fw_exit;
 		}
 	} else if (change_status != LANCER_NO_RESET_NEEDED) {
-			dev_err(&adapter->pdev->dev,
-				"System reboot required for new FW"
-				" to be active\n");
+		dev_err(&adapter->pdev->dev,
+			"System reboot required for new FW to be active\n");
 	}
 
 	dev_info(&adapter->pdev->dev, "Firmware flashed successfully\n");
@@ -4042,7 +4143,7 @@ static int be_fw_download(struct be_adapter *adapter, const struct firmware* fw)
 			switch (ufi_type) {
 			case UFI_TYPE4:
 				status = be_flash_skyhawk(adapter, fw,
-							&flash_cmd, num_imgs);
+							  &flash_cmd, num_imgs);
 				break;
 			case UFI_TYPE3R:
 				status = be_flash_BEx(adapter, fw, &flash_cmd,
@@ -4112,8 +4213,7 @@ fw_exit:
 	return status;
 }
 
-static int be_ndo_bridge_setlink(struct net_device *dev,
-				    struct nlmsghdr *nlh)
+static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh)
 {
 	struct be_adapter *adapter = netdev_priv(dev);
 	struct nlattr *attr, *br_spec;
@@ -4155,8 +4255,7 @@ err:
 }
 
 static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
-				    struct net_device *dev,
-				    u32 filter_mask)
+				 struct net_device *dev, u32 filter_mask)
 {
 	struct be_adapter *adapter = netdev_priv(dev);
 	int status = 0;
@@ -4254,7 +4353,7 @@ static const struct net_device_ops be_netdev_ops = {
 	.ndo_vlan_rx_kill_vid	= be_vlan_rem_vid,
 	.ndo_set_vf_mac		= be_set_vf_mac,
 	.ndo_set_vf_vlan	= be_set_vf_vlan,
-	.ndo_set_vf_tx_rate	= be_set_vf_tx_rate,
+	.ndo_set_vf_rate	= be_set_vf_tx_rate,
 	.ndo_get_vf_config	= be_get_vf_config,
 	.ndo_set_vf_link_state  = be_set_vf_link_state,
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -4301,7 +4400,7 @@ static void be_netdev_init(struct net_device *netdev)
 
 	netdev->netdev_ops = &be_netdev_ops;
 
-	SET_ETHTOOL_OPS(netdev, &be_ethtool_ops);
+	netdev->ethtool_ops = &be_ethtool_ops;
 }
 
 static void be_unmap_pci_bars(struct be_adapter *adapter)
@@ -4870,7 +4969,7 @@ static void be_shutdown(struct pci_dev *pdev)
 }
 
 static pci_ers_result_t be_eeh_err_detected(struct pci_dev *pdev,
-				pci_channel_state_t state)
+					    pci_channel_state_t state)
 {
 	struct be_adapter *adapter = pci_get_drvdata(pdev);
 	struct net_device *netdev =  adapter->netdev;
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 8b70ca7e342..f3658bdb64c 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -769,11 +769,6 @@ static int ethoc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return phy_mii_ioctl(phy, ifr, cmd);
 }
 
-static int ethoc_config(struct net_device *dev, struct ifmap *map)
-{
-	return -ENOSYS;
-}
-
 static void ethoc_do_set_mac_address(struct net_device *dev)
 {
 	struct ethoc *priv = netdev_priv(dev);
@@ -995,7 +990,6 @@ static const struct net_device_ops ethoc_netdev_ops = {
 	.ndo_open = ethoc_open,
 	.ndo_stop = ethoc_stop,
 	.ndo_do_ioctl = ethoc_ioctl,
-	.ndo_set_config = ethoc_config,
 	.ndo_set_mac_address = ethoc_set_mac_address,
 	.ndo_set_rx_mode = ethoc_set_multicast_list,
 	.ndo_change_mtu = ethoc_change_mtu,
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 68069eabc4f..c77fa4a6984 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -1210,7 +1210,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 
 	SET_NETDEV_DEV(netdev, &pdev->dev);
 
-	SET_ETHTOOL_OPS(netdev, &ftgmac100_ethtool_ops);
+	netdev->ethtool_ops = &ftgmac100_ethtool_ops;
 	netdev->netdev_ops = &ftgmac100_netdev_ops;
 	netdev->features = NETIF_F_IP_CSUM | NETIF_F_GRO;
 
diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index 8be5b40c0a1..4ff1adc6bfc 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -1085,7 +1085,7 @@ static int ftmac100_probe(struct platform_device *pdev)
 	}
 
 	SET_NETDEV_DEV(netdev, &pdev->dev);
-	SET_ETHTOOL_OPS(netdev, &ftmac100_ethtool_ops);
+	netdev->ethtool_ops = &ftmac100_ethtool_ops;
 	netdev->netdev_ops = &ftmac100_netdev_ops;
 
 	platform_set_drvdata(pdev, netdev);
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index 6048dc8604e..270308315d4 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -67,6 +67,7 @@ config FSL_XGMAC_MDIO
 	tristate "Freescale XGMAC MDIO"
 	depends on FSL_SOC
 	select PHYLIB
+	select OF_MDIO
 	---help---
 	  This driver supports the MDIO bus on the Fman 10G Ethernet MACs.
 
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 3b8d6d19ff0..671d080105a 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -221,7 +221,7 @@ struct bufdesc_ex {
 #define BD_ENET_TX_RCMASK       ((ushort)0x003c)
 #define BD_ENET_TX_UN           ((ushort)0x0002)
 #define BD_ENET_TX_CSL          ((ushort)0x0001)
-#define BD_ENET_TX_STATS        ((ushort)0x03ff)        /* All status bits */
+#define BD_ENET_TX_STATS        ((ushort)0x0fff)        /* All status bits */
 
 /*enhanced buffer descriptor control/status used by Ethernet transmit*/
 #define BD_ENET_TX_INT          0x40000000
@@ -246,8 +246,8 @@ struct bufdesc_ex {
 #define RX_RING_SIZE		(FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
 #define FEC_ENET_TX_FRSIZE	2048
 #define FEC_ENET_TX_FRPPG	(PAGE_SIZE / FEC_ENET_TX_FRSIZE)
-#define TX_RING_SIZE		16	/* Must be power of two */
-#define TX_RING_MOD_MASK	15	/*   for this to work */
+#define TX_RING_SIZE		512	/* Must be power of two */
+#define TX_RING_MOD_MASK	511	/*   for this to work */
 
 #define BD_ENET_RX_INT          0x00800000
 #define BD_ENET_RX_PTP          ((ushort)0x0400)
@@ -296,8 +296,15 @@ struct fec_enet_private {
 	/* The ring entries to be free()ed */
 	struct bufdesc	*dirty_tx;
 
+	unsigned short bufdesc_size;
 	unsigned short tx_ring_size;
 	unsigned short rx_ring_size;
+	unsigned short tx_stop_threshold;
+	unsigned short tx_wake_threshold;
+
+	/* Software TSO */
+	char *tso_hdrs;
+	dma_addr_t tso_hdrs_dma;
 
 	struct	platform_device *pdev;
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8d69e439f0c..77037fd377b 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -36,6 +36,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <net/ip.h>
+#include <net/tso.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/icmp.h>
@@ -54,6 +55,7 @@
 #include <linux/of_net.h>
 #include <linux/regulator/consumer.h>
 #include <linux/if_vlan.h>
+#include <linux/pinctrl/consumer.h>
 
 #include <asm/cacheflush.h>
 
@@ -172,10 +174,6 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #endif
 #endif /* CONFIG_M5272 */
 
-#if (((RX_RING_SIZE + TX_RING_SIZE) * 32) > PAGE_SIZE)
-#error "FEC: descriptor ring size constants too large"
-#endif
-
 /* Interrupt events/masks. */
 #define FEC_ENET_HBERR	((uint)0x80000000)	/* Heartbeat error */
 #define FEC_ENET_BABR	((uint)0x40000000)	/* Babbling receiver */
@@ -231,6 +229,15 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #define FEC_PAUSE_FLAG_AUTONEG	0x1
 #define FEC_PAUSE_FLAG_ENABLE	0x2
 
+#define TSO_HEADER_SIZE		128
+/* Max number of allowed TCP segments for software TSO */
+#define FEC_MAX_TSO_SEGS	100
+#define FEC_MAX_SKB_DESCS	(FEC_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
+
+#define IS_TSO_HEADER(txq, addr) \
+	((addr >= txq->tso_hdrs_dma) && \
+	(addr < txq->tso_hdrs_dma + txq->tx_ring_size * TSO_HEADER_SIZE))
+
 static int mii_cnt;
 
 static inline
@@ -286,6 +293,22 @@ struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp, struct fec_enet_priva
 		return (new_bd < base) ? (new_bd + ring_size) : new_bd;
 }
 
+static int fec_enet_get_bd_index(struct bufdesc *base, struct bufdesc *bdp,
+				struct fec_enet_private *fep)
+{
+	return ((const char *)bdp - (const char *)base) / fep->bufdesc_size;
+}
+
+static int fec_enet_get_free_txdesc_num(struct fec_enet_private *fep)
+{
+	int entries;
+
+	entries = ((const char *)fep->dirty_tx -
+			(const char *)fep->cur_tx) / fep->bufdesc_size - 1;
+
+	return entries > 0 ? entries : entries + fep->tx_ring_size;
+}
+
 static void *swap_buffer(void *bufaddr, int len)
 {
 	int i;
@@ -297,6 +320,11 @@ static void *swap_buffer(void *bufaddr, int len)
 	return bufaddr;
 }
 
+static inline bool is_ipv4_pkt(struct sk_buff *skb)
+{
+	return skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->version == 4;
+}
+
 static int
 fec_enet_clear_csum(struct sk_buff *skb, struct net_device *ndev)
 {
@@ -307,33 +335,134 @@ fec_enet_clear_csum(struct sk_buff *skb, struct net_device *ndev)
 	if (unlikely(skb_cow_head(skb, 0)))
 		return -1;
 
+	if (is_ipv4_pkt(skb))
+		ip_hdr(skb)->check = 0;
 	*(__sum16 *)(skb->head + skb->csum_start + skb->csum_offset) = 0;
 
 	return 0;
 }
 
-static netdev_tx_t
-fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static void
+fec_enet_submit_work(struct bufdesc *bdp, struct fec_enet_private *fep)
+{
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+	struct bufdesc *bdp_pre;
+
+	bdp_pre = fec_enet_get_prevdesc(bdp, fep);
+	if ((id_entry->driver_data & FEC_QUIRK_ERR006358) &&
+	    !(bdp_pre->cbd_sc & BD_ENET_TX_READY)) {
+		fep->delay_work.trig_tx = true;
+		schedule_delayed_work(&(fep->delay_work.delay_work),
+					msecs_to_jiffies(1));
+	}
+}
+
+static int
+fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	const struct platform_device_id *id_entry =
 				platform_get_device_id(fep->pdev);
-	struct bufdesc *bdp, *bdp_pre;
-	void *bufaddr;
-	unsigned short	status;
+	struct bufdesc *bdp = fep->cur_tx;
+	struct bufdesc_ex *ebdp;
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	int frag, frag_len;
+	unsigned short status;
+	unsigned int estatus = 0;
+	skb_frag_t *this_frag;
 	unsigned int index;
+	void *bufaddr;
+	int i;
 
-	/* Fill in a Tx ring entry */
+	for (frag = 0; frag < nr_frags; frag++) {
+		this_frag = &skb_shinfo(skb)->frags[frag];
+		bdp = fec_enet_get_nextdesc(bdp, fep);
+		ebdp = (struct bufdesc_ex *)bdp;
+
+		status = bdp->cbd_sc;
+		status &= ~BD_ENET_TX_STATS;
+		status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
+		frag_len = skb_shinfo(skb)->frags[frag].size;
+
+		/* Handle the last BD specially */
+		if (frag == nr_frags - 1) {
+			status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
+			if (fep->bufdesc_ex) {
+				estatus |= BD_ENET_TX_INT;
+				if (unlikely(skb_shinfo(skb)->tx_flags &
+					SKBTX_HW_TSTAMP && fep->hwts_tx_en))
+					estatus |= BD_ENET_TX_TS;
+			}
+		}
+
+		if (fep->bufdesc_ex) {
+			if (skb->ip_summed == CHECKSUM_PARTIAL)
+				estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
+			ebdp->cbd_bdu = 0;
+			ebdp->cbd_esc = estatus;
+		}
+
+		bufaddr = page_address(this_frag->page.p) + this_frag->page_offset;
+
+		index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+		if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
+			id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
+			memcpy(fep->tx_bounce[index], bufaddr, frag_len);
+			bufaddr = fep->tx_bounce[index];
+
+			if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
+				swap_buffer(bufaddr, frag_len);
+		}
+
+		bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, bufaddr,
+						frag_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+			dev_kfree_skb_any(skb);
+			if (net_ratelimit())
+				netdev_err(ndev, "Tx DMA memory map failed\n");
+			goto dma_mapping_error;
+		}
+
+		bdp->cbd_datlen = frag_len;
+		bdp->cbd_sc = status;
+	}
+
+	fep->cur_tx = bdp;
+
+	return 0;
+
+dma_mapping_error:
 	bdp = fep->cur_tx;
+	for (i = 0; i < frag; i++) {
+		bdp = fec_enet_get_nextdesc(bdp, fep);
+		dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
+				bdp->cbd_datlen, DMA_TO_DEVICE);
+	}
+	return NETDEV_TX_OK;
+}
 
-	status = bdp->cbd_sc;
+static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	struct bufdesc *bdp, *last_bdp;
+	void *bufaddr;
+	unsigned short status;
+	unsigned short buflen;
+	unsigned int estatus = 0;
+	unsigned int index;
+	int entries_free;
+	int ret;
 
-	if (status & BD_ENET_TX_READY) {
-		/* Ooops.  All transmit buffers are full.  Bail out.
-		 * This should not happen, since ndev->tbusy should be set.
-		 */
-		netdev_err(ndev, "tx queue full!\n");
-		return NETDEV_TX_BUSY;
+	entries_free = fec_enet_get_free_txdesc_num(fep);
+	if (entries_free < MAX_SKB_FRAGS + 1) {
+		dev_kfree_skb_any(skb);
+		if (net_ratelimit())
+			netdev_err(ndev, "NOT enough BD for SG!\n");
+		return NETDEV_TX_OK;
 	}
 
 	/* Protocol checksum off-load for TCP and UDP. */
@@ -342,102 +471,300 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		return NETDEV_TX_OK;
 	}
 
-	/* Clear all of the status flags */
+	/* Fill in a Tx ring entry */
+	bdp = fep->cur_tx;
+	status = bdp->cbd_sc;
 	status &= ~BD_ENET_TX_STATS;
 
 	/* Set buffer length and buffer pointer */
 	bufaddr = skb->data;
-	bdp->cbd_datlen = skb->len;
+	buflen = skb_headlen(skb);
 
-	/*
-	 * On some FEC implementations data must be aligned on
-	 * 4-byte boundaries. Use bounce buffers to copy data
-	 * and get it aligned. Ugh.
-	 */
-	if (fep->bufdesc_ex)
-		index = (struct bufdesc_ex *)bdp -
-			(struct bufdesc_ex *)fep->tx_bd_base;
-	else
-		index = bdp - fep->tx_bd_base;
-
-	if (((unsigned long) bufaddr) & FEC_ALIGNMENT) {
-		memcpy(fep->tx_bounce[index], skb->data, skb->len);
+	index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+	if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
+		id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
+		memcpy(fep->tx_bounce[index], skb->data, buflen);
 		bufaddr = fep->tx_bounce[index];
-	}
 
-	/*
-	 * Some design made an incorrect assumption on endian mode of
-	 * the system that it's running on. As the result, driver has to
-	 * swap every frame going to and coming from the controller.
-	 */
-	if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
-		swap_buffer(bufaddr, skb->len);
-
-	/* Save skb pointer */
-	fep->tx_skbuff[index] = skb;
+		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
+			swap_buffer(bufaddr, buflen);
+	}
 
 	/* Push the data cache so the CPM does not get stale memory
 	 * data.
 	 */
 	bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, bufaddr,
-			skb->len, DMA_TO_DEVICE);
+					buflen, DMA_TO_DEVICE);
 	if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
-		bdp->cbd_bufaddr = 0;
-		fep->tx_skbuff[index] = NULL;
 		dev_kfree_skb_any(skb);
 		if (net_ratelimit())
 			netdev_err(ndev, "Tx DMA memory map failed\n");
 		return NETDEV_TX_OK;
 	}
 
+	if (nr_frags) {
+		ret = fec_enet_txq_submit_frag_skb(skb, ndev);
+		if (ret)
+			return ret;
+	} else {
+		status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
+		if (fep->bufdesc_ex) {
+			estatus = BD_ENET_TX_INT;
+			if (unlikely(skb_shinfo(skb)->tx_flags &
+				SKBTX_HW_TSTAMP && fep->hwts_tx_en))
+				estatus |= BD_ENET_TX_TS;
+		}
+	}
+
 	if (fep->bufdesc_ex) {
 
 		struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
-		ebdp->cbd_bdu = 0;
+
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
-			fep->hwts_tx_en)) {
-			ebdp->cbd_esc = (BD_ENET_TX_TS | BD_ENET_TX_INT);
+			fep->hwts_tx_en))
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-		} else {
-			ebdp->cbd_esc = BD_ENET_TX_INT;
 
-			/* Enable protocol checksum flags
-			 * We do not bother with the IP Checksum bits as they
-			 * are done by the kernel
-			 */
-			if (skb->ip_summed == CHECKSUM_PARTIAL)
-				ebdp->cbd_esc |= BD_ENET_TX_PINS;
-		}
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
+
+		ebdp->cbd_bdu = 0;
+		ebdp->cbd_esc = estatus;
 	}
 
+	last_bdp = fep->cur_tx;
+	index = fec_enet_get_bd_index(fep->tx_bd_base, last_bdp, fep);
+	/* Save skb pointer */
+	fep->tx_skbuff[index] = skb;
+
+	bdp->cbd_datlen = buflen;
+
 	/* Send it on its way.  Tell FEC it's ready, interrupt when done,
 	 * it's the last BD of the frame, and to put the CRC on the end.
 	 */
-	status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR
-			| BD_ENET_TX_LAST | BD_ENET_TX_TC);
+	status |= (BD_ENET_TX_READY | BD_ENET_TX_TC);
 	bdp->cbd_sc = status;
 
-	bdp_pre = fec_enet_get_prevdesc(bdp, fep);
-	if ((id_entry->driver_data & FEC_QUIRK_ERR006358) &&
-	    !(bdp_pre->cbd_sc & BD_ENET_TX_READY)) {
-		fep->delay_work.trig_tx = true;
-		schedule_delayed_work(&(fep->delay_work.delay_work),
-					msecs_to_jiffies(1));
-	}
+	fec_enet_submit_work(bdp, fep);
 
 	/* If this was the last BD in the ring, start at the beginning again. */
-	bdp = fec_enet_get_nextdesc(bdp, fep);
+	bdp = fec_enet_get_nextdesc(last_bdp, fep);
 
 	skb_tx_timestamp(skb);
 
 	fep->cur_tx = bdp;
 
-	if (fep->cur_tx == fep->dirty_tx)
-		netif_stop_queue(ndev);
+	/* Trigger transmission start */
+	writel(0, fep->hwp + FEC_X_DES_ACTIVE);
+
+	return 0;
+}
+
+static int
+fec_enet_txq_put_data_tso(struct sk_buff *skb, struct net_device *ndev,
+			struct bufdesc *bdp, int index, char *data,
+			int size, bool last_tcp, bool is_last)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+	struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
+	unsigned short status;
+	unsigned int estatus = 0;
+
+	status = bdp->cbd_sc;
+	status &= ~BD_ENET_TX_STATS;
+
+	status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
+	bdp->cbd_datlen = size;
+
+	if (((unsigned long) data) & FEC_ALIGNMENT ||
+		id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
+		memcpy(fep->tx_bounce[index], data, size);
+		data = fep->tx_bounce[index];
+
+		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
+			swap_buffer(data, size);
+	}
+
+	bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, data,
+					size, DMA_TO_DEVICE);
+	if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+		dev_kfree_skb_any(skb);
+		if (net_ratelimit())
+			netdev_err(ndev, "Tx DMA memory map failed\n");
+		return NETDEV_TX_BUSY;
+	}
+
+	if (fep->bufdesc_ex) {
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
+		ebdp->cbd_bdu = 0;
+		ebdp->cbd_esc = estatus;
+	}
+
+	/* Handle the last BD specially */
+	if (last_tcp)
+		status |= (BD_ENET_TX_LAST | BD_ENET_TX_TC);
+	if (is_last) {
+		status |= BD_ENET_TX_INTR;
+		if (fep->bufdesc_ex)
+			ebdp->cbd_esc |= BD_ENET_TX_INT;
+	}
+
+	bdp->cbd_sc = status;
+
+	return 0;
+}
+
+static int
+fec_enet_txq_put_hdr_tso(struct sk_buff *skb, struct net_device *ndev,
+			struct bufdesc *bdp, int index)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
+	void *bufaddr;
+	unsigned long dmabuf;
+	unsigned short status;
+	unsigned int estatus = 0;
+
+	status = bdp->cbd_sc;
+	status &= ~BD_ENET_TX_STATS;
+	status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
+
+	bufaddr = fep->tso_hdrs + index * TSO_HEADER_SIZE;
+	dmabuf = fep->tso_hdrs_dma + index * TSO_HEADER_SIZE;
+	if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
+		id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
+		memcpy(fep->tx_bounce[index], skb->data, hdr_len);
+		bufaddr = fep->tx_bounce[index];
+
+		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
+			swap_buffer(bufaddr, hdr_len);
+
+		dmabuf = dma_map_single(&fep->pdev->dev, bufaddr,
+					hdr_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(&fep->pdev->dev, dmabuf)) {
+			dev_kfree_skb_any(skb);
+			if (net_ratelimit())
+				netdev_err(ndev, "Tx DMA memory map failed\n");
+			return NETDEV_TX_BUSY;
+		}
+	}
+
+	bdp->cbd_bufaddr = dmabuf;
+	bdp->cbd_datlen = hdr_len;
+
+	if (fep->bufdesc_ex) {
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
+		ebdp->cbd_bdu = 0;
+		ebdp->cbd_esc = estatus;
+	}
+
+	bdp->cbd_sc = status;
+
+	return 0;
+}
+
+static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int total_len, data_left;
+	struct bufdesc *bdp = fep->cur_tx;
+	struct tso_t tso;
+	unsigned int index = 0;
+	int ret;
+
+	if (tso_count_descs(skb) >= fec_enet_get_free_txdesc_num(fep)) {
+		dev_kfree_skb_any(skb);
+		if (net_ratelimit())
+			netdev_err(ndev, "NOT enough BD for TSO!\n");
+		return NETDEV_TX_OK;
+	}
+
+	/* Protocol checksum off-load for TCP and UDP. */
+	if (fec_enet_clear_csum(skb, ndev)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	/* Initialize the TSO handler, and prepare the first payload */
+	tso_start(skb, &tso);
+
+	total_len = skb->len - hdr_len;
+	while (total_len > 0) {
+		char *hdr;
+
+		index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+		data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len);
+		total_len -= data_left;
+
+		/* prepare packet headers: MAC + IP + TCP */
+		hdr = fep->tso_hdrs + index * TSO_HEADER_SIZE;
+		tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0);
+		ret = fec_enet_txq_put_hdr_tso(skb, ndev, bdp, index);
+		if (ret)
+			goto err_release;
+
+		while (data_left > 0) {
+			int size;
+
+			size = min_t(int, tso.size, data_left);
+			bdp = fec_enet_get_nextdesc(bdp, fep);
+			index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+			ret = fec_enet_txq_put_data_tso(skb, ndev, bdp, index, tso.data,
+							size, size == data_left,
+							total_len == 0);
+			if (ret)
+				goto err_release;
+
+			data_left -= size;
+			tso_build_data(skb, &tso, size);
+		}
+
+		bdp = fec_enet_get_nextdesc(bdp, fep);
+	}
+
+	/* Save skb pointer */
+	fep->tx_skbuff[index] = skb;
+
+	fec_enet_submit_work(bdp, fep);
+
+	skb_tx_timestamp(skb);
+	fep->cur_tx = bdp;
 
 	/* Trigger transmission start */
 	writel(0, fep->hwp + FEC_X_DES_ACTIVE);
 
+	return 0;
+
+err_release:
+	/* TODO: Release all used data descriptors for TSO */
+	return ret;
+}
+
+static netdev_tx_t
+fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	int entries_free;
+	int ret;
+
+	if (skb_is_gso(skb))
+		ret = fec_enet_txq_submit_tso(skb, ndev);
+	else
+		ret = fec_enet_txq_submit_skb(skb, ndev);
+	if (ret)
+		return ret;
+
+	entries_free = fec_enet_get_free_txdesc_num(fep);
+	if (entries_free <= fep->tx_stop_threshold)
+		netif_stop_queue(ndev);
+
 	return NETDEV_TX_OK;
 }
 
@@ -756,6 +1083,7 @@ fec_enet_tx(struct net_device *ndev)
 	unsigned short status;
 	struct	sk_buff	*skb;
 	int	index = 0;
+	int	entries_free;
 
 	fep = netdev_priv(ndev);
 	bdp = fep->dirty_tx;
@@ -769,16 +1097,17 @@ fec_enet_tx(struct net_device *ndev)
 		if (bdp == fep->cur_tx)
 			break;
 
-		if (fep->bufdesc_ex)
-			index = (struct bufdesc_ex *)bdp -
-				(struct bufdesc_ex *)fep->tx_bd_base;
-		else
-			index = bdp - fep->tx_bd_base;
+		index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
 
 		skb = fep->tx_skbuff[index];
-		dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, skb->len,
-				DMA_TO_DEVICE);
+		if (!IS_TSO_HEADER(fep, bdp->cbd_bufaddr))
+			dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
+					bdp->cbd_datlen, DMA_TO_DEVICE);
 		bdp->cbd_bufaddr = 0;
+		if (!skb) {
+			bdp = fec_enet_get_nextdesc(bdp, fep);
+			continue;
+		}
 
 		/* Check for errors. */
 		if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC |
@@ -797,7 +1126,7 @@ fec_enet_tx(struct net_device *ndev)
 				ndev->stats.tx_carrier_errors++;
 		} else {
 			ndev->stats.tx_packets++;
-			ndev->stats.tx_bytes += bdp->cbd_datlen;
+			ndev->stats.tx_bytes += skb->len;
 		}
 
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) &&
@@ -834,15 +1163,15 @@ fec_enet_tx(struct net_device *ndev)
 
 		/* Since we have freed up a buffer, the ring is no longer full
 		 */
-		if (fep->dirty_tx != fep->cur_tx) {
-			if (netif_queue_stopped(ndev))
+		if (netif_queue_stopped(ndev)) {
+			entries_free = fec_enet_get_free_txdesc_num(fep);
+			if (entries_free >= fep->tx_wake_threshold)
 				netif_wake_queue(ndev);
 		}
 	}
 	return;
 }
 
-
 /* During a receive, the cur_rx points to the current incoming buffer.
  * When we update through the ring, if the next incoming buffer has
  * not been given to the system, we just set the empty indicator,
@@ -920,11 +1249,7 @@ fec_enet_rx(struct net_device *ndev, int budget)
 		pkt_len = bdp->cbd_datlen;
 		ndev->stats.rx_bytes += pkt_len;
 
-		if (fep->bufdesc_ex)
-			index = (struct bufdesc_ex *)bdp -
-				(struct bufdesc_ex *)fep->rx_bd_base;
-		else
-			index = bdp - fep->rx_bd_base;
+		index = fec_enet_get_bd_index(fep->rx_bd_base, bdp, fep);
 		data = fep->rx_skbuff[index]->data;
 		dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr,
 					FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
@@ -1255,6 +1580,49 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	return 0;
 }
 
+static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	int ret;
+
+	if (enable) {
+		ret = clk_prepare_enable(fep->clk_ahb);
+		if (ret)
+			return ret;
+		ret = clk_prepare_enable(fep->clk_ipg);
+		if (ret)
+			goto failed_clk_ipg;
+		if (fep->clk_enet_out) {
+			ret = clk_prepare_enable(fep->clk_enet_out);
+			if (ret)
+				goto failed_clk_enet_out;
+		}
+		if (fep->clk_ptp) {
+			ret = clk_prepare_enable(fep->clk_ptp);
+			if (ret)
+				goto failed_clk_ptp;
+		}
+	} else {
+		clk_disable_unprepare(fep->clk_ahb);
+		clk_disable_unprepare(fep->clk_ipg);
+		if (fep->clk_enet_out)
+			clk_disable_unprepare(fep->clk_enet_out);
+		if (fep->clk_ptp)
+			clk_disable_unprepare(fep->clk_ptp);
+	}
+
+	return 0;
+failed_clk_ptp:
+	if (fep->clk_enet_out)
+		clk_disable_unprepare(fep->clk_enet_out);
+failed_clk_enet_out:
+		clk_disable_unprepare(fep->clk_ipg);
+failed_clk_ipg:
+		clk_disable_unprepare(fep->clk_ahb);
+
+	return ret;
+}
+
 static int fec_enet_mii_probe(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
@@ -1364,7 +1732,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	 * Reference Manual has an error on this, and gets fixed on i.MX6Q
 	 * document.
 	 */
-	fep->phy_speed = DIV_ROUND_UP(clk_get_rate(fep->clk_ahb), 5000000);
+	fep->phy_speed = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), 5000000);
 	if (id_entry->driver_data & FEC_QUIRK_ENET_MAC)
 		fep->phy_speed--;
 	fep->phy_speed <<= 1;
@@ -1773,6 +2141,11 @@ fec_enet_open(struct net_device *ndev)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int ret;
 
+	pinctrl_pm_select_default_state(&fep->pdev->dev);
+	ret = fec_enet_clk_enable(ndev, true);
+	if (ret)
+		return ret;
+
 	/* I should reset the ring buffers here, but I don't yet know
 	 * a simple way to do that.
 	 */
@@ -1811,6 +2184,8 @@ fec_enet_close(struct net_device *ndev)
 		phy_disconnect(fep->phy_dev);
 	}
 
+	fec_enet_clk_enable(ndev, false);
+	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 	fec_enet_free_buffers(ndev);
 
 	return 0;
@@ -1988,13 +2363,35 @@ static int fec_enet_init(struct net_device *ndev)
 	const struct platform_device_id *id_entry =
 				platform_get_device_id(fep->pdev);
 	struct bufdesc *cbd_base;
+	int bd_size;
+
+	/* init the tx & rx ring size */
+	fep->tx_ring_size = TX_RING_SIZE;
+	fep->rx_ring_size = RX_RING_SIZE;
+
+	fep->tx_stop_threshold = FEC_MAX_SKB_DESCS;
+	fep->tx_wake_threshold = (fep->tx_ring_size - fep->tx_stop_threshold) / 2;
+
+	if (fep->bufdesc_ex)
+		fep->bufdesc_size = sizeof(struct bufdesc_ex);
+	else
+		fep->bufdesc_size = sizeof(struct bufdesc);
+	bd_size = (fep->tx_ring_size + fep->rx_ring_size) *
+			fep->bufdesc_size;
 
 	/* Allocate memory for buffer descriptors. */
-	cbd_base = dma_alloc_coherent(NULL, PAGE_SIZE, &fep->bd_dma,
+	cbd_base = dma_alloc_coherent(NULL, bd_size, &fep->bd_dma,
 				      GFP_KERNEL);
 	if (!cbd_base)
 		return -ENOMEM;
 
+	fep->tso_hdrs = dma_alloc_coherent(NULL, fep->tx_ring_size * TSO_HEADER_SIZE,
+						&fep->tso_hdrs_dma, GFP_KERNEL);
+	if (!fep->tso_hdrs) {
+		dma_free_coherent(NULL, bd_size, cbd_base, fep->bd_dma);
+		return -ENOMEM;
+	}
+
 	memset(cbd_base, 0, PAGE_SIZE);
 
 	fep->netdev = ndev;
@@ -2004,10 +2401,6 @@ static int fec_enet_init(struct net_device *ndev)
 	/* make sure MAC we just acquired is programmed into the hw */
 	fec_set_mac_address(ndev, NULL);
 
-	/* init the tx & rx ring size */
-	fep->tx_ring_size = TX_RING_SIZE;
-	fep->rx_ring_size = RX_RING_SIZE;
-
 	/* Set receive and transmit descriptor base. */
 	fep->rx_bd_base = cbd_base;
 	if (fep->bufdesc_ex)
@@ -2024,21 +2417,21 @@ static int fec_enet_init(struct net_device *ndev)
 	writel(FEC_RX_DISABLED_IMASK, fep->hwp + FEC_IMASK);
 	netif_napi_add(ndev, &fep->napi, fec_enet_rx_napi, NAPI_POLL_WEIGHT);
 
-	if (id_entry->driver_data & FEC_QUIRK_HAS_VLAN) {
+	if (id_entry->driver_data & FEC_QUIRK_HAS_VLAN)
 		/* enable hw VLAN support */
 		ndev->features |= NETIF_F_HW_VLAN_CTAG_RX;
-		ndev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
-	}
 
 	if (id_entry->driver_data & FEC_QUIRK_HAS_CSUM) {
+		ndev->gso_max_segs = FEC_MAX_TSO_SEGS;
+
 		/* enable hw accelerator */
 		ndev->features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
-				| NETIF_F_RXCSUM);
-		ndev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
-				| NETIF_F_RXCSUM);
+				| NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO);
 		fep->csum_flags |= FLAG_RX_CSUM_ENABLED;
 	}
 
+	ndev->hw_features = ndev->features;
+
 	fec_restart(ndev, 0);
 
 	return 0;
@@ -2114,6 +2507,9 @@ fec_probe(struct platform_device *pdev)
 		fep->pause_flag |= FEC_PAUSE_FLAG_AUTONEG;
 #endif
 
+	/* Select default pin state */
+	pinctrl_pm_select_default_state(&pdev->dev);
+
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	fep->hwp = devm_ioremap_resource(&pdev->dev, r);
 	if (IS_ERR(fep->hwp)) {
@@ -2164,26 +2560,10 @@ fec_probe(struct platform_device *pdev)
 		fep->bufdesc_ex = 0;
 	}
 
-	ret = clk_prepare_enable(fep->clk_ahb);
+	ret = fec_enet_clk_enable(ndev, true);
 	if (ret)
 		goto failed_clk;
 
-	ret = clk_prepare_enable(fep->clk_ipg);
-	if (ret)
-		goto failed_clk_ipg;
-
-	if (fep->clk_enet_out) {
-		ret = clk_prepare_enable(fep->clk_enet_out);
-		if (ret)
-			goto failed_clk_enet_out;
-	}
-
-	if (fep->clk_ptp) {
-		ret = clk_prepare_enable(fep->clk_ptp);
-		if (ret)
-			goto failed_clk_ptp;
-	}
-
 	fep->reg_phy = devm_regulator_get(&pdev->dev, "phy");
 	if (!IS_ERR(fep->reg_phy)) {
 		ret = regulator_enable(fep->reg_phy);
@@ -2225,6 +2605,8 @@ fec_probe(struct platform_device *pdev)
 
 	/* Carrier starts down, phylib will bring it up */
 	netif_carrier_off(ndev);
+	fec_enet_clk_enable(ndev, false);
+	pinctrl_pm_select_sleep_state(&pdev->dev);
 
 	ret = register_netdev(ndev);
 	if (ret)
@@ -2244,15 +2626,7 @@ failed_init:
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
 failed_regulator:
-	if (fep->clk_ptp)
-		clk_disable_unprepare(fep->clk_ptp);
-failed_clk_ptp:
-	if (fep->clk_enet_out)
-		clk_disable_unprepare(fep->clk_enet_out);
-failed_clk_enet_out:
-	clk_disable_unprepare(fep->clk_ipg);
-failed_clk_ipg:
-	clk_disable_unprepare(fep->clk_ahb);
+	fec_enet_clk_enable(ndev, false);
 failed_clk:
 failed_ioremap:
 	free_netdev(ndev);
@@ -2272,14 +2646,9 @@ fec_drv_remove(struct platform_device *pdev)
 	del_timer_sync(&fep->time_keep);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
-	if (fep->clk_ptp)
-		clk_disable_unprepare(fep->clk_ptp);
 	if (fep->ptp_clock)
 		ptp_clock_unregister(fep->ptp_clock);
-	if (fep->clk_enet_out)
-		clk_disable_unprepare(fep->clk_enet_out);
-	clk_disable_unprepare(fep->clk_ipg);
-	clk_disable_unprepare(fep->clk_ahb);
+	fec_enet_clk_enable(ndev, false);
 	free_netdev(ndev);
 
 	return 0;
@@ -2296,12 +2665,8 @@ fec_suspend(struct device *dev)
 		fec_stop(ndev);
 		netif_device_detach(ndev);
 	}
-	if (fep->clk_ptp)
-		clk_disable_unprepare(fep->clk_ptp);
-	if (fep->clk_enet_out)
-		clk_disable_unprepare(fep->clk_enet_out);
-	clk_disable_unprepare(fep->clk_ipg);
-	clk_disable_unprepare(fep->clk_ahb);
+	fec_enet_clk_enable(ndev, false);
+	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
@@ -2322,25 +2687,10 @@ fec_resume(struct device *dev)
 			return ret;
 	}
 
-	ret = clk_prepare_enable(fep->clk_ahb);
+	pinctrl_pm_select_default_state(&fep->pdev->dev);
+	ret = fec_enet_clk_enable(ndev, true);
 	if (ret)
-		goto failed_clk_ahb;
-
-	ret = clk_prepare_enable(fep->clk_ipg);
-	if (ret)
-		goto failed_clk_ipg;
-
-	if (fep->clk_enet_out) {
-		ret = clk_prepare_enable(fep->clk_enet_out);
-		if (ret)
-			goto failed_clk_enet_out;
-	}
-
-	if (fep->clk_ptp) {
-		ret = clk_prepare_enable(fep->clk_ptp);
-		if (ret)
-			goto failed_clk_ptp;
-	}
+		goto failed_clk;
 
 	if (netif_running(ndev)) {
 		fec_restart(ndev, fep->full_duplex);
@@ -2349,14 +2699,7 @@ fec_resume(struct device *dev)
 
 	return 0;
 
-failed_clk_ptp:
-	if (fep->clk_enet_out)
-		clk_disable_unprepare(fep->clk_enet_out);
-failed_clk_enet_out:
-	clk_disable_unprepare(fep->clk_ipg);
-failed_clk_ipg:
-	clk_disable_unprepare(fep->clk_ahb);
-failed_clk_ahb:
+failed_clk:
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
 	return ret;
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index dc80db41d6b..cfaf17b70f3 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -792,10 +792,6 @@ static int fs_init_phy(struct net_device *dev)
 	phydev = of_phy_connect(dev, fep->fpi->phy_node, &fs_adjust_link, 0,
 				iface);
 	if (!phydev) {
-		phydev = of_phy_connect_fixed_link(dev, &fs_adjust_link,
-						   iface);
-	}
-	if (!phydev) {
 		dev_err(&dev->dev, "Could not attach to PHY\n");
 		return -ENODEV;
 	}
@@ -1029,9 +1025,16 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	fpi->use_napi = 1;
 	fpi->napi_weight = 17;
 	fpi->phy_node = of_parse_phandle(ofdev->dev.of_node, "phy-handle", 0);
-	if ((!fpi->phy_node) && (!of_get_property(ofdev->dev.of_node, "fixed-link",
-						  NULL)))
-		goto out_free_fpi;
+	if (!fpi->phy_node && of_phy_is_fixed_link(ofdev->dev.of_node)) {
+		err = of_phy_register_fixed_link(ofdev->dev.of_node);
+		if (err)
+			goto out_free_fpi;
+
+		/* In the case of a fixed PHY, the DT node associated
+		 * to the PHY is the Ethernet MAC DT node.
+		 */
+		fpi->phy_node = ofdev->dev.of_node;
+	}
 
 	if (of_device_is_compatible(ofdev->dev.of_node, "fsl,mpc5125-fec")) {
 		phy_connection_type = of_get_property(ofdev->dev.of_node,
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index ee6ddbd4f25..a6cf40e62f3 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -889,6 +889,17 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 
 	priv->phy_node = of_parse_phandle(np, "phy-handle", 0);
 
+	/* In the case of a fixed PHY, the DT node associated
+	 * to the PHY is the Ethernet MAC DT node.
+	 */
+	if (of_phy_is_fixed_link(np)) {
+		err = of_phy_register_fixed_link(np);
+		if (err)
+			goto err_grp_init;
+
+		priv->phy_node = np;
+	}
+
 	/* Find the TBI PHY.  If it's not there, we don't support SGMII */
 	priv->tbi_node = of_parse_phandle(np, "tbi-handle", 0);
 
@@ -1231,7 +1242,7 @@ static void gfar_hw_init(struct gfar_private *priv)
 		gfar_write_isrg(priv);
 }
 
-static void __init gfar_init_addr_hash_table(struct gfar_private *priv)
+static void gfar_init_addr_hash_table(struct gfar_private *priv)
 {
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
 
@@ -1373,6 +1384,9 @@ static int gfar_probe(struct platform_device *ofdev)
 
 	gfar_hw_init(priv);
 
+	/* Carrier starts down, phylib will bring it up */
+	netif_carrier_off(dev);
+
 	err = register_netdev(dev);
 
 	if (err) {
@@ -1380,9 +1394,6 @@ static int gfar_probe(struct platform_device *ofdev)
 		goto register_fail;
 	}
 
-	/* Carrier starts down, phylib will bring it up */
-	netif_carrier_off(dev);
-
 	device_init_wakeup(&dev->dev,
 			   priv->device_flags &
 			   FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
@@ -1660,9 +1671,6 @@ static int init_phy(struct net_device *dev)
 
 	priv->phydev = of_phy_connect(dev, priv->phy_node, &adjust_link, 0,
 				      interface);
-	if (!priv->phydev)
-		priv->phydev = of_phy_connect_fixed_link(dev, &adjust_link,
-							 interface);
 	if (!priv->phydev) {
 		dev_err(&dev->dev, "could not attach to PHY\n");
 		return -ENODEV;
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index c8299c31b21..36fc429298e 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1728,9 +1728,6 @@ static int init_phy(struct net_device *dev)
 
 	phydev = of_phy_connect(dev, ug_info->phy_node, &adjust_link, 0,
 				priv->phy_interface);
-	if (!phydev)
-		phydev = of_phy_connect_fixed_link(dev, &adjust_link,
-						   priv->phy_interface);
 	if (!phydev) {
 		dev_err(&dev->dev, "Could not attach to PHY\n");
 		return -ENODEV;
@@ -2993,11 +2990,11 @@ static int ucc_geth_startup(struct ucc_geth_private *ugeth)
 	if (ug_info->rxExtendedFiltering) {
 		size += THREAD_RX_PRAM_ADDITIONAL_FOR_EXTENDED_FILTERING;
 		if (ug_info->largestexternallookupkeysize ==
-		    QE_FLTR_TABLE_LOOKUP_KEY_SIZE_8_BYTES)
+		    QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_8_BYTES)
 			size +=
 			    THREAD_RX_PRAM_ADDITIONAL_FOR_EXTENDED_FILTERING_8;
 		if (ug_info->largestexternallookupkeysize ==
-		    QE_FLTR_TABLE_LOOKUP_KEY_SIZE_16_BYTES)
+		    QE_FLTR_LARGEST_EXTERNAL_TABLE_LOOKUP_KEY_SIZE_16_BYTES)
 			size +=
 			    THREAD_RX_PRAM_ADDITIONAL_FOR_EXTENDED_FILTERING_16;
 	}
@@ -3790,6 +3787,17 @@ static int ucc_geth_probe(struct platform_device* ofdev)
 	ug_info->uf_info.irq = irq_of_parse_and_map(np, 0);
 
 	ug_info->phy_node = of_parse_phandle(np, "phy-handle", 0);
+	if (!ug_info->phy_node) {
+		/* In the case of a fixed PHY, the DT node associated
+		 * to the PHY is the Ethernet MAC DT node.
+		 */
+		if (of_phy_is_fixed_link(np)) {
+			err = of_phy_register_fixed_link(np);
+			if (err)
+				return err;
+		}
+		ug_info->phy_node = np;
+	}
 
 	/* Find the TBI PHY node.  If it's not there, we don't support SGMII */
 	ug_info->tbi_node = of_parse_phandle(np, "tbi-handle", 0);
diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index 413329eff2f..cc83350d56b 100644
--- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -417,5 +417,5 @@ static const struct ethtool_ops uec_ethtool_ops = {
 
 void uec_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &uec_ethtool_ops);
+	netdev->ethtool_ops = &uec_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c
index d449fcb9019..0c9d55c862a 100644
--- a/drivers/net/ethernet/freescale/xgmac_mdio.c
+++ b/drivers/net/ethernet/freescale/xgmac_mdio.c
@@ -162,7 +162,9 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
 
 	/* Return all Fs if nothing was there */
 	if (in_be32(&regs->mdio_stat) & MDIO_STAT_RD_ER) {
-		dev_err(&bus->dev, "MDIO read error\n");
+		dev_err(&bus->dev,
+			"Error while reading PHY%d reg at %d.%d\n",
+			phy_id, dev_addr, regnum);
 		return 0xffff;
 	}
 
diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
index 7becab1aa3e..cfe7a743173 100644
--- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
+++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
@@ -256,7 +256,7 @@ static int fmvj18x_probe(struct pcmcia_device *link)
     dev->netdev_ops = &fjn_netdev_ops;
     dev->watchdog_timeo = TX_TIMEOUT;
 
-    SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops);
+    dev->ethtool_ops = &netdev_ethtool_ops;
 
     return fmvj18x_config(link);
 } /* fmvj18x_attach */
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
new file mode 100644
index 00000000000..e9421731b05
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -0,0 +1,27 @@
+#
+# HISILICON device configuration
+#
+
+config NET_VENDOR_HISILICON
+	bool "Hisilicon devices"
+	default y
+	depends on ARM
+	---help---
+	  If you have a network (Ethernet) card belonging to this class, say Y
+	  and read the Ethernet-HOWTO, available from
+	  <http://www.tldp.org/docs.html#howto>.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about Hisilicon devices. If you say Y, you will be asked
+	  for your specific card in the following questions.
+
+if NET_VENDOR_HISILICON
+
+config HIX5HD2_GMAC
+	tristate "Hisilicon HIX5HD2 Family Network Device Support"
+	select PHYLIB
+	help
+	  This selects the hix5hd2 mac family network device.
+
+endif # NET_VENDOR_HISILICON
diff --git a/drivers/net/ethernet/hisilicon/Makefile b/drivers/net/ethernet/hisilicon/Makefile
new file mode 100644
index 00000000000..9175e84622d
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the HISILICON network device drivers.
+#
+
+obj-$(CONFIG_HIX5HD2_GMAC) += hix5hd2_gmac.o
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
new file mode 100644
index 00000000000..0ffdcd381fd
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -0,0 +1,1066 @@
+/* Copyright (c) 2014 Linaro Ltd.
+ * Copyright (c) 2014 Hisilicon Limited.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/etherdevice.h>
+#include <linux/platform_device.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+#include <linux/clk.h>
+#include <linux/circ_buf.h>
+
+#define STATION_ADDR_LOW		0x0000
+#define STATION_ADDR_HIGH		0x0004
+#define MAC_DUPLEX_HALF_CTRL		0x0008
+#define MAX_FRM_SIZE			0x003c
+#define PORT_MODE			0x0040
+#define PORT_EN				0x0044
+#define BITS_TX_EN			BIT(2)
+#define BITS_RX_EN			BIT(1)
+#define REC_FILT_CONTROL		0x0064
+#define BIT_CRC_ERR_PASS		BIT(5)
+#define BIT_PAUSE_FRM_PASS		BIT(4)
+#define BIT_VLAN_DROP_EN		BIT(3)
+#define BIT_BC_DROP_EN			BIT(2)
+#define BIT_MC_MATCH_EN			BIT(1)
+#define BIT_UC_MATCH_EN			BIT(0)
+#define PORT_MC_ADDR_LOW		0x0068
+#define PORT_MC_ADDR_HIGH		0x006C
+#define CF_CRC_STRIP			0x01b0
+#define MODE_CHANGE_EN			0x01b4
+#define BIT_MODE_CHANGE_EN		BIT(0)
+#define COL_SLOT_TIME			0x01c0
+#define RECV_CONTROL			0x01e0
+#define BIT_STRIP_PAD_EN		BIT(3)
+#define BIT_RUNT_PKT_EN			BIT(4)
+#define CONTROL_WORD			0x0214
+#define MDIO_SINGLE_CMD			0x03c0
+#define MDIO_SINGLE_DATA		0x03c4
+#define MDIO_CTRL			0x03cc
+#define MDIO_RDATA_STATUS		0x03d0
+
+#define MDIO_START			BIT(20)
+#define MDIO_R_VALID			BIT(0)
+#define MDIO_READ			(BIT(17) | MDIO_START)
+#define MDIO_WRITE			(BIT(16) | MDIO_START)
+
+#define RX_FQ_START_ADDR		0x0500
+#define RX_FQ_DEPTH			0x0504
+#define RX_FQ_WR_ADDR			0x0508
+#define RX_FQ_RD_ADDR			0x050c
+#define RX_FQ_VLDDESC_CNT		0x0510
+#define RX_FQ_ALEMPTY_TH		0x0514
+#define RX_FQ_REG_EN			0x0518
+#define BITS_RX_FQ_START_ADDR_EN	BIT(2)
+#define BITS_RX_FQ_DEPTH_EN		BIT(1)
+#define BITS_RX_FQ_RD_ADDR_EN		BIT(0)
+#define RX_FQ_ALFULL_TH			0x051c
+#define RX_BQ_START_ADDR		0x0520
+#define RX_BQ_DEPTH			0x0524
+#define RX_BQ_WR_ADDR			0x0528
+#define RX_BQ_RD_ADDR			0x052c
+#define RX_BQ_FREE_DESC_CNT		0x0530
+#define RX_BQ_ALEMPTY_TH		0x0534
+#define RX_BQ_REG_EN			0x0538
+#define BITS_RX_BQ_START_ADDR_EN	BIT(2)
+#define BITS_RX_BQ_DEPTH_EN		BIT(1)
+#define BITS_RX_BQ_WR_ADDR_EN		BIT(0)
+#define RX_BQ_ALFULL_TH			0x053c
+#define TX_BQ_START_ADDR		0x0580
+#define TX_BQ_DEPTH			0x0584
+#define TX_BQ_WR_ADDR			0x0588
+#define TX_BQ_RD_ADDR			0x058c
+#define TX_BQ_VLDDESC_CNT		0x0590
+#define TX_BQ_ALEMPTY_TH		0x0594
+#define TX_BQ_REG_EN			0x0598
+#define BITS_TX_BQ_START_ADDR_EN	BIT(2)
+#define BITS_TX_BQ_DEPTH_EN		BIT(1)
+#define BITS_TX_BQ_RD_ADDR_EN		BIT(0)
+#define TX_BQ_ALFULL_TH			0x059c
+#define TX_RQ_START_ADDR		0x05a0
+#define TX_RQ_DEPTH			0x05a4
+#define TX_RQ_WR_ADDR			0x05a8
+#define TX_RQ_RD_ADDR			0x05ac
+#define TX_RQ_FREE_DESC_CNT		0x05b0
+#define TX_RQ_ALEMPTY_TH		0x05b4
+#define TX_RQ_REG_EN			0x05b8
+#define BITS_TX_RQ_START_ADDR_EN	BIT(2)
+#define BITS_TX_RQ_DEPTH_EN		BIT(1)
+#define BITS_TX_RQ_WR_ADDR_EN		BIT(0)
+#define TX_RQ_ALFULL_TH			0x05bc
+#define RAW_PMU_INT			0x05c0
+#define ENA_PMU_INT			0x05c4
+#define STATUS_PMU_INT			0x05c8
+#define MAC_FIFO_ERR_IN			BIT(30)
+#define TX_RQ_IN_TIMEOUT_INT		BIT(29)
+#define RX_BQ_IN_TIMEOUT_INT		BIT(28)
+#define TXOUTCFF_FULL_INT		BIT(27)
+#define TXOUTCFF_EMPTY_INT		BIT(26)
+#define TXCFF_FULL_INT			BIT(25)
+#define TXCFF_EMPTY_INT			BIT(24)
+#define RXOUTCFF_FULL_INT		BIT(23)
+#define RXOUTCFF_EMPTY_INT		BIT(22)
+#define RXCFF_FULL_INT			BIT(21)
+#define RXCFF_EMPTY_INT			BIT(20)
+#define TX_RQ_IN_INT			BIT(19)
+#define TX_BQ_OUT_INT			BIT(18)
+#define RX_BQ_IN_INT			BIT(17)
+#define RX_FQ_OUT_INT			BIT(16)
+#define TX_RQ_EMPTY_INT			BIT(15)
+#define TX_RQ_FULL_INT			BIT(14)
+#define TX_RQ_ALEMPTY_INT		BIT(13)
+#define TX_RQ_ALFULL_INT		BIT(12)
+#define TX_BQ_EMPTY_INT			BIT(11)
+#define TX_BQ_FULL_INT			BIT(10)
+#define TX_BQ_ALEMPTY_INT		BIT(9)
+#define TX_BQ_ALFULL_INT		BIT(8)
+#define RX_BQ_EMPTY_INT			BIT(7)
+#define RX_BQ_FULL_INT			BIT(6)
+#define RX_BQ_ALEMPTY_INT		BIT(5)
+#define RX_BQ_ALFULL_INT		BIT(4)
+#define RX_FQ_EMPTY_INT			BIT(3)
+#define RX_FQ_FULL_INT			BIT(2)
+#define RX_FQ_ALEMPTY_INT		BIT(1)
+#define RX_FQ_ALFULL_INT		BIT(0)
+
+#define DEF_INT_MASK			(RX_BQ_IN_INT | RX_BQ_IN_TIMEOUT_INT | \
+					TX_RQ_IN_INT | TX_RQ_IN_TIMEOUT_INT)
+
+#define DESC_WR_RD_ENA			0x05cc
+#define IN_QUEUE_TH			0x05d8
+#define OUT_QUEUE_TH			0x05dc
+#define QUEUE_TX_BQ_SHIFT		16
+#define RX_BQ_IN_TIMEOUT_TH		0x05e0
+#define TX_RQ_IN_TIMEOUT_TH		0x05e4
+#define STOP_CMD			0x05e8
+#define BITS_TX_STOP			BIT(1)
+#define BITS_RX_STOP			BIT(0)
+#define FLUSH_CMD			0x05eC
+#define BITS_TX_FLUSH_CMD		BIT(5)
+#define BITS_RX_FLUSH_CMD		BIT(4)
+#define BITS_TX_FLUSH_FLAG_DOWN		BIT(3)
+#define BITS_TX_FLUSH_FLAG_UP		BIT(2)
+#define BITS_RX_FLUSH_FLAG_DOWN		BIT(1)
+#define BITS_RX_FLUSH_FLAG_UP		BIT(0)
+#define RX_CFF_NUM_REG			0x05f0
+#define PMU_FSM_REG			0x05f8
+#define RX_FIFO_PKT_IN_NUM		0x05fc
+#define RX_FIFO_PKT_OUT_NUM		0x0600
+
+#define RGMII_SPEED_1000		0x2c
+#define RGMII_SPEED_100			0x2f
+#define RGMII_SPEED_10			0x2d
+#define MII_SPEED_100			0x0f
+#define MII_SPEED_10			0x0d
+#define GMAC_SPEED_1000			0x05
+#define GMAC_SPEED_100			0x01
+#define GMAC_SPEED_10			0x00
+#define GMAC_FULL_DUPLEX		BIT(4)
+
+#define RX_BQ_INT_THRESHOLD		0x01
+#define TX_RQ_INT_THRESHOLD		0x01
+#define RX_BQ_IN_TIMEOUT		0x10000
+#define TX_RQ_IN_TIMEOUT		0x50000
+
+#define MAC_MAX_FRAME_SIZE		1600
+#define DESC_SIZE			32
+#define RX_DESC_NUM			1024
+#define TX_DESC_NUM			1024
+
+#define DESC_VLD_FREE			0
+#define DESC_VLD_BUSY			0x80000000
+#define DESC_FL_MID			0
+#define DESC_FL_LAST			0x20000000
+#define DESC_FL_FIRST			0x40000000
+#define DESC_FL_FULL			0x60000000
+#define DESC_DATA_LEN_OFF		16
+#define DESC_BUFF_LEN_OFF		0
+#define DESC_DATA_MASK			0x7ff
+
+/* DMA descriptor ring helpers */
+#define dma_ring_incr(n, s)		(((n) + 1) & ((s) - 1))
+#define dma_cnt(n)			((n) >> 5)
+#define dma_byte(n)			((n) << 5)
+
+struct hix5hd2_desc {
+	__le32 buff_addr;
+	__le32 cmd;
+} __aligned(32);
+
+struct hix5hd2_desc_sw {
+	struct hix5hd2_desc *desc;
+	dma_addr_t	phys_addr;
+	unsigned int	count;
+	unsigned int	size;
+};
+
+#define QUEUE_NUMS	4
+struct hix5hd2_priv {
+	struct hix5hd2_desc_sw pool[QUEUE_NUMS];
+#define rx_fq		pool[0]
+#define rx_bq		pool[1]
+#define tx_bq		pool[2]
+#define tx_rq		pool[3]
+
+	void __iomem *base;
+	void __iomem *ctrl_base;
+
+	struct sk_buff *tx_skb[TX_DESC_NUM];
+	struct sk_buff *rx_skb[RX_DESC_NUM];
+
+	struct device *dev;
+	struct net_device *netdev;
+
+	struct phy_device *phy;
+	struct device_node *phy_node;
+	phy_interface_t	phy_mode;
+
+	unsigned int speed;
+	unsigned int duplex;
+
+	struct clk *clk;
+	struct mii_bus *bus;
+	struct napi_struct napi;
+	struct work_struct tx_timeout_task;
+};
+
+static void hix5hd2_config_port(struct net_device *dev, u32 speed, u32 duplex)
+{
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+	u32 val;
+
+	priv->speed = speed;
+	priv->duplex = duplex;
+
+	switch (priv->phy_mode) {
+	case PHY_INTERFACE_MODE_RGMII:
+		if (speed == SPEED_1000)
+			val = RGMII_SPEED_1000;
+		else if (speed == SPEED_100)
+			val = RGMII_SPEED_100;
+		else
+			val = RGMII_SPEED_10;
+		break;
+	case PHY_INTERFACE_MODE_MII:
+		if (speed == SPEED_100)
+			val = MII_SPEED_100;
+		else
+			val = MII_SPEED_10;
+		break;
+	default:
+		netdev_warn(dev, "not supported mode\n");
+		val = MII_SPEED_10;
+		break;
+	}
+
+	if (duplex)
+		val |= GMAC_FULL_DUPLEX;
+	writel_relaxed(val, priv->ctrl_base);
+
+	writel_relaxed(BIT_MODE_CHANGE_EN, priv->base + MODE_CHANGE_EN);
+	if (speed == SPEED_1000)
+		val = GMAC_SPEED_1000;
+	else if (speed == SPEED_100)
+		val = GMAC_SPEED_100;
+	else
+		val = GMAC_SPEED_10;
+	writel_relaxed(val, priv->base + PORT_MODE);
+	writel_relaxed(0, priv->base + MODE_CHANGE_EN);
+	writel_relaxed(duplex, priv->base + MAC_DUPLEX_HALF_CTRL);
+}
+
+static void hix5hd2_set_desc_depth(struct hix5hd2_priv *priv, int rx, int tx)
+{
+	writel_relaxed(BITS_RX_FQ_DEPTH_EN, priv->base + RX_FQ_REG_EN);
+	writel_relaxed(rx << 3, priv->base + RX_FQ_DEPTH);
+	writel_relaxed(0, priv->base + RX_FQ_REG_EN);
+
+	writel_relaxed(BITS_RX_BQ_DEPTH_EN, priv->base + RX_BQ_REG_EN);
+	writel_relaxed(rx << 3, priv->base + RX_BQ_DEPTH);
+	writel_relaxed(0, priv->base + RX_BQ_REG_EN);
+
+	writel_relaxed(BITS_TX_BQ_DEPTH_EN, priv->base + TX_BQ_REG_EN);
+	writel_relaxed(tx << 3, priv->base + TX_BQ_DEPTH);
+	writel_relaxed(0, priv->base + TX_BQ_REG_EN);
+
+	writel_relaxed(BITS_TX_RQ_DEPTH_EN, priv->base + TX_RQ_REG_EN);
+	writel_relaxed(tx << 3, priv->base + TX_RQ_DEPTH);
+	writel_relaxed(0, priv->base + TX_RQ_REG_EN);
+}
+
+static void hix5hd2_set_rx_fq(struct hix5hd2_priv *priv, dma_addr_t phy_addr)
+{
+	writel_relaxed(BITS_RX_FQ_START_ADDR_EN, priv->base + RX_FQ_REG_EN);
+	writel_relaxed(phy_addr, priv->base + RX_FQ_START_ADDR);
+	writel_relaxed(0, priv->base + RX_FQ_REG_EN);
+}
+
+static void hix5hd2_set_rx_bq(struct hix5hd2_priv *priv, dma_addr_t phy_addr)
+{
+	writel_relaxed(BITS_RX_BQ_START_ADDR_EN, priv->base + RX_BQ_REG_EN);
+	writel_relaxed(phy_addr, priv->base + RX_BQ_START_ADDR);
+	writel_relaxed(0, priv->base + RX_BQ_REG_EN);
+}
+
+static void hix5hd2_set_tx_bq(struct hix5hd2_priv *priv, dma_addr_t phy_addr)
+{
+	writel_relaxed(BITS_TX_BQ_START_ADDR_EN, priv->base + TX_BQ_REG_EN);
+	writel_relaxed(phy_addr, priv->base + TX_BQ_START_ADDR);
+	writel_relaxed(0, priv->base + TX_BQ_REG_EN);
+}
+
+static void hix5hd2_set_tx_rq(struct hix5hd2_priv *priv, dma_addr_t phy_addr)
+{
+	writel_relaxed(BITS_TX_RQ_START_ADDR_EN, priv->base + TX_RQ_REG_EN);
+	writel_relaxed(phy_addr, priv->base + TX_RQ_START_ADDR);
+	writel_relaxed(0, priv->base + TX_RQ_REG_EN);
+}
+
+static void hix5hd2_set_desc_addr(struct hix5hd2_priv *priv)
+{
+	hix5hd2_set_rx_fq(priv, priv->rx_fq.phys_addr);
+	hix5hd2_set_rx_bq(priv, priv->rx_bq.phys_addr);
+	hix5hd2_set_tx_rq(priv, priv->tx_rq.phys_addr);
+	hix5hd2_set_tx_bq(priv, priv->tx_bq.phys_addr);
+}
+
+static void hix5hd2_hw_init(struct hix5hd2_priv *priv)
+{
+	u32 val;
+
+	/* disable and clear all interrupts */
+	writel_relaxed(0, priv->base + ENA_PMU_INT);
+	writel_relaxed(~0, priv->base + RAW_PMU_INT);
+
+	writel_relaxed(BIT_CRC_ERR_PASS, priv->base + REC_FILT_CONTROL);
+	writel_relaxed(MAC_MAX_FRAME_SIZE, priv->base + CONTROL_WORD);
+	writel_relaxed(0, priv->base + COL_SLOT_TIME);
+
+	val = RX_BQ_INT_THRESHOLD | TX_RQ_INT_THRESHOLD << QUEUE_TX_BQ_SHIFT;
+	writel_relaxed(val, priv->base + IN_QUEUE_TH);
+
+	writel_relaxed(RX_BQ_IN_TIMEOUT, priv->base + RX_BQ_IN_TIMEOUT_TH);
+	writel_relaxed(TX_RQ_IN_TIMEOUT, priv->base + TX_RQ_IN_TIMEOUT_TH);
+
+	hix5hd2_set_desc_depth(priv, RX_DESC_NUM, TX_DESC_NUM);
+	hix5hd2_set_desc_addr(priv);
+}
+
+static void hix5hd2_irq_enable(struct hix5hd2_priv *priv)
+{
+	writel_relaxed(DEF_INT_MASK, priv->base + ENA_PMU_INT);
+}
+
+static void hix5hd2_irq_disable(struct hix5hd2_priv *priv)
+{
+	writel_relaxed(0, priv->base + ENA_PMU_INT);
+}
+
+static void hix5hd2_port_enable(struct hix5hd2_priv *priv)
+{
+	writel_relaxed(0xf, priv->base + DESC_WR_RD_ENA);
+	writel_relaxed(BITS_RX_EN | BITS_TX_EN, priv->base + PORT_EN);
+}
+
+static void hix5hd2_port_disable(struct hix5hd2_priv *priv)
+{
+	writel_relaxed(~(BITS_RX_EN | BITS_TX_EN), priv->base + PORT_EN);
+	writel_relaxed(0, priv->base + DESC_WR_RD_ENA);
+}
+
+static void hix5hd2_hw_set_mac_addr(struct net_device *dev)
+{
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+	unsigned char *mac = dev->dev_addr;
+	u32 val;
+
+	val = mac[1] | (mac[0] << 8);
+	writel_relaxed(val, priv->base + STATION_ADDR_HIGH);
+
+	val = mac[5] | (mac[4] << 8) | (mac[3] << 16) | (mac[2] << 24);
+	writel_relaxed(val, priv->base + STATION_ADDR_LOW);
+}
+
+static int hix5hd2_net_set_mac_address(struct net_device *dev, void *p)
+{
+	int ret;
+
+	ret = eth_mac_addr(dev, p);
+	if (!ret)
+		hix5hd2_hw_set_mac_addr(dev);
+
+	return ret;
+}
+
+static void hix5hd2_adjust_link(struct net_device *dev)
+{
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+	struct phy_device *phy = priv->phy;
+
+	if ((priv->speed != phy->speed) || (priv->duplex != phy->duplex)) {
+		hix5hd2_config_port(dev, phy->speed, phy->duplex);
+		phy_print_status(phy);
+	}
+}
+
+static void hix5hd2_rx_refill(struct hix5hd2_priv *priv)
+{
+	struct hix5hd2_desc *desc;
+	struct sk_buff *skb;
+	u32 start, end, num, pos, i;
+	u32 len = MAC_MAX_FRAME_SIZE;
+	dma_addr_t addr;
+
+	/* software write pointer */
+	start = dma_cnt(readl_relaxed(priv->base + RX_FQ_WR_ADDR));
+	/* logic read pointer */
+	end = dma_cnt(readl_relaxed(priv->base + RX_FQ_RD_ADDR));
+	num = CIRC_SPACE(start, end, RX_DESC_NUM);
+
+	for (i = 0, pos = start; i < num; i++) {
+		if (priv->rx_skb[pos]) {
+			break;
+		} else {
+			skb = netdev_alloc_skb_ip_align(priv->netdev, len);
+			if (unlikely(skb == NULL))
+				break;
+		}
+
+		addr = dma_map_single(priv->dev, skb->data, len, DMA_FROM_DEVICE);
+		if (dma_mapping_error(priv->dev, addr)) {
+			dev_kfree_skb_any(skb);
+			break;
+		}
+
+		desc = priv->rx_fq.desc + pos;
+		desc->buff_addr = cpu_to_le32(addr);
+		priv->rx_skb[pos] = skb;
+		desc->cmd = cpu_to_le32(DESC_VLD_FREE |
+					(len - 1) << DESC_BUFF_LEN_OFF);
+		pos = dma_ring_incr(pos, RX_DESC_NUM);
+	}
+
+	/* ensure desc updated */
+	wmb();
+
+	if (pos != start)
+		writel_relaxed(dma_byte(pos), priv->base + RX_FQ_WR_ADDR);
+}
+
+static int hix5hd2_rx(struct net_device *dev, int limit)
+{
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+	struct sk_buff *skb;
+	struct hix5hd2_desc *desc;
+	dma_addr_t addr;
+	u32 start, end, num, pos, i, len;
+
+	/* software read pointer */
+	start = dma_cnt(readl_relaxed(priv->base + RX_BQ_RD_ADDR));
+	/* logic write pointer */
+	end = dma_cnt(readl_relaxed(priv->base + RX_BQ_WR_ADDR));
+	num = CIRC_CNT(end, start, RX_DESC_NUM);
+	if (num > limit)
+		num = limit;
+
+	/* ensure get updated desc */
+	rmb();
+	for (i = 0, pos = start; i < num; i++) {
+		skb = priv->rx_skb[pos];
+		if (unlikely(!skb)) {
+			netdev_err(dev, "inconsistent rx_skb\n");
+			break;
+		}
+		priv->rx_skb[pos] = NULL;
+
+		desc = priv->rx_bq.desc + pos;
+		len = (le32_to_cpu(desc->cmd) >> DESC_DATA_LEN_OFF) &
+		       DESC_DATA_MASK;
+		addr = le32_to_cpu(desc->buff_addr);
+		dma_unmap_single(priv->dev, addr, MAC_MAX_FRAME_SIZE,
+				 DMA_FROM_DEVICE);
+
+		skb_put(skb, len);
+		if (skb->len > MAC_MAX_FRAME_SIZE) {
+			netdev_err(dev, "rcv len err, len = %d\n", skb->len);
+			dev->stats.rx_errors++;
+			dev->stats.rx_length_errors++;
+			dev_kfree_skb_any(skb);
+			goto next;
+		}
+
+		skb->protocol = eth_type_trans(skb, dev);
+		napi_gro_receive(&priv->napi, skb);
+		dev->stats.rx_packets++;
+		dev->stats.rx_bytes += skb->len;
+		dev->last_rx = jiffies;
+next:
+		pos = dma_ring_incr(pos, RX_DESC_NUM);
+	}
+
+	if (pos != start)
+		writel_relaxed(dma_byte(pos), priv->base + RX_BQ_RD_ADDR);
+
+	hix5hd2_rx_refill(priv);
+
+	return num;
+}
+
+static void hix5hd2_xmit_reclaim(struct net_device *dev)
+{
+	struct sk_buff *skb;
+	struct hix5hd2_desc *desc;
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+	unsigned int bytes_compl = 0, pkts_compl = 0;
+	u32 start, end, num, pos, i;
+	dma_addr_t addr;
+
+	netif_tx_lock(dev);
+
+	/* software read */
+	start = dma_cnt(readl_relaxed(priv->base + TX_RQ_RD_ADDR));
+	/* logic write */
+	end = dma_cnt(readl_relaxed(priv->base + TX_RQ_WR_ADDR));
+	num = CIRC_CNT(end, start, TX_DESC_NUM);
+
+	for (i = 0, pos = start; i < num; i++) {
+		skb = priv->tx_skb[pos];
+		if (unlikely(!skb)) {
+			netdev_err(dev, "inconsistent tx_skb\n");
+			break;
+		}
+
+		pkts_compl++;
+		bytes_compl += skb->len;
+		desc = priv->tx_rq.desc + pos;
+		addr = le32_to_cpu(desc->buff_addr);
+		dma_unmap_single(priv->dev, addr, skb->len, DMA_TO_DEVICE);
+		priv->tx_skb[pos] = NULL;
+		dev_consume_skb_any(skb);
+		pos = dma_ring_incr(pos, TX_DESC_NUM);
+	}
+
+	if (pos != start)
+		writel_relaxed(dma_byte(pos), priv->base + TX_RQ_RD_ADDR);
+
+	netif_tx_unlock(dev);
+
+	if (pkts_compl || bytes_compl)
+		netdev_completed_queue(dev, pkts_compl, bytes_compl);
+
+	if (unlikely(netif_queue_stopped(priv->netdev)) && pkts_compl)
+		netif_wake_queue(priv->netdev);
+}
+
+static int hix5hd2_poll(struct napi_struct *napi, int budget)
+{
+	struct hix5hd2_priv *priv = container_of(napi,
+				struct hix5hd2_priv, napi);
+	struct net_device *dev = priv->netdev;
+	int work_done = 0, task = budget;
+	int ints, num;
+
+	do {
+		hix5hd2_xmit_reclaim(dev);
+		num = hix5hd2_rx(dev, task);
+		work_done += num;
+		task -= num;
+		if ((work_done >= budget) || (num == 0))
+			break;
+
+		ints = readl_relaxed(priv->base + RAW_PMU_INT);
+		writel_relaxed(ints, priv->base + RAW_PMU_INT);
+	} while (ints & DEF_INT_MASK);
+
+	if (work_done < budget) {
+		napi_complete(napi);
+		hix5hd2_irq_enable(priv);
+	}
+
+	return work_done;
+}
+
+static irqreturn_t hix5hd2_interrupt(int irq, void *dev_id)
+{
+	struct net_device *dev = (struct net_device *)dev_id;
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+	int ints = readl_relaxed(priv->base + RAW_PMU_INT);
+
+	writel_relaxed(ints, priv->base + RAW_PMU_INT);
+	if (likely(ints & DEF_INT_MASK)) {
+		hix5hd2_irq_disable(priv);
+		napi_schedule(&priv->napi);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int hix5hd2_net_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+	struct hix5hd2_desc *desc;
+	dma_addr_t addr;
+	u32 pos;
+
+	/* software write pointer */
+	pos = dma_cnt(readl_relaxed(priv->base + TX_BQ_WR_ADDR));
+	if (unlikely(priv->tx_skb[pos])) {
+		dev->stats.tx_dropped++;
+		dev->stats.tx_fifo_errors++;
+		netif_stop_queue(dev);
+		return NETDEV_TX_BUSY;
+	}
+
+	addr = dma_map_single(priv->dev, skb->data, skb->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(priv->dev, addr)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	desc = priv->tx_bq.desc + pos;
+	desc->buff_addr = cpu_to_le32(addr);
+	priv->tx_skb[pos] = skb;
+	desc->cmd = cpu_to_le32(DESC_VLD_BUSY | DESC_FL_FULL |
+				(skb->len & DESC_DATA_MASK) << DESC_DATA_LEN_OFF |
+				(skb->len & DESC_DATA_MASK) << DESC_BUFF_LEN_OFF);
+
+	/* ensure desc updated */
+	wmb();
+
+	pos = dma_ring_incr(pos, TX_DESC_NUM);
+	writel_relaxed(dma_byte(pos), priv->base + TX_BQ_WR_ADDR);
+
+	dev->trans_start = jiffies;
+	dev->stats.tx_packets++;
+	dev->stats.tx_bytes += skb->len;
+	netdev_sent_queue(dev, skb->len);
+
+	return NETDEV_TX_OK;
+}
+
+static void hix5hd2_free_dma_desc_rings(struct hix5hd2_priv *priv)
+{
+	struct hix5hd2_desc *desc;
+	dma_addr_t addr;
+	int i;
+
+	for (i = 0; i < RX_DESC_NUM; i++) {
+		struct sk_buff *skb = priv->rx_skb[i];
+		if (skb == NULL)
+			continue;
+
+		desc = priv->rx_fq.desc + i;
+		addr = le32_to_cpu(desc->buff_addr);
+		dma_unmap_single(priv->dev, addr,
+				 MAC_MAX_FRAME_SIZE, DMA_FROM_DEVICE);
+		dev_kfree_skb_any(skb);
+		priv->rx_skb[i] = NULL;
+	}
+
+	for (i = 0; i < TX_DESC_NUM; i++) {
+		struct sk_buff *skb = priv->tx_skb[i];
+		if (skb == NULL)
+			continue;
+
+		desc = priv->tx_rq.desc + i;
+		addr = le32_to_cpu(desc->buff_addr);
+		dma_unmap_single(priv->dev, addr, skb->len, DMA_TO_DEVICE);
+		dev_kfree_skb_any(skb);
+		priv->tx_skb[i] = NULL;
+	}
+}
+
+static int hix5hd2_net_open(struct net_device *dev)
+{
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+	int ret;
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret < 0) {
+		netdev_err(dev, "failed to enable clk %d\n", ret);
+		return ret;
+	}
+
+	priv->phy = of_phy_connect(dev, priv->phy_node,
+				   &hix5hd2_adjust_link, 0, priv->phy_mode);
+	if (!priv->phy)
+		return -ENODEV;
+
+	phy_start(priv->phy);
+	hix5hd2_hw_init(priv);
+	hix5hd2_rx_refill(priv);
+
+	netdev_reset_queue(dev);
+	netif_start_queue(dev);
+	napi_enable(&priv->napi);
+
+	hix5hd2_port_enable(priv);
+	hix5hd2_irq_enable(priv);
+
+	return 0;
+}
+
+static int hix5hd2_net_close(struct net_device *dev)
+{
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+
+	hix5hd2_port_disable(priv);
+	hix5hd2_irq_disable(priv);
+	napi_disable(&priv->napi);
+	netif_stop_queue(dev);
+	hix5hd2_free_dma_desc_rings(priv);
+
+	if (priv->phy) {
+		phy_stop(priv->phy);
+		phy_disconnect(priv->phy);
+	}
+
+	clk_disable_unprepare(priv->clk);
+
+	return 0;
+}
+
+static void hix5hd2_tx_timeout_task(struct work_struct *work)
+{
+	struct hix5hd2_priv *priv;
+
+	priv = container_of(work, struct hix5hd2_priv, tx_timeout_task);
+	hix5hd2_net_close(priv->netdev);
+	hix5hd2_net_open(priv->netdev);
+}
+
+static void hix5hd2_net_timeout(struct net_device *dev)
+{
+	struct hix5hd2_priv *priv = netdev_priv(dev);
+
+	schedule_work(&priv->tx_timeout_task);
+}
+
+static const struct net_device_ops hix5hd2_netdev_ops = {
+	.ndo_open		= hix5hd2_net_open,
+	.ndo_stop		= hix5hd2_net_close,
+	.ndo_start_xmit		= hix5hd2_net_xmit,
+	.ndo_tx_timeout		= hix5hd2_net_timeout,
+	.ndo_set_mac_address	= hix5hd2_net_set_mac_address,
+};
+
+static int hix5hd2_get_settings(struct net_device *net_dev,
+				struct ethtool_cmd *cmd)
+{
+	struct hix5hd2_priv *priv = netdev_priv(net_dev);
+
+	if (!priv->phy)
+		return -ENODEV;
+
+	return phy_ethtool_gset(priv->phy, cmd);
+}
+
+static int hix5hd2_set_settings(struct net_device *net_dev,
+				struct ethtool_cmd *cmd)
+{
+	struct hix5hd2_priv *priv = netdev_priv(net_dev);
+
+	if (!priv->phy)
+		return -ENODEV;
+
+	return phy_ethtool_sset(priv->phy, cmd);
+}
+
+static struct ethtool_ops hix5hd2_ethtools_ops = {
+	.get_link		= ethtool_op_get_link,
+	.get_settings		= hix5hd2_get_settings,
+	.set_settings		= hix5hd2_set_settings,
+};
+
+static int hix5hd2_mdio_wait_ready(struct mii_bus *bus)
+{
+	struct hix5hd2_priv *priv = bus->priv;
+	void __iomem *base = priv->base;
+	int i, timeout = 10000;
+
+	for (i = 0; readl_relaxed(base + MDIO_SINGLE_CMD) & MDIO_START; i++) {
+		if (i == timeout)
+			return -ETIMEDOUT;
+		usleep_range(10, 20);
+	}
+
+	return 0;
+}
+
+static int hix5hd2_mdio_read(struct mii_bus *bus, int phy, int reg)
+{
+	struct hix5hd2_priv *priv = bus->priv;
+	void __iomem *base = priv->base;
+	int val, ret;
+
+	ret = hix5hd2_mdio_wait_ready(bus);
+	if (ret < 0)
+		goto out;
+
+	writel_relaxed(MDIO_READ | phy << 8 | reg, base + MDIO_SINGLE_CMD);
+	ret = hix5hd2_mdio_wait_ready(bus);
+	if (ret < 0)
+		goto out;
+
+	val = readl_relaxed(base + MDIO_RDATA_STATUS);
+	if (val & MDIO_R_VALID) {
+		dev_err(bus->parent, "SMI bus read not valid\n");
+		ret = -ENODEV;
+		goto out;
+	}
+
+	val = readl_relaxed(priv->base + MDIO_SINGLE_DATA);
+	ret = (val >> 16) & 0xFFFF;
+out:
+	return ret;
+}
+
+static int hix5hd2_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val)
+{
+	struct hix5hd2_priv *priv = bus->priv;
+	void __iomem *base = priv->base;
+	int ret;
+
+	ret = hix5hd2_mdio_wait_ready(bus);
+	if (ret < 0)
+		goto out;
+
+	writel_relaxed(val, base + MDIO_SINGLE_DATA);
+	writel_relaxed(MDIO_WRITE | phy << 8 | reg, base + MDIO_SINGLE_CMD);
+	ret = hix5hd2_mdio_wait_ready(bus);
+out:
+	return ret;
+}
+
+static void hix5hd2_destroy_hw_desc_queue(struct hix5hd2_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < QUEUE_NUMS; i++) {
+		if (priv->pool[i].desc) {
+			dma_free_coherent(priv->dev, priv->pool[i].size,
+					  priv->pool[i].desc,
+					  priv->pool[i].phys_addr);
+			priv->pool[i].desc = NULL;
+		}
+	}
+}
+
+static int hix5hd2_init_hw_desc_queue(struct hix5hd2_priv *priv)
+{
+	struct device *dev = priv->dev;
+	struct hix5hd2_desc *virt_addr;
+	dma_addr_t phys_addr;
+	int size, i;
+
+	priv->rx_fq.count = RX_DESC_NUM;
+	priv->rx_bq.count = RX_DESC_NUM;
+	priv->tx_bq.count = TX_DESC_NUM;
+	priv->tx_rq.count = TX_DESC_NUM;
+
+	for (i = 0; i < QUEUE_NUMS; i++) {
+		size = priv->pool[i].count * sizeof(struct hix5hd2_desc);
+		virt_addr = dma_alloc_coherent(dev, size, &phys_addr,
+					       GFP_KERNEL);
+		if (virt_addr == NULL)
+			goto error_free_pool;
+
+		memset(virt_addr, 0, size);
+		priv->pool[i].size = size;
+		priv->pool[i].desc = virt_addr;
+		priv->pool[i].phys_addr = phys_addr;
+	}
+	return 0;
+
+error_free_pool:
+	hix5hd2_destroy_hw_desc_queue(priv);
+
+	return -ENOMEM;
+}
+
+static int hix5hd2_dev_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *node = dev->of_node;
+	struct net_device *ndev;
+	struct hix5hd2_priv *priv;
+	struct resource *res;
+	struct mii_bus *bus;
+	const char *mac_addr;
+	int ret;
+
+	ndev = alloc_etherdev(sizeof(struct hix5hd2_priv));
+	if (!ndev)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, ndev);
+
+	priv = netdev_priv(ndev);
+	priv->dev = dev;
+	priv->netdev = ndev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(priv->base)) {
+		ret = PTR_ERR(priv->base);
+		goto out_free_netdev;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	priv->ctrl_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(priv->ctrl_base)) {
+		ret = PTR_ERR(priv->ctrl_base);
+		goto out_free_netdev;
+	}
+
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		netdev_err(ndev, "failed to get clk\n");
+		ret = -ENODEV;
+		goto out_free_netdev;
+	}
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret < 0) {
+		netdev_err(ndev, "failed to enable clk %d\n", ret);
+		goto out_free_netdev;
+	}
+
+	bus = mdiobus_alloc();
+	if (bus == NULL) {
+		ret = -ENOMEM;
+		goto out_free_netdev;
+	}
+
+	bus->priv = priv;
+	bus->name = "hix5hd2_mii_bus";
+	bus->read = hix5hd2_mdio_read;
+	bus->write = hix5hd2_mdio_write;
+	bus->parent = &pdev->dev;
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(&pdev->dev));
+	priv->bus = bus;
+
+	ret = of_mdiobus_register(bus, node);
+	if (ret)
+		goto err_free_mdio;
+
+	priv->phy_mode = of_get_phy_mode(node);
+	if (priv->phy_mode < 0) {
+		netdev_err(ndev, "not find phy-mode\n");
+		ret = -EINVAL;
+		goto err_mdiobus;
+	}
+
+	priv->phy_node = of_parse_phandle(node, "phy-handle", 0);
+	if (!priv->phy_node) {
+		netdev_err(ndev, "not find phy-handle\n");
+		ret = -EINVAL;
+		goto err_mdiobus;
+	}
+
+	ndev->irq = platform_get_irq(pdev, 0);
+	if (ndev->irq <= 0) {
+		netdev_err(ndev, "No irq resource\n");
+		ret = -EINVAL;
+		goto out_phy_node;
+	}
+
+	ret = devm_request_irq(dev, ndev->irq, hix5hd2_interrupt,
+			       0, pdev->name, ndev);
+	if (ret) {
+		netdev_err(ndev, "devm_request_irq failed\n");
+		goto out_phy_node;
+	}
+
+	mac_addr = of_get_mac_address(node);
+	if (mac_addr)
+		ether_addr_copy(ndev->dev_addr, mac_addr);
+	if (!is_valid_ether_addr(ndev->dev_addr)) {
+		eth_hw_addr_random(ndev);
+		netdev_warn(ndev, "using random MAC address %pM\n",
+			    ndev->dev_addr);
+	}
+
+	INIT_WORK(&priv->tx_timeout_task, hix5hd2_tx_timeout_task);
+	ndev->watchdog_timeo = 6 * HZ;
+	ndev->priv_flags |= IFF_UNICAST_FLT;
+	ndev->netdev_ops = &hix5hd2_netdev_ops;
+	ndev->ethtool_ops = &hix5hd2_ethtools_ops;
+	SET_NETDEV_DEV(ndev, dev);
+
+	ret = hix5hd2_init_hw_desc_queue(priv);
+	if (ret)
+		goto out_phy_node;
+
+	netif_napi_add(ndev, &priv->napi, hix5hd2_poll, NAPI_POLL_WEIGHT);
+	ret = register_netdev(priv->netdev);
+	if (ret) {
+		netdev_err(ndev, "register_netdev failed!");
+		goto out_destroy_queue;
+	}
+
+	clk_disable_unprepare(priv->clk);
+
+	return ret;
+
+out_destroy_queue:
+	netif_napi_del(&priv->napi);
+	hix5hd2_destroy_hw_desc_queue(priv);
+out_phy_node:
+	of_node_put(priv->phy_node);
+err_mdiobus:
+	mdiobus_unregister(bus);
+err_free_mdio:
+	mdiobus_free(bus);
+out_free_netdev:
+	free_netdev(ndev);
+
+	return ret;
+}
+
+static int hix5hd2_dev_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct hix5hd2_priv *priv = netdev_priv(ndev);
+
+	netif_napi_del(&priv->napi);
+	unregister_netdev(ndev);
+	mdiobus_unregister(priv->bus);
+	mdiobus_free(priv->bus);
+
+	hix5hd2_destroy_hw_desc_queue(priv);
+	of_node_put(priv->phy_node);
+	cancel_work_sync(&priv->tx_timeout_task);
+	free_netdev(ndev);
+
+	return 0;
+}
+
+static const struct of_device_id hix5hd2_of_match[] = {
+	{.compatible = "hisilicon,hix5hd2-gmac",},
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, hix5hd2_of_match);
+
+static struct platform_driver hix5hd2_dev_driver = {
+	.driver = {
+		.name = "hix5hd2-gmac",
+		.of_match_table = hix5hd2_of_match,
+	},
+	.probe = hix5hd2_dev_probe,
+	.remove = hix5hd2_dev_remove,
+};
+
+module_platform_driver(hix5hd2_dev_driver);
+
+MODULE_DESCRIPTION("HISILICON HIX5HD2 Ethernet driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:hix5hd2-gmac");
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c b/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
index 95837b99a46..85a3866459c 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c
@@ -63,8 +63,8 @@ static int ehea_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		cmd->duplex = port->full_duplex == 1 ?
 						     DUPLEX_FULL : DUPLEX_HALF;
 	} else {
-		speed = ~0;
-		cmd->duplex = -1;
+		speed = SPEED_UNKNOWN;
+		cmd->duplex = DUPLEX_UNKNOWN;
 	}
 	ethtool_cmd_speed_set(cmd, speed);
 
@@ -278,5 +278,5 @@ static const struct ethtool_ops ehea_ethtool_ops = {
 
 void ehea_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &ehea_ethtool_ops);
+	netdev->ethtool_ops = &ehea_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 538903bf13b..a0b418e007a 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -28,6 +28,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/device.h>
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
@@ -3273,7 +3274,7 @@ static int ehea_probe_adapter(struct platform_device *dev)
 		return -EINVAL;
 	}
 
-	adapter = kzalloc(sizeof(*adapter), GFP_KERNEL);
+	adapter = devm_kzalloc(&dev->dev, sizeof(*adapter), GFP_KERNEL);
 	if (!adapter) {
 		ret = -ENOMEM;
 		dev_err(&dev->dev, "no mem for ehea_adapter\n");
@@ -3359,7 +3360,6 @@ out_kill_eq:
 
 out_free_ad:
 	list_del(&adapter->list);
-	kfree(adapter);
 
 out:
 	ehea_update_firmware_handles();
@@ -3386,7 +3386,6 @@ static int ehea_remove(struct platform_device *dev)
 	ehea_destroy_eq(adapter->neq);
 	ehea_remove_adapter_mr(adapter);
 	list_del(&adapter->list);
-	kfree(adapter);
 
 	ehea_update_firmware_handles();
 
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c b/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
index 9b03033bb55..a0820f72b25 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_qmr.c
@@ -103,12 +103,14 @@ out_nomem:
 
 static void hw_queue_dtor(struct hw_queue *queue)
 {
-	int pages_per_kpage = PAGE_SIZE / queue->pagesize;
+	int pages_per_kpage;
 	int i, nr_pages;
 
 	if (!queue || !queue->queue_pages)
 		return;
 
+	pages_per_kpage = PAGE_SIZE / queue->pagesize;
+
 	nr_pages = queue->queue_length / queue->pagesize;
 
 	for (i = 0; i < nr_pages; i += pages_per_kpage)
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index ae342fdb42c..87bd953cc2e 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2879,7 +2879,7 @@ static int emac_probe(struct platform_device *ofdev)
 		dev->commac.ops = &emac_commac_sg_ops;
 	} else
 		ndev->netdev_ops = &emac_netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &emac_ethtool_ops);
+	ndev->ethtool_ops = &emac_ethtool_ops;
 
 	netif_carrier_off(ndev);
 
diff --git a/drivers/net/ethernet/icplus/ipg.c b/drivers/net/ethernet/icplus/ipg.c
index 25045ae0717..5727779a7df 100644
--- a/drivers/net/ethernet/icplus/ipg.c
+++ b/drivers/net/ethernet/icplus/ipg.c
@@ -2245,7 +2245,7 @@ static int ipg_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	 */
 	dev->netdev_ops = &ipg_netdev_ops;
 	SET_NETDEV_DEV(dev, &pdev->dev);
-	SET_ETHTOOL_OPS(dev, &ipg_ethtool_ops);
+	dev->ethtool_ops = &ipg_ethtool_ops;
 
 	rc = pci_request_regions(pdev, DRV_NAME);
 	if (rc)
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index b56461ce674..9d979d7debe 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -2854,7 +2854,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->hw_features |= NETIF_F_RXALL;
 
 	netdev->netdev_ops = &e100_netdev_ops;
-	SET_ETHTOOL_OPS(netdev, &e100_ethtool_ops);
+	netdev->ethtool_ops = &e100_ethtool_ops;
 	netdev->watchdog_timeo = E100_WATCHDOG_PERIOD;
 	strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1);
 
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 73a8aeefb92..d50f78afb56 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -168,8 +168,8 @@ static int e1000_get_settings(struct net_device *netdev,
 		else
 			ecmd->duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	ecmd->autoneg = ((hw->media_type == e1000_media_type_fiber) ||
@@ -1460,7 +1460,8 @@ static int e1000_run_loopback_test(struct e1000_adapter *adapter)
 			 * enough time to complete the receives, if it's
 			 * exceeded, break and error off
 			 */
-		} while (good_cnt < 64 && jiffies < (time + 20));
+		} while (good_cnt < 64 && time_after(time + 20, jiffies));
+
 		if (good_cnt != 64) {
 			ret_val = 13; /* ret_val is the same as mis-compare */
 			break;
@@ -1905,5 +1906,5 @@ static const struct ethtool_ops e1000_ethtool_ops = {
 
 void e1000_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &e1000_ethtool_ops);
+	netdev->ethtool_ops = &e1000_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c
index c1d3fdb296a..e9b07ccc0eb 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c
@@ -4877,10 +4877,10 @@ void e1000_tbi_adjust_stats(struct e1000_hw *hw, struct e1000_hw_stats *stats,
 	 * since the test for a multicast frame will test positive on
 	 * a broadcast frame.
 	 */
-	if ((mac_addr[0] == (u8) 0xff) && (mac_addr[1] == (u8) 0xff))
+	if (is_broadcast_ether_addr(mac_addr))
 		/* Broadcast packet */
 		stats->bprc++;
-	else if (*mac_addr & 0x01)
+	else if (is_multicast_ether_addr(mac_addr))
 		/* Multicast packet */
 		stats->mprc++;
 
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 27058dfe418..660971f304b 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3105,11 +3105,6 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 	 */
 	tx_ring = adapter->tx_ring;
 
-	if (unlikely(skb->len <= 0)) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
-
 	/* On PCI/PCI-X HW, if packet size is less than ETH_ZLEN,
 	 * packets may get corrupted during padding by HW.
 	 * To WA this issue, pad all small packets manually.
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index a5f6b11d699..08f22f34880 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -1365,6 +1365,7 @@ static const struct e1000_mac_operations es2_mac_ops = {
 	.setup_led		= e1000e_setup_led_generic,
 	.config_collision_dist	= e1000e_config_collision_dist_generic,
 	.rar_set		= e1000e_rar_set_generic,
+	.rar_get_count		= e1000e_rar_get_count_generic,
 };
 
 static const struct e1000_phy_operations es2_phy_ops = {
diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c
index e0aa7f1efb0..218481e509f 100644
--- a/drivers/net/ethernet/intel/e1000e/82571.c
+++ b/drivers/net/ethernet/intel/e1000e/82571.c
@@ -1896,6 +1896,7 @@ static const struct e1000_mac_operations e82571_mac_ops = {
 	.config_collision_dist	= e1000e_config_collision_dist_generic,
 	.read_mac_addr		= e1000_read_mac_addr_82571,
 	.rar_set		= e1000e_rar_set_generic,
+	.rar_get_count		= e1000e_rar_get_count_generic,
 };
 
 static const struct e1000_phy_operations e82_phy_ops_igp = {
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 1471c5464a8..7785240a0da 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -265,10 +265,10 @@ struct e1000_adapter {
 	u32 tx_hwtstamp_timeouts;
 
 	/* Rx */
-	bool (*clean_rx) (struct e1000_ring *ring, int *work_done,
-			  int work_to_do) ____cacheline_aligned_in_smp;
-	void (*alloc_rx_buf) (struct e1000_ring *ring, int cleaned_count,
-			      gfp_t gfp);
+	bool (*clean_rx)(struct e1000_ring *ring, int *work_done,
+			 int work_to_do) ____cacheline_aligned_in_smp;
+	void (*alloc_rx_buf)(struct e1000_ring *ring, int cleaned_count,
+			     gfp_t gfp);
 	struct e1000_ring *rx_ring;
 
 	u32 rx_int_delay;
@@ -391,6 +391,8 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
  * 25MHz	46-bit	2^46 / 10^9 / 3600 = 19.55 hours
  */
 #define E1000_SYSTIM_OVERFLOW_PERIOD	(HZ * 60 * 60 * 4)
+#define E1000_MAX_82574_SYSTIM_REREADS	50
+#define E1000_82574_SYSTIM_EPSILON	(1ULL << 35ULL)
 
 /* hardware capability, feature, and workaround flags */
 #define FLAG_HAS_AMT                      (1 << 0)
@@ -573,35 +575,8 @@ static inline u32 __er32(struct e1000_hw *hw, unsigned long reg)
 
 #define er32(reg)	__er32(hw, E1000_##reg)
 
-/**
- * __ew32_prepare - prepare to write to MAC CSR register on certain parts
- * @hw: pointer to the HW structure
- *
- * When updating the MAC CSR registers, the Manageability Engine (ME) could
- * be accessing the registers at the same time.  Normally, this is handled in
- * h/w by an arbiter but on some parts there is a bug that acknowledges Host
- * accesses later than it should which could result in the register to have
- * an incorrect value.  Workaround this by checking the FWSM register which
- * has bit 24 set while ME is accessing MAC CSR registers, wait if it is set
- * and try again a number of times.
- **/
-static inline s32 __ew32_prepare(struct e1000_hw *hw)
-{
-	s32 i = E1000_ICH_FWSM_PCIM2PCI_COUNT;
-
-	while ((er32(FWSM) & E1000_ICH_FWSM_PCIM2PCI) && --i)
-		udelay(50);
-
-	return i;
-}
-
-static inline void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
-{
-	if (hw->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
-		__ew32_prepare(hw);
-
-	writel(val, hw->hw_addr + reg);
-}
+s32 __ew32_prepare(struct e1000_hw *hw);
+void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val);
 
 #define ew32(reg, val)	__ew32(hw, E1000_##reg, (val))
 
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index cad250bc1b9..815e26c6d34 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -159,8 +159,8 @@ static int e1000_get_settings(struct net_device *netdev,
 		ecmd->transceiver = XCVR_EXTERNAL;
 	}
 
-	speed = -1;
-	ecmd->duplex = -1;
+	speed = SPEED_UNKNOWN;
+	ecmd->duplex = DUPLEX_UNKNOWN;
 
 	if (netif_running(netdev)) {
 		if (netif_carrier_ok(netdev)) {
@@ -169,6 +169,7 @@ static int e1000_get_settings(struct net_device *netdev,
 		}
 	} else if (!pm_runtime_suspended(netdev->dev.parent)) {
 		u32 status = er32(STATUS);
+
 		if (status & E1000_STATUS_LU) {
 			if (status & E1000_STATUS_SPEED_1000)
 				speed = SPEED_1000;
@@ -783,25 +784,26 @@ static bool reg_pattern_test(struct e1000_adapter *adapter, u64 *data,
 			      reg + (offset << 2), val,
 			      (test[pat] & write & mask));
 			*data = reg;
-			return 1;
+			return true;
 		}
 	}
-	return 0;
+	return false;
 }
 
 static bool reg_set_and_check(struct e1000_adapter *adapter, u64 *data,
 			      int reg, u32 mask, u32 write)
 {
 	u32 val;
+
 	__ew32(&adapter->hw, reg, write & mask);
 	val = __er32(&adapter->hw, reg);
 	if ((write & mask) != (val & mask)) {
 		e_err("set/check test failed (reg 0x%05X): got 0x%08X expected 0x%08X\n",
 		      reg, (val & mask), (write & mask));
 		*data = reg;
-		return 1;
+		return true;
 	}
-	return 0;
+	return false;
 }
 
 #define REG_PATTERN_TEST_ARRAY(reg, offset, mask, write)                       \
@@ -1717,6 +1719,7 @@ static int e1000_link_test(struct e1000_adapter *adapter, u64 *data)
 	*data = 0;
 	if (hw->phy.media_type == e1000_media_type_internal_serdes) {
 		int i = 0;
+
 		hw->mac.serdes_has_link = false;
 
 		/* On some blade server designs, link establishment
@@ -2315,5 +2318,5 @@ static const struct ethtool_ops e1000_ethtool_ops = {
 
 void e1000e_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &e1000_ethtool_ops);
+	netdev->ethtool_ops = &e1000_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h
index 6b3de5f39a9..72f5475c4b9 100644
--- a/drivers/net/ethernet/intel/e1000e/hw.h
+++ b/drivers/net/ethernet/intel/e1000e/hw.h
@@ -469,8 +469,9 @@ struct e1000_mac_operations {
 	s32  (*setup_led)(struct e1000_hw *);
 	void (*write_vfta)(struct e1000_hw *, u32, u32);
 	void (*config_collision_dist)(struct e1000_hw *);
-	void (*rar_set)(struct e1000_hw *, u8 *, u32);
+	int  (*rar_set)(struct e1000_hw *, u8 *, u32);
 	s32  (*read_mac_addr)(struct e1000_hw *);
+	u32  (*rar_get_count)(struct e1000_hw *);
 };
 
 /* When to use various PHY register access functions:
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index f0bbd4246d7..8894ab8ed6b 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -139,8 +139,9 @@ static s32 e1000_k1_gig_workaround_hv(struct e1000_hw *hw, bool link);
 static s32 e1000_set_mdio_slow_mode_hv(struct e1000_hw *hw);
 static bool e1000_check_mng_mode_ich8lan(struct e1000_hw *hw);
 static bool e1000_check_mng_mode_pchlan(struct e1000_hw *hw);
-static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index);
-static void e1000_rar_set_pch_lpt(struct e1000_hw *hw, u8 *addr, u32 index);
+static int e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index);
+static int e1000_rar_set_pch_lpt(struct e1000_hw *hw, u8 *addr, u32 index);
+static u32 e1000_rar_get_count_pch_lpt(struct e1000_hw *hw);
 static s32 e1000_k1_workaround_lv(struct e1000_hw *hw);
 static void e1000_gate_hw_phy_config_ich8lan(struct e1000_hw *hw, bool gate);
 static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force);
@@ -704,6 +705,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw)
 		mac->ops.rar_set = e1000_rar_set_pch_lpt;
 		mac->ops.setup_physical_interface =
 		    e1000_setup_copper_link_pch_lpt;
+		mac->ops.rar_get_count = e1000_rar_get_count_pch_lpt;
 	}
 
 	/* Enable PCS Lock-loss workaround for ICH8 */
@@ -1334,6 +1336,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 	if (((hw->mac.type == e1000_pch2lan) ||
 	     (hw->mac.type == e1000_pch_lpt)) && link) {
 		u32 reg;
+
 		reg = er32(STATUS);
 		if (!(reg & (E1000_STATUS_FD | E1000_STATUS_SPEED_MASK))) {
 			u16 emi_addr;
@@ -1634,9 +1637,9 @@ static bool e1000_check_mng_mode_ich8lan(struct e1000_hw *hw)
 	u32 fwsm;
 
 	fwsm = er32(FWSM);
-	return ((fwsm & E1000_ICH_FWSM_FW_VALID) &&
+	return (fwsm & E1000_ICH_FWSM_FW_VALID) &&
 		((fwsm & E1000_FWSM_MODE_MASK) ==
-		 (E1000_ICH_MNG_IAMT_MODE << E1000_FWSM_MODE_SHIFT)));
+		 (E1000_ICH_MNG_IAMT_MODE << E1000_FWSM_MODE_SHIFT));
 }
 
 /**
@@ -1667,7 +1670,7 @@ static bool e1000_check_mng_mode_pchlan(struct e1000_hw *hw)
  *  contain the MAC address but RAR[1-6] are reserved for manageability (ME).
  *  Use SHRA[0-3] in place of those reserved for ME.
  **/
-static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index)
+static int e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index)
 {
 	u32 rar_low, rar_high;
 
@@ -1689,7 +1692,7 @@ static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index)
 		e1e_flush();
 		ew32(RAH(index), rar_high);
 		e1e_flush();
-		return;
+		return 0;
 	}
 
 	/* RAR[1-6] are owned by manageability.  Skip those and program the
@@ -1712,7 +1715,7 @@ static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index)
 		/* verify the register updates */
 		if ((er32(SHRAL(index - 1)) == rar_low) &&
 		    (er32(SHRAH(index - 1)) == rar_high))
-			return;
+			return 0;
 
 		e_dbg("SHRA[%d] might be locked by ME - FWSM=0x%8.8x\n",
 		      (index - 1), er32(FWSM));
@@ -1720,6 +1723,43 @@ static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index)
 
 out:
 	e_dbg("Failed to write receive address at index %d\n", index);
+	return -E1000_ERR_CONFIG;
+}
+
+/**
+ *  e1000_rar_get_count_pch_lpt - Get the number of available SHRA
+ *  @hw: pointer to the HW structure
+ *
+ *  Get the number of available receive registers that the Host can
+ *  program. SHRA[0-10] are the shared receive address registers
+ *  that are shared between the Host and manageability engine (ME).
+ *  ME can reserve any number of addresses and the host needs to be
+ *  able to tell how many available registers it has access to.
+ **/
+static u32 e1000_rar_get_count_pch_lpt(struct e1000_hw *hw)
+{
+	u32 wlock_mac;
+	u32 num_entries;
+
+	wlock_mac = er32(FWSM) & E1000_FWSM_WLOCK_MAC_MASK;
+	wlock_mac >>= E1000_FWSM_WLOCK_MAC_SHIFT;
+
+	switch (wlock_mac) {
+	case 0:
+		/* All SHRA[0..10] and RAR[0] available */
+		num_entries = hw->mac.rar_entry_count;
+		break;
+	case 1:
+		/* Only RAR[0] available */
+		num_entries = 1;
+		break;
+	default:
+		/* SHRA[0..(wlock_mac - 1)] available + RAR[0] */
+		num_entries = wlock_mac + 1;
+		break;
+	}
+
+	return num_entries;
 }
 
 /**
@@ -1733,7 +1773,7 @@ out:
  *  contain the MAC address. SHRA[0-10] are the shared receive address
  *  registers that are shared between the Host and manageability engine (ME).
  **/
-static void e1000_rar_set_pch_lpt(struct e1000_hw *hw, u8 *addr, u32 index)
+static int e1000_rar_set_pch_lpt(struct e1000_hw *hw, u8 *addr, u32 index)
 {
 	u32 rar_low, rar_high;
 	u32 wlock_mac;
@@ -1755,7 +1795,7 @@ static void e1000_rar_set_pch_lpt(struct e1000_hw *hw, u8 *addr, u32 index)
 		e1e_flush();
 		ew32(RAH(index), rar_high);
 		e1e_flush();
-		return;
+		return 0;
 	}
 
 	/* The manageability engine (ME) can lock certain SHRAR registers that
@@ -1787,12 +1827,13 @@ static void e1000_rar_set_pch_lpt(struct e1000_hw *hw, u8 *addr, u32 index)
 			/* verify the register updates */
 			if ((er32(SHRAL_PCH_LPT(index - 1)) == rar_low) &&
 			    (er32(SHRAH_PCH_LPT(index - 1)) == rar_high))
-				return;
+				return 0;
 		}
 	}
 
 out:
 	e_dbg("Failed to write receive address at index %d\n", index);
+	return -E1000_ERR_CONFIG;
 }
 
 /**
@@ -4976,6 +5017,7 @@ static const struct e1000_mac_operations ich8_mac_ops = {
 	/* id_led_init dependent on mac type */
 	.config_collision_dist	= e1000e_config_collision_dist_generic,
 	.rar_set		= e1000e_rar_set_generic,
+	.rar_get_count		= e1000e_rar_get_count_generic,
 };
 
 static const struct e1000_phy_operations ich8_phy_ops = {
diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index baa0a466d1d..8c386f3a15e 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -211,6 +211,11 @@ s32 e1000_check_alt_mac_addr_generic(struct e1000_hw *hw)
 	return 0;
 }
 
+u32 e1000e_rar_get_count_generic(struct e1000_hw *hw)
+{
+	return hw->mac.rar_entry_count;
+}
+
 /**
  *  e1000e_rar_set_generic - Set receive address register
  *  @hw: pointer to the HW structure
@@ -220,7 +225,7 @@ s32 e1000_check_alt_mac_addr_generic(struct e1000_hw *hw)
  *  Sets the receive address array register at index to the address passed
  *  in by addr.
  **/
-void e1000e_rar_set_generic(struct e1000_hw *hw, u8 *addr, u32 index)
+int e1000e_rar_set_generic(struct e1000_hw *hw, u8 *addr, u32 index)
 {
 	u32 rar_low, rar_high;
 
@@ -244,6 +249,8 @@ void e1000e_rar_set_generic(struct e1000_hw *hw, u8 *addr, u32 index)
 	e1e_flush();
 	ew32(RAH(index), rar_high);
 	e1e_flush();
+
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/e1000e/mac.h b/drivers/net/ethernet/intel/e1000e/mac.h
index 4e81c2825b7..0513d90cdee 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.h
+++ b/drivers/net/ethernet/intel/e1000e/mac.h
@@ -61,7 +61,8 @@ void e1000e_update_adaptive(struct e1000_hw *hw);
 void e1000_write_vfta_generic(struct e1000_hw *hw, u32 offset, u32 value);
 
 void e1000_set_lan_id_multi_port_pcie(struct e1000_hw *hw);
-void e1000e_rar_set_generic(struct e1000_hw *hw, u8 *addr, u32 index);
+u32 e1000e_rar_get_count_generic(struct e1000_hw *hw);
+int e1000e_rar_set_generic(struct e1000_hw *hw, u8 *addr, u32 index);
 void e1000e_config_collision_dist_generic(struct e1000_hw *hw);
 
 #endif
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 3e69386add0..201cc93f362 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -124,6 +124,36 @@ static const struct e1000_reg_info e1000_reg_info_tbl[] = {
 };
 
 /**
+ * __ew32_prepare - prepare to write to MAC CSR register on certain parts
+ * @hw: pointer to the HW structure
+ *
+ * When updating the MAC CSR registers, the Manageability Engine (ME) could
+ * be accessing the registers at the same time.  Normally, this is handled in
+ * h/w by an arbiter but on some parts there is a bug that acknowledges Host
+ * accesses later than it should which could result in the register to have
+ * an incorrect value.  Workaround this by checking the FWSM register which
+ * has bit 24 set while ME is accessing MAC CSR registers, wait if it is set
+ * and try again a number of times.
+ **/
+s32 __ew32_prepare(struct e1000_hw *hw)
+{
+	s32 i = E1000_ICH_FWSM_PCIM2PCI_COUNT;
+
+	while ((er32(FWSM) & E1000_ICH_FWSM_PCIM2PCI) && --i)
+		udelay(50);
+
+	return i;
+}
+
+void __ew32(struct e1000_hw *hw, unsigned long reg, u32 val)
+{
+	if (hw->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA)
+		__ew32_prepare(hw);
+
+	writel(val, hw->hw_addr + reg);
+}
+
+/**
  * e1000_regdump - register printout routine
  * @hw: pointer to the HW structure
  * @reginfo: pointer to the register info table
@@ -599,6 +629,7 @@ static void e1000e_update_rdt_wa(struct e1000_ring *rx_ring, unsigned int i)
 
 	if (unlikely(!ret_val && (i != readl(rx_ring->tail)))) {
 		u32 rctl = er32(RCTL);
+
 		ew32(RCTL, rctl & ~E1000_RCTL_EN);
 		e_err("ME firmware caused invalid RDT - resetting\n");
 		schedule_work(&adapter->reset_task);
@@ -615,6 +646,7 @@ static void e1000e_update_tdt_wa(struct e1000_ring *tx_ring, unsigned int i)
 
 	if (unlikely(!ret_val && (i != readl(tx_ring->tail)))) {
 		u32 tctl = er32(TCTL);
+
 		ew32(TCTL, tctl & ~E1000_TCTL_EN);
 		e_err("ME firmware caused invalid TDT - resetting\n");
 		schedule_work(&adapter->reset_task);
@@ -1198,6 +1230,7 @@ static bool e1000_clean_tx_irq(struct e1000_ring *tx_ring)
 	while ((eop_desc->upper.data & cpu_to_le32(E1000_TXD_STAT_DD)) &&
 	       (count < tx_ring->count)) {
 		bool cleaned = false;
+
 		rmb();		/* read buffer_info after eop_desc */
 		for (; !cleaned; count++) {
 			tx_desc = E1000_TX_DESC(*tx_ring, i);
@@ -1753,6 +1786,7 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data)
 		    adapter->flags & FLAG_RX_NEEDS_RESTART) {
 			/* disable receives */
 			u32 rctl = er32(RCTL);
+
 			ew32(RCTL, rctl & ~E1000_RCTL_EN);
 			adapter->flags |= FLAG_RESTART_NOW;
 		}
@@ -1960,6 +1994,7 @@ static void e1000_configure_msix(struct e1000_adapter *adapter)
 	/* Workaround issue with spurious interrupts on 82574 in MSI-X mode */
 	if (hw->mac.type == e1000_82574) {
 		u32 rfctl = er32(RFCTL);
+
 		rfctl |= E1000_RFCTL_ACK_DIS;
 		ew32(RFCTL, rfctl);
 	}
@@ -2204,6 +2239,7 @@ static void e1000_irq_disable(struct e1000_adapter *adapter)
 
 	if (adapter->msix_entries) {
 		int i;
+
 		for (i = 0; i < adapter->num_vectors; i++)
 			synchronize_irq(adapter->msix_entries[i].vector);
 	} else {
@@ -2921,6 +2957,7 @@ static void e1000_configure_tx(struct e1000_adapter *adapter)
 
 	if (adapter->flags2 & FLAG2_DMA_BURST) {
 		u32 txdctl = er32(TXDCTL(0));
+
 		txdctl &= ~(E1000_TXDCTL_PTHRESH | E1000_TXDCTL_HTHRESH |
 			    E1000_TXDCTL_WTHRESH);
 		/* set up some performance related parameters to encourage the
@@ -3239,6 +3276,7 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
 
 		if (adapter->flags & FLAG_IS_ICH) {
 			u32 rxdctl = er32(RXDCTL(0));
+
 			ew32(RXDCTL(0), rxdctl | 0x3);
 		}
 
@@ -3303,9 +3341,11 @@ static int e1000e_write_uc_addr_list(struct net_device *netdev)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	unsigned int rar_entries = hw->mac.rar_entry_count;
+	unsigned int rar_entries;
 	int count = 0;
 
+	rar_entries = hw->mac.ops.rar_get_count(hw);
+
 	/* save a rar entry for our hardware address */
 	rar_entries--;
 
@@ -3324,9 +3364,13 @@ static int e1000e_write_uc_addr_list(struct net_device *netdev)
 		 * combining
 		 */
 		netdev_for_each_uc_addr(ha, netdev) {
+			int rval;
+
 			if (!rar_entries)
 				break;
-			hw->mac.ops.rar_set(hw, ha->addr, rar_entries--);
+			rval = hw->mac.ops.rar_set(hw, ha->addr, rar_entries--);
+			if (rval < 0)
+				return -ENOMEM;
 			count++;
 		}
 	}
@@ -4085,12 +4129,37 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc)
 	struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
 						     cc);
 	struct e1000_hw *hw = &adapter->hw;
-	cycle_t systim;
+	cycle_t systim, systim_next;
 
 	/* latch SYSTIMH on read of SYSTIML */
 	systim = (cycle_t)er32(SYSTIML);
 	systim |= (cycle_t)er32(SYSTIMH) << 32;
 
+	if ((hw->mac.type == e1000_82574) || (hw->mac.type == e1000_82583)) {
+		u64 incvalue, time_delta, rem, temp;
+		int i;
+
+		/* errata for 82574/82583 possible bad bits read from SYSTIMH/L
+		 * check to see that the time is incrementing at a reasonable
+		 * rate and is a multiple of incvalue
+		 */
+		incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK;
+		for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) {
+			/* latch SYSTIMH on read of SYSTIML */
+			systim_next = (cycle_t)er32(SYSTIML);
+			systim_next |= (cycle_t)er32(SYSTIMH) << 32;
+
+			time_delta = systim_next - systim;
+			temp = time_delta;
+			rem = do_div(temp, incvalue);
+
+			systim = systim_next;
+
+			if ((time_delta < E1000_82574_SYSTIM_EPSILON) &&
+			    (rem == 0))
+				break;
+		}
+	}
 	return systim;
 }
 
@@ -4491,7 +4560,7 @@ static void e1000e_update_phy_task(struct work_struct *work)
 	e1000_get_phy_info(hw);
 
 	/* Enable EEE on 82579 after link up */
-	if (hw->phy.type == e1000_phy_82579)
+	if (hw->phy.type >= e1000_phy_82579)
 		e1000_set_eee_pchlan(hw);
 }
 
@@ -4695,6 +4764,7 @@ static void e1000e_update_stats(struct e1000_adapter *adapter)
 	/* Correctable ECC Errors */
 	if (hw->mac.type == e1000_pch_lpt) {
 		u32 pbeccsts = er32(PBECCSTS);
+
 		adapter->corr_errors +=
 		    pbeccsts & E1000_PBECCSTS_CORR_ERR_CNT_MASK;
 		adapter->uncorr_errors +=
@@ -4808,6 +4878,7 @@ static void e1000e_enable_receives(struct e1000_adapter *adapter)
 	    (adapter->flags & FLAG_RESTART_NOW)) {
 		struct e1000_hw *hw = &adapter->hw;
 		u32 rctl = er32(RCTL);
+
 		ew32(RCTL, rctl | E1000_RCTL_EN);
 		adapter->flags &= ~FLAG_RESTART_NOW;
 	}
@@ -4930,6 +5001,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 			if ((adapter->flags & FLAG_TARC_SPEED_MODE_BIT) &&
 			    !txb2b) {
 				u32 tarc0;
+
 				tarc0 = er32(TARC(0));
 				tarc0 &= ~SPEED_MODE_BIT;
 				ew32(TARC(0), tarc0);
@@ -5170,7 +5242,7 @@ static bool e1000_tx_csum(struct e1000_ring *tx_ring, struct sk_buff *skb)
 	__be16 protocol;
 
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
-		return 0;
+		return false;
 
 	if (skb->protocol == cpu_to_be16(ETH_P_8021Q))
 		protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto;
@@ -5215,7 +5287,7 @@ static bool e1000_tx_csum(struct e1000_ring *tx_ring, struct sk_buff *skb)
 		i = 0;
 	tx_ring->next_to_use = i;
 
-	return 1;
+	return true;
 }
 
 static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb,
@@ -6209,6 +6281,7 @@ static int __e1000_resume(struct pci_dev *pdev)
 		e1e_wphy(&adapter->hw, BM_WUS, ~0);
 	} else {
 		u32 wus = er32(WUS);
+
 		if (wus) {
 			e_info("MAC Wakeup cause - %s\n",
 			       wus & E1000_WUS_EX ? "Unicast Packet" :
@@ -7027,7 +7100,7 @@ static const struct pci_error_handlers e1000_err_handler = {
 	.resume = e1000_io_resume,
 };
 
-static DEFINE_PCI_DEVICE_TABLE(e1000_pci_tbl) = {
+static const struct pci_device_id e1000_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_COPPER), board_82571 },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_FIBER), board_82571 },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_82571EB_QUAD_COPPER), board_82571 },
@@ -7144,6 +7217,7 @@ static struct pci_driver e1000_driver = {
 static int __init e1000_init_module(void)
 {
 	int ret;
+
 	pr_info("Intel(R) PRO/1000 Network Driver - %s\n",
 		e1000e_driver_version);
 	pr_info("Copyright(c) 1999 - 2014 Intel Corporation.\n");
diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c
index a9a976f04bf..b1f212b7baf 100644
--- a/drivers/net/ethernet/intel/e1000e/nvm.c
+++ b/drivers/net/ethernet/intel/e1000e/nvm.c
@@ -398,6 +398,7 @@ s32 e1000e_write_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data)
 		/* Loop to allow for up to whole page write of eeprom */
 		while (widx < words) {
 			u16 word_out = data[widx];
+
 			word_out = (word_out >> 8) | (word_out << 8);
 			e1000_shift_out_eec_bits(hw, word_out, 16);
 			widx++;
diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c
index d0ac0f3249c..aa1923f7ebd 100644
--- a/drivers/net/ethernet/intel/e1000e/param.c
+++ b/drivers/net/ethernet/intel/e1000e/param.c
@@ -436,6 +436,7 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 
 		if (num_IntMode > bd) {
 			unsigned int int_mode = IntMode[bd];
+
 			e1000_validate_option(&int_mode, &opt, adapter);
 			adapter->int_mode = int_mode;
 		} else {
@@ -457,6 +458,7 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 
 		if (num_SmartPowerDownEnable > bd) {
 			unsigned int spd = SmartPowerDownEnable[bd];
+
 			e1000_validate_option(&spd, &opt, adapter);
 			if ((adapter->flags & FLAG_HAS_SMART_POWER_DOWN) && spd)
 				adapter->flags |= FLAG_SMART_POWER_DOWN;
@@ -473,6 +475,7 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 
 		if (num_CrcStripping > bd) {
 			unsigned int crc_stripping = CrcStripping[bd];
+
 			e1000_validate_option(&crc_stripping, &opt, adapter);
 			if (crc_stripping == OPTION_ENABLED) {
 				adapter->flags2 |= FLAG2_CRC_STRIPPING;
@@ -495,6 +498,7 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 
 		if (num_KumeranLockLoss > bd) {
 			unsigned int kmrn_lock_loss = KumeranLockLoss[bd];
+
 			e1000_validate_option(&kmrn_lock_loss, &opt, adapter);
 			enabled = kmrn_lock_loss;
 		}
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index 00b3fc98bf3..b2005e13fb0 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -2896,6 +2896,7 @@ static s32 __e1000_write_phy_reg_hv(struct e1000_hw *hw, u32 offset, u16 data,
 		    (hw->phy.addr == 2) &&
 		    !(MAX_PHY_REG_ADDRESS & reg) && (data & (1 << 11))) {
 			u16 data2 = 0x7EFF;
+
 			ret_val = e1000_access_phy_debug_regs_hv(hw,
 								 (1 << 6) | 0x3,
 								 &data2, false);
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index beb7b4393a6..65985846345 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -72,6 +72,7 @@
 #define I40E_MIN_NUM_DESCRIPTORS      64
 #define I40E_MIN_MSIX                 2
 #define I40E_DEFAULT_NUM_VMDQ_VSI     8 /* max 256 VSIs */
+#define I40E_MIN_VSI_ALLOC            51 /* LAN, ATR, FCOE, 32 VF, 16 VMDQ */
 #define I40E_DEFAULT_QUEUES_PER_VMDQ  2 /* max 16 qps */
 #define I40E_DEFAULT_QUEUES_PER_VF    4
 #define I40E_DEFAULT_QUEUES_PER_TC    1 /* should be a power of 2 */
@@ -97,10 +98,6 @@
 #define STRINGIFY(foo)  #foo
 #define XSTRINGIFY(bar) STRINGIFY(bar)
 
-#ifndef ARCH_HAS_PREFETCH
-#define prefetch(X)
-#endif
-
 #define I40E_RX_DESC(R, i)			\
 	((ring_is_16byte_desc_enabled(R))	\
 		? (union i40e_32byte_rx_desc *)	\
@@ -157,11 +154,23 @@ struct i40e_lump_tracking {
 #define I40E_FDIR_BUFFER_FULL_MARGIN	10
 #define I40E_FDIR_BUFFER_HEAD_ROOM	200
 
+enum i40e_fd_stat_idx {
+	I40E_FD_STAT_ATR,
+	I40E_FD_STAT_SB,
+	I40E_FD_STAT_PF_COUNT
+};
+#define I40E_FD_STAT_PF_IDX(pf_id) ((pf_id) * I40E_FD_STAT_PF_COUNT)
+#define I40E_FD_ATR_STAT_IDX(pf_id) \
+			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_ATR)
+#define I40E_FD_SB_STAT_IDX(pf_id)  \
+			(I40E_FD_STAT_PF_IDX(pf_id) + I40E_FD_STAT_SB)
+
 struct i40e_fdir_filter {
 	struct hlist_node fdir_node;
 	/* filter ipnut set */
 	u8 flow_type;
 	u8 ip4_proto;
+	/* TX packet view of src and dst */
 	__be32 dst_ip[4];
 	__be32 src_ip[4];
 	__be16 src_port;
@@ -205,7 +214,6 @@ struct i40e_pf {
 	unsigned long state;
 	unsigned long link_check_timeout;
 	struct msix_entry *msix_entries;
-	u16 num_msix_entries;
 	bool fc_autoneg_status;
 
 	u16 eeprom_version;
@@ -220,11 +228,14 @@ struct i40e_pf {
 	u16 rss_size;              /* num queues in the RSS array */
 	u16 rss_size_max;          /* HW defined max RSS queues */
 	u16 fdir_pf_filter_count;  /* num of guaranteed filters for this PF */
+	u16 num_alloc_vsi;         /* num VSIs this driver supports */
 	u8 atr_sample_rate;
 	bool wol_en;
 
 	struct hlist_head fdir_filter_list;
 	u16 fdir_pf_active_filters;
+	u16 fd_sb_cnt_idx;
+	u16 fd_atr_cnt_idx;
 
 #ifdef CONFIG_I40E_VXLAN
 	__be16  vxlan_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS];
@@ -266,6 +277,7 @@ struct i40e_pf {
 #ifdef CONFIG_I40E_VXLAN
 #define I40E_FLAG_VXLAN_FILTER_SYNC            (u64)(1 << 27)
 #endif
+#define I40E_FLAG_DCB_CAPABLE                  (u64)(1 << 29)
 
 	/* tracks features that get auto disabled by errors */
 	u64 auto_disable_flags;
@@ -300,7 +312,6 @@ struct i40e_pf {
 	u16 pf_seid;
 	u16 main_vsi_seid;
 	u16 mac_seid;
-	struct i40e_aqc_get_switch_config_data *sw_config;
 	struct kobject *switch_kobj;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *i40e_dbg_pf;
@@ -329,9 +340,7 @@ struct i40e_pf {
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_caps;
 	struct sk_buff *ptp_tx_skb;
-	struct work_struct ptp_tx_work;
 	struct hwtstamp_config tstamp_config;
-	unsigned long ptp_tx_start;
 	unsigned long last_rx_ptp_check;
 	spinlock_t tmreg_lock; /* Used to protect the device time registers. */
 	u64 ptp_base_adj;
@@ -420,6 +429,7 @@ struct i40e_vsi {
 	struct i40e_q_vector **q_vectors;
 	int num_q_vectors;
 	int base_vector;
+	bool irqs_ready;
 
 	u16 seid;            /* HW index of this VSI (absolute index) */
 	u16 id;              /* VSI number */
@@ -540,6 +550,15 @@ static inline bool i40e_rx_is_programming_status(u64 qw)
 		(qw >> I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT);
 }
 
+/**
+ * i40e_get_fd_cnt_all - get the total FD filter space available
+ * @pf: pointer to the pf struct
+ **/
+static inline int i40e_get_fd_cnt_all(struct i40e_pf *pf)
+{
+	return pf->hw.fdir_shared_filter_count + pf->fdir_pf_filter_count;
+}
+
 /* needed by i40e_ethtool.c */
 int i40e_up(struct i40e_vsi *vsi);
 void i40e_down(struct i40e_vsi *vsi);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index ed3902bf249..7a027499fc5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -33,6 +33,16 @@
 static void i40e_resume_aq(struct i40e_hw *hw);
 
 /**
+ * i40e_is_nvm_update_op - return true if this is an NVM update operation
+ * @desc: API request descriptor
+ **/
+static inline bool i40e_is_nvm_update_op(struct i40e_aq_desc *desc)
+{
+	return (desc->opcode == i40e_aqc_opc_nvm_erase) ||
+	       (desc->opcode == i40e_aqc_opc_nvm_update);
+}
+
+/**
  *  i40e_adminq_init_regs - Initialize AdminQ registers
  *  @hw: pointer to the hardware structure
  *
@@ -281,8 +291,11 @@ static void i40e_free_asq_bufs(struct i40e_hw *hw)
  *
  *  Configure base address and length registers for the transmit queue
  **/
-static void i40e_config_asq_regs(struct i40e_hw *hw)
+static i40e_status i40e_config_asq_regs(struct i40e_hw *hw)
 {
+	i40e_status ret_code = 0;
+	u32 reg = 0;
+
 	if (hw->mac.type == I40E_MAC_VF) {
 		/* configure the transmit queue */
 		wr32(hw, I40E_VF_ATQBAH1,
@@ -291,6 +304,7 @@ static void i40e_config_asq_regs(struct i40e_hw *hw)
 		    lower_32_bits(hw->aq.asq.desc_buf.pa));
 		wr32(hw, I40E_VF_ATQLEN1, (hw->aq.num_asq_entries |
 					  I40E_VF_ATQLEN1_ATQENABLE_MASK));
+		reg = rd32(hw, I40E_VF_ATQBAL1);
 	} else {
 		/* configure the transmit queue */
 		wr32(hw, I40E_PF_ATQBAH,
@@ -299,7 +313,14 @@ static void i40e_config_asq_regs(struct i40e_hw *hw)
 		    lower_32_bits(hw->aq.asq.desc_buf.pa));
 		wr32(hw, I40E_PF_ATQLEN, (hw->aq.num_asq_entries |
 					  I40E_PF_ATQLEN_ATQENABLE_MASK));
+		reg = rd32(hw, I40E_PF_ATQBAL);
 	}
+
+	/* Check one register to verify that config was applied */
+	if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa))
+		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+
+	return ret_code;
 }
 
 /**
@@ -308,8 +329,11 @@ static void i40e_config_asq_regs(struct i40e_hw *hw)
  *
  * Configure base address and length registers for the receive (event queue)
  **/
-static void i40e_config_arq_regs(struct i40e_hw *hw)
+static i40e_status i40e_config_arq_regs(struct i40e_hw *hw)
 {
+	i40e_status ret_code = 0;
+	u32 reg = 0;
+
 	if (hw->mac.type == I40E_MAC_VF) {
 		/* configure the receive queue */
 		wr32(hw, I40E_VF_ARQBAH1,
@@ -318,6 +342,7 @@ static void i40e_config_arq_regs(struct i40e_hw *hw)
 		    lower_32_bits(hw->aq.arq.desc_buf.pa));
 		wr32(hw, I40E_VF_ARQLEN1, (hw->aq.num_arq_entries |
 					  I40E_VF_ARQLEN1_ARQENABLE_MASK));
+		reg = rd32(hw, I40E_VF_ARQBAL1);
 	} else {
 		/* configure the receive queue */
 		wr32(hw, I40E_PF_ARQBAH,
@@ -326,10 +351,17 @@ static void i40e_config_arq_regs(struct i40e_hw *hw)
 		    lower_32_bits(hw->aq.arq.desc_buf.pa));
 		wr32(hw, I40E_PF_ARQLEN, (hw->aq.num_arq_entries |
 					  I40E_PF_ARQLEN_ARQENABLE_MASK));
+		reg = rd32(hw, I40E_PF_ARQBAL);
 	}
 
 	/* Update tail in the HW to post pre-allocated buffers */
 	wr32(hw, hw->aq.arq.tail, hw->aq.num_arq_entries - 1);
+
+	/* Check one register to verify that config was applied */
+	if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa))
+		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+
+	return ret_code;
 }
 
 /**
@@ -377,7 +409,9 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw)
 		goto init_adminq_free_rings;
 
 	/* initialize base registers */
-	i40e_config_asq_regs(hw);
+	ret_code = i40e_config_asq_regs(hw);
+	if (ret_code)
+		goto init_adminq_free_rings;
 
 	/* success! */
 	goto init_adminq_exit;
@@ -434,7 +468,9 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw)
 		goto init_adminq_free_rings;
 
 	/* initialize base registers */
-	i40e_config_arq_regs(hw);
+	ret_code = i40e_config_arq_regs(hw);
+	if (ret_code)
+		goto init_adminq_free_rings;
 
 	/* success! */
 	goto init_adminq_exit;
@@ -577,14 +613,14 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw)
 	i40e_read_nvm_word(hw, I40E_SR_NVM_EETRACK_HI, &eetrack_hi);
 	hw->nvm.eetrack = (eetrack_hi << 16) | eetrack_lo;
 
-	if (hw->aq.api_maj_ver != I40E_FW_API_VERSION_MAJOR ||
-	    hw->aq.api_min_ver > I40E_FW_API_VERSION_MINOR) {
+	if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) {
 		ret_code = I40E_ERR_FIRMWARE_API_VERSION;
 		goto init_adminq_free_arq;
 	}
 
 	/* pre-emptive resource lock release */
 	i40e_aq_release_resource(hw, I40E_NVM_RESOURCE_ID, 0, NULL);
+	hw->aq.nvm_busy = false;
 
 	ret_code = i40e_aq_set_hmc_resource_profile(hw,
 						    I40E_HMC_PROFILE_DEFAULT,
@@ -708,6 +744,12 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 		goto asq_send_command_exit;
 	}
 
+	if (i40e_is_nvm_update_op(desc) && hw->aq.nvm_busy) {
+		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: NVM busy.\n");
+		status = I40E_ERR_NVM;
+		goto asq_send_command_exit;
+	}
+
 	details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
 	if (cmd_details) {
 		*details = *cmd_details;
@@ -835,6 +877,9 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
 	}
 
+	if (i40e_is_nvm_update_op(desc))
+		hw->aq.nvm_busy = true;
+
 	/* update the error if time out occurred */
 	if ((!cmd_completed) &&
 	    (!details->async && !details->postpone)) {
@@ -929,6 +974,9 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
 			       e->msg_size);
 	}
 
+	if (i40e_is_nvm_update_op(&e->desc))
+		hw->aq.nvm_busy = false;
+
 	/* Restore the original datalen and buffer address in the desc,
 	 * FW updates datalen to indicate the event message
 	 * size
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
index 993f7685a91..b1552fbc48a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
@@ -90,6 +90,7 @@ struct i40e_adminq_info {
 	u16 fw_min_ver;                 /* firmware minor version */
 	u16 api_maj_ver;                /* api major version */
 	u16 api_min_ver;                /* api minor version */
+	bool nvm_busy;
 
 	struct mutex asq_mutex; /* Send queue lock */
 	struct mutex arq_mutex; /* Receive queue lock */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 7b6374a8f8d..15f289f2917 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -34,7 +34,7 @@
  */
 
 #define I40E_FW_API_VERSION_MAJOR  0x0001
-#define I40E_FW_API_VERSION_MINOR  0x0001
+#define I40E_FW_API_VERSION_MINOR  0x0002
 
 struct i40e_aq_desc {
 	__le16 flags;
@@ -123,6 +123,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_get_version      = 0x0001,
 	i40e_aqc_opc_driver_version   = 0x0002,
 	i40e_aqc_opc_queue_shutdown   = 0x0003,
+	i40e_aqc_opc_set_pf_context   = 0x0004,
 
 	/* resource ownership */
 	i40e_aqc_opc_request_resource = 0x0008,
@@ -182,9 +183,6 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_add_mirror_rule    = 0x0260,
 	i40e_aqc_opc_delete_mirror_rule = 0x0261,
 
-	i40e_aqc_opc_set_storm_control_config = 0x0280,
-	i40e_aqc_opc_get_storm_control_config = 0x0281,
-
 	/* DCB commands */
 	i40e_aqc_opc_dcb_ignore_pfc = 0x0301,
 	i40e_aqc_opc_dcb_updated    = 0x0302,
@@ -207,6 +205,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_query_switching_comp_bw_config        = 0x041A,
 	i40e_aqc_opc_suspend_port_tx                       = 0x041B,
 	i40e_aqc_opc_resume_port_tx                        = 0x041C,
+	i40e_aqc_opc_configure_partition_bw                = 0x041D,
 
 	/* hmc */
 	i40e_aqc_opc_query_hmc_resource_profile = 0x0500,
@@ -224,13 +223,15 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_get_partner_advt    = 0x0616,
 	i40e_aqc_opc_set_lb_modes        = 0x0618,
 	i40e_aqc_opc_get_phy_wol_caps    = 0x0621,
-	i40e_aqc_opc_set_phy_reset       = 0x0622,
+	i40e_aqc_opc_set_phy_debug	 = 0x0622,
 	i40e_aqc_opc_upload_ext_phy_fm   = 0x0625,
 
 	/* NVM commands */
-	i40e_aqc_opc_nvm_read   = 0x0701,
-	i40e_aqc_opc_nvm_erase  = 0x0702,
-	i40e_aqc_opc_nvm_update = 0x0703,
+	i40e_aqc_opc_nvm_read         = 0x0701,
+	i40e_aqc_opc_nvm_erase        = 0x0702,
+	i40e_aqc_opc_nvm_update       = 0x0703,
+	i40e_aqc_opc_nvm_config_read  = 0x0704,
+	i40e_aqc_opc_nvm_config_write = 0x0705,
 
 	/* virtualization commands */
 	i40e_aqc_opc_send_msg_to_pf   = 0x0801,
@@ -272,8 +273,6 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_debug_set_mode         = 0xFF01,
 	i40e_aqc_opc_debug_read_reg         = 0xFF03,
 	i40e_aqc_opc_debug_write_reg        = 0xFF04,
-	i40e_aqc_opc_debug_read_reg_sg      = 0xFF05,
-	i40e_aqc_opc_debug_write_reg_sg     = 0xFF06,
 	i40e_aqc_opc_debug_modify_reg       = 0xFF07,
 	i40e_aqc_opc_debug_dump_internals   = 0xFF08,
 	i40e_aqc_opc_debug_modify_internals = 0xFF09,
@@ -341,6 +340,14 @@ struct i40e_aqc_queue_shutdown {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown);
 
+/* Set PF context (0x0004, direct) */
+struct i40e_aqc_set_pf_context {
+	u8	pf_id;
+	u8	reserved[15];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_pf_context);
+
 /* Request resource ownership (direct 0x0008)
  * Release resource ownership (direct 0x0009)
  */
@@ -1289,27 +1296,6 @@ struct i40e_aqc_add_delete_mirror_rule_completion {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion);
 
-/* Set Storm Control Configuration (direct 0x0280)
- * Get Storm Control Configuration (direct 0x0281)
- *    the command and response use the same descriptor structure
- */
-struct i40e_aqc_set_get_storm_control_config {
-	__le32 broadcast_threshold;
-	__le32 multicast_threshold;
-	__le32 control_flags;
-#define I40E_AQC_STORM_CONTROL_MDIPW            0x01
-#define I40E_AQC_STORM_CONTROL_MDICW            0x02
-#define I40E_AQC_STORM_CONTROL_BDIPW            0x04
-#define I40E_AQC_STORM_CONTROL_BDICW            0x08
-#define I40E_AQC_STORM_CONTROL_BIDU             0x10
-#define I40E_AQC_STORM_CONTROL_INTERVAL_SHIFT   8
-#define I40E_AQC_STORM_CONTROL_INTERVAL_MASK    (0x3FF << \
-					I40E_AQC_STORM_CONTROL_INTERVAL_SHIFT)
-	u8     reserved[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_get_storm_control_config);
-
 /* DCB 0x03xx*/
 
 /* PFC Ignore (direct 0x0301)
@@ -1427,11 +1413,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_switching_comp_bw_limit);
 struct i40e_aqc_configure_switching_comp_ets_data {
 	u8     reserved[4];
 	u8     tc_valid_bits;
-	u8     reserved1;
+	u8     seepage;
+#define I40E_AQ_ETS_SEEPAGE_EN_MASK     0x1
 	u8     tc_strict_priority_flags;
-	u8     reserved2[17];
+	u8     reserved1[17];
 	u8     tc_bw_share_credits[8];
-	u8     reserved3[96];
+	u8     reserved2[96];
 };
 
 /* Configure Switching Component Bandwidth Limits per Tc (indirect 0x0416) */
@@ -1499,6 +1486,15 @@ struct i40e_aqc_query_switching_comp_bw_config_resp {
  * (direct 0x041B and 0x041C) uses the generic SEID struct
  */
 
+/* Configure partition BW
+ * (indirect 0x041D)
+ */
+struct i40e_aqc_configure_partition_bw_data {
+	__le16 pf_valid_bits;
+	u8     min_bw[16];      /* guaranteed bandwidth */
+	u8     max_bw[16];      /* bandwidth limit */
+};
+
 /* Get and set the active HMC resource profile and status.
  * (direct 0x0500) and (direct 0x0501)
  */
@@ -1539,6 +1535,8 @@ enum i40e_aq_phy_type {
 	I40E_PHY_TYPE_XLPPI			= 0x9,
 	I40E_PHY_TYPE_40GBASE_CR4_CU		= 0xA,
 	I40E_PHY_TYPE_10GBASE_CR1_CU		= 0xB,
+	I40E_PHY_TYPE_10GBASE_AOC		= 0xC,
+	I40E_PHY_TYPE_40GBASE_AOC		= 0xD,
 	I40E_PHY_TYPE_100BASE_TX		= 0x11,
 	I40E_PHY_TYPE_1000BASE_T		= 0x12,
 	I40E_PHY_TYPE_10GBASE_T			= 0x13,
@@ -1549,7 +1547,10 @@ enum i40e_aq_phy_type {
 	I40E_PHY_TYPE_40GBASE_CR4		= 0x18,
 	I40E_PHY_TYPE_40GBASE_SR4		= 0x19,
 	I40E_PHY_TYPE_40GBASE_LR4		= 0x1A,
-	I40E_PHY_TYPE_20GBASE_KR2		= 0x1B,
+	I40E_PHY_TYPE_1000BASE_SX		= 0x1B,
+	I40E_PHY_TYPE_1000BASE_LX		= 0x1C,
+	I40E_PHY_TYPE_1000BASE_T_OPTICAL	= 0x1D,
+	I40E_PHY_TYPE_20GBASE_KR2		= 0x1E,
 	I40E_PHY_TYPE_MAX
 };
 
@@ -1583,11 +1584,8 @@ struct i40e_aq_get_phy_abilities_resp {
 #define I40E_AQ_PHY_FLAG_PAUSE_TX         0x01
 #define I40E_AQ_PHY_FLAG_PAUSE_RX         0x02
 #define I40E_AQ_PHY_FLAG_LOW_POWER        0x04
-#define I40E_AQ_PHY_FLAG_AN_SHIFT         3
-#define I40E_AQ_PHY_FLAG_AN_MASK          (0x3 << I40E_AQ_PHY_FLAG_AN_SHIFT)
-#define I40E_AQ_PHY_FLAG_AN_OFF           0x00 /* link forced on */
-#define I40E_AQ_PHY_FLAG_AN_OFF_LINK_DOWN 0x01
-#define I40E_AQ_PHY_FLAG_AN_ON            0x02
+#define I40E_AQ_PHY_LINK_ENABLED		  0x08
+#define I40E_AQ_PHY_AN_ENABLED			  0x10
 #define I40E_AQ_PHY_FLAG_MODULE_QUAL      0x20
 	__le16 eee_capability;
 #define I40E_AQ_EEE_100BASE_TX       0x0002
@@ -1696,6 +1694,7 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_LINK_TX_ACTIVE       0x00
 #define I40E_AQ_LINK_TX_DRAINED      0x01
 #define I40E_AQ_LINK_TX_FLUSHED      0x03
+#define I40E_AQ_LINK_FORCED_40G      0x10
 	u8     loopback;         /* use defines from i40e_aqc_set_lb_mode */
 	__le16 max_frame_size;
 	u8     config;
@@ -1747,14 +1746,21 @@ struct i40e_aqc_set_lb_mode {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_set_lb_mode);
 
-/* Set PHY Reset command (0x0622) */
-struct i40e_aqc_set_phy_reset {
-	u8     reset_flags;
-#define I40E_AQ_PHY_RESET_REQUEST  0x02
+/* Set PHY Debug command (0x0622) */
+struct i40e_aqc_set_phy_debug {
+	u8     command_flags;
+#define I40E_AQ_PHY_DEBUG_RESET_INTERNAL	0x02
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT	2
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_MASK	(0x03 << \
+					I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT)
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_NONE	0x00
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_HARD	0x01
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SOFT	0x02
+#define I40E_AQ_PHY_DEBUG_DISABLE_LINK_FW	0x10
 	u8     reserved[15];
 };
 
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_reset);
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_debug);
 
 enum i40e_aq_phy_reg_type {
 	I40E_AQC_PHY_REG_INTERNAL         = 0x1,
@@ -1779,6 +1785,47 @@ struct i40e_aqc_nvm_update {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update);
 
+/* NVM Config Read (indirect 0x0704) */
+struct i40e_aqc_nvm_config_read {
+	__le16 cmd_flags;
+#define ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK	1
+#define ANVM_READ_SINGLE_FEATURE		0
+#define ANVM_READ_MULTIPLE_FEATURES		1
+	__le16 element_count;
+	__le16 element_id;		/* Feature/field ID */
+	u8     reserved[2];
+	__le32 address_high;
+	__le32 address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_read);
+
+/* NVM Config Write (indirect 0x0705) */
+struct i40e_aqc_nvm_config_write {
+	__le16 cmd_flags;
+	__le16 element_count;
+	u8     reserved[4];
+	__le32 address_high;
+	__le32 address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_write);
+
+struct i40e_aqc_nvm_config_data_feature {
+	__le16 feature_id;
+	__le16 instance_id;
+	__le16 feature_options;
+	__le16 feature_selection;
+};
+
+struct i40e_aqc_nvm_config_data_immediate_field {
+#define ANVM_FEATURE_OR_IMMEDIATE_MASK	0x2
+	__le16 field_id;
+	__le16 instance_id;
+	__le16 field_options;
+	__le16 field_value;
+};
+
 /* Send to PF command (indirect 0x0801) id is only used by PF
  * Send to VF command (indirect 0x0802) id is only used by PF
  * Send to Peer PF command (indirect 0x0803)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 922cdcc45c5..6e65f19dd6e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -43,12 +43,10 @@ static i40e_status i40e_set_mac_type(struct i40e_hw *hw)
 	if (hw->vendor_id == PCI_VENDOR_ID_INTEL) {
 		switch (hw->device_id) {
 		case I40E_DEV_ID_SFP_XL710:
-		case I40E_DEV_ID_SFP_X710:
 		case I40E_DEV_ID_QEMU:
 		case I40E_DEV_ID_KX_A:
 		case I40E_DEV_ID_KX_B:
 		case I40E_DEV_ID_KX_C:
-		case I40E_DEV_ID_KX_D:
 		case I40E_DEV_ID_QSFP_A:
 		case I40E_DEV_ID_QSFP_B:
 		case I40E_DEV_ID_QSFP_C:
@@ -133,7 +131,11 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
  **/
 bool i40e_check_asq_alive(struct i40e_hw *hw)
 {
-	return !!(rd32(hw, hw->aq.asq.len) & I40E_PF_ATQLEN_ATQENABLE_MASK);
+	if (hw->aq.asq.len)
+		return !!(rd32(hw, hw->aq.asq.len) &
+			  I40E_PF_ATQLEN_ATQENABLE_MASK);
+	else
+		return false;
 }
 
 /**
@@ -653,6 +655,36 @@ i40e_status i40e_get_mac_addr(struct i40e_hw *hw, u8 *mac_addr)
 }
 
 /**
+ * i40e_pre_tx_queue_cfg - pre tx queue configure
+ * @hw: pointer to the HW structure
+ * @queue: target pf queue index
+ * @enable: state change request
+ *
+ * Handles hw requirement to indicate intention to enable
+ * or disable target queue.
+ **/
+void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable)
+{
+	u32 abs_queue_idx = hw->func_caps.base_queue + queue;
+	u32 reg_block = 0;
+	u32 reg_val;
+
+	if (abs_queue_idx >= 128)
+		reg_block = abs_queue_idx / 128;
+
+	reg_val = rd32(hw, I40E_GLLAN_TXPRE_QDIS(reg_block));
+	reg_val &= ~I40E_GLLAN_TXPRE_QDIS_QINDX_MASK;
+	reg_val |= (abs_queue_idx << I40E_GLLAN_TXPRE_QDIS_QINDX_SHIFT);
+
+	if (enable)
+		reg_val |= I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_MASK;
+	else
+		reg_val |= I40E_GLLAN_TXPRE_QDIS_SET_QDIS_MASK;
+
+	wr32(hw, I40E_GLLAN_TXPRE_QDIS(reg_block), reg_val);
+}
+
+/**
  * i40e_get_media_type - Gets media type
  * @hw: pointer to the hardware structure
  **/
@@ -699,7 +731,7 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw)
 }
 
 #define I40E_PF_RESET_WAIT_COUNT_A0	200
-#define I40E_PF_RESET_WAIT_COUNT	10
+#define I40E_PF_RESET_WAIT_COUNT	100
 /**
  * i40e_pf_reset - Reset the PF
  * @hw: pointer to the hardware structure
@@ -789,6 +821,9 @@ void i40e_clear_pxe_mode(struct i40e_hw *hw)
 {
 	u32 reg;
 
+	if (i40e_check_asq_alive(hw))
+		i40e_aq_clear_pxe_mode(hw, NULL);
+
 	/* Clear single descriptor fetch/write-back mode */
 	reg = rd32(hw, I40E_GLLAN_RCTL_0);
 
@@ -907,6 +942,33 @@ void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink)
 /* Admin command wrappers */
 
 /**
+ * i40e_aq_clear_pxe_mode
+ * @hw: pointer to the hw struct
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Tell the firmware that the driver is taking over from PXE
+ **/
+i40e_status i40e_aq_clear_pxe_mode(struct i40e_hw *hw,
+				struct i40e_asq_cmd_details *cmd_details)
+{
+	i40e_status status;
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_clear_pxe *cmd =
+		(struct i40e_aqc_clear_pxe *)&desc.params.raw;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_clear_pxe_mode);
+
+	cmd->rx_cnt = 0x2;
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	wr32(hw, I40E_GLLAN_RCTL_0, 0x1);
+
+	return status;
+}
+
+/**
  * i40e_aq_set_link_restart_an
  * @hw: pointer to the hw struct
  * @cmd_details: pointer to command details structure or NULL
@@ -975,6 +1037,13 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
 	hw_link_info->an_info = resp->an_info;
 	hw_link_info->ext_info = resp->ext_info;
 	hw_link_info->loopback = resp->loopback;
+	hw_link_info->max_frame_size = le16_to_cpu(resp->max_frame_size);
+	hw_link_info->pacing = resp->config & I40E_AQ_CONFIG_PACING_MASK;
+
+	if (resp->config & I40E_AQ_CONFIG_CRC_ENA)
+		hw_link_info->crc_enable = true;
+	else
+		hw_link_info->crc_enable = false;
 
 	if (resp->command_flags & cpu_to_le16(I40E_AQ_LSE_ENABLE))
 		hw_link_info->lse_enable = true;
@@ -1021,8 +1090,6 @@ i40e_status i40e_aq_add_vsi(struct i40e_hw *hw,
 	cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags);
 
 	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
-	if (sizeof(vsi_ctx->info) > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
 				    sizeof(vsi_ctx->info), cmd_details);
@@ -1163,8 +1230,6 @@ i40e_status i40e_aq_get_vsi_params(struct i40e_hw *hw,
 	cmd->uplink_seid = cpu_to_le16(vsi_ctx->seid);
 
 	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	if (sizeof(vsi_ctx->info) > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
 				    sizeof(vsi_ctx->info), NULL);
@@ -1203,8 +1268,6 @@ i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw,
 	cmd->uplink_seid = cpu_to_le16(vsi_ctx->seid);
 
 	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
-	if (sizeof(vsi_ctx->info) > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
 				    sizeof(vsi_ctx->info), cmd_details);
@@ -1300,6 +1363,7 @@ i40e_status i40e_aq_send_driver_version(struct i40e_hw *hw,
 	struct i40e_aqc_driver_version *cmd =
 		(struct i40e_aqc_driver_version *)&desc.params.raw;
 	i40e_status status;
+	u16 len;
 
 	if (dv == NULL)
 		return I40E_ERR_PARAM;
@@ -1311,7 +1375,14 @@ i40e_status i40e_aq_send_driver_version(struct i40e_hw *hw,
 	cmd->driver_minor_ver = dv->minor_version;
 	cmd->driver_build_ver = dv->build_version;
 	cmd->driver_subbuild_ver = dv->subbuild_version;
-	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	len = 0;
+	while (len < sizeof(dv->driver_string) &&
+	       (dv->driver_string[len] < 0x80) &&
+	       dv->driver_string[len])
+		len++;
+	status = i40e_asq_send_command(hw, &desc, dv->driver_string,
+				       len, cmd_details);
 
 	return status;
 }
@@ -1900,6 +1971,12 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 		}
 	}
 
+	/* Software override ensuring FCoE is disabled if npar or mfp
+	 * mode because it is not supported in these modes.
+	 */
+	if (p->npar_enable || p->mfp_mode_1)
+		p->fcoe = false;
+
 	/* additional HW specific goodies that might
 	 * someday be HW version specific
 	 */
@@ -2094,8 +2171,8 @@ i40e_status i40e_aq_start_lldp(struct i40e_hw *hw,
  * @cmd_details: pointer to command details structure or NULL
  **/
 i40e_status i40e_aq_add_udp_tunnel(struct i40e_hw *hw,
-				u16 udp_port, u8 header_len,
-				u8 protocol_index, u8 *filter_index,
+				u16 udp_port, u8 protocol_index,
+				u8 *filter_index,
 				struct i40e_asq_cmd_details *cmd_details)
 {
 	struct i40e_aq_desc desc;
@@ -2253,6 +2330,35 @@ static i40e_status i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid,
 }
 
 /**
+ * i40e_aq_config_vsi_bw_limit - Configure VSI BW Limit
+ * @hw: pointer to the hw struct
+ * @seid: VSI seid
+ * @credit: BW limit credits (0 = disabled)
+ * @max_credit: Max BW limit credits
+ * @cmd_details: pointer to command details structure or NULL
+ **/
+i40e_status i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw,
+				u16 seid, u16 credit, u8 max_credit,
+				struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aq_desc desc;
+	struct i40e_aqc_configure_vsi_bw_limit *cmd =
+		(struct i40e_aqc_configure_vsi_bw_limit *)&desc.params.raw;
+	i40e_status status;
+
+	i40e_fill_default_direct_cmd_desc(&desc,
+					  i40e_aqc_opc_configure_vsi_bw_limit);
+
+	cmd->vsi_seid = cpu_to_le16(seid);
+	cmd->credit = cpu_to_le16(credit);
+	cmd->max_credit = max_credit;
+
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+	return status;
+}
+
+/**
  * i40e_aq_config_vsi_tc_bw - Config VSI BW Allocation per TC
  * @hw: pointer to the hw struct
  * @seid: VSI seid
@@ -2405,7 +2511,7 @@ static i40e_status i40e_validate_filter_settings(struct i40e_hw *hw,
 {
 	u32 fcoe_cntx_size, fcoe_filt_size;
 	u32 pe_cntx_size, pe_filt_size;
-	u32 fcoe_fmax, pe_fmax;
+	u32 fcoe_fmax;
 	u32 val;
 
 	/* Validate FCoE settings passed */
@@ -2480,13 +2586,6 @@ static i40e_status i40e_validate_filter_settings(struct i40e_hw *hw,
 	if (fcoe_filt_size + fcoe_cntx_size >  fcoe_fmax)
 		return I40E_ERR_INVALID_SIZE;
 
-	/* PEHSIZE + PEDSIZE should not be greater than PMPEXFMAX */
-	val = rd32(hw, I40E_GLHMC_PEXFMAX);
-	pe_fmax = (val & I40E_GLHMC_PEXFMAX_PMPEXFMAX_MASK)
-		   >> I40E_GLHMC_PEXFMAX_PMPEXFMAX_SHIFT;
-	if (pe_filt_size + pe_cntx_size >  pe_fmax)
-		return I40E_ERR_INVALID_SIZE;
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c
index 6e8103abfd0..00bc0cdb3a0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c
@@ -232,7 +232,7 @@ static void i40e_dcbnl_del_app(struct i40e_pf *pf,
 			      struct i40e_ieee_app_priority_table *app)
 {
 	int v, err;
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v] && pf->vsi[v]->netdev) {
 			err = i40e_dcbnl_vsi_del_app(pf->vsi[v], app);
 			if (err)
@@ -302,8 +302,8 @@ void i40e_dcbnl_setup(struct i40e_vsi *vsi)
 	struct net_device *dev = vsi->netdev;
 	struct i40e_pf *pf = i40e_netdev_to_pf(dev);
 
-	/* DCB not enabled */
-	if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
+	/* Not DCB capable */
+	if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
 		return;
 
 	/* Do not setup DCB NL ops for MFP mode */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 3c37386fd13..cffdfc21290 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -45,7 +45,7 @@ static struct i40e_vsi *i40e_dbg_find_vsi(struct i40e_pf *pf, int seid)
 	if (seid < 0)
 		dev_info(&pf->pdev->dev, "%d: bad seid\n", seid);
 	else
-		for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+		for (i = 0; i < pf->num_alloc_vsi; i++)
 			if (pf->vsi[i] && (pf->vsi[i]->seid == seid))
 				return pf->vsi[i];
 
@@ -843,7 +843,7 @@ static void i40e_dbg_dump_vsi_no_seid(struct i40e_pf *pf)
 {
 	int i;
 
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+	for (i = 0; i < pf->num_alloc_vsi; i++)
 		if (pf->vsi[i])
 			dev_info(&pf->pdev->dev, "dump vsi[%d]: %d\n",
 				 i, pf->vsi[i]->seid);
@@ -862,12 +862,11 @@ static void i40e_dbg_dump_eth_stats(struct i40e_pf *pf,
 		 "    rx_bytes = \t%lld \trx_unicast = \t\t%lld \trx_multicast = \t%lld\n",
 		estats->rx_bytes, estats->rx_unicast, estats->rx_multicast);
 	dev_info(&pf->pdev->dev,
-		 "    rx_broadcast = \t%lld \trx_discards = \t\t%lld \trx_errors = \t%lld\n",
-		 estats->rx_broadcast, estats->rx_discards, estats->rx_errors);
+		 "    rx_broadcast = \t%lld \trx_discards = \t\t%lld\n",
+		 estats->rx_broadcast, estats->rx_discards);
 	dev_info(&pf->pdev->dev,
-		 "    rx_missed = \t%lld \trx_unknown_protocol = \t%lld \ttx_bytes = \t%lld\n",
-		 estats->rx_missed, estats->rx_unknown_protocol,
-		 estats->tx_bytes);
+		 "    rx_unknown_protocol = \t%lld \ttx_bytes = \t%lld\n",
+		 estats->rx_unknown_protocol, estats->tx_bytes);
 	dev_info(&pf->pdev->dev,
 		 "    tx_unicast = \t%lld \ttx_multicast = \t\t%lld \ttx_broadcast = \t%lld\n",
 		 estats->tx_unicast, estats->tx_multicast, estats->tx_broadcast);
@@ -1527,7 +1526,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			cnt = sscanf(&cmd_buf[15], "%i", &vsi_seid);
 			if (cnt == 0) {
 				int i;
-				for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+				for (i = 0; i < pf->num_alloc_vsi; i++)
 					i40e_vsi_reset_stats(pf->vsi[i]);
 				dev_info(&pf->pdev->dev, "vsi clear stats called for all vsi's\n");
 			} else if (cnt == 1) {
@@ -1744,10 +1743,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 		i40e_dbg_cmd_fd_ctrl(pf, I40E_FLAG_FD_ATR_ENABLED, false);
 	} else if (strncmp(cmd_buf, "fd-atr on", 9) == 0) {
 		i40e_dbg_cmd_fd_ctrl(pf, I40E_FLAG_FD_ATR_ENABLED, true);
-	} else if (strncmp(cmd_buf, "fd-sb off", 9) == 0) {
-		i40e_dbg_cmd_fd_ctrl(pf, I40E_FLAG_FD_SB_ENABLED, false);
-	} else if (strncmp(cmd_buf, "fd-sb on", 8) == 0) {
-		i40e_dbg_cmd_fd_ctrl(pf, I40E_FLAG_FD_SB_ENABLED, true);
 	} else if (strncmp(cmd_buf, "lldp", 4) == 0) {
 		if (strncmp(&cmd_buf[5], "stop", 4) == 0) {
 			int ret;
@@ -1967,8 +1962,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 		dev_info(&pf->pdev->dev, "  rem fd_filter <dest q_index> <flex_off> <pctype> <dest_vsi> <dest_ctl> <fd_status> <cnt_index> <fd_id> <packet_len> <packet>\n");
 		dev_info(&pf->pdev->dev, "  fd-atr off\n");
 		dev_info(&pf->pdev->dev, "  fd-atr on\n");
-		dev_info(&pf->pdev->dev, "  fd-sb off\n");
-		dev_info(&pf->pdev->dev, "  fd-sb on\n");
 		dev_info(&pf->pdev->dev, "  lldp start\n");
 		dev_info(&pf->pdev->dev, "  lldp stop\n");
 		dev_info(&pf->pdev->dev, "  lldp get local\n");
diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c
index b2380daef8c..56438bd579e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_diag.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c
@@ -67,17 +67,25 @@ static i40e_status i40e_diag_reg_pattern_test(struct i40e_hw *hw,
 
 struct i40e_diag_reg_test_info i40e_reg_list[] = {
 	/* offset               mask         elements   stride */
-	{I40E_QTX_CTL(0),       0x0000FFBF,   4, I40E_QTX_CTL(1) - I40E_QTX_CTL(0)},
-	{I40E_PFINT_ITR0(0),    0x00000FFF,   3, I40E_PFINT_ITR0(1) - I40E_PFINT_ITR0(0)},
-	{I40E_PFINT_ITRN(0, 0), 0x00000FFF,   8, I40E_PFINT_ITRN(0, 1) - I40E_PFINT_ITRN(0, 0)},
-	{I40E_PFINT_ITRN(1, 0), 0x00000FFF,   8, I40E_PFINT_ITRN(1, 1) - I40E_PFINT_ITRN(1, 0)},
-	{I40E_PFINT_ITRN(2, 0), 0x00000FFF,   8, I40E_PFINT_ITRN(2, 1) - I40E_PFINT_ITRN(2, 0)},
-	{I40E_PFINT_STAT_CTL0,  0x0000000C,   1, 0},
-	{I40E_PFINT_LNKLST0,    0x00001FFF,   1, 0},
-	{I40E_PFINT_LNKLSTN(0), 0x000007FF,  64, I40E_PFINT_LNKLSTN(1) - I40E_PFINT_LNKLSTN(0)},
-	{I40E_QINT_TQCTL(0),    0x000000FF,  64, I40E_QINT_TQCTL(1) - I40E_QINT_TQCTL(0)},
-	{I40E_QINT_RQCTL(0),    0x000000FF,  64, I40E_QINT_RQCTL(1) - I40E_QINT_RQCTL(0)},
-	{I40E_PFINT_ICR0_ENA,   0xF7F20000,   1, 0},
+	{I40E_QTX_CTL(0),       0x0000FFBF, 1,
+		I40E_QTX_CTL(1) - I40E_QTX_CTL(0)},
+	{I40E_PFINT_ITR0(0),    0x00000FFF, 3,
+		I40E_PFINT_ITR0(1) - I40E_PFINT_ITR0(0)},
+	{I40E_PFINT_ITRN(0, 0), 0x00000FFF, 1,
+		I40E_PFINT_ITRN(0, 1) - I40E_PFINT_ITRN(0, 0)},
+	{I40E_PFINT_ITRN(1, 0), 0x00000FFF, 1,
+		I40E_PFINT_ITRN(1, 1) - I40E_PFINT_ITRN(1, 0)},
+	{I40E_PFINT_ITRN(2, 0), 0x00000FFF, 1,
+		I40E_PFINT_ITRN(2, 1) - I40E_PFINT_ITRN(2, 0)},
+	{I40E_PFINT_STAT_CTL0,  0x0000000C, 1, 0},
+	{I40E_PFINT_LNKLST0,    0x00001FFF, 1, 0},
+	{I40E_PFINT_LNKLSTN(0), 0x000007FF, 1,
+		I40E_PFINT_LNKLSTN(1) - I40E_PFINT_LNKLSTN(0)},
+	{I40E_QINT_TQCTL(0),    0x000000FF, 1,
+		I40E_QINT_TQCTL(1) - I40E_QINT_TQCTL(0)},
+	{I40E_QINT_RQCTL(0),    0x000000FF, 1,
+		I40E_QINT_RQCTL(1) - I40E_QINT_RQCTL(0)},
+	{I40E_PFINT_ICR0_ENA,   0xF7F20000, 1, 0},
 	{ 0 }
 };
 
@@ -93,9 +101,25 @@ i40e_status i40e_diag_reg_test(struct i40e_hw *hw)
 	u32 reg, mask;
 	u32 i, j;
 
-	for (i = 0; (i40e_reg_list[i].offset != 0) && !ret_code; i++) {
+	for (i = 0; i40e_reg_list[i].offset != 0 &&
+					     !ret_code; i++) {
+
+		/* set actual reg range for dynamically allocated resources */
+		if (i40e_reg_list[i].offset == I40E_QTX_CTL(0) &&
+		    hw->func_caps.num_tx_qp != 0)
+			i40e_reg_list[i].elements = hw->func_caps.num_tx_qp;
+		if ((i40e_reg_list[i].offset == I40E_PFINT_ITRN(0, 0) ||
+		     i40e_reg_list[i].offset == I40E_PFINT_ITRN(1, 0) ||
+		     i40e_reg_list[i].offset == I40E_PFINT_ITRN(2, 0) ||
+		     i40e_reg_list[i].offset == I40E_QINT_TQCTL(0) ||
+		     i40e_reg_list[i].offset == I40E_QINT_RQCTL(0)) &&
+		    hw->func_caps.num_msix_vectors != 0)
+			i40e_reg_list[i].elements =
+				hw->func_caps.num_msix_vectors - 1;
+
+		/* test register access */
 		mask = i40e_reg_list[i].mask;
-		for (j = 0; (j < i40e_reg_list[i].elements) && !ret_code; j++) {
+		for (j = 0; j < i40e_reg_list[i].elements && !ret_code; j++) {
 			reg = i40e_reg_list[i].offset +
 			      (j * i40e_reg_list[i].stride);
 			ret_code = i40e_diag_reg_pattern_test(hw, reg, mask);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 03d99cbc5c2..4a488ffcd6b 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -46,6 +46,8 @@ struct i40e_stats {
 		I40E_STAT(struct i40e_pf, _name, _stat)
 #define I40E_VSI_STAT(_name, _stat) \
 		I40E_STAT(struct i40e_vsi, _name, _stat)
+#define I40E_VEB_STAT(_name, _stat) \
+		I40E_STAT(struct i40e_veb, _name, _stat)
 
 static const struct i40e_stats i40e_gstrings_net_stats[] = {
 	I40E_NETDEV_STAT(rx_packets),
@@ -56,12 +58,36 @@ static const struct i40e_stats i40e_gstrings_net_stats[] = {
 	I40E_NETDEV_STAT(tx_errors),
 	I40E_NETDEV_STAT(rx_dropped),
 	I40E_NETDEV_STAT(tx_dropped),
-	I40E_NETDEV_STAT(multicast),
 	I40E_NETDEV_STAT(collisions),
 	I40E_NETDEV_STAT(rx_length_errors),
 	I40E_NETDEV_STAT(rx_crc_errors),
 };
 
+static const struct i40e_stats i40e_gstrings_veb_stats[] = {
+	I40E_VEB_STAT("rx_bytes", stats.rx_bytes),
+	I40E_VEB_STAT("tx_bytes", stats.tx_bytes),
+	I40E_VEB_STAT("rx_unicast", stats.rx_unicast),
+	I40E_VEB_STAT("tx_unicast", stats.tx_unicast),
+	I40E_VEB_STAT("rx_multicast", stats.rx_multicast),
+	I40E_VEB_STAT("tx_multicast", stats.tx_multicast),
+	I40E_VEB_STAT("rx_broadcast", stats.rx_broadcast),
+	I40E_VEB_STAT("tx_broadcast", stats.tx_broadcast),
+	I40E_VEB_STAT("rx_discards", stats.rx_discards),
+	I40E_VEB_STAT("tx_discards", stats.tx_discards),
+	I40E_VEB_STAT("tx_errors", stats.tx_errors),
+	I40E_VEB_STAT("rx_unknown_protocol", stats.rx_unknown_protocol),
+};
+
+static const struct i40e_stats i40e_gstrings_misc_stats[] = {
+	I40E_VSI_STAT("rx_unicast", eth_stats.rx_unicast),
+	I40E_VSI_STAT("tx_unicast", eth_stats.tx_unicast),
+	I40E_VSI_STAT("rx_multicast", eth_stats.rx_multicast),
+	I40E_VSI_STAT("tx_multicast", eth_stats.tx_multicast),
+	I40E_VSI_STAT("rx_broadcast", eth_stats.rx_broadcast),
+	I40E_VSI_STAT("tx_broadcast", eth_stats.tx_broadcast),
+	I40E_VSI_STAT("rx_unknown_protocol", eth_stats.rx_unknown_protocol),
+};
+
 static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 				 struct ethtool_rxnfc *cmd);
 
@@ -78,7 +104,12 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 static struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("rx_bytes", stats.eth.rx_bytes),
 	I40E_PF_STAT("tx_bytes", stats.eth.tx_bytes),
-	I40E_PF_STAT("rx_errors", stats.eth.rx_errors),
+	I40E_PF_STAT("rx_unicast", stats.eth.rx_unicast),
+	I40E_PF_STAT("tx_unicast", stats.eth.tx_unicast),
+	I40E_PF_STAT("rx_multicast", stats.eth.rx_multicast),
+	I40E_PF_STAT("tx_multicast", stats.eth.tx_multicast),
+	I40E_PF_STAT("rx_broadcast", stats.eth.rx_broadcast),
+	I40E_PF_STAT("tx_broadcast", stats.eth.tx_broadcast),
 	I40E_PF_STAT("tx_errors", stats.eth.tx_errors),
 	I40E_PF_STAT("rx_dropped", stats.eth.rx_discards),
 	I40E_PF_STAT("tx_dropped", stats.eth.tx_discards),
@@ -88,6 +119,7 @@ static struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("mac_local_faults", stats.mac_local_faults),
 	I40E_PF_STAT("mac_remote_faults", stats.mac_remote_faults),
 	I40E_PF_STAT("tx_timeout", tx_timeout_count),
+	I40E_PF_STAT("rx_csum_bad", hw_csum_rx_error),
 	I40E_PF_STAT("rx_length_errors", stats.rx_length_errors),
 	I40E_PF_STAT("link_xon_rx", stats.link_xon_rx),
 	I40E_PF_STAT("link_xoff_rx", stats.link_xoff_rx),
@@ -112,8 +144,10 @@ static struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("rx_oversize", stats.rx_oversize),
 	I40E_PF_STAT("rx_jabber", stats.rx_jabber),
 	I40E_PF_STAT("VF_admin_queue_requests", vf_aq_requests),
-	I40E_PF_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts),
 	I40E_PF_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
+	I40E_PF_STAT("fdir_atr_match", stats.fd_atr_match),
+	I40E_PF_STAT("fdir_sb_match", stats.fd_sb_match),
+
 	/* LPI stats */
 	I40E_PF_STAT("tx_lpi_status", stats.tx_lpi_status),
 	I40E_PF_STAT("rx_lpi_status", stats.rx_lpi_status),
@@ -122,11 +156,14 @@ static struct i40e_stats i40e_gstrings_stats[] = {
 };
 
 #define I40E_QUEUE_STATS_LEN(n) \
-  ((((struct i40e_netdev_priv *)netdev_priv((n)))->vsi->num_queue_pairs + \
-    ((struct i40e_netdev_priv *)netdev_priv((n)))->vsi->num_queue_pairs) * 2)
+	(((struct i40e_netdev_priv *)netdev_priv((n)))->vsi->num_queue_pairs \
+	    * 2 /* Tx and Rx together */                                     \
+	    * (sizeof(struct i40e_queue_stats) / sizeof(u64)))
 #define I40E_GLOBAL_STATS_LEN	ARRAY_SIZE(i40e_gstrings_stats)
 #define I40E_NETDEV_STATS_LEN   ARRAY_SIZE(i40e_gstrings_net_stats)
+#define I40E_MISC_STATS_LEN	ARRAY_SIZE(i40e_gstrings_misc_stats)
 #define I40E_VSI_STATS_LEN(n)   (I40E_NETDEV_STATS_LEN + \
+				 I40E_MISC_STATS_LEN + \
 				 I40E_QUEUE_STATS_LEN((n)))
 #define I40E_PFC_STATS_LEN ( \
 		(FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_rx) + \
@@ -135,6 +172,7 @@ static struct i40e_stats i40e_gstrings_stats[] = {
 		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_tx) + \
 		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_2_xoff)) \
 		 / sizeof(u64))
+#define I40E_VEB_STATS_LEN	ARRAY_SIZE(i40e_gstrings_veb_stats)
 #define I40E_PF_STATS_LEN(n)	(I40E_GLOBAL_STATS_LEN + \
 				 I40E_PFC_STATS_LEN + \
 				 I40E_VSI_STATS_LEN((n)))
@@ -620,10 +658,15 @@ static int i40e_get_sset_count(struct net_device *netdev, int sset)
 	case ETH_SS_TEST:
 		return I40E_TEST_LEN;
 	case ETH_SS_STATS:
-		if (vsi == pf->vsi[pf->lan_vsi])
-			return I40E_PF_STATS_LEN(netdev);
-		else
+		if (vsi == pf->vsi[pf->lan_vsi]) {
+			int len = I40E_PF_STATS_LEN(netdev);
+
+			if (pf->lan_veb != I40E_NO_VEB)
+				len += I40E_VEB_STATS_LEN;
+			return len;
+		} else {
 			return I40E_VSI_STATS_LEN(netdev);
+		}
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -633,6 +676,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 				   struct ethtool_stats *stats, u64 *data)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_ring *tx_ring, *rx_ring;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
 	int i = 0;
@@ -648,10 +692,14 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 		data[i++] = (i40e_gstrings_net_stats[j].sizeof_stat ==
 			sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 	}
+	for (j = 0; j < I40E_MISC_STATS_LEN; j++) {
+		p = (char *)vsi + i40e_gstrings_misc_stats[j].stat_offset;
+		data[i++] = (i40e_gstrings_misc_stats[j].sizeof_stat ==
+			    sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+	}
 	rcu_read_lock();
-	for (j = 0; j < vsi->num_queue_pairs; j++, i += 4) {
-		struct i40e_ring *tx_ring = ACCESS_ONCE(vsi->tx_rings[j]);
-		struct i40e_ring *rx_ring;
+	for (j = 0; j < vsi->num_queue_pairs; j++) {
+		tx_ring = ACCESS_ONCE(vsi->tx_rings[j]);
 
 		if (!tx_ring)
 			continue;
@@ -662,33 +710,45 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 			data[i] = tx_ring->stats.packets;
 			data[i + 1] = tx_ring->stats.bytes;
 		} while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start));
+		i += 2;
 
 		/* Rx ring is the 2nd half of the queue pair */
 		rx_ring = &tx_ring[1];
 		do {
 			start = u64_stats_fetch_begin_irq(&rx_ring->syncp);
-			data[i + 2] = rx_ring->stats.packets;
-			data[i + 3] = rx_ring->stats.bytes;
+			data[i] = rx_ring->stats.packets;
+			data[i + 1] = rx_ring->stats.bytes;
 		} while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start));
+		i += 2;
 	}
 	rcu_read_unlock();
-	if (vsi == pf->vsi[pf->lan_vsi]) {
-		for (j = 0; j < I40E_GLOBAL_STATS_LEN; j++) {
-			p = (char *)pf + i40e_gstrings_stats[j].stat_offset;
-			data[i++] = (i40e_gstrings_stats[j].sizeof_stat ==
-				   sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-		}
-		for (j = 0; j < I40E_MAX_USER_PRIORITY; j++) {
-			data[i++] = pf->stats.priority_xon_tx[j];
-			data[i++] = pf->stats.priority_xoff_tx[j];
-		}
-		for (j = 0; j < I40E_MAX_USER_PRIORITY; j++) {
-			data[i++] = pf->stats.priority_xon_rx[j];
-			data[i++] = pf->stats.priority_xoff_rx[j];
+	if (vsi != pf->vsi[pf->lan_vsi])
+		return;
+
+	if (pf->lan_veb != I40E_NO_VEB) {
+		struct i40e_veb *veb = pf->veb[pf->lan_veb];
+		for (j = 0; j < I40E_VEB_STATS_LEN; j++) {
+			p = (char *)veb;
+			p += i40e_gstrings_veb_stats[j].stat_offset;
+			data[i++] = (i40e_gstrings_veb_stats[j].sizeof_stat ==
+				     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 		}
-		for (j = 0; j < I40E_MAX_USER_PRIORITY; j++)
-			data[i++] = pf->stats.priority_xon_2_xoff[j];
 	}
+	for (j = 0; j < I40E_GLOBAL_STATS_LEN; j++) {
+		p = (char *)pf + i40e_gstrings_stats[j].stat_offset;
+		data[i++] = (i40e_gstrings_stats[j].sizeof_stat ==
+			     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+	}
+	for (j = 0; j < I40E_MAX_USER_PRIORITY; j++) {
+		data[i++] = pf->stats.priority_xon_tx[j];
+		data[i++] = pf->stats.priority_xoff_tx[j];
+	}
+	for (j = 0; j < I40E_MAX_USER_PRIORITY; j++) {
+		data[i++] = pf->stats.priority_xon_rx[j];
+		data[i++] = pf->stats.priority_xoff_rx[j];
+	}
+	for (j = 0; j < I40E_MAX_USER_PRIORITY; j++)
+		data[i++] = pf->stats.priority_xon_2_xoff[j];
 }
 
 static void i40e_get_strings(struct net_device *netdev, u32 stringset,
@@ -713,6 +773,11 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset,
 				 i40e_gstrings_net_stats[i].stat_string);
 			p += ETH_GSTRING_LEN;
 		}
+		for (i = 0; i < I40E_MISC_STATS_LEN; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "%s",
+				 i40e_gstrings_misc_stats[i].stat_string);
+			p += ETH_GSTRING_LEN;
+		}
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
 			snprintf(p, ETH_GSTRING_LEN, "tx-%u.tx_packets", i);
 			p += ETH_GSTRING_LEN;
@@ -723,34 +788,42 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset,
 			snprintf(p, ETH_GSTRING_LEN, "rx-%u.rx_bytes", i);
 			p += ETH_GSTRING_LEN;
 		}
-		if (vsi == pf->vsi[pf->lan_vsi]) {
-			for (i = 0; i < I40E_GLOBAL_STATS_LEN; i++) {
-				snprintf(p, ETH_GSTRING_LEN, "port.%s",
-					 i40e_gstrings_stats[i].stat_string);
-				p += ETH_GSTRING_LEN;
-			}
-			for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-				snprintf(p, ETH_GSTRING_LEN,
-					 "port.tx_priority_%u_xon", i);
-				p += ETH_GSTRING_LEN;
-				snprintf(p, ETH_GSTRING_LEN,
-					 "port.tx_priority_%u_xoff", i);
-				p += ETH_GSTRING_LEN;
-			}
-			for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-				snprintf(p, ETH_GSTRING_LEN,
-					 "port.rx_priority_%u_xon", i);
-				p += ETH_GSTRING_LEN;
-				snprintf(p, ETH_GSTRING_LEN,
-					 "port.rx_priority_%u_xoff", i);
-				p += ETH_GSTRING_LEN;
-			}
-			for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-				snprintf(p, ETH_GSTRING_LEN,
-					 "port.rx_priority_%u_xon_2_xoff", i);
+		if (vsi != pf->vsi[pf->lan_vsi])
+			return;
+
+		if (pf->lan_veb != I40E_NO_VEB) {
+			for (i = 0; i < I40E_VEB_STATS_LEN; i++) {
+				snprintf(p, ETH_GSTRING_LEN, "veb.%s",
+					i40e_gstrings_veb_stats[i].stat_string);
 				p += ETH_GSTRING_LEN;
 			}
 		}
+		for (i = 0; i < I40E_GLOBAL_STATS_LEN; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "port.%s",
+				 i40e_gstrings_stats[i].stat_string);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+			snprintf(p, ETH_GSTRING_LEN,
+				 "port.tx_priority_%u_xon", i);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN,
+				 "port.tx_priority_%u_xoff", i);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+			snprintf(p, ETH_GSTRING_LEN,
+				 "port.rx_priority_%u_xon", i);
+			p += ETH_GSTRING_LEN;
+			snprintf(p, ETH_GSTRING_LEN,
+				 "port.rx_priority_%u_xoff", i);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+			snprintf(p, ETH_GSTRING_LEN,
+				 "port.rx_priority_%u_xon_2_xoff", i);
+			p += ETH_GSTRING_LEN;
+		}
 		/* BUG_ON(p - data != I40E_STATS_LEN * ETH_GSTRING_LEN); */
 		break;
 	}
@@ -1007,14 +1080,13 @@ static int i40e_get_coalesce(struct net_device *netdev,
 	ec->rx_max_coalesced_frames_irq = vsi->work_limit;
 
 	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting))
-		ec->rx_coalesce_usecs = 1;
-	else
-		ec->rx_coalesce_usecs = vsi->rx_itr_setting;
+		ec->use_adaptive_rx_coalesce = 1;
 
 	if (ITR_IS_DYNAMIC(vsi->tx_itr_setting))
-		ec->tx_coalesce_usecs = 1;
-	else
-		ec->tx_coalesce_usecs = vsi->tx_itr_setting;
+		ec->use_adaptive_tx_coalesce = 1;
+
+	ec->rx_coalesce_usecs = vsi->rx_itr_setting & ~I40E_ITR_DYNAMIC;
+	ec->tx_coalesce_usecs = vsi->tx_itr_setting & ~I40E_ITR_DYNAMIC;
 
 	return 0;
 }
@@ -1033,37 +1105,27 @@ static int i40e_set_coalesce(struct net_device *netdev,
 	if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
 		vsi->work_limit = ec->tx_max_coalesced_frames_irq;
 
-	switch (ec->rx_coalesce_usecs) {
-	case 0:
-		vsi->rx_itr_setting = 0;
-		break;
-	case 1:
-		vsi->rx_itr_setting = (I40E_ITR_DYNAMIC |
-				       ITR_REG_TO_USEC(I40E_ITR_RX_DEF));
-		break;
-	default:
-		if ((ec->rx_coalesce_usecs < (I40E_MIN_ITR << 1)) ||
-		    (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1)))
-			return -EINVAL;
+	if ((ec->rx_coalesce_usecs >= (I40E_MIN_ITR << 1)) &&
+	    (ec->rx_coalesce_usecs <= (I40E_MAX_ITR << 1)))
 		vsi->rx_itr_setting = ec->rx_coalesce_usecs;
-		break;
-	}
+	else
+		return -EINVAL;
 
-	switch (ec->tx_coalesce_usecs) {
-	case 0:
-		vsi->tx_itr_setting = 0;
-		break;
-	case 1:
-		vsi->tx_itr_setting = (I40E_ITR_DYNAMIC |
-				       ITR_REG_TO_USEC(I40E_ITR_TX_DEF));
-		break;
-	default:
-		if ((ec->tx_coalesce_usecs < (I40E_MIN_ITR << 1)) ||
-		    (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1)))
-			return -EINVAL;
+	if ((ec->tx_coalesce_usecs >= (I40E_MIN_ITR << 1)) &&
+	    (ec->tx_coalesce_usecs <= (I40E_MAX_ITR << 1)))
 		vsi->tx_itr_setting = ec->tx_coalesce_usecs;
-		break;
-	}
+	else
+		return -EINVAL;
+
+	if (ec->use_adaptive_rx_coalesce)
+		vsi->rx_itr_setting |= I40E_ITR_DYNAMIC;
+	else
+		vsi->rx_itr_setting &= ~I40E_ITR_DYNAMIC;
+
+	if (ec->use_adaptive_tx_coalesce)
+		vsi->tx_itr_setting |= I40E_ITR_DYNAMIC;
+	else
+		vsi->tx_itr_setting &= ~I40E_ITR_DYNAMIC;
 
 	vector = vsi->base_vector;
 	for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
@@ -1140,8 +1202,7 @@ static int i40e_get_ethtool_fdir_all(struct i40e_pf *pf,
 	int cnt = 0;
 
 	/* report total rule count */
-	cmd->data = pf->hw.fdir_shared_filter_count +
-		    pf->fdir_pf_filter_count;
+	cmd->data = i40e_get_fd_cnt_all(pf);
 
 	hlist_for_each_entry_safe(rule, node2,
 				  &pf->fdir_filter_list, fdir_node) {
@@ -1175,10 +1236,6 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 	struct i40e_fdir_filter *rule = NULL;
 	struct hlist_node *node2;
 
-	/* report total rule count */
-	cmd->data = pf->hw.fdir_shared_filter_count +
-		    pf->fdir_pf_filter_count;
-
 	hlist_for_each_entry_safe(rule, node2,
 				  &pf->fdir_filter_list, fdir_node) {
 		if (fsp->location <= rule->fd_id)
@@ -1189,11 +1246,24 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 		return -EINVAL;
 
 	fsp->flow_type = rule->flow_type;
-	fsp->h_u.tcp_ip4_spec.psrc = rule->src_port;
-	fsp->h_u.tcp_ip4_spec.pdst = rule->dst_port;
-	fsp->h_u.tcp_ip4_spec.ip4src = rule->src_ip[0];
-	fsp->h_u.tcp_ip4_spec.ip4dst = rule->dst_ip[0];
-	fsp->ring_cookie = rule->q_index;
+	if (fsp->flow_type == IP_USER_FLOW) {
+		fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4;
+		fsp->h_u.usr_ip4_spec.proto = 0;
+		fsp->m_u.usr_ip4_spec.proto = 0;
+	}
+
+	/* Reverse the src and dest notion, since the HW views them from
+	 * Tx perspective where as the user expects it from Rx filter view.
+	 */
+	fsp->h_u.tcp_ip4_spec.psrc = rule->dst_port;
+	fsp->h_u.tcp_ip4_spec.pdst = rule->src_port;
+	fsp->h_u.tcp_ip4_spec.ip4src = rule->dst_ip[0];
+	fsp->h_u.tcp_ip4_spec.ip4dst = rule->src_ip[0];
+
+	if (rule->dest_ctl == I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET)
+		fsp->ring_cookie = RX_CLS_FLOW_DISC;
+	else
+		fsp->ring_cookie = rule->q_index;
 
 	return 0;
 }
@@ -1223,6 +1293,8 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
 		break;
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = pf->fdir_pf_active_filters;
+		/* report total rule count */
+		cmd->data = i40e_get_fd_cnt_all(pf);
 		ret = 0;
 		break;
 	case ETHTOOL_GRXCLSRULE:
@@ -1291,16 +1363,12 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case UDP_V4_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &=
-			~(((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) |
-			((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) |
-			((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4));
+			hena &= ~(((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
+				  ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4));
 			break;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
-			hena |=
-			(((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP)  |
-			((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) |
-			((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4));
+			hena |= (((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
+				  ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4));
 			break;
 		default:
 			return -EINVAL;
@@ -1309,16 +1377,12 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 	case UDP_V6_FLOW:
 		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
 		case 0:
-			hena &=
-			~(((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) |
-			((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP) |
-			((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6));
+			hena &= ~(((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
+				  ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6));
 			break;
 		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
-			hena |=
-			(((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP)  |
-			((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP) |
-			((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6));
+			hena |= (((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
+				 ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6));
 			break;
 		default:
 			return -EINVAL;
@@ -1503,7 +1567,8 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 		return -EINVAL;
 	}
 
-	if (fsp->ring_cookie >= vsi->num_queue_pairs)
+	if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) &&
+	    (fsp->ring_cookie >= vsi->num_queue_pairs))
 		return -EINVAL;
 
 	input = kzalloc(sizeof(*input), GFP_KERNEL);
@@ -1524,13 +1589,17 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi,
 	input->pctype = 0;
 	input->dest_vsi = vsi->id;
 	input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID;
-	input->cnt_index = 0;
+	input->cnt_index  = pf->fd_sb_cnt_idx;
 	input->flow_type = fsp->flow_type;
 	input->ip4_proto = fsp->h_u.usr_ip4_spec.proto;
-	input->src_port = fsp->h_u.tcp_ip4_spec.psrc;
-	input->dst_port = fsp->h_u.tcp_ip4_spec.pdst;
-	input->src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src;
-	input->dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst;
+
+	/* Reverse the src and dest notion, since the HW expects them to be from
+	 * Tx perspective where as the input from user is from Rx filter view.
+	 */
+	input->dst_port = fsp->h_u.tcp_ip4_spec.psrc;
+	input->src_port = fsp->h_u.tcp_ip4_spec.pdst;
+	input->dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src;
+	input->src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst;
 
 	ret = i40e_add_del_fdir(vsi, input, true);
 	if (ret)
@@ -1692,5 +1761,5 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 
 void i40e_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &i40e_ethtool_ops);
+	netdev->ethtool_ops = &i40e_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
index bf2d4cc5b56..9b987ccc9e8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c
@@ -201,7 +201,7 @@ exit:
  **/
 i40e_status i40e_remove_pd_bp(struct i40e_hw *hw,
 					struct i40e_hmc_info *hmc_info,
-					u32 idx, bool is_pf)
+					u32 idx)
 {
 	i40e_status ret_code = 0;
 	struct i40e_hmc_pd_entry *pd_entry;
@@ -237,10 +237,7 @@ i40e_status i40e_remove_pd_bp(struct i40e_hw *hw,
 	pd_addr = (u64 *)pd_table->pd_page_addr.va;
 	pd_addr += rel_pd_idx;
 	memset(pd_addr, 0, sizeof(u64));
-	if (is_pf)
-		I40E_INVALIDATE_PF_HMC_PD(hw, sd_idx, idx);
-	else
-		I40E_INVALIDATE_VF_HMC_PD(hw, sd_idx, idx, hmc_info->hmc_fn_id);
+	I40E_INVALIDATE_PF_HMC_PD(hw, sd_idx, idx);
 
 	/* free memory here */
 	ret_code = i40e_free_dma_mem(hw, &(pd_entry->bp.addr));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_hmc.h
index 0cd4701234f..b45d8fedc5e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_hmc.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.h
@@ -163,11 +163,6 @@ struct i40e_hmc_info {
 	    (((sd_idx) << I40E_PFHMC_PDINV_PMSDIDX_SHIFT) |		\
 	     ((pd_idx) << I40E_PFHMC_PDINV_PMPDIDX_SHIFT)))
 
-#define I40E_INVALIDATE_VF_HMC_PD(hw, sd_idx, pd_idx, hmc_fn_id)	   \
-	wr32((hw), I40E_GLHMC_VFPDINV((hmc_fn_id) - I40E_FIRST_VF_FPM_ID), \
-	     (((sd_idx) << I40E_PFHMC_PDINV_PMSDIDX_SHIFT) |		   \
-	      ((pd_idx) << I40E_PFHMC_PDINV_PMPDIDX_SHIFT)))
-
 /**
  * I40E_FIND_SD_INDEX_LIMIT - finds segment descriptor index limit
  * @hmc_info: pointer to the HMC configuration information structure
@@ -226,7 +221,7 @@ i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw,
 					      u32 pd_index);
 i40e_status i40e_remove_pd_bp(struct i40e_hw *hw,
 					struct i40e_hmc_info *hmc_info,
-					u32 idx, bool is_pf);
+					u32 idx);
 i40e_status i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info,
 					     u32 idx);
 i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
index d5d98fe2691..870ab1ee072 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c
@@ -397,7 +397,7 @@ static i40e_status i40e_create_lan_hmc_object(struct i40e_hw *hw,
 				/* remove the backing pages from pd_idx1 to i */
 				while (i && (i > pd_idx1)) {
 					i40e_remove_pd_bp(hw, info->hmc_info,
-							  (i - 1), true);
+							  (i - 1));
 					i--;
 				}
 			}
@@ -433,11 +433,7 @@ exit_sd_error:
 				      ((j - 1) * I40E_HMC_MAX_BP_COUNT));
 			pd_lmt1 = min(pd_lmt, (j * I40E_HMC_MAX_BP_COUNT));
 			for (i = pd_idx1; i < pd_lmt1; i++) {
-				i40e_remove_pd_bp(
-					hw,
-					info->hmc_info,
-					i,
-					true);
+				i40e_remove_pd_bp(hw, info->hmc_info, i);
 			}
 			i40e_remove_pd_page(hw, info->hmc_info, (j - 1));
 			break;
@@ -616,8 +612,7 @@ static i40e_status i40e_delete_lan_hmc_object(struct i40e_hw *hw,
 		pd_table =
 			&info->hmc_info->sd_table.sd_entry[sd_idx].u.pd_table;
 		if (pd_table->pd_entry[rel_pd_idx].valid) {
-			ret_code = i40e_remove_pd_bp(hw, info->hmc_info,
-						     j, true);
+			ret_code = i40e_remove_pd_bp(hw, info->hmc_info, j);
 			if (ret_code)
 				goto exit;
 		}
@@ -747,6 +742,7 @@ static struct i40e_context_ele i40e_hmc_rxq_ce_info[] = {
 	{ I40E_HMC_STORE(i40e_hmc_obj_rxq, tphdata_ena),  1,	195 },
 	{ I40E_HMC_STORE(i40e_hmc_obj_rxq, tphhead_ena),  1,	196 },
 	{ I40E_HMC_STORE(i40e_hmc_obj_rxq, lrxqthresh),   3,	198 },
+	{ I40E_HMC_STORE(i40e_hmc_obj_rxq, prefena),      1,	201 },
 	{ 0 }
 };
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h
index 341de925a29..eb65fe23c4a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h
@@ -56,6 +56,7 @@ struct i40e_hmc_obj_rxq {
 	u8  tphdata_ena;
 	u8  tphhead_ena;
 	u8  lrxqthresh;
+	u8  prefena;	/* NOTE: normally must be set to 1 at init */
 };
 
 /* Tx queue context data */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 2e72449f126..275ca9a1719 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -38,8 +38,8 @@ static const char i40e_driver_string[] =
 #define DRV_KERN "-k"
 
 #define DRV_VERSION_MAJOR 0
-#define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 36
+#define DRV_VERSION_MINOR 4
+#define DRV_VERSION_BUILD 10
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -67,12 +67,10 @@ static int i40e_veb_get_bw_info(struct i40e_veb *veb);
  */
 static DEFINE_PCI_DEVICE_TABLE(i40e_pci_tbl) = {
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_XL710), 0},
-	{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X710), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QEMU), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_A), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_B), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_C), 0},
-	{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_D), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_A), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_B), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0},
@@ -356,6 +354,7 @@ static struct rtnl_link_stats64 *i40e_get_netdev_stats_struct(
 					     struct rtnl_link_stats64 *stats)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_ring *tx_ring, *rx_ring;
 	struct i40e_vsi *vsi = np->vsi;
 	struct rtnl_link_stats64 *vsi_stats = i40e_get_vsi_stats_struct(vsi);
 	int i;
@@ -368,7 +367,6 @@ static struct rtnl_link_stats64 *i40e_get_netdev_stats_struct(
 
 	rcu_read_lock();
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
-		struct i40e_ring *tx_ring, *rx_ring;
 		u64 bytes, packets;
 		unsigned int start;
 
@@ -397,7 +395,7 @@ static struct rtnl_link_stats64 *i40e_get_netdev_stats_struct(
 	}
 	rcu_read_unlock();
 
-	/* following stats updated by ixgbe_watchdog_task() */
+	/* following stats updated by i40e_watchdog_subtask() */
 	stats->multicast	= vsi_stats->multicast;
 	stats->tx_errors	= vsi_stats->tx_errors;
 	stats->tx_dropped	= vsi_stats->tx_dropped;
@@ -530,6 +528,12 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi)
 	i40e_stat_update32(hw, I40E_GLV_RDPC(stat_idx),
 			   vsi->stat_offsets_loaded,
 			   &oes->rx_discards, &es->rx_discards);
+	i40e_stat_update32(hw, I40E_GLV_RUPP(stat_idx),
+			   vsi->stat_offsets_loaded,
+			   &oes->rx_unknown_protocol, &es->rx_unknown_protocol);
+	i40e_stat_update32(hw, I40E_GLV_TEPC(stat_idx),
+			   vsi->stat_offsets_loaded,
+			   &oes->tx_errors, &es->tx_errors);
 
 	i40e_stat_update48(hw, I40E_GLV_GORCH(stat_idx),
 			   I40E_GLV_GORCL(stat_idx),
@@ -648,10 +652,10 @@ static void i40e_update_link_xoff_rx(struct i40e_pf *pf)
 		return;
 
 	/* Clear the __I40E_HANG_CHECK_ARMED bit for all Tx rings */
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		struct i40e_vsi *vsi = pf->vsi[v];
 
-		if (!vsi)
+		if (!vsi || !vsi->tx_rings[0])
 			continue;
 
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
@@ -702,10 +706,10 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf)
 	}
 
 	/* Clear the __I40E_HANG_CHECK_ARMED bit for Tx rings */
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		struct i40e_vsi *vsi = pf->vsi[v];
 
-		if (!vsi)
+		if (!vsi || !vsi->tx_rings[0])
 			continue;
 
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
@@ -720,19 +724,18 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf)
 }
 
 /**
- * i40e_update_stats - Update the board statistics counters.
+ * i40e_update_vsi_stats - Update the vsi statistics counters.
  * @vsi: the VSI to be updated
  *
  * There are a few instances where we store the same stat in a
  * couple of different structs.  This is partly because we have
  * the netdev stats that need to be filled out, which is slightly
  * different from the "eth_stats" defined by the chip and used in
- * VF communications.  We sort it all out here in a central place.
+ * VF communications.  We sort it out here.
  **/
-void i40e_update_stats(struct i40e_vsi *vsi)
+static void i40e_update_vsi_stats(struct i40e_vsi *vsi)
 {
 	struct i40e_pf *pf = vsi->back;
-	struct i40e_hw *hw = &pf->hw;
 	struct rtnl_link_stats64 *ons;
 	struct rtnl_link_stats64 *ns;   /* netdev stats */
 	struct i40e_eth_stats *oes;
@@ -741,8 +744,6 @@ void i40e_update_stats(struct i40e_vsi *vsi)
 	u32 rx_page, rx_buf;
 	u64 rx_p, rx_b;
 	u64 tx_p, tx_b;
-	u32 val;
-	int i;
 	u16 q;
 
 	if (test_bit(__I40E_DOWN, &vsi->state) ||
@@ -804,196 +805,256 @@ void i40e_update_stats(struct i40e_vsi *vsi)
 	ns->tx_packets = tx_p;
 	ns->tx_bytes = tx_b;
 
-	i40e_update_eth_stats(vsi);
 	/* update netdev stats from eth stats */
-	ons->rx_errors = oes->rx_errors;
-	ns->rx_errors = es->rx_errors;
+	i40e_update_eth_stats(vsi);
 	ons->tx_errors = oes->tx_errors;
 	ns->tx_errors = es->tx_errors;
 	ons->multicast = oes->rx_multicast;
 	ns->multicast = es->rx_multicast;
+	ons->rx_dropped = oes->rx_discards;
+	ns->rx_dropped = es->rx_discards;
 	ons->tx_dropped = oes->tx_discards;
 	ns->tx_dropped = es->tx_discards;
 
-	/* Get the port data only if this is the main PF VSI */
+	/* pull in a couple PF stats if this is the main vsi */
 	if (vsi == pf->vsi[pf->lan_vsi]) {
-		struct i40e_hw_port_stats *nsd = &pf->stats;
-		struct i40e_hw_port_stats *osd = &pf->stats_offsets;
+		ns->rx_crc_errors = pf->stats.crc_errors;
+		ns->rx_errors = pf->stats.crc_errors + pf->stats.illegal_bytes;
+		ns->rx_length_errors = pf->stats.rx_length_errors;
+	}
+}
 
-		i40e_stat_update48(hw, I40E_GLPRT_GORCH(hw->port),
-				   I40E_GLPRT_GORCL(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->eth.rx_bytes, &nsd->eth.rx_bytes);
-		i40e_stat_update48(hw, I40E_GLPRT_GOTCH(hw->port),
-				   I40E_GLPRT_GOTCL(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->eth.tx_bytes, &nsd->eth.tx_bytes);
-		i40e_stat_update32(hw, I40E_GLPRT_RDPC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->eth.rx_discards,
-				   &nsd->eth.rx_discards);
-		i40e_stat_update32(hw, I40E_GLPRT_TDPC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->eth.tx_discards,
-				   &nsd->eth.tx_discards);
-		i40e_stat_update48(hw, I40E_GLPRT_MPRCH(hw->port),
-				   I40E_GLPRT_MPRCL(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->eth.rx_multicast,
-				   &nsd->eth.rx_multicast);
+/**
+ * i40e_update_pf_stats - Update the pf statistics counters.
+ * @pf: the PF to be updated
+ **/
+static void i40e_update_pf_stats(struct i40e_pf *pf)
+{
+	struct i40e_hw_port_stats *osd = &pf->stats_offsets;
+	struct i40e_hw_port_stats *nsd = &pf->stats;
+	struct i40e_hw *hw = &pf->hw;
+	u32 val;
+	int i;
 
-		i40e_stat_update32(hw, I40E_GLPRT_TDOLD(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->tx_dropped_link_down,
-				   &nsd->tx_dropped_link_down);
+	i40e_stat_update48(hw, I40E_GLPRT_GORCH(hw->port),
+			   I40E_GLPRT_GORCL(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.rx_bytes, &nsd->eth.rx_bytes);
+	i40e_stat_update48(hw, I40E_GLPRT_GOTCH(hw->port),
+			   I40E_GLPRT_GOTCL(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.tx_bytes, &nsd->eth.tx_bytes);
+	i40e_stat_update32(hw, I40E_GLPRT_RDPC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.rx_discards,
+			   &nsd->eth.rx_discards);
+	i40e_stat_update32(hw, I40E_GLPRT_TDPC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.tx_discards,
+			   &nsd->eth.tx_discards);
 
-		i40e_stat_update32(hw, I40E_GLPRT_CRCERRS(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->crc_errors, &nsd->crc_errors);
-		ns->rx_crc_errors = nsd->crc_errors;
+	i40e_stat_update48(hw, I40E_GLPRT_UPRCH(hw->port),
+			   I40E_GLPRT_UPRCL(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.rx_unicast,
+			   &nsd->eth.rx_unicast);
+	i40e_stat_update48(hw, I40E_GLPRT_MPRCH(hw->port),
+			   I40E_GLPRT_MPRCL(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.rx_multicast,
+			   &nsd->eth.rx_multicast);
+	i40e_stat_update48(hw, I40E_GLPRT_BPRCH(hw->port),
+			   I40E_GLPRT_BPRCL(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.rx_broadcast,
+			   &nsd->eth.rx_broadcast);
+	i40e_stat_update48(hw, I40E_GLPRT_UPTCH(hw->port),
+			   I40E_GLPRT_UPTCL(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.tx_unicast,
+			   &nsd->eth.tx_unicast);
+	i40e_stat_update48(hw, I40E_GLPRT_MPTCH(hw->port),
+			   I40E_GLPRT_MPTCL(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.tx_multicast,
+			   &nsd->eth.tx_multicast);
+	i40e_stat_update48(hw, I40E_GLPRT_BPTCH(hw->port),
+			   I40E_GLPRT_BPTCL(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->eth.tx_broadcast,
+			   &nsd->eth.tx_broadcast);
 
-		i40e_stat_update32(hw, I40E_GLPRT_ILLERRC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->illegal_bytes, &nsd->illegal_bytes);
-		ns->rx_errors = nsd->crc_errors
-				+ nsd->illegal_bytes;
+	i40e_stat_update32(hw, I40E_GLPRT_TDOLD(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->tx_dropped_link_down,
+			   &nsd->tx_dropped_link_down);
 
-		i40e_stat_update32(hw, I40E_GLPRT_MLFC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->mac_local_faults,
-				   &nsd->mac_local_faults);
-		i40e_stat_update32(hw, I40E_GLPRT_MRFC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->mac_remote_faults,
-				   &nsd->mac_remote_faults);
+	i40e_stat_update32(hw, I40E_GLPRT_CRCERRS(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->crc_errors, &nsd->crc_errors);
 
-		i40e_stat_update32(hw, I40E_GLPRT_RLEC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->rx_length_errors,
-				   &nsd->rx_length_errors);
-		ns->rx_length_errors = nsd->rx_length_errors;
+	i40e_stat_update32(hw, I40E_GLPRT_ILLERRC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->illegal_bytes, &nsd->illegal_bytes);
 
-		i40e_stat_update32(hw, I40E_GLPRT_LXONRXC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->link_xon_rx, &nsd->link_xon_rx);
-		i40e_stat_update32(hw, I40E_GLPRT_LXONTXC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->link_xon_tx, &nsd->link_xon_tx);
-		i40e_update_prio_xoff_rx(pf);  /* handles I40E_GLPRT_LXOFFRXC */
-		i40e_stat_update32(hw, I40E_GLPRT_LXOFFTXC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->link_xoff_tx, &nsd->link_xoff_tx);
-
-		for (i = 0; i < 8; i++) {
-			i40e_stat_update32(hw, I40E_GLPRT_PXONRXC(hw->port, i),
-					   pf->stat_offsets_loaded,
-					   &osd->priority_xon_rx[i],
-					   &nsd->priority_xon_rx[i]);
-			i40e_stat_update32(hw, I40E_GLPRT_PXONTXC(hw->port, i),
-					   pf->stat_offsets_loaded,
-					   &osd->priority_xon_tx[i],
-					   &nsd->priority_xon_tx[i]);
-			i40e_stat_update32(hw, I40E_GLPRT_PXOFFTXC(hw->port, i),
-					   pf->stat_offsets_loaded,
-					   &osd->priority_xoff_tx[i],
-					   &nsd->priority_xoff_tx[i]);
-			i40e_stat_update32(hw,
-					   I40E_GLPRT_RXON2OFFCNT(hw->port, i),
-					   pf->stat_offsets_loaded,
-					   &osd->priority_xon_2_xoff[i],
-					   &nsd->priority_xon_2_xoff[i]);
-		}
+	i40e_stat_update32(hw, I40E_GLPRT_MLFC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->mac_local_faults,
+			   &nsd->mac_local_faults);
+	i40e_stat_update32(hw, I40E_GLPRT_MRFC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->mac_remote_faults,
+			   &nsd->mac_remote_faults);
 
-		i40e_stat_update48(hw, I40E_GLPRT_PRC64H(hw->port),
-				   I40E_GLPRT_PRC64L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->rx_size_64, &nsd->rx_size_64);
-		i40e_stat_update48(hw, I40E_GLPRT_PRC127H(hw->port),
-				   I40E_GLPRT_PRC127L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->rx_size_127, &nsd->rx_size_127);
-		i40e_stat_update48(hw, I40E_GLPRT_PRC255H(hw->port),
-				   I40E_GLPRT_PRC255L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->rx_size_255, &nsd->rx_size_255);
-		i40e_stat_update48(hw, I40E_GLPRT_PRC511H(hw->port),
-				   I40E_GLPRT_PRC511L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->rx_size_511, &nsd->rx_size_511);
-		i40e_stat_update48(hw, I40E_GLPRT_PRC1023H(hw->port),
-				   I40E_GLPRT_PRC1023L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->rx_size_1023, &nsd->rx_size_1023);
-		i40e_stat_update48(hw, I40E_GLPRT_PRC1522H(hw->port),
-				   I40E_GLPRT_PRC1522L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->rx_size_1522, &nsd->rx_size_1522);
-		i40e_stat_update48(hw, I40E_GLPRT_PRC9522H(hw->port),
-				   I40E_GLPRT_PRC9522L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->rx_size_big, &nsd->rx_size_big);
+	i40e_stat_update32(hw, I40E_GLPRT_RLEC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_length_errors,
+			   &nsd->rx_length_errors);
 
-		i40e_stat_update48(hw, I40E_GLPRT_PTC64H(hw->port),
-				   I40E_GLPRT_PTC64L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->tx_size_64, &nsd->tx_size_64);
-		i40e_stat_update48(hw, I40E_GLPRT_PTC127H(hw->port),
-				   I40E_GLPRT_PTC127L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->tx_size_127, &nsd->tx_size_127);
-		i40e_stat_update48(hw, I40E_GLPRT_PTC255H(hw->port),
-				   I40E_GLPRT_PTC255L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->tx_size_255, &nsd->tx_size_255);
-		i40e_stat_update48(hw, I40E_GLPRT_PTC511H(hw->port),
-				   I40E_GLPRT_PTC511L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->tx_size_511, &nsd->tx_size_511);
-		i40e_stat_update48(hw, I40E_GLPRT_PTC1023H(hw->port),
-				   I40E_GLPRT_PTC1023L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->tx_size_1023, &nsd->tx_size_1023);
-		i40e_stat_update48(hw, I40E_GLPRT_PTC1522H(hw->port),
-				   I40E_GLPRT_PTC1522L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->tx_size_1522, &nsd->tx_size_1522);
-		i40e_stat_update48(hw, I40E_GLPRT_PTC9522H(hw->port),
-				   I40E_GLPRT_PTC9522L(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->tx_size_big, &nsd->tx_size_big);
+	i40e_stat_update32(hw, I40E_GLPRT_LXONRXC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->link_xon_rx, &nsd->link_xon_rx);
+	i40e_stat_update32(hw, I40E_GLPRT_LXONTXC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->link_xon_tx, &nsd->link_xon_tx);
+	i40e_update_prio_xoff_rx(pf);  /* handles I40E_GLPRT_LXOFFRXC */
+	i40e_stat_update32(hw, I40E_GLPRT_LXOFFTXC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->link_xoff_tx, &nsd->link_xoff_tx);
 
-		i40e_stat_update32(hw, I40E_GLPRT_RUC(hw->port),
-				   pf->stat_offsets_loaded,
-				   &osd->rx_undersize, &nsd->rx_undersize);
-		i40e_stat_update32(hw, I40E_GLPRT_RFC(hw->port),
+	for (i = 0; i < 8; i++) {
+		i40e_stat_update32(hw, I40E_GLPRT_PXONRXC(hw->port, i),
 				   pf->stat_offsets_loaded,
-				   &osd->rx_fragments, &nsd->rx_fragments);
-		i40e_stat_update32(hw, I40E_GLPRT_ROC(hw->port),
+				   &osd->priority_xon_rx[i],
+				   &nsd->priority_xon_rx[i]);
+		i40e_stat_update32(hw, I40E_GLPRT_PXONTXC(hw->port, i),
 				   pf->stat_offsets_loaded,
-				   &osd->rx_oversize, &nsd->rx_oversize);
-		i40e_stat_update32(hw, I40E_GLPRT_RJC(hw->port),
+				   &osd->priority_xon_tx[i],
+				   &nsd->priority_xon_tx[i]);
+		i40e_stat_update32(hw, I40E_GLPRT_PXOFFTXC(hw->port, i),
 				   pf->stat_offsets_loaded,
-				   &osd->rx_jabber, &nsd->rx_jabber);
-
-		val = rd32(hw, I40E_PRTPM_EEE_STAT);
-		nsd->tx_lpi_status =
-			       (val & I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_MASK) >>
-				I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT;
-		nsd->rx_lpi_status =
-			       (val & I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK) >>
-				I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT;
-		i40e_stat_update32(hw, I40E_PRTPM_TLPIC,
+				   &osd->priority_xoff_tx[i],
+				   &nsd->priority_xoff_tx[i]);
+		i40e_stat_update32(hw,
+				   I40E_GLPRT_RXON2OFFCNT(hw->port, i),
 				   pf->stat_offsets_loaded,
-				   &osd->tx_lpi_count, &nsd->tx_lpi_count);
-		i40e_stat_update32(hw, I40E_PRTPM_RLPIC,
-				   pf->stat_offsets_loaded,
-				   &osd->rx_lpi_count, &nsd->rx_lpi_count);
+				   &osd->priority_xon_2_xoff[i],
+				   &nsd->priority_xon_2_xoff[i]);
 	}
 
+	i40e_stat_update48(hw, I40E_GLPRT_PRC64H(hw->port),
+			   I40E_GLPRT_PRC64L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_size_64, &nsd->rx_size_64);
+	i40e_stat_update48(hw, I40E_GLPRT_PRC127H(hw->port),
+			   I40E_GLPRT_PRC127L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_size_127, &nsd->rx_size_127);
+	i40e_stat_update48(hw, I40E_GLPRT_PRC255H(hw->port),
+			   I40E_GLPRT_PRC255L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_size_255, &nsd->rx_size_255);
+	i40e_stat_update48(hw, I40E_GLPRT_PRC511H(hw->port),
+			   I40E_GLPRT_PRC511L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_size_511, &nsd->rx_size_511);
+	i40e_stat_update48(hw, I40E_GLPRT_PRC1023H(hw->port),
+			   I40E_GLPRT_PRC1023L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_size_1023, &nsd->rx_size_1023);
+	i40e_stat_update48(hw, I40E_GLPRT_PRC1522H(hw->port),
+			   I40E_GLPRT_PRC1522L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_size_1522, &nsd->rx_size_1522);
+	i40e_stat_update48(hw, I40E_GLPRT_PRC9522H(hw->port),
+			   I40E_GLPRT_PRC9522L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_size_big, &nsd->rx_size_big);
+
+	i40e_stat_update48(hw, I40E_GLPRT_PTC64H(hw->port),
+			   I40E_GLPRT_PTC64L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->tx_size_64, &nsd->tx_size_64);
+	i40e_stat_update48(hw, I40E_GLPRT_PTC127H(hw->port),
+			   I40E_GLPRT_PTC127L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->tx_size_127, &nsd->tx_size_127);
+	i40e_stat_update48(hw, I40E_GLPRT_PTC255H(hw->port),
+			   I40E_GLPRT_PTC255L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->tx_size_255, &nsd->tx_size_255);
+	i40e_stat_update48(hw, I40E_GLPRT_PTC511H(hw->port),
+			   I40E_GLPRT_PTC511L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->tx_size_511, &nsd->tx_size_511);
+	i40e_stat_update48(hw, I40E_GLPRT_PTC1023H(hw->port),
+			   I40E_GLPRT_PTC1023L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->tx_size_1023, &nsd->tx_size_1023);
+	i40e_stat_update48(hw, I40E_GLPRT_PTC1522H(hw->port),
+			   I40E_GLPRT_PTC1522L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->tx_size_1522, &nsd->tx_size_1522);
+	i40e_stat_update48(hw, I40E_GLPRT_PTC9522H(hw->port),
+			   I40E_GLPRT_PTC9522L(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->tx_size_big, &nsd->tx_size_big);
+
+	i40e_stat_update32(hw, I40E_GLPRT_RUC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_undersize, &nsd->rx_undersize);
+	i40e_stat_update32(hw, I40E_GLPRT_RFC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_fragments, &nsd->rx_fragments);
+	i40e_stat_update32(hw, I40E_GLPRT_ROC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_oversize, &nsd->rx_oversize);
+	i40e_stat_update32(hw, I40E_GLPRT_RJC(hw->port),
+			   pf->stat_offsets_loaded,
+			   &osd->rx_jabber, &nsd->rx_jabber);
+
+	/* FDIR stats */
+	i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_atr_cnt_idx),
+			   pf->stat_offsets_loaded,
+			   &osd->fd_atr_match, &nsd->fd_atr_match);
+	i40e_stat_update32(hw, I40E_GLQF_PCNT(pf->fd_sb_cnt_idx),
+			   pf->stat_offsets_loaded,
+			   &osd->fd_sb_match, &nsd->fd_sb_match);
+
+	val = rd32(hw, I40E_PRTPM_EEE_STAT);
+	nsd->tx_lpi_status =
+		       (val & I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_MASK) >>
+			I40E_PRTPM_EEE_STAT_TX_LPI_STATUS_SHIFT;
+	nsd->rx_lpi_status =
+		       (val & I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_MASK) >>
+			I40E_PRTPM_EEE_STAT_RX_LPI_STATUS_SHIFT;
+	i40e_stat_update32(hw, I40E_PRTPM_TLPIC,
+			   pf->stat_offsets_loaded,
+			   &osd->tx_lpi_count, &nsd->tx_lpi_count);
+	i40e_stat_update32(hw, I40E_PRTPM_RLPIC,
+			   pf->stat_offsets_loaded,
+			   &osd->rx_lpi_count, &nsd->rx_lpi_count);
+
 	pf->stat_offsets_loaded = true;
 }
 
 /**
+ * i40e_update_stats - Update the various statistics counters.
+ * @vsi: the VSI to be updated
+ *
+ * Update the various stats for this VSI and its related entities.
+ **/
+void i40e_update_stats(struct i40e_vsi *vsi)
+{
+	struct i40e_pf *pf = vsi->back;
+
+	if (vsi == pf->vsi[pf->lan_vsi])
+		i40e_update_pf_stats(pf);
+
+	i40e_update_vsi_stats(vsi);
+}
+
+/**
  * i40e_find_filter - Search VSI filter list for specific mac/vlan filter
  * @vsi: the VSI to be searched
  * @macaddr: the MAC address
@@ -1101,6 +1162,30 @@ struct i40e_mac_filter *i40e_put_mac_in_vlan(struct i40e_vsi *vsi, u8 *macaddr,
 }
 
 /**
+ * i40e_rm_default_mac_filter - Remove the default MAC filter set by NVM
+ * @vsi: the PF Main VSI - inappropriate for any other VSI
+ * @macaddr: the MAC address
+ **/
+static void i40e_rm_default_mac_filter(struct i40e_vsi *vsi, u8 *macaddr)
+{
+	struct i40e_aqc_remove_macvlan_element_data element;
+	struct i40e_pf *pf = vsi->back;
+	i40e_status aq_ret;
+
+	/* Only appropriate for the PF main VSI */
+	if (vsi->type != I40E_VSI_MAIN)
+		return;
+
+	ether_addr_copy(element.mac_addr, macaddr);
+	element.vlan_tag = 0;
+	element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH |
+			I40E_AQC_MACVLAN_DEL_IGNORE_VLAN;
+	aq_ret = i40e_aq_remove_macvlan(&pf->hw, vsi->seid, &element, 1, NULL);
+	if (aq_ret)
+		dev_err(&pf->pdev->dev, "Could not remove default MAC-VLAN\n");
+}
+
+/**
  * i40e_add_filter - Add a mac/vlan filter to the VSI
  * @vsi: the VSI to be searched
  * @macaddr: the MAC address
@@ -1125,7 +1210,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi,
 		if (!f)
 			goto add_filter_out;
 
-		memcpy(f->macaddr, macaddr, ETH_ALEN);
+		ether_addr_copy(f->macaddr, macaddr);
 		f->vlan = vlan;
 		f->changed = true;
 
@@ -1249,7 +1334,7 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 			return -EADDRNOTAVAIL;
 		}
 
-		memcpy(vsi->back->hw.mac.addr, addr->sa_data, netdev->addr_len);
+		ether_addr_copy(vsi->back->hw.mac.addr, addr->sa_data);
 	}
 
 	/* In order to be sure to not drop any packets, add the new address
@@ -1263,7 +1348,7 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
 	i40e_del_filter(vsi, netdev->dev_addr, I40E_VLAN_ANY, false, false);
 	i40e_sync_vsi_filters(vsi);
 
-	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
+	ether_addr_copy(netdev->dev_addr, addr->sa_data);
 
 	return 0;
 }
@@ -1313,7 +1398,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 	vsi->tc_config.numtc = numtc;
 	vsi->tc_config.enabled_tc = enabled_tc ? enabled_tc : 1;
 	/* Number of queues per enabled TC */
-	num_tc_qps = rounddown_pow_of_two(vsi->alloc_queue_pairs/numtc);
+	num_tc_qps = vsi->alloc_queue_pairs/numtc;
 	num_tc_qps = min_t(int, num_tc_qps, I40E_MAX_QUEUES_PER_TC);
 
 	/* Setup queue offset/count for all TCs for given VSI */
@@ -1520,8 +1605,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 			cmd_flags = 0;
 
 			/* add to delete list */
-			memcpy(del_list[num_del].mac_addr,
-			       f->macaddr, ETH_ALEN);
+			ether_addr_copy(del_list[num_del].mac_addr, f->macaddr);
 			del_list[num_del].vlan_tag =
 				cpu_to_le16((u16)(f->vlan ==
 					    I40E_VLAN_ANY ? 0 : f->vlan));
@@ -1542,7 +1626,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 				num_del = 0;
 				memset(del_list, 0, sizeof(*del_list));
 
-				if (aq_ret)
+				if (aq_ret &&
+				    pf->hw.aq.asq_last_status !=
+							      I40E_AQ_RC_ENOENT)
 					dev_info(&pf->pdev->dev,
 						 "ignoring delete macvlan error, err %d, aq_err %d while flushing a full buffer\n",
 						 aq_ret,
@@ -1554,7 +1640,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 						     del_list, num_del, NULL);
 			num_del = 0;
 
-			if (aq_ret)
+			if (aq_ret &&
+			    pf->hw.aq.asq_last_status != I40E_AQ_RC_ENOENT)
 				dev_info(&pf->pdev->dev,
 					 "ignoring delete macvlan error, err %d, aq_err %d\n",
 					 aq_ret, pf->hw.aq.asq_last_status);
@@ -1583,8 +1670,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 			cmd_flags = 0;
 
 			/* add to add array */
-			memcpy(add_list[num_add].mac_addr,
-			       f->macaddr, ETH_ALEN);
+			ether_addr_copy(add_list[num_add].mac_addr, f->macaddr);
 			add_list[num_add].vlan_tag =
 				cpu_to_le16(
 				 (u16)(f->vlan == I40E_VLAN_ANY ? 0 : f->vlan));
@@ -1681,7 +1767,7 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf)
 		return;
 	pf->flags &= ~I40E_FLAG_FILTER_SYNC;
 
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v] &&
 		    (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED))
 			i40e_sync_vsi_filters(pf->vsi[v]);
@@ -1698,7 +1784,7 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf)
 static int i40e_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
-	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN;
+	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
 	struct i40e_vsi *vsi = np->vsi;
 
 	/* MTU < 68 is an error and causes problems on some kernels */
@@ -2312,6 +2398,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	rx_ctx.crcstrip = 1;
 	rx_ctx.l2tsel = 1;
 	rx_ctx.showiv = 1;
+	/* set the prefena field to 1 because the manual says to */
+	rx_ctx.prefena = 1;
 
 	/* clear the context in the HMC */
 	err = i40e_clear_lan_rx_queue_context(hw, pf_q);
@@ -2413,6 +2501,7 @@ static int i40e_vsi_configure_rx(struct i40e_vsi *vsi)
  **/
 static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi)
 {
+	struct i40e_ring *tx_ring, *rx_ring;
 	u16 qoffset, qcount;
 	int i, n;
 
@@ -2426,8 +2515,8 @@ static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi)
 		qoffset = vsi->tc_config.tc_info[n].qoffset;
 		qcount = vsi->tc_config.tc_info[n].qcount;
 		for (i = qoffset; i < (qoffset + qcount); i++) {
-			struct i40e_ring *rx_ring = vsi->rx_rings[i];
-			struct i40e_ring *tx_ring = vsi->tx_rings[i];
+			rx_ring = vsi->rx_rings[i];
+			tx_ring = vsi->tx_rings[i];
 			rx_ring->dcb_tc = n;
 			tx_ring->dcb_tc = n;
 		}
@@ -2565,7 +2654,6 @@ static void i40e_enable_misc_int_causes(struct i40e_hw *hw)
 	      I40E_PFINT_ICR0_ENA_PCI_EXCEPTION_MASK |
 	      I40E_PFINT_ICR0_ENA_GPIO_MASK          |
 	      I40E_PFINT_ICR0_ENA_TIMESYNC_MASK      |
-	      I40E_PFINT_ICR0_ENA_STORM_DETECT_MASK  |
 	      I40E_PFINT_ICR0_ENA_HMC_ERR_MASK       |
 	      I40E_PFINT_ICR0_ENA_VFLR_MASK          |
 	      I40E_PFINT_ICR0_ENA_ADMINQ_MASK;
@@ -2733,6 +2821,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 				      &q_vector->affinity_mask);
 	}
 
+	vsi->irqs_ready = true;
 	return 0;
 
 free_queue_irqs:
@@ -3152,6 +3241,12 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 
 	pf_q = vsi->base_queue;
 	for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
+
+		/* warn the TX unit of coming changes */
+		i40e_pre_tx_queue_cfg(&pf->hw, pf_q, enable);
+		if (!enable)
+			udelay(10);
+
 		for (j = 0; j < 50; j++) {
 			tx_reg = rd32(hw, I40E_QTX_ENA(pf_q));
 			if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) ==
@@ -3160,9 +3255,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 			usleep_range(1000, 2000);
 		}
 		/* Skip if the queue is already in the requested state */
-		if (enable && (tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
-			continue;
-		if (!enable && !(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
+		if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
 			continue;
 
 		/* turn on/off the queue */
@@ -3178,13 +3271,8 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
 		/* wait for the change to finish */
 		for (j = 0; j < 10; j++) {
 			tx_reg = rd32(hw, I40E_QTX_ENA(pf_q));
-			if (enable) {
-				if ((tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
-					break;
-			} else {
-				if (!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
-					break;
-			}
+			if (enable == !!(tx_reg & I40E_QTX_ENA_QENA_STAT_MASK))
+				break;
 
 			udelay(10);
 		}
@@ -3223,15 +3311,9 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
 			usleep_range(1000, 2000);
 		}
 
-		if (enable) {
-			/* is STAT set ? */
-			if ((rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
-				continue;
-		} else {
-			/* is !STAT set ? */
-			if (!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
-				continue;
-		}
+		/* Skip if the queue is already in the requested state */
+		if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
+			continue;
 
 		/* turn on/off the queue */
 		if (enable)
@@ -3244,13 +3326,8 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
 		for (j = 0; j < 10; j++) {
 			rx_reg = rd32(hw, I40E_QRX_ENA(pf_q));
 
-			if (enable) {
-				if ((rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
-					break;
-			} else {
-				if (!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
-					break;
-			}
+			if (enable == !!(rx_reg & I40E_QRX_ENA_QENA_STAT_MASK))
+				break;
 
 			udelay(10);
 		}
@@ -3304,6 +3381,10 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
 		if (!vsi->q_vectors)
 			return;
 
+		if (!vsi->irqs_ready)
+			return;
+
+		vsi->irqs_ready = false;
 		for (i = 0; i < vsi->num_q_vectors; i++) {
 			u16 vector = i + base;
 
@@ -3476,7 +3557,7 @@ static void i40e_clear_interrupt_scheme(struct i40e_pf *pf)
 	int i;
 
 	i40e_put_lump(pf->irq_pile, 0, I40E_PILE_VALID_BIT-1);
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+	for (i = 0; i < pf->num_alloc_vsi; i++)
 		if (pf->vsi[i])
 			i40e_vsi_free_q_vectors(pf->vsi[i]);
 	i40e_reset_interrupt_capability(pf);
@@ -3513,6 +3594,19 @@ static void i40e_napi_disable_all(struct i40e_vsi *vsi)
 }
 
 /**
+ * i40e_vsi_close - Shut down a VSI
+ * @vsi: the vsi to be quelled
+ **/
+static void i40e_vsi_close(struct i40e_vsi *vsi)
+{
+	if (!test_and_set_bit(__I40E_DOWN, &vsi->state))
+		i40e_down(vsi);
+	i40e_vsi_free_irq(vsi);
+	i40e_vsi_free_tx_resources(vsi);
+	i40e_vsi_free_rx_resources(vsi);
+}
+
+/**
  * i40e_quiesce_vsi - Pause a given VSI
  * @vsi: the VSI being paused
  **/
@@ -3525,8 +3619,7 @@ static void i40e_quiesce_vsi(struct i40e_vsi *vsi)
 	if (vsi->netdev && netif_running(vsi->netdev)) {
 		vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
 	} else {
-		set_bit(__I40E_DOWN, &vsi->state);
-		i40e_down(vsi);
+		i40e_vsi_close(vsi);
 	}
 }
 
@@ -3543,7 +3636,7 @@ static void i40e_unquiesce_vsi(struct i40e_vsi *vsi)
 	if (vsi->netdev && netif_running(vsi->netdev))
 		vsi->netdev->netdev_ops->ndo_open(vsi->netdev);
 	else
-		i40e_up(vsi);   /* this clears the DOWN bit */
+		i40e_vsi_open(vsi);   /* this clears the DOWN bit */
 }
 
 /**
@@ -3554,7 +3647,7 @@ static void i40e_pf_quiesce_all_vsi(struct i40e_pf *pf)
 {
 	int v;
 
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v])
 			i40e_quiesce_vsi(pf->vsi[v]);
 	}
@@ -3568,7 +3661,7 @@ static void i40e_pf_unquiesce_all_vsi(struct i40e_pf *pf)
 {
 	int v;
 
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v])
 			i40e_unquiesce_vsi(pf->vsi[v]);
 	}
@@ -4009,7 +4102,7 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
 	}
 
 	/* Update each VSI */
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (!pf->vsi[v])
 			continue;
 
@@ -4028,6 +4121,8 @@ static void i40e_dcb_reconfigure(struct i40e_pf *pf)
 				 pf->vsi[v]->seid);
 			/* Will try to configure as many components */
 		} else {
+			/* Re-configure VSI vectors based on updated TC map */
+			i40e_vsi_map_rings_to_vectors(pf->vsi[v]);
 			if (pf->vsi[v]->netdev)
 				i40e_dcbnl_set_all(pf->vsi[v]);
 		}
@@ -4065,14 +4160,69 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 			/* When status is not DISABLED then DCBX in FW */
 			pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED |
 				       DCB_CAP_DCBX_VER_IEEE;
-			pf->flags |= I40E_FLAG_DCB_ENABLED;
+
+			pf->flags |= I40E_FLAG_DCB_CAPABLE;
+			/* Enable DCB tagging only when more than one TC */
+			if (i40e_dcb_get_num_tc(&hw->local_dcbx_config) > 1)
+				pf->flags |= I40E_FLAG_DCB_ENABLED;
 		}
+	} else {
+		dev_info(&pf->pdev->dev, "AQ Querying DCB configuration failed: %d\n",
+			 pf->hw.aq.asq_last_status);
 	}
 
 out:
 	return err;
 }
 #endif /* CONFIG_I40E_DCB */
+#define SPEED_SIZE 14
+#define FC_SIZE 8
+/**
+ * i40e_print_link_message - print link up or down
+ * @vsi: the VSI for which link needs a message
+ */
+static void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
+{
+	char speed[SPEED_SIZE] = "Unknown";
+	char fc[FC_SIZE] = "RX/TX";
+
+	if (!isup) {
+		netdev_info(vsi->netdev, "NIC Link is Down\n");
+		return;
+	}
+
+	switch (vsi->back->hw.phy.link_info.link_speed) {
+	case I40E_LINK_SPEED_40GB:
+		strncpy(speed, "40 Gbps", SPEED_SIZE);
+		break;
+	case I40E_LINK_SPEED_10GB:
+		strncpy(speed, "10 Gbps", SPEED_SIZE);
+		break;
+	case I40E_LINK_SPEED_1GB:
+		strncpy(speed, "1000 Mbps", SPEED_SIZE);
+		break;
+	default:
+		break;
+	}
+
+	switch (vsi->back->hw.fc.current_mode) {
+	case I40E_FC_FULL:
+		strncpy(fc, "RX/TX", FC_SIZE);
+		break;
+	case I40E_FC_TX_PAUSE:
+		strncpy(fc, "TX", FC_SIZE);
+		break;
+	case I40E_FC_RX_PAUSE:
+		strncpy(fc, "RX", FC_SIZE);
+		break;
+	default:
+		strncpy(fc, "None", FC_SIZE);
+		break;
+	}
+
+	netdev_info(vsi->netdev, "NIC Link is Up %s Full Duplex, Flow Control: %s\n",
+		    speed, fc);
+}
 
 /**
  * i40e_up_complete - Finish the last steps of bringing up a connection
@@ -4099,11 +4249,11 @@ static int i40e_up_complete(struct i40e_vsi *vsi)
 
 	if ((pf->hw.phy.link_info.link_info & I40E_AQ_LINK_UP) &&
 	    (vsi->netdev)) {
-		netdev_info(vsi->netdev, "NIC Link is Up\n");
+		i40e_print_link_message(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);
 	} else if (vsi->netdev) {
-		netdev_info(vsi->netdev, "NIC Link is Down\n");
+		i40e_print_link_message(vsi, false);
 	}
 
 	/* replay FDIR SB filters */
@@ -4309,24 +4459,32 @@ int i40e_vsi_open(struct i40e_vsi *vsi)
 	if (err)
 		goto err_setup_rx;
 
-	if (!vsi->netdev) {
-		err = EINVAL;
-		goto err_setup_rx;
-	}
-	snprintf(int_name, sizeof(int_name) - 1, "%s-%s",
-		 dev_driver_string(&pf->pdev->dev), vsi->netdev->name);
-	err = i40e_vsi_request_irq(vsi, int_name);
-	if (err)
-		goto err_setup_rx;
+	if (vsi->netdev) {
+		snprintf(int_name, sizeof(int_name) - 1, "%s-%s",
+			 dev_driver_string(&pf->pdev->dev), vsi->netdev->name);
+		err = i40e_vsi_request_irq(vsi, int_name);
+		if (err)
+			goto err_setup_rx;
 
-	/* Notify the stack of the actual queue counts. */
-	err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_queue_pairs);
-	if (err)
-		goto err_set_queues;
+		/* Notify the stack of the actual queue counts. */
+		err = netif_set_real_num_tx_queues(vsi->netdev,
+						   vsi->num_queue_pairs);
+		if (err)
+			goto err_set_queues;
 
-	err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_queue_pairs);
-	if (err)
-		goto err_set_queues;
+		err = netif_set_real_num_rx_queues(vsi->netdev,
+						   vsi->num_queue_pairs);
+		if (err)
+			goto err_set_queues;
+
+	} else if (vsi->type == I40E_VSI_FDIR) {
+		snprintf(int_name, sizeof(int_name) - 1, "%s-fdir",
+			 dev_driver_string(&pf->pdev->dev));
+		err = i40e_vsi_request_irq(vsi, int_name);
+	} else {
+		err = -EINVAL;
+		goto err_setup_rx;
+	}
 
 	err = i40e_up_complete(vsi);
 	if (err)
@@ -4383,14 +4541,7 @@ static int i40e_close(struct net_device *netdev)
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_vsi *vsi = np->vsi;
 
-	if (test_and_set_bit(__I40E_DOWN, &vsi->state))
-		return 0;
-
-	i40e_down(vsi);
-	i40e_vsi_free_irq(vsi);
-
-	i40e_vsi_free_tx_resources(vsi);
-	i40e_vsi_free_rx_resources(vsi);
+	i40e_vsi_close(vsi);
 
 	return 0;
 }
@@ -4410,6 +4561,9 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
 
 	WARN_ON(in_interrupt());
 
+	if (i40e_check_asq_alive(&pf->hw))
+		i40e_vc_notify_reset(pf);
+
 	/* do the biggest reset indicated */
 	if (reset_flags & (1 << __I40E_GLOBAL_RESET_REQUESTED)) {
 
@@ -4475,7 +4629,7 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags)
 		/* Find the VSI(s) that requested a re-init */
 		dev_info(&pf->pdev->dev,
 			 "VSI reinit requested\n");
-		for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+		for (v = 0; v < pf->num_alloc_vsi; v++) {
 			struct i40e_vsi *vsi = pf->vsi[v];
 			if (vsi != NULL &&
 			    test_bit(__I40E_REINIT_REQUESTED, &vsi->state)) {
@@ -4565,6 +4719,10 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	int ret = 0;
 	u8 type;
 
+	/* Not DCB capable or capability disabled */
+	if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
+		return ret;
+
 	/* Ignore if event is not for Nearest Bridge */
 	type = ((mib->type >> I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT)
 		& I40E_AQ_LLDP_BRIDGE_TYPE_MASK);
@@ -4606,6 +4764,12 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 	if (!need_reconfig)
 		goto exit;
 
+	/* Enable DCB tagging only when more than one TC */
+	if (i40e_dcb_get_num_tc(dcbx_cfg) > 1)
+		pf->flags |= I40E_FLAG_DCB_ENABLED;
+	else
+		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+
 	/* Reconfiguration needed quiesce all VSIs */
 	i40e_pf_quiesce_all_vsi(pf);
 
@@ -4709,8 +4873,7 @@ void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
 	    (pf->flags & I40E_FLAG_FD_SB_ENABLED))
 		return;
 	fcnt_prog = i40e_get_current_fd_count(pf);
-	fcnt_avail = pf->hw.fdir_shared_filter_count +
-					       pf->fdir_pf_filter_count;
+	fcnt_avail = i40e_get_fd_cnt_all(pf);
 	if (fcnt_prog < (fcnt_avail - I40E_FDIR_BUFFER_HEAD_ROOM)) {
 		if ((pf->flags & I40E_FLAG_FD_SB_ENABLED) &&
 		    (pf->auto_disable_flags & I40E_FLAG_FD_SB_ENABLED)) {
@@ -4803,7 +4966,7 @@ static void i40e_veb_link_event(struct i40e_veb *veb, bool link_up)
 			i40e_veb_link_event(pf->veb[i], link_up);
 
 	/* ... now the local VSIs */
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+	for (i = 0; i < pf->num_alloc_vsi; i++)
 		if (pf->vsi[i] && (pf->vsi[i]->uplink_seid == veb->seid))
 			i40e_vsi_link_event(pf->vsi[i], link_up);
 }
@@ -4821,10 +4984,8 @@ static void i40e_link_event(struct i40e_pf *pf)
 
 	if (new_link == old_link)
 		return;
-
 	if (!test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state))
-		netdev_info(pf->vsi[pf->lan_vsi]->netdev,
-			    "NIC Link is %s\n", (new_link ? "Up" : "Down"));
+		i40e_print_link_message(pf->vsi[pf->lan_vsi], new_link);
 
 	/* Notify the base of the switch tree connected to
 	 * the link.  Floating VEBs are not notified.
@@ -4862,7 +5023,7 @@ static void i40e_check_hang_subtask(struct i40e_pf *pf)
 	 *     for each q_vector
 	 *         force an interrupt
 	 */
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		struct i40e_vsi *vsi = pf->vsi[v];
 		int armed = 0;
 
@@ -4912,7 +5073,7 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf)
 	/* Update the stats for active netdevs so the network stack
 	 * can look at updated numbers whenever it cares to
 	 */
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+	for (i = 0; i < pf->num_alloc_vsi; i++)
 		if (pf->vsi[i] && pf->vsi[i]->netdev)
 			i40e_update_stats(pf->vsi[i]);
 
@@ -5018,11 +5179,47 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf)
 	u16 pending, i = 0;
 	i40e_status ret;
 	u16 opcode;
+	u32 oldval;
 	u32 val;
 
 	if (!test_bit(__I40E_ADMINQ_EVENT_PENDING, &pf->state))
 		return;
 
+	/* check for error indications */
+	val = rd32(&pf->hw, pf->hw.aq.arq.len);
+	oldval = val;
+	if (val & I40E_PF_ARQLEN_ARQVFE_MASK) {
+		dev_info(&pf->pdev->dev, "ARQ VF Error detected\n");
+		val &= ~I40E_PF_ARQLEN_ARQVFE_MASK;
+	}
+	if (val & I40E_PF_ARQLEN_ARQOVFL_MASK) {
+		dev_info(&pf->pdev->dev, "ARQ Overflow Error detected\n");
+		val &= ~I40E_PF_ARQLEN_ARQOVFL_MASK;
+	}
+	if (val & I40E_PF_ARQLEN_ARQCRIT_MASK) {
+		dev_info(&pf->pdev->dev, "ARQ Critical Error detected\n");
+		val &= ~I40E_PF_ARQLEN_ARQCRIT_MASK;
+	}
+	if (oldval != val)
+		wr32(&pf->hw, pf->hw.aq.arq.len, val);
+
+	val = rd32(&pf->hw, pf->hw.aq.asq.len);
+	oldval = val;
+	if (val & I40E_PF_ATQLEN_ATQVFE_MASK) {
+		dev_info(&pf->pdev->dev, "ASQ VF Error detected\n");
+		val &= ~I40E_PF_ATQLEN_ATQVFE_MASK;
+	}
+	if (val & I40E_PF_ATQLEN_ATQOVFL_MASK) {
+		dev_info(&pf->pdev->dev, "ASQ Overflow Error detected\n");
+		val &= ~I40E_PF_ATQLEN_ATQOVFL_MASK;
+	}
+	if (val & I40E_PF_ATQLEN_ATQCRIT_MASK) {
+		dev_info(&pf->pdev->dev, "ASQ Critical Error detected\n");
+		val &= ~I40E_PF_ATQLEN_ATQCRIT_MASK;
+	}
+	if (oldval != val)
+		wr32(&pf->hw, pf->hw.aq.asq.len, val);
+
 	event.msg_size = I40E_MAX_AQ_BUF_SIZE;
 	event.msg_buf = kzalloc(event.msg_size, GFP_KERNEL);
 	if (!event.msg_buf)
@@ -5128,7 +5325,7 @@ static int i40e_reconstitute_veb(struct i40e_veb *veb)
 	int ret;
 
 	/* build VSI that owns this VEB, temporarily attached to base VEB */
-	for (v = 0; v < pf->hw.func_caps.num_vsis && !ctl_vsi; v++) {
+	for (v = 0; v < pf->num_alloc_vsi && !ctl_vsi; v++) {
 		if (pf->vsi[v] &&
 		    pf->vsi[v]->veb_idx == veb->idx &&
 		    pf->vsi[v]->flags & I40E_VSI_FLAG_VEB_OWNER) {
@@ -5158,7 +5355,7 @@ static int i40e_reconstitute_veb(struct i40e_veb *veb)
 		goto end_reconstitute;
 
 	/* create the remaining VSIs attached to this VEB */
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (!pf->vsi[v] || pf->vsi[v] == ctl_vsi)
 			continue;
 
@@ -5226,9 +5423,6 @@ static int i40e_get_capabilities(struct i40e_pf *pf)
 		}
 	} while (err);
 
-	/* increment MSI-X count because current FW skips one */
-	pf->hw.func_caps.num_msix_vectors++;
-
 	if (((pf->hw.aq.fw_maj_ver == 2) && (pf->hw.aq.fw_min_ver < 22)) ||
 	    (pf->hw.aq.fw_maj_ver < 2)) {
 		pf->hw.func_caps.num_msix_vectors++;
@@ -5267,15 +5461,14 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi);
 static void i40e_fdir_sb_setup(struct i40e_pf *pf)
 {
 	struct i40e_vsi *vsi;
-	bool new_vsi = false;
-	int err, i;
+	int i;
 
 	if (!(pf->flags & I40E_FLAG_FD_SB_ENABLED))
 		return;
 
 	/* find existing VSI and see if it needs configuring */
 	vsi = NULL;
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+	for (i = 0; i < pf->num_alloc_vsi; i++) {
 		if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) {
 			vsi = pf->vsi[i];
 			break;
@@ -5288,47 +5481,12 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf)
 				     pf->vsi[pf->lan_vsi]->seid, 0);
 		if (!vsi) {
 			dev_info(&pf->pdev->dev, "Couldn't create FDir VSI\n");
-			goto err_vsi;
+			pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
+			return;
 		}
-		new_vsi = true;
-	}
-	i40e_vsi_setup_irqhandler(vsi, i40e_fdir_clean_ring);
-
-	err = i40e_vsi_setup_tx_resources(vsi);
-	if (err)
-		goto err_setup_tx;
-	err = i40e_vsi_setup_rx_resources(vsi);
-	if (err)
-		goto err_setup_rx;
-
-	if (new_vsi) {
-		char int_name[IFNAMSIZ + 9];
-		err = i40e_vsi_configure(vsi);
-		if (err)
-			goto err_setup_rx;
-		snprintf(int_name, sizeof(int_name) - 1, "%s-fdir",
-			 dev_driver_string(&pf->pdev->dev));
-		err = i40e_vsi_request_irq(vsi, int_name);
-		if (err)
-			goto err_setup_rx;
-		err = i40e_up_complete(vsi);
-		if (err)
-			goto err_up_complete;
-		clear_bit(__I40E_NEEDS_RESTART, &vsi->state);
 	}
 
-	return;
-
-err_up_complete:
-	i40e_down(vsi);
-	i40e_vsi_free_irq(vsi);
-err_setup_rx:
-	i40e_vsi_free_rx_resources(vsi);
-err_setup_tx:
-	i40e_vsi_free_tx_resources(vsi);
-err_vsi:
-	pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
-	i40e_vsi_clear(vsi);
+	i40e_vsi_setup_irqhandler(vsi, i40e_fdir_clean_ring);
 }
 
 /**
@@ -5340,7 +5498,7 @@ static void i40e_fdir_teardown(struct i40e_pf *pf)
 	int i;
 
 	i40e_fdir_filter_exit(pf);
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+	for (i = 0; i < pf->num_alloc_vsi; i++) {
 		if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) {
 			i40e_vsi_release(pf->vsi[i]);
 			break;
@@ -5357,7 +5515,7 @@ static void i40e_fdir_teardown(struct i40e_pf *pf)
 static int i40e_prep_for_reset(struct i40e_pf *pf)
 {
 	struct i40e_hw *hw = &pf->hw;
-	i40e_status ret;
+	i40e_status ret = 0;
 	u32 v;
 
 	clear_bit(__I40E_RESET_INTR_RECEIVED, &pf->state);
@@ -5366,13 +5524,10 @@ static int i40e_prep_for_reset(struct i40e_pf *pf)
 
 	dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n");
 
-	if (i40e_check_asq_alive(hw))
-		i40e_vc_notify_reset(pf);
-
 	/* quiesce the VSIs and their queues that are not already DOWN */
 	i40e_pf_quiesce_all_vsi(pf);
 
-	for (v = 0; v < pf->hw.func_caps.num_vsis; v++) {
+	for (v = 0; v < pf->num_alloc_vsi; v++) {
 		if (pf->vsi[v])
 			pf->vsi[v]->seid = 0;
 	}
@@ -5380,22 +5535,40 @@ static int i40e_prep_for_reset(struct i40e_pf *pf)
 	i40e_shutdown_adminq(&pf->hw);
 
 	/* call shutdown HMC */
-	ret = i40e_shutdown_lan_hmc(hw);
-	if (ret) {
-		dev_info(&pf->pdev->dev, "shutdown_lan_hmc failed: %d\n", ret);
-		clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state);
+	if (hw->hmc.hmc_obj) {
+		ret = i40e_shutdown_lan_hmc(hw);
+		if (ret) {
+			dev_warn(&pf->pdev->dev,
+				 "shutdown_lan_hmc failed: %d\n", ret);
+			clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state);
+		}
 	}
 	return ret;
 }
 
 /**
+ * i40e_send_version - update firmware with driver version
+ * @pf: PF struct
+ */
+static void i40e_send_version(struct i40e_pf *pf)
+{
+	struct i40e_driver_version dv;
+
+	dv.major_version = DRV_VERSION_MAJOR;
+	dv.minor_version = DRV_VERSION_MINOR;
+	dv.build_version = DRV_VERSION_BUILD;
+	dv.subbuild_version = 0;
+	strncpy(dv.driver_string, DRV_VERSION, sizeof(dv.driver_string));
+	i40e_aq_send_driver_version(&pf->hw, &dv, NULL);
+}
+
+/**
  * i40e_reset_and_rebuild - reset and rebuild using a saved config
  * @pf: board private structure
  * @reinit: if the Main VSI needs to re-initialized.
  **/
 static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 {
-	struct i40e_driver_version dv;
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret;
 	u32 v;
@@ -5405,8 +5578,10 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	 * because the reset will make them disappear.
 	 */
 	ret = i40e_pf_reset(hw);
-	if (ret)
+	if (ret) {
 		dev_info(&pf->pdev->dev, "PF reset failed, %d\n", ret);
+		goto end_core_reset;
+	}
 	pf->pfr_count++;
 
 	if (test_bit(__I40E_DOWN, &pf->state))
@@ -5426,6 +5601,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 		i40e_verify_eeprom(pf);
 	}
 
+	i40e_clear_pxe_mode(hw);
 	ret = i40e_get_capabilities(pf);
 	if (ret) {
 		dev_info(&pf->pdev->dev, "i40e_get_capabilities failed, %d\n",
@@ -5526,13 +5702,7 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit)
 	}
 
 	/* tell the firmware that we're starting */
-	dv.major_version = DRV_VERSION_MAJOR;
-	dv.minor_version = DRV_VERSION_MINOR;
-	dv.build_version = DRV_VERSION_BUILD;
-	dv.subbuild_version = 0;
-	i40e_aq_send_driver_version(&pf->hw, &dv, NULL);
-
-	dev_info(&pf->pdev->dev, "reset complete\n");
+	i40e_send_version(pf);
 
 end_core_reset:
 	clear_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state);
@@ -5642,7 +5812,6 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf)
  **/
 static void i40e_sync_vxlan_filters_subtask(struct i40e_pf *pf)
 {
-	const int vxlan_hdr_qwords = 4;
 	struct i40e_hw *hw = &pf->hw;
 	i40e_status ret;
 	u8 filter_index;
@@ -5660,7 +5829,6 @@ static void i40e_sync_vxlan_filters_subtask(struct i40e_pf *pf)
 			port = pf->vxlan_ports[i];
 			ret = port ?
 			      i40e_aq_add_udp_tunnel(hw, ntohs(port),
-						     vxlan_hdr_qwords,
 						     I40E_AQC_TUNNEL_TYPE_VXLAN,
 						     &filter_index, NULL)
 			      : i40e_aq_del_udp_tunnel(hw, i, NULL);
@@ -5839,15 +6007,15 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	 * find next empty vsi slot, looping back around if necessary
 	 */
 	i = pf->next_vsi;
-	while (i < pf->hw.func_caps.num_vsis && pf->vsi[i])
+	while (i < pf->num_alloc_vsi && pf->vsi[i])
 		i++;
-	if (i >= pf->hw.func_caps.num_vsis) {
+	if (i >= pf->num_alloc_vsi) {
 		i = 0;
 		while (i < pf->next_vsi && pf->vsi[i])
 			i++;
 	}
 
-	if (i < pf->hw.func_caps.num_vsis && !pf->vsi[i]) {
+	if (i < pf->num_alloc_vsi && !pf->vsi[i]) {
 		vsi_idx = i;             /* Found one! */
 	} else {
 		ret = -ENODEV;
@@ -5870,6 +6038,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	vsi->netdev_registered = false;
 	vsi->work_limit = I40E_DEFAULT_IRQ_WORK;
 	INIT_LIST_HEAD(&vsi->mac_filter_list);
+	vsi->irqs_ready = false;
 
 	ret = i40e_set_num_rings_in_vsi(vsi);
 	if (ret)
@@ -5987,14 +6156,12 @@ static void i40e_vsi_clear_rings(struct i40e_vsi *vsi)
  **/
 static int i40e_alloc_rings(struct i40e_vsi *vsi)
 {
+	struct i40e_ring *tx_ring, *rx_ring;
 	struct i40e_pf *pf = vsi->back;
 	int i;
 
 	/* Set basic values in the rings to be used later during open() */
 	for (i = 0; i < vsi->alloc_queue_pairs; i++) {
-		struct i40e_ring *tx_ring;
-		struct i40e_ring *rx_ring;
-
 		/* allocate space for both Tx and Rx in one shot */
 		tx_ring = kzalloc(sizeof(struct i40e_ring) * 2, GFP_KERNEL);
 		if (!tx_ring)
@@ -6052,8 +6219,6 @@ static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors)
 		vectors = 0;
 	}
 
-	pf->num_msix_entries = vectors;
-
 	return vectors;
 }
 
@@ -6107,6 +6272,16 @@ static int i40e_init_msix(struct i40e_pf *pf)
 	for (i = 0; i < v_budget; i++)
 		pf->msix_entries[i].entry = i;
 	vec = i40e_reserve_msix_vectors(pf, v_budget);
+
+	if (vec != v_budget) {
+		/* If we have limited resources, we will start with no vectors
+		 * for the special features and then allocate vectors to some
+		 * of these features based on the policy and at the end disable
+		 * the features that did not get any vectors.
+		 */
+		pf->num_vmdq_msix = 0;
+	}
+
 	if (vec < I40E_MIN_MSIX) {
 		pf->flags &= ~I40E_FLAG_MSIX_ENABLED;
 		kfree(pf->msix_entries);
@@ -6115,27 +6290,25 @@ static int i40e_init_msix(struct i40e_pf *pf)
 
 	} else if (vec == I40E_MIN_MSIX) {
 		/* Adjust for minimal MSIX use */
-		dev_info(&pf->pdev->dev, "Features disabled, not enough MSI-X vectors\n");
-		pf->flags &= ~I40E_FLAG_VMDQ_ENABLED;
 		pf->num_vmdq_vsis = 0;
 		pf->num_vmdq_qps = 0;
-		pf->num_vmdq_msix = 0;
 		pf->num_lan_qps = 1;
 		pf->num_lan_msix = 1;
 
 	} else if (vec != v_budget) {
+		/* reserve the misc vector */
+		vec--;
+
 		/* Scale vector usage down */
 		pf->num_vmdq_msix = 1;    /* force VMDqs to only one vector */
-		vec--;                    /* reserve the misc vector */
+		pf->num_vmdq_vsis = 1;
 
 		/* partition out the remaining vectors */
 		switch (vec) {
 		case 2:
-			pf->num_vmdq_vsis = 1;
 			pf->num_lan_msix = 1;
 			break;
 		case 3:
-			pf->num_vmdq_vsis = 1;
 			pf->num_lan_msix = 2;
 			break;
 		default:
@@ -6147,6 +6320,11 @@ static int i40e_init_msix(struct i40e_pf *pf)
 		}
 	}
 
+	if ((pf->flags & I40E_FLAG_VMDQ_ENABLED) &&
+	    (pf->num_vmdq_msix == 0)) {
+		dev_info(&pf->pdev->dev, "VMDq disabled, not enough MSI-X vectors\n");
+		pf->flags &= ~I40E_FLAG_VMDQ_ENABLED;
+	}
 	return err;
 }
 
@@ -6171,7 +6349,7 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx)
 	cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
 	if (vsi->netdev)
 		netif_napi_add(vsi->netdev, &q_vector->napi,
-			       i40e_napi_poll, vsi->work_limit);
+			       i40e_napi_poll, NAPI_POLL_WEIGHT);
 
 	q_vector->rx.latency_range = I40E_LOW_LATENCY;
 	q_vector->tx.latency_range = I40E_LOW_LATENCY;
@@ -6231,7 +6409,7 @@ static void i40e_init_interrupt_scheme(struct i40e_pf *pf)
 		if (err) {
 			pf->flags &= ~(I40E_FLAG_MSIX_ENABLED	|
 				       I40E_FLAG_RSS_ENABLED	|
-				       I40E_FLAG_DCB_ENABLED	|
+				       I40E_FLAG_DCB_CAPABLE	|
 				       I40E_FLAG_SRIOV_ENABLED	|
 				       I40E_FLAG_FD_SB_ENABLED	|
 				       I40E_FLAG_FD_ATR_ENABLED	|
@@ -6364,7 +6542,6 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 		return 0;
 
 	queue_count = min_t(int, queue_count, pf->rss_size_max);
-	queue_count = rounddown_pow_of_two(queue_count);
 
 	if (queue_count != pf->rss_size) {
 		i40e_prep_for_reset(pf);
@@ -6407,6 +6584,10 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		    I40E_FLAG_MSIX_ENABLED    |
 		    I40E_FLAG_RX_1BUF_ENABLED;
 
+	/* Set default ITR */
+	pf->rx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_RX_DEF;
+	pf->tx_itr_default = I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF;
+
 	/* Depending on PF configurations, it is possible that the RSS
 	 * maximum might end up larger than the available queues
 	 */
@@ -6416,7 +6597,6 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	if (pf->hw.func_caps.rss) {
 		pf->flags |= I40E_FLAG_RSS_ENABLED;
 		pf->rss_size = min_t(int, pf->rss_size_max, num_online_cpus());
-		pf->rss_size = rounddown_pow_of_two(pf->rss_size);
 	} else {
 		pf->rss_size = 1;
 	}
@@ -6432,8 +6612,12 @@ static int i40e_sw_init(struct i40e_pf *pf)
 	    (pf->hw.func_caps.fd_filters_best_effort > 0)) {
 		pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
 		pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE;
+		/* Setup a counter for fd_atr per pf */
+		pf->fd_atr_cnt_idx = I40E_FD_ATR_STAT_IDX(pf->hw.pf_id);
 		if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) {
 			pf->flags |= I40E_FLAG_FD_SB_ENABLED;
+			/* Setup a counter for fd_sb per pf */
+			pf->fd_sb_cnt_idx = I40E_FD_SB_STAT_IDX(pf->hw.pf_id);
 		} else {
 			dev_info(&pf->pdev->dev,
 				 "Flow Director Sideband mode Disabled in MFP mode\n");
@@ -6649,6 +6833,96 @@ static void i40e_del_vxlan_port(struct net_device *netdev,
 }
 
 #endif
+#ifdef HAVE_FDB_OPS
+#ifdef USE_CONST_DEV_UC_CHAR
+static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+			    struct net_device *dev,
+			    const unsigned char *addr,
+			    u16 flags)
+#else
+static int i40e_ndo_fdb_add(struct ndmsg *ndm,
+			    struct net_device *dev,
+			    unsigned char *addr,
+			    u16 flags)
+#endif
+{
+	struct i40e_netdev_priv *np = netdev_priv(dev);
+	struct i40e_pf *pf = np->vsi->back;
+	int err = 0;
+
+	if (!(pf->flags & I40E_FLAG_SRIOV_ENABLED))
+		return -EOPNOTSUPP;
+
+	/* Hardware does not support aging addresses so if a
+	 * ndm_state is given only allow permanent addresses
+	 */
+	if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) {
+		netdev_info(dev, "FDB only supports static addresses\n");
+		return -EINVAL;
+	}
+
+	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr))
+		err = dev_uc_add_excl(dev, addr);
+	else if (is_multicast_ether_addr(addr))
+		err = dev_mc_add_excl(dev, addr);
+	else
+		err = -EINVAL;
+
+	/* Only return duplicate errors if NLM_F_EXCL is set */
+	if (err == -EEXIST && !(flags & NLM_F_EXCL))
+		err = 0;
+
+	return err;
+}
+
+#ifndef USE_DEFAULT_FDB_DEL_DUMP
+#ifdef USE_CONST_DEV_UC_CHAR
+static int i40e_ndo_fdb_del(struct ndmsg *ndm,
+			    struct net_device *dev,
+			    const unsigned char *addr)
+#else
+static int i40e_ndo_fdb_del(struct ndmsg *ndm,
+			    struct net_device *dev,
+			    unsigned char *addr)
+#endif
+{
+	struct i40e_netdev_priv *np = netdev_priv(dev);
+	struct i40e_pf *pf = np->vsi->back;
+	int err = -EOPNOTSUPP;
+
+	if (ndm->ndm_state & NUD_PERMANENT) {
+		netdev_info(dev, "FDB only supports static addresses\n");
+		return -EINVAL;
+	}
+
+	if (pf->flags & I40E_FLAG_SRIOV_ENABLED) {
+		if (is_unicast_ether_addr(addr))
+			err = dev_uc_del(dev, addr);
+		else if (is_multicast_ether_addr(addr))
+			err = dev_mc_del(dev, addr);
+		else
+			err = -EINVAL;
+	}
+
+	return err;
+}
+
+static int i40e_ndo_fdb_dump(struct sk_buff *skb,
+			     struct netlink_callback *cb,
+			     struct net_device *dev,
+			     int idx)
+{
+	struct i40e_netdev_priv *np = netdev_priv(dev);
+	struct i40e_pf *pf = np->vsi->back;
+
+	if (pf->flags & I40E_FLAG_SRIOV_ENABLED)
+		idx = ndo_dflt_fdb_dump(skb, cb, dev, idx);
+
+	return idx;
+}
+
+#endif /* USE_DEFAULT_FDB_DEL_DUMP */
+#endif /* HAVE_FDB_OPS */
 static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_open		= i40e_open,
 	.ndo_stop		= i40e_close,
@@ -6669,13 +6943,21 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_set_features	= i40e_set_features,
 	.ndo_set_vf_mac		= i40e_ndo_set_vf_mac,
 	.ndo_set_vf_vlan	= i40e_ndo_set_vf_port_vlan,
-	.ndo_set_vf_tx_rate	= i40e_ndo_set_vf_bw,
+	.ndo_set_vf_rate	= i40e_ndo_set_vf_bw,
 	.ndo_get_vf_config	= i40e_ndo_get_vf_config,
 	.ndo_set_vf_link_state	= i40e_ndo_set_vf_link_state,
+	.ndo_set_vf_spoofchk	= i40e_ndo_set_vf_spoofck,
 #ifdef CONFIG_I40E_VXLAN
 	.ndo_add_vxlan_port	= i40e_add_vxlan_port,
 	.ndo_del_vxlan_port	= i40e_del_vxlan_port,
 #endif
+#ifdef HAVE_FDB_OPS
+	.ndo_fdb_add		= i40e_ndo_fdb_add,
+#ifndef USE_DEFAULT_FDB_DEL_DUMP
+	.ndo_fdb_del		= i40e_ndo_fdb_del,
+	.ndo_fdb_dump		= i40e_ndo_fdb_dump,
+#endif
+#endif
 };
 
 /**
@@ -6720,16 +7002,26 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 			   NETIF_F_TSO_ECN	       |
 			   NETIF_F_TSO6		       |
 			   NETIF_F_RXCSUM	       |
-			   NETIF_F_NTUPLE	       |
 			   NETIF_F_RXHASH	       |
 			   0;
 
+	if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
+		netdev->features |= NETIF_F_NTUPLE;
+
 	/* copy netdev features into list of user selectable features */
 	netdev->hw_features |= netdev->features;
 
 	if (vsi->type == I40E_VSI_MAIN) {
 		SET_NETDEV_DEV(netdev, &pf->pdev->dev);
-		memcpy(mac_addr, hw->mac.perm_addr, ETH_ALEN);
+		ether_addr_copy(mac_addr, hw->mac.perm_addr);
+		/* The following two steps are necessary to prevent reception
+		 * of tagged packets - by default the NVM loads a MAC-VLAN
+		 * filter that will accept any tagged packet.  This is to
+		 * prevent that during normal operations until a specific
+		 * VLAN tag filter has been set.
+		 */
+		i40e_rm_default_mac_filter(vsi, mac_addr);
+		i40e_add_filter(vsi, mac_addr, I40E_VLAN_ANY, false, true);
 	} else {
 		/* relate the VSI_VMDQ name to the VSI_MAIN name */
 		snprintf(netdev->name, IFNAMSIZ, "%sv%%d",
@@ -6739,8 +7031,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	}
 	i40e_add_filter(vsi, brdcast, I40E_VLAN_ANY, false, false);
 
-	memcpy(netdev->dev_addr, mac_addr, ETH_ALEN);
-	memcpy(netdev->perm_addr, mac_addr, ETH_ALEN);
+	ether_addr_copy(netdev->dev_addr, mac_addr);
+	ether_addr_copy(netdev->perm_addr, mac_addr);
 	/* vlan gets same features (except vlan offload)
 	 * after any tweaks for specific VSI types
 	 */
@@ -6772,7 +7064,6 @@ static void i40e_vsi_delete(struct i40e_vsi *vsi)
 		return;
 
 	i40e_aq_delete_element(&vsi->back->hw, vsi->seid, NULL);
-	return;
 }
 
 /**
@@ -6898,6 +7189,13 @@ static int i40e_add_vsi(struct i40e_vsi *vsi)
 
 		ctxt.info.valid_sections |= cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID);
 		ctxt.info.port_vlan_flags |= I40E_AQ_VSI_PVLAN_MODE_ALL;
+		if (pf->vf[vsi->vf_id].spoofchk) {
+			ctxt.info.valid_sections |=
+				cpu_to_le16(I40E_AQ_VSI_PROP_SECURITY_VALID);
+			ctxt.info.sec_flags |=
+				(I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK |
+				 I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK);
+		}
 		/* Setup the VSI tx/rx queue map for TC0 only for now */
 		i40e_vsi_setup_queue_map(vsi, &ctxt, enabled_tc, true);
 		break;
@@ -6982,11 +7280,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 				unregister_netdev(vsi->netdev);
 			}
 		} else {
-			if (!test_and_set_bit(__I40E_DOWN, &vsi->state))
-				i40e_down(vsi);
-			i40e_vsi_free_irq(vsi);
-			i40e_vsi_free_tx_resources(vsi);
-			i40e_vsi_free_rx_resources(vsi);
+			i40e_vsi_close(vsi);
 		}
 		i40e_vsi_disable_irq(vsi);
 	}
@@ -7013,7 +7307,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi)
 	 * the orphan VEBs yet.  We'll wait for an explicit remove request
 	 * from up the network stack.
 	 */
-	for (n = 0, i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+	for (n = 0, i = 0; i < pf->num_alloc_vsi; i++) {
 		if (pf->vsi[i] &&
 		    pf->vsi[i]->uplink_seid == uplink_seid &&
 		    (pf->vsi[i]->flags & I40E_VSI_FLAG_VEB_OWNER) == 0) {
@@ -7192,7 +7486,7 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type,
 
 	if (!veb && uplink_seid != pf->mac_seid) {
 
-		for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+		for (i = 0; i < pf->num_alloc_vsi; i++) {
 			if (pf->vsi[i] && pf->vsi[i]->seid == uplink_seid) {
 				vsi = pf->vsi[i];
 				break;
@@ -7435,7 +7729,7 @@ static void i40e_switch_branch_release(struct i40e_veb *branch)
 	 * NOTE: Removing the last VSI on a VEB has the SIDE EFFECT of removing
 	 *       the VEB itself, so don't use (*branch) after this loop.
 	 */
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+	for (i = 0; i < pf->num_alloc_vsi; i++) {
 		if (!pf->vsi[i])
 			continue;
 		if (pf->vsi[i]->uplink_seid == branch_seid &&
@@ -7487,7 +7781,7 @@ void i40e_veb_release(struct i40e_veb *veb)
 	pf = veb->pf;
 
 	/* find the remaining VSI and check for extras */
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+	for (i = 0; i < pf->num_alloc_vsi; i++) {
 		if (pf->vsi[i] && pf->vsi[i]->uplink_seid == veb->seid) {
 			n++;
 			vsi = pf->vsi[i];
@@ -7516,8 +7810,6 @@ void i40e_veb_release(struct i40e_veb *veb)
 
 	i40e_aq_delete_element(&pf->hw, veb->seid, NULL);
 	i40e_veb_clear(veb);
-
-	return;
 }
 
 /**
@@ -7601,10 +7893,10 @@ struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags,
 	}
 
 	/* make sure there is such a vsi and uplink */
-	for (vsi_idx = 0; vsi_idx < pf->hw.func_caps.num_vsis; vsi_idx++)
+	for (vsi_idx = 0; vsi_idx < pf->num_alloc_vsi; vsi_idx++)
 		if (pf->vsi[vsi_idx] && pf->vsi[vsi_idx]->seid == vsi_seid)
 			break;
-	if (vsi_idx >= pf->hw.func_caps.num_vsis && vsi_seid != 0) {
+	if (vsi_idx >= pf->num_alloc_vsi && vsi_seid != 0) {
 		dev_info(&pf->pdev->dev, "vsi seid %d not found\n",
 			 vsi_seid);
 		return NULL;
@@ -7639,6 +7931,8 @@ struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags,
 	ret = i40e_add_veb(veb, pf->vsi[vsi_idx]);
 	if (ret)
 		goto err_veb;
+	if (vsi_idx == pf->lan_vsi)
+		pf->lan_veb = veb->idx;
 
 	return veb;
 
@@ -7774,15 +8068,6 @@ int i40e_fetch_switch_configuration(struct i40e_pf *pf, bool printconfig)
 				 "header: %d reported %d total\n",
 				 num_reported, num_total);
 
-		if (num_reported) {
-			int sz = sizeof(*sw_config) * num_reported;
-
-			kfree(pf->sw_config);
-			pf->sw_config = kzalloc(sz, GFP_KERNEL);
-			if (pf->sw_config)
-				memcpy(pf->sw_config, sw_config, sz);
-		}
-
 		for (i = 0; i < num_reported; i++) {
 			struct i40e_aqc_switch_config_element_resp *ele =
 				&sw_config->element[i];
@@ -7949,9 +8234,7 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 	queues_left = pf->hw.func_caps.num_tx_qp;
 
 	if ((queues_left == 1) ||
-	    !(pf->flags & I40E_FLAG_MSIX_ENABLED) ||
-	    !(pf->flags & (I40E_FLAG_RSS_ENABLED | I40E_FLAG_FD_SB_ENABLED |
-			   I40E_FLAG_DCB_ENABLED))) {
+	    !(pf->flags & I40E_FLAG_MSIX_ENABLED)) {
 		/* one qp for PF, no queues for anything else */
 		queues_left = 0;
 		pf->rss_size = pf->num_lan_qps = 1;
@@ -7960,14 +8243,27 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
 			       I40E_FLAG_FD_SB_ENABLED	|
 			       I40E_FLAG_FD_ATR_ENABLED	|
-			       I40E_FLAG_DCB_ENABLED	|
+			       I40E_FLAG_DCB_CAPABLE	|
 			       I40E_FLAG_SRIOV_ENABLED	|
 			       I40E_FLAG_VMDQ_ENABLED);
+	} else if (!(pf->flags & (I40E_FLAG_RSS_ENABLED |
+				  I40E_FLAG_FD_SB_ENABLED |
+				  I40E_FLAG_FD_ATR_ENABLED |
+				  I40E_FLAG_DCB_CAPABLE))) {
+		/* one qp for PF */
+		pf->rss_size = pf->num_lan_qps = 1;
+		queues_left -= pf->num_lan_qps;
+
+		pf->flags &= ~(I40E_FLAG_RSS_ENABLED	|
+			       I40E_FLAG_FD_SB_ENABLED	|
+			       I40E_FLAG_FD_ATR_ENABLED	|
+			       I40E_FLAG_DCB_ENABLED	|
+			       I40E_FLAG_VMDQ_ENABLED);
 	} else {
 		/* Not enough queues for all TCs */
-		if ((pf->flags & I40E_FLAG_DCB_ENABLED) &&
+		if ((pf->flags & I40E_FLAG_DCB_CAPABLE) &&
 		    (queues_left < I40E_MAX_TRAFFIC_CLASS)) {
-			pf->flags &= ~I40E_FLAG_DCB_ENABLED;
+			pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
 			dev_info(&pf->pdev->dev, "not enough queues for DCB. DCB is disabled.\n");
 		}
 		pf->num_lan_qps = pf->rss_size_max;
@@ -7998,7 +8294,6 @@ static void i40e_determine_queue_usage(struct i40e_pf *pf)
 	}
 
 	pf->queues_left = queues_left;
-	return;
 }
 
 /**
@@ -8055,12 +8350,13 @@ static void i40e_print_features(struct i40e_pf *pf)
 
 	if (pf->flags & I40E_FLAG_RSS_ENABLED)
 		buf += sprintf(buf, "RSS ");
-	buf += sprintf(buf, "FDir ");
 	if (pf->flags & I40E_FLAG_FD_ATR_ENABLED)
-		buf += sprintf(buf, "ATR ");
-	if (pf->flags & I40E_FLAG_FD_SB_ENABLED)
+		buf += sprintf(buf, "FD_ATR ");
+	if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
+		buf += sprintf(buf, "FD_SB ");
 		buf += sprintf(buf, "NTUPLE ");
-	if (pf->flags & I40E_FLAG_DCB_ENABLED)
+	}
+	if (pf->flags & I40E_FLAG_DCB_CAPABLE)
 		buf += sprintf(buf, "DCB ");
 	if (pf->flags & I40E_FLAG_PTP)
 		buf += sprintf(buf, "PTP ");
@@ -8083,13 +8379,13 @@ static void i40e_print_features(struct i40e_pf *pf)
  **/
 static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
-	struct i40e_driver_version dv;
 	struct i40e_pf *pf;
 	struct i40e_hw *hw;
 	static u16 pfs_found;
 	u16 link_status;
 	int err = 0;
 	u32 len;
+	u32 i;
 
 	err = pci_enable_device_mem(pdev);
 	if (err)
@@ -8201,6 +8497,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	i40e_verify_eeprom(pf);
 
+	/* Rev 0 hardware was never productized */
+	if (hw->revision_id < 1)
+		dev_warn(&pdev->dev, "This device is a pre-production adapter/LOM. Please be aware there may be issues with your hardware. If you are experiencing problems please contact your Intel or hardware representative who provided you with this hardware.\n");
+
 	i40e_clear_pxe_mode(hw);
 	err = i40e_get_capabilities(pf);
 	if (err)
@@ -8234,7 +8534,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_mac_addr;
 	}
 	dev_info(&pdev->dev, "MAC address: %pM\n", hw->mac.addr);
-	memcpy(hw->mac.perm_addr, hw->mac.addr, ETH_ALEN);
+	ether_addr_copy(hw->mac.perm_addr, hw->mac.addr);
 
 	pci_set_drvdata(pdev, pf);
 	pci_save_state(pdev);
@@ -8242,8 +8542,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	err = i40e_init_pf_dcb(pf);
 	if (err) {
 		dev_info(&pdev->dev, "init_pf_dcb failed: %d\n", err);
-		pf->flags &= ~I40E_FLAG_DCB_ENABLED;
-		goto err_init_dcb;
+		pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+		/* Continue without DCB enabled */
 	}
 #endif /* CONFIG_I40E_DCB */
 
@@ -8264,10 +8564,18 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	i40e_determine_queue_usage(pf);
 	i40e_init_interrupt_scheme(pf);
 
-	/* Set up the *vsi struct based on the number of VSIs in the HW,
-	 * and set up our local tracking of the MAIN PF vsi.
+	/* The number of VSIs reported by the FW is the minimum guaranteed
+	 * to us; HW supports far more and we share the remaining pool with
+	 * the other PFs. We allocate space for more than the guarantee with
+	 * the understanding that we might not get them all later.
 	 */
-	len = sizeof(struct i40e_vsi *) * pf->hw.func_caps.num_vsis;
+	if (pf->hw.func_caps.num_vsis < I40E_MIN_VSI_ALLOC)
+		pf->num_alloc_vsi = I40E_MIN_VSI_ALLOC;
+	else
+		pf->num_alloc_vsi = pf->hw.func_caps.num_vsis;
+
+	/* Set up the *vsi struct and our local tracking of the MAIN PF vsi. */
+	len = sizeof(struct i40e_vsi *) * pf->num_alloc_vsi;
 	pf->vsi = kzalloc(len, GFP_KERNEL);
 	if (!pf->vsi) {
 		err = -ENOMEM;
@@ -8279,6 +8587,13 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err);
 		goto err_vsis;
 	}
+	/* if FDIR VSI was set up, start it now */
+	for (i = 0; i < pf->num_alloc_vsi; i++) {
+		if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) {
+			i40e_vsi_open(pf->vsi[i]);
+			break;
+		}
+	}
 
 	/* The main driver is (mostly) up and happy. We need to set this state
 	 * before setting up the misc vector or we get a race and the vector
@@ -8300,6 +8615,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
+#ifdef CONFIG_PCI_IOV
 	/* prep for VF support */
 	if ((pf->flags & I40E_FLAG_SRIOV_ENABLED) &&
 	    (pf->flags & I40E_FLAG_MSIX_ENABLED) &&
@@ -8322,17 +8638,14 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 					 err);
 		}
 	}
+#endif /* CONFIG_PCI_IOV */
 
 	pfs_found++;
 
 	i40e_dbg_pf_init(pf);
 
 	/* tell the firmware that we're starting */
-	dv.major_version = DRV_VERSION_MAJOR;
-	dv.minor_version = DRV_VERSION_MINOR;
-	dv.build_version = DRV_VERSION_BUILD;
-	dv.subbuild_version = 0;
-	i40e_aq_send_driver_version(&pf->hw, &dv, NULL);
+	i40e_send_version(pf);
 
 	/* since everything's happy, start the service_task timer */
 	mod_timer(&pf->service_timer,
@@ -8373,9 +8686,6 @@ err_vsis:
 err_switch_setup:
 	i40e_reset_interrupt_capability(pf);
 	del_timer_sync(&pf->service_timer);
-#ifdef CONFIG_I40E_DCB
-err_init_dcb:
-#endif /* CONFIG_I40E_DCB */
 err_mac_addr:
 err_configure_lan_hmc:
 	(void)i40e_shutdown_lan_hmc(hw);
@@ -8456,10 +8766,13 @@ static void i40e_remove(struct pci_dev *pdev)
 	}
 
 	/* shutdown and destroy the HMC */
-	ret_code = i40e_shutdown_lan_hmc(&pf->hw);
-	if (ret_code)
-		dev_warn(&pdev->dev,
-			 "Failed to destroy the HMC resources: %d\n", ret_code);
+	if (pf->hw.hmc.hmc_obj) {
+		ret_code = i40e_shutdown_lan_hmc(&pf->hw);
+		if (ret_code)
+			dev_warn(&pdev->dev,
+				 "Failed to destroy the HMC resources: %d\n",
+				 ret_code);
+	}
 
 	/* shutdown the adminq */
 	ret_code = i40e_shutdown_adminq(&pf->hw);
@@ -8470,7 +8783,7 @@ static void i40e_remove(struct pci_dev *pdev)
 
 	/* Clear all dynamic memory lists of rings, q_vectors, and VSIs */
 	i40e_clear_interrupt_scheme(pf);
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++) {
+	for (i = 0; i < pf->num_alloc_vsi; i++) {
 		if (pf->vsi[i]) {
 			i40e_vsi_clear_rings(pf->vsi[i]);
 			i40e_vsi_clear(pf->vsi[i]);
@@ -8485,7 +8798,6 @@ static void i40e_remove(struct pci_dev *pdev)
 
 	kfree(pf->qp_pile);
 	kfree(pf->irq_pile);
-	kfree(pf->sw_config);
 	kfree(pf->vsi);
 
 	/* force a PF reset to clean anything leftover */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 9cd57e61795..a430699c41d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -70,10 +70,12 @@ i40e_status i40e_aq_get_firmware_version(struct i40e_hw *hw,
 				u16 *fw_major_version, u16 *fw_minor_version,
 				u16 *api_major_version, u16 *api_minor_version,
 				struct i40e_asq_cmd_details *cmd_details);
-i40e_status i40e_aq_set_phy_reset(struct i40e_hw *hw,
+i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_set_default_vsi(struct i40e_hw *hw, u16 vsi_id,
 				struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_clear_pxe_mode(struct i40e_hw *hw,
+				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_set_link_restart_an(struct i40e_hw *hw,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
@@ -157,8 +159,8 @@ i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 i40e_status i40e_aq_start_lldp(struct i40e_hw *hw,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_add_udp_tunnel(struct i40e_hw *hw,
-				u16 udp_port, u8 header_len,
-				u8 protocol_index, u8 *filter_index,
+				u16 udp_port, u8 protocol_index,
+				u8 *filter_index,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index,
 				struct i40e_asq_cmd_details *cmd_details);
@@ -167,6 +169,9 @@ i40e_status i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
 i40e_status i40e_aq_mac_address_write(struct i40e_hw *hw,
 				    u16 flags, u8 *mac_addr,
 				    struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw,
+				u16 seid, u16 credit, u8 max_credit,
+				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_dcb_updated(struct i40e_hw *hw,
 				struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_set_hmc_resource_profile(struct i40e_hw *hw,
@@ -216,6 +221,7 @@ bool i40e_get_link_status(struct i40e_hw *hw);
 i40e_status i40e_get_mac_addr(struct i40e_hw *hw,
 						u8 *mac_addr);
 i40e_status i40e_validate_mac_addr(u8 *mac_addr);
+void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable);
 /* prototype for functions used for NVM access */
 i40e_status i40e_init_nvm(struct i40e_hw *hw);
 i40e_status i40e_acquire_nvm(struct i40e_hw *hw,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index e61e6372080..101f439acda 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -48,7 +48,6 @@
 					I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT)
 #define I40E_PRTTSYN_CTL1_TSYNTYPE_V2  (0x2 << \
 					I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT)
-#define I40E_PTP_TX_TIMEOUT  (HZ * 15)
 
 /**
  * i40e_ptp_read - Read the PHC time from the device
@@ -217,40 +216,6 @@ static int i40e_ptp_settime(struct ptp_clock_info *ptp,
 }
 
 /**
- * i40e_ptp_tx_work
- * @work: pointer to work struct
- *
- * This work function polls the PRTTSYN_STAT_0.TXTIME bit to determine when a
- * Tx timestamp event has occurred, in order to pass the Tx timestamp value up
- * the stack in the skb.
- */
-static void i40e_ptp_tx_work(struct work_struct *work)
-{
-	struct i40e_pf *pf = container_of(work, struct i40e_pf,
-					  ptp_tx_work);
-	struct i40e_hw *hw = &pf->hw;
-	u32 prttsyn_stat_0;
-
-	if (!pf->ptp_tx_skb)
-		return;
-
-	if (time_is_before_jiffies(pf->ptp_tx_start +
-				   I40E_PTP_TX_TIMEOUT)) {
-		dev_kfree_skb_any(pf->ptp_tx_skb);
-		pf->ptp_tx_skb = NULL;
-		pf->tx_hwtstamp_timeouts++;
-		dev_warn(&pf->pdev->dev, "clearing Tx timestamp hang\n");
-		return;
-	}
-
-	prttsyn_stat_0 = rd32(hw, I40E_PRTTSYN_STAT_0);
-	if (prttsyn_stat_0 & I40E_PRTTSYN_STAT_0_TXTIME_MASK)
-		i40e_ptp_tx_hwtstamp(pf);
-	else
-		schedule_work(&pf->ptp_tx_work);
-}
-
-/**
  * i40e_ptp_enable - Enable/disable ancillary features of the PHC subsystem
  * @ptp: The PTP clock structure
  * @rq: The requested feature to change
@@ -608,7 +573,6 @@ void i40e_ptp_init(struct i40e_pf *pf)
 		u32 regval;
 
 		spin_lock_init(&pf->tmreg_lock);
-		INIT_WORK(&pf->ptp_tx_work, i40e_ptp_tx_work);
 
 		dev_info(&pf->pdev->dev, "%s: added PHC on %s\n", __func__,
 			 netdev->name);
@@ -647,7 +611,6 @@ void i40e_ptp_stop(struct i40e_pf *pf)
 	pf->ptp_tx = false;
 	pf->ptp_rx = false;
 
-	cancel_work_sync(&pf->ptp_tx_work);
 	if (pf->ptp_tx_skb) {
 		dev_kfree_skb_any(pf->ptp_tx_skb);
 		pf->ptp_tx_skb = NULL;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h
index 1d40f425acf..947de98500f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_register.h
@@ -1340,8 +1340,6 @@
 #define I40E_PFINT_ICR0_GPIO_MASK (0x1 << I40E_PFINT_ICR0_GPIO_SHIFT)
 #define I40E_PFINT_ICR0_TIMESYNC_SHIFT 23
 #define I40E_PFINT_ICR0_TIMESYNC_MASK (0x1 << I40E_PFINT_ICR0_TIMESYNC_SHIFT)
-#define I40E_PFINT_ICR0_STORM_DETECT_SHIFT 24
-#define I40E_PFINT_ICR0_STORM_DETECT_MASK (0x1 << I40E_PFINT_ICR0_STORM_DETECT_SHIFT)
 #define I40E_PFINT_ICR0_LINK_STAT_CHANGE_SHIFT 25
 #define I40E_PFINT_ICR0_LINK_STAT_CHANGE_MASK (0x1 << I40E_PFINT_ICR0_LINK_STAT_CHANGE_SHIFT)
 #define I40E_PFINT_ICR0_HMC_ERR_SHIFT 26
@@ -1367,8 +1365,6 @@
 #define I40E_PFINT_ICR0_ENA_GPIO_MASK (0x1 << I40E_PFINT_ICR0_ENA_GPIO_SHIFT)
 #define I40E_PFINT_ICR0_ENA_TIMESYNC_SHIFT 23
 #define I40E_PFINT_ICR0_ENA_TIMESYNC_MASK (0x1 << I40E_PFINT_ICR0_ENA_TIMESYNC_SHIFT)
-#define I40E_PFINT_ICR0_ENA_STORM_DETECT_SHIFT 24
-#define I40E_PFINT_ICR0_ENA_STORM_DETECT_MASK (0x1 << I40E_PFINT_ICR0_ENA_STORM_DETECT_SHIFT)
 #define I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT 25
 #define I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_MASK (0x1 << I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT)
 #define I40E_PFINT_ICR0_ENA_HMC_ERR_SHIFT 26
@@ -1589,6 +1585,14 @@
 #define I40E_GLLAN_TSOMSK_M 0x000442DC
 #define I40E_GLLAN_TSOMSK_M_TCPMSKM_SHIFT 0
 #define I40E_GLLAN_TSOMSK_M_TCPMSKM_MASK (0xFFF << I40E_GLLAN_TSOMSK_M_TCPMSKM_SHIFT)
+#define I40E_GLLAN_TXPRE_QDIS(_i) (0x000E6500 + ((_i) * 4)) /* i=0..11 */
+#define I40E_GLLAN_TXPRE_QDIS_QINDX_SHIFT 0
+#define I40E_GLLAN_TXPRE_QDIS_QINDX_MASK (0x7FF << I40E_GLLAN_TXPRE_QDIS_QINDX_SHIFT)
+#define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT 30
+#define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_MASK (0x1 << I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT)
+#define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT 31
+#define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_MASK (0x1 << I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT)
+
 #define I40E_PFLAN_QALLOC 0x001C0400
 #define I40E_PFLAN_QALLOC_FIRSTQ_SHIFT 0
 #define I40E_PFLAN_QALLOC_FIRSTQ_MASK (0x7FF << I40E_PFLAN_QALLOC_FIRSTQ_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 9478ddc66ca..e49f31dbd5d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -24,6 +24,7 @@
  *
  ******************************************************************************/
 
+#include <linux/prefetch.h>
 #include "i40e.h"
 #include "i40e_prototype.h"
 
@@ -61,7 +62,7 @@ int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, u8 *raw_packet,
 
 	/* find existing FDIR VSI */
 	vsi = NULL;
-	for (i = 0; i < pf->hw.func_caps.num_vsis; i++)
+	for (i = 0; i < pf->num_alloc_vsi; i++)
 		if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR)
 			vsi = pf->vsi[i];
 	if (!vsi)
@@ -120,7 +121,7 @@ int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, u8 *raw_packet,
 		dcc |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK;
 		dcc |= ((u32)fdir_data->cnt_index <<
 			I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
-		       I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
+			I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
 	}
 
 	fdir_desc->dtype_cmd_cntindex = cpu_to_le32(dcc);
@@ -183,7 +184,6 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 	struct iphdr *ip;
 	bool err = false;
 	int ret;
-	int i;
 	static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0,
 		0x45, 0, 0, 0x1c, 0, 0, 0x40, 0, 0x40, 0x11, 0, 0, 0, 0, 0, 0,
 		0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
@@ -199,21 +199,17 @@ static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi,
 	ip->saddr = fd_data->src_ip[0];
 	udp->source = fd_data->src_port;
 
-	for (i = I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP;
-	     i <= I40E_FILTER_PCTYPE_NONF_IPV4_UDP; i++) {
-		fd_data->pctype = i;
-		ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
-
-		if (ret) {
-			dev_info(&pf->pdev->dev,
-				 "Filter command send failed for PCTYPE %d (ret = %d)\n",
-				 fd_data->pctype, ret);
-			err = true;
-		} else {
-			dev_info(&pf->pdev->dev,
-				 "Filter OK for PCTYPE %d (ret = %d)\n",
-				 fd_data->pctype, ret);
-		}
+	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
+	if (ret) {
+		dev_info(&pf->pdev->dev,
+			 "Filter command send failed for PCTYPE %d (ret = %d)\n",
+			 fd_data->pctype, ret);
+		err = true;
+	} else {
+		dev_info(&pf->pdev->dev,
+			 "Filter OK for PCTYPE %d (ret = %d)\n",
+			 fd_data->pctype, ret);
 	}
 
 	return err ? -EOPNOTSUPP : 0;
@@ -262,7 +258,7 @@ static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi,
 		}
 	}
 
-	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN;
+	fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
 	ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add);
 
 	if (ret) {
@@ -455,22 +451,20 @@ static void i40e_fd_handle_status(struct i40e_ring *rx_ring,
 
 		/* filter programming failed most likely due to table full */
 		fcnt_prog = i40e_get_current_fd_count(pf);
-		fcnt_avail = pf->hw.fdir_shared_filter_count +
-						       pf->fdir_pf_filter_count;
-
+		fcnt_avail = i40e_get_fd_cnt_all(pf);
 		/* If ATR is running fcnt_prog can quickly change,
 		 * if we are very close to full, it makes sense to disable
 		 * FD ATR/SB and then re-enable it when there is room.
 		 */
 		if (fcnt_prog >= (fcnt_avail - I40E_FDIR_BUFFER_FULL_MARGIN)) {
 			/* Turn off ATR first */
-			if (pf->flags | I40E_FLAG_FD_ATR_ENABLED) {
+			if (pf->flags & I40E_FLAG_FD_ATR_ENABLED) {
 				pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
 				dev_warn(&pdev->dev, "FD filter space full, ATR for further flows will be turned off\n");
 				pf->auto_disable_flags |=
 						       I40E_FLAG_FD_ATR_ENABLED;
 				pf->flags |= I40E_FLAG_FDIR_REQUIRES_REINIT;
-			} else if (pf->flags | I40E_FLAG_FD_SB_ENABLED) {
+			} else if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
 				pf->flags &= ~I40E_FLAG_FD_SB_ENABLED;
 				dev_warn(&pdev->dev, "FD filter space full, new ntuple rules will not be added\n");
 				pf->auto_disable_flags |=
@@ -1199,10 +1193,12 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    u32 rx_error,
 				    u16 rx_ptype)
 {
+	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(rx_ptype);
+	bool ipv4 = false, ipv6 = false;
 	bool ipv4_tunnel, ipv6_tunnel;
 	__wsum rx_udp_csum;
-	__sum16 csum;
 	struct iphdr *iph;
+	__sum16 csum;
 
 	ipv4_tunnel = (rx_ptype > I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
 		      (rx_ptype < I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
@@ -1213,29 +1209,57 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	skb->ip_summed = CHECKSUM_NONE;
 
 	/* Rx csum enabled and ip headers found? */
-	if (!(vsi->netdev->features & NETIF_F_RXCSUM &&
-	      rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
+	if (!(vsi->netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	/* did the hardware decode the packet and checksum? */
+	if (!(rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
+		return;
+
+	/* both known and outer_ip must be set for the below code to work */
+	if (!(decoded.known && decoded.outer_ip))
 		return;
 
+	if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
+	    decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4)
+		ipv4 = true;
+	else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
+		 decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6)
+		ipv6 = true;
+
+	if (ipv4 &&
+	    (rx_error & ((1 << I40E_RX_DESC_ERROR_IPE_SHIFT) |
+			 (1 << I40E_RX_DESC_ERROR_EIPE_SHIFT))))
+		goto checksum_fail;
+
 	/* likely incorrect csum if alternate IP extension headers found */
-	if (rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT))
+	if (ipv6 &&
+	    decoded.inner_prot == I40E_RX_PTYPE_INNER_PROT_TCP &&
+	    rx_error & (1 << I40E_RX_DESC_ERROR_L4E_SHIFT) &&
+	    rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT))
+		/* don't increment checksum err here, non-fatal err */
 		return;
 
-	/* IP or L4 or outmost IP checksum error */
-	if (rx_error & ((1 << I40E_RX_DESC_ERROR_IPE_SHIFT) |
-			(1 << I40E_RX_DESC_ERROR_L4E_SHIFT) |
-			(1 << I40E_RX_DESC_ERROR_EIPE_SHIFT))) {
-		vsi->back->hw_csum_rx_error++;
+	/* there was some L4 error, count error and punt packet to the stack */
+	if (rx_error & (1 << I40E_RX_DESC_ERROR_L4E_SHIFT))
+		goto checksum_fail;
+
+	/* handle packets that were not able to be checksummed due
+	 * to arrival speed, in this case the stack can compute
+	 * the csum.
+	 */
+	if (rx_error & (1 << I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
-	}
 
+	/* If VXLAN traffic has an outer UDPv4 checksum we need to check
+	 * it in the driver, hardware does not do it for us.
+	 * Since L3L4P bit was set we assume a valid IHL value (>=5)
+	 * so the total length of IPv4 header is IHL*4 bytes
+	 * The UDP_0 bit *may* bet set if the *inner* header is UDP
+	 */
 	if (ipv4_tunnel &&
+	    (decoded.inner_prot != I40E_RX_PTYPE_INNER_PROT_UDP) &&
 	    !(rx_status & (1 << I40E_RX_DESC_STATUS_UDP_0_SHIFT))) {
-		/* If VXLAN traffic has an outer UDPv4 checksum we need to check
-		 * it in the driver, hardware does not do it for us.
-		 * Since L3L4P bit was set we assume a valid IHL value (>=5)
-		 * so the total length of IPv4 header is IHL*4 bytes
-		 */
 		skb->transport_header = skb->mac_header +
 					sizeof(struct ethhdr) +
 					(ip_hdr(skb)->ihl * 4);
@@ -1252,13 +1276,16 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				(skb->len - skb_transport_offset(skb)),
 				IPPROTO_UDP, rx_udp_csum);
 
-		if (udp_hdr(skb)->check != csum) {
-			vsi->back->hw_csum_rx_error++;
-			return;
-		}
+		if (udp_hdr(skb)->check != csum)
+			goto checksum_fail;
 	}
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	return;
+
+checksum_fail:
+	vsi->back->hw_csum_rx_error++;
 }
 
 /**
@@ -1435,6 +1462,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* ERR_MASK will only have valid bits if EOP set */
 		if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
 			dev_kfree_skb_any(skb);
+			/* TODO: shouldn't we increment a counter indicating the
+			 * drop?
+			 */
 			goto next_desc;
 		}
 
@@ -1665,6 +1695,11 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	dtype_cmd |= I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID <<
 		     I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT;
 
+	dtype_cmd |= I40E_TXD_FLTR_QW1_CNT_ENA_MASK;
+	dtype_cmd |=
+		((u32)pf->fd_atr_cnt_idx << I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) &
+		I40E_TXD_FLTR_QW1_CNTINDEX_MASK;
+
 	fdir_desc->qindex_flex_ptype_vsi = cpu_to_le32(flex_ptype);
 	fdir_desc->dtype_cmd_cntindex = cpu_to_le32(dtype_cmd);
 }
@@ -1825,9 +1860,6 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	*cd_type_cmd_tso_mss |= (u64)I40E_TX_CTX_DESC_TSYN <<
 				I40E_TXD_CTX_QW1_CMD_SHIFT;
 
-	pf->ptp_tx_start = jiffies;
-	schedule_work(&pf->ptp_tx_work);
-
 	return 1;
 }
 
@@ -2179,9 +2211,7 @@ static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 				      struct i40e_ring *tx_ring)
 {
-#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
 	unsigned int f;
-#endif
 	int count = 0;
 
 	/* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
@@ -2190,12 +2220,9 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 	 *       + 1 desc for context descriptor,
 	 * otherwise try next time
 	 */
-#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
 	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
 		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
-#else
-	count += skb_shinfo(skb)->nr_frags;
-#endif
+
 	count += TXD_USE_COUNT(skb_headlen(skb));
 	if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
 		tx_ring->tx_stats.tx_busy++;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index d5349698e51..0277894fe1c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -27,7 +27,7 @@
 #ifndef _I40E_TXRX_H_
 #define _I40E_TXRX_H_
 
-/* Interrupt Throttling and Rate Limiting (storm control) Goodies */
+/* Interrupt Throttling and Rate Limiting Goodies */
 
 #define I40E_MAX_ITR               0x0FF0  /* reg uses 2 usec resolution */
 #define I40E_MIN_ITR               0x0004  /* reg uses 2 usec resolution */
@@ -69,16 +69,11 @@ enum i40e_dyn_idx_t {
 
 /* Supported RSS offloads */
 #define I40E_DEFAULT_RSS_HENA ( \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
 	((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4) | \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_UDP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP) | \
@@ -122,11 +117,11 @@ enum i40e_dyn_idx_t {
 #define i40e_rx_desc i40e_32byte_rx_desc
 
 #define I40E_MIN_TX_LEN		17
-#define I40E_MAX_DATA_PER_TXD	16383	/* aka 16kB - 1 */
+#define I40E_MAX_DATA_PER_TXD	8192
 
 /* Tx Descriptors needed, worst case */
 #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), I40E_MAX_DATA_PER_TXD)
-#define DESC_NEEDED ((MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE)) + 4)
+#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
 
 #define I40E_TX_FLAGS_CSUM		(u32)(1)
 #define I40E_TX_FLAGS_HW_VLAN		(u32)(1 << 1)
@@ -184,7 +179,6 @@ enum i40e_ring_state_t {
 	__I40E_TX_DETECT_HANG,
 	__I40E_HANG_CHECK_ARMED,
 	__I40E_RX_PS_ENABLED,
-	__I40E_RX_LRO_ENABLED,
 	__I40E_RX_16BYTE_DESC_ENABLED,
 };
 
@@ -200,12 +194,6 @@ enum i40e_ring_state_t {
 	set_bit(__I40E_TX_DETECT_HANG, &(ring)->state)
 #define clear_check_for_tx_hang(ring) \
 	clear_bit(__I40E_TX_DETECT_HANG, &(ring)->state)
-#define ring_is_lro_enabled(ring) \
-	test_bit(__I40E_RX_LRO_ENABLED, &(ring)->state)
-#define set_ring_lro_enabled(ring) \
-	set_bit(__I40E_RX_LRO_ENABLED, &(ring)->state)
-#define clear_ring_lro_enabled(ring) \
-	clear_bit(__I40E_RX_LRO_ENABLED, &(ring)->state)
 #define ring_is_16byte_desc_enabled(ring) \
 	test_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state)
 #define set_ring_16byte_desc_enabled(ring) \
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 71a968fe557..9d39ff23c5f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -36,12 +36,10 @@
 
 /* Device IDs */
 #define I40E_DEV_ID_SFP_XL710		0x1572
-#define I40E_DEV_ID_SFP_X710		0x1573
 #define I40E_DEV_ID_QEMU		0x1574
 #define I40E_DEV_ID_KX_A		0x157F
 #define I40E_DEV_ID_KX_B		0x1580
 #define I40E_DEV_ID_KX_C		0x1581
-#define I40E_DEV_ID_KX_D		0x1582
 #define I40E_DEV_ID_QSFP_A		0x1583
 #define I40E_DEV_ID_QSFP_B		0x1584
 #define I40E_DEV_ID_QSFP_C		0x1585
@@ -60,8 +58,8 @@
 /* Max default timeout in ms, */
 #define I40E_MAX_NVM_TIMEOUT		18000
 
-/* Switch from mc to the 2usec global time (this is the GTIME resolution) */
-#define I40E_MS_TO_GTIME(time)		(((time) * 1000) / 2)
+/* Switch from ms to the 1usec global time (this is the GTIME resolution) */
+#define I40E_MS_TO_GTIME(time)		((time) * 1000)
 
 /* forward declaration */
 struct i40e_hw;
@@ -167,6 +165,9 @@ struct i40e_link_status {
 	u8 loopback;
 	/* is Link Status Event notification to SW enabled */
 	bool lse_enable;
+	u16 max_frame_size;
+	bool crc_enable;
+	u8 pacing;
 };
 
 struct i40e_phy_info {
@@ -409,6 +410,7 @@ struct i40e_driver_version {
 	u8 minor_version;
 	u8 build_version;
 	u8 subbuild_version;
+	u8 driver_string[32];
 };
 
 /* RX Descriptors */
@@ -488,9 +490,6 @@ union i40e_32byte_rx_desc {
 	} wb;  /* writeback */
 };
 
-#define I40E_RXD_QW1_STATUS_SHIFT	0
-#define I40E_RXD_QW1_STATUS_MASK	(0x7FFFUL << I40E_RXD_QW1_STATUS_SHIFT)
-
 enum i40e_rx_desc_status_bits {
 	/* Note: These are predefined bit offsets */
 	I40E_RX_DESC_STATUS_DD_SHIFT		= 0,
@@ -507,9 +506,14 @@ enum i40e_rx_desc_status_bits {
 	I40E_RX_DESC_STATUS_LPBK_SHIFT		= 14,
 	I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT	= 15,
 	I40E_RX_DESC_STATUS_RESERVED_SHIFT	= 16, /* 2 BITS */
-	I40E_RX_DESC_STATUS_UDP_0_SHIFT		= 18
+	I40E_RX_DESC_STATUS_UDP_0_SHIFT		= 18,
+	I40E_RX_DESC_STATUS_LAST /* this entry must be last!!! */
 };
 
+#define I40E_RXD_QW1_STATUS_SHIFT	0
+#define I40E_RXD_QW1_STATUS_MASK	(((1 << I40E_RX_DESC_STATUS_LAST) - 1) \
+					 << I40E_RXD_QW1_STATUS_SHIFT)
+
 #define I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT   I40E_RX_DESC_STATUS_TSYNINDX_SHIFT
 #define I40E_RXD_QW1_STATUS_TSYNINDX_MASK	(0x3UL << \
 					     I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT)
@@ -537,7 +541,8 @@ enum i40e_rx_desc_error_bits {
 	I40E_RX_DESC_ERROR_IPE_SHIFT		= 3,
 	I40E_RX_DESC_ERROR_L4E_SHIFT		= 4,
 	I40E_RX_DESC_ERROR_EIPE_SHIFT		= 5,
-	I40E_RX_DESC_ERROR_OVERSIZE_SHIFT	= 6
+	I40E_RX_DESC_ERROR_OVERSIZE_SHIFT	= 6,
+	I40E_RX_DESC_ERROR_PPRS_SHIFT		= 7
 };
 
 enum i40e_rx_desc_error_l3l4e_fcoe_masks {
@@ -658,7 +663,6 @@ enum i40e_rx_desc_ext_status_bits {
 	I40E_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT	= 1,
 	I40E_RX_DESC_EXT_STATUS_FLEXBL_SHIFT	= 2, /* 2 BITS */
 	I40E_RX_DESC_EXT_STATUS_FLEXBH_SHIFT	= 4, /* 2 BITS */
-	I40E_RX_DESC_EXT_STATUS_FTYPE_SHIFT	= 6, /* 3 BITS */
 	I40E_RX_DESC_EXT_STATUS_FDLONGB_SHIFT	= 9,
 	I40E_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT	= 10,
 	I40E_RX_DESC_EXT_STATUS_PELONGB_SHIFT	= 11,
@@ -862,18 +866,14 @@ struct i40e_filter_program_desc {
 
 /* Packet Classifier Types for filters */
 enum i40e_filter_pctype {
-	/* Note: Values 0-28 are reserved for future use */
-	I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP	= 29,
-	I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP	= 30,
+	/* Note: Values 0-30 are reserved for future use */
 	I40E_FILTER_PCTYPE_NONF_IPV4_UDP		= 31,
-	I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN		= 32,
+	/* Note: Value 32 is reserved for future use */
 	I40E_FILTER_PCTYPE_NONF_IPV4_TCP		= 33,
 	I40E_FILTER_PCTYPE_NONF_IPV4_SCTP		= 34,
 	I40E_FILTER_PCTYPE_NONF_IPV4_OTHER		= 35,
 	I40E_FILTER_PCTYPE_FRAG_IPV4			= 36,
-	/* Note: Values 37-38 are reserved for future use */
-	I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP	= 39,
-	I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP	= 40,
+	/* Note: Values 37-40 are reserved for future use */
 	I40E_FILTER_PCTYPE_NONF_IPV6_UDP		= 41,
 	I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN		= 42,
 	I40E_FILTER_PCTYPE_NONF_IPV6_TCP		= 43,
@@ -955,6 +955,16 @@ struct i40e_vsi_context {
 	struct i40e_aqc_vsi_properties_data info;
 };
 
+struct i40e_veb_context {
+	u16 seid;
+	u16 uplink_seid;
+	u16 veb_number;
+	u16 vebs_allocated;
+	u16 vebs_unallocated;
+	u16 flags;
+	struct i40e_aqc_get_veb_parameters_completion info;
+};
+
 /* Statistics collected by each port, VSI, VEB, and S-channel */
 struct i40e_eth_stats {
 	u64 rx_bytes;			/* gorc */
@@ -962,8 +972,6 @@ struct i40e_eth_stats {
 	u64 rx_multicast;		/* mprc */
 	u64 rx_broadcast;		/* bprc */
 	u64 rx_discards;		/* rdpc */
-	u64 rx_errors;			/* repc */
-	u64 rx_missed;			/* rmpc */
 	u64 rx_unknown_protocol;	/* rupp */
 	u64 tx_bytes;			/* gotc */
 	u64 tx_unicast;			/* uptc */
@@ -1015,9 +1023,12 @@ struct i40e_hw_port_stats {
 	u64 tx_size_big;		/* ptc9522 */
 	u64 mac_short_packet_dropped;	/* mspdc */
 	u64 checksum_error;		/* xec */
+	/* flow director stats */
+	u64 fd_atr_match;
+	u64 fd_sb_match;
 	/* EEE LPI */
-	bool tx_lpi_status;
-	bool rx_lpi_status;
+	u32 tx_lpi_status;
+	u32 rx_lpi_status;
 	u64 tx_lpi_count;		/* etlpic */
 	u64 rx_lpi_count;		/* erlpic */
 };
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
index 22a1b69cd64..70951d2edca 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl.h
@@ -341,10 +341,6 @@ struct i40e_virtchnl_pf_event {
 	int severity;
 };
 
-/* The following are TBD, not necessary for LAN functionality.
- * I40E_VIRTCHNL_OP_FCOE
- */
-
 /* VF reset states - these are written into the RSTAT register:
  * I40E_VFGEN_RSTAT1 on the PF
  * I40E_VFGEN_RSTAT on the VF
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 02c11a7f7d2..f5b9d206257 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -29,6 +29,24 @@
 /***********************misc routines*****************************/
 
 /**
+ * i40e_vc_disable_vf
+ * @pf: pointer to the pf info
+ * @vf: pointer to the vf info
+ *
+ * Disable the VF through a SW reset
+ **/
+static inline void i40e_vc_disable_vf(struct i40e_pf *pf, struct i40e_vf *vf)
+{
+	struct i40e_hw *hw = &pf->hw;
+	u32 reg;
+
+	reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id));
+	reg |= I40E_VPGEN_VFRTRIG_VFSWR_MASK;
+	wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg);
+	i40e_flush(hw);
+}
+
+/**
  * i40e_vc_isvalid_vsi_id
  * @vf: pointer to the vf info
  * @vsi_id: vf relative vsi id
@@ -230,9 +248,8 @@ static int i40e_config_vsi_tx_queue(struct i40e_vf *vf, u16 vsi_idx,
 	tx_ctx.qlen = info->ring_len;
 	tx_ctx.rdylist = le16_to_cpu(pf->vsi[vsi_idx]->info.qs_handle[0]);
 	tx_ctx.rdylist_act = 0;
-	tx_ctx.head_wb_ena = 1;
-	tx_ctx.head_wb_addr = info->dma_ring_addr +
-			      (info->ring_len * sizeof(struct i40e_tx_desc));
+	tx_ctx.head_wb_ena = info->headwb_enabled;
+	tx_ctx.head_wb_addr = info->dma_headwb_addr;
 
 	/* clear the context in the HMC */
 	ret = i40e_clear_lan_tx_queue_context(hw, pf_queue_id);
@@ -336,6 +353,7 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_idx,
 	rx_ctx.tphhead_ena = 1;
 	rx_ctx.lrxqthresh = 2;
 	rx_ctx.crcstrip = 1;
+	rx_ctx.prefena = 1;
 
 	/* clear the context in the HMC */
 	ret = i40e_clear_lan_rx_queue_context(hw, pf_queue_id);
@@ -416,6 +434,15 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type)
 	if (ret)
 		dev_err(&pf->pdev->dev, "Unable to program ucast filters\n");
 
+	/* Set VF bandwidth if specified */
+	if (vf->tx_rate) {
+		ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid,
+						  vf->tx_rate / 50, 0, NULL);
+		if (ret)
+			dev_err(&pf->pdev->dev, "Unable to set tx rate, VF %d, error code %d.\n",
+				vf->vf_id, ret);
+	}
+
 error_alloc_vsi_res:
 	return ret;
 }
@@ -815,6 +842,10 @@ void i40e_free_vfs(struct i40e_pf *pf)
 	kfree(pf->vf);
 	pf->vf = NULL;
 
+	/* This check is for when the driver is unloaded while VFs are
+	 * assigned. Setting the number of VFs to 0 through sysfs is caught
+	 * before this function ever gets called.
+	 */
 	if (!i40e_vfs_are_assigned(pf)) {
 		pci_disable_sriov(pf->pdev);
 		/* Acknowledge VFLR for all VFS. Without this, VFs will fail to
@@ -867,6 +898,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
 		ret = -ENOMEM;
 		goto err_alloc;
 	}
+	pf->vf = vfs;
 
 	/* apply default profile */
 	for (i = 0; i < num_alloc_vfs; i++) {
@@ -876,13 +908,13 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs)
 
 		/* assign default capabilities */
 		set_bit(I40E_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps);
+		vfs[i].spoofchk = true;
 		/* vf resources get allocated during reset */
 		i40e_reset_vf(&vfs[i], false);
 
 		/* enable vf vplan_qtable mappings */
 		i40e_enable_vf_mappings(&vfs[i]);
 	}
-	pf->vf = vfs;
 	pf->num_alloc_vfs = num_alloc_vfs;
 
 	i40e_enable_pf_switch_lb(pf);
@@ -951,7 +983,12 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	if (num_vfs)
 		return i40e_pci_sriov_enable(pdev, num_vfs);
 
-	i40e_free_vfs(pf);
+	if (!i40e_vfs_are_assigned(pf)) {
+		i40e_free_vfs(pf);
+	} else {
+		dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
+		return -EINVAL;
+	}
 	return 0;
 }
 
@@ -2022,16 +2059,14 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	}
 
 	/* delete the temporary mac address */
-	i40e_del_filter(vsi, vf->default_lan_addr.addr, 0, true, false);
+	i40e_del_filter(vsi, vf->default_lan_addr.addr, vf->port_vlan_id,
+			true, false);
 
-	/* add the new mac address */
-	f = i40e_add_filter(vsi, mac, 0, true, false);
-	if (!f) {
-		dev_err(&pf->pdev->dev,
-			"Unable to add VF ucast filter\n");
-		ret = -ENOMEM;
-		goto error_param;
-	}
+	/* Delete all the filters for this VSI - we're going to kill it
+	 * anyway.
+	 */
+	list_for_each_entry(f, &vsi->mac_filter_list, list)
+		i40e_del_filter(vsi, f->macaddr, f->vlan, true, false);
 
 	dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id);
 	/* program mac filter */
@@ -2040,7 +2075,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		ret = -EIO;
 		goto error_param;
 	}
-	memcpy(vf->default_lan_addr.addr, mac, ETH_ALEN);
+	ether_addr_copy(vf->default_lan_addr.addr, mac);
 	vf->pf_set_mac = true;
 	dev_info(&pf->pdev->dev, "Reload the VF driver to make this change effective.\n");
 	ret = 0;
@@ -2088,18 +2123,28 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
 		goto error_pvid;
 	}
 
-	if (vsi->info.pvid == 0 && i40e_is_vsi_in_vlan(vsi))
+	if (vsi->info.pvid == 0 && i40e_is_vsi_in_vlan(vsi)) {
 		dev_err(&pf->pdev->dev,
 			"VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n",
 			vf_id);
+		/* Administrator Error - knock the VF offline until he does
+		 * the right thing by reconfiguring his network correctly
+		 * and then reloading the VF driver.
+		 */
+		i40e_vc_disable_vf(pf, vf);
+	}
 
 	/* Check for condition where there was already a port VLAN ID
 	 * filter set and now it is being deleted by setting it to zero.
+	 * Additionally check for the condition where there was a port
+	 * VLAN but now there is a new and different port VLAN being set.
 	 * Before deleting all the old VLAN filters we must add new ones
 	 * with -1 (I40E_VLAN_ANY) or otherwise we're left with all our
 	 * MAC addresses deleted.
 	 */
-	if (!(vlan_id || qos) && vsi->info.pvid)
+	if ((!(vlan_id || qos) ||
+	    (vlan_id | qos) != le16_to_cpu(vsi->info.pvid)) &&
+	    vsi->info.pvid)
 		ret = i40e_vsi_add_vlan(vsi, I40E_VLAN_ANY);
 
 	if (vsi->info.pvid) {
@@ -2150,6 +2195,8 @@ error_pvid:
 	return ret;
 }
 
+#define I40E_BW_CREDIT_DIVISOR 50     /* 50Mbps per BW credit */
+#define I40E_MAX_BW_INACTIVE_ACCUM 4  /* device can accumulate 4 credits max */
 /**
  * i40e_ndo_set_vf_bw
  * @netdev: network interface device structure
@@ -2158,9 +2205,76 @@ error_pvid:
  *
  * configure vf tx rate
  **/
-int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int tx_rate)
+int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
+		       int max_tx_rate)
 {
-	return -EOPNOTSUPP;
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_pf *pf = np->vsi->back;
+	struct i40e_vsi *vsi;
+	struct i40e_vf *vf;
+	int speed = 0;
+	int ret = 0;
+
+	/* validate the request */
+	if (vf_id >= pf->num_alloc_vfs) {
+		dev_err(&pf->pdev->dev, "Invalid VF Identifier %d.\n", vf_id);
+		ret = -EINVAL;
+		goto error;
+	}
+
+	if (min_tx_rate) {
+		dev_err(&pf->pdev->dev, "Invalid min tx rate (%d) (greater than 0) specified for vf %d.\n",
+			min_tx_rate, vf_id);
+		return -EINVAL;
+	}
+
+	vf = &(pf->vf[vf_id]);
+	vsi = pf->vsi[vf->lan_vsi_index];
+	if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) {
+		dev_err(&pf->pdev->dev, "Uninitialized VF %d.\n", vf_id);
+		ret = -EINVAL;
+		goto error;
+	}
+
+	switch (pf->hw.phy.link_info.link_speed) {
+	case I40E_LINK_SPEED_40GB:
+		speed = 40000;
+		break;
+	case I40E_LINK_SPEED_10GB:
+		speed = 10000;
+		break;
+	case I40E_LINK_SPEED_1GB:
+		speed = 1000;
+		break;
+	default:
+		break;
+	}
+
+	if (max_tx_rate > speed) {
+		dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for vf %d.",
+			max_tx_rate, vf->vf_id);
+		ret = -EINVAL;
+		goto error;
+	}
+
+	if ((max_tx_rate < 50) && (max_tx_rate > 0)) {
+		dev_warn(&pf->pdev->dev, "Setting max Tx rate to minimum usable value of 50Mbps.\n");
+		max_tx_rate = 50;
+	}
+
+	/* Tx rate credits are in values of 50Mbps, 0 is disabled*/
+	ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid,
+					  max_tx_rate / I40E_BW_CREDIT_DIVISOR,
+					  I40E_MAX_BW_INACTIVE_ACCUM, NULL);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Unable to set max tx rate, error code %d.\n",
+			ret);
+		ret = -EIO;
+		goto error;
+	}
+	vf->tx_rate = max_tx_rate;
+error:
+	return ret;
 }
 
 /**
@@ -2200,10 +2314,18 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 
 	memcpy(&ivi->mac, vf->default_lan_addr.addr, ETH_ALEN);
 
-	ivi->tx_rate = 0;
+	ivi->max_tx_rate = vf->tx_rate;
+	ivi->min_tx_rate = 0;
 	ivi->vlan = le16_to_cpu(vsi->info.pvid) & I40E_VLAN_MASK;
 	ivi->qos = (le16_to_cpu(vsi->info.pvid) & I40E_PRIORITY_MASK) >>
 		   I40E_VLAN_PRIORITY_SHIFT;
+	if (vf->link_forced == false)
+		ivi->linkstate = IFLA_VF_LINK_STATE_AUTO;
+	else if (vf->link_up == true)
+		ivi->linkstate = IFLA_VF_LINK_STATE_ENABLE;
+	else
+		ivi->linkstate = IFLA_VF_LINK_STATE_DISABLE;
+	ivi->spoofchk = vf->spoofchk;
 	ret = 0;
 
 error_param:
@@ -2270,3 +2392,50 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 error_out:
 	return ret;
 }
+
+/**
+ * i40e_ndo_set_vf_spoofchk
+ * @netdev: network interface device structure
+ * @vf_id: vf identifier
+ * @enable: flag to enable or disable feature
+ *
+ * Enable or disable VF spoof checking
+ **/
+int i40e_ndo_set_vf_spoofck(struct net_device *netdev, int vf_id, bool enable)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
+	struct i40e_vsi_context ctxt;
+	struct i40e_hw *hw = &pf->hw;
+	struct i40e_vf *vf;
+	int ret = 0;
+
+	/* validate the request */
+	if (vf_id >= pf->num_alloc_vfs) {
+		dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	vf = &(pf->vf[vf_id]);
+
+	if (enable == vf->spoofchk)
+		goto out;
+
+	vf->spoofchk = enable;
+	memset(&ctxt, 0, sizeof(ctxt));
+	ctxt.seid = pf->vsi[vf->lan_vsi_index]->seid;
+	ctxt.pf_num = pf->hw.pf_id;
+	ctxt.info.valid_sections = cpu_to_le16(I40E_AQ_VSI_PROP_SECURITY_VALID);
+	if (enable)
+		ctxt.info.sec_flags |= I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK;
+	ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Error %d updating VSI parameters\n",
+			ret);
+		ret = -EIO;
+	}
+out:
+	return ret;
+}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index 389c47f396d..63e7e0d81ad 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -98,8 +98,10 @@ struct i40e_vf {
 
 	unsigned long vf_caps;	/* vf's adv. capabilities */
 	unsigned long vf_states;	/* vf's runtime states */
+	unsigned int tx_rate;	/* Tx bandwidth limit in Mbps */
 	bool link_forced;
 	bool link_up;		/* only valid if vf link is forced */
+	bool spoofchk;
 };
 
 void i40e_free_vfs(struct i40e_pf *pf);
@@ -115,10 +117,12 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf);
 int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac);
 int i40e_ndo_set_vf_port_vlan(struct net_device *netdev,
 			      int vf_id, u16 vlan_id, u8 qos);
-int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int tx_rate);
+int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
+		       int max_tx_rate);
 int i40e_ndo_get_vf_config(struct net_device *netdev,
 			   int vf_id, struct ifla_vf_info *ivi);
 int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link);
+int i40e_ndo_set_vf_spoofck(struct net_device *netdev, int vf_id, bool enable);
 
 void i40e_vc_notify_link_state(struct i40e_pf *pf);
 void i40e_vc_notify_reset(struct i40e_pf *pf);
diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile
index e09be37a07a..3a423836a56 100644
--- a/drivers/net/ethernet/intel/i40evf/Makefile
+++ b/drivers/net/ethernet/intel/i40evf/Makefile
@@ -1,7 +1,7 @@
 ################################################################################
 #
 # Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
-# Copyright(c) 2013 Intel Corporation.
+# Copyright(c) 2013 - 2014 Intel Corporation.
 #
 # This program is free software; you can redistribute it and/or modify it
 # under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 # more details.
 #
+# You should have received a copy of the GNU General Public License along
+# with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
 # The full GNU General Public License is included in this distribution in
 # the file called "COPYING".
 #
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
index 5470ce95936..eb67cce3e8f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -28,6 +31,16 @@
 #include "i40e_prototype.h"
 
 /**
+ * i40e_is_nvm_update_op - return true if this is an NVM update operation
+ * @desc: API request descriptor
+ **/
+static inline bool i40e_is_nvm_update_op(struct i40e_aq_desc *desc)
+{
+	return (desc->opcode == i40e_aqc_opc_nvm_erase) ||
+	       (desc->opcode == i40e_aqc_opc_nvm_update);
+}
+
+/**
  *  i40e_adminq_init_regs - Initialize AdminQ registers
  *  @hw: pointer to the hardware structure
  *
@@ -276,8 +289,11 @@ static void i40e_free_asq_bufs(struct i40e_hw *hw)
  *
  *  Configure base address and length registers for the transmit queue
  **/
-static void i40e_config_asq_regs(struct i40e_hw *hw)
+static i40e_status i40e_config_asq_regs(struct i40e_hw *hw)
 {
+	i40e_status ret_code = 0;
+	u32 reg = 0;
+
 	if (hw->mac.type == I40E_MAC_VF) {
 		/* configure the transmit queue */
 		wr32(hw, I40E_VF_ATQBAH1,
@@ -286,6 +302,7 @@ static void i40e_config_asq_regs(struct i40e_hw *hw)
 		    lower_32_bits(hw->aq.asq.desc_buf.pa));
 		wr32(hw, I40E_VF_ATQLEN1, (hw->aq.num_asq_entries |
 					  I40E_VF_ATQLEN1_ATQENABLE_MASK));
+		reg = rd32(hw, I40E_VF_ATQBAL1);
 	} else {
 		/* configure the transmit queue */
 		wr32(hw, I40E_PF_ATQBAH,
@@ -294,7 +311,14 @@ static void i40e_config_asq_regs(struct i40e_hw *hw)
 		    lower_32_bits(hw->aq.asq.desc_buf.pa));
 		wr32(hw, I40E_PF_ATQLEN, (hw->aq.num_asq_entries |
 					  I40E_PF_ATQLEN_ATQENABLE_MASK));
+		reg = rd32(hw, I40E_PF_ATQBAL);
 	}
+
+	/* Check one register to verify that config was applied */
+	if (reg != lower_32_bits(hw->aq.asq.desc_buf.pa))
+		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+
+	return ret_code;
 }
 
 /**
@@ -303,8 +327,11 @@ static void i40e_config_asq_regs(struct i40e_hw *hw)
  *
  * Configure base address and length registers for the receive (event queue)
  **/
-static void i40e_config_arq_regs(struct i40e_hw *hw)
+static i40e_status i40e_config_arq_regs(struct i40e_hw *hw)
 {
+	i40e_status ret_code = 0;
+	u32 reg = 0;
+
 	if (hw->mac.type == I40E_MAC_VF) {
 		/* configure the receive queue */
 		wr32(hw, I40E_VF_ARQBAH1,
@@ -313,6 +340,7 @@ static void i40e_config_arq_regs(struct i40e_hw *hw)
 		    lower_32_bits(hw->aq.arq.desc_buf.pa));
 		wr32(hw, I40E_VF_ARQLEN1, (hw->aq.num_arq_entries |
 					  I40E_VF_ARQLEN1_ARQENABLE_MASK));
+		reg = rd32(hw, I40E_VF_ARQBAL1);
 	} else {
 		/* configure the receive queue */
 		wr32(hw, I40E_PF_ARQBAH,
@@ -321,10 +349,17 @@ static void i40e_config_arq_regs(struct i40e_hw *hw)
 		    lower_32_bits(hw->aq.arq.desc_buf.pa));
 		wr32(hw, I40E_PF_ARQLEN, (hw->aq.num_arq_entries |
 					  I40E_PF_ARQLEN_ARQENABLE_MASK));
+		reg = rd32(hw, I40E_PF_ARQBAL);
 	}
 
 	/* Update tail in the HW to post pre-allocated buffers */
 	wr32(hw, hw->aq.arq.tail, hw->aq.num_arq_entries - 1);
+
+	/* Check one register to verify that config was applied */
+	if (reg != lower_32_bits(hw->aq.arq.desc_buf.pa))
+		ret_code = I40E_ERR_ADMIN_QUEUE_ERROR;
+
+	return ret_code;
 }
 
 /**
@@ -372,7 +407,9 @@ static i40e_status i40e_init_asq(struct i40e_hw *hw)
 		goto init_adminq_free_rings;
 
 	/* initialize base registers */
-	i40e_config_asq_regs(hw);
+	ret_code = i40e_config_asq_regs(hw);
+	if (ret_code)
+		goto init_adminq_free_rings;
 
 	/* success! */
 	goto init_adminq_exit;
@@ -429,7 +466,9 @@ static i40e_status i40e_init_arq(struct i40e_hw *hw)
 		goto init_adminq_free_rings;
 
 	/* initialize base registers */
-	i40e_config_arq_regs(hw);
+	ret_code = i40e_config_arq_regs(hw);
+	if (ret_code)
+		goto init_adminq_free_rings;
 
 	/* success! */
 	goto init_adminq_exit;
@@ -659,6 +698,12 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 		goto asq_send_command_exit;
 	}
 
+	if (i40e_is_nvm_update_op(desc) && hw->aq.nvm_busy) {
+		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: NVM busy.\n");
+		status = I40E_ERR_NVM;
+		goto asq_send_command_exit;
+	}
+
 	details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
 	if (cmd_details) {
 		*details = *cmd_details;
@@ -786,6 +831,9 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
 	}
 
+	if (i40e_is_nvm_update_op(desc))
+		hw->aq.nvm_busy = true;
+
 	/* update the error if time out occurred */
 	if ((!cmd_completed) &&
 	    (!details->async && !details->postpone)) {
@@ -880,6 +928,9 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw,
 			       e->msg_size);
 	}
 
+	if (i40e_is_nvm_update_op(&e->desc))
+		hw->aq.nvm_busy = false;
+
 	/* Restore the original datalen and buffer address in the desc,
 	 * FW updates datalen to indicate the event message
 	 * size
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
index 8f72c31d95c..e3472c62e15 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -87,6 +90,7 @@ struct i40e_adminq_info {
 	u16 fw_min_ver;                 /* firmware minor version */
 	u16 api_maj_ver;                /* api major version */
 	u16 api_min_ver;                /* api minor version */
+	bool nvm_busy;
 
 	struct mutex asq_mutex; /* Send queue lock */
 	struct mutex arq_mutex; /* Receive queue lock */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index 97662b6bd98..e656ea7a792 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -31,7 +34,7 @@
  */
 
 #define I40E_FW_API_VERSION_MAJOR  0x0001
-#define I40E_FW_API_VERSION_MINOR  0x0001
+#define I40E_FW_API_VERSION_MINOR  0x0002
 #define I40E_FW_API_VERSION_A0_MINOR  0x0000
 
 struct i40e_aq_desc {
@@ -121,6 +124,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_get_version      = 0x0001,
 	i40e_aqc_opc_driver_version   = 0x0002,
 	i40e_aqc_opc_queue_shutdown   = 0x0003,
+	i40e_aqc_opc_set_pf_context   = 0x0004,
 
 	/* resource ownership */
 	i40e_aqc_opc_request_resource = 0x0008,
@@ -180,9 +184,6 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_add_mirror_rule    = 0x0260,
 	i40e_aqc_opc_delete_mirror_rule = 0x0261,
 
-	i40e_aqc_opc_set_storm_control_config = 0x0280,
-	i40e_aqc_opc_get_storm_control_config = 0x0281,
-
 	/* DCB commands */
 	i40e_aqc_opc_dcb_ignore_pfc = 0x0301,
 	i40e_aqc_opc_dcb_updated    = 0x0302,
@@ -205,6 +206,7 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_query_switching_comp_bw_config        = 0x041A,
 	i40e_aqc_opc_suspend_port_tx                       = 0x041B,
 	i40e_aqc_opc_resume_port_tx                        = 0x041C,
+	i40e_aqc_opc_configure_partition_bw                = 0x041D,
 
 	/* hmc */
 	i40e_aqc_opc_query_hmc_resource_profile = 0x0500,
@@ -222,13 +224,15 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_get_partner_advt    = 0x0616,
 	i40e_aqc_opc_set_lb_modes        = 0x0618,
 	i40e_aqc_opc_get_phy_wol_caps    = 0x0621,
-	i40e_aqc_opc_set_phy_reset       = 0x0622,
+	i40e_aqc_opc_set_phy_debug	 = 0x0622,
 	i40e_aqc_opc_upload_ext_phy_fm   = 0x0625,
 
 	/* NVM commands */
-	i40e_aqc_opc_nvm_read   = 0x0701,
-	i40e_aqc_opc_nvm_erase  = 0x0702,
-	i40e_aqc_opc_nvm_update = 0x0703,
+	i40e_aqc_opc_nvm_read         = 0x0701,
+	i40e_aqc_opc_nvm_erase        = 0x0702,
+	i40e_aqc_opc_nvm_update       = 0x0703,
+	i40e_aqc_opc_nvm_config_read  = 0x0704,
+	i40e_aqc_opc_nvm_config_write = 0x0705,
 
 	/* virtualization commands */
 	i40e_aqc_opc_send_msg_to_pf   = 0x0801,
@@ -270,8 +274,6 @@ enum i40e_admin_queue_opc {
 	i40e_aqc_opc_debug_set_mode         = 0xFF01,
 	i40e_aqc_opc_debug_read_reg         = 0xFF03,
 	i40e_aqc_opc_debug_write_reg        = 0xFF04,
-	i40e_aqc_opc_debug_read_reg_sg      = 0xFF05,
-	i40e_aqc_opc_debug_write_reg_sg     = 0xFF06,
 	i40e_aqc_opc_debug_modify_reg       = 0xFF07,
 	i40e_aqc_opc_debug_dump_internals   = 0xFF08,
 	i40e_aqc_opc_debug_modify_internals = 0xFF09,
@@ -339,6 +341,14 @@ struct i40e_aqc_queue_shutdown {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown);
 
+/* Set PF context (0x0004, direct) */
+struct i40e_aqc_set_pf_context {
+	u8	pf_id;
+	u8	reserved[15];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_pf_context);
+
 /* Request resource ownership (direct 0x0008)
  * Release resource ownership (direct 0x0009)
  */
@@ -678,7 +688,6 @@ struct i40e_aqc_add_get_update_vsi {
 #define I40E_AQ_VSI_TYPE_PF             0x2
 #define I40E_AQ_VSI_TYPE_EMP_MNG        0x3
 #define I40E_AQ_VSI_FLAG_CASCADED_PV    0x4
-#define I40E_AQ_VSI_FLAG_CLOUD_VSI      0x8
 	__le32 addr_high;
 	__le32 addr_low;
 };
@@ -1040,7 +1049,9 @@ struct i40e_aqc_set_vsi_promiscuous_modes {
 #define I40E_AQC_SET_VSI_PROMISC_VLAN        0x10
 	__le16 seid;
 #define I40E_AQC_VSI_PROM_CMD_SEID_MASK      0x3FF
-	u8     reserved[10];
+	__le16 vlan_tag;
+#define I40E_AQC_SET_VSI_VLAN_VALID          0x8000
+	u8     reserved[8];
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_set_vsi_promiscuous_modes);
@@ -1289,27 +1300,6 @@ struct i40e_aqc_add_delete_mirror_rule_completion {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion);
 
-/* Set Storm Control Configuration (direct 0x0280)
- * Get Storm Control Configuration (direct 0x0281)
- *    the command and response use the same descriptor structure
- */
-struct i40e_aqc_set_get_storm_control_config {
-	__le32 broadcast_threshold;
-	__le32 multicast_threshold;
-	__le32 control_flags;
-#define I40E_AQC_STORM_CONTROL_MDIPW            0x01
-#define I40E_AQC_STORM_CONTROL_MDICW            0x02
-#define I40E_AQC_STORM_CONTROL_BDIPW            0x04
-#define I40E_AQC_STORM_CONTROL_BDICW            0x08
-#define I40E_AQC_STORM_CONTROL_BIDU             0x10
-#define I40E_AQC_STORM_CONTROL_INTERVAL_SHIFT   8
-#define I40E_AQC_STORM_CONTROL_INTERVAL_MASK    (0x3FF << \
-					I40E_AQC_STORM_CONTROL_INTERVAL_SHIFT)
-	u8     reserved[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_get_storm_control_config);
-
 /* DCB 0x03xx*/
 
 /* PFC Ignore (direct 0x0301)
@@ -1427,11 +1417,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_switching_comp_bw_limit);
 struct i40e_aqc_configure_switching_comp_ets_data {
 	u8     reserved[4];
 	u8     tc_valid_bits;
-	u8     reserved1;
+	u8     seepage;
+#define I40E_AQ_ETS_SEEPAGE_EN_MASK     0x1
 	u8     tc_strict_priority_flags;
-	u8     reserved2[17];
+	u8     reserved1[17];
 	u8     tc_bw_share_credits[8];
-	u8     reserved3[96];
+	u8     reserved2[96];
 };
 
 /* Configure Switching Component Bandwidth Limits per Tc (indirect 0x0416) */
@@ -1499,6 +1490,15 @@ struct i40e_aqc_query_switching_comp_bw_config_resp {
  * (direct 0x041B and 0x041C) uses the generic SEID struct
  */
 
+/* Configure partition BW
+ * (indirect 0x041D)
+ */
+struct i40e_aqc_configure_partition_bw_data {
+	__le16 pf_valid_bits;
+	u8     min_bw[16];      /* guaranteed bandwidth */
+	u8     max_bw[16];      /* bandwidth limit */
+};
+
 /* Get and set the active HMC resource profile and status.
  * (direct 0x0500) and (direct 0x0501)
  */
@@ -1539,6 +1539,8 @@ enum i40e_aq_phy_type {
 	I40E_PHY_TYPE_XLPPI			= 0x9,
 	I40E_PHY_TYPE_40GBASE_CR4_CU		= 0xA,
 	I40E_PHY_TYPE_10GBASE_CR1_CU		= 0xB,
+	I40E_PHY_TYPE_10GBASE_AOC		= 0xC,
+	I40E_PHY_TYPE_40GBASE_AOC		= 0xD,
 	I40E_PHY_TYPE_100BASE_TX		= 0x11,
 	I40E_PHY_TYPE_1000BASE_T		= 0x12,
 	I40E_PHY_TYPE_10GBASE_T			= 0x13,
@@ -1549,7 +1551,10 @@ enum i40e_aq_phy_type {
 	I40E_PHY_TYPE_40GBASE_CR4		= 0x18,
 	I40E_PHY_TYPE_40GBASE_SR4		= 0x19,
 	I40E_PHY_TYPE_40GBASE_LR4		= 0x1A,
-	I40E_PHY_TYPE_20GBASE_KR2		= 0x1B,
+	I40E_PHY_TYPE_1000BASE_SX		= 0x1B,
+	I40E_PHY_TYPE_1000BASE_LX		= 0x1C,
+	I40E_PHY_TYPE_1000BASE_T_OPTICAL	= 0x1D,
+	I40E_PHY_TYPE_20GBASE_KR2		= 0x1E,
 	I40E_PHY_TYPE_MAX
 };
 
@@ -1583,11 +1588,8 @@ struct i40e_aq_get_phy_abilities_resp {
 #define I40E_AQ_PHY_FLAG_PAUSE_TX         0x01
 #define I40E_AQ_PHY_FLAG_PAUSE_RX         0x02
 #define I40E_AQ_PHY_FLAG_LOW_POWER        0x04
-#define I40E_AQ_PHY_FLAG_AN_SHIFT         3
-#define I40E_AQ_PHY_FLAG_AN_MASK          (0x3 << I40E_AQ_PHY_FLAG_AN_SHIFT)
-#define I40E_AQ_PHY_FLAG_AN_OFF           0x00 /* link forced on */
-#define I40E_AQ_PHY_FLAG_AN_OFF_LINK_DOWN 0x01
-#define I40E_AQ_PHY_FLAG_AN_ON            0x02
+#define I40E_AQ_PHY_LINK_ENABLED		  0x08
+#define I40E_AQ_PHY_AN_ENABLED			  0x10
 #define I40E_AQ_PHY_FLAG_MODULE_QUAL      0x20
 	__le16 eee_capability;
 #define I40E_AQ_EEE_100BASE_TX       0x0002
@@ -1696,6 +1698,7 @@ struct i40e_aqc_get_link_status {
 #define I40E_AQ_LINK_TX_ACTIVE       0x00
 #define I40E_AQ_LINK_TX_DRAINED      0x01
 #define I40E_AQ_LINK_TX_FLUSHED      0x03
+#define I40E_AQ_LINK_FORCED_40G      0x10
 	u8     loopback;         /* use defines from i40e_aqc_set_lb_mode */
 	__le16 max_frame_size;
 	u8     config;
@@ -1747,14 +1750,21 @@ struct i40e_aqc_set_lb_mode {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_set_lb_mode);
 
-/* Set PHY Reset command (0x0622) */
-struct i40e_aqc_set_phy_reset {
-	u8     reset_flags;
-#define I40E_AQ_PHY_RESET_REQUEST  0x02
+/* Set PHY Debug command (0x0622) */
+struct i40e_aqc_set_phy_debug {
+	u8     command_flags;
+#define I40E_AQ_PHY_DEBUG_RESET_INTERNAL	0x02
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT	2
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_MASK	(0x03 << \
+					I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT)
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_NONE	0x00
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_HARD	0x01
+#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SOFT	0x02
+#define I40E_AQ_PHY_DEBUG_DISABLE_LINK_FW	0x10
 	u8     reserved[15];
 };
 
-I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_reset);
+I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_debug);
 
 enum i40e_aq_phy_reg_type {
 	I40E_AQC_PHY_REG_INTERNAL         = 0x1,
@@ -1779,6 +1789,47 @@ struct i40e_aqc_nvm_update {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update);
 
+/* NVM Config Read (indirect 0x0704) */
+struct i40e_aqc_nvm_config_read {
+	__le16 cmd_flags;
+#define ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK	1
+#define ANVM_READ_SINGLE_FEATURE		0
+#define ANVM_READ_MULTIPLE_FEATURES		1
+	__le16 element_count;
+	__le16 element_id;		/* Feature/field ID */
+	u8     reserved[2];
+	__le32 address_high;
+	__le32 address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_read);
+
+/* NVM Config Write (indirect 0x0705) */
+struct i40e_aqc_nvm_config_write {
+	__le16 cmd_flags;
+	__le16 element_count;
+	u8     reserved[4];
+	__le32 address_high;
+	__le32 address_low;
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_write);
+
+struct i40e_aqc_nvm_config_data_feature {
+	__le16 feature_id;
+	__le16 instance_id;
+	__le16 feature_options;
+	__le16 feature_selection;
+};
+
+struct i40e_aqc_nvm_config_data_immediate_field {
+#define ANVM_FEATURE_OR_IMMEDIATE_MASK	0x2
+	__le16 field_id;
+	__le16 instance_id;
+	__le16 field_options;
+	__le16 field_value;
+};
+
 /* Send to PF command (indirect 0x0801) id is only used by PF
  * Send to VF command (indirect 0x0802) id is only used by PF
  * Send to Peer PF command (indirect 0x0803)
@@ -1948,19 +1999,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_start);
 /* Add Udp Tunnel command and completion (direct 0x0B00) */
 struct i40e_aqc_add_udp_tunnel {
 	__le16 udp_port;
-	u8     header_len; /* in DWords, 1 to 15 */
+	u8     reserved0[3];
 	u8     protocol_type;
-#define I40E_AQC_TUNNEL_TYPE_TEREDO	0x0
-#define I40E_AQC_TUNNEL_TYPE_VXLAN	0x2
-#define I40E_AQC_TUNNEL_TYPE_NGE	0x3
-	u8     variable_udp_length;
-#define I40E_AQC_TUNNEL_FIXED_UDP_LENGTH	0x0
-#define I40E_AQC_TUNNEL_VARIABLE_UDP_LENGTH	0x1
-	u8		udp_key_index;
-#define I40E_AQC_TUNNEL_KEY_INDEX_VXLAN			0x0
-#define I40E_AQC_TUNNEL_KEY_INDEX_NGE			0x1
-#define I40E_AQC_TUNNEL_KEY_INDEX_PROPRIETARY_UDP	0x2
-	u8		reserved[10];
+#define I40E_AQC_TUNNEL_TYPE_VXLAN	0x00
+#define I40E_AQC_TUNNEL_TYPE_NGE	0x01
+#define I40E_AQC_TUNNEL_TYPE_TEREDO	0x10
+	u8     reserved1[10];
 };
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_add_udp_tunnel);
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h b/drivers/net/ethernet/intel/i40evf/i40e_alloc.h
index d8654fb9e52..8e6a6dd9212 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_alloc.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index ae084378faa..a43155afdbe 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -40,12 +43,10 @@ i40e_status i40e_set_mac_type(struct i40e_hw *hw)
 	if (hw->vendor_id == PCI_VENDOR_ID_INTEL) {
 		switch (hw->device_id) {
 		case I40E_DEV_ID_SFP_XL710:
-		case I40E_DEV_ID_SFP_X710:
 		case I40E_DEV_ID_QEMU:
 		case I40E_DEV_ID_KX_A:
 		case I40E_DEV_ID_KX_B:
 		case I40E_DEV_ID_KX_C:
-		case I40E_DEV_ID_KX_D:
 		case I40E_DEV_ID_QSFP_A:
 		case I40E_DEV_ID_QSFP_B:
 		case I40E_DEV_ID_QSFP_C:
@@ -130,7 +131,11 @@ void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
  **/
 bool i40evf_check_asq_alive(struct i40e_hw *hw)
 {
-	return !!(rd32(hw, hw->aq.asq.len) & I40E_PF_ATQLEN_ATQENABLE_MASK);
+	if (hw->aq.asq.len)
+		return !!(rd32(hw, hw->aq.asq.len) &
+			  I40E_PF_ATQLEN_ATQENABLE_MASK);
+	else
+		return false;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h
index cb97b3eed44..a2ad9a4e399 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -160,11 +163,6 @@ struct i40e_hmc_info {
 	    (((sd_idx) << I40E_PFHMC_PDINV_PMSDIDX_SHIFT) |		\
 	     ((pd_idx) << I40E_PFHMC_PDINV_PMPDIDX_SHIFT)))
 
-#define I40E_INVALIDATE_VF_HMC_PD(hw, sd_idx, pd_idx, hmc_fn_id)	   \
-	wr32((hw), I40E_GLHMC_VFPDINV((hmc_fn_id) - I40E_FIRST_VF_FPM_ID), \
-	     (((sd_idx) << I40E_PFHMC_PDINV_PMSDIDX_SHIFT) |		   \
-	      ((pd_idx) << I40E_PFHMC_PDINV_PMPDIDX_SHIFT)))
-
 /**
  * I40E_FIND_SD_INDEX_LIMIT - finds segment descriptor index limit
  * @hmc_info: pointer to the HMC configuration information structure
@@ -223,7 +221,7 @@ i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw,
 					      u32 pd_index);
 i40e_status i40e_remove_pd_bp(struct i40e_hw *hw,
 					struct i40e_hmc_info *hmc_info,
-					u32 idx, bool is_pf);
+					u32 idx);
 i40e_status i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info,
 					     u32 idx);
 i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw,
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h
index 17e42ca26d0..d6f76224153 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -53,6 +56,7 @@ struct i40e_hmc_obj_rxq {
 	u8  tphdata_ena;
 	u8  tphhead_ena;
 	u8  lrxqthresh;
+	u8  prefena;	/* NOTE: normally must be set to 1 at init */
 };
 
 /* Tx queue context data */
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h
index 622f373b745..21a91b14bf8 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
index 97ab8c2b76f..849edcc2e39 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_register.h b/drivers/net/ethernet/intel/i40evf/i40e_register.h
index 30af953cf10..36983965581 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_register.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_register.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -1337,8 +1340,6 @@
 #define I40E_PFINT_ICR0_GPIO_MASK (0x1 << I40E_PFINT_ICR0_GPIO_SHIFT)
 #define I40E_PFINT_ICR0_TIMESYNC_SHIFT 23
 #define I40E_PFINT_ICR0_TIMESYNC_MASK (0x1 << I40E_PFINT_ICR0_TIMESYNC_SHIFT)
-#define I40E_PFINT_ICR0_STORM_DETECT_SHIFT 24
-#define I40E_PFINT_ICR0_STORM_DETECT_MASK (0x1 << I40E_PFINT_ICR0_STORM_DETECT_SHIFT)
 #define I40E_PFINT_ICR0_LINK_STAT_CHANGE_SHIFT 25
 #define I40E_PFINT_ICR0_LINK_STAT_CHANGE_MASK (0x1 << I40E_PFINT_ICR0_LINK_STAT_CHANGE_SHIFT)
 #define I40E_PFINT_ICR0_HMC_ERR_SHIFT 26
@@ -1364,8 +1365,6 @@
 #define I40E_PFINT_ICR0_ENA_GPIO_MASK (0x1 << I40E_PFINT_ICR0_ENA_GPIO_SHIFT)
 #define I40E_PFINT_ICR0_ENA_TIMESYNC_SHIFT 23
 #define I40E_PFINT_ICR0_ENA_TIMESYNC_MASK (0x1 << I40E_PFINT_ICR0_ENA_TIMESYNC_SHIFT)
-#define I40E_PFINT_ICR0_ENA_STORM_DETECT_SHIFT 24
-#define I40E_PFINT_ICR0_ENA_STORM_DETECT_MASK (0x1 << I40E_PFINT_ICR0_ENA_STORM_DETECT_SHIFT)
 #define I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT 25
 #define I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_MASK (0x1 << I40E_PFINT_ICR0_ENA_LINK_STAT_CHANGE_SHIFT)
 #define I40E_PFINT_ICR0_ENA_HMC_ERR_SHIFT 26
@@ -1586,6 +1585,14 @@
 #define I40E_GLLAN_TSOMSK_M 0x000442DC
 #define I40E_GLLAN_TSOMSK_M_TCPMSKM_SHIFT 0
 #define I40E_GLLAN_TSOMSK_M_TCPMSKM_MASK (0xFFF << I40E_GLLAN_TSOMSK_M_TCPMSKM_SHIFT)
+#define I40E_GLLAN_TXPRE_QDIS(_i) (0x000E6500 + ((_i) * 4)) /* i=0..11 */
+#define I40E_GLLAN_TXPRE_QDIS_QINDX_SHIFT 0
+#define I40E_GLLAN_TXPRE_QDIS_QINDX_MASK (0x7FF << I40E_GLLAN_TXPRE_QDIS_QINDX_SHIFT)
+#define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT 30
+#define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_MASK (0x1 << I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT)
+#define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT 31
+#define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_MASK (0x1 << I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT)
+
 #define I40E_PFLAN_QALLOC 0x001C0400
 #define I40E_PFLAN_QALLOC_FIRSTQ_SHIFT 0
 #define I40E_PFLAN_QALLOC_FIRSTQ_MASK (0x7FF << I40E_PFLAN_QALLOC_FIRSTQ_SHIFT)
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_status.h b/drivers/net/ethernet/intel/i40evf/i40e_status.h
index 7c08cc2e339..7fa7a41915c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_status.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_status.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index b9f50f40abe..48ebb6cd69f 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -725,10 +728,12 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				    u32 rx_error,
 				    u16 rx_ptype)
 {
+	struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(rx_ptype);
+	bool ipv4 = false, ipv6 = false;
 	bool ipv4_tunnel, ipv6_tunnel;
 	__wsum rx_udp_csum;
-	__sum16 csum;
 	struct iphdr *iph;
+	__sum16 csum;
 
 	ipv4_tunnel = (rx_ptype > I40E_RX_PTYPE_GRENAT4_MAC_PAY3) &&
 		      (rx_ptype < I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4);
@@ -739,29 +744,57 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 	skb->ip_summed = CHECKSUM_NONE;
 
 	/* Rx csum enabled and ip headers found? */
-	if (!(vsi->netdev->features & NETIF_F_RXCSUM &&
-	      rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
+	if (!(vsi->netdev->features & NETIF_F_RXCSUM))
 		return;
 
+	/* did the hardware decode the packet and checksum? */
+	if (!(rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT)))
+		return;
+
+	/* both known and outer_ip must be set for the below code to work */
+	if (!(decoded.known && decoded.outer_ip))
+		return;
+
+	if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
+	    decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4)
+		ipv4 = true;
+	else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP &&
+		 decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6)
+		ipv6 = true;
+
+	if (ipv4 &&
+	    (rx_error & ((1 << I40E_RX_DESC_ERROR_IPE_SHIFT) |
+			 (1 << I40E_RX_DESC_ERROR_EIPE_SHIFT))))
+		goto checksum_fail;
+
 	/* likely incorrect csum if alternate IP extension headers found */
-	if (rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT))
+	if (ipv6 &&
+	    decoded.inner_prot == I40E_RX_PTYPE_INNER_PROT_TCP &&
+	    rx_error & (1 << I40E_RX_DESC_ERROR_L4E_SHIFT) &&
+	    rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT))
+		/* don't increment checksum err here, non-fatal err */
 		return;
 
-	/* IP or L4 or outmost IP checksum error */
-	if (rx_error & ((1 << I40E_RX_DESC_ERROR_IPE_SHIFT) |
-			(1 << I40E_RX_DESC_ERROR_L4E_SHIFT) |
-			(1 << I40E_RX_DESC_ERROR_EIPE_SHIFT))) {
-		vsi->back->hw_csum_rx_error++;
+	/* there was some L4 error, count error and punt packet to the stack */
+	if (rx_error & (1 << I40E_RX_DESC_ERROR_L4E_SHIFT))
+		goto checksum_fail;
+
+	/* handle packets that were not able to be checksummed due
+	 * to arrival speed, in this case the stack can compute
+	 * the csum.
+	 */
+	if (rx_error & (1 << I40E_RX_DESC_ERROR_PPRS_SHIFT))
 		return;
-	}
 
+	/* If VXLAN traffic has an outer UDPv4 checksum we need to check
+	 * it in the driver, hardware does not do it for us.
+	 * Since L3L4P bit was set we assume a valid IHL value (>=5)
+	 * so the total length of IPv4 header is IHL*4 bytes
+	 * The UDP_0 bit *may* bet set if the *inner* header is UDP
+	 */
 	if (ipv4_tunnel &&
+	    (decoded.inner_prot != I40E_RX_PTYPE_INNER_PROT_UDP) &&
 	    !(rx_status & (1 << I40E_RX_DESC_STATUS_UDP_0_SHIFT))) {
-		/* If VXLAN traffic has an outer UDPv4 checksum we need to check
-		 * it in the driver, hardware does not do it for us.
-		 * Since L3L4P bit was set we assume a valid IHL value (>=5)
-		 * so the total length of IPv4 header is IHL*4 bytes
-		 */
 		skb->transport_header = skb->mac_header +
 					sizeof(struct ethhdr) +
 					(ip_hdr(skb)->ihl * 4);
@@ -778,13 +811,16 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi,
 				(skb->len - skb_transport_offset(skb)),
 				IPPROTO_UDP, rx_udp_csum);
 
-		if (udp_hdr(skb)->check != csum) {
-			vsi->back->hw_csum_rx_error++;
-			return;
-		}
+		if (udp_hdr(skb)->check != csum)
+			goto checksum_fail;
 	}
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	return;
+
+checksum_fail:
+	vsi->back->hw_csum_rx_error++;
 }
 
 /**
@@ -953,6 +989,9 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		/* ERR_MASK will only have valid bits if EOP set */
 		if (unlikely(rx_error & (1 << I40E_RX_DESC_ERROR_RXE_SHIFT))) {
 			dev_kfree_skb_any(skb);
+			/* TODO: shouldn't we increment a counter indicating the
+			 * drop?
+			 */
 			goto next_desc;
 		}
 
@@ -1508,9 +1547,7 @@ static int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size)
 static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 				      struct i40e_ring *tx_ring)
 {
-#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
 	unsigned int f;
-#endif
 	int count = 0;
 
 	/* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD,
@@ -1519,12 +1556,9 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb,
 	 *       + 1 desc for context descriptor,
 	 * otherwise try next time
 	 */
-#if PAGE_SIZE > I40E_MAX_DATA_PER_TXD
 	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
 		count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
-#else
-	count += skb_shinfo(skb)->nr_frags;
-#endif
+
 	count += TXD_USE_COUNT(skb_headlen(skb));
 	if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) {
 		tx_ring->tx_stats.tx_busy++;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
index 10bf49e18d7..30d248bc5d1 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -24,7 +27,7 @@
 #ifndef _I40E_TXRX_H_
 #define _I40E_TXRX_H_
 
-/* Interrupt Throttling and Rate Limiting (storm control) Goodies */
+/* Interrupt Throttling and Rate Limiting Goodies */
 
 #define I40E_MAX_ITR               0x0FF0  /* reg uses 2 usec resolution */
 #define I40E_MIN_ITR               0x0004  /* reg uses 2 usec resolution */
@@ -66,16 +69,11 @@ enum i40e_dyn_idx_t {
 
 /* Supported RSS offloads */
 #define I40E_DEFAULT_RSS_HENA ( \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
 	((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4) | \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
-	((u64)1 << I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_UDP) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN) | \
 	((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP) | \
@@ -119,11 +117,11 @@ enum i40e_dyn_idx_t {
 #define i40e_rx_desc i40e_32byte_rx_desc
 
 #define I40E_MIN_TX_LEN		17
-#define I40E_MAX_DATA_PER_TXD	16383	/* aka 16kB - 1 */
+#define I40E_MAX_DATA_PER_TXD	8192
 
 /* Tx Descriptors needed, worst case */
 #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), I40E_MAX_DATA_PER_TXD)
-#define DESC_NEEDED ((MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE)) + 4)
+#define DESC_NEEDED (MAX_SKB_FRAGS + 4)
 
 #define I40E_TX_FLAGS_CSUM		(u32)(1)
 #define I40E_TX_FLAGS_HW_VLAN		(u32)(1 << 1)
@@ -180,7 +178,6 @@ enum i40e_ring_state_t {
 	__I40E_TX_DETECT_HANG,
 	__I40E_HANG_CHECK_ARMED,
 	__I40E_RX_PS_ENABLED,
-	__I40E_RX_LRO_ENABLED,
 	__I40E_RX_16BYTE_DESC_ENABLED,
 };
 
@@ -196,12 +193,6 @@ enum i40e_ring_state_t {
 	set_bit(__I40E_TX_DETECT_HANG, &(ring)->state)
 #define clear_check_for_tx_hang(ring) \
 	clear_bit(__I40E_TX_DETECT_HANG, &(ring)->state)
-#define ring_is_lro_enabled(ring) \
-	test_bit(__I40E_RX_LRO_ENABLED, &(ring)->state)
-#define set_ring_lro_enabled(ring) \
-	set_bit(__I40E_RX_LRO_ENABLED, &(ring)->state)
-#define clear_ring_lro_enabled(ring) \
-	clear_bit(__I40E_RX_LRO_ENABLED, &(ring)->state)
 #define ring_is_16byte_desc_enabled(ring) \
 	test_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state)
 #define set_ring_16byte_desc_enabled(ring) \
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h
index 4673b3381ed..d3cf5a69de5 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -32,13 +35,11 @@
 #include "i40e_lan_hmc.h"
 
 /* Device IDs */
-#define I40E_DEV_ID_SFP_XL710	0x1572
-#define I40E_DEV_ID_SFP_X710		0x1573
+#define I40E_DEV_ID_SFP_XL710		0x1572
 #define I40E_DEV_ID_QEMU		0x1574
 #define I40E_DEV_ID_KX_A		0x157F
 #define I40E_DEV_ID_KX_B		0x1580
 #define I40E_DEV_ID_KX_C		0x1581
-#define I40E_DEV_ID_KX_D		0x1582
 #define I40E_DEV_ID_QSFP_A		0x1583
 #define I40E_DEV_ID_QSFP_B		0x1584
 #define I40E_DEV_ID_QSFP_C		0x1585
@@ -57,8 +58,8 @@
 /* Max default timeout in ms, */
 #define I40E_MAX_NVM_TIMEOUT		18000
 
-/* Switch from mc to the 2usec global time (this is the GTIME resolution) */
-#define I40E_MS_TO_GTIME(time)		(((time) * 1000) / 2)
+/* Switch from ms to the 1usec global time (this is the GTIME resolution) */
+#define I40E_MS_TO_GTIME(time)		((time) * 1000)
 
 /* forward declaration */
 struct i40e_hw;
@@ -101,15 +102,6 @@ enum i40e_debug_mask {
 	I40E_DEBUG_ALL			= 0xFFFFFFFF
 };
 
-/* PCI Bus Info */
-#define I40E_PCI_LINK_WIDTH_1		0x10
-#define I40E_PCI_LINK_WIDTH_2		0x20
-#define I40E_PCI_LINK_WIDTH_4		0x40
-#define I40E_PCI_LINK_WIDTH_8		0x80
-#define I40E_PCI_LINK_SPEED_2500	0x1
-#define I40E_PCI_LINK_SPEED_5000	0x2
-#define I40E_PCI_LINK_SPEED_8000	0x3
-
 /* These are structs for managing the hardware information and the operations.
  * The structures of function pointers are filled out at init time when we
  * know for sure exactly which hardware we're working with.  This gives us the
@@ -173,6 +165,9 @@ struct i40e_link_status {
 	u8 loopback;
 	/* is Link Status Event notification to SW enabled */
 	bool lse_enable;
+	u16 max_frame_size;
+	bool crc_enable;
+	u8 pacing;
 };
 
 struct i40e_phy_info {
@@ -415,6 +410,7 @@ struct i40e_driver_version {
 	u8 minor_version;
 	u8 build_version;
 	u8 subbuild_version;
+	u8 driver_string[32];
 };
 
 /* RX Descriptors */
@@ -494,9 +490,6 @@ union i40e_32byte_rx_desc {
 	} wb;  /* writeback */
 };
 
-#define I40E_RXD_QW1_STATUS_SHIFT	0
-#define I40E_RXD_QW1_STATUS_MASK	(0x7FFFUL << I40E_RXD_QW1_STATUS_SHIFT)
-
 enum i40e_rx_desc_status_bits {
 	/* Note: These are predefined bit offsets */
 	I40E_RX_DESC_STATUS_DD_SHIFT		= 0,
@@ -513,9 +506,14 @@ enum i40e_rx_desc_status_bits {
 	I40E_RX_DESC_STATUS_LPBK_SHIFT		= 14,
 	I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT	= 15,
 	I40E_RX_DESC_STATUS_RESERVED_SHIFT	= 16, /* 2 BITS */
-	I40E_RX_DESC_STATUS_UDP_0_SHIFT		= 18
+	I40E_RX_DESC_STATUS_UDP_0_SHIFT		= 18,
+	I40E_RX_DESC_STATUS_LAST /* this entry must be last!!! */
 };
 
+#define I40E_RXD_QW1_STATUS_SHIFT	0
+#define I40E_RXD_QW1_STATUS_MASK	(((1 << I40E_RX_DESC_STATUS_LAST) - 1) \
+					 << I40E_RXD_QW1_STATUS_SHIFT)
+
 #define I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT   I40E_RX_DESC_STATUS_TSYNINDX_SHIFT
 #define I40E_RXD_QW1_STATUS_TSYNINDX_MASK	(0x3UL << \
 					     I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT)
@@ -543,7 +541,8 @@ enum i40e_rx_desc_error_bits {
 	I40E_RX_DESC_ERROR_IPE_SHIFT		= 3,
 	I40E_RX_DESC_ERROR_L4E_SHIFT		= 4,
 	I40E_RX_DESC_ERROR_EIPE_SHIFT		= 5,
-	I40E_RX_DESC_ERROR_OVERSIZE_SHIFT	= 6
+	I40E_RX_DESC_ERROR_OVERSIZE_SHIFT	= 6,
+	I40E_RX_DESC_ERROR_PPRS_SHIFT		= 7
 };
 
 enum i40e_rx_desc_error_l3l4e_fcoe_masks {
@@ -664,7 +663,6 @@ enum i40e_rx_desc_ext_status_bits {
 	I40E_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT	= 1,
 	I40E_RX_DESC_EXT_STATUS_FLEXBL_SHIFT	= 2, /* 2 BITS */
 	I40E_RX_DESC_EXT_STATUS_FLEXBH_SHIFT	= 4, /* 2 BITS */
-	I40E_RX_DESC_EXT_STATUS_FTYPE_SHIFT	= 6, /* 3 BITS */
 	I40E_RX_DESC_EXT_STATUS_FDLONGB_SHIFT	= 9,
 	I40E_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT	= 10,
 	I40E_RX_DESC_EXT_STATUS_PELONGB_SHIFT	= 11,
@@ -868,18 +866,14 @@ struct i40e_filter_program_desc {
 
 /* Packet Classifier Types for filters */
 enum i40e_filter_pctype {
-	/* Note: Values 0-28 are reserved for future use */
-	I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP	= 29,
-	I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP	= 30,
+	/* Note: Values 0-30 are reserved for future use */
 	I40E_FILTER_PCTYPE_NONF_IPV4_UDP		= 31,
-	I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN		= 32,
+	/* Note: Value 32 is reserved for future use */
 	I40E_FILTER_PCTYPE_NONF_IPV4_TCP		= 33,
 	I40E_FILTER_PCTYPE_NONF_IPV4_SCTP		= 34,
 	I40E_FILTER_PCTYPE_NONF_IPV4_OTHER		= 35,
 	I40E_FILTER_PCTYPE_FRAG_IPV4			= 36,
-	/* Note: Values 37-38 are reserved for future use */
-	I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP	= 39,
-	I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP	= 40,
+	/* Note: Values 37-40 are reserved for future use */
 	I40E_FILTER_PCTYPE_NONF_IPV6_UDP		= 41,
 	I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN		= 42,
 	I40E_FILTER_PCTYPE_NONF_IPV6_TCP		= 43,
@@ -961,6 +955,16 @@ struct i40e_vsi_context {
 	struct i40e_aqc_vsi_properties_data info;
 };
 
+struct i40e_veb_context {
+	u16 seid;
+	u16 uplink_seid;
+	u16 veb_number;
+	u16 vebs_allocated;
+	u16 vebs_unallocated;
+	u16 flags;
+	struct i40e_aqc_get_veb_parameters_completion info;
+};
+
 /* Statistics collected by each port, VSI, VEB, and S-channel */
 struct i40e_eth_stats {
 	u64 rx_bytes;			/* gorc */
@@ -968,8 +972,6 @@ struct i40e_eth_stats {
 	u64 rx_multicast;		/* mprc */
 	u64 rx_broadcast;		/* bprc */
 	u64 rx_discards;		/* rdpc */
-	u64 rx_errors;			/* repc */
-	u64 rx_missed;			/* rmpc */
 	u64 rx_unknown_protocol;	/* rupp */
 	u64 tx_bytes;			/* gotc */
 	u64 tx_unicast;			/* uptc */
@@ -1021,9 +1023,12 @@ struct i40e_hw_port_stats {
 	u64 tx_size_big;		/* ptc9522 */
 	u64 mac_short_packet_dropped;	/* mspdc */
 	u64 checksum_error;		/* xec */
+	/* flow director stats */
+	u64 fd_atr_match;
+	u64 fd_sb_match;
 	/* EEE LPI */
-	bool tx_lpi_status;
-	bool rx_lpi_status;
+	u32 tx_lpi_status;
+	u32 rx_lpi_status;
 	u64 tx_lpi_count;		/* etlpic */
 	u64 rx_lpi_count;		/* erlpic */
 };
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
index ccf45d04b7e..cd18d568900 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_virtchnl.h
@@ -1,7 +1,7 @@
 /*******************************************************************************
  *
  * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver
- * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2013 - 2014 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -338,10 +341,6 @@ struct i40e_virtchnl_pf_event {
 	int severity;
 };
 
-/* The following are TBD, not necessary for LAN functionality.
- * I40E_VIRTCHNL_OP_FCOE
- */
-
 /* VF reset states - these are written into the RSTAT register:
  * I40E_VFGEN_RSTAT1 on the PF
  * I40E_VFGEN_RSTAT on the VF
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h
index 807807d6238..30ef519d4b9 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf.h
+++ b/drivers/net/ethernet/intel/i40evf/i40evf.h
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -77,7 +80,7 @@ struct i40e_vsi {
 #define I40EVF_MIN_TXD       64
 #define I40EVF_MAX_RXD       4096
 #define I40EVF_MIN_RXD       64
-#define I40EVF_REQ_DESCRIPTOR_MULTIPLE  8
+#define I40EVF_REQ_DESCRIPTOR_MULTIPLE  32
 
 /* Supported Rx Buffer Sizes */
 #define I40EVF_RXBUFFER_64    64     /* Used for packet split */
@@ -193,10 +196,12 @@ struct i40evf_adapter {
 	struct i40e_ring *tx_rings[I40E_MAX_VSI_QP];
 	u32 tx_timeout_count;
 	struct list_head mac_filter_list;
+	u32 tx_desc_count;
 
 	/* RX */
 	struct i40e_ring *rx_rings[I40E_MAX_VSI_QP];
 	u64 hw_csum_rx_error;
+	u32 rx_desc_count;
 	int num_msix_vectors;
 	struct msix_entry *msix_entries;
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
index 8b0db1ce179..60407a9df0c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -44,8 +47,6 @@ static const struct i40evf_stats i40evf_gstrings_stats[] = {
 	I40EVF_STAT("rx_multicast", current_stats.rx_multicast),
 	I40EVF_STAT("rx_broadcast", current_stats.rx_broadcast),
 	I40EVF_STAT("rx_discards", current_stats.rx_discards),
-	I40EVF_STAT("rx_errors", current_stats.rx_errors),
-	I40EVF_STAT("rx_missed", current_stats.rx_missed),
 	I40EVF_STAT("rx_unknown_protocol", current_stats.rx_unknown_protocol),
 	I40EVF_STAT("tx_bytes", current_stats.tx_bytes),
 	I40EVF_STAT("tx_unicast", current_stats.tx_unicast),
@@ -56,10 +57,12 @@ static const struct i40evf_stats i40evf_gstrings_stats[] = {
 };
 
 #define I40EVF_GLOBAL_STATS_LEN ARRAY_SIZE(i40evf_gstrings_stats)
-#define I40EVF_QUEUE_STATS_LEN \
+#define I40EVF_QUEUE_STATS_LEN(_dev) \
 	(((struct i40evf_adapter *) \
-		netdev_priv(netdev))->vsi_res->num_queue_pairs * 4)
-#define I40EVF_STATS_LEN (I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN)
+		netdev_priv(_dev))->vsi_res->num_queue_pairs \
+		  * 2 * (sizeof(struct i40e_queue_stats) / sizeof(u64)))
+#define I40EVF_STATS_LEN(_dev) \
+	(I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN(_dev))
 
 /**
  * i40evf_get_settings - Get Link Speed and Duplex settings
@@ -75,7 +78,7 @@ static int i40evf_get_settings(struct net_device *netdev,
 	/* In the future the VF will be able to query the PF for
 	 * some information - for now use a dummy value
 	 */
-	ecmd->supported = SUPPORTED_10000baseT_Full;
+	ecmd->supported = 0;
 	ecmd->autoneg = AUTONEG_DISABLE;
 	ecmd->transceiver = XCVR_DUMMY1;
 	ecmd->port = PORT_NONE;
@@ -94,9 +97,9 @@ static int i40evf_get_settings(struct net_device *netdev,
 static int i40evf_get_sset_count(struct net_device *netdev, int sset)
 {
 	if (sset == ETH_SS_STATS)
-		return I40EVF_STATS_LEN;
+		return I40EVF_STATS_LEN(netdev);
 	else
-		return -ENOTSUPP;
+		return -EINVAL;
 }
 
 /**
@@ -219,13 +222,11 @@ static void i40evf_get_ringparam(struct net_device *netdev,
 				  struct ethtool_ringparam *ring)
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
-	struct i40e_ring *tx_ring = adapter->tx_rings[0];
-	struct i40e_ring *rx_ring = adapter->rx_rings[0];
 
 	ring->rx_max_pending = I40EVF_MAX_RXD;
 	ring->tx_max_pending = I40EVF_MAX_TXD;
-	ring->rx_pending = rx_ring->count;
-	ring->tx_pending = tx_ring->count;
+	ring->rx_pending = adapter->rx_desc_count;
+	ring->tx_pending = adapter->tx_desc_count;
 }
 
 /**
@@ -241,7 +242,6 @@ static int i40evf_set_ringparam(struct net_device *netdev,
 {
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 	u32 new_rx_count, new_tx_count;
-	int i;
 
 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
 		return -EINVAL;
@@ -257,17 +257,16 @@ static int i40evf_set_ringparam(struct net_device *netdev,
 	new_rx_count = ALIGN(new_rx_count, I40EVF_REQ_DESCRIPTOR_MULTIPLE);
 
 	/* if nothing to do return success */
-	if ((new_tx_count == adapter->tx_rings[0]->count) &&
-	    (new_rx_count == adapter->rx_rings[0]->count))
+	if ((new_tx_count == adapter->tx_desc_count) &&
+	    (new_rx_count == adapter->rx_desc_count))
 		return 0;
 
-	for (i = 0; i < adapter->vsi_res->num_queue_pairs; i++) {
-		adapter->tx_rings[0]->count = new_tx_count;
-		adapter->rx_rings[0]->count = new_rx_count;
-	}
+	adapter->tx_desc_count = new_tx_count;
+	adapter->rx_desc_count = new_rx_count;
 
 	if (netif_running(netdev))
 		i40evf_reinit_locked(adapter);
+
 	return 0;
 }
 
@@ -290,14 +289,13 @@ static int i40evf_get_coalesce(struct net_device *netdev,
 	ec->rx_max_coalesced_frames = vsi->work_limit;
 
 	if (ITR_IS_DYNAMIC(vsi->rx_itr_setting))
-		ec->rx_coalesce_usecs = 1;
-	else
-		ec->rx_coalesce_usecs = vsi->rx_itr_setting;
+		ec->use_adaptive_rx_coalesce = 1;
 
 	if (ITR_IS_DYNAMIC(vsi->tx_itr_setting))
-		ec->tx_coalesce_usecs = 1;
-	else
-		ec->tx_coalesce_usecs = vsi->tx_itr_setting;
+		ec->use_adaptive_tx_coalesce = 1;
+
+	ec->rx_coalesce_usecs = vsi->rx_itr_setting & ~I40E_ITR_DYNAMIC;
+	ec->tx_coalesce_usecs = vsi->tx_itr_setting & ~I40E_ITR_DYNAMIC;
 
 	return 0;
 }
@@ -318,54 +316,361 @@ static int i40evf_set_coalesce(struct net_device *netdev,
 	struct i40e_q_vector *q_vector;
 	int i;
 
-	if (ec->tx_max_coalesced_frames || ec->rx_max_coalesced_frames)
-		vsi->work_limit = ec->tx_max_coalesced_frames;
+	if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
+		vsi->work_limit = ec->tx_max_coalesced_frames_irq;
+
+	if ((ec->rx_coalesce_usecs >= (I40E_MIN_ITR << 1)) &&
+	    (ec->rx_coalesce_usecs <= (I40E_MAX_ITR << 1)))
+		vsi->rx_itr_setting = ec->rx_coalesce_usecs;
+
+	else
+		return -EINVAL;
+
+	if ((ec->tx_coalesce_usecs >= (I40E_MIN_ITR << 1)) &&
+	    (ec->tx_coalesce_usecs <= (I40E_MAX_ITR << 1)))
+		vsi->tx_itr_setting = ec->tx_coalesce_usecs;
+	else if (ec->use_adaptive_tx_coalesce)
+		vsi->tx_itr_setting = (I40E_ITR_DYNAMIC |
+				       ITR_REG_TO_USEC(I40E_ITR_RX_DEF));
+	else
+		return -EINVAL;
+
+	if (ec->use_adaptive_rx_coalesce)
+		vsi->rx_itr_setting |= I40E_ITR_DYNAMIC;
+	else
+		vsi->rx_itr_setting &= ~I40E_ITR_DYNAMIC;
+
+	if (ec->use_adaptive_tx_coalesce)
+		vsi->tx_itr_setting |= I40E_ITR_DYNAMIC;
+	else
+		vsi->tx_itr_setting &= ~I40E_ITR_DYNAMIC;
 
-	switch (ec->rx_coalesce_usecs) {
-	case 0:
-		vsi->rx_itr_setting = 0;
+	for (i = 0; i < adapter->num_msix_vectors - NONQ_VECS; i++) {
+		q_vector = adapter->q_vector[i];
+		q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
+		wr32(hw, I40E_VFINT_ITRN1(0, i), q_vector->rx.itr);
+		q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
+		wr32(hw, I40E_VFINT_ITRN1(1, i), q_vector->tx.itr);
+		i40e_flush(hw);
+	}
+
+	return 0;
+}
+
+/**
+ * i40e_get_rss_hash_opts - Get RSS hash Input Set for each flow type
+ * @adapter: board private structure
+ * @cmd: ethtool rxnfc command
+ *
+ * Returns Success if the flow is supported, else Invalid Input.
+ **/
+static int i40evf_get_rss_hash_opts(struct i40evf_adapter *adapter,
+				    struct ethtool_rxnfc *cmd)
+{
+	struct i40e_hw *hw = &adapter->hw;
+	u64 hena = (u64)rd32(hw, I40E_VFQF_HENA(0)) |
+		   ((u64)rd32(hw, I40E_VFQF_HENA(1)) << 32);
+
+	/* We always hash on IP src and dest addresses */
+	cmd->data = RXH_IP_SRC | RXH_IP_DST;
+
+	switch (cmd->flow_type) {
+	case TCP_V4_FLOW:
+		if (hena & ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP))
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		break;
-	case 1:
-		vsi->rx_itr_setting = (I40E_ITR_DYNAMIC
-				       | ITR_REG_TO_USEC(I40E_ITR_RX_DEF));
+	case UDP_V4_FLOW:
+		if (hena & ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_UDP))
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		break;
-	default:
-		if ((ec->rx_coalesce_usecs < (I40E_MIN_ITR << 1)) ||
-		    (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1)))
-			return -EINVAL;
-		vsi->rx_itr_setting = ec->rx_coalesce_usecs;
+
+	case SCTP_V4_FLOW:
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case IPV4_FLOW:
+		break;
+
+	case TCP_V6_FLOW:
+		if (hena & ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP))
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
 		break;
+	case UDP_V6_FLOW:
+		if (hena & ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_UDP))
+			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		break;
+
+	case SCTP_V6_FLOW:
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case IPV6_FLOW:
+		break;
+	default:
+		cmd->data = 0;
+		return -EINVAL;
 	}
 
-	switch (ec->tx_coalesce_usecs) {
-	case 0:
-		vsi->tx_itr_setting = 0;
+	return 0;
+}
+
+/**
+ * i40evf_get_rxnfc - command to get RX flow classification rules
+ * @netdev: network interface device structure
+ * @cmd: ethtool rxnfc command
+ *
+ * Returns Success if the command is supported.
+ **/
+static int i40evf_get_rxnfc(struct net_device *netdev,
+			    struct ethtool_rxnfc *cmd,
+			    u32 *rule_locs)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_GRXRINGS:
+		cmd->data = adapter->vsi_res->num_queue_pairs;
+		ret = 0;
 		break;
-	case 1:
-		vsi->tx_itr_setting = (I40E_ITR_DYNAMIC
-				       | ITR_REG_TO_USEC(I40E_ITR_TX_DEF));
+	case ETHTOOL_GRXFH:
+		ret = i40evf_get_rss_hash_opts(adapter, cmd);
 		break;
 	default:
-		if ((ec->tx_coalesce_usecs < (I40E_MIN_ITR << 1)) ||
-		    (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1)))
+		break;
+	}
+
+	return ret;
+}
+
+/**
+ * i40evf_set_rss_hash_opt - Enable/Disable flow types for RSS hash
+ * @adapter: board private structure
+ * @cmd: ethtool rxnfc command
+ *
+ * Returns Success if the flow input set is supported.
+ **/
+static int i40evf_set_rss_hash_opt(struct i40evf_adapter *adapter,
+				   struct ethtool_rxnfc *nfc)
+{
+	struct i40e_hw *hw = &adapter->hw;
+
+	u64 hena = (u64)rd32(hw, I40E_VFQF_HENA(0)) |
+		   ((u64)rd32(hw, I40E_VFQF_HENA(1)) << 32);
+
+	/* RSS does not support anything other than hashing
+	 * to queues on src and dst IPs and ports
+	 */
+	if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+			  RXH_L4_B_0_1 | RXH_L4_B_2_3))
+		return -EINVAL;
+
+	/* We need at least the IP SRC and DEST fields for hashing */
+	if (!(nfc->data & RXH_IP_SRC) ||
+	    !(nfc->data & RXH_IP_DST))
+		return -EINVAL;
+
+	switch (nfc->flow_type) {
+	case TCP_V4_FLOW:
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			hena &= ~((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
+			break;
+		default:
 			return -EINVAL;
-		vsi->tx_itr_setting = ec->tx_coalesce_usecs;
+		}
+		break;
+	case TCP_V6_FLOW:
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			hena &= ~((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case UDP_V4_FLOW:
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			hena &= ~(((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
+				  ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4));
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			hena |= (((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
+				 ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4));
+			break;
+		default:
+			return -EINVAL;
+		}
 		break;
+	case UDP_V6_FLOW:
+		switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+		case 0:
+			hena &= ~(((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
+				  ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6));
+			break;
+		case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+			hena |= (((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
+				 ((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6));
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case AH_ESP_V4_FLOW:
+	case AH_V4_FLOW:
+	case ESP_V4_FLOW:
+	case SCTP_V4_FLOW:
+		if ((nfc->data & RXH_L4_B_0_1) ||
+		    (nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_OTHER);
+		break;
+	case AH_ESP_V6_FLOW:
+	case AH_V6_FLOW:
+	case ESP_V6_FLOW:
+	case SCTP_V6_FLOW:
+		if ((nfc->data & RXH_L4_B_0_1) ||
+		    (nfc->data & RXH_L4_B_2_3))
+			return -EINVAL;
+		hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_OTHER);
+		break;
+	case IPV4_FLOW:
+		hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) |
+			((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV4);
+		break;
+	case IPV6_FLOW:
+		hena |= ((u64)1 << I40E_FILTER_PCTYPE_NONF_IPV6_OTHER) |
+			((u64)1 << I40E_FILTER_PCTYPE_FRAG_IPV6);
+		break;
+	default:
+		return -EINVAL;
 	}
 
-	for (i = 0; i < adapter->num_msix_vectors - NONQ_VECS; i++) {
-		q_vector = adapter->q_vector[i];
-		q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
-		wr32(hw, I40E_VFINT_ITRN1(0, i), q_vector->rx.itr);
-		q_vector->tx.itr = ITR_TO_REG(vsi->tx_itr_setting);
-		wr32(hw, I40E_VFINT_ITRN1(1, i), q_vector->tx.itr);
-		i40e_flush(hw);
+	wr32(hw, I40E_VFQF_HENA(0), (u32)hena);
+	wr32(hw, I40E_VFQF_HENA(1), (u32)(hena >> 32));
+	i40e_flush(hw);
+
+	return 0;
+}
+
+/**
+ * i40evf_set_rxnfc - command to set RX flow classification rules
+ * @netdev: network interface device structure
+ * @cmd: ethtool rxnfc command
+ *
+ * Returns Success if the command is supported.
+ **/
+static int i40evf_set_rxnfc(struct net_device *netdev,
+			    struct ethtool_rxnfc *cmd)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	int ret = -EOPNOTSUPP;
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXFH:
+		ret = i40evf_set_rss_hash_opt(adapter, cmd);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+/**
+ * i40evf_get_channels: get the number of channels supported by the device
+ * @netdev: network interface device structure
+ * @ch: channel information structure
+ *
+ * For the purposes of our device, we only use combined channels, i.e. a tx/rx
+ * queue pair. Report one extra channel to match our "other" MSI-X vector.
+ **/
+static void i40evf_get_channels(struct net_device *netdev,
+				struct ethtool_channels *ch)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+
+	/* Report maximum channels */
+	ch->max_combined = adapter->vsi_res->num_queue_pairs;
+
+	ch->max_other = NONQ_VECS;
+	ch->other_count = NONQ_VECS;
+
+	ch->combined_count = adapter->vsi_res->num_queue_pairs;
+}
+
+/**
+ * i40evf_get_rxfh_indir_size - get the rx flow hash indirection table size
+ * @netdev: network interface device structure
+ *
+ * Returns the table size.
+ **/
+static u32 i40evf_get_rxfh_indir_size(struct net_device *netdev)
+{
+	return (I40E_VFQF_HLUT_MAX_INDEX + 1) * 4;
+}
+
+/**
+ * i40evf_get_rxfh - get the rx flow hash indirection table
+ * @netdev: network interface device structure
+ * @indir: indirection table
+ * @key: hash key (will be %NULL until get_rxfh_key_size is implemented)
+ *
+ * Reads the indirection table directly from the hardware. Always returns 0.
+ **/
+static int i40evf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	struct i40e_hw *hw = &adapter->hw;
+	u32 hlut_val;
+	int i, j;
+
+	for (i = 0, j = 0; i < I40E_VFQF_HLUT_MAX_INDEX; i++) {
+		hlut_val = rd32(hw, I40E_VFQF_HLUT(i));
+		indir[j++] = hlut_val & 0xff;
+		indir[j++] = (hlut_val >> 8) & 0xff;
+		indir[j++] = (hlut_val >> 16) & 0xff;
+		indir[j++] = (hlut_val >> 24) & 0xff;
+	}
+	return 0;
+}
+
+/**
+ * i40evf_set_rxfh - set the rx flow hash indirection table
+ * @netdev: network interface device structure
+ * @indir: indirection table
+ * @key: hash key (will be %NULL until get_rxfh_key_size is implemented)
+ *
+ * Returns -EINVAL if the table specifies an inavlid queue id, otherwise
+ * returns 0 after programming the table.
+ **/
+static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir,
+			   const u8 *key)
+{
+	struct i40evf_adapter *adapter = netdev_priv(netdev);
+	struct i40e_hw *hw = &adapter->hw;
+	u32 hlut_val;
+	int i, j;
+
+	for (i = 0, j = 0; i < I40E_VFQF_HLUT_MAX_INDEX + 1; i++) {
+		hlut_val = indir[j++];
+		hlut_val |= indir[j++] << 8;
+		hlut_val |= indir[j++] << 16;
+		hlut_val |= indir[j++] << 24;
+		wr32(hw, I40E_VFQF_HLUT(i), hlut_val);
 	}
 
 	return 0;
 }
 
-static struct ethtool_ops i40evf_ethtool_ops = {
+static const struct ethtool_ops i40evf_ethtool_ops = {
 	.get_settings		= i40evf_get_settings,
 	.get_drvinfo		= i40evf_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
@@ -378,6 +683,12 @@ static struct ethtool_ops i40evf_ethtool_ops = {
 	.set_msglevel		= i40evf_set_msglevel,
 	.get_coalesce		= i40evf_get_coalesce,
 	.set_coalesce		= i40evf_set_coalesce,
+	.get_rxnfc		= i40evf_get_rxnfc,
+	.set_rxnfc		= i40evf_set_rxnfc,
+	.get_rxfh_indir_size	= i40evf_get_rxfh_indir_size,
+	.get_rxfh		= i40evf_get_rxfh,
+	.set_rxfh		= i40evf_set_rxfh,
+	.get_channels		= i40evf_get_channels,
 };
 
 /**
@@ -389,5 +700,5 @@ static struct ethtool_ops i40evf_ethtool_ops = {
  **/
 void i40evf_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &i40evf_ethtool_ops);
+	netdev->ethtool_ops = &i40evf_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index 2797548fde0..7fc5f3b5d6b 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -25,13 +28,15 @@
 #include "i40e_prototype.h"
 static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter);
 static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter);
+static void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter);
+static void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter);
 static int i40evf_close(struct net_device *netdev);
 
 char i40evf_driver_name[] = "i40evf";
 static const char i40evf_driver_string[] =
 	"Intel(R) XL710 X710 Virtual Function Network Driver";
 
-#define DRV_VERSION "0.9.16"
+#define DRV_VERSION "0.9.34"
 const char i40evf_driver_version[] = DRV_VERSION;
 static const char i40evf_copyright[] =
 	"Copyright (c) 2013 - 2014 Intel Corporation.";
@@ -167,7 +172,6 @@ static void i40evf_tx_timeout(struct net_device *netdev)
 	struct i40evf_adapter *adapter = netdev_priv(netdev);
 
 	adapter->tx_timeout_count++;
-	dev_info(&adapter->pdev->dev, "TX timeout detected.\n");
 	if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) {
 		adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
 		schedule_work(&adapter->reset_task);
@@ -657,12 +661,9 @@ i40evf_vlan_filter *i40evf_add_vlan(struct i40evf_adapter *adapter, u16 vlan)
 	f = i40evf_find_vlan(adapter, vlan);
 	if (NULL == f) {
 		f = kzalloc(sizeof(*f), GFP_ATOMIC);
-		if (NULL == f) {
-			dev_info(&adapter->pdev->dev,
-				 "%s: no memory for new VLAN filter\n",
-				 __func__);
+		if (NULL == f)
 			return NULL;
-		}
+
 		f->vlan = vlan;
 
 		INIT_LIST_HEAD(&f->list);
@@ -688,7 +689,6 @@ static void i40evf_del_vlan(struct i40evf_adapter *adapter, u16 vlan)
 		f->remove = true;
 		adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER;
 	}
-	return;
 }
 
 /**
@@ -767,14 +767,12 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter,
 	if (NULL == f) {
 		f = kzalloc(sizeof(*f), GFP_ATOMIC);
 		if (NULL == f) {
-			dev_info(&adapter->pdev->dev,
-				 "%s: no memory for new filter\n", __func__);
 			clear_bit(__I40EVF_IN_CRITICAL_TASK,
 				  &adapter->crit_section);
 			return NULL;
 		}
 
-		memcpy(f->macaddr, macaddr, ETH_ALEN);
+		ether_addr_copy(f->macaddr, macaddr);
 
 		list_add(&f->list, &adapter->mac_filter_list);
 		f->add = true;
@@ -807,9 +805,8 @@ static int i40evf_set_mac(struct net_device *netdev, void *p)
 
 	f = i40evf_add_filter(adapter, addr->sa_data);
 	if (f) {
-		memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
-		memcpy(netdev->dev_addr, adapter->hw.mac.addr,
-		       netdev->addr_len);
+		ether_addr_copy(hw->mac.addr, addr->sa_data);
+		ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr);
 	}
 
 	return (f == NULL) ? -ENOMEM : 0;
@@ -841,7 +838,7 @@ static void i40evf_set_rx_mode(struct net_device *netdev)
 	list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) {
 		bool found = false;
 
-		if (f->macaddr[0] & 0x01) {
+		if (is_multicast_ether_addr(f->macaddr)) {
 			netdev_for_each_mc_addr(mca, netdev) {
 				if (ether_addr_equal(mca->addr, f->macaddr)) {
 					found = true;
@@ -970,6 +967,9 @@ void i40evf_down(struct i40evf_adapter *adapter)
 	struct net_device *netdev = adapter->netdev;
 	struct i40evf_mac_filter *f;
 
+	if (adapter->state == __I40EVF_DOWN)
+		return;
+
 	/* remove all MAC filters */
 	list_for_each_entry(f, &adapter->mac_filter_list, list) {
 		f->remove = true;
@@ -1027,30 +1027,21 @@ i40evf_acquire_msix_vectors(struct i40evf_adapter *adapter, int vectors)
 	 * Right now, we simply care about how many we'll get; we'll
 	 * set them up later while requesting irq's.
 	 */
-	while (vectors >= vector_threshold) {
-		err = pci_enable_msix(adapter->pdev, adapter->msix_entries,
-				      vectors);
-		if (!err) /* Success in acquiring all requested vectors. */
-			break;
-		else if (err < 0)
-			vectors = 0; /* Nasty failure, quit now */
-		else /* err == number of vectors we should try again with */
-			vectors = err;
-	}
-
-	if (vectors < vector_threshold) {
-		dev_err(&adapter->pdev->dev, "Unable to allocate MSI-X interrupts.\n");
+	err = pci_enable_msix_range(adapter->pdev, adapter->msix_entries,
+				    vector_threshold, vectors);
+	if (err < 0) {
+		dev_err(&adapter->pdev->dev, "Unable to allocate MSI-X interrupts\n");
 		kfree(adapter->msix_entries);
 		adapter->msix_entries = NULL;
-		err = -EIO;
-	} else {
-		/* Adjust for only the vectors we'll use, which is minimum
-		 * of max_msix_q_vectors + NONQ_VECS, or the number of
-		 * vectors we were allocated.
-		 */
-		adapter->num_msix_vectors = vectors;
+		return err;
 	}
-	return err;
+
+	/* Adjust for only the vectors we'll use, which is minimum
+	 * of max_msix_q_vectors + NONQ_VECS, or the number of
+	 * vectors we were allocated.
+	 */
+	adapter->num_msix_vectors = err;
+	return 0;
 }
 
 /**
@@ -1096,14 +1087,14 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter)
 		tx_ring->queue_index = i;
 		tx_ring->netdev = adapter->netdev;
 		tx_ring->dev = &adapter->pdev->dev;
-		tx_ring->count = I40EVF_DEFAULT_TXD;
+		tx_ring->count = adapter->tx_desc_count;
 		adapter->tx_rings[i] = tx_ring;
 
 		rx_ring = &tx_ring[1];
 		rx_ring->queue_index = i;
 		rx_ring->netdev = adapter->netdev;
 		rx_ring->dev = &adapter->pdev->dev;
-		rx_ring->count = I40EVF_DEFAULT_RXD;
+		rx_ring->count = adapter->rx_desc_count;
 		adapter->rx_rings[i] = rx_ring;
 	}
 
@@ -1141,9 +1132,6 @@ static int i40evf_set_interrupt_capability(struct i40evf_adapter *adapter)
 	v_budget = min_t(int, pairs, (int)(num_online_cpus() * 2)) + NONQ_VECS;
 	v_budget = min_t(int, v_budget, (int)adapter->vf_res->max_vectors);
 
-	/* A failure in MSI-X entry allocation isn't fatal, but it does
-	 * mean we disable MSI-X capabilities of the adapter.
-	 */
 	adapter->msix_entries = kcalloc(v_budget,
 					sizeof(struct msix_entry), GFP_KERNEL);
 	if (!adapter->msix_entries) {
@@ -1183,7 +1171,7 @@ static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter)
 		q_vector->vsi = &adapter->vsi;
 		q_vector->v_idx = q_idx;
 		netif_napi_add(adapter->netdev, &q_vector->napi,
-				       i40evf_napi_poll, 64);
+				       i40evf_napi_poll, NAPI_POLL_WEIGHT);
 		adapter->q_vector[q_idx] = q_vector;
 	}
 
@@ -1236,8 +1224,6 @@ void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter)
 	pci_disable_msix(adapter->pdev);
 	kfree(adapter->msix_entries);
 	adapter->msix_entries = NULL;
-
-	return;
 }
 
 /**
@@ -1309,7 +1295,6 @@ static void i40evf_watchdog_task(struct work_struct *work)
 		goto restart_watchdog;
 
 	if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) {
-		dev_info(&adapter->pdev->dev, "Checking for redemption\n");
 		if ((rd32(hw, I40E_VFGEN_RSTAT) & 0x3) == I40E_VFR_VFACTIVE) {
 			/* A chance for redemption! */
 			dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n");
@@ -1340,8 +1325,7 @@ static void i40evf_watchdog_task(struct work_struct *work)
 	    (rd32(hw, I40E_VFGEN_RSTAT) & 0x3) != I40E_VFR_VFACTIVE) {
 		adapter->state = __I40EVF_RESETTING;
 		adapter->flags |= I40EVF_FLAG_RESET_PENDING;
-		dev_err(&adapter->pdev->dev, "Hardware reset detected.\n");
-		dev_info(&adapter->pdev->dev, "Scheduling reset task\n");
+		dev_err(&adapter->pdev->dev, "Hardware reset detected\n");
 		schedule_work(&adapter->reset_task);
 		adapter->aq_pending = 0;
 		adapter->aq_required = 0;
@@ -1413,7 +1397,7 @@ restart_watchdog:
 }
 
 /**
- * i40evf_configure_rss - increment to next available tx queue
+ * next_queue - increment to next available tx queue
  * @adapter: board private structure
  * @j: queue counter
  *
@@ -1504,15 +1488,12 @@ static void i40evf_reset_task(struct work_struct *work)
 	for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) {
 		rstat_val = rd32(hw, I40E_VFGEN_RSTAT) &
 			    I40E_VFGEN_RSTAT_VFR_STATE_MASK;
-		if (rstat_val != I40E_VFR_VFACTIVE) {
-			dev_info(&adapter->pdev->dev, "Reset now occurring\n");
+		if (rstat_val != I40E_VFR_VFACTIVE)
 			break;
-		} else {
+		else
 			msleep(I40EVF_RESET_WAIT_MS);
-		}
 	}
 	if (i == I40EVF_RESET_WAIT_COUNT) {
-		dev_err(&adapter->pdev->dev, "Reset was not detected\n");
 		adapter->flags &= ~I40EVF_FLAG_RESET_PENDING;
 		goto continue_reset; /* act like the reset happened */
 	}
@@ -1521,22 +1502,24 @@ static void i40evf_reset_task(struct work_struct *work)
 	for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) {
 		rstat_val = rd32(hw, I40E_VFGEN_RSTAT) &
 			    I40E_VFGEN_RSTAT_VFR_STATE_MASK;
-		if (rstat_val == I40E_VFR_VFACTIVE) {
-			dev_info(&adapter->pdev->dev, "Reset is complete. Reinitializing.\n");
+		if (rstat_val == I40E_VFR_VFACTIVE)
 			break;
-		} else {
+		else
 			msleep(I40EVF_RESET_WAIT_MS);
-		}
 	}
 	if (i == I40EVF_RESET_WAIT_COUNT) {
 		/* reset never finished */
-		dev_err(&adapter->pdev->dev, "Reset never finished (%x). PF driver is dead, and so am I.\n",
+		dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
 			rstat_val);
 		adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
 
-		if (netif_running(adapter->netdev))
-			i40evf_close(adapter->netdev);
-
+		if (netif_running(adapter->netdev)) {
+			set_bit(__I40E_DOWN, &adapter->vsi.state);
+			i40evf_down(adapter);
+			i40evf_free_traffic_irqs(adapter);
+			i40evf_free_all_tx_resources(adapter);
+			i40evf_free_all_rx_resources(adapter);
+		}
 		i40evf_free_misc_irq(adapter);
 		i40evf_reset_interrupt_capability(adapter);
 		i40evf_free_queues(adapter);
@@ -1591,7 +1574,7 @@ continue_reset:
 	}
 	return;
 reset_err:
-	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit.\n");
+	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 	i40evf_close(adapter->netdev);
 }
 
@@ -1607,6 +1590,7 @@ static void i40evf_adminq_task(struct work_struct *work)
 	struct i40e_arq_event_info event;
 	struct i40e_virtchnl_msg *v_msg;
 	i40e_status ret;
+	u32 val, oldval;
 	u16 pending;
 
 	if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED)
@@ -1614,11 +1598,9 @@ static void i40evf_adminq_task(struct work_struct *work)
 
 	event.msg_size = I40EVF_MAX_AQ_BUF_SIZE;
 	event.msg_buf = kzalloc(event.msg_size, GFP_KERNEL);
-	if (!event.msg_buf) {
-		dev_info(&adapter->pdev->dev, "%s: no memory for ARQ clean\n",
-				 __func__);
+	if (!event.msg_buf)
 		return;
-	}
+
 	v_msg = (struct i40e_virtchnl_msg *)&event.desc;
 	do {
 		ret = i40evf_clean_arq_element(hw, &event, &pending);
@@ -1636,6 +1618,41 @@ static void i40evf_adminq_task(struct work_struct *work)
 		}
 	} while (pending);
 
+	/* check for error indications */
+	val = rd32(hw, hw->aq.arq.len);
+	oldval = val;
+	if (val & I40E_VF_ARQLEN_ARQVFE_MASK) {
+		dev_info(&adapter->pdev->dev, "ARQ VF Error detected\n");
+		val &= ~I40E_VF_ARQLEN_ARQVFE_MASK;
+	}
+	if (val & I40E_VF_ARQLEN_ARQOVFL_MASK) {
+		dev_info(&adapter->pdev->dev, "ARQ Overflow Error detected\n");
+		val &= ~I40E_VF_ARQLEN_ARQOVFL_MASK;
+	}
+	if (val & I40E_VF_ARQLEN_ARQCRIT_MASK) {
+		dev_info(&adapter->pdev->dev, "ARQ Critical Error detected\n");
+		val &= ~I40E_VF_ARQLEN_ARQCRIT_MASK;
+	}
+	if (oldval != val)
+		wr32(hw, hw->aq.arq.len, val);
+
+	val = rd32(hw, hw->aq.asq.len);
+	oldval = val;
+	if (val & I40E_VF_ATQLEN_ATQVFE_MASK) {
+		dev_info(&adapter->pdev->dev, "ASQ VF Error detected\n");
+		val &= ~I40E_VF_ATQLEN_ATQVFE_MASK;
+	}
+	if (val & I40E_VF_ATQLEN_ATQOVFL_MASK) {
+		dev_info(&adapter->pdev->dev, "ASQ Overflow Error detected\n");
+		val &= ~I40E_VF_ATQLEN_ATQOVFL_MASK;
+	}
+	if (val & I40E_VF_ATQLEN_ATQCRIT_MASK) {
+		dev_info(&adapter->pdev->dev, "ASQ Critical Error detected\n");
+		val &= ~I40E_VF_ATQLEN_ATQCRIT_MASK;
+	}
+	if (oldval != val)
+		wr32(hw, hw->aq.asq.len, val);
+
 	/* re-enable Admin queue interrupt cause */
 	i40evf_misc_irq_enable(adapter);
 
@@ -1673,6 +1690,7 @@ static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter)
 	int i, err = 0;
 
 	for (i = 0; i < adapter->vsi_res->num_queue_pairs; i++) {
+		adapter->tx_rings[i]->count = adapter->tx_desc_count;
 		err = i40evf_setup_tx_descriptors(adapter->tx_rings[i]);
 		if (!err)
 			continue;
@@ -1700,6 +1718,7 @@ static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter)
 	int i, err = 0;
 
 	for (i = 0; i < adapter->vsi_res->num_queue_pairs; i++) {
+		adapter->rx_rings[i]->count = adapter->rx_desc_count;
 		err = i40evf_setup_rx_descriptors(adapter->rx_rings[i]);
 		if (!err)
 			continue;
@@ -1804,12 +1823,11 @@ static int i40evf_close(struct net_device *netdev)
 	if (adapter->state <= __I40EVF_DOWN)
 		return 0;
 
-	/* signal that we are down to the interrupt handler */
-	adapter->state = __I40EVF_DOWN;
 
 	set_bit(__I40E_DOWN, &adapter->vsi.state);
 
 	i40evf_down(adapter);
+	adapter->state = __I40EVF_DOWN;
 	i40evf_free_traffic_irqs(adapter);
 
 	i40evf_free_all_tx_resources(adapter);
@@ -1848,8 +1866,6 @@ void i40evf_reinit_locked(struct i40evf_adapter *adapter)
 
 	WARN_ON(in_interrupt());
 
-	adapter->state = __I40EVF_RESETTING;
-
 	i40evf_down(adapter);
 
 	/* allocate transmit descriptors */
@@ -1872,7 +1888,7 @@ void i40evf_reinit_locked(struct i40evf_adapter *adapter)
 	return;
 
 err_reinit:
-	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit.\n");
+	dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n");
 	i40evf_close(netdev);
 }
 
@@ -1967,7 +1983,7 @@ static void i40evf_init_task(struct work_struct *work)
 		}
 		err = i40evf_check_reset_complete(hw);
 		if (err) {
-			dev_err(&pdev->dev, "Device is still in reset (%d)\n",
+			dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n",
 				err);
 			goto err;
 		}
@@ -1993,14 +2009,14 @@ static void i40evf_init_task(struct work_struct *work)
 		break;
 	case __I40EVF_INIT_VERSION_CHECK:
 		if (!i40evf_asq_done(hw)) {
-			dev_err(&pdev->dev, "Admin queue command never completed.\n");
+			dev_err(&pdev->dev, "Admin queue command never completed\n");
 			goto err;
 		}
 
 		/* aq msg sent, awaiting reply */
 		err = i40evf_verify_api_ver(adapter);
 		if (err) {
-			dev_err(&pdev->dev, "Unable to verify API version (%d)\n",
+			dev_info(&pdev->dev, "Unable to verify API version (%d), retrying\n",
 				err);
 			goto err;
 		}
@@ -2074,12 +2090,12 @@ static void i40evf_init_task(struct work_struct *work)
 	netdev->hw_features &= ~NETIF_F_RXCSUM;
 
 	if (!is_valid_ether_addr(adapter->hw.mac.addr)) {
-		dev_info(&pdev->dev, "Invalid MAC address %pMAC, using random\n",
+		dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
 			 adapter->hw.mac.addr);
 		random_ether_addr(adapter->hw.mac.addr);
 	}
-	memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len);
-	memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len);
+	ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr);
+	ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr);
 
 	INIT_LIST_HEAD(&adapter->mac_filter_list);
 	INIT_LIST_HEAD(&adapter->vlan_filter_list);
@@ -2087,7 +2103,7 @@ static void i40evf_init_task(struct work_struct *work)
 	if (NULL == f)
 		goto err_sw_init;
 
-	memcpy(f->macaddr, adapter->hw.mac.addr, ETH_ALEN);
+	ether_addr_copy(f->macaddr, adapter->hw.mac.addr);
 	f->add = true;
 	adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER;
 
@@ -2098,6 +2114,8 @@ static void i40evf_init_task(struct work_struct *work)
 	adapter->watchdog_timer.data = (unsigned long)adapter;
 	mod_timer(&adapter->watchdog_timer, jiffies + 1);
 
+	adapter->tx_desc_count = I40EVF_DEFAULT_TXD;
+	adapter->rx_desc_count = I40EVF_DEFAULT_RXD;
 	err = i40evf_init_interrupt_scheme(adapter);
 	if (err)
 		goto err_sw_init;
@@ -2114,8 +2132,10 @@ static void i40evf_init_task(struct work_struct *work)
 	adapter->vsi.back = adapter;
 	adapter->vsi.base_vector = 1;
 	adapter->vsi.work_limit = I40E_DEFAULT_IRQ_WORK;
-	adapter->vsi.rx_itr_setting = I40E_ITR_DYNAMIC;
-	adapter->vsi.tx_itr_setting = I40E_ITR_DYNAMIC;
+	adapter->vsi.rx_itr_setting = (I40E_ITR_DYNAMIC |
+				       ITR_REG_TO_USEC(I40E_ITR_RX_DEF));
+	adapter->vsi.tx_itr_setting = (I40E_ITR_DYNAMIC |
+				       ITR_REG_TO_USEC(I40E_ITR_TX_DEF));
 	adapter->vsi.netdev = adapter->netdev;
 
 	if (!adapter->netdev_registered) {
@@ -2128,7 +2148,7 @@ static void i40evf_init_task(struct work_struct *work)
 
 	netif_tx_stop_all_queues(netdev);
 
-	dev_info(&pdev->dev, "MAC address: %pMAC\n", adapter->hw.mac.addr);
+	dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr);
 	if (netdev->features & NETIF_F_GRO)
 		dev_info(&pdev->dev, "GRO is enabled\n");
 
@@ -2152,12 +2172,11 @@ err_alloc:
 err:
 	/* Things went into the weeds, so try again later */
 	if (++adapter->aq_wait_count > I40EVF_AQ_MAX_ERR) {
-		dev_err(&pdev->dev, "Failed to communicate with PF; giving up.\n");
+		dev_err(&pdev->dev, "Failed to communicate with PF; giving up\n");
 		adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED;
 		return; /* do not reschedule */
 	}
 	schedule_delayed_work(&adapter->init_task, HZ * 3);
-	return;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index e294f012647..2dc0bac7671 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -12,6 +12,9 @@
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
  *
+ * You should have received a copy of the GNU General Public License along
+ * with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
  * The full GNU General Public License is included in this distribution in
  * the file called "COPYING".
  *
@@ -216,11 +219,9 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
 	len = sizeof(struct i40e_virtchnl_vsi_queue_config_info) +
 		       (sizeof(struct i40e_virtchnl_queue_pair_info) * pairs);
 	vqci = kzalloc(len, GFP_ATOMIC);
-	if (!vqci) {
-		dev_err(&adapter->pdev->dev, "%s: unable to allocate memory\n",
-			__func__);
+	if (!vqci)
 		return;
-	}
+
 	vqci->vsi_id = adapter->vsi_res->vsi_id;
 	vqci->num_queue_pairs = pairs;
 	vqpi = vqci->qpair;
@@ -232,6 +233,9 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter)
 		vqpi->txq.queue_id = i;
 		vqpi->txq.ring_len = adapter->tx_rings[i]->count;
 		vqpi->txq.dma_ring_addr = adapter->tx_rings[i]->dma;
+		vqpi->txq.headwb_enabled = 1;
+		vqpi->txq.dma_headwb_addr = vqpi->txq.dma_ring_addr +
+		    (vqpi->txq.ring_len * sizeof(struct i40e_tx_desc));
 
 		vqpi->rxq.vsi_id = vqci->vsi_id;
 		vqpi->rxq.queue_id = i;
@@ -329,11 +333,8 @@ void i40evf_map_queues(struct i40evf_adapter *adapter)
 	      (adapter->num_msix_vectors *
 		sizeof(struct i40e_virtchnl_vector_map));
 	vimi = kzalloc(len, GFP_ATOMIC);
-	if (!vimi) {
-		dev_err(&adapter->pdev->dev, "%s: unable to allocate memory\n",
-			__func__);
+	if (!vimi)
 		return;
-	}
 
 	vimi->num_vectors = adapter->num_msix_vectors;
 	/* Queue vectors first */
@@ -390,7 +391,7 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
 	len = sizeof(struct i40e_virtchnl_ether_addr_list) +
 	      (count * sizeof(struct i40e_virtchnl_ether_addr));
 	if (len > I40EVF_MAX_AQ_BUF_SIZE) {
-		dev_warn(&adapter->pdev->dev, "%s: Too many MAC address changes in one request.\n",
+		dev_warn(&adapter->pdev->dev, "%s: Too many MAC address changes in one request\n",
 			__func__);
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_ether_addr_list)) /
@@ -399,16 +400,14 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter)
 	}
 
 	veal = kzalloc(len, GFP_ATOMIC);
-	if (!veal) {
-		dev_err(&adapter->pdev->dev, "%s: unable to allocate memory\n",
-			__func__);
+	if (!veal)
 		return;
-	}
+
 	veal->vsi_id = adapter->vsi_res->vsi_id;
 	veal->num_elements = count;
 	list_for_each_entry(f, &adapter->mac_filter_list, list) {
 		if (f->add) {
-			memcpy(veal->list[i].addr, f->macaddr, ETH_ALEN);
+			ether_addr_copy(veal->list[i].addr, f->macaddr);
 			i++;
 			f->add = false;
 		}
@@ -454,7 +453,7 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
 	len = sizeof(struct i40e_virtchnl_ether_addr_list) +
 	      (count * sizeof(struct i40e_virtchnl_ether_addr));
 	if (len > I40EVF_MAX_AQ_BUF_SIZE) {
-		dev_warn(&adapter->pdev->dev, "%s: Too many MAC address changes in one request.\n",
+		dev_warn(&adapter->pdev->dev, "%s: Too many MAC address changes in one request\n",
 			__func__);
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_ether_addr_list)) /
@@ -462,16 +461,14 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter)
 		len = I40EVF_MAX_AQ_BUF_SIZE;
 	}
 	veal = kzalloc(len, GFP_ATOMIC);
-	if (!veal) {
-		dev_err(&adapter->pdev->dev, "%s: unable to allocate memory\n",
-			__func__);
+	if (!veal)
 		return;
-	}
+
 	veal->vsi_id = adapter->vsi_res->vsi_id;
 	veal->num_elements = count;
 	list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) {
 		if (f->remove) {
-			memcpy(veal->list[i].addr, f->macaddr, ETH_ALEN);
+			ether_addr_copy(veal->list[i].addr, f->macaddr);
 			i++;
 			list_del(&f->list);
 			kfree(f);
@@ -518,7 +515,7 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter)
 	len = sizeof(struct i40e_virtchnl_vlan_filter_list) +
 	      (count * sizeof(u16));
 	if (len > I40EVF_MAX_AQ_BUF_SIZE) {
-		dev_warn(&adapter->pdev->dev, "%s: Too many VLAN changes in one request.\n",
+		dev_warn(&adapter->pdev->dev, "%s: Too many VLAN changes in one request\n",
 			__func__);
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_vlan_filter_list)) /
@@ -526,11 +523,9 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter)
 		len = I40EVF_MAX_AQ_BUF_SIZE;
 	}
 	vvfl = kzalloc(len, GFP_ATOMIC);
-	if (!vvfl) {
-		dev_err(&adapter->pdev->dev, "%s: unable to allocate memory\n",
-			__func__);
+	if (!vvfl)
 		return;
-	}
+
 	vvfl->vsi_id = adapter->vsi_res->vsi_id;
 	vvfl->num_elements = count;
 	list_for_each_entry(f, &adapter->vlan_filter_list, list) {
@@ -580,7 +575,7 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter)
 	len = sizeof(struct i40e_virtchnl_vlan_filter_list) +
 	      (count * sizeof(u16));
 	if (len > I40EVF_MAX_AQ_BUF_SIZE) {
-		dev_warn(&adapter->pdev->dev, "%s: Too many VLAN changes in one request.\n",
+		dev_warn(&adapter->pdev->dev, "%s: Too many VLAN changes in one request\n",
 			__func__);
 		count = (I40EVF_MAX_AQ_BUF_SIZE -
 			 sizeof(struct i40e_virtchnl_vlan_filter_list)) /
@@ -588,11 +583,9 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter)
 		len = I40EVF_MAX_AQ_BUF_SIZE;
 	}
 	vvfl = kzalloc(len, GFP_ATOMIC);
-	if (!vvfl) {
-		dev_err(&adapter->pdev->dev, "%s: unable to allocate memory\n",
-			__func__);
+	if (!vvfl)
 		return;
-	}
+
 	vvfl->vsi_id = adapter->vsi_res->vsi_id;
 	vvfl->num_elements = count;
 	list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) {
@@ -721,7 +714,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		return;
 	}
 	if (v_opcode != adapter->current_op) {
-		dev_err(&adapter->pdev->dev, "%s: Pending op is %d, received %d.\n",
+		dev_err(&adapter->pdev->dev, "%s: Pending op is %d, received %d\n",
 			__func__, adapter->current_op, v_opcode);
 		/* We're probably completely screwed at this point, but clear
 		 * the current op and try to carry on....
@@ -730,7 +723,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		return;
 	}
 	if (v_retval) {
-		dev_err(&adapter->pdev->dev, "%s: PF returned error %d to our request %d!\n",
+		dev_err(&adapter->pdev->dev, "%s: PF returned error %d to our request %d\n",
 			__func__, v_retval, v_opcode);
 	}
 	switch (v_opcode) {
@@ -745,9 +738,8 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 						 stats->tx_broadcast;
 		adapter->net_stats.rx_bytes = stats->rx_bytes;
 		adapter->net_stats.tx_bytes = stats->tx_bytes;
-		adapter->net_stats.rx_errors = stats->rx_errors;
 		adapter->net_stats.tx_errors = stats->tx_errors;
-		adapter->net_stats.rx_dropped = stats->rx_missed;
+		adapter->net_stats.rx_dropped = stats->rx_discards;
 		adapter->net_stats.tx_dropped = stats->tx_discards;
 		adapter->current_stats = *stats;
 		}
@@ -781,7 +773,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 		adapter->aq_pending &= ~(I40EVF_FLAG_AQ_MAP_VECTORS);
 		break;
 	default:
-		dev_warn(&adapter->pdev->dev, "%s: Received unexpected message %d from PF.\n",
+		dev_warn(&adapter->pdev->dev, "%s: Received unexpected message %d from PF\n",
 			__func__, v_opcode);
 		break;
 	} /* switch v_opcode */
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index fa36fe12e77..ee74f9536b3 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 /* e1000_82575
  * e1000_82576
@@ -73,9 +70,8 @@ static s32  igb_validate_nvm_checksum_82580(struct e1000_hw *hw);
 static s32  igb_update_nvm_checksum_82580(struct e1000_hw *hw);
 static s32 igb_validate_nvm_checksum_i350(struct e1000_hw *hw);
 static s32 igb_update_nvm_checksum_i350(struct e1000_hw *hw);
-static const u16 e1000_82580_rxpbs_table[] =
-	{ 36, 72, 144, 1, 2, 4, 8, 16,
-	  35, 70, 140 };
+static const u16 e1000_82580_rxpbs_table[] = {
+	36, 72, 144, 1, 2, 4, 8, 16, 35, 70, 140 };
 
 /**
  *  igb_sgmii_uses_mdio_82575 - Determine if I2C pins are for external MDIO
@@ -159,7 +155,7 @@ static s32 igb_check_for_link_media_swap(struct e1000_hw *hw)
 		ret_val = igb_check_for_link_82575(hw);
 	}
 
-	return E1000_SUCCESS;
+	return 0;
 }
 
 /**
@@ -526,7 +522,7 @@ out:
 static s32 igb_get_invariants_82575(struct e1000_hw *hw)
 {
 	struct e1000_mac_info *mac = &hw->mac;
-	struct e1000_dev_spec_82575 * dev_spec = &hw->dev_spec._82575;
+	struct e1000_dev_spec_82575 *dev_spec = &hw->dev_spec._82575;
 	s32 ret_val;
 	u32 ctrl_ext = 0;
 	u32 link_mode = 0;
@@ -1008,7 +1004,6 @@ out:
 static s32 igb_set_d0_lplu_state_82580(struct e1000_hw *hw, bool active)
 {
 	struct e1000_phy_info *phy = &hw->phy;
-	s32 ret_val = 0;
 	u16 data;
 
 	data = rd32(E1000_82580_PHY_POWER_MGMT);
@@ -1032,7 +1027,7 @@ static s32 igb_set_d0_lplu_state_82580(struct e1000_hw *hw, bool active)
 			data &= ~E1000_82580_PM_SPD; }
 
 	wr32(E1000_82580_PHY_POWER_MGMT, data);
-	return ret_val;
+	return 0;
 }
 
 /**
@@ -1052,7 +1047,6 @@ static s32 igb_set_d0_lplu_state_82580(struct e1000_hw *hw, bool active)
 static s32 igb_set_d3_lplu_state_82580(struct e1000_hw *hw, bool active)
 {
 	struct e1000_phy_info *phy = &hw->phy;
-	s32 ret_val = 0;
 	u16 data;
 
 	data = rd32(E1000_82580_PHY_POWER_MGMT);
@@ -1077,7 +1071,7 @@ static s32 igb_set_d3_lplu_state_82580(struct e1000_hw *hw, bool active)
 	}
 
 	wr32(E1000_82580_PHY_POWER_MGMT, data);
-	return ret_val;
+	return 0;
 }
 
 /**
@@ -1180,8 +1174,8 @@ static void igb_release_swfw_sync_82575(struct e1000_hw *hw, u16 mask)
 {
 	u32 swfw_sync;
 
-	while (igb_get_hw_semaphore(hw) != 0);
-	/* Empty */
+	while (igb_get_hw_semaphore(hw) != 0)
+		; /* Empty */
 
 	swfw_sync = rd32(E1000_SW_FW_SYNC);
 	swfw_sync &= ~mask;
@@ -1203,7 +1197,6 @@ static void igb_release_swfw_sync_82575(struct e1000_hw *hw, u16 mask)
 static s32 igb_get_cfg_done_82575(struct e1000_hw *hw)
 {
 	s32 timeout = PHY_CFG_TIMEOUT;
-	s32 ret_val = 0;
 	u32 mask = E1000_NVM_CFG_DONE_PORT_0;
 
 	if (hw->bus.func == 1)
@@ -1216,7 +1209,7 @@ static s32 igb_get_cfg_done_82575(struct e1000_hw *hw)
 	while (timeout) {
 		if (rd32(E1000_EEMNGCTL) & mask)
 			break;
-		msleep(1);
+		usleep_range(1000, 2000);
 		timeout--;
 	}
 	if (!timeout)
@@ -1227,7 +1220,7 @@ static s32 igb_get_cfg_done_82575(struct e1000_hw *hw)
 	    (hw->phy.type == e1000_phy_igp_3))
 		igb_phy_init_script_igp3(hw);
 
-	return ret_val;
+	return 0;
 }
 
 /**
@@ -1269,7 +1262,7 @@ static s32 igb_check_for_link_82575(struct e1000_hw *hw)
 
 	if (hw->phy.media_type != e1000_media_type_copper) {
 		ret_val = igb_get_pcs_speed_and_duplex_82575(hw, &speed,
-		                                             &duplex);
+							     &duplex);
 		/* Use this flag to determine if link needs to be checked or
 		 * not.  If  we have link clear the flag so that we do not
 		 * continue to check for link.
@@ -1316,7 +1309,7 @@ void igb_power_up_serdes_link_82575(struct e1000_hw *hw)
 
 	/* flush the write to verify completion */
 	wrfl();
-	msleep(1);
+	usleep_range(1000, 2000);
 }
 
 /**
@@ -1411,7 +1404,7 @@ void igb_shutdown_serdes_link_82575(struct e1000_hw *hw)
 
 		/* flush the write to verify completion */
 		wrfl();
-		msleep(1);
+		usleep_range(1000, 2000);
 	}
 }
 
@@ -1436,9 +1429,8 @@ static s32 igb_reset_hw_82575(struct e1000_hw *hw)
 
 	/* set the completion timeout for interface */
 	ret_val = igb_set_pcie_completion_timeout(hw);
-	if (ret_val) {
+	if (ret_val)
 		hw_dbg("PCI-E Set completion timeout has failed.\n");
-	}
 
 	hw_dbg("Masking off all interrupts\n");
 	wr32(E1000_IMC, 0xffffffff);
@@ -1447,7 +1439,7 @@ static s32 igb_reset_hw_82575(struct e1000_hw *hw)
 	wr32(E1000_TCTL, E1000_TCTL_PSP);
 	wrfl();
 
-	msleep(10);
+	usleep_range(10000, 20000);
 
 	ctrl = rd32(E1000_CTRL);
 
@@ -1489,6 +1481,13 @@ static s32 igb_init_hw_82575(struct e1000_hw *hw)
 	s32 ret_val;
 	u16 i, rar_count = mac->rar_entry_count;
 
+	if ((hw->mac.type >= e1000_i210) &&
+	    !(igb_get_flash_presence_i210(hw))) {
+		ret_val = igb_pll_workaround_i210(hw);
+		if (ret_val)
+			return ret_val;
+	}
+
 	/* Initialize identification LED */
 	ret_val = igb_id_led_init(hw);
 	if (ret_val) {
@@ -1622,7 +1621,7 @@ static s32 igb_setup_serdes_link_82575(struct e1000_hw *hw)
 {
 	u32 ctrl_ext, ctrl_reg, reg, anadv_reg;
 	bool pcs_autoneg;
-	s32 ret_val = E1000_SUCCESS;
+	s32 ret_val = 0;
 	u16 data;
 
 	if ((hw->phy.media_type != e1000_media_type_internal_serdes) &&
@@ -1676,7 +1675,7 @@ static s32 igb_setup_serdes_link_82575(struct e1000_hw *hw)
 		    hw->mac.type == e1000_82576) {
 			ret_val = hw->nvm.ops.read(hw, NVM_COMPAT, 1, &data);
 			if (ret_val) {
-				printk(KERN_DEBUG "NVM Read Error\n\n");
+				hw_dbg(KERN_DEBUG "NVM Read Error\n\n");
 				return ret_val;
 			}
 
@@ -1689,7 +1688,7 @@ static s32 igb_setup_serdes_link_82575(struct e1000_hw *hw)
 		 * link either autoneg or be forced to 1000/Full
 		 */
 		ctrl_reg |= E1000_CTRL_SPD_1000 | E1000_CTRL_FRCSPD |
-		            E1000_CTRL_FD | E1000_CTRL_FRCDPX;
+				E1000_CTRL_FD | E1000_CTRL_FRCDPX;
 
 		/* set speed of 1000/Full if speed/duplex is forced */
 		reg |= E1000_PCS_LCTL_FSV_1000 | E1000_PCS_LCTL_FDV_FULL;
@@ -1925,7 +1924,7 @@ void igb_rx_fifo_flush_82575(struct e1000_hw *hw)
 	}
 	/* Poll all queues to verify they have shut down */
 	for (ms_wait = 0; ms_wait < 10; ms_wait++) {
-		msleep(1);
+		usleep_range(1000, 2000);
 		rx_enabled = 0;
 		for (i = 0; i < 4; i++)
 			rx_enabled |= rd32(E1000_RXDCTL(i));
@@ -1953,7 +1952,7 @@ void igb_rx_fifo_flush_82575(struct e1000_hw *hw)
 	wr32(E1000_RCTL, temp_rctl);
 	wr32(E1000_RCTL, temp_rctl | E1000_RCTL_EN);
 	wrfl();
-	msleep(2);
+	usleep_range(2000, 3000);
 
 	/* Enable RX queues that were previously enabled and restore our
 	 * previous state
@@ -2005,14 +2004,14 @@ static s32 igb_set_pcie_completion_timeout(struct e1000_hw *hw)
 	 * 16ms to 55ms
 	 */
 	ret_val = igb_read_pcie_cap_reg(hw, PCIE_DEVICE_CONTROL2,
-	                                &pcie_devctl2);
+					&pcie_devctl2);
 	if (ret_val)
 		goto out;
 
 	pcie_devctl2 |= PCIE_DEVICE_CONTROL2_16ms;
 
 	ret_val = igb_write_pcie_cap_reg(hw, PCIE_DEVICE_CONTROL2,
-	                                 &pcie_devctl2);
+					 &pcie_devctl2);
 out:
 	/* disable completion timeout resend */
 	gcr &= ~E1000_GCR_CMPL_TMOUT_RESEND;
@@ -2241,7 +2240,7 @@ static s32 igb_reset_hw_82580(struct e1000_hw *hw)
 	wr32(E1000_TCTL, E1000_TCTL_PSP);
 	wrfl();
 
-	msleep(10);
+	usleep_range(10000, 11000);
 
 	/* Determine whether or not a global dev reset is requested */
 	if (global_device_reset &&
@@ -2259,7 +2258,7 @@ static s32 igb_reset_hw_82580(struct e1000_hw *hw)
 
 	/* Add delay to insure DEV_RST has time to complete */
 	if (global_device_reset)
-		msleep(5);
+		usleep_range(5000, 6000);
 
 	ret_val = igb_get_auto_rd_done(hw);
 	if (ret_val) {
@@ -2436,8 +2435,7 @@ static s32 igb_update_nvm_checksum_82580(struct e1000_hw *hw)
 
 	ret_val = hw->nvm.ops.read(hw, NVM_COMPATIBILITY_REG_3, 1, &nvm_data);
 	if (ret_val) {
-		hw_dbg("NVM Read Error while updating checksum"
-			" compatibility bit.\n");
+		hw_dbg("NVM Read Error while updating checksum compatibility bit.\n");
 		goto out;
 	}
 
@@ -2447,8 +2445,7 @@ static s32 igb_update_nvm_checksum_82580(struct e1000_hw *hw)
 		ret_val = hw->nvm.ops.write(hw, NVM_COMPATIBILITY_REG_3, 1,
 					&nvm_data);
 		if (ret_val) {
-			hw_dbg("NVM Write Error while updating checksum"
-				" compatibility bit.\n");
+			hw_dbg("NVM Write Error while updating checksum compatibility bit.\n");
 			goto out;
 		}
 	}
@@ -2525,7 +2522,7 @@ out:
 static s32 __igb_access_emi_reg(struct e1000_hw *hw, u16 address,
 				  u16 *data, bool read)
 {
-	s32 ret_val = E1000_SUCCESS;
+	s32 ret_val = 0;
 
 	ret_val = hw->phy.ops.write_reg(hw, E1000_EMIADD, address);
 	if (ret_val)
@@ -2559,7 +2556,6 @@ s32 igb_read_emi_reg(struct e1000_hw *hw, u16 addr, u16 *data)
  **/
 s32 igb_set_eee_i350(struct e1000_hw *hw)
 {
-	s32 ret_val = 0;
 	u32 ipcnfg, eeer;
 
 	if ((hw->mac.type < e1000_i350) ||
@@ -2593,7 +2589,7 @@ s32 igb_set_eee_i350(struct e1000_hw *hw)
 	rd32(E1000_EEER);
 out:
 
-	return ret_val;
+	return 0;
 }
 
 /**
@@ -2720,7 +2716,6 @@ static const u8 e1000_emc_therm_limit[4] = {
  **/
 static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw)
 {
-	s32 status = E1000_SUCCESS;
 	u16 ets_offset;
 	u16 ets_cfg;
 	u16 ets_sensor;
@@ -2738,7 +2733,7 @@ static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw)
 	/* Return the internal sensor only if ETS is unsupported */
 	hw->nvm.ops.read(hw, NVM_ETS_CFG, 1, &ets_offset);
 	if ((ets_offset == 0x0000) || (ets_offset == 0xFFFF))
-		return status;
+		return 0;
 
 	hw->nvm.ops.read(hw, ets_offset, 1, &ets_cfg);
 	if (((ets_cfg & NVM_ETS_TYPE_MASK) >> NVM_ETS_TYPE_SHIFT)
@@ -2762,7 +2757,7 @@ static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw)
 					E1000_I2C_THERMAL_SENSOR_ADDR,
 					&data->sensor[i].temp);
 	}
-	return status;
+	return 0;
 }
 
 /**
@@ -2774,7 +2769,6 @@ static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw)
  **/
 static s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw)
 {
-	s32 status = E1000_SUCCESS;
 	u16 ets_offset;
 	u16 ets_cfg;
 	u16 ets_sensor;
@@ -2800,7 +2794,7 @@ static s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw)
 	/* Return the internal sensor only if ETS is unsupported */
 	hw->nvm.ops.read(hw, NVM_ETS_CFG, 1, &ets_offset);
 	if ((ets_offset == 0x0000) || (ets_offset == 0xFFFF))
-		return status;
+		return 0;
 
 	hw->nvm.ops.read(hw, ets_offset, 1, &ets_cfg);
 	if (((ets_cfg & NVM_ETS_TYPE_MASK) >> NVM_ETS_TYPE_SHIFT)
@@ -2831,7 +2825,7 @@ static s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw)
 							low_thresh_delta;
 		}
 	}
-	return status;
+	return 0;
 }
 
 #endif
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.h b/drivers/net/ethernet/intel/igb/e1000_82575.h
index 09d78be7241..b407c55738f 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.h
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.h
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #ifndef _E1000_82575_H_
 #define _E1000_82575_H_
@@ -37,9 +34,9 @@ s32 igb_write_i2c_byte(struct e1000_hw *hw, u8 byte_offset, u8 dev_addr,
 		       u8 data);
 
 #define ID_LED_DEFAULT_82575_SERDES ((ID_LED_DEF1_DEF2 << 12) | \
-                                     (ID_LED_DEF1_DEF2 <<  8) | \
-                                     (ID_LED_DEF1_DEF2 <<  4) | \
-                                     (ID_LED_OFF1_ON2))
+				     (ID_LED_DEF1_DEF2 <<  8) | \
+				     (ID_LED_DEF1_DEF2 <<  4) | \
+				     (ID_LED_OFF1_ON2))
 
 #define E1000_RAR_ENTRIES_82575        16
 #define E1000_RAR_ENTRIES_82576        24
@@ -67,16 +64,16 @@ s32 igb_write_i2c_byte(struct e1000_hw *hw, u8 byte_offset, u8 dev_addr,
 #define E1000_MRQC_RSS_FIELD_IPV6_UDP_EX    0x01000000
 
 #define E1000_EICR_TX_QUEUE ( \
-    E1000_EICR_TX_QUEUE0 |    \
-    E1000_EICR_TX_QUEUE1 |    \
-    E1000_EICR_TX_QUEUE2 |    \
-    E1000_EICR_TX_QUEUE3)
+	E1000_EICR_TX_QUEUE0 |    \
+	E1000_EICR_TX_QUEUE1 |    \
+	E1000_EICR_TX_QUEUE2 |    \
+	E1000_EICR_TX_QUEUE3)
 
 #define E1000_EICR_RX_QUEUE ( \
-    E1000_EICR_RX_QUEUE0 |    \
-    E1000_EICR_RX_QUEUE1 |    \
-    E1000_EICR_RX_QUEUE2 |    \
-    E1000_EICR_RX_QUEUE3)
+	E1000_EICR_RX_QUEUE0 |    \
+	E1000_EICR_RX_QUEUE1 |    \
+	E1000_EICR_RX_QUEUE2 |    \
+	E1000_EICR_RX_QUEUE3)
 
 /* Immediate Interrupt Rx (A.K.A. Low Latency Interrupt) */
 #define E1000_IMIREXT_SIZE_BP     0x00001000  /* Packet size bypass */
@@ -92,8 +89,7 @@ union e1000_adv_rx_desc {
 		struct {
 			struct {
 				__le16 pkt_info;   /* RSS type, Packet type */
-				__le16 hdr_info;   /* Split Header,
-						    * header buffer length */
+				__le16 hdr_info;   /* Split Head, buf len */
 			} lo_dword;
 			union {
 				__le32 rss;          /* RSS Hash */
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index b05bf925ac7..217f8138851 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #ifndef _E1000_DEFINES_H_
 #define _E1000_DEFINES_H_
@@ -49,14 +46,15 @@
 #define E1000_CTRL_EXT_SDP3_DIR  0x00000800 /* SDP3 Data direction */
 
 /* Physical Func Reset Done Indication */
-#define E1000_CTRL_EXT_PFRSTD    0x00004000
-#define E1000_CTRL_EXT_LINK_MODE_MASK 0x00C00000
-#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES  0x00C00000
-#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX  0x00400000
-#define E1000_CTRL_EXT_LINK_MODE_SGMII   0x00800000
-#define E1000_CTRL_EXT_LINK_MODE_GMII   0x00000000
-#define E1000_CTRL_EXT_EIAME          0x01000000
-#define E1000_CTRL_EXT_IRCA           0x00000001
+#define E1000_CTRL_EXT_PFRSTD	0x00004000
+#define E1000_CTRL_EXT_SDLPE	0X00040000  /* SerDes Low Power Enable */
+#define E1000_CTRL_EXT_LINK_MODE_MASK	0x00C00000
+#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES	0x00C00000
+#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX	0x00400000
+#define E1000_CTRL_EXT_LINK_MODE_SGMII	0x00800000
+#define E1000_CTRL_EXT_LINK_MODE_GMII	0x00000000
+#define E1000_CTRL_EXT_EIAME	0x01000000
+#define E1000_CTRL_EXT_IRCA		0x00000001
 /* Interrupt delay cancellation */
 /* Driver loaded bit for FW */
 #define E1000_CTRL_EXT_DRV_LOAD       0x10000000
@@ -65,6 +63,7 @@
 /* packet buffer parity error detection enabled */
 /* descriptor FIFO parity error detection enable */
 #define E1000_CTRL_EXT_PBA_CLR		0x80000000 /* PBA Clear */
+#define E1000_CTRL_EXT_PHYPDEN		0x00100000
 #define E1000_I2CCMD_REG_ADDR_SHIFT	16
 #define E1000_I2CCMD_PHY_ADDR_SHIFT	24
 #define E1000_I2CCMD_OPCODE_READ	0x08000000
@@ -101,11 +100,11 @@
 
 /* Same mask, but for extended and packet split descriptors */
 #define E1000_RXDEXT_ERR_FRAME_ERR_MASK ( \
-    E1000_RXDEXT_STATERR_CE  |            \
-    E1000_RXDEXT_STATERR_SE  |            \
-    E1000_RXDEXT_STATERR_SEQ |            \
-    E1000_RXDEXT_STATERR_CXE |            \
-    E1000_RXDEXT_STATERR_RXE)
+	E1000_RXDEXT_STATERR_CE  |            \
+	E1000_RXDEXT_STATERR_SE  |            \
+	E1000_RXDEXT_STATERR_SEQ |            \
+	E1000_RXDEXT_STATERR_CXE |            \
+	E1000_RXDEXT_STATERR_RXE)
 
 #define E1000_MRQC_RSS_FIELD_IPV4_TCP          0x00010000
 #define E1000_MRQC_RSS_FIELD_IPV4              0x00020000
@@ -307,39 +306,34 @@
 #define E1000_TCTL_RTLC   0x01000000    /* Re-transmit on late collision */
 
 /* DMA Coalescing register fields */
-#define E1000_DMACR_DMACWT_MASK         0x00003FFF /* DMA Coalescing
-							* Watchdog Timer */
-#define E1000_DMACR_DMACTHR_MASK        0x00FF0000 /* DMA Coalescing Receive
-							* Threshold */
+#define E1000_DMACR_DMACWT_MASK         0x00003FFF /* DMA Coal Watchdog Timer */
+#define E1000_DMACR_DMACTHR_MASK        0x00FF0000 /* DMA Coal Rx Threshold */
 #define E1000_DMACR_DMACTHR_SHIFT       16
-#define E1000_DMACR_DMAC_LX_MASK        0x30000000 /* Lx when no PCIe
-							* transactions */
+#define E1000_DMACR_DMAC_LX_MASK        0x30000000 /* Lx when no PCIe trans */
 #define E1000_DMACR_DMAC_LX_SHIFT       28
 #define E1000_DMACR_DMAC_EN             0x80000000 /* Enable DMA Coalescing */
 /* DMA Coalescing BMC-to-OS Watchdog Enable */
 #define E1000_DMACR_DC_BMC2OSW_EN	0x00008000
 
-#define E1000_DMCTXTH_DMCTTHR_MASK      0x00000FFF /* DMA Coalescing Transmit
-							* Threshold */
+#define E1000_DMCTXTH_DMCTTHR_MASK      0x00000FFF /* DMA Coal Tx Threshold */
 
 #define E1000_DMCTLX_TTLX_MASK          0x00000FFF /* Time to LX request */
 
-#define E1000_DMCRTRH_UTRESH_MASK       0x0007FFFF /* Receive Traffic Rate
-							* Threshold */
-#define E1000_DMCRTRH_LRPRCW            0x80000000 /* Rcv packet rate in
-							* current window */
+#define E1000_DMCRTRH_UTRESH_MASK       0x0007FFFF /* Rx Traffic Rate Thresh */
+#define E1000_DMCRTRH_LRPRCW            0x80000000 /* Rx pkt rate curr window */
 
-#define E1000_DMCCNT_CCOUNT_MASK        0x01FFFFFF /* DMA Coal Rcv Traffic
-							* Current Cnt */
+#define E1000_DMCCNT_CCOUNT_MASK        0x01FFFFFF /* DMA Coal Rx Current Cnt */
 
-#define E1000_FCRTC_RTH_COAL_MASK       0x0003FFF0 /* Flow ctrl Rcv Threshold
-							* High val */
+#define E1000_FCRTC_RTH_COAL_MASK       0x0003FFF0 /* FC Rx Thresh High val */
 #define E1000_FCRTC_RTH_COAL_SHIFT      4
 #define E1000_PCIEMISC_LX_DECISION      0x00000080 /* Lx power decision */
 
 /* Timestamp in Rx buffer */
 #define E1000_RXPBS_CFG_TS_EN           0x80000000
 
+#define I210_RXPBSIZE_DEFAULT		0x000000A2 /* RXPBSIZE default */
+#define I210_TXPBSIZE_DEFAULT		0x04000014 /* TXPBSIZE default */
+
 /* SerDes Control */
 #define E1000_SCTL_DISABLE_SERDES_LOOPBACK 0x0400
 
@@ -406,12 +400,12 @@
  *   o LSC    = Link Status Change
  */
 #define IMS_ENABLE_MASK ( \
-    E1000_IMS_RXT0   |    \
-    E1000_IMS_TXDW   |    \
-    E1000_IMS_RXDMT0 |    \
-    E1000_IMS_RXSEQ  |    \
-    E1000_IMS_LSC    |    \
-    E1000_IMS_DOUTSYNC)
+	E1000_IMS_RXT0   |    \
+	E1000_IMS_TXDW   |    \
+	E1000_IMS_RXDMT0 |    \
+	E1000_IMS_RXSEQ  |    \
+	E1000_IMS_LSC    |    \
+	E1000_IMS_DOUTSYNC)
 
 /* Interrupt Mask Set */
 #define E1000_IMS_TXDW      E1000_ICR_TXDW      /* Transmit desc written back */
@@ -467,7 +461,6 @@
 #define E1000_RAH_POOL_1 0x00040000
 
 /* Error Codes */
-#define E1000_SUCCESS      0
 #define E1000_ERR_NVM      1
 #define E1000_ERR_PHY      2
 #define E1000_ERR_CONFIG   3
@@ -1011,8 +1004,7 @@
 #define E1000_VFTA_ENTRY_BIT_SHIFT_MASK      0x1F
 
 /* DMA Coalescing register fields */
-#define E1000_PCIEMISC_LX_DECISION      0x00000080 /* Lx power decision based
-                                                      on DMA coal */
+#define E1000_PCIEMISC_LX_DECISION      0x00000080 /* Lx power on DMA coal */
 
 /* Tx Rate-Scheduler Config fields */
 #define E1000_RTTBCNRC_RS_ENA		0x80000000
diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h
index 10741d170f2..ce55ea5d750 100644
--- a/drivers/net/ethernet/intel/igb/e1000_hw.h
+++ b/drivers/net/ethernet/intel/igb/e1000_hw.h
@@ -1,28 +1,24 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #ifndef _E1000_HW_H_
 #define _E1000_HW_H_
@@ -320,15 +316,15 @@ struct e1000_host_mng_command_info {
 #include "e1000_mbx.h"
 
 struct e1000_mac_operations {
-	s32  (*check_for_link)(struct e1000_hw *);
-	s32  (*reset_hw)(struct e1000_hw *);
-	s32  (*init_hw)(struct e1000_hw *);
+	s32 (*check_for_link)(struct e1000_hw *);
+	s32 (*reset_hw)(struct e1000_hw *);
+	s32 (*init_hw)(struct e1000_hw *);
 	bool (*check_mng_mode)(struct e1000_hw *);
-	s32  (*setup_physical_interface)(struct e1000_hw *);
+	s32 (*setup_physical_interface)(struct e1000_hw *);
 	void (*rar_set)(struct e1000_hw *, u8 *, u32);
-	s32  (*read_mac_addr)(struct e1000_hw *);
-	s32  (*get_speed_and_duplex)(struct e1000_hw *, u16 *, u16 *);
-	s32  (*acquire_swfw_sync)(struct e1000_hw *, u16);
+	s32 (*read_mac_addr)(struct e1000_hw *);
+	s32 (*get_speed_and_duplex)(struct e1000_hw *, u16 *, u16 *);
+	s32 (*acquire_swfw_sync)(struct e1000_hw *, u16);
 	void (*release_swfw_sync)(struct e1000_hw *, u16);
 #ifdef CONFIG_IGB_HWMON
 	s32 (*get_thermal_sensor_data)(struct e1000_hw *);
@@ -338,31 +334,31 @@ struct e1000_mac_operations {
 };
 
 struct e1000_phy_operations {
-	s32  (*acquire)(struct e1000_hw *);
-	s32  (*check_polarity)(struct e1000_hw *);
-	s32  (*check_reset_block)(struct e1000_hw *);
-	s32  (*force_speed_duplex)(struct e1000_hw *);
-	s32  (*get_cfg_done)(struct e1000_hw *hw);
-	s32  (*get_cable_length)(struct e1000_hw *);
-	s32  (*get_phy_info)(struct e1000_hw *);
-	s32  (*read_reg)(struct e1000_hw *, u32, u16 *);
+	s32 (*acquire)(struct e1000_hw *);
+	s32 (*check_polarity)(struct e1000_hw *);
+	s32 (*check_reset_block)(struct e1000_hw *);
+	s32 (*force_speed_duplex)(struct e1000_hw *);
+	s32 (*get_cfg_done)(struct e1000_hw *hw);
+	s32 (*get_cable_length)(struct e1000_hw *);
+	s32 (*get_phy_info)(struct e1000_hw *);
+	s32 (*read_reg)(struct e1000_hw *, u32, u16 *);
 	void (*release)(struct e1000_hw *);
-	s32  (*reset)(struct e1000_hw *);
-	s32  (*set_d0_lplu_state)(struct e1000_hw *, bool);
-	s32  (*set_d3_lplu_state)(struct e1000_hw *, bool);
-	s32  (*write_reg)(struct e1000_hw *, u32, u16);
+	s32 (*reset)(struct e1000_hw *);
+	s32 (*set_d0_lplu_state)(struct e1000_hw *, bool);
+	s32 (*set_d3_lplu_state)(struct e1000_hw *, bool);
+	s32 (*write_reg)(struct e1000_hw *, u32, u16);
 	s32 (*read_i2c_byte)(struct e1000_hw *, u8, u8, u8 *);
 	s32 (*write_i2c_byte)(struct e1000_hw *, u8, u8, u8);
 };
 
 struct e1000_nvm_operations {
-	s32  (*acquire)(struct e1000_hw *);
-	s32  (*read)(struct e1000_hw *, u16, u16, u16 *);
+	s32 (*acquire)(struct e1000_hw *);
+	s32 (*read)(struct e1000_hw *, u16, u16, u16 *);
 	void (*release)(struct e1000_hw *);
-	s32  (*write)(struct e1000_hw *, u16, u16, u16 *);
-	s32  (*update)(struct e1000_hw *);
-	s32  (*validate)(struct e1000_hw *);
-	s32  (*valid_led_default)(struct e1000_hw *, u16 *);
+	s32 (*write)(struct e1000_hw *, u16, u16, u16 *);
+	s32 (*update)(struct e1000_hw *);
+	s32 (*validate)(struct e1000_hw *);
+	s32 (*valid_led_default)(struct e1000_hw *, u16 *);
 };
 
 #define E1000_MAX_SENSORS		3
@@ -571,4 +567,7 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw);
 /* These functions must be implemented by drivers */
 s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value);
 s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value);
+
+void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
+void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
 #endif /* _E1000_HW_H_ */
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c
index f67f8a170b9..65d931669f8 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.c
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.c
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 /* e1000_i210
  * e1000_i211
@@ -100,7 +97,7 @@ static s32 igb_get_hw_semaphore_i210(struct e1000_hw *hw)
 		return -E1000_ERR_NVM;
 	}
 
-	return E1000_SUCCESS;
+	return 0;
 }
 
 /**
@@ -142,7 +139,7 @@ s32 igb_acquire_swfw_sync_i210(struct e1000_hw *hw, u16 mask)
 	u32 swfw_sync;
 	u32 swmask = mask;
 	u32 fwmask = mask << 16;
-	s32 ret_val = E1000_SUCCESS;
+	s32 ret_val = 0;
 	s32 i = 0, timeout = 200; /* FIXME: find real value to use here */
 
 	while (i < timeout) {
@@ -187,7 +184,7 @@ void igb_release_swfw_sync_i210(struct e1000_hw *hw, u16 mask)
 {
 	u32 swfw_sync;
 
-	while (igb_get_hw_semaphore_i210(hw) != E1000_SUCCESS)
+	while (igb_get_hw_semaphore_i210(hw))
 		; /* Empty */
 
 	swfw_sync = rd32(E1000_SW_FW_SYNC);
@@ -210,7 +207,7 @@ void igb_release_swfw_sync_i210(struct e1000_hw *hw, u16 mask)
 static s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words,
 				  u16 *data)
 {
-	s32 status = E1000_SUCCESS;
+	s32 status = 0;
 	u16 i, count;
 
 	/* We cannot hold synchronization semaphores for too long,
@@ -220,7 +217,7 @@ static s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words,
 	for (i = 0; i < words; i += E1000_EERD_EEWR_MAX_COUNT) {
 		count = (words - i) / E1000_EERD_EEWR_MAX_COUNT > 0 ?
 			E1000_EERD_EEWR_MAX_COUNT : (words - i);
-		if (hw->nvm.ops.acquire(hw) == E1000_SUCCESS) {
+		if (!(hw->nvm.ops.acquire(hw))) {
 			status = igb_read_nvm_eerd(hw, offset, count,
 						     data + i);
 			hw->nvm.ops.release(hw);
@@ -228,7 +225,7 @@ static s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words,
 			status = E1000_ERR_SWFW_SYNC;
 		}
 
-		if (status != E1000_SUCCESS)
+		if (status)
 			break;
 	}
 
@@ -253,7 +250,7 @@ static s32 igb_write_nvm_srwr(struct e1000_hw *hw, u16 offset, u16 words,
 	struct e1000_nvm_info *nvm = &hw->nvm;
 	u32 i, k, eewr = 0;
 	u32 attempts = 100000;
-	s32 ret_val = E1000_SUCCESS;
+	s32 ret_val = 0;
 
 	/* A check for invalid values:  offset too large, too many words,
 	 * too many words for the offset, and not enough words.
@@ -275,13 +272,13 @@ static s32 igb_write_nvm_srwr(struct e1000_hw *hw, u16 offset, u16 words,
 		for (k = 0; k < attempts; k++) {
 			if (E1000_NVM_RW_REG_DONE &
 			    rd32(E1000_SRWR)) {
-				ret_val = E1000_SUCCESS;
+				ret_val = 0;
 				break;
 			}
 			udelay(5);
 	}
 
-		if (ret_val != E1000_SUCCESS) {
+		if (ret_val) {
 			hw_dbg("Shadow RAM write EEWR timed out\n");
 			break;
 		}
@@ -310,7 +307,7 @@ out:
 static s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words,
 				   u16 *data)
 {
-	s32 status = E1000_SUCCESS;
+	s32 status = 0;
 	u16 i, count;
 
 	/* We cannot hold synchronization semaphores for too long,
@@ -320,7 +317,7 @@ static s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words,
 	for (i = 0; i < words; i += E1000_EERD_EEWR_MAX_COUNT) {
 		count = (words - i) / E1000_EERD_EEWR_MAX_COUNT > 0 ?
 			E1000_EERD_EEWR_MAX_COUNT : (words - i);
-		if (hw->nvm.ops.acquire(hw) == E1000_SUCCESS) {
+		if (!(hw->nvm.ops.acquire(hw))) {
 			status = igb_write_nvm_srwr(hw, offset, count,
 						      data + i);
 			hw->nvm.ops.release(hw);
@@ -328,7 +325,7 @@ static s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words,
 			status = E1000_ERR_SWFW_SYNC;
 		}
 
-		if (status != E1000_SUCCESS)
+		if (status)
 			break;
 	}
 
@@ -367,12 +364,12 @@ static s32 igb_read_invm_word_i210(struct e1000_hw *hw, u8 address, u16 *data)
 				*data = INVM_DWORD_TO_WORD_DATA(invm_dword);
 				hw_dbg("Read INVM Word 0x%02x = %x\n",
 					  address, *data);
-				status = E1000_SUCCESS;
+				status = 0;
 				break;
 			}
 		}
 	}
-	if (status != E1000_SUCCESS)
+	if (status)
 		hw_dbg("Requested word 0x%02x not found in OTP\n", address);
 	return status;
 }
@@ -388,7 +385,7 @@ static s32 igb_read_invm_word_i210(struct e1000_hw *hw, u8 address, u16 *data)
 static s32 igb_read_invm_i210(struct e1000_hw *hw, u16 offset,
 				u16 words __always_unused, u16 *data)
 {
-	s32 ret_val = E1000_SUCCESS;
+	s32 ret_val = 0;
 
 	/* Only the MAC addr is required to be present in the iNVM */
 	switch (offset) {
@@ -398,43 +395,44 @@ static s32 igb_read_invm_i210(struct e1000_hw *hw, u16 offset,
 						     &data[1]);
 		ret_val |= igb_read_invm_word_i210(hw, (u8)offset+2,
 						     &data[2]);
-		if (ret_val != E1000_SUCCESS)
+		if (ret_val)
 			hw_dbg("MAC Addr not found in iNVM\n");
 		break;
 	case NVM_INIT_CTRL_2:
 		ret_val = igb_read_invm_word_i210(hw, (u8)offset, data);
-		if (ret_val != E1000_SUCCESS) {
+		if (ret_val) {
 			*data = NVM_INIT_CTRL_2_DEFAULT_I211;
-			ret_val = E1000_SUCCESS;
+			ret_val = 0;
 		}
 		break;
 	case NVM_INIT_CTRL_4:
 		ret_val = igb_read_invm_word_i210(hw, (u8)offset, data);
-		if (ret_val != E1000_SUCCESS) {
+		if (ret_val) {
 			*data = NVM_INIT_CTRL_4_DEFAULT_I211;
-			ret_val = E1000_SUCCESS;
+			ret_val = 0;
 		}
 		break;
 	case NVM_LED_1_CFG:
 		ret_val = igb_read_invm_word_i210(hw, (u8)offset, data);
-		if (ret_val != E1000_SUCCESS) {
+		if (ret_val) {
 			*data = NVM_LED_1_CFG_DEFAULT_I211;
-			ret_val = E1000_SUCCESS;
+			ret_val = 0;
 		}
 		break;
 	case NVM_LED_0_2_CFG:
 		ret_val = igb_read_invm_word_i210(hw, (u8)offset, data);
-		if (ret_val != E1000_SUCCESS) {
+		if (ret_val) {
 			*data = NVM_LED_0_2_CFG_DEFAULT_I211;
-			ret_val = E1000_SUCCESS;
+			ret_val = 0;
 		}
 		break;
 	case NVM_ID_LED_SETTINGS:
 		ret_val = igb_read_invm_word_i210(hw, (u8)offset, data);
-		if (ret_val != E1000_SUCCESS) {
+		if (ret_val) {
 			*data = ID_LED_RESERVED_FFFF;
-			ret_val = E1000_SUCCESS;
+			ret_val = 0;
 		}
+		break;
 	case NVM_SUB_DEV_ID:
 		*data = hw->subsystem_device_id;
 		break;
@@ -488,14 +486,14 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
 		/* Check if we have first version location used */
 		if ((i == 1) && ((*record & E1000_INVM_VER_FIELD_ONE) == 0)) {
 			version = 0;
-			status = E1000_SUCCESS;
+			status = 0;
 			break;
 		}
 		/* Check if we have second version location used */
 		else if ((i == 1) &&
 			 ((*record & E1000_INVM_VER_FIELD_TWO) == 0)) {
 			version = (*record & E1000_INVM_VER_FIELD_ONE) >> 3;
-			status = E1000_SUCCESS;
+			status = 0;
 			break;
 		}
 		/* Check if we have odd version location
@@ -506,7 +504,7 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
 			 (i != 1))) {
 			version = (*next_record & E1000_INVM_VER_FIELD_TWO)
 				  >> 13;
-			status = E1000_SUCCESS;
+			status = 0;
 			break;
 		}
 		/* Check if we have even version location
@@ -515,12 +513,12 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
 		else if (((*record & E1000_INVM_VER_FIELD_TWO) == 0) &&
 			 ((*record & 0x3) == 0)) {
 			version = (*record & E1000_INVM_VER_FIELD_ONE) >> 3;
-			status = E1000_SUCCESS;
+			status = 0;
 			break;
 		}
 	}
 
-	if (status == E1000_SUCCESS) {
+	if (!status) {
 		invm_ver->invm_major = (version & E1000_INVM_MAJOR_MASK)
 					>> E1000_INVM_MAJOR_SHIFT;
 		invm_ver->invm_minor = version & E1000_INVM_MINOR_MASK;
@@ -533,7 +531,7 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
 		/* Check if we have image type in first location used */
 		if ((i == 1) && ((*record & E1000_INVM_IMGTYPE_FIELD) == 0)) {
 			invm_ver->invm_img_type = 0;
-			status = E1000_SUCCESS;
+			status = 0;
 			break;
 		}
 		/* Check if we have image type in first location used */
@@ -542,7 +540,7 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
 			 ((((*record & 0x3) != 0) && (i != 1)))) {
 			invm_ver->invm_img_type =
 				(*next_record & E1000_INVM_IMGTYPE_FIELD) >> 23;
-			status = E1000_SUCCESS;
+			status = 0;
 			break;
 		}
 	}
@@ -558,10 +556,10 @@ s32 igb_read_invm_version(struct e1000_hw *hw,
  **/
 static s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw)
 {
-	s32 status = E1000_SUCCESS;
+	s32 status = 0;
 	s32 (*read_op_ptr)(struct e1000_hw *, u16, u16, u16 *);
 
-	if (hw->nvm.ops.acquire(hw) == E1000_SUCCESS) {
+	if (!(hw->nvm.ops.acquire(hw))) {
 
 		/* Replace the read function with semaphore grabbing with
 		 * the one that skips this for a while.
@@ -593,7 +591,7 @@ static s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw)
  **/
 static s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw)
 {
-	s32 ret_val = E1000_SUCCESS;
+	s32 ret_val = 0;
 	u16 checksum = 0;
 	u16 i, nvm_data;
 
@@ -602,12 +600,12 @@ static s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw)
 	 * EEPROM read fails
 	 */
 	ret_val = igb_read_nvm_eerd(hw, 0, 1, &nvm_data);
-	if (ret_val != E1000_SUCCESS) {
+	if (ret_val) {
 		hw_dbg("EEPROM read failed\n");
 		goto out;
 	}
 
-	if (hw->nvm.ops.acquire(hw) == E1000_SUCCESS) {
+	if (!(hw->nvm.ops.acquire(hw))) {
 		/* Do not use hw->nvm.ops.write, hw->nvm.ops.read
 		 * because we do not want to take the synchronization
 		 * semaphores twice here.
@@ -625,7 +623,7 @@ static s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw)
 		checksum = (u16) NVM_SUM - checksum;
 		ret_val = igb_write_nvm_srwr(hw, NVM_CHECKSUM_REG, 1,
 						&checksum);
-		if (ret_val != E1000_SUCCESS) {
+		if (ret_val) {
 			hw->nvm.ops.release(hw);
 			hw_dbg("NVM Write Error while updating checksum.\n");
 			goto out;
@@ -654,7 +652,7 @@ static s32 igb_pool_flash_update_done_i210(struct e1000_hw *hw)
 	for (i = 0; i < E1000_FLUDONE_ATTEMPTS; i++) {
 		reg = rd32(E1000_EECD);
 		if (reg & E1000_EECD_FLUDONE_I210) {
-			ret_val = E1000_SUCCESS;
+			ret_val = 0;
 			break;
 		}
 		udelay(5);
@@ -687,7 +685,7 @@ bool igb_get_flash_presence_i210(struct e1000_hw *hw)
  **/
 static s32 igb_update_flash_i210(struct e1000_hw *hw)
 {
-	s32 ret_val = E1000_SUCCESS;
+	s32 ret_val = 0;
 	u32 flup;
 
 	ret_val = igb_pool_flash_update_done_i210(hw);
@@ -700,7 +698,7 @@ static s32 igb_update_flash_i210(struct e1000_hw *hw)
 	wr32(E1000_EECD, flup);
 
 	ret_val = igb_pool_flash_update_done_i210(hw);
-	if (ret_val == E1000_SUCCESS)
+	if (ret_val)
 		hw_dbg("Flash update complete\n");
 	else
 		hw_dbg("Flash update time out\n");
@@ -753,7 +751,7 @@ out:
 static s32 __igb_access_xmdio_reg(struct e1000_hw *hw, u16 address,
 				  u8 dev_addr, u16 *data, bool read)
 {
-	s32 ret_val = E1000_SUCCESS;
+	s32 ret_val = 0;
 
 	ret_val = hw->phy.ops.write_reg(hw, E1000_MMDAC, dev_addr);
 	if (ret_val)
@@ -836,3 +834,69 @@ s32 igb_init_nvm_params_i210(struct e1000_hw *hw)
 	}
 	return ret_val;
 }
+
+/**
+ * igb_pll_workaround_i210
+ * @hw: pointer to the HW structure
+ *
+ * Works around an errata in the PLL circuit where it occasionally
+ * provides the wrong clock frequency after power up.
+ **/
+s32 igb_pll_workaround_i210(struct e1000_hw *hw)
+{
+	s32 ret_val;
+	u32 wuc, mdicnfg, ctrl, ctrl_ext, reg_val;
+	u16 nvm_word, phy_word, pci_word, tmp_nvm;
+	int i;
+
+	/* Get and set needed register values */
+	wuc = rd32(E1000_WUC);
+	mdicnfg = rd32(E1000_MDICNFG);
+	reg_val = mdicnfg & ~E1000_MDICNFG_EXT_MDIO;
+	wr32(E1000_MDICNFG, reg_val);
+
+	/* Get data from NVM, or set default */
+	ret_val = igb_read_invm_word_i210(hw, E1000_INVM_AUTOLOAD,
+					  &nvm_word);
+	if (ret_val)
+		nvm_word = E1000_INVM_DEFAULT_AL;
+	tmp_nvm = nvm_word | E1000_INVM_PLL_WO_VAL;
+	for (i = 0; i < E1000_MAX_PLL_TRIES; i++) {
+		/* check current state directly from internal PHY */
+		igb_read_phy_reg_gs40g(hw, (E1000_PHY_PLL_FREQ_PAGE |
+					 E1000_PHY_PLL_FREQ_REG), &phy_word);
+		if ((phy_word & E1000_PHY_PLL_UNCONF)
+		    != E1000_PHY_PLL_UNCONF) {
+			ret_val = 0;
+			break;
+		} else {
+			ret_val = -E1000_ERR_PHY;
+		}
+		/* directly reset the internal PHY */
+		ctrl = rd32(E1000_CTRL);
+		wr32(E1000_CTRL, ctrl|E1000_CTRL_PHY_RST);
+
+		ctrl_ext = rd32(E1000_CTRL_EXT);
+		ctrl_ext |= (E1000_CTRL_EXT_PHYPDEN | E1000_CTRL_EXT_SDLPE);
+		wr32(E1000_CTRL_EXT, ctrl_ext);
+
+		wr32(E1000_WUC, 0);
+		reg_val = (E1000_INVM_AUTOLOAD << 4) | (tmp_nvm << 16);
+		wr32(E1000_EEARBC_I210, reg_val);
+
+		igb_read_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word);
+		pci_word |= E1000_PCI_PMCSR_D3;
+		igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word);
+		usleep_range(1000, 2000);
+		pci_word &= ~E1000_PCI_PMCSR_D3;
+		igb_write_pci_cfg(hw, E1000_PCI_PMCSR, &pci_word);
+		reg_val = (E1000_INVM_AUTOLOAD << 4) | (nvm_word << 16);
+		wr32(E1000_EEARBC_I210, reg_val);
+
+		/* restore WUC register */
+		wr32(E1000_WUC, wuc);
+	}
+	/* restore MDICNFG setting */
+	wr32(E1000_MDICNFG, mdicnfg);
+	return ret_val;
+}
diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h
index 907fe99a981..3442b6357d0 100644
--- a/drivers/net/ethernet/intel/igb/e1000_i210.h
+++ b/drivers/net/ethernet/intel/igb/e1000_i210.h
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #ifndef _E1000_I210_H_
 #define _E1000_I210_H_
@@ -36,6 +33,7 @@ s32 igb_read_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 *data);
 s32 igb_write_xmdio_reg(struct e1000_hw *hw, u16 addr, u8 dev_addr, u16 data);
 s32 igb_init_nvm_params_i210(struct e1000_hw *hw);
 bool igb_get_flash_presence_i210(struct e1000_hw *hw);
+s32 igb_pll_workaround_i210(struct e1000_hw *hw);
 
 #define E1000_STM_OPCODE		0xDB00
 #define E1000_EEPROM_FLASH_SIZE_WORD	0x11
@@ -81,4 +79,15 @@ enum E1000_INVM_STRUCTURE_TYPE {
 #define NVM_LED_1_CFG_DEFAULT_I211	0x0184
 #define NVM_LED_0_2_CFG_DEFAULT_I211	0x200C
 
+/* PLL Defines */
+#define E1000_PCI_PMCSR			0x44
+#define E1000_PCI_PMCSR_D3		0x03
+#define E1000_MAX_PLL_TRIES		5
+#define E1000_PHY_PLL_UNCONF		0xFF
+#define E1000_PHY_PLL_FREQ_PAGE		0xFC0000
+#define E1000_PHY_PLL_FREQ_REG		0x000E
+#define E1000_INVM_DEFAULT_AL		0x202F
+#define E1000_INVM_AUTOLOAD		0x0A
+#define E1000_INVM_PLL_WO_VAL		0x0010
+
 #endif
diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c
index 1e0c404db81..2a88595f956 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mac.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mac.c
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #include <linux/if_ether.h>
 #include <linux/delay.h>
@@ -442,7 +439,7 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr)
  *  The caller must have a packed mc_addr_list of multicast addresses.
  **/
 void igb_update_mc_addr_list(struct e1000_hw *hw,
-                             u8 *mc_addr_list, u32 mc_addr_count)
+			     u8 *mc_addr_list, u32 mc_addr_count)
 {
 	u32 hash_value, hash_bit, hash_reg;
 	int i;
@@ -866,8 +863,7 @@ s32 igb_config_fc_after_link_up(struct e1000_hw *hw)
 			goto out;
 
 		if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) {
-			hw_dbg("Copper PHY and Auto Neg "
-				 "has not completed.\n");
+			hw_dbg("Copper PHY and Auto Neg has not completed.\n");
 			goto out;
 		}
 
@@ -1265,7 +1261,7 @@ s32 igb_get_auto_rd_done(struct e1000_hw *hw)
 	while (i < AUTO_READ_DONE_TIMEOUT) {
 		if (rd32(E1000_EECD) & E1000_EECD_AUTO_RD)
 			break;
-		msleep(1);
+		usleep_range(1000, 2000);
 		i++;
 	}
 
@@ -1298,7 +1294,7 @@ static s32 igb_valid_led_default(struct e1000_hw *hw, u16 *data)
 	}
 
 	if (*data == ID_LED_RESERVED_0000 || *data == ID_LED_RESERVED_FFFF) {
-		switch(hw->phy.media_type) {
+		switch (hw->phy.media_type) {
 		case e1000_media_type_internal_serdes:
 			*data = ID_LED_DEFAULT_82575_SERDES;
 			break;
diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.h b/drivers/net/ethernet/intel/igb/e1000_mac.h
index 99299ba8ee3..ea24961b0d7 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mac.h
+++ b/drivers/net/ethernet/intel/igb/e1000_mac.h
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #ifndef _E1000_MAC_H_
 #define _E1000_MAC_H_
diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.c b/drivers/net/ethernet/intel/igb/e1000_mbx.c
index d5b121771c3..162cc49345d 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mbx.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mbx.c
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #include "e1000_mbx.h"
 
diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.h b/drivers/net/ethernet/intel/igb/e1000_mbx.h
index f52f5515e5a..d20af6b2f58 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mbx.h
+++ b/drivers/net/ethernet/intel/igb/e1000_mbx.h
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #ifndef _E1000_MBX_H_
 #define _E1000_MBX_H_
diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c
index 9abf82919c6..e8280d0d7f0 100644
--- a/drivers/net/ethernet/intel/igb/e1000_nvm.c
+++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c
@@ -1,28 +1,24 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #include <linux/if_ether.h>
 #include <linux/delay.h>
@@ -480,6 +476,7 @@ s32 igb_write_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data)
 		/* Loop to allow for up to whole page write of eeprom */
 		while (widx < words) {
 			u16 word_out = data[widx];
+
 			word_out = (word_out >> 8) | (word_out << 8);
 			igb_shift_out_eec_bits(hw, word_out, 16);
 			widx++;
@@ -801,5 +798,4 @@ etrack_id:
 		fw_vers->etrack_id = (eeprom_verh << NVM_ETRACK_SHIFT)
 			| eeprom_verl;
 	}
-	return;
 }
diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.h b/drivers/net/ethernet/intel/igb/e1000_nvm.h
index 5b101170b17..febc9cdb739 100644
--- a/drivers/net/ethernet/intel/igb/e1000_nvm.h
+++ b/drivers/net/ethernet/intel/igb/e1000_nvm.h
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #ifndef _E1000_NVM_H_
 #define _E1000_NVM_H_
@@ -32,7 +29,7 @@ void igb_release_nvm(struct e1000_hw *hw);
 s32  igb_read_mac_addr(struct e1000_hw *hw);
 s32  igb_read_part_num(struct e1000_hw *hw, u32 *part_num);
 s32  igb_read_part_string(struct e1000_hw *hw, u8 *part_num,
-                          u32 part_num_size);
+			  u32 part_num_size);
 s32  igb_read_nvm_eerd(struct e1000_hw *hw, u16 offset, u16 words, u16 *data);
 s32  igb_read_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data);
 s32  igb_write_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data);
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 4009bbab740..c1bb64d8366 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #include <linux/if_ether.h>
 #include <linux/delay.h>
@@ -924,8 +921,7 @@ static s32 igb_copper_link_autoneg(struct e1000_hw *hw)
 	if (phy->autoneg_wait_to_complete) {
 		ret_val = igb_wait_autoneg(hw);
 		if (ret_val) {
-			hw_dbg("Error while waiting for "
-			       "autoneg to complete\n");
+			hw_dbg("Error while waiting for autoneg to complete\n");
 			goto out;
 		}
 	}
@@ -2208,16 +2204,10 @@ s32 igb_phy_init_script_igp3(struct e1000_hw *hw)
 void igb_power_up_phy_copper(struct e1000_hw *hw)
 {
 	u16 mii_reg = 0;
-	u16 power_reg = 0;
 
 	/* The PHY will retain its settings across a power down/up cycle */
 	hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg);
 	mii_reg &= ~MII_CR_POWER_DOWN;
-	if (hw->phy.type == e1000_phy_i210) {
-		hw->phy.ops.read_reg(hw, GS40G_COPPER_SPEC, &power_reg);
-		power_reg &= ~GS40G_CS_POWER_DOWN;
-		hw->phy.ops.write_reg(hw, GS40G_COPPER_SPEC, power_reg);
-	}
 	hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);
 }
 
@@ -2231,20 +2221,12 @@ void igb_power_up_phy_copper(struct e1000_hw *hw)
 void igb_power_down_phy_copper(struct e1000_hw *hw)
 {
 	u16 mii_reg = 0;
-	u16 power_reg = 0;
 
 	/* The PHY will retain its settings across a power down/up cycle */
 	hw->phy.ops.read_reg(hw, PHY_CONTROL, &mii_reg);
 	mii_reg |= MII_CR_POWER_DOWN;
-
-	/* i210 Phy requires an additional bit for power up/down */
-	if (hw->phy.type == e1000_phy_i210) {
-		hw->phy.ops.read_reg(hw, GS40G_COPPER_SPEC, &power_reg);
-		power_reg |= GS40G_CS_POWER_DOWN;
-		hw->phy.ops.write_reg(hw, GS40G_COPPER_SPEC, power_reg);
-	}
 	hw->phy.ops.write_reg(hw, PHY_CONTROL, mii_reg);
-	msleep(1);
+	usleep_range(1000, 2000);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.h b/drivers/net/ethernet/intel/igb/e1000_phy.h
index 4c2c36c46a7..7af4ffab028 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.h
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.h
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #ifndef _E1000_PHY_H_
 #define _E1000_PHY_H_
@@ -154,7 +151,6 @@ s32  igb_check_polarity_m88(struct e1000_hw *hw);
 #define GS40G_MAC_LB			0x4140
 #define GS40G_MAC_SPEED_1G		0X0006
 #define GS40G_COPPER_SPEC		0x0010
-#define GS40G_CS_POWER_DOWN		0x0002
 #define GS40G_LINE_LB			0x4000
 
 /* SFP modules ID memory locations */
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index bdb246e848e..f5ba4e4eafb 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #ifndef _E1000_REGS_H_
 #define _E1000_REGS_H_
@@ -69,6 +66,7 @@
 #define E1000_PBA      0x01000  /* Packet Buffer Allocation - RW */
 #define E1000_PBS      0x01008  /* Packet Buffer Size */
 #define E1000_EEMNGCTL 0x01010  /* MNG EEprom Control */
+#define E1000_EEARBC_I210 0x12024  /* EEPROM Auto Read Bus Control */
 #define E1000_EEWR     0x0102C  /* EEPROM Write Register - RW */
 #define E1000_I2CCMD   0x01028  /* SFPI2C Command Register - RW */
 #define E1000_FRTIMER  0x01048  /* Free Running Timer - RW */
@@ -195,6 +193,10 @@
 				    : (0x0E038 + ((_n) * 0x40)))
 #define E1000_TDWBAH(_n)  ((_n) < 4 ? (0x0383C + ((_n) * 0x100)) \
 				    : (0x0E03C + ((_n) * 0x40)))
+
+#define E1000_RXPBS	0x02404  /* Rx Packet Buffer Size - RW */
+#define E1000_TXPBS	0x03404  /* Tx Packet Buffer Size - RW */
+
 #define E1000_TDFH     0x03410  /* TX Data FIFO Head - RW */
 #define E1000_TDFT     0x03418  /* TX Data FIFO Tail - RW */
 #define E1000_TDFHS    0x03420  /* TX Data FIFO Head Saved - RW */
@@ -301,9 +303,9 @@
 #define E1000_RA2      0x054E0  /* 2nd half of Rx address array - RW Array */
 #define E1000_PSRTYPE(_i)       (0x05480 + ((_i) * 4))
 #define E1000_RAL(_i)  (((_i) <= 15) ? (0x05400 + ((_i) * 8)) : \
-                                       (0x054E0 + ((_i - 16) * 8)))
+					(0x054E0 + ((_i - 16) * 8)))
 #define E1000_RAH(_i)  (((_i) <= 15) ? (0x05404 + ((_i) * 8)) : \
-                                       (0x054E4 + ((_i - 16) * 8)))
+					(0x054E4 + ((_i - 16) * 8)))
 #define E1000_IP4AT_REG(_i)     (0x05840 + ((_i) * 8))
 #define E1000_IP6AT_REG(_i)     (0x05880 + ((_i) * 4))
 #define E1000_WUPM_REG(_i)      (0x05A00 + ((_i) * 4))
@@ -358,8 +360,7 @@
 #define E1000_VMBMEM(_n)       (0x00800 + (64 * (_n)))
 #define E1000_VMOLR(_n)        (0x05AD0 + (4 * (_n)))
 #define E1000_DVMOLR(_n)       (0x0C038 + (64 * (_n)))
-#define E1000_VLVF(_n)         (0x05D00 + (4 * (_n))) /* VLAN Virtual Machine
-                                                       * Filter - RW */
+#define E1000_VLVF(_n)         (0x05D00 + (4 * (_n))) /* VLAN VM Filter */
 #define E1000_VMVIR(_n)        (0x03700 + (4 * (_n)))
 
 struct e1000_hw;
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 27130065d92..06102d1f7c0 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -1,29 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
-
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 /* Linux PRO/1000 Ethernet Driver main header file */
 
@@ -198,6 +194,7 @@ struct igb_tx_buffer {
 	unsigned int bytecount;
 	u16 gso_segs;
 	__be16 protocol;
+
 	DEFINE_DMA_UNMAP_ADDR(dma);
 	DEFINE_DMA_UNMAP_LEN(len);
 	u32 tx_flags;
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index e5570acbeea..c737d1f4083 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 /* ethtool support for igb */
 
@@ -144,6 +141,7 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	struct e1000_dev_spec_82575 *dev_spec = &hw->dev_spec._82575;
 	struct e1000_sfp_flags *eth_flags = &dev_spec->eth_flags;
 	u32 status;
+	u32 speed;
 
 	status = rd32(E1000_STATUS);
 	if (hw->phy.media_type == e1000_media_type_copper) {
@@ -218,13 +216,13 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	if (status & E1000_STATUS_LU) {
 		if ((status & E1000_STATUS_2P5_SKU) &&
 		    !(status & E1000_STATUS_2P5_SKU_OVER)) {
-			ecmd->speed = SPEED_2500;
+			speed = SPEED_2500;
 		} else if (status & E1000_STATUS_SPEED_1000) {
-			ecmd->speed = SPEED_1000;
+			speed = SPEED_1000;
 		} else if (status & E1000_STATUS_SPEED_100) {
-			ecmd->speed = SPEED_100;
+			speed = SPEED_100;
 		} else {
-			ecmd->speed = SPEED_10;
+			speed = SPEED_10;
 		}
 		if ((status & E1000_STATUS_FD) ||
 		    hw->phy.media_type != e1000_media_type_copper)
@@ -232,9 +230,10 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		else
 			ecmd->duplex = DUPLEX_HALF;
 	} else {
-		ecmd->speed = -1;
-		ecmd->duplex = -1;
+		speed = SPEED_UNKNOWN;
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
+	ethtool_cmd_speed_set(ecmd, speed);
 	if ((hw->phy.media_type == e1000_media_type_fiber) ||
 	    hw->mac.autoneg)
 		ecmd->autoneg = AUTONEG_ENABLE;
@@ -286,7 +285,7 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	}
 
 	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
-		msleep(1);
+		usleep_range(1000, 2000);
 
 	if (ecmd->autoneg == AUTONEG_ENABLE) {
 		hw->mac.autoneg = 1;
@@ -399,7 +398,7 @@ static int igb_set_pauseparam(struct net_device *netdev,
 	adapter->fc_autoneg = pause->autoneg;
 
 	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
-		msleep(1);
+		usleep_range(1000, 2000);
 
 	if (adapter->fc_autoneg == AUTONEG_ENABLE) {
 		hw->fc.requested_mode = e1000_fc_default;
@@ -886,7 +885,7 @@ static int igb_set_ringparam(struct net_device *netdev,
 	}
 
 	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
-		msleep(1);
+		usleep_range(1000, 2000);
 
 	if (!netif_running(adapter->netdev)) {
 		for (i = 0; i < adapter->num_tx_queues; i++)
@@ -1060,8 +1059,8 @@ static struct igb_reg_test reg_test_i350[] = {
 	{ E1000_TDT(0),	   0x100, 4,  PATTERN_TEST, 0x0000FFFF, 0x0000FFFF },
 	{ E1000_TDT(4),	   0x40,  4,  PATTERN_TEST, 0x0000FFFF, 0x0000FFFF },
 	{ E1000_RCTL,	   0x100, 1,  SET_READ_TEST, 0xFFFFFFFF, 0x00000000 },
-	{ E1000_RCTL, 	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB },
-	{ E1000_RCTL, 	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF },
+	{ E1000_RCTL,	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB },
+	{ E1000_RCTL,	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF },
 	{ E1000_TCTL,	   0x100, 1,  SET_READ_TEST, 0xFFFFFFFF, 0x00000000 },
 	{ E1000_RA,	   0, 16, TABLE64_TEST_LO,
 						0xFFFFFFFF, 0xFFFFFFFF },
@@ -1103,8 +1102,8 @@ static struct igb_reg_test reg_test_82580[] = {
 	{ E1000_TDT(0),	   0x100, 4,  PATTERN_TEST, 0x0000FFFF, 0x0000FFFF },
 	{ E1000_TDT(4),	   0x40,  4,  PATTERN_TEST, 0x0000FFFF, 0x0000FFFF },
 	{ E1000_RCTL,	   0x100, 1,  SET_READ_TEST, 0xFFFFFFFF, 0x00000000 },
-	{ E1000_RCTL, 	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB },
-	{ E1000_RCTL, 	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF },
+	{ E1000_RCTL,	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB },
+	{ E1000_RCTL,	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF },
 	{ E1000_TCTL,	   0x100, 1,  SET_READ_TEST, 0xFFFFFFFF, 0x00000000 },
 	{ E1000_RA,	   0, 16, TABLE64_TEST_LO,
 						0xFFFFFFFF, 0xFFFFFFFF },
@@ -1132,8 +1131,10 @@ static struct igb_reg_test reg_test_82576[] = {
 	{ E1000_RDBAH(4),  0x40, 12, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF },
 	{ E1000_RDLEN(4),  0x40, 12, PATTERN_TEST, 0x000FFFF0, 0x000FFFFF },
 	/* Enable all RX queues before testing. */
-	{ E1000_RXDCTL(0), 0x100, 4,  WRITE_NO_TEST, 0, E1000_RXDCTL_QUEUE_ENABLE },
-	{ E1000_RXDCTL(4), 0x40, 12,  WRITE_NO_TEST, 0, E1000_RXDCTL_QUEUE_ENABLE },
+	{ E1000_RXDCTL(0), 0x100, 4, WRITE_NO_TEST, 0,
+	  E1000_RXDCTL_QUEUE_ENABLE },
+	{ E1000_RXDCTL(4), 0x40, 12, WRITE_NO_TEST, 0,
+	  E1000_RXDCTL_QUEUE_ENABLE },
 	/* RDH is read-only for 82576, only test RDT. */
 	{ E1000_RDT(0),	   0x100, 4,  PATTERN_TEST, 0x0000FFFF, 0x0000FFFF },
 	{ E1000_RDT(4),	   0x40, 12,  PATTERN_TEST, 0x0000FFFF, 0x0000FFFF },
@@ -1149,14 +1150,14 @@ static struct igb_reg_test reg_test_82576[] = {
 	{ E1000_TDBAH(4),  0x40, 12,  PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF },
 	{ E1000_TDLEN(4),  0x40, 12,  PATTERN_TEST, 0x000FFFF0, 0x000FFFFF },
 	{ E1000_RCTL,	   0x100, 1,  SET_READ_TEST, 0xFFFFFFFF, 0x00000000 },
-	{ E1000_RCTL, 	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB },
-	{ E1000_RCTL, 	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF },
+	{ E1000_RCTL,	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0x003FFFFB },
+	{ E1000_RCTL,	   0x100, 1,  SET_READ_TEST, 0x04CFB0FE, 0xFFFFFFFF },
 	{ E1000_TCTL,	   0x100, 1,  SET_READ_TEST, 0xFFFFFFFF, 0x00000000 },
 	{ E1000_RA,	   0, 16, TABLE64_TEST_LO, 0xFFFFFFFF, 0xFFFFFFFF },
 	{ E1000_RA,	   0, 16, TABLE64_TEST_HI, 0x83FFFFFF, 0xFFFFFFFF },
 	{ E1000_RA2,	   0, 8, TABLE64_TEST_LO, 0xFFFFFFFF, 0xFFFFFFFF },
 	{ E1000_RA2,	   0, 8, TABLE64_TEST_HI, 0x83FFFFFF, 0xFFFFFFFF },
-	{ E1000_MTA,	   0, 128,TABLE32_TEST, 0xFFFFFFFF, 0xFFFFFFFF },
+	{ E1000_MTA,	   0, 128, TABLE32_TEST, 0xFFFFFFFF, 0xFFFFFFFF },
 	{ 0, 0, 0, 0 }
 };
 
@@ -1170,7 +1171,8 @@ static struct igb_reg_test reg_test_82575[] = {
 	{ E1000_RDBAH(0),  0x100, 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF },
 	{ E1000_RDLEN(0),  0x100, 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF },
 	/* Enable all four RX queues before testing. */
-	{ E1000_RXDCTL(0), 0x100, 4, WRITE_NO_TEST, 0, E1000_RXDCTL_QUEUE_ENABLE },
+	{ E1000_RXDCTL(0), 0x100, 4, WRITE_NO_TEST, 0,
+	  E1000_RXDCTL_QUEUE_ENABLE },
 	/* RDH is read-only for 82575, only test RDT. */
 	{ E1000_RDT(0),    0x100, 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF },
 	{ E1000_RXDCTL(0), 0x100, 4, WRITE_NO_TEST, 0, 0 },
@@ -1196,8 +1198,8 @@ static bool reg_pattern_test(struct igb_adapter *adapter, u64 *data,
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 pat, val;
-	static const u32 _test[] =
-		{0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF};
+	static const u32 _test[] = {
+		0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF};
 	for (pat = 0; pat < ARRAY_SIZE(_test); pat++) {
 		wr32(reg, (_test[pat] & write));
 		val = rd32(reg) & mask;
@@ -1206,11 +1208,11 @@ static bool reg_pattern_test(struct igb_adapter *adapter, u64 *data,
 				"pattern test reg %04X failed: got 0x%08X expected 0x%08X\n",
 				reg, val, (_test[pat] & write & mask));
 			*data = reg;
-			return 1;
+			return true;
 		}
 	}
 
-	return 0;
+	return false;
 }
 
 static bool reg_set_and_check(struct igb_adapter *adapter, u64 *data,
@@ -1218,17 +1220,18 @@ static bool reg_set_and_check(struct igb_adapter *adapter, u64 *data,
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 val;
+
 	wr32(reg, write & mask);
 	val = rd32(reg);
 	if ((write & mask) != (val & mask)) {
 		dev_err(&adapter->pdev->dev,
-			"set/check reg %04X test failed: got 0x%08X expected 0x%08X\n", reg,
-			(val & mask), (write & mask));
+			"set/check reg %04X test failed: got 0x%08X expected 0x%08X\n",
+			reg, (val & mask), (write & mask));
 		*data = reg;
-		return 1;
+		return true;
 	}
 
-	return 0;
+	return false;
 }
 
 #define REG_PATTERN_TEST(reg, mask, write) \
@@ -1387,14 +1390,14 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data)
 	/* Hook up test interrupt handler just for this test */
 	if (adapter->flags & IGB_FLAG_HAS_MSIX) {
 		if (request_irq(adapter->msix_entries[0].vector,
-		                igb_test_intr, 0, netdev->name, adapter)) {
+				igb_test_intr, 0, netdev->name, adapter)) {
 			*data = 1;
 			return -1;
 		}
 	} else if (adapter->flags & IGB_FLAG_HAS_MSI) {
 		shared_int = false;
 		if (request_irq(irq,
-		                igb_test_intr, 0, netdev->name, adapter)) {
+				igb_test_intr, 0, netdev->name, adapter)) {
 			*data = 1;
 			return -1;
 		}
@@ -1412,7 +1415,7 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data)
 	/* Disable all the interrupts */
 	wr32(E1000_IMC, ~0);
 	wrfl();
-	msleep(10);
+	usleep_range(10000, 11000);
 
 	/* Define all writable bits for ICS */
 	switch (hw->mac.type) {
@@ -1459,7 +1462,7 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data)
 			wr32(E1000_IMC, mask);
 			wr32(E1000_ICS, mask);
 			wrfl();
-			msleep(10);
+			usleep_range(10000, 11000);
 
 			if (adapter->test_icr & mask) {
 				*data = 3;
@@ -1481,7 +1484,7 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data)
 		wr32(E1000_IMS, mask);
 		wr32(E1000_ICS, mask);
 		wrfl();
-		msleep(10);
+		usleep_range(10000, 11000);
 
 		if (!(adapter->test_icr & mask)) {
 			*data = 4;
@@ -1503,7 +1506,7 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data)
 			wr32(E1000_IMC, ~mask);
 			wr32(E1000_ICS, ~mask);
 			wrfl();
-			msleep(10);
+			usleep_range(10000, 11000);
 
 			if (adapter->test_icr & mask) {
 				*data = 5;
@@ -1515,7 +1518,7 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data)
 	/* Disable all the interrupts */
 	wr32(E1000_IMC, ~0);
 	wrfl();
-	msleep(10);
+	usleep_range(10000, 11000);
 
 	/* Unhook test interrupt handler */
 	if (adapter->flags & IGB_FLAG_HAS_MSIX)
@@ -1664,8 +1667,8 @@ static int igb_setup_loopback_test(struct igb_adapter *adapter)
 		(hw->device_id == E1000_DEV_ID_DH89XXCC_SERDES) ||
 		(hw->device_id == E1000_DEV_ID_DH89XXCC_BACKPLANE) ||
 		(hw->device_id == E1000_DEV_ID_DH89XXCC_SFP) ||
-		(hw->device_id == E1000_DEV_ID_I354_SGMII)) {
-
+		(hw->device_id == E1000_DEV_ID_I354_SGMII) ||
+		(hw->device_id == E1000_DEV_ID_I354_BACKPLANE_2_5GBPS)) {
 			/* Enable DH89xxCC MPHY for near end loopback */
 			reg = rd32(E1000_MPHY_ADDR_CTL);
 			reg = (reg & E1000_MPHY_ADDR_CTL_OFFSET_MASK) |
@@ -1949,6 +1952,7 @@ static int igb_link_test(struct igb_adapter *adapter, u64 *data)
 	*data = 0;
 	if (hw->phy.media_type == e1000_media_type_internal_serdes) {
 		int i = 0;
+
 		hw->mac.serdes_has_link = false;
 
 		/* On some blade server designs, link establishment
@@ -2413,9 +2417,11 @@ static int igb_get_rss_hash_opts(struct igb_adapter *adapter,
 	switch (cmd->flow_type) {
 	case TCP_V4_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case UDP_V4_FLOW:
 		if (adapter->flags & IGB_FLAG_RSS_FIELD_IPV4_UDP)
 			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case SCTP_V4_FLOW:
 	case AH_ESP_V4_FLOW:
 	case AH_V4_FLOW:
@@ -2425,9 +2431,11 @@ static int igb_get_rss_hash_opts(struct igb_adapter *adapter,
 		break;
 	case TCP_V6_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case UDP_V6_FLOW:
 		if (adapter->flags & IGB_FLAG_RSS_FIELD_IPV6_UDP)
 			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case SCTP_V6_FLOW:
 	case AH_ESP_V6_FLOW:
 	case AH_V6_FLOW:
@@ -2730,7 +2738,7 @@ static int igb_get_module_info(struct net_device *netdev,
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	u32 status = E1000_SUCCESS;
+	u32 status = 0;
 	u16 sff8472_rev, addr_mode;
 	bool page_swap = false;
 
@@ -2740,12 +2748,12 @@ static int igb_get_module_info(struct net_device *netdev,
 
 	/* Check whether we support SFF-8472 or not */
 	status = igb_read_phy_reg_i2c(hw, IGB_SFF_8472_COMP, &sff8472_rev);
-	if (status != E1000_SUCCESS)
+	if (status)
 		return -EIO;
 
 	/* addressing mode is not supported */
 	status = igb_read_phy_reg_i2c(hw, IGB_SFF_8472_SWAP, &addr_mode);
-	if (status != E1000_SUCCESS)
+	if (status)
 		return -EIO;
 
 	/* addressing mode is not supported */
@@ -2772,7 +2780,7 @@ static int igb_get_module_eeprom(struct net_device *netdev,
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	u32 status = E1000_SUCCESS;
+	u32 status = 0;
 	u16 *dataword;
 	u16 first_word, last_word;
 	int i = 0;
@@ -2791,7 +2799,7 @@ static int igb_get_module_eeprom(struct net_device *netdev,
 	/* Read EEPROM block, SFF-8079/SFF-8472, word at a time */
 	for (i = 0; i < last_word - first_word + 1; i++) {
 		status = igb_read_phy_reg_i2c(hw, first_word + i, &dataword[i]);
-		if (status != E1000_SUCCESS) {
+		if (status) {
 			/* Error occurred while reading module */
 			kfree(dataword);
 			return -EIO;
@@ -2824,7 +2832,7 @@ static u32 igb_get_rxfh_indir_size(struct net_device *netdev)
 	return IGB_RETA_SIZE;
 }
 
-static int igb_get_rxfh_indir(struct net_device *netdev, u32 *indir)
+static int igb_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	int i;
@@ -2870,7 +2878,8 @@ void igb_write_rss_indir_tbl(struct igb_adapter *adapter)
 	}
 }
 
-static int igb_set_rxfh_indir(struct net_device *netdev, const u32 *indir)
+static int igb_set_rxfh(struct net_device *netdev, const u32 *indir,
+			const u8 *key)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -3019,8 +3028,8 @@ static const struct ethtool_ops igb_ethtool_ops = {
 	.get_module_info	= igb_get_module_info,
 	.get_module_eeprom	= igb_get_module_eeprom,
 	.get_rxfh_indir_size	= igb_get_rxfh_indir_size,
-	.get_rxfh_indir		= igb_get_rxfh_indir,
-	.set_rxfh_indir		= igb_set_rxfh_indir,
+	.get_rxfh		= igb_get_rxfh,
+	.set_rxfh		= igb_set_rxfh,
 	.get_channels		= igb_get_channels,
 	.set_channels		= igb_set_channels,
 	.begin			= igb_ethtool_begin,
@@ -3029,5 +3038,5 @@ static const struct ethtool_ops igb_ethtool_ops = {
 
 void igb_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &igb_ethtool_ops);
+	netdev->ethtool_ops = &igb_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/igb/igb_hwmon.c b/drivers/net/ethernet/intel/igb/igb_hwmon.c
index 8333f67acf9..44b6a68f1af 100644
--- a/drivers/net/ethernet/intel/igb/igb_hwmon.c
+++ b/drivers/net/ethernet/intel/igb/igb_hwmon.c
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #include "igb.h"
 #include "e1000_82575.h"
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 16430a8440f..a9537ba7a5a 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1,28 +1,25 @@
-/*******************************************************************************
-
-  Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2014 Intel Corporation.
-
-  This program is free software; you can redistribute it and/or modify it
-  under the terms and conditions of the GNU General Public License,
-  version 2, as published by the Free Software Foundation.
-
-  This program is distributed in the hope it will be useful, but WITHOUT
-  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-  more details.
-
-  You should have received a copy of the GNU General Public License along with
-  this program; if not, see <http://www.gnu.org/licenses/>.
-
-  The full GNU General Public License is included in this distribution in
-  the file called "COPYING".
-
-  Contact Information:
-  e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
-  Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
-
-*******************************************************************************/
+/* Intel(R) Gigabit Ethernet Linux driver
+ * Copyright(c) 2007-2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * The full GNU General Public License is included in this distribution in
+ * the file called "COPYING".
+ *
+ * Contact Information:
+ * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net>
+ * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
+ */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
@@ -75,7 +72,7 @@ static const struct e1000_info *igb_info_tbl[] = {
 	[board_82575] = &e1000_82575_info,
 };
 
-static DEFINE_PCI_DEVICE_TABLE(igb_pci_tbl) = {
+static const struct pci_device_id igb_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_I354_BACKPLANE_1GBPS) },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_I354_SGMII) },
 	{ PCI_VDEVICE(INTEL, E1000_DEV_ID_I354_BACKPLANE_2_5GBPS) },
@@ -117,7 +114,6 @@ static DEFINE_PCI_DEVICE_TABLE(igb_pci_tbl) = {
 
 MODULE_DEVICE_TABLE(pci, igb_pci_tbl);
 
-void igb_reset(struct igb_adapter *);
 static int igb_setup_all_tx_resources(struct igb_adapter *);
 static int igb_setup_all_rx_resources(struct igb_adapter *);
 static void igb_free_all_tx_resources(struct igb_adapter *);
@@ -141,7 +137,7 @@ static void igb_watchdog(unsigned long);
 static void igb_watchdog_task(struct work_struct *);
 static netdev_tx_t igb_xmit_frame(struct sk_buff *skb, struct net_device *);
 static struct rtnl_link_stats64 *igb_get_stats64(struct net_device *dev,
-						 struct rtnl_link_stats64 *stats);
+					  struct rtnl_link_stats64 *stats);
 static int igb_change_mtu(struct net_device *, int);
 static int igb_set_mac(struct net_device *, void *);
 static void igb_set_uta(struct igb_adapter *adapter);
@@ -159,7 +155,8 @@ static bool igb_clean_rx_irq(struct igb_q_vector *, int);
 static int igb_ioctl(struct net_device *, struct ifreq *, int cmd);
 static void igb_tx_timeout(struct net_device *);
 static void igb_reset_task(struct work_struct *);
-static void igb_vlan_mode(struct net_device *netdev, netdev_features_t features);
+static void igb_vlan_mode(struct net_device *netdev,
+			  netdev_features_t features);
 static int igb_vlan_rx_add_vid(struct net_device *, __be16, u16);
 static int igb_vlan_rx_kill_vid(struct net_device *, __be16, u16);
 static void igb_restore_vlan(struct igb_adapter *);
@@ -172,7 +169,7 @@ static void igb_restore_vf_multicasts(struct igb_adapter *adapter);
 static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac);
 static int igb_ndo_set_vf_vlan(struct net_device *netdev,
 			       int vf, u16 vlan, u8 qos);
-static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate);
+static int igb_ndo_set_vf_bw(struct net_device *, int, int, int);
 static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf,
 				   bool setting);
 static int igb_ndo_get_vf_config(struct net_device *netdev, int vf,
@@ -215,10 +212,9 @@ static struct notifier_block dca_notifier = {
 static void igb_netpoll(struct net_device *);
 #endif
 #ifdef CONFIG_PCI_IOV
-static unsigned int max_vfs = 0;
+static unsigned int max_vfs;
 module_param(max_vfs, uint, 0);
-MODULE_PARM_DESC(max_vfs, "Maximum number of virtual functions to allocate "
-                 "per physical function");
+MODULE_PARM_DESC(max_vfs, "Maximum number of virtual functions to allocate per physical function");
 #endif /* CONFIG_PCI_IOV */
 
 static pci_ers_result_t igb_io_error_detected(struct pci_dev *,
@@ -384,8 +380,7 @@ static void igb_dump(struct igb_adapter *adapter)
 	/* Print netdevice Info */
 	if (netdev) {
 		dev_info(&adapter->pdev->dev, "Net device Info\n");
-		pr_info("Device Name     state            trans_start      "
-			"last_rx\n");
+		pr_info("Device Name     state            trans_start      last_rx\n");
 		pr_info("%-15s %016lX %016lX %016lX\n", netdev->name,
 			netdev->state, netdev->trans_start, netdev->last_rx);
 	}
@@ -438,9 +433,7 @@ static void igb_dump(struct igb_adapter *adapter)
 		pr_info("------------------------------------\n");
 		pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index);
 		pr_info("------------------------------------\n");
-		pr_info("T [desc]     [address 63:0  ] [PlPOCIStDDM Ln] "
-			"[bi->dma       ] leng  ntw timestamp        "
-			"bi->skb\n");
+		pr_info("T [desc]     [address 63:0  ] [PlPOCIStDDM Ln] [bi->dma       ] leng  ntw timestamp        bi->skb\n");
 
 		for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
 			const char *next_desc;
@@ -458,9 +451,8 @@ static void igb_dump(struct igb_adapter *adapter)
 			else
 				next_desc = "";
 
-			pr_info("T [0x%03X]    %016llX %016llX %016llX"
-				" %04X  %p %016llX %p%s\n", i,
-				le64_to_cpu(u0->a),
+			pr_info("T [0x%03X]    %016llX %016llX %016llX %04X  %p %016llX %p%s\n",
+				i, le64_to_cpu(u0->a),
 				le64_to_cpu(u0->b),
 				(u64)dma_unmap_addr(buffer_info, dma),
 				dma_unmap_len(buffer_info, len),
@@ -519,10 +511,8 @@ rx_ring_summary:
 		pr_info("------------------------------------\n");
 		pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
 		pr_info("------------------------------------\n");
-		pr_info("R  [desc]      [ PktBuf     A0] [  HeadBuf   DD] "
-			"[bi->dma       ] [bi->skb] <-- Adv Rx Read format\n");
-		pr_info("RWB[desc]      [PcsmIpSHl PtRs] [vl er S cks ln] -----"
-			"----------- [bi->skb] <-- Adv Rx Write-Back format\n");
+		pr_info("R  [desc]      [ PktBuf     A0] [  HeadBuf   DD] [bi->dma       ] [bi->skb] <-- Adv Rx Read format\n");
+		pr_info("RWB[desc]      [PcsmIpSHl PtRs] [vl er S cks ln] ---------------- [bi->skb] <-- Adv Rx Write-Back format\n");
 
 		for (i = 0; i < rx_ring->count; i++) {
 			const char *next_desc;
@@ -584,7 +574,7 @@ static int igb_get_i2c_data(void *data)
 	struct e1000_hw *hw = &adapter->hw;
 	s32 i2cctl = rd32(E1000_I2CPARAMS);
 
-	return ((i2cctl & E1000_I2C_DATA_IN) != 0);
+	return !!(i2cctl & E1000_I2C_DATA_IN);
 }
 
 /**
@@ -648,7 +638,7 @@ static int igb_get_i2c_clk(void *data)
 	struct e1000_hw *hw = &adapter->hw;
 	s32 i2cctl = rd32(E1000_I2CPARAMS);
 
-	return ((i2cctl & E1000_I2C_CLK_IN) != 0);
+	return !!(i2cctl & E1000_I2C_CLK_IN);
 }
 
 static const struct i2c_algo_bit_data igb_i2c_algo = {
@@ -681,9 +671,9 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw)
 static int __init igb_init_module(void)
 {
 	int ret;
+
 	pr_info("%s - version %s\n",
 	       igb_driver_string, igb_driver_version);
-
 	pr_info("%s\n", igb_copyright);
 
 #ifdef CONFIG_IGB_DCA
@@ -736,12 +726,14 @@ static void igb_cache_ring_register(struct igb_adapter *adapter)
 				adapter->rx_ring[i]->reg_idx = rbase_offset +
 							       Q_IDX_82576(i);
 		}
+		/* Fall through */
 	case e1000_82575:
 	case e1000_82580:
 	case e1000_i350:
 	case e1000_i354:
 	case e1000_i210:
 	case e1000_i211:
+		/* Fall through */
 	default:
 		for (; i < adapter->num_rx_queues; i++)
 			adapter->rx_ring[i]->reg_idx = rbase_offset + i;
@@ -1292,8 +1284,7 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 		if (adapter->hw.mac.type >= e1000_82576)
 			set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags);
 
-		/*
-		 * On i350, i354, i210, and i211, loopback VLAN packets
+		/* On i350, i354, i210, and i211, loopback VLAN packets
 		 * have the tag byte-swapped.
 		 */
 		if (adapter->hw.mac.type >= e1000_i350)
@@ -1345,6 +1336,7 @@ static int igb_alloc_q_vectors(struct igb_adapter *adapter)
 	for (; v_idx < q_vectors; v_idx++) {
 		int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx);
 		int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx);
+
 		err = igb_alloc_q_vector(adapter, q_vectors, v_idx,
 					 tqpv, txr_idx, rqpv, rxr_idx);
 
@@ -1484,6 +1476,7 @@ static void igb_irq_disable(struct igb_adapter *adapter)
 	 */
 	if (adapter->flags & IGB_FLAG_HAS_MSIX) {
 		u32 regval = rd32(E1000_EIAM);
+
 		wr32(E1000_EIAM, regval & ~adapter->eims_enable_mask);
 		wr32(E1000_EIMC, adapter->eims_enable_mask);
 		regval = rd32(E1000_EIAC);
@@ -1495,6 +1488,7 @@ static void igb_irq_disable(struct igb_adapter *adapter)
 	wrfl();
 	if (adapter->flags & IGB_FLAG_HAS_MSIX) {
 		int i;
+
 		for (i = 0; i < adapter->num_q_vectors; i++)
 			synchronize_irq(adapter->msix_entries[i].vector);
 	} else {
@@ -1513,6 +1507,7 @@ static void igb_irq_enable(struct igb_adapter *adapter)
 	if (adapter->flags & IGB_FLAG_HAS_MSIX) {
 		u32 ims = E1000_IMS_LSC | E1000_IMS_DOUTSYNC | E1000_IMS_DRSTA;
 		u32 regval = rd32(E1000_EIAC);
+
 		wr32(E1000_EIAC, regval | adapter->eims_enable_mask);
 		regval = rd32(E1000_EIAM);
 		wr32(E1000_EIAM, regval | adapter->eims_enable_mask);
@@ -1745,6 +1740,7 @@ int igb_up(struct igb_adapter *adapter)
 	/* notify VFs that reset has been completed */
 	if (adapter->vfs_allocated_count) {
 		u32 reg_data = rd32(E1000_CTRL_EXT);
+
 		reg_data |= E1000_CTRL_EXT_PFRSTD;
 		wr32(E1000_CTRL_EXT, reg_data);
 	}
@@ -1787,7 +1783,7 @@ void igb_down(struct igb_adapter *adapter)
 	wr32(E1000_TCTL, tctl);
 	/* flush both disables and wait for them to finish */
 	wrfl();
-	msleep(10);
+	usleep_range(10000, 11000);
 
 	igb_irq_disable(adapter);
 
@@ -1827,7 +1823,7 @@ void igb_reinit_locked(struct igb_adapter *adapter)
 {
 	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
-		msleep(1);
+		usleep_range(1000, 2000);
 	igb_down(adapter);
 	igb_up(adapter);
 	clear_bit(__IGB_RESETTING, &adapter->state);
@@ -1960,6 +1956,7 @@ void igb_reset(struct igb_adapter *adapter)
 	/* disable receive for all VFs and wait one second */
 	if (adapter->vfs_allocated_count) {
 		int i;
+
 		for (i = 0 ; i < adapter->vfs_allocated_count; i++)
 			adapter->vf_data[i].flags &= IGB_VF_FLAG_PF_SET_MAC;
 
@@ -2087,7 +2084,7 @@ static const struct net_device_ops igb_netdev_ops = {
 	.ndo_vlan_rx_kill_vid	= igb_vlan_rx_kill_vid,
 	.ndo_set_vf_mac		= igb_ndo_set_vf_mac,
 	.ndo_set_vf_vlan	= igb_ndo_set_vf_vlan,
-	.ndo_set_vf_tx_rate	= igb_ndo_set_vf_bw,
+	.ndo_set_vf_rate	= igb_ndo_set_vf_bw,
 	.ndo_set_vf_spoofchk	= igb_ndo_set_vf_spoofchk,
 	.ndo_get_vf_config	= igb_ndo_get_vf_config,
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -2142,7 +2139,6 @@ void igb_set_fw_version(struct igb_adapter *adapter)
 		}
 		break;
 	}
-	return;
 }
 
 /**
@@ -2203,11 +2199,11 @@ static void igb_init_mas(struct igb_adapter *adapter)
  **/
 static s32 igb_init_i2c(struct igb_adapter *adapter)
 {
-	s32 status = E1000_SUCCESS;
+	s32 status = 0;
 
 	/* I2C interface supported on i350 devices */
 	if (adapter->hw.mac.type != e1000_i350)
-		return E1000_SUCCESS;
+		return 0;
 
 	/* Initialize the i2c bus which is controlled by the registers.
 	 * This bus will use the i2c_algo_bit structue that implements
@@ -2437,6 +2433,12 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* get firmware version for ethtool -i */
 	igb_set_fw_version(adapter);
 
+	/* configure RXPBSIZE and TXPBSIZE */
+	if (hw->mac.type == e1000_i210) {
+		wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT);
+		wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT);
+	}
+
 	setup_timer(&adapter->watchdog_timer, igb_watchdog,
 		    (unsigned long) adapter);
 	setup_timer(&adapter->phy_info_timer, igb_update_phy_info,
@@ -2529,7 +2531,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	/* let the f/w know that the h/w is now under the control of the
-	 * driver. */
+	 * driver.
+	 */
 	igb_get_hw_control(adapter);
 
 	strcpy(netdev->name, "eth%d");
@@ -3077,6 +3080,7 @@ static int __igb_open(struct net_device *netdev, bool resuming)
 	/* notify VFs that reset has been completed */
 	if (adapter->vfs_allocated_count) {
 		u32 reg_data = rd32(E1000_CTRL_EXT);
+
 		reg_data |= E1000_CTRL_EXT_PFRSTD;
 		wr32(E1000_CTRL_EXT, reg_data);
 	}
@@ -3248,7 +3252,7 @@ void igb_setup_tctl(struct igb_adapter *adapter)
  *  Configure a transmit ring after a reset.
  **/
 void igb_configure_tx_ring(struct igb_adapter *adapter,
-                           struct igb_ring *ring)
+			   struct igb_ring *ring)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 txdctl = 0;
@@ -3389,7 +3393,8 @@ static void igb_setup_mrqc(struct igb_adapter *adapter)
 
 	if (adapter->rss_indir_tbl_init != num_rx_queues) {
 		for (j = 0; j < IGB_RETA_SIZE; j++)
-			adapter->rss_indir_tbl[j] = (j * num_rx_queues) / IGB_RETA_SIZE;
+			adapter->rss_indir_tbl[j] =
+			(j * num_rx_queues) / IGB_RETA_SIZE;
 		adapter->rss_indir_tbl_init = num_rx_queues;
 	}
 	igb_write_rss_indir_tbl(adapter);
@@ -3430,6 +3435,7 @@ static void igb_setup_mrqc(struct igb_adapter *adapter)
 		if (hw->mac.type > e1000_82575) {
 			/* Set the default pool for the PF's first queue */
 			u32 vtctl = rd32(E1000_VT_CTL);
+
 			vtctl &= ~(E1000_VT_CTL_DEFAULT_POOL_MASK |
 				   E1000_VT_CTL_DISABLE_DEF_POOL);
 			vtctl |= adapter->vfs_allocated_count <<
@@ -3511,7 +3517,7 @@ void igb_setup_rctl(struct igb_adapter *adapter)
 }
 
 static inline int igb_set_vf_rlpml(struct igb_adapter *adapter, int size,
-                                   int vfn)
+				   int vfn)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 vmolr;
@@ -4058,7 +4064,8 @@ static void igb_check_wvbr(struct igb_adapter *adapter)
 	switch (hw->mac.type) {
 	case e1000_82576:
 	case e1000_i350:
-		if (!(wvbr = rd32(E1000_WVBR)))
+		wvbr = rd32(E1000_WVBR);
+		if (!wvbr)
 			return;
 		break;
 	default:
@@ -4077,7 +4084,7 @@ static void igb_spoof_check(struct igb_adapter *adapter)
 	if (!adapter->wvbr)
 		return;
 
-	for(j = 0; j < adapter->vfs_allocated_count; j++) {
+	for (j = 0; j < adapter->vfs_allocated_count; j++) {
 		if (adapter->wvbr & (1 << j) ||
 		    adapter->wvbr & (1 << (j + IGB_STAGGERED_QUEUE_OFFSET))) {
 			dev_warn(&adapter->pdev->dev,
@@ -4209,14 +4216,15 @@ static void igb_watchdog_task(struct work_struct *work)
 
 		if (!netif_carrier_ok(netdev)) {
 			u32 ctrl;
+
 			hw->mac.ops.get_speed_and_duplex(hw,
 							 &adapter->link_speed,
 							 &adapter->link_duplex);
 
 			ctrl = rd32(E1000_CTRL);
 			/* Links status message must follow this format */
-			printk(KERN_INFO "igb: %s NIC Link is Up %d Mbps %s "
-			       "Duplex, Flow Control: %s\n",
+			netdev_info(netdev,
+			       "igb: %s NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
 			       netdev->name,
 			       adapter->link_speed,
 			       adapter->link_duplex == FULL_DUPLEX ?
@@ -4242,11 +4250,8 @@ static void igb_watchdog_task(struct work_struct *work)
 
 			/* check for thermal sensor event */
 			if (igb_thermal_sensor_event(hw,
-			    E1000_THSTAT_LINK_THROTTLE)) {
-				netdev_info(netdev, "The network adapter link "
-					    "speed was downshifted because it "
-					    "overheated\n");
-			}
+			    E1000_THSTAT_LINK_THROTTLE))
+				netdev_info(netdev, "The network adapter link speed was downshifted because it overheated\n");
 
 			/* adjust timeout factor according to speed/duplex */
 			adapter->tx_timeout_factor = 1;
@@ -4277,12 +4282,11 @@ static void igb_watchdog_task(struct work_struct *work)
 			/* check for thermal sensor event */
 			if (igb_thermal_sensor_event(hw,
 			    E1000_THSTAT_PWR_DOWN)) {
-				netdev_err(netdev, "The network adapter was "
-					   "stopped because it overheated\n");
+				netdev_err(netdev, "The network adapter was stopped because it overheated\n");
 			}
 
 			/* Links status message must follow this format */
-			printk(KERN_INFO "igb: %s NIC Link is Down\n",
+			netdev_info(netdev, "igb: %s NIC Link is Down\n",
 			       netdev->name);
 			netif_carrier_off(netdev);
 
@@ -4344,6 +4348,7 @@ static void igb_watchdog_task(struct work_struct *work)
 	/* Cause software interrupt to ensure Rx ring is cleaned */
 	if (adapter->flags & IGB_FLAG_HAS_MSIX) {
 		u32 eics = 0;
+
 		for (i = 0; i < adapter->num_q_vectors; i++)
 			eics |= adapter->q_vector[i]->eims_value;
 		wr32(E1000_EICS, eics);
@@ -4483,13 +4488,12 @@ static void igb_update_itr(struct igb_q_vector *q_vector,
 	case low_latency:  /* 50 usec aka 20000 ints/s */
 		if (bytes > 10000) {
 			/* this if handles the TSO accounting */
-			if (bytes/packets > 8000) {
+			if (bytes/packets > 8000)
 				itrval = bulk_latency;
-			} else if ((packets < 10) || ((bytes/packets) > 1200)) {
+			else if ((packets < 10) || ((bytes/packets) > 1200))
 				itrval = bulk_latency;
-			} else if ((packets > 35)) {
+			else if ((packets > 35))
 				itrval = lowest_latency;
-			}
 		} else if (bytes/packets > 2000) {
 			itrval = bulk_latency;
 		} else if (packets <= 2 && bytes < 512) {
@@ -4675,6 +4679,7 @@ static void igb_tx_csum(struct igb_ring *tx_ring, struct igb_tx_buffer *first)
 			return;
 	} else {
 		u8 l4_hdr = 0;
+
 		switch (first->protocol) {
 		case htons(ETH_P_IP):
 			vlan_macip_lens |= skb_network_header_len(skb);
@@ -4962,6 +4967,7 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	 */
 	if (NETDEV_FRAG_PAGE_MAX_SIZE > IGB_MAX_DATA_PER_TXD) {
 		unsigned short f;
+
 		for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
 			count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
 	} else {
@@ -5140,7 +5146,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
 		max_frame = ETH_FRAME_LEN + ETH_FCS_LEN;
 
 	while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
-		msleep(1);
+		usleep_range(1000, 2000);
 
 	/* igb_down has a dependency on max_frame_size */
 	adapter->max_frame_size = max_frame;
@@ -5621,6 +5627,7 @@ static int igb_set_vf_promisc(struct igb_adapter *adapter, u32 *msgbuf, u32 vf)
 			vmolr |= E1000_VMOLR_MPME;
 		} else if (vf_data->num_vf_mc_hashes) {
 			int j;
+
 			vmolr |= E1000_VMOLR_ROMPE;
 			for (j = 0; j < vf_data->num_vf_mc_hashes; j++)
 				igb_mta_set(hw, vf_data->vf_mc_hashes[j]);
@@ -5672,6 +5679,7 @@ static void igb_restore_vf_multicasts(struct igb_adapter *adapter)
 
 	for (i = 0; i < adapter->vfs_allocated_count; i++) {
 		u32 vmolr = rd32(E1000_VMOLR(i));
+
 		vmolr &= ~(E1000_VMOLR_ROMPE | E1000_VMOLR_MPME);
 
 		vf_data = &adapter->vf_data[i];
@@ -5770,6 +5778,7 @@ static s32 igb_vlvf_set(struct igb_adapter *adapter, u32 vid, bool add, u32 vf)
 
 			if (!adapter->vf_data[vf].vlans_enabled) {
 				u32 size;
+
 				reg = rd32(E1000_VMOLR(vf));
 				size = reg & E1000_VMOLR_RLPML_MASK;
 				size += 4;
@@ -5798,6 +5807,7 @@ static s32 igb_vlvf_set(struct igb_adapter *adapter, u32 vid, bool add, u32 vf)
 			adapter->vf_data[vf].vlans_enabled--;
 			if (!adapter->vf_data[vf].vlans_enabled) {
 				u32 size;
+
 				reg = rd32(E1000_VMOLR(vf));
 				size = reg & E1000_VMOLR_RLPML_MASK;
 				size -= 4;
@@ -5902,8 +5912,8 @@ static int igb_set_vf_vlan(struct igb_adapter *adapter, u32 *msgbuf, u32 vf)
 	 */
 	if (!add && (adapter->netdev->flags & IFF_PROMISC)) {
 		u32 vlvf, bits;
-
 		int regndx = igb_find_vlvf_entry(adapter, vid);
+
 		if (regndx < 0)
 			goto out;
 		/* See if any other pools are set for this VLAN filter
@@ -6494,7 +6504,7 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring,
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
 	/* transfer page from old buffer to new buffer */
-	memcpy(new_buff, old_buff, sizeof(struct igb_rx_buffer));
+	*new_buff = *old_buff;
 
 	/* sync the buffer for use by the device */
 	dma_sync_single_range_for_device(rx_ring->dev, old_buff->dma,
@@ -6963,6 +6973,7 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring,
 	if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
 	    igb_test_staterr(rx_desc, E1000_RXD_STAT_VP)) {
 		u16 vid;
+
 		if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) &&
 		    test_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags))
 			vid = be16_to_cpu(rx_desc->wb.upper.vlan);
@@ -7051,7 +7062,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 	if (cleaned_count)
 		igb_alloc_rx_buffers(rx_ring, cleaned_count);
 
-	return (total_packets < budget);
+	return total_packets < budget;
 }
 
 static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
@@ -7172,7 +7183,7 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 		break;
 	case SIOCGMIIREG:
 		if (igb_read_phy_reg(&adapter->hw, data->reg_num & 0x1F,
-		                     &data->val_out))
+				     &data->val_out))
 			return -EIO;
 		break;
 	case SIOCSMIIREG:
@@ -7204,6 +7215,20 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	}
 }
 
+void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value)
+{
+	struct igb_adapter *adapter = hw->back;
+
+	pci_read_config_word(adapter->pdev, reg, value);
+}
+
+void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value)
+{
+	struct igb_adapter *adapter = hw->back;
+
+	pci_write_config_word(adapter->pdev, reg, *value);
+}
+
 s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value)
 {
 	struct igb_adapter *adapter = hw->back;
@@ -7567,6 +7592,8 @@ static int igb_sriov_reinit(struct pci_dev *dev)
 
 	if (netif_running(netdev))
 		igb_close(netdev);
+	else
+		igb_reset(adapter);
 
 	igb_clear_interrupt_scheme(adapter);
 
@@ -7873,7 +7900,8 @@ static void igb_check_vf_rate_limit(struct igb_adapter *adapter)
 	}
 }
 
-static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
+static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf,
+			     int min_tx_rate, int max_tx_rate)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -7882,15 +7910,19 @@ static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
 	if (hw->mac.type != e1000_82576)
 		return -EOPNOTSUPP;
 
+	if (min_tx_rate)
+		return -EINVAL;
+
 	actual_link_speed = igb_link_mbps(adapter->link_speed);
 	if ((vf >= adapter->vfs_allocated_count) ||
 	    (!(rd32(E1000_STATUS) & E1000_STATUS_LU)) ||
-	    (tx_rate < 0) || (tx_rate > actual_link_speed))
+	    (max_tx_rate < 0) ||
+	    (max_tx_rate > actual_link_speed))
 		return -EINVAL;
 
 	adapter->vf_rate_link_speed = actual_link_speed;
-	adapter->vf_data[vf].tx_rate = (u16)tx_rate;
-	igb_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed);
+	adapter->vf_data[vf].tx_rate = (u16)max_tx_rate;
+	igb_set_vf_rate_limit(hw, vf, max_tx_rate, actual_link_speed);
 
 	return 0;
 }
@@ -7919,7 +7951,7 @@ static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf,
 	wr32(reg_offset, reg_val);
 
 	adapter->vf_data[vf].spoofchk_enabled = setting;
-	return E1000_SUCCESS;
+	return 0;
 }
 
 static int igb_ndo_get_vf_config(struct net_device *netdev,
@@ -7930,7 +7962,8 @@ static int igb_ndo_get_vf_config(struct net_device *netdev,
 		return -EINVAL;
 	ivi->vf = vf;
 	memcpy(&ivi->mac, adapter->vf_data[vf].vf_mac_addresses, ETH_ALEN);
-	ivi->tx_rate = adapter->vf_data[vf].tx_rate;
+	ivi->max_tx_rate = adapter->vf_data[vf].tx_rate;
+	ivi->min_tx_rate = 0;
 	ivi->vlan = adapter->vf_data[vf].pf_vlan;
 	ivi->qos = adapter->vf_data[vf].pf_qos;
 	ivi->spoofchk = adapter->vf_data[vf].spoofchk_enabled;
@@ -7955,11 +7988,13 @@ static void igb_vmm_control(struct igb_adapter *adapter)
 		reg = rd32(E1000_DTXCTL);
 		reg |= E1000_DTXCTL_VLAN_ADDED;
 		wr32(E1000_DTXCTL, reg);
+		/* Fall through */
 	case e1000_82580:
 		/* enable replication vlan tag stripping */
 		reg = rd32(E1000_RPLOLR);
 		reg |= E1000_RPLOLR_STRVLAN;
 		wr32(E1000_RPLOLR, reg);
+		/* Fall through */
 	case e1000_i350:
 		/* none of the above registers are supported by i350 */
 		break;
@@ -8049,6 +8084,7 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba)
 		} /* endif adapter->dmac is not disabled */
 	} else if (hw->mac.type == e1000_82580) {
 		u32 reg = rd32(E1000_PCIEMISC);
+
 		wr32(E1000_PCIEMISC, reg & ~E1000_PCIEMISC_LX_DECISION);
 		wr32(E1000_DMACR, 0);
 	}
@@ -8077,8 +8113,7 @@ s32 igb_read_i2c_byte(struct e1000_hw *hw, u8 byte_offset,
 
 	swfw_mask = E1000_SWFW_PHY0_SM;
 
-	if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)
-	    != E1000_SUCCESS)
+	if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask))
 		return E1000_ERR_SWFW_SYNC;
 
 	status = i2c_smbus_read_byte_data(this_client, byte_offset);
@@ -8088,7 +8123,7 @@ s32 igb_read_i2c_byte(struct e1000_hw *hw, u8 byte_offset,
 		return E1000_ERR_I2C;
 	else {
 		*data = status;
-		return E1000_SUCCESS;
+		return 0;
 	}
 }
 
@@ -8113,7 +8148,7 @@ s32 igb_write_i2c_byte(struct e1000_hw *hw, u8 byte_offset,
 	if (!this_client)
 		return E1000_ERR_I2C;
 
-	if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask) != E1000_SUCCESS)
+	if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask))
 		return E1000_ERR_SWFW_SYNC;
 	status = i2c_smbus_write_byte_data(this_client, byte_offset, data);
 	hw->mac.ops.release_swfw_sync(hw, swfw_mask);
@@ -8121,7 +8156,7 @@ s32 igb_write_i2c_byte(struct e1000_hw *hw, u8 byte_offset,
 	if (status)
 		return E1000_ERR_I2C;
 	else
-		return E1000_SUCCESS;
+		return 0;
 
 }
 
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index ab25e49365f..794c139f0cc 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -360,8 +360,8 @@ static int igb_ptp_settime_i210(struct ptp_clock_info *ptp,
 	return 0;
 }
 
-static int igb_ptp_enable(struct ptp_clock_info *ptp,
-			  struct ptp_clock_request *rq, int on)
+static int igb_ptp_feature_enable(struct ptp_clock_info *ptp,
+				  struct ptp_clock_request *rq, int on)
 {
 	return -EOPNOTSUPP;
 }
@@ -559,10 +559,11 @@ int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
 	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
 		-EFAULT : 0;
 }
+
 /**
- * igb_ptp_set_ts_config - control hardware time stamping
- * @netdev:
- * @ifreq:
+ * igb_ptp_set_timestamp_mode - setup hardware for timestamping
+ * @adapter: networking device structure
+ * @config: hwtstamp configuration
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't case any overhead
@@ -575,12 +576,11 @@ int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr)
  * type has to be specified. Matching the kind of event packet is
  * not supported, with the exception of "all V2 events regardless of
  * level 2 or 4".
- **/
-int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
+ */
+static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter,
+				      struct hwtstamp_config *config)
 {
-	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	struct hwtstamp_config *config = &adapter->tstamp_config;
 	u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED;
 	u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED;
 	u32 tsync_rx_cfg = 0;
@@ -588,9 +588,6 @@ int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
 	bool is_l2 = false;
 	u32 regval;
 
-	if (copy_from_user(config, ifr->ifr_data, sizeof(*config)))
-		return -EFAULT;
-
 	/* reserved for future extensions */
 	if (config->flags)
 		return -EINVAL;
@@ -725,7 +722,33 @@ int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
 	regval = rd32(E1000_RXSTMPL);
 	regval = rd32(E1000_RXSTMPH);
 
-	return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ?
+	return 0;
+}
+
+/**
+ * igb_ptp_set_ts_config - set hardware time stamping config
+ * @netdev:
+ * @ifreq:
+ *
+ **/
+int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr)
+{
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct hwtstamp_config config;
+	int err;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	err = igb_ptp_set_timestamp_mode(adapter, &config);
+	if (err)
+		return err;
+
+	/* save these settings for future reference */
+	memcpy(&adapter->tstamp_config, &config,
+	       sizeof(adapter->tstamp_config));
+
+	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
 		-EFAULT : 0;
 }
 
@@ -745,7 +768,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
 		adapter->ptp_caps.gettime = igb_ptp_gettime_82576;
 		adapter->ptp_caps.settime = igb_ptp_settime_82576;
-		adapter->ptp_caps.enable = igb_ptp_enable;
+		adapter->ptp_caps.enable = igb_ptp_feature_enable;
 		adapter->cc.read = igb_ptp_read_82576;
 		adapter->cc.mask = CLOCKSOURCE_MASK(64);
 		adapter->cc.mult = 1;
@@ -765,7 +788,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
 		adapter->ptp_caps.gettime = igb_ptp_gettime_82576;
 		adapter->ptp_caps.settime = igb_ptp_settime_82576;
-		adapter->ptp_caps.enable = igb_ptp_enable;
+		adapter->ptp_caps.enable = igb_ptp_feature_enable;
 		adapter->cc.read = igb_ptp_read_82580;
 		adapter->cc.mask = CLOCKSOURCE_MASK(IGB_NBITS_82580);
 		adapter->cc.mult = 1;
@@ -784,7 +807,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210;
 		adapter->ptp_caps.gettime = igb_ptp_gettime_i210;
 		adapter->ptp_caps.settime = igb_ptp_settime_i210;
-		adapter->ptp_caps.enable = igb_ptp_enable;
+		adapter->ptp_caps.enable = igb_ptp_feature_enable;
 		/* Enable the timer functions by clearing bit 31. */
 		wr32(E1000_TSAUXC, 0x0);
 		break;
@@ -820,6 +843,9 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		wr32(E1000_IMS, E1000_IMS_TS);
 	}
 
+	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+
 	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
 						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
@@ -884,7 +910,7 @@ void igb_ptp_reset(struct igb_adapter *adapter)
 		return;
 
 	/* reset the tstamp_config */
-	memset(&adapter->tstamp_config, 0, sizeof(adapter->tstamp_config));
+	igb_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
 
 	switch (adapter->hw.mac.type) {
 	case e1000_82576:
diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c
index 90eef07943f..2178f87e9f6 100644
--- a/drivers/net/ethernet/intel/igbvf/ethtool.c
+++ b/drivers/net/ethernet/intel/igbvf/ethtool.c
@@ -101,8 +101,8 @@ static int igbvf_get_settings(struct net_device *netdev,
 		else
 			ecmd->duplex = DUPLEX_HALF;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	ecmd->autoneg = AUTONEG_DISABLE;
@@ -119,7 +119,6 @@ static int igbvf_set_settings(struct net_device *netdev,
 static void igbvf_get_pauseparam(struct net_device *netdev,
                                  struct ethtool_pauseparam *pause)
 {
-	return;
 }
 
 static int igbvf_set_pauseparam(struct net_device *netdev,
@@ -476,5 +475,5 @@ static const struct ethtool_ops igbvf_ethtool_ops = {
 
 void igbvf_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &igbvf_ethtool_ops);
+	netdev->ethtool_ops = &igbvf_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
index dbb7dd2f8e3..b311e9e710d 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
@@ -107,8 +107,8 @@ ixgb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		ethtool_cmd_speed_set(ecmd, SPEED_10000);
 		ecmd->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	ecmd->autoneg = AUTONEG_DISABLE;
@@ -656,5 +656,5 @@ static const struct ethtool_ops ixgb_ethtool_ops = {
 
 void ixgb_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &ixgb_ethtool_ops);
+	netdev->ethtool_ops = &ixgb_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index c6c4ca7d68e..ac9f2148cdc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -155,7 +155,6 @@ struct vf_data_storage {
 struct vf_macvlans {
 	struct list_head l;
 	int vf;
-	int rar_entry;
 	bool free;
 	bool is_macvlan;
 	u8 vf_macvlan[ETH_ALEN];
@@ -363,7 +362,7 @@ struct ixgbe_ring_container {
 	for (pos = (head).ring; pos != NULL; pos = pos->next)
 
 #define MAX_RX_PACKET_BUFFERS ((adapter->flags & IXGBE_FLAG_DCB_ENABLED) \
-                              ? 8 : 1)
+			      ? 8 : 1)
 #define MAX_TX_PACKET_BUFFERS MAX_RX_PACKET_BUFFERS
 
 /* MAX_Q_VECTORS of these are allocated,
@@ -613,6 +612,15 @@ static inline void ixgbe_write_tail(struct ixgbe_ring *ring, u32 value)
 #define MAX_MSIX_VECTORS_82598 18
 #define MAX_Q_VECTORS_82598 16
 
+struct ixgbe_mac_addr {
+	u8 addr[ETH_ALEN];
+	u16 queue;
+	u16 state; /* bitmask */
+};
+#define IXGBE_MAC_STATE_DEFAULT		0x1
+#define IXGBE_MAC_STATE_MODIFIED	0x2
+#define IXGBE_MAC_STATE_IN_USE		0x4
+
 #define MAX_Q_VECTORS MAX_Q_VECTORS_82599
 #define MAX_MSIX_COUNT MAX_MSIX_VECTORS_82599
 
@@ -785,6 +793,7 @@ struct ixgbe_adapter {
 
 	u32 timer_event_accumulator;
 	u32 vferr_refcount;
+	struct ixgbe_mac_addr *mac_table;
 	struct kobject *info_kobj;
 #ifdef CONFIG_IXGBE_HWMON
 	struct hwmon_buff *ixgbe_hwmon_buff;
@@ -863,6 +872,13 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter);
 int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter);
 int ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
 			       u16 subdevice_id);
+#ifdef CONFIG_PCI_IOV
+void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter);
+#endif
+int ixgbe_add_mac_filter(struct ixgbe_adapter *adapter,
+			 u8 *addr, u16 queue);
+int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter,
+			 u8 *addr, u16 queue);
 void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter);
 netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *, struct ixgbe_adapter *,
 				  struct ixgbe_ring *);
@@ -941,6 +957,7 @@ static inline struct netdev_queue *txring_txq(const struct ixgbe_ring *ring)
 }
 
 void ixgbe_ptp_init(struct ixgbe_adapter *adapter);
+void ixgbe_ptp_suspend(struct ixgbe_adapter *adapter);
 void ixgbe_ptp_stop(struct ixgbe_adapter *adapter);
 void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter);
 void ixgbe_ptp_rx_hang(struct ixgbe_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
index 4c78ea8946c..15609331ec1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c
@@ -41,10 +41,10 @@
 #define IXGBE_82598_RX_PB_SIZE	 512
 
 static s32 ixgbe_setup_copper_link_82598(struct ixgbe_hw *hw,
-                                         ixgbe_link_speed speed,
-                                         bool autoneg_wait_to_complete);
+					 ixgbe_link_speed speed,
+					 bool autoneg_wait_to_complete);
 static s32 ixgbe_read_i2c_eeprom_82598(struct ixgbe_hw *hw, u8 byte_offset,
-                                       u8 *eeprom_data);
+				       u8 *eeprom_data);
 
 /**
  *  ixgbe_set_pcie_completion_timeout - set pci-e completion timeout
@@ -140,7 +140,7 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw)
 		phy->ops.setup_link = &ixgbe_setup_phy_link_tnx;
 		phy->ops.check_link = &ixgbe_check_phy_link_tnx;
 		phy->ops.get_firmware_version =
-		             &ixgbe_get_phy_firmware_version_tnx;
+			     &ixgbe_get_phy_firmware_version_tnx;
 		break;
 	case ixgbe_phy_nl:
 		phy->ops.reset = &ixgbe_reset_phy_nl;
@@ -156,8 +156,8 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw)
 
 		/* Check to see if SFP+ module is supported */
 		ret_val = ixgbe_get_sfp_init_sequence_offsets(hw,
-		                                            &list_offset,
-		                                            &data_offset);
+							    &list_offset,
+							    &data_offset);
 		if (ret_val != 0) {
 			ret_val = IXGBE_ERR_SFP_NOT_SUPPORTED;
 			goto out;
@@ -219,8 +219,8 @@ static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw)
  *  Determines the link capabilities by reading the AUTOC register.
  **/
 static s32 ixgbe_get_link_capabilities_82598(struct ixgbe_hw *hw,
-                                             ixgbe_link_speed *speed,
-                                             bool *autoneg)
+					     ixgbe_link_speed *speed,
+					     bool *autoneg)
 {
 	s32 status = 0;
 	u32 autoc = 0;
@@ -337,19 +337,25 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw)
 	int i;
 	bool link_up;
 
-	/*
-	 * Validate the water mark configuration for packet buffer 0.  Zero
-	 * water marks indicate that the packet buffer was not configured
-	 * and the watermarks for packet buffer 0 should always be configured.
-	 */
-	if (!hw->fc.low_water ||
-	    !hw->fc.high_water[0] ||
-	    !hw->fc.pause_time) {
-		hw_dbg(hw, "Invalid water mark configuration\n");
+	/* Validate the water mark configuration */
+	if (!hw->fc.pause_time) {
 		ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS;
 		goto out;
 	}
 
+	/* Low water mark of zero causes XOFF floods */
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		if ((hw->fc.current_mode & ixgbe_fc_tx_pause) &&
+		    hw->fc.high_water[i]) {
+			if (!hw->fc.low_water[i] ||
+			    hw->fc.low_water[i] >= hw->fc.high_water[i]) {
+				hw_dbg(hw, "Invalid water mark configuration\n");
+				ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS;
+				goto out;
+			}
+		}
+	}
+
 	/*
 	 * On 82598 having Rx FC on causes resets while doing 1G
 	 * so if it's on turn it off once we know link_speed. For
@@ -432,12 +438,11 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw)
 	IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl_reg);
 	IXGBE_WRITE_REG(hw, IXGBE_RMCS, rmcs_reg);
 
-	fcrtl = (hw->fc.low_water << 10) | IXGBE_FCRTL_XONE;
-
 	/* Set up and enable Rx high/low water mark thresholds, enable XON. */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
 		if ((hw->fc.current_mode & ixgbe_fc_tx_pause) &&
 		    hw->fc.high_water[i]) {
+			fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE;
 			fcrth = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN;
 			IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), fcrtl);
 			IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), fcrth);
@@ -468,7 +473,7 @@ out:
  *  Restarts the link.  Performs autonegotiation if needed.
  **/
 static s32 ixgbe_start_mac_link_82598(struct ixgbe_hw *hw,
-                                      bool autoneg_wait_to_complete)
+				      bool autoneg_wait_to_complete)
 {
 	u32 autoc_reg;
 	u32 links_reg;
@@ -550,8 +555,8 @@ static s32 ixgbe_validate_link_ready(struct ixgbe_hw *hw)
  *  Reads the links register to determine if link is up and the current speed
  **/
 static s32 ixgbe_check_mac_link_82598(struct ixgbe_hw *hw,
-                                      ixgbe_link_speed *speed, bool *link_up,
-                                      bool link_up_wait_to_complete)
+				      ixgbe_link_speed *speed, bool *link_up,
+				      bool link_up_wait_to_complete)
 {
 	u32 links_reg;
 	u32 i;
@@ -567,7 +572,7 @@ static s32 ixgbe_check_mac_link_82598(struct ixgbe_hw *hw,
 		hw->phy.ops.read_reg(hw, 0xC79F, MDIO_MMD_PMAPMD, &link_reg);
 		hw->phy.ops.read_reg(hw, 0xC79F, MDIO_MMD_PMAPMD, &link_reg);
 		hw->phy.ops.read_reg(hw, 0xC00C, MDIO_MMD_PMAPMD,
-		                     &adapt_comp_reg);
+				     &adapt_comp_reg);
 		if (link_up_wait_to_complete) {
 			for (i = 0; i < IXGBE_LINK_UP_TIME; i++) {
 				if ((link_reg & 1) &&
@@ -579,11 +584,11 @@ static s32 ixgbe_check_mac_link_82598(struct ixgbe_hw *hw,
 				}
 				msleep(100);
 				hw->phy.ops.read_reg(hw, 0xC79F,
-				                     MDIO_MMD_PMAPMD,
-				                     &link_reg);
+						     MDIO_MMD_PMAPMD,
+						     &link_reg);
 				hw->phy.ops.read_reg(hw, 0xC00C,
-				                     MDIO_MMD_PMAPMD,
-				                     &adapt_comp_reg);
+						     MDIO_MMD_PMAPMD,
+						     &adapt_comp_reg);
 			}
 		} else {
 			if ((link_reg & 1) && ((adapt_comp_reg & 1) == 0))
@@ -656,7 +661,7 @@ static s32 ixgbe_setup_mac_link_82598(struct ixgbe_hw *hw,
 
 	/* Set KX4/KX support according to speed requested */
 	else if (link_mode == IXGBE_AUTOC_LMS_KX4_AN ||
-	         link_mode == IXGBE_AUTOC_LMS_KX4_AN_1G_AN) {
+		 link_mode == IXGBE_AUTOC_LMS_KX4_AN_1G_AN) {
 		autoc &= ~IXGBE_AUTOC_KX4_KX_SUPP_MASK;
 		if (speed & IXGBE_LINK_SPEED_10GB_FULL)
 			autoc |= IXGBE_AUTOC_KX4_SUPP;
@@ -689,14 +694,14 @@ static s32 ixgbe_setup_mac_link_82598(struct ixgbe_hw *hw,
  *  Sets the link speed in the AUTOC register in the MAC and restarts link.
  **/
 static s32 ixgbe_setup_copper_link_82598(struct ixgbe_hw *hw,
-                                               ixgbe_link_speed speed,
-                                               bool autoneg_wait_to_complete)
+					       ixgbe_link_speed speed,
+					       bool autoneg_wait_to_complete)
 {
 	s32 status;
 
 	/* Setup the PHY according to input speed */
 	status = hw->phy.ops.setup_link_speed(hw, speed,
-	                                      autoneg_wait_to_complete);
+					      autoneg_wait_to_complete);
 	/* Set up MAC */
 	ixgbe_start_mac_link_82598(hw, autoneg_wait_to_complete);
 
@@ -735,28 +740,28 @@ static s32 ixgbe_reset_hw_82598(struct ixgbe_hw *hw)
 	if (analog_val & IXGBE_ATLAS_PDN_TX_REG_EN) {
 		/* Enable Tx Atlas so packets can be transmitted again */
 		hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_LPBK,
-		                             &analog_val);
+					     &analog_val);
 		analog_val &= ~IXGBE_ATLAS_PDN_TX_REG_EN;
 		hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_LPBK,
-		                              analog_val);
+					      analog_val);
 
 		hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_10G,
-		                             &analog_val);
+					     &analog_val);
 		analog_val &= ~IXGBE_ATLAS_PDN_TX_10G_QL_ALL;
 		hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_10G,
-		                              analog_val);
+					      analog_val);
 
 		hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_1G,
-		                             &analog_val);
+					     &analog_val);
 		analog_val &= ~IXGBE_ATLAS_PDN_TX_1G_QL_ALL;
 		hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_1G,
-		                              analog_val);
+					      analog_val);
 
 		hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_AN,
-		                             &analog_val);
+					     &analog_val);
 		analog_val &= ~IXGBE_ATLAS_PDN_TX_AN_QL_ALL;
 		hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_AN,
-		                              analog_val);
+					      analog_val);
 	}
 
 	/* Reset PHY */
@@ -955,7 +960,7 @@ static s32 ixgbe_clear_vfta_82598(struct ixgbe_hw *hw)
 	for (vlanbyte = 0; vlanbyte < 4; vlanbyte++)
 		for (offset = 0; offset < hw->mac.vft_size; offset++)
 			IXGBE_WRITE_REG(hw, IXGBE_VFTAVIND(vlanbyte, offset),
-			                0);
+					0);
 
 	return 0;
 }
@@ -973,7 +978,7 @@ static s32 ixgbe_read_analog_reg8_82598(struct ixgbe_hw *hw, u32 reg, u8 *val)
 	u32  atlas_ctl;
 
 	IXGBE_WRITE_REG(hw, IXGBE_ATLASCTL,
-	                IXGBE_ATLASCTL_WRITE_CMD | (reg << 8));
+			IXGBE_ATLASCTL_WRITE_CMD | (reg << 8));
 	IXGBE_WRITE_FLUSH(hw);
 	udelay(10);
 	atlas_ctl = IXGBE_READ_REG(hw, IXGBE_ATLASCTL);
@@ -1273,8 +1278,6 @@ static void ixgbe_set_rxpba_82598(struct ixgbe_hw *hw, int num_pb,
 	/* Setup Tx packet buffer sizes */
 	for (i = 0; i < IXGBE_MAX_PACKET_BUFFERS; i++)
 		IXGBE_WRITE_REG(hw, IXGBE_TXPBSIZE(i), IXGBE_TXPBSIZE_40KB);
-
-	return;
 }
 
 static struct ixgbe_mac_operations mac_ops_82598 = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index f32b3dd1ba8..bc7c924240a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -48,17 +48,17 @@ static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw,
 						 ixgbe_link_speed speed,
 						 bool autoneg_wait_to_complete);
 static s32 ixgbe_setup_mac_link_smartspeed(struct ixgbe_hw *hw,
-                                           ixgbe_link_speed speed,
-                                           bool autoneg_wait_to_complete);
+					   ixgbe_link_speed speed,
+					   bool autoneg_wait_to_complete);
 static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw);
 static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw,
 				      bool autoneg_wait_to_complete);
 static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw,
-                               ixgbe_link_speed speed,
-                               bool autoneg_wait_to_complete);
+			       ixgbe_link_speed speed,
+			       bool autoneg_wait_to_complete);
 static s32 ixgbe_setup_copper_link_82599(struct ixgbe_hw *hw,
-                                         ixgbe_link_speed speed,
-                                         bool autoneg_wait_to_complete);
+					 ixgbe_link_speed speed,
+					 bool autoneg_wait_to_complete);
 static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw);
 static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset,
 				     u8 dev_addr, u8 *data);
@@ -96,9 +96,9 @@ static void ixgbe_init_mac_link_ops_82599(struct ixgbe_hw *hw)
 	if ((mac->ops.get_media_type(hw) == ixgbe_media_type_fiber) &&
 	    !ixgbe_mng_enabled(hw)) {
 		mac->ops.disable_tx_laser =
-		                       &ixgbe_disable_tx_laser_multispeed_fiber;
+				       &ixgbe_disable_tx_laser_multispeed_fiber;
 		mac->ops.enable_tx_laser =
-		                        &ixgbe_enable_tx_laser_multispeed_fiber;
+					&ixgbe_enable_tx_laser_multispeed_fiber;
 		mac->ops.flap_tx_laser = &ixgbe_flap_tx_laser_multispeed_fiber;
 	} else {
 		mac->ops.disable_tx_laser = NULL;
@@ -132,13 +132,13 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw)
 		hw->phy.ops.reset = NULL;
 
 		ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, &list_offset,
-		                                              &data_offset);
+							      &data_offset);
 		if (ret_val != 0)
 			goto setup_sfp_out;
 
 		/* PHY config will finish before releasing the semaphore */
 		ret_val = hw->mac.ops.acquire_swfw_sync(hw,
-		                                        IXGBE_GSSR_MAC_CSR_SM);
+							IXGBE_GSSR_MAC_CSR_SM);
 		if (ret_val != 0) {
 			ret_val = IXGBE_ERR_SWFW_SYNC;
 			goto setup_sfp_out;
@@ -334,7 +334,7 @@ static s32 ixgbe_init_phy_ops_82599(struct ixgbe_hw *hw)
 		phy->ops.check_link = &ixgbe_check_phy_link_tnx;
 		phy->ops.setup_link = &ixgbe_setup_phy_link_tnx;
 		phy->ops.get_firmware_version =
-		             &ixgbe_get_phy_firmware_version_tnx;
+			     &ixgbe_get_phy_firmware_version_tnx;
 		break;
 	default:
 		break;
@@ -352,7 +352,7 @@ static s32 ixgbe_init_phy_ops_82599(struct ixgbe_hw *hw)
  *  Determines the link capabilities by reading the AUTOC register.
  **/
 static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw,
-                                             ixgbe_link_speed *speed,
+					     ixgbe_link_speed *speed,
 					     bool *autoneg)
 {
 	s32 status = 0;
@@ -543,7 +543,7 @@ static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw)
  *  Restarts the link.  Performs autonegotiation if needed.
  **/
 static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw,
-                               bool autoneg_wait_to_complete)
+			       bool autoneg_wait_to_complete)
 {
 	u32 autoc_reg;
 	u32 links_reg;
@@ -672,8 +672,8 @@ static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw)
  *  Set the link speed in the AUTOC register and restarts link.
  **/
 static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw,
-                                          ixgbe_link_speed speed,
-                                          bool autoneg_wait_to_complete)
+					  ixgbe_link_speed speed,
+					  bool autoneg_wait_to_complete)
 {
 	s32 status = 0;
 	ixgbe_link_speed link_speed = IXGBE_LINK_SPEED_UNKNOWN;
@@ -820,8 +820,8 @@ static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw,
 	 */
 	if (speedcnt > 1)
 		status = ixgbe_setup_mac_link_multispeed_fiber(hw,
-		                                               highest_link_speed,
-		                                               autoneg_wait_to_complete);
+							       highest_link_speed,
+							       autoneg_wait_to_complete);
 
 out:
 	/* Set autoneg_advertised value based on input link speed */
@@ -1009,8 +1009,8 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw,
 		if (speed & IXGBE_LINK_SPEED_1GB_FULL)
 			autoc |= IXGBE_AUTOC_KX_SUPP;
 	} else if ((pma_pmd_1g == IXGBE_AUTOC_1G_SFI) &&
-	           (link_mode == IXGBE_AUTOC_LMS_1G_LINK_NO_AN ||
-	            link_mode == IXGBE_AUTOC_LMS_1G_AN)) {
+		   (link_mode == IXGBE_AUTOC_LMS_1G_LINK_NO_AN ||
+		    link_mode == IXGBE_AUTOC_LMS_1G_AN)) {
 		/* Switch from 1G SFI to 10G SFI if requested */
 		if ((speed == IXGBE_LINK_SPEED_10GB_FULL) &&
 		    (pma_pmd_10g_serial == IXGBE_AUTOC2_10G_SFI)) {
@@ -1018,7 +1018,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw,
 			autoc |= IXGBE_AUTOC_LMS_10G_SERIAL;
 		}
 	} else if ((pma_pmd_10g_serial == IXGBE_AUTOC2_10G_SFI) &&
-	           (link_mode == IXGBE_AUTOC_LMS_10G_SERIAL)) {
+		   (link_mode == IXGBE_AUTOC_LMS_10G_SERIAL)) {
 		/* Switch from 10G SFI to 1G SFI if requested */
 		if ((speed == IXGBE_LINK_SPEED_1GB_FULL) &&
 		    (pma_pmd_1g == IXGBE_AUTOC_1G_SFI)) {
@@ -1051,7 +1051,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw,
 				}
 				if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) {
 					status =
-					        IXGBE_ERR_AUTONEG_NOT_COMPLETE;
+						IXGBE_ERR_AUTONEG_NOT_COMPLETE;
 					hw_dbg(hw, "Autoneg did not complete.\n");
 				}
 			}
@@ -1074,14 +1074,14 @@ out:
  *  Restarts link on PHY and MAC based on settings passed in.
  **/
 static s32 ixgbe_setup_copper_link_82599(struct ixgbe_hw *hw,
-                                         ixgbe_link_speed speed,
-                                         bool autoneg_wait_to_complete)
+					 ixgbe_link_speed speed,
+					 bool autoneg_wait_to_complete)
 {
 	s32 status;
 
 	/* Setup the PHY according to input speed */
 	status = hw->phy.ops.setup_link_speed(hw, speed,
-	                                      autoneg_wait_to_complete);
+					      autoneg_wait_to_complete);
 	/* Set up MAC */
 	ixgbe_start_mac_link_82599(hw, autoneg_wait_to_complete);
 
@@ -1224,7 +1224,7 @@ mac_reset_top:
 		    (hw->mac.orig_autoc2 & IXGBE_AUTOC2_UPPER_MASK)) {
 			autoc2 &= ~IXGBE_AUTOC2_UPPER_MASK;
 			autoc2 |= (hw->mac.orig_autoc2 &
-			           IXGBE_AUTOC2_UPPER_MASK);
+				   IXGBE_AUTOC2_UPPER_MASK);
 			IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2);
 		}
 	}
@@ -1246,7 +1246,7 @@ mac_reset_top:
 	/* Add the SAN MAC address to the RAR only if it's a valid address */
 	if (is_valid_ether_addr(hw->mac.san_addr)) {
 		hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1,
-		                    hw->mac.san_addr, 0, IXGBE_RAH_AV);
+				    hw->mac.san_addr, 0, IXGBE_RAH_AV);
 
 		/* Save the SAN MAC RAR index */
 		hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1;
@@ -1257,7 +1257,7 @@ mac_reset_top:
 
 	/* Store the alternative WWNN/WWPN prefix */
 	hw->mac.ops.get_wwn_prefix(hw, &hw->mac.wwnn_prefix,
-	                               &hw->mac.wwpn_prefix);
+				       &hw->mac.wwpn_prefix);
 
 reset_hw_out:
 	return status;
@@ -1271,6 +1271,7 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw)
 {
 	int i;
 	u32 fdirctrl = IXGBE_READ_REG(hw, IXGBE_FDIRCTRL);
+
 	fdirctrl &= ~IXGBE_FDIRCTRL_INIT_DONE;
 
 	/*
@@ -1284,8 +1285,7 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw)
 		udelay(10);
 	}
 	if (i >= IXGBE_FDIRCMD_CMD_POLL) {
-		hw_dbg(hw, "Flow Director previous command isn't complete, "
-		       "aborting table re-initialization.\n");
+		hw_dbg(hw, "Flow Director previous command isn't complete, aborting table re-initialization.\n");
 		return IXGBE_ERR_FDIR_REINIT_FAILED;
 	}
 
@@ -1299,12 +1299,12 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw)
 	 * - write 0 to bit 8 of FDIRCMD register
 	 */
 	IXGBE_WRITE_REG(hw, IXGBE_FDIRCMD,
-	                (IXGBE_READ_REG(hw, IXGBE_FDIRCMD) |
-	                 IXGBE_FDIRCMD_CLEARHT));
+			(IXGBE_READ_REG(hw, IXGBE_FDIRCMD) |
+			 IXGBE_FDIRCMD_CLEARHT));
 	IXGBE_WRITE_FLUSH(hw);
 	IXGBE_WRITE_REG(hw, IXGBE_FDIRCMD,
-	                (IXGBE_READ_REG(hw, IXGBE_FDIRCMD) &
-	                 ~IXGBE_FDIRCMD_CLEARHT));
+			(IXGBE_READ_REG(hw, IXGBE_FDIRCMD) &
+			 ~IXGBE_FDIRCMD_CLEARHT));
 	IXGBE_WRITE_FLUSH(hw);
 	/*
 	 * Clear FDIR Hash register to clear any leftover hashes
@@ -1319,7 +1319,7 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw)
 	/* Poll init-done after we write FDIRCTRL register */
 	for (i = 0; i < IXGBE_FDIR_INIT_DONE_POLL; i++) {
 		if (IXGBE_READ_REG(hw, IXGBE_FDIRCTRL) &
-		                   IXGBE_FDIRCTRL_INIT_DONE)
+				   IXGBE_FDIRCTRL_INIT_DONE)
 			break;
 		usleep_range(1000, 2000);
 	}
@@ -1368,7 +1368,7 @@ static void ixgbe_fdir_enable_82599(struct ixgbe_hw *hw, u32 fdirctrl)
 	IXGBE_WRITE_FLUSH(hw);
 	for (i = 0; i < IXGBE_FDIR_INIT_DONE_POLL; i++) {
 		if (IXGBE_READ_REG(hw, IXGBE_FDIRCTRL) &
-		                   IXGBE_FDIRCTRL_INIT_DONE)
+				   IXGBE_FDIRCTRL_INIT_DONE)
 			break;
 		usleep_range(1000, 2000);
 	}
@@ -1453,7 +1453,7 @@ do { \
 		bucket_hash ^= hi_hash_dword >> n; \
 	else if (IXGBE_ATR_SIGNATURE_HASH_KEY & (0x01 << (n + 16))) \
 		sig_hash ^= hi_hash_dword << (16 - n); \
-} while (0);
+} while (0)
 
 /**
  *  ixgbe_atr_compute_sig_hash_82599 - Compute the signature hash
@@ -1529,9 +1529,9 @@ static u32 ixgbe_atr_compute_sig_hash_82599(union ixgbe_atr_hash_dword input,
  *  @queue: queue index to direct traffic to
  **/
 s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
-                                          union ixgbe_atr_hash_dword input,
-                                          union ixgbe_atr_hash_dword common,
-                                          u8 queue)
+					  union ixgbe_atr_hash_dword input,
+					  union ixgbe_atr_hash_dword common,
+					  u8 queue)
 {
 	u64  fdirhashcmd;
 	u32  fdircmd;
@@ -1555,7 +1555,7 @@ s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw,
 
 	/* configure FDIRCMD register */
 	fdircmd = IXGBE_FDIRCMD_CMD_ADD_FLOW | IXGBE_FDIRCMD_FILTER_UPDATE |
-	          IXGBE_FDIRCMD_LAST | IXGBE_FDIRCMD_QUEUE_EN;
+		  IXGBE_FDIRCMD_LAST | IXGBE_FDIRCMD_QUEUE_EN;
 	fdircmd |= input.formatted.flow_type << IXGBE_FDIRCMD_FLOW_TYPE_SHIFT;
 	fdircmd |= (u32)queue << IXGBE_FDIRCMD_RX_QUEUE_SHIFT;
 
@@ -1579,7 +1579,7 @@ do { \
 		bucket_hash ^= lo_hash_dword >> n; \
 	if (IXGBE_ATR_BUCKET_HASH_KEY & (0x01 << (n + 16))) \
 		bucket_hash ^= hi_hash_dword >> n; \
-} while (0);
+} while (0)
 
 /**
  *  ixgbe_atr_compute_perfect_hash_82599 - Compute the perfect filter hash
@@ -1651,6 +1651,7 @@ void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input,
 static u32 ixgbe_get_fdirtcpm_82599(union ixgbe_atr_input *input_mask)
 {
 	u32 mask = ntohs(input_mask->formatted.dst_port);
+
 	mask <<= IXGBE_FDIRTCPM_DPORTM_SHIFT;
 	mask |= ntohs(input_mask->formatted.src_port);
 	mask = ((mask & 0x55555555) << 1) | ((mask & 0xAAAAAAAA) >> 1);
@@ -1885,7 +1886,7 @@ static s32 ixgbe_read_analog_reg8_82599(struct ixgbe_hw *hw, u32 reg, u8 *val)
 	u32  core_ctl;
 
 	IXGBE_WRITE_REG(hw, IXGBE_CORECTL, IXGBE_CORECTL_WRITE_CMD |
-	                (reg << 8));
+			(reg << 8));
 	IXGBE_WRITE_FLUSH(hw);
 	udelay(10);
 	core_ctl = IXGBE_READ_REG(hw, IXGBE_CORECTL);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 981b8a7b100..4e5385a2a46 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -41,7 +41,7 @@ static void ixgbe_release_eeprom_semaphore(struct ixgbe_hw *hw);
 static s32 ixgbe_ready_eeprom(struct ixgbe_hw *hw);
 static void ixgbe_standby_eeprom(struct ixgbe_hw *hw);
 static void ixgbe_shift_out_eeprom_bits(struct ixgbe_hw *hw, u16 data,
-                                        u16 count);
+					u16 count);
 static u16 ixgbe_shift_in_eeprom_bits(struct ixgbe_hw *hw, u16 count);
 static void ixgbe_raise_eeprom_clk(struct ixgbe_hw *hw, u32 *eec);
 static void ixgbe_lower_eeprom_clk(struct ixgbe_hw *hw, u32 *eec);
@@ -271,6 +271,7 @@ out:
  **/
 s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw)
 {
+	s32 ret_val;
 	u32 ctrl_ext;
 
 	/* Set the media type */
@@ -292,12 +293,15 @@ s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw)
 	IXGBE_WRITE_FLUSH(hw);
 
 	/* Setup flow control */
-	ixgbe_setup_fc(hw);
+	ret_val = ixgbe_setup_fc(hw);
+	if (!ret_val)
+		goto out;
 
 	/* Clear adapter stopped flag */
 	hw->adapter_stopped = false;
 
-	return 0;
+out:
+	return ret_val;
 }
 
 /**
@@ -481,7 +485,7 @@ s32 ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw)
  *  Reads the part number string from the EEPROM.
  **/
 s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num,
-                                  u32 pba_num_size)
+				  u32 pba_num_size)
 {
 	s32 ret_val;
 	u16 data;
@@ -814,9 +818,8 @@ s32 ixgbe_init_eeprom_params_generic(struct ixgbe_hw *hw)
 			eeprom->address_bits = 16;
 		else
 			eeprom->address_bits = 8;
-		hw_dbg(hw, "Eeprom params: type = %d, size = %d, address bits: "
-			  "%d\n", eeprom->type, eeprom->word_size,
-			  eeprom->address_bits);
+		hw_dbg(hw, "Eeprom params: type = %d, size = %d, address bits: %d\n",
+		       eeprom->type, eeprom->word_size, eeprom->address_bits);
 	}
 
 	return 0;
@@ -1388,8 +1391,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw)
 	}
 
 	if (i == timeout) {
-		hw_dbg(hw, "Driver can't access the Eeprom - SMBI Semaphore "
-		       "not granted.\n");
+		hw_dbg(hw, "Driver can't access the Eeprom - SMBI Semaphore not granted.\n");
 		/*
 		 * this release is particularly important because our attempts
 		 * above to get the semaphore may have succeeded, and if there
@@ -1434,14 +1436,12 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw)
 		 * was not granted because we don't have access to the EEPROM
 		 */
 		if (i >= timeout) {
-			hw_dbg(hw, "SWESMBI Software EEPROM semaphore "
-			       "not granted.\n");
+			hw_dbg(hw, "SWESMBI Software EEPROM semaphore not granted.\n");
 			ixgbe_release_eeprom_semaphore(hw);
 			status = IXGBE_ERR_EEPROM;
 		}
 	} else {
-		hw_dbg(hw, "Software semaphore SMBI between device drivers "
-		       "not granted.\n");
+		hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n");
 	}
 
 	return status;
@@ -1483,7 +1483,7 @@ static s32 ixgbe_ready_eeprom(struct ixgbe_hw *hw)
 	 */
 	for (i = 0; i < IXGBE_EEPROM_MAX_RETRY_SPI; i += 5) {
 		ixgbe_shift_out_eeprom_bits(hw, IXGBE_EEPROM_RDSR_OPCODE_SPI,
-		                            IXGBE_EEPROM_OPCODE_BITS);
+					    IXGBE_EEPROM_OPCODE_BITS);
 		spi_stat_reg = (u8)ixgbe_shift_in_eeprom_bits(hw, 8);
 		if (!(spi_stat_reg & IXGBE_EEPROM_STATUS_RDY_SPI))
 			break;
@@ -1532,7 +1532,7 @@ static void ixgbe_standby_eeprom(struct ixgbe_hw *hw)
  *  @count: number of bits to shift out
  **/
 static void ixgbe_shift_out_eeprom_bits(struct ixgbe_hw *hw, u16 data,
-                                        u16 count)
+					u16 count)
 {
 	u32 eec;
 	u32 mask;
@@ -1736,7 +1736,7 @@ u16 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw)
  *  caller does not need checksum_val, the value can be NULL.
  **/
 s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw,
-                                           u16 *checksum_val)
+					   u16 *checksum_val)
 {
 	s32 status;
 	u16 checksum;
@@ -1809,7 +1809,7 @@ s32 ixgbe_update_eeprom_checksum_generic(struct ixgbe_hw *hw)
  *  Puts an ethernet address into a receive address register.
  **/
 s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq,
-                          u32 enable_addr)
+			  u32 enable_addr)
 {
 	u32 rar_low, rar_high;
 	u32 rar_entries = hw->mac.num_rar_entries;
@@ -2053,7 +2053,7 @@ s32 ixgbe_update_mc_addr_list_generic(struct ixgbe_hw *hw,
 
 	if (hw->addr_ctrl.mta_in_use > 0)
 		IXGBE_WRITE_REG(hw, IXGBE_MCSTCTRL,
-		                IXGBE_MCSTCTRL_MFE | hw->mac.mc_filter_type);
+				IXGBE_MCSTCTRL_MFE | hw->mac.mc_filter_type);
 
 	hw_dbg(hw, "ixgbe_update_mc_addr_list_generic Complete\n");
 	return 0;
@@ -2071,7 +2071,7 @@ s32 ixgbe_enable_mc_generic(struct ixgbe_hw *hw)
 
 	if (a->mta_in_use > 0)
 		IXGBE_WRITE_REG(hw, IXGBE_MCSTCTRL, IXGBE_MCSTCTRL_MFE |
-		                hw->mac.mc_filter_type);
+				hw->mac.mc_filter_type);
 
 	return 0;
 }
@@ -2106,19 +2106,25 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
 	u32 fcrtl, fcrth;
 	int i;
 
-	/*
-	 * Validate the water mark configuration for packet buffer 0.  Zero
-	 * water marks indicate that the packet buffer was not configured
-	 * and the watermarks for packet buffer 0 should always be configured.
-	 */
-	if (!hw->fc.low_water ||
-	    !hw->fc.high_water[0] ||
-	    !hw->fc.pause_time) {
-		hw_dbg(hw, "Invalid water mark configuration\n");
+	/* Validate the water mark configuration. */
+	if (!hw->fc.pause_time) {
 		ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS;
 		goto out;
 	}
 
+	/* Low water mark of zero causes XOFF floods */
+	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
+		if ((hw->fc.current_mode & ixgbe_fc_tx_pause) &&
+		    hw->fc.high_water[i]) {
+			if (!hw->fc.low_water[i] ||
+			    hw->fc.low_water[i] >= hw->fc.high_water[i]) {
+				hw_dbg(hw, "Invalid water mark configuration\n");
+				ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS;
+				goto out;
+			}
+		}
+	}
+
 	/* Negotiate the fc mode to use */
 	ixgbe_fc_autoneg(hw);
 
@@ -2181,12 +2187,11 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw)
 	IXGBE_WRITE_REG(hw, IXGBE_MFLCN, mflcn_reg);
 	IXGBE_WRITE_REG(hw, IXGBE_FCCFG, fccfg_reg);
 
-	fcrtl = (hw->fc.low_water << 10) | IXGBE_FCRTL_XONE;
-
 	/* Set up and enable Rx high/low water mark thresholds, enable XON. */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
 		if ((hw->fc.current_mode & ixgbe_fc_tx_pause) &&
 		    hw->fc.high_water[i]) {
+			fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE;
 			IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), fcrtl);
 			fcrth = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN;
 		} else {
@@ -2654,8 +2659,7 @@ s32 ixgbe_disable_rx_buff_generic(struct ixgbe_hw *hw)
 
 	/* For informational purposes only */
 	if (i >= IXGBE_MAX_SECRX_POLL)
-		hw_dbg(hw, "Rx unit being enabled before security "
-		       "path fully disabled.  Continuing with init.\n");
+		hw_dbg(hw, "Rx unit being enabled before security path fully disabled. Continuing with init.\n");
 
 	return 0;
 
@@ -2782,7 +2786,7 @@ out:
  *  get and set mac_addr routines.
  **/
 static s32 ixgbe_get_san_mac_addr_offset(struct ixgbe_hw *hw,
-                                        u16 *san_mac_offset)
+					u16 *san_mac_offset)
 {
 	s32 ret_val;
 
@@ -2828,7 +2832,7 @@ s32 ixgbe_get_san_mac_addr_generic(struct ixgbe_hw *hw, u8 *san_mac_addr)
 	hw->mac.ops.set_lan_id(hw);
 	/* apply the port offset to the address offset */
 	(hw->bus.func) ? (san_mac_offset += IXGBE_SAN_MAC_ADDR_PORT1_OFFSET) :
-	                 (san_mac_offset += IXGBE_SAN_MAC_ADDR_PORT0_OFFSET);
+			 (san_mac_offset += IXGBE_SAN_MAC_ADDR_PORT0_OFFSET);
 	for (i = 0; i < 3; i++) {
 		ret_val = hw->eeprom.ops.read(hw, san_mac_offset,
 					      &san_mac_data);
@@ -3068,7 +3072,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan)
  *  Turn on/off specified VLAN in the VLAN filter table.
  **/
 s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind,
-                           bool vlan_on)
+			   bool vlan_on)
 {
 	s32 regindex;
 	u32 bitindex;
@@ -3190,9 +3194,9 @@ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind,
 				 * Ignore it. */
 				vfta_changed = false;
 			}
-		}
-		else
+		} else {
 			IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), 0);
+		}
 	}
 
 	if (vfta_changed)
@@ -3292,7 +3296,7 @@ s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed,
  *  block to check the support for the alternative WWNN/WWPN prefix support.
  **/
 s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix,
-                                        u16 *wwpn_prefix)
+					u16 *wwpn_prefix)
 {
 	u16 offset, caps;
 	u16 alt_san_mac_blk_offset;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
index f12c40fb553..2ae5d4b8fc9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h
@@ -39,7 +39,7 @@ s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw);
 s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw);
 s32 ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw);
 s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num,
-                                  u32 pba_num_size);
+				  u32 pba_num_size);
 s32 ixgbe_get_mac_addr_generic(struct ixgbe_hw *hw, u8 *mac_addr);
 enum ixgbe_bus_width ixgbe_convert_bus_width(u16 link_status);
 enum ixgbe_bus_speed ixgbe_convert_bus_speed(u16 link_status);
@@ -61,16 +61,16 @@ s32 ixgbe_write_eewr_generic(struct ixgbe_hw *hw, u16 offset, u16 data);
 s32 ixgbe_write_eewr_buffer_generic(struct ixgbe_hw *hw, u16 offset,
 				    u16 words, u16 *data);
 s32 ixgbe_read_eeprom_bit_bang_generic(struct ixgbe_hw *hw, u16 offset,
-                                       u16 *data);
+				       u16 *data);
 s32 ixgbe_read_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset,
 					      u16 words, u16 *data);
 u16 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw);
 s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw,
-                                           u16 *checksum_val);
+					   u16 *checksum_val);
 s32 ixgbe_update_eeprom_checksum_generic(struct ixgbe_hw *hw);
 
 s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq,
-                          u32 enable_addr);
+			  u32 enable_addr);
 s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index);
 s32 ixgbe_init_rx_addrs_generic(struct ixgbe_hw *hw);
 s32 ixgbe_update_mc_addr_list_generic(struct ixgbe_hw *hw,
@@ -92,13 +92,13 @@ s32 ixgbe_set_vmdq_san_mac_generic(struct ixgbe_hw *hw, u32 vmdq);
 s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq);
 s32 ixgbe_init_uta_tables_generic(struct ixgbe_hw *hw);
 s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan,
-                           u32 vind, bool vlan_on);
+			   u32 vind, bool vlan_on);
 s32 ixgbe_clear_vfta_generic(struct ixgbe_hw *hw);
 s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw,
-                                 ixgbe_link_speed *speed,
-                                 bool *link_up, bool link_up_wait_to_complete);
+				 ixgbe_link_speed *speed,
+				 bool *link_up, bool link_up_wait_to_complete);
 s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix,
-                                 u16 *wwpn_prefix);
+				 u16 *wwpn_prefix);
 
 s32 prot_autoc_read_generic(struct ixgbe_hw *hw, bool *, u32 *reg_val);
 s32 prot_autoc_write_generic(struct ixgbe_hw *hw, u32 reg_val, bool locked);
@@ -141,8 +141,6 @@ static inline bool ixgbe_removed(void __iomem *addr)
 	return unlikely(!addr);
 }
 
-void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg);
-
 static inline void ixgbe_write_reg(struct ixgbe_hw *hw, u32 reg, u32 value)
 {
 	u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr);
@@ -172,18 +170,7 @@ static inline void ixgbe_write_reg64(struct ixgbe_hw *hw, u32 reg, u64 value)
 }
 #define IXGBE_WRITE_REG64(a, reg, value) ixgbe_write_reg64((a), (reg), (value))
 
-static inline u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg)
-{
-	u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr);
-	u32 value;
-
-	if (ixgbe_removed(reg_addr))
-		return IXGBE_FAILED_READ_REG;
-	value = readl(reg_addr + reg);
-	if (unlikely(value == IXGBE_FAILED_READ_REG))
-		ixgbe_check_remove(hw, reg);
-	return value;
-}
+u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg);
 #define IXGBE_READ_REG(a, reg) ixgbe_read_reg((a), (reg))
 
 #define IXGBE_WRITE_REG_ARRAY(a, reg, offset, value) \
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c
index e055e000131..a689ee0d4be 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c
@@ -267,7 +267,7 @@ void ixgbe_dcb_unpack_map(struct ixgbe_dcb_config *cfg, int direction, u8 *map)
  * Configure dcb settings and enable dcb mode.
  */
 s32 ixgbe_dcb_hw_config(struct ixgbe_hw *hw,
-                        struct ixgbe_dcb_config *dcb_config)
+			struct ixgbe_dcb_config *dcb_config)
 {
 	s32 ret = 0;
 	u8 pfc_en;
@@ -389,7 +389,6 @@ static void ixgbe_dcb_read_rtrup2tc_82599(struct ixgbe_hw *hw, u8 *map)
 	for (i = 0; i < MAX_USER_PRIORITY; i++)
 		map[i] = IXGBE_RTRUP2TC_UP_MASK &
 			(reg >> (i * IXGBE_RTRUP2TC_UP_SHIFT));
-	return;
 }
 
 void ixgbe_dcb_read_rtrup2tc(struct ixgbe_hw *hw, u8 *map)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c
index 7a77f37a7cb..d3ba63f9ad3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c
@@ -208,7 +208,6 @@ s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw, u8 pfc_en)
 
 	IXGBE_WRITE_REG(hw, IXGBE_FCTRL, reg);
 
-	fcrtl = (hw->fc.low_water << 10) | IXGBE_FCRTL_XONE;
 	/* Configure PFC Tx thresholds per TC */
 	for (i = 0; i < MAX_TRAFFIC_CLASS; i++) {
 		if (!(pfc_en & (1 << i))) {
@@ -217,6 +216,7 @@ s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw, u8 pfc_en)
 			continue;
 		}
 
+		fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE;
 		reg = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN;
 		IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), fcrtl);
 		IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), reg);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c
index bdb99b3b0f3..3b932fe64ab 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c
@@ -242,7 +242,6 @@ s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en, u8 *prio_tc)
 			max_tc = prio_tc[i];
 	}
 
-	fcrtl = (hw->fc.low_water << 10) | IXGBE_FCRTL_XONE;
 
 	/* Configure PFC Tx thresholds per TC */
 	for (i = 0; i <= max_tc; i++) {
@@ -257,6 +256,7 @@ s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en, u8 *prio_tc)
 
 		if (enabled) {
 			reg = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN;
+			fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE;
 			IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), fcrtl);
 		} else {
 			reg = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 32;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h
index d5a1e3db077..90c370230e2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h
@@ -31,17 +31,17 @@
 
 /* DCB register definitions */
 #define IXGBE_RTTDCS_TDPAC      0x00000001 /* 0 Round Robin,
-                                            * 1 WSP - Weighted Strict Priority
-                                            */
+					    * 1 WSP - Weighted Strict Priority
+					    */
 #define IXGBE_RTTDCS_VMPAC      0x00000002 /* 0 Round Robin,
-                                            * 1 WRR - Weighted Round Robin
-                                            */
+					    * 1 WRR - Weighted Round Robin
+					    */
 #define IXGBE_RTTDCS_TDRM       0x00000010 /* Transmit Recycle Mode */
 #define IXGBE_RTTDCS_ARBDIS     0x00000040 /* DCB arbiter disable */
 #define IXGBE_RTTDCS_BDPM       0x00400000 /* Bypass Data Pipe - must clear! */
 #define IXGBE_RTTDCS_BPBFSM     0x00800000 /* Bypass PB Free Space - must
-                                             * clear!
-                                             */
+					     * clear!
+					     */
 #define IXGBE_RTTDCS_SPEED_CHG  0x80000000 /* Link speed change */
 
 /* Receive UP2TC mapping */
@@ -56,11 +56,11 @@
 #define IXGBE_RTRPT4C_LSP       0x80000000 /* LSP enable bit */
 
 #define IXGBE_RDRXCTL_MPBEN     0x00000010 /* DMA config for multiple packet
-                                            * buffers enable
-                                            */
+					    * buffers enable
+					    */
 #define IXGBE_RDRXCTL_MCEN      0x00000040 /* DMA config for multiple cores
-                                            * (RSS) enable
-                                            */
+					    * (RSS) enable
+					    */
 
 /* RTRPCS Bit Masks */
 #define IXGBE_RTRPCS_RRM        0x00000002 /* Receive Recycle Mode enable */
@@ -81,8 +81,8 @@
 
 /* RTTPCS Bit Masks */
 #define IXGBE_RTTPCS_TPPAC      0x00000020 /* 0 Round Robin,
-                                            * 1 SP - Strict Priority
-                                            */
+					    * 1 SP - Strict Priority
+					    */
 #define IXGBE_RTTPCS_ARBDIS     0x00000040 /* Arbiter disable */
 #define IXGBE_RTTPCS_TPRM       0x00000100 /* Transmit Recycle Mode enable */
 #define IXGBE_RTTPCS_ARBD_SHIFT 22
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index edd89a1ef27..5172b6b12c0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -192,8 +192,8 @@ static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev,
 }
 
 static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
-                                         u8 prio, u8 bwg_id, u8 bw_pct,
-                                         u8 up_map)
+					 u8 prio, u8 bwg_id, u8 bw_pct,
+					 u8 up_map)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -210,7 +210,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 }
 
 static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
-                                          u8 bw_pct)
+					  u8 bw_pct)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -218,8 +218,8 @@ static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 }
 
 static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
-                                         u8 prio, u8 bwg_id, u8 bw_pct,
-                                         u8 up_map)
+					 u8 prio, u8 bwg_id, u8 bw_pct,
+					 u8 up_map)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -236,7 +236,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 }
 
 static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
-                                          u8 bw_pct)
+					  u8 bw_pct)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -244,8 +244,8 @@ static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 }
 
 static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
-                                         u8 *prio, u8 *bwg_id, u8 *bw_pct,
-                                         u8 *up_map)
+					 u8 *prio, u8 *bwg_id, u8 *bw_pct,
+					 u8 *up_map)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -256,7 +256,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 }
 
 static void ixgbe_dcbnl_get_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
-                                          u8 *bw_pct)
+					  u8 *bw_pct)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -264,8 +264,8 @@ static void ixgbe_dcbnl_get_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
 }
 
 static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc,
-                                         u8 *prio, u8 *bwg_id, u8 *bw_pct,
-                                         u8 *up_map)
+					 u8 *prio, u8 *bwg_id, u8 *bw_pct,
+					 u8 *up_map)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -276,7 +276,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 }
 
 static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
-                                          u8 *bw_pct)
+					  u8 *bw_pct)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -284,7 +284,7 @@ static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id,
 }
 
 static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
-                                    u8 setting)
+				    u8 setting)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -295,7 +295,7 @@ static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
 }
 
 static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
-                                    u8 *setting)
+				    u8 *setting)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
index 472b0f450bf..5e2c1e35e51 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c
@@ -253,8 +253,7 @@ void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter)
  **/
 void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter)
 {
-	if (adapter->ixgbe_dbg_adapter)
-		debugfs_remove_recursive(adapter->ixgbe_dbg_adapter);
+	debugfs_remove_recursive(adapter->ixgbe_dbg_adapter);
 	adapter->ixgbe_dbg_adapter = NULL;
 }
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 6c55c14d082..a452730a327 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -141,8 +141,8 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = {
 			 sizeof(((struct ixgbe_adapter *)0)->stats.pxofftxc)) \
 			/ sizeof(u64))
 #define IXGBE_STATS_LEN (IXGBE_GLOBAL_STATS_LEN + \
-                         IXGBE_PB_STATS_LEN + \
-                         IXGBE_QUEUE_STATS_LEN)
+			 IXGBE_PB_STATS_LEN + \
+			 IXGBE_QUEUE_STATS_LEN)
 
 static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = {
 	"Register test  (offline)", "Eeprom test    (offline)",
@@ -152,7 +152,7 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = {
 #define IXGBE_TEST_LEN sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN
 
 static int ixgbe_get_settings(struct net_device *netdev,
-                              struct ethtool_cmd *ecmd)
+			      struct ethtool_cmd *ecmd)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -161,13 +161,6 @@ static int ixgbe_get_settings(struct net_device *netdev,
 	bool autoneg = false;
 	bool link_up;
 
-	/* SFP type is needed for get_link_capabilities */
-	if (hw->phy.media_type & (ixgbe_media_type_fiber |
-				  ixgbe_media_type_fiber_qsfp)) {
-		if (hw->phy.sfp_type == ixgbe_sfp_type_not_present)
-				hw->phy.ops.identify_sfp(hw);
-	}
-
 	hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg);
 
 	/* set the supported link speeds */
@@ -303,15 +296,15 @@ static int ixgbe_get_settings(struct net_device *netdev,
 		}
 		ecmd->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	return 0;
 }
 
 static int ixgbe_set_settings(struct net_device *netdev,
-                              struct ethtool_cmd *ecmd)
+			      struct ethtool_cmd *ecmd)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -368,7 +361,7 @@ static int ixgbe_set_settings(struct net_device *netdev,
 }
 
 static void ixgbe_get_pauseparam(struct net_device *netdev,
-                                 struct ethtool_pauseparam *pause)
+				 struct ethtool_pauseparam *pause)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -390,7 +383,7 @@ static void ixgbe_get_pauseparam(struct net_device *netdev,
 }
 
 static int ixgbe_set_pauseparam(struct net_device *netdev,
-                                struct ethtool_pauseparam *pause)
+				struct ethtool_pauseparam *pause)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -450,7 +443,7 @@ static int ixgbe_get_regs_len(struct net_device *netdev)
 #define IXGBE_GET_STAT(_A_, _R_) _A_->stats._R_
 
 static void ixgbe_get_regs(struct net_device *netdev,
-                           struct ethtool_regs *regs, void *p)
+			   struct ethtool_regs *regs, void *p)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -812,7 +805,7 @@ static int ixgbe_get_eeprom_len(struct net_device *netdev)
 }
 
 static int ixgbe_get_eeprom(struct net_device *netdev,
-                            struct ethtool_eeprom *eeprom, u8 *bytes)
+			    struct ethtool_eeprom *eeprom, u8 *bytes)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -918,7 +911,7 @@ err:
 }
 
 static void ixgbe_get_drvinfo(struct net_device *netdev,
-                              struct ethtool_drvinfo *drvinfo)
+			      struct ethtool_drvinfo *drvinfo)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	u32 nvm_track_id;
@@ -940,7 +933,7 @@ static void ixgbe_get_drvinfo(struct net_device *netdev,
 }
 
 static void ixgbe_get_ringparam(struct net_device *netdev,
-                                struct ethtool_ringparam *ring)
+				struct ethtool_ringparam *ring)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_ring *tx_ring = adapter->tx_ring[0];
@@ -953,7 +946,7 @@ static void ixgbe_get_ringparam(struct net_device *netdev,
 }
 
 static int ixgbe_set_ringparam(struct net_device *netdev,
-                               struct ethtool_ringparam *ring)
+			       struct ethtool_ringparam *ring)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_ring *temp_ring;
@@ -1082,7 +1075,7 @@ static int ixgbe_get_sset_count(struct net_device *netdev, int sset)
 }
 
 static void ixgbe_get_ethtool_stats(struct net_device *netdev,
-                                    struct ethtool_stats *stats, u64 *data)
+				    struct ethtool_stats *stats, u64 *data)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct rtnl_link_stats64 temp;
@@ -1110,7 +1103,7 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 		}
 
 		data[i] = (ixgbe_gstrings_stats[i].sizeof_stat ==
-		           sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+			   sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 	}
 	for (j = 0; j < netdev->num_tx_queues; j++) {
 		ring = adapter->tx_ring[j];
@@ -1180,7 +1173,7 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 }
 
 static void ixgbe_get_strings(struct net_device *netdev, u32 stringset,
-                              u8 *data)
+			      u8 *data)
 {
 	char *p = (char *)data;
 	int i;
@@ -1357,8 +1350,7 @@ static bool reg_pattern_test(struct ixgbe_adapter *adapter, u64 *data, int reg,
 		ixgbe_write_reg(&adapter->hw, reg, test_pattern[pat] & write);
 		val = ixgbe_read_reg(&adapter->hw, reg);
 		if (val != (test_pattern[pat] & write & mask)) {
-			e_err(drv, "pattern test reg %04X failed: got "
-			      "0x%08X expected 0x%08X\n",
+			e_err(drv, "pattern test reg %04X failed: got 0x%08X expected 0x%08X\n",
 			      reg, val, (test_pattern[pat] & write & mask));
 			*data = reg;
 			ixgbe_write_reg(&adapter->hw, reg, before);
@@ -1382,8 +1374,8 @@ static bool reg_set_and_check(struct ixgbe_adapter *adapter, u64 *data, int reg,
 	ixgbe_write_reg(&adapter->hw, reg, write & mask);
 	val = ixgbe_read_reg(&adapter->hw, reg);
 	if ((write & mask) != (val & mask)) {
-		e_err(drv, "set/check reg %04X test failed: got 0x%08X "
-		      "expected 0x%08X\n", reg, (val & mask), (write & mask));
+		e_err(drv, "set/check reg %04X test failed: got 0x%08X expected 0x%08X\n",
+		      reg, (val & mask), (write & mask));
 		*data = reg;
 		ixgbe_write_reg(&adapter->hw, reg, before);
 		return true;
@@ -1430,8 +1422,8 @@ static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data)
 	ixgbe_write_reg(&adapter->hw, IXGBE_STATUS, toggle);
 	after = ixgbe_read_reg(&adapter->hw, IXGBE_STATUS) & toggle;
 	if (value != after) {
-		e_err(drv, "failed STATUS register test got: 0x%08X "
-		      "expected: 0x%08X\n", after, value);
+		e_err(drv, "failed STATUS register test got: 0x%08X expected: 0x%08X\n",
+		      after, value);
 		*data = 1;
 		return 1;
 	}
@@ -1533,10 +1525,10 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data)
 			return -1;
 		}
 	} else if (!request_irq(irq, ixgbe_test_intr, IRQF_PROBE_SHARED,
-	                        netdev->name, netdev)) {
+				netdev->name, netdev)) {
 		shared_int = false;
 	} else if (request_irq(irq, ixgbe_test_intr, IRQF_SHARED,
-	                       netdev->name, netdev)) {
+			       netdev->name, netdev)) {
 		*data = 1;
 		return -1;
 	}
@@ -1563,9 +1555,9 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data)
 			 */
 			adapter->test_icr = 0;
 			IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC,
-			                ~mask & 0x00007FFF);
+					~mask & 0x00007FFF);
 			IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS,
-			                ~mask & 0x00007FFF);
+					~mask & 0x00007FFF);
 			IXGBE_WRITE_FLUSH(&adapter->hw);
 			usleep_range(10000, 20000);
 
@@ -1587,7 +1579,7 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data)
 		IXGBE_WRITE_FLUSH(&adapter->hw);
 		usleep_range(10000, 20000);
 
-		if (!(adapter->test_icr &mask)) {
+		if (!(adapter->test_icr & mask)) {
 			*data = 4;
 			break;
 		}
@@ -1602,9 +1594,9 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data)
 			 */
 			adapter->test_icr = 0;
 			IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC,
-			                ~mask & 0x00007FFF);
+					~mask & 0x00007FFF);
 			IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS,
-			                ~mask & 0x00007FFF);
+					~mask & 0x00007FFF);
 			IXGBE_WRITE_FLUSH(&adapter->hw);
 			usleep_range(10000, 20000);
 
@@ -1964,7 +1956,7 @@ out:
 }
 
 static void ixgbe_diag_test(struct net_device *netdev,
-                            struct ethtool_test *eth_test, u64 *data)
+			    struct ethtool_test *eth_test, u64 *data)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	bool if_running = netif_running(netdev);
@@ -1987,10 +1979,7 @@ static void ixgbe_diag_test(struct net_device *netdev,
 			int i;
 			for (i = 0; i < adapter->num_vfs; i++) {
 				if (adapter->vfinfo[i].clear_to_send) {
-					netdev_warn(netdev, "%s",
-						    "offline diagnostic is not "
-						    "supported when VFs are "
-						    "present\n");
+					netdev_warn(netdev, "offline diagnostic is not supported when VFs are present\n");
 					data[0] = 1;
 					data[1] = 1;
 					data[2] = 1;
@@ -2037,8 +2026,7 @@ static void ixgbe_diag_test(struct net_device *netdev,
 		 * loopback diagnostic. */
 		if (adapter->flags & (IXGBE_FLAG_SRIOV_ENABLED |
 				      IXGBE_FLAG_VMDQ_ENABLED)) {
-			e_info(hw, "Skip MAC loopback diagnostic in VT "
-			       "mode\n");
+			e_info(hw, "Skip MAC loopback diagnostic in VT mode\n");
 			data[3] = 0;
 			goto skip_loopback;
 		}
@@ -2078,7 +2066,7 @@ skip_ol_tests:
 }
 
 static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter,
-                               struct ethtool_wolinfo *wol)
+			       struct ethtool_wolinfo *wol)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	int retval = 0;
@@ -2094,12 +2082,12 @@ static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter,
 }
 
 static void ixgbe_get_wol(struct net_device *netdev,
-                          struct ethtool_wolinfo *wol)
+			  struct ethtool_wolinfo *wol)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
 	wol->supported = WAKE_UCAST | WAKE_MCAST |
-	                 WAKE_BCAST | WAKE_MAGIC;
+			 WAKE_BCAST | WAKE_MAGIC;
 	wol->wolopts = 0;
 
 	if (ixgbe_wol_exclusion(adapter, wol) ||
@@ -2181,7 +2169,7 @@ static int ixgbe_set_phys_id(struct net_device *netdev,
 }
 
 static int ixgbe_get_coalesce(struct net_device *netdev,
-                              struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -2222,8 +2210,7 @@ static bool ixgbe_update_rsc(struct ixgbe_adapter *adapter)
 	    adapter->rx_itr_setting > IXGBE_MIN_RSC_ITR) {
 		if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) {
 			adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED;
-			e_info(probe, "rx-usecs value high enough "
-				      "to re-enable RSC\n");
+			e_info(probe, "rx-usecs value high enough to re-enable RSC\n");
 			return true;
 		}
 	/* if interrupt rate is too high then disable RSC */
@@ -2236,7 +2223,7 @@ static bool ixgbe_update_rsc(struct ixgbe_adapter *adapter)
 }
 
 static int ixgbe_set_coalesce(struct net_device *netdev,
-                              struct ethtool_coalesce *ec)
+			      struct ethtool_coalesce *ec)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_q_vector *q_vector;
@@ -2421,9 +2408,11 @@ static int ixgbe_get_rss_hash_opts(struct ixgbe_adapter *adapter,
 	switch (cmd->flow_type) {
 	case TCP_V4_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* fallthrough */
 	case UDP_V4_FLOW:
 		if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP)
 			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* fallthrough */
 	case SCTP_V4_FLOW:
 	case AH_ESP_V4_FLOW:
 	case AH_V4_FLOW:
@@ -2433,9 +2422,11 @@ static int ixgbe_get_rss_hash_opts(struct ixgbe_adapter *adapter,
 		break;
 	case TCP_V6_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* fallthrough */
 	case UDP_V6_FLOW:
 		if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP)
 			cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* fallthrough */
 	case SCTP_V6_FLOW:
 	case AH_ESP_V6_FLOW:
 	case AH_V6_FLOW:
@@ -2787,8 +2778,7 @@ static int ixgbe_set_rss_hash_opt(struct ixgbe_adapter *adapter,
 
 		if ((flags2 & UDP_RSS_FLAGS) &&
 		    !(adapter->flags2 & UDP_RSS_FLAGS))
-			e_warn(drv, "enabling UDP RSS: fragmented packets"
-			       " may arrive out of order to the stack above\n");
+			e_warn(drv, "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n");
 
 		adapter->flags2 = flags2;
 
@@ -3099,5 +3089,5 @@ static const struct ethtool_ops ixgbe_ethtool_ops = {
 
 void ixgbe_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &ixgbe_ethtool_ops);
+	netdev->ethtool_ops = &ixgbe_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h
index b16cc786750..0772b7730fc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h
@@ -81,9 +81,7 @@ struct ixgbe_fcoe {
 	void *extra_ddp_buffer;
 	dma_addr_t extra_ddp_buffer_dma;
 	unsigned long mode;
-#ifdef CONFIG_IXGBE_DCB
 	u8 up;
-#endif
 };
 
 #endif /* _IXGBE_FCOE_H */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 2067d392cc3..2d9451e3968 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -1113,8 +1113,8 @@ static void ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter)
 	err = pci_enable_msi(adapter->pdev);
 	if (err) {
 		netif_printk(adapter, hw, KERN_DEBUG, adapter->netdev,
-			     "Unable to allocate MSI interrupt, "
-			     "falling back to legacy.  Error: %d\n", err);
+			     "Unable to allocate MSI interrupt, falling back to legacy.  Error: %d\n",
+			     err);
 		return;
 	}
 	adapter->flags |= IXGBE_FLAG_MSI_ENABLED;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index c047c3ef8d7..f5aa3311ea2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -301,7 +301,7 @@ static void ixgbe_remove_adapter(struct ixgbe_hw *hw)
 		ixgbe_service_event_schedule(adapter);
 }
 
-void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg)
+static void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg)
 {
 	u32 value;
 
@@ -320,6 +320,32 @@ void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg)
 		ixgbe_remove_adapter(hw);
 }
 
+/**
+ * ixgbe_read_reg - Read from device register
+ * @hw: hw specific details
+ * @reg: offset of register to read
+ *
+ * Returns : value read or IXGBE_FAILED_READ_REG if removed
+ *
+ * This function is used to read device registers. It checks for device
+ * removal by confirming any read that returns all ones by checking the
+ * status register value for all ones. This function avoids reading from
+ * the hardware if a removal was previously detected in which case it
+ * returns IXGBE_FAILED_READ_REG (all ones).
+ */
+u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg)
+{
+	u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr);
+	u32 value;
+
+	if (ixgbe_removed(reg_addr))
+		return IXGBE_FAILED_READ_REG;
+	value = readl(reg_addr + reg);
+	if (unlikely(value == IXGBE_FAILED_READ_REG))
+		ixgbe_check_remove(hw, reg);
+	return value;
+}
+
 static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev)
 {
 	u16 value;
@@ -3743,35 +3769,6 @@ static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev,
 }
 
 /**
- * ixgbe_vlan_filter_disable - helper to disable hw vlan filtering
- * @adapter: driver data
- */
-static void ixgbe_vlan_filter_disable(struct ixgbe_adapter *adapter)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	u32 vlnctrl;
-
-	vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
-	vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN);
-	IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
-}
-
-/**
- * ixgbe_vlan_filter_enable - helper to enable hw vlan filtering
- * @adapter: driver data
- */
-static void ixgbe_vlan_filter_enable(struct ixgbe_adapter *adapter)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	u32 vlnctrl;
-
-	vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
-	vlnctrl |= IXGBE_VLNCTRL_VFE;
-	vlnctrl &= ~IXGBE_VLNCTRL_CFIEN;
-	IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
-}
-
-/**
  * ixgbe_vlan_strip_disable - helper to disable hw vlan stripping
  * @adapter: driver data
  */
@@ -3850,6 +3847,158 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter)
 }
 
 /**
+ * ixgbe_write_mc_addr_list - write multicast addresses to MTA
+ * @netdev: network interface device structure
+ *
+ * Writes multicast address list to the MTA hash table.
+ * Returns: -ENOMEM on failure
+ *                0 on no addresses written
+ *                X on writing X addresses to MTA
+ **/
+static int ixgbe_write_mc_addr_list(struct net_device *netdev)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(netdev);
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	if (!netif_running(netdev))
+		return 0;
+
+	if (hw->mac.ops.update_mc_addr_list)
+		hw->mac.ops.update_mc_addr_list(hw, netdev);
+	else
+		return -ENOMEM;
+
+#ifdef CONFIG_PCI_IOV
+	ixgbe_restore_vf_multicasts(adapter);
+#endif
+
+	return netdev_mc_count(netdev);
+}
+
+#ifdef CONFIG_PCI_IOV
+void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i;
+	for (i = 0; i < hw->mac.num_rar_entries; i++) {
+		if (adapter->mac_table[i].state & IXGBE_MAC_STATE_IN_USE)
+			hw->mac.ops.set_rar(hw, i, adapter->mac_table[i].addr,
+					    adapter->mac_table[i].queue,
+					    IXGBE_RAH_AV);
+		else
+			hw->mac.ops.clear_rar(hw, i);
+
+		adapter->mac_table[i].state &= ~(IXGBE_MAC_STATE_MODIFIED);
+	}
+}
+#endif
+
+static void ixgbe_sync_mac_table(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i;
+	for (i = 0; i < hw->mac.num_rar_entries; i++) {
+		if (adapter->mac_table[i].state & IXGBE_MAC_STATE_MODIFIED) {
+			if (adapter->mac_table[i].state &
+			    IXGBE_MAC_STATE_IN_USE)
+				hw->mac.ops.set_rar(hw, i,
+						adapter->mac_table[i].addr,
+						adapter->mac_table[i].queue,
+						IXGBE_RAH_AV);
+			else
+				hw->mac.ops.clear_rar(hw, i);
+
+			adapter->mac_table[i].state &=
+						~(IXGBE_MAC_STATE_MODIFIED);
+		}
+	}
+}
+
+static void ixgbe_flush_sw_mac_table(struct ixgbe_adapter *adapter)
+{
+	int i;
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	for (i = 0; i < hw->mac.num_rar_entries; i++) {
+		adapter->mac_table[i].state |= IXGBE_MAC_STATE_MODIFIED;
+		adapter->mac_table[i].state &= ~IXGBE_MAC_STATE_IN_USE;
+		memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
+		adapter->mac_table[i].queue = 0;
+	}
+	ixgbe_sync_mac_table(adapter);
+}
+
+static int ixgbe_available_rars(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i, count = 0;
+
+	for (i = 0; i < hw->mac.num_rar_entries; i++) {
+		if (adapter->mac_table[i].state == 0)
+			count++;
+	}
+	return count;
+}
+
+/* this function destroys the first RAR entry */
+static void ixgbe_mac_set_default_filter(struct ixgbe_adapter *adapter,
+					 u8 *addr)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	memcpy(&adapter->mac_table[0].addr, addr, ETH_ALEN);
+	adapter->mac_table[0].queue = VMDQ_P(0);
+	adapter->mac_table[0].state = (IXGBE_MAC_STATE_DEFAULT |
+				       IXGBE_MAC_STATE_IN_USE);
+	hw->mac.ops.set_rar(hw, 0, adapter->mac_table[0].addr,
+			    adapter->mac_table[0].queue,
+			    IXGBE_RAH_AV);
+}
+
+int ixgbe_add_mac_filter(struct ixgbe_adapter *adapter, u8 *addr, u16 queue)
+{
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i;
+
+	if (is_zero_ether_addr(addr))
+		return -EINVAL;
+
+	for (i = 0; i < hw->mac.num_rar_entries; i++) {
+		if (adapter->mac_table[i].state & IXGBE_MAC_STATE_IN_USE)
+			continue;
+		adapter->mac_table[i].state |= (IXGBE_MAC_STATE_MODIFIED |
+						IXGBE_MAC_STATE_IN_USE);
+		ether_addr_copy(adapter->mac_table[i].addr, addr);
+		adapter->mac_table[i].queue = queue;
+		ixgbe_sync_mac_table(adapter);
+		return i;
+	}
+	return -ENOMEM;
+}
+
+int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, u8 *addr, u16 queue)
+{
+	/* search table for addr, if found, set to 0 and sync */
+	int i;
+	struct ixgbe_hw *hw = &adapter->hw;
+
+	if (is_zero_ether_addr(addr))
+		return -EINVAL;
+
+	for (i = 0; i < hw->mac.num_rar_entries; i++) {
+		if (ether_addr_equal(addr, adapter->mac_table[i].addr) &&
+		    adapter->mac_table[i].queue == queue) {
+			adapter->mac_table[i].state |= IXGBE_MAC_STATE_MODIFIED;
+			adapter->mac_table[i].state &= ~IXGBE_MAC_STATE_IN_USE;
+			memset(adapter->mac_table[i].addr, 0, ETH_ALEN);
+			adapter->mac_table[i].queue = 0;
+			ixgbe_sync_mac_table(adapter);
+			return 0;
+		}
+	}
+	return -ENOMEM;
+}
+/**
  * ixgbe_write_uc_addr_list - write unicast addresses to RAR table
  * @netdev: network interface device structure
  *
@@ -3858,39 +4007,23 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter)
  *                0 on no addresses written
  *                X on writing X addresses to the RAR table
  **/
-static int ixgbe_write_uc_addr_list(struct net_device *netdev)
+static int ixgbe_write_uc_addr_list(struct net_device *netdev, int vfn)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	struct ixgbe_hw *hw = &adapter->hw;
-	unsigned int rar_entries = hw->mac.num_rar_entries - 1;
 	int count = 0;
 
-	/* In SR-IOV/VMDQ modes significantly less RAR entries are available */
-	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
-		rar_entries = IXGBE_MAX_PF_MACVLANS - 1;
-
 	/* return ENOMEM indicating insufficient memory for addresses */
-	if (netdev_uc_count(netdev) > rar_entries)
+	if (netdev_uc_count(netdev) > ixgbe_available_rars(adapter))
 		return -ENOMEM;
 
 	if (!netdev_uc_empty(netdev)) {
 		struct netdev_hw_addr *ha;
-		/* return error if we do not support writing to RAR table */
-		if (!hw->mac.ops.set_rar)
-			return -ENOMEM;
-
 		netdev_for_each_uc_addr(ha, netdev) {
-			if (!rar_entries)
-				break;
-			hw->mac.ops.set_rar(hw, rar_entries--, ha->addr,
-					    VMDQ_P(0), IXGBE_RAH_AV);
+			ixgbe_del_mac_filter(adapter, ha->addr, vfn);
+			ixgbe_add_mac_filter(adapter, ha->addr, vfn);
 			count++;
 		}
 	}
-	/* write the addresses in reverse order to avoid write combining */
-	for (; rar_entries > 0 ; rar_entries--)
-		hw->mac.ops.clear_rar(hw, rar_entries);
-
 	return count;
 }
 
@@ -3908,11 +4041,12 @@ void ixgbe_set_rx_mode(struct net_device *netdev)
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE;
+	u32 vlnctrl;
 	int count;
 
 	/* Check for Promiscuous and All Multicast modes */
-
 	fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL);
+	vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
 
 	/* set all bits that we expect to always be set */
 	fctrl &= ~IXGBE_FCTRL_SBP; /* disable store-bad-packets */
@@ -3922,26 +4056,24 @@ void ixgbe_set_rx_mode(struct net_device *netdev)
 
 	/* clear the bits we are changing the status of */
 	fctrl &= ~(IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE);
-
+	vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN);
 	if (netdev->flags & IFF_PROMISC) {
 		hw->addr_ctrl.user_set_promisc = true;
 		fctrl |= (IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE);
-		vmolr |= (IXGBE_VMOLR_ROPE | IXGBE_VMOLR_MPE);
+		vmolr |= IXGBE_VMOLR_MPE;
 		/* Only disable hardware filter vlans in promiscuous mode
 		 * if SR-IOV and VMDQ are disabled - otherwise ensure
 		 * that hardware VLAN filters remain enabled.
 		 */
 		if (!(adapter->flags & (IXGBE_FLAG_VMDQ_ENABLED |
 					IXGBE_FLAG_SRIOV_ENABLED)))
-			ixgbe_vlan_filter_disable(adapter);
-		else
-			ixgbe_vlan_filter_enable(adapter);
+			vlnctrl |= (IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN);
 	} else {
 		if (netdev->flags & IFF_ALLMULTI) {
 			fctrl |= IXGBE_FCTRL_MPE;
 			vmolr |= IXGBE_VMOLR_MPE;
 		}
-		ixgbe_vlan_filter_enable(adapter);
+		vlnctrl |= IXGBE_VLNCTRL_VFE;
 		hw->addr_ctrl.user_set_promisc = false;
 	}
 
@@ -3950,7 +4082,7 @@ void ixgbe_set_rx_mode(struct net_device *netdev)
 	 * sufficient space to store all the addresses then enable
 	 * unicast promiscuous mode
 	 */
-	count = ixgbe_write_uc_addr_list(netdev);
+	count = ixgbe_write_uc_addr_list(netdev, VMDQ_P(0));
 	if (count < 0) {
 		fctrl |= IXGBE_FCTRL_UPE;
 		vmolr |= IXGBE_VMOLR_ROPE;
@@ -3960,11 +4092,13 @@ void ixgbe_set_rx_mode(struct net_device *netdev)
 	 * then we should just turn on promiscuous mode so
 	 * that we can at least receive multicast traffic
 	 */
-	hw->mac.ops.update_mc_addr_list(hw, netdev);
-	vmolr |= IXGBE_VMOLR_ROMPE;
-
-	if (adapter->num_vfs)
-		ixgbe_restore_vf_multicasts(adapter);
+	count = ixgbe_write_mc_addr_list(netdev);
+	if (count < 0) {
+		fctrl |= IXGBE_FCTRL_MPE;
+		vmolr |= IXGBE_VMOLR_MPE;
+	} else if (count) {
+		vmolr |= IXGBE_VMOLR_ROMPE;
+	}
 
 	if (hw->mac.type != ixgbe_mac_82598EB) {
 		vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(VMDQ_P(0))) &
@@ -3985,6 +4119,7 @@ void ixgbe_set_rx_mode(struct net_device *netdev)
 		/* NOTE:  VLAN filtering is disabled by setting PROMISC */
 	}
 
+	IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
 	IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl);
 
 	if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX)
@@ -4101,8 +4236,8 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb)
 	    (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) &&
 	    (pb == ixgbe_fcoe_get_tc(adapter)))
 		tc = IXGBE_FCOE_JUMBO_FRAME_SIZE;
-
 #endif
+
 	/* Calculate delay value for device */
 	switch (hw->mac.type) {
 	case ixgbe_mac_X540:
@@ -4143,7 +4278,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb)
  * @adapter: board private structure to calculate for
  * @pb: packet buffer to calculate
  */
-static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter)
+static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct net_device *dev = adapter->netdev;
@@ -4153,6 +4288,14 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter)
 	/* Calculate max LAN frame size */
 	tc = dev->mtu + ETH_HLEN + ETH_FCS_LEN;
 
+#ifdef IXGBE_FCOE
+	/* FCoE traffic class uses FCOE jumbo frames */
+	if ((dev->features & NETIF_F_FCOE_MTU) &&
+	    (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) &&
+	    (pb == netdev_get_prio_tc_map(dev, adapter->fcoe.up)))
+		tc = IXGBE_FCOE_JUMBO_FRAME_SIZE;
+#endif
+
 	/* Calculate delay value for device */
 	switch (hw->mac.type) {
 	case ixgbe_mac_X540:
@@ -4179,15 +4322,17 @@ static void ixgbe_pbthresh_setup(struct ixgbe_adapter *adapter)
 	if (!num_tc)
 		num_tc = 1;
 
-	hw->fc.low_water = ixgbe_lpbthresh(adapter);
-
 	for (i = 0; i < num_tc; i++) {
 		hw->fc.high_water[i] = ixgbe_hpbthresh(adapter, i);
+		hw->fc.low_water[i] = ixgbe_lpbthresh(adapter, i);
 
 		/* Low water marks must not be larger than high water marks */
-		if (hw->fc.low_water > hw->fc.high_water[i])
-			hw->fc.low_water = 0;
+		if (hw->fc.low_water[i] > hw->fc.high_water[i])
+			hw->fc.low_water[i] = 0;
 	}
+
+	for (; i < MAX_TRAFFIC_CLASS; i++)
+		hw->fc.high_water[i] = 0;
 }
 
 static void ixgbe_configure_pb(struct ixgbe_adapter *adapter)
@@ -4249,20 +4394,10 @@ static void ixgbe_macvlan_set_rx_mode(struct net_device *dev, unsigned int pool,
 		vmolr |= IXGBE_VMOLR_ROMPE;
 		hw->mac.ops.update_mc_addr_list(hw, dev);
 	}
-	ixgbe_write_uc_addr_list(adapter->netdev);
+	ixgbe_write_uc_addr_list(adapter->netdev, pool);
 	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(pool), vmolr);
 }
 
-static void ixgbe_add_mac_filter(struct ixgbe_adapter *adapter,
-				 u8 *addr, u16 pool)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	unsigned int entry;
-
-	entry = hw->mac.num_rar_entries - pool;
-	hw->mac.ops.set_rar(hw, entry, addr, VMDQ_P(pool), IXGBE_RAH_AV);
-}
-
 static void ixgbe_fwd_psrtype(struct ixgbe_fwd_adapter *vadapter)
 {
 	struct ixgbe_adapter *adapter = vadapter->real_adapter;
@@ -4521,6 +4656,8 @@ static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw)
 	case ixgbe_phy_qsfp_active_unknown:
 	case ixgbe_phy_qsfp_intel:
 	case ixgbe_phy_qsfp_unknown:
+	/* ixgbe_phy_none is set when no SFP module is present */
+	case ixgbe_phy_none:
 		return true;
 	case ixgbe_phy_nl:
 		if (hw->mac.type == ixgbe_mac_82598EB)
@@ -4742,7 +4879,9 @@ void ixgbe_up(struct ixgbe_adapter *adapter)
 void ixgbe_reset(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
+	struct net_device *netdev = adapter->netdev;
 	int err;
+	u8 old_addr[ETH_ALEN];
 
 	if (ixgbe_removed(hw->hw_addr))
 		return;
@@ -4778,9 +4917,10 @@ void ixgbe_reset(struct ixgbe_adapter *adapter)
 	}
 
 	clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state);
-
-	/* reprogram the RAR[0] in case user changed it. */
-	hw->mac.ops.set_rar(hw, 0, hw->mac.addr, VMDQ_P(0), IXGBE_RAH_AV);
+	/* do not flush user set addresses */
+	memcpy(old_addr, &adapter->mac_table[0].addr, netdev->addr_len);
+	ixgbe_flush_sw_mac_table(adapter);
+	ixgbe_mac_set_default_filter(adapter, old_addr);
 
 	/* update SAN MAC vmdq pool selection */
 	if (hw->mac.san_mac_rar_index)
@@ -5026,6 +5166,10 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter)
 #endif /* CONFIG_IXGBE_DCB */
 #endif /* IXGBE_FCOE */
 
+	adapter->mac_table = kzalloc(sizeof(struct ixgbe_mac_addr) *
+				     hw->mac.num_rar_entries,
+				     GFP_ATOMIC);
+
 	/* Set MAC specific capability flags and exceptions */
 	switch (hw->mac.type) {
 	case ixgbe_mac_82598EB:
@@ -5517,6 +5661,17 @@ err_setup_tx:
 	return err;
 }
 
+static void ixgbe_close_suspend(struct ixgbe_adapter *adapter)
+{
+	ixgbe_ptp_suspend(adapter);
+
+	ixgbe_down(adapter);
+	ixgbe_free_irq(adapter);
+
+	ixgbe_free_all_tx_resources(adapter);
+	ixgbe_free_all_rx_resources(adapter);
+}
+
 /**
  * ixgbe_close - Disables a network interface
  * @netdev: network interface device structure
@@ -5534,14 +5689,10 @@ static int ixgbe_close(struct net_device *netdev)
 
 	ixgbe_ptp_stop(adapter);
 
-	ixgbe_down(adapter);
-	ixgbe_free_irq(adapter);
+	ixgbe_close_suspend(adapter);
 
 	ixgbe_fdir_filter_exit(adapter);
 
-	ixgbe_free_all_tx_resources(adapter);
-	ixgbe_free_all_rx_resources(adapter);
-
 	ixgbe_release_hw_control(adapter);
 
 	return 0;
@@ -5608,12 +5759,8 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
 	netif_device_detach(netdev);
 
 	rtnl_lock();
-	if (netif_running(netdev)) {
-		ixgbe_down(adapter);
-		ixgbe_free_irq(adapter);
-		ixgbe_free_all_tx_resources(adapter);
-		ixgbe_free_all_rx_resources(adapter);
-	}
+	if (netif_running(netdev))
+		ixgbe_close_suspend(adapter);
 	rtnl_unlock();
 
 	ixgbe_clear_interrupt_scheme(adapter);
@@ -5945,7 +6092,7 @@ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter)
 	if (ixgbe_reinit_fdir_tables_82599(hw) == 0) {
 		for (i = 0; i < adapter->num_tx_queues; i++)
 			set_bit(__IXGBE_TX_FDIR_INIT_DONE,
-			        &(adapter->tx_ring[i]->state));
+				&(adapter->tx_ring[i]->state));
 		/* re-enable flow director interrupts */
 		IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_FLOW_DIR);
 	} else {
@@ -7172,16 +7319,17 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p)
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct sockaddr *addr = p;
+	int ret;
 
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
+	ixgbe_del_mac_filter(adapter, hw->mac.addr, VMDQ_P(0));
 	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
 	memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len);
 
-	hw->mac.ops.set_rar(hw, 0, hw->mac.addr, VMDQ_P(0), IXGBE_RAH_AV);
-
-	return 0;
+	ret = ixgbe_add_mac_filter(adapter, hw->mac.addr, VMDQ_P(0));
+	return ret > 0 ? 0 : ret;
 }
 
 static int
@@ -7783,7 +7931,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_do_ioctl		= ixgbe_ioctl,
 	.ndo_set_vf_mac		= ixgbe_ndo_set_vf_mac,
 	.ndo_set_vf_vlan	= ixgbe_ndo_set_vf_vlan,
-	.ndo_set_vf_tx_rate	= ixgbe_ndo_set_vf_bw,
+	.ndo_set_vf_rate	= ixgbe_ndo_set_vf_bw,
 	.ndo_set_vf_spoofchk	= ixgbe_ndo_set_vf_spoofchk,
 	.ndo_get_vf_config	= ixgbe_ndo_get_vf_config,
 	.ndo_get_stats64	= ixgbe_get_stats64,
@@ -8187,6 +8335,8 @@ skip_sriov:
 		goto err_sw_init;
 	}
 
+	ixgbe_mac_set_default_filter(adapter, hw->mac.perm_addr);
+
 	setup_timer(&adapter->service_timer, &ixgbe_service_timer,
 		    (unsigned long) adapter);
 
@@ -8242,7 +8392,7 @@ skip_sriov:
 	if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present)
 		e_dev_info("MAC: %d, PHY: %d, SFP+: %d, PBA No: %s\n",
 			   hw->mac.type, hw->phy.type, hw->phy.sfp_type,
-		           part_str);
+			   part_str);
 	else
 		e_dev_info("MAC: %d, PHY: %d, PBA No: %s\n",
 			   hw->mac.type, hw->phy.type, part_str);
@@ -8304,8 +8454,8 @@ skip_sriov:
 
 	ixgbe_dbg_adapter_init(adapter);
 
-	/* Need link setup for MNG FW, else wait for IXGBE_UP */
-	if (ixgbe_mng_enabled(hw) && hw->mac.ops.setup_link)
+	/* setup link for SFP devices with MNG FW, else wait for IXGBE_UP */
+	if (ixgbe_mng_enabled(hw) && ixgbe_is_sfp(hw) && hw->mac.ops.setup_link)
 		hw->mac.ops.setup_link(hw,
 			IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL,
 			true);
@@ -8319,6 +8469,7 @@ err_sw_init:
 	ixgbe_disable_sriov(adapter);
 	adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP;
 	iounmap(adapter->io_addr);
+	kfree(adapter->mac_table);
 err_ioremap:
 	free_netdev(netdev);
 err_alloc_etherdev:
@@ -8392,6 +8543,7 @@ static void ixgbe_remove(struct pci_dev *pdev)
 
 	e_dev_info("complete\n");
 
+	kfree(adapter->mac_table);
 	free_netdev(netdev);
 
 	pci_disable_pcie_error_reporting(pdev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
index f5c6af2b891..1918e0abf73 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c
@@ -223,7 +223,7 @@ out:
  *  received an ack to that message within delay * timeout period
  **/
 static s32 ixgbe_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size,
-                           u16 mbx_id)
+			   u16 mbx_id)
 {
 	struct ixgbe_mbx_info *mbx = &hw->mbx;
 	s32 ret_val = IXGBE_ERR_MBX;
@@ -269,7 +269,7 @@ static s32 ixgbe_check_for_msg_pf(struct ixgbe_hw *hw, u16 vf_number)
 	u32 vf_bit = vf_number % 16;
 
 	if (!ixgbe_check_for_bit_pf(hw, IXGBE_MBVFICR_VFREQ_VF1 << vf_bit,
-	                            index)) {
+				    index)) {
 		ret_val = 0;
 		hw->mbx.stats.reqs++;
 	}
@@ -291,7 +291,7 @@ static s32 ixgbe_check_for_ack_pf(struct ixgbe_hw *hw, u16 vf_number)
 	u32 vf_bit = vf_number % 16;
 
 	if (!ixgbe_check_for_bit_pf(hw, IXGBE_MBVFICR_VFACK_VF1 << vf_bit,
-	                            index)) {
+				    index)) {
 		ret_val = 0;
 		hw->mbx.stats.acks++;
 	}
@@ -366,7 +366,7 @@ static s32 ixgbe_obtain_mbx_lock_pf(struct ixgbe_hw *hw, u16 vf_number)
  *  returns SUCCESS if it successfully copied message into the buffer
  **/
 static s32 ixgbe_write_mbx_pf(struct ixgbe_hw *hw, u32 *msg, u16 size,
-                              u16 vf_number)
+			      u16 vf_number)
 {
 	s32 ret_val;
 	u16 i;
@@ -407,7 +407,7 @@ out_no_write:
  *  a message due to a VF request so no polling for message is needed.
  **/
 static s32 ixgbe_read_mbx_pf(struct ixgbe_hw *hw, u32 *msg, u16 size,
-                             u16 vf_number)
+			     u16 vf_number)
 {
 	s32 ret_val;
 	u16 i;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
index a9b9ad69ed0..a5cb755de3a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h
@@ -54,11 +54,11 @@
  * Message ACK's are the value or'd with 0xF0000000
  */
 #define IXGBE_VT_MSGTYPE_ACK      0x80000000  /* Messages below or'd with
-                                               * this are the ACK */
+					       * this are the ACK */
 #define IXGBE_VT_MSGTYPE_NACK     0x40000000  /* Messages below or'd with
-                                               * this are the NACK */
+					       * this are the NACK */
 #define IXGBE_VT_MSGTYPE_CTS      0x20000000  /* Indicates that VF is still
-                                                 clear to send requests */
+						 clear to send requests */
 #define IXGBE_VT_MSGINFO_SHIFT    16
 /* bits 23:16 are used for exra info for certain messages */
 #define IXGBE_VT_MSGINFO_MASK     (0xFF << IXGBE_VT_MSGINFO_SHIFT)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index a76af8e28a0..ff68b7a9def 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -67,7 +67,7 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw)
 			if (mdio45_probe(&hw->phy.mdio, phy_addr) == 0) {
 				ixgbe_get_phy_id(hw);
 				hw->phy.type =
-				        ixgbe_get_phy_type_from_id(hw->phy.id);
+					ixgbe_get_phy_type_from_id(hw->phy.id);
 
 				if (hw->phy.type == ixgbe_phy_unknown) {
 					hw->phy.ops.read_reg(hw,
@@ -136,12 +136,12 @@ static s32 ixgbe_get_phy_id(struct ixgbe_hw *hw)
 	u16 phy_id_low = 0;
 
 	status = hw->phy.ops.read_reg(hw, MDIO_DEVID1, MDIO_MMD_PMAPMD,
-	                              &phy_id_high);
+				      &phy_id_high);
 
 	if (status == 0) {
 		hw->phy.id = (u32)(phy_id_high << 16);
 		status = hw->phy.ops.read_reg(hw, MDIO_DEVID2, MDIO_MMD_PMAPMD,
-		                              &phy_id_low);
+					      &phy_id_low);
 		hw->phy.id |= (u32)(phy_id_low & IXGBE_PHY_REVISION_MASK);
 		hw->phy.revision = (u32)(phy_id_low & ~IXGBE_PHY_REVISION_MASK);
 	}
@@ -318,7 +318,7 @@ s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type,
  *  @phy_data: Pointer to read data from PHY register
  **/
 s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
-                               u32 device_type, u16 *phy_data)
+			       u32 device_type, u16 *phy_data)
 {
 	s32 status;
 	u16 gssr;
@@ -421,7 +421,7 @@ s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr,
  *  @phy_data: Data to write to the PHY register
  **/
 s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
-                                u32 device_type, u16 phy_data)
+				u32 device_type, u16 phy_data)
 {
 	s32 status;
 	u16 gssr;
@@ -548,8 +548,8 @@ s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw)
  *  @speed: new link speed
  **/
 s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw,
-                                       ixgbe_link_speed speed,
-                                       bool autoneg_wait_to_complete)
+				       ixgbe_link_speed speed,
+				       bool autoneg_wait_to_complete)
 {
 
 	/*
@@ -582,8 +582,8 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw,
  * Determines the link capabilities by reading the AUTOC register.
  */
 s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw,
-                                               ixgbe_link_speed *speed,
-                                               bool *autoneg)
+					       ixgbe_link_speed *speed,
+					       bool *autoneg)
 {
 	s32 status = IXGBE_ERR_LINK_SETUP;
 	u16 speed_ability;
@@ -592,7 +592,7 @@ s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw,
 	*autoneg = true;
 
 	status = hw->phy.ops.read_reg(hw, MDIO_SPEED, MDIO_MMD_PMAPMD,
-	                              &speed_ability);
+				      &speed_ability);
 
 	if (status == 0) {
 		if (speed_ability & MDIO_SPEED_10G)
@@ -806,11 +806,11 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
 
 	/* reset the PHY and poll for completion */
 	hw->phy.ops.write_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS,
-	                      (phy_data | MDIO_CTRL1_RESET));
+			      (phy_data | MDIO_CTRL1_RESET));
 
 	for (i = 0; i < 100; i++) {
 		hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS,
-		                     &phy_data);
+				     &phy_data);
 		if ((phy_data & MDIO_CTRL1_RESET) == 0)
 			break;
 		usleep_range(10000, 20000);
@@ -824,7 +824,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
 
 	/* Get init offsets */
 	ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, &list_offset,
-	                                              &data_offset);
+						      &data_offset);
 	if (ret_val != 0)
 		goto out;
 
@@ -838,7 +838,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
 		if (ret_val)
 			goto err_eeprom;
 		control = (eword & IXGBE_CONTROL_MASK_NL) >>
-		           IXGBE_CONTROL_SHIFT_NL;
+			   IXGBE_CONTROL_SHIFT_NL;
 		edata = eword & IXGBE_DATA_MASK_NL;
 		switch (control) {
 		case IXGBE_DELAY_NL:
@@ -859,7 +859,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw)
 				if (ret_val)
 					goto err_eeprom;
 				hw->phy.ops.write_reg(hw, phy_offset,
-				                      MDIO_MMD_PMAPMD, eword);
+						      MDIO_MMD_PMAPMD, eword);
 				hw_dbg(hw, "Wrote %4.4x to %4.4x\n", eword,
 				       phy_offset);
 				data_offset++;
@@ -1010,10 +1010,10 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw)
 			if (cable_tech & IXGBE_SFF_DA_PASSIVE_CABLE) {
 				if (hw->bus.lan_id == 0)
 					hw->phy.sfp_type =
-					             ixgbe_sfp_type_da_cu_core0;
+						     ixgbe_sfp_type_da_cu_core0;
 				else
 					hw->phy.sfp_type =
-					             ixgbe_sfp_type_da_cu_core1;
+						     ixgbe_sfp_type_da_cu_core1;
 			} else if (cable_tech & IXGBE_SFF_DA_ACTIVE_CABLE) {
 				hw->phy.ops.read_i2c_eeprom(
 						hw, IXGBE_SFF_CABLE_SPEC_COMP,
@@ -1035,10 +1035,10 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw)
 				    IXGBE_SFF_10GBASELR_CAPABLE)) {
 				if (hw->bus.lan_id == 0)
 					hw->phy.sfp_type =
-					              ixgbe_sfp_type_srlr_core0;
+						      ixgbe_sfp_type_srlr_core0;
 				else
 					hw->phy.sfp_type =
-					              ixgbe_sfp_type_srlr_core1;
+						      ixgbe_sfp_type_srlr_core1;
 			} else if (comp_codes_1g & IXGBE_SFF_1GBASET_CAPABLE) {
 				if (hw->bus.lan_id == 0)
 					hw->phy.sfp_type =
@@ -1087,15 +1087,15 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw)
 				goto err_read_i2c_eeprom;
 
 			status = hw->phy.ops.read_i2c_eeprom(hw,
-			                            IXGBE_SFF_VENDOR_OUI_BYTE1,
-			                            &oui_bytes[1]);
+						    IXGBE_SFF_VENDOR_OUI_BYTE1,
+						    &oui_bytes[1]);
 
 			if (status != 0)
 				goto err_read_i2c_eeprom;
 
 			status = hw->phy.ops.read_i2c_eeprom(hw,
-			                            IXGBE_SFF_VENDOR_OUI_BYTE2,
-			                            &oui_bytes[2]);
+						    IXGBE_SFF_VENDOR_OUI_BYTE2,
+						    &oui_bytes[2]);
 
 			if (status != 0)
 				goto err_read_i2c_eeprom;
@@ -1403,8 +1403,8 @@ err_read_i2c_eeprom:
  *  so it returns the offsets to the phy init sequence block.
  **/
 s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
-                                        u16 *list_offset,
-                                        u16 *data_offset)
+					u16 *list_offset,
+					u16 *data_offset)
 {
 	u16 sfp_id;
 	u16 sfp_type = hw->phy.sfp_type;
@@ -1493,11 +1493,11 @@ err_phy:
  *  Performs byte read operation to SFP module's EEPROM over I2C interface.
  **/
 s32 ixgbe_read_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset,
-                                  u8 *eeprom_data)
+				  u8 *eeprom_data)
 {
 	return hw->phy.ops.read_i2c_byte(hw, byte_offset,
-	                                 IXGBE_I2C_EEPROM_DEV_ADDR,
-	                                 eeprom_data);
+					 IXGBE_I2C_EEPROM_DEV_ADDR,
+					 eeprom_data);
 }
 
 /**
@@ -1525,11 +1525,11 @@ s32 ixgbe_read_i2c_sff8472_generic(struct ixgbe_hw *hw, u8 byte_offset,
  *  Performs byte write operation to SFP module's EEPROM over I2C interface.
  **/
 s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset,
-                                   u8 eeprom_data)
+				   u8 eeprom_data)
 {
 	return hw->phy.ops.write_i2c_byte(hw, byte_offset,
-	                                  IXGBE_I2C_EEPROM_DEV_ADDR,
-	                                  eeprom_data);
+					  IXGBE_I2C_EEPROM_DEV_ADDR,
+					  eeprom_data);
 }
 
 /**
@@ -1542,7 +1542,7 @@ s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset,
  *  a specified device address.
  **/
 s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset,
-                                u8 dev_addr, u8 *data)
+				u8 dev_addr, u8 *data)
 {
 	s32 status = 0;
 	u32 max_retry = 10;
@@ -1631,7 +1631,7 @@ read_byte_out:
  *  a specified device address.
  **/
 s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset,
-                                 u8 dev_addr, u8 data)
+				 u8 dev_addr, u8 data)
 {
 	s32 status = 0;
 	u32 max_retry = 1;
@@ -2046,7 +2046,7 @@ s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw)
 
 	/* Check that the LASI temp alarm status was triggered */
 	hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG,
-	                     MDIO_MMD_PMAPMD, &phy_data);
+			     MDIO_MMD_PMAPMD, &phy_data);
 
 	if (!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM))
 		goto out;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index 0bb047f751c..54071ed17e3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -114,47 +114,47 @@ s32 ixgbe_init_phy_ops_generic(struct ixgbe_hw *hw);
 s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw);
 s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw);
 s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
-                               u32 device_type, u16 *phy_data);
+			       u32 device_type, u16 *phy_data);
 s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
-                                u32 device_type, u16 phy_data);
+				u32 device_type, u16 phy_data);
 s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr,
 			   u32 device_type, u16 *phy_data);
 s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr,
 			    u32 device_type, u16 phy_data);
 s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw);
 s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw,
-                                       ixgbe_link_speed speed,
-                                       bool autoneg_wait_to_complete);
+				       ixgbe_link_speed speed,
+				       bool autoneg_wait_to_complete);
 s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw,
-                                               ixgbe_link_speed *speed,
-                                               bool *autoneg);
+					       ixgbe_link_speed *speed,
+					       bool *autoneg);
 bool ixgbe_check_reset_blocked(struct ixgbe_hw *hw);
 
 /* PHY specific */
 s32 ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw,
-                             ixgbe_link_speed *speed,
-                             bool *link_up);
+			     ixgbe_link_speed *speed,
+			     bool *link_up);
 s32 ixgbe_setup_phy_link_tnx(struct ixgbe_hw *hw);
 s32 ixgbe_get_phy_firmware_version_tnx(struct ixgbe_hw *hw,
-                                       u16 *firmware_version);
+				       u16 *firmware_version);
 s32 ixgbe_get_phy_firmware_version_generic(struct ixgbe_hw *hw,
-                                           u16 *firmware_version);
+					   u16 *firmware_version);
 
 s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw);
 s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw);
 s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw);
 s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw,
-                                        u16 *list_offset,
-                                        u16 *data_offset);
+					u16 *list_offset,
+					u16 *data_offset);
 s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw);
 s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset,
-                                u8 dev_addr, u8 *data);
+				u8 dev_addr, u8 *data);
 s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset,
-                                 u8 dev_addr, u8 data);
+				 u8 dev_addr, u8 data);
 s32 ixgbe_read_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset,
-                                  u8 *eeprom_data);
+				  u8 *eeprom_data);
 s32 ixgbe_read_i2c_sff8472_generic(struct ixgbe_hw *hw, u8 byte_offset,
 				   u8 *sff8472_data);
 s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset,
-                                   u8 eeprom_data);
+				   u8 eeprom_data);
 #endif /* _IXGBE_PHY_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 8902ae68345..68f87ecb8a7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -26,7 +26,6 @@
 
 *******************************************************************************/
 #include "ixgbe.h"
-#include <linux/export.h>
 #include <linux/ptp_classify.h>
 
 /*
@@ -334,7 +333,7 @@ static int ixgbe_ptp_settime(struct ptp_clock_info *ptp,
 }
 
 /**
- * ixgbe_ptp_enable
+ * ixgbe_ptp_feature_enable
  * @ptp: the ptp clock structure
  * @rq: the requested feature to change
  * @on: whether to enable or disable the feature
@@ -342,8 +341,8 @@ static int ixgbe_ptp_settime(struct ptp_clock_info *ptp,
  * enable (or disable) ancillary features of the phc subsystem.
  * our driver only supports the PPS feature on the X540
  */
-static int ixgbe_ptp_enable(struct ptp_clock_info *ptp,
-			    struct ptp_clock_request *rq, int on)
+static int ixgbe_ptp_feature_enable(struct ptp_clock_info *ptp,
+				    struct ptp_clock_request *rq, int on)
 {
 	struct ixgbe_adapter *adapter =
 		container_of(ptp, struct ixgbe_adapter, ptp_caps);
@@ -570,9 +569,9 @@ int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
 }
 
 /**
- * ixgbe_ptp_set_ts_config - control hardware time stamping
- * @adapter: pointer to adapter struct
- * @ifreq: ioctl data
+ * ixgbe_ptp_set_timestamp_mode - setup the hardware for the requested mode
+ * @adapter: the private ixgbe adapter structure
+ * @config: the hwtstamp configuration requested
  *
  * Outgoing time stamping can be enabled and disabled. Play nice and
  * disable it when requested, although it shouldn't cause any overhead
@@ -590,25 +589,25 @@ int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
  * packets, regardless of the type specified in the register, only use V2
  * Event mode. This more accurately tells the user what the hardware is going
  * to do anyways.
+ *
+ * Note: this may modify the hwtstamp configuration towards a more general
+ * mode, if required to support the specifically requested mode.
  */
-int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
+static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
+				 struct hwtstamp_config *config)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
-	struct hwtstamp_config config;
 	u32 tsync_tx_ctl = IXGBE_TSYNCTXCTL_ENABLED;
 	u32 tsync_rx_ctl = IXGBE_TSYNCRXCTL_ENABLED;
 	u32 tsync_rx_mtrl = PTP_EV_PORT << 16;
 	bool is_l2 = false;
 	u32 regval;
 
-	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
-		return -EFAULT;
-
 	/* reserved for future extensions */
-	if (config.flags)
+	if (config->flags)
 		return -EINVAL;
 
-	switch (config.tx_type) {
+	switch (config->tx_type) {
 	case HWTSTAMP_TX_OFF:
 		tsync_tx_ctl = 0;
 	case HWTSTAMP_TX_ON:
@@ -617,7 +616,7 @@ int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
 		return -ERANGE;
 	}
 
-	switch (config.rx_filter) {
+	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		tsync_rx_ctl = 0;
 		tsync_rx_mtrl = 0;
@@ -641,7 +640,7 @@ int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
 		tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2;
 		is_l2 = true;
-		config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_ALL:
@@ -652,7 +651,7 @@ int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
 		 * Delay_Req messages and hardware does not support
 		 * timestamping all packets => return error
 		 */
-		config.rx_filter = HWTSTAMP_FILTER_NONE;
+		config->rx_filter = HWTSTAMP_FILTER_NONE;
 		return -ERANGE;
 	}
 
@@ -671,7 +670,6 @@ int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
 	else
 		IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_1588), 0);
 
-
 	/* enable/disable TX */
 	regval = IXGBE_READ_REG(hw, IXGBE_TSYNCTXCTL);
 	regval &= ~IXGBE_TSYNCTXCTL_ENABLED;
@@ -693,6 +691,29 @@ int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
 	regval = IXGBE_READ_REG(hw, IXGBE_TXSTMPH);
 	regval = IXGBE_READ_REG(hw, IXGBE_RXSTMPH);
 
+	return 0;
+}
+
+/**
+ * ixgbe_ptp_set_ts_config - user entry point for timestamp mode
+ * @adapter: pointer to adapter struct
+ * @ifreq: ioctl data
+ *
+ * Set hardware to requested mode. If unsupported, return an error with no
+ * changes. Otherwise, store the mode for future reference.
+ */
+int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr)
+{
+	struct hwtstamp_config config;
+	int err;
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	err = ixgbe_ptp_set_timestamp_mode(adapter, &config);
+	if (err)
+		return err;
+
 	/* save these settings for future reference */
 	memcpy(&adapter->tstamp_config, &config,
 	       sizeof(adapter->tstamp_config));
@@ -790,9 +811,13 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
  * ixgbe_ptp_reset
  * @adapter: the ixgbe private board structure
  *
- * When the MAC resets, all timesync features are reset. This function should be
- * called to re-enable the PTP clock structure. It will re-init the timecounter
- * structure based on the kernel time as well as setup the cycle counter data.
+ * When the MAC resets, all the hardware bits for timesync are reset. This
+ * function is used to re-enable the device for PTP based on current settings.
+ * We do lose the current clock time, so just reset the cyclecounter to the
+ * system real clock time.
+ *
+ * This function will maintain hwtstamp_config settings, and resets the SDP
+ * output if it was enabled.
  */
 void ixgbe_ptp_reset(struct ixgbe_adapter *adapter)
 {
@@ -804,8 +829,8 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter)
 	IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0x00000000);
 	IXGBE_WRITE_FLUSH(hw);
 
-	/* Reset the saved tstamp_config */
-	memset(&adapter->tstamp_config, 0, sizeof(adapter->tstamp_config));
+	/* reset the hardware timestamping mode */
+	ixgbe_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config);
 
 	ixgbe_ptp_start_cyclecounter(adapter);
 
@@ -825,16 +850,23 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter)
 }
 
 /**
- * ixgbe_ptp_init
+ * ixgbe_ptp_create_clock
  * @adapter: the ixgbe private adapter structure
  *
- * This function performs the required steps for enabling ptp
- * support. If ptp support has already been loaded it simply calls the
- * cyclecounter init routine and exits.
+ * This function performs setup of the user entry point function table and
+ * initializes the PTP clock device, which is used to access the clock-like
+ * features of the PTP core. It will be called by ixgbe_ptp_init, only if
+ * there isn't already a clock device (such as after a suspend/resume cycle,
+ * where the clock device wasn't destroyed).
  */
-void ixgbe_ptp_init(struct ixgbe_adapter *adapter)
+static int ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
+	long err;
+
+	/* do nothing if we already have a clock device */
+	if (!IS_ERR_OR_NULL(adapter->ptp_clock))
+		return 0;
 
 	switch (adapter->hw.mac.type) {
 	case ixgbe_mac_X540:
@@ -851,7 +883,7 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
 		adapter->ptp_caps.gettime = ixgbe_ptp_gettime;
 		adapter->ptp_caps.settime = ixgbe_ptp_settime;
-		adapter->ptp_caps.enable = ixgbe_ptp_enable;
+		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
 		break;
 	case ixgbe_mac_82599EB:
 		snprintf(adapter->ptp_caps.name,
@@ -867,24 +899,57 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
 		adapter->ptp_caps.gettime = ixgbe_ptp_gettime;
 		adapter->ptp_caps.settime = ixgbe_ptp_settime;
-		adapter->ptp_caps.enable = ixgbe_ptp_enable;
+		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
 		break;
 	default:
 		adapter->ptp_clock = NULL;
-		return;
+		return -EOPNOTSUPP;
 	}
 
-	spin_lock_init(&adapter->tmreg_lock);
-	INIT_WORK(&adapter->ptp_tx_work, ixgbe_ptp_tx_hwtstamp_work);
-
 	adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps,
 						&adapter->pdev->dev);
 	if (IS_ERR(adapter->ptp_clock)) {
+		err = PTR_ERR(adapter->ptp_clock);
 		adapter->ptp_clock = NULL;
 		e_dev_err("ptp_clock_register failed\n");
+		return err;
 	} else
 		e_dev_info("registered PHC device on %s\n", netdev->name);
 
+	/* set default timestamp mode to disabled here. We do this in
+	 * create_clock instead of init, because we don't want to override the
+	 * previous settings during a resume cycle.
+	 */
+	adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+
+	return 0;
+}
+
+/**
+ * ixgbe_ptp_init
+ * @adapter: the ixgbe private adapter structure
+ *
+ * This function performs the required steps for enabling PTP
+ * support. If PTP support has already been loaded it simply calls the
+ * cyclecounter init routine and exits.
+ */
+void ixgbe_ptp_init(struct ixgbe_adapter *adapter)
+{
+	/* initialize the spin lock first since we can't control when a user
+	 * will call the entry functions once we have initialized the clock
+	 * device
+	 */
+	spin_lock_init(&adapter->tmreg_lock);
+
+	/* obtain a PTP device, or re-use an existing device */
+	if (ixgbe_ptp_create_clock(adapter))
+		return;
+
+	/* we have a clock so we can initialize work now */
+	INIT_WORK(&adapter->ptp_tx_work, ixgbe_ptp_tx_hwtstamp_work);
+
+	/* reset the PTP related hardware bits */
 	ixgbe_ptp_reset(adapter);
 
 	/* enter the IXGBE_PTP_RUNNING state */
@@ -894,28 +959,45 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter)
 }
 
 /**
- * ixgbe_ptp_stop - disable ptp device and stop the overflow check
- * @adapter: pointer to adapter struct
+ * ixgbe_ptp_suspend - stop PTP work items
+ * @ adapter: pointer to adapter struct
  *
- * this function stops the ptp support, and cancels the delayed work.
+ * this function suspends PTP activity, and prevents more PTP work from being
+ * generated, but does not destroy the PTP clock device.
  */
-void ixgbe_ptp_stop(struct ixgbe_adapter *adapter)
+void ixgbe_ptp_suspend(struct ixgbe_adapter *adapter)
 {
 	/* Leave the IXGBE_PTP_RUNNING state. */
 	if (!test_and_clear_bit(__IXGBE_PTP_RUNNING, &adapter->state))
 		return;
 
-	/* stop the PPS signal */
-	adapter->flags2 &= ~IXGBE_FLAG2_PTP_PPS_ENABLED;
-	ixgbe_ptp_setup_sdp(adapter);
+	/* since this might be called in suspend, we don't clear the state,
+	 * but simply reset the auxiliary PPS signal control register
+	 */
+	IXGBE_WRITE_REG(&adapter->hw, IXGBE_TSAUXC, 0x0);
 
+	/* ensure that we cancel any pending PTP Tx work item in progress */
 	cancel_work_sync(&adapter->ptp_tx_work);
 	if (adapter->ptp_tx_skb) {
 		dev_kfree_skb_any(adapter->ptp_tx_skb);
 		adapter->ptp_tx_skb = NULL;
 		clear_bit_unlock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state);
 	}
+}
+
+/**
+ * ixgbe_ptp_stop - close the PTP device
+ * @adapter: pointer to adapter struct
+ *
+ * completely destroy the PTP device, should only be called when the device is
+ * being fully closed.
+ */
+void ixgbe_ptp_stop(struct ixgbe_adapter *adapter)
+{
+	/* first, suspend PTP activity */
+	ixgbe_ptp_suspend(adapter);
 
+	/* disable the PTP clock device */
 	if (adapter->ptp_clock) {
 		ptp_clock_unregister(adapter->ptp_clock);
 		adapter->ptp_clock = NULL;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index e6c68d396c9..16b3a1cd9db 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -72,8 +72,6 @@ static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter)
 		for (i = 0; i < num_vf_macvlans; i++) {
 			mv_list->vf = -1;
 			mv_list->free = true;
-			mv_list->rar_entry = hw->mac.num_rar_entries -
-				(i + adapter->num_vfs + 1);
 			list_add(&mv_list->l, &adapter->vf_mvs.l);
 			mv_list++;
 		}
@@ -327,6 +325,7 @@ static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter,
 	u32 vector_bit;
 	u32 vector_reg;
 	u32 mta_reg;
+	u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
 
 	/* only so many hash values supported */
 	entries = min(entries, IXGBE_MAX_VF_MC_ENTRIES);
@@ -353,25 +352,13 @@ static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter,
 		mta_reg |= (1 << vector_bit);
 		IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg);
 	}
+	vmolr |= IXGBE_VMOLR_ROMPE;
+	IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr);
 
 	return 0;
 }
 
-static void ixgbe_restore_vf_macvlans(struct ixgbe_adapter *adapter)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	struct list_head *pos;
-	struct vf_macvlans *entry;
-
-	list_for_each(pos, &adapter->vf_mvs.l) {
-		entry = list_entry(pos, struct vf_macvlans, l);
-		if (!entry->free)
-			hw->mac.ops.set_rar(hw, entry->rar_entry,
-					    entry->vf_macvlan,
-					    entry->vf, IXGBE_RAH_AV);
-	}
-}
-
+#ifdef CONFIG_PCI_IOV
 void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -382,6 +369,7 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter)
 	u32 mta_reg;
 
 	for (i = 0; i < adapter->num_vfs; i++) {
+		u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(i));
 		vfinfo = &adapter->vfinfo[i];
 		for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) {
 			hw->addr_ctrl.mta_in_use++;
@@ -391,11 +379,18 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter)
 			mta_reg |= (1 << vector_bit);
 			IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg);
 		}
+
+		if (vfinfo->num_vf_mc_hashes)
+			vmolr |= IXGBE_VMOLR_ROMPE;
+		else
+			vmolr &= ~IXGBE_VMOLR_ROMPE;
+		IXGBE_WRITE_REG(hw, IXGBE_VMOLR(i), vmolr);
 	}
 
 	/* Restore any VF macvlans */
-	ixgbe_restore_vf_macvlans(adapter);
+	ixgbe_full_sync_mac_table(adapter);
 }
+#endif
 
 static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid,
 			     u32 vf)
@@ -495,8 +490,7 @@ static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe)
 {
 	u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf));
-	vmolr |= (IXGBE_VMOLR_ROMPE |
-		  IXGBE_VMOLR_BAM);
+	vmolr |= IXGBE_VMOLR_BAM;
 	if (aupe)
 		vmolr |= IXGBE_VMOLR_AUPE;
 	else
@@ -514,7 +508,6 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
 	struct vf_data_storage *vfinfo = &adapter->vfinfo[vf];
-	int rar_entry = hw->mac.num_rar_entries - (vf + 1);
 	u8 num_tcs = netdev_get_num_tc(adapter->netdev);
 
 	/* add PF assigned VLAN or VLAN 0 */
@@ -544,7 +537,7 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
 	/* Flush and reset the mta with the new values */
 	ixgbe_set_rx_mode(adapter->netdev);
 
-	hw->mac.ops.clear_rar(hw, rar_entry);
+	ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf);
 
 	/* reset VF api back to unknown */
 	adapter->vfinfo[vf].vf_api = ixgbe_mbox_api_10;
@@ -553,11 +546,9 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf)
 static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
 			    int vf, unsigned char *mac_addr)
 {
-	struct ixgbe_hw *hw = &adapter->hw;
-	int rar_entry = hw->mac.num_rar_entries - (vf + 1);
-
+	ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf);
 	memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, ETH_ALEN);
-	hw->mac.ops.set_rar(hw, rar_entry, mac_addr, vf, IXGBE_RAH_AV);
+	ixgbe_add_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf);
 
 	return 0;
 }
@@ -565,7 +556,6 @@ static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter,
 static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter,
 				int vf, int index, unsigned char *mac_addr)
 {
-	struct ixgbe_hw *hw = &adapter->hw;
 	struct list_head *pos;
 	struct vf_macvlans *entry;
 
@@ -576,7 +566,8 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter,
 				entry->vf = -1;
 				entry->free = true;
 				entry->is_macvlan = false;
-				hw->mac.ops.clear_rar(hw, entry->rar_entry);
+				ixgbe_del_mac_filter(adapter,
+						     entry->vf_macvlan, vf);
 			}
 		}
 	}
@@ -612,7 +603,7 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter,
 	entry->vf = vf;
 	memcpy(entry->vf_macvlan, mac_addr, ETH_ALEN);
 
-	hw->mac.ops.set_rar(hw, entry->rar_entry, mac_addr, vf, IXGBE_RAH_AV);
+	ixgbe_add_mac_filter(adapter, mac_addr, vf);
 
 	return 0;
 }
@@ -1138,9 +1129,9 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos)
 			adapter->vfinfo[vf].vlan_count--;
 		adapter->vfinfo[vf].pf_vlan = 0;
 		adapter->vfinfo[vf].pf_qos = 0;
-       }
+	}
 out:
-       return err;
+	return err;
 }
 
 static int ixgbe_link_mbps(struct ixgbe_adapter *adapter)
@@ -1231,7 +1222,8 @@ void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter)
 	}
 }
 
-int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
+int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate,
+			int max_tx_rate)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	int link_speed;
@@ -1249,13 +1241,16 @@ int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate)
 	if (link_speed != 10000)
 		return -EINVAL;
 
+	if (min_tx_rate)
+		return -EINVAL;
+
 	/* rate limit cannot be less than 10Mbs or greater than link speed */
-	if (tx_rate && ((tx_rate <= 10) || (tx_rate > link_speed)))
+	if (max_tx_rate && ((max_tx_rate <= 10) || (max_tx_rate > link_speed)))
 		return -EINVAL;
 
 	/* store values */
 	adapter->vf_rate_link_speed = link_speed;
-	adapter->vfinfo[vf].tx_rate = tx_rate;
+	adapter->vfinfo[vf].tx_rate = max_tx_rate;
 
 	/* update hardware configuration */
 	ixgbe_set_vf_rate_limit(adapter, vf);
@@ -1297,7 +1292,8 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 		return -EINVAL;
 	ivi->vf = vf;
 	memcpy(&ivi->mac, adapter->vfinfo[vf].vf_mac_addresses, ETH_ALEN);
-	ivi->tx_rate = adapter->vfinfo[vf].tx_rate;
+	ivi->max_tx_rate = adapter->vfinfo[vf].tx_rate;
+	ivi->min_tx_rate = 0;
 	ivi->vlan = adapter->vfinfo[vf].pf_vlan;
 	ivi->qos = adapter->vfinfo[vf].pf_qos;
 	ivi->spoofchk = adapter->vfinfo[vf].spoofchk_enabled;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
index 139eaddfb2e..32c26d586c0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
@@ -34,7 +34,9 @@
  */
 #define IXGBE_MAX_VFS_DRV_LIMIT  (IXGBE_MAX_VF_FUNCTIONS - 1)
 
+#ifdef CONFIG_PCI_IOV
 void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter);
+#endif
 void ixgbe_msg_task(struct ixgbe_adapter *adapter);
 int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask);
 void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter);
@@ -42,7 +44,8 @@ void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter);
 int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int queue, u8 *mac);
 int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int queue, u16 vlan,
 			   u8 qos);
-int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate);
+int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate,
+			int max_tx_rate);
 int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting);
 int ixgbe_ndo_get_vf_config(struct net_device *netdev,
 			    int vf, struct ifla_vf_info *ivi);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 8a6ff2423f0..9a89f98b35f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -160,7 +160,7 @@ struct ixgbe_thermal_sensor_data {
 #define IXGBE_MAX_EITR     0x00000FF8
 #define IXGBE_MIN_EITR     8
 #define IXGBE_EITR(_i)  (((_i) <= 23) ? (0x00820 + ((_i) * 4)) : \
-                         (0x012300 + (((_i) - 24) * 4)))
+			 (0x012300 + (((_i) - 24) * 4)))
 #define IXGBE_EITR_ITR_INT_MASK 0x00000FF8
 #define IXGBE_EITR_LLI_MOD      0x00008000
 #define IXGBE_EITR_CNT_WDIS     0x80000000
@@ -213,7 +213,7 @@ struct ixgbe_thermal_sensor_data {
  * 64-127: 0x0D014 + (n-64)*0x40
  */
 #define IXGBE_SRRCTL(_i) (((_i) <= 15) ? (0x02100 + ((_i) * 4)) : \
-                          (((_i) < 64) ? (0x01014 + ((_i) * 0x40)) : \
+			  (((_i) < 64) ? (0x01014 + ((_i) * 0x40)) : \
 			  (0x0D014 + (((_i) - 64) * 0x40))))
 /*
  * Rx DCA Control Register:
@@ -222,11 +222,11 @@ struct ixgbe_thermal_sensor_data {
  * 64-127: 0x0D00C + (n-64)*0x40
  */
 #define IXGBE_DCA_RXCTRL(_i)    (((_i) <= 15) ? (0x02200 + ((_i) * 4)) : \
-                                 (((_i) < 64) ? (0x0100C + ((_i) * 0x40)) : \
+				 (((_i) < 64) ? (0x0100C + ((_i) * 0x40)) : \
 				 (0x0D00C + (((_i) - 64) * 0x40))))
 #define IXGBE_RDRXCTL           0x02F00
 #define IXGBE_RXPBSIZE(_i)      (0x03C00 + ((_i) * 4))
-                                             /* 8 of these 0x03C00 - 0x03C1C */
+					     /* 8 of these 0x03C00 - 0x03C1C */
 #define IXGBE_RXCTRL    0x03000
 #define IXGBE_DROPEN    0x03D04
 #define IXGBE_RXPBSIZE_SHIFT 10
@@ -239,14 +239,14 @@ struct ixgbe_thermal_sensor_data {
 /* Multicast Table Array - 128 entries */
 #define IXGBE_MTA(_i)   (0x05200 + ((_i) * 4))
 #define IXGBE_RAL(_i)   (((_i) <= 15) ? (0x05400 + ((_i) * 8)) : \
-                         (0x0A200 + ((_i) * 8)))
+			 (0x0A200 + ((_i) * 8)))
 #define IXGBE_RAH(_i)   (((_i) <= 15) ? (0x05404 + ((_i) * 8)) : \
-                         (0x0A204 + ((_i) * 8)))
+			 (0x0A204 + ((_i) * 8)))
 #define IXGBE_MPSAR_LO(_i) (0x0A600 + ((_i) * 8))
 #define IXGBE_MPSAR_HI(_i) (0x0A604 + ((_i) * 8))
 /* Packet split receive type */
 #define IXGBE_PSRTYPE(_i)    (((_i) <= 15) ? (0x05480 + ((_i) * 4)) : \
-                              (0x0EA00 + ((_i) * 4)))
+			      (0x0EA00 + ((_i) * 4)))
 /* array of 4096 1-bit vlan filters */
 #define IXGBE_VFTA(_i)  (0x0A000 + ((_i) * 4))
 /*array of 4096 4-bit vlan vmdq indices */
@@ -696,7 +696,7 @@ struct ixgbe_thermal_sensor_data {
 
 #define IXGBE_RQSMR(_i) (0x02300 + ((_i) * 4))
 #define IXGBE_TQSMR(_i) (((_i) <= 7) ? (0x07300 + ((_i) * 4)) : \
-                         (0x08600 + ((_i) * 4)))
+			 (0x08600 + ((_i) * 4)))
 #define IXGBE_TQSM(_i)  (0x08600 + ((_i) * 4))
 
 #define IXGBE_QPRC(_i) (0x01030 + ((_i) * 0x40)) /* 16 of these */
@@ -820,7 +820,7 @@ struct ixgbe_thermal_sensor_data {
 #define IXGBE_GCR_EXT_VT_MODE_32        0x00000002
 #define IXGBE_GCR_EXT_VT_MODE_64        0x00000003
 #define IXGBE_GCR_EXT_SRIOV             (IXGBE_GCR_EXT_MSIX_EN | \
-                                         IXGBE_GCR_EXT_VT_MODE_64)
+					 IXGBE_GCR_EXT_VT_MODE_64)
 
 /* Time Sync Registers */
 #define IXGBE_TSYNCRXCTL 0x05188 /* Rx Time Sync Control register - RW */
@@ -1396,10 +1396,10 @@ enum {
 #define IXGBE_EIMC_OTHER        IXGBE_EICR_OTHER     /* INT Cause Active */
 
 #define IXGBE_EIMS_ENABLE_MASK ( \
-                                IXGBE_EIMS_RTX_QUEUE       | \
-                                IXGBE_EIMS_LSC             | \
-                                IXGBE_EIMS_TCP_TIMER       | \
-                                IXGBE_EIMS_OTHER)
+				IXGBE_EIMS_RTX_QUEUE       | \
+				IXGBE_EIMS_LSC             | \
+				IXGBE_EIMS_TCP_TIMER       | \
+				IXGBE_EIMS_OTHER)
 
 /* Immediate Interrupt Rx (A.K.A. Low Latency Interrupt) */
 #define IXGBE_IMIR_PORT_IM_EN     0x00010000  /* TCP port enable */
@@ -2161,18 +2161,18 @@ enum {
 
 /* Masks to determine if packets should be dropped due to frame errors */
 #define IXGBE_RXD_ERR_FRAME_ERR_MASK ( \
-                                      IXGBE_RXD_ERR_CE | \
-                                      IXGBE_RXD_ERR_LE | \
-                                      IXGBE_RXD_ERR_PE | \
-                                      IXGBE_RXD_ERR_OSE | \
-                                      IXGBE_RXD_ERR_USE)
+				      IXGBE_RXD_ERR_CE | \
+				      IXGBE_RXD_ERR_LE | \
+				      IXGBE_RXD_ERR_PE | \
+				      IXGBE_RXD_ERR_OSE | \
+				      IXGBE_RXD_ERR_USE)
 
 #define IXGBE_RXDADV_ERR_FRAME_ERR_MASK ( \
-                                      IXGBE_RXDADV_ERR_CE | \
-                                      IXGBE_RXDADV_ERR_LE | \
-                                      IXGBE_RXDADV_ERR_PE | \
-                                      IXGBE_RXDADV_ERR_OSE | \
-                                      IXGBE_RXDADV_ERR_USE)
+				      IXGBE_RXDADV_ERR_CE | \
+				      IXGBE_RXDADV_ERR_LE | \
+				      IXGBE_RXDADV_ERR_PE | \
+				      IXGBE_RXDADV_ERR_OSE | \
+				      IXGBE_RXDADV_ERR_USE)
 
 /* Multicast bit mask */
 #define IXGBE_MCSTCTRL_MFE      0x4
@@ -2393,9 +2393,9 @@ struct ixgbe_adv_tx_context_desc {
 #define IXGBE_ADVTXD_CC         0x00000080 /* Check Context */
 #define IXGBE_ADVTXD_POPTS_SHIFT      8  /* Adv desc POPTS shift */
 #define IXGBE_ADVTXD_POPTS_IXSM (IXGBE_TXD_POPTS_IXSM << \
-                                 IXGBE_ADVTXD_POPTS_SHIFT)
+				 IXGBE_ADVTXD_POPTS_SHIFT)
 #define IXGBE_ADVTXD_POPTS_TXSM (IXGBE_TXD_POPTS_TXSM << \
-                                 IXGBE_ADVTXD_POPTS_SHIFT)
+				 IXGBE_ADVTXD_POPTS_SHIFT)
 #define IXGBE_ADVTXD_POPTS_ISCO_1ST  0x00000000 /* 1st TSO of iSCSI PDU */
 #define IXGBE_ADVTXD_POPTS_ISCO_MDL  0x00000800 /* Middle TSO of iSCSI PDU */
 #define IXGBE_ADVTXD_POPTS_ISCO_LAST 0x00001000 /* Last TSO of iSCSI PDU */
@@ -2435,10 +2435,10 @@ typedef u32 ixgbe_link_speed;
 #define IXGBE_LINK_SPEED_1GB_FULL  0x0020
 #define IXGBE_LINK_SPEED_10GB_FULL 0x0080
 #define IXGBE_LINK_SPEED_82598_AUTONEG (IXGBE_LINK_SPEED_1GB_FULL | \
-                                        IXGBE_LINK_SPEED_10GB_FULL)
+					IXGBE_LINK_SPEED_10GB_FULL)
 #define IXGBE_LINK_SPEED_82599_AUTONEG (IXGBE_LINK_SPEED_100_FULL | \
-                                        IXGBE_LINK_SPEED_1GB_FULL | \
-                                        IXGBE_LINK_SPEED_10GB_FULL)
+					IXGBE_LINK_SPEED_1GB_FULL | \
+					IXGBE_LINK_SPEED_10GB_FULL)
 
 
 /* Physical layer type */
@@ -2746,7 +2746,7 @@ struct ixgbe_bus_info {
 /* Flow control parameters */
 struct ixgbe_fc_info {
 	u32 high_water[MAX_TRAFFIC_CLASS]; /* Flow Control High-water */
-	u32 low_water; /* Flow Control Low-water */
+	u32 low_water[MAX_TRAFFIC_CLASS]; /* Flow Control Low-water */
 	u16 pause_time; /* Flow Control Pause timer */
 	bool send_xon; /* Flow control send XON */
 	bool strict_ieee; /* Strict IEEE mode */
@@ -2840,7 +2840,7 @@ struct ixgbe_hw;
 
 /* iterator type for walking multicast address lists */
 typedef u8* (*ixgbe_mc_addr_itr) (struct ixgbe_hw *hw, u8 **mc_addr_ptr,
-                                  u32 *vmdq);
+				  u32 *vmdq);
 
 /* Function pointer table */
 struct ixgbe_eeprom_operations {
@@ -2887,7 +2887,7 @@ struct ixgbe_mac_operations {
 	s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool);
 	s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *, bool);
 	s32 (*get_link_capabilities)(struct ixgbe_hw *, ixgbe_link_speed *,
-	                             bool *);
+				     bool *);
 
 	/* Packet Buffer Manipulation */
 	void (*set_rxpba)(struct ixgbe_hw *, int, u32, int);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index 188a5974b85..40dd798e129 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -81,7 +81,7 @@ static s32 ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw,
 				     bool autoneg_wait_to_complete)
 {
 	return hw->phy.ops.setup_link_speed(hw, speed,
-	                                    autoneg_wait_to_complete);
+					    autoneg_wait_to_complete);
 }
 
 /**
@@ -155,7 +155,7 @@ mac_reset_top:
 	/* Add the SAN MAC address to the RAR only if it's a valid address */
 	if (is_valid_ether_addr(hw->mac.san_addr)) {
 		hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1,
-		                    hw->mac.san_addr, 0, IXGBE_RAH_AV);
+				    hw->mac.san_addr, 0, IXGBE_RAH_AV);
 
 		/* Save the SAN MAC RAR index */
 		hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1;
@@ -166,7 +166,7 @@ mac_reset_top:
 
 	/* Store the alternative WWNN/WWPN prefix */
 	hw->mac.ops.get_wwn_prefix(hw, &hw->mac.wwnn_prefix,
-	                           &hw->mac.wwpn_prefix);
+				   &hw->mac.wwpn_prefix);
 
 reset_hw_out:
 	return status;
@@ -237,9 +237,9 @@ static s32 ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw)
 
 		eec = IXGBE_READ_REG(hw, IXGBE_EEC);
 		eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >>
-		                    IXGBE_EEC_SIZE_SHIFT);
+				    IXGBE_EEC_SIZE_SHIFT);
 		eeprom->word_size = 1 << (eeprom_size +
-		                          IXGBE_EEPROM_WORD_SIZE_SHIFT);
+					  IXGBE_EEPROM_WORD_SIZE_SHIFT);
 
 		hw_dbg(hw, "Eeprom params: type = %d, size = %d\n",
 		       eeprom->type, eeprom->word_size);
@@ -712,8 +712,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw)
 			udelay(50);
 		}
 	} else {
-		hw_dbg(hw, "Software semaphore SMBI between device drivers "
-		           "not granted.\n");
+		hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n");
 	}
 
 	return status;
@@ -813,7 +812,7 @@ static struct ixgbe_mac_operations mac_ops_X540 = {
 	.clear_hw_cntrs         = &ixgbe_clear_hw_cntrs_generic,
 	.get_media_type         = &ixgbe_get_media_type_X540,
 	.get_supported_physical_layer =
-                                  &ixgbe_get_supported_physical_layer_X540,
+				  &ixgbe_get_supported_physical_layer_X540,
 	.enable_rx_dma          = &ixgbe_enable_rx_dma_generic,
 	.get_mac_addr           = &ixgbe_get_mac_addr_generic,
 	.get_san_mac_addr       = &ixgbe_get_san_mac_addr_generic,
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index 1baecb60f06..d420f124633 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -135,8 +135,8 @@ static int ixgbevf_get_settings(struct net_device *netdev,
 		ethtool_cmd_speed_set(ecmd, speed);
 		ecmd->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	return 0;
@@ -813,5 +813,5 @@ static const struct ethtool_ops ixgbevf_ethtool_ops = {
 
 void ixgbevf_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &ixgbevf_ethtool_ops);
+	netdev->ethtool_ops = &ixgbevf_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index de2793b0630..75467f83772 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -85,7 +85,7 @@ static DEFINE_PCI_DEVICE_TABLE(ixgbevf_pci_tbl) = {
 MODULE_DEVICE_TABLE(pci, ixgbevf_pci_tbl);
 
 MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
-MODULE_DESCRIPTION("Intel(R) 82599 Virtual Function Driver");
+MODULE_DESCRIPTION("Intel(R) 10 Gigabit Virtual Function Network Driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index b7b8d74c22d..b151a949f35 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -42,6 +42,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/in.h>
 #include <linux/ip.h>
+#include <net/tso.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/etherdevice.h>
@@ -179,10 +180,18 @@ static char mv643xx_eth_driver_version[] = "1.4";
  * Misc definitions.
  */
 #define DEFAULT_RX_QUEUE_SIZE	128
-#define DEFAULT_TX_QUEUE_SIZE	256
+#define DEFAULT_TX_QUEUE_SIZE	512
 #define SKB_DMA_REALIGN		((PAGE_SIZE - NET_SKB_PAD) % SMP_CACHE_BYTES)
 
+#define TSO_HEADER_SIZE		128
 
+/* Max number of allowed TCP segments for software TSO */
+#define MV643XX_MAX_TSO_SEGS 100
+#define MV643XX_MAX_SKB_DESCS (MV643XX_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
+
+#define IS_TSO_HEADER(txq, addr) \
+	((addr >= txq->tso_hdrs_dma) && \
+	 (addr < txq->tso_hdrs_dma + txq->tx_ring_size * TSO_HEADER_SIZE))
 /*
  * RX/TX descriptors.
  */
@@ -250,6 +259,7 @@ struct tx_desc {
 #define GEN_TCP_UDP_CHECKSUM		0x00020000
 #define UDP_FRAME			0x00010000
 #define MAC_HDR_EXTRA_4_BYTES		0x00008000
+#define GEN_TCP_UDP_CHK_FULL		0x00000400
 #define MAC_HDR_EXTRA_8_BYTES		0x00000200
 
 #define TX_IHL_SHIFT			11
@@ -345,6 +355,12 @@ struct tx_queue {
 	int tx_curr_desc;
 	int tx_used_desc;
 
+	int tx_stop_threshold;
+	int tx_wake_threshold;
+
+	char *tso_hdrs;
+	dma_addr_t tso_hdrs_dma;
+
 	struct tx_desc *tx_desc_area;
 	dma_addr_t tx_desc_dma;
 	int tx_desc_area_size;
@@ -491,7 +507,7 @@ static void txq_maybe_wake(struct tx_queue *txq)
 
 	if (netif_tx_queue_stopped(nq)) {
 		__netif_tx_lock(nq, smp_processor_id());
-		if (txq->tx_ring_size - txq->tx_desc_count >= MAX_SKB_FRAGS + 1)
+		if (txq->tx_desc_count <= txq->tx_wake_threshold)
 			netif_tx_wake_queue(nq);
 		__netif_tx_unlock(nq);
 	}
@@ -661,6 +677,198 @@ static inline unsigned int has_tiny_unaligned_frags(struct sk_buff *skb)
 	return 0;
 }
 
+static inline __be16 sum16_as_be(__sum16 sum)
+{
+	return (__force __be16)sum;
+}
+
+static int skb_tx_csum(struct mv643xx_eth_private *mp, struct sk_buff *skb,
+		       u16 *l4i_chk, u32 *command, int length)
+{
+	int ret;
+	u32 cmd = 0;
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		int hdr_len;
+		int tag_bytes;
+
+		BUG_ON(skb->protocol != htons(ETH_P_IP) &&
+		       skb->protocol != htons(ETH_P_8021Q));
+
+		hdr_len = (void *)ip_hdr(skb) - (void *)skb->data;
+		tag_bytes = hdr_len - ETH_HLEN;
+
+		if (length - hdr_len > mp->shared->tx_csum_limit ||
+		    unlikely(tag_bytes & ~12)) {
+			ret = skb_checksum_help(skb);
+			if (!ret)
+				goto no_csum;
+			return ret;
+		}
+
+		if (tag_bytes & 4)
+			cmd |= MAC_HDR_EXTRA_4_BYTES;
+		if (tag_bytes & 8)
+			cmd |= MAC_HDR_EXTRA_8_BYTES;
+
+		cmd |= GEN_TCP_UDP_CHECKSUM | GEN_TCP_UDP_CHK_FULL |
+			   GEN_IP_V4_CHECKSUM   |
+			   ip_hdr(skb)->ihl << TX_IHL_SHIFT;
+
+		/* TODO: Revisit this. With the usage of GEN_TCP_UDP_CHK_FULL
+		 * it seems we don't need to pass the initial checksum. */
+		switch (ip_hdr(skb)->protocol) {
+		case IPPROTO_UDP:
+			cmd |= UDP_FRAME;
+			*l4i_chk = 0;
+			break;
+		case IPPROTO_TCP:
+			*l4i_chk = 0;
+			break;
+		default:
+			WARN(1, "protocol not supported");
+		}
+	} else {
+no_csum:
+		/* Errata BTS #50, IHL must be 5 if no HW checksum */
+		cmd |= 5 << TX_IHL_SHIFT;
+	}
+	*command = cmd;
+	return 0;
+}
+
+static inline int
+txq_put_data_tso(struct net_device *dev, struct tx_queue *txq,
+		 struct sk_buff *skb, char *data, int length,
+		 bool last_tcp, bool is_last)
+{
+	int tx_index;
+	u32 cmd_sts;
+	struct tx_desc *desc;
+
+	tx_index = txq->tx_curr_desc++;
+	if (txq->tx_curr_desc == txq->tx_ring_size)
+		txq->tx_curr_desc = 0;
+	desc = &txq->tx_desc_area[tx_index];
+
+	desc->l4i_chk = 0;
+	desc->byte_cnt = length;
+	desc->buf_ptr = dma_map_single(dev->dev.parent, data,
+				       length, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev->dev.parent, desc->buf_ptr))) {
+		WARN(1, "dma_map_single failed!\n");
+		return -ENOMEM;
+	}
+
+	cmd_sts = BUFFER_OWNED_BY_DMA;
+	if (last_tcp) {
+		/* last descriptor in the TCP packet */
+		cmd_sts |= ZERO_PADDING | TX_LAST_DESC;
+		/* last descriptor in SKB */
+		if (is_last)
+			cmd_sts |= TX_ENABLE_INTERRUPT;
+	}
+	desc->cmd_sts = cmd_sts;
+	return 0;
+}
+
+static inline void
+txq_put_hdr_tso(struct sk_buff *skb, struct tx_queue *txq, int length)
+{
+	struct mv643xx_eth_private *mp = txq_to_mp(txq);
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int tx_index;
+	struct tx_desc *desc;
+	int ret;
+	u32 cmd_csum = 0;
+	u16 l4i_chk = 0;
+
+	tx_index = txq->tx_curr_desc;
+	desc = &txq->tx_desc_area[tx_index];
+
+	ret = skb_tx_csum(mp, skb, &l4i_chk, &cmd_csum, length);
+	if (ret)
+		WARN(1, "failed to prepare checksum!");
+
+	/* Should we set this? Can't use the value from skb_tx_csum()
+	 * as it's not the correct initial L4 checksum to use. */
+	desc->l4i_chk = 0;
+
+	desc->byte_cnt = hdr_len;
+	desc->buf_ptr = txq->tso_hdrs_dma +
+			txq->tx_curr_desc * TSO_HEADER_SIZE;
+	desc->cmd_sts = cmd_csum | BUFFER_OWNED_BY_DMA  | TX_FIRST_DESC |
+				   GEN_CRC;
+
+	txq->tx_curr_desc++;
+	if (txq->tx_curr_desc == txq->tx_ring_size)
+		txq->tx_curr_desc = 0;
+}
+
+static int txq_submit_tso(struct tx_queue *txq, struct sk_buff *skb,
+			  struct net_device *dev)
+{
+	struct mv643xx_eth_private *mp = txq_to_mp(txq);
+	int total_len, data_left, ret;
+	int desc_count = 0;
+	struct tso_t tso;
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+
+	/* Count needed descriptors */
+	if ((txq->tx_desc_count + tso_count_descs(skb)) >= txq->tx_ring_size) {
+		netdev_dbg(dev, "not enough descriptors for TSO!\n");
+		return -EBUSY;
+	}
+
+	/* Initialize the TSO handler, and prepare the first payload */
+	tso_start(skb, &tso);
+
+	total_len = skb->len - hdr_len;
+	while (total_len > 0) {
+		char *hdr;
+
+		data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len);
+		total_len -= data_left;
+		desc_count++;
+
+		/* prepare packet headers: MAC + IP + TCP */
+		hdr = txq->tso_hdrs + txq->tx_curr_desc * TSO_HEADER_SIZE;
+		tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0);
+		txq_put_hdr_tso(skb, txq, data_left);
+
+		while (data_left > 0) {
+			int size;
+			desc_count++;
+
+			size = min_t(int, tso.size, data_left);
+			ret = txq_put_data_tso(dev, txq, skb, tso.data, size,
+					       size == data_left,
+					       total_len == 0);
+			if (ret)
+				goto err_release;
+			data_left -= size;
+			tso_build_data(skb, &tso, size);
+		}
+	}
+
+	__skb_queue_tail(&txq->tx_skb, skb);
+	skb_tx_timestamp(skb);
+
+	/* clear TX_END status */
+	mp->work_tx_end &= ~(1 << txq->index);
+
+	/* ensure all descriptors are written before poking hardware */
+	wmb();
+	txq_enable(txq);
+	txq->tx_desc_count += desc_count;
+	return 0;
+err_release:
+	/* TODO: Release all used data descriptors; header descriptors must not
+	 * be DMA-unmapped.
+	 */
+	return ret;
+}
+
 static void txq_submit_frag_skb(struct tx_queue *txq, struct sk_buff *skb)
 {
 	struct mv643xx_eth_private *mp = txq_to_mp(txq);
@@ -671,8 +879,10 @@ static void txq_submit_frag_skb(struct tx_queue *txq, struct sk_buff *skb)
 		skb_frag_t *this_frag;
 		int tx_index;
 		struct tx_desc *desc;
+		void *addr;
 
 		this_frag = &skb_shinfo(skb)->frags[frag];
+		addr = page_address(this_frag->page.p) + this_frag->page_offset;
 		tx_index = txq->tx_curr_desc++;
 		if (txq->tx_curr_desc == txq->tx_ring_size)
 			txq->tx_curr_desc = 0;
@@ -692,19 +902,13 @@ static void txq_submit_frag_skb(struct tx_queue *txq, struct sk_buff *skb)
 
 		desc->l4i_chk = 0;
 		desc->byte_cnt = skb_frag_size(this_frag);
-		desc->buf_ptr = skb_frag_dma_map(mp->dev->dev.parent,
-						 this_frag, 0,
-						 skb_frag_size(this_frag),
-						 DMA_TO_DEVICE);
+		desc->buf_ptr = dma_map_single(mp->dev->dev.parent, addr,
+					       desc->byte_cnt, DMA_TO_DEVICE);
 	}
 }
 
-static inline __be16 sum16_as_be(__sum16 sum)
-{
-	return (__force __be16)sum;
-}
-
-static int txq_submit_skb(struct tx_queue *txq, struct sk_buff *skb)
+static int txq_submit_skb(struct tx_queue *txq, struct sk_buff *skb,
+			  struct net_device *dev)
 {
 	struct mv643xx_eth_private *mp = txq_to_mp(txq);
 	int nr_frags = skb_shinfo(skb)->nr_frags;
@@ -712,54 +916,22 @@ static int txq_submit_skb(struct tx_queue *txq, struct sk_buff *skb)
 	struct tx_desc *desc;
 	u32 cmd_sts;
 	u16 l4i_chk;
-	int length;
+	int length, ret;
 
-	cmd_sts = TX_FIRST_DESC | GEN_CRC | BUFFER_OWNED_BY_DMA;
+	cmd_sts = 0;
 	l4i_chk = 0;
 
-	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		int hdr_len;
-		int tag_bytes;
-
-		BUG_ON(skb->protocol != htons(ETH_P_IP) &&
-		       skb->protocol != htons(ETH_P_8021Q));
-
-		hdr_len = (void *)ip_hdr(skb) - (void *)skb->data;
-		tag_bytes = hdr_len - ETH_HLEN;
-		if (skb->len - hdr_len > mp->shared->tx_csum_limit ||
-		    unlikely(tag_bytes & ~12)) {
-			if (skb_checksum_help(skb) == 0)
-				goto no_csum;
-			dev_kfree_skb_any(skb);
-			return 1;
-		}
-
-		if (tag_bytes & 4)
-			cmd_sts |= MAC_HDR_EXTRA_4_BYTES;
-		if (tag_bytes & 8)
-			cmd_sts |= MAC_HDR_EXTRA_8_BYTES;
-
-		cmd_sts |= GEN_TCP_UDP_CHECKSUM |
-			   GEN_IP_V4_CHECKSUM   |
-			   ip_hdr(skb)->ihl << TX_IHL_SHIFT;
-
-		switch (ip_hdr(skb)->protocol) {
-		case IPPROTO_UDP:
-			cmd_sts |= UDP_FRAME;
-			l4i_chk = ntohs(sum16_as_be(udp_hdr(skb)->check));
-			break;
-		case IPPROTO_TCP:
-			l4i_chk = ntohs(sum16_as_be(tcp_hdr(skb)->check));
-			break;
-		default:
-			BUG();
-		}
-	} else {
-no_csum:
-		/* Errata BTS #50, IHL must be 5 if no HW checksum */
-		cmd_sts |= 5 << TX_IHL_SHIFT;
+	if (txq->tx_ring_size - txq->tx_desc_count < MAX_SKB_FRAGS + 1) {
+		if (net_ratelimit())
+			netdev_err(dev, "tx queue full?!\n");
+		return -EBUSY;
 	}
 
+	ret = skb_tx_csum(mp, skb, &l4i_chk, &cmd_sts, skb->len);
+	if (ret)
+		return ret;
+	cmd_sts |= TX_FIRST_DESC | GEN_CRC | BUFFER_OWNED_BY_DMA;
+
 	tx_index = txq->tx_curr_desc++;
 	if (txq->tx_curr_desc == txq->tx_ring_size)
 		txq->tx_curr_desc = 0;
@@ -801,7 +973,7 @@ no_csum:
 static netdev_tx_t mv643xx_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mv643xx_eth_private *mp = netdev_priv(dev);
-	int length, queue;
+	int length, queue, ret;
 	struct tx_queue *txq;
 	struct netdev_queue *nq;
 
@@ -810,30 +982,26 @@ static netdev_tx_t mv643xx_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 	nq = netdev_get_tx_queue(dev, queue);
 
 	if (has_tiny_unaligned_frags(skb) && __skb_linearize(skb)) {
-		txq->tx_dropped++;
 		netdev_printk(KERN_DEBUG, dev,
 			      "failed to linearize skb with tiny unaligned fragment\n");
 		return NETDEV_TX_BUSY;
 	}
 
-	if (txq->tx_ring_size - txq->tx_desc_count < MAX_SKB_FRAGS + 1) {
-		if (net_ratelimit())
-			netdev_err(dev, "tx queue full?!\n");
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
-
 	length = skb->len;
 
-	if (!txq_submit_skb(txq, skb)) {
-		int entries_left;
-
+	if (skb_is_gso(skb))
+		ret = txq_submit_tso(txq, skb, dev);
+	else
+		ret = txq_submit_skb(txq, skb, dev);
+	if (!ret) {
 		txq->tx_bytes += length;
 		txq->tx_packets++;
 
-		entries_left = txq->tx_ring_size - txq->tx_desc_count;
-		if (entries_left < MAX_SKB_FRAGS + 1)
+		if (txq->tx_desc_count >= txq->tx_stop_threshold)
 			netif_tx_stop_queue(nq);
+	} else {
+		txq->tx_dropped++;
+		dev_kfree_skb_any(skb);
 	}
 
 	return NETDEV_TX_OK;
@@ -907,14 +1075,9 @@ static int txq_reclaim(struct tx_queue *txq, int budget, int force)
 			mp->dev->stats.tx_errors++;
 		}
 
-		if (cmd_sts & TX_FIRST_DESC) {
+		if (!IS_TSO_HEADER(txq, desc->buf_ptr))
 			dma_unmap_single(mp->dev->dev.parent, desc->buf_ptr,
 					 desc->byte_cnt, DMA_TO_DEVICE);
-		} else {
-			dma_unmap_page(mp->dev->dev.parent, desc->buf_ptr,
-				       desc->byte_cnt, DMA_TO_DEVICE);
-		}
-
 		dev_kfree_skb(skb);
 	}
 
@@ -1010,8 +1173,9 @@ static void txq_set_fixed_prio_mode(struct tx_queue *txq)
 
 
 /* mii management interface *************************************************/
-static void mv643xx_adjust_pscr(struct mv643xx_eth_private *mp)
+static void mv643xx_eth_adjust_link(struct net_device *dev)
 {
+	struct mv643xx_eth_private *mp = netdev_priv(dev);
 	u32 pscr = rdlp(mp, PORT_SERIAL_CONTROL);
 	u32 autoneg_disable = FORCE_LINK_PASS |
 	             DISABLE_AUTO_NEG_SPEED_GMII |
@@ -1387,7 +1551,7 @@ mv643xx_eth_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 
 	ret = phy_ethtool_sset(mp->phy, cmd);
 	if (!ret)
-		mv643xx_adjust_pscr(mp);
+		mv643xx_eth_adjust_link(dev);
 	return ret;
 }
 
@@ -1456,7 +1620,11 @@ mv643xx_eth_set_ringparam(struct net_device *dev, struct ethtool_ringparam *er)
 		return -EINVAL;
 
 	mp->rx_ring_size = er->rx_pending < 4096 ? er->rx_pending : 4096;
-	mp->tx_ring_size = er->tx_pending < 4096 ? er->tx_pending : 4096;
+	mp->tx_ring_size = clamp_t(unsigned int, er->tx_pending,
+				   MV643XX_MAX_SKB_DESCS * 2, 4096);
+	if (mp->tx_ring_size != er->tx_pending)
+		netdev_warn(dev, "TX queue size set to %u (requested %u)\n",
+			    mp->tx_ring_size, er->tx_pending);
 
 	if (netif_running(dev)) {
 		mv643xx_eth_stop(dev);
@@ -1832,6 +2000,13 @@ static int txq_init(struct mv643xx_eth_private *mp, int index)
 
 	txq->tx_ring_size = mp->tx_ring_size;
 
+	/* A queue must always have room for at least one skb.
+	 * Therefore, stop the queue when the free entries reaches
+	 * the maximum number of descriptors per skb.
+	 */
+	txq->tx_stop_threshold = txq->tx_ring_size - MV643XX_MAX_SKB_DESCS;
+	txq->tx_wake_threshold = txq->tx_stop_threshold / 2;
+
 	txq->tx_desc_count = 0;
 	txq->tx_curr_desc = 0;
 	txq->tx_used_desc = 0;
@@ -1871,6 +2046,15 @@ static int txq_init(struct mv643xx_eth_private *mp, int index)
 					nexti * sizeof(struct tx_desc);
 	}
 
+	/* Allocate DMA buffers for TSO MAC/IP/TCP headers */
+	txq->tso_hdrs = dma_alloc_coherent(mp->dev->dev.parent,
+					   txq->tx_ring_size * TSO_HEADER_SIZE,
+					   &txq->tso_hdrs_dma, GFP_KERNEL);
+	if (txq->tso_hdrs == NULL) {
+		dma_free_coherent(mp->dev->dev.parent, txq->tx_desc_area_size,
+				  txq->tx_desc_area, txq->tx_desc_dma);
+		return -ENOMEM;
+	}
 	skb_queue_head_init(&txq->tx_skb);
 
 	return 0;
@@ -1891,6 +2075,10 @@ static void txq_deinit(struct tx_queue *txq)
 	else
 		dma_free_coherent(mp->dev->dev.parent, txq->tx_desc_area_size,
 				  txq->tx_desc_area, txq->tx_desc_dma);
+	if (txq->tso_hdrs)
+		dma_free_coherent(mp->dev->dev.parent,
+				  txq->tx_ring_size * TSO_HEADER_SIZE,
+				  txq->tso_hdrs, txq->tso_hdrs_dma);
 }
 
 
@@ -2303,7 +2491,7 @@ static int mv643xx_eth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 	ret = phy_mii_ioctl(mp->phy, ifr, cmd);
 	if (!ret)
-		mv643xx_adjust_pscr(mp);
+		mv643xx_eth_adjust_link(dev);
 	return ret;
 }
 
@@ -2678,6 +2866,7 @@ static void set_params(struct mv643xx_eth_private *mp,
 		       struct mv643xx_eth_platform_data *pd)
 {
 	struct net_device *dev = mp->dev;
+	unsigned int tx_ring_size;
 
 	if (is_valid_ether_addr(pd->mac_addr))
 		memcpy(dev->dev_addr, pd->mac_addr, ETH_ALEN);
@@ -2692,22 +2881,22 @@ static void set_params(struct mv643xx_eth_private *mp,
 
 	mp->rxq_count = pd->rx_queue_count ? : 1;
 
-	mp->tx_ring_size = DEFAULT_TX_QUEUE_SIZE;
+	tx_ring_size = DEFAULT_TX_QUEUE_SIZE;
 	if (pd->tx_queue_size)
-		mp->tx_ring_size = pd->tx_queue_size;
+		tx_ring_size = pd->tx_queue_size;
+
+	mp->tx_ring_size = clamp_t(unsigned int, tx_ring_size,
+				   MV643XX_MAX_SKB_DESCS * 2, 4096);
+	if (mp->tx_ring_size != tx_ring_size)
+		netdev_warn(dev, "TX queue size set to %u (requested %u)\n",
+			    mp->tx_ring_size, tx_ring_size);
+
 	mp->tx_desc_sram_addr = pd->tx_sram_addr;
 	mp->tx_desc_sram_size = pd->tx_sram_size;
 
 	mp->txq_count = pd->tx_queue_count ? : 1;
 }
 
-static void mv643xx_eth_adjust_link(struct net_device *dev)
-{
-	struct mv643xx_eth_private *mp = netdev_priv(dev);
-
-	mv643xx_adjust_pscr(mp);
-}
-
 static struct phy_device *phy_scan(struct mv643xx_eth_private *mp,
 				   int phy_addr)
 {
@@ -2889,7 +3078,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 	if (err)
 		goto out;
 
-	SET_ETHTOOL_OPS(dev, &mv643xx_eth_ethtool_ops);
+	dev->ethtool_ops = &mv643xx_eth_ethtool_ops;
 
 	init_pscr(mp, pd->speed, pd->duplex);
 
@@ -2921,11 +3110,14 @@ static int mv643xx_eth_probe(struct platform_device *pdev)
 	dev->watchdog_timeo = 2 * HZ;
 	dev->base_addr = 0;
 
-	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
-	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_RXCSUM;
-	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM;
+	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
+	dev->vlan_features = dev->features;
+
+	dev->features |= NETIF_F_RXCSUM;
+	dev->hw_features = dev->features;
 
 	dev->priv_flags |= IFF_UNICAST_FLT;
+	dev->gso_max_segs = MV643XX_MAX_TSO_SEGS;
 
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index 9d5ced263a5..fc2fb25343f 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -195,11 +195,10 @@ static int orion_mdio_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	bus = mdiobus_alloc_size(sizeof(struct orion_mdio_dev));
-	if (!bus) {
-		dev_err(&pdev->dev, "Cannot allocate MDIO bus\n");
+	bus = devm_mdiobus_alloc_size(&pdev->dev,
+				      sizeof(struct orion_mdio_dev));
+	if (!bus)
 		return -ENOMEM;
-	}
 
 	bus->name = "orion_mdio_bus";
 	bus->read = orion_mdio_read;
@@ -208,11 +207,10 @@ static int orion_mdio_probe(struct platform_device *pdev)
 		 dev_name(&pdev->dev));
 	bus->parent = &pdev->dev;
 
-	bus->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL);
-	if (!bus->irq) {
-		mdiobus_free(bus);
+	bus->irq = devm_kmalloc_array(&pdev->dev, PHY_MAX_ADDR, sizeof(int),
+				      GFP_KERNEL);
+	if (!bus->irq)
 		return -ENOMEM;
-	}
 
 	for (i = 0; i < PHY_MAX_ADDR; i++)
 		bus->irq[i] = PHY_POLL;
@@ -264,8 +262,6 @@ static int orion_mdio_probe(struct platform_device *pdev)
 out_mdio:
 	if (!IS_ERR(dev->clk))
 		clk_disable_unprepare(dev->clk);
-	kfree(bus->irq);
-	mdiobus_free(bus);
 	return ret;
 }
 
@@ -276,8 +272,6 @@ static int orion_mdio_remove(struct platform_device *pdev)
 
 	writel(0, dev->regs + MVMDIO_ERR_INT_MASK);
 	mdiobus_unregister(bus);
-	kfree(bus->irq);
-	mdiobus_free(bus);
 	if (!IS_ERR(dev->clk))
 		clk_disable_unprepare(dev->clk);
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 14786c8bf99..dadd9a5f632 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -23,6 +23,7 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <linux/io.h>
+#include <net/tso.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
@@ -218,9 +219,6 @@
 #define MVNETA_RX_COAL_PKTS		32
 #define MVNETA_RX_COAL_USEC		100
 
-/* Napi polling weight */
-#define MVNETA_RX_POLL_WEIGHT		64
-
 /* The two bytes Marvell header. Either contains a special value used
  * by Marvell switches when a specific hardware mode is enabled (not
  * supported by this driver) or is filled automatically by zeroes on
@@ -244,12 +242,20 @@
 
 #define MVNETA_TX_MTU_MAX		0x3ffff
 
+/* TSO header size */
+#define TSO_HEADER_SIZE 128
+
 /* Max number of Rx descriptors */
 #define MVNETA_MAX_RXD 128
 
 /* Max number of Tx descriptors */
 #define MVNETA_MAX_TXD 532
 
+/* Max number of allowed TCP segments for software TSO */
+#define MVNETA_MAX_TSO_SEGS 100
+
+#define MVNETA_MAX_SKB_DESCS (MVNETA_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
+
 /* descriptor aligned size */
 #define MVNETA_DESC_ALIGNED_SIZE	32
 
@@ -258,6 +264,10 @@
 	      ETH_HLEN + ETH_FCS_LEN,			     \
 	      MVNETA_CPU_D_CACHE_LINE_SIZE)
 
+#define IS_TSO_HEADER(txq, addr) \
+	((addr >= txq->tso_hdrs_phys) && \
+	 (addr < txq->tso_hdrs_phys + txq->size * TSO_HEADER_SIZE))
+
 #define MVNETA_RX_BUF_SIZE(pkt_size)   ((pkt_size) + NET_SKB_PAD)
 
 struct mvneta_pcpu_stats {
@@ -279,9 +289,6 @@ struct mvneta_port {
 	u32 cause_rx_tx;
 	struct napi_struct napi;
 
-	/* Napi weight */
-	int weight;
-
 	/* Core clock */
 	struct clk *clk;
 	u8 mcast_count[256];
@@ -390,6 +397,8 @@ struct mvneta_tx_queue {
 	 * descriptor ring
 	 */
 	int count;
+	int tx_stop_threshold;
+	int tx_wake_threshold;
 
 	/* Array of transmitted skb */
 	struct sk_buff **tx_skb;
@@ -413,6 +422,12 @@ struct mvneta_tx_queue {
 
 	/* Index of the next TX DMA descriptor to process */
 	int next_desc_to_proc;
+
+	/* DMA buffers for TSO headers */
+	char *tso_hdrs;
+
+	/* DMA address of TSO headers */
+	dma_addr_t tso_hdrs_phys;
 };
 
 struct mvneta_rx_queue {
@@ -441,7 +456,10 @@ struct mvneta_rx_queue {
 	int next_desc_to_proc;
 };
 
-static int rxq_number = 8;
+/* The hardware supports eight (8) rx queues, but we are only allowing
+ * the first one to be used. Therefore, let's just allocate one queue.
+ */
+static int rxq_number = 1;
 static int txq_number = 8;
 
 static int rxq_def;
@@ -1189,7 +1207,7 @@ static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
 	command =  l3_offs    << MVNETA_TX_L3_OFF_SHIFT;
 	command |= ip_hdr_len << MVNETA_TX_IP_HLEN_SHIFT;
 
-	if (l3_proto == swab16(ETH_P_IP))
+	if (l3_proto == htons(ETH_P_IP))
 		command |= MVNETA_TXD_IP_CSUM;
 	else
 		command |= MVNETA_TX_L3_IP6;
@@ -1277,11 +1295,12 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp,
 
 		mvneta_txq_inc_get(txq);
 
+		if (!IS_TSO_HEADER(txq, tx_desc->buf_phys_addr))
+			dma_unmap_single(pp->dev->dev.parent,
+					 tx_desc->buf_phys_addr,
+					 tx_desc->data_size, DMA_TO_DEVICE);
 		if (!skb)
 			continue;
-
-		dma_unmap_single(pp->dev->dev.parent, tx_desc->buf_phys_addr,
-				 tx_desc->data_size, DMA_TO_DEVICE);
 		dev_kfree_skb_any(skb);
 	}
 }
@@ -1302,7 +1321,7 @@ static void mvneta_txq_done(struct mvneta_port *pp,
 	txq->count -= tx_done;
 
 	if (netif_tx_queue_stopped(nq)) {
-		if (txq->size - txq->count >= MAX_SKB_FRAGS + 1)
+		if (txq->count <= txq->tx_wake_threshold)
 			netif_tx_wake_queue(nq);
 	}
 }
@@ -1519,14 +1538,134 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
 	return rx_done;
 }
 
+static inline void
+mvneta_tso_put_hdr(struct sk_buff *skb,
+		   struct mvneta_port *pp, struct mvneta_tx_queue *txq)
+{
+	struct mvneta_tx_desc *tx_desc;
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+
+	txq->tx_skb[txq->txq_put_index] = NULL;
+	tx_desc = mvneta_txq_next_desc_get(txq);
+	tx_desc->data_size = hdr_len;
+	tx_desc->command = mvneta_skb_tx_csum(pp, skb);
+	tx_desc->command |= MVNETA_TXD_F_DESC;
+	tx_desc->buf_phys_addr = txq->tso_hdrs_phys +
+				 txq->txq_put_index * TSO_HEADER_SIZE;
+	mvneta_txq_inc_put(txq);
+}
+
+static inline int
+mvneta_tso_put_data(struct net_device *dev, struct mvneta_tx_queue *txq,
+		    struct sk_buff *skb, char *data, int size,
+		    bool last_tcp, bool is_last)
+{
+	struct mvneta_tx_desc *tx_desc;
+
+	tx_desc = mvneta_txq_next_desc_get(txq);
+	tx_desc->data_size = size;
+	tx_desc->buf_phys_addr = dma_map_single(dev->dev.parent, data,
+						size, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(dev->dev.parent,
+		     tx_desc->buf_phys_addr))) {
+		mvneta_txq_desc_put(txq);
+		return -ENOMEM;
+	}
+
+	tx_desc->command = 0;
+	txq->tx_skb[txq->txq_put_index] = NULL;
+
+	if (last_tcp) {
+		/* last descriptor in the TCP packet */
+		tx_desc->command = MVNETA_TXD_L_DESC;
+
+		/* last descriptor in SKB */
+		if (is_last)
+			txq->tx_skb[txq->txq_put_index] = skb;
+	}
+	mvneta_txq_inc_put(txq);
+	return 0;
+}
+
+static int mvneta_tx_tso(struct sk_buff *skb, struct net_device *dev,
+			 struct mvneta_tx_queue *txq)
+{
+	int total_len, data_left;
+	int desc_count = 0;
+	struct mvneta_port *pp = netdev_priv(dev);
+	struct tso_t tso;
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int i;
+
+	/* Count needed descriptors */
+	if ((txq->count + tso_count_descs(skb)) >= txq->size)
+		return 0;
+
+	if (skb_headlen(skb) < (skb_transport_offset(skb) + tcp_hdrlen(skb))) {
+		pr_info("*** Is this even  possible???!?!?\n");
+		return 0;
+	}
+
+	/* Initialize the TSO handler, and prepare the first payload */
+	tso_start(skb, &tso);
+
+	total_len = skb->len - hdr_len;
+	while (total_len > 0) {
+		char *hdr;
+
+		data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len);
+		total_len -= data_left;
+		desc_count++;
+
+		/* prepare packet headers: MAC + IP + TCP */
+		hdr = txq->tso_hdrs + txq->txq_put_index * TSO_HEADER_SIZE;
+		tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0);
+
+		mvneta_tso_put_hdr(skb, pp, txq);
+
+		while (data_left > 0) {
+			int size;
+			desc_count++;
+
+			size = min_t(int, tso.size, data_left);
+
+			if (mvneta_tso_put_data(dev, txq, skb,
+						 tso.data, size,
+						 size == data_left,
+						 total_len == 0))
+				goto err_release;
+			data_left -= size;
+
+			tso_build_data(skb, &tso, size);
+		}
+	}
+
+	return desc_count;
+
+err_release:
+	/* Release all used data descriptors; header descriptors must not
+	 * be DMA-unmapped.
+	 */
+	for (i = desc_count - 1; i >= 0; i--) {
+		struct mvneta_tx_desc *tx_desc = txq->descs + i;
+		if (!IS_TSO_HEADER(txq, tx_desc->buf_phys_addr))
+			dma_unmap_single(pp->dev->dev.parent,
+					 tx_desc->buf_phys_addr,
+					 tx_desc->data_size,
+					 DMA_TO_DEVICE);
+		mvneta_txq_desc_put(txq);
+	}
+	return 0;
+}
+
 /* Handle tx fragmentation processing */
 static int mvneta_tx_frag_process(struct mvneta_port *pp, struct sk_buff *skb,
 				  struct mvneta_tx_queue *txq)
 {
 	struct mvneta_tx_desc *tx_desc;
-	int i;
+	int i, nr_frags = skb_shinfo(skb)->nr_frags;
 
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+	for (i = 0; i < nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		void *addr = page_address(frag->page.p) + frag->page_offset;
 
@@ -1543,20 +1682,16 @@ static int mvneta_tx_frag_process(struct mvneta_port *pp, struct sk_buff *skb,
 			goto error;
 		}
 
-		if (i == (skb_shinfo(skb)->nr_frags - 1)) {
+		if (i == nr_frags - 1) {
 			/* Last descriptor */
 			tx_desc->command = MVNETA_TXD_L_DESC | MVNETA_TXD_Z_PAD;
-
 			txq->tx_skb[txq->txq_put_index] = skb;
-
-			mvneta_txq_inc_put(txq);
 		} else {
 			/* Descriptor in the middle: Not First, Not Last */
 			tx_desc->command = 0;
-
 			txq->tx_skb[txq->txq_put_index] = NULL;
-			mvneta_txq_inc_put(txq);
 		}
+		mvneta_txq_inc_put(txq);
 	}
 
 	return 0;
@@ -1584,15 +1719,18 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
 	u16 txq_id = skb_get_queue_mapping(skb);
 	struct mvneta_tx_queue *txq = &pp->txqs[txq_id];
 	struct mvneta_tx_desc *tx_desc;
-	struct netdev_queue *nq;
 	int frags = 0;
 	u32 tx_cmd;
 
 	if (!netif_running(dev))
 		goto out;
 
+	if (skb_is_gso(skb)) {
+		frags = mvneta_tx_tso(skb, dev, txq);
+		goto out;
+	}
+
 	frags = skb_shinfo(skb)->nr_frags + 1;
-	nq    = netdev_get_tx_queue(dev, txq_id);
 
 	/* Get a descriptor for the first part of the packet */
 	tx_desc = mvneta_txq_next_desc_get(txq);
@@ -1635,15 +1773,16 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	txq->count += frags;
-	mvneta_txq_pend_desc_add(pp, txq, frags);
-
-	if (txq->size - txq->count < MAX_SKB_FRAGS + 1)
-		netif_tx_stop_queue(nq);
-
 out:
 	if (frags > 0) {
 		struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
+		struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id);
+
+		txq->count += frags;
+		mvneta_txq_pend_desc_add(pp, txq, frags);
+
+		if (txq->count >= txq->tx_stop_threshold)
+			netif_tx_stop_queue(nq);
 
 		u64_stats_update_begin(&stats->syncp);
 		stats->tx_packets++;
@@ -2003,7 +2142,7 @@ static void mvneta_tx_reset(struct mvneta_port *pp)
 {
 	int queue;
 
-	/* free the skb's in the hal tx ring */
+	/* free the skb's in the tx ring */
 	for (queue = 0; queue < txq_number; queue++)
 		mvneta_txq_done_force(pp, &pp->txqs[queue]);
 
@@ -2081,6 +2220,14 @@ static int mvneta_txq_init(struct mvneta_port *pp,
 {
 	txq->size = pp->tx_ring_size;
 
+	/* A queue must always have room for at least one skb.
+	 * Therefore, stop the queue when the free entries reaches
+	 * the maximum number of descriptors per skb.
+	 */
+	txq->tx_stop_threshold = txq->size - MVNETA_MAX_SKB_DESCS;
+	txq->tx_wake_threshold = txq->tx_stop_threshold / 2;
+
+
 	/* Allocate memory for TX descriptors */
 	txq->descs = dma_alloc_coherent(pp->dev->dev.parent,
 					txq->size * MVNETA_DESC_ALIGNED_SIZE,
@@ -2109,6 +2256,18 @@ static int mvneta_txq_init(struct mvneta_port *pp,
 				  txq->descs, txq->descs_phys);
 		return -ENOMEM;
 	}
+
+	/* Allocate DMA buffers for TSO MAC/IP/TCP headers */
+	txq->tso_hdrs = dma_alloc_coherent(pp->dev->dev.parent,
+					   txq->size * TSO_HEADER_SIZE,
+					   &txq->tso_hdrs_phys, GFP_KERNEL);
+	if (txq->tso_hdrs == NULL) {
+		kfree(txq->tx_skb);
+		dma_free_coherent(pp->dev->dev.parent,
+				  txq->size * MVNETA_DESC_ALIGNED_SIZE,
+				  txq->descs, txq->descs_phys);
+		return -ENOMEM;
+	}
 	mvneta_tx_done_pkts_coal_set(pp, txq, txq->done_pkts_coal);
 
 	return 0;
@@ -2120,6 +2279,10 @@ static void mvneta_txq_deinit(struct mvneta_port *pp,
 {
 	kfree(txq->tx_skb);
 
+	if (txq->tso_hdrs)
+		dma_free_coherent(pp->dev->dev.parent,
+				  txq->size * TSO_HEADER_SIZE,
+				  txq->tso_hdrs, txq->tso_hdrs_phys);
 	if (txq->descs)
 		dma_free_coherent(pp->dev->dev.parent,
 				  txq->size * MVNETA_DESC_ALIGNED_SIZE,
@@ -2279,24 +2442,28 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 		return 0;
 
 	/* The interface is running, so we have to force a
-	 * reallocation of the RXQs
+	 * reallocation of the queues
 	 */
 	mvneta_stop_dev(pp);
 
 	mvneta_cleanup_txqs(pp);
 	mvneta_cleanup_rxqs(pp);
 
-	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
+	pp->pkt_size = MVNETA_RX_PKT_SIZE(dev->mtu);
 	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
 	                SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	ret = mvneta_setup_rxqs(pp);
 	if (ret) {
-		netdev_err(pp->dev, "unable to setup rxqs after MTU change\n");
+		netdev_err(dev, "unable to setup rxqs after MTU change\n");
 		return ret;
 	}
 
-	mvneta_setup_txqs(pp);
+	ret = mvneta_setup_txqs(pp);
+	if (ret) {
+		netdev_err(dev, "unable to setup txqs after MTU change\n");
+		return ret;
+	}
 
 	mvneta_start_dev(pp);
 	mvneta_port_up(pp);
@@ -2323,22 +2490,19 @@ static void mvneta_get_mac_addr(struct mvneta_port *pp, unsigned char *addr)
 static int mvneta_set_mac_addr(struct net_device *dev, void *addr)
 {
 	struct mvneta_port *pp = netdev_priv(dev);
-	u8 *mac = addr + 2;
-	int i;
-
-	if (netif_running(dev))
-		return -EBUSY;
+	struct sockaddr *sockaddr = addr;
+	int ret;
 
+	ret = eth_prepare_mac_addr_change(dev, addr);
+	if (ret < 0)
+		return ret;
 	/* Remove previous address table entry */
 	mvneta_mac_addr_set(pp, dev->dev_addr, -1);
 
 	/* Set new addr in hw */
-	mvneta_mac_addr_set(pp, mac, rxq_def);
-
-	/* Set addr in the device */
-	for (i = 0; i < ETH_ALEN; i++)
-		dev->dev_addr[i] = mac[i];
+	mvneta_mac_addr_set(pp, sockaddr->sa_data, rxq_def);
 
+	eth_commit_mac_addr_change(dev, addr);
 	return 0;
 }
 
@@ -2365,7 +2529,7 @@ static void mvneta_adjust_link(struct net_device *ndev)
 
 			if (phydev->speed == SPEED_1000)
 				val |= MVNETA_GMAC_CONFIG_GMII_SPEED;
-			else
+			else if (phydev->speed == SPEED_100)
 				val |= MVNETA_GMAC_CONFIG_MII_SPEED;
 
 			mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
@@ -2433,8 +2597,6 @@ static int mvneta_open(struct net_device *dev)
 	struct mvneta_port *pp = netdev_priv(dev);
 	int ret;
 
-	mvneta_mac_addr_set(pp, dev->dev_addr, rxq_def);
-
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
 	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
 	                SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
@@ -2600,8 +2762,12 @@ static int mvneta_ethtool_set_ringparam(struct net_device *dev,
 		return -EINVAL;
 	pp->rx_ring_size = ring->rx_pending < MVNETA_MAX_RXD ?
 		ring->rx_pending : MVNETA_MAX_RXD;
-	pp->tx_ring_size = ring->tx_pending < MVNETA_MAX_TXD ?
-		ring->tx_pending : MVNETA_MAX_TXD;
+
+	pp->tx_ring_size = clamp_t(u16, ring->tx_pending,
+				   MVNETA_MAX_SKB_DESCS * 2, MVNETA_MAX_TXD);
+	if (pp->tx_ring_size != ring->tx_pending)
+		netdev_warn(dev, "TX queue size set to %u (requested %u)\n",
+			    pp->tx_ring_size, ring->tx_pending);
 
 	if (netif_running(dev)) {
 		mvneta_stop(dev);
@@ -2638,7 +2804,7 @@ const struct ethtool_ops mvneta_eth_tool_ops = {
 };
 
 /* Initialize hw */
-static int mvneta_init(struct mvneta_port *pp, int phy_addr)
+static int mvneta_init(struct device *dev, struct mvneta_port *pp)
 {
 	int queue;
 
@@ -2648,8 +2814,8 @@ static int mvneta_init(struct mvneta_port *pp, int phy_addr)
 	/* Set port default values */
 	mvneta_defaults_set(pp);
 
-	pp->txqs = kzalloc(txq_number * sizeof(struct mvneta_tx_queue),
-			   GFP_KERNEL);
+	pp->txqs = devm_kcalloc(dev, txq_number, sizeof(struct mvneta_tx_queue),
+				GFP_KERNEL);
 	if (!pp->txqs)
 		return -ENOMEM;
 
@@ -2661,12 +2827,10 @@ static int mvneta_init(struct mvneta_port *pp, int phy_addr)
 		txq->done_pkts_coal = MVNETA_TXDONE_COAL_PKTS;
 	}
 
-	pp->rxqs = kzalloc(rxq_number * sizeof(struct mvneta_rx_queue),
-			   GFP_KERNEL);
-	if (!pp->rxqs) {
-		kfree(pp->txqs);
+	pp->rxqs = devm_kcalloc(dev, rxq_number, sizeof(struct mvneta_rx_queue),
+				GFP_KERNEL);
+	if (!pp->rxqs)
 		return -ENOMEM;
-	}
 
 	/* Create Rx descriptor rings */
 	for (queue = 0; queue < rxq_number; queue++) {
@@ -2680,12 +2844,6 @@ static int mvneta_init(struct mvneta_port *pp, int phy_addr)
 	return 0;
 }
 
-static void mvneta_deinit(struct mvneta_port *pp)
-{
-	kfree(pp->txqs);
-	kfree(pp->rxqs);
-}
-
 /* platform glue : initialize decoding windows */
 static void mvneta_conf_mbus_windows(struct mvneta_port *pp,
 				     const struct mbus_dram_target_info *dram)
@@ -2768,7 +2926,6 @@ static int mvneta_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct device_node *dn = pdev->dev.of_node;
 	struct device_node *phy_node;
-	u32 phy_addr;
 	struct mvneta_port *pp;
 	struct net_device *dev;
 	const char *dt_mac_addr;
@@ -2797,9 +2954,22 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	phy_node = of_parse_phandle(dn, "phy", 0);
 	if (!phy_node) {
-		dev_err(&pdev->dev, "no associated PHY\n");
-		err = -ENODEV;
-		goto err_free_irq;
+		if (!of_phy_is_fixed_link(dn)) {
+			dev_err(&pdev->dev, "no PHY specified\n");
+			err = -ENODEV;
+			goto err_free_irq;
+		}
+
+		err = of_phy_register_fixed_link(dn);
+		if (err < 0) {
+			dev_err(&pdev->dev, "cannot register fixed PHY\n");
+			goto err_free_irq;
+		}
+
+		/* In the case of a fixed PHY, the DT node associated
+		 * to the PHY is the Ethernet MAC DT node.
+		 */
+		phy_node = dn;
 	}
 
 	phy_mode = of_get_phy_mode(dn);
@@ -2813,11 +2983,9 @@ static int mvneta_probe(struct platform_device *pdev)
 	dev->watchdog_timeo = 5 * HZ;
 	dev->netdev_ops = &mvneta_netdev_ops;
 
-	SET_ETHTOOL_OPS(dev, &mvneta_eth_tool_ops);
+	dev->ethtool_ops = &mvneta_eth_tool_ops;
 
 	pp = netdev_priv(dev);
-
-	pp->weight = MVNETA_RX_POLL_WEIGHT;
 	pp->phy_node = phy_node;
 	pp->phy_interface = phy_mode;
 
@@ -2864,33 +3032,32 @@ static int mvneta_probe(struct platform_device *pdev)
 	pp->dev = dev;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
-	err = mvneta_init(pp, phy_addr);
-	if (err < 0) {
-		dev_err(&pdev->dev, "can't init eth hal\n");
+	err = mvneta_init(&pdev->dev, pp);
+	if (err < 0)
 		goto err_free_stats;
-	}
 
 	err = mvneta_port_power_up(pp, phy_mode);
 	if (err < 0) {
 		dev_err(&pdev->dev, "can't power up port\n");
-		goto err_deinit;
+		goto err_free_stats;
 	}
 
 	dram_target_info = mv_mbus_dram_info();
 	if (dram_target_info)
 		mvneta_conf_mbus_windows(pp, dram_target_info);
 
-	netif_napi_add(dev, &pp->napi, mvneta_poll, pp->weight);
+	netif_napi_add(dev, &pp->napi, mvneta_poll, NAPI_POLL_WEIGHT);
 
-	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM;
-	dev->hw_features |= NETIF_F_SG | NETIF_F_IP_CSUM;
-	dev->vlan_features |= NETIF_F_SG | NETIF_F_IP_CSUM;
+	dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO;
+	dev->hw_features |= dev->features;
+	dev->vlan_features |= dev->features;
 	dev->priv_flags |= IFF_UNICAST_FLT;
+	dev->gso_max_segs = MVNETA_MAX_TSO_SEGS;
 
 	err = register_netdev(dev);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register\n");
-		goto err_deinit;
+		goto err_free_stats;
 	}
 
 	netdev_info(dev, "Using %s mac address %pM\n", mac_from,
@@ -2900,8 +3067,6 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	return 0;
 
-err_deinit:
-	mvneta_deinit(pp);
 err_free_stats:
 	free_percpu(pp->stats);
 err_clk:
@@ -2920,7 +3085,6 @@ static int mvneta_remove(struct platform_device *pdev)
 	struct mvneta_port *pp = netdev_priv(dev);
 
 	unregister_netdev(dev);
-	mvneta_deinit(pp);
 	clk_disable_unprepare(pp->clk);
 	free_percpu(pp->stats);
 	irq_dispose_mapping(dev->irq);
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index b358c2f6f4b..8f5aa7c62b1 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1488,7 +1488,7 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 	dev->netdev_ops = &pxa168_eth_netdev_ops;
 	dev->watchdog_timeo = 2 * HZ;
 	dev->base_addr = 0;
-	SET_ETHTOOL_OPS(dev, &pxa168_ethtool_ops);
+	dev->ethtool_ops = &pxa168_ethtool_ops;
 
 	INIT_WORK(&pep->tx_timeout_task, pxa168_eth_tx_timeout_task);
 
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 7f81ae66cc8..e912b6887d4 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -4199,6 +4199,13 @@ static struct dmi_system_id skge_32bit_dma_boards[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "P5NSLI")
 		},
 	},
+	{
+		.ident = "FUJITSU SIEMENS A8NE-FM",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTek Computer INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "A8NE-FM")
+		},
+	},
 	{}
 };
 
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index b81106451a0..69693384b58 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -4760,7 +4760,7 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port,
 
 	SET_NETDEV_DEV(dev, &hw->pdev->dev);
 	dev->irq = hw->pdev->irq;
-	SET_ETHTOOL_OPS(dev, &sky2_ethtool_ops);
+	dev->ethtool_ops = &sky2_ethtool_ops;
 	dev->watchdog_timeo = TX_WATCHDOG;
 	dev->netdev_ops = &sky2_netdev_ops[port];
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index c3ad464d062..b0297da5030 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -171,7 +171,7 @@ void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap)
  */
 
 int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
-		   struct mlx4_buf *buf)
+		   struct mlx4_buf *buf, gfp_t gfp)
 {
 	dma_addr_t t;
 
@@ -180,7 +180,7 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 		buf->npages       = 1;
 		buf->page_shift   = get_order(size) + PAGE_SHIFT;
 		buf->direct.buf   = dma_alloc_coherent(&dev->pdev->dev,
-						       size, &t, GFP_KERNEL);
+						       size, &t, gfp);
 		if (!buf->direct.buf)
 			return -ENOMEM;
 
@@ -200,14 +200,14 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 		buf->npages      = buf->nbufs;
 		buf->page_shift  = PAGE_SHIFT;
 		buf->page_list   = kcalloc(buf->nbufs, sizeof(*buf->page_list),
-					   GFP_KERNEL);
+					   gfp);
 		if (!buf->page_list)
 			return -ENOMEM;
 
 		for (i = 0; i < buf->nbufs; ++i) {
 			buf->page_list[i].buf =
 				dma_alloc_coherent(&dev->pdev->dev, PAGE_SIZE,
-						   &t, GFP_KERNEL);
+						   &t, gfp);
 			if (!buf->page_list[i].buf)
 				goto err_free;
 
@@ -218,7 +218,7 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 
 		if (BITS_PER_LONG == 64) {
 			struct page **pages;
-			pages = kmalloc(sizeof *pages * buf->nbufs, GFP_KERNEL);
+			pages = kmalloc(sizeof *pages * buf->nbufs, gfp);
 			if (!pages)
 				goto err_free;
 			for (i = 0; i < buf->nbufs; ++i)
@@ -260,11 +260,12 @@ void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf)
 }
 EXPORT_SYMBOL_GPL(mlx4_buf_free);
 
-static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device)
+static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device,
+						 gfp_t gfp)
 {
 	struct mlx4_db_pgdir *pgdir;
 
-	pgdir = kzalloc(sizeof *pgdir, GFP_KERNEL);
+	pgdir = kzalloc(sizeof *pgdir, gfp);
 	if (!pgdir)
 		return NULL;
 
@@ -272,7 +273,7 @@ static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device)
 	pgdir->bits[0] = pgdir->order0;
 	pgdir->bits[1] = pgdir->order1;
 	pgdir->db_page = dma_alloc_coherent(dma_device, PAGE_SIZE,
-					    &pgdir->db_dma, GFP_KERNEL);
+					    &pgdir->db_dma, gfp);
 	if (!pgdir->db_page) {
 		kfree(pgdir);
 		return NULL;
@@ -312,7 +313,7 @@ found:
 	return 0;
 }
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order)
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order, gfp_t gfp)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_db_pgdir *pgdir;
@@ -324,7 +325,7 @@ int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order)
 		if (!mlx4_alloc_db_from_pgdir(pgdir, db, order))
 			goto out;
 
-	pgdir = mlx4_alloc_db_pgdir(&(dev->pdev->dev));
+	pgdir = mlx4_alloc_db_pgdir(&(dev->pdev->dev), gfp);
 	if (!pgdir) {
 		ret = -ENOMEM;
 		goto out;
@@ -376,13 +377,13 @@ int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
 {
 	int err;
 
-	err = mlx4_db_alloc(dev, &wqres->db, 1);
+	err = mlx4_db_alloc(dev, &wqres->db, 1, GFP_KERNEL);
 	if (err)
 		return err;
 
 	*wqres->db.db = 0;
 
-	err = mlx4_buf_alloc(dev, size, max_direct, &wqres->buf);
+	err = mlx4_buf_alloc(dev, size, max_direct, &wqres->buf, GFP_KERNEL);
 	if (err)
 		goto err_db;
 
@@ -391,7 +392,7 @@ int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
 	if (err)
 		goto err_buf;
 
-	err = mlx4_buf_write_mtt(dev, &wqres->mtt, &wqres->buf);
+	err = mlx4_buf_write_mtt(dev, &wqres->mtt, &wqres->buf, GFP_KERNEL);
 	if (err)
 		goto err_mtt;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 92d3249f63f..5d940a26055 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -212,8 +212,7 @@ static int mlx4_comm_cmd_poll(struct mlx4_dev *dev, u8 cmd, u16 param,
 
 	/* First, verify that the master reports correct status */
 	if (comm_pending(dev)) {
-		mlx4_warn(dev, "Communication channel is not idle."
-			  "my toggle is %d (cmd:0x%x)\n",
+		mlx4_warn(dev, "Communication channel is not idle - my toggle is %d (cmd:0x%x)\n",
 			  priv->cmd.comm_toggle, cmd);
 		return -EAGAIN;
 	}
@@ -422,9 +421,8 @@ static int mlx4_slave_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 					*out_param =
 						be64_to_cpu(vhcr->out_param);
 				else {
-					mlx4_err(dev, "response expected while"
-						 "output mailbox is NULL for "
-						 "command 0x%x\n", op);
+					mlx4_err(dev, "response expected while output mailbox is NULL for command 0x%x\n",
+						 op);
 					vhcr->status = CMD_STAT_BAD_PARAM;
 				}
 			}
@@ -439,16 +437,15 @@ static int mlx4_slave_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 					*out_param =
 						be64_to_cpu(vhcr->out_param);
 				else {
-					mlx4_err(dev, "response expected while"
-						 "output mailbox is NULL for "
-						 "command 0x%x\n", op);
+					mlx4_err(dev, "response expected while output mailbox is NULL for command 0x%x\n",
+						 op);
 					vhcr->status = CMD_STAT_BAD_PARAM;
 				}
 			}
 			ret = mlx4_status_to_errno(vhcr->status);
 		} else
-			mlx4_err(dev, "failed execution of VHCR_POST command"
-				 "opcode 0x%x\n", op);
+			mlx4_err(dev, "failed execution of VHCR_POST command opcode 0x%x\n",
+				 op);
 	}
 
 	mutex_unlock(&priv->cmd.slave_cmd_mutex);
@@ -476,6 +473,13 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 		goto out;
 	}
 
+	if (out_is_imm && !out_param) {
+		mlx4_err(dev, "response expected while output mailbox is NULL for command 0x%x\n",
+			 op);
+		err = -EINVAL;
+		goto out;
+	}
+
 	err = mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
 			    in_modifier, op_modifier, op, CMD_POLL_TOKEN, 0);
 	if (err)
@@ -554,6 +558,13 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	cmd->free_head = context->next;
 	spin_unlock(&cmd->context_lock);
 
+	if (out_is_imm && !out_param) {
+		mlx4_err(dev, "response expected while output mailbox is NULL for command 0x%x\n",
+			 op);
+		err = -EINVAL;
+		goto out;
+	}
+
 	init_completion(&context->done);
 
 	mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
@@ -625,9 +636,8 @@ static int mlx4_ACCESS_MEM(struct mlx4_dev *dev, u64 master_addr,
 
 	if ((slave_addr & 0xfff) | (master_addr & 0xfff) |
 	    (slave & ~0x7f) | (size & 0xff)) {
-		mlx4_err(dev, "Bad access mem params - slave_addr:0x%llx "
-			      "master_addr:0x%llx slave_id:%d size:%d\n",
-			      slave_addr, master_addr, slave, size);
+		mlx4_err(dev, "Bad access mem params - slave_addr:0x%llx master_addr:0x%llx slave_id:%d size:%d\n",
+			 slave_addr, master_addr, slave, size);
 		return -EINVAL;
 	}
 
@@ -705,20 +715,28 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 	struct ib_smp *smp = inbox->buf;
 	u32 index;
 	u8 port;
+	u8 opcode_modifier;
 	u16 *table;
 	int err;
 	int vidx, pidx;
+	int network_view;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct ib_smp *outsmp = outbox->buf;
 	__be16 *outtab = (__be16 *)(outsmp->data);
 	__be32 slave_cap_mask;
 	__be64 slave_node_guid;
+
 	port = vhcr->in_modifier;
 
+	/* network-view bit is for driver use only, and should not be passed to FW */
+	opcode_modifier = vhcr->op_modifier & ~0x8; /* clear netw view bit */
+	network_view = !!(vhcr->op_modifier & 0x8);
+
 	if (smp->base_version == 1 &&
 	    smp->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED &&
 	    smp->class_version == 1) {
-		if (smp->method	== IB_MGMT_METHOD_GET) {
+		/* host view is paravirtualized */
+		if (!network_view && smp->method == IB_MGMT_METHOD_GET) {
 			if (smp->attr_id == IB_SMP_ATTR_PKEY_TABLE) {
 				index = be32_to_cpu(smp->attr_mod);
 				if (port < 1 || port > dev->caps.num_ports)
@@ -743,7 +761,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 				/*get the slave specific caps:*/
 				/*do the command */
 				err = mlx4_cmd_box(dev, inbox->dma, outbox->dma,
-					    vhcr->in_modifier, vhcr->op_modifier,
+					    vhcr->in_modifier, opcode_modifier,
 					    vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 				/* modify the response for slaves */
 				if (!err && slave != mlx4_master_func_num(dev)) {
@@ -760,7 +778,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 				smp->attr_mod = cpu_to_be32(slave / 8);
 				/* execute cmd */
 				err = mlx4_cmd_box(dev, inbox->dma, outbox->dma,
-					     vhcr->in_modifier, vhcr->op_modifier,
+					     vhcr->in_modifier, opcode_modifier,
 					     vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 				if (!err) {
 					/* if needed, move slave gid to index 0 */
@@ -774,7 +792,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 			}
 			if (smp->attr_id == IB_SMP_ATTR_NODE_INFO) {
 				err = mlx4_cmd_box(dev, inbox->dma, outbox->dma,
-					     vhcr->in_modifier, vhcr->op_modifier,
+					     vhcr->in_modifier, opcode_modifier,
 					     vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 				if (!err) {
 					slave_node_guid =  mlx4_get_slave_node_guid(dev, slave);
@@ -784,19 +802,24 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 			}
 		}
 	}
+
+	/* Non-privileged VFs are only allowed "host" view LID-routed 'Get' MADs.
+	 * These are the MADs used by ib verbs (such as ib_query_gids).
+	 */
 	if (slave != mlx4_master_func_num(dev) &&
-	    ((smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) ||
-	     (smp->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED &&
-	      smp->method == IB_MGMT_METHOD_SET))) {
-		mlx4_err(dev, "slave %d is trying to execute a Subnet MGMT MAD, "
-			 "class 0x%x, method 0x%x for attr 0x%x. Rejecting\n",
-			 slave, smp->method, smp->mgmt_class,
-			 be16_to_cpu(smp->attr_id));
-		return -EPERM;
+	    !mlx4_vf_smi_enabled(dev, slave, port)) {
+		if (!(smp->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED &&
+		      smp->method == IB_MGMT_METHOD_GET) || network_view) {
+			mlx4_err(dev, "Unprivileged slave %d is trying to execute a Subnet MGMT MAD, class 0x%x, method 0x%x, view=%s for attr 0x%x. Rejecting\n",
+				 slave, smp->method, smp->mgmt_class,
+				 network_view ? "Network" : "Host",
+				 be16_to_cpu(smp->attr_id));
+			return -EPERM;
+		}
 	}
-	/*default:*/
+
 	return mlx4_cmd_box(dev, inbox->dma, outbox->dma,
-				    vhcr->in_modifier, vhcr->op_modifier,
+				    vhcr->in_modifier, opcode_modifier,
 				    vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 }
 
@@ -1409,8 +1432,8 @@ static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
 				      ALIGN(sizeof(struct mlx4_vhcr_cmd),
 					    MLX4_ACCESS_MEM_ALIGN), 1);
 		if (ret) {
-			mlx4_err(dev, "%s:Failed reading vhcr"
-				 "ret: 0x%x\n", __func__, ret);
+			mlx4_err(dev, "%s: Failed reading vhcr ret: 0x%x\n",
+				 __func__, ret);
 			kfree(vhcr);
 			return ret;
 		}
@@ -1461,9 +1484,8 @@ static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
 
 	/* Apply permission and bound checks if applicable */
 	if (cmd->verify && cmd->verify(dev, slave, vhcr, inbox)) {
-		mlx4_warn(dev, "Command:0x%x from slave: %d failed protection "
-			  "checks for resource_id:%d\n", vhcr->op, slave,
-			  vhcr->in_modifier);
+		mlx4_warn(dev, "Command:0x%x from slave: %d failed protection checks for resource_id:%d\n",
+			  vhcr->op, slave, vhcr->in_modifier);
 		vhcr_cmd->status = CMD_STAT_BAD_OP;
 		goto out_status;
 	}
@@ -1502,8 +1524,7 @@ static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
 	}
 
 	if (err) {
-		mlx4_warn(dev, "vhcr command:0x%x slave:%d failed with"
-			  " error:%d, status %d\n",
+		mlx4_warn(dev, "vhcr command:0x%x slave:%d failed with error:%d, status %d\n",
 			  vhcr->op, slave, vhcr->errno, err);
 		vhcr_cmd->status = mlx4_errno_to_status(err);
 		goto out_status;
@@ -1537,8 +1558,8 @@ out_status:
 				 __func__);
 		else if (vhcr->e_bit &&
 			 mlx4_GEN_EQE(dev, slave, &priv->mfunc.master.cmd_eqe))
-				mlx4_warn(dev, "Failed to generate command completion "
-					  "eqe for slave %d\n", slave);
+				mlx4_warn(dev, "Failed to generate command completion eqe for slave %d\n",
+					  slave);
 	}
 
 out:
@@ -1577,8 +1598,9 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 
 	mlx4_dbg(dev, "updating immediately admin params slave %d port %d\n",
 		 slave, port);
-	mlx4_dbg(dev, "vlan %d QoS %d link down %d\n", vp_admin->default_vlan,
-		 vp_admin->default_qos, vp_admin->link_state);
+	mlx4_dbg(dev, "vlan %d QoS %d link down %d\n",
+		 vp_admin->default_vlan, vp_admin->default_qos,
+		 vp_admin->link_state);
 
 	work = kzalloc(sizeof(*work), GFP_KERNEL);
 	if (!work)
@@ -1591,7 +1613,7 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 						   &admin_vlan_ix);
 			if (err) {
 				kfree(work);
-				mlx4_warn((&priv->dev),
+				mlx4_warn(&priv->dev,
 					  "No vlan resources slave %d, port %d\n",
 					  slave, port);
 				return err;
@@ -1600,7 +1622,7 @@ static int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
 			admin_vlan_ix = NO_INDX;
 		}
 		work->flags |= MLX4_VF_IMMED_VLAN_FLAG_VLAN;
-		mlx4_dbg((&(priv->dev)),
+		mlx4_dbg(&priv->dev,
 			 "alloc vlan %d idx  %d slave %d port %d\n",
 			 (int)(vp_admin->default_vlan),
 			 admin_vlan_ix, slave, port);
@@ -1653,6 +1675,8 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 	for (port = min_port; port <= max_port; port++) {
 		if (!test_bit(port - 1, actv_ports.ports))
 			continue;
+		priv->mfunc.master.vf_oper[slave].smi_enabled[port] =
+			priv->mfunc.master.vf_admin[slave].enable_smi[port];
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
 		vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
 		vp_oper->state = *vp_admin;
@@ -1661,12 +1685,12 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 						   vp_admin->default_vlan, &(vp_oper->vlan_idx));
 			if (err) {
 				vp_oper->vlan_idx = NO_INDX;
-				mlx4_warn((&priv->dev),
+				mlx4_warn(&priv->dev,
 					  "No vlan resorces slave %d, port %d\n",
 					  slave, port);
 				return err;
 			}
-			mlx4_dbg((&(priv->dev)), "alloc vlan %d idx  %d slave %d port %d\n",
+			mlx4_dbg(&priv->dev, "alloc vlan %d idx  %d slave %d port %d\n",
 				 (int)(vp_oper->state.default_vlan),
 				 vp_oper->vlan_idx, slave, port);
 		}
@@ -1677,12 +1701,12 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 			if (0 > vp_oper->mac_idx) {
 				err = vp_oper->mac_idx;
 				vp_oper->mac_idx = NO_INDX;
-				mlx4_warn((&priv->dev),
+				mlx4_warn(&priv->dev,
 					  "No mac resorces slave %d, port %d\n",
 					  slave, port);
 				return err;
 			}
-			mlx4_dbg((&(priv->dev)), "alloc mac %llx idx  %d slave %d port %d\n",
+			mlx4_dbg(&priv->dev, "alloc mac %llx idx  %d slave %d port %d\n",
 				 vp_oper->state.mac, vp_oper->mac_idx, slave, port);
 		}
 	}
@@ -1704,6 +1728,8 @@ static void mlx4_master_deactivate_admin_state(struct mlx4_priv *priv, int slave
 	for (port = min_port; port <= max_port; port++) {
 		if (!test_bit(port - 1, actv_ports.ports))
 			continue;
+		priv->mfunc.master.vf_oper[slave].smi_enabled[port] =
+			MLX4_VF_SMI_DISABLED;
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
 		if (NO_INDX != vp_oper->vlan_idx) {
 			__mlx4_unregister_vlan(&priv->dev,
@@ -1731,8 +1757,8 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 	slave_state[slave].comm_toggle ^= 1;
 	reply = (u32) slave_state[slave].comm_toggle << 31;
 	if (toggle != slave_state[slave].comm_toggle) {
-		mlx4_warn(dev, "Incorrect toggle %d from slave %d. *** MASTER"
-			  "STATE COMPROMISIED ***\n", toggle, slave);
+		mlx4_warn(dev, "Incorrect toggle %d from slave %d. *** MASTER STATE COMPROMISED ***\n",
+			  toggle, slave);
 		goto reset_slave;
 	}
 	if (cmd == MLX4_COMM_CMD_RESET) {
@@ -1759,8 +1785,8 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 	/*command from slave in the middle of FLR*/
 	if (cmd != MLX4_COMM_CMD_RESET &&
 	    MLX4_COMM_CMD_FLR == slave_state[slave].last_cmd) {
-		mlx4_warn(dev, "slave:%d is Trying to run cmd(0x%x) "
-			  "in the middle of FLR\n", slave, cmd);
+		mlx4_warn(dev, "slave:%d is Trying to run cmd(0x%x) in the middle of FLR\n",
+			  slave, cmd);
 		return;
 	}
 
@@ -1798,8 +1824,8 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 
 		mutex_lock(&priv->cmd.slave_cmd_mutex);
 		if (mlx4_master_process_vhcr(dev, slave, NULL)) {
-			mlx4_err(dev, "Failed processing vhcr for slave:%d,"
-				 " resetting slave.\n", slave);
+			mlx4_err(dev, "Failed processing vhcr for slave:%d, resetting slave\n",
+				 slave);
 			mutex_unlock(&priv->cmd.slave_cmd_mutex);
 			goto reset_slave;
 		}
@@ -1816,8 +1842,7 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 		is_going_down = 1;
 	spin_unlock_irqrestore(&priv->mfunc.master.slave_state_lock, flags);
 	if (is_going_down) {
-		mlx4_warn(dev, "Slave is going down aborting command(%d)"
-			  " executing from slave:%d\n",
+		mlx4_warn(dev, "Slave is going down aborting command(%d) executing from slave:%d\n",
 			  cmd, slave);
 		return;
 	}
@@ -1880,10 +1905,9 @@ void mlx4_master_comm_channel(struct work_struct *work)
 			if (toggle != slt) {
 				if (master->slave_state[slave].comm_toggle
 				    != slt) {
-					printk(KERN_INFO "slave %d out of sync."
-					       " read toggle %d, state toggle %d. "
-					       "Resynching.\n", slave, slt,
-					       master->slave_state[slave].comm_toggle);
+					pr_info("slave %d out of sync. read toggle %d, state toggle %d. Resynching.\n",
+						slave, slt,
+						master->slave_state[slave].comm_toggle);
 					master->slave_state[slave].comm_toggle =
 						slt;
 				}
@@ -1896,8 +1920,7 @@ void mlx4_master_comm_channel(struct work_struct *work)
 	}
 
 	if (reported && reported != served)
-		mlx4_warn(dev, "Got command event with bitmask from %d slaves"
-			  " but %d were served\n",
+		mlx4_warn(dev, "Got command event with bitmask from %d slaves but %d were served\n",
 			  reported, served);
 
 	if (mlx4_ARM_COMM_CHANNEL(dev))
@@ -1953,7 +1976,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 		ioremap(pci_resource_start(dev->pdev, 2) +
 			MLX4_SLAVE_COMM_BASE, MLX4_COMM_PAGESIZE);
 	if (!priv->mfunc.comm) {
-		mlx4_err(dev, "Couldn't map communication vector.\n");
+		mlx4_err(dev, "Couldn't map communication vector\n");
 		goto err_vhcr;
 	}
 
@@ -2080,7 +2103,7 @@ int mlx4_cmd_init(struct mlx4_dev *dev)
 		priv->cmd.hcr = ioremap(pci_resource_start(dev->pdev, 0) +
 					MLX4_HCR_BASE, MLX4_HCR_SIZE);
 		if (!priv->cmd.hcr) {
-			mlx4_err(dev, "Couldn't map command register.\n");
+			mlx4_err(dev, "Couldn't map command register\n");
 			return -ENOMEM;
 		}
 	}
@@ -2481,11 +2504,12 @@ int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_in
 	ivf->mac[4] = ((s_info->mac >> (1*8)) & 0xff);
 	ivf->mac[5] = ((s_info->mac)  & 0xff);
 
-	ivf->vlan	= s_info->default_vlan;
-	ivf->qos	= s_info->default_qos;
-	ivf->tx_rate	= s_info->tx_rate;
-	ivf->spoofchk	= s_info->spoofchk;
-	ivf->linkstate	= s_info->link_state;
+	ivf->vlan		= s_info->default_vlan;
+	ivf->qos		= s_info->default_qos;
+	ivf->max_tx_rate	= s_info->tx_rate;
+	ivf->min_tx_rate	= 0;
+	ivf->spoofchk		= s_info->spoofchk;
+	ivf->linkstate		= s_info->link_state;
 
 	return 0;
 }
@@ -2537,3 +2561,50 @@ int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_stat
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mlx4_set_vf_link_state);
+
+int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	if (slave < 1 || slave >= dev->num_slaves ||
+	    port < 1 || port > MLX4_MAX_PORTS)
+		return 0;
+
+	return priv->mfunc.master.vf_oper[slave].smi_enabled[port] ==
+		MLX4_VF_SMI_ENABLED;
+}
+EXPORT_SYMBOL_GPL(mlx4_vf_smi_enabled);
+
+int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	if (slave == mlx4_master_func_num(dev))
+		return 1;
+
+	if (slave < 1 || slave >= dev->num_slaves ||
+	    port < 1 || port > MLX4_MAX_PORTS)
+		return 0;
+
+	return priv->mfunc.master.vf_admin[slave].enable_smi[port] ==
+		MLX4_VF_SMI_ENABLED;
+}
+EXPORT_SYMBOL_GPL(mlx4_vf_get_enable_smi_admin);
+
+int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port,
+				 int enabled)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	if (slave == mlx4_master_func_num(dev))
+		return 0;
+
+	if (slave < 1 || slave >= dev->num_slaves ||
+	    port < 1 || port > MLX4_MAX_PORTS ||
+	    enabled < 0 || enabled > 1)
+		return -EINVAL;
+
+	priv->mfunc.master.vf_admin[slave].enable_smi[port] = enabled;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_vf_set_enable_smi_admin);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 0487121e4a0..56022d64783 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -173,11 +173,11 @@ int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn)
 	if (*cqn == -1)
 		return -ENOMEM;
 
-	err = mlx4_table_get(dev, &cq_table->table, *cqn);
+	err = mlx4_table_get(dev, &cq_table->table, *cqn, GFP_KERNEL);
 	if (err)
 		goto err_out;
 
-	err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn);
+	err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn, GFP_KERNEL);
 	if (err)
 		goto err_put;
 	return 0;
@@ -293,6 +293,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	atomic_set(&cq->refcount, 1);
 	init_completion(&cq->free);
 
+	cq->irq = priv->eq_table.eq[cq->vector].irq;
 	return 0;
 
 err_radix:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index c2cd8d31bca..82322b1c841 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -125,15 +125,19 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 						   &cq->vector)) {
 					cq->vector = (cq->ring + 1 + priv->port)
 					    % mdev->dev->caps.num_comp_vectors;
-					mlx4_warn(mdev, "Failed Assigning an EQ to "
-						  "%s ,Falling back to legacy EQ's\n",
+					mlx4_warn(mdev, "Failed assigning an EQ to %s, falling back to legacy EQ's\n",
 						  name);
 				}
+
 			}
 		} else {
 			cq->vector = (cq->ring + 1 + priv->port) %
 				mdev->dev->caps.num_comp_vectors;
 		}
+
+		cq->irq_desc =
+			irq_to_desc(mlx4_eq_get_irq(mdev->dev,
+						    cq->vector));
 	} else {
 		/* For TX we use the same irq per
 		ring we assigned for the RX    */
@@ -164,6 +168,13 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq,
 			       NAPI_POLL_WEIGHT);
 	} else {
+		struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring];
+
+		err = irq_set_affinity_hint(cq->mcq.irq,
+					    ring->affinity_mask);
+		if (err)
+			mlx4_warn(mdev, "Failed setting affinity hint\n");
+
 		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64);
 		napi_hash_add(&cq->napi);
 	}
@@ -180,8 +191,9 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq)
 
 	mlx4_en_unmap_buffer(&cq->wqres.buf);
 	mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
-	if (priv->mdev->dev->caps.comp_pool && cq->vector)
+	if (priv->mdev->dev->caps.comp_pool && cq->vector) {
 		mlx4_release_eq(priv->mdev->dev, cq->vector);
+	}
 	cq->vector = 0;
 	cq->buf_size = 0;
 	cq->buf = NULL;
@@ -195,6 +207,7 @@ void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
 	if (!cq->is_tx) {
 		napi_hash_del(&cq->napi);
 		synchronize_rcu();
+		irq_set_affinity_hint(cq->mcq.irq, NULL);
 	}
 	netif_napi_del(&cq->napi);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 3e8d33605fe..68d763d2d03 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -378,8 +378,8 @@ static int mlx4_en_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		ethtool_cmd_speed_set(cmd, priv->port_state.link_speed);
 		cmd->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(cmd, -1);
-		cmd->duplex = -1;
+		ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
+		cmd->duplex = DUPLEX_UNKNOWN;
 	}
 
 	if (trans_type > 0 && trans_type <= 0xC) {
@@ -417,6 +417,8 @@ static int mlx4_en_get_coalesce(struct net_device *dev,
 
 	coal->tx_coalesce_usecs = priv->tx_usecs;
 	coal->tx_max_coalesced_frames = priv->tx_frames;
+	coal->tx_max_coalesced_frames_irq = priv->tx_work_limit;
+
 	coal->rx_coalesce_usecs = priv->rx_usecs;
 	coal->rx_max_coalesced_frames = priv->rx_frames;
 
@@ -426,6 +428,7 @@ static int mlx4_en_get_coalesce(struct net_device *dev,
 	coal->rx_coalesce_usecs_high = priv->rx_usecs_high;
 	coal->rate_sample_interval = priv->sample_interval;
 	coal->use_adaptive_rx_coalesce = priv->adaptive_rx_coal;
+
 	return 0;
 }
 
@@ -434,6 +437,9 @@ static int mlx4_en_set_coalesce(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
+	if (!coal->tx_max_coalesced_frames_irq)
+		return -EINVAL;
+
 	priv->rx_frames = (coal->rx_max_coalesced_frames ==
 			   MLX4_EN_AUTO_CONF) ?
 				MLX4_EN_RX_COAL_TARGET :
@@ -457,6 +463,7 @@ static int mlx4_en_set_coalesce(struct net_device *dev,
 	priv->rx_usecs_high = coal->rx_coalesce_usecs_high;
 	priv->sample_interval = coal->rate_sample_interval;
 	priv->adaptive_rx_coal = coal->use_adaptive_rx_coalesce;
+	priv->tx_work_limit = coal->tx_max_coalesced_frames_irq;
 
 	return mlx4_en_moderation_update(priv);
 }
@@ -564,7 +571,7 @@ static u32 mlx4_en_get_rxfh_indir_size(struct net_device *dev)
 	return priv->rx_ring_num;
 }
 
-static int mlx4_en_get_rxfh_indir(struct net_device *dev, u32 *ring_index)
+static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_rss_map *rss_map = &priv->rss_map;
@@ -582,8 +589,8 @@ static int mlx4_en_get_rxfh_indir(struct net_device *dev, u32 *ring_index)
 	return err;
 }
 
-static int mlx4_en_set_rxfh_indir(struct net_device *dev,
-		const u32 *ring_index)
+static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
+			    const u8 *key)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
@@ -925,13 +932,13 @@ static int mlx4_en_flow_replace(struct net_device *dev,
 		qpn = cmd->fs.ring_cookie & (EN_ETHTOOL_QP_ATTACH - 1);
 	} else {
 		if (cmd->fs.ring_cookie >= priv->rx_ring_num) {
-			en_warn(priv, "rxnfc: RX ring (%llu) doesn't exist.\n",
+			en_warn(priv, "rxnfc: RX ring (%llu) doesn't exist\n",
 				cmd->fs.ring_cookie);
 			return -EINVAL;
 		}
 		qpn = priv->rss_map.qps[cmd->fs.ring_cookie].qpn;
 		if (!qpn) {
-			en_warn(priv, "rxnfc: RX ring (%llu) is inactive.\n",
+			en_warn(priv, "rxnfc: RX ring (%llu) is inactive\n",
 				cmd->fs.ring_cookie);
 			return -EINVAL;
 		}
@@ -956,7 +963,7 @@ static int mlx4_en_flow_replace(struct net_device *dev,
 	}
 	err = mlx4_flow_attach(priv->mdev->dev, &rule, &reg_id);
 	if (err) {
-		en_err(priv, "Fail to attach network rule at location %d.\n",
+		en_err(priv, "Fail to attach network rule at location %d\n",
 		       cmd->fs.location);
 		goto out_free_list;
 	}
@@ -1121,7 +1128,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int port_up;
+	int port_up = 0;
 	int err = 0;
 
 	if (channel->other_count || channel->combined_count ||
@@ -1151,7 +1158,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
 
-	mlx4_en_setup_tc(dev, MLX4_EN_NUM_UP);
+	if (dev->num_tc)
+		mlx4_en_setup_tc(dev, MLX4_EN_NUM_UP);
 
 	en_warn(priv, "Using %d TX rings\n", priv->tx_ring_num);
 	en_warn(priv, "Using %d RX rings\n", priv->rx_ring_num);
@@ -1223,8 +1231,8 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
 	.get_rxnfc = mlx4_en_get_rxnfc,
 	.set_rxnfc = mlx4_en_set_rxnfc,
 	.get_rxfh_indir_size = mlx4_en_get_rxfh_indir_size,
-	.get_rxfh_indir = mlx4_en_get_rxfh_indir,
-	.set_rxfh_indir = mlx4_en_set_rxfh_indir,
+	.get_rxfh = mlx4_en_get_rxfh,
+	.set_rxfh = mlx4_en_set_rxfh,
 	.get_channels = mlx4_en_get_channels,
 	.set_channels = mlx4_en_set_channels,
 	.get_ts_info = mlx4_en_get_ts_info,
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 0c59d4fe7e3..f953c1d7eae 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -133,7 +133,7 @@ static int mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 			MLX4_EN_MAX_TX_RING_P_UP);
 	if (params->udp_rss && !(mdev->dev->caps.flags
 					& MLX4_DEV_CAP_FLAG_UDP_RSS)) {
-		mlx4_warn(mdev, "UDP RSS is not supported on this device.\n");
+		mlx4_warn(mdev, "UDP RSS is not supported on this device\n");
 		params->udp_rss = 0;
 	}
 	for (i = 1; i <= MLX4_MAX_PORTS; i++) {
@@ -251,8 +251,7 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 
 	mdev->LSO_support = !!(dev->caps.flags & (1 << 15));
 	if (!mdev->LSO_support)
-		mlx4_warn(mdev, "LSO not supported, please upgrade to later "
-				"FW version to enable LSO\n");
+		mlx4_warn(mdev, "LSO not supported, please upgrade to later FW version to enable LSO\n");
 
 	if (mlx4_mr_alloc(mdev->dev, mdev->priv_pdn, 0, ~0ull,
 			 MLX4_PERM_LOCAL_WRITE |  MLX4_PERM_LOCAL_READ,
@@ -268,7 +267,7 @@ static void *mlx4_en_add(struct mlx4_dev *dev)
 	/* Build device profile according to supplied module parameters */
 	err = mlx4_en_get_profile(mdev);
 	if (err) {
-		mlx4_err(mdev, "Bad module parameters, aborting.\n");
+		mlx4_err(mdev, "Bad module parameters, aborting\n");
 		goto err_mr;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 7e4b1720c3d..7345c43b019 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -130,7 +130,7 @@ static enum mlx4_net_trans_rule_id mlx4_ip_proto_to_trans_rule_id(u8 ip_proto)
 	case IPPROTO_TCP:
 		return MLX4_NET_TRANS_RULE_ID_TCP;
 	default:
-		return -EPROTONOSUPPORT;
+		return MLX4_NET_TRANS_RULE_NUM;
 	}
 };
 
@@ -177,7 +177,7 @@ static void mlx4_en_filter_work(struct work_struct *work)
 	int rc;
 	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
 
-	if (spec_tcp_udp.id < 0) {
+	if (spec_tcp_udp.id >= MLX4_NET_TRANS_RULE_NUM) {
 		en_warn(priv, "RFS: ignoring unsupported ip protocol (%d)\n",
 			filter->ip_proto);
 		goto ignore;
@@ -770,11 +770,12 @@ static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv)
 					  priv->dev->dev_addr, priv->prev_mac);
 		if (err)
 			en_err(priv, "Failed changing HW MAC address\n");
-		memcpy(priv->prev_mac, priv->dev->dev_addr,
-		       sizeof(priv->prev_mac));
 	} else
 		en_dbg(HW, priv, "Port is down while registering mac, exiting...\n");
 
+	memcpy(priv->prev_mac, priv->dev->dev_addr,
+	       sizeof(priv->prev_mac));
+
 	return err;
 }
 
@@ -788,9 +789,8 @@ static int mlx4_en_set_mac(struct net_device *dev, void *addr)
 	if (!is_valid_ether_addr(saddr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
-
 	mutex_lock(&mdev->state_lock);
+	memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
 	err = mlx4_en_do_set_mac(priv);
 	mutex_unlock(&mdev->state_lock);
 
@@ -1526,6 +1526,27 @@ static void mlx4_en_linkstate(struct work_struct *work)
 	mutex_unlock(&mdev->state_lock);
 }
 
+static int mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
+{
+	struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
+	int numa_node = priv->mdev->dev->numa_node;
+	int ret = 0;
+
+	if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	ret = cpumask_set_cpu_local_first(ring_idx, numa_node,
+					  ring->affinity_mask);
+	if (ret)
+		free_cpumask_var(ring->affinity_mask);
+
+	return ret;
+}
+
+static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
+{
+	free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask);
+}
 
 int mlx4_en_start_port(struct net_device *dev)
 {
@@ -1567,17 +1588,25 @@ int mlx4_en_start_port(struct net_device *dev)
 
 		mlx4_en_cq_init_lock(cq);
 
+		err = mlx4_en_init_affinity_hint(priv, i);
+		if (err) {
+			en_err(priv, "Failed preparing IRQ affinity hint\n");
+			goto cq_err;
+		}
+
 		err = mlx4_en_activate_cq(priv, cq, i);
 		if (err) {
 			en_err(priv, "Failed activating Rx CQ\n");
+			mlx4_en_free_affinity_hint(priv, i);
 			goto cq_err;
 		}
 		for (j = 0; j < cq->size; j++)
 			cq->buf[j].owner_sr_opcode = MLX4_CQE_OWNER_MASK;
 		err = mlx4_en_set_cq_moder(priv, cq);
 		if (err) {
-			en_err(priv, "Failed setting cq moderation parameters");
+			en_err(priv, "Failed setting cq moderation parameters\n");
 			mlx4_en_deactivate_cq(priv, cq);
+			mlx4_en_free_affinity_hint(priv, i);
 			goto cq_err;
 		}
 		mlx4_en_arm_cq(priv, cq);
@@ -1615,7 +1644,7 @@ int mlx4_en_start_port(struct net_device *dev)
 		}
 		err = mlx4_en_set_cq_moder(priv, cq);
 		if (err) {
-			en_err(priv, "Failed setting cq moderation parameters");
+			en_err(priv, "Failed setting cq moderation parameters\n");
 			mlx4_en_deactivate_cq(priv, cq);
 			goto tx_err;
 		}
@@ -1715,8 +1744,10 @@ rss_err:
 mac_err:
 	mlx4_en_put_qp(priv);
 cq_err:
-	while (rx_index--)
+	while (rx_index--) {
 		mlx4_en_deactivate_cq(priv, priv->rx_cq[rx_index]);
+		mlx4_en_free_affinity_hint(priv, i);
+	}
 	for (i = 0; i < priv->rx_ring_num; i++)
 		mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
 
@@ -1847,6 +1878,8 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 			msleep(1);
 		mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
 		mlx4_en_deactivate_cq(priv, cq);
+
+		mlx4_en_free_affinity_hint(priv, i);
 	}
 }
 
@@ -2303,7 +2336,7 @@ static void mlx4_en_add_vxlan_port(struct  net_device *dev,
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	__be16 current_port;
 
-	if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS))
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
 		return;
 
 	if (sa_family == AF_INET6)
@@ -2440,6 +2473,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 			MLX4_WQE_CTRL_SOLICITED);
 	priv->num_tx_rings_p_up = mdev->profile.num_tx_rings_p_up;
 	priv->tx_ring_num = prof->tx_ring_num;
+	priv->tx_work_limit = MLX4_EN_DEFAULT_TX_WORK;
 
 	priv->tx_ring = kzalloc(sizeof(struct mlx4_en_tx_ring *) * MAX_TX_RINGS,
 				GFP_KERNEL);
@@ -2539,7 +2573,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
 
-	SET_ETHTOOL_OPS(dev, &mlx4_en_ethtool_ops);
+	dev->ethtool_ops = &mlx4_en_ethtool_ops;
 
 	/*
 	 * Set driver features
@@ -2594,8 +2628,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 				    prof->tx_pause, prof->tx_ppp,
 				    prof->rx_pause, prof->rx_ppp);
 	if (err) {
-		en_err(priv, "Failed setting port general configurations "
-		       "for port %d, with error %d\n", priv->port, err);
+		en_err(priv, "Failed setting port general configurations for port %d, with error %d\n",
+		       priv->port, err);
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index ba049ae8874..5535862f27c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -40,6 +40,7 @@
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
 #include <linux/vmalloc.h>
+#include <linux/irq.h>
 
 #include "mlx4_en.h"
 
@@ -270,13 +271,11 @@ static int mlx4_en_fill_rx_buffers(struct mlx4_en_priv *priv)
 						    ring->actual_size,
 						    GFP_KERNEL)) {
 				if (ring->actual_size < MLX4_EN_MIN_RX_SIZE) {
-					en_err(priv, "Failed to allocate "
-						     "enough rx buffers\n");
+					en_err(priv, "Failed to allocate enough rx buffers\n");
 					return -ENOMEM;
 				} else {
 					new_size = rounddown_pow_of_two(ring->actual_size);
-					en_warn(priv, "Only %d buffers allocated "
-						      "reducing ring size to %d",
+					en_warn(priv, "Only %d buffers allocated reducing ring size to %d\n",
 						ring->actual_size, new_size);
 					goto reduce_rings;
 				}
@@ -685,10 +684,9 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		/* Drop packet on bad receive or bad checksum */
 		if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) ==
 						MLX4_CQE_OPCODE_ERROR)) {
-			en_err(priv, "CQE completed in error - vendor "
-				  "syndrom:%d syndrom:%d\n",
-				  ((struct mlx4_err_cqe *) cqe)->vendor_err_syndrome,
-				  ((struct mlx4_err_cqe *) cqe)->syndrome);
+			en_err(priv, "CQE completed in error - vendor syndrom:%d syndrom:%d\n",
+			       ((struct mlx4_err_cqe *)cqe)->vendor_err_syndrome,
+			       ((struct mlx4_err_cqe *)cqe)->syndrome);
 			goto next;
 		}
 		if (unlikely(cqe->badfcs_enc & MLX4_CQE_BAD_FCS)) {
@@ -785,6 +783,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 							     PKT_HASH_TYPE_L3);
 
 					skb_record_rx_queue(gro_skb, cq->ring);
+					skb_mark_napi_id(gro_skb, &cq->napi);
 
 					if (ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL) {
 						timestamp = mlx4_en_get_cqe_ts(cqe);
@@ -898,9 +897,25 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 	mlx4_en_cq_unlock_napi(cq);
 
 	/* If we used up all the quota - we're probably not done yet... */
-	if (done == budget)
+	if (done == budget) {
+		int cpu_curr;
+		const struct cpumask *aff;
+
 		INC_PERF_COUNTER(priv->pstats.napi_quota);
-	else {
+
+		cpu_curr = smp_processor_id();
+		aff = irq_desc_get_irq_data(cq->irq_desc)->affinity;
+
+		if (unlikely(!cpumask_test_cpu(cpu_curr, aff))) {
+			/* Current cpu is not according to smp_irq_affinity -
+			 * probably affinity changed. need to stop this NAPI
+			 * poll, and restart it on the right CPU
+			 */
+			napi_complete(napi);
+			mlx4_en_arm_cq(priv, cq);
+			return 0;
+		}
+	} else {
 		/* Done for now */
 		napi_complete(napi);
 		mlx4_en_arm_cq(priv, cq);
@@ -944,8 +959,8 @@ void mlx4_en_calc_rx_buf(struct net_device *dev)
 	priv->rx_skb_size = eff_mtu;
 	priv->log_rx_info = ROUNDUP_LOG2(i * sizeof(struct mlx4_en_rx_alloc));
 
-	en_dbg(DRV, priv, "Rx buffer scatter-list (effective-mtu:%d "
-		  "num_frags:%d):\n", eff_mtu, priv->num_frags);
+	en_dbg(DRV, priv, "Rx buffer scatter-list (effective-mtu:%d num_frags:%d):\n",
+	       eff_mtu, priv->num_frags);
 	for (i = 0; i < priv->num_frags; i++) {
 		en_err(priv,
 		       "  frag:%d - size:%d prefix:%d align:%d stride:%d\n",
@@ -972,7 +987,7 @@ static int mlx4_en_config_rss_qp(struct mlx4_en_priv *priv, int qpn,
 	if (!context)
 		return -ENOMEM;
 
-	err = mlx4_qp_alloc(mdev->dev, qpn, qp);
+	err = mlx4_qp_alloc(mdev->dev, qpn, qp, GFP_KERNEL);
 	if (err) {
 		en_err(priv, "Failed to allocate qp #%x\n", qpn);
 		goto out;
@@ -1012,7 +1027,7 @@ int mlx4_en_create_drop_qp(struct mlx4_en_priv *priv)
 		en_err(priv, "Failed reserving drop qpn\n");
 		return err;
 	}
-	err = mlx4_qp_alloc(priv->mdev->dev, qpn, &priv->drop_qp);
+	err = mlx4_qp_alloc(priv->mdev->dev, qpn, &priv->drop_qp, GFP_KERNEL);
 	if (err) {
 		en_err(priv, "Failed allocating drop qp\n");
 		mlx4_qp_release_range(priv->mdev->dev, qpn, 1);
@@ -1071,7 +1086,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	}
 
 	/* Configure RSS indirection qp */
-	err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, &rss_map->indir_qp);
+	err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, &rss_map->indir_qp, GFP_KERNEL);
 	if (err) {
 		en_err(priv, "Failed to allocate RSS indirection QP\n");
 		goto rss_err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index dd1f6d34645..5045bab5963 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -108,12 +108,12 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 
 	ring->buf = ring->wqres.buf.direct.buf;
 
-	en_dbg(DRV, priv, "Allocated TX ring (addr:%p) - buf:%p size:%d "
-	       "buf_size:%d dma:%llx\n", ring, ring->buf, ring->size,
-	       ring->buf_size, (unsigned long long) ring->wqres.buf.direct.map);
+	en_dbg(DRV, priv, "Allocated TX ring (addr:%p) - buf:%p size:%d buf_size:%d dma:%llx\n",
+	       ring, ring->buf, ring->size, ring->buf_size,
+	       (unsigned long long) ring->wqres.buf.direct.map);
 
 	ring->qpn = qpn;
-	err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->qp);
+	err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->qp, GFP_KERNEL);
 	if (err) {
 		en_err(priv, "Failed allocating qp %d\n", ring->qpn);
 		goto err_map;
@@ -122,7 +122,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 
 	err = mlx4_bf_alloc(mdev->dev, &ring->bf, node);
 	if (err) {
-		en_dbg(DRV, priv, "working without blueflame (%d)", err);
+		en_dbg(DRV, priv, "working without blueflame (%d)\n", err);
 		ring->bf.uar = &mdev->priv_uar;
 		ring->bf.uar->map = mdev->uar_map;
 		ring->bf_enabled = false;
@@ -351,9 +351,8 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
 	return cnt;
 }
 
-static int mlx4_en_process_tx_cq(struct net_device *dev,
-				 struct mlx4_en_cq *cq,
-				 int budget)
+static bool mlx4_en_process_tx_cq(struct net_device *dev,
+				 struct mlx4_en_cq *cq)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_cq *mcq = &cq->mcq;
@@ -372,9 +371,10 @@ static int mlx4_en_process_tx_cq(struct net_device *dev,
 	int factor = priv->cqe_factor;
 	u64 timestamp = 0;
 	int done = 0;
+	int budget = priv->tx_work_limit;
 
 	if (!priv->port_up)
-		return 0;
+		return true;
 
 	index = cons_index & size_mask;
 	cqe = &buf[(index << factor) + factor];
@@ -447,7 +447,7 @@ static int mlx4_en_process_tx_cq(struct net_device *dev,
 		netif_tx_wake_queue(ring->tx_queue);
 		ring->wake_queue++;
 	}
-	return done;
+	return done < budget;
 }
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq)
@@ -467,18 +467,16 @@ int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget)
 	struct mlx4_en_cq *cq = container_of(napi, struct mlx4_en_cq, napi);
 	struct net_device *dev = cq->dev;
 	struct mlx4_en_priv *priv = netdev_priv(dev);
-	int done;
+	int clean_complete;
 
-	done = mlx4_en_process_tx_cq(dev, cq, budget);
+	clean_complete = mlx4_en_process_tx_cq(dev, cq);
+	if (!clean_complete)
+		return budget;
 
-	/* If we used up all the quota - we're probably not done yet... */
-	if (done < budget) {
-		/* Done for now */
-		napi_complete(napi);
-		mlx4_en_arm_cq(priv, cq);
-		return done;
-	}
-	return budget;
+	napi_complete(napi);
+	mlx4_en_arm_cq(priv, cq);
+
+	return 0;
 }
 
 static struct mlx4_en_tx_desc *mlx4_en_bounce_to_desc(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index d501a2b0fb7..2a004b347e1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -152,14 +152,13 @@ void mlx4_gen_slave_eqe(struct work_struct *work)
 				if (i != dev->caps.function &&
 				    master->slave_state[i].active)
 					if (mlx4_GEN_EQE(dev, i, eqe))
-						mlx4_warn(dev, "Failed to "
-							  " generate event "
-							  "for slave %d\n", i);
+						mlx4_warn(dev, "Failed to generate event for slave %d\n",
+							  i);
 			}
 		} else {
 			if (mlx4_GEN_EQE(dev, slave, eqe))
-				mlx4_warn(dev, "Failed to generate event "
-					       "for slave %d\n", slave);
+				mlx4_warn(dev, "Failed to generate event for slave %d\n",
+					  slave);
 		}
 		++slave_eq->cons;
 	}
@@ -177,8 +176,8 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
 	s_eqe = &slave_eq->event_eqe[slave_eq->prod & (SLAVE_EVENT_EQ_SIZE - 1)];
 	if ((!!(s_eqe->owner & 0x80)) ^
 	    (!!(slave_eq->prod & SLAVE_EVENT_EQ_SIZE))) {
-		mlx4_warn(dev, "Master failed to generate an EQE for slave: %d. "
-			  "No free EQE on slave events queue\n", slave);
+		mlx4_warn(dev, "Master failed to generate an EQE for slave: %d. No free EQE on slave events queue\n",
+			  slave);
 		spin_unlock_irqrestore(&slave_eq->event_lock, flags);
 		return;
 	}
@@ -375,9 +374,9 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave,
 		}
 		break;
 	default:
-		pr_err("%s: BUG!!! UNKNOWN state: "
-		       "slave:%d, port:%d\n", __func__, slave, port);
-			goto out;
+		pr_err("%s: BUG!!! UNKNOWN state: slave:%d, port:%d\n",
+		       __func__, slave, port);
+		goto out;
 	}
 	ret = mlx4_get_slave_port_state(dev, slave, port);
 
@@ -425,8 +424,8 @@ void mlx4_master_handle_slave_flr(struct work_struct *work)
 	for (i = 0 ; i < dev->num_slaves; i++) {
 
 		if (MLX4_COMM_CMD_FLR == slave_state[i].last_cmd) {
-			mlx4_dbg(dev, "mlx4_handle_slave_flr: "
-				 "clean slave: %d\n", i);
+			mlx4_dbg(dev, "mlx4_handle_slave_flr: clean slave: %d\n",
+				 i);
 
 			mlx4_delete_all_resources_for_slave(dev, i);
 			/*return the slave to running mode*/
@@ -438,8 +437,8 @@ void mlx4_master_handle_slave_flr(struct work_struct *work)
 			err = mlx4_cmd(dev, 0, i, 0, MLX4_CMD_INFORM_FLR_DONE,
 				       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 			if (err)
-				mlx4_warn(dev, "Failed to notify FW on "
-					  "FLR done (slave:%d)\n", i);
+				mlx4_warn(dev, "Failed to notify FW on FLR done (slave:%d)\n",
+					  i);
 		}
 	}
 }
@@ -490,9 +489,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 						be32_to_cpu(eqe->event.qp.qpn)
 						& 0xffffff, &slave);
 				if (ret && ret != -ENOENT) {
-					mlx4_dbg(dev, "QP event %02x(%02x) on "
-						 "EQ %d at index %u: could "
-						 "not get slave id (%d)\n",
+					mlx4_dbg(dev, "QP event %02x(%02x) on EQ %d at index %u: could not get slave id (%d)\n",
 						 eqe->type, eqe->subtype,
 						 eq->eqn, eq->cons_index, ret);
 					break;
@@ -520,23 +517,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 						& 0xffffff,
 						&slave);
 				if (ret && ret != -ENOENT) {
-					mlx4_warn(dev, "SRQ event %02x(%02x) "
-						  "on EQ %d at index %u: could"
-						  " not get slave id (%d)\n",
+					mlx4_warn(dev, "SRQ event %02x(%02x) on EQ %d at index %u: could not get slave id (%d)\n",
 						  eqe->type, eqe->subtype,
 						  eq->eqn, eq->cons_index, ret);
 					break;
 				}
-				mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x,"
-					  " event: %02x(%02x)\n", __func__,
-					  slave,
+				mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
+					  __func__, slave,
 					  be32_to_cpu(eqe->event.srq.srqn),
 					  eqe->type, eqe->subtype);
 
 				if (!ret && slave != dev->caps.function) {
-					mlx4_warn(dev, "%s: sending event "
-						  "%02x(%02x) to slave:%d\n",
-						   __func__, eqe->type,
+					mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
+						  __func__, eqe->type,
 						  eqe->subtype, slave);
 					mlx4_slave_event(dev, slave, eqe);
 					break;
@@ -569,8 +562,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) {
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN"
-							 " to slave: %d, port:%d\n",
+						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n",
 							 __func__, i, port);
 						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
@@ -634,11 +626,9 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					be32_to_cpu(eqe->event.cq_err.cqn)
 					& 0xffffff, &slave);
 				if (ret && ret != -ENOENT) {
-					mlx4_dbg(dev, "CQ event %02x(%02x) on "
-						 "EQ %d at index %u: could "
-						  "not get slave id (%d)\n",
-						  eqe->type, eqe->subtype,
-						  eq->eqn, eq->cons_index, ret);
+					mlx4_dbg(dev, "CQ event %02x(%02x) on EQ %d at index %u: could not get slave id (%d)\n",
+						 eqe->type, eqe->subtype,
+						 eq->eqn, eq->cons_index, ret);
 					break;
 				}
 
@@ -667,8 +657,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 
 		case MLX4_EVENT_TYPE_COMM_CHANNEL:
 			if (!mlx4_is_master(dev)) {
-				mlx4_warn(dev, "Received comm channel event "
-					       "for non master device\n");
+				mlx4_warn(dev, "Received comm channel event for non master device\n");
 				break;
 			}
 			memcpy(&priv->mfunc.master.comm_arm_bit_vector,
@@ -681,8 +670,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 		case MLX4_EVENT_TYPE_FLR_EVENT:
 			flr_slave = be32_to_cpu(eqe->event.flr_event.slave_id);
 			if (!mlx4_is_master(dev)) {
-				mlx4_warn(dev, "Non-master function received"
-					       "FLR event\n");
+				mlx4_warn(dev, "Non-master function received FLR event\n");
 				break;
 			}
 
@@ -711,22 +699,17 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			if (eqe->subtype == MLX4_FATAL_WARNING_SUBTYPE_WARMING) {
 				if (mlx4_is_master(dev))
 					for (i = 0; i < dev->num_slaves; i++) {
-						mlx4_dbg(dev, "%s: Sending "
-							"MLX4_FATAL_WARNING_SUBTYPE_WARMING"
-							" to slave: %d\n", __func__, i);
+						mlx4_dbg(dev, "%s: Sending MLX4_FATAL_WARNING_SUBTYPE_WARMING to slave: %d\n",
+							 __func__, i);
 						if (i == dev->caps.function)
 							continue;
 						mlx4_slave_event(dev, i, eqe);
 					}
-				mlx4_err(dev, "Temperature Threshold was reached! "
-					"Threshold: %d celsius degrees; "
-					"Current Temperature: %d\n",
-					be16_to_cpu(eqe->event.warming.warning_threshold),
-					be16_to_cpu(eqe->event.warming.current_temperature));
+				mlx4_err(dev, "Temperature Threshold was reached! Threshold: %d celsius degrees; Current Temperature: %d\n",
+					 be16_to_cpu(eqe->event.warming.warning_threshold),
+					 be16_to_cpu(eqe->event.warming.current_temperature));
 			} else
-				mlx4_warn(dev, "Unhandled event FATAL WARNING (%02x), "
-					  "subtype %02x on EQ %d at index %u. owner=%x, "
-					  "nent=0x%x, slave=%x, ownership=%s\n",
+				mlx4_warn(dev, "Unhandled event FATAL WARNING (%02x), subtype %02x on EQ %d at index %u. owner=%x, nent=0x%x, slave=%x, ownership=%s\n",
 					  eqe->type, eqe->subtype, eq->eqn,
 					  eq->cons_index, eqe->owner, eq->nent,
 					  eqe->slave_id,
@@ -743,9 +726,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 		case MLX4_EVENT_TYPE_EEC_CATAS_ERROR:
 		case MLX4_EVENT_TYPE_ECC_DETECT:
 		default:
-			mlx4_warn(dev, "Unhandled event %02x(%02x) on EQ %d at "
-				  "index %u. owner=%x, nent=0x%x, slave=%x, "
-				  "ownership=%s\n",
+			mlx4_warn(dev, "Unhandled event %02x(%02x) on EQ %d at index %u. owner=%x, nent=0x%x, slave=%x, ownership=%s\n",
 				  eqe->type, eqe->subtype, eq->eqn,
 				  eq->cons_index, eqe->owner, eq->nent,
 				  eqe->slave_id,
@@ -1088,7 +1069,7 @@ static int mlx4_map_clr_int(struct mlx4_dev *dev)
 	priv->clr_base = ioremap(pci_resource_start(dev->pdev, priv->fw.clr_int_bar) +
 				 priv->fw.clr_int_base, MLX4_CLR_INT_SIZE);
 	if (!priv->clr_base) {
-		mlx4_err(dev, "Couldn't map interrupt clear register, aborting.\n");
+		mlx4_err(dev, "Couldn't map interrupt clear register, aborting\n");
 		return -ENOMEM;
 	}
 
@@ -1372,6 +1353,7 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 				continue;
 				/*we dont want to break here*/
 			}
+
 			eq_set_ci(&priv->eq_table.eq[vec], 1);
 		}
 	}
@@ -1387,6 +1369,14 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 }
 EXPORT_SYMBOL(mlx4_assign_eq);
 
+int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return priv->eq_table.eq[vec].irq;
+}
+EXPORT_SYMBOL(mlx4_eq_get_irq);
+
 void mlx4_release_eq(struct mlx4_dev *dev, int vec)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index d16a4d11890..688e1eabab2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -178,8 +178,8 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 				struct mlx4_cmd_info *cmd)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	u8	field;
-	u32	size;
+	u8	field, port;
+	u32	size, proxy_qp, qkey;
 	int	err = 0;
 
 #define QUERY_FUNC_CAP_FLAGS_OFFSET		0x0
@@ -209,6 +209,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 
 /* when opcode modifier = 1 */
 #define QUERY_FUNC_CAP_PHYS_PORT_OFFSET		0x3
+#define QUERY_FUNC_CAP_PRIV_VF_QKEY_OFFSET	0x4
 #define QUERY_FUNC_CAP_FLAGS0_OFFSET		0x8
 #define QUERY_FUNC_CAP_FLAGS1_OFFSET		0xc
 
@@ -221,6 +222,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 #define QUERY_FUNC_CAP_FLAGS1_FORCE_MAC		0x40
 #define QUERY_FUNC_CAP_FLAGS1_FORCE_VLAN	0x80
 #define QUERY_FUNC_CAP_FLAGS1_NIC_INFO			0x10
+#define QUERY_FUNC_CAP_VF_ENABLE_QP0		0x08
 
 #define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80
 
@@ -234,28 +236,35 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 			return -EINVAL;
 
 		vhcr->in_modifier = converted_port;
-		/* Set nic_info bit to mark new fields support */
-		field  = QUERY_FUNC_CAP_FLAGS1_NIC_INFO;
-		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS1_OFFSET);
-
 		/* phys-port = logical-port */
 		field = vhcr->in_modifier -
 			find_first_bit(actv_ports.ports, dev->caps.num_ports);
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
 
-		field = vhcr->in_modifier;
+		port = vhcr->in_modifier;
+		proxy_qp = dev->phys_caps.base_proxy_sqpn + 8 * slave + port - 1;
+
+		/* Set nic_info bit to mark new fields support */
+		field  = QUERY_FUNC_CAP_FLAGS1_NIC_INFO;
+
+		if (mlx4_vf_smi_enabled(dev, slave, port) &&
+		    !mlx4_get_parav_qkey(dev, proxy_qp, &qkey)) {
+			field |= QUERY_FUNC_CAP_VF_ENABLE_QP0;
+			MLX4_PUT(outbox->buf, qkey,
+				 QUERY_FUNC_CAP_PRIV_VF_QKEY_OFFSET);
+		}
+		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS1_OFFSET);
+
 		/* size is now the QP number */
-		size = dev->phys_caps.base_tunnel_sqpn + 8 * slave + field - 1;
+		size = dev->phys_caps.base_tunnel_sqpn + 8 * slave + port - 1;
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP0_TUNNEL);
 
 		size += 2;
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP1_TUNNEL);
 
-		size = dev->phys_caps.base_proxy_sqpn + 8 * slave + field - 1;
-		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP0_PROXY);
-
-		size += 2;
-		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP1_PROXY);
+		MLX4_PUT(outbox->buf, proxy_qp, QUERY_FUNC_CAP_QP0_PROXY);
+		proxy_qp += 2;
+		MLX4_PUT(outbox->buf, proxy_qp, QUERY_FUNC_CAP_QP1_PROXY);
 
 		MLX4_PUT(outbox->buf, dev->caps.phys_port_id[vhcr->in_modifier],
 			 QUERY_FUNC_CAP_PHYS_PORT_ID);
@@ -326,7 +335,7 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port,
 	struct mlx4_cmd_mailbox *mailbox;
 	u32			*outbox;
 	u8			field, op_modifier;
-	u32			size;
+	u32			size, qkey;
 	int			err = 0, quotas = 0;
 
 	op_modifier = !!gen_or_port; /* 0 = general, 1 = logical port */
@@ -414,7 +423,7 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port,
 
 	MLX4_GET(func_cap->flags1, outbox, QUERY_FUNC_CAP_FLAGS1_OFFSET);
 	if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_ETH) {
-		if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_OFFSET) {
+		if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_FORCE_VLAN) {
 			mlx4_err(dev, "VLAN is enforced on this port\n");
 			err = -EPROTONOSUPPORT;
 			goto out;
@@ -428,8 +437,7 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port,
 	} else if (dev->caps.port_type[gen_or_port] == MLX4_PORT_TYPE_IB) {
 		MLX4_GET(field, outbox, QUERY_FUNC_CAP_FLAGS0_OFFSET);
 		if (field & QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID) {
-			mlx4_err(dev, "phy_wqe_gid is "
-				 "enforced on this ib port\n");
+			mlx4_err(dev, "phy_wqe_gid is enforced on this ib port\n");
 			err = -EPROTONOSUPPORT;
 			goto out;
 		}
@@ -442,6 +450,13 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u32 gen_or_port,
 		goto out;
 	}
 
+	if (func_cap->flags1 & QUERY_FUNC_CAP_VF_ENABLE_QP0) {
+		MLX4_GET(qkey, outbox, QUERY_FUNC_CAP_PRIV_VF_QKEY_OFFSET);
+		func_cap->qp0_qkey = qkey;
+	} else {
+		func_cap->qp0_qkey = 0;
+	}
+
 	MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP0_TUNNEL);
 	func_cap->qp0_tunnel_qpn = size & 0xFFFFFF;
 
@@ -1054,10 +1069,10 @@ int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt)
 		 */
 		lg = ffs(mlx4_icm_addr(&iter) | mlx4_icm_size(&iter)) - 1;
 		if (lg < MLX4_ICM_PAGE_SHIFT) {
-			mlx4_warn(dev, "Got FW area not aligned to %d (%llx/%lx).\n",
-				   MLX4_ICM_PAGE_SIZE,
-				   (unsigned long long) mlx4_icm_addr(&iter),
-				   mlx4_icm_size(&iter));
+			mlx4_warn(dev, "Got FW area not aligned to %d (%llx/%lx)\n",
+				  MLX4_ICM_PAGE_SIZE,
+				  (unsigned long long) mlx4_icm_addr(&iter),
+				  mlx4_icm_size(&iter));
 			err = -EINVAL;
 			goto out;
 		}
@@ -1093,14 +1108,14 @@ int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt)
 
 	switch (op) {
 	case MLX4_CMD_MAP_FA:
-		mlx4_dbg(dev, "Mapped %d chunks/%d KB for FW.\n", tc, ts);
+		mlx4_dbg(dev, "Mapped %d chunks/%d KB for FW\n", tc, ts);
 		break;
 	case MLX4_CMD_MAP_ICM_AUX:
-		mlx4_dbg(dev, "Mapped %d chunks/%d KB for ICM aux.\n", tc, ts);
+		mlx4_dbg(dev, "Mapped %d chunks/%d KB for ICM aux\n", tc, ts);
 		break;
 	case MLX4_CMD_MAP_ICM:
-		mlx4_dbg(dev, "Mapped %d chunks/%d KB at %llx for ICM.\n",
-			  tc, ts, (unsigned long long) virt - (ts << 10));
+		mlx4_dbg(dev, "Mapped %d chunks/%d KB at %llx for ICM\n",
+			 tc, ts, (unsigned long long) virt - (ts << 10));
 		break;
 	}
 
@@ -1186,14 +1201,13 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev)
 	MLX4_GET(cmd_if_rev, outbox, QUERY_FW_CMD_IF_REV_OFFSET);
 	if (cmd_if_rev < MLX4_COMMAND_INTERFACE_MIN_REV ||
 	    cmd_if_rev > MLX4_COMMAND_INTERFACE_MAX_REV) {
-		mlx4_err(dev, "Installed FW has unsupported "
-			 "command interface revision %d.\n",
+		mlx4_err(dev, "Installed FW has unsupported command interface revision %d\n",
 			 cmd_if_rev);
 		mlx4_err(dev, "(Installed FW version is %d.%d.%03d)\n",
 			 (int) (dev->caps.fw_ver >> 32),
 			 (int) (dev->caps.fw_ver >> 16) & 0xffff,
 			 (int) dev->caps.fw_ver & 0xffff);
-		mlx4_err(dev, "This driver version supports only revisions %d to %d.\n",
+		mlx4_err(dev, "This driver version supports only revisions %d to %d\n",
 			 MLX4_COMMAND_INTERFACE_MIN_REV, MLX4_COMMAND_INTERFACE_MAX_REV);
 		err = -ENODEV;
 		goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 6811ee00ba7..1fce03ebe5c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -134,6 +134,7 @@ struct mlx4_func_cap {
 	int	max_eq;
 	int	reserved_eq;
 	int	mcg_quota;
+	u32	qp0_qkey;
 	u32	qp0_tunnel_qpn;
 	u32	qp0_proxy_qpn;
 	u32	qp1_tunnel_qpn;
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 5fbf4924c27..97c9b1db1d2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -245,7 +245,8 @@ int mlx4_UNMAP_ICM_AUX(struct mlx4_dev *dev)
 			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 }
 
-int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj)
+int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj,
+		   gfp_t gfp)
 {
 	u32 i = (obj & (table->num_obj - 1)) /
 			(MLX4_TABLE_CHUNK_SIZE / table->obj_size);
@@ -259,7 +260,7 @@ int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj)
 	}
 
 	table->icm[i] = mlx4_alloc_icm(dev, MLX4_TABLE_CHUNK_SIZE >> PAGE_SHIFT,
-				       (table->lowmem ? GFP_KERNEL : GFP_HIGHUSER) |
+				       (table->lowmem ? gfp : GFP_HIGHUSER) |
 				       __GFP_NOWARN, table->coherent);
 	if (!table->icm[i]) {
 		ret = -ENOMEM;
@@ -356,7 +357,7 @@ int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 	u32 i;
 
 	for (i = start; i <= end; i += inc) {
-		err = mlx4_table_get(dev, table, i);
+		err = mlx4_table_get(dev, table, i, GFP_KERNEL);
 		if (err)
 			goto fail;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.h b/drivers/net/ethernet/mellanox/mlx4/icm.h
index dee67fa3910..0c736455015 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.h
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.h
@@ -71,7 +71,8 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 				gfp_t gfp_mask, int coherent);
 void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent);
 
-int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj);
+int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj,
+		   gfp_t gfp);
 void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj);
 int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
 			 u32 start, u32 end);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index c187d748115..82ab427290c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -104,8 +104,6 @@ module_param(enable_64b_cqe_eqe, bool, 0444);
 MODULE_PARM_DESC(enable_64b_cqe_eqe,
 		 "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");
 
-#define HCA_GLOBAL_CAP_MASK            0
-
 #define PF_CONTEXT_BEHAVIOUR_MASK	MLX4_FUNC_CAP_64B_EQE_CQE
 
 static char mlx4_version[] =
@@ -134,8 +132,7 @@ MODULE_PARM_DESC(log_num_vlan, "Log2 max number of VLANs per ETH port (0-7)");
 
 static bool use_prio;
 module_param_named(use_prio, use_prio, bool, 0444);
-MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports "
-		  "(0/1, default 0)");
+MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports (deprecated)");
 
 int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
 module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444);
@@ -163,8 +160,7 @@ int mlx4_check_port_params(struct mlx4_dev *dev,
 	for (i = 0; i < dev->caps.num_ports - 1; i++) {
 		if (port_type[i] != port_type[i + 1]) {
 			if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP)) {
-				mlx4_err(dev, "Only same port types supported "
-					 "on this HCA, aborting.\n");
+				mlx4_err(dev, "Only same port types supported on this HCA, aborting\n");
 				return -EINVAL;
 			}
 		}
@@ -172,8 +168,8 @@ int mlx4_check_port_params(struct mlx4_dev *dev,
 
 	for (i = 0; i < dev->caps.num_ports; i++) {
 		if (!(port_type[i] & dev->caps.supported_type[i+1])) {
-			mlx4_err(dev, "Requested port type for port %d is not "
-				      "supported on this HCA\n", i + 1);
+			mlx4_err(dev, "Requested port type for port %d is not supported on this HCA\n",
+				 i + 1);
 			return -EINVAL;
 		}
 	}
@@ -195,26 +191,23 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 	err = mlx4_QUERY_DEV_CAP(dev, dev_cap);
 	if (err) {
-		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n");
 		return err;
 	}
 
 	if (dev_cap->min_page_sz > PAGE_SIZE) {
-		mlx4_err(dev, "HCA minimum page size of %d bigger than "
-			 "kernel PAGE_SIZE of %ld, aborting.\n",
+		mlx4_err(dev, "HCA minimum page size of %d bigger than kernel PAGE_SIZE of %ld, aborting\n",
 			 dev_cap->min_page_sz, PAGE_SIZE);
 		return -ENODEV;
 	}
 	if (dev_cap->num_ports > MLX4_MAX_PORTS) {
-		mlx4_err(dev, "HCA has %d ports, but we only support %d, "
-			 "aborting.\n",
+		mlx4_err(dev, "HCA has %d ports, but we only support %d, aborting\n",
 			 dev_cap->num_ports, MLX4_MAX_PORTS);
 		return -ENODEV;
 	}
 
 	if (dev_cap->uar_size > pci_resource_len(dev->pdev, 2)) {
-		mlx4_err(dev, "HCA reported UAR size of 0x%x bigger than "
-			 "PCI resource 2 size of 0x%llx, aborting.\n",
+		mlx4_err(dev, "HCA reported UAR size of 0x%x bigger than PCI resource 2 size of 0x%llx, aborting\n",
 			 dev_cap->uar_size,
 			 (unsigned long long) pci_resource_len(dev->pdev, 2));
 		return -ENODEV;
@@ -296,7 +289,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 	dev->caps.log_num_macs  = log_num_mac;
 	dev->caps.log_num_vlans = MLX4_LOG_NUM_VLANS;
-	dev->caps.log_num_prios = use_prio ? 3 : 0;
 
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
 		dev->caps.port_type[i] = MLX4_PORT_TYPE_NONE;
@@ -347,14 +339,12 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 		if (dev->caps.log_num_macs > dev_cap->log_max_macs[i]) {
 			dev->caps.log_num_macs = dev_cap->log_max_macs[i];
-			mlx4_warn(dev, "Requested number of MACs is too much "
-				  "for port %d, reducing to %d.\n",
+			mlx4_warn(dev, "Requested number of MACs is too much for port %d, reducing to %d\n",
 				  i, 1 << dev->caps.log_num_macs);
 		}
 		if (dev->caps.log_num_vlans > dev_cap->log_max_vlans[i]) {
 			dev->caps.log_num_vlans = dev_cap->log_max_vlans[i];
-			mlx4_warn(dev, "Requested number of VLANs is too much "
-				  "for port %d, reducing to %d.\n",
+			mlx4_warn(dev, "Requested number of VLANs is too much for port %d, reducing to %d\n",
 				  i, 1 << dev->caps.log_num_vlans);
 		}
 	}
@@ -366,7 +356,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] =
 		(1 << dev->caps.log_num_macs) *
 		(1 << dev->caps.log_num_vlans) *
-		(1 << dev->caps.log_num_prios) *
 		dev->caps.num_ports;
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;
 
@@ -584,13 +573,14 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	memset(&hca_param, 0, sizeof(hca_param));
 	err = mlx4_QUERY_HCA(dev, &hca_param);
 	if (err) {
-		mlx4_err(dev, "QUERY_HCA command failed, aborting.\n");
+		mlx4_err(dev, "QUERY_HCA command failed, aborting\n");
 		return err;
 	}
 
-	/*fail if the hca has an unknown capability */
-	if ((hca_param.global_caps | HCA_GLOBAL_CAP_MASK) !=
-	    HCA_GLOBAL_CAP_MASK) {
+	/* fail if the hca has an unknown global capability
+	 * at this time global_caps should be always zeroed
+	 */
+	if (hca_param.global_caps) {
 		mlx4_err(dev, "Unknown hca global capabilities\n");
 		return -ENOSYS;
 	}
@@ -603,19 +593,18 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	dev->caps.max_qp_dest_rdma = 1 << hca_param.log_rd_per_qp;
 	err = mlx4_dev_cap(dev, &dev_cap);
 	if (err) {
-		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n");
 		return err;
 	}
 
 	err = mlx4_QUERY_FW(dev);
 	if (err)
-		mlx4_err(dev, "QUERY_FW command failed: could not get FW version.\n");
+		mlx4_err(dev, "QUERY_FW command failed: could not get FW version\n");
 
 	page_size = ~dev->caps.page_size_cap + 1;
 	mlx4_warn(dev, "HCA minimum page size:%d\n", page_size);
 	if (page_size > PAGE_SIZE) {
-		mlx4_err(dev, "HCA minimum page size of %d bigger than "
-			 "kernel PAGE_SIZE of %ld, aborting.\n",
+		mlx4_err(dev, "HCA minimum page size of %d bigger than kernel PAGE_SIZE of %ld, aborting\n",
 			 page_size, PAGE_SIZE);
 		return -ENODEV;
 	}
@@ -633,8 +622,8 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	memset(&func_cap, 0, sizeof(func_cap));
 	err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap);
 	if (err) {
-		mlx4_err(dev, "QUERY_FUNC_CAP general command failed, aborting (%d).\n",
-			  err);
+		mlx4_err(dev, "QUERY_FUNC_CAP general command failed, aborting (%d)\n",
+			 err);
 		return err;
 	}
 
@@ -661,18 +650,20 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	dev->caps.num_amgms             = 0;
 
 	if (dev->caps.num_ports > MLX4_MAX_PORTS) {
-		mlx4_err(dev, "HCA has %d ports, but we only support %d, "
-			 "aborting.\n", dev->caps.num_ports, MLX4_MAX_PORTS);
+		mlx4_err(dev, "HCA has %d ports, but we only support %d, aborting\n",
+			 dev->caps.num_ports, MLX4_MAX_PORTS);
 		return -ENODEV;
 	}
 
+	dev->caps.qp0_qkey = kcalloc(dev->caps.num_ports, sizeof(u32), GFP_KERNEL);
 	dev->caps.qp0_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
 	dev->caps.qp0_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
 	dev->caps.qp1_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
 	dev->caps.qp1_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
 
 	if (!dev->caps.qp0_tunnel || !dev->caps.qp0_proxy ||
-	    !dev->caps.qp1_tunnel || !dev->caps.qp1_proxy) {
+	    !dev->caps.qp1_tunnel || !dev->caps.qp1_proxy ||
+	    !dev->caps.qp0_qkey) {
 		err = -ENOMEM;
 		goto err_mem;
 	}
@@ -680,10 +671,11 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
 		err = mlx4_QUERY_FUNC_CAP(dev, (u32) i, &func_cap);
 		if (err) {
-			mlx4_err(dev, "QUERY_FUNC_CAP port command failed for"
-				 " port %d, aborting (%d).\n", i, err);
+			mlx4_err(dev, "QUERY_FUNC_CAP port command failed for port %d, aborting (%d)\n",
+				 i, err);
 			goto err_mem;
 		}
+		dev->caps.qp0_qkey[i - 1] = func_cap.qp0_qkey;
 		dev->caps.qp0_tunnel[i - 1] = func_cap.qp0_tunnel_qpn;
 		dev->caps.qp0_proxy[i - 1] = func_cap.qp0_proxy_qpn;
 		dev->caps.qp1_tunnel[i - 1] = func_cap.qp1_tunnel_qpn;
@@ -699,8 +691,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	if (dev->caps.uar_page_size * (dev->caps.num_uars -
 				       dev->caps.reserved_uars) >
 				       pci_resource_len(dev->pdev, 2)) {
-		mlx4_err(dev, "HCA reported UAR region size of 0x%x bigger than "
-			 "PCI resource 2 size of 0x%llx, aborting.\n",
+		mlx4_err(dev, "HCA reported UAR region size of 0x%x bigger than PCI resource 2 size of 0x%llx, aborting\n",
 			 dev->caps.uar_page_size * dev->caps.num_uars,
 			 (unsigned long long) pci_resource_len(dev->pdev, 2));
 		goto err_mem;
@@ -722,19 +713,23 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 	}
 
 	dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS;
-	mlx4_warn(dev, "Timestamping is not supported in slave mode.\n");
+	mlx4_warn(dev, "Timestamping is not supported in slave mode\n");
 
 	slave_adjust_steering_mode(dev, &dev_cap, &hca_param);
 
 	return 0;
 
 err_mem:
+	kfree(dev->caps.qp0_qkey);
 	kfree(dev->caps.qp0_tunnel);
 	kfree(dev->caps.qp0_proxy);
 	kfree(dev->caps.qp1_tunnel);
 	kfree(dev->caps.qp1_proxy);
-	dev->caps.qp0_tunnel = dev->caps.qp0_proxy =
-		dev->caps.qp1_tunnel = dev->caps.qp1_proxy = NULL;
+	dev->caps.qp0_qkey = NULL;
+	dev->caps.qp0_tunnel = NULL;
+	dev->caps.qp0_proxy = NULL;
+	dev->caps.qp1_tunnel = NULL;
+	dev->caps.qp1_proxy = NULL;
 
 	return err;
 }
@@ -784,8 +779,8 @@ int mlx4_change_port_types(struct mlx4_dev *dev,
 			dev->caps.port_type[port] = port_types[port - 1];
 			err = mlx4_SET_PORT(dev, port, -1);
 			if (err) {
-				mlx4_err(dev, "Failed to set port %d, "
-					      "aborting\n", port);
+				mlx4_err(dev, "Failed to set port %d, aborting\n",
+					 port);
 				goto out;
 			}
 		}
@@ -868,9 +863,7 @@ static ssize_t set_port_type(struct device *dev,
 		}
 	}
 	if (err) {
-		mlx4_err(mdev, "Auto sensing is not supported on this HCA. "
-			       "Set only 'eth' or 'ib' for both ports "
-			       "(should be the same)\n");
+		mlx4_err(mdev, "Auto sensing is not supported on this HCA. Set only 'eth' or 'ib' for both ports (should be the same)\n");
 		goto out;
 	}
 
@@ -975,8 +968,8 @@ static ssize_t set_port_ib_mtu(struct device *dev,
 		mlx4_CLOSE_PORT(mdev, port);
 		err = mlx4_SET_PORT(mdev, port, -1);
 		if (err) {
-			mlx4_err(mdev, "Failed to set port %d, "
-				      "aborting\n", port);
+			mlx4_err(mdev, "Failed to set port %d, aborting\n",
+				 port);
 			goto err_set_port;
 		}
 	}
@@ -995,19 +988,19 @@ static int mlx4_load_fw(struct mlx4_dev *dev)
 	priv->fw.fw_icm = mlx4_alloc_icm(dev, priv->fw.fw_pages,
 					 GFP_HIGHUSER | __GFP_NOWARN, 0);
 	if (!priv->fw.fw_icm) {
-		mlx4_err(dev, "Couldn't allocate FW area, aborting.\n");
+		mlx4_err(dev, "Couldn't allocate FW area, aborting\n");
 		return -ENOMEM;
 	}
 
 	err = mlx4_MAP_FA(dev, priv->fw.fw_icm);
 	if (err) {
-		mlx4_err(dev, "MAP_FA command failed, aborting.\n");
+		mlx4_err(dev, "MAP_FA command failed, aborting\n");
 		goto err_free;
 	}
 
 	err = mlx4_RUN_FW(dev);
 	if (err) {
-		mlx4_err(dev, "RUN_FW command failed, aborting.\n");
+		mlx4_err(dev, "RUN_FW command failed, aborting\n");
 		goto err_unmap_fa;
 	}
 
@@ -1091,30 +1084,30 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 
 	err = mlx4_SET_ICM_SIZE(dev, icm_size, &aux_pages);
 	if (err) {
-		mlx4_err(dev, "SET_ICM_SIZE command failed, aborting.\n");
+		mlx4_err(dev, "SET_ICM_SIZE command failed, aborting\n");
 		return err;
 	}
 
-	mlx4_dbg(dev, "%lld KB of HCA context requires %lld KB aux memory.\n",
+	mlx4_dbg(dev, "%lld KB of HCA context requires %lld KB aux memory\n",
 		 (unsigned long long) icm_size >> 10,
 		 (unsigned long long) aux_pages << 2);
 
 	priv->fw.aux_icm = mlx4_alloc_icm(dev, aux_pages,
 					  GFP_HIGHUSER | __GFP_NOWARN, 0);
 	if (!priv->fw.aux_icm) {
-		mlx4_err(dev, "Couldn't allocate aux memory, aborting.\n");
+		mlx4_err(dev, "Couldn't allocate aux memory, aborting\n");
 		return -ENOMEM;
 	}
 
 	err = mlx4_MAP_ICM_AUX(dev, priv->fw.aux_icm);
 	if (err) {
-		mlx4_err(dev, "MAP_ICM_AUX command failed, aborting.\n");
+		mlx4_err(dev, "MAP_ICM_AUX command failed, aborting\n");
 		goto err_free_aux;
 	}
 
 	err = mlx4_init_cmpt_table(dev, init_hca->cmpt_base, dev_cap->cmpt_entry_sz);
 	if (err) {
-		mlx4_err(dev, "Failed to map cMPT context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map cMPT context memory, aborting\n");
 		goto err_unmap_aux;
 	}
 
@@ -1125,7 +1118,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  init_hca->eqc_base, dev_cap->eqc_entry_sz,
 				  num_eqs, num_eqs, 0, 0);
 	if (err) {
-		mlx4_err(dev, "Failed to map EQ context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map EQ context memory, aborting\n");
 		goto err_unmap_cmpt;
 	}
 
@@ -1146,7 +1139,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  dev->caps.num_mtts,
 				  dev->caps.reserved_mtts, 1, 0);
 	if (err) {
-		mlx4_err(dev, "Failed to map MTT context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map MTT context memory, aborting\n");
 		goto err_unmap_eq;
 	}
 
@@ -1156,7 +1149,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  dev->caps.num_mpts,
 				  dev->caps.reserved_mrws, 1, 1);
 	if (err) {
-		mlx4_err(dev, "Failed to map dMPT context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map dMPT context memory, aborting\n");
 		goto err_unmap_mtt;
 	}
 
@@ -1167,7 +1160,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
 				  0, 0);
 	if (err) {
-		mlx4_err(dev, "Failed to map QP context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map QP context memory, aborting\n");
 		goto err_unmap_dmpt;
 	}
 
@@ -1178,7 +1171,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
 				  0, 0);
 	if (err) {
-		mlx4_err(dev, "Failed to map AUXC context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map AUXC context memory, aborting\n");
 		goto err_unmap_qp;
 	}
 
@@ -1189,7 +1182,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
 				  0, 0);
 	if (err) {
-		mlx4_err(dev, "Failed to map ALTC context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map ALTC context memory, aborting\n");
 		goto err_unmap_auxc;
 	}
 
@@ -1210,7 +1203,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  dev->caps.num_cqs,
 				  dev->caps.reserved_cqs, 0, 0);
 	if (err) {
-		mlx4_err(dev, "Failed to map CQ context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map CQ context memory, aborting\n");
 		goto err_unmap_rdmarc;
 	}
 
@@ -1220,7 +1213,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  dev->caps.num_srqs,
 				  dev->caps.reserved_srqs, 0, 0);
 	if (err) {
-		mlx4_err(dev, "Failed to map SRQ context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map SRQ context memory, aborting\n");
 		goto err_unmap_cq;
 	}
 
@@ -1238,7 +1231,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  dev->caps.num_mgms + dev->caps.num_amgms,
 				  0, 0);
 	if (err) {
-		mlx4_err(dev, "Failed to map MCG context memory, aborting.\n");
+		mlx4_err(dev, "Failed to map MCG context memory, aborting\n");
 		goto err_unmap_srq;
 	}
 
@@ -1315,7 +1308,7 @@ static void mlx4_slave_exit(struct mlx4_dev *dev)
 
 	mutex_lock(&priv->cmd.slave_cmd_mutex);
 	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, MLX4_COMM_TIME))
-		mlx4_warn(dev, "Failed to close slave function.\n");
+		mlx4_warn(dev, "Failed to close slave function\n");
 	mutex_unlock(&priv->cmd.slave_cmd_mutex);
 }
 
@@ -1413,7 +1406,7 @@ static int mlx4_init_slave(struct mlx4_dev *dev)
 	u32 cmd_channel_ver;
 
 	if (atomic_read(&pf_loading)) {
-		mlx4_warn(dev, "PF is not ready. Deferring probe\n");
+		mlx4_warn(dev, "PF is not ready - Deferring probe\n");
 		return -EPROBE_DEFER;
 	}
 
@@ -1426,8 +1419,7 @@ static int mlx4_init_slave(struct mlx4_dev *dev)
 	 * NUM_OF_RESET_RETRIES times before leaving.*/
 	if (ret_from_reset) {
 		if (MLX4_DELAY_RESET_SLAVE == ret_from_reset) {
-			mlx4_warn(dev, "slave is currently in the "
-				  "middle of FLR. Deferring probe.\n");
+			mlx4_warn(dev, "slave is currently in the middle of FLR - Deferring probe\n");
 			mutex_unlock(&priv->cmd.slave_cmd_mutex);
 			return -EPROBE_DEFER;
 		} else
@@ -1441,8 +1433,7 @@ static int mlx4_init_slave(struct mlx4_dev *dev)
 
 	if (MLX4_COMM_GET_IF_REV(cmd_channel_ver) !=
 		MLX4_COMM_GET_IF_REV(slave_read)) {
-		mlx4_err(dev, "slave driver version is not supported"
-			 " by the master\n");
+		mlx4_err(dev, "slave driver version is not supported by the master\n");
 		goto err;
 	}
 
@@ -1520,8 +1511,7 @@ static void choose_steering_mode(struct mlx4_dev *dev,
 
 			if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
 			    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
-				mlx4_warn(dev, "Must have both UC_STEER and MC_STEER flags "
-					  "set to use B0 steering. Falling back to A0 steering mode.\n");
+				mlx4_warn(dev, "Must have both UC_STEER and MC_STEER flags set to use B0 steering - falling back to A0 steering mode\n");
 		}
 		dev->oper_log_mgm_entry_size =
 			mlx4_log_num_mgm_entry_size > 0 ?
@@ -1529,8 +1519,7 @@ static void choose_steering_mode(struct mlx4_dev *dev,
 			MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
 		dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
 	}
-	mlx4_dbg(dev, "Steering mode is: %s, oper_log_mgm_entry_size = %d, "
-		 "modparam log_num_mgm_entry_size = %d\n",
+	mlx4_dbg(dev, "Steering mode is: %s, oper_log_mgm_entry_size = %d, modparam log_num_mgm_entry_size = %d\n",
 		 mlx4_steering_mode_str(dev->caps.steering_mode),
 		 dev->oper_log_mgm_entry_size,
 		 mlx4_log_num_mgm_entry_size);
@@ -1564,15 +1553,15 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 		err = mlx4_QUERY_FW(dev);
 		if (err) {
 			if (err == -EACCES)
-				mlx4_info(dev, "non-primary physical function, skipping.\n");
+				mlx4_info(dev, "non-primary physical function, skipping\n");
 			else
-				mlx4_err(dev, "QUERY_FW command failed, aborting.\n");
+				mlx4_err(dev, "QUERY_FW command failed, aborting\n");
 			return err;
 		}
 
 		err = mlx4_load_fw(dev);
 		if (err) {
-			mlx4_err(dev, "Failed to start FW, aborting.\n");
+			mlx4_err(dev, "Failed to start FW, aborting\n");
 			return err;
 		}
 
@@ -1584,7 +1573,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 
 		err = mlx4_dev_cap(dev, &dev_cap);
 		if (err) {
-			mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+			mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n");
 			goto err_stop_fw;
 		}
 
@@ -1625,7 +1614,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 
 		err = mlx4_INIT_HCA(dev, &init_hca);
 		if (err) {
-			mlx4_err(dev, "INIT_HCA command failed, aborting.\n");
+			mlx4_err(dev, "INIT_HCA command failed, aborting\n");
 			goto err_free_icm;
 		}
 		/*
@@ -1636,7 +1625,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 			memset(&init_hca, 0, sizeof(init_hca));
 			err = mlx4_QUERY_HCA(dev, &init_hca);
 			if (err) {
-				mlx4_err(dev, "QUERY_HCA command failed, disable timestamp.\n");
+				mlx4_err(dev, "QUERY_HCA command failed, disable timestamp\n");
 				dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS;
 			} else {
 				dev->caps.hca_core_clock =
@@ -1649,14 +1638,14 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 			if (!dev->caps.hca_core_clock) {
 				dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS;
 				mlx4_err(dev,
-					 "HCA frequency is 0. Timestamping is not supported.");
+					 "HCA frequency is 0 - timestamping is not supported\n");
 			} else if (map_internal_clock(dev)) {
 				/*
 				 * Map internal clock,
 				 * in case of failure disable timestamping
 				 */
 				dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS;
-				mlx4_err(dev, "Failed to map internal clock. Timestamping is not supported.\n");
+				mlx4_err(dev, "Failed to map internal clock. Timestamping is not supported\n");
 			}
 		}
 	} else {
@@ -1683,7 +1672,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 
 	err = mlx4_QUERY_ADAPTER(dev, &adapter);
 	if (err) {
-		mlx4_err(dev, "QUERY_ADAPTER command failed, aborting.\n");
+		mlx4_err(dev, "QUERY_ADAPTER command failed, aborting\n");
 		goto unmap_bf;
 	}
 
@@ -1696,6 +1685,14 @@ unmap_bf:
 	unmap_internal_clock(dev);
 	unmap_bf_area(dev);
 
+	if (mlx4_is_slave(dev)) {
+		kfree(dev->caps.qp0_qkey);
+		kfree(dev->caps.qp0_tunnel);
+		kfree(dev->caps.qp0_proxy);
+		kfree(dev->caps.qp1_tunnel);
+		kfree(dev->caps.qp1_proxy);
+	}
+
 err_close:
 	if (mlx4_is_slave(dev))
 		mlx4_slave_exit(dev);
@@ -1793,79 +1790,69 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 
 	err = mlx4_init_uar_table(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to initialize "
-			 "user access region table, aborting.\n");
-		return err;
+		mlx4_err(dev, "Failed to initialize user access region table, aborting\n");
+		 return err;
 	}
 
 	err = mlx4_uar_alloc(dev, &priv->driver_uar);
 	if (err) {
-		mlx4_err(dev, "Failed to allocate driver access region, "
-			 "aborting.\n");
+		mlx4_err(dev, "Failed to allocate driver access region, aborting\n");
 		goto err_uar_table_free;
 	}
 
 	priv->kar = ioremap((phys_addr_t) priv->driver_uar.pfn << PAGE_SHIFT, PAGE_SIZE);
 	if (!priv->kar) {
-		mlx4_err(dev, "Couldn't map kernel access region, "
-			 "aborting.\n");
+		mlx4_err(dev, "Couldn't map kernel access region, aborting\n");
 		err = -ENOMEM;
 		goto err_uar_free;
 	}
 
 	err = mlx4_init_pd_table(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to initialize "
-			 "protection domain table, aborting.\n");
+		mlx4_err(dev, "Failed to initialize protection domain table, aborting\n");
 		goto err_kar_unmap;
 	}
 
 	err = mlx4_init_xrcd_table(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to initialize "
-			 "reliable connection domain table, aborting.\n");
+		mlx4_err(dev, "Failed to initialize reliable connection domain table, aborting\n");
 		goto err_pd_table_free;
 	}
 
 	err = mlx4_init_mr_table(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to initialize "
-			 "memory region table, aborting.\n");
+		mlx4_err(dev, "Failed to initialize memory region table, aborting\n");
 		goto err_xrcd_table_free;
 	}
 
 	if (!mlx4_is_slave(dev)) {
 		err = mlx4_init_mcg_table(dev);
 		if (err) {
-			mlx4_err(dev, "Failed to initialize multicast group table, aborting.\n");
+			mlx4_err(dev, "Failed to initialize multicast group table, aborting\n");
 			goto err_mr_table_free;
 		}
 	}
 
 	err = mlx4_init_eq_table(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to initialize "
-			 "event queue table, aborting.\n");
+		mlx4_err(dev, "Failed to initialize event queue table, aborting\n");
 		goto err_mcg_table_free;
 	}
 
 	err = mlx4_cmd_use_events(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to switch to event-driven "
-			 "firmware commands, aborting.\n");
+		mlx4_err(dev, "Failed to switch to event-driven firmware commands, aborting\n");
 		goto err_eq_table_free;
 	}
 
 	err = mlx4_NOP(dev);
 	if (err) {
 		if (dev->flags & MLX4_FLAG_MSI_X) {
-			mlx4_warn(dev, "NOP command failed to generate MSI-X "
-				  "interrupt IRQ %d).\n",
+			mlx4_warn(dev, "NOP command failed to generate MSI-X interrupt IRQ %d)\n",
 				  priv->eq_table.eq[dev->caps.num_comp_vectors].irq);
-			mlx4_warn(dev, "Trying again without MSI-X.\n");
+			mlx4_warn(dev, "Trying again without MSI-X\n");
 		} else {
-			mlx4_err(dev, "NOP command failed to generate interrupt "
-				 "(IRQ %d), aborting.\n",
+			mlx4_err(dev, "NOP command failed to generate interrupt (IRQ %d), aborting\n",
 				 priv->eq_table.eq[dev->caps.num_comp_vectors].irq);
 			mlx4_err(dev, "BIOS or ACPI interrupt routing problem?\n");
 		}
@@ -1877,28 +1864,25 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 
 	err = mlx4_init_cq_table(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to initialize "
-			 "completion queue table, aborting.\n");
+		mlx4_err(dev, "Failed to initialize completion queue table, aborting\n");
 		goto err_cmd_poll;
 	}
 
 	err = mlx4_init_srq_table(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to initialize "
-			 "shared receive queue table, aborting.\n");
+		mlx4_err(dev, "Failed to initialize shared receive queue table, aborting\n");
 		goto err_cq_table_free;
 	}
 
 	err = mlx4_init_qp_table(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to initialize "
-			 "queue pair table, aborting.\n");
+		mlx4_err(dev, "Failed to initialize queue pair table, aborting\n");
 		goto err_srq_table_free;
 	}
 
 	err = mlx4_init_counters_table(dev);
 	if (err && err != -ENOENT) {
-		mlx4_err(dev, "Failed to initialize counters table, aborting.\n");
+		mlx4_err(dev, "Failed to initialize counters table, aborting\n");
 		goto err_qp_table_free;
 	}
 
@@ -1908,9 +1892,8 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 			err = mlx4_get_port_ib_caps(dev, port,
 						    &ib_port_default_caps);
 			if (err)
-				mlx4_warn(dev, "failed to get port %d default "
-					  "ib capabilities (%d). Continuing "
-					  "with caps = 0\n", port, err);
+				mlx4_warn(dev, "failed to get port %d default ib capabilities (%d). Continuing with caps = 0\n",
+					  port, err);
 			dev->caps.ib_port_def_cap[port] = ib_port_default_caps;
 
 			/* initialize per-slave default ib port capabilities */
@@ -1920,7 +1903,7 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 					if (i == mlx4_master_func_num(dev))
 						continue;
 					priv->mfunc.master.slave_state[i].ib_cap_mask[port] =
-							ib_port_default_caps;
+						ib_port_default_caps;
 				}
 			}
 
@@ -1933,7 +1916,7 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 					    dev->caps.pkey_table_len[port] : -1);
 			if (err) {
 				mlx4_err(dev, "Failed to set port %d, aborting\n",
-					port);
+					 port);
 				goto err_counters_table_free;
 			}
 		}
@@ -2009,7 +1992,7 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 			kfree(entries);
 			goto no_msi;
 		} else if (nreq < MSIX_LEGACY_SZ +
-				  dev->caps.num_ports * MIN_MSIX_P_PORT) {
+			   dev->caps.num_ports * MIN_MSIX_P_PORT) {
 			/*Working in legacy mode , all EQ's shared*/
 			dev->caps.comp_pool           = 0;
 			dev->caps.num_comp_vectors = nreq - 1;
@@ -2210,8 +2193,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 
 	err = pci_enable_device(pdev);
 	if (err) {
-		dev_err(&pdev->dev, "Cannot enable PCI device, "
-			"aborting.\n");
+		dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n");
 		return err;
 	}
 
@@ -2258,14 +2240,13 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 	 */
 	if (!(pci_dev_data & MLX4_PCI_DEV_IS_VF) &&
 	    !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
-		dev_err(&pdev->dev, "Missing DCS, aborting."
-			"(driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n",
+		dev_err(&pdev->dev, "Missing DCS, aborting (driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n",
 			pci_dev_data, pci_resource_flags(pdev, 0));
 		err = -ENODEV;
 		goto err_disable_pdev;
 	}
 	if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) {
-		dev_err(&pdev->dev, "Missing UAR, aborting.\n");
+		dev_err(&pdev->dev, "Missing UAR, aborting\n");
 		err = -ENODEV;
 		goto err_disable_pdev;
 	}
@@ -2280,21 +2261,19 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 
 	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
 	if (err) {
-		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask.\n");
+		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n");
 		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
 		if (err) {
-			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting.\n");
+			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n");
 			goto err_release_regions;
 		}
 	}
 	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
 	if (err) {
-		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit "
-			 "consistent PCI DMA mask.\n");
+		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit consistent PCI DMA mask\n");
 		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
 		if (err) {
-			dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, "
-				"aborting.\n");
+			dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, aborting\n");
 			goto err_release_regions;
 		}
 	}
@@ -2325,7 +2304,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 		if (total_vfs) {
 			unsigned vfs_offset = 0;
 			for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) &&
-			     vfs_offset + nvfs[i] < extended_func_num(pdev);
+				     vfs_offset + nvfs[i] < extended_func_num(pdev);
 			     vfs_offset += nvfs[i], i++)
 				;
 			if (i == sizeof(nvfs)/sizeof(nvfs[0])) {
@@ -2351,8 +2330,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 			if (err < 0)
 				goto err_free_dev;
 			else {
-				mlx4_warn(dev, "Multiple PFs not yet supported."
-					  " Skipping PF.\n");
+				mlx4_warn(dev, "Multiple PFs not yet supported - Skipping PF\n");
 				err = -EINVAL;
 				goto err_free_dev;
 			}
@@ -2362,8 +2340,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 			mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n",
 				  total_vfs);
 			dev->dev_vfs = kzalloc(
-					total_vfs * sizeof(*dev->dev_vfs),
-					GFP_KERNEL);
+				total_vfs * sizeof(*dev->dev_vfs),
+				GFP_KERNEL);
 			if (NULL == dev->dev_vfs) {
 				mlx4_err(dev, "Failed to allocate memory for VFs\n");
 				err = 0;
@@ -2371,14 +2349,14 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 				atomic_inc(&pf_loading);
 				err = pci_enable_sriov(pdev, total_vfs);
 				if (err) {
-					mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n",
+					mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d)\n",
 						 err);
 					atomic_dec(&pf_loading);
 					err = 0;
 				} else {
 					mlx4_warn(dev, "Running in master mode\n");
 					dev->flags |= MLX4_FLAG_SRIOV |
-						      MLX4_FLAG_MASTER;
+						MLX4_FLAG_MASTER;
 					dev->num_vfs = total_vfs;
 					sriov_initialized = 1;
 				}
@@ -2395,7 +2373,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 		 */
 		err = mlx4_reset(dev);
 		if (err) {
-			mlx4_err(dev, "Failed to reset HCA, aborting.\n");
+			mlx4_err(dev, "Failed to reset HCA, aborting\n");
 			goto err_rel_own;
 		}
 	}
@@ -2403,7 +2381,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 slave_start:
 	err = mlx4_cmd_init(dev);
 	if (err) {
-		mlx4_err(dev, "Failed to init command interface, aborting.\n");
+		mlx4_err(dev, "Failed to init command interface, aborting\n");
 		goto err_sriov;
 	}
 
@@ -2417,8 +2395,7 @@ slave_start:
 			dev->num_slaves = 0;
 			err = mlx4_multi_func_init(dev);
 			if (err) {
-				mlx4_err(dev, "Failed to init slave mfunc"
-					 " interface, aborting.\n");
+				mlx4_err(dev, "Failed to init slave mfunc interface, aborting\n");
 				goto err_cmd;
 			}
 		}
@@ -2450,8 +2427,7 @@ slave_start:
 		unsigned sum = 0;
 		err = mlx4_multi_func_init(dev);
 		if (err) {
-			mlx4_err(dev, "Failed to init master mfunc"
-				 "interface, aborting.\n");
+			mlx4_err(dev, "Failed to init master mfunc interface, aborting\n");
 			goto err_close;
 		}
 		if (sriov_initialized) {
@@ -2462,11 +2438,9 @@ slave_start:
 			if (ib_ports &&
 			    (num_vfs_argc > 1 || probe_vfs_argc > 1)) {
 				mlx4_err(dev,
-					 "Invalid syntax of num_vfs/probe_vfs "
-					 "with IB port. Single port VFs syntax"
-					 " is only supported when all ports "
-					 "are configured as ethernet\n");
-				goto err_close;
+					 "Invalid syntax of num_vfs/probe_vfs with IB port - single port VFs syntax is only supported when all ports are configured as ethernet\n");
+				err = -EINVAL;
+				goto err_master_mfunc;
 			}
 			for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]); i++) {
 				unsigned j;
@@ -2491,8 +2465,7 @@ slave_start:
 	if ((mlx4_is_mfunc(dev)) &&
 	    !(dev->flags & MLX4_FLAG_MSI_X)) {
 		err = -ENOSYS;
-		mlx4_err(dev, "INTx is not supported in multi-function mode."
-			 " aborting.\n");
+		mlx4_err(dev, "INTx is not supported in multi-function mode, aborting\n");
 		goto err_free_eq;
 	}
 
@@ -2566,6 +2539,14 @@ err_master_mfunc:
 	if (mlx4_is_master(dev))
 		mlx4_multi_func_cleanup(dev);
 
+	if (mlx4_is_slave(dev)) {
+		kfree(dev->caps.qp0_qkey);
+		kfree(dev->caps.qp0_tunnel);
+		kfree(dev->caps.qp0_proxy);
+		kfree(dev->caps.qp1_tunnel);
+		kfree(dev->caps.qp1_proxy);
+	}
+
 err_close:
 	if (dev->flags & MLX4_FLAG_MSI_X)
 		pci_disable_msix(pdev);
@@ -2637,7 +2618,7 @@ static void __mlx4_remove_one(struct pci_dev *pdev)
 	/* in SRIOV it is not allowed to unload the pf's
 	 * driver while there are alive vf's */
 	if (mlx4_is_master(dev) && mlx4_how_many_lives_vf(dev))
-		printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
+		pr_warn("Removing PF when there are assigned VF's !!!\n");
 	mlx4_stop_sense(dev);
 	mlx4_unregister_device(dev);
 
@@ -2689,6 +2670,7 @@ static void __mlx4_remove_one(struct pci_dev *pdev)
 	if (!mlx4_is_slave(dev))
 		mlx4_free_ownership(dev);
 
+	kfree(dev->caps.qp0_qkey);
 	kfree(dev->caps.qp0_tunnel);
 	kfree(dev->caps.qp0_proxy);
 	kfree(dev->caps.qp1_tunnel);
@@ -2800,7 +2782,7 @@ static struct pci_driver mlx4_driver = {
 	.name		= DRV_NAME,
 	.id_table	= mlx4_pci_table,
 	.probe		= mlx4_init_one,
-	.shutdown	= mlx4_remove_one,
+	.shutdown	= __mlx4_remove_one,
 	.remove		= mlx4_remove_one,
 	.err_handler    = &mlx4_err_handler,
 };
@@ -2808,33 +2790,36 @@ static struct pci_driver mlx4_driver = {
 static int __init mlx4_verify_params(void)
 {
 	if ((log_num_mac < 0) || (log_num_mac > 7)) {
-		pr_warning("mlx4_core: bad num_mac: %d\n", log_num_mac);
+		pr_warn("mlx4_core: bad num_mac: %d\n", log_num_mac);
 		return -1;
 	}
 
 	if (log_num_vlan != 0)
-		pr_warning("mlx4_core: log_num_vlan - obsolete module param, using %d\n",
-			   MLX4_LOG_NUM_VLANS);
+		pr_warn("mlx4_core: log_num_vlan - obsolete module param, using %d\n",
+			MLX4_LOG_NUM_VLANS);
+
+	if (use_prio != 0)
+		pr_warn("mlx4_core: use_prio - obsolete module param, ignored\n");
 
 	if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) {
-		pr_warning("mlx4_core: bad log_mtts_per_seg: %d\n", log_mtts_per_seg);
+		pr_warn("mlx4_core: bad log_mtts_per_seg: %d\n",
+			log_mtts_per_seg);
 		return -1;
 	}
 
 	/* Check if module param for ports type has legal combination */
 	if (port_type_array[0] == false && port_type_array[1] == true) {
-		printk(KERN_WARNING "Module parameter configuration ETH/IB is not supported. Switching to default configuration IB/IB\n");
+		pr_warn("Module parameter configuration ETH/IB is not supported. Switching to default configuration IB/IB\n");
 		port_type_array[0] = true;
 	}
 
 	if (mlx4_log_num_mgm_entry_size != -1 &&
 	    (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
 	     mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE)) {
-		pr_warning("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not "
-			   "in legal range (-1 or %d..%d)\n",
-			   mlx4_log_num_mgm_entry_size,
-			   MLX4_MIN_MGM_LOG_ENTRY_SIZE,
-			   MLX4_MAX_MGM_LOG_ENTRY_SIZE);
+		pr_warn("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not in legal range (-1 or %d..%d)\n",
+			mlx4_log_num_mgm_entry_size,
+			MLX4_MIN_MGM_LOG_ENTRY_SIZE,
+			MLX4_MAX_MGM_LOG_ENTRY_SIZE);
 		return -1;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 80ccb4edf82..4c36def8e10 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -638,7 +638,7 @@ static int find_entry(struct mlx4_dev *dev, u8 port,
 
 		if (!(be32_to_cpu(mgm->members_count) & 0xffffff)) {
 			if (*index != hash) {
-				mlx4_err(dev, "Found zero MGID in AMGM.\n");
+				mlx4_err(dev, "Found zero MGID in AMGM\n");
 				err = -EINVAL;
 			}
 			return err;
@@ -874,7 +874,7 @@ static void mlx4_err_rule(struct mlx4_dev *dev, char *str,
 	mlx4_err(dev, "%s", buf);
 
 	if (len >= BUF_SIZE)
-		mlx4_err(dev, "Network rule error message was truncated, print buffer is too small.\n");
+		mlx4_err(dev, "Network rule error message was truncated, print buffer is too small\n");
 }
 
 int mlx4_flow_attach(struct mlx4_dev *dev,
@@ -897,7 +897,7 @@ int mlx4_flow_attach(struct mlx4_dev *dev,
 		ret = parse_trans_rule(dev, cur, mailbox->buf + size);
 		if (ret < 0) {
 			mlx4_free_cmd_mailbox(dev, mailbox);
-			return -EINVAL;
+			return ret;
 		}
 		size += ret;
 	}
@@ -905,10 +905,10 @@ int mlx4_flow_attach(struct mlx4_dev *dev,
 	ret = mlx4_QP_FLOW_STEERING_ATTACH(dev, mailbox, size >> 2, reg_id);
 	if (ret == -ENOMEM)
 		mlx4_err_rule(dev,
-			      "mcg table is full. Fail to register network rule.\n",
+			      "mcg table is full. Fail to register network rule\n",
 			      rule);
 	else if (ret)
-		mlx4_err_rule(dev, "Fail to register network rule.\n", rule);
+		mlx4_err_rule(dev, "Fail to register network rule\n", rule);
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 
@@ -994,7 +994,7 @@ int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 
 	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
 	if (members_count == dev->caps.num_qp_per_mgm) {
-		mlx4_err(dev, "MGM at index %x is full.\n", index);
+		mlx4_err(dev, "MGM at index %x is full\n", index);
 		err = -ENOMEM;
 		goto out;
 	}
@@ -1042,7 +1042,7 @@ out:
 	}
 	if (err && link && index != -1) {
 		if (index < dev->caps.num_mgms)
-			mlx4_warn(dev, "Got AMGM index %d < %d",
+			mlx4_warn(dev, "Got AMGM index %d < %d\n",
 				  index, dev->caps.num_mgms);
 		else
 			mlx4_bitmap_free(&priv->mcg_table.bitmap,
@@ -1133,7 +1133,7 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 
 		if (amgm_index) {
 			if (amgm_index < dev->caps.num_mgms)
-				mlx4_warn(dev, "MGM entry %d had AMGM index %d < %d",
+				mlx4_warn(dev, "MGM entry %d had AMGM index %d < %d\n",
 					  index, amgm_index, dev->caps.num_mgms);
 			else
 				mlx4_bitmap_free(&priv->mcg_table.bitmap,
@@ -1153,7 +1153,7 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			goto out;
 
 		if (index < dev->caps.num_mgms)
-			mlx4_warn(dev, "entry %d had next AMGM index %d < %d",
+			mlx4_warn(dev, "entry %d had next AMGM index %d < %d\n",
 				  prev, index, dev->caps.num_mgms);
 		else
 			mlx4_bitmap_free(&priv->mcg_table.bitmap,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 8e9eb02e09c..1d8af733680 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -133,6 +133,11 @@ enum {
 	MLX4_COMM_CMD_FLR = 254
 };
 
+enum {
+	MLX4_VF_SMI_DISABLED,
+	MLX4_VF_SMI_ENABLED
+};
+
 /*The flag indicates that the slave should delay the RESET cmd*/
 #define MLX4_DELAY_RESET_SLAVE 0xbbbbbbb
 /*indicates how many retries will be done if we are in the middle of FLR*/
@@ -216,18 +221,19 @@ extern int mlx4_debug_level;
 #define mlx4_debug_level	(0)
 #endif /* CONFIG_MLX4_DEBUG */
 
-#define mlx4_dbg(mdev, format, arg...)					\
+#define mlx4_dbg(mdev, format, ...)					\
 do {									\
 	if (mlx4_debug_level)						\
-		dev_printk(KERN_DEBUG, &mdev->pdev->dev, format, ##arg); \
+		dev_printk(KERN_DEBUG, &(mdev)->pdev->dev, format,	\
+			   ##__VA_ARGS__);				\
 } while (0)
 
-#define mlx4_err(mdev, format, arg...) \
-	dev_err(&mdev->pdev->dev, format, ##arg)
-#define mlx4_info(mdev, format, arg...) \
-	dev_info(&mdev->pdev->dev, format, ##arg)
-#define mlx4_warn(mdev, format, arg...) \
-	dev_warn(&mdev->pdev->dev, format, ##arg)
+#define mlx4_err(mdev, format, ...)					\
+	dev_err(&(mdev)->pdev->dev, format, ##__VA_ARGS__)
+#define mlx4_info(mdev, format, ...)					\
+	dev_info(&(mdev)->pdev->dev, format, ##__VA_ARGS__)
+#define mlx4_warn(mdev, format, ...)					\
+	dev_warn(&(mdev)->pdev->dev, format, ##__VA_ARGS__)
 
 extern int mlx4_log_num_mgm_entry_size;
 extern int log_mtts_per_seg;
@@ -488,6 +494,7 @@ struct mlx4_vport_state {
 
 struct mlx4_vf_admin_state {
 	struct mlx4_vport_state vport[MLX4_MAX_PORTS + 1];
+	u8 enable_smi[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_vport_oper_state {
@@ -495,8 +502,10 @@ struct mlx4_vport_oper_state {
 	int mac_idx;
 	int vlan_idx;
 };
+
 struct mlx4_vf_oper_state {
 	struct mlx4_vport_oper_state vport[MLX4_MAX_PORTS + 1];
+	u8 smi_enabled[MLX4_MAX_PORTS + 1];
 };
 
 struct slave_list {
@@ -895,7 +904,7 @@ void mlx4_cleanup_cq_table(struct mlx4_dev *dev);
 void mlx4_cleanup_qp_table(struct mlx4_dev *dev);
 void mlx4_cleanup_srq_table(struct mlx4_dev *dev);
 void mlx4_cleanup_mcg_table(struct mlx4_dev *dev);
-int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn);
+int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp);
 void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn);
 int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn);
 void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn);
@@ -903,7 +912,7 @@ int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn);
 void __mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn);
 int __mlx4_mpt_reserve(struct mlx4_dev *dev);
 void __mlx4_mpt_release(struct mlx4_dev *dev, u32 index);
-int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index);
+int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp);
 void __mlx4_mpt_free_icm(struct mlx4_dev *dev, u32 index);
 u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order);
 void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 first_seg, int order);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 04d9b6fe3e8..d72a5a894fc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -126,6 +126,8 @@ enum {
 #define MAX_TX_RINGS			(MLX4_EN_MAX_TX_RING_P_UP * \
 					 MLX4_EN_NUM_UP)
 
+#define MLX4_EN_DEFAULT_TX_WORK		256
+
 /* Target number of packets to coalesce with interrupt moderation */
 #define MLX4_EN_RX_COAL_TARGET	44
 #define MLX4_EN_RX_COAL_TIME	0x10
@@ -313,6 +315,7 @@ struct mlx4_en_rx_ring {
 	unsigned long csum_ok;
 	unsigned long csum_none;
 	int hwtstamp_rx_filter;
+	cpumask_var_t affinity_mask;
 };
 
 struct mlx4_en_cq {
@@ -342,6 +345,7 @@ struct mlx4_en_cq {
 #define CQ_USER_PEND (MLX4_EN_CQ_STATE_POLL | MLX4_EN_CQ_STATE_POLL_YIELD)
 	spinlock_t poll_lock; /* protects from LLS/napi conflicts */
 #endif  /* CONFIG_NET_RX_BUSY_POLL */
+	struct irq_desc *irq_desc;
 };
 
 struct mlx4_en_port_profile {
@@ -541,6 +545,7 @@ struct mlx4_en_priv {
 	__be32 ctrl_flags;
 	u32 flags;
 	u8 num_tx_rings_p_up;
+	u32 tx_work_limit;
 	u32 tx_ring_num;
 	u32 rx_ring_num;
 	u32 rx_skb_size;
@@ -830,26 +835,26 @@ __printf(3, 4)
 int en_print(const char *level, const struct mlx4_en_priv *priv,
 	     const char *format, ...);
 
-#define en_dbg(mlevel, priv, format, arg...)			\
-do {								\
-	if (NETIF_MSG_##mlevel & priv->msg_enable)		\
-		en_print(KERN_DEBUG, priv, format, ##arg);	\
+#define en_dbg(mlevel, priv, format, ...)				\
+do {									\
+	if (NETIF_MSG_##mlevel & (priv)->msg_enable)			\
+		en_print(KERN_DEBUG, priv, format, ##__VA_ARGS__);	\
 } while (0)
-#define en_warn(priv, format, arg...)			\
-	en_print(KERN_WARNING, priv, format, ##arg)
-#define en_err(priv, format, arg...)			\
-	en_print(KERN_ERR, priv, format, ##arg)
-#define en_info(priv, format, arg...)			\
-	en_print(KERN_INFO, priv, format, ## arg)
-
-#define mlx4_err(mdev, format, arg...)			\
-	pr_err("%s %s: " format, DRV_NAME,		\
-	       dev_name(&mdev->pdev->dev), ##arg)
-#define mlx4_info(mdev, format, arg...)			\
-	pr_info("%s %s: " format, DRV_NAME,		\
-		dev_name(&mdev->pdev->dev), ##arg)
-#define mlx4_warn(mdev, format, arg...)			\
-	pr_warning("%s %s: " format, DRV_NAME,		\
-		   dev_name(&mdev->pdev->dev), ##arg)
+#define en_warn(priv, format, ...)					\
+	en_print(KERN_WARNING, priv, format, ##__VA_ARGS__)
+#define en_err(priv, format, ...)					\
+	en_print(KERN_ERR, priv, format, ##__VA_ARGS__)
+#define en_info(priv, format, ...)					\
+	en_print(KERN_INFO, priv, format, ##__VA_ARGS__)
+
+#define mlx4_err(mdev, format, ...)					\
+	pr_err(DRV_NAME " %s: " format,					\
+	       dev_name(&(mdev)->pdev->dev), ##__VA_ARGS__)
+#define mlx4_info(mdev, format, ...)					\
+	pr_info(DRV_NAME " %s: " format,				\
+		dev_name(&(mdev)->pdev->dev), ##__VA_ARGS__)
+#define mlx4_warn(mdev, format, ...)					\
+	pr_warn(DRV_NAME " %s: " format,				\
+		dev_name(&(mdev)->pdev->dev), ##__VA_ARGS__)
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index 24835853b75..2839abb878a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -250,8 +250,8 @@ static void mlx4_free_mtt_range(struct mlx4_dev *dev, u32 offset, int order)
 						       MLX4_CMD_TIME_CLASS_A,
 						       MLX4_CMD_WRAPPED);
 		if (err)
-			mlx4_warn(dev, "Failed to free mtt range at:"
-				  "%d order:%d\n", offset, order);
+			mlx4_warn(dev, "Failed to free mtt range at:%d order:%d\n",
+				  offset, order);
 		return;
 	}
 	 __mlx4_free_mtt_range(dev, offset, order);
@@ -364,14 +364,14 @@ static void mlx4_mpt_release(struct mlx4_dev *dev, u32 index)
 	__mlx4_mpt_release(dev, index);
 }
 
-int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index)
+int __mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp)
 {
 	struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
 
-	return mlx4_table_get(dev, &mr_table->dmpt_table, index);
+	return mlx4_table_get(dev, &mr_table->dmpt_table, index, gfp);
 }
 
-static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index)
+static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index, gfp_t gfp)
 {
 	u64 param = 0;
 
@@ -382,7 +382,7 @@ static int mlx4_mpt_alloc_icm(struct mlx4_dev *dev, u32 index)
 							MLX4_CMD_TIME_CLASS_A,
 							MLX4_CMD_WRAPPED);
 	}
-	return __mlx4_mpt_alloc_icm(dev, index);
+	return __mlx4_mpt_alloc_icm(dev, index, gfp);
 }
 
 void __mlx4_mpt_free_icm(struct mlx4_dev *dev, u32 index)
@@ -436,8 +436,8 @@ static int mlx4_mr_free_reserved(struct mlx4_dev *dev, struct mlx4_mr *mr)
 				     key_to_hw_index(mr->key) &
 				     (dev->caps.num_mpts - 1));
 		if (err) {
-			mlx4_warn(dev, "HW2SW_MPT failed (%d),", err);
-			mlx4_warn(dev, "MR has MWs bound to it.\n");
+			mlx4_warn(dev, "HW2SW_MPT failed (%d), MR has MWs bound to it\n",
+				  err);
 			return err;
 		}
 
@@ -469,7 +469,7 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
 	struct mlx4_mpt_entry *mpt_entry;
 	int err;
 
-	err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mr->key));
+	err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mr->key), GFP_KERNEL);
 	if (err)
 		return err;
 
@@ -627,13 +627,14 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 EXPORT_SYMBOL_GPL(mlx4_write_mtt);
 
 int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
-		       struct mlx4_buf *buf)
+		       struct mlx4_buf *buf, gfp_t gfp)
 {
 	u64 *page_list;
 	int err;
 	int i;
 
-	page_list = kmalloc(buf->npages * sizeof *page_list, GFP_KERNEL);
+	page_list = kmalloc(buf->npages * sizeof *page_list,
+			    gfp);
 	if (!page_list)
 		return -ENOMEM;
 
@@ -680,7 +681,7 @@ int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw)
 	struct mlx4_mpt_entry *mpt_entry;
 	int err;
 
-	err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mw->key));
+	err = mlx4_mpt_alloc_icm(dev, key_to_hw_index(mw->key), GFP_KERNEL);
 	if (err)
 		return err;
 
@@ -773,7 +774,7 @@ int mlx4_init_mr_table(struct mlx4_dev *dev)
 			mlx4_alloc_mtt_range(dev,
 					     fls(dev->caps.reserved_mtts - 1));
 		if (priv->reserved_mtts < 0) {
-			mlx4_warn(dev, "MTT table of order %u is too small.\n",
+			mlx4_warn(dev, "MTT table of order %u is too small\n",
 				  mr_table->mtt_buddy.max_order);
 			err = -ENOMEM;
 			goto err_reserve_mtts;
@@ -954,8 +955,7 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox)) {
 		err = PTR_ERR(mailbox);
-		printk(KERN_WARNING "mlx4_ib: mlx4_alloc_cmd_mailbox"
-		       " failed (%d)\n", err);
+		pr_warn("mlx4_ib: mlx4_alloc_cmd_mailbox failed (%d)\n", err);
 		return;
 	}
 
@@ -964,8 +964,7 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 			     (dev->caps.num_mpts - 1));
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	if (err) {
-		printk(KERN_WARNING "mlx4_ib: mlx4_HW2SW_MPT failed (%d)\n",
-		       err);
+		pr_warn("mlx4_ib: mlx4_HW2SW_MPT failed (%d)\n", err);
 		return;
 	}
 	fmr->mr.enabled = MLX4_MPT_EN_SW;
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 5ec6f203c6e..7ab97174886 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -254,8 +254,8 @@ void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 	if (validate_index(dev, table, index))
 		goto out;
 	if (--table->refs[index]) {
-		mlx4_dbg(dev, "Have more references for index %d,"
-			 "no need to modify mac table\n", index);
+		mlx4_dbg(dev, "Have more references for index %d, no need to modify mac table\n",
+			 index);
 		goto out;
 	}
 
@@ -453,9 +453,8 @@ void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan)
 	}
 
 	if (--table->refs[index]) {
-		mlx4_dbg(dev, "Have %d more references for index %d,"
-			 "no need to modify vlan table\n", table->refs[index],
-			 index);
+		mlx4_dbg(dev, "Have %d more references for index %d, no need to modify vlan table\n",
+			 table->refs[index], index);
 		goto out;
 	}
 	table->entries[index] = 0;
@@ -796,8 +795,7 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 					if (!memcmp(gid_entry_mbox->raw, gid_entry_tbl->raw,
 						    sizeof(gid_entry_tbl->raw))) {
 						/* found duplicate */
-						mlx4_warn(dev, "requested gid entry for slave:%d "
-							  "is a duplicate of gid at index %d\n",
+						mlx4_warn(dev, "requested gid entry for slave:%d is a duplicate of gid at index %d\n",
 							  slave, i);
 						mutex_unlock(&(priv->port[port].gid_table.mutex));
 						return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index 8e0c3cc2a1e..14089d9e166 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -164,18 +164,17 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 		}
 
 		if (total_size > dev_cap->max_icm_sz) {
-			mlx4_err(dev, "Profile requires 0x%llx bytes; "
-				  "won't fit in 0x%llx bytes of context memory.\n",
-				  (unsigned long long) total_size,
-				  (unsigned long long) dev_cap->max_icm_sz);
+			mlx4_err(dev, "Profile requires 0x%llx bytes; won't fit in 0x%llx bytes of context memory\n",
+				 (unsigned long long) total_size,
+				 (unsigned long long) dev_cap->max_icm_sz);
 			kfree(profile);
 			return -ENOMEM;
 		}
 
 		if (profile[i].size)
-			mlx4_dbg(dev, "  profile[%2d] (%6s): 2^%02d entries @ 0x%10llx, "
-				  "size 0x%10llx\n",
-				 i, res_name[profile[i].type], profile[i].log_num,
+			mlx4_dbg(dev, "  profile[%2d] (%6s): 2^%02d entries @ 0x%10llx, size 0x%10llx\n",
+				 i, res_name[profile[i].type],
+				 profile[i].log_num,
 				 (unsigned long long) profile[i].start,
 				 (unsigned long long) profile[i].size);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index fbd32af89c7..0dc31d85fc3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -264,37 +264,37 @@ void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
 			       MLX4_CMD_FREE_RES,
 			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 		if (err) {
-			mlx4_warn(dev, "Failed to release qp range"
-				  " base:%d cnt:%d\n", base_qpn, cnt);
+			mlx4_warn(dev, "Failed to release qp range base:%d cnt:%d\n",
+				  base_qpn, cnt);
 		}
 	} else
 		 __mlx4_qp_release_range(dev, base_qpn, cnt);
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_release_range);
 
-int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
+int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
 	int err;
 
-	err = mlx4_table_get(dev, &qp_table->qp_table, qpn);
+	err = mlx4_table_get(dev, &qp_table->qp_table, qpn, gfp);
 	if (err)
 		goto err_out;
 
-	err = mlx4_table_get(dev, &qp_table->auxc_table, qpn);
+	err = mlx4_table_get(dev, &qp_table->auxc_table, qpn, gfp);
 	if (err)
 		goto err_put_qp;
 
-	err = mlx4_table_get(dev, &qp_table->altc_table, qpn);
+	err = mlx4_table_get(dev, &qp_table->altc_table, qpn, gfp);
 	if (err)
 		goto err_put_auxc;
 
-	err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn);
+	err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn, gfp);
 	if (err)
 		goto err_put_altc;
 
-	err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn);
+	err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn, gfp);
 	if (err)
 		goto err_put_rdmarc;
 
@@ -316,7 +316,7 @@ err_out:
 	return err;
 }
 
-static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
+static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp)
 {
 	u64 param = 0;
 
@@ -326,7 +326,7 @@ static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
 				    MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A,
 				    MLX4_CMD_WRAPPED);
 	}
-	return __mlx4_qp_alloc_icm(dev, qpn);
+	return __mlx4_qp_alloc_icm(dev, qpn, gfp);
 }
 
 void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
@@ -355,7 +355,7 @@ static void mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
 		__mlx4_qp_free_icm(dev, qpn);
 }
 
-int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
+int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, gfp_t gfp)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
@@ -366,7 +366,7 @@ int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
 
 	qp->qpn = qpn;
 
-	err = mlx4_qp_alloc_icm(dev, qpn);
+	err = mlx4_qp_alloc_icm(dev, qpn, gfp);
 	if (err)
 		return err;
 
@@ -612,8 +612,7 @@ int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
 				     context, 0, 0, qp);
 		if (err) {
-			mlx4_err(dev, "Failed to bring QP to state: "
-				 "%d with error: %d\n",
+			mlx4_err(dev, "Failed to bring QP to state: %d with error: %d\n",
 				 states[i + 1], err);
 			return err;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx4/reset.c b/drivers/net/ethernet/mellanox/mlx4/reset.c
index dd1b5093d8b..ea1c6d09214 100644
--- a/drivers/net/ethernet/mellanox/mlx4/reset.c
+++ b/drivers/net/ethernet/mellanox/mlx4/reset.c
@@ -72,8 +72,7 @@ int mlx4_reset(struct mlx4_dev *dev)
 	hca_header = kmalloc(256, GFP_KERNEL);
 	if (!hca_header) {
 		err = -ENOMEM;
-		mlx4_err(dev, "Couldn't allocate memory to save HCA "
-			  "PCI header, aborting.\n");
+		mlx4_err(dev, "Couldn't allocate memory to save HCA PCI header, aborting\n");
 		goto out;
 	}
 
@@ -84,8 +83,7 @@ int mlx4_reset(struct mlx4_dev *dev)
 			continue;
 		if (pci_read_config_dword(dev->pdev, i * 4, hca_header + i)) {
 			err = -ENODEV;
-			mlx4_err(dev, "Couldn't save HCA "
-				  "PCI header, aborting.\n");
+			mlx4_err(dev, "Couldn't save HCA PCI header, aborting\n");
 			goto out;
 		}
 	}
@@ -94,7 +92,7 @@ int mlx4_reset(struct mlx4_dev *dev)
 			MLX4_RESET_SIZE);
 	if (!reset) {
 		err = -ENOMEM;
-		mlx4_err(dev, "Couldn't map HCA reset register, aborting.\n");
+		mlx4_err(dev, "Couldn't map HCA reset register, aborting\n");
 		goto out;
 	}
 
@@ -133,8 +131,7 @@ int mlx4_reset(struct mlx4_dev *dev)
 
 	if (vendor == 0xffff) {
 		err = -ENODEV;
-		mlx4_err(dev, "PCI device did not come back after reset, "
-			  "aborting.\n");
+		mlx4_err(dev, "PCI device did not come back after reset, aborting\n");
 		goto out;
 	}
 
@@ -144,16 +141,14 @@ int mlx4_reset(struct mlx4_dev *dev)
 		if (pcie_capability_write_word(dev->pdev, PCI_EXP_DEVCTL,
 					       devctl)) {
 			err = -ENODEV;
-			mlx4_err(dev, "Couldn't restore HCA PCI Express "
-				 "Device Control register, aborting.\n");
+			mlx4_err(dev, "Couldn't restore HCA PCI Express Device Control register, aborting\n");
 			goto out;
 		}
 		linkctl = hca_header[(pcie_cap + PCI_EXP_LNKCTL) / 4];
 		if (pcie_capability_write_word(dev->pdev, PCI_EXP_LNKCTL,
 					       linkctl)) {
 			err = -ENODEV;
-			mlx4_err(dev, "Couldn't restore HCA PCI Express "
-				 "Link control register, aborting.\n");
+			mlx4_err(dev, "Couldn't restore HCA PCI Express Link control register, aborting\n");
 			goto out;
 		}
 	}
@@ -164,8 +159,8 @@ int mlx4_reset(struct mlx4_dev *dev)
 
 		if (pci_write_config_dword(dev->pdev, i * 4, hca_header[i])) {
 			err = -ENODEV;
-			mlx4_err(dev, "Couldn't restore HCA reg %x, "
-				  "aborting.\n", i);
+			mlx4_err(dev, "Couldn't restore HCA reg %x, aborting\n",
+				 i);
 			goto out;
 		}
 	}
@@ -173,8 +168,7 @@ int mlx4_reset(struct mlx4_dev *dev)
 	if (pci_write_config_dword(dev->pdev, PCI_COMMAND,
 				   hca_header[PCI_COMMAND / 4])) {
 		err = -ENODEV;
-		mlx4_err(dev, "Couldn't restore HCA COMMAND, "
-			  "aborting.\n");
+		mlx4_err(dev, "Couldn't restore HCA COMMAND, aborting\n");
 		goto out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index f16e539749c..0efc1368e5a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -279,7 +279,7 @@ enum qp_transition {
 };
 
 /* For Debug uses */
-static const char *ResourceType(enum mlx4_resource rt)
+static const char *resource_str(enum mlx4_resource rt)
 {
 	switch (rt) {
 	case RES_QP: return "RES_QP";
@@ -307,6 +307,7 @@ static inline int mlx4_grant_resource(struct mlx4_dev *dev, int slave,
 		&priv->mfunc.master.res_tracker.res_alloc[res_type];
 	int err = -EINVAL;
 	int allocated, free, reserved, guaranteed, from_free;
+	int from_rsvd;
 
 	if (slave > dev->num_vfs)
 		return -EINVAL;
@@ -321,11 +322,16 @@ static inline int mlx4_grant_resource(struct mlx4_dev *dev, int slave,
 		res_alloc->res_reserved;
 	guaranteed = res_alloc->guaranteed[slave];
 
-	if (allocated + count > res_alloc->quota[slave])
+	if (allocated + count > res_alloc->quota[slave]) {
+		mlx4_warn(dev, "VF %d port %d res %s: quota exceeded, count %d alloc %d quota %d\n",
+			  slave, port, resource_str(res_type), count,
+			  allocated, res_alloc->quota[slave]);
 		goto out;
+	}
 
 	if (allocated + count <= guaranteed) {
 		err = 0;
+		from_rsvd = count;
 	} else {
 		/* portion may need to be obtained from free area */
 		if (guaranteed - allocated > 0)
@@ -333,8 +339,14 @@ static inline int mlx4_grant_resource(struct mlx4_dev *dev, int slave,
 		else
 			from_free = count;
 
-		if (free - from_free > reserved)
+		from_rsvd = count - from_free;
+
+		if (free - from_free >= reserved)
 			err = 0;
+		else
+			mlx4_warn(dev, "VF %d port %d res %s: free pool empty, free %d from_free %d rsvd %d\n",
+				  slave, port, resource_str(res_type), free,
+				  from_free, reserved);
 	}
 
 	if (!err) {
@@ -342,9 +354,11 @@ static inline int mlx4_grant_resource(struct mlx4_dev *dev, int slave,
 		if (port > 0) {
 			res_alloc->allocated[(port - 1) * (dev->num_vfs + 1) + slave] += count;
 			res_alloc->res_port_free[port - 1] -= count;
+			res_alloc->res_port_rsvd[port - 1] -= from_rsvd;
 		} else {
 			res_alloc->allocated[slave] += count;
 			res_alloc->res_free -= count;
+			res_alloc->res_reserved -= from_rsvd;
 		}
 	}
 
@@ -360,17 +374,36 @@ static inline void mlx4_release_resource(struct mlx4_dev *dev, int slave,
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct resource_allocator *res_alloc =
 		&priv->mfunc.master.res_tracker.res_alloc[res_type];
+	int allocated, guaranteed, from_rsvd;
 
 	if (slave > dev->num_vfs)
 		return;
 
 	spin_lock(&res_alloc->alloc_lock);
+
+	allocated = (port > 0) ?
+		res_alloc->allocated[(port - 1) * (dev->num_vfs + 1) + slave] :
+		res_alloc->allocated[slave];
+	guaranteed = res_alloc->guaranteed[slave];
+
+	if (allocated - count >= guaranteed) {
+		from_rsvd = 0;
+	} else {
+		/* portion may need to be returned to reserved area */
+		if (allocated - guaranteed > 0)
+			from_rsvd = count - (allocated - guaranteed);
+		else
+			from_rsvd = count;
+	}
+
 	if (port > 0) {
 		res_alloc->allocated[(port - 1) * (dev->num_vfs + 1) + slave] -= count;
 		res_alloc->res_port_free[port - 1] += count;
+		res_alloc->res_port_rsvd[port - 1] += from_rsvd;
 	} else {
 		res_alloc->allocated[slave] -= count;
 		res_alloc->res_free += count;
+		res_alloc->res_reserved += from_rsvd;
 	}
 
 	spin_unlock(&res_alloc->alloc_lock);
@@ -963,7 +996,7 @@ static struct res_common *alloc_tr(u64 id, enum mlx4_resource type, int slave,
 		ret = alloc_srq_tr(id);
 		break;
 	case RES_MAC:
-		printk(KERN_ERR "implementation missing\n");
+		pr_err("implementation missing\n");
 		return NULL;
 	case RES_COUNTER:
 		ret = alloc_counter_tr(id);
@@ -1057,10 +1090,10 @@ static int remove_mtt_ok(struct res_mtt *res, int order)
 {
 	if (res->com.state == RES_MTT_BUSY ||
 	    atomic_read(&res->ref_count)) {
-		printk(KERN_DEBUG "%s-%d: state %s, ref_count %d\n",
-		       __func__, __LINE__,
-		       mtt_states_str(res->com.state),
-		       atomic_read(&res->ref_count));
+		pr_devel("%s-%d: state %s, ref_count %d\n",
+			 __func__, __LINE__,
+			 mtt_states_str(res->com.state),
+			 atomic_read(&res->ref_count));
 		return -EBUSY;
 	} else if (res->com.state != RES_MTT_ALLOCATED)
 		return -EPERM;
@@ -1533,7 +1566,7 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 			return err;
 
 		if (!fw_reserved(dev, qpn)) {
-			err = __mlx4_qp_alloc_icm(dev, qpn);
+			err = __mlx4_qp_alloc_icm(dev, qpn, GFP_KERNEL);
 			if (err) {
 				res_abort_move(dev, slave, RES_QP, qpn);
 				return err;
@@ -1620,7 +1653,7 @@ static int mpt_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 		if (err)
 			return err;
 
-		err = __mlx4_mpt_alloc_icm(dev, mpt->key);
+		err = __mlx4_mpt_alloc_icm(dev, mpt->key, GFP_KERNEL);
 		if (err) {
 			res_abort_move(dev, slave, RES_MPT, id);
 			return err;
@@ -2828,10 +2861,12 @@ static int get_containing_mtt(struct mlx4_dev *dev, int slave, int start,
 }
 
 static int verify_qp_parameters(struct mlx4_dev *dev,
+				struct mlx4_vhcr *vhcr,
 				struct mlx4_cmd_mailbox *inbox,
 				enum qp_transition transition, u8 slave)
 {
 	u32			qp_type;
+	u32			qpn;
 	struct mlx4_qp_context	*qp_ctx;
 	enum mlx4_qp_optpar	optpar;
 	int port;
@@ -2874,8 +2909,22 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 		default:
 			break;
 		}
+		break;
 
+	case MLX4_QP_ST_MLX:
+		qpn = vhcr->in_modifier & 0x7fffff;
+		port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
+		if (transition == QP_TRANS_INIT2RTR &&
+		    slave != mlx4_master_func_num(dev) &&
+		    mlx4_is_qp_reserved(dev, qpn) &&
+		    !mlx4_vf_smi_enabled(dev, slave, port)) {
+			/* only enabled VFs may create MLX proxy QPs */
+			mlx4_err(dev, "%s: unprivileged slave %d attempting to create an MLX proxy special QP on port %d\n",
+				 __func__, slave, port);
+			return -EPERM;
+		}
 		break;
+
 	default:
 		break;
 	}
@@ -3455,7 +3504,7 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
 	err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
 	if (err)
 		return err;
-	err = verify_qp_parameters(dev, inbox, QP_TRANS_INIT2RTR, slave);
+	err = verify_qp_parameters(dev, vhcr, inbox, QP_TRANS_INIT2RTR, slave);
 	if (err)
 		return err;
 
@@ -3509,7 +3558,7 @@ int mlx4_RTR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
 	err = adjust_qp_sched_queue(dev, slave, context, inbox);
 	if (err)
 		return err;
-	err = verify_qp_parameters(dev, inbox, QP_TRANS_RTR2RTS, slave);
+	err = verify_qp_parameters(dev, vhcr, inbox, QP_TRANS_RTR2RTS, slave);
 	if (err)
 		return err;
 
@@ -3531,7 +3580,7 @@ int mlx4_RTS2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
 	err = adjust_qp_sched_queue(dev, slave, context, inbox);
 	if (err)
 		return err;
-	err = verify_qp_parameters(dev, inbox, QP_TRANS_RTS2RTS, slave);
+	err = verify_qp_parameters(dev, vhcr, inbox, QP_TRANS_RTS2RTS, slave);
 	if (err)
 		return err;
 
@@ -3568,7 +3617,7 @@ int mlx4_SQD2SQD_QP_wrapper(struct mlx4_dev *dev, int slave,
 	err = adjust_qp_sched_queue(dev, slave, context, inbox);
 	if (err)
 		return err;
-	err = verify_qp_parameters(dev, inbox, QP_TRANS_SQD2SQD, slave);
+	err = verify_qp_parameters(dev, vhcr, inbox, QP_TRANS_SQD2SQD, slave);
 	if (err)
 		return err;
 
@@ -3590,7 +3639,7 @@ int mlx4_SQD2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
 	err = adjust_qp_sched_queue(dev, slave, context, inbox);
 	if (err)
 		return err;
-	err = verify_qp_parameters(dev, inbox, QP_TRANS_SQD2RTS, slave);
+	err = verify_qp_parameters(dev, vhcr, inbox, QP_TRANS_SQD2RTS, slave);
 	if (err)
 		return err;
 
@@ -3881,7 +3930,7 @@ static int add_eth_header(struct mlx4_dev *dev, int slave,
 		}
 	}
 	if (!be_mac) {
-		pr_err("Failed adding eth header to FS rule, Can't find matching MAC for port %d .\n",
+		pr_err("Failed adding eth header to FS rule, Can't find matching MAC for port %d\n",
 		       port);
 		return -EINVAL;
 	}
@@ -3978,7 +4027,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 	qpn = be32_to_cpu(ctrl->qpn) & 0xffffff;
 	err = get_res(dev, slave, qpn, RES_QP, &rqp);
 	if (err) {
-		pr_err("Steering rule with qpn 0x%x rejected.\n", qpn);
+		pr_err("Steering rule with qpn 0x%x rejected\n", qpn);
 		return err;
 	}
 	rule_header = (struct _rule_hw *)(ctrl + 1);
@@ -3996,7 +4045,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 	case MLX4_NET_TRANS_RULE_ID_IPV4:
 	case MLX4_NET_TRANS_RULE_ID_TCP:
 	case MLX4_NET_TRANS_RULE_ID_UDP:
-		pr_warn("Can't attach FS rule without L2 headers, adding L2 header.\n");
+		pr_warn("Can't attach FS rule without L2 headers, adding L2 header\n");
 		if (add_eth_header(dev, slave, inbox, rlist, header_id)) {
 			err = -EINVAL;
 			goto err_put;
@@ -4005,7 +4054,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 			sizeof(struct mlx4_net_trans_rule_hw_eth) >> 2;
 		break;
 	default:
-		pr_err("Corrupted mailbox.\n");
+		pr_err("Corrupted mailbox\n");
 		err = -EINVAL;
 		goto err_put;
 	}
@@ -4019,7 +4068,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 
 	err = add_res_range(dev, slave, vhcr->out_param, 1, RES_FS_RULE, qpn);
 	if (err) {
-		mlx4_err(dev, "Fail to add flow steering resources.\n ");
+		mlx4_err(dev, "Fail to add flow steering resources\n");
 		/* detach rule*/
 		mlx4_cmd(dev, vhcr->out_param, 0, 0,
 			 MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
@@ -4057,7 +4106,7 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
 
 	err = rem_res_range(dev, slave, vhcr->in_param, 1, RES_FS_RULE, 0);
 	if (err) {
-		mlx4_err(dev, "Fail to remove flow steering resources.\n ");
+		mlx4_err(dev, "Fail to remove flow steering resources\n");
 		goto out;
 	}
 
@@ -4135,7 +4184,7 @@ static int _move_all_busy(struct mlx4_dev *dev, int slave,
 					if (print)
 						mlx4_dbg(dev,
 							 "%s id 0x%llx is busy\n",
-							  ResourceType(type),
+							  resource_str(type),
 							  r->res_id);
 					++busy;
 				} else {
@@ -4186,8 +4235,8 @@ static void rem_slave_qps(struct mlx4_dev *dev, int slave)
 
 	err = move_all_busy(dev, slave, RES_QP);
 	if (err)
-		mlx4_warn(dev, "rem_slave_qps: Could not move all qps to busy"
-			  "for slave %d\n", slave);
+		mlx4_warn(dev, "rem_slave_qps: Could not move all qps to busy for slave %d\n",
+			  slave);
 
 	spin_lock_irq(mlx4_tlock(dev));
 	list_for_each_entry_safe(qp, tmp, qp_list, com.list) {
@@ -4225,10 +4274,8 @@ static void rem_slave_qps(struct mlx4_dev *dev, int slave)
 						       MLX4_CMD_TIME_CLASS_A,
 						       MLX4_CMD_NATIVE);
 					if (err)
-						mlx4_dbg(dev, "rem_slave_qps: failed"
-							 " to move slave %d qpn %d to"
-							 " reset\n", slave,
-							 qp->local_qpn);
+						mlx4_dbg(dev, "rem_slave_qps: failed to move slave %d qpn %d to reset\n",
+							 slave, qp->local_qpn);
 					atomic_dec(&qp->rcq->ref_count);
 					atomic_dec(&qp->scq->ref_count);
 					atomic_dec(&qp->mtt->ref_count);
@@ -4262,8 +4309,8 @@ static void rem_slave_srqs(struct mlx4_dev *dev, int slave)
 
 	err = move_all_busy(dev, slave, RES_SRQ);
 	if (err)
-		mlx4_warn(dev, "rem_slave_srqs: Could not move all srqs to "
-			  "busy for slave %d\n", slave);
+		mlx4_warn(dev, "rem_slave_srqs: Could not move all srqs - too busy for slave %d\n",
+			  slave);
 
 	spin_lock_irq(mlx4_tlock(dev));
 	list_for_each_entry_safe(srq, tmp, srq_list, com.list) {
@@ -4293,9 +4340,7 @@ static void rem_slave_srqs(struct mlx4_dev *dev, int slave)
 						       MLX4_CMD_TIME_CLASS_A,
 						       MLX4_CMD_NATIVE);
 					if (err)
-						mlx4_dbg(dev, "rem_slave_srqs: failed"
-							 " to move slave %d srq %d to"
-							 " SW ownership\n",
+						mlx4_dbg(dev, "rem_slave_srqs: failed to move slave %d srq %d to SW ownership\n",
 							 slave, srqn);
 
 					atomic_dec(&srq->mtt->ref_count);
@@ -4330,8 +4375,8 @@ static void rem_slave_cqs(struct mlx4_dev *dev, int slave)
 
 	err = move_all_busy(dev, slave, RES_CQ);
 	if (err)
-		mlx4_warn(dev, "rem_slave_cqs: Could not move all cqs to "
-			  "busy for slave %d\n", slave);
+		mlx4_warn(dev, "rem_slave_cqs: Could not move all cqs - too busy for slave %d\n",
+			  slave);
 
 	spin_lock_irq(mlx4_tlock(dev));
 	list_for_each_entry_safe(cq, tmp, cq_list, com.list) {
@@ -4361,9 +4406,7 @@ static void rem_slave_cqs(struct mlx4_dev *dev, int slave)
 						       MLX4_CMD_TIME_CLASS_A,
 						       MLX4_CMD_NATIVE);
 					if (err)
-						mlx4_dbg(dev, "rem_slave_cqs: failed"
-							 " to move slave %d cq %d to"
-							 " SW ownership\n",
+						mlx4_dbg(dev, "rem_slave_cqs: failed to move slave %d cq %d to SW ownership\n",
 							 slave, cqn);
 					atomic_dec(&cq->mtt->ref_count);
 					state = RES_CQ_ALLOCATED;
@@ -4395,8 +4438,8 @@ static void rem_slave_mrs(struct mlx4_dev *dev, int slave)
 
 	err = move_all_busy(dev, slave, RES_MPT);
 	if (err)
-		mlx4_warn(dev, "rem_slave_mrs: Could not move all mpts to "
-			  "busy for slave %d\n", slave);
+		mlx4_warn(dev, "rem_slave_mrs: Could not move all mpts - too busy for slave %d\n",
+			  slave);
 
 	spin_lock_irq(mlx4_tlock(dev));
 	list_for_each_entry_safe(mpt, tmp, mpt_list, com.list) {
@@ -4431,9 +4474,7 @@ static void rem_slave_mrs(struct mlx4_dev *dev, int slave)
 						     MLX4_CMD_TIME_CLASS_A,
 						     MLX4_CMD_NATIVE);
 					if (err)
-						mlx4_dbg(dev, "rem_slave_mrs: failed"
-							 " to move slave %d mpt %d to"
-							 " SW ownership\n",
+						mlx4_dbg(dev, "rem_slave_mrs: failed to move slave %d mpt %d to SW ownership\n",
 							 slave, mptn);
 					if (mpt->mtt)
 						atomic_dec(&mpt->mtt->ref_count);
@@ -4465,8 +4506,8 @@ static void rem_slave_mtts(struct mlx4_dev *dev, int slave)
 
 	err = move_all_busy(dev, slave, RES_MTT);
 	if (err)
-		mlx4_warn(dev, "rem_slave_mtts: Could not move all mtts to "
-			  "busy for slave %d\n", slave);
+		mlx4_warn(dev, "rem_slave_mtts: Could not move all mtts  - too busy for slave %d\n",
+			  slave);
 
 	spin_lock_irq(mlx4_tlock(dev));
 	list_for_each_entry_safe(mtt, tmp, mtt_list, com.list) {
@@ -4568,8 +4609,8 @@ static void rem_slave_eqs(struct mlx4_dev *dev, int slave)
 
 	err = move_all_busy(dev, slave, RES_EQ);
 	if (err)
-		mlx4_warn(dev, "rem_slave_eqs: Could not move all eqs to "
-			  "busy for slave %d\n", slave);
+		mlx4_warn(dev, "rem_slave_eqs: Could not move all eqs - too busy for slave %d\n",
+			  slave);
 
 	spin_lock_irq(mlx4_tlock(dev));
 	list_for_each_entry_safe(eq, tmp, eq_list, com.list) {
@@ -4601,9 +4642,8 @@ static void rem_slave_eqs(struct mlx4_dev *dev, int slave)
 							   MLX4_CMD_TIME_CLASS_A,
 							   MLX4_CMD_NATIVE);
 					if (err)
-						mlx4_dbg(dev, "rem_slave_eqs: failed"
-							 " to move slave %d eqs %d to"
-							 " SW ownership\n", slave, eqn);
+						mlx4_dbg(dev, "rem_slave_eqs: failed to move slave %d eqs %d to SW ownership\n",
+							 slave, eqn);
 					mlx4_free_cmd_mailbox(dev, mailbox);
 					atomic_dec(&eq->mtt->ref_count);
 					state = RES_EQ_RESERVED;
@@ -4632,8 +4672,8 @@ static void rem_slave_counters(struct mlx4_dev *dev, int slave)
 
 	err = move_all_busy(dev, slave, RES_COUNTER);
 	if (err)
-		mlx4_warn(dev, "rem_slave_counters: Could not move all counters to "
-			  "busy for slave %d\n", slave);
+		mlx4_warn(dev, "rem_slave_counters: Could not move all counters - too busy for slave %d\n",
+			  slave);
 
 	spin_lock_irq(mlx4_tlock(dev));
 	list_for_each_entry_safe(counter, tmp, counter_list, com.list) {
@@ -4663,8 +4703,8 @@ static void rem_slave_xrcdns(struct mlx4_dev *dev, int slave)
 
 	err = move_all_busy(dev, slave, RES_XRCD);
 	if (err)
-		mlx4_warn(dev, "rem_slave_xrcdns: Could not move all xrcdns to "
-			  "busy for slave %d\n", slave);
+		mlx4_warn(dev, "rem_slave_xrcdns: Could not move all xrcdns - too busy for slave %d\n",
+			  slave);
 
 	spin_lock_irq(mlx4_tlock(dev));
 	list_for_each_entry_safe(xrcd, tmp, xrcdn_list, com.list) {
@@ -4809,10 +4849,8 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work)
 				       0, MLX4_CMD_UPDATE_QP,
 				       MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 			if (err) {
-				mlx4_info(dev, "UPDATE_QP failed for slave %d, "
-					  "port %d, qpn %d (%d)\n",
-					  work->slave, port, qp->local_qpn,
-					  err);
+				mlx4_info(dev, "UPDATE_QP failed for slave %d, port %d, qpn %d (%d)\n",
+					  work->slave, port, qp->local_qpn, err);
 				errors++;
 			}
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c
index 98faf870b0b..67146624eb5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/srq.c
@@ -103,11 +103,11 @@ int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn)
 	if (*srqn == -1)
 		return -ENOMEM;
 
-	err = mlx4_table_get(dev, &srq_table->table, *srqn);
+	err = mlx4_table_get(dev, &srq_table->table, *srqn, GFP_KERNEL);
 	if (err)
 		goto err_out;
 
-	err = mlx4_table_get(dev, &srq_table->cmpt_table, *srqn);
+	err = mlx4_table_get(dev, &srq_table->cmpt_table, *srqn, GFP_KERNEL);
 	if (err)
 		goto err_put;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 405c4fbcd0a..87d1b018a9c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -620,8 +620,8 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 			       mlx5_command_str(msg_to_opcode(ent->in)),
 			       msg_to_opcode(ent->in));
 	}
-	mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n", err,
-		      deliv_status_to_str(ent->status), ent->status);
+	mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n",
+		      err, deliv_status_to_str(ent->status), ent->status);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 64a61b286b2..7f39ebcd6ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -208,7 +208,8 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 		 */
 		rmb();
 
-		mlx5_core_dbg(eq->dev, "eqn %d, eqe type %s\n", eq->eqn, eqe_type_str(eqe->type));
+		mlx5_core_dbg(eq->dev, "eqn %d, eqe type %s\n",
+			      eq->eqn, eqe_type_str(eqe->type));
 		switch (eqe->type) {
 		case MLX5_EVENT_TYPE_COMP:
 			cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff;
@@ -270,14 +271,16 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 				u16 func_id = be16_to_cpu(eqe->data.req_pages.func_id);
 				s32 npages = be32_to_cpu(eqe->data.req_pages.num_pages);
 
-				mlx5_core_dbg(dev, "page request for func 0x%x, napges %d\n", func_id, npages);
+				mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
+					      func_id, npages);
 				mlx5_core_req_pages_handler(dev, func_id, npages);
 			}
 			break;
 
 
 		default:
-			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n", eqe->type, eq->eqn);
+			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
+				       eqe->type, eq->eqn);
 			break;
 		}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c3eee5f7005..ee24f132e31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -66,10 +66,10 @@ static int set_dma_caps(struct pci_dev *pdev)
 
 	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
 	if (err) {
-		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask.\n");
+		dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n");
 		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
 		if (err) {
-			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting.\n");
+			dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n");
 			return err;
 		}
 	}
@@ -77,11 +77,11 @@ static int set_dma_caps(struct pci_dev *pdev)
 	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
 	if (err) {
 		dev_warn(&pdev->dev,
-			 "Warning: couldn't set 64-bit consistent PCI DMA mask.\n");
+			 "Warning: couldn't set 64-bit consistent PCI DMA mask\n");
 		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
 		if (err) {
 			dev_err(&pdev->dev,
-				"Can't set consistent PCI DMA mask, aborting.\n");
+				"Can't set consistent PCI DMA mask, aborting\n");
 			return err;
 		}
 	}
@@ -95,7 +95,7 @@ static int request_bar(struct pci_dev *pdev)
 	int err = 0;
 
 	if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
-		dev_err(&pdev->dev, "Missing registers BAR, aborting.\n");
+		dev_err(&pdev->dev, "Missing registers BAR, aborting\n");
 		return -ENODEV;
 	}
 
@@ -319,13 +319,13 @@ int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 
 	err = pci_enable_device(pdev);
 	if (err) {
-		dev_err(&pdev->dev, "Cannot enable PCI device, aborting.\n");
+		dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n");
 		goto err_dbg;
 	}
 
 	err = request_bar(pdev);
 	if (err) {
-		dev_err(&pdev->dev, "error requesting BARs, aborting.\n");
+		dev_err(&pdev->dev, "error requesting BARs, aborting\n");
 		goto err_disable;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 68b74e1ae1b..f0c9f9a7a36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -39,24 +39,26 @@
 
 extern int mlx5_core_debug_mask;
 
-#define mlx5_core_dbg(dev, format, arg...)				       \
-pr_debug("%s:%s:%d:(pid %d): " format, (dev)->priv.name, __func__, __LINE__,   \
-	 current->pid, ##arg)
+#define mlx5_core_dbg(dev, format, ...)					\
+	pr_debug("%s:%s:%d:(pid %d): " format,				\
+		 (dev)->priv.name, __func__, __LINE__, current->pid,	\
+		 ##__VA_ARGS__)
 
-#define mlx5_core_dbg_mask(dev, mask, format, arg...)			       \
-do {									       \
-	if ((mask) & mlx5_core_debug_mask)				       \
-		pr_debug("%s:%s:%d:(pid %d): " format, (dev)->priv.name,       \
-			 __func__, __LINE__, current->pid, ##arg);	       \
+#define mlx5_core_dbg_mask(dev, mask, format, ...)			\
+do {									\
+	if ((mask) & mlx5_core_debug_mask)				\
+		mlx5_core_dbg(dev, format, ##__VA_ARGS__);		\
 } while (0)
 
-#define mlx5_core_err(dev, format, arg...) \
-pr_err("%s:%s:%d:(pid %d): " format, (dev)->priv.name, __func__, __LINE__,     \
-	current->pid, ##arg)
+#define mlx5_core_err(dev, format, ...)					\
+	pr_err("%s:%s:%d:(pid %d): " format,				\
+	       (dev)->priv.name, __func__, __LINE__, current->pid,	\
+	       ##__VA_ARGS__)
 
-#define mlx5_core_warn(dev, format, arg...) \
-pr_warn("%s:%s:%d:(pid %d): " format, (dev)->priv.name, __func__, __LINE__,    \
-	current->pid, ##arg)
+#define mlx5_core_warn(dev, format, ...)				\
+	pr_warn("%s:%s:%d:(pid %d): " format,				\
+		(dev)->priv.name, __func__, __LINE__, current->pid,	\
+		##__VA_ARGS__)
 
 enum {
 	MLX5_CMD_DATA, /* print command payload only */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 4cc92764940..184c3615f47 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -73,7 +73,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 	}
 
 	if (err) {
-		mlx5_core_dbg(dev, "cmd exec faile %d\n", err);
+		mlx5_core_dbg(dev, "cmd exec failed %d\n", err);
 		return err;
 	}
 
@@ -82,7 +82,11 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 		return mlx5_cmd_status_to_err(&lout.hdr);
 	}
 
+	mr->iova = be64_to_cpu(in->seg.start_addr);
+	mr->size = be64_to_cpu(in->seg.len);
 	mr->key = mlx5_idx_to_mkey(be32_to_cpu(lout.mkey) & 0xffffff) | key;
+	mr->pd = be32_to_cpu(in->seg.flags_pd) & 0xffffff;
+
 	mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n",
 		      be32_to_cpu(lout.mkey), key, mr->key);
 
@@ -90,6 +94,11 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 	write_lock_irq(&table->lock);
 	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->key), mr);
 	write_unlock_irq(&table->lock);
+	if (err) {
+		mlx5_core_warn(dev, "failed radix tree insert of mr 0x%x, %d\n",
+			       mlx5_base_mkey(mr->key), err);
+		mlx5_core_destroy_mkey(dev, mr);
+	}
 
 	return err;
 }
@@ -100,12 +109,22 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr)
 	struct mlx5_mr_table *table = &dev->priv.mr_table;
 	struct mlx5_destroy_mkey_mbox_in in;
 	struct mlx5_destroy_mkey_mbox_out out;
+	struct mlx5_core_mr *deleted_mr;
 	unsigned long flags;
 	int err;
 
 	memset(&in, 0, sizeof(in));
 	memset(&out, 0, sizeof(out));
 
+	write_lock_irqsave(&table->lock, flags);
+	deleted_mr = radix_tree_delete(&table->tree, mlx5_base_mkey(mr->key));
+	write_unlock_irqrestore(&table->lock, flags);
+	if (!deleted_mr) {
+		mlx5_core_warn(dev, "failed radix tree delete of mr 0x%x\n",
+			       mlx5_base_mkey(mr->key));
+		return -ENOENT;
+	}
+
 	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_MKEY);
 	in.mkey = cpu_to_be32(mlx5_mkey_to_idx(mr->key));
 	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
@@ -115,10 +134,6 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr)
 	if (out.hdr.status)
 		return mlx5_cmd_status_to_err(&out.hdr);
 
-	write_lock_irqsave(&table->lock, flags);
-	radix_tree_delete(&table->tree, mlx5_base_mkey(mr->key));
-	write_unlock_irqrestore(&table->lock, flags);
-
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_destroy_mkey);
@@ -191,7 +206,8 @@ int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
 	}
 
 	if (out.hdr.status) {
-		mlx5_core_err(dev, "create_psv bad status %d\n", out.hdr.status);
+		mlx5_core_err(dev, "create_psv bad status %d\n",
+			      out.hdr.status);
 		return mlx5_cmd_status_to_err(&out.hdr);
 	}
 
@@ -220,7 +236,8 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num)
 	}
 
 	if (out.hdr.status) {
-		mlx5_core_err(dev, "destroy_psv bad status %d\n", out.hdr.status);
+		mlx5_core_err(dev, "destroy_psv bad status %d\n",
+			      out.hdr.status);
 		err = mlx5_cmd_status_to_err(&out.hdr);
 		goto out;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index d59790a82bc..c2a953ef0e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -311,7 +311,8 @@ retry:
 	in->num_entries = cpu_to_be32(npages);
 	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
 	if (err) {
-		mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n", func_id, npages, err);
+		mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n",
+			       func_id, npages, err);
 		goto out_alloc;
 	}
 	dev->priv.fw_pages += npages;
@@ -319,7 +320,8 @@ retry:
 	if (out.hdr.status) {
 		err = mlx5_cmd_status_to_err(&out.hdr);
 		if (err) {
-			mlx5_core_warn(dev, "func_id 0x%x, npages %d, status %d\n", func_id, npages, out.hdr.status);
+			mlx5_core_warn(dev, "func_id 0x%x, npages %d, status %d\n",
+				       func_id, npages, out.hdr.status);
 			goto out_alloc;
 		}
 	}
@@ -378,7 +380,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
 	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen);
 	if (err) {
-		mlx5_core_err(dev, "failed recliaming pages\n");
+		mlx5_core_err(dev, "failed reclaiming pages\n");
 		goto out_free;
 	}
 	dev->priv.fw_pages -= npages;
@@ -414,8 +416,8 @@ static void pages_work_handler(struct work_struct *work)
 		err = give_pages(dev, req->func_id, req->npages, 1);
 
 	if (err)
-		mlx5_core_warn(dev, "%s fail %d\n", req->npages < 0 ?
-			       "reclaim" : "give", err);
+		mlx5_core_warn(dev, "%s fail %d\n",
+			       req->npages < 0 ? "reclaim" : "give", err);
 
 	kfree(req);
 }
@@ -487,7 +489,8 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 					    optimal_reclaimed_pages(),
 					    &nclaimed);
 			if (err) {
-				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n", err);
+				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
+					       err);
 				return err;
 			}
 			if (nclaimed)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 510576213dd..8145b466822 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -79,7 +79,7 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 
 	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
 	if (err) {
-		mlx5_core_warn(dev, "ret %d", err);
+		mlx5_core_warn(dev, "ret %d\n", err);
 		return err;
 	}
 
@@ -96,7 +96,7 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 	err = radix_tree_insert(&table->tree, qp->qpn, qp);
 	spin_unlock_irq(&table->lock);
 	if (err) {
-		mlx5_core_warn(dev, "err %d", err);
+		mlx5_core_warn(dev, "err %d\n", err);
 		goto err_cmd;
 	}
 
diff --git a/drivers/net/ethernet/micrel/ks8695net.c b/drivers/net/ethernet/micrel/ks8695net.c
index 16435b3cfa9..6c7c78baedc 100644
--- a/drivers/net/ethernet/micrel/ks8695net.c
+++ b/drivers/net/ethernet/micrel/ks8695net.c
@@ -1504,15 +1504,15 @@ ks8695_probe(struct platform_device *pdev)
 	if (ksp->phyiface_regs && ksp->link_irq == -1) {
 		ks8695_init_switch(ksp);
 		ksp->dtype = KS8695_DTYPE_LAN;
-		SET_ETHTOOL_OPS(ndev, &ks8695_ethtool_ops);
+		ndev->ethtool_ops = &ks8695_ethtool_ops;
 	} else if (ksp->phyiface_regs && ksp->link_irq != -1) {
 		ks8695_init_wan_phy(ksp);
 		ksp->dtype = KS8695_DTYPE_WAN;
-		SET_ETHTOOL_OPS(ndev, &ks8695_wan_ethtool_ops);
+		ndev->ethtool_ops = &ks8695_wan_ethtool_ops;
 	} else {
 		/* No initialisation since HPNA does not have a PHY */
 		ksp->dtype = KS8695_DTYPE_HPNA;
-		SET_ETHTOOL_OPS(ndev, &ks8695_ethtool_ops);
+		ndev->ethtool_ops = &ks8695_ethtool_ops;
 	}
 
 	/* And bring up the net_device with the net core */
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index e0c92e0e5e1..66d4ab703f4 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -26,6 +26,8 @@
 #include <linux/regulator/consumer.h>
 
 #include <linux/spi/spi.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
 
 #include "ks8851.h"
 
@@ -85,6 +87,8 @@ union ks8851_tx_hdr {
  * @eeprom_size: Companion eeprom size in Bytes, 0 if no eeprom
  * @eeprom: 93CX6 EEPROM state for accessing on-board EEPROM.
  * @vdd_reg:	Optional regulator supplying the chip
+ * @vdd_io: Optional digital power supply for IO
+ * @gpio: Optional reset_n gpio
  *
  * The @lock ensures that the chip is protected when certain operations are
  * in progress. When the read or write packet transfer is in progress, most
@@ -133,6 +137,8 @@ struct ks8851_net {
 
 	struct eeprom_93cx6	eeprom;
 	struct regulator	*vdd_reg;
+	struct regulator	*vdd_io;
+	int			gpio;
 };
 
 static int msg_enable;
@@ -1404,6 +1410,7 @@ static int ks8851_probe(struct spi_device *spi)
 	struct ks8851_net *ks;
 	int ret;
 	unsigned cider;
+	int gpio;
 
 	ndev = alloc_etherdev(sizeof(struct ks8851_net));
 	if (!ndev)
@@ -1417,20 +1424,53 @@ static int ks8851_probe(struct spi_device *spi)
 	ks->spidev = spi;
 	ks->tx_space = 6144;
 
-	ks->vdd_reg = regulator_get_optional(&spi->dev, "vdd");
-	if (IS_ERR(ks->vdd_reg)) {
-		ret = PTR_ERR(ks->vdd_reg);
-		if (ret == -EPROBE_DEFER)
-			goto err_reg;
-	} else {
-		ret = regulator_enable(ks->vdd_reg);
+	gpio = of_get_named_gpio_flags(spi->dev.of_node, "reset-gpios",
+				       0, NULL);
+	if (gpio == -EPROBE_DEFER) {
+		ret = gpio;
+		goto err_gpio;
+	}
+
+	ks->gpio = gpio;
+	if (gpio_is_valid(gpio)) {
+		ret = devm_gpio_request_one(&spi->dev, gpio,
+					    GPIOF_OUT_INIT_LOW, "ks8851_rst_n");
 		if (ret) {
-			dev_err(&spi->dev, "regulator enable fail: %d\n",
-				ret);
-			goto err_reg_en;
+			dev_err(&spi->dev, "reset gpio request failed\n");
+			goto err_gpio;
 		}
 	}
 
+	ks->vdd_io = devm_regulator_get(&spi->dev, "vdd-io");
+	if (IS_ERR(ks->vdd_io)) {
+		ret = PTR_ERR(ks->vdd_io);
+		goto err_reg_io;
+	}
+
+	ret = regulator_enable(ks->vdd_io);
+	if (ret) {
+		dev_err(&spi->dev, "regulator vdd_io enable fail: %d\n",
+			ret);
+		goto err_reg_io;
+	}
+
+	ks->vdd_reg = devm_regulator_get(&spi->dev, "vdd");
+	if (IS_ERR(ks->vdd_reg)) {
+		ret = PTR_ERR(ks->vdd_reg);
+		goto err_reg;
+	}
+
+	ret = regulator_enable(ks->vdd_reg);
+	if (ret) {
+		dev_err(&spi->dev, "regulator vdd enable fail: %d\n",
+			ret);
+		goto err_reg;
+	}
+
+	if (gpio_is_valid(gpio)) {
+		usleep_range(10000, 11000);
+		gpio_set_value(gpio, 1);
+	}
 
 	mutex_init(&ks->lock);
 	spin_lock_init(&ks->statelock);
@@ -1471,7 +1511,7 @@ static int ks8851_probe(struct spi_device *spi)
 
 	skb_queue_head_init(&ks->txq);
 
-	SET_ETHTOOL_OPS(ndev, &ks8851_ethtool_ops);
+	ndev->ethtool_ops = &ks8851_ethtool_ops;
 	SET_NETDEV_DEV(ndev, &spi->dev);
 
 	spi_set_drvdata(spi, ks);
@@ -1527,13 +1567,14 @@ err_netdev:
 	free_irq(ndev->irq, ks);
 
 err_irq:
+	if (gpio_is_valid(gpio))
+		gpio_set_value(gpio, 0);
 err_id:
-	if (!IS_ERR(ks->vdd_reg))
-		regulator_disable(ks->vdd_reg);
-err_reg_en:
-	if (!IS_ERR(ks->vdd_reg))
-		regulator_put(ks->vdd_reg);
+	regulator_disable(ks->vdd_reg);
 err_reg:
+	regulator_disable(ks->vdd_io);
+err_reg_io:
+err_gpio:
 	free_netdev(ndev);
 	return ret;
 }
@@ -1547,18 +1588,24 @@ static int ks8851_remove(struct spi_device *spi)
 
 	unregister_netdev(priv->netdev);
 	free_irq(spi->irq, priv);
-	if (!IS_ERR(priv->vdd_reg)) {
-		regulator_disable(priv->vdd_reg);
-		regulator_put(priv->vdd_reg);
-	}
+	if (gpio_is_valid(priv->gpio))
+		gpio_set_value(priv->gpio, 0);
+	regulator_disable(priv->vdd_reg);
+	regulator_disable(priv->vdd_io);
 	free_netdev(priv->netdev);
 
 	return 0;
 }
 
+static const struct of_device_id ks8851_match_table[] = {
+	{ .compatible = "micrel,ks8851" },
+	{ }
+};
+
 static struct spi_driver ks8851_driver = {
 	.driver = {
 		.name = "ks8851",
+		.of_match_table = ks8851_match_table,
 		.owner = THIS_MODULE,
 		.pm = &ks8851_pm_ops,
 	},
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index 14ac0e2bc09..064a48d0c36 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -4930,7 +4930,7 @@ static void netdev_tx_timeout(struct net_device *dev)
 		 * Only reset the hardware if time between calls is long
 		 * enough.
 		 */
-		if (jiffies - last_reset <= dev->watchdog_timeo)
+		if (time_before_eq(jiffies, last_reset + dev->watchdog_timeo))
 			hw_priv = NULL;
 	}
 
@@ -7072,6 +7072,7 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id)
 		dev = alloc_etherdev(sizeof(struct dev_priv));
 		if (!dev)
 			goto pcidev_init_reg_err;
+		SET_NETDEV_DEV(dev, &pdev->dev);
 		info->netdev[i] = dev;
 
 		priv = netdev_priv(dev);
@@ -7106,7 +7107,7 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id)
 		}
 
 		dev->netdev_ops = &netdev_ops;
-		SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops);
+		dev->ethtool_ops = &netdev_ethtool_ops;
 		if (register_netdev(dev))
 			goto pcidev_init_reg_err;
 		port_set_power_saving(port, true);
diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c
index c7b40aa21f2..b1b5f66b8b6 100644
--- a/drivers/net/ethernet/microchip/enc28j60.c
+++ b/drivers/net/ethernet/microchip/enc28j60.c
@@ -1593,7 +1593,7 @@ static int enc28j60_probe(struct spi_device *spi)
 	dev->irq = spi->irq;
 	dev->netdev_ops = &enc28j60_netdev_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
-	SET_ETHTOOL_OPS(dev, &enc28j60_ethtool_ops);
+	dev->ethtool_ops = &enc28j60_ethtool_ops;
 
 	enc28j60_lowpower(priv, true);
 
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 130f6b204ef..f3d5d79f1cd 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -4112,7 +4112,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	setup_timer(&mgp->watchdog_timer, myri10ge_watchdog_timer,
 		    (unsigned long)mgp);
 
-	SET_ETHTOOL_OPS(netdev, &myri10ge_ethtool_ops);
+	netdev->ethtool_ops = &myri10ge_ethtool_ops;
 	INIT_WORK(&mgp->watchdog_work, myri10ge_watchdog);
 	status = register_netdev(netdev);
 	if (status != 0) {
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index 64ec2a437f4..291fba8b9f0 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -927,7 +927,7 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->netdev_ops = &natsemi_netdev_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
 
-	SET_ETHTOOL_OPS(dev, &ethtool_ops);
+	dev->ethtool_ops = &ethtool_ops;
 
 	if (mtu)
 		dev->mtu = mtu;
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index dbccf1de49e..19bb8244b9e 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -2030,7 +2030,7 @@ static int ns83820_init_one(struct pci_dev *pci_dev,
 		pci_dev->subsystem_vendor, pci_dev->subsystem_device);
 
 	ndev->netdev_ops = &netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &ops);
+	ndev->ethtool_ops = &ops;
 	ndev->watchdog_timeo = 5 * HZ;
 	pci_set_drvdata(pci_dev, ndev);
 
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index a2844ff322c..be587647c70 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -534,15 +534,6 @@ static inline void s2io_start_all_tx_queue(struct s2io_nic *sp)
 	netif_tx_start_all_queues(sp->dev);
 }
 
-static inline void s2io_start_tx_queue(struct s2io_nic *sp, int fifo_no)
-{
-	if (!sp->config.multiq)
-		sp->mac_control.fifos[fifo_no].queue_state =
-			FIFO_QUEUE_START;
-
-	netif_tx_start_all_queues(sp->dev);
-}
-
 static inline void s2io_wake_all_tx_queue(struct s2io_nic *sp)
 {
 	if (!sp->config.multiq) {
@@ -5369,8 +5360,8 @@ static int s2io_ethtool_gset(struct net_device *dev, struct ethtool_cmd *info)
 		ethtool_cmd_speed_set(info, SPEED_10000);
 		info->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(info, -1);
-		info->duplex = -1;
+		ethtool_cmd_speed_set(info, SPEED_UNKNOWN);
+		info->duplex = DUPLEX_UNKNOWN;
 	}
 
 	info->autoneg = AUTONEG_DISABLE;
@@ -7919,7 +7910,7 @@ s2io_init_nic(struct pci_dev *pdev, const struct pci_device_id *pre)
 
 	/*  Driver entry points */
 	dev->netdev_ops = &s2io_netdev_ops;
-	SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops);
+	dev->ethtool_ops = &netdev_ethtool_ops;
 	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM |
 		NETIF_F_TSO | NETIF_F_TSO6 |
 		NETIF_F_RXCSUM | NETIF_F_LRO;
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index 089b713b9f7..2bbd01fcb9b 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -120,7 +120,6 @@ __vxge_hw_device_register_poll(void __iomem *reg, u64 mask, u32 max_millis)
 {
 	u64 val64;
 	u32 i = 0;
-	enum vxge_hw_status ret = VXGE_HW_FAIL;
 
 	udelay(10);
 
@@ -139,7 +138,7 @@ __vxge_hw_device_register_poll(void __iomem *reg, u64 mask, u32 max_millis)
 		mdelay(1);
 	} while (++i <= max_millis);
 
-	return ret;
+	return VXGE_HW_FAIL;
 }
 
 static inline enum vxge_hw_status
@@ -1682,12 +1681,10 @@ enum vxge_hw_status vxge_hw_driver_stats_get(
 			struct __vxge_hw_device *hldev,
 			struct vxge_hw_device_stats_sw_info *sw_stats)
 {
-	enum vxge_hw_status status = VXGE_HW_OK;
-
 	memcpy(sw_stats, &hldev->stats.sw_dev_info_stats,
 		sizeof(struct vxge_hw_device_stats_sw_info));
 
-	return status;
+	return VXGE_HW_OK;
 }
 
 /*
@@ -3228,7 +3225,6 @@ enum vxge_hw_status
 vxge_hw_vpath_strip_fcs_check(struct __vxge_hw_device *hldev, u64 vpath_mask)
 {
 	struct vxge_hw_vpmgmt_reg       __iomem *vpmgmt_reg;
-	enum vxge_hw_status status = VXGE_HW_OK;
 	int i = 0, j = 0;
 
 	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
@@ -3241,7 +3237,7 @@ vxge_hw_vpath_strip_fcs_check(struct __vxge_hw_device *hldev, u64 vpath_mask)
 				return VXGE_HW_FAIL;
 		}
 	}
-	return status;
+	return VXGE_HW_OK;
 }
 /*
  * vxge_hw_mgmt_reg_Write - Write Titan register.
@@ -3979,7 +3975,6 @@ __vxge_hw_vpath_mgmt_read(
 {
 	u32 i, mtu = 0, max_pyld = 0;
 	u64 val64;
-	enum vxge_hw_status status = VXGE_HW_OK;
 
 	for (i = 0; i < VXGE_HW_MAC_MAX_MAC_PORT_ID; i++) {
 
@@ -4009,7 +4004,7 @@ __vxge_hw_vpath_mgmt_read(
 	else
 		VXGE_HW_DEVICE_LINK_STATE_SET(vpath->hldev, VXGE_HW_LINK_DOWN);
 
-	return status;
+	return VXGE_HW_OK;
 }
 
 /*
@@ -4039,14 +4034,13 @@ static enum vxge_hw_status
 __vxge_hw_vpath_reset(struct __vxge_hw_device *hldev, u32 vp_id)
 {
 	u64 val64;
-	enum vxge_hw_status status = VXGE_HW_OK;
 
 	val64 = VXGE_HW_CMN_RSTHDLR_CFG0_SW_RESET_VPATH(1 << (16 - vp_id));
 
 	__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn(val64, 0, 32),
 				&hldev->common_reg->cmn_rsthdlr_cfg0);
 
-	return status;
+	return VXGE_HW_OK;
 }
 
 /*
@@ -4227,7 +4221,6 @@ static enum vxge_hw_status
 __vxge_hw_vpath_mac_configure(struct __vxge_hw_device *hldev, u32 vp_id)
 {
 	u64 val64;
-	enum vxge_hw_status status = VXGE_HW_OK;
 	struct __vxge_hw_virtualpath *vpath;
 	struct vxge_hw_vp_config *vp_config;
 	struct vxge_hw_vpath_reg __iomem *vp_reg;
@@ -4283,7 +4276,7 @@ __vxge_hw_vpath_mac_configure(struct __vxge_hw_device *hldev, u32 vp_id)
 
 		writeq(val64, &vp_reg->rxmac_vcfg1);
 	}
-	return status;
+	return VXGE_HW_OK;
 }
 
 /*
@@ -4295,7 +4288,6 @@ static enum vxge_hw_status
 __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id)
 {
 	u64 val64;
-	enum vxge_hw_status status = VXGE_HW_OK;
 	struct __vxge_hw_virtualpath *vpath;
 	struct vxge_hw_vpath_reg __iomem *vp_reg;
 	struct vxge_hw_vp_config *config;
@@ -4545,7 +4537,7 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id)
 	val64 |= VXGE_HW_TIM_WRKLD_CLC_CNT_RX_TX(3);
 	writeq(val64, &vp_reg->tim_wrkld_clc);
 
-	return status;
+	return VXGE_HW_OK;
 }
 
 /*
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c b/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c
index f8f073880f8..b07d552a27d 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-ethtool.c
@@ -62,8 +62,8 @@ static int vxge_ethtool_gset(struct net_device *dev, struct ethtool_cmd *info)
 		ethtool_cmd_speed_set(info, SPEED_10000);
 		info->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(info, -1);
-		info->duplex = -1;
+		ethtool_cmd_speed_set(info, SPEED_UNKNOWN);
+		info->duplex = DUPLEX_UNKNOWN;
 	}
 
 	info->autoneg = AUTONEG_DISABLE;
@@ -1128,5 +1128,5 @@ static const struct ethtool_ops vxge_ethtool_ops = {
 
 void vxge_initialize_ethtool_ops(struct net_device *ndev)
 {
-	SET_ETHTOOL_OPS(ndev, &vxge_ethtool_ops);
+	ndev->ethtool_ops = &vxge_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index d107bcbb854..7a0deadd53b 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -2122,7 +2122,7 @@ static int vxge_open_vpaths(struct vxgedev *vdev)
 static void adaptive_coalesce_tx_interrupts(struct vxge_fifo *fifo)
 {
 	fifo->interrupt_count++;
-	if (jiffies > fifo->jiffies + HZ / 100) {
+	if (time_before(fifo->jiffies + HZ / 100, jiffies)) {
 		struct __vxge_hw_fifo *hw_fifo = fifo->handle;
 
 		fifo->jiffies = jiffies;
@@ -2150,7 +2150,7 @@ static void adaptive_coalesce_tx_interrupts(struct vxge_fifo *fifo)
 static void adaptive_coalesce_rx_interrupts(struct vxge_ring *ring)
 {
 	ring->interrupt_count++;
-	if (jiffies > ring->jiffies + HZ / 100) {
+	if (time_before(ring->jiffies + HZ / 100, jiffies)) {
 		struct __vxge_hw_ring *hw_ring = ring->handle;
 
 		ring->jiffies = jiffies;
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index fddb464aeab..9afc536c573 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -406,7 +406,7 @@ union ring_type {
 
 #define NV_RX_DESCRIPTORVALID	(1<<16)
 #define NV_RX_MISSEDFRAME	(1<<17)
-#define NV_RX_SUBSTRACT1	(1<<18)
+#define NV_RX_SUBTRACT1		(1<<18)
 #define NV_RX_ERROR1		(1<<23)
 #define NV_RX_ERROR2		(1<<24)
 #define NV_RX_ERROR3		(1<<25)
@@ -423,7 +423,7 @@ union ring_type {
 #define NV_RX2_CHECKSUM_IP_TCP	(0x14000000)
 #define NV_RX2_CHECKSUM_IP_UDP	(0x18000000)
 #define NV_RX2_DESCRIPTORVALID	(1<<29)
-#define NV_RX2_SUBSTRACT1	(1<<25)
+#define NV_RX2_SUBTRACT1	(1<<25)
 #define NV_RX2_ERROR1		(1<<18)
 #define NV_RX2_ERROR2		(1<<19)
 #define NV_RX2_ERROR3		(1<<20)
@@ -2832,7 +2832,7 @@ static int nv_rx_process(struct net_device *dev, int limit)
 					}
 					/* framing errors are soft errors */
 					else if ((flags & NV_RX_ERROR_MASK) == NV_RX_FRAMINGERR) {
-						if (flags & NV_RX_SUBSTRACT1)
+						if (flags & NV_RX_SUBTRACT1)
 							len--;
 					}
 					/* the rest are hard errors */
@@ -2863,7 +2863,7 @@ static int nv_rx_process(struct net_device *dev, int limit)
 					}
 					/* framing errors are soft errors */
 					else if ((flags & NV_RX2_ERROR_MASK) == NV_RX2_FRAMINGERR) {
-						if (flags & NV_RX2_SUBSTRACT1)
+						if (flags & NV_RX2_SUBTRACT1)
 							len--;
 					}
 					/* the rest are hard errors */
@@ -2937,7 +2937,7 @@ static int nv_rx_process_optimized(struct net_device *dev, int limit)
 				}
 				/* framing errors are soft errors */
 				else if ((flags & NV_RX2_ERROR_MASK) == NV_RX2_FRAMINGERR) {
-					if (flags & NV_RX2_SUBSTRACT1)
+					if (flags & NV_RX2_SUBTRACT1)
 						len--;
 				}
 				/* the rest are hard errors */
@@ -4285,8 +4285,8 @@ static int nv_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
 		if (np->duplex)
 			ecmd->duplex = DUPLEX_FULL;
 	} else {
-		speed = -1;
-		ecmd->duplex = -1;
+		speed = SPEED_UNKNOWN;
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 	ethtool_cmd_speed_set(ecmd, speed);
 	ecmd->autoneg = np->autoneg;
@@ -5766,7 +5766,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 		dev->netdev_ops = &nv_netdev_ops_optimized;
 
 	netif_napi_add(dev, &np->napi, nv_napi_poll, RX_WORK_PER_LOOP);
-	SET_ETHTOOL_OPS(dev, &ops);
+	dev->ethtool_ops = &ops;
 	dev->watchdog_timeo = NV_WATCHDOG_TIMEO;
 
 	pci_set_drvdata(pci_dev, dev);
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 422d9b51ac2..8706c0dbd0c 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1361,7 +1361,7 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
 	__lpc_eth_clock_enable(pldat, true);
 
 	/* Map IO space */
-	pldat->net_base = ioremap(res->start, res->end - res->start + 1);
+	pldat->net_base = ioremap(res->start, resource_size(res));
 	if (!pldat->net_base) {
 		dev_err(&pdev->dev, "failed to map registers\n");
 		ret = -ENOMEM;
@@ -1417,10 +1417,8 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
 	}
 	pldat->dma_buff_base_p = dma_handle;
 
-	netdev_dbg(ndev, "IO address start     :0x%08x\n",
-			res->start);
-	netdev_dbg(ndev, "IO address size      :%d\n",
-			res->end - res->start + 1);
+	netdev_dbg(ndev, "IO address space     :%pR\n", res);
+	netdev_dbg(ndev, "IO address size      :%d\n", resource_size(res));
 	netdev_dbg(ndev, "IO address (mapped)  :0x%p\n",
 			pldat->net_base);
 	netdev_dbg(ndev, "IRQ number           :%d\n", ndev->irq);
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
index a588ffde970..44c8be1c680 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/Kconfig
@@ -4,7 +4,7 @@
 
 config PCH_GBE
 	tristate "OKI SEMICONDUCTOR IOH(ML7223/ML7831) GbE"
-	depends on PCI && (X86 || COMPILE_TEST)
+	depends on PCI && (X86_32 || COMPILE_TEST)
 	select MII
 	select PTP_1588_CLOCK_PCH
 	---help---
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
index 826f0ccdc23..4fe8ea96bd2 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
@@ -91,7 +91,7 @@ static int pch_gbe_get_settings(struct net_device *netdev,
 	ecmd->advertising &= ~(ADVERTISED_TP | ADVERTISED_1000baseT_Half);
 
 	if (!netif_carrier_ok(adapter->netdev))
-		ethtool_cmd_speed_set(ecmd, -1);
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
 	return ret;
 }
 
@@ -508,5 +508,5 @@ static const struct ethtool_ops pch_gbe_ethtool_ops = {
 
 void pch_gbe_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &pch_gbe_ethtool_ops);
+	netdev->ethtool_ops = &pch_gbe_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c
index b6bdeb3c197..9a997e4c3e0 100644
--- a/drivers/net/ethernet/packetengines/hamachi.c
+++ b/drivers/net/ethernet/packetengines/hamachi.c
@@ -724,10 +724,8 @@ static int hamachi_init_one(struct pci_dev *pdev,
 
 	/* The Hamachi-specific entries in the device structure. */
 	dev->netdev_ops = &hamachi_netdev_ops;
-	if (chip_tbl[hmp->chip_id].flags & CanHaveMII)
-		SET_ETHTOOL_OPS(dev, &ethtool_ops);
-	else
-		SET_ETHTOOL_OPS(dev, &ethtool_ops_no_mii);
+	dev->ethtool_ops = (chip_tbl[hmp->chip_id].flags & CanHaveMII) ?
+		&ethtool_ops : &ethtool_ops_no_mii;
 	dev->watchdog_timeo = TX_TIMEOUT;
 	if (mtu)
 		dev->mtu = mtu;
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index 9a6cb482dcd..69a8dc09507 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -472,7 +472,7 @@ static int yellowfin_init_one(struct pci_dev *pdev,
 
 	/* The Yellowfin-specific entries in the device structure. */
 	dev->netdev_ops = &netdev_ops;
-	SET_ETHTOOL_OPS(dev, &ethtool_ops);
+	dev->ethtool_ops = &ethtool_ops;
 	dev->watchdog_timeo = TX_TIMEOUT;
 
 	if (mtu)
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index c14bd3116e4..d49cba12908 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -66,6 +66,17 @@ config QLCNIC_VXLAN
 	  Say Y here if you want to enable hardware offload support for
 	  Virtual eXtensible Local Area Network (VXLAN) in the driver.
 
+config QLCNIC_HWMON
+	bool "QLOGIC QLCNIC 82XX and 83XX family HWMON support"
+	depends on QLCNIC && HWMON && !(QLCNIC=y && HWMON=m)
+	default y
+	---help---
+	  This configuration parameter can be used to read the
+	  board temperature in Converged Ethernet devices
+	  supported by qlcnic.
+
+	  This data is available via the hwmon sysfs interface.
+
 config QLGE
 	tristate "QLogic QLGE 10Gb Ethernet Driver Support"
 	depends on PCI
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index f09c35d669b..5bf05818a12 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -1373,7 +1373,7 @@ netxen_setup_netdev(struct netxen_adapter *adapter,
 
 	netxen_nic_change_mtu(netdev, netdev->mtu);
 
-	SET_ETHTOOL_OPS(netdev, &netxen_nic_ethtool_ops);
+	netdev->ethtool_ops = &netxen_nic_ethtool_ops;
 
 	netdev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
 	                      NETIF_F_RXCSUM;
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 2eabd44f891..b5d6bc1a8b0 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -3838,7 +3838,7 @@ static int ql3xxx_probe(struct pci_dev *pdev,
 
 	/* Set driver entry points */
 	ndev->netdev_ops = &ql3xxx_netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &ql3xxx_ethtool_ops);
+	ndev->ethtool_ops = &ql3xxx_ethtool_ops;
 	ndev->watchdog_timeo = 5 * HZ;
 
 	netif_napi_add(ndev, &qdev->napi, ql_poll, 64);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index f785d01c7d1..be618b9e874 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -39,8 +39,8 @@
 
 #define _QLCNIC_LINUX_MAJOR 5
 #define _QLCNIC_LINUX_MINOR 3
-#define _QLCNIC_LINUX_SUBVERSION 57
-#define QLCNIC_LINUX_VERSIONID  "5.3.57"
+#define _QLCNIC_LINUX_SUBVERSION 60
+#define QLCNIC_LINUX_VERSIONID  "5.3.60"
 #define QLCNIC_DRV_IDC_VER  0x01
 #define QLCNIC_DRIVER_VERSION  ((_QLCNIC_LINUX_MAJOR << 16) |\
 		 (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION))
@@ -441,6 +441,8 @@ struct qlcnic_82xx_dump_template_hdr {
 	u32	rsvd1[0];
 };
 
+#define QLC_PEX_DMA_READ_SIZE	(PAGE_SIZE * 16)
+
 struct qlcnic_fw_dump {
 	u8	clr;	/* flag to indicate if dump is cleared */
 	bool	enable; /* enable/disable dump */
@@ -537,6 +539,7 @@ struct qlcnic_hardware_context {
 	u8 phys_port_id[ETH_ALEN];
 	u8 lb_mode;
 	u16 vxlan_port;
+	struct device *hwmon_dev;
 };
 
 struct qlcnic_adapter_stats {
@@ -1018,6 +1021,8 @@ struct qlcnic_ipaddr {
 #define QLCNIC_DEL_VXLAN_PORT		0x200000
 #endif
 
+#define QLCNIC_VLAN_FILTERING		0x800000
+
 #define QLCNIC_IS_MSI_FAMILY(adapter) \
 	((adapter)->flags & (QLCNIC_MSI_ENABLED | QLCNIC_MSIX_ENABLED))
 #define QLCNIC_IS_TSO_CAPABLE(adapter)  \
@@ -1316,6 +1321,7 @@ struct qlcnic_eswitch {
 #define QL_STATUS_INVALID_PARAM	-1
 
 #define MAX_BW			100	/* % of link speed */
+#define MIN_BW			1	/* % of link speed */
 #define MAX_VLAN_ID		4095
 #define MIN_VLAN_ID		2
 #define DEFAULT_MAC_LEARN	1
@@ -1692,7 +1698,7 @@ int qlcnic_read_mac_addr(struct qlcnic_adapter *);
 int qlcnic_setup_netdev(struct qlcnic_adapter *, struct net_device *, int);
 void qlcnic_set_netdev_features(struct qlcnic_adapter *,
 				struct qlcnic_esw_func_cfg *);
-void qlcnic_sriov_vf_schedule_multi(struct net_device *);
+void qlcnic_sriov_vf_set_multi(struct net_device *);
 int qlcnic_is_valid_nic_func(struct qlcnic_adapter *, u8);
 int qlcnic_get_pci_func_type(struct qlcnic_adapter *, u16, u16 *, u16 *,
 			     u16 *);
@@ -2338,6 +2344,16 @@ static inline bool qlcnic_83xx_vf_check(struct qlcnic_adapter *adapter)
 	return (device == PCI_DEVICE_ID_QLOGIC_VF_QLE834X) ? true : false;
 }
 
+static inline bool qlcnic_sriov_check(struct qlcnic_adapter *adapter)
+{
+	bool status;
+
+	status = (qlcnic_sriov_pf_check(adapter) ||
+		  qlcnic_sriov_vf_check(adapter)) ? true : false;
+
+	return status;
+}
+
 static inline u32 qlcnic_get_vnic_func_count(struct qlcnic_adapter *adapter)
 {
 	if (qlcnic_84xx_check(adapter))
@@ -2345,4 +2361,18 @@ static inline u32 qlcnic_get_vnic_func_count(struct qlcnic_adapter *adapter)
 	else
 		return QLC_DEFAULT_VNIC_COUNT;
 }
+
+#ifdef CONFIG_QLCNIC_HWMON
+void qlcnic_register_hwmon_dev(struct qlcnic_adapter *);
+void qlcnic_unregister_hwmon_dev(struct qlcnic_adapter *);
+#else
+static inline void qlcnic_register_hwmon_dev(struct qlcnic_adapter *adapter)
+{
+	return;
+}
+static inline void qlcnic_unregister_hwmon_dev(struct qlcnic_adapter *adapter)
+{
+	return;
+}
+#endif
 #endif				/* __QLCNIC_H_ */
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index b7cffb46a75..a4a4ec0b68f 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -33,6 +33,7 @@ static void qlcnic_83xx_get_beacon_state(struct qlcnic_adapter *);
 #define RSS_HASHTYPE_IP_TCP		0x3
 #define QLC_83XX_FW_MBX_CMD		0
 #define QLC_SKIP_INACTIVE_PCI_REGS	7
+#define QLC_MAX_LEGACY_FUNC_SUPP	8
 
 static const struct qlcnic_mailbox_metadata qlcnic_83xx_mbx_tbl[] = {
 	{QLCNIC_CMD_CONFIGURE_IP_ADDR, 6, 1},
@@ -357,8 +358,15 @@ int qlcnic_83xx_setup_intr(struct qlcnic_adapter *adapter)
 	if (!ahw->intr_tbl)
 		return -ENOMEM;
 
-	if (!(adapter->flags & QLCNIC_MSIX_ENABLED))
+	if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) {
+		if (adapter->ahw->pci_func >= QLC_MAX_LEGACY_FUNC_SUPP) {
+			dev_err(&adapter->pdev->dev, "PCI function number 8 and higher are not supported with legacy interrupt, func 0x%x\n",
+				ahw->pci_func);
+			return -EOPNOTSUPP;
+		}
+
 		qlcnic_83xx_enable_legacy(adapter);
+	}
 
 	for (i = 0; i < num_msix; i++) {
 		if (adapter->flags & QLCNIC_MSIX_ENABLED)
@@ -879,6 +887,9 @@ int qlcnic_83xx_alloc_mbx_args(struct qlcnic_cmd_args *mbx,
 			return 0;
 		}
 	}
+
+	dev_err(&adapter->pdev->dev, "%s: Invalid mailbox command opcode 0x%x\n",
+		__func__, type);
 	return -EINVAL;
 }
 
@@ -3026,19 +3037,18 @@ void qlcnic_83xx_unlock_driver(struct qlcnic_adapter *adapter)
 	QLCRDX(adapter->ahw, QLC_83XX_DRV_UNLOCK);
 }
 
-int qlcnic_83xx_ms_mem_write128(struct qlcnic_adapter *adapter, u64 addr,
+int qlcnic_ms_mem_write128(struct qlcnic_adapter *adapter, u64 addr,
 				u32 *data, u32 count)
 {
 	int i, j, ret = 0;
 	u32 temp;
-	int err = 0;
 
 	/* Check alignment */
 	if (addr & 0xF)
 		return -EIO;
 
 	mutex_lock(&adapter->ahw->mem_lock);
-	qlcnic_83xx_wrt_reg_indirect(adapter, QLCNIC_MS_ADDR_HI, 0);
+	qlcnic_ind_wr(adapter, QLCNIC_MS_ADDR_HI, 0);
 
 	for (i = 0; i < count; i++, addr += 16) {
 		if (!((ADDR_IN_RANGE(addr, QLCNIC_ADDR_QDR_NET,
@@ -3049,26 +3059,16 @@ int qlcnic_83xx_ms_mem_write128(struct qlcnic_adapter *adapter, u64 addr,
 			return -EIO;
 		}
 
-		qlcnic_83xx_wrt_reg_indirect(adapter, QLCNIC_MS_ADDR_LO, addr);
-		qlcnic_83xx_wrt_reg_indirect(adapter, QLCNIC_MS_WRTDATA_LO,
-					     *data++);
-		qlcnic_83xx_wrt_reg_indirect(adapter, QLCNIC_MS_WRTDATA_HI,
-					     *data++);
-		qlcnic_83xx_wrt_reg_indirect(adapter, QLCNIC_MS_WRTDATA_ULO,
-					     *data++);
-		qlcnic_83xx_wrt_reg_indirect(adapter, QLCNIC_MS_WRTDATA_UHI,
-					     *data++);
-		qlcnic_83xx_wrt_reg_indirect(adapter, QLCNIC_MS_CTRL,
-					     QLCNIC_TA_WRITE_ENABLE);
-		qlcnic_83xx_wrt_reg_indirect(adapter, QLCNIC_MS_CTRL,
-					     QLCNIC_TA_WRITE_START);
+		qlcnic_ind_wr(adapter, QLCNIC_MS_ADDR_LO, addr);
+		qlcnic_ind_wr(adapter, QLCNIC_MS_WRTDATA_LO, *data++);
+		qlcnic_ind_wr(adapter, QLCNIC_MS_WRTDATA_HI, *data++);
+		qlcnic_ind_wr(adapter, QLCNIC_MS_WRTDATA_ULO, *data++);
+		qlcnic_ind_wr(adapter, QLCNIC_MS_WRTDATA_UHI, *data++);
+		qlcnic_ind_wr(adapter, QLCNIC_MS_CTRL, QLCNIC_TA_WRITE_ENABLE);
+		qlcnic_ind_wr(adapter, QLCNIC_MS_CTRL, QLCNIC_TA_WRITE_START);
 
 		for (j = 0; j < MAX_CTL_CHECK; j++) {
-			temp = QLCRD32(adapter, QLCNIC_MS_CTRL, &err);
-			if (err == -EIO) {
-				mutex_unlock(&adapter->ahw->mem_lock);
-				return err;
-			}
+			temp = qlcnic_ind_rd(adapter, QLCNIC_MS_CTRL);
 
 			if ((temp & TA_CTL_BUSY) == 0)
 				break;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
index 88d809c3563..2bf101a47d0 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
@@ -418,7 +418,6 @@ enum qlcnic_83xx_states {
 #define QLC_83XX_GET_FUNC_MODE_FROM_NPAR_INFO(val)	(val & 0x80000000)
 #define QLC_83XX_GET_LRO_CAPABILITY(val)		(val & 0x20)
 #define QLC_83XX_GET_LSO_CAPABILITY(val)		(val & 0x40)
-#define QLC_83XX_GET_LSO_CAPABILITY(val)		(val & 0x40)
 #define QLC_83XX_GET_HW_LRO_CAPABILITY(val)		(val & 0x400)
 #define QLC_83XX_GET_VLAN_ALIGN_CAPABILITY(val)	(val & 0x4000)
 #define QLC_83XX_GET_FW_LRO_MSS_CAPABILITY(val)	(val & 0x20000)
@@ -560,7 +559,7 @@ void qlcnic_83xx_napi_del(struct qlcnic_adapter *);
 void qlcnic_83xx_napi_enable(struct qlcnic_adapter *);
 void qlcnic_83xx_napi_disable(struct qlcnic_adapter *);
 int qlcnic_83xx_config_led(struct qlcnic_adapter *, u32, u32);
-void qlcnic_ind_wr(struct qlcnic_adapter *, u32, u32);
+int qlcnic_ind_wr(struct qlcnic_adapter *, u32, u32);
 int qlcnic_ind_rd(struct qlcnic_adapter *, u32);
 int qlcnic_83xx_create_rx_ctx(struct qlcnic_adapter *);
 int qlcnic_83xx_create_tx_ctx(struct qlcnic_adapter *,
@@ -617,7 +616,6 @@ void qlcnic_83xx_idc_request_reset(struct qlcnic_adapter *, u32);
 int qlcnic_83xx_lock_driver(struct qlcnic_adapter *);
 void qlcnic_83xx_unlock_driver(struct qlcnic_adapter *);
 int qlcnic_83xx_set_default_offload_settings(struct qlcnic_adapter *);
-int qlcnic_83xx_ms_mem_write128(struct qlcnic_adapter *, u64, u32 *, u32);
 int qlcnic_83xx_idc_vnic_pf_entry(struct qlcnic_adapter *);
 int qlcnic_83xx_disable_vnic_mode(struct qlcnic_adapter *, int);
 int qlcnic_83xx_config_vnic_opmode(struct qlcnic_adapter *);
@@ -659,4 +657,5 @@ void qlcnic_83xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *);
 u32 qlcnic_83xx_get_cap_size(void *, int);
 void qlcnic_83xx_set_sys_info(void *, int, u32);
 void qlcnic_83xx_store_cap_mask(void *, u32);
+int qlcnic_ms_mem_write128(struct qlcnic_adapter *, u64, u32 *, u32);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index ba20c721ee9..f33559b7252 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -1363,8 +1363,8 @@ static int qlcnic_83xx_copy_bootloader(struct qlcnic_adapter *adapter)
 		return ret;
 	}
 	/* 16 byte write to MS memory */
-	ret = qlcnic_83xx_ms_mem_write128(adapter, dest, (u32 *)p_cache,
-					  size / 16);
+	ret = qlcnic_ms_mem_write128(adapter, dest, (u32 *)p_cache,
+				     size / 16);
 	if (ret) {
 		vfree(p_cache);
 		return ret;
@@ -1389,8 +1389,8 @@ static int qlcnic_83xx_copy_fw_file(struct qlcnic_adapter *adapter)
 	p_cache = (u32 *)fw->data;
 	addr = (u64)dest;
 
-	ret = qlcnic_83xx_ms_mem_write128(adapter, addr,
-					  p_cache, size / 16);
+	ret = qlcnic_ms_mem_write128(adapter, addr,
+				     p_cache, size / 16);
 	if (ret) {
 		dev_err(&adapter->pdev->dev, "MS memory write failed\n");
 		release_firmware(fw);
@@ -1405,8 +1405,8 @@ static int qlcnic_83xx_copy_fw_file(struct qlcnic_adapter *adapter)
 			data[i] = fw->data[size + i];
 		for (; i < 16; i++)
 			data[i] = 0;
-		ret = qlcnic_83xx_ms_mem_write128(adapter, addr,
-						  (u32 *)data, 1);
+		ret = qlcnic_ms_mem_write128(adapter, addr,
+					     (u32 *)data, 1);
 		if (ret) {
 			dev_err(&adapter->pdev->dev,
 				"MS memory write failed\n");
@@ -2181,6 +2181,8 @@ int qlcnic_83xx_configure_opmode(struct qlcnic_adapter *adapter)
 		max_sds_rings = QLCNIC_MAX_SDS_RINGS;
 		max_tx_rings = QLCNIC_MAX_TX_RINGS;
 	} else {
+		dev_err(&adapter->pdev->dev, "%s: Invalid opmode %d\n",
+			__func__, ret);
 		return -EIO;
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c
index c1e11f5715b..304e247bdf3 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c
@@ -1027,8 +1027,11 @@ int qlcnic_config_port_mirroring(struct qlcnic_adapter *adapter, u8 id,
 	u32 arg1;
 
 	if (adapter->ahw->op_mode != QLCNIC_MGMT_FUNC ||
-	    !(adapter->eswitch[id].flags & QLCNIC_SWITCH_ENABLE))
+	    !(adapter->eswitch[id].flags & QLCNIC_SWITCH_ENABLE)) {
+		dev_err(&adapter->pdev->dev, "%s: Not a management function\n",
+			__func__);
 		return err;
+	}
 
 	arg1 = id | (enable_mirroring ? BIT_4 : 0);
 	arg1 |= pci_func << 8;
@@ -1318,8 +1321,12 @@ int qlcnic_config_switch_port(struct qlcnic_adapter *adapter,
 	u32 arg1, arg2 = 0;
 	u8 pci_func;
 
-	if (adapter->ahw->op_mode != QLCNIC_MGMT_FUNC)
+	if (adapter->ahw->op_mode != QLCNIC_MGMT_FUNC) {
+		dev_err(&adapter->pdev->dev, "%s: Not a management function\n",
+			__func__);
 		return err;
+	}
+
 	pci_func = esw_cfg->pci_func;
 	index = qlcnic_is_valid_nic_func(adapter, pci_func);
 	if (index < 0)
@@ -1363,6 +1370,8 @@ int qlcnic_config_switch_port(struct qlcnic_adapter *adapter,
 			arg1 &= ~(0x0ffff << 16);
 			break;
 	default:
+		dev_err(&adapter->pdev->dev, "%s: Invalid opmode 0x%x\n",
+			__func__, esw_cfg->op_mode);
 		return err;
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 5bacf5210ae..1b7f3dbae28 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -726,6 +726,11 @@ static int qlcnic_set_channels(struct net_device *dev,
 	struct qlcnic_adapter *adapter = netdev_priv(dev);
 	int err;
 
+	if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) {
+		netdev_err(dev, "No RSS/TSS support in non MSI-X mode\n");
+		return -EINVAL;
+	}
+
 	if (channel->other_count || channel->combined_count)
 		return -EINVAL;
 
@@ -734,7 +739,7 @@ static int qlcnic_set_channels(struct net_device *dev,
 	if (err)
 		return err;
 
-	if (channel->rx_count) {
+	if (adapter->drv_sds_rings != channel->rx_count) {
 		err = qlcnic_validate_rings(adapter, channel->rx_count,
 					    QLCNIC_RX_QUEUE);
 		if (err) {
@@ -745,7 +750,7 @@ static int qlcnic_set_channels(struct net_device *dev,
 		adapter->drv_rss_rings = channel->rx_count;
 	}
 
-	if (channel->tx_count) {
+	if (adapter->drv_tx_rings != channel->tx_count) {
 		err = qlcnic_validate_rings(adapter, channel->tx_count,
 					    QLCNIC_TX_QUEUE);
 		if (err) {
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
index 9f3adf4e70b..851cb4a80d5 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
@@ -373,12 +373,16 @@ int qlcnic_ind_rd(struct qlcnic_adapter *adapter, u32 addr)
 	return data;
 }
 
-void qlcnic_ind_wr(struct qlcnic_adapter *adapter, u32 addr, u32 data)
+int qlcnic_ind_wr(struct qlcnic_adapter *adapter, u32 addr, u32 data)
 {
+	int ret = 0;
+
 	if (qlcnic_82xx_check(adapter))
 		qlcnic_write_window_reg(addr, adapter->ahw->pci_base0, data);
 	else
-		qlcnic_83xx_wrt_reg_indirect(adapter, addr, data);
+		ret = qlcnic_83xx_wrt_reg_indirect(adapter, addr, data);
+
+	return ret;
 }
 
 static int
@@ -567,28 +571,14 @@ static void __qlcnic_set_multi(struct net_device *netdev, u16 vlan)
 void qlcnic_set_multi(struct net_device *netdev)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
-	struct qlcnic_mac_vlan_list *cur;
-	struct netdev_hw_addr *ha;
-	size_t temp;
 
 	if (!test_bit(__QLCNIC_FW_ATTACHED, &adapter->state))
 		return;
-	if (qlcnic_sriov_vf_check(adapter)) {
-		if (!netdev_mc_empty(netdev)) {
-			netdev_for_each_mc_addr(ha, netdev) {
-				temp = sizeof(struct qlcnic_mac_vlan_list);
-				cur = kzalloc(temp, GFP_ATOMIC);
-				if (cur == NULL)
-					break;
-				memcpy(cur->mac_addr,
-				       ha->addr, ETH_ALEN);
-				list_add_tail(&cur->list, &adapter->vf_mc_list);
-			}
-		}
-		qlcnic_sriov_vf_schedule_multi(adapter->netdev);
-		return;
-	}
-	__qlcnic_set_multi(netdev, 0);
+
+	if (qlcnic_sriov_vf_check(adapter))
+		qlcnic_sriov_vf_set_multi(netdev);
+	else
+		__qlcnic_set_multi(netdev, 0);
 }
 
 int qlcnic_82xx_nic_set_promisc(struct qlcnic_adapter *adapter, u32 mode)
@@ -630,7 +620,7 @@ void qlcnic_prune_lb_filters(struct qlcnic_adapter *adapter)
 	struct hlist_node *n;
 	struct hlist_head *head;
 	int i;
-	unsigned long time;
+	unsigned long expires;
 	u8 cmd;
 
 	for (i = 0; i < adapter->fhash.fbucket_size; i++) {
@@ -638,8 +628,8 @@ void qlcnic_prune_lb_filters(struct qlcnic_adapter *adapter)
 		hlist_for_each_entry_safe(tmp_fil, n, head, fnode) {
 			cmd =  tmp_fil->vlan_id ? QLCNIC_MAC_VLAN_DEL :
 						  QLCNIC_MAC_DEL;
-			time = tmp_fil->ftime;
-			if (jiffies > (QLCNIC_FILTER_AGE * HZ + time)) {
+			expires = tmp_fil->ftime + QLCNIC_FILTER_AGE * HZ;
+			if (time_before(expires, jiffies)) {
 				qlcnic_sre_macaddr_change(adapter,
 							  tmp_fil->faddr,
 							  tmp_fil->vlan_id,
@@ -657,8 +647,8 @@ void qlcnic_prune_lb_filters(struct qlcnic_adapter *adapter)
 
 		hlist_for_each_entry_safe(tmp_fil, n, head, fnode)
 		{
-			time = tmp_fil->ftime;
-			if (jiffies > (QLCNIC_FILTER_AGE * HZ + time)) {
+			expires = tmp_fil->ftime + QLCNIC_FILTER_AGE * HZ;
+			if (time_before(expires, jiffies)) {
 				spin_lock_bh(&adapter->rx_mac_learn_lock);
 				adapter->rx_fhash.fnum--;
 				hlist_del(&tmp_fil->fnode);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 173b3d12991..e45bf09af0c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -305,7 +305,6 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter,
 {
 	struct vlan_ethhdr *vh = (struct vlan_ethhdr *)(skb->data);
 	struct ethhdr *phdr = (struct ethhdr *)(skb->data);
-	struct net_device *netdev = adapter->netdev;
 	u16 protocol = ntohs(skb->protocol);
 	struct qlcnic_filter *fil, *tmp_fil;
 	struct hlist_head *head;
@@ -314,27 +313,16 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter,
 	u16 vlan_id = 0;
 	u8 hindex, hval;
 
-	if (!qlcnic_sriov_pf_check(adapter)) {
-		if (ether_addr_equal(phdr->h_source, adapter->mac_addr))
-			return;
-	} else {
+	if (ether_addr_equal(phdr->h_source, adapter->mac_addr))
+		return;
+
+	if (adapter->flags & QLCNIC_VLAN_FILTERING) {
 		if (protocol == ETH_P_8021Q) {
 			vh = (struct vlan_ethhdr *)skb->data;
 			vlan_id = ntohs(vh->h_vlan_TCI);
 		} else if (vlan_tx_tag_present(skb)) {
 			vlan_id = vlan_tx_tag_get(skb);
 		}
-
-		if (ether_addr_equal(phdr->h_source, adapter->mac_addr) &&
-		    !vlan_id)
-			return;
-	}
-
-	if (adapter->fhash.fnum >= adapter->fhash.fmax) {
-		adapter->stats.mac_filter_limit_overrun++;
-		netdev_info(netdev, "Can not add more than %d mac-vlan filters, configured %d\n",
-			    adapter->fhash.fmax, adapter->fhash.fnum);
-		return;
 	}
 
 	memcpy(&src_addr, phdr->h_source, ETH_ALEN);
@@ -353,6 +341,11 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter,
 		}
 	}
 
+	if (unlikely(adapter->fhash.fnum >= adapter->fhash.fmax)) {
+		adapter->stats.mac_filter_limit_overrun++;
+		return;
+	}
+
 	fil = kzalloc(sizeof(struct qlcnic_filter), GFP_ATOMIC);
 	if (!fil)
 		return;
@@ -1216,8 +1209,7 @@ qlcnic_process_rcv(struct qlcnic_adapter *adapter,
 	if (!skb)
 		return buffer;
 
-	if (adapter->drv_mac_learn &&
-	    (adapter->flags & QLCNIC_ESWITCH_ENABLED)) {
+	if (adapter->rx_mac_learn) {
 		t_vid = 0;
 		is_lb_pkt = qlcnic_82xx_is_lb_pkt(sts_data0);
 		qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, t_vid);
@@ -1293,8 +1285,7 @@ qlcnic_process_lro(struct qlcnic_adapter *adapter,
 	if (!skb)
 		return buffer;
 
-	if (adapter->drv_mac_learn &&
-	    (adapter->flags & QLCNIC_ESWITCH_ENABLED)) {
+	if (adapter->rx_mac_learn) {
 		t_vid = 0;
 		is_lb_pkt = qlcnic_82xx_is_lb_pkt(sts_data0);
 		qlcnic_add_lb_filter(adapter, skb, is_lb_pkt, t_vid);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 7e55e88a81b..4fc186713b6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -378,7 +378,8 @@ static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 	if (!adapter->fdb_mac_learn)
 		return ndo_dflt_fdb_del(ndm, tb, netdev, addr);
 
-	if (adapter->flags & QLCNIC_ESWITCH_ENABLED) {
+	if ((adapter->flags & QLCNIC_ESWITCH_ENABLED) ||
+	    qlcnic_sriov_check(adapter)) {
 		if (is_unicast_ether_addr(addr)) {
 			err = dev_uc_del(netdev, addr);
 			if (!err)
@@ -402,7 +403,8 @@ static int qlcnic_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	if (!adapter->fdb_mac_learn)
 		return ndo_dflt_fdb_add(ndm, tb, netdev, addr, flags);
 
-	if (!(adapter->flags & QLCNIC_ESWITCH_ENABLED)) {
+	if (!(adapter->flags & QLCNIC_ESWITCH_ENABLED) &&
+	    !qlcnic_sriov_check(adapter)) {
 		pr_info("%s: FDB e-switch is not enabled\n", __func__);
 		return -EOPNOTSUPP;
 	}
@@ -432,7 +434,8 @@ static int qlcnic_fdb_dump(struct sk_buff *skb, struct netlink_callback *ncb,
 	if (!adapter->fdb_mac_learn)
 		return ndo_dflt_fdb_dump(skb, ncb, netdev, idx);
 
-	if (adapter->flags & QLCNIC_ESWITCH_ENABLED)
+	if ((adapter->flags & QLCNIC_ESWITCH_ENABLED) ||
+	    qlcnic_sriov_check(adapter))
 		idx = ndo_dflt_fdb_dump(skb, ncb, netdev, idx);
 
 	return idx;
@@ -522,7 +525,7 @@ static const struct net_device_ops qlcnic_netdev_ops = {
 #endif
 #ifdef CONFIG_QLCNIC_SRIOV
 	.ndo_set_vf_mac		= qlcnic_sriov_set_vf_mac,
-	.ndo_set_vf_tx_rate	= qlcnic_sriov_set_vf_tx_rate,
+	.ndo_set_vf_rate	= qlcnic_sriov_set_vf_tx_rate,
 	.ndo_get_vf_config	= qlcnic_sriov_get_vf_config,
 	.ndo_set_vf_vlan	= qlcnic_sriov_set_vf_vlan,
 	.ndo_set_vf_spoofchk	= qlcnic_sriov_set_vf_spoofchk,
@@ -690,10 +693,10 @@ int qlcnic_setup_tss_rss_intr(struct qlcnic_adapter *adapter)
 		adapter->msix_entries[vector].entry = vector;
 
 restore:
-	err = pci_enable_msix(pdev, adapter->msix_entries, num_msix);
-	if (err > 0) {
+	err = pci_enable_msix_exact(pdev, adapter->msix_entries, num_msix);
+	if (err == -ENOSPC) {
 		if (!adapter->drv_tss_rings && !adapter->drv_rss_rings)
-			return -ENOSPC;
+			return err;
 
 		netdev_info(adapter->netdev,
 			    "Unable to allocate %d MSI-X vectors, Available vectors %d\n",
@@ -1014,6 +1017,8 @@ int qlcnic_init_pci_info(struct qlcnic_adapter *adapter)
 
 		if (pfn >= ahw->max_vnic_func) {
 			ret = QL_STATUS_INVALID_PARAM;
+			dev_err(&adapter->pdev->dev, "%s: Invalid function 0x%x, max 0x%x\n",
+				__func__, pfn, ahw->max_vnic_func);
 			goto err_eswitch;
 		}
 
@@ -1915,8 +1920,6 @@ void __qlcnic_down(struct qlcnic_adapter *adapter, struct net_device *netdev)
 	if (!test_and_clear_bit(__QLCNIC_DEV_UP, &adapter->state))
 		return;
 
-	if (qlcnic_sriov_vf_check(adapter))
-		qlcnic_sriov_cleanup_async_list(&adapter->ahw->sriov->bc);
 	smp_mb();
 	netif_carrier_off(netdev);
 	adapter->ahw->linkup = 0;
@@ -1928,6 +1931,8 @@ void __qlcnic_down(struct qlcnic_adapter *adapter, struct net_device *netdev)
 		qlcnic_delete_lb_filters(adapter);
 
 	qlcnic_nic_set_promisc(adapter, QLCNIC_NIU_NON_PROMISC_MODE);
+	if (qlcnic_sriov_vf_check(adapter))
+		qlcnic_sriov_cleanup_async_list(&adapter->ahw->sriov->bc);
 
 	qlcnic_napi_disable(adapter);
 
@@ -2052,6 +2057,7 @@ out:
 
 static int qlcnic_alloc_adapter_resources(struct qlcnic_adapter *adapter)
 {
+	struct qlcnic_hardware_context *ahw = adapter->ahw;
 	int err = 0;
 
 	adapter->recv_ctx = kzalloc(sizeof(struct qlcnic_recv_context),
@@ -2061,6 +2067,18 @@ static int qlcnic_alloc_adapter_resources(struct qlcnic_adapter *adapter)
 		goto err_out;
 	}
 
+	if (qlcnic_83xx_check(adapter)) {
+		ahw->coal.type = QLCNIC_INTR_COAL_TYPE_RX_TX;
+		ahw->coal.tx_time_us = QLCNIC_DEF_INTR_COALESCE_TX_TIME_US;
+		ahw->coal.tx_packets = QLCNIC_DEF_INTR_COALESCE_TX_PACKETS;
+		ahw->coal.rx_time_us = QLCNIC_DEF_INTR_COALESCE_RX_TIME_US;
+		ahw->coal.rx_packets = QLCNIC_DEF_INTR_COALESCE_RX_PACKETS;
+	} else {
+		ahw->coal.type = QLCNIC_INTR_COAL_TYPE_RX;
+		ahw->coal.rx_time_us = QLCNIC_DEF_INTR_COALESCE_RX_TIME_US;
+		ahw->coal.rx_packets = QLCNIC_DEF_INTR_COALESCE_RX_PACKETS;
+	}
+
 	/* clear stats */
 	memset(&adapter->stats, 0, sizeof(adapter->stats));
 err_out:
@@ -2069,12 +2087,20 @@ err_out:
 
 static void qlcnic_free_adapter_resources(struct qlcnic_adapter *adapter)
 {
+	struct qlcnic_fw_dump *fw_dump = &adapter->ahw->fw_dump;
+
 	kfree(adapter->recv_ctx);
 	adapter->recv_ctx = NULL;
 
-	if (adapter->ahw->fw_dump.tmpl_hdr) {
-		vfree(adapter->ahw->fw_dump.tmpl_hdr);
-		adapter->ahw->fw_dump.tmpl_hdr = NULL;
+	if (fw_dump->tmpl_hdr) {
+		vfree(fw_dump->tmpl_hdr);
+		fw_dump->tmpl_hdr = NULL;
+	}
+
+	if (fw_dump->dma_buffer) {
+		dma_free_coherent(&adapter->pdev->dev, QLC_PEX_DMA_READ_SIZE,
+				  fw_dump->dma_buffer, fw_dump->phys_addr);
+		fw_dump->dma_buffer = NULL;
 	}
 
 	kfree(adapter->ahw->reset.buff);
@@ -2247,10 +2273,8 @@ qlcnic_setup_netdev(struct qlcnic_adapter *adapter, struct net_device *netdev,
 
 	qlcnic_change_mtu(netdev, netdev->mtu);
 
-	if (qlcnic_sriov_vf_check(adapter))
-		SET_ETHTOOL_OPS(netdev, &qlcnic_sriov_vf_ethtool_ops);
-	else
-		SET_ETHTOOL_OPS(netdev, &qlcnic_ethtool_ops);
+	netdev->ethtool_ops = (qlcnic_sriov_vf_check(adapter)) ?
+		&qlcnic_sriov_vf_ethtool_ops : &qlcnic_ethtool_ops;
 
 	netdev->features |= (NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 			     NETIF_F_IPV6_CSUM | NETIF_F_GRO |
@@ -2417,9 +2441,6 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	int err, pci_using_dac = -1;
 	char board_name[QLCNIC_MAX_BOARD_NAME_LEN + 19]; /* MAC + ": " + name */
 
-	if (pdev->is_virtfn)
-		return -ENODEV;
-
 	err = pci_enable_device(pdev);
 	if (err)
 		return err;
@@ -2552,9 +2573,11 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			case -ENOMEM:
 				dev_err(&pdev->dev, "Adapter initialization failed. Please reboot\n");
 				goto err_out_free_hw;
+			case -EOPNOTSUPP:
+				dev_err(&pdev->dev, "Adapter initialization failed\n");
+				goto err_out_free_hw;
 			default:
-				dev_err(&pdev->dev, "Adapter initialization failed. A reboot may be required to recover from this failure\n");
-				dev_err(&pdev->dev, "If reboot does not help to recover from this failure, try a flash update of the adapter\n");
+				dev_err(&pdev->dev, "Adapter initialization failed. Driver will load in maintenance mode to recover the adapter using the application\n");
 				goto err_out_maintenance_mode;
 			}
 		}
@@ -2628,7 +2651,7 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		qlcnic_alloc_lb_filters_mem(adapter);
 
 	qlcnic_add_sysfs(adapter);
-
+	qlcnic_register_hwmon_dev(adapter);
 	return 0;
 
 err_out_disable_mbx_intr:
@@ -2665,7 +2688,7 @@ err_out_disable_pdev:
 err_out_maintenance_mode:
 	set_bit(__QLCNIC_MAINTENANCE_MODE, &adapter->state);
 	netdev->netdev_ops = &qlcnic_netdev_failed_ops;
-	SET_ETHTOOL_OPS(netdev, &qlcnic_ethtool_failed_ops);
+	netdev->ethtool_ops = &qlcnic_ethtool_failed_ops;
 	ahw->port_type = QLCNIC_XGBE;
 
 	if (qlcnic_83xx_check(adapter))
@@ -2698,9 +2721,9 @@ static void qlcnic_remove(struct pci_dev *pdev)
 		return;
 
 	netdev = adapter->netdev;
-	qlcnic_sriov_pf_disable(adapter);
 
 	qlcnic_cancel_idc_work(adapter);
+	qlcnic_sriov_pf_disable(adapter);
 	ahw = adapter->ahw;
 
 	unregister_netdev(netdev);
@@ -2735,6 +2758,8 @@ static void qlcnic_remove(struct pci_dev *pdev)
 
 	qlcnic_remove_sysfs(adapter);
 
+	qlcnic_unregister_hwmon_dev(adapter);
+
 	qlcnic_cleanup_pci_map(adapter->ahw);
 
 	qlcnic_release_firmware(adapter);
@@ -2828,6 +2853,8 @@ static int qlcnic_close(struct net_device *netdev)
 	return 0;
 }
 
+#define QLCNIC_VF_LB_BUCKET_SIZE 1
+
 void qlcnic_alloc_lb_filters_mem(struct qlcnic_adapter *adapter)
 {
 	void *head;
@@ -2843,7 +2870,10 @@ void qlcnic_alloc_lb_filters_mem(struct qlcnic_adapter *adapter)
 	spin_lock_init(&adapter->mac_learn_lock);
 	spin_lock_init(&adapter->rx_mac_learn_lock);
 
-	if (qlcnic_82xx_check(adapter)) {
+	if (qlcnic_sriov_vf_check(adapter)) {
+		filter_size = QLCNIC_83XX_SRIOV_VF_MAX_MAC - 1;
+		adapter->fhash.fbucket_size = QLCNIC_VF_LB_BUCKET_SIZE;
+	} else if (qlcnic_82xx_check(adapter)) {
 		filter_size = QLCNIC_LB_MAX_FILTERS;
 		adapter->fhash.fbucket_size = QLCNIC_LB_BUCKET_SIZE;
 	} else {
@@ -3973,16 +4003,6 @@ int qlcnic_validate_rings(struct qlcnic_adapter *adapter, __u32 ring_cnt,
 		strcpy(buf, "Tx");
 	}
 
-	if (!QLCNIC_IS_MSI_FAMILY(adapter)) {
-		netdev_err(netdev, "No RSS/TSS support in INT-x mode\n");
-		return -EINVAL;
-	}
-
-	if (adapter->flags & QLCNIC_MSI_ENABLED) {
-		netdev_err(netdev, "No RSS/TSS support in MSI mode\n");
-		return -EINVAL;
-	}
-
 	if (!is_power_of_2(ring_cnt)) {
 		netdev_err(netdev, "%s rings value should be a power of 2\n",
 			   buf);
@@ -4122,7 +4142,7 @@ void qlcnic_restore_indev_addr(struct net_device *netdev, unsigned long event)
 
 	rcu_read_lock();
 	for_each_set_bit(vid, adapter->vlans, VLAN_N_VID) {
-		dev = __vlan_find_dev_deep(netdev, htons(ETH_P_8021Q), vid);
+		dev = __vlan_find_dev_deep_rcu(netdev, htons(ETH_P_8021Q), vid);
 		if (!dev)
 			continue;
 		qlcnic_config_indev_addr(adapter, dev, event);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
index 37b979b1266..e46fc39d425 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c
@@ -238,6 +238,8 @@ void qlcnic_82xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *fw_dump)
 
 	hdr->drv_cap_mask = hdr->cap_mask;
 	fw_dump->cap_mask = hdr->cap_mask;
+
+	fw_dump->use_pex_dma = (hdr->capabilities & BIT_0) ? true : false;
 }
 
 inline u32 qlcnic_82xx_get_cap_size(void *t_hdr, int index)
@@ -276,6 +278,8 @@ inline void qlcnic_83xx_set_saved_state(void *t_hdr, u32 index,
 	hdr->saved_state[index] = value;
 }
 
+#define QLCNIC_TEMPLATE_VERSION (0x20001)
+
 void qlcnic_83xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *fw_dump)
 {
 	struct qlcnic_83xx_dump_template_hdr *hdr;
@@ -288,6 +292,9 @@ void qlcnic_83xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *fw_dump)
 
 	hdr->drv_cap_mask = hdr->cap_mask;
 	fw_dump->cap_mask = hdr->cap_mask;
+
+	fw_dump->use_pex_dma = (fw_dump->version & 0xfffff) >=
+			       QLCNIC_TEMPLATE_VERSION;
 }
 
 inline u32 qlcnic_83xx_get_cap_size(void *t_hdr, int index)
@@ -653,34 +660,31 @@ out:
 #define QLC_DMA_CMD_BUFF_ADDR_HI	4
 #define QLC_DMA_CMD_STATUS_CTRL		8
 
-#define QLC_PEX_DMA_READ_SIZE		(PAGE_SIZE * 16)
-
 static int qlcnic_start_pex_dma(struct qlcnic_adapter *adapter,
 				struct __mem *mem)
 {
-	struct qlcnic_83xx_dump_template_hdr *tmpl_hdr;
 	struct device *dev = &adapter->pdev->dev;
 	u32 dma_no, dma_base_addr, temp_addr;
 	int i, ret, dma_sts;
+	void *tmpl_hdr;
 
 	tmpl_hdr = adapter->ahw->fw_dump.tmpl_hdr;
-	dma_no = tmpl_hdr->saved_state[QLC_83XX_DMA_ENGINE_INDEX];
+	dma_no = qlcnic_get_saved_state(adapter, tmpl_hdr,
+					QLC_83XX_DMA_ENGINE_INDEX);
 	dma_base_addr = QLC_DMA_REG_BASE_ADDR(dma_no);
 
 	temp_addr = dma_base_addr + QLC_DMA_CMD_BUFF_ADDR_LOW;
-	ret = qlcnic_83xx_wrt_reg_indirect(adapter, temp_addr,
-					   mem->desc_card_addr);
+	ret = qlcnic_ind_wr(adapter, temp_addr, mem->desc_card_addr);
 	if (ret)
 		return ret;
 
 	temp_addr = dma_base_addr + QLC_DMA_CMD_BUFF_ADDR_HI;
-	ret = qlcnic_83xx_wrt_reg_indirect(adapter, temp_addr, 0);
+	ret = qlcnic_ind_wr(adapter, temp_addr, 0);
 	if (ret)
 		return ret;
 
 	temp_addr = dma_base_addr + QLC_DMA_CMD_STATUS_CTRL;
-	ret = qlcnic_83xx_wrt_reg_indirect(adapter, temp_addr,
-					   mem->start_dma_cmd);
+	ret = qlcnic_ind_wr(adapter, temp_addr, mem->start_dma_cmd);
 	if (ret)
 		return ret;
 
@@ -710,15 +714,16 @@ static u32 qlcnic_read_memory_pexdma(struct qlcnic_adapter *adapter,
 	struct qlcnic_fw_dump *fw_dump = &adapter->ahw->fw_dump;
 	u32 temp, dma_base_addr, size = 0, read_size = 0;
 	struct qlcnic_pex_dma_descriptor *dma_descr;
-	struct qlcnic_83xx_dump_template_hdr *tmpl_hdr;
 	struct device *dev = &adapter->pdev->dev;
 	dma_addr_t dma_phys_addr;
 	void *dma_buffer;
+	void *tmpl_hdr;
 
 	tmpl_hdr = fw_dump->tmpl_hdr;
 
 	/* Check if DMA engine is available */
-	temp = tmpl_hdr->saved_state[QLC_83XX_DMA_ENGINE_INDEX];
+	temp = qlcnic_get_saved_state(adapter, tmpl_hdr,
+				      QLC_83XX_DMA_ENGINE_INDEX);
 	dma_base_addr = QLC_DMA_REG_BASE_ADDR(temp);
 	temp = qlcnic_ind_rd(adapter,
 			     dma_base_addr + QLC_DMA_CMD_STATUS_CTRL);
@@ -764,8 +769,8 @@ static u32 qlcnic_read_memory_pexdma(struct qlcnic_adapter *adapter,
 
 		/* Write DMA descriptor to MS memory*/
 		temp = sizeof(struct qlcnic_pex_dma_descriptor) / 16;
-		*ret = qlcnic_83xx_ms_mem_write128(adapter, mem->desc_card_addr,
-						   (u32 *)dma_descr, temp);
+		*ret = qlcnic_ms_mem_write128(adapter, mem->desc_card_addr,
+					      (u32 *)dma_descr, temp);
 		if (*ret) {
 			dev_info(dev, "Failed to write DMA descriptor to MS memory at address 0x%x\n",
 				 mem->desc_card_addr);
@@ -1141,8 +1146,6 @@ free_mem:
 	return err;
 }
 
-#define QLCNIC_TEMPLATE_VERSION (0x20001)
-
 int qlcnic_fw_cmd_get_minidump_temp(struct qlcnic_adapter *adapter)
 {
 	struct qlcnic_hardware_context *ahw;
@@ -1150,6 +1153,7 @@ int qlcnic_fw_cmd_get_minidump_temp(struct qlcnic_adapter *adapter)
 	u32 version, csum, *tmp_buf;
 	u8 use_flash_temp = 0;
 	u32 temp_size = 0;
+	void *temp_buffer;
 	int err;
 
 	ahw = adapter->ahw;
@@ -1199,16 +1203,23 @@ flash_temp:
 
 	qlcnic_cache_tmpl_hdr_values(adapter, fw_dump);
 
+	if (fw_dump->use_pex_dma) {
+		fw_dump->dma_buffer = NULL;
+		temp_buffer = dma_alloc_coherent(&adapter->pdev->dev,
+						 QLC_PEX_DMA_READ_SIZE,
+						 &fw_dump->phys_addr,
+						 GFP_KERNEL);
+		if (!temp_buffer)
+			fw_dump->use_pex_dma = false;
+		else
+			fw_dump->dma_buffer = temp_buffer;
+	}
+
+
 	dev_info(&adapter->pdev->dev,
 		 "Default minidump capture mask 0x%x\n",
 		 fw_dump->cap_mask);
 
-	if (qlcnic_83xx_check(adapter) &&
-	    (fw_dump->version & 0xfffff) >= QLCNIC_TEMPLATE_VERSION)
-		fw_dump->use_pex_dma = true;
-	else
-		fw_dump->use_pex_dma = false;
-
 	qlcnic_enable_fw_dump_state(adapter);
 
 	return 0;
@@ -1224,7 +1235,7 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter)
 	struct device *dev = &adapter->pdev->dev;
 	struct qlcnic_hardware_context *ahw;
 	struct qlcnic_dump_entry *entry;
-	void *temp_buffer, *tmpl_hdr;
+	void *tmpl_hdr;
 	u32 ocm_window;
 	__le32 *buffer;
 	char mesg[64];
@@ -1268,16 +1279,6 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter)
 	qlcnic_set_sys_info(adapter, tmpl_hdr, 0, QLCNIC_DRIVER_VERSION);
 	qlcnic_set_sys_info(adapter, tmpl_hdr, 1, adapter->fw_version);
 
-	if (fw_dump->use_pex_dma) {
-		temp_buffer = dma_alloc_coherent(dev, QLC_PEX_DMA_READ_SIZE,
-						 &fw_dump->phys_addr,
-						 GFP_KERNEL);
-		if (!temp_buffer)
-			fw_dump->use_pex_dma = false;
-		else
-			fw_dump->dma_buffer = temp_buffer;
-	}
-
 	if (qlcnic_82xx_check(adapter)) {
 		ops_cnt = ARRAY_SIZE(qlcnic_fw_dump_ops);
 		fw_dump_ops = qlcnic_fw_dump_ops;
@@ -1335,10 +1336,6 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter)
 	/* Send a udev event to notify availability of FW dump */
 	kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, msg);
 
-	if (fw_dump->use_pex_dma)
-		dma_free_coherent(dev, QLC_PEX_DMA_READ_SIZE,
-				  fw_dump->dma_buffer, fw_dump->phys_addr);
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h
index 396bd1fd1d2..4677b2edccc 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h
@@ -52,6 +52,7 @@ enum qlcnic_bc_commands {
 	QLCNIC_BC_CMD_CFG_GUEST_VLAN = 0x3,
 };
 
+#define QLCNIC_83XX_SRIOV_VF_MAX_MAC 2
 #define QLC_BC_CMD 1
 
 struct qlcnic_trans_list {
@@ -151,13 +152,14 @@ struct qlcnic_vf_info {
 	struct qlcnic_trans_list	rcv_pend;
 	struct qlcnic_adapter		*adapter;
 	struct qlcnic_vport		*vp;
-	struct mutex			vlan_list_lock;	/* Lock for VLAN list */
+	spinlock_t			vlan_list_lock;	/* Lock for VLAN list */
 };
 
 struct qlcnic_async_work_list {
 	struct list_head	list;
 	struct work_struct	work;
 	void			*ptr;
+	struct qlcnic_cmd_args	*cmd;
 };
 
 struct qlcnic_back_channel {
@@ -231,7 +233,7 @@ bool qlcnic_sriov_soft_flr_check(struct qlcnic_adapter *,
 void qlcnic_sriov_pf_reset(struct qlcnic_adapter *);
 int qlcnic_sriov_pf_reinit(struct qlcnic_adapter *);
 int qlcnic_sriov_set_vf_mac(struct net_device *, int, u8 *);
-int qlcnic_sriov_set_vf_tx_rate(struct net_device *, int, int);
+int qlcnic_sriov_set_vf_tx_rate(struct net_device *, int, int, int);
 int qlcnic_sriov_get_vf_config(struct net_device *, int ,
 			       struct ifla_vf_info *);
 int qlcnic_sriov_set_vf_vlan(struct net_device *, int, u16, u8);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index 6afe9c1f5ab..1659c804f1d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -39,6 +39,8 @@ static int qlcnic_sriov_channel_cfg_cmd(struct qlcnic_adapter *, u8);
 static void qlcnic_sriov_process_bc_cmd(struct work_struct *);
 static int qlcnic_sriov_vf_shutdown(struct pci_dev *);
 static int qlcnic_sriov_vf_resume(struct qlcnic_adapter *);
+static int qlcnic_sriov_async_issue_cmd(struct qlcnic_adapter *,
+					struct qlcnic_cmd_args *);
 
 static struct qlcnic_hardware_ops qlcnic_sriov_vf_hw_ops = {
 	.read_crb			= qlcnic_83xx_read_crb,
@@ -181,7 +183,7 @@ int qlcnic_sriov_init(struct qlcnic_adapter *adapter, int num_vfs)
 		vf->adapter = adapter;
 		vf->pci_func = qlcnic_sriov_virtid_fn(adapter, i);
 		mutex_init(&vf->send_cmd_lock);
-		mutex_init(&vf->vlan_list_lock);
+		spin_lock_init(&vf->vlan_list_lock);
 		INIT_LIST_HEAD(&vf->rcv_act.wait_list);
 		INIT_LIST_HEAD(&vf->rcv_pend.wait_list);
 		spin_lock_init(&vf->rcv_act.lock);
@@ -197,8 +199,10 @@ int qlcnic_sriov_init(struct qlcnic_adapter *adapter, int num_vfs)
 				goto qlcnic_destroy_async_wq;
 			}
 			sriov->vf_info[i].vp = vp;
+			vp->vlan_mode = QLC_GUEST_VLAN_MODE;
 			vp->max_tx_bw = MAX_BW;
-			vp->spoofchk = true;
+			vp->min_tx_bw = MIN_BW;
+			vp->spoofchk = false;
 			random_ether_addr(vp->mac);
 			dev_info(&adapter->pdev->dev,
 				 "MAC Address %pM is configured for VF %d\n",
@@ -454,6 +458,7 @@ static int qlcnic_sriov_get_vf_acl(struct qlcnic_adapter *adapter)
 	struct qlcnic_cmd_args cmd;
 	int ret = 0;
 
+	memset(&cmd, 0, sizeof(cmd));
 	ret = qlcnic_sriov_alloc_bc_mbx_args(&cmd, QLCNIC_BC_CMD_GET_ACL);
 	if (ret)
 		return ret;
@@ -515,6 +520,8 @@ static int qlcnic_sriov_setup_vf(struct qlcnic_adapter *adapter,
 {
 	int err;
 
+	adapter->flags |= QLCNIC_VLAN_FILTERING;
+	adapter->ahw->total_nic_func = 1;
 	INIT_LIST_HEAD(&adapter->vf_mc_list);
 	if (!qlcnic_use_msi_x && !!qlcnic_use_msi)
 		dev_warn(&adapter->pdev->dev,
@@ -770,6 +777,7 @@ static int qlcnic_sriov_prepare_bc_hdr(struct qlcnic_bc_trans *trans,
 		cmd->req.arg = (u32 *)trans->req_pay;
 		cmd->rsp.arg = (u32 *)trans->rsp_pay;
 		cmd_op = cmd->req.arg[0] & 0xff;
+		cmd->cmd_op = cmd_op;
 		remainder = (trans->rsp_pay_size) % (bc_pay_sz);
 		num_frags = (trans->rsp_pay_size) / (bc_pay_sz);
 		if (remainder)
@@ -1356,7 +1364,7 @@ static int qlcnic_sriov_retry_bc_cmd(struct qlcnic_adapter *adapter,
 	return -EIO;
 }
 
-static int qlcnic_sriov_issue_cmd(struct qlcnic_adapter *adapter,
+static int __qlcnic_sriov_issue_cmd(struct qlcnic_adapter *adapter,
 				  struct qlcnic_cmd_args *cmd)
 {
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
@@ -1408,12 +1416,17 @@ retry:
 	    (mbx_err_code == QLCNIC_MBX_PORT_RSP_OK)) {
 		rsp = QLCNIC_RCODE_SUCCESS;
 	} else {
-		rsp = mbx_err_code;
-		if (!rsp)
-			rsp = 1;
-		dev_err(dev,
-			"MBX command 0x%x failed with err:0x%x for VF %d\n",
-			opcode, mbx_err_code, func);
+		if (cmd->type == QLC_83XX_MBX_CMD_NO_WAIT) {
+			rsp = QLCNIC_RCODE_SUCCESS;
+		} else {
+			rsp = mbx_err_code;
+			if (!rsp)
+				rsp = 1;
+
+			dev_err(dev,
+				"MBX command 0x%x failed with err:0x%x for VF %d\n",
+				opcode, mbx_err_code, func);
+		}
 	}
 
 err_out:
@@ -1435,12 +1448,23 @@ free_cmd:
 	return rsp;
 }
 
+
+static int qlcnic_sriov_issue_cmd(struct qlcnic_adapter *adapter,
+				  struct qlcnic_cmd_args *cmd)
+{
+	if (cmd->type == QLC_83XX_MBX_CMD_NO_WAIT)
+		return qlcnic_sriov_async_issue_cmd(adapter, cmd);
+	else
+		return __qlcnic_sriov_issue_cmd(adapter, cmd);
+}
+
 static int qlcnic_sriov_channel_cfg_cmd(struct qlcnic_adapter *adapter, u8 cmd_op)
 {
 	struct qlcnic_cmd_args cmd;
 	struct qlcnic_vf_info *vf = &adapter->ahw->sriov->vf_info[0];
 	int ret;
 
+	memset(&cmd, 0, sizeof(cmd));
 	if (qlcnic_sriov_alloc_bc_mbx_args(&cmd, cmd_op))
 		return -ENOMEM;
 
@@ -1465,58 +1489,28 @@ out:
 	return ret;
 }
 
-static void qlcnic_vf_add_mc_list(struct net_device *netdev)
+static void qlcnic_vf_add_mc_list(struct net_device *netdev, const u8 *mac)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_sriov *sriov = adapter->ahw->sriov;
-	struct qlcnic_mac_vlan_list *cur;
-	struct list_head *head, tmp_list;
 	struct qlcnic_vf_info *vf;
 	u16 vlan_id;
 	int i;
 
-	static const u8 bcast_addr[ETH_ALEN] = {
-		0xff, 0xff, 0xff, 0xff, 0xff, 0xff
-	};
-
 	vf = &adapter->ahw->sriov->vf_info[0];
-	INIT_LIST_HEAD(&tmp_list);
-	head = &adapter->vf_mc_list;
-	netif_addr_lock_bh(netdev);
 
-	while (!list_empty(head)) {
-		cur = list_entry(head->next, struct qlcnic_mac_vlan_list, list);
-		list_move(&cur->list, &tmp_list);
-	}
-
-	netif_addr_unlock_bh(netdev);
-
-	while (!list_empty(&tmp_list)) {
-		cur = list_entry((&tmp_list)->next,
-				 struct qlcnic_mac_vlan_list, list);
-		if (!qlcnic_sriov_check_any_vlan(vf)) {
-			qlcnic_nic_add_mac(adapter, bcast_addr, 0);
-			qlcnic_nic_add_mac(adapter, cur->mac_addr, 0);
-		} else {
-			mutex_lock(&vf->vlan_list_lock);
-			for (i = 0; i < sriov->num_allowed_vlans; i++) {
-				vlan_id = vf->sriov_vlans[i];
-				if (vlan_id) {
-					qlcnic_nic_add_mac(adapter, bcast_addr,
-							   vlan_id);
-					qlcnic_nic_add_mac(adapter,
-							   cur->mac_addr,
-							   vlan_id);
-				}
-			}
-			mutex_unlock(&vf->vlan_list_lock);
-			if (qlcnic_84xx_check(adapter)) {
-				qlcnic_nic_add_mac(adapter, bcast_addr, 0);
-				qlcnic_nic_add_mac(adapter, cur->mac_addr, 0);
-			}
+	if (!qlcnic_sriov_check_any_vlan(vf)) {
+		qlcnic_nic_add_mac(adapter, mac, 0);
+	} else {
+		spin_lock(&vf->vlan_list_lock);
+		for (i = 0; i < sriov->num_allowed_vlans; i++) {
+			vlan_id = vf->sriov_vlans[i];
+			if (vlan_id)
+				qlcnic_nic_add_mac(adapter, mac, vlan_id);
 		}
-		list_del(&cur->list);
-		kfree(cur);
+		spin_unlock(&vf->vlan_list_lock);
+		if (qlcnic_84xx_check(adapter))
+			qlcnic_nic_add_mac(adapter, mac, 0);
 	}
 }
 
@@ -1525,6 +1519,7 @@ void qlcnic_sriov_cleanup_async_list(struct qlcnic_back_channel *bc)
 	struct list_head *head = &bc->async_list;
 	struct qlcnic_async_work_list *entry;
 
+	flush_workqueue(bc->bc_async_wq);
 	while (!list_empty(head)) {
 		entry = list_entry(head->next, struct qlcnic_async_work_list,
 				   list);
@@ -1534,10 +1529,14 @@ void qlcnic_sriov_cleanup_async_list(struct qlcnic_back_channel *bc)
 	}
 }
 
-static void qlcnic_sriov_vf_set_multi(struct net_device *netdev)
+void qlcnic_sriov_vf_set_multi(struct net_device *netdev)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_hardware_context *ahw = adapter->ahw;
+	static const u8 bcast_addr[ETH_ALEN] = {
+		0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	};
+	struct netdev_hw_addr *ha;
 	u32 mode = VPORT_MISS_MODE_DROP;
 
 	if (!test_bit(__QLCNIC_FW_ATTACHED, &adapter->state))
@@ -1549,23 +1548,49 @@ static void qlcnic_sriov_vf_set_multi(struct net_device *netdev)
 	} else if ((netdev->flags & IFF_ALLMULTI) ||
 		   (netdev_mc_count(netdev) > ahw->max_mc_count)) {
 		mode = VPORT_MISS_MODE_ACCEPT_MULTI;
+	} else {
+		qlcnic_vf_add_mc_list(netdev, bcast_addr);
+		if (!netdev_mc_empty(netdev)) {
+			netdev_for_each_mc_addr(ha, netdev)
+				qlcnic_vf_add_mc_list(netdev, ha->addr);
+		}
 	}
 
-	if (qlcnic_sriov_vf_check(adapter))
-		qlcnic_vf_add_mc_list(netdev);
+	/* configure unicast MAC address, if there is not sufficient space
+	 * to store all the unicast addresses then enable promiscuous mode
+	 */
+	if (netdev_uc_count(netdev) > ahw->max_uc_count) {
+		mode = VPORT_MISS_MODE_ACCEPT_ALL;
+	} else if (!netdev_uc_empty(netdev)) {
+		netdev_for_each_uc_addr(ha, netdev)
+			qlcnic_vf_add_mc_list(netdev, ha->addr);
+	}
+
+	if (adapter->pdev->is_virtfn) {
+		if (mode == VPORT_MISS_MODE_ACCEPT_ALL &&
+		    !adapter->fdb_mac_learn) {
+			qlcnic_alloc_lb_filters_mem(adapter);
+			adapter->drv_mac_learn = 1;
+			adapter->rx_mac_learn = true;
+		} else {
+			adapter->drv_mac_learn = 0;
+			adapter->rx_mac_learn = false;
+		}
+	}
 
 	qlcnic_nic_set_promisc(adapter, mode);
 }
 
-static void qlcnic_sriov_handle_async_multi(struct work_struct *work)
+static void qlcnic_sriov_handle_async_issue_cmd(struct work_struct *work)
 {
 	struct qlcnic_async_work_list *entry;
-	struct net_device *netdev;
+	struct qlcnic_adapter *adapter;
+	struct qlcnic_cmd_args *cmd;
 
 	entry = container_of(work, struct qlcnic_async_work_list, work);
-	netdev = (struct net_device *)entry->ptr;
-
-	qlcnic_sriov_vf_set_multi(netdev);
+	adapter = entry->ptr;
+	cmd = entry->cmd;
+	__qlcnic_sriov_issue_cmd(adapter, cmd);
 	return;
 }
 
@@ -1595,8 +1620,9 @@ qlcnic_sriov_get_free_node_async_work(struct qlcnic_back_channel *bc)
 	return entry;
 }
 
-static void qlcnic_sriov_schedule_bc_async_work(struct qlcnic_back_channel *bc,
-						work_func_t func, void *data)
+static void qlcnic_sriov_schedule_async_cmd(struct qlcnic_back_channel *bc,
+					    work_func_t func, void *data,
+					    struct qlcnic_cmd_args *cmd)
 {
 	struct qlcnic_async_work_list *entry = NULL;
 
@@ -1605,21 +1631,23 @@ static void qlcnic_sriov_schedule_bc_async_work(struct qlcnic_back_channel *bc,
 		return;
 
 	entry->ptr = data;
+	entry->cmd = cmd;
 	INIT_WORK(&entry->work, func);
 	queue_work(bc->bc_async_wq, &entry->work);
 }
 
-void qlcnic_sriov_vf_schedule_multi(struct net_device *netdev)
+static int qlcnic_sriov_async_issue_cmd(struct qlcnic_adapter *adapter,
+					struct qlcnic_cmd_args *cmd)
 {
 
-	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_back_channel *bc = &adapter->ahw->sriov->bc;
 
 	if (adapter->need_fw_reset)
-		return;
+		return -EIO;
 
-	qlcnic_sriov_schedule_bc_async_work(bc, qlcnic_sriov_handle_async_multi,
-					    netdev);
+	qlcnic_sriov_schedule_async_cmd(bc, qlcnic_sriov_handle_async_issue_cmd,
+					adapter, cmd);
+	return 0;
 }
 
 static int qlcnic_sriov_vf_reinit_driver(struct qlcnic_adapter *adapter)
@@ -1843,6 +1871,12 @@ static int qlcnic_sriov_vf_idc_unknown_state(struct qlcnic_adapter *adapter)
 	return 0;
 }
 
+static void qlcnic_sriov_vf_periodic_tasks(struct qlcnic_adapter *adapter)
+{
+	if (adapter->fhash.fnum)
+		qlcnic_prune_lb_filters(adapter);
+}
+
 static void qlcnic_sriov_vf_poll_dev_state(struct work_struct *work)
 {
 	struct qlcnic_adapter *adapter;
@@ -1874,6 +1908,8 @@ static void qlcnic_sriov_vf_poll_dev_state(struct work_struct *work)
 	}
 
 	idc->prev_state = idc->curr_state;
+	qlcnic_sriov_vf_periodic_tasks(adapter);
+
 	if (!ret && test_bit(QLC_83XX_MODULE_LOADED, &idc->status))
 		qlcnic_schedule_work(adapter, qlcnic_sriov_vf_poll_dev_state,
 				     idc->delay);
@@ -1897,7 +1933,7 @@ static int qlcnic_sriov_check_vlan_id(struct qlcnic_sriov *sriov,
 	if (!vf->sriov_vlans)
 		return err;
 
-	mutex_lock(&vf->vlan_list_lock);
+	spin_lock_bh(&vf->vlan_list_lock);
 
 	for (i = 0; i < sriov->num_allowed_vlans; i++) {
 		if (vf->sriov_vlans[i] == vlan_id) {
@@ -1906,7 +1942,7 @@ static int qlcnic_sriov_check_vlan_id(struct qlcnic_sriov *sriov,
 		}
 	}
 
-	mutex_unlock(&vf->vlan_list_lock);
+	spin_unlock_bh(&vf->vlan_list_lock);
 	return err;
 }
 
@@ -1915,12 +1951,12 @@ static int qlcnic_sriov_validate_num_vlans(struct qlcnic_sriov *sriov,
 {
 	int err = 0;
 
-	mutex_lock(&vf->vlan_list_lock);
+	spin_lock_bh(&vf->vlan_list_lock);
 
 	if (vf->num_vlan >= sriov->num_allowed_vlans)
 		err = -EINVAL;
 
-	mutex_unlock(&vf->vlan_list_lock);
+	spin_unlock_bh(&vf->vlan_list_lock);
 	return err;
 }
 
@@ -1973,7 +2009,7 @@ static void qlcnic_sriov_vlan_operation(struct qlcnic_vf_info *vf, u16 vlan_id,
 	if (!vf->sriov_vlans)
 		return;
 
-	mutex_lock(&vf->vlan_list_lock);
+	spin_lock_bh(&vf->vlan_list_lock);
 
 	switch (opcode) {
 	case QLC_VLAN_ADD:
@@ -1986,7 +2022,7 @@ static void qlcnic_sriov_vlan_operation(struct qlcnic_vf_info *vf, u16 vlan_id,
 		netdev_err(adapter->netdev, "Invalid VLAN operation\n");
 	}
 
-	mutex_unlock(&vf->vlan_list_lock);
+	spin_unlock_bh(&vf->vlan_list_lock);
 	return;
 }
 
@@ -1994,10 +2030,12 @@ int qlcnic_sriov_cfg_vf_guest_vlan(struct qlcnic_adapter *adapter,
 				   u16 vid, u8 enable)
 {
 	struct qlcnic_sriov *sriov = adapter->ahw->sriov;
+	struct net_device *netdev = adapter->netdev;
 	struct qlcnic_vf_info *vf;
 	struct qlcnic_cmd_args cmd;
 	int ret;
 
+	memset(&cmd, 0, sizeof(cmd));
 	if (vid == 0)
 		return 0;
 
@@ -2019,14 +2057,18 @@ int qlcnic_sriov_cfg_vf_guest_vlan(struct qlcnic_adapter *adapter,
 		dev_err(&adapter->pdev->dev,
 			"Failed to configure guest VLAN, err=%d\n", ret);
 	} else {
+		netif_addr_lock_bh(netdev);
 		qlcnic_free_mac_list(adapter);
+		netif_addr_unlock_bh(netdev);
 
 		if (enable)
 			qlcnic_sriov_vlan_operation(vf, vid, QLC_VLAN_ADD);
 		else
 			qlcnic_sriov_vlan_operation(vf, vid, QLC_VLAN_DELETE);
 
-		qlcnic_set_multi(adapter->netdev);
+		netif_addr_lock_bh(netdev);
+		qlcnic_set_multi(netdev);
+		netif_addr_unlock_bh(netdev);
 	}
 
 	qlcnic_free_mbx_args(&cmd);
@@ -2157,11 +2199,11 @@ bool qlcnic_sriov_check_any_vlan(struct qlcnic_vf_info *vf)
 {
 	bool err = false;
 
-	mutex_lock(&vf->vlan_list_lock);
+	spin_lock_bh(&vf->vlan_list_lock);
 
 	if (vf->num_vlan)
 		err = true;
 
-	mutex_unlock(&vf->vlan_list_lock);
+	spin_unlock_bh(&vf->vlan_list_lock);
 	return err;
 }
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 28013799154..a29538b86ed 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -16,6 +16,7 @@
 #define QLC_VF_FLOOD_BIT	BIT_16
 #define QLC_FLOOD_MODE		0x5
 #define QLC_SRIOV_ALLOW_VLAN0	BIT_19
+#define QLC_INTR_COAL_TYPE_MASK	0x7
 
 static int qlcnic_sriov_pf_get_vport_handle(struct qlcnic_adapter *, u8);
 
@@ -83,7 +84,7 @@ static int qlcnic_sriov_pf_cal_res_limit(struct qlcnic_adapter *adapter,
 	info->max_tx_ques = res->num_tx_queues / max;
 
 	if (qlcnic_83xx_pf_check(adapter))
-		num_macs = 1;
+		num_macs = QLCNIC_83XX_SRIOV_VF_MAX_MAC;
 
 	info->max_rx_mcast_mac_filters = res->num_rx_mcast_mac_filters;
 
@@ -337,9 +338,12 @@ static int qlcnic_sriov_pf_cfg_vlan_filtering(struct qlcnic_adapter *adapter,
 
 	cmd.req.arg[1] = 0x4;
 	if (enable) {
+		adapter->flags |= QLCNIC_VLAN_FILTERING;
 		cmd.req.arg[1] |= BIT_16;
 		if (qlcnic_84xx_check(adapter))
 			cmd.req.arg[1] |= QLC_SRIOV_ALLOW_VLAN0;
+	} else {
+		adapter->flags &= ~QLCNIC_VLAN_FILTERING;
 	}
 
 	err = qlcnic_issue_cmd(adapter, &cmd);
@@ -471,12 +475,12 @@ static int qlcnic_pci_sriov_disable(struct qlcnic_adapter *adapter)
 		return -EPERM;
 	}
 
+	qlcnic_sriov_pf_disable(adapter);
+
 	rtnl_lock();
 	if (netif_running(netdev))
 		__qlcnic_down(adapter, netdev);
 
-	qlcnic_sriov_pf_disable(adapter);
-
 	qlcnic_sriov_free_vlans(adapter);
 
 	qlcnic_sriov_pf_cleanup(adapter);
@@ -595,7 +599,6 @@ static int __qlcnic_pci_sriov_enable(struct qlcnic_adapter *adapter,
 
 	qlcnic_sriov_alloc_vlans(adapter);
 
-	err = qlcnic_sriov_pf_enable(adapter, num_vfs);
 	return err;
 
 del_flr_queue:
@@ -626,25 +629,36 @@ static int qlcnic_pci_sriov_enable(struct qlcnic_adapter *adapter, int num_vfs)
 		__qlcnic_down(adapter, netdev);
 
 	err = __qlcnic_pci_sriov_enable(adapter, num_vfs);
-	if (err) {
-		netdev_info(netdev, "Failed to enable SR-IOV on port %d\n",
-			    adapter->portnum);
+	if (err)
+		goto error;
 
-		err = -EIO;
-		if (qlcnic_83xx_configure_opmode(adapter))
-			goto error;
-	} else {
+	if (netif_running(netdev))
+		__qlcnic_up(adapter, netdev);
+
+	rtnl_unlock();
+	err = qlcnic_sriov_pf_enable(adapter, num_vfs);
+	if (!err) {
 		netdev_info(netdev,
 			    "SR-IOV is enabled successfully on port %d\n",
 			    adapter->portnum);
 		/* Return number of vfs enabled */
-		err = num_vfs;
+		return num_vfs;
 	}
+
+	rtnl_lock();
 	if (netif_running(netdev))
-		__qlcnic_up(adapter, netdev);
+		__qlcnic_down(adapter, netdev);
 
 error:
+	if (!qlcnic_83xx_configure_opmode(adapter)) {
+		if (netif_running(netdev))
+			__qlcnic_up(adapter, netdev);
+	}
+
 	rtnl_unlock();
+	netdev_info(netdev, "Failed to enable SR-IOV on port %d\n",
+		    adapter->portnum);
+
 	return err;
 }
 
@@ -773,7 +787,7 @@ static int qlcnic_sriov_cfg_vf_def_mac(struct qlcnic_adapter *adapter,
 				       struct qlcnic_vf_info *vf,
 				       u16 vlan, u8 op)
 {
-	struct qlcnic_cmd_args cmd;
+	struct qlcnic_cmd_args *cmd;
 	struct qlcnic_macvlan_mbx mv;
 	struct qlcnic_vport *vp;
 	u8 *addr;
@@ -783,21 +797,27 @@ static int qlcnic_sriov_cfg_vf_def_mac(struct qlcnic_adapter *adapter,
 
 	vp = vf->vp;
 
-	if (qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_CONFIG_MAC_VLAN))
+	cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC);
+	if (!cmd)
 		return -ENOMEM;
 
+	err = qlcnic_alloc_mbx_args(cmd, adapter, QLCNIC_CMD_CONFIG_MAC_VLAN);
+	if (err)
+		goto free_cmd;
+
+	cmd->type = QLC_83XX_MBX_CMD_NO_WAIT;
 	vpid = qlcnic_sriov_pf_get_vport_handle(adapter, vf->pci_func);
 	if (vpid < 0) {
 		err = -EINVAL;
-		goto out;
+		goto free_args;
 	}
 
 	if (vlan)
 		op = ((op == QLCNIC_MAC_ADD || op == QLCNIC_MAC_VLAN_ADD) ?
 		      QLCNIC_MAC_VLAN_ADD : QLCNIC_MAC_VLAN_DEL);
 
-	cmd.req.arg[1] = op | (1 << 8) | (3 << 6);
-	cmd.req.arg[1] |= ((vpid & 0xffff) << 16) | BIT_31;
+	cmd->req.arg[1] = op | (1 << 8) | (3 << 6);
+	cmd->req.arg[1] |= ((vpid & 0xffff) << 16) | BIT_31;
 
 	addr = vp->mac;
 	mv.vlan = vlan;
@@ -807,18 +827,18 @@ static int qlcnic_sriov_cfg_vf_def_mac(struct qlcnic_adapter *adapter,
 	mv.mac_addr3 = addr[3];
 	mv.mac_addr4 = addr[4];
 	mv.mac_addr5 = addr[5];
-	buf = &cmd.req.arg[2];
+	buf = &cmd->req.arg[2];
 	memcpy(buf, &mv, sizeof(struct qlcnic_macvlan_mbx));
 
-	err = qlcnic_issue_cmd(adapter, &cmd);
+	err = qlcnic_issue_cmd(adapter, cmd);
 
-	if (err)
-		dev_err(&adapter->pdev->dev,
-			"MAC-VLAN %s to CAM failed, err=%d.\n",
-			((op == 1) ? "add " : "delete "), err);
+	if (!err)
+		return err;
 
-out:
-	qlcnic_free_mbx_args(&cmd);
+free_args:
+	qlcnic_free_mbx_args(cmd);
+free_cmd:
+	kfree(cmd);
 	return err;
 }
 
@@ -840,7 +860,7 @@ static void qlcnic_83xx_cfg_default_mac_vlan(struct qlcnic_adapter *adapter,
 
 	sriov = adapter->ahw->sriov;
 
-	mutex_lock(&vf->vlan_list_lock);
+	spin_lock_bh(&vf->vlan_list_lock);
 	if (vf->num_vlan) {
 		for (i = 0; i < sriov->num_allowed_vlans; i++) {
 			vlan = vf->sriov_vlans[i];
@@ -849,7 +869,7 @@ static void qlcnic_83xx_cfg_default_mac_vlan(struct qlcnic_adapter *adapter,
 							    opcode);
 		}
 	}
-	mutex_unlock(&vf->vlan_list_lock);
+	spin_unlock_bh(&vf->vlan_list_lock);
 
 	if (vf->vp->vlan_mode != QLC_PVID_MODE) {
 		if (qlcnic_83xx_pf_check(adapter) &&
@@ -1178,19 +1198,41 @@ static int qlcnic_sriov_validate_cfg_intrcoal(struct qlcnic_adapter *adapter,
 {
 	struct qlcnic_nic_intr_coalesce *coal = &adapter->ahw->coal;
 	u16 ctx_id, pkts, time;
+	int err = -EINVAL;
+	u8 type;
 
+	type = cmd->req.arg[1] & QLC_INTR_COAL_TYPE_MASK;
 	ctx_id = cmd->req.arg[1] >> 16;
 	pkts = cmd->req.arg[2] & 0xffff;
 	time = cmd->req.arg[2] >> 16;
 
-	if (ctx_id != vf->rx_ctx_id)
-		return -EINVAL;
-	if (pkts > coal->rx_packets)
-		return -EINVAL;
-	if (time < coal->rx_time_us)
-		return -EINVAL;
+	switch (type) {
+	case QLCNIC_INTR_COAL_TYPE_RX:
+		if (ctx_id != vf->rx_ctx_id || pkts > coal->rx_packets ||
+		    time < coal->rx_time_us)
+			goto err_label;
+		break;
+	case QLCNIC_INTR_COAL_TYPE_TX:
+		if (ctx_id != vf->tx_ctx_id || pkts > coal->tx_packets ||
+		    time < coal->tx_time_us)
+			goto err_label;
+		break;
+	default:
+		netdev_err(adapter->netdev, "Invalid coalescing type 0x%x received\n",
+			   type);
+		return err;
+	}
 
 	return 0;
+
+err_label:
+	netdev_err(adapter->netdev, "Expected: rx_ctx_id 0x%x rx_packets 0x%x rx_time_us 0x%x tx_ctx_id 0x%x tx_packets 0x%x tx_time_us 0x%x\n",
+		   vf->rx_ctx_id, coal->rx_packets, coal->rx_time_us,
+		   vf->tx_ctx_id, coal->tx_packets, coal->tx_time_us);
+	netdev_err(adapter->netdev, "Received: ctx_id 0x%x packets 0x%x time_us 0x%x type 0x%x\n",
+		   ctx_id, pkts, time, type);
+
+	return err;
 }
 
 static int qlcnic_sriov_pf_cfg_intrcoal_cmd(struct qlcnic_bc_trans *tran,
@@ -1214,7 +1256,6 @@ static int qlcnic_sriov_validate_cfg_macvlan(struct qlcnic_adapter *adapter,
 					     struct qlcnic_vf_info *vf,
 					     struct qlcnic_cmd_args *cmd)
 {
-	struct qlcnic_macvlan_mbx *macvlan;
 	struct qlcnic_vport *vp = vf->vp;
 	u8 op, new_op;
 
@@ -1224,14 +1265,6 @@ static int qlcnic_sriov_validate_cfg_macvlan(struct qlcnic_adapter *adapter,
 	cmd->req.arg[1] |= (vf->vp->handle << 16);
 	cmd->req.arg[1] |= BIT_31;
 
-	macvlan = (struct qlcnic_macvlan_mbx *)&cmd->req.arg[2];
-	if (!(macvlan->mac_addr0 & BIT_0)) {
-		dev_err(&adapter->pdev->dev,
-			"MAC address change is not allowed from VF %d",
-			vf->pci_func);
-		return -EINVAL;
-	}
-
 	if (vp->vlan_mode == QLC_PVID_MODE) {
 		op = cmd->req.arg[1] & 0x7;
 		cmd->req.arg[1] &= ~0x7;
@@ -1815,7 +1848,8 @@ int qlcnic_sriov_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 	return 0;
 }
 
-int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf, int tx_rate)
+int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf,
+				int min_tx_rate, int max_tx_rate)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct qlcnic_sriov *sriov = adapter->ahw->sriov;
@@ -1830,35 +1864,52 @@ int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf, int tx_rate)
 	if (vf >= sriov->num_vfs)
 		return -EINVAL;
 
-	if (tx_rate >= 10000 || tx_rate < 100) {
+	vf_info = &sriov->vf_info[vf];
+	vp = vf_info->vp;
+	vpid = vp->handle;
+
+	if (!min_tx_rate)
+		min_tx_rate = QLC_VF_MIN_TX_RATE;
+
+	if (max_tx_rate &&
+	    (max_tx_rate >= 10000 || max_tx_rate < min_tx_rate)) {
 		netdev_err(netdev,
-			   "Invalid Tx rate, allowed range is [%d - %d]",
-			   QLC_VF_MIN_TX_RATE, QLC_VF_MAX_TX_RATE);
+			   "Invalid max Tx rate, allowed range is [%d - %d]",
+			   min_tx_rate, QLC_VF_MAX_TX_RATE);
 		return -EINVAL;
 	}
 
-	if (tx_rate == 0)
-		tx_rate = 10000;
+	if (!max_tx_rate)
+		max_tx_rate = 10000;
 
-	vf_info = &sriov->vf_info[vf];
-	vp = vf_info->vp;
-	vpid = vp->handle;
+	if (min_tx_rate &&
+	    (min_tx_rate > max_tx_rate || min_tx_rate < QLC_VF_MIN_TX_RATE)) {
+		netdev_err(netdev,
+			   "Invalid min Tx rate, allowed range is [%d - %d]",
+			   QLC_VF_MIN_TX_RATE, max_tx_rate);
+		return -EINVAL;
+	}
 
 	if (test_bit(QLC_BC_VF_STATE, &vf_info->state)) {
 		if (qlcnic_sriov_get_vf_vport_info(adapter, &nic_info, vpid))
 			return -EIO;
 
-		nic_info.max_tx_bw = tx_rate / 100;
+		nic_info.max_tx_bw = max_tx_rate / 100;
+		nic_info.min_tx_bw = min_tx_rate / 100;
 		nic_info.bit_offsets = BIT_0;
 
 		if (qlcnic_sriov_pf_set_vport_info(adapter, &nic_info, vpid))
 			return -EIO;
 	}
 
-	vp->max_tx_bw = tx_rate / 100;
+	vp->max_tx_bw = max_tx_rate / 100;
 	netdev_info(netdev,
-		    "Setting Tx rate %d (Mbps), %d %% of PF bandwidth, for VF %d\n",
-		    tx_rate, vp->max_tx_bw, vf);
+		    "Setting Max Tx rate %d (Mbps), %d %% of PF bandwidth, for VF %d\n",
+		    max_tx_rate, vp->max_tx_bw, vf);
+	vp->min_tx_bw = min_tx_rate / 100;
+	netdev_info(netdev,
+		    "Setting Min Tx rate %d (Mbps), %d %% of PF bandwidth, for VF %d\n",
+		    min_tx_rate, vp->min_tx_bw, vf);
 	return 0;
 }
 
@@ -1957,9 +2008,13 @@ int qlcnic_sriov_get_vf_config(struct net_device *netdev,
 	ivi->qos = vp->qos;
 	ivi->spoofchk = vp->spoofchk;
 	if (vp->max_tx_bw == MAX_BW)
-		ivi->tx_rate = 0;
+		ivi->max_tx_rate = 0;
+	else
+		ivi->max_tx_rate = vp->max_tx_bw * 100;
+	if (vp->min_tx_bw == MIN_BW)
+		ivi->min_tx_rate = 0;
 	else
-		ivi->tx_rate = vp->max_tx_bw * 100;
+		ivi->min_tx_rate = vp->min_tx_bw * 100;
 
 	ivi->vf = vf;
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
index cd346e27f2e..f5786d5792d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
@@ -19,6 +19,10 @@
 #include <linux/sysfs.h>
 #include <linux/aer.h>
 #include <linux/log2.h>
+#ifdef CONFIG_QLCNIC_HWMON
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#endif
 
 #define QLC_STATUS_UNSUPPORTED_CMD	-2
 
@@ -358,6 +362,8 @@ int qlcnic_is_valid_nic_func(struct qlcnic_adapter *adapter, u8 pci_func)
 		if (adapter->npars[i].pci_func == pci_func)
 			return i;
 	}
+
+	dev_err(&adapter->pdev->dev, "%s: Invalid nic function\n", __func__);
 	return -EINVAL;
 }
 
@@ -1243,6 +1249,68 @@ static struct bin_attribute bin_attr_flash = {
 	.write = qlcnic_83xx_sysfs_flash_write_handler,
 };
 
+#ifdef CONFIG_QLCNIC_HWMON
+
+static ssize_t qlcnic_hwmon_show_temp(struct device *dev,
+				      struct device_attribute *dev_attr,
+				      char *buf)
+{
+	struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
+	unsigned int temperature = 0, value = 0;
+
+	if (qlcnic_83xx_check(adapter))
+		value = QLCRDX(adapter->ahw, QLC_83XX_ASIC_TEMP);
+	else if (qlcnic_82xx_check(adapter))
+		value = QLC_SHARED_REG_RD32(adapter, QLCNIC_ASIC_TEMP);
+
+	temperature = qlcnic_get_temp_val(value);
+	/* display millidegree celcius */
+	temperature *= 1000;
+	return sprintf(buf, "%u\n", temperature);
+}
+
+/* hwmon-sysfs attributes */
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO,
+			  qlcnic_hwmon_show_temp, NULL, 1);
+
+static struct attribute *qlcnic_hwmon_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(qlcnic_hwmon);
+
+void qlcnic_register_hwmon_dev(struct qlcnic_adapter *adapter)
+{
+	struct device *dev = &adapter->pdev->dev;
+	struct device *hwmon_dev;
+
+	/* Skip hwmon registration for a VF device */
+	if (qlcnic_sriov_vf_check(adapter)) {
+		adapter->ahw->hwmon_dev = NULL;
+		return;
+	}
+	hwmon_dev = hwmon_device_register_with_groups(dev, qlcnic_driver_name,
+						      adapter,
+						      qlcnic_hwmon_groups);
+	if (IS_ERR(hwmon_dev)) {
+		dev_err(dev, "Cannot register with hwmon, err=%ld\n",
+			PTR_ERR(hwmon_dev));
+		hwmon_dev = NULL;
+	}
+	adapter->ahw->hwmon_dev = hwmon_dev;
+}
+
+void qlcnic_unregister_hwmon_dev(struct qlcnic_adapter *adapter)
+{
+	struct device *hwmon_dev = adapter->ahw->hwmon_dev;
+	if (hwmon_dev) {
+		hwmon_device_unregister(hwmon_dev);
+		adapter->ahw->hwmon_dev = NULL;
+	}
+}
+#endif
+
 void qlcnic_create_sysfs_entries(struct qlcnic_adapter *adapter)
 {
 	struct device *dev = &adapter->pdev->dev;
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 0a1d76acab8..b40050e03a5 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -3595,7 +3595,7 @@ static int ql_request_irq(struct ql_adapter *qdev)
 	}
 	return status;
 err_irq:
-	netif_err(qdev, ifup, qdev->ndev, "Failed to get the interrupts!!!/n");
+	netif_err(qdev, ifup, qdev->ndev, "Failed to get the interrupts!!!\n");
 	ql_free_irq(qdev);
 	return status;
 }
@@ -4770,7 +4770,7 @@ static int qlge_probe(struct pci_dev *pdev,
 	ndev->irq = pdev->irq;
 
 	ndev->netdev_ops = &qlge_netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &qlge_ethtool_ops);
+	ndev->ethtool_ops = &qlge_ethtool_ops;
 	ndev->watchdog_timeo = 10 * HZ;
 
 	err = register_netdev(ndev);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index aa1c079f231..61623e9af57 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -538,6 +538,7 @@ enum rtl_register_content {
 	MagicPacket	= (1 << 5),	/* Wake up when receives a Magic Packet */
 	LinkUp		= (1 << 4),	/* Wake up when the cable connection is re-established */
 	Jumbo_En0	= (1 << 2),	/* 8168 only. Reserved in the 8168b */
+	Rdy_to_L23	= (1 << 1),	/* L23 Enable */
 	Beacon_en	= (1 << 0),	/* 8168 only. Reserved in the 8168b */
 
 	/* Config4 register */
@@ -4239,6 +4240,8 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 		RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST);
 		break;
 	case RTL_GIGA_MAC_VER_40:
+		RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
+		break;
 	case RTL_GIGA_MAC_VER_41:
 	case RTL_GIGA_MAC_VER_42:
 	case RTL_GIGA_MAC_VER_43:
@@ -4897,6 +4900,21 @@ static void rtl_enable_clock_request(struct pci_dev *pdev)
 				 PCI_EXP_LNKCTL_CLKREQ_EN);
 }
 
+static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable)
+{
+	void __iomem *ioaddr = tp->mmio_addr;
+	u8 data;
+
+	data = RTL_R8(Config3);
+
+	if (enable)
+		data |= Rdy_to_L23;
+	else
+		data &= ~Rdy_to_L23;
+
+	RTL_W8(Config3, data);
+}
+
 #define R8168_CPCMD_QUIRK_MASK (\
 	EnableBist | \
 	Mac_dbgo_oe | \
@@ -5246,6 +5264,7 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp)
 	};
 
 	rtl_hw_start_8168f(tp);
+	rtl_pcie_state_l2l3_enable(tp, false);
 
 	rtl_ephy_init(tp, e_info_8168f_1, ARRAY_SIZE(e_info_8168f_1));
 
@@ -5284,6 +5303,8 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
 
 	rtl_w1w0_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06, ERIAR_EXGMAC);
 	rtl_w1w0_eri(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, 0x1000, ERIAR_EXGMAC);
+
+	rtl_pcie_state_l2l3_enable(tp, false);
 }
 
 static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
@@ -5536,6 +5557,8 @@ static void rtl_hw_start_8105e_1(struct rtl8169_private *tp)
 	RTL_W8(DLLPR, RTL_R8(DLLPR) | PFM_EN);
 
 	rtl_ephy_init(tp, e_info_8105e_1, ARRAY_SIZE(e_info_8105e_1));
+
+	rtl_pcie_state_l2l3_enable(tp, false);
 }
 
 static void rtl_hw_start_8105e_2(struct rtl8169_private *tp)
@@ -5571,6 +5594,8 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
 	rtl_w1w0_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0e00, 0xff00, ERIAR_EXGMAC);
+
+	rtl_pcie_state_l2l3_enable(tp, false);
 }
 
 static void rtl_hw_start_8106(struct rtl8169_private *tp)
@@ -5583,6 +5608,8 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
 	RTL_W32(MISC, (RTL_R32(MISC) | DISABLE_LAN_EN) & ~EARLY_TALLY_EN);
 	RTL_W8(MCU, RTL_R8(MCU) | EN_NDP | EN_OOB_RESET);
 	RTL_W8(DLLPR, RTL_R8(DLLPR) & ~PFM_EN);
+
+	rtl_pcie_state_l2l3_enable(tp, false);
 }
 
 static void rtl_hw_start_8101(struct net_device *dev)
@@ -7125,7 +7152,7 @@ rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = RTL_R8(MAC0 + i);
 
-	SET_ETHTOOL_OPS(dev, &rtl8169_ethtool_ops);
+	dev->ethtool_ops = &rtl8169_ethtool_ops;
 	dev->watchdog_timeo = RTL8169_TX_TIMEOUT;
 
 	netif_napi_add(dev, &tp->napi, rtl8169_poll, R8169_NAPI_WEIGHT);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 6a9509ccd33..7622213beef 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -307,6 +307,27 @@ static const u16 sh_eth_offset_fast_sh4[SH_ETH_MAX_REGISTER_OFFSET] = {
 };
 
 static const u16 sh_eth_offset_fast_sh3_sh2[SH_ETH_MAX_REGISTER_OFFSET] = {
+	[EDMR]		= 0x0000,
+	[EDTRR]		= 0x0004,
+	[EDRRR]		= 0x0008,
+	[TDLAR]		= 0x000c,
+	[RDLAR]		= 0x0010,
+	[EESR]		= 0x0014,
+	[EESIPR]	= 0x0018,
+	[TRSCER]	= 0x001c,
+	[RMFCR]		= 0x0020,
+	[TFTR]		= 0x0024,
+	[FDR]		= 0x0028,
+	[RMCR]		= 0x002c,
+	[EDOCR]		= 0x0030,
+	[FCFTR]		= 0x0034,
+	[RPADIR]	= 0x0038,
+	[TRIMD]		= 0x003c,
+	[RBWAR]		= 0x0040,
+	[RDFAR]		= 0x0044,
+	[TBRAR]		= 0x004c,
+	[TDFAR]		= 0x0050,
+
 	[ECMR]		= 0x0160,
 	[ECSR]		= 0x0164,
 	[ECSIPR]	= 0x0168,
@@ -546,7 +567,6 @@ static struct sh_eth_cpu_data sh7757_data = {
 	.register_type	= SH_ETH_REG_FAST_SH4,
 
 	.eesipr_value	= DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
-	.rmcr_value	= RMCR_RNC,
 
 	.tx_check	= EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO,
 	.eesr_err_check	= EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
@@ -624,7 +644,6 @@ static struct sh_eth_cpu_data sh7757_data_giga = {
 			  EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE |
 			  EESR_TDE | EESR_ECI,
 	.fdr_value	= 0x0000072f,
-	.rmcr_value	= RMCR_RNC,
 
 	.irq_flags	= IRQF_SHARED,
 	.apr		= 1,
@@ -752,7 +771,6 @@ static struct sh_eth_cpu_data r8a7740_data = {
 			  EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE |
 			  EESR_TDE | EESR_ECI,
 	.fdr_value	= 0x0000070f,
-	.rmcr_value	= RMCR_RNC,
 
 	.apr		= 1,
 	.mpr		= 1,
@@ -784,7 +802,6 @@ static struct sh_eth_cpu_data r7s72100_data = {
 			  EESR_RFE | EESR_RDE | EESR_RFRMER | EESR_TFE |
 			  EESR_TDE | EESR_ECI,
 	.fdr_value	= 0x0000070f,
-	.rmcr_value	= RMCR_RNC,
 
 	.no_psr		= 1,
 	.apr		= 1,
@@ -833,9 +850,6 @@ static void sh_eth_set_default_cpu_data(struct sh_eth_cpu_data *cd)
 	if (!cd->fdr_value)
 		cd->fdr_value = DEFAULT_FDR_INIT;
 
-	if (!cd->rmcr_value)
-		cd->rmcr_value = DEFAULT_RMCR_VALUE;
-
 	if (!cd->tx_check)
 		cd->tx_check = DEFAULT_TX_CHECK;
 
@@ -1287,8 +1301,8 @@ static int sh_eth_dev_init(struct net_device *ndev, bool start)
 	sh_eth_write(ndev, mdp->cd->fdr_value, FDR);
 	sh_eth_write(ndev, 0, TFTR);
 
-	/* Frame recv control */
-	sh_eth_write(ndev, mdp->cd->rmcr_value, RMCR);
+	/* Frame recv control (enable multiple-packets per rx irq) */
+	sh_eth_write(ndev, RMCR_RNC, RMCR);
 
 	sh_eth_write(ndev, DESC_I_RINT8 | DESC_I_RINT5 | DESC_I_TINT2, TRSCER);
 
@@ -1385,7 +1399,6 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 	int entry = mdp->cur_rx % mdp->num_rx_ring;
 	int boguscnt = (mdp->dirty_rx + mdp->num_rx_ring) - mdp->cur_rx;
 	struct sk_buff *skb;
-	int exceeded = 0;
 	u16 pkt_len = 0;
 	u32 desc_status;
 
@@ -1397,10 +1410,9 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 		if (--boguscnt < 0)
 			break;
 
-		if (*quota <= 0) {
-			exceeded = 1;
+		if (*quota <= 0)
 			break;
-		}
+
 		(*quota)--;
 
 		if (!(desc_status & RDFEND))
@@ -1448,7 +1460,6 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 			ndev->stats.rx_packets++;
 			ndev->stats.rx_bytes += pkt_len;
 		}
-		rxdesc->status |= cpu_to_edmac(mdp, RD_RACT);
 		entry = (++mdp->cur_rx) % mdp->num_rx_ring;
 		rxdesc = &mdp->rx_ring[entry];
 	}
@@ -1494,7 +1505,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 		sh_eth_write(ndev, EDRRR_R, EDRRR);
 	}
 
-	return exceeded;
+	return *quota <= 0;
 }
 
 static void sh_eth_rcv_snd_disable(struct net_device *ndev)
@@ -2627,8 +2638,8 @@ static int sh_mdio_init(struct sh_eth_private *mdp,
 		 pdev->name, pdev->id);
 
 	/* PHY IRQ */
-	mdp->mii_bus->irq = devm_kzalloc(dev, sizeof(int) * PHY_MAX_ADDR,
-					 GFP_KERNEL);
+	mdp->mii_bus->irq = devm_kmalloc_array(dev, PHY_MAX_ADDR, sizeof(int),
+					       GFP_KERNEL);
 	if (!mdp->mii_bus->irq) {
 		ret = -ENOMEM;
 		goto out_free_bus;
@@ -2843,7 +2854,7 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 		ndev->netdev_ops = &sh_eth_netdev_ops_tsu;
 	else
 		ndev->netdev_ops = &sh_eth_netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &sh_eth_ethtool_ops);
+	ndev->ethtool_ops = &sh_eth_ethtool_ops;
 	ndev->watchdog_timeo = TX_TIMEOUT;
 
 	/* debug message level */
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index d55e37cd5fe..b37c427144e 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -319,7 +319,6 @@ enum TD_STS_BIT {
 enum RMCR_BIT {
 	RMCR_RNC = 0x00000001,
 };
-#define DEFAULT_RMCR_VALUE	0x00000000
 
 /* ECMR */
 enum FELIC_MODE_BIT {
@@ -466,7 +465,6 @@ struct sh_eth_cpu_data {
 	unsigned long fdr_value;
 	unsigned long fcftr_value;
 	unsigned long rpadir_value;
-	unsigned long rmcr_value;
 
 	/* interrupt checking mask */
 	unsigned long tx_check;
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
index 0415fa50eeb..c0981ae4587 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -520,5 +520,5 @@ static const struct ethtool_ops sxgbe_ethtool_ops = {
 
 void sxgbe_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &sxgbe_ethtool_ops);
+	netdev->ethtool_ops = &sxgbe_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index 82a9a983869..698494481d1 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -425,8 +425,8 @@ dmamem_err:
  * @rx_rsize: ring size
  * Description:  this function initializes the DMA RX descriptor
  */
-void free_rx_ring(struct device *dev, struct sxgbe_rx_queue *rx_ring,
-		  int rx_rsize)
+static void free_rx_ring(struct device *dev, struct sxgbe_rx_queue *rx_ring,
+			 int rx_rsize)
 {
 	dma_free_coherent(dev, rx_rsize * sizeof(struct sxgbe_rx_norm_desc),
 			  rx_ring->dma_rx, rx_ring->dma_rx_phy);
@@ -519,8 +519,8 @@ error:
  * @tx_rsize: ring size
  * Description:  this function initializes the DMA TX descriptor
  */
-void free_tx_ring(struct device *dev, struct sxgbe_tx_queue *tx_ring,
-		  int tx_rsize)
+static void free_tx_ring(struct device *dev, struct sxgbe_tx_queue *tx_ring,
+			 int tx_rsize)
 {
 	dma_free_coherent(dev, tx_rsize * sizeof(struct sxgbe_tx_norm_desc),
 			  tx_ring->dma_tx, tx_ring->dma_tx_phy);
@@ -1221,11 +1221,10 @@ static int sxgbe_release(struct net_device *dev)
 
 	return 0;
 }
-
 /* Prepare first Tx descriptor for doing TSO operation */
-void sxgbe_tso_prepare(struct sxgbe_priv_data *priv,
-		       struct sxgbe_tx_norm_desc *first_desc,
-		       struct sk_buff *skb)
+static void sxgbe_tso_prepare(struct sxgbe_priv_data *priv,
+			      struct sxgbe_tx_norm_desc *first_desc,
+			      struct sk_buff *skb)
 {
 	unsigned int total_hdr_len, tcp_hdr_len;
 
@@ -1914,40 +1913,6 @@ static void sxgbe_set_rx_mode(struct net_device *dev)
 		   readl(ioaddr + SXGBE_HASH_LOW));
 }
 
-/**
- * sxgbe_config - entry point for changing configuration mode passed on by
- * ifconfig
- * @dev : pointer to the device structure
- * @map : pointer to the device mapping structure
- * Description:
- * This function is a driver entry point which gets called by the kernel
- * whenever some device configuration is changed.
- * Return value:
- * This function returns 0 if success and appropriate error otherwise.
- */
-static int sxgbe_config(struct net_device *dev, struct ifmap *map)
-{
-	struct sxgbe_priv_data *priv = netdev_priv(dev);
-
-	/* Can't act on a running interface */
-	if (dev->flags & IFF_UP)
-		return -EBUSY;
-
-	/* Don't allow changing the I/O address */
-	if (map->base_addr != (unsigned long)priv->ioaddr) {
-		netdev_warn(dev, "can't change I/O address\n");
-		return -EOPNOTSUPP;
-	}
-
-	/* Don't allow changing the IRQ */
-	if (map->irq != priv->irq) {
-		netdev_warn(dev, "not change IRQ number %d\n", priv->irq);
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
 #ifdef CONFIG_NET_POLL_CONTROLLER
 /**
  * sxgbe_poll_controller - entry point for polling receive by device
@@ -2009,7 +1974,6 @@ static const struct net_device_ops sxgbe_netdev_ops = {
 	.ndo_set_rx_mode	= sxgbe_set_rx_mode,
 	.ndo_tx_timeout		= sxgbe_tx_timeout,
 	.ndo_do_ioctl		= sxgbe_ioctl,
-	.ndo_set_config		= sxgbe_config,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= sxgbe_poll_controller,
 #endif
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
index 56f8bf5a3f1..81437d91df9 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
@@ -188,7 +188,6 @@
 
 /* L3/L4 function registers */
 #define SXGBE_CORE_L34_ADDCTL_REG	0x0C00
-#define SXGBE_CORE_L34_ADDCTL_REG	0x0C00
 #define SXGBE_CORE_L34_DATA_REG		0x0C04
 
 /* ARP registers */
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 63d595fd3cc..1e274045970 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -2248,7 +2248,7 @@ static int efx_register_netdev(struct efx_nic *efx)
 	} else {
 		net_dev->netdev_ops = &efx_farch_netdev_ops;
 	}
-	SET_ETHTOOL_OPS(net_dev, &efx_ethtool_ops);
+	net_dev->ethtool_ops = &efx_ethtool_ops;
 	net_dev->gso_max_segs = EFX_TSO_MAX_SEGS;
 
 	rtnl_lock();
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 0de8b07c24c..74739c4b999 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -1033,7 +1033,7 @@ static u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev)
 		0 : ARRAY_SIZE(efx->rx_indir_table));
 }
 
-static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev, u32 *indir)
+static int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
@@ -1041,8 +1041,8 @@ static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev, u32 *indir)
 	return 0;
 }
 
-static int efx_ethtool_set_rxfh_indir(struct net_device *net_dev,
-				      const u32 *indir)
+static int efx_ethtool_set_rxfh(struct net_device *net_dev,
+				const u32 *indir, const u8 *key)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
@@ -1125,8 +1125,8 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.get_rxnfc		= efx_ethtool_get_rxnfc,
 	.set_rxnfc		= efx_ethtool_set_rxnfc,
 	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
-	.get_rxfh_indir		= efx_ethtool_get_rxfh_indir,
-	.set_rxfh_indir		= efx_ethtool_set_rxfh_indir,
+	.get_rxfh		= efx_ethtool_get_rxfh,
+	.set_rxfh		= efx_ethtool_set_rxfh,
 	.get_ts_info		= efx_ethtool_get_ts_info,
 	.get_module_info	= efx_ethtool_get_module_info,
 	.get_module_eeprom	= efx_ethtool_get_module_eeprom,
diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h
index 4d3f119b67b..afb94aa2c15 100644
--- a/drivers/net/ethernet/sfc/io.h
+++ b/drivers/net/ethernet/sfc/io.h
@@ -66,10 +66,17 @@
 #define EFX_USE_QWORD_IO 1
 #endif
 
+/* Hardware issue requires that only 64-bit naturally aligned writes
+ * are seen by hardware. Its not strictly necessary to restrict to
+ * x86_64 arch, but done for safety since unusual write combining behaviour
+ * can break PIO.
+ */
+#ifdef CONFIG_X86_64
 /* PIO is a win only if write-combining is possible */
 #ifdef ARCH_HAS_IOREMAP_WC
 #define EFX_USE_PIO 1
 #endif
+#endif
 
 #ifdef EFX_USE_QWORD_IO
 static inline void _efx_writeq(struct efx_nic *efx, __le64 value,
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
index 9a9205e7789..43d2e64546e 100644
--- a/drivers/net/ethernet/sfc/siena_sriov.c
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -1633,7 +1633,8 @@ int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i,
 
 	ivi->vf = vf_i;
 	ether_addr_copy(ivi->mac, vf->addr.mac_addr);
-	ivi->tx_rate = 0;
+	ivi->max_tx_rate = 0;
+	ivi->min_tx_rate = 0;
 	tci = ntohs(vf->addr.tci);
 	ivi->vlan = tci & VLAN_VID_MASK;
 	ivi->qos = (tci >> VLAN_PRIO_SHIFT) & 0x7;
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index fa947530041..ede8dcca0ff 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -189,6 +189,18 @@ struct efx_short_copy_buffer {
 	u8 buf[L1_CACHE_BYTES];
 };
 
+/* Copy in explicit 64-bit writes. */
+static void efx_memcpy_64(void __iomem *dest, void *src, size_t len)
+{
+	u64 *src64 = src;
+	u64 __iomem *dest64 = dest;
+	size_t l64 = len / 8;
+	size_t i;
+
+	for (i = 0; i < l64; i++)
+		writeq(src64[i], &dest64[i]);
+}
+
 /* Copy to PIO, respecting that writes to PIO buffers must be dword aligned.
  * Advances piobuf pointer. Leaves additional data in the copy buffer.
  */
@@ -198,7 +210,7 @@ static void efx_memcpy_toio_aligned(struct efx_nic *efx, u8 __iomem **piobuf,
 {
 	int block_len = len & ~(sizeof(copy_buf->buf) - 1);
 
-	memcpy_toio(*piobuf, data, block_len);
+	efx_memcpy_64(*piobuf, data, block_len);
 	*piobuf += block_len;
 	len -= block_len;
 
@@ -230,7 +242,7 @@ static void efx_memcpy_toio_aligned_cb(struct efx_nic *efx, u8 __iomem **piobuf,
 		if (copy_buf->used < sizeof(copy_buf->buf))
 			return;
 
-		memcpy_toio(*piobuf, copy_buf->buf, sizeof(copy_buf->buf));
+		efx_memcpy_64(*piobuf, copy_buf->buf, sizeof(copy_buf->buf));
 		*piobuf += sizeof(copy_buf->buf);
 		data += copy_to_buf;
 		len -= copy_to_buf;
@@ -245,7 +257,7 @@ static void efx_flush_copy_buffer(struct efx_nic *efx, u8 __iomem *piobuf,
 {
 	/* if there's anything in it, write the whole buffer, including junk */
 	if (copy_buf->used)
-		memcpy_toio(piobuf, copy_buf->buf, sizeof(copy_buf->buf));
+		efx_memcpy_64(piobuf, copy_buf->buf, sizeof(copy_buf->buf));
 }
 
 /* Traverse skb structure and copy fragments in to PIO buffer.
@@ -304,8 +316,8 @@ efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 		 */
 		BUILD_BUG_ON(L1_CACHE_BYTES >
 			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
-		memcpy_toio(tx_queue->piobuf, skb->data,
-			    ALIGN(skb->len, L1_CACHE_BYTES));
+		efx_memcpy_64(tx_queue->piobuf, skb->data,
+			      ALIGN(skb->len, L1_CACHE_BYTES));
 	}
 
 	EFX_POPULATE_QWORD_5(buffer->option,
diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c
index acbbe48a519..a86339903b9 100644
--- a/drivers/net/ethernet/sis/sis190.c
+++ b/drivers/net/ethernet/sis/sis190.c
@@ -1877,7 +1877,7 @@ static int sis190_init_one(struct pci_dev *pdev,
 
 	dev->netdev_ops = &sis190_netdev_ops;
 
-	SET_ETHTOOL_OPS(dev, &sis190_ethtool_ops);
+	dev->ethtool_ops = &sis190_ethtool_ops;
 	dev->watchdog_timeo = SIS190_TX_TIMEOUT;
 
 	spin_lock_init(&tp->lock);
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index c7a4868571f..6b33127ab35 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -318,7 +318,7 @@ static int smc91c92_probe(struct pcmcia_device *link)
 
     /* The SMC91c92-specific entries in the device structure. */
     dev->netdev_ops = &smc_netdev_ops;
-    SET_ETHTOOL_OPS(dev, &ethtool_ops);
+    dev->ethtool_ops = &ethtool_ops;
     dev->watchdog_timeo = TX_TIMEOUT;
 
     smc->mii_if.dev = dev;
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index a0fc151da40..5e13fa5524a 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -2477,6 +2477,8 @@ static int smsc911x_drv_probe(struct platform_device *pdev)
 		goto out_disable_resources;
 	}
 
+	netif_carrier_off(dev);
+
 	retval = register_netdev(dev);
 	if (retval) {
 		SMSC_WARN(pdata, probe, "Error %i registering device", retval);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index b3e148ef568..9d3748361a1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -320,11 +320,8 @@ static void dwmac1000_set_eee_timer(void __iomem *ioaddr, int ls, int tw)
 
 static void dwmac1000_ctrl_ane(void __iomem *ioaddr, bool restart)
 {
-	u32 value;
-
-	value = readl(ioaddr + GMAC_AN_CTRL);
 	/* auto negotiation enable and External Loopback enable */
-	value = GMAC_AN_CTRL_ANE | GMAC_AN_CTRL_ELE;
+	u32 value = GMAC_AN_CTRL_ANE | GMAC_AN_CTRL_ELE;
 
 	if (restart)
 		value |= GMAC_AN_CTRL_RAN;
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 7e6628a9151..1e2bcf5f89e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -145,7 +145,7 @@ static void enh_desc_get_ext_status(void *data, struct stmmac_extra_stats *x,
 			x->rx_msg_type_delay_req++;
 		else if (p->des4.erx.msg_type == RDES_EXT_DELAY_RESP)
 			x->rx_msg_type_delay_resp++;
-		else if (p->des4.erx.msg_type == RDES_EXT_DELAY_REQ)
+		else if (p->des4.erx.msg_type == RDES_EXT_PDELAY_REQ)
 			x->rx_msg_type_pdelay_req++;
 		else if (p->des4.erx.msg_type == RDES_EXT_PDELAY_RESP)
 			x->rx_msg_type_pdelay_resp++;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index c5f9cb85c8e..c62e67f3c2f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -322,9 +322,7 @@ static int stmmac_ethtool_getsettings(struct net_device *dev,
 		return -EBUSY;
 	}
 	cmd->transceiver = XCVR_INTERNAL;
-	spin_lock_irq(&priv->lock);
 	rc = phy_ethtool_gset(phy, cmd);
-	spin_unlock_irq(&priv->lock);
 	return rc;
 }
 
@@ -431,8 +429,6 @@ stmmac_get_pauseparam(struct net_device *netdev,
 	if (priv->pcs)	/* FIXME */
 		return;
 
-	spin_lock(&priv->lock);
-
 	pause->rx_pause = 0;
 	pause->tx_pause = 0;
 	pause->autoneg = priv->phydev->autoneg;
@@ -442,7 +438,6 @@ stmmac_get_pauseparam(struct net_device *netdev,
 	if (priv->flow_ctrl & FLOW_TX)
 		pause->tx_pause = 1;
 
-	spin_unlock(&priv->lock);
 }
 
 static int
@@ -457,8 +452,6 @@ stmmac_set_pauseparam(struct net_device *netdev,
 	if (priv->pcs)	/* FIXME */
 		return -EOPNOTSUPP;
 
-	spin_lock(&priv->lock);
-
 	if (pause->rx_pause)
 		new_pause |= FLOW_RX;
 	if (pause->tx_pause)
@@ -473,7 +466,6 @@ stmmac_set_pauseparam(struct net_device *netdev,
 	} else
 		priv->hw->mac->flow_ctrl(priv->ioaddr, phy->duplex,
 					 priv->flow_ctrl, priv->pause);
-	spin_unlock(&priv->lock);
 	return ret;
 }
 
@@ -784,5 +776,5 @@ static const struct ethtool_ops stmmac_ethtool_ops = {
 
 void stmmac_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &stmmac_ethtool_ops);
+	netdev->ethtool_ops = &stmmac_ethtool_ops;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 0f4841d2e8d..057a1208e59 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1753,7 +1753,7 @@ static int stmmac_open(struct net_device *dev)
 	}
 
 	/* Request the IRQ lines */
-	if (priv->lpi_irq != -ENXIO) {
+	if (priv->lpi_irq > 0) {
 		ret = request_irq(priv->lpi_irq, stmmac_interrupt, IRQF_SHARED,
 				  dev->name, dev);
 		if (unlikely(ret < 0)) {
@@ -1813,7 +1813,7 @@ static int stmmac_release(struct net_device *dev)
 	free_irq(dev->irq, dev);
 	if (priv->wol_irq != dev->irq)
 		free_irq(priv->wol_irq, dev);
-	if (priv->lpi_irq != -ENXIO)
+	if (priv->lpi_irq > 0)
 		free_irq(priv->lpi_irq, dev);
 
 	/* Stop TX/RX DMA and clear the descriptors */
@@ -2212,27 +2212,6 @@ static void stmmac_tx_timeout(struct net_device *dev)
 	stmmac_tx_err(priv);
 }
 
-/* Configuration changes (passed on by ifconfig) */
-static int stmmac_config(struct net_device *dev, struct ifmap *map)
-{
-	if (dev->flags & IFF_UP)	/* can't act on a running interface */
-		return -EBUSY;
-
-	/* Don't allow changing the I/O address */
-	if (map->base_addr != dev->base_addr) {
-		pr_warn("%s: can't change I/O address\n", dev->name);
-		return -EOPNOTSUPP;
-	}
-
-	/* Don't allow changing the IRQ */
-	if (map->irq != dev->irq) {
-		pr_warn("%s: not change IRQ number %d\n", dev->name, dev->irq);
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
 /**
  *  stmmac_set_rx_mode - entry point for multicast addressing
  *  @dev : pointer to the device structure
@@ -2598,7 +2577,6 @@ static const struct net_device_ops stmmac_netdev_ops = {
 	.ndo_set_rx_mode = stmmac_set_rx_mode,
 	.ndo_tx_timeout = stmmac_tx_timeout,
 	.ndo_do_ioctl = stmmac_ioctl,
-	.ndo_set_config = stmmac_config,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = stmmac_poll_controller,
 #endif
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index a468eb10782..a5b1e1b776f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -205,10 +205,13 @@ int stmmac_mdio_register(struct net_device *ndev)
 	if (new_bus == NULL)
 		return -ENOMEM;
 
-	if (mdio_bus_data->irqs)
+	if (mdio_bus_data->irqs) {
 		irqlist = mdio_bus_data->irqs;
-	else
+	} else {
+		for (addr = 0; addr < PHY_MAX_ADDR; addr++)
+			priv->mii_irq[addr] = PHY_POLL;
 		irqlist = priv->mii_irq;
+	}
 
 #ifdef CONFIG_OF
 	if (priv->device->of_node)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 46aef5108be..ea7a65be1f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -237,10 +237,12 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
 
 	/* Get the MAC information */
 	priv->dev->irq = platform_get_irq_byname(pdev, "macirq");
-	if (priv->dev->irq == -ENXIO) {
-		pr_err("%s: ERROR: MAC IRQ configuration "
-		       "information not found\n", __func__);
-		return -ENXIO;
+	if (priv->dev->irq < 0) {
+		if (priv->dev->irq != -EPROBE_DEFER) {
+			netdev_err(priv->dev,
+				   "MAC IRQ configuration information not found\n");
+		}
+		return priv->dev->irq;
 	}
 
 	/*
@@ -252,10 +254,15 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
 	 * so the driver will continue to use the mac irq (ndev->irq)
 	 */
 	priv->wol_irq = platform_get_irq_byname(pdev, "eth_wake_irq");
-	if (priv->wol_irq == -ENXIO)
+	if (priv->wol_irq < 0) {
+		if (priv->wol_irq == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
 		priv->wol_irq = priv->dev->irq;
+	}
 
 	priv->lpi_irq = platform_get_irq_byname(pdev, "eth_lpi");
+	if (priv->lpi_irq == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
 
 	platform_set_drvdata(pdev, priv->dev);
 
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 1c24a8f368b..d813bfb1a84 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -610,6 +610,13 @@ static int __vnet_tx_trigger(struct vnet_port *port)
 	return err;
 }
 
+static inline bool port_is_up(struct vnet_port *vnet)
+{
+	struct vio_driver_state *vio = &vnet->vio;
+
+	return !!(vio->hs_state & VIO_HS_COMPLETE);
+}
+
 struct vnet_port *__tx_port_find(struct vnet *vp, struct sk_buff *skb)
 {
 	unsigned int hash = vnet_hashfn(skb->data);
@@ -617,14 +624,19 @@ struct vnet_port *__tx_port_find(struct vnet *vp, struct sk_buff *skb)
 	struct vnet_port *port;
 
 	hlist_for_each_entry(port, hp, hash) {
+		if (!port_is_up(port))
+			continue;
 		if (ether_addr_equal(port->raddr, skb->data))
 			return port;
 	}
-	port = NULL;
-	if (!list_empty(&vp->port_list))
-		port = list_entry(vp->port_list.next, struct vnet_port, list);
-
-	return port;
+	list_for_each_entry(port, &vp->port_list, list) {
+		if (!port->switch_port)
+			continue;
+		if (!port_is_up(port))
+			continue;
+		return port;
+	}
+	return NULL;
 }
 
 struct vnet_port *tx_port_find(struct vnet *vp, struct sk_buff *skb)
@@ -1083,6 +1095,24 @@ static struct vnet *vnet_find_or_create(const u64 *local_mac)
 	return vp;
 }
 
+static void vnet_cleanup(void)
+{
+	struct vnet *vp;
+	struct net_device *dev;
+
+	mutex_lock(&vnet_list_mutex);
+	while (!list_empty(&vnet_list)) {
+		vp = list_first_entry(&vnet_list, struct vnet, list);
+		list_del(&vp->list);
+		dev = vp->dev;
+		/* vio_unregister_driver() should have cleaned up port_list */
+		BUG_ON(!list_empty(&vp->port_list));
+		unregister_netdev(dev);
+		free_netdev(dev);
+	}
+	mutex_unlock(&vnet_list_mutex);
+}
+
 static const char *local_mac_prop = "local-mac-address";
 
 static struct vnet *vnet_find_parent(struct mdesc_handle *hp,
@@ -1240,7 +1270,6 @@ static int vnet_port_remove(struct vio_dev *vdev)
 
 		kfree(port);
 
-		unregister_netdev(vp->dev);
 	}
 	return 0;
 }
@@ -1268,6 +1297,7 @@ static int __init vnet_init(void)
 static void __exit vnet_exit(void)
 {
 	vio_unregister_driver(&vnet_port_driver);
+	vnet_cleanup();
 }
 
 module_init(vnet_init);
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 2ead87759ab..38da73a2a88 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -2413,7 +2413,7 @@ static void bdx_set_ethtool_ops(struct net_device *netdev)
 		.get_ethtool_stats = bdx_get_ethtool_stats,
 	};
 
-	SET_ETHTOOL_OPS(netdev, &bdx_ethtool_ops);
+	netdev->ethtool_ops = &bdx_ethtool_ops;
 }
 
 /**
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index 73f74f36943..7399a52f7c2 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -313,19 +313,6 @@ static int mii_irqs[PHY_MAX_ADDR] = { PHY_POLL, };
 
 static struct mii_bus *cpmac_mii;
 
-static int cpmac_config(struct net_device *dev, struct ifmap *map)
-{
-	if (dev->flags & IFF_UP)
-		return -EBUSY;
-
-	/* Don't allow changing the I/O address */
-	if (map->base_addr != dev->base_addr)
-		return -EOPNOTSUPP;
-
-	/* ignore other fields */
-	return 0;
-}
-
 static void cpmac_set_multicast_list(struct net_device *dev)
 {
 	struct netdev_hw_addr *ha;
@@ -1100,7 +1087,6 @@ static const struct net_device_ops cpmac_netdev_ops = {
 	.ndo_tx_timeout		= cpmac_tx_timeout,
 	.ndo_set_rx_mode	= cpmac_set_multicast_list,
 	.ndo_do_ioctl		= cpmac_ioctl,
-	.ndo_set_config		= cpmac_config,
 	.ndo_change_mtu		= eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c
index 148da9ae836..aa8bf45e53d 100644
--- a/drivers/net/ethernet/ti/cpsw-phy-sel.c
+++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c
@@ -29,6 +29,8 @@
 #define AM33XX_GMII_SEL_RMII2_IO_CLK_EN	BIT(7)
 #define AM33XX_GMII_SEL_RMII1_IO_CLK_EN	BIT(6)
 
+#define GMII_SEL_MODE_MASK		0x3
+
 struct cpsw_phy_sel_priv {
 	struct device	*dev;
 	u32 __iomem	*gmii_sel;
@@ -65,7 +67,7 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv,
 		break;
 	};
 
-	mask = 0x3 << (slave * 2) | BIT(slave + 6);
+	mask = GMII_SEL_MODE_MASK << (slave * 2) | BIT(slave + 6);
 	mode <<= slave * 2;
 
 	if (priv->rmii_clock_external) {
@@ -81,6 +83,55 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv,
 	writel(reg, priv->gmii_sel);
 }
 
+static void cpsw_gmii_sel_dra7xx(struct cpsw_phy_sel_priv *priv,
+				 phy_interface_t phy_mode, int slave)
+{
+	u32 reg;
+	u32 mask;
+	u32 mode = 0;
+
+	reg = readl(priv->gmii_sel);
+
+	switch (phy_mode) {
+	case PHY_INTERFACE_MODE_RMII:
+		mode = AM33XX_GMII_SEL_MODE_RMII;
+		break;
+
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		mode = AM33XX_GMII_SEL_MODE_RGMII;
+		break;
+
+	case PHY_INTERFACE_MODE_MII:
+	default:
+		mode = AM33XX_GMII_SEL_MODE_MII;
+		break;
+	};
+
+	switch (slave) {
+	case 0:
+		mask = GMII_SEL_MODE_MASK;
+		break;
+	case 1:
+		mask = GMII_SEL_MODE_MASK << 4;
+		mode <<= 4;
+		break;
+	default:
+		dev_err(priv->dev, "invalid slave number...\n");
+		return;
+	}
+
+	if (priv->rmii_clock_external)
+		dev_err(priv->dev, "RMII External clock is not supported\n");
+
+	reg &= ~mask;
+	reg |= mode;
+
+	writel(reg, priv->gmii_sel);
+}
+
 static struct platform_driver cpsw_phy_sel_driver;
 static int match(struct device *dev, void *data)
 {
@@ -112,6 +163,14 @@ static const struct of_device_id cpsw_phy_sel_id_table[] = {
 		.compatible	= "ti,am3352-cpsw-phy-sel",
 		.data		= &cpsw_gmii_sel_am3352,
 	},
+	{
+		.compatible	= "ti,dra7xx-cpsw-phy-sel",
+		.data		= &cpsw_gmii_sel_dra7xx,
+	},
+	{
+		.compatible	= "ti,am43xx-cpsw-phy-sel",
+		.data		= &cpsw_gmii_sel_am3352,
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, cpsw_phy_sel_id_table);
@@ -132,6 +191,7 @@ static int cpsw_phy_sel_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	priv->dev = &pdev->dev;
 	priv->cpsw_phy_sel = of_id->data;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "gmii-sel");
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index c331b7ebc81..b988d16cd34 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -143,13 +143,13 @@ do {								\
 		u32 i;		\
 		for (i = 0; i < priv->num_irqs; i++) \
 			enable_irq(priv->irqs_table[i]); \
-	} while (0);
+	} while (0)
 #define cpsw_disable_irq(priv)	\
 	do {			\
 		u32 i;		\
 		for (i = 0; i < priv->num_irqs; i++) \
 			disable_irq_nosync(priv->irqs_table[i]); \
-	} while (0);
+	} while (0)
 
 #define cpsw_slave_index(priv)				\
 		((priv->data.dual_emac) ? priv->emac_port :	\
@@ -248,20 +248,31 @@ struct cpsw_ss_regs {
 #define TS_131              (1<<11) /* Time Sync Dest IP Addr 131 enable */
 #define TS_130              (1<<10) /* Time Sync Dest IP Addr 130 enable */
 #define TS_129              (1<<9)  /* Time Sync Dest IP Addr 129 enable */
-#define TS_BIT8             (1<<8)  /* ts_ttl_nonzero? */
+#define TS_TTL_NONZERO      (1<<8)  /* Time Sync Time To Live Non-zero enable */
+#define TS_ANNEX_F_EN       (1<<6)  /* Time Sync Annex F enable */
 #define TS_ANNEX_D_EN       (1<<4)  /* Time Sync Annex D enable */
 #define TS_LTYPE2_EN        (1<<3)  /* Time Sync LTYPE 2 enable */
 #define TS_LTYPE1_EN        (1<<2)  /* Time Sync LTYPE 1 enable */
 #define TS_TX_EN            (1<<1)  /* Time Sync Transmit Enable */
 #define TS_RX_EN            (1<<0)  /* Time Sync Receive Enable */
 
-#define CTRL_TS_BITS \
-	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 | TS_BIT8 | \
-	 TS_ANNEX_D_EN | TS_LTYPE1_EN)
+#define CTRL_V2_TS_BITS \
+	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
+	 TS_TTL_NONZERO  | TS_ANNEX_D_EN | TS_LTYPE1_EN)
+
+#define CTRL_V2_ALL_TS_MASK (CTRL_V2_TS_BITS | TS_TX_EN | TS_RX_EN)
+#define CTRL_V2_TX_TS_BITS  (CTRL_V2_TS_BITS | TS_TX_EN)
+#define CTRL_V2_RX_TS_BITS  (CTRL_V2_TS_BITS | TS_RX_EN)
+
+
+#define CTRL_V3_TS_BITS \
+	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
+	 TS_TTL_NONZERO | TS_ANNEX_F_EN | TS_ANNEX_D_EN |\
+	 TS_LTYPE1_EN)
 
-#define CTRL_ALL_TS_MASK (CTRL_TS_BITS | TS_TX_EN | TS_RX_EN)
-#define CTRL_TX_TS_BITS  (CTRL_TS_BITS | TS_TX_EN)
-#define CTRL_RX_TS_BITS  (CTRL_TS_BITS | TS_RX_EN)
+#define CTRL_V3_ALL_TS_MASK (CTRL_V3_TS_BITS | TS_TX_EN | TS_RX_EN)
+#define CTRL_V3_TX_TS_BITS  (CTRL_V3_TS_BITS | TS_TX_EN)
+#define CTRL_V3_RX_TS_BITS  (CTRL_V3_TS_BITS | TS_RX_EN)
 
 /* Bit definitions for the CPSW2_TS_SEQ_MTYPE register */
 #define TS_SEQ_ID_OFFSET_SHIFT   (16)    /* Time Sync Sequence ID Offset */
@@ -1201,7 +1212,12 @@ static int cpsw_ndo_open(struct net_device *ndev)
 	for_each_slave(priv, cpsw_slave_open, priv);
 
 	/* Add default VLAN */
-	cpsw_add_default_vlan(priv);
+	if (!priv->data.dual_emac)
+		cpsw_add_default_vlan(priv);
+	else
+		cpsw_ale_add_vlan(priv->ale, priv->data.default_vlan,
+				  ALE_ALL_PORTS << priv->host_port,
+				  ALE_ALL_PORTS << priv->host_port, 0, 0);
 
 	if (!cpsw_common_res_usage_state(priv)) {
 		/* setup tx dma to fixed prio and zero offset */
@@ -1376,13 +1392,27 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
 		slave = &priv->slaves[priv->data.active_slave];
 
 	ctrl = slave_read(slave, CPSW2_CONTROL);
-	ctrl &= ~CTRL_ALL_TS_MASK;
+	switch (priv->version) {
+	case CPSW_VERSION_2:
+		ctrl &= ~CTRL_V2_ALL_TS_MASK;
 
-	if (priv->cpts->tx_enable)
-		ctrl |= CTRL_TX_TS_BITS;
+		if (priv->cpts->tx_enable)
+			ctrl |= CTRL_V2_TX_TS_BITS;
 
-	if (priv->cpts->rx_enable)
-		ctrl |= CTRL_RX_TS_BITS;
+		if (priv->cpts->rx_enable)
+			ctrl |= CTRL_V2_RX_TS_BITS;
+	break;
+	case CPSW_VERSION_3:
+	default:
+		ctrl &= ~CTRL_V3_ALL_TS_MASK;
+
+		if (priv->cpts->tx_enable)
+			ctrl |= CTRL_V3_TX_TS_BITS;
+
+		if (priv->cpts->rx_enable)
+			ctrl |= CTRL_V3_RX_TS_BITS;
+	break;
+	}
 
 	mtype = (30 << TS_SEQ_ID_OFFSET_SHIFT) | EVENT_MSG_BITS;
 
@@ -1398,7 +1428,8 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	struct hwtstamp_config cfg;
 
 	if (priv->version != CPSW_VERSION_1 &&
-	    priv->version != CPSW_VERSION_2)
+	    priv->version != CPSW_VERSION_2 &&
+	    priv->version != CPSW_VERSION_3)
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
@@ -1443,6 +1474,7 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 		cpsw_hwtstamp_v1(priv);
 		break;
 	case CPSW_VERSION_2:
+	case CPSW_VERSION_3:
 		cpsw_hwtstamp_v2(priv);
 		break;
 	default:
@@ -1459,7 +1491,8 @@ static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 	struct hwtstamp_config cfg;
 
 	if (priv->version != CPSW_VERSION_1 &&
-	    priv->version != CPSW_VERSION_2)
+	    priv->version != CPSW_VERSION_2 &&
+	    priv->version != CPSW_VERSION_3)
 		return -EOPNOTSUPP;
 
 	cfg.flags = 0;
@@ -1780,25 +1813,25 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		return -EINVAL;
 
 	if (of_property_read_u32(node, "slaves", &prop)) {
-		pr_err("Missing slaves property in the DT.\n");
+		dev_err(&pdev->dev, "Missing slaves property in the DT.\n");
 		return -EINVAL;
 	}
 	data->slaves = prop;
 
 	if (of_property_read_u32(node, "active_slave", &prop)) {
-		pr_err("Missing active_slave property in the DT.\n");
+		dev_err(&pdev->dev, "Missing active_slave property in the DT.\n");
 		return -EINVAL;
 	}
 	data->active_slave = prop;
 
 	if (of_property_read_u32(node, "cpts_clock_mult", &prop)) {
-		pr_err("Missing cpts_clock_mult property in the DT.\n");
+		dev_err(&pdev->dev, "Missing cpts_clock_mult property in the DT.\n");
 		return -EINVAL;
 	}
 	data->cpts_clock_mult = prop;
 
 	if (of_property_read_u32(node, "cpts_clock_shift", &prop)) {
-		pr_err("Missing cpts_clock_shift property in the DT.\n");
+		dev_err(&pdev->dev, "Missing cpts_clock_shift property in the DT.\n");
 		return -EINVAL;
 	}
 	data->cpts_clock_shift = prop;
@@ -1810,31 +1843,31 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		return -ENOMEM;
 
 	if (of_property_read_u32(node, "cpdma_channels", &prop)) {
-		pr_err("Missing cpdma_channels property in the DT.\n");
+		dev_err(&pdev->dev, "Missing cpdma_channels property in the DT.\n");
 		return -EINVAL;
 	}
 	data->channels = prop;
 
 	if (of_property_read_u32(node, "ale_entries", &prop)) {
-		pr_err("Missing ale_entries property in the DT.\n");
+		dev_err(&pdev->dev, "Missing ale_entries property in the DT.\n");
 		return -EINVAL;
 	}
 	data->ale_entries = prop;
 
 	if (of_property_read_u32(node, "bd_ram_size", &prop)) {
-		pr_err("Missing bd_ram_size property in the DT.\n");
+		dev_err(&pdev->dev, "Missing bd_ram_size property in the DT.\n");
 		return -EINVAL;
 	}
 	data->bd_ram_size = prop;
 
 	if (of_property_read_u32(node, "rx_descs", &prop)) {
-		pr_err("Missing rx_descs property in the DT.\n");
+		dev_err(&pdev->dev, "Missing rx_descs property in the DT.\n");
 		return -EINVAL;
 	}
 	data->rx_descs = prop;
 
 	if (of_property_read_u32(node, "mac_control", &prop)) {
-		pr_err("Missing mac_control property in the DT.\n");
+		dev_err(&pdev->dev, "Missing mac_control property in the DT.\n");
 		return -EINVAL;
 	}
 	data->mac_control = prop;
@@ -1848,7 +1881,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 	ret = of_platform_populate(node, NULL, NULL, &pdev->dev);
 	/* We do not want to force this, as in some cases may not have child */
 	if (ret)
-		pr_warn("Doesn't have any child node\n");
+		dev_warn(&pdev->dev, "Doesn't have any child node\n");
 
 	for_each_child_of_node(node, slave_node) {
 		struct cpsw_slave_data *slave_data = data->slave_data + i;
@@ -1865,7 +1898,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 
 		parp = of_get_property(slave_node, "phy_id", &lenp);
 		if ((parp == NULL) || (lenp != (sizeof(void *) * 2))) {
-			pr_err("Missing slave[%d] phy_id property\n", i);
+			dev_err(&pdev->dev, "Missing slave[%d] phy_id property\n", i);
 			return -EINVAL;
 		}
 		mdio_node = of_find_node_by_phandle(be32_to_cpup(parp));
@@ -1885,18 +1918,18 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 
 		slave_data->phy_if = of_get_phy_mode(slave_node);
 		if (slave_data->phy_if < 0) {
-			pr_err("Missing or malformed slave[%d] phy-mode property\n",
-			       i);
+			dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n",
+				i);
 			return slave_data->phy_if;
 		}
 
 		if (data->dual_emac) {
 			if (of_property_read_u32(slave_node, "dual_emac_res_vlan",
 						 &prop)) {
-				pr_err("Missing dual_emac_res_vlan in DT.\n");
+				dev_err(&pdev->dev, "Missing dual_emac_res_vlan in DT.\n");
 				slave_data->dual_emac_res_vlan = i+1;
-				pr_err("Using %d as Reserved VLAN for %d slave\n",
-				       slave_data->dual_emac_res_vlan, i);
+				dev_err(&pdev->dev, "Using %d as Reserved VLAN for %d slave\n",
+					slave_data->dual_emac_res_vlan, i);
 			} else {
 				slave_data->dual_emac_res_vlan = prop;
 			}
@@ -1920,7 +1953,7 @@ static int cpsw_probe_dual_emac(struct platform_device *pdev,
 
 	ndev = alloc_etherdev(sizeof(struct cpsw_priv));
 	if (!ndev) {
-		pr_err("cpsw: error allocating net_device\n");
+		dev_err(&pdev->dev, "cpsw: error allocating net_device\n");
 		return -ENOMEM;
 	}
 
@@ -1936,10 +1969,10 @@ static int cpsw_probe_dual_emac(struct platform_device *pdev,
 	if (is_valid_ether_addr(data->slave_data[1].mac_addr)) {
 		memcpy(priv_sl2->mac_addr, data->slave_data[1].mac_addr,
 			ETH_ALEN);
-		pr_info("cpsw: Detected MACID = %pM\n", priv_sl2->mac_addr);
+		dev_info(&pdev->dev, "cpsw: Detected MACID = %pM\n", priv_sl2->mac_addr);
 	} else {
 		random_ether_addr(priv_sl2->mac_addr);
-		pr_info("cpsw: Random MACID = %pM\n", priv_sl2->mac_addr);
+		dev_info(&pdev->dev, "cpsw: Random MACID = %pM\n", priv_sl2->mac_addr);
 	}
 	memcpy(ndev->dev_addr, priv_sl2->mac_addr, ETH_ALEN);
 
@@ -1970,14 +2003,14 @@ static int cpsw_probe_dual_emac(struct platform_device *pdev,
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &cpsw_ethtool_ops);
+	ndev->ethtool_ops = &cpsw_ethtool_ops;
 	netif_napi_add(ndev, &priv_sl2->napi, cpsw_poll, CPSW_POLL_WEIGHT);
 
 	/* register the network device */
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 	ret = register_netdev(ndev);
 	if (ret) {
-		pr_err("cpsw: error registering net device\n");
+		dev_err(&pdev->dev, "cpsw: error registering net device\n");
 		free_netdev(ndev);
 		ret = -ENODEV;
 	}
@@ -1999,7 +2032,7 @@ static int cpsw_probe(struct platform_device *pdev)
 
 	ndev = alloc_etherdev(sizeof(struct cpsw_priv));
 	if (!ndev) {
-		pr_err("error allocating net_device\n");
+		dev_err(&pdev->dev, "error allocating net_device\n");
 		return -ENOMEM;
 	}
 
@@ -2014,7 +2047,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	priv->cpts = devm_kzalloc(&pdev->dev, sizeof(struct cpts), GFP_KERNEL);
 	priv->irq_enabled = true;
 	if (!priv->cpts) {
-		pr_err("error allocating cpts\n");
+		dev_err(&pdev->dev, "error allocating cpts\n");
 		goto clean_ndev_ret;
 	}
 
@@ -2027,7 +2060,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	pinctrl_pm_select_default_state(&pdev->dev);
 
 	if (cpsw_probe_dt(&priv->data, pdev)) {
-		pr_err("cpsw: platform data missing\n");
+		dev_err(&pdev->dev, "cpsw: platform data missing\n");
 		ret = -ENODEV;
 		goto clean_runtime_disable_ret;
 	}
@@ -2035,10 +2068,10 @@ static int cpsw_probe(struct platform_device *pdev)
 
 	if (is_valid_ether_addr(data->slave_data[0].mac_addr)) {
 		memcpy(priv->mac_addr, data->slave_data[0].mac_addr, ETH_ALEN);
-		pr_info("Detected MACID = %pM\n", priv->mac_addr);
+		dev_info(&pdev->dev, "Detected MACID = %pM\n", priv->mac_addr);
 	} else {
 		eth_random_addr(priv->mac_addr);
-		pr_info("Random MACID = %pM\n", priv->mac_addr);
+		dev_info(&pdev->dev, "Random MACID = %pM\n", priv->mac_addr);
 	}
 
 	memcpy(ndev->dev_addr, priv->mac_addr, ETH_ALEN);
@@ -2199,7 +2232,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &cpsw_ethtool_ops);
+	ndev->ethtool_ops = &cpsw_ethtool_ops;
 	netif_napi_add(ndev, &priv->napi, cpsw_poll, CPSW_POLL_WEIGHT);
 
 	/* register the network device */
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 243513980b5..6b56f85951e 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -236,13 +236,11 @@ static void cpts_overflow_check(struct work_struct *work)
 	schedule_delayed_work(&cpts->overflow_work, CPTS_OVERFLOW_PERIOD);
 }
 
-#define CPTS_REF_CLOCK_NAME "cpsw_cpts_rft_clk"
-
-static void cpts_clk_init(struct cpts *cpts)
+static void cpts_clk_init(struct device *dev, struct cpts *cpts)
 {
-	cpts->refclk = clk_get(NULL, CPTS_REF_CLOCK_NAME);
+	cpts->refclk = devm_clk_get(dev, "cpts");
 	if (IS_ERR(cpts->refclk)) {
-		pr_err("Failed to clk_get %s\n", CPTS_REF_CLOCK_NAME);
+		dev_err(dev, "Failed to get cpts refclk\n");
 		cpts->refclk = NULL;
 		return;
 	}
@@ -252,7 +250,6 @@ static void cpts_clk_init(struct cpts *cpts)
 static void cpts_clk_release(struct cpts *cpts)
 {
 	clk_disable(cpts->refclk);
-	clk_put(cpts->refclk);
 }
 
 static int cpts_match(struct sk_buff *skb, unsigned int ptp_class,
@@ -390,7 +387,7 @@ int cpts_register(struct device *dev, struct cpts *cpts,
 	for (i = 0; i < CPTS_MAX_EVENTS; i++)
 		list_add(&cpts->pool_data[i].list, &cpts->pool);
 
-	cpts_clk_init(cpts);
+	cpts_clk_init(dev, cpts);
 	cpts_write32(cpts, CPTS_EN, control);
 	cpts_write32(cpts, TS_PEND_EN, int_enable);
 
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 88ef27067bf..4a000f6dd6f 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -158,9 +158,9 @@ cpdma_desc_pool_create(struct device *dev, u32 phys, u32 hw_addr,
 	int bitmap_size;
 	struct cpdma_desc_pool *pool;
 
-	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	pool = devm_kzalloc(dev, sizeof(*pool), GFP_KERNEL);
 	if (!pool)
-		return NULL;
+		goto fail;
 
 	spin_lock_init(&pool->lock);
 
@@ -170,7 +170,7 @@ cpdma_desc_pool_create(struct device *dev, u32 phys, u32 hw_addr,
 	pool->num_desc	= size / pool->desc_size;
 
 	bitmap_size  = (pool->num_desc / BITS_PER_LONG) * sizeof(long);
-	pool->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	pool->bitmap = devm_kzalloc(dev, bitmap_size, GFP_KERNEL);
 	if (!pool->bitmap)
 		goto fail;
 
@@ -187,10 +187,7 @@ cpdma_desc_pool_create(struct device *dev, u32 phys, u32 hw_addr,
 
 	if (pool->iomap)
 		return pool;
-
 fail:
-	kfree(pool->bitmap);
-	kfree(pool);
 	return NULL;
 }
 
@@ -203,7 +200,6 @@ static void cpdma_desc_pool_destroy(struct cpdma_desc_pool *pool)
 
 	spin_lock_irqsave(&pool->lock, flags);
 	WARN_ON(pool->used_desc);
-	kfree(pool->bitmap);
 	if (pool->cpumap) {
 		dma_free_coherent(pool->dev, pool->mem_size, pool->cpumap,
 				  pool->phys);
@@ -211,7 +207,6 @@ static void cpdma_desc_pool_destroy(struct cpdma_desc_pool *pool)
 		iounmap(pool->iomap);
 	}
 	spin_unlock_irqrestore(&pool->lock, flags);
-	kfree(pool);
 }
 
 static inline dma_addr_t desc_phys(struct cpdma_desc_pool *pool,
@@ -276,7 +271,7 @@ struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params)
 {
 	struct cpdma_ctlr *ctlr;
 
-	ctlr = kzalloc(sizeof(*ctlr), GFP_KERNEL);
+	ctlr = devm_kzalloc(params->dev, sizeof(*ctlr), GFP_KERNEL);
 	if (!ctlr)
 		return NULL;
 
@@ -290,10 +285,8 @@ struct cpdma_ctlr *cpdma_ctlr_create(struct cpdma_params *params)
 					    ctlr->params.desc_hw_addr,
 					    ctlr->params.desc_mem_size,
 					    ctlr->params.desc_align);
-	if (!ctlr->pool) {
-		kfree(ctlr);
+	if (!ctlr->pool)
 		return NULL;
-	}
 
 	if (WARN_ON(ctlr->num_chan > CPDMA_MAX_CHANNELS))
 		ctlr->num_chan = CPDMA_MAX_CHANNELS;
@@ -468,7 +461,6 @@ int cpdma_ctlr_destroy(struct cpdma_ctlr *ctlr)
 
 	cpdma_desc_pool_destroy(ctlr->pool);
 	spin_unlock_irqrestore(&ctlr->lock, flags);
-	kfree(ctlr);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(cpdma_ctlr_destroy);
@@ -507,21 +499,22 @@ struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
 				     cpdma_handler_fn handler)
 {
 	struct cpdma_chan *chan;
-	int ret, offset = (chan_num % CPDMA_MAX_CHANNELS) * 4;
+	int offset = (chan_num % CPDMA_MAX_CHANNELS) * 4;
 	unsigned long flags;
 
 	if (__chan_linear(chan_num) >= ctlr->num_chan)
 		return NULL;
 
-	ret = -ENOMEM;
-	chan = kzalloc(sizeof(*chan), GFP_KERNEL);
+	chan = devm_kzalloc(ctlr->dev, sizeof(*chan), GFP_KERNEL);
 	if (!chan)
-		goto err_chan_alloc;
+		return ERR_PTR(-ENOMEM);
 
 	spin_lock_irqsave(&ctlr->lock, flags);
-	ret = -EBUSY;
-	if (ctlr->channels[chan_num])
-		goto err_chan_busy;
+	if (ctlr->channels[chan_num]) {
+		spin_unlock_irqrestore(&ctlr->lock, flags);
+		devm_kfree(ctlr->dev, chan);
+		return ERR_PTR(-EBUSY);
+	}
 
 	chan->ctlr	= ctlr;
 	chan->state	= CPDMA_STATE_IDLE;
@@ -551,12 +544,6 @@ struct cpdma_chan *cpdma_chan_create(struct cpdma_ctlr *ctlr, int chan_num,
 	ctlr->channels[chan_num] = chan;
 	spin_unlock_irqrestore(&ctlr->lock, flags);
 	return chan;
-
-err_chan_busy:
-	spin_unlock_irqrestore(&ctlr->lock, flags);
-	kfree(chan);
-err_chan_alloc:
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(cpdma_chan_create);
 
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 8f0e69ce07c..35a139e9a83 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1567,7 +1567,6 @@ static int emac_dev_open(struct net_device *ndev)
 	while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ,
 					    res_num))) {
 		for (irq_num = res->start; irq_num <= res->end; irq_num++) {
-			dev_err(emac_dev, "Request IRQ %d\n", irq_num);
 			if (request_irq(irq_num, emac_irq, 0, ndev->name,
 					ndev)) {
 				dev_err(emac_dev,
@@ -1865,7 +1864,6 @@ static int davinci_emac_probe(struct platform_device *pdev)
 	struct emac_priv *priv;
 	unsigned long hw_ram_addr;
 	struct emac_platform_data *pdata;
-	struct device *emac_dev;
 	struct cpdma_params dma_params;
 	struct clk *emac_clk;
 	unsigned long emac_bus_frequency;
@@ -1911,7 +1909,6 @@ static int davinci_emac_probe(struct platform_device *pdev)
 	priv->coal_intvl = 0;
 	priv->bus_freq_mhz = (u32)(emac_bus_frequency / 1000000);
 
-	emac_dev = &ndev->dev;
 	/* Get EMAC platform data */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	priv->emac_base_phys = res->start + pdata->ctrl_reg_offset;
@@ -1930,7 +1927,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
 		hw_ram_addr = (u32 __force)res->start + pdata->ctrl_ram_offset;
 
 	memset(&dma_params, 0, sizeof(dma_params));
-	dma_params.dev			= emac_dev;
+	dma_params.dev			= &pdev->dev;
 	dma_params.dmaregs		= priv->emac_base;
 	dma_params.rxthresh		= priv->emac_base + 0x120;
 	dma_params.rxfree		= priv->emac_base + 0x140;
@@ -1980,7 +1977,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
 	}
 
 	ndev->netdev_ops = &emac_netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &ethtool_ops);
+	ndev->ethtool_ops = &ethtool_ops;
 	netif_napi_add(ndev, &priv->napi, emac_poll, EMAC_POLL_WEIGHT);
 
 	/* register the network device */
@@ -1994,7 +1991,7 @@ static int davinci_emac_probe(struct platform_device *pdev)
 
 
 	if (netif_msg_probe(priv)) {
-		dev_notice(emac_dev, "DaVinci EMAC Probe found device "\
+		dev_notice(&pdev->dev, "DaVinci EMAC Probe found device "
 			   "(regs: %p, irq: %d)\n",
 			   (void *)priv->emac_base_phys, ndev->irq);
 	}
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index 0cca9dec5d8..735dc53d4b0 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -303,7 +303,7 @@ static int davinci_mdio_probe_dt(struct mdio_platform_data *data,
 		return -EINVAL;
 
 	if (of_property_read_u32(node, "bus_freq", &prop)) {
-		pr_err("Missing bus_freq property in the DT.\n");
+		dev_err(&pdev->dev, "Missing bus_freq property in the DT.\n");
 		return -EINVAL;
 	}
 	data->bus_freq = prop;
@@ -321,15 +321,14 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	struct phy_device *phy;
 	int ret, addr;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	data->bus = mdiobus_alloc();
+	data->bus = devm_mdiobus_alloc(dev);
 	if (!data->bus) {
 		dev_err(dev, "failed to alloc mii bus\n");
-		ret = -ENOMEM;
-		goto bail_out;
+		return -ENOMEM;
 	}
 
 	if (dev->of_node) {
@@ -349,12 +348,9 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	data->bus->parent	= dev;
 	data->bus->priv		= data;
 
-	/* Select default pin state */
-	pinctrl_pm_select_default_state(&pdev->dev);
-
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
-	data->clk = clk_get(&pdev->dev, "fck");
+	data->clk = devm_clk_get(dev, "fck");
 	if (IS_ERR(data->clk)) {
 		dev_err(dev, "failed to get device clock\n");
 		ret = PTR_ERR(data->clk);
@@ -367,24 +363,9 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	spin_lock_init(&data->lock);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "could not find register map resource\n");
-		ret = -ENOENT;
-		goto bail_out;
-	}
-
-	res = devm_request_mem_region(dev, res->start, resource_size(res),
-					    dev_name(dev));
-	if (!res) {
-		dev_err(dev, "could not allocate register map resource\n");
-		ret = -ENXIO;
-		goto bail_out;
-	}
-
-	data->regs = devm_ioremap_nocache(dev, res->start, resource_size(res));
-	if (!data->regs) {
-		dev_err(dev, "could not map mdio registers\n");
-		ret = -ENOMEM;
+	data->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(data->regs)) {
+		ret = PTR_ERR(data->regs);
 		goto bail_out;
 	}
 
@@ -406,16 +387,9 @@ static int davinci_mdio_probe(struct platform_device *pdev)
 	return 0;
 
 bail_out:
-	if (data->bus)
-		mdiobus_free(data->bus);
-
-	if (data->clk)
-		clk_put(data->clk);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
-	kfree(data);
-
 	return ret;
 }
 
@@ -423,18 +397,12 @@ static int davinci_mdio_remove(struct platform_device *pdev)
 {
 	struct davinci_mdio_data *data = platform_get_drvdata(pdev);
 
-	if (data->bus) {
+	if (data->bus)
 		mdiobus_unregister(data->bus);
-		mdiobus_free(data->bus);
-	}
 
-	if (data->clk)
-		clk_put(data->clk);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
-	kfree(data);
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 449011b0e00..4c70360967c 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -2191,8 +2191,6 @@ static void tile_net_setup(struct net_device *dev)
 static void tile_net_dev_init(const char *name, const uint8_t *mac)
 {
 	int ret;
-	int i;
-	int nz_addr = 0;
 	struct net_device *dev;
 	struct tile_net_priv *priv;
 
@@ -2212,7 +2210,6 @@ static void tile_net_dev_init(const char *name, const uint8_t *mac)
 
 	/* Initialize "priv". */
 	priv = netdev_priv(dev);
-	memset(priv, 0, sizeof(*priv));
 	priv->dev = dev;
 	priv->channel = -1;
 	priv->loopify_channel = -1;
@@ -2223,15 +2220,10 @@ static void tile_net_dev_init(const char *name, const uint8_t *mac)
 	 * be done before the device is opened.  If the MAC is all zeroes,
 	 * we use a random address, since we're probably on the simulator.
 	 */
-	for (i = 0; i < 6; i++)
-		nz_addr |= mac[i];
-
-	if (nz_addr) {
-		memcpy(dev->dev_addr, mac, ETH_ALEN);
-		dev->addr_len = 6;
-	} else {
+	if (!is_zero_ether_addr(mac))
+		ether_addr_copy(dev->dev_addr, mac);
+	else
 		eth_hw_addr_random(dev);
-	}
 
 	/* Register the network device. */
 	ret = register_netdev(dev);
diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
index d899d0072ae..bb799280466 100644
--- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c
+++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c
@@ -1561,7 +1561,7 @@ static struct gelic_card *gelic_alloc_card_net(struct net_device **netdev)
 	 * alloc netdev
 	 */
 	*netdev = alloc_etherdev(sizeof(struct gelic_port));
-	if (!netdev) {
+	if (!*netdev) {
 		kfree(card->unalign);
 		return NULL;
 	}
diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig
index 8a049a2b447..f66ddaee0c8 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -19,7 +19,7 @@ if NET_VENDOR_VIA
 
 config VIA_RHINE
 	tristate "VIA Rhine support"
-	depends on PCI
+	depends on (PCI || USE_OF)
 	select CRC32
 	select MII
 	---help---
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index f61dc2b72bb..2d72f96a9e2 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -94,6 +94,10 @@ static const int multicast_filter_limit = 32;
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/pci.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
@@ -116,13 +120,6 @@ static const int multicast_filter_limit = 32;
 static const char version[] =
 	"v1.10-LK" DRV_VERSION " " DRV_RELDATE " Written by Donald Becker";
 
-/* This driver was written to use PCI memory space. Some early versions
-   of the Rhine may only work correctly with I/O space accesses. */
-#ifdef CONFIG_VIA_RHINE_MMIO
-#define USE_MMIO
-#else
-#endif
-
 MODULE_AUTHOR("Donald Becker <becker@scyld.com>");
 MODULE_DESCRIPTION("VIA Rhine PCI Fast Ethernet driver");
 MODULE_LICENSE("GPL");
@@ -260,6 +257,12 @@ enum rhine_quirks {
 	rq6patterns	= 0x0040,	/* 6 instead of 4 patterns for WOL */
 	rqStatusWBRace	= 0x0080,	/* Tx Status Writeback Error possible */
 	rqRhineI	= 0x0100,	/* See comment below */
+	rqIntPHY	= 0x0200,	/* Integrated PHY */
+	rqMgmt		= 0x0400,	/* Management adapter */
+	rqNeedEnMMIO	= 0x0800,	/* Whether the core needs to be
+					 * switched from PIO mode to MMIO
+					 * (only applies to PCI)
+					 */
 };
 /*
  * rqRhineI: VT86C100A (aka Rhine-I) uses different bits to enable
@@ -279,6 +282,15 @@ static DEFINE_PCI_DEVICE_TABLE(rhine_pci_tbl) = {
 };
 MODULE_DEVICE_TABLE(pci, rhine_pci_tbl);
 
+/* OpenFirmware identifiers for platform-bus devices
+ * The .data field is currently only used to store quirks
+ */
+static u32 vt8500_quirks = rqWOL | rqForceReset | rq6patterns;
+static struct of_device_id rhine_of_tbl[] = {
+	{ .compatible = "via,vt8500-rhine", .data = &vt8500_quirks },
+	{ }	/* terminate list */
+};
+MODULE_DEVICE_TABLE(of, rhine_of_tbl);
 
 /* Offsets to the device registers. */
 enum register_offsets {
@@ -338,13 +350,11 @@ enum bcr1_bits {
 	BCR1_MED1=0x80,		/* for VT6102 */
 };
 
-#ifdef USE_MMIO
 /* Registers we check that mmio and reg are the same. */
 static const int mmio_verify_registers[] = {
 	RxConfig, TxConfig, IntrEnable, ConfigA, ConfigB, ConfigC, ConfigD,
 	0
 };
-#endif
 
 /* Bits in the interrupt status/mask registers. */
 enum intr_status_bits {
@@ -446,7 +456,7 @@ struct rhine_private {
 	unsigned char *tx_bufs;
 	dma_addr_t tx_bufs_dma;
 
-	struct pci_dev *pdev;
+	int irq;
 	long pioaddr;
 	struct net_device *dev;
 	struct napi_struct napi;
@@ -649,20 +659,46 @@ static void rhine_chip_reset(struct net_device *dev)
 		   "failed" : "succeeded");
 }
 
-#ifdef USE_MMIO
 static void enable_mmio(long pioaddr, u32 quirks)
 {
 	int n;
-	if (quirks & rqRhineI) {
-		/* More recent docs say that this bit is reserved ... */
-		n = inb(pioaddr + ConfigA) | 0x20;
-		outb(n, pioaddr + ConfigA);
-	} else {
-		n = inb(pioaddr + ConfigD) | 0x80;
-		outb(n, pioaddr + ConfigD);
+
+	if (quirks & rqNeedEnMMIO) {
+		if (quirks & rqRhineI) {
+			/* More recent docs say that this bit is reserved */
+			n = inb(pioaddr + ConfigA) | 0x20;
+			outb(n, pioaddr + ConfigA);
+		} else {
+			n = inb(pioaddr + ConfigD) | 0x80;
+			outb(n, pioaddr + ConfigD);
+		}
 	}
 }
-#endif
+
+static inline int verify_mmio(struct device *hwdev,
+			      long pioaddr,
+			      void __iomem *ioaddr,
+			      u32 quirks)
+{
+	if (quirks & rqNeedEnMMIO) {
+		int i = 0;
+
+		/* Check that selected MMIO registers match the PIO ones */
+		while (mmio_verify_registers[i]) {
+			int reg = mmio_verify_registers[i++];
+			unsigned char a = inb(pioaddr+reg);
+			unsigned char b = readb(ioaddr+reg);
+
+			if (a != b) {
+				dev_err(hwdev,
+					"MMIO do not match PIO [%02x] (%02x != %02x)\n",
+					reg, a, b);
+				return -EIO;
+			}
+		}
+	}
+	return 0;
+}
 
 /*
  * Loads bytes 0x00-0x05, 0x6E-0x6F, 0x78-0x7B from EEPROM
@@ -682,14 +718,12 @@ static void rhine_reload_eeprom(long pioaddr, struct net_device *dev)
 	if (i > 512)
 		pr_info("%4d cycles used @ %s:%d\n", i, __func__, __LINE__);
 
-#ifdef USE_MMIO
 	/*
 	 * Reloading from EEPROM overwrites ConfigA-D, so we must re-enable
 	 * MMIO. If reloading EEPROM was done first this could be avoided, but
 	 * it is not known if that still works with the "win98-reboot" problem.
 	 */
 	enable_mmio(pioaddr, rp->quirks);
-#endif
 
 	/* Turn off EEPROM-controlled wake-up (magic packet) */
 	if (rp->quirks & rqWOL)
@@ -701,7 +735,7 @@ static void rhine_reload_eeprom(long pioaddr, struct net_device *dev)
 static void rhine_poll(struct net_device *dev)
 {
 	struct rhine_private *rp = netdev_priv(dev);
-	const int irq = rp->pdev->irq;
+	const int irq = rp->irq;
 
 	disable_irq(irq);
 	rhine_interrupt(irq, dev);
@@ -846,7 +880,8 @@ static void rhine_hw_init(struct net_device *dev, long pioaddr)
 		msleep(5);
 
 	/* Reload EEPROM controlled bytes cleared by soft reset */
-	rhine_reload_eeprom(pioaddr, dev);
+	if (dev_is_pci(dev->dev.parent))
+		rhine_reload_eeprom(pioaddr, dev);
 }
 
 static const struct net_device_ops rhine_netdev_ops = {
@@ -867,125 +902,37 @@ static const struct net_device_ops rhine_netdev_ops = {
 #endif
 };
 
-static int rhine_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
+static int rhine_init_one_common(struct device *hwdev, u32 quirks,
+				 long pioaddr, void __iomem *ioaddr, int irq)
 {
 	struct net_device *dev;
 	struct rhine_private *rp;
-	int i, rc;
-	u32 quirks;
-	long pioaddr;
-	long memaddr;
-	void __iomem *ioaddr;
-	int io_size, phy_id;
+	int i, rc, phy_id;
 	const char *name;
-#ifdef USE_MMIO
-	int bar = 1;
-#else
-	int bar = 0;
-#endif
-
-/* when built into the kernel, we only print version if device is found */
-#ifndef MODULE
-	pr_info_once("%s\n", version);
-#endif
-
-	io_size = 256;
-	phy_id = 0;
-	quirks = 0;
-	name = "Rhine";
-	if (pdev->revision < VTunknown0) {
-		quirks = rqRhineI;
-		io_size = 128;
-	}
-	else if (pdev->revision >= VT6102) {
-		quirks = rqWOL | rqForceReset;
-		if (pdev->revision < VT6105) {
-			name = "Rhine II";
-			quirks |= rqStatusWBRace;	/* Rhine-II exclusive */
-		}
-		else {
-			phy_id = 1;	/* Integrated PHY, phy_id fixed to 1 */
-			if (pdev->revision >= VT6105_B0)
-				quirks |= rq6patterns;
-			if (pdev->revision < VT6105M)
-				name = "Rhine III";
-			else
-				name = "Rhine III (Management Adapter)";
-		}
-	}
-
-	rc = pci_enable_device(pdev);
-	if (rc)
-		goto err_out;
 
 	/* this should always be supported */
-	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+	rc = dma_set_mask(hwdev, DMA_BIT_MASK(32));
 	if (rc) {
-		dev_err(&pdev->dev,
-			"32-bit PCI DMA addresses not supported by the card!?\n");
-		goto err_out_pci_disable;
-	}
-
-	/* sanity check */
-	if ((pci_resource_len(pdev, 0) < io_size) ||
-	    (pci_resource_len(pdev, 1) < io_size)) {
-		rc = -EIO;
-		dev_err(&pdev->dev, "Insufficient PCI resources, aborting\n");
-		goto err_out_pci_disable;
+		dev_err(hwdev, "32-bit DMA addresses not supported by the card!?\n");
+		goto err_out;
 	}
 
-	pioaddr = pci_resource_start(pdev, 0);
-	memaddr = pci_resource_start(pdev, 1);
-
-	pci_set_master(pdev);
-
 	dev = alloc_etherdev(sizeof(struct rhine_private));
 	if (!dev) {
 		rc = -ENOMEM;
-		goto err_out_pci_disable;
+		goto err_out;
 	}
-	SET_NETDEV_DEV(dev, &pdev->dev);
+	SET_NETDEV_DEV(dev, hwdev);
 
 	rp = netdev_priv(dev);
 	rp->dev = dev;
 	rp->quirks = quirks;
 	rp->pioaddr = pioaddr;
-	rp->pdev = pdev;
+	rp->base = ioaddr;
+	rp->irq = irq;
 	rp->msg_enable = netif_msg_init(debug, RHINE_MSG_DEFAULT);
 
-	rc = pci_request_regions(pdev, DRV_NAME);
-	if (rc)
-		goto err_out_free_netdev;
-
-	ioaddr = pci_iomap(pdev, bar, io_size);
-	if (!ioaddr) {
-		rc = -EIO;
-		dev_err(&pdev->dev,
-			"ioremap failed for device %s, region 0x%X @ 0x%lX\n",
-			pci_name(pdev), io_size, memaddr);
-		goto err_out_free_res;
-	}
-
-#ifdef USE_MMIO
-	enable_mmio(pioaddr, quirks);
-
-	/* Check that selected MMIO registers match the PIO ones */
-	i = 0;
-	while (mmio_verify_registers[i]) {
-		int reg = mmio_verify_registers[i++];
-		unsigned char a = inb(pioaddr+reg);
-		unsigned char b = readb(ioaddr+reg);
-		if (a != b) {
-			rc = -EIO;
-			dev_err(&pdev->dev,
-				"MMIO do not match PIO [%02x] (%02x != %02x)\n",
-				reg, a, b);
-			goto err_out_unmap;
-		}
-	}
-#endif /* USE_MMIO */
-
-	rp->base = ioaddr;
+	phy_id = rp->quirks & rqIntPHY ? 1 : 0;
 
 	u64_stats_init(&rp->tx_stats.syncp);
 	u64_stats_init(&rp->rx_stats.syncp);
@@ -1030,7 +977,7 @@ static int rhine_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rp->quirks & rqRhineI)
 		dev->features |= NETIF_F_SG|NETIF_F_HW_CSUM;
 
-	if (pdev->revision >= VT6105M)
+	if (rp->quirks & rqMgmt)
 		dev->features |= NETIF_F_HW_VLAN_CTAG_TX |
 				 NETIF_F_HW_VLAN_CTAG_RX |
 				 NETIF_F_HW_VLAN_CTAG_FILTER;
@@ -1038,18 +985,21 @@ static int rhine_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* dev->name not defined before register_netdev()! */
 	rc = register_netdev(dev);
 	if (rc)
-		goto err_out_unmap;
+		goto err_out_free_netdev;
+
+	if (rp->quirks & rqRhineI)
+		name = "Rhine";
+	else if (rp->quirks & rqStatusWBRace)
+		name = "Rhine II";
+	else if (rp->quirks & rqMgmt)
+		name = "Rhine III (Management Adapter)";
+	else
+		name = "Rhine III";
 
 	netdev_info(dev, "VIA %s at 0x%lx, %pM, IRQ %d\n",
-		    name,
-#ifdef USE_MMIO
-		    memaddr,
-#else
-		    (long)ioaddr,
-#endif
-		    dev->dev_addr, pdev->irq);
+		    name, (long)ioaddr, dev->dev_addr, rp->irq);
 
-	pci_set_drvdata(pdev, dev);
+	dev_set_drvdata(hwdev, dev);
 
 	{
 		u16 mii_cmd;
@@ -1078,41 +1028,158 @@ static int rhine_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	return 0;
 
+err_out_free_netdev:
+	free_netdev(dev);
+err_out:
+	return rc;
+}
+
+static int rhine_init_one_pci(struct pci_dev *pdev,
+			      const struct pci_device_id *ent)
+{
+	struct device *hwdev = &pdev->dev;
+	int rc;
+	long pioaddr, memaddr;
+	void __iomem *ioaddr;
+	int io_size = pdev->revision < VTunknown0 ? 128 : 256;
+
+/* This driver was written to use PCI memory space. Some early versions
+ * of the Rhine may only work correctly with I/O space accesses.
+ * TODO: determine for which revisions this is true and assign the flag
+ *	 in code as opposed to this Kconfig option (???)
+ */
+#ifdef CONFIG_VIA_RHINE_MMIO
+	u32 quirks = rqNeedEnMMIO;
+#else
+	u32 quirks = 0;
+#endif
+
+/* when built into the kernel, we only print version if device is found */
+#ifndef MODULE
+	pr_info_once("%s\n", version);
+#endif
+
+	rc = pci_enable_device(pdev);
+	if (rc)
+		goto err_out;
+
+	if (pdev->revision < VTunknown0) {
+		quirks |= rqRhineI;
+	} else if (pdev->revision >= VT6102) {
+		quirks |= rqWOL | rqForceReset;
+		if (pdev->revision < VT6105) {
+			quirks |= rqStatusWBRace;
+		} else {
+			quirks |= rqIntPHY;
+			if (pdev->revision >= VT6105_B0)
+				quirks |= rq6patterns;
+			if (pdev->revision >= VT6105M)
+				quirks |= rqMgmt;
+		}
+	}
+
+	/* sanity check */
+	if ((pci_resource_len(pdev, 0) < io_size) ||
+	    (pci_resource_len(pdev, 1) < io_size)) {
+		rc = -EIO;
+		dev_err(hwdev, "Insufficient PCI resources, aborting\n");
+		goto err_out_pci_disable;
+	}
+
+	pioaddr = pci_resource_start(pdev, 0);
+	memaddr = pci_resource_start(pdev, 1);
+
+	pci_set_master(pdev);
+
+	rc = pci_request_regions(pdev, DRV_NAME);
+	if (rc)
+		goto err_out_pci_disable;
+
+	ioaddr = pci_iomap(pdev, (quirks & rqNeedEnMMIO ? 1 : 0), io_size);
+	if (!ioaddr) {
+		rc = -EIO;
+		dev_err(hwdev,
+			"ioremap failed for device %s, region 0x%X @ 0x%lX\n",
+			dev_name(hwdev), io_size, memaddr);
+		goto err_out_free_res;
+	}
+
+	enable_mmio(pioaddr, quirks);
+
+	rc = verify_mmio(hwdev, pioaddr, ioaddr, quirks);
+	if (rc)
+		goto err_out_unmap;
+
+	rc = rhine_init_one_common(&pdev->dev, quirks,
+				   pioaddr, ioaddr, pdev->irq);
+	if (!rc)
+		return 0;
+
 err_out_unmap:
 	pci_iounmap(pdev, ioaddr);
 err_out_free_res:
 	pci_release_regions(pdev);
-err_out_free_netdev:
-	free_netdev(dev);
 err_out_pci_disable:
 	pci_disable_device(pdev);
 err_out:
 	return rc;
 }
 
+static int rhine_init_one_platform(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+	const u32 *quirks;
+	int irq;
+	struct resource *res;
+	void __iomem *ioaddr;
+
+	match = of_match_device(rhine_of_tbl, &pdev->dev);
+	if (!match)
+		return -EINVAL;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ioaddr = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ioaddr))
+		return PTR_ERR(ioaddr);
+
+	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+	if (!irq)
+		return -EINVAL;
+
+	quirks = match->data;
+	if (!quirks)
+		return -EINVAL;
+
+	return rhine_init_one_common(&pdev->dev, *quirks,
+				     (long)ioaddr, ioaddr, irq);
+}
+
 static int alloc_ring(struct net_device* dev)
 {
 	struct rhine_private *rp = netdev_priv(dev);
+	struct device *hwdev = dev->dev.parent;
 	void *ring;
 	dma_addr_t ring_dma;
 
-	ring = pci_alloc_consistent(rp->pdev,
-				    RX_RING_SIZE * sizeof(struct rx_desc) +
-				    TX_RING_SIZE * sizeof(struct tx_desc),
-				    &ring_dma);
+	ring = dma_alloc_coherent(hwdev,
+				  RX_RING_SIZE * sizeof(struct rx_desc) +
+				  TX_RING_SIZE * sizeof(struct tx_desc),
+				  &ring_dma,
+				  GFP_ATOMIC);
 	if (!ring) {
 		netdev_err(dev, "Could not allocate DMA memory\n");
 		return -ENOMEM;
 	}
 	if (rp->quirks & rqRhineI) {
-		rp->tx_bufs = pci_alloc_consistent(rp->pdev,
-						   PKT_BUF_SZ * TX_RING_SIZE,
-						   &rp->tx_bufs_dma);
+		rp->tx_bufs = dma_alloc_coherent(hwdev,
+						 PKT_BUF_SZ * TX_RING_SIZE,
+						 &rp->tx_bufs_dma,
+						 GFP_ATOMIC);
 		if (rp->tx_bufs == NULL) {
-			pci_free_consistent(rp->pdev,
-				    RX_RING_SIZE * sizeof(struct rx_desc) +
-				    TX_RING_SIZE * sizeof(struct tx_desc),
-				    ring, ring_dma);
+			dma_free_coherent(hwdev,
+					  RX_RING_SIZE * sizeof(struct rx_desc) +
+					  TX_RING_SIZE * sizeof(struct tx_desc),
+					  ring, ring_dma);
 			return -ENOMEM;
 		}
 	}
@@ -1128,16 +1195,17 @@ static int alloc_ring(struct net_device* dev)
 static void free_ring(struct net_device* dev)
 {
 	struct rhine_private *rp = netdev_priv(dev);
+	struct device *hwdev = dev->dev.parent;
 
-	pci_free_consistent(rp->pdev,
-			    RX_RING_SIZE * sizeof(struct rx_desc) +
-			    TX_RING_SIZE * sizeof(struct tx_desc),
-			    rp->rx_ring, rp->rx_ring_dma);
+	dma_free_coherent(hwdev,
+			  RX_RING_SIZE * sizeof(struct rx_desc) +
+			  TX_RING_SIZE * sizeof(struct tx_desc),
+			  rp->rx_ring, rp->rx_ring_dma);
 	rp->tx_ring = NULL;
 
 	if (rp->tx_bufs)
-		pci_free_consistent(rp->pdev, PKT_BUF_SZ * TX_RING_SIZE,
-				    rp->tx_bufs, rp->tx_bufs_dma);
+		dma_free_coherent(hwdev, PKT_BUF_SZ * TX_RING_SIZE,
+				  rp->tx_bufs, rp->tx_bufs_dma);
 
 	rp->tx_bufs = NULL;
 
@@ -1146,6 +1214,7 @@ static void free_ring(struct net_device* dev)
 static void alloc_rbufs(struct net_device *dev)
 {
 	struct rhine_private *rp = netdev_priv(dev);
+	struct device *hwdev = dev->dev.parent;
 	dma_addr_t next;
 	int i;
 
@@ -1174,9 +1243,9 @@ static void alloc_rbufs(struct net_device *dev)
 			break;
 
 		rp->rx_skbuff_dma[i] =
-			pci_map_single(rp->pdev, skb->data, rp->rx_buf_sz,
-				       PCI_DMA_FROMDEVICE);
-		if (dma_mapping_error(&rp->pdev->dev, rp->rx_skbuff_dma[i])) {
+			dma_map_single(hwdev, skb->data, rp->rx_buf_sz,
+				       DMA_FROM_DEVICE);
+		if (dma_mapping_error(hwdev, rp->rx_skbuff_dma[i])) {
 			rp->rx_skbuff_dma[i] = 0;
 			dev_kfree_skb(skb);
 			break;
@@ -1190,6 +1259,7 @@ static void alloc_rbufs(struct net_device *dev)
 static void free_rbufs(struct net_device* dev)
 {
 	struct rhine_private *rp = netdev_priv(dev);
+	struct device *hwdev = dev->dev.parent;
 	int i;
 
 	/* Free all the skbuffs in the Rx queue. */
@@ -1197,9 +1267,9 @@ static void free_rbufs(struct net_device* dev)
 		rp->rx_ring[i].rx_status = 0;
 		rp->rx_ring[i].addr = cpu_to_le32(0xBADF00D0); /* An invalid address. */
 		if (rp->rx_skbuff[i]) {
-			pci_unmap_single(rp->pdev,
+			dma_unmap_single(hwdev,
 					 rp->rx_skbuff_dma[i],
-					 rp->rx_buf_sz, PCI_DMA_FROMDEVICE);
+					 rp->rx_buf_sz, DMA_FROM_DEVICE);
 			dev_kfree_skb(rp->rx_skbuff[i]);
 		}
 		rp->rx_skbuff[i] = NULL;
@@ -1230,6 +1300,7 @@ static void alloc_tbufs(struct net_device* dev)
 static void free_tbufs(struct net_device* dev)
 {
 	struct rhine_private *rp = netdev_priv(dev);
+	struct device *hwdev = dev->dev.parent;
 	int i;
 
 	for (i = 0; i < TX_RING_SIZE; i++) {
@@ -1238,10 +1309,10 @@ static void free_tbufs(struct net_device* dev)
 		rp->tx_ring[i].addr = cpu_to_le32(0xBADF00D0); /* An invalid address. */
 		if (rp->tx_skbuff[i]) {
 			if (rp->tx_skbuff_dma[i]) {
-				pci_unmap_single(rp->pdev,
+				dma_unmap_single(hwdev,
 						 rp->tx_skbuff_dma[i],
 						 rp->tx_skbuff[i]->len,
-						 PCI_DMA_TODEVICE);
+						 DMA_TO_DEVICE);
 			}
 			dev_kfree_skb(rp->tx_skbuff[i]);
 		}
@@ -1278,8 +1349,9 @@ static void rhine_set_carrier(struct mii_if_info *mii)
 		/* autoneg is off: Link is always assumed to be up */
 		if (!netif_carrier_ok(dev))
 			netif_carrier_on(dev);
-	} else	/* Let MMI library update carrier status */
-		rhine_check_media(dev, 0);
+	}
+
+	rhine_check_media(dev, 0);
 
 	netif_info(rp, link, dev, "force_media %d, carrier %d\n",
 		   mii->force_media, netif_carrier_ok(dev));
@@ -1469,7 +1541,7 @@ static void init_registers(struct net_device *dev)
 
 	rhine_set_rx_mode(dev);
 
-	if (rp->pdev->revision >= VT6105M)
+	if (rp->quirks & rqMgmt)
 		rhine_init_cam_filter(dev);
 
 	napi_enable(&rp->napi);
@@ -1581,16 +1653,15 @@ static int rhine_open(struct net_device *dev)
 	void __iomem *ioaddr = rp->base;
 	int rc;
 
-	rc = request_irq(rp->pdev->irq, rhine_interrupt, IRQF_SHARED, dev->name,
-			dev);
+	rc = request_irq(rp->irq, rhine_interrupt, IRQF_SHARED, dev->name, dev);
 	if (rc)
 		return rc;
 
-	netif_dbg(rp, ifup, dev, "%s() irq %d\n", __func__, rp->pdev->irq);
+	netif_dbg(rp, ifup, dev, "%s() irq %d\n", __func__, rp->irq);
 
 	rc = alloc_ring(dev);
 	if (rc) {
-		free_irq(rp->pdev->irq, dev);
+		free_irq(rp->irq, dev);
 		return rc;
 	}
 	alloc_rbufs(dev);
@@ -1659,6 +1730,7 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 				  struct net_device *dev)
 {
 	struct rhine_private *rp = netdev_priv(dev);
+	struct device *hwdev = dev->dev.parent;
 	void __iomem *ioaddr = rp->base;
 	unsigned entry;
 
@@ -1695,9 +1767,9 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 						       rp->tx_bufs));
 	} else {
 		rp->tx_skbuff_dma[entry] =
-			pci_map_single(rp->pdev, skb->data, skb->len,
-				       PCI_DMA_TODEVICE);
-		if (dma_mapping_error(&rp->pdev->dev, rp->tx_skbuff_dma[entry])) {
+			dma_map_single(hwdev, skb->data, skb->len,
+				       DMA_TO_DEVICE);
+		if (dma_mapping_error(hwdev, rp->tx_skbuff_dma[entry])) {
 			dev_kfree_skb_any(skb);
 			rp->tx_skbuff_dma[entry] = 0;
 			dev->stats.tx_dropped++;
@@ -1788,6 +1860,7 @@ static irqreturn_t rhine_interrupt(int irq, void *dev_instance)
 static void rhine_tx(struct net_device *dev)
 {
 	struct rhine_private *rp = netdev_priv(dev);
+	struct device *hwdev = dev->dev.parent;
 	int txstatus = 0, entry = rp->dirty_tx % TX_RING_SIZE;
 
 	/* find and cleanup dirty tx descriptors */
@@ -1831,10 +1904,10 @@ static void rhine_tx(struct net_device *dev)
 		}
 		/* Free the original skb. */
 		if (rp->tx_skbuff_dma[entry]) {
-			pci_unmap_single(rp->pdev,
+			dma_unmap_single(hwdev,
 					 rp->tx_skbuff_dma[entry],
 					 rp->tx_skbuff[entry]->len,
-					 PCI_DMA_TODEVICE);
+					 DMA_TO_DEVICE);
 		}
 		dev_consume_skb_any(rp->tx_skbuff[entry]);
 		rp->tx_skbuff[entry] = NULL;
@@ -1863,6 +1936,7 @@ static inline u16 rhine_get_vlan_tci(struct sk_buff *skb, int data_size)
 static int rhine_rx(struct net_device *dev, int limit)
 {
 	struct rhine_private *rp = netdev_priv(dev);
+	struct device *hwdev = dev->dev.parent;
 	int count;
 	int entry = rp->cur_rx % RX_RING_SIZE;
 
@@ -1924,19 +1998,19 @@ static int rhine_rx(struct net_device *dev, int limit)
 			if (pkt_len < rx_copybreak)
 				skb = netdev_alloc_skb_ip_align(dev, pkt_len);
 			if (skb) {
-				pci_dma_sync_single_for_cpu(rp->pdev,
-							    rp->rx_skbuff_dma[entry],
-							    rp->rx_buf_sz,
-							    PCI_DMA_FROMDEVICE);
+				dma_sync_single_for_cpu(hwdev,
+							rp->rx_skbuff_dma[entry],
+							rp->rx_buf_sz,
+							DMA_FROM_DEVICE);
 
 				skb_copy_to_linear_data(skb,
 						 rp->rx_skbuff[entry]->data,
 						 pkt_len);
 				skb_put(skb, pkt_len);
-				pci_dma_sync_single_for_device(rp->pdev,
-							       rp->rx_skbuff_dma[entry],
-							       rp->rx_buf_sz,
-							       PCI_DMA_FROMDEVICE);
+				dma_sync_single_for_device(hwdev,
+							   rp->rx_skbuff_dma[entry],
+							   rp->rx_buf_sz,
+							   DMA_FROM_DEVICE);
 			} else {
 				skb = rp->rx_skbuff[entry];
 				if (skb == NULL) {
@@ -1945,10 +2019,10 @@ static int rhine_rx(struct net_device *dev, int limit)
 				}
 				rp->rx_skbuff[entry] = NULL;
 				skb_put(skb, pkt_len);
-				pci_unmap_single(rp->pdev,
+				dma_unmap_single(hwdev,
 						 rp->rx_skbuff_dma[entry],
 						 rp->rx_buf_sz,
-						 PCI_DMA_FROMDEVICE);
+						 DMA_FROM_DEVICE);
 			}
 
 			if (unlikely(desc_length & DescTag))
@@ -1979,10 +2053,11 @@ static int rhine_rx(struct net_device *dev, int limit)
 			if (skb == NULL)
 				break;	/* Better luck next round. */
 			rp->rx_skbuff_dma[entry] =
-				pci_map_single(rp->pdev, skb->data,
+				dma_map_single(hwdev, skb->data,
 					       rp->rx_buf_sz,
-					       PCI_DMA_FROMDEVICE);
-			if (dma_mapping_error(&rp->pdev->dev, rp->rx_skbuff_dma[entry])) {
+					       DMA_FROM_DEVICE);
+			if (dma_mapping_error(hwdev,
+					      rp->rx_skbuff_dma[entry])) {
 				dev_kfree_skb(skb);
 				rp->rx_skbuff_dma[entry] = 0;
 				break;
@@ -2103,7 +2178,7 @@ static void rhine_set_rx_mode(struct net_device *dev)
 		/* Too many to match, or accept all multicasts. */
 		iowrite32(0xffffffff, ioaddr + MulticastFilter0);
 		iowrite32(0xffffffff, ioaddr + MulticastFilter1);
-	} else if (rp->pdev->revision >= VT6105M) {
+	} else if (rp->quirks & rqMgmt) {
 		int i = 0;
 		u32 mCAMmask = 0;	/* 32 mCAMs (6105M and better) */
 		netdev_for_each_mc_addr(ha, dev) {
@@ -2125,7 +2200,7 @@ static void rhine_set_rx_mode(struct net_device *dev)
 		iowrite32(mc_filter[1], ioaddr + MulticastFilter1);
 	}
 	/* enable/disable VLAN receive filtering */
-	if (rp->pdev->revision >= VT6105M) {
+	if (rp->quirks & rqMgmt) {
 		if (dev->flags & IFF_PROMISC)
 			BYTE_REG_BITS_OFF(BCR1_VIDFR, ioaddr + PCIBusConfig1);
 		else
@@ -2136,11 +2211,11 @@ static void rhine_set_rx_mode(struct net_device *dev)
 
 static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
-	struct rhine_private *rp = netdev_priv(dev);
+	struct device *hwdev = dev->dev.parent;
 
 	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
 	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
-	strlcpy(info->bus_info, pci_name(rp->pdev), sizeof(info->bus_info));
+	strlcpy(info->bus_info, dev_name(hwdev), sizeof(info->bus_info));
 }
 
 static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
@@ -2277,7 +2352,7 @@ static int rhine_close(struct net_device *dev)
 	/* Stop the chip's Tx and Rx processes. */
 	iowrite16(CmdStop, ioaddr + ChipCmd);
 
-	free_irq(rp->pdev->irq, dev);
+	free_irq(rp->irq, dev);
 	free_rbufs(dev);
 	free_tbufs(dev);
 	free_ring(dev);
@@ -2286,7 +2361,7 @@ static int rhine_close(struct net_device *dev)
 }
 
 
-static void rhine_remove_one(struct pci_dev *pdev)
+static void rhine_remove_one_pci(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct rhine_private *rp = netdev_priv(dev);
@@ -2300,7 +2375,21 @@ static void rhine_remove_one(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
-static void rhine_shutdown (struct pci_dev *pdev)
+static int rhine_remove_one_platform(struct platform_device *pdev)
+{
+	struct net_device *dev = platform_get_drvdata(pdev);
+	struct rhine_private *rp = netdev_priv(dev);
+
+	unregister_netdev(dev);
+
+	iounmap(rp->base);
+
+	free_netdev(dev);
+
+	return 0;
+}
+
+static void rhine_shutdown_pci(struct pci_dev *pdev)
 {
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct rhine_private *rp = netdev_priv(dev);
@@ -2354,8 +2443,7 @@ static void rhine_shutdown (struct pci_dev *pdev)
 #ifdef CONFIG_PM_SLEEP
 static int rhine_suspend(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rhine_private *rp = netdev_priv(dev);
 
 	if (!netif_running(dev))
@@ -2367,23 +2455,21 @@ static int rhine_suspend(struct device *device)
 
 	netif_device_detach(dev);
 
-	rhine_shutdown(pdev);
+	if (dev_is_pci(device))
+		rhine_shutdown_pci(to_pci_dev(device));
 
 	return 0;
 }
 
 static int rhine_resume(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rhine_private *rp = netdev_priv(dev);
 
 	if (!netif_running(dev))
 		return 0;
 
-#ifdef USE_MMIO
 	enable_mmio(rp->pioaddr, rp->quirks);
-#endif
 	rhine_power_init(dev);
 	free_tbufs(dev);
 	free_rbufs(dev);
@@ -2408,15 +2494,26 @@ static SIMPLE_DEV_PM_OPS(rhine_pm_ops, rhine_suspend, rhine_resume);
 
 #endif /* !CONFIG_PM_SLEEP */
 
-static struct pci_driver rhine_driver = {
+static struct pci_driver rhine_driver_pci = {
 	.name		= DRV_NAME,
 	.id_table	= rhine_pci_tbl,
-	.probe		= rhine_init_one,
-	.remove		= rhine_remove_one,
-	.shutdown	= rhine_shutdown,
+	.probe		= rhine_init_one_pci,
+	.remove		= rhine_remove_one_pci,
+	.shutdown	= rhine_shutdown_pci,
 	.driver.pm	= RHINE_PM_OPS,
 };
 
+static struct platform_driver rhine_driver_platform = {
+	.probe		= rhine_init_one_platform,
+	.remove		= rhine_remove_one_platform,
+	.driver = {
+		.name	= DRV_NAME,
+		.owner	= THIS_MODULE,
+		.of_match_table	= rhine_of_tbl,
+		.pm		= RHINE_PM_OPS,
+	}
+};
+
 static struct dmi_system_id rhine_dmi_table[] __initdata = {
 	{
 		.ident = "EPIA-M",
@@ -2437,6 +2534,8 @@ static struct dmi_system_id rhine_dmi_table[] __initdata = {
 
 static int __init rhine_init(void)
 {
+	int ret_pci, ret_platform;
+
 /* when a module, this is printed whether or not devices are found in probe */
 #ifdef MODULE
 	pr_info("%s\n", version);
@@ -2449,13 +2548,19 @@ static int __init rhine_init(void)
 	else if (avoid_D3)
 		pr_info("avoid_D3 set\n");
 
-	return pci_register_driver(&rhine_driver);
+	ret_pci = pci_register_driver(&rhine_driver_pci);
+	ret_platform = platform_driver_register(&rhine_driver_platform);
+	if ((ret_pci < 0) && (ret_platform < 0))
+		return ret_pci;
+
+	return 0;
 }
 
 
 static void __exit rhine_cleanup(void)
 {
-	pci_unregister_driver(&rhine_driver);
+	platform_driver_unregister(&rhine_driver_platform);
+	pci_unregister_driver(&rhine_driver_pci);
 }
 
 
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index fa193c4688d..4ef818a7a6c 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -75,7 +75,7 @@ int temac_indirect_busywait(struct temac_local *lp)
 	long end = jiffies + 2;
 
 	while (!(temac_ior(lp, XTE_RDY0_OFFSET) & XTE_RDY0_HARD_ACS_RDY_MASK)) {
-		if (end - jiffies <= 0) {
+		if (time_before_eq(end, jiffies)) {
 			WARN_ON(1);
 			return -ETIMEDOUT;
 		}
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
index 64b4639f43b..d4abf478e2b 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
@@ -22,7 +22,7 @@ int axienet_mdio_wait_until_ready(struct axienet_local *lp)
 	long end = jiffies + 2;
 	while (!(axienet_ior(lp, XAE_MDIO_MCR_OFFSET) &
 		 XAE_MDIO_MCR_READY_MASK)) {
-		if (end - jiffies <= 0) {
+		if (time_before_eq(end, jiffies)) {
 			WARN_ON(1);
 			return -ETIMEDOUT;
 		}
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 0d87c67a5ff..8c4aed3053e 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -702,7 +702,7 @@ static int xemaclite_mdio_wait(struct net_local *lp)
 	*/
 	while (__raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
 			XEL_MDIOCTRL_MDIOSTS_MASK) {
-		if (end - jiffies <= 0) {
+		if (time_before_eq(end, jiffies)) {
 			WARN_ON(1);
 			return -ETIMEDOUT;
 		}
diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c
index eb78203cd58..2aa57270838 100644
--- a/drivers/net/fddi/defxx.c
+++ b/drivers/net/fddi/defxx.c
@@ -291,7 +291,11 @@ static int		dfx_hw_dma_uninit(DFX_board_t *bp, PI_UINT32 type);
 
 static int		dfx_rcv_init(DFX_board_t *bp, int get_buffers);
 static void		dfx_rcv_queue_process(DFX_board_t *bp);
+#ifdef DYNAMIC_BUFFERS
 static void		dfx_rcv_flush(DFX_board_t *bp);
+#else
+static inline void	dfx_rcv_flush(DFX_board_t *bp) {}
+#endif
 
 static netdev_tx_t dfx_xmt_queue_pkt(struct sk_buff *skb,
 				     struct net_device *dev);
@@ -2849,7 +2853,7 @@ static int dfx_hw_dma_uninit(DFX_board_t *bp, PI_UINT32 type)
  *	Align an sk_buff to a boundary power of 2
  *
  */
-
+#ifdef DYNAMIC_BUFFERS
 static void my_skb_align(struct sk_buff *skb, int n)
 {
 	unsigned long x = (unsigned long)skb->data;
@@ -2859,7 +2863,7 @@ static void my_skb_align(struct sk_buff *skb, int n)
 
 	skb_reserve(skb, v - x);
 }
-
+#endif
 
 /*
  * ================
@@ -3074,10 +3078,7 @@ static void dfx_rcv_queue_process(
 					break;
 					}
 				else {
-#ifndef DYNAMIC_BUFFERS
-					if (! rx_in_place)
-#endif
-					{
+					if (!rx_in_place) {
 						/* Receive buffer allocated, pass receive packet up */
 
 						skb_copy_to_linear_data(skb,
@@ -3453,10 +3454,6 @@ static void dfx_rcv_flush( DFX_board_t *bp )
 		}
 
 	}
-#else
-static inline void dfx_rcv_flush( DFX_board_t *bp )
-{
-}
 #endif /* DYNAMIC_BUFFERS */
 
 /*
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index d18f711d0b0..6cc37c15e0b 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -28,50 +28,119 @@
 #include <linux/hyperv.h>
 #include <linux/rndis.h>
 
-/* Fwd declaration */
-struct hv_netvsc_packet;
-struct ndis_tcp_ip_checksum_info;
+/* RSS related */
+#define OID_GEN_RECEIVE_SCALE_CAPABILITIES 0x00010203  /* query only */
+#define OID_GEN_RECEIVE_SCALE_PARAMETERS 0x00010204  /* query and set */
 
-/* Represent the xfer page packet which contains 1 or more netvsc packet */
-struct xferpage_packet {
-	struct list_head list_ent;
-	u32 status;
+#define NDIS_OBJECT_TYPE_RSS_CAPABILITIES 0x88
+#define NDIS_OBJECT_TYPE_RSS_PARAMETERS 0x89
 
-	/* # of netvsc packets this xfer packet contains */
-	u32 count;
+#define NDIS_RECEIVE_SCALE_CAPABILITIES_REVISION_2 2
+#define NDIS_RECEIVE_SCALE_PARAMETERS_REVISION_2 2
+
+struct ndis_obj_header {
+	u8 type;
+	u8 rev;
+	u16 size;
+} __packed;
+
+/* ndis_recv_scale_cap/cap_flag */
+#define NDIS_RSS_CAPS_MESSAGE_SIGNALED_INTERRUPTS 0x01000000
+#define NDIS_RSS_CAPS_CLASSIFICATION_AT_ISR       0x02000000
+#define NDIS_RSS_CAPS_CLASSIFICATION_AT_DPC       0x04000000
+#define NDIS_RSS_CAPS_USING_MSI_X                 0x08000000
+#define NDIS_RSS_CAPS_RSS_AVAILABLE_ON_PORTS      0x10000000
+#define NDIS_RSS_CAPS_SUPPORTS_MSI_X              0x20000000
+#define NDIS_RSS_CAPS_HASH_TYPE_TCP_IPV4          0x00000100
+#define NDIS_RSS_CAPS_HASH_TYPE_TCP_IPV6          0x00000200
+#define NDIS_RSS_CAPS_HASH_TYPE_TCP_IPV6_EX       0x00000400
+
+struct ndis_recv_scale_cap { /* NDIS_RECEIVE_SCALE_CAPABILITIES */
+	struct ndis_obj_header hdr;
+	u32 cap_flag;
+	u32 num_int_msg;
+	u32 num_recv_que;
+	u16 num_indirect_tabent;
+} __packed;
+
+
+/* ndis_recv_scale_param flags */
+#define NDIS_RSS_PARAM_FLAG_BASE_CPU_UNCHANGED     0x0001
+#define NDIS_RSS_PARAM_FLAG_HASH_INFO_UNCHANGED    0x0002
+#define NDIS_RSS_PARAM_FLAG_ITABLE_UNCHANGED       0x0004
+#define NDIS_RSS_PARAM_FLAG_HASH_KEY_UNCHANGED     0x0008
+#define NDIS_RSS_PARAM_FLAG_DISABLE_RSS            0x0010
+
+/* Hash info bits */
+#define NDIS_HASH_FUNC_TOEPLITZ 0x00000001
+#define NDIS_HASH_IPV4          0x00000100
+#define NDIS_HASH_TCP_IPV4      0x00000200
+#define NDIS_HASH_IPV6          0x00000400
+#define NDIS_HASH_IPV6_EX       0x00000800
+#define NDIS_HASH_TCP_IPV6      0x00001000
+#define NDIS_HASH_TCP_IPV6_EX   0x00002000
+
+#define NDIS_RSS_INDIRECTION_TABLE_MAX_SIZE_REVISION_2 (128 * 4)
+#define NDIS_RSS_HASH_SECRET_KEY_MAX_SIZE_REVISION_2   40
+
+#define ITAB_NUM 128
+#define HASH_KEYLEN NDIS_RSS_HASH_SECRET_KEY_MAX_SIZE_REVISION_2
+extern u8 netvsc_hash_key[];
+
+struct ndis_recv_scale_param { /* NDIS_RECEIVE_SCALE_PARAMETERS */
+	struct ndis_obj_header hdr;
+
+	/* Qualifies the rest of the information */
+	u16 flag;
+
+	/* The base CPU number to do receive processing. not used */
+	u16 base_cpu_number;
+
+	/* This describes the hash function and type being enabled */
+	u32 hashinfo;
+
+	/* The size of indirection table array */
+	u16 indirect_tabsize;
+
+	/* The offset of the indirection table from the beginning of this
+	 * structure
+	 */
+	u32 indirect_taboffset;
+
+	/* The size of the hash secret key */
+	u16 hashkey_size;
+
+	/* The offset of the secret key from the beginning of this structure */
+	u32 kashkey_offset;
+
+	u32 processor_masks_offset;
+	u32 num_processor_masks;
+	u32 processor_masks_entry_size;
 };
 
+/* Fwd declaration */
+struct ndis_tcp_ip_checksum_info;
+
 /*
  * Represent netvsc packet which contains 1 RNDIS and 1 ethernet frame
  * within the RNDIS
  */
 struct hv_netvsc_packet {
 	/* Bookkeeping stuff */
-	struct list_head list_ent;
 	u32 status;
 
 	struct hv_device *device;
 	bool is_data_pkt;
 	u16 vlan_tci;
 
-	/*
-	 * Valid only for receives when we break a xfer page packet
-	 * into multiple netvsc packets
-	 */
-	struct xferpage_packet *xfer_page_pkt;
+	u16 q_idx;
+	struct vmbus_channel *channel;
 
-	union {
-		struct {
-			u64 recv_completion_tid;
-			void *recv_completion_ctx;
-			void (*recv_completion)(void *context);
-		} recv;
-		struct {
-			u64 send_completion_tid;
-			void *send_completion_ctx;
-			void (*send_completion)(void *context);
-		} send;
-	} completion;
+	u64 send_completion_tid;
+	void *send_completion_ctx;
+	void (*send_completion)(void *context);
+
+	u32 send_buf_index;
 
 	/* This points to the memory after page_buf */
 	struct rndis_message *rndis_msg;
@@ -120,6 +189,7 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj,
 int netvsc_recv_callback(struct hv_device *device_obj,
 			struct hv_netvsc_packet *packet,
 			struct ndis_tcp_ip_checksum_info *csum_info);
+void netvsc_channel_cb(void *context);
 int rndis_filter_open(struct hv_device *dev);
 int rndis_filter_close(struct hv_device *dev);
 int rndis_filter_device_add(struct hv_device *dev,
@@ -514,14 +584,16 @@ struct nvsp_message {
 
 #define NETVSC_RECEIVE_BUFFER_SIZE		(1024*1024*16)	/* 16MB */
 #define NETVSC_RECEIVE_BUFFER_SIZE_LEGACY	(1024*1024*15)  /* 15MB */
+#define NETVSC_SEND_BUFFER_SIZE			(1024 * 1024)   /* 1MB */
+#define NETVSC_INVALID_INDEX			-1
 
-#define NETVSC_RECEIVE_BUFFER_ID		0xcafe
 
-/* Preallocated receive packets */
-#define NETVSC_RECEIVE_PACKETLIST_COUNT		256
+#define NETVSC_RECEIVE_BUFFER_ID		0xcafe
 
 #define NETVSC_PACKET_SIZE                      2048
 
+#define VRSS_SEND_TAB_SIZE 16
+
 /* Per netvsc channel-specific */
 struct netvsc_device {
 	struct hv_device *dev;
@@ -532,12 +604,6 @@ struct netvsc_device {
 	wait_queue_head_t wait_drain;
 	bool start_remove;
 	bool destroy;
-	/*
-	 * List of free preallocated hv_netvsc_packet to represent receive
-	 * packet
-	 */
-	struct list_head recv_pkt_list;
-	spinlock_t recv_pkt_list_lock;
 
 	/* Receive buffer allocated by us but manages by NetVSP */
 	void *recv_buf;
@@ -546,6 +612,15 @@ struct netvsc_device {
 	u32 recv_section_cnt;
 	struct nvsp_1_receive_buffer_section *recv_section;
 
+	/* Send buffer allocated by us */
+	void *send_buf;
+	u32 send_buf_size;
+	u32 send_buf_gpadl_handle;
+	u32 send_section_cnt;
+	u32 send_section_size;
+	unsigned long *send_section_map;
+	int map_words;
+
 	/* Used for NetVSP initialization protocol */
 	struct completion channel_init_wait;
 	struct nvsp_message channel_init_pkt;
@@ -555,10 +630,20 @@ struct netvsc_device {
 
 	struct net_device *ndev;
 
+	struct vmbus_channel *chn_table[NR_CPUS];
+	u32 send_table[VRSS_SEND_TAB_SIZE];
+	u32 num_chn;
+	atomic_t queue_sends[NR_CPUS];
+
 	/* Holds rndis device info */
 	void *extension;
-	/* The recive buffer for this device */
+
+	int ring_size;
+
+	/* The primary channel callback buffer */
 	unsigned char cb_buffer[NETVSC_PACKET_SIZE];
+	/* The sub channel callback buffer */
+	unsigned char *sub_cb_buf;
 };
 
 /* NdisInitialize message */
@@ -706,6 +791,7 @@ enum ndis_per_pkt_info_type {
 	IEEE_8021Q_INFO,
 	ORIGINAL_PKTINFO,
 	PACKET_CANCEL_ID,
+	NBL_HASH_VALUE = PACKET_CANCEL_ID,
 	ORIGINAL_NET_BUFLIST,
 	CACHED_NET_BUFLIST,
 	SHORT_PKT_PADINFO,
@@ -852,6 +938,9 @@ struct ndis_tcp_lso_info {
 #define NDIS_LSO_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \
 		sizeof(struct ndis_tcp_lso_info))
 
+#define NDIS_HASH_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \
+		sizeof(u32))
+
 /* Format of Information buffer passed in a SetRequest for the OID */
 /* OID_GEN_RNDIS_CONFIG_PARAMETER. */
 struct rndis_config_parameter_info {
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index f7629ecefa8..d97d5f39a04 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/netdevice.h>
 #include <linux/if_ether.h>
+#include <asm/sync_bitops.h>
 
 #include "hyperv_net.h"
 
@@ -80,7 +81,7 @@ get_in_err:
 }
 
 
-static int netvsc_destroy_recv_buf(struct netvsc_device *net_device)
+static int netvsc_destroy_buf(struct netvsc_device *net_device)
 {
 	struct nvsp_message *revoke_packet;
 	int ret = 0;
@@ -146,10 +147,62 @@ static int netvsc_destroy_recv_buf(struct netvsc_device *net_device)
 		net_device->recv_section = NULL;
 	}
 
+	/* Deal with the send buffer we may have setup.
+	 * If we got a  send section size, it means we received a
+	 * SendsendBufferComplete msg (ie sent
+	 * NvspMessage1TypeSendReceiveBuffer msg) therefore, we need
+	 * to send a revoke msg here
+	 */
+	if (net_device->send_section_size) {
+		/* Send the revoke receive buffer */
+		revoke_packet = &net_device->revoke_packet;
+		memset(revoke_packet, 0, sizeof(struct nvsp_message));
+
+		revoke_packet->hdr.msg_type =
+			NVSP_MSG1_TYPE_REVOKE_SEND_BUF;
+		revoke_packet->msg.v1_msg.revoke_recv_buf.id = 0;
+
+		ret = vmbus_sendpacket(net_device->dev->channel,
+				       revoke_packet,
+				       sizeof(struct nvsp_message),
+				       (unsigned long)revoke_packet,
+				       VM_PKT_DATA_INBAND, 0);
+		/* If we failed here, we might as well return and
+		 * have a leak rather than continue and a bugchk
+		 */
+		if (ret != 0) {
+			netdev_err(ndev, "unable to send "
+				   "revoke send buffer to netvsp\n");
+			return ret;
+		}
+	}
+	/* Teardown the gpadl on the vsp end */
+	if (net_device->send_buf_gpadl_handle) {
+		ret = vmbus_teardown_gpadl(net_device->dev->channel,
+					   net_device->send_buf_gpadl_handle);
+
+		/* If we failed here, we might as well return and have a leak
+		 * rather than continue and a bugchk
+		 */
+		if (ret != 0) {
+			netdev_err(ndev,
+				   "unable to teardown send buffer's gpadl\n");
+			return ret;
+		}
+		net_device->send_buf_gpadl_handle = 0;
+	}
+	if (net_device->send_buf) {
+		/* Free up the receive buffer */
+		free_pages((unsigned long)net_device->send_buf,
+			   get_order(net_device->send_buf_size));
+		net_device->send_buf = NULL;
+	}
+	kfree(net_device->send_section_map);
+
 	return ret;
 }
 
-static int netvsc_init_recv_buf(struct hv_device *device)
+static int netvsc_init_buf(struct hv_device *device)
 {
 	int ret = 0;
 	int t;
@@ -248,10 +301,92 @@ static int netvsc_init_recv_buf(struct hv_device *device)
 		goto cleanup;
 	}
 
+	/* Now setup the send buffer.
+	 */
+	net_device->send_buf =
+		(void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
+					 get_order(net_device->send_buf_size));
+	if (!net_device->send_buf) {
+		netdev_err(ndev, "unable to allocate send "
+			   "buffer of size %d\n", net_device->send_buf_size);
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	/* Establish the gpadl handle for this buffer on this
+	 * channel.  Note: This call uses the vmbus connection rather
+	 * than the channel to establish the gpadl handle.
+	 */
+	ret = vmbus_establish_gpadl(device->channel, net_device->send_buf,
+				    net_device->send_buf_size,
+				    &net_device->send_buf_gpadl_handle);
+	if (ret != 0) {
+		netdev_err(ndev,
+			   "unable to establish send buffer's gpadl\n");
+		goto cleanup;
+	}
+
+	/* Notify the NetVsp of the gpadl handle */
+	init_packet = &net_device->channel_init_pkt;
+	memset(init_packet, 0, sizeof(struct nvsp_message));
+	init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_SEND_BUF;
+	init_packet->msg.v1_msg.send_recv_buf.gpadl_handle =
+		net_device->send_buf_gpadl_handle;
+	init_packet->msg.v1_msg.send_recv_buf.id = 0;
+
+	/* Send the gpadl notification request */
+	ret = vmbus_sendpacket(device->channel, init_packet,
+			       sizeof(struct nvsp_message),
+			       (unsigned long)init_packet,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret != 0) {
+		netdev_err(ndev,
+			   "unable to send send buffer's gpadl to netvsp\n");
+		goto cleanup;
+	}
+
+	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
+	BUG_ON(t == 0);
+
+	/* Check the response */
+	if (init_packet->msg.v1_msg.
+	    send_send_buf_complete.status != NVSP_STAT_SUCCESS) {
+		netdev_err(ndev, "Unable to complete send buffer "
+			   "initialization with NetVsp - status %d\n",
+			   init_packet->msg.v1_msg.
+			   send_recv_buf_complete.status);
+		ret = -EINVAL;
+		goto cleanup;
+	}
+
+	/* Parse the response */
+	net_device->send_section_size = init_packet->msg.
+				v1_msg.send_send_buf_complete.section_size;
+
+	/* Section count is simply the size divided by the section size.
+	 */
+	net_device->send_section_cnt =
+		net_device->send_buf_size/net_device->send_section_size;
+
+	dev_info(&device->device, "Send section size: %d, Section count:%d\n",
+		 net_device->send_section_size, net_device->send_section_cnt);
+
+	/* Setup state for managing the send buffer. */
+	net_device->map_words = DIV_ROUND_UP(net_device->send_section_cnt,
+					     BITS_PER_LONG);
+
+	net_device->send_section_map =
+		kzalloc(net_device->map_words * sizeof(ulong), GFP_KERNEL);
+	if (net_device->send_section_map == NULL) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
 	goto exit;
 
 cleanup:
-	netvsc_destroy_recv_buf(net_device);
+	netvsc_destroy_buf(net_device);
 
 exit:
 	return ret;
@@ -369,8 +504,9 @@ static int netvsc_connect_vsp(struct hv_device *device)
 		net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE_LEGACY;
 	else
 		net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE;
+	net_device->send_buf_size = NETVSC_SEND_BUFFER_SIZE;
 
-	ret = netvsc_init_recv_buf(device);
+	ret = netvsc_init_buf(device);
 
 cleanup:
 	return ret;
@@ -378,7 +514,7 @@ cleanup:
 
 static void netvsc_disconnect_vsp(struct netvsc_device *net_device)
 {
-	netvsc_destroy_recv_buf(net_device);
+	netvsc_destroy_buf(net_device);
 }
 
 /*
@@ -387,7 +523,6 @@ static void netvsc_disconnect_vsp(struct netvsc_device *net_device)
 int netvsc_device_remove(struct hv_device *device)
 {
 	struct netvsc_device *net_device;
-	struct hv_netvsc_packet *netvsc_packet, *pos;
 	unsigned long flags;
 
 	net_device = hv_get_drvdata(device);
@@ -416,11 +551,8 @@ int netvsc_device_remove(struct hv_device *device)
 	vmbus_close(device->channel);
 
 	/* Release all resources */
-	list_for_each_entry_safe(netvsc_packet, pos,
-				 &net_device->recv_pkt_list, list_ent) {
-		list_del(&netvsc_packet->list_ent);
-		kfree(netvsc_packet);
-	}
+	if (net_device->sub_cb_buf)
+		vfree(net_device->sub_cb_buf);
 
 	kfree(net_device);
 	return 0;
@@ -444,6 +576,12 @@ static inline u32 hv_ringbuf_avail_percent(
 	return avail_write * 100 / ring_info->ring_datasize;
 }
 
+static inline void netvsc_free_send_slot(struct netvsc_device *net_device,
+					 u32 index)
+{
+	sync_change_bit(index, net_device->send_section_map);
+}
+
 static void netvsc_send_completion(struct netvsc_device *net_device,
 				   struct hv_device *device,
 				   struct vmpacket_descriptor *packet)
@@ -451,6 +589,7 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 	struct nvsp_message *nvsp_packet;
 	struct hv_netvsc_packet *nvsc_packet;
 	struct net_device *ndev;
+	u32 send_index;
 
 	ndev = net_device->ndev;
 
@@ -461,7 +600,9 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 	    (nvsp_packet->hdr.msg_type ==
 	     NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE) ||
 	    (nvsp_packet->hdr.msg_type ==
-	     NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE)) {
+	     NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE) ||
+	    (nvsp_packet->hdr.msg_type ==
+	     NVSP_MSG5_TYPE_SUBCHANNEL)) {
 		/* Copy the response back */
 		memcpy(&net_device->channel_init_pkt, nvsp_packet,
 		       sizeof(struct nvsp_message));
@@ -469,28 +610,39 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 	} else if (nvsp_packet->hdr.msg_type ==
 		   NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE) {
 		int num_outstanding_sends;
+		u16 q_idx = 0;
+		struct vmbus_channel *channel = device->channel;
+		int queue_sends;
 
 		/* Get the send context */
 		nvsc_packet = (struct hv_netvsc_packet *)(unsigned long)
 			packet->trans_id;
 
 		/* Notify the layer above us */
-		if (nvsc_packet)
-			nvsc_packet->completion.send.send_completion(
-				nvsc_packet->completion.send.
-				send_completion_ctx);
+		if (nvsc_packet) {
+			send_index = nvsc_packet->send_buf_index;
+			if (send_index != NETVSC_INVALID_INDEX)
+				netvsc_free_send_slot(net_device, send_index);
+			q_idx = nvsc_packet->q_idx;
+			channel = nvsc_packet->channel;
+			nvsc_packet->send_completion(nvsc_packet->
+						     send_completion_ctx);
+		}
 
 		num_outstanding_sends =
 			atomic_dec_return(&net_device->num_outstanding_sends);
+		queue_sends = atomic_dec_return(&net_device->
+						queue_sends[q_idx]);
 
 		if (net_device->destroy && num_outstanding_sends == 0)
 			wake_up(&net_device->wait_drain);
 
-		if (netif_queue_stopped(ndev) && !net_device->start_remove &&
-			(hv_ringbuf_avail_percent(&device->channel->outbound)
-			> RING_AVAIL_PERCENT_HIWATER ||
-			num_outstanding_sends < 1))
-				netif_wake_queue(ndev);
+		if (netif_tx_queue_stopped(netdev_get_tx_queue(ndev, q_idx)) &&
+		    !net_device->start_remove &&
+		    (hv_ringbuf_avail_percent(&channel->outbound) >
+		     RING_AVAIL_PERCENT_HIWATER || queue_sends < 1))
+				netif_tx_wake_queue(netdev_get_tx_queue(
+						    ndev, q_idx));
 	} else {
 		netdev_err(ndev, "Unknown send completion packet type- "
 			   "%d received!!\n", nvsp_packet->hdr.msg_type);
@@ -498,6 +650,52 @@ static void netvsc_send_completion(struct netvsc_device *net_device,
 
 }
 
+static u32 netvsc_get_next_send_section(struct netvsc_device *net_device)
+{
+	unsigned long index;
+	u32 max_words = net_device->map_words;
+	unsigned long *map_addr = (unsigned long *)net_device->send_section_map;
+	u32 section_cnt = net_device->send_section_cnt;
+	int ret_val = NETVSC_INVALID_INDEX;
+	int i;
+	int prev_val;
+
+	for (i = 0; i < max_words; i++) {
+		if (!~(map_addr[i]))
+			continue;
+		index = ffz(map_addr[i]);
+		prev_val = sync_test_and_set_bit(index, &map_addr[i]);
+		if (prev_val)
+			continue;
+		if ((index + (i * BITS_PER_LONG)) >= section_cnt)
+			break;
+		ret_val = (index + (i * BITS_PER_LONG));
+		break;
+	}
+	return ret_val;
+}
+
+u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
+			    unsigned int section_index,
+			    struct hv_netvsc_packet *packet)
+{
+	char *start = net_device->send_buf;
+	char *dest = (start + (section_index * net_device->send_section_size));
+	int i;
+	u32 msg_size = 0;
+
+	for (i = 0; i < packet->page_buf_cnt; i++) {
+		char *src = phys_to_virt(packet->page_buf[i].pfn << PAGE_SHIFT);
+		u32 offset = packet->page_buf[i].offset;
+		u32 len = packet->page_buf[i].len;
+
+		memcpy(dest, (src + offset), len);
+		msg_size += len;
+		dest += len;
+	}
+	return msg_size;
+}
+
 int netvsc_send(struct hv_device *device,
 			struct hv_netvsc_packet *packet)
 {
@@ -505,7 +703,12 @@ int netvsc_send(struct hv_device *device,
 	int ret = 0;
 	struct nvsp_message sendMessage;
 	struct net_device *ndev;
+	struct vmbus_channel *out_channel = NULL;
 	u64 req_id;
+	unsigned int section_index = NETVSC_INVALID_INDEX;
+	u32 msg_size = 0;
+	struct sk_buff *skb;
+
 
 	net_device = get_outbound_net_device(device);
 	if (!net_device)
@@ -521,25 +724,46 @@ int netvsc_send(struct hv_device *device,
 		sendMessage.msg.v1_msg.send_rndis_pkt.channel_type = 1;
 	}
 
-	/* Not using send buffer section */
+	/* Attempt to send via sendbuf */
+	if (packet->total_data_buflen < net_device->send_section_size) {
+		section_index = netvsc_get_next_send_section(net_device);
+		if (section_index != NETVSC_INVALID_INDEX) {
+			msg_size = netvsc_copy_to_send_buf(net_device,
+							   section_index,
+							   packet);
+			skb = (struct sk_buff *)
+			      (unsigned long)packet->send_completion_tid;
+			if (skb)
+				dev_kfree_skb_any(skb);
+			packet->page_buf_cnt = 0;
+		}
+	}
+	packet->send_buf_index = section_index;
+
+
 	sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_index =
-		0xFFFFFFFF;
-	sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_size = 0;
+		section_index;
+	sendMessage.msg.v1_msg.send_rndis_pkt.send_buf_section_size = msg_size;
 
-	if (packet->completion.send.send_completion)
+	if (packet->send_completion)
 		req_id = (ulong)packet;
 	else
 		req_id = 0;
 
+	out_channel = net_device->chn_table[packet->q_idx];
+	if (out_channel == NULL)
+		out_channel = device->channel;
+	packet->channel = out_channel;
+
 	if (packet->page_buf_cnt) {
-		ret = vmbus_sendpacket_pagebuffer(device->channel,
+		ret = vmbus_sendpacket_pagebuffer(out_channel,
 						  packet->page_buf,
 						  packet->page_buf_cnt,
 						  &sendMessage,
 						  sizeof(struct nvsp_message),
 						  req_id);
 	} else {
-		ret = vmbus_sendpacket(device->channel, &sendMessage,
+		ret = vmbus_sendpacket(out_channel, &sendMessage,
 				sizeof(struct nvsp_message),
 				req_id,
 				VM_PKT_DATA_INBAND,
@@ -548,17 +772,24 @@ int netvsc_send(struct hv_device *device,
 
 	if (ret == 0) {
 		atomic_inc(&net_device->num_outstanding_sends);
-		if (hv_ringbuf_avail_percent(&device->channel->outbound) <
+		atomic_inc(&net_device->queue_sends[packet->q_idx]);
+
+		if (hv_ringbuf_avail_percent(&out_channel->outbound) <
 			RING_AVAIL_PERCENT_LOWATER) {
-			netif_stop_queue(ndev);
+			netif_tx_stop_queue(netdev_get_tx_queue(
+					    ndev, packet->q_idx));
+
 			if (atomic_read(&net_device->
-				num_outstanding_sends) < 1)
-				netif_wake_queue(ndev);
+				queue_sends[packet->q_idx]) < 1)
+				netif_tx_wake_queue(netdev_get_tx_queue(
+						    ndev, packet->q_idx));
 		}
 	} else if (ret == -EAGAIN) {
-		netif_stop_queue(ndev);
-		if (atomic_read(&net_device->num_outstanding_sends) < 1) {
-			netif_wake_queue(ndev);
+		netif_tx_stop_queue(netdev_get_tx_queue(
+				    ndev, packet->q_idx));
+		if (atomic_read(&net_device->queue_sends[packet->q_idx]) < 1) {
+			netif_tx_wake_queue(netdev_get_tx_queue(
+					    ndev, packet->q_idx));
 			ret = -ENOSPC;
 		}
 	} else {
@@ -570,6 +801,7 @@ int netvsc_send(struct hv_device *device,
 }
 
 static void netvsc_send_recv_completion(struct hv_device *device,
+					struct vmbus_channel *channel,
 					struct netvsc_device *net_device,
 					u64 transaction_id, u32 status)
 {
@@ -587,7 +819,7 @@ static void netvsc_send_recv_completion(struct hv_device *device,
 
 retry_send_cmplt:
 	/* Send the completion */
-	ret = vmbus_sendpacket(device->channel, &recvcompMessage,
+	ret = vmbus_sendpacket(channel, &recvcompMessage,
 			       sizeof(struct nvsp_message), transaction_id,
 			       VM_PKT_COMP, 0);
 	if (ret == 0) {
@@ -613,76 +845,20 @@ retry_send_cmplt:
 	}
 }
 
-/* Send a receive completion packet to RNDIS device (ie NetVsp) */
-static void netvsc_receive_completion(void *context)
-{
-	struct hv_netvsc_packet *packet = context;
-	struct hv_device *device = packet->device;
-	struct netvsc_device *net_device;
-	u64 transaction_id = 0;
-	bool fsend_receive_comp = false;
-	unsigned long flags;
-	struct net_device *ndev;
-	u32 status = NVSP_STAT_NONE;
-
-	/*
-	 * Even though it seems logical to do a GetOutboundNetDevice() here to
-	 * send out receive completion, we are using GetInboundNetDevice()
-	 * since we may have disable outbound traffic already.
-	 */
-	net_device = get_inbound_net_device(device);
-	if (!net_device)
-		return;
-	ndev = net_device->ndev;
-
-	/* Overloading use of the lock. */
-	spin_lock_irqsave(&net_device->recv_pkt_list_lock, flags);
-
-	if (packet->status != NVSP_STAT_SUCCESS)
-		packet->xfer_page_pkt->status = NVSP_STAT_FAIL;
-
-	packet->xfer_page_pkt->count--;
-
-	/*
-	 * Last one in the line that represent 1 xfer page packet.
-	 * Return the xfer page packet itself to the freelist
-	 */
-	if (packet->xfer_page_pkt->count == 0) {
-		fsend_receive_comp = true;
-		transaction_id = packet->completion.recv.recv_completion_tid;
-		status = packet->xfer_page_pkt->status;
-		list_add_tail(&packet->xfer_page_pkt->list_ent,
-			      &net_device->recv_pkt_list);
-
-	}
-
-	/* Put the packet back */
-	list_add_tail(&packet->list_ent, &net_device->recv_pkt_list);
-	spin_unlock_irqrestore(&net_device->recv_pkt_list_lock, flags);
-
-	/* Send a receive completion for the xfer page packet */
-	if (fsend_receive_comp)
-		netvsc_send_recv_completion(device, net_device, transaction_id,
-					status);
-
-}
-
 static void netvsc_receive(struct netvsc_device *net_device,
+			struct vmbus_channel *channel,
 			struct hv_device *device,
 			struct vmpacket_descriptor *packet)
 {
 	struct vmtransfer_page_packet_header *vmxferpage_packet;
 	struct nvsp_message *nvsp_packet;
-	struct hv_netvsc_packet *netvsc_packet = NULL;
-	/* struct netvsc_driver *netvscDriver; */
-	struct xferpage_packet *xferpage_packet = NULL;
+	struct hv_netvsc_packet nv_pkt;
+	struct hv_netvsc_packet *netvsc_packet = &nv_pkt;
+	u32 status = NVSP_STAT_SUCCESS;
 	int i;
 	int count = 0;
-	unsigned long flags;
 	struct net_device *ndev;
 
-	LIST_HEAD(listHead);
-
 	ndev = net_device->ndev;
 
 	/*
@@ -715,77 +891,14 @@ static void netvsc_receive(struct netvsc_device *net_device,
 		return;
 	}
 
-	/*
-	 * Grab free packets (range count + 1) to represent this xfer
-	 * page packet. +1 to represent the xfer page packet itself.
-	 * We grab it here so that we know exactly how many we can
-	 * fulfil
-	 */
-	spin_lock_irqsave(&net_device->recv_pkt_list_lock, flags);
-	while (!list_empty(&net_device->recv_pkt_list)) {
-		list_move_tail(net_device->recv_pkt_list.next, &listHead);
-		if (++count == vmxferpage_packet->range_cnt + 1)
-			break;
-	}
-	spin_unlock_irqrestore(&net_device->recv_pkt_list_lock, flags);
-
-	/*
-	 * We need at least 2 netvsc pkts (1 to represent the xfer
-	 * page and at least 1 for the range) i.e. we can handled
-	 * some of the xfer page packet ranges...
-	 */
-	if (count < 2) {
-		netdev_err(ndev, "Got only %d netvsc pkt...needed "
-			"%d pkts. Dropping this xfer page packet completely!\n",
-			count, vmxferpage_packet->range_cnt + 1);
-
-		/* Return it to the freelist */
-		spin_lock_irqsave(&net_device->recv_pkt_list_lock, flags);
-		for (i = count; i != 0; i--) {
-			list_move_tail(listHead.next,
-				       &net_device->recv_pkt_list);
-		}
-		spin_unlock_irqrestore(&net_device->recv_pkt_list_lock,
-				       flags);
-
-		netvsc_send_recv_completion(device, net_device,
-					    vmxferpage_packet->d.trans_id,
-					    NVSP_STAT_FAIL);
-
-		return;
-	}
-
-	/* Remove the 1st packet to represent the xfer page packet itself */
-	xferpage_packet = (struct xferpage_packet *)listHead.next;
-	list_del(&xferpage_packet->list_ent);
-	xferpage_packet->status = NVSP_STAT_SUCCESS;
-
-	/* This is how much we can satisfy */
-	xferpage_packet->count = count - 1;
-
-	if (xferpage_packet->count != vmxferpage_packet->range_cnt) {
-		netdev_err(ndev, "Needed %d netvsc pkts to satisfy "
-			"this xfer page...got %d\n",
-			vmxferpage_packet->range_cnt, xferpage_packet->count);
-	}
+	count = vmxferpage_packet->range_cnt;
+	netvsc_packet->device = device;
+	netvsc_packet->channel = channel;
 
 	/* Each range represents 1 RNDIS pkt that contains 1 ethernet frame */
-	for (i = 0; i < (count - 1); i++) {
-		netvsc_packet = (struct hv_netvsc_packet *)listHead.next;
-		list_del(&netvsc_packet->list_ent);
-
+	for (i = 0; i < count; i++) {
 		/* Initialize the netvsc packet */
 		netvsc_packet->status = NVSP_STAT_SUCCESS;
-		netvsc_packet->xfer_page_pkt = xferpage_packet;
-		netvsc_packet->completion.recv.recv_completion =
-					netvsc_receive_completion;
-		netvsc_packet->completion.recv.recv_completion_ctx =
-					netvsc_packet;
-		netvsc_packet->device = device;
-		/* Save this so that we can send it back */
-		netvsc_packet->completion.recv.recv_completion_tid =
-					vmxferpage_packet->d.trans_id;
-
 		netvsc_packet->data = (void *)((unsigned long)net_device->
 			recv_buf + vmxferpage_packet->ranges[i].byte_offset);
 		netvsc_packet->total_data_buflen =
@@ -794,16 +907,53 @@ static void netvsc_receive(struct netvsc_device *net_device,
 		/* Pass it to the upper layer */
 		rndis_filter_receive(device, netvsc_packet);
 
-		netvsc_receive_completion(netvsc_packet->
-				completion.recv.recv_completion_ctx);
+		if (netvsc_packet->status != NVSP_STAT_SUCCESS)
+			status = NVSP_STAT_FAIL;
 	}
 
+	netvsc_send_recv_completion(device, channel, net_device,
+				    vmxferpage_packet->d.trans_id, status);
 }
 
-static void netvsc_channel_cb(void *context)
+
+static void netvsc_send_table(struct hv_device *hdev,
+			      struct vmpacket_descriptor *vmpkt)
+{
+	struct netvsc_device *nvscdev;
+	struct net_device *ndev;
+	struct nvsp_message *nvmsg;
+	int i;
+	u32 count, *tab;
+
+	nvscdev = get_outbound_net_device(hdev);
+	if (!nvscdev)
+		return;
+	ndev = nvscdev->ndev;
+
+	nvmsg = (struct nvsp_message *)((unsigned long)vmpkt +
+					(vmpkt->offset8 << 3));
+
+	if (nvmsg->hdr.msg_type != NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE)
+		return;
+
+	count = nvmsg->msg.v5_msg.send_table.count;
+	if (count != VRSS_SEND_TAB_SIZE) {
+		netdev_err(ndev, "Received wrong send-table size:%u\n", count);
+		return;
+	}
+
+	tab = (u32 *)((unsigned long)&nvmsg->msg.v5_msg.send_table +
+		      nvmsg->msg.v5_msg.send_table.offset);
+
+	for (i = 0; i < count; i++)
+		nvscdev->send_table[i] = tab[i];
+}
+
+void netvsc_channel_cb(void *context)
 {
 	int ret;
-	struct hv_device *device = context;
+	struct vmbus_channel *channel = (struct vmbus_channel *)context;
+	struct hv_device *device;
 	struct netvsc_device *net_device;
 	u32 bytes_recvd;
 	u64 request_id;
@@ -812,14 +962,19 @@ static void netvsc_channel_cb(void *context)
 	int bufferlen = NETVSC_PACKET_SIZE;
 	struct net_device *ndev;
 
+	if (channel->primary_channel != NULL)
+		device = channel->primary_channel->device_obj;
+	else
+		device = channel->device_obj;
+
 	net_device = get_inbound_net_device(device);
 	if (!net_device)
 		return;
 	ndev = net_device->ndev;
-	buffer = net_device->cb_buffer;
+	buffer = get_per_channel_state(channel);
 
 	do {
-		ret = vmbus_recvpacket_raw(device->channel, buffer, bufferlen,
+		ret = vmbus_recvpacket_raw(channel, buffer, bufferlen,
 					   &bytes_recvd, &request_id);
 		if (ret == 0) {
 			if (bytes_recvd > 0) {
@@ -831,8 +986,12 @@ static void netvsc_channel_cb(void *context)
 					break;
 
 				case VM_PKT_DATA_USING_XFER_PAGES:
-					netvsc_receive(net_device,
-							device, desc);
+					netvsc_receive(net_device, channel,
+						       device, desc);
+					break;
+
+				case VM_PKT_DATA_INBAND:
+					netvsc_send_table(device, desc);
 					break;
 
 				default:
@@ -880,11 +1039,9 @@ static void netvsc_channel_cb(void *context)
 int netvsc_device_add(struct hv_device *device, void *additional_info)
 {
 	int ret = 0;
-	int i;
 	int ring_size =
 	((struct netvsc_device_info *)additional_info)->ring_size;
 	struct netvsc_device *net_device;
-	struct hv_netvsc_packet *packet, *pos;
 	struct net_device *ndev;
 
 	net_device = alloc_net_device(device);
@@ -893,6 +1050,8 @@ int netvsc_device_add(struct hv_device *device, void *additional_info)
 		goto cleanup;
 	}
 
+	net_device->ring_size = ring_size;
+
 	/*
 	 * Coming into this function, struct net_device * is
 	 * registered as the driver private data.
@@ -903,24 +1062,14 @@ int netvsc_device_add(struct hv_device *device, void *additional_info)
 	ndev = net_device->ndev;
 
 	/* Initialize the NetVSC channel extension */
-	spin_lock_init(&net_device->recv_pkt_list_lock);
-
-	INIT_LIST_HEAD(&net_device->recv_pkt_list);
-
-	for (i = 0; i < NETVSC_RECEIVE_PACKETLIST_COUNT; i++) {
-		packet = kzalloc(sizeof(struct hv_netvsc_packet), GFP_KERNEL);
-		if (!packet)
-			break;
-
-		list_add_tail(&packet->list_ent,
-			      &net_device->recv_pkt_list);
-	}
 	init_completion(&net_device->channel_init_wait);
 
+	set_per_channel_state(device->channel, net_device->cb_buffer);
+
 	/* Open the channel */
 	ret = vmbus_open(device->channel, ring_size * PAGE_SIZE,
 			 ring_size * PAGE_SIZE, NULL, 0,
-			 netvsc_channel_cb, device);
+			 netvsc_channel_cb, device->channel);
 
 	if (ret != 0) {
 		netdev_err(ndev, "unable to open channel: %d\n", ret);
@@ -930,6 +1079,8 @@ int netvsc_device_add(struct hv_device *device, void *additional_info)
 	/* Channel is opened */
 	pr_info("hv_netvsc channel opened successfully\n");
 
+	net_device->chn_table[0] = device->channel;
+
 	/* Connect with the NetVsp */
 	ret = netvsc_connect_vsp(device);
 	if (ret != 0) {
@@ -946,16 +1097,8 @@ close:
 
 cleanup:
 
-	if (net_device) {
-		list_for_each_entry_safe(packet, pos,
-					 &net_device->recv_pkt_list,
-					 list_ent) {
-			list_del(&packet->list_ent);
-			kfree(packet);
-		}
-
+	if (net_device)
 		kfree(net_device);
-	}
 
 	return ret;
 }
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 7918d5132c1..4fd71b75e66 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -101,7 +101,7 @@ static int netvsc_open(struct net_device *net)
 		return ret;
 	}
 
-	netif_start_queue(net);
+	netif_tx_start_all_queues(net);
 
 	nvdev = hv_get_drvdata(device_obj);
 	rdev = nvdev->extension;
@@ -149,15 +149,100 @@ static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size,
 	return ppi;
 }
 
+union sub_key {
+	u64 k;
+	struct {
+		u8 pad[3];
+		u8 kb;
+		u32 ka;
+	};
+};
+
+/* Toeplitz hash function
+ * data: network byte order
+ * return: host byte order
+ */
+static u32 comp_hash(u8 *key, int klen, u8 *data, int dlen)
+{
+	union sub_key subk;
+	int k_next = 4;
+	u8 dt;
+	int i, j;
+	u32 ret = 0;
+
+	subk.k = 0;
+	subk.ka = ntohl(*(u32 *)key);
+
+	for (i = 0; i < dlen; i++) {
+		subk.kb = key[k_next];
+		k_next = (k_next + 1) % klen;
+		dt = data[i];
+		for (j = 0; j < 8; j++) {
+			if (dt & 0x80)
+				ret ^= subk.ka;
+			dt <<= 1;
+			subk.k <<= 1;
+		}
+	}
+
+	return ret;
+}
+
+static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb)
+{
+	struct iphdr *iphdr;
+	int data_len;
+	bool ret = false;
+
+	if (eth_hdr(skb)->h_proto != htons(ETH_P_IP))
+		return false;
+
+	iphdr = ip_hdr(skb);
+
+	if (iphdr->version == 4) {
+		if (iphdr->protocol == IPPROTO_TCP)
+			data_len = 12;
+		else
+			data_len = 8;
+		*hash = comp_hash(netvsc_hash_key, HASH_KEYLEN,
+				  (u8 *)&iphdr->saddr, data_len);
+		ret = true;
+	}
+
+	return ret;
+}
+
+static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
+			void *accel_priv, select_queue_fallback_t fallback)
+{
+	struct net_device_context *net_device_ctx = netdev_priv(ndev);
+	struct hv_device *hdev =  net_device_ctx->device_ctx;
+	struct netvsc_device *nvsc_dev = hv_get_drvdata(hdev);
+	u32 hash;
+	u16 q_idx = 0;
+
+	if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1)
+		return 0;
+
+	if (netvsc_set_hash(&hash, skb)) {
+		q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] %
+			ndev->real_num_tx_queues;
+		skb_set_hash(skb, hash, PKT_HASH_TYPE_L3);
+	}
+
+	return q_idx;
+}
+
 static void netvsc_xmit_completion(void *context)
 {
 	struct hv_netvsc_packet *packet = (struct hv_netvsc_packet *)context;
 	struct sk_buff *skb = (struct sk_buff *)
-		(unsigned long)packet->completion.send.send_completion_tid;
+		(unsigned long)packet->send_completion_tid;
+	u32 index = packet->send_buf_index;
 
 	kfree(packet);
 
-	if (skb)
+	if (skb && (index == NETVSC_INVALID_INDEX))
 		dev_kfree_skb_any(skb);
 }
 
@@ -301,6 +386,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	struct ndis_tcp_lso_info *lso_info;
 	int  hdr_offset;
 	u32 net_trans_info;
+	u32 hash;
 
 
 	/* We will atmost need two pages to describe the rndis
@@ -319,9 +405,8 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 	packet = kzalloc(sizeof(struct hv_netvsc_packet) +
 			 (num_data_pgs * sizeof(struct hv_page_buffer)) +
 			 sizeof(struct rndis_message) +
-			 NDIS_VLAN_PPI_SIZE +
-			 NDIS_CSUM_PPI_SIZE +
-			 NDIS_LSO_PPI_SIZE, GFP_ATOMIC);
+			 NDIS_VLAN_PPI_SIZE + NDIS_CSUM_PPI_SIZE +
+			 NDIS_LSO_PPI_SIZE + NDIS_HASH_PPI_SIZE, GFP_ATOMIC);
 	if (!packet) {
 		/* out of memory, drop packet */
 		netdev_err(net, "unable to allocate hv_netvsc_packet\n");
@@ -333,6 +418,8 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 
 	packet->vlan_tci = skb->vlan_tci;
 
+	packet->q_idx = skb_get_queue_mapping(skb);
+
 	packet->is_data_pkt = true;
 	packet->total_data_buflen = skb->len;
 
@@ -341,9 +428,9 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 				(num_data_pgs * sizeof(struct hv_page_buffer)));
 
 	/* Set the completion routine */
-	packet->completion.send.send_completion = netvsc_xmit_completion;
-	packet->completion.send.send_completion_ctx = packet;
-	packet->completion.send.send_completion_tid = (unsigned long)skb;
+	packet->send_completion = netvsc_xmit_completion;
+	packet->send_completion_ctx = packet;
+	packet->send_completion_tid = (unsigned long)skb;
 
 	isvlan = packet->vlan_tci & VLAN_TAG_PRESENT;
 
@@ -358,6 +445,14 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net)
 
 	rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet);
 
+	hash = skb_get_hash_raw(skb);
+	if (hash != 0 && net->real_num_tx_queues > 1) {
+		rndis_msg_size += NDIS_HASH_PPI_SIZE;
+		ppi = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE,
+				    NBL_HASH_VALUE);
+		*(u32 *)((void *)ppi + ppi->ppi_offset) = hash;
+	}
+
 	if (isvlan) {
 		struct ndis_pkt_8021q_info *vlan;
 
@@ -558,6 +653,9 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 				       packet->vlan_tci);
 
+	skb_record_rx_queue(skb, packet->channel->
+			    offermsg.offer.sub_channel_index);
+
 	net->stats.rx_packets++;
 	net->stats.rx_bytes += packet->total_data_buflen;
 
@@ -606,7 +704,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu)
 	hv_set_drvdata(hdev, ndev);
 	device_info.ring_size = ring_size;
 	rndis_filter_device_add(hdev, &device_info);
-	netif_wake_queue(ndev);
+	netif_tx_wake_all_queues(ndev);
 
 	return 0;
 }
@@ -652,6 +750,7 @@ static const struct net_device_ops device_ops = {
 	.ndo_change_mtu =		netvsc_change_mtu,
 	.ndo_validate_addr =		eth_validate_addr,
 	.ndo_set_mac_address =		netvsc_set_mac_addr,
+	.ndo_select_queue =		netvsc_select_queue,
 };
 
 /*
@@ -698,9 +797,11 @@ static int netvsc_probe(struct hv_device *dev,
 	struct net_device *net = NULL;
 	struct net_device_context *net_device_ctx;
 	struct netvsc_device_info device_info;
+	struct netvsc_device *nvdev;
 	int ret;
 
-	net = alloc_etherdev(sizeof(struct net_device_context));
+	net = alloc_etherdev_mq(sizeof(struct net_device_context),
+				num_online_cpus());
 	if (!net)
 		return -ENOMEM;
 
@@ -719,7 +820,7 @@ static int netvsc_probe(struct hv_device *dev,
 	net->features = NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_SG | NETIF_F_RXCSUM |
 			NETIF_F_IP_CSUM | NETIF_F_TSO;
 
-	SET_ETHTOOL_OPS(net, &ethtool_ops);
+	net->ethtool_ops = &ethtool_ops;
 	SET_NETDEV_DEV(net, &dev->device);
 
 	/* Notify the netvsc driver of the new device */
@@ -733,6 +834,10 @@ static int netvsc_probe(struct hv_device *dev,
 	}
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
+	nvdev = hv_get_drvdata(dev);
+	netif_set_real_num_tx_queues(net, nvdev->num_chn);
+	netif_set_real_num_rx_queues(net, nvdev->num_chn);
+
 	ret = register_netdev(net);
 	if (ret != 0) {
 		pr_err("Unable to register netdev.\n");
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 143a98caf61..99c527adae5 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -31,7 +31,7 @@
 #include "hyperv_net.h"
 
 
-#define RNDIS_EXT_LEN 100
+#define RNDIS_EXT_LEN PAGE_SIZE
 struct rndis_request {
 	struct list_head list_ent;
 	struct completion  wait_event;
@@ -94,6 +94,8 @@ static struct rndis_request *get_rndis_request(struct rndis_device *dev,
 	rndis_msg->ndis_msg_type = msg_type;
 	rndis_msg->msg_len = msg_len;
 
+	request->pkt.q_idx = 0;
+
 	/*
 	 * Set the request id. This field is always after the rndis header for
 	 * request/response packet types so we just used the SetRequest as a
@@ -234,7 +236,7 @@ static int rndis_filter_send_request(struct rndis_device *dev,
 			packet->page_buf[0].len;
 	}
 
-	packet->completion.send.send_completion = NULL;
+	packet->send_completion = NULL;
 
 	ret = netvsc_send(dev->net_dev->dev, packet);
 	return ret;
@@ -399,8 +401,6 @@ static void rndis_filter_receive_data(struct rndis_device *dev,
 	pkt->total_data_buflen = rndis_pkt->data_len;
 	pkt->data = (void *)((unsigned long)pkt->data + data_offset);
 
-	pkt->is_data_pkt = true;
-
 	vlan = rndis_get_ppi(rndis_pkt, IEEE_8021Q_INFO);
 	if (vlan) {
 		pkt->vlan_tci = VLAN_TAG_PRESENT | vlan->vlanid |
@@ -509,6 +509,19 @@ static int rndis_filter_query_device(struct rndis_device *dev, u32 oid,
 	query->info_buflen = 0;
 	query->dev_vc_handle = 0;
 
+	if (oid == OID_GEN_RECEIVE_SCALE_CAPABILITIES) {
+		struct ndis_recv_scale_cap *cap;
+
+		request->request_msg.msg_len +=
+			sizeof(struct ndis_recv_scale_cap);
+		query->info_buflen = sizeof(struct ndis_recv_scale_cap);
+		cap = (struct ndis_recv_scale_cap *)((unsigned long)query +
+						     query->info_buf_offset);
+		cap->hdr.type = NDIS_OBJECT_TYPE_RSS_CAPABILITIES;
+		cap->hdr.rev = NDIS_RECEIVE_SCALE_CAPABILITIES_REVISION_2;
+		cap->hdr.size = sizeof(struct ndis_recv_scale_cap);
+	}
+
 	ret = rndis_filter_send_request(dev, request);
 	if (ret != 0)
 		goto cleanup;
@@ -695,6 +708,89 @@ cleanup:
 	return ret;
 }
 
+u8 netvsc_hash_key[HASH_KEYLEN] = {
+	0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2,
+	0x41, 0x67, 0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0,
+	0xd0, 0xca, 0x2b, 0xcb, 0xae, 0x7b, 0x30, 0xb4,
+	0x77, 0xcb, 0x2d, 0xa3, 0x80, 0x30, 0xf2, 0x0c,
+	0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa
+};
+
+int rndis_filter_set_rss_param(struct rndis_device *rdev, int num_queue)
+{
+	struct net_device *ndev = rdev->net_dev->ndev;
+	struct rndis_request *request;
+	struct rndis_set_request *set;
+	struct rndis_set_complete *set_complete;
+	u32 extlen = sizeof(struct ndis_recv_scale_param) +
+		     4*ITAB_NUM + HASH_KEYLEN;
+	struct ndis_recv_scale_param *rssp;
+	u32 *itab;
+	u8 *keyp;
+	int i, t, ret;
+
+	request = get_rndis_request(
+			rdev, RNDIS_MSG_SET,
+			RNDIS_MESSAGE_SIZE(struct rndis_set_request) + extlen);
+	if (!request)
+		return -ENOMEM;
+
+	set = &request->request_msg.msg.set_req;
+	set->oid = OID_GEN_RECEIVE_SCALE_PARAMETERS;
+	set->info_buflen = extlen;
+	set->info_buf_offset = sizeof(struct rndis_set_request);
+	set->dev_vc_handle = 0;
+
+	rssp = (struct ndis_recv_scale_param *)(set + 1);
+	rssp->hdr.type = NDIS_OBJECT_TYPE_RSS_PARAMETERS;
+	rssp->hdr.rev = NDIS_RECEIVE_SCALE_PARAMETERS_REVISION_2;
+	rssp->hdr.size = sizeof(struct ndis_recv_scale_param);
+	rssp->flag = 0;
+	rssp->hashinfo = NDIS_HASH_FUNC_TOEPLITZ | NDIS_HASH_IPV4 |
+			 NDIS_HASH_TCP_IPV4;
+	rssp->indirect_tabsize = 4*ITAB_NUM;
+	rssp->indirect_taboffset = sizeof(struct ndis_recv_scale_param);
+	rssp->hashkey_size = HASH_KEYLEN;
+	rssp->kashkey_offset = rssp->indirect_taboffset +
+			       rssp->indirect_tabsize;
+
+	/* Set indirection table entries */
+	itab = (u32 *)(rssp + 1);
+	for (i = 0; i < ITAB_NUM; i++)
+		itab[i] = i % num_queue;
+
+	/* Set hask key values */
+	keyp = (u8 *)((unsigned long)rssp + rssp->kashkey_offset);
+	for (i = 0; i < HASH_KEYLEN; i++)
+		keyp[i] = netvsc_hash_key[i];
+
+
+	ret = rndis_filter_send_request(rdev, request);
+	if (ret != 0)
+		goto cleanup;
+
+	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	if (t == 0) {
+		netdev_err(ndev, "timeout before we got a set response...\n");
+		/* can't put_rndis_request, since we may still receive a
+		 * send-completion.
+		 */
+		return -ETIMEDOUT;
+	} else {
+		set_complete = &request->response_msg.msg.set_complete;
+		if (set_complete->status != RNDIS_STATUS_SUCCESS) {
+			netdev_err(ndev, "Fail to set RSS parameters:0x%x\n",
+				   set_complete->status);
+			ret = -EINVAL;
+		}
+	}
+
+cleanup:
+	put_rndis_request(rdev, request);
+	return ret;
+}
+
+
 static int rndis_filter_query_device_link_status(struct rndis_device *dev)
 {
 	u32 size = sizeof(u32);
@@ -886,6 +982,28 @@ static int rndis_filter_close_device(struct rndis_device *dev)
 	return ret;
 }
 
+static void netvsc_sc_open(struct vmbus_channel *new_sc)
+{
+	struct netvsc_device *nvscdev;
+	u16 chn_index = new_sc->offermsg.offer.sub_channel_index;
+	int ret;
+
+	nvscdev = hv_get_drvdata(new_sc->primary_channel->device_obj);
+
+	if (chn_index >= nvscdev->num_chn)
+		return;
+
+	set_per_channel_state(new_sc, nvscdev->sub_cb_buf + (chn_index - 1) *
+			      NETVSC_PACKET_SIZE);
+
+	ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE,
+			 nvscdev->ring_size * PAGE_SIZE, NULL, 0,
+			 netvsc_channel_cb, new_sc);
+
+	if (ret == 0)
+		nvscdev->chn_table[chn_index] = new_sc;
+}
+
 int rndis_filter_device_add(struct hv_device *dev,
 				  void *additional_info)
 {
@@ -894,6 +1012,10 @@ int rndis_filter_device_add(struct hv_device *dev,
 	struct rndis_device *rndis_device;
 	struct netvsc_device_info *device_info = additional_info;
 	struct ndis_offload_params offloads;
+	struct nvsp_message *init_packet;
+	int t;
+	struct ndis_recv_scale_cap rsscap;
+	u32 rsscap_size = sizeof(struct ndis_recv_scale_cap);
 
 	rndis_device = get_rndis_device();
 	if (!rndis_device)
@@ -913,6 +1035,7 @@ int rndis_filter_device_add(struct hv_device *dev,
 
 	/* Initialize the rndis device */
 	net_device = hv_get_drvdata(dev);
+	net_device->num_chn = 1;
 
 	net_device->extension = rndis_device;
 	rndis_device->net_dev = net_device;
@@ -952,7 +1075,6 @@ int rndis_filter_device_add(struct hv_device *dev,
 	if (ret)
 		goto err_dev_remv;
 
-
 	rndis_filter_query_device_link_status(rndis_device);
 
 	device_info->link_state = rndis_device->link_state;
@@ -961,7 +1083,66 @@ int rndis_filter_device_add(struct hv_device *dev,
 		 rndis_device->hw_mac_adr,
 		 device_info->link_state ? "down" : "up");
 
-	return ret;
+	if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_5)
+		return 0;
+
+	/* vRSS setup */
+	memset(&rsscap, 0, rsscap_size);
+	ret = rndis_filter_query_device(rndis_device,
+					OID_GEN_RECEIVE_SCALE_CAPABILITIES,
+					&rsscap, &rsscap_size);
+	if (ret || rsscap.num_recv_que < 2)
+		goto out;
+
+	net_device->num_chn = (num_online_cpus() < rsscap.num_recv_que) ?
+			       num_online_cpus() : rsscap.num_recv_que;
+	if (net_device->num_chn == 1)
+		goto out;
+
+	net_device->sub_cb_buf = vzalloc((net_device->num_chn - 1) *
+					 NETVSC_PACKET_SIZE);
+	if (!net_device->sub_cb_buf) {
+		net_device->num_chn = 1;
+		dev_info(&dev->device, "No memory for subchannels.\n");
+		goto out;
+	}
+
+	vmbus_set_sc_create_callback(dev->channel, netvsc_sc_open);
+
+	init_packet = &net_device->channel_init_pkt;
+	memset(init_packet, 0, sizeof(struct nvsp_message));
+	init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
+	init_packet->msg.v5_msg.subchn_req.op = NVSP_SUBCHANNEL_ALLOCATE;
+	init_packet->msg.v5_msg.subchn_req.num_subchannels =
+						net_device->num_chn - 1;
+	ret = vmbus_sendpacket(dev->channel, init_packet,
+			       sizeof(struct nvsp_message),
+			       (unsigned long)init_packet,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret)
+		goto out;
+	t = wait_for_completion_timeout(&net_device->channel_init_wait, 5*HZ);
+	if (t == 0) {
+		ret = -ETIMEDOUT;
+		goto out;
+	}
+	if (init_packet->msg.v5_msg.subchn_comp.status !=
+	    NVSP_STAT_SUCCESS) {
+		ret = -ENODEV;
+		goto out;
+	}
+	net_device->num_chn = 1 +
+		init_packet->msg.v5_msg.subchn_comp.num_subchannels;
+
+	vmbus_are_subchannels_present(dev->channel);
+
+	ret = rndis_filter_set_rss_param(rndis_device, net_device->num_chn);
+
+out:
+	if (ret)
+		net_device->num_chn = 1;
+	return 0; /* return 0 because primary channel can be used alone */
 
 err_dev_remv:
 	rndis_filter_device_remove(dev);
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index e36f194673a..50899416f66 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
@@ -692,10 +693,7 @@ at86rf230_xmit(struct ieee802154_dev *dev, struct sk_buff *skb)
 	if (rc < 0)
 		goto err_rx;
 
-	rc = at86rf230_start(dev);
-
-	return rc;
-
+	return at86rf230_start(dev);
 err_rx:
 	at86rf230_start(dev);
 err:
@@ -963,33 +961,24 @@ static irqreturn_t at86rf230_isr_level(int irq, void *data)
 	return at86rf230_isr(irq, data);
 }
 
-static int at86rf230_irq_polarity(struct at86rf230_local *lp, int pol)
-{
-	return at86rf230_write_subreg(lp, SR_IRQ_POLARITY, pol);
-}
-
 static int at86rf230_hw_init(struct at86rf230_local *lp)
 {
-	struct at86rf230_platform_data *pdata = lp->spi->dev.platform_data;
-	int rc, irq_pol;
-	u8 status;
+	int rc, irq_pol, irq_type;
+	u8 dvdd;
 	u8 csma_seed[2];
 
-	rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status);
-	if (rc)
-		return rc;
-
 	rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_FORCE_TRX_OFF);
 	if (rc)
 		return rc;
 
+	irq_type = irq_get_trigger_type(lp->spi->irq);
 	/* configure irq polarity, defaults to high active */
-	if (pdata->irq_type & (IRQF_TRIGGER_FALLING | IRQF_TRIGGER_LOW))
+	if (irq_type & (IRQF_TRIGGER_FALLING | IRQF_TRIGGER_LOW))
 		irq_pol = IRQ_ACTIVE_LOW;
 	else
 		irq_pol = IRQ_ACTIVE_HIGH;
 
-	rc = at86rf230_irq_polarity(lp, irq_pol);
+	rc = at86rf230_write_subreg(lp, SR_IRQ_POLARITY, irq_pol);
 	if (rc)
 		return rc;
 
@@ -1017,10 +1006,10 @@ static int at86rf230_hw_init(struct at86rf230_local *lp)
 	/* Wait the next SLEEP cycle */
 	msleep(100);
 
-	rc = at86rf230_read_subreg(lp, SR_DVDD_OK, &status);
+	rc = at86rf230_read_subreg(lp, SR_DVDD_OK, &dvdd);
 	if (rc)
 		return rc;
-	if (!status) {
+	if (!dvdd) {
 		dev_err(&lp->spi->dev, "DVDD error\n");
 		return -EINVAL;
 	}
@@ -1032,7 +1021,6 @@ static struct at86rf230_platform_data *
 at86rf230_get_pdata(struct spi_device *spi)
 {
 	struct at86rf230_platform_data *pdata;
-	const char *irq_type;
 
 	if (!IS_ENABLED(CONFIG_OF) || !spi->dev.of_node)
 		return spi->dev.platform_data;
@@ -1044,19 +1032,6 @@ at86rf230_get_pdata(struct spi_device *spi)
 	pdata->rstn = of_get_named_gpio(spi->dev.of_node, "reset-gpio", 0);
 	pdata->slp_tr = of_get_named_gpio(spi->dev.of_node, "sleep-gpio", 0);
 
-	pdata->irq_type = IRQF_TRIGGER_RISING;
-	of_property_read_string(spi->dev.of_node, "irq-type", &irq_type);
-	if (!strcmp(irq_type, "level-high"))
-		pdata->irq_type = IRQF_TRIGGER_HIGH;
-	else if (!strcmp(irq_type, "level-low"))
-		pdata->irq_type = IRQF_TRIGGER_LOW;
-	else if (!strcmp(irq_type, "edge-rising"))
-		pdata->irq_type = IRQF_TRIGGER_RISING;
-	else if (!strcmp(irq_type, "edge-falling"))
-		pdata->irq_type = IRQF_TRIGGER_FALLING;
-	else
-		dev_warn(&spi->dev, "wrong irq-type specified using edge-rising\n");
-
 	spi->dev.platform_data = pdata;
 done:
 	return pdata;
@@ -1071,7 +1046,7 @@ static int at86rf230_probe(struct spi_device *spi)
 	u8 part = 0, version = 0, status;
 	irq_handler_t irq_handler;
 	work_func_t irq_worker;
-	int rc;
+	int rc, irq_type;
 	const char *chip;
 	struct ieee802154_ops *ops = NULL;
 
@@ -1087,27 +1062,17 @@ static int at86rf230_probe(struct spi_device *spi)
 	}
 
 	if (gpio_is_valid(pdata->rstn)) {
-		rc = gpio_request(pdata->rstn, "rstn");
+		rc = devm_gpio_request_one(&spi->dev, pdata->rstn,
+					   GPIOF_OUT_INIT_HIGH, "rstn");
 		if (rc)
 			return rc;
 	}
 
 	if (gpio_is_valid(pdata->slp_tr)) {
-		rc = gpio_request(pdata->slp_tr, "slp_tr");
-		if (rc)
-			goto err_slp_tr;
-	}
-
-	if (gpio_is_valid(pdata->rstn)) {
-		rc = gpio_direction_output(pdata->rstn, 1);
-		if (rc)
-			goto err_gpio_dir;
-	}
-
-	if (gpio_is_valid(pdata->slp_tr)) {
-		rc = gpio_direction_output(pdata->slp_tr, 0);
+		rc = devm_gpio_request_one(&spi->dev, pdata->slp_tr,
+					   GPIOF_OUT_INIT_LOW, "slp_tr");
 		if (rc)
-			goto err_gpio_dir;
+			return rc;
 	}
 
 	/* Reset */
@@ -1121,13 +1086,12 @@ static int at86rf230_probe(struct spi_device *spi)
 
 	rc = __at86rf230_detect_device(spi, &man_id, &part, &version);
 	if (rc < 0)
-		goto err_gpio_dir;
+		return rc;
 
 	if (man_id != 0x001f) {
 		dev_err(&spi->dev, "Non-Atmel dev found (MAN_ID %02x %02x)\n",
 			man_id >> 8, man_id & 0xFF);
-		rc = -EINVAL;
-		goto err_gpio_dir;
+		return -EINVAL;
 	}
 
 	switch (part) {
@@ -1154,16 +1118,12 @@ static int at86rf230_probe(struct spi_device *spi)
 	}
 
 	dev_info(&spi->dev, "Detected %s chip version %d\n", chip, version);
-	if (!ops) {
-		rc = -ENOTSUPP;
-		goto err_gpio_dir;
-	}
+	if (!ops)
+		return -ENOTSUPP;
 
 	dev = ieee802154_alloc_device(sizeof(*lp), ops);
-	if (!dev) {
-		rc = -ENOMEM;
-		goto err_gpio_dir;
-	}
+	if (!dev)
+		return -ENOMEM;
 
 	lp = dev->priv;
 	lp->dev = dev;
@@ -1176,7 +1136,10 @@ static int at86rf230_probe(struct spi_device *spi)
 	dev->extra_tx_headroom = 0;
 	dev->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK;
 
-	if (pdata->irq_type & (IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING)) {
+	irq_type = irq_get_trigger_type(spi->irq);
+	if (!irq_type)
+		irq_type = IRQF_TRIGGER_RISING;
+	if (irq_type & (IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING)) {
 		irq_worker = at86rf230_irqwork;
 		irq_handler = at86rf230_isr;
 	} else {
@@ -1202,75 +1165,66 @@ static int at86rf230_probe(struct spi_device *spi)
 	if (rc)
 		goto err_hw_init;
 
-	rc = request_irq(spi->irq, irq_handler,
-			 IRQF_SHARED | pdata->irq_type,
-			 dev_name(&spi->dev), lp);
+	/* Read irq status register to reset irq line */
+	rc = at86rf230_read_subreg(lp, RG_IRQ_STATUS, 0xff, 0, &status);
 	if (rc)
 		goto err_hw_init;
 
-	/* Read irq status register to reset irq line */
-	rc = at86rf230_read_subreg(lp, RG_IRQ_STATUS, 0xff, 0, &status);
+	rc = devm_request_irq(&spi->dev, spi->irq, irq_handler,
+			      IRQF_SHARED | irq_type,
+			      dev_name(&spi->dev), lp);
 	if (rc)
-		goto err_irq;
+		goto err_hw_init;
 
 	rc = ieee802154_register_device(lp->dev);
 	if (rc)
-		goto err_irq;
+		goto err_hw_init;
 
 	return rc;
 
-err_irq:
-	free_irq(spi->irq, lp);
 err_hw_init:
 	flush_work(&lp->irqwork);
-	spi_set_drvdata(spi, NULL);
 	mutex_destroy(&lp->bmux);
 	ieee802154_free_device(lp->dev);
 
-err_gpio_dir:
-	if (gpio_is_valid(pdata->slp_tr))
-		gpio_free(pdata->slp_tr);
-err_slp_tr:
-	if (gpio_is_valid(pdata->rstn))
-		gpio_free(pdata->rstn);
 	return rc;
 }
 
 static int at86rf230_remove(struct spi_device *spi)
 {
 	struct at86rf230_local *lp = spi_get_drvdata(spi);
-	struct at86rf230_platform_data *pdata = spi->dev.platform_data;
 
 	/* mask all at86rf230 irq's */
 	at86rf230_write_subreg(lp, SR_IRQ_MASK, 0);
 	ieee802154_unregister_device(lp->dev);
-
-	free_irq(spi->irq, lp);
 	flush_work(&lp->irqwork);
-
-	if (gpio_is_valid(pdata->slp_tr))
-		gpio_free(pdata->slp_tr);
-	if (gpio_is_valid(pdata->rstn))
-		gpio_free(pdata->rstn);
-
 	mutex_destroy(&lp->bmux);
 	ieee802154_free_device(lp->dev);
-
 	dev_dbg(&spi->dev, "unregistered at86rf230\n");
+
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_OF)
-static struct of_device_id at86rf230_of_match[] = {
+static const struct of_device_id at86rf230_of_match[] = {
 	{ .compatible = "atmel,at86rf230", },
 	{ .compatible = "atmel,at86rf231", },
 	{ .compatible = "atmel,at86rf233", },
 	{ .compatible = "atmel,at86rf212", },
 	{ },
 };
-#endif
+MODULE_DEVICE_TABLE(of, at86rf230_of_match);
+
+static const struct spi_device_id at86rf230_device_id[] = {
+	{ .name = "at86rf230", },
+	{ .name = "at86rf231", },
+	{ .name = "at86rf233", },
+	{ .name = "at86rf212", },
+	{ },
+};
+MODULE_DEVICE_TABLE(spi, at86rf230_device_id);
 
 static struct spi_driver at86rf230_driver = {
+	.id_table = at86rf230_device_id,
 	.driver = {
 		.of_match_table = of_match_ptr(at86rf230_of_match),
 		.name	= "at86rf230",
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index b8d22173925..27d83207d24 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -26,6 +26,7 @@
 #include <linux/timer.h>
 #include <linux/platform_device.h>
 #include <linux/netdevice.h>
+#include <linux/device.h>
 #include <linux/spinlock.h>
 #include <net/mac802154.h>
 #include <net/wpan-phy.h>
@@ -228,7 +229,8 @@ static int fakelb_probe(struct platform_device *pdev)
 	int err = -ENOMEM;
 	int i;
 
-	priv = kzalloc(sizeof(struct fakelb_priv), GFP_KERNEL);
+	priv = devm_kzalloc(&pdev->dev, sizeof(struct fakelb_priv),
+			    GFP_KERNEL);
 	if (!priv)
 		goto err_alloc;
 
@@ -248,7 +250,6 @@ static int fakelb_probe(struct platform_device *pdev)
 err_slave:
 	list_for_each_entry(dp, &priv->list, list)
 		fakelb_del(dp);
-	kfree(priv);
 err_alloc:
 	return err;
 }
@@ -260,7 +261,6 @@ static int fakelb_remove(struct platform_device *pdev)
 
 	list_for_each_entry_safe(dp, temp, &priv->list, list)
 		fakelb_del(dp);
-	kfree(priv);
 
 	return 0;
 }
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index 78a6552ed70..4048062011b 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -618,12 +618,12 @@ static int mrf24j40_probe(struct spi_device *spi)
 
 	printk(KERN_INFO "mrf24j40: probe(). IRQ: %d\n", spi->irq);
 
-	devrec = kzalloc(sizeof(struct mrf24j40), GFP_KERNEL);
+	devrec = devm_kzalloc(&spi->dev, sizeof(struct mrf24j40), GFP_KERNEL);
 	if (!devrec)
-		goto err_devrec;
-	devrec->buf = kzalloc(3, GFP_KERNEL);
+		goto err_ret;
+	devrec->buf = devm_kzalloc(&spi->dev, 3, GFP_KERNEL);
 	if (!devrec->buf)
-		goto err_buf;
+		goto err_ret;
 
 	spi->mode = SPI_MODE_0; /* TODO: Is this appropriate for right here? */
 	if (spi->max_speed_hz > MAX_SPI_SPEED_HZ)
@@ -638,7 +638,7 @@ static int mrf24j40_probe(struct spi_device *spi)
 
 	devrec->dev = ieee802154_alloc_device(0, &mrf24j40_ops);
 	if (!devrec->dev)
-		goto err_alloc_dev;
+		goto err_ret;
 
 	devrec->dev->priv = devrec;
 	devrec->dev->parent = &devrec->spi->dev;
@@ -676,12 +676,13 @@ static int mrf24j40_probe(struct spi_device *spi)
 	val &= ~0x3; /* Clear RX mode (normal) */
 	write_short_reg(devrec, REG_RXMCR, val);
 
-	ret = request_threaded_irq(spi->irq,
-				   NULL,
-				   mrf24j40_isr,
-				   IRQF_TRIGGER_LOW|IRQF_ONESHOT,
-				   dev_name(&spi->dev),
-				   devrec);
+	ret = devm_request_threaded_irq(&spi->dev,
+					spi->irq,
+					NULL,
+					mrf24j40_isr,
+					IRQF_TRIGGER_LOW|IRQF_ONESHOT,
+					dev_name(&spi->dev),
+					devrec);
 
 	if (ret) {
 		dev_err(printdev(devrec), "Unable to get IRQ");
@@ -695,11 +696,7 @@ err_read_reg:
 	ieee802154_unregister_device(devrec->dev);
 err_register_device:
 	ieee802154_free_device(devrec->dev);
-err_alloc_dev:
-	kfree(devrec->buf);
-err_buf:
-	kfree(devrec);
-err_devrec:
+err_ret:
 	return ret;
 }
 
@@ -709,15 +706,11 @@ static int mrf24j40_remove(struct spi_device *spi)
 
 	dev_dbg(printdev(devrec), "remove\n");
 
-	free_irq(spi->irq, devrec);
 	ieee802154_unregister_device(devrec->dev);
 	ieee802154_free_device(devrec->dev);
 	/* TODO: Will ieee802154_free_device() wait until ->xmit() is
 	 * complete? */
 
-	/* Clean up the SPI stuff. */
-	kfree(devrec->buf);
-	kfree(devrec);
 	return 0;
 }
 
diff --git a/drivers/net/irda/Kconfig b/drivers/net/irda/Kconfig
index 3da44d5d914..8d101d63abc 100644
--- a/drivers/net/irda/Kconfig
+++ b/drivers/net/irda/Kconfig
@@ -396,7 +396,8 @@ config MCS_FIR
 
 config SH_IRDA
 	tristate "SuperH IrDA driver"
-	depends on IRDA && ARCH_SHMOBILE
+	depends on IRDA
+	depends on ARCH_SHMOBILE || COMPILE_TEST
 	help
 	  Say Y here if your want to enable SuperH IrDA devices.
 
diff --git a/drivers/net/irda/via-ircc.c b/drivers/net/irda/via-ircc.c
index 2900af091c2..998bb89ede7 100644
--- a/drivers/net/irda/via-ircc.c
+++ b/drivers/net/irda/via-ircc.c
@@ -510,10 +510,8 @@ static void via_hw_init(struct via_ircc_cb *self)
  */
 static int via_ircc_read_dongle_id(int iobase)
 {
-	int dongle_id = 9;	/* Default to IBM */
-
 	IRDA_ERROR("via-ircc: dongle probing not supported, please specify dongle_id module parameter.\n");
-	return dongle_id;
+	return 9;	/* Default to IBM */
 }
 
 /*
@@ -926,7 +924,6 @@ static int via_ircc_dma_xmit(struct via_ircc_cb *self, u16 iobase)
 static int via_ircc_dma_xmit_complete(struct via_ircc_cb *self)
 {
 	int iobase;
-	int ret = TRUE;
 	u8 Tx_status;
 
 	IRDA_DEBUG(3, "%s()\n", __func__);
@@ -983,7 +980,7 @@ F01_E*/
 	// Tell the network layer, that we can accept more frames 
 	netif_wake_queue(self->netdev);
 //F01   }
-	return ret;
+	return TRUE;
 }
 
 /*
diff --git a/drivers/net/irda/w83977af_ir.c b/drivers/net/irda/w83977af_ir.c
index e641bb24036..11dbdf36d9c 100644
--- a/drivers/net/irda/w83977af_ir.c
+++ b/drivers/net/irda/w83977af_ir.c
@@ -62,10 +62,6 @@
 #include "w83977af.h"
 #include "w83977af_ir.h"
 
-#ifdef  CONFIG_ARCH_NETWINDER            /* Adjust to NetWinder differences */
-#undef  CONFIG_NETWINDER_TX_DMA_PROBLEMS /* Not needed */
-#define CONFIG_NETWINDER_RX_DMA_PROBLEMS /* Must have this one! */
-#endif
 #define CONFIG_USE_W977_PNP        /* Currently needed */
 #define PIO_MAX_SPEED       115200 
 
@@ -332,7 +328,7 @@ static int w83977af_probe(int iobase, int irq, int dma)
  		w977_write_reg(0x74, dma+1, efbase[i]);
 #else
  		w977_write_reg(0x74, dma, efbase[i]);   
-#endif /*CONFIG_ARCH_NETWINDER */
+#endif /* CONFIG_ARCH_NETWINDER */
  		w977_write_reg(0x75, 0x04, efbase[i]);  /* Disable Tx DMA */
   	
  		/* Set append hardware CRC, enable IR bank selection */	
@@ -563,10 +559,6 @@ static netdev_tx_t w83977af_hard_xmit(struct sk_buff *skb,
 static void w83977af_dma_write(struct w83977af_ir *self, int iobase)
 {
 	__u8 set;
-#ifdef CONFIG_NETWINDER_TX_DMA_PROBLEMS
-	unsigned long flags;
-	__u8 hcr;
-#endif
         IRDA_DEBUG(4, "%s(), len=%d\n", __func__ , self->tx_buff.len);
 
 	/* Save current set */
@@ -579,30 +571,13 @@ static void w83977af_dma_write(struct w83977af_ir *self, int iobase)
 	/* Choose transmit DMA channel  */ 
 	switch_bank(iobase, SET2);
 	outb(ADCR1_D_CHSW|/*ADCR1_DMA_F|*/ADCR1_ADV_SL, iobase+ADCR1);
-#ifdef CONFIG_NETWINDER_TX_DMA_PROBLEMS
-	spin_lock_irqsave(&self->lock, flags);
-
-	disable_dma(self->io.dma);
-	clear_dma_ff(self->io.dma);
-	set_dma_mode(self->io.dma, DMA_MODE_READ);
-	set_dma_addr(self->io.dma, self->tx_buff_dma);
-	set_dma_count(self->io.dma, self->tx_buff.len);
-#else
 	irda_setup_dma(self->io.dma, self->tx_buff_dma, self->tx_buff.len,
 		       DMA_MODE_WRITE);	
-#endif
 	self->io.direction = IO_XMIT;
 	
 	/* Enable DMA */
  	switch_bank(iobase, SET0);
-#ifdef CONFIG_NETWINDER_TX_DMA_PROBLEMS
-	hcr = inb(iobase+HCR);
-	outb(hcr | HCR_EN_DMA, iobase+HCR);
-	enable_dma(self->io.dma);
-	spin_unlock_irqrestore(&self->lock, flags);
-#else	
 	outb(inb(iobase+HCR) | HCR_EN_DMA | HCR_TX_WT, iobase+HCR);
-#endif
 
 	/* Restore set register */
 	outb(set, iobase+SSR);
@@ -711,7 +686,7 @@ static int w83977af_dma_receive(struct w83977af_ir *self)
 {
 	int iobase;
 	__u8 set;
-#ifdef CONFIG_NETWINDER_RX_DMA_PROBLEMS
+#ifdef CONFIG_ARCH_NETWINDER
 	unsigned long flags;
 	__u8 hcr;
 #endif
@@ -736,7 +711,7 @@ static int w83977af_dma_receive(struct w83977af_ir *self)
 	self->io.direction = IO_RECV;
 	self->rx_buff.data = self->rx_buff.head;
 
-#ifdef CONFIG_NETWINDER_RX_DMA_PROBLEMS
+#ifdef CONFIG_ARCH_NETWINDER
 	spin_lock_irqsave(&self->lock, flags);
 
 	disable_dma(self->io.dma);
@@ -759,7 +734,7 @@ static int w83977af_dma_receive(struct w83977af_ir *self)
 	
 	/* Enable DMA */
 	switch_bank(iobase, SET0);
-#ifdef CONFIG_NETWINDER_RX_DMA_PROBLEMS
+#ifdef CONFIG_ARCH_NETWINDER
 	hcr = inb(iobase+HCR);
 	outb(hcr | HCR_EN_DMA, iobase+HCR);
 	enable_dma(self->io.dma);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index d53e299ae1d..958df383068 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -30,8 +30,10 @@
 #include <linux/if_link.h>
 #include <linux/if_macvlan.h>
 #include <linux/hash.h>
+#include <linux/workqueue.h>
 #include <net/rtnetlink.h>
 #include <net/xfrm.h>
+#include <linux/netpoll.h>
 
 #define MACVLAN_HASH_SIZE	(1 << BITS_PER_BYTE)
 
@@ -40,10 +42,19 @@ struct macvlan_port {
 	struct hlist_head	vlan_hash[MACVLAN_HASH_SIZE];
 	struct list_head	vlans;
 	struct rcu_head		rcu;
+	struct sk_buff_head	bc_queue;
+	struct work_struct	bc_work;
 	bool 			passthru;
-	int			count;
 };
 
+#define MACVLAN_PORT_IS_EMPTY(port)    list_empty(&port->vlans)
+
+struct macvlan_skb_cb {
+	const struct macvlan_dev *src;
+};
+
+#define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0]))
+
 static void macvlan_port_destroy(struct net_device *dev);
 
 static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev)
@@ -120,7 +131,7 @@ static int macvlan_broadcast_one(struct sk_buff *skb,
 	struct net_device *dev = vlan->dev;
 
 	if (local)
-		return dev_forward_skb(dev, skb);
+		return __dev_forward_skb(dev, skb);
 
 	skb->dev = dev;
 	if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
@@ -128,7 +139,7 @@ static int macvlan_broadcast_one(struct sk_buff *skb,
 	else
 		skb->pkt_type = PACKET_MULTICAST;
 
-	return netif_rx(skb);
+	return 0;
 }
 
 static u32 macvlan_hash_mix(const struct macvlan_dev *vlan)
@@ -175,32 +186,32 @@ static void macvlan_broadcast(struct sk_buff *skb,
 			if (likely(nskb))
 				err = macvlan_broadcast_one(
 					nskb, vlan, eth,
-					mode == MACVLAN_MODE_BRIDGE);
+					mode == MACVLAN_MODE_BRIDGE) ?:
+				      netif_rx_ni(nskb);
 			macvlan_count_rx(vlan, skb->len + ETH_HLEN,
 					 err == NET_RX_SUCCESS, 1);
 		}
 	}
 }
 
-/* called under rcu_read_lock() from netif_receive_skb */
-static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
+static void macvlan_process_broadcast(struct work_struct *w)
 {
-	struct macvlan_port *port;
-	struct sk_buff *skb = *pskb;
-	const struct ethhdr *eth = eth_hdr(skb);
-	const struct macvlan_dev *vlan;
-	const struct macvlan_dev *src;
-	struct net_device *dev;
-	unsigned int len = 0;
-	int ret = NET_RX_DROP;
+	struct macvlan_port *port = container_of(w, struct macvlan_port,
+						 bc_work);
+	struct sk_buff *skb;
+	struct sk_buff_head list;
+
+	skb_queue_head_init(&list);
+
+	spin_lock_bh(&port->bc_queue.lock);
+	skb_queue_splice_tail_init(&port->bc_queue, &list);
+	spin_unlock_bh(&port->bc_queue.lock);
+
+	while ((skb = __skb_dequeue(&list))) {
+		const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src;
+
+		rcu_read_lock();
 
-	port = macvlan_port_get_rcu(skb->dev);
-	if (is_multicast_ether_addr(eth->h_dest)) {
-		skb = ip_check_defrag(skb, IP_DEFRAG_MACVLAN);
-		if (!skb)
-			return RX_HANDLER_CONSUMED;
-		eth = eth_hdr(skb);
-		src = macvlan_hash_lookup(port, eth->h_source);
 		if (!src)
 			/* frame comes from an external address */
 			macvlan_broadcast(skb, port, NULL,
@@ -213,20 +224,80 @@ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
 			macvlan_broadcast(skb, port, src->dev,
 					  MACVLAN_MODE_VEPA |
 					  MACVLAN_MODE_BRIDGE);
-		else if (src->mode == MACVLAN_MODE_BRIDGE)
+		else
 			/*
 			 * flood only to VEPA ports, bridge ports
 			 * already saw the frame on the way out.
 			 */
 			macvlan_broadcast(skb, port, src->dev,
 					  MACVLAN_MODE_VEPA);
-		else {
+
+		rcu_read_unlock();
+
+		kfree_skb(skb);
+	}
+}
+
+static void macvlan_broadcast_enqueue(struct macvlan_port *port,
+				      struct sk_buff *skb)
+{
+	struct sk_buff *nskb;
+	int err = -ENOMEM;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		goto err;
+
+	spin_lock(&port->bc_queue.lock);
+	if (skb_queue_len(&port->bc_queue) < skb->dev->tx_queue_len) {
+		__skb_queue_tail(&port->bc_queue, nskb);
+		err = 0;
+	}
+	spin_unlock(&port->bc_queue.lock);
+
+	if (err)
+		goto free_nskb;
+
+	schedule_work(&port->bc_work);
+	return;
+
+free_nskb:
+	kfree_skb(nskb);
+err:
+	atomic_long_inc(&skb->dev->rx_dropped);
+}
+
+/* called under rcu_read_lock() from netif_receive_skb */
+static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb)
+{
+	struct macvlan_port *port;
+	struct sk_buff *skb = *pskb;
+	const struct ethhdr *eth = eth_hdr(skb);
+	const struct macvlan_dev *vlan;
+	const struct macvlan_dev *src;
+	struct net_device *dev;
+	unsigned int len = 0;
+	int ret = NET_RX_DROP;
+
+	port = macvlan_port_get_rcu(skb->dev);
+	if (is_multicast_ether_addr(eth->h_dest)) {
+		skb = ip_check_defrag(skb, IP_DEFRAG_MACVLAN);
+		if (!skb)
+			return RX_HANDLER_CONSUMED;
+		eth = eth_hdr(skb);
+		src = macvlan_hash_lookup(port, eth->h_source);
+		if (src && src->mode != MACVLAN_MODE_VEPA &&
+		    src->mode != MACVLAN_MODE_BRIDGE) {
 			/* forward to original port. */
 			vlan = src;
-			ret = macvlan_broadcast_one(skb, vlan, eth, 0);
+			ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?:
+			      netif_rx(skb);
 			goto out;
 		}
 
+		MACVLAN_SKB_CB(skb)->src = src;
+		macvlan_broadcast_enqueue(port, skb);
+
 		return RX_HANDLER_PASS;
 	}
 
@@ -287,12 +358,26 @@ xmit_world:
 	return dev_queue_xmit(skb);
 }
 
+static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	if (vlan->netpoll)
+		netpoll_send_skb(vlan->netpoll, skb);
+#else
+	BUG();
+#endif
+	return NETDEV_TX_OK;
+}
+
 static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
 				      struct net_device *dev)
 {
 	unsigned int len = skb->len;
 	int ret;
-	const struct macvlan_dev *vlan = netdev_priv(dev);
+	struct macvlan_dev *vlan = netdev_priv(dev);
+
+	if (unlikely(netpoll_tx_running(dev)))
+		return macvlan_netpoll_send_skb(vlan, skb);
 
 	if (vlan->fwd_priv) {
 		skb->dev = vlan->lowerdev;
@@ -424,35 +509,49 @@ hash_del:
 	return 0;
 }
 
-static int macvlan_set_mac_address(struct net_device *dev, void *p)
+static int macvlan_sync_address(struct net_device *dev, unsigned char *addr)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct net_device *lowerdev = vlan->lowerdev;
-	struct sockaddr *addr = p;
 	int err;
 
-	if (!is_valid_ether_addr(addr->sa_data))
-		return -EADDRNOTAVAIL;
-
 	if (!(dev->flags & IFF_UP)) {
 		/* Just copy in the new address */
-		memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+		ether_addr_copy(dev->dev_addr, addr);
 	} else {
 		/* Rehash and update the device filters */
-		if (macvlan_addr_busy(vlan->port, addr->sa_data))
+		if (macvlan_addr_busy(vlan->port, addr))
 			return -EBUSY;
 
-		err = dev_uc_add(lowerdev, addr->sa_data);
-		if (err)
-			return err;
+		if (!vlan->port->passthru) {
+			err = dev_uc_add(lowerdev, addr);
+			if (err)
+				return err;
 
-		dev_uc_del(lowerdev, dev->dev_addr);
+			dev_uc_del(lowerdev, dev->dev_addr);
+		}
 
-		macvlan_hash_change_addr(vlan, addr->sa_data);
+		macvlan_hash_change_addr(vlan, addr);
 	}
 	return 0;
 }
 
+static int macvlan_set_mac_address(struct net_device *dev, void *p)
+{
+	struct macvlan_dev *vlan = netdev_priv(dev);
+	struct sockaddr *addr = p;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
+		dev_set_mac_address(vlan->lowerdev, addr);
+		return 0;
+	}
+
+	return macvlan_sync_address(dev, addr->sa_data);
+}
+
 static void macvlan_change_rx_flags(struct net_device *dev, int change)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
@@ -567,8 +666,7 @@ static void macvlan_uninit(struct net_device *dev)
 
 	free_percpu(vlan->pcpu_stats);
 
-	port->count -= 1;
-	if (!port->count)
+	if (MACVLAN_PORT_IS_EMPTY(port))
 		macvlan_port_destroy(port->dev);
 }
 
@@ -705,6 +803,50 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev,
 	return features;
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void macvlan_dev_poll_controller(struct net_device *dev)
+{
+	return;
+}
+
+static int macvlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
+{
+	struct macvlan_dev *vlan = netdev_priv(dev);
+	struct net_device *real_dev = vlan->lowerdev;
+	struct netpoll *netpoll;
+	int err = 0;
+
+	netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
+	err = -ENOMEM;
+	if (!netpoll)
+		goto out;
+
+	err = __netpoll_setup(netpoll, real_dev);
+	if (err) {
+		kfree(netpoll);
+		goto out;
+	}
+
+	vlan->netpoll = netpoll;
+
+out:
+	return err;
+}
+
+static void macvlan_dev_netpoll_cleanup(struct net_device *dev)
+{
+	struct macvlan_dev *vlan = netdev_priv(dev);
+	struct netpoll *netpoll = vlan->netpoll;
+
+	if (!netpoll)
+		return;
+
+	vlan->netpoll = NULL;
+
+	__netpoll_free_async(netpoll);
+}
+#endif	/* CONFIG_NET_POLL_CONTROLLER */
+
 static const struct ethtool_ops macvlan_ethtool_ops = {
 	.get_link		= ethtool_op_get_link,
 	.get_settings		= macvlan_ethtool_get_settings,
@@ -730,6 +872,11 @@ static const struct net_device_ops macvlan_netdev_ops = {
 	.ndo_fdb_del		= macvlan_fdb_del,
 	.ndo_fdb_dump		= ndo_dflt_fdb_dump,
 	.ndo_get_lock_subclass  = macvlan_get_nest_level,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= macvlan_dev_poll_controller,
+	.ndo_netpoll_setup	= macvlan_dev_netpoll_setup,
+	.ndo_netpoll_cleanup	= macvlan_dev_netpoll_cleanup,
+#endif
 };
 
 void macvlan_common_setup(struct net_device *dev)
@@ -770,6 +917,9 @@ static int macvlan_port_create(struct net_device *dev)
 	for (i = 0; i < MACVLAN_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&port->vlan_hash[i]);
 
+	skb_queue_head_init(&port->bc_queue);
+	INIT_WORK(&port->bc_work, macvlan_process_broadcast);
+
 	err = netdev_rx_handler_register(dev, macvlan_handle_frame, port);
 	if (err)
 		kfree(port);
@@ -782,6 +932,7 @@ static void macvlan_port_destroy(struct net_device *dev)
 {
 	struct macvlan_port *port = macvlan_port_get_rtnl(dev);
 
+	cancel_work_sync(&port->bc_work);
 	dev->priv_flags &= ~IFF_MACVLAN_PORT;
 	netdev_rx_handler_unregister(dev);
 	kfree_rcu(port, rcu);
@@ -868,13 +1019,12 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 		vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]);
 
 	if (vlan->mode == MACVLAN_MODE_PASSTHRU) {
-		if (port->count)
+		if (!MACVLAN_PORT_IS_EMPTY(port))
 			return -EINVAL;
 		port->passthru = true;
 		eth_hw_addr_inherit(dev, lowerdev);
 	}
 
-	port->count += 1;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto destroy_port;
@@ -892,8 +1042,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 unregister_netdev:
 	unregister_netdevice(dev);
 destroy_port:
-	port->count -= 1;
-	if (!port->count)
+	if (MACVLAN_PORT_IS_EMPTY(port))
 		macvlan_port_destroy(lowerdev);
 
 	return err;
@@ -1028,6 +1177,25 @@ static int macvlan_device_event(struct notifier_block *unused,
 			netdev_update_features(vlan->dev);
 		}
 		break;
+	case NETDEV_CHANGEMTU:
+		list_for_each_entry(vlan, &port->vlans, list) {
+			if (vlan->dev->mtu <= dev->mtu)
+				continue;
+			dev_set_mtu(vlan->dev, dev->mtu);
+		}
+		break;
+	case NETDEV_CHANGEADDR:
+		if (!port->passthru)
+			return NOTIFY_DONE;
+
+		vlan = list_first_entry_or_null(&port->vlans,
+						struct macvlan_dev,
+						list);
+
+		if (macvlan_sync_address(vlan->dev, dev->dev_addr))
+			return NOTIFY_BAD;
+
+		break;
 	case NETDEV_UNREGISTER:
 		/* twiddle thumbs on netns device moves */
 		if (dev->reg_state != NETREG_UNREGISTERING)
@@ -1036,11 +1204,17 @@ static int macvlan_device_event(struct notifier_block *unused,
 		list_for_each_entry_safe(vlan, next, &port->vlans, list)
 			vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill);
 		unregister_netdevice_many(&list_kill);
-		list_del(&list_kill);
 		break;
 	case NETDEV_PRE_TYPE_CHANGE:
 		/* Forbid underlaying device to change its type. */
 		return NOTIFY_BAD;
+
+	case NETDEV_NOTIFY_PEERS:
+	case NETDEV_BONDING_FAILOVER:
+	case NETDEV_RESEND_IGMP:
+		/* Propagate to all vlans */
+		list_for_each_entry(vlan, &port->vlans, list)
+			call_netdevice_notifiers(event, vlan->dev);
 	}
 	return NOTIFY_DONE;
 }
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 63aa9d9e34c..5a7e6397440 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -298,7 +298,6 @@ static int ntb_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 {
 	cmd->supported = SUPPORTED_Backplane;
 	cmd->advertising = ADVERTISED_Backplane;
-	cmd->speed = SPEED_UNKNOWN;
 	ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN);
 	cmd->duplex = DUPLEX_FULL;
 	cmd->port = PORT_OTHER;
@@ -348,7 +347,7 @@ static int ntb_netdev_probe(struct pci_dev *pdev)
 	memcpy(ndev->dev_addr, ndev->perm_addr, ndev->addr_len);
 
 	ndev->netdev_ops = &ntb_netdev_ops;
-	SET_ETHTOOL_OPS(ndev, &ntb_ethtool_ops);
+	ndev->ethtool_ops = &ntb_ethtool_ops;
 
 	dev->qp = ntb_transport_create_queue(ndev, pdev, &ntb_netdev_handlers);
 	if (!dev->qp) {
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 6a17f92153b..65de0cab8d0 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -24,6 +24,12 @@ config AMD_PHY
 	---help---
 	  Currently supports the am79c874
 
+config AMD_XGBE_PHY
+	tristate "Driver for the AMD 10GbE (amd-xgbe) PHYs"
+	depends on OF
+	---help---
+	  Currently supports the AMD 10GbE PHY
+
 config MARVELL_PHY
 	tristate "Drivers for Marvell PHYs"
 	---help---
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 07d24024863..7dc3d5b304c 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -33,3 +33,4 @@ obj-$(CONFIG_MDIO_BUS_MUX_GPIO)	+= mdio-mux-gpio.o
 obj-$(CONFIG_MDIO_BUS_MUX_MMIOREG) += mdio-mux-mmioreg.o
 obj-$(CONFIG_MDIO_SUN4I)	+= mdio-sun4i.o
 obj-$(CONFIG_MDIO_MOXART)	+= mdio-moxart.o
+obj-$(CONFIG_AMD_XGBE_PHY)	+= amd-xgbe-phy.o
diff --git a/drivers/net/phy/amd-xgbe-phy.c b/drivers/net/phy/amd-xgbe-phy.c
new file mode 100644
index 00000000000..b57c2244286
--- /dev/null
+++ b/drivers/net/phy/amd-xgbe-phy.c
@@ -0,0 +1,1357 @@
+/*
+ * AMD 10Gb Ethernet PHY driver
+ *
+ * This file is available to you under your choice of the following two
+ * licenses:
+ *
+ * License 1: GPLv2
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ *
+ * This file is free software; you may copy, redistribute and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ *
+ * License 2: Modified BSD
+ *
+ * Copyright (c) 2014 Advanced Micro Devices, Inc.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Advanced Micro Devices, Inc. nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL <COPYRIGHT HOLDER> BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+ * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/mii.h>
+#include <linux/ethtool.h>
+#include <linux/phy.h>
+#include <linux/mdio.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/of_device.h>
+#include <linux/uaccess.h>
+#include <asm/irq.h>
+
+
+MODULE_AUTHOR("Tom Lendacky <thomas.lendacky@amd.com>");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION("1.0.0-a");
+MODULE_DESCRIPTION("AMD 10GbE (amd-xgbe) PHY driver");
+
+#define XGBE_PHY_ID	0x000162d0
+#define XGBE_PHY_MASK	0xfffffff0
+
+#define XGBE_AN_INT_CMPLT		0x01
+#define XGBE_AN_INC_LINK		0x02
+#define XGBE_AN_PG_RCV			0x04
+
+#define XNP_MCF_NULL_MESSAGE		0x001
+#define XNP_ACK_PROCESSED		(1 << 12)
+#define XNP_MP_FORMATTED		(1 << 13)
+#define XNP_NP_EXCHANGE			(1 << 15)
+
+#ifndef MDIO_PMA_10GBR_PMD_CTRL
+#define MDIO_PMA_10GBR_PMD_CTRL		0x0096
+#endif
+#ifndef MDIO_PMA_10GBR_FEC_CTRL
+#define MDIO_PMA_10GBR_FEC_CTRL		0x00ab
+#endif
+#ifndef MDIO_AN_XNP
+#define MDIO_AN_XNP			0x0016
+#endif
+
+#ifndef MDIO_AN_INTMASK
+#define MDIO_AN_INTMASK			0x8001
+#endif
+#ifndef MDIO_AN_INT
+#define MDIO_AN_INT			0x8002
+#endif
+
+#ifndef MDIO_CTRL1_SPEED1G
+#define MDIO_CTRL1_SPEED1G		(MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100)
+#endif
+
+/* SerDes integration register offsets */
+#define SIR0_STATUS			0x0040
+#define SIR1_SPEED			0x0000
+
+/* SerDes integration register entry bit positions and sizes */
+#define SIR0_STATUS_RX_READY_INDEX	0
+#define SIR0_STATUS_RX_READY_WIDTH	1
+#define SIR0_STATUS_TX_READY_INDEX	8
+#define SIR0_STATUS_TX_READY_WIDTH	1
+#define SIR1_SPEED_DATARATE_INDEX	4
+#define SIR1_SPEED_DATARATE_WIDTH	2
+#define SIR1_SPEED_PI_SPD_SEL_INDEX	12
+#define SIR1_SPEED_PI_SPD_SEL_WIDTH	4
+#define SIR1_SPEED_PLLSEL_INDEX		3
+#define SIR1_SPEED_PLLSEL_WIDTH		1
+#define SIR1_SPEED_RATECHANGE_INDEX	6
+#define SIR1_SPEED_RATECHANGE_WIDTH	1
+#define SIR1_SPEED_TXAMP_INDEX		8
+#define SIR1_SPEED_TXAMP_WIDTH		4
+#define SIR1_SPEED_WORDMODE_INDEX	0
+#define SIR1_SPEED_WORDMODE_WIDTH	3
+
+#define SPEED_10000_CDR			0x7
+#define SPEED_10000_PLL			0x1
+#define SPEED_10000_RATE		0x0
+#define SPEED_10000_TXAMP		0xa
+#define SPEED_10000_WORD		0x7
+
+#define SPEED_2500_CDR			0x2
+#define SPEED_2500_PLL			0x0
+#define SPEED_2500_RATE			0x2
+#define SPEED_2500_TXAMP		0xf
+#define SPEED_2500_WORD			0x1
+
+#define SPEED_1000_CDR			0x2
+#define SPEED_1000_PLL			0x0
+#define SPEED_1000_RATE			0x3
+#define SPEED_1000_TXAMP		0xf
+#define SPEED_1000_WORD			0x1
+
+
+/* SerDes RxTx register offsets */
+#define RXTX_REG20			0x0050
+#define RXTX_REG114			0x01c8
+
+/* SerDes RxTx register entry bit positions and sizes */
+#define RXTX_REG20_BLWC_ENA_INDEX	2
+#define RXTX_REG20_BLWC_ENA_WIDTH	1
+#define RXTX_REG114_PQ_REG_INDEX	9
+#define RXTX_REG114_PQ_REG_WIDTH	7
+
+#define RXTX_10000_BLWC			0
+#define RXTX_10000_PQ			0x1e
+
+#define RXTX_2500_BLWC			1
+#define RXTX_2500_PQ			0xa
+
+#define RXTX_1000_BLWC			1
+#define RXTX_1000_PQ			0xa
+
+/* Bit setting and getting macros
+ *  The get macro will extract the current bit field value from within
+ *  the variable
+ *
+ *  The set macro will clear the current bit field value within the
+ *  variable and then set the bit field of the variable to the
+ *  specified value
+ */
+#define GET_BITS(_var, _index, _width)					\
+	(((_var) >> (_index)) & ((0x1 << (_width)) - 1))
+
+#define SET_BITS(_var, _index, _width, _val)				\
+do {									\
+	(_var) &= ~(((0x1 << (_width)) - 1) << (_index));		\
+	(_var) |= (((_val) & ((0x1 << (_width)) - 1)) << (_index));	\
+} while (0)
+
+/* Macros for reading or writing SerDes integration registers
+ *  The ioread macros will get bit fields or full values using the
+ *  register definitions formed using the input names
+ *
+ *  The iowrite macros will set bit fields or full values using the
+ *  register definitions formed using the input names
+ */
+#define XSIR0_IOREAD(_priv, _reg)					\
+	ioread16((_priv)->sir0_regs + _reg)
+
+#define XSIR0_IOREAD_BITS(_priv, _reg, _field)				\
+	GET_BITS(XSIR0_IOREAD((_priv), _reg),				\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH)
+
+#define XSIR0_IOWRITE(_priv, _reg, _val)				\
+	iowrite16((_val), (_priv)->sir0_regs + _reg)
+
+#define XSIR0_IOWRITE_BITS(_priv, _reg, _field, _val)			\
+do {									\
+	u16 reg_val = XSIR0_IOREAD((_priv), _reg);			\
+	SET_BITS(reg_val,						\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH, (_val));			\
+	XSIR0_IOWRITE((_priv), _reg, reg_val);				\
+} while (0)
+
+#define XSIR1_IOREAD(_priv, _reg)					\
+	ioread16((_priv)->sir1_regs + _reg)
+
+#define XSIR1_IOREAD_BITS(_priv, _reg, _field)				\
+	GET_BITS(XSIR1_IOREAD((_priv), _reg),				\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH)
+
+#define XSIR1_IOWRITE(_priv, _reg, _val)				\
+	iowrite16((_val), (_priv)->sir1_regs + _reg)
+
+#define XSIR1_IOWRITE_BITS(_priv, _reg, _field, _val)			\
+do {									\
+	u16 reg_val = XSIR1_IOREAD((_priv), _reg);			\
+	SET_BITS(reg_val,						\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH, (_val));			\
+	XSIR1_IOWRITE((_priv), _reg, reg_val);				\
+} while (0)
+
+
+/* Macros for reading or writing SerDes RxTx registers
+ *  The ioread macros will get bit fields or full values using the
+ *  register definitions formed using the input names
+ *
+ *  The iowrite macros will set bit fields or full values using the
+ *  register definitions formed using the input names
+ */
+#define XRXTX_IOREAD(_priv, _reg)					\
+	ioread16((_priv)->rxtx_regs + _reg)
+
+#define XRXTX_IOREAD_BITS(_priv, _reg, _field)				\
+	GET_BITS(XRXTX_IOREAD((_priv), _reg),				\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH)
+
+#define XRXTX_IOWRITE(_priv, _reg, _val)				\
+	iowrite16((_val), (_priv)->rxtx_regs + _reg)
+
+#define XRXTX_IOWRITE_BITS(_priv, _reg, _field, _val)			\
+do {									\
+	u16 reg_val = XRXTX_IOREAD((_priv), _reg);			\
+	SET_BITS(reg_val,						\
+		 _reg##_##_field##_INDEX,				\
+		 _reg##_##_field##_WIDTH, (_val));			\
+	XRXTX_IOWRITE((_priv), _reg, reg_val);				\
+} while (0)
+
+
+enum amd_xgbe_phy_an {
+	AMD_XGBE_AN_READY = 0,
+	AMD_XGBE_AN_START,
+	AMD_XGBE_AN_EVENT,
+	AMD_XGBE_AN_PAGE_RECEIVED,
+	AMD_XGBE_AN_INCOMPAT_LINK,
+	AMD_XGBE_AN_COMPLETE,
+	AMD_XGBE_AN_NO_LINK,
+	AMD_XGBE_AN_EXIT,
+	AMD_XGBE_AN_ERROR,
+};
+
+enum amd_xgbe_phy_rx {
+	AMD_XGBE_RX_READY = 0,
+	AMD_XGBE_RX_BPA,
+	AMD_XGBE_RX_XNP,
+	AMD_XGBE_RX_COMPLETE,
+};
+
+enum amd_xgbe_phy_mode {
+	AMD_XGBE_MODE_KR,
+	AMD_XGBE_MODE_KX,
+};
+
+struct amd_xgbe_phy_priv {
+	struct platform_device *pdev;
+	struct device *dev;
+
+	struct phy_device *phydev;
+
+	/* SerDes related mmio resources */
+	struct resource *rxtx_res;
+	struct resource *sir0_res;
+	struct resource *sir1_res;
+
+	/* SerDes related mmio registers */
+	void __iomem *rxtx_regs;	/* SerDes Rx/Tx CSRs */
+	void __iomem *sir0_regs;	/* SerDes integration registers (1/2) */
+	void __iomem *sir1_regs;	/* SerDes integration registers (2/2) */
+
+	/* Maintain link status for re-starting auto-negotiation */
+	unsigned int link;
+	enum amd_xgbe_phy_mode mode;
+
+	/* Auto-negotiation state machine support */
+	struct mutex an_mutex;
+	enum amd_xgbe_phy_an an_result;
+	enum amd_xgbe_phy_an an_state;
+	enum amd_xgbe_phy_rx kr_state;
+	enum amd_xgbe_phy_rx kx_state;
+	struct work_struct an_work;
+	struct workqueue_struct *an_workqueue;
+};
+
+static int amd_xgbe_an_enable_kr_training(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
+	if (ret < 0)
+		return ret;
+
+	ret |= 0x02;
+	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, ret);
+
+	return 0;
+}
+
+static int amd_xgbe_an_disable_kr_training(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~0x02;
+	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, ret);
+
+	return 0;
+}
+
+static int amd_xgbe_phy_pcs_power_cycle(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret |= MDIO_CTRL1_LPOWER;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
+
+	usleep_range(75, 100);
+
+	ret &= ~MDIO_CTRL1_LPOWER;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
+
+	return 0;
+}
+
+static void amd_xgbe_phy_serdes_start_ratechange(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+
+	/* Assert Rx and Tx ratechange */
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, RATECHANGE, 1);
+}
+
+static void amd_xgbe_phy_serdes_complete_ratechange(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+
+	/* Release Rx and Tx ratechange */
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, RATECHANGE, 0);
+
+	/* Wait for Rx and Tx ready */
+	while (!XSIR0_IOREAD_BITS(priv, SIR0_STATUS, RX_READY) &&
+	       !XSIR0_IOREAD_BITS(priv, SIR0_STATUS, TX_READY))
+		usleep_range(10, 20);
+}
+
+static int amd_xgbe_phy_xgmii_mode(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	int ret;
+
+	/* Enable KR training */
+	ret = amd_xgbe_an_enable_kr_training(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Set PCS to KR/10G speed */
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~MDIO_PCS_CTRL2_TYPE;
+	ret |= MDIO_PCS_CTRL2_10GBR;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2, ret);
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~MDIO_CTRL1_SPEEDSEL;
+	ret |= MDIO_CTRL1_SPEED10G;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
+
+	ret = amd_xgbe_phy_pcs_power_cycle(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Set SerDes to 10G speed */
+	amd_xgbe_phy_serdes_start_ratechange(phydev);
+
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, DATARATE, SPEED_10000_RATE);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, WORDMODE, SPEED_10000_WORD);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, TXAMP, SPEED_10000_TXAMP);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, PLLSEL, SPEED_10000_PLL);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, PI_SPD_SEL, SPEED_10000_CDR);
+
+	XRXTX_IOWRITE_BITS(priv, RXTX_REG20, BLWC_ENA, RXTX_10000_BLWC);
+	XRXTX_IOWRITE_BITS(priv, RXTX_REG114, PQ_REG, RXTX_10000_PQ);
+
+	amd_xgbe_phy_serdes_complete_ratechange(phydev);
+
+	priv->mode = AMD_XGBE_MODE_KR;
+
+	return 0;
+}
+
+static int amd_xgbe_phy_gmii_2500_mode(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	int ret;
+
+	/* Disable KR training */
+	ret = amd_xgbe_an_disable_kr_training(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Set PCS to KX/1G speed */
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~MDIO_PCS_CTRL2_TYPE;
+	ret |= MDIO_PCS_CTRL2_10GBX;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2, ret);
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~MDIO_CTRL1_SPEEDSEL;
+	ret |= MDIO_CTRL1_SPEED1G;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
+
+	ret = amd_xgbe_phy_pcs_power_cycle(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Set SerDes to 2.5G speed */
+	amd_xgbe_phy_serdes_start_ratechange(phydev);
+
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, DATARATE, SPEED_2500_RATE);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, WORDMODE, SPEED_2500_WORD);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, TXAMP, SPEED_2500_TXAMP);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, PLLSEL, SPEED_2500_PLL);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, PI_SPD_SEL, SPEED_2500_CDR);
+
+	XRXTX_IOWRITE_BITS(priv, RXTX_REG20, BLWC_ENA, RXTX_2500_BLWC);
+	XRXTX_IOWRITE_BITS(priv, RXTX_REG114, PQ_REG, RXTX_2500_PQ);
+
+	amd_xgbe_phy_serdes_complete_ratechange(phydev);
+
+	priv->mode = AMD_XGBE_MODE_KX;
+
+	return 0;
+}
+
+static int amd_xgbe_phy_gmii_mode(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	int ret;
+
+	/* Disable KR training */
+	ret = amd_xgbe_an_disable_kr_training(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Set PCS to KX/1G speed */
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~MDIO_PCS_CTRL2_TYPE;
+	ret |= MDIO_PCS_CTRL2_10GBX;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2, ret);
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~MDIO_CTRL1_SPEEDSEL;
+	ret |= MDIO_CTRL1_SPEED1G;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
+
+	ret = amd_xgbe_phy_pcs_power_cycle(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Set SerDes to 1G speed */
+	amd_xgbe_phy_serdes_start_ratechange(phydev);
+
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, DATARATE, SPEED_1000_RATE);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, WORDMODE, SPEED_1000_WORD);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, TXAMP, SPEED_1000_TXAMP);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, PLLSEL, SPEED_1000_PLL);
+	XSIR1_IOWRITE_BITS(priv, SIR1_SPEED, PI_SPD_SEL, SPEED_1000_CDR);
+
+	XRXTX_IOWRITE_BITS(priv, RXTX_REG20, BLWC_ENA, RXTX_1000_BLWC);
+	XRXTX_IOWRITE_BITS(priv, RXTX_REG114, PQ_REG, RXTX_1000_PQ);
+
+	amd_xgbe_phy_serdes_complete_ratechange(phydev);
+
+	priv->mode = AMD_XGBE_MODE_KX;
+
+	return 0;
+}
+
+static int amd_xgbe_phy_switch_mode(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	int ret;
+
+	/* If we are in KR switch to KX, and vice-versa */
+	if (priv->mode == AMD_XGBE_MODE_KR)
+		ret = amd_xgbe_phy_gmii_mode(phydev);
+	else
+		ret = amd_xgbe_phy_xgmii_mode(phydev);
+
+	return ret;
+}
+
+static enum amd_xgbe_phy_an amd_xgbe_an_switch_mode(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = amd_xgbe_phy_switch_mode(phydev);
+	if (ret < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	return AMD_XGBE_AN_START;
+}
+
+static enum amd_xgbe_phy_an amd_xgbe_an_tx_training(struct phy_device *phydev,
+						    enum amd_xgbe_phy_rx *state)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	int ad_reg, lp_reg, ret;
+
+	*state = AMD_XGBE_RX_COMPLETE;
+
+	/* If we're in KX mode then we're done */
+	if (priv->mode == AMD_XGBE_MODE_KX)
+		return AMD_XGBE_AN_EVENT;
+
+	/* Enable/Disable FEC */
+	ad_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
+	if (ad_reg < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	lp_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA + 2);
+	if (lp_reg < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FEC_CTRL);
+	if (ret < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	if ((ad_reg & 0xc000) && (lp_reg & 0xc000))
+		ret |= 0x01;
+	else
+		ret &= ~0x01;
+
+	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FEC_CTRL, ret);
+
+	/* Start KR training */
+	ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL);
+	if (ret < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	ret |= 0x01;
+	phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, ret);
+
+	return AMD_XGBE_AN_EVENT;
+}
+
+static enum amd_xgbe_phy_an amd_xgbe_an_tx_xnp(struct phy_device *phydev,
+					       enum amd_xgbe_phy_rx *state)
+{
+	u16 msg;
+
+	*state = AMD_XGBE_RX_XNP;
+
+	msg = XNP_MCF_NULL_MESSAGE;
+	msg |= XNP_MP_FORMATTED;
+
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_XNP + 2, 0);
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_XNP + 1, 0);
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_XNP, msg);
+
+	return AMD_XGBE_AN_EVENT;
+}
+
+static enum amd_xgbe_phy_an amd_xgbe_an_rx_bpa(struct phy_device *phydev,
+					       enum amd_xgbe_phy_rx *state)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	unsigned int link_support;
+	int ret, ad_reg, lp_reg;
+
+	/* Read Base Ability register 2 first */
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA + 1);
+	if (ret < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	/* Check for a supported mode, otherwise restart in a different one */
+	link_support = (priv->mode == AMD_XGBE_MODE_KR) ? 0x80 : 0x20;
+	if (!(ret & link_support))
+		return amd_xgbe_an_switch_mode(phydev);
+
+	/* Check Extended Next Page support */
+	ad_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
+	if (ad_reg < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	lp_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA);
+	if (lp_reg < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	return ((ad_reg & XNP_NP_EXCHANGE) || (lp_reg & XNP_NP_EXCHANGE)) ?
+	       amd_xgbe_an_tx_xnp(phydev, state) :
+	       amd_xgbe_an_tx_training(phydev, state);
+}
+
+static enum amd_xgbe_phy_an amd_xgbe_an_rx_xnp(struct phy_device *phydev,
+					       enum amd_xgbe_phy_rx *state)
+{
+	int ad_reg, lp_reg;
+
+	/* Check Extended Next Page support */
+	ad_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
+	if (ad_reg < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	lp_reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA);
+	if (lp_reg < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	return ((ad_reg & XNP_NP_EXCHANGE) || (lp_reg & XNP_NP_EXCHANGE)) ?
+	       amd_xgbe_an_tx_xnp(phydev, state) :
+	       amd_xgbe_an_tx_training(phydev, state);
+}
+
+static enum amd_xgbe_phy_an amd_xgbe_an_start(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	int ret;
+
+	/* Be sure we aren't looping trying to negotiate */
+	if (priv->mode == AMD_XGBE_MODE_KR) {
+		if (priv->kr_state != AMD_XGBE_RX_READY)
+			return AMD_XGBE_AN_NO_LINK;
+		priv->kr_state = AMD_XGBE_RX_BPA;
+	} else {
+		if (priv->kx_state != AMD_XGBE_RX_READY)
+			return AMD_XGBE_AN_NO_LINK;
+		priv->kx_state = AMD_XGBE_RX_BPA;
+	}
+
+	/* Set up Advertisement register 3 first */
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2);
+	if (ret < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	if (phydev->supported & SUPPORTED_10000baseR_FEC)
+		ret |= 0xc000;
+	else
+		ret &= ~0xc000;
+
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2, ret);
+
+	/* Set up Advertisement register 2 next */
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1);
+	if (ret < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	if (phydev->supported & SUPPORTED_10000baseKR_Full)
+		ret |= 0x80;
+	else
+		ret &= ~0x80;
+
+	if (phydev->supported & SUPPORTED_1000baseKX_Full)
+		ret |= 0x20;
+	else
+		ret &= ~0x20;
+
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1, ret);
+
+	/* Set up Advertisement register 1 last */
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
+	if (ret < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	if (phydev->supported & SUPPORTED_Pause)
+		ret |= 0x400;
+	else
+		ret &= ~0x400;
+
+	if (phydev->supported & SUPPORTED_Asym_Pause)
+		ret |= 0x800;
+	else
+		ret &= ~0x800;
+
+	/* We don't intend to perform XNP */
+	ret &= ~XNP_NP_EXCHANGE;
+
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE, ret);
+
+	/* Enable and start auto-negotiation */
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT, 0);
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1);
+	if (ret < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	ret |= MDIO_AN_CTRL1_ENABLE;
+	ret |= MDIO_AN_CTRL1_RESTART;
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1, ret);
+
+	return AMD_XGBE_AN_EVENT;
+}
+
+static enum amd_xgbe_phy_an amd_xgbe_an_event(struct phy_device *phydev)
+{
+	enum amd_xgbe_phy_an new_state;
+	int ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT);
+	if (ret < 0)
+		return AMD_XGBE_AN_ERROR;
+
+	new_state = AMD_XGBE_AN_EVENT;
+	if (ret & XGBE_AN_PG_RCV)
+		new_state = AMD_XGBE_AN_PAGE_RECEIVED;
+	else if (ret & XGBE_AN_INC_LINK)
+		new_state = AMD_XGBE_AN_INCOMPAT_LINK;
+	else if (ret & XGBE_AN_INT_CMPLT)
+		new_state = AMD_XGBE_AN_COMPLETE;
+
+	if (new_state != AMD_XGBE_AN_EVENT)
+		phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT, 0);
+
+	return new_state;
+}
+
+static enum amd_xgbe_phy_an amd_xgbe_an_page_received(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	enum amd_xgbe_phy_rx *state;
+	int ret;
+
+	state = (priv->mode == AMD_XGBE_MODE_KR) ? &priv->kr_state
+						 : &priv->kx_state;
+
+	switch (*state) {
+	case AMD_XGBE_RX_BPA:
+		ret = amd_xgbe_an_rx_bpa(phydev, state);
+		break;
+
+	case AMD_XGBE_RX_XNP:
+		ret = amd_xgbe_an_rx_xnp(phydev, state);
+		break;
+
+	default:
+		ret = AMD_XGBE_AN_ERROR;
+	}
+
+	return ret;
+}
+
+static enum amd_xgbe_phy_an amd_xgbe_an_incompat_link(struct phy_device *phydev)
+{
+	return amd_xgbe_an_switch_mode(phydev);
+}
+
+static void amd_xgbe_an_state_machine(struct work_struct *work)
+{
+	struct amd_xgbe_phy_priv *priv = container_of(work,
+						      struct amd_xgbe_phy_priv,
+						      an_work);
+	struct phy_device *phydev = priv->phydev;
+	enum amd_xgbe_phy_an cur_state;
+	int sleep;
+
+	while (1) {
+		mutex_lock(&priv->an_mutex);
+
+		cur_state = priv->an_state;
+
+		switch (priv->an_state) {
+		case AMD_XGBE_AN_START:
+			priv->an_state = amd_xgbe_an_start(phydev);
+			break;
+
+		case AMD_XGBE_AN_EVENT:
+			priv->an_state = amd_xgbe_an_event(phydev);
+			break;
+
+		case AMD_XGBE_AN_PAGE_RECEIVED:
+			priv->an_state = amd_xgbe_an_page_received(phydev);
+			break;
+
+		case AMD_XGBE_AN_INCOMPAT_LINK:
+			priv->an_state = amd_xgbe_an_incompat_link(phydev);
+			break;
+
+		case AMD_XGBE_AN_COMPLETE:
+		case AMD_XGBE_AN_NO_LINK:
+		case AMD_XGBE_AN_EXIT:
+			goto exit_unlock;
+
+		default:
+			priv->an_state = AMD_XGBE_AN_ERROR;
+		}
+
+		if (priv->an_state == AMD_XGBE_AN_ERROR) {
+			netdev_err(phydev->attached_dev,
+				   "error during auto-negotiation, state=%u\n",
+				   cur_state);
+			goto exit_unlock;
+		}
+
+		sleep = (priv->an_state == AMD_XGBE_AN_EVENT) ? 1 : 0;
+
+		mutex_unlock(&priv->an_mutex);
+
+		if (sleep)
+			usleep_range(20, 50);
+	}
+
+exit_unlock:
+	priv->an_result = priv->an_state;
+	priv->an_state = AMD_XGBE_AN_READY;
+
+	mutex_unlock(&priv->an_mutex);
+}
+
+static int amd_xgbe_phy_soft_reset(struct phy_device *phydev)
+{
+	int count, ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret |= MDIO_CTRL1_RESET;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
+
+	count = 50;
+	do {
+		msleep(20);
+		ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
+		if (ret < 0)
+			return ret;
+	} while ((ret & MDIO_CTRL1_RESET) && --count);
+
+	if (ret & MDIO_CTRL1_RESET)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int amd_xgbe_phy_config_init(struct phy_device *phydev)
+{
+	/* Initialize supported features */
+	phydev->supported = SUPPORTED_Autoneg;
+	phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+	phydev->supported |= SUPPORTED_Backplane;
+	phydev->supported |= SUPPORTED_1000baseKX_Full |
+			     SUPPORTED_2500baseX_Full;
+	phydev->supported |= SUPPORTED_10000baseKR_Full |
+			     SUPPORTED_10000baseR_FEC;
+	phydev->advertising = phydev->supported;
+
+	/* Turn off and clear interrupts */
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INTMASK, 0);
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_INT, 0);
+
+	return 0;
+}
+
+static int amd_xgbe_phy_setup_forced(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Disable auto-negotiation */
+	ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1);
+	if (ret < 0)
+		return ret;
+
+	ret &= ~MDIO_AN_CTRL1_ENABLE;
+	phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1, ret);
+
+	/* Validate/Set specified speed */
+	switch (phydev->speed) {
+	case SPEED_10000:
+		ret = amd_xgbe_phy_xgmii_mode(phydev);
+		break;
+
+	case SPEED_2500:
+		ret = amd_xgbe_phy_gmii_2500_mode(phydev);
+		break;
+
+	case SPEED_1000:
+		ret = amd_xgbe_phy_gmii_mode(phydev);
+		break;
+
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret < 0)
+		return ret;
+
+	/* Validate duplex mode */
+	if (phydev->duplex != DUPLEX_FULL)
+		return -EINVAL;
+
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+
+	return 0;
+}
+
+static int amd_xgbe_phy_config_aneg(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	u32 mmd_mask = phydev->c45_ids.devices_in_package;
+	int ret;
+
+	if (phydev->autoneg != AUTONEG_ENABLE)
+		return amd_xgbe_phy_setup_forced(phydev);
+
+	/* Make sure we have the AN MMD present */
+	if (!(mmd_mask & MDIO_DEVS_AN))
+		return -EINVAL;
+
+	/* Get the current speed mode */
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
+	if (ret < 0)
+		return ret;
+
+	/* Start/Restart the auto-negotiation state machine */
+	mutex_lock(&priv->an_mutex);
+	priv->an_result = AMD_XGBE_AN_READY;
+	priv->an_state = AMD_XGBE_AN_START;
+	priv->kr_state = AMD_XGBE_RX_READY;
+	priv->kx_state = AMD_XGBE_RX_READY;
+	mutex_unlock(&priv->an_mutex);
+
+	queue_work(priv->an_workqueue, &priv->an_work);
+
+	return 0;
+}
+
+static int amd_xgbe_phy_aneg_done(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	enum amd_xgbe_phy_an state;
+
+	mutex_lock(&priv->an_mutex);
+	state = priv->an_result;
+	mutex_unlock(&priv->an_mutex);
+
+	return (state == AMD_XGBE_AN_COMPLETE);
+}
+
+static int amd_xgbe_phy_update_link(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	enum amd_xgbe_phy_an state;
+	unsigned int check_again, autoneg;
+	int ret;
+
+	/* If we're doing auto-negotiation don't report link down */
+	mutex_lock(&priv->an_mutex);
+	state = priv->an_state;
+	mutex_unlock(&priv->an_mutex);
+
+	if (state != AMD_XGBE_AN_READY) {
+		phydev->link = 1;
+		return 0;
+	}
+
+	/* Since the device can be in the wrong mode when a link is
+	 * (re-)established (cable connected after the interface is
+	 * up, etc.), the link status may report no link. If there
+	 * is no link, try switching modes and checking the status
+	 * again.
+	 */
+	check_again = 1;
+again:
+	/* Link status is latched low, so read once to clear
+	 * and then read again to get current state
+	 */
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_STAT1);
+	if (ret < 0)
+		return ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_STAT1);
+	if (ret < 0)
+		return ret;
+
+	phydev->link = (ret & MDIO_STAT1_LSTATUS) ? 1 : 0;
+
+	if (!phydev->link) {
+		ret = amd_xgbe_phy_switch_mode(phydev);
+		if (check_again) {
+			check_again = 0;
+			goto again;
+		}
+	}
+
+	autoneg = (phydev->link && !priv->link) ? 1 : 0;
+	priv->link = phydev->link;
+	if (autoneg) {
+		/* Link is (back) up, re-start auto-negotiation */
+		ret = amd_xgbe_phy_config_aneg(phydev);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int amd_xgbe_phy_read_status(struct phy_device *phydev)
+{
+	u32 mmd_mask = phydev->c45_ids.devices_in_package;
+	int ret, mode, ad_ret, lp_ret;
+
+	ret = amd_xgbe_phy_update_link(phydev);
+	if (ret)
+		return ret;
+
+	mode = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
+	if (mode < 0)
+		return mode;
+	mode &= MDIO_PCS_CTRL2_TYPE;
+
+	if (phydev->autoneg == AUTONEG_ENABLE) {
+		if (!(mmd_mask & MDIO_DEVS_AN))
+			return -EINVAL;
+
+		if (!amd_xgbe_phy_aneg_done(phydev))
+			return 0;
+
+		/* Compare Advertisement and Link Partner register 1 */
+		ad_ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE);
+		if (ad_ret < 0)
+			return ad_ret;
+		lp_ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA);
+		if (lp_ret < 0)
+			return lp_ret;
+
+		ad_ret &= lp_ret;
+		phydev->pause = (ad_ret & 0x400) ? 1 : 0;
+		phydev->asym_pause = (ad_ret & 0x800) ? 1 : 0;
+
+		/* Compare Advertisement and Link Partner register 2 */
+		ad_ret = phy_read_mmd(phydev, MDIO_MMD_AN,
+				      MDIO_AN_ADVERTISE + 1);
+		if (ad_ret < 0)
+			return ad_ret;
+		lp_ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_LPA + 1);
+		if (lp_ret < 0)
+			return lp_ret;
+
+		ad_ret &= lp_ret;
+		if (ad_ret & 0x80) {
+			phydev->speed = SPEED_10000;
+			if (mode != MDIO_PCS_CTRL2_10GBR) {
+				ret = amd_xgbe_phy_xgmii_mode(phydev);
+				if (ret < 0)
+					return ret;
+			}
+		} else {
+			phydev->speed = SPEED_1000;
+			if (mode == MDIO_PCS_CTRL2_10GBR) {
+				ret = amd_xgbe_phy_gmii_mode(phydev);
+				if (ret < 0)
+					return ret;
+			}
+		}
+
+		phydev->duplex = DUPLEX_FULL;
+	} else {
+		phydev->speed = (mode == MDIO_PCS_CTRL2_10GBR) ? SPEED_10000
+							       : SPEED_1000;
+		phydev->duplex = DUPLEX_FULL;
+		phydev->pause = 0;
+		phydev->asym_pause = 0;
+	}
+
+	return 0;
+}
+
+static int amd_xgbe_phy_suspend(struct phy_device *phydev)
+{
+	int ret;
+
+	mutex_lock(&phydev->lock);
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
+	if (ret < 0)
+		goto unlock;
+
+	ret |= MDIO_CTRL1_LPOWER;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
+
+	ret = 0;
+
+unlock:
+	mutex_unlock(&phydev->lock);
+
+	return ret;
+}
+
+static int amd_xgbe_phy_resume(struct phy_device *phydev)
+{
+	int ret;
+
+	mutex_lock(&phydev->lock);
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1);
+	if (ret < 0)
+		goto unlock;
+
+	ret &= ~MDIO_CTRL1_LPOWER;
+	phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, ret);
+
+	ret = 0;
+
+unlock:
+	mutex_unlock(&phydev->lock);
+
+	return ret;
+}
+
+static int amd_xgbe_phy_probe(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv;
+	struct platform_device *pdev;
+	struct device *dev;
+	char *wq_name;
+	int ret;
+
+	if (!phydev->dev.of_node)
+		return -EINVAL;
+
+	pdev = of_find_device_by_node(phydev->dev.of_node);
+	if (!pdev)
+		return -EINVAL;
+	dev = &pdev->dev;
+
+	wq_name = kasprintf(GFP_KERNEL, "%s-amd-xgbe-phy", phydev->bus->name);
+	if (!wq_name) {
+		ret = -ENOMEM;
+		goto err_pdev;
+	}
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		ret = -ENOMEM;
+		goto err_name;
+	}
+
+	priv->pdev = pdev;
+	priv->dev = dev;
+	priv->phydev = phydev;
+
+	/* Get the device mmio areas */
+	priv->rxtx_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->rxtx_regs = devm_ioremap_resource(dev, priv->rxtx_res);
+	if (IS_ERR(priv->rxtx_regs)) {
+		dev_err(dev, "rxtx ioremap failed\n");
+		ret = PTR_ERR(priv->rxtx_regs);
+		goto err_priv;
+	}
+
+	priv->sir0_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	priv->sir0_regs = devm_ioremap_resource(dev, priv->sir0_res);
+	if (IS_ERR(priv->sir0_regs)) {
+		dev_err(dev, "sir0 ioremap failed\n");
+		ret = PTR_ERR(priv->sir0_regs);
+		goto err_rxtx;
+	}
+
+	priv->sir1_res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	priv->sir1_regs = devm_ioremap_resource(dev, priv->sir1_res);
+	if (IS_ERR(priv->sir1_regs)) {
+		dev_err(dev, "sir1 ioremap failed\n");
+		ret = PTR_ERR(priv->sir1_regs);
+		goto err_sir0;
+	}
+
+	priv->link = 1;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL2);
+	if (ret < 0)
+		goto err_sir1;
+	if ((ret & MDIO_PCS_CTRL2_TYPE) == MDIO_PCS_CTRL2_10GBR)
+		priv->mode = AMD_XGBE_MODE_KR;
+	else
+		priv->mode = AMD_XGBE_MODE_KX;
+
+	mutex_init(&priv->an_mutex);
+	INIT_WORK(&priv->an_work, amd_xgbe_an_state_machine);
+	priv->an_workqueue = create_singlethread_workqueue(wq_name);
+	if (!priv->an_workqueue) {
+		ret = -ENOMEM;
+		goto err_sir1;
+	}
+
+	phydev->priv = priv;
+
+	kfree(wq_name);
+	of_dev_put(pdev);
+
+	return 0;
+
+err_sir1:
+	devm_iounmap(dev, priv->sir1_regs);
+	devm_release_mem_region(dev, priv->sir1_res->start,
+				resource_size(priv->sir1_res));
+
+err_sir0:
+	devm_iounmap(dev, priv->sir0_regs);
+	devm_release_mem_region(dev, priv->sir0_res->start,
+				resource_size(priv->sir0_res));
+
+err_rxtx:
+	devm_iounmap(dev, priv->rxtx_regs);
+	devm_release_mem_region(dev, priv->rxtx_res->start,
+				resource_size(priv->rxtx_res));
+
+err_priv:
+	devm_kfree(dev, priv);
+
+err_name:
+	kfree(wq_name);
+
+err_pdev:
+	of_dev_put(pdev);
+
+	return ret;
+}
+
+static void amd_xgbe_phy_remove(struct phy_device *phydev)
+{
+	struct amd_xgbe_phy_priv *priv = phydev->priv;
+	struct device *dev = priv->dev;
+
+	/* Stop any in process auto-negotiation */
+	mutex_lock(&priv->an_mutex);
+	priv->an_state = AMD_XGBE_AN_EXIT;
+	mutex_unlock(&priv->an_mutex);
+
+	flush_workqueue(priv->an_workqueue);
+	destroy_workqueue(priv->an_workqueue);
+
+	/* Release resources */
+	devm_iounmap(dev, priv->sir1_regs);
+	devm_release_mem_region(dev, priv->sir1_res->start,
+				resource_size(priv->sir1_res));
+
+	devm_iounmap(dev, priv->sir0_regs);
+	devm_release_mem_region(dev, priv->sir0_res->start,
+				resource_size(priv->sir0_res));
+
+	devm_iounmap(dev, priv->rxtx_regs);
+	devm_release_mem_region(dev, priv->rxtx_res->start,
+				resource_size(priv->rxtx_res));
+
+	devm_kfree(dev, priv);
+}
+
+static int amd_xgbe_match_phy_device(struct phy_device *phydev)
+{
+	return phydev->c45_ids.device_ids[MDIO_MMD_PCS] == XGBE_PHY_ID;
+}
+
+static struct phy_driver amd_xgbe_phy_driver[] = {
+	{
+		.phy_id			= XGBE_PHY_ID,
+		.phy_id_mask		= XGBE_PHY_MASK,
+		.name			= "AMD XGBE PHY",
+		.features		= 0,
+		.probe			= amd_xgbe_phy_probe,
+		.remove			= amd_xgbe_phy_remove,
+		.soft_reset		= amd_xgbe_phy_soft_reset,
+		.config_init		= amd_xgbe_phy_config_init,
+		.suspend		= amd_xgbe_phy_suspend,
+		.resume			= amd_xgbe_phy_resume,
+		.config_aneg		= amd_xgbe_phy_config_aneg,
+		.aneg_done		= amd_xgbe_phy_aneg_done,
+		.read_status		= amd_xgbe_phy_read_status,
+		.match_phy_device	= amd_xgbe_match_phy_device,
+		.driver			= {
+			.owner = THIS_MODULE,
+		},
+	},
+};
+
+static int __init amd_xgbe_phy_init(void)
+{
+	return phy_drivers_register(amd_xgbe_phy_driver,
+				    ARRAY_SIZE(amd_xgbe_phy_driver));
+}
+
+static void __exit amd_xgbe_phy_exit(void)
+{
+	phy_drivers_unregister(amd_xgbe_phy_driver,
+			       ARRAY_SIZE(amd_xgbe_phy_driver));
+}
+
+module_init(amd_xgbe_phy_init);
+module_exit(amd_xgbe_phy_exit);
+
+static struct mdio_device_id __maybe_unused amd_xgbe_phy_ids[] = {
+	{ XGBE_PHY_ID, XGBE_PHY_MASK },
+	{ }
+};
+MODULE_DEVICE_TABLE(mdio, amd_xgbe_phy_ids);
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 643464d5a72..fdc1b418fa6 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -16,9 +16,13 @@
 #include <linux/string.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/of_gpio.h>
+#include <linux/gpio/consumer.h>
 
 #define AT803X_INTR_ENABLE			0x12
 #define AT803X_INTR_STATUS			0x13
+#define AT803X_SMART_SPEED			0x14
+#define AT803X_LED_CONTROL			0x18
 #define AT803X_WOL_ENABLE			0x01
 #define AT803X_DEVICE_ADDR			0x03
 #define AT803X_LOC_MAC_ADDR_0_15_OFFSET		0x804C
@@ -35,10 +39,52 @@
 #define AT803X_DEBUG_SYSTEM_MODE_CTRL		0x05
 #define AT803X_DEBUG_RGMII_TX_CLK_DLY		BIT(8)
 
+#define ATH8030_PHY_ID 0x004dd076
+#define ATH8031_PHY_ID 0x004dd074
+#define ATH8035_PHY_ID 0x004dd072
+
 MODULE_DESCRIPTION("Atheros 803x PHY driver");
 MODULE_AUTHOR("Matus Ujhelyi");
 MODULE_LICENSE("GPL");
 
+struct at803x_priv {
+	bool phy_reset:1;
+	struct gpio_desc *gpiod_reset;
+};
+
+struct at803x_context {
+	u16 bmcr;
+	u16 advertise;
+	u16 control1000;
+	u16 int_enable;
+	u16 smart_speed;
+	u16 led_control;
+};
+
+/* save relevant PHY registers to private copy */
+static void at803x_context_save(struct phy_device *phydev,
+				struct at803x_context *context)
+{
+	context->bmcr = phy_read(phydev, MII_BMCR);
+	context->advertise = phy_read(phydev, MII_ADVERTISE);
+	context->control1000 = phy_read(phydev, MII_CTRL1000);
+	context->int_enable = phy_read(phydev, AT803X_INTR_ENABLE);
+	context->smart_speed = phy_read(phydev, AT803X_SMART_SPEED);
+	context->led_control = phy_read(phydev, AT803X_LED_CONTROL);
+}
+
+/* restore relevant PHY registers from private copy */
+static void at803x_context_restore(struct phy_device *phydev,
+				   const struct at803x_context *context)
+{
+	phy_write(phydev, MII_BMCR, context->bmcr);
+	phy_write(phydev, MII_ADVERTISE, context->advertise);
+	phy_write(phydev, MII_CTRL1000, context->control1000);
+	phy_write(phydev, AT803X_INTR_ENABLE, context->int_enable);
+	phy_write(phydev, AT803X_SMART_SPEED, context->smart_speed);
+	phy_write(phydev, AT803X_LED_CONTROL, context->led_control);
+}
+
 static int at803x_set_wol(struct phy_device *phydev,
 			  struct ethtool_wolinfo *wol)
 {
@@ -142,43 +188,33 @@ static int at803x_resume(struct phy_device *phydev)
 	return 0;
 }
 
+static int at803x_probe(struct phy_device *phydev)
+{
+	struct device *dev = &phydev->dev;
+	struct at803x_priv *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->gpiod_reset = devm_gpiod_get(dev, "reset");
+	if (IS_ERR(priv->gpiod_reset))
+		priv->gpiod_reset = NULL;
+	else
+		gpiod_direction_output(priv->gpiod_reset, 1);
+
+	phydev->priv = priv;
+
+	return 0;
+}
+
 static int at803x_config_init(struct phy_device *phydev)
 {
-	int val;
 	int ret;
-	u32 features;
-
-	features = SUPPORTED_TP | SUPPORTED_MII | SUPPORTED_AUI |
-		   SUPPORTED_FIBRE | SUPPORTED_BNC;
-
-	val = phy_read(phydev, MII_BMSR);
-	if (val < 0)
-		return val;
-
-	if (val & BMSR_ANEGCAPABLE)
-		features |= SUPPORTED_Autoneg;
-	if (val & BMSR_100FULL)
-		features |= SUPPORTED_100baseT_Full;
-	if (val & BMSR_100HALF)
-		features |= SUPPORTED_100baseT_Half;
-	if (val & BMSR_10FULL)
-		features |= SUPPORTED_10baseT_Full;
-	if (val & BMSR_10HALF)
-		features |= SUPPORTED_10baseT_Half;
-
-	if (val & BMSR_ESTATEN) {
-		val = phy_read(phydev, MII_ESTATUS);
-		if (val < 0)
-			return val;
-
-		if (val & ESTATUS_1000_TFULL)
-			features |= SUPPORTED_1000baseT_Full;
-		if (val & ESTATUS_1000_THALF)
-			features |= SUPPORTED_1000baseT_Half;
-	}
 
-	phydev->supported = features;
-	phydev->advertising = features;
+	ret = genphy_config_init(phydev);
+	if (ret < 0)
+		return ret;
 
 	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) {
 		ret = phy_write(phydev, AT803X_DEBUG_ADDR,
@@ -219,58 +255,99 @@ static int at803x_config_intr(struct phy_device *phydev)
 	return err;
 }
 
+static void at803x_link_change_notify(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+
+	/*
+	 * Conduct a hardware reset for AT8030 every time a link loss is
+	 * signalled. This is necessary to circumvent a hardware bug that
+	 * occurs when the cable is unplugged while TX packets are pending
+	 * in the FIFO. In such cases, the FIFO enters an error mode it
+	 * cannot recover from by software.
+	 */
+	if (phydev->drv->phy_id == ATH8030_PHY_ID) {
+		if (phydev->state == PHY_NOLINK) {
+			if (priv->gpiod_reset && !priv->phy_reset) {
+				struct at803x_context context;
+
+				at803x_context_save(phydev, &context);
+
+				gpiod_set_value(priv->gpiod_reset, 0);
+				msleep(1);
+				gpiod_set_value(priv->gpiod_reset, 1);
+				msleep(1);
+
+				at803x_context_restore(phydev, &context);
+
+				dev_dbg(&phydev->dev, "%s(): phy was reset\n",
+					__func__);
+				priv->phy_reset = true;
+			}
+		} else {
+			priv->phy_reset = false;
+		}
+	}
+}
+
 static struct phy_driver at803x_driver[] = {
 {
 	/* ATHEROS 8035 */
-	.phy_id		= 0x004dd072,
-	.name		= "Atheros 8035 ethernet",
-	.phy_id_mask	= 0xffffffef,
-	.config_init	= at803x_config_init,
-	.set_wol	= at803x_set_wol,
-	.get_wol	= at803x_get_wol,
-	.suspend	= at803x_suspend,
-	.resume		= at803x_resume,
-	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
-	.config_aneg	= genphy_config_aneg,
-	.read_status	= genphy_read_status,
-	.driver		= {
+	.phy_id			= ATH8035_PHY_ID,
+	.name			= "Atheros 8035 ethernet",
+	.phy_id_mask		= 0xffffffef,
+	.probe			= at803x_probe,
+	.config_init		= at803x_config_init,
+	.link_change_notify	= at803x_link_change_notify,
+	.set_wol		= at803x_set_wol,
+	.get_wol		= at803x_get_wol,
+	.suspend		= at803x_suspend,
+	.resume			= at803x_resume,
+	.features		= PHY_GBIT_FEATURES,
+	.flags			= PHY_HAS_INTERRUPT,
+	.config_aneg		= genphy_config_aneg,
+	.read_status		= genphy_read_status,
+	.driver			= {
 		.owner = THIS_MODULE,
 	},
 }, {
 	/* ATHEROS 8030 */
-	.phy_id		= 0x004dd076,
-	.name		= "Atheros 8030 ethernet",
-	.phy_id_mask	= 0xffffffef,
-	.config_init	= at803x_config_init,
-	.set_wol	= at803x_set_wol,
-	.get_wol	= at803x_get_wol,
-	.suspend	= at803x_suspend,
-	.resume		= at803x_resume,
-	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
-	.config_aneg	= genphy_config_aneg,
-	.read_status	= genphy_read_status,
-	.driver		= {
+	.phy_id			= ATH8030_PHY_ID,
+	.name			= "Atheros 8030 ethernet",
+	.phy_id_mask		= 0xffffffef,
+	.probe			= at803x_probe,
+	.config_init		= at803x_config_init,
+	.link_change_notify	= at803x_link_change_notify,
+	.set_wol		= at803x_set_wol,
+	.get_wol		= at803x_get_wol,
+	.suspend		= at803x_suspend,
+	.resume			= at803x_resume,
+	.features		= PHY_GBIT_FEATURES,
+	.flags			= PHY_HAS_INTERRUPT,
+	.config_aneg		= genphy_config_aneg,
+	.read_status		= genphy_read_status,
+	.driver			= {
 		.owner = THIS_MODULE,
 	},
 }, {
 	/* ATHEROS 8031 */
-	.phy_id		= 0x004dd074,
-	.name		= "Atheros 8031 ethernet",
-	.phy_id_mask	= 0xffffffef,
-	.config_init	= at803x_config_init,
-	.set_wol	= at803x_set_wol,
-	.get_wol	= at803x_get_wol,
-	.suspend	= at803x_suspend,
-	.resume		= at803x_resume,
-	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
-	.config_aneg	= genphy_config_aneg,
-	.read_status	= genphy_read_status,
-	.ack_interrupt  = &at803x_ack_interrupt,
-	.config_intr    = &at803x_config_intr,
-	.driver		= {
+	.phy_id			= ATH8031_PHY_ID,
+	.name			= "Atheros 8031 ethernet",
+	.phy_id_mask		= 0xffffffef,
+	.probe			= at803x_probe,
+	.config_init		= at803x_config_init,
+	.link_change_notify	= at803x_link_change_notify,
+	.set_wol		= at803x_set_wol,
+	.get_wol		= at803x_get_wol,
+	.suspend		= at803x_suspend,
+	.resume			= at803x_resume,
+	.features		= PHY_GBIT_FEATURES,
+	.flags			= PHY_HAS_INTERRUPT,
+	.config_aneg		= genphy_config_aneg,
+	.read_status		= genphy_read_status,
+	.ack_interrupt		= &at803x_ack_interrupt,
+	.config_intr		= &at803x_config_intr,
+	.driver			= {
 		.owner = THIS_MODULE,
 	},
 } };
@@ -283,17 +360,16 @@ static int __init atheros_init(void)
 
 static void __exit atheros_exit(void)
 {
-	return phy_drivers_unregister(at803x_driver,
-				      ARRAY_SIZE(at803x_driver));
+	phy_drivers_unregister(at803x_driver, ARRAY_SIZE(at803x_driver));
 }
 
 module_init(atheros_init);
 module_exit(atheros_exit);
 
 static struct mdio_device_id __maybe_unused atheros_tbl[] = {
-	{ 0x004dd076, 0xffffffef },
-	{ 0x004dd074, 0xffffffef },
-	{ 0x004dd072, 0xffffffef },
+	{ ATH8030_PHY_ID, 0xffffffef },
+	{ ATH8031_PHY_ID, 0xffffffef },
+	{ ATH8035_PHY_ID, 0xffffffef },
 	{ }
 };
 
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 6a999e6814a..9408157a246 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -1323,15 +1323,15 @@ static bool dp83640_rxtstamp(struct phy_device *phydev,
 {
 	struct dp83640_private *dp83640 = phydev->priv;
 
-	if (!dp83640->hwts_rx_en)
-		return false;
-
 	if (is_status_frame(skb, type)) {
 		decode_status_frame(dp83640, skb);
 		kfree_skb(skb);
 		return true;
 	}
 
+	if (!dp83640->hwts_rx_en)
+		return false;
+
 	SKB_PTP_TYPE(skb) = type;
 	skb_queue_tail(&dp83640->rx_queue, skb);
 	schedule_work(&dp83640->ts_work);
diff --git a/drivers/net/phy/fixed.c b/drivers/net/phy/fixed.c
index ba55adfc7aa..d60d875cb44 100644
--- a/drivers/net/phy/fixed.c
+++ b/drivers/net/phy/fixed.c
@@ -21,6 +21,7 @@
 #include <linux/phy_fixed.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/of.h>
 
 #define MII_REGS_NUM 29
 
@@ -31,7 +32,7 @@ struct fixed_mdio_bus {
 };
 
 struct fixed_phy {
-	int id;
+	int addr;
 	u16 regs[MII_REGS_NUM];
 	struct phy_device *phydev;
 	struct fixed_phy_status status;
@@ -104,8 +105,8 @@ static int fixed_phy_update_regs(struct fixed_phy *fp)
 	if (fp->status.asym_pause)
 		lpa |= LPA_PAUSE_ASYM;
 
-	fp->regs[MII_PHYSID1] = fp->id >> 16;
-	fp->regs[MII_PHYSID2] = fp->id;
+	fp->regs[MII_PHYSID1] = 0;
+	fp->regs[MII_PHYSID2] = 0;
 
 	fp->regs[MII_BMSR] = bmsr;
 	fp->regs[MII_BMCR] = bmcr;
@@ -115,7 +116,7 @@ static int fixed_phy_update_regs(struct fixed_phy *fp)
 	return 0;
 }
 
-static int fixed_mdio_read(struct mii_bus *bus, int phy_id, int reg_num)
+static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num)
 {
 	struct fixed_mdio_bus *fmb = bus->priv;
 	struct fixed_phy *fp;
@@ -124,7 +125,7 @@ static int fixed_mdio_read(struct mii_bus *bus, int phy_id, int reg_num)
 		return -1;
 
 	list_for_each_entry(fp, &fmb->phys, node) {
-		if (fp->id == phy_id) {
+		if (fp->addr == phy_addr) {
 			/* Issue callback if user registered it. */
 			if (fp->link_update) {
 				fp->link_update(fp->phydev->attached_dev,
@@ -138,7 +139,7 @@ static int fixed_mdio_read(struct mii_bus *bus, int phy_id, int reg_num)
 	return 0xFFFF;
 }
 
-static int fixed_mdio_write(struct mii_bus *bus, int phy_id, int reg_num,
+static int fixed_mdio_write(struct mii_bus *bus, int phy_addr, int reg_num,
 			    u16 val)
 {
 	return 0;
@@ -160,7 +161,7 @@ int fixed_phy_set_link_update(struct phy_device *phydev,
 		return -EINVAL;
 
 	list_for_each_entry(fp, &fmb->phys, node) {
-		if (fp->id == phydev->phy_id) {
+		if (fp->addr == phydev->addr) {
 			fp->link_update = link_update;
 			fp->phydev = phydev;
 			return 0;
@@ -171,7 +172,7 @@ int fixed_phy_set_link_update(struct phy_device *phydev,
 }
 EXPORT_SYMBOL_GPL(fixed_phy_set_link_update);
 
-int fixed_phy_add(unsigned int irq, int phy_id,
+int fixed_phy_add(unsigned int irq, int phy_addr,
 		  struct fixed_phy_status *status)
 {
 	int ret;
@@ -184,9 +185,9 @@ int fixed_phy_add(unsigned int irq, int phy_id,
 
 	memset(fp->regs, 0xFF,  sizeof(fp->regs[0]) * MII_REGS_NUM);
 
-	fmb->irqs[phy_id] = irq;
+	fmb->irqs[phy_addr] = irq;
 
-	fp->id = phy_id;
+	fp->addr = phy_addr;
 	fp->status = *status;
 
 	ret = fixed_phy_update_regs(fp);
@@ -203,6 +204,66 @@ err_regs:
 }
 EXPORT_SYMBOL_GPL(fixed_phy_add);
 
+void fixed_phy_del(int phy_addr)
+{
+	struct fixed_mdio_bus *fmb = &platform_fmb;
+	struct fixed_phy *fp, *tmp;
+
+	list_for_each_entry_safe(fp, tmp, &fmb->phys, node) {
+		if (fp->addr == phy_addr) {
+			list_del(&fp->node);
+			kfree(fp);
+			return;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(fixed_phy_del);
+
+static int phy_fixed_addr;
+static DEFINE_SPINLOCK(phy_fixed_addr_lock);
+
+int fixed_phy_register(unsigned int irq,
+		       struct fixed_phy_status *status,
+		       struct device_node *np)
+{
+	struct fixed_mdio_bus *fmb = &platform_fmb;
+	struct phy_device *phy;
+	int phy_addr;
+	int ret;
+
+	/* Get the next available PHY address, up to PHY_MAX_ADDR */
+	spin_lock(&phy_fixed_addr_lock);
+	if (phy_fixed_addr == PHY_MAX_ADDR) {
+		spin_unlock(&phy_fixed_addr_lock);
+		return -ENOSPC;
+	}
+	phy_addr = phy_fixed_addr++;
+	spin_unlock(&phy_fixed_addr_lock);
+
+	ret = fixed_phy_add(PHY_POLL, phy_addr, status);
+	if (ret < 0)
+		return ret;
+
+	phy = get_phy_device(fmb->mii_bus, phy_addr, false);
+	if (!phy || IS_ERR(phy)) {
+		fixed_phy_del(phy_addr);
+		return -EINVAL;
+	}
+
+	of_node_get(np);
+	phy->dev.of_node = np;
+
+	ret = phy_device_register(phy);
+	if (ret) {
+		phy_device_free(phy);
+		of_node_put(np);
+		fixed_phy_del(phy_addr);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int __init fixed_mdio_bus_init(void)
 {
 	struct fixed_mdio_bus *fmb = &platform_fmb;
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 76f54b32a12..203651ebccb 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -69,6 +69,73 @@ struct mii_bus *mdiobus_alloc_size(size_t size)
 }
 EXPORT_SYMBOL(mdiobus_alloc_size);
 
+static void _devm_mdiobus_free(struct device *dev, void *res)
+{
+	mdiobus_free(*(struct mii_bus **)res);
+}
+
+static int devm_mdiobus_match(struct device *dev, void *res, void *data)
+{
+	struct mii_bus **r = res;
+
+	if (WARN_ON(!r || !*r))
+		return 0;
+
+	return *r == data;
+}
+
+/**
+ * devm_mdiobus_alloc_size - Resource-managed mdiobus_alloc_size()
+ * @dev:		Device to allocate mii_bus for
+ * @sizeof_priv:	Space to allocate for private structure.
+ *
+ * Managed mdiobus_alloc_size. mii_bus allocated with this function is
+ * automatically freed on driver detach.
+ *
+ * If an mii_bus allocated with this function needs to be freed separately,
+ * devm_mdiobus_free() must be used.
+ *
+ * RETURNS:
+ * Pointer to allocated mii_bus on success, NULL on failure.
+ */
+struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv)
+{
+	struct mii_bus **ptr, *bus;
+
+	ptr = devres_alloc(_devm_mdiobus_free, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return NULL;
+
+	/* use raw alloc_dr for kmalloc caller tracing */
+	bus = mdiobus_alloc_size(sizeof_priv);
+	if (bus) {
+		*ptr = bus;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return bus;
+}
+EXPORT_SYMBOL_GPL(devm_mdiobus_alloc_size);
+
+/**
+ * devm_mdiobus_free - Resource-managed mdiobus_free()
+ * @dev:		Device this mii_bus belongs to
+ * @bus:		the mii_bus associated with the device
+ *
+ * Free mii_bus allocated with devm_mdiobus_alloc_size().
+ */
+void devm_mdiobus_free(struct device *dev, struct mii_bus *bus)
+{
+	int rc;
+
+	rc = devres_release(dev, _devm_mdiobus_free,
+			    devm_mdiobus_match, bus);
+	WARN_ON(rc);
+}
+EXPORT_SYMBOL_GPL(devm_mdiobus_free);
+
 /**
  * mdiobus_release - mii_bus device release callback
  * @d: the target struct device that contains the mii_bus
@@ -120,6 +187,50 @@ struct mii_bus *of_mdio_find_bus(struct device_node *mdio_bus_np)
 	return d ? to_mii_bus(d) : NULL;
 }
 EXPORT_SYMBOL(of_mdio_find_bus);
+
+/* Walk the list of subnodes of a mdio bus and look for a node that matches the
+ * phy's address with its 'reg' property. If found, set the of_node pointer for
+ * the phy. This allows auto-probed pyh devices to be supplied with information
+ * passed in via DT.
+ */
+static void of_mdiobus_link_phydev(struct mii_bus *mdio,
+				   struct phy_device *phydev)
+{
+	struct device *dev = &phydev->dev;
+	struct device_node *child;
+
+	if (dev->of_node || !mdio->dev.of_node)
+		return;
+
+	for_each_available_child_of_node(mdio->dev.of_node, child) {
+		int addr;
+		int ret;
+
+		ret = of_property_read_u32(child, "reg", &addr);
+		if (ret < 0) {
+			dev_err(dev, "%s has invalid PHY address\n",
+				child->full_name);
+			continue;
+		}
+
+		/* A PHY must have a reg property in the range [0-31] */
+		if (addr >= PHY_MAX_ADDR) {
+			dev_err(dev, "%s PHY address %i is too large\n",
+				child->full_name, addr);
+			continue;
+		}
+
+		if (addr == phydev->addr) {
+			dev->of_node = child;
+			return;
+		}
+	}
+}
+#else /* !IS_ENABLED(CONFIG_OF_MDIO) */
+static inline void of_mdiobus_link_phydev(struct mii_bus *mdio,
+					  struct phy_device *phydev)
+{
+}
 #endif
 
 /**
@@ -144,6 +255,7 @@ int mdiobus_register(struct mii_bus *bus)
 
 	bus->dev.parent = bus->parent;
 	bus->dev.class = &mdio_bus_class;
+	bus->dev.driver = bus->parent->driver;
 	bus->dev.groups = NULL;
 	dev_set_name(&bus->dev, "%s", bus->id);
 
@@ -233,6 +345,12 @@ struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr)
 	if (IS_ERR(phydev) || phydev == NULL)
 		return phydev;
 
+	/*
+	 * For DT, see if the auto-probed phy has a correspoding child
+	 * in the bus node, and set the of_node pointer in this case.
+	 */
+	of_mdiobus_link_phydev(bus, phydev);
+
 	err = phy_device_register(phydev);
 	if (err) {
 		phy_device_free(phydev);
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index d849684231c..bc7c7d2f75f 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -283,6 +283,110 @@ static int ksz9021_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+#define MII_KSZ9031RN_MMD_CTRL_REG	0x0d
+#define MII_KSZ9031RN_MMD_REGDATA_REG	0x0e
+#define OP_DATA				1
+#define KSZ9031_PS_TO_REG		60
+
+/* Extended registers */
+#define MII_KSZ9031RN_CONTROL_PAD_SKEW	4
+#define MII_KSZ9031RN_RX_DATA_PAD_SKEW	5
+#define MII_KSZ9031RN_TX_DATA_PAD_SKEW	6
+#define MII_KSZ9031RN_CLK_PAD_SKEW	8
+
+static int ksz9031_extended_write(struct phy_device *phydev,
+				  u8 mode, u32 dev_addr, u32 regnum, u16 val)
+{
+	phy_write(phydev, MII_KSZ9031RN_MMD_CTRL_REG, dev_addr);
+	phy_write(phydev, MII_KSZ9031RN_MMD_REGDATA_REG, regnum);
+	phy_write(phydev, MII_KSZ9031RN_MMD_CTRL_REG, (mode << 14) | dev_addr);
+	return phy_write(phydev, MII_KSZ9031RN_MMD_REGDATA_REG, val);
+}
+
+static int ksz9031_extended_read(struct phy_device *phydev,
+				 u8 mode, u32 dev_addr, u32 regnum)
+{
+	phy_write(phydev, MII_KSZ9031RN_MMD_CTRL_REG, dev_addr);
+	phy_write(phydev, MII_KSZ9031RN_MMD_REGDATA_REG, regnum);
+	phy_write(phydev, MII_KSZ9031RN_MMD_CTRL_REG, (mode << 14) | dev_addr);
+	return phy_read(phydev, MII_KSZ9031RN_MMD_REGDATA_REG);
+}
+
+static int ksz9031_of_load_skew_values(struct phy_device *phydev,
+				       struct device_node *of_node,
+				       u16 reg, size_t field_sz,
+				       char *field[], u8 numfields)
+{
+	int val[4] = {-1, -2, -3, -4};
+	int matches = 0;
+	u16 mask;
+	u16 maxval;
+	u16 newval;
+	int i;
+
+	for (i = 0; i < numfields; i++)
+		if (!of_property_read_u32(of_node, field[i], val + i))
+			matches++;
+
+	if (!matches)
+		return 0;
+
+	if (matches < numfields)
+		newval = ksz9031_extended_read(phydev, OP_DATA, 2, reg);
+	else
+		newval = 0;
+
+	maxval = (field_sz == 4) ? 0xf : 0x1f;
+	for (i = 0; i < numfields; i++)
+		if (val[i] != -(i + 1)) {
+			mask = 0xffff;
+			mask ^= maxval << (field_sz * i);
+			newval = (newval & mask) |
+				(((val[i] / KSZ9031_PS_TO_REG) & maxval)
+					<< (field_sz * i));
+		}
+
+	return ksz9031_extended_write(phydev, OP_DATA, 2, reg, newval);
+}
+
+static int ksz9031_config_init(struct phy_device *phydev)
+{
+	struct device *dev = &phydev->dev;
+	struct device_node *of_node = dev->of_node;
+	char *clk_skews[2] = {"rxc-skew-ps", "txc-skew-ps"};
+	char *rx_data_skews[4] = {
+		"rxd0-skew-ps", "rxd1-skew-ps",
+		"rxd2-skew-ps", "rxd3-skew-ps"
+	};
+	char *tx_data_skews[4] = {
+		"txd0-skew-ps", "txd1-skew-ps",
+		"txd2-skew-ps", "txd3-skew-ps"
+	};
+	char *control_skews[2] = {"txen-skew-ps", "rxdv-skew-ps"};
+
+	if (!of_node && dev->parent->of_node)
+		of_node = dev->parent->of_node;
+
+	if (of_node) {
+		ksz9031_of_load_skew_values(phydev, of_node,
+				MII_KSZ9031RN_CLK_PAD_SKEW, 5,
+				clk_skews, 2);
+
+		ksz9031_of_load_skew_values(phydev, of_node,
+				MII_KSZ9031RN_CONTROL_PAD_SKEW, 4,
+				control_skews, 2);
+
+		ksz9031_of_load_skew_values(phydev, of_node,
+				MII_KSZ9031RN_RX_DATA_PAD_SKEW, 4,
+				rx_data_skews, 4);
+
+		ksz9031_of_load_skew_values(phydev, of_node,
+				MII_KSZ9031RN_TX_DATA_PAD_SKEW, 4,
+				tx_data_skews, 4);
+	}
+	return 0;
+}
+
 #define KSZ8873MLL_GLOBAL_CONTROL_4	0x06
 #define KSZ8873MLL_GLOBAL_CONTROL_4_DUPLEX	(1 << 6)
 #define KSZ8873MLL_GLOBAL_CONTROL_4_SPEED	(1 << 4)
@@ -469,7 +573,7 @@ static struct phy_driver ksphy_driver[] = {
 	.features	= (PHY_GBIT_FEATURES | SUPPORTED_Pause
 				| SUPPORTED_Asym_Pause),
 	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
-	.config_init	= kszphy_config_init,
+	.config_init	= ksz9031_config_init,
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 3bc079a67a3..f7c61812ea4 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -720,6 +720,9 @@ void phy_state_machine(struct work_struct *work)
 
 	mutex_lock(&phydev->lock);
 
+	if (phydev->drv->link_change_notify)
+		phydev->drv->link_change_notify(phydev);
+
 	switch (phydev->state) {
 	case PHY_DOWN:
 	case PHY_STARTING:
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 4987a1c6dc5..22c57be4dfa 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -33,6 +33,7 @@
 #include <linux/mdio.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
+#include <linux/of.h>
 
 #include <asm/irq.h>
 
@@ -354,7 +355,7 @@ int phy_device_register(struct phy_device *phydev)
 	phydev->bus->phy_map[phydev->addr] = phydev;
 
 	/* Run all of the fixups for this PHY */
-	err = phy_init_hw(phydev);
+	err = phy_scan_fixups(phydev);
 	if (err) {
 		pr_err("PHY %d failed to initialize\n", phydev->addr);
 		goto out;
@@ -574,6 +575,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		      u32 flags, phy_interface_t interface)
 {
 	struct device *d = &phydev->dev;
+	struct module *bus_module;
 	int err;
 
 	/* Assume that if there is no driver, that it doesn't
@@ -598,6 +600,14 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		return -EBUSY;
 	}
 
+	/* Increment the bus module reference count */
+	bus_module = phydev->bus->dev.driver ?
+		     phydev->bus->dev.driver->owner : NULL;
+	if (!try_module_get(bus_module)) {
+		dev_err(&dev->dev, "failed to get the bus module\n");
+		return -EIO;
+	}
+
 	phydev->attached_dev = dev;
 	dev->phydev = phydev;
 
@@ -663,6 +673,10 @@ EXPORT_SYMBOL(phy_attach);
 void phy_detach(struct phy_device *phydev)
 {
 	int i;
+
+	if (phydev->bus->dev.driver)
+		module_put(phydev->bus->dev.driver->owner);
+
 	phydev->attached_dev->phydev = NULL;
 	phydev->attached_dev = NULL;
 	phy_suspend(phydev);
@@ -1067,14 +1081,11 @@ int genphy_soft_reset(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(genphy_soft_reset);
 
-static int genphy_config_init(struct phy_device *phydev)
+int genphy_config_init(struct phy_device *phydev)
 {
 	int val;
 	u32 features;
 
-	/* For now, I'll claim that the generic driver supports
-	 * all possible port types
-	 */
 	features = (SUPPORTED_TP | SUPPORTED_MII
 			| SUPPORTED_AUI | SUPPORTED_FIBRE |
 			SUPPORTED_BNC);
@@ -1107,8 +1118,8 @@ static int genphy_config_init(struct phy_device *phydev)
 			features |= SUPPORTED_1000baseT_Half;
 	}
 
-	phydev->supported = features;
-	phydev->advertising = features;
+	phydev->supported &= features;
+	phydev->advertising &= features;
 
 	return 0;
 }
@@ -1118,6 +1129,7 @@ static int gen10g_soft_reset(struct phy_device *phydev)
 	/* Do nothing for now */
 	return 0;
 }
+EXPORT_SYMBOL(genphy_config_init);
 
 static int gen10g_config_init(struct phy_device *phydev)
 {
@@ -1168,6 +1180,38 @@ static int gen10g_resume(struct phy_device *phydev)
 	return 0;
 }
 
+static void of_set_phy_supported(struct phy_device *phydev)
+{
+	struct device_node *node = phydev->dev.of_node;
+	u32 max_speed;
+
+	if (!IS_ENABLED(CONFIG_OF_MDIO))
+		return;
+
+	if (!node)
+		return;
+
+	if (!of_property_read_u32(node, "max-speed", &max_speed)) {
+		/* The default values for phydev->supported are provided by the PHY
+		 * driver "features" member, we want to reset to sane defaults fist
+		 * before supporting higher speeds.
+		 */
+		phydev->supported &= PHY_DEFAULT_FEATURES;
+
+		switch (max_speed) {
+		default:
+			return;
+
+		case SPEED_1000:
+			phydev->supported |= PHY_1000BT_FEATURES;
+		case SPEED_100:
+			phydev->supported |= PHY_100BT_FEATURES;
+		case SPEED_10:
+			phydev->supported |= PHY_10BT_FEATURES;
+		}
+	}
+}
+
 /**
  * phy_probe - probe and init a PHY device
  * @dev: device to probe and init
@@ -1202,7 +1246,8 @@ static int phy_probe(struct device *dev)
 	 * or both of these values
 	 */
 	phydev->supported = phydrv->features;
-	phydev->advertising = phydrv->features;
+	of_set_phy_supported(phydev);
+	phydev->advertising = phydev->supported;
 
 	/* Set the state to READY by default */
 	phydev->state = PHY_READY;
@@ -1295,7 +1340,9 @@ static struct phy_driver genphy_driver[] = {
 	.name		= "Generic PHY",
 	.soft_reset	= genphy_soft_reset,
 	.config_init	= genphy_config_init,
-	.features	= 0,
+	.features	= PHY_GBIT_FEATURES | SUPPORTED_MII |
+			  SUPPORTED_AUI | SUPPORTED_FIBRE |
+			  SUPPORTED_BNC,
 	.config_aneg	= genphy_config_aneg,
 	.aneg_done	= genphy_aneg_done,
 	.read_status	= genphy_read_status,
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index fa1d69a38cc..45483fdfbe0 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -64,65 +64,51 @@ static int rtl8211e_config_intr(struct phy_device *phydev)
 	return err;
 }
 
-/* RTL8201CP */
-static struct phy_driver rtl8201cp_driver = {
-	.phy_id         = 0x00008201,
-	.name           = "RTL8201CP Ethernet",
-	.phy_id_mask    = 0x0000ffff,
-	.features       = PHY_BASIC_FEATURES,
-	.flags          = PHY_HAS_INTERRUPT,
-	.config_aneg    = &genphy_config_aneg,
-	.read_status    = &genphy_read_status,
-	.driver         = { .owner = THIS_MODULE,},
-};
-
-/* RTL8211B */
-static struct phy_driver rtl8211b_driver = {
-	.phy_id		= 0x001cc912,
-	.name		= "RTL8211B Gigabit Ethernet",
-	.phy_id_mask	= 0x001fffff,
-	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
-	.config_aneg	= &genphy_config_aneg,
-	.read_status	= &genphy_read_status,
-	.ack_interrupt	= &rtl821x_ack_interrupt,
-	.config_intr	= &rtl8211b_config_intr,
-	.driver		= { .owner = THIS_MODULE,},
-};
-
-/* RTL8211E */
-static struct phy_driver rtl8211e_driver = {
-	.phy_id		= 0x001cc915,
-	.name		= "RTL8211E Gigabit Ethernet",
-	.phy_id_mask	= 0x001fffff,
-	.features	= PHY_GBIT_FEATURES,
-	.flags		= PHY_HAS_INTERRUPT,
-	.config_aneg	= &genphy_config_aneg,
-	.read_status	= &genphy_read_status,
-	.ack_interrupt	= &rtl821x_ack_interrupt,
-	.config_intr	= &rtl8211e_config_intr,
-	.suspend	= genphy_suspend,
-	.resume		= genphy_resume,
-	.driver		= { .owner = THIS_MODULE,},
+static struct phy_driver realtek_drvs[] = {
+	{
+		.phy_id         = 0x00008201,
+		.name           = "RTL8201CP Ethernet",
+		.phy_id_mask    = 0x0000ffff,
+		.features       = PHY_BASIC_FEATURES,
+		.flags          = PHY_HAS_INTERRUPT,
+		.config_aneg    = &genphy_config_aneg,
+		.read_status    = &genphy_read_status,
+		.driver         = { .owner = THIS_MODULE,},
+	}, {
+		.phy_id		= 0x001cc912,
+		.name		= "RTL8211B Gigabit Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_GBIT_FEATURES,
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_aneg	= &genphy_config_aneg,
+		.read_status	= &genphy_read_status,
+		.ack_interrupt	= &rtl821x_ack_interrupt,
+		.config_intr	= &rtl8211b_config_intr,
+		.driver		= { .owner = THIS_MODULE,},
+	}, {
+		.phy_id		= 0x001cc915,
+		.name		= "RTL8211E Gigabit Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_GBIT_FEATURES,
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_aneg	= &genphy_config_aneg,
+		.read_status	= &genphy_read_status,
+		.ack_interrupt	= &rtl821x_ack_interrupt,
+		.config_intr	= &rtl8211e_config_intr,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.driver		= { .owner = THIS_MODULE,},
+	},
 };
 
 static int __init realtek_init(void)
 {
-	int ret;
-
-	ret = phy_driver_register(&rtl8201cp_driver);
-	if (ret < 0)
-		return -ENODEV;
-	ret = phy_driver_register(&rtl8211b_driver);
-	if (ret < 0)
-		return -ENODEV;
-	return phy_driver_register(&rtl8211e_driver);
+	return phy_drivers_register(realtek_drvs, ARRAY_SIZE(realtek_drvs));
 }
 
 static void __exit realtek_exit(void)
 {
-	phy_driver_unregister(&rtl8211b_driver);
-	phy_driver_unregister(&rtl8211e_driver);
+	phy_drivers_unregister(realtek_drvs, ARRAY_SIZE(realtek_drvs));
 }
 
 module_init(realtek_init);
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 11f34813e23..180c49479c4 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -249,8 +249,7 @@ static int __init smsc_init(void)
 
 static void __exit smsc_exit(void)
 {
-	return phy_drivers_unregister(smsc_phy_driver,
-		ARRAY_SIZE(smsc_phy_driver));
+	phy_drivers_unregister(smsc_phy_driver, ARRAY_SIZE(smsc_phy_driver));
 }
 
 MODULE_DESCRIPTION("SMSC PHY driver");
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 14372c65a7e..5dc0935da99 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -319,8 +319,7 @@ static int __init vsc82xx_init(void)
 
 static void __exit vsc82xx_exit(void)
 {
-	return phy_drivers_unregister(vsc82xx_driver,
-		ARRAY_SIZE(vsc82xx_driver));
+	phy_drivers_unregister(vsc82xx_driver, ARRAY_SIZE(vsc82xx_driver));
 }
 
 module_init(vsc82xx_init);
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index e3923ebb693..d5b77ef3a21 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -539,7 +539,7 @@ static int get_filter(void __user *arg, struct sock_filter **p)
 {
 	struct sock_fprog uprog;
 	struct sock_filter *code = NULL;
-	int len, err;
+	int len;
 
 	if (copy_from_user(&uprog, arg, sizeof(uprog)))
 		return -EFAULT;
@@ -554,12 +554,6 @@ static int get_filter(void __user *arg, struct sock_filter **p)
 	if (IS_ERR(code))
 		return PTR_ERR(code);
 
-	err = sk_chk_filter(code, uprog.len);
-	if (err) {
-		kfree(code);
-		return err;
-	}
-
 	*p = code;
 	return uprog.len;
 }
@@ -757,16 +751,21 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 		err = get_filter(argp, &code);
 		if (err >= 0) {
-			struct sock_fprog fprog = {
+			struct sock_fprog_kern fprog = {
 				.len = err,
 				.filter = code,
 			};
 
 			ppp_lock(ppp);
-			if (ppp->pass_filter)
+			if (ppp->pass_filter) {
 				sk_unattached_filter_destroy(ppp->pass_filter);
-			err = sk_unattached_filter_create(&ppp->pass_filter,
-							  &fprog);
+				ppp->pass_filter = NULL;
+			}
+			if (fprog.filter != NULL)
+				err = sk_unattached_filter_create(&ppp->pass_filter,
+								  &fprog);
+			else
+				err = 0;
 			kfree(code);
 			ppp_unlock(ppp);
 		}
@@ -778,16 +777,21 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 		err = get_filter(argp, &code);
 		if (err >= 0) {
-			struct sock_fprog fprog = {
+			struct sock_fprog_kern fprog = {
 				.len = err,
 				.filter = code,
 			};
 
 			ppp_lock(ppp);
-			if (ppp->active_filter)
+			if (ppp->active_filter) {
 				sk_unattached_filter_destroy(ppp->active_filter);
-			err = sk_unattached_filter_create(&ppp->active_filter,
-							  &fprog);
+				ppp->active_filter = NULL;
+			}
+			if (fprog.filter != NULL)
+				err = sk_unattached_filter_create(&ppp->active_filter,
+								  &fprog);
+			else
+				err = 0;
 			kfree(code);
 			ppp_unlock(ppp);
 		}
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 2ea7efd1185..6c9c16d7693 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -675,7 +675,7 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 		po->chan.hdrlen = (sizeof(struct pppoe_hdr) +
 				   dev->hard_header_len);
 
-		po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr);
+		po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2;
 		po->chan.private = sk;
 		po->chan.ops = &pppoe_chan_ops;
 
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 01805319e1e..1aff970be33 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	nf_reset(skb);
 
 	skb->ip_summed = CHECKSUM_NONE;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	ip_send_check(iph);
 
 	ip_local_out(skb);
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index a8497183ff8..dac7a0d9bb4 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -494,7 +494,7 @@ static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev)
 	ndev->mtu = RIO_MAX_MSG_SIZE - 14;
 	ndev->features = NETIF_F_LLTX;
 	SET_NETDEV_DEV(ndev, &mport->dev);
-	SET_ETHTOOL_OPS(ndev, &rionet_ethtool_ops);
+	ndev->ethtool_ops = &rionet_ethtool_ops;
 
 	spin_lock_init(&rnet->lock);
 	spin_lock_init(&rnet->tx_lock);
diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c
index ad4a94e9ff5..87526443841 100644
--- a/drivers/net/slip/slip.c
+++ b/drivers/net/slip/slip.c
@@ -83,6 +83,7 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/workqueue.h>
 #include "slip.h"
 #ifdef CONFIG_INET
 #include <linux/ip.h>
@@ -416,36 +417,46 @@ static void sl_encaps(struct slip *sl, unsigned char *icp, int len)
 #endif
 }
 
-/*
- * Called by the driver when there's room for more data.  If we have
- * more packets to send, we send them here.
- */
-static void slip_write_wakeup(struct tty_struct *tty)
+/* Write out any remaining transmit buffer. Scheduled when tty is writable */
+static void slip_transmit(struct work_struct *work)
 {
+	struct slip *sl = container_of(work, struct slip, tx_work);
 	int actual;
-	struct slip *sl = tty->disc_data;
 
+	spin_lock_bh(&sl->lock);
 	/* First make sure we're connected. */
-	if (!sl || sl->magic != SLIP_MAGIC || !netif_running(sl->dev))
+	if (!sl->tty || sl->magic != SLIP_MAGIC || !netif_running(sl->dev)) {
+		spin_unlock_bh(&sl->lock);
 		return;
+	}
 
-	spin_lock_bh(&sl->lock);
 	if (sl->xleft <= 0)  {
 		/* Now serial buffer is almost free & we can start
 		 * transmission of another packet */
 		sl->dev->stats.tx_packets++;
-		clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
+		clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags);
 		spin_unlock_bh(&sl->lock);
 		sl_unlock(sl);
 		return;
 	}
 
-	actual = tty->ops->write(tty, sl->xhead, sl->xleft);
+	actual = sl->tty->ops->write(sl->tty, sl->xhead, sl->xleft);
 	sl->xleft -= actual;
 	sl->xhead += actual;
 	spin_unlock_bh(&sl->lock);
 }
 
+/*
+ * Called by the driver when there's room for more data.
+ * Schedule the transmit.
+ */
+static void slip_write_wakeup(struct tty_struct *tty)
+{
+	struct slip *sl = tty->disc_data;
+
+	schedule_work(&sl->tx_work);
+}
+
 static void sl_tx_timeout(struct net_device *dev)
 {
 	struct slip *sl = netdev_priv(dev);
@@ -749,6 +760,7 @@ static struct slip *sl_alloc(dev_t line)
 	sl->magic       = SLIP_MAGIC;
 	sl->dev	      	= dev;
 	spin_lock_init(&sl->lock);
+	INIT_WORK(&sl->tx_work, slip_transmit);
 	sl->mode        = SL_MODE_DEFAULT;
 #ifdef CONFIG_SLIP_SMART
 	/* initialize timer_list struct */
@@ -872,8 +884,12 @@ static void slip_close(struct tty_struct *tty)
 	if (!sl || sl->magic != SLIP_MAGIC || sl->tty != tty)
 		return;
 
+	spin_lock_bh(&sl->lock);
 	tty->disc_data = NULL;
 	sl->tty = NULL;
+	spin_unlock_bh(&sl->lock);
+
+	flush_work(&sl->tx_work);
 
 	/* VSV = very important to remove timers */
 #ifdef CONFIG_SLIP_SMART
diff --git a/drivers/net/slip/slip.h b/drivers/net/slip/slip.h
index 67673cf1266..cf32aadf508 100644
--- a/drivers/net/slip/slip.h
+++ b/drivers/net/slip/slip.h
@@ -53,6 +53,7 @@ struct slip {
   struct tty_struct	*tty;		/* ptr to TTY structure		*/
   struct net_device	*dev;		/* easy for intr handling	*/
   spinlock_t		lock;
+  struct work_struct	tx_work;	/* Flushes transmit buffer	*/
 
 #ifdef SL_INCLUDE_CSLIP
   struct slcompress	*slcomp;	/* for header compression 	*/
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index ce4989be86d..b4958c7ffa8 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -968,7 +968,7 @@ static void team_port_disable(struct team *team,
 static void __team_compute_features(struct team *team)
 {
 	struct team_port *port;
-	u32 vlan_features = TEAM_VLAN_FEATURES;
+	u32 vlan_features = TEAM_VLAN_FEATURES & NETIF_F_ALL_FOR_ALL;
 	unsigned short max_hard_header_len = ETH_HLEN;
 	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
 
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index dbde3412ee5..a58dfebb551 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -49,7 +49,7 @@ struct lb_port_mapping {
 struct lb_priv_ex {
 	struct team *team;
 	struct lb_port_mapping tx_hash_to_port_mapping[LB_TX_HASHTABLE_SIZE];
-	struct sock_fprog *orig_fprog;
+	struct sock_fprog_kern *orig_fprog;
 	struct {
 		unsigned int refresh_interval; /* in tenths of second */
 		struct delayed_work refresh_dw;
@@ -241,15 +241,15 @@ static int lb_bpf_func_get(struct team *team, struct team_gsetter_ctx *ctx)
 	return 0;
 }
 
-static int __fprog_create(struct sock_fprog **pfprog, u32 data_len,
+static int __fprog_create(struct sock_fprog_kern **pfprog, u32 data_len,
 			  const void *data)
 {
-	struct sock_fprog *fprog;
+	struct sock_fprog_kern *fprog;
 	struct sock_filter *filter = (struct sock_filter *) data;
 
 	if (data_len % sizeof(struct sock_filter))
 		return -EINVAL;
-	fprog = kmalloc(sizeof(struct sock_fprog), GFP_KERNEL);
+	fprog = kmalloc(sizeof(*fprog), GFP_KERNEL);
 	if (!fprog)
 		return -ENOMEM;
 	fprog->filter = kmemdup(filter, data_len, GFP_KERNEL);
@@ -262,7 +262,7 @@ static int __fprog_create(struct sock_fprog **pfprog, u32 data_len,
 	return 0;
 }
 
-static void __fprog_destroy(struct sock_fprog *fprog)
+static void __fprog_destroy(struct sock_fprog_kern *fprog)
 {
 	kfree(fprog->filter);
 	kfree(fprog);
@@ -273,7 +273,7 @@ static int lb_bpf_func_set(struct team *team, struct team_gsetter_ctx *ctx)
 	struct lb_priv *lb_priv = get_lb_priv(team);
 	struct sk_filter *fp = NULL;
 	struct sk_filter *orig_fp;
-	struct sock_fprog *fprog = NULL;
+	struct sock_fprog_kern *fprog = NULL;
 	int err;
 
 	if (ctx->data.bin_val.len) {
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ee328ba101e..98bad1fb1bf 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -498,12 +498,12 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		BUG_ON(!tfile);
-		wake_up_all(&tfile->wq.wait);
+		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 		--tun->numqueues;
 	}
 	list_for_each_entry(tfile, &tun->disabled, next) {
-		wake_up_all(&tfile->wq.wait);
+		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
 	}
 	BUG_ON(tun->numqueues != 0);
@@ -807,8 +807,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Notify and wake up reader process */
 	if (tfile->flags & TUN_FASYNC)
 		kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
-	wake_up_interruptible_poll(&tfile->wq.wait, POLLIN |
-				   POLLRDNORM | POLLRDBAND);
+	tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 
 	rcu_read_unlock();
 	return NETDEV_TX_OK;
@@ -965,7 +964,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
 
 	tun_debug(KERN_INFO, tun, "tun_chr_poll\n");
 
-	poll_wait(file, &tfile->wq.wait, wait);
+	poll_wait(file, sk_sleep(sk), wait);
 
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		mask |= POLLIN | POLLRDNORM;
@@ -1330,47 +1329,26 @@ done:
 static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
 			   const struct iovec *iv, ssize_t len, int noblock)
 {
-	DECLARE_WAITQUEUE(wait, current);
 	struct sk_buff *skb;
 	ssize_t ret = 0;
+	int peeked, err, off = 0;
 
 	tun_debug(KERN_INFO, tun, "tun_do_read\n");
 
-	if (unlikely(!noblock))
-		add_wait_queue(&tfile->wq.wait, &wait);
-	while (len) {
-		if (unlikely(!noblock))
-			current->state = TASK_INTERRUPTIBLE;
+	if (!len)
+		return ret;
 
-		/* Read frames from the queue */
-		if (!(skb = skb_dequeue(&tfile->socket.sk->sk_receive_queue))) {
-			if (noblock) {
-				ret = -EAGAIN;
-				break;
-			}
-			if (signal_pending(current)) {
-				ret = -ERESTARTSYS;
-				break;
-			}
-			if (tun->dev->reg_state != NETREG_REGISTERED) {
-				ret = -EIO;
-				break;
-			}
-
-			/* Nothing to read, let's sleep */
-			schedule();
-			continue;
-		}
+	if (tun->dev->reg_state != NETREG_REGISTERED)
+		return -EIO;
 
+	/* Read frames from queue */
+	skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0,
+				  &peeked, &off, &err);
+	if (skb) {
 		ret = tun_put_user(tun, tfile, skb, iv, len);
 		kfree_skb(skb);
-		break;
-	}
-
-	if (unlikely(!noblock)) {
-		current->state = TASK_RUNNING;
-		remove_wait_queue(&tfile->wq.wait, &wait);
-	}
+	} else
+		ret = err;
 
 	return ret;
 }
@@ -2199,8 +2177,8 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 	tfile->flags = 0;
 	tfile->ifindex = 0;
 
-	rcu_assign_pointer(tfile->socket.wq, &tfile->wq);
 	init_waitqueue_head(&tfile->wq.wait);
+	RCU_INIT_POINTER(tfile->socket.wq, &tfile->wq);
 
 	tfile->socket.file = file;
 	tfile->socket.ops = &tun_socket_ops;
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 630caf48f63..8cfc3bb0c6a 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -793,7 +793,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 
 	netdev->netdev_ops = &catc_netdev_ops;
 	netdev->watchdog_timeo = TX_TIMEOUT;
-	SET_ETHTOOL_OPS(netdev, &ops);
+	netdev->ethtool_ops = &ops;
 
 	catc->usbdev = usbdev;
 	catc->netdev = netdev;
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 9ea4bfe5d31..2a32d9167d3 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -341,6 +341,22 @@ next_desc:
 		usb_driver_release_interface(driver, info->data);
 		return -ENODEV;
 	}
+
+	/* Some devices don't initialise properly. In particular
+	 * the packet filter is not reset. There are devices that
+	 * don't do reset all the way. So the packet filter should
+	 * be set to a sane initial value.
+	 */
+	usb_control_msg(dev->udev,
+			usb_sndctrlpipe(dev->udev, 0),
+			USB_CDC_SET_ETHERNET_PACKET_FILTER,
+			USB_TYPE_CLASS | USB_RECIP_INTERFACE,
+			USB_CDC_PACKET_TYPE_ALL_MULTICAST | USB_CDC_PACKET_TYPE_DIRECTED | USB_CDC_PACKET_TYPE_BROADCAST,
+			intf->cur_altsetting->desc.bInterfaceNumber,
+			NULL,
+			0,
+			USB_CTRL_SET_TIMEOUT
+		);
 	return 0;
 
 bad_desc:
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 2e025ddcef2..5ee7a1dbc02 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -24,13 +24,21 @@
 #include <net/ipv6.h>
 #include <net/addrconf.h>
 
+/* alternative VLAN for IP session 0 if not untagged */
+#define MBIM_IPS0_VID	4094
+
 /* driver specific data - must match cdc_ncm usage */
 struct cdc_mbim_state {
 	struct cdc_ncm_ctx *ctx;
 	atomic_t pmcount;
 	struct usb_driver *subdriver;
-	struct usb_interface *control;
-	struct usb_interface *data;
+	unsigned long _unused;
+	unsigned long flags;
+};
+
+/* flags for the cdc_mbim_state.flags field */
+enum cdc_mbim_flags {
+	FLAG_IPS0_VLAN = 1 << 0,	/* IP session 0 is tagged  */
 };
 
 /* using a counter to merge subdriver requests with our own into a combined state */
@@ -62,16 +70,91 @@ static int cdc_mbim_wdm_manage_power(struct usb_interface *intf, int status)
 	return cdc_mbim_manage_power(dev, status);
 }
 
+static int cdc_mbim_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
+{
+	struct usbnet *dev = netdev_priv(netdev);
+	struct cdc_mbim_state *info = (void *)&dev->data;
+
+	/* creation of this VLAN is a request to tag IP session 0 */
+	if (vid == MBIM_IPS0_VID)
+		info->flags |= FLAG_IPS0_VLAN;
+	else
+		if (vid >= 512)	/* we don't map these to MBIM session */
+			return -EINVAL;
+	return 0;
+}
+
+static int cdc_mbim_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
+{
+	struct usbnet *dev = netdev_priv(netdev);
+	struct cdc_mbim_state *info = (void *)&dev->data;
+
+	/* this is a request for an untagged IP session 0 */
+	if (vid == MBIM_IPS0_VID)
+		info->flags &= ~FLAG_IPS0_VLAN;
+	return 0;
+}
+
+static const struct net_device_ops cdc_mbim_netdev_ops = {
+	.ndo_open             = usbnet_open,
+	.ndo_stop             = usbnet_stop,
+	.ndo_start_xmit       = usbnet_start_xmit,
+	.ndo_tx_timeout       = usbnet_tx_timeout,
+	.ndo_change_mtu       = usbnet_change_mtu,
+	.ndo_set_mac_address  = eth_mac_addr,
+	.ndo_validate_addr    = eth_validate_addr,
+	.ndo_vlan_rx_add_vid  = cdc_mbim_rx_add_vid,
+	.ndo_vlan_rx_kill_vid = cdc_mbim_rx_kill_vid,
+};
+
+/* Change the control interface altsetting and update the .driver_info
+ * pointer if the matching entry after changing class codes points to
+ * a different struct
+ */
+static int cdc_mbim_set_ctrlalt(struct usbnet *dev, struct usb_interface *intf, u8 alt)
+{
+	struct usb_driver *driver = to_usb_driver(intf->dev.driver);
+	const struct usb_device_id *id;
+	struct driver_info *info;
+	int ret;
+
+	ret = usb_set_interface(dev->udev,
+				intf->cur_altsetting->desc.bInterfaceNumber,
+				alt);
+	if (ret)
+		return ret;
+
+	id = usb_match_id(intf, driver->id_table);
+	if (!id)
+		return -ENODEV;
+
+	info = (struct driver_info *)id->driver_info;
+	if (info != dev->driver_info) {
+		dev_dbg(&intf->dev, "driver_info updated to '%s'\n",
+			info->description);
+		dev->driver_info = info;
+	}
+	return 0;
+}
 
 static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	struct cdc_ncm_ctx *ctx;
 	struct usb_driver *subdriver = ERR_PTR(-ENODEV);
 	int ret = -ENODEV;
-	u8 data_altsetting = cdc_ncm_select_altsetting(dev, intf);
+	u8 data_altsetting = 1;
 	struct cdc_mbim_state *info = (void *)&dev->data;
 
-	/* Probably NCM, defer for cdc_ncm_bind */
+	/* should we change control altsetting on a NCM/MBIM function? */
+	if (cdc_ncm_select_altsetting(intf) == CDC_NCM_COMM_ALTSETTING_MBIM) {
+		data_altsetting = CDC_NCM_DATA_ALTSETTING_MBIM;
+		ret = cdc_mbim_set_ctrlalt(dev, intf, CDC_NCM_COMM_ALTSETTING_MBIM);
+		if (ret)
+			goto err;
+		ret = -ENODEV;
+	}
+
+	/* we will hit this for NCM/MBIM functions if prefer_mbim is false */
 	if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
 		goto err;
 
@@ -101,7 +184,10 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->flags |= IFF_NOARP;
 
 	/* no need to put the VLAN tci in the packet headers */
-	dev->net->features |= NETIF_F_HW_VLAN_CTAG_TX;
+	dev->net->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	/* monitor VLAN additions and removals */
+	dev->net->netdev_ops = &cdc_mbim_netdev_ops;
 err:
 	return ret;
 }
@@ -164,12 +250,24 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 			skb_pull(skb, ETH_HLEN);
 		}
 
+		/* Is IP session <0> tagged too? */
+		if (info->flags & FLAG_IPS0_VLAN) {
+			/* drop all untagged packets */
+			if (!tci)
+				goto error;
+			/* map MBIM_IPS0_VID to IPS<0> */
+			if (tci == MBIM_IPS0_VID)
+				tci = 0;
+		}
+
 		/* mapping VLANs to MBIM sessions:
-		 *   no tag     => IPS session <0>
+		 *   no tag     => IPS session <0> if !FLAG_IPS0_VLAN
 		 *   1 - 255    => IPS session <vlanid>
 		 *   256 - 511  => DSS session <vlanid - 256>
-		 *   512 - 4095 => unsupported, drop
+		 *   512 - 4093 => unsupported, drop
+		 *   4094       => IPS session <0> if FLAG_IPS0_VLAN
 		 */
+
 		switch (tci & 0x0f00) {
 		case 0x0000: /* VLAN ID 0 - 255 */
 			if (!is_ip)
@@ -178,6 +276,8 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 			c[3] = tci;
 			break;
 		case 0x0100: /* VLAN ID 256 - 511 */
+			if (is_ip)
+				goto error;
 			sign = cpu_to_le32(USB_CDC_MBIM_NDP16_DSS_SIGN);
 			c = (u8 *)&sign;
 			c[3] = tci;
@@ -223,8 +323,8 @@ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci)
 	/* need to send the NA on the VLAN dev, if any */
 	rcu_read_lock();
 	if (tci) {
-		netdev = __vlan_find_dev_deep(dev->net, htons(ETH_P_8021Q),
-					      tci);
+		netdev = __vlan_find_dev_deep_rcu(dev->net, htons(ETH_P_8021Q),
+						  tci);
 		if (!netdev) {
 			rcu_read_unlock();
 			return;
@@ -268,7 +368,7 @@ static struct sk_buff *cdc_mbim_process_dgram(struct usbnet *dev, u8 *buf, size_
 	__be16 proto = htons(ETH_P_802_3);
 	struct sk_buff *skb = NULL;
 
-	if (tci < 256) { /* IPS session? */
+	if (tci < 256 || tci == MBIM_IPS0_VID) { /* IPS session? */
 		if (len < sizeof(struct iphdr))
 			goto err;
 
@@ -320,6 +420,7 @@ static int cdc_mbim_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in)
 	struct usb_cdc_ncm_dpe16 *dpe16;
 	int ndpoffset;
 	int loopcount = 50; /* arbitrary max preventing infinite loop */
+	u32 payload = 0;
 	u8 *c;
 	u16 tci;
 
@@ -338,6 +439,9 @@ next_ndp:
 	case cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN):
 		c = (u8 *)&ndp16->dwSignature;
 		tci = c[3];
+		/* tag IPS<0> packets too if MBIM_IPS0_VID exists */
+		if (!tci && info->flags & FLAG_IPS0_VLAN)
+			tci = MBIM_IPS0_VID;
 		break;
 	case cpu_to_le32(USB_CDC_MBIM_NDP16_DSS_SIGN):
 		c = (u8 *)&ndp16->dwSignature;
@@ -379,6 +483,7 @@ next_ndp:
 			if (!skb)
 				goto error;
 			usbnet_skb_return(dev, skb);
+			payload += len;	/* count payload bytes in this NTB */
 		}
 	}
 err_ndp:
@@ -387,6 +492,10 @@ err_ndp:
 	if (ndpoffset && loopcount--)
 		goto next_ndp;
 
+	/* update stats */
+	ctx->rx_overhead += skb_in->len - payload;
+	ctx->rx_ntbs++;
+
 	return 1;
 error:
 	return 0;
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 9a2bd11943e..80a844e0ae0 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -65,19 +65,384 @@ static void cdc_ncm_tx_timeout_start(struct cdc_ncm_ctx *ctx);
 static enum hrtimer_restart cdc_ncm_tx_timer_cb(struct hrtimer *hr_timer);
 static struct usb_driver cdc_ncm_driver;
 
-static int cdc_ncm_setup(struct usbnet *dev)
+struct cdc_ncm_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int sizeof_stat;
+	int stat_offset;
+};
+
+#define CDC_NCM_STAT(str, m) { \
+		.stat_string = str, \
+		.sizeof_stat = sizeof(((struct cdc_ncm_ctx *)0)->m), \
+		.stat_offset = offsetof(struct cdc_ncm_ctx, m) }
+#define CDC_NCM_SIMPLE_STAT(m)	CDC_NCM_STAT(__stringify(m), m)
+
+static const struct cdc_ncm_stats cdc_ncm_gstrings_stats[] = {
+	CDC_NCM_SIMPLE_STAT(tx_reason_ntb_full),
+	CDC_NCM_SIMPLE_STAT(tx_reason_ndp_full),
+	CDC_NCM_SIMPLE_STAT(tx_reason_timeout),
+	CDC_NCM_SIMPLE_STAT(tx_reason_max_datagram),
+	CDC_NCM_SIMPLE_STAT(tx_overhead),
+	CDC_NCM_SIMPLE_STAT(tx_ntbs),
+	CDC_NCM_SIMPLE_STAT(rx_overhead),
+	CDC_NCM_SIMPLE_STAT(rx_ntbs),
+};
+
+static int cdc_ncm_get_sset_count(struct net_device __always_unused *netdev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(cdc_ncm_gstrings_stats);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void cdc_ncm_get_ethtool_stats(struct net_device *netdev,
+				    struct ethtool_stats __always_unused *stats,
+				    u64 *data)
+{
+	struct usbnet *dev = netdev_priv(netdev);
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	int i;
+	char *p = NULL;
+
+	for (i = 0; i < ARRAY_SIZE(cdc_ncm_gstrings_stats); i++) {
+		p = (char *)ctx + cdc_ncm_gstrings_stats[i].stat_offset;
+		data[i] = (cdc_ncm_gstrings_stats[i].sizeof_stat == sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
+	}
+}
+
+static void cdc_ncm_get_strings(struct net_device __always_unused *netdev, u32 stringset, u8 *data)
+{
+	u8 *p = data;
+	int i;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_SIZE(cdc_ncm_gstrings_stats); i++) {
+			memcpy(p, cdc_ncm_gstrings_stats[i].stat_string, ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+	}
+}
+
+static void cdc_ncm_update_rxtx_max(struct usbnet *dev, u32 new_rx, u32 new_tx);
+
+static const struct ethtool_ops cdc_ncm_ethtool_ops = {
+	.get_settings      = usbnet_get_settings,
+	.set_settings      = usbnet_set_settings,
+	.get_link          = usbnet_get_link,
+	.nway_reset        = usbnet_nway_reset,
+	.get_drvinfo       = usbnet_get_drvinfo,
+	.get_msglevel      = usbnet_get_msglevel,
+	.set_msglevel      = usbnet_set_msglevel,
+	.get_ts_info       = ethtool_op_get_ts_info,
+	.get_sset_count    = cdc_ncm_get_sset_count,
+	.get_strings       = cdc_ncm_get_strings,
+	.get_ethtool_stats = cdc_ncm_get_ethtool_stats,
+};
+
+static u32 cdc_ncm_check_rx_max(struct usbnet *dev, u32 new_rx)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	u32 val, max, min;
+
+	/* clamp new_rx to sane values */
+	min = USB_CDC_NCM_NTB_MIN_IN_SIZE;
+	max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_RX, le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize));
+
+	/* dwNtbInMaxSize spec violation? Use MIN size for both limits */
+	if (max < min) {
+		dev_warn(&dev->intf->dev, "dwNtbInMaxSize=%u is too small. Using %u\n",
+			 le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize), min);
+		max = min;
+	}
+
+	val = clamp_t(u32, new_rx, min, max);
+	if (val != new_rx)
+		dev_dbg(&dev->intf->dev, "rx_max must be in the [%u, %u] range\n", min, max);
+
+	return val;
+}
+
+static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	u32 val, max, min;
+
+	/* clamp new_tx to sane values */
+	min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth16);
+	max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize));
+
+	/* some devices set dwNtbOutMaxSize too low for the above default */
+	min = min(min, max);
+
+	val = clamp_t(u32, new_tx, min, max);
+	if (val != new_tx)
+		dev_dbg(&dev->intf->dev, "tx_max must be in the [%u, %u] range\n", min, max);
+
+	return val;
+}
+
+static ssize_t cdc_ncm_show_min_tx_pkt(struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+
+	return sprintf(buf, "%u\n", ctx->min_tx_pkt);
+}
+
+static ssize_t cdc_ncm_show_rx_max(struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+
+	return sprintf(buf, "%u\n", ctx->rx_max);
+}
+
+static ssize_t cdc_ncm_show_tx_max(struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+
+	return sprintf(buf, "%u\n", ctx->tx_max);
+}
+
+static ssize_t cdc_ncm_show_tx_timer_usecs(struct device *d, struct device_attribute *attr, char *buf)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+
+	return sprintf(buf, "%u\n", ctx->timer_interval / (u32)NSEC_PER_USEC);
+}
+
+static ssize_t cdc_ncm_store_min_tx_pkt(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	unsigned long val;
+
+	/* no need to restrict values - anything from 0 to infinity is OK */
+	if (kstrtoul(buf, 0, &val))
+		return -EINVAL;
+
+	ctx->min_tx_pkt = val;
+	return len;
+}
+
+static ssize_t cdc_ncm_store_rx_max(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	unsigned long val;
+
+	if (kstrtoul(buf, 0, &val) || cdc_ncm_check_rx_max(dev, val) != val)
+		return -EINVAL;
+
+	cdc_ncm_update_rxtx_max(dev, val, ctx->tx_max);
+	return len;
+}
+
+static ssize_t cdc_ncm_store_tx_max(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
 {
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
 	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	unsigned long val;
+
+	if (kstrtoul(buf, 0, &val) || cdc_ncm_check_tx_max(dev, val) != val)
+		return -EINVAL;
+
+	cdc_ncm_update_rxtx_max(dev, ctx->rx_max, val);
+	return len;
+}
+
+static ssize_t cdc_ncm_store_tx_timer_usecs(struct device *d,  struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct usbnet *dev = netdev_priv(to_net_dev(d));
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	ssize_t ret;
+	unsigned long val;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
+	if (val && (val < CDC_NCM_TIMER_INTERVAL_MIN || val > CDC_NCM_TIMER_INTERVAL_MAX))
+		return -EINVAL;
+
+	spin_lock_bh(&ctx->mtx);
+	ctx->timer_interval = val * NSEC_PER_USEC;
+	if (!ctx->timer_interval)
+		ctx->tx_timer_pending = 0;
+	spin_unlock_bh(&ctx->mtx);
+	return len;
+}
+
+static DEVICE_ATTR(min_tx_pkt, S_IRUGO | S_IWUSR, cdc_ncm_show_min_tx_pkt, cdc_ncm_store_min_tx_pkt);
+static DEVICE_ATTR(rx_max, S_IRUGO | S_IWUSR, cdc_ncm_show_rx_max, cdc_ncm_store_rx_max);
+static DEVICE_ATTR(tx_max, S_IRUGO | S_IWUSR, cdc_ncm_show_tx_max, cdc_ncm_store_tx_max);
+static DEVICE_ATTR(tx_timer_usecs, S_IRUGO | S_IWUSR, cdc_ncm_show_tx_timer_usecs, cdc_ncm_store_tx_timer_usecs);
+
+#define NCM_PARM_ATTR(name, format, tocpu)				\
+static ssize_t cdc_ncm_show_##name(struct device *d, struct device_attribute *attr, char *buf) \
+{ \
+	struct usbnet *dev = netdev_priv(to_net_dev(d)); \
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; \
+	return sprintf(buf, format "\n", tocpu(ctx->ncm_parm.name));	\
+} \
+static DEVICE_ATTR(name, S_IRUGO, cdc_ncm_show_##name, NULL)
+
+NCM_PARM_ATTR(bmNtbFormatsSupported, "0x%04x", le16_to_cpu);
+NCM_PARM_ATTR(dwNtbInMaxSize, "%u", le32_to_cpu);
+NCM_PARM_ATTR(wNdpInDivisor, "%u", le16_to_cpu);
+NCM_PARM_ATTR(wNdpInPayloadRemainder, "%u", le16_to_cpu);
+NCM_PARM_ATTR(wNdpInAlignment, "%u", le16_to_cpu);
+NCM_PARM_ATTR(dwNtbOutMaxSize, "%u", le32_to_cpu);
+NCM_PARM_ATTR(wNdpOutDivisor, "%u", le16_to_cpu);
+NCM_PARM_ATTR(wNdpOutPayloadRemainder, "%u", le16_to_cpu);
+NCM_PARM_ATTR(wNdpOutAlignment, "%u", le16_to_cpu);
+NCM_PARM_ATTR(wNtbOutMaxDatagrams, "%u", le16_to_cpu);
+
+static struct attribute *cdc_ncm_sysfs_attrs[] = {
+	&dev_attr_min_tx_pkt.attr,
+	&dev_attr_rx_max.attr,
+	&dev_attr_tx_max.attr,
+	&dev_attr_tx_timer_usecs.attr,
+	&dev_attr_bmNtbFormatsSupported.attr,
+	&dev_attr_dwNtbInMaxSize.attr,
+	&dev_attr_wNdpInDivisor.attr,
+	&dev_attr_wNdpInPayloadRemainder.attr,
+	&dev_attr_wNdpInAlignment.attr,
+	&dev_attr_dwNtbOutMaxSize.attr,
+	&dev_attr_wNdpOutDivisor.attr,
+	&dev_attr_wNdpOutPayloadRemainder.attr,
+	&dev_attr_wNdpOutAlignment.attr,
+	&dev_attr_wNtbOutMaxDatagrams.attr,
+	NULL,
+};
+
+static struct attribute_group cdc_ncm_sysfs_attr_group = {
+	.name = "cdc_ncm",
+	.attrs = cdc_ncm_sysfs_attrs,
+};
+
+/* handle rx_max and tx_max changes */
+static void cdc_ncm_update_rxtx_max(struct usbnet *dev, u32 new_rx, u32 new_tx)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	u8 iface_no = ctx->control->cur_altsetting->desc.bInterfaceNumber;
 	u32 val;
-	u8 flags;
-	u8 iface_no;
-	int err;
-	int eth_hlen;
-	u16 mbim_mtu;
-	u16 ntb_fmt_supported;
-	__le16 max_datagram_size;
 
-	iface_no = ctx->control->cur_altsetting->desc.bInterfaceNumber;
+	val = cdc_ncm_check_rx_max(dev, new_rx);
+
+	/* inform device about NTB input size changes */
+	if (val != ctx->rx_max) {
+		__le32 dwNtbInMaxSize = cpu_to_le32(val);
+
+		dev_info(&dev->intf->dev, "setting rx_max = %u\n", val);
+
+		/* tell device to use new size */
+		if (usbnet_write_cmd(dev, USB_CDC_SET_NTB_INPUT_SIZE,
+				     USB_TYPE_CLASS | USB_DIR_OUT
+				     | USB_RECIP_INTERFACE,
+				     0, iface_no, &dwNtbInMaxSize, 4) < 0)
+			dev_dbg(&dev->intf->dev, "Setting NTB Input Size failed\n");
+		else
+			ctx->rx_max = val;
+	}
+
+	/* usbnet use these values for sizing rx queues */
+	if (dev->rx_urb_size != ctx->rx_max) {
+		dev->rx_urb_size = ctx->rx_max;
+		if (netif_running(dev->net))
+			usbnet_unlink_rx_urbs(dev);
+	}
+
+	val = cdc_ncm_check_tx_max(dev, new_tx);
+	if (val != ctx->tx_max)
+		dev_info(&dev->intf->dev, "setting tx_max = %u\n", val);
+
+	/* Adding a pad byte here if necessary simplifies the handling
+	 * in cdc_ncm_fill_tx_frame, making tx_max always represent
+	 * the real skb max size.
+	 *
+	 * We cannot use dev->maxpacket here because this is called from
+	 * .bind which is called before usbnet sets up dev->maxpacket
+	 */
+	if (val != le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) &&
+	    val % usb_maxpacket(dev->udev, dev->out, 1) == 0)
+		val++;
+
+	/* we might need to flush any pending tx buffers if running */
+	if (netif_running(dev->net) && val > ctx->tx_max) {
+		netif_tx_lock_bh(dev->net);
+		usbnet_start_xmit(NULL, dev->net);
+		/* make sure tx_curr_skb is reallocated if it was empty */
+		if (ctx->tx_curr_skb) {
+			dev_kfree_skb_any(ctx->tx_curr_skb);
+			ctx->tx_curr_skb = NULL;
+		}
+		ctx->tx_max = val;
+		netif_tx_unlock_bh(dev->net);
+	} else {
+		ctx->tx_max = val;
+	}
+
+	dev->hard_mtu = ctx->tx_max;
+
+	/* max qlen depend on hard_mtu and rx_urb_size */
+	usbnet_update_max_qlen(dev);
+
+	/* never pad more than 3 full USB packets per transfer */
+	ctx->min_tx_pkt = clamp_t(u16, ctx->tx_max - 3 * usb_maxpacket(dev->udev, dev->out, 1),
+				  CDC_NCM_MIN_TX_PKT, ctx->tx_max);
+}
+
+/* helpers for NCM and MBIM differences */
+static u8 cdc_ncm_flags(struct usbnet *dev)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+
+	if (cdc_ncm_comm_intf_is_mbim(dev->intf->cur_altsetting) && ctx->mbim_desc)
+		return ctx->mbim_desc->bmNetworkCapabilities;
+	if (ctx->func_desc)
+		return ctx->func_desc->bmNetworkCapabilities;
+	return 0;
+}
+
+static int cdc_ncm_eth_hlen(struct usbnet *dev)
+{
+	if (cdc_ncm_comm_intf_is_mbim(dev->intf->cur_altsetting))
+		return 0;
+	return ETH_HLEN;
+}
+
+static u32 cdc_ncm_min_dgram_size(struct usbnet *dev)
+{
+	if (cdc_ncm_comm_intf_is_mbim(dev->intf->cur_altsetting))
+		return CDC_MBIM_MIN_DATAGRAM_SIZE;
+	return CDC_NCM_MIN_DATAGRAM_SIZE;
+}
+
+static u32 cdc_ncm_max_dgram_size(struct usbnet *dev)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+
+	if (cdc_ncm_comm_intf_is_mbim(dev->intf->cur_altsetting) && ctx->mbim_desc)
+		return le16_to_cpu(ctx->mbim_desc->wMaxSegmentSize);
+	if (ctx->ether_desc)
+		return le16_to_cpu(ctx->ether_desc->wMaxSegmentSize);
+	return CDC_NCM_MAX_DATAGRAM_SIZE;
+}
+
+/* initial one-time device setup.  MUST be called with the data interface
+ * in altsetting 0
+ */
+static int cdc_ncm_init(struct usbnet *dev)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	u8 iface_no = ctx->control->cur_altsetting->desc.bInterfaceNumber;
+	int err;
 
 	err = usbnet_read_cmd(dev, USB_CDC_GET_NTB_PARAMETERS,
 			      USB_TYPE_CLASS | USB_DIR_IN
@@ -89,7 +454,36 @@ static int cdc_ncm_setup(struct usbnet *dev)
 		return err; /* GET_NTB_PARAMETERS is required */
 	}
 
-	/* read correct set of parameters according to device mode */
+	/* set CRC Mode */
+	if (cdc_ncm_flags(dev) & USB_CDC_NCM_NCAP_CRC_MODE) {
+		dev_dbg(&dev->intf->dev, "Setting CRC mode off\n");
+		err = usbnet_write_cmd(dev, USB_CDC_SET_CRC_MODE,
+				       USB_TYPE_CLASS | USB_DIR_OUT
+				       | USB_RECIP_INTERFACE,
+				       USB_CDC_NCM_CRC_NOT_APPENDED,
+				       iface_no, NULL, 0);
+		if (err < 0)
+			dev_err(&dev->intf->dev, "SET_CRC_MODE failed\n");
+	}
+
+	/* set NTB format, if both formats are supported.
+	 *
+	 * "The host shall only send this command while the NCM Data
+	 *  Interface is in alternate setting 0."
+	 */
+	if (le16_to_cpu(ctx->ncm_parm.bmNtbFormatsSupported) &
+						USB_CDC_NCM_NTB32_SUPPORTED) {
+		dev_dbg(&dev->intf->dev, "Setting NTB format to 16-bit\n");
+		err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT,
+				       USB_TYPE_CLASS | USB_DIR_OUT
+				       | USB_RECIP_INTERFACE,
+				       USB_CDC_NCM_NTB16_FORMAT,
+				       iface_no, NULL, 0);
+		if (err < 0)
+			dev_err(&dev->intf->dev, "SET_NTB_FORMAT failed\n");
+	}
+
+	/* set initial device values */
 	ctx->rx_max = le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize);
 	ctx->tx_max = le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize);
 	ctx->tx_remainder = le16_to_cpu(ctx->ncm_parm.wNdpOutPayloadRemainder);
@@ -97,72 +491,79 @@ static int cdc_ncm_setup(struct usbnet *dev)
 	ctx->tx_ndp_modulus = le16_to_cpu(ctx->ncm_parm.wNdpOutAlignment);
 	/* devices prior to NCM Errata shall set this field to zero */
 	ctx->tx_max_datagrams = le16_to_cpu(ctx->ncm_parm.wNtbOutMaxDatagrams);
-	ntb_fmt_supported = le16_to_cpu(ctx->ncm_parm.bmNtbFormatsSupported);
-
-	/* there are some minor differences in NCM and MBIM defaults */
-	if (cdc_ncm_comm_intf_is_mbim(ctx->control->cur_altsetting)) {
-		if (!ctx->mbim_desc)
-			return -EINVAL;
-		eth_hlen = 0;
-		flags = ctx->mbim_desc->bmNetworkCapabilities;
-		ctx->max_datagram_size = le16_to_cpu(ctx->mbim_desc->wMaxSegmentSize);
-		if (ctx->max_datagram_size < CDC_MBIM_MIN_DATAGRAM_SIZE)
-			ctx->max_datagram_size = CDC_MBIM_MIN_DATAGRAM_SIZE;
-	} else {
-		if (!ctx->func_desc)
-			return -EINVAL;
-		eth_hlen = ETH_HLEN;
-		flags = ctx->func_desc->bmNetworkCapabilities;
-		ctx->max_datagram_size = le16_to_cpu(ctx->ether_desc->wMaxSegmentSize);
-		if (ctx->max_datagram_size < CDC_NCM_MIN_DATAGRAM_SIZE)
-			ctx->max_datagram_size = CDC_NCM_MIN_DATAGRAM_SIZE;
-	}
-
-	/* common absolute max for NCM and MBIM */
-	if (ctx->max_datagram_size > CDC_NCM_MAX_DATAGRAM_SIZE)
-		ctx->max_datagram_size = CDC_NCM_MAX_DATAGRAM_SIZE;
 
 	dev_dbg(&dev->intf->dev,
 		"dwNtbInMaxSize=%u dwNtbOutMaxSize=%u wNdpOutPayloadRemainder=%u wNdpOutDivisor=%u wNdpOutAlignment=%u wNtbOutMaxDatagrams=%u flags=0x%x\n",
 		ctx->rx_max, ctx->tx_max, ctx->tx_remainder, ctx->tx_modulus,
-		ctx->tx_ndp_modulus, ctx->tx_max_datagrams, flags);
+		ctx->tx_ndp_modulus, ctx->tx_max_datagrams, cdc_ncm_flags(dev));
 
 	/* max count of tx datagrams */
 	if ((ctx->tx_max_datagrams == 0) ||
 			(ctx->tx_max_datagrams > CDC_NCM_DPT_DATAGRAMS_MAX))
 		ctx->tx_max_datagrams = CDC_NCM_DPT_DATAGRAMS_MAX;
 
-	/* verify maximum size of received NTB in bytes */
-	if (ctx->rx_max < USB_CDC_NCM_NTB_MIN_IN_SIZE) {
-		dev_dbg(&dev->intf->dev, "Using min receive length=%d\n",
-			USB_CDC_NCM_NTB_MIN_IN_SIZE);
-		ctx->rx_max = USB_CDC_NCM_NTB_MIN_IN_SIZE;
-	}
+	/* set up maximum NDP size */
+	ctx->max_ndp_size = sizeof(struct usb_cdc_ncm_ndp16) + (ctx->tx_max_datagrams + 1) * sizeof(struct usb_cdc_ncm_dpe16);
 
-	if (ctx->rx_max > CDC_NCM_NTB_MAX_SIZE_RX) {
-		dev_dbg(&dev->intf->dev, "Using default maximum receive length=%d\n",
-			CDC_NCM_NTB_MAX_SIZE_RX);
-		ctx->rx_max = CDC_NCM_NTB_MAX_SIZE_RX;
-	}
+	/* initial coalescing timer interval */
+	ctx->timer_interval = CDC_NCM_TIMER_INTERVAL_USEC * NSEC_PER_USEC;
 
-	/* inform device about NTB input size changes */
-	if (ctx->rx_max != le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize)) {
-		__le32 dwNtbInMaxSize = cpu_to_le32(ctx->rx_max);
+	return 0;
+}
 
-		err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_INPUT_SIZE,
-				       USB_TYPE_CLASS | USB_DIR_OUT
-				       | USB_RECIP_INTERFACE,
-				       0, iface_no, &dwNtbInMaxSize, 4);
-		if (err < 0)
-			dev_dbg(&dev->intf->dev, "Setting NTB Input Size failed\n");
+/* set a new max datagram size */
+static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	u8 iface_no = ctx->control->cur_altsetting->desc.bInterfaceNumber;
+	__le16 max_datagram_size;
+	u16 mbim_mtu;
+	int err;
+
+	/* set default based on descriptors */
+	ctx->max_datagram_size = clamp_t(u32, new_size,
+					 cdc_ncm_min_dgram_size(dev),
+					 CDC_NCM_MAX_DATAGRAM_SIZE);
+
+	/* inform the device about the selected Max Datagram Size? */
+	if (!(cdc_ncm_flags(dev) & USB_CDC_NCM_NCAP_MAX_DATAGRAM_SIZE))
+		goto out;
+
+	/* read current mtu value from device */
+	err = usbnet_read_cmd(dev, USB_CDC_GET_MAX_DATAGRAM_SIZE,
+			      USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE,
+			      0, iface_no, &max_datagram_size, 2);
+	if (err < 0) {
+		dev_dbg(&dev->intf->dev, "GET_MAX_DATAGRAM_SIZE failed\n");
+		goto out;
 	}
 
-	/* verify maximum size of transmitted NTB in bytes */
-	if (ctx->tx_max > CDC_NCM_NTB_MAX_SIZE_TX) {
-		dev_dbg(&dev->intf->dev, "Using default maximum transmit length=%d\n",
-			CDC_NCM_NTB_MAX_SIZE_TX);
-		ctx->tx_max = CDC_NCM_NTB_MAX_SIZE_TX;
+	if (le16_to_cpu(max_datagram_size) == ctx->max_datagram_size)
+		goto out;
+
+	max_datagram_size = cpu_to_le16(ctx->max_datagram_size);
+	err = usbnet_write_cmd(dev, USB_CDC_SET_MAX_DATAGRAM_SIZE,
+			       USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE,
+			       0, iface_no, &max_datagram_size, 2);
+	if (err < 0)
+		dev_dbg(&dev->intf->dev, "SET_MAX_DATAGRAM_SIZE failed\n");
+
+out:
+	/* set MTU to max supported by the device if necessary */
+	dev->net->mtu = min_t(int, dev->net->mtu, ctx->max_datagram_size - cdc_ncm_eth_hlen(dev));
+
+	/* do not exceed operater preferred MTU */
+	if (ctx->mbim_extended_desc) {
+		mbim_mtu = le16_to_cpu(ctx->mbim_extended_desc->wMTU);
+		if (mbim_mtu != 0 && mbim_mtu < dev->net->mtu)
+			dev->net->mtu = mbim_mtu;
 	}
+}
+
+static void cdc_ncm_fix_modulus(struct usbnet *dev)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	u32 val;
 
 	/*
 	 * verify that the structure alignment is:
@@ -199,68 +600,31 @@ static int cdc_ncm_setup(struct usbnet *dev)
 	}
 
 	/* adjust TX-remainder according to NCM specification. */
-	ctx->tx_remainder = ((ctx->tx_remainder - eth_hlen) &
+	ctx->tx_remainder = ((ctx->tx_remainder - cdc_ncm_eth_hlen(dev)) &
 			     (ctx->tx_modulus - 1));
+}
 
-	/* additional configuration */
-
-	/* set CRC Mode */
-	if (flags & USB_CDC_NCM_NCAP_CRC_MODE) {
-		err = usbnet_write_cmd(dev, USB_CDC_SET_CRC_MODE,
-				       USB_TYPE_CLASS | USB_DIR_OUT
-				       | USB_RECIP_INTERFACE,
-				       USB_CDC_NCM_CRC_NOT_APPENDED,
-				       iface_no, NULL, 0);
-		if (err < 0)
-			dev_dbg(&dev->intf->dev, "Setting CRC mode off failed\n");
-	}
-
-	/* set NTB format, if both formats are supported */
-	if (ntb_fmt_supported & USB_CDC_NCM_NTH32_SIGN) {
-		err = usbnet_write_cmd(dev, USB_CDC_SET_NTB_FORMAT,
-				       USB_TYPE_CLASS | USB_DIR_OUT
-				       | USB_RECIP_INTERFACE,
-				       USB_CDC_NCM_NTB16_FORMAT,
-				       iface_no, NULL, 0);
-		if (err < 0)
-			dev_dbg(&dev->intf->dev, "Setting NTB format to 16-bit failed\n");
-	}
-
-	/* inform the device about the selected Max Datagram Size */
-	if (!(flags & USB_CDC_NCM_NCAP_MAX_DATAGRAM_SIZE))
-		goto out;
-
-	/* read current mtu value from device */
-	err = usbnet_read_cmd(dev, USB_CDC_GET_MAX_DATAGRAM_SIZE,
-			      USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE,
-			      0, iface_no, &max_datagram_size, 2);
-	if (err < 0) {
-		dev_dbg(&dev->intf->dev, "GET_MAX_DATAGRAM_SIZE failed\n");
-		goto out;
-	}
-
-	if (le16_to_cpu(max_datagram_size) == ctx->max_datagram_size)
-		goto out;
+static int cdc_ncm_setup(struct usbnet *dev)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+	u32 def_rx, def_tx;
 
-	max_datagram_size = cpu_to_le16(ctx->max_datagram_size);
-	err = usbnet_write_cmd(dev, USB_CDC_SET_MAX_DATAGRAM_SIZE,
-			       USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE,
-			       0, iface_no, &max_datagram_size, 2);
-	if (err < 0)
-		dev_dbg(&dev->intf->dev, "SET_MAX_DATAGRAM_SIZE failed\n");
+	/* be conservative when selecting intial buffer size to
+	 * increase the number of hosts this will work for
+	 */
+	def_rx = min_t(u32, CDC_NCM_NTB_DEF_SIZE_RX,
+		       le32_to_cpu(ctx->ncm_parm.dwNtbInMaxSize));
+	def_tx = min_t(u32, CDC_NCM_NTB_DEF_SIZE_TX,
+		       le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize));
 
-out:
-	/* set MTU to max supported by the device if necessary */
-	if (dev->net->mtu > ctx->max_datagram_size - eth_hlen)
-		dev->net->mtu = ctx->max_datagram_size - eth_hlen;
+	/* clamp rx_max and tx_max and inform device */
+	cdc_ncm_update_rxtx_max(dev, def_rx, def_tx);
 
-	/* do not exceed operater preferred MTU */
-	if (ctx->mbim_extended_desc) {
-		mbim_mtu = le16_to_cpu(ctx->mbim_extended_desc->wMTU);
-		if (mbim_mtu != 0 && mbim_mtu < dev->net->mtu)
-			dev->net->mtu = mbim_mtu;
-	}
+	/* sanitize the modulus and remainder values */
+	cdc_ncm_fix_modulus(dev);
 
+	/* set max datagram size */
+	cdc_ncm_set_dgram_size(dev, cdc_ncm_max_dgram_size(dev));
 	return 0;
 }
 
@@ -424,10 +788,21 @@ advance:
 	}
 
 	/* check if we got everything */
-	if (!ctx->data || (!ctx->mbim_desc && !ctx->ether_desc)) {
-		dev_dbg(&intf->dev, "CDC descriptors missing\n");
+	if (!ctx->data) {
+		dev_dbg(&intf->dev, "CDC Union missing and no IAD found\n");
 		goto error;
 	}
+	if (cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting)) {
+		if (!ctx->mbim_desc) {
+			dev_dbg(&intf->dev, "MBIM functional descriptor missing\n");
+			goto error;
+		}
+	} else {
+		if (!ctx->ether_desc || !ctx->func_desc) {
+			dev_dbg(&intf->dev, "NCM or ECM functional descriptors missing\n");
+			goto error;
+		}
+	}
 
 	/* claim data interface, if different from control */
 	if (ctx->data != ctx->control) {
@@ -447,8 +822,8 @@ advance:
 		goto error2;
 	}
 
-	/* initialize data interface */
-	if (cdc_ncm_setup(dev))
+	/* initialize basic device settings */
+	if (cdc_ncm_init(dev))
 		goto error2;
 
 	/* configure data interface */
@@ -477,18 +852,14 @@ advance:
 		dev_info(&intf->dev, "MAC-Address: %pM\n", dev->net->dev_addr);
 	}
 
-	/* usbnet use these values for sizing tx/rx queues */
-	dev->hard_mtu = ctx->tx_max;
-	dev->rx_urb_size = ctx->rx_max;
+	/* finish setting up the device specific data */
+	cdc_ncm_setup(dev);
 
-	/* cdc_ncm_setup will override dwNtbOutMaxSize if it is
-	 * outside the sane range. Adding a pad byte here if necessary
-	 * simplifies the handling in cdc_ncm_fill_tx_frame, making
-	 * tx_max always represent the real skb max size.
-	 */
-	if (ctx->tx_max != le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize) &&
-	    ctx->tx_max % usb_maxpacket(dev->udev, dev->out, 1) == 0)
-		ctx->tx_max++;
+	/* override ethtool_ops */
+	dev->net->ethtool_ops = &cdc_ncm_ethtool_ops;
+
+	/* add our sysfs attrs */
+	dev->net->sysfs_groups[0] = &cdc_ncm_sysfs_attr_group;
 
 	return 0;
 
@@ -541,10 +912,10 @@ void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf)
 }
 EXPORT_SYMBOL_GPL(cdc_ncm_unbind);
 
-/* Select the MBIM altsetting iff it is preferred and available,
- * returning the number of the corresponding data interface altsetting
+/* Return the number of the MBIM control interface altsetting iff it
+ * is preferred and available,
  */
-u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf)
+u8 cdc_ncm_select_altsetting(struct usb_interface *intf)
 {
 	struct usb_host_interface *alt;
 
@@ -563,15 +934,15 @@ u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf)
 	 *   the rules given in section 6 (USB Device Model) of this
 	 *   specification."
 	 */
-	if (prefer_mbim && intf->num_altsetting == 2) {
+	if (intf->num_altsetting < 2)
+		return intf->cur_altsetting->desc.bAlternateSetting;
+
+	if (prefer_mbim) {
 		alt = usb_altnum_to_altsetting(intf, CDC_NCM_COMM_ALTSETTING_MBIM);
-		if (alt && cdc_ncm_comm_intf_is_mbim(alt) &&
-		    !usb_set_interface(dev->udev,
-				       intf->cur_altsetting->desc.bInterfaceNumber,
-				       CDC_NCM_COMM_ALTSETTING_MBIM))
-			return CDC_NCM_DATA_ALTSETTING_MBIM;
+		if (alt && cdc_ncm_comm_intf_is_mbim(alt))
+			return CDC_NCM_COMM_ALTSETTING_MBIM;
 	}
-	return CDC_NCM_DATA_ALTSETTING_NCM;
+	return CDC_NCM_COMM_ALTSETTING_NCM;
 }
 EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting);
 
@@ -580,12 +951,11 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 	int ret;
 
 	/* MBIM backwards compatible function? */
-	cdc_ncm_select_altsetting(dev, intf);
-	if (cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
+	if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM)
 		return -ENODEV;
 
-	/* NCM data altsetting is always 1 */
-	ret = cdc_ncm_bind_common(dev, intf, 1);
+	/* The NCM data altsetting is fixed */
+	ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM);
 
 	/*
 	 * We should get an event when network connection is "connected" or
@@ -628,7 +998,7 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_
 	cdc_ncm_align_tail(skb, ctx->tx_ndp_modulus, 0, ctx->tx_max);
 
 	/* verify that there is room for the NDP and the datagram (reserve) */
-	if ((ctx->tx_max - skb->len - reserve) < CDC_NCM_NDP_SIZE)
+	if ((ctx->tx_max - skb->len - reserve) < ctx->max_ndp_size)
 		return NULL;
 
 	/* link to it */
@@ -638,7 +1008,7 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_
 		nth16->wNdpIndex = cpu_to_le16(skb->len);
 
 	/* push a new empty NDP */
-	ndp16 = (struct usb_cdc_ncm_ndp16 *)memset(skb_put(skb, CDC_NCM_NDP_SIZE), 0, CDC_NCM_NDP_SIZE);
+	ndp16 = (struct usb_cdc_ncm_ndp16 *)memset(skb_put(skb, ctx->max_ndp_size), 0, ctx->max_ndp_size);
 	ndp16->dwSignature = sign;
 	ndp16->wLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_ndp16) + sizeof(struct usb_cdc_ncm_dpe16));
 	return ndp16;
@@ -683,6 +1053,9 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 
 		/* count total number of frames in this NTB */
 		ctx->tx_curr_frame_num = 0;
+
+		/* recent payload counter for this skb_out */
+		ctx->tx_curr_frame_payload = 0;
 	}
 
 	for (n = ctx->tx_curr_frame_num; n < ctx->tx_max_datagrams; n++) {
@@ -720,6 +1093,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 				ctx->tx_rem_sign = sign;
 				skb = NULL;
 				ready2send = 1;
+				ctx->tx_reason_ntb_full++;	/* count reason for transmitting */
 			}
 			break;
 		}
@@ -733,12 +1107,14 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 		ndp16->dpe16[index].wDatagramIndex = cpu_to_le16(skb_out->len);
 		ndp16->wLength = cpu_to_le16(ndplen + sizeof(struct usb_cdc_ncm_dpe16));
 		memcpy(skb_put(skb_out, skb->len), skb->data, skb->len);
+		ctx->tx_curr_frame_payload += skb->len;	/* count real tx payload data */
 		dev_kfree_skb_any(skb);
 		skb = NULL;
 
 		/* send now if this NDP is full */
 		if (index >= CDC_NCM_DPT_DATAGRAMS_MAX) {
 			ready2send = 1;
+			ctx->tx_reason_ndp_full++;	/* count reason for transmitting */
 			break;
 		}
 	}
@@ -758,7 +1134,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 		ctx->tx_curr_skb = skb_out;
 		goto exit_no_skb;
 
-	} else if ((n < ctx->tx_max_datagrams) && (ready2send == 0)) {
+	} else if ((n < ctx->tx_max_datagrams) && (ready2send == 0) && (ctx->timer_interval > 0)) {
 		/* wait for more frames */
 		/* push variables */
 		ctx->tx_curr_skb = skb_out;
@@ -768,11 +1144,13 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 		goto exit_no_skb;
 
 	} else {
+		if (n == ctx->tx_max_datagrams)
+			ctx->tx_reason_max_datagram++;	/* count reason for transmitting */
 		/* frame goes out */
 		/* variables will be reset at next call */
 	}
 
-	/* If collected data size is less or equal CDC_NCM_MIN_TX_PKT
+	/* If collected data size is less or equal ctx->min_tx_pkt
 	 * bytes, we send buffers as it is. If we get more data, it
 	 * would be more efficient for USB HS mobile device with DMA
 	 * engine to receive a full size NTB, than canceling DMA
@@ -782,7 +1160,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	 * a ZLP after full sized NTBs.
 	 */
 	if (!(dev->driver_info->flags & FLAG_SEND_ZLP) &&
-	    skb_out->len > CDC_NCM_MIN_TX_PKT)
+	    skb_out->len > ctx->min_tx_pkt)
 		memset(skb_put(skb_out, ctx->tx_max - skb_out->len), 0,
 		       ctx->tx_max - skb_out->len);
 	else if (skb_out->len < ctx->tx_max && (skb_out->len % dev->maxpacket) == 0)
@@ -795,11 +1173,22 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	/* return skb */
 	ctx->tx_curr_skb = NULL;
 	dev->net->stats.tx_packets += ctx->tx_curr_frame_num;
+
+	/* keep private stats: framing overhead and number of NTBs */
+	ctx->tx_overhead += skb_out->len - ctx->tx_curr_frame_payload;
+	ctx->tx_ntbs++;
+
+	/* usbnet has already counted all the framing overhead.
+	 * Adjust the stats so that the tx_bytes counter show real
+	 * payload data instead.
+	 */
+	dev->net->stats.tx_bytes -= skb_out->len - ctx->tx_curr_frame_payload;
+
 	return skb_out;
 
 exit_no_skb:
-	/* Start timer, if there is a remaining skb */
-	if (ctx->tx_curr_skb != NULL)
+	/* Start timer, if there is a remaining non-empty skb */
+	if (ctx->tx_curr_skb != NULL && n > 0)
 		cdc_ncm_tx_timeout_start(ctx);
 	return NULL;
 }
@@ -810,7 +1199,7 @@ static void cdc_ncm_tx_timeout_start(struct cdc_ncm_ctx *ctx)
 	/* start timer, if not already started */
 	if (!(hrtimer_active(&ctx->tx_timer) || atomic_read(&ctx->stop)))
 		hrtimer_start(&ctx->tx_timer,
-				ktime_set(0, CDC_NCM_TIMER_INTERVAL),
+				ktime_set(0, ctx->timer_interval),
 				HRTIMER_MODE_REL);
 }
 
@@ -835,6 +1224,7 @@ static void cdc_ncm_txpath_bh(unsigned long param)
 		cdc_ncm_tx_timeout_start(ctx);
 		spin_unlock_bh(&ctx->mtx);
 	} else if (dev->net != NULL) {
+		ctx->tx_reason_timeout++;	/* count reason for transmitting */
 		spin_unlock_bh(&ctx->mtx);
 		netif_tx_lock_bh(dev->net);
 		usbnet_start_xmit(NULL, dev->net);
@@ -970,6 +1360,7 @@ int cdc_ncm_rx_fixup(struct usbnet *dev, struct sk_buff *skb_in)
 	struct usb_cdc_ncm_dpe16 *dpe16;
 	int ndpoffset;
 	int loopcount = 50; /* arbitrary max preventing infinite loop */
+	u32 payload = 0;
 
 	ndpoffset = cdc_ncm_rx_verify_nth16(ctx, skb_in);
 	if (ndpoffset < 0)
@@ -1015,13 +1406,13 @@ next_ndp:
 			break;
 
 		} else {
-			skb = skb_clone(skb_in, GFP_ATOMIC);
+			/* create a fresh copy to reduce truesize */
+			skb = netdev_alloc_skb_ip_align(dev->net,  len);
 			if (!skb)
 				goto error;
-			skb->len = len;
-			skb->data = ((u8 *)skb_in->data) + offset;
-			skb_set_tail_pointer(skb, len);
+			memcpy(skb_put(skb, len), skb_in->data + offset, len);
 			usbnet_skb_return(dev, skb);
+			payload += len;	/* count payload bytes in this NTB */
 		}
 	}
 err_ndp:
@@ -1030,6 +1421,10 @@ err_ndp:
 	if (ndpoffset && loopcount--)
 		goto next_ndp;
 
+	/* update stats */
+	ctx->rx_overhead += skb_in->len - payload;
+	ctx->rx_ntbs++;
+
 	return 1;
 error:
 	return 0;
@@ -1049,14 +1444,14 @@ cdc_ncm_speed_change(struct usbnet *dev,
 	 */
 	if ((tx_speed > 1000000) && (rx_speed > 1000000)) {
 		netif_info(dev, link, dev->net,
-		       "%u mbit/s downlink %u mbit/s uplink\n",
-		       (unsigned int)(rx_speed / 1000000U),
-		       (unsigned int)(tx_speed / 1000000U));
+			   "%u mbit/s downlink %u mbit/s uplink\n",
+			   (unsigned int)(rx_speed / 1000000U),
+			   (unsigned int)(tx_speed / 1000000U));
 	} else {
 		netif_info(dev, link, dev->net,
-		       "%u kbit/s downlink %u kbit/s uplink\n",
-		       (unsigned int)(rx_speed / 1000U),
-		       (unsigned int)(tx_speed / 1000U));
+			   "%u kbit/s downlink %u kbit/s uplink\n",
+			   (unsigned int)(rx_speed / 1000U),
+			   (unsigned int)(tx_speed / 1000U));
 	}
 }
 
@@ -1086,11 +1481,10 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 		 * USB_CDC_NOTIFY_NETWORK_CONNECTION notification shall be
 		 * sent by device after USB_CDC_NOTIFY_SPEED_CHANGE.
 		 */
-		ctx->connected = le16_to_cpu(event->wValue);
 		netif_info(dev, link, dev->net,
 			   "network connection: %sconnected\n",
-			   ctx->connected ? "" : "dis");
-		usbnet_link_change(dev, ctx->connected, 0);
+			   !!event->wValue ? "" : "dis");
+		usbnet_link_change(dev, !!event->wValue, 0);
 		break;
 
 	case USB_CDC_NOTIFY_SPEED_CHANGE:
@@ -1110,23 +1504,11 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 	}
 }
 
-static int cdc_ncm_check_connect(struct usbnet *dev)
-{
-	struct cdc_ncm_ctx *ctx;
-
-	ctx = (struct cdc_ncm_ctx *)dev->data[0];
-	if (ctx == NULL)
-		return 1;	/* disconnected */
-
-	return !ctx->connected;
-}
-
 static const struct driver_info cdc_ncm_info = {
 	.description = "CDC NCM",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
-	.check_connect = cdc_ncm_check_connect,
 	.manage_power = usbnet_manage_power,
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
@@ -1140,7 +1522,6 @@ static const struct driver_info wwan_info = {
 			| FLAG_WWAN,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
-	.check_connect = cdc_ncm_check_connect,
 	.manage_power = usbnet_manage_power,
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
@@ -1154,7 +1535,6 @@ static const struct driver_info wwan_noarp_info = {
 			| FLAG_WWAN | FLAG_NOARP,
 	.bind = cdc_ncm_bind,
 	.unbind = cdc_ncm_unbind,
-	.check_connect = cdc_ncm_check_connect,
 	.manage_power = usbnet_manage_power,
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 660bd5ea9fc..a4272ed62da 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -258,10 +258,8 @@ struct hso_serial {
 	 * so as not to drop characters on the floor.
 	 */
 	int  curr_rx_urb_idx;
-	u16  curr_rx_urb_offset;
 	u8   rx_urb_filled[MAX_RX_URBS];
 	struct tasklet_struct unthrottle_tasklet;
-	struct work_struct    retry_unthrottle_workqueue;
 };
 
 struct hso_device {
@@ -1252,14 +1250,6 @@ static	void hso_unthrottle(struct tty_struct *tty)
 	tasklet_hi_schedule(&serial->unthrottle_tasklet);
 }
 
-static void hso_unthrottle_workfunc(struct work_struct *work)
-{
-	struct hso_serial *serial =
-	    container_of(work, struct hso_serial,
-			 retry_unthrottle_workqueue);
-	hso_unthrottle_tasklet(serial);
-}
-
 /* open the requested serial port */
 static int hso_serial_open(struct tty_struct *tty, struct file *filp)
 {
@@ -1295,8 +1285,6 @@ static int hso_serial_open(struct tty_struct *tty, struct file *filp)
 		tasklet_init(&serial->unthrottle_tasklet,
 			     (void (*)(unsigned long))hso_unthrottle_tasklet,
 			     (unsigned long)serial);
-		INIT_WORK(&serial->retry_unthrottle_workqueue,
-			  hso_unthrottle_workfunc);
 		result = hso_start_serial_device(serial->parent, GFP_KERNEL);
 		if (result) {
 			hso_stop_serial_device(serial->parent);
@@ -1345,7 +1333,6 @@ static void hso_serial_close(struct tty_struct *tty, struct file *filp)
 		if (!usb_gone)
 			hso_stop_serial_device(serial->parent);
 		tasklet_kill(&serial->unthrottle_tasklet);
-		cancel_work_sync(&serial->retry_unthrottle_workqueue);
 	}
 
 	if (!usb_gone)
@@ -2013,8 +2000,7 @@ static void ctrl_callback(struct urb *urb)
 static int put_rxbuf_data(struct urb *urb, struct hso_serial *serial)
 {
 	struct tty_struct *tty;
-	int write_length_remaining = 0;
-	int curr_write_len;
+	int count;
 
 	/* Sanity check */
 	if (urb == NULL || serial == NULL) {
@@ -2024,29 +2010,28 @@ static int put_rxbuf_data(struct urb *urb, struct hso_serial *serial)
 
 	tty = tty_port_tty_get(&serial->port);
 
+	if (tty && test_bit(TTY_THROTTLED, &tty->flags)) {
+		tty_kref_put(tty);
+		return -1;
+	}
+
 	/* Push data to tty */
-	write_length_remaining = urb->actual_length -
-		serial->curr_rx_urb_offset;
 	D1("data to push to tty");
-	while (write_length_remaining) {
-		if (tty && test_bit(TTY_THROTTLED, &tty->flags)) {
-			tty_kref_put(tty);
-			return -1;
-		}
-		curr_write_len = tty_insert_flip_string(&serial->port,
-			urb->transfer_buffer + serial->curr_rx_urb_offset,
-			write_length_remaining);
-		serial->curr_rx_urb_offset += curr_write_len;
-		write_length_remaining -= curr_write_len;
+	count = tty_buffer_request_room(&serial->port, urb->actual_length);
+	if (count >= urb->actual_length) {
+		tty_insert_flip_string(&serial->port, urb->transfer_buffer,
+				       urb->actual_length);
 		tty_flip_buffer_push(&serial->port);
+	} else {
+		dev_warn(&serial->parent->usb->dev,
+			 "dropping data, %d bytes lost\n", urb->actual_length);
 	}
+
 	tty_kref_put(tty);
 
-	if (write_length_remaining == 0) {
-		serial->curr_rx_urb_offset = 0;
-		serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 0;
-	}
-	return write_length_remaining;
+	serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 0;
+
+	return 0;
 }
 
 
@@ -2217,7 +2202,6 @@ static int hso_stop_serial_device(struct hso_device *hso_dev)
 		}
 	}
 	serial->curr_rx_urb_idx = 0;
-	serial->curr_rx_urb_offset = 0;
 
 	if (serial->tx_urb)
 		usb_kill_urb(serial->tx_urb);
@@ -2425,7 +2409,7 @@ static void hso_net_init(struct net_device *net)
 	net->type = ARPHRD_NONE;
 	net->mtu = DEFAULT_MTU - 14;
 	net->tx_queue_len = 10;
-	SET_ETHTOOL_OPS(net, &ops);
+	net->ethtool_ops = &ops;
 
 	/* and initialize the semaphore */
 	spin_lock_init(&hso_net->net_lock);
diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c
index 312178d7b69..735f7dadb9a 100644
--- a/drivers/net/usb/huawei_cdc_ncm.c
+++ b/drivers/net/usb/huawei_cdc_ncm.c
@@ -84,12 +84,13 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev,
 	ctx = drvstate->ctx;
 
 	if (usbnet_dev->status)
-		/* CDC-WMC r1.1 requires wMaxCommand to be "at least 256
-		 * decimal (0x100)"
+		/* The wMaxCommand buffer must be big enough to hold
+		 * any message from the modem. Experience has shown
+		 * that some replies are more than 256 bytes long
 		 */
 		subdriver = usb_cdc_wdm_register(ctx->control,
 						 &usbnet_dev->status->desc,
-						 256, /* wMaxCommand */
+						 1024, /* wMaxCommand */
 						 huawei_cdc_ncm_wdm_manage_power);
 	if (IS_ERR(subdriver)) {
 		ret = PTR_ERR(subdriver);
@@ -172,24 +173,11 @@ err:
 	return ret;
 }
 
-static int huawei_cdc_ncm_check_connect(struct usbnet *usbnet_dev)
-{
-	struct cdc_ncm_ctx *ctx;
-
-	ctx = (struct cdc_ncm_ctx *)usbnet_dev->data[0];
-
-	if (ctx == NULL)
-		return 1; /* disconnected */
-
-	return !ctx->connected;
-}
-
 static const struct driver_info huawei_cdc_ncm_info = {
 	.description = "Huawei CDC NCM device",
 	.flags = FLAG_NO_SETINT | FLAG_MULTI_PACKET | FLAG_WWAN,
 	.bind = huawei_cdc_ncm_bind,
 	.unbind = huawei_cdc_ncm_unbind,
-	.check_connect = huawei_cdc_ncm_check_connect,
 	.manage_power = huawei_cdc_ncm_manage_power,
 	.rx_fixup = cdc_ncm_rx_fixup,
 	.tx_fixup = cdc_ncm_tx_fixup,
@@ -206,6 +194,9 @@ static const struct usb_device_id huawei_cdc_ncm_devs[] = {
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x02, 0x76),
 	  .driver_info = (unsigned long)&huawei_cdc_ncm_info,
 	},
+	{ USB_VENDOR_AND_INTERFACE_INFO(0x12d1, 0xff, 0x03, 0x16),
+	  .driver_info = (unsigned long)&huawei_cdc_ncm_info,
+	},
 
 	/* Terminating entry */
 	{
diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
index 973275fef25..76465b117b7 100644
--- a/drivers/net/usb/ipheth.c
+++ b/drivers/net/usb/ipheth.c
@@ -534,7 +534,7 @@ static int ipheth_probe(struct usb_interface *intf,
 	usb_set_intfdata(intf, dev);
 
 	SET_NETDEV_DEV(netdev, &intf->dev);
-	SET_ETHTOOL_OPS(netdev, &ops);
+	netdev->ethtool_ops = &ops;
 
 	retval = register_netdev(netdev);
 	if (retval) {
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index a359d3bb7c5..dcb6d33141e 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -1171,7 +1171,7 @@ err_fw:
 	netdev->netdev_ops = &kaweth_netdev_ops;
 	netdev->watchdog_timeo = KAWETH_TX_TIMEOUT;
 	netdev->mtu = le16_to_cpu(kaweth->configuration.segment_size);
-	SET_ETHTOOL_OPS(netdev, &ops);
+	netdev->ethtool_ops = &ops;
 
 	/* kaweth is zeroed as part of alloc_netdev */
 	INIT_DELAYED_WORK(&kaweth->lowmem_work, kaweth_resubmit_tl);
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 03e8a15d7de..f8408021591 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -1159,7 +1159,7 @@ static int pegasus_probe(struct usb_interface *intf,
 
 	net->watchdog_timeo = PEGASUS_TX_TIMEOUT;
 	net->netdev_ops = &pegasus_netdev_ops;
-	SET_ETHTOOL_OPS(net, &ops);
+	net->ethtool_ops = &ops;
 	pegasus->mii.dev = net;
 	pegasus->mii.mdio_read = mdio_read;
 	pegasus->mii.mdio_write = mdio_write;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index dc4bf06948c..22756db53dc 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -667,6 +667,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x05c6, 0x9084, 4)},
 	{QMI_FIXED_INTF(0x05c6, 0x920d, 0)},
 	{QMI_FIXED_INTF(0x05c6, 0x920d, 5)},
+	{QMI_FIXED_INTF(0x0846, 0x68a2, 8)},
 	{QMI_FIXED_INTF(0x12d1, 0x140c, 1)},	/* Huawei E173 */
 	{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)},	/* Huawei E1820 */
 	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
@@ -741,6 +742,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x1424, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1425, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1426, 2)},	/* ZTE MF91 */
+	{QMI_FIXED_INTF(0x19d2, 0x1428, 2)},	/* Telewell TW-LTE 4G v2 */
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
@@ -756,6 +758,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1199, 0x9054, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9055, 8)},	/* Netgear AirCard 341U */
 	{QMI_FIXED_INTF(0x1199, 0x9056, 8)},	/* Sierra Wireless Modem */
+	{QMI_FIXED_INTF(0x1199, 0x9057, 8)},
 	{QMI_FIXED_INTF(0x1199, 0x9061, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)},	/* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
 	{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)},	/* Alcatel L800MA */
@@ -763,7 +766,12 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1201, 2)},	/* Telit LE920 */
-	{QMI_FIXED_INTF(0x0b3c, 0xc005, 6)},    /* Olivetti Olicard 200 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc000, 4)},	/* Olivetti Olicard 100 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc001, 4)},	/* Olivetti Olicard 120 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc002, 4)},	/* Olivetti Olicard 140 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc004, 6)},	/* Olivetti Olicard 155 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc005, 6)},	/* Olivetti Olicard 200 */
+	{QMI_FIXED_INTF(0x0b3c, 0xc00a, 6)},	/* Olivetti Olicard 160 */
 	{QMI_FIXED_INTF(0x0b3c, 0xc00b, 4)},	/* Olivetti Olicard 500 */
 	{QMI_FIXED_INTF(0x1e2d, 0x0060, 4)},	/* Cinterion PLxx */
 	{QMI_FIXED_INTF(0x1e2d, 0x0053, 4)},	/* Cinterion PHxx,PXxx */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 3fbfb086903..3eab74c7c55 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -282,7 +282,7 @@
 /* USB_DEV_STAT */
 #define STAT_SPEED_MASK		0x0006
 #define STAT_SPEED_HIGH		0x0000
-#define STAT_SPEED_FULL		0x0001
+#define STAT_SPEED_FULL		0x0002
 
 /* USB_TX_AGG */
 #define TX_AGG_MAX_THRESHOLD	0x03
@@ -630,12 +630,10 @@ int set_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
 	int ret;
 	void *tmp;
 
-	tmp = kmalloc(size, GFP_KERNEL);
+	tmp = kmemdup(data, size, GFP_KERNEL);
 	if (!tmp)
 		return -ENOMEM;
 
-	memcpy(tmp, data, size);
-
 	ret = usb_control_msg(tp->udev, usb_sndctrlpipe(tp->udev, 0),
 			       RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE,
 			       value, index, tmp, size, 500);
@@ -1361,7 +1359,7 @@ static void r8152_csum_workaround(struct r8152 *tp, struct sk_buff *skb,
 		struct sk_buff_head seg_list;
 		struct sk_buff *segs, *nskb;
 
-		features &= ~(NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO);
+		features &= ~(NETIF_F_SG | NETIF_F_IPV6_CSUM | NETIF_F_TSO6);
 		segs = skb_gso_segment(skb, features);
 		if (IS_ERR(segs) || !segs)
 			goto drop;
@@ -2294,9 +2292,8 @@ static void r8152b_exit_oob(struct r8152 *tp)
 	/* rx share fifo credit full threshold */
 	ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL0, RXFIFO_THR1_NORMAL);
 
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_DEV_STAT);
-	ocp_data &= STAT_SPEED_MASK;
-	if (ocp_data == STAT_SPEED_FULL) {
+	if (tp->udev->speed == USB_SPEED_FULL ||
+	    tp->udev->speed == USB_SPEED_LOW) {
 		/* rx share fifo credit near full threshold */
 		ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RXFIFO_CTRL1,
 				RXFIFO_THR2_FULL);
@@ -3206,8 +3203,13 @@ static void rtl8152_get_ethtool_stats(struct net_device *dev,
 	struct r8152 *tp = netdev_priv(dev);
 	struct tally_counter tally;
 
+	if (usb_autopm_get_interface(tp->intf) < 0)
+		return;
+
 	generic_ocp_read(tp, PLA_TALLYCNT, sizeof(tally), &tally, MCU_TYPE_PLA);
 
+	usb_autopm_put_interface(tp->intf);
+
 	data[0] = le64_to_cpu(tally.tx_packets);
 	data[1] = le64_to_cpu(tally.rx_packets);
 	data[2] = le64_to_cpu(tally.tx_errors);
@@ -3452,7 +3454,7 @@ static int rtl8152_probe(struct usb_interface *intf,
 			      NETIF_F_TSO | NETIF_F_FRAGLIST |
 			      NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
 
-	SET_ETHTOOL_OPS(netdev, &ops);
+	netdev->ethtool_ops = &ops;
 	netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE);
 
 	tp->mii.dev = netdev;
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index da2c4583bd2..6e87e571004 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -878,7 +878,7 @@ static int rtl8150_probe(struct usb_interface *intf,
 	dev->netdev = netdev;
 	netdev->netdev_ops = &rtl8150_netdev_ops;
 	netdev->watchdog_timeo = RTL8150_TX_TIMEOUT;
-	SET_ETHTOOL_OPS(netdev, &ops);
+	netdev->ethtool_ops = &ops;
 	dev->intr_interval = 100;	/* 100ms */
 
 	if (!alloc_all_urbs(dev)) {
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 424db65e439..d07bf4cb893 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -1714,6 +1714,18 @@ static int smsc95xx_resume(struct usb_interface *intf)
 	return ret;
 }
 
+static int smsc95xx_reset_resume(struct usb_interface *intf)
+{
+	struct usbnet *dev = usb_get_intfdata(intf);
+	int ret;
+
+	ret = smsc95xx_reset(dev);
+	if (ret < 0)
+		return ret;
+
+	return smsc95xx_resume(intf);
+}
+
 static void smsc95xx_rx_csum_offload(struct sk_buff *skb)
 {
 	skb->csum = *(u16 *)(skb_tail_pointer(skb) - 2);
@@ -2004,7 +2016,7 @@ static struct usb_driver smsc95xx_driver = {
 	.probe		= usbnet_probe,
 	.suspend	= smsc95xx_suspend,
 	.resume		= smsc95xx_resume,
-	.reset_resume	= smsc95xx_resume,
+	.reset_resume	= smsc95xx_reset_resume,
 	.disconnect	= usbnet_disconnect,
 	.disable_hub_initiated_lpm = 1,
 	.supports_autosuspend = 1,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 8a852b5f215..7d9f84a91f3 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1646,7 +1646,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	dev->netdev_ops = &virtnet_netdev;
 	dev->features = NETIF_F_HIGHDMA;
 
-	SET_ETHTOOL_OPS(dev, &virtnet_ethtool_ops);
+	dev->ethtool_ops = &virtnet_ethtool_ops;
 	SET_NETDEV_DEV(dev, &vdev->dev);
 
 	/* Do we support "hardware" checksums? */
@@ -1724,6 +1724,13 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
 		vi->has_cvq = true;
 
+	if (vi->any_header_sg) {
+		if (vi->mergeable_rx_bufs)
+			dev->needed_headroom = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+		else
+			dev->needed_headroom = sizeof(struct virtio_net_hdr);
+	}
+
 	/* Use single tx/rx queue pair as default */
 	vi->curr_queue_pairs = 1;
 	vi->max_queue_pairs = max_queue_pairs;
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 97394345e5d..b76f7dcde0d 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -2589,8 +2589,8 @@ vmxnet3_open(struct net_device *netdev)
 	for (i = 0; i < adapter->num_tx_queues; i++)
 		spin_lock_init(&adapter->tx_queue[i].tx_lock);
 
-	err = vmxnet3_create_queues(adapter, VMXNET3_DEF_TX_RING_SIZE,
-				    VMXNET3_DEF_RX_RING_SIZE,
+	err = vmxnet3_create_queues(adapter, adapter->tx_ring_size,
+				    adapter->rx_ring_size,
 				    VMXNET3_DEF_RX_RING_SIZE);
 	if (err)
 		goto queue_err;
@@ -2968,6 +2968,9 @@ vmxnet3_probe_device(struct pci_dev *pdev,
 	adapter->netdev = netdev;
 	adapter->pdev = pdev;
 
+	adapter->tx_ring_size = VMXNET3_DEF_TX_RING_SIZE;
+	adapter->rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
+
 	spin_lock_init(&adapter->cmd_lock);
 	adapter->adapter_pa = dma_map_single(&adapter->pdev->dev, adapter,
 					     sizeof(struct vmxnet3_adapter),
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index 600ab56c000..b725fd9e780 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -431,8 +431,8 @@ vmxnet3_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 		ethtool_cmd_speed_set(ecmd, adapter->link_speed);
 		ecmd->duplex = DUPLEX_FULL;
 	} else {
-		ethtool_cmd_speed_set(ecmd, -1);
-		ecmd->duplex = -1;
+		ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN);
+		ecmd->duplex = DUPLEX_UNKNOWN;
 	}
 	return 0;
 }
@@ -449,8 +449,8 @@ vmxnet3_get_ringparam(struct net_device *netdev,
 	param->rx_mini_max_pending = 0;
 	param->rx_jumbo_max_pending = 0;
 
-	param->rx_pending = adapter->rx_queue[0].rx_ring[0].size;
-	param->tx_pending = adapter->tx_queue[0].tx_ring.size;
+	param->rx_pending = adapter->rx_ring_size;
+	param->tx_pending = adapter->tx_ring_size;
 	param->rx_mini_pending = 0;
 	param->rx_jumbo_pending = 0;
 }
@@ -529,9 +529,11 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 			 * size */
 			netdev_err(netdev, "failed to apply new sizes, "
 				   "try the default ones\n");
+			new_rx_ring_size = VMXNET3_DEF_RX_RING_SIZE;
+			new_tx_ring_size = VMXNET3_DEF_TX_RING_SIZE;
 			err = vmxnet3_create_queues(adapter,
-						    VMXNET3_DEF_TX_RING_SIZE,
-						    VMXNET3_DEF_RX_RING_SIZE,
+						    new_tx_ring_size,
+						    new_rx_ring_size,
 						    VMXNET3_DEF_RX_RING_SIZE);
 			if (err) {
 				netdev_err(netdev, "failed to create queues "
@@ -545,6 +547,8 @@ vmxnet3_set_ringparam(struct net_device *netdev,
 			netdev_err(netdev, "failed to re-activate, error %d."
 				   " Closing it\n", err);
 	}
+	adapter->tx_ring_size = new_tx_ring_size;
+	adapter->rx_ring_size = new_rx_ring_size;
 
 out:
 	clear_bit(VMXNET3_STATE_BIT_RESETTING, &adapter->state);
@@ -579,7 +583,7 @@ vmxnet3_get_rss_indir_size(struct net_device *netdev)
 }
 
 static int
-vmxnet3_get_rss_indir(struct net_device *netdev, u32 *p)
+vmxnet3_get_rss(struct net_device *netdev, u32 *p, u8 *key)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
@@ -592,7 +596,7 @@ vmxnet3_get_rss_indir(struct net_device *netdev, u32 *p)
 }
 
 static int
-vmxnet3_set_rss_indir(struct net_device *netdev, const u32 *p)
+vmxnet3_set_rss(struct net_device *netdev, const u32 *p, const u8 *key)
 {
 	unsigned int i;
 	unsigned long flags;
@@ -628,12 +632,12 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = {
 	.get_rxnfc         = vmxnet3_get_rxnfc,
 #ifdef VMXNET3_RSS
 	.get_rxfh_indir_size = vmxnet3_get_rss_indir_size,
-	.get_rxfh_indir    = vmxnet3_get_rss_indir,
-	.set_rxfh_indir    = vmxnet3_set_rss_indir,
+	.get_rxfh          = vmxnet3_get_rss,
+	.set_rxfh          = vmxnet3_set_rss,
 #endif
 };
 
 void vmxnet3_set_ethtool_ops(struct net_device *netdev)
 {
-	SET_ETHTOOL_OPS(netdev, &vmxnet3_ethtool_ops);
+	netdev->ethtool_ops = &vmxnet3_ethtool_ops;
 }
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index 190569d0245..29ee77f2c97 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -349,6 +349,11 @@ struct vmxnet3_adapter {
 	u32     link_speed; /* in mbps */
 
 	u64     tx_timeout_count;
+
+	/* Ring sizes */
+	u32 tx_ring_size;
+	u32 rx_ring_size;
+
 	struct work_struct work;
 
 	unsigned long  state;    /* VMXNET3_STATE_BIT_xxx */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 4dbb2ed85b9..9f79192c9aa 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -127,6 +127,7 @@ struct vxlan_dev {
 	struct list_head  next;		/* vxlan's per namespace list */
 	struct vxlan_sock *vn_sock;	/* listening socket */
 	struct net_device *dev;
+	struct net	  *net;		/* netns for packet i/o */
 	struct vxlan_rdst default_dst;	/* default destination */
 	union vxlan_addr  saddr;	/* source address */
 	__be16		  dst_port;
@@ -134,7 +135,7 @@ struct vxlan_dev {
 	__u16		  port_max;
 	__u8		  tos;		/* TOS override */
 	__u8		  ttl;
-	u32		  flags;	/* VXLAN_F_* below */
+	u32		  flags;	/* VXLAN_F_* in vxlan.h */
 
 	struct work_struct sock_work;
 	struct work_struct igmp_join;
@@ -149,13 +150,6 @@ struct vxlan_dev {
 	struct hlist_head fdb_head[FDB_HASH_SIZE];
 };
 
-#define VXLAN_F_LEARN	0x01
-#define VXLAN_F_PROXY	0x02
-#define VXLAN_F_RSC	0x04
-#define VXLAN_F_L2MISS	0x08
-#define VXLAN_F_L3MISS	0x10
-#define VXLAN_F_IPV6	0x20 /* internal flag */
-
 /* salt for hash table */
 static u32 vxlan_salt __read_mostly;
 static struct workqueue_struct *vxlan_wq;
@@ -345,7 +339,7 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 	ndm->ndm_state = fdb->state;
 	ndm->ndm_ifindex = vxlan->dev->ifindex;
 	ndm->ndm_flags = fdb->flags;
-	ndm->ndm_type = NDA_DST;
+	ndm->ndm_type = RTN_UNICAST;
 
 	if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
 		goto nla_put_failure;
@@ -571,6 +565,7 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff
 			goto out;
 	}
 	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
+	skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
 
 	off_eth = skb_gro_offset(skb);
 	hlen = off_eth + sizeof(*eh);
@@ -605,6 +600,7 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff
 	}
 
 	skb_gro_pull(skb, sizeof(*eh)); /* pull inner eth header */
+	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
 	pp = ptype->callbacks.gro_receive(head, skb);
 
 out_unlock:
@@ -1160,15 +1156,7 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	if (!vs)
 		goto drop;
 
-	/* If the NIC driver gave us an encapsulated packet
-	 * with the encapsulation mark, the device checksummed it
-	 * for us. Otherwise force the upper layers to verify it.
-	 */
-	if ((skb->ip_summed != CHECKSUM_UNNECESSARY && skb->ip_summed != CHECKSUM_PARTIAL) ||
-	    !skb->encapsulation)
-		skb->ip_summed = CHECKSUM_NONE;
-
-	skb->encapsulation = 0;
+	skb_pop_rcv_encapsulation(skb);
 
 	vs->rcv(vs, skb, vxh->vx_vni);
 	return 0;
@@ -1203,7 +1191,9 @@ static void vxlan_rcv(struct vxlan_sock *vs,
 
 	remote_ip = &vxlan->default_dst.remote_ip;
 	skb_reset_mac_header(skb);
+	skb_scrub_packet(skb, !net_eq(vxlan->net, dev_net(vxlan->dev)));
 	skb->protocol = eth_type_trans(skb, vxlan->dev);
+	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
 	/* Ignore packet loops (and multicast echo) */
 	if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr))
@@ -1599,18 +1589,11 @@ __be16 vxlan_src_port(__u16 port_min, __u16 port_max, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(vxlan_src_port);
 
-static int handle_offloads(struct sk_buff *skb)
+static inline struct sk_buff *vxlan_handle_offloads(struct sk_buff *skb,
+						    bool udp_csum)
 {
-	if (skb_is_gso(skb)) {
-		int err = skb_unclone(skb, GFP_ATOMIC);
-		if (unlikely(err))
-			return err;
-
-		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
-	} else if (skb->ip_summed != CHECKSUM_PARTIAL)
-		skb->ip_summed = CHECKSUM_NONE;
-
-	return 0;
+	int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+	return iptunnel_handle_offloads(skb, udp_csum, type);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1618,7 +1601,8 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 			   struct dst_entry *dst, struct sk_buff *skb,
 			   struct net_device *dev, struct in6_addr *saddr,
 			   struct in6_addr *daddr, __u8 prio, __u8 ttl,
-			   __be16 src_port, __be16 dst_port, __be32 vni)
+			   __be16 src_port, __be16 dst_port, __be32 vni,
+			   bool xnet)
 {
 	struct ipv6hdr *ip6h;
 	struct vxlanhdr *vxh;
@@ -1626,12 +1610,11 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	int min_headroom;
 	int err;
 
-	if (!skb->encapsulation) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
+	skb = vxlan_handle_offloads(skb, !udp_get_no_check6_tx(vs->sock->sk));
+	if (IS_ERR(skb))
+		return -EINVAL;
 
-	skb_scrub_packet(skb, false);
+	skb_scrub_packet(skb, xnet);
 
 	min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
 			+ VXLAN_HLEN + sizeof(struct ipv6hdr)
@@ -1663,27 +1646,14 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	uh->source = src_port;
 
 	uh->len = htons(skb->len);
-	uh->check = 0;
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
 			      IPSKB_REROUTED);
 	skb_dst_set(skb, dst);
 
-	if (!skb_is_gso(skb) && !(dst->dev->features & NETIF_F_IPV6_CSUM)) {
-		__wsum csum = skb_checksum(skb, 0, skb->len, 0);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		uh->check = csum_ipv6_magic(saddr, daddr, skb->len,
-					    IPPROTO_UDP, csum);
-		if (uh->check == 0)
-			uh->check = CSUM_MANGLED_0;
-	} else {
-		skb->ip_summed = CHECKSUM_PARTIAL;
-		skb->csum_start = skb_transport_header(skb) - skb->head;
-		skb->csum_offset = offsetof(struct udphdr, check);
-		uh->check = ~csum_ipv6_magic(saddr, daddr,
-					     skb->len, IPPROTO_UDP, 0);
-	}
+	udp6_set_csum(udp_get_no_check6_tx(vs->sock->sk), skb,
+		      saddr, daddr, skb->len);
 
 	__skb_push(skb, sizeof(*ip6h));
 	skb_reset_network_header(skb);
@@ -1699,10 +1669,6 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 	ip6h->daddr	  = *daddr;
 	ip6h->saddr	  = *saddr;
 
-	err = handle_offloads(skb);
-	if (err)
-		return err;
-
 	ip6tunnel_xmit(skb, dev);
 	return 0;
 }
@@ -1711,17 +1677,16 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
 int vxlan_xmit_skb(struct vxlan_sock *vs,
 		   struct rtable *rt, struct sk_buff *skb,
 		   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
-		   __be16 src_port, __be16 dst_port, __be32 vni)
+		   __be16 src_port, __be16 dst_port, __be32 vni, bool xnet)
 {
 	struct vxlanhdr *vxh;
 	struct udphdr *uh;
 	int min_headroom;
 	int err;
 
-	if (!skb->encapsulation) {
-		skb_reset_inner_headers(skb);
-		skb->encapsulation = 1;
-	}
+	skb = vxlan_handle_offloads(skb, !vs->sock->sk->sk_no_check_tx);
+	if (IS_ERR(skb))
+		return -EINVAL;
 
 	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
 			+ VXLAN_HLEN + sizeof(struct iphdr)
@@ -1753,14 +1718,12 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
 	uh->source = src_port;
 
 	uh->len = htons(skb->len);
-	uh->check = 0;
 
-	err = handle_offloads(skb);
-	if (err)
-		return err;
+	udp_set_csum(vs->sock->sk->sk_no_check_tx, skb,
+		     src, dst, skb->len);
 
 	return iptunnel_xmit(vs->sock->sk, rt, skb, src, dst, IPPROTO_UDP,
-			     tos, ttl, df, false);
+			     tos, ttl, df, xnet);
 }
 EXPORT_SYMBOL_GPL(vxlan_xmit_skb);
 
@@ -1853,7 +1816,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		fl4.daddr = dst->sin.sin_addr.s_addr;
 		fl4.saddr = vxlan->saddr.sin.sin_addr.s_addr;
 
-		rt = ip_route_output_key(dev_net(dev), &fl4);
+		rt = ip_route_output_key(vxlan->net, &fl4);
 		if (IS_ERR(rt)) {
 			netdev_dbg(dev, "no route to %pI4\n",
 				   &dst->sin.sin_addr.s_addr);
@@ -1874,7 +1837,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			struct vxlan_dev *dst_vxlan;
 
 			ip_rt_put(rt);
-			dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+			dst_vxlan = vxlan_find_vni(vxlan->net, vni, dst_port);
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -1887,7 +1850,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		err = vxlan_xmit_skb(vxlan->vn_sock, rt, skb,
 				     fl4.saddr, dst->sin.sin_addr.s_addr,
 				     tos, ttl, df, src_port, dst_port,
-				     htonl(vni << 8));
+				     htonl(vni << 8),
+				     !net_eq(vxlan->net, dev_net(vxlan->dev)));
 
 		if (err < 0)
 			goto rt_tx_error;
@@ -1927,7 +1891,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 			struct vxlan_dev *dst_vxlan;
 
 			dst_release(ndst);
-			dst_vxlan = vxlan_find_vni(dev_net(dev), vni, dst_port);
+			dst_vxlan = vxlan_find_vni(vxlan->net, vni, dst_port);
 			if (!dst_vxlan)
 				goto tx_error;
 			vxlan_encap_bypass(skb, vxlan, dst_vxlan);
@@ -1938,7 +1902,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 
 		err = vxlan6_xmit_skb(vxlan->vn_sock, ndst, skb,
 				      dev, &fl6.saddr, &fl6.daddr, 0, ttl,
-				      src_port, dst_port, htonl(vni << 8));
+				      src_port, dst_port, htonl(vni << 8),
+				      !net_eq(vxlan->net, dev_net(vxlan->dev)));
 #endif
 	}
 
@@ -2082,7 +2047,7 @@ static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan)
 static int vxlan_init(struct net_device *dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
+	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	struct vxlan_sock *vs;
 
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
@@ -2090,7 +2055,7 @@ static int vxlan_init(struct net_device *dev)
 		return -ENOMEM;
 
 	spin_lock(&vn->sock_lock);
-	vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port);
+	vs = vxlan_find_sock(vxlan->net, vxlan->dst_port);
 	if (vs) {
 		/* If we have a socket with same port already, reuse it */
 		atomic_inc(&vs->refcnt);
@@ -2172,8 +2137,8 @@ static void vxlan_flush(struct vxlan_dev *vxlan)
 /* Cleanup timer and forwarding table on shutdown */
 static int vxlan_stop(struct net_device *dev)
 {
-	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 	struct vxlan_sock *vs = vxlan->vn_sock;
 
 	if (vs && vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
@@ -2202,7 +2167,7 @@ static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
 	struct net_device *lowerdev;
 	int max_mtu;
 
-	lowerdev = __dev_get_by_index(dev_net(dev), dst->remote_ifindex);
+	lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex);
 	if (lowerdev == NULL)
 		return eth_change_mtu(dev, new_mtu);
 
@@ -2275,9 +2240,9 @@ static void vxlan_setup(struct net_device *dev)
 	eth_hw_addr_random(dev);
 	ether_setup(dev);
 	if (vxlan->default_dst.remote_ip.sa.sa_family == AF_INET6)
-		dev->hard_header_len = ETH_HLEN + VXLAN6_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
 	else
-		dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
+		dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
 
 	dev->netdev_ops = &vxlan_netdev_ops;
 	dev->destructor = free_netdev;
@@ -2285,7 +2250,6 @@ static void vxlan_setup(struct net_device *dev)
 
 	dev->tx_queue_len = 0;
 	dev->features	|= NETIF_F_LLTX;
-	dev->features	|= NETIF_F_NETNS_LOCAL;
 	dev->features	|= NETIF_F_SG | NETIF_F_HW_CSUM;
 	dev->features   |= NETIF_F_RXCSUM;
 	dev->features   |= NETIF_F_GSO_SOFTWARE;
@@ -2401,7 +2365,7 @@ static void vxlan_del_work(struct work_struct *work)
  * could be used for both IPv4 and IPv6 communications, but
  * users may set bindv6only=1.
  */
-static struct socket *create_v6_sock(struct net *net, __be16 port)
+static struct socket *create_v6_sock(struct net *net, __be16 port, u32 flags)
 {
 	struct sock *sk;
 	struct socket *sock;
@@ -2438,18 +2402,25 @@ static struct socket *create_v6_sock(struct net *net, __be16 port)
 
 	/* Disable multicast loopback */
 	inet_sk(sk)->mc_loop = 0;
+
+	if (flags & VXLAN_F_UDP_ZERO_CSUM6_TX)
+		udp_set_no_check6_tx(sk, true);
+
+	if (flags & VXLAN_F_UDP_ZERO_CSUM6_RX)
+		udp_set_no_check6_rx(sk, true);
+
 	return sock;
 }
 
 #else
 
-static struct socket *create_v6_sock(struct net *net, __be16 port)
+static struct socket *create_v6_sock(struct net *net, __be16 port, u32 flags)
 {
 		return ERR_PTR(-EPFNOSUPPORT);
 }
 #endif
 
-static struct socket *create_v4_sock(struct net *net, __be16 port)
+static struct socket *create_v4_sock(struct net *net, __be16 port, u32 flags)
 {
 	struct sock *sk;
 	struct socket *sock;
@@ -2482,18 +2453,24 @@ static struct socket *create_v4_sock(struct net *net, __be16 port)
 
 	/* Disable multicast loopback */
 	inet_sk(sk)->mc_loop = 0;
+
+	if (!(flags & VXLAN_F_UDP_CSUM))
+		sock->sk->sk_no_check_tx = 1;
+
 	return sock;
 }
 
 /* Create new listen socket if needed */
 static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
-					      vxlan_rcv_t *rcv, void *data, bool ipv6)
+					      vxlan_rcv_t *rcv, void *data,
+					      u32 flags)
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_sock *vs;
 	struct socket *sock;
 	struct sock *sk;
 	unsigned int h;
+	bool ipv6 = !!(flags & VXLAN_F_IPV6);
 
 	vs = kzalloc(sizeof(*vs), GFP_KERNEL);
 	if (!vs)
@@ -2505,9 +2482,9 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 	INIT_WORK(&vs->del_work, vxlan_del_work);
 
 	if (ipv6)
-		sock = create_v6_sock(net, port);
+		sock = create_v6_sock(net, port, flags);
 	else
-		sock = create_v4_sock(net, port);
+		sock = create_v4_sock(net, port, flags);
 	if (IS_ERR(sock)) {
 		kfree(vs);
 		return ERR_CAST(sock);
@@ -2545,12 +2522,12 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
 
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 				  vxlan_rcv_t *rcv, void *data,
-				  bool no_share, bool ipv6)
+				  bool no_share, u32 flags)
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_sock *vs;
 
-	vs = vxlan_socket_create(net, port, rcv, data, ipv6);
+	vs = vxlan_socket_create(net, port, rcv, data, flags);
 	if (!IS_ERR(vs))
 		return vs;
 
@@ -2578,12 +2555,12 @@ EXPORT_SYMBOL_GPL(vxlan_sock_add);
 static void vxlan_sock_work(struct work_struct *work)
 {
 	struct vxlan_dev *vxlan = container_of(work, struct vxlan_dev, sock_work);
-	struct net *net = dev_net(vxlan->dev);
+	struct net *net = vxlan->net;
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	__be16 port = vxlan->dst_port;
 	struct vxlan_sock *nvs;
 
-	nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags & VXLAN_F_IPV6);
+	nvs = vxlan_sock_add(net, port, vxlan_rcv, NULL, false, vxlan->flags);
 	spin_lock(&vn->sock_lock);
 	if (!IS_ERR(nvs))
 		vxlan_vs_add_dev(nvs, vxlan);
@@ -2605,6 +2582,8 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	if (!data[IFLA_VXLAN_ID])
 		return -EINVAL;
 
+	vxlan->net = dev_net(dev);
+
 	vni = nla_get_u32(data[IFLA_VXLAN_ID]);
 	dst->remote_vni = vni;
 
@@ -2660,8 +2639,7 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 		if (!tb[IFLA_MTU])
 			dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 
-		/* update header length based on lower device */
-		dev->hard_header_len = lowerdev->hard_header_len +
+		dev->needed_headroom = lowerdev->hard_header_len +
 				       (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
 	} else if (use_ipv6)
 		vxlan->flags |= VXLAN_F_IPV6;
@@ -2705,12 +2683,23 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 	if (data[IFLA_VXLAN_PORT])
 		vxlan->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]);
 
+	if (data[IFLA_VXLAN_UDP_CSUM] && nla_get_u8(data[IFLA_VXLAN_UDP_CSUM]))
+		vxlan->flags |= VXLAN_F_UDP_CSUM;
+
+	if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] &&
+	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]))
+		vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_TX;
+
+	if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] &&
+	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
+		vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
+
 	if (vxlan_find_vni(net, vni, vxlan->dst_port)) {
 		pr_info("duplicate VNI %u\n", vni);
 		return -EEXIST;
 	}
 
-	SET_ETHTOOL_OPS(dev, &vxlan_ethtool_ops);
+	dev->ethtool_ops = &vxlan_ethtool_ops;
 
 	/* create an fdb entry for a valid default destination */
 	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
@@ -2739,8 +2728,8 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 {
-	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 
 	spin_lock(&vn->sock_lock);
 	if (!hlist_unhashed(&vxlan->hlist))
@@ -2768,7 +2757,10 @@ static size_t vxlan_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u32)) +	/* IFLA_VXLAN_AGEING */
 		nla_total_size(sizeof(__u32)) +	/* IFLA_VXLAN_LIMIT */
 		nla_total_size(sizeof(struct ifla_vxlan_port_range)) +
-		nla_total_size(sizeof(__be16))+ /* IFLA_VXLAN_PORT */
+		nla_total_size(sizeof(__be16)) + /* IFLA_VXLAN_PORT */
+		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */
+		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */
+		nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */
 		0;
 }
 
@@ -2828,7 +2820,13 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 			!!(vxlan->flags & VXLAN_F_L3MISS)) ||
 	    nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->age_interval) ||
 	    nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->addrmax) ||
-	    nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->dst_port))
+	    nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->dst_port) ||
+	    nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM,
+			!!(vxlan->flags & VXLAN_F_UDP_CSUM)) ||
+	    nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
+			!!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) ||
+	    nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
+			!!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_RX)))
 		goto nla_put_failure;
 
 	if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports))
@@ -2905,8 +2903,33 @@ static __net_init int vxlan_init_net(struct net *net)
 	return 0;
 }
 
+static void __net_exit vxlan_exit_net(struct net *net)
+{
+	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	struct vxlan_dev *vxlan, *next;
+	struct net_device *dev, *aux;
+	LIST_HEAD(list);
+
+	rtnl_lock();
+	for_each_netdev_safe(net, dev, aux)
+		if (dev->rtnl_link_ops == &vxlan_link_ops)
+			unregister_netdevice_queue(dev, &list);
+
+	list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) {
+		/* If vxlan->dev is in the same netns, it has already been added
+		 * to the list by the previous loop.
+		 */
+		if (!net_eq(dev_net(vxlan->dev), net))
+			unregister_netdevice_queue(dev, &list);
+	}
+
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
+}
+
 static struct pernet_operations vxlan_net_ops = {
 	.init = vxlan_init_net,
+	.exit = vxlan_exit_net,
 	.id   = &vxlan_net_id,
 	.size = sizeof(struct vxlan_net),
 };
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index bcfff0d62de..1f041271f7f 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -26,6 +26,7 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/delay.h>
 #include <linux/if.h>
 #include <linux/hdlc.h>
 #include <asm/io.h>
@@ -678,7 +679,6 @@ static inline void
 fst_cpureset(struct fst_card_info *card)
 {
 	unsigned char interrupt_line_register;
-	unsigned long j = jiffies + 1;
 	unsigned int regval;
 
 	if (card->family == FST_FAMILY_TXU) {
@@ -696,16 +696,12 @@ fst_cpureset(struct fst_card_info *card)
 		/*
 		 * We are delaying here to allow the 9054 to reset itself
 		 */
-		j = jiffies + 1;
-		while (jiffies < j)
-			/* Do nothing */ ;
+		usleep_range(10, 20);
 		outw(0x240f, card->pci_conf + CNTRL_9054 + 2);
 		/*
 		 * We are delaying here to allow the 9054 to reload its eeprom
 		 */
-		j = jiffies + 1;
-		while (jiffies < j)
-			/* Do nothing */ ;
+		usleep_range(10, 20);
 		outw(0x040f, card->pci_conf + CNTRL_9054 + 2);
 
 		if (pci_write_config_byte
@@ -886,20 +882,18 @@ fst_rx_dma_complete(struct fst_card_info *card, struct fst_port_info *port,
  *      Receive a frame through the DMA
  */
 static inline void
-fst_rx_dma(struct fst_card_info *card, dma_addr_t skb,
-	   dma_addr_t mem, int len)
+fst_rx_dma(struct fst_card_info *card, dma_addr_t dma, u32 mem, int len)
 {
 	/*
 	 * This routine will setup the DMA and start it
 	 */
 
-	dbg(DBG_RX, "In fst_rx_dma %lx %lx %d\n",
-	    (unsigned long) skb, (unsigned long) mem, len);
+	dbg(DBG_RX, "In fst_rx_dma %x %x %d\n", (u32)dma, mem, len);
 	if (card->dmarx_in_progress) {
 		dbg(DBG_ASS, "In fst_rx_dma while dma in progress\n");
 	}
 
-	outl(skb, card->pci_conf + DMAPADR0);	/* Copy to here */
+	outl(dma, card->pci_conf + DMAPADR0);	/* Copy to here */
 	outl(mem, card->pci_conf + DMALADR0);	/* from here */
 	outl(len, card->pci_conf + DMASIZ0);	/* for this length */
 	outl(0x00000000c, card->pci_conf + DMADPR0);	/* In this direction */
@@ -915,20 +909,19 @@ fst_rx_dma(struct fst_card_info *card, dma_addr_t skb,
  *      Send a frame through the DMA
  */
 static inline void
-fst_tx_dma(struct fst_card_info *card, unsigned char *skb,
-	   unsigned char *mem, int len)
+fst_tx_dma(struct fst_card_info *card, dma_addr_t dma, u32 mem, int len)
 {
 	/*
 	 * This routine will setup the DMA and start it.
 	 */
 
-	dbg(DBG_TX, "In fst_tx_dma %p %p %d\n", skb, mem, len);
+	dbg(DBG_TX, "In fst_tx_dma %x %x %d\n", (u32)dma, mem, len);
 	if (card->dmatx_in_progress) {
 		dbg(DBG_ASS, "In fst_tx_dma while dma in progress\n");
 	}
 
-	outl((unsigned long) skb, card->pci_conf + DMAPADR1);	/* Copy from here */
-	outl((unsigned long) mem, card->pci_conf + DMALADR1);	/* to here */
+	outl(dma, card->pci_conf + DMAPADR1);	/* Copy from here */
+	outl(mem, card->pci_conf + DMALADR1);	/* to here */
 	outl(len, card->pci_conf + DMASIZ1);	/* for this length */
 	outl(0x000000004, card->pci_conf + DMADPR1);	/* In this direction */
 
@@ -1405,9 +1398,7 @@ do_bottom_half_tx(struct fst_card_info *card)
 					card->dma_len_tx = skb->len;
 					card->dma_txpos = port->txpos;
 					fst_tx_dma(card,
-						   (char *) card->
-						   tx_dma_handle_card,
-						   (char *)
+						   card->tx_dma_handle_card,
 						   BUF_OFFSET(txBuffer[pi]
 							      [port->txpos][0]),
 						   skb->len);
@@ -2372,7 +2363,7 @@ static char *type_strings[] = {
 	"FarSync TE1"
 };
 
-static void
+static int
 fst_init_card(struct fst_card_info *card)
 {
 	int i;
@@ -2383,24 +2374,21 @@ fst_init_card(struct fst_card_info *card)
 	 * we'll have to revise it in some way then.
 	 */
 	for (i = 0; i < card->nports; i++) {
-                err = register_hdlc_device(card->ports[i].dev);
-                if (err < 0) {
-			int j;
+		err = register_hdlc_device(card->ports[i].dev);
+		if (err < 0) {
 			pr_err("Cannot register HDLC device for port %d (errno %d)\n",
-			       i, -err);
-			for (j = i; j < card->nports; j++) {
-				free_netdev(card->ports[j].dev);
-				card->ports[j].dev = NULL;
-			}
-                        card->nports = i;
-                        break;
-                }
+				i, -err);
+			while (i--)
+				unregister_hdlc_device(card->ports[i].dev);
+			return err;
+		}
 	}
 
 	pr_info("%s-%s: %s IRQ%d, %d ports\n",
 		port_to_dev(&card->ports[0])->name,
 		port_to_dev(&card->ports[card->nports - 1])->name,
 		type_strings[card->type], card->irq, card->nports);
+	return 0;
 }
 
 static const struct net_device_ops fst_ops = {
@@ -2456,15 +2444,12 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Try to enable the device */
 	if ((err = pci_enable_device(pdev)) != 0) {
 		pr_err("Failed to enable card. Err %d\n", -err);
-		kfree(card);
-		return err;
+		goto enable_fail;
 	}
 
 	if ((err = pci_request_regions(pdev, "FarSync")) !=0) {
 		pr_err("Failed to allocate regions. Err %d\n", -err);
-		pci_disable_device(pdev);
-		kfree(card);
-	        return err;
+		goto regions_fail;
 	}
 
 	/* Get virtual addresses of memory regions */
@@ -2473,30 +2458,21 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	card->phys_ctlmem = pci_resource_start(pdev, 3);
 	if ((card->mem = ioremap(card->phys_mem, FST_MEMSIZE)) == NULL) {
 		pr_err("Physical memory remap failed\n");
-		pci_release_regions(pdev);
-		pci_disable_device(pdev);
-		kfree(card);
-		return -ENODEV;
+		err = -ENODEV;
+		goto ioremap_physmem_fail;
 	}
 	if ((card->ctlmem = ioremap(card->phys_ctlmem, 0x10)) == NULL) {
 		pr_err("Control memory remap failed\n");
-		pci_release_regions(pdev);
-		pci_disable_device(pdev);
-		iounmap(card->mem);
-		kfree(card);
-		return -ENODEV;
+		err = -ENODEV;
+		goto ioremap_ctlmem_fail;
 	}
 	dbg(DBG_PCI, "kernel mem %p, ctlmem %p\n", card->mem, card->ctlmem);
 
 	/* Register the interrupt handler */
 	if (request_irq(pdev->irq, fst_intr, IRQF_SHARED, FST_DEV_NAME, card)) {
 		pr_err("Unable to register interrupt %d\n", card->irq);
-		pci_release_regions(pdev);
-		pci_disable_device(pdev);
-		iounmap(card->ctlmem);
-		iounmap(card->mem);
-		kfree(card);
-		return -ENODEV;
+		err = -ENODEV;
+		goto irq_fail;
 	}
 
 	/* Record info we need */
@@ -2522,13 +2498,8 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			while (i--)
 				free_netdev(card->ports[i].dev);
 			pr_err("FarSync: out of memory\n");
-                        free_irq(card->irq, card);
-                        pci_release_regions(pdev);
-                        pci_disable_device(pdev);
-                        iounmap(card->ctlmem);
-                        iounmap(card->mem);
-                        kfree(card);
-                        return -ENODEV;
+			err = -ENOMEM;
+			goto hdlcdev_fail;
 		}
 		card->ports[i].dev    = dev;
                 card->ports[i].card   = card;
@@ -2574,9 +2545,16 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	pci_set_drvdata(pdev, card);
 
 	/* Remainder of card setup */
+	if (no_of_cards_added >= FST_MAX_CARDS) {
+		pr_err("FarSync: too many cards\n");
+		err = -ENOMEM;
+		goto card_array_fail;
+	}
 	fst_card_array[no_of_cards_added] = card;
 	card->card_no = no_of_cards_added++;	/* Record instance and bump it */
-	fst_init_card(card);
+	err = fst_init_card(card);
+	if (err)
+		goto init_card_fail;
 	if (card->family == FST_FAMILY_TXU) {
 		/*
 		 * Allocate a dma buffer for transmit and receives
@@ -2586,29 +2564,46 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 					 &card->rx_dma_handle_card);
 		if (card->rx_dma_handle_host == NULL) {
 			pr_err("Could not allocate rx dma buffer\n");
-			fst_disable_intr(card);
-			pci_release_regions(pdev);
-			pci_disable_device(pdev);
-			iounmap(card->ctlmem);
-			iounmap(card->mem);
-			kfree(card);
-			return -ENOMEM;
+			err = -ENOMEM;
+			goto rx_dma_fail;
 		}
 		card->tx_dma_handle_host =
 		    pci_alloc_consistent(card->device, FST_MAX_MTU,
 					 &card->tx_dma_handle_card);
 		if (card->tx_dma_handle_host == NULL) {
 			pr_err("Could not allocate tx dma buffer\n");
-			fst_disable_intr(card);
-			pci_release_regions(pdev);
-			pci_disable_device(pdev);
-			iounmap(card->ctlmem);
-			iounmap(card->mem);
-			kfree(card);
-			return -ENOMEM;
+			err = -ENOMEM;
+			goto tx_dma_fail;
 		}
 	}
 	return 0;		/* Success */
+
+tx_dma_fail:
+	pci_free_consistent(card->device, FST_MAX_MTU,
+			    card->rx_dma_handle_host,
+			    card->rx_dma_handle_card);
+rx_dma_fail:
+	fst_disable_intr(card);
+	for (i = 0 ; i < card->nports ; i++)
+		unregister_hdlc_device(card->ports[i].dev);
+init_card_fail:
+	fst_card_array[card->card_no] = NULL;
+card_array_fail:
+	for (i = 0 ; i < card->nports ; i++)
+		free_netdev(card->ports[i].dev);
+hdlcdev_fail:
+	free_irq(card->irq, card);
+irq_fail:
+	iounmap(card->ctlmem);
+ioremap_ctlmem_fail:
+	iounmap(card->mem);
+ioremap_physmem_fail:
+	pci_release_regions(pdev);
+regions_fail:
+	pci_disable_device(pdev);
+enable_fail:
+	kfree(card);
+	return err;
 }
 
 /*
diff --git a/drivers/net/wan/sdla.c b/drivers/net/wan/sdla.c
index de3bbf43fc5..cdd45fb8a1f 100644
--- a/drivers/net/wan/sdla.c
+++ b/drivers/net/wan/sdla.c
@@ -1322,10 +1322,6 @@ NOTE:  This is rather a useless action right now, as the
 
 static int sdla_change_mtu(struct net_device *dev, int new_mtu)
 {
-	struct frad_local *flp;
-
-	flp = netdev_priv(dev);
-
 	if (netif_running(dev))
 		return -EBUSY;
 
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 5895f197869..fa9fdfa128c 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -122,8 +122,12 @@ static int x25_asy_change_mtu(struct net_device *dev, int newmtu)
 {
 	struct x25_asy *sl = netdev_priv(dev);
 	unsigned char *xbuff, *rbuff;
-	int len = 2 * newmtu;
+	int len;
 
+	if (newmtu > 65534)
+		return -EINVAL;
+
+	len = 2 * newmtu;
 	xbuff = kmalloc(len + 4, GFP_ATOMIC);
 	rbuff = kmalloc(len + 4, GFP_ATOMIC);
 
diff --git a/drivers/net/wimax/i2400m/control.c b/drivers/net/wimax/i2400m/control.c
index 4a01e5c7fe0..4c417903e9b 100644
--- a/drivers/net/wimax/i2400m/control.c
+++ b/drivers/net/wimax/i2400m/control.c
@@ -1061,7 +1061,7 @@ int i2400m_firmware_check(struct i2400m *i2400m)
 		goto error_bad_major;
 	}
 	result = 0;
-	if (minor < I2400M_HDIv_MINOR_2 && minor > I2400M_HDIv_MINOR)
+	if (minor > I2400M_HDIv_MINOR_2 || minor < I2400M_HDIv_MINOR)
 		dev_warn(dev, "untested minor fw version %u.%u.%u\n",
 			 major, minor, branch);
 	/* Yes, we ignore the branch -- we don't have to track it */
diff --git a/drivers/net/wimax/i2400m/driver.c b/drivers/net/wimax/i2400m/driver.c
index 9c34d2fccfa..9c78090e72f 100644
--- a/drivers/net/wimax/i2400m/driver.c
+++ b/drivers/net/wimax/i2400m/driver.c
@@ -500,26 +500,23 @@ int i2400m_pm_notifier(struct notifier_block *notifier,
  */
 int i2400m_pre_reset(struct i2400m *i2400m)
 {
-	int result;
 	struct device *dev = i2400m_dev(i2400m);
 
 	d_fnstart(3, dev, "(i2400m %p)\n", i2400m);
 	d_printf(1, dev, "pre-reset shut down\n");
 
-	result = 0;
 	mutex_lock(&i2400m->init_mutex);
 	if (i2400m->updown) {
 		netif_tx_disable(i2400m->wimax_dev.net_dev);
 		__i2400m_dev_stop(i2400m);
-		result = 0;
 		/* down't set updown to zero -- this way
 		 * post_reset can restore properly */
 	}
 	mutex_unlock(&i2400m->init_mutex);
 	if (i2400m->bus_release)
 		i2400m->bus_release(i2400m);
-	d_fnend(3, dev, "(i2400m %p) = %d\n", i2400m, result);
-	return result;
+	d_fnend(3, dev, "(i2400m %p) = 0\n", i2400m);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(i2400m_pre_reset);
 
diff --git a/drivers/net/wireless/at76c50x-usb.c b/drivers/net/wireless/at76c50x-usb.c
index 99b3bfa717d..d48776e4f34 100644
--- a/drivers/net/wireless/at76c50x-usb.c
+++ b/drivers/net/wireless/at76c50x-usb.c
@@ -365,15 +365,15 @@ static inline unsigned long at76_get_timeout(struct dfu_status *s)
 static int at76_usbdfu_download(struct usb_device *udev, u8 *buf, u32 size,
 				int manifest_sync_timeout)
 {
-	u8 *block;
-	struct dfu_status dfu_stat_buf;
 	int ret = 0;
 	int need_dfu_state = 1;
 	int is_done = 0;
-	u8 dfu_state = 0;
 	u32 dfu_timeout = 0;
 	int bsize = 0;
 	int blockno = 0;
+	struct dfu_status *dfu_stat_buf = NULL;
+	u8 *dfu_state = NULL;
+	u8 *block = NULL;
 
 	at76_dbg(DBG_DFU, "%s( %p, %u, %d)", __func__, buf, size,
 		 manifest_sync_timeout);
@@ -383,13 +383,28 @@ static int at76_usbdfu_download(struct usb_device *udev, u8 *buf, u32 size,
 		return -EINVAL;
 	}
 
+	dfu_stat_buf = kmalloc(sizeof(struct dfu_status), GFP_KERNEL);
+	if (!dfu_stat_buf) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
 	block = kmalloc(FW_BLOCK_SIZE, GFP_KERNEL);
-	if (!block)
-		return -ENOMEM;
+	if (!block) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	dfu_state = kmalloc(sizeof(u8), GFP_KERNEL);
+	if (!dfu_state) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+	*dfu_state = 0;
 
 	do {
 		if (need_dfu_state) {
-			ret = at76_dfu_get_state(udev, &dfu_state);
+			ret = at76_dfu_get_state(udev, dfu_state);
 			if (ret < 0) {
 				dev_err(&udev->dev,
 					"cannot get DFU state: %d\n", ret);
@@ -398,13 +413,13 @@ static int at76_usbdfu_download(struct usb_device *udev, u8 *buf, u32 size,
 			need_dfu_state = 0;
 		}
 
-		switch (dfu_state) {
+		switch (*dfu_state) {
 		case STATE_DFU_DOWNLOAD_SYNC:
 			at76_dbg(DBG_DFU, "STATE_DFU_DOWNLOAD_SYNC");
-			ret = at76_dfu_get_status(udev, &dfu_stat_buf);
+			ret = at76_dfu_get_status(udev, dfu_stat_buf);
 			if (ret >= 0) {
-				dfu_state = dfu_stat_buf.state;
-				dfu_timeout = at76_get_timeout(&dfu_stat_buf);
+				*dfu_state = dfu_stat_buf->state;
+				dfu_timeout = at76_get_timeout(dfu_stat_buf);
 				need_dfu_state = 0;
 			} else
 				dev_err(&udev->dev,
@@ -447,12 +462,12 @@ static int at76_usbdfu_download(struct usb_device *udev, u8 *buf, u32 size,
 		case STATE_DFU_MANIFEST_SYNC:
 			at76_dbg(DBG_DFU, "STATE_DFU_MANIFEST_SYNC");
 
-			ret = at76_dfu_get_status(udev, &dfu_stat_buf);
+			ret = at76_dfu_get_status(udev, dfu_stat_buf);
 			if (ret < 0)
 				break;
 
-			dfu_state = dfu_stat_buf.state;
-			dfu_timeout = at76_get_timeout(&dfu_stat_buf);
+			*dfu_state = dfu_stat_buf->state;
+			dfu_timeout = at76_get_timeout(dfu_stat_buf);
 			need_dfu_state = 0;
 
 			/* override the timeout from the status response,
@@ -484,14 +499,17 @@ static int at76_usbdfu_download(struct usb_device *udev, u8 *buf, u32 size,
 			break;
 
 		default:
-			at76_dbg(DBG_DFU, "DFU UNKNOWN STATE (%d)", dfu_state);
+			at76_dbg(DBG_DFU, "DFU UNKNOWN STATE (%d)", *dfu_state);
 			ret = -EINVAL;
 			break;
 		}
 	} while (!is_done && (ret >= 0));
 
 exit:
+	kfree(dfu_state);
 	kfree(block);
+	kfree(dfu_stat_buf);
+
 	if (ret >= 0)
 		ret = 0;
 
@@ -1277,6 +1295,7 @@ static int at76_load_external_fw(struct usb_device *udev, struct fwentry *fwe)
 			dev_err(&udev->dev,
 				"loading %dth firmware block failed: %d\n",
 				blockno, ret);
+			ret = -EIO;
 			goto exit;
 		}
 		buf += bsize;
@@ -1410,6 +1429,8 @@ static int at76_startup_device(struct at76_priv *priv)
 	/* remove BSSID from previous run */
 	memset(priv->bssid, 0, ETH_ALEN);
 
+	priv->scanning = false;
+
 	if (at76_set_radio(priv, 1) == 1)
 		at76_wait_completion(priv, CMD_RADIO_ON);
 
@@ -1483,6 +1504,52 @@ static void at76_work_submit_rx(struct work_struct *work)
 	mutex_unlock(&priv->mtx);
 }
 
+/* This is a workaround to make scan working:
+ * currently mac80211 does not process frames with no frequency
+ * information.
+ * However during scan the HW performs a sweep by itself, and we
+ * are unable to know where the radio is actually tuned.
+ * This function tries to do its best to guess this information..
+ * During scan, If the current frame is a beacon or a probe response,
+ * the channel information is extracted from it.
+ * When not scanning, for other frames, or if it happens that for
+ * whatever reason we fail to parse beacons and probe responses, this
+ * function returns the priv->channel information, that should be correct
+ * at least when we are not scanning.
+ */
+static inline int at76_guess_freq(struct at76_priv *priv)
+{
+	size_t el_off;
+	const u8 *el;
+	int channel = priv->channel;
+	int len = priv->rx_skb->len;
+	struct ieee80211_hdr *hdr = (void *)priv->rx_skb->data;
+
+	if (!priv->scanning)
+		goto exit;
+
+	if (len < 24)
+		goto exit;
+
+	if (ieee80211_is_probe_resp(hdr->frame_control)) {
+		el_off = offsetof(struct ieee80211_mgmt, u.probe_resp.variable);
+		el = ((struct ieee80211_mgmt *)hdr)->u.probe_resp.variable;
+	} else if (ieee80211_is_beacon(hdr->frame_control)) {
+		el_off = offsetof(struct ieee80211_mgmt, u.beacon.variable);
+		el = ((struct ieee80211_mgmt *)hdr)->u.beacon.variable;
+	} else {
+		goto exit;
+	}
+	len -= el_off;
+
+	el = cfg80211_find_ie(WLAN_EID_DS_PARAMS, el, len);
+	if (el && el[1] > 0)
+		channel = el[2];
+
+exit:
+	return ieee80211_channel_to_frequency(channel, IEEE80211_BAND_2GHZ);
+}
+
 static void at76_rx_tasklet(unsigned long param)
 {
 	struct urb *urb = (struct urb *)param;
@@ -1523,6 +1590,8 @@ static void at76_rx_tasklet(unsigned long param)
 	rx_status.signal = buf->rssi;
 	rx_status.flag |= RX_FLAG_DECRYPTED;
 	rx_status.flag |= RX_FLAG_IV_STRIPPED;
+	rx_status.band = IEEE80211_BAND_2GHZ;
+	rx_status.freq = at76_guess_freq(priv);
 
 	at76_dbg(DBG_MAC80211, "calling ieee80211_rx_irqsafe(): %d/%d",
 		 priv->rx_skb->len, priv->rx_skb->data_len);
@@ -1875,6 +1944,8 @@ static void at76_dwork_hw_scan(struct work_struct *work)
 	if (is_valid_ether_addr(priv->bssid))
 		at76_join(priv);
 
+	priv->scanning = false;
+
 	mutex_unlock(&priv->mtx);
 
 	ieee80211_scan_completed(priv->hw, false);
@@ -1929,6 +2000,7 @@ static int at76_hw_scan(struct ieee80211_hw *hw,
 		goto exit;
 	}
 
+	priv->scanning = true;
 	ieee80211_queue_delayed_work(priv->hw, &priv->dwork_hw_scan,
 				     SCAN_POLL_INTERVAL);
 
@@ -2020,6 +2092,44 @@ static void at76_configure_filter(struct ieee80211_hw *hw,
 	ieee80211_queue_work(hw, &priv->work_set_promisc);
 }
 
+static int at76_set_wep(struct at76_priv *priv)
+{
+	int ret = 0;
+	struct mib_mac_wep *mib_data = &priv->mib_buf.data.wep_mib;
+
+	priv->mib_buf.type = MIB_MAC_WEP;
+	priv->mib_buf.size = sizeof(struct mib_mac_wep);
+	priv->mib_buf.index = 0;
+
+	memset(mib_data, 0, sizeof(*mib_data));
+
+	if (priv->wep_enabled) {
+		if (priv->wep_keys_len[priv->wep_key_id] > WEP_SMALL_KEY_LEN)
+			mib_data->encryption_level = 2;
+		else
+			mib_data->encryption_level = 1;
+
+		/* always exclude unencrypted if WEP is active */
+		mib_data->exclude_unencrypted = 1;
+	} else {
+		mib_data->exclude_unencrypted = 0;
+		mib_data->encryption_level = 0;
+	}
+
+	mib_data->privacy_invoked = priv->wep_enabled;
+	mib_data->wep_default_key_id = priv->wep_key_id;
+	memcpy(mib_data->wep_default_keyvalue, priv->wep_keys,
+	       sizeof(priv->wep_keys));
+
+	ret = at76_set_mib(priv, &priv->mib_buf);
+
+	if (ret < 0)
+		wiphy_err(priv->hw->wiphy,
+			  "set_mib (wep) failed: %d\n", ret);
+
+	return ret;
+}
+
 static int at76_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			struct ieee80211_vif *vif, struct ieee80211_sta *sta,
 			struct ieee80211_key_conf *key)
@@ -2062,7 +2172,7 @@ static int at76_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			priv->wep_enabled = 1;
 	}
 
-	at76_startup_device(priv);
+	at76_set_wep(priv);
 
 	mutex_unlock(&priv->mtx);
 
@@ -2330,16 +2440,22 @@ static int at76_probe(struct usb_interface *interface,
 	struct usb_device *udev;
 	int op_mode;
 	int need_ext_fw = 0;
-	struct mib_fw_version fwv;
+	struct mib_fw_version *fwv = NULL;
 	int board_type = (int)id->driver_info;
 
 	udev = usb_get_dev(interface_to_usbdev(interface));
 
+	fwv = kmalloc(sizeof(*fwv), GFP_KERNEL);
+	if (!fwv) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
 	/* Load firmware into kernel memory */
 	fwe = at76_load_firmware(udev, board_type);
 	if (!fwe) {
 		ret = -ENOENT;
-		goto error;
+		goto exit;
 	}
 
 	op_mode = at76_get_op_mode(udev);
@@ -2353,7 +2469,7 @@ static int at76_probe(struct usb_interface *interface,
 		dev_err(&interface->dev,
 			"cannot handle a device in HW_CONFIG_MODE\n");
 		ret = -EBUSY;
-		goto error;
+		goto exit;
 	}
 
 	if (op_mode != OPMODE_NORMAL_NIC_WITH_FLASH
@@ -2366,10 +2482,10 @@ static int at76_probe(struct usb_interface *interface,
 			dev_err(&interface->dev,
 				"error %d downloading internal firmware\n",
 				ret);
-			goto error;
+			goto exit;
 		}
 		usb_put_dev(udev);
-		return ret;
+		goto exit;
 	}
 
 	/* Internal firmware already inside the device.  Get firmware
@@ -2382,8 +2498,8 @@ static int at76_probe(struct usb_interface *interface,
 	 * query the device for the fw version */
 	if ((fwe->fw_version.major > 0 || fwe->fw_version.minor >= 100)
 	    || (op_mode == OPMODE_NORMAL_NIC_WITH_FLASH)) {
-		ret = at76_get_mib(udev, MIB_FW_VERSION, &fwv, sizeof(fwv));
-		if (ret < 0 || (fwv.major | fwv.minor) == 0)
+		ret = at76_get_mib(udev, MIB_FW_VERSION, fwv, sizeof(*fwv));
+		if (ret < 0 || (fwv->major | fwv->minor) == 0)
 			need_ext_fw = 1;
 	} else
 		/* No way to check firmware version, reload to be sure */
@@ -2394,37 +2510,37 @@ static int at76_probe(struct usb_interface *interface,
 			   "downloading external firmware\n");
 
 		ret = at76_load_external_fw(udev, fwe);
-		if (ret)
-			goto error;
+		if (ret < 0)
+			goto exit;
 
 		/* Re-check firmware version */
-		ret = at76_get_mib(udev, MIB_FW_VERSION, &fwv, sizeof(fwv));
+		ret = at76_get_mib(udev, MIB_FW_VERSION, fwv, sizeof(*fwv));
 		if (ret < 0) {
 			dev_err(&interface->dev,
 				"error %d getting firmware version\n", ret);
-			goto error;
+			goto exit;
 		}
 	}
 
 	priv = at76_alloc_new_device(udev);
 	if (!priv) {
 		ret = -ENOMEM;
-		goto error;
+		goto exit;
 	}
 
 	usb_set_intfdata(interface, priv);
 
-	memcpy(&priv->fw_version, &fwv, sizeof(struct mib_fw_version));
+	memcpy(&priv->fw_version, fwv, sizeof(struct mib_fw_version));
 	priv->board_type = board_type;
 
 	ret = at76_init_new_device(priv, interface);
 	if (ret < 0)
 		at76_delete_device(priv);
 
-	return ret;
-
-error:
-	usb_put_dev(udev);
+exit:
+	kfree(fwv);
+	if (ret < 0)
+		usb_put_dev(udev);
 	return ret;
 }
 
diff --git a/drivers/net/wireless/at76c50x-usb.h b/drivers/net/wireless/at76c50x-usb.h
index f14a65473fe..55090a38ac9 100644
--- a/drivers/net/wireless/at76c50x-usb.h
+++ b/drivers/net/wireless/at76c50x-usb.h
@@ -219,18 +219,6 @@ struct at76_req_join {
 	u8 reserved;
 } __packed;
 
-struct set_mib_buffer {
-	u8 type;
-	u8 size;
-	u8 index;
-	u8 reserved;
-	union {
-		u8 byte;
-		__le16 word;
-		u8 addr[ETH_ALEN];
-	} data;
-} __packed;
-
 struct mib_local {
 	u16 reserved0;
 	u8 beacon_enable;
@@ -334,6 +322,19 @@ struct mib_mdomain {
 	u8 channel_list[14];	/* 0 for invalid channels */
 } __packed;
 
+struct set_mib_buffer {
+	u8 type;
+	u8 size;
+	u8 index;
+	u8 reserved;
+	union {
+		u8 byte;
+		__le16 word;
+		u8 addr[ETH_ALEN];
+		struct mib_mac_wep wep_mib;
+	} data;
+} __packed;
+
 struct at76_fw_header {
 	__le32 crc;		/* CRC32 of the whole image */
 	__le32 board_type;	/* firmware compatibility code */
@@ -417,6 +418,7 @@ struct at76_priv {
 	int scan_max_time;	/* scan max channel time */
 	int scan_mode;		/* SCAN_TYPE_ACTIVE, SCAN_TYPE_PASSIVE */
 	int scan_need_any;	/* if set, need to scan for any ESSID */
+	bool scanning;		/* if set, the scan is running */
 
 	u16 assoc_id;		/* current association ID, if associated */
 
diff --git a/drivers/net/wireless/ath/ar5523/ar5523.c b/drivers/net/wireless/ath/ar5523/ar5523.c
index 507d9a9ee69..f92050617ae 100644
--- a/drivers/net/wireless/ath/ar5523/ar5523.c
+++ b/drivers/net/wireless/ath/ar5523/ar5523.c
@@ -1090,7 +1090,8 @@ static int ar5523_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 	return ret;
 }
 
-static void ar5523_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void ar5523_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 u32 queues, bool drop)
 {
 	struct ar5523 *ar = hw->priv;
 
diff --git a/drivers/net/wireless/ath/ath10k/bmi.c b/drivers/net/wireless/ath/ath10k/bmi.c
index a1f09962885..17d221abd58 100644
--- a/drivers/net/wireless/ath/ath10k/bmi.c
+++ b/drivers/net/wireless/ath/ath10k/bmi.c
@@ -175,7 +175,7 @@ int ath10k_bmi_write_memory(struct ath10k *ar,
 	return 0;
 }
 
-int ath10k_bmi_execute(struct ath10k *ar, u32 address, u32 *param)
+int ath10k_bmi_execute(struct ath10k *ar, u32 address, u32 param, u32 *result)
 {
 	struct bmi_cmd cmd;
 	union bmi_resp resp;
@@ -184,7 +184,7 @@ int ath10k_bmi_execute(struct ath10k *ar, u32 address, u32 *param)
 	int ret;
 
 	ath10k_dbg(ATH10K_DBG_BMI, "bmi execute address 0x%x param 0x%x\n",
-		   address, *param);
+		   address, param);
 
 	if (ar->bmi.done_sent) {
 		ath10k_warn("command disallowed\n");
@@ -193,7 +193,7 @@ int ath10k_bmi_execute(struct ath10k *ar, u32 address, u32 *param)
 
 	cmd.id            = __cpu_to_le32(BMI_EXECUTE);
 	cmd.execute.addr  = __cpu_to_le32(address);
-	cmd.execute.param = __cpu_to_le32(*param);
+	cmd.execute.param = __cpu_to_le32(param);
 
 	ret = ath10k_hif_exchange_bmi_msg(ar, &cmd, cmdlen, &resp, &resplen);
 	if (ret) {
@@ -204,10 +204,13 @@ int ath10k_bmi_execute(struct ath10k *ar, u32 address, u32 *param)
 	if (resplen < sizeof(resp.execute)) {
 		ath10k_warn("invalid execute response length (%d)\n",
 			    resplen);
-		return ret;
+		return -EIO;
 	}
 
-	*param = __le32_to_cpu(resp.execute.result);
+	*result = __le32_to_cpu(resp.execute.result);
+
+	ath10k_dbg(ATH10K_DBG_BMI, "bmi execute result 0x%x\n", *result);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/bmi.h b/drivers/net/wireless/ath/ath10k/bmi.h
index 8d81ce1cec2..111ab701465 100644
--- a/drivers/net/wireless/ath/ath10k/bmi.h
+++ b/drivers/net/wireless/ath/ath10k/bmi.h
@@ -201,7 +201,8 @@ int ath10k_bmi_write_memory(struct ath10k *ar, u32 address,
 									\
 		addr = host_interest_item_address(HI_ITEM(item));	\
 		ret = ath10k_bmi_read_memory(ar, addr, (u8 *)&tmp, 4); \
-		*val = __le32_to_cpu(tmp);				\
+		if (!ret)						\
+			*val = __le32_to_cpu(tmp);			\
 		ret;							\
 	 })
 
@@ -217,7 +218,7 @@ int ath10k_bmi_write_memory(struct ath10k *ar, u32 address,
 		ret;							\
 	})
 
-int ath10k_bmi_execute(struct ath10k *ar, u32 address, u32 *param);
+int ath10k_bmi_execute(struct ath10k *ar, u32 address, u32 param, u32 *result);
 int ath10k_bmi_lz_stream_start(struct ath10k *ar, u32 address);
 int ath10k_bmi_lz_data(struct ath10k *ar, const void *buffer, u32 length);
 int ath10k_bmi_fast_download(struct ath10k *ar, u32 address,
diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c
index a79499c8235..d185dc0cd12 100644
--- a/drivers/net/wireless/ath/ath10k/ce.c
+++ b/drivers/net/wireless/ath/ath10k/ce.c
@@ -329,6 +329,33 @@ exit:
 	return ret;
 }
 
+void __ath10k_ce_send_revert(struct ath10k_ce_pipe *pipe)
+{
+	struct ath10k *ar = pipe->ar;
+	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+	struct ath10k_ce_ring *src_ring = pipe->src_ring;
+	u32 ctrl_addr = pipe->ctrl_addr;
+
+	lockdep_assert_held(&ar_pci->ce_lock);
+
+	/*
+	 * This function must be called only if there is an incomplete
+	 * scatter-gather transfer (before index register is updated)
+	 * that needs to be cleaned up.
+	 */
+	if (WARN_ON_ONCE(src_ring->write_index == src_ring->sw_index))
+		return;
+
+	if (WARN_ON_ONCE(src_ring->write_index ==
+			 ath10k_ce_src_ring_write_index_get(ar, ctrl_addr)))
+		return;
+
+	src_ring->write_index--;
+	src_ring->write_index &= src_ring->nentries_mask;
+
+	src_ring->per_transfer_context[src_ring->write_index] = NULL;
+}
+
 int ath10k_ce_send(struct ath10k_ce_pipe *ce_state,
 		   void *per_transfer_context,
 		   u32 buffer,
@@ -840,35 +867,17 @@ void ath10k_ce_recv_cb_register(struct ath10k_ce_pipe *ce_state,
 
 static int ath10k_ce_init_src_ring(struct ath10k *ar,
 				   unsigned int ce_id,
-				   struct ath10k_ce_pipe *ce_state,
 				   const struct ce_attr *attr)
 {
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
-	struct ath10k_ce_ring *src_ring;
-	unsigned int nentries = attr->src_nentries;
-	unsigned int ce_nbytes;
-	u32 ctrl_addr = ath10k_ce_base_address(ce_id);
-	dma_addr_t base_addr;
-	char *ptr;
-
-	nentries = roundup_pow_of_two(nentries);
-
-	if (ce_state->src_ring) {
-		WARN_ON(ce_state->src_ring->nentries != nentries);
-		return 0;
-	}
-
-	ce_nbytes = sizeof(struct ath10k_ce_ring) + (nentries * sizeof(void *));
-	ptr = kzalloc(ce_nbytes, GFP_KERNEL);
-	if (ptr == NULL)
-		return -ENOMEM;
+	struct ath10k_ce_pipe *ce_state = &ar_pci->ce_states[ce_id];
+	struct ath10k_ce_ring *src_ring = ce_state->src_ring;
+	u32 nentries, ctrl_addr = ath10k_ce_base_address(ce_id);
 
-	ce_state->src_ring = (struct ath10k_ce_ring *)ptr;
-	src_ring = ce_state->src_ring;
+	nentries = roundup_pow_of_two(attr->src_nentries);
 
-	ptr += sizeof(struct ath10k_ce_ring);
-	src_ring->nentries = nentries;
-	src_ring->nentries_mask = nentries - 1;
+	memset(src_ring->per_transfer_context, 0,
+	       nentries * sizeof(*src_ring->per_transfer_context));
 
 	src_ring->sw_index = ath10k_ce_src_ring_read_index_get(ar, ctrl_addr);
 	src_ring->sw_index &= src_ring->nentries_mask;
@@ -878,21 +887,87 @@ static int ath10k_ce_init_src_ring(struct ath10k *ar,
 		ath10k_ce_src_ring_write_index_get(ar, ctrl_addr);
 	src_ring->write_index &= src_ring->nentries_mask;
 
-	src_ring->per_transfer_context = (void **)ptr;
+	ath10k_ce_src_ring_base_addr_set(ar, ctrl_addr,
+					 src_ring->base_addr_ce_space);
+	ath10k_ce_src_ring_size_set(ar, ctrl_addr, nentries);
+	ath10k_ce_src_ring_dmax_set(ar, ctrl_addr, attr->src_sz_max);
+	ath10k_ce_src_ring_byte_swap_set(ar, ctrl_addr, 0);
+	ath10k_ce_src_ring_lowmark_set(ar, ctrl_addr, 0);
+	ath10k_ce_src_ring_highmark_set(ar, ctrl_addr, nentries);
+
+	ath10k_dbg(ATH10K_DBG_BOOT,
+		   "boot init ce src ring id %d entries %d base_addr %p\n",
+		   ce_id, nentries, src_ring->base_addr_owner_space);
+
+	return 0;
+}
+
+static int ath10k_ce_init_dest_ring(struct ath10k *ar,
+				    unsigned int ce_id,
+				    const struct ce_attr *attr)
+{
+	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+	struct ath10k_ce_pipe *ce_state = &ar_pci->ce_states[ce_id];
+	struct ath10k_ce_ring *dest_ring = ce_state->dest_ring;
+	u32 nentries, ctrl_addr = ath10k_ce_base_address(ce_id);
+
+	nentries = roundup_pow_of_two(attr->dest_nentries);
+
+	memset(dest_ring->per_transfer_context, 0,
+	       nentries * sizeof(*dest_ring->per_transfer_context));
+
+	dest_ring->sw_index = ath10k_ce_dest_ring_read_index_get(ar, ctrl_addr);
+	dest_ring->sw_index &= dest_ring->nentries_mask;
+	dest_ring->write_index =
+		ath10k_ce_dest_ring_write_index_get(ar, ctrl_addr);
+	dest_ring->write_index &= dest_ring->nentries_mask;
+
+	ath10k_ce_dest_ring_base_addr_set(ar, ctrl_addr,
+					  dest_ring->base_addr_ce_space);
+	ath10k_ce_dest_ring_size_set(ar, ctrl_addr, nentries);
+	ath10k_ce_dest_ring_byte_swap_set(ar, ctrl_addr, 0);
+	ath10k_ce_dest_ring_lowmark_set(ar, ctrl_addr, 0);
+	ath10k_ce_dest_ring_highmark_set(ar, ctrl_addr, nentries);
+
+	ath10k_dbg(ATH10K_DBG_BOOT,
+		   "boot ce dest ring id %d entries %d base_addr %p\n",
+		   ce_id, nentries, dest_ring->base_addr_owner_space);
+
+	return 0;
+}
+
+static struct ath10k_ce_ring *
+ath10k_ce_alloc_src_ring(struct ath10k *ar, unsigned int ce_id,
+			 const struct ce_attr *attr)
+{
+	struct ath10k_ce_ring *src_ring;
+	u32 nentries = attr->src_nentries;
+	dma_addr_t base_addr;
+
+	nentries = roundup_pow_of_two(nentries);
+
+	src_ring = kzalloc(sizeof(*src_ring) +
+			   (nentries *
+			    sizeof(*src_ring->per_transfer_context)),
+			   GFP_KERNEL);
+	if (src_ring == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	src_ring->nentries = nentries;
+	src_ring->nentries_mask = nentries - 1;
 
 	/*
 	 * Legacy platforms that do not support cache
 	 * coherent DMA are unsupported
 	 */
 	src_ring->base_addr_owner_space_unaligned =
-		pci_alloc_consistent(ar_pci->pdev,
-				     (nentries * sizeof(struct ce_desc) +
-				      CE_DESC_RING_ALIGN),
-				     &base_addr);
+		dma_alloc_coherent(ar->dev,
+				   (nentries * sizeof(struct ce_desc) +
+				    CE_DESC_RING_ALIGN),
+				   &base_addr, GFP_KERNEL);
 	if (!src_ring->base_addr_owner_space_unaligned) {
-		kfree(ce_state->src_ring);
-		ce_state->src_ring = NULL;
-		return -ENOMEM;
+		kfree(src_ring);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	src_ring->base_addr_ce_space_unaligned = base_addr;
@@ -912,88 +987,54 @@ static int ath10k_ce_init_src_ring(struct ath10k *ar,
 		kmalloc((nentries * sizeof(struct ce_desc) +
 			 CE_DESC_RING_ALIGN), GFP_KERNEL);
 	if (!src_ring->shadow_base_unaligned) {
-		pci_free_consistent(ar_pci->pdev,
-				    (nentries * sizeof(struct ce_desc) +
-				     CE_DESC_RING_ALIGN),
-				    src_ring->base_addr_owner_space,
-				    src_ring->base_addr_ce_space);
-		kfree(ce_state->src_ring);
-		ce_state->src_ring = NULL;
-		return -ENOMEM;
+		dma_free_coherent(ar->dev,
+				  (nentries * sizeof(struct ce_desc) +
+				   CE_DESC_RING_ALIGN),
+				  src_ring->base_addr_owner_space,
+				  src_ring->base_addr_ce_space);
+		kfree(src_ring);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	src_ring->shadow_base = PTR_ALIGN(
 			src_ring->shadow_base_unaligned,
 			CE_DESC_RING_ALIGN);
 
-	ath10k_ce_src_ring_base_addr_set(ar, ctrl_addr,
-					 src_ring->base_addr_ce_space);
-	ath10k_ce_src_ring_size_set(ar, ctrl_addr, nentries);
-	ath10k_ce_src_ring_dmax_set(ar, ctrl_addr, attr->src_sz_max);
-	ath10k_ce_src_ring_byte_swap_set(ar, ctrl_addr, 0);
-	ath10k_ce_src_ring_lowmark_set(ar, ctrl_addr, 0);
-	ath10k_ce_src_ring_highmark_set(ar, ctrl_addr, nentries);
-
-	ath10k_dbg(ATH10K_DBG_BOOT,
-		   "boot ce src ring id %d entries %d base_addr %p\n",
-		   ce_id, nentries, src_ring->base_addr_owner_space);
-
-	return 0;
+	return src_ring;
 }
 
-static int ath10k_ce_init_dest_ring(struct ath10k *ar,
-				    unsigned int ce_id,
-				    struct ath10k_ce_pipe *ce_state,
-				    const struct ce_attr *attr)
+static struct ath10k_ce_ring *
+ath10k_ce_alloc_dest_ring(struct ath10k *ar, unsigned int ce_id,
+			  const struct ce_attr *attr)
 {
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 	struct ath10k_ce_ring *dest_ring;
-	unsigned int nentries = attr->dest_nentries;
-	unsigned int ce_nbytes;
-	u32 ctrl_addr = ath10k_ce_base_address(ce_id);
+	u32 nentries;
 	dma_addr_t base_addr;
-	char *ptr;
 
-	nentries = roundup_pow_of_two(nentries);
+	nentries = roundup_pow_of_two(attr->dest_nentries);
 
-	if (ce_state->dest_ring) {
-		WARN_ON(ce_state->dest_ring->nentries != nentries);
-		return 0;
-	}
-
-	ce_nbytes = sizeof(struct ath10k_ce_ring) + (nentries * sizeof(void *));
-	ptr = kzalloc(ce_nbytes, GFP_KERNEL);
-	if (ptr == NULL)
-		return -ENOMEM;
+	dest_ring = kzalloc(sizeof(*dest_ring) +
+			    (nentries *
+			     sizeof(*dest_ring->per_transfer_context)),
+			    GFP_KERNEL);
+	if (dest_ring == NULL)
+		return ERR_PTR(-ENOMEM);
 
-	ce_state->dest_ring = (struct ath10k_ce_ring *)ptr;
-	dest_ring = ce_state->dest_ring;
-
-	ptr += sizeof(struct ath10k_ce_ring);
 	dest_ring->nentries = nentries;
 	dest_ring->nentries_mask = nentries - 1;
 
-	dest_ring->sw_index = ath10k_ce_dest_ring_read_index_get(ar, ctrl_addr);
-	dest_ring->sw_index &= dest_ring->nentries_mask;
-	dest_ring->write_index =
-		ath10k_ce_dest_ring_write_index_get(ar, ctrl_addr);
-	dest_ring->write_index &= dest_ring->nentries_mask;
-
-	dest_ring->per_transfer_context = (void **)ptr;
-
 	/*
 	 * Legacy platforms that do not support cache
 	 * coherent DMA are unsupported
 	 */
 	dest_ring->base_addr_owner_space_unaligned =
-		pci_alloc_consistent(ar_pci->pdev,
-				     (nentries * sizeof(struct ce_desc) +
-				      CE_DESC_RING_ALIGN),
-				     &base_addr);
+		dma_alloc_coherent(ar->dev,
+				   (nentries * sizeof(struct ce_desc) +
+				    CE_DESC_RING_ALIGN),
+				   &base_addr, GFP_KERNEL);
 	if (!dest_ring->base_addr_owner_space_unaligned) {
-		kfree(ce_state->dest_ring);
-		ce_state->dest_ring = NULL;
-		return -ENOMEM;
+		kfree(dest_ring);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	dest_ring->base_addr_ce_space_unaligned = base_addr;
@@ -1012,39 +1053,7 @@ static int ath10k_ce_init_dest_ring(struct ath10k *ar,
 			dest_ring->base_addr_ce_space_unaligned,
 			CE_DESC_RING_ALIGN);
 
-	ath10k_ce_dest_ring_base_addr_set(ar, ctrl_addr,
-					  dest_ring->base_addr_ce_space);
-	ath10k_ce_dest_ring_size_set(ar, ctrl_addr, nentries);
-	ath10k_ce_dest_ring_byte_swap_set(ar, ctrl_addr, 0);
-	ath10k_ce_dest_ring_lowmark_set(ar, ctrl_addr, 0);
-	ath10k_ce_dest_ring_highmark_set(ar, ctrl_addr, nentries);
-
-	ath10k_dbg(ATH10K_DBG_BOOT,
-		   "boot ce dest ring id %d entries %d base_addr %p\n",
-		   ce_id, nentries, dest_ring->base_addr_owner_space);
-
-	return 0;
-}
-
-static struct ath10k_ce_pipe *ath10k_ce_init_state(struct ath10k *ar,
-					     unsigned int ce_id,
-					     const struct ce_attr *attr)
-{
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
-	struct ath10k_ce_pipe *ce_state = &ar_pci->ce_states[ce_id];
-	u32 ctrl_addr = ath10k_ce_base_address(ce_id);
-
-	spin_lock_bh(&ar_pci->ce_lock);
-
-	ce_state->ar = ar;
-	ce_state->id = ce_id;
-	ce_state->ctrl_addr = ctrl_addr;
-	ce_state->attr_flags = attr->flags;
-	ce_state->src_sz_max = attr->src_sz_max;
-
-	spin_unlock_bh(&ar_pci->ce_lock);
-
-	return ce_state;
+	return dest_ring;
 }
 
 /*
@@ -1054,11 +1063,11 @@ static struct ath10k_ce_pipe *ath10k_ce_init_state(struct ath10k *ar,
  * initialization. It may be that only one side or the other is
  * initialized by software/firmware.
  */
-struct ath10k_ce_pipe *ath10k_ce_init(struct ath10k *ar,
-				unsigned int ce_id,
-				const struct ce_attr *attr)
+int ath10k_ce_init_pipe(struct ath10k *ar, unsigned int ce_id,
+			const struct ce_attr *attr)
 {
-	struct ath10k_ce_pipe *ce_state;
+	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+	struct ath10k_ce_pipe *ce_state = &ar_pci->ce_states[ce_id];
 	int ret;
 
 	/*
@@ -1074,64 +1083,128 @@ struct ath10k_ce_pipe *ath10k_ce_init(struct ath10k *ar,
 
 	ret = ath10k_pci_wake(ar);
 	if (ret)
-		return NULL;
+		return ret;
 
-	ce_state = ath10k_ce_init_state(ar, ce_id, attr);
-	if (!ce_state) {
-		ath10k_err("Failed to initialize CE state for ID: %d\n", ce_id);
-		goto out;
-	}
+	spin_lock_bh(&ar_pci->ce_lock);
+	ce_state->ar = ar;
+	ce_state->id = ce_id;
+	ce_state->ctrl_addr = ath10k_ce_base_address(ce_id);
+	ce_state->attr_flags = attr->flags;
+	ce_state->src_sz_max = attr->src_sz_max;
+	spin_unlock_bh(&ar_pci->ce_lock);
 
 	if (attr->src_nentries) {
-		ret = ath10k_ce_init_src_ring(ar, ce_id, ce_state, attr);
+		ret = ath10k_ce_init_src_ring(ar, ce_id, attr);
 		if (ret) {
 			ath10k_err("Failed to initialize CE src ring for ID: %d (%d)\n",
 				   ce_id, ret);
-			ath10k_ce_deinit(ce_state);
-			ce_state = NULL;
 			goto out;
 		}
 	}
 
 	if (attr->dest_nentries) {
-		ret = ath10k_ce_init_dest_ring(ar, ce_id, ce_state, attr);
+		ret = ath10k_ce_init_dest_ring(ar, ce_id, attr);
 		if (ret) {
 			ath10k_err("Failed to initialize CE dest ring for ID: %d (%d)\n",
 				   ce_id, ret);
-			ath10k_ce_deinit(ce_state);
-			ce_state = NULL;
 			goto out;
 		}
 	}
 
 out:
 	ath10k_pci_sleep(ar);
-	return ce_state;
+	return ret;
 }
 
-void ath10k_ce_deinit(struct ath10k_ce_pipe *ce_state)
+static void ath10k_ce_deinit_src_ring(struct ath10k *ar, unsigned int ce_id)
+{
+	u32 ctrl_addr = ath10k_ce_base_address(ce_id);
+
+	ath10k_ce_src_ring_base_addr_set(ar, ctrl_addr, 0);
+	ath10k_ce_src_ring_size_set(ar, ctrl_addr, 0);
+	ath10k_ce_src_ring_dmax_set(ar, ctrl_addr, 0);
+	ath10k_ce_src_ring_highmark_set(ar, ctrl_addr, 0);
+}
+
+static void ath10k_ce_deinit_dest_ring(struct ath10k *ar, unsigned int ce_id)
+{
+	u32 ctrl_addr = ath10k_ce_base_address(ce_id);
+
+	ath10k_ce_dest_ring_base_addr_set(ar, ctrl_addr, 0);
+	ath10k_ce_dest_ring_size_set(ar, ctrl_addr, 0);
+	ath10k_ce_dest_ring_highmark_set(ar, ctrl_addr, 0);
+}
+
+void ath10k_ce_deinit_pipe(struct ath10k *ar, unsigned int ce_id)
+{
+	int ret;
+
+	ret = ath10k_pci_wake(ar);
+	if (ret)
+		return;
+
+	ath10k_ce_deinit_src_ring(ar, ce_id);
+	ath10k_ce_deinit_dest_ring(ar, ce_id);
+
+	ath10k_pci_sleep(ar);
+}
+
+int ath10k_ce_alloc_pipe(struct ath10k *ar, int ce_id,
+			 const struct ce_attr *attr)
+{
+	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+	struct ath10k_ce_pipe *ce_state = &ar_pci->ce_states[ce_id];
+	int ret;
+
+	if (attr->src_nentries) {
+		ce_state->src_ring = ath10k_ce_alloc_src_ring(ar, ce_id, attr);
+		if (IS_ERR(ce_state->src_ring)) {
+			ret = PTR_ERR(ce_state->src_ring);
+			ath10k_err("failed to allocate copy engine source ring %d: %d\n",
+				   ce_id, ret);
+			ce_state->src_ring = NULL;
+			return ret;
+		}
+	}
+
+	if (attr->dest_nentries) {
+		ce_state->dest_ring = ath10k_ce_alloc_dest_ring(ar, ce_id,
+								attr);
+		if (IS_ERR(ce_state->dest_ring)) {
+			ret = PTR_ERR(ce_state->dest_ring);
+			ath10k_err("failed to allocate copy engine destination ring %d: %d\n",
+				   ce_id, ret);
+			ce_state->dest_ring = NULL;
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+void ath10k_ce_free_pipe(struct ath10k *ar, int ce_id)
 {
-	struct ath10k *ar = ce_state->ar;
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+	struct ath10k_ce_pipe *ce_state = &ar_pci->ce_states[ce_id];
 
 	if (ce_state->src_ring) {
 		kfree(ce_state->src_ring->shadow_base_unaligned);
-		pci_free_consistent(ar_pci->pdev,
-				    (ce_state->src_ring->nentries *
-				     sizeof(struct ce_desc) +
-				     CE_DESC_RING_ALIGN),
-				    ce_state->src_ring->base_addr_owner_space,
-				    ce_state->src_ring->base_addr_ce_space);
+		dma_free_coherent(ar->dev,
+				  (ce_state->src_ring->nentries *
+				   sizeof(struct ce_desc) +
+				   CE_DESC_RING_ALIGN),
+				  ce_state->src_ring->base_addr_owner_space,
+				  ce_state->src_ring->base_addr_ce_space);
 		kfree(ce_state->src_ring);
 	}
 
 	if (ce_state->dest_ring) {
-		pci_free_consistent(ar_pci->pdev,
-				    (ce_state->dest_ring->nentries *
-				     sizeof(struct ce_desc) +
-				     CE_DESC_RING_ALIGN),
-				    ce_state->dest_ring->base_addr_owner_space,
-				    ce_state->dest_ring->base_addr_ce_space);
+		dma_free_coherent(ar->dev,
+				  (ce_state->dest_ring->nentries *
+				   sizeof(struct ce_desc) +
+				   CE_DESC_RING_ALIGN),
+				  ce_state->dest_ring->base_addr_owner_space,
+				  ce_state->dest_ring->base_addr_ce_space);
 		kfree(ce_state->dest_ring);
 	}
 
diff --git a/drivers/net/wireless/ath/ath10k/ce.h b/drivers/net/wireless/ath/ath10k/ce.h
index 8eb7f99ed99..7a5a36fc59c 100644
--- a/drivers/net/wireless/ath/ath10k/ce.h
+++ b/drivers/net/wireless/ath/ath10k/ce.h
@@ -104,7 +104,8 @@ struct ath10k_ce_ring {
 	void *shadow_base_unaligned;
 	struct ce_desc *shadow_base;
 
-	void **per_transfer_context;
+	/* keep last */
+	void *per_transfer_context[0];
 };
 
 struct ath10k_ce_pipe {
@@ -159,6 +160,8 @@ int ath10k_ce_send_nolock(struct ath10k_ce_pipe *ce_state,
 			  unsigned int transfer_id,
 			  unsigned int flags);
 
+void __ath10k_ce_send_revert(struct ath10k_ce_pipe *pipe);
+
 void ath10k_ce_send_cb_register(struct ath10k_ce_pipe *ce_state,
 				void (*send_cb)(struct ath10k_ce_pipe *),
 				int disable_interrupts);
@@ -210,10 +213,12 @@ int ath10k_ce_completed_send_next(struct ath10k_ce_pipe *ce_state,
 
 /*==================CE Engine Initialization=======================*/
 
-/* Initialize an instance of a CE */
-struct ath10k_ce_pipe *ath10k_ce_init(struct ath10k *ar,
-				unsigned int ce_id,
-				const struct ce_attr *attr);
+int ath10k_ce_init_pipe(struct ath10k *ar, unsigned int ce_id,
+			const struct ce_attr *attr);
+void ath10k_ce_deinit_pipe(struct ath10k *ar, unsigned int ce_id);
+int ath10k_ce_alloc_pipe(struct ath10k *ar, int ce_id,
+			  const struct ce_attr *attr);
+void ath10k_ce_free_pipe(struct ath10k *ar, int ce_id);
 
 /*==================CE Engine Shutdown=======================*/
 /*
@@ -236,8 +241,6 @@ int ath10k_ce_cancel_send_next(struct ath10k_ce_pipe *ce_state,
 			       unsigned int *nbytesp,
 			       unsigned int *transfer_idp);
 
-void ath10k_ce_deinit(struct ath10k_ce_pipe *ce_state);
-
 /*==================CE Interrupt Handlers====================*/
 void ath10k_ce_per_engine_service_any(struct ath10k *ar);
 void ath10k_ce_per_engine_service(struct ath10k *ar, unsigned int ce_id);
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index ebc5fc2ede7..e6c56c5bb0f 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -58,36 +58,6 @@ static void ath10k_send_suspend_complete(struct ath10k *ar)
 	complete(&ar->target_suspend);
 }
 
-static int ath10k_init_connect_htc(struct ath10k *ar)
-{
-	int status;
-
-	status = ath10k_wmi_connect_htc_service(ar);
-	if (status)
-		goto conn_fail;
-
-	/* Start HTC */
-	status = ath10k_htc_start(&ar->htc);
-	if (status)
-		goto conn_fail;
-
-	/* Wait for WMI event to be ready */
-	status = ath10k_wmi_wait_for_service_ready(ar);
-	if (status <= 0) {
-		ath10k_warn("wmi service ready event not received");
-		status = -ETIMEDOUT;
-		goto timeout;
-	}
-
-	ath10k_dbg(ATH10K_DBG_BOOT, "boot wmi ready\n");
-	return 0;
-
-timeout:
-	ath10k_htc_stop(&ar->htc);
-conn_fail:
-	return status;
-}
-
 static int ath10k_init_configure_target(struct ath10k *ar)
 {
 	u32 param_host;
@@ -249,30 +219,40 @@ exit:
 
 static int ath10k_download_and_run_otp(struct ath10k *ar)
 {
-	u32 address = ar->hw_params.patch_load_addr;
-	u32 exec_param;
+	u32 result, address = ar->hw_params.patch_load_addr;
 	int ret;
 
 	/* OTP is optional */
 
-	if (!ar->otp_data || !ar->otp_len)
+	if (!ar->otp_data || !ar->otp_len) {
+		ath10k_warn("Not running otp, calibration will be incorrect (otp-data %p otp_len %zd)!\n",
+			    ar->otp_data, ar->otp_len);
 		return 0;
+	}
+
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot upload otp to 0x%x len %zd\n",
+		   address, ar->otp_len);
 
 	ret = ath10k_bmi_fast_download(ar, address, ar->otp_data, ar->otp_len);
 	if (ret) {
 		ath10k_err("could not write otp (%d)\n", ret);
-		goto exit;
+		return ret;
 	}
 
-	exec_param = 0;
-	ret = ath10k_bmi_execute(ar, address, &exec_param);
+	ret = ath10k_bmi_execute(ar, address, 0, &result);
 	if (ret) {
 		ath10k_err("could not execute otp (%d)\n", ret);
-		goto exit;
+		return ret;
 	}
 
-exit:
-	return ret;
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot otp execute result %d\n", result);
+
+	if (result != 0) {
+		ath10k_err("otp calibration failed: %d", result);
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 static int ath10k_download_fw(struct ath10k *ar)
@@ -389,8 +369,8 @@ static int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name)
 	/* first fetch the firmware file (firmware-*.bin) */
 	ar->firmware = ath10k_fetch_fw_file(ar, ar->hw_params.fw.dir, name);
 	if (IS_ERR(ar->firmware)) {
-		ath10k_err("Could not fetch firmware file '%s': %ld\n",
-			   name, PTR_ERR(ar->firmware));
+		ath10k_err("could not fetch firmware file '%s/%s': %ld\n",
+			   ar->hw_params.fw.dir, name, PTR_ERR(ar->firmware));
 		return PTR_ERR(ar->firmware);
 	}
 
@@ -401,14 +381,14 @@ static int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name)
 	magic_len = strlen(ATH10K_FIRMWARE_MAGIC) + 1;
 
 	if (len < magic_len) {
-		ath10k_err("firmware image too small to contain magic: %zu\n",
-			   len);
+		ath10k_err("firmware file '%s/%s' too small to contain magic: %zu\n",
+			   ar->hw_params.fw.dir, name, len);
 		ret = -EINVAL;
 		goto err;
 	}
 
 	if (memcmp(data, ATH10K_FIRMWARE_MAGIC, magic_len) != 0) {
-		ath10k_err("Invalid firmware magic\n");
+		ath10k_err("invalid firmware magic\n");
 		ret = -EINVAL;
 		goto err;
 	}
@@ -430,7 +410,7 @@ static int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name)
 		data += sizeof(*hdr);
 
 		if (len < ie_len) {
-			ath10k_err("Invalid length for FW IE %d (%zu < %zu)\n",
+			ath10k_err("invalid length for FW IE %d (%zu < %zu)\n",
 				   ie_id, len, ie_len);
 			ret = -EINVAL;
 			goto err;
@@ -513,8 +493,8 @@ static int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name)
 	}
 
 	if (!ar->firmware_data || !ar->firmware_len) {
-		ath10k_warn("No ATH10K_FW_IE_FW_IMAGE found from %s, skipping\n",
-			    name);
+		ath10k_warn("No ATH10K_FW_IE_FW_IMAGE found from '%s/%s', skipping\n",
+			    ar->hw_params.fw.dir, name);
 		ret = -ENOMEDIUM;
 		goto err;
 	}
@@ -531,7 +511,9 @@ static int ath10k_core_fetch_firmware_api_n(struct ath10k *ar, const char *name)
 					 ar->hw_params.fw.board);
 	if (IS_ERR(ar->board)) {
 		ret = PTR_ERR(ar->board);
-		ath10k_err("could not fetch board data (%d)\n", ret);
+		ath10k_err("could not fetch board data '%s/%s' (%d)\n",
+			   ar->hw_params.fw.dir, ar->hw_params.fw.board,
+			   ret);
 		goto err;
 	}
 
@@ -549,19 +531,21 @@ static int ath10k_core_fetch_firmware_files(struct ath10k *ar)
 {
 	int ret;
 
+	ar->fw_api = 2;
+	ath10k_dbg(ATH10K_DBG_BOOT, "trying fw api %d\n", ar->fw_api);
+
 	ret = ath10k_core_fetch_firmware_api_n(ar, ATH10K_FW_API2_FILE);
-	if (ret == 0) {
-		ar->fw_api = 2;
-		goto out;
-	}
+	if (ret == 0)
+		goto success;
+
+	ar->fw_api = 1;
+	ath10k_dbg(ATH10K_DBG_BOOT, "trying fw api %d\n", ar->fw_api);
 
 	ret = ath10k_core_fetch_firmware_api_1(ar);
 	if (ret)
 		return ret;
 
-	ar->fw_api = 1;
-
-out:
+success:
 	ath10k_dbg(ATH10K_DBG_BOOT, "using fw api %d\n", ar->fw_api);
 
 	return 0;
@@ -572,16 +556,22 @@ static int ath10k_init_download_firmware(struct ath10k *ar)
 	int ret;
 
 	ret = ath10k_download_board_data(ar);
-	if (ret)
+	if (ret) {
+		ath10k_err("failed to download board data: %d\n", ret);
 		return ret;
+	}
 
 	ret = ath10k_download_and_run_otp(ar);
-	if (ret)
+	if (ret) {
+		ath10k_err("failed to run otp: %d\n", ret);
 		return ret;
+	}
 
 	ret = ath10k_download_fw(ar);
-	if (ret)
+	if (ret) {
+		ath10k_err("failed to download firmware: %d\n", ret);
 		return ret;
+	}
 
 	return ret;
 }
@@ -660,8 +650,9 @@ static void ath10k_core_restart(struct work_struct *work)
 
 	switch (ar->state) {
 	case ATH10K_STATE_ON:
-		ath10k_halt(ar);
 		ar->state = ATH10K_STATE_RESTARTING;
+		del_timer_sync(&ar->scan.timeout);
+		ath10k_reset_scan((unsigned long)ar);
 		ieee80211_restart_hw(ar->hw);
 		break;
 	case ATH10K_STATE_OFF:
@@ -670,6 +661,8 @@ static void ath10k_core_restart(struct work_struct *work)
 		ath10k_warn("cannot restart a device that hasn't been started\n");
 		break;
 	case ATH10K_STATE_RESTARTING:
+		/* hw restart might be requested from multiple places */
+		break;
 	case ATH10K_STATE_RESTARTED:
 		ar->state = ATH10K_STATE_WEDGED;
 		/* fall through */
@@ -681,70 +674,6 @@ static void ath10k_core_restart(struct work_struct *work)
 	mutex_unlock(&ar->conf_mutex);
 }
 
-struct ath10k *ath10k_core_create(void *hif_priv, struct device *dev,
-				  const struct ath10k_hif_ops *hif_ops)
-{
-	struct ath10k *ar;
-
-	ar = ath10k_mac_create();
-	if (!ar)
-		return NULL;
-
-	ar->ath_common.priv = ar;
-	ar->ath_common.hw = ar->hw;
-
-	ar->p2p = !!ath10k_p2p;
-	ar->dev = dev;
-
-	ar->hif.priv = hif_priv;
-	ar->hif.ops = hif_ops;
-
-	init_completion(&ar->scan.started);
-	init_completion(&ar->scan.completed);
-	init_completion(&ar->scan.on_channel);
-	init_completion(&ar->target_suspend);
-
-	init_completion(&ar->install_key_done);
-	init_completion(&ar->vdev_setup_done);
-
-	setup_timer(&ar->scan.timeout, ath10k_reset_scan, (unsigned long)ar);
-
-	ar->workqueue = create_singlethread_workqueue("ath10k_wq");
-	if (!ar->workqueue)
-		goto err_wq;
-
-	mutex_init(&ar->conf_mutex);
-	spin_lock_init(&ar->data_lock);
-
-	INIT_LIST_HEAD(&ar->peers);
-	init_waitqueue_head(&ar->peer_mapping_wq);
-
-	init_completion(&ar->offchan_tx_completed);
-	INIT_WORK(&ar->offchan_tx_work, ath10k_offchan_tx_work);
-	skb_queue_head_init(&ar->offchan_tx_queue);
-
-	INIT_WORK(&ar->wmi_mgmt_tx_work, ath10k_mgmt_over_wmi_tx_work);
-	skb_queue_head_init(&ar->wmi_mgmt_tx_queue);
-
-	INIT_WORK(&ar->restart_work, ath10k_core_restart);
-
-	return ar;
-
-err_wq:
-	ath10k_mac_destroy(ar);
-	return NULL;
-}
-EXPORT_SYMBOL(ath10k_core_create);
-
-void ath10k_core_destroy(struct ath10k *ar)
-{
-	flush_workqueue(ar->workqueue);
-	destroy_workqueue(ar->workqueue);
-
-	ath10k_mac_destroy(ar);
-}
-EXPORT_SYMBOL(ath10k_core_destroy);
-
 int ath10k_core_start(struct ath10k *ar)
 {
 	int status;
@@ -785,10 +714,28 @@ int ath10k_core_start(struct ath10k *ar)
 		goto err;
 	}
 
+	status = ath10k_htt_init(ar);
+	if (status) {
+		ath10k_err("failed to init htt: %d\n", status);
+		goto err_wmi_detach;
+	}
+
+	status = ath10k_htt_tx_alloc(&ar->htt);
+	if (status) {
+		ath10k_err("failed to alloc htt tx: %d\n", status);
+		goto err_wmi_detach;
+	}
+
+	status = ath10k_htt_rx_alloc(&ar->htt);
+	if (status) {
+		ath10k_err("failed to alloc htt rx: %d\n", status);
+		goto err_htt_tx_detach;
+	}
+
 	status = ath10k_hif_start(ar);
 	if (status) {
 		ath10k_err("could not start HIF: %d\n", status);
-		goto err_wmi_detach;
+		goto err_htt_rx_detach;
 	}
 
 	status = ath10k_htc_wait_target(&ar->htc);
@@ -797,15 +744,30 @@ int ath10k_core_start(struct ath10k *ar)
 		goto err_hif_stop;
 	}
 
-	status = ath10k_htt_attach(ar);
+	status = ath10k_htt_connect(&ar->htt);
 	if (status) {
-		ath10k_err("could not attach htt (%d)\n", status);
+		ath10k_err("failed to connect htt (%d)\n", status);
 		goto err_hif_stop;
 	}
 
-	status = ath10k_init_connect_htc(ar);
-	if (status)
-		goto err_htt_detach;
+	status = ath10k_wmi_connect(ar);
+	if (status) {
+		ath10k_err("could not connect wmi: %d\n", status);
+		goto err_hif_stop;
+	}
+
+	status = ath10k_htc_start(&ar->htc);
+	if (status) {
+		ath10k_err("failed to start htc: %d\n", status);
+		goto err_hif_stop;
+	}
+
+	status = ath10k_wmi_wait_for_service_ready(ar);
+	if (status <= 0) {
+		ath10k_warn("wmi service ready event not received");
+		status = -ETIMEDOUT;
+		goto err_htc_stop;
+	}
 
 	ath10k_dbg(ATH10K_DBG_BOOT, "firmware %s booted\n",
 		   ar->hw->wiphy->fw_version);
@@ -813,31 +775,40 @@ int ath10k_core_start(struct ath10k *ar)
 	status = ath10k_wmi_cmd_init(ar);
 	if (status) {
 		ath10k_err("could not send WMI init command (%d)\n", status);
-		goto err_disconnect_htc;
+		goto err_htc_stop;
 	}
 
 	status = ath10k_wmi_wait_for_unified_ready(ar);
 	if (status <= 0) {
 		ath10k_err("wmi unified ready event not received\n");
 		status = -ETIMEDOUT;
-		goto err_disconnect_htc;
+		goto err_htc_stop;
 	}
 
-	status = ath10k_htt_attach_target(&ar->htt);
-	if (status)
-		goto err_disconnect_htc;
+	status = ath10k_htt_setup(&ar->htt);
+	if (status) {
+		ath10k_err("failed to setup htt: %d\n", status);
+		goto err_htc_stop;
+	}
 
 	status = ath10k_debug_start(ar);
 	if (status)
-		goto err_disconnect_htc;
+		goto err_htc_stop;
+
+	if (test_bit(ATH10K_FW_FEATURE_WMI_10X, ar->fw_features))
+		ar->free_vdev_map = (1 << TARGET_10X_NUM_VDEVS) - 1;
+	else
+		ar->free_vdev_map = (1 << TARGET_NUM_VDEVS) - 1;
 
-	ar->free_vdev_map = (1 << TARGET_NUM_VDEVS) - 1;
 	INIT_LIST_HEAD(&ar->arvifs);
 
 	if (!test_bit(ATH10K_FLAG_FIRST_BOOT_DONE, &ar->dev_flags))
-		ath10k_info("%s (0x%x) fw %s api %d htt %d.%d\n",
-			    ar->hw_params.name, ar->target_version,
-			    ar->hw->wiphy->fw_version, ar->fw_api,
+		ath10k_info("%s (0x%08x, 0x%08x) fw %s api %d htt %d.%d\n",
+			    ar->hw_params.name,
+			    ar->target_version,
+			    ar->chip_id,
+			    ar->hw->wiphy->fw_version,
+			    ar->fw_api,
 			    ar->htt.target_version_major,
 			    ar->htt.target_version_minor);
 
@@ -845,12 +816,14 @@ int ath10k_core_start(struct ath10k *ar)
 
 	return 0;
 
-err_disconnect_htc:
+err_htc_stop:
 	ath10k_htc_stop(&ar->htc);
-err_htt_detach:
-	ath10k_htt_detach(&ar->htt);
 err_hif_stop:
 	ath10k_hif_stop(ar);
+err_htt_rx_detach:
+	ath10k_htt_rx_free(&ar->htt);
+err_htt_tx_detach:
+	ath10k_htt_tx_free(&ar->htt);
 err_wmi_detach:
 	ath10k_wmi_detach(ar);
 err:
@@ -885,10 +858,14 @@ void ath10k_core_stop(struct ath10k *ar)
 	lockdep_assert_held(&ar->conf_mutex);
 
 	/* try to suspend target */
-	ath10k_wait_for_suspend(ar, WMI_PDEV_SUSPEND_AND_DISABLE_INTR);
+	if (ar->state != ATH10K_STATE_RESTARTING)
+		ath10k_wait_for_suspend(ar, WMI_PDEV_SUSPEND_AND_DISABLE_INTR);
+
 	ath10k_debug_stop(ar);
 	ath10k_htc_stop(&ar->htc);
-	ath10k_htt_detach(&ar->htt);
+	ath10k_hif_stop(ar);
+	ath10k_htt_tx_free(&ar->htt);
+	ath10k_htt_rx_free(&ar->htt);
 	ath10k_wmi_detach(ar);
 }
 EXPORT_SYMBOL(ath10k_core_stop);
@@ -980,22 +957,15 @@ static int ath10k_core_check_chip_id(struct ath10k *ar)
 	return 0;
 }
 
-int ath10k_core_register(struct ath10k *ar, u32 chip_id)
+static void ath10k_core_register_work(struct work_struct *work)
 {
+	struct ath10k *ar = container_of(work, struct ath10k, register_work);
 	int status;
 
-	ar->chip_id = chip_id;
-
-	status = ath10k_core_check_chip_id(ar);
-	if (status) {
-		ath10k_err("Unsupported chip id 0x%08x\n", ar->chip_id);
-		return status;
-	}
-
 	status = ath10k_core_probe_fw(ar);
 	if (status) {
 		ath10k_err("could not probe fw (%d)\n", status);
-		return status;
+		goto err;
 	}
 
 	status = ath10k_mac_register(ar);
@@ -1010,18 +980,43 @@ int ath10k_core_register(struct ath10k *ar, u32 chip_id)
 		goto err_unregister_mac;
 	}
 
-	return 0;
+	set_bit(ATH10K_FLAG_CORE_REGISTERED, &ar->dev_flags);
+	return;
 
 err_unregister_mac:
 	ath10k_mac_unregister(ar);
 err_release_fw:
 	ath10k_core_free_firmware_files(ar);
-	return status;
+err:
+	device_release_driver(ar->dev);
+	return;
+}
+
+int ath10k_core_register(struct ath10k *ar, u32 chip_id)
+{
+	int status;
+
+	ar->chip_id = chip_id;
+
+	status = ath10k_core_check_chip_id(ar);
+	if (status) {
+		ath10k_err("Unsupported chip id 0x%08x\n", ar->chip_id);
+		return status;
+	}
+
+	queue_work(ar->workqueue, &ar->register_work);
+
+	return 0;
 }
 EXPORT_SYMBOL(ath10k_core_register);
 
 void ath10k_core_unregister(struct ath10k *ar)
 {
+	cancel_work_sync(&ar->register_work);
+
+	if (!test_bit(ATH10K_FLAG_CORE_REGISTERED, &ar->dev_flags))
+		return;
+
 	/* We must unregister from mac80211 before we stop HTC and HIF.
 	 * Otherwise we will fail to submit commands to FW and mac80211 will be
 	 * unhappy about callback failures. */
@@ -1033,6 +1028,71 @@ void ath10k_core_unregister(struct ath10k *ar)
 }
 EXPORT_SYMBOL(ath10k_core_unregister);
 
+struct ath10k *ath10k_core_create(void *hif_priv, struct device *dev,
+				  const struct ath10k_hif_ops *hif_ops)
+{
+	struct ath10k *ar;
+
+	ar = ath10k_mac_create();
+	if (!ar)
+		return NULL;
+
+	ar->ath_common.priv = ar;
+	ar->ath_common.hw = ar->hw;
+
+	ar->p2p = !!ath10k_p2p;
+	ar->dev = dev;
+
+	ar->hif.priv = hif_priv;
+	ar->hif.ops = hif_ops;
+
+	init_completion(&ar->scan.started);
+	init_completion(&ar->scan.completed);
+	init_completion(&ar->scan.on_channel);
+	init_completion(&ar->target_suspend);
+
+	init_completion(&ar->install_key_done);
+	init_completion(&ar->vdev_setup_done);
+
+	setup_timer(&ar->scan.timeout, ath10k_reset_scan, (unsigned long)ar);
+
+	ar->workqueue = create_singlethread_workqueue("ath10k_wq");
+	if (!ar->workqueue)
+		goto err_wq;
+
+	mutex_init(&ar->conf_mutex);
+	spin_lock_init(&ar->data_lock);
+
+	INIT_LIST_HEAD(&ar->peers);
+	init_waitqueue_head(&ar->peer_mapping_wq);
+
+	init_completion(&ar->offchan_tx_completed);
+	INIT_WORK(&ar->offchan_tx_work, ath10k_offchan_tx_work);
+	skb_queue_head_init(&ar->offchan_tx_queue);
+
+	INIT_WORK(&ar->wmi_mgmt_tx_work, ath10k_mgmt_over_wmi_tx_work);
+	skb_queue_head_init(&ar->wmi_mgmt_tx_queue);
+
+	INIT_WORK(&ar->register_work, ath10k_core_register_work);
+	INIT_WORK(&ar->restart_work, ath10k_core_restart);
+
+	return ar;
+
+err_wq:
+	ath10k_mac_destroy(ar);
+	return NULL;
+}
+EXPORT_SYMBOL(ath10k_core_create);
+
+void ath10k_core_destroy(struct ath10k *ar)
+{
+	flush_workqueue(ar->workqueue);
+	destroy_workqueue(ar->workqueue);
+
+	ath10k_mac_destroy(ar);
+}
+EXPORT_SYMBOL(ath10k_core_destroy);
+
 MODULE_AUTHOR("Qualcomm Atheros");
 MODULE_DESCRIPTION("Core module for QCA988X PCIe devices.");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 0e71979d837..68ceef61933 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -119,6 +119,7 @@ struct ath10k_peer_stat {
 	u8 peer_macaddr[ETH_ALEN];
 	u32 peer_rssi;
 	u32 peer_tx_rate;
+	u32 peer_rx_rate; /* 10x only */
 };
 
 struct ath10k_target_stats {
@@ -130,6 +131,12 @@ struct ath10k_target_stats {
 	u32 cycle_count;
 	u32 phy_err_count;
 	u32 chan_tx_power;
+	u32 ack_rx_bad;
+	u32 rts_bad;
+	u32 rts_good;
+	u32 fcs_bad;
+	u32 no_beacons;
+	u32 mib_int_count;
 
 	/* PDEV TX stats */
 	s32 comp_queued;
@@ -260,6 +267,8 @@ struct ath10k_vif {
 	u8 fixed_rate;
 	u8 fixed_nss;
 	u8 force_sgi;
+	bool use_cts_prot;
+	int num_legacy_stations;
 };
 
 struct ath10k_vif_iter {
@@ -326,6 +335,7 @@ enum ath10k_dev_flags {
 	/* Indicates that ath10k device is during CAC phase of DFS */
 	ATH10K_CAC_RUNNING,
 	ATH10K_FLAG_FIRST_BOOT_DONE,
+	ATH10K_FLAG_CORE_REGISTERED,
 };
 
 struct ath10k {
@@ -419,13 +429,24 @@ struct ath10k {
 	struct cfg80211_chan_def chandef;
 
 	int free_vdev_map;
+	bool promisc;
+	bool monitor;
 	int monitor_vdev_id;
-	bool monitor_enabled;
-	bool monitor_present;
+	bool monitor_started;
 	unsigned int filter_flags;
 	unsigned long dev_flags;
 	u32 dfs_block_radar_events;
 
+	/* protected by conf_mutex */
+	bool radar_enabled;
+	int num_started_vdevs;
+
+	/* Protected by conf-mutex */
+	u8 supp_tx_chainmask;
+	u8 supp_rx_chainmask;
+	u8 cfg_tx_chainmask;
+	u8 cfg_rx_chainmask;
+
 	struct wmi_pdev_set_wmm_params_arg wmm_params;
 	struct completion install_key_done;
 
@@ -456,6 +477,7 @@ struct ath10k {
 
 	enum ath10k_state state;
 
+	struct work_struct register_work;
 	struct work_struct restart_work;
 
 	/* cycle count is reported twice for each visited channel during scan.
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index 6debd281350..1b7ff4ba122 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -161,7 +161,7 @@ void ath10k_debug_read_target_stats(struct ath10k *ar,
 	u8 *tmp = ev->data;
 	struct ath10k_target_stats *stats;
 	int num_pdev_stats, num_vdev_stats, num_peer_stats;
-	struct wmi_pdev_stats *ps;
+	struct wmi_pdev_stats_10x *ps;
 	int i;
 
 	spin_lock_bh(&ar->data_lock);
@@ -173,7 +173,7 @@ void ath10k_debug_read_target_stats(struct ath10k *ar,
 	num_peer_stats = __le32_to_cpu(ev->num_peer_stats); /* 0 or max peers */
 
 	if (num_pdev_stats) {
-		ps = (struct wmi_pdev_stats *)tmp;
+		ps = (struct wmi_pdev_stats_10x *)tmp;
 
 		stats->ch_noise_floor = __le32_to_cpu(ps->chan_nf);
 		stats->tx_frame_count = __le32_to_cpu(ps->tx_frame_count);
@@ -228,7 +228,18 @@ void ath10k_debug_read_target_stats(struct ath10k *ar,
 		stats->phy_err_drop = __le32_to_cpu(ps->wal.rx.phy_err_drop);
 		stats->mpdu_errs = __le32_to_cpu(ps->wal.rx.mpdu_errs);
 
-		tmp += sizeof(struct wmi_pdev_stats);
+		if (test_bit(ATH10K_FW_FEATURE_WMI_10X,
+			     ar->fw_features)) {
+			stats->ack_rx_bad = __le32_to_cpu(ps->ack_rx_bad);
+			stats->rts_bad = __le32_to_cpu(ps->rts_bad);
+			stats->rts_good = __le32_to_cpu(ps->rts_good);
+			stats->fcs_bad = __le32_to_cpu(ps->fcs_bad);
+			stats->no_beacons = __le32_to_cpu(ps->no_beacons);
+			stats->mib_int_count = __le32_to_cpu(ps->mib_int_count);
+			tmp += sizeof(struct wmi_pdev_stats_10x);
+		} else {
+			tmp += sizeof(struct wmi_pdev_stats_old);
+		}
 	}
 
 	/* 0 or max vdevs */
@@ -243,22 +254,29 @@ void ath10k_debug_read_target_stats(struct ath10k *ar,
 	}
 
 	if (num_peer_stats) {
-		struct wmi_peer_stats *peer_stats;
+		struct wmi_peer_stats_10x *peer_stats;
 		struct ath10k_peer_stat *s;
 
 		stats->peers = num_peer_stats;
 
 		for (i = 0; i < num_peer_stats; i++) {
-			peer_stats = (struct wmi_peer_stats *)tmp;
+			peer_stats = (struct wmi_peer_stats_10x *)tmp;
 			s = &stats->peer_stat[i];
 
-			WMI_MAC_ADDR_TO_CHAR_ARRAY(&peer_stats->peer_macaddr,
-						   s->peer_macaddr);
+			memcpy(s->peer_macaddr, &peer_stats->peer_macaddr.addr,
+			       ETH_ALEN);
 			s->peer_rssi = __le32_to_cpu(peer_stats->peer_rssi);
 			s->peer_tx_rate =
 				__le32_to_cpu(peer_stats->peer_tx_rate);
-
-			tmp += sizeof(struct wmi_peer_stats);
+			if (test_bit(ATH10K_FW_FEATURE_WMI_10X,
+				     ar->fw_features)) {
+				s->peer_rx_rate =
+					__le32_to_cpu(peer_stats->peer_rx_rate);
+				tmp += sizeof(struct wmi_peer_stats_10x);
+
+			} else {
+				tmp += sizeof(struct wmi_peer_stats_old);
+			}
 		}
 	}
 
@@ -272,7 +290,7 @@ static ssize_t ath10k_read_fw_stats(struct file *file, char __user *user_buf,
 	struct ath10k *ar = file->private_data;
 	struct ath10k_target_stats *fw_stats;
 	char *buf = NULL;
-	unsigned int len = 0, buf_len = 2500;
+	unsigned int len = 0, buf_len = 8000;
 	ssize_t ret_cnt = 0;
 	long left;
 	int i;
@@ -320,6 +338,16 @@ static ssize_t ath10k_read_fw_stats(struct file *file, char __user *user_buf,
 			 "Cycle count", fw_stats->cycle_count);
 	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
 			 "PHY error count", fw_stats->phy_err_count);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "RTS bad count", fw_stats->rts_bad);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "RTS good count", fw_stats->rts_good);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "FCS bad count", fw_stats->fcs_bad);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "No beacon count", fw_stats->no_beacons);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "MIB int count", fw_stats->mib_int_count);
 
 	len += scnprintf(buf + len, buf_len - len, "\n");
 	len += scnprintf(buf + len, buf_len - len, "%30s\n",
@@ -411,8 +439,8 @@ static ssize_t ath10k_read_fw_stats(struct file *file, char __user *user_buf,
 			 "MPDU errors (FCS, MIC, ENC)", fw_stats->mpdu_errs);
 
 	len += scnprintf(buf + len, buf_len - len, "\n");
-	len += scnprintf(buf + len, buf_len - len, "%30s\n",
-			 "ath10k PEER stats");
+	len += scnprintf(buf + len, buf_len - len, "%30s (%d)\n",
+			 "ath10k PEER stats", fw_stats->peers);
 	len += scnprintf(buf + len, buf_len - len, "%30s\n\n",
 				 "=================");
 
@@ -425,6 +453,9 @@ static ssize_t ath10k_read_fw_stats(struct file *file, char __user *user_buf,
 		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
 				 "Peer TX rate",
 				 fw_stats->peer_stat[i].peer_tx_rate);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "Peer RX rate",
+				 fw_stats->peer_stat[i].peer_rx_rate);
 		len += scnprintf(buf + len, buf_len - len, "\n");
 	}
 	spin_unlock_bh(&ar->data_lock);
@@ -451,27 +482,37 @@ static ssize_t ath10k_read_simulate_fw_crash(struct file *file,
 					     char __user *user_buf,
 					     size_t count, loff_t *ppos)
 {
-	const char buf[] = "To simulate firmware crash write the keyword"
-			   " `crash` to this file.\nThis will force firmware"
-			   " to report a crash to the host system.\n";
+	const char buf[] = "To simulate firmware crash write one of the"
+			   " keywords to this file:\n `soft` - this will send"
+			   " WMI_FORCE_FW_HANG_ASSERT to firmware if FW"
+			   " supports that command.\n `hard` - this will send"
+			   " to firmware command with illegal parameters"
+			   " causing firmware crash.\n";
+
 	return simple_read_from_buffer(user_buf, count, ppos, buf, strlen(buf));
 }
 
+/* Simulate firmware crash:
+ * 'soft': Call wmi command causing firmware hang. This firmware hang is
+ * recoverable by warm firmware reset.
+ * 'hard': Force firmware crash by setting any vdev parameter for not allowed
+ * vdev id. This is hard firmware crash because it is recoverable only by cold
+ * firmware reset.
+ */
 static ssize_t ath10k_write_simulate_fw_crash(struct file *file,
 					      const char __user *user_buf,
 					      size_t count, loff_t *ppos)
 {
 	struct ath10k *ar = file->private_data;
-	char buf[32] = {};
+	char buf[32];
 	int ret;
 
 	mutex_lock(&ar->conf_mutex);
 
 	simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, user_buf, count);
-	if (strcmp(buf, "crash") && strcmp(buf, "crash\n")) {
-		ret = -EINVAL;
-		goto exit;
-	}
+
+	/* make sure that buf is null terminated */
+	buf[sizeof(buf) - 1] = 0;
 
 	if (ar->state != ATH10K_STATE_ON &&
 	    ar->state != ATH10K_STATE_RESTARTED) {
@@ -479,14 +520,30 @@ static ssize_t ath10k_write_simulate_fw_crash(struct file *file,
 		goto exit;
 	}
 
-	ath10k_info("simulating firmware crash\n");
+	/* drop the possible '\n' from the end */
+	if (buf[count - 1] == '\n') {
+		buf[count - 1] = 0;
+		count--;
+	}
 
-	ret = ath10k_wmi_force_fw_hang(ar, WMI_FORCE_FW_HANG_ASSERT, 0);
-	if (ret)
-		ath10k_warn("failed to force fw hang (%d)\n", ret);
+	if (!strcmp(buf, "soft")) {
+		ath10k_info("simulating soft firmware crash\n");
+		ret = ath10k_wmi_force_fw_hang(ar, WMI_FORCE_FW_HANG_ASSERT, 0);
+	} else if (!strcmp(buf, "hard")) {
+		ath10k_info("simulating hard firmware crash\n");
+		ret = ath10k_wmi_vdev_set_param(ar, TARGET_NUM_VDEVS + 1,
+					ar->wmi.vdev_param->rts_threshold, 0);
+	} else {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	if (ret) {
+		ath10k_warn("failed to simulate firmware crash: %d\n", ret);
+		goto exit;
+	}
 
-	if (ret == 0)
-		ret = count;
+	ret = count;
 
 exit:
 	mutex_unlock(&ar->conf_mutex);
diff --git a/drivers/net/wireless/ath/ath10k/htc.c b/drivers/net/wireless/ath/ath10k/htc.c
index 7f1bccd3597..e493db4b4a4 100644
--- a/drivers/net/wireless/ath/ath10k/htc.c
+++ b/drivers/net/wireless/ath/ath10k/htc.c
@@ -157,6 +157,9 @@ int ath10k_htc_send(struct ath10k_htc *htc,
 			goto err_pull;
 		}
 		ep->tx_credits -= credits;
+		ath10k_dbg(ATH10K_DBG_HTC,
+			   "htc ep %d consumed %d credits (total %d)\n",
+			   eid, credits, ep->tx_credits);
 		spin_unlock_bh(&htc->tx_lock);
 	}
 
@@ -185,6 +188,9 @@ err_credits:
 	if (ep->tx_credit_flow_enabled) {
 		spin_lock_bh(&htc->tx_lock);
 		ep->tx_credits += credits;
+		ath10k_dbg(ATH10K_DBG_HTC,
+			   "htc ep %d reverted %d credits back (total %d)\n",
+			   eid, credits, ep->tx_credits);
 		spin_unlock_bh(&htc->tx_lock);
 
 		if (ep->ep_ops.ep_tx_credits)
@@ -234,12 +240,12 @@ ath10k_htc_process_credit_report(struct ath10k_htc *htc,
 		if (report->eid >= ATH10K_HTC_EP_COUNT)
 			break;
 
-		ath10k_dbg(ATH10K_DBG_HTC, "ep %d got %d credits\n",
-			   report->eid, report->credits);
-
 		ep = &htc->endpoint[report->eid];
 		ep->tx_credits += report->credits;
 
+		ath10k_dbg(ATH10K_DBG_HTC, "htc ep %d got %d credits (total %d)\n",
+			   report->eid, report->credits, ep->tx_credits);
+
 		if (ep->ep_ops.ep_tx_credits) {
 			spin_unlock_bh(&htc->tx_lock);
 			ep->ep_ops.ep_tx_credits(htc->ar);
@@ -824,17 +830,11 @@ int ath10k_htc_start(struct ath10k_htc *htc)
 	return 0;
 }
 
-/*
- * stop HTC communications, i.e. stop interrupt reception, and flush all
- * queued buffers
- */
 void ath10k_htc_stop(struct ath10k_htc *htc)
 {
 	spin_lock_bh(&htc->tx_lock);
 	htc->stopped = true;
 	spin_unlock_bh(&htc->tx_lock);
-
-	ath10k_hif_stop(htc->ar);
 }
 
 /* registered target arrival callback from the HIF layer */
diff --git a/drivers/net/wireless/ath/ath10k/htt.c b/drivers/net/wireless/ath/ath10k/htt.c
index 69697af59ce..19c12cc8d66 100644
--- a/drivers/net/wireless/ath/ath10k/htt.c
+++ b/drivers/net/wireless/ath/ath10k/htt.c
@@ -22,7 +22,7 @@
 #include "core.h"
 #include "debug.h"
 
-static int ath10k_htt_htc_attach(struct ath10k_htt *htt)
+int ath10k_htt_connect(struct ath10k_htt *htt)
 {
 	struct ath10k_htc_svc_conn_req conn_req;
 	struct ath10k_htc_svc_conn_resp conn_resp;
@@ -48,39 +48,14 @@ static int ath10k_htt_htc_attach(struct ath10k_htt *htt)
 	return 0;
 }
 
-int ath10k_htt_attach(struct ath10k *ar)
+int ath10k_htt_init(struct ath10k *ar)
 {
 	struct ath10k_htt *htt = &ar->htt;
-	int ret;
 
 	htt->ar = ar;
 	htt->max_throughput_mbps = 800;
 
 	/*
-	 * Connect to HTC service.
-	 * This has to be done before calling ath10k_htt_rx_attach,
-	 * since ath10k_htt_rx_attach involves sending a rx ring configure
-	 * message to the target.
-	 */
-	ret = ath10k_htt_htc_attach(htt);
-	if (ret) {
-		ath10k_err("could not attach htt htc (%d)\n", ret);
-		goto err_htc_attach;
-	}
-
-	ret = ath10k_htt_tx_attach(htt);
-	if (ret) {
-		ath10k_err("could not attach htt tx (%d)\n", ret);
-		goto err_htc_attach;
-	}
-
-	ret = ath10k_htt_rx_attach(htt);
-	if (ret) {
-		ath10k_err("could not attach htt rx (%d)\n", ret);
-		goto err_rx_attach;
-	}
-
-	/*
 	 * Prefetch enough data to satisfy target
 	 * classification engine.
 	 * This is for LL chips. HL chips will probably
@@ -93,11 +68,6 @@ int ath10k_htt_attach(struct ath10k *ar)
 		2; /* ip4 dscp or ip6 priority */
 
 	return 0;
-
-err_rx_attach:
-	ath10k_htt_tx_detach(htt);
-err_htc_attach:
-	return ret;
 }
 
 #define HTT_TARGET_VERSION_TIMEOUT_HZ (3*HZ)
@@ -117,7 +87,7 @@ static int ath10k_htt_verify_version(struct ath10k_htt *htt)
 	return 0;
 }
 
-int ath10k_htt_attach_target(struct ath10k_htt *htt)
+int ath10k_htt_setup(struct ath10k_htt *htt)
 {
 	int status;
 
@@ -140,9 +110,3 @@ int ath10k_htt_attach_target(struct ath10k_htt *htt)
 
 	return ath10k_htt_send_rx_ring_cfg_ll(htt);
 }
-
-void ath10k_htt_detach(struct ath10k_htt *htt)
-{
-	ath10k_htt_rx_detach(htt);
-	ath10k_htt_tx_detach(htt);
-}
diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h
index 654867fc1ae..9a263462c79 100644
--- a/drivers/net/wireless/ath/ath10k/htt.h
+++ b/drivers/net/wireless/ath/ath10k/htt.h
@@ -21,6 +21,7 @@
 #include <linux/bug.h>
 #include <linux/interrupt.h>
 #include <linux/dmapool.h>
+#include <net/mac80211.h>
 
 #include "htc.h"
 #include "rx_desc.h"
@@ -1172,23 +1173,6 @@ struct htt_peer_unmap_event {
 	u16 peer_id;
 };
 
-struct htt_rx_info {
-	struct sk_buff *skb;
-	enum htt_rx_mpdu_status status;
-	enum htt_rx_mpdu_encrypt_type encrypt_type;
-	s8 signal;
-	struct {
-		u8 info0;
-		u32 info1;
-		u32 info2;
-	} rate;
-
-	u32 tsf;
-	bool fcs_err;
-	bool amsdu_more;
-	bool mic_err;
-};
-
 struct ath10k_htt_txbuf {
 	struct htt_data_tx_desc_frag frags[2];
 	struct ath10k_htc_hdr htc_hdr;
@@ -1289,6 +1273,9 @@ struct ath10k_htt {
 	struct tasklet_struct txrx_compl_task;
 	struct sk_buff_head tx_compl_q;
 	struct sk_buff_head rx_compl_q;
+
+	/* rx_status template */
+	struct ieee80211_rx_status rx_status;
 };
 
 #define RX_HTT_HDR_STATUS_LEN 64
@@ -1341,14 +1328,16 @@ struct htt_rx_desc {
 #define HTT_LOG2_MAX_CACHE_LINE_SIZE 7	/* 2^7 = 128 */
 #define HTT_MAX_CACHE_LINE_SIZE_MASK ((1 << HTT_LOG2_MAX_CACHE_LINE_SIZE) - 1)
 
-int ath10k_htt_attach(struct ath10k *ar);
-int ath10k_htt_attach_target(struct ath10k_htt *htt);
-void ath10k_htt_detach(struct ath10k_htt *htt);
+int ath10k_htt_connect(struct ath10k_htt *htt);
+int ath10k_htt_init(struct ath10k *ar);
+int ath10k_htt_setup(struct ath10k_htt *htt);
+
+int ath10k_htt_tx_alloc(struct ath10k_htt *htt);
+void ath10k_htt_tx_free(struct ath10k_htt *htt);
+
+int ath10k_htt_rx_alloc(struct ath10k_htt *htt);
+void ath10k_htt_rx_free(struct ath10k_htt *htt);
 
-int ath10k_htt_tx_attach(struct ath10k_htt *htt);
-void ath10k_htt_tx_detach(struct ath10k_htt *htt);
-int ath10k_htt_rx_attach(struct ath10k_htt *htt);
-void ath10k_htt_rx_detach(struct ath10k_htt *htt);
 void ath10k_htt_htc_tx_complete(struct ath10k *ar, struct sk_buff *skb);
 void ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb);
 int ath10k_htt_h2t_ver_req_msg(struct ath10k_htt *htt);
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index cdcbe2de95f..eebc860c365 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -225,10 +225,26 @@ static void ath10k_htt_rx_ring_refill_retry(unsigned long arg)
 	ath10k_htt_rx_msdu_buff_replenish(htt);
 }
 
-void ath10k_htt_rx_detach(struct ath10k_htt *htt)
+static void ath10k_htt_rx_ring_clean_up(struct ath10k_htt *htt)
 {
-	int sw_rd_idx = htt->rx_ring.sw_rd_idx.msdu_payld;
+	struct sk_buff *skb;
+	int i;
+
+	for (i = 0; i < htt->rx_ring.size; i++) {
+		skb = htt->rx_ring.netbufs_ring[i];
+		if (!skb)
+			continue;
 
+		dma_unmap_single(htt->ar->dev, ATH10K_SKB_CB(skb)->paddr,
+				 skb->len + skb_tailroom(skb),
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb_any(skb);
+		htt->rx_ring.netbufs_ring[i] = NULL;
+	}
+}
+
+void ath10k_htt_rx_free(struct ath10k_htt *htt)
+{
 	del_timer_sync(&htt->rx_ring.refill_retry_timer);
 	tasklet_kill(&htt->rx_replenish_task);
 	tasklet_kill(&htt->txrx_compl_task);
@@ -236,18 +252,7 @@ void ath10k_htt_rx_detach(struct ath10k_htt *htt)
 	skb_queue_purge(&htt->tx_compl_q);
 	skb_queue_purge(&htt->rx_compl_q);
 
-	while (sw_rd_idx != __le32_to_cpu(*(htt->rx_ring.alloc_idx.vaddr))) {
-		struct sk_buff *skb =
-				htt->rx_ring.netbufs_ring[sw_rd_idx];
-		struct ath10k_skb_cb *cb = ATH10K_SKB_CB(skb);
-
-		dma_unmap_single(htt->ar->dev, cb->paddr,
-				 skb->len + skb_tailroom(skb),
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb_any(htt->rx_ring.netbufs_ring[sw_rd_idx]);
-		sw_rd_idx++;
-		sw_rd_idx &= htt->rx_ring.size_mask;
-	}
+	ath10k_htt_rx_ring_clean_up(htt);
 
 	dma_free_coherent(htt->ar->dev,
 			  (htt->rx_ring.size *
@@ -277,6 +282,7 @@ static inline struct sk_buff *ath10k_htt_rx_netbuf_pop(struct ath10k_htt *htt)
 
 	idx = htt->rx_ring.sw_rd_idx.msdu_payld;
 	msdu = htt->rx_ring.netbufs_ring[idx];
+	htt->rx_ring.netbufs_ring[idx] = NULL;
 
 	idx++;
 	idx &= htt->rx_ring.size_mask;
@@ -297,6 +303,7 @@ static void ath10k_htt_rx_free_msdu_chain(struct sk_buff *skb)
 	}
 }
 
+/* return: < 0 fatal error, 0 - non chained msdu, 1 chained msdu */
 static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt,
 				   u8 **fw_desc, int *fw_desc_len,
 				   struct sk_buff **head_msdu,
@@ -310,7 +317,7 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt,
 
 	if (htt->rx_confused) {
 		ath10k_warn("htt is confused. refusing rx\n");
-		return 0;
+		return -1;
 	}
 
 	msdu = *head_msdu = ath10k_htt_rx_netbuf_pop(htt);
@@ -398,7 +405,6 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt,
 		msdu_len = MS(__le32_to_cpu(rx_desc->msdu_start.info0),
 			      RX_MSDU_START_INFO0_MSDU_LENGTH);
 		msdu_chained = rx_desc->frag_info.ring2_more_count;
-		msdu_chaining = msdu_chained;
 
 		if (msdu_len_invalid)
 			msdu_len = 0;
@@ -426,6 +432,7 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt,
 
 			msdu->next = next;
 			msdu = next;
+			msdu_chaining = 1;
 		}
 
 		last_msdu = __le32_to_cpu(rx_desc->msdu_end.info0) &
@@ -442,6 +449,9 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt,
 	}
 	*tail_msdu = msdu;
 
+	if (*head_msdu == NULL)
+		msdu_chaining = -1;
+
 	/*
 	 * Don't refill the ring yet.
 	 *
@@ -464,7 +474,7 @@ static void ath10k_htt_rx_replenish_task(unsigned long ptr)
 	ath10k_htt_rx_msdu_buff_replenish(htt);
 }
 
-int ath10k_htt_rx_attach(struct ath10k_htt *htt)
+int ath10k_htt_rx_alloc(struct ath10k_htt *htt)
 {
 	dma_addr_t paddr;
 	void *vaddr;
@@ -490,7 +500,7 @@ int ath10k_htt_rx_attach(struct ath10k_htt *htt)
 	htt->rx_ring.fill_level = ath10k_htt_rx_ring_fill_level(htt);
 
 	htt->rx_ring.netbufs_ring =
-		kmalloc(htt->rx_ring.size * sizeof(struct sk_buff *),
+		kzalloc(htt->rx_ring.size * sizeof(struct sk_buff *),
 			GFP_KERNEL);
 	if (!htt->rx_ring.netbufs_ring)
 		goto err_netbuf;
@@ -636,6 +646,203 @@ struct amsdu_subframe_hdr {
 	__be16 len;
 } __packed;
 
+static const u8 rx_legacy_rate_idx[] = {
+	3,	/* 0x00  - 11Mbps  */
+	2,	/* 0x01  - 5.5Mbps */
+	1,	/* 0x02  - 2Mbps   */
+	0,	/* 0x03  - 1Mbps   */
+	3,	/* 0x04  - 11Mbps  */
+	2,	/* 0x05  - 5.5Mbps */
+	1,	/* 0x06  - 2Mbps   */
+	0,	/* 0x07  - 1Mbps   */
+	10,	/* 0x08  - 48Mbps  */
+	8,	/* 0x09  - 24Mbps  */
+	6,	/* 0x0A  - 12Mbps  */
+	4,	/* 0x0B  - 6Mbps   */
+	11,	/* 0x0C  - 54Mbps  */
+	9,	/* 0x0D  - 36Mbps  */
+	7,	/* 0x0E  - 18Mbps  */
+	5,	/* 0x0F  - 9Mbps   */
+};
+
+static void ath10k_htt_rx_h_rates(struct ath10k *ar,
+				  enum ieee80211_band band,
+				  u8 info0, u32 info1, u32 info2,
+				  struct ieee80211_rx_status *status)
+{
+	u8 cck, rate, rate_idx, bw, sgi, mcs, nss;
+	u8 preamble = 0;
+
+	/* Check if valid fields */
+	if (!(info0 & HTT_RX_INDICATION_INFO0_START_VALID))
+		return;
+
+	preamble = MS(info1, HTT_RX_INDICATION_INFO1_PREAMBLE_TYPE);
+
+	switch (preamble) {
+	case HTT_RX_LEGACY:
+		cck = info0 & HTT_RX_INDICATION_INFO0_LEGACY_RATE_CCK;
+		rate = MS(info0, HTT_RX_INDICATION_INFO0_LEGACY_RATE);
+		rate_idx = 0;
+
+		if (rate < 0x08 || rate > 0x0F)
+			break;
+
+		switch (band) {
+		case IEEE80211_BAND_2GHZ:
+			if (cck)
+				rate &= ~BIT(3);
+			rate_idx = rx_legacy_rate_idx[rate];
+			break;
+		case IEEE80211_BAND_5GHZ:
+			rate_idx = rx_legacy_rate_idx[rate];
+			/* We are using same rate table registering
+			   HW - ath10k_rates[]. In case of 5GHz skip
+			   CCK rates, so -4 here */
+			rate_idx -= 4;
+			break;
+		default:
+			break;
+		}
+
+		status->rate_idx = rate_idx;
+		break;
+	case HTT_RX_HT:
+	case HTT_RX_HT_WITH_TXBF:
+		/* HT-SIG - Table 20-11 in info1 and info2 */
+		mcs = info1 & 0x1F;
+		nss = mcs >> 3;
+		bw = (info1 >> 7) & 1;
+		sgi = (info2 >> 7) & 1;
+
+		status->rate_idx = mcs;
+		status->flag |= RX_FLAG_HT;
+		if (sgi)
+			status->flag |= RX_FLAG_SHORT_GI;
+		if (bw)
+			status->flag |= RX_FLAG_40MHZ;
+		break;
+	case HTT_RX_VHT:
+	case HTT_RX_VHT_WITH_TXBF:
+		/* VHT-SIG-A1 in info 1, VHT-SIG-A2 in info2
+		   TODO check this */
+		mcs = (info2 >> 4) & 0x0F;
+		nss = ((info1 >> 10) & 0x07) + 1;
+		bw = info1 & 3;
+		sgi = info2 & 1;
+
+		status->rate_idx = mcs;
+		status->vht_nss = nss;
+
+		if (sgi)
+			status->flag |= RX_FLAG_SHORT_GI;
+
+		switch (bw) {
+		/* 20MHZ */
+		case 0:
+			break;
+		/* 40MHZ */
+		case 1:
+			status->flag |= RX_FLAG_40MHZ;
+			break;
+		/* 80MHZ */
+		case 2:
+			status->vht_flag |= RX_VHT_FLAG_80MHZ;
+		}
+
+		status->flag |= RX_FLAG_VHT;
+		break;
+	default:
+		break;
+	}
+}
+
+static void ath10k_htt_rx_h_protected(struct ath10k_htt *htt,
+				      struct ieee80211_rx_status *rx_status,
+				      struct sk_buff *skb,
+				      enum htt_rx_mpdu_encrypt_type enctype,
+				      enum rx_msdu_decap_format fmt,
+				      bool dot11frag)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+
+	rx_status->flag &= ~(RX_FLAG_DECRYPTED |
+			     RX_FLAG_IV_STRIPPED |
+			     RX_FLAG_MMIC_STRIPPED);
+
+	if (enctype == HTT_RX_MPDU_ENCRYPT_NONE)
+		return;
+
+	/*
+	 * There's no explicit rx descriptor flag to indicate whether a given
+	 * frame has been decrypted or not. We're forced to use the decap
+	 * format as an implicit indication. However fragmentation rx is always
+	 * raw and it probably never reports undecrypted raws.
+	 *
+	 * This makes sure sniffed frames are reported as-is without stripping
+	 * the protected flag.
+	 */
+	if (fmt == RX_MSDU_DECAP_RAW && !dot11frag)
+		return;
+
+	rx_status->flag |= RX_FLAG_DECRYPTED |
+			   RX_FLAG_IV_STRIPPED |
+			   RX_FLAG_MMIC_STRIPPED;
+	hdr->frame_control = __cpu_to_le16(__le16_to_cpu(hdr->frame_control) &
+					   ~IEEE80211_FCTL_PROTECTED);
+}
+
+static bool ath10k_htt_rx_h_channel(struct ath10k *ar,
+				    struct ieee80211_rx_status *status)
+{
+	struct ieee80211_channel *ch;
+
+	spin_lock_bh(&ar->data_lock);
+	ch = ar->scan_channel;
+	if (!ch)
+		ch = ar->rx_channel;
+	spin_unlock_bh(&ar->data_lock);
+
+	if (!ch)
+		return false;
+
+	status->band = ch->band;
+	status->freq = ch->center_freq;
+
+	return true;
+}
+
+static void ath10k_process_rx(struct ath10k *ar,
+			      struct ieee80211_rx_status *rx_status,
+			      struct sk_buff *skb)
+{
+	struct ieee80211_rx_status *status;
+
+	status = IEEE80211_SKB_RXCB(skb);
+	*status = *rx_status;
+
+	ath10k_dbg(ATH10K_DBG_DATA,
+		   "rx skb %p len %u %s%s%s%s%s %srate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %imic-err %i\n",
+		   skb,
+		   skb->len,
+		   status->flag == 0 ? "legacy" : "",
+		   status->flag & RX_FLAG_HT ? "ht" : "",
+		   status->flag & RX_FLAG_VHT ? "vht" : "",
+		   status->flag & RX_FLAG_40MHZ ? "40" : "",
+		   status->vht_flag & RX_VHT_FLAG_80MHZ ? "80" : "",
+		   status->flag & RX_FLAG_SHORT_GI ? "sgi " : "",
+		   status->rate_idx,
+		   status->vht_nss,
+		   status->freq,
+		   status->band, status->flag,
+		   !!(status->flag & RX_FLAG_FAILED_FCS_CRC),
+		   !!(status->flag & RX_FLAG_MMIC_ERROR));
+	ath10k_dbg_dump(ATH10K_DBG_HTT_DUMP, NULL, "rx skb: ",
+			skb->data, skb->len);
+
+	ieee80211_rx(ar->hw, skb);
+}
+
 static int ath10k_htt_rx_nwifi_hdrlen(struct ieee80211_hdr *hdr)
 {
 	/* nwifi header is padded to 4 bytes. this fixes 4addr rx */
@@ -643,11 +850,12 @@ static int ath10k_htt_rx_nwifi_hdrlen(struct ieee80211_hdr *hdr)
 }
 
 static void ath10k_htt_rx_amsdu(struct ath10k_htt *htt,
-				struct htt_rx_info *info)
+				struct ieee80211_rx_status *rx_status,
+				struct sk_buff *skb_in)
 {
 	struct htt_rx_desc *rxd;
+	struct sk_buff *skb = skb_in;
 	struct sk_buff *first;
-	struct sk_buff *skb = info->skb;
 	enum rx_msdu_decap_format fmt;
 	enum htt_rx_mpdu_encrypt_type enctype;
 	struct ieee80211_hdr *hdr;
@@ -728,24 +936,28 @@ static void ath10k_htt_rx_amsdu(struct ath10k_htt *htt,
 			break;
 		}
 
-		info->skb = skb;
-		info->encrypt_type = enctype;
+		skb_in = skb;
+		ath10k_htt_rx_h_protected(htt, rx_status, skb_in, enctype, fmt,
+					  false);
 		skb = skb->next;
-		info->skb->next = NULL;
+		skb_in->next = NULL;
 
 		if (skb)
-			info->amsdu_more = true;
+			rx_status->flag |= RX_FLAG_AMSDU_MORE;
+		else
+			rx_status->flag &= ~RX_FLAG_AMSDU_MORE;
 
-		ath10k_process_rx(htt->ar, info);
+		ath10k_process_rx(htt->ar, rx_status, skb_in);
 	}
 
 	/* FIXME: It might be nice to re-assemble the A-MSDU when there's a
 	 * monitor interface active for sniffing purposes. */
 }
 
-static void ath10k_htt_rx_msdu(struct ath10k_htt *htt, struct htt_rx_info *info)
+static void ath10k_htt_rx_msdu(struct ath10k_htt *htt,
+			       struct ieee80211_rx_status *rx_status,
+			       struct sk_buff *skb)
 {
-	struct sk_buff *skb = info->skb;
 	struct htt_rx_desc *rxd;
 	struct ieee80211_hdr *hdr;
 	enum rx_msdu_decap_format fmt;
@@ -808,66 +1020,9 @@ static void ath10k_htt_rx_msdu(struct ath10k_htt *htt, struct htt_rx_info *info)
 		break;
 	}
 
-	info->skb = skb;
-	info->encrypt_type = enctype;
-
-	ath10k_process_rx(htt->ar, info);
-}
-
-static bool ath10k_htt_rx_has_decrypt_err(struct sk_buff *skb)
-{
-	struct htt_rx_desc *rxd;
-	u32 flags;
-
-	rxd = (void *)skb->data - sizeof(*rxd);
-	flags = __le32_to_cpu(rxd->attention.flags);
-
-	if (flags & RX_ATTENTION_FLAGS_DECRYPT_ERR)
-		return true;
-
-	return false;
-}
-
-static bool ath10k_htt_rx_has_fcs_err(struct sk_buff *skb)
-{
-	struct htt_rx_desc *rxd;
-	u32 flags;
-
-	rxd = (void *)skb->data - sizeof(*rxd);
-	flags = __le32_to_cpu(rxd->attention.flags);
-
-	if (flags & RX_ATTENTION_FLAGS_FCS_ERR)
-		return true;
+	ath10k_htt_rx_h_protected(htt, rx_status, skb, enctype, fmt, false);
 
-	return false;
-}
-
-static bool ath10k_htt_rx_has_mic_err(struct sk_buff *skb)
-{
-	struct htt_rx_desc *rxd;
-	u32 flags;
-
-	rxd = (void *)skb->data - sizeof(*rxd);
-	flags = __le32_to_cpu(rxd->attention.flags);
-
-	if (flags & RX_ATTENTION_FLAGS_TKIP_MIC_ERR)
-		return true;
-
-	return false;
-}
-
-static bool ath10k_htt_rx_is_mgmt(struct sk_buff *skb)
-{
-	struct htt_rx_desc *rxd;
-	u32 flags;
-
-	rxd = (void *)skb->data - sizeof(*rxd);
-	flags = __le32_to_cpu(rxd->attention.flags);
-
-	if (flags & RX_ATTENTION_FLAGS_MGMT_TYPE)
-		return true;
-
-	return false;
+	ath10k_process_rx(htt->ar, rx_status, skb);
 }
 
 static int ath10k_htt_rx_get_csum_state(struct sk_buff *skb)
@@ -952,21 +1107,73 @@ static int ath10k_unchain_msdu(struct sk_buff *msdu_head)
 	return 0;
 }
 
+static bool ath10k_htt_rx_amsdu_allowed(struct ath10k_htt *htt,
+					struct sk_buff *head,
+					enum htt_rx_mpdu_status status,
+					bool channel_set,
+					u32 attention)
+{
+	if (head->len == 0) {
+		ath10k_dbg(ATH10K_DBG_HTT,
+			   "htt rx dropping due to zero-len\n");
+		return false;
+	}
+
+	if (attention & RX_ATTENTION_FLAGS_DECRYPT_ERR) {
+		ath10k_dbg(ATH10K_DBG_HTT,
+			   "htt rx dropping due to decrypt-err\n");
+		return false;
+	}
+
+	if (!channel_set) {
+		ath10k_warn("no channel configured; ignoring frame!\n");
+		return false;
+	}
+
+	/* Skip mgmt frames while we handle this in WMI */
+	if (status == HTT_RX_IND_MPDU_STATUS_MGMT_CTRL ||
+	    attention & RX_ATTENTION_FLAGS_MGMT_TYPE) {
+		ath10k_dbg(ATH10K_DBG_HTT, "htt rx mgmt ctrl\n");
+		return false;
+	}
+
+	if (status != HTT_RX_IND_MPDU_STATUS_OK &&
+	    status != HTT_RX_IND_MPDU_STATUS_TKIP_MIC_ERR &&
+	    status != HTT_RX_IND_MPDU_STATUS_ERR_INV_PEER &&
+	    !htt->ar->monitor_started) {
+		ath10k_dbg(ATH10K_DBG_HTT,
+			   "htt rx ignoring frame w/ status %d\n",
+			   status);
+		return false;
+	}
+
+	if (test_bit(ATH10K_CAC_RUNNING, &htt->ar->dev_flags)) {
+		ath10k_dbg(ATH10K_DBG_HTT,
+			   "htt rx CAC running\n");
+		return false;
+	}
+
+	return true;
+}
+
 static void ath10k_htt_rx_handler(struct ath10k_htt *htt,
 				  struct htt_rx_indication *rx)
 {
-	struct htt_rx_info info;
+	struct ieee80211_rx_status *rx_status = &htt->rx_status;
 	struct htt_rx_indication_mpdu_range *mpdu_ranges;
+	struct htt_rx_desc *rxd;
+	enum htt_rx_mpdu_status status;
 	struct ieee80211_hdr *hdr;
 	int num_mpdu_ranges;
+	u32 attention;
 	int fw_desc_len;
 	u8 *fw_desc;
+	bool channel_set;
 	int i, j;
+	int ret;
 
 	lockdep_assert_held(&htt->rx_ring.lock);
 
-	memset(&info, 0, sizeof(info));
-
 	fw_desc_len = __le16_to_cpu(rx->prefix.fw_rx_desc_bytes);
 	fw_desc = (u8 *)&rx->fw_desc;
 
@@ -974,106 +1181,90 @@ static void ath10k_htt_rx_handler(struct ath10k_htt *htt,
 			     HTT_RX_INDICATION_INFO1_NUM_MPDU_RANGES);
 	mpdu_ranges = htt_rx_ind_get_mpdu_ranges(rx);
 
+	/* Fill this once, while this is per-ppdu */
+	if (rx->ppdu.info0 & HTT_RX_INDICATION_INFO0_START_VALID) {
+		memset(rx_status, 0, sizeof(*rx_status));
+		rx_status->signal  = ATH10K_DEFAULT_NOISE_FLOOR +
+				     rx->ppdu.combined_rssi;
+	}
+
+	if (rx->ppdu.info0 & HTT_RX_INDICATION_INFO0_END_VALID) {
+		/* TSF available only in 32-bit */
+		rx_status->mactime = __le32_to_cpu(rx->ppdu.tsf) & 0xffffffff;
+		rx_status->flag |= RX_FLAG_MACTIME_END;
+	}
+
+	channel_set = ath10k_htt_rx_h_channel(htt->ar, rx_status);
+
+	if (channel_set) {
+		ath10k_htt_rx_h_rates(htt->ar, rx_status->band,
+				      rx->ppdu.info0,
+				      __le32_to_cpu(rx->ppdu.info1),
+				      __le32_to_cpu(rx->ppdu.info2),
+				      rx_status);
+	}
+
 	ath10k_dbg_dump(ATH10K_DBG_HTT_DUMP, NULL, "htt rx ind: ",
 			rx, sizeof(*rx) +
 			(sizeof(struct htt_rx_indication_mpdu_range) *
 				num_mpdu_ranges));
 
 	for (i = 0; i < num_mpdu_ranges; i++) {
-		info.status = mpdu_ranges[i].mpdu_range_status;
+		status = mpdu_ranges[i].mpdu_range_status;
 
 		for (j = 0; j < mpdu_ranges[i].mpdu_count; j++) {
 			struct sk_buff *msdu_head, *msdu_tail;
-			enum htt_rx_mpdu_status status;
-			int msdu_chaining;
 
 			msdu_head = NULL;
 			msdu_tail = NULL;
-			msdu_chaining = ath10k_htt_rx_amsdu_pop(htt,
-							 &fw_desc,
-							 &fw_desc_len,
-							 &msdu_head,
-							 &msdu_tail);
-
-			if (!msdu_head) {
-				ath10k_warn("htt rx no data!\n");
-				continue;
-			}
-
-			if (msdu_head->len == 0) {
-				ath10k_dbg(ATH10K_DBG_HTT,
-					   "htt rx dropping due to zero-len\n");
-				ath10k_htt_rx_free_msdu_chain(msdu_head);
-				continue;
-			}
-
-			if (ath10k_htt_rx_has_decrypt_err(msdu_head)) {
-				ath10k_dbg(ATH10K_DBG_HTT,
-					   "htt rx dropping due to decrypt-err\n");
-				ath10k_htt_rx_free_msdu_chain(msdu_head);
-				continue;
-			}
-
-			status = info.status;
-
-			/* Skip mgmt frames while we handle this in WMI */
-			if (status == HTT_RX_IND_MPDU_STATUS_MGMT_CTRL ||
-			    ath10k_htt_rx_is_mgmt(msdu_head)) {
-				ath10k_dbg(ATH10K_DBG_HTT, "htt rx mgmt ctrl\n");
+			ret = ath10k_htt_rx_amsdu_pop(htt,
+						      &fw_desc,
+						      &fw_desc_len,
+						      &msdu_head,
+						      &msdu_tail);
+
+			if (ret < 0) {
+				ath10k_warn("failed to pop amsdu from htt rx ring %d\n",
+					    ret);
 				ath10k_htt_rx_free_msdu_chain(msdu_head);
 				continue;
 			}
 
-			if (status != HTT_RX_IND_MPDU_STATUS_OK &&
-			    status != HTT_RX_IND_MPDU_STATUS_TKIP_MIC_ERR &&
-			    status != HTT_RX_IND_MPDU_STATUS_ERR_INV_PEER &&
-			    !htt->ar->monitor_enabled) {
-				ath10k_dbg(ATH10K_DBG_HTT,
-					   "htt rx ignoring frame w/ status %d\n",
-					   status);
-				ath10k_htt_rx_free_msdu_chain(msdu_head);
-				continue;
-			}
+			rxd = container_of((void *)msdu_head->data,
+					   struct htt_rx_desc,
+					   msdu_payload);
+			attention = __le32_to_cpu(rxd->attention.flags);
 
-			if (test_bit(ATH10K_CAC_RUNNING, &htt->ar->dev_flags)) {
-				ath10k_dbg(ATH10K_DBG_HTT,
-					   "htt rx CAC running\n");
+			if (!ath10k_htt_rx_amsdu_allowed(htt, msdu_head,
+							 status,
+							 channel_set,
+							 attention)) {
 				ath10k_htt_rx_free_msdu_chain(msdu_head);
 				continue;
 			}
 
-			if (msdu_chaining &&
-			    (ath10k_unchain_msdu(msdu_head) < 0)) {
+			if (ret > 0 &&
+			    ath10k_unchain_msdu(msdu_head) < 0) {
 				ath10k_htt_rx_free_msdu_chain(msdu_head);
 				continue;
 			}
 
-			info.skb     = msdu_head;
-			info.fcs_err = ath10k_htt_rx_has_fcs_err(msdu_head);
-			info.mic_err = ath10k_htt_rx_has_mic_err(msdu_head);
-
-			if (info.fcs_err)
-				ath10k_dbg(ATH10K_DBG_HTT,
-					   "htt rx has FCS err\n");
-
-			if (info.mic_err)
-				ath10k_dbg(ATH10K_DBG_HTT,
-					   "htt rx has MIC err\n");
-
-			info.signal  = ATH10K_DEFAULT_NOISE_FLOOR;
-			info.signal += rx->ppdu.combined_rssi;
+			if (attention & RX_ATTENTION_FLAGS_FCS_ERR)
+				rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
+			else
+				rx_status->flag &= ~RX_FLAG_FAILED_FCS_CRC;
 
-			info.rate.info0 = rx->ppdu.info0;
-			info.rate.info1 = __le32_to_cpu(rx->ppdu.info1);
-			info.rate.info2 = __le32_to_cpu(rx->ppdu.info2);
-			info.tsf = __le32_to_cpu(rx->ppdu.tsf);
+			if (attention & RX_ATTENTION_FLAGS_TKIP_MIC_ERR)
+				rx_status->flag |= RX_FLAG_MMIC_ERROR;
+			else
+				rx_status->flag &= ~RX_FLAG_MMIC_ERROR;
 
 			hdr = ath10k_htt_rx_skb_get_hdr(msdu_head);
 
 			if (ath10k_htt_rx_hdr_is_amsdu(hdr))
-				ath10k_htt_rx_amsdu(htt, &info);
+				ath10k_htt_rx_amsdu(htt, rx_status, msdu_head);
 			else
-				ath10k_htt_rx_msdu(htt, &info);
+				ath10k_htt_rx_msdu(htt, rx_status, msdu_head);
 		}
 	}
 
@@ -1084,11 +1275,12 @@ static void ath10k_htt_rx_frag_handler(struct ath10k_htt *htt,
 				struct htt_rx_fragment_indication *frag)
 {
 	struct sk_buff *msdu_head, *msdu_tail;
+	enum htt_rx_mpdu_encrypt_type enctype;
 	struct htt_rx_desc *rxd;
 	enum rx_msdu_decap_format fmt;
-	struct htt_rx_info info = {};
+	struct ieee80211_rx_status *rx_status = &htt->rx_status;
 	struct ieee80211_hdr *hdr;
-	int msdu_chaining;
+	int ret;
 	bool tkip_mic_err;
 	bool decrypt_err;
 	u8 *fw_desc;
@@ -1102,24 +1294,21 @@ static void ath10k_htt_rx_frag_handler(struct ath10k_htt *htt,
 	msdu_tail = NULL;
 
 	spin_lock_bh(&htt->rx_ring.lock);
-	msdu_chaining = ath10k_htt_rx_amsdu_pop(htt, &fw_desc, &fw_desc_len,
-						&msdu_head, &msdu_tail);
+	ret = ath10k_htt_rx_amsdu_pop(htt, &fw_desc, &fw_desc_len,
+				      &msdu_head, &msdu_tail);
 	spin_unlock_bh(&htt->rx_ring.lock);
 
 	ath10k_dbg(ATH10K_DBG_HTT_DUMP, "htt rx frag ahead\n");
 
-	if (!msdu_head) {
-		ath10k_warn("htt rx frag no data\n");
-		return;
-	}
-
-	if (msdu_chaining || msdu_head != msdu_tail) {
-		ath10k_warn("aggregation with fragmentation?!\n");
+	if (ret) {
+		ath10k_warn("failed to pop amsdu from httr rx ring for fragmented rx %d\n",
+			    ret);
 		ath10k_htt_rx_free_msdu_chain(msdu_head);
 		return;
 	}
 
 	/* FIXME: implement signal strength */
+	rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL;
 
 	hdr = (struct ieee80211_hdr *)msdu_head->data;
 	rxd = (void *)msdu_head->data - sizeof(*rxd);
@@ -1136,57 +1325,55 @@ static void ath10k_htt_rx_frag_handler(struct ath10k_htt *htt,
 		goto end;
 	}
 
-	info.skb = msdu_head;
-	info.status = HTT_RX_IND_MPDU_STATUS_OK;
-	info.encrypt_type = MS(__le32_to_cpu(rxd->mpdu_start.info0),
-				RX_MPDU_START_INFO0_ENCRYPT_TYPE);
-	info.skb->ip_summed = ath10k_htt_rx_get_csum_state(info.skb);
+	enctype = MS(__le32_to_cpu(rxd->mpdu_start.info0),
+		     RX_MPDU_START_INFO0_ENCRYPT_TYPE);
+	ath10k_htt_rx_h_protected(htt, rx_status, msdu_head, enctype, fmt,
+				  true);
+	msdu_head->ip_summed = ath10k_htt_rx_get_csum_state(msdu_head);
 
-	if (tkip_mic_err) {
+	if (tkip_mic_err)
 		ath10k_warn("tkip mic error\n");
-		info.status = HTT_RX_IND_MPDU_STATUS_TKIP_MIC_ERR;
-	}
 
 	if (decrypt_err) {
 		ath10k_warn("decryption err in fragmented rx\n");
-		dev_kfree_skb_any(info.skb);
+		dev_kfree_skb_any(msdu_head);
 		goto end;
 	}
 
-	if (info.encrypt_type != HTT_RX_MPDU_ENCRYPT_NONE) {
+	if (enctype != HTT_RX_MPDU_ENCRYPT_NONE) {
 		hdrlen = ieee80211_hdrlen(hdr->frame_control);
-		paramlen = ath10k_htt_rx_crypto_param_len(info.encrypt_type);
+		paramlen = ath10k_htt_rx_crypto_param_len(enctype);
 
 		/* It is more efficient to move the header than the payload */
-		memmove((void *)info.skb->data + paramlen,
-			(void *)info.skb->data,
+		memmove((void *)msdu_head->data + paramlen,
+			(void *)msdu_head->data,
 			hdrlen);
-		skb_pull(info.skb, paramlen);
-		hdr = (struct ieee80211_hdr *)info.skb->data;
+		skb_pull(msdu_head, paramlen);
+		hdr = (struct ieee80211_hdr *)msdu_head->data;
 	}
 
 	/* remove trailing FCS */
 	trim  = 4;
 
 	/* remove crypto trailer */
-	trim += ath10k_htt_rx_crypto_tail_len(info.encrypt_type);
+	trim += ath10k_htt_rx_crypto_tail_len(enctype);
 
 	/* last fragment of TKIP frags has MIC */
 	if (!ieee80211_has_morefrags(hdr->frame_control) &&
-	    info.encrypt_type == HTT_RX_MPDU_ENCRYPT_TKIP_WPA)
+	    enctype == HTT_RX_MPDU_ENCRYPT_TKIP_WPA)
 		trim += 8;
 
-	if (trim > info.skb->len) {
+	if (trim > msdu_head->len) {
 		ath10k_warn("htt rx fragment: trailer longer than the frame itself? drop\n");
-		dev_kfree_skb_any(info.skb);
+		dev_kfree_skb_any(msdu_head);
 		goto end;
 	}
 
-	skb_trim(info.skb, info.skb->len - trim);
+	skb_trim(msdu_head, msdu_head->len - trim);
 
 	ath10k_dbg_dump(ATH10K_DBG_HTT_DUMP, NULL, "htt rx frag mpdu: ",
-			info.skb->data, info.skb->len);
-	ath10k_process_rx(htt->ar, &info);
+			msdu_head->data, msdu_head->len);
+	ath10k_process_rx(htt->ar, rx_status, msdu_head);
 
 end:
 	if (fw_desc_len > 0) {
diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index 7a3e2e40dd5..7064354d1f4 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -83,7 +83,7 @@ void ath10k_htt_tx_free_msdu_id(struct ath10k_htt *htt, u16 msdu_id)
 	__clear_bit(msdu_id, htt->used_msdu_ids);
 }
 
-int ath10k_htt_tx_attach(struct ath10k_htt *htt)
+int ath10k_htt_tx_alloc(struct ath10k_htt *htt)
 {
 	spin_lock_init(&htt->tx_lock);
 	init_waitqueue_head(&htt->empty_tx_wq);
@@ -120,7 +120,7 @@ int ath10k_htt_tx_attach(struct ath10k_htt *htt)
 	return 0;
 }
 
-static void ath10k_htt_tx_cleanup_pending(struct ath10k_htt *htt)
+static void ath10k_htt_tx_free_pending(struct ath10k_htt *htt)
 {
 	struct htt_tx_done tx_done = {0};
 	int msdu_id;
@@ -141,9 +141,9 @@ static void ath10k_htt_tx_cleanup_pending(struct ath10k_htt *htt)
 	spin_unlock_bh(&htt->tx_lock);
 }
 
-void ath10k_htt_tx_detach(struct ath10k_htt *htt)
+void ath10k_htt_tx_free(struct ath10k_htt *htt)
 {
-	ath10k_htt_tx_cleanup_pending(htt);
+	ath10k_htt_tx_free_pending(htt);
 	kfree(htt->pending_tx);
 	kfree(htt->used_msdu_ids);
 	dma_pool_destroy(htt->tx_pool);
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 35fc44e281f..007e855f4ba 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -28,6 +28,7 @@
 #define QCA988X_HW_2_0_CHIP_ID_REV	0x2
 #define QCA988X_HW_2_0_FW_DIR		"ath10k/QCA988X/hw2.0"
 #define QCA988X_HW_2_0_FW_FILE		"firmware.bin"
+#define QCA988X_HW_2_0_FW_2_FILE	"firmware-2.bin"
 #define QCA988X_HW_2_0_OTP_FILE		"otp.bin"
 #define QCA988X_HW_2_0_BOARD_DATA_FILE	"board.bin"
 #define QCA988X_HW_2_0_PATCH_LOAD_ADDR	0x1234
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 511a2f81e7a..a21080028c5 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -54,7 +54,10 @@ static int ath10k_send_key(struct ath10k_vif *arvif,
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_CCMP:
 		arg.key_cipher = WMI_CIPHER_AES_CCM;
-		key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
+		if (arvif->vdev_type == WMI_VDEV_TYPE_AP)
+			key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV_MGMT;
+		else
+			key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
 		break;
 	case WLAN_CIPHER_SUITE_TKIP:
 		arg.key_cipher = WMI_CIPHER_TKIP;
@@ -165,7 +168,7 @@ static int ath10k_clear_peer_keys(struct ath10k_vif *arvif,
 			first_errno = ret;
 
 		if (ret)
-			ath10k_warn("could not remove peer wep key %d (%d)\n",
+			ath10k_warn("failed to remove peer wep key %d: %d\n",
 				    i, ret);
 
 		peer->keys[i] = NULL;
@@ -213,7 +216,8 @@ static int ath10k_clear_vdev_key(struct ath10k_vif *arvif,
 			first_errno = ret;
 
 		if (ret)
-			ath10k_warn("could not remove key for %pM\n", addr);
+			ath10k_warn("failed to remove key for %pM: %d\n",
+				    addr, ret);
 	}
 
 	return first_errno;
@@ -323,14 +327,14 @@ static int ath10k_peer_create(struct ath10k *ar, u32 vdev_id, const u8 *addr)
 
 	ret = ath10k_wmi_peer_create(ar, vdev_id, addr);
 	if (ret) {
-		ath10k_warn("Failed to create wmi peer %pM on vdev %i: %i\n",
+		ath10k_warn("failed to create wmi peer %pM on vdev %i: %i\n",
 			    addr, vdev_id, ret);
 		return ret;
 	}
 
 	ret = ath10k_wait_for_peer_created(ar, vdev_id, addr);
 	if (ret) {
-		ath10k_warn("Failed to wait for created wmi peer %pM on vdev %i: %i\n",
+		ath10k_warn("failed to wait for created wmi peer %pM on vdev %i: %i\n",
 			    addr, vdev_id, ret);
 		return ret;
 	}
@@ -351,7 +355,7 @@ static int ath10k_mac_set_kickout(struct ath10k_vif *arvif)
 	ret = ath10k_wmi_pdev_set_param(ar, param,
 					ATH10K_KICKOUT_THRESHOLD);
 	if (ret) {
-		ath10k_warn("Failed to set kickout threshold on vdev %i: %d\n",
+		ath10k_warn("failed to set kickout threshold on vdev %i: %d\n",
 			    arvif->vdev_id, ret);
 		return ret;
 	}
@@ -360,7 +364,7 @@ static int ath10k_mac_set_kickout(struct ath10k_vif *arvif)
 	ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id, param,
 					ATH10K_KEEPALIVE_MIN_IDLE);
 	if (ret) {
-		ath10k_warn("Failed to set keepalive minimum idle time on vdev %i : %d\n",
+		ath10k_warn("failed to set keepalive minimum idle time on vdev %i: %d\n",
 			    arvif->vdev_id, ret);
 		return ret;
 	}
@@ -369,7 +373,7 @@ static int ath10k_mac_set_kickout(struct ath10k_vif *arvif)
 	ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id, param,
 					ATH10K_KEEPALIVE_MAX_IDLE);
 	if (ret) {
-		ath10k_warn("Failed to set keepalive maximum idle time on vdev %i: %d\n",
+		ath10k_warn("failed to set keepalive maximum idle time on vdev %i: %d\n",
 			    arvif->vdev_id, ret);
 		return ret;
 	}
@@ -378,7 +382,7 @@ static int ath10k_mac_set_kickout(struct ath10k_vif *arvif)
 	ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id, param,
 					ATH10K_KEEPALIVE_MAX_UNRESPONSIVE);
 	if (ret) {
-		ath10k_warn("Failed to set keepalive maximum unresponsive time on vdev %i: %d\n",
+		ath10k_warn("failed to set keepalive maximum unresponsive time on vdev %i: %d\n",
 			    arvif->vdev_id, ret);
 		return ret;
 	}
@@ -488,92 +492,20 @@ static inline int ath10k_vdev_setup_sync(struct ath10k *ar)
 	return 0;
 }
 
-static int ath10k_vdev_start(struct ath10k_vif *arvif)
+static bool ath10k_monitor_is_enabled(struct ath10k *ar)
 {
-	struct ath10k *ar = arvif->ar;
-	struct cfg80211_chan_def *chandef = &ar->chandef;
-	struct wmi_vdev_start_request_arg arg = {};
-	int ret = 0;
-
 	lockdep_assert_held(&ar->conf_mutex);
 
-	reinit_completion(&ar->vdev_setup_done);
-
-	arg.vdev_id = arvif->vdev_id;
-	arg.dtim_period = arvif->dtim_period;
-	arg.bcn_intval = arvif->beacon_interval;
-
-	arg.channel.freq = chandef->chan->center_freq;
-	arg.channel.band_center_freq1 = chandef->center_freq1;
-	arg.channel.mode = chan_to_phymode(chandef);
-
-	arg.channel.min_power = 0;
-	arg.channel.max_power = chandef->chan->max_power * 2;
-	arg.channel.max_reg_power = chandef->chan->max_reg_power * 2;
-	arg.channel.max_antenna_gain = chandef->chan->max_antenna_gain * 2;
-
-	if (arvif->vdev_type == WMI_VDEV_TYPE_AP) {
-		arg.ssid = arvif->u.ap.ssid;
-		arg.ssid_len = arvif->u.ap.ssid_len;
-		arg.hidden_ssid = arvif->u.ap.hidden_ssid;
-
-		/* For now allow DFS for AP mode */
-		arg.channel.chan_radar =
-			!!(chandef->chan->flags & IEEE80211_CHAN_RADAR);
-	} else if (arvif->vdev_type == WMI_VDEV_TYPE_IBSS) {
-		arg.ssid = arvif->vif->bss_conf.ssid;
-		arg.ssid_len = arvif->vif->bss_conf.ssid_len;
-	}
-
 	ath10k_dbg(ATH10K_DBG_MAC,
-		   "mac vdev %d start center_freq %d phymode %s\n",
-		   arg.vdev_id, arg.channel.freq,
-		   ath10k_wmi_phymode_str(arg.channel.mode));
+		   "mac monitor refs: promisc %d monitor %d cac %d\n",
+		   ar->promisc, ar->monitor,
+		   test_bit(ATH10K_CAC_RUNNING, &ar->dev_flags));
 
-	ret = ath10k_wmi_vdev_start(ar, &arg);
-	if (ret) {
-		ath10k_warn("WMI vdev %i start failed: ret %d\n",
-			    arg.vdev_id, ret);
-		return ret;
-	}
-
-	ret = ath10k_vdev_setup_sync(ar);
-	if (ret) {
-		ath10k_warn("vdev %i setup failed %d\n",
-			    arg.vdev_id, ret);
-		return ret;
-	}
-
-	return ret;
+	return ar->promisc || ar->monitor ||
+	       test_bit(ATH10K_CAC_RUNNING, &ar->dev_flags);
 }
 
-static int ath10k_vdev_stop(struct ath10k_vif *arvif)
-{
-	struct ath10k *ar = arvif->ar;
-	int ret;
-
-	lockdep_assert_held(&ar->conf_mutex);
-
-	reinit_completion(&ar->vdev_setup_done);
-
-	ret = ath10k_wmi_vdev_stop(ar, arvif->vdev_id);
-	if (ret) {
-		ath10k_warn("WMI vdev %i stop failed: ret %d\n",
-			    arvif->vdev_id, ret);
-		return ret;
-	}
-
-	ret = ath10k_vdev_setup_sync(ar);
-	if (ret) {
-		ath10k_warn("vdev %i setup sync failed %d\n",
-			    arvif->vdev_id, ret);
-		return ret;
-	}
-
-	return ret;
-}
-
-static int ath10k_monitor_start(struct ath10k *ar, int vdev_id)
+static int ath10k_monitor_vdev_start(struct ath10k *ar, int vdev_id)
 {
 	struct cfg80211_chan_def *chandef = &ar->chandef;
 	struct ieee80211_channel *channel = chandef->chan;
@@ -582,11 +514,6 @@ static int ath10k_monitor_start(struct ath10k *ar, int vdev_id)
 
 	lockdep_assert_held(&ar->conf_mutex);
 
-	if (!ar->monitor_present) {
-		ath10k_warn("mac montor stop -- monitor is not present\n");
-		return -EINVAL;
-	}
-
 	arg.vdev_id = vdev_id;
 	arg.channel.freq = channel->center_freq;
 	arg.channel.band_center_freq1 = chandef->center_freq1;
@@ -604,88 +531,75 @@ static int ath10k_monitor_start(struct ath10k *ar, int vdev_id)
 
 	ret = ath10k_wmi_vdev_start(ar, &arg);
 	if (ret) {
-		ath10k_warn("Monitor vdev %i start failed: ret %d\n",
+		ath10k_warn("failed to request monitor vdev %i start: %d\n",
 			    vdev_id, ret);
 		return ret;
 	}
 
 	ret = ath10k_vdev_setup_sync(ar);
 	if (ret) {
-		ath10k_warn("Monitor vdev %i setup failed %d\n",
+		ath10k_warn("failed to synchronize setup for monitor vdev %i: %d\n",
 			    vdev_id, ret);
 		return ret;
 	}
 
 	ret = ath10k_wmi_vdev_up(ar, vdev_id, 0, ar->mac_addr);
 	if (ret) {
-		ath10k_warn("Monitor vdev %i up failed: %d\n",
+		ath10k_warn("failed to put up monitor vdev %i: %d\n",
 			    vdev_id, ret);
 		goto vdev_stop;
 	}
 
 	ar->monitor_vdev_id = vdev_id;
-	ar->monitor_enabled = true;
 
+	ath10k_dbg(ATH10K_DBG_MAC, "mac monitor vdev %i started\n",
+		   ar->monitor_vdev_id);
 	return 0;
 
 vdev_stop:
 	ret = ath10k_wmi_vdev_stop(ar, ar->monitor_vdev_id);
 	if (ret)
-		ath10k_warn("Monitor vdev %i stop failed: %d\n",
+		ath10k_warn("failed to stop monitor vdev %i after start failure: %d\n",
 			    ar->monitor_vdev_id, ret);
 
 	return ret;
 }
 
-static int ath10k_monitor_stop(struct ath10k *ar)
+static int ath10k_monitor_vdev_stop(struct ath10k *ar)
 {
 	int ret = 0;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
-	if (!ar->monitor_present) {
-		ath10k_warn("mac montor stop -- monitor is not present\n");
-		return -EINVAL;
-	}
-
-	if (!ar->monitor_enabled) {
-		ath10k_warn("mac montor stop -- monitor is not enabled\n");
-		return -EINVAL;
-	}
-
 	ret = ath10k_wmi_vdev_down(ar, ar->monitor_vdev_id);
 	if (ret)
-		ath10k_warn("Monitor vdev %i down failed: %d\n",
+		ath10k_warn("failed to put down monitor vdev %i: %d\n",
 			    ar->monitor_vdev_id, ret);
 
 	ret = ath10k_wmi_vdev_stop(ar, ar->monitor_vdev_id);
 	if (ret)
-		ath10k_warn("Monitor vdev %i stop failed: %d\n",
+		ath10k_warn("failed to to request monitor vdev %i stop: %d\n",
 			    ar->monitor_vdev_id, ret);
 
 	ret = ath10k_vdev_setup_sync(ar);
 	if (ret)
-		ath10k_warn("Monitor_down sync failed, vdev %i: %d\n",
+		ath10k_warn("failed to synchronise monitor vdev %i: %d\n",
 			    ar->monitor_vdev_id, ret);
 
-	ar->monitor_enabled = false;
+	ath10k_dbg(ATH10K_DBG_MAC, "mac monitor vdev %i stopped\n",
+		   ar->monitor_vdev_id);
 	return ret;
 }
 
-static int ath10k_monitor_create(struct ath10k *ar)
+static int ath10k_monitor_vdev_create(struct ath10k *ar)
 {
 	int bit, ret = 0;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
-	if (ar->monitor_present) {
-		ath10k_warn("Monitor mode already enabled\n");
-		return 0;
-	}
-
 	bit = ffs(ar->free_vdev_map);
 	if (bit == 0) {
-		ath10k_warn("No free VDEV slots\n");
+		ath10k_warn("failed to find free vdev id for monitor vdev\n");
 		return -ENOMEM;
 	}
 
@@ -696,7 +610,7 @@ static int ath10k_monitor_create(struct ath10k *ar)
 				     WMI_VDEV_TYPE_MONITOR,
 				     0, ar->mac_addr);
 	if (ret) {
-		ath10k_warn("WMI vdev %i monitor create failed: ret %d\n",
+		ath10k_warn("failed to request monitor vdev %i creation: %d\n",
 			    ar->monitor_vdev_id, ret);
 		goto vdev_fail;
 	}
@@ -704,7 +618,6 @@ static int ath10k_monitor_create(struct ath10k *ar)
 	ath10k_dbg(ATH10K_DBG_MAC, "mac monitor vdev %d created\n",
 		   ar->monitor_vdev_id);
 
-	ar->monitor_present = true;
 	return 0;
 
 vdev_fail:
@@ -715,48 +628,123 @@ vdev_fail:
 	return ret;
 }
 
-static int ath10k_monitor_destroy(struct ath10k *ar)
+static int ath10k_monitor_vdev_delete(struct ath10k *ar)
 {
 	int ret = 0;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
-	if (!ar->monitor_present)
-		return 0;
-
 	ret = ath10k_wmi_vdev_delete(ar, ar->monitor_vdev_id);
 	if (ret) {
-		ath10k_warn("WMI vdev %i monitor delete failed: %d\n",
+		ath10k_warn("failed to request wmi monitor vdev %i removal: %d\n",
 			    ar->monitor_vdev_id, ret);
 		return ret;
 	}
 
 	ar->free_vdev_map |= 1 << (ar->monitor_vdev_id);
-	ar->monitor_present = false;
 
 	ath10k_dbg(ATH10K_DBG_MAC, "mac monitor vdev %d deleted\n",
 		   ar->monitor_vdev_id);
 	return ret;
 }
 
-static int ath10k_start_cac(struct ath10k *ar)
+static int ath10k_monitor_start(struct ath10k *ar)
 {
 	int ret;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
-	set_bit(ATH10K_CAC_RUNNING, &ar->dev_flags);
+	if (!ath10k_monitor_is_enabled(ar)) {
+		ath10k_warn("trying to start monitor with no references\n");
+		return 0;
+	}
+
+	if (ar->monitor_started) {
+		ath10k_dbg(ATH10K_DBG_MAC, "mac monitor already started\n");
+		return 0;
+	}
 
-	ret = ath10k_monitor_create(ar);
+	ret = ath10k_monitor_vdev_create(ar);
 	if (ret) {
-		clear_bit(ATH10K_CAC_RUNNING, &ar->dev_flags);
+		ath10k_warn("failed to create monitor vdev: %d\n", ret);
 		return ret;
 	}
 
-	ret = ath10k_monitor_start(ar, ar->monitor_vdev_id);
+	ret = ath10k_monitor_vdev_start(ar, ar->monitor_vdev_id);
+	if (ret) {
+		ath10k_warn("failed to start monitor vdev: %d\n", ret);
+		ath10k_monitor_vdev_delete(ar);
+		return ret;
+	}
+
+	ar->monitor_started = true;
+	ath10k_dbg(ATH10K_DBG_MAC, "mac monitor started\n");
+
+	return 0;
+}
+
+static void ath10k_monitor_stop(struct ath10k *ar)
+{
+	int ret;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	if (ath10k_monitor_is_enabled(ar)) {
+		ath10k_dbg(ATH10K_DBG_MAC,
+			   "mac monitor will be stopped later\n");
+		return;
+	}
+
+	if (!ar->monitor_started) {
+		ath10k_dbg(ATH10K_DBG_MAC,
+			   "mac monitor probably failed to start earlier\n");
+		return;
+	}
+
+	ret = ath10k_monitor_vdev_stop(ar);
+	if (ret)
+		ath10k_warn("failed to stop monitor vdev: %d\n", ret);
+
+	ret = ath10k_monitor_vdev_delete(ar);
+	if (ret)
+		ath10k_warn("failed to delete monitor vdev: %d\n", ret);
+
+	ar->monitor_started = false;
+	ath10k_dbg(ATH10K_DBG_MAC, "mac monitor stopped\n");
+}
+
+static int ath10k_recalc_rtscts_prot(struct ath10k_vif *arvif)
+{
+	struct ath10k *ar = arvif->ar;
+	u32 vdev_param, rts_cts = 0;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	vdev_param = ar->wmi.vdev_param->enable_rtscts;
+
+	if (arvif->use_cts_prot || arvif->num_legacy_stations > 0)
+		rts_cts |= SM(WMI_RTSCTS_ENABLED, WMI_RTSCTS_SET);
+
+	if (arvif->num_legacy_stations > 0)
+		rts_cts |= SM(WMI_RTSCTS_ACROSS_SW_RETRIES,
+			      WMI_RTSCTS_PROFILE);
+
+	return ath10k_wmi_vdev_set_param(ar, arvif->vdev_id, vdev_param,
+					 rts_cts);
+}
+
+static int ath10k_start_cac(struct ath10k *ar)
+{
+	int ret;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	set_bit(ATH10K_CAC_RUNNING, &ar->dev_flags);
+
+	ret = ath10k_monitor_start(ar);
 	if (ret) {
+		ath10k_warn("failed to start monitor (cac): %d\n", ret);
 		clear_bit(ATH10K_CAC_RUNNING, &ar->dev_flags);
-		ath10k_monitor_destroy(ar);
 		return ret;
 	}
 
@@ -774,58 +762,26 @@ static int ath10k_stop_cac(struct ath10k *ar)
 	if (!test_bit(ATH10K_CAC_RUNNING, &ar->dev_flags))
 		return 0;
 
-	ath10k_monitor_stop(ar);
-	ath10k_monitor_destroy(ar);
 	clear_bit(ATH10K_CAC_RUNNING, &ar->dev_flags);
+	ath10k_monitor_stop(ar);
 
 	ath10k_dbg(ATH10K_DBG_MAC, "mac cac finished\n");
 
 	return 0;
 }
 
-static const char *ath10k_dfs_state(enum nl80211_dfs_state dfs_state)
+static void ath10k_recalc_radar_detection(struct ath10k *ar)
 {
-	switch (dfs_state) {
-	case NL80211_DFS_USABLE:
-		return "USABLE";
-	case NL80211_DFS_UNAVAILABLE:
-		return "UNAVAILABLE";
-	case NL80211_DFS_AVAILABLE:
-		return "AVAILABLE";
-	default:
-		WARN_ON(1);
-		return "bug";
-	}
-}
-
-static void ath10k_config_radar_detection(struct ath10k *ar)
-{
-	struct ieee80211_channel *chan = ar->hw->conf.chandef.chan;
-	bool radar = ar->hw->conf.radar_enabled;
-	bool chan_radar = !!(chan->flags & IEEE80211_CHAN_RADAR);
-	enum nl80211_dfs_state dfs_state = chan->dfs_state;
 	int ret;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
-	ath10k_dbg(ATH10K_DBG_MAC,
-		   "mac radar config update: chan %dMHz radar %d chan radar %d chan state %s\n",
-		   chan->center_freq, radar, chan_radar,
-		   ath10k_dfs_state(dfs_state));
-
-	/*
-	 * It's safe to call it even if CAC is not started.
-	 * This call here guarantees changing channel, etc. will stop CAC.
-	 */
 	ath10k_stop_cac(ar);
 
-	if (!radar)
-		return;
-
-	if (!chan_radar)
+	if (!ar->radar_enabled)
 		return;
 
-	if (dfs_state != NL80211_DFS_USABLE)
+	if (ar->num_started_vdevs > 0)
 		return;
 
 	ret = ath10k_start_cac(ar);
@@ -835,11 +791,106 @@ static void ath10k_config_radar_detection(struct ath10k *ar)
 		 * radiation is not allowed, make this channel DFS_UNAVAILABLE
 		 * by indicating that radar was detected.
 		 */
-		ath10k_warn("failed to start CAC (%d)\n", ret);
+		ath10k_warn("failed to start CAC: %d\n", ret);
 		ieee80211_radar_detected(ar->hw);
 	}
 }
 
+static int ath10k_vdev_start(struct ath10k_vif *arvif)
+{
+	struct ath10k *ar = arvif->ar;
+	struct cfg80211_chan_def *chandef = &ar->chandef;
+	struct wmi_vdev_start_request_arg arg = {};
+	int ret = 0;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	reinit_completion(&ar->vdev_setup_done);
+
+	arg.vdev_id = arvif->vdev_id;
+	arg.dtim_period = arvif->dtim_period;
+	arg.bcn_intval = arvif->beacon_interval;
+
+	arg.channel.freq = chandef->chan->center_freq;
+	arg.channel.band_center_freq1 = chandef->center_freq1;
+	arg.channel.mode = chan_to_phymode(chandef);
+
+	arg.channel.min_power = 0;
+	arg.channel.max_power = chandef->chan->max_power * 2;
+	arg.channel.max_reg_power = chandef->chan->max_reg_power * 2;
+	arg.channel.max_antenna_gain = chandef->chan->max_antenna_gain * 2;
+
+	if (arvif->vdev_type == WMI_VDEV_TYPE_AP) {
+		arg.ssid = arvif->u.ap.ssid;
+		arg.ssid_len = arvif->u.ap.ssid_len;
+		arg.hidden_ssid = arvif->u.ap.hidden_ssid;
+
+		/* For now allow DFS for AP mode */
+		arg.channel.chan_radar =
+			!!(chandef->chan->flags & IEEE80211_CHAN_RADAR);
+	} else if (arvif->vdev_type == WMI_VDEV_TYPE_IBSS) {
+		arg.ssid = arvif->vif->bss_conf.ssid;
+		arg.ssid_len = arvif->vif->bss_conf.ssid_len;
+	}
+
+	ath10k_dbg(ATH10K_DBG_MAC,
+		   "mac vdev %d start center_freq %d phymode %s\n",
+		   arg.vdev_id, arg.channel.freq,
+		   ath10k_wmi_phymode_str(arg.channel.mode));
+
+	ret = ath10k_wmi_vdev_start(ar, &arg);
+	if (ret) {
+		ath10k_warn("failed to start WMI vdev %i: %d\n",
+			    arg.vdev_id, ret);
+		return ret;
+	}
+
+	ret = ath10k_vdev_setup_sync(ar);
+	if (ret) {
+		ath10k_warn("failed to synchronise setup for vdev %i: %d\n",
+			    arg.vdev_id, ret);
+		return ret;
+	}
+
+	ar->num_started_vdevs++;
+	ath10k_recalc_radar_detection(ar);
+
+	return ret;
+}
+
+static int ath10k_vdev_stop(struct ath10k_vif *arvif)
+{
+	struct ath10k *ar = arvif->ar;
+	int ret;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	reinit_completion(&ar->vdev_setup_done);
+
+	ret = ath10k_wmi_vdev_stop(ar, arvif->vdev_id);
+	if (ret) {
+		ath10k_warn("failed to stop WMI vdev %i: %d\n",
+			    arvif->vdev_id, ret);
+		return ret;
+	}
+
+	ret = ath10k_vdev_setup_sync(ar);
+	if (ret) {
+		ath10k_warn("failed to syncronise setup for vdev %i: %d\n",
+			    arvif->vdev_id, ret);
+		return ret;
+	}
+
+	WARN_ON(ar->num_started_vdevs == 0);
+
+	if (ar->num_started_vdevs != 0) {
+		ar->num_started_vdevs--;
+		ath10k_recalc_radar_detection(ar);
+	}
+
+	return ret;
+}
+
 static void ath10k_control_beaconing(struct ath10k_vif *arvif,
 				struct ieee80211_bss_conf *info)
 {
@@ -880,7 +931,7 @@ static void ath10k_control_beaconing(struct ath10k_vif *arvif,
 	ret = ath10k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid,
 				 arvif->bssid);
 	if (ret) {
-		ath10k_warn("Failed to bring up vdev %d: %i\n",
+		ath10k_warn("failed to bring up vdev %d: %i\n",
 			    arvif->vdev_id, ret);
 		ath10k_vdev_stop(arvif);
 		return;
@@ -904,7 +955,7 @@ static void ath10k_control_ibss(struct ath10k_vif *arvif,
 	if (!info->ibss_joined) {
 		ret = ath10k_peer_delete(arvif->ar, arvif->vdev_id, self_peer);
 		if (ret)
-			ath10k_warn("Failed to delete IBSS self peer:%pM for VDEV:%d ret:%d\n",
+			ath10k_warn("failed to delete IBSS self peer %pM for vdev %d: %d\n",
 				    self_peer, arvif->vdev_id, ret);
 
 		if (is_zero_ether_addr(arvif->bssid))
@@ -913,7 +964,7 @@ static void ath10k_control_ibss(struct ath10k_vif *arvif,
 		ret = ath10k_peer_delete(arvif->ar, arvif->vdev_id,
 					 arvif->bssid);
 		if (ret) {
-			ath10k_warn("Failed to delete IBSS BSSID peer:%pM for VDEV:%d ret:%d\n",
+			ath10k_warn("failed to delete IBSS BSSID peer %pM for vdev %d: %d\n",
 				    arvif->bssid, arvif->vdev_id, ret);
 			return;
 		}
@@ -925,7 +976,7 @@ static void ath10k_control_ibss(struct ath10k_vif *arvif,
 
 	ret = ath10k_peer_create(arvif->ar, arvif->vdev_id, self_peer);
 	if (ret) {
-		ath10k_warn("Failed to create IBSS self peer:%pM for VDEV:%d ret:%d\n",
+		ath10k_warn("failed to create IBSS self peer %pM for vdev %d: %d\n",
 			    self_peer, arvif->vdev_id, ret);
 		return;
 	}
@@ -934,7 +985,7 @@ static void ath10k_control_ibss(struct ath10k_vif *arvif,
 	ret = ath10k_wmi_vdev_set_param(arvif->ar, arvif->vdev_id, vdev_param,
 					ATH10K_DEFAULT_ATIM);
 	if (ret)
-		ath10k_warn("Failed to set IBSS ATIM for VDEV:%d ret:%d\n",
+		ath10k_warn("failed to set IBSS ATIM for vdev %d: %d\n",
 			    arvif->vdev_id, ret);
 }
 
@@ -961,7 +1012,7 @@ static int ath10k_mac_vif_setup_ps(struct ath10k_vif *arvif)
 		ret = ath10k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param,
 						  conf->dynamic_ps_timeout);
 		if (ret) {
-			ath10k_warn("Failed to set inactivity time for vdev %d: %i\n",
+			ath10k_warn("failed to set inactivity time for vdev %d: %i\n",
 				    arvif->vdev_id, ret);
 			return ret;
 		}
@@ -974,8 +1025,8 @@ static int ath10k_mac_vif_setup_ps(struct ath10k_vif *arvif)
 
 	ret = ath10k_wmi_set_psmode(ar, arvif->vdev_id, psmode);
 	if (ret) {
-		ath10k_warn("Failed to set PS Mode: %d for VDEV: %d\n",
-			    psmode, arvif->vdev_id);
+		ath10k_warn("failed to set PS Mode %d for vdev %d: %d\n",
+			    psmode, arvif->vdev_id, ret);
 		return ret;
 	}
 
@@ -1429,7 +1480,7 @@ static void ath10k_bss_assoc(struct ieee80211_hw *hw,
 
 	ap_sta = ieee80211_find_sta(vif, bss_conf->bssid);
 	if (!ap_sta) {
-		ath10k_warn("Failed to find station entry for %pM, vdev %i\n",
+		ath10k_warn("failed to find station entry for bss %pM vdev %i\n",
 			    bss_conf->bssid, arvif->vdev_id);
 		rcu_read_unlock();
 		return;
@@ -1442,7 +1493,7 @@ static void ath10k_bss_assoc(struct ieee80211_hw *hw,
 	ret = ath10k_peer_assoc_prepare(ar, arvif, ap_sta,
 					bss_conf, &peer_arg);
 	if (ret) {
-		ath10k_warn("Peer assoc prepare failed for %pM vdev %i\n: %d",
+		ath10k_warn("failed to prepare peer assoc for %pM vdev %i: %d\n",
 			    bss_conf->bssid, arvif->vdev_id, ret);
 		rcu_read_unlock();
 		return;
@@ -1452,7 +1503,7 @@ static void ath10k_bss_assoc(struct ieee80211_hw *hw,
 
 	ret = ath10k_wmi_peer_assoc(ar, &peer_arg);
 	if (ret) {
-		ath10k_warn("Peer assoc failed for %pM vdev %i\n: %d",
+		ath10k_warn("failed to run peer assoc for %pM vdev %i: %d\n",
 			    bss_conf->bssid, arvif->vdev_id, ret);
 		return;
 	}
@@ -1473,7 +1524,7 @@ static void ath10k_bss_assoc(struct ieee80211_hw *hw,
 
 	ret = ath10k_wmi_vdev_up(ar, arvif->vdev_id, arvif->aid, arvif->bssid);
 	if (ret) {
-		ath10k_warn("VDEV: %d up failed: ret %d\n",
+		ath10k_warn("failed to set vdev %d up: %d\n",
 			    arvif->vdev_id, ret);
 		return;
 	}
@@ -1524,7 +1575,7 @@ static void ath10k_bss_disassoc(struct ieee80211_hw *hw,
 }
 
 static int ath10k_station_assoc(struct ath10k *ar, struct ath10k_vif *arvif,
-				struct ieee80211_sta *sta)
+				struct ieee80211_sta *sta, bool reassoc)
 {
 	struct wmi_peer_assoc_complete_arg peer_arg;
 	int ret = 0;
@@ -1533,34 +1584,46 @@ static int ath10k_station_assoc(struct ath10k *ar, struct ath10k_vif *arvif,
 
 	ret = ath10k_peer_assoc_prepare(ar, arvif, sta, NULL, &peer_arg);
 	if (ret) {
-		ath10k_warn("WMI peer assoc prepare failed for %pM vdev %i: %i\n",
+		ath10k_warn("failed to prepare WMI peer assoc for %pM vdev %i: %i\n",
 			    sta->addr, arvif->vdev_id, ret);
 		return ret;
 	}
 
+	peer_arg.peer_reassoc = reassoc;
 	ret = ath10k_wmi_peer_assoc(ar, &peer_arg);
 	if (ret) {
-		ath10k_warn("Peer assoc failed for STA %pM vdev %i: %d\n",
+		ath10k_warn("failed to run peer assoc for STA %pM vdev %i: %d\n",
 			    sta->addr, arvif->vdev_id, ret);
 		return ret;
 	}
 
 	ret = ath10k_setup_peer_smps(ar, arvif, sta->addr, &sta->ht_cap);
 	if (ret) {
-		ath10k_warn("failed to setup peer SMPS for vdev: %d\n", ret);
+		ath10k_warn("failed to setup peer SMPS for vdev %d: %d\n",
+			    arvif->vdev_id, ret);
 		return ret;
 	}
 
+	if (!sta->wme) {
+		arvif->num_legacy_stations++;
+		ret  = ath10k_recalc_rtscts_prot(arvif);
+		if (ret) {
+			ath10k_warn("failed to recalculate rts/cts prot for vdev %d: %d\n",
+				    arvif->vdev_id, ret);
+			return ret;
+		}
+	}
+
 	ret = ath10k_install_peer_wep_keys(arvif, sta->addr);
 	if (ret) {
-		ath10k_warn("could not install peer wep keys for vdev %i: %d\n",
+		ath10k_warn("failed to install peer wep keys for vdev %i: %d\n",
 			    arvif->vdev_id, ret);
 		return ret;
 	}
 
 	ret = ath10k_peer_assoc_qos_ap(ar, arvif, sta);
 	if (ret) {
-		ath10k_warn("could not set qos params for STA %pM for vdev %i: %d\n",
+		ath10k_warn("failed to set qos params for STA %pM for vdev %i: %d\n",
 			    sta->addr, arvif->vdev_id, ret);
 		return ret;
 	}
@@ -1575,9 +1638,19 @@ static int ath10k_station_disassoc(struct ath10k *ar, struct ath10k_vif *arvif,
 
 	lockdep_assert_held(&ar->conf_mutex);
 
+	if (!sta->wme) {
+		arvif->num_legacy_stations--;
+		ret = ath10k_recalc_rtscts_prot(arvif);
+		if (ret) {
+			ath10k_warn("failed to recalculate rts/cts prot for vdev %d: %d\n",
+				    arvif->vdev_id, ret);
+			return ret;
+		}
+	}
+
 	ret = ath10k_clear_peer_keys(arvif, sta->addr);
 	if (ret) {
-		ath10k_warn("could not clear all peer wep keys for vdev %i: %d\n",
+		ath10k_warn("failed to clear all peer wep keys for vdev %i: %d\n",
 			    arvif->vdev_id, ret);
 		return ret;
 	}
@@ -1685,19 +1758,44 @@ static int ath10k_update_channel_list(struct ath10k *ar)
 	return ret;
 }
 
+static enum wmi_dfs_region
+ath10k_mac_get_dfs_region(enum nl80211_dfs_regions dfs_region)
+{
+	switch (dfs_region) {
+	case NL80211_DFS_UNSET:
+		return WMI_UNINIT_DFS_DOMAIN;
+	case NL80211_DFS_FCC:
+		return WMI_FCC_DFS_DOMAIN;
+	case NL80211_DFS_ETSI:
+		return WMI_ETSI_DFS_DOMAIN;
+	case NL80211_DFS_JP:
+		return WMI_MKK4_DFS_DOMAIN;
+	}
+	return WMI_UNINIT_DFS_DOMAIN;
+}
+
 static void ath10k_regd_update(struct ath10k *ar)
 {
 	struct reg_dmn_pair_mapping *regpair;
 	int ret;
+	enum wmi_dfs_region wmi_dfs_reg;
+	enum nl80211_dfs_regions nl_dfs_reg;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
 	ret = ath10k_update_channel_list(ar);
 	if (ret)
-		ath10k_warn("could not update channel list (%d)\n", ret);
+		ath10k_warn("failed to update channel list: %d\n", ret);
 
 	regpair = ar->ath_common.regulatory.regpair;
 
+	if (config_enabled(CONFIG_ATH10K_DFS_CERTIFIED) && ar->dfs_detector) {
+		nl_dfs_reg = ar->dfs_detector->region;
+		wmi_dfs_reg = ath10k_mac_get_dfs_region(nl_dfs_reg);
+	} else {
+		wmi_dfs_reg = WMI_UNINIT_DFS_DOMAIN;
+	}
+
 	/* Target allows setting up per-band regdomain but ath_common provides
 	 * a combined one only */
 	ret = ath10k_wmi_pdev_set_regdomain(ar,
@@ -1705,9 +1803,10 @@ static void ath10k_regd_update(struct ath10k *ar)
 					    regpair->reg_domain, /* 2ghz */
 					    regpair->reg_domain, /* 5ghz */
 					    regpair->reg_2ghz_ctl,
-					    regpair->reg_5ghz_ctl);
+					    regpair->reg_5ghz_ctl,
+					    wmi_dfs_reg);
 	if (ret)
-		ath10k_warn("could not set pdev regdomain (%d)\n", ret);
+		ath10k_warn("failed to set pdev regdomain: %d\n", ret);
 }
 
 static void ath10k_reg_notifier(struct wiphy *wiphy,
@@ -1725,7 +1824,7 @@ static void ath10k_reg_notifier(struct wiphy *wiphy,
 		result = ar->dfs_detector->set_dfs_domain(ar->dfs_detector,
 							  request->dfs_region);
 		if (!result)
-			ath10k_warn("dfs region 0x%X not supported, will trigger radar for every pulse\n",
+			ath10k_warn("DFS region 0x%X not supported, will trigger radar for every pulse\n",
 				    request->dfs_region);
 	}
 
@@ -1759,10 +1858,10 @@ static u8 ath10k_tx_h_get_vdev_id(struct ath10k *ar,
 	if (info->control.vif)
 		return ath10k_vif_to_arvif(info->control.vif)->vdev_id;
 
-	if (ar->monitor_enabled)
+	if (ar->monitor_started)
 		return ar->monitor_vdev_id;
 
-	ath10k_warn("could not resolve vdev id\n");
+	ath10k_warn("failed to resolve vdev id\n");
 	return 0;
 }
 
@@ -1792,8 +1891,13 @@ static void ath10k_tx_wep_key_work(struct work_struct *work)
 						wep_key_work);
 	int ret, keyidx = arvif->def_wep_key_newidx;
 
+	mutex_lock(&arvif->ar->conf_mutex);
+
+	if (arvif->ar->state != ATH10K_STATE_ON)
+		goto unlock;
+
 	if (arvif->def_wep_key_idx == keyidx)
-		return;
+		goto unlock;
 
 	ath10k_dbg(ATH10K_DBG_MAC, "mac vdev %d set keyidx %d\n",
 		   arvif->vdev_id, keyidx);
@@ -1803,11 +1907,16 @@ static void ath10k_tx_wep_key_work(struct work_struct *work)
 					arvif->ar->wmi.vdev_param->def_keyid,
 					keyidx);
 	if (ret) {
-		ath10k_warn("could not update wep keyidx (%d)\n", ret);
-		return;
+		ath10k_warn("failed to update wep key index for vdev %d: %d\n",
+			    arvif->vdev_id,
+			    ret);
+		goto unlock;
 	}
 
 	arvif->def_wep_key_idx = keyidx;
+
+unlock:
+	mutex_unlock(&arvif->ar->conf_mutex);
 }
 
 static void ath10k_tx_h_update_wep_key(struct sk_buff *skb)
@@ -1879,7 +1988,7 @@ static void ath10k_tx_htt(struct ath10k *ar, struct sk_buff *skb)
 			     ar->fw_features)) {
 			if (skb_queue_len(&ar->wmi_mgmt_tx_queue) >=
 			    ATH10K_MAX_NUM_MGMT_PENDING) {
-				ath10k_warn("wmi mgmt_tx queue limit reached\n");
+				ath10k_warn("reached WMI management tranmist queue limit\n");
 				ret = -EBUSY;
 				goto exit;
 			}
@@ -1903,7 +2012,7 @@ static void ath10k_tx_htt(struct ath10k *ar, struct sk_buff *skb)
 
 exit:
 	if (ret) {
-		ath10k_warn("tx failed (%d). dropping packet.\n", ret);
+		ath10k_warn("failed to transmit packet, dropping: %d\n", ret);
 		ieee80211_free_txskb(ar->hw, skb);
 	}
 }
@@ -1964,7 +2073,7 @@ void ath10k_offchan_tx_work(struct work_struct *work)
 		if (!peer) {
 			ret = ath10k_peer_create(ar, vdev_id, peer_addr);
 			if (ret)
-				ath10k_warn("peer %pM on vdev %d not created (%d)\n",
+				ath10k_warn("failed to create peer %pM on vdev %d: %d\n",
 					    peer_addr, vdev_id, ret);
 		}
 
@@ -1984,7 +2093,7 @@ void ath10k_offchan_tx_work(struct work_struct *work)
 		if (!peer) {
 			ret = ath10k_peer_delete(ar, vdev_id, peer_addr);
 			if (ret)
-				ath10k_warn("peer %pM on vdev %d not deleted (%d)\n",
+				ath10k_warn("failed to delete peer %pM on vdev %d: %d\n",
 					    peer_addr, vdev_id, ret);
 		}
 
@@ -2018,7 +2127,8 @@ void ath10k_mgmt_over_wmi_tx_work(struct work_struct *work)
 
 		ret = ath10k_wmi_mgmt_tx(ar, skb);
 		if (ret) {
-			ath10k_warn("wmi mgmt_tx failed (%d)\n", ret);
+			ath10k_warn("failed to transmit management frame via WMI: %d\n",
+				    ret);
 			ieee80211_free_txskb(ar->hw, skb);
 		}
 	}
@@ -2043,7 +2153,7 @@ void ath10k_reset_scan(unsigned long ptr)
 		return;
 	}
 
-	ath10k_warn("scan timeout. resetting. fw issue?\n");
+	ath10k_warn("scan timed out, firmware problem?\n");
 
 	if (ar->scan.is_roc)
 		ieee80211_remain_on_channel_expired(ar->hw);
@@ -2079,7 +2189,7 @@ static int ath10k_abort_scan(struct ath10k *ar)
 
 	ret = ath10k_wmi_stop_scan(ar, &arg);
 	if (ret) {
-		ath10k_warn("could not submit wmi stop scan (%d)\n", ret);
+		ath10k_warn("failed to stop wmi scan: %d\n", ret);
 		spin_lock_bh(&ar->data_lock);
 		ar->scan.in_progress = false;
 		ath10k_offchan_tx_purge(ar);
@@ -2099,7 +2209,7 @@ static int ath10k_abort_scan(struct ath10k *ar)
 
 	spin_lock_bh(&ar->data_lock);
 	if (ar->scan.in_progress) {
-		ath10k_warn("could not stop scan. its still in progress\n");
+		ath10k_warn("failed to stop scan, it's still in progress\n");
 		ar->scan.in_progress = false;
 		ath10k_offchan_tx_purge(ar);
 		ret = -ETIMEDOUT;
@@ -2187,72 +2297,171 @@ static void ath10k_tx(struct ieee80211_hw *hw,
 	ath10k_tx_htt(ar, skb);
 }
 
-/*
- * Initialize various parameters with default vaules.
- */
+/* Must not be called with conf_mutex held as workers can use that also. */
+static void ath10k_drain_tx(struct ath10k *ar)
+{
+	/* make sure rcu-protected mac80211 tx path itself is drained */
+	synchronize_net();
+
+	ath10k_offchan_tx_purge(ar);
+	ath10k_mgmt_over_wmi_tx_purge(ar);
+
+	cancel_work_sync(&ar->offchan_tx_work);
+	cancel_work_sync(&ar->wmi_mgmt_tx_work);
+}
+
 void ath10k_halt(struct ath10k *ar)
 {
+	struct ath10k_vif *arvif;
+
 	lockdep_assert_held(&ar->conf_mutex);
 
-	ath10k_stop_cac(ar);
+	if (ath10k_monitor_is_enabled(ar)) {
+		clear_bit(ATH10K_CAC_RUNNING, &ar->dev_flags);
+		ar->promisc = false;
+		ar->monitor = false;
+		ath10k_monitor_stop(ar);
+	}
+
 	del_timer_sync(&ar->scan.timeout);
-	ath10k_offchan_tx_purge(ar);
-	ath10k_mgmt_over_wmi_tx_purge(ar);
+	ath10k_reset_scan((unsigned long)ar);
 	ath10k_peer_cleanup_all(ar);
 	ath10k_core_stop(ar);
 	ath10k_hif_power_down(ar);
 
 	spin_lock_bh(&ar->data_lock);
-	if (ar->scan.in_progress) {
-		del_timer(&ar->scan.timeout);
-		ar->scan.in_progress = false;
-		ieee80211_scan_completed(ar->hw, true);
+	list_for_each_entry(arvif, &ar->arvifs, list) {
+		if (!arvif->beacon)
+			continue;
+
+		dma_unmap_single(arvif->ar->dev,
+				 ATH10K_SKB_CB(arvif->beacon)->paddr,
+				 arvif->beacon->len, DMA_TO_DEVICE);
+		dev_kfree_skb_any(arvif->beacon);
+		arvif->beacon = NULL;
 	}
 	spin_unlock_bh(&ar->data_lock);
 }
 
+static int ath10k_get_antenna(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant)
+{
+	struct ath10k *ar = hw->priv;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->cfg_tx_chainmask) {
+		*tx_ant = ar->cfg_tx_chainmask;
+		*rx_ant = ar->cfg_rx_chainmask;
+	} else {
+		*tx_ant = ar->supp_tx_chainmask;
+		*rx_ant = ar->supp_rx_chainmask;
+	}
+
+	mutex_unlock(&ar->conf_mutex);
+
+	return 0;
+}
+
+static int __ath10k_set_antenna(struct ath10k *ar, u32 tx_ant, u32 rx_ant)
+{
+	int ret;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	ar->cfg_tx_chainmask = tx_ant;
+	ar->cfg_rx_chainmask = rx_ant;
+
+	if ((ar->state != ATH10K_STATE_ON) &&
+	    (ar->state != ATH10K_STATE_RESTARTED))
+		return 0;
+
+	ret = ath10k_wmi_pdev_set_param(ar, ar->wmi.pdev_param->tx_chain_mask,
+					tx_ant);
+	if (ret) {
+		ath10k_warn("failed to set tx-chainmask: %d, req 0x%x\n",
+			    ret, tx_ant);
+		return ret;
+	}
+
+	ret = ath10k_wmi_pdev_set_param(ar, ar->wmi.pdev_param->rx_chain_mask,
+					rx_ant);
+	if (ret) {
+		ath10k_warn("failed to set rx-chainmask: %d, req 0x%x\n",
+			    ret, rx_ant);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int ath10k_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
+{
+	struct ath10k *ar = hw->priv;
+	int ret;
+
+	mutex_lock(&ar->conf_mutex);
+	ret = __ath10k_set_antenna(ar, tx_ant, rx_ant);
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
+}
+
 static int ath10k_start(struct ieee80211_hw *hw)
 {
 	struct ath10k *ar = hw->priv;
 	int ret = 0;
 
+	/*
+	 * This makes sense only when restarting hw. It is harmless to call
+	 * uncoditionally. This is necessary to make sure no HTT/WMI tx
+	 * commands will be submitted while restarting.
+	 */
+	ath10k_drain_tx(ar);
+
 	mutex_lock(&ar->conf_mutex);
 
-	if (ar->state != ATH10K_STATE_OFF &&
-	    ar->state != ATH10K_STATE_RESTARTING) {
+	switch (ar->state) {
+	case ATH10K_STATE_OFF:
+		ar->state = ATH10K_STATE_ON;
+		break;
+	case ATH10K_STATE_RESTARTING:
+		ath10k_halt(ar);
+		ar->state = ATH10K_STATE_RESTARTED;
+		break;
+	case ATH10K_STATE_ON:
+	case ATH10K_STATE_RESTARTED:
+	case ATH10K_STATE_WEDGED:
+		WARN_ON(1);
 		ret = -EINVAL;
-		goto exit;
+		goto err;
 	}
 
 	ret = ath10k_hif_power_up(ar);
 	if (ret) {
-		ath10k_err("could not init hif (%d)\n", ret);
-		ar->state = ATH10K_STATE_OFF;
-		goto exit;
+		ath10k_err("Could not init hif: %d\n", ret);
+		goto err_off;
 	}
 
 	ret = ath10k_core_start(ar);
 	if (ret) {
-		ath10k_err("could not init core (%d)\n", ret);
-		ath10k_hif_power_down(ar);
-		ar->state = ATH10K_STATE_OFF;
-		goto exit;
+		ath10k_err("Could not init core: %d\n", ret);
+		goto err_power_down;
 	}
 
-	if (ar->state == ATH10K_STATE_OFF)
-		ar->state = ATH10K_STATE_ON;
-	else if (ar->state == ATH10K_STATE_RESTARTING)
-		ar->state = ATH10K_STATE_RESTARTED;
-
 	ret = ath10k_wmi_pdev_set_param(ar, ar->wmi.pdev_param->pmf_qos, 1);
-	if (ret)
-		ath10k_warn("could not enable WMI_PDEV_PARAM_PMF_QOS (%d)\n",
-			    ret);
+	if (ret) {
+		ath10k_warn("failed to enable PMF QOS: %d\n", ret);
+		goto err_core_stop;
+	}
 
 	ret = ath10k_wmi_pdev_set_param(ar, ar->wmi.pdev_param->dynamic_bw, 1);
-	if (ret)
-		ath10k_warn("could not init WMI_PDEV_PARAM_DYNAMIC_BW (%d)\n",
-			    ret);
+	if (ret) {
+		ath10k_warn("failed to enable dynamic BW: %d\n", ret);
+		goto err_core_stop;
+	}
+
+	if (ar->cfg_tx_chainmask)
+		__ath10k_set_antenna(ar, ar->cfg_tx_chainmask,
+				     ar->cfg_rx_chainmask);
 
 	/*
 	 * By default FW set ARP frames ac to voice (6). In that case ARP
@@ -2266,15 +2475,27 @@ static int ath10k_start(struct ieee80211_hw *hw)
 	ret = ath10k_wmi_pdev_set_param(ar,
 					ar->wmi.pdev_param->arp_ac_override, 0);
 	if (ret) {
-		ath10k_warn("could not set arp ac override parameter: %d\n",
+		ath10k_warn("failed to set arp ac override parameter: %d\n",
 			    ret);
-		goto exit;
+		goto err_core_stop;
 	}
 
+	ar->num_started_vdevs = 0;
 	ath10k_regd_update(ar);
-	ret = 0;
 
-exit:
+	mutex_unlock(&ar->conf_mutex);
+	return 0;
+
+err_core_stop:
+	ath10k_core_stop(ar);
+
+err_power_down:
+	ath10k_hif_power_down(ar);
+
+err_off:
+	ar->state = ATH10K_STATE_OFF;
+
+err:
 	mutex_unlock(&ar->conf_mutex);
 	return ret;
 }
@@ -2283,19 +2504,15 @@ static void ath10k_stop(struct ieee80211_hw *hw)
 {
 	struct ath10k *ar = hw->priv;
 
+	ath10k_drain_tx(ar);
+
 	mutex_lock(&ar->conf_mutex);
-	if (ar->state == ATH10K_STATE_ON ||
-	    ar->state == ATH10K_STATE_RESTARTED ||
-	    ar->state == ATH10K_STATE_WEDGED)
+	if (ar->state != ATH10K_STATE_OFF) {
 		ath10k_halt(ar);
-
-	ar->state = ATH10K_STATE_OFF;
+		ar->state = ATH10K_STATE_OFF;
+	}
 	mutex_unlock(&ar->conf_mutex);
 
-	ath10k_mgmt_over_wmi_tx_purge(ar);
-
-	cancel_work_sync(&ar->offchan_tx_work);
-	cancel_work_sync(&ar->wmi_mgmt_tx_work);
 	cancel_work_sync(&ar->restart_work);
 }
 
@@ -2309,7 +2526,7 @@ static int ath10k_config_ps(struct ath10k *ar)
 	list_for_each_entry(arvif, &ar->arvifs, list) {
 		ret = ath10k_mac_vif_setup_ps(arvif);
 		if (ret) {
-			ath10k_warn("could not setup powersave (%d)\n", ret);
+			ath10k_warn("failed to setup powersave: %d\n", ret);
 			break;
 		}
 	}
@@ -2343,7 +2560,6 @@ static const char *chandef_get_width(enum nl80211_chan_width width)
 static void ath10k_config_chan(struct ath10k *ar)
 {
 	struct ath10k_vif *arvif;
-	bool monitor_was_enabled;
 	int ret;
 
 	lockdep_assert_held(&ar->conf_mutex);
@@ -2357,10 +2573,8 @@ static void ath10k_config_chan(struct ath10k *ar)
 
 	/* First stop monitor interface. Some FW versions crash if there's a
 	 * lone monitor interface. */
-	monitor_was_enabled = ar->monitor_enabled;
-
-	if (ar->monitor_enabled)
-		ath10k_monitor_stop(ar);
+	if (ar->monitor_started)
+		ath10k_monitor_vdev_stop(ar);
 
 	list_for_each_entry(arvif, &ar->arvifs, list) {
 		if (!arvif->is_started)
@@ -2371,7 +2585,7 @@ static void ath10k_config_chan(struct ath10k *ar)
 
 		ret = ath10k_vdev_stop(arvif);
 		if (ret) {
-			ath10k_warn("could not stop vdev %d (%d)\n",
+			ath10k_warn("failed to stop vdev %d: %d\n",
 				    arvif->vdev_id, ret);
 			continue;
 		}
@@ -2388,7 +2602,7 @@ static void ath10k_config_chan(struct ath10k *ar)
 
 		ret = ath10k_vdev_start(arvif);
 		if (ret) {
-			ath10k_warn("could not start vdev %d (%d)\n",
+			ath10k_warn("failed to start vdev %d: %d\n",
 				    arvif->vdev_id, ret);
 			continue;
 		}
@@ -2399,14 +2613,14 @@ static void ath10k_config_chan(struct ath10k *ar)
 		ret = ath10k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid,
 					 arvif->bssid);
 		if (ret) {
-			ath10k_warn("could not bring vdev up %d (%d)\n",
+			ath10k_warn("failed to bring vdev up %d: %d\n",
 				    arvif->vdev_id, ret);
 			continue;
 		}
 	}
 
-	if (monitor_was_enabled)
-		ath10k_monitor_start(ar, ar->monitor_vdev_id);
+	if (ath10k_monitor_is_enabled(ar))
+		ath10k_monitor_vdev_start(ar, ar->monitor_vdev_id);
 }
 
 static int ath10k_config(struct ieee80211_hw *hw, u32 changed)
@@ -2420,15 +2634,17 @@ static int ath10k_config(struct ieee80211_hw *hw, u32 changed)
 
 	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
 		ath10k_dbg(ATH10K_DBG_MAC,
-			   "mac config channel %d mhz flags 0x%x\n",
+			   "mac config channel %dMHz flags 0x%x radar %d\n",
 			   conf->chandef.chan->center_freq,
-			   conf->chandef.chan->flags);
+			   conf->chandef.chan->flags,
+			   conf->radar_enabled);
 
 		spin_lock_bh(&ar->data_lock);
 		ar->rx_channel = conf->chandef.chan;
 		spin_unlock_bh(&ar->data_lock);
 
-		ath10k_config_radar_detection(ar);
+		ar->radar_enabled = conf->radar_enabled;
+		ath10k_recalc_radar_detection(ar);
 
 		if (!cfg80211_chandef_identical(&ar->chandef, &conf->chandef)) {
 			ar->chandef = conf->chandef;
@@ -2444,14 +2660,14 @@ static int ath10k_config(struct ieee80211_hw *hw, u32 changed)
 		ret = ath10k_wmi_pdev_set_param(ar, param,
 						hw->conf.power_level * 2);
 		if (ret)
-			ath10k_warn("mac failed to set 2g txpower %d (%d)\n",
+			ath10k_warn("failed to set 2g txpower %d: %d\n",
 				    hw->conf.power_level, ret);
 
 		param = ar->wmi.pdev_param->txpower_limit5g;
 		ret = ath10k_wmi_pdev_set_param(ar, param,
 						hw->conf.power_level * 2);
 		if (ret)
-			ath10k_warn("mac failed to set 5g txpower %d (%d)\n",
+			ath10k_warn("failed to set 5g txpower %d: %d\n",
 				    hw->conf.power_level, ret);
 	}
 
@@ -2459,10 +2675,19 @@ static int ath10k_config(struct ieee80211_hw *hw, u32 changed)
 		ath10k_config_ps(ar);
 
 	if (changed & IEEE80211_CONF_CHANGE_MONITOR) {
-		if (conf->flags & IEEE80211_CONF_MONITOR)
-			ret = ath10k_monitor_create(ar);
-		else
-			ret = ath10k_monitor_destroy(ar);
+		if (conf->flags & IEEE80211_CONF_MONITOR && !ar->monitor) {
+			ar->monitor = true;
+			ret = ath10k_monitor_start(ar);
+			if (ret) {
+				ath10k_warn("failed to start monitor (config): %d\n",
+					    ret);
+				ar->monitor = false;
+			}
+		} else if (!(conf->flags & IEEE80211_CONF_MONITOR) &&
+			   ar->monitor) {
+			ar->monitor = false;
+			ath10k_monitor_stop(ar);
+		}
 	}
 
 	mutex_unlock(&ar->conf_mutex);
@@ -2497,12 +2722,6 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 	INIT_WORK(&arvif->wep_key_work, ath10k_tx_wep_key_work);
 	INIT_LIST_HEAD(&arvif->list);
 
-	if ((vif->type == NL80211_IFTYPE_MONITOR) && ar->monitor_present) {
-		ath10k_warn("Only one monitor interface allowed\n");
-		ret = -EBUSY;
-		goto err;
-	}
-
 	bit = ffs(ar->free_vdev_map);
 	if (bit == 0) {
 		ret = -EBUSY;
@@ -2545,7 +2764,7 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 	ret = ath10k_wmi_vdev_create(ar, arvif->vdev_id, arvif->vdev_type,
 				     arvif->vdev_subtype, vif->addr);
 	if (ret) {
-		ath10k_warn("WMI vdev %i create failed: ret %d\n",
+		ath10k_warn("failed to create WMI vdev %i: %d\n",
 			    arvif->vdev_id, ret);
 		goto err;
 	}
@@ -2557,7 +2776,7 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 	ret = ath10k_wmi_vdev_set_param(ar, 0, vdev_param,
 					arvif->def_wep_key_idx);
 	if (ret) {
-		ath10k_warn("Failed to set vdev %i default keyid: %d\n",
+		ath10k_warn("failed to set vdev %i default key id: %d\n",
 			    arvif->vdev_id, ret);
 		goto err_vdev_delete;
 	}
@@ -2567,7 +2786,7 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 					ATH10K_HW_TXRX_NATIVE_WIFI);
 	/* 10.X firmware does not support this VDEV parameter. Do not warn */
 	if (ret && ret != -EOPNOTSUPP) {
-		ath10k_warn("Failed to set vdev %i TX encap: %d\n",
+		ath10k_warn("failed to set vdev %i TX encapsulation: %d\n",
 			    arvif->vdev_id, ret);
 		goto err_vdev_delete;
 	}
@@ -2575,14 +2794,14 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 	if (arvif->vdev_type == WMI_VDEV_TYPE_AP) {
 		ret = ath10k_peer_create(ar, arvif->vdev_id, vif->addr);
 		if (ret) {
-			ath10k_warn("Failed to create vdev %i peer for AP: %d\n",
+			ath10k_warn("failed to create vdev %i peer for AP: %d\n",
 				    arvif->vdev_id, ret);
 			goto err_vdev_delete;
 		}
 
 		ret = ath10k_mac_set_kickout(arvif);
 		if (ret) {
-			ath10k_warn("Failed to set vdev %i kickout parameters: %d\n",
+			ath10k_warn("failed to set vdev %i kickout parameters: %d\n",
 				    arvif->vdev_id, ret);
 			goto err_peer_delete;
 		}
@@ -2594,7 +2813,7 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 		ret = ath10k_wmi_set_sta_ps_param(ar, arvif->vdev_id,
 						  param, value);
 		if (ret) {
-			ath10k_warn("Failed to set vdev %i RX wake policy: %d\n",
+			ath10k_warn("failed to set vdev %i RX wake policy: %d\n",
 				    arvif->vdev_id, ret);
 			goto err_peer_delete;
 		}
@@ -2604,7 +2823,7 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 		ret = ath10k_wmi_set_sta_ps_param(ar, arvif->vdev_id,
 						  param, value);
 		if (ret) {
-			ath10k_warn("Failed to set vdev %i TX wake thresh: %d\n",
+			ath10k_warn("failed to set vdev %i TX wake thresh: %d\n",
 				    arvif->vdev_id, ret);
 			goto err_peer_delete;
 		}
@@ -2614,7 +2833,7 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 		ret = ath10k_wmi_set_sta_ps_param(ar, arvif->vdev_id,
 						  param, value);
 		if (ret) {
-			ath10k_warn("Failed to set vdev %i PSPOLL count: %d\n",
+			ath10k_warn("failed to set vdev %i PSPOLL count: %d\n",
 				    arvif->vdev_id, ret);
 			goto err_peer_delete;
 		}
@@ -2622,21 +2841,18 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 
 	ret = ath10k_mac_set_rts(arvif, ar->hw->wiphy->rts_threshold);
 	if (ret) {
-		ath10k_warn("failed to set rts threshold for vdev %d (%d)\n",
+		ath10k_warn("failed to set rts threshold for vdev %d: %d\n",
 			    arvif->vdev_id, ret);
 		goto err_peer_delete;
 	}
 
 	ret = ath10k_mac_set_frag(arvif, ar->hw->wiphy->frag_threshold);
 	if (ret) {
-		ath10k_warn("failed to set frag threshold for vdev %d (%d)\n",
+		ath10k_warn("failed to set frag threshold for vdev %d: %d\n",
 			    arvif->vdev_id, ret);
 		goto err_peer_delete;
 	}
 
-	if (arvif->vdev_type == WMI_VDEV_TYPE_MONITOR)
-		ar->monitor_present = true;
-
 	mutex_unlock(&ar->conf_mutex);
 	return 0;
 
@@ -2668,6 +2884,9 @@ static void ath10k_remove_interface(struct ieee80211_hw *hw,
 
 	spin_lock_bh(&ar->data_lock);
 	if (arvif->beacon) {
+		dma_unmap_single(arvif->ar->dev,
+				 ATH10K_SKB_CB(arvif->beacon)->paddr,
+				 arvif->beacon->len, DMA_TO_DEVICE);
 		dev_kfree_skb_any(arvif->beacon);
 		arvif->beacon = NULL;
 	}
@@ -2679,7 +2898,7 @@ static void ath10k_remove_interface(struct ieee80211_hw *hw,
 	if (arvif->vdev_type == WMI_VDEV_TYPE_AP) {
 		ret = ath10k_peer_delete(arvif->ar, arvif->vdev_id, vif->addr);
 		if (ret)
-			ath10k_warn("Failed to remove peer for AP vdev %i: %d\n",
+			ath10k_warn("failed to remove peer for AP vdev %i: %d\n",
 				    arvif->vdev_id, ret);
 
 		kfree(arvif->u.ap.noa_data);
@@ -2690,12 +2909,9 @@ static void ath10k_remove_interface(struct ieee80211_hw *hw,
 
 	ret = ath10k_wmi_vdev_delete(ar, arvif->vdev_id);
 	if (ret)
-		ath10k_warn("WMI vdev %i delete failed: %d\n",
+		ath10k_warn("failed to delete WMI vdev %i: %d\n",
 			    arvif->vdev_id, ret);
 
-	if (arvif->vdev_type == WMI_VDEV_TYPE_MONITOR)
-		ar->monitor_present = false;
-
 	ath10k_peer_cleanup(ar, arvif->vdev_id);
 
 	mutex_unlock(&ar->conf_mutex);
@@ -2728,28 +2944,17 @@ static void ath10k_configure_filter(struct ieee80211_hw *hw,
 	*total_flags &= SUPPORTED_FILTERS;
 	ar->filter_flags = *total_flags;
 
-	/* Monitor must not be started if it wasn't created first.
-	 * Promiscuous mode may be started on a non-monitor interface - in
-	 * such case the monitor vdev is not created so starting the
-	 * monitor makes no sense. Since ath10k uses no special RX filters
-	 * (only BSS filter in STA mode) there's no need for any special
-	 * action here. */
-	if ((ar->filter_flags & FIF_PROMISC_IN_BSS) &&
-	    !ar->monitor_enabled && ar->monitor_present) {
-		ath10k_dbg(ATH10K_DBG_MAC, "mac monitor %d start\n",
-			   ar->monitor_vdev_id);
-
-		ret = ath10k_monitor_start(ar, ar->monitor_vdev_id);
-		if (ret)
-			ath10k_warn("Unable to start monitor mode\n");
-	} else if (!(ar->filter_flags & FIF_PROMISC_IN_BSS) &&
-		   ar->monitor_enabled && ar->monitor_present) {
-		ath10k_dbg(ATH10K_DBG_MAC, "mac monitor %d stop\n",
-			   ar->monitor_vdev_id);
-
-		ret = ath10k_monitor_stop(ar);
-		if (ret)
-			ath10k_warn("Unable to stop monitor mode\n");
+	if (ar->filter_flags & FIF_PROMISC_IN_BSS && !ar->promisc) {
+		ar->promisc = true;
+		ret = ath10k_monitor_start(ar);
+		if (ret) {
+			ath10k_warn("failed to start monitor (promisc): %d\n",
+				    ret);
+			ar->promisc = false;
+		}
+	} else if (!(ar->filter_flags & FIF_PROMISC_IN_BSS) && ar->promisc) {
+		ar->promisc = false;
+		ath10k_monitor_stop(ar);
 	}
 
 	mutex_unlock(&ar->conf_mutex);
@@ -2780,7 +2985,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 			   arvif->vdev_id, arvif->beacon_interval);
 
 		if (ret)
-			ath10k_warn("Failed to set beacon interval for vdev %d: %i\n",
+			ath10k_warn("failed to set beacon interval for vdev %d: %i\n",
 				    arvif->vdev_id, ret);
 	}
 
@@ -2793,7 +2998,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 		ret = ath10k_wmi_pdev_set_param(ar, pdev_param,
 						WMI_BEACON_STAGGERED_MODE);
 		if (ret)
-			ath10k_warn("Failed to set beacon mode for vdev %d: %i\n",
+			ath10k_warn("failed to set beacon mode for vdev %d: %i\n",
 				    arvif->vdev_id, ret);
 	}
 
@@ -2808,7 +3013,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 		ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id, vdev_param,
 						arvif->dtim_period);
 		if (ret)
-			ath10k_warn("Failed to set dtim period for vdev %d: %i\n",
+			ath10k_warn("failed to set dtim period for vdev %d: %i\n",
 				    arvif->vdev_id, ret);
 	}
 
@@ -2820,7 +3025,12 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 		arvif->u.ap.hidden_ssid = info->hidden_ssid;
 	}
 
-	if (changed & BSS_CHANGED_BSSID) {
+	/*
+	 * Firmware manages AP self-peer internally so make sure to not create
+	 * it in driver. Otherwise AP self-peer deletion may timeout later.
+	 */
+	if (changed & BSS_CHANGED_BSSID &&
+	    vif->type != NL80211_IFTYPE_AP) {
 		if (!is_zero_ether_addr(info->bssid)) {
 			ath10k_dbg(ATH10K_DBG_MAC,
 				   "mac vdev %d create peer %pM\n",
@@ -2829,7 +3039,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 			ret = ath10k_peer_create(ar, arvif->vdev_id,
 						 info->bssid);
 			if (ret)
-				ath10k_warn("Failed to add peer %pM for vdev %d when changing bssid: %i\n",
+				ath10k_warn("failed to add peer %pM for vdev %d when changing bssid: %i\n",
 					    info->bssid, arvif->vdev_id, ret);
 
 			if (vif->type == NL80211_IFTYPE_STATION) {
@@ -2868,20 +3078,13 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 		ath10k_control_beaconing(arvif, info);
 
 	if (changed & BSS_CHANGED_ERP_CTS_PROT) {
-		u32 cts_prot;
-		if (info->use_cts_prot)
-			cts_prot = 1;
-		else
-			cts_prot = 0;
-
+		arvif->use_cts_prot = info->use_cts_prot;
 		ath10k_dbg(ATH10K_DBG_MAC, "mac vdev %d cts_prot %d\n",
-			   arvif->vdev_id, cts_prot);
+			   arvif->vdev_id, info->use_cts_prot);
 
-		vdev_param = ar->wmi.vdev_param->enable_rtscts;
-		ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id, vdev_param,
-						cts_prot);
+		ret = ath10k_recalc_rtscts_prot(arvif);
 		if (ret)
-			ath10k_warn("Failed to set CTS prot for vdev %d: %d\n",
+			ath10k_warn("failed to recalculate rts/cts prot for vdev %d: %d\n",
 				    arvif->vdev_id, ret);
 	}
 
@@ -2900,7 +3103,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 		ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id, vdev_param,
 						slottime);
 		if (ret)
-			ath10k_warn("Failed to set erp slot for vdev %d: %i\n",
+			ath10k_warn("failed to set erp slot for vdev %d: %i\n",
 				    arvif->vdev_id, ret);
 	}
 
@@ -2919,7 +3122,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 		ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id, vdev_param,
 						preamble);
 		if (ret)
-			ath10k_warn("Failed to set preamble for vdev %d: %i\n",
+			ath10k_warn("failed to set preamble for vdev %d: %i\n",
 				    arvif->vdev_id, ret);
 	}
 
@@ -2990,7 +3193,7 @@ static int ath10k_hw_scan(struct ieee80211_hw *hw,
 
 	ret = ath10k_start_scan(ar, &arg);
 	if (ret) {
-		ath10k_warn("could not start hw scan (%d)\n", ret);
+		ath10k_warn("failed to start hw scan: %d\n", ret);
 		spin_lock_bh(&ar->data_lock);
 		ar->scan.in_progress = false;
 		spin_unlock_bh(&ar->data_lock);
@@ -3010,8 +3213,7 @@ static void ath10k_cancel_hw_scan(struct ieee80211_hw *hw,
 	mutex_lock(&ar->conf_mutex);
 	ret = ath10k_abort_scan(ar);
 	if (ret) {
-		ath10k_warn("couldn't abort scan (%d). forcefully sending scan completion to mac80211\n",
-			    ret);
+		ath10k_warn("failed to abort scan: %d\n", ret);
 		ieee80211_scan_completed(hw, 1 /* aborted */);
 	}
 	mutex_unlock(&ar->conf_mutex);
@@ -3089,7 +3291,7 @@ static int ath10k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 
 	if (!peer) {
 		if (cmd == SET_KEY) {
-			ath10k_warn("cannot install key for non-existent peer %pM\n",
+			ath10k_warn("failed to install key for non-existent peer %pM\n",
 				    peer_addr);
 			ret = -EOPNOTSUPP;
 			goto exit;
@@ -3112,7 +3314,7 @@ static int ath10k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 
 	ret = ath10k_install_key(arvif, key, cmd, peer_addr);
 	if (ret) {
-		ath10k_warn("key installation failed for vdev %i peer %pM: %d\n",
+		ath10k_warn("failed to install key for vdev %i peer %pM: %d\n",
 			    arvif->vdev_id, peer_addr, ret);
 		goto exit;
 	}
@@ -3127,7 +3329,7 @@ static int ath10k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		peer->keys[key->keyidx] = NULL;
 	else if (peer == NULL)
 		/* impossible unless FW goes crazy */
-		ath10k_warn("peer %pM disappeared!\n", peer_addr);
+		ath10k_warn("Peer %pM disappeared!\n", peer_addr);
 	spin_unlock_bh(&ar->data_lock);
 
 exit:
@@ -3195,6 +3397,16 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk)
 				    sta->addr, smps, err);
 	}
 
+	if (changed & IEEE80211_RC_SUPP_RATES_CHANGED) {
+		ath10k_dbg(ATH10K_DBG_MAC, "mac update sta %pM supp rates\n",
+			   sta->addr);
+
+		err = ath10k_station_assoc(ar, arvif, sta, true);
+		if (err)
+			ath10k_warn("failed to reassociate station: %pM\n",
+				    sta->addr);
+	}
+
 	mutex_unlock(&ar->conf_mutex);
 }
 
@@ -3236,7 +3448,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 			max_num_peers = TARGET_NUM_PEERS;
 
 		if (ar->num_peers >= max_num_peers) {
-			ath10k_warn("Number of peers exceeded: peers number %d (max peers %d)\n",
+			ath10k_warn("number of peers exceeded: peers number %d (max peers %d)\n",
 				    ar->num_peers, max_num_peers);
 			ret = -ENOBUFS;
 			goto exit;
@@ -3248,7 +3460,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 
 		ret = ath10k_peer_create(ar, arvif->vdev_id, sta->addr);
 		if (ret)
-			ath10k_warn("Failed to add peer %pM for vdev %d when adding a new sta: %i\n",
+			ath10k_warn("failed to add peer %pM for vdev %d when adding a new sta: %i\n",
 				    sta->addr, arvif->vdev_id, ret);
 	} else if ((old_state == IEEE80211_STA_NONE &&
 		    new_state == IEEE80211_STA_NOTEXIST)) {
@@ -3260,7 +3472,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 			   arvif->vdev_id, sta->addr);
 		ret = ath10k_peer_delete(ar, arvif->vdev_id, sta->addr);
 		if (ret)
-			ath10k_warn("Failed to delete peer %pM for vdev %d: %i\n",
+			ath10k_warn("failed to delete peer %pM for vdev %d: %i\n",
 				    sta->addr, arvif->vdev_id, ret);
 
 		if (vif->type == NL80211_IFTYPE_STATION)
@@ -3275,9 +3487,9 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 		ath10k_dbg(ATH10K_DBG_MAC, "mac sta %pM associated\n",
 			   sta->addr);
 
-		ret = ath10k_station_assoc(ar, arvif, sta);
+		ret = ath10k_station_assoc(ar, arvif, sta, false);
 		if (ret)
-			ath10k_warn("Failed to associate station %pM for vdev %i: %i\n",
+			ath10k_warn("failed to associate station %pM for vdev %i: %i\n",
 				    sta->addr, arvif->vdev_id, ret);
 	} else if (old_state == IEEE80211_STA_ASSOC &&
 		   new_state == IEEE80211_STA_AUTH &&
@@ -3291,7 +3503,7 @@ static int ath10k_sta_state(struct ieee80211_hw *hw,
 
 		ret = ath10k_station_disassoc(ar, arvif, sta);
 		if (ret)
-			ath10k_warn("Failed to disassociate station: %pM vdev %i ret %i\n",
+			ath10k_warn("failed to disassociate station: %pM vdev %i: %i\n",
 				    sta->addr, arvif->vdev_id, ret);
 	}
 exit:
@@ -3339,7 +3551,7 @@ static int ath10k_conf_tx_uapsd(struct ath10k *ar, struct ieee80211_vif *vif,
 					  WMI_STA_PS_PARAM_UAPSD,
 					  arvif->u.sta.uapsd);
 	if (ret) {
-		ath10k_warn("could not set uapsd params %d\n", ret);
+		ath10k_warn("failed to set uapsd params: %d\n", ret);
 		goto exit;
 	}
 
@@ -3352,7 +3564,7 @@ static int ath10k_conf_tx_uapsd(struct ath10k *ar, struct ieee80211_vif *vif,
 					  WMI_STA_PS_PARAM_RX_WAKE_POLICY,
 					  value);
 	if (ret)
-		ath10k_warn("could not set rx wake param %d\n", ret);
+		ath10k_warn("failed to set rx wake param: %d\n", ret);
 
 exit:
 	return ret;
@@ -3402,13 +3614,13 @@ static int ath10k_conf_tx(struct ieee80211_hw *hw,
 	/* FIXME: FW accepts wmm params per hw, not per vif */
 	ret = ath10k_wmi_pdev_set_wmm_params(ar, &ar->wmm_params);
 	if (ret) {
-		ath10k_warn("could not set wmm params %d\n", ret);
+		ath10k_warn("failed to set wmm params: %d\n", ret);
 		goto exit;
 	}
 
 	ret = ath10k_conf_tx_uapsd(ar, vif, ac, params->uapsd);
 	if (ret)
-		ath10k_warn("could not set sta uapsd %d\n", ret);
+		ath10k_warn("failed to set sta uapsd: %d\n", ret);
 
 exit:
 	mutex_unlock(&ar->conf_mutex);
@@ -3461,7 +3673,7 @@ static int ath10k_remain_on_channel(struct ieee80211_hw *hw,
 
 	ret = ath10k_start_scan(ar, &arg);
 	if (ret) {
-		ath10k_warn("could not start roc scan (%d)\n", ret);
+		ath10k_warn("failed to start roc scan: %d\n", ret);
 		spin_lock_bh(&ar->data_lock);
 		ar->scan.in_progress = false;
 		spin_unlock_bh(&ar->data_lock);
@@ -3470,7 +3682,7 @@ static int ath10k_remain_on_channel(struct ieee80211_hw *hw,
 
 	ret = wait_for_completion_timeout(&ar->scan.on_channel, 3*HZ);
 	if (ret == 0) {
-		ath10k_warn("could not switch to channel for roc scan\n");
+		ath10k_warn("failed to switch to channel for roc scan\n");
 		ath10k_abort_scan(ar);
 		ret = -ETIMEDOUT;
 		goto exit;
@@ -3511,7 +3723,7 @@ static int ath10k_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 
 		ret = ath10k_mac_set_rts(arvif, value);
 		if (ret) {
-			ath10k_warn("could not set rts threshold for vdev %d (%d)\n",
+			ath10k_warn("failed to set rts threshold for vdev %d: %d\n",
 				    arvif->vdev_id, ret);
 			break;
 		}
@@ -3534,7 +3746,7 @@ static int ath10k_set_frag_threshold(struct ieee80211_hw *hw, u32 value)
 
 		ret = ath10k_mac_set_rts(arvif, value);
 		if (ret) {
-			ath10k_warn("could not set fragmentation threshold for vdev %d (%d)\n",
+			ath10k_warn("failed to set fragmentation threshold for vdev %d: %d\n",
 				    arvif->vdev_id, ret);
 			break;
 		}
@@ -3544,7 +3756,8 @@ static int ath10k_set_frag_threshold(struct ieee80211_hw *hw, u32 value)
 	return ret;
 }
 
-static void ath10k_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void ath10k_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 u32 queues, bool drop)
 {
 	struct ath10k *ar = hw->priv;
 	bool skip;
@@ -3573,7 +3786,7 @@ static void ath10k_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
 		}), ATH10K_FLUSH_TIMEOUT_HZ);
 
 	if (ret <= 0 || skip)
-		ath10k_warn("tx not flushed (skip %i ar-state %i): %i\n",
+		ath10k_warn("failed to flush transmit queue (skip %i ar-state %i): %i\n",
 			    skip, ar->state, ret);
 
 skip:
@@ -3608,7 +3821,7 @@ static int ath10k_suspend(struct ieee80211_hw *hw,
 
 	ret = ath10k_hif_suspend(ar);
 	if (ret) {
-		ath10k_warn("could not suspend hif (%d)\n", ret);
+		ath10k_warn("failed to suspend hif: %d\n", ret);
 		goto resume;
 	}
 
@@ -3617,7 +3830,7 @@ static int ath10k_suspend(struct ieee80211_hw *hw,
 resume:
 	ret = ath10k_wmi_pdev_resume_target(ar);
 	if (ret)
-		ath10k_warn("could not resume target (%d)\n", ret);
+		ath10k_warn("failed to resume target: %d\n", ret);
 
 	ret = 1;
 exit:
@@ -3634,14 +3847,14 @@ static int ath10k_resume(struct ieee80211_hw *hw)
 
 	ret = ath10k_hif_resume(ar);
 	if (ret) {
-		ath10k_warn("could not resume hif (%d)\n", ret);
+		ath10k_warn("failed to resume hif: %d\n", ret);
 		ret = 1;
 		goto exit;
 	}
 
 	ret = ath10k_wmi_pdev_resume_target(ar);
 	if (ret) {
-		ath10k_warn("could not resume target (%d)\n", ret);
+		ath10k_warn("failed to resume target: %d\n", ret);
 		ret = 1;
 		goto exit;
 	}
@@ -3964,7 +4177,7 @@ static int ath10k_set_fixed_rate_param(struct ath10k_vif *arvif,
 	ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id,
 					vdev_param, fixed_rate);
 	if (ret) {
-		ath10k_warn("Could not set fixed_rate param 0x%02x: %d\n",
+		ath10k_warn("failed to set fixed rate param 0x%02x: %d\n",
 			    fixed_rate, ret);
 		ret = -EINVAL;
 		goto exit;
@@ -3977,7 +4190,7 @@ static int ath10k_set_fixed_rate_param(struct ath10k_vif *arvif,
 					vdev_param, fixed_nss);
 
 	if (ret) {
-		ath10k_warn("Could not set fixed_nss param %d: %d\n",
+		ath10k_warn("failed to set fixed nss param %d: %d\n",
 			    fixed_nss, ret);
 		ret = -EINVAL;
 		goto exit;
@@ -3990,7 +4203,7 @@ static int ath10k_set_fixed_rate_param(struct ath10k_vif *arvif,
 					force_sgi);
 
 	if (ret) {
-		ath10k_warn("Could not set sgi param %d: %d\n",
+		ath10k_warn("failed to set sgi param %d: %d\n",
 			    force_sgi, ret);
 		ret = -EINVAL;
 		goto exit;
@@ -4026,7 +4239,7 @@ static int ath10k_set_bitrate_mask(struct ieee80211_hw *hw,
 	}
 
 	if (fixed_rate == WMI_FIXED_RATE_NONE && force_sgi) {
-		ath10k_warn("Could not force SGI usage for default rate settings\n");
+		ath10k_warn("failed to force SGI usage for default rate settings\n");
 		return -EINVAL;
 	}
 
@@ -4034,14 +4247,6 @@ static int ath10k_set_bitrate_mask(struct ieee80211_hw *hw,
 					   fixed_nss, force_sgi);
 }
 
-static void ath10k_channel_switch_beacon(struct ieee80211_hw *hw,
-					 struct ieee80211_vif *vif,
-					 struct cfg80211_chan_def *chandef)
-{
-	/* there's no need to do anything here. vif->csa_active is enough */
-	return;
-}
-
 static void ath10k_sta_rc_update(struct ieee80211_hw *hw,
 				 struct ieee80211_vif *vif,
 				 struct ieee80211_sta *sta,
@@ -4072,8 +4277,8 @@ static void ath10k_sta_rc_update(struct ieee80211_hw *hw,
 			bw = WMI_PEER_CHWIDTH_80MHZ;
 			break;
 		case IEEE80211_STA_RX_BW_160:
-			ath10k_warn("mac sta rc update for %pM: invalid bw %d\n",
-				    sta->addr, sta->bandwidth);
+			ath10k_warn("Invalid bandwith %d in rc update for %pM\n",
+				    sta->bandwidth, sta->addr);
 			bw = WMI_PEER_CHWIDTH_20MHZ;
 			break;
 		}
@@ -4099,8 +4304,8 @@ static void ath10k_sta_rc_update(struct ieee80211_hw *hw,
 			smps = WMI_PEER_SMPS_DYNAMIC;
 			break;
 		case IEEE80211_SMPS_NUM_MODES:
-			ath10k_warn("mac sta rc update for %pM: invalid smps: %d\n",
-				    sta->addr, sta->smps_mode);
+			ath10k_warn("Invalid smps %d in sta rc update for %pM\n",
+				    sta->smps_mode, sta->addr);
 			smps = WMI_PEER_SMPS_PS_NONE;
 			break;
 		}
@@ -4108,15 +4313,6 @@ static void ath10k_sta_rc_update(struct ieee80211_hw *hw,
 		arsta->smps = smps;
 	}
 
-	if (changed & IEEE80211_RC_SUPP_RATES_CHANGED) {
-		/* FIXME: Not implemented. Probably the only way to do it would
-		 * be to re-assoc the peer. */
-		changed &= ~IEEE80211_RC_SUPP_RATES_CHANGED;
-		ath10k_dbg(ATH10K_DBG_MAC,
-			   "mac sta rc update for %pM: changing supported rates not implemented\n",
-			   sta->addr);
-	}
-
 	arsta->changed |= changed;
 
 	spin_unlock_bh(&ar->data_lock);
@@ -4154,10 +4350,11 @@ static const struct ieee80211_ops ath10k_ops = {
 	.set_frag_threshold		= ath10k_set_frag_threshold,
 	.flush				= ath10k_flush,
 	.tx_last_beacon			= ath10k_tx_last_beacon,
+	.set_antenna			= ath10k_set_antenna,
+	.get_antenna			= ath10k_get_antenna,
 	.restart_complete		= ath10k_restart_complete,
 	.get_survey			= ath10k_get_survey,
 	.set_bitrate_mask		= ath10k_set_bitrate_mask,
-	.channel_switch_beacon		= ath10k_channel_switch_beacon,
 	.sta_rc_update			= ath10k_sta_rc_update,
 	.get_tsf			= ath10k_get_tsf,
 #ifdef CONFIG_PM
@@ -4503,6 +4700,18 @@ int ath10k_mac_register(struct ath10k *ar)
 		BIT(NL80211_IFTYPE_ADHOC) |
 		BIT(NL80211_IFTYPE_AP);
 
+	if (test_bit(ATH10K_FW_FEATURE_WMI_10X, ar->fw_features)) {
+		/* TODO:  Have to deal with 2x2 chips if/when the come out. */
+		ar->supp_tx_chainmask = TARGET_10X_TX_CHAIN_MASK;
+		ar->supp_rx_chainmask = TARGET_10X_RX_CHAIN_MASK;
+	} else {
+		ar->supp_tx_chainmask = TARGET_TX_CHAIN_MASK;
+		ar->supp_rx_chainmask = TARGET_RX_CHAIN_MASK;
+	}
+
+	ar->hw->wiphy->available_antennas_rx = ar->supp_rx_chainmask;
+	ar->hw->wiphy->available_antennas_tx = ar->supp_tx_chainmask;
+
 	if (!test_bit(ATH10K_FW_FEATURE_NO_P2P, ar->fw_features))
 		ar->hw->wiphy->interface_modes |=
 			BIT(NL80211_IFTYPE_P2P_CLIENT) |
@@ -4516,7 +4725,6 @@ int ath10k_mac_register(struct ath10k *ar)
 			IEEE80211_HW_REPORTS_TX_ACK_STATUS |
 			IEEE80211_HW_HAS_RATE_CONTROL |
 			IEEE80211_HW_SUPPORTS_STATIC_SMPS |
-			IEEE80211_HW_WANT_MONITOR_VIF |
 			IEEE80211_HW_AP_LINK_PS |
 			IEEE80211_HW_SPECTRUM_MGMT;
 
@@ -4570,19 +4778,19 @@ int ath10k_mac_register(struct ath10k *ar)
 							     NL80211_DFS_UNSET);
 
 		if (!ar->dfs_detector)
-			ath10k_warn("dfs pattern detector init failed\n");
+			ath10k_warn("failed to initialise DFS pattern detector\n");
 	}
 
 	ret = ath_regd_init(&ar->ath_common.regulatory, ar->hw->wiphy,
 			    ath10k_reg_notifier);
 	if (ret) {
-		ath10k_err("Regulatory initialization failed: %i\n", ret);
+		ath10k_err("failed to initialise regulatory: %i\n", ret);
 		goto err_free;
 	}
 
 	ret = ieee80211_register_hw(ar->hw);
 	if (ret) {
-		ath10k_err("ieee80211 registration failed: %d\n", ret);
+		ath10k_err("failed to register ieee80211: %d\n", ret);
 		goto err_free;
 	}
 
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 9d242d801d9..d0004d59c97 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -39,15 +39,28 @@ enum ath10k_pci_irq_mode {
 	ATH10K_PCI_IRQ_MSI = 2,
 };
 
-static unsigned int ath10k_target_ps;
+enum ath10k_pci_reset_mode {
+	ATH10K_PCI_RESET_AUTO = 0,
+	ATH10K_PCI_RESET_WARM_ONLY = 1,
+};
+
+static unsigned int ath10k_pci_target_ps;
 static unsigned int ath10k_pci_irq_mode = ATH10K_PCI_IRQ_AUTO;
+static unsigned int ath10k_pci_reset_mode = ATH10K_PCI_RESET_AUTO;
 
-module_param(ath10k_target_ps, uint, 0644);
-MODULE_PARM_DESC(ath10k_target_ps, "Enable ath10k Target (SoC) PS option");
+module_param_named(target_ps, ath10k_pci_target_ps, uint, 0644);
+MODULE_PARM_DESC(target_ps, "Enable ath10k Target (SoC) PS option");
 
 module_param_named(irq_mode, ath10k_pci_irq_mode, uint, 0644);
 MODULE_PARM_DESC(irq_mode, "0: auto, 1: legacy, 2: msi (default: 0)");
 
+module_param_named(reset_mode, ath10k_pci_reset_mode, uint, 0644);
+MODULE_PARM_DESC(reset_mode, "0: auto, 1: warm only (default: 0)");
+
+/* how long wait to wait for target to initialise, in ms */
+#define ATH10K_PCI_TARGET_WAIT 3000
+#define ATH10K_PCI_NUM_WARM_RESET_ATTEMPTS 3
+
 #define QCA988X_2_0_DEVICE_ID	(0x003c)
 
 static DEFINE_PCI_DEVICE_TABLE(ath10k_pci_id_table) = {
@@ -346,9 +359,10 @@ static int ath10k_pci_diag_read_mem(struct ath10k *ar, u32 address, void *data,
 	 *   2) Buffer in DMA-able space
 	 */
 	orig_nbytes = nbytes;
-	data_buf = (unsigned char *)pci_alloc_consistent(ar_pci->pdev,
-							 orig_nbytes,
-							 &ce_data_base);
+	data_buf = (unsigned char *)dma_alloc_coherent(ar->dev,
+						       orig_nbytes,
+						       &ce_data_base,
+						       GFP_ATOMIC);
 
 	if (!data_buf) {
 		ret = -ENOMEM;
@@ -442,12 +456,12 @@ done:
 				__le32_to_cpu(((__le32 *)data_buf)[i]);
 		}
 	} else
-		ath10k_dbg(ATH10K_DBG_PCI, "%s failure (0x%x)\n",
-			   __func__, address);
+		ath10k_warn("failed to read diag value at 0x%x: %d\n",
+			    address, ret);
 
 	if (data_buf)
-		pci_free_consistent(ar_pci->pdev, orig_nbytes,
-				    data_buf, ce_data_base);
+		dma_free_coherent(ar->dev, orig_nbytes, data_buf,
+				  ce_data_base);
 
 	return ret;
 }
@@ -490,9 +504,10 @@ static int ath10k_pci_diag_write_mem(struct ath10k *ar, u32 address,
 	 *   2) Buffer in DMA-able space
 	 */
 	orig_nbytes = nbytes;
-	data_buf = (unsigned char *)pci_alloc_consistent(ar_pci->pdev,
-							 orig_nbytes,
-							 &ce_data_base);
+	data_buf = (unsigned char *)dma_alloc_coherent(ar->dev,
+						       orig_nbytes,
+						       &ce_data_base,
+						       GFP_ATOMIC);
 	if (!data_buf) {
 		ret = -ENOMEM;
 		goto done;
@@ -588,13 +603,13 @@ static int ath10k_pci_diag_write_mem(struct ath10k *ar, u32 address,
 
 done:
 	if (data_buf) {
-		pci_free_consistent(ar_pci->pdev, orig_nbytes, data_buf,
-				    ce_data_base);
+		dma_free_coherent(ar->dev, orig_nbytes, data_buf,
+				  ce_data_base);
 	}
 
 	if (ret != 0)
-		ath10k_dbg(ATH10K_DBG_PCI, "%s failure (0x%x)\n", __func__,
-			   address);
+		ath10k_warn("failed to write diag value at 0x%x: %d\n",
+			    address, ret);
 
 	return ret;
 }
@@ -747,17 +762,21 @@ static int ath10k_pci_hif_tx_sg(struct ath10k *ar, u8 pipe_id,
 	struct ath10k_pci_pipe *pci_pipe = &ar_pci->pipe_info[pipe_id];
 	struct ath10k_ce_pipe *ce_pipe = pci_pipe->ce_hdl;
 	struct ath10k_ce_ring *src_ring = ce_pipe->src_ring;
-	unsigned int nentries_mask = src_ring->nentries_mask;
-	unsigned int sw_index = src_ring->sw_index;
-	unsigned int write_index = src_ring->write_index;
-	int err, i;
+	unsigned int nentries_mask;
+	unsigned int sw_index;
+	unsigned int write_index;
+	int err, i = 0;
 
 	spin_lock_bh(&ar_pci->ce_lock);
 
+	nentries_mask = src_ring->nentries_mask;
+	sw_index = src_ring->sw_index;
+	write_index = src_ring->write_index;
+
 	if (unlikely(CE_RING_DELTA(nentries_mask,
 				   write_index, sw_index - 1) < n_items)) {
 		err = -ENOBUFS;
-		goto unlock;
+		goto err;
 	}
 
 	for (i = 0; i < n_items - 1; i++) {
@@ -774,7 +793,7 @@ static int ath10k_pci_hif_tx_sg(struct ath10k *ar, u8 pipe_id,
 					    items[i].transfer_id,
 					    CE_SEND_FLAG_GATHER);
 		if (err)
-			goto unlock;
+			goto err;
 	}
 
 	/* `i` is equal to `n_items -1` after for() */
@@ -792,10 +811,15 @@ static int ath10k_pci_hif_tx_sg(struct ath10k *ar, u8 pipe_id,
 				    items[i].transfer_id,
 				    0);
 	if (err)
-		goto unlock;
+		goto err;
+
+	spin_unlock_bh(&ar_pci->ce_lock);
+	return 0;
+
+err:
+	for (; i > 0; i--)
+		__ath10k_ce_send_revert(ce_pipe);
 
-	err = 0;
-unlock:
 	spin_unlock_bh(&ar_pci->ce_lock);
 	return err;
 }
@@ -803,6 +827,9 @@ unlock:
 static u16 ath10k_pci_hif_get_free_queue_number(struct ath10k *ar, u8 pipe)
 {
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+
+	ath10k_dbg(ATH10K_DBG_PCI, "pci hif get free queue number\n");
+
 	return ath10k_ce_num_free_src_entries(ar_pci->pipe_info[pipe].ce_hdl);
 }
 
@@ -854,6 +881,8 @@ static void ath10k_pci_hif_dump_area(struct ath10k *ar)
 static void ath10k_pci_hif_send_complete_check(struct ath10k *ar, u8 pipe,
 					       int force)
 {
+	ath10k_dbg(ATH10K_DBG_PCI, "pci hif send complete check\n");
+
 	if (!force) {
 		int resources;
 		/*
@@ -880,7 +909,7 @@ static void ath10k_pci_hif_set_callbacks(struct ath10k *ar,
 {
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 
-	ath10k_dbg(ATH10K_DBG_PCI, "%s\n", __func__);
+	ath10k_dbg(ATH10K_DBG_PCI, "pci hif set callbacks\n");
 
 	memcpy(&ar_pci->msg_callbacks_current, callbacks,
 	       sizeof(ar_pci->msg_callbacks_current));
@@ -938,6 +967,8 @@ static int ath10k_pci_hif_map_service_to_pipe(struct ath10k *ar,
 {
 	int ret = 0;
 
+	ath10k_dbg(ATH10K_DBG_PCI, "pci hif map service\n");
+
 	/* polling for received messages not supported */
 	*dl_is_polled = 0;
 
@@ -997,6 +1028,8 @@ static void ath10k_pci_hif_get_default_pipe(struct ath10k *ar,
 {
 	int ul_is_polled, dl_is_polled;
 
+	ath10k_dbg(ATH10K_DBG_PCI, "pci hif get default pipe\n");
+
 	(void)ath10k_pci_hif_map_service_to_pipe(ar,
 						 ATH10K_HTC_SVC_ID_RSVD_CTRL,
 						 ul_pipe,
@@ -1098,6 +1131,8 @@ static int ath10k_pci_hif_start(struct ath10k *ar)
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 	int ret, ret_early;
 
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot hif start\n");
+
 	ath10k_pci_free_early_irq(ar);
 	ath10k_pci_kill_tasklet(ar);
 
@@ -1233,18 +1268,10 @@ static void ath10k_pci_buffer_cleanup(struct ath10k *ar)
 
 static void ath10k_pci_ce_deinit(struct ath10k *ar)
 {
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
-	struct ath10k_pci_pipe *pipe_info;
-	int pipe_num;
+	int i;
 
-	for (pipe_num = 0; pipe_num < CE_COUNT; pipe_num++) {
-		pipe_info = &ar_pci->pipe_info[pipe_num];
-		if (pipe_info->ce_hdl) {
-			ath10k_ce_deinit(pipe_info->ce_hdl);
-			pipe_info->ce_hdl = NULL;
-			pipe_info->buf_sz = 0;
-		}
-	}
+	for (i = 0; i < CE_COUNT; i++)
+		ath10k_ce_deinit_pipe(ar, i);
 }
 
 static void ath10k_pci_hif_stop(struct ath10k *ar)
@@ -1252,7 +1279,10 @@ static void ath10k_pci_hif_stop(struct ath10k *ar)
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 	int ret;
 
-	ath10k_dbg(ATH10K_DBG_PCI, "%s\n", __func__);
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot hif stop\n");
+
+	if (WARN_ON(!ar_pci->started))
+		return;
 
 	ret = ath10k_ce_disable_interrupts(ar);
 	if (ret)
@@ -1697,30 +1727,49 @@ static int ath10k_pci_init_config(struct ath10k *ar)
 	return 0;
 }
 
+static int ath10k_pci_alloc_ce(struct ath10k *ar)
+{
+	int i, ret;
+
+	for (i = 0; i < CE_COUNT; i++) {
+		ret = ath10k_ce_alloc_pipe(ar, i, &host_ce_config_wlan[i]);
+		if (ret) {
+			ath10k_err("failed to allocate copy engine pipe %d: %d\n",
+				   i, ret);
+			return ret;
+		}
+	}
 
+	return 0;
+}
+
+static void ath10k_pci_free_ce(struct ath10k *ar)
+{
+	int i;
+
+	for (i = 0; i < CE_COUNT; i++)
+		ath10k_ce_free_pipe(ar, i);
+}
 
 static int ath10k_pci_ce_init(struct ath10k *ar)
 {
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 	struct ath10k_pci_pipe *pipe_info;
 	const struct ce_attr *attr;
-	int pipe_num;
+	int pipe_num, ret;
 
 	for (pipe_num = 0; pipe_num < CE_COUNT; pipe_num++) {
 		pipe_info = &ar_pci->pipe_info[pipe_num];
+		pipe_info->ce_hdl = &ar_pci->ce_states[pipe_num];
 		pipe_info->pipe_num = pipe_num;
 		pipe_info->hif_ce_state = ar;
 		attr = &host_ce_config_wlan[pipe_num];
 
-		pipe_info->ce_hdl = ath10k_ce_init(ar, pipe_num, attr);
-		if (pipe_info->ce_hdl == NULL) {
-			ath10k_err("failed to initialize CE for pipe: %d\n",
-				   pipe_num);
-
-			/* It is safe to call it here. It checks if ce_hdl is
-			 * valid for each pipe */
-			ath10k_pci_ce_deinit(ar);
-			return -1;
+		ret = ath10k_ce_init_pipe(ar, pipe_num, attr);
+		if (ret) {
+			ath10k_err("failed to initialize copy engine pipe %d: %d\n",
+				   pipe_num, ret);
+			return ret;
 		}
 
 		if (pipe_num == CE_COUNT - 1) {
@@ -1741,16 +1790,15 @@ static int ath10k_pci_ce_init(struct ath10k *ar)
 static void ath10k_pci_fw_interrupt_handler(struct ath10k *ar)
 {
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
-	u32 fw_indicator_address, fw_indicator;
+	u32 fw_indicator;
 
 	ath10k_pci_wake(ar);
 
-	fw_indicator_address = ar_pci->fw_indicator_address;
-	fw_indicator = ath10k_pci_read32(ar, fw_indicator_address);
+	fw_indicator = ath10k_pci_read32(ar, FW_INDICATOR_ADDRESS);
 
 	if (fw_indicator & FW_IND_EVENT_PENDING) {
 		/* ACK: clear Target-side pending event */
-		ath10k_pci_write32(ar, fw_indicator_address,
+		ath10k_pci_write32(ar, FW_INDICATOR_ADDRESS,
 				   fw_indicator & ~FW_IND_EVENT_PENDING);
 
 		if (ar_pci->started) {
@@ -1767,13 +1815,32 @@ static void ath10k_pci_fw_interrupt_handler(struct ath10k *ar)
 	ath10k_pci_sleep(ar);
 }
 
+/* this function effectively clears target memory controller assert line */
+static void ath10k_pci_warm_reset_si0(struct ath10k *ar)
+{
+	u32 val;
+
+	val = ath10k_pci_soc_read32(ar, SOC_RESET_CONTROL_ADDRESS);
+	ath10k_pci_soc_write32(ar, SOC_RESET_CONTROL_ADDRESS,
+			       val | SOC_RESET_CONTROL_SI0_RST_MASK);
+	val = ath10k_pci_soc_read32(ar, SOC_RESET_CONTROL_ADDRESS);
+
+	msleep(10);
+
+	val = ath10k_pci_soc_read32(ar, SOC_RESET_CONTROL_ADDRESS);
+	ath10k_pci_soc_write32(ar, SOC_RESET_CONTROL_ADDRESS,
+			       val & ~SOC_RESET_CONTROL_SI0_RST_MASK);
+	val = ath10k_pci_soc_read32(ar, SOC_RESET_CONTROL_ADDRESS);
+
+	msleep(10);
+}
+
 static int ath10k_pci_warm_reset(struct ath10k *ar)
 {
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 	int ret = 0;
 	u32 val;
 
-	ath10k_dbg(ATH10K_DBG_BOOT, "boot performing warm chip reset\n");
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot warm reset\n");
 
 	ret = ath10k_do_pci_wake(ar);
 	if (ret) {
@@ -1801,7 +1868,7 @@ static int ath10k_pci_warm_reset(struct ath10k *ar)
 	msleep(100);
 
 	/* clear fw indicator */
-	ath10k_pci_write32(ar, ar_pci->fw_indicator_address, 0);
+	ath10k_pci_write32(ar, FW_INDICATOR_ADDRESS, 0);
 
 	/* clear target LF timer interrupts */
 	val = ath10k_pci_read32(ar, RTC_SOC_BASE_ADDRESS +
@@ -1826,6 +1893,8 @@ static int ath10k_pci_warm_reset(struct ath10k *ar)
 				SOC_RESET_CONTROL_ADDRESS);
 	msleep(10);
 
+	ath10k_pci_warm_reset_si0(ar);
+
 	/* debug */
 	val = ath10k_pci_read32(ar, SOC_CORE_BASE_ADDRESS +
 				PCIE_INTR_CAUSE_ADDRESS);
@@ -1934,7 +2003,9 @@ static int __ath10k_pci_hif_power_up(struct ath10k *ar, bool cold_reset)
 		irq_mode = "legacy";
 
 	if (!test_bit(ATH10K_FLAG_FIRST_BOOT_DONE, &ar->dev_flags))
-		ath10k_info("pci irq %s\n", irq_mode);
+		ath10k_info("pci irq %s irq_mode %d reset_mode %d\n",
+			    irq_mode, ath10k_pci_irq_mode,
+			    ath10k_pci_reset_mode);
 
 	return 0;
 
@@ -1952,23 +2023,52 @@ err:
 	return ret;
 }
 
+static int ath10k_pci_hif_power_up_warm(struct ath10k *ar)
+{
+	int i, ret;
+
+	/*
+	 * Sometime warm reset succeeds after retries.
+	 *
+	 * FIXME: It might be possible to tune ath10k_pci_warm_reset() to work
+	 * at first try.
+	 */
+	for (i = 0; i < ATH10K_PCI_NUM_WARM_RESET_ATTEMPTS; i++) {
+		ret = __ath10k_pci_hif_power_up(ar, false);
+		if (ret == 0)
+			break;
+
+		ath10k_warn("failed to warm reset (attempt %d out of %d): %d\n",
+			    i + 1, ATH10K_PCI_NUM_WARM_RESET_ATTEMPTS, ret);
+	}
+
+	return ret;
+}
+
 static int ath10k_pci_hif_power_up(struct ath10k *ar)
 {
 	int ret;
 
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot hif power up\n");
+
 	/*
 	 * Hardware CUS232 version 2 has some issues with cold reset and the
 	 * preferred (and safer) way to perform a device reset is through a
 	 * warm reset.
 	 *
-	 * Warm reset doesn't always work though (notably after a firmware
-	 * crash) so fall back to cold reset if necessary.
+	 * Warm reset doesn't always work though so fall back to cold reset may
+	 * be necessary.
 	 */
-	ret = __ath10k_pci_hif_power_up(ar, false);
+	ret = ath10k_pci_hif_power_up_warm(ar);
 	if (ret) {
-		ath10k_warn("failed to power up target using warm reset (%d), trying cold reset\n",
+		ath10k_warn("failed to power up target using warm reset: %d\n",
 			    ret);
 
+		if (ath10k_pci_reset_mode == ATH10K_PCI_RESET_WARM_ONLY)
+			return ret;
+
+		ath10k_warn("trying cold reset\n");
+
 		ret = __ath10k_pci_hif_power_up(ar, true);
 		if (ret) {
 			ath10k_err("failed to power up target using cold reset too (%d)\n",
@@ -1984,12 +2084,14 @@ static void ath10k_pci_hif_power_down(struct ath10k *ar)
 {
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot hif power down\n");
+
 	ath10k_pci_free_early_irq(ar);
 	ath10k_pci_kill_tasklet(ar);
 	ath10k_pci_deinit_irq(ar);
+	ath10k_pci_ce_deinit(ar);
 	ath10k_pci_warm_reset(ar);
 
-	ath10k_pci_ce_deinit(ar);
 	if (!test_bit(ATH10K_PCI_FEATURE_SOC_POWER_SAVE, ar_pci->features))
 		ath10k_do_pci_sleep(ar);
 }
@@ -2137,7 +2239,6 @@ static irqreturn_t ath10k_pci_interrupt_handler(int irq, void *arg)
 static void ath10k_pci_early_irq_tasklet(unsigned long data)
 {
 	struct ath10k *ar = (struct ath10k *)data;
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 	u32 fw_ind;
 	int ret;
 
@@ -2148,14 +2249,11 @@ static void ath10k_pci_early_irq_tasklet(unsigned long data)
 		return;
 	}
 
-	fw_ind = ath10k_pci_read32(ar, ar_pci->fw_indicator_address);
+	fw_ind = ath10k_pci_read32(ar, FW_INDICATOR_ADDRESS);
 	if (fw_ind & FW_IND_EVENT_PENDING) {
-		ath10k_pci_write32(ar, ar_pci->fw_indicator_address,
+		ath10k_pci_write32(ar, FW_INDICATOR_ADDRESS,
 				   fw_ind & ~FW_IND_EVENT_PENDING);
-
-		/* Some structures are unavailable during early boot or at
-		 * driver teardown so just print that the device has crashed. */
-		ath10k_warn("device crashed - no diagnostics available\n");
+		ath10k_pci_hif_dump_area(ar);
 	}
 
 	ath10k_pci_sleep(ar);
@@ -2385,33 +2483,69 @@ static int ath10k_pci_deinit_irq(struct ath10k *ar)
 static int ath10k_pci_wait_for_target_init(struct ath10k *ar)
 {
 	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
-	int wait_limit = 300; /* 3 sec */
+	unsigned long timeout;
 	int ret;
+	u32 val;
+
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot waiting target to initialise\n");
 
 	ret = ath10k_pci_wake(ar);
 	if (ret) {
-		ath10k_err("failed to wake up target: %d\n", ret);
+		ath10k_err("failed to wake up target for init: %d\n", ret);
 		return ret;
 	}
 
-	while (wait_limit-- &&
-	       !(ioread32(ar_pci->mem + FW_INDICATOR_ADDRESS) &
-		 FW_IND_INITIALIZED)) {
+	timeout = jiffies + msecs_to_jiffies(ATH10K_PCI_TARGET_WAIT);
+
+	do {
+		val = ath10k_pci_read32(ar, FW_INDICATOR_ADDRESS);
+
+		ath10k_dbg(ATH10K_DBG_BOOT, "boot target indicator %x\n", val);
+
+		/* target should never return this */
+		if (val == 0xffffffff)
+			continue;
+
+		/* the device has crashed so don't bother trying anymore */
+		if (val & FW_IND_EVENT_PENDING)
+			break;
+
+		if (val & FW_IND_INITIALIZED)
+			break;
+
 		if (ar_pci->num_msi_intrs == 0)
 			/* Fix potential race by repeating CORE_BASE writes */
-			iowrite32(PCIE_INTR_FIRMWARE_MASK |
-				  PCIE_INTR_CE_MASK_ALL,
-				  ar_pci->mem + (SOC_CORE_BASE_ADDRESS |
-						 PCIE_INTR_ENABLE_ADDRESS));
+			ath10k_pci_soc_write32(ar, PCIE_INTR_ENABLE_ADDRESS,
+					       PCIE_INTR_FIRMWARE_MASK |
+					       PCIE_INTR_CE_MASK_ALL);
+
 		mdelay(10);
-	}
+	} while (time_before(jiffies, timeout));
 
-	if (wait_limit < 0) {
-		ath10k_err("target stalled\n");
+	if (val == 0xffffffff) {
+		ath10k_err("failed to read device register, device is gone\n");
 		ret = -EIO;
 		goto out;
 	}
 
+	if (val & FW_IND_EVENT_PENDING) {
+		ath10k_warn("device has crashed during init\n");
+		ath10k_pci_write32(ar, FW_INDICATOR_ADDRESS,
+				   val & ~FW_IND_EVENT_PENDING);
+		ath10k_pci_hif_dump_area(ar);
+		ret = -ECOMM;
+		goto out;
+	}
+
+	if (!(val & FW_IND_INITIALIZED)) {
+		ath10k_err("failed to receive initialized event from target: %08x\n",
+			   val);
+		ret = -ETIMEDOUT;
+		goto out;
+	}
+
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot target initialised\n");
+
 out:
 	ath10k_pci_sleep(ar);
 	return ret;
@@ -2422,6 +2556,8 @@ static int ath10k_pci_cold_reset(struct ath10k *ar)
 	int i, ret;
 	u32 val;
 
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot cold reset\n");
+
 	ret = ath10k_do_pci_wake(ar);
 	if (ret) {
 		ath10k_err("failed to wake up target: %d\n",
@@ -2453,6 +2589,9 @@ static int ath10k_pci_cold_reset(struct ath10k *ar)
 	}
 
 	ath10k_do_pci_sleep(ar);
+
+	ath10k_dbg(ATH10K_DBG_BOOT, "boot cold reset complete\n");
+
 	return 0;
 }
 
@@ -2484,7 +2623,7 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 	struct ath10k_pci *ar_pci;
 	u32 lcr_val, chip_id;
 
-	ath10k_dbg(ATH10K_DBG_PCI, "%s\n", __func__);
+	ath10k_dbg(ATH10K_DBG_PCI, "pci probe\n");
 
 	ar_pci = kzalloc(sizeof(*ar_pci), GFP_KERNEL);
 	if (ar_pci == NULL)
@@ -2503,7 +2642,7 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 		goto err_ar_pci;
 	}
 
-	if (ath10k_target_ps)
+	if (ath10k_pci_target_ps)
 		set_bit(ATH10K_PCI_FEATURE_SOC_POWER_SAVE, ar_pci->features);
 
 	ath10k_pci_dump_features(ar_pci);
@@ -2516,23 +2655,10 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 	}
 
 	ar_pci->ar = ar;
-	ar_pci->fw_indicator_address = FW_INDICATOR_ADDRESS;
 	atomic_set(&ar_pci->keep_awake_count, 0);
 
 	pci_set_drvdata(pdev, ar);
 
-	/*
-	 * Without any knowledge of the Host, the Target may have been reset or
-	 * power cycled and its Config Space may no longer reflect the PCI
-	 * address space that was assigned earlier by the PCI infrastructure.
-	 * Refresh it now.
-	 */
-	ret = pci_assign_resource(pdev, BAR_NUM);
-	if (ret) {
-		ath10k_err("failed to assign PCI space: %d\n", ret);
-		goto err_ar;
-	}
-
 	ret = pci_enable_device(pdev);
 	if (ret) {
 		ath10k_err("failed to enable PCI device: %d\n", ret);
@@ -2594,16 +2720,24 @@ static int ath10k_pci_probe(struct pci_dev *pdev,
 
 	ath10k_do_pci_sleep(ar);
 
+	ret = ath10k_pci_alloc_ce(ar);
+	if (ret) {
+		ath10k_err("failed to allocate copy engine pipes: %d\n", ret);
+		goto err_iomap;
+	}
+
 	ath10k_dbg(ATH10K_DBG_BOOT, "boot pci_mem 0x%p\n", ar_pci->mem);
 
 	ret = ath10k_core_register(ar, chip_id);
 	if (ret) {
 		ath10k_err("failed to register driver core: %d\n", ret);
-		goto err_iomap;
+		goto err_free_ce;
 	}
 
 	return 0;
 
+err_free_ce:
+	ath10k_pci_free_ce(ar);
 err_iomap:
 	pci_iounmap(pdev, mem);
 err_master:
@@ -2626,7 +2760,7 @@ static void ath10k_pci_remove(struct pci_dev *pdev)
 	struct ath10k *ar = pci_get_drvdata(pdev);
 	struct ath10k_pci *ar_pci;
 
-	ath10k_dbg(ATH10K_DBG_PCI, "%s\n", __func__);
+	ath10k_dbg(ATH10K_DBG_PCI, "pci remove\n");
 
 	if (!ar)
 		return;
@@ -2636,9 +2770,8 @@ static void ath10k_pci_remove(struct pci_dev *pdev)
 	if (!ar_pci)
 		return;
 
-	tasklet_kill(&ar_pci->msi_fw_err);
-
 	ath10k_core_unregister(ar);
+	ath10k_pci_free_ce(ar);
 
 	pci_iounmap(pdev, ar_pci->mem);
 	pci_release_region(pdev, BAR_NUM);
@@ -2680,6 +2813,5 @@ module_exit(ath10k_pci_exit);
 MODULE_AUTHOR("Qualcomm Atheros");
 MODULE_DESCRIPTION("Driver support for Atheros QCA988X PCIe devices");
 MODULE_LICENSE("Dual BSD/GPL");
-MODULE_FIRMWARE(QCA988X_HW_2_0_FW_DIR "/" QCA988X_HW_2_0_FW_FILE);
-MODULE_FIRMWARE(QCA988X_HW_2_0_FW_DIR "/" QCA988X_HW_2_0_OTP_FILE);
+MODULE_FIRMWARE(QCA988X_HW_2_0_FW_DIR "/" QCA988X_HW_2_0_FW_2_FILE);
 MODULE_FIRMWARE(QCA988X_HW_2_0_FW_DIR "/" QCA988X_HW_2_0_BOARD_DATA_FILE);
diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h
index b43fdb4f731..dfdebb4157a 100644
--- a/drivers/net/wireless/ath/ath10k/pci.h
+++ b/drivers/net/wireless/ath/ath10k/pci.h
@@ -189,9 +189,6 @@ struct ath10k_pci {
 
 	struct ath10k_hif_cb msg_callbacks_current;
 
-	/* Target address used to signal a pending firmware event */
-	u32 fw_indicator_address;
-
 	/* Copy Engine used for Diagnostic Accesses */
 	struct ath10k_ce_pipe *ce_diag;
 
diff --git a/drivers/net/wireless/ath/ath10k/txrx.c b/drivers/net/wireless/ath/ath10k/txrx.c
index 0541dd939ce..82669a77e55 100644
--- a/drivers/net/wireless/ath/ath10k/txrx.c
+++ b/drivers/net/wireless/ath/ath10k/txrx.c
@@ -100,189 +100,6 @@ exit:
 		wake_up(&htt->empty_tx_wq);
 }
 
-static const u8 rx_legacy_rate_idx[] = {
-	3,	/* 0x00  - 11Mbps  */
-	2,	/* 0x01  - 5.5Mbps */
-	1,	/* 0x02  - 2Mbps   */
-	0,	/* 0x03  - 1Mbps   */
-	3,	/* 0x04  - 11Mbps  */
-	2,	/* 0x05  - 5.5Mbps */
-	1,	/* 0x06  - 2Mbps   */
-	0,	/* 0x07  - 1Mbps   */
-	10,	/* 0x08  - 48Mbps  */
-	8,	/* 0x09  - 24Mbps  */
-	6,	/* 0x0A  - 12Mbps  */
-	4,	/* 0x0B  - 6Mbps   */
-	11,	/* 0x0C  - 54Mbps  */
-	9,	/* 0x0D  - 36Mbps  */
-	7,	/* 0x0E  - 18Mbps  */
-	5,	/* 0x0F  - 9Mbps   */
-};
-
-static void process_rx_rates(struct ath10k *ar, struct htt_rx_info *info,
-			     enum ieee80211_band band,
-			     struct ieee80211_rx_status *status)
-{
-	u8 cck, rate, rate_idx, bw, sgi, mcs, nss;
-	u8 info0 = info->rate.info0;
-	u32 info1 = info->rate.info1;
-	u32 info2 = info->rate.info2;
-	u8 preamble = 0;
-
-	/* Check if valid fields */
-	if (!(info0 & HTT_RX_INDICATION_INFO0_START_VALID))
-		return;
-
-	preamble = MS(info1, HTT_RX_INDICATION_INFO1_PREAMBLE_TYPE);
-
-	switch (preamble) {
-	case HTT_RX_LEGACY:
-		cck = info0 & HTT_RX_INDICATION_INFO0_LEGACY_RATE_CCK;
-		rate = MS(info0, HTT_RX_INDICATION_INFO0_LEGACY_RATE);
-		rate_idx = 0;
-
-		if (rate < 0x08 || rate > 0x0F)
-			break;
-
-		switch (band) {
-		case IEEE80211_BAND_2GHZ:
-			if (cck)
-				rate &= ~BIT(3);
-			rate_idx = rx_legacy_rate_idx[rate];
-			break;
-		case IEEE80211_BAND_5GHZ:
-			rate_idx = rx_legacy_rate_idx[rate];
-			/* We are using same rate table registering
-			   HW - ath10k_rates[]. In case of 5GHz skip
-			   CCK rates, so -4 here */
-			rate_idx -= 4;
-			break;
-		default:
-			break;
-		}
-
-		status->rate_idx = rate_idx;
-		break;
-	case HTT_RX_HT:
-	case HTT_RX_HT_WITH_TXBF:
-		/* HT-SIG - Table 20-11 in info1 and info2 */
-		mcs = info1 & 0x1F;
-		nss = mcs >> 3;
-		bw = (info1 >> 7) & 1;
-		sgi = (info2 >> 7) & 1;
-
-		status->rate_idx = mcs;
-		status->flag |= RX_FLAG_HT;
-		if (sgi)
-			status->flag |= RX_FLAG_SHORT_GI;
-		if (bw)
-			status->flag |= RX_FLAG_40MHZ;
-		break;
-	case HTT_RX_VHT:
-	case HTT_RX_VHT_WITH_TXBF:
-		/* VHT-SIG-A1 in info 1, VHT-SIG-A2 in info2
-		   TODO check this */
-		mcs = (info2 >> 4) & 0x0F;
-		nss = ((info1 >> 10) & 0x07) + 1;
-		bw = info1 & 3;
-		sgi = info2 & 1;
-
-		status->rate_idx = mcs;
-		status->vht_nss = nss;
-
-		if (sgi)
-			status->flag |= RX_FLAG_SHORT_GI;
-
-		switch (bw) {
-		/* 20MHZ */
-		case 0:
-			break;
-		/* 40MHZ */
-		case 1:
-			status->flag |= RX_FLAG_40MHZ;
-			break;
-		/* 80MHZ */
-		case 2:
-			status->vht_flag |= RX_VHT_FLAG_80MHZ;
-		}
-
-		status->flag |= RX_FLAG_VHT;
-		break;
-	default:
-		break;
-	}
-}
-
-void ath10k_process_rx(struct ath10k *ar, struct htt_rx_info *info)
-{
-	struct ieee80211_rx_status *status;
-	struct ieee80211_channel *ch;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)info->skb->data;
-
-	status = IEEE80211_SKB_RXCB(info->skb);
-	memset(status, 0, sizeof(*status));
-
-	if (info->encrypt_type != HTT_RX_MPDU_ENCRYPT_NONE) {
-		status->flag |= RX_FLAG_DECRYPTED | RX_FLAG_IV_STRIPPED |
-				RX_FLAG_MMIC_STRIPPED;
-		hdr->frame_control = __cpu_to_le16(
-				__le16_to_cpu(hdr->frame_control) &
-				~IEEE80211_FCTL_PROTECTED);
-	}
-
-	if (info->mic_err)
-		status->flag |= RX_FLAG_MMIC_ERROR;
-
-	if (info->fcs_err)
-		status->flag |= RX_FLAG_FAILED_FCS_CRC;
-
-	if (info->amsdu_more)
-		status->flag |= RX_FLAG_AMSDU_MORE;
-
-	status->signal = info->signal;
-
-	spin_lock_bh(&ar->data_lock);
-	ch = ar->scan_channel;
-	if (!ch)
-		ch = ar->rx_channel;
-	spin_unlock_bh(&ar->data_lock);
-
-	if (!ch) {
-		ath10k_warn("no channel configured; ignoring frame!\n");
-		dev_kfree_skb_any(info->skb);
-		return;
-	}
-
-	process_rx_rates(ar, info, ch->band, status);
-	status->band = ch->band;
-	status->freq = ch->center_freq;
-
-	if (info->rate.info0 & HTT_RX_INDICATION_INFO0_END_VALID) {
-		/* TSF available only in 32-bit */
-		status->mactime = info->tsf & 0xffffffff;
-		status->flag |= RX_FLAG_MACTIME_END;
-	}
-
-	ath10k_dbg(ATH10K_DBG_DATA,
-		   "rx skb %p len %u %s%s%s%s%s %srate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i\n",
-		   info->skb,
-		   info->skb->len,
-		   status->flag == 0 ? "legacy" : "",
-		   status->flag & RX_FLAG_HT ? "ht" : "",
-		   status->flag & RX_FLAG_VHT ? "vht" : "",
-		   status->flag & RX_FLAG_40MHZ ? "40" : "",
-		   status->vht_flag & RX_VHT_FLAG_80MHZ ? "80" : "",
-		   status->flag & RX_FLAG_SHORT_GI ? "sgi " : "",
-		   status->rate_idx,
-		   status->vht_nss,
-		   status->freq,
-		   status->band, status->flag, info->fcs_err);
-	ath10k_dbg_dump(ATH10K_DBG_HTT_DUMP, NULL, "rx skb: ",
-			info->skb->data, info->skb->len);
-
-	ieee80211_rx(ar->hw, info->skb);
-}
-
 struct ath10k_peer *ath10k_peer_find(struct ath10k *ar, int vdev_id,
 				     const u8 *addr)
 {
diff --git a/drivers/net/wireless/ath/ath10k/txrx.h b/drivers/net/wireless/ath/ath10k/txrx.h
index 356dc9c04c9..aee3e20058f 100644
--- a/drivers/net/wireless/ath/ath10k/txrx.h
+++ b/drivers/net/wireless/ath/ath10k/txrx.h
@@ -21,7 +21,6 @@
 
 void ath10k_txrx_tx_unref(struct ath10k_htt *htt,
 			  const struct htt_tx_done *tx_done);
-void ath10k_process_rx(struct ath10k *ar, struct htt_rx_info *info);
 
 struct ath10k_peer *ath10k_peer_find(struct ath10k *ar, int vdev_id,
 				     const u8 *addr);
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index cb1f7b5bcf4..4b7782a529a 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -639,6 +639,7 @@ int ath10k_wmi_mgmt_tx(struct ath10k *ar, struct sk_buff *skb)
 	struct sk_buff *wmi_skb;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	int len;
+	u32 buf_len = skb->len;
 	u16 fc;
 
 	hdr = (struct ieee80211_hdr *)skb->data;
@@ -648,6 +649,15 @@ int ath10k_wmi_mgmt_tx(struct ath10k *ar, struct sk_buff *skb)
 		return -EINVAL;
 
 	len = sizeof(cmd->hdr) + skb->len;
+
+	if ((ieee80211_is_action(hdr->frame_control) ||
+	     ieee80211_is_deauth(hdr->frame_control) ||
+	     ieee80211_is_disassoc(hdr->frame_control)) &&
+	     ieee80211_has_protected(hdr->frame_control)) {
+		len += IEEE80211_CCMP_MIC_LEN;
+		buf_len += IEEE80211_CCMP_MIC_LEN;
+	}
+
 	len = round_up(len, 4);
 
 	wmi_skb = ath10k_wmi_alloc_skb(len);
@@ -659,7 +669,7 @@ int ath10k_wmi_mgmt_tx(struct ath10k *ar, struct sk_buff *skb)
 	cmd->hdr.vdev_id = __cpu_to_le32(ATH10K_SKB_CB(skb)->vdev_id);
 	cmd->hdr.tx_rate = 0;
 	cmd->hdr.tx_power = 0;
-	cmd->hdr.buf_len = __cpu_to_le32((u32)(skb->len));
+	cmd->hdr.buf_len = __cpu_to_le32(buf_len);
 
 	memcpy(cmd->hdr.peer_macaddr.addr, ieee80211_get_DA(hdr), ETH_ALEN);
 	memcpy(cmd->buf, skb->data, skb->len);
@@ -957,10 +967,16 @@ static int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb)
 	 * frames with Protected Bit set. */
 	if (ieee80211_has_protected(hdr->frame_control) &&
 	    !ieee80211_is_auth(hdr->frame_control)) {
-		status->flag |= RX_FLAG_DECRYPTED | RX_FLAG_IV_STRIPPED |
-				RX_FLAG_MMIC_STRIPPED;
-		hdr->frame_control = __cpu_to_le16(fc &
+		status->flag |= RX_FLAG_DECRYPTED;
+
+		if (!ieee80211_is_action(hdr->frame_control) &&
+		    !ieee80211_is_deauth(hdr->frame_control) &&
+		    !ieee80211_is_disassoc(hdr->frame_control)) {
+			status->flag |= RX_FLAG_IV_STRIPPED |
+					RX_FLAG_MMIC_STRIPPED;
+			hdr->frame_control = __cpu_to_le16(fc &
 					~IEEE80211_FCTL_PROTECTED);
+		}
 	}
 
 	ath10k_dbg(ATH10K_DBG_MGMT,
@@ -1362,13 +1378,10 @@ static void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb)
 	struct sk_buff *bcn;
 	int ret, vdev_id = 0;
 
-	ath10k_dbg(ATH10K_DBG_MGMT, "WMI_HOST_SWBA_EVENTID\n");
-
 	ev = (struct wmi_host_swba_event *)skb->data;
 	map = __le32_to_cpu(ev->vdev_map);
 
-	ath10k_dbg(ATH10K_DBG_MGMT, "host swba:\n"
-		   "-vdev map 0x%x\n",
+	ath10k_dbg(ATH10K_DBG_MGMT, "mgmt swba vdev_map 0x%x\n",
 		   ev->vdev_map);
 
 	for (; map; map >>= 1, vdev_id++) {
@@ -1385,12 +1398,7 @@ static void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb)
 		bcn_info = &ev->bcn_info[i];
 
 		ath10k_dbg(ATH10K_DBG_MGMT,
-			   "-bcn_info[%d]:\n"
-			   "--tim_len %d\n"
-			   "--tim_mcast %d\n"
-			   "--tim_changed %d\n"
-			   "--tim_num_ps_pending %d\n"
-			   "--tim_bitmap 0x%08x%08x%08x%08x\n",
+			   "mgmt event bcn_info %d tim_len %d mcast %d changed %d num_ps_pending %d bitmap 0x%08x%08x%08x%08x\n",
 			   i,
 			   __le32_to_cpu(bcn_info->tim_info.tim_len),
 			   __le32_to_cpu(bcn_info->tim_info.tim_mcast),
@@ -1439,6 +1447,7 @@ static void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb)
 					 ATH10K_SKB_CB(arvif->beacon)->paddr,
 					 arvif->beacon->len, DMA_TO_DEVICE);
 			dev_kfree_skb_any(arvif->beacon);
+			arvif->beacon = NULL;
 		}
 
 		ATH10K_SKB_CB(bcn)->paddr = dma_map_single(arvif->ar->dev,
@@ -1448,6 +1457,7 @@ static void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb)
 					ATH10K_SKB_CB(bcn)->paddr);
 		if (ret) {
 			ath10k_warn("failed to map beacon: %d\n", ret);
+			dev_kfree_skb_any(bcn);
 			goto skip;
 		}
 
@@ -2365,7 +2375,7 @@ void ath10k_wmi_detach(struct ath10k *ar)
 	ar->wmi.num_mem_chunks = 0;
 }
 
-int ath10k_wmi_connect_htc_service(struct ath10k *ar)
+int ath10k_wmi_connect(struct ath10k *ar)
 {
 	int status;
 	struct ath10k_htc_svc_conn_req conn_req;
@@ -2393,8 +2403,9 @@ int ath10k_wmi_connect_htc_service(struct ath10k *ar)
 	return 0;
 }
 
-int ath10k_wmi_pdev_set_regdomain(struct ath10k *ar, u16 rd, u16 rd2g,
-				  u16 rd5g, u16 ctl2g, u16 ctl5g)
+static int ath10k_wmi_main_pdev_set_regdomain(struct ath10k *ar, u16 rd,
+					      u16 rd2g, u16 rd5g, u16 ctl2g,
+					      u16 ctl5g)
 {
 	struct wmi_pdev_set_regdomain_cmd *cmd;
 	struct sk_buff *skb;
@@ -2418,6 +2429,46 @@ int ath10k_wmi_pdev_set_regdomain(struct ath10k *ar, u16 rd, u16 rd2g,
 				   ar->wmi.cmd->pdev_set_regdomain_cmdid);
 }
 
+static int ath10k_wmi_10x_pdev_set_regdomain(struct ath10k *ar, u16 rd,
+					     u16 rd2g, u16 rd5g,
+					     u16 ctl2g, u16 ctl5g,
+					     enum wmi_dfs_region dfs_reg)
+{
+	struct wmi_pdev_set_regdomain_cmd_10x *cmd;
+	struct sk_buff *skb;
+
+	skb = ath10k_wmi_alloc_skb(sizeof(*cmd));
+	if (!skb)
+		return -ENOMEM;
+
+	cmd = (struct wmi_pdev_set_regdomain_cmd_10x *)skb->data;
+	cmd->reg_domain = __cpu_to_le32(rd);
+	cmd->reg_domain_2G = __cpu_to_le32(rd2g);
+	cmd->reg_domain_5G = __cpu_to_le32(rd5g);
+	cmd->conformance_test_limit_2G = __cpu_to_le32(ctl2g);
+	cmd->conformance_test_limit_5G = __cpu_to_le32(ctl5g);
+	cmd->dfs_domain = __cpu_to_le32(dfs_reg);
+
+	ath10k_dbg(ATH10K_DBG_WMI,
+		   "wmi pdev regdomain rd %x rd2g %x rd5g %x ctl2g %x ctl5g %x dfs_region %x\n",
+		   rd, rd2g, rd5g, ctl2g, ctl5g, dfs_reg);
+
+	return ath10k_wmi_cmd_send(ar, skb,
+				   ar->wmi.cmd->pdev_set_regdomain_cmdid);
+}
+
+int ath10k_wmi_pdev_set_regdomain(struct ath10k *ar, u16 rd, u16 rd2g,
+				  u16 rd5g, u16 ctl2g, u16 ctl5g,
+				  enum wmi_dfs_region dfs_reg)
+{
+	if (test_bit(ATH10K_FW_FEATURE_WMI_10X, ar->fw_features))
+		return ath10k_wmi_10x_pdev_set_regdomain(ar, rd, rd2g, rd5g,
+							ctl2g, ctl5g, dfs_reg);
+	else
+		return ath10k_wmi_main_pdev_set_regdomain(ar, rd, rd2g, rd5g,
+							 ctl2g, ctl5g);
+}
+
 int ath10k_wmi_pdev_set_channel(struct ath10k *ar,
 				const struct wmi_channel_arg *arg)
 {
@@ -3456,8 +3507,9 @@ int ath10k_wmi_peer_assoc(struct ath10k *ar,
 		__cpu_to_le32(arg->peer_vht_rates.tx_mcs_set);
 
 	ath10k_dbg(ATH10K_DBG_WMI,
-		   "wmi peer assoc vdev %d addr %pM\n",
-		   arg->vdev_id, arg->addr);
+		   "wmi peer assoc vdev %d addr %pM (%s)\n",
+		   arg->vdev_id, arg->addr,
+		   arg->peer_reassoc ? "reassociate" : "new");
 	return ath10k_wmi_cmd_send(ar, skb, ar->wmi.cmd->peer_assoc_cmdid);
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index f51d5ca0141..e93df2c1041 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -198,16 +198,6 @@ struct wmi_mac_addr {
 	} __packed;
 } __packed;
 
-/* macro to convert MAC address from WMI word format to char array */
-#define WMI_MAC_ADDR_TO_CHAR_ARRAY(pwmi_mac_addr, c_macaddr) do { \
-	(c_macaddr)[0] =  ((pwmi_mac_addr)->word0) & 0xff; \
-	(c_macaddr)[1] = (((pwmi_mac_addr)->word0) >> 8) & 0xff; \
-	(c_macaddr)[2] = (((pwmi_mac_addr)->word0) >> 16) & 0xff; \
-	(c_macaddr)[3] = (((pwmi_mac_addr)->word0) >> 24) & 0xff; \
-	(c_macaddr)[4] =  ((pwmi_mac_addr)->word1) & 0xff; \
-	(c_macaddr)[5] = (((pwmi_mac_addr)->word1) >> 8) & 0xff; \
-	} while (0)
-
 struct wmi_cmd_map {
 	u32 init_cmdid;
 	u32 start_scan_cmdid;
@@ -2185,6 +2175,31 @@ struct wmi_pdev_set_regdomain_cmd {
 	__le32 conformance_test_limit_5G;
 } __packed;
 
+enum wmi_dfs_region {
+	/* Uninitialized dfs domain */
+	WMI_UNINIT_DFS_DOMAIN = 0,
+
+	/* FCC3 dfs domain */
+	WMI_FCC_DFS_DOMAIN = 1,
+
+	/* ETSI dfs domain */
+	WMI_ETSI_DFS_DOMAIN = 2,
+
+	/*Japan dfs domain */
+	WMI_MKK4_DFS_DOMAIN = 3,
+};
+
+struct wmi_pdev_set_regdomain_cmd_10x {
+	__le32 reg_domain;
+	__le32 reg_domain_2G;
+	__le32 reg_domain_5G;
+	__le32 conformance_test_limit_2G;
+	__le32 conformance_test_limit_5G;
+
+	/* dfs domain from wmi_dfs_region */
+	__le32 dfs_domain;
+} __packed;
+
 /* Command to set/unset chip in quiet mode */
 struct wmi_pdev_set_quiet_cmd {
 	/* period in TUs */
@@ -2210,6 +2225,19 @@ enum ath10k_protmode {
 	ATH10K_PROT_RTSCTS   = 2,    /* RTS-CTS */
 };
 
+enum wmi_rtscts_profile {
+	WMI_RTSCTS_FOR_NO_RATESERIES = 0,
+	WMI_RTSCTS_FOR_SECOND_RATESERIES,
+	WMI_RTSCTS_ACROSS_SW_RETRIES
+};
+
+#define WMI_RTSCTS_ENABLED		1
+#define WMI_RTSCTS_SET_MASK		0x0f
+#define WMI_RTSCTS_SET_LSB		0
+
+#define WMI_RTSCTS_PROFILE_MASK		0xf0
+#define WMI_RTSCTS_PROFILE_LSB		4
+
 enum wmi_beacon_gen_mode {
 	WMI_BEACON_STAGGERED_MODE = 0,
 	WMI_BEACON_BURST_MODE = 1
@@ -2295,9 +2323,9 @@ struct wmi_pdev_param_map {
 #define WMI_PDEV_PARAM_UNSUPPORTED 0
 
 enum wmi_pdev_param {
-	/* TX chian mask */
+	/* TX chain mask */
 	WMI_PDEV_PARAM_TX_CHAIN_MASK = 0x1,
-	/* RX chian mask */
+	/* RX chain mask */
 	WMI_PDEV_PARAM_RX_CHAIN_MASK,
 	/* TX power limit for 2G Radio */
 	WMI_PDEV_PARAM_TXPOWER_LIMIT2G,
@@ -2682,6 +2710,9 @@ struct wal_dbg_tx_stats {
 	/* wal pdev resets  */
 	__le32 pdev_resets;
 
+	/* frames dropped due to non-availability of stateless TIDs */
+	__le32 stateless_tid_alloc_failure;
+
 	__le32 phy_underrun;
 
 	/* MPDU is more than txop limit */
@@ -2738,13 +2769,21 @@ enum wmi_stats_id {
 	WMI_REQUEST_AP_STAT	= 0x02
 };
 
+struct wlan_inst_rssi_args {
+	__le16 cfg_retry_count;
+	__le16 retry_count;
+};
+
 struct wmi_request_stats_cmd {
 	__le32 stats_id;
 
-	/*
-	 * Space to add parameters like
-	 * peer mac addr
-	 */
+	__le32 vdev_id;
+
+	/* peer MAC address */
+	struct wmi_mac_addr peer_macaddr;
+
+	/* Instantaneous RSSI arguments */
+	struct wlan_inst_rssi_args inst_rssi_args;
 } __packed;
 
 /* Suspend option */
@@ -2795,7 +2834,18 @@ struct wmi_stats_event {
  * PDEV statistics
  * TODO: add all PDEV stats here
  */
-struct wmi_pdev_stats {
+struct wmi_pdev_stats_old {
+	__le32 chan_nf;        /* Channel noise floor */
+	__le32 tx_frame_count; /* TX frame count */
+	__le32 rx_frame_count; /* RX frame count */
+	__le32 rx_clear_count; /* rx clear count */
+	__le32 cycle_count;    /* cycle count */
+	__le32 phy_err_count;  /* Phy error count */
+	__le32 chan_tx_pwr;    /* channel tx power */
+	struct wal_dbg_stats wal; /* WAL dbg stats */
+} __packed;
+
+struct wmi_pdev_stats_10x {
 	__le32 chan_nf;        /* Channel noise floor */
 	__le32 tx_frame_count; /* TX frame count */
 	__le32 rx_frame_count; /* RX frame count */
@@ -2804,6 +2854,12 @@ struct wmi_pdev_stats {
 	__le32 phy_err_count;  /* Phy error count */
 	__le32 chan_tx_pwr;    /* channel tx power */
 	struct wal_dbg_stats wal; /* WAL dbg stats */
+	__le32 ack_rx_bad;
+	__le32 rts_bad;
+	__le32 rts_good;
+	__le32 fcs_bad;
+	__le32 no_beacons;
+	__le32 mib_int_count;
 } __packed;
 
 /*
@@ -2818,10 +2874,17 @@ struct wmi_vdev_stats {
  * peer statistics.
  * TODO: add more stats
  */
-struct wmi_peer_stats {
+struct wmi_peer_stats_old {
+	struct wmi_mac_addr peer_macaddr;
+	__le32 peer_rssi;
+	__le32 peer_tx_rate;
+} __packed;
+
+struct wmi_peer_stats_10x {
 	struct wmi_mac_addr peer_macaddr;
 	__le32 peer_rssi;
 	__le32 peer_tx_rate;
+	__le32 peer_rx_rate;
 } __packed;
 
 struct wmi_vdev_create_cmd {
@@ -4196,13 +4259,14 @@ void ath10k_wmi_detach(struct ath10k *ar);
 int ath10k_wmi_wait_for_service_ready(struct ath10k *ar);
 int ath10k_wmi_wait_for_unified_ready(struct ath10k *ar);
 
-int ath10k_wmi_connect_htc_service(struct ath10k *ar);
+int ath10k_wmi_connect(struct ath10k *ar);
 int ath10k_wmi_pdev_set_channel(struct ath10k *ar,
 				const struct wmi_channel_arg *);
 int ath10k_wmi_pdev_suspend_target(struct ath10k *ar, u32 suspend_opt);
 int ath10k_wmi_pdev_resume_target(struct ath10k *ar);
 int ath10k_wmi_pdev_set_regdomain(struct ath10k *ar, u16 rd, u16 rd2g,
-				  u16 rd5g, u16 ctl2g, u16 ctl5g);
+				  u16 rd5g, u16 ctl2g, u16 ctl5g,
+				  enum wmi_dfs_region dfs_reg);
 int ath10k_wmi_pdev_set_param(struct ath10k *ar, u32 id, u32 value);
 int ath10k_wmi_cmd_init(struct ath10k *ar);
 int ath10k_wmi_start_scan(struct ath10k *ar, const struct wmi_start_scan_arg *);
diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c
index 1a2973b7acf..0fce1c76638 100644
--- a/drivers/net/wireless/ath/ath5k/phy.c
+++ b/drivers/net/wireless/ath/ath5k/phy.c
@@ -3709,8 +3709,8 @@ ath5k_hw_txpower(struct ath5k_hw *ah, struct ieee80211_channel *channel,
 			AR5K_REG_MS(AR5K_TUNE_MAX_TXPOWER, AR5K_TPC_CHIRP),
 			AR5K_TPC);
 	} else {
-		ath5k_hw_reg_write(ah, AR5K_PHY_TXPOWER_RATE_MAX |
-			AR5K_TUNE_MAX_TXPOWER, AR5K_PHY_TXPOWER_RATE_MAX);
+		ath5k_hw_reg_write(ah, AR5K_TUNE_MAX_TXPOWER,
+			AR5K_PHY_TXPOWER_RATE_MAX);
 	}
 
 	return 0;
diff --git a/drivers/net/wireless/ath/ath6kl/Kconfig b/drivers/net/wireless/ath/ath6kl/Kconfig
index e39e5860a2e..9c125ff083f 100644
--- a/drivers/net/wireless/ath/ath6kl/Kconfig
+++ b/drivers/net/wireless/ath/ath6kl/Kconfig
@@ -1,11 +1,19 @@
 config ATH6KL
 	tristate "Atheros mobile chipsets support"
+	depends on CFG80211
+        ---help---
+	  This module adds core support for wireless adapters based on
+	  Atheros AR6003 and AR6004 chipsets. You still need separate
+	  bus drivers for USB and SDIO to be able to use real devices.
+
+	  If you choose to build it as a module, it will be called
+	  ath6kl_core. Please note that AR6002 and AR6001 are not
+	  supported by this driver.
 
 config ATH6KL_SDIO
 	tristate "Atheros ath6kl SDIO support"
 	depends on ATH6KL
 	depends on MMC
-	depends on CFG80211
 	---help---
 	  This module adds support for wireless adapters based on
 	  Atheros AR6003 and AR6004 chipsets running over SDIO. If you
@@ -17,25 +25,31 @@ config ATH6KL_USB
 	tristate "Atheros ath6kl USB support"
 	depends on ATH6KL
 	depends on USB
-	depends on CFG80211
 	---help---
 	  This module adds support for wireless adapters based on
-	  Atheros AR6004 chipset running over USB. This is still under
-	  implementation and it isn't functional. If you choose to
-	  build it as a module, it will be called ath6kl_usb.
+	  Atheros AR6004 chipset and chipsets based on it running over
+	  USB. If you choose to build it as a module, it will be
+	  called ath6kl_usb.
 
 config ATH6KL_DEBUG
 	bool "Atheros ath6kl debugging"
 	depends on ATH6KL
 	---help---
-	  Enables debug support
+	  Enables ath6kl debug support, including debug messages
+	  enabled with debug_mask module parameter and debugfs
+	  interface.
+
+	  If unsure, say Y to make it easier to debug problems.
 
 config ATH6KL_TRACING
 	bool "Atheros ath6kl tracing support"
 	depends on ATH6KL
 	depends on EVENT_TRACING
 	---help---
-	  Select this to ath6kl use tracing infrastructure.
+	  Select this to ath6kl use tracing infrastructure which, for
+	  example, can be enabled with help of trace-cmd. All debug
+	  messages and commands are delivered to using individually
+	  enablable trace points.
 
 	  If unsure, say Y to make it easier to debug problems.
 
@@ -47,3 +61,5 @@ config ATH6KL_REGDOMAIN
 	  Enabling this makes it possible to change the regdomain in
 	  the firmware. This can be only enabled if regulatory requirements
 	  are taken into account.
+
+	  If unsure, say N.
diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index c2c6f460495..0e26f4a34fd 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -724,8 +724,9 @@ ath6kl_add_bss_if_needed(struct ath6kl_vif *vif,
 			ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
 				   "added bss %pM to cfg80211\n", bssid);
 		kfree(ie);
-	} else
+	} else {
 		ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "cfg80211 already has a bss\n");
+	}
 
 	return bss;
 }
@@ -970,7 +971,6 @@ static int ath6kl_set_probed_ssids(struct ath6kl *ar,
 					  ssid_list[i].flag,
 					  ssid_list[i].ssid.ssid_len,
 					  ssid_list[i].ssid.ssid);
-
 	}
 
 	/* Make sure no old entries are left behind */
@@ -1759,7 +1759,7 @@ static bool is_rate_ht40(s32 rate, u8 *mcs, bool *sgi)
 }
 
 static int ath6kl_get_station(struct wiphy *wiphy, struct net_device *dev,
-			      u8 *mac, struct station_info *sinfo)
+			      const u8 *mac, struct station_info *sinfo)
 {
 	struct ath6kl *ar = ath6kl_priv(dev);
 	struct ath6kl_vif *vif = netdev_priv(dev);
@@ -1897,7 +1897,6 @@ static int ath6kl_wow_usr(struct ath6kl *ar, struct ath6kl_vif *vif,
 
 	/* Configure the patterns that we received from the user. */
 	for (i = 0; i < wow->n_patterns; i++) {
-
 		/*
 		 * Convert given nl80211 specific mask value to equivalent
 		 * driver specific mask value and send it to the chip along
@@ -2850,8 +2849,9 @@ static int ath6kl_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	if (p.prwise_crypto_type == 0) {
 		p.prwise_crypto_type = NONE_CRYPT;
 		ath6kl_set_cipher(vif, 0, true);
-	} else if (info->crypto.n_ciphers_pairwise == 1)
+	} else if (info->crypto.n_ciphers_pairwise == 1) {
 		ath6kl_set_cipher(vif, info->crypto.ciphers_pairwise[0], true);
+	}
 
 	switch (info->crypto.cipher_group) {
 	case WLAN_CIPHER_SUITE_WEP40:
@@ -2897,7 +2897,6 @@ static int ath6kl_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	}
 
 	if (info->inactivity_timeout) {
-
 		inactivity_timeout = info->inactivity_timeout;
 
 		if (ar->hw.flags & ATH6KL_HW_AP_INACTIVITY_MINS)
@@ -2975,7 +2974,7 @@ static int ath6kl_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 static const u8 bcast_addr[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 
 static int ath6kl_del_station(struct wiphy *wiphy, struct net_device *dev,
-			      u8 *mac)
+			      const u8 *mac)
 {
 	struct ath6kl *ar = ath6kl_priv(dev);
 	struct ath6kl_vif *vif = netdev_priv(dev);
@@ -2986,7 +2985,8 @@ static int ath6kl_del_station(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ath6kl_change_station(struct wiphy *wiphy, struct net_device *dev,
-				 u8 *mac, struct station_parameters *params)
+				 const u8 *mac,
+				 struct station_parameters *params)
 {
 	struct ath6kl *ar = ath6kl_priv(dev);
 	struct ath6kl_vif *vif = netdev_priv(dev);
diff --git a/drivers/net/wireless/ath/ath6kl/core.c b/drivers/net/wireless/ath/ath6kl/core.c
index 4b46adbe8c9..b0b65204276 100644
--- a/drivers/net/wireless/ath/ath6kl/core.c
+++ b/drivers/net/wireless/ath/ath6kl/core.c
@@ -45,9 +45,9 @@ module_param(testmode, uint, 0644);
 module_param(recovery_enable, uint, 0644);
 module_param(heart_beat_poll, uint, 0644);
 MODULE_PARM_DESC(recovery_enable, "Enable recovery from firmware error");
-MODULE_PARM_DESC(heart_beat_poll, "Enable fw error detection periodic"   \
-		 "polling. This also specifies the polling interval in"  \
-		 "msecs. Set reocvery_enable for this to be effective");
+MODULE_PARM_DESC(heart_beat_poll,
+		 "Enable fw error detection periodic polling in msecs - Also set recovery_enable for this to be effective");
+
 
 void ath6kl_core_tx_complete(struct ath6kl *ar, struct sk_buff *skb)
 {
diff --git a/drivers/net/wireless/ath/ath6kl/debug.c b/drivers/net/wireless/ath/ath6kl/debug.c
index dbfd17d0a5f..55c4064dd50 100644
--- a/drivers/net/wireless/ath/ath6kl/debug.c
+++ b/drivers/net/wireless/ath/ath6kl/debug.c
@@ -172,7 +172,6 @@ void ath6kl_dump_registers(struct ath6kl_device *dev,
 			   struct ath6kl_irq_proc_registers *irq_proc_reg,
 			   struct ath6kl_irq_enable_reg *irq_enable_reg)
 {
-
 	ath6kl_dbg(ATH6KL_DBG_IRQ, ("<------- Register Table -------->\n"));
 
 	if (irq_proc_reg != NULL) {
@@ -219,7 +218,6 @@ void ath6kl_dump_registers(struct ath6kl_device *dev,
 				   "GMBOX lookahead alias 1:   0x%x\n",
 				   irq_proc_reg->rx_gmbox_lkahd_alias[1]);
 		}
-
 	}
 
 	if (irq_enable_reg != NULL) {
@@ -1396,7 +1394,6 @@ static ssize_t ath6kl_create_qos_write(struct file *file,
 						const char __user *user_buf,
 						size_t count, loff_t *ppos)
 {
-
 	struct ath6kl *ar = file->private_data;
 	struct ath6kl_vif *vif;
 	char buf[200];
@@ -1575,7 +1572,6 @@ static ssize_t ath6kl_delete_qos_write(struct file *file,
 				const char __user *user_buf,
 				size_t count, loff_t *ppos)
 {
-
 	struct ath6kl *ar = file->private_data;
 	struct ath6kl_vif *vif;
 	char buf[100];
diff --git a/drivers/net/wireless/ath/ath6kl/debug.h b/drivers/net/wireless/ath/ath6kl/debug.h
index ca9ba005f28..e194c10d9f0 100644
--- a/drivers/net/wireless/ath/ath6kl/debug.h
+++ b/drivers/net/wireless/ath/ath6kl/debug.h
@@ -97,8 +97,8 @@ static inline void ath6kl_dump_registers(struct ath6kl_device *dev,
 		struct ath6kl_irq_proc_registers *irq_proc_reg,
 		struct ath6kl_irq_enable_reg *irq_en_reg)
 {
-
 }
+
 static inline void dump_cred_dist_stats(struct htc_target *target)
 {
 }
diff --git a/drivers/net/wireless/ath/ath6kl/hif.c b/drivers/net/wireless/ath/ath6kl/hif.c
index fea7709b5dd..18c070850a0 100644
--- a/drivers/net/wireless/ath/ath6kl/hif.c
+++ b/drivers/net/wireless/ath/ath6kl/hif.c
@@ -37,7 +37,6 @@ static int ath6kl_hif_cp_scat_dma_buf(struct hif_scatter_req *req,
 	buf = req->virt_dma_buf;
 
 	for (i = 0; i < req->scat_entries; i++) {
-
 		if (from_dma)
 			memcpy(req->scat_list[i].buf, buf,
 			       req->scat_list[i].len);
@@ -116,7 +115,6 @@ static void ath6kl_hif_dump_fw_crash(struct ath6kl *ar)
 			    le32_to_cpu(regdump_val[i + 2]),
 			    le32_to_cpu(regdump_val[i + 3]));
 	}
-
 }
 
 static int ath6kl_hif_proc_dbg_intr(struct ath6kl_device *dev)
@@ -701,5 +699,4 @@ int ath6kl_hif_setup(struct ath6kl_device *dev)
 
 fail_setup:
 	return status;
-
 }
diff --git a/drivers/net/wireless/ath/ath6kl/hif.h b/drivers/net/wireless/ath/ath6kl/hif.h
index 61f6b21fb0a..dc6bd8cd9b8 100644
--- a/drivers/net/wireless/ath/ath6kl/hif.h
+++ b/drivers/net/wireless/ath/ath6kl/hif.h
@@ -197,9 +197,9 @@ struct hif_scatter_req {
 	/* bounce buffer for upper layers to copy to/from */
 	u8 *virt_dma_buf;
 
-	struct hif_scatter_item scat_list[1];
-
 	u32 scat_q_depth;
+
+	struct hif_scatter_item scat_list[0];
 };
 
 struct ath6kl_irq_proc_registers {
diff --git a/drivers/net/wireless/ath/ath6kl/htc_mbox.c b/drivers/net/wireless/ath/ath6kl/htc_mbox.c
index 65e5b719093..e481f14b987 100644
--- a/drivers/net/wireless/ath/ath6kl/htc_mbox.c
+++ b/drivers/net/wireless/ath/ath6kl/htc_mbox.c
@@ -112,9 +112,9 @@ static void ath6kl_credit_init(struct ath6kl_htc_credit_info *cred_info,
 		if (cur_ep_dist->endpoint == ENDPOINT_0)
 			continue;
 
-		if (cur_ep_dist->svc_id == WMI_CONTROL_SVC)
+		if (cur_ep_dist->svc_id == WMI_CONTROL_SVC) {
 			cur_ep_dist->cred_norm = cur_ep_dist->cred_per_msg;
-		else {
+		} else {
 			/*
 			 * For the remaining data endpoints, we assume that
 			 * each cred_per_msg are the same. We use a simple
@@ -129,7 +129,6 @@ static void ath6kl_credit_init(struct ath6kl_htc_credit_info *cred_info,
 			count = (count * 3) >> 2;
 			count = max(count, cur_ep_dist->cred_per_msg);
 			cur_ep_dist->cred_norm = count;
-
 		}
 
 		ath6kl_dbg(ATH6KL_DBG_CREDIT,
@@ -549,7 +548,6 @@ static int htc_check_credits(struct htc_target *target,
 			     enum htc_endpoint_id eid, unsigned int len,
 			     int *req_cred)
 {
-
 	*req_cred = (len > target->tgt_cred_sz) ?
 		     DIV_ROUND_UP(len, target->tgt_cred_sz) : 1;
 
@@ -608,7 +606,6 @@ static void ath6kl_htc_tx_pkts_get(struct htc_target *target,
 	unsigned int len;
 
 	while (true) {
-
 		flags = 0;
 
 		if (list_empty(&endpoint->txq))
@@ -889,7 +886,6 @@ static void ath6kl_htc_tx_from_queue(struct htc_target *target,
 		ac = target->dev->ar->ep2ac_map[endpoint->eid];
 
 	while (true) {
-
 		if (list_empty(&endpoint->txq))
 			break;
 
@@ -1190,7 +1186,6 @@ static void ath6kl_htc_mbox_flush_txep(struct htc_target *target,
 		list_add_tail(&packet->list, &container);
 		htc_tx_complete(endpoint, &container);
 	}
-
 }
 
 static void ath6kl_htc_flush_txep_all(struct htc_target *target)
@@ -1394,7 +1389,6 @@ static int ath6kl_htc_rx_setup(struct htc_target *target,
 
 	ep_cb = ep->ep_cb;
 	for (j = 0; j < n_msg; j++) {
-
 		/*
 		 * Reset flag, any packets allocated using the
 		 * rx_alloc() API cannot be recycled on
@@ -1424,9 +1418,9 @@ static int ath6kl_htc_rx_setup(struct htc_target *target,
 				}
 			}
 
-			if (list_empty(&ep->rx_bufq))
+			if (list_empty(&ep->rx_bufq)) {
 				packet = NULL;
-			else {
+			} else {
 				packet = list_first_entry(&ep->rx_bufq,
 						struct htc_packet, list);
 				list_del(&packet->list);
@@ -1487,7 +1481,6 @@ static int ath6kl_htc_rx_alloc(struct htc_target *target,
 	spin_lock_bh(&target->rx_lock);
 
 	for (i = 0; i < msg; i++) {
-
 		htc_hdr = (struct htc_frame_hdr *)&lk_ahds[i];
 
 		if (htc_hdr->eid >= ENDPOINT_MAX) {
@@ -1708,7 +1701,6 @@ static int htc_parse_trailer(struct htc_target *target,
 		lk_ahd = (struct htc_lookahead_report *) record_buf;
 		if ((lk_ahd->pre_valid == ((~lk_ahd->post_valid) & 0xFF)) &&
 		    next_lk_ahds) {
-
 			ath6kl_dbg(ATH6KL_DBG_HTC,
 				   "htc rx lk_ahd found pre_valid 0x%x post_valid 0x%x\n",
 				   lk_ahd->pre_valid, lk_ahd->post_valid);
@@ -1755,7 +1747,6 @@ static int htc_parse_trailer(struct htc_target *target,
 	}
 
 	return 0;
-
 }
 
 static int htc_proc_trailer(struct htc_target *target,
@@ -1776,7 +1767,6 @@ static int htc_proc_trailer(struct htc_target *target,
 	status = 0;
 
 	while (len > 0) {
-
 		if (len < sizeof(struct htc_record_hdr)) {
 			status = -ENOMEM;
 			break;
@@ -2098,7 +2088,6 @@ static int ath6kl_htc_rx_fetch(struct htc_target *target,
 		}
 
 		if (!fetched_pkts) {
-
 			packet = list_first_entry(rx_pktq, struct htc_packet,
 						   list);
 
@@ -2173,7 +2162,6 @@ int ath6kl_htc_rxmsg_pending_handler(struct htc_target *target,
 	look_aheads[0] = msg_look_ahead;
 
 	while (true) {
-
 		/*
 		 * First lookahead sets the expected endpoint IDs for all
 		 * packets in a bundle.
@@ -2825,8 +2813,9 @@ static int ath6kl_htc_reset(struct htc_target *target)
 			packet->buf = packet->buf_start;
 			packet->endpoint = ENDPOINT_0;
 			list_add_tail(&packet->list, &target->free_ctrl_rxbuf);
-		} else
+		} else {
 			list_add_tail(&packet->list, &target->free_ctrl_txbuf);
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/wireless/ath/ath6kl/htc_pipe.c b/drivers/net/wireless/ath/ath6kl/htc_pipe.c
index 67aa924ed8b..756fe52a12c 100644
--- a/drivers/net/wireless/ath/ath6kl/htc_pipe.c
+++ b/drivers/net/wireless/ath/ath6kl/htc_pipe.c
@@ -137,7 +137,6 @@ static void get_htc_packet_credit_based(struct htc_target *target,
 			credits_required = 0;
 
 		} else {
-
 			if (ep->cred_dist.credits < credits_required)
 				break;
 
@@ -169,7 +168,6 @@ static void get_htc_packet_credit_based(struct htc_target *target,
 		/* queue this packet into the caller's queue */
 		list_add_tail(&packet->list, queue);
 	}
-
 }
 
 static void get_htc_packet(struct htc_target *target,
@@ -279,7 +277,6 @@ static int htc_issue_packets(struct htc_target *target,
 			list_add(&packet->list, pkt_queue);
 			break;
 		}
-
 	}
 
 	if (status != 0) {
@@ -385,7 +382,6 @@ static enum htc_send_queue_result htc_try_send(struct htc_target *target,
 			 */
 			list_for_each_entry_safe(packet, tmp_pkt,
 						 txq, list) {
-
 				ath6kl_dbg(ATH6KL_DBG_HTC,
 					   "%s: Indicat overflowed TX pkts: %p\n",
 					   __func__, packet);
@@ -403,7 +399,6 @@ static enum htc_send_queue_result htc_try_send(struct htc_target *target,
 					list_move_tail(&packet->list,
 						       &send_queue);
 				}
-
 			}
 
 			if (list_empty(&send_queue)) {
@@ -454,7 +449,6 @@ static enum htc_send_queue_result htc_try_send(struct htc_target *target,
 	 * enough transmit resources.
 	 */
 	while (true) {
-
 		if (get_queue_depth(&ep->txq) == 0)
 			break;
 
@@ -495,8 +489,8 @@ static enum htc_send_queue_result htc_try_send(struct htc_target *target,
 		}
 
 		spin_lock_bh(&target->tx_lock);
-
 	}
+
 	/* done with this endpoint, we can clear the count */
 	ep->tx_proc_cnt = 0;
 	spin_unlock_bh(&target->tx_lock);
@@ -1106,7 +1100,6 @@ free_skb:
 	dev_kfree_skb(skb);
 
 	return status;
-
 }
 
 static void htc_flush_rx_queue(struct htc_target *target,
@@ -1258,7 +1251,6 @@ static int ath6kl_htc_pipe_conn_service(struct htc_target *target,
 		tx_alloc = 0;
 
 	} else {
-
 		tx_alloc = htc_get_credit_alloc(target, conn_req->svc_id);
 		if (tx_alloc == 0) {
 			status = -ENOMEM;
diff --git a/drivers/net/wireless/ath/ath6kl/init.c b/drivers/net/wireless/ath/ath6kl/init.c
index 4f316bdcbab..d5ef211f261 100644
--- a/drivers/net/wireless/ath/ath6kl/init.c
+++ b/drivers/net/wireless/ath/ath6kl/init.c
@@ -1192,7 +1192,6 @@ static int ath6kl_upload_board_file(struct ath6kl *ar)
 
 	if (board_ext_address &&
 	    ar->fw_board_len == (board_data_size + board_ext_data_size)) {
-
 		/* write extended board data */
 		ath6kl_dbg(ATH6KL_DBG_BOOT,
 			   "writing extended board data to 0x%x (%d B)\n",
diff --git a/drivers/net/wireless/ath/ath6kl/main.c b/drivers/net/wireless/ath/ath6kl/main.c
index 5839fc23bdc..d56554674da 100644
--- a/drivers/net/wireless/ath/ath6kl/main.c
+++ b/drivers/net/wireless/ath/ath6kl/main.c
@@ -571,7 +571,6 @@ void ath6kl_scan_complete_evt(struct ath6kl_vif *vif, int status)
 
 static int ath6kl_commit_ch_switch(struct ath6kl_vif *vif, u16 channel)
 {
-
 	struct ath6kl *ar = vif->ar;
 
 	vif->profile.ch = cpu_to_le16(channel);
@@ -600,7 +599,6 @@ static int ath6kl_commit_ch_switch(struct ath6kl_vif *vif, u16 channel)
 
 static void ath6kl_check_ch_switch(struct ath6kl *ar, u16 channel)
 {
-
 	struct ath6kl_vif *vif;
 	int res = 0;
 
@@ -692,9 +690,9 @@ void ath6kl_tkip_micerr_event(struct ath6kl_vif *vif, u8 keyid, bool ismcast)
 		cfg80211_michael_mic_failure(vif->ndev, sta->mac,
 					     NL80211_KEYTYPE_PAIRWISE, keyid,
 					     tsc, GFP_KERNEL);
-	} else
+	} else {
 		ath6kl_cfg80211_tkip_micerr_event(vif, keyid, ismcast);
-
+	}
 }
 
 static void ath6kl_update_target_stats(struct ath6kl_vif *vif, u8 *ptr, u32 len)
@@ -1093,8 +1091,9 @@ static int ath6kl_open(struct net_device *dev)
 	if (test_bit(CONNECTED, &vif->flags)) {
 		netif_carrier_on(dev);
 		netif_wake_queue(dev);
-	} else
+	} else {
 		netif_carrier_off(dev);
+	}
 
 	return 0;
 }
@@ -1146,7 +1145,6 @@ static int ath6kl_set_features(struct net_device *dev,
 			dev->features = features | NETIF_F_RXCSUM;
 			return err;
 		}
-
 	}
 
 	return err;
diff --git a/drivers/net/wireless/ath/ath6kl/sdio.c b/drivers/net/wireless/ath/ath6kl/sdio.c
index 7126bdd4236..339d89f14d3 100644
--- a/drivers/net/wireless/ath/ath6kl/sdio.c
+++ b/drivers/net/wireless/ath/ath6kl/sdio.c
@@ -348,7 +348,7 @@ static int ath6kl_sdio_alloc_prep_scat_req(struct ath6kl_sdio *ar_sdio,
 	int i, scat_req_sz, scat_list_sz, size;
 	u8 *virt_buf;
 
-	scat_list_sz = (n_scat_entry - 1) * sizeof(struct hif_scatter_item);
+	scat_list_sz = n_scat_entry * sizeof(struct hif_scatter_item);
 	scat_req_sz = sizeof(*s_req) + scat_list_sz;
 
 	if (!virt_scat)
@@ -425,8 +425,9 @@ static int ath6kl_sdio_read_write_sync(struct ath6kl *ar, u32 addr, u8 *buf,
 			memcpy(tbuf, buf, len);
 
 		bounced = true;
-	} else
+	} else {
 		tbuf = buf;
+	}
 
 	ret = ath6kl_sdio_io(ar_sdio->func, request, addr, tbuf, len);
 	if ((request & HIF_READ) && bounced)
@@ -441,9 +442,9 @@ static int ath6kl_sdio_read_write_sync(struct ath6kl *ar, u32 addr, u8 *buf,
 static void __ath6kl_sdio_write_async(struct ath6kl_sdio *ar_sdio,
 				      struct bus_request *req)
 {
-	if (req->scat_req)
+	if (req->scat_req) {
 		ath6kl_sdio_scat_rw(ar_sdio, req);
-	else {
+	} else {
 		void *context;
 		int status;
 
@@ -656,7 +657,6 @@ static void ath6kl_sdio_scatter_req_add(struct ath6kl *ar,
 	list_add_tail(&s_req->list, &ar_sdio->scat_req);
 
 	spin_unlock_bh(&ar_sdio->scat_lock);
-
 }
 
 /* scatter gather read write request */
@@ -674,9 +674,9 @@ static int ath6kl_sdio_async_rw_scatter(struct ath6kl *ar,
 		   "hif-scatter: total len: %d scatter entries: %d\n",
 		   scat_req->len, scat_req->scat_entries);
 
-	if (request & HIF_SYNCHRONOUS)
+	if (request & HIF_SYNCHRONOUS) {
 		status = ath6kl_sdio_scat_rw(ar_sdio, scat_req->busrequest);
-	else {
+	} else {
 		spin_lock_bh(&ar_sdio->wr_async_lock);
 		list_add_tail(&scat_req->busrequest->list, &ar_sdio->wr_asyncq);
 		spin_unlock_bh(&ar_sdio->wr_async_lock);
@@ -856,7 +856,6 @@ static int ath6kl_sdio_suspend(struct ath6kl *ar, struct cfg80211_wowlan *wow)
 
 	if (ar->suspend_mode == WLAN_POWER_STATE_WOW ||
 	    (!ar->suspend_mode && wow)) {
-
 		ret = ath6kl_set_sdio_pm_caps(ar);
 		if (ret)
 			goto cut_pwr;
@@ -878,7 +877,6 @@ static int ath6kl_sdio_suspend(struct ath6kl *ar, struct cfg80211_wowlan *wow)
 
 	if (ar->suspend_mode == WLAN_POWER_STATE_DEEP_SLEEP ||
 	    !ar->suspend_mode || try_deepsleep) {
-
 		flags = sdio_get_host_pm_caps(func);
 		if (!(flags & MMC_PM_KEEP_POWER))
 			goto cut_pwr;
@@ -1061,7 +1059,6 @@ static int ath6kl_sdio_bmi_credits(struct ath6kl *ar)
 
 	timeout = jiffies + msecs_to_jiffies(BMI_COMMUNICATION_TIMEOUT);
 	while (time_before(jiffies, timeout) && !ar->bmi.cmd_credits) {
-
 		/*
 		 * Hit the credit counter with a 4-byte access, the first byte
 		 * read will hit the counter and cause a decrement, while the
diff --git a/drivers/net/wireless/ath/ath6kl/target.h b/drivers/net/wireless/ath/ath6kl/target.h
index a580a629a0d..d5eeeae7711 100644
--- a/drivers/net/wireless/ath/ath6kl/target.h
+++ b/drivers/net/wireless/ath/ath6kl/target.h
@@ -289,7 +289,7 @@ struct host_interest {
 	u32 hi_hp_rx_traffic_ratio;                    /* 0xd8 */
 
 	/* test applications flags */
-	u32 hi_test_apps_related    ;                  /* 0xdc */
+	u32 hi_test_apps_related;                      /* 0xdc */
 	/* location of test script */
 	u32 hi_ota_testscript;                         /* 0xe0 */
 	/* location of CAL data */
diff --git a/drivers/net/wireless/ath/ath6kl/txrx.c b/drivers/net/wireless/ath/ath6kl/txrx.c
index ebb24045a8a..40432fe7a5d 100644
--- a/drivers/net/wireless/ath/ath6kl/txrx.c
+++ b/drivers/net/wireless/ath/ath6kl/txrx.c
@@ -125,8 +125,9 @@ static bool ath6kl_process_uapsdq(struct ath6kl_sta *conn,
 		*flags |= WMI_DATA_HDR_FLAGS_UAPSD;
 		spin_unlock_bh(&conn->psq_lock);
 		return false;
-	} else if (!conn->apsd_info)
+	} else if (!conn->apsd_info) {
 		return false;
+	}
 
 	if (test_bit(WMM_ENABLED, &vif->flags)) {
 		ether_type = be16_to_cpu(datap->h_proto);
@@ -316,8 +317,9 @@ int ath6kl_control_tx(void *devt, struct sk_buff *skb,
 		cookie = NULL;
 		ath6kl_err("wmi ctrl ep full, dropping pkt : 0x%p, len:%d\n",
 			   skb, skb->len);
-	} else
+	} else {
 		cookie = ath6kl_alloc_cookie(ar);
+	}
 
 	if (cookie == NULL) {
 		spin_unlock_bh(&ar->lock);
@@ -359,7 +361,7 @@ int ath6kl_data_tx(struct sk_buff *skb, struct net_device *dev)
 	struct ath6kl_vif *vif = netdev_priv(dev);
 	u32 map_no = 0;
 	u16 htc_tag = ATH6KL_DATA_PKT_TAG;
-	u8 ac = 99 ; /* initialize to unmapped ac */
+	u8 ac = 99; /* initialize to unmapped ac */
 	bool chk_adhoc_ps_mapping = false;
 	int ret;
 	struct wmi_tx_meta_v2 meta_v2;
@@ -449,8 +451,9 @@ int ath6kl_data_tx(struct sk_buff *skb, struct net_device *dev)
 			if (ret)
 				goto fail_tx;
 		}
-	} else
+	} else {
 		goto fail_tx;
+	}
 
 	spin_lock_bh(&ar->lock);
 
@@ -702,7 +705,6 @@ void ath6kl_tx_complete(struct htc_target *target,
 
 	/* reap completed packets */
 	while (!list_empty(packet_queue)) {
-
 		packet = list_first_entry(packet_queue, struct htc_packet,
 					  list);
 		list_del(&packet->list);
@@ -1089,8 +1091,9 @@ static void aggr_deque_frms(struct aggr_info_conn *agg_conn, u8 tid,
 			else
 				skb_queue_tail(&rxtid->q, node->skb);
 			node->skb = NULL;
-		} else
+		} else {
 			stats->num_hole++;
+		}
 
 		rxtid->seq_next = ATH6KL_NEXT_SEQ_NO(rxtid->seq_next);
 		idx = AGGR_WIN_IDX(rxtid->seq_next, rxtid->hold_q_sz);
@@ -1211,7 +1214,7 @@ static bool aggr_process_recv_frm(struct aggr_info_conn *agg_conn, u8 tid,
 		return is_queued;
 
 	spin_lock_bh(&rxtid->lock);
-	for (idx = 0 ; idx < rxtid->hold_q_sz; idx++) {
+	for (idx = 0; idx < rxtid->hold_q_sz; idx++) {
 		if (rxtid->hold_q[idx].skb) {
 			/*
 			 * There is a frame in the queue and no
@@ -1265,7 +1268,6 @@ static void ath6kl_uapsd_trigger_frame_rx(struct ath6kl_vif *vif,
 	is_apsdq_empty_at_start = is_apsdq_empty;
 
 	while ((!is_apsdq_empty) && (num_frames_to_deliver)) {
-
 		spin_lock_bh(&conn->psq_lock);
 		skb = skb_dequeue(&conn->apsdq);
 		is_apsdq_empty = skb_queue_empty(&conn->apsdq);
@@ -1606,16 +1608,18 @@ void ath6kl_rx(struct htc_target *target, struct htc_packet *packet)
 			if (!conn)
 				return;
 			aggr_conn = conn->aggr_conn;
-		} else
+		} else {
 			aggr_conn = vif->aggr_cntxt->aggr_conn;
+		}
 
 		if (aggr_process_recv_frm(aggr_conn, tid, seq_no,
 					  is_amsdu, skb)) {
 			/* aggregation code will handle the skb */
 			return;
 		}
-	} else if (!is_broadcast_ether_addr(datap->h_dest))
+	} else if (!is_broadcast_ether_addr(datap->h_dest)) {
 		vif->net_stats.multicast++;
+	}
 
 	ath6kl_deliver_frames_to_nw_stack(vif->ndev, skb);
 }
@@ -1710,8 +1714,9 @@ void aggr_recv_addba_req_evt(struct ath6kl_vif *vif, u8 tid_mux, u16 seq_no,
 		sta = ath6kl_find_sta_by_aid(vif->ar, aid);
 		if (sta)
 			aggr_conn = sta->aggr_conn;
-	} else
+	} else {
 		aggr_conn = vif->aggr_cntxt->aggr_conn;
+	}
 
 	if (!aggr_conn)
 		return;
@@ -1766,7 +1771,6 @@ void aggr_conn_init(struct ath6kl_vif *vif, struct aggr_info *aggr_info,
 		skb_queue_head_init(&rxtid->q);
 		spin_lock_init(&rxtid->lock);
 	}
-
 }
 
 struct aggr_info *aggr_init(struct ath6kl_vif *vif)
@@ -1806,8 +1810,9 @@ void aggr_recv_delba_req_evt(struct ath6kl_vif *vif, u8 tid_mux)
 		sta = ath6kl_find_sta_by_aid(vif->ar, aid);
 		if (sta)
 			aggr_conn = sta->aggr_conn;
-	} else
+	} else {
 		aggr_conn = vif->aggr_cntxt->aggr_conn;
+	}
 
 	if (!aggr_conn)
 		return;
diff --git a/drivers/net/wireless/ath/ath6kl/usb.c b/drivers/net/wireless/ath/ath6kl/usb.c
index 56c3fd5cef6..3afc5a463d0 100644
--- a/drivers/net/wireless/ath/ath6kl/usb.c
+++ b/drivers/net/wireless/ath/ath6kl/usb.c
@@ -236,7 +236,6 @@ static void ath6kl_usb_free_pipe_resources(struct ath6kl_usb_pipe *pipe)
 			break;
 		kfree(urb_context);
 	}
-
 }
 
 static void ath6kl_usb_cleanup_pipe_resources(struct ath6kl_usb *ar_usb)
@@ -245,7 +244,6 @@ static void ath6kl_usb_cleanup_pipe_resources(struct ath6kl_usb *ar_usb)
 
 	for (i = 0; i < ATH6KL_USB_PIPE_MAX; i++)
 		ath6kl_usb_free_pipe_resources(&ar_usb->pipes[i]);
-
 }
 
 static u8 ath6kl_usb_get_logical_pipe_num(struct ath6kl_usb *ar_usb,
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index 8b4ce28e3ce..4d7f9e4712e 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -289,8 +289,9 @@ int ath6kl_wmi_implicit_create_pstream(struct wmi *wmi, u8 if_idx,
 			   ath6kl_wmi_determine_user_priority(((u8 *) llc_hdr) +
 					sizeof(struct ath6kl_llc_snap_hdr),
 					layer2_priority);
-		} else
+		} else {
 			usr_pri = layer2_priority & 0x7;
+		}
 
 		/*
 		 * Queue the EAPOL frames in the same WMM_AC_VO queue
@@ -359,8 +360,9 @@ int ath6kl_wmi_dot11_hdr_remove(struct wmi *wmi, struct sk_buff *skb)
 		hdr_size = roundup(sizeof(struct ieee80211_qos_hdr),
 				   sizeof(u32));
 		skb_pull(skb, hdr_size);
-	} else if (sub_type == cpu_to_le16(IEEE80211_STYPE_DATA))
+	} else if (sub_type == cpu_to_le16(IEEE80211_STYPE_DATA)) {
 		skb_pull(skb, sizeof(struct ieee80211_hdr_3addr));
+	}
 
 	datap = skb->data;
 	llc_hdr = (struct ath6kl_llc_snap_hdr *)(datap);
@@ -936,7 +938,6 @@ ath6kl_regd_find_country_by_rd(u16 regdmn)
 
 static void ath6kl_wmi_regdomain_event(struct wmi *wmi, u8 *datap, int len)
 {
-
 	struct ath6kl_wmi_regdomain *ev;
 	struct country_code_to_enum_rd *country = NULL;
 	struct reg_dmn_pair_mapping *regpair = NULL;
@@ -946,10 +947,9 @@ static void ath6kl_wmi_regdomain_event(struct wmi *wmi, u8 *datap, int len)
 	ev = (struct ath6kl_wmi_regdomain *) datap;
 	reg_code = le32_to_cpu(ev->reg_code);
 
-	if ((reg_code >> ATH6KL_COUNTRY_RD_SHIFT) & COUNTRY_ERD_FLAG)
+	if ((reg_code >> ATH6KL_COUNTRY_RD_SHIFT) & COUNTRY_ERD_FLAG) {
 		country = ath6kl_regd_find_country((u16) reg_code);
-	else if (!(((u16) reg_code & WORLD_SKU_MASK) == WORLD_SKU_PREFIX)) {
-
+	} else if (!(((u16) reg_code & WORLD_SKU_MASK) == WORLD_SKU_PREFIX)) {
 		regpair = ath6kl_get_regpair((u16) reg_code);
 		country = ath6kl_regd_find_country_by_rd((u16) reg_code);
 		if (regpair)
@@ -1499,7 +1499,6 @@ static int ath6kl_wmi_cac_event_rx(struct wmi *wmi, u8 *datap, int len,
 
 	if ((reply->cac_indication == CAC_INDICATION_ADMISSION_RESP) &&
 	    (reply->status_code != IEEE80211_TSPEC_STATUS_ADMISS_ACCEPTED)) {
-
 		ts = (struct ieee80211_tspec_ie *) &(reply->tspec_suggestion);
 		tsinfo = le16_to_cpu(ts->tsinfo);
 		tsid = (tsinfo >> IEEE80211_WMM_IE_TSPEC_TID_SHIFT) &
@@ -1530,7 +1529,6 @@ static int ath6kl_wmi_cac_event_rx(struct wmi *wmi, u8 *datap, int len,
 	 * for delete qos stream from AP
 	 */
 	else if (reply->cac_indication == CAC_INDICATION_DELETE) {
-
 		ts = (struct ieee80211_tspec_ie *) &(reply->tspec_suggestion);
 		tsinfo = le16_to_cpu(ts->tsinfo);
 		ts_id = ((tsinfo >> IEEE80211_WMM_IE_TSPEC_TID_SHIFT) &
@@ -2322,7 +2320,7 @@ int ath6kl_wmi_addkey_cmd(struct wmi *wmi, u8 if_idx, u8 key_index,
 	return ret;
 }
 
-int ath6kl_wmi_add_krk_cmd(struct wmi *wmi, u8 if_idx, u8 *krk)
+int ath6kl_wmi_add_krk_cmd(struct wmi *wmi, u8 if_idx, const u8 *krk)
 {
 	struct sk_buff *skb;
 	struct wmi_add_krk_cmd *cmd;
@@ -2479,7 +2477,6 @@ static int ath6kl_wmi_sync_point(struct wmi *wmi, u8 if_idx)
 		goto free_data_skb;
 
 	for (index = 0; index < num_pri_streams; index++) {
-
 		if (WARN_ON(!data_sync_bufs[index].skb))
 			goto free_data_skb;
 
@@ -2704,7 +2701,6 @@ static void ath6kl_wmi_relinquish_implicit_pstream_credits(struct wmi *wmi)
 
 	for (i = 0; i < WMM_NUM_AC; i++) {
 		if (stream_exist & (1 << i)) {
-
 			/*
 			 * FIXME: Is this lock & unlock inside
 			 * for loop correct? may need rework.
@@ -2870,8 +2866,9 @@ int ath6kl_wmi_set_host_sleep_mode_cmd(struct wmi *wmi, u8 if_idx,
 	if (host_mode == ATH6KL_HOST_MODE_ASLEEP) {
 		ath6kl_wmi_relinquish_implicit_pstream_credits(wmi);
 		cmd->asleep = cpu_to_le32(1);
-	} else
+	} else {
 		cmd->awake = cpu_to_le32(1);
+	}
 
 	ret = ath6kl_wmi_cmd_send(wmi, if_idx, skb,
 				  WMI_SET_HOST_SLEEP_MODE_CMDID,
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.h b/drivers/net/wireless/ath/ath6kl/wmi.h
index 5c702ae4d9f..bb23fc00111 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.h
+++ b/drivers/net/wireless/ath/ath6kl/wmi.h
@@ -898,7 +898,6 @@ struct wmi_start_scan_cmd {
  *  flags here
  */
 enum wmi_scan_ctrl_flags_bits {
-
 	/* set if can scan in the connect cmd */
 	CONNECT_SCAN_CTRL_FLAGS = 0x01,
 
@@ -2617,7 +2616,7 @@ int ath6kl_wmi_addkey_cmd(struct wmi *wmi, u8 if_idx, u8 key_index,
 			  u8 *key_material,
 			  u8 key_op_ctrl, u8 *mac_addr,
 			  enum wmi_sync_flag sync_flag);
-int ath6kl_wmi_add_krk_cmd(struct wmi *wmi, u8 if_idx, u8 *krk);
+int ath6kl_wmi_add_krk_cmd(struct wmi *wmi, u8 if_idx, const u8 *krk);
 int ath6kl_wmi_deletekey_cmd(struct wmi *wmi, u8 if_idx, u8 key_index);
 int ath6kl_wmi_setpmkid_cmd(struct wmi *wmi, u8 if_idx, const u8 *bssid,
 			    const u8 *pmkid, bool set);
diff --git a/drivers/net/wireless/ath/ath9k/Makefile b/drivers/net/wireless/ath/ath9k/Makefile
index 8e1c7b0fe76..8fcd586d1c3 100644
--- a/drivers/net/wireless/ath/ath9k/Makefile
+++ b/drivers/net/wireless/ath/ath9k/Makefile
@@ -53,7 +53,8 @@ obj-$(CONFIG_ATH9K_HW) += ath9k_hw.o
 obj-$(CONFIG_ATH9K_COMMON) += ath9k_common.o
 ath9k_common-y:=	common.o \
 			common-init.o \
-			common-beacon.o
+			common-beacon.o \
+			common-debug.o
 
 ath9k_htc-y +=	htc_hst.o \
 		hif_usb.o \
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_2p2_initvals.h b/drivers/net/wireless/ath/ath9k/ar9003_2p2_initvals.h
index 0a6163e9248..c38399bc9aa 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_2p2_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9003_2p2_initvals.h
@@ -410,7 +410,7 @@ static const u32 ar9300_2p2_baseband_core[][2] = {
 	{0x00009e30, 0x06336f77},
 	{0x00009e34, 0x6af6532f},
 	{0x00009e38, 0x0cc80c00},
-	{0x00009e40, 0x0d261820},
+	{0x00009e40, 0x0d261800},
 	{0x00009e4c, 0x00001004},
 	{0x00009e50, 0x00ff03f1},
 	{0x00009e54, 0x00000000},
diff --git a/drivers/net/wireless/ath/ath9k/ar9330_1p1_initvals.h b/drivers/net/wireless/ath/ath9k/ar9330_1p1_initvals.h
index f76139bbb74..2c42ff05efa 100644
--- a/drivers/net/wireless/ath/ath9k/ar9330_1p1_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9330_1p1_initvals.h
@@ -592,7 +592,7 @@ static const u32 ar9331_1p1_baseband_core[][2] = {
 	{0x00009e30, 0x06336f77},
 	{0x00009e34, 0x6af6532f},
 	{0x00009e38, 0x0cc80c00},
-	{0x00009e40, 0x0d261820},
+	{0x00009e40, 0x0d261800},
 	{0x00009e4c, 0x00001004},
 	{0x00009e50, 0x00ff03f1},
 	{0x00009fc0, 0x803e4788},
diff --git a/drivers/net/wireless/ath/ath9k/ar9330_1p2_initvals.h b/drivers/net/wireless/ath/ath9k/ar9330_1p2_initvals.h
index 0ac8be96097..2154efcd390 100644
--- a/drivers/net/wireless/ath/ath9k/ar9330_1p2_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9330_1p2_initvals.h
@@ -231,7 +231,7 @@ static const u32 ar9331_1p2_baseband_core[][2] = {
 	{0x00009e30, 0x06336f77},
 	{0x00009e34, 0x6af6532f},
 	{0x00009e38, 0x0cc80c00},
-	{0x00009e40, 0x0d261820},
+	{0x00009e40, 0x0d261800},
 	{0x00009e4c, 0x00001004},
 	{0x00009e50, 0x00ff03f1},
 	{0x00009fc0, 0x803e4788},
diff --git a/drivers/net/wireless/ath/ath9k/ar9340_initvals.h b/drivers/net/wireless/ath/ath9k/ar9340_initvals.h
index a01f0edb651..b995ffe88b3 100644
--- a/drivers/net/wireless/ath/ath9k/ar9340_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9340_initvals.h
@@ -318,7 +318,7 @@ static const u32 ar9340_1p0_baseband_core[][2] = {
 	{0x00009e30, 0x06336f77},
 	{0x00009e34, 0x6af6532f},
 	{0x00009e38, 0x0cc80c00},
-	{0x00009e40, 0x0d261820},
+	{0x00009e40, 0x0d261800},
 	{0x00009e4c, 0x00001004},
 	{0x00009e50, 0x00ff03f1},
 	{0x00009e54, 0x00000000},
@@ -348,9 +348,9 @@ static const u32 ar9340_1p0_baseband_core[][2] = {
 	{0x0000a370, 0x00000000},
 	{0x0000a390, 0x00000001},
 	{0x0000a394, 0x00000444},
-	{0x0000a398, 0x00000000},
-	{0x0000a39c, 0x210d0401},
-	{0x0000a3a0, 0xab9a7144},
+	{0x0000a398, 0x001f0e0f},
+	{0x0000a39c, 0x0075393f},
+	{0x0000a3a0, 0xb79f6427},
 	{0x0000a3a4, 0x00000000},
 	{0x0000a3a8, 0xaaaaaaaa},
 	{0x0000a3ac, 0x3c466478},
diff --git a/drivers/net/wireless/ath/ath9k/ar953x_initvals.h b/drivers/net/wireless/ath/ath9k/ar953x_initvals.h
index 3c9113d9b1b..8e5c3b9786e 100644
--- a/drivers/net/wireless/ath/ath9k/ar953x_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar953x_initvals.h
@@ -257,9 +257,9 @@ static const u32 qca953x_1p0_baseband_core[][2] = {
 	{0x0000a370, 0x00000000},
 	{0x0000a390, 0x00000001},
 	{0x0000a394, 0x00000444},
-	{0x0000a398, 0x1f020503},
-	{0x0000a39c, 0x29180c03},
-	{0x0000a3a0, 0x9a8b6844},
+	{0x0000a398, 0x001f0e0f},
+	{0x0000a39c, 0x0075393f},
+	{0x0000a3a0, 0xb79f6427},
 	{0x0000a3a4, 0x000000ff},
 	{0x0000a3a8, 0x6a6a6a6a},
 	{0x0000a3ac, 0x6a6a6a6a},
diff --git a/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h b/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h
index e6aec2c0207..a5ca65240af 100644
--- a/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9580_1p0_initvals.h
@@ -90,7 +90,7 @@ static const u32 ar9580_1p0_baseband_core[][2] = {
 	{0x00009e30, 0x06336f77},
 	{0x00009e34, 0x6af6532f},
 	{0x00009e38, 0x0cc80c00},
-	{0x00009e40, 0x0d261820},
+	{0x00009e40, 0x0d261800},
 	{0x00009e4c, 0x00001004},
 	{0x00009e50, 0x00ff03f1},
 	{0x00009e54, 0x00000000},
diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index 3ba03dde421..2ca8f7e0617 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -23,8 +23,8 @@
 #include <linux/leds.h>
 #include <linux/completion.h>
 
-#include "debug.h"
 #include "common.h"
+#include "debug.h"
 #include "mci.h"
 #include "dfs.h"
 #include "spectral.h"
@@ -114,6 +114,9 @@ int ath_descdma_setup(struct ath_softc *sc, struct ath_descdma *dd,
 #define ATH_TXFIFO_DEPTH           8
 #define ATH_TX_ERROR               0x01
 
+/* Stop tx traffic 1ms before the GO goes away */
+#define ATH_P2P_PS_STOP_TIME       1000
+
 #define IEEE80211_SEQ_SEQ_SHIFT    4
 #define IEEE80211_SEQ_MAX          4096
 #define IEEE80211_WEP_IVLEN        3
@@ -271,6 +274,7 @@ struct ath_node {
 #ifdef CONFIG_ATH9K_STATION_STATISTICS
 	struct ath_rx_rate_stats rx_rate_stats;
 #endif
+	u8 key_idx[4];
 };
 
 struct ath_tx_control {
@@ -366,11 +370,15 @@ void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 /********/
 
 struct ath_vif {
+	struct ieee80211_vif *vif;
 	struct ath_node mcast_node;
 	int av_bslot;
 	bool primary_sta_vif;
 	__le64 tsf_adjust; /* TSF adjustment for staggered beacons */
 	struct ath_buf *av_bcbuf;
+
+	/* P2P Client */
+	struct ieee80211_noa_data noa;
 };
 
 struct ath9k_vif_iter_data {
@@ -463,6 +471,8 @@ int ath_update_survey_stats(struct ath_softc *sc);
 void ath_update_survey_nf(struct ath_softc *sc, int channel);
 void ath9k_queue_reset(struct ath_softc *sc, enum ath_reset_type type);
 void ath_ps_full_sleep(unsigned long data);
+void ath9k_p2p_ps_timer(void *priv);
+void ath9k_update_p2p_ps(struct ath_softc *sc, struct ieee80211_vif *vif);
 
 /**********/
 /* BTCOEX */
@@ -713,6 +723,9 @@ struct ath_softc {
 	struct completion paprd_complete;
 	wait_queue_head_t tx_wait;
 
+	struct ath_gen_timer *p2p_ps_timer;
+	struct ath_vif *p2p_ps_vif;
+
 	unsigned long driver_data;
 
 	u8 gtt_cnt;
@@ -757,6 +770,7 @@ struct ath_softc {
 	struct ath_ant_comb ant_comb;
 	u8 ant_tx, ant_rx;
 	struct dfs_pattern_detector *dfs_detector;
+	u64 dfs_prev_pulse_ts;
 	u32 wow_enabled;
 	/* relay(fs) channel for spectral scan */
 	struct rchan *rfs_chan_spec_scan;
diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c
index bd9e634879e..e387f0b2954 100644
--- a/drivers/net/wireless/ath/ath9k/beacon.c
+++ b/drivers/net/wireless/ath/ath9k/beacon.c
@@ -537,8 +537,6 @@ static void ath9k_cache_beacon_config(struct ath_softc *sc,
 	cur_conf->dtim_period = bss_conf->dtim_period;
 	cur_conf->dtim_count = 1;
 	cur_conf->ibss_creator = bss_conf->ibss_creator;
-	cur_conf->bmiss_timeout =
-		ATH_DEFAULT_BMISS_LIMIT * cur_conf->beacon_interval;
 
 	/*
 	 * It looks like mac80211 may end up using beacon interval of zero in
@@ -549,6 +547,9 @@ static void ath9k_cache_beacon_config(struct ath_softc *sc,
 	if (cur_conf->beacon_interval == 0)
 		cur_conf->beacon_interval = 100;
 
+	cur_conf->bmiss_timeout =
+		ATH_DEFAULT_BMISS_LIMIT * cur_conf->beacon_interval;
+
 	/*
 	 * We don't parse dtim period from mac80211 during the driver
 	 * initialization as it breaks association with hidden-ssid
diff --git a/drivers/net/wireless/ath/ath9k/common-debug.c b/drivers/net/wireless/ath/ath9k/common-debug.c
new file mode 100644
index 00000000000..3b289f93340
--- /dev/null
+++ b/drivers/net/wireless/ath/ath9k/common-debug.c
@@ -0,0 +1,253 @@
+/*
+ * Copyright (c) 2008-2011 Atheros Communications Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "common.h"
+
+static ssize_t read_file_modal_eeprom(struct file *file, char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	struct ath_hw *ah = file->private_data;
+	u32 len = 0, size = 6000;
+	char *buf;
+	size_t retval;
+
+	buf = kzalloc(size, GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	len = ah->eep_ops->dump_eeprom(ah, false, buf, len, size);
+
+	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
+	kfree(buf);
+
+	return retval;
+}
+
+static const struct file_operations fops_modal_eeprom = {
+	.read = read_file_modal_eeprom,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+
+void ath9k_cmn_debug_modal_eeprom(struct dentry *debugfs_phy,
+				  struct ath_hw *ah)
+{
+	debugfs_create_file("modal_eeprom", S_IRUSR, debugfs_phy, ah,
+			    &fops_modal_eeprom);
+}
+EXPORT_SYMBOL(ath9k_cmn_debug_modal_eeprom);
+
+static ssize_t read_file_base_eeprom(struct file *file, char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	struct ath_hw *ah = file->private_data;
+	u32 len = 0, size = 1500;
+	ssize_t retval = 0;
+	char *buf;
+
+	buf = kzalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	len = ah->eep_ops->dump_eeprom(ah, true, buf, len, size);
+
+	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
+	kfree(buf);
+
+	return retval;
+}
+
+static const struct file_operations fops_base_eeprom = {
+	.read = read_file_base_eeprom,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+void ath9k_cmn_debug_base_eeprom(struct dentry *debugfs_phy,
+				 struct ath_hw *ah)
+{
+	debugfs_create_file("base_eeprom", S_IRUSR, debugfs_phy, ah,
+			    &fops_base_eeprom);
+}
+EXPORT_SYMBOL(ath9k_cmn_debug_base_eeprom);
+
+void ath9k_cmn_debug_stat_rx(struct ath_rx_stats *rxstats,
+			     struct ath_rx_status *rs)
+{
+#define RX_PHY_ERR_INC(c) rxstats->phy_err_stats[c]++
+#define RX_CMN_STAT_INC(c) (rxstats->c++)
+
+	RX_CMN_STAT_INC(rx_pkts_all);
+	rxstats->rx_bytes_all += rs->rs_datalen;
+
+	if (rs->rs_status & ATH9K_RXERR_CRC)
+		RX_CMN_STAT_INC(crc_err);
+	if (rs->rs_status & ATH9K_RXERR_DECRYPT)
+		RX_CMN_STAT_INC(decrypt_crc_err);
+	if (rs->rs_status & ATH9K_RXERR_MIC)
+		RX_CMN_STAT_INC(mic_err);
+	if (rs->rs_status & ATH9K_RX_DELIM_CRC_PRE)
+		RX_CMN_STAT_INC(pre_delim_crc_err);
+	if (rs->rs_status & ATH9K_RX_DELIM_CRC_POST)
+		RX_CMN_STAT_INC(post_delim_crc_err);
+	if (rs->rs_status & ATH9K_RX_DECRYPT_BUSY)
+		RX_CMN_STAT_INC(decrypt_busy_err);
+
+	if (rs->rs_status & ATH9K_RXERR_PHY) {
+		RX_CMN_STAT_INC(phy_err);
+		if (rs->rs_phyerr < ATH9K_PHYERR_MAX)
+			RX_PHY_ERR_INC(rs->rs_phyerr);
+	}
+
+#undef RX_CMN_STAT_INC
+#undef RX_PHY_ERR_INC
+}
+EXPORT_SYMBOL(ath9k_cmn_debug_stat_rx);
+
+static ssize_t read_file_recv(struct file *file, char __user *user_buf,
+			      size_t count, loff_t *ppos)
+{
+#define RXS_ERR(s, e)					\
+	do {						\
+		len += scnprintf(buf + len, size - len,	\
+				 "%18s : %10u\n", s,	\
+				 rxstats->e);		\
+	} while (0)
+
+	struct ath_rx_stats *rxstats = file->private_data;
+	char *buf;
+	unsigned int len = 0, size = 1600;
+	ssize_t retval = 0;
+
+	buf = kzalloc(size, GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	RXS_ERR("PKTS-ALL", rx_pkts_all);
+	RXS_ERR("BYTES-ALL", rx_bytes_all);
+	RXS_ERR("BEACONS", rx_beacons);
+	RXS_ERR("FRAGS", rx_frags);
+	RXS_ERR("SPECTRAL", rx_spectral);
+
+	RXS_ERR("CRC ERR", crc_err);
+	RXS_ERR("DECRYPT CRC ERR", decrypt_crc_err);
+	RXS_ERR("PHY ERR", phy_err);
+	RXS_ERR("MIC ERR", mic_err);
+	RXS_ERR("PRE-DELIM CRC ERR", pre_delim_crc_err);
+	RXS_ERR("POST-DELIM CRC ERR", post_delim_crc_err);
+	RXS_ERR("DECRYPT BUSY ERR", decrypt_busy_err);
+	RXS_ERR("LENGTH-ERR", rx_len_err);
+	RXS_ERR("OOM-ERR", rx_oom_err);
+	RXS_ERR("RATE-ERR", rx_rate_err);
+	RXS_ERR("TOO-MANY-FRAGS", rx_too_many_frags_err);
+
+	if (len > size)
+		len = size;
+
+	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
+	kfree(buf);
+
+	return retval;
+
+#undef RXS_ERR
+}
+
+static const struct file_operations fops_recv = {
+	.read = read_file_recv,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+void ath9k_cmn_debug_recv(struct dentry *debugfs_phy,
+			  struct ath_rx_stats *rxstats)
+{
+	debugfs_create_file("recv", S_IRUSR, debugfs_phy, rxstats,
+			    &fops_recv);
+}
+EXPORT_SYMBOL(ath9k_cmn_debug_recv);
+
+static ssize_t read_file_phy_err(struct file *file, char __user *user_buf,
+				 size_t count, loff_t *ppos)
+{
+#define PHY_ERR(s, p) \
+	len += scnprintf(buf + len, size - len, "%22s : %10u\n", s, \
+			 rxstats->phy_err_stats[p]);
+
+	struct ath_rx_stats *rxstats = file->private_data;
+	char *buf;
+	unsigned int len = 0, size = 1600;
+	ssize_t retval = 0;
+
+	buf = kzalloc(size, GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	PHY_ERR("UNDERRUN ERR", ATH9K_PHYERR_UNDERRUN);
+	PHY_ERR("TIMING ERR", ATH9K_PHYERR_TIMING);
+	PHY_ERR("PARITY ERR", ATH9K_PHYERR_PARITY);
+	PHY_ERR("RATE ERR", ATH9K_PHYERR_RATE);
+	PHY_ERR("LENGTH ERR", ATH9K_PHYERR_LENGTH);
+	PHY_ERR("RADAR ERR", ATH9K_PHYERR_RADAR);
+	PHY_ERR("SERVICE ERR", ATH9K_PHYERR_SERVICE);
+	PHY_ERR("TOR ERR", ATH9K_PHYERR_TOR);
+	PHY_ERR("OFDM-TIMING ERR", ATH9K_PHYERR_OFDM_TIMING);
+	PHY_ERR("OFDM-SIGNAL-PARITY ERR", ATH9K_PHYERR_OFDM_SIGNAL_PARITY);
+	PHY_ERR("OFDM-RATE ERR", ATH9K_PHYERR_OFDM_RATE_ILLEGAL);
+	PHY_ERR("OFDM-LENGTH ERR", ATH9K_PHYERR_OFDM_LENGTH_ILLEGAL);
+	PHY_ERR("OFDM-POWER-DROP ERR", ATH9K_PHYERR_OFDM_POWER_DROP);
+	PHY_ERR("OFDM-SERVICE ERR", ATH9K_PHYERR_OFDM_SERVICE);
+	PHY_ERR("OFDM-RESTART ERR", ATH9K_PHYERR_OFDM_RESTART);
+	PHY_ERR("FALSE-RADAR-EXT ERR", ATH9K_PHYERR_FALSE_RADAR_EXT);
+	PHY_ERR("CCK-TIMING ERR", ATH9K_PHYERR_CCK_TIMING);
+	PHY_ERR("CCK-HEADER-CRC ERR", ATH9K_PHYERR_CCK_HEADER_CRC);
+	PHY_ERR("CCK-RATE ERR", ATH9K_PHYERR_CCK_RATE_ILLEGAL);
+	PHY_ERR("CCK-SERVICE ERR", ATH9K_PHYERR_CCK_SERVICE);
+	PHY_ERR("CCK-RESTART ERR", ATH9K_PHYERR_CCK_RESTART);
+	PHY_ERR("CCK-LENGTH ERR", ATH9K_PHYERR_CCK_LENGTH_ILLEGAL);
+	PHY_ERR("CCK-POWER-DROP ERR", ATH9K_PHYERR_CCK_POWER_DROP);
+	PHY_ERR("HT-CRC ERR", ATH9K_PHYERR_HT_CRC_ERROR);
+	PHY_ERR("HT-LENGTH ERR", ATH9K_PHYERR_HT_LENGTH_ILLEGAL);
+	PHY_ERR("HT-RATE ERR", ATH9K_PHYERR_HT_RATE_ILLEGAL);
+
+	if (len > size)
+		len = size;
+
+	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
+	kfree(buf);
+
+	return retval;
+
+#undef PHY_ERR
+}
+
+static const struct file_operations fops_phy_err = {
+	.read = read_file_phy_err,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+void ath9k_cmn_debug_phy_err(struct dentry *debugfs_phy,
+			     struct ath_rx_stats *rxstats)
+{
+	debugfs_create_file("phy_err", S_IRUSR, debugfs_phy, rxstats,
+			    &fops_phy_err);
+}
+EXPORT_SYMBOL(ath9k_cmn_debug_phy_err);
diff --git a/drivers/net/wireless/ath/ath9k/common-debug.h b/drivers/net/wireless/ath/ath9k/common-debug.h
new file mode 100644
index 00000000000..7c9788490f7
--- /dev/null
+++ b/drivers/net/wireless/ath/ath9k/common-debug.h
@@ -0,0 +1,72 @@
+/*
+ * Copyright (c) 2008-2011 Atheros Communications Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+
+
+/**
+ * struct ath_rx_stats - RX Statistics
+ * @rx_pkts_all:  No. of total frames received, including ones that
+	may have had errors.
+ * @rx_bytes_all:  No. of total bytes received, including ones that
+	may have had errors.
+ * @crc_err: No. of frames with incorrect CRC value
+ * @decrypt_crc_err: No. of frames whose CRC check failed after
+	decryption process completed
+ * @phy_err: No. of frames whose reception failed because the PHY
+	encountered an error
+ * @mic_err: No. of frames with incorrect TKIP MIC verification failure
+ * @pre_delim_crc_err: Pre-Frame delimiter CRC error detections
+ * @post_delim_crc_err: Post-Frame delimiter CRC error detections
+ * @decrypt_busy_err: Decryption interruptions counter
+ * @phy_err_stats: Individual PHY error statistics
+ * @rx_len_err:  No. of frames discarded due to bad length.
+ * @rx_oom_err:  No. of frames dropped due to OOM issues.
+ * @rx_rate_err:  No. of frames dropped due to rate errors.
+ * @rx_too_many_frags_err:  Frames dropped due to too-many-frags received.
+ * @rx_beacons:  No. of beacons received.
+ * @rx_frags:  No. of rx-fragements received.
+ * @rx_spectral: No of spectral packets received.
+ */
+struct ath_rx_stats {
+	u32 rx_pkts_all;
+	u32 rx_bytes_all;
+	u32 crc_err;
+	u32 decrypt_crc_err;
+	u32 phy_err;
+	u32 mic_err;
+	u32 pre_delim_crc_err;
+	u32 post_delim_crc_err;
+	u32 decrypt_busy_err;
+	u32 phy_err_stats[ATH9K_PHYERR_MAX];
+	u32 rx_len_err;
+	u32 rx_oom_err;
+	u32 rx_rate_err;
+	u32 rx_too_many_frags_err;
+	u32 rx_beacons;
+	u32 rx_frags;
+	u32 rx_spectral;
+};
+
+void ath9k_cmn_debug_modal_eeprom(struct dentry *debugfs_phy,
+				  struct ath_hw *ah);
+void ath9k_cmn_debug_base_eeprom(struct dentry *debugfs_phy,
+				 struct ath_hw *ah);
+void ath9k_cmn_debug_stat_rx(struct ath_rx_stats *rxstats,
+			     struct ath_rx_status *rs);
+void ath9k_cmn_debug_recv(struct dentry *debugfs_phy,
+			  struct ath_rx_stats *rxstats);
+void ath9k_cmn_debug_phy_err(struct dentry *debugfs_phy,
+			     struct ath_rx_stats *rxstats);
diff --git a/drivers/net/wireless/ath/ath9k/common.h b/drivers/net/wireless/ath/ath9k/common.h
index ca38116838f..ffc454b1863 100644
--- a/drivers/net/wireless/ath/ath9k/common.h
+++ b/drivers/net/wireless/ath/ath9k/common.h
@@ -23,6 +23,7 @@
 
 #include "common-init.h"
 #include "common-beacon.h"
+#include "common-debug.h"
 
 /* Common header for Atheros 802.11n base driver cores */
 
diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index 780ff1bee6f..6cc42be48d4 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -948,151 +948,11 @@ static const struct file_operations fops_reset = {
 	.llseek = default_llseek,
 };
 
-static ssize_t read_file_recv(struct file *file, char __user *user_buf,
-			      size_t count, loff_t *ppos)
-{
-#define RXS_ERR(s, e)					    \
-	do {						    \
-		len += scnprintf(buf + len, size - len,	    \
-				 "%18s : %10u\n", s,	    \
-				 sc->debug.stats.rxstats.e);\
-	} while (0)
-
-	struct ath_softc *sc = file->private_data;
-	char *buf;
-	unsigned int len = 0, size = 1600;
-	ssize_t retval = 0;
-
-	buf = kzalloc(size, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	RXS_ERR("PKTS-ALL", rx_pkts_all);
-	RXS_ERR("BYTES-ALL", rx_bytes_all);
-	RXS_ERR("BEACONS", rx_beacons);
-	RXS_ERR("FRAGS", rx_frags);
-	RXS_ERR("SPECTRAL", rx_spectral);
-
-	RXS_ERR("CRC ERR", crc_err);
-	RXS_ERR("DECRYPT CRC ERR", decrypt_crc_err);
-	RXS_ERR("PHY ERR", phy_err);
-	RXS_ERR("MIC ERR", mic_err);
-	RXS_ERR("PRE-DELIM CRC ERR", pre_delim_crc_err);
-	RXS_ERR("POST-DELIM CRC ERR", post_delim_crc_err);
-	RXS_ERR("DECRYPT BUSY ERR", decrypt_busy_err);
-	RXS_ERR("LENGTH-ERR", rx_len_err);
-	RXS_ERR("OOM-ERR", rx_oom_err);
-	RXS_ERR("RATE-ERR", rx_rate_err);
-	RXS_ERR("TOO-MANY-FRAGS", rx_too_many_frags_err);
-
-	if (len > size)
-		len = size;
-
-	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return retval;
-
-#undef RXS_ERR
-}
-
 void ath_debug_stat_rx(struct ath_softc *sc, struct ath_rx_status *rs)
 {
-#define RX_PHY_ERR_INC(c) sc->debug.stats.rxstats.phy_err_stats[c]++
-
-	RX_STAT_INC(rx_pkts_all);
-	sc->debug.stats.rxstats.rx_bytes_all += rs->rs_datalen;
-
-	if (rs->rs_status & ATH9K_RXERR_CRC)
-		RX_STAT_INC(crc_err);
-	if (rs->rs_status & ATH9K_RXERR_DECRYPT)
-		RX_STAT_INC(decrypt_crc_err);
-	if (rs->rs_status & ATH9K_RXERR_MIC)
-		RX_STAT_INC(mic_err);
-	if (rs->rs_status & ATH9K_RX_DELIM_CRC_PRE)
-		RX_STAT_INC(pre_delim_crc_err);
-	if (rs->rs_status & ATH9K_RX_DELIM_CRC_POST)
-		RX_STAT_INC(post_delim_crc_err);
-	if (rs->rs_status & ATH9K_RX_DECRYPT_BUSY)
-		RX_STAT_INC(decrypt_busy_err);
-
-	if (rs->rs_status & ATH9K_RXERR_PHY) {
-		RX_STAT_INC(phy_err);
-		if (rs->rs_phyerr < ATH9K_PHYERR_MAX)
-			RX_PHY_ERR_INC(rs->rs_phyerr);
-	}
-
-#undef RX_PHY_ERR_INC
+	ath9k_cmn_debug_stat_rx(&sc->debug.stats.rxstats, rs);
 }
 
-static const struct file_operations fops_recv = {
-	.read = read_file_recv,
-	.open = simple_open,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
-static ssize_t read_file_phy_err(struct file *file, char __user *user_buf,
-				 size_t count, loff_t *ppos)
-{
-#define PHY_ERR(s, p) \
-	len += scnprintf(buf + len, size - len, "%22s : %10u\n", s, \
-			 sc->debug.stats.rxstats.phy_err_stats[p]);
-
-	struct ath_softc *sc = file->private_data;
-	char *buf;
-	unsigned int len = 0, size = 1600;
-	ssize_t retval = 0;
-
-	buf = kzalloc(size, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	PHY_ERR("UNDERRUN ERR", ATH9K_PHYERR_UNDERRUN);
-	PHY_ERR("TIMING ERR", ATH9K_PHYERR_TIMING);
-	PHY_ERR("PARITY ERR", ATH9K_PHYERR_PARITY);
-	PHY_ERR("RATE ERR", ATH9K_PHYERR_RATE);
-	PHY_ERR("LENGTH ERR", ATH9K_PHYERR_LENGTH);
-	PHY_ERR("RADAR ERR", ATH9K_PHYERR_RADAR);
-	PHY_ERR("SERVICE ERR", ATH9K_PHYERR_SERVICE);
-	PHY_ERR("TOR ERR", ATH9K_PHYERR_TOR);
-	PHY_ERR("OFDM-TIMING ERR", ATH9K_PHYERR_OFDM_TIMING);
-	PHY_ERR("OFDM-SIGNAL-PARITY ERR", ATH9K_PHYERR_OFDM_SIGNAL_PARITY);
-	PHY_ERR("OFDM-RATE ERR", ATH9K_PHYERR_OFDM_RATE_ILLEGAL);
-	PHY_ERR("OFDM-LENGTH ERR", ATH9K_PHYERR_OFDM_LENGTH_ILLEGAL);
-	PHY_ERR("OFDM-POWER-DROP ERR", ATH9K_PHYERR_OFDM_POWER_DROP);
-	PHY_ERR("OFDM-SERVICE ERR", ATH9K_PHYERR_OFDM_SERVICE);
-	PHY_ERR("OFDM-RESTART ERR", ATH9K_PHYERR_OFDM_RESTART);
-	PHY_ERR("FALSE-RADAR-EXT ERR", ATH9K_PHYERR_FALSE_RADAR_EXT);
-	PHY_ERR("CCK-TIMING ERR", ATH9K_PHYERR_CCK_TIMING);
-	PHY_ERR("CCK-HEADER-CRC ERR", ATH9K_PHYERR_CCK_HEADER_CRC);
-	PHY_ERR("CCK-RATE ERR", ATH9K_PHYERR_CCK_RATE_ILLEGAL);
-	PHY_ERR("CCK-SERVICE ERR", ATH9K_PHYERR_CCK_SERVICE);
-	PHY_ERR("CCK-RESTART ERR", ATH9K_PHYERR_CCK_RESTART);
-	PHY_ERR("CCK-LENGTH ERR", ATH9K_PHYERR_CCK_LENGTH_ILLEGAL);
-	PHY_ERR("CCK-POWER-DROP ERR", ATH9K_PHYERR_CCK_POWER_DROP);
-	PHY_ERR("HT-CRC ERR", ATH9K_PHYERR_HT_CRC_ERROR);
-	PHY_ERR("HT-LENGTH ERR", ATH9K_PHYERR_HT_LENGTH_ILLEGAL);
-	PHY_ERR("HT-RATE ERR", ATH9K_PHYERR_HT_RATE_ILLEGAL);
-
-	if (len > size)
-		len = size;
-
-	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return retval;
-
-#undef PHY_ERR
-}
-
-static const struct file_operations fops_phy_err = {
-	.read = read_file_phy_err,
-	.open = simple_open,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
 static ssize_t read_file_regidx(struct file *file, char __user *user_buf,
                                 size_t count, loff_t *ppos)
 {
@@ -1268,62 +1128,6 @@ static const struct file_operations fops_dump_nfcal = {
 	.llseek = default_llseek,
 };
 
-static ssize_t read_file_base_eeprom(struct file *file, char __user *user_buf,
-				     size_t count, loff_t *ppos)
-{
-	struct ath_softc *sc = file->private_data;
-	struct ath_hw *ah = sc->sc_ah;
-	u32 len = 0, size = 1500;
-	ssize_t retval = 0;
-	char *buf;
-
-	buf = kzalloc(size, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	len = ah->eep_ops->dump_eeprom(ah, true, buf, len, size);
-
-	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return retval;
-}
-
-static const struct file_operations fops_base_eeprom = {
-	.read = read_file_base_eeprom,
-	.open = simple_open,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
-static ssize_t read_file_modal_eeprom(struct file *file, char __user *user_buf,
-				      size_t count, loff_t *ppos)
-{
-	struct ath_softc *sc = file->private_data;
-	struct ath_hw *ah = sc->sc_ah;
-	u32 len = 0, size = 6000;
-	char *buf;
-	size_t retval;
-
-	buf = kzalloc(size, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	len = ah->eep_ops->dump_eeprom(ah, false, buf, len, size);
-
-	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return retval;
-}
-
-static const struct file_operations fops_modal_eeprom = {
-	.read = read_file_modal_eeprom,
-	.open = simple_open,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
 #ifdef CONFIG_ATH9K_BTCOEX_SUPPORT
 static ssize_t read_file_btcoex(struct file *file, char __user *user_buf,
 				size_t count, loff_t *ppos)
@@ -1524,10 +1328,10 @@ int ath9k_init_debug(struct ath_hw *ah)
 			    &fops_misc);
 	debugfs_create_file("reset", S_IRUSR, sc->debug.debugfs_phy, sc,
 			    &fops_reset);
-	debugfs_create_file("recv", S_IRUSR, sc->debug.debugfs_phy, sc,
-			    &fops_recv);
-	debugfs_create_file("phy_err", S_IRUSR, sc->debug.debugfs_phy, sc,
-			    &fops_phy_err);
+
+	ath9k_cmn_debug_recv(sc->debug.debugfs_phy, &sc->debug.stats.rxstats);
+	ath9k_cmn_debug_phy_err(sc->debug.debugfs_phy, &sc->debug.stats.rxstats);
+
 	debugfs_create_u8("rx_chainmask", S_IRUSR, sc->debug.debugfs_phy,
 			  &ah->rxchainmask);
 	debugfs_create_u8("tx_chainmask", S_IRUSR, sc->debug.debugfs_phy,
@@ -1547,10 +1351,10 @@ int ath9k_init_debug(struct ath_hw *ah)
 			    &fops_regdump);
 	debugfs_create_file("dump_nfcal", S_IRUSR, sc->debug.debugfs_phy, sc,
 			    &fops_dump_nfcal);
-	debugfs_create_file("base_eeprom", S_IRUSR, sc->debug.debugfs_phy, sc,
-			    &fops_base_eeprom);
-	debugfs_create_file("modal_eeprom", S_IRUSR, sc->debug.debugfs_phy, sc,
-			    &fops_modal_eeprom);
+
+	ath9k_cmn_debug_base_eeprom(sc->debug.debugfs_phy, sc->sc_ah);
+	ath9k_cmn_debug_modal_eeprom(sc->debug.debugfs_phy, sc->sc_ah);
+
 	debugfs_create_u32("gpio_mask", S_IRUSR | S_IWUSR,
 			   sc->debug.debugfs_phy, &sc->sc_ah->gpio_mask);
 	debugfs_create_u32("gpio_val", S_IRUSR | S_IWUSR,
diff --git a/drivers/net/wireless/ath/ath9k/debug.h b/drivers/net/wireless/ath/ath9k/debug.h
index 559a68c2709..53ae15bd0c9 100644
--- a/drivers/net/wireless/ath/ath9k/debug.h
+++ b/drivers/net/wireless/ath/ath9k/debug.h
@@ -221,50 +221,6 @@ struct ath_rx_rate_stats {
 	} cck_stats[4];
 };
 
-/**
- * struct ath_rx_stats - RX Statistics
- * @rx_pkts_all:  No. of total frames received, including ones that
-	may have had errors.
- * @rx_bytes_all:  No. of total bytes received, including ones that
-	may have had errors.
- * @crc_err: No. of frames with incorrect CRC value
- * @decrypt_crc_err: No. of frames whose CRC check failed after
-	decryption process completed
- * @phy_err: No. of frames whose reception failed because the PHY
-	encountered an error
- * @mic_err: No. of frames with incorrect TKIP MIC verification failure
- * @pre_delim_crc_err: Pre-Frame delimiter CRC error detections
- * @post_delim_crc_err: Post-Frame delimiter CRC error detections
- * @decrypt_busy_err: Decryption interruptions counter
- * @phy_err_stats: Individual PHY error statistics
- * @rx_len_err:  No. of frames discarded due to bad length.
- * @rx_oom_err:  No. of frames dropped due to OOM issues.
- * @rx_rate_err:  No. of frames dropped due to rate errors.
- * @rx_too_many_frags_err:  Frames dropped due to too-many-frags received.
- * @rx_beacons:  No. of beacons received.
- * @rx_frags:  No. of rx-fragements received.
- * @rx_spectral: No of spectral packets received.
- */
-struct ath_rx_stats {
-	u32 rx_pkts_all;
-	u32 rx_bytes_all;
-	u32 crc_err;
-	u32 decrypt_crc_err;
-	u32 phy_err;
-	u32 mic_err;
-	u32 pre_delim_crc_err;
-	u32 post_delim_crc_err;
-	u32 decrypt_busy_err;
-	u32 phy_err_stats[ATH9K_PHYERR_MAX];
-	u32 rx_len_err;
-	u32 rx_oom_err;
-	u32 rx_rate_err;
-	u32 rx_too_many_frags_err;
-	u32 rx_beacons;
-	u32 rx_frags;
-	u32 rx_spectral;
-};
-
 #define ANT_MAIN 0
 #define ANT_ALT  1
 
diff --git a/drivers/net/wireless/ath/ath9k/dfs.c b/drivers/net/wireless/ath/ath9k/dfs.c
index 857bb28b389..726271c7c33 100644
--- a/drivers/net/wireless/ath/ath9k/dfs.c
+++ b/drivers/net/wireless/ath/ath9k/dfs.c
@@ -178,12 +178,12 @@ void ath9k_dfs_process_phyerr(struct ath_softc *sc, void *data,
 	pe.ts = mactime;
 	if (ath9k_postprocess_radar_event(sc, &ard, &pe)) {
 		struct dfs_pattern_detector *pd = sc->dfs_detector;
-		static u64 last_ts;
 		ath_dbg(common, DFS,
 			"ath9k_dfs_process_phyerr: channel=%d, ts=%llu, "
 			"width=%d, rssi=%d, delta_ts=%llu\n",
-			pe.freq, pe.ts, pe.width, pe.rssi, pe.ts-last_ts);
-		last_ts = pe.ts;
+			pe.freq, pe.ts, pe.width, pe.rssi,
+			pe.ts - sc->dfs_prev_pulse_ts);
+		sc->dfs_prev_pulse_ts = pe.ts;
 		DFS_STAT_INC(sc, pulses_processed);
 		if (pd != NULL && pd->add_pulse(pd, &pe)) {
 			DFS_STAT_INC(sc, radar_detected);
diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h
index dab1f0cab99..09a5d72f3ff 100644
--- a/drivers/net/wireless/ath/ath9k/htc.h
+++ b/drivers/net/wireless/ath/ath9k/htc.h
@@ -325,14 +325,14 @@ static inline struct ath9k_htc_tx_ctl *HTC_SKB_CB(struct sk_buff *skb)
 
 #define TX_STAT_INC(c) (hif_dev->htc_handle->drv_priv->debug.tx_stats.c++)
 #define TX_STAT_ADD(c, a) (hif_dev->htc_handle->drv_priv->debug.tx_stats.c += a)
-#define RX_STAT_INC(c) (hif_dev->htc_handle->drv_priv->debug.rx_stats.c++)
-#define RX_STAT_ADD(c, a) (hif_dev->htc_handle->drv_priv->debug.rx_stats.c += a)
+#define RX_STAT_INC(c) (hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c++)
+#define RX_STAT_ADD(c, a) (hif_dev->htc_handle->drv_priv->debug.skbrx_stats.c += a)
 #define CAB_STAT_INC   priv->debug.tx_stats.cab_queued++
 
 #define TX_QSTAT_INC(q) (priv->debug.tx_stats.queue_stats[q]++)
 
 void ath9k_htc_err_stat_rx(struct ath9k_htc_priv *priv,
-			   struct ath_htc_rx_status *rxs);
+			   struct ath_rx_status *rs);
 
 struct ath_tx_stats {
 	u32 buf_queued;
@@ -345,25 +345,18 @@ struct ath_tx_stats {
 	u32 queue_stats[IEEE80211_NUM_ACS];
 };
 
-struct ath_rx_stats {
+struct ath_skbrx_stats {
 	u32 skb_allocated;
 	u32 skb_completed;
 	u32 skb_completed_bytes;
 	u32 skb_dropped;
-	u32 err_crc;
-	u32 err_decrypt_crc;
-	u32 err_mic;
-	u32 err_pre_delim;
-	u32 err_post_delim;
-	u32 err_decrypt_busy;
-	u32 err_phy;
-	u32 err_phy_stats[ATH9K_PHYERR_MAX];
 };
 
 struct ath9k_debug {
 	struct dentry *debugfs_phy;
 	struct ath_tx_stats tx_stats;
 	struct ath_rx_stats rx_stats;
+	struct ath_skbrx_stats skbrx_stats;
 };
 
 void ath9k_htc_get_et_strings(struct ieee80211_hw *hw,
@@ -385,7 +378,7 @@ void ath9k_htc_get_et_stats(struct ieee80211_hw *hw,
 #define TX_QSTAT_INC(c) do { } while (0)
 
 static inline void ath9k_htc_err_stat_rx(struct ath9k_htc_priv *priv,
-					 struct ath_htc_rx_status *rxs)
+					 struct ath_rx_status *rs)
 {
 }
 
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
index fb071ee4fcf..8b529e4b8ac 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
@@ -243,39 +243,14 @@ static const struct file_operations fops_xmit = {
 };
 
 void ath9k_htc_err_stat_rx(struct ath9k_htc_priv *priv,
-			   struct ath_htc_rx_status *rxs)
+			     struct ath_rx_status *rs)
 {
-#define RX_PHY_ERR_INC(c) priv->debug.rx_stats.err_phy_stats[c]++
-
-	if (rxs->rs_status & ATH9K_RXERR_CRC)
-		priv->debug.rx_stats.err_crc++;
-	if (rxs->rs_status & ATH9K_RXERR_DECRYPT)
-		priv->debug.rx_stats.err_decrypt_crc++;
-	if (rxs->rs_status & ATH9K_RXERR_MIC)
-		priv->debug.rx_stats.err_mic++;
-	if (rxs->rs_status & ATH9K_RX_DELIM_CRC_PRE)
-		priv->debug.rx_stats.err_pre_delim++;
-	if (rxs->rs_status & ATH9K_RX_DELIM_CRC_POST)
-		priv->debug.rx_stats.err_post_delim++;
-	if (rxs->rs_status & ATH9K_RX_DECRYPT_BUSY)
-		priv->debug.rx_stats.err_decrypt_busy++;
-
-	if (rxs->rs_status & ATH9K_RXERR_PHY) {
-		priv->debug.rx_stats.err_phy++;
-		if (rxs->rs_phyerr < ATH9K_PHYERR_MAX)
-			RX_PHY_ERR_INC(rxs->rs_phyerr);
-	}
-
-#undef RX_PHY_ERR_INC
+	ath9k_cmn_debug_stat_rx(&priv->debug.rx_stats, rs);
 }
 
-static ssize_t read_file_recv(struct file *file, char __user *user_buf,
+static ssize_t read_file_skb_rx(struct file *file, char __user *user_buf,
 			      size_t count, loff_t *ppos)
 {
-#define PHY_ERR(s, p)							\
-	len += scnprintf(buf + len, size - len, "%20s : %10u\n", s,	\
-			 priv->debug.rx_stats.err_phy_stats[p]);
-
 	struct ath9k_htc_priv *priv = file->private_data;
 	char *buf;
 	unsigned int len = 0, size = 1500;
@@ -287,63 +262,13 @@ static ssize_t read_file_recv(struct file *file, char __user *user_buf,
 
 	len += scnprintf(buf + len, size - len,
 			 "%20s : %10u\n", "SKBs allocated",
-			 priv->debug.rx_stats.skb_allocated);
+			 priv->debug.skbrx_stats.skb_allocated);
 	len += scnprintf(buf + len, size - len,
 			 "%20s : %10u\n", "SKBs completed",
-			 priv->debug.rx_stats.skb_completed);
+			 priv->debug.skbrx_stats.skb_completed);
 	len += scnprintf(buf + len, size - len,
 			 "%20s : %10u\n", "SKBs Dropped",
-			 priv->debug.rx_stats.skb_dropped);
-
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10u\n", "CRC ERR",
-			 priv->debug.rx_stats.err_crc);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10u\n", "DECRYPT CRC ERR",
-			 priv->debug.rx_stats.err_decrypt_crc);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10u\n", "MIC ERR",
-			 priv->debug.rx_stats.err_mic);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10u\n", "PRE-DELIM CRC ERR",
-			 priv->debug.rx_stats.err_pre_delim);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10u\n", "POST-DELIM CRC ERR",
-			 priv->debug.rx_stats.err_post_delim);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10u\n", "DECRYPT BUSY ERR",
-			 priv->debug.rx_stats.err_decrypt_busy);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10u\n", "TOTAL PHY ERR",
-			 priv->debug.rx_stats.err_phy);
-
-
-	PHY_ERR("UNDERRUN", ATH9K_PHYERR_UNDERRUN);
-	PHY_ERR("TIMING", ATH9K_PHYERR_TIMING);
-	PHY_ERR("PARITY", ATH9K_PHYERR_PARITY);
-	PHY_ERR("RATE", ATH9K_PHYERR_RATE);
-	PHY_ERR("LENGTH", ATH9K_PHYERR_LENGTH);
-	PHY_ERR("RADAR", ATH9K_PHYERR_RADAR);
-	PHY_ERR("SERVICE", ATH9K_PHYERR_SERVICE);
-	PHY_ERR("TOR", ATH9K_PHYERR_TOR);
-	PHY_ERR("OFDM-TIMING", ATH9K_PHYERR_OFDM_TIMING);
-	PHY_ERR("OFDM-SIGNAL-PARITY", ATH9K_PHYERR_OFDM_SIGNAL_PARITY);
-	PHY_ERR("OFDM-RATE", ATH9K_PHYERR_OFDM_RATE_ILLEGAL);
-	PHY_ERR("OFDM-LENGTH", ATH9K_PHYERR_OFDM_LENGTH_ILLEGAL);
-	PHY_ERR("OFDM-POWER-DROP", ATH9K_PHYERR_OFDM_POWER_DROP);
-	PHY_ERR("OFDM-SERVICE", ATH9K_PHYERR_OFDM_SERVICE);
-	PHY_ERR("OFDM-RESTART", ATH9K_PHYERR_OFDM_RESTART);
-	PHY_ERR("FALSE-RADAR-EXT", ATH9K_PHYERR_FALSE_RADAR_EXT);
-	PHY_ERR("CCK-TIMING", ATH9K_PHYERR_CCK_TIMING);
-	PHY_ERR("CCK-HEADER-CRC", ATH9K_PHYERR_CCK_HEADER_CRC);
-	PHY_ERR("CCK-RATE", ATH9K_PHYERR_CCK_RATE_ILLEGAL);
-	PHY_ERR("CCK-SERVICE", ATH9K_PHYERR_CCK_SERVICE);
-	PHY_ERR("CCK-RESTART", ATH9K_PHYERR_CCK_RESTART);
-	PHY_ERR("CCK-LENGTH", ATH9K_PHYERR_CCK_LENGTH_ILLEGAL);
-	PHY_ERR("CCK-POWER-DROP", ATH9K_PHYERR_CCK_POWER_DROP);
-	PHY_ERR("HT-CRC", ATH9K_PHYERR_HT_CRC_ERROR);
-	PHY_ERR("HT-LENGTH", ATH9K_PHYERR_HT_LENGTH_ILLEGAL);
-	PHY_ERR("HT-RATE", ATH9K_PHYERR_HT_RATE_ILLEGAL);
+			 priv->debug.skbrx_stats.skb_dropped);
 
 	if (len > size)
 		len = size;
@@ -352,12 +277,10 @@ static ssize_t read_file_recv(struct file *file, char __user *user_buf,
 	kfree(buf);
 
 	return retval;
-
-#undef PHY_ERR
 }
 
-static const struct file_operations fops_recv = {
-	.read = read_file_recv,
+static const struct file_operations fops_skb_rx = {
+	.read = read_file_skb_rx,
 	.open = simple_open,
 	.owner = THIS_MODULE,
 	.llseek = default_llseek,
@@ -486,423 +409,6 @@ static const struct file_operations fops_debug = {
 	.llseek = default_llseek,
 };
 
-static ssize_t read_file_base_eeprom(struct file *file, char __user *user_buf,
-				     size_t count, loff_t *ppos)
-{
-	struct ath9k_htc_priv *priv = file->private_data;
-	struct ath_common *common = ath9k_hw_common(priv->ah);
-	struct base_eep_header *pBase = NULL;
-	unsigned int len = 0, size = 1500;
-	ssize_t retval = 0;
-	char *buf;
-
-	pBase = ath9k_htc_get_eeprom_base(priv);
-
-	if (pBase == NULL) {
-		ath_err(common, "Unknown EEPROM type\n");
-		return 0;
-	}
-
-	buf = kzalloc(size, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n", "Major Version",
-			 pBase->version >> 12);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n", "Minor Version",
-			 pBase->version & 0xFFF);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n", "Checksum",
-			 pBase->checksum);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n", "Length",
-			 pBase->length);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n", "RegDomain1",
-			 pBase->regDmn[0]);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n", "RegDomain2",
-			 pBase->regDmn[1]);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "TX Mask", pBase->txMask);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "RX Mask", pBase->rxMask);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Allow 5GHz",
-			 !!(pBase->opCapFlags & AR5416_OPFLAGS_11A));
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Allow 2GHz",
-			 !!(pBase->opCapFlags & AR5416_OPFLAGS_11G));
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Disable 2GHz HT20",
-			 !!(pBase->opCapFlags & AR5416_OPFLAGS_N_2G_HT20));
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Disable 2GHz HT40",
-			 !!(pBase->opCapFlags & AR5416_OPFLAGS_N_2G_HT40));
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Disable 5Ghz HT20",
-			 !!(pBase->opCapFlags & AR5416_OPFLAGS_N_5G_HT20));
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Disable 5Ghz HT40",
-			 !!(pBase->opCapFlags & AR5416_OPFLAGS_N_5G_HT40));
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Big Endian",
-			 !!(pBase->eepMisc & 0x01));
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Cal Bin Major Ver",
-			 (pBase->binBuildNumber >> 24) & 0xFF);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Cal Bin Minor Ver",
-			 (pBase->binBuildNumber >> 16) & 0xFF);
-	len += scnprintf(buf + len, size - len,
-			 "%20s : %10d\n",
-			 "Cal Bin Build",
-			 (pBase->binBuildNumber >> 8) & 0xFF);
-
-	/*
-	 * UB91 specific data.
-	 */
-	if (AR_SREV_9271(priv->ah)) {
-		struct base_eep_header_4k *pBase4k =
-			&priv->ah->eeprom.map4k.baseEepHeader;
-
-		len += scnprintf(buf + len, size - len,
-				 "%20s : %10d\n",
-				 "TX Gain type",
-				 pBase4k->txGainType);
-	}
-
-	/*
-	 * UB95 specific data.
-	 */
-	if (priv->ah->hw_version.usbdev == AR9287_USB) {
-		struct base_eep_ar9287_header *pBase9287 =
-			&priv->ah->eeprom.map9287.baseEepHeader;
-
-		len += scnprintf(buf + len, size - len,
-				 "%20s : %10ddB\n",
-				 "Power Table Offset",
-				 pBase9287->pwrTableOffset);
-
-		len += scnprintf(buf + len, size - len,
-				 "%20s : %10d\n",
-				 "OpenLoop Power Ctrl",
-				 pBase9287->openLoopPwrCntl);
-	}
-
-	len += scnprintf(buf + len, size - len, "%20s : %pM\n", "MacAddress",
-			 pBase->macAddr);
-	if (len > size)
-		len = size;
-
-	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return retval;
-}
-
-static const struct file_operations fops_base_eeprom = {
-	.read = read_file_base_eeprom,
-	.open = simple_open,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
-static ssize_t read_4k_modal_eeprom(struct file *file,
-				    char __user *user_buf,
-				    size_t count, loff_t *ppos)
-{
-#define PR_EEP(_s, _val)						\
-	do {								\
-		len += scnprintf(buf + len, size - len, "%20s : %10d\n",\
-				 _s, (_val));				\
-	} while (0)
-
-	struct ath9k_htc_priv *priv = file->private_data;
-	struct modal_eep_4k_header *pModal = &priv->ah->eeprom.map4k.modalHeader;
-	unsigned int len = 0, size = 2048;
-	ssize_t retval = 0;
-	char *buf;
-
-	buf = kzalloc(size, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	PR_EEP("Chain0 Ant. Control", pModal->antCtrlChain[0]);
-	PR_EEP("Ant. Common Control", pModal->antCtrlCommon);
-	PR_EEP("Chain0 Ant. Gain", pModal->antennaGainCh[0]);
-	PR_EEP("Switch Settle", pModal->switchSettling);
-	PR_EEP("Chain0 TxRxAtten", pModal->txRxAttenCh[0]);
-	PR_EEP("Chain0 RxTxMargin", pModal->rxTxMarginCh[0]);
-	PR_EEP("ADC Desired size", pModal->adcDesiredSize);
-	PR_EEP("PGA Desired size", pModal->pgaDesiredSize);
-	PR_EEP("Chain0 xlna Gain", pModal->xlnaGainCh[0]);
-	PR_EEP("txEndToXpaOff", pModal->txEndToXpaOff);
-	PR_EEP("txEndToRxOn", pModal->txEndToRxOn);
-	PR_EEP("txFrameToXpaOn", pModal->txFrameToXpaOn);
-	PR_EEP("CCA Threshold)", pModal->thresh62);
-	PR_EEP("Chain0 NF Threshold", pModal->noiseFloorThreshCh[0]);
-	PR_EEP("xpdGain", pModal->xpdGain);
-	PR_EEP("External PD", pModal->xpd);
-	PR_EEP("Chain0 I Coefficient", pModal->iqCalICh[0]);
-	PR_EEP("Chain0 Q Coefficient", pModal->iqCalQCh[0]);
-	PR_EEP("pdGainOverlap", pModal->pdGainOverlap);
-	PR_EEP("O/D Bias Version", pModal->version);
-	PR_EEP("CCK OutputBias", pModal->ob_0);
-	PR_EEP("BPSK OutputBias", pModal->ob_1);
-	PR_EEP("QPSK OutputBias", pModal->ob_2);
-	PR_EEP("16QAM OutputBias", pModal->ob_3);
-	PR_EEP("64QAM OutputBias", pModal->ob_4);
-	PR_EEP("CCK Driver1_Bias", pModal->db1_0);
-	PR_EEP("BPSK Driver1_Bias", pModal->db1_1);
-	PR_EEP("QPSK Driver1_Bias", pModal->db1_2);
-	PR_EEP("16QAM Driver1_Bias", pModal->db1_3);
-	PR_EEP("64QAM Driver1_Bias", pModal->db1_4);
-	PR_EEP("CCK Driver2_Bias", pModal->db2_0);
-	PR_EEP("BPSK Driver2_Bias", pModal->db2_1);
-	PR_EEP("QPSK Driver2_Bias", pModal->db2_2);
-	PR_EEP("16QAM Driver2_Bias", pModal->db2_3);
-	PR_EEP("64QAM Driver2_Bias", pModal->db2_4);
-	PR_EEP("xPA Bias Level", pModal->xpaBiasLvl);
-	PR_EEP("txFrameToDataStart", pModal->txFrameToDataStart);
-	PR_EEP("txFrameToPaOn", pModal->txFrameToPaOn);
-	PR_EEP("HT40 Power Inc.", pModal->ht40PowerIncForPdadc);
-	PR_EEP("Chain0 bswAtten", pModal->bswAtten[0]);
-	PR_EEP("Chain0 bswMargin", pModal->bswMargin[0]);
-	PR_EEP("HT40 Switch Settle", pModal->swSettleHt40);
-	PR_EEP("Chain0 xatten2Db", pModal->xatten2Db[0]);
-	PR_EEP("Chain0 xatten2Margin", pModal->xatten2Margin[0]);
-	PR_EEP("Ant. Diversity ctl1", pModal->antdiv_ctl1);
-	PR_EEP("Ant. Diversity ctl2", pModal->antdiv_ctl2);
-	PR_EEP("TX Diversity", pModal->tx_diversity);
-
-	if (len > size)
-		len = size;
-
-	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return retval;
-
-#undef PR_EEP
-}
-
-static ssize_t read_def_modal_eeprom(struct file *file,
-				     char __user *user_buf,
-				     size_t count, loff_t *ppos)
-{
-#define PR_EEP(_s, _val)						\
-	do {								\
-		if (pBase->opCapFlags & AR5416_OPFLAGS_11G) {		\
-			pModal = &priv->ah->eeprom.def.modalHeader[1];	\
-			len += scnprintf(buf + len, size - len, "%20s : %8d%7s", \
-					 _s, (_val), "|");		\
-		}							\
-		if (pBase->opCapFlags & AR5416_OPFLAGS_11A) {		\
-			pModal = &priv->ah->eeprom.def.modalHeader[0];	\
-			len += scnprintf(buf + len, size - len, "%9d\n",\
-					(_val));			\
-		}							\
-	} while (0)
-
-	struct ath9k_htc_priv *priv = file->private_data;
-	struct base_eep_header *pBase = &priv->ah->eeprom.def.baseEepHeader;
-	struct modal_eep_header *pModal = NULL;
-	unsigned int len = 0, size = 3500;
-	ssize_t retval = 0;
-	char *buf;
-
-	buf = kzalloc(size, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	len += scnprintf(buf + len, size - len,
-			 "%31s %15s\n", "2G", "5G");
-	len += scnprintf(buf + len, size - len,
-			 "%32s %16s\n", "====", "====\n");
-
-	PR_EEP("Chain0 Ant. Control", pModal->antCtrlChain[0]);
-	PR_EEP("Chain1 Ant. Control", pModal->antCtrlChain[1]);
-	PR_EEP("Chain2 Ant. Control", pModal->antCtrlChain[2]);
-	PR_EEP("Ant. Common Control", pModal->antCtrlCommon);
-	PR_EEP("Chain0 Ant. Gain", pModal->antennaGainCh[0]);
-	PR_EEP("Chain1 Ant. Gain", pModal->antennaGainCh[1]);
-	PR_EEP("Chain2 Ant. Gain", pModal->antennaGainCh[2]);
-	PR_EEP("Switch Settle", pModal->switchSettling);
-	PR_EEP("Chain0 TxRxAtten", pModal->txRxAttenCh[0]);
-	PR_EEP("Chain1 TxRxAtten", pModal->txRxAttenCh[1]);
-	PR_EEP("Chain2 TxRxAtten", pModal->txRxAttenCh[2]);
-	PR_EEP("Chain0 RxTxMargin", pModal->rxTxMarginCh[0]);
-	PR_EEP("Chain1 RxTxMargin", pModal->rxTxMarginCh[1]);
-	PR_EEP("Chain2 RxTxMargin", pModal->rxTxMarginCh[2]);
-	PR_EEP("ADC Desired size", pModal->adcDesiredSize);
-	PR_EEP("PGA Desired size", pModal->pgaDesiredSize);
-	PR_EEP("Chain0 xlna Gain", pModal->xlnaGainCh[0]);
-	PR_EEP("Chain1 xlna Gain", pModal->xlnaGainCh[1]);
-	PR_EEP("Chain2 xlna Gain", pModal->xlnaGainCh[2]);
-	PR_EEP("txEndToXpaOff", pModal->txEndToXpaOff);
-	PR_EEP("txEndToRxOn", pModal->txEndToRxOn);
-	PR_EEP("txFrameToXpaOn", pModal->txFrameToXpaOn);
-	PR_EEP("CCA Threshold)", pModal->thresh62);
-	PR_EEP("Chain0 NF Threshold", pModal->noiseFloorThreshCh[0]);
-	PR_EEP("Chain1 NF Threshold", pModal->noiseFloorThreshCh[1]);
-	PR_EEP("Chain2 NF Threshold", pModal->noiseFloorThreshCh[2]);
-	PR_EEP("xpdGain", pModal->xpdGain);
-	PR_EEP("External PD", pModal->xpd);
-	PR_EEP("Chain0 I Coefficient", pModal->iqCalICh[0]);
-	PR_EEP("Chain1 I Coefficient", pModal->iqCalICh[1]);
-	PR_EEP("Chain2 I Coefficient", pModal->iqCalICh[2]);
-	PR_EEP("Chain0 Q Coefficient", pModal->iqCalQCh[0]);
-	PR_EEP("Chain1 Q Coefficient", pModal->iqCalQCh[1]);
-	PR_EEP("Chain2 Q Coefficient", pModal->iqCalQCh[2]);
-	PR_EEP("pdGainOverlap", pModal->pdGainOverlap);
-	PR_EEP("Chain0 OutputBias", pModal->ob);
-	PR_EEP("Chain0 DriverBias", pModal->db);
-	PR_EEP("xPA Bias Level", pModal->xpaBiasLvl);
-	PR_EEP("2chain pwr decrease", pModal->pwrDecreaseFor2Chain);
-	PR_EEP("3chain pwr decrease", pModal->pwrDecreaseFor3Chain);
-	PR_EEP("txFrameToDataStart", pModal->txFrameToDataStart);
-	PR_EEP("txFrameToPaOn", pModal->txFrameToPaOn);
-	PR_EEP("HT40 Power Inc.", pModal->ht40PowerIncForPdadc);
-	PR_EEP("Chain0 bswAtten", pModal->bswAtten[0]);
-	PR_EEP("Chain1 bswAtten", pModal->bswAtten[1]);
-	PR_EEP("Chain2 bswAtten", pModal->bswAtten[2]);
-	PR_EEP("Chain0 bswMargin", pModal->bswMargin[0]);
-	PR_EEP("Chain1 bswMargin", pModal->bswMargin[1]);
-	PR_EEP("Chain2 bswMargin", pModal->bswMargin[2]);
-	PR_EEP("HT40 Switch Settle", pModal->swSettleHt40);
-	PR_EEP("Chain0 xatten2Db", pModal->xatten2Db[0]);
-	PR_EEP("Chain1 xatten2Db", pModal->xatten2Db[1]);
-	PR_EEP("Chain2 xatten2Db", pModal->xatten2Db[2]);
-	PR_EEP("Chain0 xatten2Margin", pModal->xatten2Margin[0]);
-	PR_EEP("Chain1 xatten2Margin", pModal->xatten2Margin[1]);
-	PR_EEP("Chain2 xatten2Margin", pModal->xatten2Margin[2]);
-	PR_EEP("Chain1 OutputBias", pModal->ob_ch1);
-	PR_EEP("Chain1 DriverBias", pModal->db_ch1);
-	PR_EEP("LNA Control", pModal->lna_ctl);
-	PR_EEP("XPA Bias Freq0", pModal->xpaBiasLvlFreq[0]);
-	PR_EEP("XPA Bias Freq1", pModal->xpaBiasLvlFreq[1]);
-	PR_EEP("XPA Bias Freq2", pModal->xpaBiasLvlFreq[2]);
-
-	if (len > size)
-		len = size;
-
-	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return retval;
-
-#undef PR_EEP
-}
-
-static ssize_t read_9287_modal_eeprom(struct file *file,
-				      char __user *user_buf,
-				      size_t count, loff_t *ppos)
-{
-#define PR_EEP(_s, _val)						\
-	do {								\
-		len += scnprintf(buf + len, size - len, "%20s : %10d\n",\
-				 _s, (_val));				\
-	} while (0)
-
-	struct ath9k_htc_priv *priv = file->private_data;
-	struct modal_eep_ar9287_header *pModal = &priv->ah->eeprom.map9287.modalHeader;
-	unsigned int len = 0, size = 3000;
-	ssize_t retval = 0;
-	char *buf;
-
-	buf = kzalloc(size, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
-
-	PR_EEP("Chain0 Ant. Control", pModal->antCtrlChain[0]);
-	PR_EEP("Chain1 Ant. Control", pModal->antCtrlChain[1]);
-	PR_EEP("Ant. Common Control", pModal->antCtrlCommon);
-	PR_EEP("Chain0 Ant. Gain", pModal->antennaGainCh[0]);
-	PR_EEP("Chain1 Ant. Gain", pModal->antennaGainCh[1]);
-	PR_EEP("Switch Settle", pModal->switchSettling);
-	PR_EEP("Chain0 TxRxAtten", pModal->txRxAttenCh[0]);
-	PR_EEP("Chain1 TxRxAtten", pModal->txRxAttenCh[1]);
-	PR_EEP("Chain0 RxTxMargin", pModal->rxTxMarginCh[0]);
-	PR_EEP("Chain1 RxTxMargin", pModal->rxTxMarginCh[1]);
-	PR_EEP("ADC Desired size", pModal->adcDesiredSize);
-	PR_EEP("txEndToXpaOff", pModal->txEndToXpaOff);
-	PR_EEP("txEndToRxOn", pModal->txEndToRxOn);
-	PR_EEP("txFrameToXpaOn", pModal->txFrameToXpaOn);
-	PR_EEP("CCA Threshold)", pModal->thresh62);
-	PR_EEP("Chain0 NF Threshold", pModal->noiseFloorThreshCh[0]);
-	PR_EEP("Chain1 NF Threshold", pModal->noiseFloorThreshCh[1]);
-	PR_EEP("xpdGain", pModal->xpdGain);
-	PR_EEP("External PD", pModal->xpd);
-	PR_EEP("Chain0 I Coefficient", pModal->iqCalICh[0]);
-	PR_EEP("Chain1 I Coefficient", pModal->iqCalICh[1]);
-	PR_EEP("Chain0 Q Coefficient", pModal->iqCalQCh[0]);
-	PR_EEP("Chain1 Q Coefficient", pModal->iqCalQCh[1]);
-	PR_EEP("pdGainOverlap", pModal->pdGainOverlap);
-	PR_EEP("xPA Bias Level", pModal->xpaBiasLvl);
-	PR_EEP("txFrameToDataStart", pModal->txFrameToDataStart);
-	PR_EEP("txFrameToPaOn", pModal->txFrameToPaOn);
-	PR_EEP("HT40 Power Inc.", pModal->ht40PowerIncForPdadc);
-	PR_EEP("Chain0 bswAtten", pModal->bswAtten[0]);
-	PR_EEP("Chain1 bswAtten", pModal->bswAtten[1]);
-	PR_EEP("Chain0 bswMargin", pModal->bswMargin[0]);
-	PR_EEP("Chain1 bswMargin", pModal->bswMargin[1]);
-	PR_EEP("HT40 Switch Settle", pModal->swSettleHt40);
-	PR_EEP("AR92x7 Version", pModal->version);
-	PR_EEP("DriverBias1", pModal->db1);
-	PR_EEP("DriverBias2", pModal->db1);
-	PR_EEP("CCK OutputBias", pModal->ob_cck);
-	PR_EEP("PSK OutputBias", pModal->ob_psk);
-	PR_EEP("QAM OutputBias", pModal->ob_qam);
-	PR_EEP("PAL_OFF OutputBias", pModal->ob_pal_off);
-
-	if (len > size)
-		len = size;
-
-	retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
-	kfree(buf);
-
-	return retval;
-
-#undef PR_EEP
-}
-
-static ssize_t read_file_modal_eeprom(struct file *file, char __user *user_buf,
-				      size_t count, loff_t *ppos)
-{
-	struct ath9k_htc_priv *priv = file->private_data;
-
-	if (AR_SREV_9271(priv->ah))
-		return read_4k_modal_eeprom(file, user_buf, count, ppos);
-	else if (priv->ah->hw_version.usbdev == AR9280_USB)
-		return read_def_modal_eeprom(file, user_buf, count, ppos);
-	else if (priv->ah->hw_version.usbdev == AR9287_USB)
-		return read_9287_modal_eeprom(file, user_buf, count, ppos);
-
-	return 0;
-}
-
-static const struct file_operations fops_modal_eeprom = {
-	.read = read_file_modal_eeprom,
-	.open = simple_open,
-	.owner = THIS_MODULE,
-	.llseek = default_llseek,
-};
-
-
 /* Ethtool support for get-stats */
 #define AMKSTR(nm) #nm "_BE", #nm "_BK", #nm "_VI", #nm "_VO"
 static const char ath9k_htc_gstrings_stats[][ETH_GSTRING_LEN] = {
@@ -947,6 +453,8 @@ int ath9k_htc_get_et_sset_count(struct ieee80211_hw *hw,
 
 #define STXBASE priv->debug.tx_stats
 #define SRXBASE priv->debug.rx_stats
+#define SKBTXBASE priv->debug.tx_stats
+#define SKBRXBASE priv->debug.skbrx_stats
 #define ASTXQ(a)					\
 	data[i++] = STXBASE.a[IEEE80211_AC_BE];		\
 	data[i++] = STXBASE.a[IEEE80211_AC_BK];		\
@@ -960,24 +468,24 @@ void ath9k_htc_get_et_stats(struct ieee80211_hw *hw,
 	struct ath9k_htc_priv *priv = hw->priv;
 	int i = 0;
 
-	data[i++] = STXBASE.skb_success;
-	data[i++] = STXBASE.skb_success_bytes;
-	data[i++] = SRXBASE.skb_completed;
-	data[i++] = SRXBASE.skb_completed_bytes;
+	data[i++] = SKBTXBASE.skb_success;
+	data[i++] = SKBTXBASE.skb_success_bytes;
+	data[i++] = SKBRXBASE.skb_completed;
+	data[i++] = SKBRXBASE.skb_completed_bytes;
 
 	ASTXQ(queue_stats);
 
-	data[i++] = SRXBASE.err_crc;
-	data[i++] = SRXBASE.err_decrypt_crc;
-	data[i++] = SRXBASE.err_phy;
-	data[i++] = SRXBASE.err_mic;
-	data[i++] = SRXBASE.err_pre_delim;
-	data[i++] = SRXBASE.err_post_delim;
-	data[i++] = SRXBASE.err_decrypt_busy;
+	data[i++] = SRXBASE.crc_err;
+	data[i++] = SRXBASE.decrypt_crc_err;
+	data[i++] = SRXBASE.phy_err;
+	data[i++] = SRXBASE.mic_err;
+	data[i++] = SRXBASE.pre_delim_crc_err;
+	data[i++] = SRXBASE.post_delim_crc_err;
+	data[i++] = SRXBASE.decrypt_busy_err;
 
-	data[i++] = SRXBASE.err_phy_stats[ATH9K_PHYERR_RADAR];
-	data[i++] = SRXBASE.err_phy_stats[ATH9K_PHYERR_OFDM_TIMING];
-	data[i++] = SRXBASE.err_phy_stats[ATH9K_PHYERR_CCK_TIMING];
+	data[i++] = SRXBASE.phy_err_stats[ATH9K_PHYERR_RADAR];
+	data[i++] = SRXBASE.phy_err_stats[ATH9K_PHYERR_OFDM_TIMING];
+	data[i++] = SRXBASE.phy_err_stats[ATH9K_PHYERR_CCK_TIMING];
 
 	WARN_ON(i != ATH9K_HTC_SSTATS_LEN);
 }
@@ -1001,18 +509,21 @@ int ath9k_htc_init_debug(struct ath_hw *ah)
 			    priv, &fops_tgt_rx_stats);
 	debugfs_create_file("xmit", S_IRUSR, priv->debug.debugfs_phy,
 			    priv, &fops_xmit);
-	debugfs_create_file("recv", S_IRUSR, priv->debug.debugfs_phy,
-			    priv, &fops_recv);
+	debugfs_create_file("skb_rx", S_IRUSR, priv->debug.debugfs_phy,
+			    priv, &fops_skb_rx);
+
+	ath9k_cmn_debug_recv(priv->debug.debugfs_phy, &priv->debug.rx_stats);
+	ath9k_cmn_debug_phy_err(priv->debug.debugfs_phy, &priv->debug.rx_stats);
+
 	debugfs_create_file("slot", S_IRUSR, priv->debug.debugfs_phy,
 			    priv, &fops_slot);
 	debugfs_create_file("queue", S_IRUSR, priv->debug.debugfs_phy,
 			    priv, &fops_queue);
 	debugfs_create_file("debug", S_IRUSR | S_IWUSR, priv->debug.debugfs_phy,
 			    priv, &fops_debug);
-	debugfs_create_file("base_eeprom", S_IRUSR, priv->debug.debugfs_phy,
-			    priv, &fops_base_eeprom);
-	debugfs_create_file("modal_eeprom", S_IRUSR, priv->debug.debugfs_phy,
-			    priv, &fops_modal_eeprom);
+
+	ath9k_cmn_debug_base_eeprom(priv->debug.debugfs_phy, priv->ah);
+	ath9k_cmn_debug_modal_eeprom(priv->debug.debugfs_phy, priv->ah);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 289f3d8924b..bb86eb2ffc9 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -996,8 +996,6 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv,
 		goto rx_next;
 	}
 
-	ath9k_htc_err_stat_rx(priv, rxstatus);
-
 	/* Get the RX status information */
 
 	memset(rx_status, 0, sizeof(struct ieee80211_rx_status));
@@ -1005,6 +1003,7 @@ static bool ath9k_rx_prepare(struct ath9k_htc_priv *priv,
 	/* Copy everything from ath_htc_rx_status (HTC_RX_FRAME_HEADER).
 	 * After this, we can drop this part of skb. */
 	rx_status_htc_to_ath(&rx_stats, rxstatus);
+	ath9k_htc_err_stat_rx(priv, &rx_stats);
 	rx_status->mactime = be64_to_cpu(rxstatus->rs_tstamp);
 	skb_pull(skb, HTC_RX_FRAME_HEADER_SIZE);
 
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index c8a9dfab1fe..2a8ed8375ec 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -26,7 +26,6 @@
 #include "ar9003_mac.h"
 #include "ar9003_mci.h"
 #include "ar9003_phy.h"
-#include "debug.h"
 #include "ath9k.h"
 
 static bool ath9k_hw_set_reset_reg(struct ath_hw *ah, u32 type);
@@ -246,6 +245,8 @@ static void ath9k_hw_read_revisions(struct ath_hw *ah)
 		return;
 	case AR9300_DEVID_AR953X:
 		ah->hw_version.macVersion = AR_SREV_VERSION_9531;
+		if (ah->get_mac_revision)
+			ah->hw_version.macRev = ah->get_mac_revision();
 		return;
 	}
 
diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index 36ae6490e55..0246b990fe8 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -61,6 +61,10 @@ static int ath9k_ps_enable;
 module_param_named(ps_enable, ath9k_ps_enable, int, 0444);
 MODULE_PARM_DESC(ps_enable, "Enable WLAN PowerSave");
 
+static int ath9k_use_chanctx;
+module_param_named(use_chanctx, ath9k_use_chanctx, int, 0444);
+MODULE_PARM_DESC(use_chanctx, "Enable channel context for concurrency");
+
 bool is_ath9k_unloaded;
 
 #ifdef CONFIG_MAC80211_LEDS
@@ -508,7 +512,7 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc,
 	sc->tx99_power = MAX_RATE_POWER + 1;
 	init_waitqueue_head(&sc->tx_wait);
 
-	if (!pdata) {
+	if (!pdata || pdata->use_eeprom) {
 		ah->ah_flags |= AH_USE_EEPROM;
 		sc->sc_ah->led_pin = -1;
 	} else {
@@ -589,6 +593,9 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc,
 	if (ret)
 		goto err_btcoex;
 
+	sc->p2p_ps_timer = ath_gen_timer_alloc(sc->sc_ah, ath9k_p2p_ps_timer,
+		NULL, sc, AR_FIRST_NDP_TIMER);
+
 	ath9k_cmn_init_crypto(sc->sc_ah);
 	ath9k_init_misc(sc);
 	ath_fill_led_pin(sc);
@@ -643,17 +650,20 @@ static void ath9k_init_txpower_limits(struct ath_softc *sc)
 }
 
 static const struct ieee80211_iface_limit if_limits[] = {
-	{ .max = 2048,	.types = BIT(NL80211_IFTYPE_STATION) |
-				 BIT(NL80211_IFTYPE_P2P_CLIENT) |
-				 BIT(NL80211_IFTYPE_WDS) },
+	{ .max = 2048,	.types = BIT(NL80211_IFTYPE_STATION) },
 	{ .max = 8,	.types =
 #ifdef CONFIG_MAC80211_MESH
 				 BIT(NL80211_IFTYPE_MESH_POINT) |
 #endif
-				 BIT(NL80211_IFTYPE_AP) |
+				 BIT(NL80211_IFTYPE_AP) },
+	{ .max = 1,	.types = BIT(NL80211_IFTYPE_P2P_CLIENT) |
 				 BIT(NL80211_IFTYPE_P2P_GO) },
 };
 
+static const struct ieee80211_iface_limit wds_limits[] = {
+	{ .max = 2048,	.types = BIT(NL80211_IFTYPE_WDS) },
+};
+
 static const struct ieee80211_iface_limit if_dfs_limits[] = {
 	{ .max = 1,	.types = BIT(NL80211_IFTYPE_AP) |
 #ifdef CONFIG_MAC80211_MESH
@@ -670,6 +680,13 @@ static const struct ieee80211_iface_combination if_comb[] = {
 		.num_different_channels = 1,
 		.beacon_int_infra_match = true,
 	},
+	{
+		.limits = wds_limits,
+		.n_limits = ARRAY_SIZE(wds_limits),
+		.max_interfaces = 2048,
+		.num_different_channels = 1,
+		.beacon_int_infra_match = true,
+	},
 #ifdef CONFIG_ATH9K_DFS_CERTIFIED
 	{
 		.limits = if_dfs_limits,
@@ -711,19 +728,23 @@ static void ath9k_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw)
 	if (AR_SREV_9160_10_OR_LATER(sc->sc_ah) || ath9k_modparam_nohwcrypt)
 		hw->flags |= IEEE80211_HW_MFP_CAPABLE;
 
-	hw->wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR;
+	hw->wiphy->features |= (NL80211_FEATURE_ACTIVE_MONITOR |
+				NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE);
 
 	if (!config_enabled(CONFIG_ATH9K_TX99)) {
 		hw->wiphy->interface_modes =
 			BIT(NL80211_IFTYPE_P2P_GO) |
 			BIT(NL80211_IFTYPE_P2P_CLIENT) |
 			BIT(NL80211_IFTYPE_AP) |
-			BIT(NL80211_IFTYPE_WDS) |
 			BIT(NL80211_IFTYPE_STATION) |
 			BIT(NL80211_IFTYPE_ADHOC) |
 			BIT(NL80211_IFTYPE_MESH_POINT);
 		hw->wiphy->iface_combinations = if_comb;
-		hw->wiphy->n_iface_combinations = ARRAY_SIZE(if_comb);
+		if (!ath9k_use_chanctx) {
+			hw->wiphy->n_iface_combinations = ARRAY_SIZE(if_comb);
+			hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_WDS);
+		} else
+			hw->wiphy->n_iface_combinations = 1;
 	}
 
 	hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -855,6 +876,9 @@ static void ath9k_deinit_softc(struct ath_softc *sc)
 {
 	int i = 0;
 
+	if (sc->p2p_ps_timer)
+		ath_gen_timer_free(sc->sc_ah, sc->p2p_ps_timer);
+
 	ath9k_deinit_btcoex(sc);
 
 	for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++)
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index 51ce36f108f..275205ab5f1 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -958,3 +958,25 @@ void ath9k_hw_set_interrupts(struct ath_hw *ah)
 	return;
 }
 EXPORT_SYMBOL(ath9k_hw_set_interrupts);
+
+#define ATH9K_HW_MAX_DCU       10
+#define ATH9K_HW_SLICE_PER_DCU 16
+#define ATH9K_HW_BIT_IN_SLICE  16
+void ath9k_hw_set_tx_filter(struct ath_hw *ah, u8 destidx, bool set)
+{
+	int dcu_idx;
+	u32 filter;
+
+	for (dcu_idx = 0; dcu_idx < 10; dcu_idx++) {
+		filter = SM(set, AR_D_TXBLK_WRITE_COMMAND);
+		filter |= SM(dcu_idx, AR_D_TXBLK_WRITE_DCU);
+		filter |= SM((destidx / ATH9K_HW_SLICE_PER_DCU),
+			     AR_D_TXBLK_WRITE_SLICE);
+		filter |= BIT(destidx % ATH9K_HW_BIT_IN_SLICE);
+		ath_dbg(ath9k_hw_common(ah), PS,
+			"DCU%d staid %d set %d txfilter %08x\n",
+			dcu_idx, destidx, set, filter);
+		REG_WRITE(ah, AR_D_TXBLK_BASE, filter);
+	}
+}
+EXPORT_SYMBOL(ath9k_hw_set_tx_filter);
diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h
index 89df634e81f..da768675753 100644
--- a/drivers/net/wireless/ath/ath9k/mac.h
+++ b/drivers/net/wireless/ath/ath9k/mac.h
@@ -729,6 +729,7 @@ void ath9k_hw_startpcureceive(struct ath_hw *ah, bool is_scanning);
 void ath9k_hw_abortpcurecv(struct ath_hw *ah);
 bool ath9k_hw_stopdmarecv(struct ath_hw *ah, bool *reset);
 int ath9k_hw_beaconq_setup(struct ath_hw *ah);
+void ath9k_hw_set_tx_filter(struct ath_hw *ah, u8 destidx, bool set);
 
 /* Interrupt Handling */
 bool ath9k_hw_intrpend(struct ath_hw *ah);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index d69853b848c..62ac95d6bb9 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -261,6 +261,8 @@ static bool ath_complete_reset(struct ath_softc *sc, bool start)
 	sc->gtt_cnt = 0;
 	ieee80211_wake_queues(sc->hw);
 
+	ath9k_p2p_ps_timer(sc);
+
 	return true;
 }
 
@@ -419,6 +421,7 @@ static void ath_node_attach(struct ath_softc *sc, struct ieee80211_sta *sta,
 	an->sc = sc;
 	an->sta = sta;
 	an->vif = vif;
+	memset(&an->key_idx, 0, sizeof(an->key_idx));
 
 	ath_tx_node_init(sc, an);
 }
@@ -1119,6 +1122,8 @@ static int ath9k_add_interface(struct ieee80211_hw *hw,
 	if (ath9k_uses_beacons(vif->type))
 		ath9k_beacon_assign_slot(sc, vif);
 
+	avp->vif = vif;
+
 	an->sc = sc;
 	an->sta = NULL;
 	an->vif = vif;
@@ -1163,6 +1168,29 @@ static int ath9k_change_interface(struct ieee80211_hw *hw,
 	return 0;
 }
 
+static void
+ath9k_update_p2p_ps_timer(struct ath_softc *sc, struct ath_vif *avp)
+{
+	struct ath_hw *ah = sc->sc_ah;
+	s32 tsf, target_tsf;
+
+	if (!avp || !avp->noa.has_next_tsf)
+		return;
+
+	ath9k_hw_gen_timer_stop(ah, sc->p2p_ps_timer);
+
+	tsf = ath9k_hw_gettsf32(sc->sc_ah);
+
+	target_tsf = avp->noa.next_tsf;
+	if (!avp->noa.absent)
+		target_tsf -= ATH_P2P_PS_STOP_TIME;
+
+	if (target_tsf - tsf < ATH_P2P_PS_STOP_TIME)
+		target_tsf = tsf + ATH_P2P_PS_STOP_TIME;
+
+	ath9k_hw_gen_timer_start(ah, sc->p2p_ps_timer, (u32) target_tsf, 1000000);
+}
+
 static void ath9k_remove_interface(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif)
 {
@@ -1174,6 +1202,13 @@ static void ath9k_remove_interface(struct ieee80211_hw *hw,
 
 	mutex_lock(&sc->mutex);
 
+	spin_lock_bh(&sc->sc_pcu_lock);
+	if (avp == sc->p2p_ps_vif) {
+		sc->p2p_ps_vif = NULL;
+		ath9k_update_p2p_ps_timer(sc, NULL);
+	}
+	spin_unlock_bh(&sc->sc_pcu_lock);
+
 	sc->nvifs--;
 	sc->tx99_vif = NULL;
 
@@ -1427,8 +1462,10 @@ static int ath9k_sta_add(struct ieee80211_hw *hw,
 		return 0;
 
 	key = ath_key_config(common, vif, sta, &ps_key);
-	if (key > 0)
+	if (key > 0) {
 		an->ps_key = key;
+		an->key_idx[0] = key;
+	}
 
 	return 0;
 }
@@ -1446,6 +1483,7 @@ static void ath9k_del_ps_key(struct ath_softc *sc,
 
 	ath_key_delete(common, &ps_key);
 	an->ps_key = 0;
+	an->key_idx[0] = 0;
 }
 
 static int ath9k_sta_remove(struct ieee80211_hw *hw,
@@ -1460,6 +1498,19 @@ static int ath9k_sta_remove(struct ieee80211_hw *hw,
 	return 0;
 }
 
+static void ath9k_sta_set_tx_filter(struct ath_hw *ah,
+				    struct ath_node *an,
+				    bool set)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(an->key_idx); i++) {
+		if (!an->key_idx[i])
+			continue;
+		ath9k_hw_set_tx_filter(ah, an->key_idx[i], set);
+	}
+}
+
 static void ath9k_sta_notify(struct ieee80211_hw *hw,
 			 struct ieee80211_vif *vif,
 			 enum sta_notify_cmd cmd,
@@ -1472,8 +1523,10 @@ static void ath9k_sta_notify(struct ieee80211_hw *hw,
 	case STA_NOTIFY_SLEEP:
 		an->sleeping = true;
 		ath_tx_aggr_sleep(sta, sc, an);
+		ath9k_sta_set_tx_filter(sc->sc_ah, an, true);
 		break;
 	case STA_NOTIFY_AWAKE:
+		ath9k_sta_set_tx_filter(sc->sc_ah, an, false);
 		an->sleeping = false;
 		ath_tx_aggr_wakeup(sc, an);
 		break;
@@ -1529,7 +1582,8 @@ static int ath9k_set_key(struct ieee80211_hw *hw,
 {
 	struct ath_softc *sc = hw->priv;
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
-	int ret = 0;
+	struct ath_node *an = NULL;
+	int ret = 0, i;
 
 	if (ath9k_modparam_nohwcrypt)
 		return -ENOSPC;
@@ -1551,13 +1605,16 @@ static int ath9k_set_key(struct ieee80211_hw *hw,
 
 	mutex_lock(&sc->mutex);
 	ath9k_ps_wakeup(sc);
-	ath_dbg(common, CONFIG, "Set HW Key\n");
+	ath_dbg(common, CONFIG, "Set HW Key %d\n", cmd);
+	if (sta)
+		an = (struct ath_node *)sta->drv_priv;
 
 	switch (cmd) {
 	case SET_KEY:
 		if (sta)
 			ath9k_del_ps_key(sc, vif, sta);
 
+		key->hw_key_idx = 0;
 		ret = ath_key_config(common, vif, sta, key);
 		if (ret >= 0) {
 			key->hw_key_idx = ret;
@@ -1570,9 +1627,27 @@ static int ath9k_set_key(struct ieee80211_hw *hw,
 				key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
 			ret = 0;
 		}
+		if (an && key->hw_key_idx) {
+			for (i = 0; i < ARRAY_SIZE(an->key_idx); i++) {
+				if (an->key_idx[i])
+					continue;
+				an->key_idx[i] = key->hw_key_idx;
+				break;
+			}
+			WARN_ON(i == ARRAY_SIZE(an->key_idx));
+		}
 		break;
 	case DISABLE_KEY:
 		ath_key_delete(common, key);
+		if (an) {
+			for (i = 0; i < ARRAY_SIZE(an->key_idx); i++) {
+				if (an->key_idx[i] != key->hw_key_idx)
+					continue;
+				an->key_idx[i] = 0;
+				break;
+			}
+		}
+		key->hw_key_idx = 0;
 		break;
 	default:
 		ret = -EINVAL;
@@ -1636,6 +1711,66 @@ static void ath9k_bss_assoc_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 		ath9k_set_assoc_state(sc, vif);
 }
 
+void ath9k_p2p_ps_timer(void *priv)
+{
+	struct ath_softc *sc = priv;
+	struct ath_vif *avp = sc->p2p_ps_vif;
+	struct ieee80211_vif *vif;
+	struct ieee80211_sta *sta;
+	struct ath_node *an;
+	u32 tsf;
+
+	if (!avp)
+		return;
+
+	tsf = ath9k_hw_gettsf32(sc->sc_ah);
+	if (!avp->noa.absent)
+		tsf += ATH_P2P_PS_STOP_TIME;
+
+	if (!avp->noa.has_next_tsf ||
+	    avp->noa.next_tsf - tsf > BIT(31))
+		ieee80211_update_p2p_noa(&avp->noa, tsf);
+
+	ath9k_update_p2p_ps_timer(sc, avp);
+
+	rcu_read_lock();
+
+	vif = avp->vif;
+	sta = ieee80211_find_sta(vif, vif->bss_conf.bssid);
+	if (!sta)
+		goto out;
+
+	an = (void *) sta->drv_priv;
+	if (an->sleeping == !!avp->noa.absent)
+		goto out;
+
+	an->sleeping = avp->noa.absent;
+	if (an->sleeping)
+		ath_tx_aggr_sleep(sta, sc, an);
+	else
+		ath_tx_aggr_wakeup(sc, an);
+
+out:
+	rcu_read_unlock();
+}
+
+void ath9k_update_p2p_ps(struct ath_softc *sc, struct ieee80211_vif *vif)
+{
+	struct ath_vif *avp = (void *)vif->drv_priv;
+	u32 tsf;
+
+	if (!sc->p2p_ps_timer)
+		return;
+
+	if (vif->type != NL80211_IFTYPE_STATION || !vif->p2p)
+		return;
+
+	sc->p2p_ps_vif = avp;
+	tsf = ath9k_hw_gettsf32(sc->sc_ah);
+	ieee80211_parse_p2p_noa(&vif->bss_conf.p2p_noa_attr, &avp->noa, tsf);
+	ath9k_update_p2p_ps_timer(sc, avp);
+}
+
 static void ath9k_bss_info_changed(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_bss_conf *bss_conf,
@@ -1650,6 +1785,7 @@ static void ath9k_bss_info_changed(struct ieee80211_hw *hw,
 	struct ath_hw *ah = sc->sc_ah;
 	struct ath_common *common = ath9k_hw_common(ah);
 	struct ath_vif *avp = (void *)vif->drv_priv;
+	unsigned long flags;
 	int slottime;
 
 	ath9k_ps_wakeup(sc);
@@ -1710,6 +1846,15 @@ static void ath9k_bss_info_changed(struct ieee80211_hw *hw,
 		}
 	}
 
+	if (changed & BSS_CHANGED_P2P_PS) {
+		spin_lock_bh(&sc->sc_pcu_lock);
+		spin_lock_irqsave(&sc->sc_pm_lock, flags);
+		if (!(sc->ps_flags & PS_BEACON_SYNC))
+			ath9k_update_p2p_ps(sc, vif);
+		spin_unlock_irqrestore(&sc->sc_pm_lock, flags);
+		spin_unlock_bh(&sc->sc_pcu_lock);
+	}
+
 	if (changed & CHECK_ANI)
 		ath_check_ani(sc);
 
@@ -1883,7 +2028,8 @@ static bool ath9k_has_tx_pending(struct ath_softc *sc)
 	return !!npend;
 }
 
-static void ath9k_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void ath9k_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			u32 queues, bool drop)
 {
 	struct ath_softc *sc = hw->priv;
 	struct ath_hw *ah = sc->sc_ah;
@@ -2084,14 +2230,6 @@ static void ath9k_sw_scan_complete(struct ieee80211_hw *hw)
 	clear_bit(ATH_OP_SCANNING, &common->op_flags);
 }
 
-static void ath9k_channel_switch_beacon(struct ieee80211_hw *hw,
-					struct ieee80211_vif *vif,
-					struct cfg80211_chan_def *chandef)
-{
-	/* depend on vif->csa_active only */
-	return;
-}
-
 struct ieee80211_ops ath9k_ops = {
 	.tx 		    = ath9k_tx,
 	.start 		    = ath9k_start,
@@ -2139,5 +2277,4 @@ struct ieee80211_ops ath9k_ops = {
 #endif
 	.sw_scan_start	    = ath9k_sw_scan_start,
 	.sw_scan_complete   = ath9k_sw_scan_complete,
-	.channel_switch_beacon     = ath9k_channel_switch_beacon,
 };
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index 914dbc6b172..4dec09e565e 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -686,7 +686,7 @@ static bool ath_pci_eeprom_read(struct ath_common *common, u32 off, u16 *data)
 	struct ath_softc *sc = (struct ath_softc *) common->priv;
 	struct ath9k_platform_data *pdata = sc->dev->platform_data;
 
-	if (pdata) {
+	if (pdata && !pdata->use_eeprom) {
 		if (off >= (ARRAY_SIZE(pdata->eeprom_data))) {
 			ath_err(common,
 				"%s: eeprom read failed, offset %08x is out of range\n",
@@ -914,6 +914,7 @@ static int ath_pci_suspend(struct device *device)
 	 */
 	ath9k_stop_btcoex(sc);
 	ath9k_hw_disable(sc->sc_ah);
+	del_timer_sync(&sc->sleep_timer);
 	ath9k_hw_setpower(sc->sc_ah, ATH9K_PM_FULL_SLEEP);
 
 	return 0;
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index 19df969ec90..9105a92364f 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -34,7 +34,8 @@ static inline bool ath9k_check_auto_sleep(struct ath_softc *sc)
  * buffer (or rx fifo). This can incorrectly acknowledge packets
  * to a sender if last desc is self-linked.
  */
-static void ath_rx_buf_link(struct ath_softc *sc, struct ath_rxbuf *bf)
+static void ath_rx_buf_link(struct ath_softc *sc, struct ath_rxbuf *bf,
+			    bool flush)
 {
 	struct ath_hw *ah = sc->sc_ah;
 	struct ath_common *common = ath9k_hw_common(ah);
@@ -59,18 +60,19 @@ static void ath_rx_buf_link(struct ath_softc *sc, struct ath_rxbuf *bf)
 			     common->rx_bufsize,
 			     0);
 
-	if (sc->rx.rxlink == NULL)
-		ath9k_hw_putrxbuf(ah, bf->bf_daddr);
-	else
+	if (sc->rx.rxlink)
 		*sc->rx.rxlink = bf->bf_daddr;
+	else if (!flush)
+		ath9k_hw_putrxbuf(ah, bf->bf_daddr);
 
 	sc->rx.rxlink = &ds->ds_link;
 }
 
-static void ath_rx_buf_relink(struct ath_softc *sc, struct ath_rxbuf *bf)
+static void ath_rx_buf_relink(struct ath_softc *sc, struct ath_rxbuf *bf,
+			      bool flush)
 {
 	if (sc->rx.buf_hold)
-		ath_rx_buf_link(sc, sc->rx.buf_hold);
+		ath_rx_buf_link(sc, sc->rx.buf_hold, flush);
 
 	sc->rx.buf_hold = bf;
 }
@@ -442,7 +444,7 @@ int ath_startrecv(struct ath_softc *sc)
 	sc->rx.buf_hold = NULL;
 	sc->rx.rxlink = NULL;
 	list_for_each_entry_safe(bf, tbf, &sc->rx.rxbuf, list) {
-		ath_rx_buf_link(sc, bf);
+		ath_rx_buf_link(sc, bf, false);
 	}
 
 	/* We could have deleted elements so the list may be empty now */
@@ -538,7 +540,10 @@ static void ath_rx_ps_beacon(struct ath_softc *sc, struct sk_buff *skb)
 		sc->ps_flags &= ~PS_BEACON_SYNC;
 		ath_dbg(common, PS,
 			"Reconfigure beacon timers based on synchronized timestamp\n");
-		ath9k_set_beacon(sc);
+		if (!(WARN_ON_ONCE(sc->cur_beacon_conf.beacon_interval == 0)))
+			ath9k_set_beacon(sc);
+		if (sc->p2p_ps_vif)
+			ath9k_update_p2p_ps(sc, sc->p2p_ps_vif->vif);
 	}
 
 	if (ath_beacon_dtim_pending_cab(skb)) {
@@ -1115,12 +1120,12 @@ requeue_drop_frag:
 requeue:
 		list_add_tail(&bf->list, &sc->rx.rxbuf);
 
-		if (edma) {
-			ath_rx_edma_buf_link(sc, qtype);
-		} else {
-			ath_rx_buf_relink(sc, bf);
+		if (!edma) {
+			ath_rx_buf_relink(sc, bf, flush);
 			if (!flush)
 				ath9k_hw_rxena(ah);
+		} else if (!flush) {
+			ath_rx_edma_buf_link(sc, qtype);
 		}
 
 		if (!budget--)
diff --git a/drivers/net/wireless/ath/ath9k/reg.h b/drivers/net/wireless/ath/ath9k/reg.h
index b1fd3fa8498..f1bbce3f777 100644
--- a/drivers/net/wireless/ath/ath9k/reg.h
+++ b/drivers/net/wireless/ath/ath9k/reg.h
@@ -505,9 +505,6 @@
 #define AR_D_QCUMASK         0x000003FF
 #define AR_D_QCUMASK_RESV0   0xFFFFFC00
 
-#define AR_D_TXBLK_CMD  0x1038
-#define AR_D_TXBLK_DATA(i) (AR_D_TXBLK_CMD+(i))
-
 #define AR_D0_LCL_IFS     0x1040
 #define AR_D1_LCL_IFS     0x1044
 #define AR_D2_LCL_IFS     0x1048
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 66acb2cbd9d..7c28cb55610 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -887,6 +887,15 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 
 		tx_info = IEEE80211_SKB_CB(skb);
 		tx_info->flags &= ~IEEE80211_TX_CTL_CLEAR_PS_FILT;
+
+		/*
+		 * No aggregation session is running, but there may be frames
+		 * from a previous session or a failed attempt in the queue.
+		 * Send them out as normal data frames
+		 */
+		if (!tid->active)
+			tx_info->flags &= ~IEEE80211_TX_CTL_AMPDU;
+
 		if (!(tx_info->flags & IEEE80211_TX_CTL_AMPDU)) {
 			bf->bf_state.bf_type = 0;
 			return bf;
diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c
index 4c8cdb097b6..f8ded84b7be 100644
--- a/drivers/net/wireless/ath/carl9170/main.c
+++ b/drivers/net/wireless/ath/carl9170/main.c
@@ -1707,7 +1707,9 @@ found:
 	return 0;
 }
 
-static void carl9170_op_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void carl9170_op_flush(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      u32 queues, bool drop)
 {
 	struct ar9170 *ar = hw->priv;
 	unsigned int vid;
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index ca115f33746..f35c7f30f9a 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -1076,8 +1076,14 @@ static int carl9170_usb_probe(struct usb_interface *intf,
 
 	carl9170_set_state(ar, CARL9170_STOPPED);
 
-	return request_firmware_nowait(THIS_MODULE, 1, CARL9170FW_NAME,
+	err = request_firmware_nowait(THIS_MODULE, 1, CARL9170FW_NAME,
 		&ar->udev->dev, GFP_KERNEL, ar, carl9170_usb_firmware_step2);
+	if (err) {
+		usb_put_dev(udev);
+		usb_put_dev(udev);
+		carl9170_free(ar);
+	}
+	return err;
 }
 
 static void carl9170_usb_disconnect(struct usb_interface *intf)
diff --git a/drivers/net/wireless/ath/dfs_pattern_detector.c b/drivers/net/wireless/ath/dfs_pattern_detector.c
index a1a69c5db40..650be79c7ac 100644
--- a/drivers/net/wireless/ath/dfs_pattern_detector.c
+++ b/drivers/net/wireless/ath/dfs_pattern_detector.c
@@ -73,9 +73,52 @@ static const struct radar_types etsi_radar_types_v15 = {
 	.radar_types		= etsi_radar_ref_types_v15,
 };
 
-/* for now, we support ETSI radar types, FCC and JP are TODO */
+#define FCC_PATTERN(ID, WMIN, WMAX, PMIN, PMAX, PRF, PPB)	\
+{								\
+	ID, WIDTH_LOWER(WMIN), WIDTH_UPPER(WMAX),		\
+	PMIN - PRI_TOLERANCE,					\
+	PMAX * PRF + PRI_TOLERANCE, PRF, PPB * PRF,		\
+	PPB_THRESH(PPB), PRI_TOLERANCE,				\
+}
+
+static const struct radar_detector_specs fcc_radar_ref_types[] = {
+	FCC_PATTERN(0, 0, 1, 1428, 1428, 1, 18),
+	FCC_PATTERN(1, 0, 5, 150, 230, 1, 23),
+	FCC_PATTERN(2, 6, 10, 200, 500, 1, 16),
+	FCC_PATTERN(3, 11, 20, 200, 500, 1, 12),
+	FCC_PATTERN(4, 50, 100, 1000, 2000, 20, 1),
+	FCC_PATTERN(5, 0, 1, 333, 333, 1, 9),
+};
+
+static const struct radar_types fcc_radar_types = {
+	.region			= NL80211_DFS_FCC,
+	.num_radar_types	= ARRAY_SIZE(fcc_radar_ref_types),
+	.radar_types		= fcc_radar_ref_types,
+};
+
+#define JP_PATTERN FCC_PATTERN
+static const struct radar_detector_specs jp_radar_ref_types[] = {
+	JP_PATTERN(0, 0, 1, 1428, 1428, 1, 18),
+	JP_PATTERN(1, 2, 3, 3846, 3846, 1, 18),
+	JP_PATTERN(2, 0, 1, 1388, 1388, 1, 18),
+	JP_PATTERN(3, 1, 2, 4000, 4000, 1, 18),
+	JP_PATTERN(4, 0, 5, 150, 230, 1, 23),
+	JP_PATTERN(5, 6, 10, 200, 500, 1, 16),
+	JP_PATTERN(6, 11, 20, 200, 500, 1, 12),
+	JP_PATTERN(7, 50, 100, 1000, 2000, 20, 1),
+	JP_PATTERN(5, 0, 1, 333, 333, 1, 9),
+};
+
+static const struct radar_types jp_radar_types = {
+	.region			= NL80211_DFS_JP,
+	.num_radar_types	= ARRAY_SIZE(jp_radar_ref_types),
+	.radar_types		= jp_radar_ref_types,
+};
+
 static const struct radar_types *dfs_domains[] = {
 	&etsi_radar_types_v15,
+	&fcc_radar_types,
+	&jp_radar_types,
 };
 
 /**
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index 7bf0ef8a1f5..63986931829 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -2068,7 +2068,7 @@ static void wcn36xx_smd_rsp_process(struct wcn36xx *wcn, void *buf, size_t len)
 		if (!msg_ind)
 			goto nomem;
 		msg_ind->msg_len = len;
-		msg_ind->msg = kmalloc(len, GFP_KERNEL);
+		msg_ind->msg = kmemdup(buf, len, GFP_KERNEL);
 		if (!msg_ind->msg) {
 			kfree(msg_ind);
 nomem:
@@ -2080,7 +2080,6 @@ nomem:
 				    msg_header->msg_type);
 			break;
 		}
-		memcpy(msg_ind->msg, buf, len);
 		mutex_lock(&wcn->hal_ind_mutex);
 		list_add_tail(&msg_ind->list, &wcn->hal_ind_queue);
 		queue_work(wcn->hal_ind_wq, &wcn->hal_ind_work);
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 4806a49cb61..820d4ebd932 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -172,7 +172,7 @@ static int wil_cid_fill_sinfo(struct wil6210_priv *wil, int cid,
 
 static int wil_cfg80211_get_station(struct wiphy *wiphy,
 				    struct net_device *ndev,
-				    u8 *mac, struct station_info *sinfo)
+				    const u8 *mac, struct station_info *sinfo)
 {
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
 	int rc;
@@ -288,6 +288,7 @@ static int wil_cfg80211_scan(struct wiphy *wiphy,
 	}
 
 	wil->scan_request = request;
+	mod_timer(&wil->scan_timer, jiffies + WIL6210_SCAN_TO);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.cmd.num_channels = 0;
@@ -671,7 +672,7 @@ static int wil_cfg80211_stop_ap(struct wiphy *wiphy,
 }
 
 static int wil_cfg80211_del_station(struct wiphy *wiphy,
-				    struct net_device *dev, u8 *mac)
+				    struct net_device *dev, const u8 *mac)
 {
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
 
diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index ecdabe4adec..8d4bc4bfb66 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -35,7 +35,7 @@ static void wil_print_vring(struct seq_file *s, struct wil6210_priv *wil,
 	void __iomem *x = wmi_addr(wil, vring->hwtail);
 
 	seq_printf(s, "VRING %s = {\n", name);
-	seq_printf(s, "  pa     = 0x%016llx\n", (unsigned long long)vring->pa);
+	seq_printf(s, "  pa     = %pad\n", &vring->pa);
 	seq_printf(s, "  va     = 0x%p\n", vring->va);
 	seq_printf(s, "  size   = %d\n", vring->size);
 	seq_printf(s, "  swtail = %d\n", vring->swtail);
@@ -473,7 +473,7 @@ static int wil_txdesc_debugfs_show(struct seq_file *s, void *data)
 			   u[0], u[1], u[2], u[3]);
 		seq_printf(s, "  DMA = 0x%08x 0x%08x 0x%08x 0x%08x\n",
 			   u[4], u[5], u[6], u[7]);
-		seq_printf(s, "  SKB = %p\n", skb);
+		seq_printf(s, "  SKB = 0x%p\n", skb);
 
 		if (skb) {
 			skb_get(skb);
diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c
index 5824cd41e4b..73593aa3cd9 100644
--- a/drivers/net/wireless/ath/wil6210/interrupt.c
+++ b/drivers/net/wireless/ath/wil6210/interrupt.c
@@ -338,7 +338,7 @@ static irqreturn_t wil6210_irq_misc_thread(int irq, void *cookie)
 	}
 
 	if (isr)
-		wil_err(wil, "un-handled MISC ISR bits 0x%08x\n", isr);
+		wil_dbg_irq(wil, "un-handled MISC ISR bits 0x%08x\n", isr);
 
 	wil->isr_misc = 0;
 
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 95f4efe9ef3..11e6d9d22ea 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -81,7 +81,7 @@ static void wil_disconnect_cid(struct wil6210_priv *wil, int cid)
 	memset(&sta->stats, 0, sizeof(sta->stats));
 }
 
-static void _wil6210_disconnect(struct wil6210_priv *wil, void *bssid)
+static void _wil6210_disconnect(struct wil6210_priv *wil, const u8 *bssid)
 {
 	int cid = -ENOENT;
 	struct net_device *ndev = wil_to_ndev(wil);
@@ -150,6 +150,15 @@ static void wil_connect_timer_fn(ulong x)
 	schedule_work(&wil->disconnect_worker);
 }
 
+static void wil_scan_timer_fn(ulong x)
+{
+	struct wil6210_priv *wil = (void *)x;
+
+	clear_bit(wil_status_fwready, &wil->status);
+	wil_err(wil, "Scan timeout detected, start fw error recovery\n");
+	schedule_work(&wil->fw_error_worker);
+}
+
 static void wil_fw_error_worker(struct work_struct *work)
 {
 	struct wil6210_priv *wil = container_of(work,
@@ -161,12 +170,30 @@ static void wil_fw_error_worker(struct work_struct *work)
 	if (no_fw_recovery)
 		return;
 
+	/* increment @recovery_count if less then WIL6210_FW_RECOVERY_TO
+	 * passed since last recovery attempt
+	 */
+	if (time_is_after_jiffies(wil->last_fw_recovery +
+				  WIL6210_FW_RECOVERY_TO))
+		wil->recovery_count++;
+	else
+		wil->recovery_count = 1; /* fw was alive for a long time */
+
+	if (wil->recovery_count > WIL6210_FW_RECOVERY_RETRIES) {
+		wil_err(wil, "too many recovery attempts (%d), giving up\n",
+			wil->recovery_count);
+		return;
+	}
+
+	wil->last_fw_recovery = jiffies;
+
 	mutex_lock(&wil->mutex);
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_MONITOR:
-		wil_info(wil, "fw error recovery started...\n");
+		wil_info(wil, "fw error recovery started (try %d)...\n",
+			 wil->recovery_count);
 		wil_reset(wil);
 
 		/* need to re-allocate Rx ring after reset */
@@ -230,6 +257,7 @@ int wil_priv_init(struct wil6210_priv *wil)
 
 	wil->pending_connect_cid = -1;
 	setup_timer(&wil->connect_timer, wil_connect_timer_fn, (ulong)wil);
+	setup_timer(&wil->scan_timer, wil_scan_timer_fn, (ulong)wil);
 
 	INIT_WORK(&wil->connect_worker, wil_connect_worker);
 	INIT_WORK(&wil->disconnect_worker, wil_disconnect_worker);
@@ -249,10 +277,12 @@ int wil_priv_init(struct wil6210_priv *wil)
 		return -EAGAIN;
 	}
 
+	wil->last_fw_recovery = jiffies;
+
 	return 0;
 }
 
-void wil6210_disconnect(struct wil6210_priv *wil, void *bssid)
+void wil6210_disconnect(struct wil6210_priv *wil, const u8 *bssid)
 {
 	del_timer_sync(&wil->connect_timer);
 	_wil6210_disconnect(wil, bssid);
@@ -260,6 +290,7 @@ void wil6210_disconnect(struct wil6210_priv *wil, void *bssid)
 
 void wil_priv_deinit(struct wil6210_priv *wil)
 {
+	del_timer_sync(&wil->scan_timer);
 	cancel_work_sync(&wil->disconnect_worker);
 	cancel_work_sync(&wil->fw_error_worker);
 	mutex_lock(&wil->mutex);
@@ -363,8 +394,8 @@ static int wil_wait_for_fw_ready(struct wil6210_priv *wil)
 		wil_err(wil, "Firmware not ready\n");
 		return -ETIME;
 	} else {
-		wil_dbg_misc(wil, "FW ready after %d ms\n",
-			     jiffies_to_msecs(to-left));
+		wil_info(wil, "FW ready after %d ms. HW version 0x%08x\n",
+			 jiffies_to_msecs(to-left), wil->hw_version);
 	}
 	return 0;
 }
@@ -391,6 +422,7 @@ int wil_reset(struct wil6210_priv *wil)
 	if (wil->scan_request) {
 		wil_dbg_misc(wil, "Abort scan_request 0x%p\n",
 			     wil->scan_request);
+		del_timer_sync(&wil->scan_timer);
 		cfg80211_scan_done(wil->scan_request, true);
 		wil->scan_request = NULL;
 	}
@@ -520,6 +552,7 @@ static int __wil_down(struct wil6210_priv *wil)
 	napi_disable(&wil->napi_tx);
 
 	if (wil->scan_request) {
+		del_timer_sync(&wil->scan_timer);
 		cfg80211_scan_done(wil->scan_request, true);
 		wil->scan_request = NULL;
 	}
diff --git a/drivers/net/wireless/ath/wil6210/netdev.c b/drivers/net/wireless/ath/wil6210/netdev.c
index fdcaeb820e7..106b6dcb773 100644
--- a/drivers/net/wireless/ath/wil6210/netdev.c
+++ b/drivers/net/wireless/ath/wil6210/netdev.c
@@ -32,12 +32,26 @@ static int wil_stop(struct net_device *ndev)
 	return wil_down(wil);
 }
 
+static int wil_change_mtu(struct net_device *ndev, int new_mtu)
+{
+	struct wil6210_priv *wil = ndev_to_wil(ndev);
+
+	if (new_mtu < 68 || new_mtu > IEEE80211_MAX_DATA_LEN_DMG)
+		return -EINVAL;
+
+	wil_dbg_misc(wil, "change MTU %d -> %d\n", ndev->mtu, new_mtu);
+	ndev->mtu = new_mtu;
+
+	return 0;
+}
+
 static const struct net_device_ops wil_netdev_ops = {
 	.ndo_open		= wil_open,
 	.ndo_stop		= wil_stop,
 	.ndo_start_xmit		= wil_start_xmit,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_mtu		= wil_change_mtu,
 };
 
 static int wil6210_netdev_poll_rx(struct napi_struct *napi, int budget)
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index f1e1bb338d6..1e2e07b9d13 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -74,8 +74,6 @@ static int wil_if_pcie_enable(struct wil6210_priv *wil)
 	if (rc)
 		goto release_irq;
 
-	wil_info(wil, "HW version: 0x%08x\n", wil->hw_version);
-
 	return 0;
 
  release_irq:
@@ -140,7 +138,7 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_release_reg;
 	}
 	/* rollback to err_iounmap */
-	dev_info(&pdev->dev, "CSR at %pR -> %p\n", &pdev->resource[0], csr);
+	dev_info(&pdev->dev, "CSR at %pR -> 0x%p\n", &pdev->resource[0], csr);
 
 	wil = wil_if_alloc(dev, csr);
 	if (IS_ERR(wil)) {
diff --git a/drivers/net/wireless/ath/wil6210/rx_reorder.c b/drivers/net/wireless/ath/wil6210/rx_reorder.c
index d04629fe053..747ae127587 100644
--- a/drivers/net/wireless/ath/wil6210/rx_reorder.c
+++ b/drivers/net/wireless/ath/wil6210/rx_reorder.c
@@ -49,10 +49,17 @@ static void wil_release_reorder_frames(struct wil6210_priv *wil,
 {
 	int index;
 
-	while (seq_less(r->head_seq_num, hseq)) {
+	/* note: this function is never called with
+	 * hseq preceding r->head_seq_num, i.e it is always true
+	 * !seq_less(hseq, r->head_seq_num)
+	 * and thus on loop exit it should be
+	 * r->head_seq_num == hseq
+	 */
+	while (seq_less(r->head_seq_num, hseq) && r->stored_mpdu_num) {
 		index = reorder_index(r, r->head_seq_num);
 		wil_release_reorder_frame(wil, r, index);
 	}
+	r->head_seq_num = hseq;
 }
 
 static void wil_reorder_release(struct wil6210_priv *wil,
@@ -91,6 +98,22 @@ void wil_rx_reorder(struct wil6210_priv *wil, struct sk_buff *skb)
 
 	spin_lock(&r->reorder_lock);
 
+	/** Due to the race between WMI events, where BACK establishment
+	 * reported, and data Rx, few packets may be pass up before reorder
+	 * buffer get allocated. Catch up by pretending SSN is what we
+	 * see in the 1-st Rx packet
+	 */
+	if (r->first_time) {
+		r->first_time = false;
+		if (seq != r->head_seq_num) {
+			wil_err(wil, "Error: 1-st frame with wrong sequence"
+				" %d, should be %d. Fixing...\n", seq,
+				r->head_seq_num);
+			r->head_seq_num = seq;
+			r->ssn = seq;
+		}
+	}
+
 	/* frame with out of date sequence number */
 	if (seq_less(seq, r->head_seq_num)) {
 		dev_kfree_skb(skb);
@@ -162,6 +185,7 @@ struct wil_tid_ampdu_rx *wil_tid_ampdu_rx_alloc(struct wil6210_priv *wil,
 	r->head_seq_num = ssn;
 	r->buf_size = size;
 	r->stored_mpdu_num = 0;
+	r->first_time = true;
 	return r;
 }
 
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index c8c547457eb..0784ef3d4ce 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -64,6 +64,22 @@ static inline int wil_vring_avail_tx(struct vring *vring)
 	return vring->size - used - 1;
 }
 
+/**
+ * wil_vring_wmark_low - low watermark for available descriptor space
+ */
+static inline int wil_vring_wmark_low(struct vring *vring)
+{
+	return vring->size/8;
+}
+
+/**
+ * wil_vring_wmark_high - high watermark for available descriptor space
+ */
+static inline int wil_vring_wmark_high(struct vring *vring)
+{
+	return vring->size/4;
+}
+
 static int wil_vring_alloc(struct wil6210_priv *wil, struct vring *vring)
 {
 	struct device *dev = wil_to_dev(wil);
@@ -98,8 +114,8 @@ static int wil_vring_alloc(struct wil6210_priv *wil, struct vring *vring)
 		_d->dma.status = TX_DMA_STATUS_DU;
 	}
 
-	wil_dbg_misc(wil, "vring[%d] 0x%p:0x%016llx 0x%p\n", vring->size,
-		     vring->va, (unsigned long long)vring->pa, vring->ctx);
+	wil_dbg_misc(wil, "vring[%d] 0x%p:%pad 0x%p\n", vring->size,
+		     vring->va, &vring->pa, vring->ctx);
 
 	return 0;
 }
@@ -880,8 +896,8 @@ static int wil_tx_vring(struct wil6210_priv *wil, struct vring *vring,
 	pa = dma_map_single(dev, skb->data,
 			skb_headlen(skb), DMA_TO_DEVICE);
 
-	wil_dbg_txrx(wil, "Tx skb %d bytes %p -> %#08llx\n", skb_headlen(skb),
-		     skb->data, (unsigned long long)pa);
+	wil_dbg_txrx(wil, "Tx skb %d bytes 0x%p -> %pad\n", skb_headlen(skb),
+		     skb->data, &pa);
 	wil_hex_dump_txrx("Tx ", DUMP_PREFIX_OFFSET, 16, 1,
 			  skb->data, skb_headlen(skb), false);
 
@@ -1007,7 +1023,7 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	rc = wil_tx_vring(wil, vring, skb);
 
 	/* do we still have enough room in the vring? */
-	if (wil_vring_avail_tx(vring) < vring->size/8)
+	if (wil_vring_avail_tx(vring) < wil_vring_wmark_low(vring))
 		netif_tx_stop_all_queues(wil_to_ndev(wil));
 
 	switch (rc) {
@@ -1116,7 +1132,7 @@ int wil_tx_complete(struct wil6210_priv *wil, int ringid)
 			done++;
 		}
 	}
-	if (wil_vring_avail_tx(vring) > vring->size/4)
+	if (wil_vring_avail_tx(vring) > wil_vring_wmark_high(vring))
 		netif_tx_wake_all_queues(wil_to_ndev(wil));
 
 	return done;
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 2a2dec75f02..e25edc52398 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -35,11 +35,14 @@ static inline u32 WIL_GET_BITS(u32 x, int b0, int b1)
 #define WIL6210_MEM_SIZE (2*1024*1024UL)
 
 #define WIL6210_RX_RING_SIZE	(128)
-#define WIL6210_TX_RING_SIZE	(128)
+#define WIL6210_TX_RING_SIZE	(512)
 #define WIL6210_MAX_TX_RINGS	(24) /* HW limit */
 #define WIL6210_MAX_CID		(8) /* HW limit */
 #define WIL6210_NAPI_BUDGET	(16) /* arbitrary */
 #define WIL6210_ITR_TRSH	(10000) /* arbitrary - about 15 IRQs/msec */
+#define WIL6210_FW_RECOVERY_RETRIES	(5) /* try to recover this many times */
+#define WIL6210_FW_RECOVERY_TO	msecs_to_jiffies(5000)
+#define WIL6210_SCAN_TO		msecs_to_jiffies(10000)
 
 /* Hardware definitions begin */
 
@@ -301,6 +304,7 @@ struct wil_tid_ampdu_rx {
 	u16 buf_size;
 	u16 timeout;
 	u8 dialog_token;
+	bool first_time; /* is it 1-st time this buffer used? */
 };
 
 struct wil6210_stats {
@@ -360,6 +364,8 @@ struct wil6210_priv {
 	u32 fw_version;
 	u32 hw_version;
 	u8 n_mids; /* number of additional MIDs as reported by FW */
+	int recovery_count; /* num of FW recovery attempts in a short time */
+	unsigned long last_fw_recovery; /* jiffies of last fw recovery */
 	/* profile */
 	u32 monitor_flags;
 	u32 secure_pcp; /* create secure PCP? */
@@ -381,6 +387,7 @@ struct wil6210_priv {
 	struct work_struct disconnect_worker;
 	struct work_struct fw_error_worker;	/* for FW error recovery */
 	struct timer_list connect_timer;
+	struct timer_list scan_timer; /* detect scan timeout */
 	int pending_connect_cid;
 	struct list_head pending_wmi_ev;
 	/*
@@ -507,7 +514,7 @@ void wil_wdev_free(struct wil6210_priv *wil);
 int wmi_set_mac_address(struct wil6210_priv *wil, void *addr);
 int wmi_pcp_start(struct wil6210_priv *wil, int bi, u8 wmi_nettype, u8 chan);
 int wmi_pcp_stop(struct wil6210_priv *wil);
-void wil6210_disconnect(struct wil6210_priv *wil, void *bssid);
+void wil6210_disconnect(struct wil6210_priv *wil, const u8 *bssid);
 
 int wil_rx_init(struct wil6210_priv *wil);
 void wil_rx_fini(struct wil6210_priv *wil);
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 2ba56eef0c4..6cc0e182cc7 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -192,7 +192,7 @@ static int __wmi_send(struct wil6210_priv *wil, u16 cmdid, void *buf, u16 len)
 	might_sleep();
 
 	if (!test_bit(wil_status_fwready, &wil->status)) {
-		wil_err(wil, "FW not ready\n");
+		wil_err(wil, "WMI: cannot send command while FW not ready\n");
 		return -EAGAIN;
 	}
 
@@ -276,8 +276,8 @@ static void wmi_evt_ready(struct wil6210_priv *wil, int id, void *d, int len)
 	wil->fw_version = le32_to_cpu(evt->sw_version);
 	wil->n_mids = evt->numof_additional_mids;
 
-	wil_dbg_wmi(wil, "FW ver. %d; MAC %pM; %d MID's\n", wil->fw_version,
-		    evt->mac, wil->n_mids);
+	wil_info(wil, "FW ver. %d; MAC %pM; %d MID's\n", wil->fw_version,
+		 evt->mac, wil->n_mids);
 
 	if (!is_valid_ether_addr(ndev->dev_addr)) {
 		memcpy(ndev->dev_addr, evt->mac, ETH_ALEN);
@@ -290,7 +290,7 @@ static void wmi_evt_ready(struct wil6210_priv *wil, int id, void *d, int len)
 static void wmi_evt_fw_ready(struct wil6210_priv *wil, int id, void *d,
 			     int len)
 {
-	wil_dbg_wmi(wil, "WMI: FW ready\n");
+	wil_dbg_wmi(wil, "WMI: got FW ready event\n");
 
 	set_bit(wil_status_fwready, &wil->status);
 	/* reuse wmi_ready for the firmware ready indication */
@@ -348,9 +348,10 @@ static void wmi_evt_scan_complete(struct wil6210_priv *wil, int id,
 {
 	if (wil->scan_request) {
 		struct wmi_scan_complete_event *data = d;
-		bool aborted = (data->status != 0);
+		bool aborted = (data->status != WMI_SCAN_SUCCESS);
 
 		wil_dbg_wmi(wil, "SCAN_COMPLETE(0x%08x)\n", data->status);
+		del_timer_sync(&wil->scan_timer);
 		cfg80211_scan_done(wil->scan_request, aborted);
 		wil->scan_request = NULL;
 	} else {
@@ -658,21 +659,27 @@ void wmi_recv_cmd(struct wil6210_priv *wil)
 	u8 *cmd;
 	void __iomem *src;
 	ulong flags;
+	unsigned n;
 
 	if (!test_bit(wil_status_reset_done, &wil->status)) {
 		wil_err(wil, "Reset not completed\n");
 		return;
 	}
 
-	for (;;) {
+	for (n = 0;; n++) {
 		u16 len;
 
 		r->head = ioread32(wil->csr + HOST_MBOX +
 				   offsetof(struct wil6210_mbox_ctl, rx.head));
-		if (r->tail == r->head)
+		if (r->tail == r->head) {
+			if (n == 0)
+				wil_dbg_wmi(wil, "No events?\n");
 			return;
+		}
 
-		/* read cmd from tail */
+		wil_dbg_wmi(wil, "Mbox head %08x tail %08x\n",
+			    r->head, r->tail);
+		/* read cmd descriptor from tail */
 		wil_memcpy_fromio_32(&d_tail, wil->csr + HOSTADDR(r->tail),
 				     sizeof(struct wil6210_mbox_ring_desc));
 		if (d_tail.sync == 0) {
@@ -680,13 +687,18 @@ void wmi_recv_cmd(struct wil6210_priv *wil)
 			return;
 		}
 
+		/* read cmd header from descriptor */
 		if (0 != wmi_read_hdr(wil, d_tail.addr, &hdr)) {
 			wil_err(wil, "Mbox evt at 0x%08x?\n",
 				le32_to_cpu(d_tail.addr));
 			return;
 		}
-
 		len = le16_to_cpu(hdr.len);
+		wil_dbg_wmi(wil, "Mbox evt %04x %04x %04x %02x\n",
+			    le16_to_cpu(hdr.seq), len, le16_to_cpu(hdr.type),
+			    hdr.flags);
+
+		/* read cmd buffer from descriptor */
 		src = wmi_buffer(wil, d_tail.addr) +
 		      sizeof(struct wil6210_mbox_hdr);
 		evt = kmalloc(ALIGN(offsetof(struct pending_wmi_event,
@@ -702,9 +714,6 @@ void wmi_recv_cmd(struct wil6210_priv *wil)
 		iowrite32(0, wil->csr + HOSTADDR(r->tail) +
 			  offsetof(struct wil6210_mbox_ring_desc, sync));
 		/* indicate */
-		wil_dbg_wmi(wil, "Mbox evt %04x %04x %04x %02x\n",
-			    le16_to_cpu(hdr.seq), len, le16_to_cpu(hdr.type),
-			    hdr.flags);
 		if ((hdr.type == WIL_MBOX_HDR_TYPE_WMI) &&
 		    (len >= sizeof(struct wil6210_mbox_hdr_wmi))) {
 			struct wil6210_mbox_hdr_wmi *wmi = &evt->event.wmi;
@@ -734,6 +743,8 @@ void wmi_recv_cmd(struct wil6210_priv *wil)
 			wil_dbg_wmi(wil, "queue_work -> %d\n", q);
 		}
 	}
+	if (n > 1)
+		wil_dbg_wmi(wil, "%s -> %d events processed\n", __func__, n);
 }
 
 int wmi_call(struct wil6210_priv *wil, u16 cmdid, void *buf, u16 len,
@@ -802,6 +813,7 @@ int wmi_pcp_start(struct wil6210_priv *wil, int bi, u8 wmi_nettype, u8 chan)
 		.network_type = wmi_nettype,
 		.disable_sec_offload = 1,
 		.channel = chan - 1,
+		.pcp_max_assoc_sta = WIL6210_MAX_CID,
 	};
 	struct {
 		struct wil6210_mbox_hdr_wmi wmi;
diff --git a/drivers/net/wireless/ath/wil6210/wmi.h b/drivers/net/wireless/ath/wil6210/wmi.h
index 50b8528394f..17334c85286 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.h
+++ b/drivers/net/wireless/ath/wil6210/wmi.h
@@ -28,7 +28,7 @@
 #define __WILOCITY_WMI_H__
 
 /* General */
-
+#define WILOCITY_MAX_ASSOC_STA (8)
 #define WMI_MAC_LEN		(6)
 #define WMI_PROX_RANGE_NUM	(3)
 
@@ -219,15 +219,6 @@ struct wmi_disconnect_sta_cmd {
 	__le16 disconnect_reason;
 } __packed;
 
-/*
- * WMI_RECONNECT_CMDID
- */
-struct wmi_reconnect_cmd {
-	u8 channel;			/* hint */
-	u8 reserved;
-	u8 bssid[WMI_MAC_LEN];		/* mandatory if set */
-} __packed;
-
 
 /*
  * WMI_SET_PMK_CMDID
@@ -296,11 +287,13 @@ enum wmi_scan_type {
 	WMI_LONG_SCAN		= 0,
 	WMI_SHORT_SCAN		= 1,
 	WMI_PBC_SCAN		= 2,
+	WMI_ACTIVE_SCAN		= 3,
+	WMI_DIRECT_SCAN		= 4,
 };
 
 struct wmi_start_scan_cmd {
-	u8 reserved[8];
-
+	u8 direct_scan_mac_addr[6];
+	u8 reserved[2];
 	__le32 home_dwell_time;	/* Max duration in the home channel(ms) */
 	__le32 force_scan_interval;	/* Time interval between scans (ms)*/
 	u8 scan_type;		/* wmi_scan_type */
@@ -332,6 +325,7 @@ struct wmi_probed_ssid_cmd {
 	u8 ssid[WMI_MAX_SSID_LEN];
 } __packed;
 
+
 /*
  * WMI_SET_APPIE_CMDID
  * Add Application specified IE to a management frame
@@ -427,7 +421,7 @@ struct wmi_bcon_ctrl_cmd {
 	__le16 frag_num;
 	__le64 ss_mask;
 	u8 network_type;
-	u8 reserved;
+	u8 pcp_max_assoc_sta;
 	u8 disable_sec_offload;
 	u8 disable_sec;
 } __packed;
@@ -450,7 +444,7 @@ enum wmi_port_role {
 struct wmi_port_allocate_cmd {
 	u8 mac[WMI_MAC_LEN];
 	u8 port_role;
-	u8 midid;
+	u8 mid;
 } __packed;
 
 /*
@@ -467,6 +461,7 @@ struct wmi_delete_port_cmd {
 enum wmi_discovery_mode {
 	WMI_DISCOVERY_MODE_NON_OFFLOAD	= 0,
 	WMI_DISCOVERY_MODE_OFFLOAD	= 1,
+	WMI_DISCOVERY_MODE_PEER2PEER	= 2,
 };
 
 struct wmi_p2p_cfg_cmd {
@@ -493,7 +488,8 @@ struct wmi_power_mgmt_cfg_cmd {
  */
 struct wmi_pcp_start_cmd {
 	__le16 bcon_interval;
-	u8 reserved0[10];
+	u8 pcp_max_assoc_sta;
+	u8 reserved0[9];
 	u8 network_type;
 	u8 channel;
 	u8 disable_sec_offload;
@@ -857,6 +853,7 @@ enum wmi_event_id {
 	WMI_RF_MGMT_STATUS_EVENTID		= 0x1853,
 	WMI_BF_SM_MGMT_DONE_EVENTID		= 0x1838,
 	WMI_RX_MGMT_PACKET_EVENTID		= 0x1840,
+	WMI_TX_MGMT_PACKET_EVENTID		= 0x1841,
 
 	/* Performance monitoring events */
 	WMI_DATA_PORT_OPEN_EVENTID		= 0x1860,
@@ -1040,16 +1037,23 @@ enum wmi_disconnect_reason {
 struct wmi_disconnect_event {
 	__le16 protocol_reason_status;	/* reason code, see 802.11 spec. */
 	u8 bssid[WMI_MAC_LEN];		/* set if known */
-	u8 disconnect_reason;		/* see wmi_disconnect_reason_e */
-	u8 assoc_resp_len;
-	u8 assoc_info[0];
+	u8 disconnect_reason;		/* see wmi_disconnect_reason */
+	u8 assoc_resp_len;		/* not in use */
+	u8 assoc_info[0];		/* not in use */
 } __packed;
 
 /*
  * WMI_SCAN_COMPLETE_EVENTID
  */
+enum scan_status {
+	WMI_SCAN_SUCCESS	= 0,
+	WMI_SCAN_FAILED		= 1,
+	WMI_SCAN_ABORTED	= 2,
+	WMI_SCAN_REJECTED	= 3,
+};
+
 struct wmi_scan_complete_event {
-	__le32 status;
+	__le32 status;	/* scan_status */
 } __packed;
 
 /*
@@ -1256,6 +1260,14 @@ struct wmi_rx_mgmt_info {
 	u8 channel;	/* From Radio MNGR */
 } __packed;
 
+
+/*
+ * WMI_TX_MGMT_PACKET_EVENTID
+ */
+struct wmi_tx_mgmt_packet_event {
+	u8 payload[0];
+} __packed;
+
 struct wmi_rx_mgmt_packet_event {
 	struct wmi_rx_mgmt_info info;
 	u8 payload[0];
diff --git a/drivers/net/wireless/b43/Kconfig b/drivers/net/wireless/b43/Kconfig
index 088d544ec63..40fd9b7b142 100644
--- a/drivers/net/wireless/b43/Kconfig
+++ b/drivers/net/wireless/b43/Kconfig
@@ -1,7 +1,8 @@
 config B43
 	tristate "Broadcom 43xx wireless support (mac80211 stack)"
-	depends on SSB_POSSIBLE && MAC80211 && HAS_DMA
-	select SSB
+	depends on (BCMA_POSSIBLE || SSB_POSSIBLE) && MAC80211 && HAS_DMA
+	select BCMA if B43_BCMA
+	select SSB if B43_SSB
 	select FW_LOADER
 	---help---
 	  b43 is a driver for the Broadcom 43xx series wireless devices.
@@ -27,14 +28,33 @@ config B43
 	  If unsure, say M.
 
 config B43_BCMA
-	bool "Support for BCMA bus"
-	depends on B43 && (BCMA = y || BCMA = B43)
-	default y
+	bool
 
 config B43_SSB
 	bool
-	depends on B43 && (SSB = y || SSB = B43)
-	default y
+
+choice
+	prompt "Supported bus types"
+	depends on B43
+	default B43_BUSES_BCMA_AND_SSB
+
+config B43_BUSES_BCMA_AND_SSB
+	bool "BCMA and SSB"
+	depends on BCMA_POSSIBLE && SSB_POSSIBLE
+	select B43_BCMA
+	select B43_SSB
+
+config B43_BUSES_BCMA
+	bool "BCMA only"
+	depends on BCMA_POSSIBLE
+	select B43_BCMA
+
+config B43_BUSES_SSB
+	bool "SSB only"
+	depends on SSB_POSSIBLE
+	select B43_SSB
+
+endchoice
 
 # Auto-select SSB PCI-HOST support, if possible
 config B43_PCI_AUTOSELECT
@@ -53,7 +73,7 @@ config B43_PCICORE_AUTOSELECT
 
 config B43_PCMCIA
 	bool "Broadcom 43xx PCMCIA device support"
-	depends on B43 && SSB_PCMCIAHOST_POSSIBLE
+	depends on B43 && B43_SSB && SSB_PCMCIAHOST_POSSIBLE
 	select SSB_PCMCIAHOST
 	---help---
 	  Broadcom 43xx PCMCIA device support.
@@ -73,7 +93,7 @@ config B43_PCMCIA
 
 config B43_SDIO
 	bool "Broadcom 43xx SDIO device support"
-	depends on B43 && SSB_SDIOHOST_POSSIBLE
+	depends on B43 && B43_SSB && SSB_SDIOHOST_POSSIBLE
 	select SSB_SDIOHOST
 	---help---
 	  Broadcom 43xx device support for Soft-MAC SDIO devices.
@@ -98,7 +118,7 @@ config B43_BCMA_PIO
 
 config B43_PIO
 	bool
-	depends on B43
+	depends on B43 && B43_SSB
 	select SSB_BLOCKIO
 	default y
 
@@ -116,7 +136,7 @@ config B43_PHY_N
 
 config B43_PHY_LP
 	bool "Support for low-power (LP-PHY) devices"
-	depends on B43
+	depends on B43 && B43_SSB
 	default y
 	---help---
 	  Support for the LP-PHY.
diff --git a/drivers/net/wireless/b43/b43.h b/drivers/net/wireless/b43/b43.h
index 54376fddfaf..4113b693476 100644
--- a/drivers/net/wireless/b43/b43.h
+++ b/drivers/net/wireless/b43/b43.h
@@ -915,10 +915,6 @@ struct b43_wl {
 	char rng_name[30 + 1];
 #endif /* CONFIG_B43_HWRNG */
 
-	/* List of all wireless devices on this chip */
-	struct list_head devlist;
-	u8 nr_devs;
-
 	bool radiotap_enabled;
 	bool radio_enabled;
 
diff --git a/drivers/net/wireless/b43/bus.h b/drivers/net/wireless/b43/bus.h
index 184c9565927..f3205c6988b 100644
--- a/drivers/net/wireless/b43/bus.h
+++ b/drivers/net/wireless/b43/bus.h
@@ -5,7 +5,9 @@ enum b43_bus_type {
 #ifdef CONFIG_B43_BCMA
 	B43_BUS_BCMA,
 #endif
+#ifdef CONFIG_B43_SSB
 	B43_BUS_SSB,
+#endif
 };
 
 struct b43_bus_dev {
@@ -52,13 +54,21 @@ struct b43_bus_dev {
 
 static inline bool b43_bus_host_is_pcmcia(struct b43_bus_dev *dev)
 {
+#ifdef CONFIG_B43_SSB
 	return (dev->bus_type == B43_BUS_SSB &&
 		dev->sdev->bus->bustype == SSB_BUSTYPE_PCMCIA);
+#else
+	return false;
+#endif
 }
 static inline bool b43_bus_host_is_sdio(struct b43_bus_dev *dev)
 {
+#ifdef CONFIG_B43_SSB
 	return (dev->bus_type == B43_BUS_SSB &&
 		dev->sdev->bus->bustype == SSB_BUSTYPE_SDIO);
+#else
+	return false;
+#endif
 }
 
 struct b43_bus_dev *b43_bus_dev_bcma_init(struct bcma_device *core);
diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c
index 69fc3d65531..0d6a0bb1f87 100644
--- a/drivers/net/wireless/b43/main.c
+++ b/drivers/net/wireless/b43/main.c
@@ -182,7 +182,7 @@ static struct ieee80211_rate __b43_ratetable[] = {
 #define b43_g_ratetable		(__b43_ratetable + 0)
 #define b43_g_ratetable_size	12
 
-#define CHAN4G(_channel, _freq, _flags) {			\
+#define CHAN2G(_channel, _freq, _flags) {			\
 	.band			= IEEE80211_BAND_2GHZ,		\
 	.center_freq		= (_freq),			\
 	.hw_value		= (_channel),			\
@@ -191,23 +191,31 @@ static struct ieee80211_rate __b43_ratetable[] = {
 	.max_power		= 30,				\
 }
 static struct ieee80211_channel b43_2ghz_chantable[] = {
-	CHAN4G(1, 2412, 0),
-	CHAN4G(2, 2417, 0),
-	CHAN4G(3, 2422, 0),
-	CHAN4G(4, 2427, 0),
-	CHAN4G(5, 2432, 0),
-	CHAN4G(6, 2437, 0),
-	CHAN4G(7, 2442, 0),
-	CHAN4G(8, 2447, 0),
-	CHAN4G(9, 2452, 0),
-	CHAN4G(10, 2457, 0),
-	CHAN4G(11, 2462, 0),
-	CHAN4G(12, 2467, 0),
-	CHAN4G(13, 2472, 0),
-	CHAN4G(14, 2484, 0),
+	CHAN2G(1, 2412, 0),
+	CHAN2G(2, 2417, 0),
+	CHAN2G(3, 2422, 0),
+	CHAN2G(4, 2427, 0),
+	CHAN2G(5, 2432, 0),
+	CHAN2G(6, 2437, 0),
+	CHAN2G(7, 2442, 0),
+	CHAN2G(8, 2447, 0),
+	CHAN2G(9, 2452, 0),
+	CHAN2G(10, 2457, 0),
+	CHAN2G(11, 2462, 0),
+	CHAN2G(12, 2467, 0),
+	CHAN2G(13, 2472, 0),
+	CHAN2G(14, 2484, 0),
 };
-#undef CHAN4G
+#undef CHAN2G
 
+#define CHAN4G(_channel, _flags) {				\
+	.band			= IEEE80211_BAND_5GHZ,		\
+	.center_freq		= 4000 + (5 * (_channel)),	\
+	.hw_value		= (_channel),			\
+	.flags			= (_flags),			\
+	.max_antenna_gain	= 0,				\
+	.max_power		= 30,				\
+}
 #define CHAN5G(_channel, _flags) {				\
 	.band			= IEEE80211_BAND_5GHZ,		\
 	.center_freq		= 5000 + (5 * (_channel)),	\
@@ -217,6 +225,18 @@ static struct ieee80211_channel b43_2ghz_chantable[] = {
 	.max_power		= 30,				\
 }
 static struct ieee80211_channel b43_5ghz_nphy_chantable[] = {
+	CHAN4G(184, 0),		CHAN4G(186, 0),
+	CHAN4G(188, 0),		CHAN4G(190, 0),
+	CHAN4G(192, 0),		CHAN4G(194, 0),
+	CHAN4G(196, 0),		CHAN4G(198, 0),
+	CHAN4G(200, 0),		CHAN4G(202, 0),
+	CHAN4G(204, 0),		CHAN4G(206, 0),
+	CHAN4G(208, 0),		CHAN4G(210, 0),
+	CHAN4G(212, 0),		CHAN4G(214, 0),
+	CHAN4G(216, 0),		CHAN4G(218, 0),
+	CHAN4G(220, 0),		CHAN4G(222, 0),
+	CHAN4G(224, 0),		CHAN4G(226, 0),
+	CHAN4G(228, 0),
 	CHAN5G(32, 0),		CHAN5G(34, 0),
 	CHAN5G(36, 0),		CHAN5G(38, 0),
 	CHAN5G(40, 0),		CHAN5G(42, 0),
@@ -260,18 +280,7 @@ static struct ieee80211_channel b43_5ghz_nphy_chantable[] = {
 	CHAN5G(170, 0),		CHAN5G(172, 0),
 	CHAN5G(174, 0),		CHAN5G(176, 0),
 	CHAN5G(178, 0),		CHAN5G(180, 0),
-	CHAN5G(182, 0),		CHAN5G(184, 0),
-	CHAN5G(186, 0),		CHAN5G(188, 0),
-	CHAN5G(190, 0),		CHAN5G(192, 0),
-	CHAN5G(194, 0),		CHAN5G(196, 0),
-	CHAN5G(198, 0),		CHAN5G(200, 0),
-	CHAN5G(202, 0),		CHAN5G(204, 0),
-	CHAN5G(206, 0),		CHAN5G(208, 0),
-	CHAN5G(210, 0),		CHAN5G(212, 0),
-	CHAN5G(214, 0),		CHAN5G(216, 0),
-	CHAN5G(218, 0),		CHAN5G(220, 0),
-	CHAN5G(222, 0),		CHAN5G(224, 0),
-	CHAN5G(226, 0),		CHAN5G(228, 0),
+	CHAN5G(182, 0),
 };
 
 static struct ieee80211_channel b43_5ghz_aphy_chantable[] = {
@@ -295,6 +304,7 @@ static struct ieee80211_channel b43_5ghz_aphy_chantable[] = {
 	CHAN5G(208, 0),		CHAN5G(212, 0),
 	CHAN5G(216, 0),
 };
+#undef CHAN4G
 #undef CHAN5G
 
 static struct ieee80211_supported_band b43_band_5GHz_nphy = {
@@ -1175,18 +1185,7 @@ static void b43_bcma_phy_reset(struct b43_wldev *dev)
 	bcma_awrite32(dev->dev->bdev, BCMA_IOCTL, flags);
 	udelay(2);
 
-	/* Take PHY out of reset */
-	flags = bcma_aread32(dev->dev->bdev, BCMA_IOCTL);
-	flags &= ~B43_BCMA_IOCTL_PHY_RESET;
-	flags |= BCMA_IOCTL_FGC;
-	bcma_awrite32(dev->dev->bdev, BCMA_IOCTL, flags);
-	udelay(1);
-
-	/* Do not force clock anymore */
-	flags = bcma_aread32(dev->dev->bdev, BCMA_IOCTL);
-	flags &= ~BCMA_IOCTL_FGC;
-	bcma_awrite32(dev->dev->bdev, BCMA_IOCTL, flags);
-	udelay(1);
+	b43_phy_take_out_of_reset(dev);
 }
 
 static void b43_bcma_wireless_core_reset(struct b43_wldev *dev, bool gmode)
@@ -1195,18 +1194,22 @@ static void b43_bcma_wireless_core_reset(struct b43_wldev *dev, bool gmode)
 		  B43_BCMA_CLKCTLST_PHY_PLL_REQ;
 	u32 status = B43_BCMA_CLKCTLST_80211_PLL_ST |
 		     B43_BCMA_CLKCTLST_PHY_PLL_ST;
+	u32 flags;
+
+	flags = B43_BCMA_IOCTL_PHY_CLKEN;
+	if (gmode)
+		flags |= B43_BCMA_IOCTL_GMODE;
+	b43_device_enable(dev, flags);
 
-	b43_device_enable(dev, B43_BCMA_IOCTL_PHY_CLKEN);
 	bcma_core_set_clockmode(dev->dev->bdev, BCMA_CLKMODE_FAST);
 	b43_bcma_phy_reset(dev);
 	bcma_core_pll_ctl(dev->dev->bdev, req, status, true);
 }
 #endif
 
+#ifdef CONFIG_B43_SSB
 static void b43_ssb_wireless_core_reset(struct b43_wldev *dev, bool gmode)
 {
-	struct ssb_device *sdev = dev->dev->sdev;
-	u32 tmslow;
 	u32 flags = 0;
 
 	if (gmode)
@@ -1218,18 +1221,9 @@ static void b43_ssb_wireless_core_reset(struct b43_wldev *dev, bool gmode)
 	b43_device_enable(dev, flags);
 	msleep(2);		/* Wait for the PLL to turn on. */
 
-	/* Now take the PHY out of Reset again */
-	tmslow = ssb_read32(sdev, SSB_TMSLOW);
-	tmslow |= SSB_TMSLOW_FGC;
-	tmslow &= ~B43_TMSLOW_PHYRESET;
-	ssb_write32(sdev, SSB_TMSLOW, tmslow);
-	ssb_read32(sdev, SSB_TMSLOW);	/* flush */
-	msleep(1);
-	tmslow &= ~SSB_TMSLOW_FGC;
-	ssb_write32(sdev, SSB_TMSLOW, tmslow);
-	ssb_read32(sdev, SSB_TMSLOW);	/* flush */
-	msleep(1);
+	b43_phy_take_out_of_reset(dev);
 }
+#endif
 
 void b43_wireless_core_reset(struct b43_wldev *dev, bool gmode)
 {
@@ -2704,32 +2698,37 @@ static int b43_upload_initvals(struct b43_wldev *dev)
 	struct b43_firmware *fw = &dev->fw;
 	const struct b43_iv *ivals;
 	size_t count;
-	int err;
 
 	hdr = (const struct b43_fw_header *)(fw->initvals.data->data);
 	ivals = (const struct b43_iv *)(fw->initvals.data->data + hdr_len);
 	count = be32_to_cpu(hdr->size);
-	err = b43_write_initvals(dev, ivals, count,
+	return b43_write_initvals(dev, ivals, count,
 				 fw->initvals.data->size - hdr_len);
-	if (err)
-		goto out;
-	if (fw->initvals_band.data) {
-		hdr = (const struct b43_fw_header *)(fw->initvals_band.data->data);
-		ivals = (const struct b43_iv *)(fw->initvals_band.data->data + hdr_len);
-		count = be32_to_cpu(hdr->size);
-		err = b43_write_initvals(dev, ivals, count,
-					 fw->initvals_band.data->size - hdr_len);
-		if (err)
-			goto out;
-	}
-out:
+}
 
-	return err;
+static int b43_upload_initvals_band(struct b43_wldev *dev)
+{
+	const size_t hdr_len = sizeof(struct b43_fw_header);
+	const struct b43_fw_header *hdr;
+	struct b43_firmware *fw = &dev->fw;
+	const struct b43_iv *ivals;
+	size_t count;
+
+	if (!fw->initvals_band.data)
+		return 0;
+
+	hdr = (const struct b43_fw_header *)(fw->initvals_band.data->data);
+	ivals = (const struct b43_iv *)(fw->initvals_band.data->data + hdr_len);
+	count = be32_to_cpu(hdr->size);
+	return b43_write_initvals(dev, ivals, count,
+				  fw->initvals_band.data->size - hdr_len);
 }
 
 /* Initialize the GPIOs
  * http://bcm-specs.sipsolutions.net/GPIO
  */
+
+#ifdef CONFIG_B43_SSB
 static struct ssb_device *b43_ssb_gpio_dev(struct b43_wldev *dev)
 {
 	struct ssb_bus *bus = dev->dev->sdev->bus;
@@ -2740,10 +2739,13 @@ static struct ssb_device *b43_ssb_gpio_dev(struct b43_wldev *dev)
 	return bus->chipco.dev;
 #endif
 }
+#endif
 
 static int b43_gpio_init(struct b43_wldev *dev)
 {
+#ifdef CONFIG_B43_SSB
 	struct ssb_device *gpiodev;
+#endif
 	u32 mask, set;
 
 	b43_maskset32(dev, B43_MMIO_MACCTL, ~B43_MACCTL_GPOUTSMSK, 0);
@@ -2802,7 +2804,9 @@ static int b43_gpio_init(struct b43_wldev *dev)
 /* Turn off all GPIO stuff. Call this on module unload, for example. */
 static void b43_gpio_cleanup(struct b43_wldev *dev)
 {
+#ifdef CONFIG_B43_SSB
 	struct ssb_device *gpiodev;
+#endif
 
 	switch (dev->dev->bus_type) {
 #ifdef CONFIG_B43_BCMA
@@ -3086,6 +3090,10 @@ static int b43_chip_init(struct b43_wldev *dev)
 	if (err)
 		goto err_gpio_clean;
 
+	err = b43_upload_initvals_band(dev);
+	if (err)
+		goto err_gpio_clean;
+
 	/* Turn the Analog on and initialize the PHY. */
 	phy->ops->switch_analog(dev, 1);
 	err = b43_phy_init(dev);
@@ -3685,37 +3693,6 @@ static void b43_op_set_tsf(struct ieee80211_hw *hw,
 	mutex_unlock(&wl->mutex);
 }
 
-static void b43_put_phy_into_reset(struct b43_wldev *dev)
-{
-	u32 tmp;
-
-	switch (dev->dev->bus_type) {
-#ifdef CONFIG_B43_BCMA
-	case B43_BUS_BCMA:
-		b43err(dev->wl,
-		       "Putting PHY into reset not supported on BCMA\n");
-		break;
-#endif
-#ifdef CONFIG_B43_SSB
-	case B43_BUS_SSB:
-		tmp = ssb_read32(dev->dev->sdev, SSB_TMSLOW);
-		tmp &= ~B43_TMSLOW_GMODE;
-		tmp |= B43_TMSLOW_PHYRESET;
-		tmp |= SSB_TMSLOW_FGC;
-		ssb_write32(dev->dev->sdev, SSB_TMSLOW, tmp);
-		msleep(1);
-
-		tmp = ssb_read32(dev->dev->sdev, SSB_TMSLOW);
-		tmp &= ~SSB_TMSLOW_FGC;
-		tmp |= B43_TMSLOW_PHYRESET;
-		ssb_write32(dev->dev->sdev, SSB_TMSLOW, tmp);
-		msleep(1);
-
-		break;
-#endif
-	}
-}
-
 static const char *band_to_string(enum ieee80211_band band)
 {
 	switch (band) {
@@ -3731,94 +3708,75 @@ static const char *band_to_string(enum ieee80211_band band)
 }
 
 /* Expects wl->mutex locked */
-static int b43_switch_band(struct b43_wl *wl, struct ieee80211_channel *chan)
+static int b43_switch_band(struct b43_wldev *dev,
+			   struct ieee80211_channel *chan)
 {
-	struct b43_wldev *up_dev = NULL;
-	struct b43_wldev *down_dev;
-	struct b43_wldev *d;
-	int err;
-	bool uninitialized_var(gmode);
-	int prev_status;
+	struct b43_phy *phy = &dev->phy;
+	bool gmode;
+	u32 tmp;
 
-	/* Find a device and PHY which supports the band. */
-	list_for_each_entry(d, &wl->devlist, list) {
-		switch (chan->band) {
-		case IEEE80211_BAND_5GHZ:
-			if (d->phy.supports_5ghz) {
-				up_dev = d;
-				gmode = false;
-			}
-			break;
-		case IEEE80211_BAND_2GHZ:
-			if (d->phy.supports_2ghz) {
-				up_dev = d;
-				gmode = true;
-			}
-			break;
-		default:
-			B43_WARN_ON(1);
-			return -EINVAL;
-		}
-		if (up_dev)
-			break;
+	switch (chan->band) {
+	case IEEE80211_BAND_5GHZ:
+		gmode = false;
+		break;
+	case IEEE80211_BAND_2GHZ:
+		gmode = true;
+		break;
+	default:
+		B43_WARN_ON(1);
+		return -EINVAL;
 	}
-	if (!up_dev) {
-		b43err(wl, "Could not find a device for %s-GHz band operation\n",
+
+	if (!((gmode && phy->supports_2ghz) ||
+	      (!gmode && phy->supports_5ghz))) {
+		b43err(dev->wl, "This device doesn't support %s-GHz band\n",
 		       band_to_string(chan->band));
 		return -ENODEV;
 	}
-	if ((up_dev == wl->current_dev) &&
-	    (!!wl->current_dev->phy.gmode == !!gmode)) {
+
+	if (!!phy->gmode == !!gmode) {
 		/* This device is already running. */
 		return 0;
 	}
-	b43dbg(wl, "Switching to %s-GHz band\n",
+
+	b43dbg(dev->wl, "Switching to %s GHz band\n",
 	       band_to_string(chan->band));
-	down_dev = wl->current_dev;
 
-	prev_status = b43_status(down_dev);
-	/* Shutdown the currently running core. */
-	if (prev_status >= B43_STAT_STARTED)
-		down_dev = b43_wireless_core_stop(down_dev);
-	if (prev_status >= B43_STAT_INITIALIZED)
-		b43_wireless_core_exit(down_dev);
+	/* Some new devices don't need disabling radio for band switching */
+	if (!(phy->type == B43_PHYTYPE_N && phy->rev >= 3))
+		b43_software_rfkill(dev, true);
 
-	if (down_dev != up_dev) {
-		/* We switch to a different core, so we put PHY into
-		 * RESET on the old core. */
-		b43_put_phy_into_reset(down_dev);
+	phy->gmode = gmode;
+	b43_phy_put_into_reset(dev);
+	switch (dev->dev->bus_type) {
+#ifdef CONFIG_B43_BCMA
+	case B43_BUS_BCMA:
+		tmp = bcma_aread32(dev->dev->bdev, BCMA_IOCTL);
+		if (gmode)
+			tmp |= B43_BCMA_IOCTL_GMODE;
+		else
+			tmp &= ~B43_BCMA_IOCTL_GMODE;
+		bcma_awrite32(dev->dev->bdev, BCMA_IOCTL, tmp);
+		break;
+#endif
+#ifdef CONFIG_B43_SSB
+	case B43_BUS_SSB:
+		tmp = ssb_read32(dev->dev->sdev, SSB_TMSLOW);
+		if (gmode)
+			tmp |= B43_TMSLOW_GMODE;
+		else
+			tmp &= ~B43_TMSLOW_GMODE;
+		ssb_write32(dev->dev->sdev, SSB_TMSLOW, tmp);
+		break;
+#endif
 	}
+	b43_phy_take_out_of_reset(dev);
 
-	/* Now start the new core. */
-	up_dev->phy.gmode = gmode;
-	if (prev_status >= B43_STAT_INITIALIZED) {
-		err = b43_wireless_core_init(up_dev);
-		if (err) {
-			b43err(wl, "Fatal: Could not initialize device for "
-			       "selected %s-GHz band\n",
-			       band_to_string(chan->band));
-			goto init_failure;
-		}
-	}
-	if (prev_status >= B43_STAT_STARTED) {
-		err = b43_wireless_core_start(up_dev);
-		if (err) {
-			b43err(wl, "Fatal: Could not start device for "
-			       "selected %s-GHz band\n",
-			       band_to_string(chan->band));
-			b43_wireless_core_exit(up_dev);
-			goto init_failure;
-		}
-	}
-	B43_WARN_ON(b43_status(up_dev) != prev_status);
+	b43_upload_initvals_band(dev);
 
-	wl->current_dev = up_dev;
+	b43_phy_init(dev);
 
 	return 0;
-init_failure:
-	/* Whoops, failed to init the new core. No core is operating now. */
-	wl->current_dev = NULL;
-	return err;
 }
 
 /* Write the short and long frame retry limit values. */
@@ -3851,8 +3809,10 @@ static int b43_op_config(struct ieee80211_hw *hw, u32 changed)
 
 	dev = wl->current_dev;
 
+	b43_mac_suspend(dev);
+
 	/* Switch the band (if necessary). This might change the active core. */
-	err = b43_switch_band(wl, conf->chandef.chan);
+	err = b43_switch_band(dev, conf->chandef.chan);
 	if (err)
 		goto out_unlock_mutex;
 
@@ -3871,8 +3831,6 @@ static int b43_op_config(struct ieee80211_hw *hw, u32 changed)
 	else
 		phy->is_40mhz = false;
 
-	b43_mac_suspend(dev);
-
 	if (changed & IEEE80211_CONF_CHANGE_RETRY_LIMITS)
 		b43_set_retry_limits(dev, conf->short_frame_max_tx_count,
 					  conf->long_frame_max_tx_count);
@@ -4582,8 +4540,12 @@ static void b43_imcfglo_timeouts_workaround(struct b43_wldev *dev)
 	struct ssb_bus *bus;
 	u32 tmp;
 
+#ifdef CONFIG_B43_SSB
 	if (dev->dev->bus_type != B43_BUS_SSB)
 		return;
+#else
+	return;
+#endif
 
 	bus = dev->dev->sdev->bus;
 
@@ -4738,7 +4700,7 @@ static int b43_wireless_core_init(struct b43_wldev *dev)
 	}
 	if (sprom->boardflags_lo & B43_BFL_XTAL_NOSLOW)
 		hf |= B43_HF_DSCRQ; /* Disable slowclock requests from ucode. */
-#ifdef CONFIG_SSB_DRIVER_PCICORE
+#if defined(CONFIG_B43_SSB) && defined(CONFIG_SSB_DRIVER_PCICORE)
 	if (dev->dev->bus_type == B43_BUS_SSB &&
 	    dev->dev->sdev->bus->bustype == SSB_BUSTYPE_PCI &&
 	    dev->dev->sdev->bus->pcicore.dev->id.revision <= 10)
@@ -5129,10 +5091,82 @@ static void b43_wireless_core_detach(struct b43_wldev *dev)
 	b43_phy_free(dev);
 }
 
+static void b43_supported_bands(struct b43_wldev *dev, bool *have_2ghz_phy,
+				bool *have_5ghz_phy)
+{
+	u16 dev_id = 0;
+
+#ifdef CONFIG_B43_BCMA
+	if (dev->dev->bus_type == B43_BUS_BCMA &&
+	    dev->dev->bdev->bus->hosttype == BCMA_HOSTTYPE_PCI)
+		dev_id = dev->dev->bdev->bus->host_pci->device;
+#endif
+#ifdef CONFIG_B43_SSB
+	if (dev->dev->bus_type == B43_BUS_SSB &&
+	    dev->dev->sdev->bus->bustype == SSB_BUSTYPE_PCI)
+		dev_id = dev->dev->sdev->bus->host_pci->device;
+#endif
+	/* Override with SPROM value if available */
+	if (dev->dev->bus_sprom->dev_id)
+		dev_id = dev->dev->bus_sprom->dev_id;
+
+	/* Note: below IDs can be "virtual" (not maching e.g. real PCI ID) */
+	switch (dev_id) {
+	case 0x4324: /* BCM4306 */
+	case 0x4312: /* BCM4311 */
+	case 0x4319: /* BCM4318 */
+	case 0x4328: /* BCM4321 */
+	case 0x432b: /* BCM4322 */
+	case 0x4350: /* BCM43222 */
+	case 0x4353: /* BCM43224 */
+	case 0x0576: /* BCM43224 */
+	case 0x435f: /* BCM6362 */
+	case 0x4331: /* BCM4331 */
+	case 0x4359: /* BCM43228 */
+	case 0x43a0: /* BCM4360 */
+	case 0x43b1: /* BCM4352 */
+		/* Dual band devices */
+		*have_2ghz_phy = true;
+		*have_5ghz_phy = true;
+		return;
+	case 0x4321: /* BCM4306 */
+	case 0x4313: /* BCM4311 */
+	case 0x431a: /* BCM4318 */
+	case 0x432a: /* BCM4321 */
+	case 0x432d: /* BCM4322 */
+	case 0x4352: /* BCM43222 */
+	case 0x4333: /* BCM4331 */
+	case 0x43a2: /* BCM4360 */
+	case 0x43b3: /* BCM4352 */
+		/* 5 GHz only devices */
+		*have_2ghz_phy = false;
+		*have_5ghz_phy = true;
+		return;
+	}
+
+	/* As a fallback, try to guess using PHY type */
+	switch (dev->phy.type) {
+	case B43_PHYTYPE_A:
+		*have_2ghz_phy = false;
+		*have_5ghz_phy = true;
+		return;
+	case B43_PHYTYPE_G:
+	case B43_PHYTYPE_N:
+	case B43_PHYTYPE_LP:
+	case B43_PHYTYPE_HT:
+	case B43_PHYTYPE_LCN:
+		*have_2ghz_phy = true;
+		*have_5ghz_phy = false;
+		return;
+	}
+
+	B43_WARN_ON(1);
+}
+
 static int b43_wireless_core_attach(struct b43_wldev *dev)
 {
 	struct b43_wl *wl = dev->wl;
-	struct pci_dev *pdev = NULL;
+	struct b43_phy *phy = &dev->phy;
 	int err;
 	u32 tmp;
 	bool have_2ghz_phy = false, have_5ghz_phy = false;
@@ -5144,19 +5178,15 @@ static int b43_wireless_core_attach(struct b43_wldev *dev)
 	 * that in core_init(), too.
 	 */
 
-#ifdef CONFIG_B43_SSB
-	if (dev->dev->bus_type == B43_BUS_SSB &&
-	    dev->dev->sdev->bus->bustype == SSB_BUSTYPE_PCI)
-		pdev = dev->dev->sdev->bus->host_pci;
-#endif
-
 	err = b43_bus_powerup(dev, 0);
 	if (err) {
 		b43err(wl, "Bus powerup failed\n");
 		goto out;
 	}
 
-	/* Get the PHY type. */
+	phy->do_full_init = true;
+
+	/* Try to guess supported bands for the first init needs */
 	switch (dev->dev->bus_type) {
 #ifdef CONFIG_B43_BCMA
 	case B43_BUS_BCMA:
@@ -5178,51 +5208,32 @@ static int b43_wireless_core_attach(struct b43_wldev *dev)
 	}
 
 	dev->phy.gmode = have_2ghz_phy;
-	dev->phy.radio_on = true;
 	b43_wireless_core_reset(dev, dev->phy.gmode);
 
+	/* Get the PHY type. */
 	err = b43_phy_versioning(dev);
 	if (err)
 		goto err_powerdown;
-	/* Check if this device supports multiband. */
-	if (!pdev ||
-	    (pdev->device != 0x4312 &&
-	     pdev->device != 0x4319 && pdev->device != 0x4324)) {
-		/* No multiband support. */
-		have_2ghz_phy = false;
+
+	/* Get real info about supported bands */
+	b43_supported_bands(dev, &have_2ghz_phy, &have_5ghz_phy);
+
+	/* We don't support 5 GHz on some PHYs yet */
+	switch (dev->phy.type) {
+	case B43_PHYTYPE_A:
+	case B43_PHYTYPE_G:
+	case B43_PHYTYPE_N:
+	case B43_PHYTYPE_LP:
+	case B43_PHYTYPE_HT:
+		b43warn(wl, "5 GHz band is unsupported on this PHY\n");
 		have_5ghz_phy = false;
-		switch (dev->phy.type) {
-		case B43_PHYTYPE_A:
-			have_5ghz_phy = true;
-			break;
-		case B43_PHYTYPE_LP: //FIXME not always!
-#if 0 //FIXME enabling 5GHz causes a NULL pointer dereference
-			have_5ghz_phy = 1;
-#endif
-		case B43_PHYTYPE_G:
-		case B43_PHYTYPE_N:
-		case B43_PHYTYPE_HT:
-		case B43_PHYTYPE_LCN:
-			have_2ghz_phy = true;
-			break;
-		default:
-			B43_WARN_ON(1);
-		}
 	}
-	if (dev->phy.type == B43_PHYTYPE_A) {
-		/* FIXME */
-		b43err(wl, "IEEE 802.11a devices are unsupported\n");
+
+	if (!have_2ghz_phy && !have_5ghz_phy) {
+		b43err(wl, "b43 can't support any band on this device\n");
 		err = -EOPNOTSUPP;
 		goto err_powerdown;
 	}
-	if (1 /* disable A-PHY */) {
-		/* FIXME: For now we disable the A-PHY on multi-PHY devices. */
-		if (dev->phy.type != B43_PHYTYPE_N &&
-		    dev->phy.type != B43_PHYTYPE_LP) {
-			have_2ghz_phy = true;
-			have_5ghz_phy = false;
-		}
-	}
 
 	err = b43_phy_allocate(dev);
 	if (err)
@@ -5270,7 +5281,6 @@ static void b43_one_core_detach(struct b43_bus_dev *dev)
 	b43_debugfs_remove_device(wldev);
 	b43_wireless_core_detach(wldev);
 	list_del(&wldev->list);
-	wl->nr_devs--;
 	b43_bus_set_wldev(dev, NULL);
 	kfree(wldev);
 }
@@ -5295,8 +5305,6 @@ static int b43_one_core_attach(struct b43_bus_dev *dev, struct b43_wl *wl)
 	if (err)
 		goto err_kfree_wldev;
 
-	list_add(&wldev->list, &wl->devlist);
-	wl->nr_devs++;
 	b43_bus_set_wldev(dev, wldev);
 	b43_debugfs_add_device(wldev);
 
@@ -5314,6 +5322,7 @@ static int b43_one_core_attach(struct b43_bus_dev *dev, struct b43_wl *wl)
 	(pdev->subsystem_vendor == PCI_VENDOR_ID_##_subvendor) &&	\
 	(pdev->subsystem_device == _subdevice)				)
 
+#ifdef CONFIG_B43_SSB
 static void b43_sprom_fixup(struct ssb_bus *bus)
 {
 	struct pci_dev *pdev;
@@ -5345,6 +5354,7 @@ static void b43_wireless_exit(struct b43_bus_dev *dev, struct b43_wl *wl)
 	ssb_set_devtypedata(dev->sdev, NULL);
 	ieee80211_free_hw(hw);
 }
+#endif
 
 static struct b43_wl *b43_wireless_init(struct b43_bus_dev *dev)
 {
@@ -5386,7 +5396,6 @@ static struct b43_wl *b43_wireless_init(struct b43_bus_dev *dev)
 	wl->hw = hw;
 	mutex_init(&wl->mutex);
 	spin_lock_init(&wl->hardirq_lock);
-	INIT_LIST_HEAD(&wl->devlist);
 	INIT_WORK(&wl->beacon_update_trigger, b43_beacon_update_trigger_work);
 	INIT_WORK(&wl->txpower_adjust_work, b43_phy_txpower_adjust_work);
 	INIT_WORK(&wl->tx_work, b43_tx_work);
@@ -5486,39 +5495,42 @@ int b43_ssb_probe(struct ssb_device *sdev, const struct ssb_device_id *id)
 	struct b43_bus_dev *dev;
 	struct b43_wl *wl;
 	int err;
-	int first = 0;
 
 	dev = b43_bus_dev_ssb_init(sdev);
 	if (!dev)
 		return -ENOMEM;
 
 	wl = ssb_get_devtypedata(sdev);
-	if (!wl) {
-		/* Probing the first core. Must setup common struct b43_wl */
-		first = 1;
-		b43_sprom_fixup(sdev->bus);
-		wl = b43_wireless_init(dev);
-		if (IS_ERR(wl)) {
-			err = PTR_ERR(wl);
-			goto out;
-		}
-		ssb_set_devtypedata(sdev, wl);
-		B43_WARN_ON(ssb_get_devtypedata(sdev) != wl);
+	if (wl) {
+		b43err(NULL, "Dual-core devices are not supported\n");
+		err = -ENOTSUPP;
+		goto err_ssb_kfree_dev;
+	}
+
+	b43_sprom_fixup(sdev->bus);
+
+	wl = b43_wireless_init(dev);
+	if (IS_ERR(wl)) {
+		err = PTR_ERR(wl);
+		goto err_ssb_kfree_dev;
 	}
+	ssb_set_devtypedata(sdev, wl);
+	B43_WARN_ON(ssb_get_devtypedata(sdev) != wl);
+
 	err = b43_one_core_attach(dev, wl);
 	if (err)
-		goto err_wireless_exit;
+		goto err_ssb_wireless_exit;
 
 	/* setup and start work to load firmware */
 	INIT_WORK(&wl->firmware_load, b43_request_firmware);
 	schedule_work(&wl->firmware_load);
 
-      out:
 	return err;
 
-      err_wireless_exit:
-	if (first)
-		b43_wireless_exit(dev, wl);
+err_ssb_wireless_exit:
+	b43_wireless_exit(dev, wl);
+err_ssb_kfree_dev:
+	kfree(dev);
 	return err;
 }
 
@@ -5546,13 +5558,8 @@ static void b43_ssb_remove(struct ssb_device *sdev)
 	/* Unregister HW RNG driver */
 	b43_rng_exit(wl);
 
-	if (list_empty(&wl->devlist)) {
-		b43_leds_unregister(wl);
-		/* Last core on the chip unregistered.
-		 * We can destroy common struct b43_wl.
-		 */
-		b43_wireless_exit(dev, wl);
-	}
+	b43_leds_unregister(wl);
+	b43_wireless_exit(dev, wl);
 }
 
 static struct ssb_driver b43_ssb_driver = {
diff --git a/drivers/net/wireless/b43/phy_common.c b/drivers/net/wireless/b43/phy_common.c
index dbaa5189019..08244b3b327 100644
--- a/drivers/net/wireless/b43/phy_common.c
+++ b/drivers/net/wireless/b43/phy_common.c
@@ -96,12 +96,16 @@ int b43_phy_init(struct b43_wldev *dev)
 
 	phy->channel = ops->get_default_chan(dev);
 
-	ops->software_rfkill(dev, false);
+	phy->ops->switch_analog(dev, true);
+	b43_software_rfkill(dev, false);
+
 	err = ops->init(dev);
 	if (err) {
 		b43err(dev->wl, "PHY init failed\n");
 		goto err_block_rf;
 	}
+	phy->do_full_init = false;
+
 	/* Make sure to switch hardware and firmware (SHM) to
 	 * the default channel. */
 	err = b43_switch_channel(dev, ops->get_default_chan(dev));
@@ -113,10 +117,11 @@ int b43_phy_init(struct b43_wldev *dev)
 	return 0;
 
 err_phy_exit:
+	phy->do_full_init = true;
 	if (ops->exit)
 		ops->exit(dev);
 err_block_rf:
-	ops->software_rfkill(dev, true);
+	b43_software_rfkill(dev, true);
 
 	return err;
 }
@@ -125,7 +130,8 @@ void b43_phy_exit(struct b43_wldev *dev)
 {
 	const struct b43_phy_operations *ops = dev->phy.ops;
 
-	ops->software_rfkill(dev, true);
+	b43_software_rfkill(dev, true);
+	dev->phy.do_full_init = true;
 	if (ops->exit)
 		ops->exit(dev);
 }
@@ -312,6 +318,90 @@ void b43_phy_maskset(struct b43_wldev *dev, u16 offset, u16 mask, u16 set)
 	}
 }
 
+void b43_phy_put_into_reset(struct b43_wldev *dev)
+{
+	u32 tmp;
+
+	switch (dev->dev->bus_type) {
+#ifdef CONFIG_B43_BCMA
+	case B43_BUS_BCMA:
+		tmp = bcma_aread32(dev->dev->bdev, BCMA_IOCTL);
+		tmp &= ~B43_BCMA_IOCTL_GMODE;
+		tmp |= B43_BCMA_IOCTL_PHY_RESET;
+		tmp |= BCMA_IOCTL_FGC;
+		bcma_awrite32(dev->dev->bdev, BCMA_IOCTL, tmp);
+		udelay(1);
+
+		tmp = bcma_aread32(dev->dev->bdev, BCMA_IOCTL);
+		tmp &= ~BCMA_IOCTL_FGC;
+		bcma_awrite32(dev->dev->bdev, BCMA_IOCTL, tmp);
+		udelay(1);
+		break;
+#endif
+#ifdef CONFIG_B43_SSB
+	case B43_BUS_SSB:
+		tmp = ssb_read32(dev->dev->sdev, SSB_TMSLOW);
+		tmp &= ~B43_TMSLOW_GMODE;
+		tmp |= B43_TMSLOW_PHYRESET;
+		tmp |= SSB_TMSLOW_FGC;
+		ssb_write32(dev->dev->sdev, SSB_TMSLOW, tmp);
+		usleep_range(1000, 2000);
+
+		tmp = ssb_read32(dev->dev->sdev, SSB_TMSLOW);
+		tmp &= ~SSB_TMSLOW_FGC;
+		ssb_write32(dev->dev->sdev, SSB_TMSLOW, tmp);
+		usleep_range(1000, 2000);
+
+		break;
+#endif
+	}
+}
+
+void b43_phy_take_out_of_reset(struct b43_wldev *dev)
+{
+	u32 tmp;
+
+	switch (dev->dev->bus_type) {
+#ifdef CONFIG_B43_BCMA
+	case B43_BUS_BCMA:
+		/* Unset reset bit (with forcing clock) */
+		tmp = bcma_aread32(dev->dev->bdev, BCMA_IOCTL);
+		tmp &= ~B43_BCMA_IOCTL_PHY_RESET;
+		tmp &= ~B43_BCMA_IOCTL_PHY_CLKEN;
+		tmp |= BCMA_IOCTL_FGC;
+		bcma_awrite32(dev->dev->bdev, BCMA_IOCTL, tmp);
+		udelay(1);
+
+		/* Do not force clock anymore */
+		tmp = bcma_aread32(dev->dev->bdev, BCMA_IOCTL);
+		tmp &= ~BCMA_IOCTL_FGC;
+		tmp |= B43_BCMA_IOCTL_PHY_CLKEN;
+		bcma_awrite32(dev->dev->bdev, BCMA_IOCTL, tmp);
+		udelay(1);
+		break;
+#endif
+#ifdef CONFIG_B43_SSB
+	case B43_BUS_SSB:
+		/* Unset reset bit (with forcing clock) */
+		tmp = ssb_read32(dev->dev->sdev, SSB_TMSLOW);
+		tmp &= ~B43_TMSLOW_PHYRESET;
+		tmp &= ~B43_TMSLOW_PHYCLKEN;
+		tmp |= SSB_TMSLOW_FGC;
+		ssb_write32(dev->dev->sdev, SSB_TMSLOW, tmp);
+		ssb_read32(dev->dev->sdev, SSB_TMSLOW); /* flush */
+		usleep_range(1000, 2000);
+
+		tmp = ssb_read32(dev->dev->sdev, SSB_TMSLOW);
+		tmp &= ~SSB_TMSLOW_FGC;
+		tmp |= B43_TMSLOW_PHYCLKEN;
+		ssb_write32(dev->dev->sdev, SSB_TMSLOW, tmp);
+		ssb_read32(dev->dev->sdev, SSB_TMSLOW); /* flush */
+		usleep_range(1000, 2000);
+		break;
+#endif
+	}
+}
+
 int b43_switch_channel(struct b43_wldev *dev, unsigned int new_channel)
 {
 	struct b43_phy *phy = &(dev->phy);
diff --git a/drivers/net/wireless/b43/phy_common.h b/drivers/net/wireless/b43/phy_common.h
index f1b99934987..4ad6240d9ff 100644
--- a/drivers/net/wireless/b43/phy_common.h
+++ b/drivers/net/wireless/b43/phy_common.h
@@ -231,9 +231,12 @@ struct b43_phy {
 	/* HT info */
 	bool is_40mhz;
 
-	/* GMODE bit enabled? */
+	/* Is GMODE (2 GHz mode) bit enabled? */
 	bool gmode;
 
+	/* After power reset full init has to be performed */
+	bool do_full_init;
+
 	/* Analog Type */
 	u8 analog;
 	/* B43_PHYTYPE_ */
@@ -390,6 +393,9 @@ void b43_phy_lock(struct b43_wldev *dev);
  */
 void b43_phy_unlock(struct b43_wldev *dev);
 
+void b43_phy_put_into_reset(struct b43_wldev *dev);
+void b43_phy_take_out_of_reset(struct b43_wldev *dev);
+
 /**
  * b43_switch_channel - Switch to another channel
  */
diff --git a/drivers/net/wireless/b43/phy_g.c b/drivers/net/wireless/b43/phy_g.c
index 12f467b8d56..8f5c14bc10e 100644
--- a/drivers/net/wireless/b43/phy_g.c
+++ b/drivers/net/wireless/b43/phy_g.c
@@ -1587,6 +1587,7 @@ static void b43_phy_initb5(struct b43_wldev *dev)
 	b43_write16(dev, 0x03E4, (b43_read16(dev, 0x03E4) & 0xFFC0) | 0x0004);
 }
 
+/* http://bcm-v4.sipsolutions.net/802.11/PHY/Init/B6 */
 static void b43_phy_initb6(struct b43_wldev *dev)
 {
 	struct b43_phy *phy = &dev->phy;
@@ -1670,7 +1671,7 @@ static void b43_phy_initb6(struct b43_wldev *dev)
 		b43_radio_write16(dev, 0x50, 0x20);
 	}
 	if (phy->radio_rev <= 2) {
-		b43_radio_write16(dev, 0x7C, 0x20);
+		b43_radio_write16(dev, 0x50, 0x20);
 		b43_radio_write16(dev, 0x5A, 0x70);
 		b43_radio_write16(dev, 0x5B, 0x7B);
 		b43_radio_write16(dev, 0x5C, 0xB0);
@@ -1686,9 +1687,8 @@ static void b43_phy_initb6(struct b43_wldev *dev)
 		b43_phy_write(dev, 0x2A, 0x8AC0);
 	b43_phy_write(dev, 0x0038, 0x0668);
 	b43_set_txpower_g(dev, &gphy->bbatt, &gphy->rfatt, gphy->tx_control);
-	if (phy->radio_rev <= 5) {
+	if (phy->radio_rev == 4 || phy->radio_rev == 5)
 		b43_phy_maskset(dev, 0x5D, 0xFF80, 0x0003);
-	}
 	if (phy->radio_rev <= 2)
 		b43_radio_write16(dev, 0x005D, 0x000D);
 
diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index 24ccbe96e0c..86569f6a870 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -257,6 +257,72 @@ static void b43_nphy_rf_ctl_override(struct b43_wldev *dev, u16 field,
 	}
 }
 
+static void b43_nphy_rf_ctl_intc_override_rev7(struct b43_wldev *dev,
+					       enum n_intc_override intc_override,
+					       u16 value, u8 core_sel)
+{
+	u16 reg, tmp, tmp2, val;
+	int core;
+
+	for (core = 0; core < 2; core++) {
+		if ((core_sel == 1 && core != 0) ||
+		    (core_sel == 2 && core != 1))
+			continue;
+
+		reg = (core == 0) ? B43_NPHY_RFCTL_INTC1 : B43_NPHY_RFCTL_INTC2;
+
+		switch (intc_override) {
+		case N_INTC_OVERRIDE_OFF:
+			b43_phy_write(dev, reg, 0);
+			b43_nphy_force_rf_sequence(dev, B43_RFSEQ_RESET2RX);
+			break;
+		case N_INTC_OVERRIDE_TRSW:
+			b43_phy_maskset(dev, reg, ~0xC0, value << 6);
+			b43_phy_set(dev, reg, 0x400);
+
+			b43_phy_mask(dev, 0x2ff, ~0xC000 & 0xFFFF);
+			b43_phy_set(dev, 0x2ff, 0x2000);
+			b43_phy_set(dev, 0x2ff, 0x0001);
+			break;
+		case N_INTC_OVERRIDE_PA:
+			tmp = 0x0030;
+			if (b43_current_band(dev->wl) == IEEE80211_BAND_5GHZ)
+				val = value << 5;
+			else
+				val = value << 4;
+			b43_phy_maskset(dev, reg, ~tmp, val);
+			b43_phy_set(dev, reg, 0x1000);
+			break;
+		case N_INTC_OVERRIDE_EXT_LNA_PU:
+			if (b43_current_band(dev->wl) == IEEE80211_BAND_5GHZ) {
+				tmp = 0x0001;
+				tmp2 = 0x0004;
+				val = value;
+			} else {
+				tmp = 0x0004;
+				tmp2 = 0x0001;
+				val = value << 2;
+			}
+			b43_phy_maskset(dev, reg, ~tmp, val);
+			b43_phy_mask(dev, reg, ~tmp2);
+			break;
+		case N_INTC_OVERRIDE_EXT_LNA_GAIN:
+			if (b43_current_band(dev->wl) == IEEE80211_BAND_5GHZ) {
+				tmp = 0x0002;
+				tmp2 = 0x0008;
+				val = value << 1;
+			} else {
+				tmp = 0x0008;
+				tmp2 = 0x0002;
+				val = value << 3;
+			}
+			b43_phy_maskset(dev, reg, ~tmp, val);
+			b43_phy_mask(dev, reg, ~tmp2);
+			break;
+		}
+	}
+}
+
 /* http://bcm-v4.sipsolutions.net/802.11/PHY/N/RFCtrlIntcOverride */
 static void b43_nphy_rf_ctl_intc_override(struct b43_wldev *dev,
 					  enum n_intc_override intc_override,
@@ -265,6 +331,12 @@ static void b43_nphy_rf_ctl_intc_override(struct b43_wldev *dev,
 	u8 i, j;
 	u16 reg, tmp, val;
 
+	if (dev->phy.rev >= 7) {
+		b43_nphy_rf_ctl_intc_override_rev7(dev, intc_override, value,
+						   core);
+		return;
+	}
+
 	B43_WARN_ON(dev->phy.rev < 3);
 
 	for (i = 0; i < 2; i++) {
@@ -419,7 +491,8 @@ static void b43_nphy_stay_in_carrier_search(struct b43_wldev *dev, bool enable)
 		static const u16 clip[] = { 0xFFFF, 0xFFFF };
 		if (nphy->deaf_count++ == 0) {
 			nphy->classifier_state = b43_nphy_classifier(dev, 0, 0);
-			b43_nphy_classifier(dev, 0x7, 0);
+			b43_nphy_classifier(dev, 0x7,
+					    B43_NPHY_CLASSCTL_WAITEDEN);
 			b43_nphy_read_clip_detection(dev, nphy->clip_state);
 			b43_nphy_write_clip_detection(dev, clip);
 		}
@@ -627,13 +700,11 @@ static void b43_radio_2057_init_post(struct b43_wldev *dev)
 	b43_radio_mask(dev, R2057_RFPLL_MISC_CAL_RESETN, ~0x78);
 	b43_radio_mask(dev, R2057_XTAL_CONFIG2, ~0x80);
 
-	if (dev->phy.n->init_por) {
+	if (dev->phy.do_full_init) {
 		b43_radio_2057_rcal(dev);
 		b43_radio_2057_rccal(dev);
 	}
 	b43_radio_mask(dev, R2057_RFPLL_MASTER, ~0x8);
-
-	dev->phy.n->init_por = false;
 }
 
 /* http://bcm-v4.sipsolutions.net/802.11/Radio/2057/Init */
@@ -734,9 +805,16 @@ static void b43_radio_2056_setup(struct b43_wldev *dev,
 	u16 bias, cbias;
 	u16 pag_boost, padg_boost, pgag_boost, mixg_boost;
 	u16 paa_boost, pada_boost, pgaa_boost, mixa_boost;
+	bool is_pkg_fab_smic;
 
 	B43_WARN_ON(dev->phy.rev < 3);
 
+	is_pkg_fab_smic =
+		((dev->dev->chip_id == BCMA_CHIP_ID_BCM43224 ||
+		  dev->dev->chip_id == BCMA_CHIP_ID_BCM43225 ||
+		  dev->dev->chip_id == BCMA_CHIP_ID_BCM43421) &&
+		 dev->dev->chip_pkg == BCMA_PKG_ID_BCM43224_FAB_SMIC);
+
 	b43_chantab_radio_2056_upload(dev, e);
 	b2056_upload_syn_pll_cp2(dev, band == IEEE80211_BAND_5GHZ);
 
@@ -744,7 +822,8 @@ static void b43_radio_2056_setup(struct b43_wldev *dev,
 	    b43_current_band(dev->wl) == IEEE80211_BAND_2GHZ) {
 		b43_radio_write(dev, B2056_SYN_PLL_LOOPFILTER1, 0x1F);
 		b43_radio_write(dev, B2056_SYN_PLL_LOOPFILTER2, 0x1F);
-		if (dev->dev->chip_id == 0x4716) {
+		if (dev->dev->chip_id == BCMA_CHIP_ID_BCM4716 ||
+		    dev->dev->chip_id == BCMA_CHIP_ID_BCM47162) {
 			b43_radio_write(dev, B2056_SYN_PLL_LOOPFILTER4, 0x14);
 			b43_radio_write(dev, B2056_SYN_PLL_CP2, 0);
 		} else {
@@ -752,6 +831,13 @@ static void b43_radio_2056_setup(struct b43_wldev *dev,
 			b43_radio_write(dev, B2056_SYN_PLL_CP2, 0x14);
 		}
 	}
+	if (sprom->boardflags2_hi & B43_BFH2_GPLL_WAR2 &&
+	    b43_current_band(dev->wl) == IEEE80211_BAND_2GHZ) {
+		b43_radio_write(dev, B2056_SYN_PLL_LOOPFILTER1, 0x1f);
+		b43_radio_write(dev, B2056_SYN_PLL_LOOPFILTER2, 0x1f);
+		b43_radio_write(dev, B2056_SYN_PLL_LOOPFILTER4, 0x0b);
+		b43_radio_write(dev, B2056_SYN_PLL_CP2, 0x20);
+	}
 	if (sprom->boardflags2_lo & B43_BFL2_APLL_WAR &&
 	    b43_current_band(dev->wl) == IEEE80211_BAND_5GHZ) {
 		b43_radio_write(dev, B2056_SYN_PLL_LOOPFILTER1, 0x1F);
@@ -767,7 +853,8 @@ static void b43_radio_2056_setup(struct b43_wldev *dev,
 				b43_radio_write(dev,
 					offset | B2056_TX_PADG_IDAC, 0xcc);
 
-				if (dev->dev->chip_id == 0x4716) {
+				if (dev->dev->chip_id == BCMA_CHIP_ID_BCM4716 ||
+				    dev->dev->chip_id == BCMA_CHIP_ID_BCM47162) {
 					bias = 0x40;
 					cbias = 0x45;
 					pag_boost = 0x5;
@@ -776,6 +863,10 @@ static void b43_radio_2056_setup(struct b43_wldev *dev,
 				} else {
 					bias = 0x25;
 					cbias = 0x20;
+					if (is_pkg_fab_smic) {
+						bias = 0x2a;
+						cbias = 0x38;
+					}
 					pag_boost = 0x4;
 					pgag_boost = 0x03;
 					mixg_boost = 0x65;
@@ -844,6 +935,8 @@ static void b43_radio_2056_setup(struct b43_wldev *dev,
 			mixa_boost = 0xF;
 		}
 
+		cbias = is_pkg_fab_smic ? 0x35 : 0x30;
+
 		for (i = 0; i < 2; i++) {
 			offset = i ? B2056_TX1 : B2056_TX0;
 
@@ -862,11 +955,11 @@ static void b43_radio_2056_setup(struct b43_wldev *dev,
 			b43_radio_write(dev,
 				offset | B2056_TX_PADA_CASCBIAS, 0x03);
 			b43_radio_write(dev,
-				offset | B2056_TX_INTPAA_IAUX_STAT, 0x50);
+				offset | B2056_TX_INTPAA_IAUX_STAT, 0x30);
 			b43_radio_write(dev,
-				offset | B2056_TX_INTPAA_IMAIN_STAT, 0x50);
+				offset | B2056_TX_INTPAA_IMAIN_STAT, 0x30);
 			b43_radio_write(dev,
-				offset | B2056_TX_INTPAA_CASCBIAS, 0x30);
+				offset | B2056_TX_INTPAA_CASCBIAS, cbias);
 		}
 	}
 
@@ -933,7 +1026,7 @@ static void b43_radio_init2056_post(struct b43_wldev *dev)
 	b43_radio_mask(dev, B2056_SYN_COM_RESET, ~0x2);
 	b43_radio_mask(dev, B2056_SYN_PLL_MAST2, ~0xFC);
 	b43_radio_mask(dev, B2056_SYN_RCCAL_CTRL0, ~0x1);
-	if (dev->phy.n->init_por)
+	if (dev->phy.do_full_init)
 		b43_radio_2056_rcal(dev);
 }
 
@@ -946,8 +1039,6 @@ static void b43_radio_init2056(struct b43_wldev *dev)
 	b43_radio_init2056_pre(dev);
 	b2056_upload_inittabs(dev, 0, 0);
 	b43_radio_init2056_post(dev);
-
-	dev->phy.n->init_por = false;
 }
 
 /**************************************************
@@ -1164,23 +1255,20 @@ static void b43_nphy_run_samples(struct b43_wldev *dev, u16 samps, u16 loops,
 	u16 seq_mode;
 	u32 tmp;
 
-	if (nphy->hang_avoid)
-		b43_nphy_stay_in_carrier_search(dev, true);
+	b43_nphy_stay_in_carrier_search(dev, true);
 
 	if ((nphy->bb_mult_save & 0x80000000) == 0) {
 		tmp = b43_ntab_read(dev, B43_NTAB16(15, 87));
 		nphy->bb_mult_save = (tmp & 0xFFFF) | 0x80000000;
 	}
 
+	/* TODO: add modify_bbmult argument */
 	if (!dev->phy.is_40mhz)
 		tmp = 0x6464;
 	else
 		tmp = 0x4747;
 	b43_ntab_write(dev, B43_NTAB16(15, 87), tmp);
 
-	if (nphy->hang_avoid)
-		b43_nphy_stay_in_carrier_search(dev, false);
-
 	b43_phy_write(dev, B43_NPHY_SAMP_DEPCNT, (samps - 1));
 
 	if (loops != 0xFFFF)
@@ -1213,6 +1301,8 @@ static void b43_nphy_run_samples(struct b43_wldev *dev, u16 samps, u16 loops,
 		b43err(dev->wl, "run samples timeout\n");
 
 	b43_phy_write(dev, B43_NPHY_RFSEQMODE, seq_mode);
+
+	b43_nphy_stay_in_carrier_search(dev, false);
 }
 
 /**************************************************
@@ -1588,8 +1678,8 @@ static void b43_nphy_rev3_rssi_cal(struct b43_wldev *dev)
 	struct b43_phy_n *nphy = dev->phy.n;
 
 	u16 saved_regs_phy_rfctl[2];
-	u16 saved_regs_phy[13];
-	u16 regs_to_store[] = {
+	u16 saved_regs_phy[22];
+	u16 regs_to_store_rev3[] = {
 		B43_NPHY_AFECTL_OVER1, B43_NPHY_AFECTL_OVER,
 		B43_NPHY_AFECTL_C1, B43_NPHY_AFECTL_C2,
 		B43_NPHY_TXF_40CO_B1S1, B43_NPHY_RFCTL_OVER,
@@ -1598,6 +1688,20 @@ static void b43_nphy_rev3_rssi_cal(struct b43_wldev *dev)
 		B43_NPHY_RFCTL_LUT_TRSW_UP1, B43_NPHY_RFCTL_LUT_TRSW_UP2,
 		B43_NPHY_RFCTL_RSSIO1, B43_NPHY_RFCTL_RSSIO2
 	};
+	u16 regs_to_store_rev7[] = {
+		B43_NPHY_AFECTL_OVER1, B43_NPHY_AFECTL_OVER,
+		B43_NPHY_AFECTL_C1, B43_NPHY_AFECTL_C2,
+		B43_NPHY_TXF_40CO_B1S1, B43_NPHY_RFCTL_OVER,
+		0x342, 0x343, 0x346, 0x347,
+		0x2ff,
+		B43_NPHY_TXF_40CO_B1S0, B43_NPHY_TXF_40CO_B32S1,
+		B43_NPHY_RFCTL_CMD,
+		B43_NPHY_RFCTL_LUT_TRSW_UP1, B43_NPHY_RFCTL_LUT_TRSW_UP2,
+		0x340, 0x341, 0x344, 0x345,
+		B43_NPHY_RFCTL_RSSIO1, B43_NPHY_RFCTL_RSSIO2
+	};
+	u16 *regs_to_store;
+	int regs_amount;
 
 	u16 class;
 
@@ -1617,6 +1721,15 @@ static void b43_nphy_rev3_rssi_cal(struct b43_wldev *dev)
 	u8 rx_core_state;
 	int core, i, j, vcm;
 
+	if (dev->phy.rev >= 7) {
+		regs_to_store = regs_to_store_rev7;
+		regs_amount = ARRAY_SIZE(regs_to_store_rev7);
+	} else {
+		regs_to_store = regs_to_store_rev3;
+		regs_amount = ARRAY_SIZE(regs_to_store_rev3);
+	}
+	BUG_ON(regs_amount > ARRAY_SIZE(saved_regs_phy));
+
 	class = b43_nphy_classifier(dev, 0, 0);
 	b43_nphy_classifier(dev, 7, 4);
 	b43_nphy_read_clip_detection(dev, clip_state);
@@ -1624,22 +1737,29 @@ static void b43_nphy_rev3_rssi_cal(struct b43_wldev *dev)
 
 	saved_regs_phy_rfctl[0] = b43_phy_read(dev, B43_NPHY_RFCTL_INTC1);
 	saved_regs_phy_rfctl[1] = b43_phy_read(dev, B43_NPHY_RFCTL_INTC2);
-	for (i = 0; i < ARRAY_SIZE(regs_to_store); i++)
+	for (i = 0; i < regs_amount; i++)
 		saved_regs_phy[i] = b43_phy_read(dev, regs_to_store[i]);
 
 	b43_nphy_rf_ctl_intc_override(dev, N_INTC_OVERRIDE_OFF, 0, 7);
 	b43_nphy_rf_ctl_intc_override(dev, N_INTC_OVERRIDE_TRSW, 1, 7);
-	b43_nphy_rf_ctl_override(dev, 0x1, 0, 0, false);
-	b43_nphy_rf_ctl_override(dev, 0x2, 1, 0, false);
-	b43_nphy_rf_ctl_override(dev, 0x80, 1, 0, false);
-	b43_nphy_rf_ctl_override(dev, 0x40, 1, 0, false);
-
-	if (b43_current_band(dev->wl) == IEEE80211_BAND_5GHZ) {
-		b43_nphy_rf_ctl_override(dev, 0x20, 0, 0, false);
-		b43_nphy_rf_ctl_override(dev, 0x10, 1, 0, false);
+
+	if (dev->phy.rev >= 7) {
+		/* TODO */
+		if (b43_current_band(dev->wl) == IEEE80211_BAND_5GHZ) {
+		} else {
+		}
 	} else {
-		b43_nphy_rf_ctl_override(dev, 0x10, 0, 0, false);
-		b43_nphy_rf_ctl_override(dev, 0x20, 1, 0, false);
+		b43_nphy_rf_ctl_override(dev, 0x1, 0, 0, false);
+		b43_nphy_rf_ctl_override(dev, 0x2, 1, 0, false);
+		b43_nphy_rf_ctl_override(dev, 0x80, 1, 0, false);
+		b43_nphy_rf_ctl_override(dev, 0x40, 1, 0, false);
+		if (b43_current_band(dev->wl) == IEEE80211_BAND_5GHZ) {
+			b43_nphy_rf_ctl_override(dev, 0x20, 0, 0, false);
+			b43_nphy_rf_ctl_override(dev, 0x10, 1, 0, false);
+		} else {
+			b43_nphy_rf_ctl_override(dev, 0x10, 0, 0, false);
+			b43_nphy_rf_ctl_override(dev, 0x20, 1, 0, false);
+		}
 	}
 
 	rx_core_state = b43_nphy_get_rx_core_state(dev);
@@ -1654,8 +1774,11 @@ static void b43_nphy_rev3_rssi_cal(struct b43_wldev *dev)
 
 		/* Grab RSSI results for every possible VCM */
 		for (vcm = 0; vcm < 8; vcm++) {
-			b43_radio_maskset(dev, r | B2056_RX_RSSI_MISC, 0xE3,
-					vcm << 2);
+			if (dev->phy.rev >= 7)
+				;
+			else
+				b43_radio_maskset(dev, r | B2056_RX_RSSI_MISC,
+						  0xE3, vcm << 2);
 			b43_nphy_poll_rssi(dev, N_RSSI_NB, results[vcm], 8);
 		}
 
@@ -1682,8 +1805,11 @@ static void b43_nphy_rev3_rssi_cal(struct b43_wldev *dev)
 		}
 
 		/* Select the best VCM */
-		b43_radio_maskset(dev, r | B2056_RX_RSSI_MISC, 0xE3,
-				  vcm_final << 2);
+		if (dev->phy.rev >= 7)
+			;
+		else
+			b43_radio_maskset(dev, r | B2056_RX_RSSI_MISC,
+					  0xE3, vcm_final << 2);
 
 		for (i = 0; i < 4; i++) {
 			if (core != i / 2)
@@ -1736,9 +1862,9 @@ static void b43_nphy_rev3_rssi_cal(struct b43_wldev *dev)
 
 	b43_phy_set(dev, B43_NPHY_RFCTL_OVER, 0x1);
 	b43_phy_set(dev, B43_NPHY_RFCTL_CMD, B43_NPHY_RFCTL_CMD_RXTX);
-	b43_phy_mask(dev, B43_NPHY_TXF_40CO_B1S1, ~0x1);
+	b43_phy_mask(dev, B43_NPHY_RFCTL_OVER, ~0x1);
 
-	for (i = 0; i < ARRAY_SIZE(regs_to_store); i++)
+	for (i = 0; i < regs_amount; i++)
 		b43_phy_write(dev, regs_to_store[i], saved_regs_phy[i]);
 
 	/* Store for future configuration */
@@ -2494,8 +2620,8 @@ static void b43_nphy_workarounds_rev3plus(struct b43_wldev *dev)
 	struct ssb_sprom *sprom = dev->dev->bus_sprom;
 
 	/* TX to RX */
-	u8 tx2rx_events[8] = { 0x4, 0x3, 0x6, 0x5, 0x2, 0x1, 0x8, 0x1F };
-	u8 tx2rx_delays[8] = { 8, 4, 2, 2, 4, 4, 6, 1 };
+	u8 tx2rx_events[7] = { 0x4, 0x3, 0x5, 0x2, 0x1, 0x8, 0x1F };
+	u8 tx2rx_delays[7] = { 8, 4, 4, 4, 4, 6, 1 };
 	/* RX to TX */
 	u8 rx2tx_events_ipa[9] = { 0x0, 0x1, 0x2, 0x8, 0x5, 0x6, 0xF, 0x3,
 					0x1F };
@@ -2503,6 +2629,23 @@ static void b43_nphy_workarounds_rev3plus(struct b43_wldev *dev)
 	u8 rx2tx_events[9] = { 0x0, 0x1, 0x2, 0x8, 0x5, 0x6, 0x3, 0x4, 0x1F };
 	u8 rx2tx_delays[9] = { 8, 6, 6, 4, 4, 18, 42, 1, 1 };
 
+	u16 vmids[5][4] = {
+		{ 0xa2, 0xb4, 0xb4, 0x89, }, /* 0 */
+		{ 0xb4, 0xb4, 0xb4, 0x24, }, /* 1 */
+		{ 0xa2, 0xb4, 0xb4, 0x74, }, /* 2 */
+		{ 0xa2, 0xb4, 0xb4, 0x270, }, /* 3 */
+		{ 0xa2, 0xb4, 0xb4, 0x00, }, /* 4 and 5 */
+	};
+	u16 gains[5][4] = {
+		{ 0x02, 0x02, 0x02, 0x00, }, /* 0 */
+		{ 0x02, 0x02, 0x02, 0x02, }, /* 1 */
+		{ 0x02, 0x02, 0x02, 0x04, }, /* 2 */
+		{ 0x02, 0x02, 0x02, 0x00, }, /* 3 */
+		{ 0x02, 0x02, 0x02, 0x00, }, /* 4 and 5 */
+	};
+	u16 *vmid, *gain;
+
+	u8 pdet_range;
 	u16 tmp16;
 	u32 tmp32;
 
@@ -2561,7 +2704,71 @@ static void b43_nphy_workarounds_rev3plus(struct b43_wldev *dev)
 	b43_ntab_write(dev, B43_NTAB16(8, 0), 2);
 	b43_ntab_write(dev, B43_NTAB16(8, 16), 2);
 
-	/* TODO */
+	if (b43_current_band(dev->wl) == IEEE80211_BAND_2GHZ)
+		pdet_range = sprom->fem.ghz2.pdet_range;
+	else
+		pdet_range = sprom->fem.ghz5.pdet_range;
+	vmid = vmids[min_t(u16, pdet_range, 4)];
+	gain = gains[min_t(u16, pdet_range, 4)];
+	switch (pdet_range) {
+	case 3:
+		if (!(dev->phy.rev >= 4 &&
+		      b43_current_band(dev->wl) == IEEE80211_BAND_2GHZ))
+			break;
+		/* FALL THROUGH */
+	case 0:
+	case 1:
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x08), 4, vmid);
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x18), 4, vmid);
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x0c), 4, gain);
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x1c), 4, gain);
+		break;
+	case 2:
+		if (dev->phy.rev >= 6) {
+			if (b43_current_band(dev->wl) == IEEE80211_BAND_2GHZ)
+				vmid[3] = 0x94;
+			else
+				vmid[3] = 0x8e;
+			gain[3] = 3;
+		} else if (dev->phy.rev == 5) {
+			vmid[3] = 0x84;
+			gain[3] = 2;
+		}
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x08), 4, vmid);
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x18), 4, vmid);
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x0c), 4, gain);
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x1c), 4, gain);
+		break;
+	case 4:
+	case 5:
+		if (b43_current_band(dev->wl) != IEEE80211_BAND_2GHZ) {
+			if (pdet_range == 4) {
+				vmid[3] = 0x8e;
+				tmp16 = 0x96;
+				gain[3] = 0x2;
+			} else {
+				vmid[3] = 0x89;
+				tmp16 = 0x89;
+				gain[3] = 0;
+			}
+		} else {
+			if (pdet_range == 4) {
+				vmid[3] = 0x89;
+				tmp16 = 0x8b;
+				gain[3] = 0x2;
+			} else {
+				vmid[3] = 0x74;
+				tmp16 = 0x70;
+				gain[3] = 0;
+			}
+		}
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x08), 4, vmid);
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x0c), 4, gain);
+		vmid[3] = tmp16;
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x18), 4, vmid);
+		b43_ntab_write_bulk(dev, B43_NTAB16(8, 0x1c), 4, gain);
+		break;
+	}
 
 	b43_radio_write(dev, B2056_RX0 | B2056_RX_MIXA_MAST_BIAS, 0x00);
 	b43_radio_write(dev, B2056_RX1 | B2056_RX_MIXA_MAST_BIAS, 0x00);
@@ -2600,7 +2807,7 @@ static void b43_nphy_workarounds_rev3plus(struct b43_wldev *dev)
 	/* Dropped probably-always-true condition */
 	b43_phy_write(dev, B43_NPHY_ED_CRS40ASSERTTHRESH0, 0x03eb);
 	b43_phy_write(dev, B43_NPHY_ED_CRS40ASSERTTHRESH1, 0x03eb);
-	b43_phy_write(dev, B43_NPHY_ED_CRS40DEASSERTTHRESH1, 0x0341);
+	b43_phy_write(dev, B43_NPHY_ED_CRS40DEASSERTTHRESH0, 0x0341);
 	b43_phy_write(dev, B43_NPHY_ED_CRS40DEASSERTTHRESH1, 0x0341);
 	b43_phy_write(dev, B43_NPHY_ED_CRS20LASSERTTHRESH0, 0x042b);
 	b43_phy_write(dev, B43_NPHY_ED_CRS20LASSERTTHRESH1, 0x042b);
@@ -3211,6 +3418,20 @@ static void b43_nphy_tx_prepare_adjusted_power_table(struct b43_wldev *dev)
 	u8 idx, delta;
 	u8 i, stf_mode;
 
+	/* Array adj_pwr_tbl corresponds to the hardware table. It consists of
+	 * 21 groups, each containing 4 entries.
+	 *
+	 * First group has entries for CCK modulation.
+	 * The rest of groups has 1 entry per modulation (SISO, CDD, STBC, SDM).
+	 *
+	 * Group 0 is for CCK
+	 * Groups 1..4 use BPSK (group per coding rate)
+	 * Groups 5..8 use QPSK (group per coding rate)
+	 * Groups 9..12 use 16-QAM (group per coding rate)
+	 * Groups 13..16 use 64-QAM (group per coding rate)
+	 * Groups 17..20 are unknown
+	 */
+
 	for (i = 0; i < 4; i++)
 		nphy->adj_pwr_tbl[i] = nphy->tx_power_offset[i];
 
@@ -3409,10 +3630,8 @@ static void b43_nphy_tx_power_ctl_setup(struct b43_wldev *dev)
 	}
 
 	b43_nphy_tx_prepare_adjusted_power_table(dev);
-	/*
 	b43_ntab_write_bulk(dev, B43_NTAB16(26, 64), 84, nphy->adj_pwr_tbl);
 	b43_ntab_write_bulk(dev, B43_NTAB16(27, 64), 84, nphy->adj_pwr_tbl);
-	*/
 
 	if (nphy->hang_avoid)
 		b43_nphy_stay_in_carrier_search(dev, false);
@@ -5124,7 +5343,7 @@ static int b43_phy_initn(struct b43_wldev *dev)
 	b43_phy_write(dev, B43_NPHY_TXMACIF_HOLDOFF, 0x0015);
 	b43_phy_write(dev, B43_NPHY_TXMACDELAY, 0x0320);
 	if (phy->rev >= 3 && phy->rev <= 6)
-		b43_phy_write(dev, B43_NPHY_PLOAD_CSENSE_EXTLEN, 0x0014);
+		b43_phy_write(dev, B43_NPHY_PLOAD_CSENSE_EXTLEN, 0x0032);
 	b43_nphy_tx_lp_fbw(dev);
 	if (phy->rev >= 3)
 		b43_nphy_spur_workaround(dev);
@@ -5338,7 +5557,6 @@ static void b43_nphy_op_prepare_structs(struct b43_wldev *dev)
 	nphy->hang_avoid = (phy->rev == 3 || phy->rev == 4);
 	nphy->spur_avoid = (phy->rev >= 3) ?
 				B43_SPUR_AVOID_AUTO : B43_SPUR_AVOID_DISABLE;
-	nphy->init_por = true;
 	nphy->gain_boost = true; /* this way we follow wl, assume it is true */
 	nphy->txrx_chain = 2; /* sth different than 0 and 1 for now */
 	nphy->phyrxchain = 3; /* to avoid b43_nphy_set_rx_core_state like wl */
@@ -5379,8 +5597,6 @@ static void b43_nphy_op_prepare_structs(struct b43_wldev *dev)
 		nphy->ipa2g_on = sprom->fem.ghz2.extpa_gain == 2;
 		nphy->ipa5g_on = sprom->fem.ghz5.extpa_gain == 2;
 	}
-
-	nphy->init_por = true;
 }
 
 static void b43_nphy_op_free(struct b43_wldev *dev)
@@ -5441,8 +5657,11 @@ static u16 b43_nphy_op_radio_read(struct b43_wldev *dev, u16 reg)
 {
 	/* Register 1 is a 32-bit register. */
 	B43_WARN_ON(reg == 1);
-	/* N-PHY needs 0x100 for read access */
-	reg |= 0x100;
+
+	if (dev->phy.rev >= 7)
+		reg |= 0x200; /* Radio 0x2057 */
+	else
+		reg |= 0x100;
 
 	b43_write16(dev, B43_MMIO_RADIO_CONTROL, reg);
 	return b43_read16(dev, B43_MMIO_RADIO_DATA_LOW);
@@ -5488,10 +5707,12 @@ static void b43_nphy_op_software_rfkill(struct b43_wldev *dev,
 		}
 	} else {
 		if (dev->phy.rev >= 7) {
-			b43_radio_2057_init(dev);
+			if (!dev->phy.radio_on)
+				b43_radio_2057_init(dev);
 			b43_switch_channel(dev, dev->phy.channel);
 		} else if (dev->phy.rev >= 3) {
-			b43_radio_init2056(dev);
+			if (!dev->phy.radio_on)
+				b43_radio_init2056(dev);
 			b43_switch_channel(dev, dev->phy.channel);
 		} else {
 			b43_radio_init2055(dev);
diff --git a/drivers/net/wireless/b43/phy_n.h b/drivers/net/wireless/b43/phy_n.h
index 9a5b6bc27d2..ecfbf66dbc3 100644
--- a/drivers/net/wireless/b43/phy_n.h
+++ b/drivers/net/wireless/b43/phy_n.h
@@ -931,7 +931,6 @@ struct b43_phy_n {
 	u16 papd_epsilon_offset[2];
 	s32 preamble_override;
 	u32 bb_mult_save;
-	bool init_por;
 
 	bool gain_boost;
 	bool elna_gain_config;
diff --git a/drivers/net/wireless/b43/radio_2056.c b/drivers/net/wireless/b43/radio_2056.c
index b4fd9345d67..2ce25607c60 100644
--- a/drivers/net/wireless/b43/radio_2056.c
+++ b/drivers/net/wireless/b43/radio_2056.c
@@ -48,7 +48,7 @@ struct b2056_inittabs_pts {
 	unsigned int rx_length;
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev3_syn[] = {
+static const struct b2056_inittab_entry b2056_inittab_phy_rev3_syn[] = {
 	[B2056_SYN_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -232,7 +232,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev3_syn[] = {
 	[B2056_SYN_LOGEN_TX_CMOS_VALID]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev3_tx[] = {
+static const struct b2056_inittab_entry b2056_inittab_phy_rev3_tx[] = {
 	[B2056_TX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -380,7 +380,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev3_tx[] = {
 	[B2056_TX_STATUS_TXLPF_RC]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev3_rx[] = {
+static const struct b2056_inittab_entry b2056_inittab_phy_rev3_rx[] = {
 	[B2056_RX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -530,7 +530,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev3_rx[] = {
 	[B2056_RX_STATUS_HPC_RC]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev4_syn[] = {
+static const struct b2056_inittab_entry b2056_inittab_phy_rev4_syn[] = {
 	[B2056_SYN_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -714,7 +714,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev4_syn[] = {
 	[B2056_SYN_LOGEN_TX_CMOS_VALID]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev4_tx[] = {
+static const struct b2056_inittab_entry b2056_inittab_phy_rev4_tx[] = {
 	[B2056_TX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -862,7 +862,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev4_tx[] = {
 	[B2056_TX_STATUS_TXLPF_RC]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev4_rx[] = {
+static const struct b2056_inittab_entry b2056_inittab_phy_rev4_rx[] = {
 	[B2056_RX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -1012,7 +1012,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev4_rx[] = {
 	[B2056_RX_STATUS_HPC_RC]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev5_syn[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev5_syn[] = {
 	[B2056_SYN_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -1196,7 +1196,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev5_syn[] = {
 	[B2056_SYN_LOGEN_TX_CMOS_VALID]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev5_tx[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev5_tx[] = {
 	[B2056_TX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -1352,7 +1352,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev5_tx[] = {
 	[B2056_TX_GMBB_IDAC7]		= { .ghz5 = 0x0075, .ghz2 = 0x0075, UPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev5_rx[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev5_rx[] = {
 	[B2056_RX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -1502,7 +1502,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev5_rx[] = {
 	[B2056_RX_STATUS_HPC_RC]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev6_syn[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev6_syn[] = {
 	[B2056_SYN_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -1686,7 +1686,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev6_syn[] = {
 	[B2056_SYN_LOGEN_TX_CMOS_VALID]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev6_tx[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev6_tx[] = {
 	[B2056_TX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -1842,7 +1842,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev6_tx[] = {
 	[B2056_TX_GMBB_IDAC7]		= { .ghz5 = 0x0070, .ghz2 = 0x0070, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev6_rx[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev6_rx[] = {
 	[B2056_RX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -1992,7 +1992,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev6_rx[] = {
 	[B2056_RX_STATUS_HPC_RC]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev7_syn[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev7_9_syn[] = {
 	[B2056_SYN_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -2176,7 +2176,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev7_syn[] = {
 	[B2056_SYN_LOGEN_TX_CMOS_VALID]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev7_tx[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev7_9_tx[] = {
 	[B2056_TX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -2332,7 +2332,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev7_tx[] = {
 	[B2056_TX_GMBB_IDAC7]		= { .ghz5 = 0x0075, .ghz2 = 0x0075, UPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev7_rx[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev7_9_rx[] = {
 	[B2056_RX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -2482,7 +2482,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev7_rx[] = {
 	[B2056_RX_STATUS_HPC_RC]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev8_syn[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev8_syn[] = {
 	[B2056_SYN_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_SYN_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -2666,7 +2666,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev8_syn[] = {
 	[B2056_SYN_LOGEN_TX_CMOS_VALID]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev8_tx[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev8_tx[] = {
 	[B2056_TX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_TX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -2822,7 +2822,7 @@ static const struct b2056_inittab_entry b2056_inittab_rev8_tx[] = {
 	[B2056_TX_GMBB_IDAC7]		= { .ghz5 = 0x0070, .ghz2 = 0x0070, NOUPLOAD, },
 };
 
-static const struct b2056_inittab_entry b2056_inittab_rev8_rx[] = {
+static const struct b2056_inittab_entry b2056_inittab_radio_rev8_rx[] = {
 	[B2056_RX_RESERVED_ADDR2]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR3]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 	[B2056_RX_RESERVED_ADDR4]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
@@ -2972,24 +2972,69 @@ static const struct b2056_inittab_entry b2056_inittab_rev8_rx[] = {
 	[B2056_RX_STATUS_HPC_RC]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, NOUPLOAD, },
 };
 
-#define INITTABSPTS(prefix) \
-	.syn		= prefix##_syn,			\
-	.syn_length	= ARRAY_SIZE(prefix##_syn),	\
-	.tx		= prefix##_tx,			\
-	.tx_length	= ARRAY_SIZE(prefix##_tx),	\
-	.rx		= prefix##_rx,			\
-	.rx_length	= ARRAY_SIZE(prefix##_rx)
+static const struct b2056_inittab_entry b2056_inittab_radio_rev11_syn[] = {
+	[B2056_SYN_PLL_PFD]		= { .ghz5 = 0x0006, .ghz2 = 0x0006, UPLOAD, },
+	[B2056_SYN_PLL_CP2]		= { .ghz5 = 0x003f, .ghz2 = 0x003f, UPLOAD, },
+	[B2056_SYN_PLL_LOOPFILTER1]	= { .ghz5 = 0x0006, .ghz2 = 0x0006, UPLOAD, },
+	[B2056_SYN_PLL_LOOPFILTER2]	= { .ghz5 = 0x0006, .ghz2 = 0x0006, UPLOAD, },
+	[B2056_SYN_PLL_LOOPFILTER4]	= { .ghz5 = 0x002b, .ghz2 = 0x002b, UPLOAD, },
+	[B2056_SYN_PLL_VCO2]		= { .ghz5 = 0x00f7, .ghz2 = 0x00f7, UPLOAD, },
+	[B2056_SYN_PLL_VCOCAL12]	= { .ghz5 = 0x0007, .ghz2 = 0x0007, UPLOAD, },
+	[B2056_SYN_LOGENBUF2]		= { .ghz5 = 0x008f, .ghz2 = 0x008f, UPLOAD, },
+};
 
-static const struct b2056_inittabs_pts b2056_inittabs[] = {
-	[3] = { INITTABSPTS(b2056_inittab_rev3) },
-	[4] = { INITTABSPTS(b2056_inittab_rev4) },
-	[5] = { INITTABSPTS(b2056_inittab_rev5) },
-	[6] = { INITTABSPTS(b2056_inittab_rev6) },
-	[7] = { INITTABSPTS(b2056_inittab_rev7) },
-	[8] = { INITTABSPTS(b2056_inittab_rev8) },
-	[9] = { INITTABSPTS(b2056_inittab_rev7) },
+static const struct b2056_inittab_entry b2056_inittab_radio_rev11_tx[] = {
+	[B2056_TX_PA_SPARE2]		= { .ghz5 = 0x00ee, .ghz2 = 0x00ee, UPLOAD, },
+	[B2056_TX_INTPAA_IAUX_STAT]	= { .ghz5 = 0x0050, .ghz2 = 0x0050, UPLOAD, },
+	[B2056_TX_INTPAA_IMAIN_STAT]	= { .ghz5 = 0x0050, .ghz2 = 0x0050, UPLOAD, },
+	[B2056_TX_INTPAA_PASLOPE]	= { .ghz5 = 0x00f0, .ghz2 = 0x00f0, UPLOAD, },
+	[B2056_TX_INTPAG_PASLOPE]	= { .ghz5 = 0x00f0, .ghz2 = 0x00f0, UPLOAD, },
+	[B2056_TX_PADA_IDAC]		= { .ghz5 = 0x00ff, .ghz2 = 0x00ff, UPLOAD, },
+	[B2056_TX_PADA_SLOPE]		= { .ghz5 = 0x0070, .ghz2 = 0x0070, UPLOAD, },
+	[B2056_TX_PADG_SLOPE]		= { .ghz5 = 0x0070, .ghz2 = 0x0070, UPLOAD, },
+	[B2056_TX_PGAA_IDAC]		= { .ghz5 = 0x00ff, .ghz2 = 0x00ff, UPLOAD, },
+	[B2056_TX_PGAA_SLOPE]		= { .ghz5 = 0x0077, .ghz2 = 0x0077, UPLOAD, },
+	[B2056_TX_PGAG_SLOPE]		= { .ghz5 = 0x0077, .ghz2 = 0x0077, UPLOAD, },
+	[B2056_TX_GMBB_IDAC]		= { .ghz5 = 0x0000, .ghz2 = 0x0000, UPLOAD, },
+	[B2056_TX_TXSPARE1]		= { .ghz5 = 0x0030, .ghz2 = 0x0030, UPLOAD, },
+};
+
+static const struct b2056_inittab_entry b2056_inittab_radio_rev11_rx[] = {
+	[B2056_RX_BIASPOLE_LNAA1_IDAC]	= { .ghz5 = 0x0017, .ghz2 = 0x0017, UPLOAD, },
+	[B2056_RX_LNAA2_IDAC]		= { .ghz5 = 0x00ff, .ghz2 = 0x00ff, UPLOAD, },
+	[B2056_RX_BIASPOLE_LNAG1_IDAC]	= { .ghz5 = 0x0017, .ghz2 = 0x0017, UPLOAD, },
+	[B2056_RX_LNAG2_IDAC]		= { .ghz5 = 0x00f0, .ghz2 = 0x00f0, UPLOAD, },
+	[B2056_RX_MIXA_VCM]		= { .ghz5 = 0x0055, .ghz2 = 0x0055, UPLOAD, },
+	[B2056_RX_MIXA_LOB_BIAS]	= { .ghz5 = 0x0088, .ghz2 = 0x0088, UPLOAD, },
+	[B2056_RX_MIXA_BIAS_AUX]	= { .ghz5 = 0x0007, .ghz2 = 0x0007, UPLOAD, },
+	[B2056_RX_MIXG_VCM]		= { .ghz5 = 0x0055, .ghz2 = 0x0055, UPLOAD, },
+	[B2056_RX_TIA_IOPAMP]		= { .ghz5 = 0x0026, .ghz2 = 0x0026, UPLOAD, },
+	[B2056_RX_TIA_QOPAMP]		= { .ghz5 = 0x0026, .ghz2 = 0x0026, UPLOAD, },
+	[B2056_RX_TIA_IMISC]		= { .ghz5 = 0x000f, .ghz2 = 0x000f, UPLOAD, },
+	[B2056_RX_TIA_QMISC]		= { .ghz5 = 0x000f, .ghz2 = 0x000f, UPLOAD, },
+	[B2056_RX_RXLPF_OUTVCM]		= { .ghz5 = 0x0004, .ghz2 = 0x0004, UPLOAD, },
+	[B2056_RX_VGA_BIAS_DCCANCEL]	= { .ghz5 = 0x0000, .ghz2 = 0x0000, UPLOAD, },
+	[B2056_RX_RXSPARE3]		= { .ghz5 = 0x0005, .ghz2 = 0x0005, UPLOAD, },
 };
 
+#define INITTABSPTS(prefix) \
+	static const struct b2056_inittabs_pts prefix = {	\
+		.syn		= prefix##_syn,			\
+		.syn_length	= ARRAY_SIZE(prefix##_syn),	\
+		.tx		= prefix##_tx,			\
+		.tx_length	= ARRAY_SIZE(prefix##_tx),	\
+		.rx		= prefix##_rx,			\
+		.rx_length	= ARRAY_SIZE(prefix##_rx),	\
+	}
+
+INITTABSPTS(b2056_inittab_phy_rev3);
+INITTABSPTS(b2056_inittab_phy_rev4);
+INITTABSPTS(b2056_inittab_radio_rev5);
+INITTABSPTS(b2056_inittab_radio_rev6);
+INITTABSPTS(b2056_inittab_radio_rev7_9);
+INITTABSPTS(b2056_inittab_radio_rev8);
+INITTABSPTS(b2056_inittab_radio_rev11);
+
 #define RADIOREGS3(r00, r01, r02, r03, r04, r05, r06, r07, r08, r09, \
 		   r10, r11, r12, r13, r14, r15, r16, r17, r18, r19, \
 		   r20, r21, r22, r23, r24, r25, r26, r27, r28, r29, \
@@ -3041,7 +3086,7 @@ static const struct b2056_inittabs_pts b2056_inittabs[] = {
 	.phy_regs.phy_bw6	= r5
 
 /* http://bcm-v4.sipsolutions.net/802.11/Radio/2056/ChannelTable */
-static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev3[] = {
+static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_phy_rev3[] = {
   {	.freq			= 4920,
 	RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xec, 0x05, 0x05, 0x04,
 		   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
@@ -4036,7 +4081,7 @@ static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev3[] =
   },
 };
 
-static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev4[] = {
+static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_phy_rev4[] = {
   {	.freq			= 4920,
 	RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xec, 0x05, 0x05, 0x04,
 		   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
@@ -5031,7 +5076,7 @@ static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev4[] =
   },
 };
 
-static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev5[] = {
+static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_radio_rev5[] = {
   {	.freq			= 4920,
 	RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xec, 0x05, 0x05, 0x04,
 		   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
@@ -6026,7 +6071,7 @@ static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev5[] =
   },
 };
 
-static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev6[] = {
+static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_radio_rev6[] = {
   {	.freq			= 4920,
 	RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xec, 0x05, 0x05, 0x04,
 		   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
@@ -7021,7 +7066,7 @@ static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev6[] =
   },
 };
 
-static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev7_9[] = {
+static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_radio_rev7_9[] = {
   {	.freq			= 4920,
 	RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xec, 0x05, 0x05, 0x04,
 		   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
@@ -8016,7 +8061,7 @@ static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev7_9[]
   },
 };
 
-static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev8[] = {
+static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_radio_rev8[] = {
   {	.freq			= 4920,
 	RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xec, 0x05, 0x05, 0x04,
 		   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
@@ -9011,6 +9056,1154 @@ static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_rev8[] =
   },
 };
 
+static const struct b43_nphy_channeltab_entry_rev3 b43_nphy_channeltab_radio_rev11[] = {
+	{
+		.freq			= 4920,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xec, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07b4, 0x07b0, 0x07ac, 0x0214, 0x0215, 0x0216),
+	},
+	{
+		.freq			= 4930,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xed, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07b8, 0x07b4, 0x07b0, 0x0213, 0x0214, 0x0215),
+	},
+	{
+		.freq			= 4940,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xee, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07bc, 0x07b8, 0x07b4, 0x0212, 0x0213, 0x0214),
+	},
+	{
+		.freq			= 4950,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xef, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x00, 0x00, 0x00, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07c0, 0x07bc, 0x07b8, 0x0211, 0x0212, 0x0213),
+	},
+	{
+		.freq			= 4960,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xf0, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07c4, 0x07c0, 0x07bc, 0x020f, 0x0211, 0x0212),
+	},
+	{
+		.freq			= 4970,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xf1, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07c8, 0x07c4, 0x07c0, 0x020e, 0x020f, 0x0211),
+	},
+	{
+		.freq			= 4980,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xf2, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07cc, 0x07c8, 0x07c4, 0x020d, 0x020e, 0x020f),
+	},
+	{
+		.freq			= 4990,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xf3, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07d0, 0x07cc, 0x07c8, 0x020c, 0x020d, 0x020e),
+	},
+	{
+		.freq			= 5000,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xf4, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07d4, 0x07d0, 0x07cc, 0x020b, 0x020c, 0x020d),
+	},
+	{
+		.freq			= 5010,
+		RADIOREGS3(0xff, 0x01, 0x01, 0x01, 0xf5, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07d8, 0x07d4, 0x07d0, 0x020a, 0x020b, 0x020c),
+	},
+	{
+		.freq			= 5020,
+		RADIOREGS3(0xf7, 0x01, 0x01, 0x01, 0xf6, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07dc, 0x07d8, 0x07d4, 0x0209, 0x020a, 0x020b),
+	},
+	{
+		.freq			= 5030,
+		RADIOREGS3(0xf7, 0x01, 0x01, 0x01, 0xf7, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07e0, 0x07dc, 0x07d8, 0x0208, 0x0209, 0x020a),
+	},
+	{
+		.freq			= 5040,
+		RADIOREGS3(0xef, 0x01, 0x01, 0x01, 0xf8, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07e4, 0x07e0, 0x07dc, 0x0207, 0x0208, 0x0209),
+	},
+	{
+		.freq			= 5050,
+		RADIOREGS3(0xef, 0x01, 0x01, 0x01, 0xf9, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07e8, 0x07e4, 0x07e0, 0x0206, 0x0207, 0x0208),
+	},
+	{
+		.freq			= 5060,
+		RADIOREGS3(0xe6, 0x01, 0x01, 0x01, 0xfa, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfe, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfe, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07ec, 0x07e8, 0x07e4, 0x0205, 0x0206, 0x0207),
+	},
+	{
+		.freq			= 5070,
+		RADIOREGS3(0xe6, 0x01, 0x01, 0x01, 0xfb, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfd, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfd, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07f0, 0x07ec, 0x07e8, 0x0204, 0x0205, 0x0206),
+	},
+	{
+		.freq			= 5080,
+		RADIOREGS3(0xde, 0x01, 0x01, 0x01, 0xfc, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfd, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfd, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07f4, 0x07f0, 0x07ec, 0x0203, 0x0204, 0x0205),
+	},
+	{
+		.freq			= 5090,
+		RADIOREGS3(0xde, 0x01, 0x01, 0x01, 0xfd, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x01, 0x01, 0x01, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfd, 0x00, 0x09, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfd, 0x00, 0x09, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07f8, 0x07f4, 0x07f0, 0x0202, 0x0203, 0x0204),
+	},
+	{
+		.freq			= 5100,
+		RADIOREGS3(0xd6, 0x01, 0x01, 0x01, 0xfe, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfd, 0x00, 0x08, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfd, 0x00, 0x08, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x07fc, 0x07f8, 0x07f4, 0x0201, 0x0202, 0x0203),
+	},
+	{
+		.freq			= 5110,
+		RADIOREGS3(0xd6, 0x01, 0x01, 0x01, 0xff, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfc, 0x00, 0x08, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfc, 0x00, 0x08, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0800, 0x07fc, 0x07f8, 0x0200, 0x0201, 0x0202),
+	},
+	{
+		.freq			= 5120,
+		RADIOREGS3(0xce, 0x01, 0x01, 0x02, 0x00, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfc, 0x00, 0x08, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfc, 0x00, 0x08, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0804, 0x0800, 0x07fc, 0x01ff, 0x0200, 0x0201),
+	},
+	{
+		.freq			= 5130,
+		RADIOREGS3(0xce, 0x01, 0x01, 0x02, 0x01, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfc, 0x00, 0x08, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfc, 0x00, 0x08, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0808, 0x0804, 0x0800, 0x01fe, 0x01ff, 0x0200),
+	},
+	{
+		.freq			= 5140,
+		RADIOREGS3(0xc6, 0x01, 0x01, 0x02, 0x02, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfb, 0x00, 0x08, 0x00, 0x77, 0x00, 0x0f,
+			   0x00, 0x6f, 0x00, 0xfb, 0x00, 0x08, 0x00, 0x77,
+			   0x00, 0x0f, 0x00, 0x6f, 0x00),
+		PHYREGS(0x080c, 0x0808, 0x0804, 0x01fd, 0x01fe, 0x01ff),
+	},
+	{
+		.freq			= 5160,
+		RADIOREGS3(0xbe, 0x01, 0x01, 0x02, 0x04, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfa, 0x00, 0x07, 0x00, 0x77, 0x00, 0x0e,
+			   0x00, 0x6f, 0x00, 0xfa, 0x00, 0x07, 0x00, 0x77,
+			   0x00, 0x0e, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0814, 0x0810, 0x080c, 0x01fb, 0x01fc, 0x01fd),
+	},
+	{
+		.freq			= 5170,
+		RADIOREGS3(0xbe, 0x01, 0x01, 0x02, 0x05, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xfa, 0x00, 0x07, 0x00, 0x77, 0x00, 0x0e,
+			   0x00, 0x6f, 0x00, 0xfa, 0x00, 0x07, 0x00, 0x77,
+			   0x00, 0x0e, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0818, 0x0814, 0x0810, 0x01fa, 0x01fb, 0x01fc),
+	},
+	{
+		.freq			= 5180,
+		RADIOREGS3(0xb6, 0x01, 0x01, 0x02, 0x06, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xf9, 0x00, 0x06, 0x00, 0x77, 0x00, 0x0e,
+			   0x00, 0x6f, 0x00, 0xf9, 0x00, 0x06, 0x00, 0x77,
+			   0x00, 0x0e, 0x00, 0x6f, 0x00),
+		PHYREGS(0x081c, 0x0818, 0x0814, 0x01f9, 0x01fa, 0x01fb),
+	},
+	{
+		.freq			= 5190,
+		RADIOREGS3(0xb6, 0x01, 0x01, 0x02, 0x07, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xf9, 0x00, 0x06, 0x00, 0x77, 0x00, 0x0d,
+			   0x00, 0x6f, 0x00, 0xf9, 0x00, 0x06, 0x00, 0x77,
+			   0x00, 0x0d, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0820, 0x081c, 0x0818, 0x01f8, 0x01f9, 0x01fa),
+	},
+	{
+		.freq			= 5200,
+		RADIOREGS3(0xaf, 0x01, 0x01, 0x02, 0x08, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xf9, 0x00, 0x05, 0x00, 0x77, 0x00, 0x0d,
+			   0x00, 0x6f, 0x00, 0xf9, 0x00, 0x05, 0x00, 0x77,
+			   0x00, 0x0d, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0824, 0x0820, 0x081c, 0x01f7, 0x01f8, 0x01f9),
+	},
+	{
+		.freq			= 5210,
+		RADIOREGS3(0xaf, 0x01, 0x01, 0x02, 0x09, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8f, 0x0f, 0x00,
+			   0xff, 0xf9, 0x00, 0x05, 0x00, 0x77, 0x00, 0x0d,
+			   0x00, 0x6f, 0x00, 0xf9, 0x00, 0x05, 0x00, 0x77,
+			   0x00, 0x0d, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0828, 0x0824, 0x0820, 0x01f6, 0x01f7, 0x01f8),
+	},
+	{
+		.freq			= 5220,
+		RADIOREGS3(0xa7, 0x01, 0x01, 0x02, 0x0a, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8e, 0x0f, 0x00,
+			   0xfe, 0xd8, 0x00, 0x05, 0x00, 0x77, 0x00, 0x0d,
+			   0x00, 0x6f, 0x00, 0xd8, 0x00, 0x05, 0x00, 0x77,
+			   0x00, 0x0d, 0x00, 0x6f, 0x00),
+		PHYREGS(0x082c, 0x0828, 0x0824, 0x01f5, 0x01f6, 0x01f7),
+	},
+	{
+		.freq			= 5230,
+		RADIOREGS3(0xa7, 0x01, 0x01, 0x02, 0x0b, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8e, 0x0f, 0x00,
+			   0xee, 0xd8, 0x00, 0x05, 0x00, 0x77, 0x00, 0x0d,
+			   0x00, 0x6f, 0x00, 0xd8, 0x00, 0x05, 0x00, 0x77,
+			   0x00, 0x0d, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0830, 0x082c, 0x0828, 0x01f4, 0x01f5, 0x01f6),
+	},
+	{
+		.freq			= 5240,
+		RADIOREGS3(0xa0, 0x01, 0x01, 0x02, 0x0c, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8e, 0x0f, 0x00,
+			   0xee, 0xc8, 0x00, 0x05, 0x00, 0x77, 0x00, 0x0d,
+			   0x00, 0x6f, 0x00, 0xc8, 0x00, 0x05, 0x00, 0x77,
+			   0x00, 0x0d, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0834, 0x0830, 0x082c, 0x01f3, 0x01f4, 0x01f5),
+	},
+	{
+		.freq			= 5250,
+		RADIOREGS3(0xa0, 0x01, 0x01, 0x02, 0x0d, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8e, 0x0f, 0x00,
+			   0xed, 0xc7, 0x00, 0x05, 0x00, 0x77, 0x00, 0x0d,
+			   0x00, 0x6f, 0x00, 0xc7, 0x00, 0x05, 0x00, 0x77,
+			   0x00, 0x0d, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0838, 0x0834, 0x0830, 0x01f2, 0x01f3, 0x01f4),
+	},
+	{
+		.freq			= 5260,
+		RADIOREGS3(0x98, 0x01, 0x01, 0x02, 0x0e, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x02, 0x02, 0x02, 0x8e, 0x0e, 0x00,
+			   0xed, 0xc7, 0x00, 0x04, 0x00, 0x77, 0x00, 0x0d,
+			   0x00, 0x6f, 0x00, 0xc7, 0x00, 0x04, 0x00, 0x77,
+			   0x00, 0x0d, 0x00, 0x6f, 0x00),
+		PHYREGS(0x083c, 0x0838, 0x0834, 0x01f1, 0x01f2, 0x01f3),
+	},
+	{
+		.freq			= 5270,
+		RADIOREGS3(0x98, 0x01, 0x01, 0x02, 0x0f, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8e, 0x0e, 0x00,
+			   0xed, 0xc7, 0x00, 0x04, 0x00, 0x77, 0x00, 0x0c,
+			   0x00, 0x6f, 0x00, 0xc7, 0x00, 0x04, 0x00, 0x77,
+			   0x00, 0x0c, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0840, 0x083c, 0x0838, 0x01f0, 0x01f1, 0x01f2),
+	},
+	{
+		.freq			= 5280,
+		RADIOREGS3(0x91, 0x01, 0x01, 0x02, 0x10, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8d, 0x0e, 0x00,
+			   0xdc, 0xb7, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0c,
+			   0x00, 0x6f, 0x00, 0xb7, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0c, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0844, 0x0840, 0x083c, 0x01f0, 0x01f0, 0x01f1),
+	},
+	{
+		.freq			= 5290,
+		RADIOREGS3(0x91, 0x01, 0x01, 0x02, 0x11, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8d, 0x0e, 0x00,
+			   0xdc, 0xb7, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0c,
+			   0x00, 0x6f, 0x00, 0xb7, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0c, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0848, 0x0844, 0x0840, 0x01ef, 0x01f0, 0x01f0),
+	},
+	{
+		.freq			= 5300,
+		RADIOREGS3(0x8a, 0x01, 0x01, 0x02, 0x12, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8d, 0x0e, 0x00,
+			   0xdc, 0xb7, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0c,
+			   0x00, 0x6f, 0x00, 0xb7, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0c, 0x00, 0x6f, 0x00),
+		PHYREGS(0x084c, 0x0848, 0x0844, 0x01ee, 0x01ef, 0x01f0),
+	},
+	{
+		.freq			= 5310,
+		RADIOREGS3(0x8a, 0x01, 0x01, 0x02, 0x13, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8d, 0x0e, 0x00,
+			   0xdc, 0xb7, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0c,
+			   0x00, 0x6f, 0x00, 0xb7, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0c, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0850, 0x084c, 0x0848, 0x01ed, 0x01ee, 0x01ef),
+	},
+	{
+		.freq			= 5320,
+		RADIOREGS3(0x83, 0x01, 0x01, 0x02, 0x14, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8d, 0x0e, 0x00,
+			   0xdb, 0xb7, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0c,
+			   0x00, 0x6f, 0x00, 0xb7, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0c, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0854, 0x0850, 0x084c, 0x01ec, 0x01ed, 0x01ee),
+	},
+	{
+		.freq			= 5330,
+		RADIOREGS3(0x83, 0x01, 0x01, 0x02, 0x15, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8d, 0x0d, 0x00,
+			   0xcb, 0xa6, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0b,
+			   0x00, 0x6f, 0x00, 0xa6, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0b, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0858, 0x0854, 0x0850, 0x01eb, 0x01ec, 0x01ed),
+	},
+	{
+		.freq			= 5340,
+		RADIOREGS3(0x7c, 0x01, 0x01, 0x02, 0x16, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8d, 0x0d, 0x00,
+			   0xca, 0xa6, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0b,
+			   0x00, 0x6f, 0x00, 0xa6, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0b, 0x00, 0x6f, 0x00),
+		PHYREGS(0x085c, 0x0858, 0x0854, 0x01ea, 0x01eb, 0x01ec),
+	},
+	{
+		.freq			= 5350,
+		RADIOREGS3(0x7c, 0x01, 0x01, 0x02, 0x17, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8c, 0x0d, 0x00,
+			   0xca, 0xa6, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0b,
+			   0x00, 0x6f, 0x00, 0xa6, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0b, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0860, 0x085c, 0x0858, 0x01e9, 0x01ea, 0x01eb),
+	},
+	{
+		.freq			= 5360,
+		RADIOREGS3(0x75, 0x01, 0x01, 0x02, 0x18, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8c, 0x0d, 0x00,
+			   0xc9, 0x95, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0a,
+			   0x00, 0x6f, 0x00, 0x95, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0a, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0864, 0x0860, 0x085c, 0x01e8, 0x01e9, 0x01ea),
+	},
+	{
+		.freq			= 5370,
+		RADIOREGS3(0x75, 0x01, 0x01, 0x02, 0x19, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8c, 0x0d, 0x00,
+			   0xc9, 0x95, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0a,
+			   0x00, 0x6f, 0x00, 0x95, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0a, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0868, 0x0864, 0x0860, 0x01e7, 0x01e8, 0x01e9),
+	},
+	{
+		.freq			= 5380,
+		RADIOREGS3(0x6e, 0x01, 0x01, 0x02, 0x1a, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8c, 0x0c, 0x00,
+			   0xb8, 0x95, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0a,
+			   0x00, 0x6f, 0x00, 0x95, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0a, 0x00, 0x6f, 0x00),
+		PHYREGS(0x086c, 0x0868, 0x0864, 0x01e6, 0x01e7, 0x01e8),
+	},
+	{
+		.freq			= 5390,
+		RADIOREGS3(0x6e, 0x01, 0x01, 0x02, 0x1b, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8c, 0x0c, 0x00,
+			   0xb8, 0x84, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0a,
+			   0x00, 0x6f, 0x00, 0x84, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0a, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0870, 0x086c, 0x0868, 0x01e5, 0x01e6, 0x01e7),
+	},
+	{
+		.freq			= 5400,
+		RADIOREGS3(0x67, 0x01, 0x01, 0x02, 0x1c, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8c, 0x0c, 0x00,
+			   0xb8, 0x84, 0x00, 0x03, 0x00, 0x77, 0x00, 0x0a,
+			   0x00, 0x6f, 0x00, 0x84, 0x00, 0x03, 0x00, 0x77,
+			   0x00, 0x0a, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0874, 0x0870, 0x086c, 0x01e5, 0x01e5, 0x01e6),
+	},
+	{
+		.freq			= 5410,
+		RADIOREGS3(0x67, 0x01, 0x01, 0x02, 0x1d, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8c, 0x0c, 0x00,
+			   0xb7, 0x84, 0x00, 0x02, 0x00, 0x77, 0x00, 0x0a,
+			   0x00, 0x6f, 0x00, 0x84, 0x00, 0x02, 0x00, 0x77,
+			   0x00, 0x0a, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0878, 0x0874, 0x0870, 0x01e4, 0x01e5, 0x01e5),
+	},
+	{
+		.freq			= 5420,
+		RADIOREGS3(0x61, 0x01, 0x01, 0x02, 0x1e, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8c, 0x0c, 0x00,
+			   0xa7, 0x84, 0x00, 0x02, 0x00, 0x77, 0x00, 0x0a,
+			   0x00, 0x6f, 0x00, 0x84, 0x00, 0x02, 0x00, 0x77,
+			   0x00, 0x0a, 0x00, 0x6f, 0x00),
+		PHYREGS(0x087c, 0x0878, 0x0874, 0x01e3, 0x01e4, 0x01e5),
+	},
+	{
+		.freq			= 5430,
+		RADIOREGS3(0x61, 0x01, 0x01, 0x02, 0x1f, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x03, 0x03, 0x03, 0x8c, 0x0b, 0x00,
+			   0xa6, 0x84, 0x00, 0x02, 0x00, 0x77, 0x00, 0x0a,
+			   0x00, 0x6f, 0x00, 0x84, 0x00, 0x02, 0x00, 0x77,
+			   0x00, 0x0a, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0880, 0x087c, 0x0878, 0x01e2, 0x01e3, 0x01e4),
+	},
+	{
+		.freq			= 5440,
+		RADIOREGS3(0x5a, 0x01, 0x01, 0x02, 0x20, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8b, 0x0b, 0x00,
+			   0xa6, 0x84, 0x00, 0x02, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x84, 0x00, 0x02, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0884, 0x0880, 0x087c, 0x01e1, 0x01e2, 0x01e3),
+	},
+	{
+		.freq			= 5450,
+		RADIOREGS3(0x5a, 0x01, 0x01, 0x02, 0x21, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8b, 0x0b, 0x00,
+			   0x95, 0x84, 0x00, 0x01, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x84, 0x00, 0x01, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0888, 0x0884, 0x0880, 0x01e0, 0x01e1, 0x01e2),
+	},
+	{
+		.freq			= 5460,
+		RADIOREGS3(0x53, 0x01, 0x01, 0x02, 0x22, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8b, 0x0b, 0x00,
+			   0x95, 0x84, 0x00, 0x01, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x84, 0x00, 0x01, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x088c, 0x0888, 0x0884, 0x01df, 0x01e0, 0x01e1),
+	},
+	{
+		.freq			= 5470,
+		RADIOREGS3(0x53, 0x01, 0x01, 0x02, 0x23, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8b, 0x0b, 0x00,
+			   0x94, 0x73, 0x00, 0x01, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x01, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0890, 0x088c, 0x0888, 0x01de, 0x01df, 0x01e0),
+	},
+	{
+		.freq			= 5480,
+		RADIOREGS3(0x4d, 0x01, 0x01, 0x02, 0x24, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8a, 0x0a, 0x00,
+			   0x84, 0x73, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0894, 0x0890, 0x088c, 0x01dd, 0x01de, 0x01df),
+	},
+	{
+		.freq			= 5490,
+		RADIOREGS3(0x4d, 0x01, 0x01, 0x02, 0x25, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8a, 0x0a, 0x00,
+			   0x83, 0x73, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x0898, 0x0894, 0x0890, 0x01dd, 0x01dd, 0x01de),
+	},
+	{
+		.freq			= 5500,
+		RADIOREGS3(0x47, 0x01, 0x01, 0x02, 0x26, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8a, 0x0a, 0x00,
+			   0x82, 0x73, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x089c, 0x0898, 0x0894, 0x01dc, 0x01dd, 0x01dd),
+	},
+	{
+		.freq			= 5510,
+		RADIOREGS3(0x47, 0x01, 0x01, 0x02, 0x27, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8a, 0x0a, 0x00,
+			   0x82, 0x73, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08a0, 0x089c, 0x0898, 0x01db, 0x01dc, 0x01dd),
+	},
+	{
+		.freq			= 5520,
+		RADIOREGS3(0x40, 0x01, 0x01, 0x02, 0x28, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8a, 0x0a, 0x00,
+			   0x72, 0x73, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08a4, 0x08a0, 0x089c, 0x01da, 0x01db, 0x01dc),
+	},
+	{
+		.freq			= 5530,
+		RADIOREGS3(0x40, 0x01, 0x01, 0x02, 0x29, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8a, 0x09, 0x00,
+			   0x72, 0x73, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08a8, 0x08a4, 0x08a0, 0x01d9, 0x01da, 0x01db),
+	},
+	{
+		.freq			= 5540,
+		RADIOREGS3(0x3a, 0x01, 0x01, 0x02, 0x2a, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x8a, 0x09, 0x00,
+			   0x71, 0x73, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08ac, 0x08a8, 0x08a4, 0x01d8, 0x01d9, 0x01da),
+	},
+	{
+		.freq			= 5550,
+		RADIOREGS3(0x3a, 0x01, 0x01, 0x02, 0x2b, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x89, 0x09, 0x00,
+			   0x61, 0x73, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08b0, 0x08ac, 0x08a8, 0x01d7, 0x01d8, 0x01d9),
+	},
+	{
+		.freq			= 5560,
+		RADIOREGS3(0x34, 0x01, 0x01, 0x02, 0x2c, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x89, 0x09, 0x00,
+			   0x61, 0x73, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x73, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08b4, 0x08b0, 0x08ac, 0x01d7, 0x01d7, 0x01d8),
+	},
+	{
+		.freq			= 5570,
+		RADIOREGS3(0x34, 0x01, 0x01, 0x02, 0x2d, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x89, 0x09, 0x00,
+			   0x61, 0x62, 0x00, 0x00, 0x00, 0x77, 0x00, 0x09,
+			   0x00, 0x6f, 0x00, 0x62, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x09, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08b8, 0x08b4, 0x08b0, 0x01d6, 0x01d7, 0x01d7),
+	},
+	{
+		.freq			= 5580,
+		RADIOREGS3(0x2e, 0x01, 0x01, 0x02, 0x2e, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x89, 0x08, 0x00,
+			   0x60, 0x62, 0x00, 0x00, 0x00, 0x77, 0x00, 0x08,
+			   0x00, 0x6f, 0x00, 0x62, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x08, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08bc, 0x08b8, 0x08b4, 0x01d5, 0x01d6, 0x01d7),
+	},
+	{
+		.freq			= 5590,
+		RADIOREGS3(0x2e, 0x01, 0x01, 0x02, 0x2f, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x04, 0x04, 0x04, 0x89, 0x08, 0x00,
+			   0x50, 0x61, 0x00, 0x00, 0x00, 0x77, 0x00, 0x08,
+			   0x00, 0x6f, 0x00, 0x61, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x08, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08c0, 0x08bc, 0x08b8, 0x01d4, 0x01d5, 0x01d6),
+	},
+	{
+		.freq			= 5600,
+		RADIOREGS3(0x28, 0x01, 0x01, 0x02, 0x30, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x89, 0x08, 0x00,
+			   0x50, 0x51, 0x00, 0x00, 0x00, 0x77, 0x00, 0x08,
+			   0x00, 0x6f, 0x00, 0x51, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x08, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08c4, 0x08c0, 0x08bc, 0x01d3, 0x01d4, 0x01d5),
+	},
+	{
+		.freq			= 5610,
+		RADIOREGS3(0x28, 0x01, 0x01, 0x02, 0x31, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x89, 0x08, 0x00,
+			   0x50, 0x51, 0x00, 0x00, 0x00, 0x77, 0x00, 0x08,
+			   0x00, 0x6f, 0x00, 0x51, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x08, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08c8, 0x08c4, 0x08c0, 0x01d2, 0x01d3, 0x01d4),
+	},
+	{
+		.freq			= 5620,
+		RADIOREGS3(0x21, 0x01, 0x01, 0x02, 0x32, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x89, 0x08, 0x00,
+			   0x50, 0x50, 0x00, 0x00, 0x00, 0x77, 0x00, 0x07,
+			   0x00, 0x6f, 0x00, 0x50, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x07, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08cc, 0x08c8, 0x08c4, 0x01d2, 0x01d2, 0x01d3),
+	},
+	{
+		.freq			= 5630,
+		RADIOREGS3(0x21, 0x01, 0x01, 0x02, 0x33, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x88, 0x07, 0x00,
+			   0x50, 0x50, 0x00, 0x00, 0x00, 0x77, 0x00, 0x07,
+			   0x00, 0x6f, 0x00, 0x50, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x07, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08d0, 0x08cc, 0x08c8, 0x01d1, 0x01d2, 0x01d2),
+	},
+	{
+		.freq			= 5640,
+		RADIOREGS3(0x1c, 0x01, 0x01, 0x02, 0x34, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x88, 0x07, 0x00,
+			   0x40, 0x50, 0x00, 0x00, 0x00, 0x77, 0x00, 0x07,
+			   0x00, 0x6f, 0x00, 0x50, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x07, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08d4, 0x08d0, 0x08cc, 0x01d0, 0x01d1, 0x01d2),
+	},
+	{
+		.freq			= 5650,
+		RADIOREGS3(0x1c, 0x01, 0x01, 0x02, 0x35, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x88, 0x07, 0x00,
+			   0x40, 0x40, 0x00, 0x00, 0x00, 0x77, 0x00, 0x07,
+			   0x00, 0x6f, 0x00, 0x40, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x07, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08d8, 0x08d4, 0x08d0, 0x01cf, 0x01d0, 0x01d1),
+	},
+	{
+		.freq			= 5660,
+		RADIOREGS3(0x16, 0x01, 0x01, 0x02, 0x36, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x88, 0x07, 0x00,
+			   0x40, 0x40, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6f, 0x00, 0x40, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08dc, 0x08d8, 0x08d4, 0x01ce, 0x01cf, 0x01d0),
+	},
+	{
+		.freq			= 5670,
+		RADIOREGS3(0x16, 0x01, 0x01, 0x02, 0x37, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x88, 0x07, 0x00,
+			   0x40, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6f, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08e0, 0x08dc, 0x08d8, 0x01ce, 0x01ce, 0x01cf),
+	},
+	{
+		.freq			= 5680,
+		RADIOREGS3(0x10, 0x01, 0x01, 0x02, 0x38, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x87, 0x06, 0x00,
+			   0x30, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6f, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08e4, 0x08e0, 0x08dc, 0x01cd, 0x01ce, 0x01ce),
+	},
+	{
+		.freq			= 5690,
+		RADIOREGS3(0x10, 0x01, 0x01, 0x02, 0x39, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x87, 0x06, 0x00,
+			   0x30, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6f, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6f, 0x00),
+		PHYREGS(0x08e8, 0x08e4, 0x08e0, 0x01cc, 0x01cd, 0x01ce),
+	},
+	{
+		.freq			= 5700,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x3a, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x87, 0x06, 0x00,
+			   0x30, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6e, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6e, 0x00),
+		PHYREGS(0x08ec, 0x08e8, 0x08e4, 0x01cb, 0x01cc, 0x01cd),
+	},
+	{
+		.freq			= 5710,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x3b, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x87, 0x06, 0x00,
+			   0x30, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6e, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6e, 0x00),
+		PHYREGS(0x08f0, 0x08ec, 0x08e8, 0x01ca, 0x01cb, 0x01cc),
+	},
+	{
+		.freq			= 5720,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x3c, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x87, 0x06, 0x00,
+			   0x30, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6e, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6e, 0x00),
+		PHYREGS(0x08f4, 0x08f0, 0x08ec, 0x01c9, 0x01ca, 0x01cb),
+	},
+	{
+		.freq			= 5725,
+		RADIOREGS3(0x03, 0x01, 0x02, 0x04, 0x79, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x05, 0x05, 0x05, 0x87, 0x06, 0x00,
+			   0x30, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6e, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6e, 0x00),
+		PHYREGS(0x08f6, 0x08f2, 0x08ee, 0x01c9, 0x01ca, 0x01cb),
+	},
+	{
+		.freq			= 5730,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x3d, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x87, 0x05, 0x00,
+			   0x20, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6e, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6e, 0x00),
+		PHYREGS(0x08f8, 0x08f4, 0x08f0, 0x01c9, 0x01c9, 0x01ca),
+	},
+	{
+		.freq			= 5735,
+		RADIOREGS3(0x03, 0x01, 0x02, 0x04, 0x7b, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x05, 0x05, 0x05, 0x87, 0x05, 0x00,
+			   0x20, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6d, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6d, 0x00),
+		PHYREGS(0x08fa, 0x08f6, 0x08f2, 0x01c8, 0x01c9, 0x01ca),
+	},
+	{
+		.freq			= 5740,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x3e, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x87, 0x05, 0x00,
+			   0x20, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6d, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6d, 0x00),
+		PHYREGS(0x08fc, 0x08f8, 0x08f4, 0x01c8, 0x01c9, 0x01c9),
+	},
+	{
+		.freq			= 5745,
+		RADIOREGS3(0xfe, 0x00, 0x02, 0x04, 0x7d, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x05, 0x05, 0x05, 0x87, 0x05, 0x00,
+			   0x20, 0x30, 0x00, 0x00, 0x00, 0x77, 0x00, 0x06,
+			   0x00, 0x6d, 0x00, 0x30, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x06, 0x00, 0x6d, 0x00),
+		PHYREGS(0x08fe, 0x08fa, 0x08f6, 0x01c8, 0x01c8, 0x01c9),
+	},
+	{
+		.freq			= 5750,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x3f, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x87, 0x05, 0x00,
+			   0x20, 0x20, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6d, 0x00, 0x20, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6d, 0x00),
+		PHYREGS(0x0900, 0x08fc, 0x08f8, 0x01c7, 0x01c8, 0x01c9),
+	},
+	{
+		.freq			= 5755,
+		RADIOREGS3(0xfe, 0x00, 0x02, 0x04, 0x7f, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x05, 0x05, 0x05, 0x87, 0x05, 0x00,
+			   0x10, 0x20, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6c, 0x00, 0x20, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6c, 0x00),
+		PHYREGS(0x0902, 0x08fe, 0x08fa, 0x01c7, 0x01c8, 0x01c8),
+	},
+	{
+		.freq			= 5760,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x40, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x86, 0x05, 0x00,
+			   0x10, 0x20, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6c, 0x00, 0x20, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6c, 0x00),
+		PHYREGS(0x0904, 0x0900, 0x08fc, 0x01c6, 0x01c7, 0x01c8),
+	},
+	{
+		.freq			= 5765,
+		RADIOREGS3(0xf8, 0x00, 0x02, 0x04, 0x81, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x05, 0x05, 0x05, 0x86, 0x05, 0x00,
+			   0x10, 0x10, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6c, 0x00, 0x10, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6c, 0x00),
+		PHYREGS(0x0906, 0x0902, 0x08fe, 0x01c6, 0x01c7, 0x01c8),
+	},
+	{
+		.freq			= 5770,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x41, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x86, 0x04, 0x00,
+			   0x10, 0x10, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6b, 0x00, 0x10, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6b, 0x00),
+		PHYREGS(0x0908, 0x0904, 0x0900, 0x01c6, 0x01c6, 0x01c7),
+	},
+	{
+		.freq			= 5775,
+		RADIOREGS3(0xf8, 0x00, 0x02, 0x04, 0x83, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x05, 0x05, 0x05, 0x86, 0x04, 0x00,
+			   0x10, 0x10, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6b, 0x00, 0x10, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6b, 0x00),
+		PHYREGS(0x090a, 0x0906, 0x0902, 0x01c5, 0x01c6, 0x01c7),
+	},
+	{
+		.freq			= 5780,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x42, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x05, 0x05, 0x05, 0x86, 0x04, 0x00,
+			   0x10, 0x10, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6b, 0x00, 0x10, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6b, 0x00),
+		PHYREGS(0x090c, 0x0908, 0x0904, 0x01c5, 0x01c6, 0x01c6),
+	},
+	{
+		.freq			= 5785,
+		RADIOREGS3(0xf2, 0x00, 0x02, 0x04, 0x85, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x10, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6b, 0x00, 0x10, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6b, 0x00),
+		PHYREGS(0x090e, 0x090a, 0x0906, 0x01c4, 0x01c5, 0x01c6),
+	},
+	{
+		.freq			= 5790,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x43, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x10, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6b, 0x00, 0x10, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6b, 0x00),
+		PHYREGS(0x0910, 0x090c, 0x0908, 0x01c4, 0x01c5, 0x01c6),
+	},
+	{
+		.freq			= 5795,
+		RADIOREGS3(0xf2, 0x00, 0x02, 0x04, 0x87, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6b, 0x00),
+		PHYREGS(0x0912, 0x090e, 0x090a, 0x01c4, 0x01c4, 0x01c5),
+	},
+	{
+		.freq			= 5800,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x44, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6b, 0x00),
+		PHYREGS(0x0914, 0x0910, 0x090c, 0x01c3, 0x01c4, 0x01c5),
+	},
+	{
+		.freq			= 5805,
+		RADIOREGS3(0xed, 0x00, 0x02, 0x04, 0x89, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6a, 0x00),
+		PHYREGS(0x0916, 0x0912, 0x090e, 0x01c3, 0x01c4, 0x01c4),
+	},
+	{
+		.freq			= 5810,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x45, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6a, 0x00),
+		PHYREGS(0x0918, 0x0914, 0x0910, 0x01c2, 0x01c3, 0x01c4),
+	},
+	{
+		.freq			= 5815,
+		RADIOREGS3(0xed, 0x00, 0x02, 0x04, 0x8b, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6a, 0x00),
+		PHYREGS(0x091a, 0x0916, 0x0912, 0x01c2, 0x01c3, 0x01c4),
+	},
+	{
+		.freq			= 5820,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x46, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x6a, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x6a, 0x00),
+		PHYREGS(0x091c, 0x0918, 0x0914, 0x01c2, 0x01c2, 0x01c3),
+	},
+	{
+		.freq			= 5825,
+		RADIOREGS3(0xed, 0x00, 0x02, 0x04, 0x8d, 0x05, 0x05, 0x02,
+			   0x15, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x69, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x69, 0x00),
+		PHYREGS(0x091e, 0x091a, 0x0916, 0x01c1, 0x01c2, 0x01c3),
+	},
+	{
+		.freq			= 5830,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x47, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x05,
+			   0x00, 0x69, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x05, 0x00, 0x69, 0x00),
+		PHYREGS(0x0920, 0x091c, 0x0918, 0x01c1, 0x01c2, 0x01c2),
+	},
+	{
+		.freq			= 5840,
+		RADIOREGS3(0x0a, 0x01, 0x01, 0x02, 0x48, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x86, 0x04, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x04,
+			   0x00, 0x69, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x04, 0x00, 0x69, 0x00),
+		PHYREGS(0x0924, 0x0920, 0x091c, 0x01c0, 0x01c1, 0x01c2),
+	},
+	{
+		.freq			= 5850,
+		RADIOREGS3(0xe0, 0x00, 0x01, 0x02, 0x49, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x85, 0x03, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x04,
+			   0x00, 0x69, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x04, 0x00, 0x69, 0x00),
+		PHYREGS(0x0928, 0x0924, 0x0920, 0x01bf, 0x01c0, 0x01c1),
+	},
+	{
+		.freq			= 5860,
+		RADIOREGS3(0xde, 0x00, 0x01, 0x02, 0x4a, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x85, 0x03, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x04,
+			   0x00, 0x69, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x04, 0x00, 0x69, 0x00),
+		PHYREGS(0x092c, 0x0928, 0x0924, 0x01bf, 0x01bf, 0x01c0),
+	},
+	{
+		.freq			= 5870,
+		RADIOREGS3(0xdb, 0x00, 0x01, 0x02, 0x4b, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x85, 0x03, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x04,
+			   0x00, 0x68, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x04, 0x00, 0x68, 0x00),
+		PHYREGS(0x0930, 0x092c, 0x0928, 0x01be, 0x01bf, 0x01bf),
+	},
+	{
+		.freq			= 5880,
+		RADIOREGS3(0xd8, 0x00, 0x01, 0x02, 0x4c, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x85, 0x03, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x04,
+			   0x00, 0x68, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x04, 0x00, 0x68, 0x00),
+		PHYREGS(0x0934, 0x0930, 0x092c, 0x01bd, 0x01be, 0x01bf),
+	},
+	{
+		.freq			= 5890,
+		RADIOREGS3(0xd6, 0x00, 0x01, 0x02, 0x4d, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x85, 0x03, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x04,
+			   0x00, 0x68, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x04, 0x00, 0x68, 0x00),
+		PHYREGS(0x0938, 0x0934, 0x0930, 0x01bc, 0x01bd, 0x01be),
+	},
+	{
+		.freq			= 5900,
+		RADIOREGS3(0xd3, 0x00, 0x01, 0x02, 0x4e, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x85, 0x03, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x04,
+			   0x00, 0x68, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x04, 0x00, 0x68, 0x00),
+		PHYREGS(0x093c, 0x0938, 0x0934, 0x01bc, 0x01bc, 0x01bd),
+	},
+	{
+		.freq			= 5910,
+		RADIOREGS3(0xd6, 0x00, 0x01, 0x02, 0x4f, 0x05, 0x05, 0x02,
+			   0x0c, 0x01, 0x06, 0x06, 0x06, 0x85, 0x03, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x00, 0x77, 0x00, 0x04,
+			   0x00, 0x68, 0x00, 0x00, 0x00, 0x00, 0x00, 0x77,
+			   0x00, 0x04, 0x00, 0x68, 0x00),
+		PHYREGS(0x0940, 0x093c, 0x0938, 0x01bb, 0x01bc, 0x01bc),
+	},
+	{
+		.freq			= 2412,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x6c, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x04, 0x04, 0x04, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x78, 0x00, 0x03, 0x00, 0x70, 0x00,
+			   0x0b, 0x00, 0x0a, 0x00, 0x89, 0x00, 0x03, 0x00,
+			   0x70, 0x00, 0x0b, 0x00, 0x0a),
+		PHYREGS(0x03c9, 0x03c5, 0x03c1, 0x043a, 0x043f, 0x0443),
+	},
+	{
+		.freq			= 2417,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x71, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x05, 0x05, 0x05, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x78, 0x00, 0x03, 0x00, 0x70, 0x00,
+			   0x0b, 0x00, 0x0a, 0x00, 0x89, 0x00, 0x03, 0x00,
+			   0x70, 0x00, 0x0b, 0x00, 0x0a),
+		PHYREGS(0x03cb, 0x03c7, 0x03c3, 0x0438, 0x043d, 0x0441),
+	},
+	{
+		.freq			= 2422,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x76, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x05, 0x05, 0x05, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x67, 0x00, 0x03, 0x00, 0x70, 0x00,
+			   0x0b, 0x00, 0x0a, 0x00, 0x89, 0x00, 0x03, 0x00,
+			   0x70, 0x00, 0x0b, 0x00, 0x0a),
+		PHYREGS(0x03cd, 0x03c9, 0x03c5, 0x0436, 0x043a, 0x043f),
+	},
+	{
+		.freq			= 2427,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x7b, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x05, 0x05, 0x05, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x57, 0x00, 0x03, 0x00, 0x70, 0x00,
+			   0x0a, 0x00, 0x0a, 0x00, 0x78, 0x00, 0x03, 0x00,
+			   0x70, 0x00, 0x0a, 0x00, 0x0a),
+		PHYREGS(0x03cf, 0x03cb, 0x03c7, 0x0434, 0x0438, 0x043d),
+	},
+	{
+		.freq			= 2432,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x80, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x05, 0x05, 0x05, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x56, 0x00, 0x03, 0x00, 0x70, 0x00,
+			   0x0a, 0x00, 0x0a, 0x00, 0x77, 0x00, 0x03, 0x00,
+			   0x70, 0x00, 0x0a, 0x00, 0x0a),
+		PHYREGS(0x03d1, 0x03cd, 0x03c9, 0x0431, 0x0436, 0x043a),
+	},
+	{
+		.freq			= 2437,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x85, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x05, 0x05, 0x05, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x46, 0x00, 0x03, 0x00, 0x70, 0x00,
+			   0x0a, 0x00, 0x0a, 0x00, 0x76, 0x00, 0x03, 0x00,
+			   0x70, 0x00, 0x0a, 0x00, 0x0a),
+		PHYREGS(0x03d3, 0x03cf, 0x03cb, 0x042f, 0x0434, 0x0438),
+	},
+	{
+		.freq			= 2442,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x8a, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x05, 0x05, 0x05, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x45, 0x00, 0x02, 0x00, 0x70, 0x00,
+			   0x0a, 0x00, 0x0a, 0x00, 0x66, 0x00, 0x02, 0x00,
+			   0x70, 0x00, 0x0a, 0x00, 0x0a),
+		PHYREGS(0x03d5, 0x03d1, 0x03cd, 0x042d, 0x0431, 0x0436),
+	},
+	{
+		.freq			= 2447,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x8f, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x06, 0x06, 0x06, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x34, 0x00, 0x02, 0x00, 0x70, 0x00,
+			   0x0a, 0x00, 0x09, 0x00, 0x55, 0x00, 0x02, 0x00,
+			   0x70, 0x00, 0x0a, 0x00, 0x09),
+		PHYREGS(0x03d7, 0x03d3, 0x03cf, 0x042b, 0x042f, 0x0434),
+	},
+	{
+		.freq			= 2452,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x94, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x06, 0x06, 0x06, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x23, 0x00, 0x02, 0x00, 0x70, 0x00,
+			   0x0a, 0x00, 0x09, 0x00, 0x45, 0x00, 0x02, 0x00,
+			   0x70, 0x00, 0x0a, 0x00, 0x09),
+		PHYREGS(0x03d9, 0x03d5, 0x03d1, 0x0429, 0x042d, 0x0431),
+	},
+	{
+		.freq			= 2457,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x99, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x06, 0x06, 0x06, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x12, 0x00, 0x02, 0x00, 0x70, 0x00,
+			   0x0a, 0x00, 0x09, 0x00, 0x34, 0x00, 0x02, 0x00,
+			   0x70, 0x00, 0x0a, 0x00, 0x09),
+		PHYREGS(0x03db, 0x03d7, 0x03d3, 0x0427, 0x042b, 0x042f),
+	},
+	{
+		.freq			= 2462,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0x9e, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x06, 0x06, 0x06, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x02, 0x00, 0x02, 0x00, 0x70, 0x00,
+			   0x09, 0x00, 0x09, 0x00, 0x33, 0x00, 0x02, 0x00,
+			   0x70, 0x00, 0x09, 0x00, 0x09),
+		PHYREGS(0x03dd, 0x03d9, 0x03d5, 0x0424, 0x0429, 0x042d),
+	},
+	{
+		.freq			= 2467,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0xa3, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x06, 0x06, 0x06, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x01, 0x00, 0x02, 0x00, 0x70, 0x00,
+			   0x09, 0x00, 0x09, 0x00, 0x22, 0x00, 0x02, 0x00,
+			   0x70, 0x00, 0x09, 0x00, 0x09),
+		PHYREGS(0x03df, 0x03db, 0x03d7, 0x0422, 0x0427, 0x042b),
+	},
+	{
+		.freq			= 2472,
+		RADIOREGS3(0x00, 0x01, 0x03, 0x09, 0xa8, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x07, 0x07, 0x07, 0x8f, 0x30, 0x00,
+			   0x00, 0x00, 0x01, 0x00, 0x02, 0x00, 0x70, 0x00,
+			   0x09, 0x00, 0x09, 0x00, 0x11, 0x00, 0x02, 0x00,
+			   0x70, 0x00, 0x09, 0x00, 0x09),
+		PHYREGS(0x03e1, 0x03dd, 0x03d9, 0x0420, 0x0424, 0x0429),
+	},
+	{
+		.freq			= 2484,
+		RADIOREGS3(0xff, 0x01, 0x03, 0x09, 0xb4, 0x06, 0x06, 0x04,
+			   0x2b, 0x01, 0x07, 0x07, 0x07, 0x8f, 0x20, 0x00,
+			   0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x70, 0x00,
+			   0x09, 0x00, 0x09, 0x00, 0x00, 0x00, 0x02, 0x00,
+			   0x70, 0x00, 0x09, 0x00, 0x09),
+		PHYREGS(0x03e6, 0x03e2, 0x03de, 0x041b, 0x041f, 0x0424),
+	},
+};
+
+static const struct b2056_inittabs_pts
+*b43_nphy_get_inittabs_rev3(struct b43_wldev *dev)
+{
+	struct b43_phy *phy = &dev->phy;
+
+	switch (dev->phy.rev) {
+	case 3:
+		return &b2056_inittab_phy_rev3;
+	case 4:
+		return &b2056_inittab_phy_rev4;
+	default:
+		switch (phy->radio_rev) {
+		case 5:
+			return &b2056_inittab_radio_rev5;
+		case 6:
+			return &b2056_inittab_radio_rev6;
+		case 7:
+		case 9:
+			return &b2056_inittab_radio_rev7_9;
+		case 8:
+			return &b2056_inittab_radio_rev8;
+		case 11:
+			return &b2056_inittab_radio_rev11;
+		}
+	}
+
+	return NULL;
+}
+
 static void b2056_upload_inittab(struct b43_wldev *dev, bool ghz5,
 				 bool ignore_uploadflag, u16 routing,
 				 const struct b2056_inittab_entry *e,
@@ -9037,11 +10230,11 @@ void b2056_upload_inittabs(struct b43_wldev *dev,
 {
 	const struct b2056_inittabs_pts *pts;
 
-	if (dev->phy.rev >= ARRAY_SIZE(b2056_inittabs)) {
+	pts = b43_nphy_get_inittabs_rev3(dev);
+	if (!pts) {
 		B43_WARN_ON(1);
 		return;
 	}
-	pts = &b2056_inittabs[dev->phy.rev];
 
 	b2056_upload_inittab(dev, ghz5, ignore_uploadflag,
 				B2056_SYN, pts->syn, pts->syn_length);
@@ -9060,11 +10253,12 @@ void b2056_upload_syn_pll_cp2(struct b43_wldev *dev, bool ghz5)
 	const struct b2056_inittabs_pts *pts;
 	const struct b2056_inittab_entry *e;
 
-	if (dev->phy.rev >= ARRAY_SIZE(b2056_inittabs)) {
+	pts = b43_nphy_get_inittabs_rev3(dev);
+	if (!pts) {
 		B43_WARN_ON(1);
 		return;
 	}
-	pts = &b2056_inittabs[dev->phy.rev];
+
 	e = &pts->syn[B2056_SYN_PLL_CP2];
 
 	b43_radio_write(dev, B2056_SYN_PLL_CP2, ghz5 ? e->ghz5 : e->ghz2);
@@ -9073,38 +10267,46 @@ void b2056_upload_syn_pll_cp2(struct b43_wldev *dev, bool ghz5)
 const struct b43_nphy_channeltab_entry_rev3 *
 b43_nphy_get_chantabent_rev3(struct b43_wldev *dev, u16 freq)
 {
+	struct b43_phy *phy = &dev->phy;
 	const struct b43_nphy_channeltab_entry_rev3 *e;
 	unsigned int length, i;
 
-	switch (dev->phy.rev) {
+	switch (phy->rev) {
 	case 3:
-		e = b43_nphy_channeltab_rev3;
-		length = ARRAY_SIZE(b43_nphy_channeltab_rev3);
+		e = b43_nphy_channeltab_phy_rev3;
+		length = ARRAY_SIZE(b43_nphy_channeltab_phy_rev3);
 		break;
 	case 4:
-		e = b43_nphy_channeltab_rev4;
-		length = ARRAY_SIZE(b43_nphy_channeltab_rev4);
-		break;
-	case 5:
-		e = b43_nphy_channeltab_rev5;
-		length = ARRAY_SIZE(b43_nphy_channeltab_rev5);
-		break;
-	case 6:
-		e = b43_nphy_channeltab_rev6;
-		length = ARRAY_SIZE(b43_nphy_channeltab_rev6);
-		break;
-	case 7:
-	case 9:
-		e = b43_nphy_channeltab_rev7_9;
-		length = ARRAY_SIZE(b43_nphy_channeltab_rev7_9);
-		break;
-	case 8:
-		e = b43_nphy_channeltab_rev8;
-		length = ARRAY_SIZE(b43_nphy_channeltab_rev8);
+		e = b43_nphy_channeltab_phy_rev4;
+		length = ARRAY_SIZE(b43_nphy_channeltab_phy_rev4);
 		break;
 	default:
-		B43_WARN_ON(1);
-		return NULL;
+		switch (phy->radio_rev) {
+		case 5:
+			e = b43_nphy_channeltab_radio_rev5;
+			length = ARRAY_SIZE(b43_nphy_channeltab_radio_rev5);
+			break;
+		case 6:
+			e = b43_nphy_channeltab_radio_rev6;
+			length = ARRAY_SIZE(b43_nphy_channeltab_radio_rev6);
+			break;
+		case 7:
+		case 9:
+			e = b43_nphy_channeltab_radio_rev7_9;
+			length = ARRAY_SIZE(b43_nphy_channeltab_radio_rev7_9);
+			break;
+		case 8:
+			e = b43_nphy_channeltab_radio_rev8;
+			length = ARRAY_SIZE(b43_nphy_channeltab_radio_rev8);
+			break;
+		case 11:
+			e = b43_nphy_channeltab_radio_rev11;
+			length = ARRAY_SIZE(b43_nphy_channeltab_radio_rev11);
+			break;
+		default:
+			B43_WARN_ON(1);
+			return NULL;
+		}
 	}
 
 	for (i = 0; i < length; i++, e++) {
diff --git a/drivers/net/wireless/b43/tables_nphy.c b/drivers/net/wireless/b43/tables_nphy.c
index 94c755fdda1..4047c05e380 100644
--- a/drivers/net/wireless/b43/tables_nphy.c
+++ b/drivers/net/wireless/b43/tables_nphy.c
@@ -1627,74 +1627,7 @@ static const u32 b43_ntab_tdtrn_r3[] = {
 	0xfa58fc00, 0x0b64fc7e, 0x0800f7b6, 0x00f006be,
 };
 
-static const u32 b43_ntab_noisevar0_r3[] = {
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
-};
-
-static const u32 b43_ntab_noisevar1_r3[] = {
+static const u32 b43_ntab_noisevar_r3[] = {
 	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
 	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
 	0x02110211, 0x0000014d, 0x02110211, 0x0000014d,
@@ -3109,31 +3042,32 @@ static void b43_nphy_tables_init_rev3(struct b43_wldev *dev)
 		antswlut = sprom->fem.ghz2.antswlut;
 
 	/* Static tables */
-	ntab_upload(dev, B43_NTAB_FRAMESTRUCT_R3, b43_ntab_framestruct_r3);
-	ntab_upload(dev, B43_NTAB_PILOT_R3, b43_ntab_pilot_r3);
-	ntab_upload(dev, B43_NTAB_TMAP_R3, b43_ntab_tmap_r3);
-	ntab_upload(dev, B43_NTAB_INTLEVEL_R3, b43_ntab_intlevel_r3);
-	ntab_upload(dev, B43_NTAB_TDTRN_R3, b43_ntab_tdtrn_r3);
-	ntab_upload(dev, B43_NTAB_NOISEVAR0_R3, b43_ntab_noisevar0_r3);
-	ntab_upload(dev, B43_NTAB_NOISEVAR1_R3, b43_ntab_noisevar1_r3);
-	ntab_upload(dev, B43_NTAB_MCS_R3, b43_ntab_mcs_r3);
-	ntab_upload(dev, B43_NTAB_TDI20A0_R3, b43_ntab_tdi20a0_r3);
-	ntab_upload(dev, B43_NTAB_TDI20A1_R3, b43_ntab_tdi20a1_r3);
-	ntab_upload(dev, B43_NTAB_TDI40A0_R3, b43_ntab_tdi40a0_r3);
-	ntab_upload(dev, B43_NTAB_TDI40A1_R3, b43_ntab_tdi40a1_r3);
-	ntab_upload(dev, B43_NTAB_PILOTLT_R3, b43_ntab_pilotlt_r3);
-	ntab_upload(dev, B43_NTAB_CHANEST_R3, b43_ntab_channelest_r3);
-	ntab_upload(dev, B43_NTAB_FRAMELT_R3, b43_ntab_framelookup_r3);
-	ntab_upload(dev, B43_NTAB_C0_ESTPLT_R3, b43_ntab_estimatepowerlt0_r3);
-	ntab_upload(dev, B43_NTAB_C1_ESTPLT_R3, b43_ntab_estimatepowerlt1_r3);
-	ntab_upload(dev, B43_NTAB_C0_ADJPLT_R3, b43_ntab_adjustpower0_r3);
-	ntab_upload(dev, B43_NTAB_C1_ADJPLT_R3, b43_ntab_adjustpower1_r3);
-	ntab_upload(dev, B43_NTAB_C0_GAINCTL_R3, b43_ntab_gainctl0_r3);
-	ntab_upload(dev, B43_NTAB_C1_GAINCTL_R3, b43_ntab_gainctl1_r3);
-	ntab_upload(dev, B43_NTAB_C0_IQLT_R3, b43_ntab_iqlt0_r3);
-	ntab_upload(dev, B43_NTAB_C1_IQLT_R3, b43_ntab_iqlt1_r3);
-	ntab_upload(dev, B43_NTAB_C0_LOFEEDTH_R3, b43_ntab_loftlt0_r3);
-	ntab_upload(dev, B43_NTAB_C1_LOFEEDTH_R3, b43_ntab_loftlt1_r3);
+	if (dev->phy.do_full_init) {
+		ntab_upload(dev, B43_NTAB_FRAMESTRUCT_R3, b43_ntab_framestruct_r3);
+		ntab_upload(dev, B43_NTAB_PILOT_R3, b43_ntab_pilot_r3);
+		ntab_upload(dev, B43_NTAB_TMAP_R3, b43_ntab_tmap_r3);
+		ntab_upload(dev, B43_NTAB_INTLEVEL_R3, b43_ntab_intlevel_r3);
+		ntab_upload(dev, B43_NTAB_TDTRN_R3, b43_ntab_tdtrn_r3);
+		ntab_upload(dev, B43_NTAB_NOISEVAR_R3, b43_ntab_noisevar_r3);
+		ntab_upload(dev, B43_NTAB_MCS_R3, b43_ntab_mcs_r3);
+		ntab_upload(dev, B43_NTAB_TDI20A0_R3, b43_ntab_tdi20a0_r3);
+		ntab_upload(dev, B43_NTAB_TDI20A1_R3, b43_ntab_tdi20a1_r3);
+		ntab_upload(dev, B43_NTAB_TDI40A0_R3, b43_ntab_tdi40a0_r3);
+		ntab_upload(dev, B43_NTAB_TDI40A1_R3, b43_ntab_tdi40a1_r3);
+		ntab_upload(dev, B43_NTAB_PILOTLT_R3, b43_ntab_pilotlt_r3);
+		ntab_upload(dev, B43_NTAB_CHANEST_R3, b43_ntab_channelest_r3);
+		ntab_upload(dev, B43_NTAB_FRAMELT_R3, b43_ntab_framelookup_r3);
+		ntab_upload(dev, B43_NTAB_C0_ESTPLT_R3, b43_ntab_estimatepowerlt0_r3);
+		ntab_upload(dev, B43_NTAB_C1_ESTPLT_R3, b43_ntab_estimatepowerlt1_r3);
+		ntab_upload(dev, B43_NTAB_C0_ADJPLT_R3, b43_ntab_adjustpower0_r3);
+		ntab_upload(dev, B43_NTAB_C1_ADJPLT_R3, b43_ntab_adjustpower1_r3);
+		ntab_upload(dev, B43_NTAB_C0_GAINCTL_R3, b43_ntab_gainctl0_r3);
+		ntab_upload(dev, B43_NTAB_C1_GAINCTL_R3, b43_ntab_gainctl1_r3);
+		ntab_upload(dev, B43_NTAB_C0_IQLT_R3, b43_ntab_iqlt0_r3);
+		ntab_upload(dev, B43_NTAB_C1_IQLT_R3, b43_ntab_iqlt1_r3);
+		ntab_upload(dev, B43_NTAB_C0_LOFEEDTH_R3, b43_ntab_loftlt0_r3);
+		ntab_upload(dev, B43_NTAB_C1_LOFEEDTH_R3, b43_ntab_loftlt1_r3);
+	}
 
 	/* Volatile tables */
 	if (antswlut < ARRAY_SIZE(b43_ntab_antswctl_r3))
@@ -3146,20 +3080,22 @@ static void b43_nphy_tables_init_rev3(struct b43_wldev *dev)
 static void b43_nphy_tables_init_rev0(struct b43_wldev *dev)
 {
 	/* Static tables */
-	ntab_upload(dev, B43_NTAB_FRAMESTRUCT, b43_ntab_framestruct);
-	ntab_upload(dev, B43_NTAB_FRAMELT, b43_ntab_framelookup);
-	ntab_upload(dev, B43_NTAB_TMAP, b43_ntab_tmap);
-	ntab_upload(dev, B43_NTAB_TDTRN, b43_ntab_tdtrn);
-	ntab_upload(dev, B43_NTAB_INTLEVEL, b43_ntab_intlevel);
-	ntab_upload(dev, B43_NTAB_PILOT, b43_ntab_pilot);
-	ntab_upload(dev, B43_NTAB_TDI20A0, b43_ntab_tdi20a0);
-	ntab_upload(dev, B43_NTAB_TDI20A1, b43_ntab_tdi20a1);
-	ntab_upload(dev, B43_NTAB_TDI40A0, b43_ntab_tdi40a0);
-	ntab_upload(dev, B43_NTAB_TDI40A1, b43_ntab_tdi40a1);
-	ntab_upload(dev, B43_NTAB_CHANEST, b43_ntab_channelest);
-	ntab_upload(dev, B43_NTAB_MCS, b43_ntab_mcs);
-	ntab_upload(dev, B43_NTAB_NOISEVAR10, b43_ntab_noisevar10);
-	ntab_upload(dev, B43_NTAB_NOISEVAR11, b43_ntab_noisevar11);
+	if (dev->phy.do_full_init) {
+		ntab_upload(dev, B43_NTAB_FRAMESTRUCT, b43_ntab_framestruct);
+		ntab_upload(dev, B43_NTAB_FRAMELT, b43_ntab_framelookup);
+		ntab_upload(dev, B43_NTAB_TMAP, b43_ntab_tmap);
+		ntab_upload(dev, B43_NTAB_TDTRN, b43_ntab_tdtrn);
+		ntab_upload(dev, B43_NTAB_INTLEVEL, b43_ntab_intlevel);
+		ntab_upload(dev, B43_NTAB_PILOT, b43_ntab_pilot);
+		ntab_upload(dev, B43_NTAB_TDI20A0, b43_ntab_tdi20a0);
+		ntab_upload(dev, B43_NTAB_TDI20A1, b43_ntab_tdi20a1);
+		ntab_upload(dev, B43_NTAB_TDI40A0, b43_ntab_tdi40a0);
+		ntab_upload(dev, B43_NTAB_TDI40A1, b43_ntab_tdi40a1);
+		ntab_upload(dev, B43_NTAB_CHANEST, b43_ntab_channelest);
+		ntab_upload(dev, B43_NTAB_MCS, b43_ntab_mcs);
+		ntab_upload(dev, B43_NTAB_NOISEVAR10, b43_ntab_noisevar10);
+		ntab_upload(dev, B43_NTAB_NOISEVAR11, b43_ntab_noisevar11);
+	}
 
 	/* Volatile tables */
 	ntab_upload(dev, B43_NTAB_BDI, b43_ntab_bdi);
diff --git a/drivers/net/wireless/b43/tables_nphy.h b/drivers/net/wireless/b43/tables_nphy.h
index 9ff33adcff8..3a58aee4c4c 100644
--- a/drivers/net/wireless/b43/tables_nphy.h
+++ b/drivers/net/wireless/b43/tables_nphy.h
@@ -143,8 +143,7 @@ struct nphy_gain_ctl_workaround_entry *b43_nphy_get_gain_ctl_workaround_ent(
 #define B43_NTAB_TMAP_R3		B43_NTAB32(12,   0) /* TM AP  */
 #define B43_NTAB_INTLEVEL_R3		B43_NTAB32(13,   0) /* INT LV  */
 #define B43_NTAB_TDTRN_R3		B43_NTAB32(14,   0) /* TD TRN  */
-#define B43_NTAB_NOISEVAR0_R3		B43_NTAB32(16,   0) /* noise variance 0  */
-#define B43_NTAB_NOISEVAR1_R3		B43_NTAB32(16, 128) /* noise variance 1  */
+#define B43_NTAB_NOISEVAR_R3		B43_NTAB32(16,   0) /* noise variance */
 #define B43_NTAB_MCS_R3			B43_NTAB16(18,   0) /* MCS  */
 #define B43_NTAB_TDI20A0_R3		B43_NTAB32(19, 128) /* TDI 20/0  */
 #define B43_NTAB_TDI20A1_R3		B43_NTAB32(19, 256) /* TDI 20/1  */
diff --git a/drivers/net/wireless/b43/wa.c b/drivers/net/wireless/b43/wa.c
index 9b1a038be08..c218c08fb2f 100644
--- a/drivers/net/wireless/b43/wa.c
+++ b/drivers/net/wireless/b43/wa.c
@@ -441,7 +441,7 @@ static void b43_wa_altagc(struct b43_wldev *dev)
 
 static void b43_wa_tr_ltov(struct b43_wldev *dev) /* TR Lookup Table Original Values */
 {
-	b43_gtab_write(dev, B43_GTAB_ORIGTR, 0, 0xC480);
+	b43_gtab_write(dev, B43_GTAB_ORIGTR, 0, 0x7654);
 }
 
 static void b43_wa_cpll_nonpilot(struct b43_wldev *dev)
diff --git a/drivers/net/wireless/b43/xmit.c b/drivers/net/wireless/b43/xmit.c
index 31adb8cf029..6e6ef3fc224 100644
--- a/drivers/net/wireless/b43/xmit.c
+++ b/drivers/net/wireless/b43/xmit.c
@@ -408,7 +408,7 @@ int b43_generate_txhdr(struct b43_wldev *dev,
 		mac_ctl |= B43_TXH_MAC_HWSEQ;
 	if (info->flags & IEEE80211_TX_CTL_FIRST_FRAGMENT)
 		mac_ctl |= B43_TXH_MAC_STMSDU;
-	if (phy->type == B43_PHYTYPE_A)
+	if (!phy->gmode)
 		mac_ctl |= B43_TXH_MAC_5GHZ;
 
 	/* Overwrite rates[0].count to make the retry calculation
@@ -811,9 +811,13 @@ void b43_rx(struct b43_wldev *dev, struct sk_buff *skb, const void *_rxhdr)
 		break;
 	case B43_PHYTYPE_G:
 		status.band = IEEE80211_BAND_2GHZ;
-		/* chanid is the radio channel cookie value as used
-		 * to tune the radio. */
-		status.freq = chanid + 2400;
+		/* Somewhere between 478.104 and 508.1084 firmware for G-PHY
+		 * has been modified to be compatible with N-PHY and others.
+		 */
+		if (dev->fw.rev >= 508)
+			status.freq = ieee80211_channel_to_frequency(chanid, status.band);
+		else
+			status.freq = chanid + 2400;
 		break;
 	case B43_PHYTYPE_N:
 	case B43_PHYTYPE_LP:
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/Makefile b/drivers/net/wireless/brcm80211/brcmfmac/Makefile
index 1d2ceac3a22..98e67c18f27 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/Makefile
+++ b/drivers/net/wireless/brcm80211/brcmfmac/Makefile
@@ -33,7 +33,7 @@ brcmfmac-objs += \
 		bcdc.o \
 		dhd_common.o \
 		dhd_linux.o \
-		nvram.o \
+		firmware.o \
 		btcoex.o
 brcmfmac-$(CONFIG_BRCMFMAC_SDIO) += \
 		dhd_sdio.o \
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd.h b/drivers/net/wireless/brcm80211/brcmfmac/dhd.h
index 939d6b13292..16f9ab2568a 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd.h
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd.h
@@ -186,7 +186,7 @@ void brcmf_del_if(struct brcmf_pub *drvr, s32 bssidx);
 void brcmf_txflowblock_if(struct brcmf_if *ifp,
 			  enum brcmf_netif_stop_reason reason, bool state);
 u32 brcmf_get_chip_info(struct brcmf_if *ifp);
-void brcmf_txfinalize(struct brcmf_pub *drvr, struct sk_buff *txp,
+void brcmf_txfinalize(struct brcmf_pub *drvr, struct sk_buff *txp, u8 ifidx,
 		      bool success);
 
 /* Sets dongle media info (drv_version, mac address). */
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h b/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h
index c4535616064..7735328fff2 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_bus.h
@@ -63,7 +63,6 @@ struct brcmf_bus_dcmd {
  */
 struct brcmf_bus_ops {
 	int (*preinit)(struct device *dev);
-	int (*init)(struct device *dev);
 	void (*stop)(struct device *dev);
 	int (*txdata)(struct device *dev, struct sk_buff *skb);
 	int (*txctl)(struct device *dev, unsigned char *msg, uint len);
@@ -99,6 +98,7 @@ struct brcmf_bus {
 	unsigned long tx_realloc;
 	u32 chip;
 	u32 chiprev;
+	bool always_use_fws_queue;
 
 	struct brcmf_bus_ops *ops;
 };
@@ -113,11 +113,6 @@ static inline int brcmf_bus_preinit(struct brcmf_bus *bus)
 	return bus->ops->preinit(bus->dev);
 }
 
-static inline int brcmf_bus_init(struct brcmf_bus *bus)
-{
-	return bus->ops->init(bus->dev);
-}
-
 static inline void brcmf_bus_stop(struct brcmf_bus *bus)
 {
 	bus->ops->stop(bus->dev);
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_common.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_common.c
index 6a8983a1fb9..ed3e32ce8c2 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_common.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_common.c
@@ -32,6 +32,9 @@
 #define BRCMF_DEFAULT_SCAN_UNASSOC_TIME	40
 #define BRCMF_DEFAULT_PACKET_FILTER	"100 0 0 0 0x01 0x00"
 
+/* boost value for RSSI_DELTA in preferred join selection */
+#define BRCMF_JOIN_PREF_RSSI_BOOST	8
+
 
 bool brcmf_c_prec_enq(struct device *dev, struct pktq *q,
 		      struct sk_buff *pkt, int prec)
@@ -246,6 +249,7 @@ int brcmf_c_preinit_dcmds(struct brcmf_if *ifp)
 {
 	s8 eventmask[BRCMF_EVENTING_MASK_LEN];
 	u8 buf[BRCMF_DCMD_SMLEN];
+	struct brcmf_join_pref_params join_pref_params[2];
 	char *ptr;
 	s32 err;
 
@@ -298,6 +302,20 @@ int brcmf_c_preinit_dcmds(struct brcmf_if *ifp)
 		goto done;
 	}
 
+	/* Setup join_pref to select target by RSSI(with boost on 5GHz) */
+	join_pref_params[0].type = BRCMF_JOIN_PREF_RSSI_DELTA;
+	join_pref_params[0].len = 2;
+	join_pref_params[0].rssi_gain = BRCMF_JOIN_PREF_RSSI_BOOST;
+	join_pref_params[0].band = WLC_BAND_5G;
+	join_pref_params[1].type = BRCMF_JOIN_PREF_RSSI;
+	join_pref_params[1].len = 2;
+	join_pref_params[1].rssi_gain = 0;
+	join_pref_params[1].band = 0;
+	err = brcmf_fil_iovar_data_set(ifp, "join_pref", join_pref_params,
+				       sizeof(join_pref_params));
+	if (err)
+		brcmf_err("Set join_pref error (%d)\n", err);
+
 	/* Setup event_msgs, enable E_IF */
 	err = brcmf_fil_iovar_data_get(ifp, "event_msgs", eventmask,
 				       BRCMF_EVENTING_MASK_LEN);
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
index 7d28cd38509..09dd8c13d84 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_linux.c
@@ -190,7 +190,7 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb,
 	int ret;
 	struct brcmf_if *ifp = netdev_priv(ndev);
 	struct brcmf_pub *drvr = ifp->drvr;
-	struct ethhdr *eh;
+	struct ethhdr *eh = (struct ethhdr *)(skb->data);
 
 	brcmf_dbg(DATA, "Enter, idx=%d\n", ifp->bssidx);
 
@@ -236,6 +236,9 @@ static netdev_tx_t brcmf_netdev_start_xmit(struct sk_buff *skb,
 		goto done;
 	}
 
+	if (eh->h_proto == htons(ETH_P_PAE))
+		atomic_inc(&ifp->pend_8021x_cnt);
+
 	ret = brcmf_fws_process_skb(ifp, skb);
 
 done:
@@ -538,31 +541,26 @@ void brcmf_rx_frame(struct device *dev, struct sk_buff *skb)
 		brcmf_netif_rx(ifp, skb);
 }
 
-void brcmf_txfinalize(struct brcmf_pub *drvr, struct sk_buff *txp,
+void brcmf_txfinalize(struct brcmf_pub *drvr, struct sk_buff *txp, u8 ifidx,
 		      bool success)
 {
 	struct brcmf_if *ifp;
 	struct ethhdr *eh;
-	u8 ifidx;
 	u16 type;
-	int res;
-
-	res = brcmf_proto_hdrpull(drvr, false, &ifidx, txp);
 
 	ifp = drvr->iflist[ifidx];
 	if (!ifp)
 		goto done;
 
-	if (res == 0) {
-		eh = (struct ethhdr *)(txp->data);
-		type = ntohs(eh->h_proto);
+	eh = (struct ethhdr *)(txp->data);
+	type = ntohs(eh->h_proto);
 
-		if (type == ETH_P_PAE) {
-			atomic_dec(&ifp->pend_8021x_cnt);
-			if (waitqueue_active(&ifp->pend_8021x_wait))
-				wake_up(&ifp->pend_8021x_wait);
-		}
+	if (type == ETH_P_PAE) {
+		atomic_dec(&ifp->pend_8021x_cnt);
+		if (waitqueue_active(&ifp->pend_8021x_wait))
+			wake_up(&ifp->pend_8021x_wait);
 	}
+
 	if (!success)
 		ifp->stats.tx_errors++;
 done:
@@ -573,13 +571,17 @@ void brcmf_txcomplete(struct device *dev, struct sk_buff *txp, bool success)
 {
 	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
 	struct brcmf_pub *drvr = bus_if->drvr;
+	u8 ifidx;
 
 	/* await txstatus signal for firmware if active */
 	if (brcmf_fws_fc_active(drvr->fws)) {
 		if (!success)
 			brcmf_fws_bustxfail(drvr->fws, txp);
 	} else {
-		brcmf_txfinalize(drvr, txp, success);
+		if (brcmf_proto_hdrpull(drvr, false, &ifidx, txp))
+			brcmu_pkt_buf_free_skb(txp);
+		else
+			brcmf_txfinalize(drvr, txp, ifidx, success);
 	}
 }
 
@@ -914,13 +916,6 @@ int brcmf_bus_start(struct device *dev)
 
 	brcmf_dbg(TRACE, "\n");
 
-	/* Bring up the bus */
-	ret = brcmf_bus_init(bus_if);
-	if (ret != 0) {
-		brcmf_err("brcmf_sdbrcm_bus_init failed %d\n", ret);
-		return ret;
-	}
-
 	/* add primary networking interface */
 	ifp = brcmf_add_if(drvr, 0, 0, "wlan%d", NULL);
 	if (IS_ERR(ifp))
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
index 13c89a0c4ba..8fa0dbbbda7 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
@@ -42,7 +42,7 @@
 #include <soc.h>
 #include "sdio_host.h"
 #include "chip.h"
-#include "nvram.h"
+#include "firmware.h"
 
 #define DCMD_RESP_TIMEOUT  2000	/* In milli second */
 
@@ -632,43 +632,28 @@ static const struct brcmf_firmware_names brcmf_fwname_data[] = {
 	{ BCM4354_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4354) }
 };
 
-
-static const struct firmware *brcmf_sdio_get_fw(struct brcmf_sdio *bus,
-						  enum brcmf_firmware_type type)
+static const char *brcmf_sdio_get_fwname(struct brcmf_chip *ci,
+					 enum brcmf_firmware_type type)
 {
-	const struct firmware *fw;
-	const char *name;
-	int err, i;
+	int i;
 
 	for (i = 0; i < ARRAY_SIZE(brcmf_fwname_data); i++) {
-		if (brcmf_fwname_data[i].chipid == bus->ci->chip &&
-		    brcmf_fwname_data[i].revmsk & BIT(bus->ci->chiprev)) {
+		if (brcmf_fwname_data[i].chipid == ci->chip &&
+		    brcmf_fwname_data[i].revmsk & BIT(ci->chiprev)) {
 			switch (type) {
 			case BRCMF_FIRMWARE_BIN:
-				name = brcmf_fwname_data[i].bin;
-				break;
+				return brcmf_fwname_data[i].bin;
 			case BRCMF_FIRMWARE_NVRAM:
-				name = brcmf_fwname_data[i].nv;
-				break;
+				return brcmf_fwname_data[i].nv;
 			default:
 				brcmf_err("invalid firmware type (%d)\n", type);
 				return NULL;
 			}
-			goto found;
 		}
 	}
 	brcmf_err("Unknown chipid %d [%d]\n",
-		  bus->ci->chip, bus->ci->chiprev);
+		  ci->chip, ci->chiprev);
 	return NULL;
-
-found:
-	err = request_firmware(&fw, name, &bus->sdiodev->func[2]->dev);
-	if ((err) || (!fw)) {
-		brcmf_err("fail to request firmware %s (%d)\n", name, err);
-		return NULL;
-	}
-
-	return fw;
 }
 
 static void pkt_align(struct sk_buff *p, int len, int align)
@@ -3278,20 +3263,13 @@ static int brcmf_sdio_download_code_file(struct brcmf_sdio *bus,
 }
 
 static int brcmf_sdio_download_nvram(struct brcmf_sdio *bus,
-				     const struct firmware *nv)
+				     void *vars, u32 varsz)
 {
-	void *vars;
-	u32 varsz;
 	int address;
 	int err;
 
 	brcmf_dbg(TRACE, "Enter\n");
 
-	vars = brcmf_nvram_strip(nv, &varsz);
-
-	if (vars == NULL)
-		return -EINVAL;
-
 	address = bus->ci->ramsize - varsz + bus->ci->rambase;
 	err = brcmf_sdiod_ramrw(bus->sdiodev, true, address, vars, varsz);
 	if (err)
@@ -3300,15 +3278,14 @@ static int brcmf_sdio_download_nvram(struct brcmf_sdio *bus,
 	else if (!brcmf_sdio_verifymemory(bus->sdiodev, address, vars, varsz))
 		err = -EIO;
 
-	brcmf_nvram_free(vars);
-
 	return err;
 }
 
-static int brcmf_sdio_download_firmware(struct brcmf_sdio *bus)
+static int brcmf_sdio_download_firmware(struct brcmf_sdio *bus,
+					const struct firmware *fw,
+					void *nvram, u32 nvlen)
 {
 	int bcmerror = -EFAULT;
-	const struct firmware *fw;
 	u32 rstvec;
 
 	sdio_claim_host(bus->sdiodev->func[1]);
@@ -3317,12 +3294,6 @@ static int brcmf_sdio_download_firmware(struct brcmf_sdio *bus)
 	/* Keep arm in reset */
 	brcmf_chip_enter_download(bus->ci);
 
-	fw = brcmf_sdio_get_fw(bus, BRCMF_FIRMWARE_BIN);
-	if (fw == NULL) {
-		bcmerror = -ENOENT;
-		goto err;
-	}
-
 	rstvec = get_unaligned_le32(fw->data);
 	brcmf_dbg(SDIO, "firmware rstvec: %x\n", rstvec);
 
@@ -3330,17 +3301,12 @@ static int brcmf_sdio_download_firmware(struct brcmf_sdio *bus)
 	release_firmware(fw);
 	if (bcmerror) {
 		brcmf_err("dongle image file download failed\n");
+		brcmf_fw_nvram_free(nvram);
 		goto err;
 	}
 
-	fw = brcmf_sdio_get_fw(bus, BRCMF_FIRMWARE_NVRAM);
-	if (fw == NULL) {
-		bcmerror = -ENOENT;
-		goto err;
-	}
-
-	bcmerror = brcmf_sdio_download_nvram(bus, fw);
-	release_firmware(fw);
+	bcmerror = brcmf_sdio_download_nvram(bus, nvram, nvlen);
+	brcmf_fw_nvram_free(nvram);
 	if (bcmerror) {
 		brcmf_err("dongle nvram file download failed\n");
 		goto err;
@@ -3490,97 +3456,6 @@ done:
 	return err;
 }
 
-static int brcmf_sdio_bus_init(struct device *dev)
-{
-	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
-	struct brcmf_sdio_dev *sdiodev = bus_if->bus_priv.sdio;
-	struct brcmf_sdio *bus = sdiodev->bus;
-	int err, ret = 0;
-	u8 saveclk;
-
-	brcmf_dbg(TRACE, "Enter\n");
-
-	/* try to download image and nvram to the dongle */
-	if (bus_if->state == BRCMF_BUS_DOWN) {
-		bus->alp_only = true;
-		err = brcmf_sdio_download_firmware(bus);
-		if (err)
-			return err;
-		bus->alp_only = false;
-	}
-
-	if (!bus->sdiodev->bus_if->drvr)
-		return 0;
-
-	/* Start the watchdog timer */
-	bus->sdcnt.tickcnt = 0;
-	brcmf_sdio_wd_timer(bus, BRCMF_WD_POLL_MS);
-
-	sdio_claim_host(bus->sdiodev->func[1]);
-
-	/* Make sure backplane clock is on, needed to generate F2 interrupt */
-	brcmf_sdio_clkctl(bus, CLK_AVAIL, false);
-	if (bus->clkstate != CLK_AVAIL)
-		goto exit;
-
-	/* Force clocks on backplane to be sure F2 interrupt propagates */
-	saveclk = brcmf_sdiod_regrb(bus->sdiodev,
-				    SBSDIO_FUNC1_CHIPCLKCSR, &err);
-	if (!err) {
-		brcmf_sdiod_regwb(bus->sdiodev, SBSDIO_FUNC1_CHIPCLKCSR,
-				  (saveclk | SBSDIO_FORCE_HT), &err);
-	}
-	if (err) {
-		brcmf_err("Failed to force clock for F2: err %d\n", err);
-		goto exit;
-	}
-
-	/* Enable function 2 (frame transfers) */
-	w_sdreg32(bus, SDPCM_PROT_VERSION << SMB_DATA_VERSION_SHIFT,
-		  offsetof(struct sdpcmd_regs, tosbmailboxdata));
-	err = sdio_enable_func(bus->sdiodev->func[SDIO_FUNC_2]);
-
-
-	brcmf_dbg(INFO, "enable F2: err=%d\n", err);
-
-	/* If F2 successfully enabled, set core and enable interrupts */
-	if (!err) {
-		/* Set up the interrupt mask and enable interrupts */
-		bus->hostintmask = HOSTINTMASK;
-		w_sdreg32(bus, bus->hostintmask,
-			  offsetof(struct sdpcmd_regs, hostintmask));
-
-		brcmf_sdiod_regwb(bus->sdiodev, SBSDIO_WATERMARK, 8, &err);
-	} else {
-		/* Disable F2 again */
-		sdio_disable_func(bus->sdiodev->func[SDIO_FUNC_2]);
-		ret = -ENODEV;
-	}
-
-	if (brcmf_chip_sr_capable(bus->ci)) {
-		brcmf_sdio_sr_init(bus);
-	} else {
-		/* Restore previous clock setting */
-		brcmf_sdiod_regwb(bus->sdiodev, SBSDIO_FUNC1_CHIPCLKCSR,
-				  saveclk, &err);
-	}
-
-	if (ret == 0) {
-		ret = brcmf_sdiod_intr_register(bus->sdiodev);
-		if (ret != 0)
-			brcmf_err("intr register failed:%d\n", ret);
-	}
-
-	/* If we didn't come up, turn off backplane clock */
-	if (ret != 0)
-		brcmf_sdio_clkctl(bus, CLK_NONE, false);
-
-exit:
-	sdio_release_host(bus->sdiodev->func[1]);
-
-	return ret;
-}
-
 void brcmf_sdio_isr(struct brcmf_sdio *bus)
 {
 	brcmf_dbg(TRACE, "Enter\n");
@@ -4020,13 +3895,114 @@ brcmf_sdio_watchdog(unsigned long data)
 static struct brcmf_bus_ops brcmf_sdio_bus_ops = {
 	.stop = brcmf_sdio_bus_stop,
 	.preinit = brcmf_sdio_bus_preinit,
-	.init = brcmf_sdio_bus_init,
 	.txdata = brcmf_sdio_bus_txdata,
 	.txctl = brcmf_sdio_bus_txctl,
 	.rxctl = brcmf_sdio_bus_rxctl,
 	.gettxq = brcmf_sdio_bus_gettxq,
 };
 
+static void brcmf_sdio_firmware_callback(struct device *dev,
+					 const struct firmware *code,
+					 void *nvram, u32 nvram_len)
+{
+	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
+	struct brcmf_sdio_dev *sdiodev = bus_if->bus_priv.sdio;
+	struct brcmf_sdio *bus = sdiodev->bus;
+	int err = 0;
+	u8 saveclk;
+
+	brcmf_dbg(TRACE, "Enter: dev=%s\n", dev_name(dev));
+
+	/* try to download image and nvram to the dongle */
+	if (bus_if->state == BRCMF_BUS_DOWN) {
+		bus->alp_only = true;
+		err = brcmf_sdio_download_firmware(bus, code, nvram, nvram_len);
+		if (err)
+			goto fail;
+		bus->alp_only = false;
+	}
+
+	if (!bus_if->drvr)
+		return;
+
+	/* Start the watchdog timer */
+	bus->sdcnt.tickcnt = 0;
+	brcmf_sdio_wd_timer(bus, BRCMF_WD_POLL_MS);
+
+	sdio_claim_host(sdiodev->func[1]);
+
+	/* Make sure backplane clock is on, needed to generate F2 interrupt */
+	brcmf_sdio_clkctl(bus, CLK_AVAIL, false);
+	if (bus->clkstate != CLK_AVAIL)
+		goto release;
+
+	/* Force clocks on backplane to be sure F2 interrupt propagates */
+	saveclk = brcmf_sdiod_regrb(sdiodev, SBSDIO_FUNC1_CHIPCLKCSR, &err);
+	if (!err) {
+		brcmf_sdiod_regwb(sdiodev, SBSDIO_FUNC1_CHIPCLKCSR,
+				  (saveclk | SBSDIO_FORCE_HT), &err);
+	}
+	if (err) {
+		brcmf_err("Failed to force clock for F2: err %d\n", err);
+		goto release;
+	}
+
+	/* Enable function 2 (frame transfers) */
+	w_sdreg32(bus, SDPCM_PROT_VERSION << SMB_DATA_VERSION_SHIFT,
+		  offsetof(struct sdpcmd_regs, tosbmailboxdata));
+	err = sdio_enable_func(sdiodev->func[SDIO_FUNC_2]);
+
+
+	brcmf_dbg(INFO, "enable F2: err=%d\n", err);
+
+	/* If F2 successfully enabled, set core and enable interrupts */
+	if (!err) {
+		/* Set up the interrupt mask and enable interrupts */
+		bus->hostintmask = HOSTINTMASK;
+		w_sdreg32(bus, bus->hostintmask,
+			  offsetof(struct sdpcmd_regs, hostintmask));
+
+		brcmf_sdiod_regwb(sdiodev, SBSDIO_WATERMARK, 8, &err);
+	} else {
+		/* Disable F2 again */
+		sdio_disable_func(sdiodev->func[SDIO_FUNC_2]);
+		goto release;
+	}
+
+	if (brcmf_chip_sr_capable(bus->ci)) {
+		brcmf_sdio_sr_init(bus);
+	} else {
+		/* Restore previous clock setting */
+		brcmf_sdiod_regwb(sdiodev, SBSDIO_FUNC1_CHIPCLKCSR,
+				  saveclk, &err);
+	}
+
+	if (err == 0) {
+		err = brcmf_sdiod_intr_register(sdiodev);
+		if (err != 0)
+			brcmf_err("intr register failed:%d\n", err);
+	}
+
+	/* If we didn't come up, turn off backplane clock */
+	if (err != 0)
+		brcmf_sdio_clkctl(bus, CLK_NONE, false);
+
+	sdio_release_host(sdiodev->func[1]);
+
+	err = brcmf_bus_start(dev);
+	if (err != 0) {
+		brcmf_err("dongle is not responding\n");
+		goto fail;
+	}
+	return;
+
+release:
+	sdio_release_host(sdiodev->func[1]);
+fail:
+	brcmf_dbg(TRACE, "failed: dev=%s, err=%d\n", dev_name(dev), err);
+	device_release_driver(dev);
+}
+
 struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 {
 	int ret;
@@ -4110,8 +4086,13 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 		goto fail;
 	}
 
+	/* Query the F2 block size, set roundup accordingly */
+	bus->blocksize = bus->sdiodev->func[2]->cur_blksize;
+	bus->roundup = min(max_roundup, bus->blocksize);
+
 	/* Allocate buffers */
 	if (bus->sdiodev->bus_if->maxctl) {
+		bus->sdiodev->bus_if->maxctl += bus->roundup;
 		bus->rxblen =
 		    roundup((bus->sdiodev->bus_if->maxctl + SDPCM_HDRLEN),
 			    ALIGNMENT) + bus->head_align;
@@ -4139,10 +4120,6 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 	bus->idletime = BRCMF_IDLE_INTERVAL;
 	bus->idleclock = BRCMF_IDLE_ACTIVE;
 
-	/* Query the F2 block size, set roundup accordingly */
-	bus->blocksize = bus->sdiodev->func[2]->cur_blksize;
-	bus->roundup = min(max_roundup, bus->blocksize);
-
 	/* SR state */
 	bus->sleeping = false;
 	bus->sr_enabled = false;
@@ -4150,10 +4127,14 @@ struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev)
 	brcmf_sdio_debugfs_create(bus);
 	brcmf_dbg(INFO, "completed!!\n");
 
-	/* if firmware path present try to download and bring up bus */
-	ret = brcmf_bus_start(bus->sdiodev->dev);
+	ret = brcmf_fw_get_firmwares(sdiodev->dev, BRCMF_FW_REQUEST_NVRAM,
+				     brcmf_sdio_get_fwname(bus->ci,
+							   BRCMF_FIRMWARE_BIN),
+				     brcmf_sdio_get_fwname(bus->ci,
+							   BRCMF_FIRMWARE_NVRAM),
+				     brcmf_sdio_firmware_callback);
 	if (ret != 0) {
-		brcmf_err("dongle is not responding\n");
+		brcmf_err("async firmware request failed: %d\n", ret);
 		goto fail;
 	}
 
@@ -4173,9 +4154,7 @@ void brcmf_sdio_remove(struct brcmf_sdio *bus)
 		/* De-register interrupt handler */
 		brcmf_sdiod_intr_unregister(bus->sdiodev);
 
-		if (bus->sdiodev->bus_if->drvr) {
-			brcmf_detach(bus->sdiodev->dev);
-		}
+		brcmf_detach(bus->sdiodev->dev);
 
 		cancel_work_sync(&bus->datawork);
 		if (bus->brcmf_wq)
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/firmware.c b/drivers/net/wireless/brcm80211/brcmfmac/firmware.c
new file mode 100644
index 00000000000..7b7d237c1dd
--- /dev/null
+++ b/drivers/net/wireless/brcm80211/brcmfmac/firmware.c
@@ -0,0 +1,332 @@
+/*
+ * Copyright (c) 2013 Broadcom Corporation
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+ * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
+ * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
+ * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/firmware.h>
+
+#include "dhd_dbg.h"
+#include "firmware.h"
+
+enum nvram_parser_state {
+	IDLE,
+	KEY,
+	VALUE,
+	COMMENT,
+	END
+};
+
+/**
+ * struct nvram_parser - internal info for parser.
+ *
+ * @state: current parser state.
+ * @fwnv: input buffer being parsed.
+ * @nvram: output buffer with parse result.
+ * @nvram_len: lenght of parse result.
+ * @line: current line.
+ * @column: current column in line.
+ * @pos: byte offset in input buffer.
+ * @entry: start position of key,value entry.
+ */
+struct nvram_parser {
+	enum nvram_parser_state state;
+	const struct firmware *fwnv;
+	u8 *nvram;
+	u32 nvram_len;
+	u32 line;
+	u32 column;
+	u32 pos;
+	u32 entry;
+};
+
+static bool is_nvram_char(char c)
+{
+	/* comment marker excluded */
+	if (c == '#')
+		return false;
+
+	/* key and value may have any other readable character */
+	return (c > 0x20 && c < 0x7f);
+}
+
+static bool is_whitespace(char c)
+{
+	return (c == ' ' || c == '\r' || c == '\n' || c == '\t');
+}
+
+static enum nvram_parser_state brcmf_nvram_handle_idle(struct nvram_parser *nvp)
+{
+	char c;
+
+	c = nvp->fwnv->data[nvp->pos];
+	if (c == '\n')
+		return COMMENT;
+	if (is_whitespace(c))
+		goto proceed;
+	if (c == '#')
+		return COMMENT;
+	if (is_nvram_char(c)) {
+		nvp->entry = nvp->pos;
+		return KEY;
+	}
+	brcmf_dbg(INFO, "warning: ln=%d:col=%d: ignoring invalid character\n",
+		  nvp->line, nvp->column);
+proceed:
+	nvp->column++;
+	nvp->pos++;
+	return IDLE;
+}
+
+static enum nvram_parser_state brcmf_nvram_handle_key(struct nvram_parser *nvp)
+{
+	enum nvram_parser_state st = nvp->state;
+	char c;
+
+	c = nvp->fwnv->data[nvp->pos];
+	if (c == '=') {
+		st = VALUE;
+	} else if (!is_nvram_char(c)) {
+		brcmf_dbg(INFO, "warning: ln=%d:col=%d: '=' expected, skip invalid key entry\n",
+			  nvp->line, nvp->column);
+		return COMMENT;
+	}
+
+	nvp->column++;
+	nvp->pos++;
+	return st;
+}
+
+static enum nvram_parser_state
+brcmf_nvram_handle_value(struct nvram_parser *nvp)
+{
+	char c;
+	char *skv;
+	char *ekv;
+	u32 cplen;
+
+	c = nvp->fwnv->data[nvp->pos];
+	if (!is_nvram_char(c)) {
+		/* key,value pair complete */
+		ekv = (u8 *)&nvp->fwnv->data[nvp->pos];
+		skv = (u8 *)&nvp->fwnv->data[nvp->entry];
+		cplen = ekv - skv;
+		/* copy to output buffer */
+		memcpy(&nvp->nvram[nvp->nvram_len], skv, cplen);
+		nvp->nvram_len += cplen;
+		nvp->nvram[nvp->nvram_len] = '\0';
+		nvp->nvram_len++;
+		return IDLE;
+	}
+	nvp->pos++;
+	nvp->column++;
+	return VALUE;
+}
+
+static enum nvram_parser_state
+brcmf_nvram_handle_comment(struct nvram_parser *nvp)
+{
+	char *eol, *sol;
+
+	sol = (char *)&nvp->fwnv->data[nvp->pos];
+	eol = strchr(sol, '\n');
+	if (eol == NULL)
+		return END;
+
+	/* eat all moving to next line */
+	nvp->line++;
+	nvp->column = 1;
+	nvp->pos += (eol - sol) + 1;
+	return IDLE;
+}
+
+static enum nvram_parser_state brcmf_nvram_handle_end(struct nvram_parser *nvp)
+{
+	/* final state */
+	return END;
+}
+
+static enum nvram_parser_state
+(*nv_parser_states[])(struct nvram_parser *nvp) = {
+	brcmf_nvram_handle_idle,
+	brcmf_nvram_handle_key,
+	brcmf_nvram_handle_value,
+	brcmf_nvram_handle_comment,
+	brcmf_nvram_handle_end
+};
+
+static int brcmf_init_nvram_parser(struct nvram_parser *nvp,
+				   const struct firmware *nv)
+{
+	memset(nvp, 0, sizeof(*nvp));
+	nvp->fwnv = nv;
+	/* Alloc for extra 0 byte + roundup by 4 + length field */
+	nvp->nvram = kzalloc(nv->size + 1 + 3 + sizeof(u32), GFP_KERNEL);
+	if (!nvp->nvram)
+		return -ENOMEM;
+
+	nvp->line = 1;
+	nvp->column = 1;
+	return 0;
+}
+
+/* brcmf_nvram_strip :Takes a buffer of "<var>=<value>\n" lines read from a fil
+ * and ending in a NUL. Removes carriage returns, empty lines, comment lines,
+ * and converts newlines to NULs. Shortens buffer as needed and pads with NULs.
+ * End of buffer is completed with token identifying length of buffer.
+ */
+static void *brcmf_fw_nvram_strip(const struct firmware *nv, u32 *new_length)
+{
+	struct nvram_parser nvp;
+	u32 pad;
+	u32 token;
+	__le32 token_le;
+
+	if (brcmf_init_nvram_parser(&nvp, nv) < 0)
+		return NULL;
+
+	while (nvp.pos < nv->size) {
+		nvp.state = nv_parser_states[nvp.state](&nvp);
+		if (nvp.state == END)
+			break;
+	}
+	pad = nvp.nvram_len;
+	*new_length = roundup(nvp.nvram_len + 1, 4);
+	while (pad != *new_length) {
+		nvp.nvram[pad] = 0;
+		pad++;
+	}
+
+	token = *new_length / 4;
+	token = (~token << 16) | (token & 0x0000FFFF);
+	token_le = cpu_to_le32(token);
+
+	memcpy(&nvp.nvram[*new_length], &token_le, sizeof(token_le));
+	*new_length += sizeof(token_le);
+
+	return nvp.nvram;
+}
+
+void brcmf_fw_nvram_free(void *nvram)
+{
+	kfree(nvram);
+}
+
+struct brcmf_fw {
+	struct device *dev;
+	u16 flags;
+	const struct firmware *code;
+	const char *nvram_name;
+	void (*done)(struct device *dev, const struct firmware *fw,
+		     void *nvram_image, u32 nvram_len);
+};
+
+static void brcmf_fw_request_nvram_done(const struct firmware *fw, void *ctx)
+{
+	struct brcmf_fw *fwctx = ctx;
+	u32 nvram_length = 0;
+	void *nvram = NULL;
+
+	brcmf_dbg(TRACE, "enter: dev=%s\n", dev_name(fwctx->dev));
+	if (!fw && !(fwctx->flags & BRCMF_FW_REQ_NV_OPTIONAL))
+		goto fail;
+
+	if (fw) {
+		nvram = brcmf_fw_nvram_strip(fw, &nvram_length);
+		release_firmware(fw);
+		if (!nvram && !(fwctx->flags & BRCMF_FW_REQ_NV_OPTIONAL))
+			goto fail;
+	}
+
+	fwctx->done(fwctx->dev, fwctx->code, nvram, nvram_length);
+	kfree(fwctx);
+	return;
+
+fail:
+	brcmf_dbg(TRACE, "failed: dev=%s\n", dev_name(fwctx->dev));
+	if (fwctx->code)
+		release_firmware(fwctx->code);
+	device_release_driver(fwctx->dev);
+	kfree(fwctx);
+}
+
+static void brcmf_fw_request_code_done(const struct firmware *fw, void *ctx)
+{
+	struct brcmf_fw *fwctx = ctx;
+	int ret;
+
+	brcmf_dbg(TRACE, "enter: dev=%s\n", dev_name(fwctx->dev));
+	if (!fw)
+		goto fail;
+
+	/* only requested code so done here */
+	if (!(fwctx->flags & BRCMF_FW_REQUEST_NVRAM)) {
+		fwctx->done(fwctx->dev, fw, NULL, 0);
+		kfree(fwctx);
+		return;
+	}
+	fwctx->code = fw;
+	ret = request_firmware_nowait(THIS_MODULE, true, fwctx->nvram_name,
+				      fwctx->dev, GFP_KERNEL, fwctx,
+				      brcmf_fw_request_nvram_done);
+
+	if (!ret)
+		return;
+
+	/* when nvram is optional call .done() callback here */
+	if (fwctx->flags & BRCMF_FW_REQ_NV_OPTIONAL) {
+		fwctx->done(fwctx->dev, fw, NULL, 0);
+		kfree(fwctx);
+		return;
+	}
+
+	/* failed nvram request */
+	release_firmware(fw);
+fail:
+	brcmf_dbg(TRACE, "failed: dev=%s\n", dev_name(fwctx->dev));
+	device_release_driver(fwctx->dev);
+	kfree(fwctx);
+}
+
+int brcmf_fw_get_firmwares(struct device *dev, u16 flags,
+			   const char *code, const char *nvram,
+			   void (*fw_cb)(struct device *dev,
+					 const struct firmware *fw,
+					 void *nvram_image, u32 nvram_len))
+{
+	struct brcmf_fw *fwctx;
+
+	brcmf_dbg(TRACE, "enter: dev=%s\n", dev_name(dev));
+	if (!fw_cb || !code)
+		return -EINVAL;
+
+	if ((flags & BRCMF_FW_REQUEST_NVRAM) && !nvram)
+		return -EINVAL;
+
+	fwctx = kzalloc(sizeof(*fwctx), GFP_KERNEL);
+	if (!fwctx)
+		return -ENOMEM;
+
+	fwctx->dev = dev;
+	fwctx->flags = flags;
+	fwctx->done = fw_cb;
+	if (flags & BRCMF_FW_REQUEST_NVRAM)
+		fwctx->nvram_name = nvram;
+
+	return request_firmware_nowait(THIS_MODULE, true, code, dev,
+				       GFP_KERNEL, fwctx,
+				       brcmf_fw_request_code_done);
+}
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/nvram.h b/drivers/net/wireless/brcm80211/brcmfmac/firmware.h
index d454580928c..6431bfd7aff 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/nvram.h
+++ b/drivers/net/wireless/brcm80211/brcmfmac/firmware.h
@@ -13,12 +13,24 @@
  * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
  * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
-#ifndef BRCMFMAC_NVRAM_H
-#define BRCMFMAC_NVRAM_H
+#ifndef BRCMFMAC_FIRMWARE_H
+#define BRCMFMAC_FIRMWARE_H
 
+#define BRCMF_FW_REQUEST		0x000F
+#define  BRCMF_FW_REQUEST_NVRAM		0x0001
+#define BRCMF_FW_REQ_FLAGS		0x00F0
+#define  BRCMF_FW_REQ_NV_OPTIONAL	0x0010
 
-void *brcmf_nvram_strip(const struct firmware *nv, u32 *new_length);
-void brcmf_nvram_free(void *nvram);
-
+void brcmf_fw_nvram_free(void *nvram);
+/*
+ * Request firmware(s) asynchronously. When the asynchronous request
+ * fails it will not use the callback, but call device_release_driver()
+ * instead which will call the driver .remove() callback.
+ */
+int brcmf_fw_get_firmwares(struct device *dev, u16 flags,
+			   const char *code, const char *nvram,
+			   void (*fw_cb)(struct device *dev,
+					 const struct firmware *fw,
+					 void *nvram_image, u32 nvram_len));
 
-#endif /* BRCMFMAC_NVRAM_H */
+#endif /* BRCMFMAC_FIRMWARE_H */
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/brcm80211/brcmfmac/fwil_types.h
index 614e4888504..2bc68a2137f 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/fwil_types.h
+++ b/drivers/net/wireless/brcm80211/brcmfmac/fwil_types.h
@@ -53,6 +53,14 @@
 #define BRCMF_OBSS_COEX_OFF		0
 #define BRCMF_OBSS_COEX_ON		1
 
+/* join preference types for join_pref iovar */
+enum brcmf_join_pref_types {
+	BRCMF_JOIN_PREF_RSSI = 1,
+	BRCMF_JOIN_PREF_WPA,
+	BRCMF_JOIN_PREF_BAND,
+	BRCMF_JOIN_PREF_RSSI_DELTA,
+};
+
 enum brcmf_fil_p2p_if_types {
 	BRCMF_FIL_P2P_IF_CLIENT,
 	BRCMF_FIL_P2P_IF_GO,
@@ -282,6 +290,22 @@ struct brcmf_assoc_params_le {
 	__le16 chanspec_list[1];
 };
 
+/**
+ * struct join_pref params - parameters for preferred join selection.
+ *
+ * @type: preference type (see enum brcmf_join_pref_types).
+ * @len: length of bytes following (currently always 2).
+ * @rssi_gain: signal gain for selection (only when @type is RSSI_DELTA).
+ * @band: band to which selection preference applies.
+ *	This is used if @type is BAND or RSSI_DELTA.
+ */
+struct brcmf_join_pref_params {
+	u8 type;
+	u8 len;
+	u8 rssi_gain;
+	u8 band;
+};
+
 /* used for join with or without a specific bssid and channel list */
 struct brcmf_join_params {
 	struct brcmf_ssid_le ssid_le;
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c
index c3e7d76dbf3..699908de314 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/fwsignal.c
@@ -476,6 +476,7 @@ struct brcmf_fws_info {
 	bool bus_flow_blocked;
 	bool creditmap_received;
 	u8 mode;
+	bool avoid_queueing;
 };
 
 /*
@@ -1369,13 +1370,12 @@ done:
 }
 
 static int brcmf_fws_txstatus_suppressed(struct brcmf_fws_info *fws, int fifo,
-					 struct sk_buff *skb, u32 genbit,
-					 u16 seq)
+					 struct sk_buff *skb, u8 ifidx,
+					 u32 genbit, u16 seq)
 {
 	struct brcmf_fws_mac_descriptor *entry = brcmf_skbcb(skb)->mac;
 	u32 hslot;
 	int ret;
-	u8 ifidx;
 
 	hslot = brcmf_skb_htod_tag_get_field(skb, HSLOT);
 
@@ -1389,29 +1389,21 @@ static int brcmf_fws_txstatus_suppressed(struct brcmf_fws_info *fws, int fifo,
 
 	entry->generation = genbit;
 
-	ret = brcmf_proto_hdrpull(fws->drvr, false, &ifidx, skb);
-	if (ret == 0) {
-		brcmf_skb_htod_tag_set_field(skb, GENERATION, genbit);
-		brcmf_skbcb(skb)->htod_seq = seq;
-		if (brcmf_skb_htod_seq_get_field(skb, FROMFW)) {
-			brcmf_skb_htod_seq_set_field(skb, FROMDRV, 1);
-			brcmf_skb_htod_seq_set_field(skb, FROMFW, 0);
-		} else {
-			brcmf_skb_htod_seq_set_field(skb, FROMDRV, 0);
-		}
-		ret = brcmf_fws_enq(fws, BRCMF_FWS_SKBSTATE_SUPPRESSED, fifo,
-				    skb);
+	brcmf_skb_htod_tag_set_field(skb, GENERATION, genbit);
+	brcmf_skbcb(skb)->htod_seq = seq;
+	if (brcmf_skb_htod_seq_get_field(skb, FROMFW)) {
+		brcmf_skb_htod_seq_set_field(skb, FROMDRV, 1);
+		brcmf_skb_htod_seq_set_field(skb, FROMFW, 0);
+	} else {
+		brcmf_skb_htod_seq_set_field(skb, FROMDRV, 0);
 	}
+	ret = brcmf_fws_enq(fws, BRCMF_FWS_SKBSTATE_SUPPRESSED, fifo, skb);
 
 	if (ret != 0) {
-		/* suppress q is full or hdrpull failed, drop this packet */
-		brcmf_fws_hanger_poppkt(&fws->hanger, hslot, &skb,
-					true);
+		/* suppress q is full drop this packet */
+		brcmf_fws_hanger_poppkt(&fws->hanger, hslot, &skb, true);
 	} else {
-		/*
-		 * Mark suppressed to avoid a double free during
-		 * wlfc cleanup
-		 */
+		/* Mark suppressed to avoid a double free during wlfc cleanup */
 		brcmf_fws_hanger_mark_suppressed(&fws->hanger, hslot);
 	}
 
@@ -1428,6 +1420,7 @@ brcmf_fws_txs_process(struct brcmf_fws_info *fws, u8 flags, u32 hslot,
 	struct sk_buff *skb;
 	struct brcmf_skbuff_cb *skcb;
 	struct brcmf_fws_mac_descriptor *entry = NULL;
+	u8 ifidx;
 
 	brcmf_dbg(DATA, "flags %d\n", flags);
 
@@ -1476,12 +1469,15 @@ brcmf_fws_txs_process(struct brcmf_fws_info *fws, u8 flags, u32 hslot,
 	}
 	brcmf_fws_macdesc_return_req_credit(skb);
 
+	if (brcmf_proto_hdrpull(fws->drvr, false, &ifidx, skb)) {
+		brcmu_pkt_buf_free_skb(skb);
+		return -EINVAL;
+	}
 	if (!remove_from_hanger)
-		ret = brcmf_fws_txstatus_suppressed(fws, fifo, skb, genbit,
-						    seq);
-
+		ret = brcmf_fws_txstatus_suppressed(fws, fifo, skb, ifidx,
+						    genbit, seq);
 	if (remove_from_hanger || ret)
-		brcmf_txfinalize(fws->drvr, skb, true);
+		brcmf_txfinalize(fws->drvr, skb, ifidx, true);
 
 	return 0;
 }
@@ -1868,7 +1864,7 @@ int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb)
 	struct ethhdr *eh = (struct ethhdr *)(skb->data);
 	int fifo = BRCMF_FWS_FIFO_BCMC;
 	bool multicast = is_multicast_ether_addr(eh->h_dest);
-	bool pae = eh->h_proto == htons(ETH_P_PAE);
+	int rc = 0;
 
 	brcmf_dbg(DATA, "tx proto=0x%X\n", ntohs(eh->h_proto));
 	/* determine the priority */
@@ -1876,8 +1872,13 @@ int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb)
 		skb->priority = cfg80211_classify8021d(skb, NULL);
 
 	drvr->tx_multicast += !!multicast;
-	if (pae)
-		atomic_inc(&ifp->pend_8021x_cnt);
+
+	if (fws->avoid_queueing) {
+		rc = brcmf_proto_txdata(drvr, ifp->ifidx, 0, skb);
+		if (rc < 0)
+			brcmf_txfinalize(drvr, skb, ifp->ifidx, false);
+		return rc;
+	}
 
 	/* set control buffer information */
 	skcb->if_flags = 0;
@@ -1899,15 +1900,12 @@ int brcmf_fws_process_skb(struct brcmf_if *ifp, struct sk_buff *skb)
 		brcmf_fws_schedule_deq(fws);
 	} else {
 		brcmf_err("drop skb: no hanger slot\n");
-		if (pae) {
-			atomic_dec(&ifp->pend_8021x_cnt);
-			if (waitqueue_active(&ifp->pend_8021x_wait))
-				wake_up(&ifp->pend_8021x_wait);
-		}
-		brcmu_pkt_buf_free_skb(skb);
+		brcmf_txfinalize(drvr, skb, ifp->ifidx, false);
+		rc = -ENOMEM;
 	}
 	brcmf_fws_unlock(fws);
-	return 0;
+
+	return rc;
 }
 
 void brcmf_fws_reset_interface(struct brcmf_if *ifp)
@@ -1982,7 +1980,8 @@ static void brcmf_fws_dequeue_worker(struct work_struct *worker)
 				ret = brcmf_proto_txdata(drvr, ifidx, 0, skb);
 				brcmf_fws_lock(fws);
 				if (ret < 0)
-					brcmf_txfinalize(drvr, skb, false);
+					brcmf_txfinalize(drvr, skb, ifidx,
+							 false);
 				if (fws->bus_flow_blocked)
 					break;
 			}
@@ -2039,6 +2038,13 @@ int brcmf_fws_init(struct brcmf_pub *drvr)
 	fws->drvr = drvr;
 	fws->fcmode = fcmode;
 
+	if ((drvr->bus_if->always_use_fws_queue == false) &&
+	    (fcmode == BRCMF_FWS_FCMODE_NONE)) {
+		fws->avoid_queueing = true;
+		brcmf_dbg(INFO, "FWS queueing will be avoided\n");
+		return 0;
+	}
+
 	fws->fws_wq = create_singlethread_workqueue("brcmf_fws_wq");
 	if (fws->fws_wq == NULL) {
 		brcmf_err("workqueue creation failed\n");
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/nvram.c b/drivers/net/wireless/brcm80211/brcmfmac/nvram.c
deleted file mode 100644
index d5ef86db631..00000000000
--- a/drivers/net/wireless/brcm80211/brcmfmac/nvram.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Copyright (c) 2013 Broadcom Corporation
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
- * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
- * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
- * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/firmware.h>
-
-#include "nvram.h"
-
-/* brcmf_nvram_strip :Takes a buffer of "<var>=<value>\n" lines read from a file
- * and ending in a NUL. Removes carriage returns, empty lines, comment lines,
- * and converts newlines to NULs. Shortens buffer as needed and pads with NULs.
- * End of buffer is completed with token identifying length of buffer.
- */
-void *brcmf_nvram_strip(const struct firmware *nv, u32 *new_length)
-{
-	u8 *nvram;
-	u32 i;
-	u32 len;
-	u32 column;
-	u8 val;
-	bool comment;
-	u32 token;
-	__le32 token_le;
-
-	/* Alloc for extra 0 byte + roundup by 4 + length field */
-	nvram = kmalloc(nv->size + 1 + 3 + sizeof(token_le), GFP_KERNEL);
-	if (!nvram)
-		return NULL;
-
-	len = 0;
-	column = 0;
-	comment = false;
-	for (i = 0; i < nv->size; i++) {
-		val = nv->data[i];
-		if (val == 0)
-			break;
-		if (val == '\r')
-			continue;
-		if (comment && (val != '\n'))
-			continue;
-		comment = false;
-		if (val == '#') {
-			comment = true;
-			continue;
-		}
-		if (val == '\n') {
-			if (column == 0)
-				continue;
-			nvram[len] = 0;
-			len++;
-			column = 0;
-			continue;
-		}
-		nvram[len] = val;
-		len++;
-		column++;
-	}
-	column = len;
-	*new_length = roundup(len + 1, 4);
-	while (column != *new_length) {
-		nvram[column] = 0;
-		column++;
-	}
-
-	token = *new_length / 4;
-	token = (~token << 16) | (token & 0x0000FFFF);
-	token_le = cpu_to_le32(token);
-
-	memcpy(&nvram[*new_length], &token_le, sizeof(token_le));
-	*new_length += sizeof(token_le);
-
-	return nvram;
-}
-
-void brcmf_nvram_free(void *nvram)
-{
-	kfree(nvram);
-}
-
-
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/brcm80211/brcmfmac/usb.c
index 24f65cd5385..d06fcb05adf 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/usb.c
@@ -25,6 +25,7 @@
 #include <dhd_bus.h>
 #include <dhd_dbg.h>
 
+#include "firmware.h"
 #include "usb_rdl.h"
 #include "usb.h"
 
@@ -61,12 +62,6 @@ struct brcmf_usb_image {
 	u8 *image;
 	int image_len;
 };
-static struct list_head fw_image_list;
-
-struct intr_transfer_buf {
-	u32 notification;
-	u32 reserved;
-};
 
 struct brcmf_usbdev_info {
 	struct brcmf_usbdev bus_pub; /* MUST BE FIRST */
@@ -75,7 +70,7 @@ struct brcmf_usbdev_info {
 	struct list_head rx_postq;
 	struct list_head tx_freeq;
 	struct list_head tx_postq;
-	uint rx_pipe, tx_pipe, intr_pipe, rx_pipe2;
+	uint rx_pipe, tx_pipe, rx_pipe2;
 
 	int rx_low_watermark;
 	int tx_low_watermark;
@@ -87,7 +82,7 @@ struct brcmf_usbdev_info {
 	struct brcmf_usbreq *tx_reqs;
 	struct brcmf_usbreq *rx_reqs;
 
-	u8 *image;	/* buffer for combine fw and nvram */
+	const u8 *image;	/* buffer for combine fw and nvram */
 	int image_len;
 
 	struct usb_device *usbdev;
@@ -104,10 +99,6 @@ struct brcmf_usbdev_info {
 	ulong ctl_op;
 
 	struct urb *bulk_urb; /* used for FW download */
-	struct urb *intr_urb; /* URB for interrupt endpoint */
-	int intr_size;          /* Size of interrupt message */
-	int interval;           /* Interrupt polling interval */
-	struct intr_transfer_buf intr; /* Data buffer for interrupt endpoint */
 };
 
 static void brcmf_usb_rx_refill(struct brcmf_usbdev_info *devinfo,
@@ -531,39 +522,6 @@ brcmf_usb_state_change(struct brcmf_usbdev_info *devinfo, int state)
 	}
 }
 
-static void
-brcmf_usb_intr_complete(struct urb *urb)
-{
-	struct brcmf_usbdev_info *devinfo =
-			(struct brcmf_usbdev_info *)urb->context;
-	int err;
-
-	brcmf_dbg(USB, "Enter, urb->status=%d\n", urb->status);
-
-	if (devinfo == NULL)
-		return;
-
-	if (unlikely(urb->status)) {
-		if (urb->status == -ENOENT ||
-		    urb->status == -ESHUTDOWN ||
-		    urb->status == -ENODEV) {
-			brcmf_usb_state_change(devinfo,
-					       BRCMFMAC_USB_STATE_DOWN);
-		}
-	}
-
-	if (devinfo->bus_pub.state == BRCMFMAC_USB_STATE_DOWN) {
-		brcmf_err("intr cb when DBUS down, ignoring\n");
-		return;
-	}
-
-	if (devinfo->bus_pub.state == BRCMFMAC_USB_STATE_UP) {
-		err = usb_submit_urb(devinfo->intr_urb, GFP_ATOMIC);
-		if (err)
-			brcmf_err("usb_submit_urb, err=%d\n", err);
-	}
-}
-
 static int brcmf_usb_tx(struct device *dev, struct sk_buff *skb)
 {
 	struct brcmf_usbdev_info *devinfo = brcmf_usb_get_businfo(dev);
@@ -619,7 +577,6 @@ static int brcmf_usb_up(struct device *dev)
 {
 	struct brcmf_usbdev_info *devinfo = brcmf_usb_get_businfo(dev);
 	u16 ifnum;
-	int ret;
 
 	brcmf_dbg(USB, "Enter\n");
 	if (devinfo->bus_pub.state == BRCMFMAC_USB_STATE_UP)
@@ -628,23 +585,6 @@ static int brcmf_usb_up(struct device *dev)
 	/* Success, indicate devinfo is fully up */
 	brcmf_usb_state_change(devinfo, BRCMFMAC_USB_STATE_UP);
 
-	if (devinfo->intr_urb) {
-		usb_fill_int_urb(devinfo->intr_urb, devinfo->usbdev,
-			devinfo->intr_pipe,
-			&devinfo->intr,
-			devinfo->intr_size,
-			(usb_complete_t)brcmf_usb_intr_complete,
-			devinfo,
-			devinfo->interval);
-
-		ret = usb_submit_urb(devinfo->intr_urb, GFP_ATOMIC);
-		if (ret) {
-			brcmf_err("USB_SUBMIT_URB failed with status %d\n",
-				  ret);
-			return -EINVAL;
-		}
-	}
-
 	if (devinfo->ctl_urb) {
 		devinfo->ctl_in_pipe = usb_rcvctrlpipe(devinfo->usbdev, 0);
 		devinfo->ctl_out_pipe = usb_sndctrlpipe(devinfo->usbdev, 0);
@@ -681,8 +621,6 @@ static void brcmf_usb_down(struct device *dev)
 		return;
 
 	brcmf_usb_state_change(devinfo, BRCMFMAC_USB_STATE_DOWN);
-	if (devinfo->intr_urb)
-		usb_kill_urb(devinfo->intr_urb);
 
 	if (devinfo->ctl_urb)
 		usb_kill_urb(devinfo->ctl_urb);
@@ -1021,7 +959,7 @@ brcmf_usb_fw_download(struct brcmf_usbdev_info *devinfo)
 	}
 
 	err = brcmf_usb_dlstart(devinfo,
-		devinfo->image, devinfo->image_len);
+		(u8 *)devinfo->image, devinfo->image_len);
 	if (err == 0)
 		err = brcmf_usb_dlrun(devinfo);
 	return err;
@@ -1036,7 +974,6 @@ static void brcmf_usb_detach(struct brcmf_usbdev_info *devinfo)
 	brcmf_usb_free_q(&devinfo->rx_freeq, false);
 	brcmf_usb_free_q(&devinfo->tx_freeq, false);
 
-	usb_free_urb(devinfo->intr_urb);
 	usb_free_urb(devinfo->ctl_urb);
 	usb_free_urb(devinfo->bulk_urb);
 
@@ -1080,68 +1017,20 @@ static int check_file(const u8 *headers)
 	return -1;
 }
 
-static int brcmf_usb_get_fw(struct brcmf_usbdev_info *devinfo)
+static const char *brcmf_usb_get_fwname(struct brcmf_usbdev_info *devinfo)
 {
-	s8 *fwname;
-	const struct firmware *fw;
-	struct brcmf_usb_image *fw_image;
-	int err;
-
-	brcmf_dbg(USB, "Enter\n");
 	switch (devinfo->bus_pub.devid) {
 	case 43143:
-		fwname = BRCMF_USB_43143_FW_NAME;
-		break;
+		return BRCMF_USB_43143_FW_NAME;
 	case 43235:
 	case 43236:
 	case 43238:
-		fwname = BRCMF_USB_43236_FW_NAME;
-		break;
+		return BRCMF_USB_43236_FW_NAME;
 	case 43242:
-		fwname = BRCMF_USB_43242_FW_NAME;
-		break;
+		return BRCMF_USB_43242_FW_NAME;
 	default:
-		return -EINVAL;
-		break;
-	}
-	brcmf_dbg(USB, "Loading FW %s\n", fwname);
-	list_for_each_entry(fw_image, &fw_image_list, list) {
-		if (fw_image->fwname == fwname) {
-			devinfo->image = fw_image->image;
-			devinfo->image_len = fw_image->image_len;
-			return 0;
-		}
-	}
-	/* fw image not yet loaded. Load it now and add to list */
-	err = request_firmware(&fw, fwname, devinfo->dev);
-	if (!fw) {
-		brcmf_err("fail to request firmware %s\n", fwname);
-		return err;
-	}
-	if (check_file(fw->data) < 0) {
-		brcmf_err("invalid firmware %s\n", fwname);
-		return -EINVAL;
+		return NULL;
 	}
-
-	fw_image = kzalloc(sizeof(*fw_image), GFP_ATOMIC);
-	if (!fw_image)
-		return -ENOMEM;
-	INIT_LIST_HEAD(&fw_image->list);
-	list_add_tail(&fw_image->list, &fw_image_list);
-	fw_image->fwname = fwname;
-	fw_image->image = vmalloc(fw->size);
-	if (!fw_image->image)
-		return -ENOMEM;
-
-	memcpy(fw_image->image, fw->data, fw->size);
-	fw_image->image_len = fw->size;
-
-	release_firmware(fw);
-
-	devinfo->image = fw_image->image;
-	devinfo->image_len = fw_image->image_len;
-
-	return 0;
 }
 
 
@@ -1186,11 +1075,6 @@ struct brcmf_usbdev *brcmf_usb_attach(struct brcmf_usbdev_info *devinfo,
 		goto error;
 	devinfo->tx_freecount = ntxq;
 
-	devinfo->intr_urb = usb_alloc_urb(0, GFP_ATOMIC);
-	if (!devinfo->intr_urb) {
-		brcmf_err("usb_alloc_urb (intr) failed\n");
-		goto error;
-	}
 	devinfo->ctl_urb = usb_alloc_urb(0, GFP_ATOMIC);
 	if (!devinfo->ctl_urb) {
 		brcmf_err("usb_alloc_urb (ctl) failed\n");
@@ -1202,16 +1086,6 @@ struct brcmf_usbdev *brcmf_usb_attach(struct brcmf_usbdev_info *devinfo,
 		goto error;
 	}
 
-	if (!brcmf_usb_dlneeded(devinfo))
-		return &devinfo->bus_pub;
-
-	brcmf_dbg(USB, "Start fw downloading\n");
-	if (brcmf_usb_get_fw(devinfo))
-		goto error;
-
-	if (brcmf_usb_fw_download(devinfo))
-		goto error;
-
 	return &devinfo->bus_pub;
 
 error:
@@ -1222,18 +1096,77 @@ error:
 
 static struct brcmf_bus_ops brcmf_usb_bus_ops = {
 	.txdata = brcmf_usb_tx,
-	.init = brcmf_usb_up,
 	.stop = brcmf_usb_down,
 	.txctl = brcmf_usb_tx_ctlpkt,
 	.rxctl = brcmf_usb_rx_ctlpkt,
 };
 
+static int brcmf_usb_bus_setup(struct brcmf_usbdev_info *devinfo)
+{
+	int ret;
+
+	/* Attach to the common driver interface */
+	ret = brcmf_attach(devinfo->dev);
+	if (ret) {
+		brcmf_err("brcmf_attach failed\n");
+		return ret;
+	}
+
+	ret = brcmf_usb_up(devinfo->dev);
+	if (ret)
+		goto fail;
+
+	ret = brcmf_bus_start(devinfo->dev);
+	if (ret)
+		goto fail;
+
+	return 0;
+fail:
+	brcmf_detach(devinfo->dev);
+	return ret;
+}
+
+static void brcmf_usb_probe_phase2(struct device *dev,
+				   const struct firmware *fw,
+				   void *nvram, u32 nvlen)
+{
+	struct brcmf_bus *bus = dev_get_drvdata(dev);
+	struct brcmf_usbdev_info *devinfo;
+	int ret;
+
+	brcmf_dbg(USB, "Start fw downloading\n");
+	ret = check_file(fw->data);
+	if (ret < 0) {
+		brcmf_err("invalid firmware\n");
+		release_firmware(fw);
+		goto error;
+	}
+
+	devinfo = bus->bus_priv.usb->devinfo;
+	devinfo->image = fw->data;
+	devinfo->image_len = fw->size;
+
+	ret = brcmf_usb_fw_download(devinfo);
+	release_firmware(fw);
+	if (ret)
+		goto error;
+
+	ret = brcmf_usb_bus_setup(devinfo);
+	if (ret)
+		goto error;
+
+	return;
+error:
+	brcmf_dbg(TRACE, "failed: dev=%s, err=%d\n", dev_name(dev), ret);
+	device_release_driver(dev);
+}
+
 static int brcmf_usb_probe_cb(struct brcmf_usbdev_info *devinfo)
 {
 	struct brcmf_bus *bus = NULL;
 	struct brcmf_usbdev *bus_pub = NULL;
-	int ret;
 	struct device *dev = devinfo->dev;
+	int ret;
 
 	brcmf_dbg(USB, "Enter\n");
 	bus_pub = brcmf_usb_attach(devinfo, BRCMF_USB_NRXQ, BRCMF_USB_NTXQ);
@@ -1251,25 +1184,22 @@ static int brcmf_usb_probe_cb(struct brcmf_usbdev_info *devinfo)
 	bus->bus_priv.usb = bus_pub;
 	dev_set_drvdata(dev, bus);
 	bus->ops = &brcmf_usb_bus_ops;
-	bus->chip = bus_pub->devid;
-	bus->chiprev = bus_pub->chiprev;
 	bus->proto_type = BRCMF_PROTO_BCDC;
+	bus->always_use_fws_queue = true;
 
-	/* Attach to the common driver interface */
-	ret = brcmf_attach(dev);
-	if (ret) {
-		brcmf_err("brcmf_attach failed\n");
-		goto fail;
-	}
-
-	ret = brcmf_bus_start(dev);
-	if (ret) {
-		brcmf_err("dongle is not responding\n");
-		brcmf_detach(dev);
-		goto fail;
+	if (!brcmf_usb_dlneeded(devinfo)) {
+		ret = brcmf_usb_bus_setup(devinfo);
+		if (ret)
+			goto fail;
 	}
+	bus->chip = bus_pub->devid;
+	bus->chiprev = bus_pub->chiprev;
 
+	/* request firmware here */
+	brcmf_fw_get_firmwares(dev, 0, brcmf_usb_get_fwname(devinfo), NULL,
+			       brcmf_usb_probe_phase2);
 	return 0;
+
 fail:
 	/* Release resources in reverse order */
 	kfree(bus);
@@ -1357,9 +1287,6 @@ brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 		goto fail;
 	}
 
-	endpoint_num = endpoint->bEndpointAddress & USB_ENDPOINT_NUMBER_MASK;
-	devinfo->intr_pipe = usb_rcvintpipe(usb, endpoint_num);
-
 	devinfo->rx_pipe = 0;
 	devinfo->rx_pipe2 = 0;
 	devinfo->tx_pipe = 0;
@@ -1391,16 +1318,9 @@ brcmf_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 		}
 	}
 
-	/* Allocate interrupt URB and data buffer */
-	/* RNDIS says 8-byte intr, our old drivers used 4-byte */
-	if (IFEPDESC(usb, CONTROL_IF, 0).wMaxPacketSize == cpu_to_le16(16))
-		devinfo->intr_size = 8;
-	else
-		devinfo->intr_size = 4;
-
-	devinfo->interval = IFEPDESC(usb, CONTROL_IF, 0).bInterval;
-
-	if (usb->speed == USB_SPEED_HIGH)
+	if (usb->speed == USB_SPEED_SUPER)
+		brcmf_dbg(USB, "Broadcom super speed USB wireless device detected\n");
+	else if (usb->speed == USB_SPEED_HIGH)
 		brcmf_dbg(USB, "Broadcom high speed USB wireless device detected\n");
 	else
 		brcmf_dbg(USB, "Broadcom full speed USB wireless device detected\n");
@@ -1455,23 +1375,18 @@ static int brcmf_usb_resume(struct usb_interface *intf)
 	struct brcmf_usbdev_info *devinfo = brcmf_usb_get_businfo(&usb->dev);
 
 	brcmf_dbg(USB, "Enter\n");
-	if (!brcmf_attach(devinfo->dev))
-		return brcmf_bus_start(&usb->dev);
-
-	return 0;
+	return brcmf_usb_bus_setup(devinfo);
 }
 
 static int brcmf_usb_reset_resume(struct usb_interface *intf)
 {
 	struct usb_device *usb = interface_to_usbdev(intf);
 	struct brcmf_usbdev_info *devinfo = brcmf_usb_get_businfo(&usb->dev);
-
 	brcmf_dbg(USB, "Enter\n");
 
-	if (!brcmf_usb_fw_download(devinfo))
-		return brcmf_usb_resume(intf);
-
-	return -EIO;
+	return brcmf_fw_get_firmwares(&usb->dev, 0,
+				      brcmf_usb_get_fwname(devinfo), NULL,
+				      brcmf_usb_probe_phase2);
 }
 
 #define BRCMF_USB_VENDOR_ID_BROADCOM	0x0a5c
@@ -1506,16 +1421,6 @@ static struct usb_driver brcmf_usbdrvr = {
 	.disable_hub_initiated_lpm = 1,
 };
 
-static void brcmf_release_fw(struct list_head *q)
-{
-	struct brcmf_usb_image *fw_image, *next;
-
-	list_for_each_entry_safe(fw_image, next, q, list) {
-		vfree(fw_image->image);
-		list_del_init(&fw_image->list);
-	}
-}
-
 static int brcmf_usb_reset_device(struct device *dev, void *notused)
 {
 	/* device past is the usb interface so we
@@ -1534,12 +1439,10 @@ void brcmf_usb_exit(void)
 	ret = driver_for_each_device(drv, NULL, NULL,
 				     brcmf_usb_reset_device);
 	usb_deregister(&brcmf_usbdrvr);
-	brcmf_release_fw(&fw_image_list);
 }
 
 void brcmf_usb_register(void)
 {
 	brcmf_dbg(USB, "Enter\n");
-	INIT_LIST_HEAD(&fw_image_list);
 	usb_register(&brcmf_usbdrvr);
 }
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
index be1985296bd..d8fa276e368 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
@@ -221,9 +221,9 @@ static const struct ieee80211_regdomain brcmf_regdom = {
 		 */
 		REG_RULE(2484-10, 2484+10, 20, 6, 20, 0),
 		/* IEEE 802.11a, channel 36..64 */
-		REG_RULE(5150-10, 5350+10, 40, 6, 20, 0),
+		REG_RULE(5150-10, 5350+10, 80, 6, 20, 0),
 		/* IEEE 802.11a, channel 100..165 */
-		REG_RULE(5470-10, 5850+10, 40, 6, 20, 0), }
+		REG_RULE(5470-10, 5850+10, 80, 6, 20, 0), }
 };
 
 static const u32 __wl_cipher_suites[] = {
@@ -341,6 +341,60 @@ static u8 brcmf_mw_to_qdbm(u16 mw)
 	return qdbm;
 }
 
+static u16 chandef_to_chanspec(struct brcmu_d11inf *d11inf,
+			       struct cfg80211_chan_def *ch)
+{
+	struct brcmu_chan ch_inf;
+	s32 primary_offset;
+
+	brcmf_dbg(TRACE, "chandef: control %d center %d width %d\n",
+		  ch->chan->center_freq, ch->center_freq1, ch->width);
+	ch_inf.chnum = ieee80211_frequency_to_channel(ch->center_freq1);
+	primary_offset = ch->center_freq1 - ch->chan->center_freq;
+	switch (ch->width) {
+	case NL80211_CHAN_WIDTH_20:
+		ch_inf.bw = BRCMU_CHAN_BW_20;
+		WARN_ON(primary_offset != 0);
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		ch_inf.bw = BRCMU_CHAN_BW_40;
+		if (primary_offset < 0)
+			ch_inf.sb = BRCMU_CHAN_SB_U;
+		else
+			ch_inf.sb = BRCMU_CHAN_SB_L;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		ch_inf.bw = BRCMU_CHAN_BW_80;
+		if (primary_offset < 0) {
+			if (primary_offset < -CH_10MHZ_APART)
+				ch_inf.sb = BRCMU_CHAN_SB_UU;
+			else
+				ch_inf.sb = BRCMU_CHAN_SB_UL;
+		} else {
+			if (primary_offset > CH_10MHZ_APART)
+				ch_inf.sb = BRCMU_CHAN_SB_LL;
+			else
+				ch_inf.sb = BRCMU_CHAN_SB_LU;
+		}
+		break;
+	default:
+		WARN_ON_ONCE(1);
+	}
+	switch (ch->chan->band) {
+	case IEEE80211_BAND_2GHZ:
+		ch_inf.band = BRCMU_CHAN_BAND_2G;
+		break;
+	case IEEE80211_BAND_5GHZ:
+		ch_inf.band = BRCMU_CHAN_BAND_5G;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+	}
+	d11inf->encchspec(&ch_inf);
+
+	return ch_inf.chspec;
+}
+
 u16 channel_to_chanspec(struct brcmu_d11inf *d11inf,
 			struct ieee80211_channel *ch)
 {
@@ -586,6 +640,9 @@ s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg,
 		if (err)
 			brcmf_err("Scan abort  failed\n");
 	}
+
+	brcmf_set_mpc(ifp, 1);
+
 	/*
 	 * e-scan can be initiated by scheduled scan
 	 * which takes precedence.
@@ -595,12 +652,10 @@ s32 brcmf_notify_escan_complete(struct brcmf_cfg80211_info *cfg,
 		cfg->sched_escan = false;
 		if (!aborted)
 			cfg80211_sched_scan_results(cfg_to_wiphy(cfg));
-		brcmf_set_mpc(ifp, 1);
 	} else if (scan_request) {
 		brcmf_dbg(SCAN, "ESCAN Completed scan: %s\n",
 			  aborted ? "Aborted" : "Done");
 		cfg80211_scan_done(scan_request, aborted);
-		brcmf_set_mpc(ifp, 1);
 	}
 	if (!test_and_clear_bit(BRCMF_SCAN_STATUS_BUSY, &cfg->scan_status))
 		brcmf_dbg(SCAN, "Scan complete, probably P2P scan\n");
@@ -1236,8 +1291,8 @@ brcmf_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *ndev,
 				params->chandef.chan->center_freq);
 		if (params->channel_fixed) {
 			/* adding chanspec */
-			chanspec = channel_to_chanspec(&cfg->d11inf,
-						       params->chandef.chan);
+			chanspec = chandef_to_chanspec(&cfg->d11inf,
+						       &params->chandef);
 			join_params.params_le.chanspec_list[0] =
 				cpu_to_le16(chanspec);
 			join_params.params_le.chanspec_num = cpu_to_le32(1);
@@ -2182,7 +2237,7 @@ brcmf_cfg80211_config_default_mgmt_key(struct wiphy *wiphy,
 
 static s32
 brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
-			   u8 *mac, struct station_info *sinfo)
+			   const u8 *mac, struct station_info *sinfo)
 {
 	struct brcmf_if *ifp = netdev_priv(ndev);
 	struct brcmf_cfg80211_profile *profile = &ifp->vif->profile;
@@ -3124,7 +3179,7 @@ brcmf_cfg80211_sched_scan_start(struct wiphy *wiphy,
 	}
 
 	if (!request->n_ssids || !request->n_match_sets) {
-		brcmf_err("Invalid sched scan req!! n_ssids:%d\n",
+		brcmf_dbg(SCAN, "Invalid sched scan req!! n_ssids:%d\n",
 			  request->n_ssids);
 		return -EINVAL;
 	}
@@ -3734,23 +3789,6 @@ brcmf_config_ap_mgmt_ie(struct brcmf_cfg80211_vif *vif,
 }
 
 static s32
-brcmf_cfg80211_set_channel(struct brcmf_cfg80211_info *cfg,
-			   struct brcmf_if *ifp,
-			   struct ieee80211_channel *channel)
-{
-	u16 chanspec;
-	s32 err;
-
-	brcmf_dbg(TRACE, "band=%d, center_freq=%d\n", channel->band,
-		  channel->center_freq);
-
-	chanspec = channel_to_chanspec(&cfg->d11inf, channel);
-	err = brcmf_fil_iovar_int_set(ifp, "chanspec", chanspec);
-
-	return err;
-}
-
-static s32
 brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 			struct cfg80211_ap_settings *settings)
 {
@@ -3765,11 +3803,12 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 	struct brcmf_join_params join_params;
 	enum nl80211_iftype dev_role;
 	struct brcmf_fil_bss_enable_le bss_enable;
+	u16 chanspec;
 
-	brcmf_dbg(TRACE, "channel_type=%d, beacon_interval=%d, dtim_period=%d,\n",
-		  cfg80211_get_chandef_type(&settings->chandef),
-		  settings->beacon_interval,
-		  settings->dtim_period);
+	brcmf_dbg(TRACE, "ctrlchn=%d, center=%d, bw=%d, beacon_interval=%d, dtim_period=%d,\n",
+		  settings->chandef.chan->hw_value,
+		  settings->chandef.center_freq1, settings->chandef.width,
+		  settings->beacon_interval, settings->dtim_period);
 	brcmf_dbg(TRACE, "ssid=%s(%zu), auth_type=%d, inactivity_timeout=%d\n",
 		  settings->ssid, settings->ssid_len, settings->auth_type,
 		  settings->inactivity_timeout);
@@ -3826,9 +3865,10 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev,
 
 	brcmf_config_ap_mgmt_ie(ifp->vif, &settings->beacon);
 
-	err = brcmf_cfg80211_set_channel(cfg, ifp, settings->chandef.chan);
+	chanspec = chandef_to_chanspec(&cfg->d11inf, &settings->chandef);
+	err = brcmf_fil_iovar_int_set(ifp, "chanspec", chanspec);
 	if (err < 0) {
-		brcmf_err("Set Channel failed, %d\n", err);
+		brcmf_err("Set Channel failed: chspec=%d, %d\n", chanspec, err);
 		goto exit;
 	}
 
@@ -3975,7 +4015,7 @@ brcmf_cfg80211_change_beacon(struct wiphy *wiphy, struct net_device *ndev,
 
 static int
 brcmf_cfg80211_del_station(struct wiphy *wiphy, struct net_device *ndev,
-			   u8 *mac)
+			   const u8 *mac)
 {
 	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
 	struct brcmf_scb_val_le scbval;
@@ -4203,7 +4243,7 @@ static int brcmf_convert_nl80211_tdls_oper(enum nl80211_tdls_operation oper)
 }
 
 static int brcmf_cfg80211_tdls_oper(struct wiphy *wiphy,
-				    struct net_device *ndev, u8 *peer,
+				    struct net_device *ndev, const u8 *peer,
 				    enum nl80211_tdls_operation oper)
 {
 	struct brcmf_if *ifp;
@@ -4364,6 +4404,8 @@ static struct wiphy *brcmf_setup_wiphy(struct device *phydev)
 			WIPHY_FLAG_OFFCHAN_TX |
 			WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL |
 			WIPHY_FLAG_SUPPORTS_TDLS;
+	if (!brcmf_roamoff)
+		wiphy->flags |= WIPHY_FLAG_SUPPORTS_FW_ROAM;
 	wiphy->mgmt_stypes = brcmf_txrx_stypes;
 	wiphy->max_remain_on_channel_duration = 5000;
 	brcmf_wiphy_pno_params(wiphy);
@@ -4685,7 +4727,6 @@ brcmf_notify_connect_status(struct brcmf_if *ifp,
 	struct brcmf_cfg80211_profile *profile = &ifp->vif->profile;
 	struct ieee80211_channel *chan;
 	s32 err = 0;
-	u16 reason;
 
 	if (brcmf_is_apmode(ifp->vif)) {
 		err = brcmf_notify_connect_status_ap(cfg, ndev, e, data);
@@ -4706,16 +4747,6 @@ brcmf_notify_connect_status(struct brcmf_if *ifp,
 		brcmf_dbg(CONN, "Linkdown\n");
 		if (!brcmf_is_ibssmode(ifp->vif)) {
 			brcmf_bss_connect_done(cfg, ndev, e, false);
-			if (test_and_clear_bit(BRCMF_VIF_STATUS_CONNECTED,
-					       &ifp->vif->sme_state)) {
-				reason = 0;
-				if (((e->event_code == BRCMF_E_DEAUTH_IND) ||
-				     (e->event_code == BRCMF_E_DISASSOC_IND)) &&
-				    (e->reason != WLAN_REASON_UNSPECIFIED))
-					reason = e->reason;
-				cfg80211_disconnected(ndev, reason, NULL, 0,
-						      GFP_KERNEL);
-			}
 		}
 		brcmf_link_down(ifp->vif);
 		brcmf_init_prof(ndev_to_prof(ndev));
@@ -5215,6 +5246,9 @@ static s32 brcmf_construct_reginfo(struct brcmf_cfg80211_info *cfg,
 		if (!(bw_cap[band] & WLC_BW_40MHZ_BIT) &&
 		    ch.bw == BRCMU_CHAN_BW_40)
 			continue;
+		if (!(bw_cap[band] & WLC_BW_80MHZ_BIT) &&
+		    ch.bw == BRCMU_CHAN_BW_80)
+			continue;
 		update = false;
 		for (j = 0; (j < *n_cnt && (*n_cnt < array_size)); j++) {
 			if (band_chan_arr[j].hw_value == ch.chnum) {
@@ -5231,10 +5265,13 @@ static s32 brcmf_construct_reginfo(struct brcmf_cfg80211_info *cfg,
 				ieee80211_channel_to_frequency(ch.chnum, band);
 			band_chan_arr[index].hw_value = ch.chnum;
 
-			if (ch.bw == BRCMU_CHAN_BW_40) {
-				/* assuming the order is HT20, HT40 Upper,
-				 * HT40 lower from chanspecs
-				 */
+			/* assuming the chanspecs order is HT20,
+			 * HT40 upper, HT40 lower, and VHT80.
+			 */
+			if (ch.bw == BRCMU_CHAN_BW_80) {
+				band_chan_arr[index].flags &=
+					~IEEE80211_CHAN_NO_80MHZ;
+			} else if (ch.bw == BRCMU_CHAN_BW_40) {
 				ht40_flag = band_chan_arr[index].flags &
 					    IEEE80211_CHAN_NO_HT40;
 				if (ch.sb == BRCMU_CHAN_SB_U) {
@@ -5255,8 +5292,13 @@ static s32 brcmf_construct_reginfo(struct brcmf_cfg80211_info *cfg,
 						    IEEE80211_CHAN_NO_HT40MINUS;
 				}
 			} else {
+				/* disable other bandwidths for now as mentioned
+				 * order assure they are enabled for subsequent
+				 * chanspecs.
+				 */
 				band_chan_arr[index].flags =
-							IEEE80211_CHAN_NO_HT40;
+						IEEE80211_CHAN_NO_HT40 |
+						IEEE80211_CHAN_NO_80MHZ;
 				ch.bw = BRCMU_CHAN_BW_20;
 				cfg->d11inf.encchspec(&ch);
 				channel = ch.chspec;
@@ -5323,13 +5365,63 @@ static void brcmf_get_bwcap(struct brcmf_if *ifp, u32 bw_cap[])
 	}
 }
 
+static void brcmf_update_ht_cap(struct ieee80211_supported_band *band,
+				u32 bw_cap[2], u32 nchain)
+{
+	band->ht_cap.ht_supported = true;
+	if (bw_cap[band->band] & WLC_BW_40MHZ_BIT) {
+		band->ht_cap.cap |= IEEE80211_HT_CAP_SGI_40;
+		band->ht_cap.cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40;
+	}
+	band->ht_cap.cap |= IEEE80211_HT_CAP_SGI_20;
+	band->ht_cap.cap |= IEEE80211_HT_CAP_DSSSCCK40;
+	band->ht_cap.ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K;
+	band->ht_cap.ampdu_density = IEEE80211_HT_MPDU_DENSITY_16;
+	memset(band->ht_cap.mcs.rx_mask, 0xff, nchain);
+	band->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
+}
+
+static __le16 brcmf_get_mcs_map(u32 nchain, enum ieee80211_vht_mcs_support supp)
+{
+	u16 mcs_map;
+	int i;
+
+	for (i = 0, mcs_map = 0xFFFF; i < nchain; i++)
+		mcs_map = (mcs_map << 2) | supp;
+
+	return cpu_to_le16(mcs_map);
+}
+
+static void brcmf_update_vht_cap(struct ieee80211_supported_band *band,
+				 u32 bw_cap[2], u32 nchain)
+{
+	__le16 mcs_map;
+
+	/* not allowed in 2.4G band */
+	if (band->band == IEEE80211_BAND_2GHZ)
+		return;
+
+	band->vht_cap.vht_supported = true;
+	/* 80MHz is mandatory */
+	band->vht_cap.cap |= IEEE80211_VHT_CAP_SHORT_GI_80;
+	if (bw_cap[band->band] & WLC_BW_160MHZ_BIT) {
+		band->vht_cap.cap |= IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ;
+		band->vht_cap.cap |= IEEE80211_VHT_CAP_SHORT_GI_160;
+	}
+	/* all support 256-QAM */
+	mcs_map = brcmf_get_mcs_map(nchain, IEEE80211_VHT_MCS_SUPPORT_0_9);
+	band->vht_cap.vht_mcs.rx_mcs_map = mcs_map;
+	band->vht_cap.vht_mcs.tx_mcs_map = mcs_map;
+}
+
 static s32 brcmf_update_wiphybands(struct brcmf_cfg80211_info *cfg)
 {
 	struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg));
 	struct wiphy *wiphy;
 	s32 phy_list;
 	u32 band_list[3];
-	u32 nmode;
+	u32 nmode = 0;
+	u32 vhtmode = 0;
 	u32 bw_cap[2] = { 0, 0 };
 	u32 rxchain;
 	u32 nchain;
@@ -5360,14 +5452,16 @@ static s32 brcmf_update_wiphybands(struct brcmf_cfg80211_info *cfg)
 	brcmf_dbg(INFO, "BRCMF_C_GET_BANDLIST reported: 0x%08x 0x%08x 0x%08x phy\n",
 		  band_list[0], band_list[1], band_list[2]);
 
+	(void)brcmf_fil_iovar_int_get(ifp, "vhtmode", &vhtmode);
 	err = brcmf_fil_iovar_int_get(ifp, "nmode", &nmode);
 	if (err) {
 		brcmf_err("nmode error (%d)\n", err);
 	} else {
 		brcmf_get_bwcap(ifp, bw_cap);
 	}
-	brcmf_dbg(INFO, "nmode=%d, bw_cap=(%d, %d)\n", nmode,
-		  bw_cap[IEEE80211_BAND_2GHZ], bw_cap[IEEE80211_BAND_5GHZ]);
+	brcmf_dbg(INFO, "nmode=%d, vhtmode=%d, bw_cap=(%d, %d)\n",
+		  nmode, vhtmode, bw_cap[IEEE80211_BAND_2GHZ],
+		  bw_cap[IEEE80211_BAND_5GHZ]);
 
 	err = brcmf_fil_iovar_int_get(ifp, "rxchain", &rxchain);
 	if (err) {
@@ -5398,17 +5492,10 @@ static s32 brcmf_update_wiphybands(struct brcmf_cfg80211_info *cfg)
 		else
 			continue;
 
-		if (bw_cap[band->band] & WLC_BW_40MHZ_BIT) {
-			band->ht_cap.cap |= IEEE80211_HT_CAP_SGI_40;
-			band->ht_cap.cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40;
-		}
-		band->ht_cap.cap |= IEEE80211_HT_CAP_SGI_20;
-		band->ht_cap.cap |= IEEE80211_HT_CAP_DSSSCCK40;
-		band->ht_cap.ht_supported = true;
-		band->ht_cap.ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K;
-		band->ht_cap.ampdu_density = IEEE80211_HT_MPDU_DENSITY_16;
-		memset(band->ht_cap.mcs.rx_mask, 0xff, nchain);
-		band->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
+		if (nmode)
+			brcmf_update_ht_cap(band, bw_cap, nchain);
+		if (vhtmode)
+			brcmf_update_vht_cap(band, bw_cap, nchain);
 		bands[band->band] = band;
 	}
 
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
index 8c5fa4e5813..43c71bfaa47 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
@@ -897,7 +897,8 @@ static bool brcms_tx_flush_completed(struct brcms_info *wl)
 	return result;
 }
 
-static void brcms_ops_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void brcms_ops_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			    u32 queues, bool drop)
 {
 	struct brcms_info *wl = hw->priv;
 	int ret;
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/main.c b/drivers/net/wireless/brcm80211/brcmsmac/main.c
index 9417cb5a255..af8ba64ace3 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/main.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/main.c
@@ -4870,14 +4870,11 @@ static void brcms_c_detach_module(struct brcms_c_info *wlc)
 /*
  * low level detach
  */
-static int brcms_b_detach(struct brcms_c_info *wlc)
+static void brcms_b_detach(struct brcms_c_info *wlc)
 {
 	uint i;
 	struct brcms_hw_band *band;
 	struct brcms_hardware *wlc_hw = wlc->hw;
-	int callbacks;
-
-	callbacks = 0;
 
 	brcms_b_detach_dmapio(wlc_hw);
 
@@ -4900,9 +4897,6 @@ static int brcms_b_detach(struct brcms_c_info *wlc)
 		ai_detach(wlc_hw->sih);
 		wlc_hw->sih = NULL;
 	}
-
-	return callbacks;
-
 }
 
 /*
@@ -4917,14 +4911,15 @@ static int brcms_b_detach(struct brcms_c_info *wlc)
  */
 uint brcms_c_detach(struct brcms_c_info *wlc)
 {
-	uint callbacks = 0;
+	uint callbacks;
 
 	if (wlc == NULL)
 		return 0;
 
-	callbacks += brcms_b_detach(wlc);
+	brcms_b_detach(wlc);
 
 	/* delete software timers */
+	callbacks = 0;
 	if (!brcms_c_radio_monitor_stop(wlc))
 		callbacks++;
 
diff --git a/drivers/net/wireless/brcm80211/brcmutil/d11.c b/drivers/net/wireless/brcm80211/brcmutil/d11.c
index 30e54e2c6c9..2b2522bdd8e 100644
--- a/drivers/net/wireless/brcm80211/brcmutil/d11.c
+++ b/drivers/net/wireless/brcm80211/brcmutil/d11.c
@@ -21,19 +21,46 @@
 #include <brcmu_wifi.h>
 #include <brcmu_d11.h>
 
-static void brcmu_d11n_encchspec(struct brcmu_chan *ch)
+static u16 d11n_sb(enum brcmu_chan_sb sb)
 {
-	ch->chspec = ch->chnum & BRCMU_CHSPEC_CH_MASK;
+	switch (sb) {
+	case BRCMU_CHAN_SB_NONE:
+		return BRCMU_CHSPEC_D11N_SB_N;
+	case BRCMU_CHAN_SB_L:
+		return BRCMU_CHSPEC_D11N_SB_L;
+	case BRCMU_CHAN_SB_U:
+		return BRCMU_CHSPEC_D11N_SB_U;
+	default:
+		WARN_ON(1);
+	}
+	return 0;
+}
 
-	switch (ch->bw) {
+static u16 d11n_bw(enum brcmu_chan_bw bw)
+{
+	switch (bw) {
 	case BRCMU_CHAN_BW_20:
-		ch->chspec |= BRCMU_CHSPEC_D11N_BW_20 | BRCMU_CHSPEC_D11N_SB_N;
-		break;
+		return BRCMU_CHSPEC_D11N_BW_20;
 	case BRCMU_CHAN_BW_40:
+		return BRCMU_CHSPEC_D11N_BW_40;
 	default:
-		WARN_ON_ONCE(1);
-		break;
+		WARN_ON(1);
 	}
+	return 0;
+}
+
+static void brcmu_d11n_encchspec(struct brcmu_chan *ch)
+{
+	if (ch->bw == BRCMU_CHAN_BW_20)
+		ch->sb = BRCMU_CHAN_SB_NONE;
+
+	ch->chspec = 0;
+	brcmu_maskset16(&ch->chspec, BRCMU_CHSPEC_CH_MASK,
+			BRCMU_CHSPEC_CH_SHIFT, ch->chnum);
+	brcmu_maskset16(&ch->chspec, BRCMU_CHSPEC_D11N_SB_MASK,
+			0, d11n_sb(ch->sb));
+	brcmu_maskset16(&ch->chspec, BRCMU_CHSPEC_D11N_BW_MASK,
+			0, d11n_bw(ch->bw));
 
 	if (ch->chnum <= CH_MAX_2G_CHANNEL)
 		ch->chspec |= BRCMU_CHSPEC_D11N_BND_2G;
@@ -41,23 +68,34 @@ static void brcmu_d11n_encchspec(struct brcmu_chan *ch)
 		ch->chspec |= BRCMU_CHSPEC_D11N_BND_5G;
 }
 
-static void brcmu_d11ac_encchspec(struct brcmu_chan *ch)
+static u16 d11ac_bw(enum brcmu_chan_bw bw)
 {
-	ch->chspec = ch->chnum & BRCMU_CHSPEC_CH_MASK;
-
-	switch (ch->bw) {
+	switch (bw) {
 	case BRCMU_CHAN_BW_20:
-		ch->chspec |= BRCMU_CHSPEC_D11AC_BW_20;
-		break;
+		return BRCMU_CHSPEC_D11AC_BW_20;
 	case BRCMU_CHAN_BW_40:
+		return BRCMU_CHSPEC_D11AC_BW_40;
 	case BRCMU_CHAN_BW_80:
-	case BRCMU_CHAN_BW_80P80:
-	case BRCMU_CHAN_BW_160:
+		return BRCMU_CHSPEC_D11AC_BW_80;
 	default:
-		WARN_ON_ONCE(1);
-		break;
+		WARN_ON(1);
 	}
+	return 0;
+}
 
+static void brcmu_d11ac_encchspec(struct brcmu_chan *ch)
+{
+	if (ch->bw == BRCMU_CHAN_BW_20 || ch->sb == BRCMU_CHAN_SB_NONE)
+		ch->sb = BRCMU_CHAN_SB_L;
+
+	brcmu_maskset16(&ch->chspec, BRCMU_CHSPEC_CH_MASK,
+			BRCMU_CHSPEC_CH_SHIFT, ch->chnum);
+	brcmu_maskset16(&ch->chspec, BRCMU_CHSPEC_D11AC_SB_MASK,
+			BRCMU_CHSPEC_D11AC_SB_SHIFT, ch->sb);
+	brcmu_maskset16(&ch->chspec, BRCMU_CHSPEC_D11AC_BW_MASK,
+			0, d11ac_bw(ch->bw));
+
+	ch->chspec &= ~BRCMU_CHSPEC_D11AC_BND_MASK;
 	if (ch->chnum <= CH_MAX_2G_CHANNEL)
 		ch->chspec |= BRCMU_CHSPEC_D11AC_BND_2G;
 	else
@@ -73,6 +111,7 @@ static void brcmu_d11n_decchspec(struct brcmu_chan *ch)
 	switch (ch->chspec & BRCMU_CHSPEC_D11N_BW_MASK) {
 	case BRCMU_CHSPEC_D11N_BW_20:
 		ch->bw = BRCMU_CHAN_BW_20;
+		ch->sb = BRCMU_CHAN_SB_NONE;
 		break;
 	case BRCMU_CHSPEC_D11N_BW_40:
 		ch->bw = BRCMU_CHAN_BW_40;
@@ -112,6 +151,7 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch)
 	switch (ch->chspec & BRCMU_CHSPEC_D11AC_BW_MASK) {
 	case BRCMU_CHSPEC_D11AC_BW_20:
 		ch->bw = BRCMU_CHAN_BW_20;
+		ch->sb = BRCMU_CHAN_SB_NONE;
 		break;
 	case BRCMU_CHSPEC_D11AC_BW_40:
 		ch->bw = BRCMU_CHAN_BW_40;
@@ -128,6 +168,25 @@ static void brcmu_d11ac_decchspec(struct brcmu_chan *ch)
 		break;
 	case BRCMU_CHSPEC_D11AC_BW_80:
 		ch->bw = BRCMU_CHAN_BW_80;
+		ch->sb = brcmu_maskget16(ch->chspec, BRCMU_CHSPEC_D11AC_SB_MASK,
+					 BRCMU_CHSPEC_D11AC_SB_SHIFT);
+		switch (ch->sb) {
+		case BRCMU_CHAN_SB_LL:
+			ch->chnum -= CH_30MHZ_APART;
+			break;
+		case BRCMU_CHAN_SB_LU:
+			ch->chnum -= CH_10MHZ_APART;
+			break;
+		case BRCMU_CHAN_SB_UL:
+			ch->chnum += CH_10MHZ_APART;
+			break;
+		case BRCMU_CHAN_SB_UU:
+			ch->chnum += CH_30MHZ_APART;
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			break;
+		}
 		break;
 	case BRCMU_CHSPEC_D11AC_BW_8080:
 	case BRCMU_CHSPEC_D11AC_BW_160:
diff --git a/drivers/net/wireless/brcm80211/include/brcmu_d11.h b/drivers/net/wireless/brcm80211/include/brcmu_d11.h
index 8660a2cba09..f9745ea8b3e 100644
--- a/drivers/net/wireless/brcm80211/include/brcmu_d11.h
+++ b/drivers/net/wireless/brcm80211/include/brcmu_d11.h
@@ -108,13 +108,7 @@ enum brcmu_chan_bw {
 };
 
 enum brcmu_chan_sb {
-	BRCMU_CHAN_SB_NONE = 0,
-	BRCMU_CHAN_SB_L,
-	BRCMU_CHAN_SB_U,
-	BRCMU_CHAN_SB_LL,
-	BRCMU_CHAN_SB_LU,
-	BRCMU_CHAN_SB_UL,
-	BRCMU_CHAN_SB_UU,
+	BRCMU_CHAN_SB_NONE = -1,
 	BRCMU_CHAN_SB_LLL,
 	BRCMU_CHAN_SB_LLU,
 	BRCMU_CHAN_SB_LUL,
@@ -123,6 +117,12 @@ enum brcmu_chan_sb {
 	BRCMU_CHAN_SB_ULU,
 	BRCMU_CHAN_SB_UUL,
 	BRCMU_CHAN_SB_UUU,
+	BRCMU_CHAN_SB_L = BRCMU_CHAN_SB_LLL,
+	BRCMU_CHAN_SB_U = BRCMU_CHAN_SB_LLU,
+	BRCMU_CHAN_SB_LL = BRCMU_CHAN_SB_LLL,
+	BRCMU_CHAN_SB_LU = BRCMU_CHAN_SB_LLU,
+	BRCMU_CHAN_SB_UL = BRCMU_CHAN_SB_LUL,
+	BRCMU_CHAN_SB_UU = BRCMU_CHAN_SB_LUU,
 };
 
 struct brcmu_chan {
diff --git a/drivers/net/wireless/brcm80211/include/brcmu_wifi.h b/drivers/net/wireless/brcm80211/include/brcmu_wifi.h
index 74419d4bd12..76b5d3a8629 100644
--- a/drivers/net/wireless/brcm80211/include/brcmu_wifi.h
+++ b/drivers/net/wireless/brcm80211/include/brcmu_wifi.h
@@ -29,6 +29,7 @@
 #define CH_UPPER_SB			0x01
 #define CH_LOWER_SB			0x02
 #define CH_EWA_VALID			0x04
+#define CH_30MHZ_APART			6
 #define CH_20MHZ_APART			4
 #define CH_10MHZ_APART			2
 #define CH_5MHZ_APART			1 /* 2G band channels are 5 Mhz apart */
diff --git a/drivers/net/wireless/cw1200/sta.c b/drivers/net/wireless/cw1200/sta.c
index 103f7bce893..cd0cad7f775 100644
--- a/drivers/net/wireless/cw1200/sta.c
+++ b/drivers/net/wireless/cw1200/sta.c
@@ -936,7 +936,8 @@ static int __cw1200_flush(struct cw1200_common *priv, bool drop)
 	return ret;
 }
 
-void cw1200_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+void cw1200_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  u32 queues, bool drop)
 {
 	struct cw1200_common *priv = hw->priv;
 
diff --git a/drivers/net/wireless/cw1200/sta.h b/drivers/net/wireless/cw1200/sta.h
index 35babb62cc6..b7e386b7662 100644
--- a/drivers/net/wireless/cw1200/sta.h
+++ b/drivers/net/wireless/cw1200/sta.h
@@ -40,7 +40,8 @@ int cw1200_set_key(struct ieee80211_hw *dev, enum set_key_cmd cmd,
 
 int cw1200_set_rts_threshold(struct ieee80211_hw *hw, u32 value);
 
-void cw1200_flush(struct ieee80211_hw *hw, u32 queues, bool drop);
+void cw1200_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  u32 queues, bool drop);
 
 u64 cw1200_prepare_multicast(struct ieee80211_hw *hw,
 			     struct netdev_hw_addr_list *mc_list);
diff --git a/drivers/net/wireless/hostap/hostap_main.c b/drivers/net/wireless/hostap/hostap_main.c
index 67db34e56d7..52919ad4272 100644
--- a/drivers/net/wireless/hostap/hostap_main.c
+++ b/drivers/net/wireless/hostap/hostap_main.c
@@ -882,7 +882,7 @@ void hostap_setup_dev(struct net_device *dev, local_info_t *local,
 	dev->mtu = local->mtu;
 
 
-	SET_ETHTOOL_OPS(dev, &prism2_ethtool_ops);
+	dev->ethtool_ops = &prism2_ethtool_ops;
 
 }
 
diff --git a/drivers/net/wireless/iwlegacy/3945.c b/drivers/net/wireless/iwlegacy/3945.c
index d37a6fd90d4..b598e280350 100644
--- a/drivers/net/wireless/iwlegacy/3945.c
+++ b/drivers/net/wireless/iwlegacy/3945.c
@@ -573,7 +573,7 @@ il3945_hdl_rx(struct il_priv *il, struct il_rx_buf *rxb)
 		rx_status.flag |= RX_FLAG_SHORTPRE;
 
 	if ((unlikely(rx_stats->phy_count > 20))) {
-		D_DROP("dsp size out of range [0,20]: %d/n",
+		D_DROP("dsp size out of range [0,20]: %d\n",
 		       rx_stats->phy_count);
 		return;
 	}
diff --git a/drivers/net/wireless/iwlegacy/4965-mac.c b/drivers/net/wireless/iwlegacy/4965-mac.c
index 888ad5c7463..c159c05db6e 100644
--- a/drivers/net/wireless/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/iwlegacy/4965-mac.c
@@ -670,7 +670,7 @@ il4965_hdl_rx(struct il_priv *il, struct il_rx_buf *rxb)
 	}
 
 	if ((unlikely(phy_res->cfg_phy_cnt > 20))) {
-		D_DROP("dsp size out of range [0,20]: %d/n",
+		D_DROP("dsp size out of range [0,20]: %d\n",
 		       phy_res->cfg_phy_cnt);
 		return;
 	}
diff --git a/drivers/net/wireless/iwlegacy/common.c b/drivers/net/wireless/iwlegacy/common.c
index 4f42174d999..ecc674627e6 100644
--- a/drivers/net/wireless/iwlegacy/common.c
+++ b/drivers/net/wireless/iwlegacy/common.c
@@ -4755,7 +4755,8 @@ out:
 }
 EXPORT_SYMBOL(il_mac_change_interface);
 
-void il_mac_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+void il_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  u32 queues, bool drop)
 {
 	struct il_priv *il = hw->priv;
 	unsigned long timeout = jiffies + msecs_to_jiffies(500);
diff --git a/drivers/net/wireless/iwlegacy/common.h b/drivers/net/wireless/iwlegacy/common.h
index dfb13c70efe..ea5c0f863c4 100644
--- a/drivers/net/wireless/iwlegacy/common.h
+++ b/drivers/net/wireless/iwlegacy/common.h
@@ -1723,7 +1723,8 @@ void il_mac_remove_interface(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif);
 int il_mac_change_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			    enum nl80211_iftype newtype, bool newp2p);
-void il_mac_flush(struct ieee80211_hw *hw, u32 queues, bool drop);
+void il_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  u32 queues, bool drop);
 int il_alloc_txq_mem(struct il_priv *il);
 void il_free_txq_mem(struct il_priv *il);
 
diff --git a/drivers/net/wireless/iwlwifi/Kconfig b/drivers/net/wireless/iwlwifi/Kconfig
index 74b3b4de7bb..7fd50428b93 100644
--- a/drivers/net/wireless/iwlwifi/Kconfig
+++ b/drivers/net/wireless/iwlwifi/Kconfig
@@ -2,10 +2,6 @@ config IWLWIFI
 	tristate "Intel Wireless WiFi Next Gen AGN - Wireless-N/Advanced-N/Ultimate-N (iwlwifi) "
 	depends on PCI && MAC80211 && HAS_IOMEM
 	select FW_LOADER
-	select NEW_LEDS
-	select LEDS_CLASS
-	select LEDS_TRIGGERS
-	select MAC80211_LEDS
 	---help---
 	  Select to build the driver supporting the:
 
@@ -43,6 +39,14 @@ config IWLWIFI
 	  say M here and read <file:Documentation/kbuild/modules.txt>.  The
 	  module will be called iwlwifi.
 
+config IWLWIFI_LEDS
+	bool
+	depends on IWLWIFI
+	depends on LEDS_CLASS=y || LEDS_CLASS=IWLWIFI
+	select LEDS_TRIGGERS
+	select MAC80211_LEDS
+	default y
+
 config IWLDVM
 	tristate "Intel Wireless WiFi DVM Firmware support"
 	depends on IWLWIFI
@@ -124,7 +128,6 @@ config IWLWIFI_DEBUG_EXPERIMENTAL_UCODE
 	  Enable use of experimental ucode for testing and debugging.
 
 config IWLWIFI_DEVICE_TRACING
-
 	bool "iwlwifi device access tracing"
 	depends on IWLWIFI
 	depends on EVENT_TRACING
diff --git a/drivers/net/wireless/iwlwifi/dvm/Makefile b/drivers/net/wireless/iwlwifi/dvm/Makefile
index dce7ab2e0c4..4d19685f31c 100644
--- a/drivers/net/wireless/iwlwifi/dvm/Makefile
+++ b/drivers/net/wireless/iwlwifi/dvm/Makefile
@@ -4,9 +4,10 @@ iwldvm-objs		+= main.o rs.o mac80211.o ucode.o tx.o
 iwldvm-objs		+= lib.o calib.o tt.o sta.o rx.o
 
 iwldvm-objs		+= power.o
-iwldvm-objs		+= scan.o led.o
+iwldvm-objs		+= scan.o
 iwldvm-objs		+= rxon.o devices.o
 
+iwldvm-$(CONFIG_IWLWIFI_LEDS) += led.o
 iwldvm-$(CONFIG_IWLWIFI_DEBUGFS) += debugfs.o
 
 ccflags-y += -D__CHECK_ENDIAN__ -I$(src)/../
diff --git a/drivers/net/wireless/iwlwifi/dvm/calib.c b/drivers/net/wireless/iwlwifi/dvm/calib.c
index be1086c8715..20e6aa91070 100644
--- a/drivers/net/wireless/iwlwifi/dvm/calib.c
+++ b/drivers/net/wireless/iwlwifi/dvm/calib.c
@@ -94,7 +94,6 @@ int iwl_send_calib_results(struct iwl_priv *priv)
 {
 	struct iwl_host_cmd hcmd = {
 		.id = REPLY_PHY_CALIBRATION_CMD,
-		.flags = CMD_SYNC,
 	};
 	struct iwl_calib_result *res;
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/debugfs.c b/drivers/net/wireless/iwlwifi/dvm/debugfs.c
index d2fe2596d54..0ffb6ff1a25 100644
--- a/drivers/net/wireless/iwlwifi/dvm/debugfs.c
+++ b/drivers/net/wireless/iwlwifi/dvm/debugfs.c
@@ -1481,7 +1481,7 @@ static ssize_t iwl_dbgfs_ucode_bt_stats_read(struct file *file,
 
 	/* make request to uCode to retrieve statistics information */
 	mutex_lock(&priv->mutex);
-	ret = iwl_send_statistics_request(priv, CMD_SYNC, false);
+	ret = iwl_send_statistics_request(priv, 0, false);
 	mutex_unlock(&priv->mutex);
 
 	if (ret)
@@ -1868,7 +1868,7 @@ static ssize_t iwl_dbgfs_clear_ucode_statistics_write(struct file *file,
 
 	/* make request to uCode to retrieve statistics information */
 	mutex_lock(&priv->mutex);
-	iwl_send_statistics_request(priv, CMD_SYNC, true);
+	iwl_send_statistics_request(priv, 0, true);
 	mutex_unlock(&priv->mutex);
 
 	return count;
@@ -2188,7 +2188,6 @@ static int iwl_cmd_echo_test(struct iwl_priv *priv)
 	struct iwl_host_cmd cmd = {
 		.id = REPLY_ECHO,
 		.len = { 0 },
-		.flags = CMD_SYNC,
 	};
 
 	ret = iwl_dvm_send_cmd(priv, &cmd);
@@ -2320,7 +2319,7 @@ static ssize_t iwl_dbgfs_fw_restart_write(struct file *file,
 	mutex_lock(&priv->mutex);
 
 	/* take the return value to make compiler happy - it will fail anyway */
-	ret = iwl_dvm_send_cmd_pdu(priv, REPLY_ERROR, CMD_SYNC, 0, NULL);
+	ret = iwl_dvm_send_cmd_pdu(priv, REPLY_ERROR, 0, 0, NULL);
 
 	mutex_unlock(&priv->mutex);
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/dev.h b/drivers/net/wireless/iwlwifi/dvm/dev.h
index 3441f70d0ff..a6f22c32a27 100644
--- a/drivers/net/wireless/iwlwifi/dvm/dev.h
+++ b/drivers/net/wireless/iwlwifi/dvm/dev.h
@@ -888,9 +888,11 @@ struct iwl_priv {
 
 	struct iwl_event_log event_log;
 
+#ifdef CONFIG_IWLWIFI_LEDS
 	struct led_classdev led;
 	unsigned long blink_on, blink_off;
 	bool led_registered;
+#endif
 
 	/* WoWLAN GTK rekey data */
 	u8 kck[NL80211_KCK_LEN], kek[NL80211_KEK_LEN];
diff --git a/drivers/net/wireless/iwlwifi/dvm/devices.c b/drivers/net/wireless/iwlwifi/dvm/devices.c
index 758c54eeb20..34b41e5f7cf 100644
--- a/drivers/net/wireless/iwlwifi/dvm/devices.c
+++ b/drivers/net/wireless/iwlwifi/dvm/devices.c
@@ -417,7 +417,6 @@ static int iwl5000_hw_channel_switch(struct iwl_priv *priv,
 	struct iwl_host_cmd hcmd = {
 		.id = REPLY_CHANNEL_SWITCH,
 		.len = { sizeof(cmd), },
-		.flags = CMD_SYNC,
 		.data = { &cmd, },
 	};
 
@@ -579,7 +578,6 @@ static int iwl6000_hw_channel_switch(struct iwl_priv *priv,
 	struct iwl_host_cmd hcmd = {
 		.id = REPLY_CHANNEL_SWITCH,
 		.len = { sizeof(*cmd), },
-		.flags = CMD_SYNC,
 		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
 	};
 	int err;
diff --git a/drivers/net/wireless/iwlwifi/dvm/led.h b/drivers/net/wireless/iwlwifi/dvm/led.h
index 6a0817d9c4f..1c6b2252d0f 100644
--- a/drivers/net/wireless/iwlwifi/dvm/led.h
+++ b/drivers/net/wireless/iwlwifi/dvm/led.h
@@ -36,8 +36,20 @@ struct iwl_priv;
 #define IWL_LED_ACTIVITY       (0<<1)
 #define IWL_LED_LINK           (1<<1)
 
+#ifdef CONFIG_IWLWIFI_LEDS
 void iwlagn_led_enable(struct iwl_priv *priv);
 void iwl_leds_init(struct iwl_priv *priv);
 void iwl_leds_exit(struct iwl_priv *priv);
+#else
+static inline void iwlagn_led_enable(struct iwl_priv *priv)
+{
+}
+static inline void iwl_leds_init(struct iwl_priv *priv)
+{
+}
+static inline void iwl_leds_exit(struct iwl_priv *priv)
+{
+}
+#endif
 
 #endif /* __iwl_leds_h__ */
diff --git a/drivers/net/wireless/iwlwifi/dvm/lib.c b/drivers/net/wireless/iwlwifi/dvm/lib.c
index 576f7ee38ca..2191621d69c 100644
--- a/drivers/net/wireless/iwlwifi/dvm/lib.c
+++ b/drivers/net/wireless/iwlwifi/dvm/lib.c
@@ -81,7 +81,7 @@ int iwlagn_send_tx_power(struct iwl_priv *priv)
 	else
 		tx_ant_cfg_cmd = REPLY_TX_POWER_DBM_CMD;
 
-	return iwl_dvm_send_cmd_pdu(priv, tx_ant_cfg_cmd, CMD_SYNC,
+	return iwl_dvm_send_cmd_pdu(priv, tx_ant_cfg_cmd, 0,
 			sizeof(tx_power_cmd), &tx_power_cmd);
 }
 
@@ -141,7 +141,6 @@ int iwlagn_txfifo_flush(struct iwl_priv *priv, u32 scd_q_msk)
 	struct iwl_host_cmd cmd = {
 		.id = REPLY_TXFIFO_FLUSH,
 		.len = { sizeof(struct iwl_txfifo_flush_cmd), },
-		.flags = CMD_SYNC,
 		.data = { &flush_cmd, },
 	};
 
@@ -180,7 +179,7 @@ void iwlagn_dev_txfifo_flush(struct iwl_priv *priv)
 		goto done;
 	}
 	IWL_DEBUG_INFO(priv, "wait transmit/flush all frames\n");
-	iwl_trans_wait_tx_queue_empty(priv->trans);
+	iwl_trans_wait_tx_queue_empty(priv->trans, 0xffffffff);
 done:
 	ieee80211_wake_queues(priv->hw);
 	mutex_unlock(&priv->mutex);
@@ -333,12 +332,12 @@ void iwlagn_send_advance_bt_config(struct iwl_priv *priv)
 		memcpy(&bt_cmd_v2.basic, &basic,
 			sizeof(basic));
 		ret = iwl_dvm_send_cmd_pdu(priv, REPLY_BT_CONFIG,
-			CMD_SYNC, sizeof(bt_cmd_v2), &bt_cmd_v2);
+			0, sizeof(bt_cmd_v2), &bt_cmd_v2);
 	} else {
 		memcpy(&bt_cmd_v1.basic, &basic,
 			sizeof(basic));
 		ret = iwl_dvm_send_cmd_pdu(priv, REPLY_BT_CONFIG,
-			CMD_SYNC, sizeof(bt_cmd_v1), &bt_cmd_v1);
+			0, sizeof(bt_cmd_v1), &bt_cmd_v1);
 	}
 	if (ret)
 		IWL_ERR(priv, "failed to send BT Coex Config\n");
@@ -1044,7 +1043,6 @@ int iwlagn_send_patterns(struct iwl_priv *priv,
 	struct iwl_host_cmd cmd = {
 		.id = REPLY_WOWLAN_PATTERNS,
 		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
-		.flags = CMD_SYNC,
 	};
 	int i, err;
 
@@ -1201,7 +1199,6 @@ int iwlagn_suspend(struct iwl_priv *priv, struct cfg80211_wowlan *wowlan)
 		if (key_data.use_rsc_tsc) {
 			struct iwl_host_cmd rsc_tsc_cmd = {
 				.id = REPLY_WOWLAN_TSC_RSC_PARAMS,
-				.flags = CMD_SYNC,
 				.data[0] = key_data.rsc_tsc,
 				.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
 				.len[0] = sizeof(*key_data.rsc_tsc),
@@ -1215,7 +1212,7 @@ int iwlagn_suspend(struct iwl_priv *priv, struct cfg80211_wowlan *wowlan)
 		if (key_data.use_tkip) {
 			ret = iwl_dvm_send_cmd_pdu(priv,
 						 REPLY_WOWLAN_TKIP_PARAMS,
-						 CMD_SYNC, sizeof(tkip_cmd),
+						 0, sizeof(tkip_cmd),
 						 &tkip_cmd);
 			if (ret)
 				goto out;
@@ -1231,20 +1228,20 @@ int iwlagn_suspend(struct iwl_priv *priv, struct cfg80211_wowlan *wowlan)
 
 			ret = iwl_dvm_send_cmd_pdu(priv,
 						 REPLY_WOWLAN_KEK_KCK_MATERIAL,
-						 CMD_SYNC, sizeof(kek_kck_cmd),
+						 0, sizeof(kek_kck_cmd),
 						 &kek_kck_cmd);
 			if (ret)
 				goto out;
 		}
 	}
 
-	ret = iwl_dvm_send_cmd_pdu(priv, REPLY_D3_CONFIG, CMD_SYNC,
+	ret = iwl_dvm_send_cmd_pdu(priv, REPLY_D3_CONFIG, 0,
 				     sizeof(d3_cfg_cmd), &d3_cfg_cmd);
 	if (ret)
 		goto out;
 
 	ret = iwl_dvm_send_cmd_pdu(priv, REPLY_WOWLAN_WAKEUP_FILTER,
-				 CMD_SYNC, sizeof(wakeup_filter_cmd),
+				 0, sizeof(wakeup_filter_cmd),
 				 &wakeup_filter_cmd);
 	if (ret)
 		goto out;
diff --git a/drivers/net/wireless/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
index dd55c9cf7ba..29af7b51e37 100644
--- a/drivers/net/wireless/iwlwifi/dvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/dvm/mac80211.c
@@ -1091,7 +1091,8 @@ static void iwlagn_configure_filter(struct ieee80211_hw *hw,
 			FIF_BCN_PRBRESP_PROMISC | FIF_CONTROL;
 }
 
-static void iwlagn_mac_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void iwlagn_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			     u32 queues, bool drop)
 {
 	struct iwl_priv *priv = IWL_MAC80211_GET_DVM(hw);
 
@@ -1119,7 +1120,7 @@ static void iwlagn_mac_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
 		}
 	}
 	IWL_DEBUG_MAC80211(priv, "wait transmit/flush all frames\n");
-	iwl_trans_wait_tx_queue_empty(priv->trans);
+	iwl_trans_wait_tx_queue_empty(priv->trans, 0xffffffff);
 done:
 	mutex_unlock(&priv->mutex);
 	IWL_DEBUG_MAC80211(priv, "leave\n");
diff --git a/drivers/net/wireless/iwlwifi/dvm/main.c b/drivers/net/wireless/iwlwifi/dvm/main.c
index 6a6df71af1d..0b7f46f0b07 100644
--- a/drivers/net/wireless/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/iwlwifi/dvm/main.c
@@ -128,7 +128,6 @@ int iwlagn_send_beacon_cmd(struct iwl_priv *priv)
 	struct iwl_tx_beacon_cmd *tx_beacon_cmd;
 	struct iwl_host_cmd cmd = {
 		.id = REPLY_TX_BEACON,
-		.flags = CMD_SYNC,
 	};
 	struct ieee80211_tx_info *info;
 	u32 frame_size;
@@ -311,8 +310,7 @@ int iwl_send_statistics_request(struct iwl_priv *priv, u8 flags, bool clear)
 					sizeof(struct iwl_statistics_cmd),
 					&statistics_cmd);
 	else
-		return iwl_dvm_send_cmd_pdu(priv, REPLY_STATISTICS_CMD,
-					CMD_SYNC,
+		return iwl_dvm_send_cmd_pdu(priv, REPLY_STATISTICS_CMD, 0,
 					sizeof(struct iwl_statistics_cmd),
 					&statistics_cmd);
 }
@@ -622,7 +620,7 @@ static void iwl_rf_kill_ct_config(struct iwl_priv *priv)
 
 		ret = iwl_dvm_send_cmd_pdu(priv,
 				       REPLY_CT_KILL_CONFIG_CMD,
-				       CMD_SYNC, sizeof(adv_cmd), &adv_cmd);
+				       0, sizeof(adv_cmd), &adv_cmd);
 		if (ret)
 			IWL_ERR(priv, "REPLY_CT_KILL_CONFIG_CMD failed\n");
 		else
@@ -637,7 +635,7 @@ static void iwl_rf_kill_ct_config(struct iwl_priv *priv)
 
 		ret = iwl_dvm_send_cmd_pdu(priv,
 				       REPLY_CT_KILL_CONFIG_CMD,
-				       CMD_SYNC, sizeof(cmd), &cmd);
+				       0, sizeof(cmd), &cmd);
 		if (ret)
 			IWL_ERR(priv, "REPLY_CT_KILL_CONFIG_CMD failed\n");
 		else
@@ -673,9 +671,7 @@ static int iwlagn_send_tx_ant_config(struct iwl_priv *priv, u8 valid_tx_ant)
 
 	if (IWL_UCODE_API(priv->fw->ucode_ver) > 1) {
 		IWL_DEBUG_HC(priv, "select valid tx ant: %u\n", valid_tx_ant);
-		return iwl_dvm_send_cmd_pdu(priv,
-					TX_ANT_CONFIGURATION_CMD,
-					CMD_SYNC,
+		return iwl_dvm_send_cmd_pdu(priv, TX_ANT_CONFIGURATION_CMD, 0,
 					sizeof(struct iwl_tx_ant_config_cmd),
 					&tx_ant_cmd);
 	} else {
@@ -703,7 +699,7 @@ static void iwl_send_bt_config(struct iwl_priv *priv)
 		(bt_cmd.flags == BT_COEX_DISABLE) ? "disable" : "active");
 
 	if (iwl_dvm_send_cmd_pdu(priv, REPLY_BT_CONFIG,
-			     CMD_SYNC, sizeof(struct iwl_bt_cmd), &bt_cmd))
+			     0, sizeof(struct iwl_bt_cmd), &bt_cmd))
 		IWL_ERR(priv, "failed to send BT Coex Config\n");
 }
 
@@ -987,7 +983,7 @@ static void iwl_bg_restart(struct work_struct *data)
 			ieee80211_restart_hw(priv->hw);
 		else
 			IWL_ERR(priv,
-				"Cannot request restart before registrating with mac80211");
+				"Cannot request restart before registrating with mac80211\n");
 	} else {
 		WARN_ON(1);
 	}
@@ -1127,7 +1123,6 @@ static void iwl_option_config(struct iwl_priv *priv)
 static int iwl_eeprom_init_hw_params(struct iwl_priv *priv)
 {
 	struct iwl_nvm_data *data = priv->nvm_data;
-	char *debug_msg;
 
 	if (data->sku_cap_11n_enable &&
 	    !priv->cfg->ht_params) {
@@ -1141,8 +1136,8 @@ static int iwl_eeprom_init_hw_params(struct iwl_priv *priv)
 		return -EINVAL;
 	}
 
-	debug_msg = "Device SKU: 24GHz %s %s, 52GHz %s %s, 11.n %s %s\n";
-	IWL_DEBUG_INFO(priv, debug_msg,
+	IWL_DEBUG_INFO(priv,
+		       "Device SKU: 24GHz %s %s, 52GHz %s %s, 11.n %s %s\n",
 		       data->sku_cap_band_24GHz_enable ? "" : "NOT", "enabled",
 		       data->sku_cap_band_52GHz_enable ? "" : "NOT", "enabled",
 		       data->sku_cap_11n_enable ? "" : "NOT", "enabled");
@@ -1350,7 +1345,7 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 	iwl_set_hw_params(priv);
 
 	if (!(priv->nvm_data->sku_cap_ipan_enable)) {
-		IWL_DEBUG_INFO(priv, "Your EEPROM disabled PAN");
+		IWL_DEBUG_INFO(priv, "Your EEPROM disabled PAN\n");
 		ucode_flags &= ~IWL_UCODE_TLV_FLAGS_PAN;
 		/*
 		 * if not PAN, then don't support P2P -- might be a uCode
@@ -2019,10 +2014,10 @@ void iwlagn_lift_passive_no_rx(struct iwl_priv *priv)
 
 	for (mq = 0; mq < IWLAGN_FIRST_AMPDU_QUEUE; mq++) {
 		if (!test_bit(mq, &priv->transport_queue_stop)) {
-			IWL_DEBUG_TX_QUEUES(priv, "Wake queue %d", mq);
+			IWL_DEBUG_TX_QUEUES(priv, "Wake queue %d\n", mq);
 			ieee80211_wake_queue(priv->hw, mq);
 		} else {
-			IWL_DEBUG_TX_QUEUES(priv, "Don't wake queue %d", mq);
+			IWL_DEBUG_TX_QUEUES(priv, "Don't wake queue %d\n", mq);
 		}
 	}
 
@@ -2053,6 +2048,17 @@ static bool iwl_set_hw_rfkill_state(struct iwl_op_mode *op_mode, bool state)
 	return false;
 }
 
+static void iwl_napi_add(struct iwl_op_mode *op_mode,
+			 struct napi_struct *napi,
+			 struct net_device *napi_dev,
+			 int (*poll)(struct napi_struct *, int),
+			 int weight)
+{
+	struct iwl_priv *priv = IWL_OP_MODE_GET_DVM(op_mode);
+
+	ieee80211_napi_add(priv->hw, napi, napi_dev, poll, weight);
+}
+
 static const struct iwl_op_mode_ops iwl_dvm_ops = {
 	.start = iwl_op_mode_dvm_start,
 	.stop = iwl_op_mode_dvm_stop,
@@ -2065,6 +2071,7 @@ static const struct iwl_op_mode_ops iwl_dvm_ops = {
 	.cmd_queue_full = iwl_cmd_queue_full,
 	.nic_config = iwl_nic_config,
 	.wimax_active = iwl_wimax_active,
+	.napi_add = iwl_napi_add,
 };
 
 /*****************************************************************************
diff --git a/drivers/net/wireless/iwlwifi/dvm/power.c b/drivers/net/wireless/iwlwifi/dvm/power.c
index b4e61417013..f2c1439566b 100644
--- a/drivers/net/wireless/iwlwifi/dvm/power.c
+++ b/drivers/net/wireless/iwlwifi/dvm/power.c
@@ -278,7 +278,7 @@ static int iwl_set_power(struct iwl_priv *priv, struct iwl_powertable_cmd *cmd)
 			le32_to_cpu(cmd->sleep_interval[3]),
 			le32_to_cpu(cmd->sleep_interval[4]));
 
-	return iwl_dvm_send_cmd_pdu(priv, POWER_TABLE_CMD, CMD_SYNC,
+	return iwl_dvm_send_cmd_pdu(priv, POWER_TABLE_CMD, 0,
 				sizeof(struct iwl_powertable_cmd), cmd);
 }
 
@@ -361,7 +361,7 @@ int iwl_power_set_mode(struct iwl_priv *priv, struct iwl_powertable_cmd *cmd,
 
 		memcpy(&priv->power_data.sleep_cmd, cmd, sizeof(*cmd));
 	} else
-		IWL_ERR(priv, "set power fail, ret = %d", ret);
+		IWL_ERR(priv, "set power fail, ret = %d\n", ret);
 
 	return ret;
 }
diff --git a/drivers/net/wireless/iwlwifi/dvm/rs.c b/drivers/net/wireless/iwlwifi/dvm/rs.c
index aa773a2da4a..32b78a66536 100644
--- a/drivers/net/wireless/iwlwifi/dvm/rs.c
+++ b/drivers/net/wireless/iwlwifi/dvm/rs.c
@@ -1453,7 +1453,7 @@ static int rs_move_legacy_other(struct iwl_priv *priv,
 			tbl->action = IWL_LEGACY_SWITCH_SISO;
 		break;
 	default:
-		IWL_ERR(priv, "Invalid BT load %d", priv->bt_traffic_load);
+		IWL_ERR(priv, "Invalid BT load %d\n", priv->bt_traffic_load);
 		break;
 	}
 
@@ -1628,7 +1628,7 @@ static int rs_move_siso_to_other(struct iwl_priv *priv,
 			tbl->action = IWL_SISO_SWITCH_ANTENNA1;
 		break;
 	default:
-		IWL_ERR(priv, "Invalid BT load %d", priv->bt_traffic_load);
+		IWL_ERR(priv, "Invalid BT load %d\n", priv->bt_traffic_load);
 		break;
 	}
 
@@ -1799,7 +1799,7 @@ static int rs_move_mimo2_to_other(struct iwl_priv *priv,
 			tbl->action = IWL_MIMO2_SWITCH_SISO_A;
 		break;
 	default:
-		IWL_ERR(priv, "Invalid BT load %d", priv->bt_traffic_load);
+		IWL_ERR(priv, "Invalid BT load %d\n", priv->bt_traffic_load);
 		break;
 	}
 
@@ -1969,7 +1969,7 @@ static int rs_move_mimo3_to_other(struct iwl_priv *priv,
 			tbl->action = IWL_MIMO3_SWITCH_SISO_A;
 		break;
 	default:
-		IWL_ERR(priv, "Invalid BT load %d", priv->bt_traffic_load);
+		IWL_ERR(priv, "Invalid BT load %d\n", priv->bt_traffic_load);
 		break;
 	}
 
@@ -2709,7 +2709,7 @@ static void rs_initialize_lq(struct iwl_priv *priv,
 	rs_set_expected_tpt_table(lq_sta, tbl);
 	rs_fill_link_cmd(NULL, lq_sta, rate);
 	priv->stations[lq_sta->lq.sta_id].lq = &lq_sta->lq;
-	iwl_send_lq_cmd(priv, ctx, &lq_sta->lq, CMD_SYNC, true);
+	iwl_send_lq_cmd(priv, ctx, &lq_sta->lq, 0, true);
 }
 
 static void rs_get_rate(void *priv_r, struct ieee80211_sta *sta, void *priv_sta,
diff --git a/drivers/net/wireless/iwlwifi/dvm/rx.c b/drivers/net/wireless/iwlwifi/dvm/rx.c
index cd8377346af..debec963c61 100644
--- a/drivers/net/wireless/iwlwifi/dvm/rx.c
+++ b/drivers/net/wireless/iwlwifi/dvm/rx.c
@@ -786,7 +786,7 @@ static void iwlagn_pass_packet_to_mac80211(struct iwl_priv *priv,
 
 	memcpy(IEEE80211_SKB_RXCB(skb), stats, sizeof(*stats));
 
-	ieee80211_rx_ni(priv->hw, skb);
+	ieee80211_rx(priv->hw, skb);
 }
 
 static u32 iwlagn_translate_rx_status(struct iwl_priv *priv, u32 decrypt_in)
diff --git a/drivers/net/wireless/iwlwifi/dvm/rxon.c b/drivers/net/wireless/iwlwifi/dvm/rxon.c
index 503a81e5818..6dc5dd3ced4 100644
--- a/drivers/net/wireless/iwlwifi/dvm/rxon.c
+++ b/drivers/net/wireless/iwlwifi/dvm/rxon.c
@@ -104,7 +104,7 @@ static int iwlagn_disable_bss(struct iwl_priv *priv,
 
 	send->filter_flags &= ~RXON_FILTER_ASSOC_MSK;
 	ret = iwl_dvm_send_cmd_pdu(priv, ctx->rxon_cmd,
-				CMD_SYNC, sizeof(*send), send);
+				0, sizeof(*send), send);
 
 	send->filter_flags = old_filter;
 
@@ -134,7 +134,7 @@ static int iwlagn_disable_pan(struct iwl_priv *priv,
 	send->filter_flags &= ~RXON_FILTER_ASSOC_MSK;
 	send->dev_type = RXON_DEV_TYPE_P2P;
 	ret = iwl_dvm_send_cmd_pdu(priv, ctx->rxon_cmd,
-				CMD_SYNC, sizeof(*send), send);
+				0, sizeof(*send), send);
 
 	send->filter_flags = old_filter;
 	send->dev_type = old_dev_type;
@@ -160,7 +160,7 @@ static int iwlagn_disconn_pan(struct iwl_priv *priv,
 	int ret;
 
 	send->filter_flags &= ~RXON_FILTER_ASSOC_MSK;
-	ret = iwl_dvm_send_cmd_pdu(priv, ctx->rxon_cmd, CMD_SYNC,
+	ret = iwl_dvm_send_cmd_pdu(priv, ctx->rxon_cmd, 0,
 				sizeof(*send), send);
 
 	send->filter_flags = old_filter;
@@ -189,7 +189,7 @@ static void iwlagn_update_qos(struct iwl_priv *priv,
 		      ctx->qos_data.qos_active,
 		      ctx->qos_data.def_qos_parm.qos_flags);
 
-	ret = iwl_dvm_send_cmd_pdu(priv, ctx->qos_cmd, CMD_SYNC,
+	ret = iwl_dvm_send_cmd_pdu(priv, ctx->qos_cmd, 0,
 			       sizeof(struct iwl_qosparam_cmd),
 			       &ctx->qos_data.def_qos_parm);
 	if (ret)
@@ -353,7 +353,7 @@ static int iwl_send_rxon_timing(struct iwl_priv *priv,
 			le16_to_cpu(ctx->timing.atim_window));
 
 	return iwl_dvm_send_cmd_pdu(priv, ctx->rxon_timing_cmd,
-				CMD_SYNC, sizeof(ctx->timing), &ctx->timing);
+				0, sizeof(ctx->timing), &ctx->timing);
 }
 
 static int iwlagn_rxon_disconn(struct iwl_priv *priv,
@@ -495,7 +495,7 @@ static int iwlagn_rxon_connect(struct iwl_priv *priv,
 	 * Associated RXON doesn't clear the station table in uCode,
 	 * so we don't need to restore stations etc. after this.
 	 */
-	ret = iwl_dvm_send_cmd_pdu(priv, ctx->rxon_cmd, CMD_SYNC,
+	ret = iwl_dvm_send_cmd_pdu(priv, ctx->rxon_cmd, 0,
 		      sizeof(struct iwl_rxon_cmd), &ctx->staging);
 	if (ret) {
 		IWL_ERR(priv, "Error setting new RXON (%d)\n", ret);
@@ -610,7 +610,7 @@ int iwlagn_set_pan_params(struct iwl_priv *priv)
 	cmd.slots[0].width = cpu_to_le16(slot0);
 	cmd.slots[1].width = cpu_to_le16(slot1);
 
-	ret = iwl_dvm_send_cmd_pdu(priv, REPLY_WIPAN_PARAMS, CMD_SYNC,
+	ret = iwl_dvm_send_cmd_pdu(priv, REPLY_WIPAN_PARAMS, 0,
 			sizeof(cmd), &cmd);
 	if (ret)
 		IWL_ERR(priv, "Error setting PAN parameters (%d)\n", ret);
@@ -823,7 +823,7 @@ static int iwl_check_rxon_cmd(struct iwl_priv *priv,
 
 	if ((rxon->flags & (RXON_FLG_CCK_MSK | RXON_FLG_AUTO_DETECT_MSK))
 			== (RXON_FLG_CCK_MSK | RXON_FLG_AUTO_DETECT_MSK)) {
-		IWL_WARN(priv, "CCK and auto detect");
+		IWL_WARN(priv, "CCK and auto detect\n");
 		errors |= BIT(8);
 	}
 
@@ -1068,13 +1068,6 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 	/* recalculate basic rates */
 	iwl_calc_basic_rates(priv, ctx);
 
-	/*
-	 * force CTS-to-self frames protection if RTS-CTS is not preferred
-	 * one aggregation protection method
-	 */
-	if (!priv->hw_params.use_rts_for_aggregation)
-		ctx->staging.flags |= RXON_FLG_SELF_CTS_EN;
-
 	if ((ctx->vif && ctx->vif->bss_conf.use_short_slot) ||
 	    !(ctx->staging.flags & RXON_FLG_BAND_24G_MSK))
 		ctx->staging.flags |= RXON_FLG_SHORT_SLOT_MSK;
@@ -1395,7 +1388,7 @@ static void iwlagn_chain_noise_reset(struct iwl_priv *priv)
 			priv->phy_calib_chain_noise_reset_cmd);
 		ret = iwl_dvm_send_cmd_pdu(priv,
 					REPLY_PHY_CALIBRATION_CMD,
-					CMD_SYNC, sizeof(cmd), &cmd);
+					0, sizeof(cmd), &cmd);
 		if (ret)
 			IWL_ERR(priv,
 				"Could not send REPLY_PHY_CALIBRATION_CMD\n");
@@ -1480,11 +1473,6 @@ void iwlagn_bss_info_changed(struct ieee80211_hw *hw,
 	else
 		ctx->staging.flags &= ~RXON_FLG_TGG_PROTECT_MSK;
 
-	if (bss_conf->use_cts_prot)
-		ctx->staging.flags |= RXON_FLG_SELF_CTS_EN;
-	else
-		ctx->staging.flags &= ~RXON_FLG_SELF_CTS_EN;
-
 	memcpy(ctx->staging.bssid_addr, bss_conf->bssid, ETH_ALEN);
 
 	if (vif->type == NL80211_IFTYPE_AP ||
diff --git a/drivers/net/wireless/iwlwifi/dvm/scan.c b/drivers/net/wireless/iwlwifi/dvm/scan.c
index be98b913ed5..43bef901e8f 100644
--- a/drivers/net/wireless/iwlwifi/dvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/dvm/scan.c
@@ -59,7 +59,7 @@ static int iwl_send_scan_abort(struct iwl_priv *priv)
 	int ret;
 	struct iwl_host_cmd cmd = {
 		.id = REPLY_SCAN_ABORT_CMD,
-		.flags = CMD_SYNC | CMD_WANT_SKB,
+		.flags = CMD_WANT_SKB,
 	};
 	__le32 *status;
 
@@ -639,7 +639,6 @@ static int iwlagn_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif)
 	struct iwl_host_cmd cmd = {
 		.id = REPLY_SCAN_CMD,
 		.len = { sizeof(struct iwl_scan_cmd), },
-		.flags = CMD_SYNC,
 	};
 	struct iwl_scan_cmd *scan;
 	struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS];
diff --git a/drivers/net/wireless/iwlwifi/dvm/sta.c b/drivers/net/wireless/iwlwifi/dvm/sta.c
index 9cdd91cdf66..6ec86adbe4a 100644
--- a/drivers/net/wireless/iwlwifi/dvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/dvm/sta.c
@@ -39,7 +39,7 @@ static int iwl_sta_ucode_activate(struct iwl_priv *priv, u8 sta_id)
 	lockdep_assert_held(&priv->sta_lock);
 
 	if (sta_id >= IWLAGN_STATION_COUNT) {
-		IWL_ERR(priv, "invalid sta_id %u", sta_id);
+		IWL_ERR(priv, "invalid sta_id %u\n", sta_id);
 		return -EINVAL;
 	}
 	if (!(priv->stations[sta_id].used & IWL_STA_DRIVER_ACTIVE))
@@ -165,7 +165,7 @@ int iwl_send_add_sta(struct iwl_priv *priv,
 	iwl_free_resp(&cmd);
 
 	if (cmd.handler_status)
-		IWL_ERR(priv, "%s - error in the CMD response %d", __func__,
+		IWL_ERR(priv, "%s - error in the CMD response %d\n", __func__,
 			cmd.handler_status);
 
 	return cmd.handler_status;
@@ -261,7 +261,7 @@ int iwl_sta_update_ht(struct iwl_priv *priv, struct iwl_rxon_context *ctx,
 	cmd.station_flags = flags;
 	cmd.sta.sta_id = sta_id;
 
-	return iwl_send_add_sta(priv, &cmd, CMD_SYNC);
+	return iwl_send_add_sta(priv, &cmd, 0);
 }
 
 static void iwl_set_ht_add_station(struct iwl_priv *priv, u8 index,
@@ -413,7 +413,7 @@ int iwl_add_station_common(struct iwl_priv *priv, struct iwl_rxon_context *ctx,
 	spin_unlock_bh(&priv->sta_lock);
 
 	/* Add station to device's station table */
-	ret = iwl_send_add_sta(priv, &sta_cmd, CMD_SYNC);
+	ret = iwl_send_add_sta(priv, &sta_cmd, 0);
 	if (ret) {
 		spin_lock_bh(&priv->sta_lock);
 		IWL_ERR(priv, "Adding station %pM failed.\n",
@@ -456,7 +456,6 @@ static int iwl_send_remove_station(struct iwl_priv *priv,
 	struct iwl_host_cmd cmd = {
 		.id = REPLY_REMOVE_STA,
 		.len = { sizeof(struct iwl_rem_sta_cmd), },
-		.flags = CMD_SYNC,
 		.data = { &rm_sta_cmd, },
 	};
 
@@ -740,7 +739,7 @@ void iwl_restore_stations(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 					send_lq = true;
 			}
 			spin_unlock_bh(&priv->sta_lock);
-			ret = iwl_send_add_sta(priv, &sta_cmd, CMD_SYNC);
+			ret = iwl_send_add_sta(priv, &sta_cmd, 0);
 			if (ret) {
 				spin_lock_bh(&priv->sta_lock);
 				IWL_ERR(priv, "Adding station %pM failed.\n",
@@ -756,8 +755,7 @@ void iwl_restore_stations(struct iwl_priv *priv, struct iwl_rxon_context *ctx)
 			 * current LQ command
 			 */
 			if (send_lq)
-				iwl_send_lq_cmd(priv, ctx, &lq,
-						CMD_SYNC, true);
+				iwl_send_lq_cmd(priv, ctx, &lq, 0, true);
 			spin_lock_bh(&priv->sta_lock);
 			priv->stations[i].used &= ~IWL_STA_UCODE_INPROGRESS;
 		}
@@ -968,7 +966,7 @@ int iwlagn_add_bssid_station(struct iwl_priv *priv,
 		return -ENOMEM;
 	}
 
-	ret = iwl_send_lq_cmd(priv, ctx, link_cmd, CMD_SYNC, true);
+	ret = iwl_send_lq_cmd(priv, ctx, link_cmd, 0, true);
 	if (ret)
 		IWL_ERR(priv, "Link quality command failed (%d)\n", ret);
 
@@ -999,7 +997,6 @@ static int iwl_send_static_wepkey_cmd(struct iwl_priv *priv,
 	struct iwl_host_cmd cmd = {
 		.id = ctx->wep_key_cmd,
 		.data = { wep_cmd, },
-		.flags = CMD_SYNC,
 	};
 
 	might_sleep();
@@ -1248,7 +1245,7 @@ int iwl_remove_dynamic_key(struct iwl_priv *priv,
 	sta_cmd.sta.modify_mask = STA_MODIFY_KEY_MASK;
 	sta_cmd.mode = STA_CONTROL_MODIFY_MSK;
 
-	return iwl_send_add_sta(priv, &sta_cmd, CMD_SYNC);
+	return iwl_send_add_sta(priv, &sta_cmd, 0);
 }
 
 int iwl_set_dynamic_key(struct iwl_priv *priv,
@@ -1284,13 +1281,13 @@ int iwl_set_dynamic_key(struct iwl_priv *priv,
 		ieee80211_get_key_rx_seq(keyconf, 0, &seq);
 		ieee80211_get_tkip_rx_p1k(keyconf, addr, seq.tkip.iv32, p1k);
 		ret = iwlagn_send_sta_key(priv, keyconf, sta_id,
-					  seq.tkip.iv32, p1k, CMD_SYNC);
+					  seq.tkip.iv32, p1k, 0);
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_WEP40:
 	case WLAN_CIPHER_SUITE_WEP104:
 		ret = iwlagn_send_sta_key(priv, keyconf, sta_id,
-					  0, NULL, CMD_SYNC);
+					  0, NULL, 0);
 		break;
 	default:
 		IWL_ERR(priv, "Unknown cipher %x\n", keyconf->cipher);
@@ -1409,7 +1406,7 @@ int iwl_sta_tx_modify_enable_tid(struct iwl_priv *priv, int sta_id, int tid)
 	memcpy(&sta_cmd, &priv->stations[sta_id].sta, sizeof(struct iwl_addsta_cmd));
 	spin_unlock_bh(&priv->sta_lock);
 
-	return iwl_send_add_sta(priv, &sta_cmd, CMD_SYNC);
+	return iwl_send_add_sta(priv, &sta_cmd, 0);
 }
 
 int iwl_sta_rx_agg_start(struct iwl_priv *priv, struct ieee80211_sta *sta,
@@ -1433,7 +1430,7 @@ int iwl_sta_rx_agg_start(struct iwl_priv *priv, struct ieee80211_sta *sta,
 	memcpy(&sta_cmd, &priv->stations[sta_id].sta, sizeof(struct iwl_addsta_cmd));
 	spin_unlock_bh(&priv->sta_lock);
 
-	return iwl_send_add_sta(priv, &sta_cmd, CMD_SYNC);
+	return iwl_send_add_sta(priv, &sta_cmd, 0);
 }
 
 int iwl_sta_rx_agg_stop(struct iwl_priv *priv, struct ieee80211_sta *sta,
@@ -1458,7 +1455,7 @@ int iwl_sta_rx_agg_stop(struct iwl_priv *priv, struct ieee80211_sta *sta,
 	memcpy(&sta_cmd, &priv->stations[sta_id].sta, sizeof(struct iwl_addsta_cmd));
 	spin_unlock_bh(&priv->sta_lock);
 
-	return iwl_send_add_sta(priv, &sta_cmd, CMD_SYNC);
+	return iwl_send_add_sta(priv, &sta_cmd, 0);
 }
 
 
diff --git a/drivers/net/wireless/iwlwifi/dvm/tt.c b/drivers/net/wireless/iwlwifi/dvm/tt.c
index 058c5892c42..acb981a0a0a 100644
--- a/drivers/net/wireless/iwlwifi/dvm/tt.c
+++ b/drivers/net/wireless/iwlwifi/dvm/tt.c
@@ -236,7 +236,7 @@ static void iwl_prepare_ct_kill_task(struct iwl_priv *priv)
 {
 	IWL_DEBUG_TEMP(priv, "Prepare to enter IWL_TI_CT_KILL\n");
 	/* make request to retrieve statistics information */
-	iwl_send_statistics_request(priv, CMD_SYNC, false);
+	iwl_send_statistics_request(priv, 0, false);
 	/* Reschedule the ct_kill wait timer */
 	mod_timer(&priv->thermal_throttle.ct_kill_waiting_tm,
 		 jiffies + msecs_to_jiffies(CT_KILL_WAITING_DURATION));
diff --git a/drivers/net/wireless/iwlwifi/dvm/tx.c b/drivers/net/wireless/iwlwifi/dvm/tx.c
index 398dd096674..3255a1723d1 100644
--- a/drivers/net/wireless/iwlwifi/dvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/dvm/tx.c
@@ -402,10 +402,10 @@ int iwlagn_tx_skb(struct iwl_priv *priv,
 		/* aggregation is on for this <sta,tid> */
 		if (info->flags & IEEE80211_TX_CTL_AMPDU &&
 		    tid_data->agg.state != IWL_AGG_ON) {
-			IWL_ERR(priv, "TX_CTL_AMPDU while not in AGG:"
-				" Tx flags = 0x%08x, agg.state = %d",
+			IWL_ERR(priv,
+				"TX_CTL_AMPDU while not in AGG: Tx flags = 0x%08x, agg.state = %d\n",
 				info->flags, tid_data->agg.state);
-			IWL_ERR(priv, "sta_id = %d, tid = %d seq_num = %d",
+			IWL_ERR(priv, "sta_id = %d, tid = %d seq_num = %d\n",
 				sta_id, tid,
 				IEEE80211_SEQ_TO_SN(tid_data->seq_number));
 			goto drop_unlock_sta;
@@ -416,7 +416,7 @@ int iwlagn_tx_skb(struct iwl_priv *priv,
 		 */
 		if (WARN_ONCE(tid_data->agg.state != IWL_AGG_ON &&
 			      tid_data->agg.state != IWL_AGG_OFF,
-		    "Tx while agg.state = %d", tid_data->agg.state))
+			      "Tx while agg.state = %d\n", tid_data->agg.state))
 			goto drop_unlock_sta;
 
 		seq_number = tid_data->seq_number;
@@ -778,8 +778,8 @@ static void iwlagn_check_ratid_empty(struct iwl_priv *priv, int sta_id, u8 tid)
 		/* There are no packets for this RA / TID in the HW any more */
 		if (tid_data->agg.ssn == tid_data->next_reclaimed) {
 			IWL_DEBUG_TX_QUEUES(priv,
-				"Can continue DELBA flow ssn = next_recl ="
-				" %d", tid_data->next_reclaimed);
+				"Can continue DELBA flow ssn = next_recl = %d\n",
+				tid_data->next_reclaimed);
 			iwl_trans_txq_disable(priv->trans,
 					      tid_data->agg.txq_id);
 			iwlagn_dealloc_agg_txq(priv, tid_data->agg.txq_id);
@@ -791,8 +791,8 @@ static void iwlagn_check_ratid_empty(struct iwl_priv *priv, int sta_id, u8 tid)
 		/* There are no packets for this RA / TID in the HW any more */
 		if (tid_data->agg.ssn == tid_data->next_reclaimed) {
 			IWL_DEBUG_TX_QUEUES(priv,
-				"Can continue ADDBA flow ssn = next_recl ="
-				" %d", tid_data->next_reclaimed);
+				"Can continue ADDBA flow ssn = next_recl = %d\n",
+				tid_data->next_reclaimed);
 			tid_data->agg.state = IWL_AGG_STARTING;
 			ieee80211_start_tx_ba_cb_irqsafe(vif, addr, tid);
 		}
@@ -1216,8 +1216,8 @@ int iwlagn_rx_reply_tx(struct iwl_priv *priv, struct iwl_rx_cmd_buffer *rxb,
 			    ctx->vif->type == NL80211_IFTYPE_STATION) {
 				/* block and stop all queues */
 				priv->passive_no_rx = true;
-				IWL_DEBUG_TX_QUEUES(priv, "stop all queues: "
-						    "passive channel");
+				IWL_DEBUG_TX_QUEUES(priv,
+					"stop all queues: passive channel\n");
 				ieee80211_stop_queues(priv->hw);
 
 				IWL_DEBUG_TX_REPLY(priv,
@@ -1271,7 +1271,7 @@ int iwlagn_rx_reply_tx(struct iwl_priv *priv, struct iwl_rx_cmd_buffer *rxb,
 
 	while (!skb_queue_empty(&skbs)) {
 		skb = __skb_dequeue(&skbs);
-		ieee80211_tx_status_ni(priv->hw, skb);
+		ieee80211_tx_status(priv->hw, skb);
 	}
 
 	return 0;
@@ -1411,7 +1411,7 @@ int iwlagn_rx_reply_compressed_ba(struct iwl_priv *priv,
 
 	while (!skb_queue_empty(&reclaimed_skbs)) {
 		skb = __skb_dequeue(&reclaimed_skbs);
-		ieee80211_tx_status_ni(priv->hw, skb);
+		ieee80211_tx_status(priv->hw, skb);
 	}
 
 	return 0;
diff --git a/drivers/net/wireless/iwlwifi/dvm/ucode.c b/drivers/net/wireless/iwlwifi/dvm/ucode.c
index cf03ef5619d..d5cee153059 100644
--- a/drivers/net/wireless/iwlwifi/dvm/ucode.c
+++ b/drivers/net/wireless/iwlwifi/dvm/ucode.c
@@ -172,7 +172,7 @@ static int iwl_send_wimax_coex(struct iwl_priv *priv)
 	memset(&coex_cmd, 0, sizeof(coex_cmd));
 
 	return iwl_dvm_send_cmd_pdu(priv,
-				COEX_PRIORITY_TABLE_CMD, CMD_SYNC,
+				COEX_PRIORITY_TABLE_CMD, 0,
 				sizeof(coex_cmd), &coex_cmd);
 }
 
@@ -205,7 +205,7 @@ void iwl_send_prio_tbl(struct iwl_priv *priv)
 	memcpy(prio_tbl_cmd.prio_tbl, iwl_bt_prio_tbl,
 		sizeof(iwl_bt_prio_tbl));
 	if (iwl_dvm_send_cmd_pdu(priv,
-				REPLY_BT_COEX_PRIO_TABLE, CMD_SYNC,
+				REPLY_BT_COEX_PRIO_TABLE, 0,
 				sizeof(prio_tbl_cmd), &prio_tbl_cmd))
 		IWL_ERR(priv, "failed to send BT prio tbl command\n");
 }
@@ -218,7 +218,7 @@ int iwl_send_bt_env(struct iwl_priv *priv, u8 action, u8 type)
 	env_cmd.action = action;
 	env_cmd.type = type;
 	ret = iwl_dvm_send_cmd_pdu(priv,
-			       REPLY_BT_COEX_PROT_ENV, CMD_SYNC,
+			       REPLY_BT_COEX_PROT_ENV, 0,
 			       sizeof(env_cmd), &env_cmd);
 	if (ret)
 		IWL_ERR(priv, "failed to send BT env command\n");
diff --git a/drivers/net/wireless/iwlwifi/iwl-1000.c b/drivers/net/wireless/iwlwifi/iwl-1000.c
index 854ba84ccb7..c3817fae16c 100644
--- a/drivers/net/wireless/iwlwifi/iwl-1000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-1000.c
@@ -62,6 +62,7 @@ static const struct iwl_base_params iwl1000_base_params = {
 	.led_compensation = 51,
 	.wd_timeout = IWL_WATCHDOG_DISABLED,
 	.max_event_log_size = 128,
+	.scd_chain_ext_wa = true,
 };
 
 static const struct iwl_ht_params iwl1000_ht_params = {
diff --git a/drivers/net/wireless/iwlwifi/iwl-2000.c b/drivers/net/wireless/iwlwifi/iwl-2000.c
index 3e63323637f..21e5d0843a6 100644
--- a/drivers/net/wireless/iwlwifi/iwl-2000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-2000.c
@@ -75,6 +75,7 @@ static const struct iwl_base_params iwl2000_base_params = {
 	.wd_timeout = IWL_DEF_WD_TIMEOUT,
 	.max_event_log_size = 512,
 	.shadow_reg_enable = false, /* TODO: fix bugs using this feature */
+	.scd_chain_ext_wa = true,
 };
 
 
@@ -88,6 +89,7 @@ static const struct iwl_base_params iwl2030_base_params = {
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
 	.max_event_log_size = 512,
 	.shadow_reg_enable = false, /* TODO: fix bugs using this feature */
+	.scd_chain_ext_wa = true,
 };
 
 static const struct iwl_ht_params iwl2000_ht_params = {
diff --git a/drivers/net/wireless/iwlwifi/iwl-5000.c b/drivers/net/wireless/iwlwifi/iwl-5000.c
index 6674f2c4541..332bbede39e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-5000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-5000.c
@@ -61,6 +61,7 @@ static const struct iwl_base_params iwl5000_base_params = {
 	.led_compensation = 51,
 	.wd_timeout = IWL_WATCHDOG_DISABLED,
 	.max_event_log_size = 512,
+	.scd_chain_ext_wa = true,
 };
 
 static const struct iwl_ht_params iwl5000_ht_params = {
diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c
index 8048de90233..8f2c3c8c6b8 100644
--- a/drivers/net/wireless/iwlwifi/iwl-6000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-6000.c
@@ -85,6 +85,7 @@ static const struct iwl_base_params iwl6000_base_params = {
 	.wd_timeout = IWL_DEF_WD_TIMEOUT,
 	.max_event_log_size = 512,
 	.shadow_reg_enable = false, /* TODO: fix bugs using this feature */
+	.scd_chain_ext_wa = true,
 };
 
 static const struct iwl_base_params iwl6050_base_params = {
@@ -97,6 +98,7 @@ static const struct iwl_base_params iwl6050_base_params = {
 	.wd_timeout = IWL_DEF_WD_TIMEOUT,
 	.max_event_log_size = 1024,
 	.shadow_reg_enable = false, /* TODO: fix bugs using this feature */
+	.scd_chain_ext_wa = true,
 };
 
 static const struct iwl_base_params iwl6000_g2_base_params = {
@@ -109,6 +111,7 @@ static const struct iwl_base_params iwl6000_g2_base_params = {
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
 	.max_event_log_size = 512,
 	.shadow_reg_enable = false, /* TODO: fix bugs using this feature */
+	.scd_chain_ext_wa = true,
 };
 
 static const struct iwl_ht_params iwl6000_ht_params = {
diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c
index 4c2d4ef28b2..48730064da7 100644
--- a/drivers/net/wireless/iwlwifi/iwl-7000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-7000.c
@@ -71,12 +71,12 @@
 #define IWL3160_UCODE_API_MAX	9
 
 /* Oldest version we won't warn about */
-#define IWL7260_UCODE_API_OK	8
-#define IWL3160_UCODE_API_OK	8
+#define IWL7260_UCODE_API_OK	9
+#define IWL3160_UCODE_API_OK	9
 
 /* Lowest firmware API version supported */
-#define IWL7260_UCODE_API_MIN	7
-#define IWL3160_UCODE_API_MIN	7
+#define IWL7260_UCODE_API_MIN	8
+#define IWL3160_UCODE_API_MIN	8
 
 /* NVM versions */
 #define IWL7260_NVM_VERSION		0x0a1d
@@ -98,7 +98,7 @@
 #define NVM_HW_SECTION_NUM_FAMILY_7000		0
 
 static const struct iwl_base_params iwl7000_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_7000,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.pll_cfg_val = 0,
 	.shadow_ram_support = true,
@@ -107,6 +107,7 @@ static const struct iwl_base_params iwl7000_base_params = {
 	.max_event_log_size = 512,
 	.shadow_reg_enable = true,
 	.pcie_l1_allowed = true,
+	.apmg_wake_up_wa = true,
 };
 
 static const struct iwl_ht_params iwl7000_ht_params = {
diff --git a/drivers/net/wireless/iwlwifi/iwl-8000.c b/drivers/net/wireless/iwlwifi/iwl-8000.c
index f5bd82b8859..51c41531d81 100644
--- a/drivers/net/wireless/iwlwifi/iwl-8000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-8000.c
@@ -83,9 +83,10 @@
 #define IWL8000_MODULE_FIRMWARE(api) IWL8000_FW_PRE __stringify(api) ".ucode"
 
 #define NVM_HW_SECTION_NUM_FAMILY_8000		10
+#define DEFAULT_NVM_FILE_FAMILY_8000		"iwl_nvm_8000.bin"
 
 static const struct iwl_base_params iwl8000_base_params = {
-	.eeprom_size = OTP_LOW_IMAGE_SIZE,
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_8000,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
 	.pll_cfg_val = 0,
 	.shadow_ram_support = true,
@@ -118,6 +119,7 @@ const struct iwl_cfg iwl8260_2ac_cfg = {
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
+	.default_nvm_file = DEFAULT_NVM_FILE_FAMILY_8000,
 };
 
 const struct iwl_cfg iwl8260_n_cfg = {
@@ -127,6 +129,7 @@ const struct iwl_cfg iwl8260_n_cfg = {
 	.ht_params = &iwl8000_ht_params,
 	.nvm_ver = IWL8000_NVM_VERSION,
 	.nvm_calib_ver = IWL8000_TX_POWER_VERSION,
+	.default_nvm_file = DEFAULT_NVM_FILE_FAMILY_8000,
 };
 
 MODULE_FIRMWARE(IWL8000_MODULE_FIRMWARE(IWL8000_UCODE_API_OK));
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-hw.h b/drivers/net/wireless/iwlwifi/iwl-agn-hw.h
index 7f37fb86837..04a483d3865 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-hw.h
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-hw.h
@@ -102,9 +102,7 @@
 
 /* EEPROM */
 #define IWLAGN_EEPROM_IMG_SIZE		2048
-/* OTP */
-/* lower blocks contain EEPROM image and calibration data */
-#define OTP_LOW_IMAGE_SIZE		(2 * 512 * sizeof(u16)) /* 2 KB */
+
 /* high blocks contain PAPD data */
 #define OTP_HIGH_IMAGE_SIZE_6x00        (6 * 512 * sizeof(u16)) /* 6 KB */
 #define OTP_HIGH_IMAGE_SIZE_1000        (0x200 * sizeof(u16)) /* 1024 bytes */
diff --git a/drivers/net/wireless/iwlwifi/iwl-config.h b/drivers/net/wireless/iwlwifi/iwl-config.h
index 3f17dc3f2c8..b7047905f41 100644
--- a/drivers/net/wireless/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/iwlwifi/iwl-config.h
@@ -146,6 +146,9 @@ static inline u8 num_of_ant(u8 mask)
  * @wd_timeout: TX queues watchdog timeout
  * @max_event_log_size: size of event log buffer size for ucode event logging
  * @shadow_reg_enable: HW shadow register support
+ * @apmg_wake_up_wa: should the MAC access REQ be asserted when a command
+ *	is in flight. This is due to a HW bug in 7260, 3160 and 7265.
+ * @scd_chain_ext_wa: should the chain extension feature in SCD be disabled.
  */
 struct iwl_base_params {
 	int eeprom_size;
@@ -160,6 +163,8 @@ struct iwl_base_params {
 	u32 max_event_log_size;
 	const bool shadow_reg_enable;
 	const bool pcie_l1_allowed;
+	const bool apmg_wake_up_wa;
+	const bool scd_chain_ext_wa;
 };
 
 /*
@@ -188,6 +193,11 @@ struct iwl_ht_params {
 #define EEPROM_6000_REG_BAND_24_HT40_CHANNELS	0x80
 #define EEPROM_REGULATORY_BAND_NO_HT40		0
 
+/* lower blocks contain EEPROM image and calibration data */
+#define OTP_LOW_IMAGE_SIZE		(2 * 512 * sizeof(u16)) /* 2 KB */
+#define OTP_LOW_IMAGE_SIZE_FAMILY_7000	(16 * 512 * sizeof(u16)) /* 16 KB */
+#define OTP_LOW_IMAGE_SIZE_FAMILY_8000	(32 * 512 * sizeof(u16)) /* 32 KB */
+
 struct iwl_eeprom_params {
 	const u8 regulatory_bands[7];
 	bool enhanced_txpower;
@@ -264,6 +274,8 @@ struct iwl_cfg {
 	u8   nvm_hw_section_num;
 	bool lp_xtal_workaround;
 	const struct iwl_pwr_tx_backoff *pwr_tx_backoffs;
+	bool no_power_up_nic_in_init;
+	const char *default_nvm_file;
 };
 
 /*
diff --git a/drivers/net/wireless/iwlwifi/iwl-debug.c b/drivers/net/wireless/iwlwifi/iwl-debug.c
index 8a44f594528..09feff4fa22 100644
--- a/drivers/net/wireless/iwlwifi/iwl-debug.c
+++ b/drivers/net/wireless/iwlwifi/iwl-debug.c
@@ -61,8 +61,6 @@
  *
  *****************************************************************************/
 
-#define DEBUG
-
 #include <linux/device.h>
 #include <linux/interrupt.h>
 #include <linux/export.h>
@@ -128,8 +126,8 @@ void __iwl_dbg(struct device *dev,
 #ifdef CONFIG_IWLWIFI_DEBUG
 	if (iwl_have_debug_level(level) &&
 	    (!limit || net_ratelimit()))
-		dev_dbg(dev, "%c %s %pV", in_interrupt() ? 'I' : 'U',
-			function, &vaf);
+		dev_printk(KERN_DEBUG, dev, "%c %s %pV",
+			   in_interrupt() ? 'I' : 'U', function, &vaf);
 #endif
 	trace_iwlwifi_dbg(level, in_interrupt(), function, &vaf);
 	va_end(args);
diff --git a/drivers/net/wireless/iwlwifi/iwl-debug.h b/drivers/net/wireless/iwlwifi/iwl-debug.h
index c8cbdbe1592..295083510e7 100644
--- a/drivers/net/wireless/iwlwifi/iwl-debug.h
+++ b/drivers/net/wireless/iwlwifi/iwl-debug.h
@@ -47,12 +47,32 @@ void __iwl_warn(struct device *dev, const char *fmt, ...) __printf(2, 3);
 void __iwl_info(struct device *dev, const char *fmt, ...) __printf(2, 3);
 void __iwl_crit(struct device *dev, const char *fmt, ...) __printf(2, 3);
 
+/* not all compilers can evaluate strlen() at compile time, so use sizeof() */
+#define CHECK_FOR_NEWLINE(f) BUILD_BUG_ON(f[sizeof(f) - 2] != '\n')
+
 /* No matter what is m (priv, bus, trans), this will work */
-#define IWL_ERR(m, f, a...) __iwl_err((m)->dev, false, false, f, ## a)
-#define IWL_ERR_DEV(d, f, a...) __iwl_err((d), false, false, f, ## a)
-#define IWL_WARN(m, f, a...) __iwl_warn((m)->dev, f, ## a)
-#define IWL_INFO(m, f, a...) __iwl_info((m)->dev, f, ## a)
-#define IWL_CRIT(m, f, a...) __iwl_crit((m)->dev, f, ## a)
+#define IWL_ERR_DEV(d, f, a...)						\
+	do {								\
+		CHECK_FOR_NEWLINE(f);					\
+		__iwl_err((d), false, false, f, ## a);			\
+	} while (0)
+#define IWL_ERR(m, f, a...)						\
+	IWL_ERR_DEV((m)->dev, f, ## a)
+#define IWL_WARN(m, f, a...)						\
+	do {								\
+		CHECK_FOR_NEWLINE(f);					\
+		__iwl_warn((m)->dev, f, ## a);				\
+	} while (0)
+#define IWL_INFO(m, f, a...)						\
+	do {								\
+		CHECK_FOR_NEWLINE(f);					\
+		__iwl_info((m)->dev, f, ## a);				\
+	} while (0)
+#define IWL_CRIT(m, f, a...)						\
+	do {								\
+		CHECK_FOR_NEWLINE(f);					\
+		__iwl_crit((m)->dev, f, ## a);				\
+	} while (0)
 
 #if defined(CONFIG_IWLWIFI_DEBUG) || defined(CONFIG_IWLWIFI_DEVICE_TRACING)
 void __iwl_dbg(struct device *dev,
@@ -72,12 +92,17 @@ do {									\
 		       DUMP_PREFIX_OFFSET, 16, 1, p, len, 1);		\
 } while (0)
 
+#define __IWL_DEBUG_DEV(dev, level, limit, fmt, args...)		\
+	do {								\
+		CHECK_FOR_NEWLINE(fmt);					\
+		__iwl_dbg(dev, level, limit, __func__, fmt, ##args);	\
+	} while (0)
 #define IWL_DEBUG(m, level, fmt, args...)				\
-	__iwl_dbg((m)->dev, level, false, __func__, fmt, ##args)
+	__IWL_DEBUG_DEV((m)->dev, level, false, fmt, ##args)
 #define IWL_DEBUG_DEV(dev, level, fmt, args...)				\
-	__iwl_dbg((dev), level, false, __func__, fmt, ##args)
+	__IWL_DEBUG_DEV(dev, level, false, fmt, ##args)
 #define IWL_DEBUG_LIMIT(m, level, fmt, args...)				\
-	__iwl_dbg((m)->dev, level, true, __func__, fmt, ##args)
+	__IWL_DEBUG_DEV((m)->dev, level, true, fmt, ##args)
 
 #ifdef CONFIG_IWLWIFI_DEBUG
 #define iwl_print_hex_dump(m, level, p, len)				\
diff --git a/drivers/net/wireless/iwlwifi/iwl-drv.c b/drivers/net/wireless/iwlwifi/iwl-drv.c
index 0a3e841b44a..f2a5c12269a 100644
--- a/drivers/net/wireless/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/iwlwifi/iwl-drv.c
@@ -1243,6 +1243,7 @@ struct iwl_mod_params iwlwifi_mod_params = {
 	.bt_coex_active = true,
 	.power_level = IWL_POWER_INDEX_1,
 	.wd_disable = true,
+	.uapsd_disable = false,
 	/* the rest are 0 by default */
 };
 IWL_EXPORT_SYMBOL(iwlwifi_mod_params);
@@ -1356,6 +1357,10 @@ MODULE_PARM_DESC(wd_disable,
 module_param_named(nvm_file, iwlwifi_mod_params.nvm_file, charp, S_IRUGO);
 MODULE_PARM_DESC(nvm_file, "NVM file name");
 
+module_param_named(uapsd_disable, iwlwifi_mod_params.uapsd_disable,
+		   bool, S_IRUGO);
+MODULE_PARM_DESC(uapsd_disable, "disable U-APSD functionality (default: N)");
+
 /*
  * set bt_coex_active to true, uCode will do kill/defer
  * every time the priority line is asserted (BT is sending signals on the
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-error-dump.h b/drivers/net/wireless/iwlwifi/iwl-fw-error-dump.h
index 58c8941c0d9..2953ffceda3 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-error-dump.h
+++ b/drivers/net/wireless/iwlwifi/iwl-fw-error-dump.h
@@ -71,10 +71,15 @@
  * enum iwl_fw_error_dump_type - types of data in the dump file
  * @IWL_FW_ERROR_DUMP_SRAM:
  * @IWL_FW_ERROR_DUMP_REG:
+ * @IWL_FW_ERROR_DUMP_RXF:
+ * @IWL_FW_ERROR_DUMP_TXCMD: last TX command data, structured as
+ *	&struct iwl_fw_error_dump_txcmd packets
  */
 enum iwl_fw_error_dump_type {
 	IWL_FW_ERROR_DUMP_SRAM = 0,
 	IWL_FW_ERROR_DUMP_REG = 1,
+	IWL_FW_ERROR_DUMP_RXF = 2,
+	IWL_FW_ERROR_DUMP_TXCMD = 3,
 
 	IWL_FW_ERROR_DUMP_MAX,
 };
@@ -89,7 +94,7 @@ struct iwl_fw_error_dump_data {
 	__le32 type;
 	__le32 len;
 	__u8 data[];
-} __packed __aligned(4);
+} __packed;
 
 /**
  * struct iwl_fw_error_dump_file - the layout of the header of the file
@@ -101,6 +106,29 @@ struct iwl_fw_error_dump_file {
 	__le32 barker;
 	__le32 file_len;
 	u8 data[0];
-} __packed __aligned(4);
+} __packed;
+
+/**
+ * struct iwl_fw_error_dump_txcmd - TX command data
+ * @cmdlen: original length of command
+ * @caplen: captured length of command (may be less)
+ * @data: captured command data, @caplen bytes
+ */
+struct iwl_fw_error_dump_txcmd {
+	__le32 cmdlen;
+	__le32 caplen;
+	u8 data[];
+} __packed;
+
+/**
+ * iwl_mvm_fw_error_next_data - advance fw error dump data pointer
+ * @data: previous data block
+ * Returns: next data block
+ */
+static inline struct iwl_fw_error_dump_data *
+iwl_mvm_fw_error_next_data(struct iwl_fw_error_dump_data *data)
+{
+	return (void *)(data->data + le32_to_cpu(data->len));
+}
 
 #endif /* __fw_error_dump_h__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-fw.h b/drivers/net/wireless/iwlwifi/iwl-fw.h
index d14f19339d6..b1a33322b9b 100644
--- a/drivers/net/wireless/iwlwifi/iwl-fw.h
+++ b/drivers/net/wireless/iwlwifi/iwl-fw.h
@@ -74,29 +74,25 @@
  * @IWL_UCODE_TLV_FLAGS_MFP: This uCode image supports MFP (802.11w).
  * @IWL_UCODE_TLV_FLAGS_P2P: This uCode image supports P2P.
  * @IWL_UCODE_TLV_FLAGS_DW_BC_TABLE: The SCD byte count table is in DWORDS
- * @IWL_UCODE_TLV_FLAGS_UAPSD: This uCode image supports uAPSD
+ * @IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT: This uCode image supports uAPSD
  * @IWL_UCODE_TLV_FLAGS_SHORT_BL: 16 entries of black list instead of 64 in scan
  *	offload profile config command.
- * @IWL_UCODE_TLV_FLAGS_RX_ENERGY_API: supports rx signal strength api
- * @IWL_UCODE_TLV_FLAGS_TIME_EVENT_API_V2: using the new time event API.
  * @IWL_UCODE_TLV_FLAGS_D3_6_IPV6_ADDRS: D3 image supports up to six
  *	(rather than two) IPv6 addresses
- * @IWL_UCODE_TLV_FLAGS_BF_UPDATED: new beacon filtering API
  * @IWL_UCODE_TLV_FLAGS_NO_BASIC_SSID: not sending a probe with the SSID element
  *	from the probe request template.
- * @IWL_UCODE_TLV_FLAGS_D3_CONTINUITY_API: modified D3 API to allow keeping
- *	connection when going back to D0
  * @IWL_UCODE_TLV_FLAGS_NEW_NSOFFL_SMALL: new NS offload (small version)
  * @IWL_UCODE_TLV_FLAGS_NEW_NSOFFL_LARGE: new NS offload (large version)
- * @IWL_UCODE_TLV_FLAGS_SCHED_SCAN: this uCode image supports scheduled scan.
- * @IWL_UCODE_TLV_FLAGS_STA_KEY_CMD: new ADD_STA and ADD_STA_KEY command API
- * @IWL_UCODE_TLV_FLAGS_DEVICE_PS_CMD: support device wide power command
- *	containing CAM (Continuous Active Mode) indication.
+ * @IWL_UCODE_TLV_FLAGS_P2P_PM: P2P client supports PM as a stand alone MAC
  * @IWL_UCODE_TLV_FLAGS_P2P_BSS_PS_DCM: support power save on BSS station and
  *	P2P client interfaces simultaneously if they are in different bindings.
+ * @IWL_UCODE_TLV_FLAGS_P2P_BSS_PS_SCM: support power save on BSS station and
+ *	P2P client interfaces simultaneously if they are in same bindings.
+ * @IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT: General support for uAPSD
  * @IWL_UCODE_TLV_FLAGS_P2P_PS_UAPSD: P2P client supports uAPSD power save
  * @IWL_UCODE_TLV_FLAGS_BCAST_FILTERING: uCode supports broadcast filtering.
  * @IWL_UCODE_TLV_FLAGS_GO_UAPSD: AP/GO interfaces support uAPSD clients
+ * @IWL_UCODE_TLV_FLAGS_EBS_SUPPORT: this uCode image supports EBS.
  */
 enum iwl_ucode_tlv_flag {
 	IWL_UCODE_TLV_FLAGS_PAN			= BIT(0),
@@ -104,22 +100,16 @@ enum iwl_ucode_tlv_flag {
 	IWL_UCODE_TLV_FLAGS_MFP			= BIT(2),
 	IWL_UCODE_TLV_FLAGS_P2P			= BIT(3),
 	IWL_UCODE_TLV_FLAGS_DW_BC_TABLE		= BIT(4),
-	IWL_UCODE_TLV_FLAGS_NEWBT_COEX		= BIT(5),
-	IWL_UCODE_TLV_FLAGS_PM_CMD_SUPPORT	= BIT(6),
 	IWL_UCODE_TLV_FLAGS_SHORT_BL		= BIT(7),
-	IWL_UCODE_TLV_FLAGS_RX_ENERGY_API	= BIT(8),
-	IWL_UCODE_TLV_FLAGS_TIME_EVENT_API_V2	= BIT(9),
 	IWL_UCODE_TLV_FLAGS_D3_6_IPV6_ADDRS	= BIT(10),
-	IWL_UCODE_TLV_FLAGS_BF_UPDATED		= BIT(11),
 	IWL_UCODE_TLV_FLAGS_NO_BASIC_SSID	= BIT(12),
-	IWL_UCODE_TLV_FLAGS_D3_CONTINUITY_API	= BIT(14),
 	IWL_UCODE_TLV_FLAGS_NEW_NSOFFL_SMALL	= BIT(15),
 	IWL_UCODE_TLV_FLAGS_NEW_NSOFFL_LARGE	= BIT(16),
-	IWL_UCODE_TLV_FLAGS_SCHED_SCAN		= BIT(17),
-	IWL_UCODE_TLV_FLAGS_STA_KEY_CMD		= BIT(19),
-	IWL_UCODE_TLV_FLAGS_DEVICE_PS_CMD	= BIT(20),
+	IWL_UCODE_TLV_FLAGS_P2P_PM		= BIT(21),
 	IWL_UCODE_TLV_FLAGS_BSS_P2P_PS_DCM	= BIT(22),
+	IWL_UCODE_TLV_FLAGS_BSS_P2P_PS_SCM	= BIT(23),
 	IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT	= BIT(24),
+	IWL_UCODE_TLV_FLAGS_EBS_SUPPORT		= BIT(25),
 	IWL_UCODE_TLV_FLAGS_P2P_PS_UAPSD	= BIT(26),
 	IWL_UCODE_TLV_FLAGS_BCAST_FILTERING	= BIT(29),
 	IWL_UCODE_TLV_FLAGS_GO_UAPSD		= BIT(30),
@@ -128,9 +118,11 @@ enum iwl_ucode_tlv_flag {
 /**
  * enum iwl_ucode_tlv_api - ucode api
  * @IWL_UCODE_TLV_API_WOWLAN_CONFIG_TID: wowlan config includes tid field.
+ * @IWL_UCODE_TLV_API_CSA_FLOW: ucode can do unbind-bind flow for CSA.
  */
 enum iwl_ucode_tlv_api {
 	IWL_UCODE_TLV_API_WOWLAN_CONFIG_TID	= BIT(0),
+	IWL_UCODE_TLV_API_CSA_FLOW		= BIT(4),
 };
 
 /**
@@ -183,6 +175,7 @@ enum iwl_ucode_sec {
 #define IWL_UCODE_SECTION_MAX 12
 #define IWL_API_ARRAY_SIZE	1
 #define IWL_CAPABILITIES_ARRAY_SIZE	1
+#define CPU1_CPU2_SEPARATOR_SECTION	0xFFFFCCCC
 
 struct iwl_ucode_capabilities {
 	u32 max_probe_length;
@@ -205,6 +198,11 @@ struct fw_img {
 	bool is_dual_cpus;
 };
 
+struct iwl_sf_region {
+	u32 addr;
+	u32 size;
+};
+
 /* uCode version contains 4 values: Major/Minor/API/Serial */
 #define IWL_UCODE_MAJOR(ver)	(((ver) & 0xFF000000) >> 24)
 #define IWL_UCODE_MINOR(ver)	(((ver) & 0x00FF0000) >> 16)
diff --git a/drivers/net/wireless/iwlwifi/iwl-io.c b/drivers/net/wireless/iwlwifi/iwl-io.c
index 44cc3cf4576..5eef4ae7333 100644
--- a/drivers/net/wireless/iwlwifi/iwl-io.c
+++ b/drivers/net/wireless/iwlwifi/iwl-io.c
@@ -33,6 +33,7 @@
 #include "iwl-io.h"
 #include "iwl-csr.h"
 #include "iwl-debug.h"
+#include "iwl-prph.h"
 #include "iwl-fh.h"
 
 #define IWL_POLL_INTERVAL 10	/* microseconds */
@@ -183,6 +184,23 @@ void iwl_clear_bits_prph(struct iwl_trans *trans, u32 ofs, u32 mask)
 }
 IWL_EXPORT_SYMBOL(iwl_clear_bits_prph);
 
+void iwl_force_nmi(struct iwl_trans *trans)
+{
+	/*
+	 * In HW previous to the 8000 HW family, and in the 8000 HW family
+	 * itself when the revision step==0, the DEVICE_SET_NMI_REG is used
+	 * to force an NMI. Otherwise, a different register -
+	 * DEVICE_SET_NMI_8000B_REG - is used.
+	 */
+	if ((trans->cfg->device_family != IWL_DEVICE_FAMILY_8000) ||
+	    ((trans->hw_rev & 0xc) == 0x0))
+		iwl_write_prph(trans, DEVICE_SET_NMI_REG, DEVICE_SET_NMI_VAL);
+	else
+		iwl_write_prph(trans, DEVICE_SET_NMI_8000B_REG,
+			       DEVICE_SET_NMI_8000B_VAL);
+}
+IWL_EXPORT_SYMBOL(iwl_force_nmi);
+
 static const char *get_fh_string(int cmd)
 {
 #define IWL_CMD(x) case x: return #x
diff --git a/drivers/net/wireless/iwlwifi/iwl-io.h b/drivers/net/wireless/iwlwifi/iwl-io.h
index 665ddd9dbbc..705d12c079e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-io.h
+++ b/drivers/net/wireless/iwlwifi/iwl-io.h
@@ -80,6 +80,7 @@ void iwl_set_bits_prph(struct iwl_trans *trans, u32 ofs, u32 mask);
 void iwl_set_bits_mask_prph(struct iwl_trans *trans, u32 ofs,
 			    u32 bits, u32 mask);
 void iwl_clear_bits_prph(struct iwl_trans *trans, u32 ofs, u32 mask);
+void iwl_force_nmi(struct iwl_trans *trans);
 
 /* Error handling */
 int iwl_dump_fh(struct iwl_trans *trans, char **buf);
diff --git a/drivers/net/wireless/iwlwifi/iwl-modparams.h b/drivers/net/wireless/iwlwifi/iwl-modparams.h
index d994317db85..d051857729a 100644
--- a/drivers/net/wireless/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/iwlwifi/iwl-modparams.h
@@ -119,6 +119,7 @@ struct iwl_mod_params {
 #endif
 	int ant_coupling;
 	char *nvm_file;
+	bool uapsd_disable;
 };
 
 #endif /* #__iwl_modparams_h__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
index 6be30c69850..85eee79c495 100644
--- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
@@ -62,6 +62,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/etherdevice.h>
 #include "iwl-drv.h"
 #include "iwl-modparams.h"
 #include "iwl-nvm-parse.h"
@@ -127,19 +128,20 @@ static const u8 iwl_nvm_channels[] = {
 
 static const u8 iwl_nvm_channels_family_8000[] = {
 	/* 2.4 GHz */
-	1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13,
+	1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
 	/* 5 GHz */
 	36, 40, 44, 48, 52, 56, 60, 64, 68, 72, 76, 80, 84, 88, 92,
 	96, 100, 104, 108, 112, 116, 120, 124, 128, 132, 136, 140, 144,
 	149, 153, 157, 161, 165, 169, 173, 177, 181
 };
 
-#define IWL_NUM_CHANNELS	ARRAY_SIZE(iwl_nvm_channels)
+#define IWL_NUM_CHANNELS		ARRAY_SIZE(iwl_nvm_channels)
 #define IWL_NUM_CHANNELS_FAMILY_8000	ARRAY_SIZE(iwl_nvm_channels_family_8000)
-#define NUM_2GHZ_CHANNELS	14
-#define FIRST_2GHZ_HT_MINUS	5
-#define LAST_2GHZ_HT_PLUS	9
-#define LAST_5GHZ_HT		161
+#define NUM_2GHZ_CHANNELS		14
+#define NUM_2GHZ_CHANNELS_FAMILY_8000	14
+#define FIRST_2GHZ_HT_MINUS		5
+#define LAST_2GHZ_HT_PLUS		9
+#define LAST_5GHZ_HT			161
 
 #define DEFAULT_MAX_TX_POWER 16
 
@@ -202,21 +204,23 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 	struct ieee80211_channel *channel;
 	u16 ch_flags;
 	bool is_5ghz;
-	int num_of_ch;
+	int num_of_ch, num_2ghz_channels;
 	const u8 *nvm_chan;
 
 	if (cfg->device_family != IWL_DEVICE_FAMILY_8000) {
 		num_of_ch = IWL_NUM_CHANNELS;
 		nvm_chan = &iwl_nvm_channels[0];
+		num_2ghz_channels = NUM_2GHZ_CHANNELS;
 	} else {
 		num_of_ch = IWL_NUM_CHANNELS_FAMILY_8000;
 		nvm_chan = &iwl_nvm_channels_family_8000[0];
+		num_2ghz_channels = NUM_2GHZ_CHANNELS_FAMILY_8000;
 	}
 
 	for (ch_idx = 0; ch_idx < num_of_ch; ch_idx++) {
 		ch_flags = __le16_to_cpup(nvm_ch_flags + ch_idx);
 
-		if (ch_idx >= NUM_2GHZ_CHANNELS &&
+		if (ch_idx >= num_2ghz_channels &&
 		    !data->sku_cap_band_52GHz_enable)
 			ch_flags &= ~NVM_CHANNEL_VALID;
 
@@ -225,7 +229,7 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 					 "Ch. %d Flags %x [%sGHz] - No traffic\n",
 					 nvm_chan[ch_idx],
 					 ch_flags,
-					 (ch_idx >= NUM_2GHZ_CHANNELS) ?
+					 (ch_idx >= num_2ghz_channels) ?
 					 "5.2" : "2.4");
 			continue;
 		}
@@ -234,7 +238,7 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 		n_channels++;
 
 		channel->hw_value = nvm_chan[ch_idx];
-		channel->band = (ch_idx < NUM_2GHZ_CHANNELS) ?
+		channel->band = (ch_idx < num_2ghz_channels) ?
 				IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
 		channel->center_freq =
 			ieee80211_channel_to_frequency(
@@ -242,7 +246,7 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 
 		/* TODO: Need to be dependent to the NVM */
 		channel->flags = IEEE80211_CHAN_NO_HT40;
-		if (ch_idx < NUM_2GHZ_CHANNELS &&
+		if (ch_idx < num_2ghz_channels &&
 		    (ch_flags & NVM_CHANNEL_40MHZ)) {
 			if (nvm_chan[ch_idx] <= LAST_2GHZ_HT_PLUS)
 				channel->flags &= ~IEEE80211_CHAN_NO_HT40PLUS;
@@ -250,7 +254,7 @@ static int iwl_init_channel_map(struct device *dev, const struct iwl_cfg *cfg,
 				channel->flags &= ~IEEE80211_CHAN_NO_HT40MINUS;
 		} else if (nvm_chan[ch_idx] <= LAST_5GHZ_HT &&
 			   (ch_flags & NVM_CHANNEL_40MHZ)) {
-			if ((ch_idx - NUM_2GHZ_CHANNELS) % 2 == 0)
+			if ((ch_idx - num_2ghz_channels) % 2 == 0)
 				channel->flags &= ~IEEE80211_CHAN_NO_HT40PLUS;
 			else
 				channel->flags &= ~IEEE80211_CHAN_NO_HT40MINUS;
@@ -447,13 +451,7 @@ static void iwl_set_hw_address(const struct iwl_cfg *cfg,
 			       struct iwl_nvm_data *data,
 			       const __le16 *nvm_sec)
 {
-	u8 hw_addr[ETH_ALEN];
-
-	if (cfg->device_family != IWL_DEVICE_FAMILY_8000)
-		memcpy(hw_addr, nvm_sec + HW_ADDR, ETH_ALEN);
-	else
-		memcpy(hw_addr, nvm_sec + MAC_ADDRESS_OVERRIDE_FAMILY_8000,
-		       ETH_ALEN);
+	const u8 *hw_addr = (const u8 *)(nvm_sec + HW_ADDR);
 
 	/* The byte order is little endian 16 bit, meaning 214365 */
 	data->hw_addr[0] = hw_addr[1];
@@ -464,6 +462,41 @@ static void iwl_set_hw_address(const struct iwl_cfg *cfg,
 	data->hw_addr[5] = hw_addr[4];
 }
 
+static void iwl_set_hw_address_family_8000(const struct iwl_cfg *cfg,
+					   struct iwl_nvm_data *data,
+					   const __le16 *mac_override,
+					   const __le16 *nvm_hw)
+{
+	const u8 *hw_addr;
+
+	if (mac_override) {
+		hw_addr = (const u8 *)(mac_override +
+				 MAC_ADDRESS_OVERRIDE_FAMILY_8000);
+
+		/* The byte order is little endian 16 bit, meaning 214365 */
+		data->hw_addr[0] = hw_addr[1];
+		data->hw_addr[1] = hw_addr[0];
+		data->hw_addr[2] = hw_addr[3];
+		data->hw_addr[3] = hw_addr[2];
+		data->hw_addr[4] = hw_addr[5];
+		data->hw_addr[5] = hw_addr[4];
+
+		if (is_valid_ether_addr(hw_addr))
+			return;
+	}
+
+	/* take the MAC address from the OTP */
+	hw_addr = (const u8 *)(nvm_hw + HW_ADDR0_FAMILY_8000);
+	data->hw_addr[0] = hw_addr[3];
+	data->hw_addr[1] = hw_addr[2];
+	data->hw_addr[2] = hw_addr[1];
+	data->hw_addr[3] = hw_addr[0];
+
+	hw_addr = (const u8 *)(nvm_hw + HW_ADDR1_FAMILY_8000);
+	data->hw_addr[4] = hw_addr[1];
+	data->hw_addr[5] = hw_addr[0];
+}
+
 struct iwl_nvm_data *
 iwl_parse_nvm_data(struct device *dev, const struct iwl_cfg *cfg,
 		   const __le16 *nvm_hw, const __le16 *nvm_sw,
@@ -523,7 +556,7 @@ iwl_parse_nvm_data(struct device *dev, const struct iwl_cfg *cfg,
 				rx_chains);
 	} else {
 		/* MAC address in family 8000 */
-		iwl_set_hw_address(cfg, data, mac_override);
+		iwl_set_hw_address_family_8000(cfg, data, mac_override, nvm_hw);
 
 		iwl_init_sbands(dev, cfg, data, regulatory,
 				sku & NVM_SKU_CAP_11AC_ENABLE, tx_chains,
diff --git a/drivers/net/wireless/iwlwifi/iwl-op-mode.h b/drivers/net/wireless/iwlwifi/iwl-op-mode.h
index ea29504ac61..99785c892f9 100644
--- a/drivers/net/wireless/iwlwifi/iwl-op-mode.h
+++ b/drivers/net/wireless/iwlwifi/iwl-op-mode.h
@@ -63,6 +63,7 @@
 #ifndef __iwl_op_mode_h__
 #define __iwl_op_mode_h__
 
+#include <linux/netdevice.h>
 #include <linux/debugfs.h>
 
 struct iwl_op_mode;
@@ -112,8 +113,11 @@ struct iwl_cfg;
  * @stop: stop the op_mode. Must free all the memory allocated.
  *	May sleep
  * @rx: Rx notification to the op_mode. rxb is the Rx buffer itself. Cmd is the
- *	HCMD this Rx responds to.
- *	This callback may sleep, it is called from a threaded IRQ handler.
+ *	HCMD this Rx responds to. Can't sleep.
+ * @napi_add: NAPI initialisation. The transport is fully responsible for NAPI,
+ *	but the higher layers need to know about it (in particular mac80211 to
+ *	to able to call the right NAPI RX functions); this function is needed
+ *	to eventually call netif_napi_add() with higher layer involvement.
  * @queue_full: notifies that a HW queue is full.
  *	Must be atomic and called with BH disabled.
  * @queue_not_full: notifies that a HW queue is not full any more.
@@ -143,6 +147,11 @@ struct iwl_op_mode_ops {
 	void (*stop)(struct iwl_op_mode *op_mode);
 	int (*rx)(struct iwl_op_mode *op_mode, struct iwl_rx_cmd_buffer *rxb,
 		  struct iwl_device_cmd *cmd);
+	void (*napi_add)(struct iwl_op_mode *op_mode,
+			 struct napi_struct *napi,
+			 struct net_device *napi_dev,
+			 int (*poll)(struct napi_struct *, int),
+			 int weight);
 	void (*queue_full)(struct iwl_op_mode *op_mode, int queue);
 	void (*queue_not_full)(struct iwl_op_mode *op_mode, int queue);
 	bool (*hw_rf_kill)(struct iwl_op_mode *op_mode, bool state);
@@ -180,7 +189,6 @@ static inline int iwl_op_mode_rx(struct iwl_op_mode *op_mode,
 				  struct iwl_rx_cmd_buffer *rxb,
 				  struct iwl_device_cmd *cmd)
 {
-	might_sleep();
 	return op_mode->ops->rx(op_mode, rxb, cmd);
 }
 
@@ -249,4 +257,15 @@ static inline int iwl_op_mode_exit_d0i3(struct iwl_op_mode *op_mode)
 	return op_mode->ops->exit_d0i3(op_mode);
 }
 
+static inline void iwl_op_mode_napi_add(struct iwl_op_mode *op_mode,
+					struct napi_struct *napi,
+					struct net_device *napi_dev,
+					int (*poll)(struct napi_struct *, int),
+					int weight)
+{
+	if (!op_mode->ops->napi_add)
+		return;
+	op_mode->ops->napi_add(op_mode, napi, napi_dev, poll, weight);
+}
+
 #endif /* __iwl_op_mode_h__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-phy-db.c b/drivers/net/wireless/iwlwifi/iwl-phy-db.c
index b761ac4822a..d4fb5cad07e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-phy-db.c
+++ b/drivers/net/wireless/iwlwifi/iwl-phy-db.c
@@ -345,7 +345,6 @@ static int iwl_send_phy_db_cmd(struct iwl_phy_db *phy_db, u16 type,
 	struct iwl_phy_db_cmd phy_db_cmd;
 	struct iwl_host_cmd cmd = {
 		.id = PHY_DB_CMD,
-		.flags = CMD_SYNC,
 	};
 
 	IWL_DEBUG_INFO(phy_db->trans,
@@ -393,13 +392,13 @@ static int iwl_phy_db_send_all_channel_groups(
 					  entry->data);
 		if (err) {
 			IWL_ERR(phy_db->trans,
-				"Can't SEND phy_db section %d (%d), err %d",
+				"Can't SEND phy_db section %d (%d), err %d\n",
 				type, i, err);
 			return err;
 		}
 
 		IWL_DEBUG_INFO(phy_db->trans,
-			       "Sent PHY_DB HCMD, type = %d num = %d",
+			       "Sent PHY_DB HCMD, type = %d num = %d\n",
 			       type, i);
 	}
 
@@ -451,7 +450,7 @@ int iwl_send_phy_db_data(struct iwl_phy_db *phy_db)
 						 IWL_NUM_PAPD_CH_GROUPS);
 	if (err) {
 		IWL_ERR(phy_db->trans,
-			"Cannot send channel specific PAPD groups");
+			"Cannot send channel specific PAPD groups\n");
 		return err;
 	}
 
@@ -461,7 +460,7 @@ int iwl_send_phy_db_data(struct iwl_phy_db *phy_db)
 						 IWL_NUM_TXP_CH_GROUPS);
 	if (err) {
 		IWL_ERR(phy_db->trans,
-			"Cannot send channel specific TX power groups");
+			"Cannot send channel specific TX power groups\n");
 		return err;
 	}
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-prph.h b/drivers/net/wireless/iwlwifi/iwl-prph.h
index 5f657c50140..4997e27672b 100644
--- a/drivers/net/wireless/iwlwifi/iwl-prph.h
+++ b/drivers/net/wireless/iwlwifi/iwl-prph.h
@@ -105,6 +105,9 @@
 
 /* Device NMI register */
 #define DEVICE_SET_NMI_REG 0x00a01c30
+#define DEVICE_SET_NMI_VAL 0x1
+#define DEVICE_SET_NMI_8000B_REG 0x00a01c24
+#define DEVICE_SET_NMI_8000B_VAL 0x1000000
 
 /* Shared registers (0x0..0x3ff, via target indirect or periphery */
 #define SHR_BASE	0x00a10000
@@ -348,4 +351,12 @@ enum secure_load_status_reg {
 
 #define LMPM_SECURE_TIME_OUT	(100)
 
+/* Rx FIFO */
+#define RXF_SIZE_ADDR			(0xa00c88)
+#define RXF_SIZE_BYTE_CND_POS		(7)
+#define RXF_SIZE_BYTE_CNT_MSK		(0x3ff << RXF_SIZE_BYTE_CND_POS)
+
+#define RXF_LD_FENCE_OFFSET_ADDR	(0xa00c10)
+#define RXF_FIFO_RD_FENCE_ADDR		(0xa00c0c)
+
 #endif				/* __iwl_prph_h__ */
diff --git a/drivers/net/wireless/iwlwifi/iwl-trans.h b/drivers/net/wireless/iwlwifi/iwl-trans.h
index 8cdb0dd618a..34d49e171fb 100644
--- a/drivers/net/wireless/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/iwlwifi/iwl-trans.h
@@ -189,10 +189,9 @@ static inline u32 iwl_rx_packet_payload_len(const struct iwl_rx_packet *pkt)
 /**
  * enum CMD_MODE - how to send the host commands ?
  *
- * @CMD_SYNC: The caller will be stalled until the fw responds to the command
  * @CMD_ASYNC: Return right away and don't wait for the response
- * @CMD_WANT_SKB: valid only with CMD_SYNC. The caller needs the buffer of the
- *	response. The caller needs to call iwl_free_resp when done.
+ * @CMD_WANT_SKB: Not valid with CMD_ASYNC. The caller needs the buffer of
+ *	the response. The caller needs to call iwl_free_resp when done.
  * @CMD_HIGH_PRIO: The command is high priority - it goes to the front of the
  *	command queue, but after other high priority commands. valid only
  *	with CMD_ASYNC.
@@ -202,7 +201,6 @@ static inline u32 iwl_rx_packet_payload_len(const struct iwl_rx_packet *pkt)
  *	(i.e. mark it as non-idle).
  */
 enum CMD_MODE {
-	CMD_SYNC		= 0,
 	CMD_ASYNC		= BIT(0),
 	CMD_WANT_SKB		= BIT(1),
 	CMD_SEND_IN_RFKILL	= BIT(2),
@@ -427,7 +425,7 @@ struct iwl_trans;
  * @send_cmd:send a host command. Must return -ERFKILL if RFkill is asserted.
  *	If RFkill is asserted in the middle of a SYNC host command, it must
  *	return -ERFKILL straight away.
- *	May sleep only if CMD_SYNC is set
+ *	May sleep only if CMD_ASYNC is not set
  * @tx: send an skb
  *	Must be atomic
  * @reclaim: free packet until ssn. Returns a list of freed packets.
@@ -437,8 +435,7 @@ struct iwl_trans;
  *	this one. The op_mode must not configure the HCMD queue. May sleep.
  * @txq_disable: de-configure a Tx queue to send AMPDUs
  *	Must be atomic
- * @wait_tx_queue_empty: wait until all tx queues are empty
- *	May sleep
+ * @wait_tx_queue_empty: wait until tx queues are empty. May sleep.
  * @dbgfs_register: add the dbgfs files under this directory. Files will be
  *	automatically deleted.
  * @write8: write a u8 to a register at offset ofs from the BAR
@@ -464,6 +461,11 @@ struct iwl_trans;
  * @unref: release a reference previously taken with @ref. Note that
  *	initially the reference count is 1, making an initial @unref
  *	necessary to allow low power states.
+ * @dump_data: fill a data dump with debug data, maybe containing last
+ *	TX'ed commands and similar. When called with a NULL buffer and
+ *	zero buffer length, provide only the (estimated) required buffer
+ *	length. Return the used buffer length.
+ *	Note that the transport must fill in the proper file headers.
  */
 struct iwl_trans_ops {
 
@@ -471,6 +473,8 @@ struct iwl_trans_ops {
 	void (*op_mode_leave)(struct iwl_trans *iwl_trans);
 	int (*start_fw)(struct iwl_trans *trans, const struct fw_img *fw,
 			bool run_in_rfkill);
+	int (*update_sf)(struct iwl_trans *trans,
+			 struct iwl_sf_region *st_fwrd_space);
 	void (*fw_alive)(struct iwl_trans *trans, u32 scd_addr);
 	void (*stop_device)(struct iwl_trans *trans);
 
@@ -490,7 +494,7 @@ struct iwl_trans_ops {
 	void (*txq_disable)(struct iwl_trans *trans, int queue);
 
 	int (*dbgfs_register)(struct iwl_trans *trans, struct dentry* dir);
-	int (*wait_tx_queue_empty)(struct iwl_trans *trans);
+	int (*wait_tx_queue_empty)(struct iwl_trans *trans, u32 txq_bm);
 
 	void (*write8)(struct iwl_trans *trans, u32 ofs, u8 val);
 	void (*write32)(struct iwl_trans *trans, u32 ofs, u32 val);
@@ -512,6 +516,10 @@ struct iwl_trans_ops {
 			      u32 value);
 	void (*ref)(struct iwl_trans *trans);
 	void (*unref)(struct iwl_trans *trans);
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	u32 (*dump_data)(struct iwl_trans *trans, void *buf, u32 buflen);
+#endif
 };
 
 /**
@@ -630,6 +638,17 @@ static inline int iwl_trans_start_fw(struct iwl_trans *trans,
 	return trans->ops->start_fw(trans, fw, run_in_rfkill);
 }
 
+static inline int iwl_trans_update_sf(struct iwl_trans *trans,
+				      struct iwl_sf_region *st_fwrd_space)
+{
+	might_sleep();
+
+	if (trans->ops->update_sf)
+		return trans->ops->update_sf(trans, st_fwrd_space);
+
+	return 0;
+}
+
 static inline void iwl_trans_stop_device(struct iwl_trans *trans)
 {
 	might_sleep();
@@ -665,6 +684,16 @@ static inline void iwl_trans_unref(struct iwl_trans *trans)
 		trans->ops->unref(trans);
 }
 
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+static inline u32 iwl_trans_dump_data(struct iwl_trans *trans,
+				      void *buf, u32 buflen)
+{
+	if (!trans->ops->dump_data)
+		return 0;
+	return trans->ops->dump_data(trans, buf, buflen);
+}
+#endif
+
 static inline int iwl_trans_send_cmd(struct iwl_trans *trans,
 				     struct iwl_host_cmd *cmd)
 {
@@ -678,7 +707,7 @@ static inline int iwl_trans_send_cmd(struct iwl_trans *trans,
 		return -EIO;
 
 	if (unlikely(trans->state != IWL_TRANS_FW_ALIVE)) {
-		IWL_ERR(trans, "%s bad state = %d", __func__, trans->state);
+		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
 		return -EIO;
 	}
 
@@ -720,7 +749,7 @@ static inline int iwl_trans_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		return -EIO;
 
 	if (unlikely(trans->state != IWL_TRANS_FW_ALIVE))
-		IWL_ERR(trans, "%s bad state = %d", __func__, trans->state);
+		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
 
 	return trans->ops->tx(trans, skb, dev_cmd, queue);
 }
@@ -729,7 +758,7 @@ static inline void iwl_trans_reclaim(struct iwl_trans *trans, int queue,
 				     int ssn, struct sk_buff_head *skbs)
 {
 	if (unlikely(trans->state != IWL_TRANS_FW_ALIVE))
-		IWL_ERR(trans, "%s bad state = %d", __func__, trans->state);
+		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
 
 	trans->ops->reclaim(trans, queue, ssn, skbs);
 }
@@ -746,7 +775,7 @@ static inline void iwl_trans_txq_enable(struct iwl_trans *trans, int queue,
 	might_sleep();
 
 	if (unlikely((trans->state != IWL_TRANS_FW_ALIVE)))
-		IWL_ERR(trans, "%s bad state = %d", __func__, trans->state);
+		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
 
 	trans->ops->txq_enable(trans, queue, fifo, sta_id, tid,
 				 frame_limit, ssn);
@@ -759,12 +788,13 @@ static inline void iwl_trans_ac_txq_enable(struct iwl_trans *trans, int queue,
 			     IWL_MAX_TID_COUNT, IWL_FRAME_LIMIT, 0);
 }
 
-static inline int iwl_trans_wait_tx_queue_empty(struct iwl_trans *trans)
+static inline int iwl_trans_wait_tx_queue_empty(struct iwl_trans *trans,
+						u32 txq_bm)
 {
 	if (unlikely(trans->state != IWL_TRANS_FW_ALIVE))
-		IWL_ERR(trans, "%s bad state = %d", __func__, trans->state);
+		IWL_ERR(trans, "%s bad state = %d\n", __func__, trans->state);
 
-	return trans->ops->wait_tx_queue_empty(trans);
+	return trans->ops->wait_tx_queue_empty(trans, txq_bm);
 }
 
 static inline int iwl_trans_dbgfs_register(struct iwl_trans *trans,
diff --git a/drivers/net/wireless/iwlwifi/mvm/Makefile b/drivers/net/wireless/iwlwifi/mvm/Makefile
index ccdd3b7c4cc..c30d7f64ec1 100644
--- a/drivers/net/wireless/iwlwifi/mvm/Makefile
+++ b/drivers/net/wireless/iwlwifi/mvm/Makefile
@@ -3,8 +3,9 @@ iwlmvm-y += fw.o mac80211.o nvm.o ops.o phy-ctxt.o mac-ctxt.o
 iwlmvm-y += utils.o rx.o tx.o binding.o quota.o sta.o sf.o
 iwlmvm-y += scan.o time-event.o rs.o
 iwlmvm-y += power.o coex.o
-iwlmvm-y += led.o tt.o offloading.o
+iwlmvm-y += tt.o offloading.o
 iwlmvm-$(CONFIG_IWLWIFI_DEBUGFS) += debugfs.o debugfs-vif.o
+iwlmvm-$(CONFIG_IWLWIFI_LEDS) += led.o
 iwlmvm-$(CONFIG_PM_SLEEP) += d3.o
 
 ccflags-y += -D__CHECK_ENDIAN__ -I$(src)/../
diff --git a/drivers/net/wireless/iwlwifi/mvm/coex.c b/drivers/net/wireless/iwlwifi/mvm/coex.c
index 0489314425c..c8c3b38228f 100644
--- a/drivers/net/wireless/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/iwlwifi/mvm/coex.c
@@ -104,12 +104,9 @@ static const u8 iwl_bt_prio_tbl[BT_COEX_PRIO_TBL_EVT_MAX] = {
 #define BT_DISABLE_REDUCED_TXPOWER_THRESHOLD	(-65)
 #define BT_ANTENNA_COUPLING_THRESHOLD		(30)
 
-int iwl_send_bt_prio_tbl(struct iwl_mvm *mvm)
+static int iwl_send_bt_prio_tbl(struct iwl_mvm *mvm)
 {
-	if (!(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_NEWBT_COEX))
-		return 0;
-
-	return iwl_mvm_send_cmd_pdu(mvm, BT_COEX_PRIO_TABLE, CMD_SYNC,
+	return iwl_mvm_send_cmd_pdu(mvm, BT_COEX_PRIO_TABLE, 0,
 				    sizeof(struct iwl_bt_coex_prio_tbl_cmd),
 				    &iwl_bt_prio_tbl);
 }
@@ -127,10 +124,10 @@ const u32 iwl_bt_cts_kill_msk[BT_KILL_MSK_MAX] = {
 };
 
 static const __le32 iwl_bt_prio_boost[BT_COEX_BOOST_SIZE] = {
-	cpu_to_le32(0xf0f0f0f0),
-	cpu_to_le32(0xc0c0c0c0),
-	cpu_to_le32(0xfcfcfcfc),
-	cpu_to_le32(0xff00ff00),
+	cpu_to_le32(0xf0f0f0f0), /* 50% */
+	cpu_to_le32(0xc0c0c0c0), /* 25% */
+	cpu_to_le32(0xfcfcfcfc), /* 75% */
+	cpu_to_le32(0xfefefefe), /* 87.5% */
 };
 
 static const __le32 iwl_single_shared_ant[BT_COEX_MAX_LUT][BT_COEX_LUT_SIZE] = {
@@ -303,8 +300,8 @@ static const __le64 iwl_ci_mask[][3] = {
 };
 
 static const __le32 iwl_bt_mprio_lut[BT_COEX_MULTI_PRIO_LUT_SIZE] = {
-	cpu_to_le32(0x22002200),
-	cpu_to_le32(0x33113311),
+	cpu_to_le32(0x28412201),
+	cpu_to_le32(0x11118451),
 };
 
 struct corunning_block_luts {
@@ -568,13 +565,13 @@ int iwl_send_bt_init_conf(struct iwl_mvm *mvm)
 		.id = BT_CONFIG,
 		.len = { sizeof(*bt_cmd), },
 		.dataflags = { IWL_HCMD_DFL_NOCOPY, },
-		.flags = CMD_SYNC,
 	};
 	int ret;
 	u32 flags;
 
-	if (!(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_NEWBT_COEX))
-		return 0;
+	ret = iwl_send_bt_prio_tbl(mvm);
+	if (ret)
+		return ret;
 
 	bt_cmd = kzalloc(sizeof(*bt_cmd), GFP_KERNEL);
 	if (!bt_cmd)
@@ -582,10 +579,12 @@ int iwl_send_bt_init_conf(struct iwl_mvm *mvm)
 	cmd.data[0] = bt_cmd;
 
 	bt_cmd->max_kill = 5;
-	bt_cmd->bt4_antenna_isolation_thr = BT_ANTENNA_COUPLING_THRESHOLD,
-	bt_cmd->bt4_antenna_isolation = iwlwifi_mod_params.ant_coupling,
-	bt_cmd->bt4_tx_tx_delta_freq_thr = 15,
-	bt_cmd->bt4_tx_rx_max_freq0 = 15,
+	bt_cmd->bt4_antenna_isolation_thr = BT_ANTENNA_COUPLING_THRESHOLD;
+	bt_cmd->bt4_antenna_isolation = iwlwifi_mod_params.ant_coupling;
+	bt_cmd->bt4_tx_tx_delta_freq_thr = 15;
+	bt_cmd->bt4_tx_rx_max_freq0 = 15;
+	bt_cmd->override_primary_lut = BT_COEX_INVALID_LUT;
+	bt_cmd->override_secondary_lut = BT_COEX_INVALID_LUT;
 
 	flags = iwlwifi_mod_params.bt_coex_active ?
 			BT_COEX_NW : BT_COEX_DISABLE;
@@ -663,7 +662,6 @@ static int iwl_mvm_bt_udpate_ctrl_kill_msk(struct iwl_mvm *mvm,
 		.data[0] = &bt_cmd,
 		.len = { sizeof(*bt_cmd), },
 		.dataflags = { IWL_HCMD_DFL_NOCOPY, },
-		.flags = CMD_SYNC,
 	};
 	int ret = 0;
 
@@ -717,7 +715,8 @@ static int iwl_mvm_bt_udpate_ctrl_kill_msk(struct iwl_mvm *mvm,
 	return ret;
 }
 
-int iwl_mvm_bt_coex_reduced_txp(struct iwl_mvm *mvm, u8 sta_id, bool enable)
+static int iwl_mvm_bt_coex_reduced_txp(struct iwl_mvm *mvm, u8 sta_id,
+				       bool enable)
 {
 	struct iwl_bt_coex_cmd *bt_cmd;
 	/* Send ASYNC since this can be sent from an atomic context */
@@ -735,8 +734,7 @@ int iwl_mvm_bt_coex_reduced_txp(struct iwl_mvm *mvm, u8 sta_id, bool enable)
 		return 0;
 
 	/* nothing to do */
-	if (mvmsta->bt_reduced_txpower_dbg ||
-	    mvmsta->bt_reduced_txpower == enable)
+	if (mvmsta->bt_reduced_txpower == enable)
 		return 0;
 
 	bt_cmd = kzalloc(sizeof(*bt_cmd), GFP_ATOMIC);
@@ -803,23 +801,10 @@ static void iwl_mvm_bt_notif_iterator(void *_data, u8 *mac,
 
 	switch (vif->type) {
 	case NL80211_IFTYPE_STATION:
+		/* Count BSSes vifs */
+		data->num_bss_ifaces++;
 		/* default smps_mode for BSS / P2P client is AUTOMATIC */
 		smps_mode = IEEE80211_SMPS_AUTOMATIC;
-		data->num_bss_ifaces++;
-
-		/*
-		 * Count unassoc BSSes, relax SMSP constraints
-		 * and disable reduced Tx Power
-		 */
-		if (!vif->bss_conf.assoc) {
-			iwl_mvm_update_smps(mvm, vif, IWL_MVM_SMPS_REQ_BT_COEX,
-					    smps_mode);
-			if (iwl_mvm_bt_coex_reduced_txp(mvm,
-							mvmvif->ap_sta_id,
-							false))
-				IWL_ERR(mvm, "Couldn't send BT_CONFIG cmd\n");
-			return;
-		}
 		break;
 	case NL80211_IFTYPE_AP:
 		/* default smps_mode for AP / GO is OFF */
@@ -845,8 +830,12 @@ static void iwl_mvm_bt_notif_iterator(void *_data, u8 *mac,
 		/* ... relax constraints and disable rssi events */
 		iwl_mvm_update_smps(mvm, vif, IWL_MVM_SMPS_REQ_BT_COEX,
 				    smps_mode);
-		if (vif->type == NL80211_IFTYPE_STATION)
+		data->reduced_tx_power = false;
+		if (vif->type == NL80211_IFTYPE_STATION) {
+			iwl_mvm_bt_coex_reduced_txp(mvm, mvmvif->ap_sta_id,
+						    false);
 			iwl_mvm_bt_coex_enable_rssi_event(mvm, vif, false, 0);
+		}
 		return;
 	}
 
@@ -857,6 +846,11 @@ static void iwl_mvm_bt_notif_iterator(void *_data, u8 *mac,
 		smps_mode = vif->type == NL80211_IFTYPE_AP ?
 				IEEE80211_SMPS_OFF :
 				IEEE80211_SMPS_DYNAMIC;
+
+	/* relax SMPS contraints for next association */
+	if (!vif->bss_conf.assoc)
+		smps_mode = IEEE80211_SMPS_AUTOMATIC;
+
 	IWL_DEBUG_COEX(data->mvm,
 		       "mac %d: bt_status %d bt_activity_grading %d smps_req %d\n",
 		       mvmvif->id, data->notif->bt_status, bt_activity_grading,
@@ -903,22 +897,18 @@ static void iwl_mvm_bt_notif_iterator(void *_data, u8 *mac,
 		/* if secondary is not NULL, it might be a GO */
 		data->secondary = chanctx_conf;
 
-	/* don't reduce the Tx power if in loose scheme */
+	/*
+	 * don't reduce the Tx power if one of these is true:
+	 *  we are in LOOSE
+	 *  single share antenna product
+	 *  BT is active
+	 *  we are associated
+	 */
 	if (iwl_get_coex_type(mvm, vif) == BT_COEX_LOOSE_LUT ||
-	    mvm->cfg->bt_shared_single_ant) {
-		data->reduced_tx_power = false;
-		iwl_mvm_bt_coex_enable_rssi_event(mvm, vif, false, 0);
-		return;
-	}
-
-	/* reduced Txpower only if BT is on, so ...*/
-	if (!data->notif->bt_status) {
-		/* ... cancel reduced Tx power ... */
-		if (iwl_mvm_bt_coex_reduced_txp(mvm, mvmvif->ap_sta_id, false))
-			IWL_ERR(mvm, "Couldn't send BT_CONFIG cmd\n");
+	    mvm->cfg->bt_shared_single_ant || !vif->bss_conf.assoc ||
+	    !data->notif->bt_status) {
 		data->reduced_tx_power = false;
-
-		/* ... and there is no need to get reports on RSSI any more. */
+		iwl_mvm_bt_coex_reduced_txp(mvm, mvmvif->ap_sta_id, false);
 		iwl_mvm_bt_coex_enable_rssi_event(mvm, vif, false, 0);
 		return;
 	}
@@ -1022,9 +1012,9 @@ static void iwl_mvm_bt_coex_notif_handle(struct iwl_mvm *mvm)
 
 	/* Don't spam the fw with the same command over and over */
 	if (memcmp(&cmd, &mvm->last_bt_ci_cmd, sizeof(cmd))) {
-		if (iwl_mvm_send_cmd_pdu(mvm, BT_COEX_CI, CMD_SYNC,
+		if (iwl_mvm_send_cmd_pdu(mvm, BT_COEX_CI, 0,
 					 sizeof(cmd), &cmd))
-			IWL_ERR(mvm, "Failed to send BT_CI cmd");
+			IWL_ERR(mvm, "Failed to send BT_CI cmd\n");
 		memcpy(&mvm->last_bt_ci_cmd, &cmd, sizeof(cmd));
 	}
 
@@ -1039,7 +1029,6 @@ static void iwl_mvm_bt_coex_notif_handle(struct iwl_mvm *mvm)
 		IWL_ERR(mvm, "Failed to update the ctrl_kill_msk\n");
 }
 
-/* upon association, the fw will send in BT Coex notification */
 int iwl_mvm_rx_bt_coex_notif(struct iwl_mvm *mvm,
 			     struct iwl_rx_cmd_buffer *rxb,
 			     struct iwl_device_cmd *dev_cmd)
@@ -1215,6 +1204,17 @@ bool iwl_mvm_bt_coex_is_mimo_allowed(struct iwl_mvm *mvm,
 	return iwl_get_coex_type(mvm, mvmsta->vif) == BT_COEX_TIGHT_LUT;
 }
 
+bool iwl_mvm_bt_coex_is_tpc_allowed(struct iwl_mvm *mvm,
+				    enum ieee80211_band band)
+{
+	u32 bt_activity = le32_to_cpu(mvm->last_bt_notif.bt_activity_grading);
+
+	if (band != IEEE80211_BAND_2GHZ)
+		return false;
+
+	return bt_activity >= BT_LOW_TRAFFIC;
+}
+
 u8 iwl_mvm_bt_coex_tx_prio(struct iwl_mvm *mvm, struct ieee80211_hdr *hdr,
 			   struct ieee80211_tx_info *info, u8 ac)
 {
@@ -1249,9 +1249,6 @@ u8 iwl_mvm_bt_coex_tx_prio(struct iwl_mvm *mvm, struct ieee80211_hdr *hdr,
 
 void iwl_mvm_bt_coex_vif_change(struct iwl_mvm *mvm)
 {
-	if (!(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_NEWBT_COEX))
-		return;
-
 	iwl_mvm_bt_coex_notif_handle(mvm);
 }
 
@@ -1270,7 +1267,6 @@ int iwl_mvm_rx_ant_coupling_notif(struct iwl_mvm *mvm,
 		.id = BT_CONFIG,
 		.len = { sizeof(*bt_cmd), },
 		.dataflags = { IWL_HCMD_DFL_NOCOPY, },
-		.flags = CMD_SYNC,
 	};
 
 	if (!IWL_MVM_BT_COEX_CORUNNING)
diff --git a/drivers/net/wireless/iwlwifi/mvm/d3.c b/drivers/net/wireless/iwlwifi/mvm/d3.c
index e56f5a0edf8..645b3cfc29a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/iwlwifi/mvm/d3.c
@@ -193,8 +193,7 @@ static void iwl_mvm_wowlan_program_keys(struct ieee80211_hw *hw,
 			wkc.wep_key.key_offset = data->wep_key_idx;
 		}
 
-		ret = iwl_mvm_send_cmd_pdu(mvm, WEP_KEY, CMD_SYNC,
-					   sizeof(wkc), &wkc);
+		ret = iwl_mvm_send_cmd_pdu(mvm, WEP_KEY, 0, sizeof(wkc), &wkc);
 		data->error = ret != 0;
 
 		mvm->ptk_ivlen = key->iv_len;
@@ -341,7 +340,6 @@ static int iwl_mvm_send_patterns(struct iwl_mvm *mvm,
 	struct iwl_host_cmd cmd = {
 		.id = WOWLAN_PATTERNS,
 		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
-		.flags = CMD_SYNC,
 	};
 	int i, err;
 
@@ -518,7 +516,6 @@ static int iwl_mvm_send_remote_wake_cfg(struct iwl_mvm *mvm,
 		.id = REMOTE_WAKE_CONFIG_CMD,
 		.len = { sizeof(*cfg), },
 		.dataflags = { IWL_HCMD_DFL_NOCOPY, },
-		.flags = CMD_SYNC,
 	};
 	int ret;
 
@@ -666,10 +663,8 @@ static int iwl_mvm_d3_reprogram(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	if (WARN_ON(!vif->bss_conf.assoc))
 		return -EINVAL;
-	/* hack */
-	vif->bss_conf.assoc = false;
+
 	ret = iwl_mvm_mac_ctxt_add(mvm, vif);
-	vif->bss_conf.assoc = true;
 	if (ret)
 		return ret;
 
@@ -705,7 +700,7 @@ static int iwl_mvm_d3_reprogram(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		return ret;
 	rcu_assign_pointer(mvm->fw_id_to_mac_id[mvmvif->ap_sta_id], ap_sta);
 
-	ret = iwl_mvm_mac_ctxt_changed(mvm, vif);
+	ret = iwl_mvm_mac_ctxt_changed(mvm, vif, false);
 	if (ret)
 		return ret;
 
@@ -719,7 +714,7 @@ static int iwl_mvm_d3_reprogram(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	for (i = 1; i < MAX_BINDINGS; i++)
 		quota_cmd.quotas[i].id_and_color = cpu_to_le32(FW_CTXT_INVALID);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, CMD_SYNC,
+	ret = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, 0,
 				   sizeof(quota_cmd), &quota_cmd);
 	if (ret)
 		IWL_ERR(mvm, "Failed to send quota: %d\n", ret);
@@ -739,15 +734,13 @@ static int iwl_mvm_get_last_nonqos_seq(struct iwl_mvm *mvm,
 	};
 	struct iwl_host_cmd cmd = {
 		.id = NON_QOS_TX_COUNTER_CMD,
-		.flags = CMD_SYNC | CMD_WANT_SKB,
+		.flags = CMD_WANT_SKB,
 	};
 	int err;
 	u32 size;
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_D3_CONTINUITY_API) {
-		cmd.data[0] = &query_cmd;
-		cmd.len[0] = sizeof(query_cmd);
-	}
+	cmd.data[0] = &query_cmd;
+	cmd.len[0] = sizeof(query_cmd);
 
 	err = iwl_mvm_send_cmd(mvm, &cmd);
 	if (err)
@@ -758,10 +751,8 @@ static int iwl_mvm_get_last_nonqos_seq(struct iwl_mvm *mvm,
 		err = -EINVAL;
 	} else {
 		err = le16_to_cpup((__le16 *)cmd.resp_pkt->data);
-		/* new API returns next, not last-used seqno */
-		if (mvm->fw->ucode_capa.flags &
-				IWL_UCODE_TLV_FLAGS_D3_CONTINUITY_API)
-			err = (u16) (err - 0x10);
+		/* firmware returns next, not last-used seqno */
+		err = (u16) (err - 0x10);
 	}
 
 	iwl_free_resp(&cmd);
@@ -785,11 +776,7 @@ void iwl_mvm_set_last_nonqos_seq(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 
 	mvmvif->seqno_valid = false;
 
-	if (!(mvm->fw->ucode_capa.flags &
-			IWL_UCODE_TLV_FLAGS_D3_CONTINUITY_API))
-		return;
-
-	if (iwl_mvm_send_cmd_pdu(mvm, NON_QOS_TX_COUNTER_CMD, CMD_SYNC,
+	if (iwl_mvm_send_cmd_pdu(mvm, NON_QOS_TX_COUNTER_CMD, 0,
 				 sizeof(query_cmd), &query_cmd))
 		IWL_ERR(mvm, "failed to set non-QoS seqno\n");
 }
@@ -804,7 +791,7 @@ iwl_mvm_send_wowlan_config_cmd(struct iwl_mvm *mvm,
 	if (mvm->fw->ucode_capa.api[0] & IWL_UCODE_TLV_API_WOWLAN_CONFIG_TID)
 		cmd_len = sizeof(*cmd);
 
-	return iwl_mvm_send_cmd_pdu(mvm, WOWLAN_CONFIGURATION, CMD_SYNC,
+	return iwl_mvm_send_cmd_pdu(mvm, WOWLAN_CONFIGURATION, 0,
 				    cmd_len, cmd);
 }
 
@@ -833,7 +820,7 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 	};
 	struct iwl_host_cmd d3_cfg_cmd = {
 		.id = D3_CONFIG_CMD,
-		.flags = CMD_SYNC | CMD_WANT_SKB,
+		.flags = CMD_WANT_SKB,
 		.data[0] = &d3_cfg_cmd_data,
 		.len[0] = sizeof(d3_cfg_cmd_data),
 	};
@@ -983,7 +970,6 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 		if (key_data.use_rsc_tsc) {
 			struct iwl_host_cmd rsc_tsc_cmd = {
 				.id = WOWLAN_TSC_RSC_PARAM,
-				.flags = CMD_SYNC,
 				.data[0] = key_data.rsc_tsc,
 				.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
 				.len[0] = sizeof(*key_data.rsc_tsc),
@@ -997,7 +983,7 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 		if (key_data.use_tkip) {
 			ret = iwl_mvm_send_cmd_pdu(mvm,
 						   WOWLAN_TKIP_PARAM,
-						   CMD_SYNC, sizeof(tkip_cmd),
+						   0, sizeof(tkip_cmd),
 						   &tkip_cmd);
 			if (ret)
 				goto out;
@@ -1014,8 +1000,7 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 			kek_kck_cmd.replay_ctr = mvmvif->rekey_data.replay_ctr;
 
 			ret = iwl_mvm_send_cmd_pdu(mvm,
-						   WOWLAN_KEK_KCK_MATERIAL,
-						   CMD_SYNC,
+						   WOWLAN_KEK_KCK_MATERIAL, 0,
 						   sizeof(kek_kck_cmd),
 						   &kek_kck_cmd);
 			if (ret)
@@ -1031,7 +1016,7 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 	if (ret)
 		goto out;
 
-	ret = iwl_mvm_send_proto_offload(mvm, vif, false, CMD_SYNC);
+	ret = iwl_mvm_send_proto_offload(mvm, vif, false, 0);
 	if (ret)
 		goto out;
 
@@ -1043,7 +1028,7 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 	if (ret)
 		goto out;
 
-	ret = iwl_mvm_power_update_mac(mvm, vif);
+	ret = iwl_mvm_power_update_mac(mvm);
 	if (ret)
 		goto out;
 
@@ -1082,6 +1067,15 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 
 int iwl_mvm_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 {
+	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+
+	if (iwl_mvm_is_d0i3_supported(mvm)) {
+		mutex_lock(&mvm->d0i3_suspend_mutex);
+		__set_bit(D0I3_DEFER_WAKEUP, &mvm->d0i3_suspend_flags);
+		mutex_unlock(&mvm->d0i3_suspend_mutex);
+		return 0;
+	}
+
 	return __iwl_mvm_suspend(hw, wowlan, false);
 }
 
@@ -1277,7 +1271,7 @@ static void iwl_mvm_set_tkip_rx_seq(struct tkip_sc *scs,
 }
 
 static void iwl_mvm_set_key_rx_seq(struct ieee80211_key_conf *key,
-				   struct iwl_wowlan_status_v6 *status)
+				   struct iwl_wowlan_status *status)
 {
 	union iwl_all_tsc_rsc *rsc = &status->gtk.rsc.all_tsc_rsc;
 
@@ -1294,7 +1288,7 @@ static void iwl_mvm_set_key_rx_seq(struct ieee80211_key_conf *key,
 }
 
 struct iwl_mvm_d3_gtk_iter_data {
-	struct iwl_wowlan_status_v6 *status;
+	struct iwl_wowlan_status *status;
 	void *last_gtk;
 	u32 cipher;
 	bool find_phase, unhandled_cipher;
@@ -1370,7 +1364,7 @@ static void iwl_mvm_d3_update_gtks(struct ieee80211_hw *hw,
 
 static bool iwl_mvm_setup_connection_keep(struct iwl_mvm *mvm,
 					  struct ieee80211_vif *vif,
-					  struct iwl_wowlan_status_v6 *status)
+					  struct iwl_wowlan_status *status)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	struct iwl_mvm_d3_gtk_iter_data gtkdata = {
@@ -1465,10 +1459,10 @@ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm,
 	} err_info;
 	struct iwl_host_cmd cmd = {
 		.id = WOWLAN_GET_STATUSES,
-		.flags = CMD_SYNC | CMD_WANT_SKB,
+		.flags = CMD_WANT_SKB,
 	};
 	struct iwl_wowlan_status_data status;
-	struct iwl_wowlan_status_v6 *status_v6;
+	struct iwl_wowlan_status *fw_status;
 	int ret, len, status_size, i;
 	bool keep;
 	struct ieee80211_sta *ap_sta;
@@ -1491,7 +1485,7 @@ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm,
 	}
 
 	/* only for tracing for now */
-	ret = iwl_mvm_send_cmd_pdu(mvm, OFFLOADS_QUERY_CMD, CMD_SYNC, 0, NULL);
+	ret = iwl_mvm_send_cmd_pdu(mvm, OFFLOADS_QUERY_CMD, 0, 0, NULL);
 	if (ret)
 		IWL_ERR(mvm, "failed to query offload statistics (%d)\n", ret);
 
@@ -1505,10 +1499,7 @@ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm,
 	if (!cmd.resp_pkt)
 		goto out_unlock;
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_D3_CONTINUITY_API)
-		status_size = sizeof(struct iwl_wowlan_status_v6);
-	else
-		status_size = sizeof(struct iwl_wowlan_status_v4);
+	status_size = sizeof(*fw_status);
 
 	len = iwl_rx_packet_payload_len(cmd.resp_pkt);
 	if (len < status_size) {
@@ -1516,35 +1507,18 @@ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm,
 		goto out_free_resp;
 	}
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_D3_CONTINUITY_API) {
-		status_v6 = (void *)cmd.resp_pkt->data;
-
-		status.pattern_number = le16_to_cpu(status_v6->pattern_number);
-		for (i = 0; i < 8; i++)
-			status.qos_seq_ctr[i] =
-				le16_to_cpu(status_v6->qos_seq_ctr[i]);
-		status.wakeup_reasons = le32_to_cpu(status_v6->wakeup_reasons);
-		status.wake_packet_length =
-			le32_to_cpu(status_v6->wake_packet_length);
-		status.wake_packet_bufsize =
-			le32_to_cpu(status_v6->wake_packet_bufsize);
-		status.wake_packet = status_v6->wake_packet;
-	} else {
-		struct iwl_wowlan_status_v4 *status_v4;
-		status_v6 = NULL;
-		status_v4 = (void *)cmd.resp_pkt->data;
-
-		status.pattern_number = le16_to_cpu(status_v4->pattern_number);
-		for (i = 0; i < 8; i++)
-			status.qos_seq_ctr[i] =
-				le16_to_cpu(status_v4->qos_seq_ctr[i]);
-		status.wakeup_reasons = le32_to_cpu(status_v4->wakeup_reasons);
-		status.wake_packet_length =
-			le32_to_cpu(status_v4->wake_packet_length);
-		status.wake_packet_bufsize =
-			le32_to_cpu(status_v4->wake_packet_bufsize);
-		status.wake_packet = status_v4->wake_packet;
-	}
+	fw_status = (void *)cmd.resp_pkt->data;
+
+	status.pattern_number = le16_to_cpu(fw_status->pattern_number);
+	for (i = 0; i < 8; i++)
+		status.qos_seq_ctr[i] =
+			le16_to_cpu(fw_status->qos_seq_ctr[i]);
+	status.wakeup_reasons = le32_to_cpu(fw_status->wakeup_reasons);
+	status.wake_packet_length =
+		le32_to_cpu(fw_status->wake_packet_length);
+	status.wake_packet_bufsize =
+		le32_to_cpu(fw_status->wake_packet_bufsize);
+	status.wake_packet = fw_status->wake_packet;
 
 	if (len != status_size + ALIGN(status.wake_packet_bufsize, 4)) {
 		IWL_ERR(mvm, "Invalid WoWLAN status response!\n");
@@ -1571,7 +1545,7 @@ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm,
 
 	iwl_mvm_report_wakeup_reasons(mvm, vif, &status);
 
-	keep = iwl_mvm_setup_connection_keep(mvm, vif, status_v6);
+	keep = iwl_mvm_setup_connection_keep(mvm, vif, fw_status);
 
 	iwl_free_resp(&cmd);
 	return keep;
@@ -1674,6 +1648,19 @@ int iwl_mvm_resume(struct ieee80211_hw *hw)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
 
+	if (iwl_mvm_is_d0i3_supported(mvm)) {
+		bool exit_now;
+
+		mutex_lock(&mvm->d0i3_suspend_mutex);
+		__clear_bit(D0I3_DEFER_WAKEUP, &mvm->d0i3_suspend_flags);
+		exit_now = __test_and_clear_bit(D0I3_PENDING_WAKEUP,
+						&mvm->d0i3_suspend_flags);
+		mutex_unlock(&mvm->d0i3_suspend_mutex);
+		if (exit_now)
+			_iwl_mvm_exit_d0i3(mvm);
+		return 0;
+	}
+
 	return __iwl_mvm_resume(mvm, false);
 }
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/iwlwifi/mvm/debugfs-vif.c
index 9b59e1d7ae7..2e90ff795c1 100644
--- a/drivers/net/wireless/iwlwifi/mvm/debugfs-vif.c
+++ b/drivers/net/wireless/iwlwifi/mvm/debugfs-vif.c
@@ -103,10 +103,6 @@ static void iwl_dbgfs_update_pm(struct iwl_mvm *mvm,
 		IWL_DEBUG_POWER(mvm, "tx_data_timeout=%d\n", val);
 		dbgfs_pm->tx_data_timeout = val;
 		break;
-	case MVM_DEBUGFS_PM_DISABLE_POWER_OFF:
-		IWL_DEBUG_POWER(mvm, "disable_power_off=%d\n", val);
-		dbgfs_pm->disable_power_off = val;
-		break;
 	case MVM_DEBUGFS_PM_LPRX_ENA:
 		IWL_DEBUG_POWER(mvm, "lprx %s\n", val ? "enabled" : "disabled");
 		dbgfs_pm->lprx_ena = val;
@@ -154,12 +150,6 @@ static ssize_t iwl_dbgfs_pm_params_write(struct ieee80211_vif *vif, char *buf,
 		if (sscanf(buf + 16, "%d", &val) != 1)
 			return -EINVAL;
 		param = MVM_DEBUGFS_PM_TX_DATA_TIMEOUT;
-	} else if (!strncmp("disable_power_off=", buf, 18) &&
-		   !(mvm->fw->ucode_capa.flags &
-		     IWL_UCODE_TLV_FLAGS_DEVICE_PS_CMD)) {
-		if (sscanf(buf + 18, "%d", &val) != 1)
-			return -EINVAL;
-		param = MVM_DEBUGFS_PM_DISABLE_POWER_OFF;
 	} else if (!strncmp("lprx=", buf, 5)) {
 		if (sscanf(buf + 5, "%d", &val) != 1)
 			return -EINVAL;
@@ -185,7 +175,7 @@ static ssize_t iwl_dbgfs_pm_params_write(struct ieee80211_vif *vif, char *buf,
 
 	mutex_lock(&mvm->mutex);
 	iwl_dbgfs_update_pm(mvm, vif, param, val);
-	ret = iwl_mvm_power_update_mac(mvm, vif);
+	ret = iwl_mvm_power_update_mac(mvm);
 	mutex_unlock(&mvm->mutex);
 
 	return ret ?: count;
@@ -272,10 +262,9 @@ static ssize_t iwl_dbgfs_mac_params_read(struct file *file,
 			struct iwl_mvm_sta *mvm_sta = (void *)sta->drv_priv;
 
 			pos += scnprintf(buf+pos, bufsz-pos,
-					 "ap_sta_id %d - reduced Tx power %d force %d\n",
+					 "ap_sta_id %d - reduced Tx power %d\n",
 					 ap_sta_id,
-					 mvm_sta->bt_reduced_txpower,
-					 mvm_sta->bt_reduced_txpower_dbg);
+					 mvm_sta->bt_reduced_txpower);
 		}
 	}
 
@@ -293,41 +282,6 @@ static ssize_t iwl_dbgfs_mac_params_read(struct file *file,
 	return simple_read_from_buffer(user_buf, count, ppos, buf, pos);
 }
 
-static ssize_t iwl_dbgfs_reduced_txp_write(struct ieee80211_vif *vif,
-					   char *buf, size_t count,
-					   loff_t *ppos)
-{
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	struct iwl_mvm *mvm = mvmvif->mvm;
-	struct iwl_mvm_sta *mvmsta;
-	bool reduced_tx_power;
-	int ret;
-
-	if (mvmvif->ap_sta_id >= ARRAY_SIZE(mvm->fw_id_to_mac_id))
-		return -ENOTCONN;
-
-	if (strtobool(buf, &reduced_tx_power) != 0)
-		return -EINVAL;
-
-	mutex_lock(&mvm->mutex);
-
-	mvmsta = iwl_mvm_sta_from_staid_protected(mvm, mvmvif->ap_sta_id);
-	if (IS_ERR_OR_NULL(mvmsta)) {
-		mutex_unlock(&mvm->mutex);
-		return -ENOTCONN;
-	}
-
-	mvmsta->bt_reduced_txpower_dbg = false;
-	ret = iwl_mvm_bt_coex_reduced_txp(mvm, mvmvif->ap_sta_id,
-					  reduced_tx_power);
-	if (!ret)
-		mvmsta->bt_reduced_txpower_dbg = true;
-
-	mutex_unlock(&mvm->mutex);
-
-	return ret ? : count;
-}
-
 static void iwl_dbgfs_update_bf(struct ieee80211_vif *vif,
 				enum iwl_dbgfs_bf_mask param, int value)
 {
@@ -462,9 +416,9 @@ static ssize_t iwl_dbgfs_bf_params_write(struct ieee80211_vif *vif, char *buf,
 	mutex_lock(&mvm->mutex);
 	iwl_dbgfs_update_bf(vif, param, value);
 	if (param == MVM_DEBUGFS_BF_ENABLE_BEACON_FILTER && !value)
-		ret = iwl_mvm_disable_beacon_filter(mvm, vif, CMD_SYNC);
+		ret = iwl_mvm_disable_beacon_filter(mvm, vif, 0);
 	else
-		ret = iwl_mvm_enable_beacon_filter(mvm, vif, CMD_SYNC);
+		ret = iwl_mvm_enable_beacon_filter(mvm, vif, 0);
 	mutex_unlock(&mvm->mutex);
 
 	return ret ?: count;
@@ -568,7 +522,6 @@ MVM_DEBUGFS_READ_FILE_OPS(mac_params);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(pm_params, 32);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(bf_params, 256);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(low_latency, 10);
-MVM_DEBUGFS_WRITE_FILE_OPS(reduced_txp, 10);
 
 void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 {
@@ -592,8 +545,7 @@ void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		return;
 	}
 
-	if ((mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_PM_CMD_SUPPORT) &&
-	    iwlmvm_mod_params.power_scheme != IWL_POWER_SCHEME_CAM &&
+	if (iwlmvm_mod_params.power_scheme != IWL_POWER_SCHEME_CAM &&
 	    ((vif->type == NL80211_IFTYPE_STATION && !vif->p2p) ||
 	     (vif->type == NL80211_IFTYPE_STATION && vif->p2p &&
 	      mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_BSS_P2P_PS_DCM)))
@@ -601,7 +553,6 @@ void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 					 S_IRUSR);
 
 	MVM_DEBUGFS_ADD_FILE_VIF(mac_params, mvmvif->dbgfs_dir, S_IRUSR);
-	MVM_DEBUGFS_ADD_FILE_VIF(reduced_txp, mvmvif->dbgfs_dir, S_IWUSR);
 	MVM_DEBUGFS_ADD_FILE_VIF(low_latency, mvmvif->dbgfs_dir,
 				 S_IRUSR | S_IWUSR);
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/iwlwifi/mvm/debugfs.c
index 1b52deea608..29ca72695ea 100644
--- a/drivers/net/wireless/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/iwlwifi/mvm/debugfs.c
@@ -65,9 +65,8 @@
 #include "mvm.h"
 #include "sta.h"
 #include "iwl-io.h"
-#include "iwl-prph.h"
 #include "debugfs.h"
-#include "fw-error-dump.h"
+#include "iwl-fw-error-dump.h"
 
 static ssize_t iwl_dbgfs_tx_flush_write(struct iwl_mvm *mvm, char *buf,
 					size_t count, loff_t *ppos)
@@ -136,9 +135,6 @@ static int iwl_dbgfs_fw_error_dump_open(struct inode *inode, struct file *file)
 
 	file->private_data = mvm->fw_error_dump;
 	mvm->fw_error_dump = NULL;
-	kfree(mvm->fw_error_sram);
-	mvm->fw_error_sram = NULL;
-	mvm->fw_error_sram_len = 0;
 	ret = 0;
 
 out:
@@ -684,7 +680,7 @@ static ssize_t iwl_dbgfs_fw_restart_write(struct iwl_mvm *mvm, char *buf,
 		mvm->restart_fw++;
 
 	/* take the return value to make compiler happy - it will fail anyway */
-	ret = iwl_mvm_send_cmd_pdu(mvm, REPLY_ERROR, CMD_SYNC, 0, NULL);
+	ret = iwl_mvm_send_cmd_pdu(mvm, REPLY_ERROR, 0, 0, NULL);
 
 	mutex_unlock(&mvm->mutex);
 
@@ -694,7 +690,7 @@ static ssize_t iwl_dbgfs_fw_restart_write(struct iwl_mvm *mvm, char *buf,
 static ssize_t iwl_dbgfs_fw_nmi_write(struct iwl_mvm *mvm, char *buf,
 				      size_t count, loff_t *ppos)
 {
-	iwl_write_prph(mvm->trans, DEVICE_SET_NMI_REG, 1);
+	iwl_force_nmi(mvm->trans);
 
 	return count;
 }
@@ -841,7 +837,7 @@ static ssize_t iwl_dbgfs_bcast_filters_write(struct iwl_mvm *mvm, char *buf,
 	/* send updated bcast filtering configuration */
 	if (mvm->dbgfs_bcast_filtering.override &&
 	    iwl_mvm_bcast_filter_build_cmd(mvm, &cmd))
-		err = iwl_mvm_send_cmd_pdu(mvm, BCAST_FILTER_CMD, CMD_SYNC,
+		err = iwl_mvm_send_cmd_pdu(mvm, BCAST_FILTER_CMD, 0,
 					   sizeof(cmd), &cmd);
 	mutex_unlock(&mvm->mutex);
 
@@ -913,7 +909,7 @@ static ssize_t iwl_dbgfs_bcast_filters_macs_write(struct iwl_mvm *mvm,
 	/* send updated bcast filtering configuration */
 	if (mvm->dbgfs_bcast_filtering.override &&
 	    iwl_mvm_bcast_filter_build_cmd(mvm, &cmd))
-		err = iwl_mvm_send_cmd_pdu(mvm, BCAST_FILTER_CMD, CMD_SYNC,
+		err = iwl_mvm_send_cmd_pdu(mvm, BCAST_FILTER_CMD, 0,
 					   sizeof(cmd), &cmd);
 	mutex_unlock(&mvm->mutex);
 
@@ -1004,6 +1000,7 @@ static ssize_t iwl_dbgfs_d0i3_refs_read(struct file *file,
 	PRINT_MVM_REF(IWL_MVM_REF_P2P_CLIENT);
 	PRINT_MVM_REF(IWL_MVM_REF_AP_IBSS);
 	PRINT_MVM_REF(IWL_MVM_REF_USER);
+	PRINT_MVM_REF(IWL_MVM_REF_EXIT_WORK);
 
 	return simple_read_from_buffer(user_buf, count, ppos, buf, pos);
 }
@@ -1108,9 +1105,9 @@ MVM_DEBUGFS_READ_WRITE_FILE_OPS(scan_ant_rxchain, 8);
 MVM_DEBUGFS_READ_WRITE_FILE_OPS(d0i3_refs, 8);
 
 static const struct file_operations iwl_dbgfs_fw_error_dump_ops = {
-        .open = iwl_dbgfs_fw_error_dump_open,
-        .read = iwl_dbgfs_fw_error_dump_read,
-        .release = iwl_dbgfs_fw_error_dump_release,
+	.open = iwl_dbgfs_fw_error_dump_open,
+	.read = iwl_dbgfs_fw_error_dump_read,
+	.release = iwl_dbgfs_fw_error_dump_release,
 };
 
 #ifdef CONFIG_IWLWIFI_BCAST_FILTERING
@@ -1138,9 +1135,8 @@ int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir)
 	MVM_DEBUGFS_ADD_FILE(fw_error_dump, dbgfs_dir, S_IRUSR);
 	MVM_DEBUGFS_ADD_FILE(bt_notif, dbgfs_dir, S_IRUSR);
 	MVM_DEBUGFS_ADD_FILE(bt_cmd, dbgfs_dir, S_IRUSR);
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_DEVICE_PS_CMD)
-		MVM_DEBUGFS_ADD_FILE(disable_power_off, mvm->debugfs_dir,
-				     S_IRUSR | S_IWUSR);
+	MVM_DEBUGFS_ADD_FILE(disable_power_off, mvm->debugfs_dir,
+			     S_IRUSR | S_IWUSR);
 	MVM_DEBUGFS_ADD_FILE(fw_rx_stats, mvm->debugfs_dir, S_IRUSR);
 	MVM_DEBUGFS_ADD_FILE(drv_rx_stats, mvm->debugfs_dir, S_IRUSR);
 	MVM_DEBUGFS_ADD_FILE(fw_restart, mvm->debugfs_dir, S_IWUSR);
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-coex.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-coex.h
index 21877e5966a..5fe82c29c8a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-coex.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-coex.h
@@ -141,7 +141,8 @@ enum iwl_bt_coex_lut_type {
 	BT_COEX_TX_DIS_LUT,
 
 	BT_COEX_MAX_LUT,
-};
+	BT_COEX_INVALID_LUT = 0xff,
+}; /* BT_COEX_DECISION_LUT_INDEX_API_E_VER_1 */
 
 #define BT_COEX_LUT_SIZE (12)
 #define BT_COEX_CORUN_LUT_SIZE (32)
@@ -154,19 +155,23 @@ enum iwl_bt_coex_lut_type {
  * @flags:&enum iwl_bt_coex_flags
  * @max_kill:
  * @bt_reduced_tx_power: enum %iwl_bt_reduced_tx_power
- * @bt4_antenna_isolation:
- * @bt4_antenna_isolation_thr:
- * @bt4_tx_tx_delta_freq_thr:
- * @bt4_tx_rx_max_freq0:
- * @bt_prio_boost:
+ * @override_primary_lut: enum %iwl_bt_coex_lut_type: BT_COEX_INVALID_LUT
+ *	should be set by default
+ * @override_secondary_lut: enum %iwl_bt_coex_lut_type: BT_COEX_INVALID_LUT
+ *	should be set by default
+ * @bt4_antenna_isolation: antenna isolation
+ * @bt4_antenna_isolation_thr: antenna threshold value
+ * @bt4_tx_tx_delta_freq_thr: TxTx delta frequency
+ * @bt4_tx_rx_max_freq0: TxRx max frequency
+ * @bt_prio_boost: BT priority boost registers
  * @wifi_tx_prio_boost: SW boost of wifi tx priority
  * @wifi_rx_prio_boost: SW boost of wifi rx priority
- * @kill_ack_msk:
- * @kill_cts_msk:
- * @decision_lut:
- * @bt4_multiprio_lut:
- * @bt4_corun_lut20:
- * @bt4_corun_lut40:
+ * @kill_ack_msk: kill ACK mask. 1 - Tx ACK, 0 - kill Tx of ACK.
+ * @kill_cts_msk: kill CTS mask. 1 - Tx CTS, 0 - kill Tx of CTS.
+ * @decision_lut: PTA decision LUT, per Prio-Ch
+ * @bt4_multiprio_lut: multi priority LUT configuration
+ * @bt4_corun_lut20: co-running 20 MHz LUT configuration
+ * @bt4_corun_lut40: co-running 40 MHz LUT configuration
  * @valid_bit_msk: enum %iwl_bt_coex_valid_bit_msk
  *
  * The structure is used for the BT_COEX command.
@@ -175,7 +180,8 @@ struct iwl_bt_coex_cmd {
 	__le32 flags;
 	u8 max_kill;
 	u8 bt_reduced_tx_power;
-	u8 reserved[2];
+	u8 override_primary_lut;
+	u8 override_secondary_lut;
 
 	u8 bt4_antenna_isolation;
 	u8 bt4_antenna_isolation_thr;
@@ -194,7 +200,7 @@ struct iwl_bt_coex_cmd {
 	__le32 bt4_corun_lut40[BT_COEX_CORUN_LUT_SIZE];
 
 	__le32 valid_bit_msk;
-} __packed; /* BT_COEX_CMD_API_S_VER_3 */
+} __packed; /* BT_COEX_CMD_API_S_VER_5 */
 
 /**
  * struct iwl_bt_coex_ci_cmd - bt coex channel inhibition command
@@ -282,7 +288,7 @@ enum iwl_bt_activity_grading {
 	BT_ON_NO_CONNECTION	= 1,
 	BT_LOW_TRAFFIC		= 2,
 	BT_HIGH_TRAFFIC		= 3,
-};
+}; /* BT_COEX_BT_ACTIVITY_GRADING_API_E_VER_1 */
 
 /**
  * struct iwl_bt_coex_profile_notif - notification about BT coex
@@ -310,7 +316,7 @@ struct iwl_bt_coex_profile_notif {
 	__le32 primary_ch_lut;
 	__le32 secondary_ch_lut;
 	__le32 bt_activity_grading;
-} __packed; /* BT_COEX_PROFILE_NTFY_API_S_VER_2 */
+} __packed; /* BT_COEX_PROFILE_NTFY_API_S_VER_3 */
 
 enum iwl_bt_coex_prio_table_event {
 	BT_COEX_PRIO_TBL_EVT_INIT_CALIB1		= 0,
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-d3.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-d3.h
index 10fcc1a79eb..13696fe419b 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-d3.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-d3.h
@@ -345,21 +345,6 @@ enum iwl_wowlan_wakeup_reason {
 	IWL_WOWLAN_WAKEUP_BY_REM_WAKE_WAKEUP_PACKET		= BIT(12),
 }; /* WOWLAN_WAKE_UP_REASON_API_E_VER_2 */
 
-struct iwl_wowlan_status_v4 {
-	__le64 replay_ctr;
-	__le16 pattern_number;
-	__le16 non_qos_seq_ctr;
-	__le16 qos_seq_ctr[8];
-	__le32 wakeup_reasons;
-	__le32 rekey_status;
-	__le32 num_of_gtk_rekeys;
-	__le32 transmitted_ndps;
-	__le32 received_beacons;
-	__le32 wake_packet_length;
-	__le32 wake_packet_bufsize;
-	u8 wake_packet[]; /* can be truncated from _length to _bufsize */
-} __packed; /* WOWLAN_STATUSES_API_S_VER_4 */
-
 struct iwl_wowlan_gtk_status {
 	u8 key_index;
 	u8 reserved[3];
@@ -368,7 +353,7 @@ struct iwl_wowlan_gtk_status {
 	struct iwl_wowlan_rsc_tsc_params_cmd rsc;
 } __packed;
 
-struct iwl_wowlan_status_v6 {
+struct iwl_wowlan_status {
 	struct iwl_wowlan_gtk_status gtk;
 	__le64 replay_ctr;
 	__le16 pattern_number;
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-rs.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-rs.h
index 39148b5bb33..8bb5b94bf96 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-rs.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-rs.h
@@ -334,7 +334,7 @@ enum {
  */
 struct iwl_lq_cmd {
 	u8 sta_id;
-	u8 reserved1;
+	u8 reduced_tpc;
 	u16 control;
 	/* LINK_QUAL_GENERAL_PARAMS_API_S_VER_1 */
 	u8 flags;
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
index d73a89ecd78..6959fda3fe0 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
@@ -169,8 +169,12 @@ enum iwl_scan_type {
 	SCAN_TYPE_DISCOVERY_FORCED	= 6,
 }; /* SCAN_ACTIVITY_TYPE_E_VER_1 */
 
-/* Maximal number of channels to scan */
-#define MAX_NUM_SCAN_CHANNELS 0x24
+/**
+ * Maximal number of channels to scan
+ * it should be equal to:
+ * max(IWL_NUM_CHANNELS, IWL_NUM_CHANNELS_FAMILY_8000)
+ */
+#define MAX_NUM_SCAN_CHANNELS 50
 
 /**
  * struct iwl_scan_cmd - scan request command
@@ -534,13 +538,16 @@ struct iwl_scan_offload_schedule {
  *
  * IWL_SCAN_OFFLOAD_FLAG_PASS_ALL: pass all results - no filtering.
  * IWL_SCAN_OFFLOAD_FLAG_CACHED_CHANNEL: add cached channels to partial scan.
- * IWL_SCAN_OFFLOAD_FLAG_ENERGY_SCAN: use energy based scan before partial scan
- *	on A band.
+ * IWL_SCAN_OFFLOAD_FLAG_EBS_QUICK_MODE: EBS duration is 100mSec - typical
+ *	beacon period. Finding channel activity in this mode is not guaranteed.
+ * IWL_SCAN_OFFLOAD_FLAG_EBS_ACCURATE_MODE: EBS duration is 200mSec.
+ *	Assuming beacon period is 100ms finding channel activity is guaranteed.
  */
 enum iwl_scan_offload_flags {
 	IWL_SCAN_OFFLOAD_FLAG_PASS_ALL		= BIT(0),
 	IWL_SCAN_OFFLOAD_FLAG_CACHED_CHANNEL	= BIT(2),
-	IWL_SCAN_OFFLOAD_FLAG_ENERGY_SCAN	= BIT(3),
+	IWL_SCAN_OFFLOAD_FLAG_EBS_QUICK_MODE	= BIT(5),
+	IWL_SCAN_OFFLOAD_FLAG_EBS_ACCURATE_MODE	= BIT(6),
 };
 
 /**
@@ -563,17 +570,24 @@ enum iwl_scan_offload_compleate_status {
 	IWL_SCAN_OFFLOAD_ABORTED	= 2,
 };
 
+enum iwl_scan_ebs_status {
+	IWL_SCAN_EBS_SUCCESS,
+	IWL_SCAN_EBS_FAILED,
+	IWL_SCAN_EBS_CHAN_NOT_FOUND,
+};
+
 /**
  * iwl_scan_offload_complete - SCAN_OFFLOAD_COMPLETE_NTF_API_S_VER_1
  * @last_schedule_line:		last schedule line executed (fast or regular)
  * @last_schedule_iteration:	last scan iteration executed before scan abort
  * @status:			enum iwl_scan_offload_compleate_status
+ * @ebs_status: last EBS status, see IWL_SCAN_EBS_*
  */
 struct iwl_scan_offload_complete {
 	u8 last_schedule_line;
 	u8 last_schedule_iteration;
 	u8 status;
-	u8 reserved;
+	u8 ebs_status;
 } __packed;
 
 /**
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-sta.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-sta.h
index d6364786726..39cebee8016 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-sta.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-sta.h
@@ -255,22 +255,19 @@ struct iwl_mvm_keyinfo {
 } __packed;
 
 /**
- * struct iwl_mvm_add_sta_cmd_v5 - Add/modify a station in the fw's sta table.
+ * struct iwl_mvm_add_sta_cmd - Add/modify a station in the fw's sta table.
  * ( REPLY_ADD_STA = 0x18 )
  * @add_modify: 1: modify existing, 0: add new station
- * @unicast_tx_key_id: unicast tx key id. Relevant only when unicast key sent
- * @multicast_tx_key_id: multicast tx key id. Relevant only when multicast key
- *	sent
+ * @awake_acs:
+ * @tid_disable_tx: is tid BIT(tid) enabled for Tx. Clear BIT(x) to enable
+ *	AMPDU for tid x. Set %STA_MODIFY_TID_DISABLE_TX to change this field.
  * @mac_id_n_color: the Mac context this station belongs to
  * @addr[ETH_ALEN]: station's MAC address
  * @sta_id: index of station in uCode's station table
  * @modify_mask: STA_MODIFY_*, selects which parameters to modify vs. leave
  *	alone. 1 - modify, 0 - don't change.
- * @key: look at %iwl_mvm_keyinfo
  * @station_flags: look at %iwl_sta_flags
  * @station_flags_msk: what of %station_flags have changed
- * @tid_disable_tx: is tid BIT(tid) enabled for Tx. Clear BIT(x) to enable
- *	AMPDU for tid x. Set %STA_MODIFY_TID_DISABLE_TX to change this field.
  * @add_immediate_ba_tid: tid for which to add block-ack support (Rx)
  *	Set %STA_MODIFY_ADD_BA_TID to use this field, and also set
  *	add_immediate_ba_ssn.
@@ -294,40 +291,7 @@ struct iwl_mvm_keyinfo {
  * ADD_STA sets up the table entry for one station, either creating a new
  * entry, or modifying a pre-existing one.
  */
-struct iwl_mvm_add_sta_cmd_v5 {
-	u8 add_modify;
-	u8 unicast_tx_key_id;
-	u8 multicast_tx_key_id;
-	u8 reserved1;
-	__le32 mac_id_n_color;
-	u8 addr[ETH_ALEN];
-	__le16 reserved2;
-	u8 sta_id;
-	u8 modify_mask;
-	__le16 reserved3;
-	struct iwl_mvm_keyinfo key;
-	__le32 station_flags;
-	__le32 station_flags_msk;
-	__le16 tid_disable_tx;
-	__le16 reserved4;
-	u8 add_immediate_ba_tid;
-	u8 remove_immediate_ba_tid;
-	__le16 add_immediate_ba_ssn;
-	__le16 sleep_tx_count;
-	__le16 sleep_state_flags;
-	__le16 assoc_id;
-	__le16 beamform_flags;
-	__le32 tfd_queue_msk;
-} __packed; /* ADD_STA_CMD_API_S_VER_5 */
-
-/**
- * struct iwl_mvm_add_sta_cmd_v7 - Add / modify a station
- * VER_7 of this command is quite similar to VER_5 except
- * exclusion of all fields related to the security key installation.
- * It only differs from VER_6 by the "awake_acs" field that is
- * reserved and ignored in VER_6.
- */
-struct iwl_mvm_add_sta_cmd_v7 {
+struct iwl_mvm_add_sta_cmd {
 	u8 add_modify;
 	u8 awake_acs;
 	__le16 tid_disable_tx;
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-tx.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-tx.h
index 8e122f3a7a7..6cc5f52b807 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-tx.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-tx.h
@@ -482,7 +482,8 @@ struct iwl_mvm_tx_resp {
 	u8 pa_integ_res_b[3];
 	u8 pa_integ_res_c[3];
 	__le16 measurement_req_id;
-	__le16 reserved;
+	u8 reduced_tpc;
+	u8 reserved;
 
 	__le32 tfd_info;
 	__le16 seq_ctl;
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
index 6e75b52588d..309a9b9a94f 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api.h
@@ -71,6 +71,7 @@
 #include "fw-api-power.h"
 #include "fw-api-d3.h"
 #include "fw-api-coex.h"
+#include "fw-api-scan.h"
 
 /* maximal number of Tx queues in any platform */
 #define IWL_MVM_MAX_QUEUES	20
@@ -604,52 +605,7 @@ enum {
 	TE_V1_NOTIF_INTERNAL_FRAG_END = BIT(7),
 }; /* MAC_EVENT_ACTION_API_E_VER_2 */
 
-
-/**
- * struct iwl_time_event_cmd_api_v1 - configuring Time Events
- * with struct MAC_TIME_EVENT_DATA_API_S_VER_1 (see also
- * with version 2. determined by IWL_UCODE_TLV_FLAGS)
- * ( TIME_EVENT_CMD = 0x29 )
- * @id_and_color: ID and color of the relevant MAC
- * @action: action to perform, one of FW_CTXT_ACTION_*
- * @id: this field has two meanings, depending on the action:
- *	If the action is ADD, then it means the type of event to add.
- *	For all other actions it is the unique event ID assigned when the
- *	event was added by the FW.
- * @apply_time: When to start the Time Event (in GP2)
- * @max_delay: maximum delay to event's start (apply time), in TU
- * @depends_on: the unique ID of the event we depend on (if any)
- * @interval: interval between repetitions, in TU
- * @interval_reciprocal: 2^32 / interval
- * @duration: duration of event in TU
- * @repeat: how many repetitions to do, can be TE_REPEAT_ENDLESS
- * @dep_policy: one of TE_V1_INDEPENDENT, TE_V1_DEP_OTHER, TE_V1_DEP_TSF
- *	and TE_V1_EVENT_SOCIOPATHIC
- * @is_present: 0 or 1, are we present or absent during the Time Event
- * @max_frags: maximal number of fragments the Time Event can be divided to
- * @notify: notifications using TE_V1_NOTIF_* (whom to notify when)
- */
-struct iwl_time_event_cmd_v1 {
-	/* COMMON_INDEX_HDR_API_S_VER_1 */
-	__le32 id_and_color;
-	__le32 action;
-	__le32 id;
-	/* MAC_TIME_EVENT_DATA_API_S_VER_1 */
-	__le32 apply_time;
-	__le32 max_delay;
-	__le32 dep_policy;
-	__le32 depends_on;
-	__le32 is_present;
-	__le32 max_frags;
-	__le32 interval;
-	__le32 interval_reciprocal;
-	__le32 duration;
-	__le32 repeat;
-	__le32 notify;
-} __packed; /* MAC_TIME_EVENT_CMD_API_S_VER_1 */
-
-
-/* Time event - defines for command API v2 */
+/* Time event - defines for command API */
 
 /*
  * @TE_V2_FRAG_NONE: fragmentation of the time event is NOT allowed.
@@ -680,7 +636,7 @@ enum {
 #define TE_V2_PLACEMENT_POS	12
 #define TE_V2_ABSENCE_POS	15
 
-/* Time event policy values (for time event cmd api v2)
+/* Time event policy values
  * A notification (both event and fragment) includes a status indicating weather
  * the FW was able to schedule the event or not. For fragment start/end
  * notification the status is always success. There is no start/end fragment
@@ -727,7 +683,7 @@ enum {
 };
 
 /**
- * struct iwl_time_event_cmd_api_v2 - configuring Time Events
+ * struct iwl_time_event_cmd_api - configuring Time Events
  * with struct MAC_TIME_EVENT_DATA_API_S_VER_2 (see also
  * with version 1. determined by IWL_UCODE_TLV_FLAGS)
  * ( TIME_EVENT_CMD = 0x29 )
@@ -750,7 +706,7 @@ enum {
  *	TE_EVENT_SOCIOPATHIC
  *	using TE_ABSENCE and using TE_NOTIF_*
  */
-struct iwl_time_event_cmd_v2 {
+struct iwl_time_event_cmd {
 	/* COMMON_INDEX_HDR_API_S_VER_1 */
 	__le32 id_and_color;
 	__le32 action;
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw.c b/drivers/net/wireless/iwlwifi/mvm/fw.c
index 7ce20062f32..883e702152d 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/iwlwifi/mvm/fw.c
@@ -99,7 +99,7 @@ static int iwl_send_tx_ant_cfg(struct iwl_mvm *mvm, u8 valid_tx_ant)
 	};
 
 	IWL_DEBUG_FW(mvm, "select valid tx ant: %u\n", valid_tx_ant);
-	return iwl_mvm_send_cmd_pdu(mvm, TX_ANT_CONFIGURATION_CMD, CMD_SYNC,
+	return iwl_mvm_send_cmd_pdu(mvm, TX_ANT_CONFIGURATION_CMD, 0,
 				    sizeof(tx_ant_cmd), &tx_ant_cmd);
 }
 
@@ -137,6 +137,8 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
 		alive_data->scd_base_addr = le32_to_cpu(palive2->scd_base_ptr);
 		mvm->umac_error_event_table =
 			le32_to_cpu(palive2->error_info_addr);
+		mvm->sf_space.addr = le32_to_cpu(palive2->st_fwrd_addr);
+		mvm->sf_space.size = le32_to_cpu(palive2->st_fwrd_size);
 
 		alive_data->valid = le16_to_cpu(palive2->status) ==
 				    IWL_ALIVE_STATUS_OK;
@@ -180,6 +182,7 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	int ret, i;
 	enum iwl_ucode_type old_type = mvm->cur_ucode;
 	static const u8 alive_cmd[] = { MVM_ALIVE };
+	struct iwl_sf_region st_fwrd_space;
 
 	fw = iwl_get_ucode_image(mvm, ucode_type);
 	if (WARN_ON(!fw))
@@ -215,6 +218,14 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 		return -EIO;
 	}
 
+	/*
+	 * update the sdio allocation according to the pointer we get in the
+	 * alive notification.
+	 */
+	st_fwrd_space.addr = mvm->sf_space.addr;
+	st_fwrd_space.size = mvm->sf_space.size;
+	ret = iwl_trans_update_sf(mvm->trans, &st_fwrd_space);
+
 	iwl_trans_fw_alive(mvm->trans, alive_data.scd_base_addr);
 
 	/*
@@ -256,7 +267,7 @@ static int iwl_send_phy_cfg_cmd(struct iwl_mvm *mvm)
 	IWL_DEBUG_INFO(mvm, "Sending Phy CFG command: 0x%x\n",
 		       phy_cfg_cmd.phy_cfg);
 
-	return iwl_mvm_send_cmd_pdu(mvm, PHY_CONFIGURATION_CMD, CMD_SYNC,
+	return iwl_mvm_send_cmd_pdu(mvm, PHY_CONFIGURATION_CMD, 0,
 				    sizeof(phy_cfg_cmd), &phy_cfg_cmd);
 }
 
@@ -288,14 +299,14 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
 		goto error;
 	}
 
-	ret = iwl_send_bt_prio_tbl(mvm);
+	ret = iwl_send_bt_init_conf(mvm);
 	if (ret)
 		goto error;
 
 	/* Read the NVM only at driver load time, no need to do this twice */
 	if (read_nvm) {
 		/* Read nvm */
-		ret = iwl_nvm_init(mvm);
+		ret = iwl_nvm_init(mvm, true);
 		if (ret) {
 			IWL_ERR(mvm, "Failed to read NVM: %d\n", ret);
 			goto error;
@@ -303,7 +314,7 @@ int iwl_run_init_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
 	}
 
 	/* In case we read the NVM from external file, load it to the NIC */
-	if (iwlwifi_mod_params.nvm_file)
+	if (mvm->nvm_file_name)
 		iwl_mvm_load_nvm_to_nic(mvm);
 
 	ret = iwl_nvm_check_version(mvm->nvm_data, mvm->trans);
@@ -424,10 +435,6 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	if (ret)
 		goto error;
 
-	ret = iwl_send_bt_prio_tbl(mvm);
-	if (ret)
-		goto error;
-
 	ret = iwl_send_bt_init_conf(mvm);
 	if (ret)
 		goto error;
@@ -468,12 +475,6 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	/* Initialize tx backoffs to the minimal possible */
 	iwl_mvm_tt_tx_backoff(mvm, 0);
 
-	if (!(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_PM_CMD_SUPPORT)) {
-		ret = iwl_power_legacy_set_cam_mode(mvm);
-		if (ret)
-			goto error;
-	}
-
 	ret = iwl_mvm_power_update_device(mvm);
 	if (ret)
 		goto error;
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
index 9ccec10bba1..8b79081d488 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac-ctxt.c
@@ -667,13 +667,9 @@ static void iwl_mvm_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 	if (vif->bss_conf.qos)
 		cmd->qos_flags |= cpu_to_le32(MAC_QOS_FLG_UPDATE_EDCA);
 
-	/* Don't use cts to self as the fw doesn't support it currently. */
-	if (vif->bss_conf.use_cts_prot) {
+	if (vif->bss_conf.use_cts_prot)
 		cmd->protection_flags |= cpu_to_le32(MAC_PROT_FLG_TGG_PROTECT);
-		if (IWL_UCODE_API(mvm->fw->ucode_ver) >= 8)
-			cmd->protection_flags |=
-				cpu_to_le32(MAC_PROT_FLG_SELF_CTS_EN);
-	}
+
 	IWL_DEBUG_RATE(mvm, "use_cts_prot %d, ht_operation_mode %d\n",
 		       vif->bss_conf.use_cts_prot,
 		       vif->bss_conf.ht_operation_mode);
@@ -688,7 +684,7 @@ static void iwl_mvm_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 static int iwl_mvm_mac_ctxt_send_cmd(struct iwl_mvm *mvm,
 				     struct iwl_mac_ctx_cmd *cmd)
 {
-	int ret = iwl_mvm_send_cmd_pdu(mvm, MAC_CONTEXT_CMD, CMD_SYNC,
+	int ret = iwl_mvm_send_cmd_pdu(mvm, MAC_CONTEXT_CMD, 0,
 				       sizeof(*cmd), cmd);
 	if (ret)
 		IWL_ERR(mvm, "Failed to send MAC context (action:%d): %d\n",
@@ -696,19 +692,39 @@ static int iwl_mvm_mac_ctxt_send_cmd(struct iwl_mvm *mvm,
 	return ret;
 }
 
-/*
- * Fill the specific data for mac context of type station or p2p client
- */
-static void iwl_mvm_mac_ctxt_cmd_fill_sta(struct iwl_mvm *mvm,
-					  struct ieee80211_vif *vif,
-					  struct iwl_mac_data_sta *ctxt_sta,
-					  bool force_assoc_off)
+static int iwl_mvm_mac_ctxt_cmd_sta(struct iwl_mvm *mvm,
+				    struct ieee80211_vif *vif,
+				    u32 action, bool force_assoc_off)
 {
+	struct iwl_mac_ctx_cmd cmd = {};
+	struct iwl_mac_data_sta *ctxt_sta;
+
+	WARN_ON(vif->type != NL80211_IFTYPE_STATION);
+
+	/* Fill the common data for all mac context types */
+	iwl_mvm_mac_ctxt_cmd_common(mvm, vif, &cmd, action);
+
+	if (vif->p2p) {
+		struct ieee80211_p2p_noa_attr *noa =
+			&vif->bss_conf.p2p_noa_attr;
+
+		cmd.p2p_sta.ctwin = cpu_to_le32(noa->oppps_ctwindow &
+					IEEE80211_P2P_OPPPS_CTWINDOW_MASK);
+		ctxt_sta = &cmd.p2p_sta.sta;
+	} else {
+		ctxt_sta = &cmd.sta;
+	}
+
 	/* We need the dtim_period to set the MAC as associated */
 	if (vif->bss_conf.assoc && vif->bss_conf.dtim_period &&
 	    !force_assoc_off) {
 		u32 dtim_offs;
 
+		/* Allow beacons to pass through as long as we are not
+		 * associated, or we do not have dtim period information.
+		 */
+		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_BEACON);
+
 		/*
 		 * The DTIM count counts down, so when it is N that means N
 		 * more beacon intervals happen until the DTIM TBTT. Therefore
@@ -755,51 +771,6 @@ static void iwl_mvm_mac_ctxt_cmd_fill_sta(struct iwl_mvm *mvm,
 
 	ctxt_sta->listen_interval = cpu_to_le32(mvm->hw->conf.listen_interval);
 	ctxt_sta->assoc_id = cpu_to_le32(vif->bss_conf.aid);
-}
-
-static int iwl_mvm_mac_ctxt_cmd_station(struct iwl_mvm *mvm,
-					struct ieee80211_vif *vif,
-					u32 action)
-{
-	struct iwl_mac_ctx_cmd cmd = {};
-
-	WARN_ON(vif->type != NL80211_IFTYPE_STATION || vif->p2p);
-
-	/* Fill the common data for all mac context types */
-	iwl_mvm_mac_ctxt_cmd_common(mvm, vif, &cmd, action);
-
-	/* Allow beacons to pass through as long as we are not associated,or we
-	 * do not have dtim period information */
-	if (!vif->bss_conf.assoc || !vif->bss_conf.dtim_period)
-		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_BEACON);
-	else
-		cmd.filter_flags &= ~cpu_to_le32(MAC_FILTER_IN_BEACON);
-
-	/* Fill the data specific for station mode */
-	iwl_mvm_mac_ctxt_cmd_fill_sta(mvm, vif, &cmd.sta,
-				      action == FW_CTXT_ACTION_ADD);
-
-	return iwl_mvm_mac_ctxt_send_cmd(mvm, &cmd);
-}
-
-static int iwl_mvm_mac_ctxt_cmd_p2p_client(struct iwl_mvm *mvm,
-					   struct ieee80211_vif *vif,
-					   u32 action)
-{
-	struct iwl_mac_ctx_cmd cmd = {};
-	struct ieee80211_p2p_noa_attr *noa = &vif->bss_conf.p2p_noa_attr;
-
-	WARN_ON(vif->type != NL80211_IFTYPE_STATION || !vif->p2p);
-
-	/* Fill the common data for all mac context types */
-	iwl_mvm_mac_ctxt_cmd_common(mvm, vif, &cmd, action);
-
-	/* Fill the data specific for station mode */
-	iwl_mvm_mac_ctxt_cmd_fill_sta(mvm, vif, &cmd.p2p_sta.sta,
-				      action == FW_CTXT_ACTION_ADD);
-
-	cmd.p2p_sta.ctwin = cpu_to_le32(noa->oppps_ctwindow &
-					IEEE80211_P2P_OPPPS_CTWINDOW_MASK);
 
 	return iwl_mvm_mac_ctxt_send_cmd(mvm, &cmd);
 }
@@ -1101,8 +1072,12 @@ static int iwl_mvm_mac_ctxt_cmd_ap(struct iwl_mvm *mvm,
 	/* Fill the common data for all mac context types */
 	iwl_mvm_mac_ctxt_cmd_common(mvm, vif, &cmd, action);
 
-	/* Also enable probe requests to pass */
-	cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_PROBE_REQUEST);
+	/*
+	 * pass probe requests and beacons from other APs (needed
+	 * for ht protection)
+	 */
+	cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_PROBE_REQUEST |
+					MAC_FILTER_IN_BEACON);
 
 	/* Fill the data specific for ap mode */
 	iwl_mvm_mac_ctxt_cmd_fill_ap(mvm, vif, &cmd.ap,
@@ -1123,6 +1098,13 @@ static int iwl_mvm_mac_ctxt_cmd_go(struct iwl_mvm *mvm,
 	/* Fill the common data for all mac context types */
 	iwl_mvm_mac_ctxt_cmd_common(mvm, vif, &cmd, action);
 
+	/*
+	 * pass probe requests and beacons from other APs (needed
+	 * for ht protection)
+	 */
+	cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_PROBE_REQUEST |
+					MAC_FILTER_IN_BEACON);
+
 	/* Fill the data specific for GO mode */
 	iwl_mvm_mac_ctxt_cmd_fill_ap(mvm, vif, &cmd.go.ap,
 				     action == FW_CTXT_ACTION_ADD);
@@ -1137,16 +1119,12 @@ static int iwl_mvm_mac_ctxt_cmd_go(struct iwl_mvm *mvm,
 }
 
 static int iwl_mvm_mac_ctx_send(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-				u32 action)
+				u32 action, bool force_assoc_off)
 {
 	switch (vif->type) {
 	case NL80211_IFTYPE_STATION:
-		if (!vif->p2p)
-			return iwl_mvm_mac_ctxt_cmd_station(mvm, vif,
-							    action);
-		else
-			return iwl_mvm_mac_ctxt_cmd_p2p_client(mvm, vif,
-							       action);
+		return iwl_mvm_mac_ctxt_cmd_sta(mvm, vif, action,
+						force_assoc_off);
 		break;
 	case NL80211_IFTYPE_AP:
 		if (!vif->p2p)
@@ -1176,7 +1154,8 @@ int iwl_mvm_mac_ctxt_add(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		      vif->addr, ieee80211_vif_type_p2p(vif)))
 		return -EIO;
 
-	ret = iwl_mvm_mac_ctx_send(mvm, vif, FW_CTXT_ACTION_ADD);
+	ret = iwl_mvm_mac_ctx_send(mvm, vif, FW_CTXT_ACTION_ADD,
+				   true);
 	if (ret)
 		return ret;
 
@@ -1187,7 +1166,8 @@ int iwl_mvm_mac_ctxt_add(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	return 0;
 }
 
-int iwl_mvm_mac_ctxt_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
+int iwl_mvm_mac_ctxt_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			     bool force_assoc_off)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 
@@ -1195,7 +1175,8 @@ int iwl_mvm_mac_ctxt_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		      vif->addr, ieee80211_vif_type_p2p(vif)))
 		return -EIO;
 
-	return iwl_mvm_mac_ctx_send(mvm, vif, FW_CTXT_ACTION_MODIFY);
+	return iwl_mvm_mac_ctx_send(mvm, vif, FW_CTXT_ACTION_MODIFY,
+				    force_assoc_off);
 }
 
 int iwl_mvm_mac_ctxt_remove(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
@@ -1214,7 +1195,7 @@ int iwl_mvm_mac_ctxt_remove(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 							   mvmvif->color));
 	cmd.action = cpu_to_le32(FW_CTXT_ACTION_REMOVE);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, MAC_CONTEXT_CMD, CMD_SYNC,
+	ret = iwl_mvm_send_cmd_pdu(mvm, MAC_CONTEXT_CMD, 0,
 				   sizeof(cmd), &cmd);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to remove MAC context: %d\n", ret);
@@ -1240,11 +1221,23 @@ int iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm,
 	u32 rate __maybe_unused =
 		le32_to_cpu(beacon->beacon_notify_hdr.initial_rate);
 
+	lockdep_assert_held(&mvm->mutex);
+
 	IWL_DEBUG_RX(mvm, "beacon status %#x retries:%d tsf:0x%16llX rate:%d\n",
 		     status & TX_STATUS_MSK,
 		     beacon->beacon_notify_hdr.failure_frame,
 		     le64_to_cpu(beacon->tsf),
 		     rate);
+
+	if (unlikely(mvm->csa_vif && mvm->csa_vif->csa_active)) {
+		if (!ieee80211_csa_is_complete(mvm->csa_vif)) {
+			iwl_mvm_mac_ctxt_beacon_changed(mvm, mvm->csa_vif);
+		} else {
+			ieee80211_csa_finish(mvm->csa_vif);
+			mvm->csa_vif = NULL;
+		}
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index 8735ef1f44a..98556d03c1e 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -295,7 +295,9 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	    !iwlwifi_mod_params.sw_crypto)
 		hw->flags |= IEEE80211_HW_MFP_CAPABLE;
 
-	if (0 && mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT) {
+	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT &&
+	    IWL_UCODE_API(mvm->fw->ucode_ver) >= 9 &&
+	    !iwlwifi_mod_params.uapsd_disable) {
 		hw->flags |= IEEE80211_HW_SUPPORTS_UAPSD;
 		hw->uapsd_queues = IWL_UAPSD_AC_INFO;
 		hw->uapsd_max_sp_len = IWL_UAPSD_MAX_SP;
@@ -309,11 +311,8 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 		BIT(NL80211_IFTYPE_P2P_CLIENT) |
 		BIT(NL80211_IFTYPE_AP) |
 		BIT(NL80211_IFTYPE_P2P_GO) |
-		BIT(NL80211_IFTYPE_P2P_DEVICE);
-
-	/* IBSS has bugs in older versions */
-	if (IWL_UCODE_API(mvm->fw->ucode_ver) >= 8)
-		hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_ADHOC);
+		BIT(NL80211_IFTYPE_P2P_DEVICE) |
+		BIT(NL80211_IFTYPE_ADHOC);
 
 	hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
 	hw->wiphy->regulatory_flags |= REGULATORY_CUSTOM_REG |
@@ -322,6 +321,9 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_GO_UAPSD)
 		hw->wiphy->flags |= WIPHY_FLAG_AP_UAPSD;
 
+	if (mvm->fw->ucode_capa.api[0] & IWL_UCODE_TLV_API_CSA_FLOW)
+		hw->wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH;
+
 	hw->wiphy->iface_combinations = iwl_mvm_iface_combinations;
 	hw->wiphy->n_iface_combinations =
 		ARRAY_SIZE(iwl_mvm_iface_combinations);
@@ -365,14 +367,11 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	else
 		hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_SCHED_SCAN) {
-		hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_SCHED_SCAN;
-		hw->wiphy->max_sched_scan_ssids = PROBE_OPTION_MAX;
-		hw->wiphy->max_match_sets = IWL_SCAN_MAX_PROFILES;
-		/* we create the 802.11 header and zero length SSID IE. */
-		hw->wiphy->max_sched_scan_ie_len =
-					SCAN_OFFLOAD_PROBE_REQ_SIZE - 24 - 2;
-	}
+	hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_SCHED_SCAN;
+	hw->wiphy->max_sched_scan_ssids = PROBE_OPTION_MAX;
+	hw->wiphy->max_match_sets = IWL_SCAN_MAX_PROFILES;
+	/* we create the 802.11 header and zero length SSID IE. */
+	hw->wiphy->max_sched_scan_ie_len = SCAN_OFFLOAD_PROBE_REQ_SIZE - 24 - 2;
 
 	hw->wiphy->features |= NL80211_FEATURE_P2P_GO_CTWIN |
 			       NL80211_FEATURE_P2P_GO_OPPPS;
@@ -386,7 +385,11 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	}
 
 #ifdef CONFIG_PM_SLEEP
-	if (mvm->fw->img[IWL_UCODE_WOWLAN].sec[0].len &&
+	if (iwl_mvm_is_d0i3_supported(mvm) &&
+	    device_can_wakeup(mvm->trans->dev)) {
+		mvm->wowlan.flags = WIPHY_WOWLAN_ANY;
+		hw->wiphy->wowlan = &mvm->wowlan;
+	} else if (mvm->fw->img[IWL_UCODE_WOWLAN].sec[0].len &&
 	    mvm->trans->ops->d3_suspend &&
 	    mvm->trans->ops->d3_resume &&
 	    device_can_wakeup(mvm->trans->dev)) {
@@ -540,13 +543,22 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 		return -EACCES;
 
 	/* return from D0i3 before starting a new Tx aggregation */
-	if (action == IEEE80211_AMPDU_TX_START) {
+	switch (action) {
+	case IEEE80211_AMPDU_TX_START:
+	case IEEE80211_AMPDU_TX_STOP_CONT:
+	case IEEE80211_AMPDU_TX_STOP_FLUSH:
+	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
+	case IEEE80211_AMPDU_TX_OPERATIONAL:
 		iwl_mvm_ref(mvm, IWL_MVM_REF_TX_AGG);
 		tx_agg_ref = true;
 
 		/*
-		 * wait synchronously until D0i3 exit to get the correct
-		 * sequence number for the tid
+		 * for tx start, wait synchronously until D0i3 exit to
+		 * get the correct sequence number for the tid.
+		 * additionally, some other ampdu actions use direct
+		 * target access, which is not handled automatically
+		 * by the trans layer (unlike commands), so wait for
+		 * d0i3 exit in these cases as well.
 		 */
 		if (!wait_event_timeout(mvm->d0i3_exit_waitq,
 			  !test_bit(IWL_MVM_STATUS_IN_D0I3, &mvm->status), HZ)) {
@@ -554,6 +566,9 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 			iwl_mvm_unref(mvm, IWL_MVM_REF_TX_AGG);
 			return -EIO;
 		}
+		break;
+	default:
+		break;
 	}
 
 	mutex_lock(&mvm->mutex);
@@ -758,7 +773,7 @@ static int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		.pwr_restriction = cpu_to_le16(tx_power),
 	};
 
-	return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, CMD_SYNC,
+	return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0,
 				    sizeof(reduce_txpwr_cmd),
 				    &reduce_txpwr_cmd);
 }
@@ -817,18 +832,17 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw,
 	if (ret)
 		goto out_release;
 
-	ret = iwl_mvm_power_update_mac(mvm, vif);
+	ret = iwl_mvm_power_update_mac(mvm);
 	if (ret)
 		goto out_release;
 
 	/* beacon filtering */
-	ret = iwl_mvm_disable_beacon_filter(mvm, vif, CMD_SYNC);
+	ret = iwl_mvm_disable_beacon_filter(mvm, vif, 0);
 	if (ret)
 		goto out_remove_mac;
 
-	if (!mvm->bf_allowed_vif && false &&
-	    vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
-	    mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_BF_UPDATED){
+	if (!mvm->bf_allowed_vif &&
+	    vif->type == NL80211_IFTYPE_STATION && !vif->p2p) {
 		mvm->bf_allowed_vif = mvmvif;
 		vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER |
 				     IEEE80211_VIF_SUPPORTS_CQM_RSSI;
@@ -969,7 +983,7 @@ static void iwl_mvm_mac_remove_interface(struct ieee80211_hw *hw,
 	if (mvm->vif_count && vif->type != NL80211_IFTYPE_P2P_DEVICE)
 		mvm->vif_count--;
 
-	iwl_mvm_power_update_mac(mvm, vif);
+	iwl_mvm_power_update_mac(mvm);
 	iwl_mvm_mac_ctxt_remove(mvm, vif);
 
 out_release:
@@ -1145,8 +1159,12 @@ static void iwl_mvm_bcast_filter_iterator(void *_data, u8 *mac,
 
 	bcast_mac = &cmd->macs[mvmvif->id];
 
-	/* enable filtering only for associated stations */
-	if (vif->type != NL80211_IFTYPE_STATION || !vif->bss_conf.assoc)
+	/*
+	 * enable filtering only for associated stations, but not for P2P
+	 * Clients
+	 */
+	if (vif->type != NL80211_IFTYPE_STATION || vif->p2p ||
+	    !vif->bss_conf.assoc)
 		return;
 
 	bcast_mac->default_discard = 1;
@@ -1226,7 +1244,7 @@ static int iwl_mvm_configure_bcast_filter(struct iwl_mvm *mvm,
 	if (!iwl_mvm_bcast_filter_build_cmd(mvm, &cmd))
 		return 0;
 
-	return iwl_mvm_send_cmd_pdu(mvm, BCAST_FILTER_CMD, CMD_SYNC,
+	return iwl_mvm_send_cmd_pdu(mvm, BCAST_FILTER_CMD, 0,
 				    sizeof(cmd), &cmd);
 }
 #else
@@ -1253,7 +1271,7 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 	if (changes & BSS_CHANGED_ASSOC && bss_conf->assoc)
 		iwl_mvm_mac_ctxt_recalc_tsf_id(mvm, vif);
 
-	ret = iwl_mvm_mac_ctxt_changed(mvm, vif);
+	ret = iwl_mvm_mac_ctxt_changed(mvm, vif, false);
 	if (ret)
 		IWL_ERR(mvm, "failed to update MAC %pM\n", vif->addr);
 
@@ -1333,10 +1351,10 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 		iwl_mvm_remove_time_event(mvm, mvmvif,
 					  &mvmvif->time_event_data);
 		iwl_mvm_sf_update(mvm, vif, false);
-		WARN_ON(iwl_mvm_enable_beacon_filter(mvm, vif, CMD_SYNC));
+		WARN_ON(iwl_mvm_enable_beacon_filter(mvm, vif, 0));
 	} else if (changes & (BSS_CHANGED_PS | BSS_CHANGED_P2P_PS |
 			      BSS_CHANGED_QOS)) {
-		ret = iwl_mvm_power_update_mac(mvm, vif);
+		ret = iwl_mvm_power_update_mac(mvm);
 		if (ret)
 			IWL_ERR(mvm, "failed to update power mode\n");
 	}
@@ -1347,16 +1365,19 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 	}
 
 	if (changes & BSS_CHANGED_CQM) {
-		IWL_DEBUG_MAC80211(mvm, "cqm info_changed");
+		IWL_DEBUG_MAC80211(mvm, "cqm info_changed\n");
 		/* reset cqm events tracking */
 		mvmvif->bf_data.last_cqm_event = 0;
-		ret = iwl_mvm_update_beacon_filter(mvm, vif, false, CMD_SYNC);
-		if (ret)
-			IWL_ERR(mvm, "failed to update CQM thresholds\n");
+		if (mvmvif->bf_data.bf_enabled) {
+			ret = iwl_mvm_enable_beacon_filter(mvm, vif, 0);
+			if (ret)
+				IWL_ERR(mvm,
+					"failed to update CQM thresholds\n");
+		}
 	}
 
 	if (changes & BSS_CHANGED_ARP_FILTER) {
-		IWL_DEBUG_MAC80211(mvm, "arp filter changed");
+		IWL_DEBUG_MAC80211(mvm, "arp filter changed\n");
 		iwl_mvm_configure_bcast_filter(mvm, vif);
 	}
 }
@@ -1402,7 +1423,7 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw,
 	mvmvif->ap_ibss_active = true;
 
 	/* power updated needs to be done before quotas */
-	iwl_mvm_power_update_mac(mvm, vif);
+	iwl_mvm_power_update_mac(mvm);
 
 	ret = iwl_mvm_update_quotas(mvm, vif);
 	if (ret)
@@ -1410,7 +1431,7 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw,
 
 	/* Need to update the P2P Device MAC (only GO, IBSS is single vif) */
 	if (vif->p2p && mvm->p2p_device_vif)
-		iwl_mvm_mac_ctxt_changed(mvm, mvm->p2p_device_vif);
+		iwl_mvm_mac_ctxt_changed(mvm, mvm->p2p_device_vif, false);
 
 	iwl_mvm_ref(mvm, IWL_MVM_REF_AP_IBSS);
 
@@ -1420,7 +1441,7 @@ static int iwl_mvm_start_ap_ibss(struct ieee80211_hw *hw,
 	return 0;
 
 out_quota_failed:
-	iwl_mvm_power_update_mac(mvm, vif);
+	iwl_mvm_power_update_mac(mvm);
 	mvmvif->ap_ibss_active = false;
 	iwl_mvm_send_rm_bcast_sta(mvm, &mvmvif->bcast_sta);
 out_unbind:
@@ -1450,13 +1471,13 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw,
 
 	/* Need to update the P2P Device MAC (only GO, IBSS is single vif) */
 	if (vif->p2p && mvm->p2p_device_vif)
-		iwl_mvm_mac_ctxt_changed(mvm, mvm->p2p_device_vif);
+		iwl_mvm_mac_ctxt_changed(mvm, mvm->p2p_device_vif, false);
 
 	iwl_mvm_update_quotas(mvm, NULL);
 	iwl_mvm_send_rm_bcast_sta(mvm, &mvmvif->bcast_sta);
 	iwl_mvm_binding_remove_vif(mvm, vif);
 
-	iwl_mvm_power_update_mac(mvm, vif);
+	iwl_mvm_power_update_mac(mvm);
 
 	iwl_mvm_mac_ctxt_remove(mvm, vif);
 
@@ -1477,7 +1498,7 @@ iwl_mvm_bss_info_changed_ap_ibss(struct iwl_mvm *mvm,
 
 	if (changes & (BSS_CHANGED_ERP_CTS_PROT | BSS_CHANGED_HT |
 		       BSS_CHANGED_BANDWIDTH) &&
-	    iwl_mvm_mac_ctxt_changed(mvm, vif))
+	    iwl_mvm_mac_ctxt_changed(mvm, vif, false))
 		IWL_ERR(mvm, "failed to update MAC %pM\n", vif->addr);
 
 	/* Need to send a new beacon template to the FW */
@@ -1495,6 +1516,9 @@ static void iwl_mvm_bss_info_changed(struct ieee80211_hw *hw,
 
 	mutex_lock(&mvm->mutex);
 
+	if (changes & BSS_CHANGED_IDLE && !bss_conf->idle)
+		iwl_mvm_sched_scan_stop(mvm, true);
+
 	switch (vif->type) {
 	case NL80211_IFTYPE_STATION:
 		iwl_mvm_bss_info_changed_station(mvm, vif, bss_conf, changes);
@@ -1525,7 +1549,7 @@ static int iwl_mvm_mac_hw_scan(struct ieee80211_hw *hw,
 
 	switch (mvm->scan_status) {
 	case IWL_MVM_SCAN_SCHED:
-		ret = iwl_mvm_sched_scan_stop(mvm);
+		ret = iwl_mvm_sched_scan_stop(mvm, true);
 		if (ret) {
 			ret = -EBUSY;
 			goto out;
@@ -1697,6 +1721,11 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw,
 		ret = iwl_mvm_add_sta(mvm, vif, sta);
 	} else if (old_state == IEEE80211_STA_NONE &&
 		   new_state == IEEE80211_STA_AUTH) {
+		/*
+		 * EBS may be disabled due to previous failures reported by FW.
+		 * Reset EBS status here assuming environment has been changed.
+		 */
+		mvm->last_ebs_successful = true;
 		ret = 0;
 	} else if (old_state == IEEE80211_STA_AUTH &&
 		   new_state == IEEE80211_STA_ASSOC) {
@@ -1708,14 +1737,12 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw,
 	} else if (old_state == IEEE80211_STA_ASSOC &&
 		   new_state == IEEE80211_STA_AUTHORIZED) {
 		/* enable beacon filtering */
-		if (vif->bss_conf.dtim_period)
-			WARN_ON(iwl_mvm_enable_beacon_filter(mvm, vif,
-							     CMD_SYNC));
+		WARN_ON(iwl_mvm_enable_beacon_filter(mvm, vif, 0));
 		ret = 0;
 	} else if (old_state == IEEE80211_STA_AUTHORIZED &&
 		   new_state == IEEE80211_STA_ASSOC) {
 		/* disable beacon filtering */
-		WARN_ON(iwl_mvm_disable_beacon_filter(mvm, vif, CMD_SYNC));
+		WARN_ON(iwl_mvm_disable_beacon_filter(mvm, vif, 0));
 		ret = 0;
 	} else if (old_state == IEEE80211_STA_ASSOC &&
 		   new_state == IEEE80211_STA_AUTH) {
@@ -1772,7 +1799,7 @@ static int iwl_mvm_mac_conf_tx(struct ieee80211_hw *hw,
 		int ret;
 
 		mutex_lock(&mvm->mutex);
-		ret = iwl_mvm_mac_ctxt_changed(mvm, vif);
+		ret = iwl_mvm_mac_ctxt_changed(mvm, vif, false);
 		mutex_unlock(&mvm->mutex);
 		return ret;
 	}
@@ -1865,7 +1892,7 @@ static int iwl_mvm_mac_sched_scan_stop(struct ieee80211_hw *hw,
 	int ret;
 
 	mutex_lock(&mvm->mutex);
-	ret = iwl_mvm_sched_scan_stop(mvm);
+	ret = iwl_mvm_sched_scan_stop(mvm, false);
 	mutex_unlock(&mvm->mutex);
 	iwl_mvm_wait_for_async_handlers(mvm);
 
@@ -2161,10 +2188,10 @@ static void iwl_mvm_change_chanctx(struct ieee80211_hw *hw,
 		return;
 
 	mutex_lock(&mvm->mutex);
+	iwl_mvm_bt_coex_vif_change(mvm);
 	iwl_mvm_phy_ctxt_changed(mvm, phy_ctxt, &ctx->min_def,
 				 ctx->rx_chains_static,
 				 ctx->rx_chains_dynamic);
-	iwl_mvm_bt_coex_vif_change(mvm);
 	mutex_unlock(&mvm->mutex);
 }
 
@@ -2184,6 +2211,11 @@ static int iwl_mvm_assign_vif_chanctx(struct ieee80211_hw *hw,
 
 	switch (vif->type) {
 	case NL80211_IFTYPE_AP:
+		/* Unless it's a CSA flow we have nothing to do here */
+		if (vif->csa_active) {
+			mvmvif->ap_ibss_active = true;
+			break;
+		}
 	case NL80211_IFTYPE_ADHOC:
 		/*
 		 * The AP binding flow is handled as part of the start_ap flow
@@ -2207,7 +2239,7 @@ static int iwl_mvm_assign_vif_chanctx(struct ieee80211_hw *hw,
 	 * Power state must be updated before quotas,
 	 * otherwise fw will complain.
 	 */
-	iwl_mvm_power_update_mac(mvm, vif);
+	iwl_mvm_power_update_mac(mvm);
 
 	/* Setting the quota at this stage is only required for monitor
 	 * interfaces. For the other types, the bss_info changed flow
@@ -2220,11 +2252,17 @@ static int iwl_mvm_assign_vif_chanctx(struct ieee80211_hw *hw,
 			goto out_remove_binding;
 	}
 
+	/* Handle binding during CSA */
+	if (vif->type == NL80211_IFTYPE_AP) {
+		iwl_mvm_update_quotas(mvm, vif);
+		iwl_mvm_mac_ctxt_changed(mvm, vif, false);
+	}
+
 	goto out_unlock;
 
  out_remove_binding:
 	iwl_mvm_binding_remove_vif(mvm, vif);
-	iwl_mvm_power_update_mac(mvm, vif);
+	iwl_mvm_power_update_mac(mvm);
  out_unlock:
 	mutex_unlock(&mvm->mutex);
 	if (ret)
@@ -2244,22 +2282,29 @@ static void iwl_mvm_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	iwl_mvm_remove_time_event(mvm, mvmvif, &mvmvif->time_event_data);
 
 	switch (vif->type) {
-	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_ADHOC:
 		goto out_unlock;
 	case NL80211_IFTYPE_MONITOR:
 		mvmvif->monitor_active = false;
 		iwl_mvm_update_quotas(mvm, NULL);
 		break;
+	case NL80211_IFTYPE_AP:
+		/* This part is triggered only during CSA */
+		if (!vif->csa_active || !mvmvif->ap_ibss_active)
+			goto out_unlock;
+
+		mvmvif->ap_ibss_active = false;
+		iwl_mvm_update_quotas(mvm, NULL);
+		/*TODO: bt_coex notification here? */
 	default:
 		break;
 	}
 
 	iwl_mvm_binding_remove_vif(mvm, vif);
-	iwl_mvm_power_update_mac(mvm, vif);
 
 out_unlock:
 	mvmvif->phy_ctxt = NULL;
+	iwl_mvm_power_update_mac(mvm);
 	mutex_unlock(&mvm->mutex);
 }
 
@@ -2323,9 +2368,8 @@ static int __iwl_mvm_mac_testmode_cmd(struct iwl_mvm *mvm,
 			return -EINVAL;
 
 		if (nla_get_u32(tb[IWL_MVM_TM_ATTR_BEACON_FILTER_STATE]))
-			return iwl_mvm_enable_beacon_filter(mvm, vif,
-							    CMD_SYNC);
-		return iwl_mvm_disable_beacon_filter(mvm, vif, CMD_SYNC);
+			return iwl_mvm_enable_beacon_filter(mvm, vif, 0);
+		return iwl_mvm_disable_beacon_filter(mvm, vif, 0);
 	}
 
 	return -EOPNOTSUPP;
@@ -2346,6 +2390,53 @@ static int iwl_mvm_mac_testmode_cmd(struct ieee80211_hw *hw,
 }
 #endif
 
+static void iwl_mvm_channel_switch_beacon(struct ieee80211_hw *hw,
+					  struct ieee80211_vif *vif,
+					  struct cfg80211_chan_def *chandef)
+{
+	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+
+	mutex_lock(&mvm->mutex);
+	if (WARN(mvm->csa_vif && mvm->csa_vif->csa_active,
+		 "Another CSA is already in progress"))
+		goto out_unlock;
+
+	IWL_DEBUG_MAC80211(mvm, "CSA started to freq %d\n",
+			   chandef->center_freq1);
+	mvm->csa_vif = vif;
+
+out_unlock:
+	mutex_unlock(&mvm->mutex);
+}
+
+static void iwl_mvm_mac_flush(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif, u32 queues, bool drop)
+{
+	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+	struct iwl_mvm_vif *mvmvif;
+	struct iwl_mvm_sta *mvmsta;
+
+	if (!vif || vif->type != NL80211_IFTYPE_STATION)
+		return;
+
+	mutex_lock(&mvm->mutex);
+	mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	mvmsta = iwl_mvm_sta_from_staid_protected(mvm, mvmvif->ap_sta_id);
+
+	if (WARN_ON_ONCE(!mvmsta))
+		goto done;
+
+	if (drop) {
+		if (iwl_mvm_flush_tx_path(mvm, mvmsta->tfd_queue_msk, true))
+			IWL_ERR(mvm, "flush request fail\n");
+	} else {
+		iwl_trans_wait_tx_queue_empty(mvm->trans,
+					      mvmsta->tfd_queue_msk);
+	}
+done:
+	mutex_unlock(&mvm->mutex);
+}
+
 const struct ieee80211_ops iwl_mvm_hw_ops = {
 	.tx = iwl_mvm_mac_tx,
 	.ampdu_action = iwl_mvm_mac_ampdu_action,
@@ -2369,6 +2460,7 @@ const struct ieee80211_ops iwl_mvm_hw_ops = {
 	.sta_rc_update = iwl_mvm_sta_rc_update,
 	.conf_tx = iwl_mvm_mac_conf_tx,
 	.mgd_prepare_tx = iwl_mvm_mac_mgd_prepare_tx,
+	.flush = iwl_mvm_mac_flush,
 	.sched_scan_start = iwl_mvm_mac_sched_scan_start,
 	.sched_scan_stop = iwl_mvm_mac_sched_scan_stop,
 	.set_key = iwl_mvm_mac_set_key,
@@ -2388,6 +2480,8 @@ const struct ieee80211_ops iwl_mvm_hw_ops = {
 
 	.set_tim = iwl_mvm_set_tim,
 
+	.channel_switch_beacon = iwl_mvm_channel_switch_beacon,
+
 	CFG80211_TESTMODE_CMD(iwl_mvm_mac_testmode_cmd)
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h
index f1ec0986c3c..fcc6c29482d 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h
@@ -164,7 +164,6 @@ enum iwl_dbgfs_pm_mask {
 	MVM_DEBUGFS_PM_SKIP_DTIM_PERIODS = BIT(2),
 	MVM_DEBUGFS_PM_RX_DATA_TIMEOUT = BIT(3),
 	MVM_DEBUGFS_PM_TX_DATA_TIMEOUT = BIT(4),
-	MVM_DEBUGFS_PM_DISABLE_POWER_OFF = BIT(5),
 	MVM_DEBUGFS_PM_LPRX_ENA = BIT(6),
 	MVM_DEBUGFS_PM_LPRX_RSSI_THRESHOLD = BIT(7),
 	MVM_DEBUGFS_PM_SNOOZE_ENABLE = BIT(8),
@@ -177,7 +176,6 @@ struct iwl_dbgfs_pm {
 	u32 tx_data_timeout;
 	bool skip_over_dtim;
 	u8 skip_dtim_periods;
-	bool disable_power_off;
 	bool lprx_ena;
 	u32 lprx_rssi_threshold;
 	bool snooze_ena;
@@ -232,6 +230,7 @@ enum iwl_mvm_ref_type {
 	IWL_MVM_REF_USER,
 	IWL_MVM_REF_TX,
 	IWL_MVM_REF_TX_AGG,
+	IWL_MVM_REF_EXIT_WORK,
 
 	IWL_MVM_REF_COUNT,
 };
@@ -265,6 +264,7 @@ struct iwl_mvm_vif_bf_data {
  * @uploaded: indicates the MAC context has been added to the device
  * @ap_ibss_active: indicates that AP/IBSS is configured and that the interface
  *	should get quota etc.
+ * @pm_enabled - Indicate if MAC power management is allowed
  * @monitor_active: indicates that monitor context is configured, and that the
  *	interface should get quota etc.
  * @low_latency: indicates that this interface is in low-latency mode
@@ -283,6 +283,7 @@ struct iwl_mvm_vif {
 
 	bool uploaded;
 	bool ap_ibss_active;
+	bool pm_enabled;
 	bool monitor_active;
 	bool low_latency;
 	struct iwl_mvm_vif_bf_data bf_data;
@@ -451,6 +452,11 @@ struct iwl_mvm_frame_stats {
 	int last_frame_idx;
 };
 
+enum {
+	D0I3_DEFER_WAKEUP,
+	D0I3_PENDING_WAKEUP,
+};
+
 struct iwl_mvm {
 	/* for logger access */
 	struct device *dev;
@@ -484,6 +490,7 @@ struct iwl_mvm {
 	u32 log_event_table;
 	u32 umac_error_event_table;
 	bool support_umac_log;
+	struct iwl_sf_region sf_space;
 
 	u32 ampdu_ref;
 
@@ -495,6 +502,7 @@ struct iwl_mvm {
 	u8 queue_to_mac80211[IWL_MAX_HW_QUEUES];
 	atomic_t queue_stop_count[IWL_MAX_HW_QUEUES];
 
+	const char *nvm_file_name;
 	struct iwl_nvm_data *nvm_data;
 	/* NVM sections */
 	struct iwl_nvm_section nvm_sections[NVM_MAX_NUM_SECTIONS];
@@ -535,6 +543,8 @@ struct iwl_mvm {
 	/* Internal station */
 	struct iwl_mvm_int_sta aux_sta;
 
+	bool last_ebs_successful;
+
 	u8 scan_last_antenna_idx; /* to toggle TX between antennas */
 	u8 mgmt_last_antenna_idx;
 
@@ -578,8 +588,12 @@ struct iwl_mvm {
 	void *fw_error_dump;
 	void *fw_error_sram;
 	u32 fw_error_sram_len;
+	u32 *fw_error_rxf;
+	u32 fw_error_rxf_len;
 
+#ifdef CONFIG_IWLWIFI_LEDS
 	struct led_classdev led;
+#endif
 
 	struct ieee80211_vif *p2p_device_vif;
 
@@ -601,6 +615,9 @@ struct iwl_mvm {
 	bool d0i3_offloading;
 	struct work_struct d0i3_exit_work;
 	struct sk_buff_head d0i3_tx;
+	/* protect d0i3_suspend_flags */
+	struct mutex d0i3_suspend_mutex;
+	unsigned long d0i3_suspend_flags;
 	/* sync d0i3_tx queue and IWL_MVM_STATUS_IN_D0I3 status flag */
 	spinlock_t d0i3_tx_lock;
 	wait_queue_head_t d0i3_exit_waitq;
@@ -629,8 +646,8 @@ struct iwl_mvm {
 
 	/* Indicate if device power save is allowed */
 	bool ps_disabled;
-	/* Indicate if device power management is allowed */
-	bool pm_disabled;
+
+	struct ieee80211_vif *csa_vif;
 };
 
 /* Extract MVM priv from op_mode and _hw */
@@ -705,6 +722,7 @@ void iwl_mvm_dump_nic_error_log(struct iwl_mvm *mvm);
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm);
 void iwl_mvm_fw_error_sram_dump(struct iwl_mvm *mvm);
+void iwl_mvm_fw_error_rxf_dump(struct iwl_mvm *mvm);
 #endif
 u8 first_antenna(u8 mask);
 u8 iwl_mvm_next_antenna(struct iwl_mvm *mvm, u8 valid, u8 last_idx);
@@ -745,7 +763,7 @@ int iwl_mvm_rx_statistics(struct iwl_mvm *mvm,
 			  struct iwl_device_cmd *cmd);
 
 /* NVM */
-int iwl_nvm_init(struct iwl_mvm *mvm);
+int iwl_nvm_init(struct iwl_mvm *mvm, bool read_nvm_from_nic);
 int iwl_mvm_load_nvm_to_nic(struct iwl_mvm *mvm);
 
 int iwl_mvm_up(struct iwl_mvm *mvm);
@@ -796,7 +814,8 @@ void iwl_mvm_phy_ctxt_unref(struct iwl_mvm *mvm,
 int iwl_mvm_mac_ctxt_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 void iwl_mvm_mac_ctxt_release(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 int iwl_mvm_mac_ctxt_add(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
-int iwl_mvm_mac_ctxt_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
+int iwl_mvm_mac_ctxt_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			     bool force_assoc_off);
 int iwl_mvm_mac_ctxt_remove(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 u32 iwl_mvm_mac_get_queues_mask(struct iwl_mvm *mvm,
 				struct ieee80211_vif *vif);
@@ -840,7 +859,7 @@ int iwl_mvm_config_sched_scan_profiles(struct iwl_mvm *mvm,
 				       struct cfg80211_sched_scan_request *req);
 int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm,
 			     struct cfg80211_sched_scan_request *req);
-int iwl_mvm_sched_scan_stop(struct iwl_mvm *mvm);
+int iwl_mvm_sched_scan_stop(struct iwl_mvm *mvm, bool notify);
 int iwl_mvm_rx_sched_scan_results(struct iwl_mvm *mvm,
 				  struct iwl_rx_cmd_buffer *rxb,
 				  struct iwl_device_cmd *cmd);
@@ -874,10 +893,8 @@ void iwl_mvm_update_frame_stats(struct iwl_mvm *mvm,
 int rs_pretty_print_rate(char *buf, const u32 rate);
 
 /* power management */
-int iwl_power_legacy_set_cam_mode(struct iwl_mvm *mvm);
-
 int iwl_mvm_power_update_device(struct iwl_mvm *mvm);
-int iwl_mvm_power_update_mac(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
+int iwl_mvm_power_update_mac(struct iwl_mvm *mvm);
 int iwl_mvm_power_mac_dbgfs_read(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 				 char *buf, int bufsz);
 
@@ -886,8 +903,18 @@ int iwl_mvm_power_uapsd_misbehaving_ap_notif(struct iwl_mvm *mvm,
 					     struct iwl_rx_cmd_buffer *rxb,
 					     struct iwl_device_cmd *cmd);
 
+#ifdef CONFIG_IWLWIFI_LEDS
 int iwl_mvm_leds_init(struct iwl_mvm *mvm);
 void iwl_mvm_leds_exit(struct iwl_mvm *mvm);
+#else
+static inline int iwl_mvm_leds_init(struct iwl_mvm *mvm)
+{
+	return 0;
+}
+static inline void iwl_mvm_leds_exit(struct iwl_mvm *mvm)
+{
+}
+#endif
 
 /* D3 (WoWLAN, NetDetect) */
 int iwl_mvm_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan);
@@ -922,9 +949,9 @@ int iwl_mvm_send_proto_offload(struct iwl_mvm *mvm,
 void iwl_mvm_ref(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type);
 void iwl_mvm_unref(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type);
 void iwl_mvm_d0i3_enable_tx(struct iwl_mvm *mvm, __le16 *qos_seq);
+int _iwl_mvm_exit_d0i3(struct iwl_mvm *mvm);
 
 /* BT Coex */
-int iwl_send_bt_prio_tbl(struct iwl_mvm *mvm);
 int iwl_send_bt_init_conf(struct iwl_mvm *mvm);
 int iwl_mvm_rx_bt_coex_notif(struct iwl_mvm *mvm,
 			     struct iwl_rx_cmd_buffer *rxb,
@@ -936,9 +963,10 @@ u16 iwl_mvm_coex_agg_time_limit(struct iwl_mvm *mvm,
 				struct ieee80211_sta *sta);
 bool iwl_mvm_bt_coex_is_mimo_allowed(struct iwl_mvm *mvm,
 				     struct ieee80211_sta *sta);
+bool iwl_mvm_bt_coex_is_tpc_allowed(struct iwl_mvm *mvm,
+				    enum ieee80211_band band);
 u8 iwl_mvm_bt_coex_tx_prio(struct iwl_mvm *mvm, struct ieee80211_hdr *hdr,
 			   struct ieee80211_tx_info *info, u8 ac);
-int iwl_mvm_bt_coex_reduced_txp(struct iwl_mvm *mvm, u8 sta_id, bool enable);
 
 enum iwl_bt_kill_msk {
 	BT_KILL_MSK_DEFAULT,
@@ -969,17 +997,11 @@ int iwl_mvm_enable_beacon_filter(struct iwl_mvm *mvm,
 int iwl_mvm_disable_beacon_filter(struct iwl_mvm *mvm,
 				  struct ieee80211_vif *vif,
 				  u32 flags);
-int iwl_mvm_update_beacon_abort(struct iwl_mvm *mvm,
-				struct ieee80211_vif *vif, bool enable);
-int iwl_mvm_update_beacon_filter(struct iwl_mvm *mvm,
-				 struct ieee80211_vif *vif,
-				 bool force,
-				 u32 flags);
-
 /* SMPS */
 void iwl_mvm_update_smps(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 				enum iwl_mvm_smps_type_request req_type,
 				enum ieee80211_smps_mode smps_request);
+bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm);
 
 /* Low latency */
 int iwl_mvm_update_low_latency(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/iwlwifi/mvm/nvm.c b/drivers/net/wireless/iwlwifi/mvm/nvm.c
index cf2d09f5378..808f78f6fbf 100644
--- a/drivers/net/wireless/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/iwlwifi/mvm/nvm.c
@@ -74,6 +74,12 @@
 #define NVM_WRITE_OPCODE 1
 #define NVM_READ_OPCODE 0
 
+/* load nvm chunk response */
+enum {
+	READ_NVM_CHUNK_SUCCEED = 0,
+	READ_NVM_CHUNK_NOT_VALID_ADDRESS = 1
+};
+
 /*
  * prepare the NVM host command w/ the pointers to the nvm buffer
  * and send it to fw
@@ -90,7 +96,7 @@ static int iwl_nvm_write_chunk(struct iwl_mvm *mvm, u16 section,
 	struct iwl_host_cmd cmd = {
 		.id = NVM_ACCESS_CMD,
 		.len = { sizeof(struct iwl_nvm_access_cmd), length },
-		.flags = CMD_SYNC | CMD_SEND_IN_RFKILL,
+		.flags = CMD_SEND_IN_RFKILL,
 		.data = { &nvm_access_cmd, data },
 		/* data may come from vmalloc, so use _DUP */
 		.dataflags = { 0, IWL_HCMD_DFL_DUP },
@@ -112,7 +118,7 @@ static int iwl_nvm_read_chunk(struct iwl_mvm *mvm, u16 section,
 	struct iwl_rx_packet *pkt;
 	struct iwl_host_cmd cmd = {
 		.id = NVM_ACCESS_CMD,
-		.flags = CMD_SYNC | CMD_WANT_SKB | CMD_SEND_IN_RFKILL,
+		.flags = CMD_WANT_SKB | CMD_SEND_IN_RFKILL,
 		.data = { &nvm_access_cmd, },
 	};
 	int ret, bytes_read, offset_read;
@@ -139,10 +145,26 @@ static int iwl_nvm_read_chunk(struct iwl_mvm *mvm, u16 section,
 	offset_read = le16_to_cpu(nvm_resp->offset);
 	resp_data = nvm_resp->data;
 	if (ret) {
-		IWL_ERR(mvm,
-			"NVM access command failed with status %d (device: %s)\n",
-			ret, mvm->cfg->name);
-		ret = -EINVAL;
+		if ((offset != 0) &&
+		    (ret == READ_NVM_CHUNK_NOT_VALID_ADDRESS)) {
+			/*
+			 * meaning of NOT_VALID_ADDRESS:
+			 * driver try to read chunk from address that is
+			 * multiple of 2K and got an error since addr is empty.
+			 * meaning of (offset != 0): driver already
+			 * read valid data from another chunk so this case
+			 * is not an error.
+			 */
+			IWL_DEBUG_EEPROM(mvm->trans->dev,
+					 "NVM access command failed on offset 0x%x since that section size is multiple 2K\n",
+					 offset);
+			ret = 0;
+		} else {
+			IWL_DEBUG_EEPROM(mvm->trans->dev,
+					 "NVM access command failed with status %d (device: %s)\n",
+					 ret, mvm->cfg->name);
+			ret = -EIO;
+		}
 		goto exit;
 	}
 
@@ -211,9 +233,9 @@ static int iwl_nvm_read_section(struct iwl_mvm *mvm, u16 section,
 	while (ret == length) {
 		ret = iwl_nvm_read_chunk(mvm, section, offset, length, data);
 		if (ret < 0) {
-			IWL_ERR(mvm,
-				"Cannot read NVM from section %d offset %d, length %d\n",
-				section, offset, length);
+			IWL_DEBUG_EEPROM(mvm->trans->dev,
+					 "Cannot read NVM from section %d offset %d, length %d\n",
+					 section, offset, length);
 			return ret;
 		}
 		offset += ret;
@@ -238,13 +260,20 @@ iwl_parse_nvm_sections(struct iwl_mvm *mvm)
 			return NULL;
 		}
 	} else {
+		/* SW and REGULATORY sections are mandatory */
 		if (!mvm->nvm_sections[NVM_SECTION_TYPE_SW].data ||
-		    !mvm->nvm_sections[NVM_SECTION_TYPE_MAC_OVERRIDE].data ||
 		    !mvm->nvm_sections[NVM_SECTION_TYPE_REGULATORY].data) {
 			IWL_ERR(mvm,
 				"Can't parse empty family 8000 NVM sections\n");
 			return NULL;
 		}
+		/* MAC_OVERRIDE or at least HW section must exist */
+		if (!mvm->nvm_sections[mvm->cfg->nvm_hw_section_num].data &&
+		    !mvm->nvm_sections[NVM_SECTION_TYPE_MAC_OVERRIDE].data) {
+			IWL_ERR(mvm,
+				"Can't parse mac_address, empty sections\n");
+			return NULL;
+		}
 	}
 
 	if (WARN_ON(!mvm->cfg))
@@ -311,16 +340,16 @@ static int iwl_mvm_read_external_nvm(struct iwl_mvm *mvm)
 	 * get here after that we assume the NVM request can be satisfied
 	 * synchronously.
 	 */
-	ret = request_firmware(&fw_entry, iwlwifi_mod_params.nvm_file,
+	ret = request_firmware(&fw_entry, mvm->nvm_file_name,
 			       mvm->trans->dev);
 	if (ret) {
 		IWL_ERR(mvm, "ERROR: %s isn't available %d\n",
-			iwlwifi_mod_params.nvm_file, ret);
+			mvm->nvm_file_name, ret);
 		return ret;
 	}
 
 	IWL_INFO(mvm, "Loaded NVM file %s (%zu bytes)\n",
-		 iwlwifi_mod_params.nvm_file, fw_entry->size);
+		 mvm->nvm_file_name, fw_entry->size);
 
 	if (fw_entry->size < sizeof(*file_sec)) {
 		IWL_ERR(mvm, "NVM file too small\n");
@@ -427,53 +456,28 @@ int iwl_mvm_load_nvm_to_nic(struct iwl_mvm *mvm)
 	return ret;
 }
 
-int iwl_nvm_init(struct iwl_mvm *mvm)
+int iwl_nvm_init(struct iwl_mvm *mvm, bool read_nvm_from_nic)
 {
-	int ret, i, section;
+	int ret, section;
 	u8 *nvm_buffer, *temp;
-	int nvm_to_read[NVM_MAX_NUM_SECTIONS];
-	int num_of_sections_to_read;
 
 	if (WARN_ON_ONCE(mvm->cfg->nvm_hw_section_num >= NVM_MAX_NUM_SECTIONS))
 		return -EINVAL;
 
-	/* load external NVM if configured */
-	if (iwlwifi_mod_params.nvm_file) {
-		/* move to External NVM flow */
-		ret = iwl_mvm_read_external_nvm(mvm);
-		if (ret)
-			return ret;
-	} else {
-		/* list of NVM sections we are allowed/need to read */
-		if (mvm->trans->cfg->device_family != IWL_DEVICE_FAMILY_8000) {
-			nvm_to_read[0] = mvm->cfg->nvm_hw_section_num;
-			nvm_to_read[1] = NVM_SECTION_TYPE_SW;
-			nvm_to_read[2] = NVM_SECTION_TYPE_CALIBRATION;
-			nvm_to_read[3] = NVM_SECTION_TYPE_PRODUCTION;
-			num_of_sections_to_read = 4;
-		} else {
-			nvm_to_read[0] = NVM_SECTION_TYPE_SW;
-			nvm_to_read[1] = NVM_SECTION_TYPE_CALIBRATION;
-			nvm_to_read[2] = NVM_SECTION_TYPE_PRODUCTION;
-			nvm_to_read[3] = NVM_SECTION_TYPE_REGULATORY;
-			nvm_to_read[4] = NVM_SECTION_TYPE_MAC_OVERRIDE;
-			num_of_sections_to_read = 5;
-		}
-
+	/* load NVM values from nic */
+	if (read_nvm_from_nic) {
 		/* Read From FW NVM */
 		IWL_DEBUG_EEPROM(mvm->trans->dev, "Read from NVM\n");
 
-		/* TODO: find correct NVM max size for a section */
 		nvm_buffer = kmalloc(mvm->cfg->base_params->eeprom_size,
 				     GFP_KERNEL);
 		if (!nvm_buffer)
 			return -ENOMEM;
-		for (i = 0; i < num_of_sections_to_read; i++) {
-			section = nvm_to_read[i];
+		for (section = 0; section < NVM_MAX_NUM_SECTIONS; section++) {
 			/* we override the constness for initial read */
 			ret = iwl_nvm_read_section(mvm, section, nvm_buffer);
 			if (ret < 0)
-				break;
+				continue;
 			temp = kmemdup(nvm_buffer, ret, GFP_KERNEL);
 			if (!temp) {
 				ret = -ENOMEM;
@@ -502,15 +506,21 @@ int iwl_nvm_init(struct iwl_mvm *mvm)
 					mvm->nvm_hw_blob.size = ret;
 					break;
 				}
-				WARN(1, "section: %d", section);
 			}
 #endif
 		}
 		kfree(nvm_buffer);
-		if (ret < 0)
+	}
+
+	/* load external NVM if configured */
+	if (mvm->nvm_file_name) {
+		/* move to External NVM flow */
+		ret = iwl_mvm_read_external_nvm(mvm);
+		if (ret)
 			return ret;
 	}
 
+	/* parse the relevant nvm sections */
 	mvm->nvm_data = iwl_parse_nvm_sections(mvm);
 	if (!mvm->nvm_data)
 		return -ENODATA;
diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c
index 9545d7fdd4b..cc2f7de396d 100644
--- a/drivers/net/wireless/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/iwlwifi/mvm/ops.c
@@ -79,8 +79,8 @@
 #include "iwl-prph.h"
 #include "rs.h"
 #include "fw-api-scan.h"
-#include "fw-error-dump.h"
 #include "time-event.h"
+#include "iwl-fw-error-dump.h"
 
 /*
  * module name, copyright, version, etc.
@@ -220,7 +220,7 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 	RX_HANDLER(BA_NOTIF, iwl_mvm_rx_ba_notif, false),
 
 	RX_HANDLER(BT_PROFILE_NOTIFICATION, iwl_mvm_rx_bt_coex_notif, true),
-	RX_HANDLER(BEACON_NOTIFICATION, iwl_mvm_rx_beacon_notif, false),
+	RX_HANDLER(BEACON_NOTIFICATION, iwl_mvm_rx_beacon_notif, true),
 	RX_HANDLER(STATISTICS_NOTIFICATION, iwl_mvm_rx_statistics, true),
 	RX_HANDLER(ANTENNA_COUPLING_NOTIFICATION,
 		   iwl_mvm_rx_ant_coupling_notif, true),
@@ -402,6 +402,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	mvm->sf_state = SF_UNINIT;
 
 	mutex_init(&mvm->mutex);
+	mutex_init(&mvm->d0i3_suspend_mutex);
 	spin_lock_init(&mvm->async_handlers_lock);
 	INIT_LIST_HEAD(&mvm->time_event_list);
 	INIT_LIST_HEAD(&mvm->async_handlers_list);
@@ -465,13 +466,24 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	min_backoff = calc_min_backoff(trans, cfg);
 	iwl_mvm_tt_initialize(mvm, min_backoff);
+	/* set the nvm_file_name according to priority */
+	if (iwlwifi_mod_params.nvm_file)
+		mvm->nvm_file_name = iwlwifi_mod_params.nvm_file;
+	else
+		mvm->nvm_file_name = mvm->cfg->default_nvm_file;
+
+	if (WARN(cfg->no_power_up_nic_in_init && !mvm->nvm_file_name,
+		 "not allowing power-up and not having nvm_file\n"))
+		goto out_free;
 
 	/*
-	 * If the NVM exists in an external file,
-	 * there is no need to unnecessarily power up the NIC at driver load
+	 * Even if nvm exists in the nvm_file driver should read agin the nvm
+	 * from the nic because there might be entries that exist in the OTP
+	 * and not in the file.
+	 * for nics with no_power_up_nic_in_init: rely completley on nvm_file
 	 */
-	if (iwlwifi_mod_params.nvm_file) {
-		err = iwl_nvm_init(mvm);
+	if (cfg->no_power_up_nic_in_init && mvm->nvm_file_name) {
+		err = iwl_nvm_init(mvm, false);
 		if (err)
 			goto out_free;
 	} else {
@@ -518,7 +530,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
  out_free:
 	iwl_phy_db_free(mvm->phy_db);
 	kfree(mvm->scan_cmd);
-	if (!iwlwifi_mod_params.nvm_file)
+	if (!cfg->no_power_up_nic_in_init || !mvm->nvm_file_name)
 		iwl_trans_op_mode_leave(trans);
 	ieee80211_free_hw(mvm->hw);
 	return NULL;
@@ -538,6 +550,7 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode)
 	kfree(mvm->scan_cmd);
 	vfree(mvm->fw_error_dump);
 	kfree(mvm->fw_error_sram);
+	kfree(mvm->fw_error_rxf);
 	kfree(mvm->mcast_filter_cmd);
 	mvm->mcast_filter_cmd = NULL;
 
@@ -814,6 +827,7 @@ void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm)
 	struct iwl_fw_error_dump_file *dump_file;
 	struct iwl_fw_error_dump_data *dump_data;
 	u32 file_len;
+	u32 trans_len;
 
 	lockdep_assert_held(&mvm->mutex);
 
@@ -821,8 +835,13 @@ void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm)
 		return;
 
 	file_len = mvm->fw_error_sram_len +
+		   mvm->fw_error_rxf_len +
 		   sizeof(*dump_file) +
-		   sizeof(*dump_data);
+		   sizeof(*dump_data) * 2;
+
+	trans_len = iwl_trans_dump_data(mvm->trans, NULL, 0);
+	if (trans_len)
+		file_len += trans_len;
 
 	dump_file = vmalloc(file_len);
 	if (!dump_file)
@@ -833,7 +852,12 @@ void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm)
 	dump_file->barker = cpu_to_le32(IWL_FW_ERROR_DUMP_BARKER);
 	dump_file->file_len = cpu_to_le32(file_len);
 	dump_data = (void *)dump_file->data;
-	dump_data->type = IWL_FW_ERROR_DUMP_SRAM;
+	dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_RXF);
+	dump_data->len = cpu_to_le32(mvm->fw_error_rxf_len);
+	memcpy(dump_data->data, mvm->fw_error_rxf, mvm->fw_error_rxf_len);
+
+	dump_data = iwl_mvm_fw_error_next_data(dump_data);
+	dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_SRAM);
 	dump_data->len = cpu_to_le32(mvm->fw_error_sram_len);
 
 	/*
@@ -842,6 +866,23 @@ void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm)
 	 * mvm->fw_error_sram right now.
 	 */
 	memcpy(dump_data->data, mvm->fw_error_sram, mvm->fw_error_sram_len);
+
+	kfree(mvm->fw_error_rxf);
+	mvm->fw_error_rxf = NULL;
+	mvm->fw_error_rxf_len = 0;
+
+	kfree(mvm->fw_error_sram);
+	mvm->fw_error_sram = NULL;
+	mvm->fw_error_sram_len = 0;
+
+	if (trans_len) {
+		void *buf = iwl_mvm_fw_error_next_data(dump_data);
+		u32 real_trans_len = iwl_trans_dump_data(mvm->trans, buf,
+							 trans_len);
+		dump_data = (void *)((u8 *)buf + real_trans_len);
+		dump_file->file_len =
+			cpu_to_le32(file_len - trans_len + real_trans_len);
+	}
 }
 #endif
 
@@ -853,6 +894,7 @@ static void iwl_mvm_nic_error(struct iwl_op_mode *op_mode)
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	iwl_mvm_fw_error_sram_dump(mvm);
+	iwl_mvm_fw_error_rxf_dump(mvm);
 #endif
 
 	iwl_mvm_nic_restart(mvm);
@@ -1126,9 +1168,9 @@ static void iwl_mvm_d0i3_exit_work(struct work_struct *wk)
 	struct iwl_mvm *mvm = container_of(wk, struct iwl_mvm, d0i3_exit_work);
 	struct iwl_host_cmd get_status_cmd = {
 		.id = WOWLAN_GET_STATUSES,
-		.flags = CMD_SYNC | CMD_HIGH_PRIO | CMD_WANT_SKB,
+		.flags = CMD_HIGH_PRIO | CMD_WANT_SKB,
 	};
-	struct iwl_wowlan_status_v6 *status;
+	struct iwl_wowlan_status *status;
 	int ret;
 	u32 disconnection_reasons, wakeup_reasons;
 	__le16 *qos_seq = NULL;
@@ -1158,18 +1200,27 @@ static void iwl_mvm_d0i3_exit_work(struct work_struct *wk)
 	iwl_free_resp(&get_status_cmd);
 out:
 	iwl_mvm_d0i3_enable_tx(mvm, qos_seq);
+	iwl_mvm_unref(mvm, IWL_MVM_REF_EXIT_WORK);
 	mutex_unlock(&mvm->mutex);
 }
 
-static int iwl_mvm_exit_d0i3(struct iwl_op_mode *op_mode)
+int _iwl_mvm_exit_d0i3(struct iwl_mvm *mvm)
 {
-	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
 	u32 flags = CMD_ASYNC | CMD_HIGH_PRIO | CMD_SEND_IN_IDLE |
 		    CMD_WAKE_UP_TRANS;
 	int ret;
 
 	IWL_DEBUG_RPM(mvm, "MVM exiting D0i3\n");
 
+	mutex_lock(&mvm->d0i3_suspend_mutex);
+	if (test_bit(D0I3_DEFER_WAKEUP, &mvm->d0i3_suspend_flags)) {
+		IWL_DEBUG_RPM(mvm, "Deferring d0i3 exit until resume\n");
+		__set_bit(D0I3_PENDING_WAKEUP, &mvm->d0i3_suspend_flags);
+		mutex_unlock(&mvm->d0i3_suspend_mutex);
+		return 0;
+	}
+	mutex_unlock(&mvm->d0i3_suspend_mutex);
+
 	ret = iwl_mvm_send_cmd_pdu(mvm, D0I3_END_CMD, flags, 0, NULL);
 	if (ret)
 		goto out;
@@ -1183,6 +1234,25 @@ out:
 	return ret;
 }
 
+static int iwl_mvm_exit_d0i3(struct iwl_op_mode *op_mode)
+{
+	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
+
+	iwl_mvm_ref(mvm, IWL_MVM_REF_EXIT_WORK);
+	return _iwl_mvm_exit_d0i3(mvm);
+}
+
+static void iwl_mvm_napi_add(struct iwl_op_mode *op_mode,
+			     struct napi_struct *napi,
+			     struct net_device *napi_dev,
+			     int (*poll)(struct napi_struct *, int),
+			     int weight)
+{
+	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
+
+	ieee80211_napi_add(mvm->hw, napi, napi_dev, poll, weight);
+}
+
 static const struct iwl_op_mode_ops iwl_mvm_ops = {
 	.start = iwl_op_mode_mvm_start,
 	.stop = iwl_op_mode_mvm_stop,
@@ -1196,4 +1266,5 @@ static const struct iwl_op_mode_ops iwl_mvm_ops = {
 	.nic_config = iwl_mvm_nic_config,
 	.enter_d0i3 = iwl_mvm_enter_d0i3,
 	.exit_d0i3 = iwl_mvm_exit_d0i3,
+	.napi_add = iwl_mvm_napi_add,
 };
diff --git a/drivers/net/wireless/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/iwlwifi/mvm/phy-ctxt.c
index 237efe0ac1c..539f3a942d4 100644
--- a/drivers/net/wireless/iwlwifi/mvm/phy-ctxt.c
+++ b/drivers/net/wireless/iwlwifi/mvm/phy-ctxt.c
@@ -156,6 +156,18 @@ static void iwl_mvm_phy_ctxt_cmd_data(struct iwl_mvm *mvm,
 	idle_cnt = chains_static;
 	active_cnt = chains_dynamic;
 
+	/* In scenarios where we only ever use a single-stream rates,
+	 * i.e. legacy 11b/g/a associations, single-stream APs or even
+	 * static SMPS, enable both chains to get diversity, improving
+	 * the case where we're far enough from the AP that attenuation
+	 * between the two antennas is sufficiently different to impact
+	 * performance.
+	 */
+	if (active_cnt == 1 && iwl_mvm_rx_diversity_allowed(mvm)) {
+		idle_cnt = 2;
+		active_cnt = 2;
+	}
+
 	cmd->rxchain_info = cpu_to_le32(mvm->fw->valid_rx_ant <<
 					PHY_RX_CHAIN_VALID_POS);
 	cmd->rxchain_info |= cpu_to_le32(idle_cnt << PHY_RX_CHAIN_CNT_POS);
@@ -187,7 +199,7 @@ static int iwl_mvm_phy_ctxt_apply(struct iwl_mvm *mvm,
 	iwl_mvm_phy_ctxt_cmd_data(mvm, &cmd, chandef,
 				  chains_static, chains_dynamic);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, PHY_CONTEXT_CMD, CMD_SYNC,
+	ret = iwl_mvm_send_cmd_pdu(mvm, PHY_CONTEXT_CMD, 0,
 				   sizeof(struct iwl_phy_context_cmd),
 				   &cmd);
 	if (ret)
@@ -202,18 +214,15 @@ int iwl_mvm_phy_ctxt_add(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt,
 			 struct cfg80211_chan_def *chandef,
 			 u8 chains_static, u8 chains_dynamic)
 {
-	int ret;
-
 	WARN_ON(!test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status) &&
 		ctxt->ref);
 	lockdep_assert_held(&mvm->mutex);
 
 	ctxt->channel = chandef->chan;
-	ret = iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef,
-				     chains_static, chains_dynamic,
-				     FW_CTXT_ACTION_ADD, 0);
 
-	return ret;
+	return iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef,
+				      chains_static, chains_dynamic,
+				      FW_CTXT_ACTION_ADD, 0);
 }
 
 /*
diff --git a/drivers/net/wireless/iwlwifi/mvm/power.c b/drivers/net/wireless/iwlwifi/mvm/power.c
index 6b636eab333..c182a8baf68 100644
--- a/drivers/net/wireless/iwlwifi/mvm/power.c
+++ b/drivers/net/wireless/iwlwifi/mvm/power.c
@@ -123,28 +123,6 @@ void iwl_mvm_beacon_filter_set_cqm_params(struct iwl_mvm *mvm,
 	cmd->ba_enable_beacon_abort = cpu_to_le32(mvmvif->bf_data.ba_enabled);
 }
 
-int iwl_mvm_update_beacon_abort(struct iwl_mvm *mvm,
-				struct ieee80211_vif *vif, bool enable)
-{
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	struct iwl_beacon_filter_cmd cmd = {
-		IWL_BF_CMD_CONFIG_DEFAULTS,
-		.bf_enable_beacon_filter = cpu_to_le32(1),
-		.ba_enable_beacon_abort = cpu_to_le32(enable),
-	};
-
-	if (!mvmvif->bf_data.bf_enabled)
-		return 0;
-
-	if (mvm->cur_ucode == IWL_UCODE_WOWLAN)
-		cmd.ba_escape_timer = cpu_to_le32(IWL_BA_ESCAPE_TIMER_D3);
-
-	mvmvif->bf_data.ba_enabled = enable;
-	iwl_mvm_beacon_filter_set_cqm_params(mvm, vif, &cmd);
-	iwl_mvm_beacon_filter_debugfs_parameters(vif, &cmd);
-	return iwl_mvm_beacon_filter_send_cmd(mvm, &cmd, CMD_SYNC);
-}
-
 static void iwl_mvm_power_log(struct iwl_mvm *mvm,
 			      struct iwl_mac_power_cmd *cmd)
 {
@@ -268,6 +246,57 @@ static void iwl_mvm_power_configure_uapsd(struct iwl_mvm *mvm,
 		IWL_MVM_PS_HEAVY_RX_THLD_PERCENT;
 }
 
+static void iwl_mvm_binding_iterator(void *_data, u8 *mac,
+				      struct ieee80211_vif *vif)
+{
+	unsigned long *data = _data;
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+
+	if (!mvmvif->phy_ctxt)
+		return;
+
+	if (vif->type == NL80211_IFTYPE_STATION ||
+	    vif->type == NL80211_IFTYPE_AP)
+		__set_bit(mvmvif->phy_ctxt->id, data);
+}
+
+static bool iwl_mvm_power_allow_uapsd(struct iwl_mvm *mvm,
+				       struct ieee80211_vif *vif)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	unsigned long phy_ctxt_counter = 0;
+
+	ieee80211_iterate_active_interfaces_atomic(mvm->hw,
+						   IEEE80211_IFACE_ITER_NORMAL,
+						   iwl_mvm_binding_iterator,
+						   &phy_ctxt_counter);
+
+	if (!memcmp(mvmvif->uapsd_misbehaving_bssid, vif->bss_conf.bssid,
+		    ETH_ALEN))
+		return false;
+
+	if (vif->p2p &&
+	    !(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_P2P_PS_UAPSD))
+		return false;
+	/*
+	 * Avoid using uAPSD if P2P client is associated to GO that uses
+	 * opportunistic power save. This is due to current FW limitation.
+	 */
+	if (vif->p2p &&
+	    (vif->bss_conf.p2p_noa_attr.oppps_ctwindow &
+	    IEEE80211_P2P_OPPPS_ENABLE_BIT))
+		return false;
+
+	/*
+	 * Avoid using uAPSD if client is in DCM -
+	 * low latency issue in Miracast
+	 */
+	if (hweight8(phy_ctxt_counter) >= 2)
+		return false;
+
+	return true;
+}
+
 static void iwl_mvm_power_build_cmd(struct iwl_mvm *mvm,
 				    struct ieee80211_vif *vif,
 				    struct iwl_mac_power_cmd *cmd)
@@ -280,7 +309,6 @@ static void iwl_mvm_power_build_cmd(struct iwl_mvm *mvm,
 	bool radar_detect = false;
 	struct iwl_mvm_vif *mvmvif __maybe_unused =
 		iwl_mvm_vif_from_mac80211(vif);
-	bool allow_uapsd = true;
 
 	cmd->id_and_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id,
 							    mvmvif->color));
@@ -303,13 +331,8 @@ static void iwl_mvm_power_build_cmd(struct iwl_mvm *mvm,
 
 	cmd->flags |= cpu_to_le16(POWER_FLAGS_POWER_SAVE_ENA_MSK);
 
-#ifdef CONFIG_IWLWIFI_DEBUGFS
-	if (mvmvif->dbgfs_pm.mask & MVM_DEBUGFS_PM_DISABLE_POWER_OFF &&
-	    mvmvif->dbgfs_pm.disable_power_off)
-		cmd->flags &= cpu_to_le16(~POWER_FLAGS_POWER_SAVE_ENA_MSK);
-#endif
 	if (!vif->bss_conf.ps || iwl_mvm_vif_low_latency(mvmvif) ||
-	    mvm->pm_disabled)
+	    !mvmvif->pm_enabled)
 		return;
 
 	cmd->flags |= cpu_to_le16(POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK);
@@ -351,23 +374,7 @@ static void iwl_mvm_power_build_cmd(struct iwl_mvm *mvm,
 			cpu_to_le32(IWL_MVM_WOWLAN_PS_TX_DATA_TIMEOUT);
 	}
 
-	if (!memcmp(mvmvif->uapsd_misbehaving_bssid, vif->bss_conf.bssid,
-		    ETH_ALEN))
-		allow_uapsd = false;
-
-	if (vif->p2p &&
-	    !(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_P2P_PS_UAPSD))
-		allow_uapsd = false;
-	/*
-	 * Avoid using uAPSD if P2P client is associated to GO that uses
-	 * opportunistic power save. This is due to current FW limitation.
-	 */
-	if (vif->p2p &&
-	    vif->bss_conf.p2p_noa_attr.oppps_ctwindow &
-	    IEEE80211_P2P_OPPPS_ENABLE_BIT)
-		allow_uapsd = false;
-
-	if (allow_uapsd)
+	if (iwl_mvm_power_allow_uapsd(mvm, vif))
 		iwl_mvm_power_configure_uapsd(mvm, vif, cmd);
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
@@ -421,20 +428,13 @@ static int iwl_mvm_power_send_cmd(struct iwl_mvm *mvm,
 {
 	struct iwl_mac_power_cmd cmd = {};
 
-	if (vif->type != NL80211_IFTYPE_STATION)
-		return 0;
-
-	if (vif->p2p &&
-	    !(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_BSS_P2P_PS_DCM))
-		return 0;
-
 	iwl_mvm_power_build_cmd(mvm, vif, &cmd);
 	iwl_mvm_power_log(mvm, &cmd);
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	memcpy(&iwl_mvm_vif_from_mac80211(vif)->mac_pwr_cmd, &cmd, sizeof(cmd));
 #endif
 
-	return iwl_mvm_send_cmd_pdu(mvm, MAC_PM_POWER_TABLE, CMD_SYNC,
+	return iwl_mvm_send_cmd_pdu(mvm, MAC_PM_POWER_TABLE, 0,
 				    sizeof(cmd), &cmd);
 }
 
@@ -444,12 +444,6 @@ int iwl_mvm_power_update_device(struct iwl_mvm *mvm)
 		.flags = cpu_to_le16(DEVICE_POWER_FLAGS_POWER_SAVE_ENA_MSK),
 	};
 
-	if (!(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_PM_CMD_SUPPORT))
-		return 0;
-
-	if (!(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_DEVICE_PS_CMD))
-		return 0;
-
 	if (iwlmvm_mod_params.power_scheme == IWL_POWER_SCHEME_CAM)
 		mvm->ps_disabled = true;
 
@@ -466,7 +460,7 @@ int iwl_mvm_power_update_device(struct iwl_mvm *mvm)
 			"Sending device power command with flags = 0x%X\n",
 			cmd.flags);
 
-	return iwl_mvm_send_cmd_pdu(mvm, POWER_TABLE_CMD, CMD_SYNC, sizeof(cmd),
+	return iwl_mvm_send_cmd_pdu(mvm, POWER_TABLE_CMD, 0, sizeof(cmd),
 				    &cmd);
 }
 
@@ -508,86 +502,69 @@ int iwl_mvm_power_uapsd_misbehaving_ap_notif(struct iwl_mvm *mvm,
 	return 0;
 }
 
-struct iwl_power_constraint {
+struct iwl_power_vifs {
 	struct ieee80211_vif *bf_vif;
 	struct ieee80211_vif *bss_vif;
 	struct ieee80211_vif *p2p_vif;
-	u16 bss_phyctx_id;
-	u16 p2p_phyctx_id;
-	bool pm_disabled;
-	bool ps_disabled;
-	struct iwl_mvm *mvm;
+	struct ieee80211_vif *ap_vif;
+	struct ieee80211_vif *monitor_vif;
+	bool p2p_active;
+	bool bss_active;
+	bool ap_active;
+	bool monitor_active;
 };
 
 static void iwl_mvm_power_iterator(void *_data, u8 *mac,
 				   struct ieee80211_vif *vif)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	struct iwl_power_constraint *power_iterator = _data;
-	struct iwl_mvm *mvm = power_iterator->mvm;
+	struct iwl_power_vifs *power_iterator = _data;
 
+	mvmvif->pm_enabled = false;
 	switch (ieee80211_vif_type_p2p(vif)) {
 	case NL80211_IFTYPE_P2P_DEVICE:
 		break;
 
 	case NL80211_IFTYPE_P2P_GO:
 	case NL80211_IFTYPE_AP:
-		/* no BSS power mgmt if we have an active AP */
-		if (mvmvif->ap_ibss_active)
-			power_iterator->pm_disabled = true;
+		/* only a single MAC of the same type */
+		WARN_ON(power_iterator->ap_vif);
+		power_iterator->ap_vif = vif;
+		if (mvmvif->phy_ctxt)
+			if (mvmvif->phy_ctxt->id < MAX_PHYS)
+				power_iterator->ap_active = true;
 		break;
 
 	case NL80211_IFTYPE_MONITOR:
-		/* no BSS power mgmt and no device power save */
-		power_iterator->pm_disabled = true;
-		power_iterator->ps_disabled = true;
+		/* only a single MAC of the same type */
+		WARN_ON(power_iterator->monitor_vif);
+		power_iterator->monitor_vif = vif;
+		if (mvmvif->phy_ctxt)
+			if (mvmvif->phy_ctxt->id < MAX_PHYS)
+				power_iterator->monitor_active = true;
 		break;
 
 	case NL80211_IFTYPE_P2P_CLIENT:
-		if (mvmvif->phy_ctxt)
-			power_iterator->p2p_phyctx_id = mvmvif->phy_ctxt->id;
-
-		/* we should have only one P2P vif */
+		/* only a single MAC of the same type */
 		WARN_ON(power_iterator->p2p_vif);
 		power_iterator->p2p_vif = vif;
-
-		IWL_DEBUG_POWER(mvm, "p2p: p2p_id=%d, bss_id=%d\n",
-				power_iterator->p2p_phyctx_id,
-				power_iterator->bss_phyctx_id);
-		if (!(mvm->fw->ucode_capa.flags &
-		      IWL_UCODE_TLV_FLAGS_BSS_P2P_PS_DCM)) {
-			/* no BSS power mgmt if we have a P2P client*/
-			power_iterator->pm_disabled = true;
-		} else if (power_iterator->p2p_phyctx_id < MAX_PHYS &&
-			   power_iterator->bss_phyctx_id < MAX_PHYS &&
-			   power_iterator->p2p_phyctx_id ==
-			   power_iterator->bss_phyctx_id) {
-			power_iterator->pm_disabled = true;
-		}
+		if (mvmvif->phy_ctxt)
+			if (mvmvif->phy_ctxt->id < MAX_PHYS)
+				power_iterator->p2p_active = true;
 		break;
 
 	case NL80211_IFTYPE_STATION:
-		if (mvmvif->phy_ctxt)
-			power_iterator->bss_phyctx_id = mvmvif->phy_ctxt->id;
-
-		/* we should have only one BSS vif */
+		/* only a single MAC of the same type */
 		WARN_ON(power_iterator->bss_vif);
 		power_iterator->bss_vif = vif;
+		if (mvmvif->phy_ctxt)
+			if (mvmvif->phy_ctxt->id < MAX_PHYS)
+				power_iterator->bss_active = true;
 
 		if (mvmvif->bf_data.bf_enabled &&
 		    !WARN_ON(power_iterator->bf_vif))
 			power_iterator->bf_vif = vif;
 
-		IWL_DEBUG_POWER(mvm, "bss: p2p_id=%d, bss_id=%d\n",
-				power_iterator->p2p_phyctx_id,
-				power_iterator->bss_phyctx_id);
-		if (mvm->fw->ucode_capa.flags &
-		    IWL_UCODE_TLV_FLAGS_BSS_P2P_PS_DCM &&
-			(power_iterator->p2p_phyctx_id < MAX_PHYS &&
-			 power_iterator->bss_phyctx_id < MAX_PHYS &&
-			 power_iterator->p2p_phyctx_id ==
-			 power_iterator->bss_phyctx_id))
-			power_iterator->pm_disabled = true;
 		break;
 
 	default:
@@ -596,70 +573,73 @@ static void iwl_mvm_power_iterator(void *_data, u8 *mac,
 }
 
 static void
-iwl_mvm_power_get_global_constraint(struct iwl_mvm *mvm,
-				    struct iwl_power_constraint *constraint)
+iwl_mvm_power_set_pm(struct iwl_mvm *mvm,
+				    struct iwl_power_vifs *vifs)
 {
-	lockdep_assert_held(&mvm->mutex);
+	struct iwl_mvm_vif *bss_mvmvif = NULL;
+	struct iwl_mvm_vif *p2p_mvmvif = NULL;
+	struct iwl_mvm_vif *ap_mvmvif = NULL;
+	bool client_same_channel = false;
+	bool ap_same_channel = false;
 
-	if (iwlmvm_mod_params.power_scheme == IWL_POWER_SCHEME_CAM) {
-		constraint->pm_disabled = true;
-		constraint->ps_disabled = true;
-	}
+	lockdep_assert_held(&mvm->mutex);
 
+	/* get vifs info + set pm_enable to false */
 	ieee80211_iterate_active_interfaces_atomic(mvm->hw,
 					    IEEE80211_IFACE_ITER_NORMAL,
-					    iwl_mvm_power_iterator, constraint);
-}
-
-int iwl_mvm_power_update_mac(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
-{
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	struct iwl_power_constraint constraint = {
-		    .p2p_phyctx_id = MAX_PHYS,
-		    .bss_phyctx_id = MAX_PHYS,
-		    .mvm = mvm,
-	};
-	bool ba_enable;
-	int ret;
+					    iwl_mvm_power_iterator, vifs);
 
-	lockdep_assert_held(&mvm->mutex);
+	if (vifs->bss_vif)
+		bss_mvmvif = iwl_mvm_vif_from_mac80211(vifs->bss_vif);
 
-	if (!(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_PM_CMD_SUPPORT))
-		return 0;
+	if (vifs->p2p_vif)
+		p2p_mvmvif = iwl_mvm_vif_from_mac80211(vifs->p2p_vif);
 
-	iwl_mvm_power_get_global_constraint(mvm, &constraint);
-	mvm->ps_disabled = constraint.ps_disabled;
-	mvm->pm_disabled = constraint.pm_disabled;
+	if (vifs->ap_vif)
+		ap_mvmvif = iwl_mvm_vif_from_mac80211(vifs->ap_vif);
 
-	/* don't update device power state unless we add / remove monitor */
-	if (vif->type == NL80211_IFTYPE_MONITOR) {
-		ret = iwl_mvm_power_update_device(mvm);
-		if (ret)
-			return ret;
+	/* enable PM on bss if bss stand alone */
+	if (vifs->bss_active && !vifs->p2p_active && !vifs->ap_active) {
+		bss_mvmvif->pm_enabled = true;
+		return;
 	}
 
-	if (constraint.bss_vif) {
-		ret = iwl_mvm_power_send_cmd(mvm, constraint.bss_vif);
-		if (ret)
-			return ret;
+	/* enable PM on p2p if p2p stand alone */
+	if (vifs->p2p_active && !vifs->bss_active && !vifs->ap_active) {
+		if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_P2P_PM)
+			p2p_mvmvif->pm_enabled = true;
+		return;
 	}
 
-	if (constraint.p2p_vif) {
-		ret = iwl_mvm_power_send_cmd(mvm, constraint.p2p_vif);
-		if (ret)
-			return ret;
+	if (vifs->bss_active && vifs->p2p_active)
+		client_same_channel = (bss_mvmvif->phy_ctxt->id ==
+				       p2p_mvmvif->phy_ctxt->id);
+	if (vifs->bss_active && vifs->ap_active)
+		ap_same_channel = (bss_mvmvif->phy_ctxt->id ==
+				   ap_mvmvif->phy_ctxt->id);
+
+	/* clients are not stand alone: enable PM if DCM */
+	if (!(client_same_channel || ap_same_channel) &&
+	    (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_BSS_P2P_PS_DCM)) {
+		if (vifs->bss_active)
+			bss_mvmvif->pm_enabled = true;
+		if (vifs->p2p_active &&
+		    (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_P2P_PM))
+			p2p_mvmvif->pm_enabled = true;
+		return;
 	}
 
-	if (!constraint.bf_vif)
-		return 0;
-
-	vif = constraint.bf_vif;
-	mvmvif = iwl_mvm_vif_from_mac80211(vif);
-
-	ba_enable = !(constraint.pm_disabled || constraint.ps_disabled ||
-		      !vif->bss_conf.ps || iwl_mvm_vif_low_latency(mvmvif));
-
-	return iwl_mvm_update_beacon_abort(mvm, constraint.bf_vif, ba_enable);
+	/*
+	 * There is only one channel in the system and there are only
+	 * bss and p2p clients that share it
+	 */
+	if (client_same_channel && !vifs->ap_active &&
+	    (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_BSS_P2P_PS_SCM)) {
+		/* share same channel*/
+		bss_mvmvif->pm_enabled = true;
+		if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_P2P_PM)
+			p2p_mvmvif->pm_enabled = true;
+	}
 }
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
@@ -671,19 +651,10 @@ int iwl_mvm_power_mac_dbgfs_read(struct iwl_mvm *mvm,
 	struct iwl_mac_power_cmd cmd = {};
 	int pos = 0;
 
-	if (WARN_ON(!(mvm->fw->ucode_capa.flags &
-		      IWL_UCODE_TLV_FLAGS_PM_CMD_SUPPORT)))
-		return 0;
-
 	mutex_lock(&mvm->mutex);
 	memcpy(&cmd, &mvmvif->mac_pwr_cmd, sizeof(cmd));
 	mutex_unlock(&mvm->mutex);
 
-	if (!(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_DEVICE_PS_CMD))
-		pos += scnprintf(buf+pos, bufsz-pos, "disable_power_off = %d\n",
-				 (cmd.flags &
-				 cpu_to_le16(POWER_FLAGS_POWER_SAVE_ENA_MSK)) ?
-				 0 : 1);
 	pos += scnprintf(buf+pos, bufsz-pos, "power_scheme = %d\n",
 			 iwlmvm_mod_params.power_scheme);
 	pos += scnprintf(buf+pos, bufsz-pos, "flags = 0x%x\n",
@@ -790,7 +761,7 @@ static int _iwl_mvm_enable_beacon_filter(struct iwl_mvm *mvm,
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	int ret;
 
-	if (mvmvif != mvm->bf_allowed_vif ||
+	if (mvmvif != mvm->bf_allowed_vif || !vif->bss_conf.dtim_period ||
 	    vif->type != NL80211_IFTYPE_STATION || vif->p2p)
 		return 0;
 
@@ -818,6 +789,26 @@ int iwl_mvm_enable_beacon_filter(struct iwl_mvm *mvm,
 	return _iwl_mvm_enable_beacon_filter(mvm, vif, &cmd, flags, false);
 }
 
+static int iwl_mvm_update_beacon_abort(struct iwl_mvm *mvm,
+				       struct ieee80211_vif *vif,
+				       bool enable)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	struct iwl_beacon_filter_cmd cmd = {
+		IWL_BF_CMD_CONFIG_DEFAULTS,
+		.bf_enable_beacon_filter = cpu_to_le32(1),
+	};
+
+	if (!mvmvif->bf_data.bf_enabled)
+		return 0;
+
+	if (mvm->cur_ucode == IWL_UCODE_WOWLAN)
+		cmd.ba_escape_timer = cpu_to_le32(IWL_BA_ESCAPE_TIMER_D3);
+
+	mvmvif->bf_data.ba_enabled = enable;
+	return _iwl_mvm_enable_beacon_filter(mvm, vif, &cmd, 0, false);
+}
+
 int iwl_mvm_disable_beacon_filter(struct iwl_mvm *mvm,
 				  struct ieee80211_vif *vif,
 				  u32 flags)
@@ -826,8 +817,7 @@ int iwl_mvm_disable_beacon_filter(struct iwl_mvm *mvm,
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	int ret;
 
-	if (!(mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_BF_UPDATED) ||
-	    vif->type != NL80211_IFTYPE_STATION || vif->p2p)
+	if (vif->type != NL80211_IFTYPE_STATION || vif->p2p)
 		return 0;
 
 	ret = iwl_mvm_beacon_filter_send_cmd(mvm, &cmd, flags);
@@ -838,6 +828,55 @@ int iwl_mvm_disable_beacon_filter(struct iwl_mvm *mvm,
 	return ret;
 }
 
+int iwl_mvm_power_update_mac(struct iwl_mvm *mvm)
+{
+	struct iwl_mvm_vif *mvmvif;
+	struct iwl_power_vifs vifs = {};
+	bool ba_enable;
+	int ret;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	iwl_mvm_power_set_pm(mvm, &vifs);
+
+	/* disable PS if CAM */
+	if (iwlmvm_mod_params.power_scheme == IWL_POWER_SCHEME_CAM) {
+		mvm->ps_disabled = true;
+	} else {
+	/* don't update device power state unless we add / remove monitor */
+		if (vifs.monitor_vif) {
+			if (vifs.monitor_active)
+				mvm->ps_disabled = true;
+			ret = iwl_mvm_power_update_device(mvm);
+			if (ret)
+				return ret;
+		}
+	}
+
+	if (vifs.bss_vif) {
+		ret = iwl_mvm_power_send_cmd(mvm, vifs.bss_vif);
+		if (ret)
+			return ret;
+	}
+
+	if (vifs.p2p_vif) {
+		ret = iwl_mvm_power_send_cmd(mvm, vifs.p2p_vif);
+		if (ret)
+			return ret;
+	}
+
+	if (!vifs.bf_vif)
+		return 0;
+
+	mvmvif = iwl_mvm_vif_from_mac80211(vifs.bf_vif);
+
+	ba_enable = !(!mvmvif->pm_enabled || mvm->ps_disabled ||
+		      !vifs.bf_vif->bss_conf.ps ||
+		      iwl_mvm_vif_low_latency(mvmvif));
+
+	return iwl_mvm_update_beacon_abort(mvm, vifs.bf_vif, ba_enable);
+}
+
 int iwl_mvm_update_d0i3_power_mode(struct iwl_mvm *mvm,
 				   struct ieee80211_vif *vif,
 				   bool enable, u32 flags)
@@ -861,9 +900,10 @@ int iwl_mvm_update_d0i3_power_mode(struct iwl_mvm *mvm,
 		if (WARN_ON(!dtimper_msec))
 			return 0;
 
-		cmd.flags |=
-			cpu_to_le16(POWER_FLAGS_SKIP_OVER_DTIM_MSK);
 		cmd.skip_dtim_periods = 300 / dtimper_msec;
+		if (cmd.skip_dtim_periods)
+			cmd.flags |=
+				cpu_to_le16(POWER_FLAGS_SKIP_OVER_DTIM_MSK);
 	}
 	iwl_mvm_power_log(mvm, &cmd);
 #ifdef CONFIG_IWLWIFI_DEBUGFS
@@ -894,33 +934,3 @@ int iwl_mvm_update_d0i3_power_mode(struct iwl_mvm *mvm,
 
 	return ret;
 }
-
-int iwl_mvm_update_beacon_filter(struct iwl_mvm *mvm,
-				 struct ieee80211_vif *vif,
-				 bool force,
-				 u32 flags)
-{
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-
-	if (mvmvif != mvm->bf_allowed_vif)
-		return 0;
-
-	if (!mvmvif->bf_data.bf_enabled) {
-		/* disable beacon filtering explicitly if force is true */
-		if (force)
-			return iwl_mvm_disable_beacon_filter(mvm, vif, flags);
-		return 0;
-	}
-
-	return iwl_mvm_enable_beacon_filter(mvm, vif, flags);
-}
-
-int iwl_power_legacy_set_cam_mode(struct iwl_mvm *mvm)
-{
-	struct iwl_powertable_cmd cmd = {
-		.keep_alive_seconds = POWER_KEEP_ALIVE_PERIOD_SEC,
-	};
-
-	return iwl_mvm_send_cmd_pdu(mvm, POWER_TABLE_CMD, CMD_SYNC,
-				    sizeof(cmd), &cmd);
-}
diff --git a/drivers/net/wireless/iwlwifi/mvm/quota.c b/drivers/net/wireless/iwlwifi/mvm/quota.c
index 35e86e06dff..ba68d7b8450 100644
--- a/drivers/net/wireless/iwlwifi/mvm/quota.c
+++ b/drivers/net/wireless/iwlwifi/mvm/quota.c
@@ -285,7 +285,7 @@ int iwl_mvm_update_quotas(struct iwl_mvm *mvm, struct ieee80211_vif *newvif)
 
 	iwl_mvm_adjust_quota_for_noa(mvm, &cmd);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, CMD_SYNC,
+	ret = iwl_mvm_send_cmd_pdu(mvm, TIME_QUOTA_CMD, 0,
 				   sizeof(cmd), &cmd);
 	if (ret)
 		IWL_ERR(mvm, "Failed to send quota: %d\n", ret);
diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.c b/drivers/net/wireless/iwlwifi/mvm/rs.c
index e1c83889936..306a6caa486 100644
--- a/drivers/net/wireless/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/iwlwifi/mvm/rs.c
@@ -211,7 +211,7 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.next_columns = {
 			RS_COLUMN_LEGACY_ANT_B,
 			RS_COLUMN_SISO_ANT_A,
-			RS_COLUMN_SISO_ANT_B,
+			RS_COLUMN_MIMO2,
 			RS_COLUMN_INVALID,
 			RS_COLUMN_INVALID,
 			RS_COLUMN_INVALID,
@@ -223,8 +223,8 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.ant = ANT_B,
 		.next_columns = {
 			RS_COLUMN_LEGACY_ANT_A,
-			RS_COLUMN_SISO_ANT_A,
 			RS_COLUMN_SISO_ANT_B,
+			RS_COLUMN_MIMO2,
 			RS_COLUMN_INVALID,
 			RS_COLUMN_INVALID,
 			RS_COLUMN_INVALID,
@@ -238,10 +238,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_B,
 			RS_COLUMN_MIMO2,
 			RS_COLUMN_SISO_ANT_A_SGI,
-			RS_COLUMN_SISO_ANT_B_SGI,
 			RS_COLUMN_LEGACY_ANT_A,
 			RS_COLUMN_LEGACY_ANT_B,
 			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -254,10 +254,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_A,
 			RS_COLUMN_MIMO2,
 			RS_COLUMN_SISO_ANT_B_SGI,
-			RS_COLUMN_SISO_ANT_A_SGI,
 			RS_COLUMN_LEGACY_ANT_A,
 			RS_COLUMN_LEGACY_ANT_B,
 			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -271,10 +271,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_B_SGI,
 			RS_COLUMN_MIMO2_SGI,
 			RS_COLUMN_SISO_ANT_A,
-			RS_COLUMN_SISO_ANT_B,
-			RS_COLUMN_MIMO2,
 			RS_COLUMN_LEGACY_ANT_A,
 			RS_COLUMN_LEGACY_ANT_B,
+			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -289,10 +289,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
 			RS_COLUMN_SISO_ANT_A_SGI,
 			RS_COLUMN_MIMO2_SGI,
 			RS_COLUMN_SISO_ANT_B,
-			RS_COLUMN_SISO_ANT_A,
-			RS_COLUMN_MIMO2,
 			RS_COLUMN_LEGACY_ANT_A,
 			RS_COLUMN_LEGACY_ANT_B,
+			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
 		},
 		.checks = {
 			rs_siso_allow,
@@ -304,12 +304,12 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.ant = ANT_AB,
 		.next_columns = {
 			RS_COLUMN_SISO_ANT_A,
-			RS_COLUMN_SISO_ANT_B,
-			RS_COLUMN_SISO_ANT_A_SGI,
-			RS_COLUMN_SISO_ANT_B_SGI,
 			RS_COLUMN_MIMO2_SGI,
 			RS_COLUMN_LEGACY_ANT_A,
 			RS_COLUMN_LEGACY_ANT_B,
+			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
 		},
 		.checks = {
 			rs_mimo_allow,
@@ -321,12 +321,12 @@ static const struct rs_tx_column rs_tx_columns[] = {
 		.sgi = true,
 		.next_columns = {
 			RS_COLUMN_SISO_ANT_A_SGI,
-			RS_COLUMN_SISO_ANT_B_SGI,
-			RS_COLUMN_SISO_ANT_A,
-			RS_COLUMN_SISO_ANT_B,
 			RS_COLUMN_MIMO2,
 			RS_COLUMN_LEGACY_ANT_A,
 			RS_COLUMN_LEGACY_ANT_B,
+			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
+			RS_COLUMN_INVALID,
 		},
 		.checks = {
 			rs_mimo_allow,
@@ -527,6 +527,9 @@ static void rs_rate_scale_clear_tbl_windows(struct iwl_mvm *mvm,
 	IWL_DEBUG_RATE(mvm, "Clearing up window stats\n");
 	for (i = 0; i < IWL_RATE_COUNT; i++)
 		rs_rate_scale_clear_window(&tbl->win[i]);
+
+	for (i = 0; i < ARRAY_SIZE(tbl->tpc_win); i++)
+		rs_rate_scale_clear_window(&tbl->tpc_win[i]);
 }
 
 static inline u8 rs_is_valid_ant(u8 valid_antenna, u8 ant_type)
@@ -656,17 +659,34 @@ static int _rs_collect_tx_data(struct iwl_scale_tbl_info *tbl,
 	return 0;
 }
 
-static int rs_collect_tx_data(struct iwl_scale_tbl_info *tbl,
-			      int scale_index, int attempts, int successes)
+static int rs_collect_tx_data(struct iwl_lq_sta *lq_sta,
+			      struct iwl_scale_tbl_info *tbl,
+			      int scale_index, int attempts, int successes,
+			      u8 reduced_txp)
 {
 	struct iwl_rate_scale_data *window = NULL;
+	int ret;
 
 	if (scale_index < 0 || scale_index >= IWL_RATE_COUNT)
 		return -EINVAL;
 
+	if (tbl->column != RS_COLUMN_INVALID) {
+		lq_sta->tx_stats[tbl->column][scale_index].total += attempts;
+		lq_sta->tx_stats[tbl->column][scale_index].success += successes;
+	}
+
 	/* Select window for current tx bit rate */
 	window = &(tbl->win[scale_index]);
 
+	ret = _rs_collect_tx_data(tbl, scale_index, attempts, successes,
+				  window);
+	if (ret)
+		return ret;
+
+	if (WARN_ON_ONCE(reduced_txp > TPC_MAX_REDUCTION))
+		return -EINVAL;
+
+	window = &tbl->tpc_win[reduced_txp];
 	return _rs_collect_tx_data(tbl, scale_index, attempts, successes,
 				   window);
 }
@@ -1000,6 +1020,7 @@ static void rs_tx_status(void *mvm_r, struct ieee80211_supported_band *sband,
 	u32 ucode_rate;
 	struct rs_rate rate;
 	struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl;
+	u8 reduced_txp = (uintptr_t)info->status.status_driver_data[0];
 
 	/* Treat uninitialized rate scaling data same as non-existing. */
 	if (!lq_sta) {
@@ -1141,9 +1162,10 @@ static void rs_tx_status(void *mvm_r, struct ieee80211_supported_band *sband,
 	if (info->flags & IEEE80211_TX_STAT_AMPDU) {
 		ucode_rate = le32_to_cpu(table->rs_table[0]);
 		rs_rate_from_ucode_rate(ucode_rate, info->band, &rate);
-		rs_collect_tx_data(curr_tbl, rate.index,
+		rs_collect_tx_data(lq_sta, curr_tbl, rate.index,
 				   info->status.ampdu_len,
-				   info->status.ampdu_ack_len);
+				   info->status.ampdu_ack_len,
+				   reduced_txp);
 
 		/* Update success/fail counts if not searching for new mode */
 		if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) {
@@ -1176,8 +1198,9 @@ static void rs_tx_status(void *mvm_r, struct ieee80211_supported_band *sband,
 			else
 				continue;
 
-			rs_collect_tx_data(tmp_tbl, rate.index, 1,
-					   i < retries ? 0 : legacy_success);
+			rs_collect_tx_data(lq_sta, tmp_tbl, rate.index, 1,
+					   i < retries ? 0 : legacy_success,
+					   reduced_txp);
 		}
 
 		/* Update success/fail counts if not searching for new mode */
@@ -1188,6 +1211,7 @@ static void rs_tx_status(void *mvm_r, struct ieee80211_supported_band *sband,
 	}
 	/* The last TX rate is cached in lq_sta; it's set in if/else above */
 	lq_sta->last_rate_n_flags = ucode_rate;
+	IWL_DEBUG_RATE(mvm, "reduced txpower: %d\n", reduced_txp);
 done:
 	/* See if there's a better rate or modulation mode to try. */
 	if (sta && sta->supp_rates[sband->band])
@@ -1311,105 +1335,50 @@ static void rs_set_expected_tpt_table(struct iwl_lq_sta *lq_sta,
 	tbl->expected_tpt = rs_get_expected_tpt_table(lq_sta, column, rate->bw);
 }
 
-/*
- * Find starting rate for new "search" high-throughput mode of modulation.
- * Goal is to find lowest expected rate (under perfect conditions) that is
- * above the current measured throughput of "active" mode, to give new mode
- * a fair chance to prove itself without too many challenges.
- *
- * This gets called when transitioning to more aggressive modulation
- * (i.e. legacy to SISO or MIMO, or SISO to MIMO), as well as less aggressive
- * (i.e. MIMO to SISO).  When moving to MIMO, bit rate will typically need
- * to decrease to match "active" throughput.  When moving from MIMO to SISO,
- * bit rate will typically need to increase, but not if performance was bad.
- */
 static s32 rs_get_best_rate(struct iwl_mvm *mvm,
 			    struct iwl_lq_sta *lq_sta,
 			    struct iwl_scale_tbl_info *tbl,	/* "search" */
-			    u16 rate_mask, s8 index)
+			    unsigned long rate_mask, s8 index)
 {
-	/* "active" values */
 	struct iwl_scale_tbl_info *active_tbl =
 	    &(lq_sta->lq_info[lq_sta->active_tbl]);
-	s32 active_sr = active_tbl->win[index].success_ratio;
-	s32 active_tpt = active_tbl->expected_tpt[index];
-	/* expected "search" throughput */
+	s32 success_ratio = active_tbl->win[index].success_ratio;
+	u16 expected_current_tpt = active_tbl->expected_tpt[index];
 	const u16 *tpt_tbl = tbl->expected_tpt;
-
-	s32 new_rate, high, low, start_hi;
 	u16 high_low;
-	s8 rate = index;
-
-	new_rate = high = low = start_hi = IWL_RATE_INVALID;
-
-	while (1) {
-		high_low = rs_get_adjacent_rate(mvm, rate, rate_mask,
-						tbl->rate.type);
-
-		low = high_low & 0xff;
-		high = (high_low >> 8) & 0xff;
+	u32 target_tpt;
+	int rate_idx;
 
-		/*
-		 * Lower the "search" bit rate, to give new "search" mode
-		 * approximately the same throughput as "active" if:
-		 *
-		 * 1) "Active" mode has been working modestly well (but not
-		 *    great), and expected "search" throughput (under perfect
-		 *    conditions) at candidate rate is above the actual
-		 *    measured "active" throughput (but less than expected
-		 *    "active" throughput under perfect conditions).
-		 * OR
-		 * 2) "Active" mode has been working perfectly or very well
-		 *    and expected "search" throughput (under perfect
-		 *    conditions) at candidate rate is above expected
-		 *    "active" throughput (under perfect conditions).
-		 */
-		if ((((100 * tpt_tbl[rate]) > lq_sta->last_tpt) &&
-		     ((active_sr > RS_SR_FORCE_DECREASE) &&
-		      (active_sr <= IWL_RATE_HIGH_TH) &&
-		      (tpt_tbl[rate] <= active_tpt))) ||
-		    ((active_sr >= IWL_RATE_SCALE_SWITCH) &&
-		     (tpt_tbl[rate] > active_tpt))) {
-			/* (2nd or later pass)
-			 * If we've already tried to raise the rate, and are
-			 * now trying to lower it, use the higher rate. */
-			if (start_hi != IWL_RATE_INVALID) {
-				new_rate = start_hi;
-				break;
-			}
-
-			new_rate = rate;
+	if (success_ratio > RS_SR_NO_DECREASE) {
+		target_tpt = 100 * expected_current_tpt;
+		IWL_DEBUG_RATE(mvm,
+			       "SR %d high. Find rate exceeding EXPECTED_CURRENT %d\n",
+			       success_ratio, target_tpt);
+	} else {
+		target_tpt = lq_sta->last_tpt;
+		IWL_DEBUG_RATE(mvm,
+			       "SR %d not thag good. Find rate exceeding ACTUAL_TPT %d\n",
+			       success_ratio, target_tpt);
+	}
 
-			/* Loop again with lower rate */
-			if (low != IWL_RATE_INVALID)
-				rate = low;
+	rate_idx = find_first_bit(&rate_mask, BITS_PER_LONG);
 
-			/* Lower rate not available, use the original */
-			else
-				break;
-
-		/* Else try to raise the "search" rate to match "active" */
-		} else {
-			/* (2nd or later pass)
-			 * If we've already tried to lower the rate, and are
-			 * now trying to raise it, use the lower rate. */
-			if (new_rate != IWL_RATE_INVALID)
-				break;
+	while (rate_idx != IWL_RATE_INVALID) {
+		if (target_tpt < (100 * tpt_tbl[rate_idx]))
+			break;
 
-			/* Loop again with higher rate */
-			else if (high != IWL_RATE_INVALID) {
-				start_hi = high;
-				rate = high;
+		high_low = rs_get_adjacent_rate(mvm, rate_idx, rate_mask,
+						tbl->rate.type);
 
-			/* Higher rate not available, use the original */
-			} else {
-				new_rate = rate;
-				break;
-			}
-		}
+		rate_idx = (high_low >> 8) & 0xff;
 	}
 
-	return new_rate;
+	IWL_DEBUG_RATE(mvm, "Best rate found %d target_tp %d expected_new %d\n",
+		       rate_idx, target_tpt,
+		       rate_idx != IWL_RATE_INVALID ?
+		       100 * tpt_tbl[rate_idx] : IWL_INVALID_VALUE);
+
+	return rate_idx;
 }
 
 static u32 rs_bw_from_sta_bw(struct ieee80211_sta *sta)
@@ -1584,7 +1553,7 @@ static enum rs_column rs_get_next_column(struct iwl_mvm *mvm,
 
 		tpt = lq_sta->last_tpt / 100;
 		expected_tpt_tbl = rs_get_expected_tpt_table(lq_sta, next_col,
-							     tbl->rate.bw);
+						     rs_bw_from_sta_bw(sta));
 		if (WARN_ON_ONCE(!expected_tpt_tbl))
 			continue;
 
@@ -1625,7 +1594,7 @@ static int rs_switch_to_column(struct iwl_mvm *mvm,
 	const struct rs_tx_column *curr_column = &rs_tx_columns[tbl->column];
 	u32 sz = (sizeof(struct iwl_scale_tbl_info) -
 		  (sizeof(struct iwl_rate_scale_data) * IWL_RATE_COUNT));
-	u16 rate_mask = 0;
+	unsigned long rate_mask = 0;
 	u32 rate_idx = 0;
 
 	memcpy(search_tbl, tbl, sz);
@@ -1667,7 +1636,7 @@ static int rs_switch_to_column(struct iwl_mvm *mvm,
 		    !(BIT(rate_idx) & rate_mask)) {
 			IWL_DEBUG_RATE(mvm,
 				       "can not switch with index %d"
-				       " rate mask %x\n",
+				       " rate mask %lx\n",
 				       rate_idx, rate_mask);
 
 			goto err;
@@ -1769,6 +1738,203 @@ out:
 	return action;
 }
 
+static void rs_get_adjacent_txp(struct iwl_mvm *mvm, int index,
+				int *weaker, int *stronger)
+{
+	*weaker = index + TPC_TX_POWER_STEP;
+	if (*weaker > TPC_MAX_REDUCTION)
+		*weaker = TPC_INVALID;
+
+	*stronger = index - TPC_TX_POWER_STEP;
+	if (*stronger < 0)
+		*stronger = TPC_INVALID;
+}
+
+static bool rs_tpc_allowed(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			   struct rs_rate *rate, enum ieee80211_band band)
+{
+	int index = rate->index;
+	bool cam = (iwlmvm_mod_params.power_scheme == IWL_POWER_SCHEME_CAM);
+	bool sta_ps_disabled = (vif->type == NL80211_IFTYPE_STATION &&
+				!vif->bss_conf.ps);
+
+	IWL_DEBUG_RATE(mvm, "cam: %d sta_ps_disabled %d\n",
+		       cam, sta_ps_disabled);
+	/*
+	 * allow tpc only if power management is enabled, or bt coex
+	 * activity grade allows it and we are on 2.4Ghz.
+	 */
+	if ((cam || sta_ps_disabled) &&
+	    !iwl_mvm_bt_coex_is_tpc_allowed(mvm, band))
+		return false;
+
+	IWL_DEBUG_RATE(mvm, "check rate, table type: %d\n", rate->type);
+	if (is_legacy(rate))
+		return index == IWL_RATE_54M_INDEX;
+	if (is_ht(rate))
+		return index == IWL_RATE_MCS_7_INDEX;
+	if (is_vht(rate))
+		return index == IWL_RATE_MCS_7_INDEX ||
+		       index == IWL_RATE_MCS_8_INDEX ||
+		       index == IWL_RATE_MCS_9_INDEX;
+
+	WARN_ON_ONCE(1);
+	return false;
+}
+
+enum tpc_action {
+	TPC_ACTION_STAY,
+	TPC_ACTION_DECREASE,
+	TPC_ACTION_INCREASE,
+	TPC_ACTION_NO_RESTIRCTION,
+};
+
+static enum tpc_action rs_get_tpc_action(struct iwl_mvm *mvm,
+					 s32 sr, int weak, int strong,
+					 int current_tpt,
+					 int weak_tpt, int strong_tpt)
+{
+	/* stay until we have valid tpt */
+	if (current_tpt == IWL_INVALID_VALUE) {
+		IWL_DEBUG_RATE(mvm, "no current tpt. stay.\n");
+		return TPC_ACTION_STAY;
+	}
+
+	/* Too many failures, increase txp */
+	if (sr <= TPC_SR_FORCE_INCREASE || current_tpt == 0) {
+		IWL_DEBUG_RATE(mvm, "increase txp because of weak SR\n");
+		return TPC_ACTION_NO_RESTIRCTION;
+	}
+
+	/* try decreasing first if applicable */
+	if (weak != TPC_INVALID) {
+		if (weak_tpt == IWL_INVALID_VALUE &&
+		    (strong_tpt == IWL_INVALID_VALUE ||
+		     current_tpt >= strong_tpt)) {
+			IWL_DEBUG_RATE(mvm,
+				       "no weak txp measurement. decrease txp\n");
+			return TPC_ACTION_DECREASE;
+		}
+
+		if (weak_tpt > current_tpt) {
+			IWL_DEBUG_RATE(mvm,
+				       "lower txp has better tpt. decrease txp\n");
+			return TPC_ACTION_DECREASE;
+		}
+	}
+
+	/* next, increase if needed */
+	if (sr < TPC_SR_NO_INCREASE && strong != TPC_INVALID) {
+		if (weak_tpt == IWL_INVALID_VALUE &&
+		    strong_tpt != IWL_INVALID_VALUE &&
+		    current_tpt < strong_tpt) {
+			IWL_DEBUG_RATE(mvm,
+				       "higher txp has better tpt. increase txp\n");
+			return TPC_ACTION_INCREASE;
+		}
+
+		if (weak_tpt < current_tpt &&
+		    (strong_tpt == IWL_INVALID_VALUE ||
+		     strong_tpt > current_tpt)) {
+			IWL_DEBUG_RATE(mvm,
+				       "lower txp has worse tpt. increase txp\n");
+			return TPC_ACTION_INCREASE;
+		}
+	}
+
+	IWL_DEBUG_RATE(mvm, "no need to increase or decrease txp - stay\n");
+	return TPC_ACTION_STAY;
+}
+
+static bool rs_tpc_perform(struct iwl_mvm *mvm,
+			   struct ieee80211_sta *sta,
+			   struct iwl_lq_sta *lq_sta,
+			   struct iwl_scale_tbl_info *tbl)
+{
+	struct iwl_mvm_sta *mvm_sta = (void *)sta->drv_priv;
+	struct ieee80211_vif *vif = mvm_sta->vif;
+	struct ieee80211_chanctx_conf *chanctx_conf;
+	enum ieee80211_band band;
+	struct iwl_rate_scale_data *window;
+	struct rs_rate *rate = &tbl->rate;
+	enum tpc_action action;
+	s32 sr;
+	u8 cur = lq_sta->lq.reduced_tpc;
+	int current_tpt;
+	int weak, strong;
+	int weak_tpt = IWL_INVALID_VALUE, strong_tpt = IWL_INVALID_VALUE;
+
+#ifdef CONFIG_MAC80211_DEBUGFS
+	if (lq_sta->dbg_fixed_txp_reduction <= TPC_MAX_REDUCTION) {
+		IWL_DEBUG_RATE(mvm, "fixed tpc: %d\n",
+			       lq_sta->dbg_fixed_txp_reduction);
+		lq_sta->lq.reduced_tpc = lq_sta->dbg_fixed_txp_reduction;
+		return cur != lq_sta->dbg_fixed_txp_reduction;
+	}
+#endif
+
+	rcu_read_lock();
+	chanctx_conf = rcu_dereference(vif->chanctx_conf);
+	if (WARN_ON(!chanctx_conf))
+		band = IEEE80211_NUM_BANDS;
+	else
+		band = chanctx_conf->def.chan->band;
+	rcu_read_unlock();
+
+	if (!rs_tpc_allowed(mvm, vif, rate, band)) {
+		IWL_DEBUG_RATE(mvm,
+			       "tpc is not allowed. remove txp restrictions\n");
+		lq_sta->lq.reduced_tpc = TPC_NO_REDUCTION;
+		return cur != TPC_NO_REDUCTION;
+	}
+
+	rs_get_adjacent_txp(mvm, cur, &weak, &strong);
+
+	/* Collect measured throughputs for current and adjacent rates */
+	window = tbl->tpc_win;
+	sr = window[cur].success_ratio;
+	current_tpt = window[cur].average_tpt;
+	if (weak != TPC_INVALID)
+		weak_tpt = window[weak].average_tpt;
+	if (strong != TPC_INVALID)
+		strong_tpt = window[strong].average_tpt;
+
+	IWL_DEBUG_RATE(mvm,
+		       "(TPC: %d): cur_tpt %d SR %d weak %d strong %d weak_tpt %d strong_tpt %d\n",
+		       cur, current_tpt, sr, weak, strong,
+		       weak_tpt, strong_tpt);
+
+	action = rs_get_tpc_action(mvm, sr, weak, strong,
+				   current_tpt, weak_tpt, strong_tpt);
+
+	/* override actions if we are on the edge */
+	if (weak == TPC_INVALID && action == TPC_ACTION_DECREASE) {
+		IWL_DEBUG_RATE(mvm, "already in lowest txp, stay\n");
+		action = TPC_ACTION_STAY;
+	} else if (strong == TPC_INVALID &&
+		   (action == TPC_ACTION_INCREASE ||
+		    action == TPC_ACTION_NO_RESTIRCTION)) {
+		IWL_DEBUG_RATE(mvm, "already in highest txp, stay\n");
+		action = TPC_ACTION_STAY;
+	}
+
+	switch (action) {
+	case TPC_ACTION_DECREASE:
+		lq_sta->lq.reduced_tpc = weak;
+		return true;
+	case TPC_ACTION_INCREASE:
+		lq_sta->lq.reduced_tpc = strong;
+		return true;
+	case TPC_ACTION_NO_RESTIRCTION:
+		lq_sta->lq.reduced_tpc = TPC_NO_REDUCTION;
+		return true;
+	case TPC_ACTION_STAY:
+		/* do nothing */
+		break;
+	}
+	return false;
+}
+
 /*
  * Do rate scaling and search for new modulation mode.
  */
@@ -2019,6 +2185,9 @@ static void rs_rate_scale_perform(struct iwl_mvm *mvm,
 		break;
 	case RS_ACTION_STAY:
 		/* No change */
+		if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN)
+			update_lq = rs_tpc_perform(mvm, sta, lq_sta, tbl);
+		break;
 	default:
 		break;
 	}
@@ -2271,10 +2440,6 @@ static void rs_vht_set_enabled_rates(struct ieee80211_sta *sta,
 			if (i == IWL_RATE_9M_INDEX)
 				continue;
 
-			/* Disable MCS9 as a workaround */
-			if (i == IWL_RATE_MCS_9_INDEX)
-				continue;
-
 			/* VHT MCS9 isn't valid for 20Mhz for NSS=1,2 */
 			if (i == IWL_RATE_MCS_9_INDEX &&
 			    sta->bandwidth == IEEE80211_STA_RX_BW_20)
@@ -2293,10 +2458,6 @@ static void rs_vht_set_enabled_rates(struct ieee80211_sta *sta,
 			if (i == IWL_RATE_9M_INDEX)
 				continue;
 
-			/* Disable MCS9 as a workaround */
-			if (i == IWL_RATE_MCS_9_INDEX)
-				continue;
-
 			/* VHT MCS9 isn't valid for 20Mhz for NSS=1,2 */
 			if (i == IWL_RATE_MCS_9_INDEX &&
 			    sta->bandwidth == IEEE80211_STA_RX_BW_20)
@@ -2478,6 +2639,7 @@ void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	lq_sta->is_agg = 0;
 #ifdef CONFIG_MAC80211_DEBUGFS
 	lq_sta->dbg_fixed_rate = 0;
+	lq_sta->dbg_fixed_txp_reduction = TPC_INVALID;
 #endif
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	iwl_mvm_reset_frame_stats(mvm, &mvm->drv_rx_stats);
@@ -2653,6 +2815,7 @@ static void rs_fill_lq_cmd(struct iwl_mvm *mvm,
 		rs_build_rates_table_from_fixed(mvm, lq_cmd,
 						lq_sta->band,
 						lq_sta->dbg_fixed_rate);
+		lq_cmd->reduced_tpc = 0;
 		ant = (lq_sta->dbg_fixed_rate & RATE_MCS_ANT_ABC_MSK) >>
 			RATE_MCS_ANT_POS;
 	} else
@@ -2783,7 +2946,6 @@ static ssize_t rs_sta_dbgfs_scale_table_write(struct file *file,
 	size_t buf_size;
 	u32 parsed_rate;
 
-
 	mvm = lq_sta->drv;
 	memset(buf, 0, sizeof(buf));
 	buf_size = min(count, sizeof(buf) -  1);
@@ -2856,6 +3018,7 @@ static ssize_t rs_sta_dbgfs_scale_table_read(struct file *file,
 			lq_sta->lq.agg_disable_start_th,
 			lq_sta->lq.agg_frame_cnt_limit);
 
+	desc += sprintf(buff+desc, "reduced tpc=%d\n", lq_sta->lq.reduced_tpc);
 	desc += sprintf(buff+desc,
 			"Start idx [0]=0x%x [1]=0x%x [2]=0x%x [3]=0x%x\n",
 			lq_sta->lq.initial_rate_index[0],
@@ -2928,6 +3091,94 @@ static const struct file_operations rs_sta_dbgfs_stats_table_ops = {
 	.llseek = default_llseek,
 };
 
+static ssize_t rs_sta_dbgfs_drv_tx_stats_read(struct file *file,
+					      char __user *user_buf,
+					      size_t count, loff_t *ppos)
+{
+	static const char * const column_name[] = {
+		[RS_COLUMN_LEGACY_ANT_A] = "LEGACY_ANT_A",
+		[RS_COLUMN_LEGACY_ANT_B] = "LEGACY_ANT_B",
+		[RS_COLUMN_SISO_ANT_A] = "SISO_ANT_A",
+		[RS_COLUMN_SISO_ANT_B] = "SISO_ANT_B",
+		[RS_COLUMN_SISO_ANT_A_SGI] = "SISO_ANT_A_SGI",
+		[RS_COLUMN_SISO_ANT_B_SGI] = "SISO_ANT_B_SGI",
+		[RS_COLUMN_MIMO2] = "MIMO2",
+		[RS_COLUMN_MIMO2_SGI] = "MIMO2_SGI",
+	};
+
+	static const char * const rate_name[] = {
+		[IWL_RATE_1M_INDEX] = "1M",
+		[IWL_RATE_2M_INDEX] = "2M",
+		[IWL_RATE_5M_INDEX] = "5.5M",
+		[IWL_RATE_11M_INDEX] = "11M",
+		[IWL_RATE_6M_INDEX] = "6M|MCS0",
+		[IWL_RATE_9M_INDEX] = "9M",
+		[IWL_RATE_12M_INDEX] = "12M|MCS1",
+		[IWL_RATE_18M_INDEX] = "18M|MCS2",
+		[IWL_RATE_24M_INDEX] = "24M|MCS3",
+		[IWL_RATE_36M_INDEX] = "36M|MCS4",
+		[IWL_RATE_48M_INDEX] = "48M|MCS5",
+		[IWL_RATE_54M_INDEX] = "54M|MCS6",
+		[IWL_RATE_MCS_7_INDEX] = "MCS7",
+		[IWL_RATE_MCS_8_INDEX] = "MCS8",
+		[IWL_RATE_MCS_9_INDEX] = "MCS9",
+	};
+
+	char *buff, *pos, *endpos;
+	int col, rate;
+	ssize_t ret;
+	struct iwl_lq_sta *lq_sta = file->private_data;
+	struct rs_rate_stats *stats;
+	static const size_t bufsz = 1024;
+
+	buff = kmalloc(bufsz, GFP_KERNEL);
+	if (!buff)
+		return -ENOMEM;
+
+	pos = buff;
+	endpos = pos + bufsz;
+
+	pos += scnprintf(pos, endpos - pos, "COLUMN,");
+	for (rate = 0; rate < IWL_RATE_COUNT; rate++)
+		pos += scnprintf(pos, endpos - pos, "%s,", rate_name[rate]);
+	pos += scnprintf(pos, endpos - pos, "\n");
+
+	for (col = 0; col < RS_COLUMN_COUNT; col++) {
+		pos += scnprintf(pos, endpos - pos,
+				 "%s,", column_name[col]);
+
+		for (rate = 0; rate < IWL_RATE_COUNT; rate++) {
+			stats = &(lq_sta->tx_stats[col][rate]);
+			pos += scnprintf(pos, endpos - pos,
+					 "%llu/%llu,",
+					 stats->success,
+					 stats->total);
+		}
+		pos += scnprintf(pos, endpos - pos, "\n");
+	}
+
+	ret = simple_read_from_buffer(user_buf, count, ppos, buff, pos - buff);
+	kfree(buff);
+	return ret;
+}
+
+static ssize_t rs_sta_dbgfs_drv_tx_stats_write(struct file *file,
+					       const char __user *user_buf,
+					       size_t count, loff_t *ppos)
+{
+	struct iwl_lq_sta *lq_sta = file->private_data;
+	memset(lq_sta->tx_stats, 0, sizeof(lq_sta->tx_stats));
+
+	return count;
+}
+
+static const struct file_operations rs_sta_dbgfs_drv_tx_stats_ops = {
+	.read = rs_sta_dbgfs_drv_tx_stats_read,
+	.write = rs_sta_dbgfs_drv_tx_stats_write,
+	.open = simple_open,
+	.llseek = default_llseek,
+};
+
 static void rs_add_debugfs(void *mvm, void *mvm_sta, struct dentry *dir)
 {
 	struct iwl_lq_sta *lq_sta = mvm_sta;
@@ -2937,9 +3188,15 @@ static void rs_add_debugfs(void *mvm, void *mvm_sta, struct dentry *dir)
 	lq_sta->rs_sta_dbgfs_stats_table_file =
 		debugfs_create_file("rate_stats_table", S_IRUSR, dir,
 				    lq_sta, &rs_sta_dbgfs_stats_table_ops);
+	lq_sta->rs_sta_dbgfs_drv_tx_stats_file =
+		debugfs_create_file("drv_tx_stats", S_IRUSR | S_IWUSR, dir,
+				    lq_sta, &rs_sta_dbgfs_drv_tx_stats_ops);
 	lq_sta->rs_sta_dbgfs_tx_agg_tid_en_file =
 		debugfs_create_u8("tx_agg_tid_enable", S_IRUSR | S_IWUSR, dir,
 				  &lq_sta->tx_agg_tid_en);
+	lq_sta->rs_sta_dbgfs_reduced_txp_file =
+		debugfs_create_u8("reduced_tpc", S_IRUSR | S_IWUSR, dir,
+				  &lq_sta->dbg_fixed_txp_reduction);
 }
 
 static void rs_remove_debugfs(void *mvm, void *mvm_sta)
@@ -2947,7 +3204,9 @@ static void rs_remove_debugfs(void *mvm, void *mvm_sta)
 	struct iwl_lq_sta *lq_sta = mvm_sta;
 	debugfs_remove(lq_sta->rs_sta_dbgfs_scale_table_file);
 	debugfs_remove(lq_sta->rs_sta_dbgfs_stats_table_file);
+	debugfs_remove(lq_sta->rs_sta_dbgfs_drv_tx_stats_file);
 	debugfs_remove(lq_sta->rs_sta_dbgfs_tx_agg_tid_en_file);
+	debugfs_remove(lq_sta->rs_sta_dbgfs_reduced_txp_file);
 }
 #endif
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.h b/drivers/net/wireless/iwlwifi/mvm/rs.h
index 0acfac96a56..374a83d7db2 100644
--- a/drivers/net/wireless/iwlwifi/mvm/rs.h
+++ b/drivers/net/wireless/iwlwifi/mvm/rs.h
@@ -158,6 +158,13 @@ enum {
 #define RS_SR_FORCE_DECREASE		1920	/*  15% */
 #define RS_SR_NO_DECREASE		10880	/*  85% */
 
+#define TPC_SR_FORCE_INCREASE		9600	/* 75% */
+#define TPC_SR_NO_INCREASE		10880	/* 85% */
+#define TPC_TX_POWER_STEP		3
+#define TPC_MAX_REDUCTION		15
+#define TPC_NO_REDUCTION		0
+#define TPC_INVALID			0xff
+
 #define LINK_QUAL_AGG_TIME_LIMIT_DEF	(4000) /* 4 milliseconds */
 #define LINK_QUAL_AGG_TIME_LIMIT_MAX	(8000)
 #define LINK_QUAL_AGG_TIME_LIMIT_MIN	(100)
@@ -266,9 +273,16 @@ enum rs_column {
 	RS_COLUMN_MIMO2_SGI,
 
 	RS_COLUMN_LAST = RS_COLUMN_MIMO2_SGI,
+	RS_COLUMN_COUNT = RS_COLUMN_LAST + 1,
 	RS_COLUMN_INVALID,
 };
 
+/* Packet stats per rate */
+struct rs_rate_stats {
+	u64 success;
+	u64 total;
+};
+
 /**
  * struct iwl_scale_tbl_info -- tx params and success history for all rates
  *
@@ -280,6 +294,8 @@ struct iwl_scale_tbl_info {
 	enum rs_column column;
 	const u16 *expected_tpt;	/* throughput metrics; expected_tpt_G, etc. */
 	struct iwl_rate_scale_data win[IWL_RATE_COUNT]; /* rate histories */
+	/* per txpower-reduction history */
+	struct iwl_rate_scale_data tpc_win[TPC_MAX_REDUCTION + 1];
 };
 
 enum {
@@ -315,6 +331,8 @@ struct iwl_lq_sta {
 	bool is_vht;
 	enum ieee80211_band band;
 
+	struct rs_rate_stats tx_stats[RS_COLUMN_COUNT][IWL_RATE_COUNT];
+
 	/* The following are bitmaps of rates; IWL_RATE_6M_MASK, etc. */
 	unsigned long active_legacy_rate;
 	unsigned long active_siso_rate;
@@ -334,8 +352,11 @@ struct iwl_lq_sta {
 #ifdef CONFIG_MAC80211_DEBUGFS
 	struct dentry *rs_sta_dbgfs_scale_table_file;
 	struct dentry *rs_sta_dbgfs_stats_table_file;
+	struct dentry *rs_sta_dbgfs_drv_tx_stats_file;
 	struct dentry *rs_sta_dbgfs_tx_agg_tid_en_file;
+	struct dentry *rs_sta_dbgfs_reduced_txp_file;
 	u32 dbg_fixed_rate;
+	u8 dbg_fixed_txp_reduction;
 #endif
 	struct iwl_mvm *drv;
 
@@ -345,6 +366,9 @@ struct iwl_lq_sta {
 	u32 last_rate_n_flags;
 	/* packets destined for this STA are aggregated */
 	u8 is_agg;
+
+	/* tx power reduce for this sta */
+	int tpc_reduce;
 };
 
 /* Initialize station's rate scaling information after adding station */
diff --git a/drivers/net/wireless/iwlwifi/mvm/rx.c b/drivers/net/wireless/iwlwifi/mvm/rx.c
index 6061553a5e4..cf7276967ac 100644
--- a/drivers/net/wireless/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/rx.c
@@ -60,7 +60,6 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *****************************************************************************/
 #include "iwl-trans.h"
-
 #include "mvm.h"
 #include "fw-api.h"
 
@@ -130,42 +129,7 @@ static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm,
 
 	memcpy(IEEE80211_SKB_RXCB(skb), stats, sizeof(*stats));
 
-	ieee80211_rx_ni(mvm->hw, skb);
-}
-
-static void iwl_mvm_calc_rssi(struct iwl_mvm *mvm,
-			      struct iwl_rx_phy_info *phy_info,
-			      struct ieee80211_rx_status *rx_status)
-{
-	int rssi_a, rssi_b, rssi_a_dbm, rssi_b_dbm, max_rssi_dbm;
-	u32 agc_a, agc_b;
-	u32 val;
-
-	val = le32_to_cpu(phy_info->non_cfg_phy[IWL_RX_INFO_AGC_IDX]);
-	agc_a = (val & IWL_OFDM_AGC_A_MSK) >> IWL_OFDM_AGC_A_POS;
-	agc_b = (val & IWL_OFDM_AGC_B_MSK) >> IWL_OFDM_AGC_B_POS;
-
-	val = le32_to_cpu(phy_info->non_cfg_phy[IWL_RX_INFO_RSSI_AB_IDX]);
-	rssi_a = (val & IWL_OFDM_RSSI_INBAND_A_MSK) >> IWL_OFDM_RSSI_A_POS;
-	rssi_b = (val & IWL_OFDM_RSSI_INBAND_B_MSK) >> IWL_OFDM_RSSI_B_POS;
-
-	/*
-	 * dBm = rssi dB - agc dB - constant.
-	 * Higher AGC (higher radio gain) means lower signal.
-	 */
-	rssi_a_dbm = rssi_a - IWL_RSSI_OFFSET - agc_a;
-	rssi_b_dbm = rssi_b - IWL_RSSI_OFFSET - agc_b;
-	max_rssi_dbm = max_t(int, rssi_a_dbm, rssi_b_dbm);
-
-	IWL_DEBUG_STATS(mvm, "Rssi In A %d B %d Max %d AGCA %d AGCB %d\n",
-			rssi_a_dbm, rssi_b_dbm, max_rssi_dbm, agc_a, agc_b);
-
-	rx_status->signal = max_rssi_dbm;
-	rx_status->chains = (le16_to_cpu(phy_info->phy_flags) &
-				RX_RES_PHY_FLAGS_ANTENNA)
-					>> RX_RES_PHY_FLAGS_ANTENNA_POS;
-	rx_status->chain_signal[0] = rssi_a_dbm;
-	rx_status->chain_signal[1] = rssi_b_dbm;
+	ieee80211_rx(mvm->hw, skb);
 }
 
 /*
@@ -337,10 +301,7 @@ int iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
 	 */
 	/*rx_status.flag |= RX_FLAG_MACTIME_MPDU;*/
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_RX_ENERGY_API)
-		iwl_mvm_get_signal_strength(mvm, phy_info, &rx_status);
-	else
-		iwl_mvm_calc_rssi(mvm, phy_info, &rx_status);
+	iwl_mvm_get_signal_strength(mvm, phy_info, &rx_status);
 
 	IWL_DEBUG_STATS_LIMIT(mvm, "Rssi %d, TSF %llu\n", rx_status.signal,
 			      (unsigned long long)rx_status.mactime);
@@ -394,6 +355,8 @@ int iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
 		rx_status.rate_idx = rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK;
 		rx_status.flag |= RX_FLAG_VHT;
 		rx_status.flag |= stbc << RX_FLAG_STBC_SHIFT;
+		if (rate_n_flags & RATE_MCS_BF_MSK)
+			rx_status.vht_flag |= RX_VHT_FLAG_BF;
 	} else {
 		rx_status.rate_idx =
 			iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index c28de54c75d..eac2b424f6a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -306,7 +306,6 @@ int iwl_mvm_scan_request(struct iwl_mvm *mvm,
 		.id = SCAN_REQUEST_CMD,
 		.len = { 0, },
 		.data = { mvm->scan_cmd, },
-		.flags = CMD_SYNC,
 		.dataflags = { IWL_HCMD_DFL_NOCOPY, },
 	};
 	struct iwl_scan_cmd *cmd = mvm->scan_cmd;
@@ -319,7 +318,10 @@ int iwl_mvm_scan_request(struct iwl_mvm *mvm,
 	struct iwl_mvm_scan_params params = {};
 
 	lockdep_assert_held(&mvm->mutex);
-	BUG_ON(mvm->scan_cmd == NULL);
+
+	/* we should have failed registration if scan_cmd was NULL */
+	if (WARN_ON(mvm->scan_cmd == NULL))
+		return -ENOMEM;
 
 	IWL_DEBUG_SCAN(mvm, "Handling mac80211 scan request\n");
 	mvm->scan_status = IWL_MVM_SCAN_OS;
@@ -514,7 +516,7 @@ int iwl_mvm_cancel_scan(struct iwl_mvm *mvm)
 				   ARRAY_SIZE(scan_abort_notif),
 				   iwl_mvm_scan_abort_notif, NULL);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, SCAN_ABORT_CMD, CMD_SYNC, 0, NULL);
+	ret = iwl_mvm_send_cmd_pdu(mvm, SCAN_ABORT_CMD, 0, 0, NULL);
 	if (ret) {
 		IWL_ERR(mvm, "Couldn't send SCAN_ABORT_CMD: %d\n", ret);
 		/* mac80211's state will be cleaned in the nic_restart flow */
@@ -538,9 +540,13 @@ int iwl_mvm_rx_scan_offload_complete_notif(struct iwl_mvm *mvm,
 	/* scan status must be locked for proper checking */
 	lockdep_assert_held(&mvm->mutex);
 
-	IWL_DEBUG_SCAN(mvm, "Scheduled scan completed, status %s\n",
+	IWL_DEBUG_SCAN(mvm,
+		       "Scheduled scan completed, status %s EBS status %s:%d\n",
 		       scan_notif->status == IWL_SCAN_OFFLOAD_COMPLETED ?
-		       "completed" : "aborted");
+		       "completed" : "aborted", scan_notif->ebs_status ==
+		       IWL_SCAN_EBS_SUCCESS ? "success" : "failed",
+		       scan_notif->ebs_status);
+
 
 	/* only call mac80211 completion if the stop was initiated by FW */
 	if (mvm->scan_status == IWL_MVM_SCAN_SCHED) {
@@ -548,6 +554,8 @@ int iwl_mvm_rx_scan_offload_complete_notif(struct iwl_mvm *mvm,
 		ieee80211_sched_scan_stopped(mvm->hw);
 	}
 
+	mvm->last_ebs_successful = !scan_notif->ebs_status;
+
 	return 0;
 }
 
@@ -580,9 +588,7 @@ static void iwl_build_scan_cmd(struct iwl_mvm *mvm,
 			       struct iwl_scan_offload_cmd *scan,
 			       struct iwl_mvm_scan_params *params)
 {
-	scan->channel_count =
-		mvm->nvm_data->bands[IEEE80211_BAND_2GHZ].n_channels +
-		mvm->nvm_data->bands[IEEE80211_BAND_5GHZ].n_channels;
+	scan->channel_count = req->n_channels;
 	scan->quiet_time = cpu_to_le16(IWL_ACTIVE_QUIET_TIME);
 	scan->quiet_plcp_th = cpu_to_le16(IWL_PLCP_QUIET_THRESH);
 	scan->good_CRC_th = IWL_GOOD_CRC_TH_DEFAULT;
@@ -661,61 +667,37 @@ static void iwl_build_channel_cfg(struct iwl_mvm *mvm,
 				  struct cfg80211_sched_scan_request *req,
 				  struct iwl_scan_channel_cfg *channels,
 				  enum ieee80211_band band,
-				  int *head, int *tail,
+				  int *head,
 				  u32 ssid_bitmap,
 				  struct iwl_mvm_scan_params *params)
 {
-	struct ieee80211_supported_band *s_band;
-	int n_channels = req->n_channels;
-	int i, j, index = 0;
-	bool partial;
+	int i, index = 0;
 
-	/*
-	 * We have to configure all supported channels, even if we don't want to
-	 * scan on them, but we have to send channels in the order that we want
-	 * to scan. So add requested channels to head of the list and others to
-	 * the end.
-	*/
-	s_band = &mvm->nvm_data->bands[band];
-
-	for (i = 0; i < s_band->n_channels && *head <= *tail; i++) {
-		partial = false;
-		for (j = 0; j < n_channels; j++)
-			if (s_band->channels[i].center_freq ==
-						req->channels[j]->center_freq) {
-				index = *head;
-				(*head)++;
-				/*
-				 * Channels that came with the request will be
-				 * in partial scan .
-				 */
-				partial = true;
-				break;
-			}
-		if (!partial) {
-			index = *tail;
-			(*tail)--;
-		}
-		channels->channel_number[index] =
-			cpu_to_le16(ieee80211_frequency_to_channel(
-					s_band->channels[i].center_freq));
+	for (i = 0; i < req->n_channels; i++) {
+		struct ieee80211_channel *chan = req->channels[i];
+
+		if (chan->band != band)
+			continue;
+
+		index = *head;
+		(*head)++;
+
+		channels->channel_number[index] = cpu_to_le16(chan->hw_value);
 		channels->dwell_time[index][0] = params->dwell[band].active;
 		channels->dwell_time[index][1] = params->dwell[band].passive;
 
 		channels->iter_count[index] = cpu_to_le16(1);
 		channels->iter_interval[index] = 0;
 
-		if (!(s_band->channels[i].flags & IEEE80211_CHAN_NO_IR))
+		if (!(chan->flags & IEEE80211_CHAN_NO_IR))
 			channels->type[index] |=
 				cpu_to_le32(IWL_SCAN_OFFLOAD_CHANNEL_ACTIVE);
 
 		channels->type[index] |=
-				cpu_to_le32(IWL_SCAN_OFFLOAD_CHANNEL_FULL);
-		if (partial)
-			channels->type[index] |=
-				cpu_to_le32(IWL_SCAN_OFFLOAD_CHANNEL_PARTIAL);
+				cpu_to_le32(IWL_SCAN_OFFLOAD_CHANNEL_FULL |
+					    IWL_SCAN_OFFLOAD_CHANNEL_PARTIAL);
 
-		if (s_band->channels[i].flags & IEEE80211_CHAN_NO_HT40)
+		if (chan->flags & IEEE80211_CHAN_NO_HT40)
 			channels->type[index] |=
 				cpu_to_le32(IWL_SCAN_OFFLOAD_CHANNEL_NARROW);
 
@@ -732,7 +714,6 @@ int iwl_mvm_config_sched_scan(struct iwl_mvm *mvm,
 	int band_2ghz = mvm->nvm_data->bands[IEEE80211_BAND_2GHZ].n_channels;
 	int band_5ghz = mvm->nvm_data->bands[IEEE80211_BAND_5GHZ].n_channels;
 	int head = 0;
-	int tail = band_2ghz + band_5ghz - 1;
 	u32 ssid_bitmap;
 	int cmd_len;
 	int ret;
@@ -740,7 +721,6 @@ int iwl_mvm_config_sched_scan(struct iwl_mvm *mvm,
 	struct iwl_scan_offload_cfg *scan_cfg;
 	struct iwl_host_cmd cmd = {
 		.id = SCAN_OFFLOAD_CONFIG_CMD,
-		.flags = CMD_SYNC,
 	};
 	struct iwl_mvm_scan_params params = {};
 
@@ -765,7 +745,7 @@ int iwl_mvm_config_sched_scan(struct iwl_mvm *mvm,
 					      &scan_cfg->scan_cmd.tx_cmd[0],
 					      scan_cfg->data);
 		iwl_build_channel_cfg(mvm, req, &scan_cfg->channel_cfg,
-				      IEEE80211_BAND_2GHZ, &head, &tail,
+				      IEEE80211_BAND_2GHZ, &head,
 				      ssid_bitmap, &params);
 	}
 	if (band_5ghz) {
@@ -775,7 +755,7 @@ int iwl_mvm_config_sched_scan(struct iwl_mvm *mvm,
 					      scan_cfg->data +
 						SCAN_OFFLOAD_PROBE_REQ_SIZE);
 		iwl_build_channel_cfg(mvm, req, &scan_cfg->channel_cfg,
-				      IEEE80211_BAND_5GHZ, &head, &tail,
+				      IEEE80211_BAND_5GHZ, &head,
 				      ssid_bitmap, &params);
 	}
 
@@ -798,7 +778,6 @@ int iwl_mvm_config_sched_scan_profiles(struct iwl_mvm *mvm,
 	struct iwl_scan_offload_blacklist *blacklist;
 	struct iwl_host_cmd cmd = {
 		.id = SCAN_OFFLOAD_UPDATE_PROFILES_CMD,
-		.flags = CMD_SYNC,
 		.len[1] = sizeof(*profile_cfg),
 		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
 		.dataflags[1] = IWL_HCMD_DFL_NOCOPY,
@@ -884,7 +863,12 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm,
 		scan_req.flags |= cpu_to_le16(IWL_SCAN_OFFLOAD_FLAG_PASS_ALL);
 	}
 
-	return iwl_mvm_send_cmd_pdu(mvm, SCAN_OFFLOAD_REQUEST_CMD, CMD_SYNC,
+	if (mvm->last_ebs_successful &&
+	    mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_EBS_SUPPORT)
+		scan_req.flags |=
+			cpu_to_le16(IWL_SCAN_OFFLOAD_FLAG_EBS_ACCURATE_MODE);
+
+	return iwl_mvm_send_cmd_pdu(mvm, SCAN_OFFLOAD_REQUEST_CMD, 0,
 				    sizeof(scan_req), &scan_req);
 }
 
@@ -893,7 +877,6 @@ static int iwl_mvm_send_sched_scan_abort(struct iwl_mvm *mvm)
 	int ret;
 	struct iwl_host_cmd cmd = {
 		.id = SCAN_OFFLOAD_ABORT_CMD,
-		.flags = CMD_SYNC,
 	};
 	u32 status;
 
@@ -922,7 +905,7 @@ static int iwl_mvm_send_sched_scan_abort(struct iwl_mvm *mvm)
 	return ret;
 }
 
-int iwl_mvm_sched_scan_stop(struct iwl_mvm *mvm)
+int iwl_mvm_sched_scan_stop(struct iwl_mvm *mvm, bool notify)
 {
 	int ret;
 	struct iwl_notification_wait wait_scan_done;
@@ -960,5 +943,8 @@ int iwl_mvm_sched_scan_stop(struct iwl_mvm *mvm)
 	 */
 	mvm->scan_status = IWL_MVM_SCAN_NONE;
 
+	if (notify)
+		ieee80211_sched_scan_stopped(mvm->hw);
+
 	return 0;
 }
diff --git a/drivers/net/wireless/iwlwifi/mvm/sf.c b/drivers/net/wireless/iwlwifi/mvm/sf.c
index 88809b2d165..7edfd15efc9 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sf.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sf.c
@@ -237,9 +237,6 @@ int iwl_mvm_sf_update(struct iwl_mvm *mvm, struct ieee80211_vif *changed_vif,
 		.sta_vif_ap_sta_id = IWL_MVM_STATION_COUNT,
 	};
 
-	if (IWL_UCODE_API(mvm->fw->ucode_ver) < 8)
-		return 0;
-
 	/*
 	 * Ignore the call if we are in HW Restart flow, or if the handled
 	 * vif is a p2p device.
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.c b/drivers/net/wireless/iwlwifi/mvm/sta.c
index f339ef88425..1fb01ea2e70 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.c
@@ -66,115 +66,6 @@
 #include "sta.h"
 #include "rs.h"
 
-static void iwl_mvm_add_sta_cmd_v7_to_v5(struct iwl_mvm_add_sta_cmd_v7 *cmd_v7,
-					 struct iwl_mvm_add_sta_cmd_v5 *cmd_v5)
-{
-	memset(cmd_v5, 0, sizeof(*cmd_v5));
-
-	cmd_v5->add_modify = cmd_v7->add_modify;
-	cmd_v5->tid_disable_tx = cmd_v7->tid_disable_tx;
-	cmd_v5->mac_id_n_color = cmd_v7->mac_id_n_color;
-	memcpy(cmd_v5->addr, cmd_v7->addr, ETH_ALEN);
-	cmd_v5->sta_id = cmd_v7->sta_id;
-	cmd_v5->modify_mask = cmd_v7->modify_mask;
-	cmd_v5->station_flags = cmd_v7->station_flags;
-	cmd_v5->station_flags_msk = cmd_v7->station_flags_msk;
-	cmd_v5->add_immediate_ba_tid = cmd_v7->add_immediate_ba_tid;
-	cmd_v5->remove_immediate_ba_tid = cmd_v7->remove_immediate_ba_tid;
-	cmd_v5->add_immediate_ba_ssn = cmd_v7->add_immediate_ba_ssn;
-	cmd_v5->sleep_tx_count = cmd_v7->sleep_tx_count;
-	cmd_v5->sleep_state_flags = cmd_v7->sleep_state_flags;
-	cmd_v5->assoc_id = cmd_v7->assoc_id;
-	cmd_v5->beamform_flags = cmd_v7->beamform_flags;
-	cmd_v5->tfd_queue_msk = cmd_v7->tfd_queue_msk;
-}
-
-static void
-iwl_mvm_add_sta_key_to_add_sta_cmd_v5(struct iwl_mvm_add_sta_key_cmd *key_cmd,
-				      struct iwl_mvm_add_sta_cmd_v5 *sta_cmd,
-				      u32 mac_id_n_color)
-{
-	memset(sta_cmd, 0, sizeof(*sta_cmd));
-
-	sta_cmd->sta_id = key_cmd->sta_id;
-	sta_cmd->add_modify = STA_MODE_MODIFY;
-	sta_cmd->modify_mask = STA_MODIFY_KEY;
-	sta_cmd->mac_id_n_color = cpu_to_le32(mac_id_n_color);
-
-	sta_cmd->key.key_offset = key_cmd->key_offset;
-	sta_cmd->key.key_flags = key_cmd->key_flags;
-	memcpy(sta_cmd->key.key, key_cmd->key, sizeof(sta_cmd->key.key));
-	sta_cmd->key.tkip_rx_tsc_byte2 = key_cmd->tkip_rx_tsc_byte2;
-	memcpy(sta_cmd->key.tkip_rx_ttak, key_cmd->tkip_rx_ttak,
-	       sizeof(sta_cmd->key.tkip_rx_ttak));
-}
-
-static int iwl_mvm_send_add_sta_cmd_status(struct iwl_mvm *mvm,
-					   struct iwl_mvm_add_sta_cmd_v7 *cmd,
-					   int *status)
-{
-	struct iwl_mvm_add_sta_cmd_v5 cmd_v5;
-
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_STA_KEY_CMD)
-		return iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA, sizeof(*cmd),
-						   cmd, status);
-
-	iwl_mvm_add_sta_cmd_v7_to_v5(cmd, &cmd_v5);
-
-	return iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA, sizeof(cmd_v5),
-					   &cmd_v5, status);
-}
-
-static int iwl_mvm_send_add_sta_cmd(struct iwl_mvm *mvm, u32 flags,
-				    struct iwl_mvm_add_sta_cmd_v7 *cmd)
-{
-	struct iwl_mvm_add_sta_cmd_v5 cmd_v5;
-
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_STA_KEY_CMD)
-		return iwl_mvm_send_cmd_pdu(mvm, ADD_STA, flags,
-					    sizeof(*cmd), cmd);
-
-	iwl_mvm_add_sta_cmd_v7_to_v5(cmd, &cmd_v5);
-
-	return iwl_mvm_send_cmd_pdu(mvm, ADD_STA, flags, sizeof(cmd_v5),
-				    &cmd_v5);
-}
-
-static int
-iwl_mvm_send_add_sta_key_cmd_status(struct iwl_mvm *mvm,
-				    struct iwl_mvm_add_sta_key_cmd *cmd,
-				    u32 mac_id_n_color,
-				    int *status)
-{
-	struct iwl_mvm_add_sta_cmd_v5 sta_cmd;
-
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_STA_KEY_CMD)
-		return iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA_KEY,
-						   sizeof(*cmd), cmd, status);
-
-	iwl_mvm_add_sta_key_to_add_sta_cmd_v5(cmd, &sta_cmd, mac_id_n_color);
-
-	return iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA, sizeof(sta_cmd),
-					   &sta_cmd, status);
-}
-
-static int iwl_mvm_send_add_sta_key_cmd(struct iwl_mvm *mvm,
-					u32 flags,
-					struct iwl_mvm_add_sta_key_cmd *cmd,
-					u32 mac_id_n_color)
-{
-	struct iwl_mvm_add_sta_cmd_v5 sta_cmd;
-
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_STA_KEY_CMD)
-		return iwl_mvm_send_cmd_pdu(mvm, ADD_STA_KEY, flags,
-					    sizeof(*cmd), cmd);
-
-	iwl_mvm_add_sta_key_to_add_sta_cmd_v5(cmd, &sta_cmd, mac_id_n_color);
-
-	return iwl_mvm_send_cmd_pdu(mvm, ADD_STA, flags, sizeof(sta_cmd),
-				    &sta_cmd);
-}
-
 static int iwl_mvm_find_free_sta_id(struct iwl_mvm *mvm,
 				    enum nl80211_iftype iftype)
 {
@@ -207,7 +98,7 @@ int iwl_mvm_sta_send_to_fw(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 			   bool update)
 {
 	struct iwl_mvm_sta *mvm_sta = (void *)sta->drv_priv;
-	struct iwl_mvm_add_sta_cmd_v7 add_sta_cmd;
+	struct iwl_mvm_add_sta_cmd add_sta_cmd;
 	int ret;
 	u32 status;
 	u32 agg_size = 0, mpdu_dens = 0;
@@ -295,7 +186,8 @@ int iwl_mvm_sta_send_to_fw(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 		cpu_to_le32(mpdu_dens << STA_FLG_AGG_MPDU_DENS_SHIFT);
 
 	status = ADD_STA_SUCCESS;
-	ret = iwl_mvm_send_add_sta_cmd_status(mvm, &add_sta_cmd, &status);
+	ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA, sizeof(add_sta_cmd),
+					  &add_sta_cmd, &status);
 	if (ret)
 		return ret;
 
@@ -380,7 +272,7 @@ int iwl_mvm_update_sta(struct iwl_mvm *mvm,
 int iwl_mvm_drain_sta(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta,
 		      bool drain)
 {
-	struct iwl_mvm_add_sta_cmd_v7 cmd = {};
+	struct iwl_mvm_add_sta_cmd cmd = {};
 	int ret;
 	u32 status;
 
@@ -393,7 +285,8 @@ int iwl_mvm_drain_sta(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta,
 	cmd.station_flags_msk = cpu_to_le32(STA_FLG_DRAIN_FLOW);
 
 	status = ADD_STA_SUCCESS;
-	ret = iwl_mvm_send_add_sta_cmd_status(mvm, &cmd, &status);
+	ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA, sizeof(cmd),
+					  &cmd, &status);
 	if (ret)
 		return ret;
 
@@ -434,7 +327,7 @@ static int iwl_mvm_rm_sta_common(struct iwl_mvm *mvm, u8 sta_id)
 		return -EINVAL;
 	}
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, REMOVE_STA, CMD_SYNC,
+	ret = iwl_mvm_send_cmd_pdu(mvm, REMOVE_STA, 0,
 				   sizeof(rm_sta_cmd), &rm_sta_cmd);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to remove station. Id=%d\n", sta_id);
@@ -498,7 +391,7 @@ void iwl_mvm_sta_drained_wk(struct work_struct *wk)
 				sta_id);
 			continue;
 		}
-		rcu_assign_pointer(mvm->fw_id_to_mac_id[sta_id], NULL);
+		RCU_INIT_POINTER(mvm->fw_id_to_mac_id[sta_id], NULL);
 		clear_bit(sta_id, mvm->sta_drained);
 	}
 
@@ -520,14 +413,6 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm,
 		/* flush its queues here since we are freeing mvm_sta */
 		ret = iwl_mvm_flush_tx_path(mvm, mvm_sta->tfd_queue_msk, true);
 
-		/*
-		 * Put a non-NULL since the fw station isn't removed.
-		 * It will be removed after the MAC will be set as
-		 * unassoc.
-		 */
-		rcu_assign_pointer(mvm->fw_id_to_mac_id[mvm_sta->sta_id],
-				   ERR_PTR(-EINVAL));
-
 		/* if we are associated - we can't remove the AP STA now */
 		if (vif->bss_conf.assoc)
 			return ret;
@@ -557,7 +442,7 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm,
 	} else {
 		spin_unlock_bh(&mvm_sta->lock);
 		ret = iwl_mvm_rm_sta_common(mvm, mvm_sta->sta_id);
-		rcu_assign_pointer(mvm->fw_id_to_mac_id[mvm_sta->sta_id], NULL);
+		RCU_INIT_POINTER(mvm->fw_id_to_mac_id[mvm_sta->sta_id], NULL);
 	}
 
 	return ret;
@@ -571,7 +456,7 @@ int iwl_mvm_rm_sta_id(struct iwl_mvm *mvm,
 
 	lockdep_assert_held(&mvm->mutex);
 
-	rcu_assign_pointer(mvm->fw_id_to_mac_id[sta_id], NULL);
+	RCU_INIT_POINTER(mvm->fw_id_to_mac_id[sta_id], NULL);
 	return ret;
 }
 
@@ -593,7 +478,7 @@ int iwl_mvm_allocate_int_sta(struct iwl_mvm *mvm, struct iwl_mvm_int_sta *sta,
 
 void iwl_mvm_dealloc_int_sta(struct iwl_mvm *mvm, struct iwl_mvm_int_sta *sta)
 {
-	rcu_assign_pointer(mvm->fw_id_to_mac_id[sta->sta_id], NULL);
+	RCU_INIT_POINTER(mvm->fw_id_to_mac_id[sta->sta_id], NULL);
 	memset(sta, 0, sizeof(struct iwl_mvm_int_sta));
 	sta->sta_id = IWL_MVM_STATION_COUNT;
 }
@@ -603,13 +488,13 @@ static int iwl_mvm_add_int_sta_common(struct iwl_mvm *mvm,
 				      const u8 *addr,
 				      u16 mac_id, u16 color)
 {
-	struct iwl_mvm_add_sta_cmd_v7 cmd;
+	struct iwl_mvm_add_sta_cmd cmd;
 	int ret;
 	u32 status;
 
 	lockdep_assert_held(&mvm->mutex);
 
-	memset(&cmd, 0, sizeof(struct iwl_mvm_add_sta_cmd_v7));
+	memset(&cmd, 0, sizeof(cmd));
 	cmd.sta_id = sta->sta_id;
 	cmd.mac_id_n_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(mac_id,
 							     color));
@@ -619,7 +504,8 @@ static int iwl_mvm_add_int_sta_common(struct iwl_mvm *mvm,
 	if (addr)
 		memcpy(cmd.addr, addr, ETH_ALEN);
 
-	ret = iwl_mvm_send_add_sta_cmd_status(mvm, &cmd, &status);
+	ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA, sizeof(cmd),
+					  &cmd, &status);
 	if (ret)
 		return ret;
 
@@ -753,7 +639,7 @@ int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 		       int tid, u16 ssn, bool start)
 {
 	struct iwl_mvm_sta *mvm_sta = (void *)sta->drv_priv;
-	struct iwl_mvm_add_sta_cmd_v7 cmd = {};
+	struct iwl_mvm_add_sta_cmd cmd = {};
 	int ret;
 	u32 status;
 
@@ -777,7 +663,8 @@ int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 				  STA_MODIFY_REMOVE_BA_TID;
 
 	status = ADD_STA_SUCCESS;
-	ret = iwl_mvm_send_add_sta_cmd_status(mvm, &cmd, &status);
+	ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA, sizeof(cmd),
+					  &cmd, &status);
 	if (ret)
 		return ret;
 
@@ -812,7 +699,7 @@ static int iwl_mvm_sta_tx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 			      int tid, u8 queue, bool start)
 {
 	struct iwl_mvm_sta *mvm_sta = (void *)sta->drv_priv;
-	struct iwl_mvm_add_sta_cmd_v7 cmd = {};
+	struct iwl_mvm_add_sta_cmd cmd = {};
 	int ret;
 	u32 status;
 
@@ -834,7 +721,8 @@ static int iwl_mvm_sta_tx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	cmd.tid_disable_tx = cpu_to_le16(mvm_sta->tid_disable_agg);
 
 	status = ADD_STA_SUCCESS;
-	ret = iwl_mvm_send_add_sta_cmd_status(mvm, &cmd, &status);
+	ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA, sizeof(cmd),
+					  &cmd, &status);
 	if (ret)
 		return ret;
 
@@ -1129,12 +1017,11 @@ static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 				u8 sta_id, u32 tkip_iv32, u16 *tkip_p1k,
 				u32 cmd_flags)
 {
-	__le16 key_flags;
 	struct iwl_mvm_add_sta_key_cmd cmd = {};
+	__le16 key_flags;
 	int ret, status;
 	u16 keyidx;
 	int i;
-	u32 mac_id_n_color = mvm_sta->mac_id_n_color;
 
 	keyidx = (keyconf->keyidx << STA_KEY_FLG_KEYID_POS) &
 		 STA_KEY_FLG_KEYID_MSK;
@@ -1166,13 +1053,12 @@ static int iwl_mvm_send_sta_key(struct iwl_mvm *mvm,
 	cmd.sta_id = sta_id;
 
 	status = ADD_STA_SUCCESS;
-	if (cmd_flags == CMD_SYNC)
-		ret = iwl_mvm_send_add_sta_key_cmd_status(mvm, &cmd,
-							  mac_id_n_color,
-							  &status);
+	if (cmd_flags & CMD_ASYNC)
+		ret =  iwl_mvm_send_cmd_pdu(mvm, ADD_STA_KEY, CMD_ASYNC,
+					    sizeof(cmd), &cmd);
 	else
-		ret = iwl_mvm_send_add_sta_key_cmd(mvm, CMD_ASYNC, &cmd,
-						   mac_id_n_color);
+		ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA_KEY, sizeof(cmd),
+						  &cmd, &status);
 
 	switch (status) {
 	case ADD_STA_SUCCESS:
@@ -1225,7 +1111,7 @@ static int iwl_mvm_send_sta_igtk(struct iwl_mvm *mvm,
 		       remove_key ? "removing" : "installing",
 		       igtk_cmd.sta_id);
 
-	return iwl_mvm_send_cmd_pdu(mvm, MGMT_MCAST_KEY, CMD_SYNC,
+	return iwl_mvm_send_cmd_pdu(mvm, MGMT_MCAST_KEY, 0,
 				    sizeof(igtk_cmd), &igtk_cmd);
 }
 
@@ -1312,15 +1198,15 @@ int iwl_mvm_set_sta_key(struct iwl_mvm *mvm,
 		ieee80211_get_key_rx_seq(keyconf, 0, &seq);
 		ieee80211_get_tkip_rx_p1k(keyconf, addr, seq.tkip.iv32, p1k);
 		ret = iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, sta_id,
-					   seq.tkip.iv32, p1k, CMD_SYNC);
+					   seq.tkip.iv32, p1k, 0);
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 		ret = iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, sta_id,
-					   0, NULL, CMD_SYNC);
+					   0, NULL, 0);
 		break;
 	default:
 		ret = iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf,
-					   sta_id, 0, NULL, CMD_SYNC);
+					   sta_id, 0, NULL, 0);
 	}
 
 	if (ret)
@@ -1399,9 +1285,8 @@ int iwl_mvm_remove_sta_key(struct iwl_mvm *mvm,
 	cmd.sta_id = sta_id;
 
 	status = ADD_STA_SUCCESS;
-	ret = iwl_mvm_send_add_sta_key_cmd_status(mvm, &cmd,
-						  mvm_sta->mac_id_n_color,
-						  &status);
+	ret = iwl_mvm_send_cmd_pdu_status(mvm, ADD_STA_KEY, sizeof(cmd),
+					  &cmd, &status);
 
 	switch (status) {
 	case ADD_STA_SUCCESS:
@@ -1448,7 +1333,7 @@ void iwl_mvm_sta_modify_ps_wake(struct iwl_mvm *mvm,
 				struct ieee80211_sta *sta)
 {
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
-	struct iwl_mvm_add_sta_cmd_v7 cmd = {
+	struct iwl_mvm_add_sta_cmd cmd = {
 		.add_modify = STA_MODE_MODIFY,
 		.sta_id = mvmsta->sta_id,
 		.station_flags_msk = cpu_to_le32(STA_FLG_PS),
@@ -1456,7 +1341,7 @@ void iwl_mvm_sta_modify_ps_wake(struct iwl_mvm *mvm,
 	};
 	int ret;
 
-	ret = iwl_mvm_send_add_sta_cmd(mvm, CMD_ASYNC, &cmd);
+	ret = iwl_mvm_send_cmd_pdu(mvm, ADD_STA, CMD_ASYNC, sizeof(cmd), &cmd);
 	if (ret)
 		IWL_ERR(mvm, "Failed to send ADD_STA command (%d)\n", ret);
 }
@@ -1468,7 +1353,7 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
 				       bool agg)
 {
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
-	struct iwl_mvm_add_sta_cmd_v7 cmd = {
+	struct iwl_mvm_add_sta_cmd cmd = {
 		.add_modify = STA_MODE_MODIFY,
 		.sta_id = mvmsta->sta_id,
 		.modify_mask = STA_MODIFY_SLEEPING_STA_TX_COUNT,
@@ -1538,7 +1423,7 @@ void iwl_mvm_sta_modify_sleep_tx_count(struct iwl_mvm *mvm,
 		cmd.sleep_state_flags |= cpu_to_le16(STA_SLEEP_STATE_UAPSD);
 	}
 
-	ret = iwl_mvm_send_add_sta_cmd(mvm, CMD_ASYNC, &cmd);
+	ret = iwl_mvm_send_cmd_pdu(mvm, ADD_STA, CMD_ASYNC, sizeof(cmd), &cmd);
 	if (ret)
 		IWL_ERR(mvm, "Failed to send ADD_STA command (%d)\n", ret);
 }
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.h b/drivers/net/wireless/iwlwifi/mvm/sta.h
index 2ed84c42148..d98e8a2142b 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.h
@@ -253,6 +253,8 @@ enum iwl_mvm_agg_state {
  *	This is basically (last acked packet++).
  * @rate_n_flags: Rate at which Tx was attempted. Holds the data between the
  *	Tx response (TX_CMD), and the block ack notification (COMPRESSED_BA).
+ * @reduced_tpc: Reduced tx power. Holds the data between the
+ *	Tx response (TX_CMD), and the block ack notification (COMPRESSED_BA).
  * @state: state of the BA agreement establishment / tear down.
  * @txq_id: Tx queue used by the BA session
  * @ssn: the first packet to be sent in AGG HW queue in Tx AGG start flow, or
@@ -265,6 +267,7 @@ struct iwl_mvm_tid_data {
 	u16 next_reclaimed;
 	/* The rest is Tx AGG related */
 	u32 rate_n_flags;
+	u8 reduced_tpc;
 	enum iwl_mvm_agg_state state;
 	u16 txq_id;
 	u16 ssn;
@@ -284,8 +287,6 @@ static inline u16 iwl_mvm_tid_queued(struct iwl_mvm_tid_data *tid_data)
  * @tid_disable_agg: bitmap: if bit(tid) is set, the fw won't send ampdus for
  *	tid.
  * @max_agg_bufsize: the maximal size of the AGG buffer for this station
- * @bt_reduced_txpower_dbg: debug mode in which %bt_reduced_txpower is forced
- *	by debugfs.
  * @bt_reduced_txpower: is reduced tx power enabled for this station
  * @next_status_eosp: the next reclaimed packet is a PS-Poll response and
  *	we need to signal the EOSP
@@ -306,7 +307,6 @@ struct iwl_mvm_sta {
 	u32 mac_id_n_color;
 	u16 tid_disable_agg;
 	u8 max_agg_bufsize;
-	bool bt_reduced_txpower_dbg;
 	bool bt_reduced_txpower;
 	bool next_status_eosp;
 	spinlock_t lock;
diff --git a/drivers/net/wireless/iwlwifi/mvm/time-event.c b/drivers/net/wireless/iwlwifi/mvm/time-event.c
index 61331245ad9..80100f6cc12 100644
--- a/drivers/net/wireless/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/iwlwifi/mvm/time-event.c
@@ -273,67 +273,10 @@ static bool iwl_mvm_time_event_response(struct iwl_notif_wait_data *notif_wait,
 	return true;
 }
 
-/* used to convert from time event API v2 to v1 */
-#define TE_V2_DEP_POLICY_MSK (TE_V2_DEP_OTHER | TE_V2_DEP_TSF |\
-			     TE_V2_EVENT_SOCIOPATHIC)
-static inline u16 te_v2_get_notify(__le16 policy)
-{
-	return le16_to_cpu(policy) & TE_V2_NOTIF_MSK;
-}
-
-static inline u16 te_v2_get_dep_policy(__le16 policy)
-{
-	return (le16_to_cpu(policy) & TE_V2_DEP_POLICY_MSK) >>
-		TE_V2_PLACEMENT_POS;
-}
-
-static inline u16 te_v2_get_absence(__le16 policy)
-{
-	return (le16_to_cpu(policy) & TE_V2_ABSENCE) >> TE_V2_ABSENCE_POS;
-}
-
-static void iwl_mvm_te_v2_to_v1(const struct iwl_time_event_cmd_v2 *cmd_v2,
-				struct iwl_time_event_cmd_v1 *cmd_v1)
-{
-	cmd_v1->id_and_color = cmd_v2->id_and_color;
-	cmd_v1->action = cmd_v2->action;
-	cmd_v1->id = cmd_v2->id;
-	cmd_v1->apply_time = cmd_v2->apply_time;
-	cmd_v1->max_delay = cmd_v2->max_delay;
-	cmd_v1->depends_on = cmd_v2->depends_on;
-	cmd_v1->interval = cmd_v2->interval;
-	cmd_v1->duration = cmd_v2->duration;
-	if (cmd_v2->repeat == TE_V2_REPEAT_ENDLESS)
-		cmd_v1->repeat = cpu_to_le32(TE_V1_REPEAT_ENDLESS);
-	else
-		cmd_v1->repeat = cpu_to_le32(cmd_v2->repeat);
-	cmd_v1->max_frags = cpu_to_le32(cmd_v2->max_frags);
-	cmd_v1->interval_reciprocal = 0; /* unused */
-
-	cmd_v1->dep_policy = cpu_to_le32(te_v2_get_dep_policy(cmd_v2->policy));
-	cmd_v1->is_present = cpu_to_le32(!te_v2_get_absence(cmd_v2->policy));
-	cmd_v1->notify = cpu_to_le32(te_v2_get_notify(cmd_v2->policy));
-}
-
-static int iwl_mvm_send_time_event_cmd(struct iwl_mvm *mvm,
-				       const struct iwl_time_event_cmd_v2 *cmd)
-{
-	struct iwl_time_event_cmd_v1 cmd_v1;
-
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_TIME_EVENT_API_V2)
-		return iwl_mvm_send_cmd_pdu(mvm, TIME_EVENT_CMD, CMD_SYNC,
-					    sizeof(*cmd), cmd);
-
-	iwl_mvm_te_v2_to_v1(cmd, &cmd_v1);
-	return iwl_mvm_send_cmd_pdu(mvm, TIME_EVENT_CMD, CMD_SYNC,
-				    sizeof(cmd_v1), &cmd_v1);
-}
-
-
 static int iwl_mvm_time_event_send_add(struct iwl_mvm *mvm,
 				       struct ieee80211_vif *vif,
 				       struct iwl_mvm_time_event_data *te_data,
-				       struct iwl_time_event_cmd_v2 *te_cmd)
+				       struct iwl_time_event_cmd *te_cmd)
 {
 	static const u8 time_event_response[] = { TIME_EVENT_CMD };
 	struct iwl_notification_wait wait_time_event;
@@ -369,7 +312,8 @@ static int iwl_mvm_time_event_send_add(struct iwl_mvm *mvm,
 				   ARRAY_SIZE(time_event_response),
 				   iwl_mvm_time_event_response, te_data);
 
-	ret = iwl_mvm_send_time_event_cmd(mvm, te_cmd);
+	ret = iwl_mvm_send_cmd_pdu(mvm, TIME_EVENT_CMD, 0,
+					    sizeof(*te_cmd), te_cmd);
 	if (ret) {
 		IWL_ERR(mvm, "Couldn't send TIME_EVENT_CMD: %d\n", ret);
 		iwl_remove_notification(&mvm->notif_wait, &wait_time_event);
@@ -397,7 +341,7 @@ void iwl_mvm_protect_session(struct iwl_mvm *mvm,
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	struct iwl_mvm_time_event_data *te_data = &mvmvif->time_event_data;
-	struct iwl_time_event_cmd_v2 time_cmd = {};
+	struct iwl_time_event_cmd time_cmd = {};
 
 	lockdep_assert_held(&mvm->mutex);
 
@@ -453,7 +397,7 @@ void iwl_mvm_remove_time_event(struct iwl_mvm *mvm,
 			       struct iwl_mvm_vif *mvmvif,
 			       struct iwl_mvm_time_event_data *te_data)
 {
-	struct iwl_time_event_cmd_v2 time_cmd = {};
+	struct iwl_time_event_cmd time_cmd = {};
 	u32 id, uid;
 	int ret;
 
@@ -490,7 +434,8 @@ void iwl_mvm_remove_time_event(struct iwl_mvm *mvm,
 		cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id, mvmvif->color));
 
 	IWL_DEBUG_TE(mvm, "Removing TE 0x%x\n", le32_to_cpu(time_cmd.id));
-	ret = iwl_mvm_send_time_event_cmd(mvm, &time_cmd);
+	ret = iwl_mvm_send_cmd_pdu(mvm, TIME_EVENT_CMD, 0,
+				   sizeof(time_cmd), &time_cmd);
 	if (WARN_ON(ret))
 		return;
 }
@@ -510,7 +455,7 @@ int iwl_mvm_start_p2p_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	struct iwl_mvm_time_event_data *te_data = &mvmvif->time_event_data;
-	struct iwl_time_event_cmd_v2 time_cmd = {};
+	struct iwl_time_event_cmd time_cmd = {};
 
 	lockdep_assert_held(&mvm->mutex);
 	if (te_data->running) {
diff --git a/drivers/net/wireless/iwlwifi/mvm/tt.c b/drivers/net/wireless/iwlwifi/mvm/tt.c
index 7a99fa36195..86856151278 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tt.c
@@ -409,7 +409,6 @@ void iwl_mvm_tt_tx_backoff(struct iwl_mvm *mvm, u32 backoff)
 		.id = REPLY_THERMAL_MNG_BACKOFF,
 		.len = { sizeof(u32), },
 		.data = { &backoff, },
-		.flags = CMD_SYNC,
 	};
 
 	backoff = max(backoff, mvm->thermal_throttle.min_backoff);
@@ -468,13 +467,14 @@ void iwl_mvm_tt_handler(struct iwl_mvm *mvm)
 	}
 
 	if (params->support_tx_backoff) {
-		tx_backoff = 0;
+		tx_backoff = tt->min_backoff;
 		for (i = 0; i < TT_TX_BACKOFF_SIZE; i++) {
 			if (temperature < params->tx_backoff[i].temperature)
 				break;
-			tx_backoff = params->tx_backoff[i].backoff;
+			tx_backoff = max(tt->min_backoff,
+					 params->tx_backoff[i].backoff);
 		}
-		if (tx_backoff != 0)
+		if (tx_backoff != tt->min_backoff)
 			throttle_enable = true;
 		if (tt->tx_backoff != tx_backoff)
 			iwl_mvm_tt_tx_backoff(mvm, tx_backoff);
@@ -484,7 +484,8 @@ void iwl_mvm_tt_handler(struct iwl_mvm *mvm)
 		IWL_WARN(mvm,
 			 "Due to high temperature thermal throttling initiated\n");
 		tt->throttle = true;
-	} else if (tt->throttle && !tt->dynamic_smps && tt->tx_backoff == 0 &&
+	} else if (tt->throttle && !tt->dynamic_smps &&
+		   tt->tx_backoff == tt->min_backoff &&
 		   temperature <= params->tx_protection_exit) {
 		IWL_WARN(mvm,
 			 "Temperature is back to normal thermal throttling stopped\n");
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 879aeac46cc..3846a6c41eb 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -636,7 +636,11 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 			seq_ctl = le16_to_cpu(hdr->seq_ctrl);
 		}
 
-		ieee80211_tx_status_ni(mvm->hw, skb);
+		BUILD_BUG_ON(ARRAY_SIZE(info->status.status_driver_data) < 1);
+		info->status.status_driver_data[0] =
+				(void *)(uintptr_t)tx_resp->reduced_tpc;
+
+		ieee80211_tx_status(mvm->hw, skb);
 	}
 
 	if (txq_id >= mvm->first_agg_queue) {
@@ -815,6 +819,7 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm,
 		struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 		mvmsta->tid_data[tid].rate_n_flags =
 			le32_to_cpu(tx_resp->initial_rate);
+		mvmsta->tid_data[tid].reduced_tpc = tx_resp->reduced_tpc;
 	}
 
 	rcu_read_unlock();
@@ -928,6 +933,8 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
 			info->status.ampdu_len = ba_notif->txed;
 			iwl_mvm_hwrate_to_tx_status(tid_data->rate_n_flags,
 						    info);
+			info->status.status_driver_data[0] =
+				(void *)(uintptr_t)tid_data->reduced_tpc;
 		}
 	}
 
@@ -937,7 +944,7 @@ int iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
 
 	while (!skb_queue_empty(&reclaimed_skbs)) {
 		skb = __skb_dequeue(&reclaimed_skbs);
-		ieee80211_tx_status_ni(mvm->hw, skb);
+		ieee80211_tx_status(mvm->hw, skb);
 	}
 
 	return 0;
@@ -951,7 +958,7 @@ int iwl_mvm_flush_tx_path(struct iwl_mvm *mvm, u32 tfd_msk, bool sync)
 		.flush_ctl = cpu_to_le16(DUMP_TX_FIFO_FLUSH),
 	};
 
-	u32 flags = sync ? CMD_SYNC : CMD_ASYNC;
+	u32 flags = sync ? 0 : CMD_ASYNC;
 
 	ret = iwl_mvm_send_cmd_pdu(mvm, TXPATH_FLUSH, flags,
 				   sizeof(flush_cmd), &flush_cmd);
diff --git a/drivers/net/wireless/iwlwifi/mvm/utils.c b/drivers/net/wireless/iwlwifi/mvm/utils.c
index 2180902266a..aa9fc77e841 100644
--- a/drivers/net/wireless/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/iwlwifi/mvm/utils.c
@@ -64,6 +64,7 @@
 
 #include "iwl-debug.h"
 #include "iwl-io.h"
+#include "iwl-prph.h"
 
 #include "mvm.h"
 #include "fw-api-rs.h"
@@ -143,7 +144,7 @@ int iwl_mvm_send_cmd_status(struct iwl_mvm *mvm, struct iwl_host_cmd *cmd,
 		      "cmd flags %x", cmd->flags))
 		return -EINVAL;
 
-	cmd->flags |= CMD_SYNC | CMD_WANT_SKB;
+	cmd->flags |= CMD_WANT_SKB;
 
 	ret = iwl_trans_send_cmd(mvm->trans, cmd);
 	if (ret == -ERFKILL) {
@@ -469,6 +470,8 @@ void iwl_mvm_dump_nic_error_log(struct iwl_mvm *mvm)
 			mvm->status, table.valid);
 	}
 
+	/* Do not change this output - scripts rely on it */
+
 	IWL_ERR(mvm, "Loaded firmware version: %s\n", mvm->fw->fw_version);
 
 	trace_iwlwifi_dev_ucode_error(trans->dev, table.error_id, table.tsf_low,
@@ -516,13 +519,14 @@ void iwl_mvm_dump_nic_error_log(struct iwl_mvm *mvm)
 		iwl_mvm_dump_umac_error_log(mvm);
 }
 
+#ifdef CONFIG_IWLWIFI_DEBUGFS
 void iwl_mvm_fw_error_sram_dump(struct iwl_mvm *mvm)
 {
 	const struct fw_img *img;
 	u32 ofs, sram_len;
 	void *sram;
 
-	if (!mvm->ucode_loaded || mvm->fw_error_sram)
+	if (!mvm->ucode_loaded || mvm->fw_error_sram || mvm->fw_error_dump)
 		return;
 
 	img = &mvm->fw->img[mvm->cur_ucode];
@@ -538,6 +542,48 @@ void iwl_mvm_fw_error_sram_dump(struct iwl_mvm *mvm)
 	mvm->fw_error_sram_len = sram_len;
 }
 
+void iwl_mvm_fw_error_rxf_dump(struct iwl_mvm *mvm)
+{
+	int i, reg_val;
+	unsigned long flags;
+
+	if (!mvm->ucode_loaded || mvm->fw_error_rxf || mvm->fw_error_dump)
+		return;
+
+	/* reading buffer size */
+	reg_val = iwl_trans_read_prph(mvm->trans, RXF_SIZE_ADDR);
+	mvm->fw_error_rxf_len =
+		(reg_val & RXF_SIZE_BYTE_CNT_MSK) >> RXF_SIZE_BYTE_CND_POS;
+
+	/* the register holds the value divided by 128 */
+	mvm->fw_error_rxf_len = mvm->fw_error_rxf_len << 7;
+
+	if (!mvm->fw_error_rxf_len)
+		return;
+
+	mvm->fw_error_rxf =  kzalloc(mvm->fw_error_rxf_len, GFP_ATOMIC);
+	if (!mvm->fw_error_rxf) {
+		mvm->fw_error_rxf_len = 0;
+		return;
+	}
+
+	if (!iwl_trans_grab_nic_access(mvm->trans, false, &flags)) {
+		kfree(mvm->fw_error_rxf);
+		mvm->fw_error_rxf = NULL;
+		mvm->fw_error_rxf_len = 0;
+		return;
+	}
+
+	for (i = 0; i < (mvm->fw_error_rxf_len / sizeof(u32)); i++) {
+		iwl_trans_write_prph(mvm->trans, RXF_LD_FENCE_OFFSET_ADDR,
+				     i * sizeof(u32));
+		mvm->fw_error_rxf[i] =
+			iwl_trans_read_prph(mvm->trans, RXF_FIFO_RD_FENCE_ADDR);
+	}
+	iwl_trans_release_nic_access(mvm->trans, &flags);
+}
+#endif
+
 /**
  * iwl_mvm_send_lq_cmd() - Send link quality command
  * @init: This command is sent as part of station initialization right
@@ -553,7 +599,7 @@ int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq, bool init)
 	struct iwl_host_cmd cmd = {
 		.id = LQ_CMD,
 		.len = { sizeof(struct iwl_lq_cmd), },
-		.flags = init ? CMD_SYNC : CMD_ASYNC,
+		.flags = init ? 0 : CMD_ASYNC,
 		.data = { lq, },
 	};
 
@@ -604,6 +650,39 @@ void iwl_mvm_update_smps(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	ieee80211_request_smps(vif, smps_mode);
 }
 
+static void iwl_mvm_diversity_iter(void *_data, u8 *mac,
+				   struct ieee80211_vif *vif)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	bool *result = _data;
+	int i;
+
+	for (i = 0; i < NUM_IWL_MVM_SMPS_REQ; i++) {
+		if (mvmvif->smps_requests[i] == IEEE80211_SMPS_STATIC ||
+		    mvmvif->smps_requests[i] == IEEE80211_SMPS_DYNAMIC)
+			*result = false;
+	}
+}
+
+bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm)
+{
+	bool result = true;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	if (num_of_ant(mvm->fw->valid_rx_ant) == 1)
+		return false;
+
+	if (!mvm->cfg->rx_with_siso_diversity)
+		return false;
+
+	ieee80211_iterate_active_interfaces_atomic(
+			mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
+			iwl_mvm_diversity_iter, &result);
+
+	return result;
+}
+
 int iwl_mvm_update_low_latency(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			       bool value)
 {
@@ -623,7 +702,7 @@ int iwl_mvm_update_low_latency(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 	iwl_mvm_bt_coex_vif_change(mvm);
 
-	return iwl_mvm_power_update_mac(mvm, vif);
+	return iwl_mvm_power_update_mac(mvm);
 }
 
 static void iwl_mvm_ll_iter(void *_data, u8 *mac, struct ieee80211_vif *vif)
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 3d1d57f9f5b..98950e45c7b 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -367,6 +367,7 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 	{IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5412, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5510, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5000, iwl7265_2n_cfg)},
@@ -380,7 +381,7 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 	{IWL_PCI_DEVICE(0x095A, 0x9110, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9112, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9210, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095A, 0x9200, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095B, 0x9200, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9510, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9310, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9410, iwl7265_2ac_cfg)},
@@ -417,7 +418,7 @@ static u64 splx_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splx)
 	    splx->package.count != 2 ||
 	    splx->package.elements[0].type != ACPI_TYPE_INTEGER ||
 	    splx->package.elements[0].integer.value != 0) {
-		IWL_ERR(trans, "Unsupported splx structure");
+		IWL_ERR(trans, "Unsupported splx structure\n");
 		return 0;
 	}
 
@@ -426,14 +427,14 @@ static u64 splx_get_pwr_limit(struct iwl_trans *trans, union acpi_object *splx)
 	    limits->package.count < 2 ||
 	    limits->package.elements[0].type != ACPI_TYPE_INTEGER ||
 	    limits->package.elements[1].type != ACPI_TYPE_INTEGER) {
-		IWL_ERR(trans, "Invalid limits element");
+		IWL_ERR(trans, "Invalid limits element\n");
 		return 0;
 	}
 
 	domain_type = &limits->package.elements[0];
 	power_limit = &limits->package.elements[1];
 	if (!(domain_type->integer.value & SPL_DOMAINTYPE_WIFI)) {
-		IWL_DEBUG_INFO(trans, "WiFi power is not limited");
+		IWL_DEBUG_INFO(trans, "WiFi power is not limited\n");
 		return 0;
 	}
 
@@ -450,26 +451,26 @@ static void set_dflt_pwr_limit(struct iwl_trans *trans, struct pci_dev *pdev)
 	pxsx_handle = ACPI_HANDLE(&pdev->dev);
 	if (!pxsx_handle) {
 		IWL_DEBUG_INFO(trans,
-			       "Could not retrieve root port ACPI handle");
+			       "Could not retrieve root port ACPI handle\n");
 		return;
 	}
 
 	/* Get the method's handle */
 	status = acpi_get_handle(pxsx_handle, (acpi_string)SPL_METHOD, &handle);
 	if (ACPI_FAILURE(status)) {
-		IWL_DEBUG_INFO(trans, "SPL method not found");
+		IWL_DEBUG_INFO(trans, "SPL method not found\n");
 		return;
 	}
 
 	/* Call SPLC with no arguments */
 	status = acpi_evaluate_object(handle, NULL, NULL, &splx);
 	if (ACPI_FAILURE(status)) {
-		IWL_ERR(trans, "SPLC invocation failed (0x%x)", status);
+		IWL_ERR(trans, "SPLC invocation failed (0x%x)\n", status);
 		return;
 	}
 
 	trans->dflt_pwr_limit = splx_get_pwr_limit(trans, splx.pointer);
-	IWL_DEBUG_INFO(trans, "Default power limit set to %lld",
+	IWL_DEBUG_INFO(trans, "Default power limit set to %lld\n",
 		       trans->dflt_pwr_limit);
 	kfree(splx.pointer);
 }
diff --git a/drivers/net/wireless/iwlwifi/pcie/internal.h b/drivers/net/wireless/iwlwifi/pcie/internal.h
index 9091513ea73..6c22b23a284 100644
--- a/drivers/net/wireless/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/iwlwifi/pcie/internal.h
@@ -102,7 +102,7 @@ struct iwl_rxq {
 	u32 write_actual;
 	struct list_head rx_free;
 	struct list_head rx_used;
-	int need_update;
+	bool need_update;
 	struct iwl_rb_status *rb_stts;
 	dma_addr_t rb_stts_dma;
 	spinlock_t lock;
@@ -117,21 +117,19 @@ struct iwl_dma_ptr {
 /**
  * iwl_queue_inc_wrap - increment queue index, wrap back to beginning
  * @index -- current index
- * @n_bd -- total number of entries in queue (must be power of 2)
  */
-static inline int iwl_queue_inc_wrap(int index, int n_bd)
+static inline int iwl_queue_inc_wrap(int index)
 {
-	return ++index & (n_bd - 1);
+	return ++index & (TFD_QUEUE_SIZE_MAX - 1);
 }
 
 /**
  * iwl_queue_dec_wrap - decrement queue index, wrap back to end
  * @index -- current index
- * @n_bd -- total number of entries in queue (must be power of 2)
  */
-static inline int iwl_queue_dec_wrap(int index, int n_bd)
+static inline int iwl_queue_dec_wrap(int index)
 {
-	return --index & (n_bd - 1);
+	return --index & (TFD_QUEUE_SIZE_MAX - 1);
 }
 
 struct iwl_cmd_meta {
@@ -145,13 +143,13 @@ struct iwl_cmd_meta {
  *
  * Contains common data for Rx and Tx queues.
  *
- * Note the difference between n_bd and n_window: the hardware
- * always assumes 256 descriptors, so n_bd is always 256 (unless
+ * Note the difference between TFD_QUEUE_SIZE_MAX and n_window: the hardware
+ * always assumes 256 descriptors, so TFD_QUEUE_SIZE_MAX is always 256 (unless
  * there might be HW changes in the future). For the normal TX
  * queues, n_window, which is the size of the software queue data
  * is also 256; however, for the command queue, n_window is only
  * 32 since we don't need so many commands pending. Since the HW
- * still uses 256 BDs for DMA though, n_bd stays 256. As a result,
+ * still uses 256 BDs for DMA though, TFD_QUEUE_SIZE_MAX stays 256. As a result,
  * the software buffers (in the variables @meta, @txb in struct
  * iwl_txq) only have 32 entries, while the HW buffers (@tfds in
  * the same struct) have 256.
@@ -162,7 +160,6 @@ struct iwl_cmd_meta {
  * data is a window overlayed over the HW queue.
  */
 struct iwl_queue {
-	int n_bd;              /* number of BDs in this queue */
 	int write_ptr;       /* 1-st empty entry (index) host_w*/
 	int read_ptr;         /* last used entry (index) host_r*/
 	/* use for monitoring and recovering the stuck queue */
@@ -231,7 +228,7 @@ struct iwl_txq {
 	spinlock_t lock;
 	struct timer_list stuck_timer;
 	struct iwl_trans_pcie *trans_pcie;
-	u8 need_update;
+	bool need_update;
 	u8 active;
 	bool ampdu;
 };
@@ -270,6 +267,9 @@ struct iwl_trans_pcie {
 	struct iwl_trans *trans;
 	struct iwl_drv *drv;
 
+	struct net_device napi_dev;
+	struct napi_struct napi;
+
 	/* INT ICT Table */
 	__le32 *ict_tbl;
 	dma_addr_t ict_tbl_dma;
@@ -362,7 +362,7 @@ void iwl_trans_pcie_txq_enable(struct iwl_trans *trans, int txq_id, int fifo,
 void iwl_trans_pcie_txq_disable(struct iwl_trans *trans, int queue);
 int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		      struct iwl_device_cmd *dev_cmd, int txq_id);
-void iwl_pcie_txq_inc_wr_ptr(struct iwl_trans *trans, struct iwl_txq *txq);
+void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans);
 int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans, struct iwl_host_cmd *cmd);
 void iwl_pcie_hcmd_complete(struct iwl_trans *trans,
 			    struct iwl_rx_cmd_buffer *rxb, int handler_status);
@@ -370,6 +370,13 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 			    struct sk_buff_head *skbs);
 void iwl_trans_pcie_tx_reset(struct iwl_trans *trans);
 
+static inline u16 iwl_pcie_tfd_tb_get_len(struct iwl_tfd *tfd, u8 idx)
+{
+	struct iwl_tfd_tb *tb = &tfd->tbs[idx];
+
+	return le16_to_cpu(tb->hi_n_len) >> 4;
+}
+
 /*****************************************************
 * Error handling
 ******************************************************/
diff --git a/drivers/net/wireless/iwlwifi/pcie/rx.c b/drivers/net/wireless/iwlwifi/pcie/rx.c
index fdfa3969cac..a2698e5e062 100644
--- a/drivers/net/wireless/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/rx.c
@@ -145,15 +145,13 @@ int iwl_pcie_rx_stop(struct iwl_trans *trans)
 /*
  * iwl_pcie_rxq_inc_wr_ptr - Update the write pointer for the RX queue
  */
-static void iwl_pcie_rxq_inc_wr_ptr(struct iwl_trans *trans,
-				    struct iwl_rxq *rxq)
+static void iwl_pcie_rxq_inc_wr_ptr(struct iwl_trans *trans)
 {
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_rxq *rxq = &trans_pcie->rxq;
 	u32 reg;
 
-	spin_lock(&rxq->lock);
-
-	if (rxq->need_update == 0)
-		goto exit_unlock;
+	lockdep_assert_held(&rxq->lock);
 
 	/*
 	 * explicitly wake up the NIC if:
@@ -169,13 +167,27 @@ static void iwl_pcie_rxq_inc_wr_ptr(struct iwl_trans *trans,
 				       reg);
 			iwl_set_bit(trans, CSR_GP_CNTRL,
 				    CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
-			goto exit_unlock;
+			rxq->need_update = true;
+			return;
 		}
 	}
 
 	rxq->write_actual = round_down(rxq->write, 8);
 	iwl_write32(trans, FH_RSCSR_CHNL0_WPTR, rxq->write_actual);
-	rxq->need_update = 0;
+}
+
+static void iwl_pcie_rxq_check_wrptr(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_rxq *rxq = &trans_pcie->rxq;
+
+	spin_lock(&rxq->lock);
+
+	if (!rxq->need_update)
+		goto exit_unlock;
+
+	iwl_pcie_rxq_inc_wr_ptr(trans);
+	rxq->need_update = false;
 
  exit_unlock:
 	spin_unlock(&rxq->lock);
@@ -236,9 +248,8 @@ static void iwl_pcie_rxq_restock(struct iwl_trans *trans)
 	 * Increment device's write pointer in multiples of 8. */
 	if (rxq->write_actual != (rxq->write & ~0x7)) {
 		spin_lock(&rxq->lock);
-		rxq->need_update = 1;
+		iwl_pcie_rxq_inc_wr_ptr(trans);
 		spin_unlock(&rxq->lock);
-		iwl_pcie_rxq_inc_wr_ptr(trans, rxq);
 	}
 }
 
@@ -362,20 +373,9 @@ static void iwl_pcie_rxq_free_rbs(struct iwl_trans *trans)
  * Also restock the Rx queue via iwl_pcie_rxq_restock.
  * This is called as a scheduled work item (except for during initialization)
  */
-static void iwl_pcie_rx_replenish(struct iwl_trans *trans)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-
-	iwl_pcie_rxq_alloc_rbs(trans, GFP_KERNEL);
-
-	spin_lock(&trans_pcie->irq_lock);
-	iwl_pcie_rxq_restock(trans);
-	spin_unlock(&trans_pcie->irq_lock);
-}
-
-static void iwl_pcie_rx_replenish_now(struct iwl_trans *trans)
+static void iwl_pcie_rx_replenish(struct iwl_trans *trans, gfp_t gfp)
 {
-	iwl_pcie_rxq_alloc_rbs(trans, GFP_ATOMIC);
+	iwl_pcie_rxq_alloc_rbs(trans, gfp);
 
 	iwl_pcie_rxq_restock(trans);
 }
@@ -385,7 +385,7 @@ static void iwl_pcie_rx_replenish_work(struct work_struct *data)
 	struct iwl_trans_pcie *trans_pcie =
 	    container_of(data, struct iwl_trans_pcie, rx_replenish);
 
-	iwl_pcie_rx_replenish(trans_pcie->trans);
+	iwl_pcie_rx_replenish(trans_pcie->trans, GFP_KERNEL);
 }
 
 static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
@@ -521,14 +521,13 @@ int iwl_pcie_rx_init(struct iwl_trans *trans)
 	memset(rxq->rb_stts, 0, sizeof(*rxq->rb_stts));
 	spin_unlock(&rxq->lock);
 
-	iwl_pcie_rx_replenish(trans);
+	iwl_pcie_rx_replenish(trans, GFP_KERNEL);
 
 	iwl_pcie_rx_hw_init(trans, rxq);
 
-	spin_lock(&trans_pcie->irq_lock);
-	rxq->need_update = 1;
-	iwl_pcie_rxq_inc_wr_ptr(trans, rxq);
-	spin_unlock(&trans_pcie->irq_lock);
+	spin_lock(&rxq->lock);
+	iwl_pcie_rxq_inc_wr_ptr(trans);
+	spin_unlock(&rxq->lock);
 
 	return 0;
 }
@@ -673,7 +672,6 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 	/* Reuse the page if possible. For notification packets and
 	 * SKBs that fail to Rx correctly, add them back into the
 	 * rx_free list for reuse later. */
-	spin_lock(&rxq->lock);
 	if (rxb->page != NULL) {
 		rxb->page_dma =
 			dma_map_page(trans->dev, rxb->page, 0,
@@ -694,7 +692,6 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		}
 	} else
 		list_add_tail(&rxb->list, &rxq->rx_used);
-	spin_unlock(&rxq->lock);
 }
 
 /*
@@ -709,6 +706,8 @@ static void iwl_pcie_rx_handle(struct iwl_trans *trans)
 	u32 count = 8;
 	int total_empty;
 
+restart:
+	spin_lock(&rxq->lock);
 	/* uCode's read index (stored in shared DRAM) indicates the last Rx
 	 * buffer that the driver may process (last buffer filled by ucode). */
 	r = le16_to_cpu(ACCESS_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF;
@@ -743,18 +742,25 @@ static void iwl_pcie_rx_handle(struct iwl_trans *trans)
 			count++;
 			if (count >= 8) {
 				rxq->read = i;
-				iwl_pcie_rx_replenish_now(trans);
+				spin_unlock(&rxq->lock);
+				iwl_pcie_rx_replenish(trans, GFP_ATOMIC);
 				count = 0;
+				goto restart;
 			}
 		}
 	}
 
 	/* Backtrack one entry */
 	rxq->read = i;
+	spin_unlock(&rxq->lock);
+
 	if (fill_rx)
-		iwl_pcie_rx_replenish_now(trans);
+		iwl_pcie_rx_replenish(trans, GFP_ATOMIC);
 	else
 		iwl_pcie_rxq_restock(trans);
+
+	if (trans_pcie->napi.poll)
+		napi_gro_flush(&trans_pcie->napi, false);
 }
 
 /*
@@ -844,7 +850,7 @@ static u32 iwl_pcie_int_cause_ict(struct iwl_trans *trans)
 				trans_pcie->ict_index, read);
 		trans_pcie->ict_tbl[trans_pcie->ict_index] = 0;
 		trans_pcie->ict_index =
-			iwl_queue_inc_wrap(trans_pcie->ict_index, ICT_COUNT);
+			((trans_pcie->ict_index + 1) & (ICT_COUNT - 1));
 
 		read = le32_to_cpu(trans_pcie->ict_tbl[trans_pcie->ict_index]);
 		trace_iwlwifi_dev_ict_read(trans->dev, trans_pcie->ict_index,
@@ -876,7 +882,6 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 	struct isr_statistics *isr_stats = &trans_pcie->isr_stats;
 	u32 inta = 0;
 	u32 handled = 0;
-	u32 i;
 
 	lock_map_acquire(&trans->sync_cmd_lockdep_map);
 
@@ -1028,9 +1033,8 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 	/* uCode wakes up after power-down sleep */
 	if (inta & CSR_INT_BIT_WAKEUP) {
 		IWL_DEBUG_ISR(trans, "Wakeup interrupt\n");
-		iwl_pcie_rxq_inc_wr_ptr(trans, &trans_pcie->rxq);
-		for (i = 0; i < trans->cfg->base_params->num_of_queues; i++)
-			iwl_pcie_txq_inc_wr_ptr(trans, &trans_pcie->txq[i]);
+		iwl_pcie_rxq_check_wrptr(trans);
+		iwl_pcie_txq_check_wrptrs(trans);
 
 		isr_stats->wakeup++;
 
@@ -1068,8 +1072,6 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 		iwl_write8(trans, CSR_INT_PERIODIC_REG,
 			    CSR_INT_PERIODIC_DIS);
 
-		iwl_pcie_rx_handle(trans);
-
 		/*
 		 * Enable periodic interrupt in 8 msec only if we received
 		 * real RX interrupt (instead of just periodic int), to catch
@@ -1082,6 +1084,10 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id)
 				   CSR_INT_PERIODIC_ENA);
 
 		isr_stats->rx++;
+
+		local_bh_disable();
+		iwl_pcie_rx_handle(trans);
+		local_bh_enable();
 	}
 
 	/* This "Tx" DMA channel is used only for loading uCode */
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index 2365553f1ef..788085bc65d 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -73,6 +73,7 @@
 #include "iwl-csr.h"
 #include "iwl-prph.h"
 #include "iwl-agn-hw.h"
+#include "iwl-fw-error-dump.h"
 #include "internal.h"
 
 static u32 iwl_trans_pcie_read_shr(struct iwl_trans *trans, u32 reg)
@@ -103,7 +104,6 @@ static void iwl_pcie_set_pwr(struct iwl_trans *trans, bool vaux)
 
 /* PCI registers */
 #define PCI_CFG_RETRY_TIMEOUT	0x041
-#define CPU1_CPU2_SEPARATOR_SECTION	0xFFFFCCCC
 
 static void iwl_pcie_apm_config(struct iwl_trans *trans)
 {
@@ -454,6 +454,7 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 {
 	int ret;
 	int t = 0;
+	int iter;
 
 	IWL_DEBUG_INFO(trans, "iwl_trans_prepare_card_hw enter\n");
 
@@ -462,18 +463,23 @@ static int iwl_pcie_prepare_card_hw(struct iwl_trans *trans)
 	if (ret >= 0)
 		return 0;
 
-	/* If HW is not ready, prepare the conditions to check again */
-	iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
-		    CSR_HW_IF_CONFIG_REG_PREPARE);
+	for (iter = 0; iter < 10; iter++) {
+		/* If HW is not ready, prepare the conditions to check again */
+		iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
+			    CSR_HW_IF_CONFIG_REG_PREPARE);
+
+		do {
+			ret = iwl_pcie_set_hw_ready(trans);
+			if (ret >= 0)
+				return 0;
 
-	do {
-		ret = iwl_pcie_set_hw_ready(trans);
-		if (ret >= 0)
-			return 0;
+			usleep_range(200, 1000);
+			t += 200;
+		} while (t < 150000);
+		msleep(25);
+	}
 
-		usleep_range(200, 1000);
-		t += 200;
-	} while (t < 150000);
+	IWL_DEBUG_INFO(trans, "got NIC after %d iterations\n", iter);
 
 	return ret;
 }
@@ -1053,6 +1059,12 @@ static void iwl_trans_pcie_write_prph(struct iwl_trans *trans, u32 addr,
 	iwl_trans_pcie_write32(trans, HBUS_TARG_PRPH_WDAT, val);
 }
 
+static int iwl_pcie_dummy_napi_poll(struct napi_struct *napi, int budget)
+{
+	WARN_ON(1);
+	return 0;
+}
+
 static void iwl_trans_pcie_configure(struct iwl_trans *trans,
 				     const struct iwl_trans_config *trans_cfg)
 {
@@ -1079,6 +1091,18 @@ static void iwl_trans_pcie_configure(struct iwl_trans *trans,
 
 	trans_pcie->command_names = trans_cfg->command_names;
 	trans_pcie->bc_table_dword = trans_cfg->bc_table_dword;
+
+	/* Initialize NAPI here - it should be before registering to mac80211
+	 * in the opmode but after the HW struct is allocated.
+	 * As this function may be called again in some corner cases don't
+	 * do anything if NAPI was already initialized.
+	 */
+	if (!trans_pcie->napi.poll && trans->op_mode->ops->napi_add) {
+		init_dummy_netdev(&trans_pcie->napi_dev);
+		iwl_op_mode_napi_add(trans->op_mode, &trans_pcie->napi,
+				     &trans_pcie->napi_dev,
+				     iwl_pcie_dummy_napi_poll, 64);
+	}
 }
 
 void iwl_trans_pcie_free(struct iwl_trans *trans)
@@ -1099,6 +1123,9 @@ void iwl_trans_pcie_free(struct iwl_trans *trans)
 	pci_disable_device(trans_pcie->pci_dev);
 	kmem_cache_destroy(trans->dev_cmd_pool);
 
+	if (trans_pcie->napi.poll)
+		netif_napi_del(&trans_pcie->napi);
+
 	kfree(trans);
 }
 
@@ -1237,7 +1264,7 @@ static int iwl_trans_pcie_write_mem(struct iwl_trans *trans, u32 addr,
 
 #define IWL_FLUSH_WAIT_MS	2000
 
-static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans)
+static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans, u32 txq_bm)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_txq *txq;
@@ -1250,13 +1277,31 @@ static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans)
 
 	/* waiting for all the tx frames complete might take a while */
 	for (cnt = 0; cnt < trans->cfg->base_params->num_of_queues; cnt++) {
+		u8 wr_ptr;
+
 		if (cnt == trans_pcie->cmd_queue)
 			continue;
+		if (!test_bit(cnt, trans_pcie->queue_used))
+			continue;
+		if (!(BIT(cnt) & txq_bm))
+			continue;
+
+		IWL_DEBUG_TX_QUEUES(trans, "Emptying queue %d...\n", cnt);
 		txq = &trans_pcie->txq[cnt];
 		q = &txq->q;
-		while (q->read_ptr != q->write_ptr && !time_after(jiffies,
-		       now + msecs_to_jiffies(IWL_FLUSH_WAIT_MS)))
+		wr_ptr = ACCESS_ONCE(q->write_ptr);
+
+		while (q->read_ptr != ACCESS_ONCE(q->write_ptr) &&
+		       !time_after(jiffies,
+				   now + msecs_to_jiffies(IWL_FLUSH_WAIT_MS))) {
+			u8 write_ptr = ACCESS_ONCE(q->write_ptr);
+
+			if (WARN_ONCE(wr_ptr != write_ptr,
+				      "WR pointer moved while flushing %d -> %d\n",
+				      wr_ptr, write_ptr))
+				return -ETIMEDOUT;
 			msleep(1);
+		}
 
 		if (q->read_ptr != q->write_ptr) {
 			IWL_ERR(trans,
@@ -1264,6 +1309,7 @@ static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans)
 			ret = -ETIMEDOUT;
 			break;
 		}
+		IWL_DEBUG_TX_QUEUES(trans, "Queue %d is now empty.\n", cnt);
 	}
 
 	if (!ret)
@@ -1298,8 +1344,8 @@ static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans)
 		IWL_ERR(trans,
 			"Q %d is %sactive and mapped to fifo %d ra_tid 0x%04x [%d,%d]\n",
 			cnt, active ? "" : "in", fifo, tbl_dw,
-			iwl_read_prph(trans,
-				      SCD_QUEUE_RDPTR(cnt)) & (txq->q.n_bd - 1),
+			iwl_read_prph(trans, SCD_QUEUE_RDPTR(cnt)) &
+				(TFD_QUEUE_SIZE_MAX - 1),
 			iwl_read_prph(trans, SCD_QUEUE_WRPTR(cnt)));
 	}
 
@@ -1630,6 +1676,61 @@ err:
 	IWL_ERR(trans, "failed to create the trans debugfs entry\n");
 	return -ENOMEM;
 }
+
+static u32 iwl_trans_pcie_get_cmdlen(struct iwl_tfd *tfd)
+{
+	u32 cmdlen = 0;
+	int i;
+
+	for (i = 0; i < IWL_NUM_OF_TBS; i++)
+		cmdlen += iwl_pcie_tfd_tb_get_len(tfd, i);
+
+	return cmdlen;
+}
+
+static u32 iwl_trans_pcie_dump_data(struct iwl_trans *trans,
+				    void *buf, u32 buflen)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_fw_error_dump_data *data;
+	struct iwl_txq *cmdq = &trans_pcie->txq[trans_pcie->cmd_queue];
+	struct iwl_fw_error_dump_txcmd *txcmd;
+	u32 len;
+	int i, ptr;
+
+	if (!buf)
+		return sizeof(*data) +
+		       cmdq->q.n_window * (sizeof(*txcmd) +
+					   TFD_MAX_PAYLOAD_SIZE);
+
+	len = 0;
+	data = buf;
+	data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXCMD);
+	txcmd = (void *)data->data;
+	spin_lock_bh(&cmdq->lock);
+	ptr = cmdq->q.write_ptr;
+	for (i = 0; i < cmdq->q.n_window; i++) {
+		u8 idx = get_cmd_index(&cmdq->q, ptr);
+		u32 caplen, cmdlen;
+
+		cmdlen = iwl_trans_pcie_get_cmdlen(&cmdq->tfds[ptr]);
+		caplen = min_t(u32, TFD_MAX_PAYLOAD_SIZE, cmdlen);
+
+		if (cmdlen) {
+			len += sizeof(*txcmd) + caplen;
+			txcmd->cmdlen = cpu_to_le32(cmdlen);
+			txcmd->caplen = cpu_to_le32(caplen);
+			memcpy(txcmd->data, cmdq->entries[idx].cmd, caplen);
+			txcmd = (void *)((u8 *)txcmd->data + caplen);
+		}
+
+		ptr = iwl_queue_dec_wrap(ptr);
+	}
+	spin_unlock_bh(&cmdq->lock);
+
+	data->len = cpu_to_le32(len);
+	return sizeof(*data) + len;
+}
 #else
 static int iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans,
 					 struct dentry *dir)
@@ -1672,6 +1773,10 @@ static const struct iwl_trans_ops trans_ops_pcie = {
 	.grab_nic_access = iwl_trans_pcie_grab_nic_access,
 	.release_nic_access = iwl_trans_pcie_release_nic_access,
 	.set_bits_mask = iwl_trans_pcie_set_bits_mask,
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	.dump_data = iwl_trans_pcie_dump_data,
+#endif
 };
 
 struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c
index 3b0c72c1005..038940afbdc 100644
--- a/drivers/net/wireless/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/tx.c
@@ -70,20 +70,20 @@ static int iwl_queue_space(const struct iwl_queue *q)
 
 	/*
 	 * To avoid ambiguity between empty and completely full queues, there
-	 * should always be less than q->n_bd elements in the queue.
-	 * If q->n_window is smaller than q->n_bd, there is no need to reserve
-	 * any queue entries for this purpose.
+	 * should always be less than TFD_QUEUE_SIZE_MAX elements in the queue.
+	 * If q->n_window is smaller than TFD_QUEUE_SIZE_MAX, there is no need
+	 * to reserve any queue entries for this purpose.
 	 */
-	if (q->n_window < q->n_bd)
+	if (q->n_window < TFD_QUEUE_SIZE_MAX)
 		max = q->n_window;
 	else
-		max = q->n_bd - 1;
+		max = TFD_QUEUE_SIZE_MAX - 1;
 
 	/*
-	 * q->n_bd is a power of 2, so the following is equivalent to modulo by
-	 * q->n_bd and is well defined for negative dividends.
+	 * TFD_QUEUE_SIZE_MAX is a power of 2, so the following is equivalent to
+	 * modulo by TFD_QUEUE_SIZE_MAX and is well defined.
 	 */
-	used = (q->write_ptr - q->read_ptr) & (q->n_bd - 1);
+	used = (q->write_ptr - q->read_ptr) & (TFD_QUEUE_SIZE_MAX - 1);
 
 	if (WARN_ON(used > max))
 		return 0;
@@ -94,17 +94,11 @@ static int iwl_queue_space(const struct iwl_queue *q)
 /*
  * iwl_queue_init - Initialize queue's high/low-water and read/write indexes
  */
-static int iwl_queue_init(struct iwl_queue *q, int count, int slots_num, u32 id)
+static int iwl_queue_init(struct iwl_queue *q, int slots_num, u32 id)
 {
-	q->n_bd = count;
 	q->n_window = slots_num;
 	q->id = id;
 
-	/* count must be power-of-two size, otherwise iwl_queue_inc_wrap
-	 * and iwl_queue_dec_wrap are broken. */
-	if (WARN_ON(!is_power_of_2(count)))
-		return -EINVAL;
-
 	/* slots_num must be power-of-two size, otherwise
 	 * get_cmd_index is broken. */
 	if (WARN_ON(!is_power_of_2(slots_num)))
@@ -197,17 +191,17 @@ static void iwl_pcie_txq_stuck_timer(unsigned long data)
 		IWL_ERR(trans,
 			"Q %d is %sactive and mapped to fifo %d ra_tid 0x%04x [%d,%d]\n",
 			i, active ? "" : "in", fifo, tbl_dw,
-			iwl_read_prph(trans,
-				      SCD_QUEUE_RDPTR(i)) & (txq->q.n_bd - 1),
+			iwl_read_prph(trans, SCD_QUEUE_RDPTR(i)) &
+				(TFD_QUEUE_SIZE_MAX - 1),
 			iwl_read_prph(trans, SCD_QUEUE_WRPTR(i)));
 	}
 
 	for (i = q->read_ptr; i != q->write_ptr;
-	     i = iwl_queue_inc_wrap(i, q->n_bd))
+	     i = iwl_queue_inc_wrap(i))
 		IWL_ERR(trans, "scratch %d = 0x%08x\n", i,
 			le32_to_cpu(txq->scratchbufs[i].scratch));
 
-	iwl_write_prph(trans, DEVICE_SET_NMI_REG, 1);
+	iwl_force_nmi(trans);
 }
 
 /*
@@ -287,14 +281,14 @@ static void iwl_pcie_txq_inval_byte_cnt_tbl(struct iwl_trans *trans,
 /*
  * iwl_pcie_txq_inc_wr_ptr - Send new write index to hardware
  */
-void iwl_pcie_txq_inc_wr_ptr(struct iwl_trans *trans, struct iwl_txq *txq)
+static void iwl_pcie_txq_inc_wr_ptr(struct iwl_trans *trans,
+				    struct iwl_txq *txq)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	u32 reg = 0;
 	int txq_id = txq->q.id;
 
-	if (txq->need_update == 0)
-		return;
+	lockdep_assert_held(&txq->lock);
 
 	/*
 	 * explicitly wake up the NIC if:
@@ -317,6 +311,7 @@ void iwl_pcie_txq_inc_wr_ptr(struct iwl_trans *trans, struct iwl_txq *txq)
 				       txq_id, reg);
 			iwl_set_bit(trans, CSR_GP_CNTRL,
 				    CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
+			txq->need_update = true;
 			return;
 		}
 	}
@@ -327,8 +322,23 @@ void iwl_pcie_txq_inc_wr_ptr(struct iwl_trans *trans, struct iwl_txq *txq)
 	 */
 	IWL_DEBUG_TX(trans, "Q:%d WR: 0x%x\n", txq_id, txq->q.write_ptr);
 	iwl_write32(trans, HBUS_TARG_WRPTR, txq->q.write_ptr | (txq_id << 8));
+}
+
+void iwl_pcie_txq_check_wrptrs(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	int i;
+
+	for (i = 0; i < trans->cfg->base_params->num_of_queues; i++) {
+		struct iwl_txq *txq = &trans_pcie->txq[i];
 
-	txq->need_update = 0;
+		spin_lock_bh(&txq->lock);
+		if (trans_pcie->txq[i].need_update) {
+			iwl_pcie_txq_inc_wr_ptr(trans, txq);
+			trans_pcie->txq[i].need_update = false;
+		}
+		spin_unlock_bh(&txq->lock);
+	}
 }
 
 static inline dma_addr_t iwl_pcie_tfd_tb_get_addr(struct iwl_tfd *tfd, u8 idx)
@@ -343,13 +353,6 @@ static inline dma_addr_t iwl_pcie_tfd_tb_get_addr(struct iwl_tfd *tfd, u8 idx)
 	return addr;
 }
 
-static inline u16 iwl_pcie_tfd_tb_get_len(struct iwl_tfd *tfd, u8 idx)
-{
-	struct iwl_tfd_tb *tb = &tfd->tbs[idx];
-
-	return le16_to_cpu(tb->hi_n_len) >> 4;
-}
-
 static inline void iwl_pcie_tfd_set_tb(struct iwl_tfd *tfd, u8 idx,
 				       dma_addr_t addr, u16 len)
 {
@@ -409,13 +412,17 @@ static void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 {
 	struct iwl_tfd *tfd_tmp = txq->tfds;
 
-	/* rd_ptr is bounded by n_bd and idx is bounded by n_window */
+	/* rd_ptr is bounded by TFD_QUEUE_SIZE_MAX and
+	 * idx is bounded by n_window
+	 */
 	int rd_ptr = txq->q.read_ptr;
 	int idx = get_cmd_index(&txq->q, rd_ptr);
 
 	lockdep_assert_held(&txq->lock);
 
-	/* We have only q->n_window txq->entries, but we use q->n_bd tfds */
+	/* We have only q->n_window txq->entries, but we use
+	 * TFD_QUEUE_SIZE_MAX tfds
+	 */
 	iwl_pcie_tfd_unmap(trans, &txq->entries[idx].meta, &tfd_tmp[rd_ptr]);
 
 	/* free SKB */
@@ -436,7 +443,7 @@ static void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
 }
 
 static int iwl_pcie_txq_build_tfd(struct iwl_trans *trans, struct iwl_txq *txq,
-				  dma_addr_t addr, u16 len, u8 reset)
+				  dma_addr_t addr, u16 len, bool reset)
 {
 	struct iwl_queue *q;
 	struct iwl_tfd *tfd, *tfd_tmp;
@@ -542,15 +549,14 @@ static int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
 {
 	int ret;
 
-	txq->need_update = 0;
+	txq->need_update = false;
 
 	/* TFD_QUEUE_SIZE_MAX must be power-of-two size, otherwise
 	 * iwl_queue_inc_wrap and iwl_queue_dec_wrap are broken. */
 	BUILD_BUG_ON(TFD_QUEUE_SIZE_MAX & (TFD_QUEUE_SIZE_MAX - 1));
 
 	/* Initialize queue's high/low-water marks, and head/tail indexes */
-	ret = iwl_queue_init(&txq->q, TFD_QUEUE_SIZE_MAX, slots_num,
-			txq_id);
+	ret = iwl_queue_init(&txq->q, slots_num, txq_id);
 	if (ret)
 		return ret;
 
@@ -575,15 +581,12 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 	struct iwl_txq *txq = &trans_pcie->txq[txq_id];
 	struct iwl_queue *q = &txq->q;
 
-	if (!q->n_bd)
-		return;
-
 	spin_lock_bh(&txq->lock);
 	while (q->write_ptr != q->read_ptr) {
 		IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n",
 				   txq_id, q->read_ptr);
 		iwl_pcie_txq_free_tfd(trans, txq);
-		q->read_ptr = iwl_queue_inc_wrap(q->read_ptr, q->n_bd);
+		q->read_ptr = iwl_queue_inc_wrap(q->read_ptr);
 	}
 	txq->active = false;
 	spin_unlock_bh(&txq->lock);
@@ -620,10 +623,12 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 		}
 
 	/* De-alloc circular buffer of TFDs */
-	if (txq->q.n_bd) {
-		dma_free_coherent(dev, sizeof(struct iwl_tfd) *
-				  txq->q.n_bd, txq->tfds, txq->q.dma_addr);
+	if (txq->tfds) {
+		dma_free_coherent(dev,
+				  sizeof(struct iwl_tfd) * TFD_QUEUE_SIZE_MAX,
+				  txq->tfds, txq->q.dma_addr);
 		txq->q.dma_addr = 0;
+		txq->tfds = NULL;
 
 		dma_free_coherent(dev,
 				  sizeof(*txq->scratchbufs) * txq->q.n_window,
@@ -680,7 +685,8 @@ void iwl_pcie_tx_start(struct iwl_trans *trans, u32 scd_base_addr)
 	/* The chain extension of the SCD doesn't work well. This feature is
 	 * enabled by default by the HW, so we need to disable it manually.
 	 */
-	iwl_write_prph(trans, SCD_CHAINEXT_EN, 0);
+	if (trans->cfg->base_params->scd_chain_ext_wa)
+		iwl_write_prph(trans, SCD_CHAINEXT_EN, 0);
 
 	iwl_trans_ac_txq_enable(trans, trans_pcie->cmd_queue,
 				trans_pcie->cmd_fifo);
@@ -931,8 +937,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_txq *txq = &trans_pcie->txq[txq_id];
-	/* n_bd is usually 256 => n_bd - 1 = 0xff */
-	int tfd_num = ssn & (txq->q.n_bd - 1);
+	int tfd_num = ssn & (TFD_QUEUE_SIZE_MAX - 1);
 	struct iwl_queue *q = &txq->q;
 	int last_to_free;
 
@@ -956,12 +961,12 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 	/*Since we free until index _not_ inclusive, the one before index is
 	 * the last we will free. This one must be used */
-	last_to_free = iwl_queue_dec_wrap(tfd_num, q->n_bd);
+	last_to_free = iwl_queue_dec_wrap(tfd_num);
 
 	if (!iwl_queue_used(q, last_to_free)) {
 		IWL_ERR(trans,
 			"%s: Read index for DMA queue txq id (%d), last_to_free %d is out of range [0-%d] %d %d.\n",
-			__func__, txq_id, last_to_free, q->n_bd,
+			__func__, txq_id, last_to_free, TFD_QUEUE_SIZE_MAX,
 			q->write_ptr, q->read_ptr);
 		goto out;
 	}
@@ -971,7 +976,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 	for (;
 	     q->read_ptr != tfd_num;
-	     q->read_ptr = iwl_queue_inc_wrap(q->read_ptr, q->n_bd)) {
+	     q->read_ptr = iwl_queue_inc_wrap(q->read_ptr)) {
 
 		if (WARN_ON_ONCE(txq->entries[txq->q.read_ptr].skb == NULL))
 			continue;
@@ -1010,25 +1015,26 @@ static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 
 	lockdep_assert_held(&txq->lock);
 
-	if ((idx >= q->n_bd) || (!iwl_queue_used(q, idx))) {
+	if ((idx >= TFD_QUEUE_SIZE_MAX) || (!iwl_queue_used(q, idx))) {
 		IWL_ERR(trans,
 			"%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
-			__func__, txq_id, idx, q->n_bd,
+			__func__, txq_id, idx, TFD_QUEUE_SIZE_MAX,
 			q->write_ptr, q->read_ptr);
 		return;
 	}
 
-	for (idx = iwl_queue_inc_wrap(idx, q->n_bd); q->read_ptr != idx;
-	     q->read_ptr = iwl_queue_inc_wrap(q->read_ptr, q->n_bd)) {
+	for (idx = iwl_queue_inc_wrap(idx); q->read_ptr != idx;
+	     q->read_ptr = iwl_queue_inc_wrap(q->read_ptr)) {
 
 		if (nfreed++ > 0) {
 			IWL_ERR(trans, "HCMD skipped: index (%d) %d %d\n",
 				idx, q->write_ptr, q->read_ptr);
-			iwl_write_prph(trans, DEVICE_SET_NMI_REG, 1);
+			iwl_force_nmi(trans);
 		}
 	}
 
-	if (q->read_ptr == q->write_ptr) {
+	if (trans->cfg->base_params->apmg_wake_up_wa &&
+	    q->read_ptr == q->write_ptr) {
 		spin_lock_irqsave(&trans_pcie->reg_lock, flags);
 		WARN_ON(!trans_pcie->cmd_in_flight);
 		trans_pcie->cmd_in_flight = false;
@@ -1309,28 +1315,39 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	cmd_pos = offsetof(struct iwl_device_cmd, payload);
 	copy_size = sizeof(out_cmd->hdr);
 	for (i = 0; i < IWL_MAX_CMD_TBS_PER_TFD; i++) {
-		int copy = 0;
+		int copy;
 
 		if (!cmd->len[i])
 			continue;
 
-		/* need at least IWL_HCMD_SCRATCHBUF_SIZE copied */
-		if (copy_size < IWL_HCMD_SCRATCHBUF_SIZE) {
-			copy = IWL_HCMD_SCRATCHBUF_SIZE - copy_size;
-
-			if (copy > cmd->len[i])
-				copy = cmd->len[i];
-		}
-
 		/* copy everything if not nocopy/dup */
 		if (!(cmd->dataflags[i] & (IWL_HCMD_DFL_NOCOPY |
-					   IWL_HCMD_DFL_DUP)))
+					   IWL_HCMD_DFL_DUP))) {
 			copy = cmd->len[i];
 
-		if (copy) {
 			memcpy((u8 *)out_cmd + cmd_pos, cmd->data[i], copy);
 			cmd_pos += copy;
 			copy_size += copy;
+			continue;
+		}
+
+		/*
+		 * Otherwise we need at least IWL_HCMD_SCRATCHBUF_SIZE copied
+		 * in total (for the scratchbuf handling), but copy up to what
+		 * we can fit into the payload for debug dump purposes.
+		 */
+		copy = min_t(int, TFD_MAX_PAYLOAD_SIZE - cmd_pos, cmd->len[i]);
+
+		memcpy((u8 *)out_cmd + cmd_pos, cmd->data[i], copy);
+		cmd_pos += copy;
+
+		/* However, treat copy_size the proper way, we need it below */
+		if (copy_size < IWL_HCMD_SCRATCHBUF_SIZE) {
+			copy = IWL_HCMD_SCRATCHBUF_SIZE - copy_size;
+
+			if (copy > cmd->len[i])
+				copy = cmd->len[i];
+			copy_size += copy;
 		}
 	}
 
@@ -1345,7 +1362,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	memcpy(&txq->scratchbufs[q->write_ptr], &out_cmd->hdr, scratch_size);
 	iwl_pcie_txq_build_tfd(trans, txq,
 			       iwl_pcie_get_scratchbuf_dma(txq, q->write_ptr),
-			       scratch_size, 1);
+			       scratch_size, true);
 
 	/* map first command fragment, if any remains */
 	if (copy_size > scratch_size) {
@@ -1361,7 +1378,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 		}
 
 		iwl_pcie_txq_build_tfd(trans, txq, phys_addr,
-				       copy_size - scratch_size, 0);
+				       copy_size - scratch_size, false);
 	}
 
 	/* map the remaining (adjusted) nocopy/dup fragments */
@@ -1384,7 +1401,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 			goto out;
 		}
 
-		iwl_pcie_txq_build_tfd(trans, txq, phys_addr, cmdlen[i], 0);
+		iwl_pcie_txq_build_tfd(trans, txq, phys_addr, cmdlen[i], false);
 	}
 
 	out_meta->flags = cmd->flags;
@@ -1392,8 +1409,6 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 		kfree(txq->entries[idx].free_buf);
 	txq->entries[idx].free_buf = dup_buf;
 
-	txq->need_update = 1;
-
 	trace_iwlwifi_dev_hcmd(trans->dev, cmd, cmd_size, &out_cmd->hdr);
 
 	/* start timer if queue currently empty */
@@ -1405,9 +1420,11 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	/*
 	 * wake up the NIC to make sure that the firmware will see the host
 	 * command - we will let the NIC sleep once all the host commands
-	 * returned.
+	 * returned. This needs to be done only on NICs that have
+	 * apmg_wake_up_wa set.
 	 */
-	if (!trans_pcie->cmd_in_flight) {
+	if (trans->cfg->base_params->apmg_wake_up_wa &&
+	    !trans_pcie->cmd_in_flight) {
 		trans_pcie->cmd_in_flight = true;
 		__iwl_trans_pcie_set_bit(trans, CSR_GP_CNTRL,
 					 CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
@@ -1427,7 +1444,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	}
 
 	/* Increment and update queue's write index */
-	q->write_ptr = iwl_queue_inc_wrap(q->write_ptr, q->n_bd);
+	q->write_ptr = iwl_queue_inc_wrap(q->write_ptr);
 	iwl_pcie_txq_inc_wr_ptr(trans, txq);
 
 	spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
@@ -1583,7 +1600,7 @@ static int iwl_pcie_send_hcmd_sync(struct iwl_trans *trans,
 			       get_cmd_string(trans_pcie, cmd->id));
 		ret = -ETIMEDOUT;
 
-		iwl_write_prph(trans, DEVICE_SET_NMI_REG, 1);
+		iwl_force_nmi(trans);
 		iwl_trans_fw_error(trans);
 
 		goto cancel;
@@ -1661,7 +1678,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	dma_addr_t tb0_phys, tb1_phys, scratch_phys;
 	void *tb1_addr;
 	u16 len, tb1_len, tb2_len;
-	u8 wait_write_ptr = 0;
+	bool wait_write_ptr;
 	__le16 fc = hdr->frame_control;
 	u8 hdr_len = ieee80211_hdrlen(fc);
 	u16 wifi_seq;
@@ -1722,7 +1739,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	memcpy(&txq->scratchbufs[q->write_ptr], &dev_cmd->hdr,
 	       IWL_HCMD_SCRATCHBUF_SIZE);
 	iwl_pcie_txq_build_tfd(trans, txq, tb0_phys,
-			       IWL_HCMD_SCRATCHBUF_SIZE, 1);
+			       IWL_HCMD_SCRATCHBUF_SIZE, true);
 
 	/* there must be data left over for TB1 or this code must be changed */
 	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd) < IWL_HCMD_SCRATCHBUF_SIZE);
@@ -1732,7 +1749,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	tb1_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(trans->dev, tb1_phys)))
 		goto out_err;
-	iwl_pcie_txq_build_tfd(trans, txq, tb1_phys, tb1_len, 0);
+	iwl_pcie_txq_build_tfd(trans, txq, tb1_phys, tb1_len, false);
 
 	/*
 	 * Set up TFD's third entry to point directly to remainder
@@ -1748,7 +1765,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 					   &txq->tfds[q->write_ptr]);
 			goto out_err;
 		}
-		iwl_pcie_txq_build_tfd(trans, txq, tb2_phys, tb2_len, 0);
+		iwl_pcie_txq_build_tfd(trans, txq, tb2_phys, tb2_len, false);
 	}
 
 	/* Set up entry for this TFD in Tx byte-count array */
@@ -1762,12 +1779,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	trace_iwlwifi_dev_tx_data(trans->dev, skb,
 				  skb->data + hdr_len, tb2_len);
 
-	if (!ieee80211_has_morefrags(fc)) {
-		txq->need_update = 1;
-	} else {
-		wait_write_ptr = 1;
-		txq->need_update = 0;
-	}
+	wait_write_ptr = ieee80211_has_morefrags(fc);
 
 	/* start timer if queue currently empty */
 	if (txq->need_update && q->read_ptr == q->write_ptr &&
@@ -1775,22 +1787,19 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 		mod_timer(&txq->stuck_timer, jiffies + trans_pcie->wd_timeout);
 
 	/* Tell device the write index *just past* this latest filled TFD */
-	q->write_ptr = iwl_queue_inc_wrap(q->write_ptr, q->n_bd);
-	iwl_pcie_txq_inc_wr_ptr(trans, txq);
+	q->write_ptr = iwl_queue_inc_wrap(q->write_ptr);
+	if (!wait_write_ptr)
+		iwl_pcie_txq_inc_wr_ptr(trans, txq);
 
 	/*
 	 * At this point the frame is "transmitted" successfully
-	 * and we will get a TX status notification eventually,
-	 * regardless of the value of ret. "ret" only indicates
-	 * whether or not we should update the write pointer.
+	 * and we will get a TX status notification eventually.
 	 */
 	if (iwl_queue_space(q) < q->high_mark) {
-		if (wait_write_ptr) {
-			txq->need_update = 1;
+		if (wait_write_ptr)
 			iwl_pcie_txq_inc_wr_ptr(trans, txq);
-		} else {
+		else
 			iwl_stop_queue(trans, txq);
-		}
 	}
 	spin_unlock(&txq->lock);
 	return 0;
diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c
index 54e344aed6e..47a998d8f99 100644
--- a/drivers/net/wireless/libertas/cfg.c
+++ b/drivers/net/wireless/libertas/cfg.c
@@ -1006,9 +1006,8 @@ struct cmd_key_material {
 } __packed;
 
 static int lbs_set_key_material(struct lbs_private *priv,
-				int key_type,
-				int key_info,
-				u8 *key, u16 key_len)
+				int key_type, int key_info,
+				const u8 *key, u16 key_len)
 {
 	struct cmd_key_material cmd;
 	int ret;
@@ -1610,7 +1609,7 @@ static int lbs_cfg_del_key(struct wiphy *wiphy, struct net_device *netdev,
  */
 
 static int lbs_cfg_get_station(struct wiphy *wiphy, struct net_device *dev,
-			      u8 *mac, struct station_info *sinfo)
+			       const u8 *mac, struct station_info *sinfo)
 {
 	struct lbs_private *priv = wiphy_priv(wiphy);
 	s8 signal, noise;
diff --git a/drivers/net/wireless/libertas/defs.h b/drivers/net/wireless/libertas/defs.h
index ab966f08024..407784aca62 100644
--- a/drivers/net/wireless/libertas/defs.h
+++ b/drivers/net/wireless/libertas/defs.h
@@ -90,7 +90,8 @@ do { if ((lbs_debug & (grp)) == (grp)) \
 #define lbs_deb_cfg80211(fmt, args...)  LBS_DEB_LL(LBS_DEB_CFG80211, " cfg80211", fmt, ##args)
 
 #ifdef DEBUG
-static inline void lbs_deb_hex(unsigned int grp, const char *prompt, u8 *buf, int len)
+static inline void lbs_deb_hex(unsigned int grp, const char *prompt,
+			       const u8 *buf, int len)
 {
 	int i = 0;
 
diff --git a/drivers/net/wireless/libertas/rx.c b/drivers/net/wireless/libertas/rx.c
index c7366b07b56..e446fed7b34 100644
--- a/drivers/net/wireless/libertas/rx.c
+++ b/drivers/net/wireless/libertas/rx.c
@@ -71,8 +71,10 @@ int lbs_process_rxed_packet(struct lbs_private *priv, struct sk_buff *skb)
 
 	skb->ip_summed = CHECKSUM_NONE;
 
-	if (priv->wdev->iftype == NL80211_IFTYPE_MONITOR)
-		return process_rxed_802_11_packet(priv, skb);
+	if (priv->wdev->iftype == NL80211_IFTYPE_MONITOR) {
+		ret = process_rxed_802_11_packet(priv, skb);
+		goto done;
+	}
 
 	p_rx_pd = (struct rxpd *) skb->data;
 	p_rx_pkt = (struct rxpackethdr *) ((u8 *)p_rx_pd +
@@ -86,7 +88,7 @@ int lbs_process_rxed_packet(struct lbs_private *priv, struct sk_buff *skb)
 	if (skb->len < (ETH_HLEN + 8 + sizeof(struct rxpd))) {
 		lbs_deb_rx("rx err: frame received with bad length\n");
 		dev->stats.rx_length_errors++;
-		ret = 0;
+		ret = -EINVAL;
 		dev_kfree_skb(skb);
 		goto done;
 	}
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 9d7a52f5a41..a312c653d11 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1676,7 +1676,9 @@ static int mac80211_hwsim_ampdu_action(struct ieee80211_hw *hw,
 	return 0;
 }
 
-static void mac80211_hwsim_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void mac80211_hwsim_flush(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif,
+				 u32 queues, bool drop)
 {
 	/* Not implemented, queues only on kernel side */
 }
@@ -2056,6 +2058,7 @@ static int mac80211_hwsim_create_radio(int channels, const char *reg_alpha2,
 			    WIPHY_FLAG_AP_UAPSD |
 			    WIPHY_FLAG_HAS_CHANNEL_SWITCH;
 	hw->wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR;
+	hw->wiphy->features |= NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE;
 
 	/* ask mac80211 to reserve space for magic */
 	hw->vif_data_size = sizeof(struct hwsim_vif_priv);
diff --git a/drivers/net/wireless/mwifiex/11ac.c b/drivers/net/wireless/mwifiex/11ac.c
index c92f27aa71e..706831df1fa 100644
--- a/drivers/net/wireless/mwifiex/11ac.c
+++ b/drivers/net/wireless/mwifiex/11ac.c
@@ -212,8 +212,7 @@ int mwifiex_cmd_append_11ac_tlv(struct mwifiex_private *priv,
 				      sizeof(struct mwifiex_ie_types_header));
 			memcpy((u8 *)vht_op +
 				sizeof(struct mwifiex_ie_types_header),
-			       (u8 *)bss_desc->bcn_vht_oper +
-			       sizeof(struct ieee_types_header),
+			       (u8 *)bss_desc->bcn_vht_oper,
 			       le16_to_cpu(vht_op->header.len));
 
 			/* negotiate the channel width and central freq
diff --git a/drivers/net/wireless/mwifiex/11n.c b/drivers/net/wireless/mwifiex/11n.c
index d14ead8beca..e1c2f67ae85 100644
--- a/drivers/net/wireless/mwifiex/11n.c
+++ b/drivers/net/wireless/mwifiex/11n.c
@@ -345,8 +345,7 @@ mwifiex_cmd_append_11n_tlv(struct mwifiex_private *priv,
 
 			memcpy((u8 *) ht_info +
 			       sizeof(struct mwifiex_ie_types_header),
-			       (u8 *) bss_desc->bcn_ht_oper +
-			       sizeof(struct ieee_types_header),
+			       (u8 *)bss_desc->bcn_ht_oper,
 			       le16_to_cpu(ht_info->header.len));
 
 			if (!(sband->ht_cap.cap &
@@ -750,3 +749,45 @@ void mwifiex_set_ba_params(struct mwifiex_private *priv)
 
 	return;
 }
+
+u8 mwifiex_get_sec_chan_offset(int chan)
+{
+	u8 sec_offset;
+
+	switch (chan) {
+	case 36:
+	case 44:
+	case 52:
+	case 60:
+	case 100:
+	case 108:
+	case 116:
+	case 124:
+	case 132:
+	case 140:
+	case 149:
+	case 157:
+		sec_offset = IEEE80211_HT_PARAM_CHA_SEC_ABOVE;
+		break;
+	case 40:
+	case 48:
+	case 56:
+	case 64:
+	case 104:
+	case 112:
+	case 120:
+	case 128:
+	case 136:
+	case 144:
+	case 153:
+	case 161:
+		sec_offset = IEEE80211_HT_PARAM_CHA_SEC_BELOW;
+		break;
+	case 165:
+	default:
+		sec_offset = IEEE80211_HT_PARAM_CHA_SEC_NONE;
+		break;
+	}
+
+	return sec_offset;
+}
diff --git a/drivers/net/wireless/mwifiex/11n.h b/drivers/net/wireless/mwifiex/11n.h
index 40b007a00f4..0b73fa08f5d 100644
--- a/drivers/net/wireless/mwifiex/11n.h
+++ b/drivers/net/wireless/mwifiex/11n.h
@@ -63,6 +63,7 @@ int mwifiex_cmd_amsdu_aggr_ctrl(struct host_cmd_ds_command *cmd,
 				int cmd_action,
 				struct mwifiex_ds_11n_amsdu_aggr_ctrl *aa_ctrl);
 void mwifiex_del_tx_ba_stream_tbl_by_ra(struct mwifiex_private *priv, u8 *ra);
+u8 mwifiex_get_sec_chan_offset(int chan);
 
 static inline u8
 mwifiex_is_station_ampdu_allowed(struct mwifiex_private *priv,
@@ -199,7 +200,7 @@ static inline int mwifiex_is_sta_11n_enabled(struct mwifiex_private *priv,
 }
 
 static inline u8
-mwifiex_tdls_peer_11n_enabled(struct mwifiex_private *priv, u8 *ra)
+mwifiex_tdls_peer_11n_enabled(struct mwifiex_private *priv, const u8 *ra)
 {
 	struct mwifiex_sta_node *node = mwifiex_get_sta_entry(priv, ra);
 	if (node)
diff --git a/drivers/net/wireless/mwifiex/11n_aggr.c b/drivers/net/wireless/mwifiex/11n_aggr.c
index 63211707f93..fe0f66f7350 100644
--- a/drivers/net/wireless/mwifiex/11n_aggr.c
+++ b/drivers/net/wireless/mwifiex/11n_aggr.c
@@ -100,6 +100,7 @@ mwifiex_11n_form_amsdu_txpd(struct mwifiex_private *priv,
 			    struct sk_buff *skb)
 {
 	struct txpd *local_tx_pd;
+	struct mwifiex_txinfo *tx_info = MWIFIEX_SKB_TXCB(skb);
 
 	skb_push(skb, sizeof(*local_tx_pd));
 
@@ -118,6 +119,9 @@ mwifiex_11n_form_amsdu_txpd(struct mwifiex_private *priv,
 	local_tx_pd->tx_pkt_length = cpu_to_le16(skb->len -
 						 sizeof(*local_tx_pd));
 
+	if (tx_info->flags & MWIFIEX_BUF_FLAG_TDLS_PKT)
+		local_tx_pd->flags |= MWIFIEX_TXPD_FLAGS_TDLS_PACKET;
+
 	if (local_tx_pd->tx_control == 0)
 		/* TxCtrl set by user or default */
 		local_tx_pd->tx_control = cpu_to_le32(priv->pkt_tx_ctrl);
@@ -160,6 +164,7 @@ mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
 	int pad = 0, ret;
 	struct mwifiex_tx_param tx_param;
 	struct txpd *ptx_pd = NULL;
+	struct timeval tv;
 	int headroom = adapter->iface_type == MWIFIEX_USB ? 0 : INTF_HEADER_LEN;
 
 	skb_src = skb_peek(&pra_list->skb_head);
@@ -180,10 +185,17 @@ mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
 	skb_reserve(skb_aggr, headroom + sizeof(struct txpd));
 	tx_info_aggr =  MWIFIEX_SKB_TXCB(skb_aggr);
 
+	memset(tx_info_aggr, 0, sizeof(*tx_info_aggr));
 	tx_info_aggr->bss_type = tx_info_src->bss_type;
 	tx_info_aggr->bss_num = tx_info_src->bss_num;
+
+	if (tx_info_src->flags & MWIFIEX_BUF_FLAG_TDLS_PKT)
+		tx_info_aggr->flags |= MWIFIEX_BUF_FLAG_TDLS_PKT;
 	skb_aggr->priority = skb_src->priority;
 
+	do_gettimeofday(&tv);
+	skb_aggr->tstamp = timeval_to_ktime(tv);
+
 	do {
 		/* Check if AMSDU can accommodate this MSDU */
 		if (skb_tailroom(skb_aggr) < (skb_src->len + LLC_SNAP_LEN))
@@ -236,18 +248,11 @@ mwifiex_11n_aggregate_pkt(struct mwifiex_private *priv,
 		ret = adapter->if_ops.host_to_card(adapter, MWIFIEX_USB_EP_DATA,
 						   skb_aggr, NULL);
 	} else {
-		/*
-		 * Padding per MSDU will affect the length of next
-		 * packet and hence the exact length of next packet
-		 * is uncertain here.
-		 *
-		 * Also, aggregation of transmission buffer, while
-		 * downloading the data to the card, wont gain much
-		 * on the AMSDU packets as the AMSDU packets utilizes
-		 * the transmission buffer space to the maximum
-		 * (adapter->tx_buf_size).
-		 */
-		tx_param.next_pkt_len = 0;
+		if (skb_src)
+			tx_param.next_pkt_len =
+					skb_src->len + sizeof(struct txpd);
+		else
+			tx_param.next_pkt_len = 0;
 
 		ret = adapter->if_ops.host_to_card(adapter, MWIFIEX_TYPE_DATA,
 						   skb_aggr, &tx_param);
diff --git a/drivers/net/wireless/mwifiex/README b/drivers/net/wireless/mwifiex/README
index b9242c3dca4..3b55ce5690a 100644
--- a/drivers/net/wireless/mwifiex/README
+++ b/drivers/net/wireless/mwifiex/README
@@ -200,4 +200,11 @@ getlog
 
 	cat getlog
 
+fw_dump
+	This command is used to dump firmware memory into files.
+	Separate file will be created for each memory segment.
+	Usage:
+
+	cat fw_dump
+
 ===============================================================================
diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c
index 21ee27ab7b7..b511613bba2 100644
--- a/drivers/net/wireless/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/mwifiex/cfg80211.c
@@ -220,6 +220,7 @@ mwifiex_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	}
 
 	tx_info = MWIFIEX_SKB_TXCB(skb);
+	memset(tx_info, 0, sizeof(*tx_info));
 	tx_info->bss_num = priv->bss_num;
 	tx_info->bss_type = priv->bss_type;
 	tx_info->pkt_len = pkt_len;
@@ -994,7 +995,7 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
  */
 static int
 mwifiex_cfg80211_get_station(struct wiphy *wiphy, struct net_device *dev,
-			     u8 *mac, struct station_info *sinfo)
+			     const u8 *mac, struct station_info *sinfo)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 
@@ -1270,7 +1271,7 @@ static int mwifiex_cfg80211_change_beacon(struct wiphy *wiphy,
  */
 static int
 mwifiex_cfg80211_del_station(struct wiphy *wiphy, struct net_device *dev,
-			     u8 *mac)
+			     const u8 *mac)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 	struct mwifiex_sta_node *sta_node;
@@ -2629,7 +2630,7 @@ static int mwifiex_cfg80211_set_coalesce(struct wiphy *wiphy,
  */
 static int
 mwifiex_cfg80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
-			   u8 *peer, u8 action_code, u8 dialog_token,
+			   const u8 *peer, u8 action_code, u8 dialog_token,
 			   u16 status_code, u32 peer_capability,
 			   const u8 *extra_ies, size_t extra_ies_len)
 {
@@ -2701,7 +2702,7 @@ mwifiex_cfg80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
 
 static int
 mwifiex_cfg80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
-			   u8 *peer, enum nl80211_tdls_operation action)
+			   const u8 *peer, enum nl80211_tdls_operation action)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 
@@ -2748,9 +2749,8 @@ mwifiex_cfg80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int
-mwifiex_cfg80211_add_station(struct wiphy *wiphy,
-			     struct net_device *dev,
-			     u8 *mac, struct station_parameters *params)
+mwifiex_cfg80211_add_station(struct wiphy *wiphy, struct net_device *dev,
+			     const u8 *mac, struct station_parameters *params)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 
@@ -2765,9 +2765,9 @@ mwifiex_cfg80211_add_station(struct wiphy *wiphy,
 }
 
 static int
-mwifiex_cfg80211_change_station(struct wiphy *wiphy,
-				struct net_device *dev,
-				u8 *mac, struct station_parameters *params)
+mwifiex_cfg80211_change_station(struct wiphy *wiphy, struct net_device *dev,
+				const u8 *mac,
+				struct station_parameters *params)
 {
 	int ret;
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
diff --git a/drivers/net/wireless/mwifiex/cmdevt.c b/drivers/net/wireless/mwifiex/cmdevt.c
index 1062c918a7b..c161141f6c3 100644
--- a/drivers/net/wireless/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/mwifiex/cmdevt.c
@@ -453,6 +453,7 @@ int mwifiex_process_event(struct mwifiex_adapter *adapter)
 
 	if (skb) {
 		rx_info = MWIFIEX_SKB_RXCB(skb);
+		memset(rx_info, 0, sizeof(*rx_info));
 		rx_info->bss_num = priv->bss_num;
 		rx_info->bss_type = priv->bss_type;
 	}
@@ -955,8 +956,6 @@ mwifiex_cmd_timeout_func(unsigned long function_context)
 			adapter->cmd_wait_q.status = -ETIMEDOUT;
 			wake_up_interruptible(&adapter->cmd_wait_q.wait);
 			mwifiex_cancel_pending_ioctl(adapter);
-			/* reset cmd_sent flag to unblock new commands */
-			adapter->cmd_sent = false;
 		}
 	}
 	if (adapter->hw_status == MWIFIEX_HW_STATUS_INITIALIZING)
diff --git a/drivers/net/wireless/mwifiex/debugfs.c b/drivers/net/wireless/mwifiex/debugfs.c
index b8a49aad12f..7b419bbcd54 100644
--- a/drivers/net/wireless/mwifiex/debugfs.c
+++ b/drivers/net/wireless/mwifiex/debugfs.c
@@ -257,6 +257,29 @@ free_and_exit:
 }
 
 /*
+ * Proc firmware dump read handler.
+ *
+ * This function is called when the 'fw_dump' file is opened for
+ * reading.
+ * This function dumps firmware memory in different files
+ * (ex. DTCM, ITCM, SQRAM etc.) based on the the segments for
+ * debugging.
+ */
+static ssize_t
+mwifiex_fw_dump_read(struct file *file, char __user *ubuf,
+		     size_t count, loff_t *ppos)
+{
+	struct mwifiex_private *priv = file->private_data;
+
+	if (!priv->adapter->if_ops.fw_dump)
+		return -EIO;
+
+	priv->adapter->if_ops.fw_dump(priv->adapter);
+
+	return 0;
+}
+
+/*
  * Proc getlog file read handler.
  *
  * This function is called when the 'getlog' file is opened for reading
@@ -699,6 +722,7 @@ static const struct file_operations mwifiex_dfs_##name##_fops = {       \
 MWIFIEX_DFS_FILE_READ_OPS(info);
 MWIFIEX_DFS_FILE_READ_OPS(debug);
 MWIFIEX_DFS_FILE_READ_OPS(getlog);
+MWIFIEX_DFS_FILE_READ_OPS(fw_dump);
 MWIFIEX_DFS_FILE_OPS(regrdwr);
 MWIFIEX_DFS_FILE_OPS(rdeeprom);
 
@@ -722,6 +746,7 @@ mwifiex_dev_debugfs_init(struct mwifiex_private *priv)
 	MWIFIEX_DFS_ADD_FILE(getlog);
 	MWIFIEX_DFS_ADD_FILE(regrdwr);
 	MWIFIEX_DFS_ADD_FILE(rdeeprom);
+	MWIFIEX_DFS_ADD_FILE(fw_dump);
 }
 
 /*
diff --git a/drivers/net/wireless/mwifiex/decl.h b/drivers/net/wireless/mwifiex/decl.h
index e7b3e16e5d3..38da6ff6f41 100644
--- a/drivers/net/wireless/mwifiex/decl.h
+++ b/drivers/net/wireless/mwifiex/decl.h
@@ -42,12 +42,12 @@
 #define MWIFIEX_MAX_TX_BASTREAM_SUPPORTED	2
 #define MWIFIEX_MAX_RX_BASTREAM_SUPPORTED	16
 
-#define MWIFIEX_STA_AMPDU_DEF_TXWINSIZE        16
-#define MWIFIEX_STA_AMPDU_DEF_RXWINSIZE        32
+#define MWIFIEX_STA_AMPDU_DEF_TXWINSIZE        64
+#define MWIFIEX_STA_AMPDU_DEF_RXWINSIZE        64
 #define MWIFIEX_UAP_AMPDU_DEF_TXWINSIZE        32
 #define MWIFIEX_UAP_AMPDU_DEF_RXWINSIZE        16
-#define MWIFIEX_11AC_STA_AMPDU_DEF_TXWINSIZE   32
-#define MWIFIEX_11AC_STA_AMPDU_DEF_RXWINSIZE   48
+#define MWIFIEX_11AC_STA_AMPDU_DEF_TXWINSIZE   64
+#define MWIFIEX_11AC_STA_AMPDU_DEF_RXWINSIZE   64
 #define MWIFIEX_11AC_UAP_AMPDU_DEF_TXWINSIZE   48
 #define MWIFIEX_11AC_UAP_AMPDU_DEF_RXWINSIZE   32
 
diff --git a/drivers/net/wireless/mwifiex/fw.h b/drivers/net/wireless/mwifiex/fw.h
index b485dc1ae5e..3175dd04834 100644
--- a/drivers/net/wireless/mwifiex/fw.h
+++ b/drivers/net/wireless/mwifiex/fw.h
@@ -169,6 +169,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 #define TLV_TYPE_GWK_CIPHER         (PROPRIETARY_TLV_BASE_ID + 146)
 #define TLV_TYPE_COALESCE_RULE      (PROPRIETARY_TLV_BASE_ID + 154)
 #define TLV_TYPE_KEY_PARAM_V2       (PROPRIETARY_TLV_BASE_ID + 156)
+#define TLV_TYPE_TDLS_IDLE_TIMEOUT  (PROPRIETARY_TLV_BASE_ID + 194)
 #define TLV_TYPE_FW_API_REV         (PROPRIETARY_TLV_BASE_ID + 199)
 
 #define MWIFIEX_TX_DATA_BUF_SIZE_2K        2048
@@ -229,6 +230,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 #define ISENABLED_40MHZ_INTOLERANT(Dot11nDevCap) (Dot11nDevCap & BIT(8))
 #define ISSUPP_RXLDPC(Dot11nDevCap) (Dot11nDevCap & BIT(22))
 #define ISSUPP_BEAMFORMING(Dot11nDevCap) (Dot11nDevCap & BIT(30))
+#define ISALLOWED_CHANWIDTH40(ht_param) (ht_param & BIT(2))
 
 /* httxcfg bitmap
  * 0		reserved
@@ -403,7 +405,7 @@ enum P2P_MODES {
 #define HS_CFG_CANCEL			0xffffffff
 #define HS_CFG_COND_DEF			0x00000000
 #define HS_CFG_GPIO_DEF			0xff
-#define HS_CFG_GAP_DEF			0
+#define HS_CFG_GAP_DEF			0xff
 #define HS_CFG_COND_BROADCAST_DATA	0x00000001
 #define HS_CFG_COND_UNICAST_DATA	0x00000002
 #define HS_CFG_COND_MAC_EVENT		0x00000004
@@ -487,6 +489,7 @@ enum P2P_MODES {
 #define EVENT_UAP_MIC_COUNTERMEASURES   0x0000004c
 #define EVENT_HOSTWAKE_STAIE		0x0000004d
 #define EVENT_CHANNEL_SWITCH_ANN        0x00000050
+#define EVENT_TDLS_GENERIC_EVENT        0x00000052
 #define EVENT_EXT_SCAN_REPORT           0x00000058
 #define EVENT_REMAIN_ON_CHAN_EXPIRED    0x0000005f
 
@@ -519,6 +522,7 @@ enum P2P_MODES {
 #define ACT_TDLS_DELETE            0x00
 #define ACT_TDLS_CREATE            0x01
 #define ACT_TDLS_CONFIG            0x02
+#define TDLS_EVENT_LINK_TEAR_DOWN  3
 
 #define MWIFIEX_FW_V15		   15
 
@@ -535,6 +539,7 @@ struct mwifiex_ie_types_data {
 #define MWIFIEX_TxPD_POWER_MGMT_NULL_PACKET 0x01
 #define MWIFIEX_TxPD_POWER_MGMT_LAST_PACKET 0x08
 #define MWIFIEX_TXPD_FLAGS_TDLS_PACKET      0x10
+#define MWIFIEX_RXPD_FLAGS_TDLS_PACKET      0x01
 
 struct txpd {
 	u8 bss_type;
@@ -577,7 +582,7 @@ struct rxpd {
 	 * [Bit 7] Reserved
 	 */
 	u8 ht_info;
-	u8 reserved;
+	u8 flags;
 } __packed;
 
 struct uap_txpd {
@@ -708,6 +713,13 @@ struct mwifiex_ie_types_vendor_param_set {
 	u8 ie[MWIFIEX_MAX_VSIE_LEN];
 };
 
+#define MWIFIEX_TDLS_IDLE_TIMEOUT	60
+
+struct mwifiex_ie_types_tdls_idle_timeout {
+	struct mwifiex_ie_types_header header;
+	__le16 value;
+} __packed;
+
 struct mwifiex_ie_types_rsn_param_set {
 	struct mwifiex_ie_types_header header;
 	u8 rsn_ie[1];
@@ -1745,6 +1757,15 @@ struct host_cmd_ds_802_11_subsc_evt {
 	__le16 events;
 } __packed;
 
+struct mwifiex_tdls_generic_event {
+	__le16 type;
+	u8 peer_mac[ETH_ALEN];
+	union {
+		__le16 reason_code;
+		__le16 reserved;
+	} u;
+} __packed;
+
 struct mwifiex_ie {
 	__le16 ie_index;
 	__le16 mgmt_subtype_mask;
diff --git a/drivers/net/wireless/mwifiex/ioctl.h b/drivers/net/wireless/mwifiex/ioctl.h
index ee494db5406..1b576722671 100644
--- a/drivers/net/wireless/mwifiex/ioctl.h
+++ b/drivers/net/wireless/mwifiex/ioctl.h
@@ -303,7 +303,7 @@ struct mwifiex_ds_ant_cfg {
 	u32 rx_ant;
 };
 
-#define MWIFIEX_NUM_OF_CMD_BUFFER	20
+#define MWIFIEX_NUM_OF_CMD_BUFFER	50
 #define MWIFIEX_SIZE_OF_CMD_BUFFER	2048
 
 enum {
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 9c771b3e991..e91cd0fa5ca 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -521,7 +521,6 @@ done:
 		release_firmware(adapter->firmware);
 		adapter->firmware = NULL;
 	}
-	complete(&adapter->fw_load);
 	if (init_failed)
 		mwifiex_free_adapter(adapter);
 	up(sem);
@@ -535,7 +534,6 @@ static int mwifiex_init_hw_fw(struct mwifiex_adapter *adapter)
 {
 	int ret;
 
-	init_completion(&adapter->fw_load);
 	ret = request_firmware_nowait(THIS_MODULE, 1, adapter->fw_name,
 				      adapter->dev, GFP_KERNEL, adapter,
 				      mwifiex_fw_dpc);
@@ -647,6 +645,7 @@ mwifiex_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	tx_info = MWIFIEX_SKB_TXCB(skb);
+	memset(tx_info, 0, sizeof(*tx_info));
 	tx_info->bss_num = priv->bss_num;
 	tx_info->bss_type = priv->bss_type;
 	tx_info->pkt_len = skb->len;
diff --git a/drivers/net/wireless/mwifiex/main.h b/drivers/net/wireless/mwifiex/main.h
index d53e1e8c946..1398afa8406 100644
--- a/drivers/net/wireless/mwifiex/main.h
+++ b/drivers/net/wireless/mwifiex/main.h
@@ -672,6 +672,7 @@ struct mwifiex_if_ops {
 	int (*init_fw_port) (struct mwifiex_adapter *);
 	int (*dnld_fw) (struct mwifiex_adapter *, struct mwifiex_fw_image *);
 	void (*card_reset) (struct mwifiex_adapter *);
+	void (*fw_dump)(struct mwifiex_adapter *);
 	int (*clean_pcie_ring) (struct mwifiex_adapter *adapter);
 };
 
@@ -787,7 +788,6 @@ struct mwifiex_adapter {
 	struct mwifiex_wait_queue cmd_wait_q;
 	u8 scan_wait_q_woken;
 	spinlock_t queue_lock;		/* lock for tx queues */
-	struct completion fw_load;
 	u8 country_code[IEEE80211_COUNTRY_STRING_LEN];
 	u16 max_mgmt_ie_index;
 	u8 scan_delay_cnt;
@@ -910,8 +910,6 @@ int mwifiex_handle_uap_rx_forward(struct mwifiex_private *priv,
 				  struct sk_buff *skb);
 int mwifiex_process_sta_event(struct mwifiex_private *);
 int mwifiex_process_uap_event(struct mwifiex_private *);
-struct mwifiex_sta_node *
-mwifiex_get_sta_entry(struct mwifiex_private *priv, u8 *mac);
 void mwifiex_delete_all_station_list(struct mwifiex_private *priv);
 void *mwifiex_process_sta_txpd(struct mwifiex_private *, struct sk_buff *skb);
 void *mwifiex_process_uap_txpd(struct mwifiex_private *, struct sk_buff *skb);
@@ -1101,7 +1099,7 @@ mwifiex_11h_get_csa_closed_channel(struct mwifiex_private *priv)
 		return 0;
 
 	/* Clear csa channel, if DFS channel move time has passed */
-	if (jiffies > priv->csa_expire_time) {
+	if (time_after(jiffies, priv->csa_expire_time)) {
 		priv->csa_chan = 0;
 		priv->csa_expire_time = 0;
 	}
@@ -1220,26 +1218,26 @@ void mwifiex_dnld_txpwr_table(struct mwifiex_private *priv);
 extern const struct ethtool_ops mwifiex_ethtool_ops;
 
 void mwifiex_del_all_sta_list(struct mwifiex_private *priv);
-void mwifiex_del_sta_entry(struct mwifiex_private *priv, u8 *mac);
+void mwifiex_del_sta_entry(struct mwifiex_private *priv, const u8 *mac);
 void
 mwifiex_set_sta_ht_cap(struct mwifiex_private *priv, const u8 *ies,
 		       int ies_len, struct mwifiex_sta_node *node);
 struct mwifiex_sta_node *
-mwifiex_add_sta_entry(struct mwifiex_private *priv, u8 *mac);
+mwifiex_add_sta_entry(struct mwifiex_private *priv, const u8 *mac);
 struct mwifiex_sta_node *
-mwifiex_get_sta_entry(struct mwifiex_private *priv, u8 *mac);
-int mwifiex_send_tdls_data_frame(struct mwifiex_private *priv, u8 *peer,
+mwifiex_get_sta_entry(struct mwifiex_private *priv, const u8 *mac);
+int mwifiex_send_tdls_data_frame(struct mwifiex_private *priv, const u8 *peer,
 				 u8 action_code, u8 dialog_token,
 				 u16 status_code, const u8 *extra_ies,
 				 size_t extra_ies_len);
-int mwifiex_send_tdls_action_frame(struct mwifiex_private *priv,
-				 u8 *peer, u8 action_code, u8 dialog_token,
-				 u16 status_code, const u8 *extra_ies,
-				 size_t extra_ies_len);
+int mwifiex_send_tdls_action_frame(struct mwifiex_private *priv, const u8 *peer,
+				   u8 action_code, u8 dialog_token,
+				   u16 status_code, const u8 *extra_ies,
+				   size_t extra_ies_len);
 void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 				       u8 *buf, int len);
-int mwifiex_tdls_oper(struct mwifiex_private *priv, u8 *peer, u8 action);
-int mwifiex_get_tdls_link_status(struct mwifiex_private *priv, u8 *mac);
+int mwifiex_tdls_oper(struct mwifiex_private *priv, const u8 *peer, u8 action);
+int mwifiex_get_tdls_link_status(struct mwifiex_private *priv, const u8 *mac);
 void mwifiex_disable_all_tdls_links(struct mwifiex_private *priv);
 bool mwifiex_is_bss_in_11ac_mode(struct mwifiex_private *priv);
 u8 mwifiex_get_center_freq_index(struct mwifiex_private *priv, u8 band,
diff --git a/drivers/net/wireless/mwifiex/pcie.c b/drivers/net/wireless/mwifiex/pcie.c
index a7e8b96b2d9..2cc9b6fca49 100644
--- a/drivers/net/wireless/mwifiex/pcie.c
+++ b/drivers/net/wireless/mwifiex/pcie.c
@@ -50,7 +50,7 @@ mwifiex_map_pci_memory(struct mwifiex_adapter *adapter, struct sk_buff *skb,
 		return -1;
 	}
 	mapping.len = size;
-	memcpy(skb->cb, &mapping, sizeof(mapping));
+	mwifiex_store_mapping(skb, &mapping);
 	return 0;
 }
 
@@ -60,7 +60,7 @@ static void mwifiex_unmap_pci_memory(struct mwifiex_adapter *adapter,
 	struct pcie_service_card *card = adapter->card;
 	struct mwifiex_dma_mapping mapping;
 
-	MWIFIEX_SKB_PACB(skb, &mapping);
+	mwifiex_get_mapping(skb, &mapping);
 	pci_unmap_single(card->dev, mapping.addr, mapping.len, flags);
 }
 
@@ -221,9 +221,6 @@ static void mwifiex_pcie_remove(struct pci_dev *pdev)
 	if (!adapter || !adapter->priv_num)
 		return;
 
-	/* In case driver is removed when asynchronous FW load is in progress */
-	wait_for_completion(&adapter->fw_load);
-
 	if (user_rmmod) {
 #ifdef CONFIG_PM_SLEEP
 		if (adapter->is_suspended)
@@ -1074,6 +1071,7 @@ static int mwifiex_pcie_send_data_complete(struct mwifiex_adapter *adapter)
  * is mapped to PCI device memory. Tx ring pointers are advanced accordingly.
  * Download ready interrupt to FW is deffered if Tx ring is not full and
  * additional payload can be accomodated.
+ * Caller must ensure tx_param parameter to this function is not NULL.
  */
 static int
 mwifiex_pcie_send_data(struct mwifiex_adapter *adapter, struct sk_buff *skb,
diff --git a/drivers/net/wireless/mwifiex/scan.c b/drivers/net/wireless/mwifiex/scan.c
index 7b3af3d29de..45c5b3450cf 100644
--- a/drivers/net/wireless/mwifiex/scan.c
+++ b/drivers/net/wireless/mwifiex/scan.c
@@ -29,9 +29,6 @@
 #define MWIFIEX_MAX_CHANNELS_PER_SPECIFIC_SCAN   14
 
 #define MWIFIEX_DEF_CHANNELS_PER_SCAN_CMD	4
-#define MWIFIEX_LIMIT_1_CHANNEL_PER_SCAN_CMD	15
-#define MWIFIEX_LIMIT_2_CHANNELS_PER_SCAN_CMD	27
-#define MWIFIEX_LIMIT_3_CHANNELS_PER_SCAN_CMD	35
 
 /* Memory needed to store a max sized Channel List TLV for a firmware scan */
 #define CHAN_TLV_MAX_SIZE  (sizeof(struct mwifiex_ie_types_header)         \
@@ -1055,20 +1052,10 @@ mwifiex_config_scan(struct mwifiex_private *priv,
 
 	/*
 	 * In associated state we will reduce the number of channels scanned per
-	 * scan command to avoid any traffic delay/loss. This number is decided
-	 * based on total number of channels to be scanned due to constraints
-	 * of command buffers.
+	 * scan command to 1 to avoid any traffic delay/loss.
 	 */
-	if (priv->media_connected) {
-		if (chan_num < MWIFIEX_LIMIT_1_CHANNEL_PER_SCAN_CMD)
+	if (priv->media_connected)
 			*max_chan_per_scan = 1;
-		else if (chan_num < MWIFIEX_LIMIT_2_CHANNELS_PER_SCAN_CMD)
-			*max_chan_per_scan = 2;
-		else if (chan_num < MWIFIEX_LIMIT_3_CHANNELS_PER_SCAN_CMD)
-			*max_chan_per_scan = 3;
-		else
-			*max_chan_per_scan = 4;
-	}
 }
 
 /*
@@ -1353,23 +1340,17 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 					      bss_entry->beacon_buf);
 			break;
 		case WLAN_EID_BSS_COEX_2040:
-			bss_entry->bcn_bss_co_2040 = current_ptr +
-				sizeof(struct ieee_types_header);
-			bss_entry->bss_co_2040_offset = (u16) (current_ptr +
-					sizeof(struct ieee_types_header) -
-						bss_entry->beacon_buf);
+			bss_entry->bcn_bss_co_2040 = current_ptr;
+			bss_entry->bss_co_2040_offset =
+				(u16) (current_ptr - bss_entry->beacon_buf);
 			break;
 		case WLAN_EID_EXT_CAPABILITY:
-			bss_entry->bcn_ext_cap = current_ptr +
-				sizeof(struct ieee_types_header);
-			bss_entry->ext_cap_offset = (u16) (current_ptr +
-					sizeof(struct ieee_types_header) -
-					bss_entry->beacon_buf);
+			bss_entry->bcn_ext_cap = current_ptr;
+			bss_entry->ext_cap_offset =
+				(u16) (current_ptr - bss_entry->beacon_buf);
 			break;
 		case WLAN_EID_OPMODE_NOTIF:
-			bss_entry->oper_mode =
-				(void *)(current_ptr +
-					 sizeof(struct ieee_types_header));
+			bss_entry->oper_mode = (void *)current_ptr;
 			bss_entry->oper_mode_offset =
 					(u16)((u8 *)bss_entry->oper_mode -
 					      bss_entry->beacon_buf);
@@ -1757,6 +1738,19 @@ mwifiex_parse_single_response_buf(struct mwifiex_private *priv, u8 **bss_info,
 	return 0;
 }
 
+static void mwifiex_complete_scan(struct mwifiex_private *priv)
+{
+	struct mwifiex_adapter *adapter = priv->adapter;
+
+	if (adapter->curr_cmd->wait_q_enabled) {
+		adapter->cmd_wait_q.status = 0;
+		if (!priv->scan_request) {
+			dev_dbg(adapter->dev, "complete internal scan\n");
+			mwifiex_complete_cmd(adapter, adapter->curr_cmd);
+		}
+	}
+}
+
 static void mwifiex_check_next_scan_command(struct mwifiex_private *priv)
 {
 	struct mwifiex_adapter *adapter = priv->adapter;
@@ -1770,16 +1764,9 @@ static void mwifiex_check_next_scan_command(struct mwifiex_private *priv)
 		adapter->scan_processing = false;
 		spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, flags);
 
-		/* Need to indicate IOCTL complete */
-		if (adapter->curr_cmd->wait_q_enabled) {
-			adapter->cmd_wait_q.status = 0;
-			if (!priv->scan_request) {
-				dev_dbg(adapter->dev,
-					"complete internal scan\n");
-				mwifiex_complete_cmd(adapter,
-						     adapter->curr_cmd);
-			}
-		}
+		if (!adapter->ext_scan)
+			mwifiex_complete_scan(priv);
+
 		if (priv->report_scan_result)
 			priv->report_scan_result = false;
 
@@ -1984,6 +1971,9 @@ int mwifiex_cmd_802_11_scan_ext(struct mwifiex_private *priv,
 int mwifiex_ret_802_11_scan_ext(struct mwifiex_private *priv)
 {
 	dev_dbg(priv->adapter->dev, "info: EXT scan returns successfully\n");
+
+	mwifiex_complete_scan(priv);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/mwifiex/sdio.c b/drivers/net/wireless/mwifiex/sdio.c
index d206f04d499..4ce3d7b3399 100644
--- a/drivers/net/wireless/mwifiex/sdio.c
+++ b/drivers/net/wireless/mwifiex/sdio.c
@@ -85,6 +85,8 @@ mwifiex_sdio_probe(struct sdio_func *func, const struct sdio_device_id *id)
 		card->supports_sdio_new_mode = data->supports_sdio_new_mode;
 		card->has_control_mask = data->has_control_mask;
 		card->tx_buf_size = data->tx_buf_size;
+		card->mp_tx_agg_buf_size = data->mp_tx_agg_buf_size;
+		card->mp_rx_agg_buf_size = data->mp_rx_agg_buf_size;
 	}
 
 	sdio_claim_host(func);
@@ -177,9 +179,6 @@ mwifiex_sdio_remove(struct sdio_func *func)
 	if (!adapter || !adapter->priv_num)
 		return;
 
-	/* In case driver is removed when asynchronous FW load is in progress */
-	wait_for_completion(&adapter->fw_load);
-
 	if (user_rmmod) {
 		if (adapter->is_suspended)
 			mwifiex_sdio_resume(adapter->dev);
@@ -1679,8 +1678,12 @@ static int mwifiex_sdio_host_to_card(struct mwifiex_adapter *adapter,
 	if (ret) {
 		if (type == MWIFIEX_TYPE_CMD)
 			adapter->cmd_sent = false;
-		if (type == MWIFIEX_TYPE_DATA)
+		if (type == MWIFIEX_TYPE_DATA) {
 			adapter->data_sent = false;
+			/* restore curr_wr_port in error cases */
+			card->curr_wr_port = port;
+			card->mp_wr_bitmap |= (u32)(1 << card->curr_wr_port);
+		}
 	} else {
 		if (type == MWIFIEX_TYPE_DATA) {
 			if (!(card->mp_wr_bitmap & (1 << card->curr_wr_port)))
@@ -1842,8 +1845,8 @@ static int mwifiex_init_sdio(struct mwifiex_adapter *adapter)
 	card->mpa_rx.len_arr = kzalloc(sizeof(*card->mpa_rx.len_arr) *
 				       card->mp_agg_pkt_limit, GFP_KERNEL);
 	ret = mwifiex_alloc_sdio_mpa_buffers(adapter,
-					     SDIO_MP_TX_AGGR_DEF_BUF_SIZE,
-					     SDIO_MP_RX_AGGR_DEF_BUF_SIZE);
+					     card->mp_tx_agg_buf_size,
+					     card->mp_rx_agg_buf_size);
 	if (ret) {
 		dev_err(adapter->dev, "failed to alloc sdio mp-a buffers\n");
 		kfree(card->mp_regs);
diff --git a/drivers/net/wireless/mwifiex/sdio.h b/drivers/net/wireless/mwifiex/sdio.h
index c71201b2e2a..6eea30b43ed 100644
--- a/drivers/net/wireless/mwifiex/sdio.h
+++ b/drivers/net/wireless/mwifiex/sdio.h
@@ -64,10 +64,8 @@
 #define UP_LD_CMD_PORT_HOST_INT_STATUS	(0x40U)
 #define DN_LD_CMD_PORT_HOST_INT_STATUS	(0x80U)
 
-#define SDIO_MP_TX_AGGR_DEF_BUF_SIZE        (8192)	/* 8K */
-
-/* Multi port RX aggregation buffer size */
-#define SDIO_MP_RX_AGGR_DEF_BUF_SIZE        (16384)	/* 16K */
+#define MWIFIEX_MP_AGGR_BUF_SIZE_16K	(16384)
+#define MWIFIEX_MP_AGGR_BUF_SIZE_32K	(32768)
 
 /* Misc. Config Register : Auto Re-enable interrupts */
 #define AUTO_RE_ENABLE_INT              BIT(4)
@@ -234,6 +232,8 @@ struct sdio_mmc_card {
 	bool supports_sdio_new_mode;
 	bool has_control_mask;
 	u16 tx_buf_size;
+	u32 mp_tx_agg_buf_size;
+	u32 mp_rx_agg_buf_size;
 
 	u32 mp_rd_bitmap;
 	u32 mp_wr_bitmap;
@@ -258,6 +258,8 @@ struct mwifiex_sdio_device {
 	bool supports_sdio_new_mode;
 	bool has_control_mask;
 	u16 tx_buf_size;
+	u32 mp_tx_agg_buf_size;
+	u32 mp_rx_agg_buf_size;
 };
 
 static const struct mwifiex_sdio_card_reg mwifiex_reg_sd87xx = {
@@ -315,6 +317,8 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8786 = {
 	.supports_sdio_new_mode = false,
 	.has_control_mask = true,
 	.tx_buf_size = MWIFIEX_TX_DATA_BUF_SIZE_2K,
+	.mp_tx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_16K,
+	.mp_rx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_16K,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8787 = {
@@ -325,6 +329,8 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8787 = {
 	.supports_sdio_new_mode = false,
 	.has_control_mask = true,
 	.tx_buf_size = MWIFIEX_TX_DATA_BUF_SIZE_2K,
+	.mp_tx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_16K,
+	.mp_rx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_16K,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8797 = {
@@ -335,6 +341,8 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8797 = {
 	.supports_sdio_new_mode = false,
 	.has_control_mask = true,
 	.tx_buf_size = MWIFIEX_TX_DATA_BUF_SIZE_2K,
+	.mp_tx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_16K,
+	.mp_rx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_16K,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8897 = {
@@ -345,6 +353,8 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8897 = {
 	.supports_sdio_new_mode = true,
 	.has_control_mask = false,
 	.tx_buf_size = MWIFIEX_TX_DATA_BUF_SIZE_4K,
+	.mp_tx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_32K,
+	.mp_rx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_32K,
 };
 
 /*
diff --git a/drivers/net/wireless/mwifiex/sta_cmd.c b/drivers/net/wireless/mwifiex/sta_cmd.c
index e3cac1495cc..88202ce0c13 100644
--- a/drivers/net/wireless/mwifiex/sta_cmd.c
+++ b/drivers/net/wireless/mwifiex/sta_cmd.c
@@ -1546,6 +1546,7 @@ mwifiex_cmd_tdls_oper(struct mwifiex_private *priv,
 	struct mwifiex_ie_types_extcap *extcap;
 	struct mwifiex_ie_types_vhtcap *vht_capab;
 	struct mwifiex_ie_types_aid *aid;
+	struct mwifiex_ie_types_tdls_idle_timeout *timeout;
 	u8 *pos, qos_info;
 	u16 config_len = 0;
 	struct station_parameters *params = priv->sta_params;
@@ -1643,6 +1644,12 @@ mwifiex_cmd_tdls_oper(struct mwifiex_private *priv,
 			config_len += sizeof(struct mwifiex_ie_types_aid);
 		}
 
+		timeout = (void *)(pos + config_len);
+		timeout->header.type = cpu_to_le16(TLV_TYPE_TDLS_IDLE_TIMEOUT);
+		timeout->header.len = cpu_to_le16(sizeof(timeout->value));
+		timeout->value = cpu_to_le16(MWIFIEX_TDLS_IDLE_TIMEOUT);
+		config_len += sizeof(struct mwifiex_ie_types_tdls_idle_timeout);
+
 		break;
 	default:
 		dev_err(priv->adapter->dev, "Unknown TDLS operation\n");
diff --git a/drivers/net/wireless/mwifiex/sta_cmdresp.c b/drivers/net/wireless/mwifiex/sta_cmdresp.c
index bfebb0144df..577f2979ed8 100644
--- a/drivers/net/wireless/mwifiex/sta_cmdresp.c
+++ b/drivers/net/wireless/mwifiex/sta_cmdresp.c
@@ -865,14 +865,20 @@ static int mwifiex_ret_tdls_oper(struct mwifiex_private *priv,
 
 	switch (action) {
 	case ACT_TDLS_DELETE:
-		if (reason)
-			dev_err(priv->adapter->dev,
-				"TDLS link delete for %pM failed: reason %d\n",
-				cmd_tdls_oper->peer_mac, reason);
-		else
+		if (reason) {
+			if (!node || reason == TDLS_ERR_LINK_NONEXISTENT)
+				dev_dbg(priv->adapter->dev,
+					"TDLS link delete for %pM failed: reason %d\n",
+					cmd_tdls_oper->peer_mac, reason);
+			else
+				dev_err(priv->adapter->dev,
+					"TDLS link delete for %pM failed: reason %d\n",
+					cmd_tdls_oper->peer_mac, reason);
+		} else {
 			dev_dbg(priv->adapter->dev,
-				"TDLS link config for %pM successful\n",
+				"TDLS link delete for %pM successful\n",
 				cmd_tdls_oper->peer_mac);
+		}
 		break;
 	case ACT_TDLS_CREATE:
 		if (reason) {
diff --git a/drivers/net/wireless/mwifiex/sta_event.c b/drivers/net/wireless/mwifiex/sta_event.c
index 368450cc56c..f6395ef11a7 100644
--- a/drivers/net/wireless/mwifiex/sta_event.c
+++ b/drivers/net/wireless/mwifiex/sta_event.c
@@ -134,6 +134,46 @@ mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code)
 		netif_carrier_off(priv->netdev);
 }
 
+static int mwifiex_parse_tdls_event(struct mwifiex_private *priv,
+				    struct sk_buff *event_skb)
+{
+	int ret = 0;
+	struct mwifiex_adapter *adapter = priv->adapter;
+	struct mwifiex_sta_node *sta_ptr;
+	struct mwifiex_tdls_generic_event *tdls_evt =
+			(void *)event_skb->data + sizeof(adapter->event_cause);
+
+	/* reserved 2 bytes are not mandatory in tdls event */
+	if (event_skb->len < (sizeof(struct mwifiex_tdls_generic_event) -
+			      sizeof(u16) - sizeof(adapter->event_cause))) {
+		dev_err(adapter->dev, "Invalid event length!\n");
+		return -1;
+	}
+
+	sta_ptr = mwifiex_get_sta_entry(priv, tdls_evt->peer_mac);
+	if (!sta_ptr) {
+		dev_err(adapter->dev, "cannot get sta entry!\n");
+		return -1;
+	}
+
+	switch (le16_to_cpu(tdls_evt->type)) {
+	case TDLS_EVENT_LINK_TEAR_DOWN:
+		cfg80211_tdls_oper_request(priv->netdev,
+					   tdls_evt->peer_mac,
+					   NL80211_TDLS_TEARDOWN,
+					   le16_to_cpu(tdls_evt->u.reason_code),
+					   GFP_KERNEL);
+		ret = mwifiex_tdls_oper(priv, tdls_evt->peer_mac,
+					MWIFIEX_TDLS_DISABLE_LINK);
+		queue_work(adapter->workqueue, &adapter->main_work);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 /*
  * This function handles events generated by firmware.
  *
@@ -459,6 +499,10 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 			false);
 		break;
 
+	case EVENT_TDLS_GENERIC_EVENT:
+		ret = mwifiex_parse_tdls_event(priv, adapter->event_skb);
+		break;
+
 	default:
 		dev_dbg(adapter->dev, "event: unknown event id: %#x\n",
 			eventcause);
diff --git a/drivers/net/wireless/mwifiex/sta_rx.c b/drivers/net/wireless/mwifiex/sta_rx.c
index ed26387eccf..8b639d7fe6d 100644
--- a/drivers/net/wireless/mwifiex/sta_rx.c
+++ b/drivers/net/wireless/mwifiex/sta_rx.c
@@ -183,6 +183,7 @@ int mwifiex_process_sta_rx_packet(struct mwifiex_private *priv,
 	struct rx_packet_hdr *rx_pkt_hdr;
 	u8 ta[ETH_ALEN];
 	u16 rx_pkt_type, rx_pkt_offset, rx_pkt_length, seq_num;
+	struct mwifiex_sta_node *sta_ptr;
 
 	local_rx_pd = (struct rxpd *) (skb->data);
 	rx_pkt_type = le16_to_cpu(local_rx_pd->rx_pkt_type);
@@ -213,14 +214,25 @@ int mwifiex_process_sta_rx_packet(struct mwifiex_private *priv,
 	 * If the packet is not an unicast packet then send the packet
 	 * directly to os. Don't pass thru rx reordering
 	 */
-	if (!IS_11N_ENABLED(priv) ||
+	if ((!IS_11N_ENABLED(priv) &&
+	     !(ISSUPP_TDLS_ENABLED(priv->adapter->fw_cap_info) &&
+	       !(local_rx_pd->flags & MWIFIEX_RXPD_FLAGS_TDLS_PACKET))) ||
 	    !ether_addr_equal_unaligned(priv->curr_addr, rx_pkt_hdr->eth803_hdr.h_dest)) {
 		mwifiex_process_rx_packet(priv, skb);
 		return ret;
 	}
 
-	if (mwifiex_queuing_ra_based(priv)) {
+	if (mwifiex_queuing_ra_based(priv) ||
+	    (ISSUPP_TDLS_ENABLED(priv->adapter->fw_cap_info) &&
+	     local_rx_pd->flags & MWIFIEX_RXPD_FLAGS_TDLS_PACKET)) {
 		memcpy(ta, rx_pkt_hdr->eth803_hdr.h_source, ETH_ALEN);
+		if (local_rx_pd->flags & MWIFIEX_RXPD_FLAGS_TDLS_PACKET &&
+		    local_rx_pd->priority < MAX_NUM_TID) {
+			sta_ptr = mwifiex_get_sta_entry(priv, ta);
+			if (sta_ptr)
+				sta_ptr->rx_seq[local_rx_pd->priority] =
+					      le16_to_cpu(local_rx_pd->seq_num);
+		}
 	} else {
 		if (rx_pkt_type != PKT_TYPE_BAR)
 			priv->rx_seq[local_rx_pd->priority] = seq_num;
diff --git a/drivers/net/wireless/mwifiex/sta_tx.c b/drivers/net/wireless/mwifiex/sta_tx.c
index 1236a5de7bc..70eb863c724 100644
--- a/drivers/net/wireless/mwifiex/sta_tx.c
+++ b/drivers/net/wireless/mwifiex/sta_tx.c
@@ -128,6 +128,7 @@ int mwifiex_send_null_packet(struct mwifiex_private *priv, u8 flags)
 {
 	struct mwifiex_adapter *adapter = priv->adapter;
 	struct txpd *local_tx_pd;
+	struct mwifiex_tx_param tx_param;
 /* sizeof(struct txpd) + Interface specific header */
 #define NULL_PACKET_HDR 64
 	u32 data_len = NULL_PACKET_HDR;
@@ -149,6 +150,7 @@ int mwifiex_send_null_packet(struct mwifiex_private *priv, u8 flags)
 		return -1;
 
 	tx_info = MWIFIEX_SKB_TXCB(skb);
+	memset(tx_info, 0, sizeof(*tx_info));
 	tx_info->bss_num = priv->bss_num;
 	tx_info->bss_type = priv->bss_type;
 	tx_info->pkt_len = data_len - (sizeof(struct txpd) + INTF_HEADER_LEN);
@@ -168,8 +170,9 @@ int mwifiex_send_null_packet(struct mwifiex_private *priv, u8 flags)
 						   skb, NULL);
 	} else {
 		skb_push(skb, INTF_HEADER_LEN);
+		tx_param.next_pkt_len = 0;
 		ret = adapter->if_ops.host_to_card(adapter, MWIFIEX_TYPE_DATA,
-						   skb, NULL);
+						   skb, &tx_param);
 	}
 	switch (ret) {
 	case -EBUSY:
diff --git a/drivers/net/wireless/mwifiex/tdls.c b/drivers/net/wireless/mwifiex/tdls.c
index 97662a1ba58..0e88364e0c6 100644
--- a/drivers/net/wireless/mwifiex/tdls.c
+++ b/drivers/net/wireless/mwifiex/tdls.c
@@ -25,8 +25,8 @@
 #define TDLS_RESP_FIX_LEN     8
 #define TDLS_CONFIRM_FIX_LEN  6
 
-static void
-mwifiex_restore_tdls_packets(struct mwifiex_private *priv, u8 *mac, u8 status)
+static void mwifiex_restore_tdls_packets(struct mwifiex_private *priv,
+					 const u8 *mac, u8 status)
 {
 	struct mwifiex_ra_list_tbl *ra_list;
 	struct list_head *tid_list;
@@ -84,7 +84,8 @@ mwifiex_restore_tdls_packets(struct mwifiex_private *priv, u8 *mac, u8 status)
 	return;
 }
 
-static void mwifiex_hold_tdls_packets(struct mwifiex_private *priv, u8 *mac)
+static void mwifiex_hold_tdls_packets(struct mwifiex_private *priv,
+				      const u8 *mac)
 {
 	struct mwifiex_ra_list_tbl *ra_list;
 	struct list_head *ra_list_head;
@@ -185,8 +186,50 @@ static int mwifiex_tdls_add_vht_capab(struct mwifiex_private *priv,
 	return 0;
 }
 
+static int
+mwifiex_tdls_add_ht_oper(struct mwifiex_private *priv, const u8 *mac,
+			 u8 vht_enabled, struct sk_buff *skb)
+{
+	struct ieee80211_ht_operation *ht_oper;
+	struct mwifiex_sta_node *sta_ptr;
+	struct mwifiex_bssdescriptor *bss_desc =
+					&priv->curr_bss_params.bss_descriptor;
+	u8 *pos;
+
+	sta_ptr = mwifiex_get_sta_entry(priv, mac);
+	if (unlikely(!sta_ptr)) {
+		dev_warn(priv->adapter->dev,
+			 "TDLS peer station not found in list\n");
+		return -1;
+	}
+
+	pos = (void *)skb_put(skb, sizeof(struct ieee80211_ht_operation) + 2);
+	*pos++ = WLAN_EID_HT_OPERATION;
+	*pos++ = sizeof(struct ieee80211_ht_operation);
+	ht_oper = (void *)pos;
+
+	ht_oper->primary_chan = bss_desc->channel;
+
+	/* follow AP's channel bandwidth */
+	if (ISSUPP_CHANWIDTH40(priv->adapter->hw_dot_11n_dev_cap) &&
+	    bss_desc->bcn_ht_cap &&
+	    ISALLOWED_CHANWIDTH40(bss_desc->bcn_ht_oper->ht_param))
+		ht_oper->ht_param = bss_desc->bcn_ht_oper->ht_param;
+
+	if (vht_enabled) {
+		ht_oper->ht_param =
+			  mwifiex_get_sec_chan_offset(bss_desc->channel);
+		ht_oper->ht_param |= BIT(2);
+	}
+
+	memcpy(&sta_ptr->tdls_cap.ht_oper, ht_oper,
+	       sizeof(struct ieee80211_ht_operation));
+
+	return 0;
+}
+
 static int mwifiex_tdls_add_vht_oper(struct mwifiex_private *priv,
-				     u8 *mac, struct sk_buff *skb)
+				     const u8 *mac, struct sk_buff *skb)
 {
 	struct mwifiex_bssdescriptor *bss_desc;
 	struct ieee80211_vht_operation *vht_oper;
@@ -325,8 +368,9 @@ static void mwifiex_tdls_add_qos_capab(struct sk_buff *skb)
 }
 
 static int mwifiex_prep_tdls_encap_data(struct mwifiex_private *priv,
-			     u8 *peer, u8 action_code, u8 dialog_token,
-			     u16 status_code, struct sk_buff *skb)
+					const u8 *peer, u8 action_code,
+					u8 dialog_token,
+					u16 status_code, struct sk_buff *skb)
 {
 	struct ieee80211_tdls_data *tf;
 	int ret;
@@ -428,6 +472,17 @@ static int mwifiex_prep_tdls_encap_data(struct mwifiex_private *priv,
 				dev_kfree_skb_any(skb);
 				return ret;
 			}
+			ret = mwifiex_tdls_add_ht_oper(priv, peer, 1, skb);
+			if (ret) {
+				dev_kfree_skb_any(skb);
+				return ret;
+			}
+		} else {
+			ret = mwifiex_tdls_add_ht_oper(priv, peer, 0, skb);
+			if (ret) {
+				dev_kfree_skb_any(skb);
+				return ret;
+			}
 		}
 		break;
 
@@ -453,7 +508,8 @@ static int mwifiex_prep_tdls_encap_data(struct mwifiex_private *priv,
 }
 
 static void
-mwifiex_tdls_add_link_ie(struct sk_buff *skb, u8 *src_addr, u8 *peer, u8 *bssid)
+mwifiex_tdls_add_link_ie(struct sk_buff *skb, const u8 *src_addr,
+			 const u8 *peer, const u8 *bssid)
 {
 	struct ieee80211_tdls_lnkie *lnkid;
 
@@ -467,8 +523,8 @@ mwifiex_tdls_add_link_ie(struct sk_buff *skb, u8 *src_addr, u8 *peer, u8 *bssid)
 	memcpy(lnkid->resp_sta, peer, ETH_ALEN);
 }
 
-int mwifiex_send_tdls_data_frame(struct mwifiex_private *priv,
-				 u8 *peer, u8 action_code, u8 dialog_token,
+int mwifiex_send_tdls_data_frame(struct mwifiex_private *priv, const u8 *peer,
+				 u8 action_code, u8 dialog_token,
 				 u16 status_code, const u8 *extra_ies,
 				 size_t extra_ies_len)
 {
@@ -549,6 +605,7 @@ int mwifiex_send_tdls_data_frame(struct mwifiex_private *priv,
 	}
 
 	tx_info = MWIFIEX_SKB_TXCB(skb);
+	memset(tx_info, 0, sizeof(*tx_info));
 	tx_info->bss_num = priv->bss_num;
 	tx_info->bss_type = priv->bss_type;
 
@@ -560,7 +617,8 @@ int mwifiex_send_tdls_data_frame(struct mwifiex_private *priv,
 }
 
 static int
-mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv, u8 *peer,
+mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv,
+				    const u8 *peer,
 				    u8 action_code, u8 dialog_token,
 				    u16 status_code, struct sk_buff *skb)
 {
@@ -638,10 +696,10 @@ mwifiex_construct_tdls_action_frame(struct mwifiex_private *priv, u8 *peer,
 	return 0;
 }
 
-int mwifiex_send_tdls_action_frame(struct mwifiex_private *priv,
-				 u8 *peer, u8 action_code, u8 dialog_token,
-				 u16 status_code, const u8 *extra_ies,
-				 size_t extra_ies_len)
+int mwifiex_send_tdls_action_frame(struct mwifiex_private *priv, const u8 *peer,
+				   u8 action_code, u8 dialog_token,
+				   u16 status_code, const u8 *extra_ies,
+				   size_t extra_ies_len)
 {
 	struct sk_buff *skb;
 	struct mwifiex_txinfo *tx_info;
@@ -703,6 +761,7 @@ int mwifiex_send_tdls_action_frame(struct mwifiex_private *priv,
 	skb->priority = MWIFIEX_PRIO_VI;
 
 	tx_info = MWIFIEX_SKB_TXCB(skb);
+	memset(tx_info, 0, sizeof(*tx_info));
 	tx_info->bss_num = priv->bss_num;
 	tx_info->bss_type = priv->bss_type;
 	tx_info->flags |= MWIFIEX_BUF_FLAG_TDLS_PKT;
@@ -848,7 +907,7 @@ void mwifiex_process_tdls_action_frame(struct mwifiex_private *priv,
 }
 
 static int
-mwifiex_tdls_process_config_link(struct mwifiex_private *priv, u8 *peer)
+mwifiex_tdls_process_config_link(struct mwifiex_private *priv, const u8 *peer)
 {
 	struct mwifiex_sta_node *sta_ptr;
 	struct mwifiex_ds_tdls_oper tdls_oper;
@@ -869,7 +928,7 @@ mwifiex_tdls_process_config_link(struct mwifiex_private *priv, u8 *peer)
 }
 
 static int
-mwifiex_tdls_process_create_link(struct mwifiex_private *priv, u8 *peer)
+mwifiex_tdls_process_create_link(struct mwifiex_private *priv, const u8 *peer)
 {
 	struct mwifiex_sta_node *sta_ptr;
 	struct mwifiex_ds_tdls_oper tdls_oper;
@@ -896,7 +955,7 @@ mwifiex_tdls_process_create_link(struct mwifiex_private *priv, u8 *peer)
 }
 
 static int
-mwifiex_tdls_process_disable_link(struct mwifiex_private *priv, u8 *peer)
+mwifiex_tdls_process_disable_link(struct mwifiex_private *priv, const u8 *peer)
 {
 	struct mwifiex_sta_node *sta_ptr;
 	struct mwifiex_ds_tdls_oper tdls_oper;
@@ -925,7 +984,7 @@ mwifiex_tdls_process_disable_link(struct mwifiex_private *priv, u8 *peer)
 }
 
 static int
-mwifiex_tdls_process_enable_link(struct mwifiex_private *priv, u8 *peer)
+mwifiex_tdls_process_enable_link(struct mwifiex_private *priv, const u8 *peer)
 {
 	struct mwifiex_sta_node *sta_ptr;
 	struct ieee80211_mcs_info mcs;
@@ -982,7 +1041,7 @@ mwifiex_tdls_process_enable_link(struct mwifiex_private *priv, u8 *peer)
 	return 0;
 }
 
-int mwifiex_tdls_oper(struct mwifiex_private *priv, u8 *peer, u8 action)
+int mwifiex_tdls_oper(struct mwifiex_private *priv, const u8 *peer, u8 action)
 {
 	switch (action) {
 	case MWIFIEX_TDLS_ENABLE_LINK:
@@ -997,7 +1056,7 @@ int mwifiex_tdls_oper(struct mwifiex_private *priv, u8 *peer, u8 action)
 	return 0;
 }
 
-int mwifiex_get_tdls_link_status(struct mwifiex_private *priv, u8 *mac)
+int mwifiex_get_tdls_link_status(struct mwifiex_private *priv, const u8 *mac)
 {
 	struct mwifiex_sta_node *sta_ptr;
 
diff --git a/drivers/net/wireless/mwifiex/txrx.c b/drivers/net/wireless/mwifiex/txrx.c
index 37f26afd431..fd7e5b9b458 100644
--- a/drivers/net/wireless/mwifiex/txrx.c
+++ b/drivers/net/wireless/mwifiex/txrx.c
@@ -55,6 +55,7 @@ int mwifiex_handle_rx_packet(struct mwifiex_adapter *adapter,
 		return -1;
 	}
 
+	memset(rx_info, 0, sizeof(*rx_info));
 	rx_info->bss_num = priv->bss_num;
 	rx_info->bss_type = priv->bss_type;
 
diff --git a/drivers/net/wireless/mwifiex/uap_cmd.c b/drivers/net/wireless/mwifiex/uap_cmd.c
index 9be6544bdde..32643555dd2 100644
--- a/drivers/net/wireless/mwifiex/uap_cmd.c
+++ b/drivers/net/wireless/mwifiex/uap_cmd.c
@@ -175,17 +175,19 @@ mwifiex_set_ht_params(struct mwifiex_private *priv,
 		switch (GET_RXSTBC(cap_info)) {
 		case MWIFIEX_RX_STBC1:
 			/* HT_CAP 1X1 mode */
-			memset(&bss_cfg->ht_cap.mcs, 0xff, 1);
+			bss_cfg->ht_cap.mcs.rx_mask[0] = 0xff;
 			break;
 		case MWIFIEX_RX_STBC12:	/* fall through */
 		case MWIFIEX_RX_STBC123:
 			/* HT_CAP 2X2 mode */
-			memset(&bss_cfg->ht_cap.mcs, 0xff, 2);
+			bss_cfg->ht_cap.mcs.rx_mask[0] = 0xff;
+			bss_cfg->ht_cap.mcs.rx_mask[1] = 0xff;
 			break;
 		default:
 			dev_warn(priv->adapter->dev,
 				 "Unsupported RX-STBC, default to 2x2\n");
-			memset(&bss_cfg->ht_cap.mcs, 0xff, 2);
+			bss_cfg->ht_cap.mcs.rx_mask[0] = 0xff;
+			bss_cfg->ht_cap.mcs.rx_mask[1] = 0xff;
 			break;
 		}
 		priv->ap_11n_enabled = 1;
diff --git a/drivers/net/wireless/mwifiex/uap_txrx.c b/drivers/net/wireless/mwifiex/uap_txrx.c
index 9a56bc61cb1..b0601b91cc4 100644
--- a/drivers/net/wireless/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/mwifiex/uap_txrx.c
@@ -175,6 +175,7 @@ static void mwifiex_uap_queue_bridged_pkt(struct mwifiex_private *priv,
 	}
 
 	tx_info = MWIFIEX_SKB_TXCB(skb);
+	memset(tx_info, 0, sizeof(*tx_info));
 	tx_info->bss_num = priv->bss_num;
 	tx_info->bss_type = priv->bss_type;
 	tx_info->flags |= MWIFIEX_BUF_FLAG_BRIDGED_PKT;
diff --git a/drivers/net/wireless/mwifiex/usb.c b/drivers/net/wireless/mwifiex/usb.c
index edbe4aff00d..a8ce8130cfa 100644
--- a/drivers/net/wireless/mwifiex/usb.c
+++ b/drivers/net/wireless/mwifiex/usb.c
@@ -22,9 +22,9 @@
 
 #define USB_VERSION	"1.0"
 
+static u8 user_rmmod;
 static struct mwifiex_if_ops usb_ops;
 static struct semaphore add_remove_card_sem;
-static struct usb_card_rec *usb_card;
 
 static struct usb_device_id mwifiex_usb_table[] = {
 	/* 8797 */
@@ -532,28 +532,38 @@ static int mwifiex_usb_resume(struct usb_interface *intf)
 static void mwifiex_usb_disconnect(struct usb_interface *intf)
 {
 	struct usb_card_rec *card = usb_get_intfdata(intf);
+	struct mwifiex_adapter *adapter;
 
-	if (!card) {
-		pr_err("%s: card is NULL\n", __func__);
+	if (!card || !card->adapter) {
+		pr_err("%s: card or card->adapter is NULL\n", __func__);
 		return;
 	}
 
-	mwifiex_usb_free(card);
+	adapter = card->adapter;
+	if (!adapter->priv_num)
+		return;
 
-	if (card->adapter) {
-		struct mwifiex_adapter *adapter = card->adapter;
+	if (user_rmmod) {
+#ifdef CONFIG_PM
+		if (adapter->is_suspended)
+			mwifiex_usb_resume(intf);
+#endif
 
-		if (!adapter->priv_num)
-			return;
+		mwifiex_deauthenticate_all(adapter);
 
-		dev_dbg(adapter->dev, "%s: removing card\n", __func__);
-		mwifiex_remove_card(adapter, &add_remove_card_sem);
+		mwifiex_init_shutdown_fw(mwifiex_get_priv(adapter,
+							  MWIFIEX_BSS_ROLE_ANY),
+					 MWIFIEX_FUNC_SHUTDOWN);
 	}
 
+	mwifiex_usb_free(card);
+
+	dev_dbg(adapter->dev, "%s: removing card\n", __func__);
+	mwifiex_remove_card(adapter, &add_remove_card_sem);
+
 	usb_set_intfdata(intf, NULL);
 	usb_put_dev(interface_to_usbdev(intf));
 	kfree(card);
-	usb_card = NULL;
 
 	return;
 }
@@ -565,6 +575,7 @@ static struct usb_driver mwifiex_usb_driver = {
 	.id_table = mwifiex_usb_table,
 	.suspend = mwifiex_usb_suspend,
 	.resume = mwifiex_usb_resume,
+	.soft_unbind = 1,
 };
 
 static int mwifiex_usb_tx_init(struct mwifiex_adapter *adapter)
@@ -762,7 +773,6 @@ static int mwifiex_register_dev(struct mwifiex_adapter *adapter)
 
 	card->adapter = adapter;
 	adapter->dev = &card->udev->dev;
-	usb_card = card;
 
 	switch (le16_to_cpu(card->udev->descriptor.idProduct)) {
 	case USB8897_PID_1:
@@ -1025,25 +1035,8 @@ static void mwifiex_usb_cleanup_module(void)
 	if (!down_interruptible(&add_remove_card_sem))
 		up(&add_remove_card_sem);
 
-	if (usb_card && usb_card->adapter) {
-		struct mwifiex_adapter *adapter = usb_card->adapter;
-
-		/* In case driver is removed when asynchronous FW downloading is
-		 * in progress
-		 */
-		wait_for_completion(&adapter->fw_load);
-
-#ifdef CONFIG_PM
-		if (adapter->is_suspended)
-			mwifiex_usb_resume(usb_card->intf);
-#endif
-
-		mwifiex_deauthenticate_all(adapter);
-
-		mwifiex_init_shutdown_fw(mwifiex_get_priv(adapter,
-							  MWIFIEX_BSS_ROLE_ANY),
-					 MWIFIEX_FUNC_SHUTDOWN);
-	}
+	/* set the flag as user is removing this module */
+	user_rmmod = 1;
 
 	usb_deregister(&mwifiex_usb_driver);
 }
diff --git a/drivers/net/wireless/mwifiex/util.c b/drivers/net/wireless/mwifiex/util.c
index c3824e37f3f..6da5abf52e6 100644
--- a/drivers/net/wireless/mwifiex/util.c
+++ b/drivers/net/wireless/mwifiex/util.c
@@ -259,7 +259,7 @@ int mwifiex_complete_cmd(struct mwifiex_adapter *adapter,
  * NULL is returned if station entry is not found in associated STA list.
  */
 struct mwifiex_sta_node *
-mwifiex_get_sta_entry(struct mwifiex_private *priv, u8 *mac)
+mwifiex_get_sta_entry(struct mwifiex_private *priv, const u8 *mac)
 {
 	struct mwifiex_sta_node *node;
 
@@ -280,7 +280,7 @@ mwifiex_get_sta_entry(struct mwifiex_private *priv, u8 *mac)
  * If received mac address is NULL, NULL is returned.
  */
 struct mwifiex_sta_node *
-mwifiex_add_sta_entry(struct mwifiex_private *priv, u8 *mac)
+mwifiex_add_sta_entry(struct mwifiex_private *priv, const u8 *mac)
 {
 	struct mwifiex_sta_node *node;
 	unsigned long flags;
@@ -332,7 +332,7 @@ mwifiex_set_sta_ht_cap(struct mwifiex_private *priv, const u8 *ies,
 }
 
 /* This function will delete a station entry from station list */
-void mwifiex_del_sta_entry(struct mwifiex_private *priv, u8 *mac)
+void mwifiex_del_sta_entry(struct mwifiex_private *priv, const u8 *mac)
 {
 	struct mwifiex_sta_node *node;
 	unsigned long flags;
diff --git a/drivers/net/wireless/mwifiex/util.h b/drivers/net/wireless/mwifiex/util.h
index ddae5702139..caadb3737b9 100644
--- a/drivers/net/wireless/mwifiex/util.h
+++ b/drivers/net/wireless/mwifiex/util.h
@@ -20,32 +20,55 @@
 #ifndef _MWIFIEX_UTIL_H_
 #define _MWIFIEX_UTIL_H_
 
+struct mwifiex_dma_mapping {
+	dma_addr_t addr;
+	size_t len;
+};
+
+struct mwifiex_cb {
+	struct mwifiex_dma_mapping dma_mapping;
+	union {
+		struct mwifiex_rxinfo rx_info;
+		struct mwifiex_txinfo tx_info;
+	};
+};
+
 static inline struct mwifiex_rxinfo *MWIFIEX_SKB_RXCB(struct sk_buff *skb)
 {
-	return (struct mwifiex_rxinfo *)(skb->cb + sizeof(dma_addr_t));
+	struct mwifiex_cb *cb = (struct mwifiex_cb *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(struct mwifiex_cb) > sizeof(skb->cb));
+	return &cb->rx_info;
 }
 
 static inline struct mwifiex_txinfo *MWIFIEX_SKB_TXCB(struct sk_buff *skb)
 {
-	return (struct mwifiex_txinfo *)(skb->cb + sizeof(dma_addr_t));
+	struct mwifiex_cb *cb = (struct mwifiex_cb *)skb->cb;
+
+	return &cb->tx_info;
 }
 
-struct mwifiex_dma_mapping {
-	dma_addr_t addr;
-	size_t len;
-};
+static inline void mwifiex_store_mapping(struct sk_buff *skb,
+					 struct mwifiex_dma_mapping *mapping)
+{
+	struct mwifiex_cb *cb = (struct mwifiex_cb *)skb->cb;
+
+	memcpy(&cb->dma_mapping, mapping, sizeof(*mapping));
+}
 
-static inline void MWIFIEX_SKB_PACB(struct sk_buff *skb,
-					struct mwifiex_dma_mapping *mapping)
+static inline void mwifiex_get_mapping(struct sk_buff *skb,
+				       struct mwifiex_dma_mapping *mapping)
 {
-	memcpy(mapping, skb->cb, sizeof(*mapping));
+	struct mwifiex_cb *cb = (struct mwifiex_cb *)skb->cb;
+
+	memcpy(mapping, &cb->dma_mapping, sizeof(*mapping));
 }
 
 static inline dma_addr_t MWIFIEX_SKB_DMA_ADDR(struct sk_buff *skb)
 {
 	struct mwifiex_dma_mapping mapping;
 
-	MWIFIEX_SKB_PACB(skb, &mapping);
+	mwifiex_get_mapping(skb, &mapping);
 
 	return mapping.addr;
 }
diff --git a/drivers/net/wireless/mwifiex/wmm.c b/drivers/net/wireless/mwifiex/wmm.c
index 0a7cc742aed..d3671d009f6 100644
--- a/drivers/net/wireless/mwifiex/wmm.c
+++ b/drivers/net/wireless/mwifiex/wmm.c
@@ -92,7 +92,7 @@ mwifiex_wmm_ac_debug_print(const struct ieee_types_wmm_ac_parameters *ac_param)
  * The function also initializes the list with the provided RA.
  */
 static struct mwifiex_ra_list_tbl *
-mwifiex_wmm_allocate_ralist_node(struct mwifiex_adapter *adapter, u8 *ra)
+mwifiex_wmm_allocate_ralist_node(struct mwifiex_adapter *adapter, const u8 *ra)
 {
 	struct mwifiex_ra_list_tbl *ra_list;
 
@@ -139,8 +139,7 @@ static u8 mwifiex_get_random_ba_threshold(void)
  * This function allocates and adds a RA list for all TIDs
  * with the given RA.
  */
-void
-mwifiex_ralist_add(struct mwifiex_private *priv, u8 *ra)
+void mwifiex_ralist_add(struct mwifiex_private *priv, const u8 *ra)
 {
 	int i;
 	struct mwifiex_ra_list_tbl *ra_list;
@@ -164,6 +163,7 @@ mwifiex_ralist_add(struct mwifiex_private *priv, u8 *ra)
 		if (!mwifiex_queuing_ra_based(priv)) {
 			if (mwifiex_get_tdls_link_status(priv, ra) ==
 			    TDLS_SETUP_COMPLETE) {
+				ra_list->tdls_link = true;
 				ra_list->is_11n_enabled =
 					mwifiex_tdls_peer_11n_enabled(priv, ra);
 			} else {
@@ -426,15 +426,6 @@ mwifiex_wmm_init(struct mwifiex_adapter *adapter)
 							priv->tos_to_tid_inv[i];
 		}
 
-		priv->aggr_prio_tbl[6].amsdu
-					= priv->aggr_prio_tbl[6].ampdu_ap
-					= priv->aggr_prio_tbl[6].ampdu_user
-					= BA_STREAM_NOT_ALLOWED;
-
-		priv->aggr_prio_tbl[7].amsdu = priv->aggr_prio_tbl[7].ampdu_ap
-					= priv->aggr_prio_tbl[7].ampdu_user
-					= BA_STREAM_NOT_ALLOWED;
-
 		mwifiex_set_ba_params(priv);
 		mwifiex_reset_11n_rx_seq_num(priv);
 
@@ -575,7 +566,7 @@ mwifiex_clean_txrx(struct mwifiex_private *priv)
  */
 static struct mwifiex_ra_list_tbl *
 mwifiex_wmm_get_ralist_node(struct mwifiex_private *priv, u8 tid,
-			    u8 *ra_addr)
+			    const u8 *ra_addr)
 {
 	struct mwifiex_ra_list_tbl *ra_list;
 
@@ -596,7 +587,8 @@ mwifiex_wmm_get_ralist_node(struct mwifiex_private *priv, u8 tid,
  * retrieved.
  */
 struct mwifiex_ra_list_tbl *
-mwifiex_wmm_get_queue_raptr(struct mwifiex_private *priv, u8 tid, u8 *ra_addr)
+mwifiex_wmm_get_queue_raptr(struct mwifiex_private *priv, u8 tid,
+			    const u8 *ra_addr)
 {
 	struct mwifiex_ra_list_tbl *ra_list;
 
@@ -657,7 +649,7 @@ mwifiex_wmm_add_buf_txqueue(struct mwifiex_private *priv,
 		if (ntohs(eth_hdr->h_proto) == ETH_P_TDLS)
 			dev_dbg(adapter->dev,
 				"TDLS setup packet for %pM. Don't block\n", ra);
-		else
+		else if (memcmp(priv->cfg_bssid, ra, ETH_ALEN))
 			tdls_status = mwifiex_get_tdls_link_status(priv, ra);
 	}
 
diff --git a/drivers/net/wireless/mwifiex/wmm.h b/drivers/net/wireless/mwifiex/wmm.h
index 83e42083ebf..eca56e371a5 100644
--- a/drivers/net/wireless/mwifiex/wmm.h
+++ b/drivers/net/wireless/mwifiex/wmm.h
@@ -99,7 +99,7 @@ mwifiex_wmm_is_ra_list_empty(struct list_head *ra_list_hhead)
 
 void mwifiex_wmm_add_buf_txqueue(struct mwifiex_private *priv,
 				 struct sk_buff *skb);
-void mwifiex_ralist_add(struct mwifiex_private *priv, u8 *ra);
+void mwifiex_ralist_add(struct mwifiex_private *priv, const u8 *ra);
 void mwifiex_rotate_priolists(struct mwifiex_private *priv,
 			      struct mwifiex_ra_list_tbl *ra, int tid);
 
@@ -123,7 +123,8 @@ void mwifiex_wmm_setup_ac_downgrade(struct mwifiex_private *priv);
 int mwifiex_ret_wmm_get_status(struct mwifiex_private *priv,
 			       const struct host_cmd_ds_command *resp);
 struct mwifiex_ra_list_tbl *
-mwifiex_wmm_get_queue_raptr(struct mwifiex_private *priv, u8 tid, u8 *ra_addr);
+mwifiex_wmm_get_queue_raptr(struct mwifiex_private *priv, u8 tid,
+			    const u8 *ra_addr);
 u8 mwifiex_wmm_downgrade_tid(struct mwifiex_private *priv, u32 tid);
 
 #endif /* !_MWIFIEX_WMM_H_ */
diff --git a/drivers/net/wireless/orinoco/hw.c b/drivers/net/wireless/orinoco/hw.c
index 49300d04efd..e27e32851f1 100644
--- a/drivers/net/wireless/orinoco/hw.c
+++ b/drivers/net/wireless/orinoco/hw.c
@@ -988,8 +988,8 @@ int __orinoco_hw_setup_enc(struct orinoco_private *priv)
  * tsc must be NULL or up to 8 bytes
  */
 int __orinoco_hw_set_tkip_key(struct orinoco_private *priv, int key_idx,
-			      int set_tx, u8 *key, u8 *rsc, size_t rsc_len,
-			      u8 *tsc, size_t tsc_len)
+			      int set_tx, const u8 *key, const u8 *rsc,
+			      size_t rsc_len, const u8 *tsc, size_t tsc_len)
 {
 	struct {
 		__le16 idx;
diff --git a/drivers/net/wireless/orinoco/hw.h b/drivers/net/wireless/orinoco/hw.h
index 8f6831f4e32..466d1ede76f 100644
--- a/drivers/net/wireless/orinoco/hw.h
+++ b/drivers/net/wireless/orinoco/hw.h
@@ -38,8 +38,8 @@ int __orinoco_hw_set_wap(struct orinoco_private *priv);
 int __orinoco_hw_setup_wepkeys(struct orinoco_private *priv);
 int __orinoco_hw_setup_enc(struct orinoco_private *priv);
 int __orinoco_hw_set_tkip_key(struct orinoco_private *priv, int key_idx,
-			      int set_tx, u8 *key, u8 *rsc, size_t rsc_len,
-			      u8 *tsc, size_t tsc_len);
+			      int set_tx, const u8 *key, const u8 *rsc,
+			      size_t rsc_len, const u8 *tsc, size_t tsc_len);
 int orinoco_clear_tkip_key(struct orinoco_private *priv, int key_idx);
 int __orinoco_hw_set_multicast_list(struct orinoco_private *priv,
 				    struct net_device *dev,
diff --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c
index 3ac71339d04..c90939ced0e 100644
--- a/drivers/net/wireless/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/orinoco/orinoco_usb.c
@@ -1673,7 +1673,7 @@ static int ezusb_probe(struct usb_interface *interface,
 		firmware.code = fw_entry->data;
 	}
 	if (firmware.size && firmware.code) {
-		if (ezusb_firmware_download(upriv, &firmware))
+		if (ezusb_firmware_download(upriv, &firmware) < 0)
 			goto error;
 	} else {
 		err("No firmware to download");
diff --git a/drivers/net/wireless/orinoco/wext.c b/drivers/net/wireless/orinoco/wext.c
index b7a867b50b9..6abdaf0aa05 100644
--- a/drivers/net/wireless/orinoco/wext.c
+++ b/drivers/net/wireless/orinoco/wext.c
@@ -52,9 +52,9 @@ static int orinoco_set_key(struct orinoco_private *priv, int index,
 	priv->keys[index].seq_len = seq_len;
 
 	if (key_len)
-		memcpy(priv->keys[index].key, key, key_len);
+		memcpy((void *)priv->keys[index].key, key, key_len);
 	if (seq_len)
-		memcpy(priv->keys[index].seq, seq, seq_len);
+		memcpy((void *)priv->keys[index].seq, seq, seq_len);
 
 	switch (alg) {
 	case ORINOCO_ALG_TKIP:
diff --git a/drivers/net/wireless/p54/main.c b/drivers/net/wireless/p54/main.c
index eede90b63f8..7be3a483964 100644
--- a/drivers/net/wireless/p54/main.c
+++ b/drivers/net/wireless/p54/main.c
@@ -669,7 +669,8 @@ static unsigned int p54_flush_count(struct p54_common *priv)
 	return total;
 }
 
-static void p54_flush(struct ieee80211_hw *dev, u32 queues, bool drop)
+static void p54_flush(struct ieee80211_hw *dev, struct ieee80211_vif *vif,
+		      u32 queues, bool drop)
 {
 	struct p54_common *priv = dev->priv;
 	unsigned int total, i;
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index cbf0a589d32..8330fa33e50 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -343,7 +343,7 @@ static void ray_detach(struct pcmcia_device *link)
 	ray_release(link);
 
 	local = netdev_priv(dev);
-	del_timer(&local->timer);
+	del_timer_sync(&local->timer);
 
 	if (link->priv) {
 		unregister_netdev(dev);
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 39d22a15434..d2a9a08210b 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -517,7 +517,7 @@ static int rndis_set_default_key(struct wiphy *wiphy, struct net_device *netdev,
 				 u8 key_index, bool unicast, bool multicast);
 
 static int rndis_get_station(struct wiphy *wiphy, struct net_device *dev,
-					u8 *mac, struct station_info *sinfo);
+			     const u8 *mac, struct station_info *sinfo);
 
 static int rndis_dump_station(struct wiphy *wiphy, struct net_device *dev,
 			       int idx, u8 *mac, struct station_info *sinfo);
@@ -2490,7 +2490,7 @@ static void rndis_fill_station_info(struct usbnet *usbdev,
 }
 
 static int rndis_get_station(struct wiphy *wiphy, struct net_device *dev,
-					u8 *mac, struct station_info *sinfo)
+			     const u8 *mac, struct station_info *sinfo)
 {
 	struct rndis_wlan_private *priv = wiphy_priv(wiphy);
 	struct usbnet *usbdev = priv->usbdev;
diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index 84164747ace..54aaeb09deb 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -656,6 +656,7 @@ static int rsi_mac80211_ampdu_action(struct ieee80211_hw *hw,
 	case IEEE80211_AMPDU_TX_START:
 		common->vif_info[ii].seq_start = seq_no;
 		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		status = 0;
 		break;
 
 	case IEEE80211_AMPDU_TX_STOP_CONT:
diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
index 1b28cda6ca8..2eefbf159bc 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
@@ -1083,7 +1083,7 @@ void rsi_inform_bss_status(struct rsi_common *common,
 {
 	if (status) {
 		rsi_hal_send_sta_notify_frame(common,
-					      NL80211_IFTYPE_STATION,
+					      RSI_IFTYPE_STATION,
 					      STA_CONNECTED,
 					      bssid,
 					      qos_enable,
@@ -1092,7 +1092,7 @@ void rsi_inform_bss_status(struct rsi_common *common,
 			rsi_send_auto_rate_request(common);
 	} else {
 		rsi_hal_send_sta_notify_frame(common,
-					      NL80211_IFTYPE_STATION,
+					      RSI_IFTYPE_STATION,
 					      STA_DISCONNECTED,
 					      bssid,
 					      qos_enable,
diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c
index 2e39d38d6a9..46e7af446f0 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c
@@ -285,7 +285,6 @@ static void rsi_reset_card(struct sdio_func *pfunction)
 		if (err) {
 			rsi_dbg(ERR_ZONE, "%s: CCCR speed reg read failed: %d\n",
 				__func__, err);
-			card->state &= ~MMC_STATE_HIGHSPEED;
 		} else {
 			err = rsi_cmd52writebyte(card,
 						 SDIO_CCCR_SPEED,
@@ -296,14 +295,13 @@ static void rsi_reset_card(struct sdio_func *pfunction)
 					__func__, err);
 				return;
 			}
-			mmc_card_set_highspeed(card);
 			host->ios.timing = MMC_TIMING_SD_HS;
 			host->ops->set_ios(host, &host->ios);
 		}
 	}
 
 	/* Set clock */
-	if (mmc_card_highspeed(card))
+	if (mmc_card_hs(card))
 		clock = 50000000;
 	else
 		clock = card->cis.max_dtr;
diff --git a/drivers/net/wireless/rsi/rsi_common.h b/drivers/net/wireless/rsi/rsi_common.h
index f2f70784d4a..d3fbe33d232 100644
--- a/drivers/net/wireless/rsi/rsi_common.h
+++ b/drivers/net/wireless/rsi/rsi_common.h
@@ -63,7 +63,7 @@ static inline int rsi_create_kthread(struct rsi_common *common,
 				     u8 *name)
 {
 	init_completion(&thread->completion);
-	thread->task = kthread_run(func_ptr, common, name);
+	thread->task = kthread_run(func_ptr, common, "%s", name);
 	if (IS_ERR(thread->task))
 		return (int)PTR_ERR(thread->task);
 
diff --git a/drivers/net/wireless/rsi/rsi_mgmt.h b/drivers/net/wireless/rsi/rsi_mgmt.h
index ac67c4ad63c..225215a3b8b 100644
--- a/drivers/net/wireless/rsi/rsi_mgmt.h
+++ b/drivers/net/wireless/rsi/rsi_mgmt.h
@@ -73,6 +73,7 @@
 #define RX_BA_INDICATION                1
 #define RSI_TBL_SZ                      40
 #define MAX_RETRIES                     8
+#define RSI_IFTYPE_STATION		 0
 
 #define STD_RATE_MCS7                   0x07
 #define STD_RATE_MCS6                   0x06
diff --git a/drivers/net/wireless/rt2x00/rt2500pci.c b/drivers/net/wireless/rt2x00/rt2500pci.c
index 2f1cd929c6f..a511cccc9f0 100644
--- a/drivers/net/wireless/rt2x00/rt2500pci.c
+++ b/drivers/net/wireless/rt2x00/rt2500pci.c
@@ -1681,8 +1681,13 @@ static int rt2500pci_init_eeprom(struct rt2x00_dev *rt2x00dev)
 	/*
 	 * Detect if this device has an hardware controlled radio.
 	 */
-	if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO))
+	if (rt2x00_get_field16(eeprom, EEPROM_ANTENNA_HARDWARE_RADIO)) {
 		__set_bit(CAPABILITY_HW_BUTTON, &rt2x00dev->cap_flags);
+		/*
+		 * On this device RFKILL initialized during probe does not work.
+		 */
+		__set_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags);
+	}
 
 	/*
 	 * Check if the BBP tuning should be enabled.
diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c
index 41d4a8167dc..c17fcf27272 100644
--- a/drivers/net/wireless/rt2x00/rt2800lib.c
+++ b/drivers/net/wireless/rt2x00/rt2800lib.c
@@ -1005,10 +1005,9 @@ void rt2800_write_beacon(struct queue_entry *entry, struct txentry_desc *txdesc)
 				   entry->skb->len + padding_len);
 
 	/*
-	 * Enable beaconing again.
+	 * Restore beaconing state.
 	 */
-	rt2x00_set_field32(&reg, BCN_TIME_CFG_BEACON_GEN, 1);
-	rt2800_register_write(rt2x00dev, BCN_TIME_CFG, reg);
+	rt2800_register_write(rt2x00dev, BCN_TIME_CFG, orig_reg);
 
 	/*
 	 * Clean up beacon skb.
@@ -1039,13 +1038,14 @@ static inline void rt2800_clear_beacon_register(struct rt2x00_dev *rt2x00dev,
 void rt2800_clear_beacon(struct queue_entry *entry)
 {
 	struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev;
-	u32 reg;
+	u32 orig_reg, reg;
 
 	/*
 	 * Disable beaconing while we are reloading the beacon data,
 	 * otherwise we might be sending out invalid data.
 	 */
-	rt2800_register_read(rt2x00dev, BCN_TIME_CFG, &reg);
+	rt2800_register_read(rt2x00dev, BCN_TIME_CFG, &orig_reg);
+	reg = orig_reg;
 	rt2x00_set_field32(&reg, BCN_TIME_CFG_BEACON_GEN, 0);
 	rt2800_register_write(rt2x00dev, BCN_TIME_CFG, reg);
 
@@ -1055,10 +1055,9 @@ void rt2800_clear_beacon(struct queue_entry *entry)
 	rt2800_clear_beacon_register(rt2x00dev, entry->entry_idx);
 
 	/*
-	 * Enabled beaconing again.
+	 * Restore beaconing state.
 	 */
-	rt2x00_set_field32(&reg, BCN_TIME_CFG_BEACON_GEN, 1);
-	rt2800_register_write(rt2x00dev, BCN_TIME_CFG, reg);
+	rt2800_register_write(rt2x00dev, BCN_TIME_CFG, orig_reg);
 }
 EXPORT_SYMBOL_GPL(rt2800_clear_beacon);
 
diff --git a/drivers/net/wireless/rt2x00/rt2800usb.c b/drivers/net/wireless/rt2x00/rt2800usb.c
index a49c3d73ea2..832006b5aab 100644
--- a/drivers/net/wireless/rt2x00/rt2800usb.c
+++ b/drivers/net/wireless/rt2x00/rt2800usb.c
@@ -229,6 +229,31 @@ static enum hrtimer_restart rt2800usb_tx_sta_fifo_timeout(struct hrtimer *timer)
 /*
  * Firmware functions
  */
+static int rt2800usb_autorun_detect(struct rt2x00_dev *rt2x00dev)
+{
+	__le32 *reg;
+	u32 fw_mode;
+
+	reg = kmalloc(sizeof(*reg), GFP_KERNEL);
+	if (reg == NULL)
+		return -ENOMEM;
+	/* cannot use rt2x00usb_register_read here as it uses different
+	 * mode (MULTI_READ vs. DEVICE_MODE) and does not pass the
+	 * magic value USB_MODE_AUTORUN (0x11) to the device, thus the
+	 * returned value would be invalid.
+	 */
+	rt2x00usb_vendor_request(rt2x00dev, USB_DEVICE_MODE,
+				 USB_VENDOR_REQUEST_IN, 0, USB_MODE_AUTORUN,
+				 reg, sizeof(*reg), REGISTER_TIMEOUT_FIRMWARE);
+	fw_mode = le32_to_cpu(*reg);
+	kfree(reg);
+
+	if ((fw_mode & 0x00000003) == 2)
+		return 1;
+
+	return 0;
+}
+
 static char *rt2800usb_get_firmware_name(struct rt2x00_dev *rt2x00dev)
 {
 	return FIRMWARE_RT2870;
@@ -240,6 +265,7 @@ static int rt2800usb_write_firmware(struct rt2x00_dev *rt2x00dev,
 	int status;
 	u32 offset;
 	u32 length;
+	int retval;
 
 	/*
 	 * Check which section of the firmware we need.
@@ -257,8 +283,16 @@ static int rt2800usb_write_firmware(struct rt2x00_dev *rt2x00dev,
 	/*
 	 * Write firmware to device.
 	 */
-	rt2x00usb_register_multiwrite(rt2x00dev, FIRMWARE_IMAGE_BASE,
-				      data + offset, length);
+	retval = rt2800usb_autorun_detect(rt2x00dev);
+	if (retval < 0)
+		return retval;
+	if (retval) {
+		rt2x00_info(rt2x00dev,
+			    "Firmware loading not required - NIC in AutoRun mode\n");
+	} else {
+		rt2x00usb_register_multiwrite(rt2x00dev, FIRMWARE_IMAGE_BASE,
+					      data + offset, length);
+	}
 
 	rt2x00usb_register_write(rt2x00dev, H2M_MAILBOX_CID, ~0);
 	rt2x00usb_register_write(rt2x00dev, H2M_MAILBOX_STATUS, ~0);
@@ -735,11 +769,26 @@ static void rt2800usb_fill_rxdone(struct queue_entry *entry,
 /*
  * Device probe functions.
  */
+static int rt2800usb_efuse_detect(struct rt2x00_dev *rt2x00dev)
+{
+	int retval;
+
+	retval = rt2800usb_autorun_detect(rt2x00dev);
+	if (retval < 0)
+		return retval;
+	if (retval)
+		return 1;
+	return rt2800_efuse_detect(rt2x00dev);
+}
+
 static int rt2800usb_read_eeprom(struct rt2x00_dev *rt2x00dev)
 {
 	int retval;
 
-	if (rt2800_efuse_detect(rt2x00dev))
+	retval = rt2800usb_efuse_detect(rt2x00dev);
+	if (retval < 0)
+		return retval;
+	if (retval)
 		retval = rt2800_read_eeprom_efuse(rt2x00dev);
 	else
 		retval = rt2x00usb_eeprom_read(rt2x00dev, rt2x00dev->eeprom,
diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h
index e3b885d8f7d..d13f25cd70d 100644
--- a/drivers/net/wireless/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/rt2x00/rt2x00.h
@@ -693,6 +693,7 @@ enum rt2x00_capability_flags {
 	REQUIRE_SW_SEQNO,
 	REQUIRE_HT_TX_DESC,
 	REQUIRE_PS_AUTOWAKE,
+	REQUIRE_DELAYED_RFKILL,
 
 	/*
 	 * Capabilities
@@ -1448,7 +1449,8 @@ int rt2x00mac_conf_tx(struct ieee80211_hw *hw,
 		      struct ieee80211_vif *vif, u16 queue,
 		      const struct ieee80211_tx_queue_params *params);
 void rt2x00mac_rfkill_poll(struct ieee80211_hw *hw);
-void rt2x00mac_flush(struct ieee80211_hw *hw, u32 queues, bool drop);
+void rt2x00mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		     u32 queues, bool drop);
 int rt2x00mac_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant);
 int rt2x00mac_get_antenna(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant);
 void rt2x00mac_get_ringparam(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c
index 2bde6729f5e..4fa43a2eeb7 100644
--- a/drivers/net/wireless/rt2x00/rt2x00dev.c
+++ b/drivers/net/wireless/rt2x00/rt2x00dev.c
@@ -1126,9 +1126,10 @@ static void rt2x00lib_uninitialize(struct rt2x00_dev *rt2x00dev)
 		return;
 
 	/*
-	 * Unregister extra components.
+	 * Stop rfkill polling.
 	 */
-	rt2x00rfkill_unregister(rt2x00dev);
+	if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_unregister(rt2x00dev);
 
 	/*
 	 * Allow the HW to uninitialize.
@@ -1166,6 +1167,12 @@ static int rt2x00lib_initialize(struct rt2x00_dev *rt2x00dev)
 
 	set_bit(DEVICE_STATE_INITIALIZED, &rt2x00dev->flags);
 
+	/*
+	 * Start rfkill polling.
+	 */
+	if (test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_register(rt2x00dev);
+
 	return 0;
 }
 
@@ -1375,7 +1382,12 @@ int rt2x00lib_probe_dev(struct rt2x00_dev *rt2x00dev)
 	rt2x00link_register(rt2x00dev);
 	rt2x00leds_register(rt2x00dev);
 	rt2x00debug_register(rt2x00dev);
-	rt2x00rfkill_register(rt2x00dev);
+
+	/*
+	 * Start rfkill polling.
+	 */
+	if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_register(rt2x00dev);
 
 	return 0;
 
@@ -1391,6 +1403,12 @@ void rt2x00lib_remove_dev(struct rt2x00_dev *rt2x00dev)
 	clear_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags);
 
 	/*
+	 * Stop rfkill polling.
+	 */
+	if (!test_bit(REQUIRE_DELAYED_RFKILL, &rt2x00dev->cap_flags))
+		rt2x00rfkill_unregister(rt2x00dev);
+
+	/*
 	 * Disable radio.
 	 */
 	rt2x00lib_disable_radio(rt2x00dev);
diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c
index a87ee9b6585..004dff9b962 100644
--- a/drivers/net/wireless/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/rt2x00/rt2x00mac.c
@@ -487,6 +487,8 @@ int rt2x00mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	crypto.cipher = rt2x00crypto_key_to_cipher(key);
 	if (crypto.cipher == CIPHER_NONE)
 		return -EOPNOTSUPP;
+	if (crypto.cipher == CIPHER_TKIP && rt2x00_is_usb(rt2x00dev))
+		return -EOPNOTSUPP;
 
 	crypto.cmd = cmd;
 
@@ -749,7 +751,8 @@ void rt2x00mac_rfkill_poll(struct ieee80211_hw *hw)
 }
 EXPORT_SYMBOL_GPL(rt2x00mac_rfkill_poll);
 
-void rt2x00mac_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+void rt2x00mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		     u32 queues, bool drop)
 {
 	struct rt2x00_dev *rt2x00dev = hw->priv;
 	struct data_queue *queue;
diff --git a/drivers/net/wireless/rt2x00/rt2x00usb.c b/drivers/net/wireless/rt2x00/rt2x00usb.c
index 10572452cc2..86c43d112a4 100644
--- a/drivers/net/wireless/rt2x00/rt2x00usb.c
+++ b/drivers/net/wireless/rt2x00/rt2x00usb.c
@@ -68,6 +68,12 @@ int rt2x00usb_vendor_request(struct rt2x00_dev *rt2x00dev,
 		}
 	}
 
+	/* If the port is powered down, we get a -EPROTO error, and this
+	 * leads to a endless loop. So just say that the device is gone.
+	 */
+	if (status == -EPROTO)
+		clear_bit(DEVICE_STATE_PRESENT, &rt2x00dev->flags);
+
 	rt2x00_err(rt2x00dev,
 		   "Vendor Request 0x%02x failed for offset 0x%04x with error %d\n",
 		   request, offset, status);
diff --git a/drivers/net/wireless/rt2x00/rt2x00usb.h b/drivers/net/wireless/rt2x00/rt2x00usb.h
index e7bcf62347d..831b65f93fe 100644
--- a/drivers/net/wireless/rt2x00/rt2x00usb.h
+++ b/drivers/net/wireless/rt2x00/rt2x00usb.h
@@ -93,6 +93,7 @@ enum rt2x00usb_mode_offset {
 	USB_MODE_SLEEP = 7,	/* RT73USB */
 	USB_MODE_FIRMWARE = 8,	/* RT73USB */
 	USB_MODE_WAKEUP = 9,	/* RT73USB */
+	USB_MODE_AUTORUN = 17, /* RT2800USB */
 };
 
 /**
diff --git a/drivers/net/wireless/rt2x00/rt61pci.c b/drivers/net/wireless/rt2x00/rt61pci.c
index 24402984ee5..9048a9cbe52 100644
--- a/drivers/net/wireless/rt2x00/rt61pci.c
+++ b/drivers/net/wireless/rt2x00/rt61pci.c
@@ -2031,13 +2031,14 @@ static void rt61pci_write_beacon(struct queue_entry *entry,
 static void rt61pci_clear_beacon(struct queue_entry *entry)
 {
 	struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev;
-	u32 reg;
+	u32 orig_reg, reg;
 
 	/*
 	 * Disable beaconing while we are reloading the beacon data,
 	 * otherwise we might be sending out invalid data.
 	 */
-	rt2x00mmio_register_read(rt2x00dev, TXRX_CSR9, &reg);
+	rt2x00mmio_register_read(rt2x00dev, TXRX_CSR9, &orig_reg);
+	reg = orig_reg;
 	rt2x00_set_field32(&reg, TXRX_CSR9_BEACON_GEN, 0);
 	rt2x00mmio_register_write(rt2x00dev, TXRX_CSR9, reg);
 
@@ -2048,10 +2049,9 @@ static void rt61pci_clear_beacon(struct queue_entry *entry)
 				  HW_BEACON_OFFSET(entry->entry_idx), 0);
 
 	/*
-	 * Enable beaconing again.
+	 * Restore global beaconing state.
 	 */
-	rt2x00_set_field32(&reg, TXRX_CSR9_BEACON_GEN, 1);
-	rt2x00mmio_register_write(rt2x00dev, TXRX_CSR9, reg);
+	rt2x00mmio_register_write(rt2x00dev, TXRX_CSR9, orig_reg);
 }
 
 /*
diff --git a/drivers/net/wireless/rt2x00/rt73usb.c b/drivers/net/wireless/rt2x00/rt73usb.c
index a140170b1eb..95724ff9c72 100644
--- a/drivers/net/wireless/rt2x00/rt73usb.c
+++ b/drivers/net/wireless/rt2x00/rt73usb.c
@@ -1597,13 +1597,14 @@ static void rt73usb_clear_beacon(struct queue_entry *entry)
 {
 	struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev;
 	unsigned int beacon_base;
-	u32 reg;
+	u32 orig_reg, reg;
 
 	/*
 	 * Disable beaconing while we are reloading the beacon data,
 	 * otherwise we might be sending out invalid data.
 	 */
-	rt2x00usb_register_read(rt2x00dev, TXRX_CSR9, &reg);
+	rt2x00usb_register_read(rt2x00dev, TXRX_CSR9, &orig_reg);
+	reg = orig_reg;
 	rt2x00_set_field32(&reg, TXRX_CSR9_BEACON_GEN, 0);
 	rt2x00usb_register_write(rt2x00dev, TXRX_CSR9, reg);
 
@@ -1614,10 +1615,9 @@ static void rt73usb_clear_beacon(struct queue_entry *entry)
 	rt2x00usb_register_write(rt2x00dev, beacon_base, 0);
 
 	/*
-	 * Enable beaconing again.
+	 * Restore beaconing state.
 	 */
-	rt2x00_set_field32(&reg, TXRX_CSR9_BEACON_GEN, 1);
-	rt2x00usb_register_write(rt2x00dev, TXRX_CSR9, reg);
+	rt2x00usb_register_write(rt2x00dev, TXRX_CSR9, orig_reg);
 }
 
 static int rt73usb_get_tx_data_len(struct queue_entry *entry)
diff --git a/drivers/net/wireless/rtl818x/rtl8180/Makefile b/drivers/net/wireless/rtl818x/rtl8180/Makefile
index 08b056db4a3..21005bd8b43 100644
--- a/drivers/net/wireless/rtl818x/rtl8180/Makefile
+++ b/drivers/net/wireless/rtl818x/rtl8180/Makefile
@@ -1,5 +1,5 @@
-rtl8180-objs		:= dev.o rtl8225.o sa2400.o max2820.o grf5101.o rtl8225se.o
+rtl818x_pci-objs	:= dev.o rtl8225.o sa2400.o max2820.o grf5101.o rtl8225se.o
 
-obj-$(CONFIG_RTL8180)	+= rtl8180.o
+obj-$(CONFIG_RTL8180)	+= rtl818x_pci.o
 
 ccflags-y += -Idrivers/net/wireless/rtl818x
diff --git a/drivers/net/wireless/rtl818x/rtl8180/dev.c b/drivers/net/wireless/rtl818x/rtl8180/dev.c
index 98d8256f037..2c1c02bafa1 100644
--- a/drivers/net/wireless/rtl818x/rtl8180/dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8180/dev.c
@@ -284,6 +284,8 @@ static void rtl8180_handle_rx(struct ieee80211_hw *dev)
 			rx_status.band = dev->conf.chandef.chan->band;
 			rx_status.mactime = tsft;
 			rx_status.flag |= RX_FLAG_MACTIME_START;
+			if (flags & RTL818X_RX_DESC_FLAG_SPLCP)
+				rx_status.flag |= RX_FLAG_SHORTPRE;
 			if (flags & RTL818X_RX_DESC_FLAG_CRC32_ERR)
 				rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 
@@ -461,18 +463,23 @@ static void rtl8180_tx(struct ieee80211_hw *dev,
 			    RTL818X_TX_DESC_FLAG_NO_ENC;
 
 	rc_flags = info->control.rates[0].flags;
+
+	/* HW will perform RTS-CTS when only RTS flags is set.
+	 * HW will perform CTS-to-self when both RTS and CTS flags are set.
+	 * RTS rate and RTS duration will be used also for CTS-to-self.
+	 */
 	if (rc_flags & IEEE80211_TX_RC_USE_RTS_CTS) {
 		tx_flags |= RTL818X_TX_DESC_FLAG_RTS;
 		tx_flags |= ieee80211_get_rts_cts_rate(dev, info)->hw_value << 19;
+		rts_duration = ieee80211_rts_duration(dev, priv->vif,
+						skb->len, info);
 	} else if (rc_flags & IEEE80211_TX_RC_USE_CTS_PROTECT) {
-		tx_flags |= RTL818X_TX_DESC_FLAG_CTS;
+		tx_flags |= RTL818X_TX_DESC_FLAG_RTS | RTL818X_TX_DESC_FLAG_CTS;
 		tx_flags |= ieee80211_get_rts_cts_rate(dev, info)->hw_value << 19;
+		rts_duration = ieee80211_ctstoself_duration(dev, priv->vif,
+						skb->len, info);
 	}
 
-	if (rc_flags & IEEE80211_TX_RC_USE_RTS_CTS)
-		rts_duration = ieee80211_rts_duration(dev, priv->vif, skb->len,
-						      info);
-
 	if (priv->chip_family == RTL818X_CHIP_FAMILY_RTL8180) {
 		unsigned int remainder;
 
@@ -683,9 +690,8 @@ static void rtl8180_int_enable(struct ieee80211_hw *dev)
 	struct rtl8180_priv *priv = dev->priv;
 
 	if (priv->chip_family == RTL818X_CHIP_FAMILY_RTL8187SE) {
-		rtl818x_iowrite32(priv, &priv->map->IMR, IMR_TMGDOK |
-			  IMR_TBDER | IMR_THPDER |
-			  IMR_THPDER | IMR_THPDOK |
+		rtl818x_iowrite32(priv, &priv->map->IMR,
+			  IMR_TBDER | IMR_TBDOK |
 			  IMR_TVODER | IMR_TVODOK |
 			  IMR_TVIDER | IMR_TVIDOK |
 			  IMR_TBEDER | IMR_TBEDOK |
@@ -911,7 +917,10 @@ static int rtl8180_init_hw(struct ieee80211_hw *dev)
 		reg32 &= 0x00ffff00;
 		reg32 |= 0xb8000054;
 		rtl818x_iowrite32(priv, &priv->map->RF_PARA, reg32);
-	}
+	} else
+		/* stop unused queus (no dma alloc) */
+		rtl818x_iowrite8(priv, &priv->map->TX_DMA_POLLING,
+			    (1<<1) | (1<<2));
 
 	priv->rf->init(dev);
 
diff --git a/drivers/net/wireless/rtl818x/rtl8187/dev.c b/drivers/net/wireless/rtl818x/rtl8187/dev.c
index 0ca17cda48f..629ad8cfa17 100644
--- a/drivers/net/wireless/rtl818x/rtl8187/dev.c
+++ b/drivers/net/wireless/rtl818x/rtl8187/dev.c
@@ -253,14 +253,21 @@ static void rtl8187_tx(struct ieee80211_hw *dev,
 	flags |= ieee80211_get_tx_rate(dev, info)->hw_value << 24;
 	if (ieee80211_has_morefrags(tx_hdr->frame_control))
 		flags |= RTL818X_TX_DESC_FLAG_MOREFRAG;
+
+	/* HW will perform RTS-CTS when only RTS flags is set.
+	 * HW will perform CTS-to-self when both RTS and CTS flags are set.
+	 * RTS rate and RTS duration will be used also for CTS-to-self.
+	 */
 	if (info->control.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) {
 		flags |= RTL818X_TX_DESC_FLAG_RTS;
 		flags |= ieee80211_get_rts_cts_rate(dev, info)->hw_value << 19;
 		rts_dur = ieee80211_rts_duration(dev, priv->vif,
 						 skb->len, info);
 	} else if (info->control.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT) {
-		flags |= RTL818X_TX_DESC_FLAG_CTS;
+		flags |= RTL818X_TX_DESC_FLAG_RTS | RTL818X_TX_DESC_FLAG_CTS;
 		flags |= ieee80211_get_rts_cts_rate(dev, info)->hw_value << 19;
+		rts_dur = ieee80211_ctstoself_duration(dev, priv->vif,
+						 skb->len, info);
 	}
 
 	if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ) {
@@ -381,6 +388,8 @@ static void rtl8187_rx_cb(struct urb *urb)
 	rx_status.freq = dev->conf.chandef.chan->center_freq;
 	rx_status.band = dev->conf.chandef.chan->band;
 	rx_status.flag |= RX_FLAG_MACTIME_START;
+	if (flags & RTL818X_RX_DESC_FLAG_SPLCP)
+		rx_status.flag |= RX_FLAG_SHORTPRE;
 	if (flags & RTL818X_RX_DESC_FLAG_CRC32_ERR)
 		rx_status.flag |= RX_FLAG_FAILED_FCS_CRC;
 	memcpy(IEEE80211_SKB_RXCB(skb), &rx_status, sizeof(rx_status));
diff --git a/drivers/net/wireless/rtl818x/rtl818x.h b/drivers/net/wireless/rtl818x/rtl818x.h
index 45ea4e1c4ab..7abef95d278 100644
--- a/drivers/net/wireless/rtl818x/rtl818x.h
+++ b/drivers/net/wireless/rtl818x/rtl818x.h
@@ -334,9 +334,9 @@ struct rtl818x_csr {
  * I don't like to introduce a ton of "reserved"..
  * They are for RTL8187SE
  */
-#define REG_ADDR1(addr)	((u8 __iomem *)priv->map + addr)
-#define REG_ADDR2(addr)	((__le16 __iomem *)priv->map + (addr >> 1))
-#define REG_ADDR4(addr)	((__le32 __iomem *)priv->map + (addr >> 2))
+#define REG_ADDR1(addr)	((u8 __iomem *)priv->map + (addr))
+#define REG_ADDR2(addr)	((__le16 __iomem *)priv->map + ((addr) >> 1))
+#define REG_ADDR4(addr)	((__le32 __iomem *)priv->map + ((addr) >> 2))
 
 #define FEMR_SE		REG_ADDR2(0x1D4)
 #define ARFR		REG_ADDR2(0x1E0)
diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c
index 4ec424f2667..b1ed6d0796f 100644
--- a/drivers/net/wireless/rtlwifi/core.c
+++ b/drivers/net/wireless/rtlwifi/core.c
@@ -1387,7 +1387,8 @@ static void rtl_op_rfkill_poll(struct ieee80211_hw *hw)
  * before switch channel or power save, or tx buffer packet
  * maybe send after offchannel or rf sleep, this may cause
  * dis-association by AP */
-static void rtl_op_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void rtl_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 u32 queues, bool drop)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
index 94cd9df9838..b14cf5a10f4 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
@@ -2515,23 +2515,3 @@ void rtl88ee_suspend(struct ieee80211_hw *hw)
 void rtl88ee_resume(struct ieee80211_hw *hw)
 {
 }
-
-/* Turn on AAP (RCR:bit 0) for promicuous mode. */
-void rtl88ee_allow_all_destaddr(struct ieee80211_hw *hw,
-				bool allow_all_da, bool write_into_reg)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-
-	if (allow_all_da) /* Set BIT0 */
-		rtlpci->receive_config |= RCR_AAP;
-	 else /* Clear BIT0 */
-		rtlpci->receive_config &= ~RCR_AAP;
-
-	if (write_into_reg)
-		rtl_write_dword(rtlpriv, REG_RCR, rtlpci->receive_config);
-
-	RT_TRACE(rtlpriv, COMP_TURBO | COMP_INIT, DBG_LOUD,
-		 "receive_config = 0x%08X, write_into_reg =%d\n",
-		 rtlpci->receive_config, write_into_reg);
-}
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.h b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.h
index b4460a41bd0..1850fde881b 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.h
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.h
@@ -61,8 +61,6 @@ void rtl8188ee_bt_reg_init(struct ieee80211_hw *hw);
 void rtl8188ee_bt_hw_init(struct ieee80211_hw *hw);
 void rtl88ee_suspend(struct ieee80211_hw *hw);
 void rtl88ee_resume(struct ieee80211_hw *hw);
-void rtl88ee_allow_all_destaddr(struct ieee80211_hw *hw,
-				bool allow_all_da, bool write_into_reg);
 void rtl88ee_fw_clk_off_timer_callback(unsigned long data);
 
 #endif
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/sw.c b/drivers/net/wireless/rtlwifi/rtl8188ee/sw.c
index 1b4101bf997..842d69349a3 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/sw.c
@@ -93,7 +93,7 @@ int rtl88e_init_sw_vars(struct ieee80211_hw *hw)
 	u8 tid;
 
 	rtl8188ee_bt_reg_init(hw);
-	rtlpci->msi_support = true;
+	rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support;
 
 	rtlpriv->dm.dm_initialgain_enable = 1;
 	rtlpriv->dm.dm_flag = 0;
@@ -255,7 +255,6 @@ static struct rtl_hal_ops rtl8188ee_hal_ops = {
 	.enable_hw_sec = rtl88ee_enable_hw_security_config,
 	.set_key = rtl88ee_set_key,
 	.init_sw_leds = rtl88ee_init_sw_leds,
-	.allow_all_destaddr = rtl88ee_allow_all_destaddr,
 	.get_bbreg = rtl88e_phy_query_bb_reg,
 	.set_bbreg = rtl88e_phy_set_bb_reg,
 	.get_rfreg = rtl88e_phy_query_rf_reg,
@@ -267,6 +266,7 @@ static struct rtl_mod_params rtl88ee_mod_params = {
 	.inactiveps = true,
 	.swctrl_lps = false,
 	.fwctrl_lps = true,
+	.msi_support = false,
 	.debug = DBG_EMERG,
 };
 
@@ -383,10 +383,12 @@ module_param_named(debug, rtl88ee_mod_params.debug, int, 0444);
 module_param_named(ips, rtl88ee_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl88ee_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl88ee_mod_params.fwctrl_lps, bool, 0444);
+module_param_named(msi, rtl88ee_mod_params.msi_support, bool, 0444);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
 MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n");
 MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n");
 MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n");
+MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 0)\n");
 MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)");
 
 static SIMPLE_DEV_PM_OPS(rtlwifi_pm_ops, rtl_pci_suspend, rtl_pci_resume);
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
index 55adf043aef..cdecb0fd4d8 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.c
@@ -2423,24 +2423,3 @@ void rtl92ce_suspend(struct ieee80211_hw *hw)
 void rtl92ce_resume(struct ieee80211_hw *hw)
 {
 }
-
-/* Turn on AAP (RCR:bit 0) for promicuous mode. */
-void rtl92ce_allow_all_destaddr(struct ieee80211_hw *hw,
-	bool allow_all_da, bool write_into_reg)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-
-	if (allow_all_da) {/* Set BIT0 */
-		rtlpci->receive_config |= RCR_AAP;
-	} else {/* Clear BIT0 */
-		rtlpci->receive_config &= ~RCR_AAP;
-	}
-
-	if (write_into_reg)
-		rtl_write_dword(rtlpriv, REG_RCR, rtlpci->receive_config);
-
-	RT_TRACE(rtlpriv, COMP_TURBO | COMP_INIT, DBG_LOUD,
-		 "receive_config=0x%08X, write_into_reg=%d\n",
-		 rtlpci->receive_config, write_into_reg);
-}
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.h b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.h
index 2d063b0c776..5533070f266 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/hw.h
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/hw.h
@@ -76,7 +76,5 @@ void rtl8192ce_bt_reg_init(struct ieee80211_hw *hw);
 void rtl8192ce_bt_hw_init(struct ieee80211_hw *hw);
 void rtl92ce_suspend(struct ieee80211_hw *hw);
 void rtl92ce_resume(struct ieee80211_hw *hw);
-void rtl92ce_allow_all_destaddr(struct ieee80211_hw *hw,
-				bool allow_all_da, bool write_into_reg);
 
 #endif
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c
index b790320d203..12f21f4073e 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/sw.c
@@ -229,7 +229,6 @@ static struct rtl_hal_ops rtl8192ce_hal_ops = {
 	.enable_hw_sec = rtl92ce_enable_hw_security_config,
 	.set_key = rtl92ce_set_key,
 	.init_sw_leds = rtl92ce_init_sw_leds,
-	.allow_all_destaddr = rtl92ce_allow_all_destaddr,
 	.get_bbreg = rtl92c_phy_query_bb_reg,
 	.set_bbreg = rtl92c_phy_set_bb_reg,
 	.set_rfreg = rtl92ce_phy_set_rf_reg,
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
index 07cb06da672..a903c2671b4 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
@@ -511,7 +511,7 @@ static int _rtl92cu_init_power_on(struct ieee80211_hw *hw)
 			pr_info("MAC auto ON okay!\n");
 			break;
 		}
-		if (pollingCount++ > 100) {
+		if (pollingCount++ > 1000) {
 			RT_TRACE(rtlpriv, COMP_INIT, DBG_EMERG,
 				 "Failed to polling REG_APS_FSMCO[APFM_ONMAC] done!\n");
 			return -ENODEV;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
index c61311084d7..361435f8608 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c
@@ -395,9 +395,6 @@ static struct usb_driver rtl8192cu_driver = {
 	/* .resume = rtl_usb_resume, */
 	/* .reset_resume = rtl8192c_resume, */
 #endif /* CONFIG_PM */
-#ifdef CONFIG_AUTOSUSPEND
-	.supports_autosuspend = 1,
-#endif
 	.disable_hub_initiated_lpm = 1,
 };
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
index 9098558d916..1c7101bcd79 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
@@ -2544,23 +2544,3 @@ void rtl92se_resume(struct ieee80211_hw *hw)
 		pci_write_config_dword(rtlpci->pdev, 0x40,
 			val & 0xffff00ff);
 }
-
-/* Turn on AAP (RCR:bit 0) for promicuous mode. */
-void rtl92se_allow_all_destaddr(struct ieee80211_hw *hw,
-				bool allow_all_da, bool write_into_reg)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-
-	if (allow_all_da) /* Set BIT0 */
-		rtlpci->receive_config |= RCR_AAP;
-	else /* Clear BIT0 */
-		rtlpci->receive_config &= ~RCR_AAP;
-
-	if (write_into_reg)
-		rtl_write_dword(rtlpriv, RCR, rtlpci->receive_config);
-
-	RT_TRACE(rtlpriv, COMP_TURBO | COMP_INIT, DBG_LOUD,
-		 "receive_config=0x%08X, write_into_reg=%d\n",
-		 rtlpci->receive_config, write_into_reg);
-}
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/hw.h b/drivers/net/wireless/rtlwifi/rtl8192se/hw.h
index da48aa8cbe6..4cacee10f31 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/hw.h
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/hw.h
@@ -74,7 +74,5 @@ void rtl92se_set_key(struct ieee80211_hw *hw,
 		     u8 enc_algo, bool is_wepkey, bool clear_all);
 void rtl92se_suspend(struct ieee80211_hw *hw);
 void rtl92se_resume(struct ieee80211_hw *hw);
-void rtl92se_allow_all_destaddr(struct ieee80211_hw *hw,
-				bool allow_all_da, bool write_into_reg);
 
 #endif
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/rtlwifi/rtl8192se/sw.c
index 2e8e6f8d2d5..1bff2a0f760 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/sw.c
@@ -290,7 +290,6 @@ static struct rtl_hal_ops rtl8192se_hal_ops = {
 	.enable_hw_sec = rtl92se_enable_hw_security_config,
 	.set_key = rtl92se_set_key,
 	.init_sw_leds = rtl92se_init_sw_leds,
-	.allow_all_destaddr = rtl92se_allow_all_destaddr,
 	.get_bbreg = rtl92s_phy_query_bb_reg,
 	.set_bbreg = rtl92s_phy_set_bb_reg,
 	.get_rfreg = rtl92s_phy_query_rf_reg,
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/hal_bt_coexist.c b/drivers/net/wireless/rtlwifi/rtl8723ae/hal_bt_coexist.c
index 48fee1be78c..5b4a714f3c8 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/hal_bt_coexist.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/hal_bt_coexist.c
@@ -32,7 +32,6 @@
 #include "dm.h"
 #include "fw.h"
 #include "../rtl8723com/fw_common.h"
-#include "../rtl8723com/fw_common.h"
 #include "phy.h"
 #include "reg.h"
 #include "hal_btc.h"
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
index 65c9e80e1f7..87f69166a7e 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
@@ -2383,24 +2383,3 @@ void rtl8723ae_suspend(struct ieee80211_hw *hw)
 void rtl8723ae_resume(struct ieee80211_hw *hw)
 {
 }
-
-/* Turn on AAP (RCR:bit 0) for promicuous mode. */
-void rtl8723ae_allow_all_destaddr(struct ieee80211_hw *hw,
-	bool allow_all_da, bool write_into_reg)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-
-	if (allow_all_da) /* Set BIT0 */
-		rtlpci->receive_config |= RCR_AAP;
-	else /* Clear BIT0 */
-		rtlpci->receive_config &= ~RCR_AAP;
-
-	if (write_into_reg)
-		rtl_write_dword(rtlpriv, REG_RCR, rtlpci->receive_config);
-
-
-	RT_TRACE(rtlpriv, COMP_TURBO | COMP_INIT, DBG_LOUD,
-		 "receive_config=0x%08X, write_into_reg=%d\n",
-		 rtlpci->receive_config, write_into_reg);
-}
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.h b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.h
index 6fa24f79b1d..d3bc39fb27a 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.h
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.h
@@ -67,7 +67,5 @@ void rtl8723ae_bt_reg_init(struct ieee80211_hw *hw);
 void rtl8723ae_bt_hw_init(struct ieee80211_hw *hw);
 void rtl8723ae_suspend(struct ieee80211_hw *hw);
 void rtl8723ae_resume(struct ieee80211_hw *hw);
-void rtl8723ae_allow_all_destaddr(struct ieee80211_hw *hw,
-				  bool allow_all_da, bool write_into_reg);
 
 #endif
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/rtlwifi/rtl8723ae/sw.c
index 1087a3bd07f..73cba1eec8c 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/sw.c
@@ -238,7 +238,6 @@ static struct rtl_hal_ops rtl8723ae_hal_ops = {
 	.enable_hw_sec = rtl8723ae_enable_hw_security_config,
 	.set_key = rtl8723ae_set_key,
 	.init_sw_leds = rtl8723ae_init_sw_leds,
-	.allow_all_destaddr = rtl8723ae_allow_all_destaddr,
 	.get_bbreg = rtl8723_phy_query_bb_reg,
 	.set_bbreg = rtl8723_phy_set_bb_reg,
 	.get_rfreg = rtl8723ae_phy_query_rf_reg,
diff --git a/drivers/net/wireless/rtlwifi/rtl8723be/hw.c b/drivers/net/wireless/rtlwifi/rtl8723be/hw.c
index 0fdf0909321..3d555495b45 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723be/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723be/hw.c
@@ -2501,23 +2501,3 @@ void rtl8723be_suspend(struct ieee80211_hw *hw)
 void rtl8723be_resume(struct ieee80211_hw *hw)
 {
 }
-
-/* Turn on AAP (RCR:bit 0) for promicuous mode. */
-void rtl8723be_allow_all_destaddr(struct ieee80211_hw *hw, bool allow_all_da,
-				  bool write_into_reg)
-{
-	struct rtl_priv *rtlpriv = rtl_priv(hw);
-	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
-
-	if (allow_all_da) /* Set BIT0 */
-		rtlpci->receive_config |= RCR_AAP;
-	else /* Clear BIT0 */
-		rtlpci->receive_config &= ~RCR_AAP;
-
-	if (write_into_reg)
-		rtl_write_dword(rtlpriv, REG_RCR, rtlpci->receive_config);
-
-	RT_TRACE(rtlpriv, COMP_TURBO | COMP_INIT, DBG_LOUD,
-		 "receive_config = 0x%08X, write_into_reg =%d\n",
-		 rtlpci->receive_config, write_into_reg);
-}
diff --git a/drivers/net/wireless/rtlwifi/rtl8723be/hw.h b/drivers/net/wireless/rtlwifi/rtl8723be/hw.h
index b7449a9b57e..64c7551af6b 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723be/hw.h
+++ b/drivers/net/wireless/rtlwifi/rtl8723be/hw.h
@@ -59,6 +59,4 @@ void rtl8723be_bt_reg_init(struct ieee80211_hw *hw);
 void rtl8723be_bt_hw_init(struct ieee80211_hw *hw);
 void rtl8723be_suspend(struct ieee80211_hw *hw);
 void rtl8723be_resume(struct ieee80211_hw *hw);
-void rtl8723be_allow_all_destaddr(struct ieee80211_hw *hw, bool allow_all_da,
-				  bool write_into_reg);
 #endif
diff --git a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c
index b4577ebc4bb..ff12bf41644 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c
@@ -92,7 +92,7 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_mac *mac = rtl_mac(rtl_priv(hw));
 
 	rtl8723be_bt_reg_init(hw);
-	rtlpci->msi_support = true;
+	rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support;
 	rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer();
 
 	rtlpriv->dm.dm_initialgain_enable = 1;
@@ -253,6 +253,7 @@ static struct rtl_mod_params rtl8723be_mod_params = {
 	.inactiveps = true,
 	.swctrl_lps = false,
 	.fwctrl_lps = true,
+	.msi_support = false,
 	.debug = DBG_EMERG,
 };
 
@@ -365,9 +366,11 @@ module_param_named(debug, rtl8723be_mod_params.debug, int, 0444);
 module_param_named(ips, rtl8723be_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl8723be_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl8723be_mod_params.fwctrl_lps, bool, 0444);
+module_param_named(msi, rtl8723be_mod_params.msi_support, bool, 0444);
 MODULE_PARM_DESC(swenc, "using hardware crypto (default 0 [hardware])\n");
 MODULE_PARM_DESC(ips, "using no link power save (default 1 is open)\n");
 MODULE_PARM_DESC(fwlps, "using linked fw control power save (default 1 is open)\n");
+MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 0)\n");
 MODULE_PARM_DESC(debug, "Set debug level (0-5) (default 0)");
 
 static SIMPLE_DEV_PM_OPS(rtlwifi_pm_ops, rtl_pci_suspend, rtl_pci_resume);
diff --git a/drivers/net/wireless/rtlwifi/rtl8723be/trx.c b/drivers/net/wireless/rtlwifi/rtl8723be/trx.c
index e0a0d8c8fed..969eaea5edd 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723be/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723be/trx.c
@@ -33,7 +33,6 @@
 #include "trx.h"
 #include "led.h"
 #include "dm.h"
-#include "phy.h"
 
 static u8 _rtl8723be_map_hwqueue_to_fwqueue(struct sk_buff *skb, u8 hw_queue)
 {
diff --git a/drivers/net/wireless/rtlwifi/wifi.h b/drivers/net/wireless/rtlwifi/wifi.h
index 6965afdf572..407a7936d36 100644
--- a/drivers/net/wireless/rtlwifi/wifi.h
+++ b/drivers/net/wireless/rtlwifi/wifi.h
@@ -1960,8 +1960,6 @@ struct rtl_hal_ops {
 			  u32 regaddr, u32 bitmask);
 	void (*set_rfreg) (struct ieee80211_hw *hw, enum radio_path rfpath,
 			   u32 regaddr, u32 bitmask, u32 data);
-	void (*allow_all_destaddr)(struct ieee80211_hw *hw,
-		bool allow_all_da, bool write_into_reg);
 	void (*linked_set_reg) (struct ieee80211_hw *hw);
 	void (*chk_switch_dmdp) (struct ieee80211_hw *hw);
 	void (*dualmac_easy_concurrent) (struct ieee80211_hw *hw);
@@ -2030,6 +2028,10 @@ struct rtl_mod_params {
 
 	/* default: 1 = using linked fw power save */
 	bool fwctrl_lps;
+
+	/* default: 0 = not using MSI interrupts mode */
+	/* submodules should set their own defalut value */
+	bool msi_support;
 };
 
 struct rtl_hal_usbint_cfg {
diff --git a/drivers/net/wireless/ti/wl1251/acx.c b/drivers/net/wireless/ti/wl1251/acx.c
index 5a4ec56c83d..5695628757e 100644
--- a/drivers/net/wireless/ti/wl1251/acx.c
+++ b/drivers/net/wireless/ti/wl1251/acx.c
@@ -2,7 +2,6 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/crc7.h>
 
 #include "wl1251.h"
 #include "reg.h"
diff --git a/drivers/net/wireless/ti/wl1251/cmd.c b/drivers/net/wireless/ti/wl1251/cmd.c
index bf1fa18b978..ede31f048ef 100644
--- a/drivers/net/wireless/ti/wl1251/cmd.c
+++ b/drivers/net/wireless/ti/wl1251/cmd.c
@@ -2,7 +2,6 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/crc7.h>
 #include <linux/etherdevice.h>
 
 #include "wl1251.h"
diff --git a/drivers/net/wireless/ti/wl1251/event.c b/drivers/net/wireless/ti/wl1251/event.c
index db010531374..c98630394a1 100644
--- a/drivers/net/wireless/ti/wl1251/event.c
+++ b/drivers/net/wireless/ti/wl1251/event.c
@@ -124,11 +124,12 @@ static int wl1251_event_process(struct wl1251 *wl, struct event_mailbox *mbox)
 			return ret;
 	}
 
-	if (wl->vif && vector & SYNCHRONIZATION_TIMEOUT_EVENT_ID) {
+	if (vector & SYNCHRONIZATION_TIMEOUT_EVENT_ID) {
 		wl1251_debug(DEBUG_EVENT, "SYNCHRONIZATION_TIMEOUT_EVENT");
 
 		/* indicate to the stack, that beacons have been lost */
-		ieee80211_beacon_loss(wl->vif);
+		if (wl->vif && wl->vif->type == NL80211_IFTYPE_STATION)
+			ieee80211_beacon_loss(wl->vif);
 	}
 
 	if (vector & REGAINED_BSS_EVENT_ID) {
diff --git a/drivers/net/wireless/ti/wl1251/main.c b/drivers/net/wireless/ti/wl1251/main.c
index 757e25784a8..4e782f18ae3 100644
--- a/drivers/net/wireless/ti/wl1251/main.c
+++ b/drivers/net/wireless/ti/wl1251/main.c
@@ -550,6 +550,34 @@ static void wl1251_op_remove_interface(struct ieee80211_hw *hw,
 	mutex_unlock(&wl->mutex);
 }
 
+static int wl1251_build_null_data(struct wl1251 *wl)
+{
+	struct sk_buff *skb = NULL;
+	int size;
+	void *ptr;
+	int ret = -ENOMEM;
+
+	if (wl->bss_type == BSS_TYPE_IBSS) {
+		size = sizeof(struct wl12xx_null_data_template);
+		ptr = NULL;
+	} else {
+		skb = ieee80211_nullfunc_get(wl->hw, wl->vif);
+		if (!skb)
+			goto out;
+		size = skb->len;
+		ptr = skb->data;
+	}
+
+	ret = wl1251_cmd_template_set(wl, CMD_NULL_DATA, ptr, size);
+
+out:
+	dev_kfree_skb(skb);
+	if (ret)
+		wl1251_warning("cmd buld null data failed: %d", ret);
+
+	return ret;
+}
+
 static int wl1251_build_qos_null_data(struct wl1251 *wl)
 {
 	struct ieee80211_qos_hdr template;
@@ -687,16 +715,6 @@ static int wl1251_op_config(struct ieee80211_hw *hw, u32 changed)
 		wl->power_level = conf->power_level;
 	}
 
-	/*
-	 * Tell stack that connection is lost because hw encryption isn't
-	 * supported in monitor mode.
-	 * This requires temporary enabling of the hw connection monitor flag
-	 */
-	if ((changed & IEEE80211_CONF_CHANGE_MONITOR) && wl->vif) {
-		wl->hw->flags |= IEEE80211_HW_CONNECTION_MONITOR;
-		ieee80211_connection_loss(wl->vif);
-	}
-
 out_sleep:
 	wl1251_ps_elp_sleep(wl);
 
@@ -1103,24 +1121,19 @@ static void wl1251_op_bss_info_changed(struct ieee80211_hw *hw,
 		wl->rssi_thold = bss_conf->cqm_rssi_thold;
 	}
 
-	if (changed & BSS_CHANGED_BSSID) {
+	if ((changed & BSS_CHANGED_BSSID) &&
+	    memcmp(wl->bssid, bss_conf->bssid, ETH_ALEN)) {
 		memcpy(wl->bssid, bss_conf->bssid, ETH_ALEN);
 
-		skb = ieee80211_nullfunc_get(wl->hw, wl->vif);
-		if (!skb)
-			goto out_sleep;
-
-		ret = wl1251_cmd_template_set(wl, CMD_NULL_DATA,
-					      skb->data, skb->len);
-		dev_kfree_skb(skb);
-		if (ret < 0)
-			goto out_sleep;
+		if (!is_zero_ether_addr(wl->bssid)) {
+			ret = wl1251_build_null_data(wl);
+			if (ret < 0)
+				goto out_sleep;
 
-		ret = wl1251_build_qos_null_data(wl);
-		if (ret < 0)
-			goto out;
+			ret = wl1251_build_qos_null_data(wl);
+			if (ret < 0)
+				goto out_sleep;
 
-		if (wl->bss_type != BSS_TYPE_IBSS) {
 			ret = wl1251_join(wl, wl->bss_type, wl->channel,
 					  wl->beacon_int, wl->dtim_period);
 			if (ret < 0)
@@ -1129,9 +1142,6 @@ static void wl1251_op_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_ASSOC) {
-		/* Disable temporary enabled hw connection monitor flag */
-		wl->hw->flags &= ~IEEE80211_HW_CONNECTION_MONITOR;
-
 		if (bss_conf->assoc) {
 			wl->beacon_int = bss_conf->beacon_int;
 
@@ -1216,8 +1226,8 @@ static void wl1251_op_bss_info_changed(struct ieee80211_hw *hw,
 		if (ret < 0)
 			goto out_sleep;
 
-		ret = wl1251_join(wl, wl->bss_type, wl->beacon_int,
-				  wl->channel, wl->dtim_period);
+		ret = wl1251_join(wl, wl->bss_type, wl->channel,
+				  wl->beacon_int, wl->dtim_period);
 
 		if (ret < 0)
 			goto out_sleep;
diff --git a/drivers/net/wireless/ti/wl1251/spi.c b/drivers/net/wireless/ti/wl1251/spi.c
index b06d36d9936..a0aa8fa7239 100644
--- a/drivers/net/wireless/ti/wl1251/spi.c
+++ b/drivers/net/wireless/ti/wl1251/spi.c
@@ -23,6 +23,7 @@
 #include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/swab.h>
 #include <linux/crc7.h>
 #include <linux/spi/spi.h>
 #include <linux/wl12xx.h>
@@ -83,47 +84,44 @@ static void wl1251_spi_reset(struct wl1251 *wl)
 
 static void wl1251_spi_wake(struct wl1251 *wl)
 {
-	u8 crc[WSPI_INIT_CMD_CRC_LEN], *cmd;
 	struct spi_transfer t;
 	struct spi_message m;
+	u8 *cmd = kzalloc(WSPI_INIT_CMD_LEN, GFP_KERNEL);
 
-	cmd = kzalloc(WSPI_INIT_CMD_LEN, GFP_KERNEL);
 	if (!cmd) {
 		wl1251_error("could not allocate cmd for spi init");
 		return;
 	}
 
-	memset(crc, 0, sizeof(crc));
 	memset(&t, 0, sizeof(t));
 	spi_message_init(&m);
 
 	/* Set WSPI_INIT_COMMAND
 	 * the data is being send from the MSB to LSB
 	 */
-	cmd[2] = 0xff;
-	cmd[3] = 0xff;
-	cmd[1] = WSPI_INIT_CMD_START | WSPI_INIT_CMD_TX;
-	cmd[0] = 0;
-	cmd[7] = 0;
-	cmd[6] |= HW_ACCESS_WSPI_INIT_CMD_MASK << 3;
-	cmd[6] |= HW_ACCESS_WSPI_FIXED_BUSY_LEN & WSPI_INIT_CMD_FIXEDBUSY_LEN;
+	cmd[0] = 0xff;
+	cmd[1] = 0xff;
+	cmd[2] = WSPI_INIT_CMD_START | WSPI_INIT_CMD_TX;
+	cmd[3] = 0;
+	cmd[4] = 0;
+	cmd[5] = HW_ACCESS_WSPI_INIT_CMD_MASK << 3;
+	cmd[5] |= HW_ACCESS_WSPI_FIXED_BUSY_LEN & WSPI_INIT_CMD_FIXEDBUSY_LEN;
+
+	cmd[6] = WSPI_INIT_CMD_IOD | WSPI_INIT_CMD_IP | WSPI_INIT_CMD_CS
+		| WSPI_INIT_CMD_WSPI | WSPI_INIT_CMD_WS;
 
 	if (HW_ACCESS_WSPI_FIXED_BUSY_LEN == 0)
-		cmd[5] |=  WSPI_INIT_CMD_DIS_FIXEDBUSY;
+		cmd[6] |= WSPI_INIT_CMD_DIS_FIXEDBUSY;
 	else
-		cmd[5] |= WSPI_INIT_CMD_EN_FIXEDBUSY;
-
-	cmd[5] |= WSPI_INIT_CMD_IOD | WSPI_INIT_CMD_IP | WSPI_INIT_CMD_CS
-		| WSPI_INIT_CMD_WSPI | WSPI_INIT_CMD_WS;
-
-	crc[0] = cmd[1];
-	crc[1] = cmd[0];
-	crc[2] = cmd[7];
-	crc[3] = cmd[6];
-	crc[4] = cmd[5];
+		cmd[6] |= WSPI_INIT_CMD_EN_FIXEDBUSY;
 
-	cmd[4] |= crc7(0, crc, WSPI_INIT_CMD_CRC_LEN) << 1;
-	cmd[4] |= WSPI_INIT_CMD_END;
+	cmd[7] = crc7_be(0, cmd+2, WSPI_INIT_CMD_CRC_LEN) | WSPI_INIT_CMD_END;
+	/*
+	 * The above is the logical order; it must actually be stored
+	 * in the buffer byte-swapped.
+	 */
+	__swab32s((u32 *)cmd);
+	__swab32s((u32 *)cmd+1);
 
 	t.tx_buf = cmd;
 	t.len = WSPI_INIT_CMD_LEN;
diff --git a/drivers/net/wireless/ti/wlcore/debugfs.h b/drivers/net/wireless/ti/wlcore/debugfs.h
index f7381dd6900..0f2cfb0d2a9 100644
--- a/drivers/net/wireless/ti/wlcore/debugfs.h
+++ b/drivers/net/wireless/ti/wlcore/debugfs.h
@@ -57,7 +57,7 @@ static const struct file_operations name## _ops = {			\
 					    wl, &name## _ops);		\
 		if (!entry || IS_ERR(entry))				\
 			goto err;					\
-	} while (0);
+	} while (0)
 
 
 #define DEBUGFS_ADD_PREFIX(prefix, name, parent)			\
@@ -66,7 +66,7 @@ static const struct file_operations name## _ops = {			\
 				    wl, &prefix## _## name## _ops);	\
 		if (!entry || IS_ERR(entry))				\
 			goto err;					\
-	} while (0);
+	} while (0)
 
 #define DEBUGFS_FWSTATS_FILE(sub, name, fmt, struct_type)		\
 static ssize_t sub## _ ##name## _read(struct file *file,		\
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index e71eae35336..3d6028e6275 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -1416,7 +1416,7 @@ void wl1271_rx_filter_free(struct wl12xx_rx_filter *filter)
 
 int wl1271_rx_filter_alloc_field(struct wl12xx_rx_filter *filter,
 				 u16 offset, u8 flags,
-				 u8 *pattern, u8 len)
+				 const u8 *pattern, u8 len)
 {
 	struct wl12xx_rx_filter_field *field;
 
@@ -5184,7 +5184,8 @@ out:
 	mutex_unlock(&wl->mutex);
 }
 
-static void wlcore_op_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void wlcore_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			    u32 queues, bool drop)
 {
 	struct wl1271 *wl = hw->priv;
 
diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c
index 29ef2492951..d3dd7bfdf3f 100644
--- a/drivers/net/wireless/ti/wlcore/sdio.c
+++ b/drivers/net/wireless/ti/wlcore/sdio.c
@@ -217,7 +217,7 @@ static struct wl1271_if_operations sdio_ops = {
 static int wl1271_probe(struct sdio_func *func,
 				  const struct sdio_device_id *id)
 {
-	struct wlcore_platdev_data *pdev_data;
+	struct wlcore_platdev_data pdev_data;
 	struct wl12xx_sdio_glue *glue;
 	struct resource res[1];
 	mmc_pm_flag_t mmcflags;
@@ -228,16 +228,13 @@ static int wl1271_probe(struct sdio_func *func,
 	if (func->num != 0x02)
 		return -ENODEV;
 
-	pdev_data = kzalloc(sizeof(*pdev_data), GFP_KERNEL);
-	if (!pdev_data)
-		goto out;
-
-	pdev_data->if_ops = &sdio_ops;
+	memset(&pdev_data, 0x00, sizeof(pdev_data));
+	pdev_data.if_ops = &sdio_ops;
 
 	glue = kzalloc(sizeof(*glue), GFP_KERNEL);
 	if (!glue) {
 		dev_err(&func->dev, "can't allocate glue\n");
-		goto out_free_pdev_data;
+		goto out;
 	}
 
 	glue->dev = &func->dev;
@@ -248,9 +245,9 @@ static int wl1271_probe(struct sdio_func *func,
 	/* Use block mode for transferring over one block size of data */
 	func->card->quirks |= MMC_QUIRK_BLKSZ_FOR_BYTE_MODE;
 
-	pdev_data->pdata = wl12xx_get_platform_data();
-	if (IS_ERR(pdev_data->pdata)) {
-		ret = PTR_ERR(pdev_data->pdata);
+	pdev_data.pdata = wl12xx_get_platform_data();
+	if (IS_ERR(pdev_data.pdata)) {
+		ret = PTR_ERR(pdev_data.pdata);
 		dev_err(glue->dev, "missing wlan platform data: %d\n", ret);
 		goto out_free_glue;
 	}
@@ -260,7 +257,7 @@ static int wl1271_probe(struct sdio_func *func,
 	dev_dbg(glue->dev, "sdio PM caps = 0x%x\n", mmcflags);
 
 	if (mmcflags & MMC_PM_KEEP_POWER)
-		pdev_data->pdata->pwr_in_suspend = true;
+		pdev_data.pdata->pwr_in_suspend = true;
 
 	sdio_set_drvdata(func, glue);
 
@@ -289,7 +286,7 @@ static int wl1271_probe(struct sdio_func *func,
 
 	memset(res, 0x00, sizeof(res));
 
-	res[0].start = pdev_data->pdata->irq;
+	res[0].start = pdev_data.pdata->irq;
 	res[0].flags = IORESOURCE_IRQ;
 	res[0].name = "irq";
 
@@ -299,8 +296,8 @@ static int wl1271_probe(struct sdio_func *func,
 		goto out_dev_put;
 	}
 
-	ret = platform_device_add_data(glue->core, pdev_data,
-				       sizeof(*pdev_data));
+	ret = platform_device_add_data(glue->core, &pdev_data,
+				       sizeof(pdev_data));
 	if (ret) {
 		dev_err(glue->dev, "can't add platform data\n");
 		goto out_dev_put;
@@ -319,9 +316,6 @@ out_dev_put:
 out_free_glue:
 	kfree(glue);
 
-out_free_pdev_data:
-	kfree(pdev_data);
-
 out:
 	return ret;
 }
diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c
index dbe826dd7c2..392c882b28f 100644
--- a/drivers/net/wireless/ti/wlcore/spi.c
+++ b/drivers/net/wireless/ti/wlcore/spi.c
@@ -24,11 +24,12 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/swab.h>
 #include <linux/crc7.h>
 #include <linux/spi/spi.h>
 #include <linux/wl12xx.h>
 #include <linux/platform_device.h>
-#include <linux/slab.h>
 
 #include "wlcore.h"
 #include "wl12xx_80211.h"
@@ -110,18 +111,16 @@ static void wl12xx_spi_reset(struct device *child)
 static void wl12xx_spi_init(struct device *child)
 {
 	struct wl12xx_spi_glue *glue = dev_get_drvdata(child->parent);
-	u8 crc[WSPI_INIT_CMD_CRC_LEN], *cmd;
 	struct spi_transfer t;
 	struct spi_message m;
+	u8 *cmd = kzalloc(WSPI_INIT_CMD_LEN, GFP_KERNEL);
 
-	cmd = kzalloc(WSPI_INIT_CMD_LEN, GFP_KERNEL);
 	if (!cmd) {
 		dev_err(child->parent,
 			"could not allocate cmd for spi init\n");
 		return;
 	}
 
-	memset(crc, 0, sizeof(crc));
 	memset(&t, 0, sizeof(t));
 	spi_message_init(&m);
 
@@ -129,30 +128,29 @@ static void wl12xx_spi_init(struct device *child)
 	 * Set WSPI_INIT_COMMAND
 	 * the data is being send from the MSB to LSB
 	 */
-	cmd[2] = 0xff;
-	cmd[3] = 0xff;
-	cmd[1] = WSPI_INIT_CMD_START | WSPI_INIT_CMD_TX;
-	cmd[0] = 0;
-	cmd[7] = 0;
-	cmd[6] |= HW_ACCESS_WSPI_INIT_CMD_MASK << 3;
-	cmd[6] |= HW_ACCESS_WSPI_FIXED_BUSY_LEN & WSPI_INIT_CMD_FIXEDBUSY_LEN;
+	cmd[0] = 0xff;
+	cmd[1] = 0xff;
+	cmd[2] = WSPI_INIT_CMD_START | WSPI_INIT_CMD_TX;
+	cmd[3] = 0;
+	cmd[4] = 0;
+	cmd[5] = HW_ACCESS_WSPI_INIT_CMD_MASK << 3;
+	cmd[5] |= HW_ACCESS_WSPI_FIXED_BUSY_LEN & WSPI_INIT_CMD_FIXEDBUSY_LEN;
+
+	cmd[6] = WSPI_INIT_CMD_IOD | WSPI_INIT_CMD_IP | WSPI_INIT_CMD_CS
+		| WSPI_INIT_CMD_WSPI | WSPI_INIT_CMD_WS;
 
 	if (HW_ACCESS_WSPI_FIXED_BUSY_LEN == 0)
-		cmd[5] |=  WSPI_INIT_CMD_DIS_FIXEDBUSY;
+		cmd[6] |= WSPI_INIT_CMD_DIS_FIXEDBUSY;
 	else
-		cmd[5] |= WSPI_INIT_CMD_EN_FIXEDBUSY;
-
-	cmd[5] |= WSPI_INIT_CMD_IOD | WSPI_INIT_CMD_IP | WSPI_INIT_CMD_CS
-		| WSPI_INIT_CMD_WSPI | WSPI_INIT_CMD_WS;
-
-	crc[0] = cmd[1];
-	crc[1] = cmd[0];
-	crc[2] = cmd[7];
-	crc[3] = cmd[6];
-	crc[4] = cmd[5];
+		cmd[6] |= WSPI_INIT_CMD_EN_FIXEDBUSY;
 
-	cmd[4] |= crc7(0, crc, WSPI_INIT_CMD_CRC_LEN) << 1;
-	cmd[4] |= WSPI_INIT_CMD_END;
+	cmd[7] = crc7_be(0, cmd+2, WSPI_INIT_CMD_CRC_LEN) | WSPI_INIT_CMD_END;
+	/*
+	 * The above is the logical order; it must actually be stored
+	 * in the buffer byte-swapped.
+	 */
+	__swab32s((u32 *)cmd);
+	__swab32s((u32 *)cmd+1);
 
 	t.tx_buf = cmd;
 	t.len = WSPI_INIT_CMD_LEN;
@@ -327,27 +325,25 @@ static struct wl1271_if_operations spi_ops = {
 static int wl1271_probe(struct spi_device *spi)
 {
 	struct wl12xx_spi_glue *glue;
-	struct wlcore_platdev_data *pdev_data;
+	struct wlcore_platdev_data pdev_data;
 	struct resource res[1];
 	int ret = -ENOMEM;
 
-	pdev_data = kzalloc(sizeof(*pdev_data), GFP_KERNEL);
-	if (!pdev_data)
-		goto out;
+	memset(&pdev_data, 0x00, sizeof(pdev_data));
 
-	pdev_data->pdata = dev_get_platdata(&spi->dev);
-	if (!pdev_data->pdata) {
+	pdev_data.pdata = dev_get_platdata(&spi->dev);
+	if (!pdev_data.pdata) {
 		dev_err(&spi->dev, "no platform data\n");
 		ret = -ENODEV;
-		goto out_free_pdev_data;
+		goto out;
 	}
 
-	pdev_data->if_ops = &spi_ops;
+	pdev_data.if_ops = &spi_ops;
 
 	glue = kzalloc(sizeof(*glue), GFP_KERNEL);
 	if (!glue) {
 		dev_err(&spi->dev, "can't allocate glue\n");
-		goto out_free_pdev_data;
+		goto out;
 	}
 
 	glue->dev = &spi->dev;
@@ -385,8 +381,8 @@ static int wl1271_probe(struct spi_device *spi)
 		goto out_dev_put;
 	}
 
-	ret = platform_device_add_data(glue->core, pdev_data,
-				       sizeof(*pdev_data));
+	ret = platform_device_add_data(glue->core, &pdev_data,
+				       sizeof(pdev_data));
 	if (ret) {
 		dev_err(glue->dev, "can't add platform data\n");
 		goto out_dev_put;
@@ -406,9 +402,6 @@ out_dev_put:
 out_free_glue:
 	kfree(glue);
 
-out_free_pdev_data:
-	kfree(pdev_data);
-
 out:
 	return ret;
 }
diff --git a/drivers/net/wireless/ti/wlcore/wlcore_i.h b/drivers/net/wireless/ti/wlcore/wlcore_i.h
index 756e890bc5e..c2c34a84ff3 100644
--- a/drivers/net/wireless/ti/wlcore/wlcore_i.h
+++ b/drivers/net/wireless/ti/wlcore/wlcore_i.h
@@ -512,8 +512,8 @@ int wl1271_recalc_rx_streaming(struct wl1271 *wl, struct wl12xx_vif *wlvif);
 void wl12xx_queue_recovery_work(struct wl1271 *wl);
 size_t wl12xx_copy_fwlog(struct wl1271 *wl, u8 *memblock, size_t maxlen);
 int wl1271_rx_filter_alloc_field(struct wl12xx_rx_filter *filter,
-					u16 offset, u8 flags,
-					u8 *pattern, u8 len);
+				 u16 offset, u8 flags,
+				 const u8 *pattern, u8 len);
 void wl1271_rx_filter_free(struct wl12xx_rx_filter *filter);
 struct wl12xx_rx_filter *wl1271_rx_filter_alloc(void);
 int wl1271_rx_filter_get_fields_size(struct wl12xx_rx_filter *filter);
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 0d4a285cbd7..2532ce85d71 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -99,22 +99,43 @@ struct xenvif_rx_meta {
  */
 #define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN
 
-struct xenvif {
-	/* Unique identifier for this interface. */
-	domid_t          domid;
-	unsigned int     handle;
+/* Queue name is interface name with "-qNNN" appended */
+#define QUEUE_NAME_SIZE (IFNAMSIZ + 5)
 
-	/* Is this interface disabled? True when backend discovers
-	 * frontend is rogue.
+/* IRQ name is queue name with "-tx" or "-rx" appended */
+#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
+
+struct xenvif;
+
+struct xenvif_stats {
+	/* Stats fields to be updated per-queue.
+	 * A subset of struct net_device_stats that contains only the
+	 * fields that are updated in netback.c for each queue.
 	 */
-	bool disabled;
+	unsigned int rx_bytes;
+	unsigned int rx_packets;
+	unsigned int tx_bytes;
+	unsigned int tx_packets;
+
+	/* Additional stats used by xenvif */
+	unsigned long rx_gso_checksum_fixup;
+	unsigned long tx_zerocopy_sent;
+	unsigned long tx_zerocopy_success;
+	unsigned long tx_zerocopy_fail;
+	unsigned long tx_frag_overflow;
+};
+
+struct xenvif_queue { /* Per-queue data for xenvif */
+	unsigned int id; /* Queue ID, 0-based */
+	char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */
+	struct xenvif *vif; /* Parent VIF */
 
 	/* Use NAPI for guest TX */
 	struct napi_struct napi;
 	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
 	unsigned int tx_irq;
 	/* Only used when feature-split-event-channels = 1 */
-	char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */
+	char tx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-tx */
 	struct xen_netif_tx_back_ring tx;
 	struct sk_buff_head tx_queue;
 	struct page *mmap_pages[MAX_PENDING_REQS];
@@ -150,7 +171,7 @@ struct xenvif {
 	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
 	unsigned int rx_irq;
 	/* Only used when feature-split-event-channels = 1 */
-	char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
+	char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */
 	struct xen_netif_rx_back_ring rx;
 	struct sk_buff_head rx_queue;
 	RING_IDX rx_last_skb_slots;
@@ -158,14 +179,29 @@ struct xenvif {
 
 	struct timer_list wake_queue;
 
-	/* This array is allocated seperately as it is large */
-	struct gnttab_copy *grant_copy_op;
+	struct gnttab_copy grant_copy_op[MAX_GRANT_COPY_OPS];
 
 	/* We create one meta structure per ring request we consume, so
 	 * the maximum number is the same as the ring size.
 	 */
 	struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE];
 
+	/* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */
+	unsigned long   credit_bytes;
+	unsigned long   credit_usec;
+	unsigned long   remaining_credit;
+	struct timer_list credit_timeout;
+	u64 credit_window_start;
+
+	/* Statistics */
+	struct xenvif_stats stats;
+};
+
+struct xenvif {
+	/* Unique identifier for this interface. */
+	domid_t          domid;
+	unsigned int     handle;
+
 	u8               fe_dev_addr[6];
 
 	/* Frontend feature information. */
@@ -179,19 +215,14 @@ struct xenvif {
 	/* Internal feature information. */
 	u8 can_queue:1;	    /* can queue packets for receiver? */
 
-	/* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */
-	unsigned long   credit_bytes;
-	unsigned long   credit_usec;
-	unsigned long   remaining_credit;
-	struct timer_list credit_timeout;
-	u64 credit_window_start;
+	/* Is this interface disabled? True when backend discovers
+	 * frontend is rogue.
+	 */
+	bool disabled;
 
-	/* Statistics */
-	unsigned long rx_gso_checksum_fixup;
-	unsigned long tx_zerocopy_sent;
-	unsigned long tx_zerocopy_success;
-	unsigned long tx_zerocopy_fail;
-	unsigned long tx_frag_overflow;
+	/* Queues */
+	struct xenvif_queue *queues;
+	unsigned int num_queues; /* active queues, resource allocated */
 
 	/* Miscellaneous private stuff. */
 	struct net_device *dev;
@@ -206,7 +237,10 @@ struct xenvif *xenvif_alloc(struct device *parent,
 			    domid_t domid,
 			    unsigned int handle);
 
-int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
+int xenvif_init_queue(struct xenvif_queue *queue);
+void xenvif_deinit_queue(struct xenvif_queue *queue);
+
+int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
 		   unsigned long rx_ring_ref, unsigned int tx_evtchn,
 		   unsigned int rx_evtchn);
 void xenvif_disconnect(struct xenvif *vif);
@@ -217,44 +251,47 @@ void xenvif_xenbus_fini(void);
 
 int xenvif_schedulable(struct xenvif *vif);
 
-int xenvif_must_stop_queue(struct xenvif *vif);
+int xenvif_must_stop_queue(struct xenvif_queue *queue);
+
+int xenvif_queue_stopped(struct xenvif_queue *queue);
+void xenvif_wake_queue(struct xenvif_queue *queue);
 
 /* (Un)Map communication rings. */
-void xenvif_unmap_frontend_rings(struct xenvif *vif);
-int xenvif_map_frontend_rings(struct xenvif *vif,
+void xenvif_unmap_frontend_rings(struct xenvif_queue *queue);
+int xenvif_map_frontend_rings(struct xenvif_queue *queue,
 			      grant_ref_t tx_ring_ref,
 			      grant_ref_t rx_ring_ref);
 
 /* Check for SKBs from frontend and schedule backend processing */
-void xenvif_napi_schedule_or_enable_events(struct xenvif *vif);
+void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue);
 
 /* Prevent the device from generating any further traffic. */
 void xenvif_carrier_off(struct xenvif *vif);
 
-int xenvif_tx_action(struct xenvif *vif, int budget);
+int xenvif_tx_action(struct xenvif_queue *queue, int budget);
 
 int xenvif_kthread_guest_rx(void *data);
-void xenvif_kick_thread(struct xenvif *vif);
+void xenvif_kick_thread(struct xenvif_queue *queue);
 
 int xenvif_dealloc_kthread(void *data);
 
 /* Determine whether the needed number of slots (req) are available,
  * and set req_event if not.
  */
-bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed);
+bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed);
 
-void xenvif_stop_queue(struct xenvif *vif);
+void xenvif_carrier_on(struct xenvif *vif);
 
 /* Callback from stack when TX packet can be released */
 void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
 
 /* Unmap a pending page and release it back to the guest */
-void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx);
+void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx);
 
-static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif)
+static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
 {
 	return MAX_PENDING_REQS -
-		vif->pending_prod + vif->pending_cons;
+		queue->pending_prod + queue->pending_cons;
 }
 
 /* Callback from stack when TX packet can be released */
@@ -264,5 +301,6 @@ extern bool separate_tx_rx_irq;
 
 extern unsigned int rx_drain_timeout_msecs;
 extern unsigned int rx_drain_timeout_jiffies;
+extern unsigned int xenvif_max_queues;
 
 #endif /* __XEN_NETBACK__COMMON_H__ */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 20e9defa106..9e97c7ca0dd 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -43,6 +43,16 @@
 #define XENVIF_QUEUE_LENGTH 32
 #define XENVIF_NAPI_WEIGHT  64
 
+static inline void xenvif_stop_queue(struct xenvif_queue *queue)
+{
+	struct net_device *dev = queue->vif->dev;
+
+	if (!queue->vif->can_queue)
+		return;
+
+	netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
+}
+
 int xenvif_schedulable(struct xenvif *vif)
 {
 	return netif_running(vif->dev) && netif_carrier_ok(vif->dev);
@@ -50,33 +60,34 @@ int xenvif_schedulable(struct xenvif *vif)
 
 static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
 {
-	struct xenvif *vif = dev_id;
+	struct xenvif_queue *queue = dev_id;
 
-	if (RING_HAS_UNCONSUMED_REQUESTS(&vif->tx))
-		napi_schedule(&vif->napi);
+	if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx))
+		napi_schedule(&queue->napi);
 
 	return IRQ_HANDLED;
 }
 
-static int xenvif_poll(struct napi_struct *napi, int budget)
+int xenvif_poll(struct napi_struct *napi, int budget)
 {
-	struct xenvif *vif = container_of(napi, struct xenvif, napi);
+	struct xenvif_queue *queue =
+		container_of(napi, struct xenvif_queue, napi);
 	int work_done;
 
 	/* This vif is rogue, we pretend we've there is nothing to do
 	 * for this vif to deschedule it from NAPI. But this interface
 	 * will be turned off in thread context later.
 	 */
-	if (unlikely(vif->disabled)) {
+	if (unlikely(queue->vif->disabled)) {
 		napi_complete(napi);
 		return 0;
 	}
 
-	work_done = xenvif_tx_action(vif, budget);
+	work_done = xenvif_tx_action(queue, budget);
 
 	if (work_done < budget) {
 		napi_complete(napi);
-		xenvif_napi_schedule_or_enable_events(vif);
+		xenvif_napi_schedule_or_enable_events(queue);
 	}
 
 	return work_done;
@@ -84,9 +95,9 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
 
 static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
 {
-	struct xenvif *vif = dev_id;
+	struct xenvif_queue *queue = dev_id;
 
-	xenvif_kick_thread(vif);
+	xenvif_kick_thread(queue);
 
 	return IRQ_HANDLED;
 }
@@ -99,28 +110,59 @@ static irqreturn_t xenvif_interrupt(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static void xenvif_wake_queue(unsigned long data)
+int xenvif_queue_stopped(struct xenvif_queue *queue)
+{
+	struct net_device *dev = queue->vif->dev;
+	unsigned int id = queue->id;
+	return netif_tx_queue_stopped(netdev_get_tx_queue(dev, id));
+}
+
+void xenvif_wake_queue(struct xenvif_queue *queue)
+{
+	struct net_device *dev = queue->vif->dev;
+	unsigned int id = queue->id;
+	netif_tx_wake_queue(netdev_get_tx_queue(dev, id));
+}
+
+/* Callback to wake the queue and drain it on timeout */
+static void xenvif_wake_queue_callback(unsigned long data)
 {
-	struct xenvif *vif = (struct xenvif *)data;
+	struct xenvif_queue *queue = (struct xenvif_queue *)data;
 
-	if (netif_queue_stopped(vif->dev)) {
-		netdev_err(vif->dev, "draining TX queue\n");
-		vif->rx_queue_purge = true;
-		xenvif_kick_thread(vif);
-		netif_wake_queue(vif->dev);
+	if (xenvif_queue_stopped(queue)) {
+		netdev_err(queue->vif->dev, "draining TX queue\n");
+		queue->rx_queue_purge = true;
+		xenvif_kick_thread(queue);
+		xenvif_wake_queue(queue);
 	}
 }
 
 static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct xenvif *vif = netdev_priv(dev);
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	u16 index;
 	int min_slots_needed;
 
 	BUG_ON(skb->dev != dev);
 
-	/* Drop the packet if vif is not ready */
-	if (vif->task == NULL ||
-	    vif->dealloc_task == NULL ||
+	/* Drop the packet if queues are not set up */
+	if (num_queues < 1)
+		goto drop;
+
+	/* Obtain the queue to be used to transmit this packet */
+	index = skb_get_queue_mapping(skb);
+	if (index >= num_queues) {
+		pr_warn_ratelimited("Invalid queue %hu for packet on interface %s\n.",
+				    index, vif->dev->name);
+		index %= num_queues;
+	}
+	queue = &vif->queues[index];
+
+	/* Drop the packet if queue is not ready */
+	if (queue->task == NULL ||
+	    queue->dealloc_task == NULL ||
 	    !xenvif_schedulable(vif))
 		goto drop;
 
@@ -139,16 +181,16 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * then turn off the queue to give the ring a chance to
 	 * drain.
 	 */
-	if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) {
-		vif->wake_queue.function = xenvif_wake_queue;
-		vif->wake_queue.data = (unsigned long)vif;
-		xenvif_stop_queue(vif);
-		mod_timer(&vif->wake_queue,
+	if (!xenvif_rx_ring_slots_available(queue, min_slots_needed)) {
+		queue->wake_queue.function = xenvif_wake_queue_callback;
+		queue->wake_queue.data = (unsigned long)queue;
+		xenvif_stop_queue(queue);
+		mod_timer(&queue->wake_queue,
 			jiffies + rx_drain_timeout_jiffies);
 	}
 
-	skb_queue_tail(&vif->rx_queue, skb);
-	xenvif_kick_thread(vif);
+	skb_queue_tail(&queue->rx_queue, skb);
+	xenvif_kick_thread(queue);
 
 	return NETDEV_TX_OK;
 
@@ -161,25 +203,65 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
 static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
 {
 	struct xenvif *vif = netdev_priv(dev);
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned long rx_bytes = 0;
+	unsigned long rx_packets = 0;
+	unsigned long tx_bytes = 0;
+	unsigned long tx_packets = 0;
+	unsigned int index;
+
+	if (vif->queues == NULL)
+		goto out;
+
+	/* Aggregate tx and rx stats from each queue */
+	for (index = 0; index < num_queues; ++index) {
+		queue = &vif->queues[index];
+		rx_bytes += queue->stats.rx_bytes;
+		rx_packets += queue->stats.rx_packets;
+		tx_bytes += queue->stats.tx_bytes;
+		tx_packets += queue->stats.tx_packets;
+	}
+
+out:
+	vif->dev->stats.rx_bytes = rx_bytes;
+	vif->dev->stats.rx_packets = rx_packets;
+	vif->dev->stats.tx_bytes = tx_bytes;
+	vif->dev->stats.tx_packets = tx_packets;
+
 	return &vif->dev->stats;
 }
 
 static void xenvif_up(struct xenvif *vif)
 {
-	napi_enable(&vif->napi);
-	enable_irq(vif->tx_irq);
-	if (vif->tx_irq != vif->rx_irq)
-		enable_irq(vif->rx_irq);
-	xenvif_napi_schedule_or_enable_events(vif);
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned int queue_index;
+
+	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+		queue = &vif->queues[queue_index];
+		napi_enable(&queue->napi);
+		enable_irq(queue->tx_irq);
+		if (queue->tx_irq != queue->rx_irq)
+			enable_irq(queue->rx_irq);
+		xenvif_napi_schedule_or_enable_events(queue);
+	}
 }
 
 static void xenvif_down(struct xenvif *vif)
 {
-	napi_disable(&vif->napi);
-	disable_irq(vif->tx_irq);
-	if (vif->tx_irq != vif->rx_irq)
-		disable_irq(vif->rx_irq);
-	del_timer_sync(&vif->credit_timeout);
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned int queue_index;
+
+	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+		queue = &vif->queues[queue_index];
+		napi_disable(&queue->napi);
+		disable_irq(queue->tx_irq);
+		if (queue->tx_irq != queue->rx_irq)
+			disable_irq(queue->rx_irq);
+		del_timer_sync(&queue->credit_timeout);
+	}
 }
 
 static int xenvif_open(struct net_device *dev)
@@ -187,7 +269,7 @@ static int xenvif_open(struct net_device *dev)
 	struct xenvif *vif = netdev_priv(dev);
 	if (netif_carrier_ok(dev))
 		xenvif_up(vif);
-	netif_start_queue(dev);
+	netif_tx_start_all_queues(dev);
 	return 0;
 }
 
@@ -196,7 +278,7 @@ static int xenvif_close(struct net_device *dev)
 	struct xenvif *vif = netdev_priv(dev);
 	if (netif_carrier_ok(dev))
 		xenvif_down(vif);
-	netif_stop_queue(dev);
+	netif_tx_stop_all_queues(dev);
 	return 0;
 }
 
@@ -236,29 +318,29 @@ static const struct xenvif_stat {
 } xenvif_stats[] = {
 	{
 		"rx_gso_checksum_fixup",
-		offsetof(struct xenvif, rx_gso_checksum_fixup)
+		offsetof(struct xenvif_stats, rx_gso_checksum_fixup)
 	},
 	/* If (sent != success + fail), there are probably packets never
 	 * freed up properly!
 	 */
 	{
 		"tx_zerocopy_sent",
-		offsetof(struct xenvif, tx_zerocopy_sent),
+		offsetof(struct xenvif_stats, tx_zerocopy_sent),
 	},
 	{
 		"tx_zerocopy_success",
-		offsetof(struct xenvif, tx_zerocopy_success),
+		offsetof(struct xenvif_stats, tx_zerocopy_success),
 	},
 	{
 		"tx_zerocopy_fail",
-		offsetof(struct xenvif, tx_zerocopy_fail)
+		offsetof(struct xenvif_stats, tx_zerocopy_fail)
 	},
 	/* Number of packets exceeding MAX_SKB_FRAG slots. You should use
 	 * a guest with the same MAX_SKB_FRAG
 	 */
 	{
 		"tx_frag_overflow",
-		offsetof(struct xenvif, tx_frag_overflow)
+		offsetof(struct xenvif_stats, tx_frag_overflow)
 	},
 };
 
@@ -275,11 +357,20 @@ static int xenvif_get_sset_count(struct net_device *dev, int string_set)
 static void xenvif_get_ethtool_stats(struct net_device *dev,
 				     struct ethtool_stats *stats, u64 * data)
 {
-	void *vif = netdev_priv(dev);
+	struct xenvif *vif = netdev_priv(dev);
+	unsigned int num_queues = vif->num_queues;
 	int i;
-
-	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
-		data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset);
+	unsigned int queue_index;
+	struct xenvif_stats *vif_stats;
+
+	for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) {
+		unsigned long accum = 0;
+		for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+			vif_stats = &vif->queues[queue_index].stats;
+			accum += *(unsigned long *)(vif_stats + xenvif_stats[i].offset);
+		}
+		data[i] = accum;
+	}
 }
 
 static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
@@ -321,10 +412,14 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	struct net_device *dev;
 	struct xenvif *vif;
 	char name[IFNAMSIZ] = {};
-	int i;
 
 	snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
-	dev = alloc_netdev(sizeof(struct xenvif), name, ether_setup);
+	/* Allocate a netdev with the max. supported number of queues.
+	 * When the guest selects the desired number, it will be updated
+	 * via netif_set_real_num_*_queues().
+	 */
+	dev = alloc_netdev_mq(sizeof(struct xenvif), name, ether_setup,
+			      xenvif_max_queues);
 	if (dev == NULL) {
 		pr_warn("Could not allocate netdev for %s\n", name);
 		return ERR_PTR(-ENOMEM);
@@ -334,66 +429,26 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 
 	vif = netdev_priv(dev);
 
-	vif->grant_copy_op = vmalloc(sizeof(struct gnttab_copy) *
-				     MAX_GRANT_COPY_OPS);
-	if (vif->grant_copy_op == NULL) {
-		pr_warn("Could not allocate grant copy space for %s\n", name);
-		free_netdev(dev);
-		return ERR_PTR(-ENOMEM);
-	}
-
 	vif->domid  = domid;
 	vif->handle = handle;
 	vif->can_sg = 1;
 	vif->ip_csum = 1;
 	vif->dev = dev;
-
 	vif->disabled = false;
 
-	vif->credit_bytes = vif->remaining_credit = ~0UL;
-	vif->credit_usec  = 0UL;
-	init_timer(&vif->credit_timeout);
-	vif->credit_window_start = get_jiffies_64();
-
-	init_timer(&vif->wake_queue);
+	/* Start out with no queues. */
+	vif->queues = NULL;
+	vif->num_queues = 0;
 
 	dev->netdev_ops	= &xenvif_netdev_ops;
 	dev->hw_features = NETIF_F_SG |
 		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 		NETIF_F_TSO | NETIF_F_TSO6;
 	dev->features = dev->hw_features | NETIF_F_RXCSUM;
-	SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops);
+	dev->ethtool_ops = &xenvif_ethtool_ops;
 
 	dev->tx_queue_len = XENVIF_QUEUE_LENGTH;
 
-	skb_queue_head_init(&vif->rx_queue);
-	skb_queue_head_init(&vif->tx_queue);
-
-	vif->pending_cons = 0;
-	vif->pending_prod = MAX_PENDING_REQS;
-	for (i = 0; i < MAX_PENDING_REQS; i++)
-		vif->pending_ring[i] = i;
-	spin_lock_init(&vif->callback_lock);
-	spin_lock_init(&vif->response_lock);
-	/* If ballooning is disabled, this will consume real memory, so you
-	 * better enable it. The long term solution would be to use just a
-	 * bunch of valid page descriptors, without dependency on ballooning
-	 */
-	err = alloc_xenballooned_pages(MAX_PENDING_REQS,
-				       vif->mmap_pages,
-				       false);
-	if (err) {
-		netdev_err(dev, "Could not reserve mmap_pages\n");
-		return ERR_PTR(-ENOMEM);
-	}
-	for (i = 0; i < MAX_PENDING_REQS; i++) {
-		vif->pending_tx_info[i].callback_struct = (struct ubuf_info)
-			{ .callback = xenvif_zerocopy_callback,
-			  .ctx = NULL,
-			  .desc = i };
-		vif->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
-	}
-
 	/*
 	 * Initialise a dummy MAC address. We choose the numerically
 	 * largest non-broadcast address to prevent the address getting
@@ -403,8 +458,6 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	memset(dev->dev_addr, 0xFF, ETH_ALEN);
 	dev->dev_addr[0] &= ~0x01;
 
-	netif_napi_add(dev, &vif->napi, xenvif_poll, XENVIF_NAPI_WEIGHT);
-
 	netif_carrier_off(dev);
 
 	err = register_netdev(dev);
@@ -421,98 +474,147 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	return vif;
 }
 
-int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
+int xenvif_init_queue(struct xenvif_queue *queue)
+{
+	int err, i;
+
+	queue->credit_bytes = queue->remaining_credit = ~0UL;
+	queue->credit_usec  = 0UL;
+	init_timer(&queue->credit_timeout);
+	queue->credit_window_start = get_jiffies_64();
+
+	skb_queue_head_init(&queue->rx_queue);
+	skb_queue_head_init(&queue->tx_queue);
+
+	queue->pending_cons = 0;
+	queue->pending_prod = MAX_PENDING_REQS;
+	for (i = 0; i < MAX_PENDING_REQS; ++i)
+		queue->pending_ring[i] = i;
+
+	spin_lock_init(&queue->callback_lock);
+	spin_lock_init(&queue->response_lock);
+
+	/* If ballooning is disabled, this will consume real memory, so you
+	 * better enable it. The long term solution would be to use just a
+	 * bunch of valid page descriptors, without dependency on ballooning
+	 */
+	err = alloc_xenballooned_pages(MAX_PENDING_REQS,
+				       queue->mmap_pages,
+				       false);
+	if (err) {
+		netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < MAX_PENDING_REQS; i++) {
+		queue->pending_tx_info[i].callback_struct = (struct ubuf_info)
+			{ .callback = xenvif_zerocopy_callback,
+			  .ctx = NULL,
+			  .desc = i };
+		queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
+	}
+
+	init_timer(&queue->wake_queue);
+
+	netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll,
+			XENVIF_NAPI_WEIGHT);
+
+	return 0;
+}
+
+void xenvif_carrier_on(struct xenvif *vif)
+{
+	rtnl_lock();
+	if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
+		dev_set_mtu(vif->dev, ETH_DATA_LEN);
+	netdev_update_features(vif->dev);
+	netif_carrier_on(vif->dev);
+	if (netif_running(vif->dev))
+		xenvif_up(vif);
+	rtnl_unlock();
+}
+
+int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
 		   unsigned long rx_ring_ref, unsigned int tx_evtchn,
 		   unsigned int rx_evtchn)
 {
 	struct task_struct *task;
 	int err = -ENOMEM;
 
-	BUG_ON(vif->tx_irq);
-	BUG_ON(vif->task);
-	BUG_ON(vif->dealloc_task);
+	BUG_ON(queue->tx_irq);
+	BUG_ON(queue->task);
+	BUG_ON(queue->dealloc_task);
 
-	err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref);
+	err = xenvif_map_frontend_rings(queue, tx_ring_ref, rx_ring_ref);
 	if (err < 0)
 		goto err;
 
-	init_waitqueue_head(&vif->wq);
-	init_waitqueue_head(&vif->dealloc_wq);
+	init_waitqueue_head(&queue->wq);
+	init_waitqueue_head(&queue->dealloc_wq);
 
 	if (tx_evtchn == rx_evtchn) {
 		/* feature-split-event-channels == 0 */
 		err = bind_interdomain_evtchn_to_irqhandler(
-			vif->domid, tx_evtchn, xenvif_interrupt, 0,
-			vif->dev->name, vif);
+			queue->vif->domid, tx_evtchn, xenvif_interrupt, 0,
+			queue->name, queue);
 		if (err < 0)
 			goto err_unmap;
-		vif->tx_irq = vif->rx_irq = err;
-		disable_irq(vif->tx_irq);
+		queue->tx_irq = queue->rx_irq = err;
+		disable_irq(queue->tx_irq);
 	} else {
 		/* feature-split-event-channels == 1 */
-		snprintf(vif->tx_irq_name, sizeof(vif->tx_irq_name),
-			 "%s-tx", vif->dev->name);
+		snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name),
+			 "%s-tx", queue->name);
 		err = bind_interdomain_evtchn_to_irqhandler(
-			vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
-			vif->tx_irq_name, vif);
+			queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
+			queue->tx_irq_name, queue);
 		if (err < 0)
 			goto err_unmap;
-		vif->tx_irq = err;
-		disable_irq(vif->tx_irq);
+		queue->tx_irq = err;
+		disable_irq(queue->tx_irq);
 
-		snprintf(vif->rx_irq_name, sizeof(vif->rx_irq_name),
-			 "%s-rx", vif->dev->name);
+		snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name),
+			 "%s-rx", queue->name);
 		err = bind_interdomain_evtchn_to_irqhandler(
-			vif->domid, rx_evtchn, xenvif_rx_interrupt, 0,
-			vif->rx_irq_name, vif);
+			queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0,
+			queue->rx_irq_name, queue);
 		if (err < 0)
 			goto err_tx_unbind;
-		vif->rx_irq = err;
-		disable_irq(vif->rx_irq);
+		queue->rx_irq = err;
+		disable_irq(queue->rx_irq);
 	}
 
 	task = kthread_create(xenvif_kthread_guest_rx,
-			      (void *)vif, "%s-guest-rx", vif->dev->name);
+			      (void *)queue, "%s-guest-rx", queue->name);
 	if (IS_ERR(task)) {
-		pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
+		pr_warn("Could not allocate kthread for %s\n", queue->name);
 		err = PTR_ERR(task);
 		goto err_rx_unbind;
 	}
-
-	vif->task = task;
+	queue->task = task;
 
 	task = kthread_create(xenvif_dealloc_kthread,
-			      (void *)vif, "%s-dealloc", vif->dev->name);
+			      (void *)queue, "%s-dealloc", queue->name);
 	if (IS_ERR(task)) {
-		pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
+		pr_warn("Could not allocate kthread for %s\n", queue->name);
 		err = PTR_ERR(task);
 		goto err_rx_unbind;
 	}
+	queue->dealloc_task = task;
 
-	vif->dealloc_task = task;
-
-	rtnl_lock();
-	if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
-		dev_set_mtu(vif->dev, ETH_DATA_LEN);
-	netdev_update_features(vif->dev);
-	netif_carrier_on(vif->dev);
-	if (netif_running(vif->dev))
-		xenvif_up(vif);
-	rtnl_unlock();
-
-	wake_up_process(vif->task);
-	wake_up_process(vif->dealloc_task);
+	wake_up_process(queue->task);
+	wake_up_process(queue->dealloc_task);
 
 	return 0;
 
 err_rx_unbind:
-	unbind_from_irqhandler(vif->rx_irq, vif);
-	vif->rx_irq = 0;
+	unbind_from_irqhandler(queue->rx_irq, queue);
+	queue->rx_irq = 0;
 err_tx_unbind:
-	unbind_from_irqhandler(vif->tx_irq, vif);
-	vif->tx_irq = 0;
+	unbind_from_irqhandler(queue->tx_irq, queue);
+	queue->tx_irq = 0;
 err_unmap:
-	xenvif_unmap_frontend_rings(vif);
+	xenvif_unmap_frontend_rings(queue);
 err:
 	module_put(THIS_MODULE);
 	return err;
@@ -529,38 +631,77 @@ void xenvif_carrier_off(struct xenvif *vif)
 	rtnl_unlock();
 }
 
+static void xenvif_wait_unmap_timeout(struct xenvif_queue *queue,
+				      unsigned int worst_case_skb_lifetime)
+{
+	int i, unmap_timeout = 0;
+
+	for (i = 0; i < MAX_PENDING_REQS; ++i) {
+		if (queue->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) {
+			unmap_timeout++;
+			schedule_timeout(msecs_to_jiffies(1000));
+			if (unmap_timeout > worst_case_skb_lifetime &&
+			    net_ratelimit())
+				netdev_err(queue->vif->dev,
+					   "Page still granted! Index: %x\n",
+					   i);
+			i = -1;
+		}
+	}
+}
+
 void xenvif_disconnect(struct xenvif *vif)
 {
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned int queue_index;
+
 	if (netif_carrier_ok(vif->dev))
 		xenvif_carrier_off(vif);
 
-	if (vif->task) {
-		del_timer_sync(&vif->wake_queue);
-		kthread_stop(vif->task);
-		vif->task = NULL;
-	}
+	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+		queue = &vif->queues[queue_index];
 
-	if (vif->dealloc_task) {
-		kthread_stop(vif->dealloc_task);
-		vif->dealloc_task = NULL;
-	}
+		if (queue->task) {
+			del_timer_sync(&queue->wake_queue);
+			kthread_stop(queue->task);
+			queue->task = NULL;
+		}
 
-	if (vif->tx_irq) {
-		if (vif->tx_irq == vif->rx_irq)
-			unbind_from_irqhandler(vif->tx_irq, vif);
-		else {
-			unbind_from_irqhandler(vif->tx_irq, vif);
-			unbind_from_irqhandler(vif->rx_irq, vif);
+		if (queue->dealloc_task) {
+			kthread_stop(queue->dealloc_task);
+			queue->dealloc_task = NULL;
 		}
-		vif->tx_irq = 0;
+
+		if (queue->tx_irq) {
+			if (queue->tx_irq == queue->rx_irq)
+				unbind_from_irqhandler(queue->tx_irq, queue);
+			else {
+				unbind_from_irqhandler(queue->tx_irq, queue);
+				unbind_from_irqhandler(queue->rx_irq, queue);
+			}
+			queue->tx_irq = 0;
+		}
+
+		xenvif_unmap_frontend_rings(queue);
 	}
+}
 
-	xenvif_unmap_frontend_rings(vif);
+/* Reverse the relevant parts of xenvif_init_queue().
+ * Used for queue teardown from xenvif_free(), and on the
+ * error handling paths in xenbus.c:connect().
+ */
+void xenvif_deinit_queue(struct xenvif_queue *queue)
+{
+	free_xenballooned_pages(MAX_PENDING_REQS, queue->mmap_pages);
+	netif_napi_del(&queue->napi);
 }
 
 void xenvif_free(struct xenvif *vif)
 {
-	int i, unmap_timeout = 0;
+	struct xenvif_queue *queue = NULL;
+	unsigned int num_queues = vif->num_queues;
+	unsigned int queue_index;
 	/* Here we want to avoid timeout messages if an skb can be legitimately
 	 * stuck somewhere else. Realistically this could be an another vif's
 	 * internal or QDisc queue. That another vif also has this
@@ -575,33 +716,18 @@ void xenvif_free(struct xenvif *vif)
 	unsigned int worst_case_skb_lifetime = (rx_drain_timeout_msecs/1000) *
 		DIV_ROUND_UP(XENVIF_QUEUE_LENGTH, (XEN_NETIF_RX_RING_SIZE / MAX_SKB_FRAGS));
 
-	for (i = 0; i < MAX_PENDING_REQS; ++i) {
-		if (vif->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) {
-			unmap_timeout++;
-			schedule_timeout(msecs_to_jiffies(1000));
-			if (unmap_timeout > worst_case_skb_lifetime &&
-			    net_ratelimit())
-				netdev_err(vif->dev,
-					   "Page still granted! Index: %x\n",
-					   i);
-			/* If there are still unmapped pages, reset the loop to
-			 * start checking again. We shouldn't exit here until
-			 * dealloc thread and NAPI instance release all the
-			 * pages. If a kernel bug causes the skbs to stall
-			 * somewhere, the interface cannot be brought down
-			 * properly.
-			 */
-			i = -1;
-		}
-	}
-
-	free_xenballooned_pages(MAX_PENDING_REQS, vif->mmap_pages);
+	unregister_netdev(vif->dev);
 
-	netif_napi_del(&vif->napi);
+	for (queue_index = 0; queue_index < num_queues; ++queue_index) {
+		queue = &vif->queues[queue_index];
+		xenvif_wait_unmap_timeout(queue, worst_case_skb_lifetime);
+		xenvif_deinit_queue(queue);
+	}
 
-	unregister_netdev(vif->dev);
+	vfree(vif->queues);
+	vif->queues = NULL;
+	vif->num_queues = 0;
 
-	vfree(vif->grant_copy_op);
 	free_netdev(vif->dev);
 
 	module_put(THIS_MODULE);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 7367208ee8c..c65b636bcab 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -62,6 +62,11 @@ unsigned int rx_drain_timeout_msecs = 10000;
 module_param(rx_drain_timeout_msecs, uint, 0444);
 unsigned int rx_drain_timeout_jiffies;
 
+unsigned int xenvif_max_queues;
+module_param_named(max_queues, xenvif_max_queues, uint, 0644);
+MODULE_PARM_DESC(max_queues,
+		 "Maximum number of queues per virtual interface");
+
 /*
  * This is the maximum slots a skb can have. If a guest sends a skb
  * which exceeds this limit it is considered malicious.
@@ -70,33 +75,33 @@ unsigned int rx_drain_timeout_jiffies;
 static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT;
 module_param(fatal_skb_slots, uint, 0444);
 
-static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx,
+static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 			       u8 status);
 
-static void make_tx_response(struct xenvif *vif,
+static void make_tx_response(struct xenvif_queue *queue,
 			     struct xen_netif_tx_request *txp,
 			     s8       st);
 
-static inline int tx_work_todo(struct xenvif *vif);
-static inline int rx_work_todo(struct xenvif *vif);
+static inline int tx_work_todo(struct xenvif_queue *queue);
+static inline int rx_work_todo(struct xenvif_queue *queue);
 
-static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
+static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue,
 					     u16      id,
 					     s8       st,
 					     u16      offset,
 					     u16      size,
 					     u16      flags);
 
-static inline unsigned long idx_to_pfn(struct xenvif *vif,
+static inline unsigned long idx_to_pfn(struct xenvif_queue *queue,
 				       u16 idx)
 {
-	return page_to_pfn(vif->mmap_pages[idx]);
+	return page_to_pfn(queue->mmap_pages[idx]);
 }
 
-static inline unsigned long idx_to_kaddr(struct xenvif *vif,
+static inline unsigned long idx_to_kaddr(struct xenvif_queue *queue,
 					 u16 idx)
 {
-	return (unsigned long)pfn_to_kaddr(idx_to_pfn(vif, idx));
+	return (unsigned long)pfn_to_kaddr(idx_to_pfn(queue, idx));
 }
 
 #define callback_param(vif, pending_idx) \
@@ -104,13 +109,13 @@ static inline unsigned long idx_to_kaddr(struct xenvif *vif,
 
 /* Find the containing VIF's structure from a pointer in pending_tx_info array
  */
-static inline struct xenvif *ubuf_to_vif(const struct ubuf_info *ubuf)
+static inline struct xenvif_queue *ubuf_to_queue(const struct ubuf_info *ubuf)
 {
 	u16 pending_idx = ubuf->desc;
 	struct pending_tx_info *temp =
 		container_of(ubuf, struct pending_tx_info, callback_struct);
 	return container_of(temp - pending_idx,
-			    struct xenvif,
+			    struct xenvif_queue,
 			    pending_tx_info[0]);
 }
 
@@ -136,24 +141,24 @@ static inline pending_ring_idx_t pending_index(unsigned i)
 	return i & (MAX_PENDING_REQS-1);
 }
 
-bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed)
+bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed)
 {
 	RING_IDX prod, cons;
 
 	do {
-		prod = vif->rx.sring->req_prod;
-		cons = vif->rx.req_cons;
+		prod = queue->rx.sring->req_prod;
+		cons = queue->rx.req_cons;
 
 		if (prod - cons >= needed)
 			return true;
 
-		vif->rx.sring->req_event = prod + 1;
+		queue->rx.sring->req_event = prod + 1;
 
 		/* Make sure event is visible before we check prod
 		 * again.
 		 */
 		mb();
-	} while (vif->rx.sring->req_prod != prod);
+	} while (queue->rx.sring->req_prod != prod);
 
 	return false;
 }
@@ -163,7 +168,8 @@ bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed)
  * adding 'size' bytes to a buffer which currently contains 'offset'
  * bytes.
  */
-static bool start_new_rx_buffer(int offset, unsigned long size, int head)
+static bool start_new_rx_buffer(int offset, unsigned long size, int head,
+				bool full_coalesce)
 {
 	/* simple case: we have completely filled the current buffer. */
 	if (offset == MAX_BUFFER_OFFSET)
@@ -175,6 +181,7 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
 	 *     (i)   this frag would fit completely in the next buffer
 	 * and (ii)  there is already some data in the current buffer
 	 * and (iii) this is not the head buffer.
+	 * and (iv)  there is no need to fully utilize the buffers
 	 *
 	 * Where:
 	 * - (i) stops us splitting a frag into two copies
@@ -185,6 +192,8 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
 	 *   by (ii) but is explicitly checked because
 	 *   netfront relies on the first buffer being
 	 *   non-empty and can crash otherwise.
+	 * - (iv) is needed for skbs which can use up more than MAX_SKB_FRAGS
+	 *   slot
 	 *
 	 * This means we will effectively linearise small
 	 * frags but do not needlessly split large buffers
@@ -192,7 +201,8 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
 	 * own buffers as before.
 	 */
 	BUG_ON(size > MAX_BUFFER_OFFSET);
-	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
+	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head &&
+	    !full_coalesce)
 		return true;
 
 	return false;
@@ -207,13 +217,13 @@ struct netrx_pending_operations {
 	grant_ref_t copy_gref;
 };
 
-static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif,
+static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue,
 						 struct netrx_pending_operations *npo)
 {
 	struct xenvif_rx_meta *meta;
 	struct xen_netif_rx_request *req;
 
-	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
+	req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++);
 
 	meta = npo->meta + npo->meta_prod++;
 	meta->gso_type = XEN_NETIF_GSO_TYPE_NONE;
@@ -227,15 +237,22 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif,
 	return meta;
 }
 
+struct xenvif_rx_cb {
+	int meta_slots_used;
+	bool full_coalesce;
+};
+
+#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb)
+
 /*
  * Set up the grant operations for this fragment. If it's a flipping
  * interface, we also set up the unmap request from here.
  */
-static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
+static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb,
 				 struct netrx_pending_operations *npo,
 				 struct page *page, unsigned long size,
 				 unsigned long offset, int *head,
-				 struct xenvif *foreign_vif,
+				 struct xenvif_queue *foreign_queue,
 				 grant_ref_t foreign_gref)
 {
 	struct gnttab_copy *copy_gop;
@@ -261,14 +278,17 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 		if (bytes > size)
 			bytes = size;
 
-		if (start_new_rx_buffer(npo->copy_off, bytes, *head)) {
+		if (start_new_rx_buffer(npo->copy_off,
+					bytes,
+					*head,
+					XENVIF_RX_CB(skb)->full_coalesce)) {
 			/*
 			 * Netfront requires there to be some data in the head
 			 * buffer.
 			 */
 			BUG_ON(*head);
 
-			meta = get_next_rx_buffer(vif, npo);
+			meta = get_next_rx_buffer(queue, npo);
 		}
 
 		if (npo->copy_off + bytes > MAX_BUFFER_OFFSET)
@@ -278,8 +298,8 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 		copy_gop->flags = GNTCOPY_dest_gref;
 		copy_gop->len = bytes;
 
-		if (foreign_vif) {
-			copy_gop->source.domid = foreign_vif->domid;
+		if (foreign_queue) {
+			copy_gop->source.domid = foreign_queue->vif->domid;
 			copy_gop->source.u.ref = foreign_gref;
 			copy_gop->flags |= GNTCOPY_source_gref;
 		} else {
@@ -289,7 +309,7 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 		}
 		copy_gop->source.offset = offset;
 
-		copy_gop->dest.domid = vif->domid;
+		copy_gop->dest.domid = queue->vif->domid;
 		copy_gop->dest.offset = npo->copy_off;
 		copy_gop->dest.u.ref = npo->copy_gref;
 
@@ -314,8 +334,8 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 				gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
 		}
 
-		if (*head && ((1 << gso_type) & vif->gso_mask))
-			vif->rx.req_cons++;
+		if (*head && ((1 << gso_type) & queue->vif->gso_mask))
+			queue->rx.req_cons++;
 
 		*head = 0; /* There must be something in this buffer now. */
 
@@ -337,13 +357,13 @@ static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb,
 						const int i,
 						const struct ubuf_info *ubuf)
 {
-	struct xenvif *foreign_vif = ubuf_to_vif(ubuf);
+	struct xenvif_queue *foreign_queue = ubuf_to_queue(ubuf);
 
 	do {
 		u16 pending_idx = ubuf->desc;
 
 		if (skb_shinfo(skb)->frags[i].page.p ==
-		    foreign_vif->mmap_pages[pending_idx])
+		    foreign_queue->mmap_pages[pending_idx])
 			break;
 		ubuf = (struct ubuf_info *) ubuf->ctx;
 	} while (ubuf);
@@ -364,7 +384,8 @@ static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb,
  * frontend-side LRO).
  */
 static int xenvif_gop_skb(struct sk_buff *skb,
-			  struct netrx_pending_operations *npo)
+			  struct netrx_pending_operations *npo,
+			  struct xenvif_queue *queue)
 {
 	struct xenvif *vif = netdev_priv(skb->dev);
 	int nr_frags = skb_shinfo(skb)->nr_frags;
@@ -390,7 +411,7 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 
 	/* Set up a GSO prefix descriptor, if necessary */
 	if ((1 << gso_type) & vif->gso_prefix_mask) {
-		req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
+		req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++);
 		meta = npo->meta + npo->meta_prod++;
 		meta->gso_type = gso_type;
 		meta->gso_size = skb_shinfo(skb)->gso_size;
@@ -398,7 +419,7 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 		meta->id = req->id;
 	}
 
-	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
+	req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++);
 	meta = npo->meta + npo->meta_prod++;
 
 	if ((1 << gso_type) & vif->gso_mask) {
@@ -422,7 +443,7 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 		if (data + len > skb_tail_pointer(skb))
 			len = skb_tail_pointer(skb) - data;
 
-		xenvif_gop_frag_copy(vif, skb, npo,
+		xenvif_gop_frag_copy(queue, skb, npo,
 				     virt_to_page(data), len, offset, &head,
 				     NULL,
 				     0);
@@ -433,7 +454,7 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 		/* This variable also signals whether foreign_gref has a real
 		 * value or not.
 		 */
-		struct xenvif *foreign_vif = NULL;
+		struct xenvif_queue *foreign_queue = NULL;
 		grant_ref_t foreign_gref;
 
 		if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) &&
@@ -458,8 +479,9 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 			if (likely(ubuf)) {
 				u16 pending_idx = ubuf->desc;
 
-				foreign_vif = ubuf_to_vif(ubuf);
-				foreign_gref = foreign_vif->pending_tx_info[pending_idx].req.gref;
+				foreign_queue = ubuf_to_queue(ubuf);
+				foreign_gref =
+					foreign_queue->pending_tx_info[pending_idx].req.gref;
 				/* Just a safety measure. If this was the last
 				 * element on the list, the for loop will
 				 * iterate again if a local page were added to
@@ -477,13 +499,13 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 				 */
 				ubuf = head_ubuf;
 		}
-		xenvif_gop_frag_copy(vif, skb, npo,
+		xenvif_gop_frag_copy(queue, skb, npo,
 				     skb_frag_page(&skb_shinfo(skb)->frags[i]),
 				     skb_frag_size(&skb_shinfo(skb)->frags[i]),
 				     skb_shinfo(skb)->frags[i].page_offset,
 				     &head,
-				     foreign_vif,
-				     foreign_vif ? foreign_gref : UINT_MAX);
+				     foreign_queue,
+				     foreign_queue ? foreign_gref : UINT_MAX);
 	}
 
 	return npo->meta_prod - old_meta_prod;
@@ -515,7 +537,7 @@ static int xenvif_check_gop(struct xenvif *vif, int nr_meta_slots,
 	return status;
 }
 
-static void xenvif_add_frag_responses(struct xenvif *vif, int status,
+static void xenvif_add_frag_responses(struct xenvif_queue *queue, int status,
 				      struct xenvif_rx_meta *meta,
 				      int nr_meta_slots)
 {
@@ -536,23 +558,17 @@ static void xenvif_add_frag_responses(struct xenvif *vif, int status,
 			flags = XEN_NETRXF_more_data;
 
 		offset = 0;
-		make_rx_response(vif, meta[i].id, status, offset,
+		make_rx_response(queue, meta[i].id, status, offset,
 				 meta[i].size, flags);
 	}
 }
 
-struct xenvif_rx_cb {
-	int meta_slots_used;
-};
-
-#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb)
-
-void xenvif_kick_thread(struct xenvif *vif)
+void xenvif_kick_thread(struct xenvif_queue *queue)
 {
-	wake_up(&vif->wq);
+	wake_up(&queue->wq);
 }
 
-static void xenvif_rx_action(struct xenvif *vif)
+static void xenvif_rx_action(struct xenvif_queue *queue)
 {
 	s8 status;
 	u16 flags;
@@ -565,13 +581,13 @@ static void xenvif_rx_action(struct xenvif *vif)
 	bool need_to_notify = false;
 
 	struct netrx_pending_operations npo = {
-		.copy  = vif->grant_copy_op,
-		.meta  = vif->meta,
+		.copy  = queue->grant_copy_op,
+		.meta  = queue->meta,
 	};
 
 	skb_queue_head_init(&rxq);
 
-	while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
+	while ((skb = skb_dequeue(&queue->rx_queue)) != NULL) {
 		RING_IDX max_slots_needed;
 		RING_IDX old_req_cons;
 		RING_IDX ring_slots_used;
@@ -602,10 +618,15 @@ static void xenvif_rx_action(struct xenvif *vif)
 
 		/* To avoid the estimate becoming too pessimal for some
 		 * frontends that limit posted rx requests, cap the estimate
-		 * at MAX_SKB_FRAGS.
+		 * at MAX_SKB_FRAGS. In this case netback will fully coalesce
+		 * the skb into the provided slots.
 		 */
-		if (max_slots_needed > MAX_SKB_FRAGS)
+		if (max_slots_needed > MAX_SKB_FRAGS) {
 			max_slots_needed = MAX_SKB_FRAGS;
+			XENVIF_RX_CB(skb)->full_coalesce = true;
+		} else {
+			XENVIF_RX_CB(skb)->full_coalesce = false;
+		}
 
 		/* We may need one more slot for GSO metadata */
 		if (skb_is_gso(skb) &&
@@ -614,42 +635,42 @@ static void xenvif_rx_action(struct xenvif *vif)
 			max_slots_needed++;
 
 		/* If the skb may not fit then bail out now */
-		if (!xenvif_rx_ring_slots_available(vif, max_slots_needed)) {
-			skb_queue_head(&vif->rx_queue, skb);
+		if (!xenvif_rx_ring_slots_available(queue, max_slots_needed)) {
+			skb_queue_head(&queue->rx_queue, skb);
 			need_to_notify = true;
-			vif->rx_last_skb_slots = max_slots_needed;
+			queue->rx_last_skb_slots = max_slots_needed;
 			break;
 		} else
-			vif->rx_last_skb_slots = 0;
+			queue->rx_last_skb_slots = 0;
 
-		old_req_cons = vif->rx.req_cons;
-		XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo);
-		ring_slots_used = vif->rx.req_cons - old_req_cons;
+		old_req_cons = queue->rx.req_cons;
+		XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo, queue);
+		ring_slots_used = queue->rx.req_cons - old_req_cons;
 
 		BUG_ON(ring_slots_used > max_slots_needed);
 
 		__skb_queue_tail(&rxq, skb);
 	}
 
-	BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta));
+	BUG_ON(npo.meta_prod > ARRAY_SIZE(queue->meta));
 
 	if (!npo.copy_prod)
 		goto done;
 
 	BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS);
-	gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod);
+	gnttab_batch_copy(queue->grant_copy_op, npo.copy_prod);
 
 	while ((skb = __skb_dequeue(&rxq)) != NULL) {
 
-		if ((1 << vif->meta[npo.meta_cons].gso_type) &
-		    vif->gso_prefix_mask) {
-			resp = RING_GET_RESPONSE(&vif->rx,
-						 vif->rx.rsp_prod_pvt++);
+		if ((1 << queue->meta[npo.meta_cons].gso_type) &
+		    queue->vif->gso_prefix_mask) {
+			resp = RING_GET_RESPONSE(&queue->rx,
+						 queue->rx.rsp_prod_pvt++);
 
 			resp->flags = XEN_NETRXF_gso_prefix | XEN_NETRXF_more_data;
 
-			resp->offset = vif->meta[npo.meta_cons].gso_size;
-			resp->id = vif->meta[npo.meta_cons].id;
+			resp->offset = queue->meta[npo.meta_cons].gso_size;
+			resp->id = queue->meta[npo.meta_cons].id;
 			resp->status = XENVIF_RX_CB(skb)->meta_slots_used;
 
 			npo.meta_cons++;
@@ -657,10 +678,10 @@ static void xenvif_rx_action(struct xenvif *vif)
 		}
 
 
-		vif->dev->stats.tx_bytes += skb->len;
-		vif->dev->stats.tx_packets++;
+		queue->stats.tx_bytes += skb->len;
+		queue->stats.tx_packets++;
 
-		status = xenvif_check_gop(vif,
+		status = xenvif_check_gop(queue->vif,
 					  XENVIF_RX_CB(skb)->meta_slots_used,
 					  &npo);
 
@@ -676,22 +697,22 @@ static void xenvif_rx_action(struct xenvif *vif)
 			flags |= XEN_NETRXF_data_validated;
 
 		offset = 0;
-		resp = make_rx_response(vif, vif->meta[npo.meta_cons].id,
+		resp = make_rx_response(queue, queue->meta[npo.meta_cons].id,
 					status, offset,
-					vif->meta[npo.meta_cons].size,
+					queue->meta[npo.meta_cons].size,
 					flags);
 
-		if ((1 << vif->meta[npo.meta_cons].gso_type) &
-		    vif->gso_mask) {
+		if ((1 << queue->meta[npo.meta_cons].gso_type) &
+		    queue->vif->gso_mask) {
 			struct xen_netif_extra_info *gso =
 				(struct xen_netif_extra_info *)
-				RING_GET_RESPONSE(&vif->rx,
-						  vif->rx.rsp_prod_pvt++);
+				RING_GET_RESPONSE(&queue->rx,
+						  queue->rx.rsp_prod_pvt++);
 
 			resp->flags |= XEN_NETRXF_extra_info;
 
-			gso->u.gso.type = vif->meta[npo.meta_cons].gso_type;
-			gso->u.gso.size = vif->meta[npo.meta_cons].gso_size;
+			gso->u.gso.type = queue->meta[npo.meta_cons].gso_type;
+			gso->u.gso.size = queue->meta[npo.meta_cons].gso_size;
 			gso->u.gso.pad = 0;
 			gso->u.gso.features = 0;
 
@@ -699,11 +720,11 @@ static void xenvif_rx_action(struct xenvif *vif)
 			gso->flags = 0;
 		}
 
-		xenvif_add_frag_responses(vif, status,
-					  vif->meta + npo.meta_cons + 1,
+		xenvif_add_frag_responses(queue, status,
+					  queue->meta + npo.meta_cons + 1,
 					  XENVIF_RX_CB(skb)->meta_slots_used);
 
-		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);
+		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->rx, ret);
 
 		need_to_notify |= !!ret;
 
@@ -713,20 +734,20 @@ static void xenvif_rx_action(struct xenvif *vif)
 
 done:
 	if (need_to_notify)
-		notify_remote_via_irq(vif->rx_irq);
+		notify_remote_via_irq(queue->rx_irq);
 }
 
-void xenvif_napi_schedule_or_enable_events(struct xenvif *vif)
+void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue)
 {
 	int more_to_do;
 
-	RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);
+	RING_FINAL_CHECK_FOR_REQUESTS(&queue->tx, more_to_do);
 
 	if (more_to_do)
-		napi_schedule(&vif->napi);
+		napi_schedule(&queue->napi);
 }
 
-static void tx_add_credit(struct xenvif *vif)
+static void tx_add_credit(struct xenvif_queue *queue)
 {
 	unsigned long max_burst, max_credit;
 
@@ -734,55 +755,57 @@ static void tx_add_credit(struct xenvif *vif)
 	 * Allow a burst big enough to transmit a jumbo packet of up to 128kB.
 	 * Otherwise the interface can seize up due to insufficient credit.
 	 */
-	max_burst = RING_GET_REQUEST(&vif->tx, vif->tx.req_cons)->size;
+	max_burst = RING_GET_REQUEST(&queue->tx, queue->tx.req_cons)->size;
 	max_burst = min(max_burst, 131072UL);
-	max_burst = max(max_burst, vif->credit_bytes);
+	max_burst = max(max_burst, queue->credit_bytes);
 
 	/* Take care that adding a new chunk of credit doesn't wrap to zero. */
-	max_credit = vif->remaining_credit + vif->credit_bytes;
-	if (max_credit < vif->remaining_credit)
+	max_credit = queue->remaining_credit + queue->credit_bytes;
+	if (max_credit < queue->remaining_credit)
 		max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */
 
-	vif->remaining_credit = min(max_credit, max_burst);
+	queue->remaining_credit = min(max_credit, max_burst);
 }
 
 static void tx_credit_callback(unsigned long data)
 {
-	struct xenvif *vif = (struct xenvif *)data;
-	tx_add_credit(vif);
-	xenvif_napi_schedule_or_enable_events(vif);
+	struct xenvif_queue *queue = (struct xenvif_queue *)data;
+	tx_add_credit(queue);
+	xenvif_napi_schedule_or_enable_events(queue);
 }
 
-static void xenvif_tx_err(struct xenvif *vif,
+static void xenvif_tx_err(struct xenvif_queue *queue,
 			  struct xen_netif_tx_request *txp, RING_IDX end)
 {
-	RING_IDX cons = vif->tx.req_cons;
+	RING_IDX cons = queue->tx.req_cons;
 	unsigned long flags;
 
 	do {
-		spin_lock_irqsave(&vif->response_lock, flags);
-		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
-		spin_unlock_irqrestore(&vif->response_lock, flags);
+		spin_lock_irqsave(&queue->response_lock, flags);
+		make_tx_response(queue, txp, XEN_NETIF_RSP_ERROR);
+		spin_unlock_irqrestore(&queue->response_lock, flags);
 		if (cons == end)
 			break;
-		txp = RING_GET_REQUEST(&vif->tx, cons++);
+		txp = RING_GET_REQUEST(&queue->tx, cons++);
 	} while (1);
-	vif->tx.req_cons = cons;
+	queue->tx.req_cons = cons;
 }
 
 static void xenvif_fatal_tx_err(struct xenvif *vif)
 {
 	netdev_err(vif->dev, "fatal error; disabling device\n");
 	vif->disabled = true;
-	xenvif_kick_thread(vif);
+	/* Disable the vif from queue 0's kthread */
+	if (vif->queues)
+		xenvif_kick_thread(&vif->queues[0]);
 }
 
-static int xenvif_count_requests(struct xenvif *vif,
+static int xenvif_count_requests(struct xenvif_queue *queue,
 				 struct xen_netif_tx_request *first,
 				 struct xen_netif_tx_request *txp,
 				 int work_to_do)
 {
-	RING_IDX cons = vif->tx.req_cons;
+	RING_IDX cons = queue->tx.req_cons;
 	int slots = 0;
 	int drop_err = 0;
 	int more_data;
@@ -794,10 +817,10 @@ static int xenvif_count_requests(struct xenvif *vif,
 		struct xen_netif_tx_request dropped_tx = { 0 };
 
 		if (slots >= work_to_do) {
-			netdev_err(vif->dev,
+			netdev_err(queue->vif->dev,
 				   "Asked for %d slots but exceeds this limit\n",
 				   work_to_do);
-			xenvif_fatal_tx_err(vif);
+			xenvif_fatal_tx_err(queue->vif);
 			return -ENODATA;
 		}
 
@@ -805,10 +828,10 @@ static int xenvif_count_requests(struct xenvif *vif,
 		 * considered malicious.
 		 */
 		if (unlikely(slots >= fatal_skb_slots)) {
-			netdev_err(vif->dev,
+			netdev_err(queue->vif->dev,
 				   "Malicious frontend using %d slots, threshold %u\n",
 				   slots, fatal_skb_slots);
-			xenvif_fatal_tx_err(vif);
+			xenvif_fatal_tx_err(queue->vif);
 			return -E2BIG;
 		}
 
@@ -821,7 +844,7 @@ static int xenvif_count_requests(struct xenvif *vif,
 		 */
 		if (!drop_err && slots >= XEN_NETBK_LEGACY_SLOTS_MAX) {
 			if (net_ratelimit())
-				netdev_dbg(vif->dev,
+				netdev_dbg(queue->vif->dev,
 					   "Too many slots (%d) exceeding limit (%d), dropping packet\n",
 					   slots, XEN_NETBK_LEGACY_SLOTS_MAX);
 			drop_err = -E2BIG;
@@ -830,7 +853,7 @@ static int xenvif_count_requests(struct xenvif *vif,
 		if (drop_err)
 			txp = &dropped_tx;
 
-		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + slots),
+		memcpy(txp, RING_GET_REQUEST(&queue->tx, cons + slots),
 		       sizeof(*txp));
 
 		/* If the guest submitted a frame >= 64 KiB then
@@ -844,7 +867,7 @@ static int xenvif_count_requests(struct xenvif *vif,
 		 */
 		if (!drop_err && txp->size > first->size) {
 			if (net_ratelimit())
-				netdev_dbg(vif->dev,
+				netdev_dbg(queue->vif->dev,
 					   "Invalid tx request, slot size %u > remaining size %u\n",
 					   txp->size, first->size);
 			drop_err = -EIO;
@@ -854,9 +877,9 @@ static int xenvif_count_requests(struct xenvif *vif,
 		slots++;
 
 		if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
-			netdev_err(vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n",
+			netdev_err(queue->vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n",
 				 txp->offset, txp->size);
-			xenvif_fatal_tx_err(vif);
+			xenvif_fatal_tx_err(queue->vif);
 			return -EINVAL;
 		}
 
@@ -868,7 +891,7 @@ static int xenvif_count_requests(struct xenvif *vif,
 	} while (more_data);
 
 	if (drop_err) {
-		xenvif_tx_err(vif, first, cons + slots);
+		xenvif_tx_err(queue, first, cons + slots);
 		return drop_err;
 	}
 
@@ -882,17 +905,17 @@ struct xenvif_tx_cb {
 
 #define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb)
 
-static inline void xenvif_tx_create_map_op(struct xenvif *vif,
+static inline void xenvif_tx_create_map_op(struct xenvif_queue *queue,
 					  u16 pending_idx,
 					  struct xen_netif_tx_request *txp,
 					  struct gnttab_map_grant_ref *mop)
 {
-	vif->pages_to_map[mop-vif->tx_map_ops] = vif->mmap_pages[pending_idx];
-	gnttab_set_map_op(mop, idx_to_kaddr(vif, pending_idx),
+	queue->pages_to_map[mop-queue->tx_map_ops] = queue->mmap_pages[pending_idx];
+	gnttab_set_map_op(mop, idx_to_kaddr(queue, pending_idx),
 			  GNTMAP_host_map | GNTMAP_readonly,
-			  txp->gref, vif->domid);
+			  txp->gref, queue->vif->domid);
 
-	memcpy(&vif->pending_tx_info[pending_idx].req, txp,
+	memcpy(&queue->pending_tx_info[pending_idx].req, txp,
 	       sizeof(*txp));
 }
 
@@ -913,7 +936,7 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size)
 	return skb;
 }
 
-static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
+static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue,
 							struct sk_buff *skb,
 							struct xen_netif_tx_request *txp,
 							struct gnttab_map_grant_ref *gop)
@@ -940,9 +963,9 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
 
 	for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots;
 	     shinfo->nr_frags++, txp++, gop++) {
-		index = pending_index(vif->pending_cons++);
-		pending_idx = vif->pending_ring[index];
-		xenvif_tx_create_map_op(vif, pending_idx, txp, gop);
+		index = pending_index(queue->pending_cons++);
+		pending_idx = queue->pending_ring[index];
+		xenvif_tx_create_map_op(queue, pending_idx, txp, gop);
 		frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);
 	}
 
@@ -950,7 +973,7 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
 		struct sk_buff *nskb = xenvif_alloc_skb(0);
 		if (unlikely(nskb == NULL)) {
 			if (net_ratelimit())
-				netdev_err(vif->dev,
+				netdev_err(queue->vif->dev,
 					   "Can't allocate the frag_list skb.\n");
 			return NULL;
 		}
@@ -960,9 +983,9 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
 
 		for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow;
 		     shinfo->nr_frags++, txp++, gop++) {
-			index = pending_index(vif->pending_cons++);
-			pending_idx = vif->pending_ring[index];
-			xenvif_tx_create_map_op(vif, pending_idx, txp, gop);
+			index = pending_index(queue->pending_cons++);
+			pending_idx = queue->pending_ring[index];
+			xenvif_tx_create_map_op(queue, pending_idx, txp, gop);
 			frag_set_pending_idx(&frags[shinfo->nr_frags],
 					     pending_idx);
 		}
@@ -973,57 +996,68 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
 	return gop;
 }
 
-static inline void xenvif_grant_handle_set(struct xenvif *vif,
+static inline void xenvif_grant_handle_set(struct xenvif_queue *queue,
 					   u16 pending_idx,
 					   grant_handle_t handle)
 {
-	if (unlikely(vif->grant_tx_handle[pending_idx] !=
+	if (unlikely(queue->grant_tx_handle[pending_idx] !=
 		     NETBACK_INVALID_HANDLE)) {
-		netdev_err(vif->dev,
+		netdev_err(queue->vif->dev,
 			   "Trying to overwrite active handle! pending_idx: %x\n",
 			   pending_idx);
 		BUG();
 	}
-	vif->grant_tx_handle[pending_idx] = handle;
+	queue->grant_tx_handle[pending_idx] = handle;
 }
 
-static inline void xenvif_grant_handle_reset(struct xenvif *vif,
+static inline void xenvif_grant_handle_reset(struct xenvif_queue *queue,
 					     u16 pending_idx)
 {
-	if (unlikely(vif->grant_tx_handle[pending_idx] ==
+	if (unlikely(queue->grant_tx_handle[pending_idx] ==
 		     NETBACK_INVALID_HANDLE)) {
-		netdev_err(vif->dev,
+		netdev_err(queue->vif->dev,
 			   "Trying to unmap invalid handle! pending_idx: %x\n",
 			   pending_idx);
 		BUG();
 	}
-	vif->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE;
+	queue->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE;
 }
 
-static int xenvif_tx_check_gop(struct xenvif *vif,
+static int xenvif_tx_check_gop(struct xenvif_queue *queue,
 			       struct sk_buff *skb,
 			       struct gnttab_map_grant_ref **gopp_map,
 			       struct gnttab_copy **gopp_copy)
 {
 	struct gnttab_map_grant_ref *gop_map = *gopp_map;
 	u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;
+	/* This always points to the shinfo of the skb being checked, which
+	 * could be either the first or the one on the frag_list
+	 */
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	/* If this is non-NULL, we are currently checking the frag_list skb, and
+	 * this points to the shinfo of the first one
+	 */
+	struct skb_shared_info *first_shinfo = NULL;
 	int nr_frags = shinfo->nr_frags;
+	const bool sharedslot = nr_frags &&
+				frag_get_pending_idx(&shinfo->frags[0]) == pending_idx;
 	int i, err;
-	struct sk_buff *first_skb = NULL;
 
 	/* Check status of header. */
 	err = (*gopp_copy)->status;
-	(*gopp_copy)++;
 	if (unlikely(err)) {
 		if (net_ratelimit())
-			netdev_dbg(vif->dev,
+			netdev_dbg(queue->vif->dev,
 				   "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n",
 				   (*gopp_copy)->status,
 				   pending_idx,
 				   (*gopp_copy)->source.u.ref);
-		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);
+		/* The first frag might still have this slot mapped */
+		if (!sharedslot)
+			xenvif_idx_release(queue, pending_idx,
+					   XEN_NETIF_RSP_ERROR);
 	}
+	(*gopp_copy)++;
 
 check_frags:
 	for (i = 0; i < nr_frags; i++, gop_map++) {
@@ -1035,64 +1069,86 @@ check_frags:
 		newerr = gop_map->status;
 
 		if (likely(!newerr)) {
-			xenvif_grant_handle_set(vif,
+			xenvif_grant_handle_set(queue,
 						pending_idx,
 						gop_map->handle);
 			/* Had a previous error? Invalidate this fragment. */
-			if (unlikely(err))
-				xenvif_idx_unmap(vif, pending_idx);
+			if (unlikely(err)) {
+				xenvif_idx_unmap(queue, pending_idx);
+				/* If the mapping of the first frag was OK, but
+				 * the header's copy failed, and they are
+				 * sharing a slot, send an error
+				 */
+				if (i == 0 && sharedslot)
+					xenvif_idx_release(queue, pending_idx,
+							   XEN_NETIF_RSP_ERROR);
+				else
+					xenvif_idx_release(queue, pending_idx,
+							   XEN_NETIF_RSP_OKAY);
+			}
 			continue;
 		}
 
 		/* Error on this fragment: respond to client with an error. */
 		if (net_ratelimit())
-			netdev_dbg(vif->dev,
+			netdev_dbg(queue->vif->dev,
 				   "Grant map of %d. frag failed! status: %d pending_idx: %u ref: %u\n",
 				   i,
 				   gop_map->status,
 				   pending_idx,
 				   gop_map->ref);
-		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);
+
+		xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR);
 
 		/* Not the first error? Preceding frags already invalidated. */
 		if (err)
 			continue;
-		/* First error: invalidate preceding fragments. */
+
+		/* First error: if the header haven't shared a slot with the
+		 * first frag, release it as well.
+		 */
+		if (!sharedslot)
+			xenvif_idx_release(queue,
+					   XENVIF_TX_CB(skb)->pending_idx,
+					   XEN_NETIF_RSP_OKAY);
+
+		/* Invalidate preceding fragments of this skb. */
 		for (j = 0; j < i; j++) {
 			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
-			xenvif_idx_unmap(vif, pending_idx);
+			xenvif_idx_unmap(queue, pending_idx);
+			xenvif_idx_release(queue, pending_idx,
+					   XEN_NETIF_RSP_OKAY);
+		}
+
+		/* And if we found the error while checking the frag_list, unmap
+		 * the first skb's frags
+		 */
+		if (first_shinfo) {
+			for (j = 0; j < first_shinfo->nr_frags; j++) {
+				pending_idx = frag_get_pending_idx(&first_shinfo->frags[j]);
+				xenvif_idx_unmap(queue, pending_idx);
+				xenvif_idx_release(queue, pending_idx,
+						   XEN_NETIF_RSP_OKAY);
+			}
 		}
 
 		/* Remember the error: invalidate all subsequent fragments. */
 		err = newerr;
 	}
 
-	if (skb_has_frag_list(skb)) {
-		first_skb = skb;
-		skb = shinfo->frag_list;
-		shinfo = skb_shinfo(skb);
+	if (skb_has_frag_list(skb) && !first_shinfo) {
+		first_shinfo = skb_shinfo(skb);
+		shinfo = skb_shinfo(skb_shinfo(skb)->frag_list);
 		nr_frags = shinfo->nr_frags;
 
 		goto check_frags;
 	}
 
-	/* There was a mapping error in the frag_list skb. We have to unmap
-	 * the first skb's frags
-	 */
-	if (first_skb && err) {
-		int j;
-		shinfo = skb_shinfo(first_skb);
-		for (j = 0; j < shinfo->nr_frags; j++) {
-			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
-			xenvif_idx_unmap(vif, pending_idx);
-		}
-	}
-
 	*gopp_map = gop_map;
 	return err;
 }
 
-static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
+static void xenvif_fill_frags(struct xenvif_queue *queue, struct sk_buff *skb)
 {
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	int nr_frags = shinfo->nr_frags;
@@ -1110,23 +1166,23 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
 		/* If this is not the first frag, chain it to the previous*/
 		if (prev_pending_idx == INVALID_PENDING_IDX)
 			skb_shinfo(skb)->destructor_arg =
-				&callback_param(vif, pending_idx);
+				&callback_param(queue, pending_idx);
 		else
-			callback_param(vif, prev_pending_idx).ctx =
-				&callback_param(vif, pending_idx);
+			callback_param(queue, prev_pending_idx).ctx =
+				&callback_param(queue, pending_idx);
 
-		callback_param(vif, pending_idx).ctx = NULL;
+		callback_param(queue, pending_idx).ctx = NULL;
 		prev_pending_idx = pending_idx;
 
-		txp = &vif->pending_tx_info[pending_idx].req;
-		page = virt_to_page(idx_to_kaddr(vif, pending_idx));
+		txp = &queue->pending_tx_info[pending_idx].req;
+		page = virt_to_page(idx_to_kaddr(queue, pending_idx));
 		__skb_fill_page_desc(skb, i, page, txp->offset, txp->size);
 		skb->len += txp->size;
 		skb->data_len += txp->size;
 		skb->truesize += txp->size;
 
 		/* Take an extra reference to offset network stack's put_page */
-		get_page(vif->mmap_pages[pending_idx]);
+		get_page(queue->mmap_pages[pending_idx]);
 	}
 	/* FIXME: __skb_fill_page_desc set this to true because page->pfmemalloc
 	 * overlaps with "index", and "mapping" is not set. I think mapping
@@ -1136,33 +1192,33 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
 	skb->pfmemalloc	= false;
 }
 
-static int xenvif_get_extras(struct xenvif *vif,
+static int xenvif_get_extras(struct xenvif_queue *queue,
 				struct xen_netif_extra_info *extras,
 				int work_to_do)
 {
 	struct xen_netif_extra_info extra;
-	RING_IDX cons = vif->tx.req_cons;
+	RING_IDX cons = queue->tx.req_cons;
 
 	do {
 		if (unlikely(work_to_do-- <= 0)) {
-			netdev_err(vif->dev, "Missing extra info\n");
-			xenvif_fatal_tx_err(vif);
+			netdev_err(queue->vif->dev, "Missing extra info\n");
+			xenvif_fatal_tx_err(queue->vif);
 			return -EBADR;
 		}
 
-		memcpy(&extra, RING_GET_REQUEST(&vif->tx, cons),
+		memcpy(&extra, RING_GET_REQUEST(&queue->tx, cons),
 		       sizeof(extra));
 		if (unlikely(!extra.type ||
 			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
-			vif->tx.req_cons = ++cons;
-			netdev_err(vif->dev,
+			queue->tx.req_cons = ++cons;
+			netdev_err(queue->vif->dev,
 				   "Invalid extra type: %d\n", extra.type);
-			xenvif_fatal_tx_err(vif);
+			xenvif_fatal_tx_err(queue->vif);
 			return -EINVAL;
 		}
 
 		memcpy(&extras[extra.type - 1], &extra, sizeof(extra));
-		vif->tx.req_cons = ++cons;
+		queue->tx.req_cons = ++cons;
 	} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);
 
 	return work_to_do;
@@ -1197,7 +1253,7 @@ static int xenvif_set_skb_gso(struct xenvif *vif,
 	return 0;
 }
 
-static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
+static int checksum_setup(struct xenvif_queue *queue, struct sk_buff *skb)
 {
 	bool recalculate_partial_csum = false;
 
@@ -1207,7 +1263,7 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
 	 * recalculate the partial checksum.
 	 */
 	if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
-		vif->rx_gso_checksum_fixup++;
+		queue->stats.rx_gso_checksum_fixup++;
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		recalculate_partial_csum = true;
 	}
@@ -1219,31 +1275,31 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
 	return skb_checksum_setup(skb, recalculate_partial_csum);
 }
 
-static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
+static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size)
 {
 	u64 now = get_jiffies_64();
-	u64 next_credit = vif->credit_window_start +
-		msecs_to_jiffies(vif->credit_usec / 1000);
+	u64 next_credit = queue->credit_window_start +
+		msecs_to_jiffies(queue->credit_usec / 1000);
 
 	/* Timer could already be pending in rare cases. */
-	if (timer_pending(&vif->credit_timeout))
+	if (timer_pending(&queue->credit_timeout))
 		return true;
 
 	/* Passed the point where we can replenish credit? */
 	if (time_after_eq64(now, next_credit)) {
-		vif->credit_window_start = now;
-		tx_add_credit(vif);
+		queue->credit_window_start = now;
+		tx_add_credit(queue);
 	}
 
 	/* Still too big to send right now? Set a callback. */
-	if (size > vif->remaining_credit) {
-		vif->credit_timeout.data     =
-			(unsigned long)vif;
-		vif->credit_timeout.function =
+	if (size > queue->remaining_credit) {
+		queue->credit_timeout.data     =
+			(unsigned long)queue;
+		queue->credit_timeout.function =
 			tx_credit_callback;
-		mod_timer(&vif->credit_timeout,
+		mod_timer(&queue->credit_timeout,
 			  next_credit);
-		vif->credit_window_start = next_credit;
+		queue->credit_window_start = next_credit;
 
 		return true;
 	}
@@ -1251,16 +1307,16 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
 	return false;
 }
 
-static void xenvif_tx_build_gops(struct xenvif *vif,
+static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 				     int budget,
 				     unsigned *copy_ops,
 				     unsigned *map_ops)
 {
-	struct gnttab_map_grant_ref *gop = vif->tx_map_ops, *request_gop;
+	struct gnttab_map_grant_ref *gop = queue->tx_map_ops, *request_gop;
 	struct sk_buff *skb;
 	int ret;
 
-	while (skb_queue_len(&vif->tx_queue) < budget) {
+	while (skb_queue_len(&queue->tx_queue) < budget) {
 		struct xen_netif_tx_request txreq;
 		struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX];
 		struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1];
@@ -1270,69 +1326,69 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
 		unsigned int data_len;
 		pending_ring_idx_t index;
 
-		if (vif->tx.sring->req_prod - vif->tx.req_cons >
+		if (queue->tx.sring->req_prod - queue->tx.req_cons >
 		    XEN_NETIF_TX_RING_SIZE) {
-			netdev_err(vif->dev,
+			netdev_err(queue->vif->dev,
 				   "Impossible number of requests. "
 				   "req_prod %d, req_cons %d, size %ld\n",
-				   vif->tx.sring->req_prod, vif->tx.req_cons,
+				   queue->tx.sring->req_prod, queue->tx.req_cons,
 				   XEN_NETIF_TX_RING_SIZE);
-			xenvif_fatal_tx_err(vif);
+			xenvif_fatal_tx_err(queue->vif);
 			break;
 		}
 
-		work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx);
+		work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx);
 		if (!work_to_do)
 			break;
 
-		idx = vif->tx.req_cons;
+		idx = queue->tx.req_cons;
 		rmb(); /* Ensure that we see the request before we copy it. */
-		memcpy(&txreq, RING_GET_REQUEST(&vif->tx, idx), sizeof(txreq));
+		memcpy(&txreq, RING_GET_REQUEST(&queue->tx, idx), sizeof(txreq));
 
 		/* Credit-based scheduling. */
-		if (txreq.size > vif->remaining_credit &&
-		    tx_credit_exceeded(vif, txreq.size))
+		if (txreq.size > queue->remaining_credit &&
+		    tx_credit_exceeded(queue, txreq.size))
 			break;
 
-		vif->remaining_credit -= txreq.size;
+		queue->remaining_credit -= txreq.size;
 
 		work_to_do--;
-		vif->tx.req_cons = ++idx;
+		queue->tx.req_cons = ++idx;
 
 		memset(extras, 0, sizeof(extras));
 		if (txreq.flags & XEN_NETTXF_extra_info) {
-			work_to_do = xenvif_get_extras(vif, extras,
+			work_to_do = xenvif_get_extras(queue, extras,
 						       work_to_do);
-			idx = vif->tx.req_cons;
+			idx = queue->tx.req_cons;
 			if (unlikely(work_to_do < 0))
 				break;
 		}
 
-		ret = xenvif_count_requests(vif, &txreq, txfrags, work_to_do);
+		ret = xenvif_count_requests(queue, &txreq, txfrags, work_to_do);
 		if (unlikely(ret < 0))
 			break;
 
 		idx += ret;
 
 		if (unlikely(txreq.size < ETH_HLEN)) {
-			netdev_dbg(vif->dev,
+			netdev_dbg(queue->vif->dev,
 				   "Bad packet size: %d\n", txreq.size);
-			xenvif_tx_err(vif, &txreq, idx);
+			xenvif_tx_err(queue, &txreq, idx);
 			break;
 		}
 
 		/* No crossing a page as the payload mustn't fragment. */
 		if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) {
-			netdev_err(vif->dev,
+			netdev_err(queue->vif->dev,
 				   "txreq.offset: %x, size: %u, end: %lu\n",
 				   txreq.offset, txreq.size,
 				   (txreq.offset&~PAGE_MASK) + txreq.size);
-			xenvif_fatal_tx_err(vif);
+			xenvif_fatal_tx_err(queue->vif);
 			break;
 		}
 
-		index = pending_index(vif->pending_cons);
-		pending_idx = vif->pending_ring[index];
+		index = pending_index(queue->pending_cons);
+		pending_idx = queue->pending_ring[index];
 
 		data_len = (txreq.size > PKT_PROT_LEN &&
 			    ret < XEN_NETBK_LEGACY_SLOTS_MAX) ?
@@ -1340,9 +1396,9 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
 
 		skb = xenvif_alloc_skb(data_len);
 		if (unlikely(skb == NULL)) {
-			netdev_dbg(vif->dev,
+			netdev_dbg(queue->vif->dev,
 				   "Can't allocate a skb in start_xmit.\n");
-			xenvif_tx_err(vif, &txreq, idx);
+			xenvif_tx_err(queue, &txreq, idx);
 			break;
 		}
 
@@ -1350,7 +1406,7 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
 			struct xen_netif_extra_info *gso;
 			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
 
-			if (xenvif_set_skb_gso(vif, skb, gso)) {
+			if (xenvif_set_skb_gso(queue->vif, skb, gso)) {
 				/* Failure in xenvif_set_skb_gso is fatal. */
 				kfree_skb(skb);
 				break;
@@ -1360,18 +1416,18 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
 		XENVIF_TX_CB(skb)->pending_idx = pending_idx;
 
 		__skb_put(skb, data_len);
-		vif->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref;
-		vif->tx_copy_ops[*copy_ops].source.domid = vif->domid;
-		vif->tx_copy_ops[*copy_ops].source.offset = txreq.offset;
+		queue->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref;
+		queue->tx_copy_ops[*copy_ops].source.domid = queue->vif->domid;
+		queue->tx_copy_ops[*copy_ops].source.offset = txreq.offset;
 
-		vif->tx_copy_ops[*copy_ops].dest.u.gmfn =
+		queue->tx_copy_ops[*copy_ops].dest.u.gmfn =
 			virt_to_mfn(skb->data);
-		vif->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF;
-		vif->tx_copy_ops[*copy_ops].dest.offset =
+		queue->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF;
+		queue->tx_copy_ops[*copy_ops].dest.offset =
 			offset_in_page(skb->data);
 
-		vif->tx_copy_ops[*copy_ops].len = data_len;
-		vif->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref;
+		queue->tx_copy_ops[*copy_ops].len = data_len;
+		queue->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref;
 
 		(*copy_ops)++;
 
@@ -1380,42 +1436,42 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
 			skb_shinfo(skb)->nr_frags++;
 			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
 					     pending_idx);
-			xenvif_tx_create_map_op(vif, pending_idx, &txreq, gop);
+			xenvif_tx_create_map_op(queue, pending_idx, &txreq, gop);
 			gop++;
 		} else {
 			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
 					     INVALID_PENDING_IDX);
-			memcpy(&vif->pending_tx_info[pending_idx].req, &txreq,
+			memcpy(&queue->pending_tx_info[pending_idx].req, &txreq,
 			       sizeof(txreq));
 		}
 
-		vif->pending_cons++;
+		queue->pending_cons++;
 
-		request_gop = xenvif_get_requests(vif, skb, txfrags, gop);
+		request_gop = xenvif_get_requests(queue, skb, txfrags, gop);
 		if (request_gop == NULL) {
 			kfree_skb(skb);
-			xenvif_tx_err(vif, &txreq, idx);
+			xenvif_tx_err(queue, &txreq, idx);
 			break;
 		}
 		gop = request_gop;
 
-		__skb_queue_tail(&vif->tx_queue, skb);
+		__skb_queue_tail(&queue->tx_queue, skb);
 
-		vif->tx.req_cons = idx;
+		queue->tx.req_cons = idx;
 
-		if (((gop-vif->tx_map_ops) >= ARRAY_SIZE(vif->tx_map_ops)) ||
-		    (*copy_ops >= ARRAY_SIZE(vif->tx_copy_ops)))
+		if (((gop-queue->tx_map_ops) >= ARRAY_SIZE(queue->tx_map_ops)) ||
+		    (*copy_ops >= ARRAY_SIZE(queue->tx_copy_ops)))
 			break;
 	}
 
-	(*map_ops) = gop - vif->tx_map_ops;
+	(*map_ops) = gop - queue->tx_map_ops;
 	return;
 }
 
 /* Consolidate skb with a frag_list into a brand new one with local pages on
  * frags. Returns 0 or -ENOMEM if can't allocate new pages.
  */
-static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)
+static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *skb)
 {
 	unsigned int offset = skb_headlen(skb);
 	skb_frag_t frags[MAX_SKB_FRAGS];
@@ -1423,10 +1479,10 @@ static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)
 	struct ubuf_info *uarg;
 	struct sk_buff *nskb = skb_shinfo(skb)->frag_list;
 
-	vif->tx_zerocopy_sent += 2;
-	vif->tx_frag_overflow++;
+	queue->stats.tx_zerocopy_sent += 2;
+	queue->stats.tx_frag_overflow++;
 
-	xenvif_fill_frags(vif, nskb);
+	xenvif_fill_frags(queue, nskb);
 	/* Subtract frags size, we will correct it later */
 	skb->truesize -= skb->data_len;
 	skb->len += nskb->len;
@@ -1478,37 +1534,46 @@ static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)
 	return 0;
 }
 
-static int xenvif_tx_submit(struct xenvif *vif)
+static int xenvif_tx_submit(struct xenvif_queue *queue)
 {
-	struct gnttab_map_grant_ref *gop_map = vif->tx_map_ops;
-	struct gnttab_copy *gop_copy = vif->tx_copy_ops;
+	struct gnttab_map_grant_ref *gop_map = queue->tx_map_ops;
+	struct gnttab_copy *gop_copy = queue->tx_copy_ops;
 	struct sk_buff *skb;
 	int work_done = 0;
 
-	while ((skb = __skb_dequeue(&vif->tx_queue)) != NULL) {
+	while ((skb = __skb_dequeue(&queue->tx_queue)) != NULL) {
 		struct xen_netif_tx_request *txp;
 		u16 pending_idx;
 		unsigned data_len;
 
 		pending_idx = XENVIF_TX_CB(skb)->pending_idx;
-		txp = &vif->pending_tx_info[pending_idx].req;
+		txp = &queue->pending_tx_info[pending_idx].req;
 
 		/* Check the remap error code. */
-		if (unlikely(xenvif_tx_check_gop(vif, skb, &gop_map, &gop_copy))) {
+		if (unlikely(xenvif_tx_check_gop(queue, skb, &gop_map, &gop_copy))) {
+			/* If there was an error, xenvif_tx_check_gop is
+			 * expected to release all the frags which were mapped,
+			 * so kfree_skb shouldn't do it again
+			 */
 			skb_shinfo(skb)->nr_frags = 0;
+			if (skb_has_frag_list(skb)) {
+				struct sk_buff *nskb =
+						skb_shinfo(skb)->frag_list;
+				skb_shinfo(nskb)->nr_frags = 0;
+			}
 			kfree_skb(skb);
 			continue;
 		}
 
 		data_len = skb->len;
-		callback_param(vif, pending_idx).ctx = NULL;
+		callback_param(queue, pending_idx).ctx = NULL;
 		if (data_len < txp->size) {
 			/* Append the packet payload as a fragment. */
 			txp->offset += data_len;
 			txp->size -= data_len;
 		} else {
 			/* Schedule a response immediately. */
-			xenvif_idx_release(vif, pending_idx,
+			xenvif_idx_release(queue, pending_idx,
 					   XEN_NETIF_RSP_OKAY);
 		}
 
@@ -1517,12 +1582,12 @@ static int xenvif_tx_submit(struct xenvif *vif)
 		else if (txp->flags & XEN_NETTXF_data_validated)
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-		xenvif_fill_frags(vif, skb);
+		xenvif_fill_frags(queue, skb);
 
 		if (unlikely(skb_has_frag_list(skb))) {
-			if (xenvif_handle_frag_list(vif, skb)) {
+			if (xenvif_handle_frag_list(queue, skb)) {
 				if (net_ratelimit())
-					netdev_err(vif->dev,
+					netdev_err(queue->vif->dev,
 						   "Not enough memory to consolidate frag_list!\n");
 				skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
 				kfree_skb(skb);
@@ -1535,12 +1600,12 @@ static int xenvif_tx_submit(struct xenvif *vif)
 			__pskb_pull_tail(skb, target - skb_headlen(skb));
 		}
 
-		skb->dev      = vif->dev;
+		skb->dev      = queue->vif->dev;
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		skb_reset_network_header(skb);
 
-		if (checksum_setup(vif, skb)) {
-			netdev_dbg(vif->dev,
+		if (checksum_setup(queue, skb)) {
+			netdev_dbg(queue->vif->dev,
 				   "Can't setup checksum in net_tx_action\n");
 			/* We have to set this flag to trigger the callback */
 			if (skb_shinfo(skb)->destructor_arg)
@@ -1565,8 +1630,8 @@ static int xenvif_tx_submit(struct xenvif *vif)
 				DIV_ROUND_UP(skb->len - hdrlen, mss);
 		}
 
-		vif->dev->stats.rx_bytes += skb->len;
-		vif->dev->stats.rx_packets++;
+		queue->stats.rx_bytes += skb->len;
+		queue->stats.rx_packets++;
 
 		work_done++;
 
@@ -1577,7 +1642,7 @@ static int xenvif_tx_submit(struct xenvif *vif)
 		 */
 		if (skb_shinfo(skb)->destructor_arg) {
 			skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
-			vif->tx_zerocopy_sent++;
+			queue->stats.tx_zerocopy_sent++;
 		}
 
 		netif_receive_skb(skb);
@@ -1590,47 +1655,47 @@ void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success)
 {
 	unsigned long flags;
 	pending_ring_idx_t index;
-	struct xenvif *vif = ubuf_to_vif(ubuf);
+	struct xenvif_queue *queue = ubuf_to_queue(ubuf);
 
 	/* This is the only place where we grab this lock, to protect callbacks
 	 * from each other.
 	 */
-	spin_lock_irqsave(&vif->callback_lock, flags);
+	spin_lock_irqsave(&queue->callback_lock, flags);
 	do {
 		u16 pending_idx = ubuf->desc;
 		ubuf = (struct ubuf_info *) ubuf->ctx;
-		BUG_ON(vif->dealloc_prod - vif->dealloc_cons >=
+		BUG_ON(queue->dealloc_prod - queue->dealloc_cons >=
 			MAX_PENDING_REQS);
-		index = pending_index(vif->dealloc_prod);
-		vif->dealloc_ring[index] = pending_idx;
+		index = pending_index(queue->dealloc_prod);
+		queue->dealloc_ring[index] = pending_idx;
 		/* Sync with xenvif_tx_dealloc_action:
 		 * insert idx then incr producer.
 		 */
 		smp_wmb();
-		vif->dealloc_prod++;
+		queue->dealloc_prod++;
 	} while (ubuf);
-	wake_up(&vif->dealloc_wq);
-	spin_unlock_irqrestore(&vif->callback_lock, flags);
+	wake_up(&queue->dealloc_wq);
+	spin_unlock_irqrestore(&queue->callback_lock, flags);
 
 	if (likely(zerocopy_success))
-		vif->tx_zerocopy_success++;
+		queue->stats.tx_zerocopy_success++;
 	else
-		vif->tx_zerocopy_fail++;
+		queue->stats.tx_zerocopy_fail++;
 }
 
-static inline void xenvif_tx_dealloc_action(struct xenvif *vif)
+static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue)
 {
 	struct gnttab_unmap_grant_ref *gop;
 	pending_ring_idx_t dc, dp;
 	u16 pending_idx, pending_idx_release[MAX_PENDING_REQS];
 	unsigned int i = 0;
 
-	dc = vif->dealloc_cons;
-	gop = vif->tx_unmap_ops;
+	dc = queue->dealloc_cons;
+	gop = queue->tx_unmap_ops;
 
 	/* Free up any grants we have finished using */
 	do {
-		dp = vif->dealloc_prod;
+		dp = queue->dealloc_prod;
 
 		/* Ensure we see all indices enqueued by all
 		 * xenvif_zerocopy_callback().
@@ -1638,38 +1703,38 @@ static inline void xenvif_tx_dealloc_action(struct xenvif *vif)
 		smp_rmb();
 
 		while (dc != dp) {
-			BUG_ON(gop - vif->tx_unmap_ops > MAX_PENDING_REQS);
+			BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS);
 			pending_idx =
-				vif->dealloc_ring[pending_index(dc++)];
+				queue->dealloc_ring[pending_index(dc++)];
 
-			pending_idx_release[gop-vif->tx_unmap_ops] =
+			pending_idx_release[gop-queue->tx_unmap_ops] =
 				pending_idx;
-			vif->pages_to_unmap[gop-vif->tx_unmap_ops] =
-				vif->mmap_pages[pending_idx];
+			queue->pages_to_unmap[gop-queue->tx_unmap_ops] =
+				queue->mmap_pages[pending_idx];
 			gnttab_set_unmap_op(gop,
-					    idx_to_kaddr(vif, pending_idx),
+					    idx_to_kaddr(queue, pending_idx),
 					    GNTMAP_host_map,
-					    vif->grant_tx_handle[pending_idx]);
-			xenvif_grant_handle_reset(vif, pending_idx);
+					    queue->grant_tx_handle[pending_idx]);
+			xenvif_grant_handle_reset(queue, pending_idx);
 			++gop;
 		}
 
-	} while (dp != vif->dealloc_prod);
+	} while (dp != queue->dealloc_prod);
 
-	vif->dealloc_cons = dc;
+	queue->dealloc_cons = dc;
 
-	if (gop - vif->tx_unmap_ops > 0) {
+	if (gop - queue->tx_unmap_ops > 0) {
 		int ret;
-		ret = gnttab_unmap_refs(vif->tx_unmap_ops,
+		ret = gnttab_unmap_refs(queue->tx_unmap_ops,
 					NULL,
-					vif->pages_to_unmap,
-					gop - vif->tx_unmap_ops);
+					queue->pages_to_unmap,
+					gop - queue->tx_unmap_ops);
 		if (ret) {
-			netdev_err(vif->dev, "Unmap fail: nr_ops %tx ret %d\n",
-				   gop - vif->tx_unmap_ops, ret);
-			for (i = 0; i < gop - vif->tx_unmap_ops; ++i) {
+			netdev_err(queue->vif->dev, "Unmap fail: nr_ops %tx ret %d\n",
+				   gop - queue->tx_unmap_ops, ret);
+			for (i = 0; i < gop - queue->tx_unmap_ops; ++i) {
 				if (gop[i].status != GNTST_okay)
-					netdev_err(vif->dev,
+					netdev_err(queue->vif->dev,
 						   " host_addr: %llx handle: %x status: %d\n",
 						   gop[i].host_addr,
 						   gop[i].handle,
@@ -1679,91 +1744,91 @@ static inline void xenvif_tx_dealloc_action(struct xenvif *vif)
 		}
 	}
 
-	for (i = 0; i < gop - vif->tx_unmap_ops; ++i)
-		xenvif_idx_release(vif, pending_idx_release[i],
+	for (i = 0; i < gop - queue->tx_unmap_ops; ++i)
+		xenvif_idx_release(queue, pending_idx_release[i],
 				   XEN_NETIF_RSP_OKAY);
 }
 
 
 /* Called after netfront has transmitted */
-int xenvif_tx_action(struct xenvif *vif, int budget)
+int xenvif_tx_action(struct xenvif_queue *queue, int budget)
 {
 	unsigned nr_mops, nr_cops = 0;
 	int work_done, ret;
 
-	if (unlikely(!tx_work_todo(vif)))
+	if (unlikely(!tx_work_todo(queue)))
 		return 0;
 
-	xenvif_tx_build_gops(vif, budget, &nr_cops, &nr_mops);
+	xenvif_tx_build_gops(queue, budget, &nr_cops, &nr_mops);
 
 	if (nr_cops == 0)
 		return 0;
 
-	gnttab_batch_copy(vif->tx_copy_ops, nr_cops);
+	gnttab_batch_copy(queue->tx_copy_ops, nr_cops);
 	if (nr_mops != 0) {
-		ret = gnttab_map_refs(vif->tx_map_ops,
+		ret = gnttab_map_refs(queue->tx_map_ops,
 				      NULL,
-				      vif->pages_to_map,
+				      queue->pages_to_map,
 				      nr_mops);
 		BUG_ON(ret);
 	}
 
-	work_done = xenvif_tx_submit(vif);
+	work_done = xenvif_tx_submit(queue);
 
 	return work_done;
 }
 
-static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx,
+static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 			       u8 status)
 {
 	struct pending_tx_info *pending_tx_info;
 	pending_ring_idx_t index;
 	unsigned long flags;
 
-	pending_tx_info = &vif->pending_tx_info[pending_idx];
-	spin_lock_irqsave(&vif->response_lock, flags);
-	make_tx_response(vif, &pending_tx_info->req, status);
-	index = pending_index(vif->pending_prod);
-	vif->pending_ring[index] = pending_idx;
+	pending_tx_info = &queue->pending_tx_info[pending_idx];
+	spin_lock_irqsave(&queue->response_lock, flags);
+	make_tx_response(queue, &pending_tx_info->req, status);
+	index = pending_index(queue->pending_prod);
+	queue->pending_ring[index] = pending_idx;
 	/* TX shouldn't use the index before we give it back here */
 	mb();
-	vif->pending_prod++;
-	spin_unlock_irqrestore(&vif->response_lock, flags);
+	queue->pending_prod++;
+	spin_unlock_irqrestore(&queue->response_lock, flags);
 }
 
 
-static void make_tx_response(struct xenvif *vif,
+static void make_tx_response(struct xenvif_queue *queue,
 			     struct xen_netif_tx_request *txp,
 			     s8       st)
 {
-	RING_IDX i = vif->tx.rsp_prod_pvt;
+	RING_IDX i = queue->tx.rsp_prod_pvt;
 	struct xen_netif_tx_response *resp;
 	int notify;
 
-	resp = RING_GET_RESPONSE(&vif->tx, i);
+	resp = RING_GET_RESPONSE(&queue->tx, i);
 	resp->id     = txp->id;
 	resp->status = st;
 
 	if (txp->flags & XEN_NETTXF_extra_info)
-		RING_GET_RESPONSE(&vif->tx, ++i)->status = XEN_NETIF_RSP_NULL;
+		RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL;
 
-	vif->tx.rsp_prod_pvt = ++i;
-	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->tx, notify);
+	queue->tx.rsp_prod_pvt = ++i;
+	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
 	if (notify)
-		notify_remote_via_irq(vif->tx_irq);
+		notify_remote_via_irq(queue->tx_irq);
 }
 
-static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
+static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue,
 					     u16      id,
 					     s8       st,
 					     u16      offset,
 					     u16      size,
 					     u16      flags)
 {
-	RING_IDX i = vif->rx.rsp_prod_pvt;
+	RING_IDX i = queue->rx.rsp_prod_pvt;
 	struct xen_netif_rx_response *resp;
 
-	resp = RING_GET_RESPONSE(&vif->rx, i);
+	resp = RING_GET_RESPONSE(&queue->rx, i);
 	resp->offset     = offset;
 	resp->flags      = flags;
 	resp->id         = id;
@@ -1771,26 +1836,26 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
 	if (st < 0)
 		resp->status = (s16)st;
 
-	vif->rx.rsp_prod_pvt = ++i;
+	queue->rx.rsp_prod_pvt = ++i;
 
 	return resp;
 }
 
-void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx)
+void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx)
 {
 	int ret;
 	struct gnttab_unmap_grant_ref tx_unmap_op;
 
 	gnttab_set_unmap_op(&tx_unmap_op,
-			    idx_to_kaddr(vif, pending_idx),
+			    idx_to_kaddr(queue, pending_idx),
 			    GNTMAP_host_map,
-			    vif->grant_tx_handle[pending_idx]);
-	xenvif_grant_handle_reset(vif, pending_idx);
+			    queue->grant_tx_handle[pending_idx]);
+	xenvif_grant_handle_reset(queue, pending_idx);
 
 	ret = gnttab_unmap_refs(&tx_unmap_op, NULL,
-				&vif->mmap_pages[pending_idx], 1);
+				&queue->mmap_pages[pending_idx], 1);
 	if (ret) {
-		netdev_err(vif->dev,
+		netdev_err(queue->vif->dev,
 			   "Unmap fail: ret: %d pending_idx: %d host_addr: %llx handle: %x status: %d\n",
 			   ret,
 			   pending_idx,
@@ -1799,42 +1864,39 @@ void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx)
 			   tx_unmap_op.status);
 		BUG();
 	}
-
-	xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY);
 }
 
-static inline int rx_work_todo(struct xenvif *vif)
+static inline int rx_work_todo(struct xenvif_queue *queue)
 {
-	return (!skb_queue_empty(&vif->rx_queue) &&
-	       xenvif_rx_ring_slots_available(vif, vif->rx_last_skb_slots)) ||
-	       vif->rx_queue_purge;
+	return (!skb_queue_empty(&queue->rx_queue) &&
+	       xenvif_rx_ring_slots_available(queue, queue->rx_last_skb_slots)) ||
+	       queue->rx_queue_purge;
 }
 
-static inline int tx_work_todo(struct xenvif *vif)
+static inline int tx_work_todo(struct xenvif_queue *queue)
 {
-
-	if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->tx)))
+	if (likely(RING_HAS_UNCONSUMED_REQUESTS(&queue->tx)))
 		return 1;
 
 	return 0;
 }
 
-static inline bool tx_dealloc_work_todo(struct xenvif *vif)
+static inline bool tx_dealloc_work_todo(struct xenvif_queue *queue)
 {
-	return vif->dealloc_cons != vif->dealloc_prod;
+	return queue->dealloc_cons != queue->dealloc_prod;
 }
 
-void xenvif_unmap_frontend_rings(struct xenvif *vif)
+void xenvif_unmap_frontend_rings(struct xenvif_queue *queue)
 {
-	if (vif->tx.sring)
-		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
-					vif->tx.sring);
-	if (vif->rx.sring)
-		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
-					vif->rx.sring);
+	if (queue->tx.sring)
+		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif),
+					queue->tx.sring);
+	if (queue->rx.sring)
+		xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif),
+					queue->rx.sring);
 }
 
-int xenvif_map_frontend_rings(struct xenvif *vif,
+int xenvif_map_frontend_rings(struct xenvif_queue *queue,
 			      grant_ref_t tx_ring_ref,
 			      grant_ref_t rx_ring_ref)
 {
@@ -1844,85 +1906,78 @@ int xenvif_map_frontend_rings(struct xenvif *vif,
 
 	int err = -ENOMEM;
 
-	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
+	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif),
 				     tx_ring_ref, &addr);
 	if (err)
 		goto err;
 
 	txs = (struct xen_netif_tx_sring *)addr;
-	BACK_RING_INIT(&vif->tx, txs, PAGE_SIZE);
+	BACK_RING_INIT(&queue->tx, txs, PAGE_SIZE);
 
-	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
+	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif),
 				     rx_ring_ref, &addr);
 	if (err)
 		goto err;
 
 	rxs = (struct xen_netif_rx_sring *)addr;
-	BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE);
+	BACK_RING_INIT(&queue->rx, rxs, PAGE_SIZE);
 
 	return 0;
 
 err:
-	xenvif_unmap_frontend_rings(vif);
+	xenvif_unmap_frontend_rings(queue);
 	return err;
 }
 
-void xenvif_stop_queue(struct xenvif *vif)
+static void xenvif_start_queue(struct xenvif_queue *queue)
 {
-	if (!vif->can_queue)
-		return;
-
-	netif_stop_queue(vif->dev);
-}
-
-static void xenvif_start_queue(struct xenvif *vif)
-{
-	if (xenvif_schedulable(vif))
-		netif_wake_queue(vif->dev);
+	if (xenvif_schedulable(queue->vif))
+		xenvif_wake_queue(queue);
 }
 
 int xenvif_kthread_guest_rx(void *data)
 {
-	struct xenvif *vif = data;
+	struct xenvif_queue *queue = data;
 	struct sk_buff *skb;
 
 	while (!kthread_should_stop()) {
-		wait_event_interruptible(vif->wq,
-					 rx_work_todo(vif) ||
-					 vif->disabled ||
+		wait_event_interruptible(queue->wq,
+					 rx_work_todo(queue) ||
+					 queue->vif->disabled ||
 					 kthread_should_stop());
 
 		/* This frontend is found to be rogue, disable it in
 		 * kthread context. Currently this is only set when
 		 * netback finds out frontend sends malformed packet,
 		 * but we cannot disable the interface in softirq
-		 * context so we defer it here.
+		 * context so we defer it here, if this thread is
+		 * associated with queue 0.
 		 */
-		if (unlikely(vif->disabled && netif_carrier_ok(vif->dev)))
-			xenvif_carrier_off(vif);
+		if (unlikely(queue->vif->disabled && netif_carrier_ok(queue->vif->dev) && queue->id == 0))
+			xenvif_carrier_off(queue->vif);
 
 		if (kthread_should_stop())
 			break;
 
-		if (vif->rx_queue_purge) {
-			skb_queue_purge(&vif->rx_queue);
-			vif->rx_queue_purge = false;
+		if (queue->rx_queue_purge) {
+			skb_queue_purge(&queue->rx_queue);
+			queue->rx_queue_purge = false;
 		}
 
-		if (!skb_queue_empty(&vif->rx_queue))
-			xenvif_rx_action(vif);
+		if (!skb_queue_empty(&queue->rx_queue))
+			xenvif_rx_action(queue);
 
-		if (skb_queue_empty(&vif->rx_queue) &&
-		    netif_queue_stopped(vif->dev)) {
-			del_timer_sync(&vif->wake_queue);
-			xenvif_start_queue(vif);
+		if (skb_queue_empty(&queue->rx_queue) &&
+		    xenvif_queue_stopped(queue)) {
+			del_timer_sync(&queue->wake_queue);
+			xenvif_start_queue(queue);
 		}
 
 		cond_resched();
 	}
 
 	/* Bin any remaining skbs */
-	while ((skb = skb_dequeue(&vif->rx_queue)) != NULL)
+	while ((skb = skb_dequeue(&queue->rx_queue)) != NULL)
 		dev_kfree_skb(skb);
 
 	return 0;
@@ -1930,22 +1985,22 @@ int xenvif_kthread_guest_rx(void *data)
 
 int xenvif_dealloc_kthread(void *data)
 {
-	struct xenvif *vif = data;
+	struct xenvif_queue *queue = data;
 
 	while (!kthread_should_stop()) {
-		wait_event_interruptible(vif->dealloc_wq,
-					 tx_dealloc_work_todo(vif) ||
+		wait_event_interruptible(queue->dealloc_wq,
+					 tx_dealloc_work_todo(queue) ||
 					 kthread_should_stop());
 		if (kthread_should_stop())
 			break;
 
-		xenvif_tx_dealloc_action(vif);
+		xenvif_tx_dealloc_action(queue);
 		cond_resched();
 	}
 
 	/* Unmap anything remaining*/
-	if (tx_dealloc_work_todo(vif))
-		xenvif_tx_dealloc_action(vif);
+	if (tx_dealloc_work_todo(queue))
+		xenvif_tx_dealloc_action(queue);
 
 	return 0;
 }
@@ -1957,6 +2012,9 @@ static int __init netback_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
+	/* Allow as many queues as there are CPUs, by default */
+	xenvif_max_queues = num_online_cpus();
+
 	if (fatal_skb_slots < XEN_NETBK_LEGACY_SLOTS_MAX) {
 		pr_info("fatal_skb_slots too small (%d), bump it to XEN_NETBK_LEGACY_SLOTS_MAX (%d)\n",
 			fatal_skb_slots, XEN_NETBK_LEGACY_SLOTS_MAX);
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 7a206cffb06..3d85acd84ba 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -19,6 +19,8 @@
 */
 
 #include "common.h"
+#include <linux/vmalloc.h>
+#include <linux/rtnetlink.h>
 
 struct backend_info {
 	struct xenbus_device *dev;
@@ -34,8 +36,9 @@ struct backend_info {
 	u8 have_hotplug_status_watch:1;
 };
 
-static int connect_rings(struct backend_info *);
-static void connect(struct backend_info *);
+static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
+static void connect(struct backend_info *be);
+static int read_xenbus_vif_flags(struct backend_info *be);
 static void backend_create_xenvif(struct backend_info *be);
 static void unregister_hotplug_status_watch(struct backend_info *be);
 static void set_backend_state(struct backend_info *be,
@@ -157,6 +160,12 @@ static int netback_probe(struct xenbus_device *dev,
 	if (err)
 		pr_debug("Error writing feature-split-event-channels\n");
 
+	/* Multi-queue support: This is an optional feature. */
+	err = xenbus_printf(XBT_NIL, dev->nodename,
+			    "multi-queue-max-queues", "%u", xenvif_max_queues);
+	if (err)
+		pr_debug("Error writing multi-queue-max-queues\n");
+
 	err = xenbus_switch_state(dev, XenbusStateInitWait);
 	if (err)
 		goto fail;
@@ -485,10 +494,26 @@ static void connect(struct backend_info *be)
 {
 	int err;
 	struct xenbus_device *dev = be->dev;
+	unsigned long credit_bytes, credit_usec;
+	unsigned int queue_index;
+	unsigned int requested_num_queues;
+	struct xenvif_queue *queue;
 
-	err = connect_rings(be);
-	if (err)
+	/* Check whether the frontend requested multiple queues
+	 * and read the number requested.
+	 */
+	err = xenbus_scanf(XBT_NIL, dev->otherend,
+			   "multi-queue-num-queues",
+			   "%u", &requested_num_queues);
+	if (err < 0) {
+		requested_num_queues = 1; /* Fall back to single queue */
+	} else if (requested_num_queues > xenvif_max_queues) {
+		/* buggy or malicious guest */
+		xenbus_dev_fatal(dev, err,
+				 "guest requested %u queues, exceeding the maximum of %u.",
+				 requested_num_queues, xenvif_max_queues);
 		return;
+	}
 
 	err = xen_net_read_mac(dev, be->vif->fe_dev_addr);
 	if (err) {
@@ -496,9 +521,56 @@ static void connect(struct backend_info *be)
 		return;
 	}
 
-	xen_net_read_rate(dev, &be->vif->credit_bytes,
-			  &be->vif->credit_usec);
-	be->vif->remaining_credit = be->vif->credit_bytes;
+	xen_net_read_rate(dev, &credit_bytes, &credit_usec);
+	read_xenbus_vif_flags(be);
+
+	/* Use the number of queues requested by the frontend */
+	be->vif->queues = vzalloc(requested_num_queues *
+				  sizeof(struct xenvif_queue));
+	be->vif->num_queues = requested_num_queues;
+
+	for (queue_index = 0; queue_index < requested_num_queues; ++queue_index) {
+		queue = &be->vif->queues[queue_index];
+		queue->vif = be->vif;
+		queue->id = queue_index;
+		snprintf(queue->name, sizeof(queue->name), "%s-q%u",
+				be->vif->dev->name, queue->id);
+
+		err = xenvif_init_queue(queue);
+		if (err) {
+			/* xenvif_init_queue() cleans up after itself on
+			 * failure, but we need to clean up any previously
+			 * initialised queues. Set num_queues to i so that
+			 * earlier queues can be destroyed using the regular
+			 * disconnect logic.
+			 */
+			be->vif->num_queues = queue_index;
+			goto err;
+		}
+
+		queue->remaining_credit = credit_bytes;
+
+		err = connect_rings(be, queue);
+		if (err) {
+			/* connect_rings() cleans up after itself on failure,
+			 * but we need to clean up after xenvif_init_queue() here,
+			 * and also clean up any previously initialised queues.
+			 */
+			xenvif_deinit_queue(queue);
+			be->vif->num_queues = queue_index;
+			goto err;
+		}
+	}
+
+	/* Initialisation completed, tell core driver the number of
+	 * active queues.
+	 */
+	rtnl_lock();
+	netif_set_real_num_tx_queues(be->vif->dev, requested_num_queues);
+	netif_set_real_num_rx_queues(be->vif->dev, requested_num_queues);
+	rtnl_unlock();
+
+	xenvif_carrier_on(be->vif);
 
 	unregister_hotplug_status_watch(be);
 	err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
@@ -507,45 +579,107 @@ static void connect(struct backend_info *be)
 	if (!err)
 		be->have_hotplug_status_watch = 1;
 
-	netif_wake_queue(be->vif->dev);
+	netif_tx_wake_all_queues(be->vif->dev);
+
+	return;
+
+err:
+	if (be->vif->num_queues > 0)
+		xenvif_disconnect(be->vif); /* Clean up existing queues */
+	vfree(be->vif->queues);
+	be->vif->queues = NULL;
+	be->vif->num_queues = 0;
+	return;
 }
 
 
-static int connect_rings(struct backend_info *be)
+static int connect_rings(struct backend_info *be, struct xenvif_queue *queue)
 {
-	struct xenvif *vif = be->vif;
 	struct xenbus_device *dev = be->dev;
+	unsigned int num_queues = queue->vif->num_queues;
 	unsigned long tx_ring_ref, rx_ring_ref;
-	unsigned int tx_evtchn, rx_evtchn, rx_copy;
+	unsigned int tx_evtchn, rx_evtchn;
 	int err;
-	int val;
+	char *xspath;
+	size_t xspathsize;
+	const size_t xenstore_path_ext_size = 11; /* sufficient for "/queue-NNN" */
+
+	/* If the frontend requested 1 queue, or we have fallen back
+	 * to single queue due to lack of frontend support for multi-
+	 * queue, expect the remaining XenStore keys in the toplevel
+	 * directory. Otherwise, expect them in a subdirectory called
+	 * queue-N.
+	 */
+	if (num_queues == 1) {
+		xspath = kzalloc(strlen(dev->otherend) + 1, GFP_KERNEL);
+		if (!xspath) {
+			xenbus_dev_fatal(dev, -ENOMEM,
+					 "reading ring references");
+			return -ENOMEM;
+		}
+		strcpy(xspath, dev->otherend);
+	} else {
+		xspathsize = strlen(dev->otherend) + xenstore_path_ext_size;
+		xspath = kzalloc(xspathsize, GFP_KERNEL);
+		if (!xspath) {
+			xenbus_dev_fatal(dev, -ENOMEM,
+					 "reading ring references");
+			return -ENOMEM;
+		}
+		snprintf(xspath, xspathsize, "%s/queue-%u", dev->otherend,
+			 queue->id);
+	}
 
-	err = xenbus_gather(XBT_NIL, dev->otherend,
+	err = xenbus_gather(XBT_NIL, xspath,
 			    "tx-ring-ref", "%lu", &tx_ring_ref,
 			    "rx-ring-ref", "%lu", &rx_ring_ref, NULL);
 	if (err) {
 		xenbus_dev_fatal(dev, err,
 				 "reading %s/ring-ref",
-				 dev->otherend);
-		return err;
+				 xspath);
+		goto err;
 	}
 
 	/* Try split event channels first, then single event channel. */
-	err = xenbus_gather(XBT_NIL, dev->otherend,
+	err = xenbus_gather(XBT_NIL, xspath,
 			    "event-channel-tx", "%u", &tx_evtchn,
 			    "event-channel-rx", "%u", &rx_evtchn, NULL);
 	if (err < 0) {
-		err = xenbus_scanf(XBT_NIL, dev->otherend,
+		err = xenbus_scanf(XBT_NIL, xspath,
 				   "event-channel", "%u", &tx_evtchn);
 		if (err < 0) {
 			xenbus_dev_fatal(dev, err,
 					 "reading %s/event-channel(-tx/rx)",
-					 dev->otherend);
-			return err;
+					 xspath);
+			goto err;
 		}
 		rx_evtchn = tx_evtchn;
 	}
 
+	/* Map the shared frame, irq etc. */
+	err = xenvif_connect(queue, tx_ring_ref, rx_ring_ref,
+			     tx_evtchn, rx_evtchn);
+	if (err) {
+		xenbus_dev_fatal(dev, err,
+				 "mapping shared-frames %lu/%lu port tx %u rx %u",
+				 tx_ring_ref, rx_ring_ref,
+				 tx_evtchn, rx_evtchn);
+		goto err;
+	}
+
+	err = 0;
+err: /* Regular return falls through with err == 0 */
+	kfree(xspath);
+	return err;
+}
+
+static int read_xenbus_vif_flags(struct backend_info *be)
+{
+	struct xenvif *vif = be->vif;
+	struct xenbus_device *dev = be->dev;
+	unsigned int rx_copy;
+	int err, val;
+
 	err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u",
 			   &rx_copy);
 	if (err == -ENOENT) {
@@ -621,16 +755,6 @@ static int connect_rings(struct backend_info *be)
 		val = 0;
 	vif->ipv6_csum = !!val;
 
-	/* Map the shared frame, irq etc. */
-	err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref,
-			     tx_evtchn, rx_evtchn);
-	if (err) {
-		xenbus_dev_fatal(dev, err,
-				 "mapping shared-frames %lu/%lu port tx %u rx %u",
-				 tx_ring_ref, rx_ring_ref,
-				 tx_evtchn, rx_evtchn);
-		return err;
-	}
 	return 0;
 }
 
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 158b5e639fc..055222bae6e 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -57,6 +57,12 @@
 #include <xen/interface/memory.h>
 #include <xen/interface/grant_table.h>
 
+/* Module parameters */
+static unsigned int xennet_max_queues;
+module_param_named(max_queues, xennet_max_queues, uint, 0644);
+MODULE_PARM_DESC(max_queues,
+		 "Maximum number of queues per virtual interface");
+
 static const struct ethtool_ops xennet_ethtool_ops;
 
 struct netfront_cb {
@@ -73,6 +79,12 @@ struct netfront_cb {
 #define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
 #define TX_MAX_TARGET min_t(int, NET_TX_RING_SIZE, 256)
 
+/* Queue name is interface name with "-qNNN" appended */
+#define QUEUE_NAME_SIZE (IFNAMSIZ + 6)
+
+/* IRQ name is queue name with "-tx" or "-rx" appended */
+#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
+
 struct netfront_stats {
 	u64			rx_packets;
 	u64			tx_packets;
@@ -81,9 +93,12 @@ struct netfront_stats {
 	struct u64_stats_sync	syncp;
 };
 
-struct netfront_info {
-	struct list_head list;
-	struct net_device *netdev;
+struct netfront_info;
+
+struct netfront_queue {
+	unsigned int id; /* Queue ID, 0-based */
+	char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */
+	struct netfront_info *info;
 
 	struct napi_struct napi;
 
@@ -93,10 +108,8 @@ struct netfront_info {
 	unsigned int tx_evtchn, rx_evtchn;
 	unsigned int tx_irq, rx_irq;
 	/* Only used when split event channels support is enabled */
-	char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */
-	char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
-
-	struct xenbus_device *xbdev;
+	char tx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-tx */
+	char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */
 
 	spinlock_t   tx_lock;
 	struct xen_netif_tx_front_ring tx;
@@ -140,11 +153,21 @@ struct netfront_info {
 	unsigned long rx_pfn_array[NET_RX_RING_SIZE];
 	struct multicall_entry rx_mcl[NET_RX_RING_SIZE+1];
 	struct mmu_update rx_mmu[NET_RX_RING_SIZE];
+};
+
+struct netfront_info {
+	struct list_head list;
+	struct net_device *netdev;
+
+	struct xenbus_device *xbdev;
+
+	/* Multi-queue support */
+	struct netfront_queue *queues;
 
 	/* Statistics */
 	struct netfront_stats __percpu *stats;
 
-	unsigned long rx_gso_checksum_fixup;
+	atomic_t rx_gso_checksum_fixup;
 };
 
 struct netfront_rx_info {
@@ -187,21 +210,21 @@ static int xennet_rxidx(RING_IDX idx)
 	return idx & (NET_RX_RING_SIZE - 1);
 }
 
-static struct sk_buff *xennet_get_rx_skb(struct netfront_info *np,
+static struct sk_buff *xennet_get_rx_skb(struct netfront_queue *queue,
 					 RING_IDX ri)
 {
 	int i = xennet_rxidx(ri);
-	struct sk_buff *skb = np->rx_skbs[i];
-	np->rx_skbs[i] = NULL;
+	struct sk_buff *skb = queue->rx_skbs[i];
+	queue->rx_skbs[i] = NULL;
 	return skb;
 }
 
-static grant_ref_t xennet_get_rx_ref(struct netfront_info *np,
+static grant_ref_t xennet_get_rx_ref(struct netfront_queue *queue,
 					    RING_IDX ri)
 {
 	int i = xennet_rxidx(ri);
-	grant_ref_t ref = np->grant_rx_ref[i];
-	np->grant_rx_ref[i] = GRANT_INVALID_REF;
+	grant_ref_t ref = queue->grant_rx_ref[i];
+	queue->grant_rx_ref[i] = GRANT_INVALID_REF;
 	return ref;
 }
 
@@ -221,41 +244,40 @@ static bool xennet_can_sg(struct net_device *dev)
 
 static void rx_refill_timeout(unsigned long data)
 {
-	struct net_device *dev = (struct net_device *)data;
-	struct netfront_info *np = netdev_priv(dev);
-	napi_schedule(&np->napi);
+	struct netfront_queue *queue = (struct netfront_queue *)data;
+	napi_schedule(&queue->napi);
 }
 
-static int netfront_tx_slot_available(struct netfront_info *np)
+static int netfront_tx_slot_available(struct netfront_queue *queue)
 {
-	return (np->tx.req_prod_pvt - np->tx.rsp_cons) <
+	return (queue->tx.req_prod_pvt - queue->tx.rsp_cons) <
 		(TX_MAX_TARGET - MAX_SKB_FRAGS - 2);
 }
 
-static void xennet_maybe_wake_tx(struct net_device *dev)
+static void xennet_maybe_wake_tx(struct netfront_queue *queue)
 {
-	struct netfront_info *np = netdev_priv(dev);
+	struct net_device *dev = queue->info->netdev;
+	struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, queue->id);
 
-	if (unlikely(netif_queue_stopped(dev)) &&
-	    netfront_tx_slot_available(np) &&
+	if (unlikely(netif_tx_queue_stopped(dev_queue)) &&
+	    netfront_tx_slot_available(queue) &&
 	    likely(netif_running(dev)))
-		netif_wake_queue(dev);
+		netif_tx_wake_queue(netdev_get_tx_queue(dev, queue->id));
 }
 
-static void xennet_alloc_rx_buffers(struct net_device *dev)
+static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 {
 	unsigned short id;
-	struct netfront_info *np = netdev_priv(dev);
 	struct sk_buff *skb;
 	struct page *page;
 	int i, batch_target, notify;
-	RING_IDX req_prod = np->rx.req_prod_pvt;
+	RING_IDX req_prod = queue->rx.req_prod_pvt;
 	grant_ref_t ref;
 	unsigned long pfn;
 	void *vaddr;
 	struct xen_netif_rx_request *req;
 
-	if (unlikely(!netif_carrier_ok(dev)))
+	if (unlikely(!netif_carrier_ok(queue->info->netdev)))
 		return;
 
 	/*
@@ -264,9 +286,10 @@ static void xennet_alloc_rx_buffers(struct net_device *dev)
 	 * allocator, so should reduce the chance of failed allocation requests
 	 * both for ourself and for other kernel subsystems.
 	 */
-	batch_target = np->rx_target - (req_prod - np->rx.rsp_cons);
-	for (i = skb_queue_len(&np->rx_batch); i < batch_target; i++) {
-		skb = __netdev_alloc_skb(dev, RX_COPY_THRESHOLD + NET_IP_ALIGN,
+	batch_target = queue->rx_target - (req_prod - queue->rx.rsp_cons);
+	for (i = skb_queue_len(&queue->rx_batch); i < batch_target; i++) {
+		skb = __netdev_alloc_skb(queue->info->netdev,
+					 RX_COPY_THRESHOLD + NET_IP_ALIGN,
 					 GFP_ATOMIC | __GFP_NOWARN);
 		if (unlikely(!skb))
 			goto no_skb;
@@ -279,7 +302,7 @@ static void xennet_alloc_rx_buffers(struct net_device *dev)
 			kfree_skb(skb);
 no_skb:
 			/* Could not allocate any skbuffs. Try again later. */
-			mod_timer(&np->rx_refill_timer,
+			mod_timer(&queue->rx_refill_timer,
 				  jiffies + (HZ/10));
 
 			/* Any skbuffs queued for refill? Force them out. */
@@ -289,44 +312,44 @@ no_skb:
 		}
 
 		skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
-		__skb_queue_tail(&np->rx_batch, skb);
+		__skb_queue_tail(&queue->rx_batch, skb);
 	}
 
 	/* Is the batch large enough to be worthwhile? */
-	if (i < (np->rx_target/2)) {
-		if (req_prod > np->rx.sring->req_prod)
+	if (i < (queue->rx_target/2)) {
+		if (req_prod > queue->rx.sring->req_prod)
 			goto push;
 		return;
 	}
 
 	/* Adjust our fill target if we risked running out of buffers. */
-	if (((req_prod - np->rx.sring->rsp_prod) < (np->rx_target / 4)) &&
-	    ((np->rx_target *= 2) > np->rx_max_target))
-		np->rx_target = np->rx_max_target;
+	if (((req_prod - queue->rx.sring->rsp_prod) < (queue->rx_target / 4)) &&
+	    ((queue->rx_target *= 2) > queue->rx_max_target))
+		queue->rx_target = queue->rx_max_target;
 
  refill:
 	for (i = 0; ; i++) {
-		skb = __skb_dequeue(&np->rx_batch);
+		skb = __skb_dequeue(&queue->rx_batch);
 		if (skb == NULL)
 			break;
 
-		skb->dev = dev;
+		skb->dev = queue->info->netdev;
 
 		id = xennet_rxidx(req_prod + i);
 
-		BUG_ON(np->rx_skbs[id]);
-		np->rx_skbs[id] = skb;
+		BUG_ON(queue->rx_skbs[id]);
+		queue->rx_skbs[id] = skb;
 
-		ref = gnttab_claim_grant_reference(&np->gref_rx_head);
+		ref = gnttab_claim_grant_reference(&queue->gref_rx_head);
 		BUG_ON((signed short)ref < 0);
-		np->grant_rx_ref[id] = ref;
+		queue->grant_rx_ref[id] = ref;
 
 		pfn = page_to_pfn(skb_frag_page(&skb_shinfo(skb)->frags[0]));
 		vaddr = page_address(skb_frag_page(&skb_shinfo(skb)->frags[0]));
 
-		req = RING_GET_REQUEST(&np->rx, req_prod + i);
+		req = RING_GET_REQUEST(&queue->rx, req_prod + i);
 		gnttab_grant_foreign_access_ref(ref,
-						np->xbdev->otherend_id,
+						queue->info->xbdev->otherend_id,
 						pfn_to_mfn(pfn),
 						0);
 
@@ -337,72 +360,77 @@ no_skb:
 	wmb();		/* barrier so backend seens requests */
 
 	/* Above is a suitable barrier to ensure backend will see requests. */
-	np->rx.req_prod_pvt = req_prod + i;
+	queue->rx.req_prod_pvt = req_prod + i;
  push:
-	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->rx, notify);
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->rx, notify);
 	if (notify)
-		notify_remote_via_irq(np->rx_irq);
+		notify_remote_via_irq(queue->rx_irq);
 }
 
 static int xennet_open(struct net_device *dev)
 {
 	struct netfront_info *np = netdev_priv(dev);
-
-	napi_enable(&np->napi);
-
-	spin_lock_bh(&np->rx_lock);
-	if (netif_carrier_ok(dev)) {
-		xennet_alloc_rx_buffers(dev);
-		np->rx.sring->rsp_event = np->rx.rsp_cons + 1;
-		if (RING_HAS_UNCONSUMED_RESPONSES(&np->rx))
-			napi_schedule(&np->napi);
+	unsigned int num_queues = dev->real_num_tx_queues;
+	unsigned int i = 0;
+	struct netfront_queue *queue = NULL;
+
+	for (i = 0; i < num_queues; ++i) {
+		queue = &np->queues[i];
+		napi_enable(&queue->napi);
+
+		spin_lock_bh(&queue->rx_lock);
+		if (netif_carrier_ok(dev)) {
+			xennet_alloc_rx_buffers(queue);
+			queue->rx.sring->rsp_event = queue->rx.rsp_cons + 1;
+			if (RING_HAS_UNCONSUMED_RESPONSES(&queue->rx))
+				napi_schedule(&queue->napi);
+		}
+		spin_unlock_bh(&queue->rx_lock);
 	}
-	spin_unlock_bh(&np->rx_lock);
 
-	netif_start_queue(dev);
+	netif_tx_start_all_queues(dev);
 
 	return 0;
 }
 
-static void xennet_tx_buf_gc(struct net_device *dev)
+static void xennet_tx_buf_gc(struct netfront_queue *queue)
 {
 	RING_IDX cons, prod;
 	unsigned short id;
-	struct netfront_info *np = netdev_priv(dev);
 	struct sk_buff *skb;
 
-	BUG_ON(!netif_carrier_ok(dev));
+	BUG_ON(!netif_carrier_ok(queue->info->netdev));
 
 	do {
-		prod = np->tx.sring->rsp_prod;
+		prod = queue->tx.sring->rsp_prod;
 		rmb(); /* Ensure we see responses up to 'rp'. */
 
-		for (cons = np->tx.rsp_cons; cons != prod; cons++) {
+		for (cons = queue->tx.rsp_cons; cons != prod; cons++) {
 			struct xen_netif_tx_response *txrsp;
 
-			txrsp = RING_GET_RESPONSE(&np->tx, cons);
+			txrsp = RING_GET_RESPONSE(&queue->tx, cons);
 			if (txrsp->status == XEN_NETIF_RSP_NULL)
 				continue;
 
 			id  = txrsp->id;
-			skb = np->tx_skbs[id].skb;
+			skb = queue->tx_skbs[id].skb;
 			if (unlikely(gnttab_query_foreign_access(
-				np->grant_tx_ref[id]) != 0)) {
+				queue->grant_tx_ref[id]) != 0)) {
 				pr_alert("%s: warning -- grant still in use by backend domain\n",
 					 __func__);
 				BUG();
 			}
 			gnttab_end_foreign_access_ref(
-				np->grant_tx_ref[id], GNTMAP_readonly);
+				queue->grant_tx_ref[id], GNTMAP_readonly);
 			gnttab_release_grant_reference(
-				&np->gref_tx_head, np->grant_tx_ref[id]);
-			np->grant_tx_ref[id] = GRANT_INVALID_REF;
-			np->grant_tx_page[id] = NULL;
-			add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, id);
+				&queue->gref_tx_head, queue->grant_tx_ref[id]);
+			queue->grant_tx_ref[id] = GRANT_INVALID_REF;
+			queue->grant_tx_page[id] = NULL;
+			add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id);
 			dev_kfree_skb_irq(skb);
 		}
 
-		np->tx.rsp_cons = prod;
+		queue->tx.rsp_cons = prod;
 
 		/*
 		 * Set a new event, then check for race with update of tx_cons.
@@ -412,21 +440,20 @@ static void xennet_tx_buf_gc(struct net_device *dev)
 		 * data is outstanding: in such cases notification from Xen is
 		 * likely to be the only kick that we'll get.
 		 */
-		np->tx.sring->rsp_event =
-			prod + ((np->tx.sring->req_prod - prod) >> 1) + 1;
+		queue->tx.sring->rsp_event =
+			prod + ((queue->tx.sring->req_prod - prod) >> 1) + 1;
 		mb();		/* update shared area */
-	} while ((cons == prod) && (prod != np->tx.sring->rsp_prod));
+	} while ((cons == prod) && (prod != queue->tx.sring->rsp_prod));
 
-	xennet_maybe_wake_tx(dev);
+	xennet_maybe_wake_tx(queue);
 }
 
-static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
+static void xennet_make_frags(struct sk_buff *skb, struct netfront_queue *queue,
 			      struct xen_netif_tx_request *tx)
 {
-	struct netfront_info *np = netdev_priv(dev);
 	char *data = skb->data;
 	unsigned long mfn;
-	RING_IDX prod = np->tx.req_prod_pvt;
+	RING_IDX prod = queue->tx.req_prod_pvt;
 	int frags = skb_shinfo(skb)->nr_frags;
 	unsigned int offset = offset_in_page(data);
 	unsigned int len = skb_headlen(skb);
@@ -443,19 +470,19 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 		data += tx->size;
 		offset = 0;
 
-		id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
-		np->tx_skbs[id].skb = skb_get(skb);
-		tx = RING_GET_REQUEST(&np->tx, prod++);
+		id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
+		queue->tx_skbs[id].skb = skb_get(skb);
+		tx = RING_GET_REQUEST(&queue->tx, prod++);
 		tx->id = id;
-		ref = gnttab_claim_grant_reference(&np->gref_tx_head);
+		ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 		BUG_ON((signed short)ref < 0);
 
 		mfn = virt_to_mfn(data);
-		gnttab_grant_foreign_access_ref(ref, np->xbdev->otherend_id,
+		gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
 						mfn, GNTMAP_readonly);
 
-		np->grant_tx_page[id] = virt_to_page(data);
-		tx->gref = np->grant_tx_ref[id] = ref;
+		queue->grant_tx_page[id] = virt_to_page(data);
+		tx->gref = queue->grant_tx_ref[id] = ref;
 		tx->offset = offset;
 		tx->size = len;
 		tx->flags = 0;
@@ -487,21 +514,21 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 
 			tx->flags |= XEN_NETTXF_more_data;
 
-			id = get_id_from_freelist(&np->tx_skb_freelist,
-						  np->tx_skbs);
-			np->tx_skbs[id].skb = skb_get(skb);
-			tx = RING_GET_REQUEST(&np->tx, prod++);
+			id = get_id_from_freelist(&queue->tx_skb_freelist,
+						  queue->tx_skbs);
+			queue->tx_skbs[id].skb = skb_get(skb);
+			tx = RING_GET_REQUEST(&queue->tx, prod++);
 			tx->id = id;
-			ref = gnttab_claim_grant_reference(&np->gref_tx_head);
+			ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 			BUG_ON((signed short)ref < 0);
 
 			mfn = pfn_to_mfn(page_to_pfn(page));
 			gnttab_grant_foreign_access_ref(ref,
-							np->xbdev->otherend_id,
+							queue->info->xbdev->otherend_id,
 							mfn, GNTMAP_readonly);
 
-			np->grant_tx_page[id] = page;
-			tx->gref = np->grant_tx_ref[id] = ref;
+			queue->grant_tx_page[id] = page;
+			tx->gref = queue->grant_tx_ref[id] = ref;
 			tx->offset = offset;
 			tx->size = bytes;
 			tx->flags = 0;
@@ -518,7 +545,7 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	np->tx.req_prod_pvt = prod;
+	queue->tx.req_prod_pvt = prod;
 }
 
 /*
@@ -544,6 +571,24 @@ static int xennet_count_skb_frag_slots(struct sk_buff *skb)
 	return pages;
 }
 
+static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
+			       void *accel_priv, select_queue_fallback_t fallback)
+{
+	unsigned int num_queues = dev->real_num_tx_queues;
+	u32 hash;
+	u16 queue_idx;
+
+	/* First, check if there is only one queue */
+	if (num_queues == 1) {
+		queue_idx = 0;
+	} else {
+		hash = skb_get_hash(skb);
+		queue_idx = hash % num_queues;
+	}
+
+	return queue_idx;
+}
+
 static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	unsigned short id;
@@ -559,6 +604,16 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int offset = offset_in_page(data);
 	unsigned int len = skb_headlen(skb);
 	unsigned long flags;
+	struct netfront_queue *queue = NULL;
+	unsigned int num_queues = dev->real_num_tx_queues;
+	u16 queue_index;
+
+	/* Drop the packet if no queues are set up */
+	if (num_queues < 1)
+		goto drop;
+	/* Determine which queue to transmit this SKB on */
+	queue_index = skb_get_queue_mapping(skb);
+	queue = &np->queues[queue_index];
 
 	/* If skb->len is too big for wire format, drop skb and alert
 	 * user about misconfiguration.
@@ -578,30 +633,30 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 	}
 
-	spin_lock_irqsave(&np->tx_lock, flags);
+	spin_lock_irqsave(&queue->tx_lock, flags);
 
 	if (unlikely(!netif_carrier_ok(dev) ||
 		     (slots > 1 && !xennet_can_sg(dev)) ||
 		     netif_needs_gso(skb, netif_skb_features(skb)))) {
-		spin_unlock_irqrestore(&np->tx_lock, flags);
+		spin_unlock_irqrestore(&queue->tx_lock, flags);
 		goto drop;
 	}
 
-	i = np->tx.req_prod_pvt;
+	i = queue->tx.req_prod_pvt;
 
-	id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
-	np->tx_skbs[id].skb = skb;
+	id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
+	queue->tx_skbs[id].skb = skb;
 
-	tx = RING_GET_REQUEST(&np->tx, i);
+	tx = RING_GET_REQUEST(&queue->tx, i);
 
 	tx->id   = id;
-	ref = gnttab_claim_grant_reference(&np->gref_tx_head);
+	ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 	BUG_ON((signed short)ref < 0);
 	mfn = virt_to_mfn(data);
 	gnttab_grant_foreign_access_ref(
-		ref, np->xbdev->otherend_id, mfn, GNTMAP_readonly);
-	np->grant_tx_page[id] = virt_to_page(data);
-	tx->gref = np->grant_tx_ref[id] = ref;
+		ref, queue->info->xbdev->otherend_id, mfn, GNTMAP_readonly);
+	queue->grant_tx_page[id] = virt_to_page(data);
+	tx->gref = queue->grant_tx_ref[id] = ref;
 	tx->offset = offset;
 	tx->size = len;
 
@@ -617,7 +672,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		struct xen_netif_extra_info *gso;
 
 		gso = (struct xen_netif_extra_info *)
-			RING_GET_REQUEST(&np->tx, ++i);
+			RING_GET_REQUEST(&queue->tx, ++i);
 
 		tx->flags |= XEN_NETTXF_extra_info;
 
@@ -632,14 +687,14 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		gso->flags = 0;
 	}
 
-	np->tx.req_prod_pvt = i + 1;
+	queue->tx.req_prod_pvt = i + 1;
 
-	xennet_make_frags(skb, dev, tx);
+	xennet_make_frags(skb, queue, tx);
 	tx->size = skb->len;
 
-	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->tx, notify);
+	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify);
 	if (notify)
-		notify_remote_via_irq(np->tx_irq);
+		notify_remote_via_irq(queue->tx_irq);
 
 	u64_stats_update_begin(&stats->syncp);
 	stats->tx_bytes += skb->len;
@@ -647,12 +702,12 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	u64_stats_update_end(&stats->syncp);
 
 	/* Note: It is not safe to access skb after xennet_tx_buf_gc()! */
-	xennet_tx_buf_gc(dev);
+	xennet_tx_buf_gc(queue);
 
-	if (!netfront_tx_slot_available(np))
-		netif_stop_queue(dev);
+	if (!netfront_tx_slot_available(queue))
+		netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
 
-	spin_unlock_irqrestore(&np->tx_lock, flags);
+	spin_unlock_irqrestore(&queue->tx_lock, flags);
 
 	return NETDEV_TX_OK;
 
@@ -665,32 +720,38 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 static int xennet_close(struct net_device *dev)
 {
 	struct netfront_info *np = netdev_priv(dev);
-	netif_stop_queue(np->netdev);
-	napi_disable(&np->napi);
+	unsigned int num_queues = dev->real_num_tx_queues;
+	unsigned int i;
+	struct netfront_queue *queue;
+	netif_tx_stop_all_queues(np->netdev);
+	for (i = 0; i < num_queues; ++i) {
+		queue = &np->queues[i];
+		napi_disable(&queue->napi);
+	}
 	return 0;
 }
 
-static void xennet_move_rx_slot(struct netfront_info *np, struct sk_buff *skb,
+static void xennet_move_rx_slot(struct netfront_queue *queue, struct sk_buff *skb,
 				grant_ref_t ref)
 {
-	int new = xennet_rxidx(np->rx.req_prod_pvt);
-
-	BUG_ON(np->rx_skbs[new]);
-	np->rx_skbs[new] = skb;
-	np->grant_rx_ref[new] = ref;
-	RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->id = new;
-	RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->gref = ref;
-	np->rx.req_prod_pvt++;
+	int new = xennet_rxidx(queue->rx.req_prod_pvt);
+
+	BUG_ON(queue->rx_skbs[new]);
+	queue->rx_skbs[new] = skb;
+	queue->grant_rx_ref[new] = ref;
+	RING_GET_REQUEST(&queue->rx, queue->rx.req_prod_pvt)->id = new;
+	RING_GET_REQUEST(&queue->rx, queue->rx.req_prod_pvt)->gref = ref;
+	queue->rx.req_prod_pvt++;
 }
 
-static int xennet_get_extras(struct netfront_info *np,
+static int xennet_get_extras(struct netfront_queue *queue,
 			     struct xen_netif_extra_info *extras,
 			     RING_IDX rp)
 
 {
 	struct xen_netif_extra_info *extra;
-	struct device *dev = &np->netdev->dev;
-	RING_IDX cons = np->rx.rsp_cons;
+	struct device *dev = &queue->info->netdev->dev;
+	RING_IDX cons = queue->rx.rsp_cons;
 	int err = 0;
 
 	do {
@@ -705,7 +766,7 @@ static int xennet_get_extras(struct netfront_info *np,
 		}
 
 		extra = (struct xen_netif_extra_info *)
-			RING_GET_RESPONSE(&np->rx, ++cons);
+			RING_GET_RESPONSE(&queue->rx, ++cons);
 
 		if (unlikely(!extra->type ||
 			     extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
@@ -718,33 +779,33 @@ static int xennet_get_extras(struct netfront_info *np,
 			       sizeof(*extra));
 		}
 
-		skb = xennet_get_rx_skb(np, cons);
-		ref = xennet_get_rx_ref(np, cons);
-		xennet_move_rx_slot(np, skb, ref);
+		skb = xennet_get_rx_skb(queue, cons);
+		ref = xennet_get_rx_ref(queue, cons);
+		xennet_move_rx_slot(queue, skb, ref);
 	} while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE);
 
-	np->rx.rsp_cons = cons;
+	queue->rx.rsp_cons = cons;
 	return err;
 }
 
-static int xennet_get_responses(struct netfront_info *np,
+static int xennet_get_responses(struct netfront_queue *queue,
 				struct netfront_rx_info *rinfo, RING_IDX rp,
 				struct sk_buff_head *list)
 {
 	struct xen_netif_rx_response *rx = &rinfo->rx;
 	struct xen_netif_extra_info *extras = rinfo->extras;
-	struct device *dev = &np->netdev->dev;
-	RING_IDX cons = np->rx.rsp_cons;
-	struct sk_buff *skb = xennet_get_rx_skb(np, cons);
-	grant_ref_t ref = xennet_get_rx_ref(np, cons);
+	struct device *dev = &queue->info->netdev->dev;
+	RING_IDX cons = queue->rx.rsp_cons;
+	struct sk_buff *skb = xennet_get_rx_skb(queue, cons);
+	grant_ref_t ref = xennet_get_rx_ref(queue, cons);
 	int max = MAX_SKB_FRAGS + (rx->status <= RX_COPY_THRESHOLD);
 	int slots = 1;
 	int err = 0;
 	unsigned long ret;
 
 	if (rx->flags & XEN_NETRXF_extra_info) {
-		err = xennet_get_extras(np, extras, rp);
-		cons = np->rx.rsp_cons;
+		err = xennet_get_extras(queue, extras, rp);
+		cons = queue->rx.rsp_cons;
 	}
 
 	for (;;) {
@@ -753,7 +814,7 @@ static int xennet_get_responses(struct netfront_info *np,
 			if (net_ratelimit())
 				dev_warn(dev, "rx->offset: %x, size: %u\n",
 					 rx->offset, rx->status);
-			xennet_move_rx_slot(np, skb, ref);
+			xennet_move_rx_slot(queue, skb, ref);
 			err = -EINVAL;
 			goto next;
 		}
@@ -774,7 +835,7 @@ static int xennet_get_responses(struct netfront_info *np,
 		ret = gnttab_end_foreign_access_ref(ref, 0);
 		BUG_ON(!ret);
 
-		gnttab_release_grant_reference(&np->gref_rx_head, ref);
+		gnttab_release_grant_reference(&queue->gref_rx_head, ref);
 
 		__skb_queue_tail(list, skb);
 
@@ -789,9 +850,9 @@ next:
 			break;
 		}
 
-		rx = RING_GET_RESPONSE(&np->rx, cons + slots);
-		skb = xennet_get_rx_skb(np, cons + slots);
-		ref = xennet_get_rx_ref(np, cons + slots);
+		rx = RING_GET_RESPONSE(&queue->rx, cons + slots);
+		skb = xennet_get_rx_skb(queue, cons + slots);
+		ref = xennet_get_rx_ref(queue, cons + slots);
 		slots++;
 	}
 
@@ -802,7 +863,7 @@ next:
 	}
 
 	if (unlikely(err))
-		np->rx.rsp_cons = cons + slots;
+		queue->rx.rsp_cons = cons + slots;
 
 	return err;
 }
@@ -836,17 +897,17 @@ static int xennet_set_skb_gso(struct sk_buff *skb,
 	return 0;
 }
 
-static RING_IDX xennet_fill_frags(struct netfront_info *np,
+static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 				  struct sk_buff *skb,
 				  struct sk_buff_head *list)
 {
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
-	RING_IDX cons = np->rx.rsp_cons;
+	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *nskb;
 
 	while ((nskb = __skb_dequeue(list))) {
 		struct xen_netif_rx_response *rx =
-			RING_GET_RESPONSE(&np->rx, ++cons);
+			RING_GET_RESPONSE(&queue->rx, ++cons);
 		skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
 
 		if (shinfo->nr_frags == MAX_SKB_FRAGS) {
@@ -879,7 +940,7 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
 	 */
 	if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
 		struct netfront_info *np = netdev_priv(dev);
-		np->rx_gso_checksum_fixup++;
+		atomic_inc(&np->rx_gso_checksum_fixup);
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		recalculate_partial_csum = true;
 	}
@@ -891,11 +952,10 @@ static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
 	return skb_checksum_setup(skb, recalculate_partial_csum);
 }
 
-static int handle_incoming_queue(struct net_device *dev,
+static int handle_incoming_queue(struct netfront_queue *queue,
 				 struct sk_buff_head *rxq)
 {
-	struct netfront_info *np = netdev_priv(dev);
-	struct netfront_stats *stats = this_cpu_ptr(np->stats);
+	struct netfront_stats *stats = this_cpu_ptr(queue->info->stats);
 	int packets_dropped = 0;
 	struct sk_buff *skb;
 
@@ -906,13 +966,13 @@ static int handle_incoming_queue(struct net_device *dev,
 			__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 
 		/* Ethernet work: Delayed to here as it peeks the header. */
-		skb->protocol = eth_type_trans(skb, dev);
+		skb->protocol = eth_type_trans(skb, queue->info->netdev);
 		skb_reset_network_header(skb);
 
-		if (checksum_setup(dev, skb)) {
+		if (checksum_setup(queue->info->netdev, skb)) {
 			kfree_skb(skb);
 			packets_dropped++;
-			dev->stats.rx_errors++;
+			queue->info->netdev->stats.rx_errors++;
 			continue;
 		}
 
@@ -922,7 +982,7 @@ static int handle_incoming_queue(struct net_device *dev,
 		u64_stats_update_end(&stats->syncp);
 
 		/* Pass it up. */
-		napi_gro_receive(&np->napi, skb);
+		napi_gro_receive(&queue->napi, skb);
 	}
 
 	return packets_dropped;
@@ -930,8 +990,8 @@ static int handle_incoming_queue(struct net_device *dev,
 
 static int xennet_poll(struct napi_struct *napi, int budget)
 {
-	struct netfront_info *np = container_of(napi, struct netfront_info, napi);
-	struct net_device *dev = np->netdev;
+	struct netfront_queue *queue = container_of(napi, struct netfront_queue, napi);
+	struct net_device *dev = queue->info->netdev;
 	struct sk_buff *skb;
 	struct netfront_rx_info rinfo;
 	struct xen_netif_rx_response *rx = &rinfo.rx;
@@ -944,29 +1004,29 @@ static int xennet_poll(struct napi_struct *napi, int budget)
 	unsigned long flags;
 	int err;
 
-	spin_lock(&np->rx_lock);
+	spin_lock(&queue->rx_lock);
 
 	skb_queue_head_init(&rxq);
 	skb_queue_head_init(&errq);
 	skb_queue_head_init(&tmpq);
 
-	rp = np->rx.sring->rsp_prod;
+	rp = queue->rx.sring->rsp_prod;
 	rmb(); /* Ensure we see queued responses up to 'rp'. */
 
-	i = np->rx.rsp_cons;
+	i = queue->rx.rsp_cons;
 	work_done = 0;
 	while ((i != rp) && (work_done < budget)) {
-		memcpy(rx, RING_GET_RESPONSE(&np->rx, i), sizeof(*rx));
+		memcpy(rx, RING_GET_RESPONSE(&queue->rx, i), sizeof(*rx));
 		memset(extras, 0, sizeof(rinfo.extras));
 
-		err = xennet_get_responses(np, &rinfo, rp, &tmpq);
+		err = xennet_get_responses(queue, &rinfo, rp, &tmpq);
 
 		if (unlikely(err)) {
 err:
 			while ((skb = __skb_dequeue(&tmpq)))
 				__skb_queue_tail(&errq, skb);
 			dev->stats.rx_errors++;
-			i = np->rx.rsp_cons;
+			i = queue->rx.rsp_cons;
 			continue;
 		}
 
@@ -978,7 +1038,7 @@ err:
 
 			if (unlikely(xennet_set_skb_gso(skb, gso))) {
 				__skb_queue_head(&tmpq, skb);
-				np->rx.rsp_cons += skb_queue_len(&tmpq);
+				queue->rx.rsp_cons += skb_queue_len(&tmpq);
 				goto err;
 			}
 		}
@@ -992,7 +1052,7 @@ err:
 		skb->data_len = rx->status;
 		skb->len += rx->status;
 
-		i = xennet_fill_frags(np, skb, &tmpq);
+		i = xennet_fill_frags(queue, skb, &tmpq);
 
 		if (rx->flags & XEN_NETRXF_csum_blank)
 			skb->ip_summed = CHECKSUM_PARTIAL;
@@ -1001,22 +1061,22 @@ err:
 
 		__skb_queue_tail(&rxq, skb);
 
-		np->rx.rsp_cons = ++i;
+		queue->rx.rsp_cons = ++i;
 		work_done++;
 	}
 
 	__skb_queue_purge(&errq);
 
-	work_done -= handle_incoming_queue(dev, &rxq);
+	work_done -= handle_incoming_queue(queue, &rxq);
 
 	/* If we get a callback with very few responses, reduce fill target. */
 	/* NB. Note exponential increase, linear decrease. */
-	if (((np->rx.req_prod_pvt - np->rx.sring->rsp_prod) >
-	     ((3*np->rx_target) / 4)) &&
-	    (--np->rx_target < np->rx_min_target))
-		np->rx_target = np->rx_min_target;
+	if (((queue->rx.req_prod_pvt - queue->rx.sring->rsp_prod) >
+	     ((3*queue->rx_target) / 4)) &&
+	    (--queue->rx_target < queue->rx_min_target))
+		queue->rx_target = queue->rx_min_target;
 
-	xennet_alloc_rx_buffers(dev);
+	xennet_alloc_rx_buffers(queue);
 
 	if (work_done < budget) {
 		int more_to_do = 0;
@@ -1025,14 +1085,14 @@ err:
 
 		local_irq_save(flags);
 
-		RING_FINAL_CHECK_FOR_RESPONSES(&np->rx, more_to_do);
+		RING_FINAL_CHECK_FOR_RESPONSES(&queue->rx, more_to_do);
 		if (!more_to_do)
 			__napi_complete(napi);
 
 		local_irq_restore(flags);
 	}
 
-	spin_unlock(&np->rx_lock);
+	spin_unlock(&queue->rx_lock);
 
 	return work_done;
 }
@@ -1080,43 +1140,43 @@ static struct rtnl_link_stats64 *xennet_get_stats64(struct net_device *dev,
 	return tot;
 }
 
-static void xennet_release_tx_bufs(struct netfront_info *np)
+static void xennet_release_tx_bufs(struct netfront_queue *queue)
 {
 	struct sk_buff *skb;
 	int i;
 
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
 		/* Skip over entries which are actually freelist references */
-		if (skb_entry_is_link(&np->tx_skbs[i]))
+		if (skb_entry_is_link(&queue->tx_skbs[i]))
 			continue;
 
-		skb = np->tx_skbs[i].skb;
-		get_page(np->grant_tx_page[i]);
-		gnttab_end_foreign_access(np->grant_tx_ref[i],
+		skb = queue->tx_skbs[i].skb;
+		get_page(queue->grant_tx_page[i]);
+		gnttab_end_foreign_access(queue->grant_tx_ref[i],
 					  GNTMAP_readonly,
-					  (unsigned long)page_address(np->grant_tx_page[i]));
-		np->grant_tx_page[i] = NULL;
-		np->grant_tx_ref[i] = GRANT_INVALID_REF;
-		add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, i);
+					  (unsigned long)page_address(queue->grant_tx_page[i]));
+		queue->grant_tx_page[i] = NULL;
+		queue->grant_tx_ref[i] = GRANT_INVALID_REF;
+		add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, i);
 		dev_kfree_skb_irq(skb);
 	}
 }
 
-static void xennet_release_rx_bufs(struct netfront_info *np)
+static void xennet_release_rx_bufs(struct netfront_queue *queue)
 {
 	int id, ref;
 
-	spin_lock_bh(&np->rx_lock);
+	spin_lock_bh(&queue->rx_lock);
 
 	for (id = 0; id < NET_RX_RING_SIZE; id++) {
 		struct sk_buff *skb;
 		struct page *page;
 
-		skb = np->rx_skbs[id];
+		skb = queue->rx_skbs[id];
 		if (!skb)
 			continue;
 
-		ref = np->grant_rx_ref[id];
+		ref = queue->grant_rx_ref[id];
 		if (ref == GRANT_INVALID_REF)
 			continue;
 
@@ -1128,21 +1188,28 @@ static void xennet_release_rx_bufs(struct netfront_info *np)
 		get_page(page);
 		gnttab_end_foreign_access(ref, 0,
 					  (unsigned long)page_address(page));
-		np->grant_rx_ref[id] = GRANT_INVALID_REF;
+		queue->grant_rx_ref[id] = GRANT_INVALID_REF;
 
 		kfree_skb(skb);
 	}
 
-	spin_unlock_bh(&np->rx_lock);
+	spin_unlock_bh(&queue->rx_lock);
 }
 
 static void xennet_uninit(struct net_device *dev)
 {
 	struct netfront_info *np = netdev_priv(dev);
-	xennet_release_tx_bufs(np);
-	xennet_release_rx_bufs(np);
-	gnttab_free_grant_references(np->gref_tx_head);
-	gnttab_free_grant_references(np->gref_rx_head);
+	unsigned int num_queues = dev->real_num_tx_queues;
+	struct netfront_queue *queue;
+	unsigned int i;
+
+	for (i = 0; i < num_queues; ++i) {
+		queue = &np->queues[i];
+		xennet_release_tx_bufs(queue);
+		xennet_release_rx_bufs(queue);
+		gnttab_free_grant_references(queue->gref_tx_head);
+		gnttab_free_grant_references(queue->gref_rx_head);
+	}
 }
 
 static netdev_features_t xennet_fix_features(struct net_device *dev,
@@ -1203,25 +1270,24 @@ static int xennet_set_features(struct net_device *dev,
 
 static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id)
 {
-	struct netfront_info *np = dev_id;
-	struct net_device *dev = np->netdev;
+	struct netfront_queue *queue = dev_id;
 	unsigned long flags;
 
-	spin_lock_irqsave(&np->tx_lock, flags);
-	xennet_tx_buf_gc(dev);
-	spin_unlock_irqrestore(&np->tx_lock, flags);
+	spin_lock_irqsave(&queue->tx_lock, flags);
+	xennet_tx_buf_gc(queue);
+	spin_unlock_irqrestore(&queue->tx_lock, flags);
 
 	return IRQ_HANDLED;
 }
 
 static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id)
 {
-	struct netfront_info *np = dev_id;
-	struct net_device *dev = np->netdev;
+	struct netfront_queue *queue = dev_id;
+	struct net_device *dev = queue->info->netdev;
 
 	if (likely(netif_carrier_ok(dev) &&
-		   RING_HAS_UNCONSUMED_RESPONSES(&np->rx)))
-			napi_schedule(&np->napi);
+		   RING_HAS_UNCONSUMED_RESPONSES(&queue->rx)))
+		napi_schedule(&queue->napi);
 
 	return IRQ_HANDLED;
 }
@@ -1236,7 +1302,12 @@ static irqreturn_t xennet_interrupt(int irq, void *dev_id)
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void xennet_poll_controller(struct net_device *dev)
 {
-	xennet_interrupt(0, dev);
+	/* Poll each queue */
+	struct netfront_info *info = netdev_priv(dev);
+	unsigned int num_queues = dev->real_num_tx_queues;
+	unsigned int i;
+	for (i = 0; i < num_queues; ++i)
+		xennet_interrupt(0, &info->queues[i]);
 }
 #endif
 
@@ -1251,6 +1322,7 @@ static const struct net_device_ops xennet_netdev_ops = {
 	.ndo_validate_addr   = eth_validate_addr,
 	.ndo_fix_features    = xennet_fix_features,
 	.ndo_set_features    = xennet_set_features,
+	.ndo_select_queue    = xennet_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = xennet_poll_controller,
 #endif
@@ -1258,66 +1330,30 @@ static const struct net_device_ops xennet_netdev_ops = {
 
 static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 {
-	int i, err;
+	int err;
 	struct net_device *netdev;
 	struct netfront_info *np;
 
-	netdev = alloc_etherdev(sizeof(struct netfront_info));
+	netdev = alloc_etherdev_mq(sizeof(struct netfront_info), xennet_max_queues);
 	if (!netdev)
 		return ERR_PTR(-ENOMEM);
 
 	np                   = netdev_priv(netdev);
 	np->xbdev            = dev;
 
-	spin_lock_init(&np->tx_lock);
-	spin_lock_init(&np->rx_lock);
-
-	skb_queue_head_init(&np->rx_batch);
-	np->rx_target     = RX_DFL_MIN_TARGET;
-	np->rx_min_target = RX_DFL_MIN_TARGET;
-	np->rx_max_target = RX_MAX_TARGET;
-
-	init_timer(&np->rx_refill_timer);
-	np->rx_refill_timer.data = (unsigned long)netdev;
-	np->rx_refill_timer.function = rx_refill_timeout;
+	/* No need to use rtnl_lock() before the call below as it
+	 * happens before register_netdev().
+	 */
+	netif_set_real_num_tx_queues(netdev, 0);
+	np->queues = NULL;
 
 	err = -ENOMEM;
 	np->stats = netdev_alloc_pcpu_stats(struct netfront_stats);
 	if (np->stats == NULL)
 		goto exit;
 
-	/* Initialise tx_skbs as a free chain containing every entry. */
-	np->tx_skb_freelist = 0;
-	for (i = 0; i < NET_TX_RING_SIZE; i++) {
-		skb_entry_set_link(&np->tx_skbs[i], i+1);
-		np->grant_tx_ref[i] = GRANT_INVALID_REF;
-		np->grant_tx_page[i] = NULL;
-	}
-
-	/* Clear out rx_skbs */
-	for (i = 0; i < NET_RX_RING_SIZE; i++) {
-		np->rx_skbs[i] = NULL;
-		np->grant_rx_ref[i] = GRANT_INVALID_REF;
-	}
-
-	/* A grant for every tx ring slot */
-	if (gnttab_alloc_grant_references(TX_MAX_TARGET,
-					  &np->gref_tx_head) < 0) {
-		pr_alert("can't alloc tx grant refs\n");
-		err = -ENOMEM;
-		goto exit_free_stats;
-	}
-	/* A grant for every rx ring slot */
-	if (gnttab_alloc_grant_references(RX_MAX_TARGET,
-					  &np->gref_rx_head) < 0) {
-		pr_alert("can't alloc rx grant refs\n");
-		err = -ENOMEM;
-		goto exit_free_tx;
-	}
-
 	netdev->netdev_ops	= &xennet_netdev_ops;
 
-	netif_napi_add(netdev, &np->napi, xennet_poll, 64);
 	netdev->features        = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 				  NETIF_F_GSO_ROBUST;
 	netdev->hw_features	= NETIF_F_SG |
@@ -1332,7 +1368,7 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
          */
 	netdev->features |= netdev->hw_features;
 
-	SET_ETHTOOL_OPS(netdev, &xennet_ethtool_ops);
+	netdev->ethtool_ops = &xennet_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->dev);
 
 	netif_set_gso_max_size(netdev, XEN_NETIF_MAX_TX_SIZE - MAX_TCP_HEADER);
@@ -1343,10 +1379,6 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 
 	return netdev;
 
- exit_free_tx:
-	gnttab_free_grant_references(np->gref_tx_head);
- exit_free_stats:
-	free_percpu(np->stats);
  exit:
 	free_netdev(netdev);
 	return ERR_PTR(err);
@@ -1404,30 +1436,34 @@ static void xennet_end_access(int ref, void *page)
 
 static void xennet_disconnect_backend(struct netfront_info *info)
 {
-	/* Stop old i/f to prevent errors whilst we rebuild the state. */
-	spin_lock_bh(&info->rx_lock);
-	spin_lock_irq(&info->tx_lock);
+	unsigned int i = 0;
+	unsigned int num_queues = info->netdev->real_num_tx_queues;
+
 	netif_carrier_off(info->netdev);
-	spin_unlock_irq(&info->tx_lock);
-	spin_unlock_bh(&info->rx_lock);
 
-	if (info->tx_irq && (info->tx_irq == info->rx_irq))
-		unbind_from_irqhandler(info->tx_irq, info);
-	if (info->tx_irq && (info->tx_irq != info->rx_irq)) {
-		unbind_from_irqhandler(info->tx_irq, info);
-		unbind_from_irqhandler(info->rx_irq, info);
-	}
-	info->tx_evtchn = info->rx_evtchn = 0;
-	info->tx_irq = info->rx_irq = 0;
+	for (i = 0; i < num_queues; ++i) {
+		struct netfront_queue *queue = &info->queues[i];
+
+		if (queue->tx_irq && (queue->tx_irq == queue->rx_irq))
+			unbind_from_irqhandler(queue->tx_irq, queue);
+		if (queue->tx_irq && (queue->tx_irq != queue->rx_irq)) {
+			unbind_from_irqhandler(queue->tx_irq, queue);
+			unbind_from_irqhandler(queue->rx_irq, queue);
+		}
+		queue->tx_evtchn = queue->rx_evtchn = 0;
+		queue->tx_irq = queue->rx_irq = 0;
 
-	/* End access and free the pages */
-	xennet_end_access(info->tx_ring_ref, info->tx.sring);
-	xennet_end_access(info->rx_ring_ref, info->rx.sring);
+		napi_synchronize(&queue->napi);
 
-	info->tx_ring_ref = GRANT_INVALID_REF;
-	info->rx_ring_ref = GRANT_INVALID_REF;
-	info->tx.sring = NULL;
-	info->rx.sring = NULL;
+		/* End access and free the pages */
+		xennet_end_access(queue->tx_ring_ref, queue->tx.sring);
+		xennet_end_access(queue->rx_ring_ref, queue->rx.sring);
+
+		queue->tx_ring_ref = GRANT_INVALID_REF;
+		queue->rx_ring_ref = GRANT_INVALID_REF;
+		queue->tx.sring = NULL;
+		queue->rx.sring = NULL;
+	}
 }
 
 /**
@@ -1468,100 +1504,86 @@ static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[])
 	return 0;
 }
 
-static int setup_netfront_single(struct netfront_info *info)
+static int setup_netfront_single(struct netfront_queue *queue)
 {
 	int err;
 
-	err = xenbus_alloc_evtchn(info->xbdev, &info->tx_evtchn);
+	err = xenbus_alloc_evtchn(queue->info->xbdev, &queue->tx_evtchn);
 	if (err < 0)
 		goto fail;
 
-	err = bind_evtchn_to_irqhandler(info->tx_evtchn,
+	err = bind_evtchn_to_irqhandler(queue->tx_evtchn,
 					xennet_interrupt,
-					0, info->netdev->name, info);
+					0, queue->info->netdev->name, queue);
 	if (err < 0)
 		goto bind_fail;
-	info->rx_evtchn = info->tx_evtchn;
-	info->rx_irq = info->tx_irq = err;
+	queue->rx_evtchn = queue->tx_evtchn;
+	queue->rx_irq = queue->tx_irq = err;
 
 	return 0;
 
 bind_fail:
-	xenbus_free_evtchn(info->xbdev, info->tx_evtchn);
-	info->tx_evtchn = 0;
+	xenbus_free_evtchn(queue->info->xbdev, queue->tx_evtchn);
+	queue->tx_evtchn = 0;
 fail:
 	return err;
 }
 
-static int setup_netfront_split(struct netfront_info *info)
+static int setup_netfront_split(struct netfront_queue *queue)
 {
 	int err;
 
-	err = xenbus_alloc_evtchn(info->xbdev, &info->tx_evtchn);
+	err = xenbus_alloc_evtchn(queue->info->xbdev, &queue->tx_evtchn);
 	if (err < 0)
 		goto fail;
-	err = xenbus_alloc_evtchn(info->xbdev, &info->rx_evtchn);
+	err = xenbus_alloc_evtchn(queue->info->xbdev, &queue->rx_evtchn);
 	if (err < 0)
 		goto alloc_rx_evtchn_fail;
 
-	snprintf(info->tx_irq_name, sizeof(info->tx_irq_name),
-		 "%s-tx", info->netdev->name);
-	err = bind_evtchn_to_irqhandler(info->tx_evtchn,
+	snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name),
+		 "%s-tx", queue->name);
+	err = bind_evtchn_to_irqhandler(queue->tx_evtchn,
 					xennet_tx_interrupt,
-					0, info->tx_irq_name, info);
+					0, queue->tx_irq_name, queue);
 	if (err < 0)
 		goto bind_tx_fail;
-	info->tx_irq = err;
+	queue->tx_irq = err;
 
-	snprintf(info->rx_irq_name, sizeof(info->rx_irq_name),
-		 "%s-rx", info->netdev->name);
-	err = bind_evtchn_to_irqhandler(info->rx_evtchn,
+	snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name),
+		 "%s-rx", queue->name);
+	err = bind_evtchn_to_irqhandler(queue->rx_evtchn,
 					xennet_rx_interrupt,
-					0, info->rx_irq_name, info);
+					0, queue->rx_irq_name, queue);
 	if (err < 0)
 		goto bind_rx_fail;
-	info->rx_irq = err;
+	queue->rx_irq = err;
 
 	return 0;
 
 bind_rx_fail:
-	unbind_from_irqhandler(info->tx_irq, info);
-	info->tx_irq = 0;
+	unbind_from_irqhandler(queue->tx_irq, queue);
+	queue->tx_irq = 0;
 bind_tx_fail:
-	xenbus_free_evtchn(info->xbdev, info->rx_evtchn);
-	info->rx_evtchn = 0;
+	xenbus_free_evtchn(queue->info->xbdev, queue->rx_evtchn);
+	queue->rx_evtchn = 0;
 alloc_rx_evtchn_fail:
-	xenbus_free_evtchn(info->xbdev, info->tx_evtchn);
-	info->tx_evtchn = 0;
+	xenbus_free_evtchn(queue->info->xbdev, queue->tx_evtchn);
+	queue->tx_evtchn = 0;
 fail:
 	return err;
 }
 
-static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info)
+static int setup_netfront(struct xenbus_device *dev,
+			struct netfront_queue *queue, unsigned int feature_split_evtchn)
 {
 	struct xen_netif_tx_sring *txs;
 	struct xen_netif_rx_sring *rxs;
 	int err;
-	struct net_device *netdev = info->netdev;
-	unsigned int feature_split_evtchn;
 
-	info->tx_ring_ref = GRANT_INVALID_REF;
-	info->rx_ring_ref = GRANT_INVALID_REF;
-	info->rx.sring = NULL;
-	info->tx.sring = NULL;
-	netdev->irq = 0;
-
-	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
-			   "feature-split-event-channels", "%u",
-			   &feature_split_evtchn);
-	if (err < 0)
-		feature_split_evtchn = 0;
-
-	err = xen_net_read_mac(dev, netdev->dev_addr);
-	if (err) {
-		xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
-		goto fail;
-	}
+	queue->tx_ring_ref = GRANT_INVALID_REF;
+	queue->rx_ring_ref = GRANT_INVALID_REF;
+	queue->rx.sring = NULL;
+	queue->tx.sring = NULL;
 
 	txs = (struct xen_netif_tx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH);
 	if (!txs) {
@@ -1570,13 +1592,13 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info)
 		goto fail;
 	}
 	SHARED_RING_INIT(txs);
-	FRONT_RING_INIT(&info->tx, txs, PAGE_SIZE);
+	FRONT_RING_INIT(&queue->tx, txs, PAGE_SIZE);
 
 	err = xenbus_grant_ring(dev, virt_to_mfn(txs));
 	if (err < 0)
 		goto grant_tx_ring_fail;
+	queue->tx_ring_ref = err;
 
-	info->tx_ring_ref = err;
 	rxs = (struct xen_netif_rx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH);
 	if (!rxs) {
 		err = -ENOMEM;
@@ -1584,21 +1606,21 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info)
 		goto alloc_rx_ring_fail;
 	}
 	SHARED_RING_INIT(rxs);
-	FRONT_RING_INIT(&info->rx, rxs, PAGE_SIZE);
+	FRONT_RING_INIT(&queue->rx, rxs, PAGE_SIZE);
 
 	err = xenbus_grant_ring(dev, virt_to_mfn(rxs));
 	if (err < 0)
 		goto grant_rx_ring_fail;
-	info->rx_ring_ref = err;
+	queue->rx_ring_ref = err;
 
 	if (feature_split_evtchn)
-		err = setup_netfront_split(info);
+		err = setup_netfront_split(queue);
 	/* setup single event channel if
 	 *  a) feature-split-event-channels == 0
 	 *  b) feature-split-event-channels == 1 but failed to setup
 	 */
 	if (!feature_split_evtchn || (feature_split_evtchn && err))
-		err = setup_netfront_single(info);
+		err = setup_netfront_single(queue);
 
 	if (err)
 		goto alloc_evtchn_fail;
@@ -1609,17 +1631,225 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info)
 	 * granted pages because backend is not accessing it at this point.
 	 */
 alloc_evtchn_fail:
-	gnttab_end_foreign_access_ref(info->rx_ring_ref, 0);
+	gnttab_end_foreign_access_ref(queue->rx_ring_ref, 0);
 grant_rx_ring_fail:
 	free_page((unsigned long)rxs);
 alloc_rx_ring_fail:
-	gnttab_end_foreign_access_ref(info->tx_ring_ref, 0);
+	gnttab_end_foreign_access_ref(queue->tx_ring_ref, 0);
 grant_tx_ring_fail:
 	free_page((unsigned long)txs);
 fail:
 	return err;
 }
 
+/* Queue-specific initialisation
+ * This used to be done in xennet_create_dev() but must now
+ * be run per-queue.
+ */
+static int xennet_init_queue(struct netfront_queue *queue)
+{
+	unsigned short i;
+	int err = 0;
+
+	spin_lock_init(&queue->tx_lock);
+	spin_lock_init(&queue->rx_lock);
+
+	skb_queue_head_init(&queue->rx_batch);
+	queue->rx_target     = RX_DFL_MIN_TARGET;
+	queue->rx_min_target = RX_DFL_MIN_TARGET;
+	queue->rx_max_target = RX_MAX_TARGET;
+
+	init_timer(&queue->rx_refill_timer);
+	queue->rx_refill_timer.data = (unsigned long)queue;
+	queue->rx_refill_timer.function = rx_refill_timeout;
+
+	snprintf(queue->name, sizeof(queue->name), "%s-q%u",
+		 queue->info->netdev->name, queue->id);
+
+	/* Initialise tx_skbs as a free chain containing every entry. */
+	queue->tx_skb_freelist = 0;
+	for (i = 0; i < NET_TX_RING_SIZE; i++) {
+		skb_entry_set_link(&queue->tx_skbs[i], i+1);
+		queue->grant_tx_ref[i] = GRANT_INVALID_REF;
+		queue->grant_tx_page[i] = NULL;
+	}
+
+	/* Clear out rx_skbs */
+	for (i = 0; i < NET_RX_RING_SIZE; i++) {
+		queue->rx_skbs[i] = NULL;
+		queue->grant_rx_ref[i] = GRANT_INVALID_REF;
+	}
+
+	/* A grant for every tx ring slot */
+	if (gnttab_alloc_grant_references(TX_MAX_TARGET,
+					  &queue->gref_tx_head) < 0) {
+		pr_alert("can't alloc tx grant refs\n");
+		err = -ENOMEM;
+		goto exit;
+	}
+
+	/* A grant for every rx ring slot */
+	if (gnttab_alloc_grant_references(RX_MAX_TARGET,
+					  &queue->gref_rx_head) < 0) {
+		pr_alert("can't alloc rx grant refs\n");
+		err = -ENOMEM;
+		goto exit_free_tx;
+	}
+
+	return 0;
+
+ exit_free_tx:
+	gnttab_free_grant_references(queue->gref_tx_head);
+ exit:
+	return err;
+}
+
+static int write_queue_xenstore_keys(struct netfront_queue *queue,
+			   struct xenbus_transaction *xbt, int write_hierarchical)
+{
+	/* Write the queue-specific keys into XenStore in the traditional
+	 * way for a single queue, or in a queue subkeys for multiple
+	 * queues.
+	 */
+	struct xenbus_device *dev = queue->info->xbdev;
+	int err;
+	const char *message;
+	char *path;
+	size_t pathsize;
+
+	/* Choose the correct place to write the keys */
+	if (write_hierarchical) {
+		pathsize = strlen(dev->nodename) + 10;
+		path = kzalloc(pathsize, GFP_KERNEL);
+		if (!path) {
+			err = -ENOMEM;
+			message = "out of memory while writing ring references";
+			goto error;
+		}
+		snprintf(path, pathsize, "%s/queue-%u",
+				dev->nodename, queue->id);
+	} else {
+		path = (char *)dev->nodename;
+	}
+
+	/* Write ring references */
+	err = xenbus_printf(*xbt, path, "tx-ring-ref", "%u",
+			queue->tx_ring_ref);
+	if (err) {
+		message = "writing tx-ring-ref";
+		goto error;
+	}
+
+	err = xenbus_printf(*xbt, path, "rx-ring-ref", "%u",
+			queue->rx_ring_ref);
+	if (err) {
+		message = "writing rx-ring-ref";
+		goto error;
+	}
+
+	/* Write event channels; taking into account both shared
+	 * and split event channel scenarios.
+	 */
+	if (queue->tx_evtchn == queue->rx_evtchn) {
+		/* Shared event channel */
+		err = xenbus_printf(*xbt, path,
+				"event-channel", "%u", queue->tx_evtchn);
+		if (err) {
+			message = "writing event-channel";
+			goto error;
+		}
+	} else {
+		/* Split event channels */
+		err = xenbus_printf(*xbt, path,
+				"event-channel-tx", "%u", queue->tx_evtchn);
+		if (err) {
+			message = "writing event-channel-tx";
+			goto error;
+		}
+
+		err = xenbus_printf(*xbt, path,
+				"event-channel-rx", "%u", queue->rx_evtchn);
+		if (err) {
+			message = "writing event-channel-rx";
+			goto error;
+		}
+	}
+
+	if (write_hierarchical)
+		kfree(path);
+	return 0;
+
+error:
+	if (write_hierarchical)
+		kfree(path);
+	xenbus_dev_fatal(dev, err, "%s", message);
+	return err;
+}
+
+static void xennet_destroy_queues(struct netfront_info *info)
+{
+	unsigned int i;
+
+	rtnl_lock();
+
+	for (i = 0; i < info->netdev->real_num_tx_queues; i++) {
+		struct netfront_queue *queue = &info->queues[i];
+
+		if (netif_running(info->netdev))
+			napi_disable(&queue->napi);
+		netif_napi_del(&queue->napi);
+	}
+
+	rtnl_unlock();
+
+	kfree(info->queues);
+	info->queues = NULL;
+}
+
+static int xennet_create_queues(struct netfront_info *info,
+				unsigned int num_queues)
+{
+	unsigned int i;
+	int ret;
+
+	info->queues = kcalloc(num_queues, sizeof(struct netfront_queue),
+			       GFP_KERNEL);
+	if (!info->queues)
+		return -ENOMEM;
+
+	rtnl_lock();
+
+	for (i = 0; i < num_queues; i++) {
+		struct netfront_queue *queue = &info->queues[i];
+
+		queue->id = i;
+		queue->info = info;
+
+		ret = xennet_init_queue(queue);
+		if (ret < 0) {
+			dev_warn(&info->netdev->dev, "only created %d queues\n",
+				 num_queues);
+			num_queues = i;
+			break;
+		}
+
+		netif_napi_add(queue->info->netdev, &queue->napi,
+			       xennet_poll, 64);
+		if (netif_running(info->netdev))
+			napi_enable(&queue->napi);
+	}
+
+	netif_set_real_num_tx_queues(info->netdev, num_queues);
+
+	rtnl_unlock();
+
+	if (num_queues == 0) {
+		dev_err(&info->netdev->dev, "no queues\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /* Common code used when first setting up, and when resuming. */
 static int talk_to_netback(struct xenbus_device *dev,
 			   struct netfront_info *info)
@@ -1627,11 +1857,61 @@ static int talk_to_netback(struct xenbus_device *dev,
 	const char *message;
 	struct xenbus_transaction xbt;
 	int err;
+	unsigned int feature_split_evtchn;
+	unsigned int i = 0;
+	unsigned int max_queues = 0;
+	struct netfront_queue *queue = NULL;
+	unsigned int num_queues = 1;
 
-	/* Create shared ring, alloc event channel. */
-	err = setup_netfront(dev, info);
-	if (err)
+	info->netdev->irq = 0;
+
+	/* Check if backend supports multiple queues */
+	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+			   "multi-queue-max-queues", "%u", &max_queues);
+	if (err < 0)
+		max_queues = 1;
+	num_queues = min(max_queues, xennet_max_queues);
+
+	/* Check feature-split-event-channels */
+	err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
+			   "feature-split-event-channels", "%u",
+			   &feature_split_evtchn);
+	if (err < 0)
+		feature_split_evtchn = 0;
+
+	/* Read mac addr. */
+	err = xen_net_read_mac(dev, info->netdev->dev_addr);
+	if (err) {
+		xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
 		goto out;
+	}
+
+	if (info->queues)
+		xennet_destroy_queues(info);
+
+	err = xennet_create_queues(info, num_queues);
+	if (err < 0)
+		goto destroy_ring;
+
+	/* Create shared ring, alloc event channel -- for each queue */
+	for (i = 0; i < num_queues; ++i) {
+		queue = &info->queues[i];
+		err = setup_netfront(dev, queue, feature_split_evtchn);
+		if (err) {
+			/* setup_netfront() will tidy up the current
+			 * queue on error, but we need to clean up
+			 * those already allocated.
+			 */
+			if (i > 0) {
+				rtnl_lock();
+				netif_set_real_num_tx_queues(info->netdev, i);
+				rtnl_unlock();
+				goto destroy_ring;
+			} else {
+				goto out;
+			}
+		}
+	}
 
 again:
 	err = xenbus_transaction_start(&xbt);
@@ -1640,41 +1920,29 @@ again:
 		goto destroy_ring;
 	}
 
-	err = xenbus_printf(xbt, dev->nodename, "tx-ring-ref", "%u",
-			    info->tx_ring_ref);
-	if (err) {
-		message = "writing tx ring-ref";
-		goto abort_transaction;
-	}
-	err = xenbus_printf(xbt, dev->nodename, "rx-ring-ref", "%u",
-			    info->rx_ring_ref);
-	if (err) {
-		message = "writing rx ring-ref";
-		goto abort_transaction;
-	}
-
-	if (info->tx_evtchn == info->rx_evtchn) {
-		err = xenbus_printf(xbt, dev->nodename,
-				    "event-channel", "%u", info->tx_evtchn);
-		if (err) {
-			message = "writing event-channel";
-			goto abort_transaction;
-		}
+	if (num_queues == 1) {
+		err = write_queue_xenstore_keys(&info->queues[0], &xbt, 0); /* flat */
+		if (err)
+			goto abort_transaction_no_dev_fatal;
 	} else {
-		err = xenbus_printf(xbt, dev->nodename,
-				    "event-channel-tx", "%u", info->tx_evtchn);
+		/* Write the number of queues */
+		err = xenbus_printf(xbt, dev->nodename, "multi-queue-num-queues",
+				    "%u", num_queues);
 		if (err) {
-			message = "writing event-channel-tx";
-			goto abort_transaction;
+			message = "writing multi-queue-num-queues";
+			goto abort_transaction_no_dev_fatal;
 		}
-		err = xenbus_printf(xbt, dev->nodename,
-				    "event-channel-rx", "%u", info->rx_evtchn);
-		if (err) {
-			message = "writing event-channel-rx";
-			goto abort_transaction;
+
+		/* Write the keys for each queue */
+		for (i = 0; i < num_queues; ++i) {
+			queue = &info->queues[i];
+			err = write_queue_xenstore_keys(queue, &xbt, 1); /* hierarchical */
+			if (err)
+				goto abort_transaction_no_dev_fatal;
 		}
 	}
 
+	/* The remaining keys are not queue-specific */
 	err = xenbus_printf(xbt, dev->nodename, "request-rx-copy", "%u",
 			    1);
 	if (err) {
@@ -1724,10 +1992,16 @@ again:
 	return 0;
 
  abort_transaction:
-	xenbus_transaction_end(xbt, 1);
 	xenbus_dev_fatal(dev, err, "%s", message);
+abort_transaction_no_dev_fatal:
+	xenbus_transaction_end(xbt, 1);
  destroy_ring:
 	xennet_disconnect_backend(info);
+	kfree(info->queues);
+	info->queues = NULL;
+	rtnl_lock();
+	netif_set_real_num_tx_queues(info->netdev, 0);
+	rtnl_lock();
  out:
 	return err;
 }
@@ -1735,11 +2009,14 @@ again:
 static int xennet_connect(struct net_device *dev)
 {
 	struct netfront_info *np = netdev_priv(dev);
+	unsigned int num_queues = 0;
 	int i, requeue_idx, err;
 	struct sk_buff *skb;
 	grant_ref_t ref;
 	struct xen_netif_rx_request *req;
 	unsigned int feature_rx_copy;
+	unsigned int j = 0;
+	struct netfront_queue *queue = NULL;
 
 	err = xenbus_scanf(XBT_NIL, np->xbdev->otherend,
 			   "feature-rx-copy", "%u", &feature_rx_copy);
@@ -1756,40 +2033,51 @@ static int xennet_connect(struct net_device *dev)
 	if (err)
 		return err;
 
+	/* talk_to_netback() sets the correct number of queues */
+	num_queues = dev->real_num_tx_queues;
+
 	rtnl_lock();
 	netdev_update_features(dev);
 	rtnl_unlock();
 
-	spin_lock_bh(&np->rx_lock);
-	spin_lock_irq(&np->tx_lock);
+	/* By now, the queue structures have been set up */
+	for (j = 0; j < num_queues; ++j) {
+		queue = &np->queues[j];
 
-	/* Step 1: Discard all pending TX packet fragments. */
-	xennet_release_tx_bufs(np);
+		/* Step 1: Discard all pending TX packet fragments. */
+		spin_lock_irq(&queue->tx_lock);
+		xennet_release_tx_bufs(queue);
+		spin_unlock_irq(&queue->tx_lock);
 
-	/* Step 2: Rebuild the RX buffer freelist and the RX ring itself. */
-	for (requeue_idx = 0, i = 0; i < NET_RX_RING_SIZE; i++) {
-		skb_frag_t *frag;
-		const struct page *page;
-		if (!np->rx_skbs[i])
-			continue;
+		/* Step 2: Rebuild the RX buffer freelist and the RX ring itself. */
+		spin_lock_bh(&queue->rx_lock);
+
+		for (requeue_idx = 0, i = 0; i < NET_RX_RING_SIZE; i++) {
+			skb_frag_t *frag;
+			const struct page *page;
+			if (!queue->rx_skbs[i])
+				continue;
 
-		skb = np->rx_skbs[requeue_idx] = xennet_get_rx_skb(np, i);
-		ref = np->grant_rx_ref[requeue_idx] = xennet_get_rx_ref(np, i);
-		req = RING_GET_REQUEST(&np->rx, requeue_idx);
+			skb = queue->rx_skbs[requeue_idx] = xennet_get_rx_skb(queue, i);
+			ref = queue->grant_rx_ref[requeue_idx] = xennet_get_rx_ref(queue, i);
+			req = RING_GET_REQUEST(&queue->rx, requeue_idx);
 
-		frag = &skb_shinfo(skb)->frags[0];
-		page = skb_frag_page(frag);
-		gnttab_grant_foreign_access_ref(
-			ref, np->xbdev->otherend_id,
-			pfn_to_mfn(page_to_pfn(page)),
-			0);
-		req->gref = ref;
-		req->id   = requeue_idx;
+			frag = &skb_shinfo(skb)->frags[0];
+			page = skb_frag_page(frag);
+			gnttab_grant_foreign_access_ref(
+				ref, queue->info->xbdev->otherend_id,
+				pfn_to_mfn(page_to_pfn(page)),
+				0);
+			req->gref = ref;
+			req->id   = requeue_idx;
 
-		requeue_idx++;
-	}
+			requeue_idx++;
+		}
 
-	np->rx.req_prod_pvt = requeue_idx;
+		queue->rx.req_prod_pvt = requeue_idx;
+
+		spin_unlock_bh(&queue->rx_lock);
+	}
 
 	/*
 	 * Step 3: All public and private state should now be sane.  Get
@@ -1798,14 +2086,21 @@ static int xennet_connect(struct net_device *dev)
 	 * packets.
 	 */
 	netif_carrier_on(np->netdev);
-	notify_remote_via_irq(np->tx_irq);
-	if (np->tx_irq != np->rx_irq)
-		notify_remote_via_irq(np->rx_irq);
-	xennet_tx_buf_gc(dev);
-	xennet_alloc_rx_buffers(dev);
+	for (j = 0; j < num_queues; ++j) {
+		queue = &np->queues[j];
 
-	spin_unlock_irq(&np->tx_lock);
-	spin_unlock_bh(&np->rx_lock);
+		notify_remote_via_irq(queue->tx_irq);
+		if (queue->tx_irq != queue->rx_irq)
+			notify_remote_via_irq(queue->rx_irq);
+
+		spin_lock_irq(&queue->tx_lock);
+		xennet_tx_buf_gc(queue);
+		spin_unlock_irq(&queue->tx_lock);
+
+		spin_lock_bh(&queue->rx_lock);
+		xennet_alloc_rx_buffers(queue);
+		spin_unlock_bh(&queue->rx_lock);
+	}
 
 	return 0;
 }
@@ -1878,7 +2173,7 @@ static void xennet_get_ethtool_stats(struct net_device *dev,
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(xennet_stats); i++)
-		data[i] = *(unsigned long *)(np + xennet_stats[i].offset);
+		data[i] = atomic_read((atomic_t *)(np + xennet_stats[i].offset));
 }
 
 static void xennet_get_strings(struct net_device *dev, u32 stringset, u8 * data)
@@ -1909,8 +2204,12 @@ static ssize_t show_rxbuf_min(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 	struct netfront_info *info = netdev_priv(netdev);
+	unsigned int num_queues = netdev->real_num_tx_queues;
 
-	return sprintf(buf, "%u\n", info->rx_min_target);
+	if (num_queues)
+		return sprintf(buf, "%u\n", info->queues[0].rx_min_target);
+	else
+		return sprintf(buf, "%u\n", RX_MIN_TARGET);
 }
 
 static ssize_t store_rxbuf_min(struct device *dev,
@@ -1919,8 +2218,11 @@ static ssize_t store_rxbuf_min(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 	struct netfront_info *np = netdev_priv(netdev);
+	unsigned int num_queues = netdev->real_num_tx_queues;
 	char *endp;
 	unsigned long target;
+	unsigned int i;
+	struct netfront_queue *queue;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -1934,16 +2236,19 @@ static ssize_t store_rxbuf_min(struct device *dev,
 	if (target > RX_MAX_TARGET)
 		target = RX_MAX_TARGET;
 
-	spin_lock_bh(&np->rx_lock);
-	if (target > np->rx_max_target)
-		np->rx_max_target = target;
-	np->rx_min_target = target;
-	if (target > np->rx_target)
-		np->rx_target = target;
+	for (i = 0; i < num_queues; ++i) {
+		queue = &np->queues[i];
+		spin_lock_bh(&queue->rx_lock);
+		if (target > queue->rx_max_target)
+			queue->rx_max_target = target;
+		queue->rx_min_target = target;
+		if (target > queue->rx_target)
+			queue->rx_target = target;
 
-	xennet_alloc_rx_buffers(netdev);
+		xennet_alloc_rx_buffers(queue);
 
-	spin_unlock_bh(&np->rx_lock);
+		spin_unlock_bh(&queue->rx_lock);
+	}
 	return len;
 }
 
@@ -1952,8 +2257,12 @@ static ssize_t show_rxbuf_max(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 	struct netfront_info *info = netdev_priv(netdev);
+	unsigned int num_queues = netdev->real_num_tx_queues;
 
-	return sprintf(buf, "%u\n", info->rx_max_target);
+	if (num_queues)
+		return sprintf(buf, "%u\n", info->queues[0].rx_max_target);
+	else
+		return sprintf(buf, "%u\n", RX_MAX_TARGET);
 }
 
 static ssize_t store_rxbuf_max(struct device *dev,
@@ -1962,8 +2271,11 @@ static ssize_t store_rxbuf_max(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 	struct netfront_info *np = netdev_priv(netdev);
+	unsigned int num_queues = netdev->real_num_tx_queues;
 	char *endp;
 	unsigned long target;
+	unsigned int i = 0;
+	struct netfront_queue *queue = NULL;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -1977,16 +2289,19 @@ static ssize_t store_rxbuf_max(struct device *dev,
 	if (target > RX_MAX_TARGET)
 		target = RX_MAX_TARGET;
 
-	spin_lock_bh(&np->rx_lock);
-	if (target < np->rx_min_target)
-		np->rx_min_target = target;
-	np->rx_max_target = target;
-	if (target < np->rx_target)
-		np->rx_target = target;
+	for (i = 0; i < num_queues; ++i) {
+		queue = &np->queues[i];
+		spin_lock_bh(&queue->rx_lock);
+		if (target < queue->rx_min_target)
+			queue->rx_min_target = target;
+		queue->rx_max_target = target;
+		if (target < queue->rx_target)
+			queue->rx_target = target;
 
-	xennet_alloc_rx_buffers(netdev);
+		xennet_alloc_rx_buffers(queue);
 
-	spin_unlock_bh(&np->rx_lock);
+		spin_unlock_bh(&queue->rx_lock);
+	}
 	return len;
 }
 
@@ -1995,8 +2310,12 @@ static ssize_t show_rxbuf_cur(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 	struct netfront_info *info = netdev_priv(netdev);
+	unsigned int num_queues = netdev->real_num_tx_queues;
 
-	return sprintf(buf, "%u\n", info->rx_target);
+	if (num_queues)
+		return sprintf(buf, "%u\n", info->queues[0].rx_target);
+	else
+		return sprintf(buf, "0\n");
 }
 
 static struct device_attribute xennet_attrs[] = {
@@ -2043,6 +2362,9 @@ static const struct xenbus_device_id netfront_ids[] = {
 static int xennet_remove(struct xenbus_device *dev)
 {
 	struct netfront_info *info = dev_get_drvdata(&dev->dev);
+	unsigned int num_queues = info->netdev->real_num_tx_queues;
+	struct netfront_queue *queue = NULL;
+	unsigned int i = 0;
 
 	dev_dbg(&dev->dev, "%s\n", dev->nodename);
 
@@ -2052,7 +2374,15 @@ static int xennet_remove(struct xenbus_device *dev)
 
 	unregister_netdev(info->netdev);
 
-	del_timer_sync(&info->rx_refill_timer);
+	for (i = 0; i < num_queues; ++i) {
+		queue = &info->queues[i];
+		del_timer_sync(&queue->rx_refill_timer);
+	}
+
+	if (num_queues) {
+		kfree(info->queues);
+		info->queues = NULL;
+	}
 
 	free_percpu(info->stats);
 
@@ -2078,6 +2408,9 @@ static int __init netif_init(void)
 
 	pr_info("Initialising Xen virtual ethernet driver\n");
 
+	/* Allow as many queues as there are CPUs, by default */
+	xennet_max_queues = num_online_cpus();
+
 	return xenbus_register_frontend(&netfront_driver);
 }
 module_init(netif_init);
diff --git a/drivers/nfc/Kconfig b/drivers/nfc/Kconfig
index 65d4ca19d13..26c66a12655 100644
--- a/drivers/nfc/Kconfig
+++ b/drivers/nfc/Kconfig
@@ -71,5 +71,6 @@ config NFC_PORT100
 source "drivers/nfc/pn544/Kconfig"
 source "drivers/nfc/microread/Kconfig"
 source "drivers/nfc/nfcmrvl/Kconfig"
+source "drivers/nfc/st21nfca/Kconfig"
 
 endmenu
diff --git a/drivers/nfc/Makefile b/drivers/nfc/Makefile
index ae42a3fa60c..23225b0287f 100644
--- a/drivers/nfc/Makefile
+++ b/drivers/nfc/Makefile
@@ -11,5 +11,6 @@ obj-$(CONFIG_NFC_SIM)		+= nfcsim.o
 obj-$(CONFIG_NFC_PORT100)	+= port100.o
 obj-$(CONFIG_NFC_MRVL)		+= nfcmrvl/
 obj-$(CONFIG_NFC_TRF7970A)	+= trf7970a.o
+obj-$(CONFIG_NFC_ST21NFCA)  += st21nfca/
 
 ccflags-$(CONFIG_NFC_DEBUG) := -DDEBUG
diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c
index f2acd85be86..440291ab726 100644
--- a/drivers/nfc/pn544/i2c.c
+++ b/drivers/nfc/pn544/i2c.c
@@ -22,6 +22,8 @@
 #include <linux/module.h>
 #include <linux/i2c.h>
 #include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/of_irq.h>
 #include <linux/miscdevice.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
@@ -857,6 +859,92 @@ exit_state_wait_secure_write_answer:
 	}
 }
 
+#ifdef CONFIG_OF
+
+static int pn544_hci_i2c_of_request_resources(struct i2c_client *client)
+{
+	struct pn544_i2c_phy *phy = i2c_get_clientdata(client);
+	struct device_node *pp;
+	int ret;
+
+	pp = client->dev.of_node;
+	if (!pp) {
+		ret = -ENODEV;
+		goto err_dt;
+	}
+
+	/* Obtention of EN GPIO from device tree */
+	ret = of_get_named_gpio(pp, "enable-gpios", 0);
+	if (ret < 0) {
+		if (ret != -EPROBE_DEFER)
+			nfc_err(&client->dev,
+				"Failed to get EN gpio, error: %d\n", ret);
+		goto err_dt;
+	}
+	phy->gpio_en = ret;
+
+	/* Configuration of EN GPIO */
+	ret = gpio_request(phy->gpio_en, "pn544_en");
+	if (ret) {
+		nfc_err(&client->dev, "Fail EN pin\n");
+		goto err_dt;
+	}
+	ret = gpio_direction_output(phy->gpio_en, 0);
+	if (ret) {
+		nfc_err(&client->dev, "Fail EN pin direction\n");
+		goto err_gpio_en;
+	}
+
+	/* Obtention of FW GPIO from device tree */
+	ret = of_get_named_gpio(pp, "firmware-gpios", 0);
+	if (ret < 0) {
+		if (ret != -EPROBE_DEFER)
+			nfc_err(&client->dev,
+				"Failed to get FW gpio, error: %d\n", ret);
+		goto err_gpio_en;
+	}
+	phy->gpio_fw = ret;
+
+	/* Configuration of FW GPIO */
+	ret = gpio_request(phy->gpio_fw, "pn544_fw");
+	if (ret) {
+		nfc_err(&client->dev, "Fail FW pin\n");
+		goto err_gpio_en;
+	}
+	ret = gpio_direction_output(phy->gpio_fw, 0);
+	if (ret) {
+		nfc_err(&client->dev, "Fail FW pin direction\n");
+		goto err_gpio_fw;
+	}
+
+	/* IRQ */
+	ret = irq_of_parse_and_map(pp, 0);
+	if (ret < 0) {
+		nfc_err(&client->dev,
+			"Unable to get irq, error: %d\n", ret);
+		goto err_gpio_fw;
+	}
+	client->irq = ret;
+
+	return 0;
+
+err_gpio_fw:
+	gpio_free(phy->gpio_fw);
+err_gpio_en:
+	gpio_free(phy->gpio_en);
+err_dt:
+	return ret;
+}
+
+#else
+
+static int pn544_hci_i2c_of_request_resources(struct i2c_client *client)
+{
+	return -ENODEV;
+}
+
+#endif
+
 static int pn544_hci_i2c_probe(struct i2c_client *client,
 			       const struct i2c_device_id *id)
 {
@@ -887,25 +975,36 @@ static int pn544_hci_i2c_probe(struct i2c_client *client,
 	i2c_set_clientdata(client, phy);
 
 	pdata = client->dev.platform_data;
-	if (pdata == NULL) {
-		nfc_err(&client->dev, "No platform data\n");
-		return -EINVAL;
-	}
 
-	if (pdata->request_resources == NULL) {
-		nfc_err(&client->dev, "request_resources() missing\n");
-		return -EINVAL;
-	}
+	/* No platform data, using device tree. */
+	if (!pdata && client->dev.of_node) {
+		r = pn544_hci_i2c_of_request_resources(client);
+		if (r) {
+			nfc_err(&client->dev, "No DT data\n");
+			return r;
+		}
+	/* Using platform data. */
+	} else if (pdata) {
 
-	r = pdata->request_resources(client);
-	if (r) {
-		nfc_err(&client->dev, "Cannot get platform resources\n");
-		return r;
-	}
+		if (pdata->request_resources == NULL) {
+			nfc_err(&client->dev, "request_resources() missing\n");
+			return -EINVAL;
+		}
 
-	phy->gpio_en = pdata->get_gpio(NFC_GPIO_ENABLE);
-	phy->gpio_fw = pdata->get_gpio(NFC_GPIO_FW_RESET);
-	phy->gpio_irq = pdata->get_gpio(NFC_GPIO_IRQ);
+		r = pdata->request_resources(client);
+		if (r) {
+			nfc_err(&client->dev,
+				"Cannot get platform resources\n");
+			return r;
+		}
+
+		phy->gpio_en = pdata->get_gpio(NFC_GPIO_ENABLE);
+		phy->gpio_fw = pdata->get_gpio(NFC_GPIO_FW_RESET);
+		phy->gpio_irq = pdata->get_gpio(NFC_GPIO_IRQ);
+	} else {
+		nfc_err(&client->dev, "No platform data\n");
+		return -EINVAL;
+	}
 
 	pn544_hci_i2c_platform_init(phy);
 
@@ -930,8 +1029,12 @@ err_hci:
 	free_irq(client->irq, phy);
 
 err_rti:
-	if (pdata->free_resources != NULL)
+	if (!pdata) {
+		gpio_free(phy->gpio_en);
+		gpio_free(phy->gpio_fw);
+	} else if (pdata->free_resources) {
 		pdata->free_resources();
+	}
 
 	return r;
 }
@@ -953,15 +1056,30 @@ static int pn544_hci_i2c_remove(struct i2c_client *client)
 		pn544_hci_i2c_disable(phy);
 
 	free_irq(client->irq, phy);
-	if (pdata->free_resources)
+
+	/* No platform data, GPIOs have been requested by this driver */
+	if (!pdata) {
+		gpio_free(phy->gpio_en);
+		gpio_free(phy->gpio_fw);
+	/* Using platform data */
+	} else if (pdata->free_resources) {
 		pdata->free_resources();
+	}
 
 	return 0;
 }
 
+static const struct of_device_id of_pn544_i2c_match[] = {
+	{ .compatible = "nxp,pn544-i2c", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_pn544_i2c_match);
+
 static struct i2c_driver pn544_hci_i2c_driver = {
 	.driver = {
 		   .name = PN544_HCI_I2C_DRIVER_NAME,
+		   .owner  = THIS_MODULE,
+		   .of_match_table = of_match_ptr(of_pn544_i2c_match),
 		  },
 	.probe = pn544_hci_i2c_probe,
 	.id_table = pn544_hci_i2c_id_table,
diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c
index b7a372af5eb..4ac4d31f6c5 100644
--- a/drivers/nfc/port100.c
+++ b/drivers/nfc/port100.c
@@ -28,7 +28,8 @@
 			   NFC_PROTO_MIFARE_MASK   | \
 			   NFC_PROTO_FELICA_MASK   | \
 			   NFC_PROTO_NFC_DEP_MASK  | \
-			   NFC_PROTO_ISO14443_MASK)
+			   NFC_PROTO_ISO14443_MASK | \
+			   NFC_PROTO_ISO14443_B_MASK)
 
 #define PORT100_CAPABILITIES (NFC_DIGITAL_DRV_CAPS_IN_CRC | \
 			      NFC_DIGITAL_DRV_CAPS_TG_CRC)
@@ -120,6 +121,7 @@ struct port100_in_rf_setting {
 #define PORT100_COMM_TYPE_IN_212F 0x01
 #define PORT100_COMM_TYPE_IN_424F 0x02
 #define PORT100_COMM_TYPE_IN_106A 0x03
+#define PORT100_COMM_TYPE_IN_106B 0x07
 
 static const struct port100_in_rf_setting in_rf_settings[] = {
 	[NFC_DIGITAL_RF_TECH_212F] = {
@@ -140,6 +142,12 @@ static const struct port100_in_rf_setting in_rf_settings[] = {
 		.in_recv_set_number = 15,
 		.in_recv_comm_type  = PORT100_COMM_TYPE_IN_106A,
 	},
+	[NFC_DIGITAL_RF_TECH_106B] = {
+		.in_send_set_number = 3,
+		.in_send_comm_type  = PORT100_COMM_TYPE_IN_106B,
+		.in_recv_set_number = 15,
+		.in_recv_comm_type  = PORT100_COMM_TYPE_IN_106B,
+	},
 	/* Ensures the array has NFC_DIGITAL_RF_TECH_LAST elements */
 	[NFC_DIGITAL_RF_TECH_LAST] = { 0 },
 };
@@ -340,6 +348,32 @@ in_protocols[][PORT100_IN_MAX_NUM_PROTOCOLS + 1] = {
 	[NFC_DIGITAL_FRAMING_NFC_DEP_ACTIVATED] = {
 		{ PORT100_IN_PROT_END, 0 },
 	},
+	[NFC_DIGITAL_FRAMING_NFCB] = {
+		{ PORT100_IN_PROT_INITIAL_GUARD_TIME,     20 },
+		{ PORT100_IN_PROT_ADD_CRC,                 1 },
+		{ PORT100_IN_PROT_CHECK_CRC,               1 },
+		{ PORT100_IN_PROT_MULTI_CARD,              0 },
+		{ PORT100_IN_PROT_ADD_PARITY,              0 },
+		{ PORT100_IN_PROT_CHECK_PARITY,            0 },
+		{ PORT100_IN_PROT_BITWISE_AC_RECV_MODE,    0 },
+		{ PORT100_IN_PROT_VALID_BIT_NUMBER,        8 },
+		{ PORT100_IN_PROT_CRYPTO1,                 0 },
+		{ PORT100_IN_PROT_ADD_SOF,                 1 },
+		{ PORT100_IN_PROT_CHECK_SOF,               1 },
+		{ PORT100_IN_PROT_ADD_EOF,                 1 },
+		{ PORT100_IN_PROT_CHECK_EOF,               1 },
+		{ PORT100_IN_PROT_DEAF_TIME,               4 },
+		{ PORT100_IN_PROT_CRM,                     0 },
+		{ PORT100_IN_PROT_CRM_MIN_LEN,             0 },
+		{ PORT100_IN_PROT_T1_TAG_FRAME,            0 },
+		{ PORT100_IN_PROT_RFCA,                    0 },
+		{ PORT100_IN_PROT_GUARD_TIME_AT_INITIATOR, 6 },
+		{ PORT100_IN_PROT_END,                     0 },
+	},
+	[NFC_DIGITAL_FRAMING_NFCB_T4T] = {
+		/* nfc_digital_framing_nfcb */
+		{ PORT100_IN_PROT_END,                     0 },
+	},
 	/* Ensures the array has NFC_DIGITAL_FRAMING_LAST elements */
 	[NFC_DIGITAL_FRAMING_LAST] = {
 		{ PORT100_IN_PROT_END, 0 },
diff --git a/drivers/nfc/st21nfca/Kconfig b/drivers/nfc/st21nfca/Kconfig
new file mode 100644
index 00000000000..ee459f066ad
--- /dev/null
+++ b/drivers/nfc/st21nfca/Kconfig
@@ -0,0 +1,23 @@
+config NFC_ST21NFCA
+	tristate "STMicroelectronics ST21NFCA NFC driver"
+	depends on NFC_HCI
+	select CRC_CCITT
+	default n
+	---help---
+	  STMicroelectronics ST21NFCA core driver. It implements the chipset
+	  HCI logic and hooks into the NFC kernel APIs. Physical layers will
+	  register against it.
+
+	  To compile this driver as a module, choose m here. The module will
+	  be called st21nfca.
+	  Say N if unsure.
+
+config NFC_ST21NFCA_I2C
+	tristate "NFC ST21NFCA i2c support"
+	depends on NFC_ST21NFCA && I2C && NFC_SHDLC
+	---help---
+	  This module adds support for the STMicroelectronics st21nfca i2c interface.
+	  Select this if your platform is using the i2c bus.
+
+	  If you choose to build a module, it'll be called st21nfca_i2c.
+	  Say N if unsure.
diff --git a/drivers/nfc/st21nfca/Makefile b/drivers/nfc/st21nfca/Makefile
new file mode 100644
index 00000000000..038ed093a11
--- /dev/null
+++ b/drivers/nfc/st21nfca/Makefile
@@ -0,0 +1,8 @@
+#
+# Makefile for ST21NFCA HCI based NFC driver
+#
+
+st21nfca_i2c-objs  = i2c.o
+
+obj-$(CONFIG_NFC_ST21NFCA)     += st21nfca.o
+obj-$(CONFIG_NFC_ST21NFCA_I2C) += st21nfca_i2c.o
diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c
new file mode 100644
index 00000000000..3f954ed86d9
--- /dev/null
+++ b/drivers/nfc/st21nfca/i2c.c
@@ -0,0 +1,724 @@
+/*
+ * I2C Link Layer for ST21NFCA HCI based Driver
+ * Copyright (C) 2014  STMicroelectronics SAS. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/crc-ccitt.h>
+#include <linux/module.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <linux/of_irq.h>
+#include <linux/of_gpio.h>
+#include <linux/miscdevice.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/nfc.h>
+#include <linux/firmware.h>
+#include <linux/unaligned/access_ok.h>
+#include <linux/platform_data/st21nfca.h>
+
+#include <net/nfc/hci.h>
+#include <net/nfc/llc.h>
+#include <net/nfc/nfc.h>
+
+#include "st21nfca.h"
+
+/*
+ * Every frame starts with ST21NFCA_SOF_EOF and ends with ST21NFCA_SOF_EOF.
+ * Because ST21NFCA_SOF_EOF is a possible data value, there is a mecanism
+ * called byte stuffing has been introduced.
+ *
+ * if byte == ST21NFCA_SOF_EOF or ST21NFCA_ESCAPE_BYTE_STUFFING
+ * - insert ST21NFCA_ESCAPE_BYTE_STUFFING (escape byte)
+ * - xor byte with ST21NFCA_BYTE_STUFFING_MASK
+ */
+#define ST21NFCA_SOF_EOF		0x7e
+#define ST21NFCA_BYTE_STUFFING_MASK	0x20
+#define ST21NFCA_ESCAPE_BYTE_STUFFING	0x7d
+
+/* SOF + 00 */
+#define ST21NFCA_FRAME_HEADROOM			2
+
+/* 2 bytes crc + EOF */
+#define ST21NFCA_FRAME_TAILROOM 3
+#define IS_START_OF_FRAME(buf) (buf[0] == ST21NFCA_SOF_EOF && \
+				buf[1] == 0)
+
+#define ST21NFCA_HCI_I2C_DRIVER_NAME "st21nfca_hci_i2c"
+
+static struct i2c_device_id st21nfca_hci_i2c_id_table[] = {
+	{ST21NFCA_HCI_DRIVER_NAME, 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, st21nfca_hci_i2c_id_table);
+
+struct st21nfca_i2c_phy {
+	struct i2c_client *i2c_dev;
+	struct nfc_hci_dev *hdev;
+
+	unsigned int gpio_ena;
+	unsigned int gpio_irq;
+	unsigned int irq_polarity;
+
+	struct sk_buff *pending_skb;
+	int current_read_len;
+	/*
+	 * crc might have fail because i2c macro
+	 * is disable due to other interface activity
+	 */
+	int crc_trials;
+
+	int powered;
+	int run_mode;
+
+	/*
+	 * < 0 if hardware error occured (e.g. i2c err)
+	 * and prevents normal operation.
+	 */
+	int hard_fault;
+	struct mutex phy_lock;
+};
+static u8 len_seq[] = { 13, 24, 15, 29 };
+static u16 wait_tab[] = { 2, 3, 5, 15, 20, 40};
+
+#define I2C_DUMP_SKB(info, skb)					\
+do {								\
+	pr_debug("%s:\n", info);				\
+	print_hex_dump(KERN_DEBUG, "i2c: ", DUMP_PREFIX_OFFSET,	\
+		       16, 1, (skb)->data, (skb)->len, 0);	\
+} while (0)
+
+/*
+ * In order to get the CLF in a known state we generate an internal reboot
+ * using a proprietary command.
+ * Once the reboot is completed, we expect to receive a ST21NFCA_SOF_EOF
+ * fill buffer.
+ */
+static int st21nfca_hci_platform_init(struct st21nfca_i2c_phy *phy)
+{
+	u16 wait_reboot[] = { 50, 300, 1000 };
+	char reboot_cmd[] = { 0x7E, 0x66, 0x48, 0xF6, 0x7E };
+	u8 tmp[ST21NFCA_HCI_LLC_MAX_SIZE];
+	int i, r = -1;
+
+	for (i = 0; i < ARRAY_SIZE(wait_reboot) && r < 0; i++) {
+		r = i2c_master_send(phy->i2c_dev, reboot_cmd,
+				    sizeof(reboot_cmd));
+		if (r < 0)
+			msleep(wait_reboot[i]);
+	}
+	if (r < 0)
+		return r;
+
+	/* CLF is spending about 20ms to do an internal reboot */
+	msleep(20);
+	r = -1;
+	for (i = 0; i < ARRAY_SIZE(wait_reboot) && r < 0; i++) {
+		r = i2c_master_recv(phy->i2c_dev, tmp,
+				    ST21NFCA_HCI_LLC_MAX_SIZE);
+		if (r < 0)
+			msleep(wait_reboot[i]);
+	}
+	if (r < 0)
+		return r;
+
+	for (i = 0; i < ST21NFCA_HCI_LLC_MAX_SIZE &&
+		tmp[i] == ST21NFCA_SOF_EOF; i++)
+		;
+
+	if (r != ST21NFCA_HCI_LLC_MAX_SIZE)
+		return -ENODEV;
+
+	usleep_range(1000, 1500);
+	return 0;
+}
+
+static int st21nfca_hci_i2c_enable(void *phy_id)
+{
+	struct st21nfca_i2c_phy *phy = phy_id;
+
+	gpio_set_value(phy->gpio_ena, 1);
+	phy->powered = 1;
+	phy->run_mode = ST21NFCA_HCI_MODE;
+
+	usleep_range(10000, 15000);
+
+	return 0;
+}
+
+static void st21nfca_hci_i2c_disable(void *phy_id)
+{
+	struct st21nfca_i2c_phy *phy = phy_id;
+
+	pr_info("\n");
+	gpio_set_value(phy->gpio_ena, 0);
+
+	phy->powered = 0;
+}
+
+static void st21nfca_hci_add_len_crc(struct sk_buff *skb)
+{
+	u16 crc;
+	u8 tmp;
+
+	*skb_push(skb, 1) = 0;
+
+	crc = crc_ccitt(0xffff, skb->data, skb->len);
+	crc = ~crc;
+
+	tmp = crc & 0x00ff;
+	*skb_put(skb, 1) = tmp;
+
+	tmp = (crc >> 8) & 0x00ff;
+	*skb_put(skb, 1) = tmp;
+}
+
+static void st21nfca_hci_remove_len_crc(struct sk_buff *skb)
+{
+	skb_pull(skb, ST21NFCA_FRAME_HEADROOM);
+	skb_trim(skb, skb->len - ST21NFCA_FRAME_TAILROOM);
+}
+
+/*
+ * Writing a frame must not return the number of written bytes.
+ * It must return either zero for success, or <0 for error.
+ * In addition, it must not alter the skb
+ */
+static int st21nfca_hci_i2c_write(void *phy_id, struct sk_buff *skb)
+{
+	int r = -1, i, j;
+	struct st21nfca_i2c_phy *phy = phy_id;
+	struct i2c_client *client = phy->i2c_dev;
+	u8 tmp[ST21NFCA_HCI_LLC_MAX_SIZE * 2];
+
+	I2C_DUMP_SKB("st21nfca_hci_i2c_write", skb);
+
+
+	if (phy->hard_fault != 0)
+		return phy->hard_fault;
+
+	/*
+	 * Compute CRC before byte stuffing computation on frame
+	 * Note st21nfca_hci_add_len_crc is doing a byte stuffing
+	 * on its own value
+	 */
+	st21nfca_hci_add_len_crc(skb);
+
+	/* add ST21NFCA_SOF_EOF on tail */
+	*skb_put(skb, 1) = ST21NFCA_SOF_EOF;
+	/* add ST21NFCA_SOF_EOF on head */
+	*skb_push(skb, 1) = ST21NFCA_SOF_EOF;
+
+	/*
+	 * Compute byte stuffing
+	 * if byte == ST21NFCA_SOF_EOF or ST21NFCA_ESCAPE_BYTE_STUFFING
+	 * insert ST21NFCA_ESCAPE_BYTE_STUFFING (escape byte)
+	 * xor byte with ST21NFCA_BYTE_STUFFING_MASK
+	 */
+	tmp[0] = skb->data[0];
+	for (i = 1, j = 1; i < skb->len - 1; i++, j++) {
+		if (skb->data[i] == ST21NFCA_SOF_EOF
+		    || skb->data[i] == ST21NFCA_ESCAPE_BYTE_STUFFING) {
+			tmp[j] = ST21NFCA_ESCAPE_BYTE_STUFFING;
+			j++;
+			tmp[j] = skb->data[i] ^ ST21NFCA_BYTE_STUFFING_MASK;
+		} else {
+			tmp[j] = skb->data[i];
+		}
+	}
+	tmp[j] = skb->data[i];
+	j++;
+
+	/*
+	 * Manage sleep mode
+	 * Try 3 times to send data with delay between each
+	 */
+	mutex_lock(&phy->phy_lock);
+	for (i = 0; i < ARRAY_SIZE(wait_tab) && r < 0; i++) {
+		r = i2c_master_send(client, tmp, j);
+		if (r < 0)
+			msleep(wait_tab[i]);
+	}
+	mutex_unlock(&phy->phy_lock);
+
+	if (r >= 0) {
+		if (r != j)
+			r = -EREMOTEIO;
+		else
+			r = 0;
+	}
+
+	st21nfca_hci_remove_len_crc(skb);
+
+	return r;
+}
+
+static int get_frame_size(u8 *buf, int buflen)
+{
+	int len = 0;
+	if (buf[len + 1] == ST21NFCA_SOF_EOF)
+		return 0;
+
+	for (len = 1; len < buflen && buf[len] != ST21NFCA_SOF_EOF; len++)
+		;
+
+	return len;
+}
+
+static int check_crc(u8 *buf, int buflen)
+{
+	u16 crc;
+
+	crc = crc_ccitt(0xffff, buf, buflen - 2);
+	crc = ~crc;
+
+	if (buf[buflen - 2] != (crc & 0xff) || buf[buflen - 1] != (crc >> 8)) {
+		pr_err(ST21NFCA_HCI_DRIVER_NAME
+		       ": CRC error 0x%x != 0x%x 0x%x\n", crc, buf[buflen - 1],
+		       buf[buflen - 2]);
+
+		pr_info(DRIVER_DESC ": %s : BAD CRC\n", __func__);
+		print_hex_dump(KERN_DEBUG, "crc: ", DUMP_PREFIX_NONE,
+			       16, 2, buf, buflen, false);
+		return -EPERM;
+	}
+	return 0;
+}
+
+/*
+ * Prepare received data for upper layer.
+ * Received data include byte stuffing, crc and sof/eof
+ * which is not usable by hci part.
+ * returns:
+ * frame size without sof/eof, header and byte stuffing
+ * -EBADMSG : frame was incorrect and discarded
+ */
+static int st21nfca_hci_i2c_repack(struct sk_buff *skb)
+{
+	int i, j, r, size;
+	if (skb->len < 1 || (skb->len > 1 && skb->data[1] != 0))
+		return -EBADMSG;
+
+	size = get_frame_size(skb->data, skb->len);
+	if (size > 0) {
+		skb_trim(skb, size);
+		/* remove ST21NFCA byte stuffing for upper layer */
+		for (i = 1, j = 0; i < skb->len; i++) {
+			if (skb->data[i + j] ==
+					(u8) ST21NFCA_ESCAPE_BYTE_STUFFING) {
+				skb->data[i] = skb->data[i + j + 1]
+						| ST21NFCA_BYTE_STUFFING_MASK;
+				i++;
+				j++;
+			}
+			skb->data[i] = skb->data[i + j];
+		}
+		/* remove byte stuffing useless byte */
+		skb_trim(skb, i - j);
+		/* remove ST21NFCA_SOF_EOF from head */
+		skb_pull(skb, 1);
+
+		r = check_crc(skb->data, skb->len);
+		if (r != 0) {
+			i = 0;
+			return -EBADMSG;
+		}
+
+		/* remove headbyte */
+		skb_pull(skb, 1);
+		/* remove crc. Byte Stuffing is already removed here */
+		skb_trim(skb, skb->len - 2);
+		return skb->len;
+	}
+	return 0;
+}
+
+/*
+ * Reads an shdlc frame and returns it in a newly allocated sk_buff. Guarantees
+ * that i2c bus will be flushed and that next read will start on a new frame.
+ * returned skb contains only LLC header and payload.
+ * returns:
+ * frame size : if received frame is complete (find ST21NFCA_SOF_EOF at
+ * end of read)
+ * -EAGAIN : if received frame is incomplete (not find ST21NFCA_SOF_EOF
+ * at end of read)
+ * -EREMOTEIO : i2c read error (fatal)
+ * -EBADMSG : frame was incorrect and discarded
+ * (value returned from st21nfca_hci_i2c_repack)
+ * -EIO : if no ST21NFCA_SOF_EOF is found after reaching
+ * the read length end sequence
+ */
+static int st21nfca_hci_i2c_read(struct st21nfca_i2c_phy *phy,
+				 struct sk_buff *skb)
+{
+	int r, i;
+	u8 len;
+	u8 buf[ST21NFCA_HCI_LLC_MAX_PAYLOAD];
+	struct i2c_client *client = phy->i2c_dev;
+
+	if (phy->current_read_len < ARRAY_SIZE(len_seq)) {
+		len = len_seq[phy->current_read_len];
+
+		/*
+		 * Add retry mecanism
+		 * Operation on I2C interface may fail in case of operation on
+		 * RF or SWP interface
+		 */
+		r = 0;
+		mutex_lock(&phy->phy_lock);
+		for (i = 0; i < ARRAY_SIZE(wait_tab) && r <= 0; i++) {
+			r = i2c_master_recv(client, buf, len);
+			if (r < 0)
+				msleep(wait_tab[i]);
+		}
+		mutex_unlock(&phy->phy_lock);
+
+		if (r != len) {
+			phy->current_read_len = 0;
+			return -EREMOTEIO;
+		}
+
+		/*
+		 * The first read sequence does not start with SOF.
+		 * Data is corrupeted so we drop it.
+		 */
+		if (!phy->current_read_len && buf[0] != ST21NFCA_SOF_EOF) {
+			skb_trim(skb, 0);
+			phy->current_read_len = 0;
+			return -EIO;
+		} else if (phy->current_read_len &&
+			IS_START_OF_FRAME(buf)) {
+			/*
+			 * Previous frame transmission was interrupted and
+			 * the frame got repeated.
+			 * Received frame start with ST21NFCA_SOF_EOF + 00.
+			 */
+			skb_trim(skb, 0);
+			phy->current_read_len = 0;
+		}
+
+		memcpy(skb_put(skb, len), buf, len);
+
+		if (skb->data[skb->len - 1] == ST21NFCA_SOF_EOF) {
+			phy->current_read_len = 0;
+			return st21nfca_hci_i2c_repack(skb);
+		}
+		phy->current_read_len++;
+		return -EAGAIN;
+	}
+	return -EIO;
+}
+
+/*
+ * Reads an shdlc frame from the chip. This is not as straightforward as it
+ * seems. The frame format is data-crc, and corruption can occur anywhere
+ * while transiting on i2c bus, such that we could read an invalid data.
+ * The tricky case is when we read a corrupted data or crc. We must detect
+ * this here in order to determine that data can be transmitted to the hci
+ * core. This is the reason why we check the crc here.
+ * The CLF will repeat a frame until we send a RR on that frame.
+ *
+ * On ST21NFCA, IRQ goes in idle when read starts. As no size information are
+ * available in the incoming data, other IRQ might come. Every IRQ will trigger
+ * a read sequence with different length and will fill the current frame.
+ * The reception is complete once we reach a ST21NFCA_SOF_EOF.
+ */
+static irqreturn_t st21nfca_hci_irq_thread_fn(int irq, void *phy_id)
+{
+	struct st21nfca_i2c_phy *phy = phy_id;
+	struct i2c_client *client;
+
+	int r;
+
+	if (!phy || irq != phy->i2c_dev->irq) {
+		WARN_ON_ONCE(1);
+		return IRQ_NONE;
+	}
+
+	client = phy->i2c_dev;
+	dev_dbg(&client->dev, "IRQ\n");
+
+	if (phy->hard_fault != 0)
+		return IRQ_HANDLED;
+
+	r = st21nfca_hci_i2c_read(phy, phy->pending_skb);
+	if (r == -EREMOTEIO) {
+		phy->hard_fault = r;
+
+		nfc_hci_recv_frame(phy->hdev, NULL);
+
+		return IRQ_HANDLED;
+	} else if (r == -EAGAIN || r == -EIO) {
+		return IRQ_HANDLED;
+	} else if (r == -EBADMSG && phy->crc_trials < ARRAY_SIZE(wait_tab)) {
+		/*
+		 * With ST21NFCA, only one interface (I2C, RF or SWP)
+		 * may be active at a time.
+		 * Having incorrect crc is usually due to i2c macrocell
+		 * deactivation in the middle of a transmission.
+		 * It may generate corrupted data on i2c.
+		 * We give sometime to get i2c back.
+		 * The complete frame will be repeated.
+		 */
+		msleep(wait_tab[phy->crc_trials]);
+		phy->crc_trials++;
+		phy->current_read_len = 0;
+		kfree_skb(phy->pending_skb);
+	} else if (r > 0) {
+		/*
+		 * We succeeded to read data from the CLF and
+		 * data is valid.
+		 * Reset counter.
+		 */
+		nfc_hci_recv_frame(phy->hdev, phy->pending_skb);
+		phy->crc_trials = 0;
+	}
+
+	phy->pending_skb = alloc_skb(ST21NFCA_HCI_LLC_MAX_SIZE * 2, GFP_KERNEL);
+	if (phy->pending_skb == NULL) {
+		phy->hard_fault = -ENOMEM;
+		nfc_hci_recv_frame(phy->hdev, NULL);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static struct nfc_phy_ops i2c_phy_ops = {
+	.write = st21nfca_hci_i2c_write,
+	.enable = st21nfca_hci_i2c_enable,
+	.disable = st21nfca_hci_i2c_disable,
+};
+
+#ifdef CONFIG_OF
+static int st21nfca_hci_i2c_of_request_resources(struct i2c_client *client)
+{
+	struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client);
+	struct device_node *pp;
+	int gpio;
+	int r;
+
+	pp = client->dev.of_node;
+	if (!pp)
+		return -ENODEV;
+
+	/* Get GPIO from device tree */
+	gpio = of_get_named_gpio(pp, "enable-gpios", 0);
+	if (gpio < 0) {
+		nfc_err(&client->dev, "Failed to retrieve enable-gpios from device tree\n");
+		return gpio;
+	}
+
+	/* GPIO request and configuration */
+	r = devm_gpio_request(&client->dev, gpio, "clf_enable");
+	if (r) {
+		nfc_err(&client->dev, "Failed to request enable pin\n");
+		return -ENODEV;
+	}
+
+	r = gpio_direction_output(gpio, 1);
+	if (r) {
+		nfc_err(&client->dev, "Failed to set enable pin direction as output\n");
+		return -ENODEV;
+	}
+	phy->gpio_ena = gpio;
+
+	/* IRQ */
+	r = irq_of_parse_and_map(pp, 0);
+	if (r < 0) {
+		nfc_err(&client->dev,
+				"Unable to get irq, error: %d\n", r);
+		return r;
+	}
+
+	phy->irq_polarity = irq_get_trigger_type(r);
+	client->irq = r;
+
+	return 0;
+}
+#else
+static int st21nfca_hci_i2c_of_request_resources(struct i2c_client *client)
+{
+	return -ENODEV;
+}
+#endif
+
+static int st21nfca_hci_i2c_request_resources(struct i2c_client *client)
+{
+	struct st21nfca_nfc_platform_data *pdata;
+	struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client);
+	int r;
+	int irq;
+
+	pdata = client->dev.platform_data;
+	if (pdata == NULL) {
+		nfc_err(&client->dev, "No platform data\n");
+		return -EINVAL;
+	}
+
+	/* store for later use */
+	phy->gpio_irq = pdata->gpio_irq;
+	phy->gpio_ena = pdata->gpio_ena;
+	phy->irq_polarity = pdata->irq_polarity;
+
+	r = devm_gpio_request(&client->dev, phy->gpio_irq, "wake_up");
+	if (r) {
+		pr_err("%s : gpio_request failed\n", __FILE__);
+		return -ENODEV;
+	}
+
+	r = gpio_direction_input(phy->gpio_irq);
+	if (r) {
+		pr_err("%s : gpio_direction_input failed\n", __FILE__);
+		return -ENODEV;
+	}
+
+	if (phy->gpio_ena > 0) {
+		r = devm_gpio_request(&client->dev,
+					phy->gpio_ena, "clf_enable");
+		if (r) {
+			pr_err("%s : ena gpio_request failed\n", __FILE__);
+			return -ENODEV;
+		}
+		r = gpio_direction_output(phy->gpio_ena, 1);
+
+		if (r) {
+			pr_err("%s : ena gpio_direction_output failed\n",
+			       __FILE__);
+			return -ENODEV;
+		}
+	}
+
+	/* IRQ */
+	irq = gpio_to_irq(phy->gpio_irq);
+	if (irq < 0) {
+		nfc_err(&client->dev,
+				"Unable to get irq number for GPIO %d error %d\n",
+				phy->gpio_irq, r);
+		return -ENODEV;
+	}
+	client->irq = irq;
+
+	return 0;
+}
+
+static int st21nfca_hci_i2c_probe(struct i2c_client *client,
+				  const struct i2c_device_id *id)
+{
+	struct st21nfca_i2c_phy *phy;
+	struct st21nfca_nfc_platform_data *pdata;
+	int r;
+
+	dev_dbg(&client->dev, "%s\n", __func__);
+	dev_dbg(&client->dev, "IRQ: %d\n", client->irq);
+
+	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
+		nfc_err(&client->dev, "Need I2C_FUNC_I2C\n");
+		return -ENODEV;
+	}
+
+	phy = devm_kzalloc(&client->dev, sizeof(struct st21nfca_i2c_phy),
+			   GFP_KERNEL);
+	if (!phy) {
+		nfc_err(&client->dev,
+			"Cannot allocate memory for st21nfca i2c phy.\n");
+		return -ENOMEM;
+	}
+
+	phy->i2c_dev = client;
+	phy->pending_skb = alloc_skb(ST21NFCA_HCI_LLC_MAX_SIZE * 2, GFP_KERNEL);
+	if (phy->pending_skb == NULL)
+		return -ENOMEM;
+
+	phy->current_read_len = 0;
+	phy->crc_trials = 0;
+	mutex_init(&phy->phy_lock);
+	i2c_set_clientdata(client, phy);
+
+	pdata = client->dev.platform_data;
+	if (!pdata && client->dev.of_node) {
+		r = st21nfca_hci_i2c_of_request_resources(client);
+		if (r) {
+			nfc_err(&client->dev, "No platform data\n");
+			return r;
+		}
+	} else if (pdata) {
+		r = st21nfca_hci_i2c_request_resources(client);
+		if (r) {
+			nfc_err(&client->dev, "Cannot get platform resources\n");
+			return r;
+		}
+	} else {
+		nfc_err(&client->dev, "st21nfca platform resources not available\n");
+		return -ENODEV;
+	}
+
+	r = st21nfca_hci_platform_init(phy);
+	if (r < 0) {
+		nfc_err(&client->dev, "Unable to reboot st21nfca\n");
+		return -ENODEV;
+	}
+
+	r = devm_request_threaded_irq(&client->dev, client->irq, NULL,
+				st21nfca_hci_irq_thread_fn,
+				phy->irq_polarity | IRQF_ONESHOT,
+				ST21NFCA_HCI_DRIVER_NAME, phy);
+	if (r < 0) {
+		nfc_err(&client->dev, "Unable to register IRQ handler\n");
+		return r;
+	}
+
+	return st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
+			       ST21NFCA_FRAME_HEADROOM, ST21NFCA_FRAME_TAILROOM,
+			       ST21NFCA_HCI_LLC_MAX_PAYLOAD, &phy->hdev);
+}
+
+static int st21nfca_hci_i2c_remove(struct i2c_client *client)
+{
+	struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client);
+
+	dev_dbg(&client->dev, "%s\n", __func__);
+
+	st21nfca_hci_remove(phy->hdev);
+
+	if (phy->powered)
+		st21nfca_hci_i2c_disable(phy);
+
+	return 0;
+}
+
+static const struct of_device_id of_st21nfca_i2c_match[] = {
+	{ .compatible = "st,st21nfca_i2c", },
+	{}
+};
+
+static struct i2c_driver st21nfca_hci_i2c_driver = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = ST21NFCA_HCI_I2C_DRIVER_NAME,
+		.owner = THIS_MODULE,
+		.of_match_table = of_match_ptr(of_st21nfca_i2c_match),
+	},
+	.probe = st21nfca_hci_i2c_probe,
+	.id_table = st21nfca_hci_i2c_id_table,
+	.remove = st21nfca_hci_i2c_remove,
+};
+
+module_i2c_driver(st21nfca_hci_i2c_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/nfc/st21nfca/st21nfca.c b/drivers/nfc/st21nfca/st21nfca.c
new file mode 100644
index 00000000000..51e0f00b3a4
--- /dev/null
+++ b/drivers/nfc/st21nfca/st21nfca.c
@@ -0,0 +1,698 @@
+/*
+ * HCI based Driver for STMicroelectronics NFC Chip
+ *
+ * Copyright (C) 2014  STMicroelectronics SAS. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/module.h>
+#include <linux/nfc.h>
+#include <net/nfc/hci.h>
+#include <net/nfc/llc.h>
+
+#include "st21nfca.h"
+
+#define DRIVER_DESC "HCI NFC driver for ST21NFCA"
+
+#define FULL_VERSION_LEN 3
+
+/* Proprietary gates, events, commands and registers */
+
+/* Commands that apply to all RF readers */
+#define ST21NFCA_RF_READER_CMD_PRESENCE_CHECK	0x30
+
+#define ST21NFCA_RF_READER_ISO15693_GATE	0x12
+#define ST21NFCA_RF_READER_ISO15693_INVENTORY 0x01
+
+/*
+ * Reader gate for communication with contact-less cards using Type A
+ * protocol ISO14443-3 but not compliant with ISO14443-4
+ */
+#define ST21NFCA_RF_READER_14443_3_A_GATE	0x15
+#define ST21NFCA_RF_READER_14443_3_A_UID	0x02
+#define ST21NFCA_RF_READER_14443_3_A_ATQA	0x03
+#define ST21NFCA_RF_READER_14443_3_A_SAK	0x04
+
+#define ST21NFCA_DEVICE_MGNT_GATE		0x01
+#define ST21NFCA_DEVICE_MGNT_PIPE		0x02
+
+#define ST21NFCA_DM_GETINFO         0x13
+#define ST21NFCA_DM_GETINFO_PIPE_LIST       0x02
+#define ST21NFCA_DM_GETINFO_PIPE_INFO       0x01
+#define ST21NFCA_DM_PIPE_CREATED        0x02
+#define ST21NFCA_DM_PIPE_OPEN           0x04
+#define ST21NFCA_DM_RF_ACTIVE           0x80
+
+#define ST21NFCA_DM_IS_PIPE_OPEN(p) \
+	((p & 0x0f) == (ST21NFCA_DM_PIPE_CREATED | ST21NFCA_DM_PIPE_OPEN))
+
+#define ST21NFCA_NFC_MODE	0x03	/* NFC_MODE parameter*/
+
+static DECLARE_BITMAP(dev_mask, ST21NFCA_NUM_DEVICES);
+
+static struct nfc_hci_gate st21nfca_gates[] = {
+	{NFC_HCI_ADMIN_GATE, NFC_HCI_ADMIN_PIPE},
+	{NFC_HCI_LOOPBACK_GATE, NFC_HCI_INVALID_PIPE},
+	{NFC_HCI_ID_MGMT_GATE, NFC_HCI_INVALID_PIPE},
+	{NFC_HCI_LINK_MGMT_GATE, NFC_HCI_LINK_MGMT_PIPE},
+	{NFC_HCI_RF_READER_B_GATE, NFC_HCI_INVALID_PIPE},
+	{NFC_HCI_RF_READER_A_GATE, NFC_HCI_INVALID_PIPE},
+	{ST21NFCA_DEVICE_MGNT_GATE, ST21NFCA_DEVICE_MGNT_PIPE},
+	{ST21NFCA_RF_READER_F_GATE, NFC_HCI_INVALID_PIPE},
+	{ST21NFCA_RF_READER_14443_3_A_GATE, NFC_HCI_INVALID_PIPE},
+	{ST21NFCA_RF_READER_ISO15693_GATE, NFC_HCI_INVALID_PIPE},
+};
+
+struct st21nfca_pipe_info {
+	u8 pipe_state;
+	u8 src_host_id;
+	u8 src_gate_id;
+	u8 dst_host_id;
+	u8 dst_gate_id;
+} __packed;
+
+/* Largest headroom needed for outgoing custom commands */
+#define ST21NFCA_CMDS_HEADROOM  7
+
+static int st21nfca_hci_load_session(struct nfc_hci_dev *hdev)
+{
+	int i, j, r;
+	struct sk_buff *skb_pipe_list, *skb_pipe_info;
+	struct st21nfca_pipe_info *info;
+
+	u8 pipe_list[] = { ST21NFCA_DM_GETINFO_PIPE_LIST,
+		NFC_HCI_TERMINAL_HOST_ID
+	};
+	u8 pipe_info[] = { ST21NFCA_DM_GETINFO_PIPE_INFO,
+		NFC_HCI_TERMINAL_HOST_ID, 0
+	};
+
+	skb_pipe_list = alloc_skb(ST21NFCA_HCI_LLC_MAX_SIZE, GFP_KERNEL);
+	if (!skb_pipe_list) {
+		r = -ENOMEM;
+		goto free_list;
+	}
+
+	skb_pipe_info = alloc_skb(ST21NFCA_HCI_LLC_MAX_SIZE, GFP_KERNEL);
+	if (!skb_pipe_info) {
+		r = -ENOMEM;
+		goto free_info;
+	}
+
+	/* On ST21NFCA device pipes number are dynamics
+	 * A maximum of 16 pipes can be created at the same time
+	 * If pipes are already created, hci_dev_up will fail.
+	 * Doing a clear all pipe is a bad idea because:
+	 * - It does useless EEPROM cycling
+	 * - It might cause issue for secure elements support
+	 * (such as removing connectivity or APDU reader pipe)
+	 * A better approach on ST21NFCA is to:
+	 * - get a pipe list for each host.
+	 * (eg: NFC_HCI_HOST_CONTROLLER_ID for now).
+	 * (TODO Later on UICC HOST and eSE HOST)
+	 * - get pipe information
+	 * - match retrieved pipe list in st21nfca_gates
+	 * ST21NFCA_DEVICE_MGNT_GATE is a proprietary gate
+	 * with ST21NFCA_DEVICE_MGNT_PIPE.
+	 * Pipe can be closed and need to be open.
+	 */
+	r = nfc_hci_connect_gate(hdev, NFC_HCI_HOST_CONTROLLER_ID,
+		ST21NFCA_DEVICE_MGNT_GATE, ST21NFCA_DEVICE_MGNT_PIPE);
+	if (r < 0)
+		goto free_info;
+
+	/* Get pipe list */
+	r = nfc_hci_send_cmd(hdev, ST21NFCA_DEVICE_MGNT_GATE,
+			ST21NFCA_DM_GETINFO, pipe_list, sizeof(pipe_list),
+			&skb_pipe_list);
+	if (r < 0)
+		goto free_info;
+
+	/* Complete the existing gate_pipe table */
+	for (i = 0; i < skb_pipe_list->len; i++) {
+		pipe_info[2] = skb_pipe_list->data[i];
+		r = nfc_hci_send_cmd(hdev, ST21NFCA_DEVICE_MGNT_GATE,
+					ST21NFCA_DM_GETINFO, pipe_info,
+					sizeof(pipe_info), &skb_pipe_info);
+
+		if (r)
+			continue;
+
+		/*
+		 * Match pipe ID and gate ID
+		 * Output format from ST21NFC_DM_GETINFO is:
+		 * - pipe state (1byte)
+		 * - source hid (1byte)
+		 * - source gid (1byte)
+		 * - destination hid (1byte)
+		 * - destination gid (1byte)
+		 */
+		info = (struct st21nfca_pipe_info *) skb_pipe_info->data;
+		for (j = 0; (j < ARRAY_SIZE(st21nfca_gates)) &&
+			(st21nfca_gates[j].gate != info->dst_gate_id);
+			j++)
+			;
+
+		if (j < ARRAY_SIZE(st21nfca_gates) &&
+			st21nfca_gates[j].gate == info->dst_gate_id &&
+			ST21NFCA_DM_IS_PIPE_OPEN(info->pipe_state)) {
+			st21nfca_gates[j].pipe = pipe_info[2];
+			hdev->gate2pipe[st21nfca_gates[j].gate] =
+				st21nfca_gates[j].pipe;
+		}
+	}
+
+	/*
+	 * 3 gates have a well known pipe ID.
+	 * They will never appear in the pipe list
+	 */
+	if (skb_pipe_list->len + 3 < ARRAY_SIZE(st21nfca_gates)) {
+		for (i = skb_pipe_list->len + 3;
+				i < ARRAY_SIZE(st21nfca_gates); i++) {
+			r = nfc_hci_connect_gate(hdev,
+					NFC_HCI_HOST_CONTROLLER_ID,
+					st21nfca_gates[i].gate,
+					st21nfca_gates[i].pipe);
+			if (r < 0)
+				goto free_info;
+		}
+	}
+
+	memcpy(hdev->init_data.gates, st21nfca_gates, sizeof(st21nfca_gates));
+free_info:
+	kfree_skb(skb_pipe_info);
+free_list:
+	kfree_skb(skb_pipe_list);
+	return r;
+}
+
+static int st21nfca_hci_open(struct nfc_hci_dev *hdev)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+	int r;
+
+	mutex_lock(&info->info_lock);
+
+	if (info->state != ST21NFCA_ST_COLD) {
+		r = -EBUSY;
+		goto out;
+	}
+
+	r = info->phy_ops->enable(info->phy_id);
+
+	if (r == 0)
+		info->state = ST21NFCA_ST_READY;
+
+out:
+	mutex_unlock(&info->info_lock);
+	return r;
+}
+
+static void st21nfca_hci_close(struct nfc_hci_dev *hdev)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	mutex_lock(&info->info_lock);
+
+	if (info->state == ST21NFCA_ST_COLD)
+		goto out;
+
+	info->phy_ops->disable(info->phy_id);
+	info->state = ST21NFCA_ST_COLD;
+
+out:
+	mutex_unlock(&info->info_lock);
+}
+
+static int st21nfca_hci_ready(struct nfc_hci_dev *hdev)
+{
+	struct sk_buff *skb;
+
+	u8 param;
+	int r;
+
+	param = NFC_HCI_UICC_HOST_ID;
+	r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE,
+			      NFC_HCI_ADMIN_WHITELIST, &param, 1);
+	if (r < 0)
+		return r;
+
+	/* Set NFC_MODE in device management gate to enable */
+	r = nfc_hci_get_param(hdev, ST21NFCA_DEVICE_MGNT_GATE,
+			      ST21NFCA_NFC_MODE, &skb);
+	if (r < 0)
+		return r;
+
+	if (skb->data[0] == 0) {
+		kfree_skb(skb);
+		param = 1;
+
+		r = nfc_hci_set_param(hdev, ST21NFCA_DEVICE_MGNT_GATE,
+					ST21NFCA_NFC_MODE, &param, 1);
+		if (r < 0)
+			return r;
+	}
+
+	r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
+			       NFC_HCI_EVT_END_OPERATION, NULL, 0);
+	if (r < 0)
+		return r;
+
+	r = nfc_hci_get_param(hdev, NFC_HCI_ID_MGMT_GATE,
+			      NFC_HCI_ID_MGMT_VERSION_SW, &skb);
+	if (r < 0)
+		return r;
+
+	if (skb->len != FULL_VERSION_LEN) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	print_hex_dump(KERN_DEBUG, "FULL VERSION SOFTWARE INFO: ",
+		       DUMP_PREFIX_NONE, 16, 1,
+		       skb->data, FULL_VERSION_LEN, false);
+
+	kfree_skb(skb);
+
+	return 0;
+}
+
+static int st21nfca_hci_xmit(struct nfc_hci_dev *hdev, struct sk_buff *skb)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	return info->phy_ops->write(info->phy_id, skb);
+}
+
+static int st21nfca_hci_start_poll(struct nfc_hci_dev *hdev,
+				   u32 im_protocols, u32 tm_protocols)
+{
+	int r;
+
+	pr_info(DRIVER_DESC ": %s protocols 0x%x 0x%x\n",
+		__func__, im_protocols, tm_protocols);
+
+	r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
+			       NFC_HCI_EVT_END_OPERATION, NULL, 0);
+	if (r < 0)
+		return r;
+	if (im_protocols) {
+		/*
+		 * enable polling according to im_protocols & tm_protocols
+		 * - CLOSE pipe according to im_protocols & tm_protocols
+		 */
+		if ((NFC_HCI_RF_READER_B_GATE & im_protocols) == 0) {
+			r = nfc_hci_disconnect_gate(hdev,
+					NFC_HCI_RF_READER_B_GATE);
+			if (r < 0)
+				return r;
+		}
+
+		if ((NFC_HCI_RF_READER_A_GATE & im_protocols) == 0) {
+			r = nfc_hci_disconnect_gate(hdev,
+					NFC_HCI_RF_READER_A_GATE);
+			if (r < 0)
+				return r;
+		}
+
+		if ((ST21NFCA_RF_READER_F_GATE & im_protocols) == 0) {
+			r = nfc_hci_disconnect_gate(hdev,
+					ST21NFCA_RF_READER_F_GATE);
+			if (r < 0)
+				return r;
+		}
+
+		if ((ST21NFCA_RF_READER_14443_3_A_GATE & im_protocols) == 0) {
+			r = nfc_hci_disconnect_gate(hdev,
+					ST21NFCA_RF_READER_14443_3_A_GATE);
+			if (r < 0)
+				return r;
+		}
+
+		if ((ST21NFCA_RF_READER_ISO15693_GATE & im_protocols) == 0) {
+			r = nfc_hci_disconnect_gate(hdev,
+					ST21NFCA_RF_READER_ISO15693_GATE);
+			if (r < 0)
+				return r;
+		}
+
+		r = nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
+				       NFC_HCI_EVT_READER_REQUESTED, NULL, 0);
+		if (r < 0)
+			nfc_hci_send_event(hdev, NFC_HCI_RF_READER_A_GATE,
+					   NFC_HCI_EVT_END_OPERATION, NULL, 0);
+	}
+	return r;
+}
+
+static int st21nfca_get_iso14443_3_atqa(struct nfc_hci_dev *hdev, u16 *atqa)
+{
+	int r;
+	struct sk_buff *atqa_skb = NULL;
+
+	r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_14443_3_A_GATE,
+			      ST21NFCA_RF_READER_14443_3_A_ATQA, &atqa_skb);
+	if (r < 0)
+		goto exit;
+
+	if (atqa_skb->len != 2) {
+		r = -EPROTO;
+		goto exit;
+	}
+
+	*atqa = be16_to_cpu(*(__be16 *) atqa_skb->data);
+
+exit:
+	kfree_skb(atqa_skb);
+	return r;
+}
+
+static int st21nfca_get_iso14443_3_sak(struct nfc_hci_dev *hdev, u8 *sak)
+{
+	int r;
+	struct sk_buff *sak_skb = NULL;
+
+	r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_14443_3_A_GATE,
+			      ST21NFCA_RF_READER_14443_3_A_SAK, &sak_skb);
+	if (r < 0)
+		goto exit;
+
+	if (sak_skb->len != 1) {
+		r = -EPROTO;
+		goto exit;
+	}
+
+	*sak = sak_skb->data[0];
+
+exit:
+	kfree_skb(sak_skb);
+	return r;
+}
+
+static int st21nfca_get_iso14443_3_uid(struct nfc_hci_dev *hdev, u8 *gate,
+				       int *len)
+{
+	int r;
+	struct sk_buff *uid_skb = NULL;
+
+	r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_14443_3_A_GATE,
+			      ST21NFCA_RF_READER_14443_3_A_UID, &uid_skb);
+	if (r < 0)
+		goto exit;
+
+	if (uid_skb->len == 0 || uid_skb->len > NFC_NFCID1_MAXSIZE) {
+		r = -EPROTO;
+		goto exit;
+	}
+
+	gate = uid_skb->data;
+	*len = uid_skb->len;
+exit:
+	kfree_skb(uid_skb);
+	return r;
+}
+
+static int st21nfca_get_iso15693_inventory(struct nfc_hci_dev *hdev,
+					   struct nfc_target *target)
+{
+	int r;
+	struct sk_buff *inventory_skb = NULL;
+
+	r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_ISO15693_GATE,
+			      ST21NFCA_RF_READER_ISO15693_INVENTORY,
+			      &inventory_skb);
+	if (r < 0)
+		goto exit;
+
+	skb_pull(inventory_skb, 2);
+
+	if (inventory_skb->len == 0 ||
+	    inventory_skb->len > NFC_ISO15693_UID_MAXSIZE) {
+		r = -EPROTO;
+		goto exit;
+	}
+
+	memcpy(target->iso15693_uid, inventory_skb->data, inventory_skb->len);
+	target->iso15693_dsfid	= inventory_skb->data[1];
+	target->is_iso15693 = 1;
+exit:
+	kfree_skb(inventory_skb);
+	return r;
+}
+
+static int st21nfca_hci_target_from_gate(struct nfc_hci_dev *hdev, u8 gate,
+					 struct nfc_target *target)
+{
+	int r, len;
+	u16 atqa;
+	u8 sak;
+	u8 uid[NFC_NFCID1_MAXSIZE];
+
+	switch (gate) {
+	case ST21NFCA_RF_READER_F_GATE:
+		target->supported_protocols = NFC_PROTO_FELICA_MASK;
+		break;
+	case ST21NFCA_RF_READER_14443_3_A_GATE:
+		/* ISO14443-3 type 1 or 2 tags */
+		r = st21nfca_get_iso14443_3_atqa(hdev, &atqa);
+		if (r < 0)
+			return r;
+		if (atqa == 0x000c) {
+			target->supported_protocols = NFC_PROTO_JEWEL_MASK;
+			target->sens_res = 0x0c00;
+		} else {
+			r = st21nfca_get_iso14443_3_sak(hdev, &sak);
+			if (r < 0)
+				return r;
+
+			r = st21nfca_get_iso14443_3_uid(hdev, uid, &len);
+			if (r < 0)
+				return r;
+
+			target->supported_protocols =
+			    nfc_hci_sak_to_protocol(sak);
+			if (target->supported_protocols == 0xffffffff)
+				return -EPROTO;
+
+			target->sens_res = atqa;
+			target->sel_res = sak;
+			memcpy(target->nfcid1, uid, len);
+			target->nfcid1_len = len;
+		}
+
+		break;
+	case ST21NFCA_RF_READER_ISO15693_GATE:
+		target->supported_protocols = NFC_PROTO_ISO15693_MASK;
+		r = st21nfca_get_iso15693_inventory(hdev, target);
+		if (r < 0)
+			return r;
+		break;
+	default:
+		return -EPROTO;
+	}
+
+	return 0;
+}
+
+#define ST21NFCA_CB_TYPE_READER_ISO15693 1
+static void st21nfca_hci_data_exchange_cb(void *context, struct sk_buff *skb,
+					  int err)
+{
+	struct st21nfca_hci_info *info = context;
+
+	switch (info->async_cb_type) {
+	case ST21NFCA_CB_TYPE_READER_ISO15693:
+		if (err == 0)
+			skb_trim(skb, skb->len - 1);
+		info->async_cb(info->async_cb_context, skb, err);
+		break;
+	default:
+		if (err == 0)
+			kfree_skb(skb);
+		break;
+	}
+}
+
+/*
+ * Returns:
+ * <= 0: driver handled the data exchange
+ *    1: driver doesn't especially handle, please do standard processing
+ */
+static int st21nfca_hci_im_transceive(struct nfc_hci_dev *hdev,
+				      struct nfc_target *target,
+				      struct sk_buff *skb,
+				      data_exchange_cb_t cb, void *cb_context)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	pr_info(DRIVER_DESC ": %s for gate=%d len=%d\n", __func__,
+		target->hci_reader_gate, skb->len);
+
+	switch (target->hci_reader_gate) {
+	case ST21NFCA_RF_READER_F_GATE:
+		*skb_push(skb, 1) = 0x1a;
+		return nfc_hci_send_cmd_async(hdev, target->hci_reader_gate,
+					      ST21NFCA_WR_XCHG_DATA, skb->data,
+					      skb->len, cb, cb_context);
+	case ST21NFCA_RF_READER_14443_3_A_GATE:
+		*skb_push(skb, 1) = 0x1a;	/* CTR, see spec:10.2.2.1 */
+
+		return nfc_hci_send_cmd_async(hdev, target->hci_reader_gate,
+					      ST21NFCA_WR_XCHG_DATA, skb->data,
+					      skb->len, cb, cb_context);
+	case ST21NFCA_RF_READER_ISO15693_GATE:
+		info->async_cb_type = ST21NFCA_CB_TYPE_READER_ISO15693;
+		info->async_cb = cb;
+		info->async_cb_context = cb_context;
+
+		*skb_push(skb, 1) = 0x17;
+
+		return nfc_hci_send_cmd_async(hdev, target->hci_reader_gate,
+					      ST21NFCA_WR_XCHG_DATA, skb->data,
+					      skb->len,
+					      st21nfca_hci_data_exchange_cb,
+					      info);
+		break;
+	default:
+		return 1;
+	}
+}
+
+static int st21nfca_hci_check_presence(struct nfc_hci_dev *hdev,
+				       struct nfc_target *target)
+{
+	u8 fwi = 0x11;
+	switch (target->hci_reader_gate) {
+	case NFC_HCI_RF_READER_A_GATE:
+	case NFC_HCI_RF_READER_B_GATE:
+		/*
+		 * PRESENCE_CHECK on those gates is available
+		 * However, the answer to this command is taking 3 * fwi
+		 * if the card is no present.
+		 * Instead, we send an empty I-Frame with a very short
+		 * configurable fwi ~604µs.
+		 */
+		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
+					ST21NFCA_WR_XCHG_DATA, &fwi, 1, NULL);
+	case ST21NFCA_RF_READER_14443_3_A_GATE:
+		return nfc_hci_send_cmd(hdev, target->hci_reader_gate,
+					ST21NFCA_RF_READER_CMD_PRESENCE_CHECK,
+					NULL, 0, NULL);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static struct nfc_hci_ops st21nfca_hci_ops = {
+	.open = st21nfca_hci_open,
+	.close = st21nfca_hci_close,
+	.load_session = st21nfca_hci_load_session,
+	.hci_ready = st21nfca_hci_ready,
+	.xmit = st21nfca_hci_xmit,
+	.start_poll = st21nfca_hci_start_poll,
+	.target_from_gate = st21nfca_hci_target_from_gate,
+	.im_transceive = st21nfca_hci_im_transceive,
+	.check_presence = st21nfca_hci_check_presence,
+};
+
+int st21nfca_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops,
+		       char *llc_name, int phy_headroom, int phy_tailroom,
+		       int phy_payload, struct nfc_hci_dev **hdev)
+{
+	struct st21nfca_hci_info *info;
+	int r = 0;
+	int dev_num;
+	u32 protocols;
+	struct nfc_hci_init_data init_data;
+	unsigned long quirks = 0;
+
+	info = kzalloc(sizeof(struct st21nfca_hci_info), GFP_KERNEL);
+	if (!info) {
+		r = -ENOMEM;
+		goto err_alloc_hdev;
+	}
+
+	info->phy_ops = phy_ops;
+	info->phy_id = phy_id;
+	info->state = ST21NFCA_ST_COLD;
+	mutex_init(&info->info_lock);
+
+	init_data.gate_count = ARRAY_SIZE(st21nfca_gates);
+
+	memcpy(init_data.gates, st21nfca_gates, sizeof(st21nfca_gates));
+
+	/*
+	 * Session id must include the driver name + i2c bus addr
+	 * persistent info to discriminate 2 identical chips
+	 */
+	dev_num = find_first_zero_bit(dev_mask, ST21NFCA_NUM_DEVICES);
+	if (dev_num >= ST21NFCA_NUM_DEVICES)
+		goto err_alloc_hdev;
+
+	scnprintf(init_data.session_id, sizeof(init_data.session_id), "%s%2x",
+		  "ST21AH", dev_num);
+
+	protocols = NFC_PROTO_JEWEL_MASK |
+	    NFC_PROTO_MIFARE_MASK |
+	    NFC_PROTO_FELICA_MASK |
+	    NFC_PROTO_ISO14443_MASK |
+	    NFC_PROTO_ISO14443_B_MASK |
+	    NFC_PROTO_ISO15693_MASK;
+
+	set_bit(NFC_HCI_QUIRK_SHORT_CLEAR, &quirks);
+
+	info->hdev =
+	    nfc_hci_allocate_device(&st21nfca_hci_ops, &init_data, quirks,
+				    protocols, llc_name,
+				    phy_headroom + ST21NFCA_CMDS_HEADROOM,
+				    phy_tailroom, phy_payload);
+
+	if (!info->hdev) {
+		pr_err("Cannot allocate nfc hdev.\n");
+		r = -ENOMEM;
+		goto err_alloc_hdev;
+	}
+
+	nfc_hci_set_clientdata(info->hdev, info);
+
+	r = nfc_hci_register_device(info->hdev);
+	if (r)
+		goto err_regdev;
+
+	*hdev = info->hdev;
+
+	return 0;
+
+err_regdev:
+	nfc_hci_free_device(info->hdev);
+
+err_alloc_hdev:
+	kfree(info);
+
+	return r;
+}
+EXPORT_SYMBOL(st21nfca_hci_probe);
+
+void st21nfca_hci_remove(struct nfc_hci_dev *hdev)
+{
+	struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
+
+	nfc_hci_unregister_device(hdev);
+	nfc_hci_free_device(hdev);
+	kfree(info);
+}
+EXPORT_SYMBOL(st21nfca_hci_remove);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/nfc/st21nfca/st21nfca.h b/drivers/nfc/st21nfca/st21nfca.h
new file mode 100644
index 00000000000..334cd90bcc8
--- /dev/null
+++ b/drivers/nfc/st21nfca/st21nfca.h
@@ -0,0 +1,87 @@
+/*
+ * Copyright (C) 2014  STMicroelectronics SAS. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __LOCAL_ST21NFCA_H_
+#define __LOCAL_ST21NFCA_H_
+
+#include <net/nfc/hci.h>
+
+#define HCI_MODE 0
+
+/* framing in HCI mode */
+#define ST21NFCA_SOF_EOF_LEN    2
+
+/* Almost every time value is 0 */
+#define ST21NFCA_HCI_LLC_LEN    1
+
+/* Size in worst case :
+ * In normal case CRC len = 2 but byte stuffing
+ * may appear in case one CRC byte = ST21NFCA_SOF_EOF
+ */
+#define ST21NFCA_HCI_LLC_CRC    4
+
+#define ST21NFCA_HCI_LLC_LEN_CRC        (ST21NFCA_SOF_EOF_LEN + \
+						ST21NFCA_HCI_LLC_LEN + \
+						ST21NFCA_HCI_LLC_CRC)
+#define ST21NFCA_HCI_LLC_MIN_SIZE       (1 + ST21NFCA_HCI_LLC_LEN_CRC)
+
+/* Worst case when adding byte stuffing between each byte */
+#define ST21NFCA_HCI_LLC_MAX_PAYLOAD    29
+#define ST21NFCA_HCI_LLC_MAX_SIZE       (ST21NFCA_HCI_LLC_LEN_CRC + 1 + \
+					ST21NFCA_HCI_LLC_MAX_PAYLOAD)
+
+#define DRIVER_DESC "HCI NFC driver for ST21NFCA"
+
+#define ST21NFCA_HCI_MODE 0
+
+#define ST21NFCA_NUM_DEVICES 256
+
+int st21nfca_hci_probe(void *phy_id, struct nfc_phy_ops *phy_ops,
+		       char *llc_name, int phy_headroom, int phy_tailroom,
+		       int phy_payload, struct nfc_hci_dev **hdev);
+void st21nfca_hci_remove(struct nfc_hci_dev *hdev);
+
+enum st21nfca_state {
+	ST21NFCA_ST_COLD,
+	ST21NFCA_ST_READY,
+};
+
+struct st21nfca_hci_info {
+	struct nfc_phy_ops *phy_ops;
+	void *phy_id;
+
+	struct nfc_hci_dev *hdev;
+
+	enum st21nfca_state state;
+
+	struct mutex info_lock;
+
+	int async_cb_type;
+	data_exchange_cb_t async_cb;
+	void *async_cb_context;
+
+} __packed;
+
+/* Reader RF commands */
+#define ST21NFCA_WR_XCHG_DATA            0x10
+
+#define ST21NFCA_RF_READER_F_GATE               0x14
+#define ST21NFCA_RF_READER_F_DATARATE 0x01
+#define ST21NFCA_RF_READER_F_DATARATE_106 0x01
+#define ST21NFCA_RF_READER_F_DATARATE_212 0x02
+#define ST21NFCA_RF_READER_F_DATARATE_424 0x04
+
+#endif /* __LOCAL_ST21NFCA_H_ */
diff --git a/drivers/nfc/trf7970a.c b/drivers/nfc/trf7970a.c
index d9babe98647..3b78b031e61 100644
--- a/drivers/nfc/trf7970a.c
+++ b/drivers/nfc/trf7970a.c
@@ -16,6 +16,7 @@
 #include <linux/device.h>
 #include <linux/netdevice.h>
 #include <linux/interrupt.h>
+#include <linux/pm_runtime.h>
 #include <linux/nfc.h>
 #include <linux/skbuff.h>
 #include <linux/delay.h>
@@ -67,14 +68,14 @@
  * only the SRX bit set, it means that all of the data has been received
  * (once what's in the fifo has been read).  However, depending on timing
  * an interrupt status with only the SRX bit set may not be recived.  In
- * those cases, the timeout mechanism is used to wait 5 ms in case more
- * data arrives.  After 5 ms, it is assumed that all of the data has been
+ * those cases, the timeout mechanism is used to wait 20 ms in case more
+ * data arrives.  After 20 ms, it is assumed that all of the data has been
  * received and the accumulated rx data is sent upstream.  The
  * 'TRF7970A_ST_WAIT_FOR_RX_DATA_CONT' state is used for this purpose
  * (i.e., it indicates that some data has been received but we're not sure
  * if there is more coming so a timeout in this state means all data has
- * been received and there isn't an error).  The delay is 5 ms since delays
- * over 2 ms have been observed during testing (a little extra just in case).
+ * been received and there isn't an error).  The delay is 20 ms since delays
+ * of ~16 ms have been observed during testing.
  *
  * Type 2 write and sector select commands respond with a 4-bit ACK or NACK.
  * Having only 4 bits in the FIFO won't normally generate an interrupt so
@@ -104,8 +105,11 @@
 
 #define TRF7970A_SUPPORTED_PROTOCOLS \
 		(NFC_PROTO_MIFARE_MASK | NFC_PROTO_ISO14443_MASK |	\
+		 NFC_PROTO_ISO14443_B_MASK | NFC_PROTO_FELICA_MASK | \
 		 NFC_PROTO_ISO15693_MASK)
 
+#define TRF7970A_AUTOSUSPEND_DELAY		30000 /* 30 seconds */
+
 /* TX data must be prefixed with a FIFO reset cmd, a cmd that depends
  * on what the current framing is, the address of the TX length byte 1
  * register (0x1d), and the 2 byte length of the data to be transmitted.
@@ -120,7 +124,7 @@
 /* TX length is 3 nibbles long ==> 4KB - 1 bytes max */
 #define TRF7970A_TX_MAX				(4096 - 1)
 
-#define TRF7970A_WAIT_FOR_RX_DATA_TIMEOUT	5
+#define TRF7970A_WAIT_FOR_RX_DATA_TIMEOUT	20
 #define TRF7970A_WAIT_FOR_FIFO_DRAIN_TIMEOUT	3
 #define TRF7970A_WAIT_TO_ISSUE_ISO15693_EOF	20
 
@@ -330,13 +334,15 @@ struct trf7970a {
 	struct regulator		*regulator;
 	struct nfc_digital_dev		*ddev;
 	u32				quirks;
-	bool				powering_up;
 	bool				aborting;
 	struct sk_buff			*tx_skb;
 	struct sk_buff			*rx_skb;
 	nfc_digital_cmd_complete_t	cb;
 	void				*cb_arg;
+	u8				chip_status_ctrl;
 	u8				iso_ctrl;
+	u8				iso_ctrl_tech;
+	u8				modulator_sys_clk_ctrl;
 	u8				special_fcn_reg1;
 	int				technology;
 	int				framing;
@@ -681,7 +687,9 @@ static irqreturn_t trf7970a_irq(int irq, void *dev_id)
 			trf->ignore_timeout =
 				!cancel_delayed_work(&trf->timeout_work);
 			trf7970a_drain_fifo(trf, status);
-		} else if (!(status & TRF7970A_IRQ_STATUS_TX)) {
+		} else if (status == TRF7970A_IRQ_STATUS_TX) {
+			trf7970a_cmd(trf, TRF7970A_CMD_FIFO_RESET);
+		} else {
 			trf7970a_send_err_upstream(trf, -EIO);
 		}
 		break;
@@ -757,8 +765,8 @@ static int trf7970a_init(struct trf7970a *trf)
 	if (ret)
 		goto err_out;
 
-	ret = trf7970a_write(trf, TRF7970A_MODULATOR_SYS_CLK_CTRL,
-			TRF7970A_MODULATOR_DEPTH_OOK);
+	/* Must clear NFC Target Detection Level reg due to erratum */
+	ret = trf7970a_write(trf, TRF7970A_NFC_TARGET_LEVEL, 0);
 	if (ret)
 		goto err_out;
 
@@ -774,12 +782,7 @@ static int trf7970a_init(struct trf7970a *trf)
 
 	trf->special_fcn_reg1 = 0;
 
-	ret = trf7970a_write(trf, TRF7970A_CHIP_STATUS_CTRL,
-			TRF7970A_CHIP_STATUS_RF_ON |
-				TRF7970A_CHIP_STATUS_VRS5_3);
-	if (ret)
-		goto err_out;
-
+	trf->iso_ctrl = 0xff;
 	return 0;
 
 err_out:
@@ -791,53 +794,29 @@ static void trf7970a_switch_rf_off(struct trf7970a *trf)
 {
 	dev_dbg(trf->dev, "Switching rf off\n");
 
-	gpio_set_value(trf->en_gpio, 0);
-	gpio_set_value(trf->en2_gpio, 0);
+	trf->chip_status_ctrl &= ~TRF7970A_CHIP_STATUS_RF_ON;
+
+	trf7970a_write(trf, TRF7970A_CHIP_STATUS_CTRL, trf->chip_status_ctrl);
 
 	trf->aborting = false;
 	trf->state = TRF7970A_ST_OFF;
+
+	pm_runtime_mark_last_busy(trf->dev);
+	pm_runtime_put_autosuspend(trf->dev);
 }
 
-static int trf7970a_switch_rf_on(struct trf7970a *trf)
+static void trf7970a_switch_rf_on(struct trf7970a *trf)
 {
-	unsigned long delay;
-	int ret;
-
 	dev_dbg(trf->dev, "Switching rf on\n");
 
-	if (trf->powering_up)
-		usleep_range(5000, 6000);
-
-	gpio_set_value(trf->en2_gpio, 1);
-	usleep_range(1000, 2000);
-	gpio_set_value(trf->en_gpio, 1);
+	pm_runtime_get_sync(trf->dev);
 
-	/* The delay between enabling the trf7970a and issuing the first
-	 * command is significantly longer the very first time after powering
-	 * up.  Make sure the longer delay is only done the first time.
-	 */
-	if (trf->powering_up) {
-		delay = 20000;
-		trf->powering_up = false;
-	} else {
-		delay = 5000;
-	}
-
-	usleep_range(delay, delay + 1000);
-
-	ret = trf7970a_init(trf);
-	if (ret)
-		trf7970a_switch_rf_off(trf);
-	else
-		trf->state = TRF7970A_ST_IDLE;
-
-	return ret;
+	trf->state = TRF7970A_ST_IDLE;
 }
 
 static int trf7970a_switch_rf(struct nfc_digital_dev *ddev, bool on)
 {
 	struct trf7970a *trf = nfc_digital_get_drvdata(ddev);
-	int ret = 0;
 
 	dev_dbg(trf->dev, "Switching RF - state: %d, on: %d\n", trf->state, on);
 
@@ -846,7 +825,7 @@ static int trf7970a_switch_rf(struct nfc_digital_dev *ddev, bool on)
 	if (on) {
 		switch (trf->state) {
 		case TRF7970A_ST_OFF:
-			ret = trf7970a_switch_rf_on(trf);
+			trf7970a_switch_rf_on(trf);
 			break;
 		case TRF7970A_ST_IDLE:
 		case TRF7970A_ST_IDLE_RX_BLOCKED:
@@ -871,7 +850,7 @@ static int trf7970a_switch_rf(struct nfc_digital_dev *ddev, bool on)
 	}
 
 	mutex_unlock(&trf->lock);
-	return ret;
+	return 0;
 }
 
 static int trf7970a_config_rf_tech(struct trf7970a *trf, int tech)
@@ -882,10 +861,24 @@ static int trf7970a_config_rf_tech(struct trf7970a *trf, int tech)
 
 	switch (tech) {
 	case NFC_DIGITAL_RF_TECH_106A:
-		trf->iso_ctrl = TRF7970A_ISO_CTRL_14443A_106;
+		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_14443A_106;
+		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_OOK;
+		break;
+	case NFC_DIGITAL_RF_TECH_106B:
+		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_14443B_106;
+		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_ASK10;
+		break;
+	case NFC_DIGITAL_RF_TECH_212F:
+		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_FELICA_212;
+		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_ASK10;
+		break;
+	case NFC_DIGITAL_RF_TECH_424F:
+		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_FELICA_424;
+		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_ASK10;
 		break;
 	case NFC_DIGITAL_RF_TECH_ISO15693:
-		trf->iso_ctrl = TRF7970A_ISO_CTRL_15693_SGL_1OF4_2648;
+		trf->iso_ctrl_tech = TRF7970A_ISO_CTRL_15693_SGL_1OF4_2648;
+		trf->modulator_sys_clk_ctrl = TRF7970A_MODULATOR_DEPTH_OOK;
 		break;
 	default:
 		dev_dbg(trf->dev, "Unsupported rf technology: %d\n", tech);
@@ -899,24 +892,31 @@ static int trf7970a_config_rf_tech(struct trf7970a *trf, int tech)
 
 static int trf7970a_config_framing(struct trf7970a *trf, int framing)
 {
+	u8 iso_ctrl = trf->iso_ctrl_tech;
+	int ret;
+
 	dev_dbg(trf->dev, "framing: %d\n", framing);
 
 	switch (framing) {
 	case NFC_DIGITAL_FRAMING_NFCA_SHORT:
 	case NFC_DIGITAL_FRAMING_NFCA_STANDARD:
 		trf->tx_cmd = TRF7970A_CMD_TRANSMIT_NO_CRC;
-		trf->iso_ctrl |= TRF7970A_ISO_CTRL_RX_CRC_N;
+		iso_ctrl |= TRF7970A_ISO_CTRL_RX_CRC_N;
 		break;
 	case NFC_DIGITAL_FRAMING_NFCA_STANDARD_WITH_CRC_A:
 	case NFC_DIGITAL_FRAMING_NFCA_T4T:
+	case NFC_DIGITAL_FRAMING_NFCB:
+	case NFC_DIGITAL_FRAMING_NFCB_T4T:
+	case NFC_DIGITAL_FRAMING_NFCF:
+	case NFC_DIGITAL_FRAMING_NFCF_T3T:
 	case NFC_DIGITAL_FRAMING_ISO15693_INVENTORY:
 	case NFC_DIGITAL_FRAMING_ISO15693_T5T:
 		trf->tx_cmd = TRF7970A_CMD_TRANSMIT;
-		trf->iso_ctrl &= ~TRF7970A_ISO_CTRL_RX_CRC_N;
+		iso_ctrl &= ~TRF7970A_ISO_CTRL_RX_CRC_N;
 		break;
 	case NFC_DIGITAL_FRAMING_NFCA_T2T:
 		trf->tx_cmd = TRF7970A_CMD_TRANSMIT;
-		trf->iso_ctrl |= TRF7970A_ISO_CTRL_RX_CRC_N;
+		iso_ctrl |= TRF7970A_ISO_CTRL_RX_CRC_N;
 		break;
 	default:
 		dev_dbg(trf->dev, "Unsupported Framing: %d\n", framing);
@@ -925,24 +925,46 @@ static int trf7970a_config_framing(struct trf7970a *trf, int framing)
 
 	trf->framing = framing;
 
-	return trf7970a_write(trf, TRF7970A_ISO_CTRL, trf->iso_ctrl);
+	if (iso_ctrl != trf->iso_ctrl) {
+		ret = trf7970a_write(trf, TRF7970A_ISO_CTRL, iso_ctrl);
+		if (ret)
+			return ret;
+
+		trf->iso_ctrl = iso_ctrl;
+
+		ret = trf7970a_write(trf, TRF7970A_MODULATOR_SYS_CLK_CTRL,
+				trf->modulator_sys_clk_ctrl);
+		if (ret)
+			return ret;
+	}
+
+	if (!(trf->chip_status_ctrl & TRF7970A_CHIP_STATUS_RF_ON)) {
+		ret = trf7970a_write(trf, TRF7970A_CHIP_STATUS_CTRL,
+				trf->chip_status_ctrl |
+					TRF7970A_CHIP_STATUS_RF_ON);
+		if (ret)
+			return ret;
+
+		trf->chip_status_ctrl |= TRF7970A_CHIP_STATUS_RF_ON;
+
+		usleep_range(5000, 6000);
+	}
+
+	return 0;
 }
 
 static int trf7970a_in_configure_hw(struct nfc_digital_dev *ddev, int type,
 		int param)
 {
 	struct trf7970a *trf = nfc_digital_get_drvdata(ddev);
-	int ret = 0;
+	int ret;
 
 	dev_dbg(trf->dev, "Configure hw - type: %d, param: %d\n", type, param);
 
 	mutex_lock(&trf->lock);
 
-	if (trf->state == TRF7970A_ST_OFF) {
-		ret = trf7970a_switch_rf_on(trf);
-		if (ret)
-			goto err_out;
-	}
+	if (trf->state == TRF7970A_ST_OFF)
+		trf7970a_switch_rf_on(trf);
 
 	switch (type) {
 	case NFC_DIGITAL_CONFIG_RF_TECH:
@@ -956,7 +978,6 @@ static int trf7970a_in_configure_hw(struct nfc_digital_dev *ddev, int type,
 		ret = -EINVAL;
 	}
 
-err_out:
 	mutex_unlock(&trf->lock);
 	return ret;
 }
@@ -1191,7 +1212,18 @@ static void trf7970a_abort_cmd(struct nfc_digital_dev *ddev)
 	dev_dbg(trf->dev, "Abort process initiated\n");
 
 	mutex_lock(&trf->lock);
-	trf->aborting = true;
+
+	switch (trf->state) {
+	case TRF7970A_ST_WAIT_FOR_TX_FIFO:
+	case TRF7970A_ST_WAIT_FOR_RX_DATA:
+	case TRF7970A_ST_WAIT_FOR_RX_DATA_CONT:
+	case TRF7970A_ST_WAIT_TO_ISSUE_EOF:
+		trf->aborting = true;
+		break;
+	default:
+		break;
+	}
+
 	mutex_unlock(&trf->lock);
 }
 
@@ -1206,12 +1238,25 @@ static struct nfc_digital_ops trf7970a_nfc_ops = {
 	.abort_cmd		= trf7970a_abort_cmd,
 };
 
+static int trf7970a_get_autosuspend_delay(struct device_node *np)
+{
+	int autosuspend_delay, ret;
+
+	ret = of_property_read_u32(np, "autosuspend-delay", &autosuspend_delay);
+	if (ret)
+		autosuspend_delay = TRF7970A_AUTOSUSPEND_DELAY;
+
+	of_node_put(np);
+
+	return autosuspend_delay;
+}
+
 static int trf7970a_probe(struct spi_device *spi)
 {
 	struct device_node *np = spi->dev.of_node;
 	const struct spi_device_id *id = spi_get_device_id(spi);
 	struct trf7970a *trf;
-	int ret;
+	int uvolts, autosuspend_delay, ret;
 
 	if (!np) {
 		dev_err(&spi->dev, "No Device Tree entry\n");
@@ -1281,7 +1326,10 @@ static int trf7970a_probe(struct spi_device *spi)
 		goto err_destroy_lock;
 	}
 
-	trf->powering_up = true;
+	uvolts = regulator_get_voltage(trf->regulator);
+
+	if (uvolts > 4000000)
+		trf->chip_status_ctrl = TRF7970A_CHIP_STATUS_VRS5_3;
 
 	trf->ddev = nfc_digital_allocate_device(&trf7970a_nfc_ops,
 			TRF7970A_SUPPORTED_PROTOCOLS,
@@ -1297,6 +1345,12 @@ static int trf7970a_probe(struct spi_device *spi)
 	nfc_digital_set_drvdata(trf->ddev, trf);
 	spi_set_drvdata(spi, trf);
 
+	autosuspend_delay = trf7970a_get_autosuspend_delay(np);
+
+	pm_runtime_set_autosuspend_delay(trf->dev, autosuspend_delay);
+	pm_runtime_use_autosuspend(trf->dev);
+	pm_runtime_enable(trf->dev);
+
 	ret = nfc_digital_register_device(trf->ddev);
 	if (ret) {
 		dev_err(trf->dev, "Can't register NFC digital device: %d\n",
@@ -1307,6 +1361,7 @@ static int trf7970a_probe(struct spi_device *spi)
 	return 0;
 
 err_free_ddev:
+	pm_runtime_disable(trf->dev);
 	nfc_digital_free_device(trf->ddev);
 err_disable_regulator:
 	regulator_disable(trf->regulator);
@@ -1321,15 +1376,16 @@ static int trf7970a_remove(struct spi_device *spi)
 
 	mutex_lock(&trf->lock);
 
-	trf7970a_switch_rf_off(trf);
-	trf7970a_init(trf);
-
 	switch (trf->state) {
 	case TRF7970A_ST_WAIT_FOR_TX_FIFO:
 	case TRF7970A_ST_WAIT_FOR_RX_DATA:
 	case TRF7970A_ST_WAIT_FOR_RX_DATA_CONT:
 	case TRF7970A_ST_WAIT_TO_ISSUE_EOF:
 		trf7970a_send_err_upstream(trf, -ECANCELED);
+		/* FALLTHROUGH */
+	case TRF7970A_ST_IDLE:
+	case TRF7970A_ST_IDLE_RX_BLOCKED:
+		pm_runtime_put_sync(trf->dev);
 		break;
 	default:
 		break;
@@ -1337,6 +1393,8 @@ static int trf7970a_remove(struct spi_device *spi)
 
 	mutex_unlock(&trf->lock);
 
+	pm_runtime_disable(trf->dev);
+
 	nfc_digital_unregister_device(trf->ddev);
 	nfc_digital_free_device(trf->ddev);
 
@@ -1347,6 +1405,70 @@ static int trf7970a_remove(struct spi_device *spi)
 	return 0;
 }
 
+#ifdef CONFIG_PM_RUNTIME
+static int trf7970a_pm_runtime_suspend(struct device *dev)
+{
+	struct spi_device *spi = container_of(dev, struct spi_device, dev);
+	struct trf7970a *trf = spi_get_drvdata(spi);
+	int ret;
+
+	dev_dbg(dev, "Runtime suspend\n");
+
+	if (trf->state != TRF7970A_ST_OFF) {
+		dev_dbg(dev, "Can't suspend - not in OFF state (%d)\n",
+				trf->state);
+		return -EBUSY;
+	}
+
+	gpio_set_value(trf->en_gpio, 0);
+	gpio_set_value(trf->en2_gpio, 0);
+
+	ret = regulator_disable(trf->regulator);
+	if (ret)
+		dev_err(dev, "%s - Can't disable VIN: %d\n", __func__, ret);
+
+	return ret;
+}
+
+static int trf7970a_pm_runtime_resume(struct device *dev)
+{
+	struct spi_device *spi = container_of(dev, struct spi_device, dev);
+	struct trf7970a *trf = spi_get_drvdata(spi);
+	int ret;
+
+	dev_dbg(dev, "Runtime resume\n");
+
+	ret = regulator_enable(trf->regulator);
+	if (ret) {
+		dev_err(dev, "%s - Can't enable VIN: %d\n", __func__, ret);
+		return ret;
+	}
+
+	usleep_range(5000, 6000);
+
+	gpio_set_value(trf->en2_gpio, 1);
+	usleep_range(1000, 2000);
+	gpio_set_value(trf->en_gpio, 1);
+
+	usleep_range(20000, 21000);
+
+	ret = trf7970a_init(trf);
+	if (ret) {
+		dev_err(dev, "%s - Can't initialize: %d\n", __func__, ret);
+		return ret;
+	}
+
+	pm_runtime_mark_last_busy(dev);
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops trf7970a_pm_ops = {
+	SET_RUNTIME_PM_OPS(trf7970a_pm_runtime_suspend,
+			trf7970a_pm_runtime_resume, NULL)
+};
+
 static const struct spi_device_id trf7970a_id_table[] = {
 	{ "trf7970a", TRF7970A_QUIRK_IRQ_STATUS_READ_ERRATA },
 	{ }
@@ -1360,6 +1482,7 @@ static struct spi_driver trf7970a_spi_driver = {
 	.driver		= {
 		.name	= "trf7970a",
 		.owner	= THIS_MODULE,
+		.pm	= &trf7970a_pm_ops,
 	},
 };
 
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 8368d96ae7b..b9864806e9b 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -227,7 +227,8 @@ static int __of_node_add(struct device_node *np)
 	np->kobj.kset = of_kset;
 	if (!np->parent) {
 		/* Nodes without parents are new top level trees */
-		rc = kobject_add(&np->kobj, NULL, safe_name(&of_kset->kobj, "base"));
+		rc = kobject_add(&np->kobj, NULL, "%s",
+				 safe_name(&of_kset->kobj, "base"));
 	} else {
 		name = safe_name(&np->parent->kobj, kbasename(np->full_name));
 		if (!name || !name[0])
@@ -1960,9 +1961,9 @@ int of_attach_node(struct device_node *np)
 
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np->sibling = np->parent->child;
-	np->allnext = of_allnodes;
+	np->allnext = np->parent->allnext;
+	np->parent->allnext = np;
 	np->parent->child = np;
-	of_allnodes = np;
 	of_node_clear_flag(np, OF_DETACHED);
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index c4cddf0cd96..9aa012e6ea0 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -26,6 +26,54 @@
 #include <asm/setup.h>  /* for COMMAND_LINE_SIZE */
 #include <asm/page.h>
 
+/*
+ * of_fdt_limit_memory - limit the number of regions in the /memory node
+ * @limit: maximum entries
+ *
+ * Adjust the flattened device tree to have at most 'limit' number of
+ * memory entries in the /memory node. This function may be called
+ * any time after initial_boot_param is set.
+ */
+void of_fdt_limit_memory(int limit)
+{
+	int memory;
+	int len;
+	const void *val;
+	int nr_address_cells = OF_ROOT_NODE_ADDR_CELLS_DEFAULT;
+	int nr_size_cells = OF_ROOT_NODE_SIZE_CELLS_DEFAULT;
+	const uint32_t *addr_prop;
+	const uint32_t *size_prop;
+	int root_offset;
+	int cell_size;
+
+	root_offset = fdt_path_offset(initial_boot_params, "/");
+	if (root_offset < 0)
+		return;
+
+	addr_prop = fdt_getprop(initial_boot_params, root_offset,
+				"#address-cells", NULL);
+	if (addr_prop)
+		nr_address_cells = fdt32_to_cpu(*addr_prop);
+
+	size_prop = fdt_getprop(initial_boot_params, root_offset,
+				"#size-cells", NULL);
+	if (size_prop)
+		nr_size_cells = fdt32_to_cpu(*size_prop);
+
+	cell_size = sizeof(uint32_t)*(nr_address_cells + nr_size_cells);
+
+	memory = fdt_path_offset(initial_boot_params, "/memory");
+	if (memory > 0) {
+		val = fdt_getprop(initial_boot_params, memory, "reg", &len);
+		if (len > limit*cell_size) {
+			len = limit*cell_size;
+			pr_debug("Limiting number of entries to %d\n", limit);
+			fdt_setprop(initial_boot_params, memory, "reg", val,
+					len);
+		}
+	}
+}
+
 /**
  * of_fdt_is_compatible - Return true if given node from the given blob has
  * compat in its compatible list
@@ -880,6 +928,21 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 	const u64 phys_offset = __pa(PAGE_OFFSET);
 	base &= PAGE_MASK;
 	size &= PAGE_MASK;
+
+	if (sizeof(phys_addr_t) < sizeof(u64)) {
+		if (base > ULONG_MAX) {
+			pr_warning("Ignoring memory block 0x%llx - 0x%llx\n",
+					base, base + size);
+			return;
+		}
+
+		if (base + size > ULONG_MAX) {
+			pr_warning("Ignoring memory range 0x%lx - 0x%llx\n",
+					ULONG_MAX, base + size);
+			size = ULONG_MAX - base;
+		}
+	}
+
 	if (base + size < phys_offset) {
 		pr_warning("Ignoring memory block 0x%llx - 0x%llx\n",
 			   base, base + size);
@@ -922,7 +985,7 @@ int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
 }
 #endif
 
-bool __init early_init_dt_scan(void *params)
+bool __init early_init_dt_verify(void *params)
 {
 	if (!params)
 		return false;
@@ -936,6 +999,12 @@ bool __init early_init_dt_scan(void *params)
 		return false;
 	}
 
+	return true;
+}
+
+
+void __init early_init_dt_scan_nodes(void)
+{
 	/* Retrieve various information from the /chosen node */
 	of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line);
 
@@ -944,7 +1013,17 @@ bool __init early_init_dt_scan(void *params)
 
 	/* Setup memory, calling early_init_dt_add_memory_arch */
 	of_scan_flat_dt(early_init_dt_scan_memory, NULL);
+}
+
+bool __init early_init_dt_scan(void *params)
+{
+	bool status;
+
+	status = early_init_dt_verify(params);
+	if (!status)
+		return false;
 
+	early_init_dt_scan_nodes();
 	return true;
 }
 
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 9a95831bd06..401b2453da4 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -14,6 +14,7 @@
 #include <linux/netdevice.h>
 #include <linux/err.h>
 #include <linux/phy.h>
+#include <linux/phy_fixed.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
@@ -22,27 +23,6 @@
 MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>");
 MODULE_LICENSE("GPL");
 
-static void of_set_phy_supported(struct phy_device *phydev, u32 max_speed)
-{
-	/* The default values for phydev->supported are provided by the PHY
-	 * driver "features" member, we want to reset to sane defaults fist
-	 * before supporting higher speeds.
-	 */
-	phydev->supported &= PHY_DEFAULT_FEATURES;
-
-	switch (max_speed) {
-	default:
-		return;
-
-	case SPEED_1000:
-		phydev->supported |= PHY_1000BT_FEATURES;
-	case SPEED_100:
-		phydev->supported |= PHY_100BT_FEATURES;
-	case SPEED_10:
-		phydev->supported |= PHY_10BT_FEATURES;
-	}
-}
-
 /* Extract the clause 22 phy ID from the compatible string of the form
  * ethernet-phy-idAAAA.BBBB */
 static int of_get_phy_id(struct device_node *device, u32 *phy_id)
@@ -66,7 +46,6 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *chi
 	struct phy_device *phy;
 	bool is_c45;
 	int rc;
-	u32 max_speed = 0;
 	u32 phy_id;
 
 	is_c45 = of_device_is_compatible(child,
@@ -103,17 +82,33 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *chi
 		return 1;
 	}
 
-	/* Set phydev->supported based on the "max-speed" property
-	 * if present */
-	if (!of_property_read_u32(child, "max-speed", &max_speed))
-		of_set_phy_supported(phy, max_speed);
-
 	dev_dbg(&mdio->dev, "registered phy %s at address %i\n",
 		child->name, addr);
 
 	return 0;
 }
 
+static int of_mdio_parse_addr(struct device *dev, const struct device_node *np)
+{
+	u32 addr;
+	int ret;
+
+	ret = of_property_read_u32(np, "reg", &addr);
+	if (ret < 0) {
+		dev_err(dev, "%s has invalid PHY address\n", np->full_name);
+		return ret;
+	}
+
+	/* A PHY must have a reg property in the range [0-31] */
+	if (addr >= PHY_MAX_ADDR) {
+		dev_err(dev, "%s PHY address %i is too large\n",
+			np->full_name, addr);
+		return -EINVAL;
+	}
+
+	return addr;
+}
+
 /**
  * of_mdiobus_register - Register mii_bus and create PHYs from the device tree
  * @mdio: pointer to mii_bus structure
@@ -126,9 +121,8 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 {
 	struct device_node *child;
 	const __be32 *paddr;
-	u32 addr;
 	bool scanphys = false;
-	int rc, i, len;
+	int addr, rc, i;
 
 	/* Mask out all PHYs from auto probing.  Instead the PHYs listed in
 	 * the device tree are populated after the bus has been registered */
@@ -148,19 +142,9 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 
 	/* Loop over the child nodes and register a phy_device for each one */
 	for_each_available_child_of_node(np, child) {
-		/* A PHY must have a reg property in the range [0-31] */
-		paddr = of_get_property(child, "reg", &len);
-		if (!paddr || len < sizeof(*paddr)) {
+		addr = of_mdio_parse_addr(&mdio->dev, child);
+		if (addr < 0) {
 			scanphys = true;
-			dev_err(&mdio->dev, "%s has invalid PHY address\n",
-				child->full_name);
-			continue;
-		}
-
-		addr = be32_to_cpup(paddr);
-		if (addr >= PHY_MAX_ADDR) {
-			dev_err(&mdio->dev, "%s PHY address %i is too large\n",
-				child->full_name, addr);
 			continue;
 		}
 
@@ -175,7 +159,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 	/* auto scan for PHYs with empty reg property */
 	for_each_available_child_of_node(np, child) {
 		/* Skip PHYs with reg property set */
-		paddr = of_get_property(child, "reg", &len);
+		paddr = of_get_property(child, "reg", NULL);
 		if (paddr)
 			continue;
 
@@ -245,44 +229,6 @@ struct phy_device *of_phy_connect(struct net_device *dev,
 EXPORT_SYMBOL(of_phy_connect);
 
 /**
- * of_phy_connect_fixed_link - Parse fixed-link property and return a dummy phy
- * @dev: pointer to net_device claiming the phy
- * @hndlr: Link state callback for the network device
- * @iface: PHY data interface type
- *
- * This function is a temporary stop-gap and will be removed soon.  It is
- * only to support the fs_enet, ucc_geth and gianfar Ethernet drivers.  Do
- * not call this function from new drivers.
- */
-struct phy_device *of_phy_connect_fixed_link(struct net_device *dev,
-					     void (*hndlr)(struct net_device *),
-					     phy_interface_t iface)
-{
-	struct device_node *net_np;
-	char bus_id[MII_BUS_ID_SIZE + 3];
-	struct phy_device *phy;
-	const __be32 *phy_id;
-	int sz;
-
-	if (!dev->dev.parent)
-		return NULL;
-
-	net_np = dev->dev.parent->of_node;
-	if (!net_np)
-		return NULL;
-
-	phy_id = of_get_property(net_np, "fixed-link", &sz);
-	if (!phy_id || sz < sizeof(*phy_id))
-		return NULL;
-
-	sprintf(bus_id, PHY_ID_FMT, "fixed-0", be32_to_cpu(phy_id[0]));
-
-	phy = phy_connect(dev, bus_id, hndlr, iface);
-	return IS_ERR(phy) ? NULL : phy;
-}
-EXPORT_SYMBOL(of_phy_connect_fixed_link);
-
-/**
  * of_phy_attach - Attach to a PHY without starting the state machine
  * @dev: pointer to net_device claiming the phy
  * @phy_np: Node pointer for the PHY
@@ -301,3 +247,71 @@ struct phy_device *of_phy_attach(struct net_device *dev,
 	return phy_attach_direct(dev, phy, flags, iface) ? NULL : phy;
 }
 EXPORT_SYMBOL(of_phy_attach);
+
+#if defined(CONFIG_FIXED_PHY)
+/*
+ * of_phy_is_fixed_link() and of_phy_register_fixed_link() must
+ * support two DT bindings:
+ * - the old DT binding, where 'fixed-link' was a property with 5
+ *   cells encoding various informations about the fixed PHY
+ * - the new DT binding, where 'fixed-link' is a sub-node of the
+ *   Ethernet device.
+ */
+bool of_phy_is_fixed_link(struct device_node *np)
+{
+	struct device_node *dn;
+	int len;
+
+	/* New binding */
+	dn = of_get_child_by_name(np, "fixed-link");
+	if (dn) {
+		of_node_put(dn);
+		return true;
+	}
+
+	/* Old binding */
+	if (of_get_property(np, "fixed-link", &len) &&
+	    len == (5 * sizeof(__be32)))
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL(of_phy_is_fixed_link);
+
+int of_phy_register_fixed_link(struct device_node *np)
+{
+	struct fixed_phy_status status = {};
+	struct device_node *fixed_link_node;
+	const __be32 *fixed_link_prop;
+	int len;
+
+	/* New binding */
+	fixed_link_node = of_get_child_by_name(np, "fixed-link");
+	if (fixed_link_node) {
+		status.link = 1;
+		status.duplex = of_property_read_bool(fixed_link_node,
+						      "full-duplex");
+		if (of_property_read_u32(fixed_link_node, "speed", &status.speed))
+			return -EINVAL;
+		status.pause = of_property_read_bool(fixed_link_node, "pause");
+		status.asym_pause = of_property_read_bool(fixed_link_node,
+							  "asym-pause");
+		of_node_put(fixed_link_node);
+		return fixed_phy_register(PHY_POLL, &status, np);
+	}
+
+	/* Old binding */
+	fixed_link_prop = of_get_property(np, "fixed-link", &len);
+	if (fixed_link_prop && len == (5 * sizeof(__be32))) {
+		status.link = 1;
+		status.duplex = be32_to_cpu(fixed_link_prop[1]);
+		status.speed = be32_to_cpu(fixed_link_prop[2]);
+		status.pause = be32_to_cpu(fixed_link_prop[3]);
+		status.asym_pause = be32_to_cpu(fixed_link_prop[4]);
+		return fixed_phy_register(PHY_POLL, &status, np);
+	}
+
+	return -ENODEV;
+}
+EXPORT_SYMBOL(of_phy_register_fixed_link);
+#endif
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 6c48d73a7fd..500436f9be7 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -166,10 +166,6 @@ static void of_dma_configure(struct platform_device *pdev)
 	int ret;
 	struct device *dev = &pdev->dev;
 
-#if defined(CONFIG_MICROBLAZE)
-	pdev->archdata.dma_mask = 0xffffffffUL;
-#endif
-
 	/*
 	 * Set default dma-mask to 32 bit. Drivers are expected to setup
 	 * the correct supported dma_mask.
diff --git a/drivers/parport/Kconfig b/drivers/parport/Kconfig
index 2872ece81f3..44333bd8f90 100644
--- a/drivers/parport/Kconfig
+++ b/drivers/parport/Kconfig
@@ -5,6 +5,12 @@
 # Parport configuration.
 #
 
+config ARCH_MIGHT_HAVE_PC_PARPORT
+	bool
+	help
+	  Select this config option from the architecture Kconfig if
+	  the architecture might have PC parallel port hardware.
+
 menuconfig PARPORT
 	tristate "Parallel port support"
 	depends on HAS_IOMEM
@@ -31,12 +37,6 @@ menuconfig PARPORT
 
 	  If unsure, say Y.
 
-config ARCH_MIGHT_HAVE_PC_PARPORT
-	bool
-	help
-	  Select this config option from the architecture Kconfig if
-	  the architecture might have PC parallel port hardware.
-
 if PARPORT
 
 config PARPORT_PC
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 8c148f39e8d..d292d7cb341 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -231,10 +231,7 @@ static int pci_vpd_pci22_wait(struct pci_dev *dev)
 		}
 
 		if (time_after(jiffies, timeout)) {
-			dev_printk(KERN_DEBUG, &dev->dev,
-				   "vpd r/w failed.  This is likely a firmware "
-				   "bug on this device.  Contact the card "
-				   "vendor for a firmware update.");
+			dev_printk(KERN_DEBUG, &dev->dev, "vpd r/w failed.  This is likely a firmware bug on this device.  Contact the card vendor for a firmware update\n");
 			return -ETIMEDOUT;
 		}
 		if (fatal_signal_pending(current))
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 447d393725e..73aef51a28f 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -226,6 +226,7 @@ int pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
 					 type_mask, alignf, alignf_data,
 					 &pci_32_bit);
 }
+EXPORT_SYMBOL(pci_bus_alloc_resource);
 
 void __weak pcibios_resource_survey_bus(struct pci_bus *bus) { }
 
@@ -253,6 +254,7 @@ void pci_bus_add_device(struct pci_dev *dev)
 
 	dev->is_added = 1;
 }
+EXPORT_SYMBOL_GPL(pci_bus_add_device);
 
 /**
  * pci_bus_add_devices - start driver for PCI devices
@@ -279,6 +281,7 @@ void pci_bus_add_devices(const struct pci_bus *bus)
 			pci_bus_add_devices(child);
 	}
 }
+EXPORT_SYMBOL(pci_bus_add_devices);
 
 /** pci_walk_bus - walk devices on/under bus, calling callback.
  *  @top      bus whose devices should be walked
@@ -344,6 +347,3 @@ void pci_bus_put(struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_bus_put);
 
-EXPORT_SYMBOL(pci_bus_alloc_resource);
-EXPORT_SYMBOL_GPL(pci_bus_add_device);
-EXPORT_SYMBOL(pci_bus_add_devices);
diff --git a/drivers/pci/host/pci-exynos.c b/drivers/pci/host/pci-exynos.c
index 1632661c5b7..c5d0ca38450 100644
--- a/drivers/pci/host/pci-exynos.c
+++ b/drivers/pci/host/pci-exynos.c
@@ -545,7 +545,6 @@ static int __init add_pcie_port(struct pcie_port *pp,
 	pp->root_bus_nr = -1;
 	pp->ops = &exynos_pcie_host_ops;
 
-	spin_lock_init(&pp->conf_lock);
 	ret = dw_pcie_host_init(pp);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to initialize host\n");
diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c
index 44fe6aa6a43..3d2076f5991 100644
--- a/drivers/pci/host/pci-host-generic.c
+++ b/drivers/pci/host/pci-host-generic.c
@@ -385,4 +385,4 @@ module_platform_driver(gen_pci_driver);
 
 MODULE_DESCRIPTION("Generic PCI host driver");
 MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pci-imx6.c b/drivers/pci/host/pci-imx6.c
index a5645ae4aef..a568efaa331 100644
--- a/drivers/pci/host/pci-imx6.c
+++ b/drivers/pci/host/pci-imx6.c
@@ -507,7 +507,6 @@ static int __init imx6_add_pcie_port(struct pcie_port *pp,
 	pp->root_bus_nr = -1;
 	pp->ops = &imx6_pcie_host_ops;
 
-	spin_lock_init(&pp->conf_lock);
 	ret = dw_pcie_host_init(pp);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to initialize host\n");
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index e384e253459..a8c6f1a92e0 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -113,7 +113,6 @@ struct mvebu_pcie {
 struct mvebu_pcie_port {
 	char *name;
 	void __iomem *base;
-	spinlock_t conf_lock;
 	u32 port;
 	u32 lane;
 	int devfn;
@@ -329,9 +328,11 @@ static void mvebu_pcie_add_windows(struct mvebu_pcie_port *port,
 		ret = mvebu_mbus_add_window_remap_by_id(target, attribute, base,
 							sz, remap);
 		if (ret) {
+			phys_addr_t end = base + sz - 1;
+
 			dev_err(&port->pcie->pdev->dev,
-				"Could not create MBus window at 0x%x, size 0x%x: %d\n",
-				base, sz, ret);
+				"Could not create MBus window at [mem %pa-%pa]: %d\n",
+				&base, &end, ret);
 			mvebu_pcie_del_windows(port, base - size_mapped,
 					       size_mapped);
 			return;
@@ -613,9 +614,9 @@ static inline struct mvebu_pcie *sys_to_pcie(struct pci_sys_data *sys)
 	return sys->private_data;
 }
 
-static struct mvebu_pcie_port *
-mvebu_pcie_find_port(struct mvebu_pcie *pcie, struct pci_bus *bus,
-		     int devfn)
+static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie,
+						    struct pci_bus *bus,
+						    int devfn)
 {
 	int i;
 
@@ -638,7 +639,6 @@ static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 {
 	struct mvebu_pcie *pcie = sys_to_pcie(bus->sysdata);
 	struct mvebu_pcie_port *port;
-	unsigned long flags;
 	int ret;
 
 	port = mvebu_pcie_find_port(pcie, bus, devfn);
@@ -664,10 +664,8 @@ static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	/* Access the real PCIe interface */
-	spin_lock_irqsave(&port->conf_lock, flags);
 	ret = mvebu_pcie_hw_wr_conf(port, bus, devfn,
 				    where, size, val);
-	spin_unlock_irqrestore(&port->conf_lock, flags);
 
 	return ret;
 }
@@ -678,7 +676,6 @@ static int mvebu_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where,
 {
 	struct mvebu_pcie *pcie = sys_to_pcie(bus->sysdata);
 	struct mvebu_pcie_port *port;
-	unsigned long flags;
 	int ret;
 
 	port = mvebu_pcie_find_port(pcie, bus, devfn);
@@ -710,10 +707,8 @@ static int mvebu_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where,
 	}
 
 	/* Access the real PCIe interface */
-	spin_lock_irqsave(&port->conf_lock, flags);
 	ret = mvebu_pcie_hw_rd_conf(port, bus, devfn,
 				    where, size, val);
-	spin_unlock_irqrestore(&port->conf_lock, flags);
 
 	return ret;
 }
@@ -786,10 +781,10 @@ static void mvebu_pcie_add_bus(struct pci_bus *bus)
 }
 
 static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev,
-						const struct resource *res,
-						resource_size_t start,
-						resource_size_t size,
-						resource_size_t align)
+						 const struct resource *res,
+						 resource_size_t start,
+						 resource_size_t size,
+						 resource_size_t align)
 {
 	if (dev->bus->number != 0)
 		return start;
@@ -839,7 +834,8 @@ static void mvebu_pcie_enable(struct mvebu_pcie *pcie)
  * found, maps it.
  */
 static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev,
-		      struct device_node *np, struct mvebu_pcie_port *port)
+					      struct device_node *np,
+					      struct mvebu_pcie_port *port)
 {
 	struct resource regs;
 	int ret = 0;
@@ -1060,7 +1056,6 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 		mvebu_pcie_set_local_dev_nr(port, 1);
 
 		port->dn = child;
-		spin_lock_init(&port->conf_lock);
 		mvebu_sw_pci_bridge_init(port);
 		i++;
 	}
@@ -1099,4 +1094,4 @@ module_platform_driver(mvebu_pcie_driver);
 
 MODULE_AUTHOR("Thomas Petazzoni <thomas.petazzoni@free-electrons.com>");
 MODULE_DESCRIPTION("Marvell EBU PCIe driver");
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 083cf37ca04..c284e841e3e 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -1716,4 +1716,4 @@ module_platform_driver(tegra_pcie_driver);
 
 MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>");
 MODULE_DESCRIPTION("NVIDIA Tegra PCIe driver");
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index e3bf9e6d5d9..1eaf4df3618 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -643,7 +643,6 @@ static int dw_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where,
 			int size, u32 *val)
 {
 	struct pcie_port *pp = sys_to_pcie(bus->sysdata);
-	unsigned long flags;
 	int ret;
 
 	if (!pp) {
@@ -656,13 +655,11 @@ static int dw_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where,
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	}
 
-	spin_lock_irqsave(&pp->conf_lock, flags);
 	if (bus->number != pp->root_bus_nr)
 		ret = dw_pcie_rd_other_conf(pp, bus, devfn,
 						where, size, val);
 	else
 		ret = dw_pcie_rd_own_conf(pp, where, size, val);
-	spin_unlock_irqrestore(&pp->conf_lock, flags);
 
 	return ret;
 }
@@ -671,7 +668,6 @@ static int dw_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 			int where, int size, u32 val)
 {
 	struct pcie_port *pp = sys_to_pcie(bus->sysdata);
-	unsigned long flags;
 	int ret;
 
 	if (!pp) {
@@ -682,13 +678,11 @@ static int dw_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	if (dw_pcie_valid_config(pp, bus, PCI_SLOT(devfn)) == 0)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	spin_lock_irqsave(&pp->conf_lock, flags);
 	if (bus->number != pp->root_bus_nr)
 		ret = dw_pcie_wr_other_conf(pp, bus, devfn,
 						where, size, val);
 	else
 		ret = dw_pcie_wr_own_conf(pp, where, size, val);
-	spin_unlock_irqrestore(&pp->conf_lock, flags);
 
 	return ret;
 }
diff --git a/drivers/pci/host/pcie-designware.h b/drivers/pci/host/pcie-designware.h
index a169d22d517..77f592faa7b 100644
--- a/drivers/pci/host/pcie-designware.h
+++ b/drivers/pci/host/pcie-designware.h
@@ -41,7 +41,6 @@ struct pcie_port {
 	void __iomem		*va_cfg1_base;
 	u64			io_base;
 	u64			mem_base;
-	spinlock_t		conf_lock;
 	struct resource		cfg;
 	struct resource		io;
 	struct resource		mem;
diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c
index 8e06124aa80..4884ee5e07d 100644
--- a/drivers/pci/host/pcie-rcar.c
+++ b/drivers/pci/host/pcie-rcar.c
@@ -105,7 +105,7 @@
 #define  PCIE_CONF_DEV(d)	(((d) & 0x1f) << 19)
 #define  PCIE_CONF_FUNC(f)	(((f) & 0x7) << 16)
 
-#define PCI_MAX_RESOURCES 4
+#define RCAR_PCI_MAX_RESOURCES 4
 #define MAX_NR_INBOUND_MAPS 6
 
 struct rcar_msi {
@@ -127,7 +127,7 @@ static inline struct rcar_msi *to_rcar_msi(struct msi_chip *chip)
 struct rcar_pcie {
 	struct device		*dev;
 	void __iomem		*base;
-	struct resource		res[PCI_MAX_RESOURCES];
+	struct resource		res[RCAR_PCI_MAX_RESOURCES];
 	struct resource		busn;
 	int			root_bus_nr;
 	struct clk		*clk;
@@ -140,36 +140,37 @@ static inline struct rcar_pcie *sys_to_pcie(struct pci_sys_data *sys)
 	return sys->private_data;
 }
 
-static void pci_write_reg(struct rcar_pcie *pcie, unsigned long val,
-			  unsigned long reg)
+static void rcar_pci_write_reg(struct rcar_pcie *pcie, unsigned long val,
+			       unsigned long reg)
 {
 	writel(val, pcie->base + reg);
 }
 
-static unsigned long pci_read_reg(struct rcar_pcie *pcie, unsigned long reg)
+static unsigned long rcar_pci_read_reg(struct rcar_pcie *pcie,
+				       unsigned long reg)
 {
 	return readl(pcie->base + reg);
 }
 
 enum {
-	PCI_ACCESS_READ,
-	PCI_ACCESS_WRITE,
+	RCAR_PCI_ACCESS_READ,
+	RCAR_PCI_ACCESS_WRITE,
 };
 
 static void rcar_rmw32(struct rcar_pcie *pcie, int where, u32 mask, u32 data)
 {
 	int shift = 8 * (where & 3);
-	u32 val = pci_read_reg(pcie, where & ~3);
+	u32 val = rcar_pci_read_reg(pcie, where & ~3);
 
 	val &= ~(mask << shift);
 	val |= data << shift;
-	pci_write_reg(pcie, val, where & ~3);
+	rcar_pci_write_reg(pcie, val, where & ~3);
 }
 
 static u32 rcar_read_conf(struct rcar_pcie *pcie, int where)
 {
 	int shift = 8 * (where & 3);
-	u32 val = pci_read_reg(pcie, where & ~3);
+	u32 val = rcar_pci_read_reg(pcie, where & ~3);
 
 	return val >> shift;
 }
@@ -205,14 +206,14 @@ static int rcar_pcie_config_access(struct rcar_pcie *pcie,
 		if (dev != 0)
 			return PCIBIOS_DEVICE_NOT_FOUND;
 
-		if (access_type == PCI_ACCESS_READ) {
-			*data = pci_read_reg(pcie, PCICONF(index));
+		if (access_type == RCAR_PCI_ACCESS_READ) {
+			*data = rcar_pci_read_reg(pcie, PCICONF(index));
 		} else {
 			/* Keep an eye out for changes to the root bus number */
 			if (pci_is_root_bus(bus) && (reg == PCI_PRIMARY_BUS))
 				pcie->root_bus_nr = *data & 0xff;
 
-			pci_write_reg(pcie, *data, PCICONF(index));
+			rcar_pci_write_reg(pcie, *data, PCICONF(index));
 		}
 
 		return PCIBIOS_SUCCESSFUL;
@@ -222,20 +223,20 @@ static int rcar_pcie_config_access(struct rcar_pcie *pcie,
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	/* Clear errors */
-	pci_write_reg(pcie, pci_read_reg(pcie, PCIEERRFR), PCIEERRFR);
+	rcar_pci_write_reg(pcie, rcar_pci_read_reg(pcie, PCIEERRFR), PCIEERRFR);
 
 	/* Set the PIO address */
-	pci_write_reg(pcie, PCIE_CONF_BUS(bus->number) | PCIE_CONF_DEV(dev) |
-				PCIE_CONF_FUNC(func) | reg, PCIECAR);
+	rcar_pci_write_reg(pcie, PCIE_CONF_BUS(bus->number) |
+		PCIE_CONF_DEV(dev) | PCIE_CONF_FUNC(func) | reg, PCIECAR);
 
 	/* Enable the configuration access */
 	if (bus->parent->number == pcie->root_bus_nr)
-		pci_write_reg(pcie, CONFIG_SEND_ENABLE | TYPE0, PCIECCTLR);
+		rcar_pci_write_reg(pcie, CONFIG_SEND_ENABLE | TYPE0, PCIECCTLR);
 	else
-		pci_write_reg(pcie, CONFIG_SEND_ENABLE | TYPE1, PCIECCTLR);
+		rcar_pci_write_reg(pcie, CONFIG_SEND_ENABLE | TYPE1, PCIECCTLR);
 
 	/* Check for errors */
-	if (pci_read_reg(pcie, PCIEERRFR) & UNSUPPORTED_REQUEST)
+	if (rcar_pci_read_reg(pcie, PCIEERRFR) & UNSUPPORTED_REQUEST)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	/* Check for master and target aborts */
@@ -243,13 +244,13 @@ static int rcar_pcie_config_access(struct rcar_pcie *pcie,
 		(PCI_STATUS_REC_MASTER_ABORT | PCI_STATUS_REC_TARGET_ABORT))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	if (access_type == PCI_ACCESS_READ)
-		*data = pci_read_reg(pcie, PCIECDR);
+	if (access_type == RCAR_PCI_ACCESS_READ)
+		*data = rcar_pci_read_reg(pcie, PCIECDR);
 	else
-		pci_write_reg(pcie, *data, PCIECDR);
+		rcar_pci_write_reg(pcie, *data, PCIECDR);
 
 	/* Disable the configuration access */
-	pci_write_reg(pcie, 0, PCIECCTLR);
+	rcar_pci_write_reg(pcie, 0, PCIECCTLR);
 
 	return PCIBIOS_SUCCESSFUL;
 }
@@ -260,12 +261,7 @@ static int rcar_pcie_read_conf(struct pci_bus *bus, unsigned int devfn,
 	struct rcar_pcie *pcie = sys_to_pcie(bus->sysdata);
 	int ret;
 
-	if ((size == 2) && (where & 1))
-		return PCIBIOS_BAD_REGISTER_NUMBER;
-	else if ((size == 4) && (where & 3))
-		return PCIBIOS_BAD_REGISTER_NUMBER;
-
-	ret = rcar_pcie_config_access(pcie, PCI_ACCESS_READ,
+	ret = rcar_pcie_config_access(pcie, RCAR_PCI_ACCESS_READ,
 				      bus, devfn, where, val);
 	if (ret != PCIBIOS_SUCCESSFUL) {
 		*val = 0xffffffff;
@@ -277,9 +273,8 @@ static int rcar_pcie_read_conf(struct pci_bus *bus, unsigned int devfn,
 	else if (size == 2)
 		*val = (*val >> (8 * (where & 2))) & 0xffff;
 
-	dev_dbg(&bus->dev, "pcie-config-read: bus=%3d devfn=0x%04x "
-		"where=0x%04x size=%d val=0x%08lx\n", bus->number,
-		devfn, where, size, (unsigned long)*val);
+	dev_dbg(&bus->dev, "pcie-config-read: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08lx\n",
+		bus->number, devfn, where, size, (unsigned long)*val);
 
 	return ret;
 }
@@ -292,19 +287,13 @@ static int rcar_pcie_write_conf(struct pci_bus *bus, unsigned int devfn,
 	int shift, ret;
 	u32 data;
 
-	if ((size == 2) && (where & 1))
-		return PCIBIOS_BAD_REGISTER_NUMBER;
-	else if ((size == 4) && (where & 3))
-		return PCIBIOS_BAD_REGISTER_NUMBER;
-
-	ret = rcar_pcie_config_access(pcie, PCI_ACCESS_READ,
+	ret = rcar_pcie_config_access(pcie, RCAR_PCI_ACCESS_READ,
 				      bus, devfn, where, &data);
 	if (ret != PCIBIOS_SUCCESSFUL)
 		return ret;
 
-	dev_dbg(&bus->dev, "pcie-config-write: bus=%3d devfn=0x%04x "
-		"where=0x%04x size=%d val=0x%08lx\n", bus->number,
-		devfn, where, size, (unsigned long)val);
+	dev_dbg(&bus->dev, "pcie-config-write: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08lx\n",
+		bus->number, devfn, where, size, (unsigned long)val);
 
 	if (size == 1) {
 		shift = 8 * (where & 3);
@@ -317,7 +306,7 @@ static int rcar_pcie_write_conf(struct pci_bus *bus, unsigned int devfn,
 	} else
 		data = val;
 
-	ret = rcar_pcie_config_access(pcie, PCI_ACCESS_WRITE,
+	ret = rcar_pcie_config_access(pcie, RCAR_PCI_ACCESS_WRITE,
 				      bus, devfn, where, &data);
 
 	return ret;
@@ -328,14 +317,15 @@ static struct pci_ops rcar_pcie_ops = {
 	.write	= rcar_pcie_write_conf,
 };
 
-static void rcar_pcie_setup_window(int win, struct resource *res,
-				   struct rcar_pcie *pcie)
+static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie)
 {
+	struct resource *res = &pcie->res[win];
+
 	/* Setup PCIe address space mappings for each resource */
 	resource_size_t size;
 	u32 mask;
 
-	pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win));
+	rcar_pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win));
 
 	/*
 	 * The PAMR mask is calculated in units of 128Bytes, which
@@ -343,17 +333,17 @@ static void rcar_pcie_setup_window(int win, struct resource *res,
 	 */
 	size = resource_size(res);
 	mask = (roundup_pow_of_two(size) / SZ_128) - 1;
-	pci_write_reg(pcie, mask << 7, PCIEPAMR(win));
+	rcar_pci_write_reg(pcie, mask << 7, PCIEPAMR(win));
 
-	pci_write_reg(pcie, upper_32_bits(res->start), PCIEPARH(win));
-	pci_write_reg(pcie, lower_32_bits(res->start), PCIEPARL(win));
+	rcar_pci_write_reg(pcie, upper_32_bits(res->start), PCIEPARH(win));
+	rcar_pci_write_reg(pcie, lower_32_bits(res->start), PCIEPARL(win));
 
 	/* First resource is for IO */
 	mask = PAR_ENABLE;
 	if (res->flags & IORESOURCE_IO)
 		mask |= IO_SPACE;
 
-	pci_write_reg(pcie, mask, PCIEPTCTLR(win));
+	rcar_pci_write_reg(pcie, mask, PCIEPTCTLR(win));
 }
 
 static int rcar_pcie_setup(int nr, struct pci_sys_data *sys)
@@ -365,13 +355,13 @@ static int rcar_pcie_setup(int nr, struct pci_sys_data *sys)
 	pcie->root_bus_nr = -1;
 
 	/* Setup PCI resources */
-	for (i = 0; i < PCI_MAX_RESOURCES; i++) {
+	for (i = 0; i < RCAR_PCI_MAX_RESOURCES; i++) {
 
 		res = &pcie->res[i];
 		if (!res->flags)
 			continue;
 
-		rcar_pcie_setup_window(i, res, pcie);
+		rcar_pcie_setup_window(i, pcie);
 
 		if (res->flags & IORESOURCE_IO)
 			pci_ioremap_io(nr * SZ_64K, res->start);
@@ -417,7 +407,7 @@ static int phy_wait_for_ack(struct rcar_pcie *pcie)
 	unsigned int timeout = 100;
 
 	while (timeout--) {
-		if (pci_read_reg(pcie, H1_PCIEPHYADRR) & PHY_ACK)
+		if (rcar_pci_read_reg(pcie, H1_PCIEPHYADRR) & PHY_ACK)
 			return 0;
 
 		udelay(100);
@@ -440,15 +430,15 @@ static void phy_write_reg(struct rcar_pcie *pcie,
 		((addr & 0xff) << ADR_POS);
 
 	/* Set write data */
-	pci_write_reg(pcie, data, H1_PCIEPHYDOUTR);
-	pci_write_reg(pcie, phyaddr, H1_PCIEPHYADRR);
+	rcar_pci_write_reg(pcie, data, H1_PCIEPHYDOUTR);
+	rcar_pci_write_reg(pcie, phyaddr, H1_PCIEPHYADRR);
 
 	/* Ignore errors as they will be dealt with if the data link is down */
 	phy_wait_for_ack(pcie);
 
 	/* Clear command */
-	pci_write_reg(pcie, 0, H1_PCIEPHYDOUTR);
-	pci_write_reg(pcie, 0, H1_PCIEPHYADRR);
+	rcar_pci_write_reg(pcie, 0, H1_PCIEPHYDOUTR);
+	rcar_pci_write_reg(pcie, 0, H1_PCIEPHYADRR);
 
 	/* Ignore errors as they will be dealt with if the data link is down */
 	phy_wait_for_ack(pcie);
@@ -459,7 +449,7 @@ static int rcar_pcie_wait_for_dl(struct rcar_pcie *pcie)
 	unsigned int timeout = 10;
 
 	while (timeout--) {
-		if ((pci_read_reg(pcie, PCIETSTR) & DATA_LINK_ACTIVE))
+		if ((rcar_pci_read_reg(pcie, PCIETSTR) & DATA_LINK_ACTIVE))
 			return 0;
 
 		msleep(5);
@@ -473,17 +463,17 @@ static int rcar_pcie_hw_init(struct rcar_pcie *pcie)
 	int err;
 
 	/* Begin initialization */
-	pci_write_reg(pcie, 0, PCIETCTLR);
+	rcar_pci_write_reg(pcie, 0, PCIETCTLR);
 
 	/* Set mode */
-	pci_write_reg(pcie, 1, PCIEMSR);
+	rcar_pci_write_reg(pcie, 1, PCIEMSR);
 
 	/*
 	 * Initial header for port config space is type 1, set the device
 	 * class to match. Hardware takes care of propagating the IDSETR
 	 * settings, so there is no need to bother with a quirk.
 	 */
-	pci_write_reg(pcie, PCI_CLASS_BRIDGE_PCI << 16, IDSETR1);
+	rcar_pci_write_reg(pcie, PCI_CLASS_BRIDGE_PCI << 16, IDSETR1);
 
 	/*
 	 * Setup Secondary Bus Number & Subordinate Bus Number, even though
@@ -493,33 +483,31 @@ static int rcar_pcie_hw_init(struct rcar_pcie *pcie)
 	rcar_rmw32(pcie, RCONF(PCI_SUBORDINATE_BUS), 0xff, 1);
 
 	/* Initialize default capabilities. */
-	rcar_rmw32(pcie, REXPCAP(0), 0, PCI_CAP_ID_EXP);
+	rcar_rmw32(pcie, REXPCAP(0), 0xff, PCI_CAP_ID_EXP);
 	rcar_rmw32(pcie, REXPCAP(PCI_EXP_FLAGS),
 		PCI_EXP_FLAGS_TYPE, PCI_EXP_TYPE_ROOT_PORT << 4);
 	rcar_rmw32(pcie, RCONF(PCI_HEADER_TYPE), 0x7f,
 		PCI_HEADER_TYPE_BRIDGE);
 
 	/* Enable data link layer active state reporting */
-	rcar_rmw32(pcie, REXPCAP(PCI_EXP_LNKCAP), 0, PCI_EXP_LNKCAP_DLLLARC);
+	rcar_rmw32(pcie, REXPCAP(PCI_EXP_LNKCAP), PCI_EXP_LNKCAP_DLLLARC,
+		PCI_EXP_LNKCAP_DLLLARC);
 
 	/* Write out the physical slot number = 0 */
 	rcar_rmw32(pcie, REXPCAP(PCI_EXP_SLTCAP), PCI_EXP_SLTCAP_PSN, 0);
 
 	/* Set the completion timer timeout to the maximum 50ms. */
-	rcar_rmw32(pcie, TLCTLR+1, 0x3f, 50);
+	rcar_rmw32(pcie, TLCTLR + 1, 0x3f, 50);
 
 	/* Terminate list of capabilities (Next Capability Offset=0) */
-	rcar_rmw32(pcie, RVCCAP(0), 0xfff0, 0);
-
-	/* Enable MAC data scrambling. */
-	rcar_rmw32(pcie, MACCTLR, SCRAMBLE_DISABLE, 0);
+	rcar_rmw32(pcie, RVCCAP(0), 0xfff00000, 0);
 
 	/* Enable MSI */
 	if (IS_ENABLED(CONFIG_PCI_MSI))
-		pci_write_reg(pcie, 0x101f0000, PCIEMSITXR);
+		rcar_pci_write_reg(pcie, 0x101f0000, PCIEMSITXR);
 
 	/* Finish initialization - establish a PCI Express link */
-	pci_write_reg(pcie, CFINIT, PCIETCTLR);
+	rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR);
 
 	/* This will timeout if we don't have a link. */
 	err = rcar_pcie_wait_for_dl(pcie);
@@ -529,11 +517,6 @@ static int rcar_pcie_hw_init(struct rcar_pcie *pcie)
 	/* Enable INTx interrupts */
 	rcar_rmw32(pcie, PCIEINTXR, 0, 0xF << 8);
 
-	/* Enable slave Bus Mastering */
-	rcar_rmw32(pcie, RCONF(PCI_STATUS), PCI_STATUS_DEVSEL_MASK,
-		PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER |
-		PCI_STATUS_CAP_LIST | PCI_STATUS_DEVSEL_FAST);
-
 	wmb();
 
 	return 0;
@@ -562,7 +545,7 @@ static int rcar_pcie_hw_init_h1(struct rcar_pcie *pcie)
 	phy_write_reg(pcie, 0, 0x66, 0x1, 0x00008000);
 
 	while (timeout--) {
-		if (pci_read_reg(pcie, H1_PCIEPHYSR))
+		if (rcar_pci_read_reg(pcie, H1_PCIEPHYSR))
 			return rcar_pcie_hw_init(pcie);
 
 		msleep(5);
@@ -601,7 +584,7 @@ static irqreturn_t rcar_pcie_msi_irq(int irq, void *data)
 	struct rcar_msi *msi = &pcie->msi;
 	unsigned long reg;
 
-	reg = pci_read_reg(pcie, PCIEMSIFR);
+	reg = rcar_pci_read_reg(pcie, PCIEMSIFR);
 
 	/* MSI & INTx share an interrupt - we only handle MSI here */
 	if (!reg)
@@ -612,7 +595,7 @@ static irqreturn_t rcar_pcie_msi_irq(int irq, void *data)
 		unsigned int irq;
 
 		/* clear the interrupt */
-		pci_write_reg(pcie, 1 << index, PCIEMSIFR);
+		rcar_pci_write_reg(pcie, 1 << index, PCIEMSIFR);
 
 		irq = irq_find_mapping(msi->domain, index);
 		if (irq) {
@@ -626,7 +609,7 @@ static irqreturn_t rcar_pcie_msi_irq(int irq, void *data)
 		}
 
 		/* see if there's any more pending in this vector */
-		reg = pci_read_reg(pcie, PCIEMSIFR);
+		reg = rcar_pci_read_reg(pcie, PCIEMSIFR);
 	}
 
 	return IRQ_HANDLED;
@@ -653,8 +636,8 @@ static int rcar_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev,
 
 	irq_set_msi_desc(irq, desc);
 
-	msg.address_lo = pci_read_reg(pcie, PCIEMSIALR) & ~MSIFE;
-	msg.address_hi = pci_read_reg(pcie, PCIEMSIAUR);
+	msg.address_lo = rcar_pci_read_reg(pcie, PCIEMSIALR) & ~MSIFE;
+	msg.address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR);
 	msg.data = hwirq;
 
 	write_msi_msg(irq, &msg);
@@ -731,11 +714,11 @@ static int rcar_pcie_enable_msi(struct rcar_pcie *pcie)
 	msi->pages = __get_free_pages(GFP_KERNEL, 0);
 	base = virt_to_phys((void *)msi->pages);
 
-	pci_write_reg(pcie, base | MSIFE, PCIEMSIALR);
-	pci_write_reg(pcie, 0, PCIEMSIAUR);
+	rcar_pci_write_reg(pcie, base | MSIFE, PCIEMSIALR);
+	rcar_pci_write_reg(pcie, 0, PCIEMSIAUR);
 
 	/* enable all MSI interrupts */
-	pci_write_reg(pcie, 0xffffffff, PCIEMSIIER);
+	rcar_pci_write_reg(pcie, 0xffffffff, PCIEMSIIER);
 
 	return 0;
 
@@ -828,6 +811,7 @@ static int rcar_pcie_inbound_ranges(struct rcar_pcie *pcie,
 	if (cpu_addr > 0) {
 		unsigned long nr_zeros = __ffs64(cpu_addr);
 		u64 alignment = 1ULL << nr_zeros;
+
 		size = min(range->size, alignment);
 	} else {
 		size = range->size;
@@ -843,13 +827,13 @@ static int rcar_pcie_inbound_ranges(struct rcar_pcie *pcie,
 		 * Set up 64-bit inbound regions as the range parser doesn't
 		 * distinguish between 32 and 64-bit types.
 		 */
-		pci_write_reg(pcie, lower_32_bits(pci_addr), PCIEPRAR(idx));
-		pci_write_reg(pcie, lower_32_bits(cpu_addr), PCIELAR(idx));
-		pci_write_reg(pcie, lower_32_bits(mask) | flags, PCIELAMR(idx));
+		rcar_pci_write_reg(pcie, lower_32_bits(pci_addr), PCIEPRAR(idx));
+		rcar_pci_write_reg(pcie, lower_32_bits(cpu_addr), PCIELAR(idx));
+		rcar_pci_write_reg(pcie, lower_32_bits(mask) | flags, PCIELAMR(idx));
 
-		pci_write_reg(pcie, upper_32_bits(pci_addr), PCIEPRAR(idx+1));
-		pci_write_reg(pcie, upper_32_bits(cpu_addr), PCIELAR(idx+1));
-		pci_write_reg(pcie, 0, PCIELAMR(idx+1));
+		rcar_pci_write_reg(pcie, upper_32_bits(pci_addr), PCIEPRAR(idx+1));
+		rcar_pci_write_reg(pcie, upper_32_bits(cpu_addr), PCIELAR(idx+1));
+		rcar_pci_write_reg(pcie, 0, PCIELAMR(idx + 1));
 
 		pci_addr += size;
 		cpu_addr += size;
@@ -954,7 +938,7 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 		of_pci_range_to_resource(&range, pdev->dev.of_node,
 						&pcie->res[win++]);
 
-		if (win > PCI_MAX_RESOURCES)
+		if (win > RCAR_PCI_MAX_RESOURCES)
 			break;
 	}
 
@@ -984,7 +968,7 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 		return 0;
 	}
 
-	data = pci_read_reg(pcie, MACSR);
+	data = rcar_pci_read_reg(pcie, MACSR);
 	dev_info(&pdev->dev, "PCIe x%d: link up\n", (data >> 20) & 0x3f);
 
 	rcar_pcie_enable(pcie);
@@ -1005,4 +989,4 @@ module_platform_driver(rcar_pcie_driver);
 
 MODULE_AUTHOR("Phil Edworthy <phil.edworthy@renesas.com>");
 MODULE_DESCRIPTION("Renesas R-Car PCIe driver");
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h
index 2b859249303..b0e61bf261a 100644
--- a/drivers/pci/hotplug/acpiphp.h
+++ b/drivers/pci/hotplug/acpiphp.h
@@ -142,6 +142,16 @@ static inline acpi_handle func_to_handle(struct acpiphp_func *func)
 	return func_to_acpi_device(func)->handle;
 }
 
+struct acpiphp_root_context {
+	struct acpi_hotplug_context hp;
+	struct acpiphp_bridge *root_bridge;
+};
+
+static inline struct acpiphp_root_context *to_acpiphp_root_context(struct acpi_hotplug_context *hp)
+{
+	return container_of(hp, struct acpiphp_root_context, hp);
+}
+
 /*
  * struct acpiphp_attention_info - device specific attention registration
  *
diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c
index 728c31f4c2c..e291efcd02a 100644
--- a/drivers/pci/hotplug/acpiphp_core.c
+++ b/drivers/pci/hotplug/acpiphp_core.c
@@ -63,10 +63,6 @@ MODULE_LICENSE("GPL");
 MODULE_PARM_DESC(disable, "disable acpiphp driver");
 module_param_named(disable, acpiphp_disabled, bool, 0444);
 
-/* export the attention callback registration methods */
-EXPORT_SYMBOL_GPL(acpiphp_register_attention);
-EXPORT_SYMBOL_GPL(acpiphp_unregister_attention);
-
 static int enable_slot		(struct hotplug_slot *slot);
 static int disable_slot		(struct hotplug_slot *slot);
 static int set_attention_status (struct hotplug_slot *slot, u8 value);
@@ -104,6 +100,7 @@ int acpiphp_register_attention(struct acpiphp_attention_info *info)
 	}
 	return retval;
 }
+EXPORT_SYMBOL_GPL(acpiphp_register_attention);
 
 
 /**
@@ -124,6 +121,7 @@ int acpiphp_unregister_attention(struct acpiphp_attention_info *info)
 	}
 	return retval;
 }
+EXPORT_SYMBOL_GPL(acpiphp_unregister_attention);
 
 
 /**
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 75e17833021..602d153c705 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -351,11 +351,9 @@ static acpi_status acpiphp_add_context(acpi_handle handle, u32 lvl, void *data,
 			slot->slot = NULL;
 			bridge->nr_slots--;
 			if (retval == -EBUSY)
-				pr_warn("Slot %llu already registered by another "
-					"hotplug driver\n", sun);
+				pr_warn("Slot %llu already registered by another hotplug driver\n", sun);
 			else
-				pr_warn("acpiphp_register_hotplug_slot failed "
-					"(err code = 0x%x)\n", retval);
+				pr_warn("acpiphp_register_hotplug_slot failed (err code = 0x%x)\n", retval);
 		}
 		/* Even if the slot registration fails, we can still use it. */
 	}
@@ -373,17 +371,13 @@ static acpi_status acpiphp_add_context(acpi_handle handle, u32 lvl, void *data,
 
 static struct acpiphp_bridge *acpiphp_dev_to_bridge(struct acpi_device *adev)
 {
-	struct acpiphp_context *context;
 	struct acpiphp_bridge *bridge = NULL;
 
 	acpi_lock_hp_context();
-	context = acpiphp_get_context(adev);
-	if (context) {
-		bridge = context->bridge;
+	if (adev->hp) {
+		bridge = to_acpiphp_root_context(adev->hp)->root_bridge;
 		if (bridge)
 			get_bridge(bridge);
-
-		acpiphp_put_context(context);
 	}
 	acpi_unlock_hp_context();
 	return bridge;
@@ -881,7 +875,17 @@ void acpiphp_enumerate_slots(struct pci_bus *bus)
 	 */
 	get_device(&bus->dev);
 
-	if (!pci_is_root_bus(bridge->pci_bus)) {
+	acpi_lock_hp_context();
+	if (pci_is_root_bus(bridge->pci_bus)) {
+		struct acpiphp_root_context *root_context;
+
+		root_context = kzalloc(sizeof(*root_context), GFP_KERNEL);
+		if (!root_context)
+			goto err;
+
+		root_context->root_bridge = bridge;
+		acpi_set_hp_context(adev, &root_context->hp, NULL, NULL, NULL);
+	} else {
 		struct acpiphp_context *context;
 
 		/*
@@ -890,21 +894,16 @@ void acpiphp_enumerate_slots(struct pci_bus *bus)
 		 * parent is going to be handled by pciehp, in which case this
 		 * bridge is not interesting to us either.
 		 */
-		acpi_lock_hp_context();
 		context = acpiphp_get_context(adev);
-		if (!context) {
-			acpi_unlock_hp_context();
-			put_device(&bus->dev);
-			pci_dev_put(bridge->pci_dev);
-			kfree(bridge);
-			return;
-		}
+		if (!context)
+			goto err;
+
 		bridge->context = context;
 		context->bridge = bridge;
 		/* Get a reference to the parent bridge. */
 		get_bridge(context->func.parent);
-		acpi_unlock_hp_context();
 	}
+	acpi_unlock_hp_context();
 
 	/* Must be added to the list prior to calling acpiphp_add_context(). */
 	mutex_lock(&bridge_mutex);
@@ -919,6 +918,30 @@ void acpiphp_enumerate_slots(struct pci_bus *bus)
 		cleanup_bridge(bridge);
 		put_bridge(bridge);
 	}
+	return;
+
+ err:
+	acpi_unlock_hp_context();
+	put_device(&bus->dev);
+	pci_dev_put(bridge->pci_dev);
+	kfree(bridge);
+}
+
+void acpiphp_drop_bridge(struct acpiphp_bridge *bridge)
+{
+	if (pci_is_root_bus(bridge->pci_bus)) {
+		struct acpiphp_root_context *root_context;
+		struct acpi_device *adev;
+
+		acpi_lock_hp_context();
+		adev = ACPI_COMPANION(bridge->pci_bus->bridge);
+		root_context = to_acpiphp_root_context(adev->hp);
+		adev->hp = NULL;
+		acpi_unlock_hp_context();
+		kfree(root_context);
+	}
+	cleanup_bridge(bridge);
+	put_bridge(bridge);
 }
 
 /**
@@ -936,8 +959,7 @@ void acpiphp_remove_slots(struct pci_bus *bus)
 	list_for_each_entry(bridge, &bridge_list, list)
 		if (bridge->pci_bus == bus) {
 			mutex_unlock(&bridge_mutex);
-			cleanup_bridge(bridge);
-			put_bridge(bridge);
+			acpiphp_drop_bridge(bridge);
 			return;
 		}
 
diff --git a/drivers/pci/hotplug/cpci_hotplug.h b/drivers/pci/hotplug/cpci_hotplug.h
index 1356211431d..6a0ddf75734 100644
--- a/drivers/pci/hotplug/cpci_hotplug.h
+++ b/drivers/pci/hotplug/cpci_hotplug.h
@@ -56,9 +56,9 @@ struct cpci_hp_controller_ops {
 	int (*enable_irq) (void);
 	int (*disable_irq) (void);
 	int (*check_irq) (void *dev_id);
-	int (*hardware_test) (struct slot* slot, u32 value);
-	u8  (*get_power) (struct slot* slot);
-	int (*set_power) (struct slot* slot, int value);
+	int (*hardware_test) (struct slot *slot, u32 value);
+	u8  (*get_power) (struct slot *slot);
+	int (*set_power) (struct slot *slot, int value);
 };
 
 struct cpci_hp_controller {
@@ -89,13 +89,13 @@ int cpci_hp_stop(void);
 u8 cpci_get_attention_status(struct slot *slot);
 u8 cpci_get_latch_status(struct slot *slot);
 u8 cpci_get_adapter_status(struct slot *slot);
-u16 cpci_get_hs_csr(struct slot * slot);
+u16 cpci_get_hs_csr(struct slot *slot);
 int cpci_set_attention_status(struct slot *slot, int status);
-int cpci_check_and_clear_ins(struct slot * slot);
-int cpci_check_ext(struct slot * slot);
-int cpci_clear_ext(struct slot * slot);
-int cpci_led_on(struct slot * slot);
-int cpci_led_off(struct slot * slot);
+int cpci_check_and_clear_ins(struct slot *slot);
+int cpci_check_ext(struct slot *slot);
+int cpci_clear_ext(struct slot *slot);
+int cpci_led_on(struct slot *slot);
+int cpci_led_off(struct slot *slot);
 int cpci_configure_slot(struct slot *slot);
 int cpci_unconfigure_slot(struct slot *slot);
 
diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c
index 00c81a3cefc..e09cf7827d6 100644
--- a/drivers/pci/hotplug/cpci_hotplug_core.c
+++ b/drivers/pci/hotplug/cpci_hotplug_core.c
@@ -65,10 +65,10 @@ static int thread_finished;
 static int enable_slot(struct hotplug_slot *slot);
 static int disable_slot(struct hotplug_slot *slot);
 static int set_attention_status(struct hotplug_slot *slot, u8 value);
-static int get_power_status(struct hotplug_slot *slot, u8 * value);
-static int get_attention_status(struct hotplug_slot *slot, u8 * value);
-static int get_adapter_status(struct hotplug_slot *slot, u8 * value);
-static int get_latch_status(struct hotplug_slot *slot, u8 * value);
+static int get_power_status(struct hotplug_slot *slot, u8 *value);
+static int get_attention_status(struct hotplug_slot *slot, u8 *value);
+static int get_adapter_status(struct hotplug_slot *slot, u8 *value);
+static int get_latch_status(struct hotplug_slot *slot, u8 *value);
 
 static struct hotplug_slot_ops cpci_hotplug_slot_ops = {
 	.enable_slot = enable_slot,
@@ -168,7 +168,7 @@ cpci_get_power_status(struct slot *slot)
 }
 
 static int
-get_power_status(struct hotplug_slot *hotplug_slot, u8 * value)
+get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
 
@@ -177,7 +177,7 @@ get_power_status(struct hotplug_slot *hotplug_slot, u8 * value)
 }
 
 static int
-get_attention_status(struct hotplug_slot *hotplug_slot, u8 * value)
+get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
 
@@ -192,14 +192,14 @@ set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
 }
 
 static int
-get_adapter_status(struct hotplug_slot *hotplug_slot, u8 * value)
+get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	*value = hotplug_slot->info->adapter_status;
 	return 0;
 }
 
 static int
-get_latch_status(struct hotplug_slot *hotplug_slot, u8 * value)
+get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	*value = hotplug_slot->info->latch_status;
 	return 0;
@@ -299,6 +299,7 @@ error_slot:
 error:
 	return status;
 }
+EXPORT_SYMBOL_GPL(cpci_hp_register_bus);
 
 int
 cpci_hp_unregister_bus(struct pci_bus *bus)
@@ -329,6 +330,7 @@ cpci_hp_unregister_bus(struct pci_bus *bus)
 	up_write(&list_rwsem);
 	return status;
 }
+EXPORT_SYMBOL_GPL(cpci_hp_unregister_bus);
 
 /* This is the interrupt mode interrupt handler */
 static irqreturn_t
@@ -360,7 +362,7 @@ static int
 init_slots(int clear_ins)
 {
 	struct slot *slot;
-	struct pci_dev* dev;
+	struct pci_dev *dev;
 
 	dbg("%s - enter", __func__);
 	down_read(&list_rwsem);
@@ -614,6 +616,7 @@ cpci_hp_register_controller(struct cpci_hp_controller *new_controller)
 		controller = new_controller;
 	return status;
 }
+EXPORT_SYMBOL_GPL(cpci_hp_register_controller);
 
 static void
 cleanup_slots(void)
@@ -653,6 +656,7 @@ cpci_hp_unregister_controller(struct cpci_hp_controller *old_controller)
 		status = -ENODEV;
 	return status;
 }
+EXPORT_SYMBOL_GPL(cpci_hp_unregister_controller);
 
 int
 cpci_hp_start(void)
@@ -690,6 +694,7 @@ cpci_hp_start(void)
 	dbg("%s - exit", __func__);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(cpci_hp_start);
 
 int
 cpci_hp_stop(void)
@@ -704,6 +709,7 @@ cpci_hp_stop(void)
 	cpci_stop_thread();
 	return 0;
 }
+EXPORT_SYMBOL_GPL(cpci_hp_stop);
 
 int __init
 cpci_hotplug_init(int debug)
@@ -721,10 +727,3 @@ cpci_hotplug_exit(void)
 	cpci_hp_stop();
 	cpci_hp_unregister_controller(controller);
 }
-
-EXPORT_SYMBOL_GPL(cpci_hp_register_controller);
-EXPORT_SYMBOL_GPL(cpci_hp_unregister_controller);
-EXPORT_SYMBOL_GPL(cpci_hp_register_bus);
-EXPORT_SYMBOL_GPL(cpci_hp_unregister_bus);
-EXPORT_SYMBOL_GPL(cpci_hp_start);
-EXPORT_SYMBOL_GPL(cpci_hp_stop);
diff --git a/drivers/pci/hotplug/cpci_hotplug_pci.c b/drivers/pci/hotplug/cpci_hotplug_pci.c
index f6ef64c2ccb..7d48ecae669 100644
--- a/drivers/pci/hotplug/cpci_hotplug_pci.c
+++ b/drivers/pci/hotplug/cpci_hotplug_pci.c
@@ -46,7 +46,7 @@ extern int cpci_debug;
 #define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME , ## arg)
 
 
-u8 cpci_get_attention_status(struct slot* slot)
+u8 cpci_get_attention_status(struct slot *slot)
 {
 	int hs_cap;
 	u16 hs_csr;
@@ -66,7 +66,7 @@ u8 cpci_get_attention_status(struct slot* slot)
 	return hs_csr & 0x0008 ? 1 : 0;
 }
 
-int cpci_set_attention_status(struct slot* slot, int status)
+int cpci_set_attention_status(struct slot *slot, int status)
 {
 	int hs_cap;
 	u16 hs_csr;
@@ -93,7 +93,7 @@ int cpci_set_attention_status(struct slot* slot, int status)
 	return 1;
 }
 
-u16 cpci_get_hs_csr(struct slot* slot)
+u16 cpci_get_hs_csr(struct slot *slot)
 {
 	int hs_cap;
 	u16 hs_csr;
@@ -111,7 +111,7 @@ u16 cpci_get_hs_csr(struct slot* slot)
 	return hs_csr;
 }
 
-int cpci_check_and_clear_ins(struct slot* slot)
+int cpci_check_and_clear_ins(struct slot *slot)
 {
 	int hs_cap;
 	u16 hs_csr;
@@ -140,7 +140,7 @@ int cpci_check_and_clear_ins(struct slot* slot)
 	return ins;
 }
 
-int cpci_check_ext(struct slot* slot)
+int cpci_check_ext(struct slot *slot)
 {
 	int hs_cap;
 	u16 hs_csr;
@@ -161,7 +161,7 @@ int cpci_check_ext(struct slot* slot)
 	return ext;
 }
 
-int cpci_clear_ext(struct slot* slot)
+int cpci_clear_ext(struct slot *slot)
 {
 	int hs_cap;
 	u16 hs_csr;
@@ -187,7 +187,7 @@ int cpci_clear_ext(struct slot* slot)
 	return 0;
 }
 
-int cpci_led_on(struct slot* slot)
+int cpci_led_on(struct slot *slot)
 {
 	int hs_cap;
 	u16 hs_csr;
@@ -216,7 +216,7 @@ int cpci_led_on(struct slot* slot)
 	return 0;
 }
 
-int cpci_led_off(struct slot* slot)
+int cpci_led_off(struct slot *slot)
 {
 	int hs_cap;
 	u16 hs_csr;
@@ -303,7 +303,7 @@ int cpci_configure_slot(struct slot *slot)
 	return ret;
 }
 
-int cpci_unconfigure_slot(struct slot* slot)
+int cpci_unconfigure_slot(struct slot *slot)
 {
 	struct pci_dev *dev, *temp;
 
diff --git a/drivers/pci/hotplug/cpcihp_generic.c b/drivers/pci/hotplug/cpcihp_generic.c
index 7536eef620b..04fcd781140 100644
--- a/drivers/pci/hotplug/cpcihp_generic.c
+++ b/drivers/pci/hotplug/cpcihp_generic.c
@@ -78,8 +78,8 @@ static struct cpci_hp_controller generic_hpc;
 
 static int __init validate_parameters(void)
 {
-	char* str;
-	char* p;
+	char *str;
+	char *p;
 	unsigned long tmp;
 
 	if(!bridge) {
@@ -142,8 +142,8 @@ static int query_enum(void)
 static int __init cpcihp_generic_init(void)
 {
 	int status;
-	struct resource* r;
-	struct pci_dev* dev;
+	struct resource *r;
+	struct pci_dev *dev;
 
 	info(DRIVER_DESC " version: " DRIVER_VERSION);
 	status = validate_parameters();
diff --git a/drivers/pci/hotplug/cpcihp_zt5550.c b/drivers/pci/hotplug/cpcihp_zt5550.c
index e8c4a7ccf57..6757b3ef7e1 100644
--- a/drivers/pci/hotplug/cpcihp_zt5550.c
+++ b/drivers/pci/hotplug/cpcihp_zt5550.c
@@ -295,7 +295,7 @@ static struct pci_driver zt5550_hc_driver = {
 
 static int __init zt5550_init(void)
 {
-	struct resource* r;
+	struct resource *r;
 	int rc;
 
 	info(DRIVER_DESC " version: " DRIVER_VERSION);
diff --git a/drivers/pci/hotplug/cpqphp.h b/drivers/pci/hotplug/cpqphp.h
index 516b87738b6..0450f405807 100644
--- a/drivers/pci/hotplug/cpqphp.h
+++ b/drivers/pci/hotplug/cpqphp.h
@@ -255,7 +255,7 @@ struct pci_func {
 	struct pci_resource *io_head;
 	struct pci_resource *bus_head;
 	struct timer_list *p_task_event;
-	struct pci_dev* pci_dev;
+	struct pci_dev *pci_dev;
 };
 
 struct slot {
@@ -278,7 +278,7 @@ struct slot {
 };
 
 struct pci_resource {
-	struct pci_resource * next;
+	struct pci_resource *next;
 	u32 base;
 	u32 length;
 };
diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c
index 037e2612c5b..4aaee746df8 100644
--- a/drivers/pci/hotplug/cpqphp_core.c
+++ b/drivers/pci/hotplug/cpqphp_core.c
@@ -94,7 +94,7 @@ static inline int is_slot66mhz(struct slot *slot)
  *
  * Returns pointer to the head of the SMBIOS tables (or %NULL).
  */
-static void __iomem * detect_SMBIOS_pointer(void __iomem *begin, void __iomem *end)
+static void __iomem *detect_SMBIOS_pointer(void __iomem *begin, void __iomem *end)
 {
 	void __iomem *fp;
 	void __iomem *endp;
@@ -131,7 +131,7 @@ static void __iomem * detect_SMBIOS_pointer(void __iomem *begin, void __iomem *e
  *
  * For unexpected switch opens
  */
-static int init_SERR(struct controller * ctrl)
+static int init_SERR(struct controller *ctrl)
 {
 	u32 tempdword;
 	u32 number_of_slots;
@@ -291,7 +291,7 @@ static void release_slot(struct hotplug_slot *hotplug_slot)
 	kfree(slot);
 }
 
-static int ctrl_slot_cleanup (struct controller * ctrl)
+static int ctrl_slot_cleanup (struct controller *ctrl)
 {
 	struct slot *old_slot, *next_slot;
 
@@ -706,8 +706,7 @@ static int ctrl_slot_setup(struct controller *ctrl,
 		hotplug_slot_info->adapter_status =
 			get_presence_status(ctrl, slot);
 
-		dbg("registering bus %d, dev %d, number %d, "
-				"ctrl->slot_device_offset %d, slot %d\n",
+		dbg("registering bus %d, dev %d, number %d, ctrl->slot_device_offset %d, slot %d\n",
 				slot->bus, slot->device,
 				slot->number, ctrl->slot_device_offset,
 				slot_number);
@@ -837,8 +836,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	bus = pdev->subordinate;
 	if (!bus) {
-		dev_notice(&pdev->dev, "the device is not a bridge, "
-				"skipping\n");
+		dev_notice(&pdev->dev, "the device is not a bridge, skipping\n");
 		rc = -ENODEV;
 		goto err_disable_device;
 	}
diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c
index f593585f278..bde47fce324 100644
--- a/drivers/pci/hotplug/cpqphp_ctrl.c
+++ b/drivers/pci/hotplug/cpqphp_ctrl.c
@@ -39,9 +39,9 @@
 #include <linux/kthread.h>
 #include "cpqphp.h"
 
-static u32 configure_new_device(struct controller* ctrl, struct pci_func *func,
+static u32 configure_new_device(struct controller *ctrl, struct pci_func *func,
 			u8 behind_bridge, struct resource_lists *resources);
-static int configure_new_function(struct controller* ctrl, struct pci_func *func,
+static int configure_new_function(struct controller *ctrl, struct pci_func *func,
 			u8 behind_bridge, struct resource_lists *resources);
 static void interrupt_event_handler(struct controller *ctrl);
 
@@ -64,7 +64,7 @@ static void long_delay(int delay)
 
 /* FIXME: The following line needs to be somewhere else... */
 #define WRONG_BUS_FREQUENCY 0x07
-static u8 handle_switch_change(u8 change, struct controller * ctrl)
+static u8 handle_switch_change(u8 change, struct controller *ctrl)
 {
 	int hp_slot;
 	u8 rc = 0;
@@ -138,7 +138,7 @@ static struct slot *cpqhp_find_slot(struct controller *ctrl, u8 device)
 }
 
 
-static u8 handle_presence_change(u16 change, struct controller * ctrl)
+static u8 handle_presence_change(u16 change, struct controller *ctrl)
 {
 	int hp_slot;
 	u8 rc = 0;
@@ -232,7 +232,7 @@ static u8 handle_presence_change(u16 change, struct controller * ctrl)
 }
 
 
-static u8 handle_power_fault(u8 change, struct controller * ctrl)
+static u8 handle_power_fault(u8 change, struct controller *ctrl)
 {
 	int hp_slot;
 	u8 rc = 0;
@@ -997,7 +997,7 @@ struct pci_func *cpqhp_slot_create(u8 busnumber)
  *
  * Returns %0 if successful, !0 otherwise.
  */
-static int slot_remove(struct pci_func * old_slot)
+static int slot_remove(struct pci_func *old_slot)
 {
 	struct pci_func *next;
 
@@ -1109,7 +1109,7 @@ struct pci_func *cpqhp_slot_find(u8 bus, u8 device, u8 index)
 
 /* DJZ: I don't think is_bridge will work as is.
  * FIXME */
-static int is_bridge(struct pci_func * func)
+static int is_bridge(struct pci_func *func)
 {
 	/* Check the header type */
 	if (((func->config_space[0x03] >> 16) & 0xFF) == 0x01)
@@ -1625,7 +1625,7 @@ static u32 board_added(struct pci_func *func, struct controller *ctrl)
  * @replace_flag: whether replacing or adding a new device
  * @ctrl: target controller
  */
-static u32 remove_board(struct pci_func * func, u32 replace_flag, struct controller * ctrl)
+static u32 remove_board(struct pci_func *func, u32 replace_flag, struct controller *ctrl)
 {
 	int index;
 	u8 skip = 0;
@@ -1742,7 +1742,7 @@ static void pushbutton_helper_thread(unsigned long data)
 
 
 /* this is the main worker thread */
-static int event_thread(void* data)
+static int event_thread(void *data)
 {
 	struct controller *ctrl;
 
@@ -1992,7 +1992,7 @@ int cpqhp_process_SI(struct controller *ctrl, struct pci_func *func)
 	u16 temp_word;
 	u32 tempdword;
 	int rc;
-	struct slot* p_slot;
+	struct slot *p_slot;
 	int physical_slot = 0;
 
 	tempdword = 0;
@@ -2088,7 +2088,7 @@ int cpqhp_process_SS(struct controller *ctrl, struct pci_func *func)
 	u8 replace_flag;
 	u32 rc = 0;
 	unsigned int devfn;
-	struct slot* p_slot;
+	struct slot *p_slot;
 	struct pci_bus *pci_bus = ctrl->pci_bus;
 	int physical_slot=0;
 
@@ -2270,8 +2270,8 @@ int cpqhp_hardware_test(struct controller *ctrl, int test_num)
  *
  * Returns 0 if success.
  */
-static u32 configure_new_device(struct controller * ctrl, struct pci_func * func,
-				 u8 behind_bridge, struct resource_lists * resources)
+static u32 configure_new_device(struct controller  *ctrl, struct pci_func  *func,
+				 u8 behind_bridge, struct resource_lists  *resources)
 {
 	u8 temp_byte, function, max_functions, stop_it;
 	int rc;
diff --git a/drivers/pci/hotplug/cpqphp_nvram.c b/drivers/pci/hotplug/cpqphp_nvram.c
index 9600a392eaa..0968a9bcb34 100644
--- a/drivers/pci/hotplug/cpqphp_nvram.c
+++ b/drivers/pci/hotplug/cpqphp_nvram.c
@@ -107,7 +107,7 @@ static spinlock_t int15_lock;
  */
 
 
-static u32 add_byte( u32 **p_buffer, u8 value, u32 *used, u32 *avail)
+static u32 add_byte(u32 **p_buffer, u8 value, u32 *used, u32 *avail)
 {
 	u8 **tByte;
 
@@ -122,7 +122,7 @@ static u32 add_byte( u32 **p_buffer, u8 value, u32 *used, u32 *avail)
 }
 
 
-static u32 add_dword( u32 **p_buffer, u32 value, u32 *used, u32 *avail)
+static u32 add_dword(u32 **p_buffer, u32 value, u32 *used, u32 *avail)
 {
 	if ((*used + 4) > *avail)
 		return(1);
@@ -267,12 +267,12 @@ static u32 store_HRT (void __iomem *rom_start)
 	ctrl = cpqhp_ctrl_list;
 
 	/* The revision of this structure */
-	rc = add_byte( &pFill, 1 + ctrl->push_flag, &usedbytes, &available);
+	rc = add_byte(&pFill, 1 + ctrl->push_flag, &usedbytes, &available);
 	if (rc)
 		return(rc);
 
 	/* The number of controllers */
-	rc = add_byte( &pFill, 1, &usedbytes, &available);
+	rc = add_byte(&pFill, 1, &usedbytes, &available);
 	if (rc)
 		return(rc);
 
@@ -282,22 +282,22 @@ static u32 store_HRT (void __iomem *rom_start)
 		numCtrl++;
 
 		/* The bus number */
-		rc = add_byte( &pFill, ctrl->bus, &usedbytes, &available);
+		rc = add_byte(&pFill, ctrl->bus, &usedbytes, &available);
 		if (rc)
 			return(rc);
 
 		/* The device Number */
-		rc = add_byte( &pFill, PCI_SLOT(ctrl->pci_dev->devfn), &usedbytes, &available);
+		rc = add_byte(&pFill, PCI_SLOT(ctrl->pci_dev->devfn), &usedbytes, &available);
 		if (rc)
 			return(rc);
 
 		/* The function Number */
-		rc = add_byte( &pFill, PCI_FUNC(ctrl->pci_dev->devfn), &usedbytes, &available);
+		rc = add_byte(&pFill, PCI_FUNC(ctrl->pci_dev->devfn), &usedbytes, &available);
 		if (rc)
 			return(rc);
 
 		/* Skip the number of available entries */
-		rc = add_dword( &pFill, 0, &usedbytes, &available);
+		rc = add_dword(&pFill, 0, &usedbytes, &available);
 		if (rc)
 			return(rc);
 
@@ -311,12 +311,12 @@ static u32 store_HRT (void __iomem *rom_start)
 			loop ++;
 
 			/* base */
-			rc = add_dword( &pFill, resNode->base, &usedbytes, &available);
+			rc = add_dword(&pFill, resNode->base, &usedbytes, &available);
 			if (rc)
 				return(rc);
 
 			/* length */
-			rc = add_dword( &pFill, resNode->length, &usedbytes, &available);
+			rc = add_dword(&pFill, resNode->length, &usedbytes, &available);
 			if (rc)
 				return(rc);
 
@@ -336,12 +336,12 @@ static u32 store_HRT (void __iomem *rom_start)
 			loop ++;
 
 			/* base */
-			rc = add_dword( &pFill, resNode->base, &usedbytes, &available);
+			rc = add_dword(&pFill, resNode->base, &usedbytes, &available);
 			if (rc)
 				return(rc);
 
 			/* length */
-			rc = add_dword( &pFill, resNode->length, &usedbytes, &available);
+			rc = add_dword(&pFill, resNode->length, &usedbytes, &available);
 			if (rc)
 				return(rc);
 
@@ -361,12 +361,12 @@ static u32 store_HRT (void __iomem *rom_start)
 			loop ++;
 
 			/* base */
-			rc = add_dword( &pFill, resNode->base, &usedbytes, &available);
+			rc = add_dword(&pFill, resNode->base, &usedbytes, &available);
 			if (rc)
 				return(rc);
 
 			/* length */
-			rc = add_dword( &pFill, resNode->length, &usedbytes, &available);
+			rc = add_dword(&pFill, resNode->length, &usedbytes, &available);
 			if (rc)
 				return(rc);
 
@@ -386,12 +386,12 @@ static u32 store_HRT (void __iomem *rom_start)
 			loop ++;
 
 			/* base */
-			rc = add_dword( &pFill, resNode->base, &usedbytes, &available);
+			rc = add_dword(&pFill, resNode->base, &usedbytes, &available);
 			if (rc)
 				return(rc);
 
 			/* length */
-			rc = add_dword( &pFill, resNode->length, &usedbytes, &available);
+			rc = add_dword(&pFill, resNode->length, &usedbytes, &available);
 			if (rc)
 				return(rc);
 
diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c
index a3e3c2002b5..1c8c2f130d3 100644
--- a/drivers/pci/hotplug/cpqphp_pci.c
+++ b/drivers/pci/hotplug/cpqphp_pci.c
@@ -81,7 +81,7 @@ static void __iomem *detect_HRT_floating_pointer(void __iomem *begin, void __iom
 }
 
 
-int cpqhp_configure_device (struct controller* ctrl, struct pci_func* func)
+int cpqhp_configure_device (struct controller *ctrl, struct pci_func *func)
 {
 	struct pci_bus *child;
 	int num;
@@ -121,7 +121,7 @@ int cpqhp_configure_device (struct controller* ctrl, struct pci_func* func)
 }
 
 
-int cpqhp_unconfigure_device(struct pci_func* func)
+int cpqhp_unconfigure_device(struct pci_func *func)
 {
 	int j;
 
@@ -129,7 +129,7 @@ int cpqhp_unconfigure_device(struct pci_func* func)
 
 	pci_lock_rescan_remove();
 	for (j=0; j<8 ; j++) {
-		struct pci_dev* temp = pci_get_bus_and_slot(func->bus, PCI_DEVFN(func->device, j));
+		struct pci_dev *temp = pci_get_bus_and_slot(func->bus, PCI_DEVFN(func->device, j));
 		if (temp) {
 			pci_dev_put(temp);
 			pci_stop_and_remove_bus_device(temp);
@@ -203,7 +203,7 @@ int cpqhp_set_irq (u8 bus_num, u8 dev_num, u8 int_pin, u8 irq_num)
 }
 
 
-static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 * dev_num)
+static int PCI_ScanBusForNonBridge(struct controller *ctrl, u8 bus_num, u8 *dev_num)
 {
 	u16 tdevice;
 	u32 work;
@@ -280,7 +280,7 @@ static int PCI_GetBusDevHelper(struct controller *ctrl, u8 *bus_num, u8 *dev_num
 }
 
 
-int cpqhp_get_bus_dev (struct controller *ctrl, u8 * bus_num, u8 * dev_num, u8 slot)
+int cpqhp_get_bus_dev (struct controller *ctrl, u8 *bus_num, u8 *dev_num, u8 slot)
 {
 	/* plain (bridges allowed) */
 	return PCI_GetBusDevHelper(ctrl, bus_num, dev_num, slot, 0);
@@ -465,7 +465,7 @@ int cpqhp_save_config(struct controller *ctrl, int busnumber, int is_hot_plug)
  *
  * returns 0 if success
  */
-int cpqhp_save_slot_config (struct controller *ctrl, struct pci_func * new_slot)
+int cpqhp_save_slot_config (struct controller *ctrl, struct pci_func *new_slot)
 {
 	long rc;
 	u8 class_code;
@@ -549,7 +549,7 @@ int cpqhp_save_slot_config (struct controller *ctrl, struct pci_func * new_slot)
  *
  * returns 0 if success
  */
-int cpqhp_save_base_addr_length(struct controller *ctrl, struct pci_func * func)
+int cpqhp_save_base_addr_length(struct controller *ctrl, struct pci_func *func)
 {
 	u8 cloop;
 	u8 header_type;
@@ -686,7 +686,7 @@ int cpqhp_save_base_addr_length(struct controller *ctrl, struct pci_func * func)
  *
  * returns 0 if success
  */
-int cpqhp_save_used_resources (struct controller *ctrl, struct pci_func * func)
+int cpqhp_save_used_resources (struct controller *ctrl, struct pci_func *func)
 {
 	u8 cloop;
 	u8 header_type;
@@ -949,7 +949,7 @@ int cpqhp_save_used_resources (struct controller *ctrl, struct pci_func * func)
  *
  * returns 0 if success
  */
-int cpqhp_configure_board(struct controller *ctrl, struct pci_func * func)
+int cpqhp_configure_board(struct controller *ctrl, struct pci_func *func)
 {
 	int cloop;
 	u8 header_type;
@@ -1027,7 +1027,7 @@ int cpqhp_configure_board(struct controller *ctrl, struct pci_func * func)
  *
  * returns 0 if the board is the same nonzero otherwise
  */
-int cpqhp_valid_replace(struct controller *ctrl, struct pci_func * func)
+int cpqhp_valid_replace(struct controller *ctrl, struct pci_func *func)
 {
 	u8 cloop;
 	u8 header_type;
@@ -1419,7 +1419,7 @@ int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_st
  *
  * returns 0 if success
  */
-int cpqhp_return_board_resources(struct pci_func * func, struct resource_lists * resources)
+int cpqhp_return_board_resources(struct pci_func *func, struct resource_lists *resources)
 {
 	int rc = 0;
 	struct pci_resource *node;
@@ -1475,7 +1475,7 @@ int cpqhp_return_board_resources(struct pci_func * func, struct resource_lists *
  *
  * Puts node back in the resource list pointed to by head
  */
-void cpqhp_destroy_resource_list (struct resource_lists * resources)
+void cpqhp_destroy_resource_list (struct resource_lists *resources)
 {
 	struct pci_resource *res, *tres;
 
@@ -1522,7 +1522,7 @@ void cpqhp_destroy_resource_list (struct resource_lists * resources)
  *
  * Puts node back in the resource list pointed to by head
  */
-void cpqhp_destroy_board_resources (struct pci_func * func)
+void cpqhp_destroy_board_resources (struct pci_func *func)
 {
 	struct pci_resource *res, *tres;
 
diff --git a/drivers/pci/hotplug/cpqphp_sysfs.c b/drivers/pci/hotplug/cpqphp_sysfs.c
index 17c1f36315d..d81648f7142 100644
--- a/drivers/pci/hotplug/cpqphp_sysfs.c
+++ b/drivers/pci/hotplug/cpqphp_sysfs.c
@@ -79,7 +79,7 @@ static int show_ctrl (struct controller *ctrl, char *buf)
 
 static int show_dev (struct controller *ctrl, char *buf)
 {
-	char * out = buf;
+	char *out = buf;
 	int index;
 	struct pci_resource *res;
 	struct pci_func *new_slot;
@@ -216,8 +216,7 @@ void cpqhp_create_debugfs_files(struct controller *ctrl)
 
 void cpqhp_remove_debugfs_files(struct controller *ctrl)
 {
-	if (ctrl->dentry)
-		debugfs_remove(ctrl->dentry);
+	debugfs_remove(ctrl->dentry);
 	ctrl->dentry = NULL;
 }
 
diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c
index cf3ac1e4b09..f7b8684a773 100644
--- a/drivers/pci/hotplug/ibmphp_core.c
+++ b/drivers/pci/hotplug/ibmphp_core.c
@@ -74,7 +74,7 @@ static inline int get_max_adapter_speed (struct hotplug_slot *hs, u8 *value)
 static inline int get_cur_bus_info(struct slot **sl)
 {
 	int rc = 1;
-	struct slot * slot_cur = *sl;
+	struct slot *slot_cur = *sl;
 
 	debug("options = %x\n", slot_cur->ctrl->options);
 	debug("revision = %x\n", slot_cur->ctrl->revision);
@@ -114,8 +114,8 @@ static inline int slot_update(struct slot **sl)
 
 static int __init get_max_slots (void)
 {
-	struct slot * slot_cur;
-	struct list_head * tmp;
+	struct slot *slot_cur;
+	struct list_head *tmp;
 	u8 slot_count = 0;
 
 	list_for_each(tmp, &ibmphp_slot_head) {
@@ -280,7 +280,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 value)
 	return rc;
 }
 
-static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 * value)
+static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	int rc = -ENODEV;
 	struct slot *pslot;
@@ -311,7 +311,7 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 * value)
 	return rc;
 }
 
-static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 * value)
+static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	int rc = -ENODEV;
 	struct slot *pslot;
@@ -338,7 +338,7 @@ static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 * value)
 }
 
 
-static int get_power_status(struct hotplug_slot *hotplug_slot, u8 * value)
+static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	int rc = -ENODEV;
 	struct slot *pslot;
@@ -364,7 +364,7 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 * value)
 	return rc;
 }
 
-static int get_adapter_present(struct hotplug_slot *hotplug_slot, u8 * value)
+static int get_adapter_present(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	int rc = -ENODEV;
 	struct slot *pslot;
@@ -433,7 +433,7 @@ static int get_max_bus_speed(struct slot *slot)
 }
 
 /*
-static int get_max_adapter_speed_1(struct hotplug_slot *hotplug_slot, u8 * value, u8 flag)
+static int get_max_adapter_speed_1(struct hotplug_slot *hotplug_slot, u8 *value, u8 flag)
 {
 	int rc = -ENODEV;
 	struct slot *pslot;
@@ -471,7 +471,7 @@ static int get_max_adapter_speed_1(struct hotplug_slot *hotplug_slot, u8 * value
 	return rc;
 }
 
-static int get_bus_name(struct hotplug_slot *hotplug_slot, char * value)
+static int get_bus_name(struct hotplug_slot *hotplug_slot, char *value)
 {
 	int rc = -ENODEV;
 	struct slot *pslot = NULL;
@@ -671,7 +671,7 @@ static struct pci_func *ibm_slot_find(u8 busno, u8 device, u8 function)
 {
 	struct pci_func *func_cur;
 	struct slot *slot_cur;
-	struct list_head * tmp;
+	struct list_head *tmp;
 	list_for_each(tmp, &ibmphp_slot_head) {
 		slot_cur = list_entry(tmp, struct slot, ibm_slot_list);
 		if (slot_cur->func) {
@@ -696,8 +696,8 @@ static struct pci_func *ibm_slot_find(u8 busno, u8 device, u8 function)
 static void free_slots(void)
 {
 	struct slot *slot_cur;
-	struct list_head * tmp;
-	struct list_head * next;
+	struct list_head *tmp;
+	struct list_head *next;
 
 	debug("%s -- enter\n", __func__);
 
@@ -825,10 +825,10 @@ static int ibm_configure_device(struct pci_func *func)
 /*******************************************************
  * Returns whether the bus is empty or not
  *******************************************************/
-static int is_bus_empty(struct slot * slot_cur)
+static int is_bus_empty(struct slot *slot_cur)
 {
 	int rc;
-	struct slot * tmp_slot;
+	struct slot *tmp_slot;
 	u8 i = slot_cur->bus_on->slot_min;
 
 	while (i <= slot_cur->bus_on->slot_max) {
@@ -856,7 +856,7 @@ static int is_bus_empty(struct slot * slot_cur)
  * Parameters: slot
  * Returns: bus is set (0) or error code
  ***********************************************************/
-static int set_bus(struct slot * slot_cur)
+static int set_bus(struct slot *slot_cur)
 {
 	int rc;
 	u8 speed;
@@ -956,7 +956,7 @@ static int set_bus(struct slot * slot_cur)
 static int check_limitations(struct slot *slot_cur)
 {
 	u8 i;
-	struct slot * tmp_slot;
+	struct slot *tmp_slot;
 	u8 count = 0;
 	u8 limitation = 0;
 
@@ -1045,8 +1045,7 @@ static int enable_slot(struct hotplug_slot *hs)
 	rc = check_limitations(slot_cur);
 	if (rc) {
 		err("Adding this card exceeds the limitations of this bus.\n");
-		err("(i.e., >1 133MHz cards running on same bus, or "
-		     ">2 66 PCI cards running on same bus.\n");
+		err("(i.e., >1 133MHz cards running on same bus, or >2 66 PCI cards running on same bus.\n");
 		err("Try hot-adding into another bus\n");
 		rc = -EINVAL;
 		goto error_nopower;
@@ -1070,12 +1069,10 @@ static int enable_slot(struct hotplug_slot *hs)
 					!(SLOT_PWRGD(slot_cur->status)))
 			err("power fault occurred trying to power up\n");
 		else if (SLOT_BUS_SPEED(slot_cur->status)) {
-			err("bus speed mismatch occurred.  please check "
-				"current bus speed and card capability\n");
+			err("bus speed mismatch occurred.  please check current bus speed and card capability\n");
 			print_card_capability(slot_cur);
 		} else if (SLOT_BUS_MODE(slot_cur->ext_status)) {
-			err("bus mode mismatch occurred.  please check "
-				"current bus mode and card capability\n");
+			err("bus mode mismatch occurred.  please check current bus mode and card capability\n");
 			print_card_capability(slot_cur);
 		}
 		ibmphp_update_slot_info(slot_cur);
@@ -1098,8 +1095,7 @@ static int enable_slot(struct hotplug_slot *hs)
 		goto error_power;
 	}
 	if (SLOT_POWER(slot_cur->status) && (SLOT_BUS_SPEED(slot_cur->status))) {
-		err("bus speed mismatch occurred.  please check current bus "
-					"speed and card capability\n");
+		err("bus speed mismatch occurred.  please check current bus speed and card capability\n");
 		print_card_capability(slot_cur);
 		goto error_power;
 	}
diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c
index bd044158b36..0f65ac55543 100644
--- a/drivers/pci/hotplug/ibmphp_ebda.c
+++ b/drivers/pci/hotplug/ibmphp_ebda.c
@@ -563,7 +563,7 @@ static int first_slot_num (u8 slot_num, u8 first_slot, u8 var)
 	return rc;
 }
 
-static struct opt_rio_lo * find_rxe_num (u8 slot_num)
+static struct opt_rio_lo *find_rxe_num (u8 slot_num)
 {
 	struct opt_rio_lo *opt_lo_ptr;
 
@@ -575,7 +575,7 @@ static struct opt_rio_lo * find_rxe_num (u8 slot_num)
 	return NULL;
 }
 
-static struct opt_rio * find_chassis_num (u8 slot_num)
+static struct opt_rio *find_chassis_num (u8 slot_num)
 {
 	struct opt_rio *opt_vg_ptr;
 
@@ -593,7 +593,7 @@ static struct opt_rio * find_chassis_num (u8 slot_num)
 static u8 calculate_first_slot (u8 slot_num)
 {
 	u8 first_slot = 1;
-	struct slot * slot_cur;
+	struct slot *slot_cur;
 
 	list_for_each_entry(slot_cur, &ibmphp_slot_head, ibm_slot_list) {
 		if (slot_cur->ctrl) {
@@ -607,7 +607,7 @@ static u8 calculate_first_slot (u8 slot_num)
 
 #define SLOT_NAME_SIZE 30
 
-static char *create_file_name (struct slot * slot_cur)
+static char *create_file_name (struct slot *slot_cur)
 {
 	struct opt_rio *opt_vg_ptr = NULL;
 	struct opt_rio_lo *opt_lo_ptr = NULL;
@@ -1192,7 +1192,7 @@ int ibmphp_register_pci (void)
 	}
 	return rc;
 }
-static int ibmphp_probe (struct pci_dev * dev, const struct pci_device_id *ids)
+static int ibmphp_probe (struct pci_dev *dev, const struct pci_device_id *ids)
 {
 	struct controller *ctrl;
 
diff --git a/drivers/pci/hotplug/ibmphp_hpc.c b/drivers/pci/hotplug/ibmphp_hpc.c
index 5fc7a089f53..a936022956e 100644
--- a/drivers/pci/hotplug/ibmphp_hpc.c
+++ b/drivers/pci/hotplug/ibmphp_hpc.c
@@ -533,7 +533,7 @@ static u8 hpc_readcmdtoindex (u8 cmd, u8 index)
 *
 * Return   0 or error codes
 *---------------------------------------------------------------------*/
-int ibmphp_hpc_readslot (struct slot * pslot, u8 cmd, u8 * pstatus)
+int ibmphp_hpc_readslot (struct slot *pslot, u8 cmd, u8 *pstatus)
 {
 	void __iomem *wpg_bbar = NULL;
 	struct controller *ctlr_ptr;
@@ -672,7 +672,7 @@ int ibmphp_hpc_readslot (struct slot * pslot, u8 cmd, u8 * pstatus)
 *
 * Action: issue a WRITE command to HPC
 *---------------------------------------------------------------------*/
-int ibmphp_hpc_writeslot (struct slot * pslot, u8 cmd)
+int ibmphp_hpc_writeslot (struct slot *pslot, u8 cmd)
 {
 	void __iomem *wpg_bbar = NULL;
 	struct controller *ctlr_ptr;
@@ -1102,7 +1102,7 @@ void __exit ibmphp_hpc_stop_poll_thread (void)
 * Value:
 *---------------------------------------------------------------------*/
 static int hpc_wait_ctlr_notworking (int timeout, struct controller *ctlr_ptr, void __iomem *wpg_bbar,
-				    u8 * pstatus)
+				    u8 *pstatus)
 {
 	int rc = 0;
 	u8 done = 0;
diff --git a/drivers/pci/hotplug/ibmphp_pci.c b/drivers/pci/hotplug/ibmphp_pci.c
index 639ea3a75e1..2fd296706ce 100644
--- a/drivers/pci/hotplug/ibmphp_pci.c
+++ b/drivers/pci/hotplug/ibmphp_pci.c
@@ -47,7 +47,7 @@ static u8 find_sec_number (u8 primary_busno, u8 slotno);
  * We also assign the same irq numbers for multi function devices.
  * These are PIC mode, so shouldn't matter n.e.ways (hopefully)
  */
-static void assign_alt_irq (struct pci_func * cur_func, u8 class_code)
+static void assign_alt_irq (struct pci_func *cur_func, u8 class_code)
 {
 	int j;
 	for (j = 0; j < 4; j++) {
@@ -137,8 +137,8 @@ int ibmphp_configure_card (struct pci_func *func, u8 slotno)
 				     "Please choose another device.\n", cur_func->device);
 				return -ENODEV;
 			} else if (class == PCI_CLASS_DISPLAY_VGA) {
-				err ("The device %x is not supported for hot plugging. "
-				     "Please choose another device.\n", cur_func->device);
+				err ("The device %x is not supported for hot plugging. Please choose another device.\n",
+				     cur_func->device);
 				return -ENODEV;
 			}
 			switch (hdr_type) {
@@ -179,8 +179,8 @@ int ibmphp_configure_card (struct pci_func *func, u8 slotno)
 				case PCI_HEADER_TYPE_MULTIBRIDGE:
 					class >>= 8;
 					if (class != PCI_CLASS_BRIDGE_PCI) {
-						err ("This %x is not PCI-to-PCI bridge, and as is not supported for hot-plugging. "
-						     "Please insert another card.\n", cur_func->device);
+						err ("This %x is not PCI-to-PCI bridge, and as is not supported for hot-plugging.  Please insert another card.\n",
+						     cur_func->device);
 						return -ENODEV;
 					}
 					assign_alt_irq (cur_func, class_code);
@@ -247,8 +247,8 @@ int ibmphp_configure_card (struct pci_func *func, u8 slotno)
 					class >>= 8;
 					debug ("class now is %x\n", class);
 					if (class != PCI_CLASS_BRIDGE_PCI) {
-						err ("This %x is not PCI-to-PCI bridge, and as is not supported for hot-plugging. "
-						     "Please insert another card.\n", cur_func->device);
+						err ("This %x is not PCI-to-PCI bridge, and as is not supported for hot-plugging.  Please insert another card.\n",
+						     cur_func->device);
 						return -ENODEV;
 					}
 
@@ -1073,7 +1073,7 @@ error:
  * Input: bridge function
  * Output: amount of resources needed
  *****************************************************************************/
-static struct res_needed *scan_behind_bridge (struct pci_func * func, u8 busno)
+static struct res_needed *scan_behind_bridge (struct pci_func *func, u8 busno)
 {
 	int count, len[6];
 	u16 vendor_id;
@@ -1125,13 +1125,11 @@ static struct res_needed *scan_behind_bridge (struct pci_func * func, u8 busno)
 
 				class >>= 8;	/* to take revision out, class = class.subclass.prog i/f */
 				if (class == PCI_CLASS_NOT_DEFINED_VGA) {
-					err ("The device %x is VGA compatible and as is not supported for hot plugging. "
-					     "Please choose another device.\n", device);
+					err ("The device %x is VGA compatible and as is not supported for hot plugging.  Please choose another device.\n", device);
 					amount->not_correct = 1;
 					return amount;
 				} else if (class == PCI_CLASS_DISPLAY_VGA) {
-					err ("The device %x is not supported for hot plugging. "
-					     "Please choose another device.\n", device);
+					err ("The device %x is not supported for hot plugging.  Please choose another device.\n", device);
 					amount->not_correct = 1;
 					return amount;
 				}
@@ -1483,12 +1481,10 @@ static int unconfigure_boot_card (struct slot *slot_cur)
 			debug ("hdr_type %x, class %x\n", hdr_type, class);
 			class >>= 8;	/* to take revision out, class = class.subclass.prog i/f */
 			if (class == PCI_CLASS_NOT_DEFINED_VGA) {
-				err ("The device %x function %x is VGA compatible and is not supported for hot removing. "
-				     "Please choose another device.\n", device, function);
+				err ("The device %x function %x is VGA compatible and is not supported for hot removing.  Please choose another device.\n", device, function);
 				return -ENODEV;
 			} else if (class == PCI_CLASS_DISPLAY_VGA) {
-				err ("The device %x function %x is not supported for hot removing. "
-				     "Please choose another device.\n", device, function);
+				err ("The device %x function %x is not supported for hot removing.  Please choose another device.\n", device, function);
 				return -ENODEV;
 			}
 
@@ -1513,9 +1509,7 @@ static int unconfigure_boot_card (struct slot *slot_cur)
 				case PCI_HEADER_TYPE_BRIDGE:
 					class >>= 8;
 					if (class != PCI_CLASS_BRIDGE_PCI) {
-						err ("This device %x function %x is not PCI-to-PCI bridge, "
-						     "and is not supported for hot-removing. "
-						     "Please try another card.\n", device, function);
+						err ("This device %x function %x is not PCI-to-PCI bridge, and is not supported for hot-removing.  Please try another card.\n", device, function);
 						return -ENODEV;
 					}
 					rc = unconfigure_boot_bridge (busno, device, function);
@@ -1529,9 +1523,7 @@ static int unconfigure_boot_card (struct slot *slot_cur)
 				case PCI_HEADER_TYPE_MULTIBRIDGE:
 					class >>= 8;
 					if (class != PCI_CLASS_BRIDGE_PCI) {
-						err ("This device %x function %x is not PCI-to-PCI bridge, "
-						     "and is not supported for hot-removing. "
-						     "Please try another card.\n", device, function);
+						err ("This device %x function %x is not PCI-to-PCI bridge,  and is not supported for hot-removing.  Please try another card.\n", device, function);
 						return -ENODEV;
 					}
 					rc = unconfigure_boot_bridge (busno, device, function);
diff --git a/drivers/pci/hotplug/ibmphp_res.c b/drivers/pci/hotplug/ibmphp_res.c
index a265acb2d51..f34745abd5b 100644
--- a/drivers/pci/hotplug/ibmphp_res.c
+++ b/drivers/pci/hotplug/ibmphp_res.c
@@ -46,9 +46,9 @@ static struct bus_node *find_bus_wprev (u8, struct bus_node **, u8);
 
 static LIST_HEAD(gbuses);
 
-static struct bus_node * __init alloc_error_bus (struct ebda_pci_rsrc * curr, u8 busno, int flag)
+static struct bus_node * __init alloc_error_bus (struct ebda_pci_rsrc *curr, u8 busno, int flag)
 {
-	struct bus_node * newbus;
+	struct bus_node *newbus;
 
 	if (!(curr) && !(flag)) {
 		err ("NULL pointer passed\n");
@@ -69,7 +69,7 @@ static struct bus_node * __init alloc_error_bus (struct ebda_pci_rsrc * curr, u8
 	return newbus;
 }
 
-static struct resource_node * __init alloc_resources (struct ebda_pci_rsrc * curr)
+static struct resource_node * __init alloc_resources (struct ebda_pci_rsrc *curr)
 {
 	struct resource_node *rs;
 
@@ -93,7 +93,7 @@ static struct resource_node * __init alloc_resources (struct ebda_pci_rsrc * cur
 
 static int __init alloc_bus_range (struct bus_node **new_bus, struct range_node **new_range, struct ebda_pci_rsrc *curr, int flag, u8 first_bus)
 {
-	struct bus_node * newbus;
+	struct bus_node *newbus;
 	struct range_node *newrange;
 	u8 num_ranges = 0;
 
@@ -789,8 +789,7 @@ int ibmphp_remove_resource (struct resource_node *res)
 	bus_cur = find_bus_wprev (res->busno, NULL, 0);
 
 	if (!bus_cur) {
-		err ("cannot find corresponding bus of the io resource to remove  "
-			"bailing out...\n");
+		err ("cannot find corresponding bus of the io resource to remove  bailing out...\n");
 		return -ENODEV;
 	}
 
@@ -934,9 +933,9 @@ int ibmphp_remove_resource (struct resource_node *res)
 	return 0;
 }
 
-static struct range_node * find_range (struct bus_node *bus_cur, struct resource_node * res)
+static struct range_node *find_range (struct bus_node *bus_cur, struct resource_node *res)
 {
-	struct range_node * range = NULL;
+	struct range_node *range = NULL;
 
 	switch (res->type) {
 		case IO:
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index cfa92a984e6..56d8486dc16 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -59,14 +59,12 @@ static bool debug;
 #define DRIVER_DESC	"PCI Hot Plug PCI Core"
 
 
-//////////////////////////////////////////////////////////////////
-
 static LIST_HEAD(pci_hotplug_slot_list);
 static DEFINE_MUTEX(pci_hp_mutex);
 
 /* Weee, fun with macros... */
-#define GET_STATUS(name,type)	\
-static int get_##name (struct hotplug_slot *slot, type *value)		\
+#define GET_STATUS(name, type)	\
+static int get_##name(struct hotplug_slot *slot, type *value)		\
 {									\
 	struct hotplug_slot_ops *ops = slot->ops;			\
 	int retval = 0;							\
@@ -92,42 +90,41 @@ static ssize_t power_read_file(struct pci_slot *slot, char *buf)
 
 	retval = get_power_status(slot->hotplug, &value);
 	if (retval)
-		goto exit;
-	retval = sprintf (buf, "%d\n", value);
-exit:
-	return retval;
+		return retval;
+
+	return sprintf(buf, "%d\n", value);
 }
 
 static ssize_t power_write_file(struct pci_slot *pci_slot, const char *buf,
-		size_t count)
+				size_t count)
 {
 	struct hotplug_slot *slot = pci_slot->hotplug;
 	unsigned long lpower;
 	u8 power;
 	int retval = 0;
 
-	lpower = simple_strtoul (buf, NULL, 10);
+	lpower = simple_strtoul(buf, NULL, 10);
 	power = (u8)(lpower & 0xff);
-	dbg ("power = %d\n", power);
+	dbg("power = %d\n", power);
 
 	if (!try_module_get(slot->ops->owner)) {
 		retval = -ENODEV;
 		goto exit;
 	}
 	switch (power) {
-		case 0:
-			if (slot->ops->disable_slot)
-				retval = slot->ops->disable_slot(slot);
-			break;
-
-		case 1:
-			if (slot->ops->enable_slot)
-				retval = slot->ops->enable_slot(slot);
-			break;
-
-		default:
-			err ("Illegal value specified for power\n");
-			retval = -EINVAL;
+	case 0:
+		if (slot->ops->disable_slot)
+			retval = slot->ops->disable_slot(slot);
+		break;
+
+	case 1:
+		if (slot->ops->enable_slot)
+			retval = slot->ops->enable_slot(slot);
+		break;
+
+	default:
+		err("Illegal value specified for power\n");
+		retval = -EINVAL;
 	}
 	module_put(slot->ops->owner);
 
@@ -150,24 +147,22 @@ static ssize_t attention_read_file(struct pci_slot *slot, char *buf)
 
 	retval = get_attention_status(slot->hotplug, &value);
 	if (retval)
-		goto exit;
-	retval = sprintf(buf, "%d\n", value);
+		return retval;
 
-exit:
-	return retval;
+	return sprintf(buf, "%d\n", value);
 }
 
 static ssize_t attention_write_file(struct pci_slot *slot, const char *buf,
-		size_t count)
+				    size_t count)
 {
 	struct hotplug_slot_ops *ops = slot->hotplug->ops;
 	unsigned long lattention;
 	u8 attention;
 	int retval = 0;
 
-	lattention = simple_strtoul (buf, NULL, 10);
+	lattention = simple_strtoul(buf, NULL, 10);
 	attention = (u8)(lattention & 0xff);
-	dbg (" - attention = %d\n", attention);
+	dbg(" - attention = %d\n", attention);
 
 	if (!try_module_get(ops->owner)) {
 		retval = -ENODEV;
@@ -196,11 +191,9 @@ static ssize_t latch_read_file(struct pci_slot *slot, char *buf)
 
 	retval = get_latch_status(slot->hotplug, &value);
 	if (retval)
-		goto exit;
-	retval = sprintf (buf, "%d\n", value);
+		return retval;
 
-exit:
-	return retval;
+	return sprintf(buf, "%d\n", value);
 }
 
 static struct pci_slot_attribute hotplug_slot_attr_latch = {
@@ -215,11 +208,9 @@ static ssize_t presence_read_file(struct pci_slot *slot, char *buf)
 
 	retval = get_adapter_status(slot->hotplug, &value);
 	if (retval)
-		goto exit;
-	retval = sprintf (buf, "%d\n", value);
+		return retval;
 
-exit:
-	return retval;
+	return sprintf(buf, "%d\n", value);
 }
 
 static struct pci_slot_attribute hotplug_slot_attr_presence = {
@@ -228,7 +219,7 @@ static struct pci_slot_attribute hotplug_slot_attr_presence = {
 };
 
 static ssize_t test_write_file(struct pci_slot *pci_slot, const char *buf,
-		size_t count)
+			       size_t count)
 {
 	struct hotplug_slot *slot = pci_slot->hotplug;
 	unsigned long ltest;
@@ -237,7 +228,7 @@ static ssize_t test_write_file(struct pci_slot *pci_slot, const char *buf,
 
 	ltest = simple_strtoul (buf, NULL, 10);
 	test = (u32)(ltest & 0xffffffff);
-	dbg ("test = %d\n", test);
+	dbg("test = %d\n", test);
 
 	if (!try_module_get(slot->ops->owner)) {
 		retval = -ENODEV;
@@ -261,6 +252,7 @@ static struct pci_slot_attribute hotplug_slot_attr_test = {
 static bool has_power_file(struct pci_slot *pci_slot)
 {
 	struct hotplug_slot *slot = pci_slot->hotplug;
+
 	if ((!slot) || (!slot->ops))
 		return false;
 	if ((slot->ops->enable_slot) ||
@@ -273,6 +265,7 @@ static bool has_power_file(struct pci_slot *pci_slot)
 static bool has_attention_file(struct pci_slot *pci_slot)
 {
 	struct hotplug_slot *slot = pci_slot->hotplug;
+
 	if ((!slot) || (!slot->ops))
 		return false;
 	if ((slot->ops->set_attention_status) ||
@@ -284,6 +277,7 @@ static bool has_attention_file(struct pci_slot *pci_slot)
 static bool has_latch_file(struct pci_slot *pci_slot)
 {
 	struct hotplug_slot *slot = pci_slot->hotplug;
+
 	if ((!slot) || (!slot->ops))
 		return false;
 	if (slot->ops->get_latch_status)
@@ -294,6 +288,7 @@ static bool has_latch_file(struct pci_slot *pci_slot)
 static bool has_adapter_file(struct pci_slot *pci_slot)
 {
 	struct hotplug_slot *slot = pci_slot->hotplug;
+
 	if ((!slot) || (!slot->ops))
 		return false;
 	if (slot->ops->get_adapter_status)
@@ -304,6 +299,7 @@ static bool has_adapter_file(struct pci_slot *pci_slot)
 static bool has_test_file(struct pci_slot *pci_slot)
 {
 	struct hotplug_slot *slot = pci_slot->hotplug;
+
 	if ((!slot) || (!slot->ops))
 		return false;
 	if (slot->ops->hardware_test)
@@ -397,13 +393,13 @@ static void fs_remove_slot(struct pci_slot *slot)
 	pci_hp_remove_module_link(slot);
 }
 
-static struct hotplug_slot *get_slot_from_name (const char *name)
+static struct hotplug_slot *get_slot_from_name(const char *name)
 {
 	struct hotplug_slot *slot;
 	struct list_head *tmp;
 
-	list_for_each (tmp, &pci_hotplug_slot_list) {
-		slot = list_entry (tmp, struct hotplug_slot, slot_list);
+	list_for_each(tmp, &pci_hotplug_slot_list) {
+		slot = list_entry(tmp, struct hotplug_slot, slot_list);
 		if (strcmp(hotplug_slot_name(slot), name) == 0)
 			return slot;
 	}
@@ -436,8 +432,7 @@ int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus,
 	if ((slot->info == NULL) || (slot->ops == NULL))
 		return -EINVAL;
 	if (slot->release == NULL) {
-		dbg("Why are you trying to register a hotplug slot "
-		    "without a proper release function?\n");
+		dbg("Why are you trying to register a hotplug slot without a proper release function?\n");
 		return -EINVAL;
 	}
 
@@ -468,6 +463,7 @@ out:
 	mutex_unlock(&pci_hp_mutex);
 	return result;
 }
+EXPORT_SYMBOL_GPL(__pci_hp_register);
 
 /**
  * pci_hp_deregister - deregister a hotplug_slot with the PCI hotplug subsystem
@@ -506,6 +502,7 @@ int pci_hp_deregister(struct hotplug_slot *hotplug)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pci_hp_deregister);
 
 /**
  * pci_hp_change_slot_info - changes the slot's information structure in the core
@@ -527,24 +524,23 @@ int pci_hp_change_slot_info(struct hotplug_slot *hotplug,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pci_hp_change_slot_info);
 
-static int __init pci_hotplug_init (void)
+static int __init pci_hotplug_init(void)
 {
 	int result;
 
 	result = cpci_hotplug_init(debug);
 	if (result) {
-		err ("cpci_hotplug_init with error %d\n", result);
-		goto err_cpci;
+		err("cpci_hotplug_init with error %d\n", result);
+		return result;
 	}
 
-	info (DRIVER_DESC " version: " DRIVER_VERSION "\n");
-
-err_cpci:
+	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
 	return result;
 }
 
-static void __exit pci_hotplug_exit (void)
+static void __exit pci_hotplug_exit(void)
 {
 	cpci_hotplug_exit();
 }
@@ -557,7 +553,3 @@ MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 module_param(debug, bool, 0644);
 MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
-
-EXPORT_SYMBOL_GPL(__pci_hp_register);
-EXPORT_SYMBOL_GPL(pci_hp_deregister);
-EXPORT_SYMBOL_GPL(pci_hp_change_slot_info);
diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 8e9012dca45..9e5a9fbb93d 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -92,9 +92,10 @@ struct controller {
 	struct slot *slot;
 	wait_queue_head_t queue;	/* sleep & wake process */
 	u32 slot_cap;
+	u32 slot_ctrl;
 	struct timer_list poll_timer;
+	unsigned long cmd_started;	/* jiffies */
 	unsigned int cmd_busy:1;
-	unsigned int no_cmd_complete:1;
 	unsigned int link_active_reporting:1;
 	unsigned int notification_enabled:1;
 	unsigned int power_fault_detected;
diff --git a/drivers/pci/hotplug/pciehp_acpi.c b/drivers/pci/hotplug/pciehp_acpi.c
index 20fea57d214..93cc9266e8c 100644
--- a/drivers/pci/hotplug/pciehp_acpi.c
+++ b/drivers/pci/hotplug/pciehp_acpi.c
@@ -103,10 +103,10 @@ static int __init dummy_probe(struct pcie_device *dev)
 }
 
 static struct pcie_port_service_driver __initdata dummy_driver = {
-        .name           = "pciehp_dummy",
+	.name		= "pciehp_dummy",
 	.port_type	= PCIE_ANY_PORT,
 	.service	= PCIE_PORT_SERVICE_HP,
-        .probe          = dummy_probe,
+	.probe		= dummy_probe,
 };
 
 static int __init select_detection_mode(void)
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 0e0a2fff20a..07aa722bb12 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -255,6 +255,13 @@ static int pciehp_probe(struct pcie_device *dev)
 	else if (pciehp_acpi_slot_detection_check(dev->port))
 		goto err_out_none;
 
+	if (!dev->port->subordinate) {
+		/* Can happen if we run out of bus numbers during probe */
+		dev_err(&dev->device,
+			"Hotplug bridge without secondary bus, ignoring\n");
+		goto err_out_none;
+	}
+
 	ctrl = pcie_init(dev);
 	if (!ctrl) {
 		dev_err(&dev->device, "Controller initialization failed\n");
@@ -266,8 +273,7 @@ static int pciehp_probe(struct pcie_device *dev)
 	rc = init_slot(ctrl);
 	if (rc) {
 		if (rc == -EBUSY)
-			ctrl_warn(ctrl, "Slot already registered by another "
-				  "hotplug driver\n");
+			ctrl_warn(ctrl, "Slot already registered by another hotplug driver\n");
 		else
 			ctrl_err(ctrl, "Slot initialization failed\n");
 		goto err_out_release_ctlr;
@@ -312,12 +318,12 @@ static void pciehp_remove(struct pcie_device *dev)
 }
 
 #ifdef CONFIG_PM
-static int pciehp_suspend (struct pcie_device *dev)
+static int pciehp_suspend(struct pcie_device *dev)
 {
 	return 0;
 }
 
-static int pciehp_resume (struct pcie_device *dev)
+static int pciehp_resume(struct pcie_device *dev)
 {
 	struct controller *ctrl;
 	struct slot *slot;
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index c75e6a678dc..ff32e85e1de 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -175,7 +175,7 @@ void pciehp_handle_linkstate_change(struct slot *p_slot)
    hotplug controller logic
  */
 
-static void set_slot_off(struct controller *ctrl, struct slot * pslot)
+static void set_slot_off(struct controller *ctrl, struct slot *pslot)
 {
 	/* turn off slot, turn on Amber LED, turn off Green LED if supported*/
 	if (POWER_CTRL(ctrl)) {
@@ -376,14 +376,12 @@ static void handle_button_press_event(struct slot *p_slot)
 		pciehp_get_power_status(p_slot, &getstatus);
 		if (getstatus) {
 			p_slot->state = BLINKINGOFF_STATE;
-			ctrl_info(ctrl,
-				  "PCI slot #%s - powering off due to button "
-				  "press.\n", slot_name(p_slot));
+			ctrl_info(ctrl, "PCI slot #%s - powering off due to button press\n",
+				  slot_name(p_slot));
 		} else {
 			p_slot->state = BLINKINGON_STATE;
-			ctrl_info(ctrl,
-				  "PCI slot #%s - powering on due to button "
-				  "press.\n", slot_name(p_slot));
+			ctrl_info(ctrl, "PCI slot #%s - powering on due to button press\n",
+				  slot_name(p_slot));
 		}
 		/* blink green LED and turn off amber */
 		pciehp_green_led_blink(p_slot);
@@ -404,8 +402,8 @@ static void handle_button_press_event(struct slot *p_slot)
 		else
 			pciehp_green_led_off(p_slot);
 		pciehp_set_attention_status(p_slot, 0);
-		ctrl_info(ctrl, "PCI slot #%s - action canceled "
-			  "due to button press\n", slot_name(p_slot));
+		ctrl_info(ctrl, "PCI slot #%s - action canceled due to button press\n",
+			  slot_name(p_slot));
 		p_slot->state = STATIC_STATE;
 		break;
 	case POWEROFF_STATE:
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 1463412cf7f..9da84b8b27d 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -104,11 +104,10 @@ static inline void pciehp_free_irq(struct controller *ctrl)
 		free_irq(ctrl->pcie->irq, ctrl);
 }
 
-static int pcie_poll_cmd(struct controller *ctrl)
+static int pcie_poll_cmd(struct controller *ctrl, int timeout)
 {
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 slot_status;
-	int timeout = 1000;
 
 	pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status);
 	if (slot_status & PCI_EXP_SLTSTA_CC) {
@@ -129,18 +128,52 @@ static int pcie_poll_cmd(struct controller *ctrl)
 	return 0;	/* timeout */
 }
 
-static void pcie_wait_cmd(struct controller *ctrl, int poll)
+static void pcie_wait_cmd(struct controller *ctrl)
 {
 	unsigned int msecs = pciehp_poll_mode ? 2500 : 1000;
-	unsigned long timeout = msecs_to_jiffies(msecs);
+	unsigned long duration = msecs_to_jiffies(msecs);
+	unsigned long cmd_timeout = ctrl->cmd_started + duration;
+	unsigned long now, timeout;
 	int rc;
 
-	if (poll)
-		rc = pcie_poll_cmd(ctrl);
+	/*
+	 * If the controller does not generate notifications for command
+	 * completions, we never need to wait between writes.
+	 */
+	if (NO_CMD_CMPL(ctrl))
+		return;
+
+	if (!ctrl->cmd_busy)
+		return;
+
+	/*
+	 * Even if the command has already timed out, we want to call
+	 * pcie_poll_cmd() so it can clear PCI_EXP_SLTSTA_CC.
+	 */
+	now = jiffies;
+	if (time_before_eq(cmd_timeout, now))
+		timeout = 1;
 	else
+		timeout = cmd_timeout - now;
+
+	if (ctrl->slot_ctrl & PCI_EXP_SLTCTL_HPIE &&
+	    ctrl->slot_ctrl & PCI_EXP_SLTCTL_CCIE)
 		rc = wait_event_timeout(ctrl->queue, !ctrl->cmd_busy, timeout);
+	else
+		rc = pcie_poll_cmd(ctrl, timeout);
+
+	/*
+	 * Controllers with errata like Intel CF118 don't generate
+	 * completion notifications unless the power/indicator/interlock
+	 * control bits are changed.  On such controllers, we'll emit this
+	 * timeout message when we wait for completion of commands that
+	 * don't change those bits, e.g., commands that merely enable
+	 * interrupts.
+	 */
 	if (!rc)
-		ctrl_dbg(ctrl, "Command not completed in 1000 msec\n");
+		ctrl_info(ctrl, "Timeout on hotplug command %#010x (issued %u msec ago)\n",
+			  ctrl->slot_ctrl,
+			  jiffies_to_msecs(now - ctrl->cmd_started));
 }
 
 /**
@@ -152,36 +185,12 @@ static void pcie_wait_cmd(struct controller *ctrl, int poll)
 static void pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
 {
 	struct pci_dev *pdev = ctrl_dev(ctrl);
-	u16 slot_status;
 	u16 slot_ctrl;
 
 	mutex_lock(&ctrl->ctrl_lock);
 
-	pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status);
-	if (slot_status & PCI_EXP_SLTSTA_CC) {
-		pcie_capability_write_word(pdev, PCI_EXP_SLTSTA,
-					   PCI_EXP_SLTSTA_CC);
-		if (!ctrl->no_cmd_complete) {
-			/*
-			 * After 1 sec and CMD_COMPLETED still not set, just
-			 * proceed forward to issue the next command according
-			 * to spec. Just print out the error message.
-			 */
-			ctrl_dbg(ctrl, "CMD_COMPLETED not clear after 1 sec\n");
-		} else if (!NO_CMD_CMPL(ctrl)) {
-			/*
-			 * This controller seems to notify of command completed
-			 * event even though it supports none of power
-			 * controller, attention led, power led and EMI.
-			 */
-			ctrl_dbg(ctrl, "Unexpected CMD_COMPLETED. Need to "
-				 "wait for command completed event.\n");
-			ctrl->no_cmd_complete = 0;
-		} else {
-			ctrl_dbg(ctrl, "Unexpected CMD_COMPLETED. Maybe "
-				 "the controller is broken.\n");
-		}
-	}
+	/* Wait for any previous command that might still be in progress */
+	pcie_wait_cmd(ctrl);
 
 	pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &slot_ctrl);
 	slot_ctrl &= ~mask;
@@ -189,22 +198,9 @@ static void pcie_write_cmd(struct controller *ctrl, u16 cmd, u16 mask)
 	ctrl->cmd_busy = 1;
 	smp_mb();
 	pcie_capability_write_word(pdev, PCI_EXP_SLTCTL, slot_ctrl);
+	ctrl->cmd_started = jiffies;
+	ctrl->slot_ctrl = slot_ctrl;
 
-	/*
-	 * Wait for command completion.
-	 */
-	if (!ctrl->no_cmd_complete) {
-		int poll = 0;
-		/*
-		 * if hotplug interrupt is not enabled or command
-		 * completed interrupt is not enabled, we need to poll
-		 * command completed event.
-		 */
-		if (!(slot_ctrl & PCI_EXP_SLTCTL_HPIE) ||
-		    !(slot_ctrl & PCI_EXP_SLTCTL_CCIE))
-			poll = 1;
-                pcie_wait_cmd(ctrl, poll);
-	}
 	mutex_unlock(&ctrl->ctrl_lock);
 }
 
@@ -276,15 +272,15 @@ int pciehp_check_link_status(struct controller *ctrl)
 	bool found;
 	u16 lnk_status;
 
-        /*
-         * Data Link Layer Link Active Reporting must be capable for
-         * hot-plug capable downstream port. But old controller might
-         * not implement it. In this case, we wait for 1000 ms.
-         */
-        if (ctrl->link_active_reporting)
-                pcie_wait_link_active(ctrl);
-        else
-                msleep(1000);
+	/*
+	 * Data Link Layer Link Active Reporting must be capable for
+	 * hot-plug capable downstream port. But old controller might
+	 * not implement it. In this case, we wait for 1000 ms.
+	*/
+	if (ctrl->link_active_reporting)
+		pcie_wait_link_active(ctrl);
+	else
+		msleep(1000);
 
 	/* wait 100ms before read pci conf, and try in 1s */
 	msleep(100);
@@ -295,7 +291,7 @@ int pciehp_check_link_status(struct controller *ctrl)
 	ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status);
 	if ((lnk_status & PCI_EXP_LNKSTA_LT) ||
 	    !(lnk_status & PCI_EXP_LNKSTA_NLW)) {
-		ctrl_err(ctrl, "Link Training Error occurs \n");
+		ctrl_err(ctrl, "Link Training Error occurs\n");
 		return -1;
 	}
 
@@ -414,7 +410,7 @@ void pciehp_set_attention_status(struct slot *slot, u8 value)
 		return;
 
 	switch (value) {
-	case 0 :	/* turn off */
+	case 0:		/* turn off */
 		slot_cmd = PCI_EXP_SLTCTL_ATTN_IND_OFF;
 		break;
 	case 1:		/* turn on */
@@ -470,7 +466,7 @@ void pciehp_green_led_blink(struct slot *slot)
 		 PCI_EXP_SLTCTL_PWR_IND_BLINK);
 }
 
-int pciehp_power_on_slot(struct slot * slot)
+int pciehp_power_on_slot(struct slot *slot)
 {
 	struct controller *ctrl = slot->ctrl;
 	struct pci_dev *pdev = ctrl_dev(ctrl);
@@ -496,7 +492,7 @@ int pciehp_power_on_slot(struct slot * slot)
 	return retval;
 }
 
-void pciehp_power_off_slot(struct slot * slot)
+void pciehp_power_off_slot(struct slot *slot)
 {
 	struct controller *ctrl = slot->ctrl;
 
@@ -756,7 +752,7 @@ static inline void dbg_ctrl(struct controller *ctrl)
 	ctrl_info(ctrl, "Slot Control           : 0x%04x\n", reg16);
 }
 
-#define FLAG(x,y)	(((x) & (y)) ? '+' : '-')
+#define FLAG(x, y)	(((x) & (y)) ? '+' : '-')
 
 struct controller *pcie_init(struct pcie_device *dev)
 {
@@ -775,28 +771,19 @@ struct controller *pcie_init(struct pcie_device *dev)
 	mutex_init(&ctrl->ctrl_lock);
 	init_waitqueue_head(&ctrl->queue);
 	dbg_ctrl(ctrl);
-	/*
-	 * Controller doesn't notify of command completion if the "No
-	 * Command Completed Support" bit is set in Slot Capability
-	 * register or the controller supports none of power
-	 * controller, attention led, power led and EMI.
-	 */
-	if (NO_CMD_CMPL(ctrl) ||
-	    !(POWER_CTRL(ctrl) | ATTN_LED(ctrl) | PWR_LED(ctrl) | EMI(ctrl)))
-	    ctrl->no_cmd_complete = 1;
 
-        /* Check if Data Link Layer Link Active Reporting is implemented */
-        pcie_capability_read_dword(pdev, PCI_EXP_LNKCAP, &link_cap);
-        if (link_cap & PCI_EXP_LNKCAP_DLLLARC) {
-                ctrl_dbg(ctrl, "Link Active Reporting supported\n");
-                ctrl->link_active_reporting = 1;
-        }
+	/* Check if Data Link Layer Link Active Reporting is implemented */
+	pcie_capability_read_dword(pdev, PCI_EXP_LNKCAP, &link_cap);
+	if (link_cap & PCI_EXP_LNKCAP_DLLLARC) {
+		ctrl_dbg(ctrl, "Link Active Reporting supported\n");
+		ctrl->link_active_reporting = 1;
+	}
 
 	/* Clear all remaining event bits in Slot Status register */
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA,
 		PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD |
 		PCI_EXP_SLTSTA_MRLSC | PCI_EXP_SLTSTA_PDC |
-		PCI_EXP_SLTSTA_CC);
+		PCI_EXP_SLTSTA_CC | PCI_EXP_SLTSTA_DLLSC);
 
 	/* Disable software notification */
 	pcie_disable_notification(ctrl);
diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c
index b6cb1df6709..5f871f4c4af 100644
--- a/drivers/pci/hotplug/pciehp_pci.c
+++ b/drivers/pci/hotplug/pciehp_pci.c
@@ -46,9 +46,8 @@ int pciehp_configure_device(struct slot *p_slot)
 
 	dev = pci_get_slot(parent, PCI_DEVFN(0, 0));
 	if (dev) {
-		ctrl_err(ctrl, "Device %s already exists "
-			 "at %04x:%02x:00, cannot hot-add\n", pci_name(dev),
-			 pci_domain_nr(parent), parent->number);
+		ctrl_err(ctrl, "Device %s already exists at %04x:%02x:00, cannot hot-add\n",
+			 pci_name(dev), pci_domain_nr(parent), parent->number);
 		pci_dev_put(dev);
 		ret = -EEXIST;
 		goto out;
diff --git a/drivers/pci/hotplug/pcihp_skeleton.c b/drivers/pci/hotplug/pcihp_skeleton.c
index ac69094e4b2..d062c008fc9 100644
--- a/drivers/pci/hotplug/pcihp_skeleton.c
+++ b/drivers/pci/hotplug/pcihp_skeleton.c
@@ -51,7 +51,7 @@ static LIST_HEAD(slot_list);
 #define dbg(format, arg...)					\
 	do {							\
 		if (debug)					\
-			printk (KERN_DEBUG "%s: " format "\n",	\
+			printk(KERN_DEBUG "%s: " format "\n",	\
 				MY_NAME , ## arg);		\
 	} while (0)
 #define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME , ## arg)
@@ -128,18 +128,18 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
 	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
 
 	switch (status) {
-		case 0:
-			/*
-			 * Fill in code here to turn light off
-			 */
-			break;
-
-		case 1:
-		default:
-			/*
-			 * Fill in code here to turn light on
-			 */
-			break;
+	case 0:
+		/*
+		 * Fill in code here to turn light off
+		 */
+		break;
+
+	case 1:
+	default:
+		/*
+		 * Fill in code here to turn light on
+		 */
+		break;
 	}
 
 	return retval;
@@ -153,12 +153,12 @@ static int hardware_test(struct hotplug_slot *hotplug_slot, u32 value)
 	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
 
 	switch (value) {
-		case 0:
-			/* Specify a test here */
-			break;
-		case 1:
-			/* Specify another test here */
-			break;
+	case 0:
+		/* Specify a test here */
+		break;
+	case 1:
+		/* Specify another test here */
+		break;
 	}
 
 	return retval;
diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c
index 984d708552f..93aa29f6d39 100644
--- a/drivers/pci/hotplug/rpaphp_core.c
+++ b/drivers/pci/hotplug/rpaphp_core.c
@@ -39,6 +39,7 @@
 
 bool rpaphp_debug;
 LIST_HEAD(rpaphp_slot_head);
+EXPORT_SYMBOL_GPL(rpaphp_slot_head);
 
 #define DRIVER_VERSION	"0.1"
 #define DRIVER_AUTHOR	"Linda Xie <lxie@us.ibm.com>"
@@ -88,7 +89,7 @@ static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 value)
  * @hotplug_slot: slot to get status
  * @value: pointer to store status
  */
-static int get_power_status(struct hotplug_slot *hotplug_slot, u8 * value)
+static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	int retval, level;
 	struct slot *slot = (struct slot *)hotplug_slot->private;
@@ -104,14 +105,14 @@ static int get_power_status(struct hotplug_slot *hotplug_slot, u8 * value)
  * @hotplug_slot: slot to get status
  * @value: pointer to store status
  */
-static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 * value)
+static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = (struct slot *)hotplug_slot->private;
 	*value = slot->hotplug_slot->info->attention_status;
 	return 0;
 }
 
-static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 * value)
+static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = (struct slot *)hotplug_slot->private;
 	int rc, state;
@@ -241,6 +242,7 @@ int rpaphp_get_drc_props(struct device_node *dn, int *drc_index,
 
 	return -EINVAL;
 }
+EXPORT_SYMBOL_GPL(rpaphp_get_drc_props);
 
 static int is_php_type(char *drc_type)
 {
@@ -350,6 +352,7 @@ int rpaphp_add_slot(struct device_node *dn)
 	/* XXX FIXME: reports a failure only if last entry in loop failed */
 	return retval;
 }
+EXPORT_SYMBOL_GPL(rpaphp_add_slot);
 
 static void __exit cleanup_slots(void)
 {
@@ -443,7 +446,3 @@ struct hotplug_slot_ops rpaphp_hotplug_slot_ops = {
 
 module_init(rpaphp_init);
 module_exit(rpaphp_exit);
-
-EXPORT_SYMBOL_GPL(rpaphp_add_slot);
-EXPORT_SYMBOL_GPL(rpaphp_slot_head);
-EXPORT_SYMBOL_GPL(rpaphp_get_drc_props);
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
index 613043f7576..bada2099987 100644
--- a/drivers/pci/hotplug/sgi_hotplug.c
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -188,7 +188,7 @@ static int sn_hp_slot_private_alloc(struct hotplug_slot *bss_hotplug_slot,
 	return 0;
 }
 
-static struct hotplug_slot * sn_hp_destroy(void)
+static struct hotplug_slot *sn_hp_destroy(void)
 {
 	struct slot *slot;
 	struct pci_slot *pci_slot;
@@ -250,15 +250,13 @@ static int sn_slot_enable(struct hotplug_slot *bss_hotplug_slot,
 	}
 
 	if (rc == PCI_L1_ERR) {
-		dev_dbg(&slot->pci_bus->self->dev,
-			"L1 failure %d with message: %s",
+		dev_dbg(&slot->pci_bus->self->dev, "L1 failure %d with message: %s",
 			resp.resp_sub_errno, resp.resp_l1_msg);
 		return -EPERM;
 	}
 
 	if (rc) {
-		dev_dbg(&slot->pci_bus->self->dev,
-			"insert failed with error %d sub-error %d\n",
+		dev_dbg(&slot->pci_bus->self->dev, "insert failed with error %d sub-error %d\n",
 			rc, resp.resp_sub_errno);
 		return -EIO;
 	}
@@ -288,21 +286,18 @@ static int sn_slot_disable(struct hotplug_slot *bss_hotplug_slot,
 	}
 
 	if ((action == PCI_REQ_SLOT_ELIGIBLE) && (rc == PCI_EMPTY_33MHZ)) {
-		dev_dbg(&slot->pci_bus->self->dev,
-			"Cannot remove last 33MHz card\n");
+		dev_dbg(&slot->pci_bus->self->dev, "Cannot remove last 33MHz card\n");
 		return -EPERM;
 	}
 
 	if ((action == PCI_REQ_SLOT_ELIGIBLE) && (rc == PCI_L1_ERR)) {
-		dev_dbg(&slot->pci_bus->self->dev,
-			"L1 failure %d with message \n%s\n",
+		dev_dbg(&slot->pci_bus->self->dev, "L1 failure %d with message \n%s\n",
 			resp.resp_sub_errno, resp.resp_l1_msg);
 		return -EPERM;
 	}
 
 	if ((action == PCI_REQ_SLOT_ELIGIBLE) && rc) {
-		dev_dbg(&slot->pci_bus->self->dev,
-			"remove failed with error %d sub-error %d\n",
+		dev_dbg(&slot->pci_bus->self->dev, "remove failed with error %d sub-error %d\n",
 			rc, resp.resp_sub_errno);
 		return -EIO;
 	}
@@ -417,8 +412,7 @@ static int enable_slot(struct hotplug_slot *bss_hotplug_slot)
 		phandle = acpi_device_handle(PCI_CONTROLLER(slot->pci_bus)->companion);
 
 		if (acpi_bus_get_device(phandle, &pdevice)) {
-			dev_dbg(&slot->pci_bus->self->dev,
-				"no parent device, assuming NULL\n");
+			dev_dbg(&slot->pci_bus->self->dev, "no parent device, assuming NULL\n");
 			pdevice = NULL;
 		}
 
@@ -447,10 +441,8 @@ static int enable_slot(struct hotplug_slot *bss_hotplug_slot)
 
 				ret = acpi_bus_scan(chandle);
 				if (ACPI_FAILURE(ret)) {
-					printk(KERN_ERR "%s: acpi_bus_scan "
-					       "failed (0x%x) for slot %d "
-					       "func %d\n", __func__,
-					       ret, (int)(adr>>16),
+					printk(KERN_ERR "%s: acpi_bus_scan failed (0x%x) for slot %d func %d\n",
+					       __func__, ret, (int)(adr>>16),
 					       (int)(adr&0xffff));
 					/* try to continue on */
 				}
@@ -471,11 +463,9 @@ static int enable_slot(struct hotplug_slot *bss_hotplug_slot)
 	mutex_unlock(&sn_hotplug_mutex);
 
 	if (rc == 0)
-		dev_dbg(&slot->pci_bus->self->dev,
-			"insert operation successful\n");
+		dev_dbg(&slot->pci_bus->self->dev, "insert operation successful\n");
 	else
-		dev_dbg(&slot->pci_bus->self->dev,
-			"insert operation failed rc = %d\n", rc);
+		dev_dbg(&slot->pci_bus->self->dev, "insert operation failed rc = %d\n", rc);
 
 	return rc;
 }
@@ -561,8 +551,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
 		acpi_status ret;
 		ret = acpi_unload_table_id(ssdt_id);
 		if (ACPI_FAILURE(ret)) {
-			printk(KERN_ERR "%s: acpi_unload_table_id "
-			       "failed (0x%x) for id %d\n",
+			printk(KERN_ERR "%s: acpi_unload_table_id failed (0x%x) for id %d\n",
 			       __func__, ret, ssdt_id);
 			/* try to continue on */
 		}
diff --git a/drivers/pci/hotplug/shpchp.h b/drivers/pci/hotplug/shpchp.h
index 61529097464..5897d516427 100644
--- a/drivers/pci/hotplug/shpchp.h
+++ b/drivers/pci/hotplug/shpchp.h
@@ -180,7 +180,7 @@ int shpchp_configure_device(struct slot *p_slot);
 int shpchp_unconfigure_device(struct slot *p_slot);
 void cleanup_slots(struct controller *ctrl);
 void shpchp_queue_pushbutton_work(struct work_struct *work);
-int shpc_init( struct controller *ctrl, struct pci_dev *pdev);
+int shpc_init(struct controller *ctrl, struct pci_dev *pdev);
 
 static inline const char *slot_name(struct slot *slot)
 {
@@ -295,7 +295,7 @@ static inline void amd_pogo_errata_restore_misc_reg(struct slot *p_slot)
 		pci_write_config_dword(p_slot->ctrl->pci_dev, PCIX_MEM_BASE_LIMIT_OFFSET, rse_set);
 	}
 	/* restore MiscII register */
-	pci_read_config_dword( p_slot->ctrl->pci_dev, PCIX_MISCII_OFFSET, &pcix_misc2_temp );
+	pci_read_config_dword(p_slot->ctrl->pci_dev, PCIX_MISCII_OFFSET, &pcix_misc2_temp );
 
 	if (p_slot->ctrl->pcix_misc2_reg & SERRFATALENABLE_MASK)
 		pcix_misc2_temp |= SERRFATALENABLE_MASK;
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index faf13abd5b9..294ef4b10cf 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -143,8 +143,7 @@ static int init_slots(struct controller *ctrl)
 		snprintf(name, SLOT_NAME_SIZE, "%d", slot->number);
 		hotplug_slot->ops = &shpchp_hotplug_slot_ops;
 
-		ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:%02x "
-			 "hp_slot=%x sun=%x slot_device_offset=%x\n",
+		ctrl_dbg(ctrl, "Registering domain:bus:dev=%04x:%02x:%02x hp_slot=%x sun=%x slot_device_offset=%x\n",
 			 pci_domain_nr(ctrl->pci_dev->subordinate),
 			 slot->bus, slot->device, slot->hp_slot, slot->number,
 			 ctrl->slot_device_offset);
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index 6efc2ec5e4d..a81fb67ea9a 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -162,7 +162,7 @@ u8 shpchp_handle_power_fault(u8 hp_slot, struct controller *ctrl)
 
 	p_slot = shpchp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
 
-	if ( !(p_slot->hpc_ops->query_power_fault(p_slot))) {
+	if (!(p_slot->hpc_ops->query_power_fault(p_slot))) {
 		/*
 		 * Power fault Cleared
 		 */
@@ -196,8 +196,8 @@ static int change_bus_speed(struct controller *ctrl, struct slot *p_slot,
 
 	ctrl_dbg(ctrl, "Change speed to %d\n", speed);
 	if ((rc = p_slot->hpc_ops->set_bus_speed_mode(p_slot, speed))) {
-		ctrl_err(ctrl, "%s: Issue of set bus speed mode command "
-			 "failed\n", __func__);
+		ctrl_err(ctrl, "%s: Issue of set bus speed mode command failed\n",
+			 __func__);
 		return WRONG_BUS_FREQUENCY;
 	}
 	return rc;
@@ -215,8 +215,8 @@ static int fix_bus_speed(struct controller *ctrl, struct slot *pslot,
 	 */
 	if (flag) {
 		if (asp < bsp) {
-			ctrl_err(ctrl, "Speed of bus %x and adapter %x "
-				 "mismatch\n", bsp, asp);
+			ctrl_err(ctrl, "Speed of bus %x and adapter %x mismatch\n",
+				 bsp, asp);
 			rc = WRONG_BUS_FREQUENCY;
 		}
 		return rc;
@@ -250,8 +250,7 @@ static int board_added(struct slot *p_slot)
 
 	hp_slot = p_slot->device - ctrl->slot_device_offset;
 
-	ctrl_dbg(ctrl,
-		 "%s: p_slot->device, slot_offset, hp_slot = %d, %d ,%d\n",
+	ctrl_dbg(ctrl, "%s: p_slot->device, slot_offset, hp_slot = %d, %d ,%d\n",
 		 __func__, p_slot->device, ctrl->slot_device_offset, hp_slot);
 
 	/* Power on slot without connecting to bus */
@@ -263,8 +262,8 @@ static int board_added(struct slot *p_slot)
 
 	if ((ctrl->pci_dev->vendor == 0x8086) && (ctrl->pci_dev->device == 0x0332)) {
 		if ((rc = p_slot->hpc_ops->set_bus_speed_mode(p_slot, PCI_SPEED_33MHz))) {
-			ctrl_err(ctrl, "%s: Issue of set bus speed mode command"
-				 " failed\n", __func__);
+			ctrl_err(ctrl, "%s: Issue of set bus speed mode command failed\n",
+				 __func__);
 			return WRONG_BUS_FREQUENCY;
 		}
 
@@ -277,8 +276,7 @@ static int board_added(struct slot *p_slot)
 
 	rc = p_slot->hpc_ops->get_adapter_speed(p_slot, &asp);
 	if (rc) {
-		ctrl_err(ctrl, "Can't get adapter speed or "
-			 "bus mode mismatch\n");
+		ctrl_err(ctrl, "Can't get adapter speed or bus mode mismatch\n");
 		return WRONG_BUS_FREQUENCY;
 	}
 
@@ -289,8 +287,8 @@ static int board_added(struct slot *p_slot)
 	if (!list_empty(&ctrl->pci_dev->subordinate->devices))
 		slots_not_empty = 1;
 
-	ctrl_dbg(ctrl, "%s: slots_not_empty %d, adapter_speed %d, bus_speed %d,"
-		 " max_bus_speed %d\n", __func__, slots_not_empty, asp,
+	ctrl_dbg(ctrl, "%s: slots_not_empty %d, adapter_speed %d, bus_speed %d, max_bus_speed %d\n",
+		 __func__, slots_not_empty, asp,
 		 bsp, msp);
 
 	rc = fix_bus_speed(ctrl, p_slot, slots_not_empty, asp, bsp, msp);
@@ -490,12 +488,12 @@ static void handle_button_press_event(struct slot *p_slot)
 		p_slot->hpc_ops->get_power_status(p_slot, &getstatus);
 		if (getstatus) {
 			p_slot->state = BLINKINGOFF_STATE;
-			ctrl_info(ctrl, "PCI slot #%s - powering off due to "
-				  "button press.\n", slot_name(p_slot));
+			ctrl_info(ctrl, "PCI slot #%s - powering off due to button press\n",
+				  slot_name(p_slot));
 		} else {
 			p_slot->state = BLINKINGON_STATE;
-			ctrl_info(ctrl, "PCI slot #%s - powering on due to "
-				  "button press.\n", slot_name(p_slot));
+			ctrl_info(ctrl, "PCI slot #%s - powering on due to button press\n",
+				  slot_name(p_slot));
 		}
 		/* blink green LED and turn off amber */
 		p_slot->hpc_ops->green_led_blink(p_slot);
@@ -518,8 +516,8 @@ static void handle_button_press_event(struct slot *p_slot)
 		else
 			p_slot->hpc_ops->green_led_off(p_slot);
 		p_slot->hpc_ops->set_attention_status(p_slot, 0);
-		ctrl_info(ctrl, "PCI slot #%s - action canceled due to "
-			  "button press\n", slot_name(p_slot));
+		ctrl_info(ctrl, "PCI slot #%s - action canceled due to button press\n",
+			  slot_name(p_slot));
 		p_slot->state = STATIC_STATE;
 		break;
 	case POWEROFF_STATE:
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
index 2d7f474ca0e..29e22352822 100644
--- a/drivers/pci/hotplug/shpchp_hpc.c
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -341,8 +341,7 @@ static int shpc_write_cmd(struct slot *slot, u8 t_slot, u8 cmd)
 
 	cmd_status = hpc_check_cmd_status(slot->ctrl);
 	if (cmd_status) {
-		ctrl_err(ctrl,
-			 "Failed to issued command 0x%x (error code = %d)\n",
+		ctrl_err(ctrl, "Failed to issued command 0x%x (error code = %d)\n",
 			 cmd, cmd_status);
 		retval = -EIO;
 	}
@@ -404,7 +403,7 @@ static int hpc_get_attention_status(struct slot *slot, u8 *status)
 	return 0;
 }
 
-static int hpc_get_power_status(struct slot * slot, u8 *status)
+static int hpc_get_power_status(struct slot *slot, u8 *status)
 {
 	struct controller *ctrl = slot->ctrl;
 	u32 slot_reg = shpc_readl(ctrl, SLOT_REG(slot->hp_slot));
@@ -528,7 +527,7 @@ static int hpc_get_mode1_ECC_cap(struct slot *slot, u8 *mode)
 	return retval;
 }
 
-static int hpc_query_power_fault(struct slot * slot)
+static int hpc_query_power_fault(struct slot *slot)
 {
 	struct controller *ctrl = slot->ctrl;
 	u32 slot_reg = shpc_readl(ctrl, SLOT_REG(slot->hp_slot));
@@ -614,7 +613,7 @@ static void hpc_release_ctlr(struct controller *ctrl)
 	release_mem_region(ctrl->mmio_base, ctrl->mmio_size);
 }
 
-static int hpc_power_on_slot(struct slot * slot)
+static int hpc_power_on_slot(struct slot *slot)
 {
 	int retval;
 
@@ -625,7 +624,7 @@ static int hpc_power_on_slot(struct slot * slot)
 	return retval;
 }
 
-static int hpc_slot_enable(struct slot * slot)
+static int hpc_slot_enable(struct slot *slot)
 {
 	int retval;
 
@@ -638,7 +637,7 @@ static int hpc_slot_enable(struct slot * slot)
 	return retval;
 }
 
-static int hpc_slot_disable(struct slot * slot)
+static int hpc_slot_disable(struct slot *slot)
 {
 	int retval;
 
@@ -720,7 +719,7 @@ static int shpc_get_cur_bus_speed(struct controller *ctrl)
 }
 
 
-static int hpc_set_bus_speed_mode(struct slot * slot, enum pci_bus_speed value)
+static int hpc_set_bus_speed_mode(struct slot *slot, enum pci_bus_speed value)
 {
 	int retval;
 	struct controller *ctrl = slot->ctrl;
@@ -974,8 +973,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
 		for (i = 0; i < 9 + num_slots; i++) {
 			rc = shpc_indirect_read(ctrl, i, &tempdword);
 			if (rc) {
-				ctrl_err(ctrl,
-					 "Cannot read creg (index = %d)\n", i);
+				ctrl_err(ctrl, "Cannot read creg (index = %d)\n",
+					 i);
 				goto abort;
 			}
 			ctrl_dbg(ctrl, " offset %d: value %x\n", i, tempdword);
@@ -1060,10 +1059,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
 		/* Installs the interrupt handler */
 		rc = pci_enable_msi(pdev);
 		if (rc) {
-			ctrl_info(ctrl,
-				  "Can't get msi for the hotplug controller\n");
-			ctrl_info(ctrl,
-				  "Use INTx for the hotplug controller\n");
+			ctrl_info(ctrl, "Can't get msi for the hotplug controller\n");
+			ctrl_info(ctrl, "Use INTx for the hotplug controller\n");
 		}
 
 		rc = request_irq(ctrl->pci_dev->irq, shpc_isr, IRQF_SHARED,
@@ -1071,8 +1068,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
 		ctrl_dbg(ctrl, "request_irq %d (returns %d)\n",
 			 ctrl->pci_dev->irq, rc);
 		if (rc) {
-			ctrl_err(ctrl, "Can't get irq %d for the hotplug "
-				 "controller\n", ctrl->pci_dev->irq);
+			ctrl_err(ctrl, "Can't get irq %d for the hotplug controller\n",
+				 ctrl->pci_dev->irq);
 			goto abort_iounmap;
 		}
 	}
diff --git a/drivers/pci/hotplug/shpchp_pci.c b/drivers/pci/hotplug/shpchp_pci.c
index 9202d133485..469454e0cc4 100644
--- a/drivers/pci/hotplug/shpchp_pci.c
+++ b/drivers/pci/hotplug/shpchp_pci.c
@@ -46,9 +46,9 @@ int shpchp_configure_device(struct slot *p_slot)
 
 	dev = pci_get_slot(parent, PCI_DEVFN(p_slot->device, 0));
 	if (dev) {
-		ctrl_err(ctrl, "Device %s already exists "
-			 "at %04x:%02x:%02x, cannot hot-add\n", pci_name(dev),
-			 pci_domain_nr(parent), p_slot->bus, p_slot->device);
+		ctrl_err(ctrl, "Device %s already exists at %04x:%02x:%02x, cannot hot-add\n",
+			 pci_name(dev), pci_domain_nr(parent),
+			 p_slot->bus, p_slot->device);
 		pci_dev_put(dev);
 		ret = -EINVAL;
 		goto out;
diff --git a/drivers/pci/hotplug/shpchp_sysfs.c b/drivers/pci/hotplug/shpchp_sysfs.c
index e8c31fe2056..52875b36046 100644
--- a/drivers/pci/hotplug/shpchp_sysfs.c
+++ b/drivers/pci/hotplug/shpchp_sysfs.c
@@ -38,7 +38,7 @@
 static ssize_t show_ctrl (struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pdev;
-	char * out = buf;
+	char *out = buf;
 	int index, busnr;
 	struct resource *res;
 	struct pci_bus *bus;
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index d68b030ab53..a94dd2c4183 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -102,7 +102,7 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	spin_unlock_irqrestore(&ht_irq_lock, flags);
 
 	max_irq = (data >> 16) & 0xff;
-	if ( idx > max_irq)
+	if (idx > max_irq)
 		return -EINVAL;
 
 	cfg = kmalloc(sizeof(*cfg), GFP_KERNEL);
@@ -131,6 +131,7 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 
 	return irq;
 }
+EXPORT_SYMBOL(__ht_create_irq);
 
 /**
  * ht_create_irq - create an irq and attach it to a device.
@@ -146,6 +147,7 @@ int ht_create_irq(struct pci_dev *dev, int idx)
 {
 	return __ht_create_irq(dev, idx, NULL);
 }
+EXPORT_SYMBOL(ht_create_irq);
 
 /**
  * ht_destroy_irq - destroy an irq created with ht_create_irq
@@ -165,7 +167,4 @@ void ht_destroy_irq(unsigned int irq)
 
 	kfree(cfg);
 }
-
-EXPORT_SYMBOL(__ht_create_irq);
-EXPORT_SYMBOL(ht_create_irq);
 EXPORT_SYMBOL(ht_destroy_irq);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 27a7e67ddfe..5a40516444f 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -149,15 +149,14 @@ static void msi_set_enable(struct pci_dev *dev, int enable)
 	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
 }
 
-static void msix_set_enable(struct pci_dev *dev, int enable)
+static void msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set)
 {
-	u16 control;
+	u16 ctrl;
 
-	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
-	control &= ~PCI_MSIX_FLAGS_ENABLE;
-	if (enable)
-		control |= PCI_MSIX_FLAGS_ENABLE;
-	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, control);
+	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
+	ctrl &= ~clear;
+	ctrl |= set;
+	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl);
 }
 
 static inline __attribute_const__ u32 msi_mask(unsigned x)
@@ -168,16 +167,6 @@ static inline __attribute_const__ u32 msi_mask(unsigned x)
 	return (1 << (1 << x)) - 1;
 }
 
-static inline __attribute_const__ u32 msi_capable_mask(u16 control)
-{
-	return msi_mask((control >> 1) & 7);
-}
-
-static inline __attribute_const__ u32 msi_enabled_mask(u16 control)
-{
-	return msi_mask((control >> 4) & 7);
-}
-
 /*
  * PCI 2.3 does not specify mask bits for each MSI interrupt.  Attempting to
  * mask all MSI interrupts by clearing the MSI enable bit does not work
@@ -246,7 +235,7 @@ static void msi_set_mask_bit(struct irq_data *data, u32 flag)
 		msix_mask_irq(desc, flag);
 		readl(desc->mask_base);		/* Flush write to device */
 	} else {
-		unsigned offset = data->irq - desc->dev->irq;
+		unsigned offset = data->irq - desc->irq;
 		msi_mask_irq(desc, 1 << offset, flag << offset);
 	}
 }
@@ -413,7 +402,7 @@ static void free_msi_irqs(struct pci_dev *dev)
 	if (dev->msi_irq_groups) {
 		sysfs_remove_groups(&dev->dev.kobj, dev->msi_irq_groups);
 		msi_attrs = dev->msi_irq_groups[0]->attrs;
-		list_for_each_entry(entry, &dev->msi_list, list) {
+		while (msi_attrs[count]) {
 			dev_attr = container_of(msi_attrs[count],
 						struct device_attribute, attr);
 			kfree(dev_attr->attr.name);
@@ -460,7 +449,8 @@ static void __pci_restore_msi_state(struct pci_dev *dev)
 	arch_restore_msi_irqs(dev);
 
 	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
-	msi_mask_irq(entry, msi_capable_mask(control), entry->masked);
+	msi_mask_irq(entry, msi_mask(entry->msi_attrib.multi_cap),
+		     entry->masked);
 	control &= ~PCI_MSI_FLAGS_QSIZE;
 	control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
 	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
@@ -469,26 +459,22 @@ static void __pci_restore_msi_state(struct pci_dev *dev)
 static void __pci_restore_msix_state(struct pci_dev *dev)
 {
 	struct msi_desc *entry;
-	u16 control;
 
 	if (!dev->msix_enabled)
 		return;
 	BUG_ON(list_empty(&dev->msi_list));
-	entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
-	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
 
 	/* route the table */
 	pci_intx_for_msi(dev, 0);
-	control |= PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL;
-	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, control);
+	msix_clear_and_set_ctrl(dev, 0,
+				PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL);
 
 	arch_restore_msi_irqs(dev);
 	list_for_each_entry(entry, &dev->msi_list, list) {
 		msix_mask_irq(entry, entry->masked);
 	}
 
-	control &= ~PCI_MSIX_FLAGS_MASKALL;
-	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, control);
+	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 }
 
 void pci_restore_msi_state(struct pci_dev *dev)
@@ -501,7 +487,6 @@ EXPORT_SYMBOL_GPL(pci_restore_msi_state);
 static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
 	struct msi_desc *entry;
 	unsigned long irq;
 	int retval;
@@ -510,12 +495,11 @@ static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr,
 	if (retval)
 		return retval;
 
-	list_for_each_entry(entry, &pdev->msi_list, list) {
-		if (entry->irq == irq) {
-			return sprintf(buf, "%s\n",
-				       entry->msi_attrib.is_msix ? "msix" : "msi");
-		}
-	}
+	entry = irq_get_msi_desc(irq);
+	if (entry)
+		return sprintf(buf, "%s\n",
+				entry->msi_attrib.is_msix ? "msix" : "msi");
+
 	return -ENODEV;
 }
 
@@ -594,6 +578,38 @@ error_attrs:
 	return ret;
 }
 
+static struct msi_desc *msi_setup_entry(struct pci_dev *dev)
+{
+	u16 control;
+	struct msi_desc *entry;
+
+	/* MSI Entry Initialization */
+	entry = alloc_msi_entry(dev);
+	if (!entry)
+		return NULL;
+
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
+
+	entry->msi_attrib.is_msix	= 0;
+	entry->msi_attrib.is_64		= !!(control & PCI_MSI_FLAGS_64BIT);
+	entry->msi_attrib.entry_nr	= 0;
+	entry->msi_attrib.maskbit	= !!(control & PCI_MSI_FLAGS_MASKBIT);
+	entry->msi_attrib.default_irq	= dev->irq;	/* Save IOAPIC IRQ */
+	entry->msi_attrib.pos		= dev->msi_cap;
+	entry->msi_attrib.multi_cap	= (control & PCI_MSI_FLAGS_QMASK) >> 1;
+
+	if (control & PCI_MSI_FLAGS_64BIT)
+		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
+	else
+		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_32;
+
+	/* Save the initial mask status */
+	if (entry->msi_attrib.maskbit)
+		pci_read_config_dword(dev, entry->mask_pos, &entry->masked);
+
+	return entry;
+}
+
 /**
  * msi_capability_init - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
@@ -609,32 +625,16 @@ static int msi_capability_init(struct pci_dev *dev, int nvec)
 {
 	struct msi_desc *entry;
 	int ret;
-	u16 control;
 	unsigned mask;
 
 	msi_set_enable(dev, 0);	/* Disable MSI during set up */
 
-	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
-	/* MSI Entry Initialization */
-	entry = alloc_msi_entry(dev);
+	entry = msi_setup_entry(dev);
 	if (!entry)
 		return -ENOMEM;
 
-	entry->msi_attrib.is_msix	= 0;
-	entry->msi_attrib.is_64		= !!(control & PCI_MSI_FLAGS_64BIT);
-	entry->msi_attrib.entry_nr	= 0;
-	entry->msi_attrib.maskbit	= !!(control & PCI_MSI_FLAGS_MASKBIT);
-	entry->msi_attrib.default_irq	= dev->irq;	/* Save IOAPIC IRQ */
-	entry->msi_attrib.pos		= dev->msi_cap;
-
-	if (control & PCI_MSI_FLAGS_64BIT)
-		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
-	else
-		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_32;
 	/* All MSIs are unmasked by default, Mask them all */
-	if (entry->msi_attrib.maskbit)
-		pci_read_config_dword(dev, entry->mask_pos, &entry->masked);
-	mask = msi_capable_mask(control);
+	mask = msi_mask(entry->msi_attrib.multi_cap);
 	msi_mask_irq(entry, mask, mask);
 
 	list_add_tail(&entry->list, &dev->msi_list);
@@ -743,12 +743,10 @@ static int msix_capability_init(struct pci_dev *dev,
 	u16 control;
 	void __iomem *base;
 
-	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
-
 	/* Ensure MSI-X is disabled while it is set up */
-	control &= ~PCI_MSIX_FLAGS_ENABLE;
-	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, control);
+	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
 
+	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
 	/* Request & Map MSI-X table region */
 	base = msix_map_region(dev, msix_table_size(control));
 	if (!base)
@@ -767,8 +765,8 @@ static int msix_capability_init(struct pci_dev *dev,
 	 * MSI-X registers.  We need to mask all the vectors to prevent
 	 * interrupts coming in before they're fully set up.
 	 */
-	control |= PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE;
-	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, control);
+	msix_clear_and_set_ctrl(dev, 0,
+				PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE);
 
 	msix_program_entries(dev, entries);
 
@@ -780,8 +778,7 @@ static int msix_capability_init(struct pci_dev *dev,
 	pci_intx_for_msi(dev, 0);
 	dev->msix_enabled = 1;
 
-	control &= ~PCI_MSIX_FLAGS_MASKALL;
-	pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, control);
+	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 
 	return 0;
 
@@ -882,7 +879,6 @@ void pci_msi_shutdown(struct pci_dev *dev)
 {
 	struct msi_desc *desc;
 	u32 mask;
-	u16 ctrl;
 
 	if (!pci_msi_enable || !dev || !dev->msi_enabled)
 		return;
@@ -895,8 +891,7 @@ void pci_msi_shutdown(struct pci_dev *dev)
 	dev->msi_enabled = 0;
 
 	/* Return the device with MSI unmasked as initial states */
-	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &ctrl);
-	mask = msi_capable_mask(ctrl);
+	mask = msi_mask(desc->msi_attrib.multi_cap);
 	/* Keep cached state to be restored */
 	arch_msi_mask_irq(desc, mask, ~mask);
 
@@ -980,8 +975,7 @@ int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
 
 	/* Check whether driver already requested for MSI irq */
 	if (dev->msi_enabled) {
-		dev_info(&dev->dev, "can't enable MSI-X "
-		       "(MSI IRQ already assigned)\n");
+		dev_info(&dev->dev, "can't enable MSI-X (MSI IRQ already assigned)\n");
 		return -EINVAL;
 	}
 	status = msix_capability_init(dev, entries, nvec);
@@ -1002,7 +996,7 @@ void pci_msix_shutdown(struct pci_dev *dev)
 		arch_msix_mask_irq(entry, 1);
 	}
 
-	msix_set_enable(dev, 0);
+	msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
 	pci_intx_for_msi(dev, 1);
 	dev->msix_enabled = 0;
 }
@@ -1017,24 +1011,6 @@ void pci_disable_msix(struct pci_dev *dev)
 }
 EXPORT_SYMBOL(pci_disable_msix);
 
-/**
- * msi_remove_pci_irq_vectors - reclaim MSI(X) irqs to unused state
- * @dev: pointer to the pci_dev data structure of MSI(X) device function
- *
- * Being called during hotplug remove, from which the device function
- * is hot-removed. All previous assigned MSI/MSI-X irqs, if
- * allocated for this device function, are reclaimed to unused state,
- * which may be used later on.
- **/
-void msi_remove_pci_irq_vectors(struct pci_dev *dev)
-{
-	if (!pci_msi_enable || !dev)
-		return;
-
-	if (dev->msi_enabled || dev->msix_enabled)
-		free_msi_irqs(dev);
-}
-
 void pci_no_msi(void)
 {
 	pci_msi_enable = 0;
@@ -1066,7 +1042,7 @@ void pci_msi_init_pci_dev(struct pci_dev *dev)
 
 	dev->msix_cap = pci_find_capability(dev, PCI_CAP_ID_MSIX);
 	if (dev->msix_cap)
-		msix_set_enable(dev, 0);
+		msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
 }
 
 /**
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 837d71f5390..3f8e3dbcaa7 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -77,6 +77,7 @@ int pci_add_dynid(struct pci_driver *drv,
 
 	return retval;
 }
+EXPORT_SYMBOL_GPL(pci_add_dynid);
 
 static void pci_free_dynids(struct pci_driver *drv)
 {
@@ -98,15 +99,15 @@ static void pci_free_dynids(struct pci_driver *drv)
  *
  * Allow PCI IDs to be added to an existing driver via sysfs.
  */
-static ssize_t
-store_new_id(struct device_driver *driver, const char *buf, size_t count)
+static ssize_t store_new_id(struct device_driver *driver, const char *buf,
+			    size_t count)
 {
 	struct pci_driver *pdrv = to_pci_driver(driver);
 	const struct pci_device_id *ids = pdrv->id_table;
-	__u32 vendor, device, subvendor=PCI_ANY_ID,
-		subdevice=PCI_ANY_ID, class=0, class_mask=0;
-	unsigned long driver_data=0;
-	int fields=0;
+	__u32 vendor, device, subvendor = PCI_ANY_ID,
+		subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
+	unsigned long driver_data = 0;
+	int fields = 0;
 	int retval = 0;
 
 	fields = sscanf(buf, "%x %x %x %x %x %x %lx",
@@ -166,8 +167,8 @@ static DRIVER_ATTR(new_id, S_IWUSR, NULL, store_new_id);
  *
  * Removes a dynamic pci device ID to this driver.
  */
-static ssize_t
-store_remove_id(struct device_driver *driver, const char *buf, size_t count)
+static ssize_t store_remove_id(struct device_driver *driver, const char *buf,
+			       size_t count)
 {
 	struct pci_dynid *dynid, *n;
 	struct pci_driver *pdrv = to_pci_driver(driver);
@@ -235,6 +236,7 @@ const struct pci_device_id *pci_match_id(const struct pci_device_id *ids,
 	}
 	return NULL;
 }
+EXPORT_SYMBOL(pci_match_id);
 
 static const struct pci_device_id pci_device_id_any = {
 	.vendor = PCI_ANY_ID,
@@ -372,8 +374,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
  * returns 0 on success, else error.
  * side-effect: pci_dev->driver is set to drv when drv claims pci_dev.
  */
-static int
-__pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev)
+static int __pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev)
 {
 	const struct pci_device_id *id;
 	int error = 0;
@@ -390,7 +391,7 @@ __pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev)
 	return error;
 }
 
-static int pci_device_probe(struct device * dev)
+static int pci_device_probe(struct device *dev)
 {
 	int error = 0;
 	struct pci_driver *drv;
@@ -406,10 +407,10 @@ static int pci_device_probe(struct device * dev)
 	return error;
 }
 
-static int pci_device_remove(struct device * dev)
+static int pci_device_remove(struct device *dev)
 {
-	struct pci_dev * pci_dev = to_pci_dev(dev);
-	struct pci_driver * drv = pci_dev->driver;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct pci_driver *drv = pci_dev->driver;
 
 	if (drv) {
 		if (drv->remove) {
@@ -537,8 +538,8 @@ static int pci_pm_reenable_device(struct pci_dev *pci_dev)
 
 static int pci_legacy_suspend(struct device *dev, pm_message_t state)
 {
-	struct pci_dev * pci_dev = to_pci_dev(dev);
-	struct pci_driver * drv = pci_dev->driver;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct pci_driver *drv = pci_dev->driver;
 
 	if (drv && drv->suspend) {
 		pci_power_t prev = pci_dev->current_state;
@@ -564,8 +565,8 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state)
 
 static int pci_legacy_suspend_late(struct device *dev, pm_message_t state)
 {
-	struct pci_dev * pci_dev = to_pci_dev(dev);
-	struct pci_driver * drv = pci_dev->driver;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct pci_driver *drv = pci_dev->driver;
 
 	if (drv && drv->suspend_late) {
 		pci_power_t prev = pci_dev->current_state;
@@ -595,8 +596,8 @@ static int pci_legacy_suspend_late(struct device *dev, pm_message_t state)
 
 static int pci_legacy_resume_early(struct device *dev)
 {
-	struct pci_dev * pci_dev = to_pci_dev(dev);
-	struct pci_driver * drv = pci_dev->driver;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct pci_driver *drv = pci_dev->driver;
 
 	return drv && drv->resume_early ?
 			drv->resume_early(pci_dev) : 0;
@@ -604,8 +605,8 @@ static int pci_legacy_resume_early(struct device *dev)
 
 static int pci_legacy_resume(struct device *dev)
 {
-	struct pci_dev * pci_dev = to_pci_dev(dev);
-	struct pci_driver * drv = pci_dev->driver;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	struct pci_driver *drv = pci_dev->driver;
 
 	pci_fixup_device(pci_fixup_resume, pci_dev);
 
@@ -1255,6 +1256,7 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner,
 	/* register with core */
 	return driver_register(&drv->driver);
 }
+EXPORT_SYMBOL(__pci_register_driver);
 
 /**
  * pci_unregister_driver - unregister a pci driver
@@ -1266,12 +1268,12 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner,
  * driverless.
  */
 
-void
-pci_unregister_driver(struct pci_driver *drv)
+void pci_unregister_driver(struct pci_driver *drv)
 {
 	driver_unregister(&drv->driver);
 	pci_free_dynids(drv);
 }
+EXPORT_SYMBOL(pci_unregister_driver);
 
 static struct pci_driver pci_compat_driver = {
 	.name = "compat"
@@ -1284,19 +1286,19 @@ static struct pci_driver pci_compat_driver = {
  * Returns the appropriate pci_driver structure or %NULL if there is no
  * registered driver for the device.
  */
-struct pci_driver *
-pci_dev_driver(const struct pci_dev *dev)
+struct pci_driver *pci_dev_driver(const struct pci_dev *dev)
 {
 	if (dev->driver)
 		return dev->driver;
 	else {
 		int i;
-		for(i=0; i<=PCI_ROM_RESOURCE; i++)
+		for (i = 0; i <= PCI_ROM_RESOURCE; i++)
 			if (dev->resource[i].flags & IORESOURCE_BUSY)
 				return &pci_compat_driver;
 	}
 	return NULL;
 }
+EXPORT_SYMBOL(pci_dev_driver);
 
 /**
  * pci_bus_match - Tell if a PCI device structure has a matching PCI device id structure
@@ -1342,6 +1344,7 @@ struct pci_dev *pci_dev_get(struct pci_dev *dev)
 		get_device(&dev->dev);
 	return dev;
 }
+EXPORT_SYMBOL(pci_dev_get);
 
 /**
  * pci_dev_put - release a use of the pci device structure
@@ -1355,6 +1358,7 @@ void pci_dev_put(struct pci_dev *dev)
 	if (dev)
 		put_device(&dev->dev);
 }
+EXPORT_SYMBOL(pci_dev_put);
 
 static int pci_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
@@ -1400,19 +1404,10 @@ struct bus_type pci_bus_type = {
 	.drv_groups	= pci_drv_groups,
 	.pm		= PCI_PM_OPS_PTR,
 };
+EXPORT_SYMBOL(pci_bus_type);
 
 static int __init pci_driver_init(void)
 {
 	return bus_register(&pci_bus_type);
 }
-
 postcore_initcall(pci_driver_init);
-
-EXPORT_SYMBOL_GPL(pci_add_dynid);
-EXPORT_SYMBOL(pci_match_id);
-EXPORT_SYMBOL(__pci_register_driver);
-EXPORT_SYMBOL(pci_unregister_driver);
-EXPORT_SYMBOL(pci_dev_driver);
-EXPORT_SYMBOL(pci_bus_type);
-EXPORT_SYMBOL(pci_dev_get);
-EXPORT_SYMBOL(pci_dev_put);
diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
index 45113daaa77..2ab1b47c765 100644
--- a/drivers/pci/pci-label.c
+++ b/drivers/pci/pci-label.c
@@ -40,9 +40,8 @@ enum smbios_attr_enum {
 	SMBIOS_ATTR_INSTANCE_SHOW,
 };
 
-static size_t
-find_smbios_instance_string(struct pci_dev *pdev, char *buf,
-			    enum smbios_attr_enum attribute)
+static size_t find_smbios_instance_string(struct pci_dev *pdev, char *buf,
+					  enum smbios_attr_enum attribute)
 {
 	const struct dmi_device *dmi;
 	struct dmi_dev_onboard *donboard;
@@ -74,9 +73,8 @@ find_smbios_instance_string(struct pci_dev *pdev, char *buf,
 	return 0;
 }
 
-static umode_t
-smbios_instance_string_exist(struct kobject *kobj, struct attribute *attr,
-			     int n)
+static umode_t smbios_instance_string_exist(struct kobject *kobj,
+					    struct attribute *attr, int n)
 {
 	struct device *dev;
 	struct pci_dev *pdev;
@@ -88,8 +86,8 @@ smbios_instance_string_exist(struct kobject *kobj, struct attribute *attr,
 					   S_IRUGO : 0;
 }
 
-static ssize_t
-smbioslabel_show(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t smbioslabel_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pdev;
 	pdev = to_pci_dev(dev);
@@ -98,9 +96,8 @@ smbioslabel_show(struct device *dev, struct device_attribute *attr, char *buf)
 					   SMBIOS_ATTR_LABEL_SHOW);
 }
 
-static ssize_t
-smbiosinstance_show(struct device *dev,
-		    struct device_attribute *attr, char *buf)
+static ssize_t smbiosinstance_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pdev;
 	pdev = to_pci_dev(dev);
@@ -130,26 +127,22 @@ static struct attribute_group smbios_attr_group = {
 	.is_visible = smbios_instance_string_exist,
 };
 
-static int
-pci_create_smbiosname_file(struct pci_dev *pdev)
+static int pci_create_smbiosname_file(struct pci_dev *pdev)
 {
 	return sysfs_create_group(&pdev->dev.kobj, &smbios_attr_group);
 }
 
-static void
-pci_remove_smbiosname_file(struct pci_dev *pdev)
+static void pci_remove_smbiosname_file(struct pci_dev *pdev)
 {
 	sysfs_remove_group(&pdev->dev.kobj, &smbios_attr_group);
 }
 #else
-static inline int
-pci_create_smbiosname_file(struct pci_dev *pdev)
+static inline int pci_create_smbiosname_file(struct pci_dev *pdev)
 {
 	return -1;
 }
 
-static inline void
-pci_remove_smbiosname_file(struct pci_dev *pdev)
+static inline void pci_remove_smbiosname_file(struct pci_dev *pdev)
 {
 }
 #endif
@@ -168,15 +161,15 @@ enum acpi_attr_enum {
 static void dsm_label_utf16s_to_utf8s(union acpi_object *obj, char *buf)
 {
 	int len;
-	len = utf16s_to_utf8s((const wchar_t *)obj->string.pointer,
-			      obj->string.length,
+	len = utf16s_to_utf8s((const wchar_t *)obj->buffer.pointer,
+			      obj->buffer.length,
 			      UTF16_LITTLE_ENDIAN,
 			      buf, PAGE_SIZE);
 	buf[len] = '\n';
 }
 
-static int
-dsm_get_label(struct device *dev, char *buf, enum acpi_attr_enum attr)
+static int dsm_get_label(struct device *dev, char *buf,
+			 enum acpi_attr_enum attr)
 {
 	acpi_handle handle;
 	union acpi_object *obj, *tmp;
@@ -194,16 +187,22 @@ dsm_get_label(struct device *dev, char *buf, enum acpi_attr_enum attr)
 	tmp = obj->package.elements;
 	if (obj->type == ACPI_TYPE_PACKAGE && obj->package.count == 2 &&
 	    tmp[0].type == ACPI_TYPE_INTEGER &&
-	    tmp[1].type == ACPI_TYPE_STRING) {
+	    (tmp[1].type == ACPI_TYPE_STRING ||
+	     tmp[1].type == ACPI_TYPE_BUFFER)) {
 		/*
 		 * The second string element is optional even when
 		 * this _DSM is implemented; when not implemented,
 		 * this entry must return a null string.
 		 */
-		if (attr == ACPI_ATTR_INDEX_SHOW)
+		if (attr == ACPI_ATTR_INDEX_SHOW) {
 			scnprintf(buf, PAGE_SIZE, "%llu\n", tmp->integer.value);
-		else if (attr == ACPI_ATTR_LABEL_SHOW)
-			dsm_label_utf16s_to_utf8s(tmp + 1, buf);
+		} else if (attr == ACPI_ATTR_LABEL_SHOW) {
+			if (tmp[1].type == ACPI_TYPE_STRING)
+				scnprintf(buf, PAGE_SIZE, "%s\n",
+					  tmp[1].string.pointer);
+			else if (tmp[1].type == ACPI_TYPE_BUFFER)
+				dsm_label_utf16s_to_utf8s(tmp + 1, buf);
+		}
 		len = strlen(buf) > 0 ? strlen(buf) : -1;
 	}
 
@@ -212,8 +211,7 @@ dsm_get_label(struct device *dev, char *buf, enum acpi_attr_enum attr)
 	return len;
 }
 
-static bool
-device_has_dsm(struct device *dev)
+static bool device_has_dsm(struct device *dev)
 {
 	acpi_handle handle;
 
@@ -225,8 +223,8 @@ device_has_dsm(struct device *dev)
 				1 << DEVICE_LABEL_DSM);
 }
 
-static umode_t
-acpi_index_string_exist(struct kobject *kobj, struct attribute *attr, int n)
+static umode_t acpi_index_string_exist(struct kobject *kobj,
+				       struct attribute *attr, int n)
 {
 	struct device *dev;
 
@@ -238,14 +236,14 @@ acpi_index_string_exist(struct kobject *kobj, struct attribute *attr, int n)
 	return 0;
 }
 
-static ssize_t
-acpilabel_show(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t acpilabel_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	return dsm_get_label(dev, buf, ACPI_ATTR_LABEL_SHOW);
 }
 
-static ssize_t
-acpiindex_show(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t acpiindex_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	return dsm_get_label(dev, buf, ACPI_ATTR_INDEX_SHOW);
 }
@@ -271,33 +269,28 @@ static struct attribute_group acpi_attr_group = {
 	.is_visible = acpi_index_string_exist,
 };
 
-static int
-pci_create_acpi_index_label_files(struct pci_dev *pdev)
+static int pci_create_acpi_index_label_files(struct pci_dev *pdev)
 {
 	return sysfs_create_group(&pdev->dev.kobj, &acpi_attr_group);
 }
 
-static int
-pci_remove_acpi_index_label_files(struct pci_dev *pdev)
+static int pci_remove_acpi_index_label_files(struct pci_dev *pdev)
 {
 	sysfs_remove_group(&pdev->dev.kobj, &acpi_attr_group);
 	return 0;
 }
 #else
-static inline int
-pci_create_acpi_index_label_files(struct pci_dev *pdev)
+static inline int pci_create_acpi_index_label_files(struct pci_dev *pdev)
 {
 	return -1;
 }
 
-static inline int
-pci_remove_acpi_index_label_files(struct pci_dev *pdev)
+static inline int pci_remove_acpi_index_label_files(struct pci_dev *pdev)
 {
 	return -1;
 }
 
-static inline bool
-device_has_dsm(struct device *dev)
+static inline bool device_has_dsm(struct device *dev)
 {
 	return false;
 }
diff --git a/drivers/pci/pci-stub.c b/drivers/pci/pci-stub.c
index 2ff77509d8e..886fb357027 100644
--- a/drivers/pci/pci-stub.c
+++ b/drivers/pci/pci-stub.c
@@ -55,7 +55,7 @@ static int __init pci_stub_init(void)
 	p = ids;
 	while ((id = strsep(&p, ","))) {
 		unsigned int vendor, device, subvendor = PCI_ANY_ID,
-			subdevice = PCI_ANY_ID, class=0, class_mask=0;
+			subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
 		int fields;
 
 		if (!strlen(id))
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 84c350994b0..9ff0a901ecf 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -41,8 +41,8 @@ field##_show(struct device *dev, struct device_attribute *attr, char *buf)				\
 {									\
 	struct pci_dev *pdev;						\
 									\
-	pdev = to_pci_dev (dev);					\
-	return sprintf (buf, format_string, pdev->field);		\
+	pdev = to_pci_dev(dev);						\
+	return sprintf(buf, format_string, pdev->field);		\
 }									\
 static DEVICE_ATTR_RO(field)
 
@@ -58,7 +58,7 @@ static ssize_t broken_parity_status_show(struct device *dev,
 					 char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	return sprintf (buf, "%u\n", pdev->broken_parity_status);
+	return sprintf(buf, "%u\n", pdev->broken_parity_status);
 }
 
 static ssize_t broken_parity_status_store(struct device *dev,
@@ -77,10 +77,8 @@ static ssize_t broken_parity_status_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(broken_parity_status);
 
-static ssize_t pci_dev_show_local_cpu(struct device *dev,
-		int type,
-		struct device_attribute *attr,
-		char *buf)
+static ssize_t pci_dev_show_local_cpu(struct device *dev, int type,
+				      struct device_attribute *attr, char *buf)
 {
 	const struct cpumask *mask;
 	int len;
@@ -101,14 +99,14 @@ static ssize_t pci_dev_show_local_cpu(struct device *dev,
 }
 
 static ssize_t local_cpus_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
+			       struct device_attribute *attr, char *buf)
 {
 	return pci_dev_show_local_cpu(dev, 1, attr, buf);
 }
 static DEVICE_ATTR_RO(local_cpus);
 
 static ssize_t local_cpulist_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
+				  struct device_attribute *attr, char *buf)
 {
 	return pci_dev_show_local_cpu(dev, 0, attr, buf);
 }
@@ -117,8 +115,7 @@ static DEVICE_ATTR_RO(local_cpulist);
 /*
  * PCI Bus Class Devices
  */
-static ssize_t pci_bus_show_cpuaffinity(struct device *dev,
-					int type,
+static ssize_t pci_bus_show_cpuaffinity(struct device *dev, int type,
 					struct device_attribute *attr,
 					char *buf)
 {
@@ -149,11 +146,11 @@ static ssize_t cpulistaffinity_show(struct device *dev,
 static DEVICE_ATTR_RO(cpulistaffinity);
 
 /* show resources */
-static ssize_t
-resource_show(struct device * dev, struct device_attribute *attr, char * buf)
+static ssize_t resource_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
 {
-	struct pci_dev * pci_dev = to_pci_dev(dev);
-	char * str = buf;
+	struct pci_dev *pci_dev = to_pci_dev(dev);
+	char *str = buf;
 	int i;
 	int max;
 	resource_size_t start, end;
@@ -166,7 +163,7 @@ resource_show(struct device * dev, struct device_attribute *attr, char * buf)
 	for (i = 0; i < max; i++) {
 		struct resource *res =  &pci_dev->resource[i];
 		pci_resource_to_user(pci_dev, i, res, &start, &end);
-		str += sprintf(str,"0x%016llx 0x%016llx 0x%016llx\n",
+		str += sprintf(str, "0x%016llx 0x%016llx 0x%016llx\n",
 			       (unsigned long long)start,
 			       (unsigned long long)end,
 			       (unsigned long long)res->flags);
@@ -175,7 +172,8 @@ resource_show(struct device * dev, struct device_attribute *attr, char * buf)
 }
 static DEVICE_ATTR_RO(resource);
 
-static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 
@@ -187,9 +185,8 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(modalias);
 
-static ssize_t enabled_store(struct device *dev,
-			     struct device_attribute *attr, const char *buf,
-			     size_t count)
+static ssize_t enabled_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	unsigned long val;
@@ -213,57 +210,56 @@ static ssize_t enabled_store(struct device *dev,
 	return result < 0 ? result : count;
 }
 
-static ssize_t enabled_show(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t enabled_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct pci_dev *pdev;
 
-	pdev = to_pci_dev (dev);
-	return sprintf (buf, "%u\n", atomic_read(&pdev->enable_cnt));
+	pdev = to_pci_dev(dev);
+	return sprintf(buf, "%u\n", atomic_read(&pdev->enable_cnt));
 }
 static DEVICE_ATTR_RW(enabled);
 
 #ifdef CONFIG_NUMA
-static ssize_t
-numa_node_show(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
+			      char *buf)
 {
-	return sprintf (buf, "%d\n", dev->numa_node);
+	return sprintf(buf, "%d\n", dev->numa_node);
 }
 static DEVICE_ATTR_RO(numa_node);
 #endif
 
-static ssize_t
-dma_mask_bits_show(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t dma_mask_bits_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 
-	return sprintf (buf, "%d\n", fls64(pdev->dma_mask));
+	return sprintf(buf, "%d\n", fls64(pdev->dma_mask));
 }
 static DEVICE_ATTR_RO(dma_mask_bits);
 
-static ssize_t
-consistent_dma_mask_bits_show(struct device *dev, struct device_attribute *attr,
-				 char *buf)
+static ssize_t consistent_dma_mask_bits_show(struct device *dev,
+					     struct device_attribute *attr,
+					     char *buf)
 {
-	return sprintf (buf, "%d\n", fls64(dev->coherent_dma_mask));
+	return sprintf(buf, "%d\n", fls64(dev->coherent_dma_mask));
 }
 static DEVICE_ATTR_RO(consistent_dma_mask_bits);
 
-static ssize_t
-msi_bus_show(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t msi_bus_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 
 	if (!pdev->subordinate)
 		return 0;
 
-	return sprintf (buf, "%u\n",
-			!(pdev->subordinate->bus_flags & PCI_BUS_FLAGS_NO_MSI));
+	return sprintf(buf, "%u\n",
+		       !(pdev->subordinate->bus_flags & PCI_BUS_FLAGS_NO_MSI));
 }
 
-static ssize_t
-msi_bus_store(struct device *dev, struct device_attribute *attr,
-	      const char *buf, size_t count)
+static ssize_t msi_bus_store(struct device *dev, struct device_attribute *attr,
+			     const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	unsigned long val;
@@ -290,8 +286,8 @@ msi_bus_store(struct device *dev, struct device_attribute *attr,
 	    !!val) {
 		pdev->subordinate->bus_flags ^= PCI_BUS_FLAGS_NO_MSI;
 
-		dev_warn(&pdev->dev, "forced subordinate bus to%s support MSI,"
-			 " bad things could happen\n", val ? "" : " not");
+		dev_warn(&pdev->dev, "forced subordinate bus to%s support MSI, bad things could happen\n",
+			 val ? "" : " not");
 	}
 
 	return count;
@@ -331,9 +327,9 @@ const struct attribute_group *pci_bus_groups[] = {
 	NULL,
 };
 
-static ssize_t
-dev_rescan_store(struct device *dev, struct device_attribute *attr,
-		 const char *buf, size_t count)
+static ssize_t dev_rescan_store(struct device *dev,
+				struct device_attribute *attr, const char *buf,
+				size_t count)
 {
 	unsigned long val;
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -352,9 +348,8 @@ static struct device_attribute dev_rescan_attr = __ATTR(rescan,
 							(S_IWUSR|S_IWGRP),
 							NULL, dev_rescan_store);
 
-static ssize_t
-remove_store(struct device *dev, struct device_attribute *attr,
-	     const char *buf, size_t count)
+static ssize_t remove_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	unsigned long val;
 
@@ -369,9 +364,9 @@ static struct device_attribute dev_remove_attr = __ATTR(remove,
 							(S_IWUSR|S_IWGRP),
 							NULL, remove_store);
 
-static ssize_t
-dev_bus_rescan_store(struct device *dev, struct device_attribute *attr,
-		 const char *buf, size_t count)
+static ssize_t dev_bus_rescan_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t count)
 {
 	unsigned long val;
 	struct pci_bus *bus = to_pci_bus(dev);
@@ -412,7 +407,7 @@ static ssize_t d3cold_allowed_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	return sprintf (buf, "%u\n", pdev->d3cold_allowed);
+	return sprintf(buf, "%u\n", pdev->d3cold_allowed);
 }
 static DEVICE_ATTR_RW(d3cold_allowed);
 #endif
@@ -607,8 +602,8 @@ const struct attribute_group *pcibus_groups[] = {
 	NULL,
 };
 
-static ssize_t
-boot_vga_show(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t boot_vga_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct pci_dev *vga_dev = vga_default_device();
@@ -622,22 +617,21 @@ boot_vga_show(struct device *dev, struct device_attribute *attr, char *buf)
 }
 static struct device_attribute vga_attr = __ATTR_RO(boot_vga);
 
-static ssize_t
-pci_read_config(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *bin_attr,
-		char *buf, loff_t off, size_t count)
+static ssize_t pci_read_config(struct file *filp, struct kobject *kobj,
+			       struct bin_attribute *bin_attr, char *buf,
+			       loff_t off, size_t count)
 {
-	struct pci_dev *dev = to_pci_dev(container_of(kobj,struct device,kobj));
+	struct pci_dev *dev = to_pci_dev(container_of(kobj, struct device,
+						      kobj));
 	unsigned int size = 64;
 	loff_t init_off = off;
-	u8 *data = (u8*) buf;
+	u8 *data = (u8 *) buf;
 
 	/* Several chips lock up trying to read undefined config space */
-	if (security_capable(filp->f_cred, &init_user_ns, CAP_SYS_ADMIN) == 0) {
+	if (security_capable(filp->f_cred, &init_user_ns, CAP_SYS_ADMIN) == 0)
 		size = dev->cfg_size;
-	} else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) {
+	else if (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
 		size = 128;
-	}
 
 	if (off > size)
 		return 0;
@@ -700,15 +694,15 @@ pci_read_config(struct file *filp, struct kobject *kobj,
 	return count;
 }
 
-static ssize_t
-pci_write_config(struct file* filp, struct kobject *kobj,
-		 struct bin_attribute *bin_attr,
-		 char *buf, loff_t off, size_t count)
+static ssize_t pci_write_config(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *bin_attr, char *buf,
+				loff_t off, size_t count)
 {
-	struct pci_dev *dev = to_pci_dev(container_of(kobj,struct device,kobj));
+	struct pci_dev *dev = to_pci_dev(container_of(kobj, struct device,
+						      kobj));
 	unsigned int size = count;
 	loff_t init_off = off;
-	u8 *data = (u8*) buf;
+	u8 *data = (u8 *) buf;
 
 	if (off > dev->cfg_size)
 		return 0;
@@ -728,10 +722,10 @@ pci_write_config(struct file* filp, struct kobject *kobj,
 	if ((off & 3) && size > 2) {
 		u16 val = data[off - init_off];
 		val |= (u16) data[off - init_off + 1] << 8;
-                pci_user_write_config_word(dev, off, val);
-                off += 2;
-                size -= 2;
-        }
+		pci_user_write_config_word(dev, off, val);
+		off += 2;
+		size -= 2;
+	}
 
 	while (size > 3) {
 		u32 val = data[off - init_off];
@@ -762,10 +756,9 @@ pci_write_config(struct file* filp, struct kobject *kobj,
 	return count;
 }
 
-static ssize_t
-read_vpd_attr(struct file *filp, struct kobject *kobj,
-	      struct bin_attribute *bin_attr,
-	      char *buf, loff_t off, size_t count)
+static ssize_t read_vpd_attr(struct file *filp, struct kobject *kobj,
+			     struct bin_attribute *bin_attr, char *buf,
+			     loff_t off, size_t count)
 {
 	struct pci_dev *dev =
 		to_pci_dev(container_of(kobj, struct device, kobj));
@@ -778,10 +771,9 @@ read_vpd_attr(struct file *filp, struct kobject *kobj,
 	return pci_read_vpd(dev, off, count, buf);
 }
 
-static ssize_t
-write_vpd_attr(struct file *filp, struct kobject *kobj,
-	       struct bin_attribute *bin_attr,
-	       char *buf, loff_t off, size_t count)
+static ssize_t write_vpd_attr(struct file *filp, struct kobject *kobj,
+			      struct bin_attribute *bin_attr, char *buf,
+			      loff_t off, size_t count)
 {
 	struct pci_dev *dev =
 		to_pci_dev(container_of(kobj, struct device, kobj));
@@ -807,20 +799,18 @@ write_vpd_attr(struct file *filp, struct kobject *kobj,
  * Reads 1, 2, or 4 bytes from legacy I/O port space using an arch specific
  * callback routine (pci_legacy_read).
  */
-static ssize_t
-pci_read_legacy_io(struct file *filp, struct kobject *kobj,
-		   struct bin_attribute *bin_attr,
-		   char *buf, loff_t off, size_t count)
+static ssize_t pci_read_legacy_io(struct file *filp, struct kobject *kobj,
+				  struct bin_attribute *bin_attr, char *buf,
+				  loff_t off, size_t count)
 {
-        struct pci_bus *bus = to_pci_bus(container_of(kobj,
-                                                      struct device,
+	struct pci_bus *bus = to_pci_bus(container_of(kobj, struct device,
 						      kobj));
 
-        /* Only support 1, 2 or 4 byte accesses */
-        if (count != 1 && count != 2 && count != 4)
-                return -EINVAL;
+	/* Only support 1, 2 or 4 byte accesses */
+	if (count != 1 && count != 2 && count != 4)
+		return -EINVAL;
 
-        return pci_legacy_read(bus, off, (u32 *)buf, count);
+	return pci_legacy_read(bus, off, (u32 *)buf, count);
 }
 
 /**
@@ -835,19 +825,18 @@ pci_read_legacy_io(struct file *filp, struct kobject *kobj,
  * Writes 1, 2, or 4 bytes from legacy I/O port space using an arch specific
  * callback routine (pci_legacy_write).
  */
-static ssize_t
-pci_write_legacy_io(struct file *filp, struct kobject *kobj,
-		    struct bin_attribute *bin_attr,
-		    char *buf, loff_t off, size_t count)
+static ssize_t pci_write_legacy_io(struct file *filp, struct kobject *kobj,
+				   struct bin_attribute *bin_attr, char *buf,
+				   loff_t off, size_t count)
 {
-        struct pci_bus *bus = to_pci_bus(container_of(kobj,
-						      struct device,
+	struct pci_bus *bus = to_pci_bus(container_of(kobj, struct device,
 						      kobj));
-        /* Only support 1, 2 or 4 byte accesses */
-        if (count != 1 && count != 2 && count != 4)
-                return -EINVAL;
 
-        return pci_legacy_write(bus, off, *(u32 *)buf, count);
+	/* Only support 1, 2 or 4 byte accesses */
+	if (count != 1 && count != 2 && count != 4)
+		return -EINVAL;
+
+	return pci_legacy_write(bus, off, *(u32 *)buf, count);
 }
 
 /**
@@ -861,16 +850,14 @@ pci_write_legacy_io(struct file *filp, struct kobject *kobj,
  * legacy memory space (first meg of bus space) into application virtual
  * memory space.
  */
-static int
-pci_mmap_legacy_mem(struct file *filp, struct kobject *kobj,
-		    struct bin_attribute *attr,
-                    struct vm_area_struct *vma)
+static int pci_mmap_legacy_mem(struct file *filp, struct kobject *kobj,
+			       struct bin_attribute *attr,
+			       struct vm_area_struct *vma)
 {
-        struct pci_bus *bus = to_pci_bus(container_of(kobj,
-                                                      struct device,
+	struct pci_bus *bus = to_pci_bus(container_of(kobj, struct device,
 						      kobj));
 
-        return pci_mmap_legacy_page_range(bus, vma, pci_mmap_mem);
+	return pci_mmap_legacy_page_range(bus, vma, pci_mmap_mem);
 }
 
 /**
@@ -884,16 +871,14 @@ pci_mmap_legacy_mem(struct file *filp, struct kobject *kobj,
  * legacy IO space (first meg of bus space) into application virtual
  * memory space. Returns -ENOSYS if the operation isn't supported
  */
-static int
-pci_mmap_legacy_io(struct file *filp, struct kobject *kobj,
-		   struct bin_attribute *attr,
-		   struct vm_area_struct *vma)
+static int pci_mmap_legacy_io(struct file *filp, struct kobject *kobj,
+			      struct bin_attribute *attr,
+			      struct vm_area_struct *vma)
 {
-        struct pci_bus *bus = to_pci_bus(container_of(kobj,
-                                                      struct device,
+	struct pci_bus *bus = to_pci_bus(container_of(kobj, struct device,
 						      kobj));
 
-        return pci_mmap_legacy_page_range(bus, vma, pci_mmap_io);
+	return pci_mmap_legacy_page_range(bus, vma, pci_mmap_io);
 }
 
 /**
@@ -903,10 +888,9 @@ pci_mmap_legacy_io(struct file *filp, struct kobject *kobj,
  *
  * Stub implementation. Can be overridden by arch if necessary.
  */
-void __weak
-pci_adjust_legacy_attr(struct pci_bus *b, enum pci_mmap_state mmap_type)
+void __weak pci_adjust_legacy_attr(struct pci_bus *b,
+				   enum pci_mmap_state mmap_type)
 {
-	return;
 }
 
 /**
@@ -961,8 +945,7 @@ legacy_io_err:
 	kfree(b->legacy_io);
 	b->legacy_io = NULL;
 kzalloc_err:
-	printk(KERN_WARNING "pci: warning: could not create legacy I/O port "
-	       "and ISA memory resources to sysfs\n");
+	printk(KERN_WARNING "pci: warning: could not create legacy I/O port and ISA memory resources to sysfs\n");
 	return;
 }
 
@@ -1005,9 +988,8 @@ int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma,
  *
  * Use the regular PCI mapping routines to map a PCI resource into userspace.
  */
-static int
-pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
-		  struct vm_area_struct *vma, int write_combine)
+static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
+			     struct vm_area_struct *vma, int write_combine)
 {
 	struct pci_dev *pdev = to_pci_dev(container_of(kobj,
 						       struct device, kobj));
@@ -1023,8 +1005,7 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 		return -ENODEV;
 
 	if (!pci_mmap_fits(pdev, i, vma, PCI_MMAP_SYSFS)) {
-		WARN(1, "process \"%s\" tried to map 0x%08lx bytes "
-			"at page 0x%08lx on %s BAR %d (start 0x%16Lx, size 0x%16Lx)\n",
+		WARN(1, "process \"%s\" tried to map 0x%08lx bytes at page 0x%08lx on %s BAR %d (start 0x%16Lx, size 0x%16Lx)\n",
 			current->comm, vma->vm_end-vma->vm_start, vma->vm_pgoff,
 			pci_name(pdev), i,
 			(u64)pci_resource_start(pdev, i),
@@ -1046,26 +1027,23 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 	return pci_mmap_page_range(pdev, vma, mmap_type, write_combine);
 }
 
-static int
-pci_mmap_resource_uc(struct file *filp, struct kobject *kobj,
-		     struct bin_attribute *attr,
-		     struct vm_area_struct *vma)
+static int pci_mmap_resource_uc(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *attr,
+				struct vm_area_struct *vma)
 {
 	return pci_mmap_resource(kobj, attr, vma, 0);
 }
 
-static int
-pci_mmap_resource_wc(struct file *filp, struct kobject *kobj,
-		     struct bin_attribute *attr,
-		     struct vm_area_struct *vma)
+static int pci_mmap_resource_wc(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *attr,
+				struct vm_area_struct *vma)
 {
 	return pci_mmap_resource(kobj, attr, vma, 1);
 }
 
-static ssize_t
-pci_resource_io(struct file *filp, struct kobject *kobj,
-		struct bin_attribute *attr, char *buf,
-		loff_t off, size_t count, bool write)
+static ssize_t pci_resource_io(struct file *filp, struct kobject *kobj,
+			       struct bin_attribute *attr, char *buf,
+			       loff_t off, size_t count, bool write)
 {
 	struct pci_dev *pdev = to_pci_dev(container_of(kobj,
 						       struct device, kobj));
@@ -1110,18 +1088,16 @@ pci_resource_io(struct file *filp, struct kobject *kobj,
 	return -EINVAL;
 }
 
-static ssize_t
-pci_read_resource_io(struct file *filp, struct kobject *kobj,
-		     struct bin_attribute *attr, char *buf,
-		     loff_t off, size_t count)
+static ssize_t pci_read_resource_io(struct file *filp, struct kobject *kobj,
+				    struct bin_attribute *attr, char *buf,
+				    loff_t off, size_t count)
 {
 	return pci_resource_io(filp, kobj, attr, buf, off, count, false);
 }
 
-static ssize_t
-pci_write_resource_io(struct file *filp, struct kobject *kobj,
-		      struct bin_attribute *attr, char *buf,
-		      loff_t off, size_t count)
+static ssize_t pci_write_resource_io(struct file *filp, struct kobject *kobj,
+				     struct bin_attribute *attr, char *buf,
+				     loff_t off, size_t count)
 {
 	return pci_resource_io(filp, kobj, attr, buf, off, count, true);
 }
@@ -1133,8 +1109,7 @@ pci_write_resource_io(struct file *filp, struct kobject *kobj,
  * If we created resource files for @pdev, remove them from sysfs and
  * free their resources.
  */
-static void
-pci_remove_resource_files(struct pci_dev *pdev)
+static void pci_remove_resource_files(struct pci_dev *pdev)
 {
 	int i;
 
@@ -1237,10 +1212,9 @@ void __weak pci_remove_resource_files(struct pci_dev *dev) { return; }
  *
  * writing anything except 0 enables it
  */
-static ssize_t
-pci_write_rom(struct file *filp, struct kobject *kobj,
-	      struct bin_attribute *bin_attr,
-	      char *buf, loff_t off, size_t count)
+static ssize_t pci_write_rom(struct file *filp, struct kobject *kobj,
+			     struct bin_attribute *bin_attr, char *buf,
+			     loff_t off, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(container_of(kobj, struct device, kobj));
 
@@ -1264,10 +1238,9 @@ pci_write_rom(struct file *filp, struct kobject *kobj,
  * Put @count bytes starting at @off into @buf from the ROM in the PCI
  * device corresponding to @kobj.
  */
-static ssize_t
-pci_read_rom(struct file *filp, struct kobject *kobj,
-	     struct bin_attribute *bin_attr,
-	     char *buf, loff_t off, size_t count)
+static ssize_t pci_read_rom(struct file *filp, struct kobject *kobj,
+			    struct bin_attribute *bin_attr, char *buf,
+			    loff_t off, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(container_of(kobj, struct device, kobj));
 	void __iomem *rom;
@@ -1313,9 +1286,8 @@ static struct bin_attribute pcie_config_attr = {
 	.write = pci_write_config,
 };
 
-static ssize_t reset_store(struct device *dev,
-			   struct device_attribute *attr, const char *buf,
-			   size_t count)
+static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t count)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	unsigned long val;
@@ -1382,7 +1354,7 @@ error:
 	return retval;
 }
 
-int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev)
+int __must_check pci_create_sysfs_dev_files(struct pci_dev *pdev)
 {
 	int retval;
 	int rom_size = 0;
@@ -1520,7 +1492,6 @@ static int __init pci_sysfs_init(void)
 
 	return 0;
 }
-
 late_initcall(pci_sysfs_init);
 
 static struct attribute *pci_dev_dev_attrs[] = {
@@ -1529,7 +1500,7 @@ static struct attribute *pci_dev_dev_attrs[] = {
 };
 
 static umode_t pci_dev_attrs_are_visible(struct kobject *kobj,
-						struct attribute *a, int n)
+					 struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -1548,7 +1519,7 @@ static struct attribute *pci_dev_hp_attrs[] = {
 };
 
 static umode_t pci_dev_hp_attrs_are_visible(struct kobject *kobj,
-						struct attribute *a, int n)
+					    struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -1572,7 +1543,7 @@ static struct attribute *sriov_dev_attrs[] = {
 };
 
 static umode_t sriov_attrs_are_visible(struct kobject *kobj,
-					 struct attribute *a, int n)
+				       struct attribute *a, int n)
 {
 	struct device *dev = container_of(kobj, struct device, kobj);
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 436a76ab4bb..2c9ac70254e 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -114,7 +114,7 @@ unsigned char pci_bus_max_busnr(struct pci_bus *bus)
 	max = bus->busn_res.end;
 	list_for_each_entry(tmp, &bus->children, node) {
 		n = pci_bus_max_busnr(tmp);
-		if(n > max)
+		if (n > max)
 			max = n;
 	}
 	return max;
@@ -226,6 +226,7 @@ int pci_find_capability(struct pci_dev *dev, int cap)
 
 	return pos;
 }
+EXPORT_SYMBOL(pci_find_capability);
 
 /**
  * pci_bus_find_capability - query for devices' capabilities
@@ -253,6 +254,7 @@ int pci_bus_find_capability(struct pci_bus *bus, unsigned int devfn, int cap)
 
 	return pos;
 }
+EXPORT_SYMBOL(pci_bus_find_capability);
 
 /**
  * pci_find_next_ext_capability - Find an extended capability
@@ -403,8 +405,8 @@ EXPORT_SYMBOL_GPL(pci_find_ht_capability);
  *  For given resource region of given device, return the resource
  *  region of parent bus the given region is contained in.
  */
-struct resource *
-pci_find_parent_resource(const struct pci_dev *dev, struct resource *res)
+struct resource *pci_find_parent_resource(const struct pci_dev *dev,
+					  struct resource *res)
 {
 	const struct pci_bus *bus = dev->bus;
 	struct resource *r;
@@ -436,6 +438,7 @@ pci_find_parent_resource(const struct pci_dev *dev, struct resource *res)
 	}
 	return NULL;
 }
+EXPORT_SYMBOL(pci_find_parent_resource);
 
 /**
  * pci_wait_for_pending - wait for @mask bit(s) to clear in status word @pos
@@ -470,8 +473,7 @@ int pci_wait_for_pending(struct pci_dev *dev, int pos, u16 mask)
  * Restore the BAR values for a given device, so as to make it
  * accessible by its driver.
  */
-static void
-pci_restore_bars(struct pci_dev *dev)
+static void pci_restore_bars(struct pci_dev *dev)
 {
 	int i;
 
@@ -496,7 +498,7 @@ static inline bool platform_pci_power_manageable(struct pci_dev *dev)
 }
 
 static inline int platform_pci_set_power_state(struct pci_dev *dev,
-                                                pci_power_t t)
+					       pci_power_t t)
 {
 	return pci_platform_pm ? pci_platform_pm->set_state(dev, t) : -ENOSYS;
 }
@@ -553,8 +555,8 @@ static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state)
 	 */
 	if (state != PCI_D0 && dev->current_state <= PCI_D3cold
 	    && dev->current_state > state) {
-		dev_err(&dev->dev, "invalid power transition "
-			"(from state %d to %d)\n", dev->current_state, state);
+		dev_err(&dev->dev, "invalid power transition (from state %d to %d)\n",
+			dev->current_state, state);
 		return -EINVAL;
 	}
 
@@ -601,8 +603,8 @@ static int pci_raw_set_power_state(struct pci_dev *dev, pci_power_t state)
 	pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
 	dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
 	if (dev->current_state != state && printk_ratelimit())
-		dev_info(&dev->dev, "Refused to change power state, "
-			"currently in D%d\n", dev->current_state);
+		dev_info(&dev->dev, "Refused to change power state, currently in D%d\n",
+			 dev->current_state);
 
 	/*
 	 * According to section 5.4.1 of the "PCI BUS POWER MANAGEMENT
@@ -837,15 +839,10 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 
 	if (!__pci_complete_power_transition(dev, state))
 		error = 0;
-	/*
-	 * When aspm_policy is "powersave" this call ensures
-	 * that ASPM is configured.
-	 */
-	if (!error && dev->bus->self)
-		pcie_aspm_powersave_config_link(dev->bus->self);
 
 	return error;
 }
+EXPORT_SYMBOL(pci_set_power_state);
 
 /**
  * pci_choose_state - Choose the power state of a PCI device
@@ -884,12 +881,10 @@ pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state)
 	}
 	return PCI_D0;
 }
-
 EXPORT_SYMBOL(pci_choose_state);
 
 #define PCI_EXP_SAVE_REGS	7
 
-
 static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev,
 						       u16 cap, bool extended)
 {
@@ -1001,8 +996,7 @@ static void pci_restore_pcix_state(struct pci_dev *dev)
  * pci_save_state - save the PCI configuration space of a device before suspending
  * @dev: - PCI device that we're dealing with
  */
-int
-pci_save_state(struct pci_dev *dev)
+int pci_save_state(struct pci_dev *dev)
 {
 	int i;
 	/* XXX: 100% dword access ok here? */
@@ -1017,6 +1011,7 @@ pci_save_state(struct pci_dev *dev)
 		return i;
 	return 0;
 }
+EXPORT_SYMBOL(pci_save_state);
 
 static void pci_restore_config_dword(struct pci_dev *pdev, int offset,
 				     u32 saved_val, int retry)
@@ -1028,8 +1023,8 @@ static void pci_restore_config_dword(struct pci_dev *pdev, int offset,
 		return;
 
 	for (;;) {
-		dev_dbg(&pdev->dev, "restoring config space at offset "
-			"%#x (was %#x, writing %#x)\n", offset, val, saved_val);
+		dev_dbg(&pdev->dev, "restoring config space at offset %#x (was %#x, writing %#x)\n",
+			offset, val, saved_val);
 		pci_write_config_dword(pdev, offset, saved_val);
 		if (retry-- <= 0)
 			return;
@@ -1087,6 +1082,7 @@ void pci_restore_state(struct pci_dev *dev)
 
 	dev->state_saved = false;
 }
+EXPORT_SYMBOL(pci_restore_state);
 
 struct pci_saved_state {
 	u32 config_space[16];
@@ -1193,12 +1189,18 @@ int __weak pcibios_enable_device(struct pci_dev *dev, int bars)
 static int do_pci_enable_device(struct pci_dev *dev, int bars)
 {
 	int err;
+	struct pci_dev *bridge;
 	u16 cmd;
 	u8 pin;
 
 	err = pci_set_power_state(dev, PCI_D0);
 	if (err < 0 && err != -EIO)
 		return err;
+
+	bridge = pci_upstream_bridge(dev);
+	if (bridge)
+		pcie_aspm_powersave_config_link(bridge);
+
 	err = pcibios_enable_device(dev, bars);
 	if (err < 0)
 		return err;
@@ -1231,6 +1233,7 @@ int pci_reenable_device(struct pci_dev *dev)
 		return do_pci_enable_device(dev, (1 << PCI_NUM_RESOURCES) - 1);
 	return 0;
 }
+EXPORT_SYMBOL(pci_reenable_device);
 
 static void pci_enable_bridge(struct pci_dev *dev)
 {
@@ -1305,6 +1308,7 @@ int pci_enable_device_io(struct pci_dev *dev)
 {
 	return pci_enable_device_flags(dev, IORESOURCE_IO);
 }
+EXPORT_SYMBOL(pci_enable_device_io);
 
 /**
  * pci_enable_device_mem - Initialize a device for use with Memory space
@@ -1318,6 +1322,7 @@ int pci_enable_device_mem(struct pci_dev *dev)
 {
 	return pci_enable_device_flags(dev, IORESOURCE_MEM);
 }
+EXPORT_SYMBOL(pci_enable_device_mem);
 
 /**
  * pci_enable_device - Initialize device before it's used by a driver.
@@ -1334,6 +1339,7 @@ int pci_enable_device(struct pci_dev *dev)
 {
 	return pci_enable_device_flags(dev, IORESOURCE_MEM | IORESOURCE_IO);
 }
+EXPORT_SYMBOL(pci_enable_device);
 
 /*
  * Managed PCI resources.  This manages device on/off, intx/msi/msix
@@ -1416,6 +1422,7 @@ int pcim_enable_device(struct pci_dev *pdev)
 	}
 	return rc;
 }
+EXPORT_SYMBOL(pcim_enable_device);
 
 /**
  * pcim_pin_device - Pin managed PCI device
@@ -1434,6 +1441,7 @@ void pcim_pin_device(struct pci_dev *pdev)
 	if (dr)
 		dr->pinned = 1;
 }
+EXPORT_SYMBOL(pcim_pin_device);
 
 /*
  * pcibios_add_device - provide arch specific hooks when adding device dev
@@ -1443,7 +1451,7 @@ void pcim_pin_device(struct pci_dev *pdev)
  * devices are added. This is the default implementation. Architecture
  * implementations can override this.
  */
-int __weak pcibios_add_device (struct pci_dev *dev)
+int __weak pcibios_add_device(struct pci_dev *dev)
 {
 	return 0;
 }
@@ -1515,8 +1523,7 @@ void pci_disable_enabled_device(struct pci_dev *dev)
  * Note we don't actually disable the device until all callers of
  * pci_enable_device() have called pci_disable_device().
  */
-void
-pci_disable_device(struct pci_dev *dev)
+void pci_disable_device(struct pci_dev *dev)
 {
 	struct pci_devres *dr;
 
@@ -1534,6 +1541,7 @@ pci_disable_device(struct pci_dev *dev)
 
 	dev->is_busmaster = 0;
 }
+EXPORT_SYMBOL(pci_disable_device);
 
 /**
  * pcibios_set_pcie_reset_state - set reset state for device dev
@@ -1562,6 +1570,7 @@ int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
 {
 	return pcibios_set_pcie_reset_state(dev, state);
 }
+EXPORT_SYMBOL_GPL(pci_set_pcie_reset_state);
 
 /**
  * pci_check_pme_status - Check if given device has generated PME.
@@ -1641,6 +1650,7 @@ bool pci_pme_capable(struct pci_dev *dev, pci_power_t state)
 
 	return !!(dev->pme_support & (1 << state));
 }
+EXPORT_SYMBOL(pci_pme_capable);
 
 static void pci_pme_list_scan(struct work_struct *work)
 {
@@ -1745,6 +1755,7 @@ void pci_pme_active(struct pci_dev *dev, bool enable)
 
 	dev_dbg(&dev->dev, "PME# %s\n", enable ? "enabled" : "disabled");
 }
+EXPORT_SYMBOL(pci_pme_active);
 
 /**
  * __pci_enable_wake - enable PCI device as wakeup event source
@@ -1830,6 +1841,7 @@ int pci_wake_from_d3(struct pci_dev *dev, bool enable)
 			pci_enable_wake(dev, PCI_D3cold, enable) :
 			pci_enable_wake(dev, PCI_D3hot, enable);
 }
+EXPORT_SYMBOL(pci_wake_from_d3);
 
 /**
  * pci_target_state - find an appropriate low power state for a given PCI dev
@@ -1908,6 +1920,7 @@ int pci_prepare_to_sleep(struct pci_dev *dev)
 
 	return error;
 }
+EXPORT_SYMBOL(pci_prepare_to_sleep);
 
 /**
  * pci_back_from_sleep - turn PCI device on during system-wide transition into working state
@@ -1920,6 +1933,7 @@ int pci_back_from_sleep(struct pci_dev *dev)
 	pci_enable_wake(dev, PCI_D0, false);
 	return pci_set_power_state(dev, PCI_D0);
 }
+EXPORT_SYMBOL(pci_back_from_sleep);
 
 /**
  * pci_finish_runtime_suspend - Carry out PCI-specific part of runtime suspend.
@@ -2415,8 +2429,7 @@ u8 pci_swizzle_interrupt_pin(const struct pci_dev *dev, u8 pin)
 	return (((pin - 1) + slot) % 4) + 1;
 }
 
-int
-pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge)
+int pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge)
 {
 	u8 pin;
 
@@ -2478,6 +2491,7 @@ void pci_release_region(struct pci_dev *pdev, int bar)
 	if (dr)
 		dr->region_mask &= ~(1 << bar);
 }
+EXPORT_SYMBOL(pci_release_region);
 
 /**
  *	__pci_request_region - Reserved PCI I/O and memory resource
@@ -2498,8 +2512,8 @@ void pci_release_region(struct pci_dev *pdev, int bar)
  *	Returns 0 on success, or %EBUSY on error.  A warning
  *	message is also printed on failure.
  */
-static int __pci_request_region(struct pci_dev *pdev, int bar, const char *res_name,
-									int exclusive)
+static int __pci_request_region(struct pci_dev *pdev, int bar,
+				const char *res_name, int exclusive)
 {
 	struct pci_devres *dr;
 
@@ -2510,8 +2524,7 @@ static int __pci_request_region(struct pci_dev *pdev, int bar, const char *res_n
 		if (!request_region(pci_resource_start(pdev, bar),
 			    pci_resource_len(pdev, bar), res_name))
 			goto err_out;
-	}
-	else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
+	} else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
 		if (!__request_mem_region(pci_resource_start(pdev, bar),
 					pci_resource_len(pdev, bar), res_name,
 					exclusive))
@@ -2548,6 +2561,7 @@ int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name)
 {
 	return __pci_request_region(pdev, bar, res_name, 0);
 }
+EXPORT_SYMBOL(pci_request_region);
 
 /**
  *	pci_request_region_exclusive - Reserved PCI I/O and memory resource
@@ -2567,10 +2581,13 @@ int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name)
  *	explicitly not allowed to map the resource via /dev/mem or
  *	sysfs.
  */
-int pci_request_region_exclusive(struct pci_dev *pdev, int bar, const char *res_name)
+int pci_request_region_exclusive(struct pci_dev *pdev, int bar,
+				 const char *res_name)
 {
 	return __pci_request_region(pdev, bar, res_name, IORESOURCE_EXCLUSIVE);
 }
+EXPORT_SYMBOL(pci_request_region_exclusive);
+
 /**
  * pci_release_selected_regions - Release selected PCI I/O and memory resources
  * @pdev: PCI device whose resources were previously reserved
@@ -2587,9 +2604,10 @@ void pci_release_selected_regions(struct pci_dev *pdev, int bars)
 		if (bars & (1 << i))
 			pci_release_region(pdev, i);
 }
+EXPORT_SYMBOL(pci_release_selected_regions);
 
 static int __pci_request_selected_regions(struct pci_dev *pdev, int bars,
-				 const char *res_name, int excl)
+					  const char *res_name, int excl)
 {
 	int i;
 
@@ -2600,7 +2618,7 @@ static int __pci_request_selected_regions(struct pci_dev *pdev, int bars,
 	return 0;
 
 err_out:
-	while(--i >= 0)
+	while (--i >= 0)
 		if (bars & (1 << i))
 			pci_release_region(pdev, i);
 
@@ -2619,13 +2637,15 @@ int pci_request_selected_regions(struct pci_dev *pdev, int bars,
 {
 	return __pci_request_selected_regions(pdev, bars, res_name, 0);
 }
+EXPORT_SYMBOL(pci_request_selected_regions);
 
-int pci_request_selected_regions_exclusive(struct pci_dev *pdev,
-				 int bars, const char *res_name)
+int pci_request_selected_regions_exclusive(struct pci_dev *pdev, int bars,
+					   const char *res_name)
 {
 	return __pci_request_selected_regions(pdev, bars, res_name,
 			IORESOURCE_EXCLUSIVE);
 }
+EXPORT_SYMBOL(pci_request_selected_regions_exclusive);
 
 /**
  *	pci_release_regions - Release reserved PCI I/O and memory resources
@@ -2640,6 +2660,7 @@ void pci_release_regions(struct pci_dev *pdev)
 {
 	pci_release_selected_regions(pdev, (1 << 6) - 1);
 }
+EXPORT_SYMBOL(pci_release_regions);
 
 /**
  *	pci_request_regions - Reserved PCI I/O and memory resources
@@ -2658,6 +2679,7 @@ int pci_request_regions(struct pci_dev *pdev, const char *res_name)
 {
 	return pci_request_selected_regions(pdev, ((1 << 6) - 1), res_name);
 }
+EXPORT_SYMBOL(pci_request_regions);
 
 /**
  *	pci_request_regions_exclusive - Reserved PCI I/O and memory resources
@@ -2680,6 +2702,7 @@ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name)
 	return pci_request_selected_regions_exclusive(pdev,
 					((1 << 6) - 1), res_name);
 }
+EXPORT_SYMBOL(pci_request_regions_exclusive);
 
 static void __pci_set_master(struct pci_dev *dev, bool enable)
 {
@@ -2749,6 +2772,7 @@ void pci_set_master(struct pci_dev *dev)
 	__pci_set_master(dev, true);
 	pcibios_set_master(dev);
 }
+EXPORT_SYMBOL(pci_set_master);
 
 /**
  * pci_clear_master - disables bus-mastering for device dev
@@ -2758,6 +2782,7 @@ void pci_clear_master(struct pci_dev *dev)
 {
 	__pci_set_master(dev, false);
 }
+EXPORT_SYMBOL(pci_clear_master);
 
 /**
  * pci_set_cacheline_size - ensure the CACHE_LINE_SIZE register is programmed
@@ -2790,30 +2815,13 @@ int pci_set_cacheline_size(struct pci_dev *dev)
 	if (cacheline_size == pci_cache_line_size)
 		return 0;
 
-	dev_printk(KERN_DEBUG, &dev->dev, "cache line size of %d is not "
-		   "supported\n", pci_cache_line_size << 2);
+	dev_printk(KERN_DEBUG, &dev->dev, "cache line size of %d is not supported\n",
+		   pci_cache_line_size << 2);
 
 	return -EINVAL;
 }
 EXPORT_SYMBOL_GPL(pci_set_cacheline_size);
 
-#ifdef PCI_DISABLE_MWI
-int pci_set_mwi(struct pci_dev *dev)
-{
-	return 0;
-}
-
-int pci_try_set_mwi(struct pci_dev *dev)
-{
-	return 0;
-}
-
-void pci_clear_mwi(struct pci_dev *dev)
-{
-}
-
-#else
-
 /**
  * pci_set_mwi - enables memory-write-invalidate PCI transaction
  * @dev: the PCI device for which MWI is enabled
@@ -2822,9 +2830,11 @@ void pci_clear_mwi(struct pci_dev *dev)
  *
  * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
  */
-int
-pci_set_mwi(struct pci_dev *dev)
+int pci_set_mwi(struct pci_dev *dev)
 {
+#ifdef PCI_DISABLE_MWI
+	return 0;
+#else
 	int rc;
 	u16 cmd;
 
@@ -2833,14 +2843,15 @@ pci_set_mwi(struct pci_dev *dev)
 		return rc;
 
 	pci_read_config_word(dev, PCI_COMMAND, &cmd);
-	if (! (cmd & PCI_COMMAND_INVALIDATE)) {
+	if (!(cmd & PCI_COMMAND_INVALIDATE)) {
 		dev_dbg(&dev->dev, "enabling Mem-Wr-Inval\n");
 		cmd |= PCI_COMMAND_INVALIDATE;
 		pci_write_config_word(dev, PCI_COMMAND, cmd);
 	}
-
 	return 0;
+#endif
 }
+EXPORT_SYMBOL(pci_set_mwi);
 
 /**
  * pci_try_set_mwi - enables memory-write-invalidate PCI transaction
@@ -2853,9 +2864,13 @@ pci_set_mwi(struct pci_dev *dev)
  */
 int pci_try_set_mwi(struct pci_dev *dev)
 {
-	int rc = pci_set_mwi(dev);
-	return rc;
+#ifdef PCI_DISABLE_MWI
+	return 0;
+#else
+	return pci_set_mwi(dev);
+#endif
 }
+EXPORT_SYMBOL(pci_try_set_mwi);
 
 /**
  * pci_clear_mwi - disables Memory-Write-Invalidate for device dev
@@ -2863,9 +2878,9 @@ int pci_try_set_mwi(struct pci_dev *dev)
  *
  * Disables PCI Memory-Write-Invalidate transaction on the device
  */
-void
-pci_clear_mwi(struct pci_dev *dev)
+void pci_clear_mwi(struct pci_dev *dev)
 {
+#ifndef PCI_DISABLE_MWI
 	u16 cmd;
 
 	pci_read_config_word(dev, PCI_COMMAND, &cmd);
@@ -2873,8 +2888,9 @@ pci_clear_mwi(struct pci_dev *dev)
 		cmd &= ~PCI_COMMAND_INVALIDATE;
 		pci_write_config_word(dev, PCI_COMMAND, cmd);
 	}
+#endif
 }
-#endif /* ! PCI_DISABLE_MWI */
+EXPORT_SYMBOL(pci_clear_mwi);
 
 /**
  * pci_intx - enables/disables PCI INTx for device dev
@@ -2883,18 +2899,16 @@ pci_clear_mwi(struct pci_dev *dev)
  *
  * Enables/disables PCI INTx for device dev
  */
-void
-pci_intx(struct pci_dev *pdev, int enable)
+void pci_intx(struct pci_dev *pdev, int enable)
 {
 	u16 pci_command, new;
 
 	pci_read_config_word(pdev, PCI_COMMAND, &pci_command);
 
-	if (enable) {
+	if (enable)
 		new = pci_command & ~PCI_COMMAND_INTX_DISABLE;
-	} else {
+	else
 		new = pci_command | PCI_COMMAND_INTX_DISABLE;
-	}
 
 	if (new != pci_command) {
 		struct pci_devres *dr;
@@ -2908,6 +2922,7 @@ pci_intx(struct pci_dev *pdev, int enable)
 		}
 	}
 }
+EXPORT_SYMBOL_GPL(pci_intx);
 
 /**
  * pci_intx_mask_supported - probe for INTx masking support
@@ -2937,8 +2952,8 @@ bool pci_intx_mask_supported(struct pci_dev *dev)
 	 * go ahead and check it.
 	 */
 	if ((new ^ orig) & ~PCI_COMMAND_INTX_DISABLE) {
-		dev_err(&dev->dev, "Command register changed from "
-			"0x%x to 0x%x: driver or hardware bug?\n", orig, new);
+		dev_err(&dev->dev, "Command register changed from 0x%x to 0x%x: driver or hardware bug?\n",
+			orig, new);
 	} else if ((new ^ orig) & PCI_COMMAND_INTX_DISABLE) {
 		mask_supported = true;
 		pci_write_config_word(dev, PCI_COMMAND, orig);
@@ -3120,12 +3135,16 @@ static int pci_af_flr(struct pci_dev *dev, int probe)
 	if (probe)
 		return 0;
 
-	/* Wait for Transaction Pending bit clean */
-	if (pci_wait_for_pending(dev, pos + PCI_AF_STATUS, PCI_AF_STATUS_TP))
+	/*
+	 * Wait for Transaction Pending bit to clear.  A word-aligned test
+	 * is used, so we use the conrol offset rather than status and shift
+	 * the test bit to match.
+	 */
+	if (pci_wait_for_pending(dev, pos + PCI_AF_CTRL,
+				 PCI_AF_STATUS_TP << 8))
 		goto clear;
 
-	dev_err(&dev->dev, "transaction is not cleared; "
-			"proceeding with reset anyway\n");
+	dev_err(&dev->dev, "transaction is not cleared; proceeding with reset anyway\n");
 
 clear:
 	pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR);
@@ -3179,14 +3198,7 @@ static int pci_pm_reset(struct pci_dev *dev, int probe)
 	return 0;
 }
 
-/**
- * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge.
- * @dev: Bridge device
- *
- * Use the bridge control register to assert reset on the secondary bus.
- * Devices on the secondary bus are left in power-on state.
- */
-void pci_reset_bridge_secondary_bus(struct pci_dev *dev)
+void pci_reset_secondary_bus(struct pci_dev *dev)
 {
 	u16 ctrl;
 
@@ -3211,6 +3223,23 @@ void pci_reset_bridge_secondary_bus(struct pci_dev *dev)
 	 */
 	ssleep(1);
 }
+
+void __weak pcibios_reset_secondary_bus(struct pci_dev *dev)
+{
+	pci_reset_secondary_bus(dev);
+}
+
+/**
+ * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge.
+ * @dev: Bridge device
+ *
+ * Use the bridge control register to assert reset on the secondary bus.
+ * Devices on the secondary bus are left in power-on state.
+ */
+void pci_reset_bridge_secondary_bus(struct pci_dev *dev)
+{
+	pcibios_reset_secondary_bus(dev);
+}
 EXPORT_SYMBOL_GPL(pci_reset_bridge_secondary_bus);
 
 static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
@@ -4095,6 +4124,7 @@ int pci_select_bars(struct pci_dev *dev, unsigned long flags)
 			bars |= (1 << i);
 	return bars;
 }
+EXPORT_SYMBOL(pci_select_bars);
 
 /**
  * pci_resource_bar - get position of the BAR associated with a resource
@@ -4134,7 +4164,7 @@ void __init pci_register_set_vga_state(arch_set_vga_state_t func)
 }
 
 static int pci_set_vga_state_arch(struct pci_dev *dev, bool decode,
-		      unsigned int command_bits, u32 flags)
+				  unsigned int command_bits, u32 flags)
 {
 	if (arch_set_vga_state)
 		return arch_set_vga_state(dev, decode, command_bits,
@@ -4246,11 +4276,10 @@ static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev)
 			bus == dev->bus->number &&
 			slot == PCI_SLOT(dev->devfn) &&
 			func == PCI_FUNC(dev->devfn)) {
-			if (align_order == -1) {
+			if (align_order == -1)
 				align = PAGE_SIZE;
-			} else {
+			else
 				align = 1 << align_order;
-			}
 			/* Found */
 			break;
 		}
@@ -4368,7 +4397,6 @@ static int __init pci_resource_alignment_sysfs_init(void)
 	return bus_create_file(&pci_bus_type,
 					&bus_attr_resource_alignment);
 }
-
 late_initcall(pci_resource_alignment_sysfs_init);
 
 static void pci_no_domains(void)
@@ -4447,41 +4475,3 @@ static int __init pci_setup(char *str)
 	return 0;
 }
 early_param("pci", pci_setup);
-
-EXPORT_SYMBOL(pci_reenable_device);
-EXPORT_SYMBOL(pci_enable_device_io);
-EXPORT_SYMBOL(pci_enable_device_mem);
-EXPORT_SYMBOL(pci_enable_device);
-EXPORT_SYMBOL(pcim_enable_device);
-EXPORT_SYMBOL(pcim_pin_device);
-EXPORT_SYMBOL(pci_disable_device);
-EXPORT_SYMBOL(pci_find_capability);
-EXPORT_SYMBOL(pci_bus_find_capability);
-EXPORT_SYMBOL(pci_release_regions);
-EXPORT_SYMBOL(pci_request_regions);
-EXPORT_SYMBOL(pci_request_regions_exclusive);
-EXPORT_SYMBOL(pci_release_region);
-EXPORT_SYMBOL(pci_request_region);
-EXPORT_SYMBOL(pci_request_region_exclusive);
-EXPORT_SYMBOL(pci_release_selected_regions);
-EXPORT_SYMBOL(pci_request_selected_regions);
-EXPORT_SYMBOL(pci_request_selected_regions_exclusive);
-EXPORT_SYMBOL(pci_set_master);
-EXPORT_SYMBOL(pci_clear_master);
-EXPORT_SYMBOL(pci_set_mwi);
-EXPORT_SYMBOL(pci_try_set_mwi);
-EXPORT_SYMBOL(pci_clear_mwi);
-EXPORT_SYMBOL_GPL(pci_intx);
-EXPORT_SYMBOL(pci_assign_resource);
-EXPORT_SYMBOL(pci_find_parent_resource);
-EXPORT_SYMBOL(pci_select_bars);
-
-EXPORT_SYMBOL(pci_set_power_state);
-EXPORT_SYMBOL(pci_save_state);
-EXPORT_SYMBOL(pci_restore_state);
-EXPORT_SYMBOL(pci_pme_capable);
-EXPORT_SYMBOL(pci_pme_active);
-EXPORT_SYMBOL(pci_wake_from_d3);
-EXPORT_SYMBOL(pci_prepare_to_sleep);
-EXPORT_SYMBOL(pci_back_from_sleep);
-EXPORT_SYMBOL_GPL(pci_set_pcie_reset_state);
diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c
index 587e7e85310..182224acedb 100644
--- a/drivers/pci/pcie/aer/aer_inject.c
+++ b/drivers/pci/pcie/aer/aer_inject.c
@@ -397,16 +397,14 @@ static int aer_inject(struct aer_error_inj *einj)
 	if (!aer_mask_override && einj->cor_status &&
 	    !(einj->cor_status & ~cor_mask)) {
 		ret = -EINVAL;
-		printk(KERN_WARNING "The correctable error(s) is masked "
-				"by device\n");
+		printk(KERN_WARNING "The correctable error(s) is masked by device\n");
 		spin_unlock_irqrestore(&inject_lock, flags);
 		goto out_put;
 	}
 	if (!aer_mask_override && einj->uncor_status &&
 	    !(einj->uncor_status & ~uncor_mask)) {
 		ret = -EINVAL;
-		printk(KERN_WARNING "The uncorrectable error(s) is masked "
-				"by device\n");
+		printk(KERN_WARNING "The uncorrectable error(s) is masked by device\n");
 		spin_unlock_irqrestore(&inject_lock, flags);
 		goto out_put;
 	}
@@ -464,8 +462,7 @@ static int aer_inject(struct aer_error_inj *einj)
 			goto out_put;
 		}
 		aer_irq(-1, edev);
-	}
-	else
+	} else
 		ret = -EINVAL;
 out_put:
 	kfree(err_alloc);
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index b2c8881da76..5653ea94547 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -542,8 +542,7 @@ static void aer_recover_work_func(struct work_struct *work);
 #define AER_RECOVER_RING_ORDER		4
 #define AER_RECOVER_RING_SIZE		(1 << AER_RECOVER_RING_ORDER)
 
-struct aer_recover_entry
-{
+struct aer_recover_entry {
 	u8	bus;
 	u8	devfn;
 	u16	domain;
diff --git a/drivers/pci/pcie/aer/aerdrv_errprint.c b/drivers/pci/pcie/aer/aerdrv_errprint.c
index 34ff7026440..36ed31b5219 100644
--- a/drivers/pci/pcie/aer/aerdrv_errprint.c
+++ b/drivers/pci/pcie/aer/aerdrv_errprint.c
@@ -172,9 +172,7 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 	int id = ((dev->bus->number << 8) | dev->devfn);
 
 	if (!info->status) {
-		dev_err(&dev->dev,
-			"PCIe Bus Error: severity=%s, type=Unaccessible, "
-			"id=%04x(Unregistered Agent ID)\n",
+		dev_err(&dev->dev, "PCIe Bus Error: severity=%s, type=Unaccessible, id=%04x(Unregistered Agent ID)\n",
 			aer_error_severity_string[info->severity], id);
 		goto out;
 	}
@@ -182,13 +180,11 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 	layer = AER_GET_LAYER_ERROR(info->severity, info->status);
 	agent = AER_GET_AGENT(info->severity, info->status);
 
-	dev_err(&dev->dev,
-		"PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n",
+	dev_err(&dev->dev, "PCIe Bus Error: severity=%s, type=%s, id=%04x(%s)\n",
 		aer_error_severity_string[info->severity],
 		aer_error_layer[layer], id, aer_agent_string[agent]);
 
-	dev_err(&dev->dev,
-		"  device [%04x:%04x] error status/mask=%08x/%08x\n",
+	dev_err(&dev->dev, "  device [%04x:%04x] error status/mask=%08x/%08x\n",
 		dev->vendor, dev->device,
 		info->status, info->mask);
 
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index bbc3bdd2b18..82e06a86cd7 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -199,8 +199,7 @@ static void pcie_pme_handle_request(struct pci_dev *port, u16 req_id)
 		 * assuming that the PME was reported by a PCIe-PCI bridge that
 		 * used devfn different from zero.
 		 */
-		dev_dbg(&port->dev, "PME interrupt generated for "
-			"non-existent device %02x:%02x.%d\n",
+		dev_dbg(&port->dev, "PME interrupt generated for non-existent device %02x:%02x.%d\n",
 			busnr, PCI_SLOT(devfn), PCI_FUNC(devfn));
 		found = pcie_pme_from_pci_bridge(bus, 0);
 	}
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 0d8fdc48e64..2ccc9b926ea 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -203,10 +203,6 @@ static int pcie_portdrv_probe(struct pci_dev *dev,
 	     (pci_pcie_type(dev) != PCI_EXP_TYPE_DOWNSTREAM)))
 		return -ENODEV;
 
-	if (!dev->irq && dev->pin) {
-		dev_warn(&dev->dev, "device [%04x:%04x] has invalid IRQ; "
-			 "check vendor BIOS\n", dev->vendor, dev->device);
-	}
 	status = pcie_port_device_register(dev);
 	if (status)
 		return status;
@@ -397,7 +393,7 @@ static struct pci_driver pcie_portdriver = {
 static int __init dmi_pcie_pme_disable_msi(const struct dmi_system_id *d)
 {
 	pr_notice("%s detected: will not use MSI for PCIe PME signaling\n",
-			d->ident);
+		  d->ident);
 	pcie_pme_disable_msi();
 	return 0;
 }
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 2bbf5221afb..e3cf8a2e629 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -168,7 +168,7 @@ static inline unsigned long decode_bar(struct pci_dev *dev, u32 bar)
  * Returns 1 if the BAR is 64-bit, or 0 if 32-bit.
  */
 int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
-			struct resource *res, unsigned int pos)
+		    struct resource *res, unsigned int pos)
 {
 	u32 l, sz, mask;
 	u64 l64, sz64, mask64;
@@ -433,8 +433,7 @@ static void pci_read_bridge_mmio_pref(struct pci_bus *child)
 			limit |= ((unsigned long) mem_limit_hi) << 32;
 #else
 			if (mem_base_hi || mem_limit_hi) {
-				dev_err(&dev->dev, "can't handle 64-bit "
-					"address space for bridge\n");
+				dev_err(&dev->dev, "can't handle 64-bit address space for bridge\n");
 				return;
 			}
 #endif
@@ -604,7 +603,6 @@ static enum pci_bus_speed agp_speed(int agp3, int agpstat)
 	return agp_speeds[index];
 }
 
-
 static void pci_set_bus_speed(struct pci_bus *bus)
 {
 	struct pci_dev *bridge = bus->self;
@@ -636,11 +634,10 @@ static void pci_set_bus_speed(struct pci_bus *bus)
 		} else if (status & PCI_X_SSTATUS_266MHZ) {
 			max = PCI_SPEED_133MHz_PCIX_266;
 		} else if (status & PCI_X_SSTATUS_133MHZ) {
-			if ((status & PCI_X_SSTATUS_VERS) == PCI_X_SSTATUS_V2) {
+			if ((status & PCI_X_SSTATUS_VERS) == PCI_X_SSTATUS_V2)
 				max = PCI_SPEED_133MHz_PCIX_ECC;
-			} else {
+			else
 				max = PCI_SPEED_133MHz_PCIX;
-			}
 		} else {
 			max = PCI_SPEED_66MHz_PCIX;
 		}
@@ -664,7 +661,6 @@ static void pci_set_bus_speed(struct pci_bus *bus)
 	}
 }
 
-
 static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 					   struct pci_dev *bridge, int busnr)
 {
@@ -729,7 +725,8 @@ add_dev:
 	return child;
 }
 
-struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int busnr)
+struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev,
+				int busnr)
 {
 	struct pci_bus *child;
 
@@ -741,6 +738,7 @@ struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int
 	}
 	return child;
 }
+EXPORT_SYMBOL(pci_add_new_bus);
 
 /*
  * If it's a bridge, configure it and scan the bus behind it.
@@ -887,7 +885,7 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 			 * as cards with a PCI-to-PCI bridge can be
 			 * inserted later.
 			 */
-			for (i=0; i<CARDBUS_RESERVE_BUSNR; i++) {
+			for (i = 0; i < CARDBUS_RESERVE_BUSNR; i++) {
 				struct pci_bus *parent = bus;
 				if (pci_find_bus(pci_domain_nr(bus),
 							max+i+1))
@@ -934,8 +932,7 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, int pass)
 		    (child->number > bus->busn_res.end) ||
 		    (child->number < bus->number) ||
 		    (child->busn_res.end < bus->number)) {
-			dev_info(&child->dev, "%pR %s "
-				"hidden behind%s bridge %s %pR\n",
+			dev_info(&child->dev, "%pR %s hidden behind%s bridge %s %pR\n",
 				&child->busn_res,
 				(bus->number > child->busn_res.end &&
 				 bus->busn_res.end < child->number) ?
@@ -952,6 +949,7 @@ out:
 
 	return max;
 }
+EXPORT_SYMBOL(pci_scan_bridge);
 
 /*
  * Read interrupt line and base address registers.
@@ -992,7 +990,6 @@ void set_pcie_hotplug_bridge(struct pci_dev *pdev)
 		pdev->is_hotplug_bridge = 1;
 }
 
-
 /**
  * pci_ext_cfg_is_aliased - is ext config space just an alias of std config?
  * @dev: PCI device
@@ -1225,13 +1222,13 @@ int pci_setup_device(struct pci_dev *dev)
 		break;
 
 	default:				    /* unknown header */
-		dev_err(&dev->dev, "unknown header type %02x, "
-			"ignoring device\n", dev->hdr_type);
+		dev_err(&dev->dev, "unknown header type %02x, ignoring device\n",
+			dev->hdr_type);
 		return -EIO;
 
 	bad:
-		dev_err(&dev->dev, "ignoring class %#08x (doesn't match header "
-			"type %02x)\n", dev->class, dev->hdr_type);
+		dev_err(&dev->dev, "ignoring class %#08x (doesn't match header type %02x)\n",
+			dev->class, dev->hdr_type);
 		dev->class = PCI_CLASS_NOT_DEFINED;
 	}
 
@@ -1283,7 +1280,7 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus)
 EXPORT_SYMBOL(pci_alloc_dev);
 
 bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
-				 int crs_timeout)
+				int crs_timeout)
 {
 	int delay = 1;
 
@@ -1306,10 +1303,9 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
 			return false;
 		/* Card hasn't responded in 60 seconds?  Must be stuck. */
 		if (delay > crs_timeout) {
-			printk(KERN_WARNING "pci %04x:%02x:%02x.%d: not "
-					"responding\n", pci_domain_nr(bus),
-					bus->number, PCI_SLOT(devfn),
-					PCI_FUNC(devfn));
+			printk(KERN_WARNING "pci %04x:%02x:%02x.%d: not responding\n",
+			       pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
+			       PCI_FUNC(devfn));
 			return false;
 		}
 	}
@@ -1519,6 +1515,7 @@ int pci_scan_slot(struct pci_bus *bus, int devfn)
 
 	return nr;
 }
+EXPORT_SYMBOL(pci_scan_slot);
 
 static int pcie_find_smpss(struct pci_dev *dev, void *data)
 {
@@ -1613,9 +1610,7 @@ static void pcie_write_mrrs(struct pci_dev *dev)
 	}
 
 	if (mrrs < 128)
-		dev_err(&dev->dev, "MRRS was unable to be configured with a "
-			"safe value.  If problems are experienced, try running "
-			"with pci=pcie_bus_safe.\n");
+		dev_err(&dev->dev, "MRRS was unable to be configured with a safe value.  If problems are experienced, try running with pci=pcie_bus_safe\n");
 }
 
 static void pcie_bus_detect_mps(struct pci_dev *dev)
@@ -1652,8 +1647,8 @@ static int pcie_bus_configure_set(struct pci_dev *dev, void *data)
 	pcie_write_mps(dev, mps);
 	pcie_write_mrrs(dev);
 
-	dev_info(&dev->dev, "Max Payload Size set to %4d/%4d (was %4d), "
-		 "Max Read Rq %4d\n", pcie_get_mps(dev), 128 << dev->pcie_mpss,
+	dev_info(&dev->dev, "Max Payload Size set to %4d/%4d (was %4d), Max Read Rq %4d\n",
+		 pcie_get_mps(dev), 128 << dev->pcie_mpss,
 		 orig_mps, pcie_get_readrq(dev));
 
 	return 0;
@@ -1716,7 +1711,7 @@ unsigned int pci_scan_child_bus(struct pci_bus *bus)
 		bus->is_added = 1;
 	}
 
-	for (pass=0; pass < 2; pass++)
+	for (pass = 0; pass < 2; pass++)
 		list_for_each_entry(dev, &bus->devices, bus_list) {
 			if (pci_is_bridge(dev))
 				max = pci_scan_bridge(bus, dev, max, pass);
@@ -1732,6 +1727,7 @@ unsigned int pci_scan_child_bus(struct pci_bus *bus)
 	dev_dbg(&bus->dev, "bus scan returning with max=%02x\n", max);
 	return max;
 }
+EXPORT_SYMBOL_GPL(pci_scan_child_bus);
 
 /**
  * pcibios_root_bridge_prepare - Platform-specific host bridge setup.
@@ -2040,11 +2036,6 @@ unsigned int pci_rescan_bus(struct pci_bus *bus)
 }
 EXPORT_SYMBOL_GPL(pci_rescan_bus);
 
-EXPORT_SYMBOL(pci_add_new_bus);
-EXPORT_SYMBOL(pci_scan_slot);
-EXPORT_SYMBOL(pci_scan_bridge);
-EXPORT_SYMBOL_GPL(pci_scan_child_bus);
-
 /*
  * pci_rescan_bus(), pci_rescan_bus_bridge_resize() and PCI device removal
  * routines should always be executed under this mutex.
@@ -2063,7 +2054,8 @@ void pci_unlock_rescan_remove(void)
 }
 EXPORT_SYMBOL_GPL(pci_unlock_rescan_remove);
 
-static int __init pci_sort_bf_cmp(const struct device *d_a, const struct device *d_b)
+static int __init pci_sort_bf_cmp(const struct device *d_a,
+				  const struct device *d_b)
 {
 	const struct pci_dev *a = to_pci_dev(d_a);
 	const struct pci_dev *b = to_pci_dev(d_b);
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 46d1378f2e9..3f155e78513 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -17,15 +17,14 @@
 
 static int proc_initialized;	/* = 0 */
 
-static loff_t
-proc_bus_pci_lseek(struct file *file, loff_t off, int whence)
+static loff_t proc_bus_pci_lseek(struct file *file, loff_t off, int whence)
 {
 	struct pci_dev *dev = PDE_DATA(file_inode(file));
 	return fixed_size_llseek(file, off, whence, dev->cfg_size);
 }
 
-static ssize_t
-proc_bus_pci_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
+static ssize_t proc_bus_pci_read(struct file *file, char __user *buf,
+				 size_t nbytes, loff_t *ppos)
 {
 	struct pci_dev *dev = PDE_DATA(file_inode(file));
 	unsigned int pos = *ppos;
@@ -108,8 +107,8 @@ proc_bus_pci_read(struct file *file, char __user *buf, size_t nbytes, loff_t *pp
 	return nbytes;
 }
 
-static ssize_t
-proc_bus_pci_write(struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos)
+static ssize_t proc_bus_pci_write(struct file *file, const char __user *buf,
+				  size_t nbytes, loff_t *ppos)
 {
 	struct inode *ino = file_inode(file);
 	struct pci_dev *dev = PDE_DATA(ino);
@@ -413,7 +412,7 @@ int pci_proc_detach_device(struct pci_dev *dev)
 	return 0;
 }
 
-int pci_proc_detach_bus(struct pci_bus* bus)
+int pci_proc_detach_bus(struct pci_bus *bus)
 {
 	proc_remove(bus->procdir);
 	return 0;
@@ -423,6 +422,7 @@ static int proc_bus_pci_dev_open(struct inode *inode, struct file *file)
 {
 	return seq_open(file, &proc_bus_pci_devices_op);
 }
+
 static const struct file_operations proc_bus_pci_dev_operations = {
 	.owner		= THIS_MODULE,
 	.open		= proc_bus_pci_dev_open,
@@ -443,6 +443,4 @@ static int __init pci_proc_init(void)
 
 	return 0;
 }
-
 device_initcall(pci_proc_init);
-
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 92e68c7747f..ad566827b54 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -48,8 +48,8 @@ static void quirk_mellanox_tavor(struct pci_dev *dev)
 {
 	dev->broken_parity_status = 1;	/* This device gives false positives */
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR,quirk_mellanox_tavor);
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR_BRIDGE,quirk_mellanox_tavor);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX, PCI_DEVICE_ID_MELLANOX_TAVOR, quirk_mellanox_tavor);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX, PCI_DEVICE_ID_MELLANOX_TAVOR_BRIDGE, quirk_mellanox_tavor);
 
 /* Deal with broken BIOSes that neglect to enable passive release,
    which can cause problems in combination with the 82441FX/PPro MTRRs */
@@ -82,7 +82,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82441,	quirk_p
 static void quirk_isa_dma_hangs(struct pci_dev *dev)
 {
 	if (!isa_dma_bridge_buggy) {
-		isa_dma_bridge_buggy=1;
+		isa_dma_bridge_buggy = 1;
 		dev_info(&dev->dev, "Activating ISA DMA hang workarounds\n");
 	}
 }
@@ -123,7 +123,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_TGP_LPC, quirk
  */
 static void quirk_nopcipci(struct pci_dev *dev)
 {
-	if ((pci_pci_problems & PCIPCI_FAIL)==0) {
+	if ((pci_pci_problems & PCIPCI_FAIL) == 0) {
 		dev_info(&dev->dev, "Disabling direct PCI/PCI transfers\n");
 		pci_pci_problems |= PCIPCI_FAIL;
 	}
@@ -148,7 +148,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_8151_0,	quirk_nopci
  */
 static void quirk_triton(struct pci_dev *dev)
 {
-	if ((pci_pci_problems&PCIPCI_TRITON)==0) {
+	if ((pci_pci_problems&PCIPCI_TRITON) == 0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
 		pci_pci_problems |= PCIPCI_TRITON;
 	}
@@ -163,8 +163,8 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_82439TX,	quirk_
  *	Made according to a windows driver based patch by George E. Breese
  *	see PCI Latency Adjust on http://www.viahardware.com/download/viatweak.shtm
  *	and http://www.georgebreese.com/net/software/#PCI
- *      Also see http://www.au-ja.org/review-kt133a-1-en.phtml for
- *      the info on which Mr Breese based his work.
+ *	Also see http://www.au-ja.org/review-kt133a-1-en.phtml for
+ *	the info on which Mr Breese based his work.
  *
  *	Updated based on further information from the site and also on
  *	information provided by VIA
@@ -177,14 +177,14 @@ static void quirk_vialatency(struct pci_dev *dev)
 	   a buggy southbridge */
 
 	p = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C686, NULL);
-	if (p!=NULL) {
+	if (p != NULL) {
 		/* 0x40 - 0x4f == 686B, 0x10 - 0x2f == 686A; thanks Dan Hollis */
 		/* Check for buggy part revisions */
 		if (p->revision < 0x40 || p->revision > 0x42)
 			goto exit;
 	} else {
 		p = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8231, NULL);
-		if (p==NULL)	/* No problem parts */
+		if (p == NULL)	/* No problem parts */
 			goto exit;
 		/* Check for buggy part revisions */
 		if (p->revision < 0x10 || p->revision > 0x12)
@@ -227,7 +227,7 @@ DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_8361,		quirk_viala
  */
 static void quirk_viaetbf(struct pci_dev *dev)
 {
-	if ((pci_pci_problems&PCIPCI_VIAETBF)==0) {
+	if ((pci_pci_problems&PCIPCI_VIAETBF) == 0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
 		pci_pci_problems |= PCIPCI_VIAETBF;
 	}
@@ -236,7 +236,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C597_0,	quirk_via
 
 static void quirk_vsfx(struct pci_dev *dev)
 {
-	if ((pci_pci_problems&PCIPCI_VSFX)==0) {
+	if ((pci_pci_problems&PCIPCI_VSFX) == 0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
 		pci_pci_problems |= PCIPCI_VSFX;
 	}
@@ -251,7 +251,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C576,	quirk_vsfx)
  */
 static void quirk_alimagik(struct pci_dev *dev)
 {
-	if ((pci_pci_problems&PCIPCI_ALIMAGIK)==0) {
+	if ((pci_pci_problems&PCIPCI_ALIMAGIK) == 0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
 		pci_pci_problems |= PCIPCI_ALIMAGIK|PCIPCI_TRITON;
 	}
@@ -265,7 +265,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AL,	PCI_DEVICE_ID_AL_M1651,		quirk_alimagi
  */
 static void quirk_natoma(struct pci_dev *dev)
 {
-	if ((pci_pci_problems&PCIPCI_NATOMA)==0) {
+	if ((pci_pci_problems&PCIPCI_NATOMA) == 0) {
 		dev_info(&dev->dev, "Limiting direct PCI/PCI transfers\n");
 		pci_pci_problems |= PCIPCI_NATOMA;
 	}
@@ -315,8 +315,7 @@ static void quirk_cs5536_vsa(struct pci_dev *dev)
 	if (pci_resource_len(dev, 0) != 8) {
 		struct resource *res = &dev->resource[0];
 		res->end = res->start + 8 - 1;
-		dev_info(&dev->dev, "CS5536 ISA bridge bug detected "
-				"(incorrect header); workaround applied.\n");
+		dev_info(&dev->dev, "CS5536 ISA bridge bug detected (incorrect header); workaround applied\n");
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, quirk_cs5536_vsa);
@@ -400,7 +399,8 @@ static void piix4_io_quirk(struct pci_dev *dev, const char *name, unsigned int p
 	 * let's get enough confirmation reports first.
 	 */
 	base &= -size;
-	dev_info(&dev->dev, "%s PIO at %04x-%04x\n", name, base, base + size - 1);
+	dev_info(&dev->dev, "%s PIO at %04x-%04x\n", name, base,
+		 base + size - 1);
 }
 
 static void piix4_mem_quirk(struct pci_dev *dev, const char *name, unsigned int port, unsigned int enable)
@@ -425,7 +425,8 @@ static void piix4_mem_quirk(struct pci_dev *dev, const char *name, unsigned int
 	 * reserve it, but let's get enough confirmation reports first.
 	 */
 	base &= -size;
-	dev_info(&dev->dev, "%s MMIO at %04x-%04x\n", name, base, base + size - 1);
+	dev_info(&dev->dev, "%s MMIO at %04x-%04x\n", name, base,
+		 base + size - 1);
 }
 
 /*
@@ -668,8 +669,7 @@ static void quirk_xio2000a(struct pci_dev *dev)
 	struct pci_dev *pdev;
 	u16 command;
 
-	dev_warn(&dev->dev, "TI XIO2000a quirk detected; "
-		"secondary bus fast back-to-back transfers disabled\n");
+	dev_warn(&dev->dev, "TI XIO2000a quirk detected; secondary bus fast back-to-back transfers disabled\n");
 	list_for_each_entry(pdev, &dev->subordinate->devices, bus_list) {
 		pci_read_config_word(pdev, PCI_COMMAND, &command);
 		if (command & PCI_COMMAND_FAST_BACK)
@@ -703,7 +703,7 @@ static void quirk_via_ioapic(struct pci_dev *dev)
 	       tmp == 0 ? "Disa" : "Ena");
 
 	/* Offset 0x58: External APIC IRQ output control */
-	pci_write_config_byte (dev, 0x58, tmp);
+	pci_write_config_byte(dev, 0x58, tmp);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686,	quirk_via_ioapic);
 DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_VIA,	PCI_DEVICE_ID_VIA_82C686,	quirk_via_ioapic);
@@ -761,8 +761,8 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_ANY_ID,			quirk_ioapic_rmw);
 static void quirk_amd_8131_mmrbc(struct pci_dev *dev)
 {
 	if (dev->subordinate && dev->revision <= 0x12) {
-		dev_info(&dev->dev, "AMD8131 rev %x detected; "
-			"disabling PCI-X MMRBC\n", dev->revision);
+		dev_info(&dev->dev, "AMD8131 rev %x detected; disabling PCI-X MMRBC\n",
+			 dev->revision);
 		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MMRBC;
 	}
 }
@@ -916,12 +916,12 @@ static void quirk_amd_ordering(struct pci_dev *dev)
 {
 	u32 pcic;
 	pci_read_config_dword(dev, 0x4C, &pcic);
-	if ((pcic&6)!=6) {
+	if ((pcic & 6) != 6) {
 		pcic |= 6;
 		dev_warn(&dev->dev, "BIOS failed to enable PCI standards compliance; fixing this error\n");
 		pci_write_config_dword(dev, 0x4C, pcic);
 		pci_read_config_dword(dev, 0x84, &pcic);
-		pcic |= (1<<23);	/* Required in this mode */
+		pcic |= (1 << 23);	/* Required in this mode */
 		pci_write_config_dword(dev, 0x84, pcic);
 	}
 }
@@ -937,7 +937,7 @@ DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AMD,	PCI_DEVICE_ID_AMD_FE_GATE_700C
  */
 static void quirk_dunord(struct pci_dev *dev)
 {
-	struct resource *r = &dev->resource [1];
+	struct resource *r = &dev->resource[1];
 
 	r->flags |= IORESOURCE_UNSET;
 	r->start = 0;
@@ -967,11 +967,13 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TOSHIBA,	0x605,	quirk_transparent_bridge)
 static void quirk_mediagx_master(struct pci_dev *dev)
 {
 	u8 reg;
+
 	pci_read_config_byte(dev, 0x41, &reg);
 	if (reg & 2) {
 		reg &= ~2;
-		dev_info(&dev->dev, "Fixup for MediaGX/Geode Slave Disconnect Boundary (0x41=0x%02x)\n", reg);
-                pci_write_config_byte(dev, 0x41, reg);
+		dev_info(&dev->dev, "Fixup for MediaGX/Geode Slave Disconnect Boundary (0x41=0x%02x)\n",
+			 reg);
+		pci_write_config_byte(dev, 0x41, reg);
 	}
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CYRIX,	PCI_DEVICE_ID_CYRIX_PCI_MASTER, quirk_mediagx_master);
@@ -1120,7 +1122,7 @@ static void asus_hides_smbus_hostbridge(struct pci_dev *dev)
 {
 	if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_ASUSTEK)) {
 		if (dev->device == PCI_DEVICE_ID_INTEL_82845_HB)
-			switch(dev->subsystem_device) {
+			switch (dev->subsystem_device) {
 			case 0x8025: /* P4B-LX */
 			case 0x8070: /* P4B */
 			case 0x8088: /* P4B533 */
@@ -1128,14 +1130,14 @@ static void asus_hides_smbus_hostbridge(struct pci_dev *dev)
 				asus_hides_smbus = 1;
 			}
 		else if (dev->device == PCI_DEVICE_ID_INTEL_82845G_HB)
-			switch(dev->subsystem_device) {
+			switch (dev->subsystem_device) {
 			case 0x80b1: /* P4GE-V */
 			case 0x80b2: /* P4PE */
 			case 0x8093: /* P4B533-V */
 				asus_hides_smbus = 1;
 			}
 		else if (dev->device == PCI_DEVICE_ID_INTEL_82850_HB)
-			switch(dev->subsystem_device) {
+			switch (dev->subsystem_device) {
 			case 0x8030: /* P4T533 */
 				asus_hides_smbus = 1;
 			}
@@ -1175,7 +1177,7 @@ static void asus_hides_smbus_hostbridge(struct pci_dev *dev)
 			}
 	} else if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_HP)) {
 		if (dev->device ==  PCI_DEVICE_ID_INTEL_82855PM_HB)
-			switch(dev->subsystem_device) {
+			switch (dev->subsystem_device) {
 			case 0x088C: /* HP Compaq nc8000 */
 			case 0x0890: /* HP Compaq nc6000 */
 				asus_hides_smbus = 1;
@@ -1192,20 +1194,20 @@ static void asus_hides_smbus_hostbridge(struct pci_dev *dev)
 			case 0x12bf: /* HP xw4100 */
 				asus_hides_smbus = 1;
 			}
-       } else if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_SAMSUNG)) {
-               if (dev->device ==  PCI_DEVICE_ID_INTEL_82855PM_HB)
-                       switch(dev->subsystem_device) {
-                       case 0xC00C: /* Samsung P35 notebook */
-                               asus_hides_smbus = 1;
-                       }
+	} else if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_SAMSUNG)) {
+		if (dev->device ==  PCI_DEVICE_ID_INTEL_82855PM_HB)
+			switch (dev->subsystem_device) {
+			case 0xC00C: /* Samsung P35 notebook */
+				asus_hides_smbus = 1;
+		}
 	} else if (unlikely(dev->subsystem_vendor == PCI_VENDOR_ID_COMPAQ)) {
 		if (dev->device == PCI_DEVICE_ID_INTEL_82855PM_HB)
-			switch(dev->subsystem_device) {
+			switch (dev->subsystem_device) {
 			case 0x0058: /* Compaq Evo N620c */
 				asus_hides_smbus = 1;
 			}
 		else if (dev->device == PCI_DEVICE_ID_INTEL_82810_IG3)
-			switch(dev->subsystem_device) {
+			switch (dev->subsystem_device) {
 			case 0xB16C: /* Compaq Deskpro EP 401963-001 (PCA# 010174) */
 				/* Motherboard doesn't have Host bridge
 				 * subvendor/subdevice IDs, therefore checking
@@ -1213,7 +1215,7 @@ static void asus_hides_smbus_hostbridge(struct pci_dev *dev)
 				asus_hides_smbus = 1;
 			}
 		else if (dev->device == PCI_DEVICE_ID_INTEL_82801DB_2)
-			switch(dev->subsystem_device) {
+			switch (dev->subsystem_device) {
 			case 0x00b8: /* Compaq Evo D510 CMT */
 			case 0x00b9: /* Compaq Evo D510 SFF */
 			case 0x00ba: /* Compaq Evo D510 USDT */
@@ -1261,7 +1263,8 @@ static void asus_hides_smbus_lpc(struct pci_dev *dev)
 		pci_write_config_word(dev, 0xF2, val & (~0x8));
 		pci_read_config_word(dev, 0xF2, &val);
 		if (val & 0x8)
-			dev_info(&dev->dev, "i801 SMBus device continues to play 'hide and seek'! 0x%x\n", val);
+			dev_info(&dev->dev, "i801 SMBus device continues to play 'hide and seek'! 0x%x\n",
+				 val);
 		else
 			dev_info(&dev->dev, "Enabled i801 SMBus device\n");
 	}
@@ -1409,7 +1412,8 @@ static void asus_hides_ac97_lpc(struct pci_dev *dev)
 		pci_write_config_byte(dev, 0x50, val & (~0xc0));
 		pci_read_config_byte(dev, 0x50, &val);
 		if (val & 0xc0)
-			dev_info(&dev->dev, "Onboard AC97/MC97 devices continue to play 'hide and seek'! 0x%x\n", val);
+			dev_info(&dev->dev, "Onboard AC97/MC97 devices continue to play 'hide and seek'! 0x%x\n",
+				 val);
 		else
 			dev_info(&dev->dev, "Enabled onboard AC97/MC97 devices\n");
 	}
@@ -1514,10 +1518,8 @@ static void quirk_alder_ioapic(struct pci_dev *pdev)
 
 	/* The next five BARs all seem to be rubbish, so just clean
 	 * them out */
-	for (i=1; i < 6; i++) {
+	for (i = 1; i < 6; i++)
 		memset(&pdev->resource[i], 0, sizeof(pdev->resource[i]));
-	}
-
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_EESSC,	quirk_alder_ioapic);
 #endif
@@ -1552,7 +1554,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHV,	quirk_pci
  * Some Intel PCI Express chipsets have trouble with downstream
  * device power management.
  */
-static void quirk_intel_pcie_pm(struct pci_dev * dev)
+static void quirk_intel_pcie_pm(struct pci_dev *dev)
 {
 	pci_pm_d3_delay = 120;
 	dev->no_d1d2 = 1;
@@ -1721,8 +1723,8 @@ static void quirk_disable_amd_8111_boot_interrupt(struct pci_dev *dev)
 
 	pci_read_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, &pci_config_word);
 	if (!pci_config_word) {
-		dev_info(&dev->dev, "boot interrupts on device [%04x:%04x] "
-			 "already disabled\n", dev->vendor, dev->device);
+		dev_info(&dev->dev, "boot interrupts on device [%04x:%04x] already disabled\n",
+			 dev->vendor, dev->device);
 		return;
 	}
 	pci_write_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, 0);
@@ -1770,8 +1772,7 @@ static void quirk_plx_pci9050(struct pci_dev *dev)
 		if (pci_resource_len(dev, bar) == 0x80 &&
 		    (pci_resource_start(dev, bar) & 0x80)) {
 			struct resource *r = &dev->resource[bar];
-			dev_info(&dev->dev,
-				 "Re-allocating PLX PCI 9050 BAR %u to length 256 to avoid bit 7 bug\n",
+			dev_info(&dev->dev, "Re-allocating PLX PCI 9050 BAR %u to length 256 to avoid bit 7 bug\n",
 				 bar);
 			r->flags |= IORESOURCE_UNSET;
 			r->start = 0;
@@ -1818,9 +1819,7 @@ static void quirk_netmos(struct pci_dev *dev)
 	case PCI_DEVICE_ID_NETMOS_9845:
 	case PCI_DEVICE_ID_NETMOS_9855:
 		if (num_parallel) {
-			dev_info(&dev->dev, "Netmos %04x (%u parallel, "
-				"%u serial); changing class SERIAL to OTHER "
-				"(use parport_serial)\n",
+			dev_info(&dev->dev, "Netmos %04x (%u parallel, %u serial); changing class SERIAL to OTHER (use parport_serial)\n",
 				dev->device, num_parallel, num_serial);
 			dev->class = (PCI_CLASS_COMMUNICATION_OTHER << 8) |
 			    (dev->class & 0xff);
@@ -1887,8 +1886,7 @@ static void quirk_e100_interrupt(struct pci_dev *dev)
 
 	cmd_hi = readb(csr + 3);
 	if (cmd_hi == 0) {
-		dev_warn(&dev->dev, "Firmware left e100 interrupts enabled; "
-			"disabling\n");
+		dev_warn(&dev->dev, "Firmware left e100 interrupts enabled; disabling\n");
 		writeb(1, csr + 3);
 	}
 
@@ -1958,8 +1956,7 @@ static void quirk_nvidia_ck804_pcie_aer_ext_cap(struct pci_dev *dev)
 	if (pci_read_config_byte(dev, 0xf41, &b) == 0) {
 		if (!(b & 0x20)) {
 			pci_write_config_byte(dev, 0xf41, b | 0x20);
-			dev_info(&dev->dev,
-			       "Linking AER extended capability\n");
+			dev_info(&dev->dev, "Linking AER extended capability\n");
 		}
 	}
 }
@@ -1997,8 +1994,7 @@ static void quirk_via_cx700_pci_parking_caching(struct pci_dev *dev)
 			/* Turn off PCI Bus Parking */
 			pci_write_config_byte(dev, 0x76, b ^ 0x40);
 
-			dev_info(&dev->dev,
-				"Disabling VIA CX700 PCI parking\n");
+			dev_info(&dev->dev, "Disabling VIA CX700 PCI parking\n");
 		}
 	}
 
@@ -2013,8 +2009,7 @@ static void quirk_via_cx700_pci_parking_caching(struct pci_dev *dev)
 			/* Disable "Read FIFO Timer" */
 			pci_write_config_byte(dev, 0x77, 0x0);
 
-			dev_info(&dev->dev,
-				"Disabling VIA CX700 PCI caching\n");
+			dev_info(&dev->dev, "Disabling VIA CX700 PCI caching\n");
 		}
 	}
 }
@@ -2149,8 +2144,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8380_0, quirk_disab
 static void quirk_disable_msi(struct pci_dev *dev)
 {
 	if (dev->subordinate) {
-		dev_warn(&dev->dev, "MSI quirk detected; "
-			"subordinate MSI disabled\n");
+		dev_warn(&dev->dev, "MSI quirk detected; subordinate MSI disabled\n");
 		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
 	}
 }
@@ -2189,8 +2183,7 @@ static int msi_ht_cap_enabled(struct pci_dev *dev)
 		u8 flags;
 
 		if (pci_read_config_byte(dev, pos + HT_MSI_FLAGS,
-					 &flags) == 0)
-		{
+					 &flags) == 0) {
 			dev_info(&dev->dev, "Found %s HT MSI Mapping\n",
 				flags & HT_MSI_FLAGS_ENABLE ?
 				"enabled" : "disabled");
@@ -2207,8 +2200,7 @@ static int msi_ht_cap_enabled(struct pci_dev *dev)
 static void quirk_msi_ht_cap(struct pci_dev *dev)
 {
 	if (dev->subordinate && !msi_ht_cap_enabled(dev)) {
-		dev_warn(&dev->dev, "MSI quirk detected; "
-			"subordinate MSI disabled\n");
+		dev_warn(&dev->dev, "MSI quirk detected; subordinate MSI disabled\n");
 		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
 	}
 }
@@ -2232,8 +2224,7 @@ static void quirk_nvidia_ck804_msi_ht_cap(struct pci_dev *dev)
 	if (!pdev)
 		return;
 	if (!msi_ht_cap_enabled(dev) && !msi_ht_cap_enabled(pdev)) {
-		dev_warn(&dev->dev, "MSI quirk detected; "
-			"subordinate MSI disabled\n");
+		dev_warn(&dev->dev, "MSI quirk detected; subordinate MSI disabled\n");
 		dev->subordinate->bus_flags |= PCI_BUS_FLAGS_NO_MSI;
 	}
 	pci_dev_put(pdev);
@@ -2279,8 +2270,7 @@ static void nvenet_msi_disable(struct pci_dev *dev)
 	if (board_name &&
 	    (strstr(board_name, "P5N32-SLI PREMIUM") ||
 	     strstr(board_name, "P5N32-E SLI"))) {
-		dev_info(&dev->dev,
-			 "Disabling msi for MCP55 NIC on P5N32-SLI\n");
+		dev_info(&dev->dev, "Disabling msi for MCP55 NIC on P5N32-SLI\n");
 		dev->no_msi = 1;
 	}
 }
@@ -2489,8 +2479,7 @@ static void __nv_msi_ht_cap_quirk(struct pci_dev *dev, int all)
 	 */
 	host_bridge = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
 	if (host_bridge == NULL) {
-		dev_warn(&dev->dev,
-			 "nv_msi_ht_cap_quirk didn't locate host bridge\n");
+		dev_warn(&dev->dev, "nv_msi_ht_cap_quirk didn't locate host bridge\n");
 		return;
 	}
 
@@ -2817,8 +2806,7 @@ static void quirk_intel_mc_errata(struct pci_dev *dev)
 	 */
 	err = pci_read_config_word(dev, 0x48, &rcc);
 	if (err) {
-		dev_err(&dev->dev, "Error attempting to read the read "
-			"completion coalescing register.\n");
+		dev_err(&dev->dev, "Error attempting to read the read completion coalescing register\n");
 		return;
 	}
 
@@ -2829,13 +2817,11 @@ static void quirk_intel_mc_errata(struct pci_dev *dev)
 
 	err = pci_write_config_word(dev, 0x48, rcc);
 	if (err) {
-		dev_err(&dev->dev, "Error attempting to write the read "
-			"completion coalescing register.\n");
+		dev_err(&dev->dev, "Error attempting to write the read completion coalescing register\n");
 		return;
 	}
 
-	pr_info_once("Read completion coalescing disabled due to hardware "
-		     "errata relating to 256B MPS.\n");
+	pr_info_once("Read completion coalescing disabled due to hardware errata relating to 256B MPS\n");
 }
 /* Intel 5000 series memory controllers and ports 2-7 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x25c0, quirk_intel_mc_errata);
@@ -2944,8 +2930,7 @@ static void disable_igfx_irq(struct pci_dev *dev)
 
 	/* Check if any interrupt line is still enabled */
 	if (readl(regs + I915_DEIER_REG) != 0) {
-		dev_warn(&dev->dev, "BIOS left Intel GPU interrupts enabled; "
-			"disabling\n");
+		dev_warn(&dev->dev, "BIOS left Intel GPU interrupts enabled; disabling\n");
 
 		writel(0, regs + I915_DEIER_REG);
 	}
@@ -3040,7 +3025,7 @@ void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev)
 {
 	struct pci_fixup *start, *end;
 
-	switch(pass) {
+	switch (pass) {
 	case pci_fixup_early:
 		start = __start_pci_fixups_early;
 		end = __end_pci_fixups_early;
@@ -3112,8 +3097,8 @@ static int __init pci_apply_final_quirks(void)
 			if (!tmp || cls == tmp)
 				continue;
 
-			printk(KERN_DEBUG "PCI: CLS mismatch (%u != %u), "
-			       "using %u bytes\n", cls << 2, tmp << 2,
+			printk(KERN_DEBUG "PCI: CLS mismatch (%u != %u), using %u bytes\n",
+			       cls << 2, tmp << 2,
 			       pci_dfl_cache_line_size << 2);
 			pci_cache_line_size = pci_dfl_cache_line_size;
 		}
@@ -3342,6 +3327,87 @@ int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 	return -ENOTTY;
 }
 
+static void quirk_dma_func0_alias(struct pci_dev *dev)
+{
+	if (PCI_FUNC(dev->devfn) != 0) {
+		dev->dma_alias_devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0);
+		dev->dev_flags |= PCI_DEV_FLAGS_DMA_ALIAS_DEVFN;
+	}
+}
+
+/*
+ * https://bugzilla.redhat.com/show_bug.cgi?id=605888
+ *
+ * Some Ricoh devices use function 0 as the PCIe requester ID for DMA.
+ */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_RICOH, 0xe832, quirk_dma_func0_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_RICOH, 0xe476, quirk_dma_func0_alias);
+
+static void quirk_dma_func1_alias(struct pci_dev *dev)
+{
+	if (PCI_FUNC(dev->devfn) != 1) {
+		dev->dma_alias_devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 1);
+		dev->dev_flags |= PCI_DEV_FLAGS_DMA_ALIAS_DEVFN;
+	}
+}
+
+/*
+ * Marvell 88SE9123 uses function 1 as the requester ID for DMA.  In some
+ * SKUs function 1 is present and is a legacy IDE controller, in other
+ * SKUs this function is not present, making this a ghost requester.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=42679
+ */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9123,
+			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c14 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9130,
+			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c47 + c57 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9172,
+			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c59 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x917a,
+			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c46 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0,
+			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c49 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9230,
+			 quirk_dma_func1_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TTI, 0x0642,
+			 quirk_dma_func1_alias);
+/* https://bugs.gentoo.org/show_bug.cgi?id=497630 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_JMICRON,
+			 PCI_DEVICE_ID_JMICRON_JMB388_ESD,
+			 quirk_dma_func1_alias);
+
+/*
+ * A few PCIe-to-PCI bridges fail to expose a PCIe capability, resulting in
+ * using the wrong DMA alias for the device.  Some of these devices can be
+ * used as either forward or reverse bridges, so we need to test whether the
+ * device is operating in the correct mode.  We could probably apply this
+ * quirk to PCI_ANY_ID, but for now we'll just use known offenders.  The test
+ * is for a non-root, non-PCIe bridge where the upstream device is PCIe and
+ * is not a PCIe-to-PCI bridge, then @pdev is actually a PCIe-to-PCI bridge.
+ */
+static void quirk_use_pcie_bridge_dma_alias(struct pci_dev *pdev)
+{
+	if (!pci_is_root_bus(pdev->bus) &&
+	    pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE &&
+	    !pci_is_pcie(pdev) && pci_is_pcie(pdev->bus->self) &&
+	    pci_pcie_type(pdev->bus->self) != PCI_EXP_TYPE_PCI_BRIDGE)
+		pdev->dev_flags |= PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS;
+}
+/* ASM1083/1085, https://bugzilla.kernel.org/show_bug.cgi?id=44881#c46 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ASMEDIA, 0x1080,
+			 quirk_use_pcie_bridge_dma_alias);
+/* Tundra 8113, https://bugzilla.kernel.org/show_bug.cgi?id=44881#c43 */
+DECLARE_PCI_FIXUP_HEADER(0x10e3, 0x8113, quirk_use_pcie_bridge_dma_alias);
+/* ITE 8892, https://bugzilla.kernel.org/show_bug.cgi?id=73551 */
+DECLARE_PCI_FIXUP_HEADER(0x1283, 0x8892, quirk_use_pcie_bridge_dma_alias);
+/* Intel 82801, https://bugzilla.kernel.org/show_bug.cgi?id=44881#c49 */
+DECLARE_PCI_FIXUP_HEADER(0x8086, 0x244e, quirk_use_pcie_bridge_dma_alias);
+
 static struct pci_dev *pci_func_0_dma_source(struct pci_dev *dev)
 {
 	if (!PCI_FUNC(dev->devfn))
diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index c1839450d4d..f955edb9bea 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -38,6 +38,7 @@ int pci_enable_rom(struct pci_dev *pdev)
 	pci_write_config_dword(pdev, pdev->rom_base_reg, rom_addr);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pci_enable_rom);
 
 /**
  * pci_disable_rom - disable ROM decoding for a PCI device
@@ -53,6 +54,7 @@ void pci_disable_rom(struct pci_dev *pdev)
 	rom_addr &= ~PCI_ROM_ADDRESS_ENABLE;
 	pci_write_config_dword(pdev, pdev->rom_base_reg, rom_addr);
 }
+EXPORT_SYMBOL_GPL(pci_disable_rom);
 
 /**
  * pci_get_rom_size - obtain the actual size of the ROM image
@@ -135,7 +137,7 @@ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size)
 		} else {
 			/* assign the ROM an address if it doesn't have one */
 			if (res->parent == NULL &&
-			    pci_assign_resource(pdev,PCI_ROM_RESOURCE))
+			    pci_assign_resource(pdev, PCI_ROM_RESOURCE))
 				return NULL;
 			start = pci_resource_start(pdev, PCI_ROM_RESOURCE);
 			*size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
@@ -166,6 +168,7 @@ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size)
 	*size = pci_get_rom_size(pdev, rom, *size);
 	return rom;
 }
+EXPORT_SYMBOL(pci_map_rom);
 
 /**
  * pci_unmap_rom - unmap the ROM from kernel space
@@ -187,6 +190,7 @@ void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom)
 	if (!(res->flags & (IORESOURCE_ROM_ENABLE | IORESOURCE_ROM_SHADOW)))
 		pci_disable_rom(pdev);
 }
+EXPORT_SYMBOL(pci_unmap_rom);
 
 /**
  * pci_cleanup_rom - free the ROM copy created by pci_map_rom_copy
@@ -199,7 +203,7 @@ void pci_cleanup_rom(struct pci_dev *pdev)
 	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
 
 	if (res->flags & IORESOURCE_ROM_COPY) {
-		kfree((void*)(unsigned long)res->start);
+		kfree((void *)(unsigned long)res->start);
 		res->flags |= IORESOURCE_UNSET;
 		res->flags &= ~IORESOURCE_ROM_COPY;
 		res->start = 0;
@@ -222,9 +226,4 @@ void __iomem *pci_platform_rom(struct pci_dev *pdev, size_t *size)
 
 	return NULL;
 }
-
-EXPORT_SYMBOL(pci_map_rom);
-EXPORT_SYMBOL(pci_unmap_rom);
-EXPORT_SYMBOL_GPL(pci_enable_rom);
-EXPORT_SYMBOL_GPL(pci_disable_rom);
 EXPORT_SYMBOL(pci_platform_rom);
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index 8e495bda678..827ad831f1d 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -17,14 +17,100 @@ DECLARE_RWSEM(pci_bus_sem);
 EXPORT_SYMBOL_GPL(pci_bus_sem);
 
 /*
+ * pci_for_each_dma_alias - Iterate over DMA aliases for a device
+ * @pdev: starting downstream device
+ * @fn: function to call for each alias
+ * @data: opaque data to pass to @fn
+ *
+ * Starting @pdev, walk up the bus calling @fn for each possible alias
+ * of @pdev at the root bus.
+ */
+int pci_for_each_dma_alias(struct pci_dev *pdev,
+			   int (*fn)(struct pci_dev *pdev,
+				     u16 alias, void *data), void *data)
+{
+	struct pci_bus *bus;
+	int ret;
+
+	ret = fn(pdev, PCI_DEVID(pdev->bus->number, pdev->devfn), data);
+	if (ret)
+		return ret;
+
+	/*
+	 * If the device is broken and uses an alias requester ID for
+	 * DMA, iterate over that too.
+	 */
+	if (unlikely(pdev->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN)) {
+		ret = fn(pdev, PCI_DEVID(pdev->bus->number,
+					 pdev->dma_alias_devfn), data);
+		if (ret)
+			return ret;
+	}
+
+	for (bus = pdev->bus; !pci_is_root_bus(bus); bus = bus->parent) {
+		struct pci_dev *tmp;
+
+		/* Skip virtual buses */
+		if (!bus->self)
+			continue;
+
+		tmp = bus->self;
+
+		/*
+		 * PCIe-to-PCI/X bridges alias transactions from downstream
+		 * devices using the subordinate bus number (PCI Express to
+		 * PCI/PCI-X Bridge Spec, rev 1.0, sec 2.3).  For all cases
+		 * where the upstream bus is PCI/X we alias to the bridge
+		 * (there are various conditions in the previous reference
+		 * where the bridge may take ownership of transactions, even
+		 * when the secondary interface is PCI-X).
+		 */
+		if (pci_is_pcie(tmp)) {
+			switch (pci_pcie_type(tmp)) {
+			case PCI_EXP_TYPE_ROOT_PORT:
+			case PCI_EXP_TYPE_UPSTREAM:
+			case PCI_EXP_TYPE_DOWNSTREAM:
+				continue;
+			case PCI_EXP_TYPE_PCI_BRIDGE:
+				ret = fn(tmp,
+					 PCI_DEVID(tmp->subordinate->number,
+						   PCI_DEVFN(0, 0)), data);
+				if (ret)
+					return ret;
+				continue;
+			case PCI_EXP_TYPE_PCIE_BRIDGE:
+				ret = fn(tmp,
+					 PCI_DEVID(tmp->bus->number,
+						   tmp->devfn), data);
+				if (ret)
+					return ret;
+				continue;
+			}
+		} else {
+			if (tmp->dev_flags & PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS)
+				ret = fn(tmp,
+					 PCI_DEVID(tmp->subordinate->number,
+						   PCI_DEVFN(0, 0)), data);
+			else
+				ret = fn(tmp,
+					 PCI_DEVID(tmp->bus->number,
+						   tmp->devfn), data);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+/*
  * find the upstream PCIe-to-PCI bridge of a PCI device
  * if the device is PCIE, return NULL
  * if the device isn't connected to a PCIe bridge (that is its parent is a
  * legacy PCI bridge and the bridge is directly connected to bus 0), return its
  * parent
  */
-struct pci_dev *
-pci_find_upstream_pcie_bridge(struct pci_dev *pdev)
+struct pci_dev *pci_find_upstream_pcie_bridge(struct pci_dev *pdev)
 {
 	struct pci_dev *tmp = NULL;
 
@@ -56,12 +142,12 @@ static struct pci_bus *pci_do_find_bus(struct pci_bus *bus, unsigned char busnr)
 	struct pci_bus *child;
 	struct pci_bus *tmp;
 
-	if(bus->number == busnr)
+	if (bus->number == busnr)
 		return bus;
 
 	list_for_each_entry(tmp, &bus->children, node) {
 		child = pci_do_find_bus(tmp, busnr);
-		if(child)
+		if (child)
 			return child;
 	}
 	return NULL;
@@ -76,7 +162,7 @@ static struct pci_bus *pci_do_find_bus(struct pci_bus *bus, unsigned char busnr)
  * in the global list of PCI buses.  If the bus is found, a pointer to its
  * data structure is returned.  If no bus is found, %NULL is returned.
  */
-struct pci_bus * pci_find_bus(int domain, int busnr)
+struct pci_bus *pci_find_bus(int domain, int busnr)
 {
 	struct pci_bus *bus = NULL;
 	struct pci_bus *tmp_bus;
@@ -90,6 +176,7 @@ struct pci_bus * pci_find_bus(int domain, int busnr)
 	}
 	return NULL;
 }
+EXPORT_SYMBOL(pci_find_bus);
 
 /**
  * pci_find_next_bus - begin or continue searching for a PCI bus
@@ -100,8 +187,7 @@ struct pci_bus * pci_find_bus(int domain, int busnr)
  * @from is not %NULL, searches continue from next device on the
  * global list.
  */
-struct pci_bus *
-pci_find_next_bus(const struct pci_bus *from)
+struct pci_bus *pci_find_next_bus(const struct pci_bus *from)
 {
 	struct list_head *n;
 	struct pci_bus *b = NULL;
@@ -114,6 +200,7 @@ pci_find_next_bus(const struct pci_bus *from)
 	up_read(&pci_bus_sem);
 	return b;
 }
+EXPORT_SYMBOL(pci_find_next_bus);
 
 /**
  * pci_get_slot - locate PCI device for a given PCI slot
@@ -147,6 +234,7 @@ struct pci_dev *pci_get_slot(struct pci_bus *bus, unsigned int devfn)
 	up_read(&pci_bus_sem);
 	return dev;
 }
+EXPORT_SYMBOL(pci_get_slot);
 
 /**
  * pci_get_domain_bus_and_slot - locate PCI device for a given PCI domain (segment), bus, and slot
@@ -251,6 +339,7 @@ struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device,
 
 	return pci_get_dev_by_id(&id, from);
 }
+EXPORT_SYMBOL(pci_get_subsys);
 
 /**
  * pci_get_device - begin or continue searching for a PCI device by vendor/device id
@@ -266,11 +355,12 @@ struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device,
  * from next device on the global list.  The reference count for @from is
  * always decremented if it is not %NULL.
  */
-struct pci_dev *
-pci_get_device(unsigned int vendor, unsigned int device, struct pci_dev *from)
+struct pci_dev *pci_get_device(unsigned int vendor, unsigned int device,
+			       struct pci_dev *from)
 {
 	return pci_get_subsys(vendor, device, PCI_ANY_ID, PCI_ANY_ID, from);
 }
+EXPORT_SYMBOL(pci_get_device);
 
 /**
  * pci_get_class - begin or continue searching for a PCI device by class
@@ -299,6 +389,7 @@ struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from)
 
 	return pci_get_dev_by_id(&id, from);
 }
+EXPORT_SYMBOL(pci_get_class);
 
 /**
  * pci_dev_present - Returns 1 if device matching the device list is present, 0 if not.
@@ -328,12 +419,3 @@ int pci_dev_present(const struct pci_device_id *ids)
 	return 0;
 }
 EXPORT_SYMBOL(pci_dev_present);
-
-/* For boot time work */
-EXPORT_SYMBOL(pci_find_bus);
-EXPORT_SYMBOL(pci_find_next_bus);
-/* For everyone */
-EXPORT_SYMBOL(pci_get_device);
-EXPORT_SYMBOL(pci_get_subsys);
-EXPORT_SYMBOL(pci_get_slot);
-EXPORT_SYMBOL(pci_get_class);
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index fd9b545c3cf..6373985ad3f 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -68,7 +68,7 @@ static int add_to_list(struct list_head *head,
 
 	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
 	if (!tmp) {
-		pr_warning("add_to_list: kmalloc() failed!\n");
+		pr_warn("add_to_list: kmalloc() failed!\n");
 		return -ENOMEM;
 	}
 
@@ -148,8 +148,7 @@ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head)
 
 		tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
 		if (!tmp)
-			panic("pdev_sort_resources(): "
-			      "kmalloc() failed!\n");
+			panic("pdev_sort_resources(): kmalloc() failed!\n");
 		tmp->res = r;
 		tmp->dev = dev;
 
@@ -736,7 +735,7 @@ static resource_size_t calculate_iosize(resource_size_t size,
 {
 	if (size < min_size)
 		size = min_size;
-	if (old_size == 1 )
+	if (old_size == 1)
 		old_size = 0;
 	/* To be fixed in 2.5: we should have sort of HAVE_ISA
 	   flag in the struct pci_bus. */
@@ -757,7 +756,7 @@ static resource_size_t calculate_memsize(resource_size_t size,
 {
 	if (size < min_size)
 		size = min_size;
-	if (old_size == 1 )
+	if (old_size == 1)
 		old_size = 0;
 	if (size < old_size)
 		size = old_size;
@@ -859,9 +858,8 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
 			resource_size(b_res), min_align);
 	if (!size0 && !size1) {
 		if (b_res->start || b_res->end)
-			dev_info(&bus->self->dev, "disabling bridge window "
-				 "%pR to %pR (unused)\n", b_res,
-				 &bus->busn_res);
+			dev_info(&bus->self->dev, "disabling bridge window %pR to %pR (unused)\n",
+				 b_res, &bus->busn_res);
 		b_res->flags = 0;
 		return;
 	}
@@ -872,10 +870,9 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
 	if (size1 > size0 && realloc_head) {
 		add_to_list(realloc_head, bus->self, b_res, size1-size0,
 			    min_align);
-		dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window "
-				 "%pR to %pR add_size %llx\n", b_res,
-				 &bus->busn_res,
-				 (unsigned long long)size1-size0);
+		dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window %pR to %pR add_size %llx\n",
+			   b_res, &bus->busn_res,
+			   (unsigned long long)size1-size0);
 	}
 }
 
@@ -928,7 +925,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 {
 	struct pci_dev *dev;
 	resource_size_t min_align, align, size, size0, size1;
-	resource_size_t aligns[14];	/* Alignments from 1Mb to 8Gb */
+	resource_size_t aligns[18];	/* Alignments from 1Mb to 128Gb */
 	int order, max_order;
 	struct resource *b_res = find_free_bus_resource(bus,
 					mask | IORESOURCE_PREFETCH, type);
@@ -974,9 +971,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 			if (order < 0)
 				order = 0;
 			if (order >= ARRAY_SIZE(aligns)) {
-				dev_warn(&dev->dev, "disabling BAR %d: %pR "
-					 "(bad alignment %#llx)\n", i, r,
-					 (unsigned long long) align);
+				dev_warn(&dev->dev, "disabling BAR %d: %pR (bad alignment %#llx)\n",
+					 i, r, (unsigned long long) align);
 				r->flags = 0;
 				continue;
 			}
@@ -1003,9 +999,8 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 				resource_size(b_res), min_align);
 	if (!size0 && !size1) {
 		if (b_res->start || b_res->end)
-			dev_info(&bus->self->dev, "disabling bridge window "
-				 "%pR to %pR (unused)\n", b_res,
-				 &bus->busn_res);
+			dev_info(&bus->self->dev, "disabling bridge window %pR to %pR (unused)\n",
+				 b_res, &bus->busn_res);
 		b_res->flags = 0;
 		return 0;
 	}
@@ -1014,9 +1009,9 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 	b_res->flags |= IORESOURCE_STARTALIGN;
 	if (size1 > size0 && realloc_head) {
 		add_to_list(realloc_head, bus->self, b_res, size1-size0, min_align);
-		dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window "
-				 "%pR to %pR add_size %llx\n", b_res,
-				 &bus->busn_res, (unsigned long long)size1-size0);
+		dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window %pR to %pR add_size %llx\n",
+			   b_res, &bus->busn_res,
+			   (unsigned long long)size1-size0);
 	}
 	return 0;
 }
@@ -1274,8 +1269,8 @@ void __pci_bus_assign_resources(const struct pci_bus *bus,
 			break;
 
 		default:
-			dev_info(&dev->dev, "not setting up bridge for bus "
-				 "%04x:%02x\n", pci_domain_nr(b), b->number);
+			dev_info(&dev->dev, "not setting up bridge for bus %04x:%02x\n",
+				 pci_domain_nr(b), b->number);
 			break;
 		}
 	}
@@ -1312,8 +1307,8 @@ static void __pci_bridge_assign_resources(const struct pci_dev *bridge,
 		break;
 
 	default:
-		dev_info(&bridge->dev, "not setting up bridge for bus "
-			 "%04x:%02x\n", pci_domain_nr(b), b->number);
+		dev_info(&bridge->dev, "not setting up bridge for bus %04x:%02x\n",
+			 pci_domain_nr(b), b->number);
 		break;
 	}
 }
@@ -1430,10 +1425,10 @@ static void pci_bus_dump_res(struct pci_bus *bus)
 
 	pci_bus_for_each_resource(bus, res, i) {
 		if (!res || !res->end || !res->flags)
-                        continue;
+			continue;
 
 		dev_printk(KERN_DEBUG, &bus->dev, "resource %d %pR\n", i, res);
-        }
+	}
 }
 
 static void pci_bus_dump_resources(struct pci_bus *bus)
@@ -1458,7 +1453,7 @@ static int pci_bus_get_depth(struct pci_bus *bus)
 	int depth = 0;
 	struct pci_bus *child_bus;
 
-	list_for_each_entry(child_bus, &bus->children, node){
+	list_for_each_entry(child_bus, &bus->children, node) {
 		int ret;
 
 		ret = pci_bus_get_depth(child_bus);
diff --git a/drivers/pci/setup-irq.c b/drivers/pci/setup-irq.c
index dbc4ffcf42d..4e2d595d50c 100644
--- a/drivers/pci/setup-irq.c
+++ b/drivers/pci/setup-irq.c
@@ -22,10 +22,9 @@ void __weak pcibios_update_irq(struct pci_dev *dev, int irq)
 	pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
 }
 
-static void
-pdev_fixup_irq(struct pci_dev *dev,
-	       u8 (*swizzle)(struct pci_dev *, u8 *),
-	       int (*map_irq)(const struct pci_dev *, u8, u8))
+static void pdev_fixup_irq(struct pci_dev *dev,
+			   u8 (*swizzle)(struct pci_dev *, u8 *),
+			   int (*map_irq)(const struct pci_dev *, u8, u8))
 {
 	u8 pin, slot;
 	int irq = 0;
@@ -58,11 +57,11 @@ pdev_fixup_irq(struct pci_dev *dev,
 	pcibios_update_irq(dev, irq);
 }
 
-void
-pci_fixup_irqs(u8 (*swizzle)(struct pci_dev *, u8 *),
-	       int (*map_irq)(const struct pci_dev *, u8, u8))
+void pci_fixup_irqs(u8 (*swizzle)(struct pci_dev *, u8 *),
+		    int (*map_irq)(const struct pci_dev *, u8, u8))
 {
 	struct pci_dev *dev = NULL;
+
 	for_each_pci_dev(dev)
 		pdev_fixup_irq(dev, swizzle, map_irq);
 }
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 33f9e32d94d..b7c3a5ea1fc 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -96,8 +96,8 @@ void pci_update_resource(struct pci_dev *dev, int resno)
 		pci_write_config_dword(dev, reg + 4, new);
 		pci_read_config_dword(dev, reg + 4, &check);
 		if (check != new) {
-			dev_err(&dev->dev, "BAR %d: error updating "
-			       "(high %#08x != %#08x)\n", resno, new, check);
+			dev_err(&dev->dev, "BAR %d: error updating (high %#08x != %#08x)\n",
+				resno, new, check);
 		}
 	}
 
@@ -166,11 +166,10 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
 {
 	struct resource *root, *conflict;
 	resource_size_t fw_addr, start, end;
-	int ret = 0;
 
 	fw_addr = pcibios_retrieve_fw_addr(dev, resno);
 	if (!fw_addr)
-		return 1;
+		return -ENOMEM;
 
 	start = res->start;
 	end = res->end;
@@ -189,14 +188,13 @@ static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev,
 		 resno, res);
 	conflict = request_resource_conflict(root, res);
 	if (conflict) {
-		dev_info(&dev->dev,
-			 "BAR %d: %pR conflicts with %s %pR\n", resno,
-			 res, conflict->name, conflict);
+		dev_info(&dev->dev, "BAR %d: %pR conflicts with %s %pR\n",
+			 resno, res, conflict->name, conflict);
 		res->start = start;
 		res->end = end;
-		ret = 1;
+		return -EBUSY;
 	}
-	return ret;
+	return 0;
 }
 
 static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
@@ -250,10 +248,8 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
 static int _pci_assign_resource(struct pci_dev *dev, int resno,
 				resource_size_t size, resource_size_t min_align)
 {
-	struct resource *res = dev->resource + resno;
 	struct pci_bus *bus;
 	int ret;
-	char *type;
 
 	bus = dev->bus;
 	while ((ret = __pci_assign_resource(bus, dev, resno, size, min_align))) {
@@ -262,21 +258,6 @@ static int _pci_assign_resource(struct pci_dev *dev, int resno,
 		bus = bus->parent;
 	}
 
-	if (ret) {
-		if (res->flags & IORESOURCE_MEM)
-			if (res->flags & IORESOURCE_PREFETCH)
-				type = "mem pref";
-			else
-				type = "mem";
-		else if (res->flags & IORESOURCE_IO)
-			type = "io";
-		else
-			type = "unknown";
-		dev_info(&dev->dev,
-			 "BAR %d: can't assign %s (size %#llx)\n",
-			 resno, type, (unsigned long long) resource_size(res));
-	}
-
 	return ret;
 }
 
@@ -289,8 +270,8 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
 	res->flags |= IORESOURCE_UNSET;
 	align = pci_resource_alignment(dev, res);
 	if (!align) {
-		dev_info(&dev->dev, "BAR %d: can't assign %pR "
-			 "(bogus alignment)\n", resno, res);
+		dev_info(&dev->dev, "BAR %d: can't assign %pR (bogus alignment)\n",
+			 resno, res);
 		return -EINVAL;
 	}
 
@@ -302,44 +283,61 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
 	 * where firmware left it.  That at least has a chance of
 	 * working, which is better than just leaving it disabled.
 	 */
-	if (ret < 0)
+	if (ret < 0) {
+		dev_info(&dev->dev, "BAR %d: no space for %pR\n", resno, res);
 		ret = pci_revert_fw_address(res, dev, resno, size);
+	}
 
-	if (!ret) {
-		res->flags &= ~IORESOURCE_UNSET;
-		res->flags &= ~IORESOURCE_STARTALIGN;
-		dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res);
-		if (resno < PCI_BRIDGE_RESOURCES)
-			pci_update_resource(dev, resno);
+	if (ret < 0) {
+		dev_info(&dev->dev, "BAR %d: failed to assign %pR\n", resno,
+			 res);
+		return ret;
 	}
-	return ret;
+
+	res->flags &= ~IORESOURCE_UNSET;
+	res->flags &= ~IORESOURCE_STARTALIGN;
+	dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res);
+	if (resno < PCI_BRIDGE_RESOURCES)
+		pci_update_resource(dev, resno);
+
+	return 0;
 }
+EXPORT_SYMBOL(pci_assign_resource);
 
 int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsize,
 			resource_size_t min_align)
 {
 	struct resource *res = dev->resource + resno;
+	unsigned long flags;
 	resource_size_t new_size;
 	int ret;
 
+	flags = res->flags;
 	res->flags |= IORESOURCE_UNSET;
 	if (!res->parent) {
-		dev_info(&dev->dev, "BAR %d: can't reassign an unassigned resource %pR "
-			 "\n", resno, res);
+		dev_info(&dev->dev, "BAR %d: can't reassign an unassigned resource %pR\n",
+			 resno, res);
 		return -EINVAL;
 	}
 
 	/* already aligned with min_align */
 	new_size = resource_size(res) + addsize;
 	ret = _pci_assign_resource(dev, resno, new_size, min_align);
-	if (!ret) {
-		res->flags &= ~IORESOURCE_UNSET;
-		res->flags &= ~IORESOURCE_STARTALIGN;
-		dev_info(&dev->dev, "BAR %d: reassigned %pR\n", resno, res);
-		if (resno < PCI_BRIDGE_RESOURCES)
-			pci_update_resource(dev, resno);
+	if (ret) {
+		res->flags = flags;
+		dev_info(&dev->dev, "BAR %d: %pR (failed to expand by %#llx)\n",
+			 resno, res, (unsigned long long) addsize);
+		return ret;
 	}
-	return ret;
+
+	res->flags &= ~IORESOURCE_UNSET;
+	res->flags &= ~IORESOURCE_STARTALIGN;
+	dev_info(&dev->dev, "BAR %d: reassigned %pR (expanded by %#llx)\n",
+		 resno, res, (unsigned long long) addsize);
+	if (resno < PCI_BRIDGE_RESOURCES)
+		pci_update_resource(dev, resno);
+
+	return 0;
 }
 
 int pci_enable_resources(struct pci_dev *dev, int mask)
diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c
index 24750a1b39b..b91c4da6836 100644
--- a/drivers/pci/syscall.c
+++ b/drivers/pci/syscall.c
@@ -99,7 +99,7 @@ SYSCALL_DEFINE5(pciconfig_write, unsigned long, bus, unsigned long, dfn,
 	if (!dev)
 		return -ENODEV;
 
-	switch(len) {
+	switch (len) {
 	case 1:
 		err = get_user(byte, (u8 __user *)buf);
 		if (err)
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 16a2f067c24..64b98d242ea 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -112,6 +112,7 @@ config PHY_EXYNOS5250_SATA
 config PHY_SUN4I_USB
 	tristate "Allwinner sunxi SoC USB PHY driver"
 	depends on ARCH_SUNXI && HAS_IOMEM && OF
+	depends on RESET_CONTROLLER
 	select GENERIC_PHY
 	help
 	  Enable this to support the transceiver that is part of Allwinner
@@ -122,6 +123,7 @@ config PHY_SUN4I_USB
 
 config PHY_SAMSUNG_USB2
 	tristate "Samsung USB 2.0 PHY driver"
+	depends on HAS_IOMEM
 	select GENERIC_PHY
 	select MFD_SYSCON
 	help
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index c64a2f3b2d6..49c44653010 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -614,8 +614,9 @@ struct phy *phy_create(struct device *dev, const struct phy_ops *ops,
 	return phy;
 
 put_dev:
-	put_device(&phy->dev);
-	ida_remove(&phy_ida, phy->id);
+	put_device(&phy->dev);  /* calls phy_release() which frees resources */
+	return ERR_PTR(ret);
+
 free_phy:
 	kfree(phy);
 	return ERR_PTR(ret);
@@ -799,7 +800,7 @@ static void phy_release(struct device *dev)
 
 	phy = to_phy(dev);
 	dev_vdbg(dev, "releasing '%s'\n", dev_name(dev));
-	ida_remove(&phy_ida, phy->id);
+	ida_simple_remove(&phy_ida, phy->id);
 	kfree(phy);
 }
 
diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index 7007c11fe07..34b396146c8 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -233,8 +233,8 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	if (phy_data->flags & OMAP_USB2_CALIBRATE_FALSE_DISCONNECT) {
 		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 		phy->phy_base = devm_ioremap_resource(&pdev->dev, res);
-		if (!phy->phy_base)
-			return -ENOMEM;
+		if (IS_ERR(phy->phy_base))
+			return PTR_ERR(phy->phy_base);
 		phy->flags |= OMAP_USB2_CALIBRATE_FALSE_DISCONNECT;
 	}
 
@@ -262,7 +262,6 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	otg->phy		= &phy->phy;
 
 	platform_set_drvdata(pdev, phy);
-	pm_runtime_enable(phy->dev);
 
 	generic_phy = devm_phy_create(phy->dev, &ops, NULL);
 	if (IS_ERR(generic_phy))
@@ -270,10 +269,13 @@ static int omap_usb2_probe(struct platform_device *pdev)
 
 	phy_set_drvdata(generic_phy, phy);
 
+	pm_runtime_enable(phy->dev);
 	phy_provider = devm_of_phy_provider_register(phy->dev,
 			of_phy_simple_xlate);
-	if (IS_ERR(phy_provider))
+	if (IS_ERR(phy_provider)) {
+		pm_runtime_disable(phy->dev);
 		return PTR_ERR(phy_provider);
+	}
 
 	phy->wkupclk = devm_clk_get(phy->dev, "wkupclk");
 	if (IS_ERR(phy->wkupclk)) {
@@ -317,6 +319,7 @@ static int omap_usb2_remove(struct platform_device *pdev)
 	if (!IS_ERR(phy->optclk))
 		clk_unprepare(phy->optclk);
 	usb_remove_phy(&phy->phy);
+	pm_runtime_disable(phy->dev);
 
 	return 0;
 }
diff --git a/drivers/phy/phy-samsung-usb2.c b/drivers/phy/phy-samsung-usb2.c
index 8a8c6bc8709..1e69a32c221 100644
--- a/drivers/phy/phy-samsung-usb2.c
+++ b/drivers/phy/phy-samsung-usb2.c
@@ -107,6 +107,7 @@ static const struct of_device_id samsung_usb2_phy_of_match[] = {
 #endif
 	{ },
 };
+MODULE_DEVICE_TABLE(of, samsung_usb2_phy_of_match);
 
 static int samsung_usb2_phy_probe(struct platform_device *pdev)
 {
diff --git a/drivers/pinctrl/berlin/berlin.c b/drivers/pinctrl/berlin/berlin.c
index edf5d2fd2b2..86db2235ab0 100644
--- a/drivers/pinctrl/berlin/berlin.c
+++ b/drivers/pinctrl/berlin/berlin.c
@@ -320,7 +320,7 @@ int berlin_pinctrl_probe(struct platform_device *pdev,
 
 	regmap = dev_get_regmap(&pdev->dev, NULL);
 	if (!regmap)
-		return PTR_ERR(regmap);
+		return -ENODEV;
 
 	pctrl = devm_kzalloc(dev, sizeof(*pctrl), GFP_KERNEL);
 	if (!pctrl)
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index 1bd6363bc95..9f43916637c 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -1431,7 +1431,7 @@ static void st_gpio_irqmux_handler(unsigned irq, struct irq_desc *desc)
 
 	status = readl(info->irqmux_base);
 
-	for_each_set_bit(n, &status, ST_GPIO_PINS_PER_BANK)
+	for_each_set_bit(n, &status, info->nbanks)
 		__gpio_irq_handler(&info->banks[n]);
 
 	chained_irq_exit(chip, desc);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index f1ca75e6d7b..5f38c7f6783 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -211,6 +211,10 @@ static int sunxi_pctrl_dt_node_to_map(struct pinctrl_dev *pctldev,
 			configlen++;
 
 		pinconfig = kzalloc(configlen * sizeof(*pinconfig), GFP_KERNEL);
+		if (!pinconfig) {
+			kfree(*map);
+			return -ENOMEM;
+		}
 
 		if (!of_property_read_u32(node, "allwinner,drive", &val)) {
 			u16 strength = (val + 1) * 10;
diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c
index 7f3aad0e115..7f1a2e2711b 100644
--- a/drivers/platform/chrome/chromeos_laptop.c
+++ b/drivers/platform/chrome/chromeos_laptop.c
@@ -84,21 +84,19 @@ static struct i2c_board_info tsl2563_als_device = {
 	I2C_BOARD_INFO("tsl2563", TAOS_ALS_I2C_ADDR),
 };
 
+static int mxt_t19_keys[] = {
+	KEY_RESERVED,
+	KEY_RESERVED,
+	KEY_RESERVED,
+	KEY_RESERVED,
+	KEY_RESERVED,
+	BTN_LEFT
+};
+
 static struct mxt_platform_data atmel_224s_tp_platform_data = {
-	.x_line			= 18,
-	.y_line			= 12,
-	.x_size			= 102*20,
-	.y_size			= 68*20,
-	.blen			= 0x80,	/* Gain setting is in upper 4 bits */
-	.threshold		= 0x32,
-	.voltage		= 0,	/* 3.3V */
-	.orient			= MXT_VERTICAL_FLIP,
 	.irqflags		= IRQF_TRIGGER_FALLING,
-	.is_tp			= true,
-	.key_map		= { KEY_RESERVED,
-				    KEY_RESERVED,
-				    KEY_RESERVED,
-				    BTN_LEFT },
+	.t19_num_keys		= ARRAY_SIZE(mxt_t19_keys),
+	.t19_keymap		= mxt_t19_keys,
 	.config			= NULL,
 	.config_length		= 0,
 };
@@ -110,16 +108,7 @@ static struct i2c_board_info atmel_224s_tp_device = {
 };
 
 static struct mxt_platform_data atmel_1664s_platform_data = {
-	.x_line			= 32,
-	.y_line			= 50,
-	.x_size			= 1700,
-	.y_size			= 2560,
-	.blen			= 0x89,	/* Gain setting is in upper 4 bits */
-	.threshold		= 0x28,
-	.voltage		= 0,	/* 3.3V */
-	.orient			= MXT_ROTATED_90_COUNTER,
 	.irqflags		= IRQF_TRIGGER_FALLING,
-	.is_tp			= false,
 	.config			= NULL,
 	.config_length		= 0,
 };
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 27df2c533b0..172f26ce59a 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -102,7 +102,7 @@ config DELL_LAPTOP
 	default n
 	---help---
 	This driver adds support for rfkill and backlight control to Dell
-	laptops.
+	laptops (except for some models covered by the Compal driver).
 
 config DELL_WMI
 	tristate "Dell WMI extras"
@@ -127,6 +127,16 @@ config DELL_WMI_AIO
 	  To compile this driver as a module, choose M here: the module will
 	  be called dell-wmi-aio.
 
+config DELL_SMO8800
+	tristate "Dell Latitude freefall driver (ACPI SMO8800/SMO8810)"
+	depends on ACPI
+	---help---
+	  Say Y here if you want to support SMO8800/SMO8810 freefall device
+	  on Dell Latitude laptops.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called dell-smo8800.
+
 
 config FUJITSU_LAPTOP
 	tristate "Fujitsu Laptop Extras"
@@ -265,23 +275,21 @@ config PANASONIC_LAPTOP
 	  R2, R3, R5, T2, W2 and Y2 series), say Y.
 
 config COMPAL_LAPTOP
-	tristate "Compal Laptop Extras"
+	tristate "Compal (and others) Laptop Extras"
 	depends on ACPI
 	depends on BACKLIGHT_CLASS_DEVICE
 	depends on RFKILL
 	depends on HWMON
 	depends on POWER_SUPPLY
 	---help---
-	  This is a driver for laptops built by Compal:
-
-	  Compal FL90/IFL90
-	  Compal FL91/IFL91
-	  Compal FL92/JFL92
-	  Compal FT00/IFT00
+	  This is a driver for laptops built by Compal, and some models by
+	  other brands (e.g. Dell, Toshiba).
 
-	  It adds support for Bluetooth, WLAN and LCD brightness control.
+	  It adds support for rfkill, Bluetooth, WLAN and LCD brightness
+	  control.
 
-	  If you have an Compal FL9x/IFL9x/FT00 laptop, say Y or M here.
+	  For a (possibly incomplete) list of supported laptops, please refer
+	  to: Documentation/platform/x86-laptop-drivers.txt
 
 config SONY_LAPTOP
 	tristate "Sony Laptop Extras"
@@ -724,7 +732,7 @@ config IBM_RTL
 
 config XO1_RFKILL
 	tristate "OLPC XO-1 software RF kill switch"
-	depends on OLPC
+	depends on OLPC || COMPILE_TEST
 	depends on RFKILL
 	---help---
 	  Support for enabling/disabling the WLAN interface on the OLPC XO-1
@@ -732,6 +740,7 @@ config XO1_RFKILL
 
 config XO15_EBOOK
 	tristate "OLPC XO-1.5 ebook switch"
+	depends on OLPC || COMPILE_TEST
 	depends on ACPI && INPUT
 	---help---
 	  Support for the ebook switch on the OLPC XO-1.5 laptop.
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index 1a2eafc9d48..c4ca428fd3d 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_COMPAL_LAPTOP)	+= compal-laptop.o
 obj-$(CONFIG_DELL_LAPTOP)	+= dell-laptop.o
 obj-$(CONFIG_DELL_WMI)		+= dell-wmi.o
 obj-$(CONFIG_DELL_WMI_AIO)	+= dell-wmi-aio.o
+obj-$(CONFIG_DELL_SMO8800)	+= dell-smo8800.o
 obj-$(CONFIG_ACER_WMI)		+= acer-wmi.o
 obj-$(CONFIG_ACERHDF)		+= acerhdf.o
 obj-$(CONFIG_HP_ACCEL)		+= hp_accel.o
diff --git a/drivers/platform/x86/alienware-wmi.c b/drivers/platform/x86/alienware-wmi.c
index 541f9514f76..297b6640213 100644
--- a/drivers/platform/x86/alienware-wmi.c
+++ b/drivers/platform/x86/alienware-wmi.c
@@ -32,6 +32,7 @@
 #define WMAX_METHOD_HDMI_STATUS		0x2
 #define WMAX_METHOD_BRIGHTNESS		0x3
 #define WMAX_METHOD_ZONE_CONTROL	0x4
+#define WMAX_METHOD_HDMI_CABLE		0x5
 
 MODULE_AUTHOR("Mario Limonciello <mario_limonciello@dell.com>");
 MODULE_DESCRIPTION("Alienware special feature control");
@@ -350,12 +351,11 @@ static int alienware_zone_init(struct platform_device *dev)
 	char *name;
 
 	if (interface == WMAX) {
-		global_led.max_brightness = 100;
 		lighting_control_state = WMAX_RUNNING;
 	} else if (interface == LEGACY) {
-		global_led.max_brightness = 0x0F;
 		lighting_control_state = LEGACY_RUNNING;
 	}
+	global_led.max_brightness = 0x0F;
 	global_brightness = global_led.max_brightness;
 
 	/*
@@ -423,41 +423,85 @@ static void alienware_zone_exit(struct platform_device *dev)
 	The HDMI mux sysfs node indicates the status of the HDMI input mux.
 	It can toggle between standard system GPU output and HDMI input.
 */
-static ssize_t show_hdmi(struct device *dev, struct device_attribute *attr,
-			 char *buf)
+static acpi_status alienware_hdmi_command(struct hdmi_args *in_args,
+					  u32 command, int *out_data)
 {
 	acpi_status status;
-	struct acpi_buffer input;
 	union acpi_object *obj;
-	u32 tmp = 0;
-	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_buffer input;
+	struct acpi_buffer output;
+
+	input.length = (acpi_size) sizeof(*in_args);
+	input.pointer = in_args;
+	if (out_data != NULL) {
+		output.length = ACPI_ALLOCATE_BUFFER;
+		output.pointer = NULL;
+		status = wmi_evaluate_method(WMAX_CONTROL_GUID, 1,
+					     command, &input, &output);
+	} else
+		status = wmi_evaluate_method(WMAX_CONTROL_GUID, 1,
+					     command, &input, NULL);
+
+	if (ACPI_SUCCESS(status) && out_data != NULL) {
+		obj = (union acpi_object *)output.pointer;
+		if (obj && obj->type == ACPI_TYPE_INTEGER)
+			*out_data = (u32) obj->integer.value;
+	}
+	return status;
+
+}
+
+static ssize_t show_hdmi_cable(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	acpi_status status;
+	u32 out_data;
 	struct hdmi_args in_args = {
 		.arg = 0,
 	};
-	input.length = (acpi_size) sizeof(in_args);
-	input.pointer = &in_args;
-	status = wmi_evaluate_method(WMAX_CONTROL_GUID, 1,
-				     WMAX_METHOD_HDMI_STATUS, &input, &output);
+	status =
+	    alienware_hdmi_command(&in_args, WMAX_METHOD_HDMI_CABLE,
+				   (u32 *) &out_data);
+	if (ACPI_SUCCESS(status)) {
+		if (out_data == 0)
+			return scnprintf(buf, PAGE_SIZE,
+					 "[unconnected] connected unknown\n");
+		else if (out_data == 1)
+			return scnprintf(buf, PAGE_SIZE,
+					 "unconnected [connected] unknown\n");
+	}
+	pr_err("alienware-wmi: unknown HDMI cable status: %d\n", status);
+	return scnprintf(buf, PAGE_SIZE, "unconnected connected [unknown]\n");
+}
+
+static ssize_t show_hdmi_source(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	acpi_status status;
+	u32 out_data;
+	struct hdmi_args in_args = {
+		.arg = 0,
+	};
+	status =
+	    alienware_hdmi_command(&in_args, WMAX_METHOD_HDMI_STATUS,
+				   (u32 *) &out_data);
 
 	if (ACPI_SUCCESS(status)) {
-		obj = (union acpi_object *)output.pointer;
-		if (obj && obj->type == ACPI_TYPE_INTEGER)
-			tmp = (u32) obj->integer.value;
-		if (tmp == 1)
+		if (out_data == 1)
 			return scnprintf(buf, PAGE_SIZE,
 					 "[input] gpu unknown\n");
-		else if (tmp == 2)
+		else if (out_data == 2)
 			return scnprintf(buf, PAGE_SIZE,
 					 "input [gpu] unknown\n");
 	}
-	pr_err("alienware-wmi: unknown HDMI status: %d\n", status);
+	pr_err("alienware-wmi: unknown HDMI source status: %d\n", out_data);
 	return scnprintf(buf, PAGE_SIZE, "input gpu [unknown]\n");
 }
 
-static ssize_t toggle_hdmi(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t toggle_hdmi_source(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
 {
-	struct acpi_buffer input;
 	acpi_status status;
 	struct hdmi_args args;
 	if (strcmp(buf, "gpu\n") == 0)
@@ -467,33 +511,46 @@ static ssize_t toggle_hdmi(struct device *dev, struct device_attribute *attr,
 	else
 		args.arg = 3;
 	pr_debug("alienware-wmi: setting hdmi to %d : %s", args.arg, buf);
-	input.length = (acpi_size) sizeof(args);
-	input.pointer = &args;
-	status = wmi_evaluate_method(WMAX_CONTROL_GUID, 1,
-				     WMAX_METHOD_HDMI_SOURCE, &input, NULL);
+
+	status = alienware_hdmi_command(&args, WMAX_METHOD_HDMI_SOURCE, NULL);
+
 	if (ACPI_FAILURE(status))
 		pr_err("alienware-wmi: HDMI toggle failed: results: %u\n",
 		       status);
 	return count;
 }
 
-static DEVICE_ATTR(hdmi, S_IRUGO | S_IWUSR, show_hdmi, toggle_hdmi);
+static DEVICE_ATTR(cable, S_IRUGO, show_hdmi_cable, NULL);
+static DEVICE_ATTR(source, S_IRUGO | S_IWUSR, show_hdmi_source,
+		   toggle_hdmi_source);
+
+static struct attribute *hdmi_attrs[] = {
+	&dev_attr_cable.attr,
+	&dev_attr_source.attr,
+	NULL,
+};
 
-static void remove_hdmi(struct platform_device *device)
+static struct attribute_group hdmi_attribute_group = {
+	.name = "hdmi",
+	.attrs = hdmi_attrs,
+};
+
+static void remove_hdmi(struct platform_device *dev)
 {
-	device_remove_file(&device->dev, &dev_attr_hdmi);
+	sysfs_remove_group(&dev->dev.kobj, &hdmi_attribute_group);
 }
 
-static int create_hdmi(void)
+static int create_hdmi(struct platform_device *dev)
 {
-	int ret = -ENOMEM;
-	ret = device_create_file(&platform_device->dev, &dev_attr_hdmi);
+	int ret;
+
+	ret = sysfs_create_group(&dev->dev.kobj, &hdmi_attribute_group);
 	if (ret)
 		goto error_create_hdmi;
 	return 0;
 
 error_create_hdmi:
-	remove_hdmi(platform_device);
+	remove_hdmi(dev);
 	return ret;
 }
 
@@ -527,7 +584,7 @@ static int __init alienware_wmi_init(void)
 		goto fail_platform_device2;
 
 	if (interface == WMAX) {
-		ret = create_hdmi();
+		ret = create_hdmi(platform_device);
 		if (ret)
 			goto fail_prep_hdmi;
 	}
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 563f59efa66..ddf0eefd862 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -137,6 +137,15 @@ static struct dmi_system_id asus_quirks[] = {
 	},
 	{
 		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. X550CA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X550CA"),
+		},
+		.driver_data = &quirk_asus_x401u,
+	},
+	{
+		.callback = dmi_matched,
 		.ident = "ASUSTeK COMPUTER INC. X55A",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 91ef69a5226..3c6ccedc82b 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -266,7 +266,7 @@ static int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1,
 	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
 	acpi_status status;
 	union acpi_object *obj;
-	u32 tmp;
+	u32 tmp = 0;
 
 	status = wmi_evaluate_method(ASUS_WMI_MGMT_GUID, 1, method_id,
 				     &input, &output);
@@ -277,8 +277,6 @@ static int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1,
 	obj = (union acpi_object *)output.pointer;
 	if (obj && obj->type == ACPI_TYPE_INTEGER)
 		tmp = (u32) obj->integer.value;
-	else
-		tmp = 0;
 
 	if (retval)
 		*retval = tmp;
diff --git a/drivers/platform/x86/dell-smo8800.c b/drivers/platform/x86/dell-smo8800.c
new file mode 100644
index 00000000000..a653716055d
--- /dev/null
+++ b/drivers/platform/x86/dell-smo8800.c
@@ -0,0 +1,233 @@
+/*
+ *  dell-smo8800.c - Dell Latitude ACPI SMO8800/SMO8810 freefall sensor driver
+ *
+ *  Copyright (C) 2012 Sonal Santan <sonal.santan@gmail.com>
+ *  Copyright (C) 2014 Pali Rohár <pali.rohar@gmail.com>
+ *
+ *  This is loosely based on lis3lv02d driver.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ */
+
+#define DRIVER_NAME "smo8800"
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/acpi.h>
+#include <linux/interrupt.h>
+#include <linux/miscdevice.h>
+
+struct smo8800_device {
+	u32 irq;                     /* acpi device irq */
+	atomic_t counter;            /* count after last read */
+	struct miscdevice miscdev;   /* for /dev/freefall */
+	unsigned long misc_opened;   /* whether the device is open */
+	wait_queue_head_t misc_wait; /* Wait queue for the misc dev */
+	struct device *dev;          /* acpi device */
+};
+
+static irqreturn_t smo8800_interrupt_quick(int irq, void *data)
+{
+	struct smo8800_device *smo8800 = data;
+
+	atomic_inc(&smo8800->counter);
+	wake_up_interruptible(&smo8800->misc_wait);
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t smo8800_interrupt_thread(int irq, void *data)
+{
+	struct smo8800_device *smo8800 = data;
+
+	dev_info(smo8800->dev, "detected free fall\n");
+	return IRQ_HANDLED;
+}
+
+static acpi_status smo8800_get_resource(struct acpi_resource *resource,
+					void *context)
+{
+	struct acpi_resource_extended_irq *irq;
+
+	if (resource->type != ACPI_RESOURCE_TYPE_EXTENDED_IRQ)
+		return AE_OK;
+
+	irq = &resource->data.extended_irq;
+	if (!irq || !irq->interrupt_count)
+		return AE_OK;
+
+	*((u32 *)context) = irq->interrupts[0];
+	return AE_CTRL_TERMINATE;
+}
+
+static u32 smo8800_get_irq(struct acpi_device *device)
+{
+	u32 irq = 0;
+	acpi_status status;
+
+	status = acpi_walk_resources(device->handle, METHOD_NAME__CRS,
+				     smo8800_get_resource, &irq);
+	if (ACPI_FAILURE(status)) {
+		dev_err(&device->dev, "acpi_walk_resources failed\n");
+		return 0;
+	}
+
+	return irq;
+}
+
+static ssize_t smo8800_misc_read(struct file *file, char __user *buf,
+				 size_t count, loff_t *pos)
+{
+	struct smo8800_device *smo8800 = container_of(file->private_data,
+					 struct smo8800_device, miscdev);
+
+	u32 data = 0;
+	unsigned char byte_data = 0;
+	ssize_t retval = 1;
+
+	if (count < 1)
+		return -EINVAL;
+
+	atomic_set(&smo8800->counter, 0);
+	retval = wait_event_interruptible(smo8800->misc_wait,
+				(data = atomic_xchg(&smo8800->counter, 0)));
+
+	if (retval)
+		return retval;
+
+	byte_data = 1;
+	retval = 1;
+
+	if (data < 255)
+		byte_data = data;
+	else
+		byte_data = 255;
+
+	if (put_user(byte_data, buf))
+		retval = -EFAULT;
+
+	return retval;
+}
+
+static int smo8800_misc_open(struct inode *inode, struct file *file)
+{
+	struct smo8800_device *smo8800 = container_of(file->private_data,
+					 struct smo8800_device, miscdev);
+
+	if (test_and_set_bit(0, &smo8800->misc_opened))
+		return -EBUSY; /* already open */
+
+	atomic_set(&smo8800->counter, 0);
+	return 0;
+}
+
+static int smo8800_misc_release(struct inode *inode, struct file *file)
+{
+	struct smo8800_device *smo8800 = container_of(file->private_data,
+					 struct smo8800_device, miscdev);
+
+	clear_bit(0, &smo8800->misc_opened); /* release the device */
+	return 0;
+}
+
+static const struct file_operations smo8800_misc_fops = {
+	.owner = THIS_MODULE,
+	.read = smo8800_misc_read,
+	.open = smo8800_misc_open,
+	.release = smo8800_misc_release,
+};
+
+static int smo8800_add(struct acpi_device *device)
+{
+	int err;
+	struct smo8800_device *smo8800;
+
+	smo8800 = devm_kzalloc(&device->dev, sizeof(*smo8800), GFP_KERNEL);
+	if (!smo8800) {
+		dev_err(&device->dev, "failed to allocate device data\n");
+		return -ENOMEM;
+	}
+
+	smo8800->dev = &device->dev;
+	smo8800->miscdev.minor = MISC_DYNAMIC_MINOR;
+	smo8800->miscdev.name = "freefall";
+	smo8800->miscdev.fops = &smo8800_misc_fops;
+
+	init_waitqueue_head(&smo8800->misc_wait);
+
+	err = misc_register(&smo8800->miscdev);
+	if (err) {
+		dev_err(&device->dev, "failed to register misc dev: %d\n", err);
+		return err;
+	}
+
+	device->driver_data = smo8800;
+
+	smo8800->irq = smo8800_get_irq(device);
+	if (!smo8800->irq) {
+		dev_err(&device->dev, "failed to obtain IRQ\n");
+		err = -EINVAL;
+		goto error;
+	}
+
+	err = request_threaded_irq(smo8800->irq, smo8800_interrupt_quick,
+				   smo8800_interrupt_thread,
+				   IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+				   DRIVER_NAME, smo8800);
+	if (err) {
+		dev_err(&device->dev,
+			"failed to request thread for IRQ %d: %d\n",
+			smo8800->irq, err);
+		goto error;
+	}
+
+	dev_dbg(&device->dev, "device /dev/freefall registered with IRQ %d\n",
+		 smo8800->irq);
+	return 0;
+
+error:
+	misc_deregister(&smo8800->miscdev);
+	return err;
+}
+
+static int smo8800_remove(struct acpi_device *device)
+{
+	struct smo8800_device *smo8800 = device->driver_data;
+
+	free_irq(smo8800->irq, smo8800);
+	misc_deregister(&smo8800->miscdev);
+	dev_dbg(&device->dev, "device /dev/freefall unregistered\n");
+	return 0;
+}
+
+static const struct acpi_device_id smo8800_ids[] = {
+	{ "SMO8800", 0 },
+	{ "SMO8810", 0 },
+	{ "", 0 },
+};
+
+MODULE_DEVICE_TABLE(acpi, smo8800_ids);
+
+static struct acpi_driver smo8800_driver = {
+	.name = DRIVER_NAME,
+	.class = "Latitude",
+	.ids = smo8800_ids,
+	.ops = {
+		.add = smo8800_add,
+		.remove = smo8800_remove,
+	},
+	.owner = THIS_MODULE,
+};
+
+module_acpi_driver(smo8800_driver);
+
+MODULE_DESCRIPTION("Dell Latitude freefall driver (ACPI SMO8800/SMO8810)");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sonal Santan, Pali Rohár");
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 8ba8956b5a4..484a8673b83 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -53,6 +53,7 @@ MODULE_ALIAS("wmi:5FB7F034-2C63-45e9-BE91-3D44E2C707E4");
 #define HPWMI_ALS_QUERY 0x3
 #define HPWMI_HARDWARE_QUERY 0x4
 #define HPWMI_WIRELESS_QUERY 0x5
+#define HPWMI_BIOS_QUERY 0x9
 #define HPWMI_HOTKEY_QUERY 0xc
 #define HPWMI_FEATURE_QUERY 0xd
 #define HPWMI_WIRELESS2_QUERY 0x1b
@@ -144,6 +145,7 @@ static const struct key_entry hp_wmi_keymap[] = {
 	{ KE_KEY, 0x2142, { KEY_MEDIA } },
 	{ KE_KEY, 0x213b, { KEY_INFO } },
 	{ KE_KEY, 0x2169, { KEY_DIRECTION } },
+	{ KE_KEY, 0x216a, { KEY_SETUP } },
 	{ KE_KEY, 0x231b, { KEY_HELP } },
 	{ KE_END, 0 }
 };
@@ -304,6 +306,19 @@ static int hp_wmi_bios_2009_later(void)
 	return (state & 0x10) ? 1 : 0;
 }
 
+static int hp_wmi_enable_hotkeys(void)
+{
+	int ret;
+	int query = 0x6e;
+
+	ret = hp_wmi_perform_query(HPWMI_BIOS_QUERY, 1, &query, sizeof(query),
+				   0);
+
+	if (ret)
+		return -EINVAL;
+	return 0;
+}
+
 static int hp_wmi_set_block(void *data, bool blocked)
 {
 	enum hp_wmi_radio r = (enum hp_wmi_radio) data;
@@ -648,6 +663,9 @@ static int __init hp_wmi_input_setup(void)
 			    hp_wmi_tablet_state());
 	input_sync(hp_wmi_input_dev);
 
+	if (hp_wmi_bios_2009_later() == 4)
+		hp_wmi_enable_hotkeys();
+
 	status = wmi_install_notify_handler(HPWMI_EVENT_GUID, hp_wmi_notify, NULL);
 	if (ACPI_FAILURE(status)) {
 		err = -EIO;
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 6dd060a0bb6..b4c495a62ee 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -36,6 +36,8 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/i8042.h>
+#include <linux/dmi.h>
+#include <linux/device.h>
 
 #define IDEAPAD_RFKILL_DEV_NUM	(3)
 
@@ -819,6 +821,19 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data)
 	}
 }
 
+/* Blacklist for devices where the ideapad rfkill interface does not work */
+static struct dmi_system_id rfkill_blacklist[] = {
+	/* The Lenovo Yoga 2 11 always reports everything as blocked */
+	{
+		.ident = "Lenovo Yoga 2 11",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Yoga 2 11"),
+		},
+	},
+	{}
+};
+
 static int ideapad_acpi_add(struct platform_device *pdev)
 {
 	int ret, i;
@@ -833,7 +848,7 @@ static int ideapad_acpi_add(struct platform_device *pdev)
 	if (read_method_int(adev->handle, "_CFG", &cfg))
 		return -ENODEV;
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
@@ -844,7 +859,7 @@ static int ideapad_acpi_add(struct platform_device *pdev)
 
 	ret = ideapad_sysfs_init(priv);
 	if (ret)
-		goto sysfs_failed;
+		return ret;
 
 	ret = ideapad_debugfs_init(priv);
 	if (ret)
@@ -854,11 +869,10 @@ static int ideapad_acpi_add(struct platform_device *pdev)
 	if (ret)
 		goto input_failed;
 
-	for (i = 0; i < IDEAPAD_RFKILL_DEV_NUM; i++) {
-		if (test_bit(ideapad_rfk_data[i].cfgbit, &priv->cfg))
-			ideapad_register_rfkill(priv, i);
-		else
-			priv->rfk[i] = NULL;
+	if (!dmi_check_system(rfkill_blacklist)) {
+		for (i = 0; i < IDEAPAD_RFKILL_DEV_NUM; i++)
+			if (test_bit(ideapad_rfk_data[i].cfgbit, &priv->cfg))
+				ideapad_register_rfkill(priv, i);
 	}
 	ideapad_sync_rfk_state(priv);
 	ideapad_sync_touchpad_state(priv);
@@ -884,8 +898,6 @@ input_failed:
 	ideapad_debugfs_exit(priv);
 debugfs_failed:
 	ideapad_sysfs_exit(priv);
-sysfs_failed:
-	kfree(priv);
 	return ret;
 }
 
@@ -903,7 +915,6 @@ static int ideapad_acpi_remove(struct platform_device *pdev)
 	ideapad_debugfs_exit(priv);
 	ideapad_sysfs_exit(priv);
 	dev_set_drvdata(&pdev->dev, NULL);
-	kfree(priv);
 
 	return 0;
 }
diff --git a/drivers/platform/x86/intel_mid_thermal.c b/drivers/platform/x86/intel_mid_thermal.c
index 93fab8b70ce..ab7860a21a2 100644
--- a/drivers/platform/x86/intel_mid_thermal.c
+++ b/drivers/platform/x86/intel_mid_thermal.c
@@ -481,7 +481,8 @@ static int mid_thermal_probe(struct platform_device *pdev)
 	int i;
 	struct platform_info *pinfo;
 
-	pinfo = kzalloc(sizeof(struct platform_info), GFP_KERNEL);
+	pinfo = devm_kzalloc(&pdev->dev, sizeof(struct platform_info),
+			     GFP_KERNEL);
 	if (!pinfo)
 		return -ENOMEM;
 
@@ -489,7 +490,6 @@ static int mid_thermal_probe(struct platform_device *pdev)
 	ret = mid_initialize_adc(&pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "ADC init failed");
-		kfree(pinfo);
 		return ret;
 	}
 
@@ -520,7 +520,6 @@ err:
 		thermal_zone_device_unregister(pinfo->tzd[i]);
 	}
 	configure_adc(0);
-	kfree(pinfo);
 	return ret;
 }
 
@@ -541,8 +540,6 @@ static int mid_thermal_remove(struct platform_device *pdev)
 		thermal_zone_device_unregister(pinfo->tzd[i]);
 	}
 
-	kfree(pinfo);
-
 	/* Stop the ADC */
 	return configure_adc(0);
 }
diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c
index 2805988485f..40929e4f7ad 100644
--- a/drivers/platform/x86/intel_pmic_gpio.c
+++ b/drivers/platform/x86/intel_pmic_gpio.c
@@ -91,7 +91,7 @@ static void pmic_program_irqtype(int gpio, int type)
 
 static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 {
-	if (offset > 8) {
+	if (offset >= 8) {
 		pr_err("only pin 0-7 support input\n");
 		return -1;/* we only have 8 GPIO can use as input */
 	}
@@ -130,7 +130,7 @@ static int pmic_gpio_get(struct gpio_chip *chip, unsigned offset)
 	int ret;
 
 	/* we only have 8 GPIO pins we can use as input */
-	if (offset > 8)
+	if (offset >= 8)
 		return -EOPNOTSUPP;
 	ret = intel_scu_ipc_ioread8(GPIO0 + offset, &r);
 	if (ret < 0)
diff --git a/drivers/platform/x86/pvpanic.c b/drivers/platform/x86/pvpanic.c
index c9f6e511daa..073a90a63db 100644
--- a/drivers/platform/x86/pvpanic.c
+++ b/drivers/platform/x86/pvpanic.c
@@ -70,6 +70,7 @@ pvpanic_panic_notify(struct notifier_block *nb, unsigned long code,
 
 static struct notifier_block pvpanic_panic_nb = {
 	.notifier_call = pvpanic_panic_notify,
+	.priority = 1, /* let this called before broken drm_fb_helper */
 };
 
 
diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c
index d1f03005317..5a596651227 100644
--- a/drivers/platform/x86/samsung-laptop.c
+++ b/drivers/platform/x86/samsung-laptop.c
@@ -27,6 +27,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/efi.h>
+#include <linux/suspend.h>
 #include <acpi/video.h>
 
 /*
@@ -340,6 +341,8 @@ struct samsung_laptop {
 	struct samsung_laptop_debug debug;
 	struct samsung_quirks *quirks;
 
+	struct notifier_block pm_nb;
+
 	bool handle_backlight;
 	bool has_stepping_quirk;
 
@@ -348,6 +351,8 @@ struct samsung_laptop {
 
 struct samsung_quirks {
 	bool broken_acpi_video;
+	bool four_kbd_backlight_levels;
+	bool enable_kbd_backlight;
 };
 
 static struct samsung_quirks samsung_unknown = {};
@@ -356,6 +361,11 @@ static struct samsung_quirks samsung_broken_acpi_video = {
 	.broken_acpi_video = true,
 };
 
+static struct samsung_quirks samsung_np740u3e = {
+	.four_kbd_backlight_levels = true,
+	.enable_kbd_backlight = true,
+};
+
 static bool force;
 module_param(force, bool, 0);
 MODULE_PARM_DESC(force,
@@ -1051,6 +1061,8 @@ static int __init samsung_leds_init(struct samsung_laptop *samsung)
 		samsung->kbd_led.brightness_set = kbd_led_set;
 		samsung->kbd_led.brightness_get = kbd_led_get;
 		samsung->kbd_led.max_brightness = 8;
+		if (samsung->quirks->four_kbd_backlight_levels)
+			samsung->kbd_led.max_brightness = 4;
 
 		ret = led_classdev_register(&samsung->platform_device->dev,
 					   &samsung->kbd_led);
@@ -1414,6 +1426,19 @@ static void samsung_platform_exit(struct samsung_laptop *samsung)
 	}
 }
 
+static int samsung_pm_notification(struct notifier_block *nb,
+				   unsigned long val, void *ptr)
+{
+	struct samsung_laptop *samsung;
+
+	samsung = container_of(nb, struct samsung_laptop, pm_nb);
+	if (val == PM_POST_HIBERNATION &&
+	    samsung->quirks->enable_kbd_backlight)
+		kbd_backlight_enable(samsung);
+
+	return 0;
+}
+
 static int __init samsung_platform_init(struct samsung_laptop *samsung)
 {
 	struct platform_device *pdev;
@@ -1534,6 +1559,15 @@ static struct dmi_system_id __initdata samsung_dmi_table[] = {
 		},
 	 .driver_data = &samsung_broken_acpi_video,
 	},
+	{
+	 .callback = samsung_dmi_matched,
+	 .ident = "730U3E/740U3E",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "730U3E/740U3E"),
+		},
+	 .driver_data = &samsung_np740u3e,
+	},
 	{ },
 };
 MODULE_DEVICE_TABLE(dmi, samsung_dmi_table);
@@ -1608,6 +1642,9 @@ static int __init samsung_init(void)
 	if (ret)
 		goto error_debugfs;
 
+	samsung->pm_nb.notifier_call = samsung_pm_notification;
+	register_pm_notifier(&samsung->pm_nb);
+
 	samsung_platform_device = samsung->platform_device;
 	return ret;
 
@@ -1633,6 +1670,7 @@ static void __exit samsung_exit(void)
 	struct samsung_laptop *samsung;
 
 	samsung = platform_get_drvdata(samsung_platform_device);
+	unregister_pm_notifier(&samsung->pm_nb);
 
 	samsung_debugfs_exit(samsung);
 	samsung_leds_exit(samsung);
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 15e61c16736..d82f196e3cf 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -3171,8 +3171,10 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
 		KEY_MICMUTE,	/* 0x1a: Mic mute (since ?400 or so) */
 
 		/* (assignments unknown, please report if found) */
-		KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN, KEY_UNKNOWN,
 		KEY_UNKNOWN,
+
+		/* Extra keys in use since the X240 / T440 / T540 */
+		KEY_CONFIG, KEY_SEARCH, KEY_SCALE, KEY_COMPUTER,
 		},
 	};
 
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 46473ca7566..76441dcbe5f 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -56,6 +56,7 @@
 #include <linux/workqueue.h>
 #include <linux/i8042.h>
 #include <linux/acpi.h>
+#include <linux/dmi.h>
 #include <asm/uaccess.h>
 
 MODULE_AUTHOR("John Belmonte");
@@ -213,6 +214,30 @@ static const struct key_entry toshiba_acpi_keymap[] = {
 	{ KE_END, 0 },
 };
 
+/* alternative keymap */
+static const struct dmi_system_id toshiba_alt_keymap_dmi[] = {
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Satellite M840"),
+		},
+	},
+	{}
+};
+
+static const struct key_entry toshiba_acpi_alt_keymap[] = {
+	{ KE_KEY, 0x157, { KEY_MUTE } },
+	{ KE_KEY, 0x102, { KEY_ZOOMOUT } },
+	{ KE_KEY, 0x103, { KEY_ZOOMIN } },
+	{ KE_KEY, 0x139, { KEY_ZOOMRESET } },
+	{ KE_KEY, 0x13e, { KEY_SWITCHVIDEOMODE } },
+	{ KE_KEY, 0x13c, { KEY_BRIGHTNESSDOWN } },
+	{ KE_KEY, 0x13d, { KEY_BRIGHTNESSUP } },
+	{ KE_KEY, 0x158, { KEY_WLAN } },
+	{ KE_KEY, 0x13f, { KEY_TOUCHPAD_TOGGLE } },
+	{ KE_END, 0 },
+};
+
 /* utility
  */
 
@@ -1440,6 +1465,7 @@ static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev)
 	acpi_handle ec_handle;
 	int error;
 	u32 hci_result;
+	const struct key_entry *keymap = toshiba_acpi_keymap;
 
 	dev->hotkey_dev = input_allocate_device();
 	if (!dev->hotkey_dev)
@@ -1449,7 +1475,9 @@ static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev)
 	dev->hotkey_dev->phys = "toshiba_acpi/input0";
 	dev->hotkey_dev->id.bustype = BUS_HOST;
 
-	error = sparse_keymap_setup(dev->hotkey_dev, toshiba_acpi_keymap, NULL);
+	if (dmi_check_system(toshiba_alt_keymap_dmi))
+		keymap = toshiba_acpi_alt_keymap;
+	error = sparse_keymap_setup(dev->hotkey_dev, keymap, NULL);
 	if (error)
 		goto err_free_dev;
 
diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c
index b81448b2c75..a5c6cb773e5 100644
--- a/drivers/pnp/pnpacpi/core.c
+++ b/drivers/pnp/pnpacpi/core.c
@@ -319,8 +319,7 @@ static int __init acpi_pnp_match(struct device *dev, void *_pnp)
 	struct pnp_dev *pnp = _pnp;
 
 	/* true means it matched */
-	return !acpi->physical_node_count
-	    && compare_pnp_id(pnp->id, acpi_device_hid(acpi));
+	return pnp->data == acpi;
 }
 
 static struct acpi_device * __init acpi_pnp_find_companion(struct device *dev)
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 6aea373547f..ee3de3421f2 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -74,7 +74,7 @@ config DP83640_PHY
 
 config PTP_1588_CLOCK_PCH
 	tristate "Intel PCH EG20T as PTP clock"
-	depends on X86 || COMPILE_TEST
+	depends on X86_32 || COMPILE_TEST
 	depends on HAS_IOMEM && NET
 	select PTP_1588_CLOCK
 	help
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index e25d2bc898e..296b0ec8744 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -142,7 +142,10 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct timex *tx)
 		delta = ktime_to_ns(kt);
 		err = ops->adjtime(ops, delta);
 	} else if (tx->modes & ADJ_FREQUENCY) {
-		err = ops->adjfreq(ops, scaled_ppm_to_ppb(tx->freq));
+		s32 ppb = scaled_ppm_to_ppb(tx->freq);
+		if (ppb > ops->max_adj || ppb < -ops->max_adj)
+			return -ERANGE;
+		err = ops->adjfreq(ops, ppb);
 		ptp->dialed_frequency = tx->freq;
 	} else if (tx->modes == 0) {
 		tx->freq = ptp->dialed_frequency;
diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig
index 5b34ff29ea3..4ad7b89a4cb 100644
--- a/drivers/pwm/Kconfig
+++ b/drivers/pwm/Kconfig
@@ -62,6 +62,15 @@ config PWM_ATMEL_TCB
 	  To compile this driver as a module, choose M here: the module
 	  will be called pwm-atmel-tcb.
 
+config PWM_BCM_KONA
+	tristate "Kona PWM support"
+	depends on ARCH_BCM_MOBILE
+	help
+	  Generic PWM framework driver for Broadcom Kona PWM block.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called pwm-bcm-kona.
+
 config PWM_BFIN
 	tristate "Blackfin PWM support"
 	depends on BFIN_GPTIMERS
diff --git a/drivers/pwm/Makefile b/drivers/pwm/Makefile
index e57d2c38a79..5c86a19d5d3 100644
--- a/drivers/pwm/Makefile
+++ b/drivers/pwm/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_PWM_SYSFS)		+= sysfs.o
 obj-$(CONFIG_PWM_AB8500)	+= pwm-ab8500.o
 obj-$(CONFIG_PWM_ATMEL)		+= pwm-atmel.o
 obj-$(CONFIG_PWM_ATMEL_TCB)	+= pwm-atmel-tcb.o
+obj-$(CONFIG_PWM_BCM_KONA)	+= pwm-bcm-kona.o
 obj-$(CONFIG_PWM_BFIN)		+= pwm-bfin.o
 obj-$(CONFIG_PWM_CLPS711X)	+= pwm-clps711x.o
 obj-$(CONFIG_PWM_EP93XX)	+= pwm-ep93xx.o
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index a80471399c2..4b66bf09ee5 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -661,10 +661,16 @@ struct pwm_device *pwm_get(struct device *dev, const char *con_id)
 		}
 	}
 
+	mutex_unlock(&pwm_lookup_lock);
+
 	if (chip)
 		pwm = pwm_request_from_chip(chip, index, con_id ?: dev_id);
+	if (IS_ERR(pwm))
+		return pwm;
+
+	pwm_set_period(pwm, p->period);
+	pwm_set_polarity(pwm, p->polarity);
 
-	mutex_unlock(&pwm_lookup_lock);
 
 	return pwm;
 }
diff --git a/drivers/pwm/pwm-ab8500.c b/drivers/pwm/pwm-ab8500.c
index 1d07a6f9937..4c07a8420b3 100644
--- a/drivers/pwm/pwm-ab8500.c
+++ b/drivers/pwm/pwm-ab8500.c
@@ -20,10 +20,6 @@
 #define AB8500_PWM_OUT_CTRL2_REG	0x61
 #define AB8500_PWM_OUT_CTRL7_REG	0x66
 
-/* backlight driver constants */
-#define ENABLE_PWM			1
-#define DISABLE_PWM			0
-
 struct ab8500_pwm_chip {
 	struct pwm_chip chip;
 };
@@ -64,7 +60,7 @@ static int ab8500_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
 
 	ret = abx500_mask_and_set_register_interruptible(chip->dev,
 				AB8500_MISC, AB8500_PWM_OUT_CTRL7_REG,
-				1 << (chip->base - 1), ENABLE_PWM);
+				1 << (chip->base - 1), 1 << (chip->base - 1));
 	if (ret < 0)
 		dev_err(chip->dev, "%s: Failed to enable PWM, Error %d\n",
 							pwm->label, ret);
@@ -77,11 +73,10 @@ static void ab8500_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 
 	ret = abx500_mask_and_set_register_interruptible(chip->dev,
 				AB8500_MISC, AB8500_PWM_OUT_CTRL7_REG,
-				1 << (chip->base - 1), DISABLE_PWM);
+				1 << (chip->base - 1), 0);
 	if (ret < 0)
 		dev_err(chip->dev, "%s: Failed to disable PWM, Error %d\n",
 							pwm->label, ret);
-	return;
 }
 
 static const struct pwm_ops ab8500_pwm_ops = {
@@ -101,10 +96,8 @@ static int ab8500_pwm_probe(struct platform_device *pdev)
 	 * device which is required for ab8500 read and write
 	 */
 	ab8500 = devm_kzalloc(&pdev->dev, sizeof(*ab8500), GFP_KERNEL);
-	if (ab8500 == NULL) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
+	if (ab8500 == NULL)
 		return -ENOMEM;
-	}
 
 	ab8500->chip.dev = &pdev->dev;
 	ab8500->chip.ops = &ab8500_pwm_ops;
diff --git a/drivers/pwm/pwm-atmel.c b/drivers/pwm/pwm-atmel.c
index 0adc952cc4e..6e700a541ca 100644
--- a/drivers/pwm/pwm-atmel.c
+++ b/drivers/pwm/pwm-atmel.c
@@ -357,6 +357,7 @@ static int atmel_pwm_probe(struct platform_device *pdev)
 
 	atmel_pwm->chip.base = -1;
 	atmel_pwm->chip.npwm = 4;
+	atmel_pwm->chip.can_sleep = true;
 	atmel_pwm->config = data->config;
 
 	ret = pwmchip_add(&atmel_pwm->chip);
diff --git a/drivers/pwm/pwm-bcm-kona.c b/drivers/pwm/pwm-bcm-kona.c
new file mode 100644
index 00000000000..02bc048892a
--- /dev/null
+++ b/drivers/pwm/pwm-bcm-kona.c
@@ -0,0 +1,318 @@
+/*
+ * Copyright (C) 2014 Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/math64.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pwm.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+/*
+ * The Kona PWM has some unusual characteristics.  Here are the main points.
+ *
+ * 1) There is no disable bit and the hardware docs advise programming a zero
+ *    duty to achieve output equivalent to that of a normal disable operation.
+ *
+ * 2) Changes to prescale, duty, period, and polarity do not take effect until
+ *    a subsequent rising edge of the trigger bit.
+ *
+ * 3) If the smooth bit and trigger bit are both low, the output is a constant
+ *    high signal.  Otherwise, the earlier waveform continues to be output.
+ *
+ * 4) If the smooth bit is set on the rising edge of the trigger bit, output
+ *    will transition to the new settings on a period boundary (which could be
+ *    seconds away).  If the smooth bit is clear, new settings will be applied
+ *    as soon as possible (the hardware always has a 400ns delay).
+ *
+ * 5) When the external clock that feeds the PWM is disabled, output is pegged
+ *    high or low depending on its state at that exact instant.
+ */
+
+#define PWM_CONTROL_OFFSET			(0x00000000)
+#define PWM_CONTROL_SMOOTH_SHIFT(chan)		(24 + (chan))
+#define PWM_CONTROL_TYPE_SHIFT(chan)		(16 + (chan))
+#define PWM_CONTROL_POLARITY_SHIFT(chan)	(8 + (chan))
+#define PWM_CONTROL_TRIGGER_SHIFT(chan)		(chan)
+
+#define PRESCALE_OFFSET				(0x00000004)
+#define PRESCALE_SHIFT(chan)			((chan) << 2)
+#define PRESCALE_MASK(chan)			(0x7 << PRESCALE_SHIFT(chan))
+#define PRESCALE_MIN				(0x00000000)
+#define PRESCALE_MAX				(0x00000007)
+
+#define PERIOD_COUNT_OFFSET(chan)		(0x00000008 + ((chan) << 3))
+#define PERIOD_COUNT_MIN			(0x00000002)
+#define PERIOD_COUNT_MAX			(0x00ffffff)
+
+#define DUTY_CYCLE_HIGH_OFFSET(chan)		(0x0000000c + ((chan) << 3))
+#define DUTY_CYCLE_HIGH_MIN			(0x00000000)
+#define DUTY_CYCLE_HIGH_MAX			(0x00ffffff)
+
+struct kona_pwmc {
+	struct pwm_chip chip;
+	void __iomem *base;
+	struct clk *clk;
+};
+
+static inline struct kona_pwmc *to_kona_pwmc(struct pwm_chip *_chip)
+{
+	return container_of(_chip, struct kona_pwmc, chip);
+}
+
+static void kona_pwmc_apply_settings(struct kona_pwmc *kp, unsigned int chan)
+{
+	unsigned int value = readl(kp->base + PWM_CONTROL_OFFSET);
+
+	/* Clear trigger bit but set smooth bit to maintain old output */
+	value |= 1 << PWM_CONTROL_SMOOTH_SHIFT(chan);
+	value &= ~(1 << PWM_CONTROL_TRIGGER_SHIFT(chan));
+	writel(value, kp->base + PWM_CONTROL_OFFSET);
+
+	/* Set trigger bit and clear smooth bit to apply new settings */
+	value &= ~(1 << PWM_CONTROL_SMOOTH_SHIFT(chan));
+	value |= 1 << PWM_CONTROL_TRIGGER_SHIFT(chan);
+	writel(value, kp->base + PWM_CONTROL_OFFSET);
+}
+
+static int kona_pwmc_config(struct pwm_chip *chip, struct pwm_device *pwm,
+			    int duty_ns, int period_ns)
+{
+	struct kona_pwmc *kp = to_kona_pwmc(chip);
+	u64 val, div, rate;
+	unsigned long prescale = PRESCALE_MIN, pc, dc;
+	unsigned int value, chan = pwm->hwpwm;
+
+	/*
+	 * Find period count, duty count and prescale to suit duty_ns and
+	 * period_ns. This is done according to formulas described below:
+	 *
+	 * period_ns = 10^9 * (PRESCALE + 1) * PC / PWM_CLK_RATE
+	 * duty_ns = 10^9 * (PRESCALE + 1) * DC / PWM_CLK_RATE
+	 *
+	 * PC = (PWM_CLK_RATE * period_ns) / (10^9 * (PRESCALE + 1))
+	 * DC = (PWM_CLK_RATE * duty_ns) / (10^9 * (PRESCALE + 1))
+	 */
+
+	rate = clk_get_rate(kp->clk);
+
+	while (1) {
+		div = 1000000000;
+		div *= 1 + prescale;
+		val = rate * period_ns;
+		pc = div64_u64(val, div);
+		val = rate * duty_ns;
+		dc = div64_u64(val, div);
+
+		/* If duty_ns or period_ns are not achievable then return */
+		if (pc < PERIOD_COUNT_MIN || dc < DUTY_CYCLE_HIGH_MIN)
+			return -EINVAL;
+
+		/* If pc and dc are in bounds, the calculation is done */
+		if (pc <= PERIOD_COUNT_MAX && dc <= DUTY_CYCLE_HIGH_MAX)
+			break;
+
+		/* Otherwise, increase prescale and recalculate pc and dc */
+		if (++prescale > PRESCALE_MAX)
+			return -EINVAL;
+	}
+
+	/* If the PWM channel is enabled, write the settings to the HW */
+	if (test_bit(PWMF_ENABLED, &pwm->flags)) {
+		value = readl(kp->base + PRESCALE_OFFSET);
+		value &= ~PRESCALE_MASK(chan);
+		value |= prescale << PRESCALE_SHIFT(chan);
+		writel(value, kp->base + PRESCALE_OFFSET);
+
+		writel(pc, kp->base + PERIOD_COUNT_OFFSET(chan));
+
+		writel(dc, kp->base + DUTY_CYCLE_HIGH_OFFSET(chan));
+
+		kona_pwmc_apply_settings(kp, chan);
+	}
+
+	return 0;
+}
+
+static int kona_pwmc_set_polarity(struct pwm_chip *chip, struct pwm_device *pwm,
+				  enum pwm_polarity polarity)
+{
+	struct kona_pwmc *kp = to_kona_pwmc(chip);
+	unsigned int chan = pwm->hwpwm;
+	unsigned int value;
+	int ret;
+
+	ret = clk_prepare_enable(kp->clk);
+	if (ret < 0) {
+		dev_err(chip->dev, "failed to enable clock: %d\n", ret);
+		return ret;
+	}
+
+	value = readl(kp->base + PWM_CONTROL_OFFSET);
+
+	if (polarity == PWM_POLARITY_NORMAL)
+		value |= 1 << PWM_CONTROL_POLARITY_SHIFT(chan);
+	else
+		value &= ~(1 << PWM_CONTROL_POLARITY_SHIFT(chan));
+
+	writel(value, kp->base + PWM_CONTROL_OFFSET);
+
+	kona_pwmc_apply_settings(kp, chan);
+
+	/* Wait for waveform to settle before gating off the clock */
+	ndelay(400);
+
+	clk_disable_unprepare(kp->clk);
+
+	return 0;
+}
+
+static int kona_pwmc_enable(struct pwm_chip *chip, struct pwm_device *pwm)
+{
+	struct kona_pwmc *kp = to_kona_pwmc(chip);
+	int ret;
+
+	ret = clk_prepare_enable(kp->clk);
+	if (ret < 0) {
+		dev_err(chip->dev, "failed to enable clock: %d\n", ret);
+		return ret;
+	}
+
+	ret = kona_pwmc_config(chip, pwm, pwm->duty_cycle, pwm->period);
+	if (ret < 0) {
+		clk_disable_unprepare(kp->clk);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void kona_pwmc_disable(struct pwm_chip *chip, struct pwm_device *pwm)
+{
+	struct kona_pwmc *kp = to_kona_pwmc(chip);
+	unsigned int chan = pwm->hwpwm;
+
+	/* Simulate a disable by configuring for zero duty */
+	writel(0, kp->base + DUTY_CYCLE_HIGH_OFFSET(chan));
+	kona_pwmc_apply_settings(kp, chan);
+
+	/* Wait for waveform to settle before gating off the clock */
+	ndelay(400);
+
+	clk_disable_unprepare(kp->clk);
+}
+
+static const struct pwm_ops kona_pwm_ops = {
+	.config = kona_pwmc_config,
+	.set_polarity = kona_pwmc_set_polarity,
+	.enable = kona_pwmc_enable,
+	.disable = kona_pwmc_disable,
+	.owner = THIS_MODULE,
+};
+
+static int kona_pwmc_probe(struct platform_device *pdev)
+{
+	struct kona_pwmc *kp;
+	struct resource *res;
+	unsigned int chan;
+	unsigned int value = 0;
+	int ret = 0;
+
+	kp = devm_kzalloc(&pdev->dev, sizeof(*kp), GFP_KERNEL);
+	if (kp == NULL)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, kp);
+
+	kp->chip.dev = &pdev->dev;
+	kp->chip.ops = &kona_pwm_ops;
+	kp->chip.base = -1;
+	kp->chip.npwm = 6;
+	kp->chip.of_xlate = of_pwm_xlate_with_flags;
+	kp->chip.of_pwm_n_cells = 3;
+	kp->chip.can_sleep = true;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	kp->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(kp->base))
+		return PTR_ERR(kp->base);
+
+	kp->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(kp->clk)) {
+		dev_err(&pdev->dev, "failed to get clock: %ld\n",
+			PTR_ERR(kp->clk));
+		return PTR_ERR(kp->clk);
+	}
+
+	ret = clk_prepare_enable(kp->clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to enable clock: %d\n", ret);
+		return ret;
+	}
+
+	/* Set smooth mode, push/pull, and normal polarity for all channels */
+	for (chan = 0; chan < kp->chip.npwm; chan++) {
+		value |= (1 << PWM_CONTROL_SMOOTH_SHIFT(chan));
+		value |= (1 << PWM_CONTROL_TYPE_SHIFT(chan));
+		value |= (1 << PWM_CONTROL_POLARITY_SHIFT(chan));
+	}
+
+	writel(value, kp->base + PWM_CONTROL_OFFSET);
+
+	clk_disable_unprepare(kp->clk);
+
+	ret = pwmchip_add(&kp->chip);
+	if (ret < 0)
+		dev_err(&pdev->dev, "failed to add PWM chip: %d\n", ret);
+
+	return ret;
+}
+
+static int kona_pwmc_remove(struct platform_device *pdev)
+{
+	struct kona_pwmc *kp = platform_get_drvdata(pdev);
+	unsigned int chan;
+
+	for (chan = 0; chan < kp->chip.npwm; chan++)
+		if (test_bit(PWMF_ENABLED, &kp->chip.pwms[chan].flags))
+			clk_disable_unprepare(kp->clk);
+
+	return pwmchip_remove(&kp->chip);
+}
+
+static const struct of_device_id bcm_kona_pwmc_dt[] = {
+	{ .compatible = "brcm,kona-pwm" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, bcm_kona_pwmc_dt);
+
+static struct platform_driver kona_pwmc_driver = {
+	.driver = {
+		.name = "bcm-kona-pwm",
+		.of_match_table = bcm_kona_pwmc_dt,
+	},
+	.probe = kona_pwmc_probe,
+	.remove = kona_pwmc_remove,
+};
+module_platform_driver(kona_pwmc_driver);
+
+MODULE_AUTHOR("Broadcom Corporation <bcm-kernel-feedback-list@broadcom.com>");
+MODULE_AUTHOR("Tim Kryger <tkryger@broadcom.com>");
+MODULE_DESCRIPTION("Broadcom Kona PWM driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pwm/pwm-fsl-ftm.c b/drivers/pwm/pwm-fsl-ftm.c
index 420169e96b5..a18bc8fea38 100644
--- a/drivers/pwm/pwm-fsl-ftm.c
+++ b/drivers/pwm/pwm-fsl-ftm.c
@@ -454,6 +454,7 @@ static int fsl_pwm_probe(struct platform_device *pdev)
 	fpc->chip.of_pwm_n_cells = 3;
 	fpc->chip.base = -1;
 	fpc->chip.npwm = 8;
+	fpc->chip.can_sleep = true;
 
 	ret = pwmchip_add(&fpc->chip);
 	if (ret < 0) {
diff --git a/drivers/pwm/pwm-imx.c b/drivers/pwm/pwm-imx.c
index cc477334487..d797c7b84c3 100644
--- a/drivers/pwm/pwm-imx.c
+++ b/drivers/pwm/pwm-imx.c
@@ -241,10 +241,8 @@ static int imx_pwm_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	imx = devm_kzalloc(&pdev->dev, sizeof(*imx), GFP_KERNEL);
-	if (imx == NULL) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
+	if (imx == NULL)
 		return -ENOMEM;
-	}
 
 	imx->clk_per = devm_clk_get(&pdev->dev, "per");
 	if (IS_ERR(imx->clk_per)) {
diff --git a/drivers/pwm/pwm-lp3943.c b/drivers/pwm/pwm-lp3943.c
index a40b9c34e9f..2c39b0e50fa 100644
--- a/drivers/pwm/pwm-lp3943.c
+++ b/drivers/pwm/pwm-lp3943.c
@@ -278,6 +278,7 @@ static int lp3943_pwm_probe(struct platform_device *pdev)
 	lp3943_pwm->chip.dev = &pdev->dev;
 	lp3943_pwm->chip.ops = &lp3943_pwm_ops;
 	lp3943_pwm->chip.npwm = LP3943_NUM_PWMS;
+	lp3943_pwm->chip.can_sleep = true;
 
 	platform_set_drvdata(pdev, lp3943_pwm);
 
diff --git a/drivers/pwm/pwm-lpss.c b/drivers/pwm/pwm-lpss.c
index 449e372050a..44ce6c6103a 100644
--- a/drivers/pwm/pwm-lpss.c
+++ b/drivers/pwm/pwm-lpss.c
@@ -6,6 +6,7 @@
  * Author: Chew Kean Ho <kean.ho.chew@intel.com>
  * Author: Chang Rebecca Swee Fun <rebecca.swee.fun.chang@intel.com>
  * Author: Chew Chiau Ee <chiau.ee.chew@intel.com>
+ * Author: Alan Cox <alan@linux.intel.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -19,6 +20,9 @@
 #include <linux/module.h>
 #include <linux/pwm.h>
 #include <linux/platform_device.h>
+#include <linux/pci.h>
+
+static int pci_drv, plat_drv;	/* So we know which drivers registered */
 
 #define PWM				0x00000000
 #define PWM_ENABLE			BIT(31)
@@ -34,6 +38,16 @@ struct pwm_lpss_chip {
 	struct pwm_chip chip;
 	void __iomem *regs;
 	struct clk *clk;
+	unsigned long clk_rate;
+};
+
+struct pwm_lpss_boardinfo {
+	unsigned long clk_rate;
+};
+
+/* BayTrail */
+static const struct pwm_lpss_boardinfo byt_info = {
+	25000000
 };
 
 static inline struct pwm_lpss_chip *to_lpwm(struct pwm_chip *chip)
@@ -55,7 +69,7 @@ static int pwm_lpss_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	/* The equation is: base_unit = ((freq / c) * 65536) + correction */
 	base_unit = freq * 65536;
 
-	c = clk_get_rate(lpwm->clk);
+	c = lpwm->clk_rate;
 	if (!c)
 		return -EINVAL;
 
@@ -113,52 +127,48 @@ static const struct pwm_ops pwm_lpss_ops = {
 	.owner = THIS_MODULE,
 };
 
-static const struct acpi_device_id pwm_lpss_acpi_match[] = {
-	{ "80860F09", 0 },
-	{ },
-};
-MODULE_DEVICE_TABLE(acpi, pwm_lpss_acpi_match);
-
-static int pwm_lpss_probe(struct platform_device *pdev)
+static struct pwm_lpss_chip *pwm_lpss_probe(struct device *dev,
+					    struct resource *r,
+					    const struct pwm_lpss_boardinfo *info)
 {
 	struct pwm_lpss_chip *lpwm;
-	struct resource *r;
 	int ret;
 
-	lpwm = devm_kzalloc(&pdev->dev, sizeof(*lpwm), GFP_KERNEL);
+	lpwm = devm_kzalloc(dev, sizeof(*lpwm), GFP_KERNEL);
 	if (!lpwm)
-		return -ENOMEM;
-
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		return ERR_PTR(-ENOMEM);
 
-	lpwm->regs = devm_ioremap_resource(&pdev->dev, r);
+	lpwm->regs = devm_ioremap_resource(dev, r);
 	if (IS_ERR(lpwm->regs))
-		return PTR_ERR(lpwm->regs);
-
-	lpwm->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(lpwm->clk)) {
-		dev_err(&pdev->dev, "failed to get PWM clock\n");
-		return PTR_ERR(lpwm->clk);
+		return ERR_CAST(lpwm->regs);
+
+	if (info) {
+		lpwm->clk_rate = info->clk_rate;
+	} else {
+		lpwm->clk = devm_clk_get(dev, NULL);
+		if (IS_ERR(lpwm->clk)) {
+			dev_err(dev, "failed to get PWM clock\n");
+			return ERR_CAST(lpwm->clk);
+		}
+		lpwm->clk_rate = clk_get_rate(lpwm->clk);
 	}
 
-	lpwm->chip.dev = &pdev->dev;
+	lpwm->chip.dev = dev;
 	lpwm->chip.ops = &pwm_lpss_ops;
 	lpwm->chip.base = -1;
 	lpwm->chip.npwm = 1;
 
 	ret = pwmchip_add(&lpwm->chip);
 	if (ret) {
-		dev_err(&pdev->dev, "failed to add PWM chip: %d\n", ret);
-		return ret;
+		dev_err(dev, "failed to add PWM chip: %d\n", ret);
+		return ERR_PTR(ret);
 	}
 
-	platform_set_drvdata(pdev, lpwm);
-	return 0;
+	return lpwm;
 }
 
-static int pwm_lpss_remove(struct platform_device *pdev)
+static int pwm_lpss_remove(struct pwm_lpss_chip *lpwm)
 {
-	struct pwm_lpss_chip *lpwm = platform_get_drvdata(pdev);
 	u32 ctrl;
 
 	ctrl = readl(lpwm->regs + PWM);
@@ -167,15 +177,104 @@ static int pwm_lpss_remove(struct platform_device *pdev)
 	return pwmchip_remove(&lpwm->chip);
 }
 
-static struct platform_driver pwm_lpss_driver = {
+static int pwm_lpss_probe_pci(struct pci_dev *pdev,
+			      const struct pci_device_id *id)
+{
+	const struct pwm_lpss_boardinfo *info;
+	struct pwm_lpss_chip *lpwm;
+	int err;
+
+	err = pci_enable_device(pdev);
+	if (err < 0)
+		return err;
+
+	info = (struct pwm_lpss_boardinfo *)id->driver_data;
+	lpwm = pwm_lpss_probe(&pdev->dev, &pdev->resource[0], info);
+	if (IS_ERR(lpwm))
+		return PTR_ERR(lpwm);
+
+	pci_set_drvdata(pdev, lpwm);
+	return 0;
+}
+
+static void pwm_lpss_remove_pci(struct pci_dev *pdev)
+{
+	struct pwm_lpss_chip *lpwm = pci_get_drvdata(pdev);
+
+	pwm_lpss_remove(lpwm);
+	pci_disable_device(pdev);
+}
+
+static struct pci_device_id pwm_lpss_pci_ids[] = {
+	{ PCI_VDEVICE(INTEL, 0x0f08), (unsigned long)&byt_info},
+	{ PCI_VDEVICE(INTEL, 0x0f09), (unsigned long)&byt_info},
+	{ },
+};
+MODULE_DEVICE_TABLE(pci, pwm_lpss_pci_ids);
+
+static struct pci_driver pwm_lpss_driver_pci = {
+	.name = "pwm-lpss",
+	.id_table = pwm_lpss_pci_ids,
+	.probe = pwm_lpss_probe_pci,
+	.remove = pwm_lpss_remove_pci,
+};
+
+static int pwm_lpss_probe_platform(struct platform_device *pdev)
+{
+	struct pwm_lpss_chip *lpwm;
+	struct resource *r;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	lpwm = pwm_lpss_probe(&pdev->dev, r, NULL);
+	if (IS_ERR(lpwm))
+		return PTR_ERR(lpwm);
+
+	platform_set_drvdata(pdev, lpwm);
+	return 0;
+}
+
+static int pwm_lpss_remove_platform(struct platform_device *pdev)
+{
+	struct pwm_lpss_chip *lpwm = platform_get_drvdata(pdev);
+
+	return pwm_lpss_remove(lpwm);
+}
+
+static const struct acpi_device_id pwm_lpss_acpi_match[] = {
+	{ "80860F09", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, pwm_lpss_acpi_match);
+
+static struct platform_driver pwm_lpss_driver_platform = {
 	.driver = {
 		.name = "pwm-lpss",
 		.acpi_match_table = pwm_lpss_acpi_match,
 	},
-	.probe = pwm_lpss_probe,
-	.remove = pwm_lpss_remove,
+	.probe = pwm_lpss_probe_platform,
+	.remove = pwm_lpss_remove_platform,
 };
-module_platform_driver(pwm_lpss_driver);
+
+static int __init pwm_init(void)
+{
+	pci_drv = pci_register_driver(&pwm_lpss_driver_pci);
+	plat_drv = platform_driver_register(&pwm_lpss_driver_platform);
+	if (pci_drv && plat_drv)
+		return pci_drv;
+
+	return 0;
+}
+module_init(pwm_init);
+
+static void __exit pwm_exit(void)
+{
+	if (!pci_drv)
+		pci_unregister_driver(&pwm_lpss_driver_pci);
+	if (!plat_drv)
+		platform_driver_unregister(&pwm_lpss_driver_platform);
+}
+module_exit(pwm_exit);
 
 MODULE_DESCRIPTION("PWM driver for Intel LPSS");
 MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
diff --git a/drivers/pwm/pwm-mxs.c b/drivers/pwm/pwm-mxs.c
index 9475bc7a6f9..4f1bb4e0a42 100644
--- a/drivers/pwm/pwm-mxs.c
+++ b/drivers/pwm/pwm-mxs.c
@@ -147,6 +147,7 @@ static int mxs_pwm_probe(struct platform_device *pdev)
 	mxs->chip.dev = &pdev->dev;
 	mxs->chip.ops = &mxs_pwm_ops;
 	mxs->chip.base = -1;
+	mxs->chip.can_sleep = true;
 	ret = of_property_read_u32(np, "fsl,pwm-number", &mxs->chip.npwm);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to get pwm number: %d\n", ret);
diff --git a/drivers/pwm/pwm-pxa.c b/drivers/pwm/pwm-pxa.c
index cd356d87024..0b312ec420b 100644
--- a/drivers/pwm/pwm-pxa.c
+++ b/drivers/pwm/pwm-pxa.c
@@ -179,10 +179,8 @@ static int pwm_probe(struct platform_device *pdev)
 		return -EINVAL;
 
 	pwm = devm_kzalloc(&pdev->dev, sizeof(*pwm), GFP_KERNEL);
-	if (pwm == NULL) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
+	if (pwm == NULL)
 		return -ENOMEM;
-	}
 
 	pwm->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(pwm->clk))
diff --git a/drivers/pwm/pwm-renesas-tpu.c b/drivers/pwm/pwm-renesas-tpu.c
index aff6ba9b49e..3b71b42e89d 100644
--- a/drivers/pwm/pwm-renesas-tpu.c
+++ b/drivers/pwm/pwm-renesas-tpu.c
@@ -21,13 +21,14 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
-#include <linux/platform_data/pwm-renesas-tpu.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/pwm.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
+#define TPU_CHANNEL_MAX		4
+
 #define TPU_TSTR		0x00	/* Timer start register (shared) */
 
 #define TPU_TCRn		0x00	/* Timer control register */
@@ -87,7 +88,6 @@ struct tpu_pwm_device {
 
 struct tpu_device {
 	struct platform_device *pdev;
-	enum pwm_polarity polarities[TPU_CHANNEL_MAX];
 	struct pwm_chip chip;
 	spinlock_t lock;
 
@@ -229,7 +229,7 @@ static int tpu_pwm_request(struct pwm_chip *chip, struct pwm_device *_pwm)
 
 	pwm->tpu = tpu;
 	pwm->channel = _pwm->hwpwm;
-	pwm->polarity = tpu->polarities[pwm->channel];
+	pwm->polarity = PWM_POLARITY_NORMAL;
 	pwm->prescaler = 0;
 	pwm->period = 0;
 	pwm->duty = 0;
@@ -388,16 +388,6 @@ static const struct pwm_ops tpu_pwm_ops = {
  * Probe and remove
  */
 
-static void tpu_parse_pdata(struct tpu_device *tpu)
-{
-	struct tpu_pwm_platform_data *pdata = tpu->pdev->dev.platform_data;
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(tpu->polarities); ++i)
-		tpu->polarities[i] = pdata ? pdata->channels[i].polarity
-				   : PWM_POLARITY_NORMAL;
-}
-
 static int tpu_probe(struct platform_device *pdev)
 {
 	struct tpu_device *tpu;
@@ -405,17 +395,12 @@ static int tpu_probe(struct platform_device *pdev)
 	int ret;
 
 	tpu = devm_kzalloc(&pdev->dev, sizeof(*tpu), GFP_KERNEL);
-	if (tpu == NULL) {
-		dev_err(&pdev->dev, "failed to allocate driver data\n");
+	if (tpu == NULL)
 		return -ENOMEM;
-	}
 
 	spin_lock_init(&tpu->lock);
 	tpu->pdev = pdev;
 
-	/* Initialize device configuration from platform data. */
-	tpu_parse_pdata(tpu);
-
 	/* Map memory, get clock and pin control. */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	tpu->base = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/pwm/pwm-samsung.c b/drivers/pwm/pwm-samsung.c
index d66529a995a..ba6b650cf8d 100644
--- a/drivers/pwm/pwm-samsung.c
+++ b/drivers/pwm/pwm-samsung.c
@@ -335,9 +335,6 @@ static int pwm_samsung_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	writel(tcnt, our_chip->base + REG_TCNTB(pwm->hwpwm));
 	writel(tcmp, our_chip->base + REG_TCMPB(pwm->hwpwm));
 
-	if (test_bit(PWMF_ENABLED, &pwm->flags))
-		pwm_samsung_enable(chip, pwm);
-
 	chan->period_ns = period_ns;
 	chan->tin_ns = tin_ns;
 	chan->duty_ns = duty_ns;
diff --git a/drivers/pwm/pwm-spear.c b/drivers/pwm/pwm-spear.c
index cb2d4f0f971..6fd93e6a412 100644
--- a/drivers/pwm/pwm-spear.c
+++ b/drivers/pwm/pwm-spear.c
@@ -179,10 +179,8 @@ static int spear_pwm_probe(struct platform_device *pdev)
 	u32 val;
 
 	pc = devm_kzalloc(&pdev->dev, sizeof(*pc), GFP_KERNEL);
-	if (!pc) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
+	if (!pc)
 		return -ENOMEM;
-	}
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	pc->mmio_base = devm_ioremap_resource(&pdev->dev, r);
@@ -222,7 +220,7 @@ static int spear_pwm_probe(struct platform_device *pdev)
 	}
 
 	ret = pwmchip_add(&pc->chip);
-	if (!ret) {
+	if (ret < 0) {
 		clk_unprepare(pc->clk);
 		dev_err(&pdev->dev, "pwmchip_add() failed: %d\n", ret);
 	}
diff --git a/drivers/pwm/pwm-tegra.c b/drivers/pwm/pwm-tegra.c
index 74298c561c4..61d86b9498c 100644
--- a/drivers/pwm/pwm-tegra.c
+++ b/drivers/pwm/pwm-tegra.c
@@ -173,10 +173,8 @@ static int tegra_pwm_probe(struct platform_device *pdev)
 	int ret;
 
 	pwm = devm_kzalloc(&pdev->dev, sizeof(*pwm), GFP_KERNEL);
-	if (!pwm) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
+	if (!pwm)
 		return -ENOMEM;
-	}
 
 	pwm->dev = &pdev->dev;
 
diff --git a/drivers/pwm/pwm-tiecap.c b/drivers/pwm/pwm-tiecap.c
index 032092c7a6a..74efbe7f20c 100644
--- a/drivers/pwm/pwm-tiecap.c
+++ b/drivers/pwm/pwm-tiecap.c
@@ -209,10 +209,8 @@ static int ecap_pwm_probe(struct platform_device *pdev)
 	u16 status;
 
 	pc = devm_kzalloc(&pdev->dev, sizeof(*pc), GFP_KERNEL);
-	if (!pc) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
+	if (!pc)
 		return -ENOMEM;
-	}
 
 	clk = devm_clk_get(&pdev->dev, "fck");
 	if (IS_ERR(clk)) {
diff --git a/drivers/pwm/pwm-tiehrpwm.c b/drivers/pwm/pwm-tiehrpwm.c
index aee4471424d..cb75133085a 100644
--- a/drivers/pwm/pwm-tiehrpwm.c
+++ b/drivers/pwm/pwm-tiehrpwm.c
@@ -138,12 +138,12 @@ static inline struct ehrpwm_pwm_chip *to_ehrpwm_pwm_chip(struct pwm_chip *chip)
 	return container_of(chip, struct ehrpwm_pwm_chip, chip);
 }
 
-static u16 ehrpwm_read(void __iomem *base, int offset)
+static inline u16 ehrpwm_read(void __iomem *base, int offset)
 {
 	return readw(base + offset);
 }
 
-static void ehrpwm_write(void __iomem *base, int offset, unsigned int val)
+static inline void ehrpwm_write(void __iomem *base, int offset, unsigned int val)
 {
 	writew(val & 0xFFFF, base + offset);
 }
@@ -440,10 +440,8 @@ static int ehrpwm_pwm_probe(struct platform_device *pdev)
 	u16 status;
 
 	pc = devm_kzalloc(&pdev->dev, sizeof(*pc), GFP_KERNEL);
-	if (!pc) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
+	if (!pc)
 		return -ENOMEM;
-	}
 
 	clk = devm_clk_get(&pdev->dev, "fck");
 	if (IS_ERR(clk)) {
@@ -531,6 +529,7 @@ static int ehrpwm_pwm_remove(struct platform_device *pdev)
 	return pwmchip_remove(&pc->chip);
 }
 
+#ifdef CONFIG_PM_SLEEP
 static void ehrpwm_pwm_save_context(struct ehrpwm_pwm_chip *pc)
 {
 	pm_runtime_get_sync(pc->chip.dev);
@@ -557,7 +556,6 @@ static void ehrpwm_pwm_restore_context(struct ehrpwm_pwm_chip *pc)
 	ehrpwm_write(pc->mmio_base, TBCTL, pc->ctx.tbctl);
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int ehrpwm_pwm_suspend(struct device *dev)
 {
 	struct ehrpwm_pwm_chip *pc = dev_get_drvdata(dev);
diff --git a/drivers/pwm/pwm-twl.c b/drivers/pwm/pwm-twl.c
index b99a50e626a..04f76725d59 100644
--- a/drivers/pwm/pwm-twl.c
+++ b/drivers/pwm/pwm-twl.c
@@ -265,14 +265,6 @@ static void twl6030_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
 
 	ret = twl_i2c_write_u8(TWL6030_MODULE_ID1, val, TWL6030_TOGGLE3_REG);
 	if (ret < 0) {
-		dev_err(chip->dev, "%s: Failed to read TOGGLE3\n", pwm->label);
-		goto out;
-	}
-
-	val |= TWL6030_PWM_TOGGLE(pwm->hwpwm, TWL6030_PWMXS | TWL6030_PWMXEN);
-
-	ret = twl_i2c_write_u8(TWL6030_MODULE_ID1, val, TWL6030_TOGGLE3_REG);
-	if (ret < 0) {
 		dev_err(chip->dev, "%s: Failed to disable PWM\n", pwm->label);
 		goto out;
 	}
diff --git a/drivers/pwm/pwm-vt8500.c b/drivers/pwm/pwm-vt8500.c
index 323125abf3f..652e6b5b859 100644
--- a/drivers/pwm/pwm-vt8500.c
+++ b/drivers/pwm/pwm-vt8500.c
@@ -211,10 +211,8 @@ static int vt8500_pwm_probe(struct platform_device *pdev)
 	}
 
 	chip = devm_kzalloc(&pdev->dev, sizeof(*chip), GFP_KERNEL);
-	if (chip == NULL) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
+	if (chip == NULL)
 		return -ENOMEM;
-	}
 
 	chip->chip.dev = &pdev->dev;
 	chip->chip.ops = &vt8500_pwm_ops;
diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c
index 9b60b1f3261..44341dc5b14 100644
--- a/drivers/rapidio/devices/tsi721_dma.c
+++ b/drivers/rapidio/devices/tsi721_dma.c
@@ -287,6 +287,12 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan)
 			"desc %p not ACKed\n", tx_desc);
 	}
 
+	if (ret == NULL) {
+		dev_dbg(bdma_chan->dchan.device->dev,
+			"%s: unable to obtain tx descriptor\n", __func__);
+		goto err_out;
+	}
+
 	i = bdma_chan->wr_count_next % bdma_chan->bd_num;
 	if (i == bdma_chan->bd_num - 1) {
 		i = 0;
@@ -297,7 +303,7 @@ struct tsi721_tx_desc *tsi721_desc_get(struct tsi721_bdma_chan *bdma_chan)
 	tx_desc->txd.phys = bdma_chan->bd_phys +
 				i * sizeof(struct tsi721_dma_desc);
 	tx_desc->hw_desc = &((struct tsi721_dma_desc *)bdma_chan->bd_base)[i];
-
+err_out:
 	spin_unlock_bh(&bdma_chan->lock);
 
 	return ret;
diff --git a/drivers/regulator/as3722-regulator.c b/drivers/regulator/as3722-regulator.c
index 85585219ce8..ad9e0c9b7da 100644
--- a/drivers/regulator/as3722-regulator.c
+++ b/drivers/regulator/as3722-regulator.c
@@ -433,6 +433,7 @@ static struct regulator_ops as3722_ldo3_extcntrl_ops = {
 };
 
 static const struct regulator_linear_range as3722_ldo_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0x00, 0x00, 0),
 	REGULATOR_LINEAR_RANGE(825000, 0x01, 0x24, 25000),
 	REGULATOR_LINEAR_RANGE(1725000, 0x40, 0x7F, 25000),
 };
@@ -609,6 +610,7 @@ static bool as3722_sd0_is_low_voltage(struct as3722_regulators *as3722_regs)
 }
 
 static const struct regulator_linear_range as3722_sd2345_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0x00, 0x00, 0),
 	REGULATOR_LINEAR_RANGE(612500, 0x01, 0x40, 12500),
 	REGULATOR_LINEAR_RANGE(1425000, 0x41, 0x70, 25000),
 	REGULATOR_LINEAR_RANGE(2650000, 0x71, 0x7F, 50000),
diff --git a/drivers/regulator/bcm590xx-regulator.c b/drivers/regulator/bcm590xx-regulator.c
index 57544e254a7..58ece59367a 100644
--- a/drivers/regulator/bcm590xx-regulator.c
+++ b/drivers/regulator/bcm590xx-regulator.c
@@ -119,6 +119,10 @@ static const unsigned int ldo_c_table[] = {
 	2900000, 3000000, 3300000,
 };
 
+static const unsigned int ldo_vbus[] = {
+	5000000,
+};
+
 /* DCDC group CSR: supported voltages in microvolts */
 static const struct regulator_linear_range dcdc_csr_ranges[] = {
 	REGULATOR_LINEAR_RANGE(860000, 2, 50, 10000),
@@ -192,6 +196,7 @@ static struct bcm590xx_info bcm590xx_regs[] = {
 	BCM590XX_REG_TABLE(gpldo4, ldo_a_table),
 	BCM590XX_REG_TABLE(gpldo5, ldo_a_table),
 	BCM590XX_REG_TABLE(gpldo6, ldo_a_table),
+	BCM590XX_REG_TABLE(vbus, ldo_vbus),
 };
 
 struct bcm590xx_reg {
diff --git a/drivers/regulator/ltc3589.c b/drivers/regulator/ltc3589.c
index 110a99ee116..c8105182b8b 100644
--- a/drivers/regulator/ltc3589.c
+++ b/drivers/regulator/ltc3589.c
@@ -255,7 +255,7 @@ static int ltc3589_parse_regulators_dt(struct ltc3589 *ltc3589)
 	struct device_node *node;
 	int i, ret;
 
-	node = of_find_node_by_name(dev->of_node, "regulators");
+	node = of_get_child_by_name(dev->of_node, "regulators");
 	if (!node) {
 		dev_err(dev, "regulators node not found\n");
 		return -EINVAL;
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index 864ed02ce4b..93b4ad84290 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -37,12 +37,14 @@ struct regs_info {
 };
 
 static const struct regulator_linear_range smps_low_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(500000, 0x1, 0x6, 0),
 	REGULATOR_LINEAR_RANGE(510000, 0x7, 0x79, 10000),
 	REGULATOR_LINEAR_RANGE(1650000, 0x7A, 0x7f, 0),
 };
 
 static const struct regulator_linear_range smps_high_ranges[] = {
+	REGULATOR_LINEAR_RANGE(0, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(1000000, 0x1, 0x6, 0),
 	REGULATOR_LINEAR_RANGE(1020000, 0x7, 0x79, 20000),
 	REGULATOR_LINEAR_RANGE(3300000, 0x7A, 0x7f, 0),
@@ -323,6 +325,10 @@ static int palmas_set_mode_smps(struct regulator_dev *dev, unsigned int mode)
 	if (rail_enable)
 		palmas_smps_write(pmic->palmas,
 			palmas_regs_info[id].ctrl_addr, reg);
+
+	/* Switch the enable value to ensure this is used for enable */
+	pmic->desc[id].enable_val = pmic->current_reg_mode[id];
+
 	return 0;
 }
 
@@ -962,6 +968,14 @@ static int palmas_regulators_probe(struct platform_device *pdev)
 				return ret;
 			pmic->current_reg_mode[id] = reg &
 					PALMAS_SMPS12_CTRL_MODE_ACTIVE_MASK;
+
+			pmic->desc[id].enable_reg =
+					PALMAS_BASE_TO_REG(PALMAS_SMPS_BASE,
+						palmas_regs_info[id].ctrl_addr);
+			pmic->desc[id].enable_mask =
+					PALMAS_SMPS12_CTRL_MODE_ACTIVE_MASK;
+			/* set_mode overrides this value */
+			pmic->desc[id].enable_val = SMPS_CTRL_MODE_ON;
 		}
 
 		pmic->desc[id].type = REGULATOR_VOLTAGE;
diff --git a/drivers/regulator/tps65218-regulator.c b/drivers/regulator/tps65218-regulator.c
index 69b4b775041..9effe48c605 100644
--- a/drivers/regulator/tps65218-regulator.c
+++ b/drivers/regulator/tps65218-regulator.c
@@ -209,7 +209,7 @@ static const struct regulator_desc regulators[] = {
 			   1, -1, -1, TPS65218_REG_ENABLE1,
 			   TPS65218_ENABLE1_DC6_EN, NULL, NULL, 0, 0),
 	TPS65218_REGULATOR("LDO1", TPS65218_LDO_1, tps65218_ldo1_dcdc34_ops, 64,
-			   TPS65218_REG_CONTROL_DCDC4,
+			   TPS65218_REG_CONTROL_LDO1,
 			   TPS65218_CONTROL_LDO1_MASK, TPS65218_REG_ENABLE2,
 			   TPS65218_ENABLE2_LDO1_EN, NULL, ldo1_dcdc3_ranges,
 			   2, 0),
@@ -240,6 +240,7 @@ static int tps65218_regulator_probe(struct platform_device *pdev)
 	config.init_data = init_data;
 	config.driver_data = tps;
 	config.regmap = tps->regmap;
+	config.of_node = pdev->dev.of_node;
 
 	rdev = devm_regulator_register(&pdev->dev, &regulators[id], &config);
 	if (IS_ERR(rdev)) {
diff --git a/drivers/regulator/virtual.c b/drivers/regulator/virtual.c
index f53e78b9a84..6ff95b04598 100644
--- a/drivers/regulator/virtual.c
+++ b/drivers/regulator/virtual.c
@@ -266,11 +266,11 @@ static ssize_t set_mode(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(min_microvolts, 0666, show_min_uV, set_min_uV);
-static DEVICE_ATTR(max_microvolts, 0666, show_max_uV, set_max_uV);
-static DEVICE_ATTR(min_microamps, 0666, show_min_uA, set_min_uA);
-static DEVICE_ATTR(max_microamps, 0666, show_max_uA, set_max_uA);
-static DEVICE_ATTR(mode, 0666, show_mode, set_mode);
+static DEVICE_ATTR(min_microvolts, 0664, show_min_uV, set_min_uV);
+static DEVICE_ATTR(max_microvolts, 0664, show_max_uV, set_max_uV);
+static DEVICE_ATTR(min_microamps, 0664, show_min_uA, set_min_uA);
+static DEVICE_ATTR(max_microamps, 0664, show_max_uA, set_max_uA);
+static DEVICE_ATTR(mode, 0664, show_mode, set_mode);
 
 static struct attribute *regulator_virtual_attributes[] = {
 	&dev_attr_min_microvolts.attr,
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index ce1743d0b67..5e343bab945 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -44,7 +44,7 @@ config STE_MODEM_RPROC
 config DA8XX_REMOTEPROC
 	tristate "DA8xx/OMAP-L13x remoteproc support"
 	depends on ARCH_DAVINCI_DA8XX
-	select CMA
+	select CMA if MMU
 	select REMOTEPROC
 	select RPMSG
 	help
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 71988b69eca..0754f5c7cb3 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -530,11 +530,11 @@ config RTC_DRV_RV3029C2
 	  will be called rtc-rv3029c2.
 
 config RTC_DRV_S5M
-	tristate "Samsung S5M series"
+	tristate "Samsung S2M/S5M series"
 	depends on MFD_SEC_CORE
 	help
 	  If you say yes here you will get support for the
-	  RTC of Samsung S5M PMIC series.
+	  RTC of Samsung S2MPS14 and S5M PMIC series.
 
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-s5m.
diff --git a/drivers/rtc/rtc-puv3.c b/drivers/rtc/rtc-puv3.c
index 1ecfe3bd92a..1cff2a21db6 100644
--- a/drivers/rtc/rtc-puv3.c
+++ b/drivers/rtc/rtc-puv3.c
@@ -71,7 +71,7 @@ static int puv3_rtc_setpie(struct device *dev, int enabled)
 {
 	unsigned int tmp;
 
-	dev_debug(dev, "%s: pie=%d\n", __func__, enabled);
+	dev_dbg(dev, "%s: pie=%d\n", __func__, enabled);
 
 	spin_lock_irq(&puv3_rtc_pie_lock);
 	tmp = readl(RTC_RTSR) & ~RTC_RTSR_HZE;
@@ -140,7 +140,7 @@ static int puv3_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	rtc_tm_to_time(tm, &rtcalarm_count);
 	writel(rtcalarm_count, RTC_RTAR);
 
-	puv3_rtc_setaie(&dev->dev, alrm->enabled);
+	puv3_rtc_setaie(dev, alrm->enabled);
 
 	if (alrm->enabled)
 		enable_irq_wake(puv3_rtc_alarmno);
diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index 8ec2d6a1dbe..8f06250a038 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2013 Samsung Electronics Co., Ltd
+ * Copyright (c) 2013-2014 Samsung Electronics Co., Ltd
  *	http://www.samsung.com
  *
  *  Copyright (C) 2013 Google, Inc
@@ -17,27 +17,76 @@
 
 #include <linux/module.h>
 #include <linux/i2c.h>
-#include <linux/slab.h>
 #include <linux/bcd.h>
-#include <linux/bitops.h>
 #include <linux/regmap.h>
 #include <linux/rtc.h>
-#include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/samsung/core.h>
 #include <linux/mfd/samsung/irq.h>
 #include <linux/mfd/samsung/rtc.h>
+#include <linux/mfd/samsung/s2mps14.h>
 
 /*
  * Maximum number of retries for checking changes in UDR field
- * of SEC_RTC_UDR_CON register (to limit possible endless loop).
+ * of S5M_RTC_UDR_CON register (to limit possible endless loop).
  *
  * After writing to RTC registers (setting time or alarm) read the UDR field
- * in SEC_RTC_UDR_CON register. UDR is auto-cleared when data have
+ * in S5M_RTC_UDR_CON register. UDR is auto-cleared when data have
  * been transferred.
  */
 #define UDR_READ_RETRY_CNT	5
 
+/* Registers used by the driver which are different between chipsets. */
+struct s5m_rtc_reg_config {
+	/* Number of registers used for setting time/alarm0/alarm1 */
+	unsigned int regs_count;
+	/* First register for time, seconds */
+	unsigned int time;
+	/* RTC control register */
+	unsigned int ctrl;
+	/* First register for alarm 0, seconds */
+	unsigned int alarm0;
+	/* First register for alarm 1, seconds */
+	unsigned int alarm1;
+	/* SMPL/WTSR register */
+	unsigned int smpl_wtsr;
+	/*
+	 * Register for update flag (UDR). Typically setting UDR field to 1
+	 * will enable update of time or alarm register. Then it will be
+	 * auto-cleared after successful update.
+	 */
+	unsigned int rtc_udr_update;
+	/* Mask for UDR field in 'rtc_udr_update' register */
+	unsigned int rtc_udr_mask;
+};
+
+/* Register map for S5M8763 and S5M8767 */
+static const struct s5m_rtc_reg_config s5m_rtc_regs = {
+	.regs_count		= 8,
+	.time			= S5M_RTC_SEC,
+	.ctrl			= S5M_ALARM1_CONF,
+	.alarm0			= S5M_ALARM0_SEC,
+	.alarm1			= S5M_ALARM1_SEC,
+	.smpl_wtsr		= S5M_WTSR_SMPL_CNTL,
+	.rtc_udr_update		= S5M_RTC_UDR_CON,
+	.rtc_udr_mask		= S5M_RTC_UDR_MASK,
+};
+
+/*
+ * Register map for S2MPS14.
+ * It may be also suitable for S2MPS11 but this was not tested.
+ */
+static const struct s5m_rtc_reg_config s2mps_rtc_regs = {
+	.regs_count		= 7,
+	.time			= S2MPS_RTC_SEC,
+	.ctrl			= S2MPS_RTC_CTRL,
+	.alarm0			= S2MPS_ALARM0_SEC,
+	.alarm1			= S2MPS_ALARM1_SEC,
+	.smpl_wtsr		= S2MPS_WTSR_SMPL_CNTL,
+	.rtc_udr_update		= S2MPS_RTC_UDR_CON,
+	.rtc_udr_mask		= S2MPS_RTC_WUDR_MASK,
+};
+
 struct s5m_rtc_info {
 	struct device *dev;
 	struct i2c_client *i2c;
@@ -48,13 +97,14 @@ struct s5m_rtc_info {
 	int device_type;
 	int rtc_24hr_mode;
 	bool wtsr_smpl;
+	const struct s5m_rtc_reg_config	*regs;
 };
 
 static const struct regmap_config s5m_rtc_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 
-	.max_register = SEC_RTC_REG_MAX,
+	.max_register = S5M_RTC_REG_MAX,
 };
 
 static const struct regmap_config s2mps14_rtc_regmap_config = {
@@ -119,8 +169,9 @@ static inline int s5m8767_wait_for_udr_update(struct s5m_rtc_info *info)
 	unsigned int data;
 
 	do {
-		ret = regmap_read(info->regmap, SEC_RTC_UDR_CON, &data);
-	} while (--retry && (data & RTC_UDR_MASK) && !ret);
+		ret = regmap_read(info->regmap, info->regs->rtc_udr_update,
+				&data);
+	} while (--retry && (data & info->regs->rtc_udr_mask) && !ret);
 
 	if (!retry)
 		dev_err(info->dev, "waiting for UDR update, reached max number of retries\n");
@@ -128,21 +179,53 @@ static inline int s5m8767_wait_for_udr_update(struct s5m_rtc_info *info)
 	return ret;
 }
 
+static inline int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info,
+		struct rtc_wkalrm *alarm)
+{
+	int ret;
+	unsigned int val;
+
+	switch (info->device_type) {
+	case S5M8767X:
+	case S5M8763X:
+		ret = regmap_read(info->regmap, S5M_RTC_STATUS, &val);
+		val &= S5M_ALARM0_STATUS;
+		break;
+	case S2MPS14X:
+		ret = regmap_read(info->s5m87xx->regmap_pmic, S2MPS14_REG_ST2,
+				&val);
+		val &= S2MPS_ALARM0_STATUS;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (ret < 0)
+		return ret;
+
+	if (val)
+		alarm->pending = 1;
+	else
+		alarm->pending = 0;
+
+	return 0;
+}
+
 static inline int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info)
 {
 	int ret;
 	unsigned int data;
 
-	ret = regmap_read(info->regmap, SEC_RTC_UDR_CON, &data);
+	ret = regmap_read(info->regmap, info->regs->rtc_udr_update, &data);
 	if (ret < 0) {
 		dev_err(info->dev, "failed to read update reg(%d)\n", ret);
 		return ret;
 	}
 
-	data |= RTC_TIME_EN_MASK;
-	data |= RTC_UDR_MASK;
+	data |= info->regs->rtc_udr_mask;
+	if (info->device_type == S5M8763X || info->device_type == S5M8767X)
+		data |= S5M_RTC_TIME_EN_MASK;
 
-	ret = regmap_write(info->regmap, SEC_RTC_UDR_CON, data);
+	ret = regmap_write(info->regmap, info->regs->rtc_udr_update, data);
 	if (ret < 0) {
 		dev_err(info->dev, "failed to write update reg(%d)\n", ret);
 		return ret;
@@ -158,17 +241,27 @@ static inline int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info)
 	int ret;
 	unsigned int data;
 
-	ret = regmap_read(info->regmap, SEC_RTC_UDR_CON, &data);
+	ret = regmap_read(info->regmap, info->regs->rtc_udr_update, &data);
 	if (ret < 0) {
 		dev_err(info->dev, "%s: fail to read update reg(%d)\n",
 			__func__, ret);
 		return ret;
 	}
 
-	data &= ~RTC_TIME_EN_MASK;
-	data |= RTC_UDR_MASK;
+	data |= info->regs->rtc_udr_mask;
+	switch (info->device_type) {
+	case S5M8763X:
+	case S5M8767X:
+		data &= ~S5M_RTC_TIME_EN_MASK;
+		break;
+	case S2MPS14X:
+		data |= S2MPS_RTC_RUDR_MASK;
+		break;
+	default:
+		return -EINVAL;
+	}
 
-	ret = regmap_write(info->regmap, SEC_RTC_UDR_CON, data);
+	ret = regmap_write(info->regmap, info->regs->rtc_udr_update, data);
 	if (ret < 0) {
 		dev_err(info->dev, "%s: fail to write update reg(%d)\n",
 			__func__, ret);
@@ -215,10 +308,22 @@ static void s5m8763_tm_to_data(struct rtc_time *tm, u8 *data)
 static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct s5m_rtc_info *info = dev_get_drvdata(dev);
-	u8 data[8];
+	u8 data[info->regs->regs_count];
 	int ret;
 
-	ret = regmap_bulk_read(info->regmap, SEC_RTC_SEC, data, 8);
+	if (info->device_type == S2MPS14X) {
+		ret = regmap_update_bits(info->regmap,
+				info->regs->rtc_udr_update,
+				S2MPS_RTC_RUDR_MASK, S2MPS_RTC_RUDR_MASK);
+		if (ret) {
+			dev_err(dev,
+				"Failed to prepare registers for time reading: %d\n",
+				ret);
+			return ret;
+		}
+	}
+	ret = regmap_bulk_read(info->regmap, info->regs->time, data,
+			info->regs->regs_count);
 	if (ret < 0)
 		return ret;
 
@@ -228,6 +333,7 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm)
 		break;
 
 	case S5M8767X:
+	case S2MPS14X:
 		s5m8767_data_to_tm(data, tm, info->rtc_24hr_mode);
 		break;
 
@@ -245,7 +351,7 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm)
 static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
 	struct s5m_rtc_info *info = dev_get_drvdata(dev);
-	u8 data[8];
+	u8 data[info->regs->regs_count];
 	int ret = 0;
 
 	switch (info->device_type) {
@@ -253,6 +359,7 @@ static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm)
 		s5m8763_tm_to_data(tm, data);
 		break;
 	case S5M8767X:
+	case S2MPS14X:
 		ret = s5m8767_tm_to_data(tm, data);
 		break;
 	default:
@@ -266,7 +373,8 @@ static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm)
 		1900 + tm->tm_year, 1 + tm->tm_mon, tm->tm_mday,
 		tm->tm_hour, tm->tm_min, tm->tm_sec, tm->tm_wday);
 
-	ret = regmap_raw_write(info->regmap, SEC_RTC_SEC, data, 8);
+	ret = regmap_raw_write(info->regmap, info->regs->time, data,
+			info->regs->regs_count);
 	if (ret < 0)
 		return ret;
 
@@ -278,70 +386,60 @@ static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm)
 static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 {
 	struct s5m_rtc_info *info = dev_get_drvdata(dev);
-	u8 data[8];
+	u8 data[info->regs->regs_count];
 	unsigned int val;
 	int ret, i;
 
-	ret = regmap_bulk_read(info->regmap, SEC_ALARM0_SEC, data, 8);
+	ret = regmap_bulk_read(info->regmap, info->regs->alarm0, data,
+			info->regs->regs_count);
 	if (ret < 0)
 		return ret;
 
 	switch (info->device_type) {
 	case S5M8763X:
 		s5m8763_data_to_tm(data, &alrm->time);
-		ret = regmap_read(info->regmap, SEC_ALARM0_CONF, &val);
+		ret = regmap_read(info->regmap, S5M_ALARM0_CONF, &val);
 		if (ret < 0)
 			return ret;
 
 		alrm->enabled = !!val;
-
-		ret = regmap_read(info->regmap, SEC_RTC_STATUS, &val);
-		if (ret < 0)
-			return ret;
-
 		break;
 
 	case S5M8767X:
+	case S2MPS14X:
 		s5m8767_data_to_tm(data, &alrm->time, info->rtc_24hr_mode);
-		dev_dbg(dev, "%s: %d/%d/%d %d:%d:%d(%d)\n", __func__,
-			1900 + alrm->time.tm_year, 1 + alrm->time.tm_mon,
-			alrm->time.tm_mday, alrm->time.tm_hour,
-			alrm->time.tm_min, alrm->time.tm_sec,
-			alrm->time.tm_wday);
-
 		alrm->enabled = 0;
-		for (i = 0; i < 7; i++) {
+		for (i = 0; i < info->regs->regs_count; i++) {
 			if (data[i] & ALARM_ENABLE_MASK) {
 				alrm->enabled = 1;
 				break;
 			}
 		}
-
-		alrm->pending = 0;
-		ret = regmap_read(info->regmap, SEC_RTC_STATUS, &val);
-		if (ret < 0)
-			return ret;
 		break;
 
 	default:
 		return -EINVAL;
 	}
 
-	if (val & ALARM0_STATUS)
-		alrm->pending = 1;
-	else
-		alrm->pending = 0;
+	dev_dbg(dev, "%s: %d/%d/%d %d:%d:%d(%d)\n", __func__,
+		1900 + alrm->time.tm_year, 1 + alrm->time.tm_mon,
+		alrm->time.tm_mday, alrm->time.tm_hour,
+		alrm->time.tm_min, alrm->time.tm_sec,
+		alrm->time.tm_wday);
+
+	ret = s5m_check_peding_alarm_interrupt(info, alrm);
 
 	return 0;
 }
 
 static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info)
 {
-	u8 data[8];
+	u8 data[info->regs->regs_count];
 	int ret, i;
 	struct rtc_time tm;
 
-	ret = regmap_bulk_read(info->regmap, SEC_ALARM0_SEC, data, 8);
+	ret = regmap_bulk_read(info->regmap, info->regs->alarm0, data,
+			info->regs->regs_count);
 	if (ret < 0)
 		return ret;
 
@@ -352,14 +450,16 @@ static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info)
 
 	switch (info->device_type) {
 	case S5M8763X:
-		ret = regmap_write(info->regmap, SEC_ALARM0_CONF, 0);
+		ret = regmap_write(info->regmap, S5M_ALARM0_CONF, 0);
 		break;
 
 	case S5M8767X:
-		for (i = 0; i < 7; i++)
+	case S2MPS14X:
+		for (i = 0; i < info->regs->regs_count; i++)
 			data[i] &= ~ALARM_ENABLE_MASK;
 
-		ret = regmap_raw_write(info->regmap, SEC_ALARM0_SEC, data, 8);
+		ret = regmap_raw_write(info->regmap, info->regs->alarm0, data,
+				info->regs->regs_count);
 		if (ret < 0)
 			return ret;
 
@@ -377,11 +477,12 @@ static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info)
 static int s5m_rtc_start_alarm(struct s5m_rtc_info *info)
 {
 	int ret;
-	u8 data[8];
+	u8 data[info->regs->regs_count];
 	u8 alarm0_conf;
 	struct rtc_time tm;
 
-	ret = regmap_bulk_read(info->regmap, SEC_ALARM0_SEC, data, 8);
+	ret = regmap_bulk_read(info->regmap, info->regs->alarm0, data,
+			info->regs->regs_count);
 	if (ret < 0)
 		return ret;
 
@@ -393,10 +494,11 @@ static int s5m_rtc_start_alarm(struct s5m_rtc_info *info)
 	switch (info->device_type) {
 	case S5M8763X:
 		alarm0_conf = 0x77;
-		ret = regmap_write(info->regmap, SEC_ALARM0_CONF, alarm0_conf);
+		ret = regmap_write(info->regmap, S5M_ALARM0_CONF, alarm0_conf);
 		break;
 
 	case S5M8767X:
+	case S2MPS14X:
 		data[RTC_SEC] |= ALARM_ENABLE_MASK;
 		data[RTC_MIN] |= ALARM_ENABLE_MASK;
 		data[RTC_HOUR] |= ALARM_ENABLE_MASK;
@@ -408,7 +510,8 @@ static int s5m_rtc_start_alarm(struct s5m_rtc_info *info)
 		if (data[RTC_YEAR1] & 0x7f)
 			data[RTC_YEAR1] |= ALARM_ENABLE_MASK;
 
-		ret = regmap_raw_write(info->regmap, SEC_ALARM0_SEC, data, 8);
+		ret = regmap_raw_write(info->regmap, info->regs->alarm0, data,
+				info->regs->regs_count);
 		if (ret < 0)
 			return ret;
 		ret = s5m8767_rtc_set_alarm_reg(info);
@@ -425,7 +528,7 @@ static int s5m_rtc_start_alarm(struct s5m_rtc_info *info)
 static int s5m_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 {
 	struct s5m_rtc_info *info = dev_get_drvdata(dev);
-	u8 data[8];
+	u8 data[info->regs->regs_count];
 	int ret;
 
 	switch (info->device_type) {
@@ -434,6 +537,7 @@ static int s5m_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 		break;
 
 	case S5M8767X:
+	case S2MPS14X:
 		s5m8767_tm_to_data(&alrm->time, data);
 		break;
 
@@ -450,7 +554,8 @@ static int s5m_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 	if (ret < 0)
 		return ret;
 
-	ret = regmap_raw_write(info->regmap, SEC_ALARM0_SEC, data, 8);
+	ret = regmap_raw_write(info->regmap, info->regs->alarm0, data,
+			info->regs->regs_count);
 	if (ret < 0)
 		return ret;
 
@@ -495,7 +600,7 @@ static const struct rtc_class_ops s5m_rtc_ops = {
 static void s5m_rtc_enable_wtsr(struct s5m_rtc_info *info, bool enable)
 {
 	int ret;
-	ret = regmap_update_bits(info->regmap, SEC_WTSR_SMPL_CNTL,
+	ret = regmap_update_bits(info->regmap, info->regs->smpl_wtsr,
 				 WTSR_ENABLE_MASK,
 				 enable ? WTSR_ENABLE_MASK : 0);
 	if (ret < 0)
@@ -506,7 +611,7 @@ static void s5m_rtc_enable_wtsr(struct s5m_rtc_info *info, bool enable)
 static void s5m_rtc_enable_smpl(struct s5m_rtc_info *info, bool enable)
 {
 	int ret;
-	ret = regmap_update_bits(info->regmap, SEC_WTSR_SMPL_CNTL,
+	ret = regmap_update_bits(info->regmap, info->regs->smpl_wtsr,
 				 SMPL_ENABLE_MASK,
 				 enable ? SMPL_ENABLE_MASK : 0);
 	if (ret < 0)
@@ -517,50 +622,41 @@ static void s5m_rtc_enable_smpl(struct s5m_rtc_info *info, bool enable)
 static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info)
 {
 	u8 data[2];
-	unsigned int tp_read;
 	int ret;
-	struct rtc_time tm;
 
-	ret = regmap_read(info->regmap, SEC_RTC_UDR_CON, &tp_read);
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to read control reg(%d)\n",
-			__func__, ret);
-		return ret;
-	}
+	switch (info->device_type) {
+	case S5M8763X:
+	case S5M8767X:
+		/* UDR update time. Default of 7.32 ms is too long. */
+		ret = regmap_update_bits(info->regmap, S5M_RTC_UDR_CON,
+				S5M_RTC_UDR_T_MASK, S5M_RTC_UDR_T_450_US);
+		if (ret < 0)
+			dev_err(info->dev, "%s: fail to change UDR time: %d\n",
+					__func__, ret);
 
-	/* Set RTC control register : Binary mode, 24hour mode */
-	data[0] = (1 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
-	data[1] = (0 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
+		/* Set RTC control register : Binary mode, 24hour mode */
+		data[0] = (1 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
+		data[1] = (0 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
+
+		ret = regmap_raw_write(info->regmap, S5M_ALARM0_CONF, data, 2);
+		break;
+
+	case S2MPS14X:
+		data[0] = (0 << BCD_EN_SHIFT) | (1 << MODEL24_SHIFT);
+		ret = regmap_write(info->regmap, info->regs->ctrl, data[0]);
+		break;
+
+	default:
+		return -EINVAL;
+	}
 
 	info->rtc_24hr_mode = 1;
-	ret = regmap_raw_write(info->regmap, SEC_ALARM0_CONF, data, 2);
 	if (ret < 0) {
 		dev_err(info->dev, "%s: fail to write controlm reg(%d)\n",
 			__func__, ret);
 		return ret;
 	}
 
-	/* In first boot time, Set rtc time to 1/1/2012 00:00:00(SUN) */
-	if ((tp_read & RTC_TCON_MASK) == 0) {
-		dev_dbg(info->dev, "rtc init\n");
-		tm.tm_sec = 0;
-		tm.tm_min = 0;
-		tm.tm_hour = 0;
-		tm.tm_wday = 0;
-		tm.tm_mday = 1;
-		tm.tm_mon = 0;
-		tm.tm_year = 112;
-		tm.tm_yday = 0;
-		tm.tm_isdst = 0;
-		ret = s5m_rtc_set_time(info->dev, &tm);
-	}
-
-	ret = regmap_update_bits(info->regmap, SEC_RTC_UDR_CON,
-				 RTC_TCON_MASK, tp_read | RTC_TCON_MASK);
-	if (ret < 0)
-		dev_err(info->dev, "%s: fail to update TCON reg(%d)\n",
-			__func__, ret);
-
 	return ret;
 }
 
@@ -570,7 +666,7 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 	struct sec_platform_data *pdata = s5m87xx->pdata;
 	struct s5m_rtc_info *info;
 	const struct regmap_config *regmap_cfg;
-	int ret;
+	int ret, alarm_irq;
 
 	if (!pdata) {
 		dev_err(pdev->dev.parent, "Platform data not supplied\n");
@@ -584,12 +680,18 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 	switch (pdata->device_type) {
 	case S2MPS14X:
 		regmap_cfg = &s2mps14_rtc_regmap_config;
+		info->regs = &s2mps_rtc_regs;
+		alarm_irq = S2MPS14_IRQ_RTCA0;
 		break;
 	case S5M8763X:
 		regmap_cfg = &s5m_rtc_regmap_config;
+		info->regs = &s5m_rtc_regs;
+		alarm_irq = S5M8763_IRQ_ALARM0;
 		break;
 	case S5M8767X:
 		regmap_cfg = &s5m_rtc_regmap_config;
+		info->regs = &s5m_rtc_regs;
+		alarm_irq = S5M8767_IRQ_RTCA1;
 		break;
 	default:
 		dev_err(&pdev->dev, "Device type is not supported by RTC driver\n");
@@ -615,20 +717,11 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 	info->device_type = s5m87xx->device_type;
 	info->wtsr_smpl = s5m87xx->wtsr_smpl;
 
-	switch (pdata->device_type) {
-	case S5M8763X:
-		info->irq = regmap_irq_get_virq(s5m87xx->irq_data,
-				S5M8763_IRQ_ALARM0);
-		break;
-
-	case S5M8767X:
-		info->irq = regmap_irq_get_virq(s5m87xx->irq_data,
-				S5M8767_IRQ_RTCA1);
-		break;
-
-	default:
+	info->irq = regmap_irq_get_virq(s5m87xx->irq_data, alarm_irq);
+	if (info->irq <= 0) {
 		ret = -EINVAL;
-		dev_err(&pdev->dev, "Unsupported device type: %d\n", ret);
+		dev_err(&pdev->dev, "Failed to get virtual IRQ %d\n",
+				alarm_irq);
 		goto err;
 	}
 
@@ -676,7 +769,7 @@ static void s5m_rtc_shutdown(struct platform_device *pdev)
 	if (info->wtsr_smpl) {
 		for (i = 0; i < 3; i++) {
 			s5m_rtc_enable_wtsr(info, false);
-			regmap_read(info->regmap, SEC_WTSR_SMPL_CNTL, &val);
+			regmap_read(info->regmap, info->regs->smpl_wtsr, &val);
 			pr_debug("%s: WTSR_SMPL reg(0x%02x)\n", __func__, val);
 			if (val & WTSR_ENABLE_MASK)
 				pr_emerg("%s: fail to disable WTSR\n",
@@ -730,7 +823,8 @@ static int s5m_rtc_suspend(struct device *dev)
 static SIMPLE_DEV_PM_OPS(s5m_rtc_pm_ops, s5m_rtc_suspend, s5m_rtc_resume);
 
 static const struct platform_device_id s5m_rtc_id[] = {
-	{ "s5m-rtc", 0 },
+	{ "s5m-rtc",		S5M8767X },
+	{ "s2mps14-rtc",	S2MPS14X },
 };
 
 static struct platform_driver s5m_rtc_driver = {
@@ -749,6 +843,6 @@ module_platform_driver(s5m_rtc_driver);
 
 /* Module information */
 MODULE_AUTHOR("Sangbeom Kim <sbkim73@samsung.com>");
-MODULE_DESCRIPTION("Samsung S5M RTC driver");
+MODULE_DESCRIPTION("Samsung S5M/S2MPS14 RTC driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:s5m-rtc");
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index ee0e85abe1f..0f471750327 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -593,7 +593,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	dev_info->start = dcssblk_find_lowest_addr(dev_info);
 	dev_info->end = dcssblk_find_highest_addr(dev_info);
 
-	dev_set_name(&dev_info->dev, dev_info->segment_name);
+	dev_set_name(&dev_info->dev, "%s", dev_info->segment_name);
 	dev_info->dev.release = dcssblk_release_segment;
 	dev_info->dev.groups = dcssblk_dev_attr_groups;
 	INIT_LIST_HEAD(&dev_info->lh);
diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile
index 629fcc275e9..78b6ace7edc 100644
--- a/drivers/s390/char/Makefile
+++ b/drivers/s390/char/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_SCLP_VT220_TTY) += sclp_vt220.o
 obj-$(CONFIG_SCLP_CPI) += sclp_cpi.o
 obj-$(CONFIG_SCLP_ASYNC) += sclp_async.o
 
-obj-$(CONFIG_ZVM_WATCHDOG) += vmwatchdog.o
 obj-$(CONFIG_VMLOGRDR) += vmlogrdr.o
 obj-$(CONFIG_VMCP) += vmcp.o
 
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index 15b3459f865..220acb4cbee 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -633,7 +633,6 @@ raw3270_reset_device_cb(struct raw3270_request *rq, void *data)
 	} else
 		raw3270_writesf_readpart(rp);
 	memset(&rp->init_reset, 0, sizeof(rp->init_reset));
-	memset(&rp->init_data, 0, sizeof(rp->init_data));
 }
 
 static int
diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c
index cd9c9190959..b9a9f721716 100644
--- a/drivers/s390/char/sclp_vt220.c
+++ b/drivers/s390/char/sclp_vt220.c
@@ -838,8 +838,6 @@ sclp_vt220_con_init(void)
 {
 	int rc;
 
-	if (!CONSOLE_IS_SCLP)
-		return 0;
 	rc = __sclp_vt220_init(sclp_console_pages);
 	if (rc)
 		return rc;
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index cf31d3321da..a8848db7b09 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -761,7 +761,7 @@ static int vmlogrdr_register_device(struct vmlogrdr_priv_t *priv)
 
 	dev = kzalloc(sizeof(struct device), GFP_KERNEL);
 	if (dev) {
-		dev_set_name(dev, priv->internal_name);
+		dev_set_name(dev, "%s", priv->internal_name);
 		dev->bus = &iucv_bus;
 		dev->parent = iucv_root;
 		dev->driver = &vmlogrdr_driver;
diff --git a/drivers/s390/char/vmwatchdog.c b/drivers/s390/char/vmwatchdog.c
deleted file mode 100644
index d5eac985976..00000000000
--- a/drivers/s390/char/vmwatchdog.c
+++ /dev/null
@@ -1,338 +0,0 @@
-/*
- * Watchdog implementation based on z/VM Watchdog Timer API
- *
- * Copyright IBM Corp. 2004, 2009
- *
- * The user space watchdog daemon can use this driver as
- * /dev/vmwatchdog to have z/VM execute the specified CP
- * command when the timeout expires. The default command is
- * "IPL", which which cause an immediate reboot.
- */
-#define KMSG_COMPONENT "vmwatchdog"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
-#include <linux/init.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/miscdevice.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/slab.h>
-#include <linux/suspend.h>
-#include <linux/watchdog.h>
-
-#include <asm/ebcdic.h>
-#include <asm/io.h>
-#include <asm/uaccess.h>
-
-#define MAX_CMDLEN 240
-#define MIN_INTERVAL 15
-static char vmwdt_cmd[MAX_CMDLEN] = "IPL";
-static bool vmwdt_conceal;
-
-static bool vmwdt_nowayout = WATCHDOG_NOWAYOUT;
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arnd Bergmann <arndb@de.ibm.com>");
-MODULE_DESCRIPTION("z/VM Watchdog Timer");
-module_param_string(cmd, vmwdt_cmd, MAX_CMDLEN, 0644);
-MODULE_PARM_DESC(cmd, "CP command that is run when the watchdog triggers");
-module_param_named(conceal, vmwdt_conceal, bool, 0644);
-MODULE_PARM_DESC(conceal, "Enable the CONCEAL CP option while the watchdog "
-		" is active");
-module_param_named(nowayout, vmwdt_nowayout, bool, 0);
-MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started"
-		" (default=CONFIG_WATCHDOG_NOWAYOUT)");
-MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
-
-static unsigned int vmwdt_interval = 60;
-static unsigned long vmwdt_is_open;
-static int vmwdt_expect_close;
-
-static DEFINE_MUTEX(vmwdt_mutex);
-
-#define VMWDT_OPEN	0	/* devnode is open or suspend in progress */
-#define VMWDT_RUNNING	1	/* The watchdog is armed */
-
-enum vmwdt_func {
-	/* function codes */
-	wdt_init   = 0,
-	wdt_change = 1,
-	wdt_cancel = 2,
-	/* flags */
-	wdt_conceal = 0x80000000,
-};
-
-static int __diag288(enum vmwdt_func func, unsigned int timeout,
-			    char *cmd, size_t len)
-{
-	register unsigned long __func asm("2") = func;
-	register unsigned long __timeout asm("3") = timeout;
-	register unsigned long __cmdp asm("4") = virt_to_phys(cmd);
-	register unsigned long __cmdl asm("5") = len;
-	int err;
-
-	err = -EINVAL;
-	asm volatile(
-		"	diag	%1,%3,0x288\n"
-		"0:	la	%0,0\n"
-		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (err) : "d"(__func), "d"(__timeout),
-		  "d"(__cmdp), "d"(__cmdl) : "1", "cc");
-	return err;
-}
-
-static int vmwdt_keepalive(void)
-{
-	/* we allocate new memory every time to avoid having
-	 * to track the state. static allocation is not an
-	 * option since that might not be contiguous in real
-	 * storage in case of a modular build */
-	static char *ebc_cmd;
-	size_t len;
-	int ret;
-	unsigned int func;
-
-	ebc_cmd = kmalloc(MAX_CMDLEN, GFP_KERNEL);
-	if (!ebc_cmd)
-		return -ENOMEM;
-
-	len = strlcpy(ebc_cmd, vmwdt_cmd, MAX_CMDLEN);
-	ASCEBC(ebc_cmd, MAX_CMDLEN);
-	EBC_TOUPPER(ebc_cmd, MAX_CMDLEN);
-
-	func = vmwdt_conceal ? (wdt_init | wdt_conceal) : wdt_init;
-	set_bit(VMWDT_RUNNING, &vmwdt_is_open);
-	ret = __diag288(func, vmwdt_interval, ebc_cmd, len);
-	WARN_ON(ret != 0);
-	kfree(ebc_cmd);
-	return ret;
-}
-
-static int vmwdt_disable(void)
-{
-	char cmd[] = {'\0'};
-	int ret = __diag288(wdt_cancel, 0, cmd, 0);
-	WARN_ON(ret != 0);
-	clear_bit(VMWDT_RUNNING, &vmwdt_is_open);
-	return ret;
-}
-
-static int __init vmwdt_probe(void)
-{
-	/* there is no real way to see if the watchdog is supported,
-	 * so we try initializing it with a NOP command ("BEGIN")
-	 * that won't cause any harm even if the following disable
-	 * fails for some reason */
-	char ebc_begin[] = {
-		194, 197, 199, 201, 213
-	};
-	if (__diag288(wdt_init, 15, ebc_begin, sizeof(ebc_begin)) != 0)
-		return -EINVAL;
-	return vmwdt_disable();
-}
-
-static int vmwdt_open(struct inode *i, struct file *f)
-{
-	int ret;
-	if (test_and_set_bit(VMWDT_OPEN, &vmwdt_is_open))
-		return -EBUSY;
-	ret = vmwdt_keepalive();
-	if (ret)
-		clear_bit(VMWDT_OPEN, &vmwdt_is_open);
-	return ret ? ret : nonseekable_open(i, f);
-}
-
-static int vmwdt_close(struct inode *i, struct file *f)
-{
-	if (vmwdt_expect_close == 42)
-		vmwdt_disable();
-	vmwdt_expect_close = 0;
-	clear_bit(VMWDT_OPEN, &vmwdt_is_open);
-	return 0;
-}
-
-static struct watchdog_info vmwdt_info = {
-	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
-	.firmware_version = 0,
-	.identity = "z/VM Watchdog Timer",
-};
-
-static int __vmwdt_ioctl(unsigned int cmd, unsigned long arg)
-{
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		if (copy_to_user((void __user *)arg, &vmwdt_info,
-					sizeof(vmwdt_info)))
-			return -EFAULT;
-		return 0;
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, (int __user *)arg);
-	case WDIOC_GETTEMP:
-		return -EINVAL;
-	case WDIOC_SETOPTIONS:
-		{
-			int options, ret;
-			if (get_user(options, (int __user *)arg))
-				return -EFAULT;
-			ret = -EINVAL;
-			if (options & WDIOS_DISABLECARD) {
-				ret = vmwdt_disable();
-				if (ret)
-					return ret;
-			}
-			if (options & WDIOS_ENABLECARD) {
-				ret = vmwdt_keepalive();
-			}
-			return ret;
-		}
-	case WDIOC_GETTIMEOUT:
-		return put_user(vmwdt_interval, (int __user *)arg);
-	case WDIOC_SETTIMEOUT:
-		{
-			int interval;
-			if (get_user(interval, (int __user *)arg))
-				return -EFAULT;
-			if (interval < MIN_INTERVAL)
-				return -EINVAL;
-			vmwdt_interval = interval;
-		}
-		return vmwdt_keepalive();
-	case WDIOC_KEEPALIVE:
-		return vmwdt_keepalive();
-	}
-	return -EINVAL;
-}
-
-static long vmwdt_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
-	int rc;
-
-	mutex_lock(&vmwdt_mutex);
-	rc = __vmwdt_ioctl(cmd, arg);
-	mutex_unlock(&vmwdt_mutex);
-	return (long) rc;
-}
-
-static ssize_t vmwdt_write(struct file *f, const char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	if(count) {
-		if (!vmwdt_nowayout) {
-			size_t i;
-
-			/* note: just in case someone wrote the magic character
-			 * five months ago... */
-			vmwdt_expect_close = 0;
-
-			for (i = 0; i != count; i++) {
-				char c;
-				if (get_user(c, buf+i))
-					return -EFAULT;
-				if (c == 'V')
-					vmwdt_expect_close = 42;
-			}
-		}
-		/* someone wrote to us, we should restart timer */
-		vmwdt_keepalive();
-	}
-	return count;
-}
-
-static int vmwdt_resume(void)
-{
-	clear_bit(VMWDT_OPEN, &vmwdt_is_open);
-	return NOTIFY_DONE;
-}
-
-/*
- * It makes no sense to go into suspend while the watchdog is running.
- * Depending on the memory size, the watchdog might trigger, while we
- * are still saving the memory.
- * We reuse the open flag to ensure that suspend and watchdog open are
- * exclusive operations
- */
-static int vmwdt_suspend(void)
-{
-	if (test_and_set_bit(VMWDT_OPEN, &vmwdt_is_open)) {
-		pr_err("The system cannot be suspended while the watchdog"
-			" is in use\n");
-		return notifier_from_errno(-EBUSY);
-	}
-	if (test_bit(VMWDT_RUNNING, &vmwdt_is_open)) {
-		clear_bit(VMWDT_OPEN, &vmwdt_is_open);
-		pr_err("The system cannot be suspended while the watchdog"
-			" is running\n");
-		return notifier_from_errno(-EBUSY);
-	}
-	return NOTIFY_DONE;
-}
-
-/*
- * This function is called for suspend and resume.
- */
-static int vmwdt_power_event(struct notifier_block *this, unsigned long event,
-			     void *ptr)
-{
-	switch (event) {
-	case PM_POST_HIBERNATION:
-	case PM_POST_SUSPEND:
-		return vmwdt_resume();
-	case PM_HIBERNATION_PREPARE:
-	case PM_SUSPEND_PREPARE:
-		return vmwdt_suspend();
-	default:
-		return NOTIFY_DONE;
-	}
-}
-
-static struct notifier_block vmwdt_power_notifier = {
-	.notifier_call = vmwdt_power_event,
-};
-
-static const struct file_operations vmwdt_fops = {
-	.open    = &vmwdt_open,
-	.release = &vmwdt_close,
-	.unlocked_ioctl = &vmwdt_ioctl,
-	.write   = &vmwdt_write,
-	.owner   = THIS_MODULE,
-	.llseek  = noop_llseek,
-};
-
-static struct miscdevice vmwdt_dev = {
-	.minor      = WATCHDOG_MINOR,
-	.name       = "watchdog",
-	.fops       = &vmwdt_fops,
-};
-
-static int __init vmwdt_init(void)
-{
-	int ret;
-
-	ret = vmwdt_probe();
-	if (ret)
-		return ret;
-	ret = register_pm_notifier(&vmwdt_power_notifier);
-	if (ret)
-		return ret;
-	/*
-	 * misc_register() has to be the last action in module_init(), because
-	 * file operations will be available right after this.
-	 */
-	ret = misc_register(&vmwdt_dev);
-	if (ret) {
-		unregister_pm_notifier(&vmwdt_power_notifier);
-		return ret;
-	}
-	return 0;
-}
-module_init(vmwdt_init);
-
-static void __exit vmwdt_exit(void)
-{
-	unregister_pm_notifier(&vmwdt_power_notifier);
-	misc_deregister(&vmwdt_dev);
-}
-module_exit(vmwdt_exit);
diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c
index 445564c790f..00bfbee0af9 100644
--- a/drivers/s390/cio/airq.c
+++ b/drivers/s390/cio/airq.c
@@ -196,11 +196,11 @@ EXPORT_SYMBOL(airq_iv_release);
  */
 unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num)
 {
-	unsigned long bit, i;
+	unsigned long bit, i, flags;
 
 	if (!iv->avail || num == 0)
 		return -1UL;
-	spin_lock(&iv->lock);
+	spin_lock_irqsave(&iv->lock, flags);
 	bit = find_first_bit_inv(iv->avail, iv->bits);
 	while (bit + num <= iv->bits) {
 		for (i = 1; i < num; i++)
@@ -218,9 +218,8 @@ unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num)
 	}
 	if (bit + num > iv->bits)
 		bit = -1UL;
-	spin_unlock(&iv->lock);
+	spin_unlock_irqrestore(&iv->lock, flags);
 	return bit;
-
 }
 EXPORT_SYMBOL(airq_iv_alloc);
 
@@ -232,11 +231,11 @@ EXPORT_SYMBOL(airq_iv_alloc);
  */
 void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num)
 {
-	unsigned long i;
+	unsigned long i, flags;
 
 	if (!iv->avail || num == 0)
 		return;
-	spin_lock(&iv->lock);
+	spin_lock_irqsave(&iv->lock, flags);
 	for (i = 0; i < num; i++) {
 		/* Clear (possibly left over) interrupt bit */
 		clear_bit_inv(bit + i, iv->vector);
@@ -248,7 +247,7 @@ void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num)
 		while (iv->end > 0 && !test_bit_inv(iv->end - 1, iv->avail))
 			iv->end--;
 	}
-	spin_unlock(&iv->lock);
+	spin_unlock_irqrestore(&iv->lock, flags);
 }
 EXPORT_SYMBOL(airq_iv_free);
 
diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index dfd7bc681c2..e443b0d0b23 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -184,7 +184,7 @@ static ssize_t ccwgroup_ungroup_store(struct device *dev,
 				      const char *buf, size_t count)
 {
 	struct ccwgroup_device *gdev = to_ccwgroupdev(dev);
-	int rc;
+	int rc = 0;
 
 	/* Prevent concurrent online/offline processing and ungrouping. */
 	if (atomic_cmpxchg(&gdev->onoff, 0, 1) != 0)
@@ -196,11 +196,12 @@ static ssize_t ccwgroup_ungroup_store(struct device *dev,
 
 	if (device_remove_file_self(dev, attr))
 		ccwgroup_ungroup(gdev);
+	else
+		rc = -ENODEV;
 out:
 	if (rc) {
-		if (rc != -EAGAIN)
-			/* Release onoff "lock" when ungrouping failed. */
-			atomic_set(&gdev->onoff, 0);
+		/* Release onoff "lock" when ungrouping failed. */
+		atomic_set(&gdev->onoff, 0);
 		return rc;
 	}
 	return count;
@@ -227,6 +228,7 @@ static void ccwgroup_ungroup_workfn(struct work_struct *work)
 		container_of(work, struct ccwgroup_device, ungroup_work);
 
 	ccwgroup_ungroup(gdev);
+	put_device(&gdev->dev);
 }
 
 static void ccwgroup_release(struct device *dev)
@@ -412,8 +414,10 @@ static int ccwgroup_notifier(struct notifier_block *nb, unsigned long action,
 {
 	struct ccwgroup_device *gdev = to_ccwgroupdev(data);
 
-	if (action == BUS_NOTIFY_UNBIND_DRIVER)
+	if (action == BUS_NOTIFY_UNBIND_DRIVER) {
+		get_device(&gdev->dev);
 		schedule_work(&gdev->ungroup_work);
+	}
 
 	return NOTIFY_OK;
 }
@@ -582,11 +586,7 @@ void ccwgroup_driver_unregister(struct ccwgroup_driver *cdriver)
 					 __ccwgroup_match_all))) {
 		struct ccwgroup_device *gdev = to_ccwgroupdev(dev);
 
-		mutex_lock(&gdev->reg_mutex);
-		__ccwgroup_remove_symlinks(gdev);
-		device_unregister(dev);
-		__ccwgroup_remove_cdev_refs(gdev);
-		mutex_unlock(&gdev->reg_mutex);
+		ccwgroup_ungroup(gdev);
 		put_device(dev);
 	}
 	driver_unregister(&cdriver->driver);
@@ -633,13 +633,7 @@ void ccwgroup_remove_ccwdev(struct ccw_device *cdev)
 	get_device(&gdev->dev);
 	spin_unlock_irq(cdev->ccwlock);
 	/* Unregister group device. */
-	mutex_lock(&gdev->reg_mutex);
-	if (device_is_registered(&gdev->dev)) {
-		__ccwgroup_remove_symlinks(gdev);
-		device_unregister(&gdev->dev);
-		__ccwgroup_remove_cdev_refs(gdev);
-	}
-	mutex_unlock(&gdev->reg_mutex);
+	ccwgroup_ungroup(gdev);
 	/* Release ccwgroup device reference for local processing. */
 	put_device(&gdev->dev);
 }
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 77f9c92df4b..2905d8b0ec9 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -602,6 +602,7 @@ void __init init_cio_interrupts(void)
 
 #ifdef CONFIG_CCW_CONSOLE
 static struct subchannel *console_sch;
+static struct lock_class_key console_sch_key;
 
 /*
  * Use cio_tsch to update the subchannel status and call the interrupt handler
@@ -686,6 +687,7 @@ struct subchannel *cio_probe_console(void)
 	if (IS_ERR(sch))
 		return sch;
 
+	lockdep_set_class(sch->lock, &console_sch_key);
 	isc_register(CONSOLE_ISC);
 	sch->config.isc = CONSOLE_ISC;
 	sch->config.intparm = (u32)(addr_t)sch;
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index d8d9b5b5cc5..dfef5e63cb7 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -678,18 +678,11 @@ static const struct attribute_group *ccwdev_attr_groups[] = {
 	NULL,
 };
 
-/* this is a simple abstraction for device_register that sets the
- * correct bus type and adds the bus specific files */
-static int ccw_device_register(struct ccw_device *cdev)
+static int ccw_device_add(struct ccw_device *cdev)
 {
 	struct device *dev = &cdev->dev;
-	int ret;
 
 	dev->bus = &ccw_bus_type;
-	ret = dev_set_name(&cdev->dev, "0.%x.%04x", cdev->private->dev_id.ssid,
-			   cdev->private->dev_id.devno);
-	if (ret)
-		return ret;
 	return device_add(dev);
 }
 
@@ -764,22 +757,46 @@ static void ccw_device_todo(struct work_struct *work);
 static int io_subchannel_initialize_dev(struct subchannel *sch,
 					struct ccw_device *cdev)
 {
-	cdev->private->cdev = cdev;
-	cdev->private->int_class = IRQIO_CIO;
-	atomic_set(&cdev->private->onoff, 0);
+	struct ccw_device_private *priv = cdev->private;
+	int ret;
+
+	priv->cdev = cdev;
+	priv->int_class = IRQIO_CIO;
+	priv->state = DEV_STATE_NOT_OPER;
+	priv->dev_id.devno = sch->schib.pmcw.dev;
+	priv->dev_id.ssid = sch->schid.ssid;
+	priv->schid = sch->schid;
+
+	INIT_WORK(&priv->todo_work, ccw_device_todo);
+	INIT_LIST_HEAD(&priv->cmb_list);
+	init_waitqueue_head(&priv->wait_q);
+	init_timer(&priv->timer);
+
+	atomic_set(&priv->onoff, 0);
+	cdev->ccwlock = sch->lock;
 	cdev->dev.parent = &sch->dev;
 	cdev->dev.release = ccw_device_release;
-	INIT_WORK(&cdev->private->todo_work, ccw_device_todo);
 	cdev->dev.groups = ccwdev_attr_groups;
 	/* Do first half of device_register. */
 	device_initialize(&cdev->dev);
+	ret = dev_set_name(&cdev->dev, "0.%x.%04x", cdev->private->dev_id.ssid,
+			   cdev->private->dev_id.devno);
+	if (ret)
+		goto out_put;
 	if (!get_device(&sch->dev)) {
-		/* Release reference from device_initialize(). */
-		put_device(&cdev->dev);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_put;
 	}
-	cdev->private->flags.initialized = 1;
+	priv->flags.initialized = 1;
+	spin_lock_irq(sch->lock);
+	sch_set_cdev(sch, cdev);
+	spin_unlock_irq(sch->lock);
 	return 0;
+
+out_put:
+	/* Release reference from device_initialize(). */
+	put_device(&cdev->dev);
+	return ret;
 }
 
 static struct ccw_device * io_subchannel_create_ccwdev(struct subchannel *sch)
@@ -858,7 +875,7 @@ static void io_subchannel_register(struct ccw_device *cdev)
 	dev_set_uevent_suppress(&sch->dev, 0);
 	kobject_uevent(&sch->dev.kobj, KOBJ_ADD);
 	/* make it known to the system */
-	ret = ccw_device_register(cdev);
+	ret = ccw_device_add(cdev);
 	if (ret) {
 		CIO_MSG_EVENT(0, "Could not register ccw dev 0.%x.%04x: %d\n",
 			      cdev->private->dev_id.ssid,
@@ -923,26 +940,11 @@ io_subchannel_recog_done(struct ccw_device *cdev)
 
 static void io_subchannel_recog(struct ccw_device *cdev, struct subchannel *sch)
 {
-	struct ccw_device_private *priv;
-
-	cdev->ccwlock = sch->lock;
-
-	/* Init private data. */
-	priv = cdev->private;
-	priv->dev_id.devno = sch->schib.pmcw.dev;
-	priv->dev_id.ssid = sch->schid.ssid;
-	priv->schid = sch->schid;
-	priv->state = DEV_STATE_NOT_OPER;
-	INIT_LIST_HEAD(&priv->cmb_list);
-	init_waitqueue_head(&priv->wait_q);
-	init_timer(&priv->timer);
-
 	/* Increase counter of devices currently in recognition. */
 	atomic_inc(&ccw_device_init_count);
 
 	/* Start async. device sensing. */
 	spin_lock_irq(sch->lock);
-	sch_set_cdev(sch, cdev);
 	ccw_device_recognition(cdev);
 	spin_unlock_irq(sch->lock);
 }
@@ -1083,7 +1085,7 @@ static int io_subchannel_probe(struct subchannel *sch)
 		dev_set_uevent_suppress(&sch->dev, 0);
 		kobject_uevent(&sch->dev.kobj, KOBJ_ADD);
 		cdev = sch_get_cdev(sch);
-		rc = ccw_device_register(cdev);
+		rc = ccw_device_add(cdev);
 		if (rc) {
 			/* Release online reference. */
 			put_device(&cdev->dev);
@@ -1597,7 +1599,6 @@ int __init ccw_device_enable_console(struct ccw_device *cdev)
 	if (rc)
 		return rc;
 	sch->driver = &io_subchannel_driver;
-	sch_set_cdev(sch, cdev);
 	io_subchannel_recog(cdev, sch);
 	/* Now wait for the async. recognition to come to an end. */
 	spin_lock_irq(cdev->ccwlock);
@@ -1639,6 +1640,7 @@ struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv)
 		put_device(&sch->dev);
 		return ERR_PTR(-ENOMEM);
 	}
+	set_io_private(sch, io_priv);
 	cdev = io_subchannel_create_ccwdev(sch);
 	if (IS_ERR(cdev)) {
 		put_device(&sch->dev);
@@ -1646,7 +1648,6 @@ struct ccw_device * __init ccw_device_create_console(struct ccw_driver *drv)
 		return cdev;
 	}
 	cdev->drv = drv;
-	set_io_private(sch, io_priv);
 	ccw_device_set_int_class(cdev);
 	return cdev;
 }
diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c
index 4221b02085a..f1f3baa8e6e 100644
--- a/drivers/s390/cio/qdio_debug.c
+++ b/drivers/s390/cio/qdio_debug.c
@@ -7,6 +7,7 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/export.h>
+#include <linux/slab.h>
 #include <asm/debug.h>
 #include "qdio_debug.h"
 #include "qdio.h"
@@ -16,11 +17,51 @@ debug_info_t *qdio_dbf_error;
 
 static struct dentry *debugfs_root;
 #define QDIO_DEBUGFS_NAME_LEN	10
+#define QDIO_DBF_NAME_LEN	20
 
-void qdio_allocate_dbf(struct qdio_initialize *init_data,
+struct qdio_dbf_entry {
+	char dbf_name[QDIO_DBF_NAME_LEN];
+	debug_info_t *dbf_info;
+	struct list_head dbf_list;
+};
+
+static LIST_HEAD(qdio_dbf_list);
+static DEFINE_MUTEX(qdio_dbf_list_mutex);
+
+static debug_info_t *qdio_get_dbf_entry(char *name)
+{
+	struct qdio_dbf_entry *entry;
+	debug_info_t *rc = NULL;
+
+	mutex_lock(&qdio_dbf_list_mutex);
+	list_for_each_entry(entry, &qdio_dbf_list, dbf_list) {
+		if (strcmp(entry->dbf_name, name) == 0) {
+			rc = entry->dbf_info;
+			break;
+		}
+	}
+	mutex_unlock(&qdio_dbf_list_mutex);
+	return rc;
+}
+
+static void qdio_clear_dbf_list(void)
+{
+	struct qdio_dbf_entry *entry, *tmp;
+
+	mutex_lock(&qdio_dbf_list_mutex);
+	list_for_each_entry_safe(entry, tmp, &qdio_dbf_list, dbf_list) {
+		list_del(&entry->dbf_list);
+		debug_unregister(entry->dbf_info);
+		kfree(entry);
+	}
+	mutex_unlock(&qdio_dbf_list_mutex);
+}
+
+int qdio_allocate_dbf(struct qdio_initialize *init_data,
 		       struct qdio_irq *irq_ptr)
 {
-	char text[20];
+	char text[QDIO_DBF_NAME_LEN];
+	struct qdio_dbf_entry *new_entry;
 
 	DBF_EVENT("qfmt:%1d", init_data->q_format);
 	DBF_HEX(init_data->adapter_name, 8);
@@ -38,11 +79,34 @@ void qdio_allocate_dbf(struct qdio_initialize *init_data,
 	DBF_EVENT("irq:%8lx", (unsigned long)irq_ptr);
 
 	/* allocate trace view for the interface */
-	snprintf(text, 20, "qdio_%s", dev_name(&init_data->cdev->dev));
-	irq_ptr->debug_area = debug_register(text, 2, 1, 16);
-	debug_register_view(irq_ptr->debug_area, &debug_hex_ascii_view);
-	debug_set_level(irq_ptr->debug_area, DBF_WARN);
-	DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf created");
+	snprintf(text, QDIO_DBF_NAME_LEN, "qdio_%s",
+					dev_name(&init_data->cdev->dev));
+	irq_ptr->debug_area = qdio_get_dbf_entry(text);
+	if (irq_ptr->debug_area)
+		DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf reused");
+	else {
+		irq_ptr->debug_area = debug_register(text, 2, 1, 16);
+		if (!irq_ptr->debug_area)
+			return -ENOMEM;
+		if (debug_register_view(irq_ptr->debug_area,
+						&debug_hex_ascii_view)) {
+			debug_unregister(irq_ptr->debug_area);
+			return -ENOMEM;
+		}
+		debug_set_level(irq_ptr->debug_area, DBF_WARN);
+		DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf created");
+		new_entry = kzalloc(sizeof(struct qdio_dbf_entry), GFP_KERNEL);
+		if (!new_entry) {
+			debug_unregister(irq_ptr->debug_area);
+			return -ENOMEM;
+		}
+		strlcpy(new_entry->dbf_name, text, QDIO_DBF_NAME_LEN);
+		new_entry->dbf_info = irq_ptr->debug_area;
+		mutex_lock(&qdio_dbf_list_mutex);
+		list_add(&new_entry->dbf_list, &qdio_dbf_list);
+		mutex_unlock(&qdio_dbf_list_mutex);
+	}
+	return 0;
 }
 
 static int qstat_show(struct seq_file *m, void *v)
@@ -300,6 +364,7 @@ int __init qdio_debug_init(void)
 
 void qdio_debug_exit(void)
 {
+	qdio_clear_dbf_list();
 	debugfs_remove(debugfs_root);
 	if (qdio_dbf_setup)
 		debug_unregister(qdio_dbf_setup);
diff --git a/drivers/s390/cio/qdio_debug.h b/drivers/s390/cio/qdio_debug.h
index dfac9bfefea..f33ce857761 100644
--- a/drivers/s390/cio/qdio_debug.h
+++ b/drivers/s390/cio/qdio_debug.h
@@ -75,7 +75,7 @@ static inline void DBF_DEV_HEX(struct qdio_irq *dev, void *addr,
 	}
 }
 
-void qdio_allocate_dbf(struct qdio_initialize *init_data,
+int qdio_allocate_dbf(struct qdio_initialize *init_data,
 		       struct qdio_irq *irq_ptr);
 void qdio_setup_debug_entries(struct qdio_irq *irq_ptr,
 			      struct ccw_device *cdev);
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 77466c4faab..848e3b64ea6 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -409,17 +409,16 @@ static inline void qdio_stop_polling(struct qdio_q *q)
 		set_buf_state(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT);
 }
 
-static inline void account_sbals(struct qdio_q *q, int count)
+static inline void account_sbals(struct qdio_q *q, unsigned int count)
 {
-	int pos = 0;
+	int pos;
 
 	q->q_stats.nr_sbal_total += count;
 	if (count == QDIO_MAX_BUFFERS_MASK) {
 		q->q_stats.nr_sbals[7]++;
 		return;
 	}
-	while (count >>= 1)
-		pos++;
+	pos = ilog2(count);
 	q->q_stats.nr_sbals[pos]++;
 }
 
@@ -1234,12 +1233,10 @@ int qdio_free(struct ccw_device *cdev)
 		return -ENODEV;
 
 	DBF_EVENT("qfree:%4x", cdev->private->schid.sch_no);
+	DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf abandoned");
 	mutex_lock(&irq_ptr->setup_mutex);
 
-	if (irq_ptr->debug_area != NULL) {
-		debug_unregister(irq_ptr->debug_area);
-		irq_ptr->debug_area = NULL;
-	}
+	irq_ptr->debug_area = NULL;
 	cdev->private->qdio_data = NULL;
 	mutex_unlock(&irq_ptr->setup_mutex);
 
@@ -1276,7 +1273,8 @@ int qdio_allocate(struct qdio_initialize *init_data)
 		goto out_err;
 
 	mutex_init(&irq_ptr->setup_mutex);
-	qdio_allocate_dbf(init_data, irq_ptr);
+	if (qdio_allocate_dbf(init_data, irq_ptr))
+		goto out_rel;
 
 	/*
 	 * Allocate a page for the chsc calls in qdio_establish.
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 8eec1653c9c..4038437ff03 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -77,12 +77,12 @@ MODULE_ALIAS("z90crypt");
  * Module parameter
  */
 int ap_domain_index = -1;	/* Adjunct Processor Domain Index */
-module_param_named(domain, ap_domain_index, int, 0000);
+module_param_named(domain, ap_domain_index, int, S_IRUSR|S_IRGRP);
 MODULE_PARM_DESC(domain, "domain index for ap devices");
 EXPORT_SYMBOL(ap_domain_index);
 
 static int ap_thread_flag = 0;
-module_param_named(poll_thread, ap_thread_flag, int, 0000);
+module_param_named(poll_thread, ap_thread_flag, int, S_IRUSR|S_IRGRP);
 MODULE_PARM_DESC(poll_thread, "Turn on/off poll thread, default is 0 (off).");
 
 static struct device *ap_root_device = NULL;
@@ -901,10 +901,15 @@ static int ap_device_probe(struct device *dev)
 	int rc;
 
 	ap_dev->drv = ap_drv;
+
+	spin_lock_bh(&ap_device_list_lock);
+	list_add(&ap_dev->list, &ap_device_list);
+	spin_unlock_bh(&ap_device_list_lock);
+
 	rc = ap_drv->probe ? ap_drv->probe(ap_dev) : -ENODEV;
-	if (!rc) {
+	if (rc) {
 		spin_lock_bh(&ap_device_list_lock);
-		list_add(&ap_dev->list, &ap_device_list);
+		list_del_init(&ap_dev->list);
 		spin_unlock_bh(&ap_device_list_lock);
 	}
 	return rc;
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 5222ebe1570..0e18c5dcd91 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -356,7 +356,7 @@ struct zcrypt_ops *zcrypt_msgtype_request(unsigned char *name, int variant)
 
 	zops = __ops_lookup(name, variant);
 	if (!zops) {
-		request_module(name);
+		request_module("%s", name);
 		zops = __ops_lookup(name, variant);
 	}
 	if ((!zops) || (!try_module_get(zops->owner)))
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
index 1e1fc671f89..d2c0b442bce 100644
--- a/drivers/s390/kvm/virtio_ccw.c
+++ b/drivers/s390/kvm/virtio_ccw.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/kvm_para.h>
+#include <linux/notifier.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
 #include <asm/cio.h>
@@ -62,6 +63,7 @@ struct virtio_ccw_device {
 	struct vq_config_block *config_block;
 	bool is_thinint;
 	bool going_away;
+	bool device_lost;
 	void *airq_info;
 };
 
@@ -1010,11 +1012,14 @@ static void virtio_ccw_remove(struct ccw_device *cdev)
 	unsigned long flags;
 	struct virtio_ccw_device *vcdev = virtio_grab_drvdata(cdev);
 
-	if (vcdev && cdev->online)
+	if (vcdev && cdev->online) {
+		if (vcdev->device_lost)
+			virtio_break_device(&vcdev->vdev);
 		unregister_virtio_device(&vcdev->vdev);
-	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
-	dev_set_drvdata(&cdev->dev, NULL);
-	spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
+		spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
+		dev_set_drvdata(&cdev->dev, NULL);
+		spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
+	}
 	cdev->handler = NULL;
 }
 
@@ -1023,12 +1028,14 @@ static int virtio_ccw_offline(struct ccw_device *cdev)
 	unsigned long flags;
 	struct virtio_ccw_device *vcdev = virtio_grab_drvdata(cdev);
 
-	if (vcdev) {
-		unregister_virtio_device(&vcdev->vdev);
-		spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
-		dev_set_drvdata(&cdev->dev, NULL);
-		spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
-	}
+	if (!vcdev)
+		return 0;
+	if (vcdev->device_lost)
+		virtio_break_device(&vcdev->vdev);
+	unregister_virtio_device(&vcdev->vdev);
+	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
+	dev_set_drvdata(&cdev->dev, NULL);
+	spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
 	return 0;
 }
 
@@ -1096,8 +1103,26 @@ out_free:
 
 static int virtio_ccw_cio_notify(struct ccw_device *cdev, int event)
 {
-	/* TODO: Check whether we need special handling here. */
-	return 0;
+	int rc;
+	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
+
+	/*
+	 * Make sure vcdev is set
+	 * i.e. set_offline/remove callback not already running
+	 */
+	if (!vcdev)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case CIO_GONE:
+		vcdev->device_lost = true;
+		rc = NOTIFY_DONE;
+		break;
+	default:
+		rc = NOTIFY_DONE;
+		break;
+	}
+	return rc;
 }
 
 static struct ccw_device_id virtio_ids[] = {
diff --git a/drivers/s390/net/claw.c b/drivers/s390/net/claw.c
index fd7b3bd8078..d837c3c5330 100644
--- a/drivers/s390/net/claw.c
+++ b/drivers/s390/net/claw.c
@@ -3348,7 +3348,7 @@ static int __init claw_init(void)
 	}
 	CLAW_DBF_TEXT(2, setup, "init_mod");
 	claw_root_dev = root_device_register("claw");
-	ret = PTR_RET(claw_root_dev);
+	ret = PTR_ERR_OR_ZERO(claw_root_dev);
 	if (ret)
 		goto register_err;
 	ret = ccw_driver_register(&claw_ccw_driver);
diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c
index 70b3a023100..03b6ad03557 100644
--- a/drivers/s390/net/ctcm_main.c
+++ b/drivers/s390/net/ctcm_main.c
@@ -1837,7 +1837,7 @@ static int __init ctcm_init(void)
 	if (ret)
 		goto out_err;
 	ctcm_root_dev = root_device_register("ctcm");
-	ret = PTR_RET(ctcm_root_dev);
+	ret = PTR_ERR_OR_ZERO(ctcm_root_dev);
 	if (ret)
 		goto register_err;
 	ret = ccw_driver_register(&ctcm_ccw_driver);
diff --git a/drivers/s390/net/ctcm_sysfs.c b/drivers/s390/net/ctcm_sysfs.c
index 985b5dcbdac..6bcfbbb20f0 100644
--- a/drivers/s390/net/ctcm_sysfs.c
+++ b/drivers/s390/net/ctcm_sysfs.c
@@ -34,8 +34,9 @@ static ssize_t ctcm_buffer_write(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct net_device *ndev;
-	int bs1;
+	unsigned int bs1;
 	struct ctcm_priv *priv = dev_get_drvdata(dev);
+	int rc;
 
 	ndev = priv->channel[CTCM_READ]->netdev;
 	if (!(priv && priv->channel[CTCM_READ] && ndev)) {
@@ -43,7 +44,9 @@ static ssize_t ctcm_buffer_write(struct device *dev,
 		return -ENODEV;
 	}
 
-	sscanf(buf, "%u", &bs1);
+	rc = sscanf(buf, "%u", &bs1);
+	if (rc != 1)
+		goto einval;
 	if (bs1 > CTCM_BUFSIZE_LIMIT)
 					goto einval;
 	if (bs1 < (576 + LL_HEADER_LENGTH + 2))
@@ -143,13 +146,14 @@ static ssize_t ctcm_proto_show(struct device *dev,
 static ssize_t ctcm_proto_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
-	int value;
+	int value, rc;
 	struct ctcm_priv *priv = dev_get_drvdata(dev);
 
 	if (!priv)
 		return -ENODEV;
-	sscanf(buf, "%u", &value);
-	if (!((value == CTCM_PROTO_S390)  ||
+	rc = sscanf(buf, "%d", &value);
+	if ((rc != 1) ||
+	    !((value == CTCM_PROTO_S390)  ||
 	      (value == CTCM_PROTO_LINUX) ||
 	      (value == CTCM_PROTO_MPC) ||
 	      (value == CTCM_PROTO_OS390)))
diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c
index c461f2aac61..0a7d87c372b 100644
--- a/drivers/s390/net/lcs.c
+++ b/drivers/s390/net/lcs.c
@@ -1943,14 +1943,16 @@ static ssize_t
 lcs_portno_store (struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
 {
         struct lcs_card *card;
-        int value;
+	int value, rc;
 
 	card = dev_get_drvdata(dev);
 
         if (!card)
                 return 0;
 
-        sscanf(buf, "%u", &value);
+	rc = sscanf(buf, "%d", &value);
+	if (rc != 1)
+		return -EINVAL;
         /* TODO: sanity checks */
         card->portno = value;
 
@@ -1997,14 +1999,17 @@ static ssize_t
 lcs_timeout_store (struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
 {
         struct lcs_card *card;
-        int value;
+	unsigned int value;
+	int rc;
 
 	card = dev_get_drvdata(dev);
 
         if (!card)
                 return 0;
 
-        sscanf(buf, "%u", &value);
+	rc = sscanf(buf, "%u", &value);
+	if (rc != 1)
+		return -EINVAL;
         /* TODO: sanity checks */
         card->lancmd_timeout = value;
 
@@ -2442,7 +2447,7 @@ __init lcs_init_module(void)
 	if (rc)
 		goto out_err;
 	lcs_root_dev = root_device_register("lcs");
-	rc = PTR_RET(lcs_root_dev);
+	rc = PTR_ERR_OR_ZERO(lcs_root_dev);
 	if (rc)
 		goto register_err;
 	rc = ccw_driver_register(&lcs_ccw_driver);
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 5333b2c018e..a2088af51cc 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -268,10 +268,8 @@ static inline int qeth_is_ipa_enabled(struct qeth_ipa_info *ipa,
 #define QETH_NO_PRIO_QUEUEING 0
 #define QETH_PRIO_Q_ING_PREC  1
 #define QETH_PRIO_Q_ING_TOS   2
-#define IP_TOS_LOWDELAY 0x10
-#define IP_TOS_HIGHTHROUGHPUT 0x08
-#define IP_TOS_HIGHRELIABILITY 0x04
-#define IP_TOS_NOTIMPORTANT 0x02
+#define QETH_PRIO_Q_ING_SKB   3
+#define QETH_PRIO_Q_ING_VLAN  4
 
 /* Packing */
 #define QETH_LOW_WATERMARK_PACK  2
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index e89f38c3117..f54bec54d67 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -20,6 +20,7 @@
 #include <linux/kthread.h>
 #include <linux/slab.h>
 #include <net/iucv/af_iucv.h>
+#include <net/dsfield.h>
 
 #include <asm/ebcdic.h>
 #include <asm/chpid.h>
@@ -1013,7 +1014,7 @@ static long __qeth_check_irb_error(struct ccw_device *cdev,
 
 	card = CARD_FROM_CDEV(cdev);
 
-	if (!IS_ERR(irb))
+	if (!card || !IS_ERR(irb))
 		return 0;
 
 	switch (PTR_ERR(irb)) {
@@ -1029,7 +1030,7 @@ static long __qeth_check_irb_error(struct ccw_device *cdev,
 		QETH_CARD_TEXT(card, 2, "ckirberr");
 		QETH_CARD_TEXT_(card, 2, "  rc%d", -ETIMEDOUT);
 		if (intparm == QETH_RCD_PARM) {
-			if (card && (card->data.ccwdev == cdev)) {
+			if (card->data.ccwdev == cdev) {
 				card->data.state = CH_STATE_DOWN;
 				wake_up(&card->wait_q);
 			}
@@ -3662,42 +3663,56 @@ void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 }
 EXPORT_SYMBOL_GPL(qeth_qdio_output_handler);
 
+/**
+ * Note: Function assumes that we have 4 outbound queues.
+ */
 int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
 			int ipv, int cast_type)
 {
-	if (!ipv && (card->info.type == QETH_CARD_TYPE_OSD ||
-		     card->info.type == QETH_CARD_TYPE_OSX))
-		return card->qdio.default_out_queue;
-	switch (card->qdio.no_out_queues) {
-	case 4:
-		if (cast_type && card->info.is_multicast_different)
-			return card->info.is_multicast_different &
-				(card->qdio.no_out_queues - 1);
-		if (card->qdio.do_prio_queueing && (ipv == 4)) {
-			const u8 tos = ip_hdr(skb)->tos;
-
-			if (card->qdio.do_prio_queueing ==
-				QETH_PRIO_Q_ING_TOS) {
-				if (tos & IP_TOS_NOTIMPORTANT)
-					return 3;
-				if (tos & IP_TOS_HIGHRELIABILITY)
-					return 2;
-				if (tos & IP_TOS_HIGHTHROUGHPUT)
-					return 1;
-				if (tos & IP_TOS_LOWDELAY)
-					return 0;
-			}
-			if (card->qdio.do_prio_queueing ==
-				QETH_PRIO_Q_ING_PREC)
-				return 3 - (tos >> 6);
-		} else if (card->qdio.do_prio_queueing && (ipv == 6)) {
-			/* TODO: IPv6!!! */
+	__be16 *tci;
+	u8 tos;
+
+	if (cast_type && card->info.is_multicast_different)
+		return card->info.is_multicast_different &
+			(card->qdio.no_out_queues - 1);
+
+	switch (card->qdio.do_prio_queueing) {
+	case QETH_PRIO_Q_ING_TOS:
+	case QETH_PRIO_Q_ING_PREC:
+		switch (ipv) {
+		case 4:
+			tos = ipv4_get_dsfield(ip_hdr(skb));
+			break;
+		case 6:
+			tos = ipv6_get_dsfield(ipv6_hdr(skb));
+			break;
+		default:
+			return card->qdio.default_out_queue;
 		}
-		return card->qdio.default_out_queue;
-	case 1: /* fallthrough for single-out-queue 1920-device */
+		if (card->qdio.do_prio_queueing == QETH_PRIO_Q_ING_PREC)
+			return ~tos >> 6 & 3;
+		if (tos & IPTOS_MINCOST)
+			return 3;
+		if (tos & IPTOS_RELIABILITY)
+			return 2;
+		if (tos & IPTOS_THROUGHPUT)
+			return 1;
+		if (tos & IPTOS_LOWDELAY)
+			return 0;
+		break;
+	case QETH_PRIO_Q_ING_SKB:
+		if (skb->priority > 5)
+			return 0;
+		return ~skb->priority >> 1 & 3;
+	case QETH_PRIO_Q_ING_VLAN:
+		tci = &((struct ethhdr *)skb->data)->h_proto;
+		if (*tci == ETH_P_8021Q)
+			return ~*(tci + 1) >> (VLAN_PRIO_SHIFT + 1) & 3;
+		break;
 	default:
-		return card->qdio.default_out_queue;
+		break;
 	}
+	return card->qdio.default_out_queue;
 }
 EXPORT_SYMBOL_GPL(qeth_get_priority_queue);
 
@@ -5703,6 +5718,7 @@ int qeth_core_ethtool_get_settings(struct net_device *netdev,
 	struct qeth_card *card = netdev->ml_priv;
 	enum qeth_link_types link_type;
 	struct carrier_info carrier_info;
+	u32 speed;
 
 	if ((card->info.type == QETH_CARD_TYPE_IQD) || (card->info.guestlan))
 		link_type = QETH_LINK_TYPE_10GBIT_ETH;
@@ -5717,28 +5733,29 @@ int qeth_core_ethtool_get_settings(struct net_device *netdev,
 	case QETH_LINK_TYPE_FAST_ETH:
 	case QETH_LINK_TYPE_LANE_ETH100:
 		qeth_set_ecmd_adv_sup(ecmd, SPEED_100, PORT_TP);
-		ecmd->speed = SPEED_100;
+		speed = SPEED_100;
 		ecmd->port = PORT_TP;
 		break;
 
 	case QETH_LINK_TYPE_GBIT_ETH:
 	case QETH_LINK_TYPE_LANE_ETH1000:
 		qeth_set_ecmd_adv_sup(ecmd, SPEED_1000, PORT_FIBRE);
-		ecmd->speed = SPEED_1000;
+		speed = SPEED_1000;
 		ecmd->port = PORT_FIBRE;
 		break;
 
 	case QETH_LINK_TYPE_10GBIT_ETH:
 		qeth_set_ecmd_adv_sup(ecmd, SPEED_10000, PORT_FIBRE);
-		ecmd->speed = SPEED_10000;
+		speed = SPEED_10000;
 		ecmd->port = PORT_FIBRE;
 		break;
 
 	default:
 		qeth_set_ecmd_adv_sup(ecmd, SPEED_10, PORT_TP);
-		ecmd->speed = SPEED_10;
+		speed = SPEED_10;
 		ecmd->port = PORT_TP;
 	}
+	ethtool_cmd_speed_set(ecmd, speed);
 
 	/* Check if we can obtain more accurate information.	 */
 	/* If QUERY_CARD_INFO command is not supported or fails, */
@@ -5783,18 +5800,19 @@ int qeth_core_ethtool_get_settings(struct net_device *netdev,
 
 	switch (carrier_info.port_speed) {
 	case CARD_INFO_PORTS_10M:
-		ecmd->speed = SPEED_10;
+		speed = SPEED_10;
 		break;
 	case CARD_INFO_PORTS_100M:
-		ecmd->speed = SPEED_100;
+		speed = SPEED_100;
 		break;
 	case CARD_INFO_PORTS_1G:
-		ecmd->speed = SPEED_1000;
+		speed = SPEED_1000;
 		break;
 	case CARD_INFO_PORTS_10G:
-		ecmd->speed = SPEED_10000;
+		speed = SPEED_10000;
 		break;
 	}
+	ethtool_cmd_speed_set(ecmd, speed);
 
 	return 0;
 }
@@ -5816,7 +5834,7 @@ static int __init qeth_core_init(void)
 	if (rc)
 		goto out_err;
 	qeth_core_root_dev = root_device_register("qeth");
-	rc = PTR_RET(qeth_core_root_dev);
+	rc = PTR_ERR_OR_ZERO(qeth_core_root_dev);
 	if (rc)
 		goto register_err;
 	qeth_core_header_cache = kmem_cache_create("qeth_hdr",
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 425c0ecf1f3..8a25a2be989 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -217,6 +217,10 @@ static ssize_t qeth_dev_prioqing_show(struct device *dev,
 		return sprintf(buf, "%s\n", "by precedence");
 	case QETH_PRIO_Q_ING_TOS:
 		return sprintf(buf, "%s\n", "by type of service");
+	case QETH_PRIO_Q_ING_SKB:
+		return sprintf(buf, "%s\n", "by skb-priority");
+	case QETH_PRIO_Q_ING_VLAN:
+		return sprintf(buf, "%s\n", "by VLAN headers");
 	default:
 		return sprintf(buf, "always queue %i\n",
 			       card->qdio.default_out_queue);
@@ -250,11 +254,23 @@ static ssize_t qeth_dev_prioqing_store(struct device *dev,
 	}
 
 	tmp = strsep((char **) &buf, "\n");
-	if (!strcmp(tmp, "prio_queueing_prec"))
+	if (!strcmp(tmp, "prio_queueing_prec")) {
 		card->qdio.do_prio_queueing = QETH_PRIO_Q_ING_PREC;
-	else if (!strcmp(tmp, "prio_queueing_tos"))
+		card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
+	} else if (!strcmp(tmp, "prio_queueing_skb")) {
+		card->qdio.do_prio_queueing = QETH_PRIO_Q_ING_SKB;
+		card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
+	} else if (!strcmp(tmp, "prio_queueing_tos")) {
 		card->qdio.do_prio_queueing = QETH_PRIO_Q_ING_TOS;
-	else if (!strcmp(tmp, "no_prio_queueing:0")) {
+		card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
+	} else if (!strcmp(tmp, "prio_queueing_vlan")) {
+		if (!card->options.layer2) {
+			rc = -ENOTSUPP;
+			goto out;
+		}
+		card->qdio.do_prio_queueing = QETH_PRIO_Q_ING_VLAN;
+		card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
+	} else if (!strcmp(tmp, "no_prio_queueing:0")) {
 		card->qdio.do_prio_queueing = QETH_NO_PRIO_QUEUEING;
 		card->qdio.default_out_queue = 0;
 	} else if (!strcmp(tmp, "no_prio_queueing:1")) {
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8dea3f12ccc..5ef5b4f4575 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -725,15 +725,20 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	int elements = 0;
 	struct qeth_card *card = dev->ml_priv;
 	struct sk_buff *new_skb = skb;
-	int ipv = qeth_get_ip_version(skb);
 	int cast_type = qeth_l2_get_cast_type(card, skb);
-	struct qeth_qdio_out_q *queue = card->qdio.out_qs
-		[qeth_get_priority_queue(card, skb, ipv, cast_type)];
+	struct qeth_qdio_out_q *queue;
 	int tx_bytes = skb->len;
 	int data_offset = -1;
 	int elements_needed = 0;
 	int hd_len = 0;
 
+	if (card->qdio.do_prio_queueing || (cast_type &&
+					card->info.is_multicast_different))
+		queue = card->qdio.out_qs[qeth_get_priority_queue(card, skb,
+					qeth_get_ip_version(skb), cast_type)];
+	else
+		queue = card->qdio.out_qs[card->qdio.default_out_queue];
+
 	if ((card->state != CARD_STATE_UP) || !card->lan_online) {
 		card->stats.tx_carrier_errors++;
 		goto tx_drop;
@@ -964,10 +969,9 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	card->dev->watchdog_timeo = QETH_TX_TIMEOUT;
 	card->dev->mtu = card->info.initial_mtu;
 	card->dev->netdev_ops = &qeth_l2_netdev_ops;
-	if (card->info.type != QETH_CARD_TYPE_OSN)
-		SET_ETHTOOL_OPS(card->dev, &qeth_l2_ethtool_ops);
-	else
-		SET_ETHTOOL_OPS(card->dev, &qeth_l2_osn_ops);
+	card->dev->ethtool_ops =
+		(card->info.type != QETH_CARD_TYPE_OSN) ?
+		&qeth_l2_ethtool_ops : &qeth_l2_osn_ops;
 	card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	card->info.broadcast_capable = 1;
 	qeth_l2_request_initial_mac(card);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 3524d34ff69..14e0b5810e8 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -63,7 +63,7 @@ void qeth_l3_ipaddr4_to_string(const __u8 *addr, char *buf)
 int qeth_l3_string_to_ipaddr4(const char *buf, __u8 *addr)
 {
 	int count = 0, rc = 0;
-	int in[4];
+	unsigned int in[4];
 	char c;
 
 	rc = sscanf(buf, "%u.%u.%u.%u%c",
@@ -1659,7 +1659,7 @@ static void qeth_l3_add_vlan_mc(struct qeth_card *card)
 	for_each_set_bit(vid, card->active_vlans, VLAN_N_VID) {
 		struct net_device *netdev;
 
-		netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q),
+		netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q),
 					      vid);
 		if (netdev == NULL ||
 		    !(netdev->flags & IFF_UP))
@@ -1721,7 +1721,7 @@ static void qeth_l3_add_vlan_mc6(struct qeth_card *card)
 	for_each_set_bit(vid, card->active_vlans, VLAN_N_VID) {
 		struct net_device *netdev;
 
-		netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q),
+		netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q),
 					      vid);
 		if (netdev == NULL ||
 		    !(netdev->flags & IFF_UP))
@@ -1766,7 +1766,7 @@ static void qeth_l3_free_vlan_addresses4(struct qeth_card *card,
 
 	QETH_CARD_TEXT(card, 4, "frvaddr4");
 
-	netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q), vid);
+	netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q), vid);
 	if (!netdev)
 		return;
 	in_dev = in_dev_get(netdev);
@@ -1796,7 +1796,7 @@ static void qeth_l3_free_vlan_addresses6(struct qeth_card *card,
 
 	QETH_CARD_TEXT(card, 4, "frvaddr6");
 
-	netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q), vid);
+	netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q), vid);
 	if (!netdev)
 		return;
 	in6_dev = in6_dev_get(netdev);
@@ -2089,7 +2089,7 @@ static int qeth_l3_verify_vlan_dev(struct net_device *dev,
 		struct net_device *netdev;
 
 		rcu_read_lock();
-		netdev = __vlan_find_dev_deep(card->dev, htons(ETH_P_8021Q),
+		netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q),
 					      vid);
 		rcu_read_unlock();
 		if (netdev == dev) {
@@ -2926,8 +2926,11 @@ static int qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct sk_buff *new_skb = NULL;
 	int ipv = qeth_get_ip_version(skb);
 	int cast_type = qeth_l3_get_cast_type(card, skb);
-	struct qeth_qdio_out_q *queue = card->qdio.out_qs
-		[qeth_get_priority_queue(card, skb, ipv, cast_type)];
+	struct qeth_qdio_out_q *queue =
+		card->qdio.out_qs[card->qdio.do_prio_queueing
+			|| (cast_type && card->info.is_multicast_different) ?
+			qeth_get_priority_queue(card, skb, ipv, cast_type) :
+			card->qdio.default_out_queue];
 	int tx_bytes = skb->len;
 	bool large_send;
 	int data_offset = -1;
@@ -3298,7 +3301,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 	card->dev->ml_priv = card;
 	card->dev->watchdog_timeo = QETH_TX_TIMEOUT;
 	card->dev->mtu = card->info.initial_mtu;
-	SET_ETHTOOL_OPS(card->dev, &qeth_l3_ethtool_ops);
+	card->dev->ethtool_ops = &qeth_l3_ethtool_ops;
 	card->dev->features |=	NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 02832d64d91..baca5897039 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1773,6 +1773,7 @@ config SCSI_BFA_FC
 config SCSI_VIRTIO
 	tristate "virtio-scsi support"
 	depends on VIRTIO
+	select BLK_DEV_INTEGRITY
 	help
           This is the virtual HBA driver for virtio.  If the kernel will
           be used in a virtual machine, say Y or M.
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index bcd22386822..93d13fc9a29 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -27,8 +27,6 @@
  */
 
 /*
- * $Log: NCR5380.c,v $
-
  * Revision 1.10 1998/9/2	Alan Cox
  *				(alan@lxorguk.ukuu.org.uk)
  * Fixed up the timer lockups reported so far. Things still suck. Looking 
@@ -89,13 +87,6 @@
 #include <scsi/scsi_dbg.h>
 #include <scsi/scsi_transport_spi.h>
 
-#ifndef NDEBUG
-#define NDEBUG 0
-#endif
-#ifndef NDEBUG_ABORT
-#define NDEBUG_ABORT 0
-#endif
-
 #if (NDEBUG & NDEBUG_LISTS)
 #define LIST(x,y) {printk("LINE:%d   Adding %p to %p\n", __LINE__, (void*)(x), (void*)(y)); if ((x)==(y)) udelay(5); }
 #define REMOVE(w,x,y,z) {printk("LINE:%d   Removing: %p->%p  %p->%p \n", __LINE__, (void*)(w), (void*)(x), (void*)(y), (void*)(z)); if ((x)==(y)) udelay(5); }
@@ -1005,7 +996,7 @@ static int NCR5380_queue_command_lck(Scsi_Cmnd * cmd, void (*done) (Scsi_Cmnd *)
 		LIST(cmd, tmp);
 		tmp->host_scribble = (unsigned char *) cmd;
 	}
-	dprintk(NDEBUG_QUEUES, ("scsi%d : command added to %s of queue\n", instance->host_no, (cmd->cmnd[0] == REQUEST_SENSE) ? "head" : "tail"));
+	dprintk(NDEBUG_QUEUES, "scsi%d : command added to %s of queue\n", instance->host_no, (cmd->cmnd[0] == REQUEST_SENSE) ? "head" : "tail");
 
 	/* Run the coroutine if it isn't already running. */
 	/* Kick off command processing */
@@ -1040,7 +1031,7 @@ static void NCR5380_main(struct work_struct *work)
 		/* Lock held here */
 		done = 1;
 		if (!hostdata->connected && !hostdata->selecting) {
-			dprintk(NDEBUG_MAIN, ("scsi%d : not connected\n", instance->host_no));
+			dprintk(NDEBUG_MAIN, "scsi%d : not connected\n", instance->host_no);
 			/*
 			 * Search through the issue_queue for a command destined
 			 * for a target that's not busy.
@@ -1048,7 +1039,7 @@ static void NCR5380_main(struct work_struct *work)
 			for (tmp = (Scsi_Cmnd *) hostdata->issue_queue, prev = NULL; tmp; prev = tmp, tmp = (Scsi_Cmnd *) tmp->host_scribble) 
 			{
 				if (prev != tmp)
-					dprintk(NDEBUG_LISTS, ("MAIN tmp=%p   target=%d   busy=%d lun=%d\n", tmp, tmp->target, hostdata->busy[tmp->target], tmp->lun));
+					dprintk(NDEBUG_LISTS, "MAIN tmp=%p   target=%d   busy=%d lun=%d\n", tmp, tmp->device->id, hostdata->busy[tmp->device->id], tmp->device->lun);
 				/*  When we find one, remove it from the issue queue. */
 				if (!(hostdata->busy[tmp->device->id] & (1 << tmp->device->lun))) {
 					if (prev) {
@@ -1066,7 +1057,7 @@ static void NCR5380_main(struct work_struct *work)
 					 * On failure, we must add the command back to the
 					 *   issue queue so we can keep trying. 
 					 */
-					dprintk(NDEBUG_MAIN|NDEBUG_QUEUES, ("scsi%d : main() : command for target %d lun %d removed from issue_queue\n", instance->host_no, tmp->target, tmp->lun));
+					dprintk(NDEBUG_MAIN|NDEBUG_QUEUES, "scsi%d : main() : command for target %d lun %d removed from issue_queue\n", instance->host_no, tmp->device->id, tmp->device->lun);
 	
 					/*
 					 * A successful selection is defined as one that 
@@ -1095,7 +1086,7 @@ static void NCR5380_main(struct work_struct *work)
 						tmp->host_scribble = (unsigned char *) hostdata->issue_queue;
 						hostdata->issue_queue = tmp;
 						done = 0;
-						dprintk(NDEBUG_MAIN|NDEBUG_QUEUES, ("scsi%d : main(): select() failed, returned to issue_queue\n", instance->host_no));
+						dprintk(NDEBUG_MAIN|NDEBUG_QUEUES, "scsi%d : main(): select() failed, returned to issue_queue\n", instance->host_no);
 					}
 					/* lock held here still */
 				}	/* if target/lun is not busy */
@@ -1125,9 +1116,9 @@ static void NCR5380_main(struct work_struct *work)
 #endif
 		    && (!hostdata->time_expires || time_before_eq(hostdata->time_expires, jiffies))
 		    ) {
-			dprintk(NDEBUG_MAIN, ("scsi%d : main() : performing information transfer\n", instance->host_no));
+			dprintk(NDEBUG_MAIN, "scsi%d : main() : performing information transfer\n", instance->host_no);
 			NCR5380_information_transfer(instance);
-			dprintk(NDEBUG_MAIN, ("scsi%d : main() : done set false\n", instance->host_no));
+			dprintk(NDEBUG_MAIN, "scsi%d : main() : done set false\n", instance->host_no);
 			done = 0;
 		} else
 			break;
@@ -1159,8 +1150,8 @@ static irqreturn_t NCR5380_intr(int dummy, void *dev_id)
 	unsigned char basr;
 	unsigned long flags;
 
-	dprintk(NDEBUG_INTR, ("scsi : NCR5380 irq %d triggered\n",
-		instance->irq));
+	dprintk(NDEBUG_INTR, "scsi : NCR5380 irq %d triggered\n",
+		instance->irq);
 
 	do {
 		done = 1;
@@ -1173,14 +1164,14 @@ static irqreturn_t NCR5380_intr(int dummy, void *dev_id)
 			NCR5380_dprint(NDEBUG_INTR, instance);
 			if ((NCR5380_read(STATUS_REG) & (SR_SEL | SR_IO)) == (SR_SEL | SR_IO)) {
 				done = 0;
-				dprintk(NDEBUG_INTR, ("scsi%d : SEL interrupt\n", instance->host_no));
+				dprintk(NDEBUG_INTR, "scsi%d : SEL interrupt\n", instance->host_no);
 				NCR5380_reselect(instance);
 				(void) NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 			} else if (basr & BASR_PARITY_ERROR) {
-				dprintk(NDEBUG_INTR, ("scsi%d : PARITY interrupt\n", instance->host_no));
+				dprintk(NDEBUG_INTR, "scsi%d : PARITY interrupt\n", instance->host_no);
 				(void) NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 			} else if ((NCR5380_read(STATUS_REG) & SR_RST) == SR_RST) {
-				dprintk(NDEBUG_INTR, ("scsi%d : RESET interrupt\n", instance->host_no));
+				dprintk(NDEBUG_INTR, "scsi%d : RESET interrupt\n", instance->host_no);
 				(void) NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 			} else {
 #if defined(REAL_DMA)
@@ -1210,7 +1201,7 @@ static irqreturn_t NCR5380_intr(int dummy, void *dev_id)
 					NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 				}
 #else
-				dprintk(NDEBUG_INTR, ("scsi : unknown interrupt, BASR 0x%X, MR 0x%X, SR 0x%x\n", basr, NCR5380_read(MODE_REG), NCR5380_read(STATUS_REG)));
+				dprintk(NDEBUG_INTR, "scsi : unknown interrupt, BASR 0x%X, MR 0x%X, SR 0x%x\n", basr, NCR5380_read(MODE_REG), NCR5380_read(STATUS_REG));
 				(void) NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 #endif
 			}
@@ -1304,7 +1295,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd * cmd, int tag)
 	hostdata->restart_select = 0;
 
 	NCR5380_dprint(NDEBUG_ARBITRATION, instance);
-	dprintk(NDEBUG_ARBITRATION, ("scsi%d : starting arbitration, id = %d\n", instance->host_no, instance->this_id));
+	dprintk(NDEBUG_ARBITRATION, "scsi%d : starting arbitration, id = %d\n", instance->host_no, instance->this_id);
 
 	/* 
 	 * Set the phase bits to 0, otherwise the NCR5380 won't drive the 
@@ -1333,7 +1324,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd * cmd, int tag)
 		goto failed;
 	}
 
-	dprintk(NDEBUG_ARBITRATION, ("scsi%d : arbitration complete\n", instance->host_no));
+	dprintk(NDEBUG_ARBITRATION, "scsi%d : arbitration complete\n", instance->host_no);
 
 	/* 
 	 * The arbitration delay is 2.2us, but this is a minimum and there is 
@@ -1347,7 +1338,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd * cmd, int tag)
 	/* Check for lost arbitration */
 	if ((NCR5380_read(INITIATOR_COMMAND_REG) & ICR_ARBITRATION_LOST) || (NCR5380_read(CURRENT_SCSI_DATA_REG) & hostdata->id_higher_mask) || (NCR5380_read(INITIATOR_COMMAND_REG) & ICR_ARBITRATION_LOST)) {
 		NCR5380_write(MODE_REG, MR_BASE);
-		dprintk(NDEBUG_ARBITRATION, ("scsi%d : lost arbitration, deasserting MR_ARBITRATE\n", instance->host_no));
+		dprintk(NDEBUG_ARBITRATION, "scsi%d : lost arbitration, deasserting MR_ARBITRATE\n", instance->host_no);
 		goto failed;
 	}
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_SEL);
@@ -1360,7 +1351,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd * cmd, int tag)
 	    (NCR5380_read(INITIATOR_COMMAND_REG) & ICR_ARBITRATION_LOST)) {
 		NCR5380_write(MODE_REG, MR_BASE);
 		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
-		dprintk(NDEBUG_ARBITRATION, ("scsi%d : lost arbitration, deasserting ICR_ASSERT_SEL\n", instance->host_no));
+		dprintk(NDEBUG_ARBITRATION, "scsi%d : lost arbitration, deasserting ICR_ASSERT_SEL\n", instance->host_no);
 		goto failed;
 	}
 	/* 
@@ -1370,7 +1361,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd * cmd, int tag)
 
 	udelay(2);
 
-	dprintk(NDEBUG_ARBITRATION, ("scsi%d : won arbitration\n", instance->host_no));
+	dprintk(NDEBUG_ARBITRATION, "scsi%d : won arbitration\n", instance->host_no);
 
 	/* 
 	 * Now that we have won arbitration, start Selection process, asserting 
@@ -1422,7 +1413,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd * cmd, int tag)
 
 	udelay(1);
 
-	dprintk(NDEBUG_SELECTION, ("scsi%d : selecting target %d\n", instance->host_no, scmd_id(cmd)));
+	dprintk(NDEBUG_SELECTION, "scsi%d : selecting target %d\n", instance->host_no, scmd_id(cmd));
 
 	/* 
 	 * The SCSI specification calls for a 250 ms timeout for the actual 
@@ -1487,7 +1478,7 @@ part2:
 		collect_stats(hostdata, cmd);
 		cmd->scsi_done(cmd);
 		NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
-		dprintk(NDEBUG_SELECTION, ("scsi%d : target did not respond within 250ms\n", instance->host_no));
+		dprintk(NDEBUG_SELECTION, "scsi%d : target did not respond within 250ms\n", instance->host_no);
 		NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
 		return 0;
 	}
@@ -1520,7 +1511,7 @@ part2:
 		goto failed;
 	}
 
-	dprintk(NDEBUG_SELECTION, ("scsi%d : target %d selected, going into MESSAGE OUT phase.\n", instance->host_no, cmd->device->id));
+	dprintk(NDEBUG_SELECTION, "scsi%d : target %d selected, going into MESSAGE OUT phase.\n", instance->host_no, cmd->device->id);
 	tmp[0] = IDENTIFY(((instance->irq == SCSI_IRQ_NONE) ? 0 : 1), cmd->device->lun);
 
 	len = 1;
@@ -1530,7 +1521,7 @@ part2:
 	data = tmp;
 	phase = PHASE_MSGOUT;
 	NCR5380_transfer_pio(instance, &phase, &len, &data);
-	dprintk(NDEBUG_SELECTION, ("scsi%d : nexus established.\n", instance->host_no));
+	dprintk(NDEBUG_SELECTION, "scsi%d : nexus established.\n", instance->host_no);
 	/* XXX need to handle errors here */
 	hostdata->connected = cmd;
 	hostdata->busy[cmd->device->id] |= (1 << cmd->device->lun);
@@ -1583,9 +1574,9 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance, unsigned char *phase
 	NCR5380_setup(instance);
 
 	if (!(p & SR_IO))
-		dprintk(NDEBUG_PIO, ("scsi%d : pio write %d bytes\n", instance->host_no, c));
+		dprintk(NDEBUG_PIO, "scsi%d : pio write %d bytes\n", instance->host_no, c);
 	else
-		dprintk(NDEBUG_PIO, ("scsi%d : pio read %d bytes\n", instance->host_no, c));
+		dprintk(NDEBUG_PIO, "scsi%d : pio read %d bytes\n", instance->host_no, c);
 
 	/* 
 	 * The NCR5380 chip will only drive the SCSI bus when the 
@@ -1620,11 +1611,11 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance, unsigned char *phase
 			break;
 		}
 
-		dprintk(NDEBUG_HANDSHAKE, ("scsi%d : REQ detected\n", instance->host_no));
+		dprintk(NDEBUG_HANDSHAKE, "scsi%d : REQ detected\n", instance->host_no);
 
 		/* Check for phase mismatch */
 		if ((tmp & PHASE_MASK) != p) {
-			dprintk(NDEBUG_HANDSHAKE, ("scsi%d : phase mismatch\n", instance->host_no));
+			dprintk(NDEBUG_HANDSHAKE, "scsi%d : phase mismatch\n", instance->host_no);
 			NCR5380_dprint_phase(NDEBUG_HANDSHAKE, instance);
 			break;
 		}
@@ -1660,7 +1651,7 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance, unsigned char *phase
 
 		/* FIXME - if this fails bus reset ?? */
 		NCR5380_poll_politely(instance, STATUS_REG, SR_REQ, 0, 5*HZ);
-		dprintk(NDEBUG_HANDSHAKE, ("scsi%d : req false, handshake complete\n", instance->host_no));
+		dprintk(NDEBUG_HANDSHAKE, "scsi%d : req false, handshake complete\n", instance->host_no);
 
 /*
  * We have several special cases to consider during REQ/ACK handshaking : 
@@ -1681,7 +1672,7 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance, unsigned char *phase
 		}
 	} while (--c);
 
-	dprintk(NDEBUG_PIO, ("scsi%d : residual %d\n", instance->host_no, c));
+	dprintk(NDEBUG_PIO, "scsi%d : residual %d\n", instance->host_no, c);
 
 	*count = c;
 	*data = d;
@@ -1828,7 +1819,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance, unsigned char *phase
 		c -= 2;
 	}
 #endif
-	dprintk(NDEBUG_DMA, ("scsi%d : initializing DMA channel %d for %s, %d bytes %s %0x\n", instance->host_no, instance->dma_channel, (p & SR_IO) ? "reading" : "writing", c, (p & SR_IO) ? "to" : "from", (unsigned) d));
+	dprintk(NDEBUG_DMA, "scsi%d : initializing DMA channel %d for %s, %d bytes %s %0x\n", instance->host_no, instance->dma_channel, (p & SR_IO) ? "reading" : "writing", c, (p & SR_IO) ? "to" : "from", (unsigned) d);
 	hostdata->dma_len = (p & SR_IO) ? NCR5380_dma_read_setup(instance, d, c) : NCR5380_dma_write_setup(instance, d, c);
 #endif
 
@@ -1857,7 +1848,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance, unsigned char *phase
 		NCR5380_write(MODE_REG, MR_BASE | MR_DMA_MODE);
 #endif				/* def REAL_DMA */
 
-	dprintk(NDEBUG_DMA, ("scsi%d : mode reg = 0x%X\n", instance->host_no, NCR5380_read(MODE_REG)));
+	dprintk(NDEBUG_DMA, "scsi%d : mode reg = 0x%X\n", instance->host_no, NCR5380_read(MODE_REG));
 
 	/* 
 	 *	On the PAS16 at least I/O recovery delays are not needed here.
@@ -1934,7 +1925,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance, unsigned char *phase
 		}
 	}
 
-	dprintk(NDEBUG_DMA, ("scsi%d : polled DMA transfer complete, basr 0x%X, sr 0x%X\n", instance->host_no, tmp, NCR5380_read(STATUS_REG)));
+	dprintk(NDEBUG_DMA, "scsi%d : polled DMA transfer complete, basr 0x%X, sr 0x%X\n", instance->host_no, tmp, NCR5380_read(STATUS_REG));
 
 	NCR5380_write(MODE_REG, MR_BASE);
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
@@ -1948,7 +1939,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance, unsigned char *phase
 #ifdef READ_OVERRUNS
 	if (*phase == p && (p & SR_IO) && residue == 0) {
 		if (overrun) {
-			dprintk(NDEBUG_DMA, ("Got an input overrun, using saved byte\n"));
+			dprintk(NDEBUG_DMA, "Got an input overrun, using saved byte\n");
 			**data = saved_data;
 			*data += 1;
 			*count -= 1;
@@ -1957,13 +1948,13 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance, unsigned char *phase
 			printk("No overrun??\n");
 			cnt = toPIO = 2;
 		}
-		dprintk(NDEBUG_DMA, ("Doing %d-byte PIO to 0x%X\n", cnt, *data));
+		dprintk(NDEBUG_DMA, "Doing %d-byte PIO to 0x%X\n", cnt, *data);
 		NCR5380_transfer_pio(instance, phase, &cnt, data);
 		*count -= toPIO - cnt;
 	}
 #endif
 
-	dprintk(NDEBUG_DMA, ("Return with data ptr = 0x%X, count %d, last 0x%X, next 0x%X\n", *data, *count, *(*data + *count - 1), *(*data + *count)));
+	dprintk(NDEBUG_DMA, "Return with data ptr = 0x%X, count %d, last 0x%X, next 0x%X\n", *data, *count, *(*data + *count - 1), *(*data + *count));
 	return 0;
 
 #elif defined(REAL_DMA)
@@ -2013,7 +2004,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance, unsigned char *phase
 		foo = NCR5380_pwrite(instance, d, c);
 #else
 		int timeout;
-		dprintk(NDEBUG_C400_PWRITE, ("About to pwrite %d bytes\n", c));
+		dprintk(NDEBUG_C400_PWRITE, "About to pwrite %d bytes\n", c);
 		if (!(foo = NCR5380_pwrite(instance, d, c))) {
 			/*
 			 * Wait for the last byte to be sent.  If REQ is being asserted for 
@@ -2024,19 +2015,19 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance, unsigned char *phase
 				while (!(NCR5380_read(BUS_AND_STATUS_REG) & BASR_DRQ) && (NCR5380_read(BUS_AND_STATUS_REG) & BASR_PHASE_MATCH));
 
 				if (!timeout)
-					dprintk(NDEBUG_LAST_BYTE_SENT, ("scsi%d : timed out on last byte\n", instance->host_no));
+					dprintk(NDEBUG_LAST_BYTE_SENT, "scsi%d : timed out on last byte\n", instance->host_no);
 
 				if (hostdata->flags & FLAG_CHECK_LAST_BYTE_SENT) {
 					hostdata->flags &= ~FLAG_CHECK_LAST_BYTE_SENT;
 					if (NCR5380_read(TARGET_COMMAND_REG) & TCR_LAST_BYTE_SENT) {
 						hostdata->flags |= FLAG_HAS_LAST_BYTE_SENT;
-						dprintk(NDEBUG_LAST_WRITE_SENT, ("scsi%d : last bit sent works\n", instance->host_no));
+						dprintk(NDEBUG_LAST_BYTE_SENT, "scsi%d : last byte sent works\n", instance->host_no);
 					}
 				}
 			} else {
-				dprintk(NDEBUG_C400_PWRITE, ("Waiting for LASTBYTE\n"));
+				dprintk(NDEBUG_C400_PWRITE, "Waiting for LASTBYTE\n");
 				while (!(NCR5380_read(TARGET_COMMAND_REG) & TCR_LAST_BYTE_SENT));
-				dprintk(NDEBUG_C400_PWRITE, ("Got LASTBYTE\n"));
+				dprintk(NDEBUG_C400_PWRITE, "Got LASTBYTE\n");
 			}
 		}
 #endif
@@ -2045,9 +2036,9 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance, unsigned char *phase
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 
 	if ((!(p & SR_IO)) && (hostdata->flags & FLAG_NCR53C400)) {
-		dprintk(NDEBUG_C400_PWRITE, ("53C400w: Checking for IRQ\n"));
+		dprintk(NDEBUG_C400_PWRITE, "53C400w: Checking for IRQ\n");
 		if (NCR5380_read(BUS_AND_STATUS_REG) & BASR_IRQ) {
-			dprintk(NDEBUG_C400_PWRITE, ("53C400w:    got it, reading reset interrupt reg\n"));
+			dprintk(NDEBUG_C400_PWRITE, "53C400w:    got it, reading reset interrupt reg\n");
 			NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 		} else {
 			printk("53C400w:    IRQ NOT THERE!\n");
@@ -2139,7 +2130,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 					--cmd->SCp.buffers_residual;
 					cmd->SCp.this_residual = cmd->SCp.buffer->length;
 					cmd->SCp.ptr = sg_virt(cmd->SCp.buffer);
-					dprintk(NDEBUG_INFORMATION, ("scsi%d : %d bytes and %d buffers left\n", instance->host_no, cmd->SCp.this_residual, cmd->SCp.buffers_residual));
+					dprintk(NDEBUG_INFORMATION, "scsi%d : %d bytes and %d buffers left\n", instance->host_no, cmd->SCp.this_residual, cmd->SCp.buffers_residual);
 				}
 				/*
 				 * The preferred transfer method is going to be 
@@ -2219,7 +2210,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 				case LINKED_FLG_CMD_COMPLETE:
 					/* Accept message by clearing ACK */
 					NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
-					dprintk(NDEBUG_LINKED, ("scsi%d : target %d lun %d linked command complete.\n", instance->host_no, cmd->device->id, cmd->device->lun));
+					dprintk(NDEBUG_LINKED, "scsi%d : target %d lun %d linked command complete.\n", instance->host_no, cmd->device->id, cmd->device->lun);
 					/* 
 					 * Sanity check : A linked command should only terminate with
 					 * one of these messages if there are more linked commands
@@ -2235,7 +2226,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 					/* The next command is still part of this process */
 					cmd->next_link->tag = cmd->tag;
 					cmd->result = cmd->SCp.Status | (cmd->SCp.Message << 8);
-					dprintk(NDEBUG_LINKED, ("scsi%d : target %d lun %d linked request done, calling scsi_done().\n", instance->host_no, cmd->device->id, cmd->device->lun));
+					dprintk(NDEBUG_LINKED, "scsi%d : target %d lun %d linked request done, calling scsi_done().\n", instance->host_no, cmd->device->id, cmd->device->lun);
 					collect_stats(hostdata, cmd);
 					cmd->scsi_done(cmd);
 					cmd = hostdata->connected;
@@ -2247,7 +2238,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 					sink = 1;
 					NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 					hostdata->connected = NULL;
-					dprintk(NDEBUG_QUEUES, ("scsi%d : command for target %d, lun %d completed\n", instance->host_no, cmd->device->id, cmd->device->lun));
+					dprintk(NDEBUG_QUEUES, "scsi%d : command for target %d, lun %d completed\n", instance->host_no, cmd->device->id, cmd->device->lun);
 					hostdata->busy[cmd->device->id] &= ~(1 << cmd->device->lun);
 
 					/* 
@@ -2281,13 +2272,13 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 					if ((cmd->cmnd[0] != REQUEST_SENSE) && (status_byte(cmd->SCp.Status) == CHECK_CONDITION)) {
 						scsi_eh_prep_cmnd(cmd, &hostdata->ses, NULL, 0, ~0);
 
-						dprintk(NDEBUG_AUTOSENSE, ("scsi%d : performing request sense\n", instance->host_no));
+						dprintk(NDEBUG_AUTOSENSE, "scsi%d : performing request sense\n", instance->host_no);
 
 						LIST(cmd, hostdata->issue_queue);
 						cmd->host_scribble = (unsigned char *)
 						    hostdata->issue_queue;
 						hostdata->issue_queue = (Scsi_Cmnd *) cmd;
-						dprintk(NDEBUG_QUEUES, ("scsi%d : REQUEST SENSE added to head of issue queue\n", instance->host_no));
+						dprintk(NDEBUG_QUEUES, "scsi%d : REQUEST SENSE added to head of issue queue\n", instance->host_no);
 					} else
 #endif				/* def AUTOSENSE */
 					{
@@ -2327,7 +2318,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 						    hostdata->disconnected_queue;
 						hostdata->connected = NULL;
 						hostdata->disconnected_queue = cmd;
-						dprintk(NDEBUG_QUEUES, ("scsi%d : command for target %d lun %d was moved from connected to" "  the disconnected_queue\n", instance->host_no, cmd->device->id, cmd->device->lun));
+						dprintk(NDEBUG_QUEUES, "scsi%d : command for target %d lun %d was moved from connected to" "  the disconnected_queue\n", instance->host_no, cmd->device->id, cmd->device->lun);
 						/* 
 						 * Restore phase bits to 0 so an interrupted selection, 
 						 * arbitration can resume.
@@ -2373,14 +2364,14 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 					extended_msg[0] = EXTENDED_MESSAGE;
 					/* Accept first byte by clearing ACK */
 					NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
-					dprintk(NDEBUG_EXTENDED, ("scsi%d : receiving extended message\n", instance->host_no));
+					dprintk(NDEBUG_EXTENDED, "scsi%d : receiving extended message\n", instance->host_no);
 
 					len = 2;
 					data = extended_msg + 1;
 					phase = PHASE_MSGIN;
 					NCR5380_transfer_pio(instance, &phase, &len, &data);
 
-					dprintk(NDEBUG_EXTENDED, ("scsi%d : length=%d, code=0x%02x\n", instance->host_no, (int) extended_msg[1], (int) extended_msg[2]));
+					dprintk(NDEBUG_EXTENDED, "scsi%d : length=%d, code=0x%02x\n", instance->host_no, (int) extended_msg[1], (int) extended_msg[2]);
 
 					if (!len && extended_msg[1] <= (sizeof(extended_msg) - 1)) {
 						/* Accept third byte by clearing ACK */
@@ -2390,7 +2381,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 						phase = PHASE_MSGIN;
 
 						NCR5380_transfer_pio(instance, &phase, &len, &data);
-						dprintk(NDEBUG_EXTENDED, ("scsi%d : message received, residual %d\n", instance->host_no, len));
+						dprintk(NDEBUG_EXTENDED, "scsi%d : message received, residual %d\n", instance->host_no, len);
 
 						switch (extended_msg[2]) {
 						case EXTENDED_SDTR:
@@ -2456,7 +2447,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 				NCR5380_transfer_pio(instance, &phase, &len, &data);
 				if (!cmd->device->disconnect && should_disconnect(cmd->cmnd[0])) {
 					NCR5380_set_timer(hostdata, USLEEP_SLEEP);
-					dprintk(NDEBUG_USLEEP, ("scsi%d : issued command, sleeping until %ul\n", instance->host_no, hostdata->time_expires));
+					dprintk(NDEBUG_USLEEP, "scsi%d : issued command, sleeping until %lu\n", instance->host_no, hostdata->time_expires);
 					return;
 				}
 				break;
@@ -2468,7 +2459,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 				break;
 			default:
 				printk("scsi%d : unknown phase\n", instance->host_no);
-				NCR5380_dprint(NDEBUG_ALL, instance);
+				NCR5380_dprint(NDEBUG_ANY, instance);
 			}	/* switch(phase) */
 		}		/* if (tmp * SR_REQ) */
 		else {
@@ -2476,7 +2467,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance) {
 			 */
 			if (!cmd->device->disconnect && time_after_eq(jiffies, poll_time)) {
 				NCR5380_set_timer(hostdata, USLEEP_SLEEP);
-				dprintk(NDEBUG_USLEEP, ("scsi%d : poll timed out, sleeping until %ul\n", instance->host_no, hostdata->time_expires));
+				dprintk(NDEBUG_USLEEP, "scsi%d : poll timed out, sleeping until %lu\n", instance->host_no, hostdata->time_expires);
 				return;
 			}
 		}
@@ -2517,7 +2508,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance) {
 	hostdata->restart_select = 1;
 
 	target_mask = NCR5380_read(CURRENT_SCSI_DATA_REG) & ~(hostdata->id_mask);
-	dprintk(NDEBUG_SELECTION, ("scsi%d : reselect\n", instance->host_no));
+	dprintk(NDEBUG_SELECTION, "scsi%d : reselect\n", instance->host_no);
 
 	/* 
 	 * At this point, we have detected that our SCSI ID is on the bus,
@@ -2597,7 +2588,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance) {
 		do_abort(instance);
 	} else {
 		hostdata->connected = tmp;
-		dprintk(NDEBUG_RESELECTION, ("scsi%d : nexus established, target = %d, lun = %d, tag = %d\n", instance->host_no, tmp->target, tmp->lun, tmp->tag));
+		dprintk(NDEBUG_RESELECTION, "scsi%d : nexus established, target = %d, lun = %d, tag = %d\n", instance->host_no, tmp->device->id, tmp->device->lun, tmp->tag);
 	}
 }
 
@@ -2682,8 +2673,8 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) {
 
 	NCR5380_setup(instance);
 
-	dprintk(NDEBUG_ABORT, ("scsi%d : abort called\n", instance->host_no));
-	dprintk(NDEBUG_ABORT, ("        basr 0x%X, sr 0x%X\n", NCR5380_read(BUS_AND_STATUS_REG), NCR5380_read(STATUS_REG)));
+	dprintk(NDEBUG_ABORT, "scsi%d : abort called\n", instance->host_no);
+	dprintk(NDEBUG_ABORT, "        basr 0x%X, sr 0x%X\n", NCR5380_read(BUS_AND_STATUS_REG), NCR5380_read(STATUS_REG));
 
 #if 0
 /*
@@ -2693,7 +2684,7 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) {
  */
 
 	if (hostdata->connected == cmd) {
-		dprintk(NDEBUG_ABORT, ("scsi%d : aborting connected command\n", instance->host_no));
+		dprintk(NDEBUG_ABORT, "scsi%d : aborting connected command\n", instance->host_no);
 		hostdata->aborted = 1;
 /*
  * We should perform BSY checking, and make sure we haven't slipped
@@ -2721,14 +2712,14 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) {
  *          from the issue queue.
  */
  
-	dprintk(NDEBUG_ABORT, ("scsi%d : abort going into loop.\n", instance->host_no));
+	dprintk(NDEBUG_ABORT, "scsi%d : abort going into loop.\n", instance->host_no);
 	for (prev = (Scsi_Cmnd **) & (hostdata->issue_queue), tmp = (Scsi_Cmnd *) hostdata->issue_queue; tmp; prev = (Scsi_Cmnd **) & (tmp->host_scribble), tmp = (Scsi_Cmnd *) tmp->host_scribble)
 		if (cmd == tmp) {
 			REMOVE(5, *prev, tmp, tmp->host_scribble);
 			(*prev) = (Scsi_Cmnd *) tmp->host_scribble;
 			tmp->host_scribble = NULL;
 			tmp->result = DID_ABORT << 16;
-			dprintk(NDEBUG_ABORT, ("scsi%d : abort removed command from issue queue.\n", instance->host_no));
+			dprintk(NDEBUG_ABORT, "scsi%d : abort removed command from issue queue.\n", instance->host_no);
 			tmp->scsi_done(tmp);
 			return SUCCESS;
 		}
@@ -2750,7 +2741,7 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) {
  */
 
 	if (hostdata->connected) {
-		dprintk(NDEBUG_ABORT, ("scsi%d : abort failed, command connected.\n", instance->host_no));
+		dprintk(NDEBUG_ABORT, "scsi%d : abort failed, command connected.\n", instance->host_no);
 		return FAILED;
 	}
 /*
@@ -2780,11 +2771,11 @@ static int NCR5380_abort(Scsi_Cmnd * cmd) {
 
 	for (tmp = (Scsi_Cmnd *) hostdata->disconnected_queue; tmp; tmp = (Scsi_Cmnd *) tmp->host_scribble)
 		if (cmd == tmp) {
-			dprintk(NDEBUG_ABORT, ("scsi%d : aborting disconnected command.\n", instance->host_no));
+			dprintk(NDEBUG_ABORT, "scsi%d : aborting disconnected command.\n", instance->host_no);
 
 			if (NCR5380_select(instance, cmd, (int) cmd->tag))
 				return FAILED;
-			dprintk(NDEBUG_ABORT, ("scsi%d : nexus reestablished.\n", instance->host_no));
+			dprintk(NDEBUG_ABORT, "scsi%d : nexus reestablished.\n", instance->host_no);
 
 			do_abort(instance);
 
diff --git a/drivers/scsi/NCR5380.h b/drivers/scsi/NCR5380.h
index 14964d0a0e9..c79ddfa6f53 100644
--- a/drivers/scsi/NCR5380.h
+++ b/drivers/scsi/NCR5380.h
@@ -21,10 +21,6 @@
  * 1+ (800) 334-5454
  */
 
-/*
- * $Log: NCR5380.h,v $
- */
-
 #ifndef NCR5380_H
 #define NCR5380_H
 
@@ -60,6 +56,9 @@
 #define NDEBUG_C400_PREAD	0x100000
 #define NDEBUG_C400_PWRITE	0x200000
 #define NDEBUG_LISTS		0x400000
+#define NDEBUG_ABORT		0x800000
+#define NDEBUG_TAGS		0x1000000
+#define NDEBUG_MERGING		0x2000000
 
 #define NDEBUG_ANY		0xFFFFFFFFUL
 
@@ -292,9 +291,24 @@ struct NCR5380_hostdata {
 
 #ifdef __KERNEL__
 
-#define dprintk(a,b)			do {} while(0)
-#define NCR5380_dprint(a,b)		do {} while(0)
-#define NCR5380_dprint_phase(a,b)	do {} while(0)
+#ifndef NDEBUG
+#define NDEBUG (0)
+#endif
+
+#define dprintk(flg, fmt, ...) \
+	do { if ((NDEBUG) & (flg)) pr_debug(fmt, ## __VA_ARGS__); } while (0)
+
+#if NDEBUG
+#define NCR5380_dprint(flg, arg) \
+	do { if ((NDEBUG) & (flg)) NCR5380_print(arg); } while (0)
+#define NCR5380_dprint_phase(flg, arg) \
+	do { if ((NDEBUG) & (flg)) NCR5380_print_phase(arg); } while (0)
+static void NCR5380_print_phase(struct Scsi_Host *instance);
+static void NCR5380_print(struct Scsi_Host *instance);
+#else
+#define NCR5380_dprint(flg, arg)       do {} while (0)
+#define NCR5380_dprint_phase(flg, arg) do {} while (0)
+#endif
 
 #if defined(AUTOPROBE_IRQ)
 static int NCR5380_probe_irq(struct Scsi_Host *instance, int possible);
@@ -307,10 +321,6 @@ static irqreturn_t NCR5380_intr(int irq, void *dev_id);
 #endif
 static void NCR5380_main(struct work_struct *work);
 static void __maybe_unused NCR5380_print_options(struct Scsi_Host *instance);
-#ifdef NDEBUG
-static void NCR5380_print_phase(struct Scsi_Host *instance);
-static void NCR5380_print(struct Scsi_Host *instance);
-#endif
 static int NCR5380_abort(Scsi_Cmnd * cmd);
 static int NCR5380_bus_reset(Scsi_Cmnd * cmd);
 static int NCR5380_queue_command(struct Scsi_Host *, struct scsi_cmnd *);
diff --git a/drivers/scsi/aic7xxx/aic79xx_pci.c b/drivers/scsi/aic7xxx/aic79xx_pci.c
index 14b5f8d0e7f..cc9bd26f5d1 100644
--- a/drivers/scsi/aic7xxx/aic79xx_pci.c
+++ b/drivers/scsi/aic7xxx/aic79xx_pci.c
@@ -827,7 +827,7 @@ ahd_pci_intr(struct ahd_softc *ahd)
 		for (bit = 0; bit < 8; bit++) {
 
 			if ((pci_status[i] & (0x1 << bit)) != 0) {
-				static const char *s;
+				const char *s;
 
 				s = pci_status_strings[bit];
 				if (i == 7/*TARG*/ && bit == 3)
@@ -887,23 +887,15 @@ ahd_pci_split_intr(struct ahd_softc *ahd, u_int intstat)
 
 		for (bit = 0; bit < 8; bit++) {
 
-			if ((split_status[i] & (0x1 << bit)) != 0) {
-				static const char *s;
-
-				s = split_status_strings[bit];
-				printk(s, ahd_name(ahd),
+			if ((split_status[i] & (0x1 << bit)) != 0)
+				printk(split_status_strings[bit], ahd_name(ahd),
 				       split_status_source[i]);
-			}
 
 			if (i > 1)
 				continue;
 
-			if ((sg_split_status[i] & (0x1 << bit)) != 0) {
-				static const char *s;
-
-				s = split_status_strings[bit];
-				printk(s, ahd_name(ahd), "SG");
-			}
+			if ((sg_split_status[i] & (0x1 << bit)) != 0)
+				printk(split_status_strings[bit], ahd_name(ahd), "SG");
 		}
 	}
 	/*
diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c
index 059ff477a39..2e797a36760 100644
--- a/drivers/scsi/arm/acornscsi.c
+++ b/drivers/scsi/arm/acornscsi.c
@@ -62,13 +62,6 @@
  */
 #undef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE
 /*
- * SCSI-II Linked command support.
- *
- * The higher level code doesn't support linked commands yet, and so the option
- * is undef'd here.
- */
-#undef CONFIG_SCSI_ACORNSCSI_LINK
-/*
  * SCSI-II Synchronous transfer support.
  *
  * Tried and tested...
@@ -160,10 +153,6 @@
 #error "Yippee!  ABORT TAG is now defined!  Remove this error!"
 #endif
 
-#ifdef CONFIG_SCSI_ACORNSCSI_LINK
-#error SCSI2 LINKed commands not supported (yet)!
-#endif
-
 #ifdef USE_DMAC
 /*
  * DMAC setup parameters
@@ -1668,42 +1657,6 @@ void acornscsi_message(AS_Host *host)
 	}
 	break;
 
-#ifdef CONFIG_SCSI_ACORNSCSI_LINK
-    case LINKED_CMD_COMPLETE:
-    case LINKED_FLG_CMD_COMPLETE:
-	/*
-	 * We don't support linked commands yet
-	 */
-	if (0) {
-#if (DEBUG & DEBUG_LINK)
-	    printk("scsi%d.%c: lun %d tag %d linked command complete\n",
-		    host->host->host_no, acornscsi_target(host), host->SCpnt->tag);
-#endif
-	    /*
-	     * A linked command should only terminate with one of these messages
-	     * if there are more linked commands available.
-	     */
-	    if (!host->SCpnt->next_link) {
-		printk(KERN_WARNING "scsi%d.%c: lun %d tag %d linked command complete, but no next_link\n",
-			instance->host_no, acornscsi_target(host), host->SCpnt->tag);
-		acornscsi_sbic_issuecmd(host, CMND_ASSERTATN);
-		msgqueue_addmsg(&host->scsi.msgs, 1, ABORT);
-	    } else {
-		struct scsi_cmnd *SCpnt = host->SCpnt;
-
-		acornscsi_dma_cleanup(host);
-
-		host->SCpnt = host->SCpnt->next_link;
-		host->SCpnt->tag = SCpnt->tag;
-		SCpnt->result = DID_OK | host->scsi.SCp.Message << 8 | host->Scsi.SCp.Status;
-		SCpnt->done(SCpnt);
-
-		/* initialise host->SCpnt->SCp */
-	    }
-	    break;
-	}
-#endif
-
     default: /* reject message */
 	printk(KERN_ERR "scsi%d.%c: unrecognised message %02X, rejecting\n",
 		host->host->host_no, acornscsi_target(host),
@@ -2825,9 +2778,6 @@ char *acornscsi_info(struct Scsi_Host *host)
 #ifdef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE
     " TAG"
 #endif
-#ifdef CONFIG_SCSI_ACORNSCSI_LINK
-    " LINK"
-#endif
 #if (DEBUG & DEBUG_NO_WRITE)
     " NOWRITE (" __stringify(NO_WRITE) ")"
 #endif
@@ -2851,9 +2801,6 @@ static int acornscsi_show_info(struct seq_file *m, struct Scsi_Host *instance)
 #ifdef CONFIG_SCSI_ACORNSCSI_TAGGED_QUEUE
     " TAG"
 #endif
-#ifdef CONFIG_SCSI_ACORNSCSI_LINK
-    " LINK"
-#endif
 #if (DEBUG & DEBUG_NO_WRITE)
     " NOWRITE (" __stringify(NO_WRITE) ")"
 #endif
diff --git a/drivers/scsi/arm/cumana_1.c b/drivers/scsi/arm/cumana_1.c
index f8e06090005..8ef810a4476 100644
--- a/drivers/scsi/arm/cumana_1.c
+++ b/drivers/scsi/arm/cumana_1.c
@@ -36,9 +36,6 @@
 	void __iomem *base;		\
 	void __iomem *dma
 
-#define BOARD_NORMAL	0
-#define BOARD_NCR53C400	1
-
 #include "../NCR5380.h"
 
 void cumanascsi_setup(char *str, int *ints)
diff --git a/drivers/scsi/arm/oak.c b/drivers/scsi/arm/oak.c
index 4266eef8aca..188e734c7ff 100644
--- a/drivers/scsi/arm/oak.c
+++ b/drivers/scsi/arm/oak.c
@@ -37,9 +37,6 @@
 #define NCR5380_implementation_fields	\
 	void __iomem *base
 
-#define BOARD_NORMAL	0
-#define BOARD_NCR53C400	1
-
 #include "../NCR5380.h"
 
 #undef START_DMA_INITIATOR_RECEIVE_REG
diff --git a/drivers/scsi/atari_NCR5380.c b/drivers/scsi/atari_NCR5380.c
index 0f3cdbc80ba..1814aa20b72 100644
--- a/drivers/scsi/atari_NCR5380.c
+++ b/drivers/scsi/atari_NCR5380.c
@@ -370,7 +370,7 @@ static int is_lun_busy(Scsi_Cmnd *cmd, int should_be_tagged)
 		return 0;
 	if (TagAlloc[cmd->device->id][cmd->device->lun].nr_allocated >=
 	    TagAlloc[cmd->device->id][cmd->device->lun].queue_size) {
-		TAG_PRINTK("scsi%d: target %d lun %d: no free tags\n",
+		dprintk(NDEBUG_TAGS, "scsi%d: target %d lun %d: no free tags\n",
 			   H_NO(cmd), cmd->device->id, cmd->device->lun);
 		return 1;
 	}
@@ -394,7 +394,7 @@ static void cmd_get_tag(Scsi_Cmnd *cmd, int should_be_tagged)
 	    !setup_use_tagged_queuing || !cmd->device->tagged_supported) {
 		cmd->tag = TAG_NONE;
 		hostdata->busy[cmd->device->id] |= (1 << cmd->device->lun);
-		TAG_PRINTK("scsi%d: target %d lun %d now allocated by untagged "
+		dprintk(NDEBUG_TAGS, "scsi%d: target %d lun %d now allocated by untagged "
 			   "command\n", H_NO(cmd), cmd->device->id, cmd->device->lun);
 	} else {
 		TAG_ALLOC *ta = &TagAlloc[cmd->device->id][cmd->device->lun];
@@ -402,7 +402,7 @@ static void cmd_get_tag(Scsi_Cmnd *cmd, int should_be_tagged)
 		cmd->tag = find_first_zero_bit(ta->allocated, MAX_TAGS);
 		set_bit(cmd->tag, ta->allocated);
 		ta->nr_allocated++;
-		TAG_PRINTK("scsi%d: using tag %d for target %d lun %d "
+		dprintk(NDEBUG_TAGS, "scsi%d: using tag %d for target %d lun %d "
 			   "(now %d tags in use)\n",
 			   H_NO(cmd), cmd->tag, cmd->device->id,
 			   cmd->device->lun, ta->nr_allocated);
@@ -420,7 +420,7 @@ static void cmd_free_tag(Scsi_Cmnd *cmd)
 
 	if (cmd->tag == TAG_NONE) {
 		hostdata->busy[cmd->device->id] &= ~(1 << cmd->device->lun);
-		TAG_PRINTK("scsi%d: target %d lun %d untagged cmd finished\n",
+		dprintk(NDEBUG_TAGS, "scsi%d: target %d lun %d untagged cmd finished\n",
 			   H_NO(cmd), cmd->device->id, cmd->device->lun);
 	} else if (cmd->tag >= MAX_TAGS) {
 		printk(KERN_NOTICE "scsi%d: trying to free bad tag %d!\n",
@@ -429,7 +429,7 @@ static void cmd_free_tag(Scsi_Cmnd *cmd)
 		TAG_ALLOC *ta = &TagAlloc[cmd->device->id][cmd->device->lun];
 		clear_bit(cmd->tag, ta->allocated);
 		ta->nr_allocated--;
-		TAG_PRINTK("scsi%d: freed tag %d for target %d lun %d\n",
+		dprintk(NDEBUG_TAGS, "scsi%d: freed tag %d for target %d lun %d\n",
 			   H_NO(cmd), cmd->tag, cmd->device->id, cmd->device->lun);
 	}
 }
@@ -478,7 +478,7 @@ static void merge_contiguous_buffers(Scsi_Cmnd *cmd)
 	for (endaddr = virt_to_phys(cmd->SCp.ptr + cmd->SCp.this_residual - 1) + 1;
 	     cmd->SCp.buffers_residual &&
 	     virt_to_phys(sg_virt(&cmd->SCp.buffer[1])) == endaddr;) {
-		MER_PRINTK("VTOP(%p) == %08lx -> merging\n",
+		dprintk(NDEBUG_MERGING, "VTOP(%p) == %08lx -> merging\n",
 			   page_address(sg_page(&cmd->SCp.buffer[1])), endaddr);
 #if (NDEBUG & NDEBUG_MERGING)
 		++cnt;
@@ -490,7 +490,7 @@ static void merge_contiguous_buffers(Scsi_Cmnd *cmd)
 	}
 #if (NDEBUG & NDEBUG_MERGING)
 	if (oldlen != cmd->SCp.this_residual)
-		MER_PRINTK("merged %d buffers from %p, new length %08x\n",
+		dprintk(NDEBUG_MERGING, "merged %d buffers from %p, new length %08x\n",
 			   cnt, cmd->SCp.ptr, cmd->SCp.this_residual);
 #endif
 }
@@ -626,16 +626,6 @@ static void NCR5380_print_phase(struct Scsi_Host *instance)
 	}
 }
 
-#else /* !NDEBUG */
-
-/* dummies... */
-static inline void NCR5380_print(struct Scsi_Host *instance)
-{
-};
-static inline void NCR5380_print_phase(struct Scsi_Host *instance)
-{
-};
-
 #endif
 
 /*
@@ -676,7 +666,7 @@ static inline void NCR5380_all_init(void)
 {
 	static int done = 0;
 	if (!done) {
-		INI_PRINTK("scsi : NCR5380_all_init()\n");
+		dprintk(NDEBUG_INIT, "scsi : NCR5380_all_init()\n");
 		done = 1;
 	}
 }
@@ -739,8 +729,8 @@ static void NCR5380_print_status(struct Scsi_Host *instance)
 	Scsi_Cmnd *ptr;
 	unsigned long flags;
 
-	NCR_PRINT(NDEBUG_ANY);
-	NCR_PRINT_PHASE(NDEBUG_ANY);
+	NCR5380_dprint(NDEBUG_ANY, instance);
+	NCR5380_dprint_phase(NDEBUG_ANY, instance);
 
 	hostdata = (struct NCR5380_hostdata *)instance->hostdata;
 
@@ -984,7 +974,7 @@ static int NCR5380_queue_command_lck(Scsi_Cmnd *cmd, void (*done)(Scsi_Cmnd *))
 	}
 	local_irq_restore(flags);
 
-	QU_PRINTK("scsi%d: command added to %s of queue\n", H_NO(cmd),
+	dprintk(NDEBUG_QUEUES, "scsi%d: command added to %s of queue\n", H_NO(cmd),
 		  (cmd->cmnd[0] == REQUEST_SENSE) ? "head" : "tail");
 
 	/* If queue_command() is called from an interrupt (real one or bottom
@@ -1054,7 +1044,7 @@ static void NCR5380_main(struct work_struct *work)
 		done = 1;
 
 		if (!hostdata->connected) {
-			MAIN_PRINTK("scsi%d: not connected\n", HOSTNO);
+			dprintk(NDEBUG_MAIN, "scsi%d: not connected\n", HOSTNO);
 			/*
 			 * Search through the issue_queue for a command destined
 			 * for a target that's not busy.
@@ -1107,7 +1097,7 @@ static void NCR5380_main(struct work_struct *work)
 					 * On failure, we must add the command back to the
 					 *   issue queue so we can keep trying.
 					 */
-					MAIN_PRINTK("scsi%d: main(): command for target %d "
+					dprintk(NDEBUG_MAIN, "scsi%d: main(): command for target %d "
 						    "lun %d removed from issue_queue\n",
 						    HOSTNO, tmp->device->id, tmp->device->lun);
 					/*
@@ -1140,7 +1130,7 @@ static void NCR5380_main(struct work_struct *work)
 #endif
 						falcon_dont_release--;
 						local_irq_restore(flags);
-						MAIN_PRINTK("scsi%d: main(): select() failed, "
+						dprintk(NDEBUG_MAIN, "scsi%d: main(): select() failed, "
 							    "returned to issue_queue\n", HOSTNO);
 						if (hostdata->connected)
 							break;
@@ -1155,10 +1145,10 @@ static void NCR5380_main(struct work_struct *work)
 #endif
 		    ) {
 			local_irq_restore(flags);
-			MAIN_PRINTK("scsi%d: main: performing information transfer\n",
+			dprintk(NDEBUG_MAIN, "scsi%d: main: performing information transfer\n",
 				    HOSTNO);
 			NCR5380_information_transfer(instance);
-			MAIN_PRINTK("scsi%d: main: done set false\n", HOSTNO);
+			dprintk(NDEBUG_MAIN, "scsi%d: main: done set false\n", HOSTNO);
 			done = 0;
 		}
 	} while (!done);
@@ -1204,12 +1194,12 @@ static void NCR5380_dma_complete(struct Scsi_Host *instance)
 			    (BASR_PHASE_MATCH|BASR_ACK)) {
 				saved_data = NCR5380_read(INPUT_DATA_REG);
 				overrun = 1;
-				DMA_PRINTK("scsi%d: read overrun handled\n", HOSTNO);
+				dprintk(NDEBUG_DMA, "scsi%d: read overrun handled\n", HOSTNO);
 			}
 		}
 	}
 
-	DMA_PRINTK("scsi%d: real DMA transfer complete, basr 0x%X, sr 0x%X\n",
+	dprintk(NDEBUG_DMA, "scsi%d: real DMA transfer complete, basr 0x%X, sr 0x%X\n",
 		   HOSTNO, NCR5380_read(BUS_AND_STATUS_REG),
 		   NCR5380_read(STATUS_REG));
 
@@ -1229,13 +1219,13 @@ static void NCR5380_dma_complete(struct Scsi_Host *instance)
 		if ((NCR5380_read(STATUS_REG) & PHASE_MASK) == p && (p & SR_IO)) {
 			cnt = toPIO = atari_read_overruns;
 			if (overrun) {
-				DMA_PRINTK("Got an input overrun, using saved byte\n");
+				dprintk(NDEBUG_DMA, "Got an input overrun, using saved byte\n");
 				*(*data)++ = saved_data;
 				(*count)--;
 				cnt--;
 				toPIO--;
 			}
-			DMA_PRINTK("Doing %d-byte PIO to 0x%08lx\n", cnt, (long)*data);
+			dprintk(NDEBUG_DMA, "Doing %d-byte PIO to 0x%08lx\n", cnt, (long)*data);
 			NCR5380_transfer_pio(instance, &p, &cnt, data);
 			*count -= toPIO - cnt;
 		}
@@ -1261,25 +1251,25 @@ static irqreturn_t NCR5380_intr(int irq, void *dev_id)
 	int done = 1, handled = 0;
 	unsigned char basr;
 
-	INT_PRINTK("scsi%d: NCR5380 irq triggered\n", HOSTNO);
+	dprintk(NDEBUG_INTR, "scsi%d: NCR5380 irq triggered\n", HOSTNO);
 
 	/* Look for pending interrupts */
 	basr = NCR5380_read(BUS_AND_STATUS_REG);
-	INT_PRINTK("scsi%d: BASR=%02x\n", HOSTNO, basr);
+	dprintk(NDEBUG_INTR, "scsi%d: BASR=%02x\n", HOSTNO, basr);
 	/* dispatch to appropriate routine if found and done=0 */
 	if (basr & BASR_IRQ) {
-		NCR_PRINT(NDEBUG_INTR);
+		NCR5380_dprint(NDEBUG_INTR, instance);
 		if ((NCR5380_read(STATUS_REG) & (SR_SEL|SR_IO)) == (SR_SEL|SR_IO)) {
 			done = 0;
 			ENABLE_IRQ();
-			INT_PRINTK("scsi%d: SEL interrupt\n", HOSTNO);
+			dprintk(NDEBUG_INTR, "scsi%d: SEL interrupt\n", HOSTNO);
 			NCR5380_reselect(instance);
 			(void)NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 		} else if (basr & BASR_PARITY_ERROR) {
-			INT_PRINTK("scsi%d: PARITY interrupt\n", HOSTNO);
+			dprintk(NDEBUG_INTR, "scsi%d: PARITY interrupt\n", HOSTNO);
 			(void)NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 		} else if ((NCR5380_read(STATUS_REG) & SR_RST) == SR_RST) {
-			INT_PRINTK("scsi%d: RESET interrupt\n", HOSTNO);
+			dprintk(NDEBUG_INTR, "scsi%d: RESET interrupt\n", HOSTNO);
 			(void)NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 		} else {
 			/*
@@ -1298,7 +1288,7 @@ static irqreturn_t NCR5380_intr(int irq, void *dev_id)
 			    ((basr & BASR_END_DMA_TRANSFER) ||
 			     !(basr & BASR_PHASE_MATCH))) {
 
-				INT_PRINTK("scsi%d: PHASE MISM or EOP interrupt\n", HOSTNO);
+				dprintk(NDEBUG_INTR, "scsi%d: PHASE MISM or EOP interrupt\n", HOSTNO);
 				NCR5380_dma_complete( instance );
 				done = 0;
 				ENABLE_IRQ();
@@ -1323,7 +1313,7 @@ static irqreturn_t NCR5380_intr(int irq, void *dev_id)
 	}
 
 	if (!done) {
-		INT_PRINTK("scsi%d: in int routine, calling main\n", HOSTNO);
+		dprintk(NDEBUG_INTR, "scsi%d: in int routine, calling main\n", HOSTNO);
 		/* Put a call to NCR5380_main() on the queue... */
 		queue_main();
 	}
@@ -1396,8 +1386,8 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 	unsigned long flags;
 
 	hostdata->restart_select = 0;
-	NCR_PRINT(NDEBUG_ARBITRATION);
-	ARB_PRINTK("scsi%d: starting arbitration, id = %d\n", HOSTNO,
+	NCR5380_dprint(NDEBUG_ARBITRATION, instance);
+	dprintk(NDEBUG_ARBITRATION, "scsi%d: starting arbitration, id = %d\n", HOSTNO,
 		   instance->this_id);
 
 	/*
@@ -1442,7 +1432,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 		;
 #endif
 
-	ARB_PRINTK("scsi%d: arbitration complete\n", HOSTNO);
+	dprintk(NDEBUG_ARBITRATION, "scsi%d: arbitration complete\n", HOSTNO);
 
 	if (hostdata->connected) {
 		NCR5380_write(MODE_REG, MR_BASE);
@@ -1463,7 +1453,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 	    (NCR5380_read(INITIATOR_COMMAND_REG) & ICR_ARBITRATION_LOST) ||
 	    hostdata->connected) {
 		NCR5380_write(MODE_REG, MR_BASE);
-		ARB_PRINTK("scsi%d: lost arbitration, deasserting MR_ARBITRATE\n",
+		dprintk(NDEBUG_ARBITRATION, "scsi%d: lost arbitration, deasserting MR_ARBITRATE\n",
 			   HOSTNO);
 		return -1;
 	}
@@ -1478,7 +1468,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 	    hostdata->connected) {
 		NCR5380_write(MODE_REG, MR_BASE);
 		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
-		ARB_PRINTK("scsi%d: lost arbitration, deasserting ICR_ASSERT_SEL\n",
+		dprintk(NDEBUG_ARBITRATION, "scsi%d: lost arbitration, deasserting ICR_ASSERT_SEL\n",
 			   HOSTNO);
 		return -1;
 	}
@@ -1501,7 +1491,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 		return -1;
 	}
 
-	ARB_PRINTK("scsi%d: won arbitration\n", HOSTNO);
+	dprintk(NDEBUG_ARBITRATION, "scsi%d: won arbitration\n", HOSTNO);
 
 	/*
 	 * Now that we have won arbitration, start Selection process, asserting
@@ -1561,7 +1551,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 
 	udelay(1);
 
-	SEL_PRINTK("scsi%d: selecting target %d\n", HOSTNO, cmd->device->id);
+	dprintk(NDEBUG_SELECTION, "scsi%d: selecting target %d\n", HOSTNO, cmd->device->id);
 
 	/*
 	 * The SCSI specification calls for a 250 ms timeout for the actual
@@ -1617,7 +1607,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 			printk(KERN_ERR "scsi%d: weirdness\n", HOSTNO);
 			if (hostdata->restart_select)
 				printk(KERN_NOTICE "\trestart select\n");
-			NCR_PRINT(NDEBUG_ANY);
+			NCR5380_dprint(NDEBUG_ANY, instance);
 			NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
 			return -1;
 		}
@@ -1630,7 +1620,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 #endif
 		cmd->scsi_done(cmd);
 		NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
-		SEL_PRINTK("scsi%d: target did not respond within 250ms\n", HOSTNO);
+		dprintk(NDEBUG_SELECTION, "scsi%d: target did not respond within 250ms\n", HOSTNO);
 		NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
 		return 0;
 	}
@@ -1656,7 +1646,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 	while (!(NCR5380_read(STATUS_REG) & SR_REQ))
 		;
 
-	SEL_PRINTK("scsi%d: target %d selected, going into MESSAGE OUT phase.\n",
+	dprintk(NDEBUG_SELECTION, "scsi%d: target %d selected, going into MESSAGE OUT phase.\n",
 		   HOSTNO, cmd->device->id);
 	tmp[0] = IDENTIFY(1, cmd->device->lun);
 
@@ -1676,7 +1666,7 @@ static int NCR5380_select(struct Scsi_Host *instance, Scsi_Cmnd *cmd, int tag)
 	data = tmp;
 	phase = PHASE_MSGOUT;
 	NCR5380_transfer_pio(instance, &phase, &len, &data);
-	SEL_PRINTK("scsi%d: nexus established.\n", HOSTNO);
+	dprintk(NDEBUG_SELECTION, "scsi%d: nexus established.\n", HOSTNO);
 	/* XXX need to handle errors here */
 	hostdata->connected = cmd;
 #ifndef SUPPORT_TAGS
@@ -1737,12 +1727,12 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance,
 		while (!((tmp = NCR5380_read(STATUS_REG)) & SR_REQ))
 			;
 
-		HSH_PRINTK("scsi%d: REQ detected\n", HOSTNO);
+		dprintk(NDEBUG_HANDSHAKE, "scsi%d: REQ detected\n", HOSTNO);
 
 		/* Check for phase mismatch */
 		if ((tmp & PHASE_MASK) != p) {
-			PIO_PRINTK("scsi%d: phase mismatch\n", HOSTNO);
-			NCR_PRINT_PHASE(NDEBUG_PIO);
+			dprintk(NDEBUG_PIO, "scsi%d: phase mismatch\n", HOSTNO);
+			NCR5380_dprint_phase(NDEBUG_PIO, instance);
 			break;
 		}
 
@@ -1764,25 +1754,25 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance,
 		if (!(p & SR_IO)) {
 			if (!((p & SR_MSG) && c > 1)) {
 				NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_DATA);
-				NCR_PRINT(NDEBUG_PIO);
+				NCR5380_dprint(NDEBUG_PIO, instance);
 				NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE |
 					      ICR_ASSERT_DATA | ICR_ASSERT_ACK);
 			} else {
 				NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE |
 					      ICR_ASSERT_DATA | ICR_ASSERT_ATN);
-				NCR_PRINT(NDEBUG_PIO);
+				NCR5380_dprint(NDEBUG_PIO, instance);
 				NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE |
 					      ICR_ASSERT_DATA | ICR_ASSERT_ATN | ICR_ASSERT_ACK);
 			}
 		} else {
-			NCR_PRINT(NDEBUG_PIO);
+			NCR5380_dprint(NDEBUG_PIO, instance);
 			NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_ACK);
 		}
 
 		while (NCR5380_read(STATUS_REG) & SR_REQ)
 			;
 
-		HSH_PRINTK("scsi%d: req false, handshake complete\n", HOSTNO);
+		dprintk(NDEBUG_HANDSHAKE, "scsi%d: req false, handshake complete\n", HOSTNO);
 
 		/*
 		 * We have several special cases to consider during REQ/ACK handshaking :
@@ -1803,7 +1793,7 @@ static int NCR5380_transfer_pio(struct Scsi_Host *instance,
 		}
 	} while (--c);
 
-	PIO_PRINTK("scsi%d: residual %d\n", HOSTNO, c);
+	dprintk(NDEBUG_PIO, "scsi%d: residual %d\n", HOSTNO, c);
 
 	*count = c;
 	*data = d;
@@ -1917,7 +1907,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
 	if (atari_read_overruns && (p & SR_IO))
 		c -= atari_read_overruns;
 
-	DMA_PRINTK("scsi%d: initializing DMA for %s, %d bytes %s %p\n",
+	dprintk(NDEBUG_DMA, "scsi%d: initializing DMA for %s, %d bytes %s %p\n",
 		   HOSTNO, (p & SR_IO) ? "reading" : "writing",
 		   c, (p & SR_IO) ? "to" : "from", d);
 
@@ -1997,7 +1987,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 			phase = (tmp & PHASE_MASK);
 			if (phase != old_phase) {
 				old_phase = phase;
-				NCR_PRINT_PHASE(NDEBUG_INFORMATION);
+				NCR5380_dprint_phase(NDEBUG_INFORMATION, instance);
 			}
 
 			if (sink && (phase != PHASE_MSGOUT)) {
@@ -2039,7 +2029,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 					 * they are at contiguous physical addresses.
 					 */
 					merge_contiguous_buffers(cmd);
-					INF_PRINTK("scsi%d: %d bytes and %d buffers left\n",
+					dprintk(NDEBUG_INFORMATION, "scsi%d: %d bytes and %d buffers left\n",
 						   HOSTNO, cmd->SCp.this_residual,
 						   cmd->SCp.buffers_residual);
 				}
@@ -2123,7 +2113,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 					/* Accept message by clearing ACK */
 					NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 
-					LNK_PRINTK("scsi%d: target %d lun %d linked command "
+					dprintk(NDEBUG_LINKED, "scsi%d: target %d lun %d linked command "
 						   "complete.\n", HOSTNO, cmd->device->id, cmd->device->lun);
 
 					/* Enable reselect interrupts */
@@ -2148,7 +2138,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 					 * and don't free it! */
 					cmd->next_link->tag = cmd->tag;
 					cmd->result = cmd->SCp.Status | (cmd->SCp.Message << 8);
-					LNK_PRINTK("scsi%d: target %d lun %d linked request "
+					dprintk(NDEBUG_LINKED, "scsi%d: target %d lun %d linked request "
 						   "done, calling scsi_done().\n",
 						   HOSTNO, cmd->device->id, cmd->device->lun);
 #ifdef NCR5380_STATS
@@ -2165,7 +2155,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 					/* ++guenther: possible race with Falcon locking */
 					falcon_dont_release++;
 					hostdata->connected = NULL;
-					QU_PRINTK("scsi%d: command for target %d, lun %d "
+					dprintk(NDEBUG_QUEUES, "scsi%d: command for target %d, lun %d "
 						  "completed\n", HOSTNO, cmd->device->id, cmd->device->lun);
 #ifdef SUPPORT_TAGS
 					cmd_free_tag(cmd);
@@ -2179,7 +2169,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 						/* ++Andreas: the mid level code knows about
 						   QUEUE_FULL now. */
 						TAG_ALLOC *ta = &TagAlloc[cmd->device->id][cmd->device->lun];
-						TAG_PRINTK("scsi%d: target %d lun %d returned "
+						dprintk(NDEBUG_TAGS, "scsi%d: target %d lun %d returned "
 							   "QUEUE_FULL after %d commands\n",
 							   HOSTNO, cmd->device->id, cmd->device->lun,
 							   ta->nr_allocated);
@@ -2224,14 +2214,14 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 					    (status_byte(cmd->SCp.Status) == CHECK_CONDITION)) {
 						scsi_eh_prep_cmnd(cmd, &hostdata->ses, NULL, 0, ~0);
 
-						ASEN_PRINTK("scsi%d: performing request sense\n", HOSTNO);
+						dprintk(NDEBUG_AUTOSENSE, "scsi%d: performing request sense\n", HOSTNO);
 
 						local_irq_save(flags);
 						LIST(cmd,hostdata->issue_queue);
 						SET_NEXT(cmd, hostdata->issue_queue);
 						hostdata->issue_queue = (Scsi_Cmnd *) cmd;
 						local_irq_restore(flags);
-						QU_PRINTK("scsi%d: REQUEST SENSE added to head of "
+						dprintk(NDEBUG_QUEUES, "scsi%d: REQUEST SENSE added to head of "
 							  "issue queue\n", H_NO(cmd));
 					} else
 #endif /* def AUTOSENSE */
@@ -2277,7 +2267,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 						cmd->device->tagged_supported = 0;
 						hostdata->busy[cmd->device->id] |= (1 << cmd->device->lun);
 						cmd->tag = TAG_NONE;
-						TAG_PRINTK("scsi%d: target %d lun %d rejected "
+						dprintk(NDEBUG_TAGS, "scsi%d: target %d lun %d rejected "
 							   "QUEUE_TAG message; tagged queuing "
 							   "disabled\n",
 							   HOSTNO, cmd->device->id, cmd->device->lun);
@@ -2294,7 +2284,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 					hostdata->connected = NULL;
 					hostdata->disconnected_queue = cmd;
 					local_irq_restore(flags);
-					QU_PRINTK("scsi%d: command for target %d lun %d was "
+					dprintk(NDEBUG_QUEUES, "scsi%d: command for target %d lun %d was "
 						  "moved from connected to the "
 						  "disconnected_queue\n", HOSTNO,
 						  cmd->device->id, cmd->device->lun);
@@ -2344,13 +2334,13 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 					/* Accept first byte by clearing ACK */
 					NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 
-					EXT_PRINTK("scsi%d: receiving extended message\n", HOSTNO);
+					dprintk(NDEBUG_EXTENDED, "scsi%d: receiving extended message\n", HOSTNO);
 
 					len = 2;
 					data = extended_msg + 1;
 					phase = PHASE_MSGIN;
 					NCR5380_transfer_pio(instance, &phase, &len, &data);
-					EXT_PRINTK("scsi%d: length=%d, code=0x%02x\n", HOSTNO,
+					dprintk(NDEBUG_EXTENDED, "scsi%d: length=%d, code=0x%02x\n", HOSTNO,
 						   (int)extended_msg[1], (int)extended_msg[2]);
 
 					if (!len && extended_msg[1] <=
@@ -2362,7 +2352,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 						phase = PHASE_MSGIN;
 
 						NCR5380_transfer_pio(instance, &phase, &len, &data);
-						EXT_PRINTK("scsi%d: message received, residual %d\n",
+						dprintk(NDEBUG_EXTENDED, "scsi%d: message received, residual %d\n",
 							   HOSTNO, len);
 
 						switch (extended_msg[2]) {
@@ -2451,7 +2441,7 @@ static void NCR5380_information_transfer(struct Scsi_Host *instance)
 				break;
 			default:
 				printk("scsi%d: unknown phase\n", HOSTNO);
-				NCR_PRINT(NDEBUG_ANY);
+				NCR5380_dprint(NDEBUG_ANY, instance);
 			} /* switch(phase) */
 		} /* if (tmp * SR_REQ) */
 	} /* while (1) */
@@ -2493,7 +2483,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance)
 
 	target_mask = NCR5380_read(CURRENT_SCSI_DATA_REG) & ~(hostdata->id_mask);
 
-	RSL_PRINTK("scsi%d: reselect\n", HOSTNO);
+	dprintk(NDEBUG_RESELECTION, "scsi%d: reselect\n", HOSTNO);
 
 	/*
 	 * At this point, we have detected that our SCSI ID is on the bus,
@@ -2544,7 +2534,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance)
 		if (!NCR5380_transfer_pio(instance, &phase, &len, &data) &&
 		    msg[1] == SIMPLE_QUEUE_TAG)
 			tag = msg[2];
-		TAG_PRINTK("scsi%d: target mask %02x, lun %d sent tag %d at "
+		dprintk(NDEBUG_TAGS, "scsi%d: target mask %02x, lun %d sent tag %d at "
 			   "reselection\n", HOSTNO, target_mask, lun, tag);
 	}
 #endif
@@ -2598,7 +2588,7 @@ static void NCR5380_reselect(struct Scsi_Host *instance)
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 
 	hostdata->connected = tmp;
-	RSL_PRINTK("scsi%d: nexus established, target = %d, lun = %d, tag = %d\n",
+	dprintk(NDEBUG_RESELECTION, "scsi%d: nexus established, target = %d, lun = %d, tag = %d\n",
 		   HOSTNO, tmp->device->id, tmp->device->lun, tmp->tag);
 	falcon_dont_release--;
 }
@@ -2640,7 +2630,7 @@ int NCR5380_abort(Scsi_Cmnd *cmd)
 		printk(KERN_ERR "scsi%d: !!BINGO!! Falcon has no lock in NCR5380_abort\n",
 		       HOSTNO);
 
-	ABRT_PRINTK("scsi%d: abort called basr 0x%02x, sr 0x%02x\n", HOSTNO,
+	dprintk(NDEBUG_ABORT, "scsi%d: abort called basr 0x%02x, sr 0x%02x\n", HOSTNO,
 		    NCR5380_read(BUS_AND_STATUS_REG),
 		    NCR5380_read(STATUS_REG));
 
@@ -2653,7 +2643,7 @@ int NCR5380_abort(Scsi_Cmnd *cmd)
 
 	if (hostdata->connected == cmd) {
 
-		ABRT_PRINTK("scsi%d: aborting connected command\n", HOSTNO);
+		dprintk(NDEBUG_ABORT, "scsi%d: aborting connected command\n", HOSTNO);
 		/*
 		 * We should perform BSY checking, and make sure we haven't slipped
 		 * into BUS FREE.
@@ -2683,11 +2673,11 @@ int NCR5380_abort(Scsi_Cmnd *cmd)
 			local_irq_restore(flags);
 			cmd->scsi_done(cmd);
 			falcon_release_lock_if_possible(hostdata);
-			return SCSI_ABORT_SUCCESS;
+			return SUCCESS;
 		} else {
 /*			local_irq_restore(flags); */
 			printk("scsi%d: abort of connected command failed!\n", HOSTNO);
-			return SCSI_ABORT_ERROR;
+			return FAILED;
 		}
 	}
 #endif
@@ -2705,13 +2695,13 @@ int NCR5380_abort(Scsi_Cmnd *cmd)
 			SET_NEXT(tmp, NULL);
 			tmp->result = DID_ABORT << 16;
 			local_irq_restore(flags);
-			ABRT_PRINTK("scsi%d: abort removed command from issue queue.\n",
+			dprintk(NDEBUG_ABORT, "scsi%d: abort removed command from issue queue.\n",
 				    HOSTNO);
 			/* Tagged queuing note: no tag to free here, hasn't been assigned
 			 * yet... */
 			tmp->scsi_done(tmp);
 			falcon_release_lock_if_possible(hostdata);
-			return SCSI_ABORT_SUCCESS;
+			return SUCCESS;
 		}
 	}
 
@@ -2728,8 +2718,8 @@ int NCR5380_abort(Scsi_Cmnd *cmd)
 
 	if (hostdata->connected) {
 		local_irq_restore(flags);
-		ABRT_PRINTK("scsi%d: abort failed, command connected.\n", HOSTNO);
-		return SCSI_ABORT_SNOOZE;
+		dprintk(NDEBUG_ABORT, "scsi%d: abort failed, command connected.\n", HOSTNO);
+		return FAILED;
 	}
 
 	/*
@@ -2761,12 +2751,12 @@ int NCR5380_abort(Scsi_Cmnd *cmd)
 	     tmp = NEXT(tmp)) {
 		if (cmd == tmp) {
 			local_irq_restore(flags);
-			ABRT_PRINTK("scsi%d: aborting disconnected command.\n", HOSTNO);
+			dprintk(NDEBUG_ABORT, "scsi%d: aborting disconnected command.\n", HOSTNO);
 
 			if (NCR5380_select(instance, cmd, (int)cmd->tag))
-				return SCSI_ABORT_BUSY;
+				return FAILED;
 
-			ABRT_PRINTK("scsi%d: nexus reestablished.\n", HOSTNO);
+			dprintk(NDEBUG_ABORT, "scsi%d: nexus reestablished.\n", HOSTNO);
 
 			do_abort(instance);
 
@@ -2791,7 +2781,7 @@ int NCR5380_abort(Scsi_Cmnd *cmd)
 					local_irq_restore(flags);
 					tmp->scsi_done(tmp);
 					falcon_release_lock_if_possible(hostdata);
-					return SCSI_ABORT_SUCCESS;
+					return SUCCESS;
 				}
 			}
 		}
@@ -2816,7 +2806,7 @@ int NCR5380_abort(Scsi_Cmnd *cmd)
 	 */
 	falcon_release_lock_if_possible(hostdata);
 
-	return SCSI_ABORT_NOT_RUNNING;
+	return FAILED;
 }
 
 
@@ -2825,7 +2815,7 @@ int NCR5380_abort(Scsi_Cmnd *cmd)
  *
  * Purpose : reset the SCSI bus.
  *
- * Returns : SCSI_RESET_WAKEUP
+ * Returns : SUCCESS or FAILURE
  *
  */
 
@@ -2834,7 +2824,7 @@ static int NCR5380_bus_reset(Scsi_Cmnd *cmd)
 	SETUP_HOSTDATA(cmd->device->host);
 	int i;
 	unsigned long flags;
-#if 1
+#if defined(RESET_RUN_DONE)
 	Scsi_Cmnd *connected, *disconnected_queue;
 #endif
 
@@ -2859,7 +2849,14 @@ static int NCR5380_bus_reset(Scsi_Cmnd *cmd)
 	 * through anymore ... */
 	(void)NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 
-#if 1	/* XXX Should now be done by midlevel code, but it's broken XXX */
+	/* MSch 20140115 - looking at the generic NCR5380 driver, all of this
+	 * should go.
+	 * Catch-22: if we don't clear all queues, the SCSI driver lock will
+	 * not be reset by atari_scsi_reset()!
+	 */
+
+#if defined(RESET_RUN_DONE)
+	/* XXX Should now be done by midlevel code, but it's broken XXX */
 	/* XXX see below                                            XXX */
 
 	/* MSch: old-style reset: actually abort all command processing here */
@@ -2890,7 +2887,7 @@ static int NCR5380_bus_reset(Scsi_Cmnd *cmd)
 	 */
 
 	if ((cmd = connected)) {
-		ABRT_PRINTK("scsi%d: reset aborted a connected command\n", H_NO(cmd));
+		dprintk(NDEBUG_ABORT, "scsi%d: reset aborted a connected command\n", H_NO(cmd));
 		cmd->result = (cmd->result & 0xffff) | (DID_RESET << 16);
 		cmd->scsi_done(cmd);
 	}
@@ -2902,7 +2899,7 @@ static int NCR5380_bus_reset(Scsi_Cmnd *cmd)
 		cmd->scsi_done(cmd);
 	}
 	if (i > 0)
-		ABRT_PRINTK("scsi: reset aborted %d disconnected command(s)\n", i);
+		dprintk(NDEBUG_ABORT, "scsi: reset aborted %d disconnected command(s)\n", i);
 
 	/* The Falcon lock should be released after a reset...
 	 */
@@ -2915,7 +2912,7 @@ static int NCR5380_bus_reset(Scsi_Cmnd *cmd)
 	 * the midlevel code that the reset was SUCCESSFUL, and there is no
 	 * need to 'wake up' the commands by a request_sense
 	 */
-	return SCSI_RESET_SUCCESS | SCSI_RESET_BUS_RESET;
+	return SUCCESS;
 #else /* 1 */
 
 	/* MSch: new-style reset handling: let the mid-level do what it can */
@@ -2942,11 +2939,11 @@ static int NCR5380_bus_reset(Scsi_Cmnd *cmd)
 	 */
 
 	if (hostdata->issue_queue)
-		ABRT_PRINTK("scsi%d: reset aborted issued command(s)\n", H_NO(cmd));
+		dprintk(NDEBUG_ABORT, "scsi%d: reset aborted issued command(s)\n", H_NO(cmd));
 	if (hostdata->connected)
-		ABRT_PRINTK("scsi%d: reset aborted a connected command\n", H_NO(cmd));
+		dprintk(NDEBUG_ABORT, "scsi%d: reset aborted a connected command\n", H_NO(cmd));
 	if (hostdata->disconnected_queue)
-		ABRT_PRINTK("scsi%d: reset aborted disconnected command(s)\n", H_NO(cmd));
+		dprintk(NDEBUG_ABORT, "scsi%d: reset aborted disconnected command(s)\n", H_NO(cmd));
 
 	local_irq_save(flags);
 	hostdata->issue_queue = NULL;
@@ -2963,6 +2960,6 @@ static int NCR5380_bus_reset(Scsi_Cmnd *cmd)
 	local_irq_restore(flags);
 
 	/* we did no complete reset of all commands, so a wakeup is required */
-	return SCSI_RESET_WAKEUP | SCSI_RESET_BUS_RESET;
+	return SUCCESS;
 #endif /* 1 */
 }
diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c
index a8d721ff19e..b522134528d 100644
--- a/drivers/scsi/atari_scsi.c
+++ b/drivers/scsi/atari_scsi.c
@@ -67,12 +67,6 @@
 
 #include <linux/module.h>
 
-#define NDEBUG (0)
-
-#define NDEBUG_ABORT		0x00100000
-#define NDEBUG_TAGS		0x00200000
-#define NDEBUG_MERGING		0x00400000
-
 #define AUTOSENSE
 /* For the Atari version, use only polled IO or REAL_DMA */
 #define	REAL_DMA
@@ -314,7 +308,7 @@ static irqreturn_t scsi_tt_intr(int irq, void *dummy)
 
 	dma_stat = tt_scsi_dma.dma_ctrl;
 
-	INT_PRINTK("scsi%d: NCR5380 interrupt, DMA status = %02x\n",
+	dprintk(NDEBUG_INTR, "scsi%d: NCR5380 interrupt, DMA status = %02x\n",
 		   atari_scsi_host->host_no, dma_stat & 0xff);
 
 	/* Look if it was the DMA that has interrupted: First possibility
@@ -340,7 +334,7 @@ static irqreturn_t scsi_tt_intr(int irq, void *dummy)
 	if ((dma_stat & 0x02) && !(dma_stat & 0x40)) {
 		atari_dma_residual = HOSTDATA_DMALEN - (SCSI_DMA_READ_P(dma_addr) - atari_dma_startaddr);
 
-		DMA_PRINTK("SCSI DMA: There are %ld residual bytes.\n",
+		dprintk(NDEBUG_DMA, "SCSI DMA: There are %ld residual bytes.\n",
 			   atari_dma_residual);
 
 		if ((signed int)atari_dma_residual < 0)
@@ -371,7 +365,7 @@ static irqreturn_t scsi_tt_intr(int irq, void *dummy)
 			 * other command.  These shouldn't disconnect anyway.
 			 */
 			if (atari_dma_residual & 0x1ff) {
-				DMA_PRINTK("SCSI DMA: DMA bug corrected, "
+				dprintk(NDEBUG_DMA, "SCSI DMA: DMA bug corrected, "
 					   "difference %ld bytes\n",
 					   512 - (atari_dma_residual & 0x1ff));
 				atari_dma_residual = (atari_dma_residual + 511) & ~0x1ff;
@@ -438,7 +432,7 @@ static irqreturn_t scsi_falcon_intr(int irq, void *dummy)
 			       "ST-DMA fifo\n", transferred & 15);
 
 		atari_dma_residual = HOSTDATA_DMALEN - transferred;
-		DMA_PRINTK("SCSI DMA: There are %ld residual bytes.\n",
+		dprintk(NDEBUG_DMA, "SCSI DMA: There are %ld residual bytes.\n",
 			   atari_dma_residual);
 	} else
 		atari_dma_residual = 0;
@@ -474,11 +468,11 @@ static void atari_scsi_fetch_restbytes(void)
 		/* there are 'nr' bytes left for the last long address
 		   before the DMA pointer */
 		phys_dst ^= nr;
-		DMA_PRINTK("SCSI DMA: there are %d rest bytes for phys addr 0x%08lx",
+		dprintk(NDEBUG_DMA, "SCSI DMA: there are %d rest bytes for phys addr 0x%08lx",
 			   nr, phys_dst);
 		/* The content of the DMA pointer is a physical address!  */
 		dst = phys_to_virt(phys_dst);
-		DMA_PRINTK(" = virt addr %p\n", dst);
+		dprintk(NDEBUG_DMA, " = virt addr %p\n", dst);
 		for (src = (char *)&tt_scsi_dma.dma_restdata; nr != 0; --nr)
 			*dst++ = *src++;
 	}
@@ -827,7 +821,7 @@ static int atari_scsi_bus_reset(Scsi_Cmnd *cmd)
 	} else {
 		atari_turnon_irq(IRQ_MFP_FSCSI);
 	}
-	if ((rv & SCSI_RESET_ACTION) == SCSI_RESET_SUCCESS)
+	if (rv == SUCCESS)
 		falcon_release_lock_if_possible(hostdata);
 
 	return rv;
@@ -883,7 +877,7 @@ static unsigned long atari_scsi_dma_setup(struct Scsi_Host *instance,
 {
 	unsigned long addr = virt_to_phys(data);
 
-	DMA_PRINTK("scsi%d: setting up dma, data = %p, phys = %lx, count = %ld, "
+	dprintk(NDEBUG_DMA, "scsi%d: setting up dma, data = %p, phys = %lx, count = %ld, "
 		   "dir = %d\n", instance->host_no, data, addr, count, dir);
 
 	if (!IS_A_TT() && !STRAM_ADDR(addr)) {
@@ -1063,7 +1057,7 @@ static unsigned long atari_dma_xfer_len(unsigned long wanted_len,
 		possible_len = limit;
 
 	if (possible_len != wanted_len)
-		DMA_PRINTK("Sorry, must cut DMA transfer size to %ld bytes "
+		dprintk(NDEBUG_DMA, "Sorry, must cut DMA transfer size to %ld bytes "
 			   "instead of %ld\n", possible_len, wanted_len);
 
 	return possible_len;
diff --git a/drivers/scsi/atari_scsi.h b/drivers/scsi/atari_scsi.h
index 11c624bb122..3299d91d733 100644
--- a/drivers/scsi/atari_scsi.h
+++ b/drivers/scsi/atari_scsi.h
@@ -54,125 +54,6 @@
 #define	NCR5380_dma_xfer_len(i,cmd,phase) \
 	atari_dma_xfer_len(cmd->SCp.this_residual,cmd,((phase) & SR_IO) ? 0 : 1)
 
-/* former generic SCSI error handling stuff */
-
-#define SCSI_ABORT_SNOOZE 0
-#define SCSI_ABORT_SUCCESS 1
-#define SCSI_ABORT_PENDING 2
-#define SCSI_ABORT_BUSY 3
-#define SCSI_ABORT_NOT_RUNNING 4
-#define SCSI_ABORT_ERROR 5
-
-#define SCSI_RESET_SNOOZE 0
-#define SCSI_RESET_PUNT 1
-#define SCSI_RESET_SUCCESS 2
-#define SCSI_RESET_PENDING 3
-#define SCSI_RESET_WAKEUP 4
-#define SCSI_RESET_NOT_RUNNING 5
-#define SCSI_RESET_ERROR 6
-
-#define SCSI_RESET_SYNCHRONOUS		0x01
-#define SCSI_RESET_ASYNCHRONOUS		0x02
-#define SCSI_RESET_SUGGEST_BUS_RESET	0x04
-#define SCSI_RESET_SUGGEST_HOST_RESET	0x08
-
-#define SCSI_RESET_BUS_RESET 0x100
-#define SCSI_RESET_HOST_RESET 0x200
-#define SCSI_RESET_ACTION   0xff
-
-/* Debugging printk definitions:
- *
- *  ARB  -> arbitration
- *  ASEN -> auto-sense
- *  DMA  -> DMA
- *  HSH  -> PIO handshake
- *  INF  -> information transfer
- *  INI  -> initialization
- *  INT  -> interrupt
- *  LNK  -> linked commands
- *  MAIN -> NCR5380_main() control flow
- *  NDAT -> no data-out phase
- *  NWR  -> no write commands
- *  PIO  -> PIO transfers
- *  PDMA -> pseudo DMA (unused on Atari)
- *  QU   -> queues
- *  RSL  -> reselections
- *  SEL  -> selections
- *  USL  -> usleep cpde (unused on Atari)
- *  LBS  -> last byte sent (unused on Atari)
- *  RSS  -> restarting of selections
- *  EXT  -> extended messages
- *  ABRT -> aborting and resetting
- *  TAG  -> queue tag handling
- *  MER  -> merging of consec. buffers
- *
- */
-
-#define dprint(flg, format...)			\
-({						\
-	if (NDEBUG & (flg))			\
-		printk(KERN_DEBUG format);	\
-})
-
-#define ARB_PRINTK(format, args...) \
-	dprint(NDEBUG_ARBITRATION, format , ## args)
-#define ASEN_PRINTK(format, args...) \
-	dprint(NDEBUG_AUTOSENSE, format , ## args)
-#define DMA_PRINTK(format, args...) \
-	dprint(NDEBUG_DMA, format , ## args)
-#define HSH_PRINTK(format, args...) \
-	dprint(NDEBUG_HANDSHAKE, format , ## args)
-#define INF_PRINTK(format, args...) \
-	dprint(NDEBUG_INFORMATION, format , ## args)
-#define INI_PRINTK(format, args...) \
-	dprint(NDEBUG_INIT, format , ## args)
-#define INT_PRINTK(format, args...) \
-	dprint(NDEBUG_INTR, format , ## args)
-#define LNK_PRINTK(format, args...) \
-	dprint(NDEBUG_LINKED, format , ## args)
-#define MAIN_PRINTK(format, args...) \
-	dprint(NDEBUG_MAIN, format , ## args)
-#define NDAT_PRINTK(format, args...) \
-	dprint(NDEBUG_NO_DATAOUT, format , ## args)
-#define NWR_PRINTK(format, args...) \
-	dprint(NDEBUG_NO_WRITE, format , ## args)
-#define PIO_PRINTK(format, args...) \
-	dprint(NDEBUG_PIO, format , ## args)
-#define PDMA_PRINTK(format, args...) \
-	dprint(NDEBUG_PSEUDO_DMA, format , ## args)
-#define QU_PRINTK(format, args...) \
-	dprint(NDEBUG_QUEUES, format , ## args)
-#define RSL_PRINTK(format, args...) \
-	dprint(NDEBUG_RESELECTION, format , ## args)
-#define SEL_PRINTK(format, args...) \
-	dprint(NDEBUG_SELECTION, format , ## args)
-#define USL_PRINTK(format, args...) \
-	dprint(NDEBUG_USLEEP, format , ## args)
-#define LBS_PRINTK(format, args...) \
-	dprint(NDEBUG_LAST_BYTE_SENT, format , ## args)
-#define RSS_PRINTK(format, args...) \
-	dprint(NDEBUG_RESTART_SELECT, format , ## args)
-#define EXT_PRINTK(format, args...) \
-	dprint(NDEBUG_EXTENDED, format , ## args)
-#define ABRT_PRINTK(format, args...) \
-	dprint(NDEBUG_ABORT, format , ## args)
-#define TAG_PRINTK(format, args...) \
-	dprint(NDEBUG_TAGS, format , ## args)
-#define MER_PRINTK(format, args...) \
-	dprint(NDEBUG_MERGING, format , ## args)
-
-/* conditional macros for NCR5380_print_{,phase,status} */
-
-#define NCR_PRINT(mask)	\
-	((NDEBUG & (mask)) ? NCR5380_print(instance) : (void)0)
-
-#define NCR_PRINT_PHASE(mask) \
-	((NDEBUG & (mask)) ? NCR5380_print_phase(instance) : (void)0)
-
-#define NCR_PRINT_STATUS(mask) \
-	((NDEBUG & (mask)) ? NCR5380_print_status(instance) : (void)0)
-
-
 #endif /* ndef ASM */
 #endif /* ATARI_SCSI_H */
 
diff --git a/drivers/scsi/be2iscsi/be.h b/drivers/scsi/be2iscsi/be.h
index 1bfb0bd0119..860f527d8f2 100644
--- a/drivers/scsi/be2iscsi/be.h
+++ b/drivers/scsi/be2iscsi/be.h
@@ -83,9 +83,20 @@ static inline void queue_tail_inc(struct be_queue_info *q)
 
 /*ISCSI */
 
+struct be_aic_obj {		/* Adaptive interrupt coalescing (AIC) info */
+	bool enable;
+	u32 min_eqd;		/* in usecs */
+	u32 max_eqd;		/* in usecs */
+	u32 prev_eqd;		/* in usecs */
+	u32 et_eqd;		/* configured val when aic is off */
+	ulong jiffs;
+	u64 eq_prev;		/* Used to calculate eqe */
+};
+
 struct be_eq_obj {
 	bool todo_mcc_cq;
 	bool todo_cq;
+	u32 cq_count;
 	struct be_queue_info q;
 	struct beiscsi_hba *phba;
 	struct be_queue_info *cq;
diff --git a/drivers/scsi/be2iscsi/be_cmds.h b/drivers/scsi/be2iscsi/be_cmds.h
index 7cf7f99ee44..cc7405c0eca 100644
--- a/drivers/scsi/be2iscsi/be_cmds.h
+++ b/drivers/scsi/be2iscsi/be_cmds.h
@@ -71,6 +71,7 @@ struct be_mcc_wrb {
 #define BEISCSI_FW_MBX_TIMEOUT	100
 
 /* MBOX Command VER */
+#define MBX_CMD_VER1	0x01
 #define MBX_CMD_VER2	0x02
 
 struct be_mcc_compl {
@@ -271,6 +272,12 @@ struct be_cmd_resp_eq_create {
 	u16 rsvd0;		/* sword */
 } __packed;
 
+struct be_set_eqd {
+	u32 eq_id;
+	u32 phase;
+	u32 delay_multiplier;
+} __packed;
+
 struct mgmt_chap_format {
 	u32 flags;
 	u8  intr_chap_name[256];
@@ -622,7 +629,7 @@ struct be_cmd_req_modify_eq_delay {
 		u32 eq_id;
 		u32 phase;
 		u32 delay_multiplier;
-	} delay[8];
+	} delay[MAX_CPUS];
 } __packed;
 
 /******************** Get MAC ADDR *******************/
@@ -708,6 +715,8 @@ unsigned int be_cmd_get_port_speed(struct beiscsi_hba *phba);
 
 void free_mcc_tag(struct be_ctrl_info *ctrl, unsigned int tag);
 
+int be_cmd_modify_eq_delay(struct beiscsi_hba *phba, struct be_set_eqd *,
+			    int num);
 int beiscsi_mccq_compl(struct beiscsi_hba *phba,
 			uint32_t tag, struct be_mcc_wrb **wrb,
 			struct be_dma_mem *mbx_cmd_mem);
@@ -1005,6 +1014,26 @@ struct tcp_connect_and_offload_in {
 	u8 rsvd0[3];
 } __packed;
 
+struct tcp_connect_and_offload_in_v1 {
+	struct be_cmd_req_hdr hdr;
+	struct ip_addr_format ip_address;
+	u16 tcp_port;
+	u16 cid;
+	u16 cq_id;
+	u16 defq_id;
+	struct phys_addr dataout_template_pa;
+	u16 hdr_ring_id;
+	u16 data_ring_id;
+	u8 do_offload;
+	u8 ifd_state;
+	u8 rsvd0[2];
+	u16 tcp_window_size;
+	u8 tcp_window_scale_count;
+	u8 rsvd1;
+	u32 tcp_mss:24;
+	u8 rsvd2;
+} __packed;
+
 struct tcp_connect_and_offload_out {
 	struct be_cmd_resp_hdr hdr;
 	u32 connection_handle;
diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c
index a3df43324c9..fd284ff36ec 100644
--- a/drivers/scsi/be2iscsi/be_iscsi.c
+++ b/drivers/scsi/be2iscsi/be_iscsi.c
@@ -1106,7 +1106,7 @@ static int beiscsi_open_conn(struct iscsi_endpoint *ep,
 	struct beiscsi_hba *phba = beiscsi_ep->phba;
 	struct tcp_connect_and_offload_out *ptcpcnct_out;
 	struct be_dma_mem nonemb_cmd;
-	unsigned int tag;
+	unsigned int tag, req_memsize;
 	int ret = -ENOMEM;
 
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
@@ -1127,8 +1127,14 @@ static int beiscsi_open_conn(struct iscsi_endpoint *ep,
 		       (beiscsi_ep->ep_cid)] = ep;
 
 	beiscsi_ep->cid_vld = 0;
+
+	if (is_chip_be2_be3r(phba))
+		req_memsize = sizeof(struct tcp_connect_and_offload_in);
+	else
+		req_memsize = sizeof(struct tcp_connect_and_offload_in_v1);
+
 	nonemb_cmd.va = pci_alloc_consistent(phba->ctrl.pdev,
-				sizeof(struct tcp_connect_and_offload_in),
+				req_memsize,
 				&nonemb_cmd.dma);
 	if (nonemb_cmd.va == NULL) {
 
@@ -1139,7 +1145,7 @@ static int beiscsi_open_conn(struct iscsi_endpoint *ep,
 		beiscsi_free_ep(beiscsi_ep);
 		return -ENOMEM;
 	}
-	nonemb_cmd.size = sizeof(struct tcp_connect_and_offload_in);
+	nonemb_cmd.size = req_memsize;
 	memset(nonemb_cmd.va, 0, nonemb_cmd.size);
 	tag = mgmt_open_connection(phba, dst_addr, beiscsi_ep, &nonemb_cmd);
 	if (tag <= 0) {
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 0d822297aa8..56467df3d6d 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -599,15 +599,7 @@ static struct beiscsi_hba *beiscsi_hba_alloc(struct pci_dev *pcidev)
 	pci_set_drvdata(pcidev, phba);
 	phba->interface_handle = 0xFFFFFFFF;
 
-	if (iscsi_host_add(shost, &phba->pcidev->dev))
-		goto free_devices;
-
 	return phba;
-
-free_devices:
-	pci_dev_put(phba->pcidev);
-	iscsi_host_free(phba->shost);
-	return NULL;
 }
 
 static void beiscsi_unmap_pci_function(struct beiscsi_hba *phba)
@@ -2279,6 +2271,7 @@ static int be_iopoll(struct blk_iopoll *iop, int budget)
 
 	pbe_eq = container_of(iop, struct be_eq_obj, iopoll);
 	ret = beiscsi_process_cq(pbe_eq);
+	pbe_eq->cq_count += ret;
 	if (ret < budget) {
 		phba = pbe_eq->phba;
 		blk_iopoll_complete(iop);
@@ -3692,7 +3685,7 @@ static void hwi_cleanup(struct beiscsi_hba *phba)
 	struct hwi_controller *phwi_ctrlr;
 	struct hwi_context_memory *phwi_context;
 	struct hwi_async_pdu_context *pasync_ctx;
-	int i, eq_num, ulp_num;
+	int i, eq_for_mcc, ulp_num;
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 	phwi_context = phwi_ctrlr->phwi_ctxt;
@@ -3729,16 +3722,17 @@ static void hwi_cleanup(struct beiscsi_hba *phba)
 		if (q->created)
 			beiscsi_cmd_q_destroy(ctrl, q, QTYPE_CQ);
 	}
+
+	be_mcc_queues_destroy(phba);
 	if (phba->msix_enabled)
-		eq_num = 1;
+		eq_for_mcc = 1;
 	else
-		eq_num = 0;
-	for (i = 0; i < (phba->num_cpus + eq_num); i++) {
+		eq_for_mcc = 0;
+	for (i = 0; i < (phba->num_cpus + eq_for_mcc); i++) {
 		q = &phwi_context->be_eq[i].q;
 		if (q->created)
 			beiscsi_cmd_q_destroy(ctrl, q, QTYPE_EQ);
 	}
-	be_mcc_queues_destroy(phba);
 	be_cmd_fw_uninit(ctrl);
 }
 
@@ -3833,9 +3827,9 @@ static int hwi_init_port(struct beiscsi_hba *phba)
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 	phwi_context = phwi_ctrlr->phwi_ctxt;
-	phwi_context->max_eqd = 0;
+	phwi_context->max_eqd = 128;
 	phwi_context->min_eqd = 0;
-	phwi_context->cur_eqd = 64;
+	phwi_context->cur_eqd = 0;
 	be_cmd_fw_initialize(&phba->ctrl);
 
 	status = beiscsi_create_eqs(phba, phwi_context);
@@ -4204,6 +4198,8 @@ static int hba_setup_cid_tbls(struct beiscsi_hba *phba)
 		kfree(phba->ep_array);
 		phba->ep_array = NULL;
 		ret = -ENOMEM;
+
+		goto free_memory;
 	}
 
 	for (i = 0; i < phba->params.cxns_per_ctrl; i++) {
@@ -5290,6 +5286,57 @@ static void beiscsi_msix_enable(struct beiscsi_hba *phba)
 	return;
 }
 
+static void be_eqd_update(struct beiscsi_hba *phba)
+{
+	struct be_set_eqd set_eqd[MAX_CPUS];
+	struct be_aic_obj *aic;
+	struct be_eq_obj *pbe_eq;
+	struct hwi_controller *phwi_ctrlr;
+	struct hwi_context_memory *phwi_context;
+	int eqd, i, num = 0;
+	ulong now;
+	u32 pps, delta;
+	unsigned int tag;
+
+	phwi_ctrlr = phba->phwi_ctrlr;
+	phwi_context = phwi_ctrlr->phwi_ctxt;
+
+	for (i = 0; i <= phba->num_cpus; i++) {
+		aic = &phba->aic_obj[i];
+		pbe_eq = &phwi_context->be_eq[i];
+		now = jiffies;
+		if (!aic->jiffs || time_before(now, aic->jiffs) ||
+		    pbe_eq->cq_count < aic->eq_prev) {
+			aic->jiffs = now;
+			aic->eq_prev = pbe_eq->cq_count;
+			continue;
+		}
+		delta = jiffies_to_msecs(now - aic->jiffs);
+		pps = (((u32)(pbe_eq->cq_count - aic->eq_prev) * 1000) / delta);
+		eqd = (pps / 1500) << 2;
+
+		if (eqd < 8)
+			eqd = 0;
+		eqd = min_t(u32, eqd, phwi_context->max_eqd);
+		eqd = max_t(u32, eqd, phwi_context->min_eqd);
+
+		aic->jiffs = now;
+		aic->eq_prev = pbe_eq->cq_count;
+
+		if (eqd != aic->prev_eqd) {
+			set_eqd[num].delay_multiplier = (eqd * 65)/100;
+			set_eqd[num].eq_id = pbe_eq->q.id;
+			aic->prev_eqd = eqd;
+			num++;
+		}
+	}
+	if (num) {
+		tag = be_cmd_modify_eq_delay(phba, set_eqd, num);
+		if (tag)
+			beiscsi_mccq_compl(phba, tag, NULL, NULL);
+	}
+}
+
 /*
  * beiscsi_hw_health_check()- Check adapter health
  * @work: work item to check HW health
@@ -5303,6 +5350,8 @@ beiscsi_hw_health_check(struct work_struct *work)
 		container_of(work, struct beiscsi_hba,
 			     beiscsi_hw_check_task.work);
 
+	be_eqd_update(phba);
+
 	beiscsi_ue_detect(phba);
 
 	schedule_delayed_work(&phba->beiscsi_hw_check_task,
@@ -5579,7 +5628,7 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 		phba->ctrl.mcc_numtag[i + 1] = 0;
 		phba->ctrl.mcc_tag_available++;
 		memset(&phba->ctrl.ptag_state[i].tag_mem_state, 0,
-		       sizeof(struct beiscsi_mcc_tag_state));
+		       sizeof(struct be_dma_mem));
 	}
 
 	phba->ctrl.mcc_alloc_index = phba->ctrl.mcc_free_index = 0;
@@ -5621,6 +5670,9 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 	}
 	hwi_enable_intr(phba);
 
+	if (iscsi_host_add(phba->shost, &phba->pcidev->dev))
+		goto free_blkenbld;
+
 	if (beiscsi_setup_boot_info(phba))
 		/*
 		 * log error but continue, because we may not be using
diff --git a/drivers/scsi/be2iscsi/be_main.h b/drivers/scsi/be2iscsi/be_main.h
index 9380b55bdea..9ceab426eec 100644
--- a/drivers/scsi/be2iscsi/be_main.h
+++ b/drivers/scsi/be2iscsi/be_main.h
@@ -36,7 +36,7 @@
 #include <scsi/scsi_transport_iscsi.h>
 
 #define DRV_NAME		"be2iscsi"
-#define BUILD_STR		"10.2.125.0"
+#define BUILD_STR		"10.2.273.0"
 #define BE_NAME			"Emulex OneConnect" \
 				"Open-iSCSI Driver version" BUILD_STR
 #define DRV_DESC		BE_NAME " " "Driver"
@@ -71,8 +71,8 @@
 
 #define BEISCSI_SGLIST_ELEMENTS	30
 
-#define BEISCSI_CMD_PER_LUN	128	/* scsi_host->cmd_per_lun */
-#define BEISCSI_MAX_SECTORS	2048	/* scsi_host->max_sectors */
+#define BEISCSI_CMD_PER_LUN	128 /* scsi_host->cmd_per_lun */
+#define BEISCSI_MAX_SECTORS	1024 /* scsi_host->max_sectors */
 #define BEISCSI_TEMPLATE_HDR_PER_CXN_SIZE 128 /* Template size per cxn */
 
 #define BEISCSI_MAX_CMD_LEN	16	/* scsi_host->max_cmd_len */
@@ -427,6 +427,7 @@ struct beiscsi_hba {
 	struct mgmt_session_info boot_sess;
 	struct invalidate_command_table inv_tbl[128];
 
+	struct be_aic_obj aic_obj[MAX_CPUS];
 	unsigned int attr_log_enable;
 	int (*iotask_fn)(struct iscsi_task *,
 			struct scatterlist *sg,
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index 088bdf752cf..07934b0b9ee 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -155,6 +155,43 @@ void beiscsi_ue_detect(struct beiscsi_hba *phba)
 	}
 }
 
+int be_cmd_modify_eq_delay(struct beiscsi_hba *phba,
+		 struct be_set_eqd *set_eqd, int num)
+{
+	struct be_ctrl_info *ctrl = &phba->ctrl;
+	struct be_mcc_wrb *wrb;
+	struct be_cmd_req_modify_eq_delay *req;
+	unsigned int tag = 0;
+	int i;
+
+	spin_lock(&ctrl->mbox_lock);
+	tag = alloc_mcc_tag(phba);
+	if (!tag) {
+		spin_unlock(&ctrl->mbox_lock);
+		return tag;
+	}
+
+	wrb = wrb_from_mccq(phba);
+	req = embedded_payload(wrb);
+
+	wrb->tag0 |= tag;
+	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
+	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+		OPCODE_COMMON_MODIFY_EQ_DELAY, sizeof(*req));
+
+	req->num_eq = cpu_to_le32(num);
+	for (i = 0; i < num; i++) {
+		req->delay[i].eq_id = cpu_to_le32(set_eqd[i].eq_id);
+		req->delay[i].phase = 0;
+		req->delay[i].delay_multiplier =
+				cpu_to_le32(set_eqd[i].delay_multiplier);
+	}
+
+	be_mcc_notify(phba);
+	spin_unlock(&ctrl->mbox_lock);
+	return tag;
+}
+
 /**
  * mgmt_reopen_session()- Reopen a session based on reopen_type
  * @phba: Device priv structure instance
@@ -447,8 +484,8 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 					 struct be_dma_mem *nonemb_cmd)
 {
 	struct be_cmd_resp_hdr *resp;
-	struct be_mcc_wrb *wrb = wrb_from_mccq(phba);
-	struct be_sge *mcc_sge = nonembedded_sgl(wrb);
+	struct be_mcc_wrb *wrb;
+	struct be_sge *mcc_sge;
 	unsigned int tag = 0;
 	struct iscsi_bsg_request *bsg_req = job->request;
 	struct be_bsg_vendor_cmd *req = nonemb_cmd->va;
@@ -465,7 +502,6 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 	req->sector = sector;
 	req->offset = offset;
 	spin_lock(&ctrl->mbox_lock);
-	memset(wrb, 0, sizeof(*wrb));
 
 	switch (bsg_req->rqst_data.h_vendor.vendor_cmd[0]) {
 	case BEISCSI_WRITE_FLASH:
@@ -495,6 +531,8 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 		return tag;
 	}
 
+	wrb = wrb_from_mccq(phba);
+	mcc_sge = nonembedded_sgl(wrb);
 	be_wrb_hdr_prepare(wrb, nonemb_cmd->size, false,
 			   job->request_payload.sg_cnt);
 	mcc_sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd->dma));
@@ -525,7 +563,6 @@ int mgmt_epfw_cleanup(struct beiscsi_hba *phba, unsigned short ulp_num)
 	int status = 0;
 
 	spin_lock(&ctrl->mbox_lock);
-	memset(wrb, 0, sizeof(*wrb));
 
 	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
@@ -675,7 +712,7 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 	struct sockaddr_in6 *daddr_in6 = (struct sockaddr_in6 *)dst_addr;
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct be_mcc_wrb *wrb;
-	struct tcp_connect_and_offload_in *req;
+	struct tcp_connect_and_offload_in_v1 *req;
 	unsigned short def_hdr_id;
 	unsigned short def_data_id;
 	struct phys_addr template_address = { 0, 0 };
@@ -702,17 +739,16 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 		return tag;
 	}
 	wrb = wrb_from_mccq(phba);
-	memset(wrb, 0, sizeof(*wrb));
 	sge = nonembedded_sgl(wrb);
 
 	req = nonemb_cmd->va;
 	memset(req, 0, sizeof(*req));
 	wrb->tag0 |= tag;
 
-	be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1);
+	be_wrb_hdr_prepare(wrb, nonemb_cmd->size, false, 1);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
 			   OPCODE_COMMON_ISCSI_TCP_CONNECT_AND_OFFLOAD,
-			   sizeof(*req));
+			   nonemb_cmd->size);
 	if (dst_addr->sa_family == PF_INET) {
 		__be32 s_addr = daddr_in->sin_addr.s_addr;
 		req->ip_address.ip_type = BE2_IPV4;
@@ -758,6 +794,13 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 	sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd->dma));
 	sge->pa_lo = cpu_to_le32(nonemb_cmd->dma & 0xFFFFFFFF);
 	sge->len = cpu_to_le32(nonemb_cmd->size);
+
+	if (!is_chip_be2_be3r(phba)) {
+		req->hdr.version = MBX_CMD_VER1;
+		req->tcp_window_size = 0;
+		req->tcp_window_scale_count = 2;
+	}
+
 	be_mcc_notify(phba);
 	spin_unlock(&ctrl->mbox_lock);
 	return tag;
@@ -804,7 +847,7 @@ static int mgmt_exec_nonemb_cmd(struct beiscsi_hba *phba,
 				int resp_buf_len)
 {
 	struct be_ctrl_info *ctrl = &phba->ctrl;
-	struct be_mcc_wrb *wrb = wrb_from_mccq(phba);
+	struct be_mcc_wrb *wrb;
 	struct be_sge *sge;
 	unsigned int tag;
 	int rc = 0;
@@ -816,7 +859,8 @@ static int mgmt_exec_nonemb_cmd(struct beiscsi_hba *phba,
 		rc = -ENOMEM;
 		goto free_cmd;
 	}
-	memset(wrb, 0, sizeof(*wrb));
+
+	wrb = wrb_from_mccq(phba);
 	wrb->tag0 |= tag;
 	sge = nonembedded_sgl(wrb);
 
@@ -964,10 +1008,8 @@ int mgmt_set_ip(struct beiscsi_hba *phba,
 		BE2_IPV6 : BE2_IPV4 ;
 
 	rc = mgmt_get_if_info(phba, ip_type, &if_info);
-	if (rc) {
-		kfree(if_info);
+	if (rc)
 		return rc;
-	}
 
 	if (boot_proto == ISCSI_BOOTPROTO_DHCP) {
 		if (if_info->dhcp_state) {
diff --git a/drivers/scsi/be2iscsi/be_mgmt.h b/drivers/scsi/be2iscsi/be_mgmt.h
index 01b8c97284c..24a8fc57747 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.h
+++ b/drivers/scsi/be2iscsi/be_mgmt.h
@@ -335,5 +335,7 @@ void beiscsi_offload_cxn_v0(struct beiscsi_offload_params *params,
 void beiscsi_offload_cxn_v2(struct beiscsi_offload_params *params,
 			     struct wrb_handle *pwrb_handle);
 void beiscsi_ue_detect(struct beiscsi_hba *phba);
+int be_cmd_modify_eq_delay(struct beiscsi_hba *phba,
+			 struct be_set_eqd *, int num);
 
 #endif
diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c
index cc0fbcdc519..7593b7c1d33 100644
--- a/drivers/scsi/bfa/bfad.c
+++ b/drivers/scsi/bfa/bfad.c
@@ -507,7 +507,7 @@ bfa_fcb_pbc_vport_create(struct bfad_s *bfad, struct bfi_pbc_vport_s pbc_vport)
 	struct bfad_vport_s   *vport;
 	int rc;
 
-	vport = kzalloc(sizeof(struct bfad_vport_s), GFP_KERNEL);
+	vport = kzalloc(sizeof(struct bfad_vport_s), GFP_ATOMIC);
 	if (!vport) {
 		bfa_trc(bfad, 0);
 		return;
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index f5484302346..785d0d71781 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -516,23 +516,17 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 	skb_pull(skb, sizeof(struct fcoe_hdr));
 	fr_len = skb->len - sizeof(struct fcoe_crc_eof);
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
-	stats->RxFrames++;
-	stats->RxWords += fr_len / FCOE_WORD_TO_BYTE;
-
 	fp = (struct fc_frame *)skb;
 	fc_frame_init(fp);
 	fr_dev(fp) = lport;
 	fr_sof(fp) = hp->fcoe_sof;
 	if (skb_copy_bits(skb, fr_len, &crc_eof, sizeof(crc_eof))) {
-		put_cpu();
 		kfree_skb(skb);
 		return;
 	}
 	fr_eof(fp) = crc_eof.fcoe_eof;
 	fr_crc(fp) = crc_eof.fcoe_crc32;
 	if (pskb_trim(skb, fr_len)) {
-		put_cpu();
 		kfree_skb(skb);
 		return;
 	}
@@ -544,7 +538,6 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 		port = lport_priv(vn_port);
 		if (!ether_addr_equal(port->data_src_addr, dest_mac)) {
 			BNX2FC_HBA_DBG(lport, "fpma mismatch\n");
-			put_cpu();
 			kfree_skb(skb);
 			return;
 		}
@@ -552,7 +545,6 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 	if (fh->fh_r_ctl == FC_RCTL_DD_SOL_DATA &&
 	    fh->fh_type == FC_TYPE_FCP) {
 		/* Drop FCP data. We dont this in L2 path */
-		put_cpu();
 		kfree_skb(skb);
 		return;
 	}
@@ -562,7 +554,6 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 		case ELS_LOGO:
 			if (ntoh24(fh->fh_s_id) == FC_FID_FLOGI) {
 				/* drop non-FIP LOGO */
-				put_cpu();
 				kfree_skb(skb);
 				return;
 			}
@@ -572,22 +563,23 @@ static void bnx2fc_recv_frame(struct sk_buff *skb)
 
 	if (fh->fh_r_ctl == FC_RCTL_BA_ABTS) {
 		/* Drop incoming ABTS */
-		put_cpu();
 		kfree_skb(skb);
 		return;
 	}
 
+	stats = per_cpu_ptr(lport->stats, smp_processor_id());
+	stats->RxFrames++;
+	stats->RxWords += fr_len / FCOE_WORD_TO_BYTE;
+
 	if (le32_to_cpu(fr_crc(fp)) !=
 			~crc32(~0, skb->data, fr_len)) {
 		if (stats->InvalidCRCCount < 5)
 			printk(KERN_WARNING PFX "dropping frame with "
 			       "CRC error\n");
 		stats->InvalidCRCCount++;
-		put_cpu();
 		kfree_skb(skb);
 		return;
 	}
-	put_cpu();
 	fc_exch_recv(lport, fp);
 }
 
diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
index 46a37657307..512aed3ae4f 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
@@ -1966,26 +1966,29 @@ static void bnx2fc_free_hash_table(struct bnx2fc_hba *hba)
 {
 	int i;
 	int segment_count;
-	int hash_table_size;
 	u32 *pbl;
 
-	segment_count = hba->hash_tbl_segment_count;
-	hash_table_size = BNX2FC_NUM_MAX_SESS * BNX2FC_MAX_ROWS_IN_HASH_TBL *
-		sizeof(struct fcoe_hash_table_entry);
+	if (hba->hash_tbl_segments) {
 
-	pbl = hba->hash_tbl_pbl;
-	for (i = 0; i < segment_count; ++i) {
-		dma_addr_t dma_address;
+		pbl = hba->hash_tbl_pbl;
+		if (pbl) {
+			segment_count = hba->hash_tbl_segment_count;
+			for (i = 0; i < segment_count; ++i) {
+				dma_addr_t dma_address;
 
-		dma_address = le32_to_cpu(*pbl);
-		++pbl;
-		dma_address += ((u64)le32_to_cpu(*pbl)) << 32;
-		++pbl;
-		dma_free_coherent(&hba->pcidev->dev,
-				  BNX2FC_HASH_TBL_CHUNK_SIZE,
-				  hba->hash_tbl_segments[i],
-				  dma_address);
+				dma_address = le32_to_cpu(*pbl);
+				++pbl;
+				dma_address += ((u64)le32_to_cpu(*pbl)) << 32;
+				++pbl;
+				dma_free_coherent(&hba->pcidev->dev,
+						  BNX2FC_HASH_TBL_CHUNK_SIZE,
+						  hba->hash_tbl_segments[i],
+						  dma_address);
+			}
+		}
 
+		kfree(hba->hash_tbl_segments);
+		hba->hash_tbl_segments = NULL;
 	}
 
 	if (hba->hash_tbl_pbl) {
@@ -2023,7 +2026,7 @@ static int bnx2fc_allocate_hash_table(struct bnx2fc_hba *hba)
 	dma_segment_array = kzalloc(dma_segment_array_size, GFP_KERNEL);
 	if (!dma_segment_array) {
 		printk(KERN_ERR PFX "hash table pointers (dma) alloc failed\n");
-		return -ENOMEM;
+		goto cleanup_ht;
 	}
 
 	for (i = 0; i < segment_count; ++i) {
@@ -2034,15 +2037,7 @@ static int bnx2fc_allocate_hash_table(struct bnx2fc_hba *hba)
 					   GFP_KERNEL);
 		if (!hba->hash_tbl_segments[i]) {
 			printk(KERN_ERR PFX "hash segment alloc failed\n");
-			while (--i >= 0) {
-				dma_free_coherent(&hba->pcidev->dev,
-						    BNX2FC_HASH_TBL_CHUNK_SIZE,
-						    hba->hash_tbl_segments[i],
-						    dma_segment_array[i]);
-				hba->hash_tbl_segments[i] = NULL;
-			}
-			kfree(dma_segment_array);
-			return -ENOMEM;
+			goto cleanup_dma;
 		}
 		memset(hba->hash_tbl_segments[i], 0,
 		       BNX2FC_HASH_TBL_CHUNK_SIZE);
@@ -2054,8 +2049,7 @@ static int bnx2fc_allocate_hash_table(struct bnx2fc_hba *hba)
 					       GFP_KERNEL);
 	if (!hba->hash_tbl_pbl) {
 		printk(KERN_ERR PFX "hash table pbl alloc failed\n");
-		kfree(dma_segment_array);
-		return -ENOMEM;
+		goto cleanup_dma;
 	}
 	memset(hba->hash_tbl_pbl, 0, PAGE_SIZE);
 
@@ -2080,6 +2074,22 @@ static int bnx2fc_allocate_hash_table(struct bnx2fc_hba *hba)
 	}
 	kfree(dma_segment_array);
 	return 0;
+
+cleanup_dma:
+	for (i = 0; i < segment_count; ++i) {
+		if (hba->hash_tbl_segments[i])
+			dma_free_coherent(&hba->pcidev->dev,
+					    BNX2FC_HASH_TBL_CHUNK_SIZE,
+					    hba->hash_tbl_segments[i],
+					    dma_segment_array[i]);
+	}
+
+	kfree(dma_segment_array);
+
+cleanup_ht:
+	kfree(hba->hash_tbl_segments);
+	hba->hash_tbl_segments = NULL;
+	return -ENOMEM;
 }
 
 /**
diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index 32a5e0a2a66..7bc47fc7c68 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -282,6 +282,8 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba)
 				       arr_sz, GFP_KERNEL);
 	if (!cmgr->free_list_lock) {
 		printk(KERN_ERR PFX "failed to alloc free_list_lock\n");
+		kfree(cmgr->free_list);
+		cmgr->free_list = NULL;
 		goto mem_err;
 	}
 
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 5248c888552..7bcf67eec92 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -120,6 +120,7 @@ static struct request *get_alua_req(struct scsi_device *sdev,
 			    "%s: blk_get_request failed\n", __func__);
 		return NULL;
 	}
+	blk_rq_set_block_pc(rq);
 
 	if (buflen && blk_rq_map_kern(q, rq, buffer, buflen, GFP_NOIO)) {
 		blk_put_request(rq);
@@ -128,7 +129,6 @@ static struct request *get_alua_req(struct scsi_device *sdev,
 		return NULL;
 	}
 
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 			 REQ_FAILFAST_DRIVER;
 	rq->retries = ALUA_FAILOVER_RETRIES;
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index e1c8be06de9..6f07f7fe3aa 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -280,6 +280,7 @@ static struct request *get_req(struct scsi_device *sdev, int cmd,
 		return NULL;
 	}
 
+	blk_rq_set_block_pc(rq);
 	rq->cmd_len = COMMAND_SIZE(cmd);
 	rq->cmd[0] = cmd;
 
@@ -304,7 +305,6 @@ static struct request *get_req(struct scsi_device *sdev, int cmd,
 		break;
 	}
 
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 			 REQ_FAILFAST_DRIVER;
 	rq->timeout = CLARIION_TIMEOUT;
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index 084062bb8ee..e9d9fea9e27 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -120,7 +120,7 @@ retry:
 	if (!req)
 		return SCSI_DH_RES_TEMP_UNAVAIL;
 
-	req->cmd_type = REQ_TYPE_BLOCK_PC;
+	blk_rq_set_block_pc(req);
 	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 			  REQ_FAILFAST_DRIVER;
 	req->cmd_len = COMMAND_SIZE(TEST_UNIT_READY);
@@ -250,7 +250,7 @@ static int hp_sw_start_stop(struct hp_sw_dh_data *h)
 	if (!req)
 		return SCSI_DH_RES_TEMP_UNAVAIL;
 
-	req->cmd_type = REQ_TYPE_BLOCK_PC;
+	blk_rq_set_block_pc(req);
 	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 			  REQ_FAILFAST_DRIVER;
 	req->cmd_len = COMMAND_SIZE(START_STOP);
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 4b9cf93f3fb..826069db984 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -279,6 +279,7 @@ static struct request *get_rdac_req(struct scsi_device *sdev,
 				"get_rdac_req: blk_get_request failed.\n");
 		return NULL;
 	}
+	blk_rq_set_block_pc(rq);
 
 	if (buflen && blk_rq_map_kern(q, rq, buffer, buflen, GFP_NOIO)) {
 		blk_put_request(rq);
@@ -287,7 +288,6 @@ static struct request *get_rdac_req(struct scsi_device *sdev,
 		return NULL;
 	}
 
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
 			 REQ_FAILFAST_DRIVER;
 	rq->retries = RDAC_RETRIES;
diff --git a/drivers/scsi/dtc.c b/drivers/scsi/dtc.c
index eb29fe7eaf4..0a667fe0500 100644
--- a/drivers/scsi/dtc.c
+++ b/drivers/scsi/dtc.c
@@ -3,8 +3,6 @@
 #define PSEUDO_DMA
 #define DONT_USE_INTR
 #define UNSAFE			/* Leave interrupts enabled during pseudo-dma I/O */
-#define xNDEBUG (NDEBUG_INTR+NDEBUG_RESELECTION+\
-		 NDEBUG_SELECTION+NDEBUG_ARBITRATION)
 #define DMA_WORKS_RIGHT
 
 
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index f37f3e3dd5d..6504a195c87 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -390,7 +390,7 @@ static int esas2r_probe(struct pci_dev *pcid,
 	esas2r_log_dev(ESAS2R_LOG_INFO, &(pcid->dev),
 		       "pci_enable_device() OK");
 	esas2r_log_dev(ESAS2R_LOG_INFO, &(pcid->dev),
-		       "after pci_device_enable() enable_cnt: %d",
+		       "after pci_enable_device() enable_cnt: %d",
 		       pcid->enable_cnt.counter);
 
 	host = scsi_host_alloc(&driver_template, host_alloc_size);
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 528d43b7b56..1d3521e13d7 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -39,14 +39,15 @@
 
 #define DRV_NAME		"fnic"
 #define DRV_DESCRIPTION		"Cisco FCoE HBA Driver"
-#define DRV_VERSION		"1.5.0.45"
+#define DRV_VERSION		"1.6.0.10"
 #define PFX			DRV_NAME ": "
 #define DFX                     DRV_NAME "%d: "
 
 #define DESC_CLEAN_LOW_WATERMARK 8
 #define FNIC_UCSM_DFLT_THROTTLE_CNT_BLD	16 /* UCSM default throttle count */
 #define FNIC_MIN_IO_REQ			256 /* Min IO throttle count */
-#define FNIC_MAX_IO_REQ		2048 /* scsi_cmnd tag map entries */
+#define FNIC_MAX_IO_REQ		1024 /* scsi_cmnd tag map entries */
+#define FNIC_DFLT_IO_REQ        256 /* Default scsi_cmnd tag map entries */
 #define	FNIC_IO_LOCKS		64 /* IO locks: power of 2 */
 #define FNIC_DFLT_QUEUE_DEPTH	32
 #define	FNIC_STATS_RATE_LIMIT	4 /* limit rate at which stats are pulled up */
diff --git a/drivers/scsi/fnic/fnic_debugfs.c b/drivers/scsi/fnic/fnic_debugfs.c
index b6073f87576..2c613bdea78 100644
--- a/drivers/scsi/fnic/fnic_debugfs.c
+++ b/drivers/scsi/fnic/fnic_debugfs.c
@@ -25,6 +25,21 @@ static struct dentry *fnic_trace_debugfs_file;
 static struct dentry *fnic_trace_enable;
 static struct dentry *fnic_stats_debugfs_root;
 
+static struct dentry *fnic_fc_trace_debugfs_file;
+static struct dentry *fnic_fc_rdata_trace_debugfs_file;
+static struct dentry *fnic_fc_trace_enable;
+static struct dentry *fnic_fc_trace_clear;
+
+struct fc_trace_flag_type {
+	u8 fc_row_file;
+	u8 fc_normal_file;
+	u8 fnic_trace;
+	u8 fc_trace;
+	u8 fc_clear;
+};
+
+static struct fc_trace_flag_type *fc_trc_flag;
+
 /*
  * fnic_debugfs_init - Initialize debugfs for fnic debug logging
  *
@@ -56,6 +71,18 @@ int fnic_debugfs_init(void)
 		return rc;
 	}
 
+	/* Allocate memory to structure */
+	fc_trc_flag = (struct fc_trace_flag_type *)
+		vmalloc(sizeof(struct fc_trace_flag_type));
+
+	if (fc_trc_flag) {
+		fc_trc_flag->fc_row_file = 0;
+		fc_trc_flag->fc_normal_file = 1;
+		fc_trc_flag->fnic_trace = 2;
+		fc_trc_flag->fc_trace = 3;
+		fc_trc_flag->fc_clear = 4;
+	}
+
 	rc = 0;
 	return rc;
 }
@@ -74,15 +101,19 @@ void fnic_debugfs_terminate(void)
 
 	debugfs_remove(fnic_trace_debugfs_root);
 	fnic_trace_debugfs_root = NULL;
+
+	if (fc_trc_flag)
+		vfree(fc_trc_flag);
 }
 
 /*
- * fnic_trace_ctrl_open - Open the trace_enable file
+ * fnic_trace_ctrl_open - Open the trace_enable file for fnic_trace
+ *               Or Open fc_trace_enable file for fc_trace
  * @inode: The inode pointer.
  * @file: The file pointer to attach the trace enable/disable flag.
  *
  * Description:
- * This routine opens a debugsfs file trace_enable.
+ * This routine opens a debugsfs file trace_enable or fc_trace_enable.
  *
  * Returns:
  * This function returns zero if successful.
@@ -94,15 +125,19 @@ static int fnic_trace_ctrl_open(struct inode *inode, struct file *filp)
 }
 
 /*
- * fnic_trace_ctrl_read - Read a trace_enable debugfs file
+ * fnic_trace_ctrl_read -
+ *          Read  trace_enable ,fc_trace_enable
+ *              or fc_trace_clear debugfs file
  * @filp: The file pointer to read from.
  * @ubuf: The buffer to copy the data to.
  * @cnt: The number of bytes to read.
  * @ppos: The position in the file to start reading from.
  *
  * Description:
- * This routine reads value of variable fnic_tracing_enabled
- * and stores into local @buf. It will start reading file at @ppos and
+ * This routine reads value of variable fnic_tracing_enabled or
+ * fnic_fc_tracing_enabled or fnic_fc_trace_cleared
+ * and stores into local @buf.
+ * It will start reading file at @ppos and
  * copy up to @cnt of data to @ubuf from @buf.
  *
  * Returns:
@@ -114,13 +149,25 @@ static ssize_t fnic_trace_ctrl_read(struct file *filp,
 {
 	char buf[64];
 	int len;
-	len = sprintf(buf, "%u\n", fnic_tracing_enabled);
+	u8 *trace_type;
+	len = 0;
+	trace_type = (u8 *)filp->private_data;
+	if (*trace_type == fc_trc_flag->fnic_trace)
+		len = sprintf(buf, "%u\n", fnic_tracing_enabled);
+	else if (*trace_type == fc_trc_flag->fc_trace)
+		len = sprintf(buf, "%u\n", fnic_fc_tracing_enabled);
+	else if (*trace_type == fc_trc_flag->fc_clear)
+		len = sprintf(buf, "%u\n", fnic_fc_trace_cleared);
+	else
+		pr_err("fnic: Cannot read to any debugfs file\n");
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
 }
 
 /*
- * fnic_trace_ctrl_write - Write to trace_enable debugfs file
+ * fnic_trace_ctrl_write -
+ * Write to trace_enable, fc_trace_enable or
+ *         fc_trace_clear debugfs file
  * @filp: The file pointer to write from.
  * @ubuf: The buffer to copy the data from.
  * @cnt: The number of bytes to write.
@@ -128,7 +175,8 @@ static ssize_t fnic_trace_ctrl_read(struct file *filp,
  *
  * Description:
  * This routine writes data from user buffer @ubuf to buffer @buf and
- * sets fnic_tracing_enabled value as per user input.
+ * sets fc_trace_enable ,tracing_enable or fnic_fc_trace_cleared
+ * value as per user input.
  *
  * Returns:
  * This function returns the amount of data that was written.
@@ -140,6 +188,8 @@ static ssize_t fnic_trace_ctrl_write(struct file *filp,
 	char buf[64];
 	unsigned long val;
 	int ret;
+	u8 *trace_type;
+	trace_type = (u8 *)filp->private_data;
 
 	if (cnt >= sizeof(buf))
 		return -EINVAL;
@@ -153,12 +203,27 @@ static ssize_t fnic_trace_ctrl_write(struct file *filp,
 	if (ret < 0)
 		return ret;
 
-	fnic_tracing_enabled = val;
+	if (*trace_type == fc_trc_flag->fnic_trace)
+		fnic_tracing_enabled = val;
+	else if (*trace_type == fc_trc_flag->fc_trace)
+		fnic_fc_tracing_enabled = val;
+	else if (*trace_type == fc_trc_flag->fc_clear)
+		fnic_fc_trace_cleared = val;
+	else
+		pr_err("fnic: cannot write to any debufs file\n");
+
 	(*ppos)++;
 
 	return cnt;
 }
 
+static const struct file_operations fnic_trace_ctrl_fops = {
+	.owner = THIS_MODULE,
+	.open = fnic_trace_ctrl_open,
+	.read = fnic_trace_ctrl_read,
+	.write = fnic_trace_ctrl_write,
+};
+
 /*
  * fnic_trace_debugfs_open - Open the fnic trace log
  * @inode: The inode pointer
@@ -178,19 +243,36 @@ static int fnic_trace_debugfs_open(struct inode *inode,
 				  struct file *file)
 {
 	fnic_dbgfs_t *fnic_dbg_prt;
+	u8 *rdata_ptr;
+	rdata_ptr = (u8 *)inode->i_private;
 	fnic_dbg_prt = kzalloc(sizeof(fnic_dbgfs_t), GFP_KERNEL);
 	if (!fnic_dbg_prt)
 		return -ENOMEM;
 
-	fnic_dbg_prt->buffer = vmalloc((3*(trace_max_pages * PAGE_SIZE)));
-	if (!fnic_dbg_prt->buffer) {
-		kfree(fnic_dbg_prt);
-		return -ENOMEM;
+	if (*rdata_ptr == fc_trc_flag->fnic_trace) {
+		fnic_dbg_prt->buffer = vmalloc(3 *
+					(trace_max_pages * PAGE_SIZE));
+		if (!fnic_dbg_prt->buffer) {
+			kfree(fnic_dbg_prt);
+			return -ENOMEM;
+		}
+		memset((void *)fnic_dbg_prt->buffer, 0,
+		3 * (trace_max_pages * PAGE_SIZE));
+		fnic_dbg_prt->buffer_len = fnic_get_trace_data(fnic_dbg_prt);
+	} else {
+		fnic_dbg_prt->buffer =
+			vmalloc(3 * (fnic_fc_trace_max_pages * PAGE_SIZE));
+		if (!fnic_dbg_prt->buffer) {
+			kfree(fnic_dbg_prt);
+			return -ENOMEM;
+		}
+		memset((void *)fnic_dbg_prt->buffer, 0,
+			3 * (fnic_fc_trace_max_pages * PAGE_SIZE));
+		fnic_dbg_prt->buffer_len =
+			fnic_fc_trace_get_data(fnic_dbg_prt, *rdata_ptr);
 	}
-	memset((void *)fnic_dbg_prt->buffer, 0,
-			  (3*(trace_max_pages * PAGE_SIZE)));
-	fnic_dbg_prt->buffer_len = fnic_get_trace_data(fnic_dbg_prt);
 	file->private_data = fnic_dbg_prt;
+
 	return 0;
 }
 
@@ -272,13 +354,6 @@ static int fnic_trace_debugfs_release(struct inode *inode,
 	return 0;
 }
 
-static const struct file_operations fnic_trace_ctrl_fops = {
-	.owner = THIS_MODULE,
-	.open = fnic_trace_ctrl_open,
-	.read = fnic_trace_ctrl_read,
-	.write = fnic_trace_ctrl_write,
-};
-
 static const struct file_operations fnic_trace_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.open = fnic_trace_debugfs_open,
@@ -306,9 +381,10 @@ int fnic_trace_debugfs_init(void)
 		return rc;
 	}
 	fnic_trace_enable = debugfs_create_file("tracing_enable",
-					  S_IFREG|S_IRUGO|S_IWUSR,
-					  fnic_trace_debugfs_root,
-					  NULL, &fnic_trace_ctrl_fops);
+					S_IFREG|S_IRUGO|S_IWUSR,
+					fnic_trace_debugfs_root,
+					&(fc_trc_flag->fnic_trace),
+					&fnic_trace_ctrl_fops);
 
 	if (!fnic_trace_enable) {
 		printk(KERN_DEBUG
@@ -317,10 +393,10 @@ int fnic_trace_debugfs_init(void)
 	}
 
 	fnic_trace_debugfs_file = debugfs_create_file("trace",
-						  S_IFREG|S_IRUGO|S_IWUSR,
-						  fnic_trace_debugfs_root,
-						  NULL,
-						  &fnic_trace_debugfs_fops);
+					S_IFREG|S_IRUGO|S_IWUSR,
+					fnic_trace_debugfs_root,
+					&(fc_trc_flag->fnic_trace),
+					&fnic_trace_debugfs_fops);
 
 	if (!fnic_trace_debugfs_file) {
 		printk(KERN_DEBUG
@@ -340,14 +416,104 @@ int fnic_trace_debugfs_init(void)
  */
 void fnic_trace_debugfs_terminate(void)
 {
-	if (fnic_trace_debugfs_file) {
-		debugfs_remove(fnic_trace_debugfs_file);
-		fnic_trace_debugfs_file = NULL;
+	debugfs_remove(fnic_trace_debugfs_file);
+	fnic_trace_debugfs_file = NULL;
+
+	debugfs_remove(fnic_trace_enable);
+	fnic_trace_enable = NULL;
+}
+
+/*
+ * fnic_fc_trace_debugfs_init -
+ * Initialize debugfs for fnic control frame trace logging
+ *
+ * Description:
+ * When Debugfs is configured this routine sets up the fnic_fc debugfs
+ * file system. If not already created, this routine will create the
+ * create file trace to log fnic fc trace buffer output into debugfs and
+ * it will also create file fc_trace_enable to control enable/disable of
+ * trace logging into trace buffer.
+ */
+
+int fnic_fc_trace_debugfs_init(void)
+{
+	int rc = -1;
+
+	if (!fnic_trace_debugfs_root) {
+		pr_err("fnic:Debugfs root directory doesn't exist\n");
+		return rc;
+	}
+
+	fnic_fc_trace_enable = debugfs_create_file("fc_trace_enable",
+					S_IFREG|S_IRUGO|S_IWUSR,
+					fnic_trace_debugfs_root,
+					&(fc_trc_flag->fc_trace),
+					&fnic_trace_ctrl_fops);
+
+	if (!fnic_fc_trace_enable) {
+		pr_err("fnic: Failed create fc_trace_enable file\n");
+		return rc;
+	}
+
+	fnic_fc_trace_clear = debugfs_create_file("fc_trace_clear",
+					S_IFREG|S_IRUGO|S_IWUSR,
+					fnic_trace_debugfs_root,
+					&(fc_trc_flag->fc_clear),
+					&fnic_trace_ctrl_fops);
+
+	if (!fnic_fc_trace_clear) {
+		pr_err("fnic: Failed to create fc_trace_enable file\n");
+		return rc;
+	}
+
+	fnic_fc_rdata_trace_debugfs_file =
+		debugfs_create_file("fc_trace_rdata",
+				    S_IFREG|S_IRUGO|S_IWUSR,
+				    fnic_trace_debugfs_root,
+				    &(fc_trc_flag->fc_normal_file),
+				    &fnic_trace_debugfs_fops);
+
+	if (!fnic_fc_rdata_trace_debugfs_file) {
+		pr_err("fnic: Failed create fc_rdata_trace file\n");
+		return rc;
 	}
-	if (fnic_trace_enable) {
-		debugfs_remove(fnic_trace_enable);
-		fnic_trace_enable = NULL;
+
+	fnic_fc_trace_debugfs_file =
+		debugfs_create_file("fc_trace",
+				    S_IFREG|S_IRUGO|S_IWUSR,
+				    fnic_trace_debugfs_root,
+				    &(fc_trc_flag->fc_row_file),
+				    &fnic_trace_debugfs_fops);
+
+	if (!fnic_fc_trace_debugfs_file) {
+		pr_err("fnic: Failed to create fc_trace file\n");
+		return rc;
 	}
+	rc = 0;
+	return rc;
+}
+
+/*
+ * fnic_fc_trace_debugfs_terminate - Tear down debugfs infrastructure
+ *
+ * Description:
+ * When Debugfs is configured this routine removes debugfs file system
+ * elements that are specific to fnic_fc trace logging.
+ */
+
+void fnic_fc_trace_debugfs_terminate(void)
+{
+	debugfs_remove(fnic_fc_trace_debugfs_file);
+	fnic_fc_trace_debugfs_file = NULL;
+
+	debugfs_remove(fnic_fc_rdata_trace_debugfs_file);
+	fnic_fc_rdata_trace_debugfs_file = NULL;
+
+	debugfs_remove(fnic_fc_trace_enable);
+	fnic_fc_trace_enable = NULL;
+
+	debugfs_remove(fnic_fc_trace_clear);
+	fnic_fc_trace_clear = NULL;
 }
 
 /*
diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c
index 1671325aec7..1b948f633fc 100644
--- a/drivers/scsi/fnic/fnic_fcs.c
+++ b/drivers/scsi/fnic/fnic_fcs.c
@@ -66,19 +66,35 @@ void fnic_handle_link(struct work_struct *work)
 	fnic->link_down_cnt = vnic_dev_link_down_cnt(fnic->vdev);
 
 	if (old_link_status == fnic->link_status) {
-		if (!fnic->link_status)
+		if (!fnic->link_status) {
 			/* DOWN -> DOWN */
 			spin_unlock_irqrestore(&fnic->fnic_lock, flags);
-		else {
+			fnic_fc_trace_set_data(fnic->lport->host->host_no,
+				FNIC_FC_LE, "Link Status: DOWN->DOWN",
+				strlen("Link Status: DOWN->DOWN"));
+		} else {
 			if (old_link_down_cnt != fnic->link_down_cnt) {
 				/* UP -> DOWN -> UP */
 				fnic->lport->host_stats.link_failure_count++;
 				spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+				fnic_fc_trace_set_data(
+					fnic->lport->host->host_no,
+					FNIC_FC_LE,
+					"Link Status:UP_DOWN_UP",
+					strlen("Link_Status:UP_DOWN_UP")
+					);
 				FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host,
 					     "link down\n");
 				fcoe_ctlr_link_down(&fnic->ctlr);
 				if (fnic->config.flags & VFCF_FIP_CAPABLE) {
 					/* start FCoE VLAN discovery */
+					fnic_fc_trace_set_data(
+						fnic->lport->host->host_no,
+						FNIC_FC_LE,
+						"Link Status: UP_DOWN_UP_VLAN",
+						strlen(
+						"Link Status: UP_DOWN_UP_VLAN")
+						);
 					fnic_fcoe_send_vlan_req(fnic);
 					return;
 				}
@@ -88,22 +104,36 @@ void fnic_handle_link(struct work_struct *work)
 			} else
 				/* UP -> UP */
 				spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+				fnic_fc_trace_set_data(
+					fnic->lport->host->host_no, FNIC_FC_LE,
+					"Link Status: UP_UP",
+					strlen("Link Status: UP_UP"));
 		}
 	} else if (fnic->link_status) {
 		/* DOWN -> UP */
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		if (fnic->config.flags & VFCF_FIP_CAPABLE) {
 			/* start FCoE VLAN discovery */
+				fnic_fc_trace_set_data(
+				fnic->lport->host->host_no,
+				FNIC_FC_LE, "Link Status: DOWN_UP_VLAN",
+				strlen("Link Status: DOWN_UP_VLAN"));
 			fnic_fcoe_send_vlan_req(fnic);
 			return;
 		}
 		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, "link up\n");
+		fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_LE,
+			"Link Status: DOWN_UP", strlen("Link Status: DOWN_UP"));
 		fcoe_ctlr_link_up(&fnic->ctlr);
 	} else {
 		/* UP -> DOWN */
 		fnic->lport->host_stats.link_failure_count++;
 		spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 		FNIC_FCS_DBG(KERN_DEBUG, fnic->lport->host, "link down\n");
+		fnic_fc_trace_set_data(
+			fnic->lport->host->host_no, FNIC_FC_LE,
+			"Link Status: UP_DOWN",
+			strlen("Link Status: UP_DOWN"));
 		fcoe_ctlr_link_down(&fnic->ctlr);
 	}
 
@@ -267,11 +297,6 @@ static inline int is_fnic_fip_flogi_reject(struct fcoe_ctlr *fip,
 
 	if (desc->fip_dtype == FIP_DT_FLOGI) {
 
-		shost_printk(KERN_DEBUG, lport->host,
-			  " FIP TYPE FLOGI: fab name:%llx "
-			  "vfid:%d map:%x\n",
-			  fip->sel_fcf->fabric_name, fip->sel_fcf->vfid,
-			  fip->sel_fcf->fc_map);
 		if (dlen < sizeof(*els) + sizeof(*fh) + 1)
 			return 0;
 
@@ -616,6 +641,10 @@ static inline int fnic_import_rq_eth_pkt(struct fnic *fnic, struct sk_buff *skb)
 					"using UCSM\n");
 			goto drop;
 		}
+		if ((fnic_fc_trace_set_data(fnic->lport->host->host_no,
+			FNIC_FC_RECV|0x80, (char *)skb->data, skb->len)) != 0) {
+			printk(KERN_ERR "fnic ctlr frame trace error!!!");
+		}
 		skb_queue_tail(&fnic->fip_frame_queue, skb);
 		queue_work(fnic_fip_queue, &fnic->fip_frame_work);
 		return 1;		/* let caller know packet was used */
@@ -844,6 +873,10 @@ static void fnic_rq_cmpl_frame_recv(struct vnic_rq *rq, struct cq_desc
 	}
 	fr_dev(fp) = fnic->lport;
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
+	if ((fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_RECV,
+					(char *)skb->data, skb->len)) != 0) {
+		printk(KERN_ERR "fnic ctlr frame trace error!!!");
+	}
 
 	skb_queue_tail(&fnic->frame_queue, skb);
 	queue_work(fnic_event_queue, &fnic->frame_work);
@@ -951,6 +984,15 @@ void fnic_eth_send(struct fcoe_ctlr *fip, struct sk_buff *skb)
 		vlan_hdr->h_vlan_proto = htons(ETH_P_8021Q);
 		vlan_hdr->h_vlan_encapsulated_proto = eth_hdr->h_proto;
 		vlan_hdr->h_vlan_TCI = htons(fnic->vlan_id);
+		if ((fnic_fc_trace_set_data(fnic->lport->host->host_no,
+			FNIC_FC_SEND|0x80, (char *)eth_hdr, skb->len)) != 0) {
+			printk(KERN_ERR "fnic ctlr frame trace error!!!");
+		}
+	} else {
+		if ((fnic_fc_trace_set_data(fnic->lport->host->host_no,
+			FNIC_FC_SEND|0x80, (char *)skb->data, skb->len)) != 0) {
+			printk(KERN_ERR "fnic ctlr frame trace error!!!");
+		}
 	}
 
 	pa = pci_map_single(fnic->pdev, skb->data, skb->len, PCI_DMA_TODEVICE);
@@ -1023,6 +1065,11 @@ static int fnic_send_frame(struct fnic *fnic, struct fc_frame *fp)
 
 	pa = pci_map_single(fnic->pdev, eth_hdr, tot_len, PCI_DMA_TODEVICE);
 
+	if ((fnic_fc_trace_set_data(fnic->lport->host->host_no, FNIC_FC_SEND,
+				(char *)eth_hdr, tot_len)) != 0) {
+		printk(KERN_ERR "fnic ctlr frame trace error!!!");
+	}
+
 	spin_lock_irqsave(&fnic->wq_lock[0], flags);
 
 	if (!vnic_wq_desc_avail(wq)) {
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 33e4ec2bfe7..8c56fdc3a45 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -74,6 +74,11 @@ module_param(fnic_trace_max_pages, uint, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(fnic_trace_max_pages, "Total allocated memory pages "
 					"for fnic trace buffer");
 
+unsigned int fnic_fc_trace_max_pages = 64;
+module_param(fnic_fc_trace_max_pages, uint, S_IRUGO|S_IWUSR);
+MODULE_PARM_DESC(fnic_fc_trace_max_pages,
+		 "Total allocated memory pages for fc trace buffer");
+
 static unsigned int fnic_max_qdepth = FNIC_DFLT_QUEUE_DEPTH;
 module_param(fnic_max_qdepth, uint, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(fnic_max_qdepth, "Queue depth to report for each LUN");
@@ -111,7 +116,7 @@ static struct scsi_host_template fnic_host_template = {
 	.change_queue_type = fc_change_queue_type,
 	.this_id = -1,
 	.cmd_per_lun = 3,
-	.can_queue = FNIC_MAX_IO_REQ,
+	.can_queue = FNIC_DFLT_IO_REQ,
 	.use_clustering = ENABLE_CLUSTERING,
 	.sg_tablesize = FNIC_MAX_SG_DESC_CNT,
 	.max_sectors = 0xffff,
@@ -773,6 +778,7 @@ static int fnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		shost_printk(KERN_INFO, fnic->lport->host,
 			     "firmware uses non-FIP mode\n");
 		fcoe_ctlr_init(&fnic->ctlr, FIP_MODE_NON_FIP);
+		fnic->ctlr.state = FIP_ST_NON_FIP;
 	}
 	fnic->state = FNIC_IN_FC_MODE;
 
@@ -1033,11 +1039,20 @@ static int __init fnic_init_module(void)
 	/* Allocate memory for trace buffer */
 	err = fnic_trace_buf_init();
 	if (err < 0) {
-		printk(KERN_ERR PFX "Trace buffer initialization Failed "
-				  "Fnic Tracing utility is disabled\n");
+		printk(KERN_ERR PFX
+		       "Trace buffer initialization Failed. "
+		       "Fnic Tracing utility is disabled\n");
 		fnic_trace_free();
 	}
 
+    /* Allocate memory for fc trace buffer */
+	err = fnic_fc_trace_init();
+	if (err < 0) {
+		printk(KERN_ERR PFX "FC trace buffer initialization Failed "
+		       "FC frame tracing utility is disabled\n");
+		fnic_fc_trace_free();
+	}
+
 	/* Create a cache for allocation of default size sgls */
 	len = sizeof(struct fnic_dflt_sgl_list);
 	fnic_sgl_cache[FNIC_SGL_CACHE_DFLT] = kmem_cache_create
@@ -1118,6 +1133,7 @@ err_create_fnic_sgl_slab_max:
 	kmem_cache_destroy(fnic_sgl_cache[FNIC_SGL_CACHE_DFLT]);
 err_create_fnic_sgl_slab_dflt:
 	fnic_trace_free();
+	fnic_fc_trace_free();
 	fnic_debugfs_terminate();
 	return err;
 }
@@ -1135,6 +1151,7 @@ static void __exit fnic_cleanup_module(void)
 	kmem_cache_destroy(fnic_io_req_cache);
 	fc_release_transport(fnic_fc_transport);
 	fnic_trace_free();
+	fnic_fc_trace_free();
 	fnic_debugfs_terminate();
 }
 
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 0521436d05d..ea28b5ca4c7 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -1312,8 +1312,9 @@ static void fnic_cleanup_io(struct fnic *fnic, int exclude_id)
 
 cleanup_scsi_cmd:
 		sc->result = DID_TRANSPORT_DISRUPTED << 16;
-		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host, "fnic_cleanup_io:"
-			      " DID_TRANSPORT_DISRUPTED\n");
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->lport->host,
+			      "%s: sc duration = %lu DID_TRANSPORT_DISRUPTED\n",
+			      __func__, (jiffies - start_time));
 
 		if (atomic64_read(&fnic->io_cmpl_skip))
 			atomic64_dec(&fnic->io_cmpl_skip);
@@ -1733,6 +1734,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	struct fnic_stats *fnic_stats;
 	struct abort_stats *abts_stats;
 	struct terminate_stats *term_stats;
+	enum fnic_ioreq_state old_ioreq_state;
 	int tag;
 	DECLARE_COMPLETION_ONSTACK(tm_done);
 
@@ -1793,6 +1795,7 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	 * the completion wont be done till mid-layer, since abort
 	 * has already started.
 	 */
+	old_ioreq_state = CMD_STATE(sc);
 	CMD_STATE(sc) = FNIC_IOREQ_ABTS_PENDING;
 	CMD_ABTS_STATUS(sc) = FCPIO_INVALID_CODE;
 
@@ -1816,6 +1819,8 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	if (fnic_queue_abort_io_req(fnic, sc->request->tag, task_req,
 				    fc_lun.scsi_lun, io_req)) {
 		spin_lock_irqsave(io_lock, flags);
+		if (CMD_STATE(sc) == FNIC_IOREQ_ABTS_PENDING)
+			CMD_STATE(sc) = old_ioreq_state;
 		io_req = (struct fnic_io_req *)CMD_SP(sc);
 		if (io_req)
 			io_req->abts_done = NULL;
@@ -1859,12 +1864,8 @@ int fnic_abort_cmd(struct scsi_cmnd *sc)
 	if (CMD_ABTS_STATUS(sc) == FCPIO_INVALID_CODE) {
 		spin_unlock_irqrestore(io_lock, flags);
 		if (task_req == FCPIO_ITMF_ABT_TASK) {
-			FNIC_SCSI_DBG(KERN_INFO,
-				fnic->lport->host, "Abort Driver Timeout\n");
 			atomic64_inc(&abts_stats->abort_drv_timeouts);
 		} else {
-			FNIC_SCSI_DBG(KERN_INFO, fnic->lport->host,
-				"Terminate Driver Timeout\n");
 			atomic64_inc(&term_stats->terminate_drv_timeouts);
 		}
 		CMD_FLAGS(sc) |= FNIC_IO_ABT_TERM_TIMED_OUT;
diff --git a/drivers/scsi/fnic/fnic_trace.c b/drivers/scsi/fnic/fnic_trace.c
index e002e7187dc..c7728592682 100644
--- a/drivers/scsi/fnic/fnic_trace.c
+++ b/drivers/scsi/fnic/fnic_trace.c
@@ -20,6 +20,7 @@
 #include <linux/errno.h>
 #include <linux/spinlock.h>
 #include <linux/kallsyms.h>
+#include <linux/time.h>
 #include "fnic_io.h"
 #include "fnic.h"
 
@@ -32,6 +33,16 @@ static DEFINE_SPINLOCK(fnic_trace_lock);
 static fnic_trace_dbg_t fnic_trace_entries;
 int fnic_tracing_enabled = 1;
 
+/* static char *fnic_fc_ctlr_trace_buf_p; */
+
+static int fc_trace_max_entries;
+static unsigned long fnic_fc_ctlr_trace_buf_p;
+static fnic_trace_dbg_t fc_trace_entries;
+int fnic_fc_tracing_enabled = 1;
+int fnic_fc_trace_cleared = 1;
+static DEFINE_SPINLOCK(fnic_fc_trace_lock);
+
+
 /*
  * fnic_trace_get_buf - Give buffer pointer to user to fill up trace information
  *
@@ -428,10 +439,10 @@ int fnic_trace_buf_init(void)
 	}
 	err = fnic_trace_debugfs_init();
 	if (err < 0) {
-		printk(KERN_ERR PFX "Failed to initialize debugfs for tracing\n");
+		pr_err("fnic: Failed to initialize debugfs for tracing\n");
 		goto err_fnic_trace_debugfs_init;
 	}
-	printk(KERN_INFO PFX "Successfully Initialized Trace Buffer\n");
+	pr_info("fnic: Successfully Initialized Trace Buffer\n");
 	return err;
 err_fnic_trace_debugfs_init:
 	fnic_trace_free();
@@ -456,3 +467,314 @@ void fnic_trace_free(void)
 	}
 	printk(KERN_INFO PFX "Successfully Freed Trace Buffer\n");
 }
+
+/*
+ * fnic_fc_ctlr_trace_buf_init -
+ * Initialize trace buffer to log fnic control frames
+ * Description:
+ * Initialize trace buffer data structure by allocating
+ * required memory for trace data as well as for Indexes.
+ * Frame size is 256 bytes and
+ * memory is allocated for 1024 entries of 256 bytes.
+ * Page_offset(Index) is set to the address of trace entry
+ * and page_offset is initialized by adding frame size
+ * to the previous page_offset entry.
+ */
+
+int fnic_fc_trace_init(void)
+{
+	unsigned long fc_trace_buf_head;
+	int err = 0;
+	int i;
+
+	fc_trace_max_entries = (fnic_fc_trace_max_pages * PAGE_SIZE)/
+				FC_TRC_SIZE_BYTES;
+	fnic_fc_ctlr_trace_buf_p = (unsigned long)vmalloc(
+					fnic_fc_trace_max_pages * PAGE_SIZE);
+	if (!fnic_fc_ctlr_trace_buf_p) {
+		pr_err("fnic: Failed to allocate memory for "
+		       "FC Control Trace Buf\n");
+		err = -ENOMEM;
+		goto err_fnic_fc_ctlr_trace_buf_init;
+	}
+
+	memset((void *)fnic_fc_ctlr_trace_buf_p, 0,
+			fnic_fc_trace_max_pages * PAGE_SIZE);
+
+	/* Allocate memory for page offset */
+	fc_trace_entries.page_offset = vmalloc(fc_trace_max_entries *
+						sizeof(unsigned long));
+	if (!fc_trace_entries.page_offset) {
+		pr_err("fnic:Failed to allocate memory for page_offset\n");
+		if (fnic_fc_ctlr_trace_buf_p) {
+			pr_err("fnic: Freeing FC Control Trace Buf\n");
+			vfree((void *)fnic_fc_ctlr_trace_buf_p);
+			fnic_fc_ctlr_trace_buf_p = 0;
+		}
+		err = -ENOMEM;
+		goto err_fnic_fc_ctlr_trace_buf_init;
+	}
+	memset((void *)fc_trace_entries.page_offset, 0,
+	       (fc_trace_max_entries * sizeof(unsigned long)));
+
+	fc_trace_entries.rd_idx = fc_trace_entries.wr_idx = 0;
+	fc_trace_buf_head = fnic_fc_ctlr_trace_buf_p;
+
+	/*
+	* Set up fc_trace_entries.page_offset field with memory location
+	* for every trace entry
+	*/
+	for (i = 0; i < fc_trace_max_entries; i++) {
+		fc_trace_entries.page_offset[i] = fc_trace_buf_head;
+		fc_trace_buf_head += FC_TRC_SIZE_BYTES;
+	}
+	err = fnic_fc_trace_debugfs_init();
+	if (err < 0) {
+		pr_err("fnic: Failed to initialize FC_CTLR tracing.\n");
+		goto err_fnic_fc_ctlr_trace_debugfs_init;
+	}
+	pr_info("fnic: Successfully Initialized FC_CTLR Trace Buffer\n");
+	return err;
+
+err_fnic_fc_ctlr_trace_debugfs_init:
+	fnic_fc_trace_free();
+err_fnic_fc_ctlr_trace_buf_init:
+	return err;
+}
+
+/*
+ * Fnic_fc_ctlr_trace_free - Free memory of fnic_fc_ctlr trace data structures.
+ */
+void fnic_fc_trace_free(void)
+{
+	fnic_fc_tracing_enabled = 0;
+	fnic_fc_trace_debugfs_terminate();
+	if (fc_trace_entries.page_offset) {
+		vfree((void *)fc_trace_entries.page_offset);
+		fc_trace_entries.page_offset = NULL;
+	}
+	if (fnic_fc_ctlr_trace_buf_p) {
+		vfree((void *)fnic_fc_ctlr_trace_buf_p);
+		fnic_fc_ctlr_trace_buf_p = 0;
+	}
+	pr_info("fnic:Successfully FC_CTLR Freed Trace Buffer\n");
+}
+
+/*
+ * fnic_fc_ctlr_set_trace_data:
+ *       Maintain rd & wr idx accordingly and set data
+ * Passed parameters:
+ *       host_no: host number accociated with fnic
+ *       frame_type: send_frame, rece_frame or link event
+ *       fc_frame: pointer to fc_frame
+ *       frame_len: Length of the fc_frame
+ * Description:
+ *   This routine will get next available wr_idx and
+ *   copy all passed trace data to the buffer pointed by wr_idx
+ *   and increment wr_idx. It will also make sure that we dont
+ *   overwrite the entry which we are reading and also
+ *   wrap around if we reach the maximum entries.
+ * Returned Value:
+ *   It will return 0 for success or -1 for failure
+ */
+int fnic_fc_trace_set_data(u32 host_no, u8 frame_type,
+				char *frame, u32 fc_trc_frame_len)
+{
+	unsigned long flags;
+	struct fc_trace_hdr *fc_buf;
+	unsigned long eth_fcoe_hdr_len;
+	char *fc_trace;
+
+	if (fnic_fc_tracing_enabled == 0)
+		return 0;
+
+	spin_lock_irqsave(&fnic_fc_trace_lock, flags);
+
+	if (fnic_fc_trace_cleared == 1) {
+		fc_trace_entries.rd_idx = fc_trace_entries.wr_idx = 0;
+		pr_info("fnic: Reseting the read idx\n");
+		memset((void *)fnic_fc_ctlr_trace_buf_p, 0,
+				fnic_fc_trace_max_pages * PAGE_SIZE);
+		fnic_fc_trace_cleared = 0;
+	}
+
+	fc_buf = (struct fc_trace_hdr *)
+		fc_trace_entries.page_offset[fc_trace_entries.wr_idx];
+
+	fc_trace_entries.wr_idx++;
+
+	if (fc_trace_entries.wr_idx >= fc_trace_max_entries)
+		fc_trace_entries.wr_idx = 0;
+
+	if (fc_trace_entries.wr_idx == fc_trace_entries.rd_idx) {
+		fc_trace_entries.rd_idx++;
+		if (fc_trace_entries.rd_idx >= fc_trace_max_entries)
+			fc_trace_entries.rd_idx = 0;
+	}
+
+	fc_buf->time_stamp = CURRENT_TIME;
+	fc_buf->host_no = host_no;
+	fc_buf->frame_type = frame_type;
+
+	fc_trace = (char *)FC_TRACE_ADDRESS(fc_buf);
+
+	/* During the receive path, we do not have eth hdr as well as fcoe hdr
+	 * at trace entry point so we will stuff 0xff just to make it generic.
+	 */
+	if (frame_type == FNIC_FC_RECV) {
+		eth_fcoe_hdr_len = sizeof(struct ethhdr) +
+					sizeof(struct fcoe_hdr);
+		fc_trc_frame_len = fc_trc_frame_len + eth_fcoe_hdr_len;
+		memset((char *)fc_trace, 0xff, eth_fcoe_hdr_len);
+		/* Copy the rest of data frame */
+		memcpy((char *)(fc_trace + eth_fcoe_hdr_len), (void *)frame,
+		min_t(u8, fc_trc_frame_len,
+			(u8)(FC_TRC_SIZE_BYTES - FC_TRC_HEADER_SIZE)));
+	} else {
+		memcpy((char *)fc_trace, (void *)frame,
+		min_t(u8, fc_trc_frame_len,
+			(u8)(FC_TRC_SIZE_BYTES - FC_TRC_HEADER_SIZE)));
+	}
+
+	/* Store the actual received length */
+	fc_buf->frame_len = fc_trc_frame_len;
+
+	spin_unlock_irqrestore(&fnic_fc_trace_lock, flags);
+	return 0;
+}
+
+/*
+ * fnic_fc_ctlr_get_trace_data: Copy trace buffer to a memory file
+ * Passed parameter:
+ *       @fnic_dbgfs_t: pointer to debugfs trace buffer
+ *       rdata_flag: 1 => Unformated file
+ *                   0 => formated file
+ * Description:
+ *       This routine will copy the trace data to memory file with
+ *       proper formatting and also copy to another memory
+ *       file without formatting for further procesing.
+ * Retrun Value:
+ *       Number of bytes that were dumped into fnic_dbgfs_t
+ */
+
+int fnic_fc_trace_get_data(fnic_dbgfs_t *fnic_dbgfs_prt, u8 rdata_flag)
+{
+	int rd_idx, wr_idx;
+	unsigned long flags;
+	int len = 0, j;
+	struct fc_trace_hdr *tdata;
+	char *fc_trace;
+
+	spin_lock_irqsave(&fnic_fc_trace_lock, flags);
+	if (fc_trace_entries.wr_idx == fc_trace_entries.rd_idx) {
+		spin_unlock_irqrestore(&fnic_fc_trace_lock, flags);
+		pr_info("fnic: Buffer is empty\n");
+		return 0;
+	}
+	rd_idx = fc_trace_entries.rd_idx;
+	wr_idx = fc_trace_entries.wr_idx;
+	if (rdata_flag == 0) {
+		len += snprintf(fnic_dbgfs_prt->buffer + len,
+			(fnic_fc_trace_max_pages * PAGE_SIZE * 3) - len,
+			"Time Stamp (UTC)\t\t"
+			"Host No:   F Type:  len:     FCoE_FRAME:\n");
+	}
+
+	while (rd_idx != wr_idx) {
+		tdata = (struct fc_trace_hdr *)
+			fc_trace_entries.page_offset[rd_idx];
+		if (!tdata) {
+			pr_info("fnic: Rd data is NULL\n");
+			spin_unlock_irqrestore(&fnic_fc_trace_lock, flags);
+			return 0;
+		}
+		if (rdata_flag == 0) {
+			copy_and_format_trace_data(tdata,
+				fnic_dbgfs_prt, &len, rdata_flag);
+		} else {
+			fc_trace = (char *)tdata;
+			for (j = 0; j < FC_TRC_SIZE_BYTES; j++) {
+				len += snprintf(fnic_dbgfs_prt->buffer + len,
+				(fnic_fc_trace_max_pages * PAGE_SIZE * 3)
+				- len, "%02x", fc_trace[j] & 0xff);
+			} /* for loop */
+			len += snprintf(fnic_dbgfs_prt->buffer + len,
+				(fnic_fc_trace_max_pages * PAGE_SIZE * 3) - len,
+				"\n");
+		}
+		rd_idx++;
+		if (rd_idx > (fc_trace_max_entries - 1))
+			rd_idx = 0;
+	}
+
+	spin_unlock_irqrestore(&fnic_fc_trace_lock, flags);
+	return len;
+}
+
+/*
+ * copy_and_format_trace_data: Copy formatted data to char * buffer
+ * Passed Parameter:
+ *      @fc_trace_hdr_t: pointer to trace data
+ *      @fnic_dbgfs_t: pointer to debugfs trace buffer
+ *      @orig_len: pointer to len
+ *      rdata_flag: 0 => Formated file, 1 => Unformated file
+ * Description:
+ *      This routine will format and copy the passed trace data
+ *      for formated file or unformated file accordingly.
+ */
+
+void copy_and_format_trace_data(struct fc_trace_hdr *tdata,
+				fnic_dbgfs_t *fnic_dbgfs_prt, int *orig_len,
+				u8 rdata_flag)
+{
+	struct tm tm;
+	int j, i = 1, len;
+	char *fc_trace, *fmt;
+	int ethhdr_len = sizeof(struct ethhdr) - 1;
+	int fcoehdr_len = sizeof(struct fcoe_hdr);
+	int fchdr_len = sizeof(struct fc_frame_header);
+	int max_size = fnic_fc_trace_max_pages * PAGE_SIZE * 3;
+
+	tdata->frame_type = tdata->frame_type & 0x7F;
+
+	len = *orig_len;
+
+	time_to_tm(tdata->time_stamp.tv_sec, 0, &tm);
+
+	fmt = "%02d:%02d:%04ld %02d:%02d:%02d.%09lu ns%8x       %c%8x\t";
+	len += snprintf(fnic_dbgfs_prt->buffer + len,
+		(fnic_fc_trace_max_pages * PAGE_SIZE * 3) - len,
+		fmt,
+		tm.tm_mon + 1, tm.tm_mday, tm.tm_year + 1900,
+		tm.tm_hour, tm.tm_min, tm.tm_sec,
+		tdata->time_stamp.tv_nsec, tdata->host_no,
+		tdata->frame_type, tdata->frame_len);
+
+	fc_trace = (char *)FC_TRACE_ADDRESS(tdata);
+
+	for (j = 0; j < min_t(u8, tdata->frame_len,
+		(u8)(FC_TRC_SIZE_BYTES - FC_TRC_HEADER_SIZE)); j++) {
+		if (tdata->frame_type == FNIC_FC_LE) {
+			len += snprintf(fnic_dbgfs_prt->buffer + len,
+				max_size - len, "%c", fc_trace[j]);
+		} else {
+			len += snprintf(fnic_dbgfs_prt->buffer + len,
+				max_size - len, "%02x", fc_trace[j] & 0xff);
+			len += snprintf(fnic_dbgfs_prt->buffer + len,
+				max_size - len, " ");
+			if (j == ethhdr_len ||
+				j == ethhdr_len + fcoehdr_len ||
+				j == ethhdr_len + fcoehdr_len + fchdr_len ||
+				(i > 3 && j%fchdr_len == 0)) {
+				len += snprintf(fnic_dbgfs_prt->buffer
+					+ len, (fnic_fc_trace_max_pages
+					* PAGE_SIZE * 3) - len,
+					"\n\t\t\t\t\t\t\t\t");
+				i++;
+			}
+		} /* end of else*/
+	} /* End of for loop*/
+	len += snprintf(fnic_dbgfs_prt->buffer + len,
+		max_size - len, "\n");
+	*orig_len = len;
+}
diff --git a/drivers/scsi/fnic/fnic_trace.h b/drivers/scsi/fnic/fnic_trace.h
index d412f2ee3c4..a8aa0578fcb 100644
--- a/drivers/scsi/fnic/fnic_trace.h
+++ b/drivers/scsi/fnic/fnic_trace.h
@@ -19,6 +19,17 @@
 #define __FNIC_TRACE_H__
 
 #define FNIC_ENTRY_SIZE_BYTES 64
+#define FC_TRC_SIZE_BYTES 256
+#define FC_TRC_HEADER_SIZE sizeof(struct fc_trace_hdr)
+
+/*
+ * Fisrt bit of FNIC_FC_RECV and FNIC_FC_SEND is used to represent the type
+ * of frame 1 => Eth frame, 0=> FC frame
+ */
+
+#define FNIC_FC_RECV 0x52 /* Character R */
+#define FNIC_FC_SEND 0x54 /* Character T */
+#define FNIC_FC_LE 0x4C /* Character L */
 
 extern ssize_t simple_read_from_buffer(void __user *to,
 					  size_t count,
@@ -30,6 +41,10 @@ extern unsigned int fnic_trace_max_pages;
 extern int fnic_tracing_enabled;
 extern unsigned int trace_max_pages;
 
+extern unsigned int fnic_fc_trace_max_pages;
+extern int fnic_fc_tracing_enabled;
+extern int fnic_fc_trace_cleared;
+
 typedef struct fnic_trace_dbg {
 	int wr_idx;
 	int rd_idx;
@@ -56,6 +71,16 @@ struct fnic_trace_data {
 
 typedef struct fnic_trace_data fnic_trace_data_t;
 
+struct fc_trace_hdr {
+	struct timespec time_stamp;
+	u32 host_no;
+	u8 frame_type;
+	u8 frame_len;
+} __attribute__((__packed__));
+
+#define FC_TRACE_ADDRESS(a) \
+	((unsigned long)(a) + sizeof(struct fc_trace_hdr))
+
 #define FNIC_TRACE_ENTRY_SIZE \
 		  (FNIC_ENTRY_SIZE_BYTES - sizeof(fnic_trace_data_t))
 
@@ -88,4 +113,17 @@ int fnic_debugfs_init(void);
 void fnic_debugfs_terminate(void);
 int fnic_trace_debugfs_init(void);
 void fnic_trace_debugfs_terminate(void);
+
+/* Fnic FC CTLR Trace releated function */
+int fnic_fc_trace_init(void);
+void fnic_fc_trace_free(void);
+int fnic_fc_trace_set_data(u32 host_no, u8 frame_type,
+				char *frame, u32 fc_frame_len);
+int fnic_fc_trace_get_data(fnic_dbgfs_t *fnic_dbgfs_prt, u8 rdata_flag);
+void copy_and_format_trace_data(struct fc_trace_hdr *tdata,
+				fnic_dbgfs_t *fnic_dbgfs_prt,
+				int *len, u8 rdata_flag);
+int fnic_fc_trace_debugfs_init(void);
+void fnic_fc_trace_debugfs_terminate(void);
+
 #endif
diff --git a/drivers/scsi/g_NCR5380.c b/drivers/scsi/g_NCR5380.c
index 7176365e916..a1bc8ca958e 100644
--- a/drivers/scsi/g_NCR5380.c
+++ b/drivers/scsi/g_NCR5380.c
@@ -78,10 +78,6 @@
  *     
  */
 
-/*
- * $Log: generic_NCR5380.c,v $
- */
-
 /* settings for DTC3181E card with only Mustek scanner attached */
 #define USLEEP
 #define USLEEP_POLL	1
diff --git a/drivers/scsi/g_NCR5380.h b/drivers/scsi/g_NCR5380.h
index 1bcdb7beb77..703adf78e0b 100644
--- a/drivers/scsi/g_NCR5380.h
+++ b/drivers/scsi/g_NCR5380.h
@@ -25,10 +25,6 @@
  * 1+ (800) 334-5454
  */
 
-/*
- * $Log: generic_NCR5380.h,v $
- */
-
 #ifndef GENERIC_NCR5380_H
 #define GENERIC_NCR5380_H
 
@@ -58,8 +54,6 @@ static const char* generic_NCR5380_info(struct Scsi_Host *);
 #define CAN_QUEUE 16
 #endif
 
-#ifndef HOSTS_C
-
 #define __STRVAL(x) #x
 #define STRVAL(x) __STRVAL(x)
 
@@ -131,7 +125,6 @@ static const char* generic_NCR5380_info(struct Scsi_Host *);
 #define BOARD_NCR53C400A 2
 #define BOARD_DTC3181E	3
 
-#endif /* else def HOSTS_C */
 #endif /* ndef ASM */
 #endif /* GENERIC_NCR5380_H */
 
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 9a6e4a2cd07..31184b35370 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -48,6 +48,7 @@
 #include <linux/bitmap.h>
 #include <linux/atomic.h>
 #include <linux/jiffies.h>
+#include <linux/percpu.h>
 #include <asm/div64.h>
 #include "hpsa_cmd.h"
 #include "hpsa.h"
@@ -115,9 +116,15 @@ static const struct pci_device_id hpsa_pci_device_id[] = {
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C3},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C4},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C5},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C6},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C7},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C8},
 	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21C9},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CA},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CB},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CC},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CD},
+	{PCI_VENDOR_ID_HP,     PCI_DEVICE_ID_HP_CISSI,     0x103C, 0x21CE},
 	{PCI_VENDOR_ID_HP_3PAR, 0x0075, 0x1590, 0x0076},
 	{PCI_VENDOR_ID_HP_3PAR, 0x0075, 0x1590, 0x0087},
 	{PCI_VENDOR_ID_HP_3PAR, 0x0075, 0x1590, 0x007D},
@@ -165,9 +172,15 @@ static struct board_type products[] = {
 	{0x21C3103C, "Smart Array", &SA5_access},
 	{0x21C4103C, "Smart Array", &SA5_access},
 	{0x21C5103C, "Smart Array", &SA5_access},
+	{0x21C6103C, "Smart Array", &SA5_access},
 	{0x21C7103C, "Smart Array", &SA5_access},
 	{0x21C8103C, "Smart Array", &SA5_access},
 	{0x21C9103C, "Smart Array", &SA5_access},
+	{0x21CA103C, "Smart Array", &SA5_access},
+	{0x21CB103C, "Smart Array", &SA5_access},
+	{0x21CC103C, "Smart Array", &SA5_access},
+	{0x21CD103C, "Smart Array", &SA5_access},
+	{0x21CE103C, "Smart Array", &SA5_access},
 	{0x00761590, "HP Storage P1224 Array Controller", &SA5_access},
 	{0x00871590, "HP Storage P1224e Array Controller", &SA5_access},
 	{0x007D1590, "HP Storage P1228 Array Controller", &SA5_access},
@@ -181,7 +194,8 @@ static int number_of_controllers;
 static irqreturn_t do_hpsa_intr_intx(int irq, void *dev_id);
 static irqreturn_t do_hpsa_intr_msi(int irq, void *dev_id);
 static int hpsa_ioctl(struct scsi_device *dev, int cmd, void *arg);
-static void start_io(struct ctlr_info *h);
+static void lock_and_start_io(struct ctlr_info *h);
+static void start_io(struct ctlr_info *h, unsigned long *flags);
 
 #ifdef CONFIG_COMPAT
 static int hpsa_compat_ioctl(struct scsi_device *dev, int cmd, void *arg);
@@ -683,7 +697,7 @@ static inline void addQ(struct list_head *list, struct CommandList *c)
 static inline u32 next_command(struct ctlr_info *h, u8 q)
 {
 	u32 a;
-	struct reply_pool *rq = &h->reply_queue[q];
+	struct reply_queue_buffer *rq = &h->reply_queue[q];
 	unsigned long flags;
 
 	if (h->transMethod & CFGTBL_Trans_io_accel1)
@@ -832,8 +846,8 @@ static void enqueue_cmd_and_start_io(struct ctlr_info *h,
 	spin_lock_irqsave(&h->lock, flags);
 	addQ(&h->reqQ, c);
 	h->Qdepth++;
+	start_io(h, &flags);
 	spin_unlock_irqrestore(&h->lock, flags);
-	start_io(h);
 }
 
 static inline void removeQ(struct CommandList *c)
@@ -1542,9 +1556,13 @@ static int handle_ioaccel_mode2_error(struct ctlr_info *h,
 			dev_warn(&h->pdev->dev,
 				"%s: task complete with check condition.\n",
 				"HP SSD Smart Path");
+			cmd->result |= SAM_STAT_CHECK_CONDITION;
 			if (c2->error_data.data_present !=
-					IOACCEL2_SENSE_DATA_PRESENT)
+					IOACCEL2_SENSE_DATA_PRESENT) {
+				memset(cmd->sense_buffer, 0,
+					SCSI_SENSE_BUFFERSIZE);
 				break;
+			}
 			/* copy the sense data */
 			data_len = c2->error_data.sense_data_len;
 			if (data_len > SCSI_SENSE_BUFFERSIZE)
@@ -1554,7 +1572,6 @@ static int handle_ioaccel_mode2_error(struct ctlr_info *h,
 					sizeof(c2->error_data.sense_data_buff);
 			memcpy(cmd->sense_buffer,
 				c2->error_data.sense_data_buff, data_len);
-			cmd->result |= SAM_STAT_CHECK_CONDITION;
 			retry = 1;
 			break;
 		case IOACCEL2_STATUS_SR_TASK_COMP_BUSY:
@@ -1639,16 +1656,6 @@ static void process_ioaccel2_completion(struct ctlr_info *h,
 	if (is_logical_dev_addr_mode(dev->scsi3addr) &&
 		c2->error_data.serv_response ==
 			IOACCEL2_SERV_RESPONSE_FAILURE) {
-		if (c2->error_data.status ==
-			IOACCEL2_STATUS_SR_IOACCEL_DISABLED)
-			dev_warn(&h->pdev->dev,
-				"%s: Path is unavailable, retrying on standard path.\n",
-				"HP SSD Smart Path");
-		else
-			dev_warn(&h->pdev->dev,
-				"%s: Error 0x%02x, retrying on standard path.\n",
-				"HP SSD Smart Path", c2->error_data.status);
-
 		dev->offload_enabled = 0;
 		h->drv_req_rescan = 1;	/* schedule controller for a rescan */
 		cmd->result = DID_SOFT_ERROR << 16;
@@ -1979,20 +1986,26 @@ static inline void hpsa_scsi_do_simple_cmd_core(struct ctlr_info *h,
 	wait_for_completion(&wait);
 }
 
+static u32 lockup_detected(struct ctlr_info *h)
+{
+	int cpu;
+	u32 rc, *lockup_detected;
+
+	cpu = get_cpu();
+	lockup_detected = per_cpu_ptr(h->lockup_detected, cpu);
+	rc = *lockup_detected;
+	put_cpu();
+	return rc;
+}
+
 static void hpsa_scsi_do_simple_cmd_core_if_no_lockup(struct ctlr_info *h,
 	struct CommandList *c)
 {
-	unsigned long flags;
-
 	/* If controller lockup detected, fake a hardware error. */
-	spin_lock_irqsave(&h->lock, flags);
-	if (unlikely(h->lockup_detected)) {
-		spin_unlock_irqrestore(&h->lock, flags);
+	if (unlikely(lockup_detected(h)))
 		c->err_info->CommandStatus = CMD_HARDWARE_ERR;
-	} else {
-		spin_unlock_irqrestore(&h->lock, flags);
+	else
 		hpsa_scsi_do_simple_cmd_core(h, c);
-	}
 }
 
 #define MAX_DRIVER_CMD_RETRIES 25
@@ -2417,7 +2430,7 @@ static int hpsa_get_device_id(struct ctlr_info *h, unsigned char *scsi3addr,
 		buflen = 16;
 	buf = kzalloc(64, GFP_KERNEL);
 	if (!buf)
-		return -1;
+		return -ENOMEM;
 	rc = hpsa_scsi_do_inquiry(h, scsi3addr, VPD_PAGE | 0x83, buf, 64);
 	if (rc == 0)
 		memcpy(device_id, &buf[8], buflen);
@@ -2503,27 +2516,21 @@ static int hpsa_get_volume_status(struct ctlr_info *h,
 		return HPSA_VPD_LV_STATUS_UNSUPPORTED;
 
 	/* Does controller have VPD for logical volume status? */
-	if (!hpsa_vpd_page_supported(h, scsi3addr, HPSA_VPD_LV_STATUS)) {
-		dev_warn(&h->pdev->dev, "Logical volume status VPD page is unsupported.\n");
+	if (!hpsa_vpd_page_supported(h, scsi3addr, HPSA_VPD_LV_STATUS))
 		goto exit_failed;
-	}
 
 	/* Get the size of the VPD return buffer */
 	rc = hpsa_scsi_do_inquiry(h, scsi3addr, VPD_PAGE | HPSA_VPD_LV_STATUS,
 					buf, HPSA_VPD_HEADER_SZ);
-	if (rc != 0) {
-		dev_warn(&h->pdev->dev, "Logical volume status VPD inquiry failed.\n");
+	if (rc != 0)
 		goto exit_failed;
-	}
 	size = buf[3];
 
 	/* Now get the whole VPD buffer */
 	rc = hpsa_scsi_do_inquiry(h, scsi3addr, VPD_PAGE | HPSA_VPD_LV_STATUS,
 					buf, size + HPSA_VPD_HEADER_SZ);
-	if (rc != 0) {
-		dev_warn(&h->pdev->dev, "Logical volume status VPD inquiry failed.\n");
+	if (rc != 0)
 		goto exit_failed;
-	}
 	status = buf[4]; /* status byte */
 
 	kfree(buf);
@@ -2536,11 +2543,11 @@ exit_failed:
 /* Determine offline status of a volume.
  * Return either:
  *  0 (not offline)
- * -1 (offline for unknown reasons)
+ *  0xff (offline for unknown reasons)
  *  # (integer code indicating one of several NOT READY states
  *     describing why a volume is to be kept offline)
  */
-static unsigned char hpsa_volume_offline(struct ctlr_info *h,
+static int hpsa_volume_offline(struct ctlr_info *h,
 					unsigned char scsi3addr[])
 {
 	struct CommandList *c;
@@ -2639,11 +2646,15 @@ static int hpsa_update_device_info(struct ctlr_info *h,
 
 	if (this_device->devtype == TYPE_DISK &&
 		is_logical_dev_addr_mode(scsi3addr)) {
+		int volume_offline;
+
 		hpsa_get_raid_level(h, scsi3addr, &this_device->raid_level);
 		if (h->fw_support & MISC_FW_RAID_OFFLOAD_BASIC)
 			hpsa_get_ioaccel_status(h, scsi3addr, this_device);
-		this_device->volume_offline =
-			hpsa_volume_offline(h, scsi3addr);
+		volume_offline = hpsa_volume_offline(h, scsi3addr);
+		if (volume_offline < 0 || volume_offline > 0xff)
+			volume_offline = HPSA_VPD_LV_STATUS_UNSUPPORTED;
+		this_device->volume_offline = volume_offline & 0xff;
 	} else {
 		this_device->raid_level = RAID_UNKNOWN;
 		this_device->offload_config = 0;
@@ -2836,6 +2847,8 @@ static int hpsa_get_pdisk_of_ioaccel2(struct ctlr_info *h,
 
 	/* Get the list of physical devices */
 	physicals = kzalloc(reportsize, GFP_KERNEL);
+	if (physicals == NULL)
+		return 0;
 	if (hpsa_scsi_do_report_phys_luns(h, (struct ReportLUNdata *) physicals,
 		reportsize, extended)) {
 		dev_err(&h->pdev->dev,
@@ -2847,26 +2860,20 @@ static int hpsa_get_pdisk_of_ioaccel2(struct ctlr_info *h,
 	nphysicals = be32_to_cpu(*((__be32 *)physicals->LUNListLength)) /
 							responsesize;
 
-
 	/* find ioaccel2 handle in list of physicals: */
 	for (i = 0; i < nphysicals; i++) {
+		struct ext_report_lun_entry *entry = &physicals->LUN[i];
+
 		/* handle is in bytes 28-31 of each lun */
-		if (memcmp(&((struct ReportExtendedLUNdata *)
-				physicals)->LUN[i][20], &find, 4) != 0) {
+		if (entry->ioaccel_handle != find)
 			continue; /* didn't match */
-		}
 		found = 1;
-		memcpy(scsi3addr, &((struct ReportExtendedLUNdata *)
-					physicals)->LUN[i][0], 8);
+		memcpy(scsi3addr, entry->lunid, 8);
 		if (h->raid_offload_debug > 0)
 			dev_info(&h->pdev->dev,
-				"%s: Searched h=0x%08x, Found h=0x%08x, scsiaddr 0x%02x%02x%02x%02x%02x%02x%02x%02x\n",
+				"%s: Searched h=0x%08x, Found h=0x%08x, scsiaddr 0x%8phN\n",
 				__func__, find,
-				((struct ReportExtendedLUNdata *)
-					physicals)->LUN[i][20],
-				scsi3addr[0], scsi3addr[1], scsi3addr[2],
-				scsi3addr[3], scsi3addr[4], scsi3addr[5],
-				scsi3addr[6], scsi3addr[7]);
+				entry->ioaccel_handle, scsi3addr);
 		break; /* found it */
 	}
 
@@ -2951,7 +2958,8 @@ u8 *figure_lunaddrbytes(struct ctlr_info *h, int raid_ctlr_position, int i,
 		return RAID_CTLR_LUNID;
 
 	if (i < logicals_start)
-		return &physdev_list->LUN[i - (raid_ctlr_position == 0)][0];
+		return &physdev_list->LUN[i -
+				(raid_ctlr_position == 0)].lunid[0];
 
 	if (i < last_device)
 		return &logdev_list->LUN[i - nphysicals -
@@ -2963,19 +2971,24 @@ u8 *figure_lunaddrbytes(struct ctlr_info *h, int raid_ctlr_position, int i,
 static int hpsa_hba_mode_enabled(struct ctlr_info *h)
 {
 	int rc;
+	int hba_mode_enabled;
 	struct bmic_controller_parameters *ctlr_params;
 	ctlr_params = kzalloc(sizeof(struct bmic_controller_parameters),
 		GFP_KERNEL);
 
 	if (!ctlr_params)
-		return 0;
+		return -ENOMEM;
 	rc = hpsa_bmic_ctrl_mode_sense(h, RAID_CTLR_LUNID, 0, ctlr_params,
 		sizeof(struct bmic_controller_parameters));
-	if (rc != 0) {
+	if (rc) {
 		kfree(ctlr_params);
-		return 0;
+		return rc;
 	}
-	return ctlr_params->nvram_flags & (1 << 3) ? 1 : 0;
+
+	hba_mode_enabled =
+		((ctlr_params->nvram_flags & HBA_MODE_ENABLED_FLAG) != 0);
+	kfree(ctlr_params);
+	return hba_mode_enabled;
 }
 
 static void hpsa_update_scsi_devices(struct ctlr_info *h, int hostno)
@@ -3001,7 +3014,7 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h, int hostno)
 	int reportlunsize = sizeof(*physdev_list) + HPSA_MAX_PHYS_LUN * 24;
 	int i, n_ext_target_devs, ndevs_to_allocate;
 	int raid_ctlr_position;
-	u8 rescan_hba_mode;
+	int rescan_hba_mode;
 	DECLARE_BITMAP(lunzerobits, MAX_EXT_TARGETS);
 
 	currentsd = kzalloc(sizeof(*currentsd) * HPSA_MAX_DEVICES, GFP_KERNEL);
@@ -3016,6 +3029,8 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h, int hostno)
 	memset(lunzerobits, 0, sizeof(lunzerobits));
 
 	rescan_hba_mode = hpsa_hba_mode_enabled(h);
+	if (rescan_hba_mode < 0)
+		goto out;
 
 	if (!h->hba_mode_enabled && rescan_hba_mode)
 		dev_warn(&h->pdev->dev, "HBA mode enabled\n");
@@ -3053,7 +3068,7 @@ static void hpsa_update_scsi_devices(struct ctlr_info *h, int hostno)
 		ndev_allocated++;
 	}
 
-	if (unlikely(is_scsi_rev_5(h)))
+	if (is_scsi_rev_5(h))
 		raid_ctlr_position = 0;
 	else
 		raid_ctlr_position = nphysicals + nlogicals;
@@ -3950,7 +3965,6 @@ static int hpsa_scsi_queue_command_lck(struct scsi_cmnd *cmd,
 	struct hpsa_scsi_dev_t *dev;
 	unsigned char scsi3addr[8];
 	struct CommandList *c;
-	unsigned long flags;
 	int rc = 0;
 
 	/* Get the ptr to our adapter structure out of cmd->host. */
@@ -3963,14 +3977,11 @@ static int hpsa_scsi_queue_command_lck(struct scsi_cmnd *cmd,
 	}
 	memcpy(scsi3addr, dev->scsi3addr, sizeof(scsi3addr));
 
-	spin_lock_irqsave(&h->lock, flags);
-	if (unlikely(h->lockup_detected)) {
-		spin_unlock_irqrestore(&h->lock, flags);
+	if (unlikely(lockup_detected(h))) {
 		cmd->result = DID_ERROR << 16;
 		done(cmd);
 		return 0;
 	}
-	spin_unlock_irqrestore(&h->lock, flags);
 	c = cmd_alloc(h);
 	if (c == NULL) {			/* trouble... */
 		dev_err(&h->pdev->dev, "cmd_alloc returned NULL!\n");
@@ -4082,16 +4093,13 @@ static int do_not_scan_if_controller_locked_up(struct ctlr_info *h)
 	 * we can prevent new rescan threads from piling up on a
 	 * locked up controller.
 	 */
-	spin_lock_irqsave(&h->lock, flags);
-	if (unlikely(h->lockup_detected)) {
-		spin_unlock_irqrestore(&h->lock, flags);
+	if (unlikely(lockup_detected(h))) {
 		spin_lock_irqsave(&h->scan_lock, flags);
 		h->scan_finished = 1;
 		wake_up_all(&h->scan_wait_queue);
 		spin_unlock_irqrestore(&h->scan_lock, flags);
 		return 1;
 	}
-	spin_unlock_irqrestore(&h->lock, flags);
 	return 0;
 }
 
@@ -4942,7 +4950,7 @@ static int hpsa_passthru_ioctl(struct ctlr_info *h, void __user *argp)
 		buff = kmalloc(iocommand.buf_size, GFP_KERNEL);
 		if (buff == NULL)
 			return -EFAULT;
-		if (iocommand.Request.Type.Direction == XFER_WRITE) {
+		if (iocommand.Request.Type.Direction & XFER_WRITE) {
 			/* Copy the data into the buffer we created */
 			if (copy_from_user(buff, iocommand.buf,
 				iocommand.buf_size)) {
@@ -5005,7 +5013,7 @@ static int hpsa_passthru_ioctl(struct ctlr_info *h, void __user *argp)
 		rc = -EFAULT;
 		goto out;
 	}
-	if (iocommand.Request.Type.Direction == XFER_READ &&
+	if ((iocommand.Request.Type.Direction & XFER_READ) &&
 		iocommand.buf_size > 0) {
 		/* Copy the data out of the buffer we created */
 		if (copy_to_user(iocommand.buf, buff, iocommand.buf_size)) {
@@ -5082,7 +5090,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp)
 			status = -ENOMEM;
 			goto cleanup1;
 		}
-		if (ioc->Request.Type.Direction == XFER_WRITE) {
+		if (ioc->Request.Type.Direction & XFER_WRITE) {
 			if (copy_from_user(buff[sg_used], data_ptr, sz)) {
 				status = -ENOMEM;
 				goto cleanup1;
@@ -5134,7 +5142,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp)
 		status = -EFAULT;
 		goto cleanup0;
 	}
-	if (ioc->Request.Type.Direction == XFER_READ && ioc->buf_size > 0) {
+	if ((ioc->Request.Type.Direction & XFER_READ) && ioc->buf_size > 0) {
 		/* Copy the data out of the buffer we created */
 		BYTE __user *ptr = ioc->buf;
 		for (i = 0; i < sg_used; i++) {
@@ -5438,13 +5446,12 @@ static void __iomem *remap_pci_mem(ulong base, ulong size)
 
 /* Takes cmds off the submission queue and sends them to the hardware,
  * then puts them on the queue of cmds waiting for completion.
+ * Assumes h->lock is held
  */
-static void start_io(struct ctlr_info *h)
+static void start_io(struct ctlr_info *h, unsigned long *flags)
 {
 	struct CommandList *c;
-	unsigned long flags;
 
-	spin_lock_irqsave(&h->lock, flags);
 	while (!list_empty(&h->reqQ)) {
 		c = list_entry(h->reqQ.next, struct CommandList, list);
 		/* can't do anything if fifo is full */
@@ -5467,14 +5474,20 @@ static void start_io(struct ctlr_info *h)
 		 * condition.
 		 */
 		h->commands_outstanding++;
-		if (h->commands_outstanding > h->max_outstanding)
-			h->max_outstanding = h->commands_outstanding;
 
 		/* Tell the controller execute command */
-		spin_unlock_irqrestore(&h->lock, flags);
+		spin_unlock_irqrestore(&h->lock, *flags);
 		h->access.submit_command(h, c);
-		spin_lock_irqsave(&h->lock, flags);
+		spin_lock_irqsave(&h->lock, *flags);
 	}
+}
+
+static void lock_and_start_io(struct ctlr_info *h)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&h->lock, flags);
+	start_io(h, &flags);
 	spin_unlock_irqrestore(&h->lock, flags);
 }
 
@@ -5542,7 +5555,7 @@ static inline void finish_cmd(struct CommandList *c)
 	else if (c->cmd_type == CMD_IOCTL_PEND)
 		complete(c->waiting);
 	if (unlikely(io_may_be_stalled))
-		start_io(h);
+		lock_and_start_io(h);
 }
 
 static inline u32 hpsa_tag_contains_index(u32 tag)
@@ -5819,12 +5832,12 @@ static int hpsa_controller_hard_reset(struct pci_dev *pdev,
 		dev_info(&pdev->dev, "using doorbell to reset controller\n");
 		writel(use_doorbell, vaddr + SA5_DOORBELL);
 
-		/* PMC hardware guys tell us we need a 5 second delay after
+		/* PMC hardware guys tell us we need a 10 second delay after
 		 * doorbell reset and before any attempt to talk to the board
 		 * at all to ensure that this actually works and doesn't fall
 		 * over in some weird corner cases.
 		 */
-		msleep(5000);
+		msleep(10000);
 	} else { /* Try to do it the PCI power state way */
 
 		/* Quoting from the Open CISS Specification: "The Power
@@ -6145,6 +6158,8 @@ static void hpsa_interrupt_mode(struct ctlr_info *h)
 	if (pci_find_capability(h->pdev, PCI_CAP_ID_MSIX)) {
 		dev_info(&h->pdev->dev, "MSIX\n");
 		h->msix_vector = MAX_REPLY_QUEUES;
+		if (h->msix_vector > num_online_cpus())
+			h->msix_vector = num_online_cpus();
 		err = pci_enable_msix(h->pdev, hpsa_msix_entries,
 				      h->msix_vector);
 		if (err > 0) {
@@ -6594,6 +6609,17 @@ static void hpsa_free_cmd_pool(struct ctlr_info *h)
 			h->ioaccel_cmd_pool, h->ioaccel_cmd_pool_dhandle);
 }
 
+static void hpsa_irq_affinity_hints(struct ctlr_info *h)
+{
+	int i, cpu, rc;
+
+	cpu = cpumask_first(cpu_online_mask);
+	for (i = 0; i < h->msix_vector; i++) {
+		rc = irq_set_affinity_hint(h->intr[i], get_cpu_mask(cpu));
+		cpu = cpumask_next(cpu, cpu_online_mask);
+	}
+}
+
 static int hpsa_request_irq(struct ctlr_info *h,
 	irqreturn_t (*msixhandler)(int, void *),
 	irqreturn_t (*intxhandler)(int, void *))
@@ -6613,6 +6639,7 @@ static int hpsa_request_irq(struct ctlr_info *h,
 			rc = request_irq(h->intr[i], msixhandler,
 					0, h->devname,
 					&h->q[i]);
+		hpsa_irq_affinity_hints(h);
 	} else {
 		/* Use single reply pool */
 		if (h->msix_vector > 0 || h->msi_vector) {
@@ -6664,12 +6691,15 @@ static void free_irqs(struct ctlr_info *h)
 	if (!h->msix_vector || h->intr_mode != PERF_MODE_INT) {
 		/* Single reply queue, only one irq to free */
 		i = h->intr_mode;
+		irq_set_affinity_hint(h->intr[i], NULL);
 		free_irq(h->intr[i], &h->q[i]);
 		return;
 	}
 
-	for (i = 0; i < h->msix_vector; i++)
+	for (i = 0; i < h->msix_vector; i++) {
+		irq_set_affinity_hint(h->intr[i], NULL);
 		free_irq(h->intr[i], &h->q[i]);
+	}
 }
 
 static void hpsa_free_irqs_and_disable_msix(struct ctlr_info *h)
@@ -6686,6 +6716,20 @@ static void hpsa_free_irqs_and_disable_msix(struct ctlr_info *h)
 #endif /* CONFIG_PCI_MSI */
 }
 
+static void hpsa_free_reply_queues(struct ctlr_info *h)
+{
+	int i;
+
+	for (i = 0; i < h->nreply_queues; i++) {
+		if (!h->reply_queue[i].head)
+			continue;
+		pci_free_consistent(h->pdev, h->reply_queue_size,
+			h->reply_queue[i].head, h->reply_queue[i].busaddr);
+		h->reply_queue[i].head = NULL;
+		h->reply_queue[i].busaddr = 0;
+	}
+}
+
 static void hpsa_undo_allocations_after_kdump_soft_reset(struct ctlr_info *h)
 {
 	hpsa_free_irqs_and_disable_msix(h);
@@ -6693,8 +6737,7 @@ static void hpsa_undo_allocations_after_kdump_soft_reset(struct ctlr_info *h)
 	hpsa_free_cmd_pool(h);
 	kfree(h->ioaccel1_blockFetchTable);
 	kfree(h->blockFetchTable);
-	pci_free_consistent(h->pdev, h->reply_pool_size,
-		h->reply_pool, h->reply_pool_dhandle);
+	hpsa_free_reply_queues(h);
 	if (h->vaddr)
 		iounmap(h->vaddr);
 	if (h->transtable)
@@ -6719,16 +6762,38 @@ static void fail_all_cmds_on_list(struct ctlr_info *h, struct list_head *list)
 	}
 }
 
+static void set_lockup_detected_for_all_cpus(struct ctlr_info *h, u32 value)
+{
+	int i, cpu;
+
+	cpu = cpumask_first(cpu_online_mask);
+	for (i = 0; i < num_online_cpus(); i++) {
+		u32 *lockup_detected;
+		lockup_detected = per_cpu_ptr(h->lockup_detected, cpu);
+		*lockup_detected = value;
+		cpu = cpumask_next(cpu, cpu_online_mask);
+	}
+	wmb(); /* be sure the per-cpu variables are out to memory */
+}
+
 static void controller_lockup_detected(struct ctlr_info *h)
 {
 	unsigned long flags;
+	u32 lockup_detected;
 
 	h->access.set_intr_mask(h, HPSA_INTR_OFF);
 	spin_lock_irqsave(&h->lock, flags);
-	h->lockup_detected = readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
+	lockup_detected = readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
+	if (!lockup_detected) {
+		/* no heartbeat, but controller gave us a zero. */
+		dev_warn(&h->pdev->dev,
+			"lockup detected but scratchpad register is zero\n");
+		lockup_detected = 0xffffffff;
+	}
+	set_lockup_detected_for_all_cpus(h, lockup_detected);
 	spin_unlock_irqrestore(&h->lock, flags);
 	dev_warn(&h->pdev->dev, "Controller lockup detected: 0x%08x\n",
-			h->lockup_detected);
+			lockup_detected);
 	pci_disable_device(h->pdev);
 	spin_lock_irqsave(&h->lock, flags);
 	fail_all_cmds_on_list(h, &h->cmpQ);
@@ -6863,7 +6928,7 @@ static void hpsa_monitor_ctlr_worker(struct work_struct *work)
 	struct ctlr_info *h = container_of(to_delayed_work(work),
 					struct ctlr_info, monitor_ctlr_work);
 	detect_controller_lockup(h);
-	if (h->lockup_detected)
+	if (lockup_detected(h))
 		return;
 
 	if (hpsa_ctlr_needs_rescan(h) || hpsa_offline_devices_ready(h)) {
@@ -6913,7 +6978,6 @@ reinit_after_soft_reset:
 	 * the 5 lower bits of the address are used by the hardware. and by
 	 * the driver.  See comments in hpsa.h for more info.
 	 */
-#define COMMANDLIST_ALIGNMENT 128
 	BUILD_BUG_ON(sizeof(struct CommandList) % COMMANDLIST_ALIGNMENT);
 	h = kzalloc(sizeof(*h), GFP_KERNEL);
 	if (!h)
@@ -6928,6 +6992,13 @@ reinit_after_soft_reset:
 	spin_lock_init(&h->offline_device_lock);
 	spin_lock_init(&h->scan_lock);
 	spin_lock_init(&h->passthru_count_lock);
+
+	/* Allocate and clear per-cpu variable lockup_detected */
+	h->lockup_detected = alloc_percpu(u32);
+	if (!h->lockup_detected)
+		goto clean1;
+	set_lockup_detected_for_all_cpus(h, 0);
+
 	rc = hpsa_pci_init(h);
 	if (rc != 0)
 		goto clean1;
@@ -7051,6 +7122,8 @@ clean4:
 	free_irqs(h);
 clean2:
 clean1:
+	if (h->lockup_detected)
+		free_percpu(h->lockup_detected);
 	kfree(h);
 	return rc;
 }
@@ -7059,16 +7132,10 @@ static void hpsa_flush_cache(struct ctlr_info *h)
 {
 	char *flush_buf;
 	struct CommandList *c;
-	unsigned long flags;
 
 	/* Don't bother trying to flush the cache if locked up */
-	spin_lock_irqsave(&h->lock, flags);
-	if (unlikely(h->lockup_detected)) {
-		spin_unlock_irqrestore(&h->lock, flags);
+	if (unlikely(lockup_detected(h)))
 		return;
-	}
-	spin_unlock_irqrestore(&h->lock, flags);
-
 	flush_buf = kzalloc(4, GFP_KERNEL);
 	if (!flush_buf)
 		return;
@@ -7144,8 +7211,7 @@ static void hpsa_remove_one(struct pci_dev *pdev)
 	pci_free_consistent(h->pdev,
 		h->nr_cmds * sizeof(struct ErrorInfo),
 		h->errinfo_pool, h->errinfo_pool_dhandle);
-	pci_free_consistent(h->pdev, h->reply_pool_size,
-		h->reply_pool, h->reply_pool_dhandle);
+	hpsa_free_reply_queues(h);
 	kfree(h->cmd_pool_bits);
 	kfree(h->blockFetchTable);
 	kfree(h->ioaccel1_blockFetchTable);
@@ -7153,6 +7219,7 @@ static void hpsa_remove_one(struct pci_dev *pdev)
 	kfree(h->hba_inquiry_data);
 	pci_disable_device(pdev);
 	pci_release_regions(pdev);
+	free_percpu(h->lockup_detected);
 	kfree(h);
 }
 
@@ -7257,8 +7324,16 @@ static void hpsa_enter_performant_mode(struct ctlr_info *h, u32 trans_support)
 	 * 10 = 6 s/g entry or 24k
 	 */
 
+	/* If the controller supports either ioaccel method then
+	 * we can also use the RAID stack submit path that does not
+	 * perform the superfluous readl() after each command submission.
+	 */
+	if (trans_support & (CFGTBL_Trans_io_accel1 | CFGTBL_Trans_io_accel2))
+		access = SA5_performant_access_no_read;
+
 	/* Controller spec: zero out this buffer. */
-	memset(h->reply_pool, 0, h->reply_pool_size);
+	for (i = 0; i < h->nreply_queues; i++)
+		memset(h->reply_queue[i].head, 0, h->reply_queue_size);
 
 	bft[7] = SG_ENTRIES_IN_CMD + 4;
 	calc_bucket_map(bft, ARRAY_SIZE(bft),
@@ -7274,8 +7349,7 @@ static void hpsa_enter_performant_mode(struct ctlr_info *h, u32 trans_support)
 
 	for (i = 0; i < h->nreply_queues; i++) {
 		writel(0, &h->transtable->RepQAddr[i].upper);
-		writel(h->reply_pool_dhandle +
-			(h->max_commands * sizeof(u64) * i),
+		writel(h->reply_queue[i].busaddr,
 			&h->transtable->RepQAddr[i].lower);
 	}
 
@@ -7323,8 +7397,10 @@ static void hpsa_enter_performant_mode(struct ctlr_info *h, u32 trans_support)
 				h->ioaccel1_blockFetchTable);
 
 		/* initialize all reply queue entries to unused */
-		memset(h->reply_pool, (u8) IOACCEL_MODE1_REPLY_UNUSED,
-				h->reply_pool_size);
+		for (i = 0; i < h->nreply_queues; i++)
+			memset(h->reply_queue[i].head,
+				(u8) IOACCEL_MODE1_REPLY_UNUSED,
+				h->reply_queue_size);
 
 		/* set all the constant fields in the accelerator command
 		 * frames once at init time to save CPU cycles later.
@@ -7386,7 +7462,6 @@ static int hpsa_alloc_ioaccel_cmd_and_bft(struct ctlr_info *h)
 	 * because the 7 lower bits of the address are used by the
 	 * hardware.
 	 */
-#define IOACCEL1_COMMANDLIST_ALIGNMENT 128
 	BUILD_BUG_ON(sizeof(struct io_accel1_cmd) %
 			IOACCEL1_COMMANDLIST_ALIGNMENT);
 	h->ioaccel_cmd_pool =
@@ -7424,7 +7499,6 @@ static int ioaccel2_alloc_cmds_and_bft(struct ctlr_info *h)
 	if (h->ioaccel_maxsg > IOACCEL2_MAXSGENTRIES)
 		h->ioaccel_maxsg = IOACCEL2_MAXSGENTRIES;
 
-#define IOACCEL2_COMMANDLIST_ALIGNMENT 128
 	BUILD_BUG_ON(sizeof(struct io_accel2_cmd) %
 			IOACCEL2_COMMANDLIST_ALIGNMENT);
 	h->ioaccel2_cmd_pool =
@@ -7482,16 +7556,17 @@ static void hpsa_put_ctlr_into_performant_mode(struct ctlr_info *h)
 		}
 	}
 
-	/* TODO, check that this next line h->nreply_queues is correct */
 	h->nreply_queues = h->msix_vector > 0 ? h->msix_vector : 1;
 	hpsa_get_max_perf_mode_cmds(h);
 	/* Performant mode ring buffer and supporting data structures */
-	h->reply_pool_size = h->max_commands * sizeof(u64) * h->nreply_queues;
-	h->reply_pool = pci_alloc_consistent(h->pdev, h->reply_pool_size,
-				&(h->reply_pool_dhandle));
+	h->reply_queue_size = h->max_commands * sizeof(u64);
 
 	for (i = 0; i < h->nreply_queues; i++) {
-		h->reply_queue[i].head = &h->reply_pool[h->max_commands * i];
+		h->reply_queue[i].head = pci_alloc_consistent(h->pdev,
+						h->reply_queue_size,
+						&(h->reply_queue[i].busaddr));
+		if (!h->reply_queue[i].head)
+			goto clean_up;
 		h->reply_queue[i].size = h->max_commands;
 		h->reply_queue[i].wraparound = 1;  /* spec: init to 1 */
 		h->reply_queue[i].current_entry = 0;
@@ -7500,18 +7575,14 @@ static void hpsa_put_ctlr_into_performant_mode(struct ctlr_info *h)
 	/* Need a block fetch table for performant mode */
 	h->blockFetchTable = kmalloc(((SG_ENTRIES_IN_CMD + 1) *
 				sizeof(u32)), GFP_KERNEL);
-
-	if ((h->reply_pool == NULL)
-		|| (h->blockFetchTable == NULL))
+	if (!h->blockFetchTable)
 		goto clean_up;
 
 	hpsa_enter_performant_mode(h, trans_support);
 	return;
 
 clean_up:
-	if (h->reply_pool)
-		pci_free_consistent(h->pdev, h->reply_pool_size,
-			h->reply_pool, h->reply_pool_dhandle);
+	hpsa_free_reply_queues(h);
 	kfree(h->blockFetchTable);
 }
 
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index 44235a27e1b..24472cec7de 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -57,11 +57,12 @@ struct hpsa_scsi_dev_t {
 
 };
 
-struct reply_pool {
+struct reply_queue_buffer {
 	u64 *head;
 	size_t size;
 	u8 wraparound;
 	u32 current_entry;
+	dma_addr_t busaddr;
 };
 
 #pragma pack(1)
@@ -90,6 +91,7 @@ struct bmic_controller_parameters {
 	u8   automatic_drive_slamming;
 	u8   reserved1;
 	u8   nvram_flags;
+#define HBA_MODE_ENABLED_FLAG (1 << 3)
 	u8   cache_nvram_flags;
 	u8   drive_config_flags;
 	u16  reserved2;
@@ -115,11 +117,8 @@ struct ctlr_info {
 	int 	nr_cmds; /* Number of commands allowed on this controller */
 	struct CfgTable __iomem *cfgtable;
 	int	interrupts_enabled;
-	int	major;
 	int 	max_commands;
 	int	commands_outstanding;
-	int 	max_outstanding; /* Debug */
-	int	usage_count;  /* number of opens all all minor devices */
 #	define PERF_MODE_INT	0
 #	define DOORBELL_INT	1
 #	define SIMPLE_MODE_INT	2
@@ -176,11 +175,9 @@ struct ctlr_info {
 	/*
 	 * Performant mode completion buffers
 	 */
-	u64 *reply_pool;
-	size_t reply_pool_size;
-	struct reply_pool reply_queue[MAX_REPLY_QUEUES];
+	size_t reply_queue_size;
+	struct reply_queue_buffer reply_queue[MAX_REPLY_QUEUES];
 	u8 nreply_queues;
-	dma_addr_t reply_pool_dhandle;
 	u32 *blockFetchTable;
 	u32 *ioaccel1_blockFetchTable;
 	u32 *ioaccel2_blockFetchTable;
@@ -195,7 +192,7 @@ struct ctlr_info {
 	u64 last_heartbeat_timestamp;
 	u32 heartbeat_sample_interval;
 	atomic_t firmware_flash_in_progress;
-	u32 lockup_detected;
+	u32 *lockup_detected;
 	struct delayed_work monitor_ctlr_work;
 	int remove_in_progress;
 	u32 fifo_recently_full;
@@ -232,11 +229,9 @@ struct ctlr_info {
 #define CTLR_STATE_CHANGE_EVENT_AIO_CONFIG_CHANGE	(1 << 31)
 
 #define RESCAN_REQUIRED_EVENT_BITS \
-		(CTLR_STATE_CHANGE_EVENT | \
-		CTLR_ENCLOSURE_HOT_PLUG_EVENT | \
+		(CTLR_ENCLOSURE_HOT_PLUG_EVENT | \
 		CTLR_STATE_CHANGE_EVENT_PHYSICAL_DRV | \
 		CTLR_STATE_CHANGE_EVENT_LOGICAL_DRV | \
-		CTLR_STATE_CHANGE_EVENT_REDUNDANT_CNTRL | \
 		CTLR_STATE_CHANGE_EVENT_AIO_ENABLED_DISABLED | \
 		CTLR_STATE_CHANGE_EVENT_AIO_CONFIG_CHANGE)
 	spinlock_t offline_device_lock;
@@ -345,22 +340,23 @@ struct offline_device_entry {
 static void SA5_submit_command(struct ctlr_info *h,
 	struct CommandList *c)
 {
-	dev_dbg(&h->pdev->dev, "Sending %x, tag = %x\n", c->busaddr,
-		c->Header.Tag.lower);
 	writel(c->busaddr, h->vaddr + SA5_REQUEST_PORT_OFFSET);
 	(void) readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
 }
 
+static void SA5_submit_command_no_read(struct ctlr_info *h,
+	struct CommandList *c)
+{
+	writel(c->busaddr, h->vaddr + SA5_REQUEST_PORT_OFFSET);
+}
+
 static void SA5_submit_command_ioaccel2(struct ctlr_info *h,
 	struct CommandList *c)
 {
-	dev_dbg(&h->pdev->dev, "Sending %x, tag = %x\n", c->busaddr,
-		c->Header.Tag.lower);
 	if (c->cmd_type == CMD_IOACCEL2)
 		writel(c->busaddr, h->vaddr + IOACCEL2_INBOUND_POSTQ_32);
 	else
 		writel(c->busaddr, h->vaddr + SA5_REQUEST_PORT_OFFSET);
-	(void) readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
 }
 
 /*
@@ -398,7 +394,7 @@ static void SA5_performant_intr_mask(struct ctlr_info *h, unsigned long val)
 
 static unsigned long SA5_performant_completed(struct ctlr_info *h, u8 q)
 {
-	struct reply_pool *rq = &h->reply_queue[q];
+	struct reply_queue_buffer *rq = &h->reply_queue[q];
 	unsigned long flags, register_value = FIFO_EMPTY;
 
 	/* msi auto clears the interrupt pending bit. */
@@ -477,7 +473,6 @@ static bool SA5_intr_pending(struct ctlr_info *h)
 {
 	unsigned long register_value  =
 		readl(h->vaddr + SA5_INTR_STATUS);
-	dev_dbg(&h->pdev->dev, "intr_pending %lx\n", register_value);
 	return register_value & SA5_INTR_PENDING;
 }
 
@@ -514,7 +509,7 @@ static bool SA5_ioaccel_mode1_intr_pending(struct ctlr_info *h)
 static unsigned long SA5_ioaccel_mode1_completed(struct ctlr_info *h, u8 q)
 {
 	u64 register_value;
-	struct reply_pool *rq = &h->reply_queue[q];
+	struct reply_queue_buffer *rq = &h->reply_queue[q];
 	unsigned long flags;
 
 	BUG_ON(q >= h->nreply_queues);
@@ -572,6 +567,14 @@ static struct access_method SA5_performant_access = {
 	SA5_performant_completed,
 };
 
+static struct access_method SA5_performant_access_no_read = {
+	SA5_submit_command_no_read,
+	SA5_performant_intr_mask,
+	SA5_fifo_full,
+	SA5_performant_intr_pending,
+	SA5_performant_completed,
+};
+
 struct board_type {
 	u32	board_id;
 	char	*product_name;
diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h
index b5cc7052339..b5125dc3143 100644
--- a/drivers/scsi/hpsa_cmd.h
+++ b/drivers/scsi/hpsa_cmd.h
@@ -151,7 +151,7 @@
 #define HPSA_VPD_HEADER_SZ              4
 
 /* Logical volume states */
-#define HPSA_VPD_LV_STATUS_UNSUPPORTED			-1
+#define HPSA_VPD_LV_STATUS_UNSUPPORTED			0xff
 #define HPSA_LV_OK                                      0x0
 #define HPSA_LV_UNDERGOING_ERASE			0x0F
 #define HPSA_LV_UNDERGOING_RPI				0x12
@@ -238,11 +238,21 @@ struct ReportLUNdata {
 	u8 LUN[HPSA_MAX_LUN][8];
 };
 
+struct ext_report_lun_entry {
+	u8 lunid[8];
+	u8 wwid[8];
+	u8 device_type;
+	u8 device_flags;
+	u8 lun_count; /* multi-lun device, how many luns */
+	u8 redundant_paths;
+	u32 ioaccel_handle; /* ioaccel1 only uses lower 16 bits */
+};
+
 struct ReportExtendedLUNdata {
 	u8 LUNListLength[4];
 	u8 extended_response_flag;
 	u8 reserved[3];
-	u8 LUN[HPSA_MAX_LUN][24];
+	struct ext_report_lun_entry LUN[HPSA_MAX_LUN];
 };
 
 struct SenseSubsystem_info {
@@ -375,6 +385,7 @@ struct ctlr_info; /* defined in hpsa.h */
  *        or a bus address.
  */
 
+#define COMMANDLIST_ALIGNMENT 128
 struct CommandList {
 	struct CommandListHeader Header;
 	struct RequestBlock      Request;
@@ -389,21 +400,7 @@ struct CommandList {
 	struct list_head list;
 	struct completion *waiting;
 	void   *scsi_cmd;
-
-/* on 64 bit architectures, to get this to be 32-byte-aligned
- * it so happens we need PAD_64 bytes of padding, on 32 bit systems,
- * we need PAD_32 bytes of padding (see below).   This does that.
- * If it happens that 64 bit and 32 bit systems need different
- * padding, PAD_32 and PAD_64 can be set independently, and.
- * the code below will do the right thing.
- */
-#define IS_32_BIT ((8 - sizeof(long))/4)
-#define IS_64_BIT (!IS_32_BIT)
-#define PAD_32 (40)
-#define PAD_64 (12)
-#define COMMANDLIST_PAD (IS_32_BIT * PAD_32 + IS_64_BIT * PAD_64)
-	u8 pad[COMMANDLIST_PAD];
-};
+} __aligned(COMMANDLIST_ALIGNMENT);
 
 /* Max S/G elements in I/O accelerator command */
 #define IOACCEL1_MAXSGENTRIES           24
@@ -413,6 +410,7 @@ struct CommandList {
  * Structure for I/O accelerator (mode 1) commands.
  * Note that this structure must be 128-byte aligned in size.
  */
+#define IOACCEL1_COMMANDLIST_ALIGNMENT 128
 struct io_accel1_cmd {
 	u16 dev_handle;			/* 0x00 - 0x01 */
 	u8  reserved1;			/* 0x02 */
@@ -440,12 +438,7 @@ struct io_accel1_cmd {
 	struct vals32 host_addr;	/* 0x70 - 0x77 */
 	u8  CISS_LUN[8];		/* 0x78 - 0x7F */
 	struct SGDescriptor SG[IOACCEL1_MAXSGENTRIES];
-#define IOACCEL1_PAD_64 0
-#define IOACCEL1_PAD_32 0
-#define IOACCEL1_PAD (IS_32_BIT * IOACCEL1_PAD_32 + \
-			IS_64_BIT * IOACCEL1_PAD_64)
-	u8 pad[IOACCEL1_PAD];
-};
+} __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT);
 
 #define IOACCEL1_FUNCTION_SCSIIO        0x00
 #define IOACCEL1_SGLOFFSET              32
@@ -510,14 +503,11 @@ struct io_accel2_scsi_response {
 	u8 sense_data_buff[32];		/* sense/response data buffer */
 };
 
-#define IOACCEL2_64_PAD 76
-#define IOACCEL2_32_PAD 76
-#define IOACCEL2_PAD (IS_32_BIT * IOACCEL2_32_PAD + \
-			IS_64_BIT * IOACCEL2_64_PAD)
 /*
  * Structure for I/O accelerator (mode 2 or m2) commands.
  * Note that this structure must be 128-byte aligned in size.
  */
+#define IOACCEL2_COMMANDLIST_ALIGNMENT 128
 struct io_accel2_cmd {
 	u8  IU_type;			/* IU Type */
 	u8  direction;			/* direction, memtype, and encryption */
@@ -544,8 +534,7 @@ struct io_accel2_cmd {
 	u32 tweak_upper;		/* Encryption tweak, upper 4 bytes */
 	struct ioaccel2_sg_element sg[IOACCEL2_MAXSGENTRIES];
 	struct io_accel2_scsi_response error_data;
-	u8 pad[IOACCEL2_PAD];
-};
+} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
 
 /*
  * defines for Mode 2 command struct
@@ -636,7 +625,7 @@ struct TransTable_struct {
 	u32            RepQCount;
 	u32            RepQCtrAddrLow32;
 	u32            RepQCtrAddrHigh32;
-#define MAX_REPLY_QUEUES 8
+#define MAX_REPLY_QUEUES 64
 	struct vals32  RepQAddr[MAX_REPLY_QUEUES];
 };
 
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 2ebfb2bb0f4..7b23f21f22f 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -185,6 +185,11 @@ static struct viosrp_crq *crq_queue_next_crq(struct crq_queue *queue)
 	if (crq->valid & 0x80) {
 		if (++queue->cur == queue->size)
 			queue->cur = 0;
+
+		/* Ensure the read of the valid bit occurs before reading any
+		 * other bits of the CRQ entry
+		 */
+		rmb();
 	} else
 		crq = NULL;
 	spin_unlock_irqrestore(&queue->lock, flags);
@@ -203,6 +208,11 @@ static int ibmvscsi_send_crq(struct ibmvscsi_host_data *hostdata,
 {
 	struct vio_dev *vdev = to_vio_dev(hostdata->dev);
 
+	/*
+	 * Ensure the command buffer is flushed to memory before handing it
+	 * over to the VIOS to prevent it from fetching any stale data.
+	 */
+	mb();
 	return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, word1, word2);
 }
 
@@ -797,7 +807,8 @@ static void purge_requests(struct ibmvscsi_host_data *hostdata, int error_code)
 				       evt->hostdata->dev);
 			if (evt->cmnd_done)
 				evt->cmnd_done(evt->cmnd);
-		} else if (evt->done)
+		} else if (evt->done && evt->crq.format != VIOSRP_MAD_FORMAT &&
+			   evt->iu.srp.login_req.opcode != SRP_LOGIN_REQ)
 			evt->done(evt);
 		free_event_struct(&evt->hostdata->pool, evt);
 		spin_lock_irqsave(hostdata->host->host_lock, flags);
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 11854845393..a669f2d11c3 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -244,7 +244,7 @@ iscsi_sw_tcp_conn_restore_callbacks(struct iscsi_conn *conn)
 	sk->sk_data_ready   = tcp_sw_conn->old_data_ready;
 	sk->sk_state_change = tcp_sw_conn->old_state_change;
 	sk->sk_write_space  = tcp_sw_conn->old_write_space;
-	sk->sk_no_check	 = 0;
+	sk->sk_no_check_tx = 0;
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 26dc005bb0f..3d1bc67bac9 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -338,7 +338,7 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task)
 	struct iscsi_session *session = conn->session;
 	struct scsi_cmnd *sc = task->sc;
 	struct iscsi_scsi_req *hdr;
-	unsigned hdrlength, cmd_len;
+	unsigned hdrlength, cmd_len, transfer_length;
 	itt_t itt;
 	int rc;
 
@@ -391,11 +391,11 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task)
 	if (scsi_get_prot_op(sc) != SCSI_PROT_NORMAL)
 		task->protected = true;
 
+	transfer_length = scsi_transfer_length(sc);
+	hdr->data_length = cpu_to_be32(transfer_length);
 	if (sc->sc_data_direction == DMA_TO_DEVICE) {
-		unsigned out_len = scsi_out(sc)->length;
 		struct iscsi_r2t_info *r2t = &task->unsol_r2t;
 
-		hdr->data_length = cpu_to_be32(out_len);
 		hdr->flags |= ISCSI_FLAG_CMD_WRITE;
 		/*
 		 * Write counters:
@@ -414,18 +414,19 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task)
 		memset(r2t, 0, sizeof(*r2t));
 
 		if (session->imm_data_en) {
-			if (out_len >= session->first_burst)
+			if (transfer_length >= session->first_burst)
 				task->imm_count = min(session->first_burst,
 							conn->max_xmit_dlength);
 			else
-				task->imm_count = min(out_len,
-							conn->max_xmit_dlength);
+				task->imm_count = min(transfer_length,
+						      conn->max_xmit_dlength);
 			hton24(hdr->dlength, task->imm_count);
 		} else
 			zero_data(hdr->dlength);
 
 		if (!session->initial_r2t_en) {
-			r2t->data_length = min(session->first_burst, out_len) -
+			r2t->data_length = min(session->first_burst,
+					       transfer_length) -
 					       task->imm_count;
 			r2t->data_offset = task->imm_count;
 			r2t->ttt = cpu_to_be32(ISCSI_RESERVED_TAG);
@@ -438,7 +439,6 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task)
 	} else {
 		hdr->flags |= ISCSI_FLAG_CMD_FINAL;
 		zero_data(hdr->dlength);
-		hdr->data_length = cpu_to_be32(scsi_in(sc)->length);
 
 		if (sc->sc_data_direction == DMA_FROM_DEVICE)
 			hdr->flags |= ISCSI_FLAG_CMD_READ;
@@ -466,7 +466,7 @@ static int iscsi_prep_scsi_cmd_pdu(struct iscsi_task *task)
 			  scsi_bidi_cmnd(sc) ? "bidirectional" :
 			  sc->sc_data_direction == DMA_TO_DEVICE ?
 			  "write" : "read", conn->id, sc, sc->cmnd[0],
-			  task->itt, scsi_bufflen(sc),
+			  task->itt, transfer_length,
 			  scsi_bidi_cmnd(sc) ? scsi_in(sc)->length : 0,
 			  session->cmdsn,
 			  session->max_cmdsn - session->exp_cmdsn + 1);
@@ -1442,9 +1442,9 @@ static int iscsi_xmit_task(struct iscsi_conn *conn)
 		conn->task = NULL;
 	}
 	/* regular RX path uses back_lock */
-	spin_lock_bh(&conn->session->back_lock);
+	spin_lock(&conn->session->back_lock);
 	__iscsi_put_task(task);
-	spin_unlock_bh(&conn->session->back_lock);
+	spin_unlock(&conn->session->back_lock);
 	return rc;
 }
 
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 94a3cafe719..434e9037908 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -640,6 +640,7 @@ struct lpfc_hba {
 #define HBA_DEVLOSS_TMO         0x2000 /* HBA in devloss timeout */
 #define HBA_RRQ_ACTIVE		0x4000 /* process the rrq active list */
 #define HBA_FCP_IOQ_FLUSH	0x8000 /* FCP I/O queues being flushed */
+#define HBA_FW_DUMP_OP		0x10000 /* Skips fn reset before FW dump */
 	uint32_t fcp_ring_in_use; /* When polling test if intr-hndlr active*/
 	struct lpfc_dmabuf slim2p;
 
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 8d5b6ceec9c..1d7a5c34ee8 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -919,10 +919,15 @@ lpfc_sli4_pdev_reg_request(struct lpfc_hba *phba, uint32_t opcode)
 		phba->cfg_sriov_nr_virtfn = 0;
 	}
 
+	if (opcode == LPFC_FW_DUMP)
+		phba->hba_flag |= HBA_FW_DUMP_OP;
+
 	status = lpfc_do_offline(phba, LPFC_EVT_OFFLINE);
 
-	if (status != 0)
+	if (status != 0) {
+		phba->hba_flag &= ~HBA_FW_DUMP_OP;
 		return status;
+	}
 
 	/* wait for the device to be quiesced before firmware reset */
 	msleep(100);
@@ -2364,7 +2369,7 @@ lpfc_oas_tgt_store(struct device *dev, struct device_attribute *attr,
 	uint8_t wwpn[WWN_SZ];
 	int rc;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	/* count may include a LF at end of string */
@@ -2432,7 +2437,7 @@ lpfc_oas_vpt_store(struct device *dev, struct device_attribute *attr,
 	uint8_t wwpn[WWN_SZ];
 	int rc;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	/* count may include a LF at end of string */
@@ -2499,7 +2504,7 @@ lpfc_oas_lun_state_store(struct device *dev, struct device_attribute *attr,
 	struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba;
 	int val = 0;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	if (!isdigit(buf[0]))
@@ -2565,7 +2570,7 @@ lpfc_oas_lun_state_set(struct lpfc_hba *phba, uint8_t vpt_wwpn[],
 
 	int rc = 0;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	if (oas_state) {
@@ -2670,7 +2675,7 @@ lpfc_oas_lun_show(struct device *dev, struct device_attribute *attr,
 	uint64_t oas_lun;
 	int len = 0;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	if (wwn_to_u64(phba->cfg_oas_vpt_wwpn) == 0)
@@ -2716,7 +2721,7 @@ lpfc_oas_lun_store(struct device *dev, struct device_attribute *attr,
 	uint64_t scsi_lun;
 	ssize_t rc;
 
-	if (!phba->cfg_EnableXLane)
+	if (!phba->cfg_fof)
 		return -EPERM;
 
 	if (wwn_to_u64(phba->cfg_oas_vpt_wwpn) == 0)
@@ -4655,7 +4660,7 @@ LPFC_ATTR_R(EnableXLane, 0, 0, 1, "Enable Express Lane Feature.");
 #       0x0 - 0x7f  = CS_CTL field in FC header (high 7 bits)
 # Value range is [0x0,0x7f]. Default value is 0
 */
-LPFC_ATTR_R(XLanePriority, 0, 0x0, 0x7f, "CS_CTL for Express Lane Feature.");
+LPFC_ATTR_RW(XLanePriority, 0, 0x0, 0x7f, "CS_CTL for Express Lane Feature.");
 
 /*
 # lpfc_enable_bg: Enable BlockGuard (Emulex's Implementation of T10-DIF)
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index ca2f4ea7cde..5b5c825d957 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2009-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2009-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_bsg.h b/drivers/scsi/lpfc/lpfc_bsg.h
index a94d4c9dfaa..928ef609f36 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.h
+++ b/drivers/scsi/lpfc/lpfc_bsg.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2010-2012 Emulex.  All rights reserved.                *
+ * Copyright (C) 2010-2014 Emulex.  All rights reserved.                *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index adda0bf7a24..db5604f01a1 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -289,6 +289,7 @@ int lpfc_sli_issue_iocb(struct lpfc_hba *, uint32_t,
 void lpfc_sli_pcimem_bcopy(void *, void *, uint32_t);
 void lpfc_sli_bemem_bcopy(void *, void *, uint32_t);
 void lpfc_sli_abort_iocb_ring(struct lpfc_hba *, struct lpfc_sli_ring *);
+void lpfc_sli_abort_fcp_rings(struct lpfc_hba *phba);
 void lpfc_sli_hba_iocb_abort(struct lpfc_hba *);
 void lpfc_sli_flush_fcp_rings(struct lpfc_hba *);
 int lpfc_sli_ringpostbuf_put(struct lpfc_hba *, struct lpfc_sli_ring *,
@@ -310,6 +311,9 @@ int lpfc_sli_issue_abort_iotag(struct lpfc_hba *, struct lpfc_sli_ring *,
 int lpfc_sli_sum_iocb(struct lpfc_vport *, uint16_t, uint64_t, lpfc_ctx_cmd);
 int lpfc_sli_abort_iocb(struct lpfc_vport *, struct lpfc_sli_ring *, uint16_t,
 			uint64_t, lpfc_ctx_cmd);
+int
+lpfc_sli_abort_taskmgmt(struct lpfc_vport *, struct lpfc_sli_ring *,
+			uint16_t, uint64_t, lpfc_ctx_cmd);
 
 void lpfc_mbox_timeout(unsigned long);
 void lpfc_mbox_timeout_handler(struct lpfc_hba *);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index 828c08e9389..b0aedce3f54 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2007-2012 Emulex.  All rights reserved.           *
+ * Copyright (C) 2007-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -2314,7 +2314,7 @@ proc_cq:
 			goto too_big;
 	}
 
-	if (phba->cfg_EnableXLane) {
+	if (phba->cfg_fof) {
 
 		/* OAS CQ */
 		qp = phba->sli4_hba.oas_cq;
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 624fe0b3cc0..7a5d81a65be 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 294c072e908..2a17e31265b 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -5634,6 +5634,9 @@ lpfc_nlp_init(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		ndlp->active_rrqs_xri_bitmap =
 				mempool_alloc(vport->phba->active_rrq_pool,
 					      GFP_KERNEL);
+		if (ndlp->active_rrqs_xri_bitmap)
+			memset(ndlp->active_rrqs_xri_bitmap, 0,
+			       ndlp->phba->cfg_rrq_xri_bitmap_sz);
 	}
 
 
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 3d9438ce59a..23625925237 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index fd79f7de766..f432ec180cf 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2009-2013 Emulex.  All rights reserved.                *
+ * Copyright (C) 2009-2014 Emulex.  All rights reserved.                *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 635eeb3d698..06f9a5b79e6 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -820,57 +820,153 @@ lpfc_hba_down_prep(struct lpfc_hba *phba)
 }
 
 /**
- * lpfc_hba_down_post_s3 - Perform lpfc uninitialization after HBA reset
+ * lpfc_sli4_free_sp_events - Cleanup sp_queue_events to free
+ * rspiocb which got deferred
+ *
  * @phba: pointer to lpfc HBA data structure.
  *
- * This routine will do uninitialization after the HBA is reset when bring
- * down the SLI Layer.
+ * This routine will cleanup completed slow path events after HBA is reset
+ * when bringing down the SLI Layer.
+ *
  *
  * Return codes
- *   0 - success.
- *   Any other value - error.
+ *   void.
  **/
-static int
-lpfc_hba_down_post_s3(struct lpfc_hba *phba)
+static void
+lpfc_sli4_free_sp_events(struct lpfc_hba *phba)
+{
+	struct lpfc_iocbq *rspiocbq;
+	struct hbq_dmabuf *dmabuf;
+	struct lpfc_cq_event *cq_event;
+
+	spin_lock_irq(&phba->hbalock);
+	phba->hba_flag &= ~HBA_SP_QUEUE_EVT;
+	spin_unlock_irq(&phba->hbalock);
+
+	while (!list_empty(&phba->sli4_hba.sp_queue_event)) {
+		/* Get the response iocb from the head of work queue */
+		spin_lock_irq(&phba->hbalock);
+		list_remove_head(&phba->sli4_hba.sp_queue_event,
+				 cq_event, struct lpfc_cq_event, list);
+		spin_unlock_irq(&phba->hbalock);
+
+		switch (bf_get(lpfc_wcqe_c_code, &cq_event->cqe.wcqe_cmpl)) {
+		case CQE_CODE_COMPL_WQE:
+			rspiocbq = container_of(cq_event, struct lpfc_iocbq,
+						 cq_event);
+			lpfc_sli_release_iocbq(phba, rspiocbq);
+			break;
+		case CQE_CODE_RECEIVE:
+		case CQE_CODE_RECEIVE_V1:
+			dmabuf = container_of(cq_event, struct hbq_dmabuf,
+					      cq_event);
+			lpfc_in_buf_free(phba, &dmabuf->dbuf);
+		}
+	}
+}
+
+/**
+ * lpfc_hba_free_post_buf - Perform lpfc uninitialization after HBA reset
+ * @phba: pointer to lpfc HBA data structure.
+ *
+ * This routine will cleanup posted ELS buffers after the HBA is reset
+ * when bringing down the SLI Layer.
+ *
+ *
+ * Return codes
+ *   void.
+ **/
+static void
+lpfc_hba_free_post_buf(struct lpfc_hba *phba)
 {
 	struct lpfc_sli *psli = &phba->sli;
 	struct lpfc_sli_ring *pring;
 	struct lpfc_dmabuf *mp, *next_mp;
-	LIST_HEAD(completions);
-	int i;
+	LIST_HEAD(buflist);
+	int count;
 
 	if (phba->sli3_options & LPFC_SLI3_HBQ_ENABLED)
 		lpfc_sli_hbqbuf_free_all(phba);
 	else {
 		/* Cleanup preposted buffers on the ELS ring */
 		pring = &psli->ring[LPFC_ELS_RING];
-		list_for_each_entry_safe(mp, next_mp, &pring->postbufq, list) {
+		spin_lock_irq(&phba->hbalock);
+		list_splice_init(&pring->postbufq, &buflist);
+		spin_unlock_irq(&phba->hbalock);
+
+		count = 0;
+		list_for_each_entry_safe(mp, next_mp, &buflist, list) {
 			list_del(&mp->list);
-			pring->postbufq_cnt--;
+			count++;
 			lpfc_mbuf_free(phba, mp->virt, mp->phys);
 			kfree(mp);
 		}
+
+		spin_lock_irq(&phba->hbalock);
+		pring->postbufq_cnt -= count;
+		spin_unlock_irq(&phba->hbalock);
 	}
+}
+
+/**
+ * lpfc_hba_clean_txcmplq - Perform lpfc uninitialization after HBA reset
+ * @phba: pointer to lpfc HBA data structure.
+ *
+ * This routine will cleanup the txcmplq after the HBA is reset when bringing
+ * down the SLI Layer.
+ *
+ * Return codes
+ *   void
+ **/
+static void
+lpfc_hba_clean_txcmplq(struct lpfc_hba *phba)
+{
+	struct lpfc_sli *psli = &phba->sli;
+	struct lpfc_sli_ring *pring;
+	LIST_HEAD(completions);
+	int i;
 
-	spin_lock_irq(&phba->hbalock);
 	for (i = 0; i < psli->num_rings; i++) {
 		pring = &psli->ring[i];
-
+		if (phba->sli_rev >= LPFC_SLI_REV4)
+			spin_lock_irq(&pring->ring_lock);
+		else
+			spin_lock_irq(&phba->hbalock);
 		/* At this point in time the HBA is either reset or DOA. Either
 		 * way, nothing should be on txcmplq as it will NEVER complete.
 		 */
 		list_splice_init(&pring->txcmplq, &completions);
-		spin_unlock_irq(&phba->hbalock);
+		pring->txcmplq_cnt = 0;
+
+		if (phba->sli_rev >= LPFC_SLI_REV4)
+			spin_unlock_irq(&pring->ring_lock);
+		else
+			spin_unlock_irq(&phba->hbalock);
 
 		/* Cancel all the IOCBs from the completions list */
 		lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
 				      IOERR_SLI_ABORTED);
-
 		lpfc_sli_abort_iocb_ring(phba, pring);
-		spin_lock_irq(&phba->hbalock);
 	}
-	spin_unlock_irq(&phba->hbalock);
+}
 
+/**
+ * lpfc_hba_down_post_s3 - Perform lpfc uninitialization after HBA reset
+	int i;
+ * @phba: pointer to lpfc HBA data structure.
+ *
+ * This routine will do uninitialization after the HBA is reset when bring
+ * down the SLI Layer.
+ *
+ * Return codes
+ *   0 - success.
+ *   Any other value - error.
+ **/
+static int
+lpfc_hba_down_post_s3(struct lpfc_hba *phba)
+{
+	lpfc_hba_free_post_buf(phba);
+	lpfc_hba_clean_txcmplq(phba);
 	return 0;
 }
 
@@ -890,13 +986,12 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 {
 	struct lpfc_scsi_buf *psb, *psb_next;
 	LIST_HEAD(aborts);
-	int ret;
 	unsigned long iflag = 0;
 	struct lpfc_sglq *sglq_entry = NULL;
 
-	ret = lpfc_hba_down_post_s3(phba);
-	if (ret)
-		return ret;
+	lpfc_hba_free_post_buf(phba);
+	lpfc_hba_clean_txcmplq(phba);
+
 	/* At this point in time the HBA is either reset or DOA. Either
 	 * way, nothing should be on lpfc_abts_els_sgl_list, it needs to be
 	 * on the lpfc_sgl_list so that it can either be freed if the
@@ -932,6 +1027,8 @@ lpfc_hba_down_post_s4(struct lpfc_hba *phba)
 	spin_lock_irqsave(&phba->scsi_buf_list_put_lock, iflag);
 	list_splice(&aborts, &phba->lpfc_scsi_buf_list_put);
 	spin_unlock_irqrestore(&phba->scsi_buf_list_put_lock, iflag);
+
+	lpfc_sli4_free_sp_events(phba);
 	return 0;
 }
 
@@ -1250,7 +1347,6 @@ static void
 lpfc_handle_deferred_eratt(struct lpfc_hba *phba)
 {
 	uint32_t old_host_status = phba->work_hs;
-	struct lpfc_sli_ring  *pring;
 	struct lpfc_sli *psli = &phba->sli;
 
 	/* If the pci channel is offline, ignore possible errors,
@@ -1279,8 +1375,7 @@ lpfc_handle_deferred_eratt(struct lpfc_hba *phba)
 	 * dropped by the firmware. Error iocb (I/O) on txcmplq and let the
 	 * SCSI layer retry it after re-establishing link.
 	 */
-	pring = &psli->ring[psli->fcp_ring];
-	lpfc_sli_abort_iocb_ring(phba, pring);
+	lpfc_sli_abort_fcp_rings(phba);
 
 	/*
 	 * There was a firmware error. Take the hba offline and then
@@ -1348,7 +1443,6 @@ lpfc_handle_eratt_s3(struct lpfc_hba *phba)
 {
 	struct lpfc_vport *vport = phba->pport;
 	struct lpfc_sli   *psli = &phba->sli;
-	struct lpfc_sli_ring  *pring;
 	uint32_t event_data;
 	unsigned long temperature;
 	struct temp_event temp_event_data;
@@ -1400,8 +1494,7 @@ lpfc_handle_eratt_s3(struct lpfc_hba *phba)
 		* Error iocb (I/O) on txcmplq and let the SCSI layer
 		* retry it after re-establishing link.
 		*/
-		pring = &psli->ring[psli->fcp_ring];
-		lpfc_sli_abort_iocb_ring(phba, pring);
+		lpfc_sli_abort_fcp_rings(phba);
 
 		/*
 		 * There was a firmware error.  Take the hba offline and then
@@ -1940,78 +2033,81 @@ lpfc_get_hba_model_desc(struct lpfc_hba *phba, uint8_t *mdp, uint8_t *descp)
 
 	switch (dev_id) {
 	case PCI_DEVICE_ID_FIREFLY:
-		m = (typeof(m)){"LP6000", "PCI", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP6000", "PCI",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_SUPERFLY:
 		if (vp->rev.biuRev >= 1 && vp->rev.biuRev <= 3)
-			m = (typeof(m)){"LP7000", "PCI",
-					"Fibre Channel Adapter"};
+			m = (typeof(m)){"LP7000", "PCI", ""};
 		else
-			m = (typeof(m)){"LP7000E", "PCI",
-					"Fibre Channel Adapter"};
+			m = (typeof(m)){"LP7000E", "PCI", ""};
+		m.function = "Obsolete, Unsupported Fibre Channel Adapter";
 		break;
 	case PCI_DEVICE_ID_DRAGONFLY:
 		m = (typeof(m)){"LP8000", "PCI",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_CENTAUR:
 		if (FC_JEDEC_ID(vp->rev.biuRev) == CENTAUR_2G_JEDEC_ID)
-			m = (typeof(m)){"LP9002", "PCI",
-					"Fibre Channel Adapter"};
+			m = (typeof(m)){"LP9002", "PCI", ""};
 		else
-			m = (typeof(m)){"LP9000", "PCI",
-					"Fibre Channel Adapter"};
+			m = (typeof(m)){"LP9000", "PCI", ""};
+		m.function = "Obsolete, Unsupported Fibre Channel Adapter";
 		break;
 	case PCI_DEVICE_ID_RFLY:
 		m = (typeof(m)){"LP952", "PCI",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_PEGASUS:
 		m = (typeof(m)){"LP9802", "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_THOR:
 		m = (typeof(m)){"LP10000", "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_VIPER:
 		m = (typeof(m)){"LPX1000",  "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_PFLY:
 		m = (typeof(m)){"LP982", "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_TFLY:
 		m = (typeof(m)){"LP1050", "PCI-X",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_HELIOS:
 		m = (typeof(m)){"LP11000", "PCI-X2",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_HELIOS_SCSP:
 		m = (typeof(m)){"LP11000-SP", "PCI-X2",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_HELIOS_DCSP:
 		m = (typeof(m)){"LP11002-SP",  "PCI-X2",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_NEPTUNE:
-		m = (typeof(m)){"LPe1000", "PCIe", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LPe1000", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_NEPTUNE_SCSP:
-		m = (typeof(m)){"LPe1000-SP", "PCIe", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LPe1000-SP", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_NEPTUNE_DCSP:
-		m = (typeof(m)){"LPe1002-SP", "PCIe", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LPe1002-SP", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_BMID:
 		m = (typeof(m)){"LP1150", "PCI-X2", "Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_BSMB:
-		m = (typeof(m)){"LP111", "PCI-X2", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP111", "PCI-X2",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_ZEPHYR:
 		m = (typeof(m)){"LPe11000", "PCIe", "Fibre Channel Adapter"};
@@ -2030,16 +2126,20 @@ lpfc_get_hba_model_desc(struct lpfc_hba *phba, uint8_t *mdp, uint8_t *descp)
 		m = (typeof(m)){"LPe111", "PCIe", "Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LP101:
-		m = (typeof(m)){"LP101", "PCI-X", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP101", "PCI-X",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LP10000S:
-		m = (typeof(m)){"LP10000-S", "PCI", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP10000-S", "PCI",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LP11000S:
-		m = (typeof(m)){"LP11000-S", "PCI-X2", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LP11000-S", "PCI-X2",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LPE11000S:
-		m = (typeof(m)){"LPe11000-S", "PCIe", "Fibre Channel Adapter"};
+		m = (typeof(m)){"LPe11000-S", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_SAT:
 		m = (typeof(m)){"LPe12000", "PCIe", "Fibre Channel Adapter"};
@@ -2060,20 +2160,21 @@ lpfc_get_hba_model_desc(struct lpfc_hba *phba, uint8_t *mdp, uint8_t *descp)
 		m = (typeof(m)){"LPe12000-S", "PCIe", "Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_HORNET:
-		m = (typeof(m)){"LP21000", "PCIe", "FCoE Adapter"};
+		m = (typeof(m)){"LP21000", "PCIe",
+				"Obsolete, Unsupported FCoE Adapter"};
 		GE = 1;
 		break;
 	case PCI_DEVICE_ID_PROTEUS_VF:
 		m = (typeof(m)){"LPev12000", "PCIe IOV",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_PROTEUS_PF:
 		m = (typeof(m)){"LPev12000", "PCIe IOV",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_PROTEUS_S:
 		m = (typeof(m)){"LPemv12002-S", "PCIe IOV",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_TIGERSHARK:
 		oneConnect = 1;
@@ -2089,17 +2190,24 @@ lpfc_get_hba_model_desc(struct lpfc_hba *phba, uint8_t *mdp, uint8_t *descp)
 		break;
 	case PCI_DEVICE_ID_BALIUS:
 		m = (typeof(m)){"LPVe12002", "PCIe Shared I/O",
-				"Fibre Channel Adapter"};
+				"Obsolete, Unsupported Fibre Channel Adapter"};
 		break;
 	case PCI_DEVICE_ID_LANCER_FC:
-	case PCI_DEVICE_ID_LANCER_FC_VF:
 		m = (typeof(m)){"LPe16000", "PCIe", "Fibre Channel Adapter"};
 		break;
+	case PCI_DEVICE_ID_LANCER_FC_VF:
+		m = (typeof(m)){"LPe16000", "PCIe",
+				"Obsolete, Unsupported Fibre Channel Adapter"};
+		break;
 	case PCI_DEVICE_ID_LANCER_FCOE:
-	case PCI_DEVICE_ID_LANCER_FCOE_VF:
 		oneConnect = 1;
 		m = (typeof(m)){"OCe15100", "PCIe", "FCoE"};
 		break;
+	case PCI_DEVICE_ID_LANCER_FCOE_VF:
+		oneConnect = 1;
+		m = (typeof(m)){"OCe15100", "PCIe",
+				"Obsolete, Unsupported FCoE"};
+		break;
 	case PCI_DEVICE_ID_SKYHAWK:
 	case PCI_DEVICE_ID_SKYHAWK_VF:
 		oneConnect = 1;
@@ -4614,7 +4722,10 @@ lpfc_reset_hba(struct lpfc_hba *phba)
 		phba->link_state = LPFC_HBA_ERROR;
 		return;
 	}
-	lpfc_offline_prep(phba, LPFC_MBX_WAIT);
+	if (phba->sli.sli_flag & LPFC_SLI_ACTIVE)
+		lpfc_offline_prep(phba, LPFC_MBX_WAIT);
+	else
+		lpfc_offline_prep(phba, LPFC_MBX_NO_WAIT);
 	lpfc_offline(phba);
 	lpfc_sli_brdrestart(phba);
 	lpfc_online(phba);
@@ -9663,9 +9774,6 @@ lpfc_pci_resume_one_s3(struct pci_dev *pdev)
 static void
 lpfc_sli_prep_dev_for_recover(struct lpfc_hba *phba)
 {
-	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring  *pring;
-
 	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 			"2723 PCI channel I/O abort preparing for recovery\n");
 
@@ -9673,8 +9781,7 @@ lpfc_sli_prep_dev_for_recover(struct lpfc_hba *phba)
 	 * There may be errored I/Os through HBA, abort all I/Os on txcmplq
 	 * and let the SCSI mid-layer to retry them to recover.
 	 */
-	pring = &psli->ring[psli->fcp_ring];
-	lpfc_sli_abort_iocb_ring(phba, pring);
+	lpfc_sli_abort_fcp_rings(phba);
 }
 
 /**
@@ -10417,17 +10524,13 @@ lpfc_pci_resume_one_s4(struct pci_dev *pdev)
 static void
 lpfc_sli4_prep_dev_for_recover(struct lpfc_hba *phba)
 {
-	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring  *pring;
-
 	lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 			"2828 PCI channel I/O abort preparing for recovery\n");
 	/*
 	 * There may be errored I/Os through HBA, abort all I/Os on txcmplq
 	 * and let the SCSI mid-layer to retry them to recover.
 	 */
-	pring = &psli->ring[psli->fcp_ring];
-	lpfc_sli_abort_iocb_ring(phba, pring);
+	lpfc_sli_abort_fcp_rings(phba);
 }
 
 /**
@@ -10898,7 +11001,7 @@ lpfc_sli4_oas_verify(struct lpfc_hba *phba)
 	if (phba->sli4_hba.pc_sli4_params.oas_supported) {
 		phba->cfg_fof = 1;
 	} else {
-		phba->cfg_EnableXLane = 0;
+		phba->cfg_fof = 0;
 		if (phba->device_data_mem_pool)
 			mempool_destroy(phba->device_data_mem_pool);
 		phba->device_data_mem_pool = NULL;
@@ -10928,7 +11031,7 @@ lpfc_fof_queue_setup(struct lpfc_hba *phba)
 	if (rc)
 		return -ENOMEM;
 
-	if (phba->cfg_EnableXLane) {
+	if (phba->cfg_fof) {
 
 		rc = lpfc_cq_create(phba, phba->sli4_hba.oas_cq,
 				    phba->sli4_hba.fof_eq, LPFC_WCQ, LPFC_FCP);
@@ -10947,8 +11050,7 @@ lpfc_fof_queue_setup(struct lpfc_hba *phba)
 	return 0;
 
 out_oas_wq:
-	if (phba->cfg_EnableXLane)
-		lpfc_cq_destroy(phba, phba->sli4_hba.oas_cq);
+	lpfc_cq_destroy(phba, phba->sli4_hba.oas_cq);
 out_oas_cq:
 	lpfc_eq_destroy(phba, phba->sli4_hba.fof_eq);
 	return rc;
@@ -10982,7 +11084,7 @@ lpfc_fof_queue_create(struct lpfc_hba *phba)
 
 	phba->sli4_hba.fof_eq = qdesc;
 
-	if (phba->cfg_EnableXLane) {
+	if (phba->cfg_fof) {
 
 		/* Create OAS CQ */
 		qdesc = lpfc_sli4_queue_alloc(phba, phba->sli4_hba.cq_esize,
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index ed419aad2b1..3fa65338d3f 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 462453ee0bd..2df11daad85 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -73,7 +73,7 @@ lpfc_rport_data_from_scsi_device(struct scsi_device *sdev)
 {
 	struct lpfc_vport *vport = (struct lpfc_vport *)sdev->host->hostdata;
 
-	if (vport->phba->cfg_EnableXLane)
+	if (vport->phba->cfg_fof)
 		return ((struct lpfc_device_data *)sdev->hostdata)->rport_data;
 	else
 		return (struct lpfc_rport_data *)sdev->hostdata;
@@ -3462,7 +3462,7 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd)
 	 * If the OAS driver feature is enabled and the lun is enabled for
 	 * OAS, set the oas iocb related flags.
 	 */
-	if ((phba->cfg_EnableXLane) && ((struct lpfc_device_data *)
+	if ((phba->cfg_fof) && ((struct lpfc_device_data *)
 		scsi_cmnd->device->hostdata)->oas_enabled)
 		lpfc_cmd->cur_iocbq.iocb_flag |= LPFC_IO_OAS;
 	return 0;
@@ -4314,6 +4314,7 @@ lpfc_scsi_prep_cmnd(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
 		fcp_cmnd->fcpCntl1 = SIMPLE_Q;
 
 	sli4 = (phba->sli_rev == LPFC_SLI_REV4);
+	piocbq->iocb.un.fcpi.fcpi_XRdy = 0;
 
 	/*
 	 * There are three possibilities here - use scatter-gather segment, use
@@ -4782,7 +4783,9 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	struct lpfc_scsi_buf *lpfc_cmd;
 	IOCB_t *cmd, *icmd;
 	int ret = SUCCESS, status = 0;
-	unsigned long flags;
+	struct lpfc_sli_ring *pring_s4;
+	int ring_number, ret_val;
+	unsigned long flags, iflags;
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq);
 
 	status = fc_block_scsi_eh(cmnd);
@@ -4833,6 +4836,14 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 
 	BUG_ON(iocb->context1 != lpfc_cmd);
 
+	/* abort issued in recovery is still in progress */
+	if (iocb->iocb_flag & LPFC_DRIVER_ABORTED) {
+		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
+			 "3389 SCSI Layer I/O Abort Request is pending\n");
+		spin_unlock_irqrestore(&phba->hbalock, flags);
+		goto wait_for_cmpl;
+	}
+
 	abtsiocb = __lpfc_sli_get_iocbq(phba);
 	if (abtsiocb == NULL) {
 		ret = FAILED;
@@ -4871,11 +4882,23 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 
 	abtsiocb->iocb_cmpl = lpfc_sli_abort_fcp_cmpl;
 	abtsiocb->vport = vport;
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		ring_number = MAX_SLI3_CONFIGURED_RINGS + iocb->fcp_wqidx;
+		pring_s4 = &phba->sli.ring[ring_number];
+		/* Note: both hbalock and ring_lock must be set here */
+		spin_lock_irqsave(&pring_s4->ring_lock, iflags);
+		ret_val = __lpfc_sli_issue_iocb(phba, pring_s4->ringno,
+						abtsiocb, 0);
+		spin_unlock_irqrestore(&pring_s4->ring_lock, iflags);
+	} else {
+		ret_val = __lpfc_sli_issue_iocb(phba, LPFC_FCP_RING,
+						abtsiocb, 0);
+	}
 	/* no longer need the lock after this point */
 	spin_unlock_irqrestore(&phba->hbalock, flags);
 
-	if (lpfc_sli_issue_iocb(phba, LPFC_FCP_RING, abtsiocb, 0) ==
-	    IOCB_ERROR) {
+
+	if (ret_val == IOCB_ERROR) {
 		lpfc_sli_release_iocbq(phba, abtsiocb);
 		ret = FAILED;
 		goto out;
@@ -4885,12 +4908,16 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 		lpfc_sli_handle_fast_ring_event(phba,
 			&phba->sli.ring[LPFC_FCP_RING], HA_R0RE_REQ);
 
+wait_for_cmpl:
 	lpfc_cmd->waitq = &waitq;
 	/* Wait for abort to complete */
 	wait_event_timeout(waitq,
 			  (lpfc_cmd->pCmd != cmnd),
 			   msecs_to_jiffies(2*vport->cfg_devloss_tmo*1000));
+
+	spin_lock_irqsave(shost->host_lock, flags);
 	lpfc_cmd->waitq = NULL;
+	spin_unlock_irqrestore(shost->host_lock, flags);
 
 	if (lpfc_cmd->pCmd == cmnd) {
 		ret = FAILED;
@@ -5172,8 +5199,9 @@ lpfc_reset_flush_io_context(struct lpfc_vport *vport, uint16_t tgt_id,
 
 	cnt = lpfc_sli_sum_iocb(vport, tgt_id, lun_id, context);
 	if (cnt)
-		lpfc_sli_abort_iocb(vport, &phba->sli.ring[phba->sli.fcp_ring],
-				    tgt_id, lun_id, context);
+		lpfc_sli_abort_taskmgmt(vport,
+					&phba->sli.ring[phba->sli.fcp_ring],
+					tgt_id, lun_id, context);
 	later = msecs_to_jiffies(2 * vport->cfg_devloss_tmo * 1000) + jiffies;
 	while (time_after(later, jiffies) && cnt) {
 		schedule_timeout_uninterruptible(msecs_to_jiffies(20));
@@ -5491,7 +5519,7 @@ lpfc_slave_alloc(struct scsi_device *sdev)
 	if (!rport || fc_remote_port_chkready(rport))
 		return -ENXIO;
 
-	if (phba->cfg_EnableXLane) {
+	if (phba->cfg_fof) {
 
 		/*
 		 * Check to see if the device data structure for the lun
@@ -5616,7 +5644,7 @@ lpfc_slave_destroy(struct scsi_device *sdev)
 	struct lpfc_device_data *device_data = sdev->hostdata;
 
 	atomic_dec(&phba->sdev_cnt);
-	if ((phba->cfg_EnableXLane) && (device_data)) {
+	if ((phba->cfg_fof) && (device_data)) {
 		spin_lock_irqsave(&phba->devicelock, flags);
 		device_data->available = false;
 		if (!device_data->oas_enabled)
@@ -5655,7 +5683,7 @@ lpfc_create_device_data(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 	int memory_flags;
 
 	if (unlikely(!phba) || !vport_wwpn || !target_wwpn  ||
-	    !(phba->cfg_EnableXLane))
+	    !(phba->cfg_fof))
 		return NULL;
 
 	/* Attempt to create the device data to contain lun info */
@@ -5693,7 +5721,7 @@ lpfc_delete_device_data(struct lpfc_hba *phba,
 {
 
 	if (unlikely(!phba) || !lun_info  ||
-	    !(phba->cfg_EnableXLane))
+	    !(phba->cfg_fof))
 		return;
 
 	if (!list_empty(&lun_info->listentry))
@@ -5727,7 +5755,7 @@ __lpfc_get_device_data(struct lpfc_hba *phba, struct list_head *list,
 	struct lpfc_device_data *lun_info;
 
 	if (unlikely(!phba) || !list || !vport_wwpn || !target_wwpn ||
-	    !phba->cfg_EnableXLane)
+	    !phba->cfg_fof)
 		return NULL;
 
 	/* Check to see if the lun is already enabled for OAS. */
@@ -5789,7 +5817,7 @@ lpfc_find_next_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 	    !starting_lun || !found_vport_wwpn ||
 	    !found_target_wwpn || !found_lun || !found_lun_status ||
 	    (*starting_lun == NO_MORE_OAS_LUN) ||
-	    !phba->cfg_EnableXLane)
+	    !phba->cfg_fof)
 		return false;
 
 	lun = *starting_lun;
@@ -5873,7 +5901,7 @@ lpfc_enable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 	unsigned long flags;
 
 	if (unlikely(!phba) || !vport_wwpn || !target_wwpn ||
-	    !phba->cfg_EnableXLane)
+	    !phba->cfg_fof)
 		return false;
 
 	spin_lock_irqsave(&phba->devicelock, flags);
@@ -5930,7 +5958,7 @@ lpfc_disable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 	unsigned long flags;
 
 	if (unlikely(!phba) || !vport_wwpn || !target_wwpn ||
-	    !phba->cfg_EnableXLane)
+	    !phba->cfg_fof)
 		return false;
 
 	spin_lock_irqsave(&phba->devicelock, flags);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.h b/drivers/scsi/lpfc/lpfc_scsi.h
index 0120bfccf50..0389ac1e7b8 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.h
+++ b/drivers/scsi/lpfc/lpfc_scsi.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 6bb51f8e3c1..32ada050557 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  * Portions Copyright (C) 2004-2005 Christoph Hellwig              *
@@ -265,6 +265,16 @@ lpfc_sli4_eq_get(struct lpfc_queue *q)
 		return NULL;
 
 	q->hba_index = idx;
+
+	/*
+	 * insert barrier for instruction interlock : data from the hardware
+	 * must have the valid bit checked before it can be copied and acted
+	 * upon. Given what was seen in lpfc_sli4_cq_get() of speculative
+	 * instructions allowing action on content before valid bit checked,
+	 * add barrier here as well. May not be needed as "content" is a
+	 * single 32-bit entity here (vs multi word structure for cq's).
+	 */
+	mb();
 	return eqe;
 }
 
@@ -370,6 +380,17 @@ lpfc_sli4_cq_get(struct lpfc_queue *q)
 
 	cqe = q->qe[q->hba_index].cqe;
 	q->hba_index = idx;
+
+	/*
+	 * insert barrier for instruction interlock : data from the hardware
+	 * must have the valid bit checked before it can be copied and acted
+	 * upon. Speculative instructions were allowing a bcopy at the start
+	 * of lpfc_sli4_fp_handle_wcqe(), which is called immediately
+	 * after our return, to copy data before the valid bit check above
+	 * was done. As such, some of the copied data was stale. The barrier
+	 * ensures the check is before any data is copied.
+	 */
+	mb();
 	return cqe;
 }
 
@@ -3511,14 +3532,27 @@ lpfc_sli_abort_iocb_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
 	/* Error everything on txq and txcmplq
 	 * First do the txq.
 	 */
-	spin_lock_irq(&phba->hbalock);
-	list_splice_init(&pring->txq, &completions);
+	if (phba->sli_rev >= LPFC_SLI_REV4) {
+		spin_lock_irq(&pring->ring_lock);
+		list_splice_init(&pring->txq, &completions);
+		pring->txq_cnt = 0;
+		spin_unlock_irq(&pring->ring_lock);
 
-	/* Next issue ABTS for everything on the txcmplq */
-	list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list)
-		lpfc_sli_issue_abort_iotag(phba, pring, iocb);
+		spin_lock_irq(&phba->hbalock);
+		/* Next issue ABTS for everything on the txcmplq */
+		list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list)
+			lpfc_sli_issue_abort_iotag(phba, pring, iocb);
+		spin_unlock_irq(&phba->hbalock);
+	} else {
+		spin_lock_irq(&phba->hbalock);
+		list_splice_init(&pring->txq, &completions);
+		pring->txq_cnt = 0;
 
-	spin_unlock_irq(&phba->hbalock);
+		/* Next issue ABTS for everything on the txcmplq */
+		list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list)
+			lpfc_sli_issue_abort_iotag(phba, pring, iocb);
+		spin_unlock_irq(&phba->hbalock);
+	}
 
 	/* Cancel all the IOCBs from the completions list */
 	lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
@@ -3526,6 +3560,36 @@ lpfc_sli_abort_iocb_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
 }
 
 /**
+ * lpfc_sli_abort_fcp_rings - Abort all iocbs in all FCP rings
+ * @phba: Pointer to HBA context object.
+ * @pring: Pointer to driver SLI ring object.
+ *
+ * This function aborts all iocbs in FCP rings and frees all the iocb
+ * objects in txq. This function issues an abort iocb for all the iocb commands
+ * in txcmplq. The iocbs in the txcmplq is not guaranteed to complete before
+ * the return of this function. The caller is not required to hold any locks.
+ **/
+void
+lpfc_sli_abort_fcp_rings(struct lpfc_hba *phba)
+{
+	struct lpfc_sli *psli = &phba->sli;
+	struct lpfc_sli_ring  *pring;
+	uint32_t i;
+
+	/* Look on all the FCP Rings for the iotag */
+	if (phba->sli_rev >= LPFC_SLI_REV4) {
+		for (i = 0; i < phba->cfg_fcp_io_channel; i++) {
+			pring = &psli->ring[i + MAX_SLI3_CONFIGURED_RINGS];
+			lpfc_sli_abort_iocb_ring(phba, pring);
+		}
+	} else {
+		pring = &psli->ring[psli->fcp_ring];
+		lpfc_sli_abort_iocb_ring(phba, pring);
+	}
+}
+
+
+/**
  * lpfc_sli_flush_fcp_rings - flush all iocbs in the fcp ring
  * @phba: Pointer to HBA context object.
  *
@@ -3542,28 +3606,55 @@ lpfc_sli_flush_fcp_rings(struct lpfc_hba *phba)
 	LIST_HEAD(txcmplq);
 	struct lpfc_sli *psli = &phba->sli;
 	struct lpfc_sli_ring  *pring;
-
-	/* Currently, only one fcp ring */
-	pring = &psli->ring[psli->fcp_ring];
+	uint32_t i;
 
 	spin_lock_irq(&phba->hbalock);
-	/* Retrieve everything on txq */
-	list_splice_init(&pring->txq, &txq);
-
-	/* Retrieve everything on the txcmplq */
-	list_splice_init(&pring->txcmplq, &txcmplq);
-
 	/* Indicate the I/O queues are flushed */
 	phba->hba_flag |= HBA_FCP_IOQ_FLUSH;
 	spin_unlock_irq(&phba->hbalock);
 
-	/* Flush the txq */
-	lpfc_sli_cancel_iocbs(phba, &txq, IOSTAT_LOCAL_REJECT,
-			      IOERR_SLI_DOWN);
+	/* Look on all the FCP Rings for the iotag */
+	if (phba->sli_rev >= LPFC_SLI_REV4) {
+		for (i = 0; i < phba->cfg_fcp_io_channel; i++) {
+			pring = &psli->ring[i + MAX_SLI3_CONFIGURED_RINGS];
+
+			spin_lock_irq(&pring->ring_lock);
+			/* Retrieve everything on txq */
+			list_splice_init(&pring->txq, &txq);
+			/* Retrieve everything on the txcmplq */
+			list_splice_init(&pring->txcmplq, &txcmplq);
+			pring->txq_cnt = 0;
+			pring->txcmplq_cnt = 0;
+			spin_unlock_irq(&pring->ring_lock);
+
+			/* Flush the txq */
+			lpfc_sli_cancel_iocbs(phba, &txq,
+					      IOSTAT_LOCAL_REJECT,
+					      IOERR_SLI_DOWN);
+			/* Flush the txcmpq */
+			lpfc_sli_cancel_iocbs(phba, &txcmplq,
+					      IOSTAT_LOCAL_REJECT,
+					      IOERR_SLI_DOWN);
+		}
+	} else {
+		pring = &psli->ring[psli->fcp_ring];
 
-	/* Flush the txcmpq */
-	lpfc_sli_cancel_iocbs(phba, &txcmplq, IOSTAT_LOCAL_REJECT,
-			      IOERR_SLI_DOWN);
+		spin_lock_irq(&phba->hbalock);
+		/* Retrieve everything on txq */
+		list_splice_init(&pring->txq, &txq);
+		/* Retrieve everything on the txcmplq */
+		list_splice_init(&pring->txcmplq, &txcmplq);
+		pring->txq_cnt = 0;
+		pring->txcmplq_cnt = 0;
+		spin_unlock_irq(&phba->hbalock);
+
+		/* Flush the txq */
+		lpfc_sli_cancel_iocbs(phba, &txq, IOSTAT_LOCAL_REJECT,
+				      IOERR_SLI_DOWN);
+		/* Flush the txcmpq */
+		lpfc_sli_cancel_iocbs(phba, &txcmplq, IOSTAT_LOCAL_REJECT,
+				      IOERR_SLI_DOWN);
+	}
 }
 
 /**
@@ -3966,12 +4057,13 @@ lpfc_sli4_brdreset(struct lpfc_hba *phba)
 {
 	struct lpfc_sli *psli = &phba->sli;
 	uint16_t cfg_value;
-	int rc;
+	int rc = 0;
 
 	/* Reset HBA */
 	lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
-			"0295 Reset HBA Data: x%x x%x\n",
-			phba->pport->port_state, psli->sli_flag);
+			"0295 Reset HBA Data: x%x x%x x%x\n",
+			phba->pport->port_state, psli->sli_flag,
+			phba->hba_flag);
 
 	/* perform board reset */
 	phba->fc_eventTag = 0;
@@ -3984,6 +4076,12 @@ lpfc_sli4_brdreset(struct lpfc_hba *phba)
 	phba->fcf.fcf_flag = 0;
 	spin_unlock_irq(&phba->hbalock);
 
+	/* SLI4 INTF 2: if FW dump is being taken skip INIT_PORT */
+	if (phba->hba_flag & HBA_FW_DUMP_OP) {
+		phba->hba_flag &= ~HBA_FW_DUMP_OP;
+		return rc;
+	}
+
 	/* Now physically reset the device */
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 			"0389 Performing PCI function reset!\n");
@@ -4981,7 +5079,7 @@ lpfc_sli4_arm_cqeq_intr(struct lpfc_hba *phba)
 		} while (++fcp_eqidx < phba->cfg_fcp_io_channel);
 	}
 
-	if (phba->cfg_EnableXLane)
+	if (phba->cfg_fof)
 		lpfc_sli4_cq_release(phba->sli4_hba.oas_cq, LPFC_QUEUE_REARM);
 
 	if (phba->sli4_hba.hba_eq) {
@@ -6701,7 +6799,6 @@ lpfc_mbox_timeout_handler(struct lpfc_hba *phba)
 	LPFC_MBOXQ_t *pmbox = phba->sli.mbox_active;
 	MAILBOX_t *mb = &pmbox->u.mb;
 	struct lpfc_sli *psli = &phba->sli;
-	struct lpfc_sli_ring *pring;
 
 	/* If the mailbox completed, process the completion and return */
 	if (lpfc_sli4_process_missed_mbox_completions(phba))
@@ -6743,8 +6840,7 @@ lpfc_mbox_timeout_handler(struct lpfc_hba *phba)
 	psli->sli_flag &= ~LPFC_SLI_ACTIVE;
 	spin_unlock_irq(&phba->hbalock);
 
-	pring = &psli->ring[psli->fcp_ring];
-	lpfc_sli_abort_iocb_ring(phba, pring);
+	lpfc_sli_abort_fcp_rings(phba);
 
 	lpfc_printf_log(phba, KERN_ERR, LOG_MBOX | LOG_SLI,
 			"0345 Resetting board due to mailbox timeout\n");
@@ -8112,6 +8208,7 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 	abort_tag = (uint32_t) iocbq->iotag;
 	xritag = iocbq->sli4_xritag;
 	wqe->generic.wqe_com.word7 = 0; /* The ct field has moved so reset */
+	wqe->generic.wqe_com.word10 = 0;
 	/* words0-2 bpl convert bde */
 	if (iocbq->iocb.un.genreq64.bdl.bdeFlags == BUFF_TYPE_BLP_64) {
 		numBdes = iocbq->iocb.un.genreq64.bdl.bdeSize /
@@ -8618,8 +8715,7 @@ __lpfc_sli_issue_iocb_s4(struct lpfc_hba *phba, uint32_t ring_number,
 
 	if ((piocb->iocb_flag & LPFC_IO_FCP) ||
 	    (piocb->iocb_flag & LPFC_USE_FCPWQIDX)) {
-		if (!phba->cfg_EnableXLane || (!(piocb->iocb_flag &
-			LPFC_IO_OAS))) {
+		if (!phba->cfg_fof || (!(piocb->iocb_flag & LPFC_IO_OAS))) {
 			wq = phba->sli4_hba.fcp_wq[piocb->fcp_wqidx];
 		} else {
 			wq = phba->sli4_hba.oas_wq;
@@ -8714,7 +8810,7 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number,
 
 	if (phba->sli_rev == LPFC_SLI_REV4) {
 		if (piocb->iocb_flag &  LPFC_IO_FCP) {
-			if (!phba->cfg_EnableXLane || (!(piocb->iocb_flag &
+			if (!phba->cfg_fof || (!(piocb->iocb_flag &
 				LPFC_IO_OAS))) {
 				if (unlikely(!phba->sli4_hba.fcp_wq))
 					return IOCB_ERROR;
@@ -9149,6 +9245,7 @@ lpfc_sli_queue_setup(struct lpfc_hba *phba)
 		pring->sli.sli3.next_cmdidx  = 0;
 		pring->sli.sli3.local_getidx = 0;
 		pring->sli.sli3.cmdidx = 0;
+		pring->flag = 0;
 		INIT_LIST_HEAD(&pring->txq);
 		INIT_LIST_HEAD(&pring->txcmplq);
 		INIT_LIST_HEAD(&pring->iocb_continueq);
@@ -9784,43 +9881,6 @@ abort_iotag_exit:
 }
 
 /**
- * lpfc_sli_iocb_ring_abort - Unconditionally abort all iocbs on an iocb ring
- * @phba: Pointer to HBA context object.
- * @pring: Pointer to driver SLI ring object.
- *
- * This function aborts all iocbs in the given ring and frees all the iocb
- * objects in txq. This function issues abort iocbs unconditionally for all
- * the iocb commands in txcmplq. The iocbs in the txcmplq is not guaranteed
- * to complete before the return of this function. The caller is not required
- * to hold any locks.
- **/
-static void
-lpfc_sli_iocb_ring_abort(struct lpfc_hba *phba, struct lpfc_sli_ring *pring)
-{
-	LIST_HEAD(completions);
-	struct lpfc_iocbq *iocb, *next_iocb;
-
-	if (pring->ringno == LPFC_ELS_RING)
-		lpfc_fabric_abort_hba(phba);
-
-	spin_lock_irq(&phba->hbalock);
-
-	/* Take off all the iocbs on txq for cancelling */
-	list_splice_init(&pring->txq, &completions);
-	pring->txq_cnt = 0;
-
-	/* Next issue ABTS for everything on the txcmplq */
-	list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list)
-		lpfc_sli_abort_iotag_issue(phba, pring, iocb);
-
-	spin_unlock_irq(&phba->hbalock);
-
-	/* Cancel all the IOCBs from the completions list */
-	lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT,
-			      IOERR_SLI_ABORTED);
-}
-
-/**
  * lpfc_sli_hba_iocb_abort - Abort all iocbs to an hba.
  * @phba: pointer to lpfc HBA data structure.
  *
@@ -9835,7 +9895,7 @@ lpfc_sli_hba_iocb_abort(struct lpfc_hba *phba)
 
 	for (i = 0; i < psli->num_rings; i++) {
 		pring = &psli->ring[i];
-		lpfc_sli_iocb_ring_abort(phba, pring);
+		lpfc_sli_abort_iocb_ring(phba, pring);
 	}
 }
 
@@ -10060,6 +10120,124 @@ lpfc_sli_abort_iocb(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 }
 
 /**
+ * lpfc_sli_abort_taskmgmt - issue abort for all commands on a host/target/LUN
+ * @vport: Pointer to virtual port.
+ * @pring: Pointer to driver SLI ring object.
+ * @tgt_id: SCSI ID of the target.
+ * @lun_id: LUN ID of the scsi device.
+ * @taskmgmt_cmd: LPFC_CTX_LUN/LPFC_CTX_TGT/LPFC_CTX_HOST.
+ *
+ * This function sends an abort command for every SCSI command
+ * associated with the given virtual port pending on the ring
+ * filtered by lpfc_sli_validate_fcp_iocb function.
+ * When taskmgmt_cmd == LPFC_CTX_LUN, the function sends abort only to the
+ * FCP iocbs associated with lun specified by tgt_id and lun_id
+ * parameters
+ * When taskmgmt_cmd == LPFC_CTX_TGT, the function sends abort only to the
+ * FCP iocbs associated with SCSI target specified by tgt_id parameter.
+ * When taskmgmt_cmd == LPFC_CTX_HOST, the function sends abort to all
+ * FCP iocbs associated with virtual port.
+ * This function returns number of iocbs it aborted .
+ * This function is called with no locks held right after a taskmgmt
+ * command is sent.
+ **/
+int
+lpfc_sli_abort_taskmgmt(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
+			uint16_t tgt_id, uint64_t lun_id, lpfc_ctx_cmd cmd)
+{
+	struct lpfc_hba *phba = vport->phba;
+	struct lpfc_iocbq *abtsiocbq;
+	struct lpfc_iocbq *iocbq;
+	IOCB_t *icmd;
+	int sum, i, ret_val;
+	unsigned long iflags;
+	struct lpfc_sli_ring *pring_s4;
+	uint32_t ring_number;
+
+	spin_lock_irq(&phba->hbalock);
+
+	/* all I/Os are in process of being flushed */
+	if (phba->hba_flag & HBA_FCP_IOQ_FLUSH) {
+		spin_unlock_irq(&phba->hbalock);
+		return 0;
+	}
+	sum = 0;
+
+	for (i = 1; i <= phba->sli.last_iotag; i++) {
+		iocbq = phba->sli.iocbq_lookup[i];
+
+		if (lpfc_sli_validate_fcp_iocb(iocbq, vport, tgt_id, lun_id,
+					       cmd) != 0)
+			continue;
+
+		/*
+		 * If the iocbq is already being aborted, don't take a second
+		 * action, but do count it.
+		 */
+		if (iocbq->iocb_flag & LPFC_DRIVER_ABORTED)
+			continue;
+
+		/* issue ABTS for this IOCB based on iotag */
+		abtsiocbq = __lpfc_sli_get_iocbq(phba);
+		if (abtsiocbq == NULL)
+			continue;
+
+		icmd = &iocbq->iocb;
+		abtsiocbq->iocb.un.acxri.abortType = ABORT_TYPE_ABTS;
+		abtsiocbq->iocb.un.acxri.abortContextTag = icmd->ulpContext;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			abtsiocbq->iocb.un.acxri.abortIoTag =
+							 iocbq->sli4_xritag;
+		else
+			abtsiocbq->iocb.un.acxri.abortIoTag = icmd->ulpIoTag;
+		abtsiocbq->iocb.ulpLe = 1;
+		abtsiocbq->iocb.ulpClass = icmd->ulpClass;
+		abtsiocbq->vport = vport;
+
+		/* ABTS WQE must go to the same WQ as the WQE to be aborted */
+		abtsiocbq->fcp_wqidx = iocbq->fcp_wqidx;
+		if (iocbq->iocb_flag & LPFC_IO_FCP)
+			abtsiocbq->iocb_flag |= LPFC_USE_FCPWQIDX;
+
+		if (lpfc_is_link_up(phba))
+			abtsiocbq->iocb.ulpCommand = CMD_ABORT_XRI_CN;
+		else
+			abtsiocbq->iocb.ulpCommand = CMD_CLOSE_XRI_CN;
+
+		/* Setup callback routine and issue the command. */
+		abtsiocbq->iocb_cmpl = lpfc_sli_abort_fcp_cmpl;
+
+		/*
+		 * Indicate the IO is being aborted by the driver and set
+		 * the caller's flag into the aborted IO.
+		 */
+		iocbq->iocb_flag |= LPFC_DRIVER_ABORTED;
+
+		if (phba->sli_rev == LPFC_SLI_REV4) {
+			ring_number = MAX_SLI3_CONFIGURED_RINGS +
+					 iocbq->fcp_wqidx;
+			pring_s4 = &phba->sli.ring[ring_number];
+			/* Note: both hbalock and ring_lock must be set here */
+			spin_lock_irqsave(&pring_s4->ring_lock, iflags);
+			ret_val = __lpfc_sli_issue_iocb(phba, pring_s4->ringno,
+							abtsiocbq, 0);
+			spin_unlock_irqrestore(&pring_s4->ring_lock, iflags);
+		} else {
+			ret_val = __lpfc_sli_issue_iocb(phba, pring->ringno,
+							abtsiocbq, 0);
+		}
+
+
+		if (ret_val == IOCB_ERROR)
+			__lpfc_sli_release_iocbq(phba, abtsiocbq);
+		else
+			sum++;
+	}
+	spin_unlock_irq(&phba->hbalock);
+	return sum;
+}
+
+/**
  * lpfc_sli_wake_iocb_wait - lpfc_sli_issue_iocb_wait's completion handler
  * @phba: Pointer to HBA context object.
  * @cmdiocbq: Pointer to command iocb.
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 6f04080f4ea..edb48832c39 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index 9b8cda86617..7f50aa04d66 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2009-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2009-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index e32cbec7032..41675c1193e 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -1,7 +1,7 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
+ * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.emulex.com                                                  *
  *                                                                 *
@@ -18,7 +18,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "8.3.45"
+#define LPFC_DRIVER_VERSION "10.2.8001.0."
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
@@ -30,4 +30,4 @@
 
 #define LPFC_MODULE_DESC "Emulex LightPulse Fibre Channel SCSI driver " \
 		LPFC_DRIVER_VERSION
-#define LPFC_COPYRIGHT "Copyright(c) 2004-2013 Emulex.  All rights reserved."
+#define LPFC_COPYRIGHT "Copyright(c) 2004-2014 Emulex.  All rights reserved."
diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
index f5cdc68cd5b..6a039eb1cbc 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -25,10 +25,6 @@
  * 1+ (800) 334-5454
  */
 
-/*
- * $Log: mac_NCR5380.c,v $
- */
-
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/ctype.h>
@@ -58,12 +54,6 @@
 
 #include "NCR5380.h"
 
-#if 0
-#define NDEBUG (NDEBUG_INTR | NDEBUG_PSEUDO_DMA | NDEBUG_ARBITRATION | NDEBUG_SELECTION | NDEBUG_RESELECTION)
-#else
-#define NDEBUG (NDEBUG_ABORT)
-#endif
-
 #define RESET_BOOT
 #define DRIVER_SETUP
 
diff --git a/drivers/scsi/mac_scsi.h b/drivers/scsi/mac_scsi.h
index 7dc62fce1c4..06969b06e54 100644
--- a/drivers/scsi/mac_scsi.h
+++ b/drivers/scsi/mac_scsi.h
@@ -22,10 +22,6 @@
  * 1+ (800) 334-5454
  */
 
-/*
- * $Log: cumana_NCR5380.h,v $
- */
-
 #ifndef MAC_NCR5380_H
 #define MAC_NCR5380_H
 
@@ -51,8 +47,6 @@
 
 #include <scsi/scsicam.h>
 
-#ifndef HOSTS_C
-
 #define NCR5380_implementation_fields \
     int port, ctrl
 
@@ -75,10 +69,6 @@
 #define NCR5380_show_info macscsi_show_info
 #define NCR5380_write_info macscsi_write_info
 
-#define BOARD_NORMAL	0
-#define BOARD_NCR53C400	1
-
-#endif /* ndef HOSTS_C */
 #endif /* ndef ASM */
 #endif /* MAC_NCR5380_H */
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index d84d02c2aad..112799b131a 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -3061,7 +3061,8 @@ megasas_transition_to_ready(struct megasas_instance *instance, int ocr)
 	u32 cur_state;
 	u32 abs_state, curr_abs_state;
 
-	fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) & MFI_STATE_MASK;
+	abs_state = instance->instancet->read_fw_status_reg(instance->reg_set);
+	fw_state = abs_state & MFI_STATE_MASK;
 
 	if (fw_state != MFI_STATE_READY)
 		printk(KERN_INFO "megasas: Waiting for FW to come to ready"
@@ -3069,9 +3070,6 @@ megasas_transition_to_ready(struct megasas_instance *instance, int ocr)
 
 	while (fw_state != MFI_STATE_READY) {
 
-		abs_state =
-		instance->instancet->read_fw_status_reg(instance->reg_set);
-
 		switch (fw_state) {
 
 		case MFI_STATE_FAULT:
@@ -3223,10 +3221,8 @@ megasas_transition_to_ready(struct megasas_instance *instance, int ocr)
 		 * The cur_state should not last for more than max_wait secs
 		 */
 		for (i = 0; i < (max_wait * 1000); i++) {
-			fw_state = instance->instancet->read_fw_status_reg(instance->reg_set) &
-					MFI_STATE_MASK ;
-		curr_abs_state =
-		instance->instancet->read_fw_status_reg(instance->reg_set);
+			curr_abs_state = instance->instancet->
+				read_fw_status_reg(instance->reg_set);
 
 			if (abs_state == curr_abs_state) {
 				msleep(1);
@@ -3242,6 +3238,9 @@ megasas_transition_to_ready(struct megasas_instance *instance, int ocr)
 			       "in %d secs\n", fw_state, max_wait);
 			return -ENODEV;
 		}
+
+		abs_state = curr_abs_state;
+		fw_state = curr_abs_state & MFI_STATE_MASK;
 	}
 	printk(KERN_INFO "megasas: FW now in Ready state\n");
 
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c
index bde63f7452b..8b88118e20e 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
@@ -1739,14 +1739,14 @@ mpt2sas_base_free_smid(struct MPT2SAS_ADAPTER *ioc, u16 smid)
 			list_for_each_entry_safe(chain_req, next,
 			    &ioc->scsi_lookup[i].chain_list, tracker_list) {
 				list_del_init(&chain_req->tracker_list);
-				list_add_tail(&chain_req->tracker_list,
+				list_add(&chain_req->tracker_list,
 				    &ioc->free_chain_list);
 			}
 		}
 		ioc->scsi_lookup[i].cb_idx = 0xFF;
 		ioc->scsi_lookup[i].scmd = NULL;
 		ioc->scsi_lookup[i].direct_io = 0;
-		list_add_tail(&ioc->scsi_lookup[i].tracker_list,
+		list_add(&ioc->scsi_lookup[i].tracker_list,
 		    &ioc->free_list);
 		spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
 
@@ -1764,13 +1764,13 @@ mpt2sas_base_free_smid(struct MPT2SAS_ADAPTER *ioc, u16 smid)
 		/* hi-priority */
 		i = smid - ioc->hi_priority_smid;
 		ioc->hpr_lookup[i].cb_idx = 0xFF;
-		list_add_tail(&ioc->hpr_lookup[i].tracker_list,
+		list_add(&ioc->hpr_lookup[i].tracker_list,
 		    &ioc->hpr_free_list);
 	} else if (smid <= ioc->hba_queue_depth) {
 		/* internal queue */
 		i = smid - ioc->internal_smid;
 		ioc->internal_lookup[i].cb_idx = 0xFF;
-		list_add_tail(&ioc->internal_lookup[i].tracker_list,
+		list_add(&ioc->internal_lookup[i].tracker_list,
 		    &ioc->internal_free_list);
 	}
 	spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.h b/drivers/scsi/mpt2sas/mpt2sas_base.h
index 1f2ac3a2862..fd3b998c75b 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.h
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.h
@@ -1065,7 +1065,7 @@ void mpt2sas_scsih_event_callback(struct MPT2SAS_ADAPTER *ioc, u8 msix_index,
     u32 reply);
 int mpt2sas_scsih_issue_tm(struct MPT2SAS_ADAPTER *ioc, u16 handle,
 	uint channel, uint id, uint lun, u8 type, u16 smid_task,
-	ulong timeout, unsigned long serial_number, enum mutex_type m_type);
+	ulong timeout, enum mutex_type m_type);
 void mpt2sas_scsih_set_tm_flag(struct MPT2SAS_ADAPTER *ioc, u16 handle);
 void mpt2sas_scsih_clear_tm_flag(struct MPT2SAS_ADAPTER *ioc, u16 handle);
 void mpt2sas_expander_remove(struct MPT2SAS_ADAPTER *ioc, u64 sas_address);
diff --git a/drivers/scsi/mpt2sas/mpt2sas_ctl.c b/drivers/scsi/mpt2sas/mpt2sas_ctl.c
index b7f887c9b0b..62df8f9d427 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_ctl.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_ctl.c
@@ -987,7 +987,7 @@ _ctl_do_mpt_command(struct MPT2SAS_ADAPTER *ioc, struct mpt2_ioctl_command karg,
 			mpt2sas_scsih_issue_tm(ioc,
 			    le16_to_cpu(mpi_request->FunctionDependent1), 0, 0,
 			    0, MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0, 10,
-			    0, TM_MUTEX_ON);
+			    TM_MUTEX_ON);
 			ioc->tm_cmds.status = MPT2_CMD_NOT_USED;
 		} else
 			mpt2sas_base_hard_reset_handler(ioc, CAN_SLEEP,
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 6fd7d40b2c4..5055f925d2c 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -2368,7 +2368,6 @@ mpt2sas_scsih_clear_tm_flag(struct MPT2SAS_ADAPTER *ioc, u16 handle)
  * @type: MPI2_SCSITASKMGMT_TASKTYPE__XXX (defined in mpi2_init.h)
  * @smid_task: smid assigned to the task
  * @timeout: timeout in seconds
- * @serial_number: the serial_number from scmd
  * @m_type: TM_MUTEX_ON or TM_MUTEX_OFF
  * Context: user
  *
@@ -2381,7 +2380,7 @@ mpt2sas_scsih_clear_tm_flag(struct MPT2SAS_ADAPTER *ioc, u16 handle)
 int
 mpt2sas_scsih_issue_tm(struct MPT2SAS_ADAPTER *ioc, u16 handle, uint channel,
     uint id, uint lun, u8 type, u16 smid_task, ulong timeout,
-	unsigned long serial_number, enum mutex_type m_type)
+	enum mutex_type m_type)
 {
 	Mpi2SCSITaskManagementRequest_t *mpi_request;
 	Mpi2SCSITaskManagementReply_t *mpi_reply;
@@ -2634,8 +2633,7 @@ _scsih_abort(struct scsi_cmnd *scmd)
 	handle = sas_device_priv_data->sas_target->handle;
 	r = mpt2sas_scsih_issue_tm(ioc, handle, scmd->device->channel,
 	    scmd->device->id, scmd->device->lun,
-	    MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK, smid, 30,
-	    scmd->serial_number, TM_MUTEX_ON);
+	    MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK, smid, 30, TM_MUTEX_ON);
 
  out:
 	sdev_printk(KERN_INFO, scmd->device, "task abort: %s scmd(%p)\n",
@@ -2696,8 +2694,7 @@ _scsih_dev_reset(struct scsi_cmnd *scmd)
 
 	r = mpt2sas_scsih_issue_tm(ioc, handle, scmd->device->channel,
 	    scmd->device->id, scmd->device->lun,
-	    MPI2_SCSITASKMGMT_TASKTYPE_LOGICAL_UNIT_RESET, 0, 30, 0,
-	    TM_MUTEX_ON);
+	    MPI2_SCSITASKMGMT_TASKTYPE_LOGICAL_UNIT_RESET, 0, 30, TM_MUTEX_ON);
 
  out:
 	sdev_printk(KERN_INFO, scmd->device, "device reset: %s scmd(%p)\n",
@@ -2757,7 +2754,7 @@ _scsih_target_reset(struct scsi_cmnd *scmd)
 
 	r = mpt2sas_scsih_issue_tm(ioc, handle, scmd->device->channel,
 	    scmd->device->id, 0, MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0,
-	    30, 0, TM_MUTEX_ON);
+	    30, TM_MUTEX_ON);
 
  out:
 	starget_printk(KERN_INFO, starget, "target reset: %s scmd(%p)\n",
@@ -3953,9 +3950,9 @@ _scsih_setup_direct_io(struct MPT2SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
  * SCSI_MLQUEUE_HOST_BUSY if the entire host queue is full
  */
 static int
-_scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
+_scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 {
-	struct MPT2SAS_ADAPTER *ioc = shost_priv(scmd->device->host);
+	struct MPT2SAS_ADAPTER *ioc = shost_priv(shost);
 	struct MPT2SAS_DEVICE *sas_device_priv_data;
 	struct MPT2SAS_TARGET *sas_target_priv_data;
 	struct _raid_device *raid_device;
@@ -3963,7 +3960,6 @@ _scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
 	u32 mpi_control;
 	u16 smid;
 
-	scmd->scsi_done = done;
 	sas_device_priv_data = scmd->device->hostdata;
 	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
 		scmd->result = DID_NO_CONNECT << 16;
@@ -4039,7 +4035,7 @@ _scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
 	    MPT_TARGET_FLAGS_RAID_COMPONENT)
 		mpi_request->Function = MPI2_FUNCTION_RAID_SCSI_IO_PASSTHROUGH;
 	else
-		mpi_request->Function = MPI2_FUNCTION_SCSI_IO_REQUEST;
+	mpi_request->Function = MPI2_FUNCTION_SCSI_IO_REQUEST;
 	mpi_request->DevHandle =
 	    cpu_to_le16(sas_device_priv_data->sas_target->handle);
 	mpi_request->DataLength = cpu_to_le32(scsi_bufflen(scmd));
@@ -4083,8 +4079,6 @@ _scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
 	return SCSI_MLQUEUE_HOST_BUSY;
 }
 
-static DEF_SCSI_QCMD(_scsih_qcmd)
-
 /**
  * _scsih_normalize_sense - normalize descriptor and fixed format sense data
  * @sense_buffer: sense data returned by target
@@ -5880,7 +5874,7 @@ broadcast_aen_retry:
 
 		spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
 		r = mpt2sas_scsih_issue_tm(ioc, handle, 0, 0, lun,
-		    MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK, smid, 30, 0,
+		    MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK, smid, 30,
 		    TM_MUTEX_OFF);
 		if (r == FAILED) {
 			sdev_printk(KERN_WARNING, sdev,
@@ -5922,7 +5916,7 @@ broadcast_aen_retry:
 
 		r = mpt2sas_scsih_issue_tm(ioc, handle, sdev->channel, sdev->id,
 		    sdev->lun, MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK, smid, 30,
-		    scmd->serial_number, TM_MUTEX_OFF);
+		    TM_MUTEX_OFF);
 		if (r == FAILED) {
 			sdev_printk(KERN_WARNING, sdev,
 			    "mpt2sas_scsih_issue_tm: ABORT_TASK: FAILED : "
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 0ebf5d913c8..9b90a6fef70 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -993,7 +993,7 @@ void mpt3sas_scsih_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase);
 
 int mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle,
 	uint channel, uint id, uint lun, u8 type, u16 smid_task,
-	ulong timeout, unsigned long serial_number,  enum mutex_type m_type);
+	ulong timeout, enum mutex_type m_type);
 void mpt3sas_scsih_set_tm_flag(struct MPT3SAS_ADAPTER *ioc, u16 handle);
 void mpt3sas_scsih_clear_tm_flag(struct MPT3SAS_ADAPTER *ioc, u16 handle);
 void mpt3sas_expander_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 9b89de14a0a..ba9cbe598a9 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -980,7 +980,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 			mpt3sas_scsih_issue_tm(ioc,
 			    le16_to_cpu(mpi_request->FunctionDependent1), 0, 0,
 			    0, MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0, 30,
-			    0, TM_MUTEX_ON);
+			    TM_MUTEX_ON);
 		} else
 			mpt3sas_base_hard_reset_handler(ioc, CAN_SLEEP,
 			    FORCE_BIG_HAMMER);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index a961fe11b52..18e713db1d3 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2029,7 +2029,6 @@ mpt3sas_scsih_clear_tm_flag(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * @type: MPI2_SCSITASKMGMT_TASKTYPE__XXX (defined in mpi2_init.h)
  * @smid_task: smid assigned to the task
  * @timeout: timeout in seconds
- * @serial_number: the serial_number from scmd
  * @m_type: TM_MUTEX_ON or TM_MUTEX_OFF
  * Context: user
  *
@@ -2042,7 +2041,7 @@ mpt3sas_scsih_clear_tm_flag(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 int
 mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, uint channel,
 	uint id, uint lun, u8 type, u16 smid_task, ulong timeout,
-	unsigned long serial_number, enum mutex_type m_type)
+	enum mutex_type m_type)
 {
 	Mpi2SCSITaskManagementRequest_t *mpi_request;
 	Mpi2SCSITaskManagementReply_t *mpi_reply;
@@ -2293,8 +2292,7 @@ _scsih_abort(struct scsi_cmnd *scmd)
 	handle = sas_device_priv_data->sas_target->handle;
 	r = mpt3sas_scsih_issue_tm(ioc, handle, scmd->device->channel,
 	    scmd->device->id, scmd->device->lun,
-	    MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK, smid, 30,
-	    scmd->serial_number, TM_MUTEX_ON);
+	    MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK, smid, 30, TM_MUTEX_ON);
 
  out:
 	sdev_printk(KERN_INFO, scmd->device, "task abort: %s scmd(%p)\n",
@@ -2353,8 +2351,7 @@ _scsih_dev_reset(struct scsi_cmnd *scmd)
 
 	r = mpt3sas_scsih_issue_tm(ioc, handle, scmd->device->channel,
 	    scmd->device->id, scmd->device->lun,
-	    MPI2_SCSITASKMGMT_TASKTYPE_LOGICAL_UNIT_RESET, 0, 30, 0,
-	    TM_MUTEX_ON);
+	    MPI2_SCSITASKMGMT_TASKTYPE_LOGICAL_UNIT_RESET, 0, 30, TM_MUTEX_ON);
 
  out:
 	sdev_printk(KERN_INFO, scmd->device, "device reset: %s scmd(%p)\n",
@@ -2414,7 +2411,7 @@ _scsih_target_reset(struct scsi_cmnd *scmd)
 
 	r = mpt3sas_scsih_issue_tm(ioc, handle, scmd->device->channel,
 	    scmd->device->id, 0, MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET, 0,
-	    30, 0, TM_MUTEX_ON);
+	    30, TM_MUTEX_ON);
 
  out:
 	starget_printk(KERN_INFO, starget, "target reset: %s scmd(%p)\n",
@@ -3518,7 +3515,7 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
 
 
 /**
- * _scsih_qcmd_lck - main scsi request entry point
+ * _scsih_qcmd - main scsi request entry point
  * @scmd: pointer to scsi command object
  * @done: function pointer to be invoked on completion
  *
@@ -3529,9 +3526,9 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
  * SCSI_MLQUEUE_HOST_BUSY if the entire host queue is full
  */
 static int
-_scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
+_scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 {
-	struct MPT3SAS_ADAPTER *ioc = shost_priv(scmd->device->host);
+	struct MPT3SAS_ADAPTER *ioc = shost_priv(shost);
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	struct MPT3SAS_TARGET *sas_target_priv_data;
 	Mpi2SCSIIORequest_t *mpi_request;
@@ -3544,7 +3541,6 @@ _scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
 		scsi_print_command(scmd);
 #endif
 
-	scmd->scsi_done = done;
 	sas_device_priv_data = scmd->device->hostdata;
 	if (!sas_device_priv_data || !sas_device_priv_data->sas_target) {
 		scmd->result = DID_NO_CONNECT << 16;
@@ -3659,8 +3655,6 @@ _scsih_qcmd_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
  out:
 	return SCSI_MLQUEUE_HOST_BUSY;
 }
-static DEF_SCSI_QCMD(_scsih_qcmd)
-
 
 /**
  * _scsih_normalize_sense - normalize descriptor and fixed format sense data
@@ -5425,7 +5419,7 @@ _scsih_sas_broadcast_primitive_event(struct MPT3SAS_ADAPTER *ioc,
 
 		spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
 		r = mpt3sas_scsih_issue_tm(ioc, handle, 0, 0, lun,
-		    MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK, smid, 30, 0,
+		    MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK, smid, 30,
 		    TM_MUTEX_OFF);
 		if (r == FAILED) {
 			sdev_printk(KERN_WARNING, sdev,
@@ -5467,7 +5461,7 @@ _scsih_sas_broadcast_primitive_event(struct MPT3SAS_ADAPTER *ioc,
 
 		r = mpt3sas_scsih_issue_tm(ioc, handle, sdev->channel, sdev->id,
 		    sdev->lun, MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK, smid, 30,
-		    scmd->serial_number, TM_MUTEX_OFF);
+		    TM_MUTEX_OFF);
 		if (r == FAILED) {
 			sdev_printk(KERN_WARNING, sdev,
 			    "mpt3sas_scsih_issue_tm: ABORT_TASK: FAILED : "
diff --git a/drivers/scsi/mvsas/mv_94xx.c b/drivers/scsi/mvsas/mv_94xx.c
index 1e4479f3331..9270d15ff1a 100644
--- a/drivers/scsi/mvsas/mv_94xx.c
+++ b/drivers/scsi/mvsas/mv_94xx.c
@@ -564,7 +564,7 @@ static void mvs_94xx_interrupt_enable(struct mvs_info *mvi)
 	u32 tmp;
 
 	tmp = mr32(MVS_GBL_CTL);
-	tmp |= (IRQ_SAS_A | IRQ_SAS_B);
+	tmp |= (MVS_IRQ_SAS_A | MVS_IRQ_SAS_B);
 	mw32(MVS_GBL_INT_STAT, tmp);
 	writel(tmp, regs + 0x0C);
 	writel(tmp, regs + 0x10);
@@ -580,7 +580,7 @@ static void mvs_94xx_interrupt_disable(struct mvs_info *mvi)
 
 	tmp = mr32(MVS_GBL_CTL);
 
-	tmp &= ~(IRQ_SAS_A | IRQ_SAS_B);
+	tmp &= ~(MVS_IRQ_SAS_A | MVS_IRQ_SAS_B);
 	mw32(MVS_GBL_INT_STAT, tmp);
 	writel(tmp, regs + 0x0C);
 	writel(tmp, regs + 0x10);
@@ -596,7 +596,7 @@ static u32 mvs_94xx_isr_status(struct mvs_info *mvi, int irq)
 	if (!(mvi->flags & MVF_FLAG_SOC)) {
 		stat = mr32(MVS_GBL_INT_STAT);
 
-		if (!(stat & (IRQ_SAS_A | IRQ_SAS_B)))
+		if (!(stat & (MVS_IRQ_SAS_A | MVS_IRQ_SAS_B)))
 			return 0;
 	}
 	return stat;
@@ -606,8 +606,8 @@ static irqreturn_t mvs_94xx_isr(struct mvs_info *mvi, int irq, u32 stat)
 {
 	void __iomem *regs = mvi->regs;
 
-	if (((stat & IRQ_SAS_A) && mvi->id == 0) ||
-			((stat & IRQ_SAS_B) && mvi->id == 1)) {
+	if (((stat & MVS_IRQ_SAS_A) && mvi->id == 0) ||
+			((stat & MVS_IRQ_SAS_B) && mvi->id == 1)) {
 		mw32_f(MVS_INT_STAT, CINT_DONE);
 
 		spin_lock(&mvi->lock);
diff --git a/drivers/scsi/mvsas/mv_94xx.h b/drivers/scsi/mvsas/mv_94xx.h
index 487aa6f9741..14e197497b4 100644
--- a/drivers/scsi/mvsas/mv_94xx.h
+++ b/drivers/scsi/mvsas/mv_94xx.h
@@ -150,35 +150,35 @@ enum chip_register_bits {
 
 enum pci_interrupt_cause {
 	/*  MAIN_IRQ_CAUSE (R10200) Bits*/
-	IRQ_COM_IN_I2O_IOP0            = (1 << 0),
-	IRQ_COM_IN_I2O_IOP1            = (1 << 1),
-	IRQ_COM_IN_I2O_IOP2            = (1 << 2),
-	IRQ_COM_IN_I2O_IOP3            = (1 << 3),
-	IRQ_COM_OUT_I2O_HOS0           = (1 << 4),
-	IRQ_COM_OUT_I2O_HOS1           = (1 << 5),
-	IRQ_COM_OUT_I2O_HOS2           = (1 << 6),
-	IRQ_COM_OUT_I2O_HOS3           = (1 << 7),
-	IRQ_PCIF_TO_CPU_DRBL0          = (1 << 8),
-	IRQ_PCIF_TO_CPU_DRBL1          = (1 << 9),
-	IRQ_PCIF_TO_CPU_DRBL2          = (1 << 10),
-	IRQ_PCIF_TO_CPU_DRBL3          = (1 << 11),
-	IRQ_PCIF_DRBL0                 = (1 << 12),
-	IRQ_PCIF_DRBL1                 = (1 << 13),
-	IRQ_PCIF_DRBL2                 = (1 << 14),
-	IRQ_PCIF_DRBL3                 = (1 << 15),
-	IRQ_XOR_A                      = (1 << 16),
-	IRQ_XOR_B                      = (1 << 17),
-	IRQ_SAS_A                      = (1 << 18),
-	IRQ_SAS_B                      = (1 << 19),
-	IRQ_CPU_CNTRL                  = (1 << 20),
-	IRQ_GPIO                       = (1 << 21),
-	IRQ_UART                       = (1 << 22),
-	IRQ_SPI                        = (1 << 23),
-	IRQ_I2C                        = (1 << 24),
-	IRQ_SGPIO                      = (1 << 25),
-	IRQ_COM_ERR                    = (1 << 29),
-	IRQ_I2O_ERR                    = (1 << 30),
-	IRQ_PCIE_ERR                   = (1 << 31),
+	MVS_IRQ_COM_IN_I2O_IOP0        = (1 << 0),
+	MVS_IRQ_COM_IN_I2O_IOP1        = (1 << 1),
+	MVS_IRQ_COM_IN_I2O_IOP2        = (1 << 2),
+	MVS_IRQ_COM_IN_I2O_IOP3        = (1 << 3),
+	MVS_IRQ_COM_OUT_I2O_HOS0       = (1 << 4),
+	MVS_IRQ_COM_OUT_I2O_HOS1       = (1 << 5),
+	MVS_IRQ_COM_OUT_I2O_HOS2       = (1 << 6),
+	MVS_IRQ_COM_OUT_I2O_HOS3       = (1 << 7),
+	MVS_IRQ_PCIF_TO_CPU_DRBL0      = (1 << 8),
+	MVS_IRQ_PCIF_TO_CPU_DRBL1      = (1 << 9),
+	MVS_IRQ_PCIF_TO_CPU_DRBL2      = (1 << 10),
+	MVS_IRQ_PCIF_TO_CPU_DRBL3      = (1 << 11),
+	MVS_IRQ_PCIF_DRBL0             = (1 << 12),
+	MVS_IRQ_PCIF_DRBL1             = (1 << 13),
+	MVS_IRQ_PCIF_DRBL2             = (1 << 14),
+	MVS_IRQ_PCIF_DRBL3             = (1 << 15),
+	MVS_IRQ_XOR_A                  = (1 << 16),
+	MVS_IRQ_XOR_B                  = (1 << 17),
+	MVS_IRQ_SAS_A                  = (1 << 18),
+	MVS_IRQ_SAS_B                  = (1 << 19),
+	MVS_IRQ_CPU_CNTRL              = (1 << 20),
+	MVS_IRQ_GPIO                   = (1 << 21),
+	MVS_IRQ_UART                   = (1 << 22),
+	MVS_IRQ_SPI                    = (1 << 23),
+	MVS_IRQ_I2C                    = (1 << 24),
+	MVS_IRQ_SGPIO                  = (1 << 25),
+	MVS_IRQ_COM_ERR                = (1 << 29),
+	MVS_IRQ_I2O_ERR                = (1 << 30),
+	MVS_IRQ_PCIE_ERR               = (1 << 31),
 };
 
 union reg_phy_cfg {
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index 5ff978be249..eacee48a955 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -728,6 +728,15 @@ static struct pci_device_id mvs_pci_table[] = {
 		.class_mask	= 0,
 		.driver_data	= chip_9485,
 	},
+	{
+		.vendor		= PCI_VENDOR_ID_MARVELL_EXT,
+		.device		= 0x9485,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= 0x9485,
+		.class		= 0,
+		.class_mask	= 0,
+		.driver_data	= chip_9485,
+	},
 	{ PCI_VDEVICE(OCZ, 0x1021), chip_9485}, /* OCZ RevoDrive3 */
 	{ PCI_VDEVICE(OCZ, 0x1022), chip_9485}, /* OCZ RevoDrive3/zDriveR4 (exact model unknown) */
 	{ PCI_VDEVICE(OCZ, 0x1040), chip_9485}, /* OCZ RevoDrive3/zDriveR4 (exact model unknown) */
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index bac04c2335a..5f4cbf0c475 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -1570,6 +1570,7 @@ static struct request *_make_request(struct request_queue *q, bool has_write,
 		if (unlikely(!req))
 			return ERR_PTR(-ENOMEM);
 
+		blk_rq_set_block_pc(req);
 		return req;
 	}
 }
@@ -1590,7 +1591,6 @@ static int _init_blk_request(struct osd_request *or,
 	}
 
 	or->request = req;
-	req->cmd_type = REQ_TYPE_BLOCK_PC;
 	req->cmd_flags |= REQ_QUIET;
 
 	req->timeout = or->timeout;
@@ -1608,7 +1608,7 @@ static int _init_blk_request(struct osd_request *or,
 				ret = PTR_ERR(req);
 				goto out;
 			}
-			req->cmd_type = REQ_TYPE_BLOCK_PC;
+			blk_rq_set_block_pc(req);
 			or->in.req = or->request->next_rq = req;
 		}
 	} else if (has_in)
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index 21883a2d632..0727ea7cc38 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -365,7 +365,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
 	if (!req)
 		return DRIVER_ERROR << 24;
 
-	req->cmd_type = REQ_TYPE_BLOCK_PC;
+	blk_rq_set_block_pc(req);
 	req->cmd_flags |= REQ_QUIET;
 
 	SRpnt->bio = NULL;
diff --git a/drivers/scsi/pas16.h b/drivers/scsi/pas16.h
index 3721342835e..aa528f53c53 100644
--- a/drivers/scsi/pas16.h
+++ b/drivers/scsi/pas16.h
@@ -129,8 +129,6 @@ static int pas16_bus_reset(Scsi_Cmnd *);
 #define CAN_QUEUE 32 
 #endif
 
-#ifndef HOSTS_C
-
 #define NCR5380_implementation_fields \
     volatile unsigned short io_port
 
@@ -171,6 +169,5 @@ static int pas16_bus_reset(Scsi_Cmnd *);
    
 #define PAS16_IRQS 0xd4a8 
 
-#endif /* else def HOSTS_C */
 #endif /* ndef ASM */
 #endif /* PAS16_H */
diff --git a/drivers/scsi/pm8001/pm8001_ctl.c b/drivers/scsi/pm8001/pm8001_ctl.c
index 28b4e813915..a368d77b8d4 100644
--- a/drivers/scsi/pm8001/pm8001_ctl.c
+++ b/drivers/scsi/pm8001/pm8001_ctl.c
@@ -395,6 +395,8 @@ static ssize_t pm8001_ctl_bios_version_show(struct device *cdev,
 	payload.offset = 0;
 	payload.length = 4096;
 	payload.func_specific = kzalloc(4096, GFP_KERNEL);
+	if (!payload.func_specific)
+		return -ENOMEM;
 	PM8001_CHIP_DISP->get_nvmd_req(pm8001_ha, &payload);
 	wait_for_completion(&completion);
 	virt_addr = pm8001_ha->memoryMap.region[NVMD].virt_ptr;
@@ -402,6 +404,7 @@ static ssize_t pm8001_ctl_bios_version_show(struct device *cdev,
 		bios_index++)
 		str += sprintf(str, "%c",
 			*((u8 *)((u8 *)virt_addr+bios_index)));
+	kfree(payload.func_specific);
 	return str - buf;
 }
 static DEVICE_ATTR(bios_version, S_IRUGO, pm8001_ctl_bios_version_show, NULL);
@@ -729,7 +732,7 @@ static ssize_t pm8001_show_update_fw(struct device *cdev,
 			flash_error_table[i].reason);
 }
 
-static DEVICE_ATTR(update_fw, S_IRUGO|S_IWUGO,
+static DEVICE_ATTR(update_fw, S_IRUGO|S_IWUSR|S_IWGRP,
 	pm8001_show_update_fw, pm8001_store_update_fw);
 struct device_attribute *pm8001_host_attrs[] = {
 	&dev_attr_interface_rev,
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index c4f31b21feb..e90c89f1d48 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -677,7 +677,7 @@ static void pm8001_init_sas_add(struct pm8001_hba_info *pm8001_ha)
  * pm8001_get_phy_settings_info : Read phy setting values.
  * @pm8001_ha : our hba.
  */
-void pm8001_get_phy_settings_info(struct pm8001_hba_info *pm8001_ha)
+static int pm8001_get_phy_settings_info(struct pm8001_hba_info *pm8001_ha)
 {
 
 #ifdef PM8001_READ_VPD
@@ -691,11 +691,15 @@ void pm8001_get_phy_settings_info(struct pm8001_hba_info *pm8001_ha)
 	payload.offset = 0;
 	payload.length = 4096;
 	payload.func_specific = kzalloc(4096, GFP_KERNEL);
+	if (!payload.func_specific)
+		return -ENOMEM;
 	/* Read phy setting values from flash */
 	PM8001_CHIP_DISP->get_nvmd_req(pm8001_ha, &payload);
 	wait_for_completion(&completion);
 	pm8001_set_phy_profile(pm8001_ha, sizeof(u8), payload.func_specific);
+	kfree(payload.func_specific);
 #endif
+	return 0;
 }
 
 #ifdef PM8001_USE_MSIX
@@ -879,8 +883,11 @@ static int pm8001_pci_probe(struct pci_dev *pdev,
 	pm8001_init_sas_add(pm8001_ha);
 	/* phy setting support for motherboard controller */
 	if (pdev->subsystem_vendor != PCI_VENDOR_ID_ADAPTEC2 &&
-		pdev->subsystem_vendor != 0)
-		pm8001_get_phy_settings_info(pm8001_ha);
+		pdev->subsystem_vendor != 0) {
+		rc = pm8001_get_phy_settings_info(pm8001_ha);
+		if (rc)
+			goto err_out_shost;
+	}
 	pm8001_post_sas_ha_init(shost, chip);
 	rc = sas_register_ha(SHOST_TO_SAS_HA(shost));
 	if (rc)
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 07befcf365b..16fe5196e6d 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -664,7 +664,7 @@ do_read:
 		}
 
 		rval = qla2x00_read_sfp(vha, ha->sfp_data_dma, ha->sfp_data,
-		    addr, offset, SFP_BLOCK_SIZE, 0);
+		    addr, offset, SFP_BLOCK_SIZE, BIT_1);
 		if (rval != QLA_SUCCESS) {
 			ql_log(ql_log_warn, vha, 0x706d,
 			    "Unable to read SFP data (%x/%x/%x).\n", rval,
@@ -1495,7 +1495,7 @@ qla2x00_fw_dump_size_show(struct device *dev, struct device_attribute *attr,
 
 	if (!ha->fw_dumped)
 		size = 0;
-	else if (IS_QLA82XX(ha))
+	else if (IS_P3P_TYPE(ha))
 		size = ha->md_template_size + ha->md_dump_size;
 	else
 		size = ha->fw_dump_len;
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 71ff340f6de..524f9eb7fcd 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2012 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -2054,9 +2054,49 @@ qla26xx_serdes_op(struct fc_bsg_job *bsg_job)
 		bsg_job->reply->reply_payload_rcv_len = sizeof(sr);
 		break;
 	default:
-		ql_log(ql_log_warn, vha, 0x708c,
+		ql_dbg(ql_dbg_user, vha, 0x708c,
 		    "Unknown serdes cmd %x.\n", sr.cmd);
-		rval = -EDOM;
+		rval = -EINVAL;
+		break;
+	}
+
+	bsg_job->reply->reply_data.vendor_reply.vendor_rsp[0] =
+	    rval ? EXT_STATUS_MAILBOX : 0;
+
+	bsg_job->reply_len = sizeof(struct fc_bsg_reply);
+	bsg_job->reply->result = DID_OK << 16;
+	bsg_job->job_done(bsg_job);
+	return 0;
+}
+
+static int
+qla8044_serdes_op(struct fc_bsg_job *bsg_job)
+{
+	struct Scsi_Host *host = bsg_job->shost;
+	scsi_qla_host_t *vha = shost_priv(host);
+	int rval = 0;
+	struct qla_serdes_reg_ex sr;
+
+	memset(&sr, 0, sizeof(sr));
+
+	sg_copy_to_buffer(bsg_job->request_payload.sg_list,
+	    bsg_job->request_payload.sg_cnt, &sr, sizeof(sr));
+
+	switch (sr.cmd) {
+	case INT_SC_SERDES_WRITE_REG:
+		rval = qla8044_write_serdes_word(vha, sr.addr, sr.val);
+		bsg_job->reply->reply_payload_rcv_len = 0;
+		break;
+	case INT_SC_SERDES_READ_REG:
+		rval = qla8044_read_serdes_word(vha, sr.addr, &sr.val);
+		sg_copy_from_buffer(bsg_job->reply_payload.sg_list,
+		    bsg_job->reply_payload.sg_cnt, &sr, sizeof(sr));
+		bsg_job->reply->reply_payload_rcv_len = sizeof(sr);
+		break;
+	default:
+		ql_dbg(ql_dbg_user, vha, 0x70cf,
+		    "Unknown serdes cmd %x.\n", sr.cmd);
+		rval = -EINVAL;
 		break;
 	}
 
@@ -2121,6 +2161,9 @@ qla2x00_process_vendor_specific(struct fc_bsg_job *bsg_job)
 	case QL_VND_SERDES_OP:
 		return qla26xx_serdes_op(bsg_job);
 
+	case QL_VND_SERDES_OP_EX:
+		return qla8044_serdes_op(bsg_job);
+
 	default:
 		return -ENOSYS;
 	}
diff --git a/drivers/scsi/qla2xxx/qla_bsg.h b/drivers/scsi/qla2xxx/qla_bsg.h
index e5c2126221e..d38f9efa56f 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.h
+++ b/drivers/scsi/qla2xxx/qla_bsg.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -24,6 +24,7 @@
 #define QL_VND_READ_I2C		0x11
 #define QL_VND_FX00_MGMT_CMD	0x12
 #define QL_VND_SERDES_OP	0x13
+#define	QL_VND_SERDES_OP_EX	0x14
 
 /* BSG Vendor specific subcode returns */
 #define EXT_STATUS_OK			0
@@ -225,4 +226,10 @@ struct qla_serdes_reg {
 	uint16_t val;
 } __packed;
 
+struct qla_serdes_reg_ex {
+	uint16_t cmd;
+	uint32_t addr;
+	uint32_t val;
+} __packed;
+
 #endif
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 97255f7c397..c72ee97bf3f 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -15,7 +15,7 @@
  * |                              |                    | 0x0144,0x0146	|
  * |                              |                    | 0x015b-0x0160	|
  * |                              |                    | 0x016e-0x0170	|
- * | Mailbox commands             |       0x1187       | 0x1018-0x1019	|
+ * | Mailbox commands             |       0x118d       | 0x1018-0x1019	|
  * |                              |                    | 0x10ca         |
  * |                              |                    | 0x1115-0x1116  |
  * |                              |                    | 0x111a-0x111b	|
@@ -45,12 +45,16 @@
  * |                              |                    | 0x70ad-0x70ae  |
  * |                              |                    | 0x70d7-0x70db  |
  * |                              |                    | 0x70de-0x70df  |
- * | Task Management              |       0x803d       | 0x8025-0x8026  |
- * |                              |                    | 0x800b,0x8039  |
+ * | Task Management              |       0x803d       | 0x8000,0x800b  |
+ * |                              |                    | 0x8019         |
+ * |                              |                    | 0x8025,0x8026  |
+ * |                              |                    | 0x8031,0x8032  |
+ * |                              |                    | 0x8039,0x803c  |
  * | AER/EEH                      |       0x9011       |		|
  * | Virtual Port                 |       0xa007       |		|
- * | ISP82XX Specific             |       0xb14c       | 0xb002,0xb024  |
+ * | ISP82XX Specific             |       0xb157       | 0xb002,0xb024  |
  * |                              |                    | 0xb09e,0xb0ae  |
+ * |				  |		       | 0xb0c3,0xb0c6  |
  * |                              |                    | 0xb0e0-0xb0ef  |
  * |                              |                    | 0xb085,0xb0dc  |
  * |                              |                    | 0xb107,0xb108  |
@@ -60,12 +64,12 @@
  * |                              |                    | 0xb13c-0xb140  |
  * |                              |                    | 0xb149		|
  * | MultiQ                       |       0xc00c       |		|
- * | Misc                         |       0xd2ff       | 0xd017-0xd019	|
+ * | Misc                         |       0xd212       | 0xd017-0xd019	|
  * |                              |                    | 0xd020		|
- * |                              |                    | 0xd02e-0xd0ff	|
+ * |                              |                    | 0xd030-0xd0ff	|
  * |                              |                    | 0xd101-0xd1fe	|
- * |                              |                    | 0xd212-0xd2fe	|
- * | Target Mode		  |	  0xe070       | 0xe021		|
+ * |                              |                    | 0xd213-0xd2fe	|
+ * | Target Mode		  |	  0xe078       |		|
  * | Target Mode Management	  |	  0xf072       | 0xf002-0xf003	|
  * |                              |                    | 0xf046-0xf049  |
  * | Target Mode Task Management  |	  0x1000b      |		|
@@ -277,9 +281,15 @@ qla24xx_dump_memory(struct qla_hw_data *ha, uint32_t *code_ram,
 	if (rval != QLA_SUCCESS)
 		return rval;
 
+	set_bit(RISC_SRAM_DUMP_CMPL, &ha->fw_dump_cap_flags);
+
 	/* External Memory. */
-	return qla24xx_dump_ram(ha, 0x100000, *nxt,
+	rval = qla24xx_dump_ram(ha, 0x100000, *nxt,
 	    ha->fw_memory_size - 0x100000 + 1, nxt);
+	if (rval == QLA_SUCCESS)
+		set_bit(RISC_EXT_MEM_DUMP_CMPL, &ha->fw_dump_cap_flags);
+
+	return rval;
 }
 
 static uint32_t *
@@ -296,23 +306,15 @@ qla24xx_read_window(struct device_reg_24xx __iomem *reg, uint32_t iobase,
 	return buf;
 }
 
-int
-qla24xx_pause_risc(struct device_reg_24xx __iomem *reg)
+void
+qla24xx_pause_risc(struct device_reg_24xx __iomem *reg, struct qla_hw_data *ha)
 {
-	int rval = QLA_SUCCESS;
-	uint32_t cnt;
-
 	WRT_REG_DWORD(&reg->hccr, HCCRX_SET_RISC_PAUSE);
-	for (cnt = 30000;
-	    ((RD_REG_DWORD(&reg->host_status) & HSRX_RISC_PAUSED) == 0) &&
-	    rval == QLA_SUCCESS; cnt--) {
-		if (cnt)
-			udelay(100);
-		else
-			rval = QLA_FUNCTION_TIMEOUT;
-	}
 
-	return rval;
+	/* 100 usec delay is sufficient enough for hardware to pause RISC */
+	udelay(100);
+	if (RD_REG_DWORD(&reg->host_status) & HSRX_RISC_PAUSED)
+		set_bit(RISC_PAUSE_CMPL, &ha->fw_dump_cap_flags);
 }
 
 int
@@ -320,10 +322,14 @@ qla24xx_soft_reset(struct qla_hw_data *ha)
 {
 	int rval = QLA_SUCCESS;
 	uint32_t cnt;
-	uint16_t mb0, wd;
+	uint16_t wd;
 	struct device_reg_24xx __iomem *reg = &ha->iobase->isp24;
 
-	/* Reset RISC. */
+	/*
+	 * Reset RISC. The delay is dependent on system architecture.
+	 * Driver can proceed with the reset sequence after waiting
+	 * for a timeout period.
+	 */
 	WRT_REG_DWORD(&reg->ctrl_status, CSRX_DMA_SHUTDOWN|MWB_4096_BYTES);
 	for (cnt = 0; cnt < 30000; cnt++) {
 		if ((RD_REG_DWORD(&reg->ctrl_status) & CSRX_DMA_ACTIVE) == 0)
@@ -331,19 +337,14 @@ qla24xx_soft_reset(struct qla_hw_data *ha)
 
 		udelay(10);
 	}
+	if (!(RD_REG_DWORD(&reg->ctrl_status) & CSRX_DMA_ACTIVE))
+		set_bit(DMA_SHUTDOWN_CMPL, &ha->fw_dump_cap_flags);
 
 	WRT_REG_DWORD(&reg->ctrl_status,
 	    CSRX_ISP_SOFT_RESET|CSRX_DMA_SHUTDOWN|MWB_4096_BYTES);
 	pci_read_config_word(ha->pdev, PCI_COMMAND, &wd);
 
 	udelay(100);
-	/* Wait for firmware to complete NVRAM accesses. */
-	mb0 = (uint32_t) RD_REG_WORD(&reg->mailbox0);
-	for (cnt = 10000 ; cnt && mb0; cnt--) {
-		udelay(5);
-		mb0 = (uint32_t) RD_REG_WORD(&reg->mailbox0);
-		barrier();
-	}
 
 	/* Wait for soft-reset to complete. */
 	for (cnt = 0; cnt < 30000; cnt++) {
@@ -353,16 +354,21 @@ qla24xx_soft_reset(struct qla_hw_data *ha)
 
 		udelay(10);
 	}
+	if (!(RD_REG_DWORD(&reg->ctrl_status) & CSRX_ISP_SOFT_RESET))
+		set_bit(ISP_RESET_CMPL, &ha->fw_dump_cap_flags);
+
 	WRT_REG_DWORD(&reg->hccr, HCCRX_CLR_RISC_RESET);
 	RD_REG_DWORD(&reg->hccr);             /* PCI Posting. */
 
-	for (cnt = 30000; RD_REG_WORD(&reg->mailbox0) != 0 &&
+	for (cnt = 10000; RD_REG_WORD(&reg->mailbox0) != 0 &&
 	    rval == QLA_SUCCESS; cnt--) {
 		if (cnt)
-			udelay(100);
+			udelay(10);
 		else
 			rval = QLA_FUNCTION_TIMEOUT;
 	}
+	if (rval == QLA_SUCCESS)
+		set_bit(RISC_RDY_AFT_RESET, &ha->fw_dump_cap_flags);
 
 	return rval;
 }
@@ -659,12 +665,13 @@ qla2xxx_dump_post_process(scsi_qla_host_t *vha, int rval)
 
 	if (rval != QLA_SUCCESS) {
 		ql_log(ql_log_warn, vha, 0xd000,
-		    "Failed to dump firmware (%x).\n", rval);
+		    "Failed to dump firmware (%x), dump status flags (0x%lx).\n",
+		    rval, ha->fw_dump_cap_flags);
 		ha->fw_dumped = 0;
 	} else {
 		ql_log(ql_log_info, vha, 0xd001,
-		    "Firmware dump saved to temp buffer (%ld/%p).\n",
-		    vha->host_no, ha->fw_dump);
+		    "Firmware dump saved to temp buffer (%ld/%p), dump status flags (0x%lx).\n",
+		    vha->host_no, ha->fw_dump, ha->fw_dump_cap_flags);
 		ha->fw_dumped = 1;
 		qla2x00_post_uevent_work(vha, QLA_UEVENT_CODE_FW_DUMP);
 	}
@@ -1053,6 +1060,7 @@ qla24xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	risc_address = ext_mem_cnt = 0;
 	flags = 0;
+	ha->fw_dump_cap_flags = 0;
 
 	if (!hardware_locked)
 		spin_lock_irqsave(&ha->hardware_lock, flags);
@@ -1075,10 +1083,11 @@ qla24xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	fw->host_status = htonl(RD_REG_DWORD(&reg->host_status));
 
-	/* Pause RISC. */
-	rval = qla24xx_pause_risc(reg);
-	if (rval != QLA_SUCCESS)
-		goto qla24xx_fw_dump_failed_0;
+	/*
+	 * Pause RISC. No need to track timeout, as resetting the chip
+	 * is the right approach incase of pause timeout
+	 */
+	qla24xx_pause_risc(reg, ha);
 
 	/* Host interface registers. */
 	dmp_reg = &reg->flash_addr;
@@ -1302,6 +1311,7 @@ qla25xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	risc_address = ext_mem_cnt = 0;
 	flags = 0;
+	ha->fw_dump_cap_flags = 0;
 
 	if (!hardware_locked)
 		spin_lock_irqsave(&ha->hardware_lock, flags);
@@ -1325,10 +1335,11 @@ qla25xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	fw->host_status = htonl(RD_REG_DWORD(&reg->host_status));
 
-	/* Pause RISC. */
-	rval = qla24xx_pause_risc(reg);
-	if (rval != QLA_SUCCESS)
-		goto qla25xx_fw_dump_failed_0;
+	/*
+	 * Pause RISC. No need to track timeout, as resetting the chip
+	 * is the right approach incase of pause timeout
+	 */
+	qla24xx_pause_risc(reg, ha);
 
 	/* Host/Risc registers. */
 	iter_reg = fw->host_risc_reg;
@@ -1619,6 +1630,7 @@ qla81xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	risc_address = ext_mem_cnt = 0;
 	flags = 0;
+	ha->fw_dump_cap_flags = 0;
 
 	if (!hardware_locked)
 		spin_lock_irqsave(&ha->hardware_lock, flags);
@@ -1641,10 +1653,11 @@ qla81xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	fw->host_status = htonl(RD_REG_DWORD(&reg->host_status));
 
-	/* Pause RISC. */
-	rval = qla24xx_pause_risc(reg);
-	if (rval != QLA_SUCCESS)
-		goto qla81xx_fw_dump_failed_0;
+	/*
+	 * Pause RISC. No need to track timeout, as resetting the chip
+	 * is the right approach incase of pause timeout
+	 */
+	qla24xx_pause_risc(reg, ha);
 
 	/* Host/Risc registers. */
 	iter_reg = fw->host_risc_reg;
@@ -1938,6 +1951,7 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	risc_address = ext_mem_cnt = 0;
 	flags = 0;
+	ha->fw_dump_cap_flags = 0;
 
 	if (!hardware_locked)
 		spin_lock_irqsave(&ha->hardware_lock, flags);
@@ -1959,10 +1973,11 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 
 	fw->host_status = htonl(RD_REG_DWORD(&reg->host_status));
 
-	/* Pause RISC. */
-	rval = qla24xx_pause_risc(reg);
-	if (rval != QLA_SUCCESS)
-		goto qla83xx_fw_dump_failed_0;
+	/*
+	 * Pause RISC. No need to track timeout, as resetting the chip
+	 * is the right approach incase of pause timeout
+	 */
+	qla24xx_pause_risc(reg, ha);
 
 	WRT_REG_DWORD(&reg->iobase_addr, 0x6000);
 	dmp_reg = &reg->iobase_window;
@@ -2385,9 +2400,11 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 			nxt += sizeof(fw->code_ram);
 			nxt += (ha->fw_memory_size - 0x100000 + 1);
 			goto copy_queue;
-		} else
+		} else {
+			set_bit(RISC_RDY_AFT_RESET, &ha->fw_dump_cap_flags);
 			ql_log(ql_log_warn, vha, 0xd010,
 			    "bigger hammer success?\n");
+		}
 	}
 
 	rval = qla24xx_dump_memory(ha, fw->code_ram, sizeof(fw->code_ram),
diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h
index cc961040f8b..e1fc4e66966 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.h
+++ b/drivers/scsi/qla2xxx/qla_dbg.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -353,5 +353,6 @@ extern int qla27xx_dump_mpi_ram(struct qla_hw_data *, uint32_t, uint32_t *,
 	uint32_t, void **);
 extern int qla24xx_dump_ram(struct qla_hw_data *, uint32_t, uint32_t *,
 	uint32_t, void **);
-extern int qla24xx_pause_risc(struct device_reg_24xx __iomem *);
+extern void qla24xx_pause_risc(struct device_reg_24xx __iomem *,
+	struct qla_hw_data *);
 extern int qla24xx_soft_reset(struct qla_hw_data *);
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 6a106136716..de5d0ae19d8 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -965,6 +965,13 @@ struct mbx_cmd_32 {
  */
 #define MBC_WRITE_MPI_REGISTER		0x01    /* Write MPI Register. */
 
+/*
+ * ISP8044 mailbox commands
+ */
+#define MBC_SET_GET_ETH_SERDES_REG	0x150
+#define HCS_WRITE_SERDES		0x3
+#define HCS_READ_SERDES			0x4
+
 /* Firmware return data sizes */
 #define FCAL_MAP_SIZE	128
 
@@ -1622,25 +1629,35 @@ typedef struct {
 #define PO_MODE_DIF_PASS	2
 #define PO_MODE_DIF_REPLACE	3
 #define PO_MODE_DIF_TCP_CKSUM	6
-#define PO_ENABLE_DIF_BUNDLING	BIT_8
 #define PO_ENABLE_INCR_GUARD_SEED	BIT_3
-#define PO_DISABLE_INCR_REF_TAG	BIT_5
 #define PO_DISABLE_GUARD_CHECK	BIT_4
+#define PO_DISABLE_INCR_REF_TAG	BIT_5
+#define PO_DIS_HEADER_MODE	BIT_7
+#define PO_ENABLE_DIF_BUNDLING	BIT_8
+#define PO_DIS_FRAME_MODE	BIT_9
+#define PO_DIS_VALD_APP_ESC	BIT_10 /* Dis validation for escape tag/ffffh */
+#define PO_DIS_VALD_APP_REF_ESC BIT_11
+
+#define PO_DIS_APP_TAG_REPL	BIT_12 /* disable REG Tag replacement */
+#define PO_DIS_REF_TAG_REPL	BIT_13
+#define PO_DIS_APP_TAG_VALD	BIT_14 /* disable REF Tag validation */
+#define PO_DIS_REF_TAG_VALD	BIT_15
+
 /*
  * ISP queue - 64-Bit addressing, continuation crc entry structure definition.
  */
 struct crc_context {
 	uint32_t handle;		/* System handle. */
-	uint32_t ref_tag;
-	uint16_t app_tag;
+	__le32 ref_tag;
+	__le16 app_tag;
 	uint8_t ref_tag_mask[4];	/* Validation/Replacement Mask*/
 	uint8_t app_tag_mask[2];	/* Validation/Replacement Mask*/
-	uint16_t guard_seed;		/* Initial Guard Seed */
-	uint16_t prot_opts;		/* Requested Data Protection Mode */
-	uint16_t blk_size;		/* Data size in bytes */
+	__le16 guard_seed;		/* Initial Guard Seed */
+	__le16 prot_opts;		/* Requested Data Protection Mode */
+	__le16 blk_size;		/* Data size in bytes */
 	uint16_t runt_blk_guard;	/* Guard value for runt block (tape
 					 * only) */
-	uint32_t byte_count;		/* Total byte count/ total data
+	__le32 byte_count;		/* Total byte count/ total data
 					 * transfer count */
 	union {
 		struct {
@@ -1654,10 +1671,10 @@ struct crc_context {
 			uint32_t	reserved_6;
 		} nobundling;
 		struct {
-			uint32_t	dif_byte_count;	/* Total DIF byte
+			__le32	dif_byte_count;	/* Total DIF byte
 							 * count */
 			uint16_t	reserved_1;
-			uint16_t	dseg_count;	/* Data segment count */
+			__le16	dseg_count;	/* Data segment count */
 			uint32_t	reserved_2;
 			uint32_t	data_address[2];
 			uint32_t	data_length;
@@ -1748,6 +1765,8 @@ typedef struct {
 #define CS_PORT_CONFIG_CHG	0x2A	/* Port Configuration Changed */
 #define CS_PORT_BUSY		0x2B	/* Port Busy */
 #define CS_COMPLETE_CHKCOND	0x30	/* Error? */
+#define CS_IOCB_ERROR		0x31	/* Generic error for IOCB request
+					   failure */
 #define CS_BAD_PAYLOAD		0x80	/* Driver defined */
 #define CS_UNKNOWN		0x81	/* Driver defined */
 #define CS_RETRY		0x82	/* Driver defined */
@@ -2676,6 +2695,7 @@ struct rsp_que {
 	uint32_t __iomem *rsp_q_out;
 	uint16_t  ring_index;
 	uint16_t  out_ptr;
+	uint16_t  *in_ptr;		/* queue shadow in index */
 	uint16_t  length;
 	uint16_t  options;
 	uint16_t  rid;
@@ -2702,6 +2722,7 @@ struct req_que {
 	uint32_t __iomem *req_q_out;
 	uint16_t  ring_index;
 	uint16_t  in_ptr;
+	uint16_t  *out_ptr;		/* queue shadow out index */
 	uint16_t  cnt;
 	uint16_t  length;
 	uint16_t  options;
@@ -2907,6 +2928,8 @@ struct qla_hw_data {
 #define PCI_DEVICE_ID_QLOGIC_ISP8031	0x8031
 #define PCI_DEVICE_ID_QLOGIC_ISP2031	0x2031
 #define PCI_DEVICE_ID_QLOGIC_ISP2071	0x2071
+#define PCI_DEVICE_ID_QLOGIC_ISP2271	0x2271
+
 	uint32_t	device_type;
 #define DT_ISP2100                      BIT_0
 #define DT_ISP2200                      BIT_1
@@ -2928,7 +2951,8 @@ struct qla_hw_data {
 #define DT_ISPFX00			BIT_17
 #define DT_ISP8044			BIT_18
 #define DT_ISP2071			BIT_19
-#define DT_ISP_LAST			(DT_ISP2071 << 1)
+#define DT_ISP2271			BIT_20
+#define DT_ISP_LAST			(DT_ISP2271 << 1)
 
 #define DT_T10_PI                       BIT_25
 #define DT_IIDMA                        BIT_26
@@ -2959,6 +2983,7 @@ struct qla_hw_data {
 #define IS_QLA8031(ha)	(DT_MASK(ha) & DT_ISP8031)
 #define IS_QLAFX00(ha)	(DT_MASK(ha) & DT_ISPFX00)
 #define IS_QLA2071(ha)	(DT_MASK(ha) & DT_ISP2071)
+#define IS_QLA2271(ha)	(DT_MASK(ha) & DT_ISP2271)
 
 #define IS_QLA23XX(ha)  (IS_QLA2300(ha) || IS_QLA2312(ha) || IS_QLA2322(ha) || \
 			IS_QLA6312(ha) || IS_QLA6322(ha))
@@ -2967,7 +2992,7 @@ struct qla_hw_data {
 #define IS_QLA25XX(ha)  (IS_QLA2532(ha))
 #define IS_QLA83XX(ha)	(IS_QLA2031(ha) || IS_QLA8031(ha))
 #define IS_QLA84XX(ha)  (IS_QLA8432(ha))
-#define IS_QLA27XX(ha)  (IS_QLA2071(ha))
+#define IS_QLA27XX(ha)  (IS_QLA2071(ha) || IS_QLA2271(ha))
 #define IS_QLA24XX_TYPE(ha)     (IS_QLA24XX(ha) || IS_QLA54XX(ha) || \
 				IS_QLA84XX(ha))
 #define IS_CNA_CAPABLE(ha)	(IS_QLA81XX(ha) || IS_QLA82XX(ha) || \
@@ -3006,6 +3031,7 @@ struct qla_hw_data {
     (((ha)->fw_attributes_h << 16 | (ha)->fw_attributes) & BIT_22))
 #define IS_ATIO_MSIX_CAPABLE(ha) (IS_QLA83XX(ha))
 #define IS_TGT_MODE_CAPABLE(ha)	(ha->tgt.atio_q_length)
+#define IS_SHADOW_REG_CAPABLE(ha)  (IS_QLA27XX(ha))
 
 	/* HBA serial number */
 	uint8_t		serial0;
@@ -3136,7 +3162,15 @@ struct qla_hw_data {
 	struct qla2xxx_fw_dump *fw_dump;
 	uint32_t	fw_dump_len;
 	int		fw_dumped;
+	unsigned long	fw_dump_cap_flags;
+#define RISC_PAUSE_CMPL		0
+#define DMA_SHUTDOWN_CMPL	1
+#define ISP_RESET_CMPL		2
+#define RISC_RDY_AFT_RESET	3
+#define RISC_SRAM_DUMP_CMPL	4
+#define RISC_EXT_MEM_DUMP_CMPL	5
 	int		fw_dump_reading;
+	int		prev_minidump_failed;
 	dma_addr_t	eft_dma;
 	void		*eft;
 /* Current size of mctp dump is 0x086064 bytes */
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index 32ab8095768..2ca39b8e716 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h
index 3a7353eaccb..eb8f57249f1 100644
--- a/drivers/scsi/qla2xxx/qla_fw.h
+++ b/drivers/scsi/qla2xxx/qla_fw.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -371,7 +371,10 @@ struct init_cb_24xx {
 	 * BIT 14 = Data Rate bit 1
 	 * BIT 15 = Data Rate bit 2
 	 * BIT 16 = Enable 75 ohm Termination Select
-	 * BIT 17-31 = Reserved
+	 * BIT 17-28 = Reserved
+	 * BIT 29 = Enable response queue 0 in index shadowing
+	 * BIT 30 = Enable request queue 0 out index shadowing
+	 * BIT 31 = Reserved
 	 */
 	uint32_t firmware_options_3;
 	uint16_t qos;
@@ -1134,13 +1137,6 @@ struct device_reg_24xx {
 #define MIN_MULTI_ID_FABRIC	64	/* Must be power-of-2. */
 #define MAX_MULTI_ID_FABRIC	256	/* ... */
 
-#define for_each_mapped_vp_idx(_ha, _idx)		\
-	for (_idx = find_next_bit((_ha)->vp_idx_map,	\
-		(_ha)->max_npiv_vports + 1, 1);		\
-	    _idx <= (_ha)->max_npiv_vports;		\
-	    _idx = find_next_bit((_ha)->vp_idx_map,	\
-		(_ha)->max_npiv_vports + 1, _idx + 1))	\
-
 struct mid_conf_entry_24xx {
 	uint16_t reserved_1;
 
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index e665e810993..d48dea8fab1 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -220,6 +220,13 @@ extern unsigned long qla2x00_get_async_timeout(struct scsi_qla_host *);
 
 extern void *qla2x00_alloc_iocbs(scsi_qla_host_t *, srb_t *);
 extern int qla2x00_issue_marker(scsi_qla_host_t *, int);
+extern int qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *, srb_t *,
+	uint32_t *, uint16_t, struct qla_tgt_cmd *);
+extern int qla24xx_walk_and_build_sglist(struct qla_hw_data *, srb_t *,
+	uint32_t *, uint16_t, struct qla_tgt_cmd *);
+extern int qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *, srb_t *,
+	uint32_t *, uint16_t, struct qla_tgt_cmd *);
+
 
 /*
  * Global Function Prototypes in qla_mbx.c source file.
@@ -347,6 +354,11 @@ extern int
 qla2x00_read_serdes_word(scsi_qla_host_t *, uint16_t, uint16_t *);
 
 extern int
+qla8044_write_serdes_word(scsi_qla_host_t *, uint32_t, uint32_t);
+extern int
+qla8044_read_serdes_word(scsi_qla_host_t *, uint32_t, uint32_t *);
+
+extern int
 qla2x00_set_serdes_params(scsi_qla_host_t *, uint16_t, uint16_t, uint16_t);
 
 extern int
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index e377f9d2f92..a0df3b1b382 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 38aeb54cd9d..e2184412617 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -1476,6 +1476,7 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
 	}
 
 	ha->fw_dumped = 0;
+	ha->fw_dump_cap_flags = 0;
 	dump_size = fixed_size = mem_size = eft_size = fce_size = mq_size = 0;
 	req_q_size = rsp_q_size = 0;
 
@@ -2061,6 +2062,10 @@ qla24xx_config_rings(struct scsi_qla_host *vha)
 	icb->atio_q_address[0] = cpu_to_le32(LSD(ha->tgt.atio_dma));
 	icb->atio_q_address[1] = cpu_to_le32(MSD(ha->tgt.atio_dma));
 
+	if (IS_SHADOW_REG_CAPABLE(ha))
+		icb->firmware_options_2 |=
+		    __constant_cpu_to_le32(BIT_30|BIT_29);
+
 	if (ha->mqenable || IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 		icb->qos = __constant_cpu_to_le16(QLA_DEFAULT_QUE_QOS);
 		icb->rid = __constant_cpu_to_le16(rid);
@@ -2138,6 +2143,8 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 		req = ha->req_q_map[que];
 		if (!req)
 			continue;
+		req->out_ptr = (void *)(req->ring + req->length);
+		*req->out_ptr = 0;
 		for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++)
 			req->outstanding_cmds[cnt] = NULL;
 
@@ -2153,6 +2160,8 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
 		rsp = ha->rsp_q_map[que];
 		if (!rsp)
 			continue;
+		rsp->in_ptr = (void *)(rsp->ring + rsp->length);
+		*rsp->in_ptr = 0;
 		/* Initialize response queue entries */
 		if (IS_QLAFX00(ha))
 			qlafx00_init_response_q_entries(rsp);
@@ -3406,7 +3415,7 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
 					    fcport->d_id.b.domain,
 					    fcport->d_id.b.area,
 					    fcport->d_id.b.al_pa);
-					fcport->loop_id = FC_NO_LOOP_ID;
+					qla2x00_clear_loop_id(fcport);
 				}
 			}
 		}
@@ -4727,7 +4736,6 @@ static int
 qla2x00_restart_isp(scsi_qla_host_t *vha)
 {
 	int status = 0;
-	uint32_t wait_time;
 	struct qla_hw_data *ha = vha->hw;
 	struct req_que *req = ha->req_q_map[0];
 	struct rsp_que *rsp = ha->rsp_q_map[0];
@@ -4744,14 +4752,12 @@ qla2x00_restart_isp(scsi_qla_host_t *vha)
 	if (!status && !(status = qla2x00_init_rings(vha))) {
 		clear_bit(RESET_MARKER_NEEDED, &vha->dpc_flags);
 		ha->flags.chip_reset_done = 1;
+
 		/* Initialize the queues in use */
 		qla25xx_init_queues(ha);
 
 		status = qla2x00_fw_ready(vha);
 		if (!status) {
-			ql_dbg(ql_dbg_taskm, vha, 0x8031,
-			    "Start configure loop status = %d.\n", status);
-
 			/* Issue a marker after FW becomes ready. */
 			qla2x00_marker(vha, req, rsp, 0, 0, MK_SYNC_ALL);
 
@@ -4766,24 +4772,12 @@ qla2x00_restart_isp(scsi_qla_host_t *vha)
 				qlt_24xx_process_atio_queue(vha);
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-			/* Wait at most MAX_TARGET RSCNs for a stable link. */
-			wait_time = 256;
-			do {
-				clear_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
-				qla2x00_configure_loop(vha);
-				wait_time--;
-			} while (!atomic_read(&vha->loop_down_timer) &&
-				!(test_bit(ISP_ABORT_NEEDED, &vha->dpc_flags))
-				&& wait_time && (test_bit(LOOP_RESYNC_NEEDED,
-				&vha->dpc_flags)));
+			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 		}
 
 		/* if no cable then assume it's good */
 		if ((vha->device_flags & DFLG_NO_CABLE))
 			status = 0;
-
-		ql_dbg(ql_dbg_taskm, vha, 0x8032,
-		    "Configure loop done, status = 0x%x.\n", status);
 	}
 	return (status);
 }
@@ -6130,7 +6124,6 @@ int
 qla82xx_restart_isp(scsi_qla_host_t *vha)
 {
 	int status, rval;
-	uint32_t wait_time;
 	struct qla_hw_data *ha = vha->hw;
 	struct req_que *req = ha->req_q_map[0];
 	struct rsp_que *rsp = ha->rsp_q_map[0];
@@ -6144,31 +6137,15 @@ qla82xx_restart_isp(scsi_qla_host_t *vha)
 
 		status = qla2x00_fw_ready(vha);
 		if (!status) {
-			ql_log(ql_log_info, vha, 0x803c,
-			    "Start configure loop, status =%d.\n", status);
-
 			/* Issue a marker after FW becomes ready. */
 			qla2x00_marker(vha, req, rsp, 0, 0, MK_SYNC_ALL);
-
 			vha->flags.online = 1;
-			/* Wait at most MAX_TARGET RSCNs for a stable link. */
-			wait_time = 256;
-			do {
-				clear_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
-				qla2x00_configure_loop(vha);
-				wait_time--;
-			} while (!atomic_read(&vha->loop_down_timer) &&
-			    !(test_bit(ISP_ABORT_NEEDED, &vha->dpc_flags)) &&
-			    wait_time &&
-			    (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags)));
+			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 		}
 
 		/* if no cable then assume it's good */
 		if ((vha->device_flags & DFLG_NO_CABLE))
 			status = 0;
-
-		ql_log(ql_log_info, vha, 0x8000,
-		    "Configure loop done, status = 0x%x.\n", status);
 	}
 
 	if (!status) {
@@ -6182,8 +6159,6 @@ qla82xx_restart_isp(scsi_qla_host_t *vha)
 			vha->marker_needed = 1;
 		}
 
-		vha->flags.online = 1;
-
 		ha->isp_ops->enable_intrs(ha);
 
 		ha->isp_abort_cnt = 0;
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index ce8b5fb0f34..b3b1d6fc2d6 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -1,10 +1,11 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
 
+#include "qla_target.h"
 /**
  * qla24xx_calc_iocbs() - Determine number of Command Type 3 and
  * Continuation Type 1 IOCBs to allocate.
@@ -128,12 +129,20 @@ qla2x00_clear_loop_id(fc_port_t *fcport) {
 }
 
 static inline void
-qla2x00_clean_dsd_pool(struct qla_hw_data *ha, srb_t *sp)
+qla2x00_clean_dsd_pool(struct qla_hw_data *ha, srb_t *sp,
+	struct qla_tgt_cmd *tc)
 {
 	struct dsd_dma *dsd_ptr, *tdsd_ptr;
 	struct crc_context *ctx;
 
-	ctx = (struct crc_context *)GET_CMD_CTX_SP(sp);
+	if (sp)
+		ctx = (struct crc_context *)GET_CMD_CTX_SP(sp);
+	else if (tc)
+		ctx = (struct crc_context *)tc->ctx;
+	else {
+		BUG();
+		return;
+	}
 
 	/* clean up allocated prev pool */
 	list_for_each_entry_safe(dsd_ptr, tdsd_ptr,
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index e607568bce4..76093152959 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -936,9 +936,9 @@ qla24xx_get_one_block_sg(uint32_t blk_sz, struct qla2_sgx *sgx,
 	return 1;
 }
 
-static int
+int
 qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *ha, srb_t *sp,
-	uint32_t *dsd, uint16_t tot_dsds)
+	uint32_t *dsd, uint16_t tot_dsds, struct qla_tgt_cmd *tc)
 {
 	void *next_dsd;
 	uint8_t avail_dsds = 0;
@@ -948,21 +948,35 @@ qla24xx_walk_and_build_sglist_no_difb(struct qla_hw_data *ha, srb_t *sp,
 	uint32_t *cur_dsd = dsd;
 	uint16_t	used_dsds = tot_dsds;
 
-	uint32_t	prot_int;
+	uint32_t	prot_int; /* protection interval */
 	uint32_t	partial;
 	struct qla2_sgx sgx;
 	dma_addr_t	sle_dma;
 	uint32_t	sle_dma_len, tot_prot_dma_len = 0;
-	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
-
-	prot_int = cmd->device->sector_size;
+	struct scsi_cmnd *cmd;
+	struct scsi_qla_host *vha;
 
 	memset(&sgx, 0, sizeof(struct qla2_sgx));
-	sgx.tot_bytes = scsi_bufflen(cmd);
-	sgx.cur_sg = scsi_sglist(cmd);
-	sgx.sp = sp;
-
-	sg_prot = scsi_prot_sglist(cmd);
+	if (sp) {
+		vha = sp->fcport->vha;
+		cmd = GET_CMD_SP(sp);
+		prot_int = cmd->device->sector_size;
+
+		sgx.tot_bytes = scsi_bufflen(cmd);
+		sgx.cur_sg = scsi_sglist(cmd);
+		sgx.sp = sp;
+
+		sg_prot = scsi_prot_sglist(cmd);
+	} else if (tc) {
+		vha = tc->vha;
+		prot_int      = tc->blk_sz;
+		sgx.tot_bytes = tc->bufflen;
+		sgx.cur_sg    = tc->sg;
+		sg_prot	      = tc->prot_sg;
+	} else {
+		BUG();
+		return 1;
+	}
 
 	while (qla24xx_get_one_block_sg(prot_int, &sgx, &partial)) {
 
@@ -995,10 +1009,18 @@ alloc_and_fill:
 				return 1;
 			}
 
-			list_add_tail(&dsd_ptr->list,
-			    &((struct crc_context *)sp->u.scmd.ctx)->dsd_list);
+			if (sp) {
+				list_add_tail(&dsd_ptr->list,
+				    &((struct crc_context *)
+					    sp->u.scmd.ctx)->dsd_list);
+
+				sp->flags |= SRB_CRC_CTX_DSD_VALID;
+			} else {
+				list_add_tail(&dsd_ptr->list,
+				    &(tc->ctx->dsd_list));
+				tc->ctx_dsd_alloced = 1;
+			}
 
-			sp->flags |= SRB_CRC_CTX_DSD_VALID;
 
 			/* add new list to cmd iocb or last list */
 			*cur_dsd++ = cpu_to_le32(LSD(dsd_ptr->dsd_list_dma));
@@ -1033,21 +1055,35 @@ alloc_and_fill:
 	return 0;
 }
 
-static int
+int
 qla24xx_walk_and_build_sglist(struct qla_hw_data *ha, srb_t *sp, uint32_t *dsd,
-	uint16_t tot_dsds)
+	uint16_t tot_dsds, struct qla_tgt_cmd *tc)
 {
 	void *next_dsd;
 	uint8_t avail_dsds = 0;
 	uint32_t dsd_list_len;
 	struct dsd_dma *dsd_ptr;
-	struct scatterlist *sg;
+	struct scatterlist *sg, *sgl;
 	uint32_t *cur_dsd = dsd;
 	int	i;
 	uint16_t	used_dsds = tot_dsds;
-	struct scsi_cmnd *cmd = GET_CMD_SP(sp);
+	struct scsi_cmnd *cmd;
+	struct scsi_qla_host *vha;
+
+	if (sp) {
+		cmd = GET_CMD_SP(sp);
+		sgl = scsi_sglist(cmd);
+		vha = sp->fcport->vha;
+	} else if (tc) {
+		sgl = tc->sg;
+		vha = tc->vha;
+	} else {
+		BUG();
+		return 1;
+	}
 
-	scsi_for_each_sg(cmd, sg, tot_dsds, i) {
+
+	for_each_sg(sgl, sg, tot_dsds, i) {
 		dma_addr_t	sle_dma;
 
 		/* Allocate additional continuation packets? */
@@ -1076,10 +1112,17 @@ qla24xx_walk_and_build_sglist(struct qla_hw_data *ha, srb_t *sp, uint32_t *dsd,
 				return 1;
 			}
 
-			list_add_tail(&dsd_ptr->list,
-			    &((struct crc_context *)sp->u.scmd.ctx)->dsd_list);
+			if (sp) {
+				list_add_tail(&dsd_ptr->list,
+				    &((struct crc_context *)
+					    sp->u.scmd.ctx)->dsd_list);
 
-			sp->flags |= SRB_CRC_CTX_DSD_VALID;
+				sp->flags |= SRB_CRC_CTX_DSD_VALID;
+			} else {
+				list_add_tail(&dsd_ptr->list,
+				    &(tc->ctx->dsd_list));
+				tc->ctx_dsd_alloced = 1;
+			}
 
 			/* add new list to cmd iocb or last list */
 			*cur_dsd++ = cpu_to_le32(LSD(dsd_ptr->dsd_list_dma));
@@ -1102,23 +1145,37 @@ qla24xx_walk_and_build_sglist(struct qla_hw_data *ha, srb_t *sp, uint32_t *dsd,
 	return 0;
 }
 
-static int
+int
 qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp,
-							uint32_t *dsd,
-	uint16_t tot_dsds)
+	uint32_t *dsd, uint16_t tot_dsds, struct qla_tgt_cmd *tc)
 {
 	void *next_dsd;
 	uint8_t avail_dsds = 0;
 	uint32_t dsd_list_len;
 	struct dsd_dma *dsd_ptr;
-	struct scatterlist *sg;
+	struct scatterlist *sg, *sgl;
 	int	i;
 	struct scsi_cmnd *cmd;
 	uint32_t *cur_dsd = dsd;
-	uint16_t	used_dsds = tot_dsds;
+	uint16_t used_dsds = tot_dsds;
+	struct scsi_qla_host *vha;
+
+	if (sp) {
+		cmd = GET_CMD_SP(sp);
+		sgl = scsi_prot_sglist(cmd);
+		vha = sp->fcport->vha;
+	} else if (tc) {
+		vha = tc->vha;
+		sgl = tc->prot_sg;
+	} else {
+		BUG();
+		return 1;
+	}
 
-	cmd = GET_CMD_SP(sp);
-	scsi_for_each_prot_sg(cmd, sg, tot_dsds, i) {
+	ql_dbg(ql_dbg_tgt, vha, 0xe021,
+		"%s: enter\n", __func__);
+
+	for_each_sg(sgl, sg, tot_dsds, i) {
 		dma_addr_t	sle_dma;
 
 		/* Allocate additional continuation packets? */
@@ -1147,10 +1204,17 @@ qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp,
 				return 1;
 			}
 
-			list_add_tail(&dsd_ptr->list,
-			    &((struct crc_context *)sp->u.scmd.ctx)->dsd_list);
+			if (sp) {
+				list_add_tail(&dsd_ptr->list,
+				    &((struct crc_context *)
+					    sp->u.scmd.ctx)->dsd_list);
 
-			sp->flags |= SRB_CRC_CTX_DSD_VALID;
+				sp->flags |= SRB_CRC_CTX_DSD_VALID;
+			} else {
+				list_add_tail(&dsd_ptr->list,
+				    &(tc->ctx->dsd_list));
+				tc->ctx_dsd_alloced = 1;
+			}
 
 			/* add new list to cmd iocb or last list */
 			*cur_dsd++ = cpu_to_le32(LSD(dsd_ptr->dsd_list_dma));
@@ -1386,10 +1450,10 @@ qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt,
 
 	if (!bundling && tot_prot_dsds) {
 		if (qla24xx_walk_and_build_sglist_no_difb(ha, sp,
-		    cur_dsd, tot_dsds))
+			cur_dsd, tot_dsds, NULL))
 			goto crc_queuing_error;
 	} else if (qla24xx_walk_and_build_sglist(ha, sp, cur_dsd,
-	    (tot_dsds - tot_prot_dsds)))
+			(tot_dsds - tot_prot_dsds), NULL))
 		goto crc_queuing_error;
 
 	if (bundling && tot_prot_dsds) {
@@ -1398,7 +1462,7 @@ qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt,
 			__constant_cpu_to_le16(CF_DIF_SEG_DESCR_ENABLE);
 		cur_dsd = (uint32_t *) &crc_ctx_pkt->u.bundling.dif_address;
 		if (qla24xx_walk_and_build_prot_sglist(ha, sp, cur_dsd,
-		    tot_prot_dsds))
+				tot_prot_dsds, NULL))
 			goto crc_queuing_error;
 	}
 	return QLA_SUCCESS;
@@ -1478,8 +1542,8 @@ qla24xx_start_scsi(srb_t *sp)
 	tot_dsds = nseg;
 	req_cnt = qla24xx_calc_iocbs(vha, tot_dsds);
 	if (req->cnt < (req_cnt + 2)) {
-		cnt = RD_REG_DWORD_RELAXED(req->req_q_out);
-
+		cnt = IS_SHADOW_REG_CAPABLE(ha) ? *req->out_ptr :
+		    RD_REG_DWORD_RELAXED(req->req_q_out);
 		if (req->ring_index < cnt)
 			req->cnt = cnt - req->ring_index;
 		else
@@ -1697,8 +1761,8 @@ qla24xx_dif_start_scsi(srb_t *sp)
 	tot_prot_dsds = nseg;
 	tot_dsds += nseg;
 	if (req->cnt < (req_cnt + 2)) {
-		cnt = RD_REG_DWORD_RELAXED(req->req_q_out);
-
+		cnt = IS_SHADOW_REG_CAPABLE(ha) ? *req->out_ptr :
+		    RD_REG_DWORD_RELAXED(req->req_q_out);
 		if (req->ring_index < cnt)
 			req->cnt = cnt - req->ring_index;
 		else
@@ -2825,8 +2889,8 @@ qla2x00_start_bidir(srb_t *sp, struct scsi_qla_host *vha, uint32_t tot_dsds)
 
 	/* Check for room on request queue. */
 	if (req->cnt < req_cnt + 2) {
-		cnt = RD_REG_DWORD_RELAXED(req->req_q_out);
-
+		cnt = IS_SHADOW_REG_CAPABLE(ha) ? *req->out_ptr :
+		    RD_REG_DWORD_RELAXED(req->req_q_out);
 		if  (req->ring_index < cnt)
 			req->cnt = cnt - req->ring_index;
 		else
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 95314ef2e50..a56825c73c3 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -2009,11 +2009,13 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt)
 		ql_dbg(ql_dbg_io, vha, 0x3017,
 		    "Invalid status handle (0x%x).\n", sts->handle);
 
-		if (IS_P3P_TYPE(ha))
-			set_bit(FCOE_CTX_RESET_NEEDED, &vha->dpc_flags);
-		else
-			set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
-		qla2xxx_wake_dpc(vha);
+		if (!test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags)) {
+			if (IS_P3P_TYPE(ha))
+				set_bit(FCOE_CTX_RESET_NEEDED, &vha->dpc_flags);
+			else
+				set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		}
 		return;
 	}
 
@@ -2472,12 +2474,14 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 		if (pkt->entry_status != 0) {
 			qla2x00_error_entry(vha, rsp, (sts_entry_t *) pkt);
 
-			(void)qlt_24xx_process_response_error(vha, pkt);
+			if (qlt_24xx_process_response_error(vha, pkt))
+				goto process_err;
 
 			((response_t *)pkt)->signature = RESPONSE_PROCESSED;
 			wmb();
 			continue;
 		}
+process_err:
 
 		switch (pkt->entry_type) {
 		case STATUS_TYPE:
@@ -2494,10 +2498,10 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 			qla24xx_logio_entry(vha, rsp->req,
 			    (struct logio_entry_24xx *)pkt);
 			break;
-                case CT_IOCB_TYPE:
+		case CT_IOCB_TYPE:
 			qla24xx_els_ct_entry(vha, rsp->req, pkt, CT_IOCB_TYPE);
 			break;
-                case ELS_IOCB_TYPE:
+		case ELS_IOCB_TYPE:
 			qla24xx_els_ct_entry(vha, rsp->req, pkt, ELS_IOCB_TYPE);
 			break;
 		case ABTS_RECV_24XX:
@@ -2506,6 +2510,7 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
 		case ABTS_RESP_24XX:
 		case CTIO_TYPE7:
 		case NOTIFY_ACK_TYPE:
+		case CTIO_CRC2:
 			qlt_response_pkt_all_vps(vha, (response_t *)pkt);
 			break;
 		case MARKER_TYPE:
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 2528709c4ad..1c33a77db5c 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -1319,7 +1319,7 @@ qla2x00_get_node_name_list(scsi_qla_host_t *vha, void **out_data, int *out_len)
 
 		left = 0;
 
-		list = kzalloc(dma_size, GFP_KERNEL);
+		list = kmemdup(pmap, dma_size, GFP_KERNEL);
 		if (!list) {
 			ql_log(ql_log_warn, vha, 0x1140,
 			    "%s(%ld): failed to allocate node names list "
@@ -1328,7 +1328,6 @@ qla2x00_get_node_name_list(scsi_qla_host_t *vha, void **out_data, int *out_len)
 			goto out_free;
 		}
 
-		memcpy(list, pmap, dma_size);
 restart:
 		dma_free_coherent(&ha->pdev->dev, dma_size, pmap, pmap_dma);
 	}
@@ -2644,7 +2643,10 @@ qla24xx_abort_command(srb_t *sp)
 		ql_dbg(ql_dbg_mbx, vha, 0x1090,
 		    "Failed to complete IOCB -- completion status (%x).\n",
 		    le16_to_cpu(abt->nport_handle));
-		rval = QLA_FUNCTION_FAILED;
+		if (abt->nport_handle == CS_IOCB_ERROR)
+			rval = QLA_FUNCTION_PARAMETER_ERROR;
+		else
+			rval = QLA_FUNCTION_FAILED;
 	} else {
 		ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1091,
 		    "Done %s.\n", __func__);
@@ -2879,6 +2881,78 @@ qla2x00_read_serdes_word(scsi_qla_host_t *vha, uint16_t addr, uint16_t *data)
 	return rval;
 }
 
+int
+qla8044_write_serdes_word(scsi_qla_host_t *vha, uint32_t addr, uint32_t data)
+{
+	int rval;
+	mbx_cmd_t mc;
+	mbx_cmd_t *mcp = &mc;
+
+	if (!IS_QLA8044(vha->hw))
+		return QLA_FUNCTION_FAILED;
+
+	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1186,
+	    "Entered %s.\n", __func__);
+
+	mcp->mb[0] = MBC_SET_GET_ETH_SERDES_REG;
+	mcp->mb[1] = HCS_WRITE_SERDES;
+	mcp->mb[3] = LSW(addr);
+	mcp->mb[4] = MSW(addr);
+	mcp->mb[5] = LSW(data);
+	mcp->mb[6] = MSW(data);
+	mcp->out_mb = MBX_6|MBX_5|MBX_4|MBX_3|MBX_1|MBX_0;
+	mcp->in_mb = MBX_0;
+	mcp->tov = MBX_TOV_SECONDS;
+	mcp->flags = 0;
+	rval = qla2x00_mailbox_command(vha, mcp);
+
+	if (rval != QLA_SUCCESS) {
+		ql_dbg(ql_dbg_mbx, vha, 0x1187,
+		    "Failed=%x mb[0]=%x.\n", rval, mcp->mb[0]);
+	} else {
+		ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1188,
+		    "Done %s.\n", __func__);
+	}
+
+	return rval;
+}
+
+int
+qla8044_read_serdes_word(scsi_qla_host_t *vha, uint32_t addr, uint32_t *data)
+{
+	int rval;
+	mbx_cmd_t mc;
+	mbx_cmd_t *mcp = &mc;
+
+	if (!IS_QLA8044(vha->hw))
+		return QLA_FUNCTION_FAILED;
+
+	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1189,
+	    "Entered %s.\n", __func__);
+
+	mcp->mb[0] = MBC_SET_GET_ETH_SERDES_REG;
+	mcp->mb[1] = HCS_READ_SERDES;
+	mcp->mb[3] = LSW(addr);
+	mcp->mb[4] = MSW(addr);
+	mcp->out_mb = MBX_4|MBX_3|MBX_1|MBX_0;
+	mcp->in_mb = MBX_2|MBX_1|MBX_0;
+	mcp->tov = MBX_TOV_SECONDS;
+	mcp->flags = 0;
+	rval = qla2x00_mailbox_command(vha, mcp);
+
+	*data = mcp->mb[2] << 16 | mcp->mb[1];
+
+	if (rval != QLA_SUCCESS) {
+		ql_dbg(ql_dbg_mbx, vha, 0x118a,
+		    "Failed=%x mb[0]=%x.\n", rval, mcp->mb[0]);
+	} else {
+		ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x118b,
+		    "Done %s.\n", __func__);
+	}
+
+	return rval;
+}
+
 /**
  * qla2x00_set_serdes_params() -
  * @ha: HA context
@@ -3660,6 +3734,9 @@ qla25xx_init_req_que(struct scsi_qla_host *vha, struct req_que *req)
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d3,
 	    "Entered %s.\n", __func__);
 
+	if (IS_SHADOW_REG_CAPABLE(ha))
+		req->options |= BIT_13;
+
 	mcp->mb[0] = MBC_INITIALIZE_MULTIQ;
 	mcp->mb[1] = req->options;
 	mcp->mb[2] = MSW(LSD(req->dma));
@@ -3679,7 +3756,7 @@ qla25xx_init_req_que(struct scsi_qla_host *vha, struct req_que *req)
 	/* que in ptr index */
 	mcp->mb[8] = 0;
 	/* que out ptr index */
-	mcp->mb[9] = 0;
+	mcp->mb[9] = *req->out_ptr = 0;
 	mcp->out_mb = MBX_14|MBX_13|MBX_12|MBX_11|MBX_10|MBX_9|MBX_8|MBX_7|
 			MBX_6|MBX_5|MBX_4|MBX_3|MBX_2|MBX_1|MBX_0;
 	mcp->in_mb = MBX_0;
@@ -3688,7 +3765,7 @@ qla25xx_init_req_que(struct scsi_qla_host *vha, struct req_que *req)
 
 	if (IS_QLA81XX(ha) || IS_QLA83XX(ha) || IS_QLA27XX(ha))
 		mcp->in_mb |= MBX_1;
-	if (IS_QLA83XX(ha) || !IS_QLA27XX(ha)) {
+	if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 		mcp->out_mb |= MBX_15;
 		/* debug q create issue in SR-IOV */
 		mcp->in_mb |= MBX_9 | MBX_8 | MBX_7;
@@ -3697,7 +3774,7 @@ qla25xx_init_req_que(struct scsi_qla_host *vha, struct req_que *req)
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	if (!(req->options & BIT_0)) {
 		WRT_REG_DWORD(req->req_q_in, 0);
-		if (!IS_QLA83XX(ha) || !IS_QLA27XX(ha))
+		if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 			WRT_REG_DWORD(req->req_q_out, 0);
 	}
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
@@ -3726,6 +3803,9 @@ qla25xx_init_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp)
 	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d6,
 	    "Entered %s.\n", __func__);
 
+	if (IS_SHADOW_REG_CAPABLE(ha))
+		rsp->options |= BIT_13;
+
 	mcp->mb[0] = MBC_INITIALIZE_MULTIQ;
 	mcp->mb[1] = rsp->options;
 	mcp->mb[2] = MSW(LSD(rsp->dma));
@@ -3740,7 +3820,7 @@ qla25xx_init_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp)
 
 	mcp->mb[4] = rsp->id;
 	/* que in ptr index */
-	mcp->mb[8] = 0;
+	mcp->mb[8] = *rsp->in_ptr = 0;
 	/* que out ptr index */
 	mcp->mb[9] = 0;
 	mcp->out_mb = MBX_14|MBX_13|MBX_9|MBX_8|MBX_7
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index f0a852257f9..89998244f48 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c
index 0aaf6a9c87d..abeb3901498 100644
--- a/drivers/scsi/qla2xxx/qla_mr.c
+++ b/drivers/scsi/qla2xxx/qla_mr.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -527,21 +527,63 @@ qlafx00_soc_cpu_reset(scsi_qla_host_t *vha)
 	struct qla_hw_data *ha = vha->hw;
 	int i, core;
 	uint32_t cnt;
+	uint32_t reg_val;
+
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x80004, 0);
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x82004, 0);
+
+	/* stop the XOR DMA engines */
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x60920, 0x02);
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x60924, 0x02);
+	QLAFX00_SET_HBA_SOC_REG(ha, 0xf0920, 0x02);
+	QLAFX00_SET_HBA_SOC_REG(ha, 0xf0924, 0x02);
+
+	/* stop the IDMA engines */
+	reg_val = QLAFX00_GET_HBA_SOC_REG(ha, 0x60840);
+	reg_val &= ~(1<<12);
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x60840, reg_val);
+
+	reg_val = QLAFX00_GET_HBA_SOC_REG(ha, 0x60844);
+	reg_val &= ~(1<<12);
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x60844, reg_val);
+
+	reg_val = QLAFX00_GET_HBA_SOC_REG(ha, 0x60848);
+	reg_val &= ~(1<<12);
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x60848, reg_val);
+
+	reg_val = QLAFX00_GET_HBA_SOC_REG(ha, 0x6084C);
+	reg_val &= ~(1<<12);
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x6084C, reg_val);
+
+	for (i = 0; i < 100000; i++) {
+		if ((QLAFX00_GET_HBA_SOC_REG(ha, 0xd0000) & 0x10000000) == 0 &&
+		    (QLAFX00_GET_HBA_SOC_REG(ha, 0x10600) & 0x1) == 0)
+			break;
+		udelay(100);
+	}
 
 	/* Set all 4 cores in reset */
 	for (i = 0; i < 4; i++) {
 		QLAFX00_SET_HBA_SOC_REG(ha,
 		    (SOC_SW_RST_CONTROL_REG_CORE0 + 8*i), (0xF01));
-	}
-
-	/* Set all 4 core Clock gating control */
-	for (i = 0; i < 4; i++) {
 		QLAFX00_SET_HBA_SOC_REG(ha,
 		    (SOC_SW_RST_CONTROL_REG_CORE0 + 4 + 8*i), (0x01010101));
 	}
 
 	/* Reset all units in Fabric */
-	QLAFX00_SET_HBA_SOC_REG(ha, SOC_FABRIC_RST_CONTROL_REG, (0x11F0101));
+	QLAFX00_SET_HBA_SOC_REG(ha, SOC_FABRIC_RST_CONTROL_REG, (0x011f0101));
+
+	/* */
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x10610, 1);
+	QLAFX00_SET_HBA_SOC_REG(ha, 0x10600, 0);
+
+	/* Set all 4 core Memory Power Down Registers */
+	for (i = 0; i < 5; i++) {
+		QLAFX00_SET_HBA_SOC_REG(ha,
+		    (SOC_PWR_MANAGEMENT_PWR_DOWN_REG + 4*i), (0x0));
+	}
 
 	/* Reset all interrupt control registers */
 	for (i = 0; i < 115; i++) {
@@ -564,20 +606,19 @@ qlafx00_soc_cpu_reset(scsi_qla_host_t *vha)
 	QLAFX00_SET_HBA_SOC_REG(ha, SOC_FABRIC_CONTROL_REG, (0x2));
 	QLAFX00_SET_HBA_SOC_REG(ha, SOC_FABRIC_CONFIG_REG, (0x3));
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-
 	/* Kick in Fabric units */
 	QLAFX00_SET_HBA_SOC_REG(ha, SOC_FABRIC_RST_CONTROL_REG, (0x0));
 
 	/* Kick in Core0 to start boot process */
 	QLAFX00_SET_HBA_SOC_REG(ha, SOC_SW_RST_CONTROL_REG_CORE0, (0xF00));
 
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	/* Wait 10secs for soft-reset to complete. */
 	for (cnt = 10; cnt; cnt--) {
 		msleep(1000);
 		barrier();
 	}
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
 
 /**
@@ -597,7 +638,6 @@ qlafx00_soft_reset(scsi_qla_host_t *vha)
 
 	ha->isp_ops->disable_intrs(ha);
 	qlafx00_soc_cpu_reset(vha);
-	ha->isp_ops->enable_intrs(ha);
 }
 
 /**
@@ -2675,7 +2715,7 @@ qlafx00_process_response_queue(struct scsi_qla_host *vha,
 	uint16_t lreq_q_out = 0;
 
 	lreq_q_in = RD_REG_DWORD(rsp->rsp_q_in);
-	lreq_q_out = RD_REG_DWORD(rsp->rsp_q_out);
+	lreq_q_out = rsp->ring_index;
 
 	while (lreq_q_in != lreq_q_out) {
 		lptr = rsp->ring_ptr;
@@ -3426,7 +3466,7 @@ qlafx00_fxdisc_iocb(srb_t *sp, struct fxdisc_entry_fx00 *pfxiocb)
 	    sp->fcport->vha, 0x3047,
 	    (uint8_t *)&fx_iocb, sizeof(struct fxdisc_entry_fx00));
 
-	memcpy((void *)pfxiocb, &fx_iocb,
+	memcpy_toio((void __iomem *)pfxiocb, &fx_iocb,
 	    sizeof(struct fxdisc_entry_fx00));
 	wmb();
 }
diff --git a/drivers/scsi/qla2xxx/qla_mr.h b/drivers/scsi/qla2xxx/qla_mr.h
index e529dfaeb85..aeaa1b40b1f 100644
--- a/drivers/scsi/qla2xxx/qla_mr.h
+++ b/drivers/scsi/qla2xxx/qla_mr.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -351,6 +351,7 @@ struct config_info_data {
 #define SOC_FABRIC_RST_CONTROL_REG       0x0020840
 #define SOC_FABRIC_CONTROL_REG           0x0020200
 #define SOC_FABRIC_CONFIG_REG            0x0020204
+#define SOC_PWR_MANAGEMENT_PWR_DOWN_REG  0x001820C
 
 #define SOC_INTERRUPT_SOURCE_I_CONTROL_REG     0x0020B00
 #define SOC_CORE_TIMER_REG                     0x0021850
diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c
index 5511e24b1f1..58f3c912d96 100644
--- a/drivers/scsi/qla2xxx/qla_nx.c
+++ b/drivers/scsi/qla2xxx/qla_nx.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -848,6 +848,7 @@ qla82xx_rom_lock(struct qla_hw_data *ha)
 {
 	int done = 0, timeout = 0;
 	uint32_t lock_owner = 0;
+	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 
 	while (!done) {
 		/* acquire semaphore2 from PCI HW block */
@@ -856,17 +857,21 @@ qla82xx_rom_lock(struct qla_hw_data *ha)
 			break;
 		if (timeout >= qla82xx_rom_lock_timeout) {
 			lock_owner = qla82xx_rd_32(ha, QLA82XX_ROM_LOCK_ID);
+			ql_log(ql_log_warn, vha, 0xb157,
+			    "%s: Simultaneous flash access by following ports, active port = %d: accessing port = %d",
+			    __func__, ha->portnum, lock_owner);
 			return -1;
 		}
 		timeout++;
 	}
-	qla82xx_wr_32(ha, QLA82XX_ROM_LOCK_ID, ROM_LOCK_DRIVER);
+	qla82xx_wr_32(ha, QLA82XX_ROM_LOCK_ID, ha->portnum);
 	return 0;
 }
 
 static void
 qla82xx_rom_unlock(struct qla_hw_data *ha)
 {
+	qla82xx_wr_32(ha, QLA82XX_ROM_LOCK_ID, 0xffffffff);
 	qla82xx_rd_32(ha, QLA82XX_PCIE_REG(PCIE_SEM2_UNLOCK));
 }
 
@@ -950,6 +955,7 @@ static int
 qla82xx_rom_fast_read(struct qla_hw_data *ha, int addr, int *valp)
 {
 	int ret, loops = 0;
+	uint32_t lock_owner = 0;
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 
 	while ((qla82xx_rom_lock(ha) != 0) && (loops < 50000)) {
@@ -958,8 +964,10 @@ qla82xx_rom_fast_read(struct qla_hw_data *ha, int addr, int *valp)
 		loops++;
 	}
 	if (loops >= 50000) {
+		lock_owner = qla82xx_rd_32(ha, QLA82XX_ROM_LOCK_ID);
 		ql_log(ql_log_fatal, vha, 0x00b9,
-		    "Failed to acquire SEM2 lock.\n");
+		    "Failed to acquire SEM2 lock, Lock Owner %u.\n",
+		    lock_owner);
 		return -1;
 	}
 	ret = qla82xx_do_rom_fast_read(ha, addr, valp);
@@ -1057,6 +1065,7 @@ static int
 ql82xx_rom_lock_d(struct qla_hw_data *ha)
 {
 	int loops = 0;
+	uint32_t lock_owner = 0;
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 
 	while ((qla82xx_rom_lock(ha) != 0) && (loops < 50000)) {
@@ -1065,8 +1074,9 @@ ql82xx_rom_lock_d(struct qla_hw_data *ha)
 		loops++;
 	}
 	if (loops >= 50000) {
+		lock_owner = qla82xx_rd_32(ha, QLA82XX_ROM_LOCK_ID);
 		ql_log(ql_log_warn, vha, 0xb010,
-		    "ROM lock failed.\n");
+		    "ROM lock failed, Lock Owner %u.\n", lock_owner);
 		return -1;
 	}
 	return 0;
@@ -2811,12 +2821,14 @@ static void
 qla82xx_rom_lock_recovery(struct qla_hw_data *ha)
 {
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
+	uint32_t lock_owner = 0;
 
-	if (qla82xx_rom_lock(ha))
+	if (qla82xx_rom_lock(ha)) {
+		lock_owner = qla82xx_rd_32(ha, QLA82XX_ROM_LOCK_ID);
 		/* Someone else is holding the lock. */
 		ql_log(ql_log_info, vha, 0xb022,
-		    "Resetting rom_lock.\n");
-
+		    "Resetting rom_lock, Lock Owner %u.\n", lock_owner);
+	}
 	/*
 	 * Either we got the lock, or someone
 	 * else died while holding it.
@@ -2840,47 +2852,30 @@ static int
 qla82xx_device_bootstrap(scsi_qla_host_t *vha)
 {
 	int rval = QLA_SUCCESS;
-	int i, timeout;
+	int i;
 	uint32_t old_count, count;
 	struct qla_hw_data *ha = vha->hw;
-	int need_reset = 0, peg_stuck = 1;
+	int need_reset = 0;
 
 	need_reset = qla82xx_need_reset(ha);
 
-	old_count = qla82xx_rd_32(ha, QLA82XX_PEG_ALIVE_COUNTER);
-
-	for (i = 0; i < 10; i++) {
-		timeout = msleep_interruptible(200);
-		if (timeout) {
-			qla82xx_wr_32(ha, QLA82XX_CRB_DEV_STATE,
-				QLA8XXX_DEV_FAILED);
-			return QLA_FUNCTION_FAILED;
-		}
-
-		count = qla82xx_rd_32(ha, QLA82XX_PEG_ALIVE_COUNTER);
-		if (count != old_count)
-			peg_stuck = 0;
-	}
-
 	if (need_reset) {
 		/* We are trying to perform a recovery here. */
-		if (peg_stuck)
+		if (ha->flags.isp82xx_fw_hung)
 			qla82xx_rom_lock_recovery(ha);
-		goto dev_initialize;
 	} else  {
-		/* Start of day for this ha context. */
-		if (peg_stuck) {
-			/* Either we are the first or recovery in progress. */
-			qla82xx_rom_lock_recovery(ha);
-			goto dev_initialize;
-		} else
-			/* Firmware already running. */
-			goto dev_ready;
+		old_count = qla82xx_rd_32(ha, QLA82XX_PEG_ALIVE_COUNTER);
+		for (i = 0; i < 10; i++) {
+			msleep(200);
+			count = qla82xx_rd_32(ha, QLA82XX_PEG_ALIVE_COUNTER);
+			if (count != old_count) {
+				rval = QLA_SUCCESS;
+				goto dev_ready;
+			}
+		}
+		qla82xx_rom_lock_recovery(ha);
 	}
 
-	return rval;
-
-dev_initialize:
 	/* set to DEV_INITIALIZING */
 	ql_log(ql_log_info, vha, 0x009e,
 	    "HW State: INITIALIZING.\n");
@@ -3142,18 +3137,18 @@ qla82xx_check_md_needed(scsi_qla_host_t *vha)
 
 	if (ql2xmdenable) {
 		if (!ha->fw_dumped) {
-			if (fw_major_version != ha->fw_major_version ||
+			if ((fw_major_version != ha->fw_major_version ||
 			    fw_minor_version != ha->fw_minor_version ||
-			    fw_subminor_version != ha->fw_subminor_version) {
+			    fw_subminor_version != ha->fw_subminor_version) ||
+			    (ha->prev_minidump_failed)) {
 				ql_dbg(ql_dbg_p3p, vha, 0xb02d,
-				    "Firmware version differs "
-				    "Previous version: %d:%d:%d - "
-				    "New version: %d:%d:%d\n",
+				    "Firmware version differs Previous version: %d:%d:%d - New version: %d:%d:%d, prev_minidump_failed: %d.\n",
 				    fw_major_version, fw_minor_version,
 				    fw_subminor_version,
 				    ha->fw_major_version,
 				    ha->fw_minor_version,
-				    ha->fw_subminor_version);
+				    ha->fw_subminor_version,
+				    ha->prev_minidump_failed);
 				/* Release MiniDump resources */
 				qla82xx_md_free(vha);
 				/* ALlocate MiniDump resources */
@@ -3682,8 +3677,10 @@ qla82xx_chip_reset_cleanup(scsi_qla_host_t *vha)
 			for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
 				sp = req->outstanding_cmds[cnt];
 				if (sp) {
-					if (!sp->u.scmd.ctx ||
-					    (sp->flags & SRB_FCP_CMND_DMA_VALID)) {
+					if ((!sp->u.scmd.ctx ||
+					    (sp->flags &
+						SRB_FCP_CMND_DMA_VALID)) &&
+						!ha->flags.isp82xx_fw_hung) {
 						spin_unlock_irqrestore(
 						    &ha->hardware_lock, flags);
 						if (ha->isp_ops->abort_command(sp)) {
diff --git a/drivers/scsi/qla2xxx/qla_nx.h b/drivers/scsi/qla2xxx/qla_nx.h
index 1bb93dbbccb..59c477883a7 100644
--- a/drivers/scsi/qla2xxx/qla_nx.h
+++ b/drivers/scsi/qla2xxx/qla_nx.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -333,9 +333,6 @@
 #define QLA82XX_ROMUSB_ROM_INSTR_OPCODE		(ROMUSB_ROM + 0x0004)
 #define QLA82XX_ROMUSB_GLB_CAS_RST		(ROMUSB_GLB + 0x0038)
 
-/* Lock IDs for ROM lock */
-#define ROM_LOCK_DRIVER       0x0d417340
-
 #define QLA82XX_PCI_CRB_WINDOWSIZE 0x00100000	 /* all are 1MB windows */
 #define QLA82XX_PCI_CRB_WINDOW(A) \
 	(QLA82XX_PCI_CRBSPACE + (A)*QLA82XX_PCI_CRB_WINDOWSIZE)
@@ -1186,6 +1183,7 @@ static const int MD_MIU_TEST_AGT_RDDATA[] = { 0x410000A8, 0x410000AC,
 #define CRB_NIU_XG_PAUSE_CTL_P1        0x8
 
 #define qla82xx_get_temp_val(x)          ((x) >> 16)
+#define qla82xx_get_temp_val1(x)          ((x) && 0x0000FFFF)
 #define qla82xx_get_temp_state(x)        ((x) & 0xffff)
 #define qla82xx_encode_temp(val, state)  (((val) << 16) | (state))
 
diff --git a/drivers/scsi/qla2xxx/qla_nx2.c b/drivers/scsi/qla2xxx/qla_nx2.c
index 86cf10815db..da9e3902f21 100644
--- a/drivers/scsi/qla2xxx/qla_nx2.c
+++ b/drivers/scsi/qla2xxx/qla_nx2.c
@@ -1,17 +1,20 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
 
 #include <linux/vmalloc.h>
+#include <linux/delay.h>
 
 #include "qla_def.h"
 #include "qla_gbl.h"
 
 #include <linux/delay.h>
 
+#define TIMEOUT_100_MS 100
+
 /* 8044 Flash Read/Write functions */
 uint32_t
 qla8044_rd_reg(struct qla_hw_data *ha, ulong addr)
@@ -117,6 +120,95 @@ qla8044_read_write_crb_reg(struct scsi_qla_host *vha,
 	qla8044_wr_reg_indirect(vha, waddr, value);
 }
 
+static int
+qla8044_poll_wait_for_ready(struct scsi_qla_host *vha, uint32_t addr1,
+	uint32_t mask)
+{
+	unsigned long timeout;
+	uint32_t temp;
+
+	/* jiffies after 100ms */
+	timeout = jiffies + msecs_to_jiffies(TIMEOUT_100_MS);
+	do {
+		qla8044_rd_reg_indirect(vha, addr1, &temp);
+		if ((temp & mask) != 0)
+			break;
+		if (time_after_eq(jiffies, timeout)) {
+			ql_log(ql_log_warn, vha, 0xb151,
+				"Error in processing rdmdio entry\n");
+			return -1;
+		}
+	} while (1);
+
+	return 0;
+}
+
+static uint32_t
+qla8044_ipmdio_rd_reg(struct scsi_qla_host *vha,
+	uint32_t addr1, uint32_t addr3, uint32_t mask, uint32_t addr)
+{
+	uint32_t temp;
+	int ret = 0;
+
+	ret = qla8044_poll_wait_for_ready(vha, addr1, mask);
+	if (ret == -1)
+		return -1;
+
+	temp = (0x40000000 | addr);
+	qla8044_wr_reg_indirect(vha, addr1, temp);
+
+	ret = qla8044_poll_wait_for_ready(vha, addr1, mask);
+	if (ret == -1)
+		return 0;
+
+	qla8044_rd_reg_indirect(vha, addr3, &ret);
+
+	return ret;
+}
+
+
+static int
+qla8044_poll_wait_ipmdio_bus_idle(struct scsi_qla_host *vha,
+	uint32_t addr1, uint32_t addr2, uint32_t addr3, uint32_t mask)
+{
+	unsigned long timeout;
+	uint32_t temp;
+
+	/* jiffies after 100 msecs */
+	timeout = jiffies + msecs_to_jiffies(TIMEOUT_100_MS);
+	do {
+		temp = qla8044_ipmdio_rd_reg(vha, addr1, addr3, mask, addr2);
+		if ((temp & 0x1) != 1)
+			break;
+		if (time_after_eq(jiffies, timeout)) {
+			ql_log(ql_log_warn, vha, 0xb152,
+			    "Error in processing mdiobus idle\n");
+			return -1;
+		}
+	} while (1);
+
+	return 0;
+}
+
+static int
+qla8044_ipmdio_wr_reg(struct scsi_qla_host *vha, uint32_t addr1,
+	uint32_t addr3, uint32_t mask, uint32_t addr, uint32_t value)
+{
+	int ret = 0;
+
+	ret = qla8044_poll_wait_for_ready(vha, addr1, mask);
+	if (ret == -1)
+		return -1;
+
+	qla8044_wr_reg_indirect(vha, addr3, value);
+	qla8044_wr_reg_indirect(vha, addr1, addr);
+
+	ret = qla8044_poll_wait_for_ready(vha, addr1, mask);
+	if (ret == -1)
+		return -1;
+
+	return 0;
+}
 /*
  * qla8044_rmw_crb_reg - Read value from raddr, AND with test_mask,
  * Shift Left,Right/OR/XOR with values RMW header and write value to waddr.
@@ -356,8 +448,8 @@ qla8044_flash_lock(scsi_qla_host_t *vha)
 			lock_owner = qla8044_rd_reg(ha,
 			    QLA8044_FLASH_LOCK_ID);
 			ql_log(ql_log_warn, vha, 0xb113,
-			    "%s: flash lock by %d failed, held by %d\n",
-				__func__, ha->portnum, lock_owner);
+			    "%s: Simultaneous flash access by following ports, active port = %d: accessing port = %d",
+			    __func__, ha->portnum, lock_owner);
 			ret_val = QLA_FUNCTION_FAILED;
 			break;
 		}
@@ -1541,7 +1633,7 @@ static void
 qla8044_need_reset_handler(struct scsi_qla_host *vha)
 {
 	uint32_t dev_state = 0, drv_state, drv_active;
-	unsigned long reset_timeout, dev_init_timeout;
+	unsigned long reset_timeout;
 	struct qla_hw_data *ha = vha->hw;
 
 	ql_log(ql_log_fatal, vha, 0xb0c2,
@@ -1555,84 +1647,78 @@ qla8044_need_reset_handler(struct scsi_qla_host *vha)
 		qla8044_idc_lock(ha);
 	}
 
+	dev_state = qla8044_rd_direct(vha,
+	    QLA8044_CRB_DEV_STATE_INDEX);
 	drv_state = qla8044_rd_direct(vha,
 	    QLA8044_CRB_DRV_STATE_INDEX);
 	drv_active = qla8044_rd_direct(vha,
 	    QLA8044_CRB_DRV_ACTIVE_INDEX);
 
 	ql_log(ql_log_info, vha, 0xb0c5,
-	    "%s(%ld): drv_state = 0x%x, drv_active = 0x%x\n",
-	    __func__, vha->host_no, drv_state, drv_active);
+	    "%s(%ld): drv_state = 0x%x, drv_active = 0x%x dev_state = 0x%x\n",
+	    __func__, vha->host_no, drv_state, drv_active, dev_state);
 
-	if (!ha->flags.nic_core_reset_owner) {
-		ql_dbg(ql_dbg_p3p, vha, 0xb0c3,
-		    "%s(%ld): reset acknowledged\n",
-		    __func__, vha->host_no);
-		qla8044_set_rst_ready(vha);
+	qla8044_set_rst_ready(vha);
 
-		/* Non-reset owners ACK Reset and wait for device INIT state
-		 * as part of Reset Recovery by Reset Owner
-		 */
-		dev_init_timeout = jiffies + (ha->fcoe_reset_timeout * HZ);
+	/* wait for 10 seconds for reset ack from all functions */
+	reset_timeout = jiffies + (ha->fcoe_reset_timeout * HZ);
 
-		do {
-			if (time_after_eq(jiffies, dev_init_timeout)) {
-				ql_log(ql_log_info, vha, 0xb0c4,
-				    "%s: Non Reset owner: Reset Ack Timeout!\n",
-				    __func__);
-				break;
-			}
+	do {
+		if (time_after_eq(jiffies, reset_timeout)) {
+			ql_log(ql_log_info, vha, 0xb0c4,
+			    "%s: Function %d: Reset Ack Timeout!, drv_state: 0x%08x, drv_active: 0x%08x\n",
+			    __func__, ha->portnum, drv_state, drv_active);
+			break;
+		}
 
-			qla8044_idc_unlock(ha);
-			msleep(1000);
-			qla8044_idc_lock(ha);
+		qla8044_idc_unlock(ha);
+		msleep(1000);
+		qla8044_idc_lock(ha);
 
-			dev_state = qla8044_rd_direct(vha,
-					QLA8044_CRB_DEV_STATE_INDEX);
-		} while (((drv_state & drv_active) != drv_active) &&
-		    (dev_state == QLA8XXX_DEV_NEED_RESET));
+		dev_state = qla8044_rd_direct(vha,
+		    QLA8044_CRB_DEV_STATE_INDEX);
+		drv_state = qla8044_rd_direct(vha,
+		    QLA8044_CRB_DRV_STATE_INDEX);
+		drv_active = qla8044_rd_direct(vha,
+		    QLA8044_CRB_DRV_ACTIVE_INDEX);
+	} while (((drv_state & drv_active) != drv_active) &&
+	    (dev_state == QLA8XXX_DEV_NEED_RESET));
+
+	/* Remove IDC participation of functions not acknowledging */
+	if (drv_state != drv_active) {
+		ql_log(ql_log_info, vha, 0xb0c7,
+		    "%s(%ld): Function %d turning off drv_active of non-acking function 0x%x\n",
+		    __func__, vha->host_no, ha->portnum,
+		    (drv_active ^ drv_state));
+		drv_active = drv_active & drv_state;
+		qla8044_wr_direct(vha, QLA8044_CRB_DRV_ACTIVE_INDEX,
+		    drv_active);
 	} else {
-		qla8044_set_rst_ready(vha);
-
-		/* wait for 10 seconds for reset ack from all functions */
-		reset_timeout = jiffies + (ha->fcoe_reset_timeout * HZ);
-
-		while ((drv_state & drv_active) != drv_active) {
-			if (time_after_eq(jiffies, reset_timeout)) {
-				ql_log(ql_log_info, vha, 0xb0c6,
-				    "%s: RESET TIMEOUT!"
-				    "drv_state: 0x%08x, drv_active: 0x%08x\n",
-				    QLA2XXX_DRIVER_NAME, drv_state, drv_active);
-				break;
-			}
-
-			qla8044_idc_unlock(ha);
-			msleep(1000);
-			qla8044_idc_lock(ha);
-
-			drv_state = qla8044_rd_direct(vha,
-			    QLA8044_CRB_DRV_STATE_INDEX);
-			drv_active = qla8044_rd_direct(vha,
-			    QLA8044_CRB_DRV_ACTIVE_INDEX);
-		}
-
-		if (drv_state != drv_active) {
-			ql_log(ql_log_info, vha, 0xb0c7,
-			    "%s(%ld): Reset_owner turning off drv_active "
-			    "of non-acking function 0x%x\n", __func__,
-			    vha->host_no, (drv_active ^ drv_state));
-			drv_active = drv_active & drv_state;
-			qla8044_wr_direct(vha, QLA8044_CRB_DRV_ACTIVE_INDEX,
-			    drv_active);
+		/*
+		 * Reset owner should execute reset recovery,
+		 * if all functions acknowledged
+		 */
+		if ((ha->flags.nic_core_reset_owner) &&
+		    (dev_state == QLA8XXX_DEV_NEED_RESET)) {
+			ha->flags.nic_core_reset_owner = 0;
+			qla8044_device_bootstrap(vha);
+			return;
 		}
+	}
 
-		/*
-		* Clear RESET OWNER, will be set at next reset
-		* by next RST_OWNER
-		*/
+	/* Exit if non active function */
+	if (!(drv_active & (1 << ha->portnum))) {
 		ha->flags.nic_core_reset_owner = 0;
+		return;
+	}
 
-		/* Start Reset Recovery */
+	/*
+	 * Execute Reset Recovery if Reset Owner or Function 7
+	 * is the only active function
+	 */
+	if (ha->flags.nic_core_reset_owner ||
+	    ((drv_state & drv_active) == QLA8044_FUN7_ACTIVE_INDEX)) {
+		ha->flags.nic_core_reset_owner = 0;
 		qla8044_device_bootstrap(vha);
 	}
 }
@@ -1655,6 +1741,19 @@ qla8044_set_drv_active(struct scsi_qla_host *vha)
 	qla8044_wr_direct(vha, QLA8044_CRB_DRV_ACTIVE_INDEX, drv_active);
 }
 
+static int
+qla8044_check_drv_active(struct scsi_qla_host *vha)
+{
+	uint32_t drv_active;
+	struct qla_hw_data *ha = vha->hw;
+
+	drv_active = qla8044_rd_direct(vha, QLA8044_CRB_DRV_ACTIVE_INDEX);
+	if (drv_active & (1 << ha->portnum))
+		return QLA_SUCCESS;
+	else
+		return QLA_TEST_FAILED;
+}
+
 static void
 qla8044_clear_idc_dontreset(struct scsi_qla_host *vha)
 {
@@ -1837,14 +1936,16 @@ qla8044_device_state_handler(struct scsi_qla_host *vha)
 
 	while (1) {
 		if (time_after_eq(jiffies, dev_init_timeout)) {
-			ql_log(ql_log_warn, vha, 0xb0cf,
-			    "%s: Device Init Failed 0x%x = %s\n",
-			    QLA2XXX_DRIVER_NAME, dev_state,
-			    dev_state < MAX_STATES ?
-			    qdev_state(dev_state) : "Unknown");
-
-			qla8044_wr_direct(vha, QLA8044_CRB_DEV_STATE_INDEX,
-			    QLA8XXX_DEV_FAILED);
+			if (qla8044_check_drv_active(vha) == QLA_SUCCESS) {
+				ql_log(ql_log_warn, vha, 0xb0cf,
+				    "%s: Device Init Failed 0x%x = %s\n",
+				    QLA2XXX_DRIVER_NAME, dev_state,
+				    dev_state < MAX_STATES ?
+				    qdev_state(dev_state) : "Unknown");
+				qla8044_wr_direct(vha,
+				    QLA8044_CRB_DEV_STATE_INDEX,
+				    QLA8XXX_DEV_FAILED);
+			}
 		}
 
 		dev_state = qla8044_rd_direct(vha, QLA8044_CRB_DEV_STATE_INDEX);
@@ -2017,6 +2118,13 @@ qla8044_watchdog(struct scsi_qla_host *vha)
 	    test_bit(FCOE_CTX_RESET_NEEDED, &vha->dpc_flags))) {
 		dev_state = qla8044_rd_direct(vha, QLA8044_CRB_DEV_STATE_INDEX);
 
+		if (qla8044_check_fw_alive(vha)) {
+			ha->flags.isp82xx_fw_hung = 1;
+			ql_log(ql_log_warn, vha, 0xb10a,
+			    "Firmware hung.\n");
+			qla82xx_clear_pending_mbx(vha);
+		}
+
 		if (qla8044_check_temp(vha)) {
 			set_bit(ISP_UNRECOVERABLE, &vha->dpc_flags);
 			ha->flags.isp82xx_fw_hung = 1;
@@ -2037,7 +2145,7 @@ qla8044_watchdog(struct scsi_qla_host *vha)
 			qla2xxx_wake_dpc(vha);
 		} else  {
 			/* Check firmware health */
-			if (qla8044_check_fw_alive(vha)) {
+			if (ha->flags.isp82xx_fw_hung) {
 				halt_status = qla8044_rd_direct(vha,
 					QLA8044_PEG_HALT_STATUS1_INDEX);
 				if (halt_status &
@@ -2073,12 +2181,8 @@ qla8044_watchdog(struct scsi_qla_host *vha)
 						    __func__);
 						set_bit(ISP_ABORT_NEEDED,
 						    &vha->dpc_flags);
-						qla82xx_clear_pending_mbx(vha);
 					}
 				}
-				ha->flags.isp82xx_fw_hung = 1;
-				ql_log(ql_log_warn, vha, 0xb10a,
-				    "Firmware hung.\n");
 				qla2xxx_wake_dpc(vha);
 			}
 		}
@@ -2286,8 +2390,6 @@ qla8044_minidump_process_rdmem(struct scsi_qla_host *vha,
 		}
 
 		if (j >= MAX_CTL_CHECK) {
-			printk_ratelimited(KERN_ERR
-			    "%s: failed to read through agent\n", __func__);
 			write_unlock_irqrestore(&ha->hw_lock, flags);
 			return QLA_SUCCESS;
 		}
@@ -2882,6 +2984,231 @@ error_exit:
 	return rval;
 }
 
+static uint32_t
+qla8044_minidump_process_rddfe(struct scsi_qla_host *vha,
+	struct qla8044_minidump_entry_hdr *entry_hdr, uint32_t **d_ptr)
+{
+	int loop_cnt;
+	uint32_t addr1, addr2, value, data, temp, wrVal;
+	uint8_t stride, stride2;
+	uint16_t count;
+	uint32_t poll, mask, data_size, modify_mask;
+	uint32_t wait_count = 0;
+
+	uint32_t *data_ptr = *d_ptr;
+
+	struct qla8044_minidump_entry_rddfe *rddfe;
+	rddfe = (struct qla8044_minidump_entry_rddfe *) entry_hdr;
+
+	addr1 = rddfe->addr_1;
+	value = rddfe->value;
+	stride = rddfe->stride;
+	stride2 = rddfe->stride2;
+	count = rddfe->count;
+
+	poll = rddfe->poll;
+	mask = rddfe->mask;
+	modify_mask = rddfe->modify_mask;
+	data_size = rddfe->data_size;
+
+	addr2 = addr1 + stride;
+
+	for (loop_cnt = 0x0; loop_cnt < count; loop_cnt++) {
+		qla8044_wr_reg_indirect(vha, addr1, (0x40000000 | value));
+
+		wait_count = 0;
+		while (wait_count < poll) {
+			qla8044_rd_reg_indirect(vha, addr1, &temp);
+			if ((temp & mask) != 0)
+				break;
+			wait_count++;
+		}
+
+		if (wait_count == poll) {
+			ql_log(ql_log_warn, vha, 0xb153,
+			    "%s: TIMEOUT\n", __func__);
+			goto error;
+		} else {
+			qla8044_rd_reg_indirect(vha, addr2, &temp);
+			temp = temp & modify_mask;
+			temp = (temp | ((loop_cnt << 16) | loop_cnt));
+			wrVal = ((temp << 16) | temp);
+
+			qla8044_wr_reg_indirect(vha, addr2, wrVal);
+			qla8044_wr_reg_indirect(vha, addr1, value);
+
+			wait_count = 0;
+			while (wait_count < poll) {
+				qla8044_rd_reg_indirect(vha, addr1, &temp);
+				if ((temp & mask) != 0)
+					break;
+				wait_count++;
+			}
+			if (wait_count == poll) {
+				ql_log(ql_log_warn, vha, 0xb154,
+				    "%s: TIMEOUT\n", __func__);
+				goto error;
+			}
+
+			qla8044_wr_reg_indirect(vha, addr1,
+			    ((0x40000000 | value) + stride2));
+			wait_count = 0;
+			while (wait_count < poll) {
+				qla8044_rd_reg_indirect(vha, addr1, &temp);
+				if ((temp & mask) != 0)
+					break;
+				wait_count++;
+			}
+
+			if (wait_count == poll) {
+				ql_log(ql_log_warn, vha, 0xb155,
+				    "%s: TIMEOUT\n", __func__);
+				goto error;
+			}
+
+			qla8044_rd_reg_indirect(vha, addr2, &data);
+
+			*data_ptr++ = wrVal;
+			*data_ptr++ = data;
+		}
+
+	}
+
+	*d_ptr = data_ptr;
+	return QLA_SUCCESS;
+
+error:
+	return -1;
+
+}
+
+static uint32_t
+qla8044_minidump_process_rdmdio(struct scsi_qla_host *vha,
+	struct qla8044_minidump_entry_hdr *entry_hdr, uint32_t **d_ptr)
+{
+	int ret = 0;
+	uint32_t addr1, addr2, value1, value2, data, selVal;
+	uint8_t stride1, stride2;
+	uint32_t addr3, addr4, addr5, addr6, addr7;
+	uint16_t count, loop_cnt;
+	uint32_t poll, mask;
+	uint32_t *data_ptr = *d_ptr;
+
+	struct qla8044_minidump_entry_rdmdio *rdmdio;
+
+	rdmdio = (struct qla8044_minidump_entry_rdmdio *) entry_hdr;
+
+	addr1 = rdmdio->addr_1;
+	addr2 = rdmdio->addr_2;
+	value1 = rdmdio->value_1;
+	stride1 = rdmdio->stride_1;
+	stride2 = rdmdio->stride_2;
+	count = rdmdio->count;
+
+	poll = rdmdio->poll;
+	mask = rdmdio->mask;
+	value2 = rdmdio->value_2;
+
+	addr3 = addr1 + stride1;
+
+	for (loop_cnt = 0; loop_cnt < count; loop_cnt++) {
+		ret = qla8044_poll_wait_ipmdio_bus_idle(vha, addr1, addr2,
+		    addr3, mask);
+		if (ret == -1)
+			goto error;
+
+		addr4 = addr2 - stride1;
+		ret = qla8044_ipmdio_wr_reg(vha, addr1, addr3, mask, addr4,
+		    value2);
+		if (ret == -1)
+			goto error;
+
+		addr5 = addr2 - (2 * stride1);
+		ret = qla8044_ipmdio_wr_reg(vha, addr1, addr3, mask, addr5,
+		    value1);
+		if (ret == -1)
+			goto error;
+
+		addr6 = addr2 - (3 * stride1);
+		ret = qla8044_ipmdio_wr_reg(vha, addr1, addr3, mask,
+		    addr6, 0x2);
+		if (ret == -1)
+			goto error;
+
+		ret = qla8044_poll_wait_ipmdio_bus_idle(vha, addr1, addr2,
+		    addr3, mask);
+		if (ret == -1)
+			goto error;
+
+		addr7 = addr2 - (4 * stride1);
+			data = qla8044_ipmdio_rd_reg(vha, addr1, addr3,
+			    mask, addr7);
+		if (data == -1)
+			goto error;
+
+		selVal = (value2 << 18) | (value1 << 2) | 2;
+
+		stride2 = rdmdio->stride_2;
+		*data_ptr++ = selVal;
+		*data_ptr++ = data;
+
+		value1 = value1 + stride2;
+		*d_ptr = data_ptr;
+	}
+
+	return 0;
+
+error:
+	return -1;
+}
+
+static uint32_t qla8044_minidump_process_pollwr(struct scsi_qla_host *vha,
+		struct qla8044_minidump_entry_hdr *entry_hdr, uint32_t **d_ptr)
+{
+	uint32_t addr1, addr2, value1, value2, poll, mask, r_value;
+	uint32_t wait_count = 0;
+	struct qla8044_minidump_entry_pollwr *pollwr_hdr;
+
+	pollwr_hdr = (struct qla8044_minidump_entry_pollwr *)entry_hdr;
+	addr1 = pollwr_hdr->addr_1;
+	addr2 = pollwr_hdr->addr_2;
+	value1 = pollwr_hdr->value_1;
+	value2 = pollwr_hdr->value_2;
+
+	poll = pollwr_hdr->poll;
+	mask = pollwr_hdr->mask;
+
+	while (wait_count < poll) {
+		qla8044_rd_reg_indirect(vha, addr1, &r_value);
+
+		if ((r_value & poll) != 0)
+			break;
+		wait_count++;
+	}
+
+	if (wait_count == poll) {
+		ql_log(ql_log_warn, vha, 0xb156, "%s: TIMEOUT\n", __func__);
+		goto error;
+	}
+
+	qla8044_wr_reg_indirect(vha, addr2, value2);
+	qla8044_wr_reg_indirect(vha, addr1, value1);
+
+	wait_count = 0;
+	while (wait_count < poll) {
+		qla8044_rd_reg_indirect(vha, addr1, &r_value);
+
+		if ((r_value & poll) != 0)
+			break;
+		wait_count++;
+	}
+
+	return QLA_SUCCESS;
+
+error:
+	return -1;
+}
+
 /*
  *
  * qla8044_collect_md_data - Retrieve firmware minidump data.
@@ -3089,6 +3416,24 @@ qla8044_collect_md_data(struct scsi_qla_host *vha)
 			if (rval != QLA_SUCCESS)
 				qla8044_mark_entry_skipped(vha, entry_hdr, i);
 			break;
+		case QLA8044_RDDFE:
+			rval = qla8044_minidump_process_rddfe(vha, entry_hdr,
+			    &data_ptr);
+			if (rval != QLA_SUCCESS)
+				qla8044_mark_entry_skipped(vha, entry_hdr, i);
+			break;
+		case QLA8044_RDMDIO:
+			rval = qla8044_minidump_process_rdmdio(vha, entry_hdr,
+			    &data_ptr);
+			if (rval != QLA_SUCCESS)
+				qla8044_mark_entry_skipped(vha, entry_hdr, i);
+			break;
+		case QLA8044_POLLWR:
+			rval = qla8044_minidump_process_pollwr(vha, entry_hdr,
+			    &data_ptr);
+			if (rval != QLA_SUCCESS)
+				qla8044_mark_entry_skipped(vha, entry_hdr, i);
+			break;
 		case QLA82XX_RDNOP:
 		default:
 			qla8044_mark_entry_skipped(vha, entry_hdr, i);
@@ -3110,6 +3455,7 @@ skip_nxt_entry:
 		    "Dump data mismatch: Data collected: "
 		    "[0x%x], total_data_size:[0x%x]\n",
 		    data_collected, ha->md_dump_size);
+		rval = QLA_FUNCTION_FAILED;
 		goto md_failed;
 	}
 
@@ -3134,10 +3480,12 @@ qla8044_get_minidump(struct scsi_qla_host *vha)
 
 	if (!qla8044_collect_md_data(vha)) {
 		ha->fw_dumped = 1;
+		ha->prev_minidump_failed = 0;
 	} else {
 		ql_log(ql_log_fatal, vha, 0xb0db,
 		    "%s: Unable to collect minidump\n",
 		    __func__);
+		ha->prev_minidump_failed = 1;
 	}
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_nx2.h b/drivers/scsi/qla2xxx/qla_nx2.h
index 2ab2eabab90..ada36057d7c 100644
--- a/drivers/scsi/qla2xxx/qla_nx2.h
+++ b/drivers/scsi/qla2xxx/qla_nx2.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -133,6 +133,7 @@
 #define QLA8044_LINK_SPEED(f)		(0x36E0+(((f) >> 2) * 4))
 #define QLA8044_MAX_LINK_SPEED(f)       (0x36F0+(((f) / 4) * 4))
 #define QLA8044_LINK_SPEED_FACTOR	10
+#define QLA8044_FUN7_ACTIVE_INDEX	0x80
 
 /* FLASH API Defines */
 #define QLA8044_FLASH_MAX_WAIT_USEC	100
@@ -431,6 +432,50 @@ struct qla8044_minidump_entry_pollrd {
 	uint32_t rsvd_1;
 } __packed;
 
+struct qla8044_minidump_entry_rddfe {
+	struct qla8044_minidump_entry_hdr h;
+	uint32_t addr_1;
+	uint32_t value;
+	uint8_t stride;
+	uint8_t stride2;
+	uint16_t count;
+	uint32_t poll;
+	uint32_t mask;
+	uint32_t modify_mask;
+	uint32_t data_size;
+	uint32_t rsvd;
+
+} __packed;
+
+struct qla8044_minidump_entry_rdmdio {
+	struct qla8044_minidump_entry_hdr h;
+
+	uint32_t addr_1;
+	uint32_t addr_2;
+	uint32_t value_1;
+	uint8_t stride_1;
+	uint8_t stride_2;
+	uint16_t count;
+	uint32_t poll;
+	uint32_t mask;
+	uint32_t value_2;
+	uint32_t data_size;
+
+} __packed;
+
+struct qla8044_minidump_entry_pollwr {
+	struct qla8044_minidump_entry_hdr h;
+	uint32_t addr_1;
+	uint32_t addr_2;
+	uint32_t value_1;
+	uint32_t value_2;
+	uint32_t poll;
+	uint32_t mask;
+	uint32_t data_size;
+	uint32_t rsvd;
+
+}  __packed;
+
 /* RDMUX2 Entry */
 struct qla8044_minidump_entry_rdmux2 {
 	struct qla8044_minidump_entry_hdr h;
@@ -516,6 +561,9 @@ static const uint32_t qla8044_reg_tbl[] = {
 #define QLA8044_DBG_RSVD_ARRAY_LEN              8
 #define QLA8044_DBG_OCM_WNDREG_ARRAY_LEN        16
 #define QLA8044_SS_PCI_INDEX                    0
+#define QLA8044_RDDFE          38
+#define QLA8044_RDMDIO         39
+#define QLA8044_POLLWR         40
 
 struct qla8044_minidump_template_hdr {
 	uint32_t entry_type;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index afc84814e9b..d96bfb55e57 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -616,7 +616,7 @@ qla2x00_sp_free_dma(void *vha, void *ptr)
 
 	if (sp->flags & SRB_CRC_CTX_DSD_VALID) {
 		/* List assured to be having elements */
-		qla2x00_clean_dsd_pool(ha, sp);
+		qla2x00_clean_dsd_pool(ha, sp, NULL);
 		sp->flags &= ~SRB_CRC_CTX_DSD_VALID;
 	}
 
@@ -781,7 +781,7 @@ static int
 qla2x00_eh_wait_on_command(struct scsi_cmnd *cmd)
 {
 #define ABORT_POLLING_PERIOD	1000
-#define ABORT_WAIT_ITER		((10 * 1000) / (ABORT_POLLING_PERIOD))
+#define ABORT_WAIT_ITER		((2 * 1000) / (ABORT_POLLING_PERIOD))
 	unsigned long wait_iter = ABORT_WAIT_ITER;
 	scsi_qla_host_t *vha = shost_priv(cmd->device->host);
 	struct qla_hw_data *ha = vha->hw;
@@ -844,11 +844,8 @@ qla2x00_wait_for_hba_online(scsi_qla_host_t *vha)
 }
 
 /*
- * qla2x00_wait_for_reset_ready
- *    Wait till the HBA is online after going through
- *    <= MAX_RETRIES_OF_ISP_ABORT  or
- *    finally HBA is disabled ie marked offline or flash
- *    operations are in progress.
+ * qla2x00_wait_for_hba_ready
+ * Wait till the HBA is ready before doing driver unload
  *
  * Input:
  *     ha - pointer to host adapter structure
@@ -857,35 +854,15 @@ qla2x00_wait_for_hba_online(scsi_qla_host_t *vha)
  *    Does context switching-Release SPIN_LOCK
  *    (if any) before calling this routine.
  *
- * Return:
- *    Success (Adapter is online/no flash ops) : 0
- *    Failed  (Adapter is offline/disabled/flash ops in progress) : 1
  */
-static int
-qla2x00_wait_for_reset_ready(scsi_qla_host_t *vha)
+static void
+qla2x00_wait_for_hba_ready(scsi_qla_host_t *vha)
 {
-	int		return_status;
-	unsigned long	wait_online;
 	struct qla_hw_data *ha = vha->hw;
-	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
 
-	wait_online = jiffies + (MAX_LOOP_TIMEOUT * HZ);
-	while (((test_bit(ISP_ABORT_NEEDED, &base_vha->dpc_flags)) ||
-	    test_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags) ||
-	    test_bit(ISP_ABORT_RETRY, &base_vha->dpc_flags) ||
-	    ha->optrom_state != QLA_SWAITING ||
-	    ha->dpc_active) && time_before(jiffies, wait_online))
+	while ((!(vha->flags.online) || ha->dpc_active ||
+	    ha->flags.mbox_busy))
 		msleep(1000);
-
-	if (base_vha->flags.online &&  ha->optrom_state == QLA_SWAITING)
-		return_status = QLA_SUCCESS;
-	else
-		return_status = QLA_FUNCTION_FAILED;
-
-	ql_dbg(ql_dbg_taskm, vha, 0x8019,
-	    "%s return status=%d.\n", __func__, return_status);
-
-	return return_status;
 }
 
 int
@@ -945,7 +922,7 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 	int ret;
 	unsigned int id, lun;
 	unsigned long flags;
-	int wait = 0;
+	int rval, wait = 0;
 	struct qla_hw_data *ha = vha->hw;
 
 	if (!CMD_SP(cmd))
@@ -974,10 +951,20 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 	sp_get(sp);
 
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-	if (ha->isp_ops->abort_command(sp)) {
-		ret = FAILED;
+	rval = ha->isp_ops->abort_command(sp);
+	if (rval) {
+		if (rval == QLA_FUNCTION_PARAMETER_ERROR) {
+			/*
+			 * Decrement the ref_count since we can't find the
+			 * command
+			 */
+			atomic_dec(&sp->ref_count);
+			ret = SUCCESS;
+		} else
+			ret = FAILED;
+
 		ql_dbg(ql_dbg_taskm, vha, 0x8003,
-		    "Abort command mbx failed cmd=%p.\n", cmd);
+		    "Abort command mbx failed cmd=%p, rval=%x.\n", cmd, rval);
 	} else {
 		ql_dbg(ql_dbg_taskm, vha, 0x8004,
 		    "Abort command mbx success cmd=%p.\n", cmd);
@@ -985,6 +972,12 @@ qla2xxx_eh_abort(struct scsi_cmnd *cmd)
 	}
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
+	/*
+	 * Clear the slot in the oustanding_cmds array if we can't find the
+	 * command to reclaim the resources.
+	 */
+	if (rval == QLA_FUNCTION_PARAMETER_ERROR)
+		vha->req->outstanding_cmds[sp->handle] = NULL;
 	sp->done(ha, sp, 0);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
@@ -1236,7 +1229,11 @@ qla2xxx_eh_host_reset(struct scsi_cmnd *cmd)
 	ql_log(ql_log_info, vha, 0x8018,
 	    "ADAPTER RESET ISSUED nexus=%ld:%d:%d.\n", vha->host_no, id, lun);
 
-	if (qla2x00_wait_for_reset_ready(vha) != QLA_SUCCESS)
+	/*
+	 * No point in issuing another reset if one is active.  Also do not
+	 * attempt a reset if we are updating flash.
+	 */
+	if (qla2x00_reset_active(vha) || ha->optrom_state != QLA_SWAITING)
 		goto eh_host_reset_lock;
 
 	if (vha != base_vha) {
@@ -2270,6 +2267,13 @@ qla2x00_set_isp_flags(struct qla_hw_data *ha)
 		ha->device_type |= DT_IIDMA;
 		ha->fw_srisc_address = RISC_START_ADDRESS_2400;
 		break;
+	case PCI_DEVICE_ID_QLOGIC_ISP2271:
+		ha->device_type |= DT_ISP2271;
+		ha->device_type |= DT_ZIO_SUPPORTED;
+		ha->device_type |= DT_FWI2;
+		ha->device_type |= DT_IIDMA;
+		ha->fw_srisc_address = RISC_START_ADDRESS_2400;
+		break;
 	}
 
 	if (IS_QLA82XX(ha))
@@ -2346,7 +2350,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    pdev->device == PCI_DEVICE_ID_QLOGIC_ISP8031 ||
 	    pdev->device == PCI_DEVICE_ID_QLOGIC_ISPF001 ||
 	    pdev->device == PCI_DEVICE_ID_QLOGIC_ISP8044 ||
-	    pdev->device == PCI_DEVICE_ID_QLOGIC_ISP2071) {
+	    pdev->device == PCI_DEVICE_ID_QLOGIC_ISP2071 ||
+	    pdev->device == PCI_DEVICE_ID_QLOGIC_ISP2271) {
 		bars = pci_select_bars(pdev, IORESOURCE_MEM);
 		mem_only = 1;
 		ql_dbg_pci(ql_dbg_init, pdev, 0x0007,
@@ -2877,6 +2882,7 @@ skip_dpc:
 
 	base_vha->flags.init_done = 1;
 	base_vha->flags.online = 1;
+	ha->prev_minidump_failed = 0;
 
 	ql_dbg(ql_dbg_init, base_vha, 0x00f2,
 	    "Init done and hba is online.\n");
@@ -3136,6 +3142,8 @@ qla2x00_remove_one(struct pci_dev *pdev)
 	base_vha = pci_get_drvdata(pdev);
 	ha = base_vha->hw;
 
+	qla2x00_wait_for_hba_ready(base_vha);
+
 	set_bit(UNLOADING, &base_vha->dpc_flags);
 
 	if (IS_QLAFX00(ha))
@@ -3645,6 +3653,7 @@ qla2x00_free_fw_dump(struct qla_hw_data *ha)
 	ha->eft = NULL;
 	ha->eft_dma = 0;
 	ha->fw_dumped = 0;
+	ha->fw_dump_cap_flags = 0;
 	ha->fw_dump_reading = 0;
 	ha->fw_dump = NULL;
 	ha->fw_dump_len = 0;
@@ -4913,12 +4922,13 @@ qla2x00_do_dpc(void *data)
 				if (qlafx00_reset_initialize(base_vha)) {
 					/* Failed. Abort isp later. */
 					if (!test_bit(UNLOADING,
-					    &base_vha->dpc_flags))
+					    &base_vha->dpc_flags)) {
 						set_bit(ISP_UNRECOVERABLE,
 						    &base_vha->dpc_flags);
 						ql_dbg(ql_dbg_dpc, base_vha,
 						    0x4021,
 						    "Reset Recovery Failed\n");
+					}
 				}
 			}
 
@@ -5077,8 +5087,10 @@ intr_on_check:
 			ha->isp_ops->enable_intrs(ha);
 
 		if (test_and_clear_bit(BEACON_BLINK_NEEDED,
-					&base_vha->dpc_flags))
-			ha->isp_ops->beacon_blink(base_vha);
+					&base_vha->dpc_flags)) {
+			if (ha->beacon_blink_led == 1)
+				ha->isp_ops->beacon_blink(base_vha);
+		}
 
 		if (!IS_QLAFX00(ha))
 			qla2x00_do_dpc_all_vps(base_vha);
@@ -5325,7 +5337,7 @@ qla2x00_timer(scsi_qla_host_t *vha)
 #define FW_ISP82XX	7
 #define FW_ISP2031	8
 #define FW_ISP8031	9
-#define FW_ISP2071	10
+#define FW_ISP27XX	10
 
 #define FW_FILE_ISP21XX	"ql2100_fw.bin"
 #define FW_FILE_ISP22XX	"ql2200_fw.bin"
@@ -5337,7 +5349,7 @@ qla2x00_timer(scsi_qla_host_t *vha)
 #define FW_FILE_ISP82XX	"ql8200_fw.bin"
 #define FW_FILE_ISP2031	"ql2600_fw.bin"
 #define FW_FILE_ISP8031	"ql8300_fw.bin"
-#define FW_FILE_ISP2071	"ql2700_fw.bin"
+#define FW_FILE_ISP27XX	"ql2700_fw.bin"
 
 
 static DEFINE_MUTEX(qla_fw_lock);
@@ -5353,7 +5365,7 @@ static struct fw_blob qla_fw_blobs[FW_BLOBS] = {
 	{ .name = FW_FILE_ISP82XX, },
 	{ .name = FW_FILE_ISP2031, },
 	{ .name = FW_FILE_ISP8031, },
-	{ .name = FW_FILE_ISP2071, },
+	{ .name = FW_FILE_ISP27XX, },
 };
 
 struct fw_blob *
@@ -5382,8 +5394,8 @@ qla2x00_request_firmware(scsi_qla_host_t *vha)
 		blob = &qla_fw_blobs[FW_ISP2031];
 	} else if (IS_QLA8031(ha)) {
 		blob = &qla_fw_blobs[FW_ISP8031];
-	} else if (IS_QLA2071(ha)) {
-		blob = &qla_fw_blobs[FW_ISP2071];
+	} else if (IS_QLA27XX(ha)) {
+		blob = &qla_fw_blobs[FW_ISP27XX];
 	} else {
 		return NULL;
 	}
@@ -5714,6 +5726,7 @@ static struct pci_device_id qla2xxx_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISPF001) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP8044) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP2071) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, PCI_DEVICE_ID_QLOGIC_ISP2271) },
 	{ 0 },
 };
 MODULE_DEVICE_TABLE(pci, qla2xxx_pci_tbl);
diff --git a/drivers/scsi/qla2xxx/qla_settings.h b/drivers/scsi/qla2xxx/qla_settings.h
index 46ef0ac48f4..2fb7ebfbbc3 100644
--- a/drivers/scsi/qla2xxx/qla_settings.h
+++ b/drivers/scsi/qla2xxx/qla_settings.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index f28123e8ed6..bca173e56f1 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -1727,11 +1727,8 @@ qla83xx_beacon_blink(struct scsi_qla_host *vha)
 	if (IS_QLA2031(ha)) {
 		led_select_value = qla83xx_select_led_port(ha);
 
-		qla83xx_wr_reg(vha, led_select_value, 0x40002000);
-		qla83xx_wr_reg(vha, led_select_value + 4, 0x40002000);
-		msleep(1000);
-		qla83xx_wr_reg(vha, led_select_value, 0x40004000);
-		qla83xx_wr_reg(vha, led_select_value + 4, 0x40004000);
+		qla83xx_wr_reg(vha, led_select_value, 0x40000230);
+		qla83xx_wr_reg(vha, led_select_value + 4, 0x40000230);
 	} else if (IS_QLA8031(ha)) {
 		led_select_value = qla83xx_select_led_port(ha);
 
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 0cb73074c19..e632e14180c 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -104,7 +104,6 @@ static void qlt_reject_free_srr_imm(struct scsi_qla_host *ha,
 /*
  * Global Variables
  */
-static struct kmem_cache *qla_tgt_cmd_cachep;
 static struct kmem_cache *qla_tgt_mgmt_cmd_cachep;
 static mempool_t *qla_tgt_mgmt_cmd_mempool;
 static struct workqueue_struct *qla_tgt_wq;
@@ -182,6 +181,11 @@ struct scsi_qla_host *qlt_find_host_by_vp_idx(struct scsi_qla_host *vha,
 void qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha,
 	struct atio_from_isp *atio)
 {
+	ql_dbg(ql_dbg_tgt, vha, 0xe072,
+		"%s: qla_target(%d): type %x ox_id %04x\n",
+		__func__, vha->vp_idx, atio->u.raw.entry_type,
+		be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id));
+
 	switch (atio->u.raw.entry_type) {
 	case ATIO_TYPE7:
 	{
@@ -236,6 +240,10 @@ void qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *vha,
 void qlt_response_pkt_all_vps(struct scsi_qla_host *vha, response_t *pkt)
 {
 	switch (pkt->entry_type) {
+	case CTIO_CRC2:
+		ql_dbg(ql_dbg_tgt, vha, 0xe073,
+			"qla_target(%d):%s: CRC2 Response pkt\n",
+			vha->vp_idx, __func__);
 	case CTIO_TYPE7:
 	{
 		struct ctio7_from_24xx *entry = (struct ctio7_from_24xx *)pkt;
@@ -1120,7 +1128,7 @@ static void qlt_24xx_retry_term_exchange(struct scsi_qla_host *vha,
 	ctio->u.status1.flags =
 	    __constant_cpu_to_le16(CTIO7_FLAGS_STATUS_MODE_1 |
 		CTIO7_FLAGS_TERMINATE);
-	ctio->u.status1.ox_id = entry->fcp_hdr_le.ox_id;
+	ctio->u.status1.ox_id = cpu_to_le16(entry->fcp_hdr_le.ox_id);
 
 	qla2x00_start_iocbs(vha, vha->req);
 
@@ -1254,6 +1262,7 @@ static void qlt_24xx_send_task_mgmt_ctio(struct scsi_qla_host *ha,
 {
 	struct atio_from_isp *atio = &mcmd->orig_iocb.atio;
 	struct ctio7_to_24xx *ctio;
+	uint16_t temp;
 
 	ql_dbg(ql_dbg_tgt, ha, 0xe008,
 	    "Sending task mgmt CTIO7 (ha=%p, atio=%p, resp_code=%x\n",
@@ -1284,7 +1293,8 @@ static void qlt_24xx_send_task_mgmt_ctio(struct scsi_qla_host *ha,
 	ctio->u.status1.flags = (atio->u.isp24.attr << 9) |
 	    __constant_cpu_to_le16(CTIO7_FLAGS_STATUS_MODE_1 |
 		CTIO7_FLAGS_SEND_STATUS);
-	ctio->u.status1.ox_id = swab16(atio->u.isp24.fcp_hdr.ox_id);
+	temp = be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id);
+	ctio->u.status1.ox_id = cpu_to_le16(temp);
 	ctio->u.status1.scsi_status =
 	    __constant_cpu_to_le16(SS_RESPONSE_INFO_LEN_VALID);
 	ctio->u.status1.response_len = __constant_cpu_to_le16(8);
@@ -1350,13 +1360,42 @@ static int qlt_pci_map_calc_cnt(struct qla_tgt_prm *prm)
 
 	prm->cmd->sg_mapped = 1;
 
-	/*
-	 * If greater than four sg entries then we need to allocate
-	 * the continuation entries
-	 */
-	if (prm->seg_cnt > prm->tgt->datasegs_per_cmd)
-		prm->req_cnt += DIV_ROUND_UP(prm->seg_cnt -
-		    prm->tgt->datasegs_per_cmd, prm->tgt->datasegs_per_cont);
+	if (cmd->se_cmd.prot_op == TARGET_PROT_NORMAL) {
+		/*
+		 * If greater than four sg entries then we need to allocate
+		 * the continuation entries
+		 */
+		if (prm->seg_cnt > prm->tgt->datasegs_per_cmd)
+			prm->req_cnt += DIV_ROUND_UP(prm->seg_cnt -
+			prm->tgt->datasegs_per_cmd,
+			prm->tgt->datasegs_per_cont);
+	} else {
+		/* DIF */
+		if ((cmd->se_cmd.prot_op == TARGET_PROT_DIN_INSERT) ||
+		    (cmd->se_cmd.prot_op == TARGET_PROT_DOUT_STRIP)) {
+			prm->seg_cnt = DIV_ROUND_UP(cmd->bufflen, cmd->blk_sz);
+			prm->tot_dsds = prm->seg_cnt;
+		} else
+			prm->tot_dsds = prm->seg_cnt;
+
+		if (cmd->prot_sg_cnt) {
+			prm->prot_sg      = cmd->prot_sg;
+			prm->prot_seg_cnt = pci_map_sg(prm->tgt->ha->pdev,
+				cmd->prot_sg, cmd->prot_sg_cnt,
+				cmd->dma_data_direction);
+			if (unlikely(prm->prot_seg_cnt == 0))
+				goto out_err;
+
+			if ((cmd->se_cmd.prot_op == TARGET_PROT_DIN_INSERT) ||
+			    (cmd->se_cmd.prot_op == TARGET_PROT_DOUT_STRIP)) {
+				/* Dif Bundling not support here */
+				prm->prot_seg_cnt = DIV_ROUND_UP(cmd->bufflen,
+								cmd->blk_sz);
+				prm->tot_dsds += prm->prot_seg_cnt;
+			} else
+				prm->tot_dsds += prm->prot_seg_cnt;
+		}
+	}
 
 	ql_dbg(ql_dbg_tgt, prm->cmd->vha, 0xe009, "seg_cnt=%d, req_cnt=%d\n",
 	    prm->seg_cnt, prm->req_cnt);
@@ -1377,6 +1416,16 @@ static inline void qlt_unmap_sg(struct scsi_qla_host *vha,
 	BUG_ON(!cmd->sg_mapped);
 	pci_unmap_sg(ha->pdev, cmd->sg, cmd->sg_cnt, cmd->dma_data_direction);
 	cmd->sg_mapped = 0;
+
+	if (cmd->prot_sg_cnt)
+		pci_unmap_sg(ha->pdev, cmd->prot_sg, cmd->prot_sg_cnt,
+			cmd->dma_data_direction);
+
+	if (cmd->ctx_dsd_alloced)
+		qla2x00_clean_dsd_pool(ha, NULL, cmd);
+
+	if (cmd->ctx)
+		dma_pool_free(ha->dl_dma_pool, cmd->ctx, cmd->ctx->crc_ctx_dma);
 }
 
 static int qlt_check_reserve_free_req(struct scsi_qla_host *vha,
@@ -1466,6 +1515,7 @@ static int qlt_24xx_build_ctio_pkt(struct qla_tgt_prm *prm,
 	struct ctio7_to_24xx *pkt;
 	struct qla_hw_data *ha = vha->hw;
 	struct atio_from_isp *atio = &prm->cmd->atio;
+	uint16_t temp;
 
 	pkt = (struct ctio7_to_24xx *)vha->req->ring_ptr;
 	prm->pkt = pkt;
@@ -1494,13 +1544,13 @@ static int qlt_24xx_build_ctio_pkt(struct qla_tgt_prm *prm,
 	pkt->initiator_id[2] = atio->u.isp24.fcp_hdr.s_id[0];
 	pkt->exchange_addr = atio->u.isp24.exchange_addr;
 	pkt->u.status0.flags |= (atio->u.isp24.attr << 9);
-	pkt->u.status0.ox_id = swab16(atio->u.isp24.fcp_hdr.ox_id);
+	temp = be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id);
+	pkt->u.status0.ox_id = cpu_to_le16(temp);
 	pkt->u.status0.relative_offset = cpu_to_le32(prm->cmd->offset);
 
 	ql_dbg(ql_dbg_tgt, vha, 0xe00c,
 	    "qla_target(%d): handle(cmd) -> %08x, timeout %d, ox_id %#x\n",
-	    vha->vp_idx, pkt->handle, QLA_TGT_TIMEOUT,
-	    le16_to_cpu(pkt->u.status0.ox_id));
+	    vha->vp_idx, pkt->handle, QLA_TGT_TIMEOUT, temp);
 	return 0;
 }
 
@@ -1665,8 +1715,9 @@ static int qlt_pre_xmit_response(struct qla_tgt_cmd *cmd,
 		return QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED;
 	}
 
-	ql_dbg(ql_dbg_tgt, vha, 0xe011, "qla_target(%d): tag=%u\n",
-	    vha->vp_idx, cmd->tag);
+	ql_dbg(ql_dbg_tgt, vha, 0xe011, "qla_target(%d): tag=%u ox_id %04x\n",
+		vha->vp_idx, cmd->tag,
+		be16_to_cpu(cmd->atio.u.isp24.fcp_hdr.ox_id));
 
 	prm->cmd = cmd;
 	prm->tgt = tgt;
@@ -1902,6 +1953,328 @@ skip_explict_conf:
 	/* Sense with len > 24, is it possible ??? */
 }
 
+
+
+/* diff  */
+static inline int
+qlt_hba_err_chk_enabled(struct se_cmd *se_cmd)
+{
+	/*
+	 * Uncomment when corresponding SCSI changes are done.
+	 *
+	 if (!sp->cmd->prot_chk)
+	 return 0;
+	 *
+	 */
+	switch (se_cmd->prot_op) {
+	case TARGET_PROT_DOUT_INSERT:
+	case TARGET_PROT_DIN_STRIP:
+		if (ql2xenablehba_err_chk >= 1)
+			return 1;
+		break;
+	case TARGET_PROT_DOUT_PASS:
+	case TARGET_PROT_DIN_PASS:
+		if (ql2xenablehba_err_chk >= 2)
+			return 1;
+		break;
+	case TARGET_PROT_DIN_INSERT:
+	case TARGET_PROT_DOUT_STRIP:
+		return 1;
+	default:
+		break;
+	}
+	return 0;
+}
+
+/*
+ * qla24xx_set_t10dif_tags_from_cmd - Extract Ref and App tags from SCSI command
+ *
+ */
+static inline void
+qlt_set_t10dif_tags(struct se_cmd *se_cmd, struct crc_context *ctx)
+{
+	uint32_t lba = 0xffffffff & se_cmd->t_task_lba;
+
+	/* wait til Mode Sense/Select cmd, modepage Ah, subpage 2
+	 * have been immplemented by TCM, before AppTag is avail.
+	 * Look for modesense_handlers[]
+	 */
+	ctx->app_tag = 0;
+	ctx->app_tag_mask[0] = 0x0;
+	ctx->app_tag_mask[1] = 0x0;
+
+	switch (se_cmd->prot_type) {
+	case TARGET_DIF_TYPE0_PROT:
+		/*
+		 * No check for ql2xenablehba_err_chk, as it would be an
+		 * I/O error if hba tag generation is not done.
+		 */
+		ctx->ref_tag = cpu_to_le32(lba);
+
+		if (!qlt_hba_err_chk_enabled(se_cmd))
+			break;
+
+		/* enable ALL bytes of the ref tag */
+		ctx->ref_tag_mask[0] = 0xff;
+		ctx->ref_tag_mask[1] = 0xff;
+		ctx->ref_tag_mask[2] = 0xff;
+		ctx->ref_tag_mask[3] = 0xff;
+		break;
+	/*
+	 * For TYpe 1 protection: 16 bit GUARD tag, 32 bit REF tag, and
+	 * 16 bit app tag.
+	 */
+	case TARGET_DIF_TYPE1_PROT:
+		ctx->ref_tag = cpu_to_le32(lba);
+
+		if (!qlt_hba_err_chk_enabled(se_cmd))
+			break;
+
+		/* enable ALL bytes of the ref tag */
+		ctx->ref_tag_mask[0] = 0xff;
+		ctx->ref_tag_mask[1] = 0xff;
+		ctx->ref_tag_mask[2] = 0xff;
+		ctx->ref_tag_mask[3] = 0xff;
+		break;
+	/*
+	 * For TYPE 2 protection: 16 bit GUARD + 32 bit REF tag has to
+	 * match LBA in CDB + N
+	 */
+	case TARGET_DIF_TYPE2_PROT:
+		ctx->ref_tag = cpu_to_le32(lba);
+
+		if (!qlt_hba_err_chk_enabled(se_cmd))
+			break;
+
+		/* enable ALL bytes of the ref tag */
+		ctx->ref_tag_mask[0] = 0xff;
+		ctx->ref_tag_mask[1] = 0xff;
+		ctx->ref_tag_mask[2] = 0xff;
+		ctx->ref_tag_mask[3] = 0xff;
+		break;
+
+	/* For Type 3 protection: 16 bit GUARD only */
+	case TARGET_DIF_TYPE3_PROT:
+		ctx->ref_tag_mask[0] = ctx->ref_tag_mask[1] =
+			ctx->ref_tag_mask[2] = ctx->ref_tag_mask[3] = 0x00;
+		break;
+	}
+}
+
+
+static inline int
+qlt_build_ctio_crc2_pkt(struct qla_tgt_prm *prm, scsi_qla_host_t *vha)
+{
+	uint32_t		*cur_dsd;
+	int			sgc;
+	uint32_t		transfer_length = 0;
+	uint32_t		data_bytes;
+	uint32_t		dif_bytes;
+	uint8_t			bundling = 1;
+	uint8_t			*clr_ptr;
+	struct crc_context	*crc_ctx_pkt = NULL;
+	struct qla_hw_data	*ha;
+	struct ctio_crc2_to_fw	*pkt;
+	dma_addr_t		crc_ctx_dma;
+	uint16_t		fw_prot_opts = 0;
+	struct qla_tgt_cmd	*cmd = prm->cmd;
+	struct se_cmd		*se_cmd = &cmd->se_cmd;
+	uint32_t h;
+	struct atio_from_isp *atio = &prm->cmd->atio;
+	uint16_t t16;
+
+	sgc = 0;
+	ha = vha->hw;
+
+	pkt = (struct ctio_crc2_to_fw *)vha->req->ring_ptr;
+	prm->pkt = pkt;
+	memset(pkt, 0, sizeof(*pkt));
+
+	ql_dbg(ql_dbg_tgt, vha, 0xe071,
+		"qla_target(%d):%s: se_cmd[%p] CRC2 prot_op[0x%x] cmd prot sg:cnt[%p:%x] lba[%llu]\n",
+		vha->vp_idx, __func__, se_cmd, se_cmd->prot_op,
+		prm->prot_sg, prm->prot_seg_cnt, se_cmd->t_task_lba);
+
+	if ((se_cmd->prot_op == TARGET_PROT_DIN_INSERT) ||
+	    (se_cmd->prot_op == TARGET_PROT_DOUT_STRIP))
+		bundling = 0;
+
+	/* Compute dif len and adjust data len to incude protection */
+	data_bytes = cmd->bufflen;
+	dif_bytes  = (data_bytes / cmd->blk_sz) * 8;
+
+	switch (se_cmd->prot_op) {
+	case TARGET_PROT_DIN_INSERT:
+	case TARGET_PROT_DOUT_STRIP:
+		transfer_length = data_bytes;
+		data_bytes += dif_bytes;
+		break;
+
+	case TARGET_PROT_DIN_STRIP:
+	case TARGET_PROT_DOUT_INSERT:
+	case TARGET_PROT_DIN_PASS:
+	case TARGET_PROT_DOUT_PASS:
+		transfer_length = data_bytes + dif_bytes;
+		break;
+
+	default:
+		BUG();
+		break;
+	}
+
+	if (!qlt_hba_err_chk_enabled(se_cmd))
+		fw_prot_opts |= 0x10; /* Disable Guard tag checking */
+	/* HBA error checking enabled */
+	else if (IS_PI_UNINIT_CAPABLE(ha)) {
+		if ((se_cmd->prot_type == TARGET_DIF_TYPE1_PROT) ||
+		    (se_cmd->prot_type == TARGET_DIF_TYPE2_PROT))
+			fw_prot_opts |= PO_DIS_VALD_APP_ESC;
+		else if (se_cmd->prot_type == TARGET_DIF_TYPE3_PROT)
+			fw_prot_opts |= PO_DIS_VALD_APP_REF_ESC;
+	}
+
+	switch (se_cmd->prot_op) {
+	case TARGET_PROT_DIN_INSERT:
+	case TARGET_PROT_DOUT_INSERT:
+		fw_prot_opts |= PO_MODE_DIF_INSERT;
+		break;
+	case TARGET_PROT_DIN_STRIP:
+	case TARGET_PROT_DOUT_STRIP:
+		fw_prot_opts |= PO_MODE_DIF_REMOVE;
+		break;
+	case TARGET_PROT_DIN_PASS:
+	case TARGET_PROT_DOUT_PASS:
+		fw_prot_opts |= PO_MODE_DIF_PASS;
+		/* FUTURE: does tcm require T10CRC<->IPCKSUM conversion? */
+		break;
+	default:/* Normal Request */
+		fw_prot_opts |= PO_MODE_DIF_PASS;
+		break;
+	}
+
+
+	/* ---- PKT ---- */
+	/* Update entry type to indicate Command Type CRC_2 IOCB */
+	pkt->entry_type  = CTIO_CRC2;
+	pkt->entry_count = 1;
+	pkt->vp_index = vha->vp_idx;
+
+	h = qlt_make_handle(vha);
+	if (unlikely(h == QLA_TGT_NULL_HANDLE)) {
+		/*
+		 * CTIO type 7 from the firmware doesn't provide a way to
+		 * know the initiator's LOOP ID, hence we can't find
+		 * the session and, so, the command.
+		 */
+		return -EAGAIN;
+	} else
+		ha->tgt.cmds[h-1] = prm->cmd;
+
+
+	pkt->handle  = h | CTIO_COMPLETION_HANDLE_MARK;
+	pkt->nport_handle = prm->cmd->loop_id;
+	pkt->timeout = __constant_cpu_to_le16(QLA_TGT_TIMEOUT);
+	pkt->initiator_id[0] = atio->u.isp24.fcp_hdr.s_id[2];
+	pkt->initiator_id[1] = atio->u.isp24.fcp_hdr.s_id[1];
+	pkt->initiator_id[2] = atio->u.isp24.fcp_hdr.s_id[0];
+	pkt->exchange_addr   = atio->u.isp24.exchange_addr;
+
+	/* silence compile warning */
+	t16 = be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id);
+	pkt->ox_id  = cpu_to_le16(t16);
+
+	t16 = (atio->u.isp24.attr << 9);
+	pkt->flags |= cpu_to_le16(t16);
+	pkt->relative_offset = cpu_to_le32(prm->cmd->offset);
+
+	/* Set transfer direction */
+	if (cmd->dma_data_direction == DMA_TO_DEVICE)
+		pkt->flags = __constant_cpu_to_le16(CTIO7_FLAGS_DATA_IN);
+	else if (cmd->dma_data_direction == DMA_FROM_DEVICE)
+		pkt->flags = __constant_cpu_to_le16(CTIO7_FLAGS_DATA_OUT);
+
+
+	pkt->dseg_count = prm->tot_dsds;
+	/* Fibre channel byte count */
+	pkt->transfer_length = cpu_to_le32(transfer_length);
+
+
+	/* ----- CRC context -------- */
+
+	/* Allocate CRC context from global pool */
+	crc_ctx_pkt = cmd->ctx =
+	    dma_pool_alloc(ha->dl_dma_pool, GFP_ATOMIC, &crc_ctx_dma);
+
+	if (!crc_ctx_pkt)
+		goto crc_queuing_error;
+
+	/* Zero out CTX area. */
+	clr_ptr = (uint8_t *)crc_ctx_pkt;
+	memset(clr_ptr, 0, sizeof(*crc_ctx_pkt));
+
+	crc_ctx_pkt->crc_ctx_dma = crc_ctx_dma;
+	INIT_LIST_HEAD(&crc_ctx_pkt->dsd_list);
+
+	/* Set handle */
+	crc_ctx_pkt->handle = pkt->handle;
+
+	qlt_set_t10dif_tags(se_cmd, crc_ctx_pkt);
+
+	pkt->crc_context_address[0] = cpu_to_le32(LSD(crc_ctx_dma));
+	pkt->crc_context_address[1] = cpu_to_le32(MSD(crc_ctx_dma));
+	pkt->crc_context_len = CRC_CONTEXT_LEN_FW;
+
+
+	if (!bundling) {
+		cur_dsd = (uint32_t *) &crc_ctx_pkt->u.nobundling.data_address;
+	} else {
+		/*
+		 * Configure Bundling if we need to fetch interlaving
+		 * protection PCI accesses
+		 */
+		fw_prot_opts |= PO_ENABLE_DIF_BUNDLING;
+		crc_ctx_pkt->u.bundling.dif_byte_count = cpu_to_le32(dif_bytes);
+		crc_ctx_pkt->u.bundling.dseg_count =
+			cpu_to_le16(prm->tot_dsds - prm->prot_seg_cnt);
+		cur_dsd = (uint32_t *) &crc_ctx_pkt->u.bundling.data_address;
+	}
+
+	/* Finish the common fields of CRC pkt */
+	crc_ctx_pkt->blk_size   = cpu_to_le16(cmd->blk_sz);
+	crc_ctx_pkt->prot_opts  = cpu_to_le16(fw_prot_opts);
+	crc_ctx_pkt->byte_count = cpu_to_le32(data_bytes);
+	crc_ctx_pkt->guard_seed = __constant_cpu_to_le16(0);
+
+
+	/* Walks data segments */
+	pkt->flags |= __constant_cpu_to_le16(CTIO7_FLAGS_DSD_PTR);
+
+	if (!bundling && prm->prot_seg_cnt) {
+		if (qla24xx_walk_and_build_sglist_no_difb(ha, NULL, cur_dsd,
+			prm->tot_dsds, cmd))
+			goto crc_queuing_error;
+	} else if (qla24xx_walk_and_build_sglist(ha, NULL, cur_dsd,
+		(prm->tot_dsds - prm->prot_seg_cnt), cmd))
+		goto crc_queuing_error;
+
+	if (bundling && prm->prot_seg_cnt) {
+		/* Walks dif segments */
+		pkt->add_flags |= CTIO_CRC2_AF_DIF_DSD_ENA;
+
+		cur_dsd = (uint32_t *) &crc_ctx_pkt->u.bundling.dif_address;
+		if (qla24xx_walk_and_build_prot_sglist(ha, NULL, cur_dsd,
+			prm->prot_seg_cnt, cmd))
+			goto crc_queuing_error;
+	}
+	return QLA_SUCCESS;
+
+crc_queuing_error:
+	/* Cleanup will be performed by the caller */
+
+	return QLA_FUNCTION_FAILED;
+}
+
+
 /*
  * Callback to setup response of xmit_type of QLA_TGT_XMIT_DATA and *
  * QLA_TGT_XMIT_STATUS for >= 24xx silicon
@@ -1921,9 +2294,10 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	qlt_check_srr_debug(cmd, &xmit_type);
 
 	ql_dbg(ql_dbg_tgt, cmd->vha, 0xe018,
-	    "is_send_status=%d, cmd->bufflen=%d, cmd->sg_cnt=%d, "
-	    "cmd->dma_data_direction=%d\n", (xmit_type & QLA_TGT_XMIT_STATUS) ?
-	    1 : 0, cmd->bufflen, cmd->sg_cnt, cmd->dma_data_direction);
+	    "is_send_status=%d, cmd->bufflen=%d, cmd->sg_cnt=%d, cmd->dma_data_direction=%d se_cmd[%p]\n",
+	    (xmit_type & QLA_TGT_XMIT_STATUS) ?
+	    1 : 0, cmd->bufflen, cmd->sg_cnt, cmd->dma_data_direction,
+	    &cmd->se_cmd);
 
 	res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status,
 	    &full_req_cnt);
@@ -1941,7 +2315,10 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 	if (unlikely(res))
 		goto out_unmap_unlock;
 
-	res = qlt_24xx_build_ctio_pkt(&prm, vha);
+	if (cmd->se_cmd.prot_op && (xmit_type & QLA_TGT_XMIT_DATA))
+		res = qlt_build_ctio_crc2_pkt(&prm, vha);
+	else
+		res = qlt_24xx_build_ctio_pkt(&prm, vha);
 	if (unlikely(res != 0))
 		goto out_unmap_unlock;
 
@@ -1953,7 +2330,8 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 		    __constant_cpu_to_le16(CTIO7_FLAGS_DATA_IN |
 			CTIO7_FLAGS_STATUS_MODE_0);
 
-		qlt_load_data_segments(&prm, vha);
+		if (cmd->se_cmd.prot_op == TARGET_PROT_NORMAL)
+			qlt_load_data_segments(&prm, vha);
 
 		if (prm.add_status_pkt == 0) {
 			if (xmit_type & QLA_TGT_XMIT_STATUS) {
@@ -1983,8 +2361,14 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 			ql_dbg(ql_dbg_tgt, vha, 0xe019,
 			    "Building additional status packet\n");
 
+			/*
+			 * T10Dif: ctio_crc2_to_fw overlay ontop of
+			 * ctio7_to_24xx
+			 */
 			memcpy(ctio, pkt, sizeof(*ctio));
+			/* reset back to CTIO7 */
 			ctio->entry_count = 1;
+			ctio->entry_type = CTIO_TYPE7;
 			ctio->dseg_count = 0;
 			ctio->u.status1.flags &= ~__constant_cpu_to_le16(
 			    CTIO7_FLAGS_DATA_IN);
@@ -1993,6 +2377,11 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
 			pkt->handle |= CTIO_INTERMEDIATE_HANDLE_MARK;
 			pkt->u.status0.flags |= __constant_cpu_to_le16(
 			    CTIO7_FLAGS_DONT_RET_CTIO);
+
+			/* qlt_24xx_init_ctio_to_isp will correct
+			 * all neccessary fields that's part of CTIO7.
+			 * There should be no residual of CTIO-CRC2 data.
+			 */
 			qlt_24xx_init_ctio_to_isp((struct ctio7_to_24xx *)ctio,
 			    &prm);
 			pr_debug("Status CTIO7: %p\n", ctio);
@@ -2041,8 +2430,10 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd)
 	if (qlt_issue_marker(vha, 0) != QLA_SUCCESS)
 		return -EIO;
 
-	ql_dbg(ql_dbg_tgt, vha, 0xe01b, "CTIO_start: vha(%d)",
-	    (int)vha->vp_idx);
+	ql_dbg(ql_dbg_tgt, vha, 0xe01b,
+		"%s: CTIO_start: vha(%d) se_cmd %p ox_id %04x\n",
+		__func__, (int)vha->vp_idx, &cmd->se_cmd,
+		be16_to_cpu(cmd->atio.u.isp24.fcp_hdr.ox_id));
 
 	/* Calculate number of entries and segments required */
 	if (qlt_pci_map_calc_cnt(&prm) != 0)
@@ -2054,14 +2445,19 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd)
 	res = qlt_check_reserve_free_req(vha, prm.req_cnt);
 	if (res != 0)
 		goto out_unlock_free_unmap;
+	if (cmd->se_cmd.prot_op)
+		res = qlt_build_ctio_crc2_pkt(&prm, vha);
+	else
+		res = qlt_24xx_build_ctio_pkt(&prm, vha);
 
-	res = qlt_24xx_build_ctio_pkt(&prm, vha);
 	if (unlikely(res != 0))
 		goto out_unlock_free_unmap;
 	pkt = (struct ctio7_to_24xx *)prm.pkt;
 	pkt->u.status0.flags |= __constant_cpu_to_le16(CTIO7_FLAGS_DATA_OUT |
 	    CTIO7_FLAGS_STATUS_MODE_0);
-	qlt_load_data_segments(&prm, vha);
+
+	if (cmd->se_cmd.prot_op == TARGET_PROT_NORMAL)
+		qlt_load_data_segments(&prm, vha);
 
 	cmd->state = QLA_TGT_STATE_NEED_DATA;
 
@@ -2079,6 +2475,143 @@ out_unlock_free_unmap:
 }
 EXPORT_SYMBOL(qlt_rdy_to_xfer);
 
+
+/*
+ * Checks the guard or meta-data for the type of error
+ * detected by the HBA.
+ */
+static inline int
+qlt_handle_dif_error(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd,
+		struct ctio_crc_from_fw *sts)
+{
+	uint8_t		*ap = &sts->actual_dif[0];
+	uint8_t		*ep = &sts->expected_dif[0];
+	uint32_t	e_ref_tag, a_ref_tag;
+	uint16_t	e_app_tag, a_app_tag;
+	uint16_t	e_guard, a_guard;
+	uint64_t	lba = cmd->se_cmd.t_task_lba;
+
+	a_guard   = be16_to_cpu(*(uint16_t *)(ap + 0));
+	a_app_tag = be16_to_cpu(*(uint16_t *)(ap + 2));
+	a_ref_tag = be32_to_cpu(*(uint32_t *)(ap + 4));
+
+	e_guard   = be16_to_cpu(*(uint16_t *)(ep + 0));
+	e_app_tag = be16_to_cpu(*(uint16_t *)(ep + 2));
+	e_ref_tag = be32_to_cpu(*(uint32_t *)(ep + 4));
+
+	ql_dbg(ql_dbg_tgt, vha, 0xe075,
+	    "iocb(s) %p Returned STATUS.\n", sts);
+
+	ql_dbg(ql_dbg_tgt, vha, 0xf075,
+	    "dif check TGT cdb 0x%x lba 0x%llu: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x]\n",
+	    cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
+	    a_ref_tag, e_ref_tag, a_app_tag, e_app_tag, a_guard, e_guard);
+
+	/*
+	 * Ignore sector if:
+	 * For type     3: ref & app tag is all 'f's
+	 * For type 0,1,2: app tag is all 'f's
+	 */
+	if ((a_app_tag == 0xffff) &&
+	    ((cmd->se_cmd.prot_type != TARGET_DIF_TYPE3_PROT) ||
+	     (a_ref_tag == 0xffffffff))) {
+		uint32_t blocks_done;
+
+		/* 2TB boundary case covered automatically with this */
+		blocks_done = e_ref_tag - (uint32_t)lba + 1;
+		cmd->se_cmd.bad_sector = e_ref_tag;
+		cmd->se_cmd.pi_err = 0;
+		ql_dbg(ql_dbg_tgt, vha, 0xf074,
+			"need to return scsi good\n");
+
+		/* Update protection tag */
+		if (cmd->prot_sg_cnt) {
+			uint32_t i, j = 0, k = 0, num_ent;
+			struct scatterlist *sg, *sgl;
+
+
+			sgl = cmd->prot_sg;
+
+			/* Patch the corresponding protection tags */
+			for_each_sg(sgl, sg, cmd->prot_sg_cnt, i) {
+				num_ent = sg_dma_len(sg) / 8;
+				if (k + num_ent < blocks_done) {
+					k += num_ent;
+					continue;
+				}
+				j = blocks_done - k - 1;
+				k = blocks_done;
+				break;
+			}
+
+			if (k != blocks_done) {
+				ql_log(ql_log_warn, vha, 0xf076,
+				    "unexpected tag values tag:lba=%u:%llu)\n",
+				    e_ref_tag, (unsigned long long)lba);
+				goto out;
+			}
+
+#if 0
+			struct sd_dif_tuple *spt;
+			/* TODO:
+			 * This section came from initiator. Is it valid here?
+			 * should ulp be override with actual val???
+			 */
+			spt = page_address(sg_page(sg)) + sg->offset;
+			spt += j;
+
+			spt->app_tag = 0xffff;
+			if (cmd->se_cmd.prot_type == SCSI_PROT_DIF_TYPE3)
+				spt->ref_tag = 0xffffffff;
+#endif
+		}
+
+		return 0;
+	}
+
+	/* check guard */
+	if (e_guard != a_guard) {
+		cmd->se_cmd.pi_err = TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED;
+		cmd->se_cmd.bad_sector = cmd->se_cmd.t_task_lba;
+
+		ql_log(ql_log_warn, vha, 0xe076,
+		    "Guard ERR: cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x] cmd=%p\n",
+		    cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
+		    a_ref_tag, e_ref_tag, a_app_tag, e_app_tag,
+		    a_guard, e_guard, cmd);
+		goto out;
+	}
+
+	/* check ref tag */
+	if (e_ref_tag != a_ref_tag) {
+		cmd->se_cmd.pi_err = TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED;
+		cmd->se_cmd.bad_sector = e_ref_tag;
+
+		ql_log(ql_log_warn, vha, 0xe077,
+			"Ref Tag ERR: cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x] cmd=%p\n",
+			cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
+			a_ref_tag, e_ref_tag, a_app_tag, e_app_tag,
+			a_guard, e_guard, cmd);
+		goto out;
+	}
+
+	/* check appl tag */
+	if (e_app_tag != a_app_tag) {
+		cmd->se_cmd.pi_err = TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED;
+		cmd->se_cmd.bad_sector = cmd->se_cmd.t_task_lba;
+
+		ql_log(ql_log_warn, vha, 0xe078,
+			"App Tag ERR: cdb 0x%x lba 0x%llx: [Actual|Expected] Ref Tag[0x%x|0x%x], App Tag [0x%x|0x%x], Guard [0x%x|0x%x] cmd=%p\n",
+			cmd->atio.u.isp24.fcp_cmnd.cdb[0], lba,
+			a_ref_tag, e_ref_tag, a_app_tag, e_app_tag,
+			a_guard, e_guard, cmd);
+		goto out;
+	}
+out:
+	return 1;
+}
+
+
 /* If hardware_lock held on entry, might drop it, then reaquire */
 /* This function sends the appropriate CTIO to ISP 2xxx or 24xx */
 static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
@@ -2089,6 +2622,7 @@ static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
 	struct qla_hw_data *ha = vha->hw;
 	request_t *pkt;
 	int ret = 0;
+	uint16_t temp;
 
 	ql_dbg(ql_dbg_tgt, vha, 0xe01c, "Sending TERM EXCH CTIO (ha=%p)\n", ha);
 
@@ -2125,7 +2659,8 @@ static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
 	ctio24->u.status1.flags = (atio->u.isp24.attr << 9) |
 	    __constant_cpu_to_le16(CTIO7_FLAGS_STATUS_MODE_1 |
 		CTIO7_FLAGS_TERMINATE);
-	ctio24->u.status1.ox_id = swab16(atio->u.isp24.fcp_hdr.ox_id);
+	temp = be16_to_cpu(atio->u.isp24.fcp_hdr.ox_id);
+	ctio24->u.status1.ox_id = cpu_to_le16(temp);
 
 	/* Most likely, it isn't needed */
 	ctio24->u.status1.residual = get_unaligned((uint32_t *)
@@ -2155,21 +2690,46 @@ static void qlt_send_term_exchange(struct scsi_qla_host *vha,
 	rc = __qlt_send_term_exchange(vha, cmd, atio);
 	spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
 done:
-	if (rc == 1) {
+	/*
+	 * Terminate exchange will tell fw to release any active CTIO
+	 * that's in FW posession and cleanup the exchange.
+	 *
+	 * "cmd->state == QLA_TGT_STATE_ABORTED" means CTIO is still
+	 * down at FW.  Free the cmd later when CTIO comes back later
+	 * w/aborted(0x2) status.
+	 *
+	 * "cmd->state != QLA_TGT_STATE_ABORTED" means CTIO is already
+	 * back w/some err.  Free the cmd now.
+	 */
+	if ((rc == 1) && (cmd->state != QLA_TGT_STATE_ABORTED)) {
 		if (!ha_locked && !in_interrupt())
 			msleep(250); /* just in case */
 
+		if (cmd->sg_mapped)
+			qlt_unmap_sg(vha, cmd);
 		vha->hw->tgt.tgt_ops->free_cmd(cmd);
 	}
+	return;
 }
 
 void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 {
-	BUG_ON(cmd->sg_mapped);
+	struct qla_tgt_sess *sess = cmd->sess;
 
+	ql_dbg(ql_dbg_tgt, cmd->vha, 0xe074,
+	    "%s: se_cmd[%p] ox_id %04x\n",
+	    __func__, &cmd->se_cmd,
+	    be16_to_cpu(cmd->atio.u.isp24.fcp_hdr.ox_id));
+
+	BUG_ON(cmd->sg_mapped);
 	if (unlikely(cmd->free_sg))
 		kfree(cmd->sg);
-	kmem_cache_free(qla_tgt_cmd_cachep, cmd);
+
+	if (!sess || !sess->se_sess) {
+		WARN_ON(1);
+		return;
+	}
+	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
 }
 EXPORT_SYMBOL(qlt_free_cmd);
 
@@ -2374,6 +2934,7 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 		case CTIO_LIP_RESET:
 		case CTIO_TARGET_RESET:
 		case CTIO_ABORTED:
+			/* driver request abort via Terminate exchange */
 		case CTIO_TIMEOUT:
 		case CTIO_INVALID_RX_ID:
 			/* They are OK */
@@ -2404,18 +2965,58 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 			else
 				return;
 
+		case CTIO_DIF_ERROR: {
+			struct ctio_crc_from_fw *crc =
+				(struct ctio_crc_from_fw *)ctio;
+			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf073,
+			    "qla_target(%d): CTIO with DIF_ERROR status %x received (state %x, se_cmd %p) actual_dif[0x%llx] expect_dif[0x%llx]\n",
+			    vha->vp_idx, status, cmd->state, se_cmd,
+			    *((u64 *)&crc->actual_dif[0]),
+			    *((u64 *)&crc->expected_dif[0]));
+
+			if (qlt_handle_dif_error(vha, cmd, ctio)) {
+				if (cmd->state == QLA_TGT_STATE_NEED_DATA) {
+					/* scsi Write/xfer rdy complete */
+					goto skip_term;
+				} else {
+					/* scsi read/xmit respond complete
+					 * call handle dif to send scsi status
+					 * rather than terminate exchange.
+					 */
+					cmd->state = QLA_TGT_STATE_PROCESSED;
+					ha->tgt.tgt_ops->handle_dif_err(cmd);
+					return;
+				}
+			} else {
+				/* Need to generate a SCSI good completion.
+				 * because FW did not send scsi status.
+				 */
+				status = 0;
+				goto skip_term;
+			}
+			break;
+		}
 		default:
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05b,
-			    "qla_target(%d): CTIO with error status "
-			    "0x%x received (state %x, se_cmd %p\n",
+			    "qla_target(%d): CTIO with error status 0x%x received (state %x, se_cmd %p\n",
 			    vha->vp_idx, status, cmd->state, se_cmd);
 			break;
 		}
 
-		if (cmd->state != QLA_TGT_STATE_NEED_DATA)
+
+		/* "cmd->state == QLA_TGT_STATE_ABORTED" means
+		 * cmd is already aborted/terminated, we don't
+		 * need to terminate again.  The exchange is already
+		 * cleaned up/freed at FW level.  Just cleanup at driver
+		 * level.
+		 */
+		if ((cmd->state != QLA_TGT_STATE_NEED_DATA) &&
+			(cmd->state != QLA_TGT_STATE_ABORTED)) {
 			if (qlt_term_ctio_exchange(vha, ctio, cmd, status))
 				return;
+		}
 	}
+skip_term:
 
 	if (cmd->state == QLA_TGT_STATE_PROCESSED) {
 		ql_dbg(ql_dbg_tgt, vha, 0xe01f, "Command %p finished\n", cmd);
@@ -2444,7 +3045,8 @@ static void qlt_do_ctio_completion(struct scsi_qla_host *vha, uint32_t handle,
 		    "not return a CTIO complete\n", vha->vp_idx, cmd->state);
 	}
 
-	if (unlikely(status != CTIO_SUCCESS)) {
+	if (unlikely(status != CTIO_SUCCESS) &&
+		(cmd->state != QLA_TGT_STATE_ABORTED)) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01f, "Finishing failed CTIO\n");
 		dump_stack();
 	}
@@ -2489,13 +3091,12 @@ static struct qla_tgt_sess *qlt_make_local_sess(struct scsi_qla_host *,
 /*
  * Process context for I/O path into tcm_qla2xxx code
  */
-static void qlt_do_work(struct work_struct *work)
+static void __qlt_do_work(struct qla_tgt_cmd *cmd)
 {
-	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
 	scsi_qla_host_t *vha = cmd->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
-	struct qla_tgt_sess *sess = NULL;
+	struct qla_tgt_sess *sess = cmd->sess;
 	struct atio_from_isp *atio = &cmd->atio;
 	unsigned char *cdb;
 	unsigned long flags;
@@ -2505,41 +3106,6 @@ static void qlt_do_work(struct work_struct *work)
 	if (tgt->tgt_stop)
 		goto out_term;
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-	sess = ha->tgt.tgt_ops->find_sess_by_s_id(vha,
-	    atio->u.isp24.fcp_hdr.s_id);
-	/* Do kref_get() before dropping qla_hw_data->hardware_lock. */
-	if (sess)
-		kref_get(&sess->se_sess->sess_kref);
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-
-	if (unlikely(!sess)) {
-		uint8_t *s_id =	atio->u.isp24.fcp_hdr.s_id;
-
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf022,
-			"qla_target(%d): Unable to find wwn login"
-			" (s_id %x:%x:%x), trying to create it manually\n",
-			vha->vp_idx, s_id[0], s_id[1], s_id[2]);
-
-		if (atio->u.raw.entry_count > 1) {
-			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf023,
-				"Dropping multy entry cmd %p\n", cmd);
-			goto out_term;
-		}
-
-		mutex_lock(&vha->vha_tgt.tgt_mutex);
-		sess = qlt_make_local_sess(vha, s_id);
-		/* sess has an extra creation ref. */
-		mutex_unlock(&vha->vha_tgt.tgt_mutex);
-
-		if (!sess)
-			goto out_term;
-	}
-
-	cmd->sess = sess;
-	cmd->loop_id = sess->loop_id;
-	cmd->conf_compl_supported = sess->conf_compl_supported;
-
 	cdb = &atio->u.isp24.fcp_cmnd.cdb[0];
 	cmd->tag = atio->u.isp24.exchange_addr;
 	cmd->unpacked_lun = scsilun_to_int(
@@ -2563,11 +3129,12 @@ static void qlt_do_work(struct work_struct *work)
 	    atio->u.isp24.fcp_cmnd.add_cdb_len]));
 
 	ql_dbg(ql_dbg_tgt, vha, 0xe022,
-	    "qla_target: START qla command: %p lun: 0x%04x (tag %d)\n",
-	    cmd, cmd->unpacked_lun, cmd->tag);
+		"qla_target: START qla cmd: %p se_cmd %p lun: 0x%04x (tag %d) len(%d) ox_id %x\n",
+		cmd, &cmd->se_cmd, cmd->unpacked_lun, cmd->tag, data_length,
+		cmd->atio.u.isp24.fcp_hdr.ox_id);
 
-	ret = vha->hw->tgt.tgt_ops->handle_cmd(vha, cmd, cdb, data_length,
-	    fcp_task_attr, data_dir, bidi);
+	ret = ha->tgt.tgt_ops->handle_cmd(vha, cmd, cdb, data_length,
+				          fcp_task_attr, data_dir, bidi);
 	if (ret != 0)
 		goto out_term;
 	/*
@@ -2586,17 +3153,114 @@ out_term:
 	 */
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	qlt_send_term_exchange(vha, NULL, &cmd->atio, 1);
-	kmem_cache_free(qla_tgt_cmd_cachep, cmd);
-	if (sess)
+	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+	ha->tgt.tgt_ops->put_sess(sess);
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+}
+
+static void qlt_do_work(struct work_struct *work)
+{
+	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
+
+	__qlt_do_work(cmd);
+}
+
+static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha,
+				       struct qla_tgt_sess *sess,
+				       struct atio_from_isp *atio)
+{
+	struct se_session *se_sess = sess->se_sess;
+	struct qla_tgt_cmd *cmd;
+	int tag;
+
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	if (tag < 0)
+		return NULL;
+
+	cmd = &((struct qla_tgt_cmd *)se_sess->sess_cmd_map)[tag];
+	memset(cmd, 0, sizeof(struct qla_tgt_cmd));
+
+	memcpy(&cmd->atio, atio, sizeof(*atio));
+	cmd->state = QLA_TGT_STATE_NEW;
+	cmd->tgt = vha->vha_tgt.qla_tgt;
+	cmd->vha = vha;
+	cmd->se_cmd.map_tag = tag;
+	cmd->sess = sess;
+	cmd->loop_id = sess->loop_id;
+	cmd->conf_compl_supported = sess->conf_compl_supported;
+
+	return cmd;
+}
+
+static void qlt_send_busy(struct scsi_qla_host *, struct atio_from_isp *,
+			  uint16_t);
+
+static void qlt_create_sess_from_atio(struct work_struct *work)
+{
+	struct qla_tgt_sess_op *op = container_of(work,
+					struct qla_tgt_sess_op, work);
+	scsi_qla_host_t *vha = op->vha;
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_tgt_sess *sess;
+	struct qla_tgt_cmd *cmd;
+	unsigned long flags;
+	uint8_t *s_id = op->atio.u.isp24.fcp_hdr.s_id;
+
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf022,
+		"qla_target(%d): Unable to find wwn login"
+		" (s_id %x:%x:%x), trying to create it manually\n",
+		vha->vp_idx, s_id[0], s_id[1], s_id[2]);
+
+	if (op->atio.u.raw.entry_count > 1) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf023,
+		        "Dropping multy entry atio %p\n", &op->atio);
+		goto out_term;
+	}
+
+	mutex_lock(&vha->vha_tgt.tgt_mutex);
+	sess = qlt_make_local_sess(vha, s_id);
+	/* sess has an extra creation ref. */
+	mutex_unlock(&vha->vha_tgt.tgt_mutex);
+
+	if (!sess)
+		goto out_term;
+	/*
+	 * Now obtain a pre-allocated session tag using the original op->atio
+	 * packet header, and dispatch into __qlt_do_work() using the existing
+	 * process context.
+	 */
+	cmd = qlt_get_tag(vha, sess, &op->atio);
+	if (!cmd) {
+		spin_lock_irqsave(&ha->hardware_lock, flags);
+		qlt_send_busy(vha, &op->atio, SAM_STAT_BUSY);
 		ha->tgt.tgt_ops->put_sess(sess);
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		kfree(op);
+		return;
+	}
+	/*
+	 * __qlt_do_work() will call ha->tgt.tgt_ops->put_sess() to release
+	 * the extra reference taken above by qlt_make_local_sess()
+	 */
+	__qlt_do_work(cmd);
+	kfree(op);
+	return;
+
+out_term:
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+	qlt_send_term_exchange(vha, NULL, &op->atio, 1);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+	kfree(op);
+
 }
 
 /* ha->hardware_lock supposed to be held on entry */
 static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 	struct atio_from_isp *atio)
 {
+	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
+	struct qla_tgt_sess *sess;
 	struct qla_tgt_cmd *cmd;
 
 	if (unlikely(tgt->tgt_stop)) {
@@ -2605,18 +3269,31 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha,
 		return -EFAULT;
 	}
 
-	cmd = kmem_cache_zalloc(qla_tgt_cmd_cachep, GFP_ATOMIC);
+	sess = ha->tgt.tgt_ops->find_sess_by_s_id(vha, atio->u.isp24.fcp_hdr.s_id);
+	if (unlikely(!sess)) {
+		struct qla_tgt_sess_op *op = kzalloc(sizeof(struct qla_tgt_sess_op),
+						     GFP_ATOMIC);
+		if (!op)
+			return -ENOMEM;
+
+		memcpy(&op->atio, atio, sizeof(*atio));
+		INIT_WORK(&op->work, qlt_create_sess_from_atio);
+		queue_work(qla_tgt_wq, &op->work);
+		return 0;
+	}
+	/*
+	 * Do kref_get() before returning + dropping qla_hw_data->hardware_lock.
+	 */
+	kref_get(&sess->se_sess->sess_kref);
+
+	cmd = qlt_get_tag(vha, sess, atio);
 	if (!cmd) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05e,
 		    "qla_target(%d): Allocation of cmd failed\n", vha->vp_idx);
+		ha->tgt.tgt_ops->put_sess(sess);
 		return -ENOMEM;
 	}
 
-	memcpy(&cmd->atio, atio, sizeof(*atio));
-	cmd->state = QLA_TGT_STATE_NEW;
-	cmd->tgt = vha->vha_tgt.qla_tgt;
-	cmd->vha = vha;
-
 	INIT_WORK(&cmd->work, qlt_do_work);
 	queue_work(qla_tgt_wq, &cmd->work);
 	return 0;
@@ -3527,11 +4204,11 @@ static void qlt_24xx_atio_pkt(struct scsi_qla_host *vha,
 	switch (atio->u.raw.entry_type) {
 	case ATIO_TYPE7:
 		ql_dbg(ql_dbg_tgt, vha, 0xe02d,
-		    "ATIO_TYPE7 instance %d, lun %Lx, read/write %d/%d, "
-		    "add_cdb_len %d, data_length %04x, s_id %x:%x:%x\n",
+		    "ATIO_TYPE7 instance %d, lun %Lx, read/write %d/%d, cdb %x, add_cdb_len %x, data_length %04x, s_id %02x%02x%02x\n",
 		    vha->vp_idx, atio->u.isp24.fcp_cmnd.lun,
 		    atio->u.isp24.fcp_cmnd.rddata,
 		    atio->u.isp24.fcp_cmnd.wrdata,
+		    atio->u.isp24.fcp_cmnd.cdb[0],
 		    atio->u.isp24.fcp_cmnd.add_cdb_len,
 		    be32_to_cpu(get_unaligned((uint32_t *)
 			&atio->u.isp24.fcp_cmnd.add_cdb[
@@ -3629,11 +4306,13 @@ static void qlt_response_pkt(struct scsi_qla_host *vha, response_t *pkt)
 	tgt->irq_cmd_count++;
 
 	switch (pkt->entry_type) {
+	case CTIO_CRC2:
 	case CTIO_TYPE7:
 	{
 		struct ctio7_from_24xx *entry = (struct ctio7_from_24xx *)pkt;
-		ql_dbg(ql_dbg_tgt, vha, 0xe030, "CTIO_TYPE7: instance %d\n",
-		    vha->vp_idx);
+		ql_dbg(ql_dbg_tgt, vha, 0xe030,
+			"CTIO[0x%x] 12/CTIO7 7A/CRC2: instance %d\n",
+			entry->entry_type, vha->vp_idx);
 		qlt_do_ctio_completion(vha, entry->handle,
 		    le16_to_cpu(entry->status)|(pkt->entry_status << 16),
 		    entry);
@@ -4768,6 +5447,7 @@ qlt_24xx_process_response_error(struct scsi_qla_host *vha,
 	case ABTS_RESP_24XX:
 	case CTIO_TYPE7:
 	case NOTIFY_ACK_TYPE:
+	case CTIO_CRC2:
 		return 1;
 	default:
 		return 0;
@@ -4911,23 +5591,13 @@ int __init qlt_init(void)
 	if (!QLA_TGT_MODE_ENABLED())
 		return 0;
 
-	qla_tgt_cmd_cachep = kmem_cache_create("qla_tgt_cmd_cachep",
-	    sizeof(struct qla_tgt_cmd), __alignof__(struct qla_tgt_cmd), 0,
-	    NULL);
-	if (!qla_tgt_cmd_cachep) {
-		ql_log(ql_log_fatal, NULL, 0xe06c,
-		    "kmem_cache_create for qla_tgt_cmd_cachep failed\n");
-		return -ENOMEM;
-	}
-
 	qla_tgt_mgmt_cmd_cachep = kmem_cache_create("qla_tgt_mgmt_cmd_cachep",
 	    sizeof(struct qla_tgt_mgmt_cmd), __alignof__(struct
 	    qla_tgt_mgmt_cmd), 0, NULL);
 	if (!qla_tgt_mgmt_cmd_cachep) {
 		ql_log(ql_log_fatal, NULL, 0xe06d,
 		    "kmem_cache_create for qla_tgt_mgmt_cmd_cachep failed\n");
-		ret = -ENOMEM;
-		goto out;
+		return -ENOMEM;
 	}
 
 	qla_tgt_mgmt_cmd_mempool = mempool_create(25, mempool_alloc_slab,
@@ -4955,8 +5625,6 @@ out_cmd_mempool:
 	mempool_destroy(qla_tgt_mgmt_cmd_mempool);
 out_mgmt_cmd_cachep:
 	kmem_cache_destroy(qla_tgt_mgmt_cmd_cachep);
-out:
-	kmem_cache_destroy(qla_tgt_cmd_cachep);
 	return ret;
 }
 
@@ -4968,5 +5636,4 @@ void qlt_exit(void)
 	destroy_workqueue(qla_tgt_wq);
 	mempool_destroy(qla_tgt_mgmt_cmd_mempool);
 	kmem_cache_destroy(qla_tgt_mgmt_cmd_cachep);
-	kmem_cache_destroy(qla_tgt_cmd_cachep);
 }
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index ce33d8c2640..d1d24fb0160 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -293,6 +293,7 @@ struct ctio_to_2xxx {
 #define CTIO_ABORTED			0x02
 #define CTIO_INVALID_RX_ID		0x08
 #define CTIO_TIMEOUT			0x0B
+#define CTIO_DIF_ERROR			0x0C     /* DIF error detected  */
 #define CTIO_LIP_RESET			0x0E
 #define CTIO_TARGET_RESET		0x17
 #define CTIO_PORT_UNAVAILABLE		0x28
@@ -315,7 +316,7 @@ struct fcp_hdr {
 	uint8_t  seq_id;
 	uint8_t  df_ctl;
 	uint16_t seq_cnt;
-	uint16_t ox_id;
+	__be16   ox_id;
 	uint16_t rx_id;
 	uint32_t parameter;
 } __packed;
@@ -440,9 +441,9 @@ struct ctio7_to_24xx {
 	union {
 		struct {
 			uint16_t reserved1;
-			uint16_t flags;
+			__le16 flags;
 			uint32_t residual;
-			uint16_t ox_id;
+			__le16 ox_id;
 			uint16_t scsi_status;
 			uint32_t relative_offset;
 			uint32_t reserved2;
@@ -457,7 +458,7 @@ struct ctio7_to_24xx {
 			uint16_t sense_length;
 			uint16_t flags;
 			uint32_t residual;
-			uint16_t ox_id;
+			__le16 ox_id;
 			uint16_t scsi_status;
 			uint16_t response_len;
 			uint16_t reserved;
@@ -498,11 +499,12 @@ struct ctio7_from_24xx {
 #define CTIO7_FLAGS_DONT_RET_CTIO	BIT_8
 #define CTIO7_FLAGS_STATUS_MODE_0	0
 #define CTIO7_FLAGS_STATUS_MODE_1	BIT_6
+#define CTIO7_FLAGS_STATUS_MODE_2	BIT_7
 #define CTIO7_FLAGS_EXPLICIT_CONFORM	BIT_5
 #define CTIO7_FLAGS_CONFIRM_SATISF	BIT_4
 #define CTIO7_FLAGS_DSD_PTR		BIT_2
-#define CTIO7_FLAGS_DATA_IN		BIT_1
-#define CTIO7_FLAGS_DATA_OUT		BIT_0
+#define CTIO7_FLAGS_DATA_IN		BIT_1 /* data to initiator */
+#define CTIO7_FLAGS_DATA_OUT		BIT_0 /* data from initiator */
 
 #define ELS_PLOGI			0x3
 #define ELS_FLOGI			0x4
@@ -514,6 +516,68 @@ struct ctio7_from_24xx {
 #define ELS_ADISC			0x52
 
 /*
+ *CTIO Type CRC_2 IOCB
+ */
+struct ctio_crc2_to_fw {
+	uint8_t entry_type;		/* Entry type. */
+#define CTIO_CRC2 0x7A
+	uint8_t entry_count;		/* Entry count. */
+	uint8_t sys_define;		/* System defined. */
+	uint8_t entry_status;		/* Entry Status. */
+
+	uint32_t handle;		/* System handle. */
+	uint16_t nport_handle;		/* N_PORT handle. */
+	__le16 timeout;		/* Command timeout. */
+
+	uint16_t dseg_count;		/* Data segment count. */
+	uint8_t  vp_index;
+	uint8_t  add_flags;		/* additional flags */
+#define CTIO_CRC2_AF_DIF_DSD_ENA BIT_3
+
+	uint8_t  initiator_id[3];	/* initiator ID */
+	uint8_t  reserved1;
+	uint32_t exchange_addr;		/* rcv exchange address */
+	uint16_t reserved2;
+	__le16 flags;			/* refer to CTIO7 flags values */
+	uint32_t residual;
+	__le16 ox_id;
+	uint16_t scsi_status;
+	__le32 relative_offset;
+	uint32_t reserved5;
+	__le32 transfer_length;		/* total fc transfer length */
+	uint32_t reserved6;
+	__le32 crc_context_address[2];/* Data segment address. */
+	uint16_t crc_context_len;	/* Data segment length. */
+	uint16_t reserved_1;		/* MUST be set to 0. */
+} __packed;
+
+/* CTIO Type CRC_x Status IOCB */
+struct ctio_crc_from_fw {
+	uint8_t entry_type;		/* Entry type. */
+	uint8_t entry_count;		/* Entry count. */
+	uint8_t sys_define;		/* System defined. */
+	uint8_t entry_status;		/* Entry Status. */
+
+	uint32_t handle;		/* System handle. */
+	uint16_t status;
+	uint16_t timeout;		/* Command timeout. */
+	uint16_t dseg_count;		/* Data segment count. */
+	uint32_t reserved1;
+	uint16_t state_flags;
+#define CTIO_CRC_SF_DIF_CHOPPED BIT_4
+
+	uint32_t exchange_address;	/* rcv exchange address */
+	uint16_t reserved2;
+	uint16_t flags;
+	uint32_t resid_xfer_length;
+	uint16_t ox_id;
+	uint8_t  reserved3[12];
+	uint16_t runt_guard;		/* reported runt blk guard */
+	uint8_t  actual_dif[8];
+	uint8_t  expected_dif[8];
+} __packed;
+
+/*
  * ISP queue - ABTS received/response entries structure definition for 24xx.
  */
 #define ABTS_RECV_24XX		0x54 /* ABTS received (for 24xx) */
@@ -641,6 +705,7 @@ struct qla_tgt_func_tmpl {
 	int (*handle_cmd)(struct scsi_qla_host *, struct qla_tgt_cmd *,
 			unsigned char *, uint32_t, int, int, int);
 	void (*handle_data)(struct qla_tgt_cmd *);
+	void (*handle_dif_err)(struct qla_tgt_cmd *);
 	int (*handle_tmr)(struct qla_tgt_mgmt_cmd *, uint32_t, uint8_t,
 			uint32_t);
 	void (*free_cmd)(struct qla_tgt_cmd *);
@@ -805,6 +870,12 @@ struct qla_tgt {
 	struct list_head tgt_list_entry;
 };
 
+struct qla_tgt_sess_op {
+	struct scsi_qla_host *vha;
+	struct atio_from_isp atio;
+	struct work_struct work;
+};
+
 /*
  * Equivilant to IT Nexus (Initiator-Target)
  */
@@ -829,9 +900,9 @@ struct qla_tgt_sess {
 };
 
 struct qla_tgt_cmd {
+	struct se_cmd se_cmd;
 	struct qla_tgt_sess *sess;
 	int state;
-	struct se_cmd se_cmd;
 	struct work_struct free_work;
 	struct work_struct work;
 	/* Sense buffer that will be mapped into outgoing status */
@@ -843,6 +914,7 @@ struct qla_tgt_cmd {
 	unsigned int free_sg:1;
 	unsigned int aborted:1; /* Needed in case of SRR */
 	unsigned int write_data_transferred:1;
+	unsigned int ctx_dsd_alloced:1;
 
 	struct scatterlist *sg;	/* cmd data buffer SG vector */
 	int sg_cnt;		/* SG segments count */
@@ -857,6 +929,12 @@ struct qla_tgt_cmd {
 	struct scsi_qla_host *vha;
 
 	struct atio_from_isp atio;
+	/* t10dif */
+	struct scatterlist *prot_sg;
+	uint32_t prot_sg_cnt;
+	uint32_t blk_sz;
+	struct crc_context *ctx;
+
 };
 
 struct qla_tgt_sess_work_param {
@@ -901,6 +979,10 @@ struct qla_tgt_prm {
 	int sense_buffer_len;
 	int residual;
 	int add_status_pkt;
+	/* dif */
+	struct scatterlist *prot_sg;
+	uint16_t prot_seg_cnt;
+	uint16_t tot_dsds;
 };
 
 struct qla_tgt_srr_imm {
@@ -976,6 +1058,8 @@ extern void qlt_24xx_atio_pkt_all_vps(struct scsi_qla_host *,
 extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *);
 extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *);
 extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t);
+extern int qlt_rdy_to_xfer_dif(struct qla_tgt_cmd *);
+extern int qlt_xmit_response_dif(struct qla_tgt_cmd *, int, uint8_t);
 extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_cmd(struct qla_tgt_cmd *cmd);
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index a804e9b744b..cb9a0c4bc41 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -201,7 +201,6 @@ qla27xx_read_reg(__iomem struct device_reg_24xx *reg,
 		ql_dbg(ql_dbg_misc, NULL, 0xd014,
 		    "%s: @%x\n", __func__, offset);
 	}
-	qla27xx_insert32(offset, buf, len);
 	qla27xx_read32(window, buf, len);
 }
 
@@ -220,7 +219,7 @@ qla27xx_write_reg(__iomem struct device_reg_24xx *reg,
 
 static inline void
 qla27xx_read_window(__iomem struct device_reg_24xx *reg,
-	uint32_t base, uint offset, uint count, uint width, void *buf,
+	uint32_t addr, uint offset, uint count, uint width, void *buf,
 	ulong *len)
 {
 	void *window = (void *)reg + offset;
@@ -229,14 +228,14 @@ qla27xx_read_window(__iomem struct device_reg_24xx *reg,
 	if (buf) {
 		ql_dbg(ql_dbg_misc, NULL, 0xd016,
 		    "%s: base=%x offset=%x count=%x width=%x\n",
-		    __func__, base, offset, count, width);
+		    __func__, addr, offset, count, width);
 	}
-	qla27xx_write_reg(reg, IOBASE_ADDR, base, buf);
+	qla27xx_write_reg(reg, IOBASE_ADDR, addr, buf);
 	while (count--) {
-		qla27xx_insert32(base, buf, len);
+		qla27xx_insert32(addr, buf, len);
 		readn(window, buf, len);
 		window += width;
-		base += width;
+		addr++;
 	}
 }
 
@@ -336,7 +335,8 @@ qla27xx_fwdt_entry_t260(struct scsi_qla_host *vha,
 
 	ql_dbg(ql_dbg_misc, vha, 0xd204,
 	    "%s: rdpci [%lx]\n", __func__, *len);
-	qla27xx_read_reg(reg, ent->t260.pci_addr, buf, len);
+	qla27xx_insert32(ent->t260.pci_offset, buf, len);
+	qla27xx_read_reg(reg, ent->t260.pci_offset, buf, len);
 
 	return false;
 }
@@ -349,7 +349,7 @@ qla27xx_fwdt_entry_t261(struct scsi_qla_host *vha,
 
 	ql_dbg(ql_dbg_misc, vha, 0xd205,
 	    "%s: wrpci [%lx]\n", __func__, *len);
-	qla27xx_write_reg(reg, ent->t261.pci_addr, ent->t261.write_data, buf);
+	qla27xx_write_reg(reg, ent->t261.pci_offset, ent->t261.write_data, buf);
 
 	return false;
 }
@@ -392,9 +392,9 @@ qla27xx_fwdt_entry_t262(struct scsi_qla_host *vha,
 		goto done;
 	}
 
-	if (end < start) {
+	if (end < start || end == 0) {
 		ql_dbg(ql_dbg_misc, vha, 0xd023,
-		    "%s: bad range (start=%x end=%x)\n", __func__,
+		    "%s: unusable range (start=%x end=%x)\n", __func__,
 		    ent->t262.end_addr, ent->t262.start_addr);
 		qla27xx_skip_entry(ent, buf);
 		goto done;
@@ -452,17 +452,15 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha,
 		ql_dbg(ql_dbg_misc, vha, 0xd025,
 		    "%s: unsupported atio queue\n", __func__);
 		qla27xx_skip_entry(ent, buf);
-		goto done;
 	} else {
 		ql_dbg(ql_dbg_misc, vha, 0xd026,
 		    "%s: unknown queue %u\n", __func__, ent->t263.queue_type);
 		qla27xx_skip_entry(ent, buf);
-		goto done;
 	}
 
 	if (buf)
 		ent->t263.num_queues = count;
-done:
+
 	return false;
 }
 
@@ -503,7 +501,7 @@ qla27xx_fwdt_entry_t265(struct scsi_qla_host *vha,
 	ql_dbg(ql_dbg_misc, vha, 0xd209,
 	    "%s: pause risc [%lx]\n", __func__, *len);
 	if (buf)
-		qla24xx_pause_risc(reg);
+		qla24xx_pause_risc(reg, vha->hw);
 
 	return false;
 }
@@ -590,7 +588,6 @@ qla27xx_fwdt_entry_t270(struct scsi_qla_host *vha,
 	struct qla27xx_fwdt_entry *ent, void *buf, ulong *len)
 {
 	struct device_reg_24xx __iomem *reg = qla27xx_isp_reg(vha);
-	void *window = (void *)reg + 0xc4;
 	ulong dwords = ent->t270.count;
 	ulong addr = ent->t270.addr;
 
@@ -599,10 +596,9 @@ qla27xx_fwdt_entry_t270(struct scsi_qla_host *vha,
 	qla27xx_write_reg(reg, IOBASE_ADDR, 0x40, buf);
 	while (dwords--) {
 		qla27xx_write_reg(reg, 0xc0, addr|0x80000000, buf);
-		qla27xx_read_reg(reg, 0xc4, buf, len);
 		qla27xx_insert32(addr, buf, len);
-		qla27xx_read32(window, buf, len);
-		addr++;
+		qla27xx_read_reg(reg, 0xc4, buf, len);
+		addr += sizeof(uint32_t);
 	}
 
 	return false;
@@ -614,12 +610,12 @@ qla27xx_fwdt_entry_t271(struct scsi_qla_host *vha,
 {
 	struct device_reg_24xx __iomem *reg = qla27xx_isp_reg(vha);
 	ulong addr = ent->t271.addr;
+	ulong data = ent->t271.data;
 
 	ql_dbg(ql_dbg_misc, vha, 0xd20f,
 	    "%s: wrremreg [%lx]\n", __func__, *len);
 	qla27xx_write_reg(reg, IOBASE_ADDR, 0x40, buf);
-	qla27xx_read_reg(reg, 0xc4, buf, len);
-	qla27xx_insert32(addr, buf, len);
+	qla27xx_write_reg(reg, 0xc4, data, buf);
 	qla27xx_write_reg(reg, 0xc0, addr, buf);
 
 	return false;
@@ -662,9 +658,59 @@ qla27xx_fwdt_entry_t273(struct scsi_qla_host *vha,
 			    "%s: failed pcicfg read at %lx\n", __func__, addr);
 		qla27xx_insert32(addr, buf, len);
 		qla27xx_insert32(value, buf, len);
-		addr += 4;
+		addr += sizeof(uint32_t);
+	}
+
+	return false;
+}
+
+static int
+qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha,
+	struct qla27xx_fwdt_entry *ent, void *buf, ulong *len)
+{
+	uint count = 0;
+	uint i;
+
+	ql_dbg(ql_dbg_misc, vha, 0xd212,
+	    "%s: getqsh(%x) [%lx]\n", __func__, ent->t274.queue_type, *len);
+	if (ent->t274.queue_type == T274_QUEUE_TYPE_REQ_SHAD) {
+		for (i = 0; i < vha->hw->max_req_queues; i++) {
+			struct req_que *req = vha->hw->req_q_map[i];
+			if (req || !buf) {
+				qla27xx_insert16(i, buf, len);
+				qla27xx_insert16(1, buf, len);
+				qla27xx_insert32(req && req->out_ptr ?
+				    *req->out_ptr : 0, buf, len);
+				count++;
+			}
+		}
+	} else if (ent->t274.queue_type == T274_QUEUE_TYPE_RSP_SHAD) {
+		for (i = 0; i < vha->hw->max_rsp_queues; i++) {
+			struct rsp_que *rsp = vha->hw->rsp_q_map[i];
+			if (rsp || !buf) {
+				qla27xx_insert16(i, buf, len);
+				qla27xx_insert16(1, buf, len);
+				qla27xx_insert32(rsp && rsp->in_ptr ?
+				    *rsp->in_ptr : 0, buf, len);
+				count++;
+			}
+		}
+	} else if (ent->t274.queue_type == T274_QUEUE_TYPE_ATIO_SHAD) {
+		ql_dbg(ql_dbg_misc, vha, 0xd02e,
+		    "%s: unsupported atio queue\n", __func__);
+		qla27xx_skip_entry(ent, buf);
+	} else {
+		ql_dbg(ql_dbg_misc, vha, 0xd02f,
+		    "%s: unknown queue %u\n", __func__, ent->t274.queue_type);
+		qla27xx_skip_entry(ent, buf);
 	}
 
+	if (buf)
+		ent->t274.num_queues = count;
+
+	if (!count)
+		qla27xx_skip_entry(ent, buf);
+
 	return false;
 }
 
@@ -709,6 +755,7 @@ static struct qla27xx_fwdt_entry_call ql27xx_fwdt_entry_call_list[] = {
 	{ ENTRY_TYPE_WRREMREG		, qla27xx_fwdt_entry_t271  } ,
 	{ ENTRY_TYPE_RDREMRAM		, qla27xx_fwdt_entry_t272  } ,
 	{ ENTRY_TYPE_PCICFG		, qla27xx_fwdt_entry_t273  } ,
+	{ ENTRY_TYPE_GET_SHADOW		, qla27xx_fwdt_entry_t274  } ,
 	{ -1				, qla27xx_fwdt_entry_other }
 };
 
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.h b/drivers/scsi/qla2xxx/qla_tmpl.h
index c9d2fff4d96..1967424c8e6 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.h
+++ b/drivers/scsi/qla2xxx/qla_tmpl.h
@@ -1,6 +1,6 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
@@ -52,6 +52,7 @@ struct __packed qla27xx_fwdt_template {
 #define ENTRY_TYPE_WRREMREG		271
 #define ENTRY_TYPE_RDREMRAM		272
 #define ENTRY_TYPE_PCICFG		273
+#define ENTRY_TYPE_GET_SHADOW		274
 
 #define CAPTURE_FLAG_PHYS_ONLY		BIT_0
 #define CAPTURE_FLAG_PHYS_VIRT		BIT_1
@@ -109,12 +110,12 @@ struct __packed qla27xx_fwdt_entry {
 		} t259;
 
 		struct __packed {
-			uint8_t pci_addr;
+			uint8_t pci_offset;
 			uint8_t reserved[3];
 		} t260;
 
 		struct __packed {
-			uint8_t pci_addr;
+			uint8_t pci_offset;
 			uint8_t reserved[3];
 			uint32_t write_data;
 		} t261;
@@ -186,6 +187,12 @@ struct __packed qla27xx_fwdt_entry {
 			uint32_t addr;
 			uint32_t count;
 		} t273;
+
+		struct __packed {
+			uint32_t num_queues;
+			uint8_t  queue_type;
+			uint8_t  reserved[3];
+		} t274;
 	};
 };
 
@@ -202,4 +209,8 @@ struct __packed qla27xx_fwdt_entry {
 #define T268_BUF_TYPE_EXCH_BUFOFF	2
 #define T268_BUF_TYPE_EXTD_LOGIN	3
 
+#define T274_QUEUE_TYPE_REQ_SHAD	1
+#define T274_QUEUE_TYPE_RSP_SHAD	2
+#define T274_QUEUE_TYPE_ATIO_SHAD	3
+
 #endif
diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index e36b9471254..4d2c98cbec4 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -1,13 +1,13 @@
 /*
  * QLogic Fibre Channel HBA Driver
- * Copyright (c)  2003-2013 QLogic Corporation
+ * Copyright (c)  2003-2014 QLogic Corporation
  *
  * See LICENSE.qla2xxx for copyright and licensing details.
  */
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "8.07.00.02-k"
+#define QLA2XXX_VERSION      "8.07.00.08-k"
 
 #define QLA_DRIVER_MAJOR_VER	8
 #define QLA_DRIVER_MINOR_VER	7
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 68fb66fdb75..e2beab96209 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -472,6 +472,11 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
 	cmd->sg_cnt = se_cmd->t_data_nents;
 	cmd->sg = se_cmd->t_data_sg;
 
+	cmd->prot_sg_cnt = se_cmd->t_prot_nents;
+	cmd->prot_sg = se_cmd->t_prot_sg;
+	cmd->blk_sz  = se_cmd->se_dev->dev_attrib.block_size;
+	se_cmd->pi_err = 0;
+
 	/*
 	 * qla_target.c:qlt_rdy_to_xfer() will call pci_map_sg() to setup
 	 * the SGL mappings into PCIe memory for incoming FCP WRITE data.
@@ -567,8 +572,13 @@ static void tcm_qla2xxx_handle_data_work(struct work_struct *work)
 			return;
 		}
 
-		transport_generic_request_failure(&cmd->se_cmd,
-						  TCM_CHECK_CONDITION_ABORT_CMD);
+		if (cmd->se_cmd.pi_err)
+			transport_generic_request_failure(&cmd->se_cmd,
+				cmd->se_cmd.pi_err);
+		else
+			transport_generic_request_failure(&cmd->se_cmd,
+				TCM_CHECK_CONDITION_ABORT_CMD);
+
 		return;
 	}
 
@@ -584,6 +594,27 @@ static void tcm_qla2xxx_handle_data(struct qla_tgt_cmd *cmd)
 	queue_work(tcm_qla2xxx_free_wq, &cmd->work);
 }
 
+static void tcm_qla2xxx_handle_dif_work(struct work_struct *work)
+{
+	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
+
+	/* take an extra kref to prevent cmd free too early.
+	 * need to wait for SCSI status/check condition to
+	 * finish responding generate by transport_generic_request_failure.
+	 */
+	kref_get(&cmd->se_cmd.cmd_kref);
+	transport_generic_request_failure(&cmd->se_cmd, cmd->se_cmd.pi_err);
+}
+
+/*
+ * Called from qla_target.c:qlt_do_ctio_completion()
+ */
+static void tcm_qla2xxx_handle_dif_err(struct qla_tgt_cmd *cmd)
+{
+	INIT_WORK(&cmd->work, tcm_qla2xxx_handle_dif_work);
+	queue_work(tcm_qla2xxx_free_wq, &cmd->work);
+}
+
 /*
  * Called from qla_target.c:qlt_issue_task_mgmt()
  */
@@ -610,6 +641,11 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 	cmd->sg = se_cmd->t_data_sg;
 	cmd->offset = 0;
 
+	cmd->prot_sg_cnt = se_cmd->t_prot_nents;
+	cmd->prot_sg = se_cmd->t_prot_sg;
+	cmd->blk_sz  = se_cmd->se_dev->dev_attrib.block_size;
+	se_cmd->pi_err = 0;
+
 	/*
 	 * Now queue completed DATA_IN the qla2xxx LLD and response ring
 	 */
@@ -1465,6 +1501,8 @@ static int tcm_qla2xxx_check_initiator_node_acl(
 	struct qla_tgt_sess *sess = qla_tgt_sess;
 	unsigned char port_name[36];
 	unsigned long flags;
+	int num_tags = (ha->fw_xcb_count) ? ha->fw_xcb_count :
+		       TCM_QLA2XXX_DEFAULT_TAGS;
 
 	lport = vha->vha_tgt.target_lport_ptr;
 	if (!lport) {
@@ -1482,7 +1520,9 @@ static int tcm_qla2xxx_check_initiator_node_acl(
 	}
 	se_tpg = &tpg->se_tpg;
 
-	se_sess = transport_init_session(TARGET_PROT_NORMAL);
+	se_sess = transport_init_session_tags(num_tags,
+					      sizeof(struct qla_tgt_cmd),
+					      TARGET_PROT_NORMAL);
 	if (IS_ERR(se_sess)) {
 		pr_err("Unable to initialize struct se_session\n");
 		return PTR_ERR(se_sess);
@@ -1600,6 +1640,7 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id,
 static struct qla_tgt_func_tmpl tcm_qla2xxx_template = {
 	.handle_cmd		= tcm_qla2xxx_handle_cmd,
 	.handle_data		= tcm_qla2xxx_handle_data,
+	.handle_dif_err		= tcm_qla2xxx_handle_dif_err,
 	.handle_tmr		= tcm_qla2xxx_handle_tmr,
 	.free_cmd		= tcm_qla2xxx_free_cmd,
 	.free_mcmd		= tcm_qla2xxx_free_mcmd,
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
index 33aaac8c7d5..10c00214564 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h
@@ -4,6 +4,11 @@
 #define TCM_QLA2XXX_VERSION	"v0.1"
 /* length of ASCII WWPNs including pad */
 #define TCM_QLA2XXX_NAMELEN	32
+/*
+ * Number of pre-allocated per-session tags, based upon the worst-case
+ * per port number of iocbs
+ */
+#define TCM_QLA2XXX_DEFAULT_TAGS 2088
 
 #include "qla_target.h"
 
diff --git a/drivers/scsi/qla4xxx/ql4_83xx.c b/drivers/scsi/qla4xxx/ql4_83xx.c
index 2eba3536592..556c1525f88 100644
--- a/drivers/scsi/qla4xxx/ql4_83xx.c
+++ b/drivers/scsi/qla4xxx/ql4_83xx.c
@@ -249,110 +249,6 @@ void qla4_83xx_rom_lock_recovery(struct scsi_qla_host *ha)
 	qla4_83xx_flash_unlock(ha);
 }
 
-/**
- * qla4_83xx_ms_mem_write_128b - Writes data to MS/off-chip memory
- * @ha: Pointer to adapter structure
- * @addr: Flash address to write to
- * @data: Data to be written
- * @count: word_count to be written
- *
- * Return: On success return QLA_SUCCESS
- *	   On error return QLA_ERROR
- **/
-int qla4_83xx_ms_mem_write_128b(struct scsi_qla_host *ha, uint64_t addr,
-				uint32_t *data, uint32_t count)
-{
-	int i, j;
-	uint32_t agt_ctrl;
-	unsigned long flags;
-	int ret_val = QLA_SUCCESS;
-
-	/* Only 128-bit aligned access */
-	if (addr & 0xF) {
-		ret_val = QLA_ERROR;
-		goto exit_ms_mem_write;
-	}
-
-	write_lock_irqsave(&ha->hw_lock, flags);
-
-	/* Write address */
-	ret_val = qla4_83xx_wr_reg_indirect(ha, MD_MIU_TEST_AGT_ADDR_HI, 0);
-	if (ret_val == QLA_ERROR) {
-		ql4_printk(KERN_ERR, ha, "%s: write to AGT_ADDR_HI failed\n",
-			   __func__);
-		goto exit_ms_mem_write_unlock;
-	}
-
-	for (i = 0; i < count; i++, addr += 16) {
-		if (!((QLA8XXX_ADDR_IN_RANGE(addr, QLA8XXX_ADDR_QDR_NET,
-					     QLA8XXX_ADDR_QDR_NET_MAX)) ||
-		      (QLA8XXX_ADDR_IN_RANGE(addr, QLA8XXX_ADDR_DDR_NET,
-					     QLA8XXX_ADDR_DDR_NET_MAX)))) {
-			ret_val = QLA_ERROR;
-			goto exit_ms_mem_write_unlock;
-		}
-
-		ret_val = qla4_83xx_wr_reg_indirect(ha, MD_MIU_TEST_AGT_ADDR_LO,
-						    addr);
-		/* Write data */
-		ret_val |= qla4_83xx_wr_reg_indirect(ha,
-						     MD_MIU_TEST_AGT_WRDATA_LO,
-						     *data++);
-		ret_val |= qla4_83xx_wr_reg_indirect(ha,
-						     MD_MIU_TEST_AGT_WRDATA_HI,
-						     *data++);
-		ret_val |= qla4_83xx_wr_reg_indirect(ha,
-						     MD_MIU_TEST_AGT_WRDATA_ULO,
-						     *data++);
-		ret_val |= qla4_83xx_wr_reg_indirect(ha,
-						     MD_MIU_TEST_AGT_WRDATA_UHI,
-						     *data++);
-		if (ret_val == QLA_ERROR) {
-			ql4_printk(KERN_ERR, ha, "%s: write to AGT_WRDATA failed\n",
-				   __func__);
-			goto exit_ms_mem_write_unlock;
-		}
-
-		/* Check write status */
-		ret_val = qla4_83xx_wr_reg_indirect(ha, MD_MIU_TEST_AGT_CTRL,
-						    MIU_TA_CTL_WRITE_ENABLE);
-		ret_val |= qla4_83xx_wr_reg_indirect(ha, MD_MIU_TEST_AGT_CTRL,
-						     MIU_TA_CTL_WRITE_START);
-		if (ret_val == QLA_ERROR) {
-			ql4_printk(KERN_ERR, ha, "%s: write to AGT_CTRL failed\n",
-				   __func__);
-			goto exit_ms_mem_write_unlock;
-		}
-
-		for (j = 0; j < MAX_CTL_CHECK; j++) {
-			ret_val = qla4_83xx_rd_reg_indirect(ha,
-							MD_MIU_TEST_AGT_CTRL,
-							&agt_ctrl);
-			if (ret_val == QLA_ERROR) {
-				ql4_printk(KERN_ERR, ha, "%s: failed to read MD_MIU_TEST_AGT_CTRL\n",
-					   __func__);
-				goto exit_ms_mem_write_unlock;
-			}
-			if ((agt_ctrl & MIU_TA_CTL_BUSY) == 0)
-				break;
-		}
-
-		/* Status check failed */
-		if (j >= MAX_CTL_CHECK) {
-			printk_ratelimited(KERN_ERR "%s: MS memory write failed!\n",
-					   __func__);
-			ret_val = QLA_ERROR;
-			goto exit_ms_mem_write_unlock;
-		}
-	}
-
-exit_ms_mem_write_unlock:
-	write_unlock_irqrestore(&ha->hw_lock, flags);
-
-exit_ms_mem_write:
-	return ret_val;
-}
-
 #define INTENT_TO_RECOVER	0x01
 #define PROCEED_TO_RECOVER	0x02
 
@@ -760,7 +656,7 @@ static int qla4_83xx_copy_bootloader(struct scsi_qla_host *ha)
 			  __func__));
 
 	/* 128 bit/16 byte write to MS memory */
-	ret_val = qla4_83xx_ms_mem_write_128b(ha, dest, (uint32_t *)p_cache,
+	ret_val = qla4_8xxx_ms_mem_write_128b(ha, dest, (uint32_t *)p_cache,
 					      count);
 	if (ret_val == QLA_ERROR) {
 		ql4_printk(KERN_ERR, ha, "%s: Error writing firmware to MS\n",
diff --git a/drivers/scsi/qla4xxx/ql4_83xx.h b/drivers/scsi/qla4xxx/ql4_83xx.h
index a0de6e25ea5..775fdf9fcc8 100644
--- a/drivers/scsi/qla4xxx/ql4_83xx.h
+++ b/drivers/scsi/qla4xxx/ql4_83xx.h
@@ -254,6 +254,50 @@ struct qla83xx_minidump_entry_pollrd {
 	uint32_t rsvd_1;
 };
 
+struct qla8044_minidump_entry_rddfe {
+	struct qla8xxx_minidump_entry_hdr h;
+	uint32_t addr_1;
+	uint32_t value;
+	uint8_t stride;
+	uint8_t stride2;
+	uint16_t count;
+	uint32_t poll;
+	uint32_t mask;
+	uint32_t modify_mask;
+	uint32_t data_size;
+	uint32_t rsvd;
+
+} __packed;
+
+struct qla8044_minidump_entry_rdmdio {
+	struct qla8xxx_minidump_entry_hdr h;
+
+	uint32_t addr_1;
+	uint32_t addr_2;
+	uint32_t value_1;
+	uint8_t stride_1;
+	uint8_t stride_2;
+	uint16_t count;
+	uint32_t poll;
+	uint32_t mask;
+	uint32_t value_2;
+	uint32_t data_size;
+
+} __packed;
+
+struct qla8044_minidump_entry_pollwr {
+	struct qla8xxx_minidump_entry_hdr h;
+	uint32_t addr_1;
+	uint32_t addr_2;
+	uint32_t value_1;
+	uint32_t value_2;
+	uint32_t poll;
+	uint32_t mask;
+	uint32_t data_size;
+	uint32_t rsvd;
+
+} __packed;
+
 /* RDMUX2 Entry */
 struct qla83xx_minidump_entry_rdmux2 {
 	struct qla8xxx_minidump_entry_hdr h;
diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h
index 73a502288bd..8f6d0fb2cd8 100644
--- a/drivers/scsi/qla4xxx/ql4_def.h
+++ b/drivers/scsi/qla4xxx/ql4_def.h
@@ -601,6 +601,7 @@ struct scsi_qla_host {
 #define DPC_HA_NEED_QUIESCENT		22 /* 0x00400000 ISP-82xx only*/
 #define DPC_POST_IDC_ACK		23 /* 0x00800000 */
 #define DPC_RESTORE_ACB			24 /* 0x01000000 */
+#define DPC_SYSFS_DDB_EXPORT		25 /* 0x02000000 */
 
 	struct Scsi_Host *host; /* pointer to host data */
 	uint32_t tot_ddbs;
diff --git a/drivers/scsi/qla4xxx/ql4_fw.h b/drivers/scsi/qla4xxx/ql4_fw.h
index 209853ce0bb..699575efc9b 100644
--- a/drivers/scsi/qla4xxx/ql4_fw.h
+++ b/drivers/scsi/qla4xxx/ql4_fw.h
@@ -1415,6 +1415,9 @@ struct ql_iscsi_stats {
 #define QLA83XX_DBG_OCM_WNDREG_ARRAY_LEN	16
 #define QLA83XX_SS_OCM_WNDREG_INDEX		3
 #define QLA83XX_SS_PCI_INDEX			0
+#define QLA8022_TEMPLATE_CAP_OFFSET		172
+#define QLA83XX_TEMPLATE_CAP_OFFSET		268
+#define QLA80XX_TEMPLATE_RESERVED_BITS		16
 
 struct qla4_8xxx_minidump_template_hdr {
 	uint32_t entry_type;
@@ -1434,6 +1437,7 @@ struct qla4_8xxx_minidump_template_hdr {
 	uint32_t saved_state_array[QLA8XXX_DBG_STATE_ARRAY_LEN];
 	uint32_t capture_size_array[QLA8XXX_DBG_CAP_SIZE_ARRAY_LEN];
 	uint32_t ocm_window_reg[QLA83XX_DBG_OCM_WNDREG_ARRAY_LEN];
+	uint32_t capabilities[QLA80XX_TEMPLATE_RESERVED_BITS];
 };
 
 #endif /*  _QLA4X_FW_H */
diff --git a/drivers/scsi/qla4xxx/ql4_glbl.h b/drivers/scsi/qla4xxx/ql4_glbl.h
index b1a19cd8d5b..5f58b451327 100644
--- a/drivers/scsi/qla4xxx/ql4_glbl.h
+++ b/drivers/scsi/qla4xxx/ql4_glbl.h
@@ -274,13 +274,14 @@ int qla4xxx_set_acb(struct scsi_qla_host *ha, uint32_t *mbox_cmd,
 int qla4xxx_get_acb(struct scsi_qla_host *ha, dma_addr_t acb_dma,
 		    uint32_t acb_type, uint32_t len);
 int qla4_84xx_config_acb(struct scsi_qla_host *ha, int acb_config);
-int qla4_83xx_ms_mem_write_128b(struct scsi_qla_host *ha,
+int qla4_8xxx_ms_mem_write_128b(struct scsi_qla_host *ha,
 				uint64_t addr, uint32_t *data, uint32_t count);
 uint8_t qla4xxx_set_ipaddr_state(uint8_t fw_ipaddr_state);
 int qla4_83xx_get_port_config(struct scsi_qla_host *ha, uint32_t *config);
 int qla4_83xx_set_port_config(struct scsi_qla_host *ha, uint32_t *config);
 int qla4_8xxx_check_init_adapter_retry(struct scsi_qla_host *ha);
 int qla4_83xx_is_detached(struct scsi_qla_host *ha);
+int qla4xxx_sysfs_ddb_export(struct scsi_qla_host *ha);
 
 extern int ql4xextended_error_logging;
 extern int ql4xdontresethba;
diff --git a/drivers/scsi/qla4xxx/ql4_init.c b/drivers/scsi/qla4xxx/ql4_init.c
index 28fbece7e08..6f12f859b11 100644
--- a/drivers/scsi/qla4xxx/ql4_init.c
+++ b/drivers/scsi/qla4xxx/ql4_init.c
@@ -282,6 +282,25 @@ qla4xxx_wait_for_ip_config(struct scsi_qla_host *ha)
 	return ipv4_wait|ipv6_wait;
 }
 
+static int qla4_80xx_is_minidump_dma_capable(struct scsi_qla_host *ha,
+		struct qla4_8xxx_minidump_template_hdr *md_hdr)
+{
+	int offset = (is_qla8022(ha)) ? QLA8022_TEMPLATE_CAP_OFFSET :
+					QLA83XX_TEMPLATE_CAP_OFFSET;
+	int rval = 1;
+	uint32_t *cap_offset;
+
+	cap_offset = (uint32_t *)((char *)md_hdr + offset);
+
+	if (!(le32_to_cpu(*cap_offset) & BIT_0)) {
+		ql4_printk(KERN_INFO, ha, "PEX DMA Not supported %d\n",
+			   *cap_offset);
+		rval = 0;
+	}
+
+	return rval;
+}
+
 /**
  * qla4xxx_alloc_fw_dump - Allocate memory for minidump data.
  * @ha: pointer to host adapter structure.
@@ -294,6 +313,7 @@ void qla4xxx_alloc_fw_dump(struct scsi_qla_host *ha)
 	void *md_tmp;
 	dma_addr_t md_tmp_dma;
 	struct qla4_8xxx_minidump_template_hdr *md_hdr;
+	int dma_capable;
 
 	if (ha->fw_dump) {
 		ql4_printk(KERN_WARNING, ha,
@@ -326,13 +346,19 @@ void qla4xxx_alloc_fw_dump(struct scsi_qla_host *ha)
 
 	md_hdr = (struct qla4_8xxx_minidump_template_hdr *)md_tmp;
 
+	dma_capable = qla4_80xx_is_minidump_dma_capable(ha, md_hdr);
+
 	capture_debug_level = md_hdr->capture_debug_level;
 
 	/* Get capture mask based on module loadtime setting. */
-	if (ql4xmdcapmask >= 0x3 && ql4xmdcapmask <= 0x7F)
+	if ((ql4xmdcapmask >= 0x3 && ql4xmdcapmask <= 0x7F) ||
+	    (ql4xmdcapmask == 0xFF && dma_capable))  {
 		ha->fw_dump_capture_mask = ql4xmdcapmask;
-	else
+	} else {
+		if (ql4xmdcapmask == 0xFF)
+			ql4_printk(KERN_INFO, ha, "Falling back to default capture mask, as PEX DMA is not supported\n");
 		ha->fw_dump_capture_mask = capture_debug_level;
+	}
 
 	md_hdr->driver_capture_mask = ha->fw_dump_capture_mask;
 
@@ -864,6 +890,8 @@ int qla4xxx_start_firmware(struct scsi_qla_host *ha)
 	if (status == QLA_SUCCESS) {
 		if (test_and_clear_bit(AF_GET_CRASH_RECORD, &ha->flags))
 			qla4xxx_get_crash_record(ha);
+
+		qla4xxx_init_rings(ha);
 	} else {
 		DEBUG(printk("scsi%ld: %s: Firmware has NOT started\n",
 			     ha->host_no, __func__));
diff --git a/drivers/scsi/qla4xxx/ql4_isr.c b/drivers/scsi/qla4xxx/ql4_isr.c
index b1925d195f4..081b6b78d2c 100644
--- a/drivers/scsi/qla4xxx/ql4_isr.c
+++ b/drivers/scsi/qla4xxx/ql4_isr.c
@@ -1526,7 +1526,7 @@ void qla4xxx_process_aen(struct scsi_qla_host * ha, uint8_t process_aen)
 
 int qla4xxx_request_irqs(struct scsi_qla_host *ha)
 {
-	int ret;
+	int ret = 0;
 	int rval = QLA_ERROR;
 
 	if (is_qla40XX(ha))
@@ -1580,15 +1580,13 @@ try_msi:
 		}
 	}
 
-	/*
-	 * Prevent interrupts from falling back to INTx mode in cases where
-	 * interrupts cannot get acquired through MSI-X or MSI mode.
-	 */
+try_intx:
 	if (is_qla8022(ha)) {
-		ql4_printk(KERN_WARNING, ha, "IRQ not attached -- %d.\n", ret);
+		ql4_printk(KERN_WARNING, ha, "%s: ISP82xx Legacy interrupt not supported\n",
+			   __func__);
 		goto irq_not_attached;
 	}
-try_intx:
+
 	/* Trying INTx */
 	ret = request_irq(ha->pdev->irq, ha->isp_ops->intr_handler,
 	    IRQF_SHARED, DRIVER_NAME, ha);
diff --git a/drivers/scsi/qla4xxx/ql4_mbx.c b/drivers/scsi/qla4xxx/ql4_mbx.c
index 0a6b782d6fd..0a3312c6dd6 100644
--- a/drivers/scsi/qla4xxx/ql4_mbx.c
+++ b/drivers/scsi/qla4xxx/ql4_mbx.c
@@ -2381,7 +2381,7 @@ int qla4_84xx_config_acb(struct scsi_qla_host *ha, int acb_config)
 			ql4_printk(KERN_ERR, ha, "%s: Unable to alloc acb\n",
 				   __func__);
 			rval = QLA_ERROR;
-			goto exit_config_acb;
+			goto exit_free_acb;
 		}
 		memcpy(ha->saved_acb, acb, acb_len);
 		break;
@@ -2395,8 +2395,6 @@ int qla4_84xx_config_acb(struct scsi_qla_host *ha, int acb_config)
 		}
 
 		memcpy(acb, ha->saved_acb, acb_len);
-		kfree(ha->saved_acb);
-		ha->saved_acb = NULL;
 
 		rval = qla4xxx_set_acb(ha, &mbox_cmd[0], &mbox_sts[0], acb_dma);
 		if (rval != QLA_SUCCESS)
@@ -2412,6 +2410,10 @@ exit_free_acb:
 	dma_free_coherent(&ha->pdev->dev, sizeof(struct addr_ctrl_blk), acb,
 			  acb_dma);
 exit_config_acb:
+	if ((acb_config == ACB_CONFIG_SET) && ha->saved_acb) {
+		kfree(ha->saved_acb);
+		ha->saved_acb = NULL;
+	}
 	DEBUG2(ql4_printk(KERN_INFO, ha,
 			  "%s %s\n", __func__,
 			  rval == QLA_SUCCESS ? "SUCCEEDED" : "FAILED"));
diff --git a/drivers/scsi/qla4xxx/ql4_nx.c b/drivers/scsi/qla4xxx/ql4_nx.c
index 63328c812b7..9dbdb4be2d8 100644
--- a/drivers/scsi/qla4xxx/ql4_nx.c
+++ b/drivers/scsi/qla4xxx/ql4_nx.c
@@ -14,6 +14,7 @@
 
 #include <asm-generic/io-64-nonatomic-lo-hi.h>
 
+#define TIMEOUT_100_MS	100
 #define MASK(n)		DMA_BIT_MASK(n)
 #define MN_WIN(addr)	(((addr & 0x1fc0000) >> 1) | ((addr >> 25) & 0x3ff))
 #define OCM_WIN(addr)	(((addr & 0x1ff0000) >> 1) | ((addr >> 25) & 0x3ff))
@@ -1176,6 +1177,112 @@ qla4_82xx_pinit_from_rom(struct scsi_qla_host *ha, int verbose)
 	return 0;
 }
 
+/**
+ * qla4_8xxx_ms_mem_write_128b - Writes data to MS/off-chip memory
+ * @ha: Pointer to adapter structure
+ * @addr: Flash address to write to
+ * @data: Data to be written
+ * @count: word_count to be written
+ *
+ * Return: On success return QLA_SUCCESS
+ *         On error return QLA_ERROR
+ **/
+int qla4_8xxx_ms_mem_write_128b(struct scsi_qla_host *ha, uint64_t addr,
+				uint32_t *data, uint32_t count)
+{
+	int i, j;
+	uint32_t agt_ctrl;
+	unsigned long flags;
+	int ret_val = QLA_SUCCESS;
+
+	/* Only 128-bit aligned access */
+	if (addr & 0xF) {
+		ret_val = QLA_ERROR;
+		goto exit_ms_mem_write;
+	}
+
+	write_lock_irqsave(&ha->hw_lock, flags);
+
+	/* Write address */
+	ret_val = ha->isp_ops->wr_reg_indirect(ha, MD_MIU_TEST_AGT_ADDR_HI, 0);
+	if (ret_val == QLA_ERROR) {
+		ql4_printk(KERN_ERR, ha, "%s: write to AGT_ADDR_HI failed\n",
+			   __func__);
+		goto exit_ms_mem_write_unlock;
+	}
+
+	for (i = 0; i < count; i++, addr += 16) {
+		if (!((QLA8XXX_ADDR_IN_RANGE(addr, QLA8XXX_ADDR_QDR_NET,
+					     QLA8XXX_ADDR_QDR_NET_MAX)) ||
+		      (QLA8XXX_ADDR_IN_RANGE(addr, QLA8XXX_ADDR_DDR_NET,
+					     QLA8XXX_ADDR_DDR_NET_MAX)))) {
+			ret_val = QLA_ERROR;
+			goto exit_ms_mem_write_unlock;
+		}
+
+		ret_val = ha->isp_ops->wr_reg_indirect(ha,
+						       MD_MIU_TEST_AGT_ADDR_LO,
+						       addr);
+		/* Write data */
+		ret_val |= ha->isp_ops->wr_reg_indirect(ha,
+						MD_MIU_TEST_AGT_WRDATA_LO,
+						*data++);
+		ret_val |= ha->isp_ops->wr_reg_indirect(ha,
+						MD_MIU_TEST_AGT_WRDATA_HI,
+						*data++);
+		ret_val |= ha->isp_ops->wr_reg_indirect(ha,
+						MD_MIU_TEST_AGT_WRDATA_ULO,
+						*data++);
+		ret_val |= ha->isp_ops->wr_reg_indirect(ha,
+						MD_MIU_TEST_AGT_WRDATA_UHI,
+						*data++);
+		if (ret_val == QLA_ERROR) {
+			ql4_printk(KERN_ERR, ha, "%s: write to AGT_WRDATA failed\n",
+				   __func__);
+			goto exit_ms_mem_write_unlock;
+		}
+
+		/* Check write status */
+		ret_val = ha->isp_ops->wr_reg_indirect(ha, MD_MIU_TEST_AGT_CTRL,
+						       MIU_TA_CTL_WRITE_ENABLE);
+		ret_val |= ha->isp_ops->wr_reg_indirect(ha,
+							MD_MIU_TEST_AGT_CTRL,
+							MIU_TA_CTL_WRITE_START);
+		if (ret_val == QLA_ERROR) {
+			ql4_printk(KERN_ERR, ha, "%s: write to AGT_CTRL failed\n",
+				   __func__);
+			goto exit_ms_mem_write_unlock;
+		}
+
+		for (j = 0; j < MAX_CTL_CHECK; j++) {
+			ret_val = ha->isp_ops->rd_reg_indirect(ha,
+							MD_MIU_TEST_AGT_CTRL,
+							&agt_ctrl);
+			if (ret_val == QLA_ERROR) {
+				ql4_printk(KERN_ERR, ha, "%s: failed to read MD_MIU_TEST_AGT_CTRL\n",
+					   __func__);
+				goto exit_ms_mem_write_unlock;
+			}
+			if ((agt_ctrl & MIU_TA_CTL_BUSY) == 0)
+				break;
+		}
+
+		/* Status check failed */
+		if (j >= MAX_CTL_CHECK) {
+			printk_ratelimited(KERN_ERR "%s: MS memory write failed!\n",
+					   __func__);
+			ret_val = QLA_ERROR;
+			goto exit_ms_mem_write_unlock;
+		}
+	}
+
+exit_ms_mem_write_unlock:
+	write_unlock_irqrestore(&ha->hw_lock, flags);
+
+exit_ms_mem_write:
+	return ret_val;
+}
+
 static int
 qla4_82xx_load_from_flash(struct scsi_qla_host *ha, uint32_t image_start)
 {
@@ -1714,6 +1821,101 @@ void qla4_82xx_rom_lock_recovery(struct scsi_qla_host *ha)
 	qla4_82xx_rom_unlock(ha);
 }
 
+static uint32_t ql4_84xx_poll_wait_for_ready(struct scsi_qla_host *ha,
+					     uint32_t addr1, uint32_t mask)
+{
+	unsigned long timeout;
+	uint32_t rval = QLA_SUCCESS;
+	uint32_t temp;
+
+	timeout = jiffies + msecs_to_jiffies(TIMEOUT_100_MS);
+	do {
+		ha->isp_ops->rd_reg_indirect(ha, addr1, &temp);
+		if ((temp & mask) != 0)
+			break;
+
+		if (time_after_eq(jiffies, timeout)) {
+			ql4_printk(KERN_INFO, ha, "Error in processing rdmdio entry\n");
+			return QLA_ERROR;
+		}
+	} while (1);
+
+	return rval;
+}
+
+uint32_t ql4_84xx_ipmdio_rd_reg(struct scsi_qla_host *ha, uint32_t addr1,
+				uint32_t addr3, uint32_t mask, uint32_t addr,
+				uint32_t *data_ptr)
+{
+	int rval = QLA_SUCCESS;
+	uint32_t temp;
+	uint32_t data;
+
+	rval = ql4_84xx_poll_wait_for_ready(ha, addr1, mask);
+	if (rval)
+		goto exit_ipmdio_rd_reg;
+
+	temp = (0x40000000 | addr);
+	ha->isp_ops->wr_reg_indirect(ha, addr1, temp);
+
+	rval = ql4_84xx_poll_wait_for_ready(ha, addr1, mask);
+	if (rval)
+		goto exit_ipmdio_rd_reg;
+
+	ha->isp_ops->rd_reg_indirect(ha, addr3, &data);
+	*data_ptr = data;
+
+exit_ipmdio_rd_reg:
+	return rval;
+}
+
+
+static uint32_t ql4_84xx_poll_wait_ipmdio_bus_idle(struct scsi_qla_host *ha,
+						    uint32_t addr1,
+						    uint32_t addr2,
+						    uint32_t addr3,
+						    uint32_t mask)
+{
+	unsigned long timeout;
+	uint32_t temp;
+	uint32_t rval = QLA_SUCCESS;
+
+	timeout = jiffies + msecs_to_jiffies(TIMEOUT_100_MS);
+	do {
+		ql4_84xx_ipmdio_rd_reg(ha, addr1, addr3, mask, addr2, &temp);
+		if ((temp & 0x1) != 1)
+			break;
+		if (time_after_eq(jiffies, timeout)) {
+			ql4_printk(KERN_INFO, ha, "Error in processing mdiobus idle\n");
+			return QLA_ERROR;
+		}
+	} while (1);
+
+	return rval;
+}
+
+static int ql4_84xx_ipmdio_wr_reg(struct scsi_qla_host *ha,
+				  uint32_t addr1, uint32_t addr3,
+				  uint32_t mask, uint32_t addr,
+				  uint32_t value)
+{
+	int rval = QLA_SUCCESS;
+
+	rval = ql4_84xx_poll_wait_for_ready(ha, addr1, mask);
+	if (rval)
+		goto exit_ipmdio_wr_reg;
+
+	ha->isp_ops->wr_reg_indirect(ha, addr3, value);
+	ha->isp_ops->wr_reg_indirect(ha, addr1, addr);
+
+	rval = ql4_84xx_poll_wait_for_ready(ha, addr1, mask);
+	if (rval)
+		goto exit_ipmdio_wr_reg;
+
+exit_ipmdio_wr_reg:
+	return rval;
+}
+
 static void qla4_8xxx_minidump_process_rdcrb(struct scsi_qla_host *ha,
 				struct qla8xxx_minidump_entry_hdr *entry_hdr,
 				uint32_t **d_ptr)
@@ -1822,7 +2024,7 @@ error_exit:
 	return rval;
 }
 
-static int qla4_83xx_minidump_pex_dma_read(struct scsi_qla_host *ha,
+static int qla4_8xxx_minidump_pex_dma_read(struct scsi_qla_host *ha,
 				struct qla8xxx_minidump_entry_hdr *entry_hdr,
 				uint32_t **d_ptr)
 {
@@ -1899,11 +2101,11 @@ static int qla4_83xx_minidump_pex_dma_read(struct scsi_qla_host *ha,
 		dma_desc.cmd.read_data_size = size;
 
 		/* Prepare: Write pex-dma descriptor to MS memory. */
-		rval = qla4_83xx_ms_mem_write_128b(ha,
+		rval = qla4_8xxx_ms_mem_write_128b(ha,
 			      (uint64_t)m_hdr->desc_card_addr,
 			      (uint32_t *)&dma_desc,
 			      (sizeof(struct qla4_83xx_pex_dma_descriptor)/16));
-		if (rval == -1) {
+		if (rval != QLA_SUCCESS) {
 			ql4_printk(KERN_INFO, ha,
 				   "%s: Error writing rdmem-dma-init to MS !!!\n",
 				   __func__);
@@ -2359,17 +2561,10 @@ static int qla4_8xxx_minidump_process_rdmem(struct scsi_qla_host *ha,
 	uint32_t *data_ptr = *d_ptr;
 	int rval = QLA_SUCCESS;
 
-	if (is_qla8032(ha) || is_qla8042(ha)) {
-		rval = qla4_83xx_minidump_pex_dma_read(ha, entry_hdr,
-						       &data_ptr);
-		if (rval != QLA_SUCCESS) {
-			rval = __qla4_8xxx_minidump_process_rdmem(ha, entry_hdr,
-								  &data_ptr);
-		}
-	} else {
+	rval = qla4_8xxx_minidump_pex_dma_read(ha, entry_hdr, &data_ptr);
+	if (rval != QLA_SUCCESS)
 		rval = __qla4_8xxx_minidump_process_rdmem(ha, entry_hdr,
 							  &data_ptr);
-	}
 	*d_ptr = data_ptr;
 	return rval;
 }
@@ -2440,6 +2635,227 @@ exit_process_pollrd:
 	return rval;
 }
 
+static uint32_t qla4_84xx_minidump_process_rddfe(struct scsi_qla_host *ha,
+				struct qla8xxx_minidump_entry_hdr *entry_hdr,
+				uint32_t **d_ptr)
+{
+	int loop_cnt;
+	uint32_t addr1, addr2, value, data, temp, wrval;
+	uint8_t stride, stride2;
+	uint16_t count;
+	uint32_t poll, mask, data_size, modify_mask;
+	uint32_t wait_count = 0;
+	uint32_t *data_ptr = *d_ptr;
+	struct qla8044_minidump_entry_rddfe *rddfe;
+	uint32_t rval = QLA_SUCCESS;
+
+	rddfe = (struct qla8044_minidump_entry_rddfe *)entry_hdr;
+	addr1 = le32_to_cpu(rddfe->addr_1);
+	value = le32_to_cpu(rddfe->value);
+	stride = le32_to_cpu(rddfe->stride);
+	stride2 = le32_to_cpu(rddfe->stride2);
+	count = le32_to_cpu(rddfe->count);
+
+	poll = le32_to_cpu(rddfe->poll);
+	mask = le32_to_cpu(rddfe->mask);
+	modify_mask = le32_to_cpu(rddfe->modify_mask);
+	data_size = le32_to_cpu(rddfe->data_size);
+
+	addr2 = addr1 + stride;
+
+	for (loop_cnt = 0x0; loop_cnt < count; loop_cnt++) {
+		ha->isp_ops->wr_reg_indirect(ha, addr1, (0x40000000 | value));
+
+		wait_count = 0;
+		while (wait_count < poll) {
+			ha->isp_ops->rd_reg_indirect(ha, addr1, &temp);
+			if ((temp & mask) != 0)
+				break;
+			wait_count++;
+		}
+
+		if (wait_count == poll) {
+			ql4_printk(KERN_ERR, ha, "%s: TIMEOUT\n", __func__);
+			rval = QLA_ERROR;
+			goto exit_process_rddfe;
+		} else {
+			ha->isp_ops->rd_reg_indirect(ha, addr2, &temp);
+			temp = temp & modify_mask;
+			temp = (temp | ((loop_cnt << 16) | loop_cnt));
+			wrval = ((temp << 16) | temp);
+
+			ha->isp_ops->wr_reg_indirect(ha, addr2, wrval);
+			ha->isp_ops->wr_reg_indirect(ha, addr1, value);
+
+			wait_count = 0;
+			while (wait_count < poll) {
+				ha->isp_ops->rd_reg_indirect(ha, addr1, &temp);
+				if ((temp & mask) != 0)
+					break;
+				wait_count++;
+			}
+			if (wait_count == poll) {
+				ql4_printk(KERN_ERR, ha, "%s: TIMEOUT\n",
+					   __func__);
+				rval = QLA_ERROR;
+				goto exit_process_rddfe;
+			}
+
+			ha->isp_ops->wr_reg_indirect(ha, addr1,
+						     ((0x40000000 | value) +
+						     stride2));
+			wait_count = 0;
+			while (wait_count < poll) {
+				ha->isp_ops->rd_reg_indirect(ha, addr1, &temp);
+				if ((temp & mask) != 0)
+					break;
+				wait_count++;
+			}
+
+			if (wait_count == poll) {
+				ql4_printk(KERN_ERR, ha, "%s: TIMEOUT\n",
+					   __func__);
+				rval = QLA_ERROR;
+				goto exit_process_rddfe;
+			}
+
+			ha->isp_ops->rd_reg_indirect(ha, addr2, &data);
+
+			*data_ptr++ = cpu_to_le32(wrval);
+			*data_ptr++ = cpu_to_le32(data);
+		}
+	}
+
+	*d_ptr = data_ptr;
+exit_process_rddfe:
+	return rval;
+}
+
+static uint32_t qla4_84xx_minidump_process_rdmdio(struct scsi_qla_host *ha,
+				struct qla8xxx_minidump_entry_hdr *entry_hdr,
+				uint32_t **d_ptr)
+{
+	int rval = QLA_SUCCESS;
+	uint32_t addr1, addr2, value1, value2, data, selval;
+	uint8_t stride1, stride2;
+	uint32_t addr3, addr4, addr5, addr6, addr7;
+	uint16_t count, loop_cnt;
+	uint32_t poll, mask;
+	uint32_t *data_ptr = *d_ptr;
+	struct qla8044_minidump_entry_rdmdio *rdmdio;
+
+	rdmdio = (struct qla8044_minidump_entry_rdmdio *)entry_hdr;
+	addr1 = le32_to_cpu(rdmdio->addr_1);
+	addr2 = le32_to_cpu(rdmdio->addr_2);
+	value1 = le32_to_cpu(rdmdio->value_1);
+	stride1 = le32_to_cpu(rdmdio->stride_1);
+	stride2 = le32_to_cpu(rdmdio->stride_2);
+	count = le32_to_cpu(rdmdio->count);
+
+	poll = le32_to_cpu(rdmdio->poll);
+	mask = le32_to_cpu(rdmdio->mask);
+	value2 = le32_to_cpu(rdmdio->value_2);
+
+	addr3 = addr1 + stride1;
+
+	for (loop_cnt = 0; loop_cnt < count; loop_cnt++) {
+		rval = ql4_84xx_poll_wait_ipmdio_bus_idle(ha, addr1, addr2,
+							 addr3, mask);
+		if (rval)
+			goto exit_process_rdmdio;
+
+		addr4 = addr2 - stride1;
+		rval = ql4_84xx_ipmdio_wr_reg(ha, addr1, addr3, mask, addr4,
+					     value2);
+		if (rval)
+			goto exit_process_rdmdio;
+
+		addr5 = addr2 - (2 * stride1);
+		rval = ql4_84xx_ipmdio_wr_reg(ha, addr1, addr3, mask, addr5,
+					     value1);
+		if (rval)
+			goto exit_process_rdmdio;
+
+		addr6 = addr2 - (3 * stride1);
+		rval = ql4_84xx_ipmdio_wr_reg(ha, addr1, addr3, mask,
+					     addr6, 0x2);
+		if (rval)
+			goto exit_process_rdmdio;
+
+		rval = ql4_84xx_poll_wait_ipmdio_bus_idle(ha, addr1, addr2,
+							 addr3, mask);
+		if (rval)
+			goto exit_process_rdmdio;
+
+		addr7 = addr2 - (4 * stride1);
+		rval = ql4_84xx_ipmdio_rd_reg(ha, addr1, addr3,
+						      mask, addr7, &data);
+		if (rval)
+			goto exit_process_rdmdio;
+
+		selval = (value2 << 18) | (value1 << 2) | 2;
+
+		stride2 = le32_to_cpu(rdmdio->stride_2);
+		*data_ptr++ = cpu_to_le32(selval);
+		*data_ptr++ = cpu_to_le32(data);
+
+		value1 = value1 + stride2;
+		*d_ptr = data_ptr;
+	}
+
+exit_process_rdmdio:
+	return rval;
+}
+
+static uint32_t qla4_84xx_minidump_process_pollwr(struct scsi_qla_host *ha,
+				struct qla8xxx_minidump_entry_hdr *entry_hdr,
+				uint32_t **d_ptr)
+{
+	uint32_t addr1, addr2, value1, value2, poll, mask, r_value;
+	struct qla8044_minidump_entry_pollwr *pollwr_hdr;
+	uint32_t wait_count = 0;
+	uint32_t rval = QLA_SUCCESS;
+
+	pollwr_hdr = (struct qla8044_minidump_entry_pollwr *)entry_hdr;
+	addr1 = le32_to_cpu(pollwr_hdr->addr_1);
+	addr2 = le32_to_cpu(pollwr_hdr->addr_2);
+	value1 = le32_to_cpu(pollwr_hdr->value_1);
+	value2 = le32_to_cpu(pollwr_hdr->value_2);
+
+	poll = le32_to_cpu(pollwr_hdr->poll);
+	mask = le32_to_cpu(pollwr_hdr->mask);
+
+	while (wait_count < poll) {
+		ha->isp_ops->rd_reg_indirect(ha, addr1, &r_value);
+
+		if ((r_value & poll) != 0)
+			break;
+
+		wait_count++;
+	}
+
+	if (wait_count == poll) {
+		ql4_printk(KERN_ERR, ha, "%s: TIMEOUT\n", __func__);
+		rval = QLA_ERROR;
+		goto exit_process_pollwr;
+	}
+
+	ha->isp_ops->wr_reg_indirect(ha, addr2, value2);
+	ha->isp_ops->wr_reg_indirect(ha, addr1, value1);
+
+	wait_count = 0;
+	while (wait_count < poll) {
+		ha->isp_ops->rd_reg_indirect(ha, addr1, &r_value);
+
+		if ((r_value & poll) != 0)
+			break;
+		wait_count++;
+	}
+
+exit_process_pollwr:
+	return rval;
+}
+
 static void qla83xx_minidump_process_rdmux2(struct scsi_qla_host *ha,
 				struct qla8xxx_minidump_entry_hdr *entry_hdr,
 				uint32_t **d_ptr)
@@ -2753,6 +3169,24 @@ static int qla4_8xxx_collect_md_data(struct scsi_qla_host *ha)
 			if (rval != QLA_SUCCESS)
 				qla4_8xxx_mark_entry_skipped(ha, entry_hdr, i);
 			break;
+		case QLA8044_RDDFE:
+			rval = qla4_84xx_minidump_process_rddfe(ha, entry_hdr,
+								&data_ptr);
+			if (rval != QLA_SUCCESS)
+				qla4_8xxx_mark_entry_skipped(ha, entry_hdr, i);
+			break;
+		case QLA8044_RDMDIO:
+			rval = qla4_84xx_minidump_process_rdmdio(ha, entry_hdr,
+								 &data_ptr);
+			if (rval != QLA_SUCCESS)
+				qla4_8xxx_mark_entry_skipped(ha, entry_hdr, i);
+			break;
+		case QLA8044_POLLWR:
+			rval = qla4_84xx_minidump_process_pollwr(ha, entry_hdr,
+								 &data_ptr);
+			if (rval != QLA_SUCCESS)
+				qla4_8xxx_mark_entry_skipped(ha, entry_hdr, i);
+			break;
 		case QLA8XXX_RDNOP:
 		default:
 			qla4_8xxx_mark_entry_skipped(ha, entry_hdr, i);
diff --git a/drivers/scsi/qla4xxx/ql4_nx.h b/drivers/scsi/qla4xxx/ql4_nx.h
index 14500a0f62c..337d9fcf641 100644
--- a/drivers/scsi/qla4xxx/ql4_nx.h
+++ b/drivers/scsi/qla4xxx/ql4_nx.h
@@ -858,6 +858,9 @@ struct crb_addr_pair {
 #define QLA83XX_POLLRD	35
 #define QLA83XX_RDMUX2	36
 #define QLA83XX_POLLRDMWR  37
+#define QLA8044_RDDFE	38
+#define QLA8044_RDMDIO	39
+#define QLA8044_POLLWR	40
 #define QLA8XXX_RDROM	71
 #define QLA8XXX_RDMEM	72
 #define QLA8XXX_CNTRL	98
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 459b9f7186f..32020637620 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -83,12 +83,12 @@ MODULE_PARM_DESC(ql4xsess_recovery_tmo,
 		" Target Session Recovery Timeout.\n"
 		"\t\t  Default: 120 sec.");
 
-int ql4xmdcapmask = 0x1F;
+int ql4xmdcapmask = 0;
 module_param(ql4xmdcapmask, int, S_IRUGO);
 MODULE_PARM_DESC(ql4xmdcapmask,
 		 " Set the Minidump driver capture mask level.\n"
-		 "\t\t  Default is 0x1F.\n"
-		 "\t\t  Can be set to 0x3, 0x7, 0xF, 0x1F, 0x3F, 0x7F");
+		 "\t\t  Default is 0 (firmware default capture mask)\n"
+		 "\t\t  Can be set to 0x3, 0x7, 0xF, 0x1F, 0x3F, 0x7F, 0xFF");
 
 int ql4xenablemd = 1;
 module_param(ql4xenablemd, int, S_IRUGO | S_IWUSR);
@@ -1742,6 +1742,9 @@ static int qla4xxx_get_ep_param(struct iscsi_endpoint *ep,
 	struct sockaddr *dst_addr;
 	struct scsi_qla_host *ha;
 
+	if (!qla_ep)
+		return -ENOTCONN;
+
 	ha = to_qla_host(qla_ep->host);
 	DEBUG2(ql4_printk(KERN_INFO, ha, "%s: host: %ld\n", __func__,
 			  ha->host_no));
@@ -1749,9 +1752,6 @@ static int qla4xxx_get_ep_param(struct iscsi_endpoint *ep,
 	switch (param) {
 	case ISCSI_PARAM_CONN_PORT:
 	case ISCSI_PARAM_CONN_ADDRESS:
-		if (!qla_ep)
-			return -ENOTCONN;
-
 		dst_addr = (struct sockaddr *)&qla_ep->dst_addr;
 		if (!dst_addr)
 			return -ENOTCONN;
@@ -2879,7 +2879,6 @@ static int qla4xxx_conn_get_param(struct iscsi_cls_conn *cls_conn,
 	struct iscsi_conn *conn;
 	struct qla_conn *qla_conn;
 	struct sockaddr *dst_addr;
-	int len = 0;
 
 	conn = cls_conn->dd_data;
 	qla_conn = conn->dd_data;
@@ -2893,9 +2892,6 @@ static int qla4xxx_conn_get_param(struct iscsi_cls_conn *cls_conn,
 	default:
 		return iscsi_conn_get_param(cls_conn, param, buf);
 	}
-
-	return len;
-
 }
 
 int qla4xxx_get_ddb_index(struct scsi_qla_host *ha, uint16_t *ddb_index)
@@ -3569,14 +3565,13 @@ static int qla4xxx_copy_from_fwddb_param(struct iscsi_bus_flash_session *sess,
 	if (test_bit(OPT_IPV6_DEVICE, &options)) {
 		conn->ipv6_traffic_class = fw_ddb_entry->ipv4_tos;
 
-		conn->link_local_ipv6_addr = kzalloc(IPv6_ADDR_LEN, GFP_KERNEL);
+		conn->link_local_ipv6_addr = kmemdup(
+					fw_ddb_entry->link_local_ipv6_addr,
+					IPv6_ADDR_LEN, GFP_KERNEL);
 		if (!conn->link_local_ipv6_addr) {
 			rc = -ENOMEM;
 			goto exit_copy;
 		}
-
-		memcpy(conn->link_local_ipv6_addr,
-		       fw_ddb_entry->link_local_ipv6_addr, IPv6_ADDR_LEN);
 	} else {
 		conn->ipv4_tos = fw_ddb_entry->ipv4_tos;
 	}
@@ -4565,6 +4560,7 @@ static void qla4xxx_timer(struct scsi_qla_host *ha)
 	     test_bit(DPC_LINK_CHANGED, &ha->dpc_flags) ||
 	     test_bit(DPC_HA_UNRECOVERABLE, &ha->dpc_flags) ||
 	     test_bit(DPC_HA_NEED_QUIESCENT, &ha->dpc_flags) ||
+	     test_bit(DPC_SYSFS_DDB_EXPORT, &ha->dpc_flags) ||
 	     test_bit(DPC_AEN, &ha->dpc_flags)) {
 		DEBUG2(printk("scsi%ld: %s: scheduling dpc routine"
 			      " - dpc flags = 0x%lx\n",
@@ -4862,9 +4858,6 @@ static int qla4xxx_recover_adapter(struct scsi_qla_host *ha)
 		    ha->host_no, __func__));
 		status = ha->isp_ops->reset_firmware(ha);
 		if (status == QLA_SUCCESS) {
-			if (!test_bit(AF_FW_RECOVERY, &ha->flags))
-				qla4xxx_cmd_wait(ha);
-
 			ha->isp_ops->disable_intrs(ha);
 			qla4xxx_process_aen(ha, FLUSH_DDB_CHANGED_AENS);
 			qla4xxx_abort_active_cmds(ha, DID_RESET << 16);
@@ -5432,6 +5425,11 @@ dpc_post_reset_ha:
 				qla4xxx_relogin_all_devices(ha);
 		}
 	}
+	if (test_and_clear_bit(DPC_SYSFS_DDB_EXPORT, &ha->dpc_flags)) {
+		if (qla4xxx_sysfs_ddb_export(ha))
+			ql4_printk(KERN_ERR, ha, "%s: Error exporting ddb to sysfs\n",
+				   __func__);
+	}
 }
 
 /**
@@ -8409,7 +8407,7 @@ exit_ddb_del:
  *
  * Export the firmware DDB for all send targets and normal targets to sysfs.
  **/
-static int qla4xxx_sysfs_ddb_export(struct scsi_qla_host *ha)
+int qla4xxx_sysfs_ddb_export(struct scsi_qla_host *ha)
 {
 	struct dev_db_entry *fw_ddb_entry = NULL;
 	dma_addr_t fw_ddb_entry_dma;
@@ -8847,11 +8845,8 @@ skip_retry_init:
 		ql4_printk(KERN_ERR, ha,
 			   "%s: No iSCSI boot target configured\n", __func__);
 
-	if (qla4xxx_sysfs_ddb_export(ha))
-		ql4_printk(KERN_ERR, ha,
-			   "%s: Error exporting ddb to sysfs\n", __func__);
-
-		/* Perform the build ddb list and login to each */
+	set_bit(DPC_SYSFS_DDB_EXPORT, &ha->dpc_flags);
+	/* Perform the build ddb list and login to each */
 	qla4xxx_build_ddb_list(ha, INIT_ADAPTER);
 	iscsi_host_for_each_session(ha->host, qla4xxx_login_flash_ddb);
 	qla4xxx_wait_login_resp_boot_tgt(ha);
diff --git a/drivers/scsi/qla4xxx/ql4_version.h b/drivers/scsi/qla4xxx/ql4_version.h
index c6ba0a6b845..f11eaa77333 100644
--- a/drivers/scsi/qla4xxx/ql4_version.h
+++ b/drivers/scsi/qla4xxx/ql4_version.h
@@ -5,4 +5,4 @@
  * See LICENSE.qla4xxx for copyright and licensing details.
  */
 
-#define QLA4XXX_DRIVER_VERSION	"5.04.00-k4"
+#define QLA4XXX_DRIVER_VERSION	"5.04.00-k6"
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index f3e9cc038d1..1328a262107 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -130,6 +130,7 @@ static const char * scsi_debug_version_date = "20100324";
 #define SCSI_DEBUG_OPT_DIF_ERR   32
 #define SCSI_DEBUG_OPT_DIX_ERR   64
 #define SCSI_DEBUG_OPT_MAC_TIMEOUT  128
+#define SCSI_DEBUG_OPT_SHORT_TRANSFER	256
 /* When "every_nth" > 0 then modulo "every_nth" commands:
  *   - a no response is simulated if SCSI_DEBUG_OPT_TIMEOUT is set
  *   - a RECOVERED_ERROR is simulated on successful read and write
@@ -3583,6 +3584,7 @@ int scsi_debug_queuecommand_lck(struct scsi_cmnd *SCpnt, done_funct_t done)
 	int inj_transport = 0;
 	int inj_dif = 0;
 	int inj_dix = 0;
+	int inj_short = 0;
 	int delay_override = 0;
 	int unmap = 0;
 
@@ -3628,6 +3630,8 @@ int scsi_debug_queuecommand_lck(struct scsi_cmnd *SCpnt, done_funct_t done)
 			inj_dif = 1; /* to reads and writes below */
 		else if (SCSI_DEBUG_OPT_DIX_ERR & scsi_debug_opts)
 			inj_dix = 1; /* to reads and writes below */
+		else if (SCSI_DEBUG_OPT_SHORT_TRANSFER & scsi_debug_opts)
+			inj_short = 1;
 	}
 
 	if (devip->wlun) {
@@ -3744,6 +3748,10 @@ read:
 		if (scsi_debug_fake_rw)
 			break;
 		get_data_transfer_info(cmd, &lba, &num, &ei_lba);
+
+		if (inj_short)
+			num /= 2;
+
 		errsts = resp_read(SCpnt, lba, num, devip, ei_lba);
 		if (inj_recovered && (0 == errsts)) {
 			mk_sense_buffer(devip, RECOVERED_ERROR,
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index f17aa7aa787..7e957918f33 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -131,7 +131,7 @@ scmd_eh_abort_handler(struct work_struct *work)
 				    "aborting command %p\n", scmd));
 		rtn = scsi_try_to_abort_cmd(sdev->host->hostt, scmd);
 		if (rtn == SUCCESS) {
-			scmd->result |= DID_TIME_OUT << 16;
+			set_host_byte(scmd, DID_TIME_OUT);
 			if (scsi_host_eh_past_deadline(sdev->host)) {
 				SCSI_LOG_ERROR_RECOVERY(3,
 					scmd_printk(KERN_INFO, scmd,
@@ -167,7 +167,7 @@ scmd_eh_abort_handler(struct work_struct *work)
 			scmd_printk(KERN_WARNING, scmd,
 				    "scmd %p terminate "
 				    "aborted command\n", scmd));
-		scmd->result |= DID_TIME_OUT << 16;
+		set_host_byte(scmd, DID_TIME_OUT);
 		scsi_finish_command(scmd);
 	}
 }
@@ -287,15 +287,15 @@ enum blk_eh_timer_return scsi_times_out(struct request *req)
 	else if (host->hostt->eh_timed_out)
 		rtn = host->hostt->eh_timed_out(scmd);
 
-	if (rtn == BLK_EH_NOT_HANDLED && !host->hostt->no_async_abort)
-		if (scsi_abort_command(scmd) == SUCCESS)
+	if (rtn == BLK_EH_NOT_HANDLED) {
+		if (!host->hostt->no_async_abort &&
+		    scsi_abort_command(scmd) == SUCCESS)
 			return BLK_EH_NOT_HANDLED;
 
-	scmd->result |= DID_TIME_OUT << 16;
-
-	if (unlikely(rtn == BLK_EH_NOT_HANDLED &&
-		     !scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD)))
-		rtn = BLK_EH_HANDLED;
+		set_host_byte(scmd, DID_TIME_OUT);
+		if (!scsi_eh_scmd_add(scmd, SCSI_EH_CANCEL_CMD))
+			rtn = BLK_EH_HANDLED;
+	}
 
 	return rtn;
 }
@@ -1029,6 +1029,7 @@ retry:
 		rtn = NEEDS_RETRY;
 	} else {
 		timeleft = wait_for_completion_timeout(&done, timeout);
+		rtn = SUCCESS;
 	}
 
 	shost->eh_action = NULL;
@@ -1776,7 +1777,7 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd)
 		break;
 	case DID_ABORT:
 		if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) {
-			scmd->result |= DID_TIME_OUT << 16;
+			set_host_byte(scmd, DID_TIME_OUT);
 			return SUCCESS;
 		}
 	case DID_NO_CONNECT:
@@ -1951,6 +1952,8 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 	 */
 	req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL);
 
+	blk_rq_set_block_pc(req);
+
 	req->cmd[0] = ALLOW_MEDIUM_REMOVAL;
 	req->cmd[1] = 0;
 	req->cmd[2] = 0;
@@ -1960,7 +1963,6 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
 
 	req->cmd_len = COMMAND_SIZE(req->cmd[0]);
 
-	req->cmd_type = REQ_TYPE_BLOCK_PC;
 	req->cmd_flags |= REQ_QUIET;
 	req->timeout = 10 * HZ;
 	req->retries = 5;
@@ -2306,6 +2308,12 @@ scsi_reset_provider(struct scsi_device *dev, int flag)
 	}
 
 	scmd = scsi_get_command(dev, GFP_KERNEL);
+	if (!scmd) {
+		rtn = FAILED;
+		put_device(&dev->sdev_gendev);
+		goto out_put_autopm_host;
+	}
+
 	blk_rq_init(NULL, &req);
 	scmd->request = &req;
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index a0c95cac91f..3f50dfcb322 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -195,6 +195,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	req = blk_get_request(sdev->request_queue, write, __GFP_WAIT);
 	if (!req)
 		return ret;
+	blk_rq_set_block_pc(req);
 
 	if (bufflen &&	blk_rq_map_kern(sdev->request_queue, req,
 					buffer, bufflen, __GFP_WAIT))
@@ -206,7 +207,6 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	req->sense_len = 0;
 	req->retries = retries;
 	req->timeout = timeout;
-	req->cmd_type = REQ_TYPE_BLOCK_PC;
 	req->cmd_flags |= flags | REQ_QUIET | REQ_PREEMPT;
 
 	/*
@@ -512,68 +512,6 @@ void scsi_run_host_queues(struct Scsi_Host *shost)
 		scsi_run_queue(sdev->request_queue);
 }
 
-static void __scsi_release_buffers(struct scsi_cmnd *, int);
-
-/*
- * Function:    scsi_end_request()
- *
- * Purpose:     Post-processing of completed commands (usually invoked at end
- *		of upper level post-processing and scsi_io_completion).
- *
- * Arguments:   cmd	 - command that is complete.
- *              error    - 0 if I/O indicates success, < 0 for I/O error.
- *              bytes    - number of bytes of completed I/O
- *		requeue  - indicates whether we should requeue leftovers.
- *
- * Lock status: Assumed that lock is not held upon entry.
- *
- * Returns:     cmd if requeue required, NULL otherwise.
- *
- * Notes:       This is called for block device requests in order to
- *              mark some number of sectors as complete.
- * 
- *		We are guaranteeing that the request queue will be goosed
- *		at some point during this call.
- * Notes:	If cmd was requeued, upon return it will be a stale pointer.
- */
-static struct scsi_cmnd *scsi_end_request(struct scsi_cmnd *cmd, int error,
-					  int bytes, int requeue)
-{
-	struct request_queue *q = cmd->device->request_queue;
-	struct request *req = cmd->request;
-
-	/*
-	 * If there are blocks left over at the end, set up the command
-	 * to queue the remainder of them.
-	 */
-	if (blk_end_request(req, error, bytes)) {
-		/* kill remainder if no retrys */
-		if (error && scsi_noretry_cmd(cmd))
-			blk_end_request_all(req, error);
-		else {
-			if (requeue) {
-				/*
-				 * Bleah.  Leftovers again.  Stick the
-				 * leftovers in the front of the
-				 * queue, and goose the queue again.
-				 */
-				scsi_release_buffers(cmd);
-				scsi_requeue_command(q, cmd);
-				cmd = NULL;
-			}
-			return cmd;
-		}
-	}
-
-	/*
-	 * This will goose the queue request function at the end, so we don't
-	 * need to worry about launching another command.
-	 */
-	__scsi_release_buffers(cmd, 0);
-	scsi_next_command(cmd);
-	return NULL;
-}
-
 static inline unsigned int scsi_sgtable_index(unsigned short nents)
 {
 	unsigned int index;
@@ -625,30 +563,10 @@ static void scsi_free_sgtable(struct scsi_data_buffer *sdb)
 	__sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, scsi_sg_free);
 }
 
-static void __scsi_release_buffers(struct scsi_cmnd *cmd, int do_bidi_check)
-{
-
-	if (cmd->sdb.table.nents)
-		scsi_free_sgtable(&cmd->sdb);
-
-	memset(&cmd->sdb, 0, sizeof(cmd->sdb));
-
-	if (do_bidi_check && scsi_bidi_cmnd(cmd)) {
-		struct scsi_data_buffer *bidi_sdb =
-			cmd->request->next_rq->special;
-		scsi_free_sgtable(bidi_sdb);
-		kmem_cache_free(scsi_sdb_cache, bidi_sdb);
-		cmd->request->next_rq->special = NULL;
-	}
-
-	if (scsi_prot_sg_count(cmd))
-		scsi_free_sgtable(cmd->prot_sdb);
-}
-
 /*
  * Function:    scsi_release_buffers()
  *
- * Purpose:     Completion processing for block device I/O requests.
+ * Purpose:     Free resources allocate for a scsi_command.
  *
  * Arguments:   cmd	- command that we are bailing.
  *
@@ -659,15 +577,29 @@ static void __scsi_release_buffers(struct scsi_cmnd *cmd, int do_bidi_check)
  * Notes:       In the event that an upper level driver rejects a
  *		command, we must release resources allocated during
  *		the __init_io() function.  Primarily this would involve
- *		the scatter-gather table, and potentially any bounce
- *		buffers.
+ *		the scatter-gather table.
  */
 void scsi_release_buffers(struct scsi_cmnd *cmd)
 {
-	__scsi_release_buffers(cmd, 1);
+	if (cmd->sdb.table.nents)
+		scsi_free_sgtable(&cmd->sdb);
+
+	memset(&cmd->sdb, 0, sizeof(cmd->sdb));
+
+	if (scsi_prot_sg_count(cmd))
+		scsi_free_sgtable(cmd->prot_sdb);
 }
 EXPORT_SYMBOL(scsi_release_buffers);
 
+static void scsi_release_bidi_buffers(struct scsi_cmnd *cmd)
+{
+	struct scsi_data_buffer *bidi_sdb = cmd->request->next_rq->special;
+
+	scsi_free_sgtable(bidi_sdb);
+	kmem_cache_free(scsi_sdb_cache, bidi_sdb);
+	cmd->request->next_rq->special = NULL;
+}
+
 /**
  * __scsi_error_from_host_byte - translate SCSI error code into errno
  * @cmd:	SCSI command (unused)
@@ -725,16 +657,9 @@ static int __scsi_error_from_host_byte(struct scsi_cmnd *cmd, int result)
  *
  * Returns:     Nothing
  *
- * Notes:       This function is matched in terms of capabilities to
- *              the function that created the scatter-gather list.
- *              In other words, if there are no bounce buffers
- *              (the normal case for most drivers), we don't need
- *              the logic to deal with cleaning up afterwards.
- *
- *		We must call scsi_end_request().  This will finish off
- *		the specified number of sectors.  If we are done, the
- *		command block will be released and the queue function
- *		will be goosed.  If we are not done then we have to
+ * Notes:       We will finish off the specified number of sectors.  If we
+ *		are done, the command block will be released and the queue
+ *		function will be goosed.  If we are not done then we have to
  *		figure out what to do next:
  *
  *		a) We can call scsi_requeue_command().  The request
@@ -743,7 +668,7 @@ static int __scsi_error_from_host_byte(struct scsi_cmnd *cmd, int result)
  *		   be used if we made forward progress, or if we want
  *		   to switch from READ(10) to READ(6) for example.
  *
- *		b) We can call scsi_queue_insert().  The request will
+ *		b) We can call __scsi_queue_insert().  The request will
  *		   be put back on the queue and retried using the same
  *		   command as before, possibly after a delay.
  *
@@ -801,11 +726,21 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			req->next_rq->resid_len = scsi_in(cmd)->resid;
 
 			scsi_release_buffers(cmd);
+			scsi_release_bidi_buffers(cmd);
+
 			blk_end_request_all(req, 0);
 
 			scsi_next_command(cmd);
 			return;
 		}
+	} else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) {
+		/*
+		 * Certain non BLOCK_PC requests are commands that don't
+		 * actually transfer anything (FLUSH), so cannot use
+		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
+		 * This sets the error explicitly for the problem case.
+		 */
+		error = __scsi_error_from_host_byte(cmd, result);
 	}
 
 	/* no bidi support for !REQ_TYPE_BLOCK_PC yet */
@@ -840,12 +775,25 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	}
 
 	/*
-	 * A number of bytes were successfully read.  If there
-	 * are leftovers and there is some kind of error
-	 * (result != 0), retry the rest.
+	 * If we finished all bytes in the request we are done now.
 	 */
-	if (scsi_end_request(cmd, error, good_bytes, result == 0) == NULL)
-		return;
+	if (!blk_end_request(req, error, good_bytes))
+		goto next_command;
+
+	/*
+	 * Kill remainder if no retrys.
+	 */
+	if (error && scsi_noretry_cmd(cmd)) {
+		blk_end_request_all(req, error);
+		goto next_command;
+	}
+
+	/*
+	 * If there had been no error, but we have leftover bytes in the
+	 * requeues just queue the command up again.
+	 */
+	if (result == 0)
+		goto requeue;
 
 	error = __scsi_error_from_host_byte(cmd, result);
 
@@ -973,7 +921,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	switch (action) {
 	case ACTION_FAIL:
 		/* Give up and fail the remainder of the request */
-		scsi_release_buffers(cmd);
 		if (!(req->cmd_flags & REQ_QUIET)) {
 			if (description)
 				scmd_printk(KERN_INFO, cmd, "%s\n",
@@ -983,12 +930,11 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 				scsi_print_sense("", cmd);
 			scsi_print_command(cmd);
 		}
-		if (blk_end_request_err(req, error))
-			scsi_requeue_command(q, cmd);
-		else
-			scsi_next_command(cmd);
-		break;
+		if (!blk_end_request_err(req, error))
+			goto next_command;
+		/*FALLTHRU*/
 	case ACTION_REPREP:
+	requeue:
 		/* Unprep the request and put it back at the head of the queue.
 		 * A new command will be prepared and issued.
 		 */
@@ -1004,6 +950,11 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		__scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY, 0);
 		break;
 	}
+	return;
+
+next_command:
+	scsi_release_buffers(cmd);
+	scsi_next_command(cmd);
 }
 
 static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb,
@@ -1128,15 +1079,7 @@ static struct scsi_cmnd *scsi_get_cmd_from_req(struct scsi_device *sdev,
 
 int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req)
 {
-	struct scsi_cmnd *cmd;
-	int ret = scsi_prep_state_check(sdev, req);
-
-	if (ret != BLKPREP_OK)
-		return ret;
-
-	cmd = scsi_get_cmd_from_req(sdev, req);
-	if (unlikely(!cmd))
-		return BLKPREP_DEFER;
+	struct scsi_cmnd *cmd = req->special;
 
 	/*
 	 * BLOCK_PC requests may transfer data, in which case they must
@@ -1179,15 +1122,11 @@ EXPORT_SYMBOL(scsi_setup_blk_pc_cmnd);
  */
 int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req)
 {
-	struct scsi_cmnd *cmd;
-	int ret = scsi_prep_state_check(sdev, req);
-
-	if (ret != BLKPREP_OK)
-		return ret;
+	struct scsi_cmnd *cmd = req->special;
 
 	if (unlikely(sdev->scsi_dh_data && sdev->scsi_dh_data->scsi_dh
 			 && sdev->scsi_dh_data->scsi_dh->prep_fn)) {
-		ret = sdev->scsi_dh_data->scsi_dh->prep_fn(sdev, req);
+		int ret = sdev->scsi_dh_data->scsi_dh->prep_fn(sdev, req);
 		if (ret != BLKPREP_OK)
 			return ret;
 	}
@@ -1197,16 +1136,13 @@ int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req)
 	 */
 	BUG_ON(!req->nr_phys_segments);
 
-	cmd = scsi_get_cmd_from_req(sdev, req);
-	if (unlikely(!cmd))
-		return BLKPREP_DEFER;
-
 	memset(cmd->cmnd, 0, BLK_MAX_CDB);
 	return scsi_init_io(cmd, GFP_ATOMIC);
 }
 EXPORT_SYMBOL(scsi_setup_fs_cmnd);
 
-int scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
+static int
+scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
 {
 	int ret = BLKPREP_OK;
 
@@ -1258,9 +1194,9 @@ int scsi_prep_state_check(struct scsi_device *sdev, struct request *req)
 	}
 	return ret;
 }
-EXPORT_SYMBOL(scsi_prep_state_check);
 
-int scsi_prep_return(struct request_queue *q, struct request *req, int ret)
+static int
+scsi_prep_return(struct request_queue *q, struct request *req, int ret)
 {
 	struct scsi_device *sdev = q->queuedata;
 
@@ -1291,18 +1227,44 @@ int scsi_prep_return(struct request_queue *q, struct request *req, int ret)
 
 	return ret;
 }
-EXPORT_SYMBOL(scsi_prep_return);
 
-int scsi_prep_fn(struct request_queue *q, struct request *req)
+static int scsi_prep_fn(struct request_queue *q, struct request *req)
 {
 	struct scsi_device *sdev = q->queuedata;
-	int ret = BLKPREP_KILL;
+	struct scsi_cmnd *cmd;
+	int ret;
+
+	ret = scsi_prep_state_check(sdev, req);
+	if (ret != BLKPREP_OK)
+		goto out;
 
-	if (req->cmd_type == REQ_TYPE_BLOCK_PC)
+	cmd = scsi_get_cmd_from_req(sdev, req);
+	if (unlikely(!cmd)) {
+		ret = BLKPREP_DEFER;
+		goto out;
+	}
+
+	if (req->cmd_type == REQ_TYPE_FS)
+		ret = scsi_cmd_to_driver(cmd)->init_command(cmd);
+	else if (req->cmd_type == REQ_TYPE_BLOCK_PC)
 		ret = scsi_setup_blk_pc_cmnd(sdev, req);
+	else
+		ret = BLKPREP_KILL;
+
+out:
 	return scsi_prep_return(q, req, ret);
 }
-EXPORT_SYMBOL(scsi_prep_fn);
+
+static void scsi_unprep_fn(struct request_queue *q, struct request *req)
+{
+	if (req->cmd_type == REQ_TYPE_FS) {
+		struct scsi_cmnd *cmd = req->special;
+		struct scsi_driver *drv = scsi_cmd_to_driver(cmd);
+
+		if (drv->uninit_command)
+			drv->uninit_command(cmd);
+	}
+}
 
 /*
  * scsi_dev_queue_ready: if we can send requests to sdev, return 1 else
@@ -1723,6 +1685,7 @@ struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
 		return NULL;
 
 	blk_queue_prep_rq(q, scsi_prep_fn);
+	blk_queue_unprep_rq(q, scsi_unprep_fn);
 	blk_queue_softirq_done(q, scsi_softirq_done);
 	blk_queue_rq_timed_out(q, scsi_times_out);
 	blk_queue_lld_busy(q, scsi_lld_busy);
diff --git a/drivers/scsi/scsi_trace.c b/drivers/scsi/scsi_trace.c
index 2bea4f0b684..503594e5f76 100644
--- a/drivers/scsi/scsi_trace.c
+++ b/drivers/scsi/scsi_trace.c
@@ -28,7 +28,7 @@ scsi_trace_misc(struct trace_seq *, unsigned char *, int);
 static const char *
 scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len)
 {
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 	sector_t lba = 0, txlen = 0;
 
 	lba |= ((cdb[1] & 0x1F) << 16);
@@ -46,7 +46,7 @@ scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len)
 static const char *
 scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len)
 {
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 	sector_t lba = 0, txlen = 0;
 
 	lba |= (cdb[2] << 24);
@@ -71,7 +71,7 @@ scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len)
 static const char *
 scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len)
 {
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 	sector_t lba = 0, txlen = 0;
 
 	lba |= (cdb[2] << 24);
@@ -94,7 +94,7 @@ scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len)
 static const char *
 scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len)
 {
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 	sector_t lba = 0, txlen = 0;
 
 	lba |= ((u64)cdb[2] << 56);
@@ -125,7 +125,7 @@ scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len)
 static const char *
 scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len)
 {
-	const char *ret = p->buffer + p->len, *cmd;
+	const char *ret = trace_seq_buffer_ptr(p), *cmd;
 	sector_t lba = 0, txlen = 0;
 	u32 ei_lbrt = 0;
 
@@ -180,7 +180,7 @@ out:
 static const char *
 scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len)
 {
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 	unsigned int regions = cdb[7] << 8 | cdb[8];
 
 	trace_seq_printf(p, "regions=%u", (regions - 8) / 16);
@@ -192,7 +192,7 @@ scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len)
 static const char *
 scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len)
 {
-	const char *ret = p->buffer + p->len, *cmd;
+	const char *ret = trace_seq_buffer_ptr(p), *cmd;
 	sector_t lba = 0;
 	u32 alloc_len = 0;
 
@@ -247,7 +247,7 @@ scsi_trace_varlen(struct trace_seq *p, unsigned char *cdb, int len)
 static const char *
 scsi_trace_misc(struct trace_seq *p, unsigned char *cdb, int len)
 {
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 
 	trace_seq_printf(p, "-");
 	trace_seq_putc(p, 0);
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index f80908f74ca..521f5838594 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -2549,6 +2549,7 @@ fc_rport_final_delete(struct work_struct *work)
 			fc_flush_devloss(shost);
 		if (!cancel_delayed_work(&rport->dev_loss_work))
 			fc_flush_devloss(shost);
+		cancel_work_sync(&rport->scan_work);
 		spin_lock_irqsave(shost->host_lock, flags);
 		rport->flags &= ~FC_RPORT_DEVLOSS_PENDING;
 	}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 96af195224f..6825eda1114 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -109,6 +109,8 @@ static int sd_suspend_system(struct device *);
 static int sd_suspend_runtime(struct device *);
 static int sd_resume(struct device *);
 static void sd_rescan(struct device *);
+static int sd_init_command(struct scsi_cmnd *SCpnt);
+static void sd_uninit_command(struct scsi_cmnd *SCpnt);
 static int sd_done(struct scsi_cmnd *);
 static int sd_eh_action(struct scsi_cmnd *, int);
 static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer);
@@ -503,6 +505,8 @@ static struct scsi_driver sd_template = {
 		.pm		= &sd_pm_ops,
 	},
 	.rescan			= sd_rescan,
+	.init_command		= sd_init_command,
+	.uninit_command		= sd_uninit_command,
 	.done			= sd_done,
 	.eh_action		= sd_eh_action,
 };
@@ -836,9 +840,9 @@ static int scsi_setup_flush_cmnd(struct scsi_device *sdp, struct request *rq)
 	return scsi_setup_blk_pc_cmnd(sdp, rq);
 }
 
-static void sd_unprep_fn(struct request_queue *q, struct request *rq)
+static void sd_uninit_command(struct scsi_cmnd *SCpnt)
 {
-	struct scsi_cmnd *SCpnt = rq->special;
+	struct request *rq = SCpnt->request;
 
 	if (rq->cmd_flags & REQ_DISCARD)
 		__free_page(rq->completion_data);
@@ -850,18 +854,10 @@ static void sd_unprep_fn(struct request_queue *q, struct request *rq)
 	}
 }
 
-/**
- *	sd_prep_fn - build a scsi (read or write) command from
- *	information in the request structure.
- *	@SCpnt: pointer to mid-level's per scsi command structure that
- *	contains request and into which the scsi command is written
- *
- *	Returns 1 if successful and 0 if error (or cannot be done now).
- **/
-static int sd_prep_fn(struct request_queue *q, struct request *rq)
+static int sd_init_command(struct scsi_cmnd *SCpnt)
 {
-	struct scsi_cmnd *SCpnt;
-	struct scsi_device *sdp = q->queuedata;
+	struct request *rq = SCpnt->request;
+	struct scsi_device *sdp = SCpnt->device;
 	struct gendisk *disk = rq->rq_disk;
 	struct scsi_disk *sdkp;
 	sector_t block = blk_rq_pos(rq);
@@ -883,12 +879,6 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 	} else if (rq->cmd_flags & REQ_FLUSH) {
 		ret = scsi_setup_flush_cmnd(sdp, rq);
 		goto out;
-	} else if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
-		ret = scsi_setup_blk_pc_cmnd(sdp, rq);
-		goto out;
-	} else if (rq->cmd_type != REQ_TYPE_FS) {
-		ret = BLKPREP_KILL;
-		goto out;
 	}
 	ret = scsi_setup_fs_cmnd(sdp, rq);
 	if (ret != BLKPREP_OK)
@@ -900,11 +890,10 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 	 * is used for a killable error condition */
 	ret = BLKPREP_KILL;
 
-	SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, SCpnt,
-					"sd_prep_fn: block=%llu, "
-					"count=%d\n",
-					(unsigned long long)block,
-					this_count));
+	SCSI_LOG_HLQUEUE(1,
+		scmd_printk(KERN_INFO, SCpnt,
+			"%s: block=%llu, count=%d\n",
+			__func__, (unsigned long long)block, this_count));
 
 	if (!sdp || !scsi_device_online(sdp) ||
 	    block + blk_rq_sectors(rq) > get_capacity(disk)) {
@@ -1124,7 +1113,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 	 */
 	ret = BLKPREP_OK;
  out:
-	return scsi_prep_return(q, rq, ret);
+	return ret;
 }
 
 /**
@@ -1686,12 +1675,12 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 						   sshdr.ascq));
 	}
 #endif
+	sdkp->medium_access_timed_out = 0;
+
 	if (driver_byte(result) != DRIVER_SENSE &&
 	    (!sense_valid || sense_deferred))
 		goto out;
 
-	sdkp->medium_access_timed_out = 0;
-
 	switch (sshdr.sense_key) {
 	case HARDWARE_ERROR:
 	case MEDIUM_ERROR:
@@ -2452,7 +2441,10 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer)
 		}
 
 		sdkp->DPOFUA = (data.device_specific & 0x10) != 0;
-		if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) {
+		if (sdp->broken_fua) {
+			sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n");
+			sdkp->DPOFUA = 0;
+		} else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) {
 			sd_first_printk(KERN_NOTICE, sdkp,
 				  "Uses READ/WRITE(6), disabling FUA\n");
 			sdkp->DPOFUA = 0;
@@ -2875,9 +2867,6 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 
 	sd_revalidate_disk(gd);
 
-	blk_queue_prep_rq(sdp->request_queue, sd_prep_fn);
-	blk_queue_unprep_rq(sdp->request_queue, sd_unprep_fn);
-
 	gd->driverfs_dev = &sdp->sdev_gendev;
 	gd->flags = GENHD_FL_EXT_DEVT;
 	if (sdp->removable) {
@@ -3025,8 +3014,6 @@ static int sd_remove(struct device *dev)
 
 	async_synchronize_full_domain(&scsi_sd_pm_domain);
 	async_synchronize_full_domain(&scsi_sd_probe_domain);
-	blk_queue_prep_rq(sdkp->device->request_queue, scsi_prep_fn);
-	blk_queue_unprep_rq(sdkp->device->request_queue, NULL);
 	device_del(&sdkp->dev);
 	del_gendisk(sdkp->disk);
 	sd_shutdown(dev);
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index df5e961484e..53268aaba55 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1653,10 +1653,9 @@ static int sg_start_req(Sg_request *srp, unsigned char *cmd)
 	if (!rq)
 		return -ENOMEM;
 
+	blk_rq_set_block_pc(rq);
 	memcpy(rq->cmd, cmd, hp->cmd_len);
-
 	rq->cmd_len = hp->cmd_len;
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 
 	srp->rq = rq;
 	rq->end_io_data = srp;
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 40d85929aef..93cbd36c990 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -79,6 +79,7 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_WORM);
 static DEFINE_MUTEX(sr_mutex);
 static int sr_probe(struct device *);
 static int sr_remove(struct device *);
+static int sr_init_command(struct scsi_cmnd *SCpnt);
 static int sr_done(struct scsi_cmnd *);
 static int sr_runtime_suspend(struct device *dev);
 
@@ -94,6 +95,7 @@ static struct scsi_driver sr_template = {
 		.remove		= sr_remove,
 		.pm		= &sr_pm_ops,
 	},
+	.init_command		= sr_init_command,
 	.done			= sr_done,
 };
 
@@ -378,21 +380,14 @@ static int sr_done(struct scsi_cmnd *SCpnt)
 	return good_bytes;
 }
 
-static int sr_prep_fn(struct request_queue *q, struct request *rq)
+static int sr_init_command(struct scsi_cmnd *SCpnt)
 {
 	int block = 0, this_count, s_size;
 	struct scsi_cd *cd;
-	struct scsi_cmnd *SCpnt;
-	struct scsi_device *sdp = q->queuedata;
+	struct request *rq = SCpnt->request;
+	struct scsi_device *sdp = SCpnt->device;
 	int ret;
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
-		ret = scsi_setup_blk_pc_cmnd(sdp, rq);
-		goto out;
-	} else if (rq->cmd_type != REQ_TYPE_FS) {
-		ret = BLKPREP_KILL;
-		goto out;
-	}
 	ret = scsi_setup_fs_cmnd(sdp, rq);
 	if (ret != BLKPREP_OK)
 		goto out;
@@ -517,7 +512,7 @@ static int sr_prep_fn(struct request_queue *q, struct request *rq)
 	 */
 	ret = BLKPREP_OK;
  out:
-	return scsi_prep_return(q, rq, ret);
+	return ret;
 }
 
 static int sr_block_open(struct block_device *bdev, fmode_t mode)
@@ -718,7 +713,6 @@ static int sr_probe(struct device *dev)
 
 	/* FIXME: need to handle a get_capabilities failure properly ?? */
 	get_capabilities(cd);
-	blk_queue_prep_rq(sdev->request_queue, sr_prep_fn);
 	sr_vendor_init(cd);
 
 	disk->driverfs_dev = &sdev->sdev_gendev;
@@ -993,7 +987,6 @@ static int sr_remove(struct device *dev)
 
 	scsi_autopm_get_device(cd->device);
 
-	blk_queue_prep_rq(cd->device->request_queue, scsi_prep_fn);
 	del_gendisk(cd->disk);
 
 	mutex_lock(&sr_ref_mutex);
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index afc834e172c..14eb4b256a0 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -484,7 +484,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
 	if (!req)
 		return DRIVER_ERROR << 24;
 
-	req->cmd_type = REQ_TYPE_BLOCK_PC;
+	blk_rq_set_block_pc(req);
 	req->cmd_flags |= REQ_QUIET;
 
 	mdata->null_mapped = 1;
diff --git a/drivers/scsi/sun3_NCR5380.c b/drivers/scsi/sun3_NCR5380.c
index 636bbe0ea84..88220794cc9 100644
--- a/drivers/scsi/sun3_NCR5380.c
+++ b/drivers/scsi/sun3_NCR5380.c
@@ -364,7 +364,7 @@ static int is_lun_busy(struct scsi_cmnd *cmd, int should_be_tagged)
 	return( 0 );
     if (TagAlloc[cmd->device->id][cmd->device->lun].nr_allocated >=
 	TagAlloc[cmd->device->id][cmd->device->lun].queue_size ) {
-	TAG_PRINTK( "scsi%d: target %d lun %d: no free tags\n",
+	dprintk(NDEBUG_TAGS,  "scsi%d: target %d lun %d: no free tags\n",
 		    H_NO(cmd), cmd->device->id, cmd->device->lun );
 	return( 1 );
     }
@@ -388,7 +388,7 @@ static void cmd_get_tag(struct scsi_cmnd *cmd, int should_be_tagged)
 	!setup_use_tagged_queuing || !cmd->device->tagged_supported) {
 	cmd->tag = TAG_NONE;
 	hostdata->busy[cmd->device->id] |= (1 << cmd->device->lun);
-	TAG_PRINTK( "scsi%d: target %d lun %d now allocated by untagged "
+	dprintk(NDEBUG_TAGS,  "scsi%d: target %d lun %d now allocated by untagged "
 		    "command\n", H_NO(cmd), cmd->device->id, cmd->device->lun );
     }
     else {
@@ -397,7 +397,7 @@ static void cmd_get_tag(struct scsi_cmnd *cmd, int should_be_tagged)
 	cmd->tag = find_first_zero_bit( &ta->allocated, MAX_TAGS );
 	set_bit( cmd->tag, &ta->allocated );
 	ta->nr_allocated++;
-	TAG_PRINTK( "scsi%d: using tag %d for target %d lun %d "
+	dprintk(NDEBUG_TAGS,  "scsi%d: using tag %d for target %d lun %d "
 		    "(now %d tags in use)\n",
 		    H_NO(cmd), cmd->tag, cmd->device->id, cmd->device->lun,
 		    ta->nr_allocated );
@@ -415,7 +415,7 @@ static void cmd_free_tag(struct scsi_cmnd *cmd)
 
     if (cmd->tag == TAG_NONE) {
 	hostdata->busy[cmd->device->id] &= ~(1 << cmd->device->lun);
-	TAG_PRINTK( "scsi%d: target %d lun %d untagged cmd finished\n",
+	dprintk(NDEBUG_TAGS,  "scsi%d: target %d lun %d untagged cmd finished\n",
 		    H_NO(cmd), cmd->device->id, cmd->device->lun );
     }
     else if (cmd->tag >= MAX_TAGS) {
@@ -426,7 +426,7 @@ static void cmd_free_tag(struct scsi_cmnd *cmd)
 	TAG_ALLOC *ta = &TagAlloc[cmd->device->id][cmd->device->lun];
 	clear_bit( cmd->tag, &ta->allocated );
 	ta->nr_allocated--;
-	TAG_PRINTK( "scsi%d: freed tag %d for target %d lun %d\n",
+	dprintk(NDEBUG_TAGS,  "scsi%d: freed tag %d for target %d lun %d\n",
 		    H_NO(cmd), cmd->tag, cmd->device->id, cmd->device->lun );
     }
 }
@@ -484,7 +484,7 @@ static __inline__ void initialize_SCp(struct scsi_cmnd *cmd)
 
 #include <linux/delay.h>
 
-#if 1
+#if NDEBUG
 static struct {
     unsigned char mask;
     const char * name;} 
@@ -572,12 +572,6 @@ static void NCR5380_print_phase(struct Scsi_Host *instance)
     }
 }
 
-#else /* !NDEBUG */
-
-/* dummies... */
-__inline__ void NCR5380_print(struct Scsi_Host *instance) { };
-__inline__ void NCR5380_print_phase(struct Scsi_Host *instance) { };
-
 #endif
 
 /*
@@ -618,7 +612,7 @@ static inline void NCR5380_all_init (void)
 {
     static int done = 0;
     if (!done) {
-	INI_PRINTK("scsi : NCR5380_all_init()\n");
+	dprintk(NDEBUG_INIT, "scsi : NCR5380_all_init()\n");
 	done = 1;
     }
 }
@@ -681,8 +675,8 @@ static void NCR5380_print_status(struct Scsi_Host *instance)
 	Scsi_Cmnd *ptr;
 	unsigned long flags;
 
-	NCR_PRINT(NDEBUG_ANY);
-	NCR_PRINT_PHASE(NDEBUG_ANY);
+	NCR5380_dprint(NDEBUG_ANY, instance);
+	NCR5380_dprint_phase(NDEBUG_ANY, instance);
 
 	hostdata = (struct NCR5380_hostdata *)instance->hostdata;
 
@@ -928,7 +922,7 @@ static int NCR5380_queue_command_lck(struct scsi_cmnd *cmd,
 
     local_irq_restore(flags);
 
-    QU_PRINTK("scsi%d: command added to %s of queue\n", H_NO(cmd),
+    dprintk(NDEBUG_QUEUES, "scsi%d: command added to %s of queue\n", H_NO(cmd),
 	      (cmd->cmnd[0] == REQUEST_SENSE) ? "head" : "tail");
 
     /* If queue_command() is called from an interrupt (real one or bottom
@@ -998,7 +992,7 @@ static void NCR5380_main (struct work_struct *bl)
 	done = 1;
 	
 	if (!hostdata->connected) {
-	    MAIN_PRINTK( "scsi%d: not connected\n", HOSTNO );
+	    dprintk(NDEBUG_MAIN,  "scsi%d: not connected\n", HOSTNO );
 	    /*
 	     * Search through the issue_queue for a command destined
 	     * for a target that's not busy.
@@ -1012,12 +1006,8 @@ static void NCR5380_main (struct work_struct *bl)
 	    for (tmp = (struct scsi_cmnd *) hostdata->issue_queue,
 		 prev = NULL; tmp; prev = tmp, tmp = NEXT(tmp) ) {
 
-#if (NDEBUG & NDEBUG_LISTS)
 		if (prev != tmp)
-		    printk("MAIN tmp=%p   target=%d   busy=%d lun=%d\n",
-			   tmp, tmp->target, hostdata->busy[tmp->target],
-			   tmp->lun);
-#endif
+			dprintk(NDEBUG_LISTS, "MAIN tmp=%p   target=%d   busy=%d lun=%d\n", tmp, tmp->device->id, hostdata->busy[tmp->device->id], tmp->device->lun);
 		/*  When we find one, remove it from the issue queue. */
 		/* ++guenther: possible race with Falcon locking */
 		if (
@@ -1047,9 +1037,9 @@ static void NCR5380_main (struct work_struct *bl)
 		     * On failure, we must add the command back to the
 		     *   issue queue so we can keep trying.	
 		     */
-		    MAIN_PRINTK("scsi%d: main(): command for target %d "
+		    dprintk(NDEBUG_MAIN, "scsi%d: main(): command for target %d "
 				"lun %d removed from issue_queue\n",
-				HOSTNO, tmp->target, tmp->lun);
+				HOSTNO, tmp->device->id, tmp->device->lun);
 		    /* 
 		     * REQUEST SENSE commands are issued without tagged
 		     * queueing, even on SCSI-II devices because the 
@@ -1076,7 +1066,7 @@ static void NCR5380_main (struct work_struct *bl)
 			cmd_free_tag( tmp );
 #endif
 			local_irq_restore(flags);
-			MAIN_PRINTK("scsi%d: main(): select() failed, "
+			dprintk(NDEBUG_MAIN, "scsi%d: main(): select() failed, "
 				    "returned to issue_queue\n", HOSTNO);
 			if (hostdata->connected)
 			    break;
@@ -1090,10 +1080,10 @@ static void NCR5380_main (struct work_struct *bl)
 #endif
 	    ) {
 	    local_irq_restore(flags);
-	    MAIN_PRINTK("scsi%d: main: performing information transfer\n",
+	    dprintk(NDEBUG_MAIN, "scsi%d: main: performing information transfer\n",
 			HOSTNO);
 	    NCR5380_information_transfer(instance);
-	    MAIN_PRINTK("scsi%d: main: done set false\n", HOSTNO);
+	    dprintk(NDEBUG_MAIN, "scsi%d: main: done set false\n", HOSTNO);
 	    done = 0;
 	}
     } while (!done);
@@ -1130,7 +1120,7 @@ static void NCR5380_dma_complete( struct Scsi_Host *instance )
 	return;
     }
 
-    DMA_PRINTK("scsi%d: real DMA transfer complete, basr 0x%X, sr 0x%X\n",
+    dprintk(NDEBUG_DMA, "scsi%d: real DMA transfer complete, basr 0x%X, sr 0x%X\n",
 	       HOSTNO, NCR5380_read(BUS_AND_STATUS_REG),
 	       NCR5380_read(STATUS_REG));
 
@@ -1189,27 +1179,27 @@ static irqreturn_t NCR5380_intr (int irq, void *dev_id)
     int done = 1, handled = 0;
     unsigned char basr;
 
-    INT_PRINTK("scsi%d: NCR5380 irq triggered\n", HOSTNO);
+    dprintk(NDEBUG_INTR, "scsi%d: NCR5380 irq triggered\n", HOSTNO);
 
     /* Look for pending interrupts */
     basr = NCR5380_read(BUS_AND_STATUS_REG);
-    INT_PRINTK("scsi%d: BASR=%02x\n", HOSTNO, basr);
+    dprintk(NDEBUG_INTR, "scsi%d: BASR=%02x\n", HOSTNO, basr);
     /* dispatch to appropriate routine if found and done=0 */
     if (basr & BASR_IRQ) {
-	NCR_PRINT(NDEBUG_INTR);
+	NCR5380_dprint(NDEBUG_INTR, instance);
 	if ((NCR5380_read(STATUS_REG) & (SR_SEL|SR_IO)) == (SR_SEL|SR_IO)) {
 	    done = 0;
 //	    ENABLE_IRQ();
-	    INT_PRINTK("scsi%d: SEL interrupt\n", HOSTNO);
+	    dprintk(NDEBUG_INTR, "scsi%d: SEL interrupt\n", HOSTNO);
 	    NCR5380_reselect(instance);
 	    (void) NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 	}
 	else if (basr & BASR_PARITY_ERROR) {
-	    INT_PRINTK("scsi%d: PARITY interrupt\n", HOSTNO);
+	    dprintk(NDEBUG_INTR, "scsi%d: PARITY interrupt\n", HOSTNO);
 	    (void) NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 	}
 	else if ((NCR5380_read(STATUS_REG) & SR_RST) == SR_RST) {
-	    INT_PRINTK("scsi%d: RESET interrupt\n", HOSTNO);
+	    dprintk(NDEBUG_INTR, "scsi%d: RESET interrupt\n", HOSTNO);
 	    (void)NCR5380_read(RESET_PARITY_INTERRUPT_REG);
 	}
 	else {
@@ -1229,7 +1219,7 @@ static irqreturn_t NCR5380_intr (int irq, void *dev_id)
 		((basr & BASR_END_DMA_TRANSFER) || 
 		 !(basr & BASR_PHASE_MATCH))) {
 		    
-		INT_PRINTK("scsi%d: PHASE MISM or EOP interrupt\n", HOSTNO);
+		dprintk(NDEBUG_INTR, "scsi%d: PHASE MISM or EOP interrupt\n", HOSTNO);
 		NCR5380_dma_complete( instance );
 		done = 0;
 //		ENABLE_IRQ();
@@ -1238,7 +1228,7 @@ static irqreturn_t NCR5380_intr (int irq, void *dev_id)
 	    {
 /* MS: Ignore unknown phase mismatch interrupts (caused by EOP interrupt) */
 		if (basr & BASR_PHASE_MATCH)
-		   INT_PRINTK("scsi%d: unknown interrupt, "
+		   dprintk(NDEBUG_INTR, "scsi%d: unknown interrupt, "
 			   "BASR 0x%x, MR 0x%x, SR 0x%x\n",
 			   HOSTNO, basr, NCR5380_read(MODE_REG),
 			   NCR5380_read(STATUS_REG));
@@ -1262,7 +1252,7 @@ static irqreturn_t NCR5380_intr (int irq, void *dev_id)
     }
     
     if (!done) {
-	INT_PRINTK("scsi%d: in int routine, calling main\n", HOSTNO);
+	dprintk(NDEBUG_INTR, "scsi%d: in int routine, calling main\n", HOSTNO);
 	/* Put a call to NCR5380_main() on the queue... */
 	queue_main();
     }
@@ -1338,8 +1328,8 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
     unsigned long flags;
 
     hostdata->restart_select = 0;
-    NCR_PRINT(NDEBUG_ARBITRATION);
-    ARB_PRINTK("scsi%d: starting arbitration, id = %d\n", HOSTNO,
+    NCR5380_dprint(NDEBUG_ARBITRATION, instance);
+    dprintk(NDEBUG_ARBITRATION, "scsi%d: starting arbitration, id = %d\n", HOSTNO,
 	       instance->this_id);
 
     /* 
@@ -1385,7 +1375,7 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
 	 && !hostdata->connected);
 #endif
 
-    ARB_PRINTK("scsi%d: arbitration complete\n", HOSTNO);
+    dprintk(NDEBUG_ARBITRATION, "scsi%d: arbitration complete\n", HOSTNO);
 
     if (hostdata->connected) {
 	NCR5380_write(MODE_REG, MR_BASE); 
@@ -1406,7 +1396,7 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
 	(NCR5380_read(INITIATOR_COMMAND_REG) & ICR_ARBITRATION_LOST) ||
 	hostdata->connected) {
 	NCR5380_write(MODE_REG, MR_BASE); 
-	ARB_PRINTK("scsi%d: lost arbitration, deasserting MR_ARBITRATE\n",
+	dprintk(NDEBUG_ARBITRATION, "scsi%d: lost arbitration, deasserting MR_ARBITRATE\n",
 		   HOSTNO);
 	return -1;
     }
@@ -1421,7 +1411,7 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
 	hostdata->connected) {
 	NCR5380_write(MODE_REG, MR_BASE);
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
-	ARB_PRINTK("scsi%d: lost arbitration, deasserting ICR_ASSERT_SEL\n",
+	dprintk(NDEBUG_ARBITRATION, "scsi%d: lost arbitration, deasserting ICR_ASSERT_SEL\n",
 		   HOSTNO);
 	return -1;
     }
@@ -1444,7 +1434,7 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
 	return -1;
     }
 
-    ARB_PRINTK("scsi%d: won arbitration\n", HOSTNO);
+    dprintk(NDEBUG_ARBITRATION, "scsi%d: won arbitration\n", HOSTNO);
 
     /* 
      * Now that we have won arbitration, start Selection process, asserting 
@@ -1504,7 +1494,7 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
 
     udelay(1);
 
-    SEL_PRINTK("scsi%d: selecting target %d\n", HOSTNO, cmd->device->id);
+    dprintk(NDEBUG_SELECTION, "scsi%d: selecting target %d\n", HOSTNO, cmd->device->id);
 
     /* 
      * The SCSI specification calls for a 250 ms timeout for the actual 
@@ -1559,7 +1549,7 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
 	    printk(KERN_ERR "scsi%d: weirdness\n", HOSTNO);
 	    if (hostdata->restart_select)
 		printk(KERN_NOTICE "\trestart select\n");
-	    NCR_PRINT(NDEBUG_ANY);
+	    NCR5380_dprint(NDEBUG_ANY, instance);
 	    NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
 	    return -1;
 	}
@@ -1572,7 +1562,7 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
 #endif
 	cmd->scsi_done(cmd);
 	NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
-	SEL_PRINTK("scsi%d: target did not respond within 250ms\n", HOSTNO);
+	dprintk(NDEBUG_SELECTION, "scsi%d: target did not respond within 250ms\n", HOSTNO);
 	NCR5380_write(SELECT_ENABLE_REG, hostdata->id_mask);
 	return 0;
     } 
@@ -1597,7 +1587,7 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
     /* Wait for start of REQ/ACK handshake */
     while (!(NCR5380_read(STATUS_REG) & SR_REQ));
 
-    SEL_PRINTK("scsi%d: target %d selected, going into MESSAGE OUT phase.\n",
+    dprintk(NDEBUG_SELECTION, "scsi%d: target %d selected, going into MESSAGE OUT phase.\n",
 	       HOSTNO, cmd->device->id);
     tmp[0] = IDENTIFY(1, cmd->device->lun);
 
@@ -1617,7 +1607,7 @@ static int NCR5380_select(struct Scsi_Host *instance, struct scsi_cmnd *cmd,
     data = tmp;
     phase = PHASE_MSGOUT;
     NCR5380_transfer_pio(instance, &phase, &len, &data);
-    SEL_PRINTK("scsi%d: nexus established.\n", HOSTNO);
+    dprintk(NDEBUG_SELECTION, "scsi%d: nexus established.\n", HOSTNO);
     /* XXX need to handle errors here */
     hostdata->connected = cmd;
 #ifndef SUPPORT_TAGS
@@ -1680,12 +1670,12 @@ static int NCR5380_transfer_pio( struct Scsi_Host *instance,
 	 */
 	while (!((tmp = NCR5380_read(STATUS_REG)) & SR_REQ));
 
-	HSH_PRINTK("scsi%d: REQ detected\n", HOSTNO);
+	dprintk(NDEBUG_HANDSHAKE, "scsi%d: REQ detected\n", HOSTNO);
 
 	/* Check for phase mismatch */	
 	if ((tmp & PHASE_MASK) != p) {
-	    PIO_PRINTK("scsi%d: phase mismatch\n", HOSTNO);
-	    NCR_PRINT_PHASE(NDEBUG_PIO);
+	    dprintk(NDEBUG_PIO, "scsi%d: phase mismatch\n", HOSTNO);
+	    NCR5380_dprint_phase(NDEBUG_PIO, instance);
 	    break;
 	}
 
@@ -1708,24 +1698,24 @@ static int NCR5380_transfer_pio( struct Scsi_Host *instance,
 	    if (!((p & SR_MSG) && c > 1)) {
 		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | 
 		    ICR_ASSERT_DATA);
-		NCR_PRINT(NDEBUG_PIO);
+		NCR5380_dprint(NDEBUG_PIO, instance);
 		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | 
 			ICR_ASSERT_DATA | ICR_ASSERT_ACK);
 	    } else {
 		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE |
 		    ICR_ASSERT_DATA | ICR_ASSERT_ATN);
-		NCR_PRINT(NDEBUG_PIO);
+		NCR5380_dprint(NDEBUG_PIO, instance);
 		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | 
 		    ICR_ASSERT_DATA | ICR_ASSERT_ATN | ICR_ASSERT_ACK);
 	    }
 	} else {
-	    NCR_PRINT(NDEBUG_PIO);
+	    NCR5380_dprint(NDEBUG_PIO, instance);
 	    NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_ACK);
 	}
 
 	while (NCR5380_read(STATUS_REG) & SR_REQ);
 
-	HSH_PRINTK("scsi%d: req false, handshake complete\n", HOSTNO);
+	dprintk(NDEBUG_HANDSHAKE, "scsi%d: req false, handshake complete\n", HOSTNO);
 
 /*
  * We have several special cases to consider during REQ/ACK handshaking : 
@@ -1746,7 +1736,7 @@ static int NCR5380_transfer_pio( struct Scsi_Host *instance,
 	} 
     } while (--c);
 
-    PIO_PRINTK("scsi%d: residual %d\n", HOSTNO, c);
+    dprintk(NDEBUG_PIO, "scsi%d: residual %d\n", HOSTNO, c);
 
     *count = c;
     *data = d;
@@ -1854,7 +1844,7 @@ static int NCR5380_transfer_dma( struct Scsi_Host *instance,
     }
     hostdata->dma_len = c;
 
-    DMA_PRINTK("scsi%d: initializing DMA for %s, %d bytes %s %p\n",
+    dprintk(NDEBUG_DMA, "scsi%d: initializing DMA for %s, %d bytes %s %p\n",
 	       HOSTNO, (p & SR_IO) ? "reading" : "writing",
 	       c, (p & SR_IO) ? "to" : "from", *data);
 
@@ -1931,7 +1921,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 	    phase = (tmp & PHASE_MASK); 
  	    if (phase != old_phase) {
 		old_phase = phase;
-		NCR_PRINT_PHASE(NDEBUG_INFORMATION);
+		NCR5380_dprint_phase(NDEBUG_INFORMATION, instance);
 	    }
 
 	    if(phase == PHASE_CMDOUT) {
@@ -1996,7 +1986,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 		    --cmd->SCp.buffers_residual;
 		    cmd->SCp.this_residual = cmd->SCp.buffer->length;
 		    cmd->SCp.ptr = SGADDR(cmd->SCp.buffer);
-		    INF_PRINTK("scsi%d: %d bytes and %d buffers left\n",
+		    dprintk(NDEBUG_INFORMATION, "scsi%d: %d bytes and %d buffers left\n",
 			       HOSTNO, cmd->SCp.this_residual,
 			       cmd->SCp.buffers_residual);
 		}
@@ -2088,7 +2078,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 		    /* Accept message by clearing ACK */
 		    NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 		    
-		    LNK_PRINTK("scsi%d: target %d lun %d linked command "
+		    dprintk(NDEBUG_LINKED, "scsi%d: target %d lun %d linked command "
 			       "complete.\n", HOSTNO, cmd->device->id, cmd->device->lun);
 
 		    /* Enable reselect interrupts */
@@ -2113,7 +2103,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 		     * and don't free it! */
 		    cmd->next_link->tag = cmd->tag;
 		    cmd->result = cmd->SCp.Status | (cmd->SCp.Message << 8); 
-		    LNK_PRINTK("scsi%d: target %d lun %d linked request "
+		    dprintk(NDEBUG_LINKED, "scsi%d: target %d lun %d linked request "
 			       "done, calling scsi_done().\n",
 			       HOSTNO, cmd->device->id, cmd->device->lun);
 #ifdef NCR5380_STATS
@@ -2128,7 +2118,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 		    /* Accept message by clearing ACK */
 		    NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 		    hostdata->connected = NULL;
-		    QU_PRINTK("scsi%d: command for target %d, lun %d "
+		    dprintk(NDEBUG_QUEUES, "scsi%d: command for target %d, lun %d "
 			      "completed\n", HOSTNO, cmd->device->id, cmd->device->lun);
 #ifdef SUPPORT_TAGS
 		    cmd_free_tag( cmd );
@@ -2142,7 +2132,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 			/* ++Andreas: the mid level code knows about
 			   QUEUE_FULL now. */
 			TAG_ALLOC *ta = &TagAlloc[cmd->device->id][cmd->device->lun];
-			TAG_PRINTK("scsi%d: target %d lun %d returned "
+			dprintk(NDEBUG_TAGS, "scsi%d: target %d lun %d returned "
 				   "QUEUE_FULL after %d commands\n",
 				   HOSTNO, cmd->device->id, cmd->device->lun,
 				   ta->nr_allocated);
@@ -2186,7 +2176,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 		    if ((cmd->cmnd[0] != REQUEST_SENSE) && 
 			(status_byte(cmd->SCp.Status) == CHECK_CONDITION)) {
 			scsi_eh_prep_cmnd(cmd, &hostdata->ses, NULL, 0, ~0);
-			ASEN_PRINTK("scsi%d: performing request sense\n",
+			dprintk(NDEBUG_AUTOSENSE, "scsi%d: performing request sense\n",
 				    HOSTNO);
 			/* this is initialized from initialize_SCp 
 			cmd->SCp.buffer = NULL;
@@ -2198,7 +2188,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 			SET_NEXT(cmd, hostdata->issue_queue);
 		        hostdata->issue_queue = (struct scsi_cmnd *) cmd;
 		        local_irq_restore(flags);
-			QU_PRINTK("scsi%d: REQUEST SENSE added to head of "
+			dprintk(NDEBUG_QUEUES, "scsi%d: REQUEST SENSE added to head of "
 				  "issue queue\n", H_NO(cmd));
 		   } else
 #endif /* def AUTOSENSE */
@@ -2238,7 +2228,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 			cmd->device->tagged_supported = 0;
 			hostdata->busy[cmd->device->id] |= (1 << cmd->device->lun);
 			cmd->tag = TAG_NONE;
-			TAG_PRINTK("scsi%d: target %d lun %d rejected "
+			dprintk(NDEBUG_TAGS, "scsi%d: target %d lun %d rejected "
 				   "QUEUE_TAG message; tagged queuing "
 				   "disabled\n",
 				   HOSTNO, cmd->device->id, cmd->device->lun);
@@ -2255,7 +2245,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 		    hostdata->connected = NULL;
 		    hostdata->disconnected_queue = cmd;
 		    local_irq_restore(flags);
-		    QU_PRINTK("scsi%d: command for target %d lun %d was "
+		    dprintk(NDEBUG_QUEUES, "scsi%d: command for target %d lun %d was "
 			      "moved from connected to the "
 			      "disconnected_queue\n", HOSTNO, 
 			      cmd->device->id, cmd->device->lun);
@@ -2308,13 +2298,13 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 		    /* Accept first byte by clearing ACK */
 		    NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 
-		    EXT_PRINTK("scsi%d: receiving extended message\n", HOSTNO);
+		    dprintk(NDEBUG_EXTENDED, "scsi%d: receiving extended message\n", HOSTNO);
 
 		    len = 2;
 		    data = extended_msg + 1;
 		    phase = PHASE_MSGIN;
 		    NCR5380_transfer_pio(instance, &phase, &len, &data);
-		    EXT_PRINTK("scsi%d: length=%d, code=0x%02x\n", HOSTNO,
+		    dprintk(NDEBUG_EXTENDED, "scsi%d: length=%d, code=0x%02x\n", HOSTNO,
 			       (int)extended_msg[1], (int)extended_msg[2]);
 
 		    if (!len && extended_msg[1] <= 
@@ -2326,7 +2316,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 			phase = PHASE_MSGIN;
 
 			NCR5380_transfer_pio(instance, &phase, &len, &data);
-			EXT_PRINTK("scsi%d: message received, residual %d\n",
+			dprintk(NDEBUG_EXTENDED, "scsi%d: message received, residual %d\n",
 				   HOSTNO, len);
 
 			switch (extended_msg[2]) {
@@ -2416,7 +2406,7 @@ static void NCR5380_information_transfer (struct Scsi_Host *instance)
 		break;
 	    default:
 		printk("scsi%d: unknown phase\n", HOSTNO);
-		NCR_PRINT(NDEBUG_ANY);
+		NCR5380_dprint(NDEBUG_ANY, instance);
 	    } /* switch(phase) */
 	} /* if (tmp * SR_REQ) */ 
     } /* while (1) */
@@ -2458,7 +2448,7 @@ static void NCR5380_reselect (struct Scsi_Host *instance)
 
     target_mask = NCR5380_read(CURRENT_SCSI_DATA_REG) & ~(hostdata->id_mask);
 
-    RSL_PRINTK("scsi%d: reselect\n", HOSTNO);
+    dprintk(NDEBUG_RESELECTION, "scsi%d: reselect\n", HOSTNO);
 
     /* 
      * At this point, we have detected that our SCSI ID is on the bus,
@@ -2580,14 +2570,14 @@ static void NCR5380_reselect (struct Scsi_Host *instance)
 	if (!NCR5380_transfer_pio(instance, &phase, &len, &data) &&
 	    msg[1] == SIMPLE_QUEUE_TAG)
 	    tag = msg[2];
-	TAG_PRINTK("scsi%d: target mask %02x, lun %d sent tag %d at "
+	dprintk(NDEBUG_TAGS, "scsi%d: target mask %02x, lun %d sent tag %d at "
 		   "reselection\n", HOSTNO, target_mask, lun, tag);
     }
 #endif
     
     hostdata->connected = tmp;
-    RSL_PRINTK("scsi%d: nexus established, target = %d, lun = %d, tag = %d\n",
-	       HOSTNO, tmp->target, tmp->lun, tmp->tag);
+    dprintk(NDEBUG_RESELECTION, "scsi%d: nexus established, target = %d, lun = %d, tag = %d\n",
+	       HOSTNO, tmp->device->id, tmp->device->lun, tmp->tag);
 }
 
 
@@ -2622,7 +2612,7 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 
     local_irq_save(flags);
     
-    ABRT_PRINTK("scsi%d: abort called basr 0x%02x, sr 0x%02x\n", HOSTNO,
+    dprintk(NDEBUG_ABORT, "scsi%d: abort called basr 0x%02x, sr 0x%02x\n", HOSTNO,
 		NCR5380_read(BUS_AND_STATUS_REG),
 		NCR5380_read(STATUS_REG));
 
@@ -2635,7 +2625,7 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 
     if (hostdata->connected == cmd) {
 
-	ABRT_PRINTK("scsi%d: aborting connected command\n", HOSTNO);
+	dprintk(NDEBUG_ABORT, "scsi%d: aborting connected command\n", HOSTNO);
 /*
  * We should perform BSY checking, and make sure we haven't slipped
  * into BUS FREE.
@@ -2664,11 +2654,11 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 #endif
 	  local_irq_restore(flags);
 	  cmd->scsi_done(cmd);
-	  return SCSI_ABORT_SUCCESS;
+	  return SUCCESS;
 	} else {
 /*	  local_irq_restore(flags); */
 	  printk("scsi%d: abort of connected command failed!\n", HOSTNO);
-	  return SCSI_ABORT_ERROR;
+	  return FAILED;
 	} 
    }
 #endif
@@ -2686,12 +2676,12 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 	    SET_NEXT(tmp, NULL);
 	    tmp->result = DID_ABORT << 16;
 	    local_irq_restore(flags);
-	    ABRT_PRINTK("scsi%d: abort removed command from issue queue.\n",
+	    dprintk(NDEBUG_ABORT, "scsi%d: abort removed command from issue queue.\n",
 			HOSTNO);
 	    /* Tagged queuing note: no tag to free here, hasn't been assigned
 	     * yet... */
 	    tmp->scsi_done(tmp);
-	    return SCSI_ABORT_SUCCESS;
+	    return SUCCESS;
 	}
 
 /* 
@@ -2707,8 +2697,8 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 
     if (hostdata->connected) {
 	local_irq_restore(flags);
-	ABRT_PRINTK("scsi%d: abort failed, command connected.\n", HOSTNO);
-        return SCSI_ABORT_SNOOZE;
+	dprintk(NDEBUG_ABORT, "scsi%d: abort failed, command connected.\n", HOSTNO);
+        return FAILED;
     }
 
 /*
@@ -2740,12 +2730,12 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 	 tmp = NEXT(tmp)) 
         if (cmd == tmp) {
             local_irq_restore(flags);
-	    ABRT_PRINTK("scsi%d: aborting disconnected command.\n", HOSTNO);
+	    dprintk(NDEBUG_ABORT, "scsi%d: aborting disconnected command.\n", HOSTNO);
   
             if (NCR5380_select (instance, cmd, (int) cmd->tag)) 
-		return SCSI_ABORT_BUSY;
+		return FAILED;
 
-	    ABRT_PRINTK("scsi%d: nexus reestablished.\n", HOSTNO);
+	    dprintk(NDEBUG_ABORT, "scsi%d: nexus reestablished.\n", HOSTNO);
 
 	    do_abort (instance);
 
@@ -2769,7 +2759,7 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
 #endif
 		    local_irq_restore(flags);
 		    tmp->scsi_done(tmp);
-		    return SCSI_ABORT_SUCCESS;
+		    return SUCCESS;
 		}
 	}
 
@@ -2786,7 +2776,7 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
     local_irq_restore(flags);
     printk(KERN_INFO "scsi%d: warning : SCSI command probably completed successfully before abortion\n", HOSTNO); 
 
-    return SCSI_ABORT_NOT_RUNNING;
+    return FAILED;
 }
 
 
@@ -2795,7 +2785,7 @@ static int NCR5380_abort(struct scsi_cmnd *cmd)
  * 
  * Purpose : reset the SCSI bus.
  *
- * Returns : SCSI_RESET_WAKEUP
+ * Returns : SUCCESS or FAILURE
  *
  */ 
 
@@ -2804,7 +2794,7 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
     SETUP_HOSTDATA(cmd->device->host);
     int           i;
     unsigned long flags;
-#if 1
+#if defined(RESET_RUN_DONE)
     struct scsi_cmnd *connected, *disconnected_queue;
 #endif
 
@@ -2826,8 +2816,15 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
      * through anymore ... */
     (void)NCR5380_read( RESET_PARITY_INTERRUPT_REG );
 
-#if 1 /* XXX Should now be done by midlevel code, but it's broken XXX */
-      /* XXX see below                                            XXX */
+	/* MSch 20140115 - looking at the generic NCR5380 driver, all of this
+	 * should go.
+	 * Catch-22: if we don't clear all queues, the SCSI driver lock will
+	 * not be released by atari_scsi_reset()!
+	 */
+
+#if defined(RESET_RUN_DONE)
+	/* XXX Should now be done by midlevel code, but it's broken XXX */
+	/* XXX see below                                            XXX */
 
     /* MSch: old-style reset: actually abort all command processing here */
 
@@ -2857,7 +2854,7 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
      */
 
     if ((cmd = connected)) {
-	ABRT_PRINTK("scsi%d: reset aborted a connected command\n", H_NO(cmd));
+	dprintk(NDEBUG_ABORT, "scsi%d: reset aborted a connected command\n", H_NO(cmd));
 	cmd->result = (cmd->result & 0xffff) | (DID_RESET << 16);
 	cmd->scsi_done( cmd );
     }
@@ -2869,14 +2866,14 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
 	cmd->scsi_done( cmd );
     }
     if (i > 0)
-	ABRT_PRINTK("scsi: reset aborted %d disconnected command(s)\n", i);
+	dprintk(NDEBUG_ABORT, "scsi: reset aborted %d disconnected command(s)\n", i);
 
 
     /* since all commands have been explicitly terminated, we need to tell
      * the midlevel code that the reset was SUCCESSFUL, and there is no 
      * need to 'wake up' the commands by a request_sense
      */
-    return SCSI_RESET_SUCCESS | SCSI_RESET_BUS_RESET;
+    return SUCCESS;
 #else /* 1 */
 
     /* MSch: new-style reset handling: let the mid-level do what it can */
@@ -2903,11 +2900,11 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
      */
 
     if (hostdata->issue_queue)
-	ABRT_PRINTK("scsi%d: reset aborted issued command(s)\n", H_NO(cmd));
+	dprintk(NDEBUG_ABORT, "scsi%d: reset aborted issued command(s)\n", H_NO(cmd));
     if (hostdata->connected) 
-	ABRT_PRINTK("scsi%d: reset aborted a connected command\n", H_NO(cmd));
+	dprintk(NDEBUG_ABORT, "scsi%d: reset aborted a connected command\n", H_NO(cmd));
     if (hostdata->disconnected_queue)
-	ABRT_PRINTK("scsi%d: reset aborted disconnected command(s)\n", H_NO(cmd));
+	dprintk(NDEBUG_ABORT, "scsi%d: reset aborted disconnected command(s)\n", H_NO(cmd));
 
     local_irq_save(flags);
     hostdata->issue_queue = NULL;
@@ -2924,7 +2921,7 @@ static int NCR5380_bus_reset(struct scsi_cmnd *cmd)
     local_irq_restore(flags);
 
     /* we did no complete reset of all commands, so a wakeup is required */
-    return SCSI_RESET_WAKEUP | SCSI_RESET_BUS_RESET;
+    return SUCCESS;
 #endif /* 1 */
 }
 
diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index e2c009b033c..9707b7494a8 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -3,6 +3,10 @@
  *
  * Sun3 DMA routines added by Sam Creasey (sammy@sammy.net)
  *
+ * VME support added by Sam Creasey
+ *
+ * TODO: modify this driver to support multiple Sun3 SCSI VME boards
+ *
  * Adapted from mac_scsinew.c:
  */
 /*
@@ -45,10 +49,6 @@
  * USLEEP - enable support for devices that don't disconnect.  Untested.
  */
 
-/*
- * $Log: sun3_NCR5380.c,v $
- */
-
 #define AUTOSENSE
 
 #include <linux/types.h>
@@ -69,23 +69,15 @@
 #include <asm/idprom.h>
 #include <asm/machines.h>
 
-#define NDEBUG 0
-
-#define NDEBUG_ABORT		0x00100000
-#define NDEBUG_TAGS		0x00200000
-#define NDEBUG_MERGING		0x00400000
-
 /* dma on! */
 #define REAL_DMA
 
 #include "scsi.h"
-#include "initio.h"
 #include <scsi/scsi_host.h>
 #include "sun3_scsi.h"
+#include "NCR5380.h"
 
-static void NCR5380_print(struct Scsi_Host *instance);
-
-/* #define OLDDMA */
+extern int sun3_map_test(unsigned long, char *);
 
 #define USE_WRAPPER
 /*#define RESET_BOOT */
@@ -101,7 +93,11 @@ static void NCR5380_print(struct Scsi_Host *instance);
 
 /* #define SUPPORT_TAGS */
 
+#ifdef SUN3_SCSI_VME
+#define ENABLE_IRQ()
+#else
 #define	ENABLE_IRQ()	enable_irq( IRQ_SUN3_SCSI ); 
+#endif
 
 
 static irqreturn_t scsi_sun3_intr(int irq, void *dummy);
@@ -123,6 +119,8 @@ module_param(setup_hostid, int, 0);
 
 static struct scsi_cmnd *sun3_dma_setup_done = NULL;
 
+#define	RESET_RUN_DONE
+
 #define	AFTER_RESET_DELAY	(HZ/2)
 
 /* ms to wait after hitting dma regs */
@@ -136,10 +134,9 @@ static struct scsi_cmnd *sun3_dma_setup_done = NULL;
 
 static volatile unsigned char *sun3_scsi_regp;
 static volatile struct sun3_dma_regs *dregs;
-#ifdef OLDDMA
-static unsigned char *dmabuf = NULL; /* dma memory buffer */
-#endif
+#ifndef SUN3_SCSI_VME
 static struct sun3_udc_regs *udc_regs = NULL;
+#endif
 static unsigned char *sun3_dma_orig_addr = NULL;
 static unsigned long sun3_dma_orig_count = 0;
 static int sun3_dma_active = 0;
@@ -159,6 +156,7 @@ static inline void sun3scsi_write(int reg, int value)
 	sun3_scsi_regp[reg] = value;
 }
 
+#ifndef SUN3_SCSI_VME
 /* dma controller register access functions */
 
 static inline unsigned short sun3_udc_read(unsigned char reg)
@@ -180,6 +178,7 @@ static inline void sun3_udc_write(unsigned short val, unsigned char reg)
 	dregs->udc_data = val;
 	udelay(SUN3_DMA_DELAY);
 }
+#endif
 
 /*
  * XXX: status debug
@@ -198,17 +197,32 @@ static struct Scsi_Host *default_instance;
  *
  */
  
-int __init sun3scsi_detect(struct scsi_host_template * tpnt)
+static int __init sun3scsi_detect(struct scsi_host_template *tpnt)
 {
-	unsigned long ioaddr;
+	unsigned long ioaddr, irq;
 	static int called = 0;
 	struct Scsi_Host *instance;
+#ifdef SUN3_SCSI_VME
+	int i;
+	unsigned long addrs[3] = { IOBASE_SUN3_VMESCSI,
+				   IOBASE_SUN3_VMESCSI + 0x4000,
+				   0 };
+	unsigned long vecs[3] = { SUN3_VEC_VMESCSI0,
+				  SUN3_VEC_VMESCSI1,
+				  0 };
+#endif
 
 	/* check that this machine has an onboard 5380 */
 	switch(idprom->id_machtype) {
+#ifdef SUN3_SCSI_VME
+	case SM_SUN3|SM_3_160:
+	case SM_SUN3|SM_3_260:
+		break;
+#else
 	case SM_SUN3|SM_3_50:
 	case SM_SUN3|SM_3_60:
 		break;
+#endif
 
 	default:
 		return 0;
@@ -217,7 +231,11 @@ int __init sun3scsi_detect(struct scsi_host_template * tpnt)
 	if(called)
 		return 0;
 
+#ifdef SUN3_SCSI_VME
+	tpnt->proc_name = "Sun3 5380 VME SCSI";
+#else
 	tpnt->proc_name = "Sun3 5380 SCSI";
+#endif
 
 	/* setup variables */
 	tpnt->can_queue =
@@ -234,6 +252,38 @@ int __init sun3scsi_detect(struct scsi_host_template * tpnt)
 		tpnt->this_id = 7;
 	}
 
+#ifdef SUN3_SCSI_VME
+	ioaddr = 0;
+	for (i = 0; addrs[i] != 0; i++) {
+		unsigned char x;
+
+		ioaddr = (unsigned long)sun3_ioremap(addrs[i], PAGE_SIZE,
+						     SUN3_PAGE_TYPE_VME16);
+		irq = vecs[i];
+		sun3_scsi_regp = (unsigned char *)ioaddr;
+
+		dregs = (struct sun3_dma_regs *)(((unsigned char *)ioaddr) + 8);
+
+		if (sun3_map_test((unsigned long)dregs, &x)) {
+			unsigned short oldcsr;
+
+			oldcsr = dregs->csr;
+			dregs->csr = 0;
+			udelay(SUN3_DMA_DELAY);
+			if (dregs->csr == 0x1400)
+				break;
+
+			dregs->csr = oldcsr;
+		}
+
+		iounmap((void *)ioaddr);
+		ioaddr = 0;
+	}
+
+	if (!ioaddr)
+		return 0;
+#else
+	irq = IRQ_SUN3_SCSI;
 	ioaddr = (unsigned long)ioremap(IOBASE_SUN3_SCSI, PAGE_SIZE);
 	sun3_scsi_regp = (unsigned char *)ioaddr;
 
@@ -244,11 +294,6 @@ int __init sun3scsi_detect(struct scsi_host_template * tpnt)
 	     printk("SUN3 Scsi couldn't allocate DVMA memory!\n");
 	     return 0;
 	}
-#ifdef OLDDMA
-	if((dmabuf = dvma_malloc_align(SUN3_DVMA_BUFSIZE, 0x10000)) == NULL) {
-	     printk("SUN3 Scsi couldn't allocate DVMA memory!\n");
-	     return 0;
-	}
 #endif
 #ifdef SUPPORT_TAGS
 	if (setup_use_tagged_queuing < 0)
@@ -262,7 +307,7 @@ int __init sun3scsi_detect(struct scsi_host_template * tpnt)
 	default_instance = instance;
 
         instance->io_port = (unsigned long) ioaddr;
-	instance->irq = IRQ_SUN3_SCSI;
+	instance->irq = irq;
 
 	NCR5380_init(instance, 0);
 
@@ -283,7 +328,8 @@ int __init sun3scsi_detect(struct scsi_host_template * tpnt)
 #endif
 	}
 	
-	printk("scsi%d: Sun3 5380 at port %lX irq", instance->host_no, instance->io_port);
+	pr_info("scsi%d: %s at port %lX irq", instance->host_no,
+		tpnt->proc_name, instance->io_port);
 	if (instance->irq == SCSI_IRQ_NONE)
 		printk ("s disabled");
 	else
@@ -300,6 +346,15 @@ int __init sun3scsi_detect(struct scsi_host_template * tpnt)
 	dregs->csr = CSR_SCSI | CSR_FIFO | CSR_INTR;
 	udelay(SUN3_DMA_DELAY);
 	dregs->fifo_count = 0;
+#ifdef SUN3_SCSI_VME
+	dregs->fifo_count_hi = 0;
+	dregs->dma_addr_hi = 0;
+	dregs->dma_addr_lo = 0;
+	dregs->dma_count_hi = 0;
+	dregs->dma_count_lo = 0;
+
+	dregs->ivect = VME_DATA24 | (instance->irq & 0xff);
+#endif
 
 	called = 1;
 
@@ -367,7 +422,8 @@ static void sun3_scsi_reset_boot(struct Scsi_Host *instance)
 }
 #endif
 
-const char * sun3scsi_info (struct Scsi_Host *spnt) {
+static const char *sun3scsi_info(struct Scsi_Host *spnt)
+{
     return "";
 }
 
@@ -379,6 +435,10 @@ static irqreturn_t scsi_sun3_intr(int irq, void *dummy)
 	unsigned short csr = dregs->csr;
 	int handled = 0;
 
+#ifdef SUN3_SCSI_VME
+	dregs->csr &= ~CSR_DMA_ENABLE;
+#endif
+
 	if(csr & ~CSR_GOOD) {
 		if(csr & CSR_DMA_BUSERR) {
 			printk("scsi%d: bus error in dma\n", default_instance->host_no);
@@ -422,31 +482,28 @@ void sun3_sun3_debug (void)
 /* sun3scsi_dma_setup() -- initialize the dma controller for a read/write */
 static unsigned long sun3scsi_dma_setup(void *data, unsigned long count, int write_flag)
 {
-#ifdef OLDDMA
-	if(write_flag) 
-		memcpy(dmabuf, data, count);
-	else {
-		sun3_dma_orig_addr = data;
-		sun3_dma_orig_count = count;
-	}
-#else
 	void *addr;
 
 	if(sun3_dma_orig_addr != NULL)
 		dvma_unmap(sun3_dma_orig_addr);
 
-//	addr = sun3_dvma_page((unsigned long)data, (unsigned long)dmabuf);
+#ifdef SUN3_SCSI_VME
+	addr = (void *)dvma_map_vme((unsigned long) data, count);
+#else
 	addr = (void *)dvma_map((unsigned long) data, count);
+#endif
 		
 	sun3_dma_orig_addr = addr;
 	sun3_dma_orig_count = count;
-#endif
+
+#ifndef SUN3_SCSI_VME
 	dregs->fifo_count = 0;
 	sun3_udc_write(UDC_RESET, UDC_CSR);
 	
 	/* reset fifo */
 	dregs->csr &= ~CSR_FIFO;
 	dregs->csr |= CSR_FIFO;
+#endif
 	
 	/* set direction */
 	if(write_flag)
@@ -454,6 +511,17 @@ static unsigned long sun3scsi_dma_setup(void *data, unsigned long count, int wri
 	else
 		dregs->csr &= ~CSR_SEND;
 	
+#ifdef SUN3_SCSI_VME
+	dregs->csr |= CSR_PACK_ENABLE;
+
+	dregs->dma_addr_hi = ((unsigned long)addr >> 16);
+	dregs->dma_addr_lo = ((unsigned long)addr & 0xffff);
+
+	dregs->dma_count_hi = 0;
+	dregs->dma_count_lo = 0;
+	dregs->fifo_count_hi = 0;
+	dregs->fifo_count = 0;
+#else
 	/* byte count for fifo */
 	dregs->fifo_count = count;
 
@@ -467,17 +535,12 @@ static unsigned long sun3scsi_dma_setup(void *data, unsigned long count, int wri
 		printk("scsi%d: fifo_mismatch %04x not %04x\n",
 		       default_instance->host_no, dregs->fifo_count,
 		       (unsigned int) count);
-		NCR5380_print(default_instance);
+		NCR5380_dprint(NDEBUG_DMA, default_instance);
 	}
 
 	/* setup udc */
-#ifdef OLDDMA
-	udc_regs->addr_hi = ((dvma_vtob(dmabuf) & 0xff0000) >> 8);
-	udc_regs->addr_lo = (dvma_vtob(dmabuf) & 0xffff);
-#else
 	udc_regs->addr_hi = (((unsigned long)(addr) & 0xff0000) >> 8);
 	udc_regs->addr_lo = ((unsigned long)(addr) & 0xffff);
-#endif
 	udc_regs->count = count/2; /* count in words */
 	udc_regs->mode_hi = UDC_MODE_HIWORD;
 	if(write_flag) {
@@ -501,11 +564,13 @@ static unsigned long sun3scsi_dma_setup(void *data, unsigned long count, int wri
 
 	/* interrupt enable */
 	sun3_udc_write(UDC_INT_ENABLE, UDC_CSR);
+#endif
 	
        	return count;
 
 }
 
+#ifndef SUN3_SCSI_VME
 static inline unsigned long sun3scsi_dma_count(struct Scsi_Host *instance)
 {
 	unsigned short resid;
@@ -518,6 +583,7 @@ static inline unsigned long sun3scsi_dma_count(struct Scsi_Host *instance)
 
 	return (unsigned long) resid;
 }
+#endif
 
 static inline unsigned long sun3scsi_dma_residual(struct Scsi_Host *instance)
 {
@@ -536,8 +602,23 @@ static inline unsigned long sun3scsi_dma_xfer_len(unsigned long wanted,
 
 static inline int sun3scsi_dma_start(unsigned long count, unsigned char *data)
 {
+#ifdef SUN3_SCSI_VME
+	unsigned short csr;
+
+	csr = dregs->csr;
 
+	dregs->dma_count_hi = (sun3_dma_orig_count >> 16);
+	dregs->dma_count_lo = (sun3_dma_orig_count & 0xffff);
+
+	dregs->fifo_count_hi = (sun3_dma_orig_count >> 16);
+	dregs->fifo_count = (sun3_dma_orig_count & 0xffff);
+
+/*	if(!(csr & CSR_DMA_ENABLE))
+ *		dregs->csr |= CSR_DMA_ENABLE;
+ */
+#else
     sun3_udc_write(UDC_CHN_START, UDC_CSR);
+#endif
     
     return 0;
 }
@@ -545,12 +626,46 @@ static inline int sun3scsi_dma_start(unsigned long count, unsigned char *data)
 /* clean up after our dma is done */
 static int sun3scsi_dma_finish(int write_flag)
 {
-	unsigned short count;
+	unsigned short __maybe_unused count;
 	unsigned short fifo;
 	int ret = 0;
 	
 	sun3_dma_active = 0;
-#if 1
+
+#ifdef SUN3_SCSI_VME
+	dregs->csr &= ~CSR_DMA_ENABLE;
+
+	fifo = dregs->fifo_count;
+	if (write_flag) {
+		if ((fifo > 0) && (fifo < sun3_dma_orig_count))
+			fifo++;
+	}
+
+	last_residual = fifo;
+	/* empty bytes from the fifo which didn't make it */
+	if ((!write_flag) && (dregs->csr & CSR_LEFT)) {
+		unsigned char *vaddr;
+
+		vaddr = (unsigned char *)dvma_vmetov(sun3_dma_orig_addr);
+
+		vaddr += (sun3_dma_orig_count - fifo);
+		vaddr--;
+
+		switch (dregs->csr & CSR_LEFT) {
+		case CSR_LEFT_3:
+			*vaddr = (dregs->bpack_lo & 0xff00) >> 8;
+			vaddr--;
+
+		case CSR_LEFT_2:
+			*vaddr = (dregs->bpack_hi & 0x00ff);
+			vaddr--;
+
+		case CSR_LEFT_1:
+			*vaddr = (dregs->bpack_hi & 0xff00) >> 8;
+			break;
+		}
+	}
+#else
 	// check to empty the fifo on a read
 	if(!write_flag) {
 		int tmo = 20000; /* .2 sec */
@@ -566,28 +681,8 @@ static int sun3scsi_dma_finish(int write_flag)
 			udelay(10);
 		}
 	}
-		
-#endif
 
 	count = sun3scsi_dma_count(default_instance);
-#ifdef OLDDMA
-
-	/* if we've finished a read, copy out the data we read */
- 	if(sun3_dma_orig_addr) {
-		/* check for residual bytes after dma end */
-		if(count && (NCR5380_read(BUS_AND_STATUS_REG) &
-			     (BASR_PHASE_MATCH | BASR_ACK))) {
-			printk("scsi%d: sun3_scsi_finish: read overrun baby... ", default_instance->host_no);
-			printk("basr now %02x\n", NCR5380_read(BUS_AND_STATUS_REG));
-			ret = count;
-		}
-		
-		/* copy in what we dma'd no matter what */
-		memcpy(sun3_dma_orig_addr, dmabuf, sun3_dma_orig_count);
-		sun3_dma_orig_addr = NULL;
-
-	}
-#else
 
 	fifo = dregs->fifo_count;
 	last_residual = fifo;
@@ -605,10 +700,23 @@ static int sun3scsi_dma_finish(int write_flag)
 		vaddr[-2] = (data & 0xff00) >> 8;
 		vaddr[-1] = (data & 0xff);
 	}
+#endif
 
 	dvma_unmap(sun3_dma_orig_addr);
 	sun3_dma_orig_addr = NULL;
-#endif
+
+#ifdef SUN3_SCSI_VME
+	dregs->dma_addr_hi = 0;
+	dregs->dma_addr_lo = 0;
+	dregs->dma_count_hi = 0;
+	dregs->dma_count_lo = 0;
+
+	dregs->fifo_count = 0;
+	dregs->fifo_count_hi = 0;
+
+	dregs->csr &= ~CSR_SEND;
+/*	dregs->csr |= CSR_DMA_ENABLE; */
+#else
 	sun3_udc_write(UDC_RESET, UDC_CSR);
 	dregs->fifo_count = 0;
 	dregs->csr &= ~CSR_SEND;
@@ -616,6 +724,7 @@ static int sun3scsi_dma_finish(int write_flag)
 	/* reset fifo */
 	dregs->csr &= ~CSR_FIFO;
 	dregs->csr |= CSR_FIFO;
+#endif
 	
 	sun3_dma_setup_done = NULL;
 
diff --git a/drivers/scsi/sun3_scsi.h b/drivers/scsi/sun3_scsi.h
index a8da9c710fe..e96a37cf06a 100644
--- a/drivers/scsi/sun3_scsi.h
+++ b/drivers/scsi/sun3_scsi.h
@@ -29,12 +29,8 @@
  * 1+ (800) 334-5454
  */
 
-/*
- * $Log: cumana_NCR5380.h,v $
- */
-
-#ifndef SUN3_NCR5380_H
-#define SUN3_NCR5380_H
+#ifndef SUN3_SCSI_H
+#define SUN3_SCSI_H
 
 #define SUN3SCSI_PUBLIC_RELEASE 1
 
@@ -82,8 +78,6 @@ static int sun3scsi_release (struct Scsi_Host *);
 #define SUN3_SCSI_NAME "Sun3 NCR5380 SCSI"
 #endif
 
-#ifndef HOSTS_C
-
 #define NCR5380_implementation_fields \
     int port, ctrl
 
@@ -108,9 +102,6 @@ static int sun3scsi_release (struct Scsi_Host *);
 #define NCR5380_dma_read_setup(instance, data, count) sun3scsi_dma_setup(data, count, 0)
 #define NCR5380_dma_residual sun3scsi_dma_residual
 
-#define BOARD_NORMAL	0
-#define BOARD_NCR53C400	1
-
 /* additional registers - mainly DMA control regs */
 /* these start at regbase + 8 -- directly after the NCR regs */
 struct sun3_dma_regs {
@@ -191,189 +182,5 @@ struct sun3_udc_regs {
 
 #define VME_DATA24 0x3d00
 
-// debugging printk's, taken from atari_scsi.h 
-/* Debugging printk definitions:
- *
- *  ARB  -> arbitration
- *  ASEN -> auto-sense
- *  DMA  -> DMA
- *  HSH  -> PIO handshake
- *  INF  -> information transfer
- *  INI  -> initialization
- *  INT  -> interrupt
- *  LNK  -> linked commands
- *  MAIN -> NCR5380_main() control flow
- *  NDAT -> no data-out phase
- *  NWR  -> no write commands
- *  PIO  -> PIO transfers
- *  PDMA -> pseudo DMA (unused on Atari)
- *  QU   -> queues
- *  RSL  -> reselections
- *  SEL  -> selections
- *  USL  -> usleep cpde (unused on Atari)
- *  LBS  -> last byte sent (unused on Atari)
- *  RSS  -> restarting of selections
- *  EXT  -> extended messages
- *  ABRT -> aborting and resetting
- *  TAG  -> queue tag handling
- *  MER  -> merging of consec. buffers
- *
- */
-
-#include "NCR5380.h"
-
-#if NDEBUG & NDEBUG_ARBITRATION
-#define ARB_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define ARB_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_AUTOSENSE
-#define ASEN_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define ASEN_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_DMA
-#define DMA_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define DMA_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_HANDSHAKE
-#define HSH_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define HSH_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_INFORMATION
-#define INF_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define INF_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_INIT
-#define INI_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define INI_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_INTR
-#define INT_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define INT_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_LINKED
-#define LNK_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define LNK_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_MAIN
-#define MAIN_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define MAIN_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_NO_DATAOUT
-#define NDAT_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define NDAT_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_NO_WRITE
-#define NWR_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define NWR_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_PIO
-#define PIO_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define PIO_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_PSEUDO_DMA
-#define PDMA_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define PDMA_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_QUEUES
-#define QU_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define QU_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_RESELECTION
-#define RSL_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define RSL_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_SELECTION
-#define SEL_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define SEL_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_USLEEP
-#define USL_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define USL_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_LAST_BYTE_SENT
-#define LBS_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define LBS_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_RESTART_SELECT
-#define RSS_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define RSS_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_EXTENDED
-#define EXT_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define EXT_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_ABORT
-#define ABRT_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define ABRT_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_TAGS
-#define TAG_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define TAG_PRINTK(format, args...)
-#endif
-#if NDEBUG & NDEBUG_MERGING
-#define MER_PRINTK(format, args...) \
-	printk(KERN_DEBUG format , ## args)
-#else
-#define MER_PRINTK(format, args...)
-#endif
-
-/* conditional macros for NCR5380_print_{,phase,status} */
-
-#define NCR_PRINT(mask)	\
-	((NDEBUG & (mask)) ? NCR5380_print(instance) : (void)0)
-
-#define NCR_PRINT_PHASE(mask) \
-	((NDEBUG & (mask)) ? NCR5380_print_phase(instance) : (void)0)
-
-#define NCR_PRINT_STATUS(mask) \
-	((NDEBUG & (mask)) ? NCR5380_print_status(instance) : (void)0)
-
-
-
-#endif /* ndef HOSTS_C */
-#endif /* SUN3_NCR5380_H */
+#endif /* SUN3_SCSI_H */
 
diff --git a/drivers/scsi/sun3_scsi_vme.c b/drivers/scsi/sun3_scsi_vme.c
index a3dd55d1d2f..1eeece6e204 100644
--- a/drivers/scsi/sun3_scsi_vme.c
+++ b/drivers/scsi/sun3_scsi_vme.c
@@ -1,589 +1,3 @@
- /*
- * Sun3 SCSI stuff by Erik Verbruggen (erik@bigmama.xtdnet.nl)
- *
- * Sun3 DMA routines added by Sam Creasey (sammy@sammy.net)
- *
- * VME support added by Sam Creasey
- *
- * Adapted from sun3_scsi.c -- see there for other headers
- *
- * TODO: modify this driver to support multiple Sun3 SCSI VME boards
- *
- */
-
-#define AUTOSENSE
-
-#include <linux/types.h>
-#include <linux/stddef.h>
-#include <linux/ctype.h>
-#include <linux/delay.h>
-
-#include <linux/module.h>
-#include <linux/signal.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/blkdev.h>
-
-#include <asm/io.h>
-
-#include <asm/sun3ints.h>
-#include <asm/dvma.h>
-#include <asm/idprom.h>
-#include <asm/machines.h>
-
 #define SUN3_SCSI_VME
 
-#undef SUN3_SCSI_DEBUG
-
-/* dma on! */
-#define REAL_DMA
-
-#define NDEBUG 0
-
-#define NDEBUG_ABORT		0x00100000
-#define NDEBUG_TAGS		0x00200000
-#define NDEBUG_MERGING		0x00400000
-
-#include "scsi.h"
-#include "initio.h"
-#include <scsi/scsi_host.h>
-#include "sun3_scsi.h"
-
-extern int sun3_map_test(unsigned long, char *);
-
-#define USE_WRAPPER
-/*#define RESET_BOOT */
-#define DRIVER_SETUP
-
-/*
- * BUG can be used to trigger a strange code-size related hang on 2.1 kernels
- */
-#ifdef BUG
-#undef RESET_BOOT
-#undef DRIVER_SETUP
-#endif
-
-/* #define SUPPORT_TAGS */
-
-//#define	ENABLE_IRQ()	enable_irq( SUN3_VEC_VMESCSI0 ); 
-#define ENABLE_IRQ()
-
-
-static irqreturn_t scsi_sun3_intr(int irq, void *dummy);
-static inline unsigned char sun3scsi_read(int reg);
-static inline void sun3scsi_write(int reg, int value);
-
-static int setup_can_queue = -1;
-module_param(setup_can_queue, int, 0);
-static int setup_cmd_per_lun = -1;
-module_param(setup_cmd_per_lun, int, 0);
-static int setup_sg_tablesize = -1;
-module_param(setup_sg_tablesize, int, 0);
-#ifdef SUPPORT_TAGS
-static int setup_use_tagged_queuing = -1;
-module_param(setup_use_tagged_queuing, int, 0);
-#endif
-static int setup_hostid = -1;
-module_param(setup_hostid, int, 0);
-
-static struct scsi_cmnd *sun3_dma_setup_done = NULL;
-
-#define	AFTER_RESET_DELAY	(HZ/2)
-
-/* ms to wait after hitting dma regs */
-#define SUN3_DMA_DELAY 10
-
-/* dvma buffer to allocate -- 32k should hopefully be more than sufficient */
-#define SUN3_DVMA_BUFSIZE 0xe000
-
-/* minimum number of bytes to do dma on */
-#define SUN3_DMA_MINSIZE 128
-
-static volatile unsigned char *sun3_scsi_regp;
-static volatile struct sun3_dma_regs *dregs;
-#ifdef OLDDMA
-static unsigned char *dmabuf = NULL; /* dma memory buffer */
-#endif
-static unsigned char *sun3_dma_orig_addr = NULL;
-static unsigned long sun3_dma_orig_count = 0;
-static int sun3_dma_active = 0;
-static unsigned long last_residual = 0;
-
-/*
- * NCR 5380 register access functions
- */
-
-static inline unsigned char sun3scsi_read(int reg)
-{
-	return( sun3_scsi_regp[reg] );
-}
-
-static inline void sun3scsi_write(int reg, int value)
-{
-	sun3_scsi_regp[reg] = value;
-}
-
-/*
- * XXX: status debug
- */
-static struct Scsi_Host *default_instance;
-
-/*
- * Function : int sun3scsi_detect(struct scsi_host_template * tpnt)
- *
- * Purpose : initializes mac NCR5380 driver based on the
- *	command line / compile time port and irq definitions.
- *
- * Inputs : tpnt - template for this SCSI adapter.
- *
- * Returns : 1 if a host adapter was found, 0 if not.
- *
- */
- 
-static int __init sun3scsi_detect(struct scsi_host_template * tpnt)
-{
-	unsigned long ioaddr, irq = 0;
-	static int called = 0;
-	struct Scsi_Host *instance;
-	int i;
-	unsigned long addrs[3] = { IOBASE_SUN3_VMESCSI, 
-				   IOBASE_SUN3_VMESCSI + 0x4000,
-				   0 };
-	unsigned long vecs[3] = { SUN3_VEC_VMESCSI0,
-				  SUN3_VEC_VMESCSI1,
-				  0 };
-	/* check that this machine has an onboard 5380 */
-	switch(idprom->id_machtype) {
-	case SM_SUN3|SM_3_160:
-	case SM_SUN3|SM_3_260:
-		break;
-
-	default:
-		return 0;
-	}
-
-	if(called)
-		return 0;
-
-	tpnt->proc_name = "Sun3 5380 VME SCSI";
-
-	/* setup variables */
-	tpnt->can_queue =
-		(setup_can_queue > 0) ? setup_can_queue : CAN_QUEUE;
-	tpnt->cmd_per_lun =
-		(setup_cmd_per_lun > 0) ? setup_cmd_per_lun : CMD_PER_LUN;
-	tpnt->sg_tablesize = 
-		(setup_sg_tablesize >= 0) ? setup_sg_tablesize : SG_TABLESIZE;
-	
-	if (setup_hostid >= 0)
-		tpnt->this_id = setup_hostid;
-	else {
-		/* use 7 as default */
-		tpnt->this_id = 7;
-	}
-	
-	ioaddr = 0;
-	for(i = 0; addrs[i] != 0; i++) {
-		unsigned char x;
-		
-		ioaddr = (unsigned long)sun3_ioremap(addrs[i], PAGE_SIZE,
-						     SUN3_PAGE_TYPE_VME16);
-		irq = vecs[i];
-		sun3_scsi_regp = (unsigned char *)ioaddr;
-		
-		dregs = (struct sun3_dma_regs *)(((unsigned char *)ioaddr) + 8);
-		
-		if(sun3_map_test((unsigned long)dregs, &x)) {
-			unsigned short oldcsr;
-
-			oldcsr = dregs->csr;
-			dregs->csr = 0;
-			udelay(SUN3_DMA_DELAY);
-			if(dregs->csr == 0x1400)
-				break;
-			
-			dregs->csr = oldcsr;
-		}
-
-		iounmap((void *)ioaddr);
-		ioaddr = 0;
-	}
-
-	if(!ioaddr)
-		return 0;
-	
-#ifdef SUPPORT_TAGS
-	if (setup_use_tagged_queuing < 0)
-		setup_use_tagged_queuing = USE_TAGGED_QUEUING;
-#endif
-
-	instance = scsi_register (tpnt, sizeof(struct NCR5380_hostdata));
-	if(instance == NULL)
-		return 0;
-		
-	default_instance = instance;
-
-        instance->io_port = (unsigned long) ioaddr;
-	instance->irq = irq;
-
-	NCR5380_init(instance, 0);
-
-	instance->n_io_port = 32;
-
-        ((struct NCR5380_hostdata *)instance->hostdata)->ctrl = 0;
-
-	if (request_irq(instance->irq, scsi_sun3_intr,
-			0, "Sun3SCSI-5380VME", instance)) {
-#ifndef REAL_DMA
-		printk("scsi%d: IRQ%d not free, interrupts disabled\n",
-		       instance->host_no, instance->irq);
-		instance->irq = SCSI_IRQ_NONE;
-#else
-		printk("scsi%d: IRQ%d not free, bailing out\n",
-		       instance->host_no, instance->irq);
-		return 0;
-#endif
-	}
-
-	printk("scsi%d: Sun3 5380 VME at port %lX irq", instance->host_no, instance->io_port);
-	if (instance->irq == SCSI_IRQ_NONE)
-		printk ("s disabled");
-	else
-		printk (" %d", instance->irq);
-	printk(" options CAN_QUEUE=%d CMD_PER_LUN=%d release=%d",
-	       instance->can_queue, instance->cmd_per_lun,
-	       SUN3SCSI_PUBLIC_RELEASE);
-	printk("\nscsi%d:", instance->host_no);
-	NCR5380_print_options(instance);
-	printk("\n");
-
-	dregs->csr = 0;
-	udelay(SUN3_DMA_DELAY);
-	dregs->csr = CSR_SCSI | CSR_FIFO | CSR_INTR;
-	udelay(SUN3_DMA_DELAY);
-	dregs->fifo_count = 0;
-	dregs->fifo_count_hi = 0;
-	dregs->dma_addr_hi = 0;
-	dregs->dma_addr_lo = 0;
-	dregs->dma_count_hi = 0;
-	dregs->dma_count_lo = 0;
-
-	dregs->ivect = VME_DATA24 | (instance->irq & 0xff);
-
-	called = 1;
-
-#ifdef RESET_BOOT
-	sun3_scsi_reset_boot(instance);
-#endif
-
-	return 1;
-}
-
-int sun3scsi_release (struct Scsi_Host *shpnt)
-{
-	if (shpnt->irq != SCSI_IRQ_NONE)
-		free_irq(shpnt->irq, shpnt);
-
-	iounmap((void *)sun3_scsi_regp);
-
-	NCR5380_exit(shpnt);
-	return 0;
-}
-
-#ifdef RESET_BOOT
-/*
- * Our 'bus reset on boot' function
- */
-
-static void sun3_scsi_reset_boot(struct Scsi_Host *instance)
-{
-	unsigned long end;
-
-	NCR5380_local_declare();
-	NCR5380_setup(instance);
-	
-	/*
-	 * Do a SCSI reset to clean up the bus during initialization. No
-	 * messing with the queues, interrupts, or locks necessary here.
-	 */
-
-	printk( "Sun3 SCSI: resetting the SCSI bus..." );
-
-	/* switch off SCSI IRQ - catch an interrupt without IRQ bit set else */
-//       	sun3_disable_irq( IRQ_SUN3_SCSI );
-
-	/* get in phase */
-	NCR5380_write( TARGET_COMMAND_REG,
-		      PHASE_SR_TO_TCR( NCR5380_read(STATUS_REG) ));
-
-	/* assert RST */
-	NCR5380_write( INITIATOR_COMMAND_REG, ICR_BASE | ICR_ASSERT_RST );
-
-	/* The min. reset hold time is 25us, so 40us should be enough */
-	udelay( 50 );
-
-	/* reset RST and interrupt */
-	NCR5380_write( INITIATOR_COMMAND_REG, ICR_BASE );
-	NCR5380_read( RESET_PARITY_INTERRUPT_REG );
-
-	for( end = jiffies + AFTER_RESET_DELAY; time_before(jiffies, end); )
-		barrier();
-
-	/* switch on SCSI IRQ again */
-//       	sun3_enable_irq( IRQ_SUN3_SCSI );
-
-	printk( " done\n" );
-}
-#endif
-
-static const char * sun3scsi_info (struct Scsi_Host *spnt) {
-    return "";
-}
-
-// safe bits for the CSR
-#define CSR_GOOD 0x060f
-
-static irqreturn_t scsi_sun3_intr(int irq, void *dummy)
-{
-	unsigned short csr = dregs->csr;
-	int handled = 0;
-
-	dregs->csr &= ~CSR_DMA_ENABLE;
-
-
-#ifdef SUN3_SCSI_DEBUG
-	printk("scsi_intr csr %x\n", csr);
-#endif
-
-	if(csr & ~CSR_GOOD) {
-		if(csr & CSR_DMA_BUSERR) {
-			printk("scsi%d: bus error in dma\n", default_instance->host_no);
-#ifdef SUN3_SCSI_DEBUG
-			printk("scsi: residual %x count %x addr %p dmaaddr %x\n", 
-			       dregs->fifo_count,
-			       dregs->dma_count_lo | (dregs->dma_count_hi << 16),
-			       sun3_dma_orig_addr,
-			       dregs->dma_addr_lo | (dregs->dma_addr_hi << 16));
-#endif
-		}
-
-		if(csr & CSR_DMA_CONFLICT) {
-			printk("scsi%d: dma conflict\n", default_instance->host_no);
-		}
-		handled = 1;
-	}
-
-	if(csr & (CSR_SDB_INT | CSR_DMA_INT)) {
-		NCR5380_intr(irq, dummy);
-		handled = 1;
-	}
-
-	return IRQ_RETVAL(handled);
-}
-
-/*
- * Debug stuff - to be called on NMI, or sysrq key. Use at your own risk; 
- * reentering NCR5380_print_status seems to have ugly side effects
- */
-
-/* this doesn't seem to get used at all -- sam */
-#if 0
-void sun3_sun3_debug (void)
-{
-	unsigned long flags;
-	NCR5380_local_declare();
-
-	if (default_instance) {
-			local_irq_save(flags);
-			NCR5380_print_status(default_instance);
-			local_irq_restore(flags);
-	}
-}
-#endif
-
-
-/* sun3scsi_dma_setup() -- initialize the dma controller for a read/write */
-static unsigned long sun3scsi_dma_setup(void *data, unsigned long count, int write_flag)
-{
-	void *addr;
-
-	if(sun3_dma_orig_addr != NULL)
-		dvma_unmap(sun3_dma_orig_addr);
-
-//	addr = sun3_dvma_page((unsigned long)data, (unsigned long)dmabuf);
-	addr = (void *)dvma_map_vme((unsigned long) data, count);
-		
-	sun3_dma_orig_addr = addr;
-	sun3_dma_orig_count = count;
-	
-#ifdef SUN3_SCSI_DEBUG
-	printk("scsi: dma_setup addr %p count %x\n", addr, count);
-#endif
-
-//	dregs->fifo_count = 0;
-#if 0	
-	/* reset fifo */
-	dregs->csr &= ~CSR_FIFO;
-	dregs->csr |= CSR_FIFO;
-#endif	
-	/* set direction */
-	if(write_flag)
-		dregs->csr |= CSR_SEND;
-	else
-		dregs->csr &= ~CSR_SEND;
-	
-	/* reset fifo */
-//	dregs->csr &= ~CSR_FIFO;
-//	dregs->csr |= CSR_FIFO;
-
-	dregs->csr |= CSR_PACK_ENABLE;
-
-	dregs->dma_addr_hi = ((unsigned long)addr >> 16);
-	dregs->dma_addr_lo = ((unsigned long)addr & 0xffff);
-	
-	dregs->dma_count_hi = 0;
-	dregs->dma_count_lo = 0;
-	dregs->fifo_count_hi = 0;
-	dregs->fifo_count = 0;
-		
-#ifdef SUN3_SCSI_DEBUG
-	printk("scsi: dma_setup done csr %x\n", dregs->csr);
-#endif
-       	return count;
-
-}
-
-static inline unsigned long sun3scsi_dma_residual(struct Scsi_Host *instance)
-{
-	return last_residual;
-}
-
-static inline unsigned long sun3scsi_dma_xfer_len(unsigned long wanted,
-						  struct scsi_cmnd *cmd,
-						  int write_flag)
-{
-	if (cmd->request->cmd_type == REQ_TYPE_FS)
- 		return wanted;
-	else
-		return 0;
-}
-
-static int sun3scsi_dma_start(unsigned long count, char *data)
-{
-	
-	unsigned short csr;
-
-	csr = dregs->csr;
-#ifdef SUN3_SCSI_DEBUG
-	printk("scsi: dma_start data %p count %x csr %x fifo %x\n", data, count, csr, dregs->fifo_count);
-#endif
-	
-	dregs->dma_count_hi = (sun3_dma_orig_count >> 16);
-	dregs->dma_count_lo = (sun3_dma_orig_count & 0xffff);
-
-	dregs->fifo_count_hi = (sun3_dma_orig_count >> 16);
-	dregs->fifo_count = (sun3_dma_orig_count & 0xffff);
-
-//	if(!(csr & CSR_DMA_ENABLE))
-//		dregs->csr |= CSR_DMA_ENABLE;
-
-	return 0;
-}
-
-/* clean up after our dma is done */
-static int sun3scsi_dma_finish(int write_flag)
-{
-	unsigned short fifo;
-	int ret = 0;
-	
-	sun3_dma_active = 0;
-
-	dregs->csr &= ~CSR_DMA_ENABLE;
-	
-	fifo = dregs->fifo_count;
-	if(write_flag) {
-		if((fifo > 0) && (fifo < sun3_dma_orig_count))
-			fifo++;
-	}
-
-	last_residual = fifo;
-#ifdef SUN3_SCSI_DEBUG
-	printk("scsi: residual %x total %x\n", fifo, sun3_dma_orig_count);
-#endif
-	/* empty bytes from the fifo which didn't make it */
-	if((!write_flag) && (dregs->csr & CSR_LEFT)) {
-		unsigned char *vaddr;
-
-#ifdef SUN3_SCSI_DEBUG
-		printk("scsi: got left over bytes\n");
-#endif
-
-		vaddr = (unsigned char *)dvma_vmetov(sun3_dma_orig_addr);
-		
-		vaddr += (sun3_dma_orig_count - fifo);
-		vaddr--;
-		
-		switch(dregs->csr & CSR_LEFT) {
-		case CSR_LEFT_3:
-			*vaddr = (dregs->bpack_lo & 0xff00) >> 8;
-			vaddr--;
-			
-		case CSR_LEFT_2:
-			*vaddr = (dregs->bpack_hi & 0x00ff);
-			vaddr--;
-			
-		case CSR_LEFT_1:
-			*vaddr = (dregs->bpack_hi & 0xff00) >> 8;
-			break;
-		}
-		
-		
-	}
-
-	dvma_unmap(sun3_dma_orig_addr);
-	sun3_dma_orig_addr = NULL;
-
-	dregs->dma_addr_hi = 0;
-	dregs->dma_addr_lo = 0;
-	dregs->dma_count_hi = 0;
-	dregs->dma_count_lo = 0;
-
-	dregs->fifo_count = 0;
-	dregs->fifo_count_hi = 0;
-
-	dregs->csr &= ~CSR_SEND;
-	
-//	dregs->csr |= CSR_DMA_ENABLE;
-	
-#if 0
-	/* reset fifo */
-	dregs->csr &= ~CSR_FIFO;
-	dregs->csr |= CSR_FIFO;
-#endif	
-	sun3_dma_setup_done = NULL;
-
-	return ret;
-
-}
-
-#include "sun3_NCR5380.c"
-
-static struct scsi_host_template driver_template = {
-	.name			= SUN3_SCSI_NAME,
-	.detect			= sun3scsi_detect,
-	.release		= sun3scsi_release,
-	.info			= sun3scsi_info,
-	.queuecommand		= sun3scsi_queue_command,
-	.eh_abort_handler      	= sun3scsi_abort,
-	.eh_bus_reset_handler  	= sun3scsi_bus_reset,
-	.can_queue		= CAN_QUEUE,
-	.this_id		= 7,
-	.sg_tablesize		= SG_TABLESIZE,
-	.cmd_per_lun		= CMD_PER_LUN,
-	.use_clustering		= DISABLE_CLUSTERING
-};
-
-
-#include "scsi_module.c"
-
-MODULE_LICENSE("GPL");
+#include "sun3_scsi.c"
diff --git a/drivers/scsi/t128.c b/drivers/scsi/t128.c
index a4abce9d526..8cc80931df1 100644
--- a/drivers/scsi/t128.c
+++ b/drivers/scsi/t128.c
@@ -102,10 +102,6 @@
  * 15 9-11
  */
  
-/*
- * $Log: t128.c,v $
- */
-
 #include <linux/signal.h>
 #include <linux/io.h>
 #include <linux/blkdev.h>
diff --git a/drivers/scsi/t128.h b/drivers/scsi/t128.h
index 1df82c28e56..fd68cecc62a 100644
--- a/drivers/scsi/t128.h
+++ b/drivers/scsi/t128.h
@@ -34,10 +34,6 @@
  * 1+ (800) 334-5454
  */
 
-/*
- * $Log: t128.h,v $
- */
-
 #ifndef T128_H
 #define T128_H
 
@@ -107,8 +103,6 @@ static int t128_bus_reset(struct scsi_cmnd *);
 #define CAN_QUEUE 32
 #endif
 
-#ifndef HOSTS_C
-
 #define NCR5380_implementation_fields \
     void __iomem *base
 
@@ -148,6 +142,5 @@ static int t128_bus_reset(struct scsi_cmnd *);
 
 #define T128_IRQS 0xc4a8
 
-#endif /* else def HOSTS_C */
 #endif /* ndef ASM */
 #endif /* T128_H */
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
index 72105009052..f42d1cee652 100644
--- a/drivers/scsi/ufs/ufs.h
+++ b/drivers/scsi/ufs/ufs.h
@@ -196,9 +196,9 @@ enum {
  * @dword_2: UPIU header DW-2
  */
 struct utp_upiu_header {
-	u32 dword_0;
-	u32 dword_1;
-	u32 dword_2;
+	__be32 dword_0;
+	__be32 dword_1;
+	__be32 dword_2;
 };
 
 /**
@@ -207,7 +207,7 @@ struct utp_upiu_header {
  * @cdb: Command Descriptor Block CDB DW-4 to DW-7
  */
 struct utp_upiu_cmd {
-	u32 exp_data_transfer_len;
+	__be32 exp_data_transfer_len;
 	u8 cdb[MAX_CDB_SIZE];
 };
 
@@ -228,10 +228,10 @@ struct utp_upiu_query {
 	u8 idn;
 	u8 index;
 	u8 selector;
-	u16 reserved_osf;
-	u16 length;
-	u32 value;
-	u32 reserved[2];
+	__be16 reserved_osf;
+	__be16 length;
+	__be32 value;
+	__be32 reserved[2];
 };
 
 /**
@@ -256,9 +256,9 @@ struct utp_upiu_req {
  * @sense_data: Sense data field DW-8 to DW-12
  */
 struct utp_cmd_rsp {
-	u32 residual_transfer_count;
-	u32 reserved[4];
-	u16 sense_data_len;
+	__be32 residual_transfer_count;
+	__be32 reserved[4];
+	__be16 sense_data_len;
 	u8 sense_data[18];
 };
 
@@ -286,10 +286,10 @@ struct utp_upiu_rsp {
  */
 struct utp_upiu_task_req {
 	struct utp_upiu_header header;
-	u32 input_param1;
-	u32 input_param2;
-	u32 input_param3;
-	u32 reserved[2];
+	__be32 input_param1;
+	__be32 input_param2;
+	__be32 input_param3;
+	__be32 reserved[2];
 };
 
 /**
@@ -301,9 +301,9 @@ struct utp_upiu_task_req {
  */
 struct utp_upiu_task_rsp {
 	struct utp_upiu_header header;
-	u32 output_param1;
-	u32 output_param2;
-	u32 reserved[3];
+	__be32 output_param1;
+	__be32 output_param2;
+	__be32 reserved[3];
 };
 
 /**
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 04884d663e4..0c287725125 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -55,6 +55,9 @@
 /* Query request timeout */
 #define QUERY_REQ_TIMEOUT 30 /* msec */
 
+/* Task management command timeout */
+#define TM_CMD_TIMEOUT	100 /* msecs */
+
 /* Expose the flag value from utp_upiu_query.value */
 #define MASK_QUERY_UPIU_FLAG_LOC 0xFF
 
@@ -71,9 +74,22 @@ enum {
 
 /* UFSHCD states */
 enum {
-	UFSHCD_STATE_OPERATIONAL,
 	UFSHCD_STATE_RESET,
 	UFSHCD_STATE_ERROR,
+	UFSHCD_STATE_OPERATIONAL,
+};
+
+/* UFSHCD error handling flags */
+enum {
+	UFSHCD_EH_IN_PROGRESS = (1 << 0),
+};
+
+/* UFSHCD UIC layer error flags */
+enum {
+	UFSHCD_UIC_DL_PA_INIT_ERROR = (1 << 0), /* Data link layer error */
+	UFSHCD_UIC_NL_ERROR = (1 << 1), /* Network layer error */
+	UFSHCD_UIC_TL_ERROR = (1 << 2), /* Transport Layer error */
+	UFSHCD_UIC_DME_ERROR = (1 << 3), /* DME error */
 };
 
 /* Interrupt configuration options */
@@ -83,6 +99,18 @@ enum {
 	UFSHCD_INT_CLEAR,
 };
 
+#define ufshcd_set_eh_in_progress(h) \
+	(h->eh_flags |= UFSHCD_EH_IN_PROGRESS)
+#define ufshcd_eh_in_progress(h) \
+	(h->eh_flags & UFSHCD_EH_IN_PROGRESS)
+#define ufshcd_clear_eh_in_progress(h) \
+	(h->eh_flags &= ~UFSHCD_EH_IN_PROGRESS)
+
+static void ufshcd_tmc_handler(struct ufs_hba *hba);
+static void ufshcd_async_scan(void *data, async_cookie_t cookie);
+static int ufshcd_reset_and_restore(struct ufs_hba *hba);
+static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag);
+
 /*
  * ufshcd_wait_for_register - wait for register value to change
  * @hba - per-adapter interface
@@ -163,7 +191,7 @@ static inline int ufshcd_is_device_present(u32 reg_hcs)
  */
 static inline int ufshcd_get_tr_ocs(struct ufshcd_lrb *lrbp)
 {
-	return lrbp->utr_descriptor_ptr->header.dword_2 & MASK_OCS;
+	return le32_to_cpu(lrbp->utr_descriptor_ptr->header.dword_2) & MASK_OCS;
 }
 
 /**
@@ -176,19 +204,41 @@ static inline int ufshcd_get_tr_ocs(struct ufshcd_lrb *lrbp)
 static inline int
 ufshcd_get_tmr_ocs(struct utp_task_req_desc *task_req_descp)
 {
-	return task_req_descp->header.dword_2 & MASK_OCS;
+	return le32_to_cpu(task_req_descp->header.dword_2) & MASK_OCS;
 }
 
 /**
  * ufshcd_get_tm_free_slot - get a free slot for task management request
  * @hba: per adapter instance
+ * @free_slot: pointer to variable with available slot value
  *
- * Returns maximum number of task management request slots in case of
- * task management queue full or returns the free slot number
+ * Get a free tag and lock it until ufshcd_put_tm_slot() is called.
+ * Returns 0 if free slot is not available, else return 1 with tag value
+ * in @free_slot.
  */
-static inline int ufshcd_get_tm_free_slot(struct ufs_hba *hba)
+static bool ufshcd_get_tm_free_slot(struct ufs_hba *hba, int *free_slot)
 {
-	return find_first_zero_bit(&hba->outstanding_tasks, hba->nutmrs);
+	int tag;
+	bool ret = false;
+
+	if (!free_slot)
+		goto out;
+
+	do {
+		tag = find_first_zero_bit(&hba->tm_slots_in_use, hba->nutmrs);
+		if (tag >= hba->nutmrs)
+			goto out;
+	} while (test_and_set_bit_lock(tag, &hba->tm_slots_in_use));
+
+	*free_slot = tag;
+	ret = true;
+out:
+	return ret;
+}
+
+static inline void ufshcd_put_tm_slot(struct ufs_hba *hba, int slot)
+{
+	clear_bit_unlock(slot, &hba->tm_slots_in_use);
 }
 
 /**
@@ -390,26 +440,6 @@ static inline void ufshcd_copy_sense_data(struct ufshcd_lrb *lrbp)
 }
 
 /**
- * ufshcd_query_to_cpu() - formats the buffer to native cpu endian
- * @response: upiu query response to convert
- */
-static inline void ufshcd_query_to_cpu(struct utp_upiu_query *response)
-{
-	response->length = be16_to_cpu(response->length);
-	response->value = be32_to_cpu(response->value);
-}
-
-/**
- * ufshcd_query_to_be() - formats the buffer to big endian
- * @request: upiu query request to convert
- */
-static inline void ufshcd_query_to_be(struct utp_upiu_query *request)
-{
-	request->length = cpu_to_be16(request->length);
-	request->value = cpu_to_be32(request->value);
-}
-
-/**
  * ufshcd_copy_query_response() - Copy the Query Response and the data
  * descriptor
  * @hba: per adapter instance
@@ -425,7 +455,6 @@ void ufshcd_copy_query_response(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 			UPIU_RSP_CODE_OFFSET;
 
 	memcpy(&query_res->upiu_res, &lrbp->ucd_rsp_ptr->qr, QUERY_OSF_SIZE);
-	ufshcd_query_to_cpu(&query_res->upiu_res);
 
 
 	/* Get the descriptor */
@@ -749,7 +778,7 @@ static void ufshcd_prepare_utp_query_req_upiu(struct ufs_hba *hba,
 {
 	struct utp_upiu_req *ucd_req_ptr = lrbp->ucd_req_ptr;
 	struct ufs_query *query = &hba->dev_cmd.query;
-	u16 len = query->request.upiu_req.length;
+	u16 len = be16_to_cpu(query->request.upiu_req.length);
 	u8 *descp = (u8 *)lrbp->ucd_req_ptr + GENERAL_UPIU_REQUEST_SIZE;
 
 	/* Query request header */
@@ -766,7 +795,6 @@ static void ufshcd_prepare_utp_query_req_upiu(struct ufs_hba *hba,
 	/* Copy the Query Request buffer as is */
 	memcpy(&ucd_req_ptr->qr, &query->request.upiu_req,
 			QUERY_OSF_SIZE);
-	ufshcd_query_to_be(&ucd_req_ptr->qr);
 
 	/* Copy the Descriptor */
 	if ((len > 0) && (query->request.upiu_req.opcode ==
@@ -853,10 +881,25 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 
 	tag = cmd->request->tag;
 
-	if (hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL) {
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	switch (hba->ufshcd_state) {
+	case UFSHCD_STATE_OPERATIONAL:
+		break;
+	case UFSHCD_STATE_RESET:
 		err = SCSI_MLQUEUE_HOST_BUSY;
-		goto out;
+		goto out_unlock;
+	case UFSHCD_STATE_ERROR:
+		set_host_byte(cmd, DID_ERROR);
+		cmd->scsi_done(cmd);
+		goto out_unlock;
+	default:
+		dev_WARN_ONCE(hba->dev, 1, "%s: invalid state %d\n",
+				__func__, hba->ufshcd_state);
+		set_host_byte(cmd, DID_BAD_TARGET);
+		cmd->scsi_done(cmd);
+		goto out_unlock;
 	}
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	/* acquire the tag to make sure device cmds don't use it */
 	if (test_and_set_bit_lock(tag, &hba->lrb_in_use)) {
@@ -893,6 +936,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	/* issue command to the controller */
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_send_command(hba, tag);
+out_unlock:
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 out:
 	return err;
@@ -1151,7 +1195,7 @@ static int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 	}
 
 	if (flag_res)
-		*flag_res = (response->upiu_res.value &
+		*flag_res = (be32_to_cpu(response->upiu_res.value) &
 				MASK_QUERY_UPIU_FLAG_LOC) & 0x1;
 
 out_unlock:
@@ -1170,7 +1214,7 @@ out_unlock:
  *
  * Returns 0 for success, non-zero in case of failure
 */
-int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
+static int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
 			enum attr_idn idn, u8 index, u8 selector, u32 *attr_val)
 {
 	struct ufs_query_req *request;
@@ -1195,7 +1239,7 @@ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
 	switch (opcode) {
 	case UPIU_QUERY_OPCODE_WRITE_ATTR:
 		request->query_func = UPIU_QUERY_FUNC_STANDARD_WRITE_REQUEST;
-		request->upiu_req.value = *attr_val;
+		request->upiu_req.value = cpu_to_be32(*attr_val);
 		break;
 	case UPIU_QUERY_OPCODE_READ_ATTR:
 		request->query_func = UPIU_QUERY_FUNC_STANDARD_READ_REQUEST;
@@ -1222,7 +1266,7 @@ int ufshcd_query_attr(struct ufs_hba *hba, enum query_opcode opcode,
 		goto out_unlock;
 	}
 
-	*attr_val = response->upiu_res.value;
+	*attr_val = be32_to_cpu(response->upiu_res.value);
 
 out_unlock:
 	mutex_unlock(&hba->dev_cmd.lock);
@@ -1481,7 +1525,7 @@ EXPORT_SYMBOL_GPL(ufshcd_dme_get_attr);
  *
  * Returns 0 on success, non-zero value on failure
  */
-int ufshcd_uic_change_pwr_mode(struct ufs_hba *hba, u8 mode)
+static int ufshcd_uic_change_pwr_mode(struct ufs_hba *hba, u8 mode)
 {
 	struct uic_command uic_cmd = {0};
 	struct completion pwr_done;
@@ -1701,11 +1745,6 @@ static int ufshcd_make_hba_operational(struct ufs_hba *hba)
 		goto out;
 	}
 
-	if (hba->ufshcd_state == UFSHCD_STATE_RESET)
-		scsi_unblock_requests(hba->host);
-
-	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
-
 out:
 	return err;
 }
@@ -1831,66 +1870,6 @@ static int ufshcd_verify_dev_init(struct ufs_hba *hba)
 }
 
 /**
- * ufshcd_do_reset - reset the host controller
- * @hba: per adapter instance
- *
- * Returns SUCCESS/FAILED
- */
-static int ufshcd_do_reset(struct ufs_hba *hba)
-{
-	struct ufshcd_lrb *lrbp;
-	unsigned long flags;
-	int tag;
-
-	/* block commands from midlayer */
-	scsi_block_requests(hba->host);
-
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	hba->ufshcd_state = UFSHCD_STATE_RESET;
-
-	/* send controller to reset state */
-	ufshcd_hba_stop(hba);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-
-	/* abort outstanding commands */
-	for (tag = 0; tag < hba->nutrs; tag++) {
-		if (test_bit(tag, &hba->outstanding_reqs)) {
-			lrbp = &hba->lrb[tag];
-			if (lrbp->cmd) {
-				scsi_dma_unmap(lrbp->cmd);
-				lrbp->cmd->result = DID_RESET << 16;
-				lrbp->cmd->scsi_done(lrbp->cmd);
-				lrbp->cmd = NULL;
-				clear_bit_unlock(tag, &hba->lrb_in_use);
-			}
-		}
-	}
-
-	/* complete device management command */
-	if (hba->dev_cmd.complete)
-		complete(hba->dev_cmd.complete);
-
-	/* clear outstanding request/task bit maps */
-	hba->outstanding_reqs = 0;
-	hba->outstanding_tasks = 0;
-
-	/* Host controller enable */
-	if (ufshcd_hba_enable(hba)) {
-		dev_err(hba->dev,
-			"Reset: Controller initialization failed\n");
-		return FAILED;
-	}
-
-	if (ufshcd_link_startup(hba)) {
-		dev_err(hba->dev,
-			"Reset: Link start-up failed\n");
-		return FAILED;
-	}
-
-	return SUCCESS;
-}
-
-/**
  * ufshcd_slave_alloc - handle initial SCSI device configurations
  * @sdev: pointer to SCSI device
  *
@@ -1907,6 +1886,9 @@ static int ufshcd_slave_alloc(struct scsi_device *sdev)
 	sdev->use_10_for_ms = 1;
 	scsi_set_tag_type(sdev, MSG_SIMPLE_TAG);
 
+	/* allow SCSI layer to restart the device in case of errors */
+	sdev->allow_restart = 1;
+
 	/*
 	 * Inform SCSI Midlayer that the LUN queue depth is same as the
 	 * controller queue depth. If a LUN queue depth is less than the
@@ -1934,10 +1916,11 @@ static void ufshcd_slave_destroy(struct scsi_device *sdev)
  * ufshcd_task_req_compl - handle task management request completion
  * @hba: per adapter instance
  * @index: index of the completed request
+ * @resp: task management service response
  *
- * Returns SUCCESS/FAILED
+ * Returns non-zero value on error, zero on success
  */
-static int ufshcd_task_req_compl(struct ufs_hba *hba, u32 index)
+static int ufshcd_task_req_compl(struct ufs_hba *hba, u32 index, u8 *resp)
 {
 	struct utp_task_req_desc *task_req_descp;
 	struct utp_upiu_task_rsp *task_rsp_upiup;
@@ -1958,19 +1941,15 @@ static int ufshcd_task_req_compl(struct ufs_hba *hba, u32 index)
 				task_req_descp[index].task_rsp_upiu;
 		task_result = be32_to_cpu(task_rsp_upiup->header.dword_1);
 		task_result = ((task_result & MASK_TASK_RESPONSE) >> 8);
-
-		if (task_result != UPIU_TASK_MANAGEMENT_FUNC_COMPL &&
-		    task_result != UPIU_TASK_MANAGEMENT_FUNC_SUCCEEDED)
-			task_result = FAILED;
-		else
-			task_result = SUCCESS;
+		if (resp)
+			*resp = (u8)task_result;
 	} else {
-		task_result = FAILED;
-		dev_err(hba->dev,
-			"trc: Invalid ocs = %x\n", ocs_value);
+		dev_err(hba->dev, "%s: failed, ocs = 0x%x\n",
+				__func__, ocs_value);
 	}
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
-	return task_result;
+
+	return ocs_value;
 }
 
 /**
@@ -2105,6 +2084,9 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	case OCS_ABORTED:
 		result |= DID_ABORT << 16;
 		break;
+	case OCS_INVALID_COMMAND_STATUS:
+		result |= DID_REQUEUE << 16;
+		break;
 	case OCS_INVALID_CMD_TABLE_ATTR:
 	case OCS_INVALID_PRDT_ATTR:
 	case OCS_MISMATCH_DATA_BUF_SIZE:
@@ -2422,41 +2404,145 @@ out:
 }
 
 /**
- * ufshcd_fatal_err_handler - handle fatal errors
- * @hba: per adapter instance
+ * ufshcd_err_handler - handle UFS errors that require s/w attention
+ * @work: pointer to work structure
  */
-static void ufshcd_fatal_err_handler(struct work_struct *work)
+static void ufshcd_err_handler(struct work_struct *work)
 {
 	struct ufs_hba *hba;
-	hba = container_of(work, struct ufs_hba, feh_workq);
+	unsigned long flags;
+	u32 err_xfer = 0;
+	u32 err_tm = 0;
+	int err = 0;
+	int tag;
+
+	hba = container_of(work, struct ufs_hba, eh_work);
 
 	pm_runtime_get_sync(hba->dev);
-	/* check if reset is already in progress */
-	if (hba->ufshcd_state != UFSHCD_STATE_RESET)
-		ufshcd_do_reset(hba);
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (hba->ufshcd_state == UFSHCD_STATE_RESET) {
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+		goto out;
+	}
+
+	hba->ufshcd_state = UFSHCD_STATE_RESET;
+	ufshcd_set_eh_in_progress(hba);
+
+	/* Complete requests that have door-bell cleared by h/w */
+	ufshcd_transfer_req_compl(hba);
+	ufshcd_tmc_handler(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	/* Clear pending transfer requests */
+	for_each_set_bit(tag, &hba->outstanding_reqs, hba->nutrs)
+		if (ufshcd_clear_cmd(hba, tag))
+			err_xfer |= 1 << tag;
+
+	/* Clear pending task management requests */
+	for_each_set_bit(tag, &hba->outstanding_tasks, hba->nutmrs)
+		if (ufshcd_clear_tm_cmd(hba, tag))
+			err_tm |= 1 << tag;
+
+	/* Complete the requests that are cleared by s/w */
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_transfer_req_compl(hba);
+	ufshcd_tmc_handler(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	/* Fatal errors need reset */
+	if (err_xfer || err_tm || (hba->saved_err & INT_FATAL_ERRORS) ||
+			((hba->saved_err & UIC_ERROR) &&
+			 (hba->saved_uic_err & UFSHCD_UIC_DL_PA_INIT_ERROR))) {
+		err = ufshcd_reset_and_restore(hba);
+		if (err) {
+			dev_err(hba->dev, "%s: reset and restore failed\n",
+					__func__);
+			hba->ufshcd_state = UFSHCD_STATE_ERROR;
+		}
+		/*
+		 * Inform scsi mid-layer that we did reset and allow to handle
+		 * Unit Attention properly.
+		 */
+		scsi_report_bus_reset(hba->host, 0);
+		hba->saved_err = 0;
+		hba->saved_uic_err = 0;
+	}
+	ufshcd_clear_eh_in_progress(hba);
+
+out:
+	scsi_unblock_requests(hba->host);
 	pm_runtime_put_sync(hba->dev);
 }
 
 /**
- * ufshcd_err_handler - Check for fatal errors
- * @work: pointer to a work queue structure
+ * ufshcd_update_uic_error - check and set fatal UIC error flags.
+ * @hba: per-adapter instance
  */
-static void ufshcd_err_handler(struct ufs_hba *hba)
+static void ufshcd_update_uic_error(struct ufs_hba *hba)
 {
 	u32 reg;
 
+	/* PA_INIT_ERROR is fatal and needs UIC reset */
+	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DATA_LINK_LAYER);
+	if (reg & UIC_DATA_LINK_LAYER_ERROR_PA_INIT)
+		hba->uic_error |= UFSHCD_UIC_DL_PA_INIT_ERROR;
+
+	/* UIC NL/TL/DME errors needs software retry */
+	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_NETWORK_LAYER);
+	if (reg)
+		hba->uic_error |= UFSHCD_UIC_NL_ERROR;
+
+	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_TRANSPORT_LAYER);
+	if (reg)
+		hba->uic_error |= UFSHCD_UIC_TL_ERROR;
+
+	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DME);
+	if (reg)
+		hba->uic_error |= UFSHCD_UIC_DME_ERROR;
+
+	dev_dbg(hba->dev, "%s: UIC error flags = 0x%08x\n",
+			__func__, hba->uic_error);
+}
+
+/**
+ * ufshcd_check_errors - Check for errors that need s/w attention
+ * @hba: per-adapter instance
+ */
+static void ufshcd_check_errors(struct ufs_hba *hba)
+{
+	bool queue_eh_work = false;
+
 	if (hba->errors & INT_FATAL_ERRORS)
-		goto fatal_eh;
+		queue_eh_work = true;
 
 	if (hba->errors & UIC_ERROR) {
-		reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DATA_LINK_LAYER);
-		if (reg & UIC_DATA_LINK_LAYER_ERROR_PA_INIT)
-			goto fatal_eh;
+		hba->uic_error = 0;
+		ufshcd_update_uic_error(hba);
+		if (hba->uic_error)
+			queue_eh_work = true;
 	}
-	return;
-fatal_eh:
-	hba->ufshcd_state = UFSHCD_STATE_ERROR;
-	schedule_work(&hba->feh_workq);
+
+	if (queue_eh_work) {
+		/* handle fatal errors only when link is functional */
+		if (hba->ufshcd_state == UFSHCD_STATE_OPERATIONAL) {
+			/* block commands from scsi mid-layer */
+			scsi_block_requests(hba->host);
+
+			/* transfer error masks to sticky bits */
+			hba->saved_err |= hba->errors;
+			hba->saved_uic_err |= hba->uic_error;
+
+			hba->ufshcd_state = UFSHCD_STATE_ERROR;
+			schedule_work(&hba->eh_work);
+		}
+	}
+	/*
+	 * if (!queue_eh_work) -
+	 * Other errors are either non-fatal where host recovers
+	 * itself without s/w intervention or errors that will be
+	 * handled by the SCSI core layer.
+	 */
 }
 
 /**
@@ -2469,7 +2555,7 @@ static void ufshcd_tmc_handler(struct ufs_hba *hba)
 
 	tm_doorbell = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL);
 	hba->tm_condition = tm_doorbell ^ hba->outstanding_tasks;
-	wake_up_interruptible(&hba->ufshcd_tm_wait_queue);
+	wake_up(&hba->tm_wq);
 }
 
 /**
@@ -2481,7 +2567,7 @@ static void ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status)
 {
 	hba->errors = UFSHCD_ERROR_MASK & intr_status;
 	if (hba->errors)
-		ufshcd_err_handler(hba);
+		ufshcd_check_errors(hba);
 
 	if (intr_status & UFSHCD_UIC_MASK)
 		ufshcd_uic_cmd_compl(hba, intr_status);
@@ -2519,38 +2605,58 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba)
 	return retval;
 }
 
+static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag)
+{
+	int err = 0;
+	u32 mask = 1 << tag;
+	unsigned long flags;
+
+	if (!test_bit(tag, &hba->outstanding_tasks))
+		goto out;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_writel(hba, ~(1 << tag), REG_UTP_TASK_REQ_LIST_CLEAR);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	/* poll for max. 1 sec to clear door bell register by h/w */
+	err = ufshcd_wait_for_register(hba,
+			REG_UTP_TASK_REQ_DOOR_BELL,
+			mask, 0, 1000, 1000);
+out:
+	return err;
+}
+
 /**
  * ufshcd_issue_tm_cmd - issues task management commands to controller
  * @hba: per adapter instance
- * @lrbp: pointer to local reference block
+ * @lun_id: LUN ID to which TM command is sent
+ * @task_id: task ID to which the TM command is applicable
+ * @tm_function: task management function opcode
+ * @tm_response: task management service response return value
  *
- * Returns SUCCESS/FAILED
+ * Returns non-zero value on error, zero on success.
  */
-static int
-ufshcd_issue_tm_cmd(struct ufs_hba *hba,
-		    struct ufshcd_lrb *lrbp,
-		    u8 tm_function)
+static int ufshcd_issue_tm_cmd(struct ufs_hba *hba, int lun_id, int task_id,
+		u8 tm_function, u8 *tm_response)
 {
 	struct utp_task_req_desc *task_req_descp;
 	struct utp_upiu_task_req *task_req_upiup;
 	struct Scsi_Host *host;
 	unsigned long flags;
-	int free_slot = 0;
+	int free_slot;
 	int err;
+	int task_tag;
 
 	host = hba->host;
 
-	spin_lock_irqsave(host->host_lock, flags);
-
-	/* If task management queue is full */
-	free_slot = ufshcd_get_tm_free_slot(hba);
-	if (free_slot >= hba->nutmrs) {
-		spin_unlock_irqrestore(host->host_lock, flags);
-		dev_err(hba->dev, "Task management queue full\n");
-		err = FAILED;
-		goto out;
-	}
+	/*
+	 * Get free slot, sleep if slots are unavailable.
+	 * Even though we use wait_event() which sleeps indefinitely,
+	 * the maximum wait time is bounded by %TM_CMD_TIMEOUT.
+	 */
+	wait_event(hba->tm_tag_wq, ufshcd_get_tm_free_slot(hba, &free_slot));
 
+	spin_lock_irqsave(host->host_lock, flags);
 	task_req_descp = hba->utmrdl_base_addr;
 	task_req_descp += free_slot;
 
@@ -2562,18 +2668,15 @@ ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 	/* Configure task request UPIU */
 	task_req_upiup =
 		(struct utp_upiu_task_req *) task_req_descp->task_req_upiu;
+	task_tag = hba->nutrs + free_slot;
 	task_req_upiup->header.dword_0 =
 		UPIU_HEADER_DWORD(UPIU_TRANSACTION_TASK_REQ, 0,
-					      lrbp->lun, lrbp->task_tag);
+					      lun_id, task_tag);
 	task_req_upiup->header.dword_1 =
 		UPIU_HEADER_DWORD(0, tm_function, 0, 0);
 
-	task_req_upiup->input_param1 = lrbp->lun;
-	task_req_upiup->input_param1 =
-		cpu_to_be32(task_req_upiup->input_param1);
-	task_req_upiup->input_param2 = lrbp->task_tag;
-	task_req_upiup->input_param2 =
-		cpu_to_be32(task_req_upiup->input_param2);
+	task_req_upiup->input_param1 = cpu_to_be32(lun_id);
+	task_req_upiup->input_param2 = cpu_to_be32(task_id);
 
 	/* send command to the controller */
 	__set_bit(free_slot, &hba->outstanding_tasks);
@@ -2582,91 +2685,88 @@ ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 	spin_unlock_irqrestore(host->host_lock, flags);
 
 	/* wait until the task management command is completed */
-	err =
-	wait_event_interruptible_timeout(hba->ufshcd_tm_wait_queue,
-					 (test_bit(free_slot,
-					 &hba->tm_condition) != 0),
-					 60 * HZ);
+	err = wait_event_timeout(hba->tm_wq,
+			test_bit(free_slot, &hba->tm_condition),
+			msecs_to_jiffies(TM_CMD_TIMEOUT));
 	if (!err) {
-		dev_err(hba->dev,
-			"Task management command timed-out\n");
-		err = FAILED;
-		goto out;
+		dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
+				__func__, tm_function);
+		if (ufshcd_clear_tm_cmd(hba, free_slot))
+			dev_WARN(hba->dev, "%s: unable clear tm cmd (slot %d) after timeout\n",
+					__func__, free_slot);
+		err = -ETIMEDOUT;
+	} else {
+		err = ufshcd_task_req_compl(hba, free_slot, tm_response);
 	}
+
 	clear_bit(free_slot, &hba->tm_condition);
-	err = ufshcd_task_req_compl(hba, free_slot);
-out:
+	ufshcd_put_tm_slot(hba, free_slot);
+	wake_up(&hba->tm_tag_wq);
+
 	return err;
 }
 
 /**
- * ufshcd_device_reset - reset device and abort all the pending commands
+ * ufshcd_eh_device_reset_handler - device reset handler registered to
+ *                                    scsi layer.
  * @cmd: SCSI command pointer
  *
  * Returns SUCCESS/FAILED
  */
-static int ufshcd_device_reset(struct scsi_cmnd *cmd)
+static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
 {
 	struct Scsi_Host *host;
 	struct ufs_hba *hba;
 	unsigned int tag;
 	u32 pos;
 	int err;
+	u8 resp = 0xF;
+	struct ufshcd_lrb *lrbp;
+	unsigned long flags;
 
 	host = cmd->device->host;
 	hba = shost_priv(host);
 	tag = cmd->request->tag;
 
-	err = ufshcd_issue_tm_cmd(hba, &hba->lrb[tag], UFS_LOGICAL_RESET);
-	if (err == FAILED)
+	lrbp = &hba->lrb[tag];
+	err = ufshcd_issue_tm_cmd(hba, lrbp->lun, 0, UFS_LOGICAL_RESET, &resp);
+	if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
+		if (!err)
+			err = resp;
 		goto out;
+	}
 
-	for (pos = 0; pos < hba->nutrs; pos++) {
-		if (test_bit(pos, &hba->outstanding_reqs) &&
-		    (hba->lrb[tag].lun == hba->lrb[pos].lun)) {
-
-			/* clear the respective UTRLCLR register bit */
-			ufshcd_utrl_clear(hba, pos);
-
-			clear_bit(pos, &hba->outstanding_reqs);
-
-			if (hba->lrb[pos].cmd) {
-				scsi_dma_unmap(hba->lrb[pos].cmd);
-				hba->lrb[pos].cmd->result =
-					DID_ABORT << 16;
-				hba->lrb[pos].cmd->scsi_done(cmd);
-				hba->lrb[pos].cmd = NULL;
-				clear_bit_unlock(pos, &hba->lrb_in_use);
-				wake_up(&hba->dev_cmd.tag_wq);
-			}
+	/* clear the commands that were pending for corresponding LUN */
+	for_each_set_bit(pos, &hba->outstanding_reqs, hba->nutrs) {
+		if (hba->lrb[pos].lun == lrbp->lun) {
+			err = ufshcd_clear_cmd(hba, pos);
+			if (err)
+				break;
 		}
-	} /* end of for */
+	}
+	spin_lock_irqsave(host->host_lock, flags);
+	ufshcd_transfer_req_compl(hba);
+	spin_unlock_irqrestore(host->host_lock, flags);
 out:
+	if (!err) {
+		err = SUCCESS;
+	} else {
+		dev_err(hba->dev, "%s: failed with err %d\n", __func__, err);
+		err = FAILED;
+	}
 	return err;
 }
 
 /**
- * ufshcd_host_reset - Main reset function registered with scsi layer
- * @cmd: SCSI command pointer
- *
- * Returns SUCCESS/FAILED
- */
-static int ufshcd_host_reset(struct scsi_cmnd *cmd)
-{
-	struct ufs_hba *hba;
-
-	hba = shost_priv(cmd->device->host);
-
-	if (hba->ufshcd_state == UFSHCD_STATE_RESET)
-		return SUCCESS;
-
-	return ufshcd_do_reset(hba);
-}
-
-/**
  * ufshcd_abort - abort a specific command
  * @cmd: SCSI command pointer
  *
+ * Abort the pending command in device by sending UFS_ABORT_TASK task management
+ * command, and in host controller by clearing the door-bell register. There can
+ * be race between controller sending the command to the device while abort is
+ * issued. To avoid that, first issue UFS_QUERY_TASK to check if the command is
+ * really issued and then try to abort it.
+ *
  * Returns SUCCESS/FAILED
  */
 static int ufshcd_abort(struct scsi_cmnd *cmd)
@@ -2675,33 +2775,68 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	struct ufs_hba *hba;
 	unsigned long flags;
 	unsigned int tag;
-	int err;
+	int err = 0;
+	int poll_cnt;
+	u8 resp = 0xF;
+	struct ufshcd_lrb *lrbp;
 
 	host = cmd->device->host;
 	hba = shost_priv(host);
 	tag = cmd->request->tag;
 
-	spin_lock_irqsave(host->host_lock, flags);
+	/* If command is already aborted/completed, return SUCCESS */
+	if (!(test_bit(tag, &hba->outstanding_reqs)))
+		goto out;
 
-	/* check if command is still pending */
-	if (!(test_bit(tag, &hba->outstanding_reqs))) {
-		err = FAILED;
-		spin_unlock_irqrestore(host->host_lock, flags);
+	lrbp = &hba->lrb[tag];
+	for (poll_cnt = 100; poll_cnt; poll_cnt--) {
+		err = ufshcd_issue_tm_cmd(hba, lrbp->lun, lrbp->task_tag,
+				UFS_QUERY_TASK, &resp);
+		if (!err && resp == UPIU_TASK_MANAGEMENT_FUNC_SUCCEEDED) {
+			/* cmd pending in the device */
+			break;
+		} else if (!err && resp == UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
+			u32 reg;
+
+			/*
+			 * cmd not pending in the device, check if it is
+			 * in transition.
+			 */
+			reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
+			if (reg & (1 << tag)) {
+				/* sleep for max. 200us to stabilize */
+				usleep_range(100, 200);
+				continue;
+			}
+			/* command completed already */
+			goto out;
+		} else {
+			if (!err)
+				err = resp; /* service response error */
+			goto out;
+		}
+	}
+
+	if (!poll_cnt) {
+		err = -EBUSY;
 		goto out;
 	}
-	spin_unlock_irqrestore(host->host_lock, flags);
 
-	err = ufshcd_issue_tm_cmd(hba, &hba->lrb[tag], UFS_ABORT_TASK);
-	if (err == FAILED)
+	err = ufshcd_issue_tm_cmd(hba, lrbp->lun, lrbp->task_tag,
+			UFS_ABORT_TASK, &resp);
+	if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
+		if (!err)
+			err = resp; /* service response error */
+		goto out;
+	}
+
+	err = ufshcd_clear_cmd(hba, tag);
+	if (err)
 		goto out;
 
 	scsi_dma_unmap(cmd);
 
 	spin_lock_irqsave(host->host_lock, flags);
-
-	/* clear the respective UTRLCLR register bit */
-	ufshcd_utrl_clear(hba, tag);
-
 	__clear_bit(tag, &hba->outstanding_reqs);
 	hba->lrb[tag].cmd = NULL;
 	spin_unlock_irqrestore(host->host_lock, flags);
@@ -2709,6 +2844,129 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	clear_bit_unlock(tag, &hba->lrb_in_use);
 	wake_up(&hba->dev_cmd.tag_wq);
 out:
+	if (!err) {
+		err = SUCCESS;
+	} else {
+		dev_err(hba->dev, "%s: failed with err %d\n", __func__, err);
+		err = FAILED;
+	}
+
+	return err;
+}
+
+/**
+ * ufshcd_host_reset_and_restore - reset and restore host controller
+ * @hba: per-adapter instance
+ *
+ * Note that host controller reset may issue DME_RESET to
+ * local and remote (device) Uni-Pro stack and the attributes
+ * are reset to default state.
+ *
+ * Returns zero on success, non-zero on failure
+ */
+static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
+{
+	int err;
+	async_cookie_t cookie;
+	unsigned long flags;
+
+	/* Reset the host controller */
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_hba_stop(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	err = ufshcd_hba_enable(hba);
+	if (err)
+		goto out;
+
+	/* Establish the link again and restore the device */
+	cookie = async_schedule(ufshcd_async_scan, hba);
+	/* wait for async scan to be completed */
+	async_synchronize_cookie(++cookie);
+	if (hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL)
+		err = -EIO;
+out:
+	if (err)
+		dev_err(hba->dev, "%s: Host init failed %d\n", __func__, err);
+
+	return err;
+}
+
+/**
+ * ufshcd_reset_and_restore - reset and re-initialize host/device
+ * @hba: per-adapter instance
+ *
+ * Reset and recover device, host and re-establish link. This
+ * is helpful to recover the communication in fatal error conditions.
+ *
+ * Returns zero on success, non-zero on failure
+ */
+static int ufshcd_reset_and_restore(struct ufs_hba *hba)
+{
+	int err = 0;
+	unsigned long flags;
+
+	err = ufshcd_host_reset_and_restore(hba);
+
+	/*
+	 * After reset the door-bell might be cleared, complete
+	 * outstanding requests in s/w here.
+	 */
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	ufshcd_transfer_req_compl(hba);
+	ufshcd_tmc_handler(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	return err;
+}
+
+/**
+ * ufshcd_eh_host_reset_handler - host reset handler registered to scsi layer
+ * @cmd - SCSI command pointer
+ *
+ * Returns SUCCESS/FAILED
+ */
+static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd)
+{
+	int err;
+	unsigned long flags;
+	struct ufs_hba *hba;
+
+	hba = shost_priv(cmd->device->host);
+
+	/*
+	 * Check if there is any race with fatal error handling.
+	 * If so, wait for it to complete. Even though fatal error
+	 * handling does reset and restore in some cases, don't assume
+	 * anything out of it. We are just avoiding race here.
+	 */
+	do {
+		spin_lock_irqsave(hba->host->host_lock, flags);
+		if (!(work_pending(&hba->eh_work) ||
+				hba->ufshcd_state == UFSHCD_STATE_RESET))
+			break;
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+		dev_dbg(hba->dev, "%s: reset in progress\n", __func__);
+		flush_work(&hba->eh_work);
+	} while (1);
+
+	hba->ufshcd_state = UFSHCD_STATE_RESET;
+	ufshcd_set_eh_in_progress(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	err = ufshcd_reset_and_restore(hba);
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (!err) {
+		err = SUCCESS;
+		hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
+	} else {
+		err = FAILED;
+		hba->ufshcd_state = UFSHCD_STATE_ERROR;
+	}
+	ufshcd_clear_eh_in_progress(hba);
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
 	return err;
 }
 
@@ -2737,8 +2995,13 @@ static void ufshcd_async_scan(void *data, async_cookie_t cookie)
 		goto out;
 
 	ufshcd_force_reset_auto_bkops(hba);
-	scsi_scan_host(hba->host);
-	pm_runtime_put_sync(hba->dev);
+	hba->ufshcd_state = UFSHCD_STATE_OPERATIONAL;
+
+	/* If we are in error handling context no need to scan the host */
+	if (!ufshcd_eh_in_progress(hba)) {
+		scsi_scan_host(hba->host);
+		pm_runtime_put_sync(hba->dev);
+	}
 out:
 	return;
 }
@@ -2751,8 +3014,8 @@ static struct scsi_host_template ufshcd_driver_template = {
 	.slave_alloc		= ufshcd_slave_alloc,
 	.slave_destroy		= ufshcd_slave_destroy,
 	.eh_abort_handler	= ufshcd_abort,
-	.eh_device_reset_handler = ufshcd_device_reset,
-	.eh_host_reset_handler	= ufshcd_host_reset,
+	.eh_device_reset_handler = ufshcd_eh_device_reset_handler,
+	.eh_host_reset_handler   = ufshcd_eh_host_reset_handler,
 	.this_id		= -1,
 	.sg_tablesize		= SG_ALL,
 	.cmd_per_lun		= UFSHCD_CMD_PER_LUN,
@@ -2916,10 +3179,11 @@ int ufshcd_init(struct device *dev, struct ufs_hba **hba_handle,
 	host->max_cmd_len = MAX_CDB_SIZE;
 
 	/* Initailize wait queue for task management */
-	init_waitqueue_head(&hba->ufshcd_tm_wait_queue);
+	init_waitqueue_head(&hba->tm_wq);
+	init_waitqueue_head(&hba->tm_tag_wq);
 
 	/* Initialize work queues */
-	INIT_WORK(&hba->feh_workq, ufshcd_fatal_err_handler);
+	INIT_WORK(&hba->eh_work, ufshcd_err_handler);
 	INIT_WORK(&hba->eeh_work, ufshcd_exception_event_handler);
 
 	/* Initialize UIC command mutex */
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 577679a2d18..acf318e338e 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -174,15 +174,21 @@ struct ufs_dev_cmd {
  * @irq: Irq number of the controller
  * @active_uic_cmd: handle of active UIC command
  * @uic_cmd_mutex: mutex for uic command
- * @ufshcd_tm_wait_queue: wait queue for task management
+ * @tm_wq: wait queue for task management
+ * @tm_tag_wq: wait queue for free task management slots
+ * @tm_slots_in_use: bit map of task management request slots in use
  * @pwr_done: completion for power mode change
  * @tm_condition: condition variable for task management
  * @ufshcd_state: UFSHCD states
+ * @eh_flags: Error handling flags
  * @intr_mask: Interrupt Mask Bits
  * @ee_ctrl_mask: Exception event control mask
- * @feh_workq: Work queue for fatal controller error handling
+ * @eh_work: Worker to handle UFS errors that require s/w attention
  * @eeh_work: Worker to handle exception events
  * @errors: HBA errors
+ * @uic_error: UFS interconnect layer error status
+ * @saved_err: sticky error mask
+ * @saved_uic_err: sticky UIC error mask
  * @dev_cmd: ufs device management command information
  * @auto_bkops_enabled: to track whether bkops is enabled in device
  */
@@ -217,21 +223,27 @@ struct ufs_hba {
 	struct uic_command *active_uic_cmd;
 	struct mutex uic_cmd_mutex;
 
-	wait_queue_head_t ufshcd_tm_wait_queue;
+	wait_queue_head_t tm_wq;
+	wait_queue_head_t tm_tag_wq;
 	unsigned long tm_condition;
+	unsigned long tm_slots_in_use;
 
 	struct completion *pwr_done;
 
 	u32 ufshcd_state;
+	u32 eh_flags;
 	u32 intr_mask;
 	u16 ee_ctrl_mask;
 
 	/* Work Queues */
-	struct work_struct feh_workq;
+	struct work_struct eh_work;
 	struct work_struct eeh_work;
 
 	/* HBA Errors */
 	u32 errors;
+	u32 uic_error;
+	u32 saved_err;
+	u32 saved_uic_err;
 
 	/* Device management request data */
 	struct ufs_dev_cmd dev_cmd;
@@ -263,6 +275,8 @@ static inline void check_upiu_size(void)
 		GENERAL_UPIU_REQUEST_SIZE + QUERY_DESC_MAX_SIZE);
 }
 
+extern int ufshcd_suspend(struct ufs_hba *hba, pm_message_t state);
+extern int ufshcd_resume(struct ufs_hba *hba);
 extern int ufshcd_runtime_suspend(struct ufs_hba *hba);
 extern int ufshcd_runtime_resume(struct ufs_hba *hba);
 extern int ufshcd_runtime_idle(struct ufs_hba *hba);
diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h
index 0475c6619a6..9abc7e32b43 100644
--- a/drivers/scsi/ufs/ufshci.h
+++ b/drivers/scsi/ufs/ufshci.h
@@ -304,10 +304,10 @@ enum {
  * @size: size of physical segment DW-3
  */
 struct ufshcd_sg_entry {
-	u32    base_addr;
-	u32    upper_addr;
-	u32    reserved;
-	u32    size;
+	__le32    base_addr;
+	__le32    upper_addr;
+	__le32    reserved;
+	__le32    size;
 };
 
 /**
@@ -330,10 +330,10 @@ struct utp_transfer_cmd_desc {
  * @dword3: Descriptor Header DW3
  */
 struct request_desc_header {
-	u32 dword_0;
-	u32 dword_1;
-	u32 dword_2;
-	u32 dword_3;
+	__le32 dword_0;
+	__le32 dword_1;
+	__le32 dword_2;
+	__le32 dword_3;
 };
 
 /**
@@ -352,16 +352,16 @@ struct utp_transfer_req_desc {
 	struct request_desc_header header;
 
 	/* DW 4-5*/
-	u32  command_desc_base_addr_lo;
-	u32  command_desc_base_addr_hi;
+	__le32  command_desc_base_addr_lo;
+	__le32  command_desc_base_addr_hi;
 
 	/* DW 6 */
-	u16  response_upiu_length;
-	u16  response_upiu_offset;
+	__le16  response_upiu_length;
+	__le16  response_upiu_offset;
 
 	/* DW 7 */
-	u16  prd_table_length;
-	u16  prd_table_offset;
+	__le16  prd_table_length;
+	__le16  prd_table_offset;
 };
 
 /**
@@ -376,10 +376,10 @@ struct utp_task_req_desc {
 	struct request_desc_header header;
 
 	/* DW 4-11 */
-	u32 task_req_upiu[TASK_REQ_UPIU_SIZE_DWORDS];
+	__le32 task_req_upiu[TASK_REQ_UPIU_SIZE_DWORDS];
 
 	/* DW 12-19 */
-	u32 task_rsp_upiu[TASK_RSP_UPIU_SIZE_DWORDS];
+	__le32 task_rsp_upiu[TASK_RSP_UPIU_SIZE_DWORDS];
 };
 
 #endif /* End of Header */
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index db3b494e592..308256b5e4c 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -23,6 +23,7 @@
 #include <linux/virtio_config.h>
 #include <linux/virtio_scsi.h>
 #include <linux/cpu.h>
+#include <linux/blkdev.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_cmnd.h>
@@ -37,6 +38,7 @@ struct virtio_scsi_cmd {
 	struct completion *comp;
 	union {
 		struct virtio_scsi_cmd_req       cmd;
+		struct virtio_scsi_cmd_req_pi    cmd_pi;
 		struct virtio_scsi_ctrl_tmf_req  tmf;
 		struct virtio_scsi_ctrl_an_req   an;
 	} req;
@@ -73,17 +75,12 @@ struct virtio_scsi_vq {
  * queue, and also lets the driver optimize the IRQ affinity for the virtqueues
  * (each virtqueue's affinity is set to the CPU that "owns" the queue).
  *
- * An interesting effect of this policy is that only writes to req_vq need to
- * take the tgt_lock.  Read can be done outside the lock because:
+ * tgt_lock is held to serialize reading and writing req_vq. Reading req_vq
+ * could be done locklessly, but we do not do it yet.
  *
- * - writes of req_vq only occur when atomic_inc_return(&tgt->reqs) returns 1.
- *   In that case, no other CPU is reading req_vq: even if they were in
- *   virtscsi_queuecommand_multi, they would be spinning on tgt_lock.
- *
- * - reads of req_vq only occur when the target is not idle (reqs != 0).
- *   A CPU that enters virtscsi_queuecommand_multi will not modify req_vq.
- *
- * Similarly, decrements of reqs are never concurrent with writes of req_vq.
+ * Decrements of reqs are never concurrent with writes of req_vq: before the
+ * decrement reqs will be != 0; after the decrement the virtqueue completion
+ * routine will not use the req_vq so it can be changed by a new request.
  * Thus they can happen outside the tgt_lock, provided of course we make reqs
  * an atomic_t.
  */
@@ -204,7 +201,6 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
 			set_driver_byte(sc, DRIVER_SENSE);
 	}
 
-	mempool_free(cmd, virtscsi_cmd_pool);
 	sc->scsi_done(sc);
 
 	atomic_dec(&tgt->reqs);
@@ -238,49 +234,25 @@ static void virtscsi_req_done(struct virtqueue *vq)
 	int index = vq->index - VIRTIO_SCSI_VQ_BASE;
 	struct virtio_scsi_vq *req_vq = &vscsi->req_vqs[index];
 
-	/*
-	 * Read req_vq before decrementing the reqs field in
-	 * virtscsi_complete_cmd.
-	 *
-	 * With barriers:
-	 *
-	 * 	CPU #0			virtscsi_queuecommand_multi (CPU #1)
-	 * 	------------------------------------------------------------
-	 * 	lock vq_lock
-	 * 	read req_vq
-	 * 	read reqs (reqs = 1)
-	 * 	write reqs (reqs = 0)
-	 * 				increment reqs (reqs = 1)
-	 * 				write req_vq
-	 *
-	 * Possible reordering without barriers:
-	 *
-	 * 	CPU #0			virtscsi_queuecommand_multi (CPU #1)
-	 * 	------------------------------------------------------------
-	 * 	lock vq_lock
-	 * 	read reqs (reqs = 1)
-	 * 	write reqs (reqs = 0)
-	 * 				increment reqs (reqs = 1)
-	 * 				write req_vq
-	 * 	read (wrong) req_vq
-	 *
-	 * We do not need a full smp_rmb, because req_vq is required to get
-	 * to tgt->reqs: tgt is &vscsi->tgt[sc->device->id], where sc is stored
-	 * in the virtqueue as the user token.
-	 */
-	smp_read_barrier_depends();
-
 	virtscsi_vq_done(vscsi, req_vq, virtscsi_complete_cmd);
 };
 
+static void virtscsi_poll_requests(struct virtio_scsi *vscsi)
+{
+	int i, num_vqs;
+
+	num_vqs = vscsi->num_queues;
+	for (i = 0; i < num_vqs; i++)
+		virtscsi_vq_done(vscsi, &vscsi->req_vqs[i],
+				 virtscsi_complete_cmd);
+}
+
 static void virtscsi_complete_free(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_cmd *cmd = buf;
 
 	if (cmd->comp)
 		complete_all(cmd->comp);
-	else
-		mempool_free(cmd, virtscsi_cmd_pool);
 }
 
 static void virtscsi_ctrl_done(struct virtqueue *vq)
@@ -291,6 +263,8 @@ static void virtscsi_ctrl_done(struct virtqueue *vq)
 	virtscsi_vq_done(vscsi, &vscsi->ctrl_vq, virtscsi_complete_free);
 };
 
+static void virtscsi_handle_event(struct work_struct *work);
+
 static int virtscsi_kick_event(struct virtio_scsi *vscsi,
 			       struct virtio_scsi_event_node *event_node)
 {
@@ -298,6 +272,7 @@ static int virtscsi_kick_event(struct virtio_scsi *vscsi,
 	struct scatterlist sg;
 	unsigned long flags;
 
+	INIT_WORK(&event_node->work, virtscsi_handle_event);
 	sg_init_one(&sg, &event_node->event, sizeof(struct virtio_scsi_event));
 
 	spin_lock_irqsave(&vscsi->event_vq.vq_lock, flags);
@@ -415,7 +390,6 @@ static void virtscsi_complete_event(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_event_node *event_node = buf;
 
-	INIT_WORK(&event_node->work, virtscsi_handle_event);
 	schedule_work(&event_node->work);
 }
 
@@ -433,14 +407,13 @@ static void virtscsi_event_done(struct virtqueue *vq)
  * @cmd		: command structure
  * @req_size	: size of the request buffer
  * @resp_size	: size of the response buffer
- * @gfp	: flags to use for memory allocations
  */
 static int virtscsi_add_cmd(struct virtqueue *vq,
 			    struct virtio_scsi_cmd *cmd,
-			    size_t req_size, size_t resp_size, gfp_t gfp)
+			    size_t req_size, size_t resp_size)
 {
 	struct scsi_cmnd *sc = cmd->sc;
-	struct scatterlist *sgs[4], req, resp;
+	struct scatterlist *sgs[6], req, resp;
 	struct sg_table *out, *in;
 	unsigned out_num = 0, in_num = 0;
 
@@ -458,30 +431,38 @@ static int virtscsi_add_cmd(struct virtqueue *vq,
 	sgs[out_num++] = &req;
 
 	/* Data-out buffer.  */
-	if (out)
+	if (out) {
+		/* Place WRITE protection SGLs before Data OUT payload */
+		if (scsi_prot_sg_count(sc))
+			sgs[out_num++] = scsi_prot_sglist(sc);
 		sgs[out_num++] = out->sgl;
+	}
 
 	/* Response header.  */
 	sg_init_one(&resp, &cmd->resp, resp_size);
 	sgs[out_num + in_num++] = &resp;
 
 	/* Data-in buffer */
-	if (in)
+	if (in) {
+		/* Place READ protection SGLs before Data IN payload */
+		if (scsi_prot_sg_count(sc))
+			sgs[out_num + in_num++] = scsi_prot_sglist(sc);
 		sgs[out_num + in_num++] = in->sgl;
+	}
 
-	return virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, gfp);
+	return virtqueue_add_sgs(vq, sgs, out_num, in_num, cmd, GFP_ATOMIC);
 }
 
 static int virtscsi_kick_cmd(struct virtio_scsi_vq *vq,
 			     struct virtio_scsi_cmd *cmd,
-			     size_t req_size, size_t resp_size, gfp_t gfp)
+			     size_t req_size, size_t resp_size)
 {
 	unsigned long flags;
 	int err;
 	bool needs_kick = false;
 
 	spin_lock_irqsave(&vq->vq_lock, flags);
-	err = virtscsi_add_cmd(vq->vq, cmd, req_size, resp_size, gfp);
+	err = virtscsi_add_cmd(vq->vq, cmd, req_size, resp_size);
 	if (!err)
 		needs_kick = virtqueue_kick_prepare(vq->vq);
 
@@ -492,14 +473,46 @@ static int virtscsi_kick_cmd(struct virtio_scsi_vq *vq,
 	return err;
 }
 
+static void virtio_scsi_init_hdr(struct virtio_scsi_cmd_req *cmd,
+				 struct scsi_cmnd *sc)
+{
+	cmd->lun[0] = 1;
+	cmd->lun[1] = sc->device->id;
+	cmd->lun[2] = (sc->device->lun >> 8) | 0x40;
+	cmd->lun[3] = sc->device->lun & 0xff;
+	cmd->tag = (unsigned long)sc;
+	cmd->task_attr = VIRTIO_SCSI_S_SIMPLE;
+	cmd->prio = 0;
+	cmd->crn = 0;
+}
+
+static void virtio_scsi_init_hdr_pi(struct virtio_scsi_cmd_req_pi *cmd_pi,
+				    struct scsi_cmnd *sc)
+{
+	struct request *rq = sc->request;
+	struct blk_integrity *bi;
+
+	virtio_scsi_init_hdr((struct virtio_scsi_cmd_req *)cmd_pi, sc);
+
+	if (!rq || !scsi_prot_sg_count(sc))
+		return;
+
+	bi = blk_get_integrity(rq->rq_disk);
+
+	if (sc->sc_data_direction == DMA_TO_DEVICE)
+		cmd_pi->pi_bytesout = blk_rq_sectors(rq) * bi->tuple_size;
+	else if (sc->sc_data_direction == DMA_FROM_DEVICE)
+		cmd_pi->pi_bytesin = blk_rq_sectors(rq) * bi->tuple_size;
+}
+
 static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 				 struct virtio_scsi_vq *req_vq,
 				 struct scsi_cmnd *sc)
 {
-	struct virtio_scsi_cmd *cmd;
-	int ret;
-
 	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
+	struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc);
+	int req_size;
+
 	BUG_ON(scsi_sg_count(sc) > shost->sg_tablesize);
 
 	/* TODO: check feature bit and fail if unsupported?  */
@@ -508,36 +521,24 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 	dev_dbg(&sc->device->sdev_gendev,
 		"cmd %p CDB: %#02x\n", sc, sc->cmnd[0]);
 
-	ret = SCSI_MLQUEUE_HOST_BUSY;
-	cmd = mempool_alloc(virtscsi_cmd_pool, GFP_ATOMIC);
-	if (!cmd)
-		goto out;
-
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->sc = sc;
-	cmd->req.cmd = (struct virtio_scsi_cmd_req){
-		.lun[0] = 1,
-		.lun[1] = sc->device->id,
-		.lun[2] = (sc->device->lun >> 8) | 0x40,
-		.lun[3] = sc->device->lun & 0xff,
-		.tag = (unsigned long)sc,
-		.task_attr = VIRTIO_SCSI_S_SIMPLE,
-		.prio = 0,
-		.crn = 0,
-	};
 
 	BUG_ON(sc->cmd_len > VIRTIO_SCSI_CDB_SIZE);
-	memcpy(cmd->req.cmd.cdb, sc->cmnd, sc->cmd_len);
 
-	if (virtscsi_kick_cmd(req_vq, cmd,
-			      sizeof cmd->req.cmd, sizeof cmd->resp.cmd,
-			      GFP_ATOMIC) == 0)
-		ret = 0;
-	else
-		mempool_free(cmd, virtscsi_cmd_pool);
+	if (virtio_has_feature(vscsi->vdev, VIRTIO_SCSI_F_T10_PI)) {
+		virtio_scsi_init_hdr_pi(&cmd->req.cmd_pi, sc);
+		memcpy(cmd->req.cmd_pi.cdb, sc->cmnd, sc->cmd_len);
+		req_size = sizeof(cmd->req.cmd_pi);
+	} else {
+		virtio_scsi_init_hdr(&cmd->req.cmd, sc);
+		memcpy(cmd->req.cmd.cdb, sc->cmnd, sc->cmd_len);
+		req_size = sizeof(cmd->req.cmd);
+	}
 
-out:
-	return ret;
+	if (virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)) != 0)
+		return SCSI_MLQUEUE_HOST_BUSY;
+	return 0;
 }
 
 static int virtscsi_queuecommand_single(struct Scsi_Host *sh,
@@ -560,12 +561,8 @@ static struct virtio_scsi_vq *virtscsi_pick_vq(struct virtio_scsi *vscsi,
 
 	spin_lock_irqsave(&tgt->tgt_lock, flags);
 
-	/*
-	 * The memory barrier after atomic_inc_return matches
-	 * the smp_read_barrier_depends() in virtscsi_req_done.
-	 */
 	if (atomic_inc_return(&tgt->reqs) > 1)
-		vq = ACCESS_ONCE(tgt->req_vq);
+		vq = tgt->req_vq;
 	else {
 		queue_num = smp_processor_id();
 		while (unlikely(queue_num >= vscsi->num_queues))
@@ -596,8 +593,7 @@ static int virtscsi_tmf(struct virtio_scsi *vscsi, struct virtio_scsi_cmd *cmd)
 
 	cmd->comp = &comp;
 	if (virtscsi_kick_cmd(&vscsi->ctrl_vq, cmd,
-			      sizeof cmd->req.tmf, sizeof cmd->resp.tmf,
-			      GFP_NOIO) < 0)
+			      sizeof cmd->req.tmf, sizeof cmd->resp.tmf) < 0)
 		goto out;
 
 	wait_for_completion(&comp);
@@ -605,6 +601,18 @@ static int virtscsi_tmf(struct virtio_scsi *vscsi, struct virtio_scsi_cmd *cmd)
 	    cmd->resp.tmf.response == VIRTIO_SCSI_S_FUNCTION_SUCCEEDED)
 		ret = SUCCESS;
 
+	/*
+	 * The spec guarantees that all requests related to the TMF have
+	 * been completed, but the callback might not have run yet if
+	 * we're using independent interrupts (e.g. MSI).  Poll the
+	 * virtqueues once.
+	 *
+	 * In the abort case, sc->scsi_done will do nothing, because
+	 * the block layer must have detected a timeout and as a result
+	 * REQ_ATOM_COMPLETE has been set.
+	 */
+	virtscsi_poll_requests(vscsi);
+
 out:
 	mempool_free(cmd, virtscsi_cmd_pool);
 	return ret;
@@ -683,6 +691,7 @@ static struct scsi_host_template virtscsi_host_template_single = {
 	.name = "Virtio SCSI HBA",
 	.proc_name = "virtio_scsi",
 	.this_id = -1,
+	.cmd_size = sizeof(struct virtio_scsi_cmd),
 	.queuecommand = virtscsi_queuecommand_single,
 	.eh_abort_handler = virtscsi_abort,
 	.eh_device_reset_handler = virtscsi_device_reset,
@@ -699,6 +708,7 @@ static struct scsi_host_template virtscsi_host_template_multi = {
 	.name = "Virtio SCSI HBA",
 	.proc_name = "virtio_scsi",
 	.this_id = -1,
+	.cmd_size = sizeof(struct virtio_scsi_cmd),
 	.queuecommand = virtscsi_queuecommand_multi,
 	.eh_abort_handler = virtscsi_abort,
 	.eh_device_reset_handler = virtscsi_device_reset,
@@ -875,7 +885,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
 {
 	struct Scsi_Host *shost;
 	struct virtio_scsi *vscsi;
-	int err;
+	int err, host_prot;
 	u32 sg_elems, num_targets;
 	u32 cmd_per_lun;
 	u32 num_queues;
@@ -925,6 +935,16 @@ static int virtscsi_probe(struct virtio_device *vdev)
 	shost->max_id = num_targets;
 	shost->max_channel = 0;
 	shost->max_cmd_len = VIRTIO_SCSI_CDB_SIZE;
+
+	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_T10_PI)) {
+		host_prot = SHOST_DIF_TYPE1_PROTECTION | SHOST_DIF_TYPE2_PROTECTION |
+			    SHOST_DIF_TYPE3_PROTECTION | SHOST_DIX_TYPE1_PROTECTION |
+			    SHOST_DIX_TYPE2_PROTECTION | SHOST_DIX_TYPE3_PROTECTION;
+
+		scsi_host_set_prot(shost, host_prot);
+		scsi_host_set_guard(shost, SHOST_DIX_GUARD_CRC);
+	}
+
 	err = scsi_add_host(shost, &vdev->dev);
 	if (err)
 		goto scsi_add_host_failed;
@@ -994,6 +1014,7 @@ static struct virtio_device_id id_table[] = {
 static unsigned int features[] = {
 	VIRTIO_SCSI_F_HOTPLUG,
 	VIRTIO_SCSI_F_CHANGE,
+	VIRTIO_SCSI_F_T10_PI,
 };
 
 static struct virtio_driver virtio_scsi_driver = {
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index f6759dc0153..c41ff148a2b 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -368,7 +368,7 @@ int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
 	 * otherwise we use the default. Also we use the default FIFO
 	 * thresholds for now.
 	 */
-	*burst_code = chip_info ? chip_info->dma_burst_size : 16;
+	*burst_code = chip_info ? chip_info->dma_burst_size : 1;
 	*threshold = SSCR1_RxTresh(RX_THRESH_DFLT)
 		   | SSCR1_TxTresh(TX_THRESH_DFLT);
 
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index a98df7eeb42..fe792106bdc 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -118,6 +118,7 @@ static void lpss_ssp_setup(struct driver_data *drv_data)
 	 */
 	orig = readl(drv_data->ioaddr + offset + SPI_CS_CONTROL);
 
+	/* Test SPI_CS_CONTROL_SW_MODE bit enabling */
 	value = orig | SPI_CS_CONTROL_SW_MODE;
 	writel(value, drv_data->ioaddr + offset + SPI_CS_CONTROL);
 	value = readl(drv_data->ioaddr + offset + SPI_CS_CONTROL);
@@ -126,10 +127,13 @@ static void lpss_ssp_setup(struct driver_data *drv_data)
 		goto detection_done;
 	}
 
-	value &= ~SPI_CS_CONTROL_SW_MODE;
+	orig = readl(drv_data->ioaddr + offset + SPI_CS_CONTROL);
+
+	/* Test SPI_CS_CONTROL_SW_MODE bit disabling */
+	value = orig & ~SPI_CS_CONTROL_SW_MODE;
 	writel(value, drv_data->ioaddr + offset + SPI_CS_CONTROL);
 	value = readl(drv_data->ioaddr + offset + SPI_CS_CONTROL);
-	if (value != orig) {
+	if (value != (orig & ~SPI_CS_CONTROL_SW_MODE)) {
 		offset = 0x800;
 		goto detection_done;
 	}
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index fc1de86d3c8..c08da380cb2 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -424,31 +424,6 @@ static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer)
 	return 0;
 }
 
-static void spi_qup_set_cs(struct spi_device *spi, bool enable)
-{
-	struct spi_qup *controller = spi_master_get_devdata(spi->master);
-
-	u32 iocontol, mask;
-
-	iocontol = readl_relaxed(controller->base + SPI_IO_CONTROL);
-
-	/* Disable auto CS toggle and use manual */
-	iocontol &= ~SPI_IO_C_MX_CS_MODE;
-	iocontol |= SPI_IO_C_FORCE_CS;
-
-	iocontol &= ~SPI_IO_C_CS_SELECT_MASK;
-	iocontol |= SPI_IO_C_CS_SELECT(spi->chip_select);
-
-	mask = SPI_IO_C_CS_N_POLARITY_0 << spi->chip_select;
-
-	if (enable)
-		iocontol |= mask;
-	else
-		iocontol &= ~mask;
-
-	writel_relaxed(iocontol, controller->base + SPI_IO_CONTROL);
-}
-
 static int spi_qup_transfer_one(struct spi_master *master,
 			      struct spi_device *spi,
 			      struct spi_transfer *xfer)
@@ -571,12 +546,16 @@ static int spi_qup_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	/* use num-cs unless not present or out of range */
+	if (of_property_read_u16(dev->of_node, "num-cs",
+			&master->num_chipselect) ||
+			(master->num_chipselect > SPI_NUM_CHIPSELECTS))
+		master->num_chipselect = SPI_NUM_CHIPSELECTS;
+
 	master->bus_num = pdev->id;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP;
-	master->num_chipselect = SPI_NUM_CHIPSELECTS;
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
 	master->max_speed_hz = max_freq;
-	master->set_cs = spi_qup_set_cs;
 	master->transfer_one = spi_qup_transfer_one;
 	master->dev.of_node = pdev->dev.of_node;
 	master->auto_runtime_pm = true;
@@ -640,16 +619,19 @@ static int spi_qup_probe(struct platform_device *pdev)
 	if (ret)
 		goto error;
 
-	ret = devm_spi_register_master(dev, master);
-	if (ret)
-		goto error;
-
 	pm_runtime_set_autosuspend_delay(dev, MSEC_PER_SEC);
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
+
+	ret = devm_spi_register_master(dev, master);
+	if (ret)
+		goto disable_pm;
+
 	return 0;
 
+disable_pm:
+	pm_runtime_disable(&pdev->dev);
 error:
 	clk_disable_unprepare(cclk);
 	clk_disable_unprepare(iclk);
diff --git a/drivers/spi/spi-sh-sci.c b/drivers/spi/spi-sh-sci.c
index 1f56ef651d1..b83dd733684 100644
--- a/drivers/spi/spi-sh-sci.c
+++ b/drivers/spi/spi-sh-sci.c
@@ -175,9 +175,9 @@ static int sh_sci_spi_remove(struct platform_device *dev)
 {
 	struct sh_sci_spi *sp = platform_get_drvdata(dev);
 
-	iounmap(sp->membase);
-	setbits(sp, PIN_INIT, 0);
 	spi_bitbang_stop(&sp->bitbang);
+	setbits(sp, PIN_INIT, 0);
+	iounmap(sp->membase);
 	spi_master_put(sp->bitbang.master);
 	return 0;
 }
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index d4f9670b51b..22aa41cace8 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -29,6 +29,7 @@
 #include <linux/mutex.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
+#include <linux/clk/clk-conf.h>
 #include <linux/slab.h>
 #include <linux/mod_devicetable.h>
 #include <linux/spi/spi.h>
@@ -259,6 +260,10 @@ static int spi_drv_probe(struct device *dev)
 	const struct spi_driver		*sdrv = to_spi_driver(dev->driver);
 	int ret;
 
+	ret = of_clk_set_defaults(dev->of_node, false);
+	if (ret)
+		return ret;
+
 	acpi_dev_pm_attach(dev, true);
 	ret = sdrv->probe(to_spi_device(dev));
 	if (ret)
diff --git a/drivers/staging/android/timed_output.c b/drivers/staging/android/timed_output.c
index 2c617834dc4..c341ac11c5a 100644
--- a/drivers/staging/android/timed_output.c
+++ b/drivers/staging/android/timed_output.c
@@ -97,7 +97,6 @@ void timed_output_dev_unregister(struct timed_output_dev *tdev)
 {
 	tdev->enable(tdev, 0);
 	device_destroy(timed_output_class, MKDEV(0, tdev->index));
-	dev_set_drvdata(tdev->dev, NULL);
 }
 EXPORT_SYMBOL_GPL(timed_output_dev_unregister);
 
diff --git a/drivers/staging/comedi/Kconfig b/drivers/staging/comedi/Kconfig
index 5d56428d508..a2f6957e7ee 100644
--- a/drivers/staging/comedi/Kconfig
+++ b/drivers/staging/comedi/Kconfig
@@ -651,6 +651,7 @@ config COMEDI_ADDI_APCI_1516
 
 config COMEDI_ADDI_APCI_1564
 	tristate "ADDI-DATA APCI_1564 support"
+	select COMEDI_ADDI_WATCHDOG
 	---help---
 	  Enable support for ADDI-DATA APCI_1564 cards
 
diff --git a/drivers/staging/et131x/et131x.c b/drivers/staging/et131x/et131x.c
index 0901ef5d6e8..08356b6955a 100644
--- a/drivers/staging/et131x/et131x.c
+++ b/drivers/staging/et131x/et131x.c
@@ -4605,7 +4605,7 @@ static int et131x_pci_setup(struct pci_dev *pdev,
 	netdev->netdev_ops     = &et131x_netdev_ops;
 
 	SET_NETDEV_DEV(netdev, &pdev->dev);
-	SET_ETHTOOL_OPS(netdev, &et131x_ethtool_ops);
+	netdev->ethtool_ops = &et131x_ethtool_ops;
 
 	adapter = et131x_adapter_init(netdev, pdev);
 
diff --git a/drivers/staging/ft1000/ft1000-pcmcia/ft1000_hw.c b/drivers/staging/ft1000/ft1000-pcmcia/ft1000_hw.c
index d6421b9b598..a6158bef58e 100644
--- a/drivers/staging/ft1000/ft1000-pcmcia/ft1000_hw.c
+++ b/drivers/staging/ft1000/ft1000-pcmcia/ft1000_hw.c
@@ -2249,7 +2249,7 @@ struct net_device *init_ft1000_card(struct pcmcia_device *link,
 
 	ft1000InitProc(dev);
 	ft1000_card_present = 1;
-	SET_ETHTOOL_OPS(dev, &ops);
+	dev->ethtool_ops = &ops;
 	printk(KERN_INFO "ft1000: %s: addr 0x%04lx irq %d, MAC addr %pM\n",
 			dev->name, dev->base_addr, dev->irq, dev->dev_addr);
 	return dev;
diff --git a/drivers/staging/iio/Kconfig b/drivers/staging/iio/Kconfig
index b36feb080cb..fa38be0982f 100644
--- a/drivers/staging/iio/Kconfig
+++ b/drivers/staging/iio/Kconfig
@@ -36,10 +36,11 @@ config IIO_SIMPLE_DUMMY_EVENTS
          Add some dummy events to the simple dummy driver.
 
 config IIO_SIMPLE_DUMMY_BUFFER
-       boolean "Buffered capture support"
-       select IIO_KFIFO_BUF
-       help
-         Add buffered data capture to the simple dummy driver.
+	boolean "Buffered capture support"
+	select IIO_BUFFER
+	select IIO_KFIFO_BUF
+	help
+	  Add buffered data capture to the simple dummy driver.
 
 endif # IIO_SIMPLE_DUMMY
 
diff --git a/drivers/staging/iio/adc/ad7291.c b/drivers/staging/iio/adc/ad7291.c
index 357cef2a6f4..7194bd13876 100644
--- a/drivers/staging/iio/adc/ad7291.c
+++ b/drivers/staging/iio/adc/ad7291.c
@@ -465,7 +465,7 @@ static int ad7291_probe(struct i2c_client *client,
 	struct ad7291_platform_data *pdata = client->dev.platform_data;
 	struct ad7291_chip_info *chip;
 	struct iio_dev *indio_dev;
-	int ret = 0;
+	int ret;
 
 	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*chip));
 	if (!indio_dev)
@@ -475,7 +475,7 @@ static int ad7291_probe(struct i2c_client *client,
 	if (pdata && pdata->use_external_ref) {
 		chip->reg = devm_regulator_get(&client->dev, "vref");
 		if (IS_ERR(chip->reg))
-			return ret;
+			return PTR_ERR(chip->reg);
 
 		ret = regulator_enable(chip->reg);
 		if (ret)
diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c
index dae8d1a9038..52d7517b342 100644
--- a/drivers/staging/iio/adc/mxs-lradc.c
+++ b/drivers/staging/iio/adc/mxs-lradc.c
@@ -846,6 +846,14 @@ static int mxs_lradc_read_single(struct iio_dev *iio_dev, int chan, int *val)
 			LRADC_CTRL1);
 	mxs_lradc_reg_clear(lradc, 0xff, LRADC_CTRL0);
 
+	/* Enable / disable the divider per requirement */
+	if (test_bit(chan, &lradc->is_divided))
+		mxs_lradc_reg_set(lradc, 1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET,
+			LRADC_CTRL2);
+	else
+		mxs_lradc_reg_clear(lradc,
+			1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET, LRADC_CTRL2);
+
 	/* Clean the slot's previous content, then set new one. */
 	mxs_lradc_reg_clear(lradc, LRADC_CTRL4_LRADCSELECT_MASK(0),
 			LRADC_CTRL4);
@@ -961,15 +969,11 @@ static int mxs_lradc_write_raw(struct iio_dev *iio_dev,
 		if (val == scale_avail[MXS_LRADC_DIV_DISABLED].integer &&
 		    val2 == scale_avail[MXS_LRADC_DIV_DISABLED].nano) {
 			/* divider by two disabled */
-			writel(1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET,
-			       lradc->base + LRADC_CTRL2 + STMP_OFFSET_REG_CLR);
 			clear_bit(chan->channel, &lradc->is_divided);
 			ret = 0;
 		} else if (val == scale_avail[MXS_LRADC_DIV_ENABLED].integer &&
 			   val2 == scale_avail[MXS_LRADC_DIV_ENABLED].nano) {
 			/* divider by two enabled */
-			writel(1 << LRADC_CTRL2_DIVIDE_BY_TWO_OFFSET,
-			       lradc->base + LRADC_CTRL2 + STMP_OFFSET_REG_SET);
 			set_bit(chan->channel, &lradc->is_divided);
 			ret = 0;
 		}
diff --git a/drivers/staging/iio/light/tsl2x7x_core.c b/drivers/staging/iio/light/tsl2x7x_core.c
index 9e0f2a9c73a..ab338e3ddd0 100644
--- a/drivers/staging/iio/light/tsl2x7x_core.c
+++ b/drivers/staging/iio/light/tsl2x7x_core.c
@@ -667,9 +667,13 @@ static int tsl2x7x_chip_on(struct iio_dev *indio_dev)
 	chip->tsl2x7x_config[TSL2X7X_PRX_COUNT] =
 			chip->tsl2x7x_settings.prox_pulse_count;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHLO] =
-	chip->tsl2x7x_settings.prox_thres_low;
+			(chip->tsl2x7x_settings.prox_thres_low) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MINTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_low >> 8) & 0xFF;
 	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHLO] =
-			chip->tsl2x7x_settings.prox_thres_high;
+			(chip->tsl2x7x_settings.prox_thres_high) & 0xFF;
+	chip->tsl2x7x_config[TSL2X7X_PRX_MAXTHRESHHI] =
+			(chip->tsl2x7x_settings.prox_thres_high >> 8) & 0xFF;
 
 	/* and make sure we're not already on */
 	if (chip->tsl2x7x_chip_status == TSL2X7X_CHIP_WORKING) {
diff --git a/drivers/staging/imx-drm/Kconfig b/drivers/staging/imx-drm/Kconfig
index c6e8ba7b3e4..82fb758a29b 100644
--- a/drivers/staging/imx-drm/Kconfig
+++ b/drivers/staging/imx-drm/Kconfig
@@ -39,19 +39,10 @@ config DRM_IMX_LDB
 	  Choose this to enable the internal LVDS Display Bridge (LDB)
 	  found on i.MX53 and i.MX6 processors.
 
-config DRM_IMX_IPUV3_CORE
-	tristate "IPUv3 core support"
-	depends on DRM_IMX
-	depends on RESET_CONTROLLER
-	help
-	  Choose this if you have a i.MX5/6 system and want
-	  to use the IPU. This option only enables IPU base
-	  support.
-
 config DRM_IMX_IPUV3
 	tristate "DRM Support for i.MX IPUv3"
 	depends on DRM_IMX
-	depends on DRM_IMX_IPUV3_CORE
+	depends on IMX_IPUV3_CORE
 	help
 	  Choose this if you have a i.MX5 or i.MX6 processor.
 
diff --git a/drivers/staging/imx-drm/Makefile b/drivers/staging/imx-drm/Makefile
index 129e3a3f59f..582c438d8cb 100644
--- a/drivers/staging/imx-drm/Makefile
+++ b/drivers/staging/imx-drm/Makefile
@@ -6,7 +6,6 @@ obj-$(CONFIG_DRM_IMX) += imxdrm.o
 obj-$(CONFIG_DRM_IMX_PARALLEL_DISPLAY) += parallel-display.o
 obj-$(CONFIG_DRM_IMX_TVE) += imx-tve.o
 obj-$(CONFIG_DRM_IMX_LDB) += imx-ldb.o
-obj-$(CONFIG_DRM_IMX_IPUV3_CORE) += ipu-v3/
 
 imx-ipuv3-crtc-objs  := ipuv3-crtc.o ipuv3-plane.o
 obj-$(CONFIG_DRM_IMX_IPUV3)	+= imx-ipuv3-crtc.o
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index c270c9ae6d2..def8280d7ee 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -200,13 +200,6 @@ static const struct file_operations imx_drm_driver_fops = {
 	.llseek = noop_llseek,
 };
 
-int imx_drm_connector_mode_valid(struct drm_connector *connector,
-	struct drm_display_mode *mode)
-{
-	return MODE_OK;
-}
-EXPORT_SYMBOL(imx_drm_connector_mode_valid);
-
 void imx_drm_connector_destroy(struct drm_connector *connector)
 {
 	drm_sysfs_connector_remove(connector);
@@ -305,7 +298,7 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags)
 			dev_err(drm->dev,
 				"[CONNECTOR:%d:%s] drm_sysfs_connector_add failed: %d\n",
 				connector->base.id,
-				drm_get_connector_name(connector), ret);
+				connector->name, ret);
 			goto err_unbind;
 		}
 	}
diff --git a/drivers/staging/imx-drm/imx-drm.h b/drivers/staging/imx-drm/imx-drm.h
index a322bac5541..7453ae00c41 100644
--- a/drivers/staging/imx-drm/imx-drm.h
+++ b/drivers/staging/imx-drm/imx-drm.h
@@ -50,8 +50,6 @@ int imx_drm_encoder_get_mux_id(struct device_node *node,
 int imx_drm_encoder_parse_of(struct drm_device *drm,
 	struct drm_encoder *encoder, struct device_node *np);
 
-int imx_drm_connector_mode_valid(struct drm_connector *connector,
-	struct drm_display_mode *mode);
 void imx_drm_connector_destroy(struct drm_connector *connector);
 void imx_drm_encoder_destroy(struct drm_encoder *encoder);
 
diff --git a/drivers/staging/imx-drm/imx-hdmi.c b/drivers/staging/imx-drm/imx-hdmi.c
index 1b440483f28..18c9ccd460b 100644
--- a/drivers/staging/imx-drm/imx-hdmi.c
+++ b/drivers/staging/imx-drm/imx-hdmi.c
@@ -27,8 +27,8 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_encoder_slave.h>
+#include <video/imx-ipu-v3.h>
 
-#include "ipu-v3/imx-ipu-v3.h"
 #include "imx-hdmi.h"
 #include "imx-drm.h"
 
@@ -1490,7 +1490,6 @@ static struct drm_connector_funcs imx_hdmi_connector_funcs = {
 
 static struct drm_connector_helper_funcs imx_hdmi_connector_helper_funcs = {
 	.get_modes = imx_hdmi_connector_get_modes,
-	.mode_valid = imx_drm_connector_mode_valid,
 	.best_encoder = imx_hdmi_connector_best_encoder,
 };
 
diff --git a/drivers/staging/imx-drm/imx-ldb.c b/drivers/staging/imx-drm/imx-ldb.c
index fe4c1ef4e7a..7e3f019d7e7 100644
--- a/drivers/staging/imx-drm/imx-ldb.c
+++ b/drivers/staging/imx-drm/imx-ldb.c
@@ -317,7 +317,6 @@ static struct drm_connector_funcs imx_ldb_connector_funcs = {
 static struct drm_connector_helper_funcs imx_ldb_connector_helper_funcs = {
 	.get_modes = imx_ldb_connector_get_modes,
 	.best_encoder = imx_ldb_connector_best_encoder,
-	.mode_valid = imx_drm_connector_mode_valid,
 };
 
 static struct drm_encoder_funcs imx_ldb_encoder_funcs = {
diff --git a/drivers/staging/imx-drm/imx-tve.c b/drivers/staging/imx-drm/imx-tve.c
index a23f4f77314..c628fcdc22a 100644
--- a/drivers/staging/imx-drm/imx-tve.c
+++ b/drivers/staging/imx-drm/imx-tve.c
@@ -30,8 +30,8 @@
 #include <drm/drmP.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_crtc_helper.h>
+#include <video/imx-ipu-v3.h>
 
-#include "ipu-v3/imx-ipu-v3.h"
 #include "imx-drm.h"
 
 #define TVE_COM_CONF_REG	0x00
@@ -249,11 +249,6 @@ static int imx_tve_connector_mode_valid(struct drm_connector *connector,
 {
 	struct imx_tve *tve = con_to_tve(connector);
 	unsigned long rate;
-	int ret;
-
-	ret = imx_drm_connector_mode_valid(connector, mode);
-	if (ret != MODE_OK)
-		return ret;
 
 	/* pixel clock with 2x oversampling */
 	rate = clk_round_rate(tve->clk, 2000UL * mode->clock) / 2000;
diff --git a/drivers/staging/imx-drm/ipuv3-crtc.c b/drivers/staging/imx-drm/ipuv3-crtc.c
index 47bec5e1735..720868bff35 100644
--- a/drivers/staging/imx-drm/ipuv3-crtc.c
+++ b/drivers/staging/imx-drm/ipuv3-crtc.c
@@ -30,7 +30,7 @@
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_fb_cma_helper.h>
 
-#include "ipu-v3/imx-ipu-v3.h"
+#include <video/imx-ipu-v3.h>
 #include "imx-drm.h"
 #include "ipuv3-plane.h"
 
diff --git a/drivers/staging/imx-drm/ipuv3-plane.c b/drivers/staging/imx-drm/ipuv3-plane.c
index 5697e59ddf1..6f393a11f44 100644
--- a/drivers/staging/imx-drm/ipuv3-plane.c
+++ b/drivers/staging/imx-drm/ipuv3-plane.c
@@ -17,7 +17,7 @@
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 
-#include "ipu-v3/imx-ipu-v3.h"
+#include "video/imx-ipu-v3.h"
 #include "ipuv3-plane.h"
 
 #define to_ipu_plane(x)	container_of(x, struct ipu_plane, base)
diff --git a/drivers/staging/imx-drm/parallel-display.c b/drivers/staging/imx-drm/parallel-display.c
index eaf4dda1a0c..4ca61afdf62 100644
--- a/drivers/staging/imx-drm/parallel-display.c
+++ b/drivers/staging/imx-drm/parallel-display.c
@@ -148,7 +148,6 @@ static struct drm_connector_funcs imx_pd_connector_funcs = {
 static struct drm_connector_helper_funcs imx_pd_connector_helper_funcs = {
 	.get_modes = imx_pd_connector_get_modes,
 	.best_encoder = imx_pd_connector_best_encoder,
-	.mode_valid = imx_drm_connector_mode_valid,
 };
 
 static struct drm_encoder_funcs imx_pd_encoder_funcs = {
@@ -174,6 +173,13 @@ static int imx_pd_register(struct drm_device *drm,
 	if (ret)
 		return ret;
 
+	/* set the connector's dpms to OFF so that
+	 * drm_helper_connector_dpms() won't return
+	 * immediately since the current state is ON
+	 * at this point.
+	 */
+	imxpd->connector.dpms = DRM_MODE_DPMS_OFF;
+
 	drm_encoder_helper_add(&imxpd->encoder, &imx_pd_encoder_helper_funcs);
 	drm_encoder_init(drm, &imxpd->encoder, &imx_pd_encoder_funcs,
 			 DRM_MODE_ENCODER_NONE);
diff --git a/drivers/staging/lustre/lustre/include/lclient.h b/drivers/staging/lustre/lustre/include/lclient.h
index 827209ea6bd..386a36c00f5 100644
--- a/drivers/staging/lustre/lustre/include/lclient.h
+++ b/drivers/staging/lustre/lustre/include/lclient.h
@@ -82,16 +82,7 @@ struct ccc_io {
 	/**
 	 * I/O vector information to or from which read/write is going.
 	 */
-	struct iovec *cui_iov;
-	unsigned long cui_nrsegs;
-	/**
-	 * Total iov count for left IO.
-	 */
-	unsigned long cui_tot_nrsegs;
-	/**
-	 * Old length for iov that was truncated partially.
-	 */
-	size_t cui_iov_olen;
+	struct iov_iter *cui_iter;
 	/**
 	 * Total size for the left IO.
 	 */
diff --git a/drivers/staging/lustre/lustre/lclient/lcommon_cl.c b/drivers/staging/lustre/lustre/lclient/lcommon_cl.c
index dc24cfa5803..1b0c216bc56 100644
--- a/drivers/staging/lustre/lustre/lclient/lcommon_cl.c
+++ b/drivers/staging/lustre/lustre/lclient/lcommon_cl.c
@@ -720,31 +720,12 @@ int ccc_io_one_lock_index(const struct lu_env *env, struct cl_io *io,
 void ccc_io_update_iov(const struct lu_env *env,
 		       struct ccc_io *cio, struct cl_io *io)
 {
-	int i;
 	size_t size = io->u.ci_rw.crw_count;
 
-	cio->cui_iov_olen = 0;
-	if (!cl_is_normalio(env, io) || cio->cui_tot_nrsegs == 0)
+	if (!cl_is_normalio(env, io) || cio->cui_iter == NULL)
 		return;
 
-	for (i = 0; i < cio->cui_tot_nrsegs; i++) {
-		struct iovec *iv = &cio->cui_iov[i];
-
-		if (iv->iov_len < size)
-			size -= iv->iov_len;
-		else {
-			if (iv->iov_len > size) {
-				cio->cui_iov_olen = iv->iov_len;
-				iv->iov_len = size;
-			}
-			break;
-		}
-	}
-
-	cio->cui_nrsegs = i + 1;
-	LASSERTF(cio->cui_tot_nrsegs >= cio->cui_nrsegs,
-		 "tot_nrsegs: %lu, nrsegs: %lu\n",
-		 cio->cui_tot_nrsegs, cio->cui_nrsegs);
+	iov_iter_truncate(cio->cui_iter, size);
 }
 
 int ccc_io_one_lock(const struct lu_env *env, struct cl_io *io,
@@ -775,30 +756,7 @@ void ccc_io_advance(const struct lu_env *env,
 	if (!cl_is_normalio(env, io))
 		return;
 
-	LASSERT(cio->cui_tot_nrsegs >= cio->cui_nrsegs);
-	LASSERT(cio->cui_tot_count  >= nob);
-
-	cio->cui_iov	+= cio->cui_nrsegs;
-	cio->cui_tot_nrsegs -= cio->cui_nrsegs;
-	cio->cui_tot_count  -= nob;
-
-	/* update the iov */
-	if (cio->cui_iov_olen > 0) {
-		struct iovec *iv;
-
-		cio->cui_iov--;
-		cio->cui_tot_nrsegs++;
-		iv = &cio->cui_iov[0];
-		if (io->ci_continue) {
-			iv->iov_base += iv->iov_len;
-			LASSERT(cio->cui_iov_olen > iv->iov_len);
-			iv->iov_len = cio->cui_iov_olen - iv->iov_len;
-		} else {
-			/* restore the iov_len, in case of restart io. */
-			iv->iov_len = cio->cui_iov_olen;
-		}
-		cio->cui_iov_olen = 0;
-	}
+	iov_iter_reexpand(cio->cui_iter, cio->cui_tot_count  -= nob);
 }
 
 /**
diff --git a/drivers/staging/lustre/lustre/llite/file.c b/drivers/staging/lustre/lustre/llite/file.c
index c4ddec2b358..716e1ee0104 100644
--- a/drivers/staging/lustre/lustre/llite/file.c
+++ b/drivers/staging/lustre/lustre/llite/file.c
@@ -1114,9 +1114,7 @@ restart:
 
 		switch (vio->cui_io_subtype) {
 		case IO_NORMAL:
-			cio->cui_iov = args->u.normal.via_iov;
-			cio->cui_nrsegs = args->u.normal.via_nrsegs;
-			cio->cui_tot_nrsegs = cio->cui_nrsegs;
+			cio->cui_iter = args->u.normal.via_iter;
 			cio->cui_iocb = args->u.normal.via_iocb;
 			if ((iot == CIT_WRITE) &&
 			    !(cio->cui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
@@ -1180,58 +1178,23 @@ out:
 	return result;
 }
 
-static ssize_t ll_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+static ssize_t ll_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct lu_env      *env;
 	struct vvp_io_args *args;
-	size_t	      count = 0;
 	ssize_t	     result;
 	int		 refcheck;
 
-	result = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
-	if (result)
-		return result;
-
 	env = cl_env_get(&refcheck);
 	if (IS_ERR(env))
 		return PTR_ERR(env);
 
 	args = vvp_env_args(env, IO_NORMAL);
-	args->u.normal.via_iov = (struct iovec *)iov;
-	args->u.normal.via_nrsegs = nr_segs;
+	args->u.normal.via_iter = to;
 	args->u.normal.via_iocb = iocb;
 
 	result = ll_file_io_generic(env, args, iocb->ki_filp, CIT_READ,
-				    &iocb->ki_pos, count);
-	cl_env_put(env, &refcheck);
-	return result;
-}
-
-static ssize_t ll_file_read(struct file *file, char *buf, size_t count,
-			    loff_t *ppos)
-{
-	struct lu_env *env;
-	struct iovec  *local_iov;
-	struct kiocb  *kiocb;
-	ssize_t	result;
-	int	    refcheck;
-
-	env = cl_env_get(&refcheck);
-	if (IS_ERR(env))
-		return PTR_ERR(env);
-
-	local_iov = &vvp_env_info(env)->vti_local_iov;
-	kiocb = &vvp_env_info(env)->vti_kiocb;
-	local_iov->iov_base = (void __user *)buf;
-	local_iov->iov_len = count;
-	init_sync_kiocb(kiocb, file);
-	kiocb->ki_pos = *ppos;
-	kiocb->ki_nbytes = count;
-
-	result = ll_file_aio_read(kiocb, local_iov, 1, kiocb->ki_pos);
-	*ppos = kiocb->ki_pos;
-
+				    &iocb->ki_pos, iov_iter_count(to));
 	cl_env_put(env, &refcheck);
 	return result;
 }
@@ -1239,64 +1202,27 @@ static ssize_t ll_file_read(struct file *file, char *buf, size_t count,
 /*
  * Write to a file (through the page cache).
  */
-static ssize_t ll_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				 unsigned long nr_segs, loff_t pos)
+static ssize_t ll_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct lu_env      *env;
 	struct vvp_io_args *args;
-	size_t	      count = 0;
 	ssize_t	     result;
 	int		 refcheck;
 
-	result = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
-	if (result)
-		return result;
-
 	env = cl_env_get(&refcheck);
 	if (IS_ERR(env))
 		return PTR_ERR(env);
 
 	args = vvp_env_args(env, IO_NORMAL);
-	args->u.normal.via_iov = (struct iovec *)iov;
-	args->u.normal.via_nrsegs = nr_segs;
+	args->u.normal.via_iter = from;
 	args->u.normal.via_iocb = iocb;
 
 	result = ll_file_io_generic(env, args, iocb->ki_filp, CIT_WRITE,
-				  &iocb->ki_pos, count);
+				  &iocb->ki_pos, iov_iter_count(from));
 	cl_env_put(env, &refcheck);
 	return result;
 }
 
-static ssize_t ll_file_write(struct file *file, const char *buf, size_t count,
-			     loff_t *ppos)
-{
-	struct lu_env *env;
-	struct iovec  *local_iov;
-	struct kiocb  *kiocb;
-	ssize_t	result;
-	int	    refcheck;
-
-	env = cl_env_get(&refcheck);
-	if (IS_ERR(env))
-		return PTR_ERR(env);
-
-	local_iov = &vvp_env_info(env)->vti_local_iov;
-	kiocb = &vvp_env_info(env)->vti_kiocb;
-	local_iov->iov_base = (void __user *)buf;
-	local_iov->iov_len = count;
-	init_sync_kiocb(kiocb, file);
-	kiocb->ki_pos = *ppos;
-	kiocb->ki_nbytes = count;
-
-	result = ll_file_aio_write(kiocb, local_iov, 1, kiocb->ki_pos);
-	*ppos = kiocb->ki_pos;
-
-	cl_env_put(env, &refcheck);
-	return result;
-}
-
-
-
 /*
  * Send file content (through pagecache) somewhere with helper
  */
@@ -3143,10 +3069,10 @@ int ll_inode_permission(struct inode *inode, int mask)
 
 /* -o localflock - only provides locally consistent flock locks */
 struct file_operations ll_file_operations = {
-	.read	   = ll_file_read,
-	.aio_read = ll_file_aio_read,
-	.write	  = ll_file_write,
-	.aio_write = ll_file_aio_write,
+	.read	   = new_sync_read,
+	.read_iter = ll_file_read_iter,
+	.write	  = new_sync_write,
+	.write_iter = ll_file_write_iter,
 	.unlocked_ioctl = ll_file_ioctl,
 	.open	   = ll_file_open,
 	.release	= ll_file_release,
@@ -3158,10 +3084,10 @@ struct file_operations ll_file_operations = {
 };
 
 struct file_operations ll_file_operations_flock = {
-	.read	   = ll_file_read,
-	.aio_read    = ll_file_aio_read,
-	.write	  = ll_file_write,
-	.aio_write   = ll_file_aio_write,
+	.read	   = new_sync_read,
+	.read_iter    = ll_file_read_iter,
+	.write	  = new_sync_write,
+	.write_iter   = ll_file_write_iter,
 	.unlocked_ioctl = ll_file_ioctl,
 	.open	   = ll_file_open,
 	.release	= ll_file_release,
@@ -3176,10 +3102,10 @@ struct file_operations ll_file_operations_flock = {
 
 /* These are for -o noflock - to return ENOSYS on flock calls */
 struct file_operations ll_file_operations_noflock = {
-	.read	   = ll_file_read,
-	.aio_read    = ll_file_aio_read,
-	.write	  = ll_file_write,
-	.aio_write   = ll_file_aio_write,
+	.read	   = new_sync_read,
+	.read_iter    = ll_file_read_iter,
+	.write	  = new_sync_write,
+	.write_iter   = ll_file_write_iter,
 	.unlocked_ioctl = ll_file_ioctl,
 	.open	   = ll_file_open,
 	.release	= ll_file_release,
diff --git a/drivers/staging/lustre/lustre/llite/llite_internal.h b/drivers/staging/lustre/lustre/llite/llite_internal.h
index dde7632ba01..140ee947ba4 100644
--- a/drivers/staging/lustre/lustre/llite/llite_internal.h
+++ b/drivers/staging/lustre/lustre/llite/llite_internal.h
@@ -917,8 +917,7 @@ struct vvp_io_args {
 	union {
 		struct {
 			struct kiocb      *via_iocb;
-			struct iovec      *via_iov;
-			unsigned long      via_nrsegs;
+			struct iov_iter   *via_iter;
 		} normal;
 		struct {
 			struct pipe_inode_info  *via_pipe;
diff --git a/drivers/staging/lustre/lustre/llite/rw.c b/drivers/staging/lustre/lustre/llite/rw.c
index f0122c568a0..56162103cc7 100644
--- a/drivers/staging/lustre/lustre/llite/rw.c
+++ b/drivers/staging/lustre/lustre/llite/rw.c
@@ -151,8 +151,7 @@ static struct ll_cl_context *ll_cl_init(struct file *file,
 		result = cl_io_rw_init(env, io, CIT_WRITE, pos, PAGE_CACHE_SIZE);
 		if (result == 0) {
 			cio->cui_fd = LUSTRE_FPRIVATE(file);
-			cio->cui_iov = NULL;
-			cio->cui_nrsegs = 0;
+			cio->cui_iter = NULL;
 			result = cl_io_iter_init(env, io);
 			if (result == 0) {
 				result = cl_io_lock(env, io);
diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c
index 55ca8d3c3e4..af84c1aaa5f 100644
--- a/drivers/staging/lustre/lustre/llite/rw26.c
+++ b/drivers/staging/lustre/lustre/llite/rw26.c
@@ -218,14 +218,11 @@ static void ll_free_user_pages(struct page **pages, int npages, int do_dirty)
 	int i;
 
 	for (i = 0; i < npages; i++) {
-		if (pages[i] == NULL)
-			break;
 		if (do_dirty)
 			set_page_dirty_lock(pages[i]);
 		page_cache_release(pages[i]);
 	}
-
-	OBD_FREE_LARGE(pages, npages * sizeof(*pages));
+	kvfree(pages);
 }
 
 ssize_t ll_direct_rw_pages(const struct lu_env *env, struct cl_io *io,
@@ -363,18 +360,16 @@ static ssize_t ll_direct_IO_26_seg(const struct lu_env *env, struct cl_io *io,
 #define MAX_DIO_SIZE ((MAX_MALLOC / sizeof(struct brw_page) * PAGE_CACHE_SIZE) & \
 		      ~(DT_MAX_BRW_SIZE - 1))
 static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
-			       const struct iovec *iov, loff_t file_offset,
-			       unsigned long nr_segs)
+			       struct iov_iter *iter, loff_t file_offset)
 {
 	struct lu_env *env;
 	struct cl_io *io;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct ccc_object *obj = cl_inode2ccc(inode);
-	long count = iov_length(iov, nr_segs);
-	long tot_bytes = 0, result = 0;
+	ssize_t count = iov_iter_count(iter);
+	ssize_t tot_bytes = 0, result = 0;
 	struct ll_inode_info *lli = ll_i2info(inode);
-	unsigned long seg = 0;
 	long size = MAX_DIO_SIZE;
 	int refcheck;
 
@@ -392,11 +387,8 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
 	       MAX_DIO_SIZE >> PAGE_CACHE_SHIFT);
 
 	/* Check that all user buffers are aligned as well */
-	for (seg = 0; seg < nr_segs; seg++) {
-		if (((unsigned long)iov[seg].iov_base & ~CFS_PAGE_MASK) ||
-		    (iov[seg].iov_len & ~CFS_PAGE_MASK))
-			return -EINVAL;
-	}
+	if (iov_iter_alignment(iter) & ~CFS_PAGE_MASK)
+		return -EINVAL;
 
 	env = cl_env_get(&refcheck);
 	LASSERT(!IS_ERR(env));
@@ -411,63 +403,49 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
 		mutex_lock(&inode->i_mutex);
 
 	LASSERT(obj->cob_transient_pages == 0);
-	for (seg = 0; seg < nr_segs; seg++) {
-		long iov_left = iov[seg].iov_len;
-		unsigned long user_addr = (unsigned long)iov[seg].iov_base;
+	while (iov_iter_count(iter)) {
+		struct page **pages;
+		size_t offs;
 
+		count = min_t(size_t, iov_iter_count(iter), size);
 		if (rw == READ) {
 			if (file_offset >= i_size_read(inode))
 				break;
-			if (file_offset + iov_left > i_size_read(inode))
-				iov_left = i_size_read(inode) - file_offset;
+			if (file_offset + count > i_size_read(inode))
+				count = i_size_read(inode) - file_offset;
 		}
 
-		while (iov_left > 0) {
-			struct page **pages;
-			int page_count, max_pages = 0;
-			long bytes;
-
-			bytes = min(size, iov_left);
-			page_count = ll_get_user_pages(rw, user_addr, bytes,
-						       &pages, &max_pages);
-			if (likely(page_count > 0)) {
-				if (unlikely(page_count <  max_pages))
-					bytes = page_count << PAGE_CACHE_SHIFT;
-				result = ll_direct_IO_26_seg(env, io, rw, inode,
-							     file->f_mapping,
-							     bytes, file_offset,
-							     pages, page_count);
-				ll_free_user_pages(pages, max_pages, rw==READ);
-			} else if (page_count == 0) {
-				GOTO(out, result = -EFAULT);
-			} else {
-				result = page_count;
-			}
-			if (unlikely(result <= 0)) {
-				/* If we can't allocate a large enough buffer
-				 * for the request, shrink it to a smaller
-				 * PAGE_SIZE multiple and try again.
-				 * We should always be able to kmalloc for a
-				 * page worth of page pointers = 4MB on i386. */
-				if (result == -ENOMEM &&
-				    size > (PAGE_CACHE_SIZE / sizeof(*pages)) *
-					   PAGE_CACHE_SIZE) {
-					size = ((((size / 2) - 1) |
-						 ~CFS_PAGE_MASK) + 1) &
-						CFS_PAGE_MASK;
-					CDEBUG(D_VFSTRACE,"DIO size now %lu\n",
-					       size);
-					continue;
-				}
-
-				GOTO(out, result);
+		result = iov_iter_get_pages_alloc(iter, &pages, count, &offs);
+		if (likely(result > 0)) {
+			int n = (result + offs + PAGE_SIZE - 1) / PAGE_SIZE;
+			result = ll_direct_IO_26_seg(env, io, rw, inode,
+						     file->f_mapping,
+						     result, file_offset,
+						     pages, n);
+			ll_free_user_pages(pages, n, rw==READ);
+		}
+		if (unlikely(result <= 0)) {
+			/* If we can't allocate a large enough buffer
+			 * for the request, shrink it to a smaller
+			 * PAGE_SIZE multiple and try again.
+			 * We should always be able to kmalloc for a
+			 * page worth of page pointers = 4MB on i386. */
+			if (result == -ENOMEM &&
+			    size > (PAGE_CACHE_SIZE / sizeof(*pages)) *
+				   PAGE_CACHE_SIZE) {
+				size = ((((size / 2) - 1) |
+					 ~CFS_PAGE_MASK) + 1) &
+					CFS_PAGE_MASK;
+				CDEBUG(D_VFSTRACE,"DIO size now %lu\n",
+				       size);
+				continue;
 			}
 
-			tot_bytes += result;
-			file_offset += result;
-			iov_left -= result;
-			user_addr += result;
+			GOTO(out, result);
 		}
+		iov_iter_advance(iter, result);
+		tot_bytes += result;
+		file_offset += result;
 	}
 out:
 	LASSERT(obj->cob_transient_pages == 0);
diff --git a/drivers/staging/lustre/lustre/llite/vvp_io.c b/drivers/staging/lustre/lustre/llite/vvp_io.c
index 7dd2b4723c5..0e0b404cb5e 100644
--- a/drivers/staging/lustre/lustre/llite/vvp_io.c
+++ b/drivers/staging/lustre/lustre/llite/vvp_io.c
@@ -211,27 +211,26 @@ static int vvp_mmap_locks(const struct lu_env *env,
 	struct cl_lock_descr   *descr = &cti->cti_descr;
 	ldlm_policy_data_t      policy;
 	unsigned long	   addr;
-	unsigned long	   seg;
 	ssize_t		 count;
 	int		     result;
+	struct iov_iter i;
+	struct iovec iov;
 
 	LASSERT(io->ci_type == CIT_READ || io->ci_type == CIT_WRITE);
 
 	if (!cl_is_normalio(env, io))
 		return 0;
 
-	if (vio->cui_iov == NULL) /* nfs or loop back device write */
+	if (vio->cui_iter == NULL) /* nfs or loop back device write */
 		return 0;
 
 	/* No MM (e.g. NFS)? No vmas too. */
 	if (mm == NULL)
 		return 0;
 
-	for (seg = 0; seg < vio->cui_nrsegs; seg++) {
-		const struct iovec *iv = &vio->cui_iov[seg];
-
-		addr = (unsigned long)iv->iov_base;
-		count = iv->iov_len;
+	iov_for_each(iov, i, *(vio->cui_iter)) {
+		addr = (unsigned long)iov.iov_base;
+		count = iov.iov_len;
 		if (count == 0)
 			continue;
 
@@ -527,9 +526,7 @@ static int vvp_io_read_start(const struct lu_env *env,
 	switch (vio->cui_io_subtype) {
 	case IO_NORMAL:
 		LASSERT(cio->cui_iocb->ki_pos == pos);
-		result = generic_file_aio_read(cio->cui_iocb,
-					       cio->cui_iov, cio->cui_nrsegs,
-					       cio->cui_iocb->ki_pos);
+		result = generic_file_read_iter(cio->cui_iocb, cio->cui_iter);
 		break;
 	case IO_SPLICE:
 		result = generic_file_splice_read(file, &pos,
@@ -595,12 +592,11 @@ static int vvp_io_write_start(const struct lu_env *env,
 
 	CDEBUG(D_VFSTRACE, "write: [%lli, %lli)\n", pos, pos + (long long)cnt);
 
-	if (cio->cui_iov == NULL) /* from a temp io in ll_cl_init(). */
+	if (cio->cui_iter == NULL) /* from a temp io in ll_cl_init(). */
 		result = 0;
 	else
-		result = generic_file_aio_write(cio->cui_iocb,
-						cio->cui_iov, cio->cui_nrsegs,
-						cio->cui_iocb->ki_pos);
+		result = generic_file_write_iter(cio->cui_iocb, cio->cui_iter);
+
 	if (result > 0) {
 		if (result < cnt)
 			io->ci_continue = 0;
@@ -1162,10 +1158,9 @@ int vvp_io_init(const struct lu_env *env, struct cl_object *obj,
 		 *  results."  -- Single Unix Spec */
 		if (count == 0)
 			result = 1;
-		else {
+		else
 			cio->cui_tot_count = count;
-			cio->cui_tot_nrsegs = 0;
-		}
+
 		/* for read/write, we store the jobid in the inode, and
 		 * it'll be fetched by osc when building RPC.
 		 *
diff --git a/drivers/staging/media/omap4iss/Kconfig b/drivers/staging/media/omap4iss/Kconfig
index 78b0fba7047..8afc6fee40c 100644
--- a/drivers/staging/media/omap4iss/Kconfig
+++ b/drivers/staging/media/omap4iss/Kconfig
@@ -1,6 +1,6 @@
 config VIDEO_OMAP4
 	bool "OMAP 4 Camera support"
-	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && I2C && ARCH_OMAP4
+	depends on VIDEO_V4L2=y && VIDEO_V4L2_SUBDEV_API && I2C=y && ARCH_OMAP4
 	select VIDEOBUF2_DMA_CONTIG
 	---help---
 	  Driver for an OMAP 4 ISS controller.
diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c
index ded31ea6bd3..cbf455d66f7 100644
--- a/drivers/staging/media/omap4iss/iss_video.c
+++ b/drivers/staging/media/omap4iss/iss_video.c
@@ -396,7 +396,7 @@ static void iss_video_buf_queue(struct vb2_buffer *vb)
 	}
 }
 
-static struct vb2_ops iss_video_vb2ops = {
+static const struct vb2_ops iss_video_vb2ops = {
 	.queue_setup	= iss_video_queue_setup,
 	.buf_prepare	= iss_video_buf_prepare,
 	.buf_queue	= iss_video_buf_queue,
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index 75d7c63cb41..e320d6bae91 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -1067,7 +1067,7 @@ static int xlr_net_probe(struct platform_device *pdev)
 	xlr_set_rx_mode(ndev);
 
 	priv->num_rx_desc += MAX_NUM_DESC_SPILL;
-	SET_ETHTOOL_OPS(ndev, &xlr_ethtool_ops);
+	ndev->ethtool_ops = &xlr_ethtool_ops;
 	SET_NETDEV_DEV(ndev, &pdev->dev);
 
 	/* Common registers, do one time initialization */
diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c
index ff7214aac9d..da9dd6bc566 100644
--- a/drivers/staging/octeon/ethernet.c
+++ b/drivers/staging/octeon/ethernet.c
@@ -469,7 +469,7 @@ int cvm_oct_common_init(struct net_device *dev)
 
 	/* We do our own locking, Linux doesn't need to */
 	dev->features |= NETIF_F_LLTX;
-	SET_ETHTOOL_OPS(dev, &cvm_oct_ethtool_ops);
+	dev->ethtool_ops = &cvm_oct_ethtool_ops;
 
 	cvm_oct_phy_setup_device(dev);
 	cvm_oct_set_mac_filter(dev);
diff --git a/drivers/staging/rtl8192ee/core.c b/drivers/staging/rtl8192ee/core.c
index 76ea356163b..7f6accd5998 100644
--- a/drivers/staging/rtl8192ee/core.c
+++ b/drivers/staging/rtl8192ee/core.c
@@ -322,7 +322,7 @@ static void _rtl_add_wowlan_patterns(struct ieee80211_hw *hw,
 	struct rtl_mac *mac = &(rtlpriv->mac80211);
 	struct cfg80211_pkt_pattern *patterns = wow->patterns;
 	struct rtl_wow_pattern rtl_pattern;
-	u8 *pattern_os, *mask_os;
+	const u8 *pattern_os, *mask_os;
 	u8 mask[MAX_WOL_BIT_MASK_SIZE] = {0};
 	u8 content[MAX_WOL_PATTERN_SIZE] = {0};
 	u8 broadcast_addr[6] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
@@ -1561,7 +1561,7 @@ static void rtl_op_rfkill_poll(struct ieee80211_hw *hw)
  * before switch channle or power save, or tx buffer packet
  * maybe send after offchannel or rf sleep, this may cause
  * dis-association by AP */
-static void rtl_op_flush(struct ieee80211_hw *hw,
+static void rtl_op_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 u32 queues, bool drop)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
diff --git a/drivers/staging/rtl8723au/hal/rtl8723a_hal_init.c b/drivers/staging/rtl8723au/hal/rtl8723a_hal_init.c
index 0acacab95a4..46f5abcbaee 100644
--- a/drivers/staging/rtl8723au/hal/rtl8723a_hal_init.c
+++ b/drivers/staging/rtl8723au/hal/rtl8723a_hal_init.c
@@ -298,7 +298,7 @@ int rtl8723a_FirmwareDownload(struct rtw_adapter *padapter)
 	RT_TRACE(_module_hal_init_c_, _drv_info_, ("+%s\n", __func__));
 
 	if (IS_8723A_A_CUT(pHalData->VersionID)) {
-		fw_name = "rtlwifi/rtl8723aufw.bin";
+		fw_name = "rtlwifi/rtl8723aufw_A.bin";
 		RT_TRACE(_module_hal_init_c_, _drv_info_,
 			 ("rtl8723a_FirmwareDownload: R8723FwImageArray_UMC "
 			  "for RTL8723A A CUT\n"));
diff --git a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
index 0c9f5cebfb4..f0839f6a934 100644
--- a/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
+++ b/drivers/staging/rtl8723au/os_dep/ioctl_cfg80211.c
@@ -1227,7 +1227,7 @@ static int cfg80211_rtw_set_default_key(struct wiphy *wiphy,
 
 static int cfg80211_rtw_get_station(struct wiphy *wiphy,
 				    struct net_device *ndev,
-				    u8 *mac, struct station_info *sinfo)
+				    const u8 *mac, struct station_info *sinfo)
 {
 	int ret = 0;
 	struct rtw_adapter *padapter = wiphy_to_adapter(wiphy);
@@ -2903,7 +2903,7 @@ static int cfg80211_rtw_stop_ap(struct wiphy *wiphy, struct net_device *ndev)
 }
 
 static int cfg80211_rtw_add_station(struct wiphy *wiphy,
-				    struct net_device *ndev, u8 *mac,
+				    struct net_device *ndev, const u8 *mac,
 				    struct station_parameters *params)
 {
 	DBG_8723A("%s(%s)\n", __func__, ndev->name);
@@ -2912,7 +2912,7 @@ static int cfg80211_rtw_add_station(struct wiphy *wiphy,
 }
 
 static int cfg80211_rtw_del_station(struct wiphy *wiphy,
-				    struct net_device *ndev, u8 *mac)
+				    struct net_device *ndev, const u8 *mac)
 {
 	int ret = 0;
 	struct list_head *phead, *plist, *ptmp;
@@ -2988,7 +2988,7 @@ static int cfg80211_rtw_del_station(struct wiphy *wiphy,
 }
 
 static int cfg80211_rtw_change_station(struct wiphy *wiphy,
-				       struct net_device *ndev, u8 *mac,
+				       struct net_device *ndev, const u8 *mac,
 				       struct station_parameters *params)
 {
 	DBG_8723A("%s(%s)\n", __func__, ndev->name);
diff --git a/drivers/staging/rtl8723au/os_dep/os_intfs.c b/drivers/staging/rtl8723au/os_dep/os_intfs.c
index 4e32003a443..1fb34386a4e 100644
--- a/drivers/staging/rtl8723au/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8723au/os_dep/os_intfs.c
@@ -29,7 +29,9 @@ MODULE_AUTHOR("Realtek Semiconductor Corp.");
 MODULE_AUTHOR("Larry Finger <Larry.Finger@lwfinger.net>");
 MODULE_AUTHOR("Jes Sorensen <Jes.Sorensen@redhat.com>");
 MODULE_VERSION(DRIVERVERSION);
-MODULE_FIRMWARE("rtlwifi/rtl8821aefw.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8723aufw_A.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8723aufw_B.bin");
+MODULE_FIRMWARE("rtlwifi/rtl8723aufw_B_NoBT.bin");
 
 /* module param defaults */
 static int rtw_chip_version = 0x00;
diff --git a/drivers/staging/rtl8723au/os_dep/usb_intf.c b/drivers/staging/rtl8723au/os_dep/usb_intf.c
index 8b25c1aa202..ebb19b22f47 100644
--- a/drivers/staging/rtl8723au/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8723au/os_dep/usb_intf.c
@@ -530,8 +530,10 @@ int rtw_resume_process23a(struct rtw_adapter *padapter)
 	pwrpriv->bkeepfwalive = false;
 
 	DBG_8723A("bkeepfwalive(%x)\n", pwrpriv->bkeepfwalive);
-	if (pm_netdev_open23a(pnetdev, true) != 0)
+	if (pm_netdev_open23a(pnetdev, true) != 0) {
+		up(&pwrpriv->lock);
 		goto exit;
+	}
 
 	netif_device_attach(pnetdev);
 	netif_carrier_on(pnetdev);
diff --git a/drivers/staging/rtl8821ae/core.c b/drivers/staging/rtl8821ae/core.c
index 9a37408708f..046be2ce9c1 100644
--- a/drivers/staging/rtl8821ae/core.c
+++ b/drivers/staging/rtl8821ae/core.c
@@ -1278,7 +1278,9 @@ static void rtl_op_rfkill_poll(struct ieee80211_hw *hw)
  * before switch channel or power save, or tx buffer packet
  * maybe send after offchannel or rf sleep, this may cause
  * dis-association by AP */
-static void rtl_op_flush(struct ieee80211_hw *hw, u32 queues, bool drop)
+static void rtl_op_flush(struct ieee80211_hw *hw,
+			 struct ieee80211_vif *vif,
+			 u32 queues, bool drop)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
diff --git a/drivers/staging/tidspbridge/core/tiomap3430.c b/drivers/staging/tidspbridge/core/tiomap3430.c
index 8945b4e3a2a..cb50120ed7b 100644
--- a/drivers/staging/tidspbridge/core/tiomap3430.c
+++ b/drivers/staging/tidspbridge/core/tiomap3430.c
@@ -280,8 +280,10 @@ static int bridge_brd_monitor(struct bridge_dev_context *dev_ctxt)
 					OMAP3430_IVA2_MOD, OMAP2_CM_CLKSTCTRL);
 
 		/* Wait until the state has moved to ON */
-		while (*pdata->dsp_prm_read(OMAP3430_IVA2_MOD, OMAP2_PM_PWSTST)&
-					OMAP_INTRANSITION_MASK);
+		while ((*pdata->dsp_prm_read)(OMAP3430_IVA2_MOD,
+					      OMAP2_PM_PWSTST) &
+						OMAP_INTRANSITION_MASK)
+			;
 		/* Disable Automatic transition */
 		(*pdata->dsp_cm_write)(OMAP34XX_CLKSTCTRL_DISABLE_AUTO,
 					OMAP3430_IVA2_MOD, OMAP2_CM_CLKSTCTRL);
diff --git a/drivers/staging/vt6655/bssdb.c b/drivers/staging/vt6655/bssdb.c
index 59679cd4681..69b80e80b01 100644
--- a/drivers/staging/vt6655/bssdb.c
+++ b/drivers/staging/vt6655/bssdb.c
@@ -981,7 +981,7 @@ start:
 		pDevice->byERPFlag &= ~(WLAN_SET_ERP_USE_PROTECTION(1));
 	}
 
-	{
+	if (pDevice->eCommandState == WLAN_ASSOCIATE_WAIT) {
 		pDevice->byReAssocCount++;
 		/* 10 sec timeout */
 		if ((pDevice->byReAssocCount > 10) && (!pDevice->bLinkPass)) {
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index 1d3908d044d..5a5fd937a44 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -2318,6 +2318,7 @@ static  irqreturn_t  device_intr(int irq,  void *dev_instance) {
 	int             handled = 0;
 	unsigned char byData = 0;
 	int             ii = 0;
+	unsigned long flags;
 
 	MACvReadISR(pDevice->PortOffset, &pDevice->dwIsr);
 
@@ -2331,7 +2332,8 @@ static  irqreturn_t  device_intr(int irq,  void *dev_instance) {
 
 	handled = 1;
 	MACvIntDisable(pDevice->PortOffset);
-	spin_lock_irq(&pDevice->lock);
+
+	spin_lock_irqsave(&pDevice->lock, flags);
 
 	//Make sure current page is 0
 	VNSvInPortB(pDevice->PortOffset + MAC_REG_PAGE1SEL, &byOrgPageSel);
@@ -2560,7 +2562,8 @@ static  irqreturn_t  device_intr(int irq,  void *dev_instance) {
 	if (byOrgPageSel == 1)
 		MACvSelectPage1(pDevice->PortOffset);
 
-	spin_unlock_irq(&pDevice->lock);
+	spin_unlock_irqrestore(&pDevice->lock, flags);
+
 	MACvIntEnable(pDevice->PortOffset, IMR_MASK_VALUE);
 
 	return IRQ_RETVAL(handled);
diff --git a/drivers/staging/wlan-ng/cfg80211.c b/drivers/staging/wlan-ng/cfg80211.c
index f76f95c2961..723319ee08f 100644
--- a/drivers/staging/wlan-ng/cfg80211.c
+++ b/drivers/staging/wlan-ng/cfg80211.c
@@ -84,7 +84,7 @@ static int prism2_domibset_uint32(wlandevice_t *wlandev, u32 did, u32 data)
 }
 
 static int prism2_domibset_pstr32(wlandevice_t *wlandev,
-				  u32 did, u8 len, u8 *data)
+				  u32 did, u8 len, const u8 *data)
 {
 	struct p80211msg_dot11req_mibset msg;
 	p80211item_pstr32_t *mibitem =
@@ -298,7 +298,7 @@ static int prism2_set_default_key(struct wiphy *wiphy, struct net_device *dev,
 
 
 static int prism2_get_station(struct wiphy *wiphy, struct net_device *dev,
-			      u8 *mac, struct station_info *sinfo)
+			      const u8 *mac, struct station_info *sinfo)
 {
 	wlandevice_t *wlandev = dev->ml_priv;
 	struct p80211msg_lnxreq_commsquality quality;
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 9189bc0a87a..1f4c794f5fc 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -300,7 +300,7 @@ bool iscsit_check_np_match(
 		port = ntohs(sock_in->sin_port);
 	}
 
-	if ((ip_match == true) && (np->np_port == port) &&
+	if (ip_match && (np->np_port == port) &&
 	    (np->np_network_transport == network_transport))
 		return true;
 
@@ -325,7 +325,7 @@ static struct iscsi_np *iscsit_get_np(
 		}
 
 		match = iscsit_check_np_match(sockaddr, np, network_transport);
-		if (match == true) {
+		if (match) {
 			/*
 			 * Increment the np_exports reference count now to
 			 * prevent iscsit_del_np() below from being called
@@ -1121,7 +1121,7 @@ iscsit_get_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr,
 	/*
 	 * Special case for Unsupported SAM WRITE Opcodes and ImmediateData=Yes.
 	 */
-	if (dump_payload == true)
+	if (dump_payload)
 		goto after_immediate_data;
 
 	immed_ret = iscsit_handle_immediate_data(cmd, hdr,
@@ -1309,7 +1309,7 @@ iscsit_check_dataout_hdr(struct iscsi_conn *conn, unsigned char *buf,
 	if (cmd->data_direction != DMA_TO_DEVICE) {
 		pr_err("Command ITT: 0x%08x received DataOUT for a"
 			" NON-WRITE command.\n", cmd->init_task_tag);
-		return iscsit_reject_cmd(cmd, ISCSI_REASON_PROTOCOL_ERROR, buf);
+		return iscsit_dump_data_payload(conn, payload_length, 1);
 	}
 	se_cmd = &cmd->se_cmd;
 	iscsit_mod_dataout_timer(cmd);
@@ -3390,7 +3390,9 @@ static bool iscsit_check_inaddr_any(struct iscsi_np *np)
 
 #define SENDTARGETS_BUF_LIMIT 32768U
 
-static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd)
+static int
+iscsit_build_sendtargets_response(struct iscsi_cmd *cmd,
+				  enum iscsit_transport_type network_transport)
 {
 	char *payload = NULL;
 	struct iscsi_conn *conn = cmd->conn;
@@ -3467,6 +3469,9 @@ static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd)
 				struct iscsi_np *np = tpg_np->tpg_np;
 				bool inaddr_any = iscsit_check_inaddr_any(np);
 
+				if (np->np_network_transport != network_transport)
+					continue;
+
 				if (!target_name_printed) {
 					len = sprintf(buf, "TargetName=%s",
 						      tiqn->tiqn);
@@ -3485,10 +3490,8 @@ static int iscsit_build_sendtargets_response(struct iscsi_cmd *cmd)
 
 				len = sprintf(buf, "TargetAddress="
 					"%s:%hu,%hu",
-					(inaddr_any == false) ?
-						np->np_ip : conn->local_ip,
-					(inaddr_any == false) ?
-						np->np_port : conn->local_port,
+					inaddr_any ? conn->local_ip : np->np_ip,
+					inaddr_any ? conn->local_port : np->np_port,
 					tpg->tpgt);
 				len += 1;
 
@@ -3520,11 +3523,12 @@ eob:
 
 int
 iscsit_build_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn,
-		      struct iscsi_text_rsp *hdr)
+		      struct iscsi_text_rsp *hdr,
+		      enum iscsit_transport_type network_transport)
 {
 	int text_length, padding;
 
-	text_length = iscsit_build_sendtargets_response(cmd);
+	text_length = iscsit_build_sendtargets_response(cmd, network_transport);
 	if (text_length < 0)
 		return text_length;
 
@@ -3562,7 +3566,7 @@ static int iscsit_send_text_rsp(
 	u32 tx_size = 0;
 	int text_length, iov_count = 0, rc;
 
-	rc = iscsit_build_text_rsp(cmd, conn, hdr);
+	rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_TCP);
 	if (rc < 0)
 		return rc;
 
@@ -4234,8 +4238,6 @@ int iscsit_close_connection(
 	if (conn->conn_transport->iscsit_wait_conn)
 		conn->conn_transport->iscsit_wait_conn(conn);
 
-	iscsit_free_queue_reqs_for_conn(conn);
-
 	/*
 	 * During Connection recovery drop unacknowledged out of order
 	 * commands for this connection, and prepare the other commands
@@ -4252,6 +4254,7 @@ int iscsit_close_connection(
 		iscsit_clear_ooo_cmdsns_for_conn(conn);
 		iscsit_release_commands_from_conn(conn);
 	}
+	iscsit_free_queue_reqs_for_conn(conn);
 
 	/*
 	 * Handle decrementing session or connection usage count if
diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index de77d9aa22c..ab4915c0d93 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -71,6 +71,40 @@ static void chap_gen_challenge(
 			challenge_asciihex);
 }
 
+static int chap_check_algorithm(const char *a_str)
+{
+	char *tmp, *orig, *token;
+
+	tmp = kstrdup(a_str, GFP_KERNEL);
+	if (!tmp) {
+		pr_err("Memory allocation failed for CHAP_A temporary buffer\n");
+		return CHAP_DIGEST_UNKNOWN;
+	}
+	orig = tmp;
+
+	token = strsep(&tmp, "=");
+	if (!token)
+		goto out;
+
+	if (strcmp(token, "CHAP_A")) {
+		pr_err("Unable to locate CHAP_A key\n");
+		goto out;
+	}
+	while (token) {
+		token = strsep(&tmp, ",");
+		if (!token)
+			goto out;
+
+		if (!strncmp(token, "5", 1)) {
+			pr_debug("Selected MD5 Algorithm\n");
+			kfree(orig);
+			return CHAP_DIGEST_MD5;
+		}
+	}
+out:
+	kfree(orig);
+	return CHAP_DIGEST_UNKNOWN;
+}
 
 static struct iscsi_chap *chap_server_open(
 	struct iscsi_conn *conn,
@@ -79,6 +113,7 @@ static struct iscsi_chap *chap_server_open(
 	char *aic_str,
 	unsigned int *aic_len)
 {
+	int ret;
 	struct iscsi_chap *chap;
 
 	if (!(auth->naf_flags & NAF_USERID_SET) ||
@@ -93,21 +128,24 @@ static struct iscsi_chap *chap_server_open(
 		return NULL;
 
 	chap = conn->auth_protocol;
-	/*
-	 * We only support MD5 MDA presently.
-	 */
-	if (strncmp(a_str, "CHAP_A=5", 8)) {
-		pr_err("CHAP_A is not MD5.\n");
+	ret = chap_check_algorithm(a_str);
+	switch (ret) {
+	case CHAP_DIGEST_MD5:
+		pr_debug("[server] Got CHAP_A=5\n");
+		/*
+		 * Send back CHAP_A set to MD5.
+		*/
+		*aic_len = sprintf(aic_str, "CHAP_A=5");
+		*aic_len += 1;
+		chap->digest_type = CHAP_DIGEST_MD5;
+		pr_debug("[server] Sending CHAP_A=%d\n", chap->digest_type);
+		break;
+	case CHAP_DIGEST_UNKNOWN:
+	default:
+		pr_err("Unsupported CHAP_A value\n");
 		return NULL;
 	}
-	pr_debug("[server] Got CHAP_A=5\n");
-	/*
-	 * Send back CHAP_A set to MD5.
-	 */
-	*aic_len = sprintf(aic_str, "CHAP_A=5");
-	*aic_len += 1;
-	chap->digest_type = CHAP_DIGEST_MD5;
-	pr_debug("[server] Sending CHAP_A=%d\n", chap->digest_type);
+
 	/*
 	 * Set Identifier.
 	 */
@@ -136,7 +174,6 @@ static int chap_server_compute_md5(
 	char *nr_out_ptr,
 	unsigned int *nr_out_len)
 {
-	char *endptr;
 	unsigned long id;
 	unsigned char id_as_uchar;
 	unsigned char digest[MD5_SIGNATURE_SIZE];
@@ -282,9 +319,14 @@ static int chap_server_compute_md5(
 	}
 
 	if (type == HEX)
-		id = simple_strtoul(&identifier[2], &endptr, 0);
+		ret = kstrtoul(&identifier[2], 0, &id);
 	else
-		id = simple_strtoul(identifier, &endptr, 0);
+		ret = kstrtoul(identifier, 0, &id);
+
+	if (ret < 0) {
+		pr_err("kstrtoul() failed for CHAP identifier: %d\n", ret);
+		goto out;
+	}
 	if (id > 255) {
 		pr_err("chap identifier: %lu greater than 255\n", id);
 		goto out;
@@ -313,6 +355,20 @@ static int chap_server_compute_md5(
 		pr_err("Unable to convert incoming challenge\n");
 		goto out;
 	}
+	if (challenge_len > 1024) {
+		pr_err("CHAP_C exceeds maximum binary size of 1024 bytes\n");
+		goto out;
+	}
+	/*
+	 * During mutual authentication, the CHAP_C generated by the
+	 * initiator must not match the original CHAP_C generated by
+	 * the target.
+	 */
+	if (!memcmp(challenge_binhex, chap->challenge, CHAP_CHALLENGE_LENGTH)) {
+		pr_err("initiator CHAP_C matches target CHAP_C, failing"
+		       " login attempt\n");
+		goto out;
+	}
 	/*
 	 * Generate CHAP_N and CHAP_R for mutual authentication.
 	 */
diff --git a/drivers/target/iscsi/iscsi_target_auth.h b/drivers/target/iscsi/iscsi_target_auth.h
index 2f463c09626..d22f7b96a06 100644
--- a/drivers/target/iscsi/iscsi_target_auth.h
+++ b/drivers/target/iscsi/iscsi_target_auth.h
@@ -1,6 +1,7 @@
 #ifndef _ISCSI_CHAP_H_
 #define _ISCSI_CHAP_H_
 
+#define CHAP_DIGEST_UNKNOWN	0
 #define CHAP_DIGEST_MD5		5
 #define CHAP_DIGEST_SHA		6
 
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index d9b1d88e1ad..5e71ac60941 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -1145,7 +1145,7 @@ iscsit_conn_set_transport(struct iscsi_conn *conn, struct iscsit_transport *t)
 void iscsi_target_login_sess_out(struct iscsi_conn *conn,
 		struct iscsi_np *np, bool zero_tsih, bool new_sess)
 {
-	if (new_sess == false)
+	if (!new_sess)
 		goto old_sess_out;
 
 	pr_err("iSCSI Login negotiation failed.\n");
@@ -1216,7 +1216,7 @@ old_sess_out:
 static int __iscsi_target_login_thread(struct iscsi_np *np)
 {
 	u8 *buffer, zero_tsih = 0;
-	int ret = 0, rc, stop;
+	int ret = 0, rc;
 	struct iscsi_conn *conn = NULL;
 	struct iscsi_login *login;
 	struct iscsi_portal_group *tpg = NULL;
@@ -1230,6 +1230,9 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 	if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
 		np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
 		complete(&np->np_restart_comp);
+	} else if (np->np_thread_state == ISCSI_NP_THREAD_SHUTDOWN) {
+		spin_unlock_bh(&np->np_thread_lock);
+		goto exit;
 	} else {
 		np->np_thread_state = ISCSI_NP_THREAD_ACTIVE;
 	}
@@ -1422,10 +1425,8 @@ old_sess_out:
 	}
 
 out:
-	stop = kthread_should_stop();
-	/* Wait for another socket.. */
-	if (!stop)
-		return 1;
+	return 1;
+
 exit:
 	iscsi_stop_login_thread_timer(np);
 	spin_lock_bh(&np->np_thread_lock);
@@ -1442,7 +1443,7 @@ int iscsi_target_login_thread(void *arg)
 
 	allow_signal(SIGINT);
 
-	while (!kthread_should_stop()) {
+	while (1) {
 		ret = __iscsi_target_login_thread(np);
 		/*
 		 * We break and exit here unless another sock_accept() call
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 75b685960e8..62a095f36bf 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -404,7 +404,7 @@ static void iscsi_target_sk_data_ready(struct sock *sk)
 	}
 
 	rc = schedule_delayed_work(&conn->login_work, 0);
-	if (rc == false) {
+	if (!rc) {
 		pr_debug("iscsi_target_sk_data_ready, schedule_delayed_work"
 			 " got false\n");
 	}
@@ -513,7 +513,7 @@ static void iscsi_target_do_login_rx(struct work_struct *work)
 	state = (tpg->tpg_state == TPG_STATE_ACTIVE);
 	spin_unlock(&tpg->tpg_state_lock);
 
-	if (state == false) {
+	if (!state) {
 		pr_debug("iscsi_target_do_login_rx: tpg_state != TPG_STATE_ACTIVE\n");
 		iscsi_target_restore_sock_callbacks(conn);
 		iscsi_target_login_drop(conn, login);
@@ -528,7 +528,7 @@ static void iscsi_target_do_login_rx(struct work_struct *work)
 		state = iscsi_target_sk_state_check(sk);
 		read_unlock_bh(&sk->sk_callback_lock);
 
-		if (state == false) {
+		if (!state) {
 			pr_debug("iscsi_target_do_login_rx, TCP state CLOSE\n");
 			iscsi_target_restore_sock_callbacks(conn);
 			iscsi_target_login_drop(conn, login);
@@ -773,6 +773,12 @@ static int iscsi_target_handle_csg_zero(
 		}
 
 		goto do_auth;
+	} else if (!payload_length) {
+		pr_err("Initiator sent zero length security payload,"
+		       " login failed\n");
+		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_INITIATOR_ERR,
+				    ISCSI_LOGIN_STATUS_AUTH_FAILED);
+		return -1;
 	}
 
 	if (login->first_request)
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index 4d2e23fc76f..02f9de26f38 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -474,10 +474,10 @@ int iscsi_set_keys_to_negotiate(
 		if (!strcmp(param->name, AUTHMETHOD)) {
 			SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, HEADERDIGEST)) {
-			if (iser == false)
+			if (!iser)
 				SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, DATADIGEST)) {
-			if (iser == false)
+			if (!iser)
 				SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, MAXCONNECTIONS)) {
 			SET_PSTATE_NEGOTIATE(param);
@@ -497,7 +497,7 @@ int iscsi_set_keys_to_negotiate(
 		} else if (!strcmp(param->name, IMMEDIATEDATA)) {
 			SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, MAXRECVDATASEGMENTLENGTH)) {
-			if (iser == false)
+			if (!iser)
 				SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, MAXXMITDATASEGMENTLENGTH)) {
 			continue;
@@ -528,13 +528,13 @@ int iscsi_set_keys_to_negotiate(
 		} else if (!strcmp(param->name, OFMARKINT)) {
 			SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, RDMAEXTENSIONS)) {
-			if (iser == true)
+			if (iser)
 				SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, INITIATORRECVDATASEGMENTLENGTH)) {
-			if (iser == true)
+			if (iser)
 				SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, TARGETRECVDATASEGMENTLENGTH)) {
-			if (iser == true)
+			if (iser)
 				SET_PSTATE_NEGOTIATE(param);
 		}
 	}
@@ -1605,7 +1605,7 @@ int iscsi_decode_text_input(
 
 	tmpbuf = kzalloc(length + 1, GFP_KERNEL);
 	if (!tmpbuf) {
-		pr_err("Unable to allocate memory for tmpbuf.\n");
+		pr_err("Unable to allocate %u + 1 bytes for tmpbuf.\n", length);
 		return -1;
 	}
 
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 1431e8400d2..c3cb5c15efd 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -189,7 +189,7 @@ static void iscsit_clear_tpg_np_login_thread(
 	iscsit_reset_np_thread(tpg_np->tpg_np, tpg_np, tpg, shutdown);
 }
 
-void iscsit_clear_tpg_np_login_threads(
+static void iscsit_clear_tpg_np_login_threads(
 	struct iscsi_portal_group *tpg,
 	bool shutdown)
 {
@@ -276,8 +276,6 @@ int iscsit_tpg_del_portal_group(
 	tpg->tpg_state = TPG_STATE_INACTIVE;
 	spin_unlock(&tpg->tpg_state_lock);
 
-	iscsit_clear_tpg_np_login_threads(tpg, true);
-
 	if (iscsit_release_sessions_for_tpg(tpg, force) < 0) {
 		pr_err("Unable to delete iSCSI Target Portal Group:"
 			" %hu while active sessions exist, and force=0\n",
@@ -453,7 +451,7 @@ static bool iscsit_tpg_check_network_portal(
 
 			match = iscsit_check_np_match(sockaddr, np,
 						network_transport);
-			if (match == true)
+			if (match)
 				break;
 		}
 		spin_unlock(&tpg->tpg_np_lock);
@@ -475,7 +473,7 @@ struct iscsi_tpg_np *iscsit_tpg_add_network_portal(
 
 	if (!tpg_np_parent) {
 		if (iscsit_tpg_check_network_portal(tpg->tpg_tiqn, sockaddr,
-				network_transport) == true) {
+				network_transport)) {
 			pr_err("Network Portal: %s already exists on a"
 				" different TPG on %s\n", ip_str,
 				tpg->tpg_tiqn->tiqn);
diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h
index 0a182f2aa8a..e7265337bc4 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.h
+++ b/drivers/target/iscsi/iscsi_target_tpg.h
@@ -8,7 +8,6 @@ extern struct iscsi_portal_group *iscsit_get_tpg_from_np(struct iscsi_tiqn *,
 			struct iscsi_np *, struct iscsi_tpg_np **);
 extern int iscsit_get_tpg(struct iscsi_portal_group *);
 extern void iscsit_put_tpg(struct iscsi_portal_group *);
-extern void iscsit_clear_tpg_np_login_threads(struct iscsi_portal_group *, bool);
 extern void iscsit_tpg_dump_params(struct iscsi_portal_group *);
 extern int iscsit_tpg_add_portal_group(struct iscsi_tiqn *, struct iscsi_portal_group *);
 extern int iscsit_tpg_del_portal_group(struct iscsi_tiqn *, struct iscsi_portal_group *,
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 53e157cb8c5..fd90b28f1d9 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1295,6 +1295,8 @@ int iscsit_tx_login_rsp(struct iscsi_conn *conn, u8 status_class, u8 status_deta
 	login->login_failed = 1;
 	iscsit_collect_login_stats(conn, status_class, status_detail);
 
+	memset(&login->rsp[0], 0, ISCSI_HDR_LEN);
+
 	hdr	= (struct iscsi_login_rsp *)&login->rsp[0];
 	hdr->opcode		= ISCSI_OP_LOGIN_RSP;
 	hdr->status_class	= status_class;
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 73ab75ddaf4..8c64b8776a9 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -179,7 +179,7 @@ static void tcm_loop_submission_work(struct work_struct *work)
 	struct tcm_loop_hba *tl_hba;
 	struct tcm_loop_tpg *tl_tpg;
 	struct scatterlist *sgl_bidi = NULL;
-	u32 sgl_bidi_count = 0;
+	u32 sgl_bidi_count = 0, transfer_length;
 	int rc;
 
 	tl_hba = *(struct tcm_loop_hba **)shost_priv(sc->device->host);
@@ -213,12 +213,21 @@ static void tcm_loop_submission_work(struct work_struct *work)
 
 	}
 
-	if (!scsi_prot_sg_count(sc) && scsi_get_prot_op(sc) != SCSI_PROT_NORMAL)
+	transfer_length = scsi_transfer_length(sc);
+	if (!scsi_prot_sg_count(sc) &&
+	    scsi_get_prot_op(sc) != SCSI_PROT_NORMAL) {
 		se_cmd->prot_pto = true;
+		/*
+		 * loopback transport doesn't support
+		 * WRITE_GENERATE, READ_STRIP protection
+		 * information operations, go ahead unprotected.
+		 */
+		transfer_length = scsi_bufflen(sc);
+	}
 
 	rc = target_submit_cmd_map_sgls(se_cmd, tl_nexus->se_sess, sc->cmnd,
 			&tl_cmd->tl_sense_buf[0], tl_cmd->sc->device->lun,
-			scsi_bufflen(sc), tcm_loop_sam_attr(sc),
+			transfer_length, tcm_loop_sam_attr(sc),
 			sc->sc_data_direction, 0,
 			scsi_sglist(sc), scsi_sg_count(sc),
 			sgl_bidi, sgl_bidi_count,
@@ -230,6 +239,7 @@ static void tcm_loop_submission_work(struct work_struct *work)
 	return;
 
 out_done:
+	kmem_cache_free(tcm_loop_cmd_cache, tl_cmd);
 	sc->scsi_done(sc);
 	return;
 }
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 11d26fe65bf..98da9016715 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -616,6 +616,7 @@ void core_dev_unexport(
 	dev->export_count--;
 	spin_unlock(&hba->device_lock);
 
+	lun->lun_sep = NULL;
 	lun->lun_se_dev = NULL;
 }
 
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 0f199f6a073..94d00df28f3 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1055,6 +1055,8 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 			goto fail;
 		}
+
+		blk_rq_set_block_pc(req);
 	} else {
 		BUG_ON(!cmd->data_length);
 
@@ -1071,7 +1073,6 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 		}
 	}
 
-	req->cmd_type = REQ_TYPE_BLOCK_PC;
 	req->end_io = pscsi_req_done;
 	req->end_io_data = cmd;
 	req->cmd_len = scsi_command_size(pt->pscsi_cdb);
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index e0229592ec5..bd78d9235ac 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -81,7 +81,7 @@ sbc_emulate_readcapacity(struct se_cmd *cmd)
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 8);
 	return 0;
 }
 
@@ -137,7 +137,7 @@ sbc_emulate_readcapacity_16(struct se_cmd *cmd)
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 32);
 	return 0;
 }
 
@@ -176,24 +176,6 @@ static inline u32 sbc_get_size(struct se_cmd *cmd, u32 sectors)
 	return cmd->se_dev->dev_attrib.block_size * sectors;
 }
 
-static int sbc_check_valid_sectors(struct se_cmd *cmd)
-{
-	struct se_device *dev = cmd->se_dev;
-	unsigned long long end_lba;
-	u32 sectors;
-
-	sectors = cmd->data_length / dev->dev_attrib.block_size;
-	end_lba = dev->transport->get_blocks(dev) + 1;
-
-	if (cmd->t_task_lba + sectors > end_lba) {
-		pr_err("target: lba %llu, sectors %u exceeds end lba %llu\n",
-			cmd->t_task_lba, sectors, end_lba);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static inline u32 transport_get_sectors_6(unsigned char *cdb)
 {
 	/*
@@ -665,8 +647,19 @@ sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb,
 
 	cmd->prot_type = dev->dev_attrib.pi_prot_type;
 	cmd->prot_length = dev->prot_length * sectors;
-	pr_debug("%s: prot_type=%d, prot_length=%d prot_op=%d prot_checks=%d\n",
-		 __func__, cmd->prot_type, cmd->prot_length,
+
+	/**
+	 * In case protection information exists over the wire
+	 * we modify command data length to describe pure data.
+	 * The actual transfer length is data length + protection
+	 * length
+	 **/
+	if (protect)
+		cmd->data_length = sectors * dev->dev_attrib.block_size;
+
+	pr_debug("%s: prot_type=%d, data_length=%d, prot_length=%d "
+		 "prot_op=%d prot_checks=%d\n",
+		 __func__, cmd->prot_type, cmd->data_length, cmd->prot_length,
 		 cmd->prot_op, cmd->prot_checks);
 
 	return true;
@@ -877,15 +870,6 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		break;
 	case SYNCHRONIZE_CACHE:
 	case SYNCHRONIZE_CACHE_16:
-		if (!ops->execute_sync_cache) {
-			size = 0;
-			cmd->execute_cmd = sbc_emulate_noop;
-			break;
-		}
-
-		/*
-		 * Extract LBA and range to be flushed for emulated SYNCHRONIZE_CACHE
-		 */
 		if (cdb[0] == SYNCHRONIZE_CACHE) {
 			sectors = transport_get_sectors_10(cdb);
 			cmd->t_task_lba = transport_lba_32(cdb);
@@ -893,18 +877,12 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 			sectors = transport_get_sectors_16(cdb);
 			cmd->t_task_lba = transport_lba_64(cdb);
 		}
-
-		size = sbc_get_size(cmd, sectors);
-
-		/*
-		 * Check to ensure that LBA + Range does not exceed past end of
-		 * device for IBLOCK and FILEIO ->do_sync_cache() backend calls
-		 */
-		if (cmd->t_task_lba || sectors) {
-			if (sbc_check_valid_sectors(cmd) < 0)
-				return TCM_ADDRESS_OUT_OF_RANGE;
+		if (ops->execute_sync_cache) {
+			cmd->execute_cmd = ops->execute_sync_cache;
+			goto check_lba;
 		}
-		cmd->execute_cmd = ops->execute_sync_cache;
+		size = 0;
+		cmd->execute_cmd = sbc_emulate_noop;
 		break;
 	case UNMAP:
 		if (!ops->execute_unmap)
@@ -947,8 +925,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 		break;
 	case VERIFY:
 		size = 0;
+		sectors = transport_get_sectors_10(cdb);
+		cmd->t_task_lba = transport_lba_32(cdb);
 		cmd->execute_cmd = sbc_emulate_noop;
-		break;
+		goto check_lba;
 	case REZERO_UNIT:
 	case SEEK_6:
 	case SEEK_10:
@@ -988,7 +968,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 				dev->dev_attrib.hw_max_sectors);
 			return TCM_INVALID_CDB_FIELD;
 		}
-
+check_lba:
 		end_lba = dev->transport->get_blocks(dev) + 1;
 		if (cmd->t_task_lba + sectors > end_lba) {
 			pr_err("cmd exceeds last lba %llu "
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index 8653666612a..6cd7222738f 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -129,15 +129,10 @@ static sense_reason_t
 spc_emulate_evpd_80(struct se_cmd *cmd, unsigned char *buf)
 {
 	struct se_device *dev = cmd->se_dev;
-	u16 len = 0;
+	u16 len;
 
 	if (dev->dev_flags & DF_EMULATED_VPD_UNIT_SERIAL) {
-		u32 unit_serial_len;
-
-		unit_serial_len = strlen(dev->t10_wwn.unit_serial);
-		unit_serial_len++; /* For NULL Terminator */
-
-		len += sprintf(&buf[4], "%s", dev->t10_wwn.unit_serial);
+		len = sprintf(&buf[4], "%s", dev->t10_wwn.unit_serial);
 		len++; /* Extra Byte for NULL Terminator */
 		buf[3] = len;
 	}
@@ -721,6 +716,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 	unsigned char *buf;
 	sense_reason_t ret;
 	int p;
+	int len = 0;
 
 	buf = kzalloc(SE_INQUIRY_BUF, GFP_KERNEL);
 	if (!buf) {
@@ -742,6 +738,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 		}
 
 		ret = spc_emulate_inquiry_std(cmd, buf);
+		len = buf[4] + 5;
 		goto out;
 	}
 
@@ -749,6 +746,7 @@ spc_emulate_inquiry(struct se_cmd *cmd)
 		if (cdb[2] == evpd_handlers[p].page) {
 			buf[1] = cdb[2];
 			ret = evpd_handlers[p].emulate(cmd, buf);
+			len = get_unaligned_be16(&buf[2]) + 4;
 			goto out;
 		}
 	}
@@ -765,7 +763,7 @@ out:
 	kfree(buf);
 
 	if (!ret)
-		target_complete_cmd(cmd, GOOD);
+		target_complete_cmd_with_length(cmd, GOOD, len);
 	return ret;
 }
 
@@ -1103,7 +1101,7 @@ set_length:
 		transport_kunmap_data_sg(cmd);
 	}
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, length);
 	return 0;
 }
 
@@ -1279,7 +1277,7 @@ done:
 	buf[3] = (lun_count & 0xff);
 	transport_kunmap_data_sg(cmd);
 
-	target_complete_cmd(cmd, GOOD);
+	target_complete_cmd_with_length(cmd, GOOD, 8 + lun_count * 8);
 	return 0;
 }
 EXPORT_SYMBOL(spc_emulate_report_luns);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index c036595b17c..fddfae61222 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -825,7 +825,7 @@ int core_tpg_add_lun(
 
 	ret = core_dev_export(dev, tpg, lun);
 	if (ret < 0) {
-		percpu_ref_cancel_init(&lun->lun_ref);
+		percpu_ref_exit(&lun->lun_ref);
 		return ret;
 	}
 
@@ -880,5 +880,7 @@ int core_tpg_post_dellun(
 	lun->lun_status = TRANSPORT_LUN_STATUS_FREE;
 	spin_unlock(&tpg->tpg_lun_lock);
 
+	percpu_ref_exit(&lun->lun_ref);
+
 	return 0;
 }
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 2179feed0d6..7fa62fc93e0 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -504,7 +504,7 @@ void transport_deregister_session(struct se_session *se_sess)
 	 * ->acl_free_comp caller to wakeup configfs se_node_acl->acl_group
 	 * removal context.
 	 */
-	if (se_nacl && comp_nacl == true)
+	if (se_nacl && comp_nacl)
 		target_put_nacl(se_nacl);
 
 	transport_free_session(se_sess);
@@ -562,7 +562,7 @@ static int transport_cmd_check_stop(struct se_cmd *cmd, bool remove_from_lists,
 
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return 1;
 	}
 
@@ -687,7 +687,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 	if (cmd->transport_state & CMD_T_ABORTED &&
 	    cmd->transport_state & CMD_T_STOP) {
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return;
 	} else if (!success) {
 		INIT_WORK(&cmd->work, target_complete_failure_work);
@@ -703,6 +703,23 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
 }
 EXPORT_SYMBOL(target_complete_cmd);
 
+void target_complete_cmd_with_length(struct se_cmd *cmd, u8 scsi_status, int length)
+{
+	if (scsi_status == SAM_STAT_GOOD && length < cmd->data_length) {
+		if (cmd->se_cmd_flags & SCF_UNDERFLOW_BIT) {
+			cmd->residual_count += cmd->data_length - length;
+		} else {
+			cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT;
+			cmd->residual_count = cmd->data_length - length;
+		}
+
+		cmd->data_length = length;
+	}
+
+	target_complete_cmd(cmd, scsi_status);
+}
+EXPORT_SYMBOL(target_complete_cmd_with_length);
+
 static void target_add_to_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
@@ -1761,7 +1778,7 @@ void target_execute_cmd(struct se_cmd *cmd)
 			cmd->se_tfo->get_task_tag(cmd));
 
 		spin_unlock_irq(&cmd->t_state_lock);
-		complete(&cmd->t_transport_stop_comp);
+		complete_all(&cmd->t_transport_stop_comp);
 		return;
 	}
 
@@ -2363,7 +2380,7 @@ int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd,
 	 * fabric acknowledgement that requires two target_put_sess_cmd()
 	 * invocations before se_cmd descriptor release.
 	 */
-	if (ack_kref == true) {
+	if (ack_kref) {
 		kref_get(&se_cmd->cmd_kref);
 		se_cmd->se_cmd_flags |= SCF_ACK_KREF;
 	}
@@ -2407,6 +2424,10 @@ static void target_release_cmd_kref(struct kref *kref)
  */
 int target_put_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd)
 {
+	if (!se_sess) {
+		se_cmd->se_tfo->release_cmd(se_cmd);
+		return 1;
+	}
 	return kref_put_spinlock_irqsave(&se_cmd->cmd_kref, target_release_cmd_kref,
 			&se_sess->sess_cmd_lock);
 }
@@ -2934,6 +2955,12 @@ static void target_tmr_work(struct work_struct *work)
 int transport_generic_handle_tmr(
 	struct se_cmd *cmd)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->t_state_lock, flags);
+	cmd->transport_state |= CMD_T_ACTIVE;
+	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+
 	INIT_WORK(&cmd->work, target_tmr_work);
 	queue_work(cmd->se_dev->tmr_wq, &cmd->work);
 	return 0;
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 669c536fd95..e9186cdf35e 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -70,7 +70,7 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op
 	unsigned char tmp_dev_wwn[XCOPY_NAA_IEEE_REGEX_LEN], *dev_wwn;
 	int rc;
 
-	if (src == true)
+	if (src)
 		dev_wwn = &xop->dst_tid_wwn[0];
 	else
 		dev_wwn = &xop->src_tid_wwn[0];
@@ -88,7 +88,7 @@ static int target_xcopy_locate_se_dev_e4(struct se_cmd *se_cmd, struct xcopy_op
 		if (rc != 0)
 			continue;
 
-		if (src == true) {
+		if (src) {
 			xop->dst_dev = se_dev;
 			pr_debug("XCOPY 0xe4: Setting xop->dst_dev: %p from located"
 				" se_dev\n", xop->dst_dev);
@@ -166,7 +166,7 @@ static int target_xcopy_parse_tiddesc_e4(struct se_cmd *se_cmd, struct xcopy_op
 		return -EINVAL;
 	}
 
-	if (src == true) {
+	if (src) {
 		memcpy(&xop->src_tid_wwn[0], &desc[8], XCOPY_NAA_IEEE_REGEX_LEN);
 		/*
 		 * Determine if the source designator matches the local device
@@ -236,7 +236,7 @@ static int target_xcopy_parse_target_descriptors(struct se_cmd *se_cmd,
 			/*
 			 * Assume target descriptors are in source -> destination order..
 			 */
-			if (src == true)
+			if (src)
 				src = false;
 			else
 				src = true;
@@ -560,7 +560,7 @@ static int target_xcopy_init_pt_lun(
 	 * reservations.  The pt_cmd->se_lun pointer will be setup from within
 	 * target_xcopy_setup_pt_port()
 	 */
-	if (remote_port == false) {
+	if (!remote_port) {
 		pt_cmd->se_cmd_flags |= SCF_SE_LUN_CMD | SCF_CMD_XCOPY_PASSTHROUGH;
 		return 0;
 	}
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index f5fd515b2be..be0c0d08c56 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -128,6 +128,7 @@ int ft_queue_status(struct se_cmd *se_cmd)
 	struct fc_lport *lport;
 	struct fc_exch *ep;
 	size_t len;
+	int rc;
 
 	if (cmd->aborted)
 		return 0;
@@ -137,9 +138,10 @@ int ft_queue_status(struct se_cmd *se_cmd)
 	len = sizeof(*fcp) + se_cmd->scsi_sense_length;
 	fp = fc_frame_alloc(lport, len);
 	if (!fp) {
-		/* XXX shouldn't just drop it - requeue and retry? */
-		return 0;
+		se_cmd->scsi_status = SAM_STAT_TASK_SET_FULL;
+		return -ENOMEM;
 	}
+
 	fcp = fc_frame_payload_get(fp, len);
 	memset(fcp, 0, len);
 	fcp->resp.fr_status = se_cmd->scsi_status;
@@ -170,7 +172,18 @@ int ft_queue_status(struct se_cmd *se_cmd)
 	fc_fill_fc_hdr(fp, FC_RCTL_DD_CMD_STATUS, ep->did, ep->sid, FC_TYPE_FCP,
 		       FC_FC_EX_CTX | FC_FC_LAST_SEQ | FC_FC_END_SEQ, 0);
 
-	lport->tt.seq_send(lport, cmd->seq, fp);
+	rc = lport->tt.seq_send(lport, cmd->seq, fp);
+	if (rc) {
+		pr_info_ratelimited("%s: Failed to send response frame %p, "
+				    "xid <0x%x>\n", __func__, fp, ep->xid);
+		/*
+		 * Generate a TASK_SET_FULL status to notify the initiator
+		 * to reduce it's queue_depth after the se_cmd response has
+		 * been re-queued by target-core.
+		 */
+		se_cmd->scsi_status = SAM_STAT_TASK_SET_FULL;
+		return -ENOMEM;
+	}
 	lport->tt.exch_done(cmd->seq);
 	return 0;
 }
diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c
index e415af32115..97b486c3dda 100644
--- a/drivers/target/tcm_fc/tfc_io.c
+++ b/drivers/target/tcm_fc/tfc_io.c
@@ -82,6 +82,10 @@ int ft_queue_data_in(struct se_cmd *se_cmd)
 
 	if (cmd->aborted)
 		return 0;
+
+	if (se_cmd->scsi_status == SAM_STAT_TASK_SET_FULL)
+		goto queue_status;
+
 	ep = fc_seq_exch(cmd->seq);
 	lport = ep->lp;
 	cmd->seq = lport->tt.seq_start_next(cmd->seq);
@@ -178,14 +182,23 @@ int ft_queue_data_in(struct se_cmd *se_cmd)
 			       FC_TYPE_FCP, f_ctl, fh_off);
 		error = lport->tt.seq_send(lport, seq, fp);
 		if (error) {
-			/* XXX For now, initiator will retry */
-			pr_err_ratelimited("%s: Failed to send frame %p, "
+			pr_info_ratelimited("%s: Failed to send frame %p, "
 						"xid <0x%x>, remaining %zu, "
 						"lso_max <0x%x>\n",
 						__func__, fp, ep->xid,
 						remaining, lport->lso_max);
+			/*
+			 * Go ahead and set TASK_SET_FULL status ignoring the
+			 * rest of the DataIN, and immediately attempt to
+			 * send the response via ft_queue_status() in order
+			 * to notify the initiator that it should reduce it's
+			 * per LUN queue_depth.
+			 */
+			se_cmd->scsi_status = SAM_STAT_TASK_SET_FULL;
+			break;
 		}
 	}
+queue_status:
 	return ft_queue_status(se_cmd);
 }
 
diff --git a/drivers/tc/tc.c b/drivers/tc/tc.c
index a8aaf6ac2ae..946562389ca 100644
--- a/drivers/tc/tc.c
+++ b/drivers/tc/tc.c
@@ -129,7 +129,10 @@ static void __init tc_bus_add_devices(struct tc_bus *tbus)
 
 		tc_device_get_irq(tdev);
 
-		device_register(&tdev->dev);
+		if (device_register(&tdev->dev)) {
+			put_device(&tdev->dev);
+			goto out_err;
+		}
 		list_add_tail(&tdev->node, &tbus->devices);
 
 out_err:
@@ -148,7 +151,10 @@ static int __init tc_init(void)
 
 	INIT_LIST_HEAD(&tc_bus.devices);
 	dev_set_name(&tc_bus.dev, "tc");
-	device_register(&tc_bus.dev);
+	if (device_register(&tc_bus.dev)) {
+		put_device(&tc_bus.dev);
+		return 0;
+	}
 
 	if (tc_bus.info.slot_size) {
 		unsigned int tc_clock = tc_get_speed(&tc_bus) / 100000;
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 2d51912a6e4..f9a13867cb7 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -222,12 +222,24 @@ config ACPI_INT3403_THERMAL
 	  the Intel Thermal Daemon can use this information to allow the user
 	  to select his laptop to run without turning on the fans.
 
+config INTEL_SOC_DTS_THERMAL
+	tristate "Intel SoCs DTS thermal driver"
+	depends on X86 && IOSF_MBI
+	help
+	  Enable this to register Intel SoCs (e.g. Bay Trail) platform digital
+	  temperature sensor (DTS). These SoCs have two additional DTSs in
+	  addition to DTSs on CPU cores. Each DTS will be registered as a
+	  thermal zone. There are two trip points. One of the trip point can
+	  be set by user mode programs to get notifications via Linux thermal
+	  notification methods.The other trip is a critical trip point, which
+	  was set by the driver based on the TJ MAX temperature.
+
 menu "Texas Instruments thermal drivers"
 source "drivers/thermal/ti-soc-thermal/Kconfig"
 endmenu
 
 menu "Samsung thermal drivers"
-depends on PLAT_SAMSUNG
+depends on ARCH_EXYNOS
 source "drivers/thermal/samsung/Kconfig"
 endmenu
 
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 54e4ec9eb5d..de0636a57a6 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -29,5 +29,6 @@ obj-$(CONFIG_IMX_THERMAL)	+= imx_thermal.o
 obj-$(CONFIG_DB8500_CPUFREQ_COOLING)	+= db8500_cpufreq_cooling.o
 obj-$(CONFIG_INTEL_POWERCLAMP)	+= intel_powerclamp.o
 obj-$(CONFIG_X86_PKG_TEMP_THERMAL)	+= x86_pkg_temp_thermal.o
+obj-$(CONFIG_INTEL_SOC_DTS_THERMAL)	+= intel_soc_dts_thermal.o
 obj-$(CONFIG_TI_SOC_THERMAL)	+= ti-soc-thermal/
 obj-$(CONFIG_ACPI_INT3403_THERMAL)	+= int3403_thermal.o
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 5e53212b984..9d1420acb39 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -24,10 +24,7 @@
 #include <linux/of_device.h>
 #include <linux/thermal.h>
 
-#define THERMAL_VALID_OFFSET		9
 #define THERMAL_VALID_MASK		0x1
-#define THERMAL_TEMP_OFFSET		10
-#define THERMAL_TEMP_MASK		0x1ff
 
 /* Thermal Manager Control and Status Register */
 #define PMU_TDC0_SW_RST_MASK		(0x1 << 1)
@@ -38,24 +35,47 @@
 #define PMU_TDC0_OTF_CAL_MASK		(0x1 << 30)
 #define PMU_TDC0_START_CAL_MASK		(0x1 << 25)
 
-struct armada_thermal_ops;
+#define A375_Z1_CAL_RESET_LSB		0x8011e214
+#define A375_Z1_CAL_RESET_MSB		0x30a88019
+#define A375_Z1_WORKAROUND_BIT		BIT(9)
+
+#define A375_UNIT_CONTROL_SHIFT		27
+#define A375_UNIT_CONTROL_MASK		0x7
+#define A375_READOUT_INVERT		BIT(15)
+#define A375_HW_RESETn			BIT(8)
+#define A380_HW_RESET			BIT(8)
+
+struct armada_thermal_data;
 
 /* Marvell EBU Thermal Sensor Dev Structure */
 struct armada_thermal_priv {
 	void __iomem *sensor;
 	void __iomem *control;
-	struct armada_thermal_ops *ops;
+	struct armada_thermal_data *data;
 };
 
-struct armada_thermal_ops {
+struct armada_thermal_data {
 	/* Initialize the sensor */
-	void (*init_sensor)(struct armada_thermal_priv *);
+	void (*init_sensor)(struct platform_device *pdev,
+			    struct armada_thermal_priv *);
 
 	/* Test for a valid sensor value (optional) */
 	bool (*is_valid)(struct armada_thermal_priv *);
+
+	/* Formula coeficients: temp = (b + m * reg) / div */
+	unsigned long coef_b;
+	unsigned long coef_m;
+	unsigned long coef_div;
+	bool inverted;
+
+	/* Register shift and mask to access the sensor temperature */
+	unsigned int temp_shift;
+	unsigned int temp_mask;
+	unsigned int is_valid_shift;
 };
 
-static void armadaxp_init_sensor(struct armada_thermal_priv *priv)
+static void armadaxp_init_sensor(struct platform_device *pdev,
+				 struct armada_thermal_priv *priv)
 {
 	unsigned long reg;
 
@@ -80,7 +100,8 @@ static void armadaxp_init_sensor(struct armada_thermal_priv *priv)
 	writel(reg, priv->sensor);
 }
 
-static void armada370_init_sensor(struct armada_thermal_priv *priv)
+static void armada370_init_sensor(struct platform_device *pdev,
+				  struct armada_thermal_priv *priv)
 {
 	unsigned long reg;
 
@@ -99,11 +120,54 @@ static void armada370_init_sensor(struct armada_thermal_priv *priv)
 	mdelay(10);
 }
 
+static void armada375_init_sensor(struct platform_device *pdev,
+				  struct armada_thermal_priv *priv)
+{
+	unsigned long reg;
+	bool quirk_needed =
+		!!of_device_is_compatible(pdev->dev.of_node,
+					  "marvell,armada375-z1-thermal");
+
+	if (quirk_needed) {
+		/* Ensure these registers have the default (reset) values */
+		writel(A375_Z1_CAL_RESET_LSB, priv->control);
+		writel(A375_Z1_CAL_RESET_MSB, priv->control + 0x4);
+	}
+
+	reg = readl(priv->control + 4);
+	reg &= ~(A375_UNIT_CONTROL_MASK << A375_UNIT_CONTROL_SHIFT);
+	reg &= ~A375_READOUT_INVERT;
+	reg &= ~A375_HW_RESETn;
+
+	if (quirk_needed)
+		reg |= A375_Z1_WORKAROUND_BIT;
+
+	writel(reg, priv->control + 4);
+	mdelay(20);
+
+	reg |= A375_HW_RESETn;
+	writel(reg, priv->control + 4);
+	mdelay(50);
+}
+
+static void armada380_init_sensor(struct platform_device *pdev,
+				  struct armada_thermal_priv *priv)
+{
+	unsigned long reg = readl_relaxed(priv->control);
+
+	/* Reset hardware once */
+	if (!(reg & A380_HW_RESET)) {
+		reg |= A380_HW_RESET;
+		writel(reg, priv->control);
+		mdelay(10);
+	}
+}
+
 static bool armada_is_valid(struct armada_thermal_priv *priv)
 {
 	unsigned long reg = readl_relaxed(priv->sensor);
 
-	return (reg >> THERMAL_VALID_OFFSET) & THERMAL_VALID_MASK;
+	return (reg >> priv->data->is_valid_shift) & THERMAL_VALID_MASK;
 }
 
 static int armada_get_temp(struct thermal_zone_device *thermal,
@@ -111,17 +175,27 @@ static int armada_get_temp(struct thermal_zone_device *thermal,
 {
 	struct armada_thermal_priv *priv = thermal->devdata;
 	unsigned long reg;
+	unsigned long m, b, div;
 
 	/* Valid check */
-	if (priv->ops->is_valid && !priv->ops->is_valid(priv)) {
+	if (priv->data->is_valid && !priv->data->is_valid(priv)) {
 		dev_err(&thermal->device,
 			"Temperature sensor reading not valid\n");
 		return -EIO;
 	}
 
 	reg = readl_relaxed(priv->sensor);
-	reg = (reg >> THERMAL_TEMP_OFFSET) & THERMAL_TEMP_MASK;
-	*temp = (3153000000UL - (10000000UL*reg)) / 13825;
+	reg = (reg >> priv->data->temp_shift) & priv->data->temp_mask;
+
+	/* Get formula coeficients */
+	b = priv->data->coef_b;
+	m = priv->data->coef_m;
+	div = priv->data->coef_div;
+
+	if (priv->data->inverted)
+		*temp = ((m * reg) - b) / div;
+	else
+		*temp = (b - (m * reg)) / div;
 	return 0;
 }
 
@@ -129,23 +203,69 @@ static struct thermal_zone_device_ops ops = {
 	.get_temp = armada_get_temp,
 };
 
-static const struct armada_thermal_ops armadaxp_ops = {
+static const struct armada_thermal_data armadaxp_data = {
 	.init_sensor = armadaxp_init_sensor,
+	.temp_shift = 10,
+	.temp_mask = 0x1ff,
+	.coef_b = 3153000000UL,
+	.coef_m = 10000000UL,
+	.coef_div = 13825,
 };
 
-static const struct armada_thermal_ops armada370_ops = {
+static const struct armada_thermal_data armada370_data = {
 	.is_valid = armada_is_valid,
 	.init_sensor = armada370_init_sensor,
+	.is_valid_shift = 9,
+	.temp_shift = 10,
+	.temp_mask = 0x1ff,
+	.coef_b = 3153000000UL,
+	.coef_m = 10000000UL,
+	.coef_div = 13825,
+};
+
+static const struct armada_thermal_data armada375_data = {
+	.is_valid = armada_is_valid,
+	.init_sensor = armada375_init_sensor,
+	.is_valid_shift = 10,
+	.temp_shift = 0,
+	.temp_mask = 0x1ff,
+	.coef_b = 3171900000UL,
+	.coef_m = 10000000UL,
+	.coef_div = 13616,
+};
+
+static const struct armada_thermal_data armada380_data = {
+	.is_valid = armada_is_valid,
+	.init_sensor = armada380_init_sensor,
+	.is_valid_shift = 10,
+	.temp_shift = 0,
+	.temp_mask = 0x3ff,
+	.coef_b = 1169498786UL,
+	.coef_m = 2000000UL,
+	.coef_div = 4289,
+	.inverted = true,
 };
 
 static const struct of_device_id armada_thermal_id_table[] = {
 	{
 		.compatible = "marvell,armadaxp-thermal",
-		.data       = &armadaxp_ops,
+		.data       = &armadaxp_data,
 	},
 	{
 		.compatible = "marvell,armada370-thermal",
-		.data       = &armada370_ops,
+		.data       = &armada370_data,
+	},
+	{
+		.compatible = "marvell,armada375-thermal",
+		.data       = &armada375_data,
+	},
+	{
+		.compatible = "marvell,armada375-z1-thermal",
+		.data       = &armada375_data,
+	},
+	{
+		.compatible = "marvell,armada380-thermal",
+		.data       = &armada380_data,
 	},
 	{
 		/* sentinel */
@@ -178,8 +298,8 @@ static int armada_thermal_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->control))
 		return PTR_ERR(priv->control);
 
-	priv->ops = (struct armada_thermal_ops *)match->data;
-	priv->ops->init_sensor(priv);
+	priv->data = (struct armada_thermal_data *)match->data;
+	priv->data->init_sensor(pdev, priv);
 
 	thermal = thermal_zone_device_register("armada_thermal", 0, 0,
 					       priv, &ops, NULL, 0, 0);
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index a99c63152b8..2c516f2eebe 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -306,7 +306,7 @@ static int imx_get_sensor_data(struct platform_device *pdev)
 {
 	struct imx_thermal_data *data = platform_get_drvdata(pdev);
 	struct regmap *map;
-	int t1, t2, n1, n2;
+	int t1, n1;
 	int ret;
 	u32 val;
 	u64 temp64;
@@ -333,14 +333,10 @@ static int imx_get_sensor_data(struct platform_device *pdev)
 	/*
 	 * Sensor data layout:
 	 *   [31:20] - sensor value @ 25C
-	 *    [19:8] - sensor value of hot
-	 *     [7:0] - hot temperature value
 	 * Use universal formula now and only need sensor value @ 25C
 	 * slope = 0.4297157 - (0.0015976 * 25C fuse)
 	 */
 	n1 = val >> 20;
-	n2 = (val & 0xfff00) >> 8;
-	t2 = val & 0xff;
 	t1 = 25; /* t1 always 25C */
 
 	/*
@@ -366,16 +362,16 @@ static int imx_get_sensor_data(struct platform_device *pdev)
 	data->c2 = n1 * data->c1 + 1000 * t1;
 
 	/*
-	 * Set the default passive cooling trip point to 20 °C below the
-	 * maximum die temperature. Can be changed from userspace.
+	 * Set the default passive cooling trip point,
+	 * can be changed from userspace.
 	 */
-	data->temp_passive = 1000 * (t2 - 20);
+	data->temp_passive = IMX_TEMP_PASSIVE;
 
 	/*
-	 * The maximum die temperature is t2, let's give 5 °C cushion
-	 * for noise and possible temperature rise between measurements.
+	 * The maximum die temperature set to 20 C higher than
+	 * IMX_TEMP_PASSIVE.
 	 */
-	data->temp_critical = 1000 * (t2 - 5);
+	data->temp_critical = 1000 * 20 + data->temp_passive;
 
 	return 0;
 }
diff --git a/drivers/thermal/int3403_thermal.c b/drivers/thermal/int3403_thermal.c
index 1301681d9a7..e93f0253f6e 100644
--- a/drivers/thermal/int3403_thermal.c
+++ b/drivers/thermal/int3403_thermal.c
@@ -62,7 +62,13 @@ static int sys_get_trip_hyst(struct thermal_zone_device *tzone,
 	if (ACPI_FAILURE(status))
 		return -EIO;
 
-	*temp = DECI_KELVIN_TO_MILLI_CELSIUS(hyst, KELVIN_OFFSET);
+	/*
+	 * Thermal hysteresis represents a temperature difference.
+	 * Kelvin and Celsius have same degree size. So the
+	 * conversion here between tenths of degree Kelvin unit
+	 * and Milli-Celsius unit is just to multiply 100.
+	 */
+	*temp = hyst * 100;
 
 	return 0;
 }
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index a084325f138..95cb7fc20e1 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -681,8 +681,10 @@ static const struct x86_cpu_id intel_powerclamp_ids[] = {
 	{ X86_VENDOR_INTEL, 6, 0x2d},
 	{ X86_VENDOR_INTEL, 6, 0x2e},
 	{ X86_VENDOR_INTEL, 6, 0x2f},
+	{ X86_VENDOR_INTEL, 6, 0x37},
 	{ X86_VENDOR_INTEL, 6, 0x3a},
 	{ X86_VENDOR_INTEL, 6, 0x3c},
+	{ X86_VENDOR_INTEL, 6, 0x3d},
 	{ X86_VENDOR_INTEL, 6, 0x3e},
 	{ X86_VENDOR_INTEL, 6, 0x3f},
 	{ X86_VENDOR_INTEL, 6, 0x45},
diff --git a/drivers/thermal/intel_soc_dts_thermal.c b/drivers/thermal/intel_soc_dts_thermal.c
new file mode 100644
index 00000000000..a6a0a18ec0a
--- /dev/null
+++ b/drivers/thermal/intel_soc_dts_thermal.c
@@ -0,0 +1,479 @@
+/*
+ * intel_soc_dts_thermal.c
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/thermal.h>
+#include <asm/cpu_device_id.h>
+#include <asm/iosf_mbi.h>
+
+#define SOC_DTS_OFFSET_ENABLE	0xB0
+#define SOC_DTS_OFFSET_TEMP	0xB1
+
+#define SOC_DTS_OFFSET_PTPS	0xB2
+#define SOC_DTS_OFFSET_PTTS	0xB3
+#define SOC_DTS_OFFSET_PTTSS	0xB4
+#define SOC_DTS_OFFSET_PTMC	0x80
+#define SOC_DTS_TE_AUX0		0xB5
+#define SOC_DTS_TE_AUX1		0xB6
+
+#define SOC_DTS_AUX0_ENABLE_BIT		BIT(0)
+#define SOC_DTS_AUX1_ENABLE_BIT		BIT(1)
+#define SOC_DTS_CPU_MODULE0_ENABLE_BIT	BIT(16)
+#define SOC_DTS_CPU_MODULE1_ENABLE_BIT	BIT(17)
+#define SOC_DTS_TE_SCI_ENABLE		BIT(9)
+#define SOC_DTS_TE_SMI_ENABLE		BIT(10)
+#define SOC_DTS_TE_MSI_ENABLE		BIT(11)
+#define SOC_DTS_TE_APICA_ENABLE		BIT(14)
+#define SOC_DTS_PTMC_APIC_DEASSERT_BIT	BIT(4)
+
+/* DTS encoding for TJ MAX temperature */
+#define SOC_DTS_TJMAX_ENCODING	0x7F
+
+/* IRQ 86 is a fixed APIC interrupt for BYT DTS Aux threshold notifications */
+#define BYT_SOC_DTS_APIC_IRQ	86
+
+/* Only 2 out of 4 is allowed for OSPM */
+#define SOC_MAX_DTS_TRIPS	2
+
+/* Mask for two trips in status bits */
+#define SOC_DTS_TRIP_MASK	0x03
+
+/* DTS0 and DTS 1 */
+#define SOC_MAX_DTS_SENSORS	2
+
+#define CRITICAL_OFFSET_FROM_TJ_MAX	5000
+
+struct soc_sensor_entry {
+	int id;
+	u32 tj_max;
+	u32 temp_mask;
+	u32 temp_shift;
+	u32 store_status;
+	struct thermal_zone_device *tzone;
+};
+
+static struct soc_sensor_entry *soc_dts[SOC_MAX_DTS_SENSORS];
+
+static int crit_offset = CRITICAL_OFFSET_FROM_TJ_MAX;
+module_param(crit_offset, int, 0644);
+MODULE_PARM_DESC(crit_offset,
+	"Critical Temperature offset from tj max in millidegree Celsius.");
+
+static DEFINE_MUTEX(aux_update_mutex);
+static spinlock_t intr_notify_lock;
+static int soc_dts_thres_irq;
+
+static int get_tj_max(u32 *tj_max)
+{
+	u32 eax, edx;
+	u32 val;
+	int err;
+
+	err = rdmsr_safe(MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
+	if (err)
+		goto err_ret;
+	else {
+		val = (eax >> 16) & 0xff;
+		if (val)
+			*tj_max = val * 1000;
+		else {
+			err = -EINVAL;
+			goto err_ret;
+		}
+	}
+
+	return 0;
+err_ret:
+	*tj_max = 0;
+
+	return err;
+}
+
+static int sys_get_trip_temp(struct thermal_zone_device *tzd,
+					int trip, unsigned long *temp)
+{
+	int status;
+	u32 out;
+	struct soc_sensor_entry *aux_entry;
+
+	aux_entry = tzd->devdata;
+
+	if (!trip) {
+		/* Just return the critical temp */
+		*temp = aux_entry->tj_max - crit_offset;
+		return 0;
+	}
+
+	mutex_lock(&aux_update_mutex);
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ,
+					SOC_DTS_OFFSET_PTPS, &out);
+	mutex_unlock(&aux_update_mutex);
+	if (status)
+		return status;
+
+	out = (out >> (trip * 8)) & SOC_DTS_TJMAX_ENCODING;
+
+	if (!out)
+		*temp = 0;
+	else
+		*temp = aux_entry->tj_max - out * 1000;
+
+	return 0;
+}
+
+static int update_trip_temp(struct soc_sensor_entry *aux_entry,
+				int thres_index, unsigned long temp)
+{
+	int status;
+	u32 temp_out;
+	u32 out;
+	u32 store_ptps;
+	u32 store_ptmc;
+	u32 store_te_out;
+	u32 te_out;
+
+	u32 int_enable_bit = SOC_DTS_TE_APICA_ENABLE |
+						SOC_DTS_TE_MSI_ENABLE;
+
+	temp_out = (aux_entry->tj_max - temp) / 1000;
+
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ,
+				SOC_DTS_OFFSET_PTPS, &store_ptps);
+	if (status)
+		return status;
+
+	out = (store_ptps & ~(0xFF << (thres_index * 8)));
+	out |= (temp_out & 0xFF) << (thres_index * 8);
+	status = iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+				SOC_DTS_OFFSET_PTPS, out);
+	if (status)
+		return status;
+	pr_debug("update_trip_temp PTPS = %x\n", out);
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ,
+					SOC_DTS_OFFSET_PTMC, &out);
+	if (status)
+		goto err_restore_ptps;
+
+	store_ptmc = out;
+
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ,
+					SOC_DTS_TE_AUX0 + thres_index,
+					&te_out);
+	if (status)
+		goto err_restore_ptmc;
+
+	store_te_out = te_out;
+
+	/* Enable for CPU module 0 and module 1 */
+	out |= (SOC_DTS_CPU_MODULE0_ENABLE_BIT |
+					SOC_DTS_CPU_MODULE1_ENABLE_BIT);
+	if (temp) {
+		if (thres_index)
+			out |= SOC_DTS_AUX1_ENABLE_BIT;
+		else
+			out |= SOC_DTS_AUX0_ENABLE_BIT;
+		te_out |= int_enable_bit;
+	} else {
+		if (thres_index)
+			out &= ~SOC_DTS_AUX1_ENABLE_BIT;
+		else
+			out &= ~SOC_DTS_AUX0_ENABLE_BIT;
+		te_out &= ~int_enable_bit;
+	}
+	status = iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+					SOC_DTS_OFFSET_PTMC, out);
+	if (status)
+		goto err_restore_te_out;
+
+	status = iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+					SOC_DTS_TE_AUX0 + thres_index,
+					te_out);
+	if (status)
+		goto err_restore_te_out;
+
+	return 0;
+
+err_restore_te_out:
+	iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+				SOC_DTS_OFFSET_PTMC, store_te_out);
+err_restore_ptmc:
+	iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+				SOC_DTS_OFFSET_PTMC, store_ptmc);
+err_restore_ptps:
+	iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+				SOC_DTS_OFFSET_PTPS, store_ptps);
+	/* Nothing we can do if restore fails */
+
+	return status;
+}
+
+static int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip,
+							unsigned long temp)
+{
+	struct soc_sensor_entry *aux_entry = tzd->devdata;
+	int status;
+
+	if (temp > (aux_entry->tj_max - crit_offset))
+		return -EINVAL;
+
+	mutex_lock(&aux_update_mutex);
+	status = update_trip_temp(tzd->devdata, trip, temp);
+	mutex_unlock(&aux_update_mutex);
+
+	return status;
+}
+
+static int sys_get_trip_type(struct thermal_zone_device *thermal,
+		int trip, enum thermal_trip_type *type)
+{
+	if (trip)
+		*type = THERMAL_TRIP_PASSIVE;
+	else
+		*type = THERMAL_TRIP_CRITICAL;
+
+	return 0;
+}
+
+static int sys_get_curr_temp(struct thermal_zone_device *tzd,
+						unsigned long *temp)
+{
+	int status;
+	u32 out;
+	struct soc_sensor_entry *aux_entry;
+
+	aux_entry = tzd->devdata;
+
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ,
+					SOC_DTS_OFFSET_TEMP, &out);
+	if (status)
+		return status;
+
+	out = (out & aux_entry->temp_mask) >> aux_entry->temp_shift;
+	out -= SOC_DTS_TJMAX_ENCODING;
+	*temp = aux_entry->tj_max - out * 1000;
+
+	return 0;
+}
+
+static struct thermal_zone_device_ops tzone_ops = {
+	.get_temp = sys_get_curr_temp,
+	.get_trip_temp = sys_get_trip_temp,
+	.get_trip_type = sys_get_trip_type,
+	.set_trip_temp = sys_set_trip_temp,
+};
+
+static void free_soc_dts(struct soc_sensor_entry *aux_entry)
+{
+	if (aux_entry) {
+		iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+			SOC_DTS_OFFSET_ENABLE, aux_entry->store_status);
+		thermal_zone_device_unregister(aux_entry->tzone);
+		kfree(aux_entry);
+	}
+}
+
+static int soc_dts_enable(int id)
+{
+	u32 out;
+	int ret;
+
+	ret = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ,
+					SOC_DTS_OFFSET_ENABLE, &out);
+	if (ret)
+		return ret;
+
+	if (!(out & BIT(id))) {
+		out |= BIT(id);
+		ret = iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+					SOC_DTS_OFFSET_ENABLE, out);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static struct soc_sensor_entry *alloc_soc_dts(int id, u32 tj_max)
+{
+	struct soc_sensor_entry *aux_entry;
+	char name[10];
+	int err;
+
+	aux_entry = kzalloc(sizeof(*aux_entry), GFP_KERNEL);
+	if (!aux_entry) {
+		err = -ENOMEM;
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* Store status to restor on exit */
+	err = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ,
+					SOC_DTS_OFFSET_ENABLE,
+					&aux_entry->store_status);
+	if (err)
+		goto err_ret;
+
+	aux_entry->id = id;
+	aux_entry->tj_max = tj_max;
+	aux_entry->temp_mask = 0x00FF << (id * 8);
+	aux_entry->temp_shift = id * 8;
+	snprintf(name, sizeof(name), "soc_dts%d", id);
+	aux_entry->tzone = thermal_zone_device_register(name,
+			SOC_MAX_DTS_TRIPS,
+			0x02,
+			aux_entry, &tzone_ops, NULL, 0, 0);
+	if (IS_ERR(aux_entry->tzone)) {
+		err = PTR_ERR(aux_entry->tzone);
+		goto err_ret;
+	}
+
+	err = soc_dts_enable(id);
+	if (err)
+		goto err_aux_status;
+
+	return aux_entry;
+
+err_aux_status:
+	thermal_zone_device_unregister(aux_entry->tzone);
+err_ret:
+	kfree(aux_entry);
+	return ERR_PTR(err);
+}
+
+static void proc_thermal_interrupt(void)
+{
+	u32 sticky_out;
+	int status;
+	u32 ptmc_out;
+
+	/* Clear APIC interrupt */
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ,
+				SOC_DTS_OFFSET_PTMC, &ptmc_out);
+
+	ptmc_out |= SOC_DTS_PTMC_APIC_DEASSERT_BIT;
+	status = iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+					SOC_DTS_OFFSET_PTMC, ptmc_out);
+
+	/* Read status here */
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_READ,
+					SOC_DTS_OFFSET_PTTSS, &sticky_out);
+	pr_debug("status %d PTTSS %x\n", status, sticky_out);
+	if (sticky_out & SOC_DTS_TRIP_MASK) {
+		int i;
+		/* reset sticky bit */
+		status = iosf_mbi_write(BT_MBI_UNIT_PMC, BT_MBI_BUNIT_WRITE,
+					SOC_DTS_OFFSET_PTTSS, sticky_out);
+		for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i) {
+			pr_debug("TZD update for zone %d\n", i);
+			thermal_zone_device_update(soc_dts[i]->tzone);
+		}
+	}
+
+}
+
+static irqreturn_t soc_irq_thread_fn(int irq, void *dev_data)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&intr_notify_lock, flags);
+	proc_thermal_interrupt();
+	spin_unlock_irqrestore(&intr_notify_lock, flags);
+	pr_debug("proc_thermal_interrupt\n");
+
+	return IRQ_HANDLED;
+}
+
+static const struct x86_cpu_id soc_thermal_ids[] = {
+	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, 0x37, 0, BYT_SOC_DTS_APIC_IRQ},
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, soc_thermal_ids);
+
+static int __init intel_soc_thermal_init(void)
+{
+	u32 tj_max;
+	int err = 0;
+	int i;
+	const struct x86_cpu_id *match_cpu;
+
+	match_cpu = x86_match_cpu(soc_thermal_ids);
+	if (!match_cpu)
+		return -ENODEV;
+
+	if (get_tj_max(&tj_max))
+		return -EINVAL;
+
+	for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i) {
+		soc_dts[i] = alloc_soc_dts(i, tj_max);
+		if (IS_ERR(soc_dts[i])) {
+			err = PTR_ERR(soc_dts[i]);
+			goto err_free;
+		}
+	}
+
+	spin_lock_init(&intr_notify_lock);
+
+	soc_dts_thres_irq = (int)match_cpu->driver_data;
+
+	err = request_threaded_irq(soc_dts_thres_irq, NULL,
+					soc_irq_thread_fn,
+					IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+					"soc_dts", soc_dts);
+	if (err) {
+		pr_err("request_threaded_irq ret %d\n", err);
+		goto err_free;
+	}
+
+	for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i) {
+		err = update_trip_temp(soc_dts[i], 0, tj_max - crit_offset);
+		if (err)
+			goto err_trip_temp;
+	}
+
+	return 0;
+
+err_trip_temp:
+	i = SOC_MAX_DTS_SENSORS;
+	free_irq(soc_dts_thres_irq, soc_dts);
+err_free:
+	while (--i >= 0)
+		free_soc_dts(soc_dts[i]);
+
+	return err;
+}
+
+static void __exit intel_soc_thermal_exit(void)
+{
+	int i;
+
+	for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i)
+		update_trip_temp(soc_dts[i], 0, 0);
+
+	free_irq(soc_dts_thres_irq, soc_dts);
+
+	for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i)
+		free_soc_dts(soc_dts[i]);
+
+}
+
+module_init(intel_soc_thermal_init)
+module_exit(intel_soc_thermal_exit)
+
+MODULE_DESCRIPTION("Intel SoC DTS Thermal Driver");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c
index 04b1be7fa01..4b2b999b761 100644
--- a/drivers/thermal/of-thermal.c
+++ b/drivers/thermal/of-thermal.c
@@ -156,8 +156,8 @@ static int of_thermal_bind(struct thermal_zone_device *thermal,
 
 			ret = thermal_zone_bind_cooling_device(thermal,
 						tbp->trip_id, cdev,
-						tbp->min,
-						tbp->max);
+						tbp->max,
+						tbp->min);
 			if (ret)
 				return ret;
 		}
@@ -712,11 +712,12 @@ thermal_of_build_thermal_zone(struct device_node *np)
 	}
 
 	i = 0;
-	for_each_child_of_node(child, gchild)
+	for_each_child_of_node(child, gchild) {
 		ret = thermal_of_populate_bind_params(gchild, &tz->tbps[i++],
 						      tz->trips, tz->ntrips);
 		if (ret)
 			goto free_tbps;
+	}
 
 finish:
 	of_node_put(child);
diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 5a37940b02c..8803e693fe6 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -374,10 +374,8 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 	int idle = IDLE_INTERVAL;
 
 	common = devm_kzalloc(dev, sizeof(*common), GFP_KERNEL);
-	if (!common) {
-		dev_err(dev, "Could not allocate common\n");
+	if (!common)
 		return -ENOMEM;
-	}
 
 	INIT_LIST_HEAD(&common->head);
 	spin_lock_init(&common->lock);
@@ -423,7 +421,6 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 
 		priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 		if (!priv) {
-			dev_err(dev, "Could not allocate priv\n");
 			ret = -ENOMEM;
 			goto error_unregister;
 		}
@@ -470,7 +467,7 @@ error_unregister:
 			rcar_thermal_irq_disable(priv);
 	}
 
-	pm_runtime_put_sync(dev);
+	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
 
 	return ret;
@@ -488,7 +485,7 @@ static int rcar_thermal_remove(struct platform_device *pdev)
 			rcar_thermal_irq_disable(priv);
 	}
 
-	pm_runtime_put_sync(dev);
+	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
 
 	return 0;
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index 0d96a510389..d7ca9f49c9c 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -41,12 +41,13 @@
  * @id: identifier of the one instance of the TMU controller.
  * @pdata: pointer to the tmu platform/configuration data
  * @base: base address of the single instance of the TMU controller.
- * @base_common: base address of the common registers of the TMU controller.
+ * @base_second: base address of the common registers of the TMU controller.
  * @irq: irq number of the TMU controller.
  * @soc: id of the SOC type.
  * @irq_work: pointer to the irq work structure.
  * @lock: lock to implement synchronization.
  * @clk: pointer to the clock structure.
+ * @clk_sec: pointer to the clock structure for accessing the base_second.
  * @temp_error1: fused value of the first point trim.
  * @temp_error2: fused value of the second point trim.
  * @regulator: pointer to the TMU regulator structure.
@@ -56,12 +57,12 @@ struct exynos_tmu_data {
 	int id;
 	struct exynos_tmu_platform_data *pdata;
 	void __iomem *base;
-	void __iomem *base_common;
+	void __iomem *base_second;
 	int irq;
 	enum soc_type soc;
 	struct work_struct irq_work;
 	struct mutex lock;
-	struct clk *clk;
+	struct clk *clk, *clk_sec;
 	u8 temp_error1, temp_error2;
 	struct regulator *regulator;
 	struct thermal_sensor_conf *reg_conf;
@@ -152,6 +153,8 @@ static int exynos_tmu_initialize(struct platform_device *pdev)
 
 	mutex_lock(&data->lock);
 	clk_enable(data->clk);
+	if (!IS_ERR(data->clk_sec))
+		clk_enable(data->clk_sec);
 
 	if (TMU_SUPPORTS(pdata, READY_STATUS)) {
 		status = readb(data->base + reg->tmu_status);
@@ -186,7 +189,12 @@ static int exynos_tmu_initialize(struct platform_device *pdev)
 			EXYNOS5440_EFUSE_SWAP_OFFSET + reg->triminfo_data);
 		}
 	} else {
-		trim_info = readl(data->base + reg->triminfo_data);
+		/* On exynos5420 the triminfo register is in the shared space */
+		if (data->soc == SOC_ARCH_EXYNOS5420_TRIMINFO)
+			trim_info = readl(data->base_second +
+							reg->triminfo_data);
+		else
+			trim_info = readl(data->base + reg->triminfo_data);
 	}
 	data->temp_error1 = trim_info & EXYNOS_TMU_TEMP_MASK;
 	data->temp_error2 = ((trim_info >> reg->triminfo_85_shift) &
@@ -225,6 +233,8 @@ skip_calib_data:
 			trigger_levs++;
 	}
 
+	rising_threshold = readl(data->base + reg->threshold_th0);
+
 	if (data->soc == SOC_ARCH_EXYNOS4210) {
 		/* Write temperature code for threshold */
 		threshold_code = temp_to_code(data, pdata->threshold);
@@ -238,7 +248,7 @@ skip_calib_data:
 			writeb(pdata->trigger_levels[i], data->base +
 			reg->threshold_th0 + i * sizeof(reg->threshold_th0));
 
-		writel(reg->inten_rise_mask, data->base + reg->tmu_intclear);
+		writel(reg->intclr_rise_mask, data->base + reg->tmu_intclear);
 	} else {
 		/* Write temperature code for rising and falling threshold */
 		for (i = 0;
@@ -249,6 +259,7 @@ skip_calib_data:
 				ret = threshold_code;
 				goto out;
 			}
+			rising_threshold &= ~(0xff << 8 * i);
 			rising_threshold |= threshold_code << 8 * i;
 			if (pdata->threshold_falling) {
 				threshold_code = temp_to_code(data,
@@ -265,8 +276,8 @@ skip_calib_data:
 		writel(falling_threshold,
 				data->base + reg->threshold_th1);
 
-		writel((reg->inten_rise_mask << reg->inten_rise_shift) |
-			(reg->inten_fall_mask << reg->inten_fall_shift),
+		writel((reg->intclr_rise_mask << reg->intclr_rise_shift) |
+			(reg->intclr_fall_mask << reg->intclr_fall_shift),
 				data->base + reg->tmu_intclear);
 
 		/* if last threshold limit is also present */
@@ -281,6 +292,7 @@ skip_calib_data:
 			}
 			if (i == EXYNOS_MAX_TRIGGER_PER_REG - 1) {
 				/* 1-4 level to be assigned in th0 reg */
+				rising_threshold &= ~(0xff << 8 * i);
 				rising_threshold |= threshold_code << 8 * i;
 				writel(rising_threshold,
 					data->base + reg->threshold_th0);
@@ -298,10 +310,12 @@ skip_calib_data:
 	}
 	/*Clear the PMIN in the common TMU register*/
 	if (reg->tmu_pmin && !data->id)
-		writel(0, data->base_common + reg->tmu_pmin);
+		writel(0, data->base_second + reg->tmu_pmin);
 out:
 	clk_disable(data->clk);
 	mutex_unlock(&data->lock);
+	if (!IS_ERR(data->clk_sec))
+		clk_disable(data->clk_sec);
 
 	return ret;
 }
@@ -453,12 +467,16 @@ static void exynos_tmu_work(struct work_struct *work)
 	const struct exynos_tmu_registers *reg = pdata->registers;
 	unsigned int val_irq, val_type;
 
+	if (!IS_ERR(data->clk_sec))
+		clk_enable(data->clk_sec);
 	/* Find which sensor generated this interrupt */
 	if (reg->tmu_irqstatus) {
-		val_type = readl(data->base_common + reg->tmu_irqstatus);
+		val_type = readl(data->base_second + reg->tmu_irqstatus);
 		if (!((val_type >> data->id) & 0x1))
 			goto out;
 	}
+	if (!IS_ERR(data->clk_sec))
+		clk_disable(data->clk_sec);
 
 	exynos_report_trigger(data->reg_conf);
 	mutex_lock(&data->lock);
@@ -499,6 +517,18 @@ static const struct of_device_id exynos_tmu_match[] = {
 		.data = (void *)EXYNOS5250_TMU_DRV_DATA,
 	},
 	{
+		.compatible = "samsung,exynos5260-tmu",
+		.data = (void *)EXYNOS5260_TMU_DRV_DATA,
+	},
+	{
+		.compatible = "samsung,exynos5420-tmu",
+		.data = (void *)EXYNOS5420_TMU_DRV_DATA,
+	},
+	{
+		.compatible = "samsung,exynos5420-tmu-ext-triminfo",
+		.data = (void *)EXYNOS5420_TMU_DRV_DATA,
+	},
+	{
 		.compatible = "samsung,exynos5440-tmu",
 		.data = (void *)EXYNOS5440_TMU_DRV_DATA,
 	},
@@ -580,7 +610,7 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 	 * Check if the TMU shares some registers and then try to map the
 	 * memory of common registers.
 	 */
-	if (!TMU_SUPPORTS(pdata, SHARED_MEMORY))
+	if (!TMU_SUPPORTS(pdata, ADDRESS_MULTIPLE))
 		return 0;
 
 	if (of_address_to_resource(pdev->dev.of_node, 1, &res)) {
@@ -588,9 +618,9 @@ static int exynos_map_dt_data(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	data->base_common = devm_ioremap(&pdev->dev, res.start,
+	data->base_second = devm_ioremap(&pdev->dev, res.start,
 					resource_size(&res));
-	if (!data->base_common) {
+	if (!data->base_second) {
 		dev_err(&pdev->dev, "Failed to ioremap memory\n");
 		return -ENOMEM;
 	}
@@ -607,10 +637,8 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 
 	data = devm_kzalloc(&pdev->dev, sizeof(struct exynos_tmu_data),
 					GFP_KERNEL);
-	if (!data) {
-		dev_err(&pdev->dev, "Failed to allocate driver structure\n");
+	if (!data)
 		return -ENOMEM;
-	}
 
 	platform_set_drvdata(pdev, data);
 	mutex_init(&data->lock);
@@ -629,13 +657,31 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 		return  PTR_ERR(data->clk);
 	}
 
+	data->clk_sec = devm_clk_get(&pdev->dev, "tmu_triminfo_apbif");
+	if (IS_ERR(data->clk_sec)) {
+		if (data->soc == SOC_ARCH_EXYNOS5420_TRIMINFO) {
+			dev_err(&pdev->dev, "Failed to get triminfo clock\n");
+			return PTR_ERR(data->clk_sec);
+		}
+	} else {
+		ret = clk_prepare(data->clk_sec);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to get clock\n");
+			return ret;
+		}
+	}
+
 	ret = clk_prepare(data->clk);
-	if (ret)
-		return ret;
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to get clock\n");
+		goto err_clk_sec;
+	}
 
 	if (pdata->type == SOC_ARCH_EXYNOS4210 ||
 	    pdata->type == SOC_ARCH_EXYNOS4412 ||
 	    pdata->type == SOC_ARCH_EXYNOS5250 ||
+	    pdata->type == SOC_ARCH_EXYNOS5260 ||
+	    pdata->type == SOC_ARCH_EXYNOS5420_TRIMINFO ||
 	    pdata->type == SOC_ARCH_EXYNOS5440)
 		data->soc = pdata->type;
 	else {
@@ -656,7 +702,6 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 	sensor_conf = devm_kzalloc(&pdev->dev,
 				sizeof(struct thermal_sensor_conf), GFP_KERNEL);
 	if (!sensor_conf) {
-		dev_err(&pdev->dev, "Failed to allocate registration struct\n");
 		ret = -ENOMEM;
 		goto err_clk;
 	}
@@ -704,6 +749,9 @@ static int exynos_tmu_probe(struct platform_device *pdev)
 	return 0;
 err_clk:
 	clk_unprepare(data->clk);
+err_clk_sec:
+	if (!IS_ERR(data->clk_sec))
+		clk_unprepare(data->clk_sec);
 	return ret;
 }
 
@@ -716,6 +764,8 @@ static int exynos_tmu_remove(struct platform_device *pdev)
 	exynos_unregister_thermal(data->reg_conf);
 
 	clk_unprepare(data->clk);
+	if (!IS_ERR(data->clk_sec))
+		clk_unprepare(data->clk_sec);
 
 	if (!IS_ERR(data->regulator))
 		regulator_disable(data->regulator);
diff --git a/drivers/thermal/samsung/exynos_tmu.h b/drivers/thermal/samsung/exynos_tmu.h
index 3fb65547e64..edd08cf7672 100644
--- a/drivers/thermal/samsung/exynos_tmu.h
+++ b/drivers/thermal/samsung/exynos_tmu.h
@@ -43,6 +43,8 @@ enum soc_type {
 	SOC_ARCH_EXYNOS4210 = 1,
 	SOC_ARCH_EXYNOS4412,
 	SOC_ARCH_EXYNOS5250,
+	SOC_ARCH_EXYNOS5260,
+	SOC_ARCH_EXYNOS5420_TRIMINFO,
 	SOC_ARCH_EXYNOS5440,
 };
 
@@ -60,7 +62,7 @@ enum soc_type {
  *			state(active/idle) can be checked.
  * TMU_SUPPORT_EMUL_TIME - This features allows to set next temp emulation
  *			sample time.
- * TMU_SUPPORT_SHARED_MEMORY - This feature tells that the different TMU
+ * TMU_SUPPORT_ADDRESS_MULTIPLE - This feature tells that the different TMU
  *			sensors shares some common registers.
  * TMU_SUPPORT - macro to compare the above features with the supplied.
  */
@@ -70,7 +72,7 @@ enum soc_type {
 #define TMU_SUPPORT_FALLING_TRIP		BIT(3)
 #define TMU_SUPPORT_READY_STATUS		BIT(4)
 #define TMU_SUPPORT_EMUL_TIME			BIT(5)
-#define TMU_SUPPORT_SHARED_MEMORY		BIT(6)
+#define TMU_SUPPORT_ADDRESS_MULTIPLE		BIT(6)
 
 #define TMU_SUPPORTS(a, b)	(a->features & TMU_SUPPORT_ ## b)
 
@@ -122,10 +124,6 @@ enum soc_type {
  * @threshold_th3_l0_shift: shift bits of level0 threshold temperature.
  * @tmu_inten: register containing the different threshold interrupt
 	enable bits.
- * @inten_rise_shift: shift bits of all rising interrupt bits.
- * @inten_rise_mask: mask bits of all rising interrupt bits.
- * @inten_fall_shift: shift bits of all rising interrupt bits.
- * @inten_fall_mask: mask bits of all rising interrupt bits.
  * @inten_rise0_shift: shift bits of rising 0 interrupt bits.
  * @inten_rise1_shift: shift bits of rising 1 interrupt bits.
  * @inten_rise2_shift: shift bits of rising 2 interrupt bits.
@@ -136,6 +134,10 @@ enum soc_type {
  * @inten_fall3_shift: shift bits of falling 3 interrupt bits.
  * @tmu_intstat: Register containing the interrupt status values.
  * @tmu_intclear: Register for clearing the raised interrupt status.
+ * @intclr_fall_shift: shift bits for interrupt clear fall 0
+ * @intclr_rise_shift: shift bits of all rising interrupt bits.
+ * @intclr_rise_mask: mask bits of all rising interrupt bits.
+ * @intclr_fall_mask: mask bits of all rising interrupt bits.
  * @emul_con: TMU emulation controller register.
  * @emul_temp_shift: shift bits of emulation temperature.
  * @emul_time_shift: shift bits of emulation time.
@@ -149,6 +151,7 @@ struct exynos_tmu_registers {
 	u32	triminfo_85_shift;
 
 	u32	triminfo_ctrl;
+	u32	triminfo_ctrl1;
 	u32	triminfo_reload_shift;
 
 	u32	tmu_ctrl;
@@ -191,10 +194,6 @@ struct exynos_tmu_registers {
 	u32	threshold_th3_l0_shift;
 
 	u32	tmu_inten;
-	u32	inten_rise_shift;
-	u32	inten_rise_mask;
-	u32	inten_fall_shift;
-	u32	inten_fall_mask;
 	u32	inten_rise0_shift;
 	u32	inten_rise1_shift;
 	u32	inten_rise2_shift;
@@ -207,6 +206,10 @@ struct exynos_tmu_registers {
 	u32	tmu_intstat;
 
 	u32	tmu_intclear;
+	u32	intclr_fall_shift;
+	u32	intclr_rise_shift;
+	u32	intclr_fall_mask;
+	u32	intclr_rise_mask;
 
 	u32	emul_con;
 	u32	emul_temp_shift;
diff --git a/drivers/thermal/samsung/exynos_tmu_data.c b/drivers/thermal/samsung/exynos_tmu_data.c
index 476b768c633..c1d81dcd781 100644
--- a/drivers/thermal/samsung/exynos_tmu_data.c
+++ b/drivers/thermal/samsung/exynos_tmu_data.c
@@ -40,13 +40,13 @@ static const struct exynos_tmu_registers exynos4210_tmu_registers = {
 	.threshold_temp = EXYNOS4210_TMU_REG_THRESHOLD_TEMP,
 	.threshold_th0 = EXYNOS4210_TMU_REG_TRIG_LEVEL0,
 	.tmu_inten = EXYNOS_TMU_REG_INTEN,
-	.inten_rise_mask = EXYNOS4210_TMU_TRIG_LEVEL_MASK,
 	.inten_rise0_shift = EXYNOS_TMU_INTEN_RISE0_SHIFT,
 	.inten_rise1_shift = EXYNOS_TMU_INTEN_RISE1_SHIFT,
 	.inten_rise2_shift = EXYNOS_TMU_INTEN_RISE2_SHIFT,
 	.inten_rise3_shift = EXYNOS_TMU_INTEN_RISE3_SHIFT,
 	.tmu_intstat = EXYNOS_TMU_REG_INTSTAT,
 	.tmu_intclear = EXYNOS_TMU_REG_INTCLEAR,
+	.intclr_rise_mask = EXYNOS4210_TMU_TRIG_LEVEL_MASK,
 };
 
 struct exynos_tmu_init_data const exynos4210_default_tmu_data = {
@@ -112,10 +112,6 @@ static const struct exynos_tmu_registers exynos4412_tmu_registers = {
 	.threshold_th0 = EXYNOS_THD_TEMP_RISE,
 	.threshold_th1 = EXYNOS_THD_TEMP_FALL,
 	.tmu_inten = EXYNOS_TMU_REG_INTEN,
-	.inten_rise_mask = EXYNOS_TMU_RISE_INT_MASK,
-	.inten_rise_shift = EXYNOS_TMU_RISE_INT_SHIFT,
-	.inten_fall_mask = EXYNOS_TMU_FALL_INT_MASK,
-	.inten_fall_shift = EXYNOS_TMU_FALL_INT_SHIFT,
 	.inten_rise0_shift = EXYNOS_TMU_INTEN_RISE0_SHIFT,
 	.inten_rise1_shift = EXYNOS_TMU_INTEN_RISE1_SHIFT,
 	.inten_rise2_shift = EXYNOS_TMU_INTEN_RISE2_SHIFT,
@@ -123,6 +119,10 @@ static const struct exynos_tmu_registers exynos4412_tmu_registers = {
 	.inten_fall0_shift = EXYNOS_TMU_INTEN_FALL0_SHIFT,
 	.tmu_intstat = EXYNOS_TMU_REG_INTSTAT,
 	.tmu_intclear = EXYNOS_TMU_REG_INTCLEAR,
+	.intclr_fall_shift = EXYNOS_TMU_CLEAR_FALL_INT_SHIFT,
+	.intclr_rise_shift = EXYNOS_TMU_RISE_INT_SHIFT,
+	.intclr_rise_mask = EXYNOS_TMU_RISE_INT_MASK,
+	.intclr_fall_mask = EXYNOS_TMU_FALL_INT_MASK,
 	.emul_con = EXYNOS_EMUL_CON,
 	.emul_temp_shift = EXYNOS_EMUL_DATA_SHIFT,
 	.emul_time_shift = EXYNOS_EMUL_TIME_SHIFT,
@@ -194,6 +194,197 @@ struct exynos_tmu_init_data const exynos5250_default_tmu_data = {
 };
 #endif
 
+#if defined(CONFIG_SOC_EXYNOS5260)
+static const struct exynos_tmu_registers exynos5260_tmu_registers = {
+	.triminfo_data = EXYNOS_TMU_REG_TRIMINFO,
+	.triminfo_25_shift = EXYNOS_TRIMINFO_25_SHIFT,
+	.triminfo_85_shift = EXYNOS_TRIMINFO_85_SHIFT,
+	.tmu_ctrl = EXYNOS_TMU_REG_CONTROL,
+	.tmu_ctrl = EXYNOS_TMU_REG_CONTROL1,
+	.buf_vref_sel_shift = EXYNOS_TMU_REF_VOLTAGE_SHIFT,
+	.buf_vref_sel_mask = EXYNOS_TMU_REF_VOLTAGE_MASK,
+	.therm_trip_mode_shift = EXYNOS_TMU_TRIP_MODE_SHIFT,
+	.therm_trip_mode_mask = EXYNOS_TMU_TRIP_MODE_MASK,
+	.therm_trip_en_shift = EXYNOS_TMU_THERM_TRIP_EN_SHIFT,
+	.buf_slope_sel_shift = EXYNOS_TMU_BUF_SLOPE_SEL_SHIFT,
+	.buf_slope_sel_mask = EXYNOS_TMU_BUF_SLOPE_SEL_MASK,
+	.core_en_shift = EXYNOS_TMU_CORE_EN_SHIFT,
+	.tmu_status = EXYNOS_TMU_REG_STATUS,
+	.tmu_cur_temp = EXYNOS_TMU_REG_CURRENT_TEMP,
+	.threshold_th0 = EXYNOS_THD_TEMP_RISE,
+	.threshold_th1 = EXYNOS_THD_TEMP_FALL,
+	.tmu_inten = EXYNOS5260_TMU_REG_INTEN,
+	.inten_rise0_shift = EXYNOS_TMU_INTEN_RISE0_SHIFT,
+	.inten_rise1_shift = EXYNOS_TMU_INTEN_RISE1_SHIFT,
+	.inten_rise2_shift = EXYNOS_TMU_INTEN_RISE2_SHIFT,
+	.inten_rise3_shift = EXYNOS_TMU_INTEN_RISE3_SHIFT,
+	.inten_fall0_shift = EXYNOS_TMU_INTEN_FALL0_SHIFT,
+	.tmu_intstat = EXYNOS5260_TMU_REG_INTSTAT,
+	.tmu_intclear = EXYNOS5260_TMU_REG_INTCLEAR,
+	.intclr_fall_shift = EXYNOS5420_TMU_CLEAR_FALL_INT_SHIFT,
+	.intclr_rise_shift = EXYNOS_TMU_RISE_INT_SHIFT,
+	.intclr_rise_mask = EXYNOS5260_TMU_RISE_INT_MASK,
+	.intclr_fall_mask = EXYNOS5260_TMU_FALL_INT_MASK,
+	.emul_con = EXYNOS5260_EMUL_CON,
+	.emul_temp_shift = EXYNOS_EMUL_DATA_SHIFT,
+	.emul_time_shift = EXYNOS_EMUL_TIME_SHIFT,
+	.emul_time_mask = EXYNOS_EMUL_TIME_MASK,
+};
+
+#define __EXYNOS5260_TMU_DATA	\
+	.threshold_falling = 10, \
+	.trigger_levels[0] = 85, \
+	.trigger_levels[1] = 103, \
+	.trigger_levels[2] = 110, \
+	.trigger_levels[3] = 120, \
+	.trigger_enable[0] = true, \
+	.trigger_enable[1] = true, \
+	.trigger_enable[2] = true, \
+	.trigger_enable[3] = false, \
+	.trigger_type[0] = THROTTLE_ACTIVE, \
+	.trigger_type[1] = THROTTLE_ACTIVE, \
+	.trigger_type[2] = SW_TRIP, \
+	.trigger_type[3] = HW_TRIP, \
+	.max_trigger_level = 4, \
+	.gain = 8, \
+	.reference_voltage = 16, \
+	.noise_cancel_mode = 4, \
+	.cal_type = TYPE_ONE_POINT_TRIMMING, \
+	.efuse_value = 55, \
+	.min_efuse_value = 40, \
+	.max_efuse_value = 100, \
+	.first_point_trim = 25, \
+	.second_point_trim = 85, \
+	.default_temp_offset = 50, \
+	.freq_tab[0] = { \
+		.freq_clip_max = 800 * 1000, \
+		.temp_level = 85, \
+	}, \
+	.freq_tab[1] = { \
+		.freq_clip_max = 200 * 1000, \
+		.temp_level = 103, \
+	}, \
+	.freq_tab_count = 2, \
+	.registers = &exynos5260_tmu_registers, \
+
+#define EXYNOS5260_TMU_DATA \
+	__EXYNOS5260_TMU_DATA \
+	.type = SOC_ARCH_EXYNOS5260, \
+	.features = (TMU_SUPPORT_EMULATION | TMU_SUPPORT_TRIM_RELOAD | \
+			TMU_SUPPORT_FALLING_TRIP | TMU_SUPPORT_READY_STATUS | \
+			TMU_SUPPORT_EMUL_TIME)
+
+struct exynos_tmu_init_data const exynos5260_default_tmu_data = {
+	.tmu_data = {
+		{ EXYNOS5260_TMU_DATA },
+		{ EXYNOS5260_TMU_DATA },
+		{ EXYNOS5260_TMU_DATA },
+		{ EXYNOS5260_TMU_DATA },
+		{ EXYNOS5260_TMU_DATA },
+	},
+	.tmu_count = 5,
+};
+#endif
+
+#if defined(CONFIG_SOC_EXYNOS5420)
+static const struct exynos_tmu_registers exynos5420_tmu_registers = {
+	.triminfo_data = EXYNOS_TMU_REG_TRIMINFO,
+	.triminfo_25_shift = EXYNOS_TRIMINFO_25_SHIFT,
+	.triminfo_85_shift = EXYNOS_TRIMINFO_85_SHIFT,
+	.tmu_ctrl = EXYNOS_TMU_REG_CONTROL,
+	.buf_vref_sel_shift = EXYNOS_TMU_REF_VOLTAGE_SHIFT,
+	.buf_vref_sel_mask = EXYNOS_TMU_REF_VOLTAGE_MASK,
+	.therm_trip_mode_shift = EXYNOS_TMU_TRIP_MODE_SHIFT,
+	.therm_trip_mode_mask = EXYNOS_TMU_TRIP_MODE_MASK,
+	.therm_trip_en_shift = EXYNOS_TMU_THERM_TRIP_EN_SHIFT,
+	.buf_slope_sel_shift = EXYNOS_TMU_BUF_SLOPE_SEL_SHIFT,
+	.buf_slope_sel_mask = EXYNOS_TMU_BUF_SLOPE_SEL_MASK,
+	.core_en_shift = EXYNOS_TMU_CORE_EN_SHIFT,
+	.tmu_status = EXYNOS_TMU_REG_STATUS,
+	.tmu_cur_temp = EXYNOS_TMU_REG_CURRENT_TEMP,
+	.threshold_th0 = EXYNOS_THD_TEMP_RISE,
+	.threshold_th1 = EXYNOS_THD_TEMP_FALL,
+	.tmu_inten = EXYNOS_TMU_REG_INTEN,
+	.inten_rise0_shift = EXYNOS_TMU_INTEN_RISE0_SHIFT,
+	.inten_rise1_shift = EXYNOS_TMU_INTEN_RISE1_SHIFT,
+	.inten_rise2_shift = EXYNOS_TMU_INTEN_RISE2_SHIFT,
+	/* INTEN_RISE3 Not availble in exynos5420 */
+	.inten_rise3_shift = EXYNOS_TMU_INTEN_RISE3_SHIFT,
+	.inten_fall0_shift = EXYNOS_TMU_INTEN_FALL0_SHIFT,
+	.tmu_intstat = EXYNOS_TMU_REG_INTSTAT,
+	.tmu_intclear = EXYNOS_TMU_REG_INTCLEAR,
+	.intclr_fall_shift = EXYNOS5420_TMU_CLEAR_FALL_INT_SHIFT,
+	.intclr_rise_shift = EXYNOS_TMU_RISE_INT_SHIFT,
+	.intclr_rise_mask = EXYNOS_TMU_RISE_INT_MASK,
+	.intclr_fall_mask = EXYNOS_TMU_FALL_INT_MASK,
+	.emul_con = EXYNOS_EMUL_CON,
+	.emul_temp_shift = EXYNOS_EMUL_DATA_SHIFT,
+	.emul_time_shift = EXYNOS_EMUL_TIME_SHIFT,
+	.emul_time_mask = EXYNOS_EMUL_TIME_MASK,
+};
+
+#define __EXYNOS5420_TMU_DATA	\
+	.threshold_falling = 10, \
+	.trigger_levels[0] = 85, \
+	.trigger_levels[1] = 103, \
+	.trigger_levels[2] = 110, \
+	.trigger_levels[3] = 120, \
+	.trigger_enable[0] = true, \
+	.trigger_enable[1] = true, \
+	.trigger_enable[2] = true, \
+	.trigger_enable[3] = false, \
+	.trigger_type[0] = THROTTLE_ACTIVE, \
+	.trigger_type[1] = THROTTLE_ACTIVE, \
+	.trigger_type[2] = SW_TRIP, \
+	.trigger_type[3] = HW_TRIP, \
+	.max_trigger_level = 4, \
+	.gain = 8, \
+	.reference_voltage = 16, \
+	.noise_cancel_mode = 4, \
+	.cal_type = TYPE_ONE_POINT_TRIMMING, \
+	.efuse_value = 55, \
+	.min_efuse_value = 40, \
+	.max_efuse_value = 100, \
+	.first_point_trim = 25, \
+	.second_point_trim = 85, \
+	.default_temp_offset = 50, \
+	.freq_tab[0] = { \
+		.freq_clip_max = 800 * 1000, \
+		.temp_level = 85, \
+	}, \
+	.freq_tab[1] = { \
+		.freq_clip_max = 200 * 1000, \
+		.temp_level = 103, \
+	}, \
+	.freq_tab_count = 2, \
+	.registers = &exynos5420_tmu_registers, \
+
+#define EXYNOS5420_TMU_DATA \
+	__EXYNOS5420_TMU_DATA \
+	.type = SOC_ARCH_EXYNOS5250, \
+	.features = (TMU_SUPPORT_EMULATION | TMU_SUPPORT_TRIM_RELOAD | \
+			TMU_SUPPORT_FALLING_TRIP | TMU_SUPPORT_READY_STATUS | \
+			TMU_SUPPORT_EMUL_TIME)
+
+#define EXYNOS5420_TMU_DATA_SHARED \
+	__EXYNOS5420_TMU_DATA \
+	.type = SOC_ARCH_EXYNOS5420_TRIMINFO, \
+	.features = (TMU_SUPPORT_EMULATION | TMU_SUPPORT_TRIM_RELOAD | \
+			TMU_SUPPORT_FALLING_TRIP | TMU_SUPPORT_READY_STATUS | \
+			TMU_SUPPORT_EMUL_TIME | TMU_SUPPORT_ADDRESS_MULTIPLE)
+
+struct exynos_tmu_init_data const exynos5420_default_tmu_data = {
+	.tmu_data = {
+		{ EXYNOS5420_TMU_DATA },
+		{ EXYNOS5420_TMU_DATA },
+		{ EXYNOS5420_TMU_DATA_SHARED },
+		{ EXYNOS5420_TMU_DATA_SHARED },
+		{ EXYNOS5420_TMU_DATA_SHARED },
+	},
+	.tmu_count = 5,
+};
+#endif
+
 #if defined(CONFIG_SOC_EXYNOS5440)
 static const struct exynos_tmu_registers exynos5440_tmu_registers = {
 	.triminfo_data = EXYNOS5440_TMU_S0_7_TRIM,
@@ -217,10 +408,6 @@ static const struct exynos_tmu_registers exynos5440_tmu_registers = {
 	.threshold_th2 = EXYNOS5440_TMU_S0_7_TH2,
 	.threshold_th3_l0_shift = EXYNOS5440_TMU_TH_RISE4_SHIFT,
 	.tmu_inten = EXYNOS5440_TMU_S0_7_IRQEN,
-	.inten_rise_mask = EXYNOS5440_TMU_RISE_INT_MASK,
-	.inten_rise_shift = EXYNOS5440_TMU_RISE_INT_SHIFT,
-	.inten_fall_mask = EXYNOS5440_TMU_FALL_INT_MASK,
-	.inten_fall_shift = EXYNOS5440_TMU_FALL_INT_SHIFT,
 	.inten_rise0_shift = EXYNOS5440_TMU_INTEN_RISE0_SHIFT,
 	.inten_rise1_shift = EXYNOS5440_TMU_INTEN_RISE1_SHIFT,
 	.inten_rise2_shift = EXYNOS5440_TMU_INTEN_RISE2_SHIFT,
@@ -228,6 +415,10 @@ static const struct exynos_tmu_registers exynos5440_tmu_registers = {
 	.inten_fall0_shift = EXYNOS5440_TMU_INTEN_FALL0_SHIFT,
 	.tmu_intstat = EXYNOS5440_TMU_S0_7_IRQ,
 	.tmu_intclear = EXYNOS5440_TMU_S0_7_IRQ,
+	.intclr_fall_shift = EXYNOS5440_TMU_CLEAR_FALL_INT_SHIFT,
+	.intclr_rise_shift = EXYNOS5440_TMU_RISE_INT_SHIFT,
+	.intclr_rise_mask = EXYNOS5440_TMU_RISE_INT_MASK,
+	.intclr_fall_mask = EXYNOS5440_TMU_FALL_INT_MASK,
 	.tmu_irqstatus = EXYNOS5440_TMU_IRQ_STATUS,
 	.emul_con = EXYNOS5440_TMU_S0_7_DEBUG,
 	.emul_temp_shift = EXYNOS_EMUL_DATA_SHIFT,
@@ -255,7 +446,7 @@ static const struct exynos_tmu_registers exynos5440_tmu_registers = {
 	.type = SOC_ARCH_EXYNOS5440, \
 	.registers = &exynos5440_tmu_registers, \
 	.features = (TMU_SUPPORT_EMULATION | TMU_SUPPORT_FALLING_TRIP | \
-			TMU_SUPPORT_MULTI_INST | TMU_SUPPORT_SHARED_MEMORY),
+			TMU_SUPPORT_MULTI_INST | TMU_SUPPORT_ADDRESS_MULTIPLE),
 
 struct exynos_tmu_init_data const exynos5440_default_tmu_data = {
 	.tmu_data = {
diff --git a/drivers/thermal/samsung/exynos_tmu_data.h b/drivers/thermal/samsung/exynos_tmu_data.h
index a1ea19d9e0a..d268981b65e 100644
--- a/drivers/thermal/samsung/exynos_tmu_data.h
+++ b/drivers/thermal/samsung/exynos_tmu_data.h
@@ -69,9 +69,11 @@
 #define EXYNOS_TMU_RISE_INT_MASK	0x111
 #define EXYNOS_TMU_RISE_INT_SHIFT	0
 #define EXYNOS_TMU_FALL_INT_MASK	0x111
-#define EXYNOS_TMU_FALL_INT_SHIFT	12
 #define EXYNOS_TMU_CLEAR_RISE_INT	0x111
 #define EXYNOS_TMU_CLEAR_FALL_INT	(0x111 << 12)
+#define EXYNOS_TMU_CLEAR_FALL_INT_SHIFT	12
+#define EXYNOS5420_TMU_CLEAR_FALL_INT_SHIFT	16
+#define EXYNOS5440_TMU_CLEAR_FALL_INT_SHIFT	4
 #define EXYNOS_TMU_TRIP_MODE_SHIFT	13
 #define EXYNOS_TMU_TRIP_MODE_MASK	0x7
 #define EXYNOS_TMU_THERM_TRIP_EN_SHIFT	12
@@ -85,6 +87,7 @@
 #define EXYNOS_TMU_INTEN_FALL0_SHIFT	16
 #define EXYNOS_TMU_INTEN_FALL1_SHIFT	20
 #define EXYNOS_TMU_INTEN_FALL2_SHIFT	24
+#define EXYNOS_TMU_INTEN_FALL3_SHIFT	28
 
 #define EXYNOS_EMUL_TIME	0x57F0
 #define EXYNOS_EMUL_TIME_MASK	0xffff
@@ -95,6 +98,17 @@
 
 #define EXYNOS_MAX_TRIGGER_PER_REG	4
 
+/* Exynos5260 specific */
+#define EXYNOS_TMU_REG_CONTROL1			0x24
+#define EXYNOS5260_TMU_REG_INTEN		0xC0
+#define EXYNOS5260_TMU_REG_INTSTAT		0xC4
+#define EXYNOS5260_TMU_REG_INTCLEAR		0xC8
+#define EXYNOS5260_TMU_CLEAR_RISE_INT		0x1111
+#define EXYNOS5260_TMU_CLEAR_FALL_INT		(0x1111 << 16)
+#define EXYNOS5260_TMU_RISE_INT_MASK		0x1111
+#define EXYNOS5260_TMU_FALL_INT_MASK		0x1111
+#define EXYNOS5260_EMUL_CON			0x100
+
 /* Exynos4412 specific */
 #define EXYNOS4412_MUX_ADDR_VALUE          6
 #define EXYNOS4412_MUX_ADDR_SHIFT          20
@@ -119,7 +133,6 @@
 #define EXYNOS5440_TMU_RISE_INT_MASK		0xf
 #define EXYNOS5440_TMU_RISE_INT_SHIFT		0
 #define EXYNOS5440_TMU_FALL_INT_MASK		0xf
-#define EXYNOS5440_TMU_FALL_INT_SHIFT		4
 #define EXYNOS5440_TMU_INTEN_RISE0_SHIFT	0
 #define EXYNOS5440_TMU_INTEN_RISE1_SHIFT	1
 #define EXYNOS5440_TMU_INTEN_RISE2_SHIFT	2
@@ -156,6 +169,20 @@ extern struct exynos_tmu_init_data const exynos5250_default_tmu_data;
 #define EXYNOS5250_TMU_DRV_DATA (NULL)
 #endif
 
+#if defined(CONFIG_SOC_EXYNOS5260)
+extern struct exynos_tmu_init_data const exynos5260_default_tmu_data;
+#define EXYNOS5260_TMU_DRV_DATA (&exynos5260_default_tmu_data)
+#else
+#define EXYNOS5260_TMU_DRV_DATA (NULL)
+#endif
+
+#if defined(CONFIG_SOC_EXYNOS5420)
+extern struct exynos_tmu_init_data const exynos5420_default_tmu_data;
+#define EXYNOS5420_TMU_DRV_DATA (&exynos5420_default_tmu_data)
+#else
+#define EXYNOS5420_TMU_DRV_DATA (NULL)
+#endif
+
 #if defined(CONFIG_SOC_EXYNOS5440)
 extern struct exynos_tmu_init_data const exynos5440_default_tmu_data;
 #define EXYNOS5440_TMU_DRV_DATA (&exynos5440_default_tmu_data)
diff --git a/drivers/thermal/spear_thermal.c b/drivers/thermal/spear_thermal.c
index ab79ea4701d..1e2193fc324 100644
--- a/drivers/thermal/spear_thermal.c
+++ b/drivers/thermal/spear_thermal.c
@@ -113,10 +113,8 @@ static int spear_thermal_probe(struct platform_device *pdev)
 	}
 
 	stdev = devm_kzalloc(&pdev->dev, sizeof(*stdev), GFP_KERNEL);
-	if (!stdev) {
-		dev_err(&pdev->dev, "kzalloc fail\n");
+	if (!stdev)
 		return -ENOMEM;
-	}
 
 	/* Enable thermal sensor */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index fdb07199d9c..1967bee4f07 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -140,6 +140,12 @@ thermal_hwmon_lookup_temp(const struct thermal_hwmon_device *hwmon,
 	return NULL;
 }
 
+static bool thermal_zone_crit_temp_valid(struct thermal_zone_device *tz)
+{
+	unsigned long temp;
+	return tz->ops->get_crit_temp && !tz->ops->get_crit_temp(tz, &temp);
+}
+
 int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 {
 	struct thermal_hwmon_device *hwmon;
@@ -189,21 +195,18 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 	if (result)
 		goto free_temp_mem;
 
-	if (tz->ops->get_crit_temp) {
-		unsigned long temperature;
-		if (!tz->ops->get_crit_temp(tz, &temperature)) {
-			snprintf(temp->temp_crit.name,
-				 sizeof(temp->temp_crit.name),
+	if (thermal_zone_crit_temp_valid(tz)) {
+		snprintf(temp->temp_crit.name,
+				sizeof(temp->temp_crit.name),
 				"temp%d_crit", hwmon->count);
-			temp->temp_crit.attr.attr.name = temp->temp_crit.name;
-			temp->temp_crit.attr.attr.mode = 0444;
-			temp->temp_crit.attr.show = temp_crit_show;
-			sysfs_attr_init(&temp->temp_crit.attr.attr);
-			result = device_create_file(hwmon->device,
-						    &temp->temp_crit.attr);
-			if (result)
-				goto unregister_input;
-		}
+		temp->temp_crit.attr.attr.name = temp->temp_crit.name;
+		temp->temp_crit.attr.attr.mode = 0444;
+		temp->temp_crit.attr.show = temp_crit_show;
+		sysfs_attr_init(&temp->temp_crit.attr.attr);
+		result = device_create_file(hwmon->device,
+					    &temp->temp_crit.attr);
+		if (result)
+			goto unregister_input;
 	}
 
 	mutex_lock(&thermal_hwmon_list_lock);
@@ -250,7 +253,7 @@ void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
 	}
 
 	device_remove_file(hwmon->device, &temp->temp_input.attr);
-	if (tz->ops->get_crit_temp)
+	if (thermal_zone_crit_temp_valid(tz))
 		device_remove_file(hwmon->device, &temp->temp_crit.attr);
 
 	mutex_lock(&thermal_hwmon_list_lock);
diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
index 3ab12ee359b..634b6ce0e63 100644
--- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c
+++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
@@ -1155,7 +1155,7 @@ static struct ti_bandgap *ti_bandgap_build(struct platform_device *pdev)
 	/* register shadow for context save and restore */
 	bgp->regval = devm_kzalloc(&pdev->dev, sizeof(*bgp->regval) *
 				   bgp->conf->sensor_count, GFP_KERNEL);
-	if (!bgp) {
+	if (!bgp->regval) {
 		dev_err(&pdev->dev, "Unable to allocate mem for driver ref\n");
 		return ERR_PTR(-ENOMEM);
 	}
@@ -1248,7 +1248,7 @@ int ti_bandgap_probe(struct platform_device *pdev)
 	clk_rate = clk_round_rate(bgp->div_clk,
 				  bgp->conf->sensors[0].ts_data->max_freq);
 	if (clk_rate < bgp->conf->sensors[0].ts_data->min_freq ||
-	    clk_rate == 0xffffffff) {
+	    clk_rate <= 0) {
 		ret = -ENODEV;
 		dev_err(&pdev->dev, "wrong clock rate (%d)\n", clk_rate);
 		goto put_clks;
diff --git a/drivers/tty/hvc/hvc_tile.c b/drivers/tty/hvc/hvc_tile.c
index 147d49e95db..df374860037 100644
--- a/drivers/tty/hvc/hvc_tile.c
+++ b/drivers/tty/hvc/hvc_tile.c
@@ -196,7 +196,7 @@ static int __init hvc_tile_init(void)
 #ifndef __tilegx__
 	struct hvc_struct *hp;
 	hp = hvc_alloc(0, 0, &hvc_tile_get_put_ops, 128);
-	return IS_ERR(hp) ? PTR_ERR(hp) : 0;
+	return PTR_ERR_OR_ZERO(hp);
 #else
 	platform_device_register(&hvc_tile_pdev);
 	return platform_driver_register(&hvc_tile_driver);
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index f95569dedc8..f44f1ba762c 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1214,15 +1214,16 @@ static void n_tty_receive_parity_error(struct tty_struct *tty, unsigned char c)
 {
 	struct n_tty_data *ldata = tty->disc_data;
 
-	if (I_IGNPAR(tty))
-		return;
-	if (I_PARMRK(tty)) {
-		put_tty_queue('\377', ldata);
-		put_tty_queue('\0', ldata);
-		put_tty_queue(c, ldata);
-	} else	if (I_INPCK(tty))
-		put_tty_queue('\0', ldata);
-	else
+	if (I_INPCK(tty)) {
+		if (I_IGNPAR(tty))
+			return;
+		if (I_PARMRK(tty)) {
+			put_tty_queue('\377', ldata);
+			put_tty_queue('\0', ldata);
+			put_tty_queue(c, ldata);
+		} else
+			put_tty_queue('\0', ldata);
+	} else
 		put_tty_queue(c, ldata);
 	if (waitqueue_active(&tty->read_wait))
 		wake_up_interruptible(&tty->read_wait);
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 27f7ad6b74c..7a91c6d1eb7 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -2357,7 +2357,7 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c
index cfef801a49d..4858b8a99d3 100644
--- a/drivers/tty/serial/8250/8250_early.c
+++ b/drivers/tty/serial/8250/8250_early.c
@@ -144,8 +144,11 @@ static int __init early_serial8250_setup(struct earlycon_device *device,
 	if (!(device->port.membase || device->port.iobase))
 		return 0;
 
-	if (!device->baud)
+	if (!device->baud) {
 		device->baud = probe_baud(&device->port);
+		snprintf(device->options, sizeof(device->options), "%u",
+			 device->baud);
+	}
 
 	init_port(device);
 
diff --git a/drivers/tty/serial/altera_uart.c b/drivers/tty/serial/altera_uart.c
index 501667e3e3f..323376668b7 100644
--- a/drivers/tty/serial/altera_uart.c
+++ b/drivers/tty/serial/altera_uart.c
@@ -185,6 +185,12 @@ static void altera_uart_set_termios(struct uart_port *port,
 	uart_update_timeout(port, termios->c_cflag, baud);
 	altera_uart_writel(port, baudclk, ALTERA_UART_DIVISOR_REG);
 	spin_unlock_irqrestore(&port->lock, flags);
+
+	/*
+	 * FIXME: port->read_status_mask and port->ignore_status_mask
+	 * need to be initialized based on termios settings for
+	 * INPCK, IGNBRK, IGNPAR, PARMRK, BRKINT
+	 */
 }
 
 static void altera_uart_rx_chars(struct altera_uart *pp)
diff --git a/drivers/tty/serial/amba-pl010.c b/drivers/tty/serial/amba-pl010.c
index 01c9e72433e..971af1e22d0 100644
--- a/drivers/tty/serial/amba-pl010.c
+++ b/drivers/tty/serial/amba-pl010.c
@@ -420,7 +420,7 @@ pl010_set_termios(struct uart_port *port, struct ktermios *termios,
 	uap->port.read_status_mask = UART01x_RSR_OE;
 	if (termios->c_iflag & INPCK)
 		uap->port.read_status_mask |= UART01x_RSR_FE | UART01x_RSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		uap->port.read_status_mask |= UART01x_RSR_BE;
 
 	/*
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 908a6e3142a..0e26dcbd5ea 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1744,7 +1744,7 @@ pl011_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = UART011_DR_OE | 255;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART011_DR_FE | UART011_DR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART011_DR_BE;
 
 	/*
diff --git a/drivers/tty/serial/arc_uart.c b/drivers/tty/serial/arc_uart.c
index c9f5c9dcc15..008c223eaf2 100644
--- a/drivers/tty/serial/arc_uart.c
+++ b/drivers/tty/serial/arc_uart.c
@@ -177,7 +177,7 @@ static void arc_serial_tx_chars(struct arc_uart_port *uart)
 		uart->port.icount.tx++;
 		uart->port.x_char = 0;
 		sent = 1;
-	} else if (xmit->tail != xmit->head) {	/* TODO: uart_circ_empty */
+	} else if (!uart_circ_empty(xmit)) {
 		ch = xmit->buf[xmit->tail];
 		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
 		uart->port.icount.tx++;
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 3fceae099c4..c4f75031410 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -1932,7 +1932,7 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = ATMEL_US_OVRE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= (ATMEL_US_FRAME | ATMEL_US_PARE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= ATMEL_US_RXBRK;
 
 	if (atmel_use_pdc_rx(port))
diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c
index a47421e4627..231519022b7 100644
--- a/drivers/tty/serial/bcm63xx_uart.c
+++ b/drivers/tty/serial/bcm63xx_uart.c
@@ -567,7 +567,7 @@ static void bcm_uart_set_termios(struct uart_port *port,
 		port->read_status_mask |= UART_FIFO_FRAMEERR_MASK;
 		port->read_status_mask |= UART_FIFO_PARERR_MASK;
 	}
-	if (new->c_iflag & (BRKINT))
+	if (new->c_iflag & (IGNBRK | BRKINT))
 		port->read_status_mask |= UART_FIFO_BRKDET_MASK;
 
 	port->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/bfin_uart.c b/drivers/tty/serial/bfin_uart.c
index 869ceba2ec5..ac86a20992e 100644
--- a/drivers/tty/serial/bfin_uart.c
+++ b/drivers/tty/serial/bfin_uart.c
@@ -833,7 +833,7 @@ bfin_serial_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = OE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= (FE | PE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= BI;
 
 	/*
diff --git a/drivers/tty/serial/dz.c b/drivers/tty/serial/dz.c
index 2f2b2e538a5..cdbbc788230 100644
--- a/drivers/tty/serial/dz.c
+++ b/drivers/tty/serial/dz.c
@@ -625,7 +625,7 @@ static void dz_set_termios(struct uart_port *uport, struct ktermios *termios,
 	dport->port.read_status_mask = DZ_OERR;
 	if (termios->c_iflag & INPCK)
 		dport->port.read_status_mask |= DZ_FERR | DZ_PERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		dport->port.read_status_mask |= DZ_BREAK;
 
 	/* characters to ignore */
diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c
index 5131b5ee616..a514ee6f540 100644
--- a/drivers/tty/serial/earlycon.c
+++ b/drivers/tty/serial/earlycon.c
@@ -25,7 +25,7 @@
 #include <asm/serial.h>
 
 static struct console early_con = {
-	.name =		"earlycon",
+	.name =		"uart", /* 8250 console switch requires this name */
 	.flags =	CON_PRINTBUFFER | CON_BOOT,
 	.index =	-1,
 };
diff --git a/drivers/tty/serial/efm32-uart.c b/drivers/tty/serial/efm32-uart.c
index b373f6416e8..3b0ee9afd76 100644
--- a/drivers/tty/serial/efm32-uart.c
+++ b/drivers/tty/serial/efm32-uart.c
@@ -407,7 +407,7 @@ static void efm32_uart_set_termios(struct uart_port *port,
 	if (new->c_iflag & INPCK)
 		port->read_status_mask |=
 			UARTn_RXDATAX_FERR | UARTn_RXDATAX_PERR;
-	if (new->c_iflag & (BRKINT | PARMRK))
+	if (new->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= SW_UARTn_RXDATAX_BERR;
 
 	port->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index c5eb897de9d..49385c86cfb 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -902,7 +902,7 @@ lpuart_set_termios(struct uart_port *port, struct ktermios *termios,
 	sport->port.read_status_mask = 0;
 	if (termios->c_iflag & INPCK)
 		sport->port.read_status_mask |=	(UARTSR1_FE | UARTSR1_PE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		sport->port.read_status_mask |= UARTSR1_FE;
 
 	/* characters to ignore */
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index e2f93874989..044e86d528a 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -567,6 +567,9 @@ static void imx_start_tx(struct uart_port *port)
 	struct imx_port *sport = (struct imx_port *)port;
 	unsigned long temp;
 
+	if (uart_circ_empty(&port->state->xmit))
+		return;
+
 	if (USE_IRDA(sport)) {
 		/* half duplex in IrDA mode; have to disable receive mode */
 		temp = readl(sport->port.membase + UCR4);
diff --git a/drivers/tty/serial/ip22zilog.c b/drivers/tty/serial/ip22zilog.c
index 1d9420548e1..99b7b869786 100644
--- a/drivers/tty/serial/ip22zilog.c
+++ b/drivers/tty/serial/ip22zilog.c
@@ -603,6 +603,8 @@ static void ip22zilog_start_tx(struct uart_port *port)
 	} else {
 		struct circ_buf *xmit = &port->state->xmit;
 
+		if (uart_circ_empty(xmit))
+			return;
 		writeb(xmit->buf[xmit->tail], &channel->data);
 		ZSDELAY();
 		ZS_WSYNC(channel);
@@ -850,7 +852,7 @@ ip22zilog_convert_to_zs(struct uart_ip22zilog_port *up, unsigned int cflag,
 	up->port.read_status_mask = Rx_OVR;
 	if (iflag & INPCK)
 		up->port.read_status_mask |= CRC_ERR | PAR_ERR;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= BRK_ABRT;
 
 	up->port.ignore_status_mask = 0;
diff --git a/drivers/tty/serial/m32r_sio.c b/drivers/tty/serial/m32r_sio.c
index 9cd9b4eba9f..5702828fb62 100644
--- a/drivers/tty/serial/m32r_sio.c
+++ b/drivers/tty/serial/m32r_sio.c
@@ -266,9 +266,11 @@ static void m32r_sio_start_tx(struct uart_port *port)
 	if (!(up->ier & UART_IER_THRI)) {
 		up->ier |= UART_IER_THRI;
 		serial_out(up, UART_IER, up->ier);
-		serial_out(up, UART_TX, xmit->buf[xmit->tail]);
-		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
-		up->port.icount.tx++;
+		if (!uart_circ_empty(xmit)) {
+			serial_out(up, UART_TX, xmit->buf[xmit->tail]);
+			xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
+			up->port.icount.tx++;
+		}
 	}
 	while((serial_in(up, UART_LSR) & UART_EMPTY) != UART_EMPTY);
 #else
@@ -737,7 +739,7 @@ static void m32r_sio_set_termios(struct uart_port *port,
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 2a99d0c61b9..ba285cd45b5 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -835,7 +835,7 @@ static void max310x_set_termios(struct uart_port *port,
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= MAX310X_LSR_RXPAR_BIT |
 					  MAX310X_LSR_FRERR_BIT;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= MAX310X_LSR_RXBRK_BIT;
 
 	/* Set status ignore mask */
diff --git a/drivers/tty/serial/mcf.c b/drivers/tty/serial/mcf.c
index 0edfaf8cd26..a6f085717f9 100644
--- a/drivers/tty/serial/mcf.c
+++ b/drivers/tty/serial/mcf.c
@@ -248,6 +248,12 @@ static void mcf_set_termios(struct uart_port *port, struct ktermios *termios,
 		mr1 |= MCFUART_MR1_PARITYNONE;
 	}
 
+	/*
+	 * FIXME: port->read_status_mask and port->ignore_status_mask
+	 * need to be initialized based on termios settings for
+	 * INPCK, IGNBRK, IGNPAR, PARMRK, BRKINT
+	 */
+
 	if (termios->c_cflag & CSTOPB)
 		mr2 |= MCFUART_MR2_STOP2;
 	else
diff --git a/drivers/tty/serial/mfd.c b/drivers/tty/serial/mfd.c
index 52c930fac21..445799dc984 100644
--- a/drivers/tty/serial/mfd.c
+++ b/drivers/tty/serial/mfd.c
@@ -977,7 +977,7 @@ serial_hsu_set_termios(struct uart_port *port, struct ktermios *termios,
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/* Characters to ignore */
diff --git a/drivers/tty/serial/mpsc.c b/drivers/tty/serial/mpsc.c
index e30a3ca3cea..759c6a6fa74 100644
--- a/drivers/tty/serial/mpsc.c
+++ b/drivers/tty/serial/mpsc.c
@@ -1458,7 +1458,7 @@ static void mpsc_set_termios(struct uart_port *port, struct ktermios *termios,
 		pi->port.read_status_mask |= SDMA_DESC_CMDSTAT_PE
 			| SDMA_DESC_CMDSTAT_FR;
 
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		pi->port.read_status_mask |= SDMA_DESC_CMDSTAT_BR;
 
 	/* Characters/events to ignore */
diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index 778e376f197..72000a6d5af 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -582,7 +582,7 @@ static void msm_set_termios(struct uart_port *port, struct ktermios *termios,
 	port->read_status_mask = 0;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= UART_SR_PAR_FRAME_ERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART_SR_RX_BREAK;
 
 	uart_update_timeout(port, termios->c_cflag, baud);
@@ -991,7 +991,7 @@ static const struct of_device_id msm_uartdm_table[] = {
 	{ }
 };
 
-static int __init msm_serial_probe(struct platform_device *pdev)
+static int msm_serial_probe(struct platform_device *pdev)
 {
 	struct msm_port *msm_port;
 	struct resource *resource;
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 4b5b3c2fe32..86de4477d98 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -604,7 +604,7 @@ static void mxs_auart_settermios(struct uart_port *u,
 
 	if (termios->c_iflag & INPCK)
 		u->read_status_mask |= AUART_STAT_PERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		u->read_status_mask |= AUART_STAT_BERR;
 
 	/*
diff --git a/drivers/tty/serial/netx-serial.c b/drivers/tty/serial/netx-serial.c
index 0a4dd70d29e..7a6745601d4 100644
--- a/drivers/tty/serial/netx-serial.c
+++ b/drivers/tty/serial/netx-serial.c
@@ -419,7 +419,7 @@ netx_set_termios(struct uart_port *port, struct ktermios *termios,
 	}
 
 	port->read_status_mask = 0;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= SR_BE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= SR_PE | SR_FE;
diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c
index e9d420ff393..f7ad5b90305 100644
--- a/drivers/tty/serial/pmac_zilog.c
+++ b/drivers/tty/serial/pmac_zilog.c
@@ -653,6 +653,8 @@ static void pmz_start_tx(struct uart_port *port)
 	} else {
 		struct circ_buf *xmit = &port->state->xmit;
 
+		if (uart_circ_empty(xmit))
+			goto out;
 		write_zsdata(uap, xmit->buf[xmit->tail]);
 		zssync(uap);
 		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
@@ -661,6 +663,7 @@ static void pmz_start_tx(struct uart_port *port)
 		if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
 			uart_write_wakeup(&uap->port);
 	}
+ out:
 	pmz_debug("pmz: start_tx() done.\n");
 }
 
@@ -1092,7 +1095,7 @@ static void pmz_convert_to_zs(struct uart_pmac_port *uap, unsigned int cflag,
 	uap->port.read_status_mask = Rx_OVR;
 	if (iflag & INPCK)
 		uap->port.read_status_mask |= CRC_ERR | PAR_ERR;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		uap->port.read_status_mask |= BRK_ABRT;
 
 	uap->port.ignore_status_mask = 0;
diff --git a/drivers/tty/serial/pnx8xxx_uart.c b/drivers/tty/serial/pnx8xxx_uart.c
index de6c05c6368..2ba24a45c97 100644
--- a/drivers/tty/serial/pnx8xxx_uart.c
+++ b/drivers/tty/serial/pnx8xxx_uart.c
@@ -477,7 +477,7 @@ pnx8xxx_set_termios(struct uart_port *port, struct ktermios *termios,
 		sport->port.read_status_mask |=
 			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXFE) |
 			FIFO_TO_SM(PNX8XXX_UART_FIFO_RXPAR);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		sport->port.read_status_mask |=
 			ISTAT_TO_SM(PNX8XXX_UART_INT_BREAK);
 
diff --git a/drivers/tty/serial/pxa.c b/drivers/tty/serial/pxa.c
index 9e7ee39f8b2..c638c53cd2b 100644
--- a/drivers/tty/serial/pxa.c
+++ b/drivers/tty/serial/pxa.c
@@ -492,7 +492,7 @@ serial_pxa_set_termios(struct uart_port *port, struct ktermios *termios,
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/samsung.c b/drivers/tty/serial/samsung.c
index 329337711bb..c1d3ebdf3b9 100644
--- a/drivers/tty/serial/samsung.c
+++ b/drivers/tty/serial/samsung.c
@@ -66,7 +66,7 @@ static void dbg(const char *fmt, ...)
 	char buff[256];
 
 	va_start(va, fmt);
-	vscnprintf(buff, sizeof(buf), fmt, va);
+	vscnprintf(buff, sizeof(buff), fmt, va);
 	va_end(va);
 
 	printascii(buff);
diff --git a/drivers/tty/serial/sb1250-duart.c b/drivers/tty/serial/sb1250-duart.c
index a7cdec2962d..771f361c47e 100644
--- a/drivers/tty/serial/sb1250-duart.c
+++ b/drivers/tty/serial/sb1250-duart.c
@@ -596,7 +596,7 @@ static void sbd_set_termios(struct uart_port *uport, struct ktermios *termios,
 	if (termios->c_iflag & INPCK)
 		uport->read_status_mask |= M_DUART_FRM_ERR |
 					   M_DUART_PARITY_ERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		uport->read_status_mask |= M_DUART_RCVD_BRK;
 
 	uport->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/sccnxp.c b/drivers/tty/serial/sccnxp.c
index 5443b46345e..e84b6a3bdd1 100644
--- a/drivers/tty/serial/sccnxp.c
+++ b/drivers/tty/serial/sccnxp.c
@@ -665,7 +665,7 @@ static void sccnxp_set_termios(struct uart_port *port,
 	port->read_status_mask = SR_OVR;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= SR_PE | SR_FE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= SR_BRK;
 
 	/* Set status ignore mask */
diff --git a/drivers/tty/serial/serial_ks8695.c b/drivers/tty/serial/serial_ks8695.c
index e1caa99e3d3..5c79bdab985 100644
--- a/drivers/tty/serial/serial_ks8695.c
+++ b/drivers/tty/serial/serial_ks8695.c
@@ -437,7 +437,7 @@ static void ks8695uart_set_termios(struct uart_port *port, struct ktermios *term
 	port->read_status_mask = URLS_URROE;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= (URLS_URFE | URLS_URPE);
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= URLS_URBI;
 
 	/*
diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c
index 60f49b9d7e3..ea8546092c7 100644
--- a/drivers/tty/serial/serial_txx9.c
+++ b/drivers/tty/serial/serial_txx9.c
@@ -697,7 +697,7 @@ serial_txx9_set_termios(struct uart_port *port, struct ktermios *termios,
 		TXX9_SIDISR_TDIS | TXX9_SIDISR_RDIS;
 	if (termios->c_iflag & INPCK)
 		up->port.read_status_mask |= TXX9_SIDISR_UFER | TXX9_SIDISR_UPER;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= TXX9_SIDISR_UBRK;
 
 	/*
diff --git a/drivers/tty/serial/sirfsoc_uart.c b/drivers/tty/serial/sirfsoc_uart.c
index 1f2be48c92c..9b4d71cff00 100644
--- a/drivers/tty/serial/sirfsoc_uart.c
+++ b/drivers/tty/serial/sirfsoc_uart.c
@@ -896,7 +896,7 @@ static void sirfsoc_uart_set_termios(struct uart_port *port,
 		if (termios->c_iflag & INPCK)
 			port->read_status_mask |= uint_en->sirfsoc_frm_err_en;
 	}
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 			port->read_status_mask |= uint_en->sirfsoc_rxd_brk_en;
 	if (sirfport->uart_reg->uart_type == SIRF_REAL_UART) {
 		if (termios->c_iflag & IGNPAR)
diff --git a/drivers/tty/serial/st-asc.c b/drivers/tty/serial/st-asc.c
index c7f61ac2713..f48b1cc07ee 100644
--- a/drivers/tty/serial/st-asc.c
+++ b/drivers/tty/serial/st-asc.c
@@ -547,7 +547,7 @@ static void asc_set_termios(struct uart_port *port, struct ktermios *termios,
 	ascport->port.read_status_mask = ASC_RXBUF_DUMMY_OE;
 	if (termios->c_iflag & INPCK)
 		ascport->port.read_status_mask |= ASC_RXBUF_FE | ASC_RXBUF_PE;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		ascport->port.read_status_mask |= ASC_RXBUF_DUMMY_BE;
 
 	/*
diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c
index 5faa8e905e9..2f57df9a71d 100644
--- a/drivers/tty/serial/sunsab.c
+++ b/drivers/tty/serial/sunsab.c
@@ -427,6 +427,9 @@ static void sunsab_start_tx(struct uart_port *port)
 	struct circ_buf *xmit = &up->port.state->xmit;
 	int i;
 
+	if (uart_circ_empty(xmit))
+		return;
+
 	up->interrupt_mask1 &= ~(SAB82532_IMR1_ALLS|SAB82532_IMR1_XPR);
 	writeb(up->interrupt_mask1, &up->regs->w.imr1);
 	
@@ -719,7 +722,7 @@ static void sunsab_convert_to_sab(struct uart_sunsab_port *up, unsigned int cfla
 	if (iflag & INPCK)
 		up->port.read_status_mask |= (SAB82532_ISR0_PERR |
 					      SAB82532_ISR0_FERR);
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= (SAB82532_ISR1_BRK << 8);
 
 	/*
diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c
index 9a0f24f8372..5326ae195e5 100644
--- a/drivers/tty/serial/sunsu.c
+++ b/drivers/tty/serial/sunsu.c
@@ -834,7 +834,7 @@ sunsu_change_speed(struct uart_port *port, unsigned int cflag,
 	up->port.read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR;
 	if (iflag & INPCK)
 		up->port.read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= UART_LSR_BI;
 
 	/*
diff --git a/drivers/tty/serial/sunzilog.c b/drivers/tty/serial/sunzilog.c
index a2c40ed287d..02df3940b95 100644
--- a/drivers/tty/serial/sunzilog.c
+++ b/drivers/tty/serial/sunzilog.c
@@ -703,6 +703,8 @@ static void sunzilog_start_tx(struct uart_port *port)
 	} else {
 		struct circ_buf *xmit = &port->state->xmit;
 
+		if (uart_circ_empty(xmit))
+			return;
 		writeb(xmit->buf[xmit->tail], &channel->data);
 		ZSDELAY();
 		ZS_WSYNC(channel);
@@ -915,7 +917,7 @@ sunzilog_convert_to_zs(struct uart_sunzilog_port *up, unsigned int cflag,
 	up->port.read_status_mask = Rx_OVR;
 	if (iflag & INPCK)
 		up->port.read_status_mask |= CRC_ERR | PAR_ERR;
-	if (iflag & (BRKINT | PARMRK))
+	if (iflag & (IGNBRK | BRKINT | PARMRK))
 		up->port.read_status_mask |= BRK_ABRT;
 
 	up->port.ignore_status_mask = 0;
diff --git a/drivers/tty/serial/ucc_uart.c b/drivers/tty/serial/ucc_uart.c
index d569ca58bab..1c52074c38d 100644
--- a/drivers/tty/serial/ucc_uart.c
+++ b/drivers/tty/serial/ucc_uart.c
@@ -936,7 +936,7 @@ static void qe_uart_set_termios(struct uart_port *port,
 	port->read_status_mask = BD_SC_EMPTY | BD_SC_OV;
 	if (termios->c_iflag & INPCK)
 		port->read_status_mask |= BD_SC_FR | BD_SC_PR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= BD_SC_BR;
 
 	/*
diff --git a/drivers/tty/serial/vr41xx_siu.c b/drivers/tty/serial/vr41xx_siu.c
index a63c14bc9a2..db0c8a4ab03 100644
--- a/drivers/tty/serial/vr41xx_siu.c
+++ b/drivers/tty/serial/vr41xx_siu.c
@@ -559,7 +559,7 @@ static void siu_set_termios(struct uart_port *port, struct ktermios *new,
 	port->read_status_mask = UART_LSR_THRE | UART_LSR_OE | UART_LSR_DR;
 	if (c_iflag & INPCK)
 		port->read_status_mask |= UART_LSR_FE | UART_LSR_PE;
-	if (c_iflag & (BRKINT | PARMRK))
+	if (c_iflag & (IGNBRK | BRKINT | PARMRK))
 		port->read_status_mask |= UART_LSR_BI;
 
 	port->ignore_status_mask = 0;
diff --git a/drivers/tty/serial/zs.c b/drivers/tty/serial/zs.c
index 6a169877109..2b65bb7ffb8 100644
--- a/drivers/tty/serial/zs.c
+++ b/drivers/tty/serial/zs.c
@@ -923,7 +923,7 @@ static void zs_set_termios(struct uart_port *uport, struct ktermios *termios,
 	uport->read_status_mask = Rx_OVR;
 	if (termios->c_iflag & INPCK)
 		uport->read_status_mask |= FRM_ERR | PAR_ERR;
-	if (termios->c_iflag & (BRKINT | PARMRK))
+	if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
 		uport->read_status_mask |= Rx_BRK;
 
 	uport->ignore_status_mask = 0;
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 5e0f6ff2e2f..b33b00b386d 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -3226,8 +3226,7 @@ int do_unbind_con_driver(const struct consw *csw, int first, int last, int deflt
 	for (i = 0; i < MAX_NR_CON_DRIVER; i++) {
 		con_back = &registered_con_driver[i];
 
-		if (con_back->con &&
-		    !(con_back->flag & CON_DRIVER_FLAG_MODULE)) {
+		if (con_back->con && con_back->con != csw) {
 			defcsw = con_back->con;
 			retval = 0;
 			break;
@@ -3332,6 +3331,7 @@ static int vt_unbind(struct con_driver *con)
 {
 	const struct consw *csw = NULL;
 	int i, more = 1, first = -1, last = -1, deflt = 0;
+	int ret;
 
  	if (!con->con || !(con->flag & CON_DRIVER_FLAG_MODULE) ||
 	    con_is_graphics(con->con, con->first, con->last))
@@ -3357,8 +3357,10 @@ static int vt_unbind(struct con_driver *con)
 
 		if (first != -1) {
 			console_lock();
-			do_unbind_con_driver(csw, first, last, deflt);
+			ret = do_unbind_con_driver(csw, first, last, deflt);
 			console_unlock();
+			if (ret != 0)
+				return ret;
 		}
 
 		first = -1;
@@ -3645,17 +3647,20 @@ err:
  */
 int do_unregister_con_driver(const struct consw *csw)
 {
-	int i, retval = -ENODEV;
+	int i;
 
 	/* cannot unregister a bound driver */
 	if (con_is_bound(csw))
-		goto err;
+		return -EBUSY;
+
+	if (csw == conswitchp)
+		return -EINVAL;
 
 	for (i = 0; i < MAX_NR_CON_DRIVER; i++) {
 		struct con_driver *con_driver = &registered_con_driver[i];
 
 		if (con_driver->con == csw &&
-		    con_driver->flag & CON_DRIVER_FLAG_MODULE) {
+		    con_driver->flag & CON_DRIVER_FLAG_INIT) {
 			vtconsole_deinit_device(con_driver);
 			device_destroy(vtconsole_class,
 				       MKDEV(0, con_driver->node));
@@ -3666,12 +3671,11 @@ int do_unregister_con_driver(const struct consw *csw)
 			con_driver->flag = 0;
 			con_driver->first = 0;
 			con_driver->last = 0;
-			retval = 0;
-			break;
+			return 0;
 		}
 	}
-err:
-	return retval;
+
+	return -ENODEV;
 }
 EXPORT_SYMBOL_GPL(do_unregister_con_driver);
 
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index e371f5af11f..a673e5b6a2e 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -655,7 +655,7 @@ static int uio_mmap_physical(struct vm_area_struct *vma)
 
 	if (mem->addr & ~PAGE_MASK)
 		return -ENODEV;
-	if (vma->vm_end - vma->vm_start > PAGE_ALIGN(mem->size))
+	if (vma->vm_end - vma->vm_start > mem->size)
 		return -EINVAL;
 
 	vma->vm_ops = &uio_physical_vm_ops;
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 69425b3cb6b..b8125aa64ad 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1169,8 +1169,8 @@ static int ep_enable(struct usb_ep *ep,
 
 	if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
 		cap |= QH_IOS;
-	if (hwep->num)
-		cap |= QH_ZLT;
+
+	cap |= QH_ZLT;
 	cap |= (hwep->ep.maxpacket << __ffs(QH_MAX_PKT)) & QH_MAX_PKT;
 	/*
 	 * For ISO-TX, we set mult at QH as the largest value, and use
@@ -1321,6 +1321,7 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
 	struct ci_hw_ep  *hwep  = container_of(ep,  struct ci_hw_ep, ep);
 	struct ci_hw_req *hwreq = container_of(req, struct ci_hw_req, req);
 	unsigned long flags;
+	struct td_node *node, *tmpnode;
 
 	if (ep == NULL || req == NULL || hwreq->req.status != -EALREADY ||
 		hwep->ep.desc == NULL || list_empty(&hwreq->queue) ||
@@ -1331,6 +1332,12 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
 
 	hw_ep_flush(hwep->ci, hwep->num, hwep->dir);
 
+	list_for_each_entry_safe(node, tmpnode, &hwreq->tds, td) {
+		dma_pool_free(hwep->td_pool, node->ptr, node->dma);
+		list_del(&node->td);
+		kfree(node);
+	}
+
 	/* pop request */
 	list_del_init(&hwreq->queue);
 
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 879b66e1337..0e950ad8cb2 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -889,6 +889,25 @@ static int hub_usb3_port_disable(struct usb_hub *hub, int port1)
 	if (!hub_is_superspeed(hub->hdev))
 		return -EINVAL;
 
+	ret = hub_port_status(hub, port1, &portstatus, &portchange);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * USB controller Advanced Micro Devices, Inc. [AMD] FCH USB XHCI
+	 * Controller [1022:7814] will have spurious result making the following
+	 * usb 3.0 device hotplugging route to the 2.0 root hub and recognized
+	 * as high-speed device if we set the usb 3.0 port link state to
+	 * Disabled. Since it's already in USB_SS_PORT_LS_RX_DETECT state, we
+	 * check the state here to avoid the bug.
+	 */
+	if ((portstatus & USB_PORT_STAT_LINK_STATE) ==
+				USB_SS_PORT_LS_RX_DETECT) {
+		dev_dbg(&hub->ports[port1 - 1]->dev,
+			 "Not disabling port; link state is RxDetect\n");
+		return ret;
+	}
+
 	ret = hub_set_port_link_state(hub, port1, USB_SS_PORT_LS_SS_DISABLED);
 	if (ret)
 		return ret;
@@ -1526,18 +1545,6 @@ static int hub_configure(struct usb_hub *hub,
 		dev_dbg(hub_dev, "%umA bus power budget for each child\n",
 				hub->mA_per_port);
 
-	/* Update the HCD's internal representation of this hub before khubd
-	 * starts getting port status changes for devices under the hub.
-	 */
-	if (hcd->driver->update_hub_device) {
-		ret = hcd->driver->update_hub_device(hcd, hdev,
-				&hub->tt, GFP_KERNEL);
-		if (ret < 0) {
-			message = "can't update HCD hub info";
-			goto fail;
-		}
-	}
-
 	ret = hub_hub_status(hub, &hubstatus, &hubchange);
 	if (ret < 0) {
 		message = "can't get hub status";
@@ -1589,10 +1596,28 @@ static int hub_configure(struct usb_hub *hub,
 		}
 	}
 	hdev->maxchild = i;
+	for (i = 0; i < hdev->maxchild; i++) {
+		struct usb_port *port_dev = hub->ports[i];
+
+		pm_runtime_put(&port_dev->dev);
+	}
+
 	mutex_unlock(&usb_port_peer_mutex);
 	if (ret < 0)
 		goto fail;
 
+	/* Update the HCD's internal representation of this hub before khubd
+	 * starts getting port status changes for devices under the hub.
+	 */
+	if (hcd->driver->update_hub_device) {
+		ret = hcd->driver->update_hub_device(hcd, hdev,
+				&hub->tt, GFP_KERNEL);
+		if (ret < 0) {
+			message = "can't update HCD hub info";
+			goto fail;
+		}
+	}
+
 	usb_hub_adjust_deviceremovable(hdev, hub->descriptor);
 
 	hub_activate(hub, HUB_INIT);
@@ -3458,7 +3483,8 @@ static int hub_suspend(struct usb_interface *intf, pm_message_t msg)
 		struct usb_device *udev = port_dev->child;
 
 		if (udev && udev->can_submit) {
-			dev_warn(&port_dev->dev, "not suspended yet\n");
+			dev_warn(&port_dev->dev, "device %s not suspended yet\n",
+					dev_name(&udev->dev));
 			if (PMSG_IS_AUTO(msg))
 				return -EBUSY;
 		}
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index 0a7cdc0ef0a..326308e5396 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -84,6 +84,7 @@ struct usb_hub {
  * @dev: generic device interface
  * @port_owner: port's owner
  * @peer: related usb2 and usb3 ports (share the same connector)
+ * @req: default pm qos request for hubs without port power control
  * @connect_type: port's connect type
  * @location: opaque representation of platform connector location
  * @status_lock: synchronize port_event() vs usb_port_{suspend|resume}
@@ -95,6 +96,7 @@ struct usb_port {
 	struct device dev;
 	struct usb_dev_state *port_owner;
 	struct usb_port *peer;
+	struct dev_pm_qos_request *req;
 	enum usb_port_connect_type connect_type;
 	usb_port_location_t location;
 	struct mutex status_lock;
diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c
index 62036faf56c..fe1b6d0967e 100644
--- a/drivers/usb/core/port.c
+++ b/drivers/usb/core/port.c
@@ -21,6 +21,8 @@
 
 #include "hub.h"
 
+static int usb_port_block_power_off;
+
 static const struct attribute_group *port_dev_group[];
 
 static ssize_t connect_type_show(struct device *dev,
@@ -66,6 +68,7 @@ static void usb_port_device_release(struct device *dev)
 {
 	struct usb_port *port_dev = to_usb_port(dev);
 
+	kfree(port_dev->req);
 	kfree(port_dev);
 }
 
@@ -142,6 +145,9 @@ static int usb_port_runtime_suspend(struct device *dev)
 			== PM_QOS_FLAGS_ALL)
 		return -EAGAIN;
 
+	if (usb_port_block_power_off)
+		return -EBUSY;
+
 	usb_autopm_get_interface(intf);
 	retval = usb_hub_set_port_power(hdev, hub, port1, false);
 	usb_clear_port_feature(hdev, port1, USB_PORT_FEAT_C_CONNECTION);
@@ -190,11 +196,19 @@ static int link_peers(struct usb_port *left, struct usb_port *right)
 	if (left->peer || right->peer) {
 		struct usb_port *lpeer = left->peer;
 		struct usb_port *rpeer = right->peer;
-
-		WARN(1, "failed to peer %s and %s (%s -> %p) (%s -> %p)\n",
-			dev_name(&left->dev), dev_name(&right->dev),
-			dev_name(&left->dev), lpeer,
-			dev_name(&right->dev), rpeer);
+		char *method;
+
+		if (left->location && left->location == right->location)
+			method = "location";
+		else
+			method = "default";
+
+		pr_warn("usb: failed to peer %s and %s by %s (%s:%s) (%s:%s)\n",
+			dev_name(&left->dev), dev_name(&right->dev), method,
+			dev_name(&left->dev),
+			lpeer ? dev_name(&lpeer->dev) : "none",
+			dev_name(&right->dev),
+			rpeer ? dev_name(&rpeer->dev) : "none");
 		return -EBUSY;
 	}
 
@@ -251,6 +265,7 @@ static void link_peers_report(struct usb_port *left, struct usb_port *right)
 		dev_warn(&left->dev, "failed to peer to %s (%d)\n",
 				dev_name(&right->dev), rc);
 		pr_warn_once("usb: port power management may be unreliable\n");
+		usb_port_block_power_off = 1;
 	}
 }
 
@@ -386,9 +401,13 @@ int usb_hub_create_port_device(struct usb_hub *hub, int port1)
 	int retval;
 
 	port_dev = kzalloc(sizeof(*port_dev), GFP_KERNEL);
-	if (!port_dev) {
-		retval = -ENOMEM;
-		goto exit;
+	if (!port_dev)
+		return -ENOMEM;
+
+	port_dev->req = kzalloc(sizeof(*(port_dev->req)), GFP_KERNEL);
+	if (!port_dev->req) {
+		kfree(port_dev);
+		return -ENOMEM;
 	}
 
 	hub->ports[port1 - 1] = port_dev;
@@ -404,31 +423,53 @@ int usb_hub_create_port_device(struct usb_hub *hub, int port1)
 			port1);
 	mutex_init(&port_dev->status_lock);
 	retval = device_register(&port_dev->dev);
-	if (retval)
-		goto error_register;
+	if (retval) {
+		put_device(&port_dev->dev);
+		return retval;
+	}
+
+	/* Set default policy of port-poweroff disabled. */
+	retval = dev_pm_qos_add_request(&port_dev->dev, port_dev->req,
+			DEV_PM_QOS_FLAGS, PM_QOS_FLAG_NO_POWER_OFF);
+	if (retval < 0) {
+		device_unregister(&port_dev->dev);
+		return retval;
+	}
 
 	find_and_link_peer(hub, port1);
 
+	/*
+	 * Enable runtime pm and hold a refernce that hub_configure()
+	 * will drop once the PM_QOS_NO_POWER_OFF flag state has been set
+	 * and the hub has been fully registered (hdev->maxchild set).
+	 */
 	pm_runtime_set_active(&port_dev->dev);
+	pm_runtime_get_noresume(&port_dev->dev);
+	pm_runtime_enable(&port_dev->dev);
+	device_enable_async_suspend(&port_dev->dev);
 
 	/*
-	 * Do not enable port runtime pm if the hub does not support
-	 * power switching.  Also, userspace must have final say of
-	 * whether a port is permitted to power-off.  Do not enable
-	 * runtime pm if we fail to expose pm_qos_no_power_off.
+	 * Keep hidden the ability to enable port-poweroff if the hub
+	 * does not support power switching.
 	 */
-	if (hub_is_port_power_switchable(hub)
-			&& dev_pm_qos_expose_flags(&port_dev->dev,
-			PM_QOS_FLAG_NO_POWER_OFF) == 0)
-		pm_runtime_enable(&port_dev->dev);
+	if (!hub_is_port_power_switchable(hub))
+		return 0;
 
-	device_enable_async_suspend(&port_dev->dev);
-	return 0;
+	/* Attempt to let userspace take over the policy. */
+	retval = dev_pm_qos_expose_flags(&port_dev->dev,
+			PM_QOS_FLAG_NO_POWER_OFF);
+	if (retval < 0) {
+		dev_warn(&port_dev->dev, "failed to expose pm_qos_no_poweroff\n");
+		return 0;
+	}
 
-error_register:
-	put_device(&port_dev->dev);
-exit:
-	return retval;
+	/* Userspace owns the policy, drop the kernel 'no_poweroff' request. */
+	retval = dev_pm_qos_remove_request(port_dev->req);
+	if (retval >= 0) {
+		kfree(port_dev->req);
+		port_dev->req = NULL;
+	}
+	return 0;
 }
 
 void usb_hub_remove_port_device(struct usb_hub *hub, int port1)
diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig
index 8eb996e4f05..261c3b42822 100644
--- a/drivers/usb/dwc3/Kconfig
+++ b/drivers/usb/dwc3/Kconfig
@@ -45,6 +45,7 @@ comment "Platform Glue Driver Support"
 config USB_DWC3_OMAP
 	tristate "Texas Instruments OMAP5 and similar Platforms"
 	depends on EXTCON && (ARCH_OMAP2PLUS || COMPILE_TEST)
+	depends on OF
 	default USB_DWC3
 	help
 	  Some platforms from Texas Instruments like OMAP5, DRA7xxx and
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index 4af4c356765..07a736acd0f 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -322,7 +322,7 @@ static int dwc3_omap_remove_core(struct device *dev, void *c)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 
-	platform_device_unregister(pdev);
+	of_device_unregister(pdev);
 
 	return 0;
 }
@@ -599,7 +599,7 @@ static int dwc3_omap_prepare(struct device *dev)
 {
 	struct dwc3_omap	*omap = dev_get_drvdata(dev);
 
-	dwc3_omap_disable_irqs(omap);
+	dwc3_omap_write_irqmisc_set(omap, 0x00);
 
 	return 0;
 }
@@ -607,8 +607,19 @@ static int dwc3_omap_prepare(struct device *dev)
 static void dwc3_omap_complete(struct device *dev)
 {
 	struct dwc3_omap	*omap = dev_get_drvdata(dev);
+	u32			reg;
 
-	dwc3_omap_enable_irqs(omap);
+	reg = (USBOTGSS_IRQMISC_OEVT |
+			USBOTGSS_IRQMISC_DRVVBUS_RISE |
+			USBOTGSS_IRQMISC_CHRGVBUS_RISE |
+			USBOTGSS_IRQMISC_DISCHRGVBUS_RISE |
+			USBOTGSS_IRQMISC_IDPULLUP_RISE |
+			USBOTGSS_IRQMISC_DRVVBUS_FALL |
+			USBOTGSS_IRQMISC_CHRGVBUS_FALL |
+			USBOTGSS_IRQMISC_DISCHRGVBUS_FALL |
+			USBOTGSS_IRQMISC_IDPULLUP_FALL);
+
+	dwc3_omap_write_irqmisc_set(omap, reg);
 }
 
 static int dwc3_omap_suspend(struct device *dev)
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 9d64dd02c57..dab7927d100 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -828,10 +828,6 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
 			length, last ? " last" : "",
 			chain ? " chain" : "");
 
-	/* Skip the LINK-TRB on ISOC */
-	if (((dep->free_slot & DWC3_TRB_MASK) == DWC3_TRB_NUM - 1) &&
-			usb_endpoint_xfer_isoc(dep->endpoint.desc))
-		dep->free_slot++;
 
 	trb = &dep->trb_pool[dep->free_slot & DWC3_TRB_MASK];
 
@@ -843,6 +839,10 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
 	}
 
 	dep->free_slot++;
+	/* Skip the LINK-TRB on ISOC */
+	if (((dep->free_slot & DWC3_TRB_MASK) == DWC3_TRB_NUM - 1) &&
+			usb_endpoint_xfer_isoc(dep->endpoint.desc))
+		dep->free_slot++;
 
 	trb->size = DWC3_TRB_SIZE_LENGTH(length);
 	trb->bpl = lower_32_bits(dma);
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 2ddcd635ca2..97142146eea 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -1145,15 +1145,15 @@ static struct configfs_item_operations interf_item_ops = {
 	.store_attribute	= usb_os_desc_attr_store,
 };
 
-static ssize_t rndis_grp_compatible_id_show(struct usb_os_desc *desc,
-					    char *page)
+static ssize_t interf_grp_compatible_id_show(struct usb_os_desc *desc,
+					     char *page)
 {
 	memcpy(page, desc->ext_compat_id, 8);
 	return 8;
 }
 
-static ssize_t rndis_grp_compatible_id_store(struct usb_os_desc *desc,
-					     const char *page, size_t len)
+static ssize_t interf_grp_compatible_id_store(struct usb_os_desc *desc,
+					      const char *page, size_t len)
 {
 	int l;
 
@@ -1171,20 +1171,20 @@ static ssize_t rndis_grp_compatible_id_store(struct usb_os_desc *desc,
 	return len;
 }
 
-static struct usb_os_desc_attribute rndis_grp_attr_compatible_id =
+static struct usb_os_desc_attribute interf_grp_attr_compatible_id =
 	__CONFIGFS_ATTR(compatible_id, S_IRUGO | S_IWUSR,
-			rndis_grp_compatible_id_show,
-			rndis_grp_compatible_id_store);
+			interf_grp_compatible_id_show,
+			interf_grp_compatible_id_store);
 
-static ssize_t rndis_grp_sub_compatible_id_show(struct usb_os_desc *desc,
-						char *page)
+static ssize_t interf_grp_sub_compatible_id_show(struct usb_os_desc *desc,
+						 char *page)
 {
 	memcpy(page, desc->ext_compat_id + 8, 8);
 	return 8;
 }
 
-static ssize_t rndis_grp_sub_compatible_id_store(struct usb_os_desc *desc,
-						 const char *page, size_t len)
+static ssize_t interf_grp_sub_compatible_id_store(struct usb_os_desc *desc,
+						  const char *page, size_t len)
 {
 	int l;
 
@@ -1202,20 +1202,21 @@ static ssize_t rndis_grp_sub_compatible_id_store(struct usb_os_desc *desc,
 	return len;
 }
 
-static struct usb_os_desc_attribute rndis_grp_attr_sub_compatible_id =
+static struct usb_os_desc_attribute interf_grp_attr_sub_compatible_id =
 	__CONFIGFS_ATTR(sub_compatible_id, S_IRUGO | S_IWUSR,
-			rndis_grp_sub_compatible_id_show,
-			rndis_grp_sub_compatible_id_store);
+			interf_grp_sub_compatible_id_show,
+			interf_grp_sub_compatible_id_store);
 
 static struct configfs_attribute *interf_grp_attrs[] = {
-	&rndis_grp_attr_compatible_id.attr,
-	&rndis_grp_attr_sub_compatible_id.attr,
+	&interf_grp_attr_compatible_id.attr,
+	&interf_grp_attr_sub_compatible_id.attr,
 	NULL
 };
 
 int usb_os_desc_prepare_interf_dir(struct config_group *parent,
 				   int n_interf,
 				   struct usb_os_desc **desc,
+				   char **names,
 				   struct module *owner)
 {
 	struct config_group **f_default_groups, *os_desc_group,
@@ -1257,8 +1258,8 @@ int usb_os_desc_prepare_interf_dir(struct config_group *parent,
 		d = desc[n_interf];
 		d->owner = owner;
 		config_group_init_type_name(&d->group, "", interface_type);
-		config_item_set_name(&d->group.cg_item, "interface.%d",
-				     n_interf);
+		config_item_set_name(&d->group.cg_item, "interface.%s",
+				     names[n_interf]);
 		interface_groups[n_interf] = &d->group;
 	}
 
diff --git a/drivers/usb/gadget/configfs.h b/drivers/usb/gadget/configfs.h
index a14ac792c69..36c468c4f5e 100644
--- a/drivers/usb/gadget/configfs.h
+++ b/drivers/usb/gadget/configfs.h
@@ -8,6 +8,7 @@ void unregister_gadget_item(struct config_item *item);
 int usb_os_desc_prepare_interf_dir(struct config_group *parent,
 				   int n_interf,
 				   struct usb_os_desc **desc,
+				   char **names,
 				   struct module *owner);
 
 static inline struct usb_os_desc *to_usb_os_desc(struct config_item *item)
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index 74202d67f91..8598c27c7d4 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -1483,11 +1483,13 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev)
 	ffs->ep0req->context = ffs;
 
 	lang = ffs->stringtabs;
-	for (lang = ffs->stringtabs; *lang; ++lang) {
-		struct usb_string *str = (*lang)->strings;
-		int id = first_id;
-		for (; str->s; ++id, ++str)
-			str->id = id;
+	if (lang) {
+		for (; *lang; ++lang) {
+			struct usb_string *str = (*lang)->strings;
+			int id = first_id;
+			for (; str->s; ++id, ++str)
+				str->id = id;
+		}
 	}
 
 	ffs->gadget = cdev->gadget;
diff --git a/drivers/usb/gadget/f_rndis.c b/drivers/usb/gadget/f_rndis.c
index eed3ad87804..9c41e9515b8 100644
--- a/drivers/usb/gadget/f_rndis.c
+++ b/drivers/usb/gadget/f_rndis.c
@@ -687,7 +687,7 @@ rndis_bind(struct usb_configuration *c, struct usb_function *f)
 		f->os_desc_table = kzalloc(sizeof(*f->os_desc_table),
 					   GFP_KERNEL);
 		if (!f->os_desc_table)
-			return PTR_ERR(f->os_desc_table);
+			return -ENOMEM;
 		f->os_desc_n = 1;
 		f->os_desc_table[0].os_desc = &rndis_opts->rndis_os_desc;
 	}
@@ -905,6 +905,7 @@ static struct usb_function_instance *rndis_alloc_inst(void)
 {
 	struct f_rndis_opts *opts;
 	struct usb_os_desc *descs[1];
+	char *names[1];
 
 	opts = kzalloc(sizeof(*opts), GFP_KERNEL);
 	if (!opts)
@@ -922,8 +923,9 @@ static struct usb_function_instance *rndis_alloc_inst(void)
 	INIT_LIST_HEAD(&opts->rndis_os_desc.ext_prop);
 
 	descs[0] = &opts->rndis_os_desc;
+	names[0] = "rndis";
 	usb_os_desc_prepare_interf_dir(&opts->func_inst.group, 1, descs,
-				       THIS_MODULE);
+				       names, THIS_MODULE);
 	config_group_init_type_name(&opts->func_inst.group, "",
 				    &rndis_func_type);
 
diff --git a/drivers/usb/gadget/gr_udc.c b/drivers/usb/gadget/gr_udc.c
index 99a37ed03e2..c7004ee89c9 100644
--- a/drivers/usb/gadget/gr_udc.c
+++ b/drivers/usb/gadget/gr_udc.c
@@ -1532,8 +1532,9 @@ static int gr_ep_enable(struct usb_ep *_ep,
 			"%s mode: multiple trans./microframe not valid\n",
 			(mode == 2 ? "Bulk" : "Control"));
 		return -EINVAL;
-	} else if (nt == 0x11) {
-		dev_err(dev->dev, "Invalid value for trans./microframe\n");
+	} else if (nt == 0x3) {
+		dev_err(dev->dev,
+			"Invalid value 0x3 for additional trans./microframe\n");
 		return -EINVAL;
 	} else if ((nt + 1) * max > buffer_size) {
 		dev_err(dev->dev, "Hw buffer size %d < max payload %d * %d\n",
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index ee6c16416c3..2e4ce770490 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -1264,8 +1264,13 @@ dev_release (struct inode *inode, struct file *fd)
 
 	kfree (dev->buf);
 	dev->buf = NULL;
-	put_dev (dev);
 
+	/* other endpoints were all decoupled from this device */
+	spin_lock_irq(&dev->lock);
+	dev->state = STATE_DEV_DISABLED;
+	spin_unlock_irq(&dev->lock);
+
+	put_dev (dev);
 	return 0;
 }
 
diff --git a/drivers/usb/gadget/storage_common.c b/drivers/usb/gadget/storage_common.c
index ff205a7bc55..648f9e489b3 100644
--- a/drivers/usb/gadget/storage_common.c
+++ b/drivers/usb/gadget/storage_common.c
@@ -220,11 +220,11 @@ int fsg_lun_open(struct fsg_lun *curlun, const char *filename)
 	 * If we can't read the file, it's no good.
 	 * If we can't write the file, use it read-only.
 	 */
-	if (!(filp->f_op->read || filp->f_op->aio_read)) {
+	if (!(filp->f_mode & FMODE_CAN_READ)) {
 		LINFO(curlun, "file not readable: %s\n", filename);
 		goto out;
 	}
-	if (!(filp->f_op->write || filp->f_op->aio_write))
+	if (!(filp->f_mode & FMODE_CAN_WRITE))
 		ro = 1;
 
 	size = i_size_read(inode->i_mapping->host);
diff --git a/drivers/usb/gadget/u_ether.c b/drivers/usb/gadget/u_ether.c
index fe0880d0873..97b027724ee 100644
--- a/drivers/usb/gadget/u_ether.c
+++ b/drivers/usb/gadget/u_ether.c
@@ -793,7 +793,7 @@ struct eth_dev *gether_setup_name(struct usb_gadget *g,
 
 	net->netdev_ops = &eth_netdev_ops;
 
-	SET_ETHTOOL_OPS(net, &ops);
+	net->ethtool_ops = &ops;
 
 	dev->gadget = g;
 	SET_NETDEV_DEV(net, &g->dev);
@@ -850,7 +850,7 @@ struct net_device *gether_setup_name_default(const char *netname)
 
 	net->netdev_ops = &eth_netdev_ops;
 
-	SET_ETHTOOL_OPS(net, &ops);
+	net->ethtool_ops = &ops;
 	SET_NETDEV_DEVTYPE(net, &gadget_type);
 
 	return net;
@@ -1120,7 +1120,10 @@ void gether_disconnect(struct gether *link)
 
 	DBG(dev, "%s\n", __func__);
 
+	netif_tx_lock(dev->net);
 	netif_stop_queue(dev->net);
+	netif_tx_unlock(dev->net);
+
 	netif_carrier_off(dev->net);
 
 	/* disable endpoints, forcing (synchronous) completion
diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index 61b7817bd66..03314f861be 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -176,7 +176,7 @@ config USB_EHCI_HCD_AT91
 
 config USB_EHCI_MSM
 	tristate "Support for Qualcomm QSD/MSM on-chip EHCI USB controller"
-	depends on ARCH_MSM
+	depends on ARCH_MSM || ARCH_QCOM
 	select USB_EHCI_ROOT_HUB_TT
 	---help---
 	  Enables support for the USB Host controller present on the
diff --git a/drivers/usb/host/ehci-pmcmsp.c b/drivers/usb/host/ehci-pmcmsp.c
index af3974a5e7c..7d75465d97c 100644
--- a/drivers/usb/host/ehci-pmcmsp.c
+++ b/drivers/usb/host/ehci-pmcmsp.c
@@ -68,9 +68,6 @@ static void usb_hcd_tdi_set_mode(struct ehci_hcd *ehci)
 
 	/* set TWI GPIO USB_HOST_DEV pin high */
 	gpio_direction_output(MSP_PIN_USB0_HOST_DEV, 1);
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-	gpio_direction_output(MSP_PIN_USB1_HOST_DEV, 1);
-#endif
 }
 
 /* called during probe() after chip reset completes */
@@ -248,33 +245,6 @@ void usb_hcd_msp_remove(struct usb_hcd *hcd, struct platform_device *dev)
 	usb_put_hcd(hcd);
 }
 
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-/*
- * Wrapper around the main ehci_irq.  Since both USB host controllers are
- * sharing the same IRQ, need to first determine whether we're the intended
- * recipient of this interrupt.
- */
-static irqreturn_t ehci_msp_irq(struct usb_hcd *hcd)
-{
-	u32 int_src;
-	struct device *dev = hcd->self.controller;
-	struct platform_device *pdev;
-	struct mspusb_device *mdev;
-	struct ehci_hcd	*ehci = hcd_to_ehci(hcd);
-	/* need to reverse-map a couple of containers to get our device */
-	pdev = to_platform_device(dev);
-	mdev = to_mspusb_device(pdev);
-
-	/* Check to see if this interrupt is for this host controller */
-	int_src = ehci_readl(ehci, &mdev->mab_regs->int_stat);
-	if (int_src & (1 << pdev->id))
-		return ehci_irq(hcd);
-
-	/* Not for this device */
-	return IRQ_NONE;
-}
-#endif /* DUAL_USB */
-
 static const struct hc_driver ehci_msp_hc_driver = {
 	.description =		hcd_name,
 	.product_desc =		"PMC MSP EHCI",
@@ -283,11 +253,7 @@ static const struct hc_driver ehci_msp_hc_driver = {
 	/*
 	 * generic hardware linkage
 	 */
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-	.irq =			ehci_msp_irq,
-#else
 	.irq =			ehci_irq,
-#endif
 	.flags =		HCD_MEMORY | HCD_USB2 | HCD_BH,
 
 	/*
@@ -334,9 +300,6 @@ static int ehci_hcd_msp_drv_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	gpio_request(MSP_PIN_USB0_HOST_DEV, "USB0_HOST_DEV_GPIO");
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-	gpio_request(MSP_PIN_USB1_HOST_DEV, "USB1_HOST_DEV_GPIO");
-#endif
 
 	ret = usb_hcd_msp_probe(&ehci_msp_hc_driver, pdev);
 
@@ -351,9 +314,6 @@ static int ehci_hcd_msp_drv_remove(struct platform_device *pdev)
 
 	/* free TWI GPIO USB_HOST_DEV pin */
 	gpio_free(MSP_PIN_USB0_HOST_DEV);
-#ifdef CONFIG_MSP_HAS_DUAL_USB
-	gpio_free(MSP_PIN_USB1_HOST_DEV);
-#endif
 
 	return 0;
 }
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 4a6d3dd6857..2f3acebb577 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -656,6 +656,14 @@ static const struct dmi_system_id ehci_dmi_nohandoff_table[] = {
 			DMI_MATCH(DMI_BIOS_VERSION, "Lucid-"),
 		},
 	},
+	{
+		/* HASEE E200 */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HASEE"),
+			DMI_MATCH(DMI_BOARD_NAME, "E210"),
+			DMI_MATCH(DMI_BIOS_VERSION, "6.00"),
+		},
+	},
 	{ }
 };
 
@@ -665,9 +673,14 @@ static void ehci_bios_handoff(struct pci_dev *pdev,
 {
 	int try_handoff = 1, tried_handoff = 0;
 
-	/* The Pegatron Lucid tablet sporadically waits for 98 seconds trying
-	 * the handoff on its unused controller.  Skip it. */
-	if (pdev->vendor == 0x8086 && pdev->device == 0x283a) {
+	/*
+	 * The Pegatron Lucid tablet sporadically waits for 98 seconds trying
+	 * the handoff on its unused controller.  Skip it.
+	 *
+	 * The HASEE E200 hangs when the semaphore is set (bugzilla #77021).
+	 */
+	if (pdev->vendor == 0x8086 && (pdev->device == 0x283a ||
+			pdev->device == 0x27cc)) {
 		if (dmi_check_system(ehci_dmi_nohandoff_table))
 			try_handoff = 0;
 	}
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 6231ce6aa0c..aa79e874904 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -22,6 +22,7 @@
 
 
 #include <linux/slab.h>
+#include <linux/device.h>
 #include <asm/unaligned.h>
 
 #include "xhci.h"
@@ -287,7 +288,7 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend)
 		if (virt_dev->eps[i].ring && virt_dev->eps[i].ring->dequeue) {
 			struct xhci_command *command;
 			command = xhci_alloc_command(xhci, false, false,
-						     GFP_NOIO);
+						     GFP_NOWAIT);
 			if (!command) {
 				spin_unlock_irqrestore(&xhci->lock, flags);
 				xhci_free_command(xhci, cmd);
@@ -1139,7 +1140,9 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 		 * including the USB 3.0 roothub, but only if CONFIG_PM_RUNTIME
 		 * is enabled, so also enable remote wake here.
 		 */
-		if (hcd->self.root_hub->do_remote_wakeup) {
+		if (hcd->self.root_hub->do_remote_wakeup
+				&& device_may_wakeup(hcd->self.controller)) {
+
 			if (t1 & PORT_CONNECT) {
 				t2 |= PORT_WKOC_E | PORT_WKDISC_E;
 				t2 &= ~PORT_WKCONN_E;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index d67ff71209f..749fc68eb5c 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1433,8 +1433,11 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
 		xhci_handle_cmd_reset_ep(xhci, slot_id, cmd_trb, cmd_comp_code);
 		break;
 	case TRB_RESET_DEV:
-		WARN_ON(slot_id != TRB_TO_SLOT_ID(
-				le32_to_cpu(cmd_trb->generic.field[3])));
+		/* SLOT_ID field in reset device cmd completion event TRB is 0.
+		 * Use the SLOT_ID from the command TRB instead (xhci 4.6.11)
+		 */
+		slot_id = TRB_TO_SLOT_ID(
+				le32_to_cpu(cmd_trb->generic.field[3]));
 		xhci_handle_cmd_reset_dev(xhci, slot_id, event);
 		break;
 	case TRB_NEC_GET_FW:
@@ -3534,7 +3537,7 @@ static unsigned int xhci_get_burst_count(struct xhci_hcd *xhci,
 		return 0;
 
 	max_burst = urb->ep->ss_ep_comp.bMaxBurst;
-	return roundup(total_packet_count, max_burst + 1) - 1;
+	return DIV_ROUND_UP(total_packet_count, max_burst + 1) - 1;
 }
 
 /*
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 2b8d9a24af0..7436d5f5e67 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -936,7 +936,7 @@ int xhci_suspend(struct xhci_hcd *xhci)
  */
 int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 {
-	u32			command, temp = 0;
+	u32			command, temp = 0, status;
 	struct usb_hcd		*hcd = xhci_to_hcd(xhci);
 	struct usb_hcd		*secondary_hcd;
 	int			retval = 0;
@@ -1054,8 +1054,12 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 
  done:
 	if (retval == 0) {
-		usb_hcd_resume_root_hub(hcd);
-		usb_hcd_resume_root_hub(xhci->shared_hcd);
+		/* Resume root hubs only when have pending events. */
+		status = readl(&xhci->op_regs->status);
+		if (status & STS_EINT) {
+			usb_hcd_resume_root_hub(hcd);
+			usb_hcd_resume_root_hub(xhci->shared_hcd);
+		}
 	}
 
 	/*
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index 51a6da25677..829f446064e 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -7,7 +7,7 @@
 #include <linux/moduleparam.h>
 #include <linux/scatterlist.h>
 #include <linux/mutex.h>
-
+#include <linux/timer.h>
 #include <linux/usb.h>
 
 #define SIMPLE_IO_TIMEOUT	10000	/* in milliseconds */
@@ -484,6 +484,14 @@ alloc_sglist(int nents, int max, int vary)
 	return sg;
 }
 
+static void sg_timeout(unsigned long _req)
+{
+	struct usb_sg_request	*req = (struct usb_sg_request *) _req;
+
+	req->status = -ETIMEDOUT;
+	usb_sg_cancel(req);
+}
+
 static int perform_sglist(
 	struct usbtest_dev	*tdev,
 	unsigned		iterations,
@@ -495,6 +503,9 @@ static int perform_sglist(
 {
 	struct usb_device	*udev = testdev_to_usbdev(tdev);
 	int			retval = 0;
+	struct timer_list	sg_timer;
+
+	setup_timer_on_stack(&sg_timer, sg_timeout, (unsigned long) req);
 
 	while (retval == 0 && iterations-- > 0) {
 		retval = usb_sg_init(req, udev, pipe,
@@ -505,7 +516,10 @@ static int perform_sglist(
 
 		if (retval)
 			break;
+		mod_timer(&sg_timer, jiffies +
+				msecs_to_jiffies(SIMPLE_IO_TIMEOUT));
 		usb_sg_wait(req);
+		del_timer_sync(&sg_timer);
 		retval = req->status;
 
 		/* FIXME check resulting data pattern */
diff --git a/drivers/usb/musb/musb_am335x.c b/drivers/usb/musb/musb_am335x.c
index d2353781bd2..1e58ed2361c 100644
--- a/drivers/usb/musb/musb_am335x.c
+++ b/drivers/usb/musb/musb_am335x.c
@@ -19,21 +19,6 @@ err:
 	return ret;
 }
 
-static int of_remove_populated_child(struct device *dev, void *d)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-
-	of_device_unregister(pdev);
-	return 0;
-}
-
-static int am335x_child_remove(struct platform_device *pdev)
-{
-	device_for_each_child(&pdev->dev, NULL, of_remove_populated_child);
-	pm_runtime_disable(&pdev->dev);
-	return 0;
-}
-
 static const struct of_device_id am335x_child_of_match[] = {
 	{ .compatible = "ti,am33xx-usb" },
 	{  },
@@ -42,13 +27,17 @@ MODULE_DEVICE_TABLE(of, am335x_child_of_match);
 
 static struct platform_driver am335x_child_driver = {
 	.probe		= am335x_child_probe,
-	.remove         = am335x_child_remove,
 	.driver         = {
 		.name   = "am335x-usb-childs",
 		.of_match_table	= am335x_child_of_match,
 	},
 };
 
-module_platform_driver(am335x_child_driver);
+static int __init am335x_child_init(void)
+{
+	return platform_driver_register(&am335x_child_driver);
+}
+module_init(am335x_child_init);
+
 MODULE_DESCRIPTION("AM33xx child devices");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 61da471b7ae..eff3c5cf84f 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -849,7 +849,7 @@ b_host:
 	}
 
 	/* handle babble condition */
-	if (int_usb & MUSB_INTR_BABBLE)
+	if (int_usb & MUSB_INTR_BABBLE && is_host_active(musb))
 		schedule_work(&musb->recover_work);
 
 #if 0
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index 7b8bbf53127..5341bb223b7 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -318,7 +318,7 @@ static void cppi41_dma_callback(void *private_data)
 		}
 		list_add_tail(&cppi41_channel->tx_check,
 				&controller->early_tx_list);
-		if (!hrtimer_active(&controller->early_tx)) {
+		if (!hrtimer_is_queued(&controller->early_tx)) {
 			hrtimer_start_range_ns(&controller->early_tx,
 				ktime_set(0, 140 * NSEC_PER_USEC),
 				40 * NSEC_PER_USEC,
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 51beb13c7e1..09529f94e72 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -494,10 +494,9 @@ static int dsps_musb_set_mode(struct musb *musb, u8 mode)
 	struct dsps_glue *glue = dev_get_drvdata(dev->parent);
 	const struct dsps_musb_wrapper *wrp = glue->wrp;
 	void __iomem *ctrl_base = musb->ctrl_base;
-	void __iomem *base = musb->mregs;
 	u32 reg;
 
-	reg = dsps_readl(base, wrp->mode);
+	reg = dsps_readl(ctrl_base, wrp->mode);
 
 	switch (mode) {
 	case MUSB_HOST:
@@ -510,7 +509,7 @@ static int dsps_musb_set_mode(struct musb *musb, u8 mode)
 		 */
 		reg |= (1 << wrp->iddig_mux);
 
-		dsps_writel(base, wrp->mode, reg);
+		dsps_writel(ctrl_base, wrp->mode, reg);
 		dsps_writel(ctrl_base, wrp->phy_utmi, 0x02);
 		break;
 	case MUSB_PERIPHERAL:
@@ -523,10 +522,10 @@ static int dsps_musb_set_mode(struct musb *musb, u8 mode)
 		 */
 		reg |= (1 << wrp->iddig_mux);
 
-		dsps_writel(base, wrp->mode, reg);
+		dsps_writel(ctrl_base, wrp->mode, reg);
 		break;
 	case MUSB_OTG:
-		dsps_writel(base, wrp->phy_utmi, 0x02);
+		dsps_writel(ctrl_base, wrp->phy_utmi, 0x02);
 		break;
 	default:
 		dev_err(glue->dev, "unsupported mode %d\n", mode);
diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c
index c2e45e63272..f202e508846 100644
--- a/drivers/usb/musb/ux500.c
+++ b/drivers/usb/musb/ux500.c
@@ -274,7 +274,6 @@ static int ux500_probe(struct platform_device *pdev)
 	musb->dev.parent		= &pdev->dev;
 	musb->dev.dma_mask		= &pdev->dev.coherent_dma_mask;
 	musb->dev.coherent_dma_mask	= pdev->dev.coherent_dma_mask;
-	musb->dev.of_node		= pdev->dev.of_node;
 
 	glue->dev			= &pdev->dev;
 	glue->musb			= musb;
diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c
index ced34f39bdd..c929370cdaa 100644
--- a/drivers/usb/phy/phy-msm-usb.c
+++ b/drivers/usb/phy/phy-msm-usb.c
@@ -1229,7 +1229,9 @@ static void msm_otg_sm_work(struct work_struct *w)
 			motg->chg_state = USB_CHG_STATE_UNDEFINED;
 			motg->chg_type = USB_INVALID_CHARGER;
 		}
-		pm_runtime_put_sync(otg->phy->dev);
+
+		if (otg->phy->state == OTG_STATE_B_IDLE)
+			pm_runtime_put_sync(otg->phy->dev);
 		break;
 	case OTG_STATE_B_PERIPHERAL:
 		dev_dbg(otg->phy->dev, "OTG_STATE_B_PERIPHERAL state\n");
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index d49f9c32603..4fd36530bfa 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -681,6 +681,14 @@ usbhs_fifo_read_end:
 		usbhs_pipe_number(pipe),
 		pkt->length, pkt->actual, *is_done, pkt->zero);
 
+	/*
+	 * Transmission end
+	 */
+	if (*is_done) {
+		if (usbhs_pipe_is_dcp(pipe))
+			usbhs_dcp_control_transfer_done(pipe);
+	}
+
 usbhs_fifo_read_busy:
 	usbhsf_fifo_unselect(pipe, fifo);
 
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 762e4a5f5ae..330df5ce435 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -153,6 +153,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */
 	{ USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */
 	{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
+	{ USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */
 	{ USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */
 	{ USB_DEVICE(0x1E29, 0x0102) }, /* Festo CPX-USB */
 	{ USB_DEVICE(0x1E29, 0x0501) }, /* Festo CMSP */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index edf3b124583..8a3813be1b2 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -720,7 +720,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_ACG_HFDUAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_YEI_SERVOCENTER31_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_THORLABS_PID) },
-	{ USB_DEVICE(TESTO_VID, TESTO_USB_INTERFACE_PID) },
+	{ USB_DEVICE(TESTO_VID, TESTO_1_PID) },
+	{ USB_DEVICE(TESTO_VID, TESTO_3_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_GAMMA_SCOUT_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13M_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_TACTRIX_OPENPORT_13S_PID) },
@@ -944,6 +945,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_2_PID) },
 	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_3_PID) },
 	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_4_PID) },
+	/* Infineon Devices */
+	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) },
 	{ }					/* Terminating entry */
 };
 
@@ -1566,14 +1569,17 @@ static void ftdi_set_max_packet_size(struct usb_serial_port *port)
 	struct usb_device *udev = serial->dev;
 
 	struct usb_interface *interface = serial->interface;
-	struct usb_endpoint_descriptor *ep_desc = &interface->cur_altsetting->endpoint[1].desc;
+	struct usb_endpoint_descriptor *ep_desc;
 
 	unsigned num_endpoints;
-	int i;
+	unsigned i;
 
 	num_endpoints = interface->cur_altsetting->desc.bNumEndpoints;
 	dev_info(&udev->dev, "Number of endpoints %d\n", num_endpoints);
 
+	if (!num_endpoints)
+		return;
+
 	/* NOTE: some customers have programmed FT232R/FT245R devices
 	 * with an endpoint size of 0 - not good.  In this case, we
 	 * want to override the endpoint descriptor setting and use a
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 500474c48f4..c4777bc6aee 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -584,6 +584,12 @@
 #define RATOC_PRODUCT_ID_USB60F	0xb020
 
 /*
+ * Infineon Technologies
+ */
+#define INFINEON_VID		0x058b
+#define INFINEON_TRIBOARD_PID	0x0028 /* DAS JTAG TriBoard TC1798 V1.0 */
+
+/*
  * Acton Research Corp.
  */
 #define ACTON_VID		0x0647	/* Vendor ID */
@@ -798,7 +804,8 @@
  * Submitted by Colin Leroy
  */
 #define TESTO_VID			0x128D
-#define TESTO_USB_INTERFACE_PID		0x0001
+#define TESTO_1_PID			0x0001
+#define TESTO_3_PID			0x0003
 
 /*
  * Mobility Electronics products.
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 59c3108cc13..a9688940543 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -352,6 +352,9 @@ static void option_instat_callback(struct urb *urb);
 /* Zoom */
 #define ZOOM_PRODUCT_4597			0x9607
 
+/* SpeedUp SU9800 usb 3g modem */
+#define SPEEDUP_PRODUCT_SU9800			0x9800
+
 /* Haier products */
 #define HAIER_VENDOR_ID				0x201e
 #define HAIER_PRODUCT_CE100			0x2009
@@ -372,8 +375,12 @@ static void option_instat_callback(struct urb *urb);
 /* Olivetti products */
 #define OLIVETTI_VENDOR_ID			0x0b3c
 #define OLIVETTI_PRODUCT_OLICARD100		0xc000
+#define OLIVETTI_PRODUCT_OLICARD120		0xc001
+#define OLIVETTI_PRODUCT_OLICARD140		0xc002
 #define OLIVETTI_PRODUCT_OLICARD145		0xc003
+#define OLIVETTI_PRODUCT_OLICARD155		0xc004
 #define OLIVETTI_PRODUCT_OLICARD200		0xc005
+#define OLIVETTI_PRODUCT_OLICARD160		0xc00a
 #define OLIVETTI_PRODUCT_OLICARD500		0xc00b
 
 /* Celot products */
@@ -1480,6 +1487,8 @@ static const struct usb_device_id option_ids[] = {
 		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1426, 0xff, 0xff, 0xff),  /* ZTE MF91 */
 		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1428, 0xff, 0xff, 0xff),  /* Telewell TW-LTE 4G v2 */
+		.driver_info = (kernel_ulong_t)&net_intf2_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1533, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1534, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1535, 0xff, 0xff, 0xff) },
@@ -1577,6 +1586,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14),
   	  .driver_info = (kernel_ulong_t)&four_g_w14_blacklist
   	},
+	{ USB_DEVICE_INTERFACE_CLASS(LONGCHEER_VENDOR_ID, SPEEDUP_PRODUCT_SU9800, 0xff) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, ZOOM_PRODUCT_4597) },
 	{ USB_DEVICE(LONGCHEER_VENDOR_ID, IBALL_3_5G_CONNECT) },
 	{ USB_DEVICE(HAIER_VENDOR_ID, HAIER_PRODUCT_CE100) },
@@ -1611,15 +1621,21 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDMNET) },
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) }, /* HC28 enumerates with Siemens or Cinterion VID depending on FW revision */
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) },
-
-	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100) },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD100),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD120),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD140),
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD145) },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD155),
+		.driver_info = (kernel_ulong_t)&net_intf6_blacklist },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD200),
-		.driver_info = (kernel_ulong_t)&net_intf6_blacklist
-	},
+		.driver_info = (kernel_ulong_t)&net_intf6_blacklist },
+	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD160),
+		.driver_info = (kernel_ulong_t)&net_intf6_blacklist },
 	{ USB_DEVICE(OLIVETTI_VENDOR_ID, OLIVETTI_PRODUCT_OLICARD500),
-		.driver_info = (kernel_ulong_t)&net_intf4_blacklist
-	},
+		.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
 	{ USB_DEVICE(CELOT_VENDOR_ID, CELOT_PRODUCT_CT680M) }, /* CT-650 CDMA 450 1xEVDO modem */
 	{ USB_DEVICE_AND_INTERFACE_INFO(SAMSUNG_VENDOR_ID, SAMSUNG_PRODUCT_GT_B3730, USB_CLASS_CDC_DATA, 0x00, 0x00) }, /* Samsung GT-B3730 LTE USB modem.*/
 	{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CEM600) },
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 9d38ddc8da4..866b5df36ed 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -256,6 +256,10 @@ static int slave_configure(struct scsi_device *sdev)
 		if (us->fflags & US_FL_WRITE_CACHE)
 			sdev->wce_default_on = 1;
 
+		/* A few buggy USB-ATA bridges don't understand FUA */
+		if (us->fflags & US_FL_BROKEN_FUA)
+			sdev->broken_fua = 1;
+
 	} else {
 
 		/* Non-disk-type devices don't need to blacklist any pages
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 174a447868c..80a5b366255 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1936,6 +1936,13 @@ UNUSUAL_DEV(  0x14cd, 0x6600, 0x0201, 0x0201,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE ),
 
+/* Reported by Michael Büsch <m@bues.ch> */
+UNUSUAL_DEV(  0x152d, 0x0567, 0x0114, 0x0114,
+		"JMicron",
+		"USB to ATA/ATAPI Bridge",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_BROKEN_FUA ),
+
 /* Reported by Alexandre Oliva <oliva@lsd.ic.unicamp.br>
  * JMicron responds to USN and several other SCSI ioctls with a
  * residue that causes subsequent I/O requests to fail.  */
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index be414d2b2b2..8dae2f724a3 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -17,6 +17,7 @@
 #include <linux/workqueue.h>
 #include <linux/file.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #include <linux/net.h>
 #include <linux/if_packet.h>
@@ -373,7 +374,7 @@ static void handle_tx(struct vhost_net *net)
 			      % UIO_MAXIOV == nvq->done_idx))
 			break;
 
-		head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
+		head = vhost_get_vq_desc(vq, vq->iov,
 					 ARRAY_SIZE(vq->iov),
 					 &out, &in,
 					 NULL, NULL);
@@ -505,7 +506,7 @@ static int get_rx_bufs(struct vhost_virtqueue *vq,
 			r = -ENOBUFS;
 			goto err;
 		}
-		r = vhost_get_vq_desc(vq->dev, vq, vq->iov + seg,
+		r = vhost_get_vq_desc(vq, vq->iov + seg,
 				      ARRAY_SIZE(vq->iov) - seg, &out,
 				      &in, log, log_num);
 		if (unlikely(r < 0))
@@ -584,9 +585,9 @@ static void handle_rx(struct vhost_net *net)
 	vhost_hlen = nvq->vhost_hlen;
 	sock_hlen = nvq->sock_hlen;
 
-	vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
+	vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ?
 		vq->log : NULL;
-	mergeable = vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF);
+	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
 
 	while ((sock_len = peek_head_len(sock->sk))) {
 		sock_len += sock_hlen;
@@ -701,16 +702,20 @@ static void handle_rx_net(struct vhost_work *work)
 
 static int vhost_net_open(struct inode *inode, struct file *f)
 {
-	struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
+	struct vhost_net *n;
 	struct vhost_dev *dev;
 	struct vhost_virtqueue **vqs;
 	int i;
 
-	if (!n)
-		return -ENOMEM;
+	n = kmalloc(sizeof *n, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	if (!n) {
+		n = vmalloc(sizeof *n);
+		if (!n)
+			return -ENOMEM;
+	}
 	vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
 	if (!vqs) {
-		kfree(n);
+		kvfree(n);
 		return -ENOMEM;
 	}
 
@@ -827,7 +832,7 @@ static int vhost_net_release(struct inode *inode, struct file *f)
 	 * since jobs can re-queue themselves. */
 	vhost_net_flush(n);
 	kfree(n->dev.vqs);
-	kfree(n);
+	kvfree(n);
 	return 0;
 }
 
@@ -1038,15 +1043,13 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 		mutex_unlock(&n->dev.mutex);
 		return -EFAULT;
 	}
-	n->dev.acked_features = features;
-	smp_wmb();
 	for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
 		mutex_lock(&n->vqs[i].vq.mutex);
+		n->vqs[i].vq.acked_features = features;
 		n->vqs[i].vhost_hlen = vhost_hlen;
 		n->vqs[i].sock_hlen = sock_hlen;
 		mutex_unlock(&n->vqs[i].vq.mutex);
 	}
-	vhost_net_flush(n);
 	mutex_unlock(&n->dev.mutex);
 	return 0;
 }
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index aeb51310844..69906cacd04 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -57,7 +57,8 @@
 #define TCM_VHOST_MAX_CDB_SIZE 32
 #define TCM_VHOST_DEFAULT_TAGS 256
 #define TCM_VHOST_PREALLOC_SGLS 2048
-#define TCM_VHOST_PREALLOC_PAGES 2048
+#define TCM_VHOST_PREALLOC_UPAGES 2048
+#define TCM_VHOST_PREALLOC_PROT_SGLS 512
 
 struct vhost_scsi_inflight {
 	/* Wait for the flush operation to finish */
@@ -79,10 +80,12 @@ struct tcm_vhost_cmd {
 	u64 tvc_tag;
 	/* The number of scatterlists associated with this cmd */
 	u32 tvc_sgl_count;
+	u32 tvc_prot_sgl_count;
 	/* Saved unpacked SCSI LUN for tcm_vhost_submission_work() */
 	u32 tvc_lun;
 	/* Pointer to the SGL formatted memory from virtio-scsi */
 	struct scatterlist *tvc_sgl;
+	struct scatterlist *tvc_prot_sgl;
 	struct page **tvc_upages;
 	/* Pointer to response */
 	struct virtio_scsi_cmd_resp __user *tvc_resp;
@@ -166,7 +169,8 @@ enum {
 };
 
 enum {
-	VHOST_SCSI_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_SCSI_F_HOTPLUG)
+	VHOST_SCSI_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_SCSI_F_HOTPLUG) |
+					       (1ULL << VIRTIO_SCSI_F_T10_PI)
 };
 
 #define VHOST_SCSI_MAX_TARGET	256
@@ -456,12 +460,16 @@ static void tcm_vhost_release_cmd(struct se_cmd *se_cmd)
 	struct tcm_vhost_cmd *tv_cmd = container_of(se_cmd,
 				struct tcm_vhost_cmd, tvc_se_cmd);
 	struct se_session *se_sess = se_cmd->se_sess;
+	int i;
 
 	if (tv_cmd->tvc_sgl_count) {
-		u32 i;
 		for (i = 0; i < tv_cmd->tvc_sgl_count; i++)
 			put_page(sg_page(&tv_cmd->tvc_sgl[i]));
 	}
+	if (tv_cmd->tvc_prot_sgl_count) {
+		for (i = 0; i < tv_cmd->tvc_prot_sgl_count; i++)
+			put_page(sg_page(&tv_cmd->tvc_prot_sgl[i]));
+	}
 
 	tcm_vhost_put_inflight(tv_cmd->inflight);
 	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
@@ -606,7 +614,7 @@ tcm_vhost_do_evt_work(struct vhost_scsi *vs, struct tcm_vhost_evt *evt)
 
 again:
 	vhost_disable_notify(&vs->dev, vq);
-	head = vhost_get_vq_desc(&vs->dev, vq, vq->iov,
+	head = vhost_get_vq_desc(vq, vq->iov,
 			ARRAY_SIZE(vq->iov), &out, &in,
 			NULL, NULL);
 	if (head < 0) {
@@ -713,16 +721,14 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
 }
 
 static struct tcm_vhost_cmd *
-vhost_scsi_get_tag(struct vhost_virtqueue *vq,
-			struct tcm_vhost_tpg *tpg,
-			struct virtio_scsi_cmd_req *v_req,
-			u32 exp_data_len,
-			int data_direction)
+vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct tcm_vhost_tpg *tpg,
+		   unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr,
+		   u32 exp_data_len, int data_direction)
 {
 	struct tcm_vhost_cmd *cmd;
 	struct tcm_vhost_nexus *tv_nexus;
 	struct se_session *se_sess;
-	struct scatterlist *sg;
+	struct scatterlist *sg, *prot_sg;
 	struct page **pages;
 	int tag;
 
@@ -741,19 +747,24 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq,
 
 	cmd = &((struct tcm_vhost_cmd *)se_sess->sess_cmd_map)[tag];
 	sg = cmd->tvc_sgl;
+	prot_sg = cmd->tvc_prot_sgl;
 	pages = cmd->tvc_upages;
 	memset(cmd, 0, sizeof(struct tcm_vhost_cmd));
 
 	cmd->tvc_sgl = sg;
+	cmd->tvc_prot_sgl = prot_sg;
 	cmd->tvc_upages = pages;
 	cmd->tvc_se_cmd.map_tag = tag;
-	cmd->tvc_tag = v_req->tag;
-	cmd->tvc_task_attr = v_req->task_attr;
+	cmd->tvc_tag = scsi_tag;
+	cmd->tvc_lun = lun;
+	cmd->tvc_task_attr = task_attr;
 	cmd->tvc_exp_data_len = exp_data_len;
 	cmd->tvc_data_direction = data_direction;
 	cmd->tvc_nexus = tv_nexus;
 	cmd->inflight = tcm_vhost_get_inflight(vq);
 
+	memcpy(cmd->tvc_cdb, cdb, TCM_VHOST_MAX_CDB_SIZE);
+
 	return cmd;
 }
 
@@ -767,35 +778,28 @@ vhost_scsi_map_to_sgl(struct tcm_vhost_cmd *tv_cmd,
 		      struct scatterlist *sgl,
 		      unsigned int sgl_count,
 		      struct iovec *iov,
-		      int write)
+		      struct page **pages,
+		      bool write)
 {
 	unsigned int npages = 0, pages_nr, offset, nbytes;
 	struct scatterlist *sg = sgl;
 	void __user *ptr = iov->iov_base;
 	size_t len = iov->iov_len;
-	struct page **pages;
 	int ret, i;
 
-	if (sgl_count > TCM_VHOST_PREALLOC_SGLS) {
-		pr_err("vhost_scsi_map_to_sgl() psgl_count: %u greater than"
-		       " preallocated TCM_VHOST_PREALLOC_SGLS: %u\n",
-			sgl_count, TCM_VHOST_PREALLOC_SGLS);
-		return -ENOBUFS;
-	}
-
 	pages_nr = iov_num_pages(iov);
-	if (pages_nr > sgl_count)
+	if (pages_nr > sgl_count) {
+		pr_err("vhost_scsi_map_to_sgl() pages_nr: %u greater than"
+		       " sgl_count: %u\n", pages_nr, sgl_count);
 		return -ENOBUFS;
-
-	if (pages_nr > TCM_VHOST_PREALLOC_PAGES) {
+	}
+	if (pages_nr > TCM_VHOST_PREALLOC_UPAGES) {
 		pr_err("vhost_scsi_map_to_sgl() pages_nr: %u greater than"
-		       " preallocated TCM_VHOST_PREALLOC_PAGES: %u\n",
-			pages_nr, TCM_VHOST_PREALLOC_PAGES);
+		       " preallocated TCM_VHOST_PREALLOC_UPAGES: %u\n",
+			pages_nr, TCM_VHOST_PREALLOC_UPAGES);
 		return -ENOBUFS;
 	}
 
-	pages = tv_cmd->tvc_upages;
-
 	ret = get_user_pages_fast((unsigned long)ptr, pages_nr, write, pages);
 	/* No pages were pinned */
 	if (ret < 0)
@@ -825,33 +829,32 @@ out:
 static int
 vhost_scsi_map_iov_to_sgl(struct tcm_vhost_cmd *cmd,
 			  struct iovec *iov,
-			  unsigned int niov,
-			  int write)
+			  int niov,
+			  bool write)
 {
-	int ret;
-	unsigned int i;
-	u32 sgl_count;
-	struct scatterlist *sg;
+	struct scatterlist *sg = cmd->tvc_sgl;
+	unsigned int sgl_count = 0;
+	int ret, i;
 
-	/*
-	 * Find out how long sglist needs to be
-	 */
-	sgl_count = 0;
 	for (i = 0; i < niov; i++)
 		sgl_count += iov_num_pages(&iov[i]);
 
-	/* TODO overflow checking */
+	if (sgl_count > TCM_VHOST_PREALLOC_SGLS) {
+		pr_err("vhost_scsi_map_iov_to_sgl() sgl_count: %u greater than"
+			" preallocated TCM_VHOST_PREALLOC_SGLS: %u\n",
+			sgl_count, TCM_VHOST_PREALLOC_SGLS);
+		return -ENOBUFS;
+	}
 
-	sg = cmd->tvc_sgl;
 	pr_debug("%s sg %p sgl_count %u\n", __func__, sg, sgl_count);
 	sg_init_table(sg, sgl_count);
-
 	cmd->tvc_sgl_count = sgl_count;
 
-	pr_debug("Mapping %u iovecs for %u pages\n", niov, sgl_count);
+	pr_debug("Mapping iovec %p for %u pages\n", &iov[0], sgl_count);
+
 	for (i = 0; i < niov; i++) {
 		ret = vhost_scsi_map_to_sgl(cmd, sg, sgl_count, &iov[i],
-					    write);
+					    cmd->tvc_upages, write);
 		if (ret < 0) {
 			for (i = 0; i < cmd->tvc_sgl_count; i++)
 				put_page(sg_page(&cmd->tvc_sgl[i]));
@@ -859,31 +862,70 @@ vhost_scsi_map_iov_to_sgl(struct tcm_vhost_cmd *cmd,
 			cmd->tvc_sgl_count = 0;
 			return ret;
 		}
-
 		sg += ret;
 		sgl_count -= ret;
 	}
 	return 0;
 }
 
+static int
+vhost_scsi_map_iov_to_prot(struct tcm_vhost_cmd *cmd,
+			   struct iovec *iov,
+			   int niov,
+			   bool write)
+{
+	struct scatterlist *prot_sg = cmd->tvc_prot_sgl;
+	unsigned int prot_sgl_count = 0;
+	int ret, i;
+
+	for (i = 0; i < niov; i++)
+		prot_sgl_count += iov_num_pages(&iov[i]);
+
+	if (prot_sgl_count > TCM_VHOST_PREALLOC_PROT_SGLS) {
+		pr_err("vhost_scsi_map_iov_to_prot() sgl_count: %u greater than"
+			" preallocated TCM_VHOST_PREALLOC_PROT_SGLS: %u\n",
+			prot_sgl_count, TCM_VHOST_PREALLOC_PROT_SGLS);
+		return -ENOBUFS;
+	}
+
+	pr_debug("%s prot_sg %p prot_sgl_count %u\n", __func__,
+		 prot_sg, prot_sgl_count);
+	sg_init_table(prot_sg, prot_sgl_count);
+	cmd->tvc_prot_sgl_count = prot_sgl_count;
+
+	for (i = 0; i < niov; i++) {
+		ret = vhost_scsi_map_to_sgl(cmd, prot_sg, prot_sgl_count, &iov[i],
+					    cmd->tvc_upages, write);
+		if (ret < 0) {
+			for (i = 0; i < cmd->tvc_prot_sgl_count; i++)
+				put_page(sg_page(&cmd->tvc_prot_sgl[i]));
+
+			cmd->tvc_prot_sgl_count = 0;
+			return ret;
+		}
+		prot_sg += ret;
+		prot_sgl_count -= ret;
+	}
+	return 0;
+}
+
 static void tcm_vhost_submission_work(struct work_struct *work)
 {
 	struct tcm_vhost_cmd *cmd =
 		container_of(work, struct tcm_vhost_cmd, work);
 	struct tcm_vhost_nexus *tv_nexus;
 	struct se_cmd *se_cmd = &cmd->tvc_se_cmd;
-	struct scatterlist *sg_ptr, *sg_bidi_ptr = NULL;
-	int rc, sg_no_bidi = 0;
+	struct scatterlist *sg_ptr, *sg_prot_ptr = NULL;
+	int rc;
 
+	/* FIXME: BIDI operation */
 	if (cmd->tvc_sgl_count) {
 		sg_ptr = cmd->tvc_sgl;
-/* FIXME: Fix BIDI operation in tcm_vhost_submission_work() */
-#if 0
-		if (se_cmd->se_cmd_flags & SCF_BIDI) {
-			sg_bidi_ptr = NULL;
-			sg_no_bidi = 0;
-		}
-#endif
+
+		if (cmd->tvc_prot_sgl_count)
+			sg_prot_ptr = cmd->tvc_prot_sgl;
+		else
+			se_cmd->prot_pto = true;
 	} else {
 		sg_ptr = NULL;
 	}
@@ -894,7 +936,7 @@ static void tcm_vhost_submission_work(struct work_struct *work)
 			cmd->tvc_lun, cmd->tvc_exp_data_len,
 			cmd->tvc_task_attr, cmd->tvc_data_direction,
 			TARGET_SCF_ACK_KREF, sg_ptr, cmd->tvc_sgl_count,
-			sg_bidi_ptr, sg_no_bidi, NULL, 0);
+			NULL, 0, sg_prot_ptr, cmd->tvc_prot_sgl_count);
 	if (rc < 0) {
 		transport_send_check_condition_and_sense(se_cmd,
 				TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE, 0);
@@ -926,12 +968,18 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 {
 	struct tcm_vhost_tpg **vs_tpg;
 	struct virtio_scsi_cmd_req v_req;
+	struct virtio_scsi_cmd_req_pi v_req_pi;
 	struct tcm_vhost_tpg *tpg;
 	struct tcm_vhost_cmd *cmd;
-	u32 exp_data_len, data_first, data_num, data_direction;
+	u64 tag;
+	u32 exp_data_len, data_first, data_num, data_direction, prot_first;
 	unsigned out, in, i;
-	int head, ret;
-	u8 target;
+	int head, ret, data_niov, prot_niov, prot_bytes;
+	size_t req_size;
+	u16 lun;
+	u8 *target, *lunp, task_attr;
+	bool hdr_pi;
+	void *req, *cdb;
 
 	mutex_lock(&vq->mutex);
 	/*
@@ -945,7 +993,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 	vhost_disable_notify(&vs->dev, vq);
 
 	for (;;) {
-		head = vhost_get_vq_desc(&vs->dev, vq, vq->iov,
+		head = vhost_get_vq_desc(vq, vq->iov,
 					ARRAY_SIZE(vq->iov), &out, &in,
 					NULL, NULL);
 		pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n",
@@ -962,7 +1010,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			break;
 		}
 
-/* FIXME: BIDI operation */
+		/* FIXME: BIDI operation */
 		if (out == 1 && in == 1) {
 			data_direction = DMA_NONE;
 			data_first = 0;
@@ -992,29 +1040,38 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			break;
 		}
 
-		if (unlikely(vq->iov[0].iov_len != sizeof(v_req))) {
-			vq_err(vq, "Expecting virtio_scsi_cmd_req, got %zu"
-				" bytes\n", vq->iov[0].iov_len);
+		if (vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI)) {
+			req = &v_req_pi;
+			lunp = &v_req_pi.lun[0];
+			target = &v_req_pi.lun[1];
+			req_size = sizeof(v_req_pi);
+			hdr_pi = true;
+		} else {
+			req = &v_req;
+			lunp = &v_req.lun[0];
+			target = &v_req.lun[1];
+			req_size = sizeof(v_req);
+			hdr_pi = false;
+		}
+
+		if (unlikely(vq->iov[0].iov_len < req_size)) {
+			pr_err("Expecting virtio-scsi header: %zu, got %zu\n",
+			       req_size, vq->iov[0].iov_len);
 			break;
 		}
-		pr_debug("Calling __copy_from_user: vq->iov[0].iov_base: %p,"
-			" len: %zu\n", vq->iov[0].iov_base, sizeof(v_req));
-		ret = __copy_from_user(&v_req, vq->iov[0].iov_base,
-				sizeof(v_req));
+		ret = memcpy_fromiovecend(req, &vq->iov[0], 0, req_size);
 		if (unlikely(ret)) {
 			vq_err(vq, "Faulted on virtio_scsi_cmd_req\n");
 			break;
 		}
 
 		/* virtio-scsi spec requires byte 0 of the lun to be 1 */
-		if (unlikely(v_req.lun[0] != 1)) {
+		if (unlikely(*lunp != 1)) {
 			vhost_scsi_send_bad_target(vs, vq, head, out);
 			continue;
 		}
 
-		/* Extract the tpgt */
-		target = v_req.lun[1];
-		tpg = ACCESS_ONCE(vs_tpg[target]);
+		tpg = ACCESS_ONCE(vs_tpg[*target]);
 
 		/* Target does not exist, fail the request */
 		if (unlikely(!tpg)) {
@@ -1022,17 +1079,79 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 			continue;
 		}
 
+		data_niov = data_num;
+		prot_niov = prot_first = prot_bytes = 0;
+		/*
+		 * Determine if any protection information iovecs are preceeding
+		 * the actual data payload, and adjust data_first + data_niov
+		 * values accordingly for vhost_scsi_map_iov_to_sgl() below.
+		 *
+		 * Also extract virtio_scsi header bits for vhost_scsi_get_tag()
+		 */
+		if (hdr_pi) {
+			if (v_req_pi.pi_bytesout) {
+				if (data_direction != DMA_TO_DEVICE) {
+					vq_err(vq, "Received non zero do_pi_niov"
+						", but wrong data_direction\n");
+					goto err_cmd;
+				}
+				prot_bytes = v_req_pi.pi_bytesout;
+			} else if (v_req_pi.pi_bytesin) {
+				if (data_direction != DMA_FROM_DEVICE) {
+					vq_err(vq, "Received non zero di_pi_niov"
+						", but wrong data_direction\n");
+					goto err_cmd;
+				}
+				prot_bytes = v_req_pi.pi_bytesin;
+			}
+			if (prot_bytes) {
+				int tmp = 0;
+
+				for (i = 0; i < data_num; i++) {
+					tmp += vq->iov[data_first + i].iov_len;
+					prot_niov++;
+					if (tmp >= prot_bytes)
+						break;
+				}
+				prot_first = data_first;
+				data_first += prot_niov;
+				data_niov = data_num - prot_niov;
+			}
+			tag = v_req_pi.tag;
+			task_attr = v_req_pi.task_attr;
+			cdb = &v_req_pi.cdb[0];
+			lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF;
+		} else {
+			tag = v_req.tag;
+			task_attr = v_req.task_attr;
+			cdb = &v_req.cdb[0];
+			lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;
+		}
 		exp_data_len = 0;
-		for (i = 0; i < data_num; i++)
+		for (i = 0; i < data_niov; i++)
 			exp_data_len += vq->iov[data_first + i].iov_len;
+		/*
+		 * Check that the recieved CDB size does not exceeded our
+		 * hardcoded max for vhost-scsi
+		 *
+		 * TODO what if cdb was too small for varlen cdb header?
+		 */
+		if (unlikely(scsi_command_size(cdb) > TCM_VHOST_MAX_CDB_SIZE)) {
+			vq_err(vq, "Received SCSI CDB with command_size: %d that"
+				" exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n",
+				scsi_command_size(cdb), TCM_VHOST_MAX_CDB_SIZE);
+			goto err_cmd;
+		}
 
-		cmd = vhost_scsi_get_tag(vq, tpg, &v_req,
-					 exp_data_len, data_direction);
+		cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr,
+					 exp_data_len + prot_bytes,
+					 data_direction);
 		if (IS_ERR(cmd)) {
 			vq_err(vq, "vhost_scsi_get_tag failed %ld\n",
 					PTR_ERR(cmd));
 			goto err_cmd;
 		}
+
 		pr_debug("Allocated tv_cmd: %p exp_data_len: %d, data_direction"
 			": %d\n", cmd, exp_data_len, data_direction);
 
@@ -1040,40 +1159,28 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
 		cmd->tvc_vq = vq;
 		cmd->tvc_resp = vq->iov[out].iov_base;
 
-		/*
-		 * Copy in the recieved CDB descriptor into cmd->tvc_cdb
-		 * that will be used by tcm_vhost_new_cmd_map() and down into
-		 * target_setup_cmd_from_cdb()
-		 */
-		memcpy(cmd->tvc_cdb, v_req.cdb, TCM_VHOST_MAX_CDB_SIZE);
-		/*
-		 * Check that the recieved CDB size does not exceeded our
-		 * hardcoded max for tcm_vhost
-		 */
-		/* TODO what if cdb was too small for varlen cdb header? */
-		if (unlikely(scsi_command_size(cmd->tvc_cdb) >
-					TCM_VHOST_MAX_CDB_SIZE)) {
-			vq_err(vq, "Received SCSI CDB with command_size: %d that"
-				" exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n",
-				scsi_command_size(cmd->tvc_cdb),
-				TCM_VHOST_MAX_CDB_SIZE);
-			goto err_free;
-		}
-		cmd->tvc_lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF;
-
 		pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
 			cmd->tvc_cdb[0], cmd->tvc_lun);
 
+		if (prot_niov) {
+			ret = vhost_scsi_map_iov_to_prot(cmd,
+					&vq->iov[prot_first], prot_niov,
+					data_direction == DMA_FROM_DEVICE);
+			if (unlikely(ret)) {
+				vq_err(vq, "Failed to map iov to"
+					" prot_sgl\n");
+				goto err_free;
+			}
+		}
 		if (data_direction != DMA_NONE) {
 			ret = vhost_scsi_map_iov_to_sgl(cmd,
-					&vq->iov[data_first], data_num,
+					&vq->iov[data_first], data_niov,
 					data_direction == DMA_FROM_DEVICE);
 			if (unlikely(ret)) {
 				vq_err(vq, "Failed to map iov to sgl\n");
 				goto err_free;
 			}
 		}
-
 		/*
 		 * Save the descriptor from vhost_get_vq_desc() to be used to
 		 * complete the virtio-scsi request in TCM callback context via
@@ -1373,6 +1480,9 @@ err_dev:
 
 static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features)
 {
+	struct vhost_virtqueue *vq;
+	int i;
+
 	if (features & ~VHOST_SCSI_FEATURES)
 		return -EOPNOTSUPP;
 
@@ -1382,21 +1492,17 @@ static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features)
 		mutex_unlock(&vs->dev.mutex);
 		return -EFAULT;
 	}
-	vs->dev.acked_features = features;
-	smp_wmb();
-	vhost_scsi_flush(vs);
+
+	for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
+		vq = &vs->vqs[i].vq;
+		mutex_lock(&vq->mutex);
+		vq->acked_features = features;
+		mutex_unlock(&vq->mutex);
+	}
 	mutex_unlock(&vs->dev.mutex);
 	return 0;
 }
 
-static void vhost_scsi_free(struct vhost_scsi *vs)
-{
-	if (is_vmalloc_addr(vs))
-		vfree(vs);
-	else
-		kfree(vs);
-}
-
 static int vhost_scsi_open(struct inode *inode, struct file *f)
 {
 	struct vhost_scsi *vs;
@@ -1436,7 +1542,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 	return 0;
 
 err_vqs:
-	vhost_scsi_free(vs);
+	kvfree(vs);
 err_vs:
 	return r;
 }
@@ -1455,7 +1561,7 @@ static int vhost_scsi_release(struct inode *inode, struct file *f)
 	/* Jobs can re-queue themselves in evt kick handler. Do extra flush. */
 	vhost_scsi_flush(vs);
 	kfree(vs->dev.vqs);
-	vhost_scsi_free(vs);
+	kvfree(vs);
 	return 0;
 }
 
@@ -1591,10 +1697,6 @@ tcm_vhost_do_plug(struct tcm_vhost_tpg *tpg,
 		return;
 
 	mutex_lock(&vs->dev.mutex);
-	if (!vhost_has_feature(&vs->dev, VIRTIO_SCSI_F_HOTPLUG)) {
-		mutex_unlock(&vs->dev.mutex);
-		return;
-	}
 
 	if (plug)
 		reason = VIRTIO_SCSI_EVT_RESET_RESCAN;
@@ -1603,8 +1705,9 @@ tcm_vhost_do_plug(struct tcm_vhost_tpg *tpg,
 
 	vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
 	mutex_lock(&vq->mutex);
-	tcm_vhost_send_evt(vs, tpg, lun,
-			VIRTIO_SCSI_T_TRANSPORT_RESET, reason);
+	if (vhost_has_feature(vq, VIRTIO_SCSI_F_HOTPLUG))
+		tcm_vhost_send_evt(vs, tpg, lun,
+				   VIRTIO_SCSI_T_TRANSPORT_RESET, reason);
 	mutex_unlock(&vq->mutex);
 	mutex_unlock(&vs->dev.mutex);
 }
@@ -1712,6 +1815,7 @@ static void tcm_vhost_free_cmd_map_res(struct tcm_vhost_nexus *nexus,
 		tv_cmd = &((struct tcm_vhost_cmd *)se_sess->sess_cmd_map)[i];
 
 		kfree(tv_cmd->tvc_sgl);
+		kfree(tv_cmd->tvc_prot_sgl);
 		kfree(tv_cmd->tvc_upages);
 	}
 }
@@ -1746,7 +1850,7 @@ static int tcm_vhost_make_nexus(struct tcm_vhost_tpg *tpg,
 	tv_nexus->tvn_se_sess = transport_init_session_tags(
 					TCM_VHOST_DEFAULT_TAGS,
 					sizeof(struct tcm_vhost_cmd),
-					TARGET_PROT_NORMAL);
+					TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS);
 	if (IS_ERR(tv_nexus->tvn_se_sess)) {
 		mutex_unlock(&tpg->tv_tpg_mutex);
 		kfree(tv_nexus);
@@ -1765,12 +1869,20 @@ static int tcm_vhost_make_nexus(struct tcm_vhost_tpg *tpg,
 		}
 
 		tv_cmd->tvc_upages = kzalloc(sizeof(struct page *) *
-					TCM_VHOST_PREALLOC_PAGES, GFP_KERNEL);
+					TCM_VHOST_PREALLOC_UPAGES, GFP_KERNEL);
 		if (!tv_cmd->tvc_upages) {
 			mutex_unlock(&tpg->tv_tpg_mutex);
 			pr_err("Unable to allocate tv_cmd->tvc_upages\n");
 			goto out;
 		}
+
+		tv_cmd->tvc_prot_sgl = kzalloc(sizeof(struct scatterlist) *
+					TCM_VHOST_PREALLOC_PROT_SGLS, GFP_KERNEL);
+		if (!tv_cmd->tvc_prot_sgl) {
+			mutex_unlock(&tpg->tv_tpg_mutex);
+			pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n");
+			goto out;
+		}
 	}
 	/*
 	 * Since we are running in 'demo mode' this call with generate a
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index c2a54fbf7f9..d9c501eaa6c 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -53,7 +53,7 @@ static void handle_vq(struct vhost_test *n)
 	vhost_disable_notify(&n->dev, vq);
 
 	for (;;) {
-		head = vhost_get_vq_desc(&n->dev, vq, vq->iov,
+		head = vhost_get_vq_desc(vq, vq->iov,
 					 ARRAY_SIZE(vq->iov),
 					 &out, &in,
 					 NULL, NULL);
@@ -241,15 +241,18 @@ done:
 
 static int vhost_test_set_features(struct vhost_test *n, u64 features)
 {
+	struct vhost_virtqueue *vq;
+
 	mutex_lock(&n->dev.mutex);
 	if ((features & (1 << VHOST_F_LOG_ALL)) &&
 	    !vhost_log_access_ok(&n->dev)) {
 		mutex_unlock(&n->dev.mutex);
 		return -EFAULT;
 	}
-	n->dev.acked_features = features;
-	smp_wmb();
-	vhost_test_flush(n);
+	vq = &n->vqs[VHOST_TEST_VQ];
+	mutex_lock(&vq->mutex);
+	vq->acked_features = features;
+	mutex_unlock(&vq->mutex);
 	mutex_unlock(&n->dev.mutex);
 	return 0;
 }
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 78987e481bc..c90f4374442 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -18,7 +18,6 @@
 #include <linux/mmu_context.h>
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
-#include <linux/rcupdate.h>
 #include <linux/poll.h>
 #include <linux/file.h>
 #include <linux/highmem.h>
@@ -191,6 +190,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->log_used = false;
 	vq->log_addr = -1ull;
 	vq->private_data = NULL;
+	vq->acked_features = 0;
 	vq->log_base = NULL;
 	vq->error_ctx = NULL;
 	vq->error = NULL;
@@ -198,6 +198,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->call_ctx = NULL;
 	vq->call = NULL;
 	vq->log_ctx = NULL;
+	vq->memory = NULL;
 }
 
 static int vhost_worker(void *data)
@@ -415,11 +416,18 @@ EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare);
 /* Caller should have device mutex */
 void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_memory *memory)
 {
+	int i;
+
 	vhost_dev_cleanup(dev, true);
 
 	/* Restore memory to default empty mapping. */
 	memory->nregions = 0;
-	RCU_INIT_POINTER(dev->memory, memory);
+	dev->memory = memory;
+	/* We don't need VQ locks below since vhost_dev_cleanup makes sure
+	 * VQs aren't running.
+	 */
+	for (i = 0; i < dev->nvqs; ++i)
+		dev->vqs[i]->memory = memory;
 }
 EXPORT_SYMBOL_GPL(vhost_dev_reset_owner);
 
@@ -462,10 +470,8 @@ void vhost_dev_cleanup(struct vhost_dev *dev, bool locked)
 		fput(dev->log_file);
 	dev->log_file = NULL;
 	/* No one will access memory at this point */
-	kfree(rcu_dereference_protected(dev->memory,
-					locked ==
-						lockdep_is_held(&dev->mutex)));
-	RCU_INIT_POINTER(dev->memory, NULL);
+	kfree(dev->memory);
+	dev->memory = NULL;
 	WARN_ON(!list_empty(&dev->work_list));
 	if (dev->worker) {
 		kthread_stop(dev->worker);
@@ -524,11 +530,13 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
 
 	for (i = 0; i < d->nvqs; ++i) {
 		int ok;
+		bool log;
+
 		mutex_lock(&d->vqs[i]->mutex);
+		log = log_all || vhost_has_feature(d->vqs[i], VHOST_F_LOG_ALL);
 		/* If ring is inactive, will check when it's enabled. */
 		if (d->vqs[i]->private_data)
-			ok = vq_memory_access_ok(d->vqs[i]->log_base, mem,
-						 log_all);
+			ok = vq_memory_access_ok(d->vqs[i]->log_base, mem, log);
 		else
 			ok = 1;
 		mutex_unlock(&d->vqs[i]->mutex);
@@ -538,12 +546,12 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
 	return 1;
 }
 
-static int vq_access_ok(struct vhost_dev *d, unsigned int num,
+static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
 			struct vring_desc __user *desc,
 			struct vring_avail __user *avail,
 			struct vring_used __user *used)
 {
-	size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
+	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 	return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
 	       access_ok(VERIFY_READ, avail,
 			 sizeof *avail + num * sizeof *avail->ring + s) &&
@@ -555,26 +563,19 @@ static int vq_access_ok(struct vhost_dev *d, unsigned int num,
 /* Caller should have device mutex but not vq mutex */
 int vhost_log_access_ok(struct vhost_dev *dev)
 {
-	struct vhost_memory *mp;
-
-	mp = rcu_dereference_protected(dev->memory,
-				       lockdep_is_held(&dev->mutex));
-	return memory_access_ok(dev, mp, 1);
+	return memory_access_ok(dev, dev->memory, 1);
 }
 EXPORT_SYMBOL_GPL(vhost_log_access_ok);
 
 /* Verify access for write logging. */
 /* Caller should have vq mutex and device mutex */
-static int vq_log_access_ok(struct vhost_dev *d, struct vhost_virtqueue *vq,
+static int vq_log_access_ok(struct vhost_virtqueue *vq,
 			    void __user *log_base)
 {
-	struct vhost_memory *mp;
-	size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
+	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 
-	mp = rcu_dereference_protected(vq->dev->memory,
-				       lockdep_is_held(&vq->mutex));
-	return vq_memory_access_ok(log_base, mp,
-			    vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
+	return vq_memory_access_ok(log_base, vq->memory,
+				   vhost_has_feature(vq, VHOST_F_LOG_ALL)) &&
 		(!vq->log_used || log_access_ok(log_base, vq->log_addr,
 					sizeof *vq->used +
 					vq->num * sizeof *vq->used->ring + s));
@@ -584,8 +585,8 @@ static int vq_log_access_ok(struct vhost_dev *d, struct vhost_virtqueue *vq,
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-	return vq_access_ok(vq->dev, vq->num, vq->desc, vq->avail, vq->used) &&
-		vq_log_access_ok(vq->dev, vq, vq->log_base);
+	return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used) &&
+		vq_log_access_ok(vq, vq->log_base);
 }
 EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
 
@@ -593,6 +594,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 {
 	struct vhost_memory mem, *newmem, *oldmem;
 	unsigned long size = offsetof(struct vhost_memory, regions);
+	int i;
 
 	if (copy_from_user(&mem, m, size))
 		return -EFAULT;
@@ -611,15 +613,19 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 		return -EFAULT;
 	}
 
-	if (!memory_access_ok(d, newmem,
-			      vhost_has_feature(d, VHOST_F_LOG_ALL))) {
+	if (!memory_access_ok(d, newmem, 0)) {
 		kfree(newmem);
 		return -EFAULT;
 	}
-	oldmem = rcu_dereference_protected(d->memory,
-					   lockdep_is_held(&d->mutex));
-	rcu_assign_pointer(d->memory, newmem);
-	synchronize_rcu();
+	oldmem = d->memory;
+	d->memory = newmem;
+
+	/* All memory accesses are done under some VQ mutex. */
+	for (i = 0; i < d->nvqs; ++i) {
+		mutex_lock(&d->vqs[i]->mutex);
+		d->vqs[i]->memory = newmem;
+		mutex_unlock(&d->vqs[i]->mutex);
+	}
 	kfree(oldmem);
 	return 0;
 }
@@ -718,7 +724,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp)
 		 * If it is not, we don't as size might not have been setup.
 		 * We will verify when backend is configured. */
 		if (vq->private_data) {
-			if (!vq_access_ok(d, vq->num,
+			if (!vq_access_ok(vq, vq->num,
 				(void __user *)(unsigned long)a.desc_user_addr,
 				(void __user *)(unsigned long)a.avail_user_addr,
 				(void __user *)(unsigned long)a.used_user_addr)) {
@@ -858,7 +864,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
 			vq = d->vqs[i];
 			mutex_lock(&vq->mutex);
 			/* If ring is inactive, will check when it's enabled. */
-			if (vq->private_data && !vq_log_access_ok(d, vq, base))
+			if (vq->private_data && !vq_log_access_ok(vq, base))
 				r = -EFAULT;
 			else
 				vq->log_base = base;
@@ -1044,7 +1050,7 @@ int vhost_init_used(struct vhost_virtqueue *vq)
 }
 EXPORT_SYMBOL_GPL(vhost_init_used);
 
-static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
+static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
 			  struct iovec iov[], int iov_size)
 {
 	const struct vhost_memory_region *reg;
@@ -1053,9 +1059,7 @@ static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
 	u64 s = 0;
 	int ret = 0;
 
-	rcu_read_lock();
-
-	mem = rcu_dereference(dev->memory);
+	mem = vq->memory;
 	while ((u64)len > s) {
 		u64 size;
 		if (unlikely(ret >= iov_size)) {
@@ -1077,7 +1081,6 @@ static int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
 		++ret;
 	}
 
-	rcu_read_unlock();
 	return ret;
 }
 
@@ -1102,7 +1105,7 @@ static unsigned next_desc(struct vring_desc *desc)
 	return next;
 }
 
-static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
+static int get_indirect(struct vhost_virtqueue *vq,
 			struct iovec iov[], unsigned int iov_size,
 			unsigned int *out_num, unsigned int *in_num,
 			struct vhost_log *log, unsigned int *log_num,
@@ -1121,7 +1124,7 @@ static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 		return -EINVAL;
 	}
 
-	ret = translate_desc(dev, indirect->addr, indirect->len, vq->indirect,
+	ret = translate_desc(vq, indirect->addr, indirect->len, vq->indirect,
 			     UIO_MAXIOV);
 	if (unlikely(ret < 0)) {
 		vq_err(vq, "Translation failure %d in indirect.\n", ret);
@@ -1161,7 +1164,7 @@ static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 			return -EINVAL;
 		}
 
-		ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
+		ret = translate_desc(vq, desc.addr, desc.len, iov + iov_count,
 				     iov_size - iov_count);
 		if (unlikely(ret < 0)) {
 			vq_err(vq, "Translation failure %d indirect idx %d\n",
@@ -1198,7 +1201,7 @@ static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
  * This function returns the descriptor number found, or vq->num (which is
  * never a valid descriptor number) if none was found.  A negative code is
  * returned on error. */
-int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
+int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 		      struct iovec iov[], unsigned int iov_size,
 		      unsigned int *out_num, unsigned int *in_num,
 		      struct vhost_log *log, unsigned int *log_num)
@@ -1272,7 +1275,7 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 			return -EFAULT;
 		}
 		if (desc.flags & VRING_DESC_F_INDIRECT) {
-			ret = get_indirect(dev, vq, iov, iov_size,
+			ret = get_indirect(vq, iov, iov_size,
 					   out_num, in_num,
 					   log, log_num, &desc);
 			if (unlikely(ret < 0)) {
@@ -1283,7 +1286,7 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 			continue;
 		}
 
-		ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
+		ret = translate_desc(vq, desc.addr, desc.len, iov + iov_count,
 				     iov_size - iov_count);
 		if (unlikely(ret < 0)) {
 			vq_err(vq, "Translation failure %d descriptor idx %d\n",
@@ -1426,11 +1429,11 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	 * interrupts. */
 	smp_mb();
 
-	if (vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
+	if (vhost_has_feature(vq, VIRTIO_F_NOTIFY_ON_EMPTY) &&
 	    unlikely(vq->avail_idx == vq->last_avail_idx))
 		return true;
 
-	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
 		__u16 flags;
 		if (__get_user(flags, &vq->avail->flags)) {
 			vq_err(vq, "Failed to get flags");
@@ -1491,7 +1494,7 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
 		return false;
 	vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
-	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
 		r = vhost_update_used_flags(vq);
 		if (r) {
 			vq_err(vq, "Failed to enable notification at %p: %d\n",
@@ -1528,7 +1531,7 @@ void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
 		return;
 	vq->used_flags |= VRING_USED_F_NO_NOTIFY;
-	if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+	if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) {
 		r = vhost_update_used_flags(vq);
 		if (r)
 			vq_err(vq, "Failed to enable notification at %p: %d\n",
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 35eeb2a1bad..3eda654b8f5 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -104,20 +104,18 @@ struct vhost_virtqueue {
 	struct iovec *indirect;
 	struct vring_used_elem *heads;
 	/* Protected by virtqueue mutex. */
+	struct vhost_memory *memory;
 	void *private_data;
+	unsigned acked_features;
 	/* Log write descriptors */
 	void __user *log_base;
 	struct vhost_log *log;
 };
 
 struct vhost_dev {
-	/* Readers use RCU to access memory table pointer
-	 * log base pointer and features.
-	 * Writers use mutex below.*/
-	struct vhost_memory __rcu *memory;
+	struct vhost_memory *memory;
 	struct mm_struct *mm;
 	struct mutex mutex;
-	unsigned acked_features;
 	struct vhost_virtqueue **vqs;
 	int nvqs;
 	struct file *log_file;
@@ -140,7 +138,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp);
 int vhost_vq_access_ok(struct vhost_virtqueue *vq);
 int vhost_log_access_ok(struct vhost_dev *);
 
-int vhost_get_vq_desc(struct vhost_dev *, struct vhost_virtqueue *,
+int vhost_get_vq_desc(struct vhost_virtqueue *,
 		      struct iovec iov[], unsigned int iov_count,
 		      unsigned int *out_num, unsigned int *in_num,
 		      struct vhost_log *log, unsigned int *log_num);
@@ -174,13 +172,8 @@ enum {
 			 (1ULL << VHOST_F_LOG_ALL),
 };
 
-static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
+static inline int vhost_has_feature(struct vhost_virtqueue *vq, int bit)
 {
-	unsigned acked_features;
-
-	/* TODO: check that we are running from vhost_worker or dev mutex is
-	 * held? */
-	acked_features = rcu_dereference_index_check(dev->acked_features, 1);
-	return acked_features & (1 << bit);
+	return vq->acked_features & (1 << bit);
 }
 #endif
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index c7b4f0f927b..8bf495ffb02 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -20,6 +20,7 @@ source "drivers/char/agp/Kconfig"
 source "drivers/gpu/vga/Kconfig"
 
 source "drivers/gpu/host1x/Kconfig"
+source "drivers/gpu/ipu-v3/Kconfig"
 
 menu "Direct Rendering Manager"
 source "drivers/gpu/drm/Kconfig"
diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index 5a3eb2ecb52..5d449059a55 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -29,7 +29,7 @@ if LCD_CLASS_DEVICE
 
 config LCD_CORGI
 	tristate "LCD Panel support for SHARP corgi/spitz model"
-	depends on SPI_MASTER && PXA_SHARPSL
+	depends on SPI_MASTER && PXA_SHARPSL && BACKLIGHT_CLASS_DEVICE
 	help
 	  Say y here to support the LCD panels usually found on SHARP
 	  corgi (C7x0) and spitz (Cxx00) models.
@@ -370,7 +370,7 @@ config BACKLIGHT_AAT2870
 
 config BACKLIGHT_LM3630A
 	tristate "Backlight Driver for LM3630A"
-	depends on BACKLIGHT_CLASS_DEVICE && I2C
+	depends on BACKLIGHT_CLASS_DEVICE && I2C && PWM
 	select REGMAP_I2C
 	help
 	  This supports TI LM3630A Backlight Driver
@@ -386,14 +386,14 @@ config BACKLIGHT_LM3639
 
 config BACKLIGHT_LP855X
 	tristate "Backlight driver for TI LP855X"
-	depends on BACKLIGHT_CLASS_DEVICE && I2C
+	depends on BACKLIGHT_CLASS_DEVICE && I2C && PWM
 	help
 	  This supports TI LP8550, LP8551, LP8552, LP8553, LP8555, LP8556 and
 	  LP8557 backlight driver.
 
 config BACKLIGHT_LP8788
 	tristate "Backlight driver for TI LP8788 MFD"
-	depends on BACKLIGHT_CLASS_DEVICE && MFD_LP8788
+	depends on BACKLIGHT_CLASS_DEVICE && MFD_LP8788 && PWM
 	help
 	  This supports TI LP8788 backlight driver.
 
diff --git a/drivers/video/backlight/gpio_backlight.c b/drivers/video/backlight/gpio_backlight.c
index a2eba12e1cb..1cea68848f1 100644
--- a/drivers/video/backlight/gpio_backlight.c
+++ b/drivers/video/backlight/gpio_backlight.c
@@ -38,7 +38,8 @@ static int gpio_backlight_update_status(struct backlight_device *bl)
 	    bl->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK))
 		brightness = 0;
 
-	gpio_set_value(gbl->gpio, brightness ? gbl->active : !gbl->active);
+	gpio_set_value_cansleep(gbl->gpio,
+				brightness ? gbl->active : !gbl->active);
 
 	return 0;
 }
diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c
index b75201ff46f..38ca88bc5c3 100644
--- a/drivers/video/backlight/pwm_bl.c
+++ b/drivers/video/backlight/pwm_bl.c
@@ -10,8 +10,8 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/gpio/consumer.h>
 #include <linux/gpio.h>
-#include <linux/of_gpio.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -32,8 +32,7 @@ struct pwm_bl_data {
 	unsigned int		*levels;
 	bool			enabled;
 	struct regulator	*power_supply;
-	int			enable_gpio;
-	unsigned long		enable_gpio_flags;
+	struct gpio_desc	*enable_gpio;
 	unsigned int		scale;
 	int			(*notify)(struct device *,
 					  int brightness);
@@ -54,12 +53,8 @@ static void pwm_backlight_power_on(struct pwm_bl_data *pb, int brightness)
 	if (err < 0)
 		dev_err(pb->dev, "failed to enable power supply\n");
 
-	if (gpio_is_valid(pb->enable_gpio)) {
-		if (pb->enable_gpio_flags & PWM_BACKLIGHT_GPIO_ACTIVE_LOW)
-			gpio_set_value(pb->enable_gpio, 0);
-		else
-			gpio_set_value(pb->enable_gpio, 1);
-	}
+	if (pb->enable_gpio)
+		gpiod_set_value(pb->enable_gpio, 1);
 
 	pwm_enable(pb->pwm);
 	pb->enabled = true;
@@ -73,12 +68,8 @@ static void pwm_backlight_power_off(struct pwm_bl_data *pb)
 	pwm_config(pb->pwm, 0, pb->period);
 	pwm_disable(pb->pwm);
 
-	if (gpio_is_valid(pb->enable_gpio)) {
-		if (pb->enable_gpio_flags & PWM_BACKLIGHT_GPIO_ACTIVE_LOW)
-			gpio_set_value(pb->enable_gpio, 1);
-		else
-			gpio_set_value(pb->enable_gpio, 0);
-	}
+	if (pb->enable_gpio)
+		gpiod_set_value(pb->enable_gpio, 0);
 
 	regulator_disable(pb->power_supply);
 	pb->enabled = false;
@@ -148,7 +139,6 @@ static int pwm_backlight_parse_dt(struct device *dev,
 				  struct platform_pwm_backlight_data *data)
 {
 	struct device_node *node = dev->of_node;
-	enum of_gpio_flags flags;
 	struct property *prop;
 	int length;
 	u32 value;
@@ -189,14 +179,6 @@ static int pwm_backlight_parse_dt(struct device *dev,
 		data->max_brightness--;
 	}
 
-	data->enable_gpio = of_get_named_gpio_flags(node, "enable-gpios", 0,
-						    &flags);
-	if (data->enable_gpio == -EPROBE_DEFER)
-		return -EPROBE_DEFER;
-
-	if (gpio_is_valid(data->enable_gpio) && (flags & OF_GPIO_ACTIVE_LOW))
-		data->enable_gpio_flags |= PWM_BACKLIGHT_GPIO_ACTIVE_LOW;
-
 	return 0;
 }
 
@@ -256,8 +238,6 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	} else
 		pb->scale = data->max_brightness;
 
-	pb->enable_gpio = data->enable_gpio;
-	pb->enable_gpio_flags = data->enable_gpio_flags;
 	pb->notify = data->notify;
 	pb->notify_after = data->notify_after;
 	pb->check_fb = data->check_fb;
@@ -265,26 +245,38 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	pb->dev = &pdev->dev;
 	pb->enabled = false;
 
-	if (gpio_is_valid(pb->enable_gpio)) {
-		unsigned long flags;
-
-		if (pb->enable_gpio_flags & PWM_BACKLIGHT_GPIO_ACTIVE_LOW)
-			flags = GPIOF_OUT_INIT_HIGH;
+	pb->enable_gpio = devm_gpiod_get(&pdev->dev, "enable");
+	if (IS_ERR(pb->enable_gpio)) {
+		ret = PTR_ERR(pb->enable_gpio);
+		if (ret == -ENOENT)
+			pb->enable_gpio = NULL;
 		else
-			flags = GPIOF_OUT_INIT_LOW;
+			goto err_alloc;
+	}
 
-		ret = gpio_request_one(pb->enable_gpio, flags, "enable");
+	/*
+	 * Compatibility fallback for drivers still using the integer GPIO
+	 * platform data. Must go away soon.
+	 */
+	if (!pb->enable_gpio && gpio_is_valid(data->enable_gpio)) {
+		ret = devm_gpio_request_one(&pdev->dev, data->enable_gpio,
+					    GPIOF_OUT_INIT_HIGH, "enable");
 		if (ret < 0) {
 			dev_err(&pdev->dev, "failed to request GPIO#%d: %d\n",
-				pb->enable_gpio, ret);
+				data->enable_gpio, ret);
 			goto err_alloc;
 		}
+
+		pb->enable_gpio = gpio_to_desc(data->enable_gpio);
 	}
 
+	if (pb->enable_gpio)
+		gpiod_direction_output(pb->enable_gpio, 1);
+
 	pb->power_supply = devm_regulator_get(&pdev->dev, "power");
 	if (IS_ERR(pb->power_supply)) {
 		ret = PTR_ERR(pb->power_supply);
-		goto err_gpio;
+		goto err_alloc;
 	}
 
 	pb->pwm = devm_pwm_get(&pdev->dev, NULL);
@@ -295,7 +287,7 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 		if (IS_ERR(pb->pwm)) {
 			dev_err(&pdev->dev, "unable to request legacy PWM\n");
 			ret = PTR_ERR(pb->pwm);
-			goto err_gpio;
+			goto err_alloc;
 		}
 	}
 
@@ -304,12 +296,15 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	/*
 	 * The DT case will set the pwm_period_ns field to 0 and store the
 	 * period, parsed from the DT, in the PWM device. For the non-DT case,
-	 * set the period from platform data.
+	 * set the period from platform data if it has not already been set
+	 * via the PWM lookup table.
 	 */
-	if (data->pwm_period_ns > 0)
+	pb->period = pwm_get_period(pb->pwm);
+	if (!pb->period && (data->pwm_period_ns > 0)) {
+		pb->period = data->pwm_period_ns;
 		pwm_set_period(pb->pwm, data->pwm_period_ns);
+	}
 
-	pb->period = pwm_get_period(pb->pwm);
 	pb->lth_brightness = data->lth_brightness * (pb->period / pb->scale);
 
 	memset(&props, 0, sizeof(struct backlight_properties));
@@ -320,7 +315,7 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	if (IS_ERR(bl)) {
 		dev_err(&pdev->dev, "failed to register backlight\n");
 		ret = PTR_ERR(bl);
-		goto err_gpio;
+		goto err_alloc;
 	}
 
 	if (data->dft_brightness > data->max_brightness) {
@@ -336,9 +331,6 @@ static int pwm_backlight_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, bl);
 	return 0;
 
-err_gpio:
-	if (gpio_is_valid(pb->enable_gpio))
-		gpio_free(pb->enable_gpio);
 err_alloc:
 	if (data->exit)
 		data->exit(&pdev->dev);
@@ -359,6 +351,14 @@ static int pwm_backlight_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static void pwm_backlight_shutdown(struct platform_device *pdev)
+{
+	struct backlight_device *bl = platform_get_drvdata(pdev);
+	struct pwm_bl_data *pb = bl_get_data(bl);
+
+	pwm_backlight_power_off(pb);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int pwm_backlight_suspend(struct device *dev)
 {
@@ -404,6 +404,7 @@ static struct platform_driver pwm_backlight_driver = {
 	},
 	.probe		= pwm_backlight_probe,
 	.remove		= pwm_backlight_remove,
+	.shutdown	= pwm_backlight_shutdown,
 };
 
 module_platform_driver(pwm_backlight_driver);
diff --git a/drivers/video/backlight/s6e63m0.c b/drivers/video/backlight/s6e63m0.c
index 510a1bcf76f..2d6d48196c6 100644
--- a/drivers/video/backlight/s6e63m0.c
+++ b/drivers/video/backlight/s6e63m0.c
@@ -703,7 +703,7 @@ static ssize_t s6e63m0_sysfs_show_gamma_table(struct device *dev,
 	struct s6e63m0 *lcd = dev_get_drvdata(dev);
 	char temp[3];
 
-	sprintf(temp, "%d\n", lcd->gamma_table_count);
+	sprintf(temp, "%u\n", lcd->gamma_table_count);
 	strcpy(buf, temp);
 
 	return strlen(buf);
diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c
index b63860f7bea..40bec8d64b0 100644
--- a/drivers/video/console/dummycon.c
+++ b/drivers/video/console/dummycon.c
@@ -77,3 +77,4 @@ const struct consw dummy_con = {
     .con_set_palette =	DUMMY,
     .con_scrolldelta =	DUMMY,
 };
+EXPORT_SYMBOL_GPL(dummy_con);
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index f267284b423..6e6aa704fe8 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -1441,5 +1441,6 @@ const struct consw vga_con = {
 	.con_build_attr = vgacon_build_attr,
 	.con_invert_region = vgacon_invert_region,
 };
+EXPORT_SYMBOL(vga_con);
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c
index e683b6ef959..d36e830d6fc 100644
--- a/drivers/video/fbdev/atmel_lcdfb.c
+++ b/drivers/video/fbdev/atmel_lcdfb.c
@@ -1057,6 +1057,7 @@ static int atmel_lcdfb_of_init(struct atmel_lcdfb_info *sinfo)
 		goto put_display_node;
 	}
 
+	INIT_LIST_HEAD(&pdata->pwr_gpios);
 	ret = -ENOMEM;
 	for (i = 0; i < of_gpio_named_count(display_np, "atmel,power-control-gpio"); i++) {
 		gpio = of_get_named_gpio_flags(display_np, "atmel,power-control-gpio",
@@ -1082,6 +1083,7 @@ static int atmel_lcdfb_of_init(struct atmel_lcdfb_info *sinfo)
 			dev_err(dev, "set direction output gpio %d failed\n", gpio);
 			goto put_display_node;
 		}
+		list_add(&og->list, &pdata->pwr_gpios);
 	}
 
 	if (is_gpio_power)
diff --git a/drivers/video/fbdev/bfin_adv7393fb.c b/drivers/video/fbdev/bfin_adv7393fb.c
index a54f7f7d763..8fe41caac38 100644
--- a/drivers/video/fbdev/bfin_adv7393fb.c
+++ b/drivers/video/fbdev/bfin_adv7393fb.c
@@ -408,7 +408,7 @@ static int bfin_adv7393_fb_probe(struct i2c_client *client,
 	/* Workaround "PPI Does Not Start Properly In Specific Mode" */
 	if (ANOMALY_05000400) {
 		ret = gpio_request_one(P_IDENT(P_PPI0_FS3), GPIOF_OUT_INIT_LOW,
-					"PPI0_FS3")
+					"PPI0_FS3");
 		if (ret) {
 			dev_err(&client->dev, "PPI0_FS3 GPIO request failed\n");
 			ret = -EBUSY;
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index ae9618ff673..982f6abe6fa 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -19,8 +19,6 @@
 
 static bool request_mem_succeeded = false;
 
-static struct pci_dev *default_vga;
-
 static struct fb_var_screeninfo efifb_defined = {
 	.activate		= FB_ACTIVATE_NOW,
 	.height			= -1,
@@ -84,23 +82,10 @@ static struct fb_ops efifb_ops = {
 	.fb_imageblit	= cfb_imageblit,
 };
 
-struct pci_dev *vga_default_device(void)
-{
-	return default_vga;
-}
-
-EXPORT_SYMBOL_GPL(vga_default_device);
-
-void vga_set_default_device(struct pci_dev *pdev)
-{
-	default_vga = pdev;
-}
-
 static int efifb_setup(char *options)
 {
 	char *this_opt;
 	int i;
-	struct pci_dev *dev = NULL;
 
 	if (options && *options) {
 		while ((this_opt = strsep(&options, ",")) != NULL) {
@@ -126,30 +111,6 @@ static int efifb_setup(char *options)
 		}
 	}
 
-	for_each_pci_dev(dev) {
-		int i;
-
-		if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA)
-			continue;
-
-		for (i=0; i < DEVICE_COUNT_RESOURCE; i++) {
-			resource_size_t start, end;
-
-			if (!(pci_resource_flags(dev, i) & IORESOURCE_MEM))
-				continue;
-
-			start = pci_resource_start(dev, i);
-			end  = pci_resource_end(dev, i);
-
-			if (!start || !end)
-				continue;
-
-			if (screen_info.lfb_base >= start &&
-			    (screen_info.lfb_base + screen_info.lfb_size) < end)
-				default_vga = dev;
-		}
-	}
-
 	return 0;
 }
 
diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c
index 7d44d669d5b..43a0a52fc52 100644
--- a/drivers/video/fbdev/offb.c
+++ b/drivers/video/fbdev/offb.c
@@ -91,15 +91,6 @@ extern boot_infos_t *boot_infos;
 #define AVIVO_DC_LUTB_WHITE_OFFSET_GREEN        0x6cd4
 #define AVIVO_DC_LUTB_WHITE_OFFSET_RED          0x6cd8
 
-#define FB_RIGHT_POS(p, bpp)         (fb_be_math(p) ? 0 : (32 - (bpp)))
-
-static inline u32 offb_cmap_byteswap(struct fb_info *info, u32 value)
-{
-	u32 bpp = info->var.bits_per_pixel;
-
-	return cpu_to_be32(value) >> FB_RIGHT_POS(info, bpp);
-}
-
     /*
      *  Set a single color register. The values supplied are already
      *  rounded down to the hardware's capabilities (according to the
@@ -129,7 +120,7 @@ static int offb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 			mask <<= info->var.transp.offset;
 			value |= mask;
 		}
-		pal[regno] = offb_cmap_byteswap(info, value);
+		pal[regno] = value;
 		return 0;
 	}
 
diff --git a/drivers/video/fbdev/omap2/dss/omapdss-boot-init.c b/drivers/video/fbdev/omap2/dss/omapdss-boot-init.c
index 99af9e88b2d..2f0822ee3ff 100644
--- a/drivers/video/fbdev/omap2/dss/omapdss-boot-init.c
+++ b/drivers/video/fbdev/omap2/dss/omapdss-boot-init.c
@@ -121,9 +121,11 @@ static void __init omapdss_add_to_list(struct device_node *node, bool root)
 {
 	struct dss_conv_node *n = kmalloc(sizeof(struct dss_conv_node),
 		GFP_KERNEL);
-	n->node = node;
-	n->root = root;
-	list_add(&n->list, &dss_conv_list);
+	if (n) {
+		n->node = node;
+		n->root = root;
+		list_add(&n->list, &dss_conv_list);
+	}
 }
 
 static bool __init omapdss_list_contains(const struct device_node *node)
diff --git a/drivers/video/fbdev/sm501fb.c b/drivers/video/fbdev/sm501fb.c
index 1501979099d..c2c8eb66878 100644
--- a/drivers/video/fbdev/sm501fb.c
+++ b/drivers/video/fbdev/sm501fb.c
@@ -1215,7 +1215,7 @@ static ssize_t sm501fb_crtsrc_store(struct device *dev,
 }
 
 /* Prepare the device_attr for registration with sysfs later */
-static DEVICE_ATTR(crt_src, 0666, sm501fb_crtsrc_show, sm501fb_crtsrc_store);
+static DEVICE_ATTR(crt_src, 0664, sm501fb_crtsrc_show, sm501fb_crtsrc_store);
 
 /* sm501fb_show_regs
  *
diff --git a/drivers/video/fbdev/vt8500lcdfb.c b/drivers/video/fbdev/vt8500lcdfb.c
index a8f2b280f79..a1134c3f6c1 100644
--- a/drivers/video/fbdev/vt8500lcdfb.c
+++ b/drivers/video/fbdev/vt8500lcdfb.c
@@ -474,8 +474,6 @@ static int vt8500lcd_remove(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	release_mem_region(res->start, resource_size(res));
 
-	kfree(fbi);
-
 	return 0;
 }
 
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 1e443629f76..4d08f45a9c2 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -865,4 +865,19 @@ bool virtqueue_is_broken(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_is_broken);
 
+/*
+ * This should prevent the device from being used, allowing drivers to
+ * recover.  You may need to grab appropriate locks to flush.
+ */
+void virtio_break_device(struct virtio_device *dev)
+{
+	struct virtqueue *_vq;
+
+	list_for_each_entry(_vq, &dev->vqs, list) {
+		struct vring_virtqueue *vq = to_vvq(_vq);
+		vq->broken = true;
+	}
+}
+EXPORT_SYMBOL_GPL(virtio_break_device);
+
 MODULE_LICENSE("GPL");
diff --git a/drivers/w1/masters/mxc_w1.c b/drivers/w1/masters/mxc_w1.c
index 67b067a3e2a..a5df5e89d45 100644
--- a/drivers/w1/masters/mxc_w1.c
+++ b/drivers/w1/masters/mxc_w1.c
@@ -66,7 +66,7 @@ static u8 mxc_w1_ds2_reset_bus(void *data)
 
 		udelay(100);
 	}
-	return !!(reg_val & MXC_W1_CONTROL_PST);
+	return !(reg_val & MXC_W1_CONTROL_PST);
 }
 
 /*
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 74ec8fc5cc0..76dd54122f7 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -272,7 +272,7 @@ config PNX4008_WATCHDOG
 
 config IOP_WATCHDOG
 	tristate "IOP Watchdog"
-	depends on PLAT_IOP
+	depends on ARCH_IOP13XX
 	select WATCHDOG_NOWAYOUT if (ARCH_IOP32X || ARCH_IOP33X)
 	help
 	  Say Y here if to include support for the watchdog timer
@@ -378,6 +378,8 @@ config MAX63XX_WATCHDOG
 config IMX2_WDT
 	tristate "IMX2+ Watchdog"
 	depends on ARCH_MXC
+	select REGMAP_MMIO
+	select WATCHDOG_CORE
 	help
 	  This is the driver for the hardware watchdog
 	  on the Freescale IMX2 and later processors.
@@ -663,6 +665,19 @@ config INTEL_SCU_WATCHDOG
 
 	  To compile this driver as a module, choose M here.
 
+config INTEL_MID_WATCHDOG
+	tristate "Intel MID Watchdog Timer"
+	depends on X86_INTEL_MID
+	select WATCHDOG_CORE
+	---help---
+	  Watchdog timer driver built into the Intel SCU for Intel MID
+	  Platforms.
+
+	  This driver currently supports only the watchdog evolution
+	  implementation in SCU, available for Merrifield generation.
+
+	  To compile this driver as a module, choose M here.
+
 config ITCO_WDT
 	tristate "Intel TCO Timer/Watchdog"
 	depends on (X86 || IA64) && PCI
@@ -835,7 +850,7 @@ config 60XX_WDT
 
 config SBC8360_WDT
 	tristate "SBC8360 Watchdog Timer"
-	depends on X86
+	depends on X86_32
 	---help---
 
 	  This is the driver for the hardware watchdog on the SBC8360 Single
@@ -938,36 +953,6 @@ config W83627HF_WDT
 
 	  Most people will say N.
 
-config W83697HF_WDT
-	tristate "W83697HF/W83697HG Watchdog Timer"
-	depends on X86
-	---help---
-	  This is the driver for the hardware watchdog on the W83697HF/HG
-	  chipset as used in Dedibox/VIA motherboards (and likely others).
-	  This watchdog simply watches your kernel to make sure it doesn't
-	  freeze, and if it does, it reboots your computer after a certain
-	  amount of time.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called w83697hf_wdt.
-
-	  Most people will say N.
-
-config W83697UG_WDT
-	tristate "W83697UG/W83697UF Watchdog Timer"
-	depends on X86
-	---help---
-	  This is the driver for the hardware watchdog on the W83697UG/UF
-	  chipset as used in MSI Fuzzy CX700 VIA motherboards (and likely others).
-	  This watchdog simply watches your kernel to make sure it doesn't
-	  freeze, and if it does, it reboots your computer after a certain
-	  amount of time.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called w83697ug_wdt.
-
-	  Most people will say N.
-
 config W83877F_WDT
 	tristate "W83877F (EMACS) Watchdog Timer"
 	depends on X86
@@ -1295,14 +1280,17 @@ config WATCHDOG_RTAS
 
 # S390 Architecture
 
-config ZVM_WATCHDOG
-	tristate "z/VM Watchdog Timer"
+config DIAG288_WATCHDOG
+	tristate "System z diag288 Watchdog"
 	depends on S390
+	select WATCHDOG_CORE
 	help
 	  IBM s/390 and zSeries machines running under z/VM 5.1 or later
 	  provide a virtual watchdog timer to their guest that cause a
 	  user define Control Program command to be executed after a
 	  timeout.
+	  LPAR provides a very similar interface. This driver handles
+	  both.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called vmwatchdog.
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 1b5f3d5efad..468c3204c3b 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -107,13 +107,12 @@ obj-$(CONFIG_SMSC_SCH311X_WDT) += sch311x_wdt.o
 obj-$(CONFIG_SMSC37B787_WDT) += smsc37b787_wdt.o
 obj-$(CONFIG_VIA_WDT) += via_wdt.o
 obj-$(CONFIG_W83627HF_WDT) += w83627hf_wdt.o
-obj-$(CONFIG_W83697HF_WDT) += w83697hf_wdt.o
-obj-$(CONFIG_W83697UG_WDT) += w83697ug_wdt.o
 obj-$(CONFIG_W83877F_WDT) += w83877f_wdt.o
 obj-$(CONFIG_W83977F_WDT) += w83977f_wdt.o
 obj-$(CONFIG_MACHZ_WDT) += machzwd.o
 obj-$(CONFIG_SBC_EPX_C3_WATCHDOG) += sbc_epx_c3.o
 obj-$(CONFIG_INTEL_SCU_WATCHDOG) += intel_scu_watchdog.o
+obj-$(CONFIG_INTEL_MID_WATCHDOG) += intel-mid_wdt.o
 
 # M32R Architecture
 
@@ -154,6 +153,7 @@ obj-$(CONFIG_MEN_A21_WDT) += mena21_wdt.o
 obj-$(CONFIG_WATCHDOG_RTAS) += wdrtas.o
 
 # S390 Architecture
+obj-$(CONFIG_DIAG288_WATCHDOG) += diag288_wdt.o
 
 # SUPERH (sh + sh64) Architecture
 obj-$(CONFIG_SH_WDT) += shwdt.o
diff --git a/drivers/watchdog/ath79_wdt.c b/drivers/watchdog/ath79_wdt.c
index 399c3fddecf..41ac4660fb8 100644
--- a/drivers/watchdog/ath79_wdt.c
+++ b/drivers/watchdog/ath79_wdt.c
@@ -20,6 +20,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/bitops.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/io.h>
@@ -90,6 +91,15 @@ static inline void ath79_wdt_keepalive(void)
 static inline void ath79_wdt_enable(void)
 {
 	ath79_wdt_keepalive();
+
+	/*
+	 * Updating the TIMER register requires a few microseconds
+	 * on the AR934x SoCs at least. Use a small delay to ensure
+	 * that the TIMER register is updated within the hardware
+	 * before enabling the watchdog.
+	 */
+	udelay(2);
+
 	ath79_wdt_wr(WDOG_REG_CTRL, WDOG_CTRL_ACTION_FCR);
 	/* flush write */
 	ath79_wdt_rr(WDOG_REG_CTRL);
@@ -255,7 +265,7 @@ static int ath79_wdt_probe(struct platform_device *pdev)
 	if (IS_ERR(wdt_clk))
 		return PTR_ERR(wdt_clk);
 
-	err = clk_enable(wdt_clk);
+	err = clk_prepare_enable(wdt_clk);
 	if (err)
 		return err;
 
@@ -286,14 +296,14 @@ static int ath79_wdt_probe(struct platform_device *pdev)
 	return 0;
 
 err_clk_disable:
-	clk_disable(wdt_clk);
+	clk_disable_unprepare(wdt_clk);
 	return err;
 }
 
 static int ath79_wdt_remove(struct platform_device *pdev)
 {
 	misc_deregister(&ath79_wdt_miscdev);
-	clk_disable(wdt_clk);
+	clk_disable_unprepare(wdt_clk);
 	return 0;
 }
 
diff --git a/drivers/watchdog/booke_wdt.c b/drivers/watchdog/booke_wdt.c
index a8dbceb3291..08a785398ea 100644
--- a/drivers/watchdog/booke_wdt.c
+++ b/drivers/watchdog/booke_wdt.c
@@ -41,6 +41,28 @@ u32 booke_wdt_period = CONFIG_BOOKE_WDT_DEFAULT_TIMEOUT;
 #define WDTP_MASK	(TCR_WP_MASK)
 #endif
 
+/* Checks wdt=x and wdt_period=xx command-line option */
+notrace int __init early_parse_wdt(char *p)
+{
+	if (p && strncmp(p, "0", 1) != 0)
+		booke_wdt_enabled = 1;
+
+	return 0;
+}
+early_param("wdt", early_parse_wdt);
+
+int __init early_parse_wdt_period(char *p)
+{
+	unsigned long ret;
+	if (p) {
+		if (!kstrtol(p, 0, &ret))
+			booke_wdt_period = ret;
+	}
+
+	return 0;
+}
+early_param("wdt_period", early_parse_wdt_period);
+
 #ifdef CONFIG_PPC_FSL_BOOK3E
 
 /* For the specified period, determine the number of seconds
@@ -103,17 +125,18 @@ static unsigned int sec_to_period(unsigned int secs)
 static void __booke_wdt_set(void *data)
 {
 	u32 val;
+	struct watchdog_device *wdog = data;
 
 	val = mfspr(SPRN_TCR);
 	val &= ~WDTP_MASK;
-	val |= WDTP(booke_wdt_period);
+	val |= WDTP(sec_to_period(wdog->timeout));
 
 	mtspr(SPRN_TCR, val);
 }
 
-static void booke_wdt_set(void)
+static void booke_wdt_set(void *data)
 {
-	on_each_cpu(__booke_wdt_set, NULL, 0);
+	on_each_cpu(__booke_wdt_set, data, 0);
 }
 
 static void __booke_wdt_ping(void *data)
@@ -131,12 +154,13 @@ static int booke_wdt_ping(struct watchdog_device *wdog)
 static void __booke_wdt_enable(void *data)
 {
 	u32 val;
+	struct watchdog_device *wdog = data;
 
 	/* clear status before enabling watchdog */
 	__booke_wdt_ping(NULL);
 	val = mfspr(SPRN_TCR);
 	val &= ~WDTP_MASK;
-	val |= (TCR_WIE|TCR_WRC(WRC_CHIP)|WDTP(booke_wdt_period));
+	val |= (TCR_WIE|TCR_WRC(WRC_CHIP)|WDTP(sec_to_period(wdog->timeout)));
 
 	mtspr(SPRN_TCR, val);
 }
@@ -162,25 +186,17 @@ static void __booke_wdt_disable(void *data)
 
 }
 
-static void __booke_wdt_start(struct watchdog_device *wdog)
+static int booke_wdt_start(struct watchdog_device *wdog)
 {
-	on_each_cpu(__booke_wdt_enable, NULL, 0);
+	on_each_cpu(__booke_wdt_enable, wdog, 0);
 	pr_debug("watchdog enabled (timeout = %u sec)\n", wdog->timeout);
-}
 
-static int booke_wdt_start(struct watchdog_device *wdog)
-{
-	if (booke_wdt_enabled == 0) {
-		booke_wdt_enabled = 1;
-		__booke_wdt_start(wdog);
-	}
 	return 0;
 }
 
 static int booke_wdt_stop(struct watchdog_device *wdog)
 {
 	on_each_cpu(__booke_wdt_disable, NULL, 0);
-	booke_wdt_enabled = 0;
 	pr_debug("watchdog disabled\n");
 
 	return 0;
@@ -191,9 +207,8 @@ static int booke_wdt_set_timeout(struct watchdog_device *wdt_dev,
 {
 	if (timeout > MAX_WDT_TIMEOUT)
 		return -EINVAL;
-	booke_wdt_period = sec_to_period(timeout);
 	wdt_dev->timeout = timeout;
-	booke_wdt_set();
+	booke_wdt_set(wdt_dev);
 
 	return 0;
 }
@@ -231,10 +246,10 @@ static int __init booke_wdt_init(void)
 	pr_info("powerpc book-e watchdog driver loaded\n");
 	booke_wdt_info.firmware_version = cur_cpu_spec->pvr_value;
 	booke_wdt_set_timeout(&booke_wdt_dev,
-			      period_to_sec(CONFIG_BOOKE_WDT_DEFAULT_TIMEOUT));
+			      period_to_sec(booke_wdt_period));
 	watchdog_set_nowayout(&booke_wdt_dev, nowayout);
 	if (booke_wdt_enabled)
-		__booke_wdt_start(&booke_wdt_dev);
+		booke_wdt_start(&booke_wdt_dev);
 
 	ret = watchdog_register_device(&booke_wdt_dev);
 
diff --git a/drivers/watchdog/diag288_wdt.c b/drivers/watchdog/diag288_wdt.c
new file mode 100644
index 00000000000..429494b6c82
--- /dev/null
+++ b/drivers/watchdog/diag288_wdt.c
@@ -0,0 +1,316 @@
+/*
+ * Watchdog driver for z/VM and LPAR using the diag 288 interface.
+ *
+ * Under z/VM, expiration of the watchdog will send a "system restart" command
+ * to CP.
+ *
+ * The command can be altered using the module parameter "cmd". This is
+ * not recommended because it's only supported on z/VM but not whith LPAR.
+ *
+ * On LPAR, the watchdog will always trigger a system restart. the module
+ * paramter cmd is meaningless here.
+ *
+ *
+ * Copyright IBM Corp. 2004, 2013
+ * Author(s): Arnd Bergmann (arndb@de.ibm.com)
+ *	      Philipp Hachtmann (phacht@de.ibm.com)
+ *
+ */
+
+#define KMSG_COMPONENT "diag288_wdt"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/miscdevice.h>
+#include <linux/watchdog.h>
+#include <linux/suspend.h>
+#include <asm/ebcdic.h>
+#include <linux/io.h>
+#include <linux/uaccess.h>
+
+#define MAX_CMDLEN 240
+#define DEFAULT_CMD "SYSTEM RESTART"
+
+#define MIN_INTERVAL 15     /* Minimal time supported by diag88 */
+#define MAX_INTERVAL 3600   /* One hour should be enough - pure estimation */
+
+#define WDT_DEFAULT_TIMEOUT 30
+
+/* Function codes - init, change, cancel */
+#define WDT_FUNC_INIT 0
+#define WDT_FUNC_CHANGE 1
+#define WDT_FUNC_CANCEL 2
+#define WDT_FUNC_CONCEAL 0x80000000
+
+/* Action codes for LPAR watchdog */
+#define LPARWDT_RESTART 0
+
+static char wdt_cmd[MAX_CMDLEN] = DEFAULT_CMD;
+static bool conceal_on;
+static bool nowayout_info = WATCHDOG_NOWAYOUT;
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arnd Bergmann <arndb@de.ibm.com>");
+MODULE_AUTHOR("Philipp Hachtmann <phacht@de.ibm.com>");
+
+MODULE_DESCRIPTION("System z diag288  Watchdog Timer");
+
+module_param_string(cmd, wdt_cmd, MAX_CMDLEN, 0644);
+MODULE_PARM_DESC(cmd, "CP command that is run when the watchdog triggers (z/VM only)");
+
+module_param_named(conceal, conceal_on, bool, 0644);
+MODULE_PARM_DESC(conceal, "Enable the CONCEAL CP option while the watchdog is active (z/VM only)");
+
+module_param_named(nowayout, nowayout_info, bool, 0444);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default = CONFIG_WATCHDOG_NOWAYOUT)");
+
+MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
+MODULE_ALIAS("vmwatchdog");
+
+static int __diag288(unsigned int func, unsigned int timeout,
+		     unsigned long action, unsigned int len)
+{
+	register unsigned long __func asm("2") = func;
+	register unsigned long __timeout asm("3") = timeout;
+	register unsigned long __action asm("4") = action;
+	register unsigned long __len asm("5") = len;
+	int err;
+
+	err = -EINVAL;
+	asm volatile(
+		"	diag	%1, %3, 0x288\n"
+		"0:	la	%0, 0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: "+d" (err) : "d"(__func), "d"(__timeout),
+		  "d"(__action), "d"(__len) : "1", "cc");
+	return err;
+}
+
+static int __diag288_vm(unsigned int  func, unsigned int timeout,
+			char *cmd, size_t len)
+{
+	return __diag288(func, timeout, virt_to_phys(cmd), len);
+}
+
+static int __diag288_lpar(unsigned int func, unsigned int timeout,
+			  unsigned long action)
+{
+	return __diag288(func, timeout, action, 0);
+}
+
+static int wdt_start(struct watchdog_device *dev)
+{
+	char *ebc_cmd;
+	size_t len;
+	int ret;
+	unsigned int func;
+
+	ret = -ENODEV;
+
+	if (MACHINE_IS_VM) {
+		ebc_cmd = kmalloc(MAX_CMDLEN, GFP_KERNEL);
+		if (!ebc_cmd)
+			return -ENOMEM;
+		len = strlcpy(ebc_cmd, wdt_cmd, MAX_CMDLEN);
+		ASCEBC(ebc_cmd, MAX_CMDLEN);
+		EBC_TOUPPER(ebc_cmd, MAX_CMDLEN);
+
+		func = conceal_on ? (WDT_FUNC_INIT | WDT_FUNC_CONCEAL)
+			: WDT_FUNC_INIT;
+		ret = __diag288_vm(func, dev->timeout, ebc_cmd, len);
+		WARN_ON(ret != 0);
+		kfree(ebc_cmd);
+	}
+
+	if (MACHINE_IS_LPAR) {
+		ret = __diag288_lpar(WDT_FUNC_INIT,
+				     dev->timeout, LPARWDT_RESTART);
+	}
+
+	if (ret) {
+		pr_err("The watchdog cannot be activated\n");
+		return ret;
+	}
+	pr_info("The watchdog was activated\n");
+	return 0;
+}
+
+static int wdt_stop(struct watchdog_device *dev)
+{
+	int ret;
+
+	ret = __diag288(WDT_FUNC_CANCEL, 0, 0, 0);
+	pr_info("The watchdog was deactivated\n");
+	return ret;
+}
+
+static int wdt_ping(struct watchdog_device *dev)
+{
+	char *ebc_cmd;
+	size_t len;
+	int ret;
+	unsigned int func;
+
+	ret = -ENODEV;
+
+	if (MACHINE_IS_VM) {
+		ebc_cmd = kmalloc(MAX_CMDLEN, GFP_KERNEL);
+		if (!ebc_cmd)
+			return -ENOMEM;
+		len = strlcpy(ebc_cmd, wdt_cmd, MAX_CMDLEN);
+		ASCEBC(ebc_cmd, MAX_CMDLEN);
+		EBC_TOUPPER(ebc_cmd, MAX_CMDLEN);
+
+		/*
+		 * It seems to be ok to z/VM to use the init function to
+		 * retrigger the watchdog. On LPAR WDT_FUNC_CHANGE must
+		 * be used when the watchdog is running.
+		 */
+		func = conceal_on ? (WDT_FUNC_INIT | WDT_FUNC_CONCEAL)
+			: WDT_FUNC_INIT;
+
+		ret = __diag288_vm(func, dev->timeout, ebc_cmd, len);
+		WARN_ON(ret != 0);
+		kfree(ebc_cmd);
+	}
+
+	if (MACHINE_IS_LPAR)
+		ret = __diag288_lpar(WDT_FUNC_CHANGE, dev->timeout, 0);
+
+	if (ret)
+		pr_err("The watchdog timer cannot be started or reset\n");
+	return ret;
+}
+
+static int wdt_set_timeout(struct watchdog_device * dev, unsigned int new_to)
+{
+	dev->timeout = new_to;
+	return wdt_ping(dev);
+}
+
+static struct watchdog_ops wdt_ops = {
+	.owner = THIS_MODULE,
+	.start = wdt_start,
+	.stop = wdt_stop,
+	.ping = wdt_ping,
+	.set_timeout = wdt_set_timeout,
+};
+
+static struct watchdog_info wdt_info = {
+	.options = WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE,
+	.firmware_version = 0,
+	.identity = "z Watchdog",
+};
+
+static struct watchdog_device wdt_dev = {
+	.parent = NULL,
+	.info = &wdt_info,
+	.ops = &wdt_ops,
+	.bootstatus = 0,
+	.timeout = WDT_DEFAULT_TIMEOUT,
+	.min_timeout = MIN_INTERVAL,
+	.max_timeout = MAX_INTERVAL,
+};
+
+/*
+ * It makes no sense to go into suspend while the watchdog is running.
+ * Depending on the memory size, the watchdog might trigger, while we
+ * are still saving the memory.
+ * We reuse the open flag to ensure that suspend and watchdog open are
+ * exclusive operations
+ */
+static int wdt_suspend(void)
+{
+	if (test_and_set_bit(WDOG_DEV_OPEN, &wdt_dev.status)) {
+		pr_err("Linux cannot be suspended while the watchdog is in use\n");
+		return notifier_from_errno(-EBUSY);
+	}
+	if (test_bit(WDOG_ACTIVE, &wdt_dev.status)) {
+		clear_bit(WDOG_DEV_OPEN, &wdt_dev.status);
+		pr_err("Linux cannot be suspended while the watchdog is in use\n");
+		return notifier_from_errno(-EBUSY);
+	}
+	return NOTIFY_DONE;
+}
+
+static int wdt_resume(void)
+{
+	clear_bit(WDOG_DEV_OPEN, &wdt_dev.status);
+	return NOTIFY_DONE;
+}
+
+static int wdt_power_event(struct notifier_block *this, unsigned long event,
+			   void *ptr)
+{
+	switch (event) {
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		return wdt_resume();
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		return wdt_suspend();
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static struct notifier_block wdt_power_notifier = {
+	.notifier_call = wdt_power_event,
+};
+
+static int __init diag288_init(void)
+{
+	int ret;
+	char ebc_begin[] = {
+		194, 197, 199, 201, 213
+	};
+
+	watchdog_set_nowayout(&wdt_dev, nowayout_info);
+
+	if (MACHINE_IS_VM) {
+		pr_info("The watchdog device driver detected a z/VM environment\n");
+		if (__diag288_vm(WDT_FUNC_INIT, 15,
+				 ebc_begin, sizeof(ebc_begin)) != 0) {
+			pr_err("The watchdog cannot be initialized\n");
+			return -EINVAL;
+		}
+	} else if (MACHINE_IS_LPAR) {
+		pr_info("The watchdog device driver detected an LPAR environment\n");
+		if (__diag288_lpar(WDT_FUNC_INIT, 30, LPARWDT_RESTART)) {
+			pr_err("The watchdog cannot be initialized\n");
+			return -EINVAL;
+		}
+	} else {
+		pr_err("Linux runs in an environment that does not support the diag288 watchdog\n");
+		return -ENODEV;
+	}
+
+	if (__diag288_lpar(WDT_FUNC_CANCEL, 0, 0)) {
+		pr_err("The watchdog cannot be deactivated\n");
+		return -EINVAL;
+	}
+
+	ret = register_pm_notifier(&wdt_power_notifier);
+	if (ret)
+		return ret;
+
+	ret = watchdog_register_device(&wdt_dev);
+	if (ret)
+		unregister_pm_notifier(&wdt_power_notifier);
+
+	return ret;
+}
+
+static void __exit diag288_exit(void)
+{
+	watchdog_unregister_device(&wdt_dev);
+	unregister_pm_notifier(&wdt_power_notifier);
+}
+
+module_init(diag288_init);
+module_exit(diag288_exit);
diff --git a/drivers/watchdog/imx2_wdt.c b/drivers/watchdog/imx2_wdt.c
index dd51d9539b3..9d4874f0994 100644
--- a/drivers/watchdog/imx2_wdt.c
+++ b/drivers/watchdog/imx2_wdt.c
@@ -21,19 +21,17 @@
  * Halt on suspend:	Manual		Can be automatic
  */
 
+#include <linux/clk.h>
 #include <linux/init.h>
+#include <linux/io.h>
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
-#include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/platform_device.h>
-#include <linux/watchdog.h>
-#include <linux/clk.h>
-#include <linux/fs.h>
-#include <linux/io.h>
-#include <linux/uaccess.h>
+#include <linux/regmap.h>
 #include <linux/timer.h>
-#include <linux/jiffies.h>
+#include <linux/watchdog.h>
 
 #define DRIVER_NAME "imx2-wdt"
 
@@ -55,19 +53,12 @@
 
 #define WDOG_SEC_TO_COUNT(s)	((s * 2 - 1) << 8)
 
-#define IMX2_WDT_STATUS_OPEN	0
-#define IMX2_WDT_STATUS_STARTED	1
-#define IMX2_WDT_EXPECT_CLOSE	2
-
-static struct {
+struct imx2_wdt_device {
 	struct clk *clk;
-	void __iomem *base;
-	unsigned timeout;
-	unsigned long status;
+	struct regmap *regmap;
 	struct timer_list timer;	/* Pings the watchdog when closed */
-} imx2_wdt;
-
-static struct miscdevice imx2_wdt_miscdev;
+	struct watchdog_device wdog;
+};
 
 static bool nowayout = WATCHDOG_NOWAYOUT;
 module_param(nowayout, bool, 0);
@@ -85,9 +76,12 @@ static const struct watchdog_info imx2_wdt_info = {
 	.options = WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE,
 };
 
-static inline void imx2_wdt_setup(void)
+static inline void imx2_wdt_setup(struct watchdog_device *wdog)
 {
-	u16 val = __raw_readw(imx2_wdt.base + IMX2_WDT_WCR);
+	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
+	u32 val;
+
+	regmap_read(wdev->regmap, IMX2_WDT_WCR, &val);
 
 	/* Suspend timer in low power mode, write once-only */
 	val |= IMX2_WDT_WCR_WDZST;
@@ -98,227 +92,199 @@ static inline void imx2_wdt_setup(void)
 	/* Keep Watchdog Disabled */
 	val &= ~IMX2_WDT_WCR_WDE;
 	/* Set the watchdog's Time-Out value */
-	val |= WDOG_SEC_TO_COUNT(imx2_wdt.timeout);
+	val |= WDOG_SEC_TO_COUNT(wdog->timeout);
 
-	__raw_writew(val, imx2_wdt.base + IMX2_WDT_WCR);
+	regmap_write(wdev->regmap, IMX2_WDT_WCR, val);
 
 	/* enable the watchdog */
 	val |= IMX2_WDT_WCR_WDE;
-	__raw_writew(val, imx2_wdt.base + IMX2_WDT_WCR);
+	regmap_write(wdev->regmap, IMX2_WDT_WCR, val);
 }
 
-static inline void imx2_wdt_ping(void)
+static inline bool imx2_wdt_is_running(struct imx2_wdt_device *wdev)
 {
-	__raw_writew(IMX2_WDT_SEQ1, imx2_wdt.base + IMX2_WDT_WSR);
-	__raw_writew(IMX2_WDT_SEQ2, imx2_wdt.base + IMX2_WDT_WSR);
-}
+	u32 val;
 
-static void imx2_wdt_timer_ping(unsigned long arg)
-{
-	/* ping it every imx2_wdt.timeout / 2 seconds to prevent reboot */
-	imx2_wdt_ping();
-	mod_timer(&imx2_wdt.timer, jiffies + imx2_wdt.timeout * HZ / 2);
+	regmap_read(wdev->regmap, IMX2_WDT_WCR, &val);
+
+	return val & IMX2_WDT_WCR_WDE;
 }
 
-static void imx2_wdt_start(void)
+static int imx2_wdt_ping(struct watchdog_device *wdog)
 {
-	if (!test_and_set_bit(IMX2_WDT_STATUS_STARTED, &imx2_wdt.status)) {
-		/* at our first start we enable clock and do initialisations */
-		clk_prepare_enable(imx2_wdt.clk);
+	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
 
-		imx2_wdt_setup();
-	} else	/* delete the timer that pings the watchdog after close */
-		del_timer_sync(&imx2_wdt.timer);
-
-	/* Watchdog is enabled - time to reload the timeout value */
-	imx2_wdt_ping();
+	regmap_write(wdev->regmap, IMX2_WDT_WSR, IMX2_WDT_SEQ1);
+	regmap_write(wdev->regmap, IMX2_WDT_WSR, IMX2_WDT_SEQ2);
+	return 0;
 }
 
-static void imx2_wdt_stop(void)
+static void imx2_wdt_timer_ping(unsigned long arg)
 {
-	/* we don't need a clk_disable, it cannot be disabled once started.
-	 * We use a timer to ping the watchdog while /dev/watchdog is closed */
-	imx2_wdt_timer_ping(0);
+	struct watchdog_device *wdog = (struct watchdog_device *)arg;
+	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
+
+	/* ping it every wdog->timeout / 2 seconds to prevent reboot */
+	imx2_wdt_ping(wdog);
+	mod_timer(&wdev->timer, jiffies + wdog->timeout * HZ / 2);
 }
 
-static void imx2_wdt_set_timeout(int new_timeout)
+static int imx2_wdt_set_timeout(struct watchdog_device *wdog,
+				unsigned int new_timeout)
 {
-	u16 val = __raw_readw(imx2_wdt.base + IMX2_WDT_WCR);
+	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
 
-	/* set the new timeout value in the WSR */
-	val &= ~IMX2_WDT_WCR_WT;
-	val |= WDOG_SEC_TO_COUNT(new_timeout);
-	__raw_writew(val, imx2_wdt.base + IMX2_WDT_WCR);
+	regmap_update_bits(wdev->regmap, IMX2_WDT_WCR, IMX2_WDT_WCR_WT,
+			   WDOG_SEC_TO_COUNT(new_timeout));
+	return 0;
 }
 
-static int imx2_wdt_open(struct inode *inode, struct file *file)
+static int imx2_wdt_start(struct watchdog_device *wdog)
 {
-	if (test_and_set_bit(IMX2_WDT_STATUS_OPEN, &imx2_wdt.status))
-		return -EBUSY;
+	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
+
+	if (imx2_wdt_is_running(wdev)) {
+		/* delete the timer that pings the watchdog after close */
+		del_timer_sync(&wdev->timer);
+		imx2_wdt_set_timeout(wdog, wdog->timeout);
+	} else
+		imx2_wdt_setup(wdog);
 
-	imx2_wdt_start();
-	return nonseekable_open(inode, file);
+	return imx2_wdt_ping(wdog);
 }
 
-static int imx2_wdt_close(struct inode *inode, struct file *file)
+static int imx2_wdt_stop(struct watchdog_device *wdog)
 {
-	if (test_bit(IMX2_WDT_EXPECT_CLOSE, &imx2_wdt.status) && !nowayout)
-		imx2_wdt_stop();
-	else {
-		dev_crit(imx2_wdt_miscdev.parent,
-			"Unexpected close: Expect reboot!\n");
-		imx2_wdt_ping();
-	}
-
-	clear_bit(IMX2_WDT_EXPECT_CLOSE, &imx2_wdt.status);
-	clear_bit(IMX2_WDT_STATUS_OPEN, &imx2_wdt.status);
+	/*
+	 * We don't need a clk_disable, it cannot be disabled once started.
+	 * We use a timer to ping the watchdog while /dev/watchdog is closed
+	 */
+	imx2_wdt_timer_ping((unsigned long)wdog);
 	return 0;
 }
 
-static long imx2_wdt_ioctl(struct file *file, unsigned int cmd,
-							unsigned long arg)
+static inline void imx2_wdt_ping_if_active(struct watchdog_device *wdog)
 {
-	void __user *argp = (void __user *)arg;
-	int __user *p = argp;
-	int new_value;
-	u16 val;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		return copy_to_user(argp, &imx2_wdt_info,
-			sizeof(struct watchdog_info)) ? -EFAULT : 0;
-
-	case WDIOC_GETSTATUS:
-		return put_user(0, p);
-
-	case WDIOC_GETBOOTSTATUS:
-		val = __raw_readw(imx2_wdt.base + IMX2_WDT_WRSR);
-		new_value = val & IMX2_WDT_WRSR_TOUT ? WDIOF_CARDRESET : 0;
-		return put_user(new_value, p);
-
-	case WDIOC_KEEPALIVE:
-		imx2_wdt_ping();
-		return 0;
-
-	case WDIOC_SETTIMEOUT:
-		if (get_user(new_value, p))
-			return -EFAULT;
-		if ((new_value < 1) || (new_value > IMX2_WDT_MAX_TIME))
-			return -EINVAL;
-		imx2_wdt_set_timeout(new_value);
-		imx2_wdt.timeout = new_value;
-		imx2_wdt_ping();
-
-		/* Fallthrough to return current value */
-	case WDIOC_GETTIMEOUT:
-		return put_user(imx2_wdt.timeout, p);
-
-	default:
-		return -ENOTTY;
-	}
-}
+	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
 
-static ssize_t imx2_wdt_write(struct file *file, const char __user *data,
-						size_t len, loff_t *ppos)
-{
-	size_t i;
-	char c;
-
-	if (len == 0)	/* Can we see this even ? */
-		return 0;
-
-	clear_bit(IMX2_WDT_EXPECT_CLOSE, &imx2_wdt.status);
-	/* scan to see whether or not we got the magic character */
-	for (i = 0; i != len; i++) {
-		if (get_user(c, data + i))
-			return -EFAULT;
-		if (c == 'V')
-			set_bit(IMX2_WDT_EXPECT_CLOSE, &imx2_wdt.status);
+	if (imx2_wdt_is_running(wdev)) {
+		imx2_wdt_set_timeout(wdog, wdog->timeout);
+		imx2_wdt_timer_ping((unsigned long)wdog);
 	}
-
-	imx2_wdt_ping();
-	return len;
 }
 
-static const struct file_operations imx2_wdt_fops = {
+static struct watchdog_ops imx2_wdt_ops = {
 	.owner = THIS_MODULE,
-	.llseek = no_llseek,
-	.unlocked_ioctl = imx2_wdt_ioctl,
-	.open = imx2_wdt_open,
-	.release = imx2_wdt_close,
-	.write = imx2_wdt_write,
+	.start = imx2_wdt_start,
+	.stop = imx2_wdt_stop,
+	.ping = imx2_wdt_ping,
+	.set_timeout = imx2_wdt_set_timeout,
 };
 
-static struct miscdevice imx2_wdt_miscdev = {
-	.minor = WATCHDOG_MINOR,
-	.name = "watchdog",
-	.fops = &imx2_wdt_fops,
+static struct regmap_config imx2_wdt_regmap_config = {
+	.reg_bits = 16,
+	.reg_stride = 2,
+	.val_bits = 16,
+	.max_register = 0x8,
 };
 
 static int __init imx2_wdt_probe(struct platform_device *pdev)
 {
-	int ret;
+	struct imx2_wdt_device *wdev;
+	struct watchdog_device *wdog;
 	struct resource *res;
+	void __iomem *base;
+	int ret;
+	u32 val;
+
+	wdev = devm_kzalloc(&pdev->dev, sizeof(*wdev), GFP_KERNEL);
+	if (!wdev)
+		return -ENOMEM;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	imx2_wdt.base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(imx2_wdt.base))
-		return PTR_ERR(imx2_wdt.base);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	wdev->regmap = devm_regmap_init_mmio_clk(&pdev->dev, NULL, base,
+						 &imx2_wdt_regmap_config);
+	if (IS_ERR(wdev->regmap)) {
+		dev_err(&pdev->dev, "regmap init failed\n");
+		return PTR_ERR(wdev->regmap);
+	}
 
-	imx2_wdt.clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(imx2_wdt.clk)) {
+	wdev->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(wdev->clk)) {
 		dev_err(&pdev->dev, "can't get Watchdog clock\n");
-		return PTR_ERR(imx2_wdt.clk);
+		return PTR_ERR(wdev->clk);
 	}
 
-	imx2_wdt.timeout = clamp_t(unsigned, timeout, 1, IMX2_WDT_MAX_TIME);
-	if (imx2_wdt.timeout != timeout)
-		dev_warn(&pdev->dev, "Initial timeout out of range! "
-			"Clamped from %u to %u\n", timeout, imx2_wdt.timeout);
+	wdog			= &wdev->wdog;
+	wdog->info		= &imx2_wdt_info;
+	wdog->ops		= &imx2_wdt_ops;
+	wdog->min_timeout	= 1;
+	wdog->max_timeout	= IMX2_WDT_MAX_TIME;
 
-	setup_timer(&imx2_wdt.timer, imx2_wdt_timer_ping, 0);
+	clk_prepare_enable(wdev->clk);
 
-	imx2_wdt_miscdev.parent = &pdev->dev;
-	ret = misc_register(&imx2_wdt_miscdev);
-	if (ret)
-		goto fail;
+	regmap_read(wdev->regmap, IMX2_WDT_WRSR, &val);
+	wdog->bootstatus = val & IMX2_WDT_WRSR_TOUT ? WDIOF_CARDRESET : 0;
 
-	dev_info(&pdev->dev,
-		"IMX2+ Watchdog Timer enabled. timeout=%ds (nowayout=%d)\n",
-						imx2_wdt.timeout, nowayout);
-	return 0;
+	wdog->timeout = clamp_t(unsigned, timeout, 1, IMX2_WDT_MAX_TIME);
+	if (wdog->timeout != timeout)
+		dev_warn(&pdev->dev, "Initial timeout out of range! Clamped from %u to %u\n",
+			 timeout, wdog->timeout);
+
+	platform_set_drvdata(pdev, wdog);
+	watchdog_set_drvdata(wdog, wdev);
+	watchdog_set_nowayout(wdog, nowayout);
+	watchdog_init_timeout(wdog, timeout, &pdev->dev);
+
+	setup_timer(&wdev->timer, imx2_wdt_timer_ping, (unsigned long)wdog);
+
+	imx2_wdt_ping_if_active(wdog);
 
-fail:
-	imx2_wdt_miscdev.parent = NULL;
-	return ret;
+	ret = watchdog_register_device(wdog);
+	if (ret) {
+		dev_err(&pdev->dev, "cannot register watchdog device\n");
+		return ret;
+	}
+
+	dev_info(&pdev->dev, "timeout %d sec (nowayout=%d)\n",
+		 wdog->timeout, nowayout);
+
+	return 0;
 }
 
 static int __exit imx2_wdt_remove(struct platform_device *pdev)
 {
-	misc_deregister(&imx2_wdt_miscdev);
+	struct watchdog_device *wdog = platform_get_drvdata(pdev);
+	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
 
-	if (test_bit(IMX2_WDT_STATUS_STARTED, &imx2_wdt.status)) {
-		del_timer_sync(&imx2_wdt.timer);
+	watchdog_unregister_device(wdog);
 
-		dev_crit(imx2_wdt_miscdev.parent,
-			"Device removed: Expect reboot!\n");
+	if (imx2_wdt_is_running(wdev)) {
+		del_timer_sync(&wdev->timer);
+		imx2_wdt_ping(wdog);
+		dev_crit(&pdev->dev, "Device removed: Expect reboot!\n");
 	}
-
-	imx2_wdt_miscdev.parent = NULL;
 	return 0;
 }
 
 static void imx2_wdt_shutdown(struct platform_device *pdev)
 {
-	if (test_bit(IMX2_WDT_STATUS_STARTED, &imx2_wdt.status)) {
-		/* we are running, we need to delete the timer but will give
-		 * max timeout before reboot will take place */
-		del_timer_sync(&imx2_wdt.timer);
-		imx2_wdt_set_timeout(IMX2_WDT_MAX_TIME);
-		imx2_wdt_ping();
-
-		dev_crit(imx2_wdt_miscdev.parent,
-			"Device shutdown: Expect reboot!\n");
+	struct watchdog_device *wdog = platform_get_drvdata(pdev);
+	struct imx2_wdt_device *wdev = watchdog_get_drvdata(wdog);
+
+	if (imx2_wdt_is_running(wdev)) {
+		/*
+		 * We are running, we need to delete the timer but will
+		 * give max timeout before reboot will take place
+		 */
+		del_timer_sync(&wdev->timer);
+		imx2_wdt_set_timeout(wdog, IMX2_WDT_MAX_TIME);
+		imx2_wdt_ping(wdog);
+		dev_crit(&pdev->dev, "Device shutdown: Expect reboot!\n");
 	}
 }
 
diff --git a/drivers/watchdog/intel-mid_wdt.c b/drivers/watchdog/intel-mid_wdt.c
new file mode 100644
index 00000000000..ca66e8e7463
--- /dev/null
+++ b/drivers/watchdog/intel-mid_wdt.c
@@ -0,0 +1,184 @@
+/*
+ *      intel-mid_wdt: generic Intel MID SCU watchdog driver
+ *
+ *      Platforms supported so far:
+ *      - Merrifield only
+ *
+ *      Copyright (C) 2014 Intel Corporation. All rights reserved.
+ *      Contact: David Cohen <david.a.cohen@linux.intel.com>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of version 2 of the GNU General
+ *      Public License as published by the Free Software Foundation.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
+#include <linux/platform_device.h>
+#include <linux/watchdog.h>
+#include <linux/platform_data/intel-mid_wdt.h>
+
+#include <asm/intel_scu_ipc.h>
+#include <asm/intel-mid.h>
+
+#define IPC_WATCHDOG 0xf8
+
+#define MID_WDT_PRETIMEOUT		15
+#define MID_WDT_TIMEOUT_MIN		(1 + MID_WDT_PRETIMEOUT)
+#define MID_WDT_TIMEOUT_MAX		170
+#define MID_WDT_DEFAULT_TIMEOUT		90
+
+/* SCU watchdog messages */
+enum {
+	SCU_WATCHDOG_START = 0,
+	SCU_WATCHDOG_STOP,
+	SCU_WATCHDOG_KEEPALIVE,
+};
+
+static inline int wdt_command(int sub, u32 *in, int inlen)
+{
+	return intel_scu_ipc_command(IPC_WATCHDOG, sub, in, inlen, NULL, 0);
+}
+
+static int wdt_start(struct watchdog_device *wd)
+{
+	int ret, in_size;
+	int timeout = wd->timeout;
+	struct ipc_wd_start {
+		u32 pretimeout;
+		u32 timeout;
+	} ipc_wd_start = { timeout - MID_WDT_PRETIMEOUT, timeout };
+
+	/*
+	 * SCU expects the input size for watchdog IPC to
+	 * be based on 4 bytes
+	 */
+	in_size = DIV_ROUND_UP(sizeof(ipc_wd_start), 4);
+
+	ret = wdt_command(SCU_WATCHDOG_START, (u32 *)&ipc_wd_start, in_size);
+	if (ret) {
+		struct device *dev = watchdog_get_drvdata(wd);
+		dev_crit(dev, "error starting watchdog: %d\n", ret);
+	}
+
+	return ret;
+}
+
+static int wdt_ping(struct watchdog_device *wd)
+{
+	int ret;
+
+	ret = wdt_command(SCU_WATCHDOG_KEEPALIVE, NULL, 0);
+	if (ret) {
+		struct device *dev = watchdog_get_drvdata(wd);
+		dev_crit(dev, "Error executing keepalive: 0x%x\n", ret);
+	}
+
+	return ret;
+}
+
+static int wdt_stop(struct watchdog_device *wd)
+{
+	int ret;
+
+	ret = wdt_command(SCU_WATCHDOG_STOP, NULL, 0);
+	if (ret) {
+		struct device *dev = watchdog_get_drvdata(wd);
+		dev_crit(dev, "Error stopping watchdog: 0x%x\n", ret);
+	}
+
+	return ret;
+}
+
+static irqreturn_t mid_wdt_irq(int irq, void *dev_id)
+{
+	panic("Kernel Watchdog");
+
+	/* This code should not be reached */
+	return IRQ_HANDLED;
+}
+
+static const struct watchdog_info mid_wdt_info = {
+	.identity = "Intel MID SCU watchdog",
+	.options = WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT,
+};
+
+static const struct watchdog_ops mid_wdt_ops = {
+	.owner = THIS_MODULE,
+	.start = wdt_start,
+	.stop = wdt_stop,
+	.ping = wdt_ping,
+};
+
+static int mid_wdt_probe(struct platform_device *pdev)
+{
+	struct watchdog_device *wdt_dev;
+	struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
+	int ret;
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "missing platform data\n");
+		return -EINVAL;
+	}
+
+	if (pdata->probe) {
+		ret = pdata->probe(pdev);
+		if (ret)
+			return ret;
+	}
+
+	wdt_dev = devm_kzalloc(&pdev->dev, sizeof(*wdt_dev), GFP_KERNEL);
+	if (!wdt_dev)
+		return -ENOMEM;
+
+	wdt_dev->info = &mid_wdt_info;
+	wdt_dev->ops = &mid_wdt_ops;
+	wdt_dev->min_timeout = MID_WDT_TIMEOUT_MIN;
+	wdt_dev->max_timeout = MID_WDT_TIMEOUT_MAX;
+	wdt_dev->timeout = MID_WDT_DEFAULT_TIMEOUT;
+
+	watchdog_set_drvdata(wdt_dev, &pdev->dev);
+	platform_set_drvdata(pdev, wdt_dev);
+
+	ret = devm_request_irq(&pdev->dev, pdata->irq, mid_wdt_irq,
+			       IRQF_SHARED | IRQF_NO_SUSPEND, "watchdog",
+			       wdt_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "error requesting warning irq %d\n",
+			pdata->irq);
+		return ret;
+	}
+
+	ret = watchdog_register_device(wdt_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "error registering watchdog device\n");
+		return ret;
+	}
+
+	dev_info(&pdev->dev, "Intel MID watchdog device probed\n");
+
+	return 0;
+}
+
+static int mid_wdt_remove(struct platform_device *pdev)
+{
+	struct watchdog_device *wd = platform_get_drvdata(pdev);
+	watchdog_unregister_device(wd);
+	return 0;
+}
+
+static struct platform_driver mid_wdt_driver = {
+	.probe		= mid_wdt_probe,
+	.remove		= mid_wdt_remove,
+	.driver		= {
+		.owner	= THIS_MODULE,
+		.name	= "intel_mid_wdt",
+	},
+};
+
+module_platform_driver(mid_wdt_driver);
+
+MODULE_AUTHOR("David Cohen <david.a.cohen@linux.intel.com>");
+MODULE_DESCRIPTION("Watchdog Driver for Intel MID platform");
+MODULE_LICENSE("GPL");
diff --git a/drivers/watchdog/kempld_wdt.c b/drivers/watchdog/kempld_wdt.c
index 20dc7384473..d9c1a160192 100644
--- a/drivers/watchdog/kempld_wdt.c
+++ b/drivers/watchdog/kempld_wdt.c
@@ -162,7 +162,7 @@ static int kempld_wdt_set_stage_timeout(struct kempld_wdt_data *wdt_data,
 	kempld_get_mutex(pld);
 	stage_cfg = kempld_read8(pld, KEMPLD_WDT_STAGE_CFG(stage->id));
 	stage_cfg &= ~STAGE_CFG_PRESCALER_MASK;
-	stage_cfg |= STAGE_CFG_SET_PRESCALER(prescaler);
+	stage_cfg |= STAGE_CFG_SET_PRESCALER(PRESCALER_21);
 	kempld_write8(pld, KEMPLD_WDT_STAGE_CFG(stage->id), stage_cfg);
 	kempld_write32(pld, KEMPLD_WDT_STAGE_TIMEOUT(stage->id),
 			stage_timeout);
diff --git a/drivers/watchdog/of_xilinx_wdt.c b/drivers/watchdog/of_xilinx_wdt.c
index 57ccae8327f..1e6e28df5d7 100644
--- a/drivers/watchdog/of_xilinx_wdt.c
+++ b/drivers/watchdog/of_xilinx_wdt.c
@@ -225,7 +225,7 @@ static int xwdt_remove(struct platform_device *pdev)
 }
 
 /* Match table for of_platform binding */
-static struct of_device_id xwdt_of_match[] = {
+static const struct of_device_id xwdt_of_match[] = {
 	{ .compatible = "xlnx,xps-timebase-wdt-1.00.a", },
 	{ .compatible = "xlnx,xps-timebase-wdt-1.01.a", },
 	{},
diff --git a/drivers/watchdog/orion_wdt.c b/drivers/watchdog/orion_wdt.c
index 9b3c41d1870..00d0741228f 100644
--- a/drivers/watchdog/orion_wdt.c
+++ b/drivers/watchdog/orion_wdt.c
@@ -55,15 +55,19 @@ struct orion_watchdog_data {
 	int wdt_counter_offset;
 	int wdt_enable_bit;
 	int rstout_enable_bit;
+	int rstout_mask_bit;
 	int (*clock_init)(struct platform_device *,
 			  struct orion_watchdog *);
+	int (*enabled)(struct orion_watchdog *);
 	int (*start)(struct watchdog_device *);
+	int (*stop)(struct watchdog_device *);
 };
 
 struct orion_watchdog {
 	struct watchdog_device wdt;
 	void __iomem *reg;
 	void __iomem *rstout;
+	void __iomem *rstout_mask;
 	unsigned long clk_rate;
 	struct clk *clk;
 	const struct orion_watchdog_data *data;
@@ -142,9 +146,35 @@ static int orion_wdt_ping(struct watchdog_device *wdt_dev)
 	return 0;
 }
 
+static int armada375_start(struct watchdog_device *wdt_dev)
+{
+	struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev);
+	u32 reg;
+
+	/* Set watchdog duration */
+	writel(dev->clk_rate * wdt_dev->timeout,
+	       dev->reg + dev->data->wdt_counter_offset);
+
+	/* Clear the watchdog expiration bit */
+	atomic_io_modify(dev->reg + TIMER_A370_STATUS, WDT_A370_EXPIRED, 0);
+
+	/* Enable watchdog timer */
+	atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit,
+						dev->data->wdt_enable_bit);
+
+	/* Enable reset on watchdog */
+	reg = readl(dev->rstout);
+	reg |= dev->data->rstout_enable_bit;
+	writel(reg, dev->rstout);
+
+	atomic_io_modify(dev->rstout_mask, dev->data->rstout_mask_bit, 0);
+	return 0;
+}
+
 static int armada370_start(struct watchdog_device *wdt_dev)
 {
 	struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev);
+	u32 reg;
 
 	/* Set watchdog duration */
 	writel(dev->clk_rate * wdt_dev->timeout,
@@ -157,8 +187,10 @@ static int armada370_start(struct watchdog_device *wdt_dev)
 	atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit,
 						dev->data->wdt_enable_bit);
 
-	atomic_io_modify(dev->rstout, dev->data->rstout_enable_bit,
-				      dev->data->rstout_enable_bit);
+	/* Enable reset on watchdog */
+	reg = readl(dev->rstout);
+	reg |= dev->data->rstout_enable_bit;
+	writel(reg, dev->rstout);
 	return 0;
 }
 
@@ -189,7 +221,7 @@ static int orion_wdt_start(struct watchdog_device *wdt_dev)
 	return dev->data->start(wdt_dev);
 }
 
-static int orion_wdt_stop(struct watchdog_device *wdt_dev)
+static int orion_stop(struct watchdog_device *wdt_dev)
 {
 	struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev);
 
@@ -202,7 +234,48 @@ static int orion_wdt_stop(struct watchdog_device *wdt_dev)
 	return 0;
 }
 
-static int orion_wdt_enabled(struct orion_watchdog *dev)
+static int armada375_stop(struct watchdog_device *wdt_dev)
+{
+	struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev);
+	u32 reg;
+
+	/* Disable reset on watchdog */
+	atomic_io_modify(dev->rstout_mask, dev->data->rstout_mask_bit,
+					   dev->data->rstout_mask_bit);
+	reg = readl(dev->rstout);
+	reg &= ~dev->data->rstout_enable_bit;
+	writel(reg, dev->rstout);
+
+	/* Disable watchdog timer */
+	atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit, 0);
+
+	return 0;
+}
+
+static int armada370_stop(struct watchdog_device *wdt_dev)
+{
+	struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev);
+	u32 reg;
+
+	/* Disable reset on watchdog */
+	reg = readl(dev->rstout);
+	reg &= ~dev->data->rstout_enable_bit;
+	writel(reg, dev->rstout);
+
+	/* Disable watchdog timer */
+	atomic_io_modify(dev->reg + TIMER_CTRL, dev->data->wdt_enable_bit, 0);
+
+	return 0;
+}
+
+static int orion_wdt_stop(struct watchdog_device *wdt_dev)
+{
+	struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev);
+
+	return dev->data->stop(wdt_dev);
+}
+
+static int orion_enabled(struct orion_watchdog *dev)
 {
 	bool enabled, running;
 
@@ -212,6 +285,24 @@ static int orion_wdt_enabled(struct orion_watchdog *dev)
 	return enabled && running;
 }
 
+static int armada375_enabled(struct orion_watchdog *dev)
+{
+	bool masked, enabled, running;
+
+	masked = readl(dev->rstout_mask) & dev->data->rstout_mask_bit;
+	enabled = readl(dev->rstout) & dev->data->rstout_enable_bit;
+	running = readl(dev->reg + TIMER_CTRL) & dev->data->wdt_enable_bit;
+
+	return !masked && enabled && running;
+}
+
+static int orion_wdt_enabled(struct watchdog_device *wdt_dev)
+{
+	struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev);
+
+	return dev->data->enabled(dev);
+}
+
 static unsigned int orion_wdt_get_timeleft(struct watchdog_device *wdt_dev)
 {
 	struct orion_watchdog *dev = watchdog_get_drvdata(wdt_dev);
@@ -262,10 +353,6 @@ static void __iomem *orion_wdt_ioremap_rstout(struct platform_device *pdev,
 		return devm_ioremap(&pdev->dev, res->start,
 				    resource_size(res));
 
-	/* This workaround works only for "orion-wdt", DT-enabled */
-	if (!of_device_is_compatible(pdev->dev.of_node, "marvell,orion-wdt"))
-		return NULL;
-
 	rstout = internal_regs + ORION_RSTOUT_MASK_OFFSET;
 
 	WARN(1, FW_BUG "falling back to harcoded RSTOUT reg %pa\n", &rstout);
@@ -277,7 +364,9 @@ static const struct orion_watchdog_data orion_data = {
 	.wdt_enable_bit = BIT(4),
 	.wdt_counter_offset = 0x24,
 	.clock_init = orion_wdt_clock_init,
+	.enabled = orion_enabled,
 	.start = orion_start,
+	.stop = orion_stop,
 };
 
 static const struct orion_watchdog_data armada370_data = {
@@ -285,7 +374,9 @@ static const struct orion_watchdog_data armada370_data = {
 	.wdt_enable_bit = BIT(8),
 	.wdt_counter_offset = 0x34,
 	.clock_init = armada370_wdt_clock_init,
+	.enabled = orion_enabled,
 	.start = armada370_start,
+	.stop = armada370_stop,
 };
 
 static const struct orion_watchdog_data armadaxp_data = {
@@ -293,7 +384,31 @@ static const struct orion_watchdog_data armadaxp_data = {
 	.wdt_enable_bit = BIT(8),
 	.wdt_counter_offset = 0x34,
 	.clock_init = armadaxp_wdt_clock_init,
+	.enabled = orion_enabled,
 	.start = armada370_start,
+	.stop = armada370_stop,
+};
+
+static const struct orion_watchdog_data armada375_data = {
+	.rstout_enable_bit = BIT(8),
+	.rstout_mask_bit = BIT(10),
+	.wdt_enable_bit = BIT(8),
+	.wdt_counter_offset = 0x34,
+	.clock_init = armada370_wdt_clock_init,
+	.enabled = armada375_enabled,
+	.start = armada375_start,
+	.stop = armada375_stop,
+};
+
+static const struct orion_watchdog_data armada380_data = {
+	.rstout_enable_bit = BIT(8),
+	.rstout_mask_bit = BIT(10),
+	.wdt_enable_bit = BIT(8),
+	.wdt_counter_offset = 0x34,
+	.clock_init = armadaxp_wdt_clock_init,
+	.enabled = armada375_enabled,
+	.start = armada375_start,
+	.stop = armada375_stop,
 };
 
 static const struct of_device_id orion_wdt_of_match_table[] = {
@@ -309,16 +424,78 @@ static const struct of_device_id orion_wdt_of_match_table[] = {
 		.compatible = "marvell,armada-xp-wdt",
 		.data = &armadaxp_data,
 	},
+	{
+		.compatible = "marvell,armada-375-wdt",
+		.data = &armada375_data,
+	},
+	{
+		.compatible = "marvell,armada-380-wdt",
+		.data = &armada380_data,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, orion_wdt_of_match_table);
 
+static int orion_wdt_get_regs(struct platform_device *pdev,
+			      struct orion_watchdog *dev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	struct resource *res;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
+	dev->reg = devm_ioremap(&pdev->dev, res->start,
+				resource_size(res));
+	if (!dev->reg)
+		return -ENOMEM;
+
+	/* Each supported compatible has some RSTOUT register quirk */
+	if (of_device_is_compatible(node, "marvell,orion-wdt")) {
+
+		dev->rstout = orion_wdt_ioremap_rstout(pdev, res->start &
+						       INTERNAL_REGS_MASK);
+		if (!dev->rstout)
+			return -ENODEV;
+
+	} else if (of_device_is_compatible(node, "marvell,armada-370-wdt") ||
+		   of_device_is_compatible(node, "marvell,armada-xp-wdt")) {
+
+		/* Dedicated RSTOUT register, can be requested. */
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		dev->rstout = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(dev->rstout))
+			return PTR_ERR(dev->rstout);
+
+	} else if (of_device_is_compatible(node, "marvell,armada-375-wdt") ||
+		   of_device_is_compatible(node, "marvell,armada-380-wdt")) {
+
+		/* Dedicated RSTOUT register, can be requested. */
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		dev->rstout = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(dev->rstout))
+			return PTR_ERR(dev->rstout);
+
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+		if (!res)
+			return -ENODEV;
+		dev->rstout_mask = devm_ioremap(&pdev->dev, res->start,
+						resource_size(res));
+		if (!dev->rstout_mask)
+			return -ENOMEM;
+
+	} else {
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int orion_wdt_probe(struct platform_device *pdev)
 {
 	struct orion_watchdog *dev;
 	const struct of_device_id *match;
 	unsigned int wdt_max_duration;	/* (seconds) */
-	struct resource *res;
 	int ret, irq;
 
 	dev = devm_kzalloc(&pdev->dev, sizeof(struct orion_watchdog),
@@ -336,19 +513,9 @@ static int orion_wdt_probe(struct platform_device *pdev)
 	dev->wdt.min_timeout = 1;
 	dev->data = match->data;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-
-	dev->reg = devm_ioremap(&pdev->dev, res->start,
-			       resource_size(res));
-	if (!dev->reg)
-		return -ENOMEM;
-
-	dev->rstout = orion_wdt_ioremap_rstout(pdev, res->start &
-						     INTERNAL_REGS_MASK);
-	if (!dev->rstout)
-		return -ENODEV;
+	ret = orion_wdt_get_regs(pdev, dev);
+	if (ret)
+		return ret;
 
 	ret = dev->data->clock_init(pdev, dev);
 	if (ret) {
@@ -371,7 +538,7 @@ static int orion_wdt_probe(struct platform_device *pdev)
 	 * removed and re-insterted, or if the bootloader explicitly
 	 * set a running watchdog before booting the kernel.
 	 */
-	if (!orion_wdt_enabled(dev))
+	if (!orion_wdt_enabled(&dev->wdt))
 		orion_wdt_stop(&dev->wdt);
 
 	/* Request the IRQ only after the watchdog is disabled */
diff --git a/drivers/watchdog/shwdt.c b/drivers/watchdog/shwdt.c
index d04d02b41c3..061756e36cf 100644
--- a/drivers/watchdog/shwdt.c
+++ b/drivers/watchdog/shwdt.c
@@ -282,8 +282,6 @@ static int sh_wdt_probe(struct platform_device *pdev)
 	wdt->timer.data		= (unsigned long)wdt;
 	wdt->timer.expires	= next_ping_period(clock_division_ratio);
 
-	platform_set_drvdata(pdev, wdt);
-
 	dev_info(&pdev->dev, "initialized.\n");
 
 	pm_runtime_enable(&pdev->dev);
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 47629d268e0..c1b03f4235b 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -59,7 +59,6 @@
  * @adev: amba device structure of wdt
  * @status: current status of wdt
  * @load_val: load value to be set for current timeout
- * @timeout: current programmed timeout
  */
 struct sp805_wdt {
 	struct watchdog_device		wdd;
@@ -68,7 +67,6 @@ struct sp805_wdt {
 	struct clk			*clk;
 	struct amba_device		*adev;
 	unsigned int			load_val;
-	unsigned int			timeout;
 };
 
 static bool nowayout = WATCHDOG_NOWAYOUT;
@@ -98,7 +96,7 @@ static int wdt_setload(struct watchdog_device *wdd, unsigned int timeout)
 	spin_lock(&wdt->lock);
 	wdt->load_val = load;
 	/* roundup timeout to closest positive integer value */
-	wdt->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
+	wdd->timeout = div_u64((load + 1) * 2 + (rate / 2), rate);
 	spin_unlock(&wdt->lock);
 
 	return 0;
diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c
index cd00a7836cd..693b9d2c6e3 100644
--- a/drivers/watchdog/sunxi_wdt.c
+++ b/drivers/watchdog/sunxi_wdt.c
@@ -57,17 +57,17 @@ struct sunxi_wdt_dev {
  */
 
 static const int wdt_timeout_map[] = {
-	[1] = 0b0001,  /* 1s  */
-	[2] = 0b0010,  /* 2s  */
-	[3] = 0b0011,  /* 3s  */
-	[4] = 0b0100,  /* 4s  */
-	[5] = 0b0101,  /* 5s  */
-	[6] = 0b0110,  /* 6s  */
-	[8] = 0b0111,  /* 8s  */
-	[10] = 0b1000, /* 10s */
-	[12] = 0b1001, /* 12s */
-	[14] = 0b1010, /* 14s */
-	[16] = 0b1011, /* 16s */
+	[1] = 0x1,  /* 1s  */
+	[2] = 0x2,  /* 2s  */
+	[3] = 0x3,  /* 3s  */
+	[4] = 0x4,  /* 4s  */
+	[5] = 0x5,  /* 5s  */
+	[6] = 0x6,  /* 6s  */
+	[8] = 0x7,  /* 8s  */
+	[10] = 0x8, /* 10s */
+	[12] = 0x9, /* 12s */
+	[14] = 0xA, /* 14s */
+	[16] = 0xB, /* 16s */
 };
 
 static int sunxi_wdt_ping(struct watchdog_device *wdt_dev)
diff --git a/drivers/watchdog/via_wdt.c b/drivers/watchdog/via_wdt.c
index d2cd9f0bcb9..56369c4f196 100644
--- a/drivers/watchdog/via_wdt.c
+++ b/drivers/watchdog/via_wdt.c
@@ -232,7 +232,7 @@ err_out_disable_device:
 static void wdt_remove(struct pci_dev *pdev)
 {
 	watchdog_unregister_device(&wdt_dev);
-	del_timer(&timer);
+	del_timer_sync(&timer);
 	iounmap(wdt_mem);
 	release_mem_region(mmio, VIA_WDT_MMIO_LEN);
 	release_resource(&wdt_res);
diff --git a/drivers/watchdog/w83627hf_wdt.c b/drivers/watchdog/w83627hf_wdt.c
index b1da0c18fd1..7165704a3e3 100644
--- a/drivers/watchdog/w83627hf_wdt.c
+++ b/drivers/watchdog/w83627hf_wdt.c
@@ -64,6 +64,10 @@ MODULE_PARM_DESC(nowayout,
 		"Watchdog cannot be stopped once started (default="
 				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 
+static int early_disable;
+module_param(early_disable, int, 0);
+MODULE_PARM_DESC(early_disable, "Disable watchdog at boot time (default=0)");
+
 /*
  *	Kernel methods.
  */
@@ -208,9 +212,14 @@ static int w83627hf_init(struct watchdog_device *wdog, enum chips chip)
 
 	t = superio_inb(cr_wdt_timeout);
 	if (t != 0) {
-		pr_info("Watchdog already running. Resetting timeout to %d sec\n",
-			wdog->timeout);
-		superio_outb(cr_wdt_timeout, wdog->timeout);
+		if (early_disable) {
+			pr_warn("Stopping previously enabled watchdog until userland kicks in\n");
+			superio_outb(cr_wdt_timeout, 0);
+		} else {
+			pr_info("Watchdog already running. Resetting timeout to %d sec\n",
+				wdog->timeout);
+			superio_outb(cr_wdt_timeout, wdog->timeout);
+		}
 	}
 
 	/* set second mode & disable keyboard turning off watchdog */
diff --git a/drivers/watchdog/w83697hf_wdt.c b/drivers/watchdog/w83697hf_wdt.c
deleted file mode 100644
index e9ea856b8ff..00000000000
--- a/drivers/watchdog/w83697hf_wdt.c
+++ /dev/null
@@ -1,460 +0,0 @@
-/*
- *	w83697hf/hg WDT driver
- *
- *	(c) Copyright 2006 Samuel Tardieu <sam@rfc1149.net>
- *	(c) Copyright 2006 Marcus Junker <junker@anduras.de>
- *
- *	Based on w83627hf_wdt.c which is based on advantechwdt.c
- *	which is based on wdt.c.
- *	Original copyright messages:
- *
- *	(c) Copyright 2003 Pádraig Brady <P@draigBrady.com>
- *
- *	(c) Copyright 2000-2001 Marek Michalkiewicz <marekm@linux.org.pl>
- *
- *	(c) Copyright 1996 Alan Cox <alan@lxorguk.ukuu.org.uk>,
- *						All Rights Reserved.
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	Neither Marcus Junker nor ANDURAS AG admit liability nor provide
- *	warranty for any of this software. This material is provided
- *	"AS-IS" and at no charge.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/types.h>
-#include <linux/miscdevice.h>
-#include <linux/watchdog.h>
-#include <linux/fs.h>
-#include <linux/ioport.h>
-#include <linux/notifier.h>
-#include <linux/reboot.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/io.h>
-#include <linux/uaccess.h>
-
-
-#define WATCHDOG_NAME "w83697hf/hg WDT"
-#define WATCHDOG_TIMEOUT 60		/* 60 sec default timeout */
-#define WATCHDOG_EARLY_DISABLE 1	/* Disable until userland kicks in */
-
-static unsigned long wdt_is_open;
-static char expect_close;
-static DEFINE_SPINLOCK(io_lock);
-
-/* You must set this - there is no sane way to probe for this board. */
-static int wdt_io = 0x2e;
-module_param(wdt_io, int, 0);
-MODULE_PARM_DESC(wdt_io,
-		"w83697hf/hg WDT io port (default 0x2e, 0 = autodetect)");
-
-static int timeout = WATCHDOG_TIMEOUT;	/* in seconds */
-module_param(timeout, int, 0);
-MODULE_PARM_DESC(timeout,
-	"Watchdog timeout in seconds. 1<= timeout <=255 (default="
-				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
-
-static bool nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, bool, 0);
-MODULE_PARM_DESC(nowayout,
-	"Watchdog cannot be stopped once started (default="
-				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
-
-static int early_disable = WATCHDOG_EARLY_DISABLE;
-module_param(early_disable, int, 0);
-MODULE_PARM_DESC(early_disable,
-	"Watchdog gets disabled at boot time (default="
-				__MODULE_STRING(WATCHDOG_EARLY_DISABLE) ")");
-
-/*
- *	Kernel methods.
- */
-
-#define W83697HF_EFER (wdt_io + 0)  /* Extended Function Enable Register */
-#define W83697HF_EFIR (wdt_io + 0)  /* Extended Function Index Register
-							(same as EFER) */
-#define W83697HF_EFDR (wdt_io + 1)  /* Extended Function Data Register */
-
-static inline void w83697hf_unlock(void)
-{
-	outb_p(0x87, W83697HF_EFER);	/* Enter extended function mode */
-	outb_p(0x87, W83697HF_EFER);	/* Again according to manual */
-}
-
-static inline void w83697hf_lock(void)
-{
-	outb_p(0xAA, W83697HF_EFER);	/* Leave extended function mode */
-}
-
-/*
- *	The three functions w83697hf_get_reg(), w83697hf_set_reg() and
- *	w83697hf_write_timeout() must be called with the device unlocked.
- */
-
-static unsigned char w83697hf_get_reg(unsigned char reg)
-{
-	outb_p(reg, W83697HF_EFIR);
-	return inb_p(W83697HF_EFDR);
-}
-
-static void w83697hf_set_reg(unsigned char reg, unsigned char data)
-{
-	outb_p(reg, W83697HF_EFIR);
-	outb_p(data, W83697HF_EFDR);
-}
-
-static void w83697hf_write_timeout(int timeout)
-{
-	/* Write Timeout counter to CRF4 */
-	w83697hf_set_reg(0xF4, timeout);
-}
-
-static void w83697hf_select_wdt(void)
-{
-	w83697hf_unlock();
-	w83697hf_set_reg(0x07, 0x08);	/* Switch to logic device 8 (GPIO2) */
-}
-
-static inline void w83697hf_deselect_wdt(void)
-{
-	w83697hf_lock();
-}
-
-static void w83697hf_init(void)
-{
-	unsigned char bbuf;
-
-	w83697hf_select_wdt();
-
-	bbuf = w83697hf_get_reg(0x29);
-	bbuf &= ~0x60;
-	bbuf |= 0x20;
-
-	/* Set pin 119 to WDTO# mode (= CR29, WDT0) */
-	w83697hf_set_reg(0x29, bbuf);
-
-	bbuf = w83697hf_get_reg(0xF3);
-	bbuf &= ~0x04;
-	w83697hf_set_reg(0xF3, bbuf);	/* Count mode is seconds */
-
-	w83697hf_deselect_wdt();
-}
-
-static void wdt_ping(void)
-{
-	spin_lock(&io_lock);
-	w83697hf_select_wdt();
-
-	w83697hf_write_timeout(timeout);
-
-	w83697hf_deselect_wdt();
-	spin_unlock(&io_lock);
-}
-
-static void wdt_enable(void)
-{
-	spin_lock(&io_lock);
-	w83697hf_select_wdt();
-
-	w83697hf_write_timeout(timeout);
-	w83697hf_set_reg(0x30, 1);	/* Enable timer */
-
-	w83697hf_deselect_wdt();
-	spin_unlock(&io_lock);
-}
-
-static void wdt_disable(void)
-{
-	spin_lock(&io_lock);
-	w83697hf_select_wdt();
-
-	w83697hf_set_reg(0x30, 0);	/* Disable timer */
-	w83697hf_write_timeout(0);
-
-	w83697hf_deselect_wdt();
-	spin_unlock(&io_lock);
-}
-
-static unsigned char wdt_running(void)
-{
-	unsigned char t;
-
-	spin_lock(&io_lock);
-	w83697hf_select_wdt();
-
-	t = w83697hf_get_reg(0xF4);	/* Read timer */
-
-	w83697hf_deselect_wdt();
-	spin_unlock(&io_lock);
-
-	return t;
-}
-
-static int wdt_set_heartbeat(int t)
-{
-	if (t < 1 || t > 255)
-		return -EINVAL;
-
-	timeout = t;
-	return 0;
-}
-
-static ssize_t wdt_write(struct file *file, const char __user *buf,
-						size_t count, loff_t *ppos)
-{
-	if (count) {
-		if (!nowayout) {
-			size_t i;
-
-			expect_close = 0;
-
-			for (i = 0; i != count; i++) {
-				char c;
-				if (get_user(c, buf + i))
-					return -EFAULT;
-				if (c == 'V')
-					expect_close = 42;
-			}
-		}
-		wdt_ping();
-	}
-	return count;
-}
-
-static long wdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	void __user *argp = (void __user *)arg;
-	int __user *p = argp;
-	int new_timeout;
-	static const struct watchdog_info ident = {
-		.options = WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT
-							| WDIOF_MAGICCLOSE,
-		.firmware_version = 1,
-		.identity = "W83697HF WDT",
-	};
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		if (copy_to_user(argp, &ident, sizeof(ident)))
-			return -EFAULT;
-		break;
-
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, p);
-
-	case WDIOC_SETOPTIONS:
-	{
-		int options, retval = -EINVAL;
-
-		if (get_user(options, p))
-			return -EFAULT;
-
-		if (options & WDIOS_DISABLECARD) {
-			wdt_disable();
-			retval = 0;
-		}
-
-		if (options & WDIOS_ENABLECARD) {
-			wdt_enable();
-			retval = 0;
-		}
-
-		return retval;
-	}
-
-	case WDIOC_KEEPALIVE:
-		wdt_ping();
-		break;
-
-	case WDIOC_SETTIMEOUT:
-		if (get_user(new_timeout, p))
-			return -EFAULT;
-		if (wdt_set_heartbeat(new_timeout))
-			return -EINVAL;
-		wdt_ping();
-		/* Fall */
-
-	case WDIOC_GETTIMEOUT:
-		return put_user(timeout, p);
-
-	default:
-		return -ENOTTY;
-	}
-	return 0;
-}
-
-static int wdt_open(struct inode *inode, struct file *file)
-{
-	if (test_and_set_bit(0, &wdt_is_open))
-		return -EBUSY;
-	/*
-	 *	Activate
-	 */
-
-	wdt_enable();
-	return nonseekable_open(inode, file);
-}
-
-static int wdt_close(struct inode *inode, struct file *file)
-{
-	if (expect_close == 42)
-		wdt_disable();
-	else {
-		pr_crit("Unexpected close, not stopping watchdog!\n");
-		wdt_ping();
-	}
-	expect_close = 0;
-	clear_bit(0, &wdt_is_open);
-	return 0;
-}
-
-/*
- *	Notifier for system down
- */
-
-static int wdt_notify_sys(struct notifier_block *this, unsigned long code,
-	void *unused)
-{
-	if (code == SYS_DOWN || code == SYS_HALT)
-		wdt_disable();	/* Turn the WDT off */
-
-	return NOTIFY_DONE;
-}
-
-/*
- *	Kernel Interfaces
- */
-
-static const struct file_operations wdt_fops = {
-	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
-	.write		= wdt_write,
-	.unlocked_ioctl	= wdt_ioctl,
-	.open		= wdt_open,
-	.release	= wdt_close,
-};
-
-static struct miscdevice wdt_miscdev = {
-	.minor = WATCHDOG_MINOR,
-	.name = "watchdog",
-	.fops = &wdt_fops,
-};
-
-/*
- *	The WDT needs to learn about soft shutdowns in order to
- *	turn the timebomb registers off.
- */
-
-static struct notifier_block wdt_notifier = {
-	.notifier_call = wdt_notify_sys,
-};
-
-static int w83697hf_check_wdt(void)
-{
-	if (!request_region(wdt_io, 2, WATCHDOG_NAME)) {
-		pr_err("I/O address 0x%x already in use\n", wdt_io);
-		return -EIO;
-	}
-
-	pr_debug("Looking for watchdog at address 0x%x\n", wdt_io);
-	w83697hf_unlock();
-	if (w83697hf_get_reg(0x20) == 0x60) {
-		pr_info("watchdog found at address 0x%x\n", wdt_io);
-		w83697hf_lock();
-		return 0;
-	}
-	/* Reprotect in case it was a compatible device */
-	w83697hf_lock();
-
-	pr_info("watchdog not found at address 0x%x\n", wdt_io);
-	release_region(wdt_io, 2);
-	return -EIO;
-}
-
-static int w83697hf_ioports[] = { 0x2e, 0x4e, 0x00 };
-
-static int __init wdt_init(void)
-{
-	int ret, i, found = 0;
-
-	pr_info("WDT driver for W83697HF/HG initializing\n");
-
-	if (wdt_io == 0) {
-		/* we will autodetect the W83697HF/HG watchdog */
-		for (i = 0; ((!found) && (w83697hf_ioports[i] != 0)); i++) {
-			wdt_io = w83697hf_ioports[i];
-			if (!w83697hf_check_wdt())
-				found++;
-		}
-	} else {
-		if (!w83697hf_check_wdt())
-			found++;
-	}
-
-	if (!found) {
-		pr_err("No W83697HF/HG could be found\n");
-		ret = -ENODEV;
-		goto out;
-	}
-
-	w83697hf_init();
-	if (early_disable) {
-		if (wdt_running())
-			pr_warn("Stopping previously enabled watchdog until userland kicks in\n");
-		wdt_disable();
-	}
-
-	if (wdt_set_heartbeat(timeout)) {
-		wdt_set_heartbeat(WATCHDOG_TIMEOUT);
-		pr_info("timeout value must be 1 <= timeout <= 255, using %d\n",
-			WATCHDOG_TIMEOUT);
-	}
-
-	ret = register_reboot_notifier(&wdt_notifier);
-	if (ret != 0) {
-		pr_err("cannot register reboot notifier (err=%d)\n", ret);
-		goto unreg_regions;
-	}
-
-	ret = misc_register(&wdt_miscdev);
-	if (ret != 0) {
-		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
-		       WATCHDOG_MINOR, ret);
-		goto unreg_reboot;
-	}
-
-	pr_info("initialized. timeout=%d sec (nowayout=%d)\n",
-		timeout, nowayout);
-
-out:
-	return ret;
-unreg_reboot:
-	unregister_reboot_notifier(&wdt_notifier);
-unreg_regions:
-	release_region(wdt_io, 2);
-	goto out;
-}
-
-static void __exit wdt_exit(void)
-{
-	misc_deregister(&wdt_miscdev);
-	unregister_reboot_notifier(&wdt_notifier);
-	release_region(wdt_io, 2);
-}
-
-module_init(wdt_init);
-module_exit(wdt_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Marcus Junker <junker@anduras.de>");
-MODULE_AUTHOR("Samuel Tardieu <sam@rfc1149.net>");
-MODULE_DESCRIPTION("w83697hf/hg WDT driver");
diff --git a/drivers/watchdog/w83697ug_wdt.c b/drivers/watchdog/w83697ug_wdt.c
deleted file mode 100644
index ff58cb74671..00000000000
--- a/drivers/watchdog/w83697ug_wdt.c
+++ /dev/null
@@ -1,397 +0,0 @@
-/*
- *	w83697ug/uf WDT driver
- *
- *	(c) Copyright 2008 Flemming Fransen <ff@nrvissing.net>
- *		reused original code to support w83697ug/uf.
- *
- *	Based on w83627hf_wdt.c which is based on advantechwdt.c
- *	which is based on wdt.c.
- *	Original copyright messages:
- *
- *	(c) Copyright 2007 Vlad Drukker <vlad@storewiz.com>
- *		added support for W83627THF.
- *
- *	(c) Copyright 2003 Pádraig Brady <P@draigBrady.com>
- *
- *	(c) Copyright 2000-2001 Marek Michalkiewicz <marekm@linux.org.pl>
- *
- *	(c) Copyright 1996 Alan Cox <alan@redhat.com>, All Rights Reserved.
- *				http://www.redhat.com
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	Neither Alan Cox nor CymruNet Ltd. admit liability nor provide
- *	warranty for any of this software. This material is provided
- *	"AS-IS" and at no charge.
- *
- *	(c) Copyright 1995    Alan Cox <alan@redhat.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/types.h>
-#include <linux/miscdevice.h>
-#include <linux/watchdog.h>
-#include <linux/fs.h>
-#include <linux/ioport.h>
-#include <linux/notifier.h>
-#include <linux/reboot.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/io.h>
-#include <linux/uaccess.h>
-
-
-#define WATCHDOG_NAME "w83697ug/uf WDT"
-#define WATCHDOG_TIMEOUT 60		/* 60 sec default timeout */
-
-static unsigned long wdt_is_open;
-static char expect_close;
-static DEFINE_SPINLOCK(io_lock);
-
-static int wdt_io = 0x2e;
-module_param(wdt_io, int, 0);
-MODULE_PARM_DESC(wdt_io, "w83697ug/uf WDT io port (default 0x2e)");
-
-static int timeout = WATCHDOG_TIMEOUT;	/* in seconds */
-module_param(timeout, int, 0);
-MODULE_PARM_DESC(timeout,
-	"Watchdog timeout in seconds. 1<= timeout <=255 (default="
-				__MODULE_STRING(WATCHDOG_TIMEOUT) ")");
-
-static bool nowayout = WATCHDOG_NOWAYOUT;
-module_param(nowayout, bool, 0);
-MODULE_PARM_DESC(nowayout,
-	"Watchdog cannot be stopped once started (default="
-				__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
-
-/*
- *	Kernel methods.
- */
-
-#define WDT_EFER (wdt_io+0)   /* Extended Function Enable Registers */
-#define WDT_EFIR (wdt_io+0)   /* Extended Function Index Register
-							(same as EFER) */
-#define WDT_EFDR (WDT_EFIR+1) /* Extended Function Data Register */
-
-static int w83697ug_select_wd_register(void)
-{
-	unsigned char c;
-	unsigned char version;
-
-	outb_p(0x87, WDT_EFER); /* Enter extended function mode */
-	outb_p(0x87, WDT_EFER); /* Again according to manual */
-
-	outb(0x20, WDT_EFER);	/* check chip version	*/
-	version = inb(WDT_EFDR);
-
-	if (version == 0x68) {	/* W83697UG		*/
-		pr_info("Watchdog chip version 0x%02x = W83697UG/UF found at 0x%04x\n",
-			version, wdt_io);
-
-		outb_p(0x2b, WDT_EFER);
-		c = inb_p(WDT_EFDR);    /* select WDT0 */
-		c &= ~0x04;
-		outb_p(0x2b, WDT_EFER);
-		outb_p(c, WDT_EFDR);	/* set pin118 to WDT0 */
-
-	} else {
-		pr_err("No W83697UG/UF could be found\n");
-		return -ENODEV;
-	}
-
-	outb_p(0x07, WDT_EFER); /* point to logical device number reg */
-	outb_p(0x08, WDT_EFDR); /* select logical device 8 (GPIO2) */
-	outb_p(0x30, WDT_EFER); /* select CR30 */
-	c = inb_p(WDT_EFDR);
-	outb_p(c | 0x01, WDT_EFDR); /* set bit 0 to activate GPIO2 */
-
-	return 0;
-}
-
-static void w83697ug_unselect_wd_register(void)
-{
-	outb_p(0xAA, WDT_EFER); /* Leave extended function mode */
-}
-
-static int w83697ug_init(void)
-{
-	int ret;
-	unsigned char t;
-
-	ret = w83697ug_select_wd_register();
-	if (ret != 0)
-		return ret;
-
-	outb_p(0xF6, WDT_EFER); /* Select CRF6 */
-	t = inb_p(WDT_EFDR);    /* read CRF6 */
-	if (t != 0) {
-		pr_info("Watchdog already running. Resetting timeout to %d sec\n",
-			timeout);
-		outb_p(timeout, WDT_EFDR);    /* Write back to CRF6 */
-	}
-	outb_p(0xF5, WDT_EFER); /* Select CRF5 */
-	t = inb_p(WDT_EFDR);    /* read CRF5 */
-	t &= ~0x0C;             /* set second mode &
-					disable keyboard turning off watchdog */
-	outb_p(t, WDT_EFDR);    /* Write back to CRF5 */
-
-	w83697ug_unselect_wd_register();
-	return 0;
-}
-
-static void wdt_ctrl(int timeout)
-{
-	spin_lock(&io_lock);
-
-	if (w83697ug_select_wd_register() < 0) {
-		spin_unlock(&io_lock);
-		return;
-	}
-
-	outb_p(0xF4, WDT_EFER);    /* Select CRF4 */
-	outb_p(timeout, WDT_EFDR); /* Write Timeout counter to CRF4 */
-
-	w83697ug_unselect_wd_register();
-
-	spin_unlock(&io_lock);
-}
-
-static int wdt_ping(void)
-{
-	wdt_ctrl(timeout);
-	return 0;
-}
-
-static int wdt_disable(void)
-{
-	wdt_ctrl(0);
-	return 0;
-}
-
-static int wdt_set_heartbeat(int t)
-{
-	if (t < 1 || t > 255)
-		return -EINVAL;
-
-	timeout = t;
-	return 0;
-}
-
-static ssize_t wdt_write(struct file *file, const char __user *buf,
-						size_t count, loff_t *ppos)
-{
-	if (count) {
-		if (!nowayout) {
-			size_t i;
-
-			expect_close = 0;
-
-			for (i = 0; i != count; i++) {
-				char c;
-				if (get_user(c, buf + i))
-					return -EFAULT;
-				if (c == 'V')
-					expect_close = 42;
-			}
-		}
-		wdt_ping();
-	}
-	return count;
-}
-
-static long wdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	void __user *argp = (void __user *)arg;
-	int __user *p = argp;
-	int new_timeout;
-	static const struct watchdog_info ident = {
-		.options =		WDIOF_KEEPALIVEPING |
-					WDIOF_SETTIMEOUT |
-					WDIOF_MAGICCLOSE,
-		.firmware_version =	1,
-		.identity =		"W83697UG WDT",
-	};
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		if (copy_to_user(argp, &ident, sizeof(ident)))
-			return -EFAULT;
-		break;
-
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, p);
-
-	case WDIOC_SETOPTIONS:
-	{
-		int options, retval = -EINVAL;
-
-		if (get_user(options, p))
-			return -EFAULT;
-
-		if (options & WDIOS_DISABLECARD) {
-			wdt_disable();
-			retval = 0;
-		}
-
-		if (options & WDIOS_ENABLECARD) {
-			wdt_ping();
-			retval = 0;
-		}
-
-		return retval;
-	}
-
-	case WDIOC_KEEPALIVE:
-		wdt_ping();
-		break;
-
-	case WDIOC_SETTIMEOUT:
-		if (get_user(new_timeout, p))
-			return -EFAULT;
-		if (wdt_set_heartbeat(new_timeout))
-			return -EINVAL;
-		wdt_ping();
-		/* Fall */
-
-	case WDIOC_GETTIMEOUT:
-		return put_user(timeout, p);
-
-	default:
-		return -ENOTTY;
-	}
-	return 0;
-}
-
-static int wdt_open(struct inode *inode, struct file *file)
-{
-	if (test_and_set_bit(0, &wdt_is_open))
-		return -EBUSY;
-	/*
-	 *	Activate
-	 */
-
-	wdt_ping();
-	return nonseekable_open(inode, file);
-}
-
-static int wdt_close(struct inode *inode, struct file *file)
-{
-	if (expect_close == 42)
-		wdt_disable();
-	else {
-		pr_crit("Unexpected close, not stopping watchdog!\n");
-		wdt_ping();
-	}
-	expect_close = 0;
-	clear_bit(0, &wdt_is_open);
-	return 0;
-}
-
-/*
- *	Notifier for system down
- */
-
-static int wdt_notify_sys(struct notifier_block *this, unsigned long code,
-	void *unused)
-{
-	if (code == SYS_DOWN || code == SYS_HALT)
-		wdt_disable();	/* Turn the WDT off */
-
-	return NOTIFY_DONE;
-}
-
-/*
- *	Kernel Interfaces
- */
-
-static const struct file_operations wdt_fops = {
-	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
-	.write		= wdt_write,
-	.unlocked_ioctl	= wdt_ioctl,
-	.open		= wdt_open,
-	.release	= wdt_close,
-};
-
-static struct miscdevice wdt_miscdev = {
-	.minor = WATCHDOG_MINOR,
-	.name = "watchdog",
-	.fops = &wdt_fops,
-};
-
-/*
- *	The WDT needs to learn about soft shutdowns in order to
- *	turn the timebomb registers off.
- */
-
-static struct notifier_block wdt_notifier = {
-	.notifier_call = wdt_notify_sys,
-};
-
-static int __init wdt_init(void)
-{
-	int ret;
-
-	pr_info("WDT driver for the Winbond(TM) W83697UG/UF Super I/O chip initialising\n");
-
-	if (wdt_set_heartbeat(timeout)) {
-		wdt_set_heartbeat(WATCHDOG_TIMEOUT);
-		pr_info("timeout value must be 1<=timeout<=255, using %d\n",
-			WATCHDOG_TIMEOUT);
-	}
-
-	if (!request_region(wdt_io, 1, WATCHDOG_NAME)) {
-		pr_err("I/O address 0x%04x already in use\n", wdt_io);
-		ret = -EIO;
-		goto out;
-	}
-
-	ret = w83697ug_init();
-	if (ret != 0)
-		goto unreg_regions;
-
-	ret = register_reboot_notifier(&wdt_notifier);
-	if (ret != 0) {
-		pr_err("cannot register reboot notifier (err=%d)\n", ret);
-		goto unreg_regions;
-	}
-
-	ret = misc_register(&wdt_miscdev);
-	if (ret != 0) {
-		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
-		       WATCHDOG_MINOR, ret);
-		goto unreg_reboot;
-	}
-
-	pr_info("initialized. timeout=%d sec (nowayout=%d)\n",
-		timeout, nowayout);
-
-out:
-	return ret;
-unreg_reboot:
-	unregister_reboot_notifier(&wdt_notifier);
-unreg_regions:
-	release_region(wdt_io, 1);
-	goto out;
-}
-
-static void __exit wdt_exit(void)
-{
-	misc_deregister(&wdt_miscdev);
-	unregister_reboot_notifier(&wdt_notifier);
-	release_region(wdt_io, 1);
-}
-
-module_init(wdt_init);
-module_exit(wdt_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Flemming Frandsen <ff@nrvissing.net>");
-MODULE_DESCRIPTION("w83697ug/uf WDT driver");
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 38fb36e1c59..8bc01838daf 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -240,4 +240,8 @@ config XEN_MCE_LOG
 config XEN_HAVE_PVMMU
        bool
 
+config XEN_EFI
+	def_bool y
+	depends on X86_64 && EFI
+
 endmenu
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 45e00afa7f2..84044b554e3 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -9,6 +9,8 @@ obj-y	+= xenbus/
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_features.o			:= $(nostackp)
 
+CFLAGS_efi.o				+= -fshort-wchar
+
 dom0-$(CONFIG_PCI) += pci.o
 dom0-$(CONFIG_USB_SUPPORT) += dbgp.o
 dom0-$(CONFIG_ACPI) += acpi.o $(xen-pad-y)
@@ -33,6 +35,7 @@ obj-$(CONFIG_XEN_STUB)			+= xen-stub.o
 obj-$(CONFIG_XEN_ACPI_HOTPLUG_MEMORY)	+= xen-acpi-memhotplug.o
 obj-$(CONFIG_XEN_ACPI_HOTPLUG_CPU)	+= xen-acpi-cpuhotplug.o
 obj-$(CONFIG_XEN_ACPI_PROCESSOR)	+= xen-acpi-processor.o
+obj-$(CONFIG_XEN_EFI)			+= efi.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
 xen-gntalloc-y				:= gntalloc.o
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index b7a506f2bb1..5c660c77f03 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -426,20 +426,18 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 		 * p2m are consistent.
 		 */
 		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long p;
-			struct page   *scratch_page = get_balloon_scratch_page();
-
 			if (!PageHighMem(page)) {
+				struct page *scratch_page = get_balloon_scratch_page();
+
 				ret = HYPERVISOR_update_va_mapping(
 						(unsigned long)__va(pfn << PAGE_SHIFT),
 						pfn_pte(page_to_pfn(scratch_page),
 							PAGE_KERNEL_RO), 0);
 				BUG_ON(ret);
-			}
-			p = page_to_pfn(scratch_page);
-			__set_phys_to_machine(pfn, pfn_to_mfn(p));
 
-			put_balloon_scratch_page();
+				put_balloon_scratch_page();
+			}
+			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 		}
 #endif
 
diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c
new file mode 100644
index 00000000000..31f618a4966
--- /dev/null
+++ b/drivers/xen/efi.c
@@ -0,0 +1,368 @@
+/*
+ * EFI support for Xen.
+ *
+ * Copyright (C) 1999 VA Linux Systems
+ * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
+ * Copyright (C) 1999-2002 Hewlett-Packard Co.
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ *	Stephane Eranian <eranian@hpl.hp.com>
+ * Copyright (C) 2005-2008 Intel Co.
+ *	Fenghua Yu <fenghua.yu@intel.com>
+ *	Bibo Mao <bibo.mao@intel.com>
+ *	Chandramouli Narayanan <mouli@linux.intel.com>
+ *	Huang Ying <ying.huang@intel.com>
+ * Copyright (C) 2011 Novell Co.
+ *	Jan Beulich <JBeulich@suse.com>
+ * Copyright (C) 2011-2012 Oracle Co.
+ *	Liang Tang <liang.tang@oracle.com>
+ * Copyright (c) 2014 Oracle Co., Daniel Kiper
+ */
+
+#include <linux/bug.h>
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/string.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/platform.h>
+#include <xen/xen.h>
+
+#include <asm/xen/hypercall.h>
+
+#define INIT_EFI_OP(name) \
+	{.cmd = XENPF_efi_runtime_call, \
+	 .u.efi_runtime_call.function = XEN_EFI_##name, \
+	 .u.efi_runtime_call.misc = 0}
+
+#define efi_data(op)	(op.u.efi_runtime_call)
+
+static efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_time);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	if (tm) {
+		BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.get_time.time));
+		memcpy(tm, &efi_data(op).u.get_time.time, sizeof(*tm));
+	}
+
+	if (tc) {
+		tc->resolution = efi_data(op).u.get_time.resolution;
+		tc->accuracy = efi_data(op).u.get_time.accuracy;
+		tc->sets_to_zero = !!(efi_data(op).misc &
+				      XEN_EFI_GET_TIME_SET_CLEARS_NS);
+	}
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_set_time(efi_time_t *tm)
+{
+	struct xen_platform_op op = INIT_EFI_OP(set_time);
+
+	BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.set_time));
+	memcpy(&efi_data(op).u.set_time, tm, sizeof(*tm));
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled,
+					    efi_bool_t *pending,
+					    efi_time_t *tm)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	if (tm) {
+		BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.get_wakeup_time));
+		memcpy(tm, &efi_data(op).u.get_wakeup_time, sizeof(*tm));
+	}
+
+	if (enabled)
+		*enabled = !!(efi_data(op).misc & XEN_EFI_GET_WAKEUP_TIME_ENABLED);
+
+	if (pending)
+		*pending = !!(efi_data(op).misc & XEN_EFI_GET_WAKEUP_TIME_PENDING);
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+{
+	struct xen_platform_op op = INIT_EFI_OP(set_wakeup_time);
+
+	BUILD_BUG_ON(sizeof(*tm) != sizeof(efi_data(op).u.set_wakeup_time));
+	if (enabled)
+		efi_data(op).misc = XEN_EFI_SET_WAKEUP_TIME_ENABLE;
+	if (tm)
+		memcpy(&efi_data(op).u.set_wakeup_time, tm, sizeof(*tm));
+	else
+		efi_data(op).misc |= XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY;
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_get_variable(efi_char16_t *name,
+					 efi_guid_t *vendor,
+					 u32 *attr,
+					 unsigned long *data_size,
+					 void *data)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_variable);
+
+	set_xen_guest_handle(efi_data(op).u.get_variable.name, name);
+	BUILD_BUG_ON(sizeof(*vendor) !=
+		     sizeof(efi_data(op).u.get_variable.vendor_guid));
+	memcpy(&efi_data(op).u.get_variable.vendor_guid, vendor, sizeof(*vendor));
+	efi_data(op).u.get_variable.size = *data_size;
+	set_xen_guest_handle(efi_data(op).u.get_variable.data, data);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*data_size = efi_data(op).u.get_variable.size;
+	if (attr)
+		*attr = efi_data(op).misc;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
+					      efi_char16_t *name,
+					      efi_guid_t *vendor)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_next_variable_name);
+
+	efi_data(op).u.get_next_variable_name.size = *name_size;
+	set_xen_guest_handle(efi_data(op).u.get_next_variable_name.name, name);
+	BUILD_BUG_ON(sizeof(*vendor) !=
+		     sizeof(efi_data(op).u.get_next_variable_name.vendor_guid));
+	memcpy(&efi_data(op).u.get_next_variable_name.vendor_guid, vendor,
+	       sizeof(*vendor));
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*name_size = efi_data(op).u.get_next_variable_name.size;
+	memcpy(vendor, &efi_data(op).u.get_next_variable_name.vendor_guid,
+	       sizeof(*vendor));
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_set_variable(efi_char16_t *name,
+					 efi_guid_t *vendor,
+					 u32 attr,
+					 unsigned long data_size,
+					 void *data)
+{
+	struct xen_platform_op op = INIT_EFI_OP(set_variable);
+
+	set_xen_guest_handle(efi_data(op).u.set_variable.name, name);
+	efi_data(op).misc = attr;
+	BUILD_BUG_ON(sizeof(*vendor) !=
+		     sizeof(efi_data(op).u.set_variable.vendor_guid));
+	memcpy(&efi_data(op).u.set_variable.vendor_guid, vendor, sizeof(*vendor));
+	efi_data(op).u.set_variable.size = data_size;
+	set_xen_guest_handle(efi_data(op).u.set_variable.data, data);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_query_variable_info(u32 attr,
+						u64 *storage_space,
+						u64 *remaining_space,
+						u64 *max_variable_size)
+{
+	struct xen_platform_op op = INIT_EFI_OP(query_variable_info);
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	efi_data(op).u.query_variable_info.attr = attr;
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*storage_space = efi_data(op).u.query_variable_info.max_store_size;
+	*remaining_space = efi_data(op).u.query_variable_info.remain_store_size;
+	*max_variable_size = efi_data(op).u.query_variable_info.max_size;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_get_next_high_mono_count(u32 *count)
+{
+	struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count);
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*count = efi_data(op).misc;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
+					   unsigned long count,
+					   unsigned long sg_list)
+{
+	struct xen_platform_op op = INIT_EFI_OP(update_capsule);
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	set_xen_guest_handle(efi_data(op).u.update_capsule.capsule_header_array,
+			     capsules);
+	efi_data(op).u.update_capsule.capsule_count = count;
+	efi_data(op).u.update_capsule.sg_list = sg_list;
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	return efi_data(op).status;
+}
+
+static efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
+					       unsigned long count,
+					       u64 *max_size,
+					       int *reset_type)
+{
+	struct xen_platform_op op = INIT_EFI_OP(query_capsule_capabilities);
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	set_xen_guest_handle(efi_data(op).u.query_capsule_capabilities.capsule_header_array,
+					capsules);
+	efi_data(op).u.query_capsule_capabilities.capsule_count = count;
+
+	if (HYPERVISOR_dom0_op(&op) < 0)
+		return EFI_UNSUPPORTED;
+
+	*max_size = efi_data(op).u.query_capsule_capabilities.max_capsule_size;
+	*reset_type = efi_data(op).u.query_capsule_capabilities.reset_type;
+
+	return efi_data(op).status;
+}
+
+static efi_char16_t vendor[100] __initdata;
+
+static efi_system_table_t efi_systab_xen __initdata = {
+	.hdr = {
+		.signature	= EFI_SYSTEM_TABLE_SIGNATURE,
+		.revision	= 0, /* Initialized later. */
+		.headersize	= 0, /* Ignored by Linux Kernel. */
+		.crc32		= 0, /* Ignored by Linux Kernel. */
+		.reserved	= 0
+	},
+	.fw_vendor	= EFI_INVALID_TABLE_ADDR, /* Initialized later. */
+	.fw_revision	= 0,			  /* Initialized later. */
+	.con_in_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.con_in		= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.con_out_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.con_out	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.stderr_handle	= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.stderr		= EFI_INVALID_TABLE_ADDR, /* Not used under Xen. */
+	.runtime	= (efi_runtime_services_t *)EFI_INVALID_TABLE_ADDR,
+						  /* Not used under Xen. */
+	.boottime	= (efi_boot_services_t *)EFI_INVALID_TABLE_ADDR,
+						  /* Not used under Xen. */
+	.nr_tables	= 0,			  /* Initialized later. */
+	.tables		= EFI_INVALID_TABLE_ADDR  /* Initialized later. */
+};
+
+static const struct efi efi_xen __initconst = {
+	.systab                   = NULL, /* Initialized later. */
+	.runtime_version	  = 0,    /* Initialized later. */
+	.mps                      = EFI_INVALID_TABLE_ADDR,
+	.acpi                     = EFI_INVALID_TABLE_ADDR,
+	.acpi20                   = EFI_INVALID_TABLE_ADDR,
+	.smbios                   = EFI_INVALID_TABLE_ADDR,
+	.sal_systab               = EFI_INVALID_TABLE_ADDR,
+	.boot_info                = EFI_INVALID_TABLE_ADDR,
+	.hcdp                     = EFI_INVALID_TABLE_ADDR,
+	.uga                      = EFI_INVALID_TABLE_ADDR,
+	.uv_systab                = EFI_INVALID_TABLE_ADDR,
+	.fw_vendor                = EFI_INVALID_TABLE_ADDR,
+	.runtime                  = EFI_INVALID_TABLE_ADDR,
+	.config_table             = EFI_INVALID_TABLE_ADDR,
+	.get_time                 = xen_efi_get_time,
+	.set_time                 = xen_efi_set_time,
+	.get_wakeup_time          = xen_efi_get_wakeup_time,
+	.set_wakeup_time          = xen_efi_set_wakeup_time,
+	.get_variable             = xen_efi_get_variable,
+	.get_next_variable        = xen_efi_get_next_variable,
+	.set_variable             = xen_efi_set_variable,
+	.query_variable_info      = xen_efi_query_variable_info,
+	.update_capsule           = xen_efi_update_capsule,
+	.query_capsule_caps       = xen_efi_query_capsule_caps,
+	.get_next_high_mono_count = xen_efi_get_next_high_mono_count,
+	.reset_system             = NULL, /* Functionality provided by Xen. */
+	.set_virtual_address_map  = NULL, /* Not used under Xen. */
+	.memmap                   = NULL, /* Not used under Xen. */
+	.flags			  = 0     /* Initialized later. */
+};
+
+efi_system_table_t __init *xen_efi_probe(void)
+{
+	struct xen_platform_op op = {
+		.cmd = XENPF_firmware_info,
+		.u.firmware_info = {
+			.type = XEN_FW_EFI_INFO,
+			.index = XEN_FW_EFI_CONFIG_TABLE
+		}
+	};
+	union xenpf_efi_info *info = &op.u.firmware_info.u.efi_info;
+
+	if (!xen_initial_domain() || HYPERVISOR_dom0_op(&op) < 0)
+		return NULL;
+
+	/* Here we know that Xen runs on EFI platform. */
+
+	efi = efi_xen;
+
+	efi_systab_xen.tables = info->cfg.addr;
+	efi_systab_xen.nr_tables = info->cfg.nent;
+
+	op.cmd = XENPF_firmware_info;
+	op.u.firmware_info.type = XEN_FW_EFI_INFO;
+	op.u.firmware_info.index = XEN_FW_EFI_VENDOR;
+	info->vendor.bufsz = sizeof(vendor);
+	set_xen_guest_handle(info->vendor.name, vendor);
+
+	if (HYPERVISOR_dom0_op(&op) == 0) {
+		efi_systab_xen.fw_vendor = __pa_symbol(vendor);
+		efi_systab_xen.fw_revision = info->vendor.revision;
+	} else
+		efi_systab_xen.fw_vendor = __pa_symbol(L"UNKNOWN");
+
+	op.cmd = XENPF_firmware_info;
+	op.u.firmware_info.type = XEN_FW_EFI_INFO;
+	op.u.firmware_info.index = XEN_FW_EFI_VERSION;
+
+	if (HYPERVISOR_dom0_op(&op) == 0)
+		efi_systab_xen.hdr.revision = info->version;
+
+	op.cmd = XENPF_firmware_info;
+	op.u.firmware_info.type = XEN_FW_EFI_INFO;
+	op.u.firmware_info.index = XEN_FW_EFI_RT_VERSION;
+
+	if (HYPERVISOR_dom0_op(&op) == 0)
+		efi.runtime_version = info->version;
+
+	return &efi_systab_xen;
+}
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 6d325bda76d..eeba7544f0c 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -1168,7 +1168,8 @@ int gnttab_resume(void)
 
 int gnttab_suspend(void)
 {
-	gnttab_interface->unmap_frames();
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		gnttab_interface->unmap_frames();
 	return 0;
 }
 
@@ -1194,18 +1195,20 @@ static int gnttab_expand(unsigned int req_entries)
 int gnttab_init(void)
 {
 	int i;
+	unsigned long max_nr_grant_frames;
 	unsigned int max_nr_glist_frames, nr_glist_frames;
 	unsigned int nr_init_grefs;
 	int ret;
 
 	gnttab_request_version();
+	max_nr_grant_frames = gnttab_max_grant_frames();
 	nr_grant_frames = 1;
 
 	/* Determine the maximum number of frames required for the
 	 * grant reference free list on the current hypervisor.
 	 */
 	BUG_ON(grefs_per_grant_frame == 0);
-	max_nr_glist_frames = (gnttab_max_grant_frames() *
+	max_nr_glist_frames = (max_nr_grant_frames *
 			       grefs_per_grant_frame / RPP);
 
 	gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *),
@@ -1222,6 +1225,11 @@ int gnttab_init(void)
 		}
 	}
 
+	ret = arch_gnttab_init(max_nr_grant_frames,
+			       nr_status_frames(max_nr_grant_frames));
+	if (ret < 0)
+		goto ini_nomem;
+
 	if (gnttab_setup() < 0) {
 		ret = -ENODEV;
 		goto ini_nomem;
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index c3667b202f2..5f1e1f3cd18 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -88,7 +88,6 @@ static int xen_suspend(void *data)
 
 	if (!si->cancelled) {
 		xen_irq_resume();
-		xen_console_resume();
 		xen_timer_resume();
 	}
 
@@ -135,6 +134,10 @@ static void do_suspend(void)
 
 	err = stop_machine(xen_suspend, &si, cpumask_of(0));
 
+	/* Resume console as early as possible. */
+	if (!si.cancelled)
+		xen_console_resume();
+
 	raw_notifier_call_chain(&xen_resume_notifier, 0, NULL);
 
 	dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE);
diff --git a/drivers/zorro/names.c b/drivers/zorro/names.c
index 6f3fd9903ac..83eedddbb79 100644
--- a/drivers/zorro/names.c
+++ b/drivers/zorro/names.c
@@ -46,13 +46,13 @@ struct zorro_manuf_info {
 #include "devlist.h"
 
 static struct zorro_manuf_info __initdata zorro_manuf_list[] = {
-#define MANUF( manuf, name )		{ 0x##manuf, sizeof(__prods_##manuf) / sizeof(struct zorro_prod_info), __manufstr_##manuf, __prods_##manuf },
+#define MANUF( manuf, name )		{ 0x##manuf, ARRAY_SIZE(__prods_##manuf), __manufstr_##manuf, __prods_##manuf },
 #define ENDMANUF()
 #define PRODUCT( manuf, prod, name )
 #include "devlist.h"
 };
 
-#define MANUFS (sizeof(zorro_manuf_list)/sizeof(struct zorro_manuf_info))
+#define MANUFS ARRAY_SIZE(zorro_manuf_list)
 
 void __init zorro_name_device(struct zorro_dev *dev)
 {
diff --git a/firmware/Makefile b/firmware/Makefile
index cbb09ce9730..0862d34cf7d 100644
--- a/firmware/Makefile
+++ b/firmware/Makefile
@@ -4,10 +4,10 @@
 
 # Create $(fwabs) from $(CONFIG_EXTRA_FIRMWARE_DIR) -- if it doesn't have a
 # leading /, it's relative to $(srctree).
-fwdir := $(subst ",,$(CONFIG_EXTRA_FIRMWARE_DIR))
+fwdir := $(subst $(quote),,$(CONFIG_EXTRA_FIRMWARE_DIR))
 fwabs := $(addprefix $(srctree)/,$(filter-out /%,$(fwdir)))$(filter /%,$(fwdir))
 
-fw-external-y := $(subst ",,$(CONFIG_EXTRA_FIRMWARE))
+fw-external-y := $(subst $(quote),,$(CONFIG_EXTRA_FIRMWARE))
 
 # There are three cases to care about:
 # 1. Building kernel with CONFIG_FIRMWARE_IN_KERNEL=y -- $(fw-shipped-y) should
@@ -138,12 +138,6 @@ fw-shipped-$(CONFIG_YAM) += yam/1200.bin yam/9600.bin
 
 fw-shipped-all := $(fw-shipped-y) $(fw-shipped-m) $(fw-shipped-)
 
-# Directories which we _might_ need to create, so we have a rule for them.
-firmware-dirs := $(sort $(addprefix $(objtree)/$(obj)/,$(dir $(fw-external-y) $(fw-shipped-all))))
-
-quiet_cmd_mkdir = MKDIR   $(patsubst $(objtree)/%,%,$@)
-      cmd_mkdir = mkdir -p $@
-
 quiet_cmd_ihex  = IHEX    $@
       cmd_ihex  = $(OBJCOPY) -Iihex -Obinary $< $@
 
@@ -184,21 +178,10 @@ wordsize_deps := $(wildcard include/config/64bit.h include/config/32bit.h \
 		include/config/superh32.h include/config/superh64.h \
 		include/config/x86_32.h include/config/x86_64.h)
 
-# Workaround for make < 3.81, where .SECONDEXPANSION doesn't work.
-# It'll end up depending on these targets, so make them a PHONY rule which
-# depends on _all_ the directories in $(firmware-dirs), and it'll work out OK.
-PHONY += $(objtree)/$$(%) $(objtree)/$(obj)/$$(%)
-$(objtree)/$$(%) $(objtree)/$(obj)/$$(%): $(firmware-dirs)
-	@true
-
-# For the $$(dir %) trick, where we need % to be expanded first.
-.SECONDEXPANSION:
-
-$(patsubst %,$(obj)/%.gen.S, $(fw-shipped-y)): %: $(wordsize_deps) \
-		| $(objtree)/$$(dir %)
+$(patsubst %,$(obj)/%.gen.S, $(fw-shipped-y)): %: $(wordsize_deps)
 	$(call cmd,fwbin,$(patsubst %.gen.S,%,$@))
 $(patsubst %,$(obj)/%.gen.S, $(fw-external-y)): %: $(wordsize_deps) \
-		include/config/extra/firmware/dir.h | $(objtree)/$$(dir %)
+		include/config/extra/firmware/dir.h
 	$(call cmd,fwbin,$(fwabs)/$(patsubst $(obj)/%.gen.S,%,$@))
 
 # The .o files depend on the binaries directly; the .S files don't.
@@ -207,7 +190,7 @@ $(patsubst %,$(obj)/%.gen.o, $(fw-external-y)): $(obj)/%.gen.o: $(fwdir)/%
 
 # .ihex is used just as a simple way to hold binary files in a source tree
 # where binaries are frowned upon. They are directly converted with objcopy.
-$(obj)/%: $(obj)/%.ihex | $(objtree)/$(obj)/$$(dir %)
+$(obj)/%: $(obj)/%.ihex
 	$(call cmd,ihex)
 
 # Don't depend on ihex2fw if we're installing and it already exists.
@@ -226,19 +209,22 @@ endif
 # is actually meaningful, because the firmware has to be loaded in a certain
 # order rather than as a single binary blob. Thus, we convert them into our
 # more compact binary representation of ihex records (<linux/ihex.h>)
-$(obj)/%.fw: $(obj)/%.HEX $(ihex2fw_dep) | $(objtree)/$(obj)/$$(dir %)
+$(obj)/%.fw: $(obj)/%.HEX $(ihex2fw_dep)
 	$(call cmd,ihex2fw)
 
 # .H16 is our own modified form of Intel HEX, with 16-bit length for records.
-$(obj)/%.fw: $(obj)/%.H16 $(ihex2fw_dep) | $(objtree)/$(obj)/$$(dir %)
+$(obj)/%.fw: $(obj)/%.H16 $(ihex2fw_dep)
 	$(call cmd,h16tofw)
 
-$(firmware-dirs):
-	$(call cmd,mkdir)
-
 obj-y				 += $(patsubst %,%.gen.o, $(fw-external-y))
 obj-$(CONFIG_FIRMWARE_IN_KERNEL) += $(patsubst %,%.gen.o, $(fw-shipped-y))
 
+ifeq ($(KBUILD_SRC),)
+# Makefile.build only creates subdirectories for O= builds, but external
+# firmware might live outside the kernel source tree
+_dummy := $(foreach d,$(addprefix $(obj)/,$(dir $(fw-external-y))), $(shell [ -d $(d) ] || mkdir -p $(d)))
+endif
+
 # Remove .S files and binaries created from ihex
 # (during 'make clean' .config isn't included so they're all in $(fw-shipped-))
 targets := $(fw-shipped-) $(patsubst $(obj)/%,%, \
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index c71e88602ff..cc1cfae726b 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -259,8 +259,7 @@ static int v9fs_launder_page(struct page *page)
  *
  */
 static ssize_t
-v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-	       loff_t pos, unsigned long nr_segs)
+v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
 	/*
 	 * FIXME
@@ -269,7 +268,7 @@ v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	 */
 	p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) off/no(%lld/%lu) EINVAL\n",
 		 iocb->ki_filp->f_path.dentry->d_name.name,
-		 (long long)pos, nr_segs);
+		 (long long)pos, iter->nr_segs);
 
 	return -EINVAL;
 }
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 96e55076069..520c11c2dcc 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -692,7 +692,7 @@ v9fs_cached_file_read(struct file *filp, char __user *data, size_t count,
 {
 	if (filp->f_flags & O_DIRECT)
 		return v9fs_direct_read(filp, data, count, offset);
-	return do_sync_read(filp, data, count, offset);
+	return new_sync_read(filp, data, count, offset);
 }
 
 /**
@@ -760,7 +760,7 @@ err_out:
 
 buff_write:
 	mutex_unlock(&inode->i_mutex);
-	return do_sync_write(filp, data, count, offsetp);
+	return new_sync_write(filp, data, count, offsetp);
 }
 
 /**
@@ -778,7 +778,7 @@ v9fs_cached_file_write(struct file *filp, const char __user * data,
 
 	if (filp->f_flags & O_DIRECT)
 		return v9fs_direct_write(filp, data, count, offset);
-	return do_sync_write(filp, data, count, offset);
+	return new_sync_write(filp, data, count, offset);
 }
 
 
@@ -847,8 +847,8 @@ const struct file_operations v9fs_cached_file_operations = {
 	.llseek = generic_file_llseek,
 	.read = v9fs_cached_file_read,
 	.write = v9fs_cached_file_write,
-	.aio_read = generic_file_aio_read,
-	.aio_write = generic_file_aio_write,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
 	.open = v9fs_file_open,
 	.release = v9fs_dir_release,
 	.lock = v9fs_file_lock,
@@ -860,8 +860,8 @@ const struct file_operations v9fs_cached_file_operations_dotl = {
 	.llseek = generic_file_llseek,
 	.read = v9fs_cached_file_read,
 	.write = v9fs_cached_file_write,
-	.aio_read = generic_file_aio_read,
-	.aio_write = generic_file_aio_write,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
 	.open = v9fs_file_open,
 	.release = v9fs_dir_release,
 	.lock = v9fs_file_lock_dotl,
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 00d140fb226..7fa4f7a7653 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -147,7 +147,7 @@ static umode_t p9mode2unixmode(struct v9fs_session_info *v9ses,
 		int major = -1, minor = -1;
 
 		strlcpy(ext, stat->extension, sizeof(ext));
-		sscanf(ext, "%c %u %u", &type, &major, &minor);
+		sscanf(ext, "%c %i %i", &type, &major, &minor);
 		switch (type) {
 		case 'c':
 			res |= S_IFCHR;
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c
index 04133a1fd9c..f95e01e058e 100644
--- a/fs/9p/xattr.c
+++ b/fs/9p/xattr.c
@@ -156,7 +156,7 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
 		offset += write_count;
 		value_len -= write_count;
 	}
-	retval = offset;
+	retval = 0;
 err:
 	p9_client_clunk(fid);
 	return retval;
diff --git a/fs/adfs/file.c b/fs/adfs/file.c
index a36da5382b4..07c9edce5aa 100644
--- a/fs/adfs/file.c
+++ b/fs/adfs/file.c
@@ -23,12 +23,12 @@
 
 const struct file_operations adfs_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= generic_file_fsync,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.splice_read	= generic_file_splice_read,
 };
 
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 0270303388e..a7fe57d2cd9 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -27,10 +27,10 @@ static int affs_file_release(struct inode *inode, struct file *filp);
 
 const struct file_operations affs_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.open		= affs_file_open,
 	.release	= affs_file_release,
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 66d50fe2ee4..932ce07948b 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -31,10 +31,10 @@ const struct file_operations afs_file_operations = {
 	.open		= afs_open,
 	.release	= afs_release,
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= afs_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= afs_file_write,
 	.mmap		= generic_file_readonly_mmap,
 	.splice_read	= generic_file_splice_read,
 	.fsync		= afs_fsync,
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 590b55f46d6..71d5982312f 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -747,8 +747,7 @@ extern int afs_write_end(struct file *file, struct address_space *mapping,
 extern int afs_writepage(struct page *, struct writeback_control *);
 extern int afs_writepages(struct address_space *, struct writeback_control *);
 extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *);
-extern ssize_t afs_file_write(struct kiocb *, const struct iovec *,
-			      unsigned long, loff_t);
+extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *);
 extern int afs_writeback_all(struct afs_vnode *);
 extern int afs_fsync(struct file *, loff_t, loff_t, int);
 
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 42dd2e499ed..35de0c04729 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -55,13 +55,13 @@ static int __init afs_get_client_UUID(void)
 	afs_uuid.time_low = uuidtime;
 	afs_uuid.time_mid = uuidtime >> 32;
 	afs_uuid.time_hi_and_version = (uuidtime >> 48) & AFS_UUID_TIMEHI_MASK;
-	afs_uuid.time_hi_and_version = AFS_UUID_VERSION_TIME;
+	afs_uuid.time_hi_and_version |= AFS_UUID_VERSION_TIME;
 
 	get_random_bytes(&clockseq, 2);
 	afs_uuid.clock_seq_low = clockseq;
 	afs_uuid.clock_seq_hi_and_reserved =
 		(clockseq >> 8) & AFS_UUID_CLOCKHI_MASK;
-	afs_uuid.clock_seq_hi_and_reserved = AFS_UUID_VARIANT_STD;
+	afs_uuid.clock_seq_hi_and_reserved |= AFS_UUID_VARIANT_STD;
 
 	_debug("AFS UUID: %08x-%04x-%04x-%02x%02x-%02x%02x%02x%02x%02x%02x",
 	       afs_uuid.time_low,
diff --git a/fs/afs/write.c b/fs/afs/write.c
index a890db4b989..ab6adfd5251 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -625,15 +625,14 @@ void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call)
 /*
  * write to an AFS file
  */
-ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov,
-		       unsigned long nr_segs, loff_t pos)
+ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp));
 	ssize_t result;
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(from);
 
-	_enter("{%x.%u},{%zu},%lu,",
-	       vnode->fid.vid, vnode->fid.vnode, count, nr_segs);
+	_enter("{%x.%u},{%zu},",
+	       vnode->fid.vid, vnode->fid.vnode, count);
 
 	if (IS_SWAPFILE(&vnode->vfs_inode)) {
 		printk(KERN_INFO
@@ -644,7 +643,7 @@ ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov,
 	if (!count)
 		return 0;
 
-	result = generic_file_aio_write(iocb, iov, nr_segs, pos);
+	result = generic_file_write_iter(iocb, from);
 	if (IS_ERR_VALUE(result)) {
 		_leave(" = %zd", result);
 		return result;
diff --git a/fs/aio.c b/fs/aio.c
index a0ed6c7d2cd..bd7ec2cc267 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -477,7 +477,7 @@ void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel)
 }
 EXPORT_SYMBOL(kiocb_set_cancel_fn);
 
-static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb)
+static int kiocb_cancel(struct kiocb *kiocb)
 {
 	kiocb_cancel_fn *old, *cancel;
 
@@ -506,6 +506,8 @@ static void free_ioctx(struct work_struct *work)
 
 	aio_free_ring(ctx);
 	free_percpu(ctx->cpu);
+	percpu_ref_exit(&ctx->reqs);
+	percpu_ref_exit(&ctx->users);
 	kmem_cache_free(kioctx_cachep, ctx);
 }
 
@@ -538,7 +540,7 @@ static void free_ioctx_users(struct percpu_ref *ref)
 				       struct kiocb, ki_list);
 
 		list_del_init(&req->ki_list);
-		kiocb_cancel(ctx, req);
+		kiocb_cancel(req);
 	}
 
 	spin_unlock_irq(&ctx->ctx_lock);
@@ -715,8 +717,8 @@ err_ctx:
 err:
 	mutex_unlock(&ctx->ring_lock);
 	free_percpu(ctx->cpu);
-	free_percpu(ctx->reqs.pcpu_count);
-	free_percpu(ctx->users.pcpu_count);
+	percpu_ref_exit(&ctx->reqs);
+	percpu_ref_exit(&ctx->users);
 	kmem_cache_free(kioctx_cachep, ctx);
 	pr_debug("error allocating ioctx %d\n", err);
 	return ERR_PTR(err);
@@ -727,42 +729,42 @@ err:
  *	when the processes owning a context have all exited to encourage
  *	the rapid destruction of the kioctx.
  */
-static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
+static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
 		struct completion *requests_done)
 {
-	if (!atomic_xchg(&ctx->dead, 1)) {
-		struct kioctx_table *table;
+	struct kioctx_table *table;
 
-		spin_lock(&mm->ioctx_lock);
-		rcu_read_lock();
-		table = rcu_dereference(mm->ioctx_table);
+	if (atomic_xchg(&ctx->dead, 1))
+		return -EINVAL;
 
-		WARN_ON(ctx != table->table[ctx->id]);
-		table->table[ctx->id] = NULL;
-		rcu_read_unlock();
-		spin_unlock(&mm->ioctx_lock);
 
-		/* percpu_ref_kill() will do the necessary call_rcu() */
-		wake_up_all(&ctx->wait);
+	spin_lock(&mm->ioctx_lock);
+	rcu_read_lock();
+	table = rcu_dereference(mm->ioctx_table);
 
-		/*
-		 * It'd be more correct to do this in free_ioctx(), after all
-		 * the outstanding kiocbs have finished - but by then io_destroy
-		 * has already returned, so io_setup() could potentially return
-		 * -EAGAIN with no ioctxs actually in use (as far as userspace
-		 *  could tell).
-		 */
-		aio_nr_sub(ctx->max_reqs);
+	WARN_ON(ctx != table->table[ctx->id]);
+	table->table[ctx->id] = NULL;
+	rcu_read_unlock();
+	spin_unlock(&mm->ioctx_lock);
 
-		if (ctx->mmap_size)
-			vm_munmap(ctx->mmap_base, ctx->mmap_size);
+	/* percpu_ref_kill() will do the necessary call_rcu() */
+	wake_up_all(&ctx->wait);
 
-		ctx->requests_done = requests_done;
-		percpu_ref_kill(&ctx->users);
-	} else {
-		if (requests_done)
-			complete(requests_done);
-	}
+	/*
+	 * It'd be more correct to do this in free_ioctx(), after all
+	 * the outstanding kiocbs have finished - but by then io_destroy
+	 * has already returned, so io_setup() could potentially return
+	 * -EAGAIN with no ioctxs actually in use (as far as userspace
+	 *  could tell).
+	 */
+	aio_nr_sub(ctx->max_reqs);
+
+	if (ctx->mmap_size)
+		vm_munmap(ctx->mmap_base, ctx->mmap_size);
+
+	ctx->requests_done = requests_done;
+	percpu_ref_kill(&ctx->users);
+	return 0;
 }
 
 /* wait_on_sync_kiocb:
@@ -830,16 +832,20 @@ void exit_aio(struct mm_struct *mm)
 static void put_reqs_available(struct kioctx *ctx, unsigned nr)
 {
 	struct kioctx_cpu *kcpu;
+	unsigned long flags;
 
 	preempt_disable();
 	kcpu = this_cpu_ptr(ctx->cpu);
 
+	local_irq_save(flags);
 	kcpu->reqs_available += nr;
+
 	while (kcpu->reqs_available >= ctx->req_batch * 2) {
 		kcpu->reqs_available -= ctx->req_batch;
 		atomic_add(ctx->req_batch, &ctx->reqs_available);
 	}
 
+	local_irq_restore(flags);
 	preempt_enable();
 }
 
@@ -847,10 +853,12 @@ static bool get_reqs_available(struct kioctx *ctx)
 {
 	struct kioctx_cpu *kcpu;
 	bool ret = false;
+	unsigned long flags;
 
 	preempt_disable();
 	kcpu = this_cpu_ptr(ctx->cpu);
 
+	local_irq_save(flags);
 	if (!kcpu->reqs_available) {
 		int old, avail = atomic_read(&ctx->reqs_available);
 
@@ -869,6 +877,7 @@ static bool get_reqs_available(struct kioctx *ctx)
 	ret = true;
 	kcpu->reqs_available--;
 out:
+	local_irq_restore(flags);
 	preempt_enable();
 	return ret;
 }
@@ -1021,6 +1030,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2)
 
 	/* everything turned out well, dispose of the aiocb. */
 	kiocb_free(iocb);
+	put_reqs_available(ctx, 1);
 
 	/*
 	 * We have to order our ring_info tail store above and test
@@ -1062,6 +1072,9 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	if (head == tail)
 		goto out;
 
+	head %= ctx->nr_events;
+	tail %= ctx->nr_events;
+
 	while (ret < nr) {
 		long avail;
 		struct io_event *ev;
@@ -1100,8 +1113,6 @@ static long aio_read_events_ring(struct kioctx *ctx,
 	flush_dcache_page(ctx->ring_pages[0]);
 
 	pr_debug("%li  h%u t%u\n", ret, head, tail);
-
-	put_reqs_available(ctx, ret);
 out:
 	mutex_unlock(&ctx->ring_lock);
 
@@ -1219,21 +1230,23 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 	if (likely(NULL != ioctx)) {
 		struct completion requests_done =
 			COMPLETION_INITIALIZER_ONSTACK(requests_done);
+		int ret;
 
 		/* Pass requests_done to kill_ioctx() where it can be set
 		 * in a thread-safe way. If we try to set it here then we have
 		 * a race condition if two io_destroy() called simultaneously.
 		 */
-		kill_ioctx(current->mm, ioctx, &requests_done);
+		ret = kill_ioctx(current->mm, ioctx, &requests_done);
 		percpu_ref_put(&ioctx->users);
 
 		/* Wait until all IO for the context are done. Otherwise kernel
 		 * keep using user-space buffers even if user thinks the context
 		 * is destroyed.
 		 */
-		wait_for_completion(&requests_done);
+		if (!ret)
+			wait_for_completion(&requests_done);
 
-		return 0;
+		return ret;
 	}
 	pr_debug("EINVAL: io_destroy: invalid context id\n");
 	return -EINVAL;
@@ -1241,6 +1254,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 
 typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *,
 			    unsigned long, loff_t);
+typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *);
 
 static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb,
 				     int rw, char __user *buf,
@@ -1298,7 +1312,9 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
 	int rw;
 	fmode_t mode;
 	aio_rw_op *rw_op;
+	rw_iter_op *iter_op;
 	struct iovec inline_vec, *iovec = &inline_vec;
+	struct iov_iter iter;
 
 	switch (opcode) {
 	case IOCB_CMD_PREAD:
@@ -1306,6 +1322,7 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
 		mode	= FMODE_READ;
 		rw	= READ;
 		rw_op	= file->f_op->aio_read;
+		iter_op	= file->f_op->read_iter;
 		goto rw_common;
 
 	case IOCB_CMD_PWRITE:
@@ -1313,12 +1330,13 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode,
 		mode	= FMODE_WRITE;
 		rw	= WRITE;
 		rw_op	= file->f_op->aio_write;
+		iter_op	= file->f_op->write_iter;
 		goto rw_common;
 rw_common:
 		if (unlikely(!(file->f_mode & mode)))
 			return -EBADF;
 
-		if (!rw_op)
+		if (!rw_op && !iter_op)
 			return -EINVAL;
 
 		ret = (opcode == IOCB_CMD_PREADV ||
@@ -1347,7 +1365,12 @@ rw_common:
 		if (rw == WRITE)
 			file_start_write(file);
 
-		ret = rw_op(req, iovec, nr_segs, req->ki_pos);
+		if (iter_op) {
+			iov_iter_init(&iter, rw, iovec, nr_segs, req->ki_nbytes);
+			ret = iter_op(req, &iter);
+		} else {
+			ret = rw_op(req, iovec, nr_segs, req->ki_pos);
+		}
 
 		if (rw == WRITE)
 			file_end_write(file);
@@ -1585,7 +1608,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 
 	kiocb = lookup_kiocb(ctx, iocb, key);
 	if (kiocb)
-		ret = kiocb_cancel(ctx, kiocb);
+		ret = kiocb_cancel(kiocb);
 	else
 		ret = -EINVAL;
 
diff --git a/fs/attr.c b/fs/attr.c
index 5d4e59d56e8..6530ced1969 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -50,14 +50,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 	if ((ia_valid & ATTR_UID) &&
 	    (!uid_eq(current_fsuid(), inode->i_uid) ||
 	     !uid_eq(attr->ia_uid, inode->i_uid)) &&
-	    !inode_capable(inode, CAP_CHOWN))
+	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
 		return -EPERM;
 
 	/* Make sure caller can chgrp. */
 	if ((ia_valid & ATTR_GID) &&
 	    (!uid_eq(current_fsuid(), inode->i_uid) ||
 	    (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) &&
-	    !inode_capable(inode, CAP_CHOWN))
+	    !capable_wrt_inode_uidgid(inode, CAP_CHOWN))
 		return -EPERM;
 
 	/* Make sure a caller can chmod. */
@@ -67,7 +67,7 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr)
 		/* Also check the setgid bit! */
 		if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
 				inode->i_gid) &&
-		    !inode_capable(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
 			attr->ia_mode &= ~S_ISGID;
 	}
 
@@ -160,7 +160,7 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 		umode_t mode = attr->ia_mode;
 
 		if (!in_group_p(inode->i_gid) &&
-		    !inode_capable(inode, CAP_FSETID))
+		    !capable_wrt_inode_uidgid(inode, CAP_FSETID))
 			mode &= ~S_ISGID;
 		inode->i_mode = mode;
 	}
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index d7bd395ab58..1c55388ae63 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -210,7 +210,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
 	int pipefd;
 	struct autofs_sb_info *sbi;
 	struct autofs_info *ino;
-	int pgrp;
+	int pgrp = 0;
 	bool pgrp_set = false;
 	int ret = -EINVAL;
 
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index ae289221833..e7f88ace1a2 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -23,10 +23,10 @@
 
 const struct file_operations bfs_file_operations = {
 	.llseek 	= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.splice_read	= generic_file_splice_read,
 };
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 83fba15cc39..6d7274619bf 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -165,14 +165,15 @@ blkdev_get_block(struct inode *inode, sector_t iblock,
 }
 
 static ssize_t
-blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs)
+blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+			loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 
-	return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset,
-				    nr_segs, blkdev_get_block, NULL, NULL, 0);
+	return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iter,
+				    offset, blkdev_get_block,
+				    NULL, NULL, 0);
 }
 
 int __sync_blockdev(struct block_device *bdev, int wait)
@@ -1571,43 +1572,38 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
  * Does not take i_mutex for the write and thus is not for general purpose
  * use.
  */
-ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			 unsigned long nr_segs, loff_t pos)
+ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct blk_plug plug;
 	ssize_t ret;
 
-	BUG_ON(iocb->ki_pos != pos);
-
 	blk_start_plug(&plug);
-	ret = __generic_file_aio_write(iocb, iov, nr_segs);
+	ret = __generic_file_write_iter(iocb, from);
 	if (ret > 0) {
 		ssize_t err;
-
-		err = generic_write_sync(file, pos, ret);
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
 		if (err < 0)
 			ret = err;
 	}
 	blk_finish_plug(&plug);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(blkdev_aio_write);
+EXPORT_SYMBOL_GPL(blkdev_write_iter);
 
-static ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov,
-			 unsigned long nr_segs, loff_t pos)
+static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *bd_inode = file->f_mapping->host;
 	loff_t size = i_size_read(bd_inode);
+	loff_t pos = iocb->ki_pos;
 
 	if (pos >= size)
 		return 0;
 
 	size -= pos;
-	if (size < iocb->ki_nbytes)
-		nr_segs = iov_shorten((struct iovec *)iov, nr_segs, size);
-	return generic_file_aio_read(iocb, iov, nr_segs, pos);
+	iov_iter_truncate(to, size);
+	return generic_file_read_iter(iocb, to);
 }
 
 /*
@@ -1639,10 +1635,10 @@ const struct file_operations def_blk_fops = {
 	.open		= blkdev_open,
 	.release	= blkdev_close,
 	.llseek		= block_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= blkdev_aio_read,
-	.aio_write	= blkdev_aio_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= blkdev_read_iter,
+	.write_iter	= blkdev_write_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
@@ -1650,7 +1646,7 @@ const struct file_operations def_blk_fops = {
 	.compat_ioctl	= compat_blkdev_ioctl,
 #endif
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 };
 
 int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index f341a98031d..6d1d0b93b1a 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -16,4 +16,4 @@ btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
 
 btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \
 	tests/extent-buffer-tests.o tests/btrfs-tests.o \
-	tests/extent-io-tests.o tests/inode-tests.o
+	tests/extent-io-tests.o tests/inode-tests.o tests/qgroup-tests.o
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index ff9b3995d45..9a0124a9585 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -79,13 +79,6 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans,
 	const char *name;
 	char *value = NULL;
 
-	if (acl) {
-		ret = posix_acl_valid(acl);
-		if (ret < 0)
-			return ret;
-		ret = 0;
-	}
-
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = POSIX_ACL_XATTR_ACCESS;
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 10db21fa092..e25564bfcb4 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -900,7 +900,11 @@ again:
 		goto out;
 	BUG_ON(ret == 0);
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (trans && likely(trans->type != __TRANS_DUMMY)) {
+#else
 	if (trans) {
+#endif
 		/*
 		 * look if there are updates for this ref queued and lock the
 		 * head
@@ -984,11 +988,12 @@ again:
 				goto out;
 		}
 		if (ref->count && ref->parent) {
-			if (extent_item_pos && !ref->inode_list) {
+			if (extent_item_pos && !ref->inode_list &&
+			    ref->level == 0) {
 				u32 bsz;
 				struct extent_buffer *eb;
 				bsz = btrfs_level_size(fs_info->extent_root,
-							info_level);
+							ref->level);
 				eb = read_tree_block(fs_info->extent_root,
 							   ref->parent, bsz, 0);
 				if (!eb || !extent_buffer_uptodate(eb)) {
@@ -1404,9 +1409,10 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
  * returns <0 on error
  */
 static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
-				struct btrfs_extent_item *ei, u32 item_size,
-				struct btrfs_extent_inline_ref **out_eiref,
-				int *out_type)
+				   struct btrfs_key *key,
+				   struct btrfs_extent_item *ei, u32 item_size,
+				   struct btrfs_extent_inline_ref **out_eiref,
+				   int *out_type)
 {
 	unsigned long end;
 	u64 flags;
@@ -1416,19 +1422,26 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
 		/* first call */
 		flags = btrfs_extent_flags(eb, ei);
 		if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
-			info = (struct btrfs_tree_block_info *)(ei + 1);
-			*out_eiref =
-				(struct btrfs_extent_inline_ref *)(info + 1);
+			if (key->type == BTRFS_METADATA_ITEM_KEY) {
+				/* a skinny metadata extent */
+				*out_eiref =
+				     (struct btrfs_extent_inline_ref *)(ei + 1);
+			} else {
+				WARN_ON(key->type != BTRFS_EXTENT_ITEM_KEY);
+				info = (struct btrfs_tree_block_info *)(ei + 1);
+				*out_eiref =
+				   (struct btrfs_extent_inline_ref *)(info + 1);
+			}
 		} else {
 			*out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1);
 		}
 		*ptr = (unsigned long)*out_eiref;
-		if ((void *)*ptr >= (void *)ei + item_size)
+		if ((unsigned long)(*ptr) >= (unsigned long)ei + item_size)
 			return -ENOENT;
 	}
 
 	end = (unsigned long)ei + item_size;
-	*out_eiref = (struct btrfs_extent_inline_ref *)*ptr;
+	*out_eiref = (struct btrfs_extent_inline_ref *)(*ptr);
 	*out_type = btrfs_extent_inline_ref_type(eb, *out_eiref);
 
 	*ptr += btrfs_extent_inline_ref_size(*out_type);
@@ -1447,8 +1460,8 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb,
  * <0 on error.
  */
 int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
-				struct btrfs_extent_item *ei, u32 item_size,
-				u64 *out_root, u8 *out_level)
+			    struct btrfs_key *key, struct btrfs_extent_item *ei,
+			    u32 item_size, u64 *out_root, u8 *out_level)
 {
 	int ret;
 	int type;
@@ -1459,8 +1472,8 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 		return 1;
 
 	while (1) {
-		ret = __get_extent_inline_ref(ptr, eb, ei, item_size,
-						&eiref, &type);
+		ret = __get_extent_inline_ref(ptr, eb, key, ei, item_size,
+					      &eiref, &type);
 		if (ret < 0)
 			return ret;
 
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index a910b27a8ad..86fc20fec28 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -40,8 +40,8 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
 			u64 *flags);
 
 int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
-				struct btrfs_extent_item *ei, u32 item_size,
-				u64 *out_root, u8 *out_level);
+			    struct btrfs_key *key, struct btrfs_extent_item *ei,
+			    u32 item_size, u64 *out_root, u8 *out_level);
 
 int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 				u64 extent_item_objectid,
@@ -55,8 +55,8 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
 int paths_from_inode(u64 inum, struct inode_fs_paths *ipath);
 
 int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info, u64 bytenr,
-				u64 time_seq, struct ulist **roots);
+			 struct btrfs_fs_info *fs_info, u64 bytenr,
+			 u64 time_seq, struct ulist **roots);
 char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 			u32 name_len, unsigned long name_off,
 			struct extent_buffer *eb_in, u64 parent,
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 2256e9cceec..4794923c410 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -284,4 +284,6 @@ static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
 		  &BTRFS_I(inode)->runtime_flags);
 }
 
+bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end);
+
 #endif
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 0e8388e72d8..ce92ae30250 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1093,6 +1093,7 @@ leaf_item_out_of_bounce_error:
 					next_stack =
 					    btrfsic_stack_frame_alloc();
 					if (NULL == next_stack) {
+						sf->error = -1;
 						btrfsic_release_block_ctx(
 								&sf->
 								next_block_ctx);
@@ -1190,8 +1191,10 @@ continue_with_current_node_stack_frame:
 				    sf->next_block_ctx.datav[0];
 
 				next_stack = btrfsic_stack_frame_alloc();
-				if (NULL == next_stack)
+				if (NULL == next_stack) {
+					sf->error = -1;
 					goto one_stack_frame_backwards;
+				}
 
 				next_stack->i = -1;
 				next_stack->block = sf->next_block;
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d43c544d3b6..1daea0b4718 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -821,7 +821,7 @@ static void free_workspace(int type, struct list_head *workspace)
 
 	spin_lock(workspace_lock);
 	if (*num_workspace < num_online_cpus()) {
-		list_add_tail(workspace, idle_workspace);
+		list_add(workspace, idle_workspace);
 		(*num_workspace)++;
 		spin_unlock(workspace_lock);
 		goto wake;
@@ -887,7 +887,7 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 
 	workspace = find_workspace(type);
 	if (IS_ERR(workspace))
-		return -1;
+		return PTR_ERR(workspace);
 
 	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
 						      start, len, pages,
@@ -923,7 +923,7 @@ static int btrfs_decompress_biovec(int type, struct page **pages_in,
 
 	workspace = find_workspace(type);
 	if (IS_ERR(workspace))
-		return -ENOMEM;
+		return PTR_ERR(workspace);
 
 	ret = btrfs_compress_op[type-1]->decompress_biovec(workspace, pages_in,
 							 disk_start,
@@ -945,7 +945,7 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 
 	workspace = find_workspace(type);
 	if (IS_ERR(workspace))
-		return -ENOMEM;
+		return PTR_ERR(workspace);
 
 	ret = btrfs_compress_op[type-1]->decompress(workspace, data_in,
 						  dest_page, start_byte,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 1bcfcdb23cf..aeab453b8e2 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -224,7 +224,8 @@ static struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
 static void add_root_to_dirty_list(struct btrfs_root *root)
 {
 	spin_lock(&root->fs_info->trans_lock);
-	if (root->track_dirty && list_empty(&root->dirty_list)) {
+	if (test_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state) &&
+	    list_empty(&root->dirty_list)) {
 		list_add(&root->dirty_list,
 			 &root->fs_info->dirty_cowonly_roots);
 	}
@@ -246,9 +247,10 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 	int level;
 	struct btrfs_disk_key disk_key;
 
-	WARN_ON(root->ref_cows && trans->transid !=
-		root->fs_info->running_transaction->transid);
-	WARN_ON(root->ref_cows && trans->transid != root->last_trans);
+	WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+		trans->transid != root->fs_info->running_transaction->transid);
+	WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+		trans->transid != root->last_trans);
 
 	level = btrfs_header_level(buf);
 	if (level == 0)
@@ -354,44 +356,14 @@ static inline void tree_mod_log_write_unlock(struct btrfs_fs_info *fs_info)
 }
 
 /*
- * Increment the upper half of tree_mod_seq, set lower half zero.
- *
- * Must be called with fs_info->tree_mod_seq_lock held.
- */
-static inline u64 btrfs_inc_tree_mod_seq_major(struct btrfs_fs_info *fs_info)
-{
-	u64 seq = atomic64_read(&fs_info->tree_mod_seq);
-	seq &= 0xffffffff00000000ull;
-	seq += 1ull << 32;
-	atomic64_set(&fs_info->tree_mod_seq, seq);
-	return seq;
-}
-
-/*
- * Increment the lower half of tree_mod_seq.
- *
- * Must be called with fs_info->tree_mod_seq_lock held. The way major numbers
- * are generated should not technically require a spin lock here. (Rationale:
- * incrementing the minor while incrementing the major seq number is between its
- * atomic64_read and atomic64_set calls doesn't duplicate sequence numbers, it
- * just returns a unique sequence number as usual.) We have decided to leave
- * that requirement in here and rethink it once we notice it really imposes a
- * problem on some workload.
+ * Pull a new tree mod seq number for our operation.
  */
-static inline u64 btrfs_inc_tree_mod_seq_minor(struct btrfs_fs_info *fs_info)
+static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
 {
 	return atomic64_inc_return(&fs_info->tree_mod_seq);
 }
 
 /*
- * return the last minor in the previous major tree_mod_seq number
- */
-u64 btrfs_tree_mod_seq_prev(u64 seq)
-{
-	return (seq & 0xffffffff00000000ull) - 1ull;
-}
-
-/*
  * This adds a new blocker to the tree mod log's blocker list if the @elem
  * passed does not already have a sequence number set. So when a caller expects
  * to record tree modifications, it should ensure to set elem->seq to zero
@@ -402,19 +374,16 @@ u64 btrfs_tree_mod_seq_prev(u64 seq)
 u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
 			   struct seq_list *elem)
 {
-	u64 seq;
-
 	tree_mod_log_write_lock(fs_info);
 	spin_lock(&fs_info->tree_mod_seq_lock);
 	if (!elem->seq) {
-		elem->seq = btrfs_inc_tree_mod_seq_major(fs_info);
+		elem->seq = btrfs_inc_tree_mod_seq(fs_info);
 		list_add_tail(&elem->list, &fs_info->tree_mod_seq_list);
 	}
-	seq = btrfs_inc_tree_mod_seq_minor(fs_info);
 	spin_unlock(&fs_info->tree_mod_seq_lock);
 	tree_mod_log_write_unlock(fs_info);
 
-	return seq;
+	return elem->seq;
 }
 
 void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
@@ -487,9 +456,7 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
 
 	BUG_ON(!tm);
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
-	tm->seq = btrfs_inc_tree_mod_seq_minor(fs_info);
-	spin_unlock(&fs_info->tree_mod_seq_lock);
+	tm->seq = btrfs_inc_tree_mod_seq(fs_info);
 
 	tm_root = &fs_info->tree_mod_log;
 	new = &tm_root->rb_node;
@@ -997,14 +964,14 @@ int btrfs_block_can_be_shared(struct btrfs_root *root,
 	 * snapshot and the block was not allocated by tree relocation,
 	 * we know the block is not shared.
 	 */
-	if (root->ref_cows &&
+	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
 	    buf != root->node && buf != root->commit_root &&
 	    (btrfs_header_generation(buf) <=
 	     btrfs_root_last_snapshot(&root->root_item) ||
 	     btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
 		return 1;
 #ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (root->ref_cows &&
+	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
 	    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
 		return 1;
 #endif
@@ -1146,9 +1113,10 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 
 	btrfs_assert_tree_locked(buf);
 
-	WARN_ON(root->ref_cows && trans->transid !=
-		root->fs_info->running_transaction->transid);
-	WARN_ON(root->ref_cows && trans->transid != root->last_trans);
+	WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+		trans->transid != root->fs_info->running_transaction->transid);
+	WARN_ON(test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+		trans->transid != root->last_trans);
 
 	level = btrfs_header_level(buf);
 
@@ -1193,7 +1161,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	if (root->ref_cows) {
+	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) {
 		ret = btrfs_reloc_cow_block(trans, root, buf, cow);
 		if (ret)
 			return ret;
@@ -1538,6 +1506,10 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root,
 				   struct extent_buffer *buf)
 {
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+		return 0;
+#endif
 	/* ensure we can see the force_cow */
 	smp_rmb();
 
@@ -1556,7 +1528,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
 	    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
 	    !(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
 	      btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) &&
-	    !root->force_cow)
+	    !test_bit(BTRFS_ROOT_FORCE_COW, &root->state))
 		return 0;
 	return 1;
 }
@@ -5125,7 +5097,17 @@ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
 		return ret;
 	btrfs_item_key(path->nodes[0], &found_key, 0);
 	ret = comp_keys(&found_key, &key);
-	if (ret < 0)
+	/*
+	 * We might have had an item with the previous key in the tree right
+	 * before we released our path. And after we released our path, that
+	 * item might have been pushed to the first slot (0) of the leaf we
+	 * were holding due to a tree balance. Alternatively, an item with the
+	 * previous key can exist as the only element of a leaf (big fat item).
+	 * Therefore account for these 2 cases, so that our callers (like
+	 * btrfs_previous_item) don't miss an existing item with a key matching
+	 * the previous key we computed above.
+	 */
+	if (ret <= 0)
 		return 0;
 	return 1;
 }
@@ -5736,6 +5718,24 @@ again:
 		ret = 0;
 		goto done;
 	}
+	/*
+	 * So the above check misses one case:
+	 * - after releasing the path above, someone has removed the item that
+	 *   used to be at the very end of the block, and balance between leafs
+	 *   gets another one with bigger key.offset to replace it.
+	 *
+	 * This one should be returned as well, or we can get leaf corruption
+	 * later(esp. in __btrfs_drop_extents()).
+	 *
+	 * And a bit more explanation about this check,
+	 * with ret > 0, the key isn't found, the path points to the slot
+	 * where it should be inserted, so the path->slots[0] item must be the
+	 * bigger one.
+	 */
+	if (nritems > 0 && ret > 0 && path->slots[0] == nritems - 1) {
+		ret = 0;
+		goto done;
+	}
 
 	while (level < BTRFS_MAX_LEVEL) {
 		if (!path->nodes[level]) {
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ba6b88528dc..be91397f4e9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -33,6 +33,7 @@
 #include <asm/kmap_types.h>
 #include <linux/pagemap.h>
 #include <linux/btrfs.h>
+#include <linux/workqueue.h>
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
@@ -756,6 +757,12 @@ struct btrfs_dir_item {
 
 #define BTRFS_ROOT_SUBVOL_RDONLY	(1ULL << 0)
 
+/*
+ * Internal in-memory flag that a subvolume has been marked for deletion but
+ * still visible as a directory
+ */
+#define BTRFS_ROOT_SUBVOL_DEAD		(1ULL << 48)
+
 struct btrfs_root_item {
 	struct btrfs_inode_item inode;
 	__le64 generation;
@@ -840,7 +847,10 @@ struct btrfs_disk_balance_args {
 	/* BTRFS_BALANCE_ARGS_* */
 	__le64 flags;
 
-	__le64 unused[8];
+	/* BTRFS_BALANCE_ARGS_LIMIT value */
+	__le64 limit;
+
+	__le64 unused[7];
 } __attribute__ ((__packed__));
 
 /*
@@ -1113,6 +1123,12 @@ struct btrfs_qgroup_limit_item {
 	__le64 rsv_excl;
 } __attribute__ ((__packed__));
 
+/* For raid type sysfs entries */
+struct raid_kobject {
+	int raid_type;
+	struct kobject kobj;
+};
+
 struct btrfs_space_info {
 	spinlock_t lock;
 
@@ -1163,7 +1179,7 @@ struct btrfs_space_info {
 	wait_queue_head_t wait;
 
 	struct kobject kobj;
-	struct kobject block_group_kobjs[BTRFS_NR_RAID_TYPES];
+	struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES];
 };
 
 #define	BTRFS_BLOCK_RSV_GLOBAL		1
@@ -1243,11 +1259,19 @@ struct btrfs_block_group_cache {
 	spinlock_t lock;
 	u64 pinned;
 	u64 reserved;
+	u64 delalloc_bytes;
 	u64 bytes_super;
 	u64 flags;
 	u64 sectorsize;
 	u64 cache_generation;
 
+	/*
+	 * It is just used for the delayed data space allocation because
+	 * only the data space allocation and the relative metadata update
+	 * can be done cross the transaction.
+	 */
+	struct rw_semaphore data_rwsem;
+
 	/* for raid56, this is a full stripe, without parity */
 	unsigned long full_stripe_len;
 
@@ -1313,6 +1337,8 @@ struct btrfs_stripe_hash_table {
 
 #define BTRFS_STRIPE_HASH_TABLE_BITS 11
 
+void btrfs_init_async_reclaim_work(struct work_struct *work);
+
 /* fs_info */
 struct reloc_control;
 struct btrfs_device;
@@ -1534,6 +1560,9 @@ struct btrfs_fs_info {
 	 */
 	struct btrfs_workqueue *fixup_workers;
 	struct btrfs_workqueue *delayed_workers;
+
+	/* the extent workers do delayed refs on the extent allocation tree */
+	struct btrfs_workqueue *extent_workers;
 	struct task_struct *transaction_kthread;
 	struct task_struct *cleaner_kthread;
 	int thread_pool_size;
@@ -1636,7 +1665,10 @@ struct btrfs_fs_info {
 
 	/* holds configuration and tracking. Protected by qgroup_lock */
 	struct rb_root qgroup_tree;
+	struct rb_root qgroup_op_tree;
 	spinlock_t qgroup_lock;
+	spinlock_t qgroup_op_lock;
+	atomic_t qgroup_op_seq;
 
 	/*
 	 * used to avoid frequently calling ulist_alloc()/ulist_free()
@@ -1688,6 +1720,9 @@ struct btrfs_fs_info {
 
 	struct semaphore uuid_tree_rescan_sem;
 	unsigned int update_uuid_tree_gen:1;
+
+	/* Used to reclaim the metadata space in the background. */
+	struct work_struct async_reclaim_work;
 };
 
 struct btrfs_subvolume_writers {
@@ -1696,6 +1731,26 @@ struct btrfs_subvolume_writers {
 };
 
 /*
+ * The state of btrfs root
+ */
+/*
+ * btrfs_record_root_in_trans is a multi-step process,
+ * and it can race with the balancing code.   But the
+ * race is very small, and only the first time the root
+ * is added to each transaction.  So IN_TRANS_SETUP
+ * is used to tell us when more checks are required
+ */
+#define BTRFS_ROOT_IN_TRANS_SETUP	0
+#define BTRFS_ROOT_REF_COWS		1
+#define BTRFS_ROOT_TRACK_DIRTY		2
+#define BTRFS_ROOT_IN_RADIX		3
+#define BTRFS_ROOT_DUMMY_ROOT		4
+#define BTRFS_ROOT_ORPHAN_ITEM_INSERTED	5
+#define BTRFS_ROOT_DEFRAG_RUNNING	6
+#define BTRFS_ROOT_FORCE_COW		7
+#define BTRFS_ROOT_MULTI_LOG_TASKS	8
+
+/*
  * in ram representation of the tree.  extent_root is used for all allocations
  * and for the extent tree extent_root root.
  */
@@ -1706,6 +1761,7 @@ struct btrfs_root {
 	struct btrfs_root *log_root;
 	struct btrfs_root *reloc_root;
 
+	unsigned long state;
 	struct btrfs_root_item root_item;
 	struct btrfs_key root_key;
 	struct btrfs_fs_info *fs_info;
@@ -1740,7 +1796,6 @@ struct btrfs_root {
 	/* Just be updated when the commit succeeds. */
 	int last_log_commit;
 	pid_t log_start_pid;
-	bool log_multiple_pids;
 
 	u64 objectid;
 	u64 last_trans;
@@ -1760,23 +1815,13 @@ struct btrfs_root {
 
 	u64 highest_objectid;
 
-	/* btrfs_record_root_in_trans is a multi-step process,
-	 * and it can race with the balancing code.   But the
-	 * race is very small, and only the first time the root
-	 * is added to each transaction.  So in_trans_setup
-	 * is used to tell us when more checks are required
-	 */
-	unsigned long in_trans_setup;
-	int ref_cows;
-	int track_dirty;
-	int in_radix;
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-	int dummy_root;
+	u64 alloc_bytenr;
 #endif
+
 	u64 defrag_trans_start;
 	struct btrfs_key defrag_progress;
 	struct btrfs_key defrag_max;
-	int defrag_running;
 	char *name;
 
 	/* the dirty list is only used by non-reference counted roots */
@@ -1790,7 +1835,6 @@ struct btrfs_root {
 	spinlock_t orphan_lock;
 	atomic_t orphan_inodes;
 	struct btrfs_block_rsv *orphan_block_rsv;
-	int orphan_item_inserted;
 	int orphan_cleanup_state;
 
 	spinlock_t inode_lock;
@@ -1808,8 +1852,6 @@ struct btrfs_root {
 	 */
 	dev_t anon_dev;
 
-	int force_cow;
-
 	spinlock_t root_item_lock;
 	atomic_t refs;
 
@@ -2788,6 +2830,11 @@ static inline bool btrfs_root_readonly(struct btrfs_root *root)
 	return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_RDONLY)) != 0;
 }
 
+static inline bool btrfs_root_dead(struct btrfs_root *root)
+{
+	return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0;
+}
+
 /* struct btrfs_root_backup */
 BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup,
 		   tree_root, 64);
@@ -2897,6 +2944,7 @@ btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
 	cpu->vend = le64_to_cpu(disk->vend);
 	cpu->target = le64_to_cpu(disk->target);
 	cpu->flags = le64_to_cpu(disk->flags);
+	cpu->limit = le64_to_cpu(disk->limit);
 }
 
 static inline void
@@ -2914,6 +2962,7 @@ btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
 	disk->vend = cpu_to_le64(cpu->vend);
 	disk->target = cpu_to_le64(cpu->target);
 	disk->flags = cpu_to_le64(cpu->flags);
+	disk->limit = cpu_to_le64(cpu->limit);
 }
 
 /* struct btrfs_super_block */
@@ -3236,6 +3285,8 @@ int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, unsigned long count);
+int btrfs_async_run_delayed_refs(struct btrfs_root *root,
+				 unsigned long count, int wait);
 int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 bytenr,
@@ -3273,11 +3324,11 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 				   struct btrfs_key *ins);
 int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes,
 			 u64 min_alloc_size, u64 empty_size, u64 hint_byte,
-			 struct btrfs_key *ins, int is_data);
+			 struct btrfs_key *ins, int is_data, int delalloc);
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf, int full_backref, int for_cow);
+		  struct extent_buffer *buf, int full_backref, int no_quota);
 int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf, int full_backref, int for_cow);
+		  struct extent_buffer *buf, int full_backref, int no_quota);
 int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				u64 bytenr, u64 num_bytes, u64 flags,
@@ -3285,9 +3336,10 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
 int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root,
 		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
-		      u64 owner, u64 offset, int for_cow);
+		      u64 owner, u64 offset, int no_quota);
 
-int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len);
+int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len,
+			       int delalloc);
 int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root,
 				       u64 start, u64 len);
 void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
@@ -3297,7 +3349,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 u64 bytenr, u64 num_bytes, u64 parent,
-			 u64 root_objectid, u64 owner, u64 offset, int for_cow);
+			 u64 root_objectid, u64 owner, u64 offset, int no_quota);
 
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 				    struct btrfs_root *root);
@@ -3385,7 +3437,6 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
 int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
 					 struct btrfs_fs_info *fs_info);
 int __get_raid_index(u64 flags);
-
 int btrfs_start_nocow_write(struct btrfs_root *root);
 void btrfs_end_nocow_write(struct btrfs_root *root);
 /* ctree.c */
@@ -3561,7 +3612,6 @@ u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
 			   struct seq_list *elem);
 void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 			    struct seq_list *elem);
-u64 btrfs_tree_mod_seq_prev(u64 seq);
 int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq);
 
 /* root-item.c */
@@ -3708,6 +3758,12 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		       struct bio *bio, u64 file_start, int contig);
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit);
+void btrfs_extent_item_to_extent_map(struct inode *inode,
+				     const struct btrfs_path *path,
+				     struct btrfs_file_extent_item *fi,
+				     const bool new_inline,
+				     struct extent_map *em);
+
 /* inode.c */
 struct btrfs_delalloc_work {
 	struct inode *inode;
@@ -4069,52 +4125,6 @@ void btrfs_reada_detach(void *handle);
 int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
 			 u64 start, int err);
 
-/* qgroup.c */
-struct qgroup_update {
-	struct list_head list;
-	struct btrfs_delayed_ref_node *node;
-	struct btrfs_delayed_extent_op *extent_op;
-};
-
-int btrfs_quota_enable(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info);
-int btrfs_quota_disable(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
-void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info);
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
-int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
-int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid,
-			char *name);
-int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 qgroupid);
-int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 qgroupid,
-		       struct btrfs_qgroup_limit *limit);
-int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);
-void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
-struct btrfs_delayed_extent_op;
-int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans,
-			    struct btrfs_delayed_ref_node *node,
-			    struct btrfs_delayed_extent_op *extent_op);
-int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info,
-			     struct btrfs_delayed_ref_node *node,
-			     struct btrfs_delayed_extent_op *extent_op);
-int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
-			 struct btrfs_qgroup_inherit *inherit);
-int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes);
-void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes);
-
-void assert_qgroups_uptodate(struct btrfs_trans_handle *trans);
-
 static inline int is_fstree(u64 rootid)
 {
 	if (rootid == BTRFS_FS_TREE_OBJECTID ||
@@ -4131,6 +4141,8 @@ static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info)
 /* Sanity test specific functions */
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 void btrfs_test_destroy_inode(struct inode *inode);
+int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
+			       u64 rfer, u64 excl);
 #endif
 
 #endif
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 33e561a8401..da775bfdebc 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -149,8 +149,8 @@ again:
 	spin_lock(&root->inode_lock);
 	ret = radix_tree_insert(&root->delayed_nodes_tree, ino, node);
 	if (ret == -EEXIST) {
-		kmem_cache_free(delayed_node_cache, node);
 		spin_unlock(&root->inode_lock);
+		kmem_cache_free(delayed_node_cache, node);
 		radix_tree_preload_end();
 		goto again;
 	}
@@ -267,14 +267,17 @@ static void __btrfs_release_delayed_node(
 	mutex_unlock(&delayed_node->mutex);
 
 	if (atomic_dec_and_test(&delayed_node->refs)) {
+		bool free = false;
 		struct btrfs_root *root = delayed_node->root;
 		spin_lock(&root->inode_lock);
 		if (atomic_read(&delayed_node->refs) == 0) {
 			radix_tree_delete(&root->delayed_nodes_tree,
 					  delayed_node->inode_id);
-			kmem_cache_free(delayed_node_cache, delayed_node);
+			free = true;
 		}
 		spin_unlock(&root->inode_lock);
+		if (free)
+			kmem_cache_free(delayed_node_cache, delayed_node);
 	}
 }
 
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 31299646024..6d16bea94e1 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -106,6 +106,10 @@ static int comp_entry(struct btrfs_delayed_ref_node *ref2,
 		return -1;
 	if (ref1->type > ref2->type)
 		return 1;
+	if (ref1->no_quota > ref2->no_quota)
+		return 1;
+	if (ref1->no_quota < ref2->no_quota)
+		return -1;
 	/* merging of sequenced refs is not allowed */
 	if (compare_seq) {
 		if (ref1->seq < ref2->seq)
@@ -635,7 +639,7 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 		     struct btrfs_delayed_ref_head *head_ref,
 		     struct btrfs_delayed_ref_node *ref, u64 bytenr,
 		     u64 num_bytes, u64 parent, u64 ref_root, int level,
-		     int action, int for_cow)
+		     int action, int no_quota)
 {
 	struct btrfs_delayed_ref_node *existing;
 	struct btrfs_delayed_tree_ref *full_ref;
@@ -645,6 +649,8 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	if (action == BTRFS_ADD_DELAYED_EXTENT)
 		action = BTRFS_ADD_DELAYED_REF;
 
+	if (is_fstree(ref_root))
+		seq = atomic64_read(&fs_info->tree_mod_seq);
 	delayed_refs = &trans->transaction->delayed_refs;
 
 	/* first set the basic ref node struct up */
@@ -655,9 +661,7 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	ref->action = action;
 	ref->is_head = 0;
 	ref->in_tree = 1;
-
-	if (need_ref_seq(for_cow, ref_root))
-		seq = btrfs_get_tree_mod_seq(fs_info, &trans->delayed_ref_elem);
+	ref->no_quota = no_quota;
 	ref->seq = seq;
 
 	full_ref = btrfs_delayed_node_to_tree_ref(ref);
@@ -697,7 +701,7 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 		     struct btrfs_delayed_ref_head *head_ref,
 		     struct btrfs_delayed_ref_node *ref, u64 bytenr,
 		     u64 num_bytes, u64 parent, u64 ref_root, u64 owner,
-		     u64 offset, int action, int for_cow)
+		     u64 offset, int action, int no_quota)
 {
 	struct btrfs_delayed_ref_node *existing;
 	struct btrfs_delayed_data_ref *full_ref;
@@ -709,6 +713,9 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 
 	delayed_refs = &trans->transaction->delayed_refs;
 
+	if (is_fstree(ref_root))
+		seq = atomic64_read(&fs_info->tree_mod_seq);
+
 	/* first set the basic ref node struct up */
 	atomic_set(&ref->refs, 1);
 	ref->bytenr = bytenr;
@@ -717,9 +724,7 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	ref->action = action;
 	ref->is_head = 0;
 	ref->in_tree = 1;
-
-	if (need_ref_seq(for_cow, ref_root))
-		seq = btrfs_get_tree_mod_seq(fs_info, &trans->delayed_ref_elem);
+	ref->no_quota = no_quota;
 	ref->seq = seq;
 
 	full_ref = btrfs_delayed_node_to_data_ref(ref);
@@ -762,12 +767,15 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root,  int level, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
-			       int for_cow)
+			       int no_quota)
 {
 	struct btrfs_delayed_tree_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 
+	if (!is_fstree(ref_root) || !fs_info->quota_enabled)
+		no_quota = 0;
+
 	BUG_ON(extent_op && extent_op->is_data);
 	ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
 	if (!ref)
@@ -793,10 +801,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 
 	add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
 				   num_bytes, parent, ref_root, level, action,
-				   for_cow);
+				   no_quota);
 	spin_unlock(&delayed_refs->lock);
-	if (need_ref_seq(for_cow, ref_root))
-		btrfs_qgroup_record_ref(trans, &ref->node, extent_op);
 
 	return 0;
 }
@@ -810,12 +816,15 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
-			       int for_cow)
+			       int no_quota)
 {
 	struct btrfs_delayed_data_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 
+	if (!is_fstree(ref_root) || !fs_info->quota_enabled)
+		no_quota = 0;
+
 	BUG_ON(extent_op && !extent_op->is_data);
 	ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
 	if (!ref)
@@ -841,10 +850,8 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 
 	add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
 				   num_bytes, parent, ref_root, owner, offset,
-				   action, for_cow);
+				   action, no_quota);
 	spin_unlock(&delayed_refs->lock);
-	if (need_ref_seq(for_cow, ref_root))
-		btrfs_qgroup_record_ref(trans, &ref->node, extent_op);
 
 	return 0;
 }
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 4ba9b93022f..a764e2340d4 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -52,6 +52,7 @@ struct btrfs_delayed_ref_node {
 
 	unsigned int action:8;
 	unsigned int type:8;
+	unsigned int no_quota:1;
 	/* is this node still in the rbtree? */
 	unsigned int is_head:1;
 	unsigned int in_tree:1;
@@ -196,14 +197,14 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root, int level, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
-			       int for_cow);
+			       int no_quota);
 int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 			       struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
-			       int for_cow);
+			       int no_quota);
 int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
 				struct btrfs_trans_handle *trans,
 				u64 bytenr, u64 num_bytes,
@@ -231,25 +232,6 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
 			    u64 seq);
 
 /*
- * delayed refs with a ref_seq > 0 must be held back during backref walking.
- * this only applies to items in one of the fs-trees. for_cow items never need
- * to be held back, so they won't get a ref_seq number.
- */
-static inline int need_ref_seq(int for_cow, u64 rootid)
-{
-	if (for_cow)
-		return 0;
-
-	if (rootid == BTRFS_FS_TREE_OBJECTID)
-		return 1;
-
-	if ((s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID)
-		return 1;
-
-	return 0;
-}
-
-/*
  * a node might live in a head or a regular ref, this lets you
  * test for the proper type to use.
  */
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 9f2290509ac..eea26e1b2fd 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -36,6 +36,7 @@
 #include "check-integrity.h"
 #include "rcu-string.h"
 #include "dev-replace.h"
+#include "sysfs.h"
 
 static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 				       int scrub_ret);
@@ -313,7 +314,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 
 	if (btrfs_fs_incompat(fs_info, RAID56)) {
 		btrfs_warn(fs_info, "dev_replace cannot yet handle RAID5/RAID6");
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	switch (args->start.cont_reading_from_srcdev_mode) {
@@ -562,6 +563,10 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		fs_info->fs_devices->latest_bdev = tgt_device->bdev;
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 
+	/* replace the sysfs entry */
+	btrfs_kobj_rm_device(fs_info, src_device);
+	btrfs_kobj_add_device(fs_info, tgt_device);
+
 	btrfs_rm_dev_replace_blocked(fs_info);
 
 	btrfs_rm_dev_replace_srcdev(fs_info, src_device);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 983314932af..08e65e9cf2a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -49,6 +49,7 @@
 #include "dev-replace.h"
 #include "raid56.h"
 #include "sysfs.h"
+#include "qgroup.h"
 
 #ifdef CONFIG_X86
 #include <asm/cpufeature.h>
@@ -368,7 +369,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 out:
 	unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
 			     &cached_state, GFP_NOFS);
-	btrfs_tree_read_unlock_blocking(eb);
+	if (need_lock)
+		btrfs_tree_read_unlock_blocking(eb);
 	return ret;
 }
 
@@ -1109,6 +1111,11 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						 u64 bytenr, u32 blocksize)
 {
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+		return alloc_test_extent_buffer(root->fs_info, bytenr,
+						blocksize);
+#endif
 	return alloc_extent_buffer(root->fs_info, bytenr, blocksize);
 }
 
@@ -1201,10 +1208,7 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	root->nodesize = nodesize;
 	root->leafsize = leafsize;
 	root->stripesize = stripesize;
-	root->ref_cows = 0;
-	root->track_dirty = 0;
-	root->in_radix = 0;
-	root->orphan_item_inserted = 0;
+	root->state = 0;
 	root->orphan_cleanup_state = 0;
 
 	root->objectid = objectid;
@@ -1265,7 +1269,6 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	else
 		root->defrag_trans_start = 0;
 	init_completion(&root->kobj_unregister);
-	root->defrag_running = 0;
 	root->root_key.objectid = objectid;
 	root->anon_dev = 0;
 
@@ -1290,7 +1293,8 @@ struct btrfs_root *btrfs_alloc_dummy_root(void)
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 	__setup_root(4096, 4096, 4096, 4096, root, NULL, 1);
-	root->dummy_root = 1;
+	set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
+	root->alloc_bytenr = 0;
 
 	return root;
 }
@@ -1341,8 +1345,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 
 	root->commit_root = btrfs_root_node(root);
-	root->track_dirty = 1;
-
+	set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
 
 	root->root_item.flags = 0;
 	root->root_item.byte_limit = 0;
@@ -1371,6 +1374,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 fail:
 	if (leaf) {
 		btrfs_tree_unlock(leaf);
+		free_extent_buffer(root->commit_root);
 		free_extent_buffer(leaf);
 	}
 	kfree(root);
@@ -1396,13 +1400,15 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
 	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
 	root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;
+
 	/*
+	 * DON'T set REF_COWS for log trees
+	 *
 	 * log trees do not get reference counted because they go away
 	 * before a real commit is actually done.  They do store pointers
 	 * to file data extents, and those reference counts still get
 	 * updated (along with back refs to the log tree).
 	 */
-	root->ref_cows = 0;
 
 	leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
 				      BTRFS_TREE_LOG_OBJECTID, NULL,
@@ -1536,7 +1542,7 @@ struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
 		return root;
 
 	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
-		root->ref_cows = 1;
+		set_bit(BTRFS_ROOT_REF_COWS, &root->state);
 		btrfs_check_and_init_root_item(&root->root_item);
 	}
 
@@ -1606,7 +1612,7 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
 				(unsigned long)root->root_key.objectid,
 				root);
 	if (ret == 0)
-		root->in_radix = 1;
+		set_bit(BTRFS_ROOT_IN_RADIX, &root->state);
 	spin_unlock(&fs_info->fs_roots_radix_lock);
 	radix_tree_preload_end();
 
@@ -1662,7 +1668,7 @@ again:
 	if (ret < 0)
 		goto fail;
 	if (ret == 0)
-		root->orphan_item_inserted = 1;
+		set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
 
 	ret = btrfs_insert_fs_root(fs_info, root);
 	if (ret) {
@@ -2064,6 +2070,7 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->readahead_workers);
 	btrfs_destroy_workqueue(fs_info->flush_workers);
 	btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
+	btrfs_destroy_workqueue(fs_info->extent_workers);
 }
 
 static void free_root_extent_buffers(struct btrfs_root *root)
@@ -2090,7 +2097,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 }
 
-static void del_fs_roots(struct btrfs_fs_info *fs_info)
+void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
 {
 	int ret;
 	struct btrfs_root *gang[8];
@@ -2101,7 +2108,7 @@ static void del_fs_roots(struct btrfs_fs_info *fs_info)
 				     struct btrfs_root, root_list);
 		list_del(&gang[0]->root_list);
 
-		if (gang[0]->in_radix) {
+		if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state)) {
 			btrfs_drop_and_free_fs_root(fs_info, gang[0]);
 		} else {
 			free_extent_buffer(gang[0]->node);
@@ -2221,6 +2228,7 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->free_chunk_lock);
 	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	spin_lock_init(&fs_info->super_lock);
+	spin_lock_init(&fs_info->qgroup_op_lock);
 	spin_lock_init(&fs_info->buffer_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->reloc_mutex);
@@ -2246,6 +2254,7 @@ int open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->async_submit_draining, 0);
 	atomic_set(&fs_info->nr_async_bios, 0);
 	atomic_set(&fs_info->defrag_running, 0);
+	atomic_set(&fs_info->qgroup_op_seq, 0);
 	atomic64_set(&fs_info->tree_mod_seq, 0);
 	fs_info->sb = sb;
 	fs_info->max_inline = 8192 * 1024;
@@ -2291,6 +2300,7 @@ int open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->balance_cancel_req, 0);
 	fs_info->balance_ctl = NULL;
 	init_waitqueue_head(&fs_info->balance_wait_q);
+	btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work);
 
 	sb->s_blocksize = 4096;
 	sb->s_blocksize_bits = blksize_bits(4096);
@@ -2354,6 +2364,7 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->qgroup_lock);
 	mutex_init(&fs_info->qgroup_ioctl_lock);
 	fs_info->qgroup_tree = RB_ROOT;
+	fs_info->qgroup_op_tree = RB_ROOT;
 	INIT_LIST_HEAD(&fs_info->dirty_qgroups);
 	fs_info->qgroup_seq = 1;
 	fs_info->quota_enabled = 0;
@@ -2577,6 +2588,10 @@ int open_ctree(struct super_block *sb,
 		btrfs_alloc_workqueue("readahead", flags, max_active, 2);
 	fs_info->qgroup_rescan_workers =
 		btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0);
+	fs_info->extent_workers =
+		btrfs_alloc_workqueue("extent-refs", flags,
+				      min_t(u64, fs_devices->num_devices,
+					    max_active), 8);
 
 	if (!(fs_info->workers && fs_info->delalloc_workers &&
 	      fs_info->submit_workers && fs_info->flush_workers &&
@@ -2586,6 +2601,7 @@ int open_ctree(struct super_block *sb,
 	      fs_info->endio_freespace_worker && fs_info->rmw_workers &&
 	      fs_info->caching_workers && fs_info->readahead_workers &&
 	      fs_info->fixup_workers && fs_info->delayed_workers &&
+	      fs_info->fixup_workers && fs_info->extent_workers &&
 	      fs_info->qgroup_rescan_workers)) {
 		err = -ENOMEM;
 		goto fail_sb_buffer;
@@ -2693,7 +2709,7 @@ retry_root_backup:
 		ret = PTR_ERR(extent_root);
 		goto recovery_tree_root;
 	}
-	extent_root->track_dirty = 1;
+	set_bit(BTRFS_ROOT_TRACK_DIRTY, &extent_root->state);
 	fs_info->extent_root = extent_root;
 
 	location.objectid = BTRFS_DEV_TREE_OBJECTID;
@@ -2702,7 +2718,7 @@ retry_root_backup:
 		ret = PTR_ERR(dev_root);
 		goto recovery_tree_root;
 	}
-	dev_root->track_dirty = 1;
+	set_bit(BTRFS_ROOT_TRACK_DIRTY, &dev_root->state);
 	fs_info->dev_root = dev_root;
 	btrfs_init_devices_late(fs_info);
 
@@ -2712,13 +2728,13 @@ retry_root_backup:
 		ret = PTR_ERR(csum_root);
 		goto recovery_tree_root;
 	}
-	csum_root->track_dirty = 1;
+	set_bit(BTRFS_ROOT_TRACK_DIRTY, &csum_root->state);
 	fs_info->csum_root = csum_root;
 
 	location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
 	quota_root = btrfs_read_tree_root(tree_root, &location);
 	if (!IS_ERR(quota_root)) {
-		quota_root->track_dirty = 1;
+		set_bit(BTRFS_ROOT_TRACK_DIRTY, &quota_root->state);
 		fs_info->quota_enabled = 1;
 		fs_info->pending_quota_state = 1;
 		fs_info->quota_root = quota_root;
@@ -2733,7 +2749,7 @@ retry_root_backup:
 		create_uuid_tree = true;
 		check_uuid_tree = false;
 	} else {
-		uuid_root->track_dirty = 1;
+		set_bit(BTRFS_ROOT_TRACK_DIRTY, &uuid_root->state);
 		fs_info->uuid_root = uuid_root;
 		create_uuid_tree = false;
 		check_uuid_tree =
@@ -2889,7 +2905,9 @@ retry_root_backup:
 		if (ret)
 			goto fail_qgroup;
 
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(tree_root);
+		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret < 0) {
 			printk(KERN_WARNING
 			       "BTRFS: failed to recover relocation\n");
@@ -2966,7 +2984,7 @@ fail_qgroup:
 fail_trans_kthread:
 	kthread_stop(fs_info->transaction_kthread);
 	btrfs_cleanup_transaction(fs_info->tree_root);
-	del_fs_roots(fs_info);
+	btrfs_free_fs_roots(fs_info);
 fail_cleaner:
 	kthread_stop(fs_info->cleaner_kthread);
 
@@ -3501,8 +3519,10 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
 		btrfs_free_log(NULL, root);
 
-	__btrfs_remove_free_space_cache(root->free_ino_pinned);
-	__btrfs_remove_free_space_cache(root->free_ino_ctl);
+	if (root->free_ino_pinned)
+		__btrfs_remove_free_space_cache(root->free_ino_pinned);
+	if (root->free_ino_ctl)
+		__btrfs_remove_free_space_cache(root->free_ino_ctl);
 	free_fs_root(root);
 }
 
@@ -3533,28 +3553,51 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 {
 	u64 root_objectid = 0;
 	struct btrfs_root *gang[8];
-	int i;
-	int ret;
+	int i = 0;
+	int err = 0;
+	unsigned int ret = 0;
+	int index;
 
 	while (1) {
+		index = srcu_read_lock(&fs_info->subvol_srcu);
 		ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
 					     (void **)gang, root_objectid,
 					     ARRAY_SIZE(gang));
-		if (!ret)
+		if (!ret) {
+			srcu_read_unlock(&fs_info->subvol_srcu, index);
 			break;
-
+		}
 		root_objectid = gang[ret - 1]->root_key.objectid + 1;
+
 		for (i = 0; i < ret; i++) {
-			int err;
+			/* Avoid to grab roots in dead_roots */
+			if (btrfs_root_refs(&gang[i]->root_item) == 0) {
+				gang[i] = NULL;
+				continue;
+			}
+			/* grab all the search result for later use */
+			gang[i] = btrfs_grab_fs_root(gang[i]);
+		}
+		srcu_read_unlock(&fs_info->subvol_srcu, index);
 
+		for (i = 0; i < ret; i++) {
+			if (!gang[i])
+				continue;
 			root_objectid = gang[i]->root_key.objectid;
 			err = btrfs_orphan_cleanup(gang[i]);
 			if (err)
-				return err;
+				break;
+			btrfs_put_fs_root(gang[i]);
 		}
 		root_objectid++;
 	}
-	return 0;
+
+	/* release the uncleaned roots due to error */
+	for (; i < ret; i++) {
+		if (gang[i])
+			btrfs_put_fs_root(gang[i]);
+	}
+	return err;
 }
 
 int btrfs_commit_super(struct btrfs_root *root)
@@ -3603,6 +3646,8 @@ int close_ctree(struct btrfs_root *root)
 	/* clear out the rbtree of defraggable inodes */
 	btrfs_cleanup_defrag_inodes(fs_info);
 
+	cancel_work_sync(&fs_info->async_reclaim_work);
+
 	if (!(fs_info->sb->s_flags & MS_RDONLY)) {
 		ret = btrfs_commit_super(root);
 		if (ret)
@@ -3627,12 +3672,17 @@ int close_ctree(struct btrfs_root *root)
 
 	btrfs_sysfs_remove_one(fs_info);
 
-	del_fs_roots(fs_info);
+	btrfs_free_fs_roots(fs_info);
 
 	btrfs_put_block_group_cache(fs_info);
 
 	btrfs_free_block_groups(fs_info);
 
+	/*
+	 * we must make sure there is not any read request to
+	 * submit after we stopping all workers.
+	 */
+	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
 	free_root_pointers(fs_info, 1);
@@ -3709,6 +3759,12 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 		__percpu_counter_add(&root->fs_info->dirty_metadata_bytes,
 				     buf->len,
 				     root->fs_info->dirty_metadata_batch);
+#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+	if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) {
+		btrfs_print_leaf(root, buf);
+		ASSERT(0);
+	}
+#endif
 }
 
 static void __btrfs_btree_balance_dirty(struct btrfs_root *root,
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 53059df350f..23ce3ceba0a 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -68,6 +68,7 @@ struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
 int btrfs_init_fs_root(struct btrfs_root *root);
 int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
 			 struct btrfs_root *root);
+void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
 
 struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     struct btrfs_key *key,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 5590af92094..813537f362f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -26,16 +26,16 @@
 #include <linux/ratelimit.h>
 #include <linux/percpu_counter.h>
 #include "hash.h"
-#include "ctree.h"
+#include "tree-log.h"
 #include "disk-io.h"
 #include "print-tree.h"
-#include "transaction.h"
 #include "volumes.h"
 #include "raid56.h"
 #include "locking.h"
 #include "free-space-cache.h"
 #include "math.h"
 #include "sysfs.h"
+#include "qgroup.h"
 
 #undef SCRAMBLE_DELAYED_REFS
 
@@ -81,7 +81,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				u64 bytenr, u64 num_bytes, u64 parent,
 				u64 root_objectid, u64 owner_objectid,
 				u64 owner_offset, int refs_to_drop,
-				struct btrfs_delayed_extent_op *extra_op);
+				struct btrfs_delayed_extent_op *extra_op,
+				int no_quota);
 static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
 				    struct extent_buffer *leaf,
 				    struct btrfs_extent_item *ei);
@@ -94,7 +95,8 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
 				     u64 parent, u64 root_objectid,
 				     u64 flags, struct btrfs_disk_key *key,
-				     int level, struct btrfs_key *ins);
+				     int level, struct btrfs_key *ins,
+				     int no_quota);
 static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *extent_root, u64 flags,
 			  int force);
@@ -103,7 +105,8 @@ static int find_next_key(struct btrfs_path *path, int level,
 static void dump_space_info(struct btrfs_space_info *info, u64 bytes,
 			    int dump_block_groups);
 static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
-				       u64 num_bytes, int reserve);
+				       u64 num_bytes, int reserve,
+				       int delalloc);
 static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
 			       u64 num_bytes);
 int btrfs_pin_extent(struct btrfs_root *root,
@@ -1271,7 +1274,7 @@ fail:
 static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 					   struct btrfs_root *root,
 					   struct btrfs_path *path,
-					   int refs_to_drop)
+					   int refs_to_drop, int *last_ref)
 {
 	struct btrfs_key key;
 	struct btrfs_extent_data_ref *ref1 = NULL;
@@ -1307,6 +1310,7 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 
 	if (num_refs == 0) {
 		ret = btrfs_del_item(trans, root, path);
+		*last_ref = 1;
 	} else {
 		if (key.type == BTRFS_EXTENT_DATA_REF_KEY)
 			btrfs_set_extent_data_ref_count(leaf, ref1, num_refs);
@@ -1764,7 +1768,8 @@ void update_inline_extent_backref(struct btrfs_root *root,
 				  struct btrfs_path *path,
 				  struct btrfs_extent_inline_ref *iref,
 				  int refs_to_mod,
-				  struct btrfs_delayed_extent_op *extent_op)
+				  struct btrfs_delayed_extent_op *extent_op,
+				  int *last_ref)
 {
 	struct extent_buffer *leaf;
 	struct btrfs_extent_item *ei;
@@ -1808,6 +1813,7 @@ void update_inline_extent_backref(struct btrfs_root *root,
 		else
 			btrfs_set_shared_data_ref_count(leaf, sref, refs);
 	} else {
+		*last_ref = 1;
 		size =  btrfs_extent_inline_ref_size(type);
 		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
 		ptr = (unsigned long)iref;
@@ -1839,7 +1845,7 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 	if (ret == 0) {
 		BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
 		update_inline_extent_backref(root, path, iref,
-					     refs_to_add, extent_op);
+					     refs_to_add, extent_op, NULL);
 	} else if (ret == -ENOENT) {
 		setup_inline_extent_backref(root, path, iref, parent,
 					    root_objectid, owner, offset,
@@ -1872,17 +1878,19 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref *iref,
-				 int refs_to_drop, int is_data)
+				 int refs_to_drop, int is_data, int *last_ref)
 {
 	int ret = 0;
 
 	BUG_ON(!is_data && refs_to_drop != 1);
 	if (iref) {
 		update_inline_extent_backref(root, path, iref,
-					     -refs_to_drop, NULL);
+					     -refs_to_drop, NULL, last_ref);
 	} else if (is_data) {
-		ret = remove_extent_data_ref(trans, root, path, refs_to_drop);
+		ret = remove_extent_data_ref(trans, root, path, refs_to_drop,
+					     last_ref);
 	} else {
+		*last_ref = 1;
 		ret = btrfs_del_item(trans, root, path);
 	}
 	return ret;
@@ -1946,7 +1954,8 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 u64 bytenr, u64 num_bytes, u64 parent,
-			 u64 root_objectid, u64 owner, u64 offset, int for_cow)
+			 u64 root_objectid, u64 owner, u64 offset,
+			 int no_quota)
 {
 	int ret;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -1958,12 +1967,12 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
 					num_bytes,
 					parent, root_objectid, (int)owner,
-					BTRFS_ADD_DELAYED_REF, NULL, for_cow);
+					BTRFS_ADD_DELAYED_REF, NULL, no_quota);
 	} else {
 		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
 					num_bytes,
 					parent, root_objectid, owner, offset,
-					BTRFS_ADD_DELAYED_REF, NULL, for_cow);
+					BTRFS_ADD_DELAYED_REF, NULL, no_quota);
 	}
 	return ret;
 }
@@ -1973,31 +1982,64 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 				  u64 bytenr, u64 num_bytes,
 				  u64 parent, u64 root_objectid,
 				  u64 owner, u64 offset, int refs_to_add,
+				  int no_quota,
 				  struct btrfs_delayed_extent_op *extent_op)
 {
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_extent_item *item;
+	struct btrfs_key key;
 	u64 refs;
 	int ret;
+	enum btrfs_qgroup_operation_type type = BTRFS_QGROUP_OPER_ADD_EXCL;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
+	if (!is_fstree(root_objectid) || !root->fs_info->quota_enabled)
+		no_quota = 1;
+
 	path->reada = 1;
 	path->leave_spinning = 1;
 	/* this will setup the path even if it fails to insert the back ref */
-	ret = insert_inline_extent_backref(trans, root->fs_info->extent_root,
-					   path, bytenr, num_bytes, parent,
+	ret = insert_inline_extent_backref(trans, fs_info->extent_root, path,
+					   bytenr, num_bytes, parent,
 					   root_objectid, owner, offset,
 					   refs_to_add, extent_op);
-	if (ret != -EAGAIN)
+	if ((ret < 0 && ret != -EAGAIN) || (!ret && no_quota))
 		goto out;
+	/*
+	 * Ok we were able to insert an inline extent and it appears to be a new
+	 * reference, deal with the qgroup accounting.
+	 */
+	if (!ret && !no_quota) {
+		ASSERT(root->fs_info->quota_enabled);
+		leaf = path->nodes[0];
+		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+		item = btrfs_item_ptr(leaf, path->slots[0],
+				      struct btrfs_extent_item);
+		if (btrfs_extent_refs(leaf, item) > (u64)refs_to_add)
+			type = BTRFS_QGROUP_OPER_ADD_SHARED;
+		btrfs_release_path(path);
+
+		ret = btrfs_qgroup_record_ref(trans, fs_info, root_objectid,
+					      bytenr, num_bytes, type, 0);
+		goto out;
+	}
 
+	/*
+	 * Ok we had -EAGAIN which means we didn't have space to insert and
+	 * inline extent ref, so just update the reference count and add a
+	 * normal backref.
+	 */
 	leaf = path->nodes[0];
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	refs = btrfs_extent_refs(leaf, item);
+	if (refs)
+		type = BTRFS_QGROUP_OPER_ADD_SHARED;
 	btrfs_set_extent_refs(leaf, item, refs + refs_to_add);
 	if (extent_op)
 		__run_delayed_extent_op(extent_op, leaf, item);
@@ -2005,9 +2047,15 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 
+	if (!no_quota) {
+		ret = btrfs_qgroup_record_ref(trans, fs_info, root_objectid,
+					      bytenr, num_bytes, type, 0);
+		if (ret)
+			goto out;
+	}
+
 	path->reada = 1;
 	path->leave_spinning = 1;
-
 	/* now insert the actual backref */
 	ret = insert_extent_backref(trans, root->fs_info->extent_root,
 				    path, bytenr, parent, root_objectid,
@@ -2041,8 +2089,7 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 
 	if (node->type == BTRFS_SHARED_DATA_REF_KEY)
 		parent = ref->parent;
-	else
-		ref_root = ref->root;
+	ref_root = ref->root;
 
 	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
 		if (extent_op)
@@ -2056,13 +2103,13 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 					     node->num_bytes, parent,
 					     ref_root, ref->objectid,
 					     ref->offset, node->ref_mod,
-					     extent_op);
+					     node->no_quota, extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
 		ret = __btrfs_free_extent(trans, root, node->bytenr,
 					  node->num_bytes, parent,
 					  ref_root, ref->objectid,
 					  ref->offset, node->ref_mod,
-					  extent_op);
+					  extent_op, node->no_quota);
 	} else {
 		BUG();
 	}
@@ -2199,8 +2246,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 
 	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY)
 		parent = ref->parent;
-	else
-		ref_root = ref->root;
+	ref_root = ref->root;
 
 	ins.objectid = node->bytenr;
 	if (skinny_metadata) {
@@ -2218,15 +2264,18 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 						parent, ref_root,
 						extent_op->flags_to_set,
 						&extent_op->key,
-						ref->level, &ins);
+						ref->level, &ins,
+						node->no_quota);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
 		ret = __btrfs_inc_extent_ref(trans, root, node->bytenr,
 					     node->num_bytes, parent, ref_root,
-					     ref->level, 0, 1, extent_op);
+					     ref->level, 0, 1, node->no_quota,
+					     extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
 		ret = __btrfs_free_extent(trans, root, node->bytenr,
 					  node->num_bytes, parent, ref_root,
-					  ref->level, 0, 1, extent_op);
+					  ref->level, 0, 1, extent_op,
+					  node->no_quota);
 	} else {
 		BUG();
 	}
@@ -2574,42 +2623,6 @@ static u64 find_middle(struct rb_root *root)
 }
 #endif
 
-int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
-					 struct btrfs_fs_info *fs_info)
-{
-	struct qgroup_update *qgroup_update;
-	int ret = 0;
-
-	if (list_empty(&trans->qgroup_ref_list) !=
-	    !trans->delayed_ref_elem.seq) {
-		/* list without seq or seq without list */
-		btrfs_err(fs_info,
-			"qgroup accounting update error, list is%s empty, seq is %#x.%x",
-			list_empty(&trans->qgroup_ref_list) ? "" : " not",
-			(u32)(trans->delayed_ref_elem.seq >> 32),
-			(u32)trans->delayed_ref_elem.seq);
-		BUG();
-	}
-
-	if (!trans->delayed_ref_elem.seq)
-		return 0;
-
-	while (!list_empty(&trans->qgroup_ref_list)) {
-		qgroup_update = list_first_entry(&trans->qgroup_ref_list,
-						 struct qgroup_update, list);
-		list_del(&qgroup_update->list);
-		if (!ret)
-			ret = btrfs_qgroup_account_ref(
-					trans, fs_info, qgroup_update->node,
-					qgroup_update->extent_op);
-		kfree(qgroup_update);
-	}
-
-	btrfs_put_tree_mod_seq(fs_info, &trans->delayed_ref_elem);
-
-	return ret;
-}
-
 static inline u64 heads_to_leaves(struct btrfs_root *root, u64 heads)
 {
 	u64 num_bytes;
@@ -2662,15 +2675,94 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
 	u64 num_entries =
 		atomic_read(&trans->transaction->delayed_refs.num_entries);
 	u64 avg_runtime;
+	u64 val;
 
 	smp_mb();
 	avg_runtime = fs_info->avg_delayed_ref_runtime;
+	val = num_entries * avg_runtime;
 	if (num_entries * avg_runtime >= NSEC_PER_SEC)
 		return 1;
+	if (val >= NSEC_PER_SEC / 2)
+		return 2;
 
 	return btrfs_check_space_for_delayed_refs(trans, root);
 }
 
+struct async_delayed_refs {
+	struct btrfs_root *root;
+	int count;
+	int error;
+	int sync;
+	struct completion wait;
+	struct btrfs_work work;
+};
+
+static void delayed_ref_async_start(struct btrfs_work *work)
+{
+	struct async_delayed_refs *async;
+	struct btrfs_trans_handle *trans;
+	int ret;
+
+	async = container_of(work, struct async_delayed_refs, work);
+
+	trans = btrfs_join_transaction(async->root);
+	if (IS_ERR(trans)) {
+		async->error = PTR_ERR(trans);
+		goto done;
+	}
+
+	/*
+	 * trans->sync means that when we call end_transaciton, we won't
+	 * wait on delayed refs
+	 */
+	trans->sync = true;
+	ret = btrfs_run_delayed_refs(trans, async->root, async->count);
+	if (ret)
+		async->error = ret;
+
+	ret = btrfs_end_transaction(trans, async->root);
+	if (ret && !async->error)
+		async->error = ret;
+done:
+	if (async->sync)
+		complete(&async->wait);
+	else
+		kfree(async);
+}
+
+int btrfs_async_run_delayed_refs(struct btrfs_root *root,
+				 unsigned long count, int wait)
+{
+	struct async_delayed_refs *async;
+	int ret;
+
+	async = kmalloc(sizeof(*async), GFP_NOFS);
+	if (!async)
+		return -ENOMEM;
+
+	async->root = root->fs_info->tree_root;
+	async->count = count;
+	async->error = 0;
+	if (wait)
+		async->sync = 1;
+	else
+		async->sync = 0;
+	init_completion(&async->wait);
+
+	btrfs_init_work(&async->work, delayed_ref_async_start,
+			NULL, NULL);
+
+	btrfs_queue_work(root->fs_info->extent_workers, &async->work);
+
+	if (wait) {
+		wait_for_completion(&async->wait);
+		ret = async->error;
+		kfree(async);
+		return ret;
+	}
+	return 0;
+}
+
 /*
  * this starts processing the delayed reference count updates and
  * extent insertions we have queued up so far.  count can be
@@ -2698,8 +2790,6 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 	if (root == root->fs_info->extent_root)
 		root = root->fs_info->tree_root;
 
-	btrfs_delayed_refs_qgroup_accounting(trans, root->fs_info);
-
 	delayed_refs = &trans->transaction->delayed_refs;
 	if (count == 0) {
 		count = atomic_read(&delayed_refs->num_entries) * 2;
@@ -2758,6 +2848,9 @@ again:
 		goto again;
 	}
 out:
+	ret = btrfs_delayed_qgroup_accounting(trans, root->fs_info);
+	if (ret)
+		return ret;
 	assert_qgroups_uptodate(trans);
 	return 0;
 }
@@ -2964,7 +3057,7 @@ out:
 static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct extent_buffer *buf,
-			   int full_backref, int inc, int for_cow)
+			   int full_backref, int inc, int no_quota)
 {
 	u64 bytenr;
 	u64 num_bytes;
@@ -2979,11 +3072,15 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 	int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *,
 			    u64, u64, u64, u64, u64, u64, int);
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+		return 0;
+#endif
 	ref_root = btrfs_header_owner(buf);
 	nritems = btrfs_header_nritems(buf);
 	level = btrfs_header_level(buf);
 
-	if (!root->ref_cows && level == 0)
+	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state) && level == 0)
 		return 0;
 
 	if (inc)
@@ -3014,7 +3111,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			key.offset -= btrfs_file_extent_offset(buf, fi);
 			ret = process_func(trans, root, bytenr, num_bytes,
 					   parent, ref_root, key.objectid,
-					   key.offset, for_cow);
+					   key.offset, no_quota);
 			if (ret)
 				goto fail;
 		} else {
@@ -3022,7 +3119,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
 			num_bytes = btrfs_level_size(root, level - 1);
 			ret = process_func(trans, root, bytenr, num_bytes,
 					   parent, ref_root, level - 1, 0,
-					   for_cow);
+					   no_quota);
 			if (ret)
 				goto fail;
 		}
@@ -3033,15 +3130,15 @@ fail:
 }
 
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf, int full_backref, int for_cow)
+		  struct extent_buffer *buf, int full_backref, int no_quota)
 {
-	return __btrfs_mod_ref(trans, root, buf, full_backref, 1, for_cow);
+	return __btrfs_mod_ref(trans, root, buf, full_backref, 1, no_quota);
 }
 
 int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf, int full_backref, int for_cow)
+		  struct extent_buffer *buf, int full_backref, int no_quota)
 {
-	return __btrfs_mod_ref(trans, root, buf, full_backref, 0, for_cow);
+	return __btrfs_mod_ref(trans, root, buf, full_backref, 0, no_quota);
 }
 
 static int write_one_cache_group(struct btrfs_trans_handle *trans,
@@ -3164,7 +3261,8 @@ again:
 
 	spin_lock(&block_group->lock);
 	if (block_group->cached != BTRFS_CACHE_FINISHED ||
-	    !btrfs_test_opt(root, SPACE_CACHE)) {
+	    !btrfs_test_opt(root, SPACE_CACHE) ||
+	    block_group->delalloc_bytes) {
 		/*
 		 * don't bother trying to write stuff out _if_
 		 * a) we're not cached,
@@ -3401,10 +3499,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 		return ret;
 	}
 
-	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
 		INIT_LIST_HEAD(&found->block_groups[i]);
-		kobject_init(&found->block_group_kobjs[i], &btrfs_raid_ktype);
-	}
 	init_rwsem(&found->groups_sem);
 	spin_lock_init(&found->lock);
 	found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
@@ -4204,6 +4300,104 @@ static int flush_space(struct btrfs_root *root,
 
 	return ret;
 }
+
+static inline u64
+btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
+				 struct btrfs_space_info *space_info)
+{
+	u64 used;
+	u64 expected;
+	u64 to_reclaim;
+
+	to_reclaim = min_t(u64, num_online_cpus() * 1024 * 1024,
+				16 * 1024 * 1024);
+	spin_lock(&space_info->lock);
+	if (can_overcommit(root, space_info, to_reclaim,
+			   BTRFS_RESERVE_FLUSH_ALL)) {
+		to_reclaim = 0;
+		goto out;
+	}
+
+	used = space_info->bytes_used + space_info->bytes_reserved +
+	       space_info->bytes_pinned + space_info->bytes_readonly +
+	       space_info->bytes_may_use;
+	if (can_overcommit(root, space_info, 1024 * 1024,
+			   BTRFS_RESERVE_FLUSH_ALL))
+		expected = div_factor_fine(space_info->total_bytes, 95);
+	else
+		expected = div_factor_fine(space_info->total_bytes, 90);
+
+	if (used > expected)
+		to_reclaim = used - expected;
+	else
+		to_reclaim = 0;
+	to_reclaim = min(to_reclaim, space_info->bytes_may_use +
+				     space_info->bytes_reserved);
+out:
+	spin_unlock(&space_info->lock);
+
+	return to_reclaim;
+}
+
+static inline int need_do_async_reclaim(struct btrfs_space_info *space_info,
+					struct btrfs_fs_info *fs_info, u64 used)
+{
+	return (used >= div_factor_fine(space_info->total_bytes, 98) &&
+		!btrfs_fs_closing(fs_info) &&
+		!test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state));
+}
+
+static int btrfs_need_do_async_reclaim(struct btrfs_space_info *space_info,
+				       struct btrfs_fs_info *fs_info)
+{
+	u64 used;
+
+	spin_lock(&space_info->lock);
+	used = space_info->bytes_used + space_info->bytes_reserved +
+	       space_info->bytes_pinned + space_info->bytes_readonly +
+	       space_info->bytes_may_use;
+	if (need_do_async_reclaim(space_info, fs_info, used)) {
+		spin_unlock(&space_info->lock);
+		return 1;
+	}
+	spin_unlock(&space_info->lock);
+
+	return 0;
+}
+
+static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
+{
+	struct btrfs_fs_info *fs_info;
+	struct btrfs_space_info *space_info;
+	u64 to_reclaim;
+	int flush_state;
+
+	fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work);
+	space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
+
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
+						      space_info);
+	if (!to_reclaim)
+		return;
+
+	flush_state = FLUSH_DELAYED_ITEMS_NR;
+	do {
+		flush_space(fs_info->fs_root, space_info, to_reclaim,
+			    to_reclaim, flush_state);
+		flush_state++;
+		if (!btrfs_need_do_async_reclaim(space_info, fs_info))
+			return;
+	} while (flush_state <= COMMIT_TRANS);
+
+	if (btrfs_need_do_async_reclaim(space_info, fs_info))
+		queue_work(system_unbound_wq, work);
+}
+
+void btrfs_init_async_reclaim_work(struct work_struct *work)
+{
+	INIT_WORK(work, btrfs_async_reclaim_metadata_space);
+}
+
 /**
  * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
  * @root - the root we're allocating for
@@ -4311,8 +4505,13 @@ again:
 	if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
 		flushing = true;
 		space_info->flush = 1;
+	} else if (!ret && space_info->flags & BTRFS_BLOCK_GROUP_METADATA) {
+		used += orig_bytes;
+		if (need_do_async_reclaim(space_info, root->fs_info, used) &&
+		    !work_busy(&root->fs_info->async_reclaim_work))
+			queue_work(system_unbound_wq,
+				   &root->fs_info->async_reclaim_work);
 	}
-
 	spin_unlock(&space_info->lock);
 
 	if (!ret || flush == BTRFS_RESERVE_NO_FLUSH)
@@ -4369,7 +4568,7 @@ static struct btrfs_block_rsv *get_block_rsv(
 {
 	struct btrfs_block_rsv *block_rsv = NULL;
 
-	if (root->ref_cows)
+	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		block_rsv = trans->block_rsv;
 
 	if (root == root->fs_info->csum_root && trans->adding_csums)
@@ -5416,6 +5615,7 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log,
  * @cache:	The cache we are manipulating
  * @num_bytes:	The number of bytes in question
  * @reserve:	One of the reservation enums
+ * @delalloc:   The blocks are allocated for the delalloc write
  *
  * This is called by the allocator when it reserves space, or by somebody who is
  * freeing space that was never actually used on disk.  For example if you
@@ -5434,7 +5634,7 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log,
  * succeeds.
  */
 static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
-				       u64 num_bytes, int reserve)
+				       u64 num_bytes, int reserve, int delalloc)
 {
 	struct btrfs_space_info *space_info = cache->space_info;
 	int ret = 0;
@@ -5453,12 +5653,18 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
 						num_bytes, 0);
 				space_info->bytes_may_use -= num_bytes;
 			}
+
+			if (delalloc)
+				cache->delalloc_bytes += num_bytes;
 		}
 	} else {
 		if (cache->ro)
 			space_info->bytes_readonly += num_bytes;
 		cache->reserved -= num_bytes;
 		space_info->bytes_reserved -= num_bytes;
+
+		if (delalloc)
+			cache->delalloc_bytes -= num_bytes;
 	}
 	spin_unlock(&cache->lock);
 	spin_unlock(&space_info->lock);
@@ -5472,7 +5678,6 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 	struct btrfs_caching_control *next;
 	struct btrfs_caching_control *caching_ctl;
 	struct btrfs_block_group_cache *cache;
-	struct btrfs_space_info *space_info;
 
 	down_write(&fs_info->commit_root_sem);
 
@@ -5495,9 +5700,6 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 
 	up_write(&fs_info->commit_root_sem);
 
-	list_for_each_entry_rcu(space_info, &fs_info->space_info, list)
-		percpu_counter_set(&space_info->total_bytes_pinned, 0);
-
 	update_global_block_rsv(fs_info);
 }
 
@@ -5535,6 +5737,7 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 		spin_lock(&cache->lock);
 		cache->pinned -= len;
 		space_info->bytes_pinned -= len;
+		percpu_counter_add(&space_info->total_bytes_pinned, -len);
 		if (cache->ro) {
 			space_info->bytes_readonly += len;
 			readonly = true;
@@ -5621,7 +5824,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				u64 bytenr, u64 num_bytes, u64 parent,
 				u64 root_objectid, u64 owner_objectid,
 				u64 owner_offset, int refs_to_drop,
-				struct btrfs_delayed_extent_op *extent_op)
+				struct btrfs_delayed_extent_op *extent_op,
+				int no_quota)
 {
 	struct btrfs_key key;
 	struct btrfs_path *path;
@@ -5637,9 +5841,14 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	int num_to_del = 1;
 	u32 item_size;
 	u64 refs;
+	int last_ref = 0;
+	enum btrfs_qgroup_operation_type type = BTRFS_QGROUP_OPER_SUB_EXCL;
 	bool skinny_metadata = btrfs_fs_incompat(root->fs_info,
 						 SKINNY_METADATA);
 
+	if (!info->quota_enabled || !is_fstree(root_objectid))
+		no_quota = 1;
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -5687,7 +5896,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			BUG_ON(iref);
 			ret = remove_extent_backref(trans, extent_root, path,
 						    NULL, refs_to_drop,
-						    is_data);
+						    is_data, &last_ref);
 			if (ret) {
 				btrfs_abort_transaction(trans, extent_root, ret);
 				goto out;
@@ -5806,7 +6015,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	refs = btrfs_extent_refs(leaf, ei);
 	if (refs < refs_to_drop) {
 		btrfs_err(info, "trying to drop %d refs but we only have %Lu "
-			  "for bytenr %Lu\n", refs_to_drop, refs, bytenr);
+			  "for bytenr %Lu", refs_to_drop, refs, bytenr);
 		ret = -EINVAL;
 		btrfs_abort_transaction(trans, extent_root, ret);
 		goto out;
@@ -5814,6 +6023,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	refs -= refs_to_drop;
 
 	if (refs > 0) {
+		type = BTRFS_QGROUP_OPER_SUB_SHARED;
 		if (extent_op)
 			__run_delayed_extent_op(extent_op, leaf, ei);
 		/*
@@ -5829,7 +6039,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 		if (found_extent) {
 			ret = remove_extent_backref(trans, extent_root, path,
 						    iref, refs_to_drop,
-						    is_data);
+						    is_data, &last_ref);
 			if (ret) {
 				btrfs_abort_transaction(trans, extent_root, ret);
 				goto out;
@@ -5850,6 +6060,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			}
 		}
 
+		last_ref = 1;
 		ret = btrfs_del_items(trans, extent_root, path, path->slots[0],
 				      num_to_del);
 		if (ret) {
@@ -5872,6 +6083,20 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 	}
+	btrfs_release_path(path);
+
+	/* Deal with the quota accounting */
+	if (!ret && last_ref && !no_quota) {
+		int mod_seq = 0;
+
+		if (owner_objectid >= BTRFS_FIRST_FREE_OBJECTID &&
+		    type == BTRFS_QGROUP_OPER_SUB_SHARED)
+			mod_seq = 1;
+
+		ret = btrfs_qgroup_record_ref(trans, info, root_objectid,
+					      bytenr, num_bytes, type,
+					      mod_seq);
+	}
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -5987,7 +6212,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
 
 		btrfs_add_free_space(cache, buf->start, buf->len);
-		btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE);
+		btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);
 		trace_btrfs_reserved_extent_free(root, buf->start, buf->len);
 		pin = 0;
 	}
@@ -6008,11 +6233,15 @@ out:
 /* Can return -ENOMEM */
 int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
-		      u64 owner, u64 offset, int for_cow)
+		      u64 owner, u64 offset, int no_quota)
 {
 	int ret;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+		return 0;
+#endif
 	add_pinned_bytes(root->fs_info, num_bytes, owner, root_objectid);
 
 	/*
@@ -6028,13 +6257,13 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
 					num_bytes,
 					parent, root_objectid, (int)owner,
-					BTRFS_DROP_DELAYED_REF, NULL, for_cow);
+					BTRFS_DROP_DELAYED_REF, NULL, no_quota);
 	} else {
 		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
 						num_bytes,
 						parent, root_objectid, owner,
 						offset, BTRFS_DROP_DELAYED_REF,
-						NULL, for_cow);
+						NULL, no_quota);
 	}
 	return ret;
 }
@@ -6142,6 +6371,70 @@ enum btrfs_loop_type {
 	LOOP_NO_EMPTY_SIZE = 3,
 };
 
+static inline void
+btrfs_lock_block_group(struct btrfs_block_group_cache *cache,
+		       int delalloc)
+{
+	if (delalloc)
+		down_read(&cache->data_rwsem);
+}
+
+static inline void
+btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
+		       int delalloc)
+{
+	btrfs_get_block_group(cache);
+	if (delalloc)
+		down_read(&cache->data_rwsem);
+}
+
+static struct btrfs_block_group_cache *
+btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
+		   struct btrfs_free_cluster *cluster,
+		   int delalloc)
+{
+	struct btrfs_block_group_cache *used_bg;
+	bool locked = false;
+again:
+	spin_lock(&cluster->refill_lock);
+	if (locked) {
+		if (used_bg == cluster->block_group)
+			return used_bg;
+
+		up_read(&used_bg->data_rwsem);
+		btrfs_put_block_group(used_bg);
+	}
+
+	used_bg = cluster->block_group;
+	if (!used_bg)
+		return NULL;
+
+	if (used_bg == block_group)
+		return used_bg;
+
+	btrfs_get_block_group(used_bg);
+
+	if (!delalloc)
+		return used_bg;
+
+	if (down_read_trylock(&used_bg->data_rwsem))
+		return used_bg;
+
+	spin_unlock(&cluster->refill_lock);
+	down_read(&used_bg->data_rwsem);
+	locked = true;
+	goto again;
+}
+
+static inline void
+btrfs_release_block_group(struct btrfs_block_group_cache *cache,
+			 int delalloc)
+{
+	if (delalloc)
+		up_read(&cache->data_rwsem);
+	btrfs_put_block_group(cache);
+}
+
 /*
  * walks the btree of allocated extents and find a hole of a given size.
  * The key ins is changed to record the hole:
@@ -6156,7 +6449,7 @@ enum btrfs_loop_type {
 static noinline int find_free_extent(struct btrfs_root *orig_root,
 				     u64 num_bytes, u64 empty_size,
 				     u64 hint_byte, struct btrfs_key *ins,
-				     u64 flags)
+				     u64 flags, int delalloc)
 {
 	int ret = 0;
 	struct btrfs_root *root = orig_root->fs_info->extent_root;
@@ -6244,6 +6537,7 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
 				up_read(&space_info->groups_sem);
 			} else {
 				index = get_block_group_index(block_group);
+				btrfs_lock_block_group(block_group, delalloc);
 				goto have_block_group;
 			}
 		} else if (block_group) {
@@ -6258,7 +6552,7 @@ search:
 		u64 offset;
 		int cached;
 
-		btrfs_get_block_group(block_group);
+		btrfs_grab_block_group(block_group, delalloc);
 		search_start = block_group->key.objectid;
 
 		/*
@@ -6306,16 +6600,16 @@ have_block_group:
 			 * the refill lock keeps out other
 			 * people trying to start a new cluster
 			 */
-			spin_lock(&last_ptr->refill_lock);
-			used_block_group = last_ptr->block_group;
-			if (used_block_group != block_group &&
-			    (!used_block_group ||
-			     used_block_group->ro ||
-			     !block_group_bits(used_block_group, flags)))
+			used_block_group = btrfs_lock_cluster(block_group,
+							      last_ptr,
+							      delalloc);
+			if (!used_block_group)
 				goto refill_cluster;
 
-			if (used_block_group != block_group)
-				btrfs_get_block_group(used_block_group);
+			if (used_block_group != block_group &&
+			    (used_block_group->ro ||
+			     !block_group_bits(used_block_group, flags)))
+				goto release_cluster;
 
 			offset = btrfs_alloc_from_cluster(used_block_group,
 						last_ptr,
@@ -6329,16 +6623,15 @@ have_block_group:
 						used_block_group,
 						search_start, num_bytes);
 				if (used_block_group != block_group) {
-					btrfs_put_block_group(block_group);
+					btrfs_release_block_group(block_group,
+								  delalloc);
 					block_group = used_block_group;
 				}
 				goto checks;
 			}
 
 			WARN_ON(last_ptr->block_group != used_block_group);
-			if (used_block_group != block_group)
-				btrfs_put_block_group(used_block_group);
-refill_cluster:
+release_cluster:
 			/* If we are on LOOP_NO_EMPTY_SIZE, we can't
 			 * set up a new clusters, so lets just skip it
 			 * and let the allocator find whatever block
@@ -6355,8 +6648,10 @@ refill_cluster:
 			 * succeeding in the unclustered
 			 * allocation.  */
 			if (loop >= LOOP_NO_EMPTY_SIZE &&
-			    last_ptr->block_group != block_group) {
+			    used_block_group != block_group) {
 				spin_unlock(&last_ptr->refill_lock);
+				btrfs_release_block_group(used_block_group,
+							  delalloc);
 				goto unclustered_alloc;
 			}
 
@@ -6366,6 +6661,10 @@ refill_cluster:
 			 */
 			btrfs_return_cluster_to_free_space(NULL, last_ptr);
 
+			if (used_block_group != block_group)
+				btrfs_release_block_group(used_block_group,
+							  delalloc);
+refill_cluster:
 			if (loop >= LOOP_NO_EMPTY_SIZE) {
 				spin_unlock(&last_ptr->refill_lock);
 				goto unclustered_alloc;
@@ -6473,7 +6772,7 @@ checks:
 		BUG_ON(offset > search_start);
 
 		ret = btrfs_update_reserved_bytes(block_group, num_bytes,
-						  alloc_type);
+						  alloc_type, delalloc);
 		if (ret == -EAGAIN) {
 			btrfs_add_free_space(block_group, offset, num_bytes);
 			goto loop;
@@ -6485,13 +6784,13 @@ checks:
 
 		trace_btrfs_reserve_extent(orig_root, block_group,
 					   search_start, num_bytes);
-		btrfs_put_block_group(block_group);
+		btrfs_release_block_group(block_group, delalloc);
 		break;
 loop:
 		failed_cluster_refill = false;
 		failed_alloc = false;
 		BUG_ON(index != get_block_group_index(block_group));
-		btrfs_put_block_group(block_group);
+		btrfs_release_block_group(block_group, delalloc);
 	}
 	up_read(&space_info->groups_sem);
 
@@ -6514,8 +6813,14 @@ loop:
 		loop++;
 		if (loop == LOOP_ALLOC_CHUNK) {
 			struct btrfs_trans_handle *trans;
+			int exist = 0;
+
+			trans = current->journal_info;
+			if (trans)
+				exist = 1;
+			else
+				trans = btrfs_join_transaction(root);
 
-			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans)) {
 				ret = PTR_ERR(trans);
 				goto out;
@@ -6532,7 +6837,8 @@ loop:
 							root, ret);
 			else
 				ret = 0;
-			btrfs_end_transaction(trans, root);
+			if (!exist)
+				btrfs_end_transaction(trans, root);
 			if (ret)
 				goto out;
 		}
@@ -6597,7 +6903,7 @@ again:
 int btrfs_reserve_extent(struct btrfs_root *root,
 			 u64 num_bytes, u64 min_alloc_size,
 			 u64 empty_size, u64 hint_byte,
-			 struct btrfs_key *ins, int is_data)
+			 struct btrfs_key *ins, int is_data, int delalloc)
 {
 	bool final_tried = false;
 	u64 flags;
@@ -6607,7 +6913,7 @@ int btrfs_reserve_extent(struct btrfs_root *root,
 again:
 	WARN_ON(num_bytes < root->sectorsize);
 	ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
-			       flags);
+			       flags, delalloc);
 
 	if (ret == -ENOSPC) {
 		if (!final_tried && ins->offset) {
@@ -6632,7 +6938,8 @@ again:
 }
 
 static int __btrfs_free_reserved_extent(struct btrfs_root *root,
-					u64 start, u64 len, int pin)
+					u64 start, u64 len,
+					int pin, int delalloc)
 {
 	struct btrfs_block_group_cache *cache;
 	int ret = 0;
@@ -6651,7 +6958,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root,
 		pin_down_extent(root, cache, start, len, 1);
 	else {
 		btrfs_add_free_space(cache, start, len);
-		btrfs_update_reserved_bytes(cache, len, RESERVE_FREE);
+		btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc);
 	}
 	btrfs_put_block_group(cache);
 
@@ -6661,15 +6968,15 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root,
 }
 
 int btrfs_free_reserved_extent(struct btrfs_root *root,
-					u64 start, u64 len)
+			       u64 start, u64 len, int delalloc)
 {
-	return __btrfs_free_reserved_extent(root, start, len, 0);
+	return __btrfs_free_reserved_extent(root, start, len, 0, delalloc);
 }
 
 int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root,
 				       u64 start, u64 len)
 {
-	return __btrfs_free_reserved_extent(root, start, len, 1);
+	return __btrfs_free_reserved_extent(root, start, len, 1, 0);
 }
 
 static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
@@ -6733,6 +7040,13 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(path->nodes[0]);
 	btrfs_free_path(path);
 
+	/* Always set parent to 0 here since its exclusive anyway. */
+	ret = btrfs_qgroup_record_ref(trans, fs_info, root_objectid,
+				      ins->objectid, ins->offset,
+				      BTRFS_QGROUP_OPER_ADD_EXCL, 0);
+	if (ret)
+		return ret;
+
 	ret = update_block_group(root, ins->objectid, ins->offset, 1);
 	if (ret) { /* -ENOENT, logic error */
 		btrfs_err(fs_info, "update block group failed for %llu %llu",
@@ -6747,7 +7061,8 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
 				     u64 parent, u64 root_objectid,
 				     u64 flags, struct btrfs_disk_key *key,
-				     int level, struct btrfs_key *ins)
+				     int level, struct btrfs_key *ins,
+				     int no_quota)
 {
 	int ret;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -6757,6 +7072,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	u32 size = sizeof(*extent_item) + sizeof(*iref);
+	u64 num_bytes = ins->offset;
 	bool skinny_metadata = btrfs_fs_incompat(root->fs_info,
 						 SKINNY_METADATA);
 
@@ -6790,6 +7106,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 
 	if (skinny_metadata) {
 		iref = (struct btrfs_extent_inline_ref *)(extent_item + 1);
+		num_bytes = root->leafsize;
 	} else {
 		block_info = (struct btrfs_tree_block_info *)(extent_item + 1);
 		btrfs_set_tree_block_key(leaf, block_info, key);
@@ -6811,6 +7128,14 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_free_path(path);
 
+	if (!no_quota) {
+		ret = btrfs_qgroup_record_ref(trans, fs_info, root_objectid,
+					      ins->objectid, num_bytes,
+					      BTRFS_QGROUP_OPER_ADD_EXCL, 0);
+		if (ret)
+			return ret;
+	}
+
 	ret = update_block_group(root, ins->objectid, root->leafsize, 1);
 	if (ret) { /* -ENOENT, logic error */
 		btrfs_err(fs_info, "update block group failed for %llu %llu",
@@ -6866,7 +7191,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 		return -EINVAL;
 
 	ret = btrfs_update_reserved_bytes(block_group, ins->offset,
-					  RESERVE_ALLOC_NO_ACCOUNT);
+					  RESERVE_ALLOC_NO_ACCOUNT, 0);
 	BUG_ON(ret); /* logic error */
 	ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
 					 0, owner, offset, ins, 1);
@@ -6994,12 +7319,21 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 	bool skinny_metadata = btrfs_fs_incompat(root->fs_info,
 						 SKINNY_METADATA);
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state))) {
+		buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
+					    blocksize, level);
+		if (!IS_ERR(buf))
+			root->alloc_bytenr += blocksize;
+		return buf;
+	}
+#endif
 	block_rsv = use_block_rsv(trans, root, blocksize);
 	if (IS_ERR(block_rsv))
 		return ERR_CAST(block_rsv);
 
 	ret = btrfs_reserve_extent(root, blocksize, blocksize,
-				   empty_size, hint, &ins, 0);
+				   empty_size, hint, &ins, 0, 0);
 	if (ret) {
 		unuse_block_rsv(root->fs_info, block_rsv, blocksize);
 		return ERR_PTR(ret);
@@ -7735,7 +8069,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		}
 	}
 
-	if (root->in_radix) {
+	if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) {
 		btrfs_drop_and_free_fs_root(tree_root->fs_info, root);
 	} else {
 		free_extent_buffer(root->node);
@@ -8327,8 +8661,9 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		list_del(&space_info->list);
 		for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
 			struct kobject *kobj;
-			kobj = &space_info->block_group_kobjs[i];
-			if (kobj->parent) {
+			kobj = space_info->block_group_kobjs[i];
+			space_info->block_group_kobjs[i] = NULL;
+			if (kobj) {
 				kobject_del(kobj);
 				kobject_put(kobj);
 			}
@@ -8352,17 +8687,26 @@ static void __link_block_group(struct btrfs_space_info *space_info,
 	up_write(&space_info->groups_sem);
 
 	if (first) {
-		struct kobject *kobj = &space_info->block_group_kobjs[index];
+		struct raid_kobject *rkobj;
 		int ret;
 
-		kobject_get(&space_info->kobj); /* put in release */
-		ret = kobject_add(kobj, &space_info->kobj, "%s",
-				  get_raid_name(index));
+		rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS);
+		if (!rkobj)
+			goto out_err;
+		rkobj->raid_type = index;
+		kobject_init(&rkobj->kobj, &btrfs_raid_ktype);
+		ret = kobject_add(&rkobj->kobj, &space_info->kobj,
+				  "%s", get_raid_name(index));
 		if (ret) {
-			pr_warn("BTRFS: failed to add kobject for block cache. ignoring.\n");
-			kobject_put(&space_info->kobj);
+			kobject_put(&rkobj->kobj);
+			goto out_err;
 		}
+		space_info->block_group_kobjs[index] = &rkobj->kobj;
 	}
+
+	return;
+out_err:
+	pr_warn("BTRFS: failed to add kobject for block cache. ignoring.\n");
 }
 
 static struct btrfs_block_group_cache *
@@ -8392,6 +8736,7 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
 					       start);
 	atomic_set(&cache->count, 1);
 	spin_lock_init(&cache->lock);
+	init_rwsem(&cache->data_rwsem);
 	INIT_LIST_HEAD(&cache->list);
 	INIT_LIST_HEAD(&cache->cluster_list);
 	INIT_LIST_HEAD(&cache->new_bg_list);
@@ -8611,7 +8956,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 
 	extent_root = root->fs_info->extent_root;
 
-	root->fs_info->last_trans_log_full_commit = trans->transid;
+	btrfs_set_log_full_commit(root->fs_info, trans);
 
 	cache = btrfs_create_block_group_cache(root, chunk_offset, size);
 	if (!cache)
@@ -8697,6 +9042,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_root *tree_root = root->fs_info->tree_root;
 	struct btrfs_key key;
 	struct inode *inode;
+	struct kobject *kobj = NULL;
 	int ret;
 	int index;
 	int factor;
@@ -8796,11 +9142,15 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 */
 	list_del_init(&block_group->list);
 	if (list_empty(&block_group->space_info->block_groups[index])) {
-		kobject_del(&block_group->space_info->block_group_kobjs[index]);
-		kobject_put(&block_group->space_info->block_group_kobjs[index]);
+		kobj = block_group->space_info->block_group_kobjs[index];
+		block_group->space_info->block_group_kobjs[index] = NULL;
 		clear_avail_alloc_bits(root->fs_info, block_group->flags);
 	}
 	up_write(&block_group->space_info->groups_sem);
+	if (kobj) {
+		kobject_del(kobj);
+		kobject_put(kobj);
+	}
 
 	if (block_group->cached == BTRFS_CACHE_STARTED)
 		wait_block_group_cache_done(block_group);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4cd0ac983f9..3e11aab9f39 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1693,6 +1693,7 @@ again:
 		 * shortening the size of the delalloc range we're searching
 		 */
 		free_extent_state(cached_state);
+		cached_state = NULL;
 		if (!loops) {
 			max_bytes = PAGE_CACHE_SIZE;
 			loops = 1;
@@ -2353,7 +2354,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 {
 	int uptodate = (err == 0);
 	struct extent_io_tree *tree;
-	int ret;
+	int ret = 0;
 
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
 
@@ -2367,6 +2368,8 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 	if (!uptodate) {
 		ClearPageUptodate(page);
 		SetPageError(page);
+		ret = ret < 0 ? ret : -EIO;
+		mapping_set_error(page->mapping, ret);
 	}
 	return 0;
 }
@@ -3098,143 +3101,130 @@ static noinline void update_nr_written(struct page *page,
 }
 
 /*
- * the writepage semantics are similar to regular writepage.  extent
- * records are inserted to lock ranges in the tree, and as dirty areas
- * are found, they are marked writeback.  Then the lock bits are removed
- * and the end_io handler clears the writeback ranges
+ * helper for __extent_writepage, doing all of the delayed allocation setup.
+ *
+ * This returns 1 if our fill_delalloc function did all the work required
+ * to write the page (copy into inline extent).  In this case the IO has
+ * been started and the page is already unlocked.
+ *
+ * This returns 0 if all went well (page still locked)
+ * This returns < 0 if there were errors (page still locked)
  */
-static int __extent_writepage(struct page *page, struct writeback_control *wbc,
-			      void *data)
+static noinline_for_stack int writepage_delalloc(struct inode *inode,
+			      struct page *page, struct writeback_control *wbc,
+			      struct extent_page_data *epd,
+			      u64 delalloc_start,
+			      unsigned long *nr_written)
+{
+	struct extent_io_tree *tree = epd->tree;
+	u64 page_end = delalloc_start + PAGE_CACHE_SIZE - 1;
+	u64 nr_delalloc;
+	u64 delalloc_to_write = 0;
+	u64 delalloc_end = 0;
+	int ret;
+	int page_started = 0;
+
+	if (epd->extent_locked || !tree->ops || !tree->ops->fill_delalloc)
+		return 0;
+
+	while (delalloc_end < page_end) {
+		nr_delalloc = find_lock_delalloc_range(inode, tree,
+					       page,
+					       &delalloc_start,
+					       &delalloc_end,
+					       128 * 1024 * 1024);
+		if (nr_delalloc == 0) {
+			delalloc_start = delalloc_end + 1;
+			continue;
+		}
+		ret = tree->ops->fill_delalloc(inode, page,
+					       delalloc_start,
+					       delalloc_end,
+					       &page_started,
+					       nr_written);
+		/* File system has been set read-only */
+		if (ret) {
+			SetPageError(page);
+			/* fill_delalloc should be return < 0 for error
+			 * but just in case, we use > 0 here meaning the
+			 * IO is started, so we don't want to return > 0
+			 * unless things are going well.
+			 */
+			ret = ret < 0 ? ret : -EIO;
+			goto done;
+		}
+		/*
+		 * delalloc_end is already one less than the total
+		 * length, so we don't subtract one from
+		 * PAGE_CACHE_SIZE
+		 */
+		delalloc_to_write += (delalloc_end - delalloc_start +
+				      PAGE_CACHE_SIZE) >>
+				      PAGE_CACHE_SHIFT;
+		delalloc_start = delalloc_end + 1;
+	}
+	if (wbc->nr_to_write < delalloc_to_write) {
+		int thresh = 8192;
+
+		if (delalloc_to_write < thresh * 2)
+			thresh = delalloc_to_write;
+		wbc->nr_to_write = min_t(u64, delalloc_to_write,
+					 thresh);
+	}
+
+	/* did the fill delalloc function already unlock and start
+	 * the IO?
+	 */
+	if (page_started) {
+		/*
+		 * we've unlocked the page, so we can't update
+		 * the mapping's writeback index, just update
+		 * nr_to_write.
+		 */
+		wbc->nr_to_write -= *nr_written;
+		return 1;
+	}
+
+	ret = 0;
+
+done:
+	return ret;
+}
+
+/*
+ * helper for __extent_writepage.  This calls the writepage start hooks,
+ * and does the loop to map the page into extents and bios.
+ *
+ * We return 1 if the IO is started and the page is unlocked,
+ * 0 if all went well (page still locked)
+ * < 0 if there were errors (page still locked)
+ */
+static noinline_for_stack int __extent_writepage_io(struct inode *inode,
+				 struct page *page,
+				 struct writeback_control *wbc,
+				 struct extent_page_data *epd,
+				 loff_t i_size,
+				 unsigned long nr_written,
+				 int write_flags, int *nr_ret)
 {
-	struct inode *inode = page->mapping->host;
-	struct extent_page_data *epd = data;
 	struct extent_io_tree *tree = epd->tree;
 	u64 start = page_offset(page);
-	u64 delalloc_start;
 	u64 page_end = start + PAGE_CACHE_SIZE - 1;
 	u64 end;
 	u64 cur = start;
 	u64 extent_offset;
-	u64 last_byte = i_size_read(inode);
 	u64 block_start;
 	u64 iosize;
 	sector_t sector;
 	struct extent_state *cached_state = NULL;
 	struct extent_map *em;
 	struct block_device *bdev;
-	int ret;
-	int nr = 0;
 	size_t pg_offset = 0;
 	size_t blocksize;
-	loff_t i_size = i_size_read(inode);
-	unsigned long end_index = i_size >> PAGE_CACHE_SHIFT;
-	u64 nr_delalloc;
-	u64 delalloc_end;
-	int page_started;
-	int compressed;
-	int write_flags;
-	unsigned long nr_written = 0;
-	bool fill_delalloc = true;
-
-	if (wbc->sync_mode == WB_SYNC_ALL)
-		write_flags = WRITE_SYNC;
-	else
-		write_flags = WRITE;
-
-	trace___extent_writepage(page, inode, wbc);
-
-	WARN_ON(!PageLocked(page));
-
-	ClearPageError(page);
-
-	pg_offset = i_size & (PAGE_CACHE_SIZE - 1);
-	if (page->index > end_index ||
-	   (page->index == end_index && !pg_offset)) {
-		page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
-		unlock_page(page);
-		return 0;
-	}
-
-	if (page->index == end_index) {
-		char *userpage;
-
-		userpage = kmap_atomic(page);
-		memset(userpage + pg_offset, 0,
-		       PAGE_CACHE_SIZE - pg_offset);
-		kunmap_atomic(userpage);
-		flush_dcache_page(page);
-	}
-	pg_offset = 0;
-
-	set_page_extent_mapped(page);
-
-	if (!tree->ops || !tree->ops->fill_delalloc)
-		fill_delalloc = false;
-
-	delalloc_start = start;
-	delalloc_end = 0;
-	page_started = 0;
-	if (!epd->extent_locked && fill_delalloc) {
-		u64 delalloc_to_write = 0;
-		/*
-		 * make sure the wbc mapping index is at least updated
-		 * to this page.
-		 */
-		update_nr_written(page, wbc, 0);
-
-		while (delalloc_end < page_end) {
-			nr_delalloc = find_lock_delalloc_range(inode, tree,
-						       page,
-						       &delalloc_start,
-						       &delalloc_end,
-						       128 * 1024 * 1024);
-			if (nr_delalloc == 0) {
-				delalloc_start = delalloc_end + 1;
-				continue;
-			}
-			ret = tree->ops->fill_delalloc(inode, page,
-						       delalloc_start,
-						       delalloc_end,
-						       &page_started,
-						       &nr_written);
-			/* File system has been set read-only */
-			if (ret) {
-				SetPageError(page);
-				goto done;
-			}
-			/*
-			 * delalloc_end is already one less than the total
-			 * length, so we don't subtract one from
-			 * PAGE_CACHE_SIZE
-			 */
-			delalloc_to_write += (delalloc_end - delalloc_start +
-					      PAGE_CACHE_SIZE) >>
-					      PAGE_CACHE_SHIFT;
-			delalloc_start = delalloc_end + 1;
-		}
-		if (wbc->nr_to_write < delalloc_to_write) {
-			int thresh = 8192;
-
-			if (delalloc_to_write < thresh * 2)
-				thresh = delalloc_to_write;
-			wbc->nr_to_write = min_t(u64, delalloc_to_write,
-						 thresh);
-		}
+	int ret = 0;
+	int nr = 0;
+	bool compressed;
 
-		/* did the fill delalloc function already unlock and start
-		 * the IO?
-		 */
-		if (page_started) {
-			ret = 0;
-			/*
-			 * we've unlocked the page, so we can't update
-			 * the mapping's writeback index, just update
-			 * nr_to_write.
-			 */
-			wbc->nr_to_write -= nr_written;
-			goto done_unlocked;
-		}
-	}
 	if (tree->ops && tree->ops->writepage_start_hook) {
 		ret = tree->ops->writepage_start_hook(page, start,
 						      page_end);
@@ -3244,9 +3234,10 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 				wbc->pages_skipped++;
 			else
 				redirty_page_for_writepage(wbc, page);
+
 			update_nr_written(page, wbc, nr_written);
 			unlock_page(page);
-			ret = 0;
+			ret = 1;
 			goto done_unlocked;
 		}
 	}
@@ -3258,7 +3249,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	update_nr_written(page, wbc, nr_written + 1);
 
 	end = page_end;
-	if (last_byte <= start) {
+	if (i_size <= start) {
 		if (tree->ops && tree->ops->writepage_end_io_hook)
 			tree->ops->writepage_end_io_hook(page, start,
 							 page_end, NULL, 1);
@@ -3268,7 +3259,8 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	blocksize = inode->i_sb->s_blocksize;
 
 	while (cur <= end) {
-		if (cur >= last_byte) {
+		u64 em_end;
+		if (cur >= i_size) {
 			if (tree->ops && tree->ops->writepage_end_io_hook)
 				tree->ops->writepage_end_io_hook(page, cur,
 							 page_end, NULL, 1);
@@ -3278,13 +3270,15 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 				     end - cur + 1, 1);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
+			ret = PTR_ERR_OR_ZERO(em);
 			break;
 		}
 
 		extent_offset = cur - em->start;
-		BUG_ON(extent_map_end(em) <= cur);
+		em_end = extent_map_end(em);
+		BUG_ON(em_end <= cur);
 		BUG_ON(end < cur);
-		iosize = min(extent_map_end(em) - cur, end - cur + 1);
+		iosize = min(em_end - cur, end - cur + 1);
 		iosize = ALIGN(iosize, blocksize);
 		sector = (em->block_start + extent_offset) >> 9;
 		bdev = em->bdev;
@@ -3320,13 +3314,6 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 			pg_offset += iosize;
 			continue;
 		}
-		/* leave this out until we have a page_mkwrite call */
-		if (0 && !test_range_bit(tree, cur, cur + iosize - 1,
-				   EXTENT_DIRTY, 0, NULL)) {
-			cur = cur + iosize;
-			pg_offset += iosize;
-			continue;
-		}
 
 		if (tree->ops && tree->ops->writepage_io_hook) {
 			ret = tree->ops->writepage_io_hook(page, cur,
@@ -3337,7 +3324,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 		if (ret) {
 			SetPageError(page);
 		} else {
-			unsigned long max_nr = end_index + 1;
+			unsigned long max_nr = (i_size >> PAGE_CACHE_SHIFT) + 1;
 
 			set_range_writeback(tree, cur, cur + iosize - 1);
 			if (!PageWriteback(page)) {
@@ -3359,35 +3346,107 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 		nr++;
 	}
 done:
-	if (nr == 0) {
-		/* make sure the mapping tag for page dirty gets cleared */
-		set_page_writeback(page);
-		end_page_writeback(page);
-	}
-	unlock_page(page);
+	*nr_ret = nr;
 
 done_unlocked:
 
 	/* drop our reference on any cached states */
 	free_extent_state(cached_state);
-	return 0;
+	return ret;
 }
 
-static int eb_wait(void *word)
+/*
+ * the writepage semantics are similar to regular writepage.  extent
+ * records are inserted to lock ranges in the tree, and as dirty areas
+ * are found, they are marked writeback.  Then the lock bits are removed
+ * and the end_io handler clears the writeback ranges
+ */
+static int __extent_writepage(struct page *page, struct writeback_control *wbc,
+			      void *data)
 {
-	io_schedule();
+	struct inode *inode = page->mapping->host;
+	struct extent_page_data *epd = data;
+	u64 start = page_offset(page);
+	u64 page_end = start + PAGE_CACHE_SIZE - 1;
+	int ret;
+	int nr = 0;
+	size_t pg_offset = 0;
+	loff_t i_size = i_size_read(inode);
+	unsigned long end_index = i_size >> PAGE_CACHE_SHIFT;
+	int write_flags;
+	unsigned long nr_written = 0;
+
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		write_flags = WRITE_SYNC;
+	else
+		write_flags = WRITE;
+
+	trace___extent_writepage(page, inode, wbc);
+
+	WARN_ON(!PageLocked(page));
+
+	ClearPageError(page);
+
+	pg_offset = i_size & (PAGE_CACHE_SIZE - 1);
+	if (page->index > end_index ||
+	   (page->index == end_index && !pg_offset)) {
+		page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
+		unlock_page(page);
+		return 0;
+	}
+
+	if (page->index == end_index) {
+		char *userpage;
+
+		userpage = kmap_atomic(page);
+		memset(userpage + pg_offset, 0,
+		       PAGE_CACHE_SIZE - pg_offset);
+		kunmap_atomic(userpage);
+		flush_dcache_page(page);
+	}
+
+	pg_offset = 0;
+
+	set_page_extent_mapped(page);
+
+	ret = writepage_delalloc(inode, page, wbc, epd, start, &nr_written);
+	if (ret == 1)
+		goto done_unlocked;
+	if (ret)
+		goto done;
+
+	ret = __extent_writepage_io(inode, page, wbc, epd,
+				    i_size, nr_written, write_flags, &nr);
+	if (ret == 1)
+		goto done_unlocked;
+
+done:
+	if (nr == 0) {
+		/* make sure the mapping tag for page dirty gets cleared */
+		set_page_writeback(page);
+		end_page_writeback(page);
+	}
+	if (PageError(page)) {
+		ret = ret < 0 ? ret : -EIO;
+		end_extent_writepage(page, ret, start, page_end);
+	}
+	unlock_page(page);
+	return ret;
+
+done_unlocked:
 	return 0;
 }
 
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
 {
-	wait_on_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK, eb_wait,
-		    TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK,
+		       TASK_UNINTERRUPTIBLE);
 }
 
-static int lock_extent_buffer_for_io(struct extent_buffer *eb,
-				     struct btrfs_fs_info *fs_info,
-				     struct extent_page_data *epd)
+static noinline_for_stack int
+lock_extent_buffer_for_io(struct extent_buffer *eb,
+			  struct btrfs_fs_info *fs_info,
+			  struct extent_page_data *epd)
 {
 	unsigned long i, num_pages;
 	int flush = 0;
@@ -3492,7 +3551,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
 	bio_put(bio);
 }
 
-static int write_one_eb(struct extent_buffer *eb,
+static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 			struct btrfs_fs_info *fs_info,
 			struct writeback_control *wbc,
 			struct extent_page_data *epd)
@@ -3690,6 +3749,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 	struct inode *inode = mapping->host;
 	int ret = 0;
 	int done = 0;
+	int err = 0;
 	int nr_to_write_done = 0;
 	struct pagevec pvec;
 	int nr_pages;
@@ -3776,8 +3836,8 @@ retry:
 				unlock_page(page);
 				ret = 0;
 			}
-			if (ret)
-				done = 1;
+			if (!err && ret < 0)
+				err = ret;
 
 			/*
 			 * the filesystem may choose to bump up nr_to_write.
@@ -3789,7 +3849,7 @@ retry:
 		pagevec_release(&pvec);
 		cond_resched();
 	}
-	if (!scanned && !done) {
+	if (!scanned && !done && !err) {
 		/*
 		 * We hit the last page and there is more work to be done: wrap
 		 * back to the start of the file
@@ -3799,7 +3859,7 @@ retry:
 		goto retry;
 	}
 	btrfs_add_delayed_iput(inode);
-	return ret;
+	return err;
 }
 
 static void flush_epd_write_bio(struct extent_page_data *epd)
@@ -4543,6 +4603,53 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 	return NULL;
 }
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
+					       u64 start, unsigned long len)
+{
+	struct extent_buffer *eb, *exists = NULL;
+	int ret;
+
+	eb = find_extent_buffer(fs_info, start);
+	if (eb)
+		return eb;
+	eb = alloc_dummy_extent_buffer(start, len);
+	if (!eb)
+		return NULL;
+	eb->fs_info = fs_info;
+again:
+	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+	if (ret)
+		goto free_eb;
+	spin_lock(&fs_info->buffer_lock);
+	ret = radix_tree_insert(&fs_info->buffer_radix,
+				start >> PAGE_CACHE_SHIFT, eb);
+	spin_unlock(&fs_info->buffer_lock);
+	radix_tree_preload_end();
+	if (ret == -EEXIST) {
+		exists = find_extent_buffer(fs_info, start);
+		if (exists)
+			goto free_eb;
+		else
+			goto again;
+	}
+	check_buffer_tree_ref(eb);
+	set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
+
+	/*
+	 * We will free dummy extent buffer's if they come into
+	 * free_extent_buffer with a ref count of 2, but if we are using this we
+	 * want the buffers to stay in memory until we're done with them, so
+	 * bump the ref count again.
+	 */
+	atomic_inc(&eb->refs);
+	return eb;
+free_eb:
+	btrfs_release_extent_buffer(eb);
+	return exists;
+}
+#endif
+
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 					  u64 start, unsigned long len)
 {
@@ -4955,6 +5062,43 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
 	}
 }
 
+int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
+			unsigned long start,
+			unsigned long len)
+{
+	size_t cur;
+	size_t offset;
+	struct page *page;
+	char *kaddr;
+	char __user *dst = (char __user *)dstv;
+	size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
+	unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+	int ret = 0;
+
+	WARN_ON(start > eb->len);
+	WARN_ON(start + len > eb->start + eb->len);
+
+	offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+
+	while (len > 0) {
+		page = extent_buffer_page(eb, i);
+
+		cur = min(len, (PAGE_CACHE_SIZE - offset));
+		kaddr = page_address(page);
+		if (copy_to_user(dst, kaddr + offset, cur)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		dst += cur;
+		len -= cur;
+		offset = 0;
+		i++;
+	}
+
+	return ret;
+}
+
 int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 			       unsigned long min_len, char **map,
 			       unsigned long *map_start,
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index c488b45237b..ccc264e7bde 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -158,7 +158,6 @@ struct extent_buffer {
 	 * to unlock
 	 */
 	wait_queue_head_t read_lock_wq;
-	wait_queue_head_t lock_wq;
 	struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
 #ifdef CONFIG_BTRFS_DEBUG
 	struct list_head leak_list;
@@ -304,6 +303,9 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
 void read_extent_buffer(struct extent_buffer *eb, void *dst,
 			unsigned long start,
 			unsigned long len);
+int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dst,
+			       unsigned long start,
+			       unsigned long len);
 void write_extent_buffer(struct extent_buffer *eb, const void *src,
 			 unsigned long start, unsigned long len);
 void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
@@ -350,5 +352,7 @@ noinline u64 find_lock_delalloc_range(struct inode *inode,
 				      struct extent_io_tree *tree,
 				      struct page *locked_page, u64 *start,
 				      u64 *end, u64 max_bytes);
+struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
+					       u64 start, unsigned long len);
 #endif
 #endif
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 1874aee69c8..225302b39af 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -75,6 +75,8 @@ void free_extent_map(struct extent_map *em)
 	if (atomic_dec_and_test(&em->refs)) {
 		WARN_ON(extent_map_in_tree(em));
 		WARN_ON(!list_empty(&em->list));
+		if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
+			kfree(em->bdev);
 		kmem_cache_free(extent_map_cache, em);
 	}
 }
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index e7fd8a56a14..b2991fd8583 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -15,6 +15,7 @@
 #define EXTENT_FLAG_PREALLOC 3 /* pre-allocated extent */
 #define EXTENT_FLAG_LOGGING 4 /* Logging this extent */
 #define EXTENT_FLAG_FILLING 5 /* Filling in a preallocated extent */
+#define EXTENT_FLAG_FS_MAPPING 6 /* filesystem extent mapping type */
 
 struct extent_map {
 	struct rb_node rb_node;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 127555b29f5..f46cfe45d68 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -281,10 +281,10 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 found:
 		csum += count * csum_size;
 		nblocks -= count;
+		bio_index += count;
 		while (count--) {
 			disk_bytenr += bvec->bv_len;
 			offset += bvec->bv_len;
-			bio_index++;
 			bvec++;
 		}
 	}
@@ -750,7 +750,7 @@ again:
 		int slot = path->slots[0] + 1;
 		/* we didn't find a csum item, insert one */
 		nritems = btrfs_header_nritems(path->nodes[0]);
-		if (path->slots[0] >= nritems - 1) {
+		if (!nritems || (path->slots[0] >= nritems - 1)) {
 			ret = btrfs_next_leaf(root, path);
 			if (ret == 1)
 				found_next = 1;
@@ -885,3 +885,79 @@ out:
 fail_unlock:
 	goto out;
 }
+
+void btrfs_extent_item_to_extent_map(struct inode *inode,
+				     const struct btrfs_path *path,
+				     struct btrfs_file_extent_item *fi,
+				     const bool new_inline,
+				     struct extent_map *em)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct extent_buffer *leaf = path->nodes[0];
+	const int slot = path->slots[0];
+	struct btrfs_key key;
+	u64 extent_start, extent_end;
+	u64 bytenr;
+	u8 type = btrfs_file_extent_type(leaf, fi);
+	int compress_type = btrfs_file_extent_compression(leaf, fi);
+
+	em->bdev = root->fs_info->fs_devices->latest_bdev;
+	btrfs_item_key_to_cpu(leaf, &key, slot);
+	extent_start = key.offset;
+
+	if (type == BTRFS_FILE_EXTENT_REG ||
+	    type == BTRFS_FILE_EXTENT_PREALLOC) {
+		extent_end = extent_start +
+			btrfs_file_extent_num_bytes(leaf, fi);
+	} else if (type == BTRFS_FILE_EXTENT_INLINE) {
+		size_t size;
+		size = btrfs_file_extent_inline_len(leaf, slot, fi);
+		extent_end = ALIGN(extent_start + size, root->sectorsize);
+	}
+
+	em->ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
+	if (type == BTRFS_FILE_EXTENT_REG ||
+	    type == BTRFS_FILE_EXTENT_PREALLOC) {
+		em->start = extent_start;
+		em->len = extent_end - extent_start;
+		em->orig_start = extent_start -
+			btrfs_file_extent_offset(leaf, fi);
+		em->orig_block_len = btrfs_file_extent_disk_num_bytes(leaf, fi);
+		bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
+		if (bytenr == 0) {
+			em->block_start = EXTENT_MAP_HOLE;
+			return;
+		}
+		if (compress_type != BTRFS_COMPRESS_NONE) {
+			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+			em->compress_type = compress_type;
+			em->block_start = bytenr;
+			em->block_len = em->orig_block_len;
+		} else {
+			bytenr += btrfs_file_extent_offset(leaf, fi);
+			em->block_start = bytenr;
+			em->block_len = em->len;
+			if (type == BTRFS_FILE_EXTENT_PREALLOC)
+				set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
+		}
+	} else if (type == BTRFS_FILE_EXTENT_INLINE) {
+		em->block_start = EXTENT_MAP_INLINE;
+		em->start = extent_start;
+		em->len = extent_end - extent_start;
+		/*
+		 * Initialize orig_start and block_len with the same values
+		 * as in inode.c:btrfs_get_extent().
+		 */
+		em->orig_start = EXTENT_MAP_HOLE;
+		em->block_len = (u64)-1;
+		if (!new_inline && compress_type != BTRFS_COMPRESS_NONE) {
+			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+			em->compress_type = compress_type;
+		}
+	} else {
+		btrfs_err(root->fs_info,
+			  "unknown file extent item type %d, inode %llu, offset %llu, root %llu",
+			  type, btrfs_ino(inode), extent_start,
+			  root->root_key.objectid);
+	}
+}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 74272a3f9d9..1f2b99cb55e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -40,6 +40,7 @@
 #include "tree-log.h"
 #include "locking.h"
 #include "volumes.h"
+#include "qgroup.h"
 
 static struct kmem_cache *btrfs_inode_defrag_cachep;
 /*
@@ -447,7 +448,7 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 		write_bytes -= copied;
 		total_copied += copied;
 
-		/* Return to btrfs_file_aio_write to fault page */
+		/* Return to btrfs_file_write_iter to fault page */
 		if (unlikely(copied == 0))
 			break;
 
@@ -715,7 +716,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	int recow;
 	int ret;
 	int modify_tree = -1;
-	int update_refs = (root->ref_cows || root == root->fs_info->tree_root);
+	int update_refs;
 	int found = 0;
 	int leafs_visited = 0;
 
@@ -725,6 +726,8 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent)
 		modify_tree = 0;
 
+	update_refs = (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+		       root == root->fs_info->tree_root);
 	while (1) {
 		recow = 0;
 		ret = btrfs_lookup_file_extent(trans, root, path, ino,
@@ -781,6 +784,18 @@ next_slot:
 			extent_end = search_start;
 		}
 
+		/*
+		 * Don't skip extent items representing 0 byte lengths. They
+		 * used to be created (bug) if while punching holes we hit
+		 * -ENOSPC condition. So if we find one here, just ensure we
+		 * delete it, otherwise we would insert a new file extent item
+		 * with the same key (offset) as that 0 bytes length file
+		 * extent item in the call to setup_items_for_insert() later
+		 * in this function.
+		 */
+		if (extent_end == key.offset && extent_end >= search_start)
+			goto delete_extent_item;
+
 		if (extent_end <= search_start) {
 			path->slots[0]++;
 			goto next_slot;
@@ -836,7 +851,7 @@ next_slot:
 						disk_bytenr, num_bytes, 0,
 						root->root_key.objectid,
 						new_key.objectid,
-						start - extent_offset, 0);
+						start - extent_offset, 1);
 				BUG_ON(ret); /* -ENOMEM */
 			}
 			key.offset = start;
@@ -894,6 +909,7 @@ next_slot:
 		 *    | ------ extent ------ |
 		 */
 		if (start <= key.offset && end >= extent_end) {
+delete_extent_item:
 			if (del_nr == 0) {
 				del_slot = path->slots[0];
 				del_nr = 1;
@@ -1192,7 +1208,7 @@ again:
 
 		ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
 					   root->root_key.objectid,
-					   ino, orig_offset, 0);
+					   ino, orig_offset, 1);
 		BUG_ON(ret); /* -ENOMEM */
 
 		if (split == start) {
@@ -1659,27 +1675,22 @@ again:
 }
 
 static ssize_t __btrfs_direct_write(struct kiocb *iocb,
-				    const struct iovec *iov,
-				    unsigned long nr_segs, loff_t pos,
-				    size_t count, size_t ocount)
+				    struct iov_iter *from,
+				    loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
-	struct iov_iter i;
 	ssize_t written;
 	ssize_t written_buffered;
 	loff_t endbyte;
 	int err;
 
-	written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
-					    count, ocount);
+	written = generic_file_direct_write(iocb, from, pos);
 
-	if (written < 0 || written == count)
+	if (written < 0 || !iov_iter_count(from))
 		return written;
 
 	pos += written;
-	count -= written;
-	iov_iter_init(&i, iov, nr_segs, count, written);
-	written_buffered = __btrfs_buffered_write(file, &i, pos);
+	written_buffered = __btrfs_buffered_write(file, from, pos);
 	if (written_buffered < 0) {
 		err = written_buffered;
 		goto out;
@@ -1714,9 +1725,8 @@ static void update_time_for_write(struct inode *inode)
 		inode_inc_iversion(inode);
 }
 
-static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
-				    const struct iovec *iov,
-				    unsigned long nr_segs, loff_t pos)
+static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
+				    struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
@@ -1725,18 +1735,12 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	u64 end_pos;
 	ssize_t num_written = 0;
 	ssize_t err = 0;
-	size_t count, ocount;
+	size_t count = iov_iter_count(from);
 	bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host);
+	loff_t pos = iocb->ki_pos;
 
 	mutex_lock(&inode->i_mutex);
 
-	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
-	if (err) {
-		mutex_unlock(&inode->i_mutex);
-		goto out;
-	}
-	count = ocount;
-
 	current->backing_dev_info = inode->i_mapping->backing_dev_info;
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err) {
@@ -1749,6 +1753,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		goto out;
 	}
 
+	iov_iter_truncate(from, count);
+
 	err = file_remove_suid(file);
 	if (err) {
 		mutex_unlock(&inode->i_mutex);
@@ -1790,14 +1796,9 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		atomic_inc(&BTRFS_I(inode)->sync_writers);
 
 	if (unlikely(file->f_flags & O_DIRECT)) {
-		num_written = __btrfs_direct_write(iocb, iov, nr_segs,
-						   pos, count, ocount);
+		num_written = __btrfs_direct_write(iocb, from, pos);
 	} else {
-		struct iov_iter i;
-
-		iov_iter_init(&i, iov, nr_segs, count, num_written);
-
-		num_written = __btrfs_buffered_write(file, &i, pos);
+		num_written = __btrfs_buffered_write(file, from, pos);
 		if (num_written > 0)
 			iocb->ki_pos = pos + num_written;
 	}
@@ -2010,8 +2011,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		if (!full_sync) {
 			ret = btrfs_wait_ordered_range(inode, start,
 						       end - start + 1);
-			if (ret)
+			if (ret) {
+				btrfs_end_transaction(trans, root);
 				goto out;
+			}
 		}
 		ret = btrfs_commit_transaction(trans, root);
 	} else {
@@ -2169,6 +2172,37 @@ out:
 	return 0;
 }
 
+/*
+ * Find a hole extent on given inode and change start/len to the end of hole
+ * extent.(hole/vacuum extent whose em->start <= start &&
+ *	   em->start + em->len > start)
+ * When a hole extent is found, return 1 and modify start/len.
+ */
+static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len)
+{
+	struct extent_map *em;
+	int ret = 0;
+
+	em = btrfs_get_extent(inode, NULL, 0, *start, *len, 0);
+	if (IS_ERR_OR_NULL(em)) {
+		if (!em)
+			ret = -ENOMEM;
+		else
+			ret = PTR_ERR(em);
+		return ret;
+	}
+
+	/* Hole or vacuum extent(only exists in no-hole mode) */
+	if (em->block_start == EXTENT_MAP_HOLE) {
+		ret = 1;
+		*len = em->start + em->len > *start + *len ?
+		       0 : *start + *len - em->start - em->len;
+		*start = em->start + em->len;
+	}
+	free_extent_map(em);
+	return ret;
+}
+
 static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -2176,25 +2210,42 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	struct btrfs_path *path;
 	struct btrfs_block_rsv *rsv;
 	struct btrfs_trans_handle *trans;
-	u64 lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
-	u64 lockend = round_down(offset + len,
-				 BTRFS_I(inode)->root->sectorsize) - 1;
-	u64 cur_offset = lockstart;
+	u64 lockstart;
+	u64 lockend;
+	u64 tail_start;
+	u64 tail_len;
+	u64 orig_start = offset;
+	u64 cur_offset;
 	u64 min_size = btrfs_calc_trunc_metadata_size(root, 1);
 	u64 drop_end;
 	int ret = 0;
 	int err = 0;
 	int rsv_count;
-	bool same_page = ((offset >> PAGE_CACHE_SHIFT) ==
-			  ((offset + len - 1) >> PAGE_CACHE_SHIFT));
+	bool same_page;
 	bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
-	u64 ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
+	u64 ino_size;
 
 	ret = btrfs_wait_ordered_range(inode, offset, len);
 	if (ret)
 		return ret;
 
 	mutex_lock(&inode->i_mutex);
+	ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
+	ret = find_first_non_hole(inode, &offset, &len);
+	if (ret < 0)
+		goto out_only_mutex;
+	if (ret && !len) {
+		/* Already in a large hole */
+		ret = 0;
+		goto out_only_mutex;
+	}
+
+	lockstart = round_up(offset , BTRFS_I(inode)->root->sectorsize);
+	lockend = round_down(offset + len,
+			     BTRFS_I(inode)->root->sectorsize) - 1;
+	same_page = ((offset >> PAGE_CACHE_SHIFT) ==
+		    ((offset + len - 1) >> PAGE_CACHE_SHIFT));
+
 	/*
 	 * We needn't truncate any page which is beyond the end of the file
 	 * because we are sure there is no data there.
@@ -2206,8 +2257,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	if (same_page && len < PAGE_CACHE_SIZE) {
 		if (offset < ino_size)
 			ret = btrfs_truncate_page(inode, offset, len, 0);
-		mutex_unlock(&inode->i_mutex);
-		return ret;
+		goto out_only_mutex;
 	}
 
 	/* zero back part of the first page */
@@ -2219,12 +2269,39 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		}
 	}
 
-	/* zero the front end of the last page */
-	if (offset + len < ino_size) {
-		ret = btrfs_truncate_page(inode, offset + len, 0, 1);
-		if (ret) {
-			mutex_unlock(&inode->i_mutex);
-			return ret;
+	/* Check the aligned pages after the first unaligned page,
+	 * if offset != orig_start, which means the first unaligned page
+	 * including serveral following pages are already in holes,
+	 * the extra check can be skipped */
+	if (offset == orig_start) {
+		/* after truncate page, check hole again */
+		len = offset + len - lockstart;
+		offset = lockstart;
+		ret = find_first_non_hole(inode, &offset, &len);
+		if (ret < 0)
+			goto out_only_mutex;
+		if (ret && !len) {
+			ret = 0;
+			goto out_only_mutex;
+		}
+		lockstart = offset;
+	}
+
+	/* Check the tail unaligned part is in a hole */
+	tail_start = lockend + 1;
+	tail_len = offset + len - tail_start;
+	if (tail_len) {
+		ret = find_first_non_hole(inode, &tail_start, &tail_len);
+		if (unlikely(ret < 0))
+			goto out_only_mutex;
+		if (!ret) {
+			/* zero the front end of the last page */
+			if (tail_start + tail_len < ino_size) {
+				ret = btrfs_truncate_page(inode,
+						tail_start + tail_len, 0, 1);
+				if (ret)
+					goto out_only_mutex;
+				}
 		}
 	}
 
@@ -2250,9 +2327,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		if ((!ordered ||
 		    (ordered->file_offset + ordered->len <= lockstart ||
 		     ordered->file_offset > lockend)) &&
-		     !test_range_bit(&BTRFS_I(inode)->io_tree, lockstart,
-				     lockend, EXTENT_UPTODATE, 0,
-				     cached_state)) {
+		     !btrfs_page_exists_in_range(inode, lockstart, lockend)) {
 			if (ordered)
 				btrfs_put_ordered_extent(ordered);
 			break;
@@ -2300,6 +2375,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	BUG_ON(ret);
 	trans->block_rsv = rsv;
 
+	cur_offset = lockstart;
+	len = lockend - cur_offset;
 	while (cur_offset < lockend) {
 		ret = __btrfs_drop_extents(trans, root, inode, path,
 					   cur_offset, lockend + 1,
@@ -2340,6 +2417,14 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 					      rsv, min_size);
 		BUG_ON(ret);	/* shouldn't happen */
 		trans->block_rsv = rsv;
+
+		ret = find_first_non_hole(inode, &cur_offset, &len);
+		if (unlikely(ret < 0))
+			break;
+		if (ret && !len) {
+			ret = 0;
+			break;
+		}
 	}
 
 	if (ret) {
@@ -2348,7 +2433,12 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	}
 
 	trans->block_rsv = &root->fs_info->trans_block_rsv;
-	if (cur_offset < ino_size) {
+	/*
+	 * Don't insert file hole extent item if it's for a range beyond eof
+	 * (because it's useless) or if it represents a 0 bytes range (when
+	 * cur_offset == drop_end).
+	 */
+	if (cur_offset < ino_size && cur_offset < drop_end) {
 		ret = fill_holes(trans, inode, path, cur_offset, drop_end);
 		if (ret) {
 			err = ret;
@@ -2373,6 +2463,7 @@ out_free:
 out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			     &cached_state, GFP_NOFS);
+out_only_mutex:
 	mutex_unlock(&inode->i_mutex);
 	if (ret && !err)
 		err = ret;
@@ -2634,11 +2725,11 @@ out:
 
 const struct file_operations btrfs_file_operations = {
 	.llseek		= btrfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read       = generic_file_aio_read,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter      = generic_file_read_iter,
 	.splice_read	= generic_file_splice_read,
-	.aio_write	= btrfs_file_aio_write,
+	.write_iter	= btrfs_file_write_iter,
 	.mmap		= btrfs_file_mmap,
 	.open		= generic_file_open,
 	.release	= btrfs_release_file,
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 73f3de7a083..2b0a627cb5f 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -274,18 +274,32 @@ struct io_ctl {
 };
 
 static int io_ctl_init(struct io_ctl *io_ctl, struct inode *inode,
-		       struct btrfs_root *root)
+		       struct btrfs_root *root, int write)
 {
+	int num_pages;
+	int check_crcs = 0;
+
+	num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+		    PAGE_CACHE_SHIFT;
+
+	if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID)
+		check_crcs = 1;
+
+	/* Make sure we can fit our crcs into the first page */
+	if (write && check_crcs &&
+	    (num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE)
+		return -ENOSPC;
+
 	memset(io_ctl, 0, sizeof(struct io_ctl));
-	io_ctl->num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
-		PAGE_CACHE_SHIFT;
-	io_ctl->pages = kzalloc(sizeof(struct page *) * io_ctl->num_pages,
-				GFP_NOFS);
+
+	io_ctl->pages = kzalloc(sizeof(struct page *) * num_pages, GFP_NOFS);
 	if (!io_ctl->pages)
 		return -ENOMEM;
+
+	io_ctl->num_pages = num_pages;
 	io_ctl->root = root;
-	if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID)
-		io_ctl->check_crcs = 1;
+	io_ctl->check_crcs = check_crcs;
+
 	return 0;
 }
 
@@ -666,6 +680,13 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 	generation = btrfs_free_space_generation(leaf, header);
 	btrfs_release_path(path);
 
+	if (!BTRFS_I(inode)->generation) {
+		btrfs_info(root->fs_info,
+			   "The free space cache file (%llu) is invalid. skip it\n",
+			   offset);
+		return 0;
+	}
+
 	if (BTRFS_I(inode)->generation != generation) {
 		btrfs_err(root->fs_info,
 			"free space inode generation (%llu) "
@@ -677,7 +698,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 	if (!num_entries)
 		return 0;
 
-	ret = io_ctl_init(&io_ctl, inode, root);
+	ret = io_ctl_init(&io_ctl, inode, root, 0);
 	if (ret)
 		return ret;
 
@@ -831,7 +852,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 
 	if (!matched) {
 		__btrfs_remove_free_space_cache(ctl);
-		btrfs_err(fs_info, "block group %llu has wrong amount of free space",
+		btrfs_warn(fs_info, "block group %llu has wrong amount of free space",
 			block_group->key.objectid);
 		ret = -1;
 	}
@@ -843,7 +864,7 @@ out:
 		spin_unlock(&block_group->lock);
 		ret = 0;
 
-		btrfs_err(fs_info, "failed to load free space cache for block group %llu",
+		btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuild it now",
 			block_group->key.objectid);
 	}
 
@@ -851,90 +872,44 @@ out:
 	return ret;
 }
 
-/**
- * __btrfs_write_out_cache - write out cached info to an inode
- * @root - the root the inode belongs to
- * @ctl - the free space cache we are going to write out
- * @block_group - the block_group for this cache if it belongs to a block_group
- * @trans - the trans handle
- * @path - the path to use
- * @offset - the offset for the key we'll insert
- *
- * This function writes out a free space cache struct to disk for quick recovery
- * on mount.  This will return 0 if it was successfull in writing the cache out,
- * and -1 if it was not.
- */
-static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
-				   struct btrfs_free_space_ctl *ctl,
-				   struct btrfs_block_group_cache *block_group,
-				   struct btrfs_trans_handle *trans,
-				   struct btrfs_path *path, u64 offset)
+static noinline_for_stack
+int write_cache_extent_entries(struct io_ctl *io_ctl,
+			      struct btrfs_free_space_ctl *ctl,
+			      struct btrfs_block_group_cache *block_group,
+			      int *entries, int *bitmaps,
+			      struct list_head *bitmap_list)
 {
-	struct btrfs_free_space_header *header;
-	struct extent_buffer *leaf;
-	struct rb_node *node;
-	struct list_head *pos, *n;
-	struct extent_state *cached_state = NULL;
-	struct btrfs_free_cluster *cluster = NULL;
-	struct extent_io_tree *unpin = NULL;
-	struct io_ctl io_ctl;
-	struct list_head bitmap_list;
-	struct btrfs_key key;
-	u64 start, extent_start, extent_end, len;
-	int entries = 0;
-	int bitmaps = 0;
 	int ret;
-	int err = -1;
-
-	INIT_LIST_HEAD(&bitmap_list);
-
-	if (!i_size_read(inode))
-		return -1;
-
-	ret = io_ctl_init(&io_ctl, inode, root);
-	if (ret)
-		return -1;
+	struct btrfs_free_cluster *cluster = NULL;
+	struct rb_node *node = rb_first(&ctl->free_space_offset);
 
 	/* Get the cluster for this block_group if it exists */
-	if (block_group && !list_empty(&block_group->cluster_list))
+	if (block_group && !list_empty(&block_group->cluster_list)) {
 		cluster = list_entry(block_group->cluster_list.next,
 				     struct btrfs_free_cluster,
 				     block_group_list);
+	}
 
-	/* Lock all pages first so we can lock the extent safely. */
-	io_ctl_prepare_pages(&io_ctl, inode, 0);
-
-	lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
-			 0, &cached_state);
-
-	node = rb_first(&ctl->free_space_offset);
 	if (!node && cluster) {
 		node = rb_first(&cluster->root);
 		cluster = NULL;
 	}
 
-	/* Make sure we can fit our crcs into the first page */
-	if (io_ctl.check_crcs &&
-	    (io_ctl.num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE)
-		goto out_nospc;
-
-	io_ctl_set_generation(&io_ctl, trans->transid);
-
 	/* Write out the extent entries */
 	while (node) {
 		struct btrfs_free_space *e;
 
 		e = rb_entry(node, struct btrfs_free_space, offset_index);
-		entries++;
+		*entries += 1;
 
-		ret = io_ctl_add_entry(&io_ctl, e->offset, e->bytes,
+		ret = io_ctl_add_entry(io_ctl, e->offset, e->bytes,
 				       e->bitmap);
 		if (ret)
-			goto out_nospc;
+			goto fail;
 
 		if (e->bitmap) {
-			list_add_tail(&e->list, &bitmap_list);
-			bitmaps++;
+			list_add_tail(&e->list, bitmap_list);
+			*bitmaps += 1;
 		}
 		node = rb_next(node);
 		if (!node && cluster) {
@@ -942,136 +917,289 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 			cluster = NULL;
 		}
 	}
+	return 0;
+fail:
+	return -ENOSPC;
+}
+
+static noinline_for_stack int
+update_cache_item(struct btrfs_trans_handle *trans,
+		  struct btrfs_root *root,
+		  struct inode *inode,
+		  struct btrfs_path *path, u64 offset,
+		  int entries, int bitmaps)
+{
+	struct btrfs_key key;
+	struct btrfs_free_space_header *header;
+	struct extent_buffer *leaf;
+	int ret;
+
+	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
+	key.offset = offset;
+	key.type = 0;
+
+	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	if (ret < 0) {
+		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1,
+				 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL,
+				 GFP_NOFS);
+		goto fail;
+	}
+	leaf = path->nodes[0];
+	if (ret > 0) {
+		struct btrfs_key found_key;
+		ASSERT(path->slots[0]);
+		path->slots[0]--;
+		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+		if (found_key.objectid != BTRFS_FREE_SPACE_OBJECTID ||
+		    found_key.offset != offset) {
+			clear_extent_bit(&BTRFS_I(inode)->io_tree, 0,
+					 inode->i_size - 1,
+					 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0,
+					 NULL, GFP_NOFS);
+			btrfs_release_path(path);
+			goto fail;
+		}
+	}
+
+	BTRFS_I(inode)->generation = trans->transid;
+	header = btrfs_item_ptr(leaf, path->slots[0],
+				struct btrfs_free_space_header);
+	btrfs_set_free_space_entries(leaf, header, entries);
+	btrfs_set_free_space_bitmaps(leaf, header, bitmaps);
+	btrfs_set_free_space_generation(leaf, header, trans->transid);
+	btrfs_mark_buffer_dirty(leaf);
+	btrfs_release_path(path);
+
+	return 0;
+
+fail:
+	return -1;
+}
+
+static noinline_for_stack int
+write_pinned_extent_entries(struct btrfs_root *root,
+			    struct btrfs_block_group_cache *block_group,
+			    struct io_ctl *io_ctl,
+			    int *entries)
+{
+	u64 start, extent_start, extent_end, len;
+	struct extent_io_tree *unpin = NULL;
+	int ret;
+
+	if (!block_group)
+		return 0;
 
 	/*
 	 * We want to add any pinned extents to our free space cache
 	 * so we don't leak the space
-	 */
-
-	/*
+	 *
 	 * We shouldn't have switched the pinned extents yet so this is the
 	 * right one
 	 */
 	unpin = root->fs_info->pinned_extents;
 
-	if (block_group)
-		start = block_group->key.objectid;
+	start = block_group->key.objectid;
 
-	while (block_group && (start < block_group->key.objectid +
-			       block_group->key.offset)) {
+	while (start < block_group->key.objectid + block_group->key.offset) {
 		ret = find_first_extent_bit(unpin, start,
 					    &extent_start, &extent_end,
 					    EXTENT_DIRTY, NULL);
-		if (ret) {
-			ret = 0;
-			break;
-		}
+		if (ret)
+			return 0;
 
 		/* This pinned extent is out of our range */
 		if (extent_start >= block_group->key.objectid +
 		    block_group->key.offset)
-			break;
+			return 0;
 
 		extent_start = max(extent_start, start);
 		extent_end = min(block_group->key.objectid +
 				 block_group->key.offset, extent_end + 1);
 		len = extent_end - extent_start;
 
-		entries++;
-		ret = io_ctl_add_entry(&io_ctl, extent_start, len, NULL);
+		*entries += 1;
+		ret = io_ctl_add_entry(io_ctl, extent_start, len, NULL);
 		if (ret)
-			goto out_nospc;
+			return -ENOSPC;
 
 		start = extent_end;
 	}
 
+	return 0;
+}
+
+static noinline_for_stack int
+write_bitmap_entries(struct io_ctl *io_ctl, struct list_head *bitmap_list)
+{
+	struct list_head *pos, *n;
+	int ret;
+
 	/* Write out the bitmaps */
-	list_for_each_safe(pos, n, &bitmap_list) {
+	list_for_each_safe(pos, n, bitmap_list) {
 		struct btrfs_free_space *entry =
 			list_entry(pos, struct btrfs_free_space, list);
 
-		ret = io_ctl_add_bitmap(&io_ctl, entry->bitmap);
+		ret = io_ctl_add_bitmap(io_ctl, entry->bitmap);
 		if (ret)
-			goto out_nospc;
+			return -ENOSPC;
 		list_del_init(&entry->list);
 	}
 
-	/* Zero out the rest of the pages just to make sure */
-	io_ctl_zero_remaining_pages(&io_ctl);
-
-	ret = btrfs_dirty_pages(root, inode, io_ctl.pages, io_ctl.num_pages,
-				0, i_size_read(inode), &cached_state);
-	io_ctl_drop_pages(&io_ctl);
-	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
-			     i_size_read(inode) - 1, &cached_state, GFP_NOFS);
+	return 0;
+}
 
-	if (ret)
-		goto out;
+static int flush_dirty_cache(struct inode *inode)
+{
+	int ret;
 
 	ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
-	if (ret) {
+	if (ret)
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1,
 				 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL,
 				 GFP_NOFS);
-		goto out;
-	}
 
-	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.offset = offset;
-	key.type = 0;
+	return ret;
+}
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
-	if (ret < 0) {
-		clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1,
-				 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL,
-				 GFP_NOFS);
-		goto out;
+static void noinline_for_stack
+cleanup_write_cache_enospc(struct inode *inode,
+			   struct io_ctl *io_ctl,
+			   struct extent_state **cached_state,
+			   struct list_head *bitmap_list)
+{
+	struct list_head *pos, *n;
+
+	list_for_each_safe(pos, n, bitmap_list) {
+		struct btrfs_free_space *entry =
+			list_entry(pos, struct btrfs_free_space, list);
+		list_del_init(&entry->list);
 	}
-	leaf = path->nodes[0];
-	if (ret > 0) {
-		struct btrfs_key found_key;
-		ASSERT(path->slots[0]);
-		path->slots[0]--;
-		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-		if (found_key.objectid != BTRFS_FREE_SPACE_OBJECTID ||
-		    found_key.offset != offset) {
-			clear_extent_bit(&BTRFS_I(inode)->io_tree, 0,
-					 inode->i_size - 1,
-					 EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0,
-					 NULL, GFP_NOFS);
-			btrfs_release_path(path);
+	io_ctl_drop_pages(io_ctl);
+	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
+			     i_size_read(inode) - 1, cached_state,
+			     GFP_NOFS);
+}
+
+/**
+ * __btrfs_write_out_cache - write out cached info to an inode
+ * @root - the root the inode belongs to
+ * @ctl - the free space cache we are going to write out
+ * @block_group - the block_group for this cache if it belongs to a block_group
+ * @trans - the trans handle
+ * @path - the path to use
+ * @offset - the offset for the key we'll insert
+ *
+ * This function writes out a free space cache struct to disk for quick recovery
+ * on mount.  This will return 0 if it was successfull in writing the cache out,
+ * and -1 if it was not.
+ */
+static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
+				   struct btrfs_free_space_ctl *ctl,
+				   struct btrfs_block_group_cache *block_group,
+				   struct btrfs_trans_handle *trans,
+				   struct btrfs_path *path, u64 offset)
+{
+	struct extent_state *cached_state = NULL;
+	struct io_ctl io_ctl;
+	LIST_HEAD(bitmap_list);
+	int entries = 0;
+	int bitmaps = 0;
+	int ret;
+
+	if (!i_size_read(inode))
+		return -1;
+
+	ret = io_ctl_init(&io_ctl, inode, root, 1);
+	if (ret)
+		return -1;
+
+	if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) {
+		down_write(&block_group->data_rwsem);
+		spin_lock(&block_group->lock);
+		if (block_group->delalloc_bytes) {
+			block_group->disk_cache_state = BTRFS_DC_WRITTEN;
+			spin_unlock(&block_group->lock);
+			up_write(&block_group->data_rwsem);
+			BTRFS_I(inode)->generation = 0;
+			ret = 0;
 			goto out;
 		}
+		spin_unlock(&block_group->lock);
 	}
 
-	BTRFS_I(inode)->generation = trans->transid;
-	header = btrfs_item_ptr(leaf, path->slots[0],
-				struct btrfs_free_space_header);
-	btrfs_set_free_space_entries(leaf, header, entries);
-	btrfs_set_free_space_bitmaps(leaf, header, bitmaps);
-	btrfs_set_free_space_generation(leaf, header, trans->transid);
-	btrfs_mark_buffer_dirty(leaf);
-	btrfs_release_path(path);
+	/* Lock all pages first so we can lock the extent safely. */
+	io_ctl_prepare_pages(&io_ctl, inode, 0);
+
+	lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
+			 0, &cached_state);
+
+	io_ctl_set_generation(&io_ctl, trans->transid);
+
+	/* Write out the extent entries in the free space cache */
+	ret = write_cache_extent_entries(&io_ctl, ctl,
+					 block_group, &entries, &bitmaps,
+					 &bitmap_list);
+	if (ret)
+		goto out_nospc;
+
+	/*
+	 * Some spaces that are freed in the current transaction are pinned,
+	 * they will be added into free space cache after the transaction is
+	 * committed, we shouldn't lose them.
+	 */
+	ret = write_pinned_extent_entries(root, block_group, &io_ctl, &entries);
+	if (ret)
+		goto out_nospc;
+
+	/* At last, we write out all the bitmaps. */
+	ret = write_bitmap_entries(&io_ctl, &bitmap_list);
+	if (ret)
+		goto out_nospc;
+
+	/* Zero out the rest of the pages just to make sure */
+	io_ctl_zero_remaining_pages(&io_ctl);
+
+	/* Everything is written out, now we dirty the pages in the file. */
+	ret = btrfs_dirty_pages(root, inode, io_ctl.pages, io_ctl.num_pages,
+				0, i_size_read(inode), &cached_state);
+	if (ret)
+		goto out_nospc;
+
+	if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
+		up_write(&block_group->data_rwsem);
+	/*
+	 * Release the pages and unlock the extent, we will flush
+	 * them out later
+	 */
+	io_ctl_drop_pages(&io_ctl);
+
+	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
+			     i_size_read(inode) - 1, &cached_state, GFP_NOFS);
+
+	/* Flush the dirty pages in the cache file. */
+	ret = flush_dirty_cache(inode);
+	if (ret)
+		goto out;
 
-	err = 0;
+	/* Update the cache item to tell everyone this cache file is valid. */
+	ret = update_cache_item(trans, root, inode, path, offset,
+				entries, bitmaps);
 out:
 	io_ctl_free(&io_ctl);
-	if (err) {
+	if (ret) {
 		invalidate_inode_pages2(inode->i_mapping);
 		BTRFS_I(inode)->generation = 0;
 	}
 	btrfs_update_inode(trans, root, inode);
-	return err;
+	return ret;
 
 out_nospc:
-	list_for_each_safe(pos, n, &bitmap_list) {
-		struct btrfs_free_space *entry =
-			list_entry(pos, struct btrfs_free_space, list);
-		list_del_init(&entry->list);
-	}
-	io_ctl_drop_pages(&io_ctl);
-	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
-			     i_size_read(inode) - 1, &cached_state, GFP_NOFS);
+	cleanup_write_cache_enospc(inode, &io_ctl, &cached_state, &bitmap_list);
+
+	if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
+		up_write(&block_group->data_rwsem);
+
 	goto out;
 }
 
@@ -1091,6 +1219,12 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 		spin_unlock(&block_group->lock);
 		return 0;
 	}
+
+	if (block_group->delalloc_bytes) {
+		block_group->disk_cache_state = BTRFS_DC_WRITTEN;
+		spin_unlock(&block_group->lock);
+		return 0;
+	}
 	spin_unlock(&block_group->lock);
 
 	inode = lookup_free_space_inode(root, block_group, path);
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 86935f5ae29..888fbe19079 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -174,7 +174,7 @@ static void start_caching(struct btrfs_root *root)
 				       BTRFS_LAST_FREE_OBJECTID - objectid + 1);
 	}
 
-	tsk = kthread_run(caching_kthread, root, "btrfs-ino-cache-%llu\n",
+	tsk = kthread_run(caching_kthread, root, "btrfs-ino-cache-%llu",
 			  root->root_key.objectid);
 	if (IS_ERR(tsk)) {
 		btrfs_warn(root->fs_info, "failed to start inode caching task");
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5a3b8371772..3668048e16f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -125,7 +125,7 @@ static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
  * the btree.  The caller should have done a btrfs_drop_extents so that
  * no overlapping inline items exist in the btree
  */
-static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
+static int insert_inline_extent(struct btrfs_trans_handle *trans,
 				struct btrfs_path *path, int extent_inserted,
 				struct btrfs_root *root, struct inode *inode,
 				u64 start, size_t size, size_t compressed_size,
@@ -693,7 +693,7 @@ retry:
 		ret = btrfs_reserve_extent(root,
 					   async_extent->compressed_size,
 					   async_extent->compressed_size,
-					   0, alloc_hint, &ins, 1);
+					   0, alloc_hint, &ins, 1, 1);
 		if (ret) {
 			int i;
 
@@ -794,7 +794,7 @@ retry:
 out:
 	return ret;
 out_free_reserve:
-	btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+	btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 out_free:
 	extent_clear_unlock_delalloc(inode, async_extent->start,
 				     async_extent->start +
@@ -917,7 +917,7 @@ static noinline int cow_file_range(struct inode *inode,
 		cur_alloc_size = disk_num_bytes;
 		ret = btrfs_reserve_extent(root, cur_alloc_size,
 					   root->sectorsize, 0, alloc_hint,
-					   &ins, 1);
+					   &ins, 1, 1);
 		if (ret < 0)
 			goto out_unlock;
 
@@ -995,7 +995,7 @@ out:
 	return ret;
 
 out_reserve:
-	btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+	btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 out_unlock:
 	extent_clear_unlock_delalloc(inode, start, end, locked_page,
 				     EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
@@ -2599,6 +2599,21 @@ out_kfree:
 	return NULL;
 }
 
+static void btrfs_release_delalloc_bytes(struct btrfs_root *root,
+					 u64 start, u64 len)
+{
+	struct btrfs_block_group_cache *cache;
+
+	cache = btrfs_lookup_block_group(root->fs_info, start);
+	ASSERT(cache);
+
+	spin_lock(&cache->lock);
+	cache->delalloc_bytes -= len;
+	spin_unlock(&cache->lock);
+
+	btrfs_put_block_group(cache);
+}
+
 /* as ordered data IO finishes, this gets called so we can finish
  * an ordered extent if the range of bytes in the file it covers are
  * fully written.
@@ -2678,6 +2693,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		trans = NULL;
 		goto out_unlock;
 	}
+
 	trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
 	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
@@ -2697,6 +2713,10 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 						logical_len, logical_len,
 						compress_type, 0, 0,
 						BTRFS_FILE_EXTENT_REG);
+		if (!ret)
+			btrfs_release_delalloc_bytes(root,
+						     ordered_extent->start,
+						     ordered_extent->disk_len);
 	}
 	unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
 			   ordered_extent->file_offset, ordered_extent->len,
@@ -2749,7 +2769,7 @@ out:
 		    !test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
 		    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
 			btrfs_free_reserved_extent(root, ordered_extent->start,
-						   ordered_extent->disk_len);
+						   ordered_extent->disk_len, 1);
 	}
 
 
@@ -2947,14 +2967,15 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
 	root->orphan_block_rsv = NULL;
 	spin_unlock(&root->orphan_lock);
 
-	if (root->orphan_item_inserted &&
+	if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state) &&
 	    btrfs_root_refs(&root->root_item) > 0) {
 		ret = btrfs_del_orphan_item(trans, root->fs_info->tree_root,
 					    root->root_key.objectid);
 		if (ret)
 			btrfs_abort_transaction(trans, root, ret);
 		else
-			root->orphan_item_inserted = 0;
+			clear_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
+				  &root->state);
 	}
 
 	if (block_rsv) {
@@ -3271,7 +3292,8 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		btrfs_block_rsv_release(root, root->orphan_block_rsv,
 					(u64)-1);
 
-	if (root->orphan_block_rsv || root->orphan_item_inserted) {
+	if (root->orphan_block_rsv ||
+	    test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
 		trans = btrfs_join_transaction(root);
 		if (!IS_ERR(trans))
 			btrfs_end_transaction(trans, root);
@@ -3473,7 +3495,7 @@ cache_acl:
 		ret = btrfs_load_inode_props(inode, path);
 		if (ret)
 			btrfs_err(root->fs_info,
-				  "error loading props for ino %llu (root %llu): %d\n",
+				  "error loading props for ino %llu (root %llu): %d",
 				  btrfs_ino(inode),
 				  root->root_key.objectid, ret);
 	}
@@ -3998,7 +4020,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	 * not block aligned since we will be keeping the last block of the
 	 * extent just the way it is.
 	 */
-	if (root->ref_cows || root == root->fs_info->tree_root)
+	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+	    root == root->fs_info->tree_root)
 		btrfs_drop_extent_cache(inode, ALIGN(new_size,
 					root->sectorsize), (u64)-1, 0);
 
@@ -4091,7 +4114,9 @@ search_again:
 							 extent_num_bytes);
 				num_dec = (orig_num_bytes -
 					   extent_num_bytes);
-				if (root->ref_cows && extent_start != 0)
+				if (test_bit(BTRFS_ROOT_REF_COWS,
+					     &root->state) &&
+				    extent_start != 0)
 					inode_sub_bytes(inode, num_dec);
 				btrfs_mark_buffer_dirty(leaf);
 			} else {
@@ -4105,7 +4130,8 @@ search_again:
 				num_dec = btrfs_file_extent_num_bytes(leaf, fi);
 				if (extent_start != 0) {
 					found_extent = 1;
-					if (root->ref_cows)
+					if (test_bit(BTRFS_ROOT_REF_COWS,
+						     &root->state))
 						inode_sub_bytes(inode, num_dec);
 				}
 			}
@@ -4120,10 +4146,9 @@ search_again:
 			    btrfs_file_extent_other_encoding(leaf, fi) == 0) {
 				u32 size = new_size - found_key.offset;
 
-				if (root->ref_cows) {
+				if (test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 					inode_sub_bytes(inode, item_end + 1 -
 							new_size);
-				}
 
 				/*
 				 * update the ram bytes to properly reflect
@@ -4133,7 +4158,8 @@ search_again:
 				size =
 				    btrfs_file_extent_calc_inline_size(size);
 				btrfs_truncate_item(root, path, size, 1);
-			} else if (root->ref_cows) {
+			} else if (test_bit(BTRFS_ROOT_REF_COWS,
+					    &root->state)) {
 				inode_sub_bytes(inode, item_end + 1 -
 						found_key.offset);
 			}
@@ -4155,8 +4181,9 @@ delete:
 		} else {
 			break;
 		}
-		if (found_extent && (root->ref_cows ||
-				     root == root->fs_info->tree_root)) {
+		if (found_extent &&
+		    (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
+		     root == root->fs_info->tree_root)) {
 			btrfs_set_path_blocking(path);
 			ret = btrfs_free_extent(trans, root, extent_start,
 						extent_num_bytes, 0,
@@ -5168,8 +5195,7 @@ static int btrfs_dentry_delete(const struct dentry *dentry)
 
 static void btrfs_dentry_release(struct dentry *dentry)
 {
-	if (dentry->d_fsdata)
-		kfree(dentry->d_fsdata);
+	kfree(dentry->d_fsdata);
 }
 
 static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
@@ -5553,6 +5579,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_inode_ref *ref;
 	struct btrfs_key key[2];
 	u32 sizes[2];
+	int nitems = name ? 2 : 1;
 	unsigned long ptr;
 	int ret;
 
@@ -5572,7 +5599,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	 */
 	inode->i_ino = objectid;
 
-	if (dir) {
+	if (dir && name) {
 		trace_btrfs_inode_request(dir);
 
 		ret = btrfs_set_inode_index(dir, index);
@@ -5581,6 +5608,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 			iput(inode);
 			return ERR_PTR(ret);
 		}
+	} else if (dir) {
+		*index = 0;
 	}
 	/*
 	 * index_cnt is ignored for everything but a dir,
@@ -5605,21 +5634,24 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
 	key[0].offset = 0;
 
-	/*
-	 * Start new inodes with an inode_ref. This is slightly more
-	 * efficient for small numbers of hard links since they will
-	 * be packed into one item. Extended refs will kick in if we
-	 * add more hard links than can fit in the ref item.
-	 */
-	key[1].objectid = objectid;
-	btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
-	key[1].offset = ref_objectid;
-
 	sizes[0] = sizeof(struct btrfs_inode_item);
-	sizes[1] = name_len + sizeof(*ref);
+
+	if (name) {
+		/*
+		 * Start new inodes with an inode_ref. This is slightly more
+		 * efficient for small numbers of hard links since they will
+		 * be packed into one item. Extended refs will kick in if we
+		 * add more hard links than can fit in the ref item.
+		 */
+		key[1].objectid = objectid;
+		btrfs_set_key_type(&key[1], BTRFS_INODE_REF_KEY);
+		key[1].offset = ref_objectid;
+
+		sizes[1] = name_len + sizeof(*ref);
+	}
 
 	path->leave_spinning = 1;
-	ret = btrfs_insert_empty_items(trans, root, path, key, sizes, 2);
+	ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems);
 	if (ret != 0)
 		goto fail;
 
@@ -5632,12 +5664,14 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 			     sizeof(*inode_item));
 	fill_inode_item(trans, path->nodes[0], inode_item, inode);
 
-	ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
-			     struct btrfs_inode_ref);
-	btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
-	btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
-	ptr = (unsigned long)(ref + 1);
-	write_extent_buffer(path->nodes[0], name, ptr, name_len);
+	if (name) {
+		ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
+				     struct btrfs_inode_ref);
+		btrfs_set_inode_ref_name_len(path->nodes[0], ref, name_len);
+		btrfs_set_inode_ref_index(path->nodes[0], ref, *index);
+		ptr = (unsigned long)(ref + 1);
+		write_extent_buffer(path->nodes[0], name, ptr, name_len);
+	}
 
 	btrfs_mark_buffer_dirty(path->nodes[0]);
 	btrfs_free_path(path);
@@ -5673,7 +5707,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 
 	return inode;
 fail:
-	if (dir)
+	if (dir && name)
 		BTRFS_I(dir)->index_cnt--;
 	btrfs_free_path(path);
 	iput(inode);
@@ -5958,6 +5992,15 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		err = btrfs_update_inode(trans, root, inode);
 		if (err)
 			goto fail;
+		if (inode->i_nlink == 1) {
+			/*
+			 * If new hard link count is 1, it's a file created
+			 * with open(2) O_TMPFILE flag.
+			 */
+			err = btrfs_orphan_del(trans, inode);
+			if (err)
+				goto fail;
+		}
 		d_instantiate(dentry, inode);
 		btrfs_log_new_name(trans, inode, NULL, parent);
 	}
@@ -6086,16 +6129,8 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size);
 	ret = btrfs_decompress(compress_type, tmp, page,
 			       extent_offset, inline_size, max_size);
-	if (ret) {
-		char *kaddr = kmap_atomic(page);
-		unsigned long copy_size = min_t(u64,
-				  PAGE_CACHE_SIZE - pg_offset,
-				  max_size - extent_offset);
-		memset(kaddr + pg_offset, 0, copy_size);
-		kunmap_atomic(kaddr);
-	}
 	kfree(tmp);
-	return 0;
+	return ret;
 }
 
 /*
@@ -6113,7 +6148,6 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 {
 	int ret;
 	int err = 0;
-	u64 bytenr;
 	u64 extent_start = 0;
 	u64 extent_end = 0;
 	u64 objectid = btrfs_ino(inode);
@@ -6127,7 +6161,7 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_trans_handle *trans = NULL;
-	int compress_type;
+	const bool new_inline = !page || create;
 
 again:
 	read_lock(&em_tree->lock);
@@ -6201,7 +6235,6 @@ again:
 
 	found_type = btrfs_file_extent_type(leaf, item);
 	extent_start = found_key.offset;
-	compress_type = btrfs_file_extent_compression(leaf, item);
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
 		extent_end = extent_start +
@@ -6236,32 +6269,10 @@ next:
 		goto not_found_em;
 	}
 
-	em->ram_bytes = btrfs_file_extent_ram_bytes(leaf, item);
+	btrfs_extent_item_to_extent_map(inode, path, item, new_inline, em);
+
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
-		em->start = extent_start;
-		em->len = extent_end - extent_start;
-		em->orig_start = extent_start -
-				 btrfs_file_extent_offset(leaf, item);
-		em->orig_block_len = btrfs_file_extent_disk_num_bytes(leaf,
-								      item);
-		bytenr = btrfs_file_extent_disk_bytenr(leaf, item);
-		if (bytenr == 0) {
-			em->block_start = EXTENT_MAP_HOLE;
-			goto insert;
-		}
-		if (compress_type != BTRFS_COMPRESS_NONE) {
-			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-			em->compress_type = compress_type;
-			em->block_start = bytenr;
-			em->block_len = em->orig_block_len;
-		} else {
-			bytenr += btrfs_file_extent_offset(leaf, item);
-			em->block_start = bytenr;
-			em->block_len = em->len;
-			if (found_type == BTRFS_FILE_EXTENT_PREALLOC)
-				set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
-		}
 		goto insert;
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		unsigned long ptr;
@@ -6270,12 +6281,8 @@ next:
 		size_t extent_offset;
 		size_t copy_size;
 
-		em->block_start = EXTENT_MAP_INLINE;
-		if (!page || create) {
-			em->start = extent_start;
-			em->len = extent_end - extent_start;
+		if (new_inline)
 			goto out;
-		}
 
 		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
 		extent_offset = page_offset(page) + pg_offset - extent_start;
@@ -6285,10 +6292,6 @@ next:
 		em->len = ALIGN(copy_size, root->sectorsize);
 		em->orig_block_len = em->len;
 		em->orig_start = em->start;
-		if (compress_type) {
-			set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-			em->compress_type = compress_type;
-		}
 		ptr = btrfs_file_extent_inline_start(item) + extent_offset;
 		if (create == 0 && !PageUptodate(page)) {
 			if (btrfs_file_extent_compression(leaf, item) !=
@@ -6296,7 +6299,10 @@ next:
 				ret = uncompress_inline(path, inode, page,
 							pg_offset,
 							extent_offset, item);
-				BUG_ON(ret); /* -ENOMEM */
+				if (ret) {
+					err = ret;
+					goto out;
+				}
 			} else {
 				map = kmap(page);
 				read_extent_buffer(leaf, map + pg_offset, ptr,
@@ -6332,8 +6338,6 @@ next:
 		set_extent_uptodate(io_tree, em->start,
 				    extent_map_end(em) - 1, NULL, GFP_NOFS);
 		goto insert;
-	} else {
-		WARN(1, KERN_ERR "btrfs unknown found_type %d\n", found_type);
 	}
 not_found:
 	em->start = start;
@@ -6550,21 +6554,21 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 
 	alloc_hint = get_extent_allocation_hint(inode, start, len);
 	ret = btrfs_reserve_extent(root, len, root->sectorsize, 0,
-				   alloc_hint, &ins, 1);
+				   alloc_hint, &ins, 1, 1);
 	if (ret)
 		return ERR_PTR(ret);
 
 	em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
 			      ins.offset, ins.offset, ins.offset, 0);
 	if (IS_ERR(em)) {
-		btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 		return em;
 	}
 
 	ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
 					   ins.offset, ins.offset, 0);
 	if (ret) {
-		btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 		free_extent_map(em);
 		return ERR_PTR(ret);
 	}
@@ -6717,6 +6721,76 @@ out:
 	return ret;
 }
 
+bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
+{
+	struct radix_tree_root *root = &inode->i_mapping->page_tree;
+	int found = false;
+	void **pagep = NULL;
+	struct page *page = NULL;
+	int start_idx;
+	int end_idx;
+
+	start_idx = start >> PAGE_CACHE_SHIFT;
+
+	/*
+	 * end is the last byte in the last page.  end == start is legal
+	 */
+	end_idx = end >> PAGE_CACHE_SHIFT;
+
+	rcu_read_lock();
+
+	/* Most of the code in this while loop is lifted from
+	 * find_get_page.  It's been modified to begin searching from a
+	 * page and return just the first page found in that range.  If the
+	 * found idx is less than or equal to the end idx then we know that
+	 * a page exists.  If no pages are found or if those pages are
+	 * outside of the range then we're fine (yay!) */
+	while (page == NULL &&
+	       radix_tree_gang_lookup_slot(root, &pagep, NULL, start_idx, 1)) {
+		page = radix_tree_deref_slot(pagep);
+		if (unlikely(!page))
+			break;
+
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				page = NULL;
+				continue;
+			}
+			/*
+			 * Otherwise, shmem/tmpfs must be storing a swap entry
+			 * here as an exceptional entry: so return it without
+			 * attempting to raise page count.
+			 */
+			page = NULL;
+			break; /* TODO: Is this relevant for this use case? */
+		}
+
+		if (!page_cache_get_speculative(page)) {
+			page = NULL;
+			continue;
+		}
+
+		/*
+		 * Has the page moved?
+		 * This is part of the lockless pagecache protocol. See
+		 * include/linux/pagemap.h for details.
+		 */
+		if (unlikely(page != *pagep)) {
+			page_cache_release(page);
+			page = NULL;
+		}
+	}
+
+	if (page) {
+		if (page->index <= end_idx)
+			found = true;
+		page_cache_release(page);
+	}
+
+	rcu_read_unlock();
+	return found;
+}
+
 static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 			      struct extent_state **cached_state, int writing)
 {
@@ -6741,10 +6815,9 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 		 * invalidate needs to happen so that reads after a write do not
 		 * get stale data.
 		 */
-		if (!ordered && (!writing ||
-		    !test_range_bit(&BTRFS_I(inode)->io_tree,
-				    lockstart, lockend, EXTENT_UPTODATE, 0,
-				    *cached_state)))
+		if (!ordered &&
+		    (!writing ||
+		     !btrfs_page_exists_in_range(inode, lockstart, lockend)))
 			break;
 
 		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
@@ -7383,7 +7456,7 @@ free_ordered:
 		if (!test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags) &&
 		    !test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags))
 			btrfs_free_reserved_extent(root, ordered->start,
-						   ordered->disk_len);
+						   ordered->disk_len, 1);
 		btrfs_put_ordered_extent(ordered);
 		btrfs_put_ordered_extent(ordered);
 	}
@@ -7391,39 +7464,30 @@ free_ordered:
 }
 
 static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *iocb,
-			const struct iovec *iov, loff_t offset,
-			unsigned long nr_segs)
+			const struct iov_iter *iter, loff_t offset)
 {
 	int seg;
 	int i;
-	size_t size;
-	unsigned long addr;
 	unsigned blocksize_mask = root->sectorsize - 1;
 	ssize_t retval = -EINVAL;
-	loff_t end = offset;
 
 	if (offset & blocksize_mask)
 		goto out;
 
-	/* Check the memory alignment.  Blocks cannot straddle pages */
-	for (seg = 0; seg < nr_segs; seg++) {
-		addr = (unsigned long)iov[seg].iov_base;
-		size = iov[seg].iov_len;
-		end += size;
-		if ((addr & blocksize_mask) || (size & blocksize_mask))
-			goto out;
-
-		/* If this is a write we don't need to check anymore */
-		if (rw & WRITE)
-			continue;
+	if (iov_iter_alignment(iter) & blocksize_mask)
+		goto out;
 
-		/*
-		 * Check to make sure we don't have duplicate iov_base's in this
-		 * iovec, if so return EINVAL, otherwise we'll get csum errors
-		 * when reading back.
-		 */
-		for (i = seg + 1; i < nr_segs; i++) {
-			if (iov[seg].iov_base == iov[i].iov_base)
+	/* If this is a write we don't need to check anymore */
+	if (rw & WRITE)
+		return 0;
+	/*
+	 * Check to make sure we don't have duplicate iov_base's in this
+	 * iovec, if so return EINVAL, otherwise we'll get csum errors
+	 * when reading back.
+	 */
+	for (seg = 0; seg < iter->nr_segs; seg++) {
+		for (i = seg + 1; i < iter->nr_segs; i++) {
+			if (iter->iov[seg].iov_base == iter->iov[i].iov_base)
 				goto out;
 		}
 	}
@@ -7433,8 +7497,7 @@ out:
 }
 
 static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
-			const struct iovec *iov, loff_t offset,
-			unsigned long nr_segs)
+			struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -7444,8 +7507,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 	bool relock = false;
 	ssize_t ret;
 
-	if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov,
-			    offset, nr_segs))
+	if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iter, offset))
 		return 0;
 
 	atomic_inc(&inode->i_dio_count);
@@ -7457,7 +7519,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 	 * we need to flush the dirty pages again to make absolutely sure
 	 * that any outstanding dirty pages are on disk.
 	 */
-	count = iov_length(iov, nr_segs);
+	count = iov_iter_count(iter);
 	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
 		     &BTRFS_I(inode)->runtime_flags))
 		filemap_fdatawrite_range(inode->i_mapping, offset, count);
@@ -7484,7 +7546,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 
 	ret = __blockdev_direct_IO(rw, iocb, inode,
 			BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
-			iov, offset, nr_segs, btrfs_get_blocks_direct, NULL,
+			iter, offset, btrfs_get_blocks_direct, NULL,
 			btrfs_submit_direct, flags);
 	if (rw & WRITE) {
 		if (ret < 0 && ret != -EIOCBQUEUED)
@@ -7992,7 +8054,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 	err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
 	if (err)
 		btrfs_err(new_root->fs_info,
-			  "error inheriting subvolume %llu properties: %d\n",
+			  "error inheriting subvolume %llu properties: %d",
 			  new_root->root_key.objectid, err);
 
 	err = btrfs_update_inode(trans, new_root, inode);
@@ -8311,7 +8373,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	BTRFS_I(old_inode)->dir_index = 0ULL;
 	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		/* force full log commit if subvolume involved. */
-		root->fs_info->last_trans_log_full_commit = trans->transid;
+		btrfs_set_log_full_commit(root->fs_info, trans);
 	} else {
 		ret = btrfs_insert_inode_ref(trans, dest,
 					     new_dentry->d_name.name,
@@ -8765,7 +8827,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		cur_bytes = min(num_bytes, 256ULL * 1024 * 1024);
 		cur_bytes = max(cur_bytes, min_size);
 		ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0,
-					   *alloc_hint, &ins, 1);
+					   *alloc_hint, &ins, 1, 0);
 		if (ret) {
 			if (own_trans)
 				btrfs_end_transaction(trans, root);
@@ -8779,7 +8841,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 						  BTRFS_FILE_EXTENT_PREALLOC);
 		if (ret) {
 			btrfs_free_reserved_extent(root, ins.objectid,
-						   ins.offset);
+						   ins.offset, 0);
 			btrfs_abort_transaction(trans, root, ret);
 			if (own_trans)
 				btrfs_end_transaction(trans, root);
@@ -8889,6 +8951,66 @@ static int btrfs_permission(struct inode *inode, int mask)
 	return generic_permission(inode, mask);
 }
 
+static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *root = BTRFS_I(dir)->root;
+	struct inode *inode = NULL;
+	u64 objectid;
+	u64 index;
+	int ret = 0;
+
+	/*
+	 * 5 units required for adding orphan entry
+	 */
+	trans = btrfs_start_transaction(root, 5);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	ret = btrfs_find_free_ino(root, &objectid);
+	if (ret)
+		goto out;
+
+	inode = btrfs_new_inode(trans, root, dir, NULL, 0,
+				btrfs_ino(dir), objectid, mode, &index);
+	if (IS_ERR(inode)) {
+		ret = PTR_ERR(inode);
+		inode = NULL;
+		goto out;
+	}
+
+	ret = btrfs_init_inode_security(trans, inode, dir, NULL);
+	if (ret)
+		goto out;
+
+	ret = btrfs_update_inode(trans, root, inode);
+	if (ret)
+		goto out;
+
+	inode->i_fop = &btrfs_file_operations;
+	inode->i_op = &btrfs_file_inode_operations;
+
+	inode->i_mapping->a_ops = &btrfs_aops;
+	inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
+	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+
+	ret = btrfs_orphan_add(trans, inode);
+	if (ret)
+		goto out;
+
+	d_tmpfile(dentry, inode);
+	mark_inode_dirty(inode);
+
+out:
+	btrfs_end_transaction(trans, root);
+	if (ret)
+		iput(inode);
+	btrfs_balance_delayed_items(root);
+	btrfs_btree_balance_dirty(root);
+
+	return ret;
+}
+
 static const struct inode_operations btrfs_dir_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.lookup		= btrfs_lookup,
@@ -8909,6 +9031,7 @@ static const struct inode_operations btrfs_dir_inode_operations = {
 	.get_acl	= btrfs_get_acl,
 	.set_acl	= btrfs_set_acl,
 	.update_time	= btrfs_update_time,
+	.tmpfile        = btrfs_tmpfile,
 };
 static const struct inode_operations btrfs_dir_ro_inode_operations = {
 	.lookup		= btrfs_lookup,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 3f52bb7a58d..47aceb494d1 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -58,6 +58,7 @@
 #include "dev-replace.h"
 #include "props.h"
 #include "sysfs.h"
+#include "qgroup.h"
 
 #ifdef CONFIG_64BIT
 /* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
@@ -135,19 +136,22 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
 void btrfs_update_iflags(struct inode *inode)
 {
 	struct btrfs_inode *ip = BTRFS_I(inode);
-
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	unsigned int new_fl = 0;
 
 	if (ip->flags & BTRFS_INODE_SYNC)
-		inode->i_flags |= S_SYNC;
+		new_fl |= S_SYNC;
 	if (ip->flags & BTRFS_INODE_IMMUTABLE)
-		inode->i_flags |= S_IMMUTABLE;
+		new_fl |= S_IMMUTABLE;
 	if (ip->flags & BTRFS_INODE_APPEND)
-		inode->i_flags |= S_APPEND;
+		new_fl |= S_APPEND;
 	if (ip->flags & BTRFS_INODE_NOATIME)
-		inode->i_flags |= S_NOATIME;
+		new_fl |= S_NOATIME;
 	if (ip->flags & BTRFS_INODE_DIRSYNC)
-		inode->i_flags |= S_DIRSYNC;
+		new_fl |= S_DIRSYNC;
+
+	set_mask_bits(&inode->i_flags,
+		      S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | S_DIRSYNC,
+		      new_fl);
 }
 
 /*
@@ -638,7 +642,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	struct btrfs_trans_handle *trans;
 	int ret;
 
-	if (!root->ref_cows)
+	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		return -EINVAL;
 
 	atomic_inc(&root->will_be_snapshoted);
@@ -711,6 +715,35 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (ret)
 		goto fail;
 
+	/*
+	 * If orphan cleanup did remove any orphans, it means the tree was
+	 * modified and therefore the commit root is not the same as the
+	 * current root anymore. This is a problem, because send uses the
+	 * commit root and therefore can see inode items that don't exist
+	 * in the current root anymore, and for example make calls to
+	 * btrfs_iget, which will do tree lookups based on the current root
+	 * and not on the commit root. Those lookups will fail, returning a
+	 * -ESTALE error, and making send fail with that error. So make sure
+	 * a send does not see any orphans we have just removed, and that it
+	 * will see the same inodes regardless of whether a transaction
+	 * commit happened before it started (meaning that the commit root
+	 * will be the same as the current root) or not.
+	 */
+	if (readonly && pending_snapshot->snap->node !=
+	    pending_snapshot->snap->commit_root) {
+		trans = btrfs_join_transaction(pending_snapshot->snap);
+		if (IS_ERR(trans) && PTR_ERR(trans) != -ENOENT) {
+			ret = PTR_ERR(trans);
+			goto fail;
+		}
+		if (!IS_ERR(trans)) {
+			ret = btrfs_commit_transaction(trans,
+						       pending_snapshot->snap);
+			if (ret)
+				goto fail;
+		}
+	}
+
 	inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
@@ -1502,11 +1535,12 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 	sizestr = vol_args->name;
 	devstr = strchr(sizestr, ':');
 	if (devstr) {
-		char *end;
 		sizestr = devstr + 1;
 		*devstr = '\0';
 		devstr = vol_args->name;
-		devid = simple_strtoull(devstr, &end, 10);
+		ret = kstrtoull(devstr, 10, &devid);
+		if (ret)
+			goto out_free;
 		if (!devid) {
 			ret = -EINVAL;
 			goto out_free;
@@ -1562,7 +1596,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		new_size = old_size - new_size;
 	} else if (mod > 0) {
 		if (new_size > ULLONG_MAX - old_size) {
-			ret = -EINVAL;
+			ret = -ERANGE;
 			goto out_free;
 		}
 		new_size = old_size + new_size;
@@ -1926,7 +1960,8 @@ static noinline int copy_to_sk(struct btrfs_root *root,
 			       struct btrfs_path *path,
 			       struct btrfs_key *key,
 			       struct btrfs_ioctl_search_key *sk,
-			       char *buf,
+			       size_t *buf_size,
+			       char __user *ubuf,
 			       unsigned long *sk_offset,
 			       int *num_found)
 {
@@ -1958,13 +1993,25 @@ static noinline int copy_to_sk(struct btrfs_root *root,
 		if (!key_in_sk(key, sk))
 			continue;
 
-		if (sizeof(sh) + item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
+		if (sizeof(sh) + item_len > *buf_size) {
+			if (*num_found) {
+				ret = 1;
+				goto out;
+			}
+
+			/*
+			 * return one empty item back for v1, which does not
+			 * handle -EOVERFLOW
+			 */
+
+			*buf_size = sizeof(sh) + item_len;
 			item_len = 0;
+			ret = -EOVERFLOW;
+		}
 
-		if (sizeof(sh) + item_len + *sk_offset >
-		    BTRFS_SEARCH_ARGS_BUFSIZE) {
+		if (sizeof(sh) + item_len + *sk_offset > *buf_size) {
 			ret = 1;
-			goto overflow;
+			goto out;
 		}
 
 		sh.objectid = key->objectid;
@@ -1974,20 +2021,33 @@ static noinline int copy_to_sk(struct btrfs_root *root,
 		sh.transid = found_transid;
 
 		/* copy search result header */
-		memcpy(buf + *sk_offset, &sh, sizeof(sh));
+		if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) {
+			ret = -EFAULT;
+			goto out;
+		}
+
 		*sk_offset += sizeof(sh);
 
 		if (item_len) {
-			char *p = buf + *sk_offset;
+			char __user *up = ubuf + *sk_offset;
 			/* copy the item */
-			read_extent_buffer(leaf, p,
-					   item_off, item_len);
+			if (read_extent_buffer_to_user(leaf, up,
+						       item_off, item_len)) {
+				ret = -EFAULT;
+				goto out;
+			}
+
 			*sk_offset += item_len;
 		}
 		(*num_found)++;
 
-		if (*num_found >= sk->nr_items)
-			break;
+		if (ret) /* -EOVERFLOW from above */
+			goto out;
+
+		if (*num_found >= sk->nr_items) {
+			ret = 1;
+			goto out;
+		}
 	}
 advance_key:
 	ret = 0;
@@ -2002,22 +2062,37 @@ advance_key:
 		key->objectid++;
 	} else
 		ret = 1;
-overflow:
+out:
+	/*
+	 *  0: all items from this leaf copied, continue with next
+	 *  1: * more items can be copied, but unused buffer is too small
+	 *     * all items were found
+	 *     Either way, it will stops the loop which iterates to the next
+	 *     leaf
+	 *  -EOVERFLOW: item was to large for buffer
+	 *  -EFAULT: could not copy extent buffer back to userspace
+	 */
 	return ret;
 }
 
 static noinline int search_ioctl(struct inode *inode,
-				 struct btrfs_ioctl_search_args *args)
+				 struct btrfs_ioctl_search_key *sk,
+				 size_t *buf_size,
+				 char __user *ubuf)
 {
 	struct btrfs_root *root;
 	struct btrfs_key key;
 	struct btrfs_path *path;
-	struct btrfs_ioctl_search_key *sk = &args->key;
 	struct btrfs_fs_info *info = BTRFS_I(inode)->root->fs_info;
 	int ret;
 	int num_found = 0;
 	unsigned long sk_offset = 0;
 
+	if (*buf_size < sizeof(struct btrfs_ioctl_search_header)) {
+		*buf_size = sizeof(struct btrfs_ioctl_search_header);
+		return -EOVERFLOW;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -2051,14 +2126,15 @@ static noinline int search_ioctl(struct inode *inode,
 				ret = 0;
 			goto err;
 		}
-		ret = copy_to_sk(root, path, &key, sk, args->buf,
+		ret = copy_to_sk(root, path, &key, sk, buf_size, ubuf,
 				 &sk_offset, &num_found);
 		btrfs_release_path(path);
-		if (ret || num_found >= sk->nr_items)
+		if (ret)
 			break;
 
 	}
-	ret = 0;
+	if (ret > 0)
+		ret = 0;
 err:
 	sk->nr_items = num_found;
 	btrfs_free_path(path);
@@ -2068,22 +2144,73 @@ err:
 static noinline int btrfs_ioctl_tree_search(struct file *file,
 					   void __user *argp)
 {
-	 struct btrfs_ioctl_search_args *args;
-	 struct inode *inode;
-	 int ret;
+	struct btrfs_ioctl_search_args __user *uargs;
+	struct btrfs_ioctl_search_key sk;
+	struct inode *inode;
+	int ret;
+	size_t buf_size;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	args = memdup_user(argp, sizeof(*args));
-	if (IS_ERR(args))
-		return PTR_ERR(args);
+	uargs = (struct btrfs_ioctl_search_args __user *)argp;
+
+	if (copy_from_user(&sk, &uargs->key, sizeof(sk)))
+		return -EFAULT;
+
+	buf_size = sizeof(uargs->buf);
 
 	inode = file_inode(file);
-	ret = search_ioctl(inode, args);
-	if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
+	ret = search_ioctl(inode, &sk, &buf_size, uargs->buf);
+
+	/*
+	 * In the origin implementation an overflow is handled by returning a
+	 * search header with a len of zero, so reset ret.
+	 */
+	if (ret == -EOVERFLOW)
+		ret = 0;
+
+	if (ret == 0 && copy_to_user(&uargs->key, &sk, sizeof(sk)))
 		ret = -EFAULT;
-	kfree(args);
+	return ret;
+}
+
+static noinline int btrfs_ioctl_tree_search_v2(struct file *file,
+					       void __user *argp)
+{
+	struct btrfs_ioctl_search_args_v2 __user *uarg;
+	struct btrfs_ioctl_search_args_v2 args;
+	struct inode *inode;
+	int ret;
+	size_t buf_size;
+	const size_t buf_limit = 16 * 1024 * 1024;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* copy search header and buffer size */
+	uarg = (struct btrfs_ioctl_search_args_v2 __user *)argp;
+	if (copy_from_user(&args, uarg, sizeof(args)))
+		return -EFAULT;
+
+	buf_size = args.buf_size;
+
+	if (buf_size < sizeof(struct btrfs_ioctl_search_header))
+		return -EOVERFLOW;
+
+	/* limit result size to 16MB */
+	if (buf_size > buf_limit)
+		buf_size = buf_limit;
+
+	inode = file_inode(file);
+	ret = search_ioctl(inode, &args.key, &buf_size,
+			   (char *)(&uarg->buf[0]));
+	if (ret == 0 && copy_to_user(&uarg->key, &args.key, sizeof(args.key)))
+		ret = -EFAULT;
+	else if (ret == -EOVERFLOW &&
+		copy_to_user(&uarg->buf_size, &buf_size, sizeof(buf_size)))
+		ret = -EFAULT;
+
 	return ret;
 }
 
@@ -2219,6 +2346,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	struct btrfs_ioctl_vol_args *vol_args;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_block_rsv block_rsv;
+	u64 root_flags;
 	u64 qgroup_reserved;
 	int namelen;
 	int ret;
@@ -2240,6 +2368,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	if (err)
 		goto out;
 
+
 	err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
 	if (err == -EINTR)
 		goto out_drop_write;
@@ -2301,6 +2430,27 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	}
 
 	mutex_lock(&inode->i_mutex);
+
+	/*
+	 * Don't allow to delete a subvolume with send in progress. This is
+	 * inside the i_mutex so the error handling that has to drop the bit
+	 * again is not run concurrently.
+	 */
+	spin_lock(&dest->root_item_lock);
+	root_flags = btrfs_root_flags(&dest->root_item);
+	if (dest->send_in_progress == 0) {
+		btrfs_set_root_flags(&dest->root_item,
+				root_flags | BTRFS_ROOT_SUBVOL_DEAD);
+		spin_unlock(&dest->root_item_lock);
+	} else {
+		spin_unlock(&dest->root_item_lock);
+		btrfs_warn(root->fs_info,
+			"Attempt to delete subvolume %llu during send",
+			dest->root_key.objectid);
+		err = -EPERM;
+		goto out_dput;
+	}
+
 	err = d_invalidate(dentry);
 	if (err)
 		goto out_unlock;
@@ -2346,7 +2496,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	dest->root_item.drop_level = 0;
 	btrfs_set_root_refs(&dest->root_item, 0);
 
-	if (!xchg(&dest->orphan_item_inserted, 1)) {
+	if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
 		ret = btrfs_insert_orphan_item(trans,
 					root->fs_info->tree_root,
 					dest->root_key.objectid);
@@ -2389,11 +2539,19 @@ out_release:
 out_up_write:
 	up_write(&root->fs_info->subvol_sem);
 out_unlock:
+	if (err) {
+		spin_lock(&dest->root_item_lock);
+		root_flags = btrfs_root_flags(&dest->root_item);
+		btrfs_set_root_flags(&dest->root_item,
+				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
+		spin_unlock(&dest->root_item_lock);
+	}
 	mutex_unlock(&inode->i_mutex);
 	if (!err) {
 		shrink_dcache_sb(root->fs_info->sb);
 		btrfs_invalidate_inodes(dest);
 		d_delete(dentry);
+		ASSERT(dest->send_in_progress == 0);
 
 		/* the last ref */
 		if (dest->cache_inode) {
@@ -2557,9 +2715,6 @@ static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg)
 	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
 	int ret = 0;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
 	fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL);
 	if (!fi_args)
 		return -ENOMEM;
@@ -2574,6 +2729,10 @@ static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg)
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
+	fi_args->nodesize = root->fs_info->super_copy->nodesize;
+	fi_args->sectorsize = root->fs_info->super_copy->sectorsize;
+	fi_args->clone_alignment = root->fs_info->super_copy->sectorsize;
+
 	if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
 		ret = -EFAULT;
 
@@ -2589,9 +2748,6 @@ static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg)
 	int ret = 0;
 	char *s_uuid = NULL;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
 	di_args = memdup_user(arg, sizeof(*di_args));
 	if (IS_ERR(di_args))
 		return PTR_ERR(di_args);
@@ -2669,10 +2825,15 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 		lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
 		ordered = btrfs_lookup_first_ordered_extent(inode,
 							    off + len - 1);
-		if (!ordered &&
+		if ((!ordered ||
+		     ordered->file_offset + ordered->len <= off ||
+		     ordered->file_offset >= off + len) &&
 		    !test_range_bit(&BTRFS_I(inode)->io_tree, off,
-				    off + len - 1, EXTENT_DELALLOC, 0, NULL))
+				    off + len - 1, EXTENT_DELALLOC, 0, NULL)) {
+			if (ordered)
+				btrfs_put_ordered_extent(ordered);
 			break;
+		}
 		unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
@@ -2912,6 +3073,129 @@ out:
 	return ret;
 }
 
+/* Helper to check and see if this root currently has a ref on the given disk
+ * bytenr.  If it does then we need to update the quota for this root.  This
+ * doesn't do anything if quotas aren't enabled.
+ */
+static int check_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		     u64 disko)
+{
+	struct seq_list tree_mod_seq_elem = {};
+	struct ulist *roots;
+	struct ulist_iterator uiter;
+	struct ulist_node *root_node = NULL;
+	int ret;
+
+	if (!root->fs_info->quota_enabled)
+		return 1;
+
+	btrfs_get_tree_mod_seq(root->fs_info, &tree_mod_seq_elem);
+	ret = btrfs_find_all_roots(trans, root->fs_info, disko,
+				   tree_mod_seq_elem.seq, &roots);
+	if (ret < 0)
+		goto out;
+	ret = 0;
+	ULIST_ITER_INIT(&uiter);
+	while ((root_node = ulist_next(roots, &uiter))) {
+		if (root_node->val == root->objectid) {
+			ret = 1;
+			break;
+		}
+	}
+	ulist_free(roots);
+out:
+	btrfs_put_tree_mod_seq(root->fs_info, &tree_mod_seq_elem);
+	return ret;
+}
+
+static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
+				     struct inode *inode,
+				     u64 endoff,
+				     const u64 destoff,
+				     const u64 olen)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	int ret;
+
+	inode_inc_iversion(inode);
+	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	/*
+	 * We round up to the block size at eof when determining which
+	 * extents to clone above, but shouldn't round up the file size.
+	 */
+	if (endoff > destoff + olen)
+		endoff = destoff + olen;
+	if (endoff > inode->i_size)
+		btrfs_i_size_write(inode, endoff);
+
+	ret = btrfs_update_inode(trans, root, inode);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		btrfs_end_transaction(trans, root);
+		goto out;
+	}
+	ret = btrfs_end_transaction(trans, root);
+out:
+	return ret;
+}
+
+static void clone_update_extent_map(struct inode *inode,
+				    const struct btrfs_trans_handle *trans,
+				    const struct btrfs_path *path,
+				    const u64 hole_offset,
+				    const u64 hole_len)
+{
+	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map *em;
+	int ret;
+
+	em = alloc_extent_map();
+	if (!em) {
+		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+			&BTRFS_I(inode)->runtime_flags);
+		return;
+	}
+
+	if (path) {
+		struct btrfs_file_extent_item *fi;
+
+		fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				    struct btrfs_file_extent_item);
+		btrfs_extent_item_to_extent_map(inode, path, fi, false, em);
+		em->generation = -1;
+		if (btrfs_file_extent_type(path->nodes[0], fi) ==
+		    BTRFS_FILE_EXTENT_INLINE)
+			set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+				&BTRFS_I(inode)->runtime_flags);
+	} else {
+		em->start = hole_offset;
+		em->len = hole_len;
+		em->ram_bytes = em->len;
+		em->orig_start = hole_offset;
+		em->block_start = EXTENT_MAP_HOLE;
+		em->block_len = 0;
+		em->orig_block_len = 0;
+		em->compress_type = BTRFS_COMPRESS_NONE;
+		em->generation = trans->transid;
+	}
+
+	while (1) {
+		write_lock(&em_tree->lock);
+		ret = add_extent_mapping(em_tree, em, 1);
+		write_unlock(&em_tree->lock);
+		if (ret != -EEXIST) {
+			free_extent_map(em);
+			break;
+		}
+		btrfs_drop_extent_cache(inode, em->start,
+					em->start + em->len - 1, 0);
+	}
+
+	if (unlikely(ret))
+		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+			&BTRFS_I(inode)->runtime_flags);
+}
+
 /**
  * btrfs_clone() - clone a range from inode file to another
  *
@@ -2924,7 +3208,8 @@ out:
  * @destoff: Offset within @inode to start clone
  */
 static int btrfs_clone(struct inode *src, struct inode *inode,
-		       u64 off, u64 olen, u64 olen_aligned, u64 destoff)
+		       const u64 off, const u64 olen, const u64 olen_aligned,
+		       const u64 destoff)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path = NULL;
@@ -2935,7 +3220,10 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	u32 nritems;
 	int slot;
 	int ret;
-	u64 len = olen_aligned;
+	int no_quota;
+	const u64 len = olen_aligned;
+	u64 last_disko = 0;
+	u64 last_dest_end = destoff;
 
 	ret = -ENOMEM;
 	buf = vmalloc(btrfs_level_size(root, 0));
@@ -2952,7 +3240,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	/* clone data */
 	key.objectid = btrfs_ino(src);
 	key.type = BTRFS_EXTENT_DATA_KEY;
-	key.offset = 0;
+	key.offset = off;
 
 	while (1) {
 		/*
@@ -2964,9 +3252,21 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 				0, 0);
 		if (ret < 0)
 			goto out;
+		/*
+		 * First search, if no extent item that starts at offset off was
+		 * found but the previous item is an extent item, it's possible
+		 * it might overlap our target range, therefore process it.
+		 */
+		if (key.offset == off && ret > 0 && path->slots[0] > 0) {
+			btrfs_item_key_to_cpu(path->nodes[0], &key,
+					      path->slots[0] - 1);
+			if (key.type == BTRFS_EXTENT_DATA_KEY)
+				path->slots[0]--;
+		}
 
 		nritems = btrfs_header_nritems(path->nodes[0]);
 process_slot:
+		no_quota = 1;
 		if (path->slots[0] >= nritems) {
 			ret = btrfs_next_leaf(BTRFS_I(src)->root, path);
 			if (ret < 0)
@@ -2991,7 +3291,7 @@ process_slot:
 			u64 disko = 0, diskl = 0;
 			u64 datao = 0, datal = 0;
 			u8 comp;
-			u64 endoff;
+			u64 drop_start;
 
 			extent = btrfs_item_ptr(leaf, slot,
 						struct btrfs_file_extent_item);
@@ -3012,10 +3312,16 @@ process_slot:
 								    extent);
 			}
 
-			if (key.offset + datal <= off ||
-			    key.offset >= off + len - 1) {
+			/*
+			 * The first search might have left us at an extent
+			 * item that ends before our target range's start, can
+			 * happen if we have holes and NO_HOLES feature enabled.
+			 */
+			if (key.offset + datal <= off) {
 				path->slots[0]++;
 				goto process_slot;
+			} else if (key.offset >= off + len) {
+				break;
 			}
 
 			size = btrfs_item_size_nr(leaf, slot);
@@ -3034,6 +3340,18 @@ process_slot:
 				new_key.offset = destoff;
 
 			/*
+			 * Deal with a hole that doesn't have an extent item
+			 * that represents it (NO_HOLES feature enabled).
+			 * This hole is either in the middle of the cloning
+			 * range or at the beginning (fully overlaps it or
+			 * partially overlaps it).
+			 */
+			if (new_key.offset != last_dest_end)
+				drop_start = last_dest_end;
+			else
+				drop_start = new_key.offset;
+
+			/*
 			 * 1 - adjusting old extent (we may have to split it)
 			 * 1 - add new extent
 			 * 1 - inode update
@@ -3051,18 +3369,18 @@ process_slot:
 				 * | ------------- extent ------------- |
 				 */
 
-				/* substract range b */
+				/* subtract range b */
 				if (key.offset + datal > off + len)
 					datal = off + len - key.offset;
 
-				/* substract range a */
+				/* subtract range a */
 				if (off > key.offset) {
 					datao += off - key.offset;
 					datal -= off - key.offset;
 				}
 
 				ret = btrfs_drop_extents(trans, root, inode,
-							 new_key.offset,
+							 drop_start,
 							 new_key.offset + datal,
 							 1);
 				if (ret) {
@@ -3099,6 +3417,28 @@ process_slot:
 							     datao);
 				btrfs_set_file_extent_num_bytes(leaf, extent,
 								datal);
+
+				/*
+				 * We need to look up the roots that point at
+				 * this bytenr and see if the new root does.  If
+				 * it does not we need to make sure we update
+				 * quotas appropriately.
+				 */
+				if (disko && root != BTRFS_I(src)->root &&
+				    disko != last_disko) {
+					no_quota = check_ref(trans, root,
+							     disko);
+					if (no_quota < 0) {
+						btrfs_abort_transaction(trans,
+									root,
+									ret);
+						btrfs_end_transaction(trans,
+								      root);
+						ret = no_quota;
+						goto out;
+					}
+				}
+
 				if (disko) {
 					inode_add_bytes(inode, datal);
 					ret = btrfs_inc_extent_ref(trans, root,
@@ -3106,7 +3446,7 @@ process_slot:
 							root->root_key.objectid,
 							btrfs_ino(inode),
 							new_key.offset - datao,
-							0);
+							no_quota);
 					if (ret) {
 						btrfs_abort_transaction(trans,
 									root,
@@ -3141,7 +3481,7 @@ process_slot:
 				aligned_end = ALIGN(new_key.offset + datal,
 						    root->sectorsize);
 				ret = btrfs_drop_extents(trans, root, inode,
-							 new_key.offset,
+							 drop_start,
 							 aligned_end,
 							 1);
 				if (ret) {
@@ -3176,38 +3516,62 @@ process_slot:
 				inode_add_bytes(inode, datal);
 			}
 
+			/* If we have an implicit hole (NO_HOLES feature). */
+			if (drop_start < new_key.offset)
+				clone_update_extent_map(inode, trans,
+						NULL, drop_start,
+						new_key.offset - drop_start);
+
+			clone_update_extent_map(inode, trans, path, 0, 0);
+
 			btrfs_mark_buffer_dirty(leaf);
 			btrfs_release_path(path);
 
-			inode_inc_iversion(inode);
-			inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-
-			/*
-			 * we round up to the block size at eof when
-			 * determining which extents to clone above,
-			 * but shouldn't round up the file size
-			 */
-			endoff = new_key.offset + datal;
-			if (endoff > destoff+olen)
-				endoff = destoff+olen;
-			if (endoff > inode->i_size)
-				btrfs_i_size_write(inode, endoff);
-
-			ret = btrfs_update_inode(trans, root, inode);
-			if (ret) {
-				btrfs_abort_transaction(trans, root, ret);
-				btrfs_end_transaction(trans, root);
+			last_dest_end = new_key.offset + datal;
+			ret = clone_finish_inode_update(trans, inode,
+							last_dest_end,
+							destoff, olen);
+			if (ret)
 				goto out;
-			}
-			ret = btrfs_end_transaction(trans, root);
+			if (new_key.offset + datal >= destoff + len)
+				break;
 		}
 		btrfs_release_path(path);
 		key.offset++;
 	}
 	ret = 0;
 
+	if (last_dest_end < destoff + len) {
+		/*
+		 * We have an implicit hole (NO_HOLES feature is enabled) that
+		 * fully or partially overlaps our cloning range at its end.
+		 */
+		btrfs_release_path(path);
+
+		/*
+		 * 1 - remove extent(s)
+		 * 1 - inode update
+		 */
+		trans = btrfs_start_transaction(root, 2);
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+			goto out;
+		}
+		ret = btrfs_drop_extents(trans, root, inode,
+					 last_dest_end, destoff + len, 1);
+		if (ret) {
+			if (ret != -EOPNOTSUPP)
+				btrfs_abort_transaction(trans, root, ret);
+			btrfs_end_transaction(trans, root);
+			goto out;
+		}
+		clone_update_extent_map(inode, trans, NULL, last_dest_end,
+					destoff + len - last_dest_end);
+		ret = clone_finish_inode_update(trans, inode, destoff + len,
+						destoff, olen);
+	}
+
 out:
-	btrfs_release_path(path);
 	btrfs_free_path(path);
 	vfree(buf);
 	return ret;
@@ -3319,15 +3683,41 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
 			goto out_unlock;
 	}
 
-	/* truncate page cache pages from target inode range */
-	truncate_inode_pages_range(&inode->i_data, destoff,
-				   PAGE_CACHE_ALIGN(destoff + len) - 1);
+	/*
+	 * Lock the target range too. Right after we replace the file extent
+	 * items in the fs tree (which now point to the cloned data), we might
+	 * have a worker replace them with extent items relative to a write
+	 * operation that was issued before this clone operation (i.e. confront
+	 * with inode.c:btrfs_finish_ordered_io).
+	 */
+	if (same_inode) {
+		u64 lock_start = min_t(u64, off, destoff);
+		u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
 
-	lock_extent_range(src, off, len);
+		lock_extent_range(src, lock_start, lock_len);
+	} else {
+		lock_extent_range(src, off, len);
+		lock_extent_range(inode, destoff, len);
+	}
 
 	ret = btrfs_clone(src, inode, off, olen, len, destoff);
 
-	unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
+	if (same_inode) {
+		u64 lock_start = min_t(u64, off, destoff);
+		u64 lock_end = max_t(u64, off, destoff) + len - 1;
+
+		unlock_extent(&BTRFS_I(src)->io_tree, lock_start, lock_end);
+	} else {
+		unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
+		unlock_extent(&BTRFS_I(inode)->io_tree, destoff,
+			      destoff + len - 1);
+	}
+	/*
+	 * Truncate page cache pages so that future reads will see the cloned
+	 * data immediately and not the previous data.
+	 */
+	truncate_inode_pages_range(&inode->i_data, destoff,
+				   PAGE_CACHE_ALIGN(destoff + len) - 1);
 out_unlock:
 	if (!same_inode) {
 		if (inode < src) {
@@ -4902,6 +5292,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_trans_end(file);
 	case BTRFS_IOC_TREE_SEARCH:
 		return btrfs_ioctl_tree_search(file, argp);
+	case BTRFS_IOC_TREE_SEARCH_V2:
+		return btrfs_ioctl_tree_search_v2(file, argp);
 	case BTRFS_IOC_INO_LOOKUP:
 		return btrfs_ioctl_ino_lookup(file, argp);
 	case BTRFS_IOC_INO_PATHS:
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 01277b8f237..5665d214924 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -33,14 +33,14 @@ static void btrfs_assert_tree_read_locked(struct extent_buffer *eb);
  */
 void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
 {
-	if (eb->lock_nested) {
-		read_lock(&eb->lock);
-		if (eb->lock_nested && current->pid == eb->lock_owner) {
-			read_unlock(&eb->lock);
-			return;
-		}
-		read_unlock(&eb->lock);
-	}
+	/*
+	 * no lock is required.  The lock owner may change if
+	 * we have a read lock, but it won't change to or away
+	 * from us.  If we have the write lock, we are the owner
+	 * and it'll never change.
+	 */
+	if (eb->lock_nested && current->pid == eb->lock_owner)
+		return;
 	if (rw == BTRFS_WRITE_LOCK) {
 		if (atomic_read(&eb->blocking_writers) == 0) {
 			WARN_ON(atomic_read(&eb->spinning_writers) != 1);
@@ -65,14 +65,15 @@ void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
  */
 void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
 {
-	if (eb->lock_nested) {
-		read_lock(&eb->lock);
-		if (eb->lock_nested && current->pid == eb->lock_owner) {
-			read_unlock(&eb->lock);
-			return;
-		}
-		read_unlock(&eb->lock);
-	}
+	/*
+	 * no lock is required.  The lock owner may change if
+	 * we have a read lock, but it won't change to or away
+	 * from us.  If we have the write lock, we are the owner
+	 * and it'll never change.
+	 */
+	if (eb->lock_nested && current->pid == eb->lock_owner)
+		return;
+
 	if (rw == BTRFS_WRITE_LOCK_BLOCKING) {
 		BUG_ON(atomic_read(&eb->blocking_writers) != 1);
 		write_lock(&eb->lock);
@@ -99,6 +100,9 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
 void btrfs_tree_read_lock(struct extent_buffer *eb)
 {
 again:
+	BUG_ON(!atomic_read(&eb->blocking_writers) &&
+	       current->pid == eb->lock_owner);
+
 	read_lock(&eb->lock);
 	if (atomic_read(&eb->blocking_writers) &&
 	    current->pid == eb->lock_owner) {
@@ -132,7 +136,9 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb)
 	if (atomic_read(&eb->blocking_writers))
 		return 0;
 
-	read_lock(&eb->lock);
+	if (!read_trylock(&eb->lock))
+		return 0;
+
 	if (atomic_read(&eb->blocking_writers)) {
 		read_unlock(&eb->lock);
 		return 0;
@@ -151,7 +157,10 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
 	if (atomic_read(&eb->blocking_writers) ||
 	    atomic_read(&eb->blocking_readers))
 		return 0;
-	write_lock(&eb->lock);
+
+	if (!write_trylock(&eb->lock))
+		return 0;
+
 	if (atomic_read(&eb->blocking_writers) ||
 	    atomic_read(&eb->blocking_readers)) {
 		write_unlock(&eb->lock);
@@ -168,14 +177,15 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
  */
 void btrfs_tree_read_unlock(struct extent_buffer *eb)
 {
-	if (eb->lock_nested) {
-		read_lock(&eb->lock);
-		if (eb->lock_nested && current->pid == eb->lock_owner) {
-			eb->lock_nested = 0;
-			read_unlock(&eb->lock);
-			return;
-		}
-		read_unlock(&eb->lock);
+	/*
+	 * if we're nested, we have the write lock.  No new locking
+	 * is needed as long as we are the lock owner.
+	 * The write unlock will do a barrier for us, and the lock_nested
+	 * field only matters to the lock owner.
+	 */
+	if (eb->lock_nested && current->pid == eb->lock_owner) {
+		eb->lock_nested = 0;
+		return;
 	}
 	btrfs_assert_tree_read_locked(eb);
 	WARN_ON(atomic_read(&eb->spinning_readers) == 0);
@@ -189,14 +199,15 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb)
  */
 void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
 {
-	if (eb->lock_nested) {
-		read_lock(&eb->lock);
-		if (eb->lock_nested && current->pid == eb->lock_owner) {
-			eb->lock_nested = 0;
-			read_unlock(&eb->lock);
-			return;
-		}
-		read_unlock(&eb->lock);
+	/*
+	 * if we're nested, we have the write lock.  No new locking
+	 * is needed as long as we are the lock owner.
+	 * The write unlock will do a barrier for us, and the lock_nested
+	 * field only matters to the lock owner.
+	 */
+	if (eb->lock_nested && current->pid == eb->lock_owner) {
+		eb->lock_nested = 0;
+		return;
 	}
 	btrfs_assert_tree_read_locked(eb);
 	WARN_ON(atomic_read(&eb->blocking_readers) == 0);
@@ -244,6 +255,7 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
 	BUG_ON(blockers > 1);
 
 	btrfs_assert_tree_locked(eb);
+	eb->lock_owner = 0;
 	atomic_dec(&eb->write_locks);
 
 	if (blockers) {
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index b47f669aca7..dfad8514f0d 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -143,7 +143,7 @@ static int lzo_compress_pages(struct list_head *ws,
 		if (ret != LZO_E_OK) {
 			printk(KERN_DEBUG "BTRFS: deflate in loop returned %d\n",
 			       ret);
-			ret = -1;
+			ret = -EIO;
 			goto out;
 		}
 
@@ -189,7 +189,7 @@ static int lzo_compress_pages(struct list_head *ws,
 				kunmap(out_page);
 				if (nr_pages == nr_dest_pages) {
 					out_page = NULL;
-					ret = -1;
+					ret = -E2BIG;
 					goto out;
 				}
 
@@ -208,7 +208,7 @@ static int lzo_compress_pages(struct list_head *ws,
 
 		/* we're making it bigger, give up */
 		if (tot_in > 8192 && tot_in < tot_out) {
-			ret = -1;
+			ret = -E2BIG;
 			goto out;
 		}
 
@@ -335,7 +335,7 @@ cont:
 					break;
 
 				if (page_in_index + 1 >= total_pages_in) {
-					ret = -1;
+					ret = -EIO;
 					goto done;
 				}
 
@@ -358,7 +358,7 @@ cont:
 			kunmap(pages_in[page_in_index - 1]);
 		if (ret != LZO_E_OK) {
 			printk(KERN_WARNING "BTRFS: decompress failed\n");
-			ret = -1;
+			ret = -EIO;
 			break;
 		}
 
@@ -402,12 +402,12 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
 	ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
 	if (ret != LZO_E_OK) {
 		printk(KERN_WARNING "BTRFS: decompress failed!\n");
-		ret = -1;
+		ret = -EIO;
 		goto out;
 	}
 
 	if (out_len < start_byte) {
-		ret = -1;
+		ret = -EIO;
 		goto out;
 	}
 
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index a94b05f7286..7187b14faa6 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -67,7 +67,7 @@ static void ordered_data_tree_panic(struct inode *inode, int errno,
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	btrfs_panic(fs_info, errno, "Inconsistency in ordered tree at offset "
-		    "%llu\n", offset);
+		    "%llu", offset);
 }
 
 /*
@@ -484,8 +484,19 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid)
 					   log_list);
 		list_del_init(&ordered->log_list);
 		spin_unlock_irq(&log->log_extents_lock[index]);
+
+		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
+		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
+			struct inode *inode = ordered->inode;
+			u64 start = ordered->file_offset;
+			u64 end = ordered->file_offset + ordered->len - 1;
+
+			WARN_ON(!inode);
+			filemap_fdatawrite_range(inode->i_mapping, start, end);
+		}
 		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
 						   &ordered->flags));
+
 		btrfs_put_ordered_extent(ordered);
 		spin_lock_irq(&log->log_extents_lock[index]);
 	}
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 6efd70d3b64..9626b4ad3b9 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -54,7 +54,7 @@ static void print_extent_data_ref(struct extent_buffer *eb,
 	       btrfs_extent_data_ref_count(eb, ref));
 }
 
-static void print_extent_item(struct extent_buffer *eb, int slot)
+static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 {
 	struct btrfs_extent_item *ei;
 	struct btrfs_extent_inline_ref *iref;
@@ -63,7 +63,6 @@ static void print_extent_item(struct extent_buffer *eb, int slot)
 	struct btrfs_disk_key key;
 	unsigned long end;
 	unsigned long ptr;
-	int type;
 	u32 item_size = btrfs_item_size_nr(eb, slot);
 	u64 flags;
 	u64 offset;
@@ -88,7 +87,8 @@ static void print_extent_item(struct extent_buffer *eb, int slot)
 	       btrfs_extent_refs(eb, ei), btrfs_extent_generation(eb, ei),
 	       flags);
 
-	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+	if ((type == BTRFS_EXTENT_ITEM_KEY) &&
+	    flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		struct btrfs_tree_block_info *info;
 		info = (struct btrfs_tree_block_info *)(ei + 1);
 		btrfs_tree_block_key(eb, info, &key);
@@ -223,7 +223,8 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 				btrfs_disk_root_refs(l, ri));
 			break;
 		case BTRFS_EXTENT_ITEM_KEY:
-			print_extent_item(l, i);
+		case BTRFS_METADATA_ITEM_KEY:
+			print_extent_item(l, i, type);
 			break;
 		case BTRFS_TREE_BLOCK_REF_KEY:
 			printk(KERN_INFO "\t\ttree block backref\n");
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 2cf905877aa..98cb6b2630f 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -32,6 +32,7 @@
 #include "ulist.h"
 #include "backref.h"
 #include "extent_io.h"
+#include "qgroup.h"
 
 /* TODO XXX FIXME
  *  - subvol delete -> delete when ref goes to 0? delete limits also?
@@ -84,8 +85,8 @@ struct btrfs_qgroup {
 	/*
 	 * temp variables for accounting operations
 	 */
-	u64 tag;
-	u64 refcnt;
+	u64 old_refcnt;
+	u64 new_refcnt;
 };
 
 /*
@@ -98,6 +99,9 @@ struct btrfs_qgroup_list {
 	struct btrfs_qgroup *member;
 };
 
+#define ptr_to_u64(x) ((u64)(uintptr_t)x)
+#define u64_to_ptr(x) ((struct btrfs_qgroup *)(uintptr_t)x)
+
 static int
 qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		   int init_flags);
@@ -242,6 +246,21 @@ static int del_relation_rb(struct btrfs_fs_info *fs_info,
 	return -ENOENT;
 }
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
+			       u64 rfer, u64 excl)
+{
+	struct btrfs_qgroup *qgroup;
+
+	qgroup = find_qgroup_rb(fs_info, qgroupid);
+	if (!qgroup)
+		return -EINVAL;
+	if (qgroup->rfer != rfer || qgroup->excl != excl)
+		return -EINVAL;
+	return 0;
+}
+#endif
+
 /*
  * The full config is read in one go, only called from open_ctree()
  * It doesn't use any locking, as at this point we're still single-threaded
@@ -520,6 +539,10 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	struct btrfs_key key;
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &quota_root->state)))
+		return 0;
+#endif
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -669,6 +692,10 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
 	int ret;
 	int slot;
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+		return 0;
+#endif
 	key.objectid = 0;
 	key.type = BTRFS_QGROUP_INFO_KEY;
 	key.offset = qgroup->qgroupid;
@@ -1174,33 +1201,198 @@ out:
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;
 }
+static int comp_oper(struct btrfs_qgroup_operation *oper1,
+		     struct btrfs_qgroup_operation *oper2)
+{
+	if (oper1->bytenr < oper2->bytenr)
+		return -1;
+	if (oper1->bytenr > oper2->bytenr)
+		return 1;
+	if (oper1->seq < oper2->seq)
+		return -1;
+	if (oper1->seq > oper2->seq)
+		return -1;
+	if (oper1->ref_root < oper2->ref_root)
+		return -1;
+	if (oper1->ref_root > oper2->ref_root)
+		return 1;
+	if (oper1->type < oper2->type)
+		return -1;
+	if (oper1->type > oper2->type)
+		return 1;
+	return 0;
+}
+
+static int insert_qgroup_oper(struct btrfs_fs_info *fs_info,
+			      struct btrfs_qgroup_operation *oper)
+{
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+	struct btrfs_qgroup_operation *cur;
+	int cmp;
+
+	spin_lock(&fs_info->qgroup_op_lock);
+	p = &fs_info->qgroup_op_tree.rb_node;
+	while (*p) {
+		parent = *p;
+		cur = rb_entry(parent, struct btrfs_qgroup_operation, n);
+		cmp = comp_oper(cur, oper);
+		if (cmp < 0) {
+			p = &(*p)->rb_right;
+		} else if (cmp) {
+			p = &(*p)->rb_left;
+		} else {
+			spin_unlock(&fs_info->qgroup_op_lock);
+			return -EEXIST;
+		}
+	}
+	rb_link_node(&oper->n, parent, p);
+	rb_insert_color(&oper->n, &fs_info->qgroup_op_tree);
+	spin_unlock(&fs_info->qgroup_op_lock);
+	return 0;
+}
 
 /*
- * btrfs_qgroup_record_ref is called when the ref is added or deleted. it puts
- * the modification into a list that's later used by btrfs_end_transaction to
- * pass the recorded modifications on to btrfs_qgroup_account_ref.
+ * Record a quota operation for processing later on.
+ * @trans: the transaction we are adding the delayed op to.
+ * @fs_info: the fs_info for this fs.
+ * @ref_root: the root of the reference we are acting on,
+ * @bytenr: the bytenr we are acting on.
+ * @num_bytes: the number of bytes in the reference.
+ * @type: the type of operation this is.
+ * @mod_seq: do we need to get a sequence number for looking up roots.
+ *
+ * We just add it to our trans qgroup_ref_list and carry on and process these
+ * operations in order at some later point.  If the reference root isn't a fs
+ * root then we don't bother with doing anything.
+ *
+ * MUST BE HOLDING THE REF LOCK.
  */
 int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans,
-			    struct btrfs_delayed_ref_node *node,
-			    struct btrfs_delayed_extent_op *extent_op)
+			    struct btrfs_fs_info *fs_info, u64 ref_root,
+			    u64 bytenr, u64 num_bytes,
+			    enum btrfs_qgroup_operation_type type, int mod_seq)
 {
-	struct qgroup_update *u;
+	struct btrfs_qgroup_operation *oper;
+	int ret;
+
+	if (!is_fstree(ref_root) || !fs_info->quota_enabled)
+		return 0;
 
-	BUG_ON(!trans->delayed_ref_elem.seq);
-	u = kmalloc(sizeof(*u), GFP_NOFS);
-	if (!u)
+	oper = kmalloc(sizeof(*oper), GFP_NOFS);
+	if (!oper)
 		return -ENOMEM;
 
-	u->node = node;
-	u->extent_op = extent_op;
-	list_add_tail(&u->list, &trans->qgroup_ref_list);
+	oper->ref_root = ref_root;
+	oper->bytenr = bytenr;
+	oper->num_bytes = num_bytes;
+	oper->type = type;
+	oper->seq = atomic_inc_return(&fs_info->qgroup_op_seq);
+	INIT_LIST_HEAD(&oper->elem.list);
+	oper->elem.seq = 0;
+	ret = insert_qgroup_oper(fs_info, oper);
+	if (ret) {
+		/* Shouldn't happen so have an assert for developers */
+		ASSERT(0);
+		kfree(oper);
+		return ret;
+	}
+	list_add_tail(&oper->list, &trans->qgroup_ref_list);
+
+	if (mod_seq)
+		btrfs_get_tree_mod_seq(fs_info, &oper->elem);
 
 	return 0;
 }
 
-static int qgroup_account_ref_step1(struct btrfs_fs_info *fs_info,
-				    struct ulist *roots, struct ulist *tmp,
-				    u64 seq)
+/*
+ * The easy accounting, if we are adding/removing the only ref for an extent
+ * then this qgroup and all of the parent qgroups get their refrence and
+ * exclusive counts adjusted.
+ */
+static int qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
+				  struct btrfs_qgroup_operation *oper)
+{
+	struct btrfs_qgroup *qgroup;
+	struct ulist *tmp;
+	struct btrfs_qgroup_list *glist;
+	struct ulist_node *unode;
+	struct ulist_iterator uiter;
+	int sign = 0;
+	int ret = 0;
+
+	tmp = ulist_alloc(GFP_NOFS);
+	if (!tmp)
+		return -ENOMEM;
+
+	spin_lock(&fs_info->qgroup_lock);
+	if (!fs_info->quota_root)
+		goto out;
+	qgroup = find_qgroup_rb(fs_info, oper->ref_root);
+	if (!qgroup)
+		goto out;
+	switch (oper->type) {
+	case BTRFS_QGROUP_OPER_ADD_EXCL:
+		sign = 1;
+		break;
+	case BTRFS_QGROUP_OPER_SUB_EXCL:
+		sign = -1;
+		break;
+	default:
+		ASSERT(0);
+	}
+	qgroup->rfer += sign * oper->num_bytes;
+	qgroup->rfer_cmpr += sign * oper->num_bytes;
+
+	WARN_ON(sign < 0 && qgroup->excl < oper->num_bytes);
+	qgroup->excl += sign * oper->num_bytes;
+	qgroup->excl_cmpr += sign * oper->num_bytes;
+
+	qgroup_dirty(fs_info, qgroup);
+
+	/* Get all of the parent groups that contain this qgroup */
+	list_for_each_entry(glist, &qgroup->groups, next_group) {
+		ret = ulist_add(tmp, glist->group->qgroupid,
+				ptr_to_u64(glist->group), GFP_ATOMIC);
+		if (ret < 0)
+			goto out;
+	}
+
+	/* Iterate all of the parents and adjust their reference counts */
+	ULIST_ITER_INIT(&uiter);
+	while ((unode = ulist_next(tmp, &uiter))) {
+		qgroup = u64_to_ptr(unode->aux);
+		qgroup->rfer += sign * oper->num_bytes;
+		qgroup->rfer_cmpr += sign * oper->num_bytes;
+		qgroup->excl += sign * oper->num_bytes;
+		if (sign < 0)
+			WARN_ON(qgroup->excl < oper->num_bytes);
+		qgroup->excl_cmpr += sign * oper->num_bytes;
+		qgroup_dirty(fs_info, qgroup);
+
+		/* Add any parents of the parents */
+		list_for_each_entry(glist, &qgroup->groups, next_group) {
+			ret = ulist_add(tmp, glist->group->qgroupid,
+					ptr_to_u64(glist->group), GFP_ATOMIC);
+			if (ret < 0)
+				goto out;
+		}
+	}
+	ret = 0;
+out:
+	spin_unlock(&fs_info->qgroup_lock);
+	ulist_free(tmp);
+	return ret;
+}
+
+/*
+ * Walk all of the roots that pointed to our bytenr and adjust their refcnts as
+ * properly.
+ */
+static int qgroup_calc_old_refcnt(struct btrfs_fs_info *fs_info,
+				  u64 root_to_skip, struct ulist *tmp,
+				  struct ulist *roots, struct ulist *qgroups,
+				  u64 seq, int *old_roots, int rescan)
 {
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
@@ -1211,256 +1403,551 @@ static int qgroup_account_ref_step1(struct btrfs_fs_info *fs_info,
 
 	ULIST_ITER_INIT(&uiter);
 	while ((unode = ulist_next(roots, &uiter))) {
+		/* We don't count our current root here */
+		if (unode->val == root_to_skip)
+			continue;
 		qg = find_qgroup_rb(fs_info, unode->val);
 		if (!qg)
 			continue;
+		/*
+		 * We could have a pending removal of this same ref so we may
+		 * not have actually found our ref root when doing
+		 * btrfs_find_all_roots, so we need to keep track of how many
+		 * old roots we find in case we removed ours and added a
+		 * different one at the same time.  I don't think this could
+		 * happen in practice but that sort of thinking leads to pain
+		 * and suffering and to the dark side.
+		 */
+		(*old_roots)++;
 
 		ulist_reinit(tmp);
-						/* XXX id not needed */
-		ret = ulist_add(tmp, qg->qgroupid,
-				(u64)(uintptr_t)qg, GFP_ATOMIC);
+		ret = ulist_add(qgroups, qg->qgroupid, ptr_to_u64(qg),
+				GFP_ATOMIC);
+		if (ret < 0)
+			return ret;
+		ret = ulist_add(tmp, qg->qgroupid, ptr_to_u64(qg), GFP_ATOMIC);
 		if (ret < 0)
 			return ret;
 		ULIST_ITER_INIT(&tmp_uiter);
 		while ((tmp_unode = ulist_next(tmp, &tmp_uiter))) {
 			struct btrfs_qgroup_list *glist;
 
-			qg = (struct btrfs_qgroup *)(uintptr_t)tmp_unode->aux;
-			if (qg->refcnt < seq)
-				qg->refcnt = seq + 1;
+			qg = u64_to_ptr(tmp_unode->aux);
+			/*
+			 * We use this sequence number to keep from having to
+			 * run the whole list and 0 out the refcnt every time.
+			 * We basically use sequnce as the known 0 count and
+			 * then add 1 everytime we see a qgroup.  This is how we
+			 * get how many of the roots actually point up to the
+			 * upper level qgroups in order to determine exclusive
+			 * counts.
+			 *
+			 * For rescan we want to set old_refcnt to seq so our
+			 * exclusive calculations end up correct.
+			 */
+			if (rescan)
+				qg->old_refcnt = seq;
+			else if (qg->old_refcnt < seq)
+				qg->old_refcnt = seq + 1;
 			else
-				++qg->refcnt;
+				qg->old_refcnt++;
 
+			if (qg->new_refcnt < seq)
+				qg->new_refcnt = seq + 1;
+			else
+				qg->new_refcnt++;
 			list_for_each_entry(glist, &qg->groups, next_group) {
+				ret = ulist_add(qgroups, glist->group->qgroupid,
+						ptr_to_u64(glist->group),
+						GFP_ATOMIC);
+				if (ret < 0)
+					return ret;
 				ret = ulist_add(tmp, glist->group->qgroupid,
-						(u64)(uintptr_t)glist->group,
+						ptr_to_u64(glist->group),
 						GFP_ATOMIC);
 				if (ret < 0)
 					return ret;
 			}
 		}
 	}
+	return 0;
+}
+
+/*
+ * We need to walk forward in our operation tree and account for any roots that
+ * were deleted after we made this operation.
+ */
+static int qgroup_account_deleted_refs(struct btrfs_fs_info *fs_info,
+				       struct btrfs_qgroup_operation *oper,
+				       struct ulist *tmp,
+				       struct ulist *qgroups, u64 seq,
+				       int *old_roots)
+{
+	struct ulist_node *unode;
+	struct ulist_iterator uiter;
+	struct btrfs_qgroup *qg;
+	struct btrfs_qgroup_operation *tmp_oper;
+	struct rb_node *n;
+	int ret;
+
+	ulist_reinit(tmp);
 
+	/*
+	 * We only walk forward in the tree since we're only interested in
+	 * removals that happened _after_  our operation.
+	 */
+	spin_lock(&fs_info->qgroup_op_lock);
+	n = rb_next(&oper->n);
+	spin_unlock(&fs_info->qgroup_op_lock);
+	if (!n)
+		return 0;
+	tmp_oper = rb_entry(n, struct btrfs_qgroup_operation, n);
+	while (tmp_oper->bytenr == oper->bytenr) {
+		/*
+		 * If it's not a removal we don't care, additions work out
+		 * properly with our refcnt tracking.
+		 */
+		if (tmp_oper->type != BTRFS_QGROUP_OPER_SUB_SHARED &&
+		    tmp_oper->type != BTRFS_QGROUP_OPER_SUB_EXCL)
+			goto next;
+		qg = find_qgroup_rb(fs_info, tmp_oper->ref_root);
+		if (!qg)
+			goto next;
+		ret = ulist_add(qgroups, qg->qgroupid, ptr_to_u64(qg),
+				GFP_ATOMIC);
+		if (ret) {
+			if (ret < 0)
+				return ret;
+			/*
+			 * We only want to increase old_roots if this qgroup is
+			 * not already in the list of qgroups.  If it is already
+			 * there then that means it must have been re-added or
+			 * the delete will be discarded because we had an
+			 * existing ref that we haven't looked up yet.  In this
+			 * case we don't want to increase old_roots.  So if ret
+			 * == 1 then we know that this is the first time we've
+			 * seen this qgroup and we can bump the old_roots.
+			 */
+			(*old_roots)++;
+			ret = ulist_add(tmp, qg->qgroupid, ptr_to_u64(qg),
+					GFP_ATOMIC);
+			if (ret < 0)
+				return ret;
+		}
+next:
+		spin_lock(&fs_info->qgroup_op_lock);
+		n = rb_next(&tmp_oper->n);
+		spin_unlock(&fs_info->qgroup_op_lock);
+		if (!n)
+			break;
+		tmp_oper = rb_entry(n, struct btrfs_qgroup_operation, n);
+	}
+
+	/* Ok now process the qgroups we found */
+	ULIST_ITER_INIT(&uiter);
+	while ((unode = ulist_next(tmp, &uiter))) {
+		struct btrfs_qgroup_list *glist;
+
+		qg = u64_to_ptr(unode->aux);
+		if (qg->old_refcnt < seq)
+			qg->old_refcnt = seq + 1;
+		else
+			qg->old_refcnt++;
+		if (qg->new_refcnt < seq)
+			qg->new_refcnt = seq + 1;
+		else
+			qg->new_refcnt++;
+		list_for_each_entry(glist, &qg->groups, next_group) {
+			ret = ulist_add(qgroups, glist->group->qgroupid,
+					ptr_to_u64(glist->group), GFP_ATOMIC);
+			if (ret < 0)
+				return ret;
+			ret = ulist_add(tmp, glist->group->qgroupid,
+					ptr_to_u64(glist->group), GFP_ATOMIC);
+			if (ret < 0)
+				return ret;
+		}
+	}
 	return 0;
 }
 
-static int qgroup_account_ref_step2(struct btrfs_fs_info *fs_info,
-				    struct ulist *roots, struct ulist *tmp,
-				    u64 seq, int sgn, u64 num_bytes,
-				    struct btrfs_qgroup *qgroup)
+/* Add refcnt for the newly added reference. */
+static int qgroup_calc_new_refcnt(struct btrfs_fs_info *fs_info,
+				  struct btrfs_qgroup_operation *oper,
+				  struct btrfs_qgroup *qgroup,
+				  struct ulist *tmp, struct ulist *qgroups,
+				  u64 seq)
 {
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
 	struct btrfs_qgroup *qg;
-	struct btrfs_qgroup_list *glist;
 	int ret;
 
 	ulist_reinit(tmp);
-	ret = ulist_add(tmp, qgroup->qgroupid, (uintptr_t)qgroup, GFP_ATOMIC);
+	ret = ulist_add(qgroups, qgroup->qgroupid, ptr_to_u64(qgroup),
+			GFP_ATOMIC);
+	if (ret < 0)
+		return ret;
+	ret = ulist_add(tmp, qgroup->qgroupid, ptr_to_u64(qgroup),
+			GFP_ATOMIC);
 	if (ret < 0)
 		return ret;
-
 	ULIST_ITER_INIT(&uiter);
 	while ((unode = ulist_next(tmp, &uiter))) {
-		qg = (struct btrfs_qgroup *)(uintptr_t)unode->aux;
-		if (qg->refcnt < seq) {
-			/* not visited by step 1 */
-			qg->rfer += sgn * num_bytes;
-			qg->rfer_cmpr += sgn * num_bytes;
-			if (roots->nnodes == 0) {
-				qg->excl += sgn * num_bytes;
-				qg->excl_cmpr += sgn * num_bytes;
-			}
-			qgroup_dirty(fs_info, qg);
-		}
-		WARN_ON(qg->tag >= seq);
-		qg->tag = seq;
+		struct btrfs_qgroup_list *glist;
 
+		qg = u64_to_ptr(unode->aux);
+		if (oper->type == BTRFS_QGROUP_OPER_ADD_SHARED) {
+			if (qg->new_refcnt < seq)
+				qg->new_refcnt = seq + 1;
+			else
+				qg->new_refcnt++;
+		} else {
+			if (qg->old_refcnt < seq)
+				qg->old_refcnt = seq + 1;
+			else
+				qg->old_refcnt++;
+		}
 		list_for_each_entry(glist, &qg->groups, next_group) {
 			ret = ulist_add(tmp, glist->group->qgroupid,
-					(uintptr_t)glist->group, GFP_ATOMIC);
+					ptr_to_u64(glist->group), GFP_ATOMIC);
+			if (ret < 0)
+				return ret;
+			ret = ulist_add(qgroups, glist->group->qgroupid,
+					ptr_to_u64(glist->group), GFP_ATOMIC);
 			if (ret < 0)
 				return ret;
 		}
 	}
-
 	return 0;
 }
 
-static int qgroup_account_ref_step3(struct btrfs_fs_info *fs_info,
-				    struct ulist *roots, struct ulist *tmp,
-				    u64 seq, int sgn, u64 num_bytes)
+/*
+ * This adjusts the counters for all referenced qgroups if need be.
+ */
+static int qgroup_adjust_counters(struct btrfs_fs_info *fs_info,
+				  u64 root_to_skip, u64 num_bytes,
+				  struct ulist *qgroups, u64 seq,
+				  int old_roots, int new_roots, int rescan)
 {
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
 	struct btrfs_qgroup *qg;
-	struct ulist_node *tmp_unode;
-	struct ulist_iterator tmp_uiter;
-	int ret;
+	u64 cur_new_count, cur_old_count;
 
 	ULIST_ITER_INIT(&uiter);
-	while ((unode = ulist_next(roots, &uiter))) {
-		qg = find_qgroup_rb(fs_info, unode->val);
-		if (!qg)
-			continue;
+	while ((unode = ulist_next(qgroups, &uiter))) {
+		bool dirty = false;
 
-		ulist_reinit(tmp);
-		ret = ulist_add(tmp, qg->qgroupid, (uintptr_t)qg, GFP_ATOMIC);
-		if (ret < 0)
-			return ret;
+		qg = u64_to_ptr(unode->aux);
+		/*
+		 * Wasn't referenced before but is now, add to the reference
+		 * counters.
+		 */
+		if (qg->old_refcnt <= seq && qg->new_refcnt > seq) {
+			qg->rfer += num_bytes;
+			qg->rfer_cmpr += num_bytes;
+			dirty = true;
+		}
 
-		ULIST_ITER_INIT(&tmp_uiter);
-		while ((tmp_unode = ulist_next(tmp, &tmp_uiter))) {
-			struct btrfs_qgroup_list *glist;
+		/*
+		 * Was referenced before but isn't now, subtract from the
+		 * reference counters.
+		 */
+		if (qg->old_refcnt > seq && qg->new_refcnt <= seq) {
+			qg->rfer -= num_bytes;
+			qg->rfer_cmpr -= num_bytes;
+			dirty = true;
+		}
 
-			qg = (struct btrfs_qgroup *)(uintptr_t)tmp_unode->aux;
-			if (qg->tag == seq)
-				continue;
+		if (qg->old_refcnt < seq)
+			cur_old_count = 0;
+		else
+			cur_old_count = qg->old_refcnt - seq;
+		if (qg->new_refcnt < seq)
+			cur_new_count = 0;
+		else
+			cur_new_count = qg->new_refcnt - seq;
 
-			if (qg->refcnt - seq == roots->nnodes) {
-				qg->excl -= sgn * num_bytes;
-				qg->excl_cmpr -= sgn * num_bytes;
-				qgroup_dirty(fs_info, qg);
-			}
+		/*
+		 * If our refcount was the same as the roots previously but our
+		 * new count isn't the same as the number of roots now then we
+		 * went from having a exclusive reference on this range to not.
+		 */
+		if (old_roots && cur_old_count == old_roots &&
+		    (cur_new_count != new_roots || new_roots == 0)) {
+			WARN_ON(cur_new_count != new_roots && new_roots == 0);
+			qg->excl -= num_bytes;
+			qg->excl_cmpr -= num_bytes;
+			dirty = true;
+		}
 
-			list_for_each_entry(glist, &qg->groups, next_group) {
-				ret = ulist_add(tmp, glist->group->qgroupid,
-						(uintptr_t)glist->group,
-						GFP_ATOMIC);
-				if (ret < 0)
-					return ret;
-			}
+		/*
+		 * If we didn't reference all the roots before but now we do we
+		 * have an exclusive reference to this range.
+		 */
+		if ((!old_roots || (old_roots && cur_old_count != old_roots))
+		    && cur_new_count == new_roots) {
+			qg->excl += num_bytes;
+			qg->excl_cmpr += num_bytes;
+			dirty = true;
 		}
-	}
 
+		if (dirty)
+			qgroup_dirty(fs_info, qg);
+	}
 	return 0;
 }
 
 /*
- * btrfs_qgroup_account_ref is called for every ref that is added to or deleted
- * from the fs. First, all roots referencing the extent are searched, and
- * then the space is accounted accordingly to the different roots. The
- * accounting algorithm works in 3 steps documented inline.
+ * If we removed a data extent and there were other references for that bytenr
+ * then we need to lookup all referenced roots to make sure we still don't
+ * reference this bytenr.  If we do then we can just discard this operation.
  */
-int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info,
-			     struct btrfs_delayed_ref_node *node,
-			     struct btrfs_delayed_extent_op *extent_op)
+static int check_existing_refs(struct btrfs_trans_handle *trans,
+			       struct btrfs_fs_info *fs_info,
+			       struct btrfs_qgroup_operation *oper)
 {
-	struct btrfs_root *quota_root;
-	u64 ref_root;
-	struct btrfs_qgroup *qgroup;
 	struct ulist *roots = NULL;
-	u64 seq;
+	struct ulist_node *unode;
+	struct ulist_iterator uiter;
 	int ret = 0;
-	int sgn;
 
-	if (!fs_info->quota_enabled)
-		return 0;
-
-	BUG_ON(!fs_info->quota_root);
+	ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr,
+				   oper->elem.seq, &roots);
+	if (ret < 0)
+		return ret;
+	ret = 0;
 
-	if (node->type == BTRFS_TREE_BLOCK_REF_KEY ||
-	    node->type == BTRFS_SHARED_BLOCK_REF_KEY) {
-		struct btrfs_delayed_tree_ref *ref;
-		ref = btrfs_delayed_node_to_tree_ref(node);
-		ref_root = ref->root;
-	} else if (node->type == BTRFS_EXTENT_DATA_REF_KEY ||
-		   node->type == BTRFS_SHARED_DATA_REF_KEY) {
-		struct btrfs_delayed_data_ref *ref;
-		ref = btrfs_delayed_node_to_data_ref(node);
-		ref_root = ref->root;
-	} else {
-		BUG();
+	ULIST_ITER_INIT(&uiter);
+	while ((unode = ulist_next(roots, &uiter))) {
+		if (unode->val == oper->ref_root) {
+			ret = 1;
+			break;
+		}
 	}
+	ulist_free(roots);
+	btrfs_put_tree_mod_seq(fs_info, &oper->elem);
 
-	if (!is_fstree(ref_root)) {
-		/*
-		 * non-fs-trees are not being accounted
-		 */
-		return 0;
-	}
+	return ret;
+}
 
-	switch (node->action) {
-	case BTRFS_ADD_DELAYED_REF:
-	case BTRFS_ADD_DELAYED_EXTENT:
-		sgn = 1;
-		seq = btrfs_tree_mod_seq_prev(node->seq);
-		break;
-	case BTRFS_DROP_DELAYED_REF:
-		sgn = -1;
-		seq = node->seq;
-		break;
-	case BTRFS_UPDATE_DELAYED_HEAD:
-		return 0;
-	default:
-		BUG();
-	}
+/*
+ * If we share a reference across multiple roots then we may need to adjust
+ * various qgroups referenced and exclusive counters.  The basic premise is this
+ *
+ * 1) We have seq to represent a 0 count.  Instead of looping through all of the
+ * qgroups and resetting their refcount to 0 we just constantly bump this
+ * sequence number to act as the base reference count.  This means that if
+ * anybody is equal to or below this sequence they were never referenced.  We
+ * jack this sequence up by the number of roots we found each time in order to
+ * make sure we don't have any overlap.
+ *
+ * 2) We first search all the roots that reference the area _except_ the root
+ * we're acting on currently.  This makes up the old_refcnt of all the qgroups
+ * before.
+ *
+ * 3) We walk all of the qgroups referenced by the root we are currently acting
+ * on, and will either adjust old_refcnt in the case of a removal or the
+ * new_refcnt in the case of an addition.
+ *
+ * 4) Finally we walk all the qgroups that are referenced by this range
+ * including the root we are acting on currently.  We will adjust the counters
+ * based on the number of roots we had and will have after this operation.
+ *
+ * Take this example as an illustration
+ *
+ *			[qgroup 1/0]
+ *		     /         |          \
+ *		[qg 0/0]   [qg 0/1]	[qg 0/2]
+ *		   \          |            /
+ *		  [	   extent	    ]
+ *
+ * Say we are adding a reference that is covered by qg 0/0.  The first step
+ * would give a refcnt of 1 to qg 0/1 and 0/2 and a refcnt of 2 to qg 1/0 with
+ * old_roots being 2.  Because it is adding new_roots will be 1.  We then go
+ * through qg 0/0 which will get the new_refcnt set to 1 and add 1 to qg 1/0's
+ * new_refcnt, bringing it to 3.  We then walk through all of the qgroups, we
+ * notice that the old refcnt for qg 0/0 < the new refcnt, so we added a
+ * reference and thus must add the size to the referenced bytes.  Everything
+ * else is the same so nothing else changes.
+ */
+static int qgroup_shared_accounting(struct btrfs_trans_handle *trans,
+				    struct btrfs_fs_info *fs_info,
+				    struct btrfs_qgroup_operation *oper)
+{
+	struct ulist *roots = NULL;
+	struct ulist *qgroups, *tmp;
+	struct btrfs_qgroup *qgroup;
+	struct seq_list elem = {};
+	u64 seq;
+	int old_roots = 0;
+	int new_roots = 0;
+	int ret = 0;
 
-	mutex_lock(&fs_info->qgroup_rescan_lock);
-	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
-		if (fs_info->qgroup_rescan_progress.objectid <= node->bytenr) {
-			mutex_unlock(&fs_info->qgroup_rescan_lock);
+	if (oper->elem.seq) {
+		ret = check_existing_refs(trans, fs_info, oper);
+		if (ret < 0)
+			return ret;
+		if (ret)
 			return 0;
-		}
 	}
-	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
-	/*
-	 * the delayed ref sequence number we pass depends on the direction of
-	 * the operation. for add operations, we pass
-	 * tree_mod_log_prev_seq(node->seq) to skip
-	 * the delayed ref's current sequence number, because we need the state
-	 * of the tree before the add operation. for delete operations, we pass
-	 * (node->seq) to include the delayed ref's current sequence number,
-	 * because we need the state of the tree after the delete operation.
-	 */
-	ret = btrfs_find_all_roots(trans, fs_info, node->bytenr, seq, &roots);
-	if (ret < 0)
-		return ret;
-
-	spin_lock(&fs_info->qgroup_lock);
+	qgroups = ulist_alloc(GFP_NOFS);
+	if (!qgroups)
+		return -ENOMEM;
 
-	quota_root = fs_info->quota_root;
-	if (!quota_root)
-		goto unlock;
+	tmp = ulist_alloc(GFP_NOFS);
+	if (!tmp) {
+		ulist_free(qgroups);
+		return -ENOMEM;
+	}
 
-	qgroup = find_qgroup_rb(fs_info, ref_root);
+	btrfs_get_tree_mod_seq(fs_info, &elem);
+	ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr, elem.seq,
+				   &roots);
+	btrfs_put_tree_mod_seq(fs_info, &elem);
+	if (ret < 0) {
+		ulist_free(qgroups);
+		ulist_free(tmp);
+		return ret;
+	}
+	spin_lock(&fs_info->qgroup_lock);
+	qgroup = find_qgroup_rb(fs_info, oper->ref_root);
 	if (!qgroup)
-		goto unlock;
+		goto out;
+	seq = fs_info->qgroup_seq;
 
 	/*
-	 * step 1: for each old ref, visit all nodes once and inc refcnt
+	 * So roots is the list of all the roots currently pointing at the
+	 * bytenr, including the ref we are adding if we are adding, or not if
+	 * we are removing a ref.  So we pass in the ref_root to skip that root
+	 * in our calculations.  We set old_refnct and new_refcnt cause who the
+	 * hell knows what everything looked like before, and it doesn't matter
+	 * except...
 	 */
-	ulist_reinit(fs_info->qgroup_ulist);
-	seq = fs_info->qgroup_seq;
-	fs_info->qgroup_seq += roots->nnodes + 1; /* max refcnt */
+	ret = qgroup_calc_old_refcnt(fs_info, oper->ref_root, tmp, roots, qgroups,
+				     seq, &old_roots, 0);
+	if (ret < 0)
+		goto out;
 
-	ret = qgroup_account_ref_step1(fs_info, roots, fs_info->qgroup_ulist,
-				       seq);
-	if (ret)
-		goto unlock;
+	/*
+	 * Now adjust the refcounts of the qgroups that care about this
+	 * reference, either the old_count in the case of removal or new_count
+	 * in the case of an addition.
+	 */
+	ret = qgroup_calc_new_refcnt(fs_info, oper, qgroup, tmp, qgroups,
+				     seq);
+	if (ret < 0)
+		goto out;
 
 	/*
-	 * step 2: walk from the new root
+	 * ...in the case of removals.  If we had a removal before we got around
+	 * to processing this operation then we need to find that guy and count
+	 * his references as if they really existed so we don't end up screwing
+	 * up the exclusive counts.  Then whenever we go to process the delete
+	 * everything will be grand and we can account for whatever exclusive
+	 * changes need to be made there.  We also have to pass in old_roots so
+	 * we have an accurate count of the roots as it pertains to this
+	 * operations view of the world.
 	 */
-	ret = qgroup_account_ref_step2(fs_info, roots, fs_info->qgroup_ulist,
-				       seq, sgn, node->num_bytes, qgroup);
-	if (ret)
-		goto unlock;
+	ret = qgroup_account_deleted_refs(fs_info, oper, tmp, qgroups, seq,
+					  &old_roots);
+	if (ret < 0)
+		goto out;
 
 	/*
-	 * step 3: walk again from old refs
+	 * We are adding our root, need to adjust up the number of roots,
+	 * otherwise old_roots is the number of roots we want.
 	 */
-	ret = qgroup_account_ref_step3(fs_info, roots, fs_info->qgroup_ulist,
-				       seq, sgn, node->num_bytes);
-	if (ret)
-		goto unlock;
+	if (oper->type == BTRFS_QGROUP_OPER_ADD_SHARED) {
+		new_roots = old_roots + 1;
+	} else {
+		new_roots = old_roots;
+		old_roots++;
+	}
+	fs_info->qgroup_seq += old_roots + 1;
 
-unlock:
+
+	/*
+	 * And now the magic happens, bless Arne for having a pretty elegant
+	 * solution for this.
+	 */
+	qgroup_adjust_counters(fs_info, oper->ref_root, oper->num_bytes,
+			       qgroups, seq, old_roots, new_roots, 0);
+out:
 	spin_unlock(&fs_info->qgroup_lock);
+	ulist_free(qgroups);
 	ulist_free(roots);
+	ulist_free(tmp);
+	return ret;
+}
+
+/*
+ * btrfs_qgroup_account_ref is called for every ref that is added to or deleted
+ * from the fs. First, all roots referencing the extent are searched, and
+ * then the space is accounted accordingly to the different roots. The
+ * accounting algorithm works in 3 steps documented inline.
+ */
+static int btrfs_qgroup_account(struct btrfs_trans_handle *trans,
+				struct btrfs_fs_info *fs_info,
+				struct btrfs_qgroup_operation *oper)
+{
+	int ret = 0;
+
+	if (!fs_info->quota_enabled)
+		return 0;
+
+	BUG_ON(!fs_info->quota_root);
+
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
+		if (fs_info->qgroup_rescan_progress.objectid <= oper->bytenr) {
+			mutex_unlock(&fs_info->qgroup_rescan_lock);
+			return 0;
+		}
+	}
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
+
+	ASSERT(is_fstree(oper->ref_root));
+
+	switch (oper->type) {
+	case BTRFS_QGROUP_OPER_ADD_EXCL:
+	case BTRFS_QGROUP_OPER_SUB_EXCL:
+		ret = qgroup_excl_accounting(fs_info, oper);
+		break;
+	case BTRFS_QGROUP_OPER_ADD_SHARED:
+	case BTRFS_QGROUP_OPER_SUB_SHARED:
+		ret = qgroup_shared_accounting(trans, fs_info, oper);
+		break;
+	default:
+		ASSERT(0);
+	}
+	return ret;
+}
+
+/*
+ * Needs to be called everytime we run delayed refs, even if there is an error
+ * in order to cleanup outstanding operations.
+ */
+int btrfs_delayed_qgroup_accounting(struct btrfs_trans_handle *trans,
+				    struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_qgroup_operation *oper;
+	int ret = 0;
 
+	while (!list_empty(&trans->qgroup_ref_list)) {
+		oper = list_first_entry(&trans->qgroup_ref_list,
+					struct btrfs_qgroup_operation, list);
+		list_del_init(&oper->list);
+		if (!ret || !trans->aborted)
+			ret = btrfs_qgroup_account(trans, fs_info, oper);
+		spin_lock(&fs_info->qgroup_op_lock);
+		rb_erase(&oper->n, &fs_info->qgroup_op_tree);
+		spin_unlock(&fs_info->qgroup_op_lock);
+		btrfs_put_tree_mod_seq(fs_info, &oper->elem);
+		kfree(oper);
+	}
 	return ret;
 }
 
@@ -1629,8 +2116,16 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		srcgroup = find_qgroup_rb(fs_info, srcid);
 		if (!srcgroup)
 			goto unlock;
-		dstgroup->rfer = srcgroup->rfer - level_size;
-		dstgroup->rfer_cmpr = srcgroup->rfer_cmpr - level_size;
+
+		/*
+		 * We call inherit after we clone the root in order to make sure
+		 * our counts don't go crazy, so at this point the only
+		 * difference between the two roots should be the root node.
+		 */
+		dstgroup->rfer = srcgroup->rfer;
+		dstgroup->rfer_cmpr = srcgroup->rfer_cmpr;
+		dstgroup->excl = level_size;
+		dstgroup->excl_cmpr = level_size;
 		srcgroup->excl = level_size;
 		srcgroup->excl_cmpr = level_size;
 		qgroup_dirty(fs_info, dstgroup);
@@ -1734,7 +2229,7 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 		struct btrfs_qgroup *qg;
 		struct btrfs_qgroup_list *glist;
 
-		qg = (struct btrfs_qgroup *)(uintptr_t)unode->aux;
+		qg = u64_to_ptr(unode->aux);
 
 		if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
 		    qg->reserved + (s64)qg->rfer + num_bytes >
@@ -1766,7 +2261,7 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 	while ((unode = ulist_next(fs_info->qgroup_ulist, &uiter))) {
 		struct btrfs_qgroup *qg;
 
-		qg = (struct btrfs_qgroup *)(uintptr_t)unode->aux;
+		qg = u64_to_ptr(unode->aux);
 
 		qg->reserved += num_bytes;
 	}
@@ -1812,7 +2307,7 @@ void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes)
 		struct btrfs_qgroup *qg;
 		struct btrfs_qgroup_list *glist;
 
-		qg = (struct btrfs_qgroup *)(uintptr_t)unode->aux;
+		qg = u64_to_ptr(unode->aux);
 
 		qg->reserved -= num_bytes;
 
@@ -1848,15 +2343,15 @@ void assert_qgroups_uptodate(struct btrfs_trans_handle *trans)
  */
 static int
 qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
-		   struct btrfs_trans_handle *trans, struct ulist *tmp,
-		   struct extent_buffer *scratch_leaf)
+		   struct btrfs_trans_handle *trans, struct ulist *qgroups,
+		   struct ulist *tmp, struct extent_buffer *scratch_leaf)
 {
 	struct btrfs_key found;
 	struct ulist *roots = NULL;
-	struct ulist_node *unode;
-	struct ulist_iterator uiter;
 	struct seq_list tree_mod_seq_elem = {};
+	u64 num_bytes;
 	u64 seq;
+	int new_roots;
 	int slot;
 	int ret;
 
@@ -1897,8 +2392,6 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
 	for (; slot < btrfs_header_nritems(scratch_leaf); ++slot) {
-		u64 num_bytes;
-
 		btrfs_item_key_to_cpu(scratch_leaf, &found, slot);
 		if (found.type != BTRFS_EXTENT_ITEM_KEY &&
 		    found.type != BTRFS_METADATA_ITEM_KEY)
@@ -1908,76 +2401,34 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 		else
 			num_bytes = found.offset;
 
-		ret = btrfs_find_all_roots(trans, fs_info, found.objectid,
-					   tree_mod_seq_elem.seq, &roots);
+		ulist_reinit(qgroups);
+		ret = btrfs_find_all_roots(NULL, fs_info, found.objectid, 0,
+					   &roots);
 		if (ret < 0)
 			goto out;
 		spin_lock(&fs_info->qgroup_lock);
 		seq = fs_info->qgroup_seq;
 		fs_info->qgroup_seq += roots->nnodes + 1; /* max refcnt */
 
-		ret = qgroup_account_ref_step1(fs_info, roots, tmp, seq);
-		if (ret) {
+		new_roots = 0;
+		ret = qgroup_calc_old_refcnt(fs_info, 0, tmp, roots, qgroups,
+					     seq, &new_roots, 1);
+		if (ret < 0) {
 			spin_unlock(&fs_info->qgroup_lock);
 			ulist_free(roots);
 			goto out;
 		}
 
-		/*
-		 * step2 of btrfs_qgroup_account_ref works from a single root,
-		 * we're doing all at once here.
-		 */
-		ulist_reinit(tmp);
-		ULIST_ITER_INIT(&uiter);
-		while ((unode = ulist_next(roots, &uiter))) {
-			struct btrfs_qgroup *qg;
-
-			qg = find_qgroup_rb(fs_info, unode->val);
-			if (!qg)
-				continue;
-
-			ret = ulist_add(tmp, qg->qgroupid, (uintptr_t)qg,
-					GFP_ATOMIC);
-			if (ret < 0) {
-				spin_unlock(&fs_info->qgroup_lock);
-				ulist_free(roots);
-				goto out;
-			}
-		}
-
-		/* this loop is similar to step 2 of btrfs_qgroup_account_ref */
-		ULIST_ITER_INIT(&uiter);
-		while ((unode = ulist_next(tmp, &uiter))) {
-			struct btrfs_qgroup *qg;
-			struct btrfs_qgroup_list *glist;
-
-			qg = (struct btrfs_qgroup *)(uintptr_t) unode->aux;
-			qg->rfer += num_bytes;
-			qg->rfer_cmpr += num_bytes;
-			WARN_ON(qg->tag >= seq);
-			if (qg->refcnt - seq == roots->nnodes) {
-				qg->excl += num_bytes;
-				qg->excl_cmpr += num_bytes;
-			}
-			qgroup_dirty(fs_info, qg);
-
-			list_for_each_entry(glist, &qg->groups, next_group) {
-				ret = ulist_add(tmp, glist->group->qgroupid,
-						(uintptr_t)glist->group,
-						GFP_ATOMIC);
-				if (ret < 0) {
-					spin_unlock(&fs_info->qgroup_lock);
-					ulist_free(roots);
-					goto out;
-				}
-			}
+		ret = qgroup_adjust_counters(fs_info, 0, num_bytes, qgroups,
+					     seq, 0, new_roots, 1);
+		if (ret < 0) {
+			spin_unlock(&fs_info->qgroup_lock);
+			ulist_free(roots);
+			goto out;
 		}
-
 		spin_unlock(&fs_info->qgroup_lock);
 		ulist_free(roots);
-		ret = 0;
 	}
-
 out:
 	btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem);
 
@@ -1990,13 +2441,16 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 						     qgroup_rescan_work);
 	struct btrfs_path *path;
 	struct btrfs_trans_handle *trans = NULL;
-	struct ulist *tmp = NULL;
+	struct ulist *tmp = NULL, *qgroups = NULL;
 	struct extent_buffer *scratch_leaf = NULL;
 	int err = -ENOMEM;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		goto out;
+	qgroups = ulist_alloc(GFP_NOFS);
+	if (!qgroups)
+		goto out;
 	tmp = ulist_alloc(GFP_NOFS);
 	if (!tmp)
 		goto out;
@@ -2015,7 +2469,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 			err = -EINTR;
 		} else {
 			err = qgroup_rescan_leaf(fs_info, path, trans,
-						 tmp, scratch_leaf);
+						 qgroups, tmp, scratch_leaf);
 		}
 		if (err > 0)
 			btrfs_commit_transaction(trans, fs_info->fs_root);
@@ -2025,6 +2479,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 
 out:
 	kfree(scratch_leaf);
+	ulist_free(qgroups);
 	ulist_free(tmp);
 	btrfs_free_path(path);
 
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
new file mode 100644
index 00000000000..5952ff1fbd7
--- /dev/null
+++ b/fs/btrfs/qgroup.h
@@ -0,0 +1,107 @@
+/*
+ * Copyright (C) 2014 Facebook.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#ifndef __BTRFS_QGROUP__
+#define __BTRFS_QGROUP__
+
+/*
+ * A description of the operations, all of these operations only happen when we
+ * are adding the 1st reference for that subvolume in the case of adding space
+ * or on the last reference delete in the case of subtraction.  The only
+ * exception is the last one, which is added for confusion.
+ *
+ * BTRFS_QGROUP_OPER_ADD_EXCL: adding bytes where this subvolume is the only
+ * one pointing at the bytes we are adding.  This is called on the first
+ * allocation.
+ *
+ * BTRFS_QGROUP_OPER_ADD_SHARED: adding bytes where this bytenr is going to be
+ * shared between subvols.  This is called on the creation of a ref that already
+ * has refs from a different subvolume, so basically reflink.
+ *
+ * BTRFS_QGROUP_OPER_SUB_EXCL: removing bytes where this subvolume is the only
+ * one referencing the range.
+ *
+ * BTRFS_QGROUP_OPER_SUB_SHARED: removing bytes where this subvolume shares with
+ * refs with other subvolumes.
+ */
+enum btrfs_qgroup_operation_type {
+	BTRFS_QGROUP_OPER_ADD_EXCL,
+	BTRFS_QGROUP_OPER_ADD_SHARED,
+	BTRFS_QGROUP_OPER_SUB_EXCL,
+	BTRFS_QGROUP_OPER_SUB_SHARED,
+};
+
+struct btrfs_qgroup_operation {
+	u64 ref_root;
+	u64 bytenr;
+	u64 num_bytes;
+	u64 seq;
+	enum btrfs_qgroup_operation_type type;
+	struct seq_list elem;
+	struct rb_node n;
+	struct list_head list;
+};
+
+int btrfs_quota_enable(struct btrfs_trans_handle *trans,
+		       struct btrfs_fs_info *fs_info);
+int btrfs_quota_disable(struct btrfs_trans_handle *trans,
+			struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
+void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info);
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
+			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
+int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
+			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
+int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
+			struct btrfs_fs_info *fs_info, u64 qgroupid,
+			char *name);
+int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
+			      struct btrfs_fs_info *fs_info, u64 qgroupid);
+int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
+		       struct btrfs_fs_info *fs_info, u64 qgroupid,
+		       struct btrfs_qgroup_limit *limit);
+int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);
+void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
+struct btrfs_delayed_extent_op;
+int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans,
+			    struct btrfs_fs_info *fs_info, u64 ref_root,
+			    u64 bytenr, u64 num_bytes,
+			    enum btrfs_qgroup_operation_type type,
+			    int mod_seq);
+int btrfs_delayed_qgroup_accounting(struct btrfs_trans_handle *trans,
+				    struct btrfs_fs_info *fs_info);
+void btrfs_remove_qgroup_operation(struct btrfs_trans_handle *trans,
+				   struct btrfs_fs_info *fs_info,
+				   struct btrfs_qgroup_operation *oper);
+int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
+		      struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
+			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
+			 struct btrfs_qgroup_inherit *inherit);
+int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes);
+void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes);
+
+void assert_qgroups_uptodate(struct btrfs_trans_handle *trans);
+
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
+			       u64 rfer, u64 excl);
+#endif
+
+#endif /* __BTRFS_QGROUP__ */
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 4055291a523..4a88f073fdd 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1956,9 +1956,10 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	 * pages are going to be uptodate.
 	 */
 	for (stripe = 0; stripe < bbio->num_stripes; stripe++) {
-		if (rbio->faila == stripe ||
-		    rbio->failb == stripe)
+		if (rbio->faila == stripe || rbio->failb == stripe) {
+			atomic_inc(&rbio->bbio->error);
 			continue;
+		}
 
 		for (pagenr = 0; pagenr < nr_pages; pagenr++) {
 			struct page *p;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 30947f92362..09230cf3a24 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -428,8 +428,13 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 			continue;
 		}
 		if (!dev->bdev) {
-			/* cannot read ahead on missing device */
-			continue;
+			/*
+			 * cannot read ahead on missing device, but for RAID5/6,
+			 * REQ_GET_READ_MIRRORS return 1. So don't skip missing
+			 * device for such case.
+			 */
+			if (nzones > 1)
+				continue;
 		}
 		if (dev_replace_is_ongoing &&
 		    dev == fs_info->dev_replace.tgtdev) {
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 7f92ab1daa8..65245a07275 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -337,7 +337,7 @@ static void backref_tree_panic(struct rb_node *rb_node, int errno, u64 bytenr)
 	if (bnode->root)
 		fs_info = bnode->root->fs_info;
 	btrfs_panic(fs_info, errno, "Inconsistency in backref cache "
-		    "found at offset %llu\n", bytenr);
+		    "found at offset %llu", bytenr);
 }
 
 /*
@@ -528,7 +528,7 @@ static int should_ignore_root(struct btrfs_root *root)
 {
 	struct btrfs_root *reloc_root;
 
-	if (!root->ref_cows)
+	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		return 0;
 
 	reloc_root = root->reloc_root;
@@ -610,7 +610,7 @@ struct btrfs_root *find_tree_root(struct reloc_control *rc,
 	root = read_fs_root(rc->extent_root->fs_info, root_objectid);
 	BUG_ON(IS_ERR(root));
 
-	if (root->ref_cows &&
+	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
 	    generation != btrfs_root_generation(&root->root_item))
 		return NULL;
 
@@ -887,7 +887,7 @@ again:
 			goto out;
 		}
 
-		if (!root->ref_cows)
+		if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 			cur->cowonly = 1;
 
 		if (btrfs_root_level(&root->root_item) == cur->level) {
@@ -954,7 +954,8 @@ again:
 				upper->bytenr = eb->start;
 				upper->owner = btrfs_header_owner(eb);
 				upper->level = lower->level + 1;
-				if (!root->ref_cows)
+				if (!test_bit(BTRFS_ROOT_REF_COWS,
+					      &root->state))
 					upper->cowonly = 1;
 
 				/*
@@ -1258,7 +1259,7 @@ static int __must_check __add_reloc_root(struct btrfs_root *root)
 	if (rb_node) {
 		btrfs_panic(root->fs_info, -EEXIST, "Duplicate root found "
 			    "for start=%llu while inserting into relocation "
-			    "tree\n", node->bytenr);
+			    "tree", node->bytenr);
 		kfree(node);
 		return -EEXIST;
 	}
@@ -2441,7 +2442,7 @@ struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans,
 		next = walk_up_backref(next, edges, &index);
 		root = next->root;
 		BUG_ON(!root);
-		BUG_ON(!root->ref_cows);
+		BUG_ON(!test_bit(BTRFS_ROOT_REF_COWS, &root->state));
 
 		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
 			record_reloc_root_in_trans(trans, root);
@@ -2506,7 +2507,7 @@ struct btrfs_root *select_one_root(struct btrfs_trans_handle *trans,
 		BUG_ON(!root);
 
 		/* no other choice for non-references counted tree */
-		if (!root->ref_cows)
+		if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 			return root;
 
 		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID)
@@ -2893,14 +2894,14 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	if (!root || root->ref_cows) {
+	if (!root || test_bit(BTRFS_ROOT_REF_COWS, &root->state)) {
 		ret = reserve_metadata_space(trans, rc, node);
 		if (ret)
 			goto out;
 	}
 
 	if (root) {
-		if (root->ref_cows) {
+		if (test_bit(BTRFS_ROOT_REF_COWS, &root->state)) {
 			BUG_ON(node->new_bytenr);
 			BUG_ON(!list_empty(&node->list));
 			btrfs_record_root_in_trans(trans, root);
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 38bb47e7d6b..360a728a639 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -306,7 +306,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
 			break;
 		}
 
-		root->orphan_item_inserted = 1;
+		set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
 
 		err = btrfs_insert_fs_root(root->fs_info, root);
 		if (err) {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 0be77993378..b6d198f5181 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -588,8 +588,9 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
 
 	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		do {
-			ret = tree_backref_for_extent(&ptr, eb, ei, item_size,
-							&ref_root, &ref_level);
+			ret = tree_backref_for_extent(&ptr, eb, &found_key, ei,
+						      item_size, &ref_root,
+						      &ref_level);
 			printk_in_rcu(KERN_WARNING
 				"BTRFS: %s at logical %llu on dev %s, "
 				"sector %llu: metadata %s (level %d) in tree "
@@ -717,8 +718,8 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 out:
 	if (page)
 		put_page(page);
-	if (inode)
-		iput(inode);
+
+	iput(inode);
 
 	if (ret < 0)
 		return ret;
@@ -2724,11 +2725,8 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
 		length = btrfs_dev_extent_length(l, dev_extent);
 
-		if (found_key.offset + length <= start) {
-			key.offset = found_key.offset + length;
-			btrfs_release_path(path);
-			continue;
-		}
+		if (found_key.offset + length <= start)
+			goto skip;
 
 		chunk_tree = btrfs_dev_extent_chunk_tree(l, dev_extent);
 		chunk_objectid = btrfs_dev_extent_chunk_objectid(l, dev_extent);
@@ -2739,10 +2737,12 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 * the chunk from going away while we scrub it
 		 */
 		cache = btrfs_lookup_block_group(fs_info, chunk_offset);
-		if (!cache) {
-			ret = -ENOENT;
-			break;
-		}
+
+		/* some chunks are removed but not committed to disk yet,
+		 * continue scrubbing */
+		if (!cache)
+			goto skip;
+
 		dev_replace->cursor_right = found_key.offset + length;
 		dev_replace->cursor_left = found_key.offset;
 		dev_replace->item_needs_writeback = 1;
@@ -2801,7 +2801,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 
 		dev_replace->cursor_left = dev_replace->cursor_right;
 		dev_replace->item_needs_writeback = 1;
-
+skip:
 		key.offset = found_key.offset + length;
 		btrfs_release_path(path);
 	}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 484aacac2c8..6528aa66218 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -975,7 +975,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 	struct btrfs_dir_item *di;
 	struct btrfs_key di_key;
 	char *buf = NULL;
-	const int buf_len = PATH_MAX;
+	int buf_len;
 	u32 name_len;
 	u32 data_len;
 	u32 cur;
@@ -985,6 +985,11 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 	int num;
 	u8 type;
 
+	if (found_key->type == BTRFS_XATTR_ITEM_KEY)
+		buf_len = BTRFS_MAX_XATTR_SIZE(root);
+	else
+		buf_len = PATH_MAX;
+
 	buf = kmalloc(buf_len, GFP_NOFS);
 	if (!buf) {
 		ret = -ENOMEM;
@@ -1006,12 +1011,23 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 		type = btrfs_dir_type(eb, di);
 		btrfs_dir_item_key_to_cpu(eb, di, &di_key);
 
-		/*
-		 * Path too long
-		 */
-		if (name_len + data_len > buf_len) {
-			ret = -ENAMETOOLONG;
-			goto out;
+		if (type == BTRFS_FT_XATTR) {
+			if (name_len > XATTR_NAME_MAX) {
+				ret = -ENAMETOOLONG;
+				goto out;
+			}
+			if (name_len + data_len > buf_len) {
+				ret = -E2BIG;
+				goto out;
+			}
+		} else {
+			/*
+			 * Path too long
+			 */
+			if (name_len + data_len > buf_len) {
+				ret = -ENAMETOOLONG;
+				goto out;
+			}
 		}
 
 		read_extent_buffer(eb, buf, (unsigned long)(di + 1),
@@ -1349,7 +1365,7 @@ static int find_extent_clone(struct send_ctx *sctx,
 		ret = -EIO;
 		btrfs_err(sctx->send_root->fs_info, "did not find backref in "
 				"send_root. inode=%llu, offset=%llu, "
-				"disk_byte=%llu found extent=%llu\n",
+				"disk_byte=%llu found extent=%llu",
 				ino, data_offset, disk_byte, found_key.objectid);
 		goto out;
 	}
@@ -1628,6 +1644,10 @@ static int lookup_dir_item_inode(struct btrfs_root *root,
 		goto out;
 	}
 	btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
+	if (key.type == BTRFS_ROOT_ITEM_KEY) {
+		ret = -ENOENT;
+		goto out;
+	}
 	*found_inode = key.objectid;
 	*found_type = btrfs_dir_type(path->nodes[0], di);
 
@@ -1693,10 +1713,12 @@ static int get_first_ref(struct btrfs_root *root, u64 ino,
 		goto out;
 	btrfs_release_path(path);
 
-	ret = get_inode_info(root, parent_dir, NULL, dir_gen, NULL, NULL,
-			NULL, NULL);
-	if (ret < 0)
-		goto out;
+	if (dir_gen) {
+		ret = get_inode_info(root, parent_dir, NULL, dir_gen, NULL,
+				     NULL, NULL, NULL);
+		if (ret < 0)
+			goto out;
+	}
 
 	*dir = parent_dir;
 
@@ -1712,13 +1734,12 @@ static int is_first_ref(struct btrfs_root *root,
 	int ret;
 	struct fs_path *tmp_name;
 	u64 tmp_dir;
-	u64 tmp_dir_gen;
 
 	tmp_name = fs_path_alloc();
 	if (!tmp_name)
 		return -ENOMEM;
 
-	ret = get_first_ref(root, ino, &tmp_dir, &tmp_dir_gen, tmp_name);
+	ret = get_first_ref(root, ino, &tmp_dir, NULL, tmp_name);
 	if (ret < 0)
 		goto out;
 
@@ -2029,7 +2050,6 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
 {
 	int ret;
 	int nce_ret;
-	struct btrfs_path *path = NULL;
 	struct name_cache_entry *nce = NULL;
 
 	/*
@@ -2055,10 +2075,6 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
 		}
 	}
 
-	path = alloc_path_for_send();
-	if (!path)
-		return -ENOMEM;
-
 	/*
 	 * If the inode is not existent yet, add the orphan name and return 1.
 	 * This should only happen for the parent dir that we determine in
@@ -2134,7 +2150,6 @@ out_cache:
 	name_cache_clean_unused(sctx);
 
 out:
-	btrfs_free_path(path);
 	return ret;
 }
 
@@ -2945,7 +2960,9 @@ static void free_waiting_dir_move(struct send_ctx *sctx,
 static int add_pending_dir_move(struct send_ctx *sctx,
 				u64 ino,
 				u64 ino_gen,
-				u64 parent_ino)
+				u64 parent_ino,
+				struct list_head *new_refs,
+				struct list_head *deleted_refs)
 {
 	struct rb_node **p = &sctx->pending_dir_moves.rb_node;
 	struct rb_node *parent = NULL;
@@ -2977,12 +2994,12 @@ static int add_pending_dir_move(struct send_ctx *sctx,
 		}
 	}
 
-	list_for_each_entry(cur, &sctx->deleted_refs, list) {
+	list_for_each_entry(cur, deleted_refs, list) {
 		ret = dup_ref(cur, &pm->update_refs);
 		if (ret < 0)
 			goto out;
 	}
-	list_for_each_entry(cur, &sctx->new_refs, list) {
+	list_for_each_entry(cur, new_refs, list) {
 		ret = dup_ref(cur, &pm->update_refs);
 		if (ret < 0)
 			goto out;
@@ -3025,6 +3042,48 @@ static struct pending_dir_move *get_pending_dir_moves(struct send_ctx *sctx,
 	return NULL;
 }
 
+static int path_loop(struct send_ctx *sctx, struct fs_path *name,
+		     u64 ino, u64 gen, u64 *ancestor_ino)
+{
+	int ret = 0;
+	u64 parent_inode = 0;
+	u64 parent_gen = 0;
+	u64 start_ino = ino;
+
+	*ancestor_ino = 0;
+	while (ino != BTRFS_FIRST_FREE_OBJECTID) {
+		fs_path_reset(name);
+
+		if (is_waiting_for_rm(sctx, ino))
+			break;
+		if (is_waiting_for_move(sctx, ino)) {
+			if (*ancestor_ino == 0)
+				*ancestor_ino = ino;
+			ret = get_first_ref(sctx->parent_root, ino,
+					    &parent_inode, &parent_gen, name);
+		} else {
+			ret = __get_cur_name_and_parent(sctx, ino, gen,
+							&parent_inode,
+							&parent_gen, name);
+			if (ret > 0) {
+				ret = 0;
+				break;
+			}
+		}
+		if (ret < 0)
+			break;
+		if (parent_inode == start_ino) {
+			ret = 1;
+			if (*ancestor_ino == 0)
+				*ancestor_ino = ino;
+			break;
+		}
+		ino = parent_inode;
+		gen = parent_gen;
+	}
+	return ret;
+}
+
 static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 {
 	struct fs_path *from_path = NULL;
@@ -3036,6 +3095,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 	struct waiting_dir_move *dm = NULL;
 	u64 rmdir_ino = 0;
 	int ret;
+	u64 ancestor = 0;
 
 	name = fs_path_alloc();
 	from_path = fs_path_alloc();
@@ -3054,34 +3114,33 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
 	if (ret < 0)
 		goto out;
 
-	if (parent_ino == sctx->cur_ino) {
-		/* child only renamed, not moved */
-		ASSERT(parent_gen == sctx->cur_inode_gen);
-		ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen,
-				   from_path);
-		if (ret < 0)
-			goto out;
-		ret = fs_path_add_path(from_path, name);
-		if (ret < 0)
-			goto out;
-	} else {
-		/* child moved and maybe renamed too */
-		sctx->send_progress = pm->ino;
-		ret = get_cur_path(sctx, pm->ino, pm->gen, from_path);
+	ret = get_cur_path(sctx, parent_ino, parent_gen,
+			   from_path);
+	if (ret < 0)
+		goto out;
+	ret = fs_path_add_path(from_path, name);
+	if (ret < 0)
+		goto out;
+
+	sctx->send_progress = sctx->cur_ino + 1;
+	ret = path_loop(sctx, name, pm->ino, pm->gen, &ancestor);
+	if (ret) {
+		LIST_HEAD(deleted_refs);
+		ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID);
+		ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor,
+					   &pm->update_refs, &deleted_refs);
 		if (ret < 0)
 			goto out;
-	}
-
-	fs_path_free(name);
-	name = NULL;
-
-	to_path = fs_path_alloc();
-	if (!to_path) {
-		ret = -ENOMEM;
+		if (rmdir_ino) {
+			dm = get_waiting_dir_move(sctx, pm->ino);
+			ASSERT(dm);
+			dm->rmdir_ino = rmdir_ino;
+		}
 		goto out;
 	}
-
-	sctx->send_progress = sctx->cur_ino + 1;
+	fs_path_reset(name);
+	to_path = name;
+	name = NULL;
 	ret = get_cur_path(sctx, pm->ino, pm->gen, to_path);
 	if (ret < 0)
 		goto out;
@@ -3205,127 +3264,74 @@ out:
 static int wait_for_parent_move(struct send_ctx *sctx,
 				struct recorded_ref *parent_ref)
 {
-	int ret;
+	int ret = 0;
 	u64 ino = parent_ref->dir;
 	u64 parent_ino_before, parent_ino_after;
-	u64 old_gen;
 	struct fs_path *path_before = NULL;
 	struct fs_path *path_after = NULL;
 	int len1, len2;
-	int register_upper_dirs;
-	u64 gen;
-
-	if (is_waiting_for_move(sctx, ino))
-		return 1;
-
-	if (parent_ref->dir <= sctx->cur_ino)
-		return 0;
-
-	ret = get_inode_info(sctx->parent_root, ino, NULL, &old_gen,
-			     NULL, NULL, NULL, NULL);
-	if (ret == -ENOENT)
-		return 0;
-	else if (ret < 0)
-		return ret;
-
-	if (parent_ref->dir_gen != old_gen)
-		return 0;
-
-	path_before = fs_path_alloc();
-	if (!path_before)
-		return -ENOMEM;
-
-	ret = get_first_ref(sctx->parent_root, ino, &parent_ino_before,
-			    NULL, path_before);
-	if (ret == -ENOENT) {
-		ret = 0;
-		goto out;
-	} else if (ret < 0) {
-		goto out;
-	}
 
 	path_after = fs_path_alloc();
-	if (!path_after) {
+	path_before = fs_path_alloc();
+	if (!path_after || !path_before) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	ret = get_first_ref(sctx->send_root, ino, &parent_ino_after,
-			    &gen, path_after);
-	if (ret == -ENOENT) {
-		ret = 0;
-		goto out;
-	} else if (ret < 0) {
-		goto out;
-	}
-
-	len1 = fs_path_len(path_before);
-	len2 = fs_path_len(path_after);
-	if (parent_ino_before != parent_ino_after || len1 != len2 ||
-	     memcmp(path_before->start, path_after->start, len1)) {
-		ret = 1;
-		goto out;
-	}
-	ret = 0;
-
 	/*
-	 * Ok, our new most direct ancestor has a higher inode number but
-	 * wasn't moved/renamed. So maybe some of the new ancestors higher in
-	 * the hierarchy have an higher inode number too *and* were renamed
-	 * or moved - in this case we need to wait for the ancestor's rename
-	 * or move operation before we can do the move/rename for the current
-	 * inode.
+	 * Our current directory inode may not yet be renamed/moved because some
+	 * ancestor (immediate or not) has to be renamed/moved first. So find if
+	 * such ancestor exists and make sure our own rename/move happens after
+	 * that ancestor is processed.
 	 */
-	register_upper_dirs = 0;
-	ino = parent_ino_after;
-again:
-	while ((ret == 0 || register_upper_dirs) && ino > sctx->cur_ino) {
-		u64 parent_gen;
+	while (ino > BTRFS_FIRST_FREE_OBJECTID) {
+		if (is_waiting_for_move(sctx, ino)) {
+			ret = 1;
+			break;
+		}
 
 		fs_path_reset(path_before);
 		fs_path_reset(path_after);
 
 		ret = get_first_ref(sctx->send_root, ino, &parent_ino_after,
-				    &parent_gen, path_after);
+				    NULL, path_after);
 		if (ret < 0)
 			goto out;
 		ret = get_first_ref(sctx->parent_root, ino, &parent_ino_before,
 				    NULL, path_before);
-		if (ret == -ENOENT) {
-			ret = 0;
-			break;
-		} else if (ret < 0) {
+		if (ret < 0 && ret != -ENOENT) {
 			goto out;
+		} else if (ret == -ENOENT) {
+			ret = 1;
+			break;
 		}
 
 		len1 = fs_path_len(path_before);
 		len2 = fs_path_len(path_after);
-		if (parent_ino_before != parent_ino_after || len1 != len2 ||
-		    memcmp(path_before->start, path_after->start, len1)) {
+		if (ino > sctx->cur_ino &&
+		    (parent_ino_before != parent_ino_after || len1 != len2 ||
+		     memcmp(path_before->start, path_after->start, len1))) {
 			ret = 1;
-			if (register_upper_dirs) {
-				break;
-			} else {
-				register_upper_dirs = 1;
-				ino = parent_ref->dir;
-				gen = parent_ref->dir_gen;
-				goto again;
-			}
-		} else if (register_upper_dirs) {
-			ret = add_pending_dir_move(sctx, ino, gen,
-						   parent_ino_after);
-			if (ret < 0 && ret != -EEXIST)
-				goto out;
+			break;
 		}
-
 		ino = parent_ino_after;
-		gen = parent_gen;
 	}
 
 out:
 	fs_path_free(path_before);
 	fs_path_free(path_after);
 
+	if (ret == 1) {
+		ret = add_pending_dir_move(sctx,
+					   sctx->cur_ino,
+					   sctx->cur_inode_gen,
+					   ino,
+					   &sctx->new_refs,
+					   &sctx->deleted_refs);
+		if (!ret)
+			ret = 1;
+	}
+
 	return ret;
 }
 
@@ -3486,10 +3492,6 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
 				if (ret < 0)
 					goto out;
 				if (ret) {
-					ret = add_pending_dir_move(sctx,
-							   sctx->cur_ino,
-							   sctx->cur_inode_gen,
-							   cur->dir);
 					*pending_move = 1;
 				} else {
 					ret = send_rename(sctx, valid_path,
@@ -5490,7 +5492,7 @@ static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
 	 */
 	if (root->send_in_progress < 0)
 		btrfs_err(root->fs_info,
-			"send_in_progres unbalanced %d root %llu\n",
+			"send_in_progres unbalanced %d root %llu",
 			root->send_in_progress, root->root_key.objectid);
 	spin_unlock(&root->root_item_lock);
 }
@@ -5518,7 +5520,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 
 	/*
 	 * The subvolume must remain read-only during send, protect against
-	 * making it RW.
+	 * making it RW. This also protects against deletion.
 	 */
 	spin_lock(&send_root->root_item_lock);
 	send_root->send_in_progress++;
@@ -5578,6 +5580,15 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 	}
 
 	sctx->send_root = send_root;
+	/*
+	 * Unlikely but possible, if the subvolume is marked for deletion but
+	 * is slow to remove the directory entry, send can still be started
+	 */
+	if (btrfs_root_dead(sctx->send_root)) {
+		ret = -EPERM;
+		goto out;
+	}
+
 	sctx->clone_roots_cnt = arg->clone_sources_count;
 
 	sctx->send_max_size = BTRFS_SEND_BUF_SIZE;
@@ -5667,7 +5678,8 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 
 		spin_lock(&sctx->parent_root->root_item_lock);
 		sctx->parent_root->send_in_progress++;
-		if (!btrfs_root_readonly(sctx->parent_root)) {
+		if (!btrfs_root_readonly(sctx->parent_root) ||
+				btrfs_root_dead(sctx->parent_root)) {
 			spin_unlock(&sctx->parent_root->root_item_lock);
 			srcu_read_unlock(&fs_info->subvol_srcu, index);
 			ret = -EPERM;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 9601d25a460..8e16bca69c5 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -511,7 +511,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			} else if (compress) {
 				if (!btrfs_test_opt(root, COMPRESS))
 					btrfs_info(root->fs_info,
-						   "btrfs: use %s compression\n",
+						   "btrfs: use %s compression",
 						   compress_type);
 			}
 			break;
@@ -522,9 +522,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 		case Opt_ssd_spread:
 			btrfs_set_and_info(root, SSD_SPREAD,
 					   "use spread ssd allocation scheme");
+			btrfs_set_opt(info->mount_opt, SSD);
 			break;
 		case Opt_nossd:
-			btrfs_clear_and_info(root, NOSSD,
+			btrfs_set_and_info(root, NOSSD,
 					     "not using ssd allocation scheme");
 			btrfs_clear_opt(info->mount_opt, SSD);
 			break;
@@ -580,8 +581,15 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			}
 			break;
 		case Opt_acl:
+#ifdef CONFIG_BTRFS_FS_POSIX_ACL
 			root->fs_info->sb->s_flags |= MS_POSIXACL;
 			break;
+#else
+			btrfs_err(root->fs_info,
+				"support for ACL not compiled in!");
+			ret = -EINVAL;
+			goto out;
+#endif
 		case Opt_noacl:
 			root->fs_info->sb->s_flags &= ~MS_POSIXACL;
 			break;
@@ -1413,6 +1421,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		 * this also happens on 'umount -rf' or on shutdown, when
 		 * the filesystem is busy.
 		 */
+		cancel_work_sync(&fs_info->async_reclaim_work);
 
 		/* wait for the uuid_scan task to finish */
 		down(&fs_info->uuid_tree_rescan_sem);
@@ -1459,7 +1468,9 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			goto restore;
 
 		/* recover relocation */
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(root);
+		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret)
 			goto restore;
 
@@ -1800,6 +1811,8 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 		list_for_each_entry(dev, head, dev_list) {
 			if (dev->missing)
 				continue;
+			if (!dev->name)
+				continue;
 			if (!first_dev || dev->devid < first_dev->devid)
 				first_dev = dev;
 		}
@@ -1894,6 +1907,9 @@ static int btrfs_run_sanity_tests(void)
 	if (ret)
 		goto out;
 	ret = btrfs_test_inodes();
+	if (ret)
+		goto out;
+	ret = btrfs_test_qgroups();
 out:
 	btrfs_destroy_test_fs();
 	return ret;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index c5eb2143dc6..78699364f53 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -254,6 +254,7 @@ static ssize_t global_rsv_reserved_show(struct kobject *kobj,
 BTRFS_ATTR(global_rsv_reserved, 0444, global_rsv_reserved_show);
 
 #define to_space_info(_kobj) container_of(_kobj, struct btrfs_space_info, kobj)
+#define to_raid_kobj(_kobj) container_of(_kobj, struct raid_kobject, kobj)
 
 static ssize_t raid_bytes_show(struct kobject *kobj,
 			       struct kobj_attribute *attr, char *buf);
@@ -266,7 +267,7 @@ static ssize_t raid_bytes_show(struct kobject *kobj,
 {
 	struct btrfs_space_info *sinfo = to_space_info(kobj->parent);
 	struct btrfs_block_group_cache *block_group;
-	int index = kobj - sinfo->block_group_kobjs;
+	int index = to_raid_kobj(kobj)->raid_type;
 	u64 val = 0;
 
 	down_read(&sinfo->groups_sem);
@@ -288,7 +289,7 @@ static struct attribute *raid_attributes[] = {
 
 static void release_raid_kobj(struct kobject *kobj)
 {
-	kobject_put(kobj->parent);
+	kfree(to_raid_kobj(kobj));
 }
 
 struct kobj_type btrfs_raid_ktype = {
@@ -374,11 +375,8 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
 	struct btrfs_root *root = fs_info->fs_root;
 	int ret;
 
-	if (len >= BTRFS_LABEL_SIZE) {
-		pr_err("BTRFS: unable to set label with more than %d bytes\n",
-		       BTRFS_LABEL_SIZE - 1);
+	if (len >= BTRFS_LABEL_SIZE)
 		return -EINVAL;
-	}
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans))
@@ -396,8 +394,48 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
 }
 BTRFS_ATTR_RW(label, 0644, btrfs_label_show, btrfs_label_store);
 
+static ssize_t btrfs_no_store(struct kobject *kobj,
+				 struct kobj_attribute *a,
+				 const char *buf, size_t len)
+{
+	return -EPERM;
+}
+
+static ssize_t btrfs_nodesize_show(struct kobject *kobj,
+				struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
+}
+
+BTRFS_ATTR_RW(nodesize, 0444, btrfs_nodesize_show, btrfs_no_store);
+
+static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
+				struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->sectorsize);
+}
+
+BTRFS_ATTR_RW(sectorsize, 0444, btrfs_sectorsize_show, btrfs_no_store);
+
+static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
+				struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->sectorsize);
+}
+
+BTRFS_ATTR_RW(clone_alignment, 0444, btrfs_clone_alignment_show, btrfs_no_store);
+
 static struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(label),
+	BTRFS_ATTR_PTR(nodesize),
+	BTRFS_ATTR_PTR(sectorsize),
+	BTRFS_ATTR_PTR(clone_alignment),
 	NULL,
 };
 
@@ -567,14 +605,37 @@ static void init_feature_attrs(void)
 	}
 }
 
-static int add_device_membership(struct btrfs_fs_info *fs_info)
+int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *one_device)
+{
+	struct hd_struct *disk;
+	struct kobject *disk_kobj;
+
+	if (!fs_info->device_dir_kobj)
+		return -EINVAL;
+
+	if (one_device) {
+		disk = one_device->bdev->bd_part;
+		disk_kobj = &part_to_dev(disk)->kobj;
+
+		sysfs_remove_link(fs_info->device_dir_kobj,
+						disk_kobj->name);
+	}
+
+	return 0;
+}
+
+int btrfs_kobj_add_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *one_device)
 {
 	int error = 0;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *dev;
 
-	fs_info->device_dir_kobj = kobject_create_and_add("devices",
+	if (!fs_info->device_dir_kobj)
+		fs_info->device_dir_kobj = kobject_create_and_add("devices",
 						&fs_info->super_kobj);
+
 	if (!fs_info->device_dir_kobj)
 		return -ENOMEM;
 
@@ -585,6 +646,9 @@ static int add_device_membership(struct btrfs_fs_info *fs_info)
 		if (!dev->bdev)
 			continue;
 
+		if (one_device && one_device != dev)
+			continue;
+
 		disk = dev->bdev->bd_part;
 		disk_kobj = &part_to_dev(disk)->kobj;
 
@@ -628,7 +692,7 @@ int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info)
 	if (error)
 		goto failure;
 
-	error = add_device_membership(fs_info);
+	error = btrfs_kobj_add_device(fs_info, NULL);
 	if (error)
 		goto failure;
 
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 9ab576318a8..ac46df37504 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -66,4 +66,8 @@ char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags);
 extern const char * const btrfs_feature_set_names[3];
 extern struct kobj_type space_info_ktype;
 extern struct kobj_type btrfs_raid_ktype;
+int btrfs_kobj_add_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *one_device);
+int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info,
+                struct btrfs_device *one_device);
 #endif /* _BTRFS_SYSFS_H_ */
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 757ef00a75a..9626252ee6b 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -21,6 +21,9 @@
 #include <linux/magic.h>
 #include "btrfs-tests.h"
 #include "../ctree.h"
+#include "../volumes.h"
+#include "../disk-io.h"
+#include "../qgroup.h"
 
 static struct vfsmount *test_mnt = NULL;
 
@@ -72,3 +75,97 @@ void btrfs_destroy_test_fs(void)
 	kern_unmount(test_mnt);
 	unregister_filesystem(&test_type);
 }
+
+struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void)
+{
+	struct btrfs_fs_info *fs_info = kzalloc(sizeof(struct btrfs_fs_info),
+						GFP_NOFS);
+
+	if (!fs_info)
+		return fs_info;
+	fs_info->fs_devices = kzalloc(sizeof(struct btrfs_fs_devices),
+				      GFP_NOFS);
+	if (!fs_info->fs_devices) {
+		kfree(fs_info);
+		return NULL;
+	}
+	fs_info->super_copy = kzalloc(sizeof(struct btrfs_super_block),
+				      GFP_NOFS);
+	if (!fs_info->super_copy) {
+		kfree(fs_info->fs_devices);
+		kfree(fs_info);
+		return NULL;
+	}
+
+	if (init_srcu_struct(&fs_info->subvol_srcu)) {
+		kfree(fs_info->fs_devices);
+		kfree(fs_info->super_copy);
+		kfree(fs_info);
+		return NULL;
+	}
+
+	spin_lock_init(&fs_info->buffer_lock);
+	spin_lock_init(&fs_info->qgroup_lock);
+	spin_lock_init(&fs_info->qgroup_op_lock);
+	spin_lock_init(&fs_info->super_lock);
+	spin_lock_init(&fs_info->fs_roots_radix_lock);
+	spin_lock_init(&fs_info->tree_mod_seq_lock);
+	mutex_init(&fs_info->qgroup_ioctl_lock);
+	mutex_init(&fs_info->qgroup_rescan_lock);
+	rwlock_init(&fs_info->tree_mod_log_lock);
+	fs_info->running_transaction = NULL;
+	fs_info->qgroup_tree = RB_ROOT;
+	fs_info->qgroup_ulist = NULL;
+	atomic64_set(&fs_info->tree_mod_seq, 0);
+	INIT_LIST_HEAD(&fs_info->dirty_qgroups);
+	INIT_LIST_HEAD(&fs_info->dead_roots);
+	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
+	INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
+	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
+	return fs_info;
+}
+
+static void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+
+	spin_lock(&fs_info->buffer_lock);
+restart:
+	radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) {
+		struct extent_buffer *eb;
+
+		eb = radix_tree_deref_slot_protected(slot, &fs_info->buffer_lock);
+		if (!eb)
+			continue;
+		/* Shouldn't happen but that kind of thinking creates CVE's */
+		if (radix_tree_exception(eb)) {
+			if (radix_tree_deref_retry(eb))
+				goto restart;
+			continue;
+		}
+		spin_unlock(&fs_info->buffer_lock);
+		free_extent_buffer_stale(eb);
+		spin_lock(&fs_info->buffer_lock);
+	}
+	spin_unlock(&fs_info->buffer_lock);
+
+	btrfs_free_qgroup_config(fs_info);
+	btrfs_free_fs_roots(fs_info);
+	cleanup_srcu_struct(&fs_info->subvol_srcu);
+	kfree(fs_info->super_copy);
+	kfree(fs_info->fs_devices);
+	kfree(fs_info);
+}
+
+void btrfs_free_dummy_root(struct btrfs_root *root)
+{
+	if (!root)
+		return;
+	if (root->node)
+		free_extent_buffer(root->node);
+	if (root->fs_info)
+		btrfs_free_dummy_fs_info(root->fs_info);
+	kfree(root);
+}
+
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index 312560a9123..fd395422448 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -23,13 +23,18 @@
 
 #define test_msg(fmt, ...) pr_info("BTRFS: selftest: " fmt, ##__VA_ARGS__)
 
+struct btrfs_root;
+
 int btrfs_test_free_space_cache(void);
 int btrfs_test_extent_buffer_operations(void);
 int btrfs_test_extent_io(void);
 int btrfs_test_inodes(void);
+int btrfs_test_qgroups(void);
 int btrfs_init_test_fs(void);
 void btrfs_destroy_test_fs(void);
 struct inode *btrfs_new_test_inode(void);
+struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void);
+void btrfs_free_dummy_root(struct btrfs_root *root);
 #else
 static inline int btrfs_test_free_space_cache(void)
 {
@@ -54,6 +59,10 @@ static inline int btrfs_test_inodes(void)
 {
 	return 0;
 }
+static inline int btrfs_test_qgroups(void)
+{
+	return 0;
+}
 #endif
 
 #endif
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 397d1f99a8e..3ae0f5b8bb8 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -23,33 +23,6 @@
 #include "../extent_io.h"
 #include "../volumes.h"
 
-static struct btrfs_fs_info *alloc_dummy_fs_info(void)
-{
-	struct btrfs_fs_info *fs_info = kzalloc(sizeof(struct btrfs_fs_info),
-						GFP_NOFS);
-	if (!fs_info)
-		return fs_info;
-	fs_info->fs_devices = kzalloc(sizeof(struct btrfs_fs_devices),
-				      GFP_NOFS);
-	if (!fs_info->fs_devices) {
-		kfree(fs_info);
-		return NULL;
-	}
-	return fs_info;
-}
-static void free_dummy_root(struct btrfs_root *root)
-{
-	if (!root)
-		return;
-	if (root->fs_info) {
-		kfree(root->fs_info->fs_devices);
-		kfree(root->fs_info);
-	}
-	if (root->node)
-		free_extent_buffer(root->node);
-	kfree(root);
-}
-
 static void insert_extent(struct btrfs_root *root, u64 start, u64 len,
 			  u64 ram_bytes, u64 offset, u64 disk_bytenr,
 			  u64 disk_len, u32 type, u8 compression, int slot)
@@ -276,7 +249,7 @@ static noinline int test_btrfs_get_extent(void)
 	 * We do this since btrfs_get_extent wants to assign em->bdev to
 	 * root->fs_info->fs_devices->latest_bdev.
 	 */
-	root->fs_info = alloc_dummy_fs_info();
+	root->fs_info = btrfs_alloc_dummy_fs_info();
 	if (!root->fs_info) {
 		test_msg("Couldn't allocate dummy fs info\n");
 		goto out;
@@ -837,7 +810,7 @@ out:
 	if (!IS_ERR(em))
 		free_extent_map(em);
 	iput(inode);
-	free_dummy_root(root);
+	btrfs_free_dummy_root(root);
 	return ret;
 }
 
@@ -864,7 +837,7 @@ static int test_hole_first(void)
 		goto out;
 	}
 
-	root->fs_info = alloc_dummy_fs_info();
+	root->fs_info = btrfs_alloc_dummy_fs_info();
 	if (!root->fs_info) {
 		test_msg("Couldn't allocate dummy fs info\n");
 		goto out;
@@ -934,7 +907,7 @@ out:
 	if (!IS_ERR(em))
 		free_extent_map(em);
 	iput(inode);
-	free_dummy_root(root);
+	btrfs_free_dummy_root(root);
 	return ret;
 }
 
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
new file mode 100644
index 00000000000..ec3dcb20235
--- /dev/null
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -0,0 +1,470 @@
+/*
+ * Copyright (C) 2013 Facebook.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include "btrfs-tests.h"
+#include "../ctree.h"
+#include "../transaction.h"
+#include "../disk-io.h"
+#include "../qgroup.h"
+
+static void init_dummy_trans(struct btrfs_trans_handle *trans)
+{
+	memset(trans, 0, sizeof(*trans));
+	trans->transid = 1;
+	INIT_LIST_HEAD(&trans->qgroup_ref_list);
+	trans->type = __TRANS_DUMMY;
+}
+
+static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr,
+				  u64 num_bytes, u64 parent, u64 root_objectid)
+{
+	struct btrfs_trans_handle trans;
+	struct btrfs_extent_item *item;
+	struct btrfs_extent_inline_ref *iref;
+	struct btrfs_tree_block_info *block_info;
+	struct btrfs_path *path;
+	struct extent_buffer *leaf;
+	struct btrfs_key ins;
+	u32 size = sizeof(*item) + sizeof(*iref) + sizeof(*block_info);
+	int ret;
+
+	init_dummy_trans(&trans);
+
+	ins.objectid = bytenr;
+	ins.type = BTRFS_EXTENT_ITEM_KEY;
+	ins.offset = num_bytes;
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		test_msg("Couldn't allocate path\n");
+		return -ENOMEM;
+	}
+
+	path->leave_spinning = 1;
+	ret = btrfs_insert_empty_item(&trans, root, path, &ins, size);
+	if (ret) {
+		test_msg("Couldn't insert ref %d\n", ret);
+		btrfs_free_path(path);
+		return ret;
+	}
+
+	leaf = path->nodes[0];
+	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+	btrfs_set_extent_refs(leaf, item, 1);
+	btrfs_set_extent_generation(leaf, item, 1);
+	btrfs_set_extent_flags(leaf, item, BTRFS_EXTENT_FLAG_TREE_BLOCK);
+	block_info = (struct btrfs_tree_block_info *)(item + 1);
+	btrfs_set_tree_block_level(leaf, block_info, 1);
+	iref = (struct btrfs_extent_inline_ref *)(block_info + 1);
+	if (parent > 0) {
+		btrfs_set_extent_inline_ref_type(leaf, iref,
+						 BTRFS_SHARED_BLOCK_REF_KEY);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
+	} else {
+		btrfs_set_extent_inline_ref_type(leaf, iref, BTRFS_TREE_BLOCK_REF_KEY);
+		btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid);
+	}
+	btrfs_free_path(path);
+	return 0;
+}
+
+static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes,
+			u64 parent, u64 root_objectid)
+{
+	struct btrfs_trans_handle trans;
+	struct btrfs_extent_item *item;
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	u64 refs;
+	int ret;
+
+	init_dummy_trans(&trans);
+
+	key.objectid = bytenr;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = num_bytes;
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		test_msg("Couldn't allocate path\n");
+		return -ENOMEM;
+	}
+
+	path->leave_spinning = 1;
+	ret = btrfs_search_slot(&trans, root, &key, path, 0, 1);
+	if (ret) {
+		test_msg("Couldn't find extent ref\n");
+		btrfs_free_path(path);
+		return ret;
+	}
+
+	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+			      struct btrfs_extent_item);
+	refs = btrfs_extent_refs(path->nodes[0], item);
+	btrfs_set_extent_refs(path->nodes[0], item, refs + 1);
+	btrfs_release_path(path);
+
+	key.objectid = bytenr;
+	if (parent) {
+		key.type = BTRFS_SHARED_BLOCK_REF_KEY;
+		key.offset = parent;
+	} else {
+		key.type = BTRFS_TREE_BLOCK_REF_KEY;
+		key.offset = root_objectid;
+	}
+
+	ret = btrfs_insert_empty_item(&trans, root, path, &key, 0);
+	if (ret)
+		test_msg("Failed to insert backref\n");
+	btrfs_free_path(path);
+	return ret;
+}
+
+static int remove_extent_item(struct btrfs_root *root, u64 bytenr,
+			      u64 num_bytes)
+{
+	struct btrfs_trans_handle trans;
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	int ret;
+
+	init_dummy_trans(&trans);
+
+	key.objectid = bytenr;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = num_bytes;
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		test_msg("Couldn't allocate path\n");
+		return -ENOMEM;
+	}
+	path->leave_spinning = 1;
+
+	ret = btrfs_search_slot(&trans, root, &key, path, -1, 1);
+	if (ret) {
+		test_msg("Didn't find our key %d\n", ret);
+		btrfs_free_path(path);
+		return ret;
+	}
+	btrfs_del_item(&trans, root, path);
+	btrfs_free_path(path);
+	return 0;
+}
+
+static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
+			     u64 num_bytes, u64 parent, u64 root_objectid)
+{
+	struct btrfs_trans_handle trans;
+	struct btrfs_extent_item *item;
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	u64 refs;
+	int ret;
+
+	init_dummy_trans(&trans);
+
+	key.objectid = bytenr;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = num_bytes;
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		test_msg("Couldn't allocate path\n");
+		return -ENOMEM;
+	}
+
+	path->leave_spinning = 1;
+	ret = btrfs_search_slot(&trans, root, &key, path, 0, 1);
+	if (ret) {
+		test_msg("Couldn't find extent ref\n");
+		btrfs_free_path(path);
+		return ret;
+	}
+
+	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+			      struct btrfs_extent_item);
+	refs = btrfs_extent_refs(path->nodes[0], item);
+	btrfs_set_extent_refs(path->nodes[0], item, refs - 1);
+	btrfs_release_path(path);
+
+	key.objectid = bytenr;
+	if (parent) {
+		key.type = BTRFS_SHARED_BLOCK_REF_KEY;
+		key.offset = parent;
+	} else {
+		key.type = BTRFS_TREE_BLOCK_REF_KEY;
+		key.offset = root_objectid;
+	}
+
+	ret = btrfs_search_slot(&trans, root, &key, path, -1, 1);
+	if (ret) {
+		test_msg("Couldn't find backref %d\n", ret);
+		btrfs_free_path(path);
+		return ret;
+	}
+	btrfs_del_item(&trans, root, path);
+	btrfs_free_path(path);
+	return ret;
+}
+
+static int test_no_shared_qgroup(struct btrfs_root *root)
+{
+	struct btrfs_trans_handle trans;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	int ret;
+
+	init_dummy_trans(&trans);
+
+	test_msg("Qgroup basic add\n");
+	ret = btrfs_create_qgroup(NULL, fs_info, 5, NULL);
+	if (ret) {
+		test_msg("Couldn't create a qgroup %d\n", ret);
+		return ret;
+	}
+
+	ret = btrfs_qgroup_record_ref(&trans, fs_info, 5, 4096, 4096,
+				      BTRFS_QGROUP_OPER_ADD_EXCL, 0);
+	if (ret) {
+		test_msg("Couldn't add space to a qgroup %d\n", ret);
+		return ret;
+	}
+
+	ret = insert_normal_tree_ref(root, 4096, 4096, 0, 5);
+	if (ret)
+		return ret;
+
+	ret = btrfs_delayed_qgroup_accounting(&trans, fs_info);
+	if (ret) {
+		test_msg("Delayed qgroup accounting failed %d\n", ret);
+		return ret;
+	}
+
+	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+		test_msg("Qgroup counts didn't match expected values\n");
+		return -EINVAL;
+	}
+
+	ret = remove_extent_item(root, 4096, 4096);
+	if (ret)
+		return -EINVAL;
+
+	ret = btrfs_qgroup_record_ref(&trans, fs_info, 5, 4096, 4096,
+				      BTRFS_QGROUP_OPER_SUB_EXCL, 0);
+	if (ret) {
+		test_msg("Couldn't remove space from the qgroup %d\n", ret);
+		return -EINVAL;
+	}
+
+	ret = btrfs_delayed_qgroup_accounting(&trans, fs_info);
+	if (ret) {
+		test_msg("Qgroup accounting failed %d\n", ret);
+		return -EINVAL;
+	}
+
+	if (btrfs_verify_qgroup_counts(fs_info, 5, 0, 0)) {
+		test_msg("Qgroup counts didn't match expected values\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Add a ref for two different roots to make sure the shared value comes out
+ * right, also remove one of the roots and make sure the exclusive count is
+ * adjusted properly.
+ */
+static int test_multiple_refs(struct btrfs_root *root)
+{
+	struct btrfs_trans_handle trans;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	int ret;
+
+	init_dummy_trans(&trans);
+
+	test_msg("Qgroup multiple refs test\n");
+
+	/* We have 5 created already from the previous test */
+	ret = btrfs_create_qgroup(NULL, fs_info, 256, NULL);
+	if (ret) {
+		test_msg("Couldn't create a qgroup %d\n", ret);
+		return ret;
+	}
+
+	ret = insert_normal_tree_ref(root, 4096, 4096, 0, 5);
+	if (ret)
+		return ret;
+
+	ret = btrfs_qgroup_record_ref(&trans, fs_info, 5, 4096, 4096,
+				      BTRFS_QGROUP_OPER_ADD_EXCL, 0);
+	if (ret) {
+		test_msg("Couldn't add space to a qgroup %d\n", ret);
+		return ret;
+	}
+
+	ret = btrfs_delayed_qgroup_accounting(&trans, fs_info);
+	if (ret) {
+		test_msg("Delayed qgroup accounting failed %d\n", ret);
+		return ret;
+	}
+
+	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+		test_msg("Qgroup counts didn't match expected values\n");
+		return -EINVAL;
+	}
+
+	ret = add_tree_ref(root, 4096, 4096, 0, 256);
+	if (ret)
+		return ret;
+
+	ret = btrfs_qgroup_record_ref(&trans, fs_info, 256, 4096, 4096,
+				      BTRFS_QGROUP_OPER_ADD_SHARED, 0);
+	if (ret) {
+		test_msg("Qgroup record ref failed %d\n", ret);
+		return ret;
+	}
+
+	ret = btrfs_delayed_qgroup_accounting(&trans, fs_info);
+	if (ret) {
+		test_msg("Qgroup accounting failed %d\n", ret);
+		return ret;
+	}
+
+	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 0)) {
+		test_msg("Qgroup counts didn't match expected values\n");
+		return -EINVAL;
+	}
+
+	if (btrfs_verify_qgroup_counts(fs_info, 256, 4096, 0)) {
+		test_msg("Qgroup counts didn't match expected values\n");
+		return -EINVAL;
+	}
+
+	ret = remove_extent_ref(root, 4096, 4096, 0, 256);
+	if (ret)
+		return ret;
+
+	ret = btrfs_qgroup_record_ref(&trans, fs_info, 256, 4096, 4096,
+				      BTRFS_QGROUP_OPER_SUB_SHARED, 0);
+	if (ret) {
+		test_msg("Qgroup record ref failed %d\n", ret);
+		return ret;
+	}
+
+	ret = btrfs_delayed_qgroup_accounting(&trans, fs_info);
+	if (ret) {
+		test_msg("Qgroup accounting failed %d\n", ret);
+		return ret;
+	}
+
+	if (btrfs_verify_qgroup_counts(fs_info, 256, 0, 0)) {
+		test_msg("Qgroup counts didn't match expected values\n");
+		return -EINVAL;
+	}
+
+	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+		test_msg("Qgroup counts didn't match expected values\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int btrfs_test_qgroups(void)
+{
+	struct btrfs_root *root;
+	struct btrfs_root *tmp_root;
+	int ret = 0;
+
+	root = btrfs_alloc_dummy_root();
+	if (IS_ERR(root)) {
+		test_msg("Couldn't allocate root\n");
+		return PTR_ERR(root);
+	}
+
+	root->fs_info = btrfs_alloc_dummy_fs_info();
+	if (!root->fs_info) {
+		test_msg("Couldn't allocate dummy fs info\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * Can't use bytenr 0, some things freak out
+	 * *cough*backref walking code*cough*
+	 */
+	root->node = alloc_test_extent_buffer(root->fs_info, 4096, 4096);
+	if (!root->node) {
+		test_msg("Couldn't allocate dummy buffer\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+	btrfs_set_header_level(root->node, 0);
+	btrfs_set_header_nritems(root->node, 0);
+	root->alloc_bytenr += 8192;
+
+	tmp_root = btrfs_alloc_dummy_root();
+	if (IS_ERR(tmp_root)) {
+		test_msg("Couldn't allocate a fs root\n");
+		ret = PTR_ERR(tmp_root);
+		goto out;
+	}
+
+	tmp_root->root_key.objectid = 5;
+	root->fs_info->fs_root = tmp_root;
+	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
+	if (ret) {
+		test_msg("Couldn't insert fs root %d\n", ret);
+		goto out;
+	}
+
+	tmp_root = btrfs_alloc_dummy_root();
+	if (IS_ERR(tmp_root)) {
+		test_msg("Couldn't allocate a fs root\n");
+		ret = PTR_ERR(tmp_root);
+		goto out;
+	}
+
+	tmp_root->root_key.objectid = 256;
+	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
+	if (ret) {
+		test_msg("Couldn't insert fs root %d\n", ret);
+		goto out;
+	}
+
+	/* We are using this root as our extent root */
+	root->fs_info->extent_root = root;
+
+	/*
+	 * Some of the paths we test assume we have a filled out fs_info, so we
+	 * just need to addt he root in there so we don't panic.
+	 */
+	root->fs_info->tree_root = root;
+	root->fs_info->quota_root = root;
+	root->fs_info->quota_enabled = 1;
+
+	test_msg("Running qgroup tests\n");
+	ret = test_no_shared_qgroup(root);
+	if (ret)
+		goto out;
+	ret = test_multiple_refs(root);
+out:
+	btrfs_free_dummy_root(root);
+	return ret;
+}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 7579f6d0b85..5f379affdf2 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -31,6 +31,7 @@
 #include "inode-map.h"
 #include "volumes.h"
 #include "dev-replace.h"
+#include "qgroup.h"
 
 #define BTRFS_ROOT_TRANS_TAG 0
 
@@ -241,18 +242,19 @@ loop:
 static int record_root_in_trans(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root)
 {
-	if (root->ref_cows && root->last_trans < trans->transid) {
+	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+	    root->last_trans < trans->transid) {
 		WARN_ON(root == root->fs_info->extent_root);
 		WARN_ON(root->commit_root != root->node);
 
 		/*
-		 * see below for in_trans_setup usage rules
+		 * see below for IN_TRANS_SETUP usage rules
 		 * we have the reloc mutex held now, so there
 		 * is only one writer in this function
 		 */
-		root->in_trans_setup = 1;
+		set_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state);
 
-		/* make sure readers find in_trans_setup before
+		/* make sure readers find IN_TRANS_SETUP before
 		 * they find our root->last_trans update
 		 */
 		smp_wmb();
@@ -279,7 +281,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 		 * But, we have to set root->last_trans before we
 		 * init the relocation root, otherwise, we trip over warnings
 		 * in ctree.c.  The solution used here is to flag ourselves
-		 * with root->in_trans_setup.  When this is 1, we're still
+		 * with root IN_TRANS_SETUP.  When this is 1, we're still
 		 * fixing up the reloc trees and everyone must wait.
 		 *
 		 * When this is zero, they can trust root->last_trans and fly
@@ -288,8 +290,8 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 		 * done before we pop in the zero below
 		 */
 		btrfs_init_reloc_root(trans, root);
-		smp_wmb();
-		root->in_trans_setup = 0;
+		smp_mb__before_atomic();
+		clear_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state);
 	}
 	return 0;
 }
@@ -298,16 +300,16 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root)
 {
-	if (!root->ref_cows)
+	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		return 0;
 
 	/*
-	 * see record_root_in_trans for comments about in_trans_setup usage
+	 * see record_root_in_trans for comments about IN_TRANS_SETUP usage
 	 * and barriers
 	 */
 	smp_rmb();
 	if (root->last_trans == trans->transid &&
-	    !root->in_trans_setup)
+	    !test_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state))
 		return 0;
 
 	mutex_lock(&root->fs_info->reloc_mutex);
@@ -365,7 +367,7 @@ static int may_wait_transaction(struct btrfs_root *root, int type)
 static inline bool need_reserve_reloc_root(struct btrfs_root *root)
 {
 	if (!root->fs_info->reloc_ctl ||
-	    !root->ref_cows ||
+	    !test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
 	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
 	    root->reloc_root)
 		return false;
@@ -384,11 +386,13 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type,
 	bool reloc_reserved = false;
 	int ret;
 
+	/* Send isn't supposed to start transactions. */
+	ASSERT(current->journal_info != (void *)BTRFS_SEND_TRANS_STUB);
+
 	if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
 		return ERR_PTR(-EROFS);
 
-	if (current->journal_info &&
-	    current->journal_info != (void *)BTRFS_SEND_TRANS_STUB) {
+	if (current->journal_info) {
 		WARN_ON(type & TRANS_EXTWRITERS);
 		h = current->journal_info;
 		h->use_count++;
@@ -489,6 +493,7 @@ again:
 	smp_mb();
 	if (cur_trans->state >= TRANS_STATE_BLOCKED &&
 	    may_wait_transaction(root, type)) {
+		current->journal_info = h;
 		btrfs_commit_transaction(h, root);
 		goto again;
 	}
@@ -695,6 +700,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	unsigned long cur = trans->delayed_ref_updates;
 	int lock = (trans->type != TRANS_JOIN_NOLOCK);
 	int err = 0;
+	int must_run_delayed_refs = 0;
 
 	if (trans->use_count > 1) {
 		trans->use_count--;
@@ -702,14 +708,27 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 		return 0;
 	}
 
-	/*
-	 * do the qgroup accounting as early as possible
-	 */
-	err = btrfs_delayed_refs_qgroup_accounting(trans, info);
-
 	btrfs_trans_release_metadata(trans, root);
 	trans->block_rsv = NULL;
 
+	if (!list_empty(&trans->new_bgs))
+		btrfs_create_pending_block_groups(trans, root);
+
+	trans->delayed_ref_updates = 0;
+	if (!trans->sync) {
+		must_run_delayed_refs =
+			btrfs_should_throttle_delayed_refs(trans, root);
+		cur = max_t(unsigned long, cur, 32);
+
+		/*
+		 * don't make the caller wait if they are from a NOLOCK
+		 * or ATTACH transaction, it will deadlock with commit
+		 */
+		if (must_run_delayed_refs == 1 &&
+		    (trans->type & (__TRANS_JOIN_NOLOCK | __TRANS_ATTACH)))
+			must_run_delayed_refs = 2;
+	}
+
 	if (trans->qgroup_reserved) {
 		/*
 		 * the same root has to be passed here between start_transaction
@@ -719,16 +738,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 		trans->qgroup_reserved = 0;
 	}
 
-	if (!list_empty(&trans->new_bgs))
-		btrfs_create_pending_block_groups(trans, root);
-
-	trans->delayed_ref_updates = 0;
-	if (!trans->sync && btrfs_should_throttle_delayed_refs(trans, root)) {
-		cur = max_t(unsigned long, cur, 32);
-		trans->delayed_ref_updates = 0;
-		btrfs_run_delayed_refs(trans, root, cur);
-	}
-
 	btrfs_trans_release_metadata(trans, root);
 	trans->block_rsv = NULL;
 
@@ -778,6 +787,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	assert_qgroups_uptodate(trans);
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
+	if (must_run_delayed_refs) {
+		btrfs_async_run_delayed_refs(root, cur,
+					     must_run_delayed_refs == 1);
+	}
 	return err;
 }
 
@@ -1049,8 +1062,8 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
 			btrfs_save_ino_cache(root, trans);
 
 			/* see comments in should_cow_block() */
-			root->force_cow = 0;
-			smp_wmb();
+			clear_bit(BTRFS_ROOT_FORCE_COW, &root->state);
+			smp_mb__after_atomic();
 
 			if (root->commit_root != root->node) {
 				list_add_tail(&root->dirty_list,
@@ -1081,7 +1094,7 @@ int btrfs_defrag_root(struct btrfs_root *root)
 	struct btrfs_trans_handle *trans;
 	int ret;
 
-	if (xchg(&root->defrag_running, 1))
+	if (test_and_set_bit(BTRFS_ROOT_DEFRAG_RUNNING, &root->state))
 		return 0;
 
 	while (1) {
@@ -1104,7 +1117,7 @@ int btrfs_defrag_root(struct btrfs_root *root)
 			break;
 		}
 	}
-	root->defrag_running = 0;
+	clear_bit(BTRFS_ROOT_DEFRAG_RUNNING, &root->state);
 	return ret;
 }
 
@@ -1168,12 +1181,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 			goto no_free_objectid;
 	}
 
-	pending->error = btrfs_qgroup_inherit(trans, fs_info,
-					      root->root_key.objectid,
-					      objectid, pending->inherit);
-	if (pending->error)
-		goto no_free_objectid;
-
 	key.objectid = objectid;
 	key.offset = (u64)-1;
 	key.type = BTRFS_ROOT_ITEM_KEY;
@@ -1270,8 +1277,26 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
+	/*
+	 * We need to flush delayed refs in order to make sure all of our quota
+	 * operations have been done before we call btrfs_qgroup_inherit.
+	 */
+	ret = btrfs_run_delayed_refs(trans, root, (unsigned long)-1);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto fail;
+	}
+
+	ret = btrfs_qgroup_inherit(trans, fs_info,
+				   root->root_key.objectid,
+				   objectid, pending->inherit);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto fail;
+	}
+
 	/* see comments in should_cow_block() */
-	root->force_cow = 1;
+	set_bit(BTRFS_ROOT_FORCE_COW, &root->state);
 	smp_wmb();
 
 	btrfs_set_root_node(new_root_item, tmp);
@@ -1593,17 +1618,6 @@ static int btrfs_flush_all_pending_stuffs(struct btrfs_trans_handle *trans,
 	int ret;
 
 	ret = btrfs_run_delayed_items(trans, root);
-	/*
-	 * running the delayed items may have added new refs. account
-	 * them now so that they hinder processing of more delayed refs
-	 * as little as possible.
-	 */
-	if (ret) {
-		btrfs_delayed_refs_qgroup_accounting(trans, root->fs_info);
-		return ret;
-	}
-
-	ret = btrfs_delayed_refs_qgroup_accounting(trans, root->fs_info);
 	if (ret)
 		return ret;
 
@@ -1984,19 +1998,6 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root)
 	}
 	root = list_first_entry(&fs_info->dead_roots,
 			struct btrfs_root, root_list);
-	/*
-	 * Make sure root is not involved in send,
-	 * if we fail with first root, we return
-	 * directly rather than continue.
-	 */
-	spin_lock(&root->root_item_lock);
-	if (root->send_in_progress) {
-		spin_unlock(&fs_info->trans_lock);
-		spin_unlock(&root->root_item_lock);
-		return 0;
-	}
-	spin_unlock(&root->root_item_lock);
-
 	list_del_init(&root->root_list);
 	spin_unlock(&fs_info->trans_lock);
 
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index b57b924e8e0..7dd558ed071 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -69,6 +69,7 @@ struct btrfs_transaction {
 #define __TRANS_ATTACH		(1U << 10)
 #define __TRANS_JOIN		(1U << 11)
 #define __TRANS_JOIN_NOLOCK	(1U << 12)
+#define __TRANS_DUMMY		(1U << 13)
 
 #define TRANS_USERSPACE		(__TRANS_USERSPACE | __TRANS_FREEZABLE)
 #define TRANS_START		(__TRANS_START | __TRANS_FREEZABLE)
diff --git a/fs/btrfs/tree-defrag.c b/fs/btrfs/tree-defrag.c
index 76928ca9774..a63719cc957 100644
--- a/fs/btrfs/tree-defrag.c
+++ b/fs/btrfs/tree-defrag.c
@@ -49,7 +49,7 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	if (root->ref_cows == 0)
+	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		goto out;
 
 	if (btrfs_test_opt(root, SSD))
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index e2f45fc0261..9e1f2cd5e67 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -20,13 +20,11 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/list_sort.h>
-#include "ctree.h"
-#include "transaction.h"
+#include "tree-log.h"
 #include "disk-io.h"
 #include "locking.h"
 #include "print-tree.h"
 #include "backref.h"
-#include "tree-log.h"
 #include "hash.h"
 
 /* magic values for the inode_only field in btrfs_log_inode:
@@ -144,17 +142,15 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&root->log_mutex);
 	if (root->log_root) {
-		if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) ==
-		    trans->transid) {
+		if (btrfs_need_log_full_commit(root->fs_info, trans)) {
 			ret = -EAGAIN;
 			goto out;
 		}
-
 		if (!root->log_start_pid) {
 			root->log_start_pid = current->pid;
-			root->log_multiple_pids = false;
+			clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
 		} else if (root->log_start_pid != current->pid) {
-			root->log_multiple_pids = true;
+			set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
 		}
 
 		atomic_inc(&root->log_batch);
@@ -181,7 +177,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 		if (ret)
 			goto out;
 	}
-	root->log_multiple_pids = false;
+	clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
 	root->log_start_pid = current->pid;
 	atomic_inc(&root->log_batch);
 	atomic_inc(&root->log_writers);
@@ -2500,7 +2496,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	while (1) {
 		int batch = atomic_read(&root->log_batch);
 		/* when we're on an ssd, just kick the log commit out */
-		if (!btrfs_test_opt(root, SSD) && root->log_multiple_pids) {
+		if (!btrfs_test_opt(root, SSD) &&
+		    test_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state)) {
 			mutex_unlock(&root->log_mutex);
 			schedule_timeout_uninterruptible(1);
 			mutex_lock(&root->log_mutex);
@@ -2511,8 +2508,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	}
 
 	/* bail out if we need to do a full commit */
-	if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) ==
-	    trans->transid) {
+	if (btrfs_need_log_full_commit(root->fs_info, trans)) {
 		ret = -EAGAIN;
 		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&root->log_mutex);
@@ -2533,8 +2529,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		blk_finish_plug(&plug);
 		btrfs_abort_transaction(trans, root, ret);
 		btrfs_free_logged_extents(log, log_transid);
-		ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) =
-								trans->transid;
+		btrfs_set_log_full_commit(root->fs_info, trans);
 		mutex_unlock(&root->log_mutex);
 		goto out;
 	}
@@ -2577,8 +2572,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 			list_del_init(&root_log_ctx.list);
 
 		blk_finish_plug(&plug);
-		ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) =
-								trans->transid;
+		btrfs_set_log_full_commit(root->fs_info, trans);
+
 		if (ret != -ENOSPC) {
 			btrfs_abort_transaction(trans, root, ret);
 			mutex_unlock(&log_root_tree->log_mutex);
@@ -2622,8 +2617,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 * now that we've moved on to the tree of log tree roots,
 	 * check the full commit flag again
 	 */
-	if (ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) ==
-	    trans->transid) {
+	if (btrfs_need_log_full_commit(root->fs_info, trans)) {
 		blk_finish_plug(&plug);
 		btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark);
 		btrfs_free_logged_extents(log, log_transid);
@@ -2637,8 +2631,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 					 EXTENT_DIRTY | EXTENT_NEW);
 	blk_finish_plug(&plug);
 	if (ret) {
-		ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) =
-								trans->transid;
+		btrfs_set_log_full_commit(root->fs_info, trans);
 		btrfs_abort_transaction(trans, root, ret);
 		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
@@ -2667,8 +2660,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 */
 	ret = write_ctree_super(trans, root->fs_info->tree_root, 1);
 	if (ret) {
-		ACCESS_ONCE(root->fs_info->last_trans_log_full_commit) =
-								trans->transid;
+		btrfs_set_log_full_commit(root->fs_info, trans);
 		btrfs_abort_transaction(trans, root, ret);
 		goto out_wake_log_root;
 	}
@@ -2886,7 +2878,7 @@ fail:
 out_unlock:
 	mutex_unlock(&BTRFS_I(dir)->log_mutex);
 	if (ret == -ENOSPC) {
-		root->fs_info->last_trans_log_full_commit = trans->transid;
+		btrfs_set_log_full_commit(root->fs_info, trans);
 		ret = 0;
 	} else if (ret < 0)
 		btrfs_abort_transaction(trans, root, ret);
@@ -2919,7 +2911,7 @@ int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 				  dirid, &index);
 	mutex_unlock(&BTRFS_I(inode)->log_mutex);
 	if (ret == -ENOSPC) {
-		root->fs_info->last_trans_log_full_commit = trans->transid;
+		btrfs_set_log_full_commit(root->fs_info, trans);
 		ret = 0;
 	} else if (ret < 0 && ret != -ENOENT)
 		btrfs_abort_transaction(trans, root, ret);
@@ -4130,8 +4122,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 			 * make sure any commits to the log are forced
 			 * to be full commits
 			 */
-			root->fs_info->last_trans_log_full_commit =
-				trans->transid;
+			btrfs_set_log_full_commit(root->fs_info, trans);
 			ret = 1;
 			break;
 		}
@@ -4177,6 +4168,10 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		goto end_no_trans;
 	}
 
+	/*
+	 * The prev transaction commit doesn't complete, we need do
+	 * full commit by ourselves.
+	 */
 	if (root->fs_info->last_trans_log_full_commit >
 	    root->fs_info->last_trans_committed) {
 		ret = 1;
@@ -4246,7 +4241,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 end_trans:
 	dput(old_parent);
 	if (ret < 0) {
-		root->fs_info->last_trans_log_full_commit = trans->transid;
+		btrfs_set_log_full_commit(root->fs_info, trans);
 		ret = 1;
 	}
 
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 91b145fce33..7f5b41bd537 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -19,6 +19,9 @@
 #ifndef __TREE_LOG_
 #define __TREE_LOG_
 
+#include "ctree.h"
+#include "transaction.h"
+
 /* return value for btrfs_log_dentry_safe that means we don't need to log it at all */
 #define BTRFS_NO_LOG_SYNC 256
 
@@ -35,6 +38,19 @@ static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx)
 	INIT_LIST_HEAD(&ctx->list);
 }
 
+static inline void btrfs_set_log_full_commit(struct btrfs_fs_info *fs_info,
+					     struct btrfs_trans_handle *trans)
+{
+	ACCESS_ONCE(fs_info->last_trans_log_full_commit) = trans->transid;
+}
+
+static inline int btrfs_need_log_full_commit(struct btrfs_fs_info *fs_info,
+					     struct btrfs_trans_handle *trans)
+{
+	return ACCESS_ONCE(fs_info->last_trans_log_full_commit) ==
+		trans->transid;
+}
+
 int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		   struct btrfs_root *root, struct btrfs_log_ctx *ctx);
 int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 49d7fab7336..6cb82f62cb7 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -40,6 +40,7 @@
 #include "rcu-string.h"
 #include "math.h"
 #include "dev-replace.h"
+#include "sysfs.h"
 
 static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
@@ -554,12 +555,14 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		 * This is ok to do without rcu read locked because we hold the
 		 * uuid mutex so nothing we touch in here is going to disappear.
 		 */
-		name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
-		if (!name) {
-			kfree(device);
-			goto error;
+		if (orig_dev->name) {
+			name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
+			if (!name) {
+				kfree(device);
+				goto error;
+			}
+			rcu_assign_pointer(device->name, name);
 		}
-		rcu_assign_pointer(device->name, name);
 
 		list_add(&device->dev_list, &fs_devices->devices);
 		device->fs_devices = fs_devices;
@@ -1452,6 +1455,22 @@ out:
 	return ret;
 }
 
+/*
+ * Function to update ctime/mtime for a given device path.
+ * Mainly used for ctime/mtime based probe like libblkid.
+ */
+static void update_dev_time(char *path_name)
+{
+	struct file *filp;
+
+	filp = filp_open(path_name, O_RDWR, 0);
+	if (!filp)
+		return;
+	file_update_time(filp);
+	filp_close(filp, NULL);
+	return;
+}
+
 static int btrfs_rm_dev_item(struct btrfs_root *root,
 			     struct btrfs_device *device)
 {
@@ -1661,8 +1680,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	if (device->bdev == root->fs_info->fs_devices->latest_bdev)
 		root->fs_info->fs_devices->latest_bdev = next_device->bdev;
 
-	if (device->bdev)
+	if (device->bdev) {
 		device->fs_devices->open_devices--;
+		/* remove sysfs entry */
+		btrfs_kobj_rm_device(root->fs_info, device);
+	}
 
 	call_rcu(&device->rcu, free_device);
 
@@ -1674,11 +1696,12 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		struct btrfs_fs_devices *fs_devices;
 		fs_devices = root->fs_info->fs_devices;
 		while (fs_devices) {
-			if (fs_devices->seed == cur_devices)
+			if (fs_devices->seed == cur_devices) {
+				fs_devices->seed = cur_devices->seed;
 				break;
+			}
 			fs_devices = fs_devices->seed;
 		}
-		fs_devices->seed = cur_devices->seed;
 		cur_devices->seed = NULL;
 		lock_chunks(root);
 		__btrfs_close_devices(cur_devices);
@@ -1694,20 +1717,55 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	 * remove it from the devices list and zero out the old super
 	 */
 	if (clear_super && disk_super) {
+		u64 bytenr;
+		int i;
+
 		/* make sure this device isn't detected as part of
 		 * the FS anymore
 		 */
 		memset(&disk_super->magic, 0, sizeof(disk_super->magic));
 		set_buffer_dirty(bh);
 		sync_dirty_buffer(bh);
+
+		/* clear the mirror copies of super block on the disk
+		 * being removed, 0th copy is been taken care above and
+		 * the below would take of the rest
+		 */
+		for (i = 1; i < BTRFS_SUPER_MIRROR_MAX; i++) {
+			bytenr = btrfs_sb_offset(i);
+			if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+					i_size_read(bdev->bd_inode))
+				break;
+
+			brelse(bh);
+			bh = __bread(bdev, bytenr / 4096,
+					BTRFS_SUPER_INFO_SIZE);
+			if (!bh)
+				continue;
+
+			disk_super = (struct btrfs_super_block *)bh->b_data;
+
+			if (btrfs_super_bytenr(disk_super) != bytenr ||
+				btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
+				continue;
+			}
+			memset(&disk_super->magic, 0,
+						sizeof(disk_super->magic));
+			set_buffer_dirty(bh);
+			sync_dirty_buffer(bh);
+		}
 	}
 
 	ret = 0;
 
-	/* Notify udev that device has changed */
-	if (bdev)
+	if (bdev) {
+		/* Notify udev that device has changed */
 		btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
 
+		/* Update ctime/mtime for device path for libblkid */
+		update_dev_time(device_path);
+	}
+
 error_brelse:
 	brelse(bh);
 	if (bdev)
@@ -1883,7 +1941,6 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
 	fs_devices->seeding = 0;
 	fs_devices->num_devices = 0;
 	fs_devices->open_devices = 0;
-	fs_devices->total_devices = 0;
 	fs_devices->seed = seed_devices;
 
 	generate_random_uuid(fs_devices->fsid);
@@ -2092,9 +2149,14 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	total_bytes = btrfs_super_num_devices(root->fs_info->super_copy);
 	btrfs_set_super_num_devices(root->fs_info->super_copy,
 				    total_bytes + 1);
+
+	/* add sysfs device entry */
+	btrfs_kobj_add_device(root->fs_info, device);
+
 	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
 	if (seeding_dev) {
+		char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
 		ret = init_first_rw_device(trans, root, device);
 		if (ret) {
 			btrfs_abort_transaction(trans, root, ret);
@@ -2105,6 +2167,14 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 			btrfs_abort_transaction(trans, root, ret);
 			goto error_trans;
 		}
+
+		/* Sprouting would change fsid of the mounted root,
+		 * so rename the fsid on the sysfs
+		 */
+		snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU",
+						root->fs_info->fsid);
+		if (kobject_rename(&root->fs_info->super_kobj, fsid_buf))
+			goto error_trans;
 	} else {
 		ret = btrfs_add_device(trans, root, device);
 		if (ret) {
@@ -2146,12 +2216,15 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 		ret = btrfs_commit_transaction(trans, root);
 	}
 
+	/* Update ctime/mtime for libblkid */
+	update_dev_time(device_path);
 	return ret;
 
 error_trans:
 	unlock_chunks(root);
 	btrfs_end_transaction(trans, root);
 	rcu_string_free(device->name);
+	btrfs_kobj_rm_device(root->fs_info, device);
 	kfree(device);
 error:
 	blkdev_put(bdev, FMODE_EXCL);
@@ -2490,9 +2563,6 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
 	remove_extent_mapping(em_tree, em);
 	write_unlock(&em_tree->lock);
 
-	kfree(map);
-	em->bdev = NULL;
-
 	/* once for the tree */
 	free_extent_map(em);
 	/* once for us */
@@ -2922,6 +2992,16 @@ static int should_balance_chunk(struct btrfs_root *root,
 		return 0;
 	}
 
+	/*
+	 * limited by count, must be the last filter
+	 */
+	if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT)) {
+		if (bargs->limit == 0)
+			return 0;
+		else
+			bargs->limit--;
+	}
+
 	return 1;
 }
 
@@ -2944,6 +3024,9 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	int ret;
 	int enospc_errors = 0;
 	bool counting = true;
+	u64 limit_data = bctl->data.limit;
+	u64 limit_meta = bctl->meta.limit;
+	u64 limit_sys = bctl->sys.limit;
 
 	/* step one make some room on all the devices */
 	devices = &fs_info->fs_devices->devices;
@@ -2982,6 +3065,11 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	memset(&bctl->stat, 0, sizeof(bctl->stat));
 	spin_unlock(&fs_info->balance_lock);
 again:
+	if (!counting) {
+		bctl->data.limit = limit_data;
+		bctl->meta.limit = limit_meta;
+		bctl->sys.limit = limit_sys;
+	}
 	key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
 	key.offset = (u64)-1;
 	key.type = BTRFS_CHUNK_ITEM_KEY;
@@ -3881,7 +3969,8 @@ static int btrfs_add_system_chunk(struct btrfs_root *root,
 	u8 *ptr;
 
 	array_size = btrfs_super_sys_array_size(super_copy);
-	if (array_size + item_size > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE)
+	if (array_size + item_size + sizeof(disk_key)
+			> BTRFS_SYSTEM_CHUNK_ARRAY_SIZE)
 		return -EFBIG;
 
 	ptr = super_copy->sys_chunk_array + array_size;
@@ -3986,6 +4075,16 @@ static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
 	btrfs_set_fs_incompat(info, RAID56);
 }
 
+#define BTRFS_MAX_DEVS(r) ((BTRFS_LEAF_DATA_SIZE(r)		\
+			- sizeof(struct btrfs_item)		\
+			- sizeof(struct btrfs_chunk))		\
+			/ sizeof(struct btrfs_stripe) + 1)
+
+#define BTRFS_MAX_DEVS_SYS_CHUNK ((BTRFS_SYSTEM_CHUNK_ARRAY_SIZE	\
+				- 2 * sizeof(struct btrfs_disk_key)	\
+				- 2 * sizeof(struct btrfs_chunk))	\
+				/ sizeof(struct btrfs_stripe) + 1)
+
 static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *extent_root, u64 start,
 			       u64 type)
@@ -4035,6 +4134,8 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
 		max_stripe_size = 1024 * 1024 * 1024;
 		max_chunk_size = 10 * max_stripe_size;
+		if (!devs_max)
+			devs_max = BTRFS_MAX_DEVS(info->chunk_root);
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
 		/* for larger filesystems, use larger metadata chunks */
 		if (fs_devices->total_rw_bytes > 50ULL * 1024 * 1024 * 1024)
@@ -4042,11 +4143,15 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 		else
 			max_stripe_size = 256 * 1024 * 1024;
 		max_chunk_size = max_stripe_size;
+		if (!devs_max)
+			devs_max = BTRFS_MAX_DEVS(info->chunk_root);
 	} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
 		max_stripe_size = 32 * 1024 * 1024;
 		max_chunk_size = 2 * max_stripe_size;
+		if (!devs_max)
+			devs_max = BTRFS_MAX_DEVS_SYS_CHUNK;
 	} else {
-		btrfs_err(info, "invalid chunk type 0x%llx requested\n",
+		btrfs_err(info, "invalid chunk type 0x%llx requested",
 		       type);
 		BUG_ON(1);
 	}
@@ -4213,9 +4318,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	em = alloc_extent_map();
 	if (!em) {
+		kfree(map);
 		ret = -ENOMEM;
 		goto error;
 	}
+	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
 	em->bdev = (struct block_device *)map;
 	em->start = start;
 	em->len = num_bytes;
@@ -4258,7 +4365,6 @@ error_del_extent:
 	/* One for the tree reference */
 	free_extent_map(em);
 error:
-	kfree(map);
 	kfree(devices_info);
 	return ret;
 }
@@ -4294,7 +4400,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 
 	if (em->start != chunk_offset || em->len != chunk_size) {
 		btrfs_crit(extent_root->fs_info, "found a bad mapping, wanted"
-			  " %Lu-%Lu, found %Lu-%Lu\n", chunk_offset,
+			  " %Lu-%Lu, found %Lu-%Lu", chunk_offset,
 			  chunk_size, em->start, em->len);
 		free_extent_map(em);
 		return -EINVAL;
@@ -4470,7 +4576,6 @@ void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree)
 		write_unlock(&tree->map_tree.lock);
 		if (!em)
 			break;
-		kfree(em->bdev);
 		/* once for us */
 		free_extent_map(em);
 		/* once for the tree */
@@ -4496,14 +4601,14 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 	 * and exit, so return 1 so the callers don't try to use other copies.
 	 */
 	if (!em) {
-		btrfs_crit(fs_info, "No mapping for %Lu-%Lu\n", logical,
+		btrfs_crit(fs_info, "No mapping for %Lu-%Lu", logical,
 			    logical+len);
 		return 1;
 	}
 
 	if (em->start > logical || em->start + em->len < logical) {
 		btrfs_crit(fs_info, "Invalid mapping for %Lu-%Lu, got "
-			    "%Lu-%Lu\n", logical, logical+len, em->start,
+			    "%Lu-%Lu", logical, logical+len, em->start,
 			    em->start + em->len);
 		free_extent_map(em);
 		return 1;
@@ -4684,7 +4789,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 
 	if (em->start > logical || em->start + em->len < logical) {
 		btrfs_crit(fs_info, "found a bad mapping, wanted %Lu, "
-			   "found %Lu-%Lu\n", logical, em->start,
+			   "found %Lu-%Lu", logical, em->start,
 			   em->start + em->len);
 		free_extent_map(em);
 		return -EINVAL;
@@ -5274,6 +5379,15 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 	return 0;
 }
 
+static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio, int err)
+{
+	if (likely(bbio->flags & BTRFS_BIO_ORIG_BIO_SUBMITTED))
+		bio_endio_nodec(bio, err);
+	else
+		bio_endio(bio, err);
+	kfree(bbio);
+}
+
 static void btrfs_end_bio(struct bio *bio, int err)
 {
 	struct btrfs_bio *bbio = bio->bi_private;
@@ -5314,12 +5428,6 @@ static void btrfs_end_bio(struct bio *bio, int err)
 			bio = bbio->orig_bio;
 		}
 
- 		/*
-		 * We have original bio now. So increment bi_remaining to
-		 * account for it in endio
-		 */
-		atomic_inc(&bio->bi_remaining);
-
 		bio->bi_private = bbio->private;
 		bio->bi_end_io = bbio->end_io;
 		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
@@ -5336,9 +5444,8 @@ static void btrfs_end_bio(struct bio *bio, int err)
 			set_bit(BIO_UPTODATE, &bio->bi_flags);
 			err = 0;
 		}
-		kfree(bbio);
 
-		bio_endio(bio, err);
+		btrfs_end_bbio(bbio, bio, err);
 	} else if (!is_orig_bio) {
 		bio_put(bio);
 	}
@@ -5501,12 +5608,15 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
 {
 	atomic_inc(&bbio->error);
 	if (atomic_dec_and_test(&bbio->stripes_pending)) {
+		/* Shoud be the original bio. */
+		WARN_ON(bio != bbio->orig_bio);
+
 		bio->bi_private = bbio->private;
 		bio->bi_end_io = bbio->end_io;
 		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
 		bio->bi_iter.bi_sector = logical >> 9;
-		kfree(bbio);
-		bio_endio(bio, -EIO);
+
+		btrfs_end_bbio(bbio, bio, -EIO);
 	}
 }
 
@@ -5593,6 +5703,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
 			BUG_ON(!bio); /* -ENOMEM */
 		} else {
 			bio = first_bio;
+			bbio->flags |= BTRFS_BIO_ORIG_BIO_SUBMITTED;
 		}
 
 		submit_stripe_bio(root, bbio, bio,
@@ -5734,6 +5845,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 		return -ENOMEM;
 	}
 
+	set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
 	em->bdev = (struct block_device *)map;
 	em->start = logical;
 	em->len = length;
@@ -5758,7 +5870,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 		map->stripes[i].dev = btrfs_find_device(root->fs_info, devid,
 							uuid, NULL);
 		if (!map->stripes[i].dev && !btrfs_test_opt(root, DEGRADED)) {
-			kfree(map);
 			free_extent_map(em);
 			return -EIO;
 		}
@@ -5766,7 +5877,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 			map->stripes[i].dev =
 				add_missing_dev(root, devid, uuid);
 			if (!map->stripes[i].dev) {
-				kfree(map);
 				free_extent_map(em);
 				return -EIO;
 			}
@@ -6058,10 +6168,14 @@ void btrfs_init_devices_late(struct btrfs_fs_info *fs_info)
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
 
-	mutex_lock(&fs_devices->device_list_mutex);
-	list_for_each_entry(device, &fs_devices->devices, dev_list)
-		device->dev_root = fs_info->dev_root;
-	mutex_unlock(&fs_devices->device_list_mutex);
+	while (fs_devices) {
+		mutex_lock(&fs_devices->device_list_mutex);
+		list_for_each_entry(device, &fs_devices->devices, dev_list)
+			device->dev_root = fs_info->dev_root;
+		mutex_unlock(&fs_devices->device_list_mutex);
+
+		fs_devices = fs_devices->seed;
+	}
 }
 
 static void __btrfs_reset_dev_stats(struct btrfs_device *dev)
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 80754f9dd3d..2aaa00c4781 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -190,11 +190,14 @@ struct btrfs_bio_stripe {
 struct btrfs_bio;
 typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
 
+#define BTRFS_BIO_ORIG_BIO_SUBMITTED	0x1
+
 struct btrfs_bio {
 	atomic_t stripes_pending;
 	struct btrfs_fs_info *fs_info;
 	bio_end_io_t *end_io;
 	struct bio *orig_bio;
+	unsigned long flags;
 	void *private;
 	atomic_t error;
 	int max_errors;
@@ -255,6 +258,7 @@ struct map_lookup {
 #define BTRFS_BALANCE_ARGS_DEVID	(1ULL << 2)
 #define BTRFS_BALANCE_ARGS_DRANGE	(1ULL << 3)
 #define BTRFS_BALANCE_ARGS_VRANGE	(1ULL << 4)
+#define BTRFS_BALANCE_ARGS_LIMIT	(1ULL << 5)
 
 /*
  * Profile changing flags.  When SOFT is set we won't relocate chunk if
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 8e57191950c..b67d8fc8127 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -98,7 +98,7 @@ static int zlib_compress_pages(struct list_head *ws,
 
 	if (Z_OK != zlib_deflateInit(&workspace->def_strm, 3)) {
 		printk(KERN_WARNING "BTRFS: deflateInit failed\n");
-		ret = -1;
+		ret = -EIO;
 		goto out;
 	}
 
@@ -110,7 +110,7 @@ static int zlib_compress_pages(struct list_head *ws,
 
 	out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
 	if (out_page == NULL) {
-		ret = -1;
+		ret = -ENOMEM;
 		goto out;
 	}
 	cpage_out = kmap(out_page);
@@ -128,7 +128,7 @@ static int zlib_compress_pages(struct list_head *ws,
 			printk(KERN_DEBUG "BTRFS: deflate in loop returned %d\n",
 			       ret);
 			zlib_deflateEnd(&workspace->def_strm);
-			ret = -1;
+			ret = -EIO;
 			goto out;
 		}
 
@@ -136,7 +136,7 @@ static int zlib_compress_pages(struct list_head *ws,
 		if (workspace->def_strm.total_in > 8192 &&
 		    workspace->def_strm.total_in <
 		    workspace->def_strm.total_out) {
-			ret = -1;
+			ret = -E2BIG;
 			goto out;
 		}
 		/* we need another page for writing out.  Test this
@@ -147,12 +147,12 @@ static int zlib_compress_pages(struct list_head *ws,
 			kunmap(out_page);
 			if (nr_pages == nr_dest_pages) {
 				out_page = NULL;
-				ret = -1;
+				ret = -E2BIG;
 				goto out;
 			}
 			out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
 			if (out_page == NULL) {
-				ret = -1;
+				ret = -ENOMEM;
 				goto out;
 			}
 			cpage_out = kmap(out_page);
@@ -188,12 +188,12 @@ static int zlib_compress_pages(struct list_head *ws,
 	zlib_deflateEnd(&workspace->def_strm);
 
 	if (ret != Z_STREAM_END) {
-		ret = -1;
+		ret = -EIO;
 		goto out;
 	}
 
 	if (workspace->def_strm.total_out >= workspace->def_strm.total_in) {
-		ret = -1;
+		ret = -E2BIG;
 		goto out;
 	}
 
@@ -253,7 +253,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 
 	if (Z_OK != zlib_inflateInit2(&workspace->inf_strm, wbits)) {
 		printk(KERN_WARNING "BTRFS: inflateInit failed\n");
-		return -1;
+		return -EIO;
 	}
 	while (workspace->inf_strm.total_in < srclen) {
 		ret = zlib_inflate(&workspace->inf_strm, Z_NO_FLUSH);
@@ -295,7 +295,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 		}
 	}
 	if (ret != Z_STREAM_END)
-		ret = -1;
+		ret = -EIO;
 	else
 		ret = 0;
 done:
@@ -337,7 +337,7 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 
 	if (Z_OK != zlib_inflateInit2(&workspace->inf_strm, wbits)) {
 		printk(KERN_WARNING "BTRFS: inflateInit failed\n");
-		return -1;
+		return -EIO;
 	}
 
 	while (bytes_left > 0) {
@@ -354,7 +354,7 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 		total_out = workspace->inf_strm.total_out;
 
 		if (total_out == buf_start) {
-			ret = -1;
+			ret = -EIO;
 			break;
 		}
 
@@ -382,7 +382,7 @@ next:
 	}
 
 	if (ret != Z_STREAM_END && bytes_left != 0)
-		ret = -1;
+		ret = -EIO;
 	else
 		ret = 0;
 
diff --git a/fs/buffer.c b/fs/buffer.c
index eba6e4f621c..8f05111bbb8 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -61,16 +61,9 @@ inline void touch_buffer(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(touch_buffer);
 
-static int sleep_on_buffer(void *word)
-{
-	io_schedule();
-	return 0;
-}
-
 void __lock_buffer(struct buffer_head *bh)
 {
-	wait_on_bit_lock(&bh->b_state, BH_Lock, sleep_on_buffer,
-							TASK_UNINTERRUPTIBLE);
+	wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_buffer);
 
@@ -123,7 +116,7 @@ EXPORT_SYMBOL(buffer_check_dirty_writeback);
  */
 void __wait_on_buffer(struct buffer_head * bh)
 {
-	wait_on_bit(&bh->b_state, BH_Lock, sleep_on_buffer, TASK_UNINTERRUPTIBLE);
+	wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__wait_on_buffer);
 
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 21887d63dad..469f2e8657e 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -104,12 +104,6 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
 	struct dentry *dentry;
 
-	if (acl) {
-		ret = posix_acl_valid(acl);
-		if (ret < 0)
-			goto out;
-	}
-
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = POSIX_ACL_XATTR_ACCESS;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 65a30e817dd..90b3954d48e 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -211,18 +211,15 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 		SetPageError(page);
 		ceph_fscache_readpage_cancel(inode, page);
 		goto out;
-	} else {
-		if (err < PAGE_CACHE_SIZE) {
-		/* zero fill remainder of page */
-			zero_user_segment(page, err, PAGE_CACHE_SIZE);
-		} else {
-			flush_dcache_page(page);
-		}
 	}
-	SetPageUptodate(page);
+	if (err < PAGE_CACHE_SIZE)
+		/* zero fill remainder of page */
+		zero_user_segment(page, err, PAGE_CACHE_SIZE);
+	else
+		flush_dcache_page(page);
 
-	if (err >= 0)
-		ceph_readpage_to_fscache(inode, page);
+	SetPageUptodate(page);
+	ceph_readpage_to_fscache(inode, page);
 
 out:
 	return err < 0 ? err : 0;
@@ -1187,8 +1184,8 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
  * never get called.
  */
 static ssize_t ceph_direct_io(int rw, struct kiocb *iocb,
-			      const struct iovec *iov,
-			      loff_t pos, unsigned long nr_segs)
+			      struct iov_iter *iter,
+			      loff_t pos)
 {
 	WARN_ON(1);
 	return -EINVAL;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index c561b628ebc..1fde164b74b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -221,8 +221,8 @@ int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
 	return 0;
 }
 
-static struct ceph_cap *get_cap(struct ceph_mds_client *mdsc,
-				struct ceph_cap_reservation *ctx)
+struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+			      struct ceph_cap_reservation *ctx)
 {
 	struct ceph_cap *cap = NULL;
 
@@ -508,15 +508,14 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
  * it is < 0.  (This is so we can atomically add the cap and add an
  * open file reference to it.)
  */
-int ceph_add_cap(struct inode *inode,
-		 struct ceph_mds_session *session, u64 cap_id,
-		 int fmode, unsigned issued, unsigned wanted,
-		 unsigned seq, unsigned mseq, u64 realmino, int flags,
-		 struct ceph_cap_reservation *caps_reservation)
+void ceph_add_cap(struct inode *inode,
+		  struct ceph_mds_session *session, u64 cap_id,
+		  int fmode, unsigned issued, unsigned wanted,
+		  unsigned seq, unsigned mseq, u64 realmino, int flags,
+		  struct ceph_cap **new_cap)
 {
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_cap *new_cap = NULL;
 	struct ceph_cap *cap;
 	int mds = session->s_mds;
 	int actual_wanted;
@@ -531,20 +530,10 @@ int ceph_add_cap(struct inode *inode,
 	if (fmode >= 0)
 		wanted |= ceph_caps_for_mode(fmode);
 
-retry:
-	spin_lock(&ci->i_ceph_lock);
 	cap = __get_cap_for_mds(ci, mds);
 	if (!cap) {
-		if (new_cap) {
-			cap = new_cap;
-			new_cap = NULL;
-		} else {
-			spin_unlock(&ci->i_ceph_lock);
-			new_cap = get_cap(mdsc, caps_reservation);
-			if (new_cap == NULL)
-				return -ENOMEM;
-			goto retry;
-		}
+		cap = *new_cap;
+		*new_cap = NULL;
 
 		cap->issued = 0;
 		cap->implemented = 0;
@@ -562,9 +551,6 @@ retry:
 		session->s_nr_caps++;
 		spin_unlock(&session->s_cap_lock);
 	} else {
-		if (new_cap)
-			ceph_put_cap(mdsc, new_cap);
-
 		/*
 		 * auth mds of the inode changed. we received the cap export
 		 * message, but still haven't received the cap import message.
@@ -626,7 +612,6 @@ retry:
 			ci->i_auth_cap = cap;
 			cap->mds_wanted = wanted;
 		}
-		ci->i_cap_exporting_issued = 0;
 	} else {
 		WARN_ON(ci->i_auth_cap == cap);
 	}
@@ -648,9 +633,6 @@ retry:
 
 	if (fmode >= 0)
 		__ceph_get_fmode(ci, fmode);
-	spin_unlock(&ci->i_ceph_lock);
-	wake_up_all(&ci->i_cap_wq);
-	return 0;
 }
 
 /*
@@ -685,7 +667,7 @@ static int __cap_is_valid(struct ceph_cap *cap)
  */
 int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
 {
-	int have = ci->i_snap_caps | ci->i_cap_exporting_issued;
+	int have = ci->i_snap_caps;
 	struct ceph_cap *cap;
 	struct rb_node *p;
 
@@ -900,7 +882,7 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci)
  */
 static int __ceph_is_any_caps(struct ceph_inode_info *ci)
 {
-	return !RB_EMPTY_ROOT(&ci->i_caps) || ci->i_cap_exporting_issued;
+	return !RB_EMPTY_ROOT(&ci->i_caps);
 }
 
 int ceph_is_any_caps(struct inode *inode)
@@ -2397,32 +2379,30 @@ static void invalidate_aliases(struct inode *inode)
  * actually be a revocation if it specifies a smaller cap set.)
  *
  * caller holds s_mutex and i_ceph_lock, we drop both.
- *
- * return value:
- *  0 - ok
- *  1 - check_caps on auth cap only (writeback)
- *  2 - check_caps (ack revoke)
  */
-static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
+static void handle_cap_grant(struct ceph_mds_client *mdsc,
+			     struct inode *inode, struct ceph_mds_caps *grant,
+			     void *snaptrace, int snaptrace_len,
+			     struct ceph_buffer *xattr_buf,
 			     struct ceph_mds_session *session,
-			     struct ceph_cap *cap,
-			     struct ceph_buffer *xattr_buf)
-		__releases(ci->i_ceph_lock)
+			     struct ceph_cap *cap, int issued)
+	__releases(ci->i_ceph_lock)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int mds = session->s_mds;
 	int seq = le32_to_cpu(grant->seq);
 	int newcaps = le32_to_cpu(grant->caps);
-	int issued, implemented, used, wanted, dirty;
+	int used, wanted, dirty;
 	u64 size = le64_to_cpu(grant->size);
 	u64 max_size = le64_to_cpu(grant->max_size);
 	struct timespec mtime, atime, ctime;
 	int check_caps = 0;
-	int wake = 0;
-	int writeback = 0;
-	int queue_invalidate = 0;
-	int deleted_inode = 0;
-	int queue_revalidate = 0;
+	bool wake = 0;
+	bool writeback = 0;
+	bool queue_trunc = 0;
+	bool queue_invalidate = 0;
+	bool queue_revalidate = 0;
+	bool deleted_inode = 0;
 
 	dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
 	     inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2466,16 +2446,13 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 	}
 
 	/* side effects now are allowed */
-
-	issued = __ceph_caps_issued(ci, &implemented);
-	issued |= implemented | __ceph_caps_dirty(ci);
-
 	cap->cap_gen = session->s_cap_gen;
 	cap->seq = seq;
 
 	__check_cap_issue(ci, cap, newcaps);
 
-	if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+	if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+	    (issued & CEPH_CAP_AUTH_EXCL) == 0) {
 		inode->i_mode = le32_to_cpu(grant->mode);
 		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
 		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
@@ -2484,7 +2461,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 		     from_kgid(&init_user_ns, inode->i_gid));
 	}
 
-	if ((issued & CEPH_CAP_LINK_EXCL) == 0) {
+	if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+	    (issued & CEPH_CAP_LINK_EXCL) == 0) {
 		set_nlink(inode, le32_to_cpu(grant->nlink));
 		if (inode->i_nlink == 0 &&
 		    (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
@@ -2511,30 +2489,35 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 	if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
 		queue_revalidate = 1;
 
-	/* size/ctime/mtime/atime? */
-	ceph_fill_file_size(inode, issued,
-			    le32_to_cpu(grant->truncate_seq),
-			    le64_to_cpu(grant->truncate_size), size);
-	ceph_decode_timespec(&mtime, &grant->mtime);
-	ceph_decode_timespec(&atime, &grant->atime);
-	ceph_decode_timespec(&ctime, &grant->ctime);
-	ceph_fill_file_time(inode, issued,
-			    le32_to_cpu(grant->time_warp_seq), &ctime, &mtime,
-			    &atime);
-
-
-	/* file layout may have changed */
-	ci->i_layout = grant->layout;
-
-	/* max size increase? */
-	if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
-		dout("max_size %lld -> %llu\n", ci->i_max_size, max_size);
-		ci->i_max_size = max_size;
-		if (max_size >= ci->i_wanted_max_size) {
-			ci->i_wanted_max_size = 0;  /* reset */
-			ci->i_requested_max_size = 0;
+	if (newcaps & CEPH_CAP_ANY_RD) {
+		/* ctime/mtime/atime? */
+		ceph_decode_timespec(&mtime, &grant->mtime);
+		ceph_decode_timespec(&atime, &grant->atime);
+		ceph_decode_timespec(&ctime, &grant->ctime);
+		ceph_fill_file_time(inode, issued,
+				    le32_to_cpu(grant->time_warp_seq),
+				    &ctime, &mtime, &atime);
+	}
+
+	if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
+		/* file layout may have changed */
+		ci->i_layout = grant->layout;
+		/* size/truncate_seq? */
+		queue_trunc = ceph_fill_file_size(inode, issued,
+					le32_to_cpu(grant->truncate_seq),
+					le64_to_cpu(grant->truncate_size),
+					size);
+		/* max size increase? */
+		if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
+			dout("max_size %lld -> %llu\n",
+			     ci->i_max_size, max_size);
+			ci->i_max_size = max_size;
+			if (max_size >= ci->i_wanted_max_size) {
+				ci->i_wanted_max_size = 0;  /* reset */
+				ci->i_requested_max_size = 0;
+			}
+			wake = 1;
 		}
-		wake = 1;
 	}
 
 	/* check cap bits */
@@ -2595,6 +2578,23 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 
 	spin_unlock(&ci->i_ceph_lock);
 
+	if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
+		down_write(&mdsc->snap_rwsem);
+		ceph_update_snap_trace(mdsc, snaptrace,
+				       snaptrace + snaptrace_len, false);
+		downgrade_write(&mdsc->snap_rwsem);
+		kick_flushing_inode_caps(mdsc, session, inode);
+		up_read(&mdsc->snap_rwsem);
+		if (newcaps & ~issued)
+			wake = 1;
+	}
+
+	if (queue_trunc) {
+		ceph_queue_vmtruncate(inode);
+		ceph_queue_revalidate(inode);
+	} else if (queue_revalidate)
+		ceph_queue_revalidate(inode);
+
 	if (writeback)
 		/*
 		 * queue inode for writeback: we can't actually call
@@ -2606,8 +2606,6 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
 		ceph_queue_invalidate(inode);
 	if (deleted_inode)
 		invalidate_aliases(inode);
-	if (queue_revalidate)
-		ceph_queue_revalidate(inode);
 	if (wake)
 		wake_up_all(&ci->i_cap_wq);
 
@@ -2784,7 +2782,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
 {
 	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_mds_session *tsession = NULL;
-	struct ceph_cap *cap, *tcap;
+	struct ceph_cap *cap, *tcap, *new_cap = NULL;
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	u64 t_cap_id;
 	unsigned mseq = le32_to_cpu(ex->migrate_seq);
@@ -2807,7 +2805,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
 retry:
 	spin_lock(&ci->i_ceph_lock);
 	cap = __get_cap_for_mds(ci, mds);
-	if (!cap)
+	if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id))
 		goto out_unlock;
 
 	if (target < 0) {
@@ -2846,15 +2844,14 @@ retry:
 		}
 		__ceph_remove_cap(cap, false);
 		goto out_unlock;
-	}
-
-	if (tsession) {
-		int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
-		spin_unlock(&ci->i_ceph_lock);
+	} else if (tsession) {
 		/* add placeholder for the export tagert */
+		int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
 		ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0,
-			     t_seq - 1, t_mseq, (u64)-1, flag, NULL);
-		goto retry;
+			     t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
+
+		__ceph_remove_cap(cap, false);
+		goto out_unlock;
 	}
 
 	spin_unlock(&ci->i_ceph_lock);
@@ -2873,6 +2870,7 @@ retry:
 					  SINGLE_DEPTH_NESTING);
 		}
 		ceph_add_cap_releases(mdsc, tsession);
+		new_cap = ceph_get_cap(mdsc, NULL);
 	} else {
 		WARN_ON(1);
 		tsession = NULL;
@@ -2887,24 +2885,27 @@ out_unlock:
 		mutex_unlock(&tsession->s_mutex);
 		ceph_put_mds_session(tsession);
 	}
+	if (new_cap)
+		ceph_put_cap(mdsc, new_cap);
 }
 
 /*
- * Handle cap IMPORT.  If there are temp bits from an older EXPORT,
- * clean them up.
+ * Handle cap IMPORT.
  *
- * caller holds s_mutex.
+ * caller holds s_mutex. acquires i_ceph_lock
  */
 static void handle_cap_import(struct ceph_mds_client *mdsc,
 			      struct inode *inode, struct ceph_mds_caps *im,
 			      struct ceph_mds_cap_peer *ph,
 			      struct ceph_mds_session *session,
-			      void *snaptrace, int snaptrace_len)
+			      struct ceph_cap **target_cap, int *old_issued)
+	__acquires(ci->i_ceph_lock)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct ceph_cap *cap;
+	struct ceph_cap *cap, *ocap, *new_cap = NULL;
 	int mds = session->s_mds;
-	unsigned issued = le32_to_cpu(im->caps);
+	int issued;
+	unsigned caps = le32_to_cpu(im->caps);
 	unsigned wanted = le32_to_cpu(im->wanted);
 	unsigned seq = le32_to_cpu(im->seq);
 	unsigned mseq = le32_to_cpu(im->migrate_seq);
@@ -2924,40 +2925,52 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
 	dout("handle_cap_import inode %p ci %p mds%d mseq %d peer %d\n",
 	     inode, ci, mds, mseq, peer);
 
+retry:
 	spin_lock(&ci->i_ceph_lock);
-	cap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
-	if (cap && cap->cap_id == p_cap_id) {
+	cap = __get_cap_for_mds(ci, mds);
+	if (!cap) {
+		if (!new_cap) {
+			spin_unlock(&ci->i_ceph_lock);
+			new_cap = ceph_get_cap(mdsc, NULL);
+			goto retry;
+		}
+		cap = new_cap;
+	} else {
+		if (new_cap) {
+			ceph_put_cap(mdsc, new_cap);
+			new_cap = NULL;
+		}
+	}
+
+	__ceph_caps_issued(ci, &issued);
+	issued |= __ceph_caps_dirty(ci);
+
+	ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq,
+		     realmino, CEPH_CAP_FLAG_AUTH, &new_cap);
+
+	ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
+	if (ocap && ocap->cap_id == p_cap_id) {
 		dout(" remove export cap %p mds%d flags %d\n",
-		     cap, peer, ph->flags);
+		     ocap, peer, ph->flags);
 		if ((ph->flags & CEPH_CAP_FLAG_AUTH) &&
-		    (cap->seq != le32_to_cpu(ph->seq) ||
-		     cap->mseq != le32_to_cpu(ph->mseq))) {
+		    (ocap->seq != le32_to_cpu(ph->seq) ||
+		     ocap->mseq != le32_to_cpu(ph->mseq))) {
 			pr_err("handle_cap_import: mismatched seq/mseq: "
 			       "ino (%llx.%llx) mds%d seq %d mseq %d "
 			       "importer mds%d has peer seq %d mseq %d\n",
-			       ceph_vinop(inode), peer, cap->seq,
-			       cap->mseq, mds, le32_to_cpu(ph->seq),
+			       ceph_vinop(inode), peer, ocap->seq,
+			       ocap->mseq, mds, le32_to_cpu(ph->seq),
 			       le32_to_cpu(ph->mseq));
 		}
-		ci->i_cap_exporting_issued = cap->issued;
-		__ceph_remove_cap(cap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
+		__ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
 	}
 
 	/* make sure we re-request max_size, if necessary */
 	ci->i_wanted_max_size = 0;
 	ci->i_requested_max_size = 0;
-	spin_unlock(&ci->i_ceph_lock);
-
-	down_write(&mdsc->snap_rwsem);
-	ceph_update_snap_trace(mdsc, snaptrace, snaptrace+snaptrace_len,
-			       false);
-	downgrade_write(&mdsc->snap_rwsem);
-	ceph_add_cap(inode, session, cap_id, -1,
-		     issued, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH,
-		     NULL /* no caps context */);
-	kick_flushing_inode_caps(mdsc, session, inode);
-	up_read(&mdsc->snap_rwsem);
 
+	*old_issued = issued;
+	*target_cap = cap;
 }
 
 /*
@@ -2977,7 +2990,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	struct ceph_mds_caps *h;
 	struct ceph_mds_cap_peer *peer = NULL;
 	int mds = session->s_mds;
-	int op;
+	int op, issued;
 	u32 seq, mseq;
 	struct ceph_vino vino;
 	u64 cap_id;
@@ -3069,7 +3082,10 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 
 	case CEPH_CAP_OP_IMPORT:
 		handle_cap_import(mdsc, inode, h, peer, session,
-				  snaptrace, snaptrace_len);
+				  &cap, &issued);
+		handle_cap_grant(mdsc, inode, h,  snaptrace, snaptrace_len,
+				 msg->middle, session, cap, issued);
+		goto done_unlocked;
 	}
 
 	/* the rest require a cap */
@@ -3086,8 +3102,10 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	switch (op) {
 	case CEPH_CAP_OP_REVOKE:
 	case CEPH_CAP_OP_GRANT:
-	case CEPH_CAP_OP_IMPORT:
-		handle_cap_grant(inode, h, session, cap, msg->middle);
+		__ceph_caps_issued(ci, &issued);
+		issued |= __ceph_caps_dirty(ci);
+		handle_cap_grant(mdsc, inode, h, NULL, 0, msg->middle,
+				 session, cap, issued);
 		goto done_unlocked;
 
 	case CEPH_CAP_OP_FLUSH_ACK:
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 00d6af6a32e..8d7d782f438 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -169,7 +169,7 @@ static struct dentry *__get_parent(struct super_block *sb,
 	return dentry;
 }
 
-struct dentry *ceph_get_parent(struct dentry *child)
+static struct dentry *ceph_get_parent(struct dentry *child)
 {
 	/* don't re-export snaps */
 	if (ceph_snap(child->d_inode) != CEPH_NOSNAP)
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 88a6df4cbe6..302085100c2 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -418,7 +418,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
 	struct page **pages;
 	u64 off = iocb->ki_pos;
 	int num_pages, ret;
-	size_t len = i->count;
+	size_t len = iov_iter_count(i);
 
 	dout("sync_read on file %p %llu~%u %s\n", file, off,
 	     (unsigned)len,
@@ -436,25 +436,26 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
 
 	if (file->f_flags & O_DIRECT) {
 		while (iov_iter_count(i)) {
-			void __user *data = i->iov[0].iov_base + i->iov_offset;
-			size_t len = i->iov[0].iov_len - i->iov_offset;
+			size_t start;
+			ssize_t n;
 
-			num_pages = calc_pages_for((unsigned long)data, len);
-			pages = ceph_get_direct_page_vector(data,
-							    num_pages, true);
-			if (IS_ERR(pages))
-				return PTR_ERR(pages);
+			n = iov_iter_get_pages_alloc(i, &pages, INT_MAX, &start);
+			if (n < 0)
+				return n;
 
-			ret = striped_read(inode, off, len,
+			num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;
+
+			ret = striped_read(inode, off, n,
 					   pages, num_pages, checkeof,
-					   1, (unsigned long)data & ~PAGE_MASK);
+					   1, start);
+
 			ceph_put_page_vector(pages, num_pages, true);
 
 			if (ret <= 0)
 				break;
 			off += ret;
 			iov_iter_advance(i, ret);
-			if (ret < len)
+			if (ret < n)
 				break;
 		}
 	} else {
@@ -466,25 +467,14 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i,
 					num_pages, checkeof, 0, 0);
 		if (ret > 0) {
 			int l, k = 0;
-			size_t left = len = ret;
+			size_t left = ret;
 
 			while (left) {
-				void __user *data = i->iov[0].iov_base
-							+ i->iov_offset;
-				l = min(i->iov[0].iov_len - i->iov_offset,
-					left);
-
-				ret = ceph_copy_page_vector_to_user(&pages[k],
-								    data, off,
-								    l);
-				if (ret > 0) {
-					iov_iter_advance(i, ret);
-					left -= ret;
-					off += ret;
-					k = calc_pages_for(iocb->ki_pos,
-							   len - left + 1) - 1;
-					BUG_ON(k >= num_pages && left);
-				} else
+				int copy = min_t(size_t, PAGE_SIZE, left);
+				l = copy_page_to_iter(pages[k++], 0, copy, i);
+				off += l;
+				left -= l;
+				if (l < copy)
 					break;
 			}
 		}
@@ -541,8 +531,7 @@ static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
  * objects, rollback on failure, etc.)
  */
 static ssize_t
-ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
-		       unsigned long nr_segs, size_t count)
+ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
@@ -556,11 +545,10 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	int written = 0;
 	int flags;
 	int check_caps = 0;
-	int page_align;
 	int ret;
 	struct timespec mtime = CURRENT_TIME;
 	loff_t pos = iocb->ki_pos;
-	struct iov_iter i;
+	size_t count = iov_iter_count(from);
 
 	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
@@ -582,13 +570,10 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
 		CEPH_OSD_FLAG_ONDISK |
 		CEPH_OSD_FLAG_WRITE;
 
-	iov_iter_init(&i, iov, nr_segs, count, 0);
-
-	while (iov_iter_count(&i) > 0) {
-		void __user *data = i.iov->iov_base + i.iov_offset;
-		u64 len = i.iov->iov_len - i.iov_offset;
-
-		page_align = (unsigned long)data & ~PAGE_MASK;
+	while (iov_iter_count(from) > 0) {
+		u64 len = iov_iter_single_seg_count(from);
+		size_t start;
+		ssize_t n;
 
 		snapc = ci->i_snap_realm->cached_context;
 		vino = ceph_vino(inode);
@@ -604,20 +589,21 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
 			break;
 		}
 
-		num_pages = calc_pages_for(page_align, len);
-		pages = ceph_get_direct_page_vector(data, num_pages, false);
-		if (IS_ERR(pages)) {
-			ret = PTR_ERR(pages);
-			goto out;
+		n = iov_iter_get_pages_alloc(from, &pages, len, &start);
+		if (unlikely(n < 0)) {
+			ret = n;
+			ceph_osdc_put_request(req);
+			break;
 		}
 
+		num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE;
 		/*
 		 * throw out any page cache pages in this range. this
 		 * may block.
 		 */
 		truncate_inode_pages_range(inode->i_mapping, pos,
-				   (pos+len) | (PAGE_CACHE_SIZE-1));
-		osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align,
+				   (pos+n) | (PAGE_CACHE_SIZE-1));
+		osd_req_op_extent_osd_data_pages(req, 0, pages, n, start,
 						false, false);
 
 		/* BUG_ON(vino.snap != CEPH_NOSNAP); */
@@ -629,22 +615,20 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
 		ceph_put_page_vector(pages, num_pages, false);
 
-out:
 		ceph_osdc_put_request(req);
-		if (ret == 0) {
-			pos += len;
-			written += len;
-			iov_iter_advance(&i, (size_t)len);
-
-			if (pos > i_size_read(inode)) {
-				check_caps = ceph_inode_set_size(inode, pos);
-				if (check_caps)
-					ceph_check_caps(ceph_inode(inode),
-							CHECK_CAPS_AUTHONLY,
-							NULL);
-			}
-		} else
+		if (ret)
 			break;
+		pos += n;
+		written += n;
+		iov_iter_advance(from, n);
+
+		if (pos > i_size_read(inode)) {
+			check_caps = ceph_inode_set_size(inode, pos);
+			if (check_caps)
+				ceph_check_caps(ceph_inode(inode),
+						CHECK_CAPS_AUTHONLY,
+						NULL);
+		}
 	}
 
 	if (ret != -EOLDSNAPC && written > 0) {
@@ -662,8 +646,7 @@ out:
  * correct atomic write, we should e.g. take write locks on all
  * objects, rollback on failure, etc.)
  */
-static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, size_t count)
+static ssize_t ceph_sync_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
@@ -681,7 +664,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
 	int ret;
 	struct timespec mtime = CURRENT_TIME;
 	loff_t pos = iocb->ki_pos;
-	struct iov_iter i;
+	size_t count = iov_iter_count(from);
 
 	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
 		return -EROFS;
@@ -703,9 +686,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
 		CEPH_OSD_FLAG_WRITE |
 		CEPH_OSD_FLAG_ACK;
 
-	iov_iter_init(&i, iov, nr_segs, count, 0);
-
-	while ((len = iov_iter_count(&i)) > 0) {
+	while ((len = iov_iter_count(from)) > 0) {
 		size_t left;
 		int n;
 
@@ -737,13 +718,12 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov,
 		left = len;
 		for (n = 0; n < num_pages; n++) {
 			size_t plen = min_t(size_t, left, PAGE_SIZE);
-			ret = iov_iter_copy_from_user(pages[n], &i, 0, plen);
+			ret = copy_page_from_iter(pages[n], 0, plen, from);
 			if (ret != plen) {
 				ret = -EFAULT;
 				break;
 			}
 			left -= ret;
-			iov_iter_advance(&i, ret);
 		}
 
 		if (ret < 0) {
@@ -796,8 +776,7 @@ out:
  *
  * Hmm, the sync read case isn't actually async... should it be?
  */
-static ssize_t ceph_aio_read(struct kiocb *iocb, const struct iovec *iov,
-			     unsigned long nr_segs, loff_t pos)
+static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *filp = iocb->ki_filp;
 	struct ceph_file_info *fi = filp->private_data;
@@ -823,40 +802,20 @@ again:
 	if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
 	    (iocb->ki_filp->f_flags & O_DIRECT) ||
 	    (fi->flags & CEPH_F_SYNC)) {
-		struct iov_iter i;
 
 		dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n",
 		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
 		     ceph_cap_string(got));
 
-		if (!read) {
-			ret = generic_segment_checks(iov, &nr_segs,
-							&len, VERIFY_WRITE);
-			if (ret)
-				goto out;
-		}
-
-		iov_iter_init(&i, iov, nr_segs, len, read);
-
 		/* hmm, this isn't really async... */
-		ret = ceph_sync_read(iocb, &i, &checkeof);
+		ret = ceph_sync_read(iocb, to, &checkeof);
 	} else {
-		/*
-		 * We can't modify the content of iov,
-		 * so we only read from beginning.
-		 */
-		if (read) {
-			iocb->ki_pos = pos;
-			len = iocb->ki_nbytes;
-			read = 0;
-		}
 		dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
-		     inode, ceph_vinop(inode), pos, (unsigned)len,
+		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
 		     ceph_cap_string(got));
 
-		ret = generic_file_aio_read(iocb, iov, nr_segs, pos);
+		ret = generic_file_read_iter(iocb, to);
 	}
-out:
 	dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
 	     inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
 	ceph_put_cap_refs(ci, got);
@@ -872,6 +831,7 @@ out:
 			     ", reading more\n", iocb->ki_pos,
 			     inode->i_size);
 
+			iov_iter_advance(to, ret);
 			read += ret;
 			len -= ret;
 			checkeof = 0;
@@ -895,8 +855,7 @@ out:
  *
  * If we are near ENOSPC, write synchronously.
  */
-static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
-		       unsigned long nr_segs, loff_t pos)
+static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct ceph_file_info *fi = file->private_data;
@@ -904,18 +863,15 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_osd_client *osdc =
 		&ceph_sb_to_client(inode->i_sb)->client->osdc;
-	ssize_t count, written = 0;
+	ssize_t count = iov_iter_count(from), written = 0;
 	int err, want, got;
+	loff_t pos = iocb->ki_pos;
 
 	if (ceph_snap(inode) != CEPH_NOSNAP)
 		return -EROFS;
 
 	mutex_lock(&inode->i_mutex);
 
-	err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
-	if (err)
-		goto out;
-
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = file->f_mapping->backing_dev_info;
 
@@ -925,6 +881,7 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
 
 	if (count == 0)
 		goto out;
+	iov_iter_truncate(from, count);
 
 	err = file_remove_suid(file);
 	if (err)
@@ -956,23 +913,26 @@ retry_snap:
 
 	if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
 	    (file->f_flags & O_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
+		struct iov_iter data;
 		mutex_unlock(&inode->i_mutex);
+		/* we might need to revert back to that point */
+		data = *from;
 		if (file->f_flags & O_DIRECT)
-			written = ceph_sync_direct_write(iocb, iov,
-							 nr_segs, count);
+			written = ceph_sync_direct_write(iocb, &data);
 		else
-			written = ceph_sync_write(iocb, iov, nr_segs, count);
+			written = ceph_sync_write(iocb, &data);
 		if (written == -EOLDSNAPC) {
 			dout("aio_write %p %llx.%llx %llu~%u"
 				"got EOLDSNAPC, retrying\n",
 				inode, ceph_vinop(inode),
-				pos, (unsigned)iov->iov_len);
+				pos, (unsigned)count);
 			mutex_lock(&inode->i_mutex);
 			goto retry_snap;
 		}
+		if (written > 0)
+			iov_iter_advance(from, written);
 	} else {
 		loff_t old_size = inode->i_size;
-		struct iov_iter from;
 		/*
 		 * No need to acquire the i_truncate_mutex. Because
 		 * the MDS revokes Fwb caps before sending truncate
@@ -980,8 +940,7 @@ retry_snap:
 		 * are pending vmtruncate. So write and vmtruncate
 		 * can not run at the same time
 		 */
-		iov_iter_init(&from, iov, nr_segs, count, 0);
-		written = generic_perform_write(file, &from, pos);
+		written = generic_perform_write(file, from, pos);
 		if (likely(written >= 0))
 			iocb->ki_pos = pos + written;
 		if (inode->i_size > old_size)
@@ -999,7 +958,7 @@ retry_snap:
 	}
 
 	dout("aio_write %p %llx.%llx %llu~%u  dropping cap refs on %s\n",
-	     inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len,
+	     inode, ceph_vinop(inode), pos, (unsigned)count,
 	     ceph_cap_string(got));
 	ceph_put_cap_refs(ci, got);
 
@@ -1276,16 +1235,16 @@ const struct file_operations ceph_file_fops = {
 	.open = ceph_open,
 	.release = ceph_release,
 	.llseek = ceph_llseek,
-	.read = do_sync_read,
-	.write = do_sync_write,
-	.aio_read = ceph_aio_read,
-	.aio_write = ceph_aio_write,
+	.read = new_sync_read,
+	.write = new_sync_write,
+	.read_iter = ceph_read_iter,
+	.write_iter = ceph_write_iter,
 	.mmap = ceph_mmap,
 	.fsync = ceph_fsync,
 	.lock = ceph_lock,
 	.flock = ceph_flock,
 	.splice_read = generic_file_splice_read,
-	.splice_write = generic_file_splice_write,
+	.splice_write = iter_file_splice_write,
 	.unlocked_ioctl = ceph_ioctl,
 	.compat_ioctl	= ceph_ioctl,
 	.fallocate	= ceph_fallocate,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e4fff9ff1c2..04c89c266ce 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -10,6 +10,7 @@
 #include <linux/writeback.h>
 #include <linux/vmalloc.h>
 #include <linux/posix_acl.h>
+#include <linux/random.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -179,9 +180,8 @@ struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f)
  * specified, copy the frag delegation info to the caller if
  * it is present.
  */
-u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
-		     struct ceph_inode_frag *pfrag,
-		     int *found)
+static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+			      struct ceph_inode_frag *pfrag, int *found)
 {
 	u32 t = ceph_frag_make(0, 0);
 	struct ceph_inode_frag *frag;
@@ -191,7 +191,6 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
 	if (found)
 		*found = 0;
 
-	mutex_lock(&ci->i_fragtree_mutex);
 	while (1) {
 		WARN_ON(!ceph_frag_contains_value(t, v));
 		frag = __ceph_find_frag(ci, t);
@@ -220,10 +219,19 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
 	}
 	dout("choose_frag(%x) = %x\n", v, t);
 
-	mutex_unlock(&ci->i_fragtree_mutex);
 	return t;
 }
 
+u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+		     struct ceph_inode_frag *pfrag, int *found)
+{
+	u32 ret;
+	mutex_lock(&ci->i_fragtree_mutex);
+	ret = __ceph_choose_frag(ci, v, pfrag, found);
+	mutex_unlock(&ci->i_fragtree_mutex);
+	return ret;
+}
+
 /*
  * Process dirfrag (delegation) info from the mds.  Include leaf
  * fragment in tree ONLY if ndist > 0.  Otherwise, only
@@ -237,11 +245,17 @@ static int ceph_fill_dirfrag(struct inode *inode,
 	u32 id = le32_to_cpu(dirinfo->frag);
 	int mds = le32_to_cpu(dirinfo->auth);
 	int ndist = le32_to_cpu(dirinfo->ndist);
+	int diri_auth = -1;
 	int i;
 	int err = 0;
 
+	spin_lock(&ci->i_ceph_lock);
+	if (ci->i_auth_cap)
+		diri_auth = ci->i_auth_cap->mds;
+	spin_unlock(&ci->i_ceph_lock);
+
 	mutex_lock(&ci->i_fragtree_mutex);
-	if (ndist == 0) {
+	if (ndist == 0 && mds == diri_auth) {
 		/* no delegation info needed. */
 		frag = __ceph_find_frag(ci, id);
 		if (!frag)
@@ -286,6 +300,75 @@ out:
 	return err;
 }
 
+static int ceph_fill_fragtree(struct inode *inode,
+			      struct ceph_frag_tree_head *fragtree,
+			      struct ceph_mds_reply_dirfrag *dirinfo)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_inode_frag *frag;
+	struct rb_node *rb_node;
+	int i;
+	u32 id, nsplits;
+	bool update = false;
+
+	mutex_lock(&ci->i_fragtree_mutex);
+	nsplits = le32_to_cpu(fragtree->nsplits);
+	if (nsplits) {
+		i = prandom_u32() % nsplits;
+		id = le32_to_cpu(fragtree->splits[i].frag);
+		if (!__ceph_find_frag(ci, id))
+			update = true;
+	} else if (!RB_EMPTY_ROOT(&ci->i_fragtree)) {
+		rb_node = rb_first(&ci->i_fragtree);
+		frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+		if (frag->frag != ceph_frag_make(0, 0) || rb_next(rb_node))
+			update = true;
+	}
+	if (!update && dirinfo) {
+		id = le32_to_cpu(dirinfo->frag);
+		if (id != __ceph_choose_frag(ci, id, NULL, NULL))
+			update = true;
+	}
+	if (!update)
+		goto out_unlock;
+
+	dout("fill_fragtree %llx.%llx\n", ceph_vinop(inode));
+	rb_node = rb_first(&ci->i_fragtree);
+	for (i = 0; i < nsplits; i++) {
+		id = le32_to_cpu(fragtree->splits[i].frag);
+		frag = NULL;
+		while (rb_node) {
+			frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+			if (ceph_frag_compare(frag->frag, id) >= 0) {
+				if (frag->frag != id)
+					frag = NULL;
+				else
+					rb_node = rb_next(rb_node);
+				break;
+			}
+			rb_node = rb_next(rb_node);
+			rb_erase(&frag->node, &ci->i_fragtree);
+			kfree(frag);
+			frag = NULL;
+		}
+		if (!frag) {
+			frag = __get_or_create_frag(ci, id);
+			if (IS_ERR(frag))
+				continue;
+		}
+		frag->split_by = le32_to_cpu(fragtree->splits[i].by);
+		dout(" frag %x split by %d\n", frag->frag, frag->split_by);
+	}
+	while (rb_node) {
+		frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+		rb_node = rb_next(rb_node);
+		rb_erase(&frag->node, &ci->i_fragtree);
+		kfree(frag);
+	}
+out_unlock:
+	mutex_unlock(&ci->i_fragtree_mutex);
+	return 0;
+}
 
 /*
  * initialize a newly allocated inode.
@@ -341,7 +424,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	INIT_LIST_HEAD(&ci->i_cap_snaps);
 	ci->i_head_snapc = NULL;
 	ci->i_snap_caps = 0;
-	ci->i_cap_exporting_issued = 0;
 
 	for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
 		ci->i_nr_by_mode[i] = 0;
@@ -407,7 +489,7 @@ void ceph_destroy_inode(struct inode *inode)
 
 	/*
 	 * we may still have a snap_realm reference if there are stray
-	 * caps in i_cap_exporting_issued or i_snap_caps.
+	 * caps in i_snap_caps.
 	 */
 	if (ci->i_snap_realm) {
 		struct ceph_mds_client *mdsc =
@@ -582,22 +664,26 @@ static int fill_inode(struct inode *inode,
 		      unsigned long ttl_from, int cap_fmode,
 		      struct ceph_cap_reservation *caps_reservation)
 {
+	struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
 	struct ceph_mds_reply_inode *info = iinfo->in;
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	int i;
-	int issued = 0, implemented;
+	int issued = 0, implemented, new_issued;
 	struct timespec mtime, atime, ctime;
-	u32 nsplits;
-	struct ceph_inode_frag *frag;
-	struct rb_node *rb_node;
 	struct ceph_buffer *xattr_blob = NULL;
+	struct ceph_cap *new_cap = NULL;
 	int err = 0;
-	int queue_trunc = 0;
+	bool wake = false;
+	bool queue_trunc = false;
+	bool new_version = false;
 
 	dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
 	     inode, ceph_vinop(inode), le64_to_cpu(info->version),
 	     ci->i_version);
 
+	/* prealloc new cap struct */
+	if (info->cap.caps && ceph_snap(inode) == CEPH_NOSNAP)
+		new_cap = ceph_get_cap(mdsc, caps_reservation);
+
 	/*
 	 * prealloc xattr data, if it looks like we'll need it.  only
 	 * if len > 4 (meaning there are actually xattrs; the first 4
@@ -623,19 +709,23 @@ static int fill_inode(struct inode *inode,
 	 *   3    2     skip
 	 *   3    3     update
 	 */
-	if (le64_to_cpu(info->version) > 0 &&
-	    (ci->i_version & ~1) >= le64_to_cpu(info->version))
-		goto no_change;
-	
+	if (ci->i_version == 0 ||
+	    ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+	     le64_to_cpu(info->version) > (ci->i_version & ~1)))
+		new_version = true;
+
 	issued = __ceph_caps_issued(ci, &implemented);
 	issued |= implemented | __ceph_caps_dirty(ci);
+	new_issued = ~issued & le32_to_cpu(info->cap.caps);
 
 	/* update inode */
 	ci->i_version = le64_to_cpu(info->version);
 	inode->i_version++;
 	inode->i_rdev = le32_to_cpu(info->rdev);
+	inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
 
-	if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+	if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
+	    (issued & CEPH_CAP_AUTH_EXCL) == 0) {
 		inode->i_mode = le32_to_cpu(info->mode);
 		inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
 		inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
@@ -644,23 +734,35 @@ static int fill_inode(struct inode *inode,
 		     from_kgid(&init_user_ns, inode->i_gid));
 	}
 
-	if ((issued & CEPH_CAP_LINK_EXCL) == 0)
+	if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) &&
+	    (issued & CEPH_CAP_LINK_EXCL) == 0)
 		set_nlink(inode, le32_to_cpu(info->nlink));
 
-	/* be careful with mtime, atime, size */
-	ceph_decode_timespec(&atime, &info->atime);
-	ceph_decode_timespec(&mtime, &info->mtime);
-	ceph_decode_timespec(&ctime, &info->ctime);
-	queue_trunc = ceph_fill_file_size(inode, issued,
-					  le32_to_cpu(info->truncate_seq),
-					  le64_to_cpu(info->truncate_size),
-					  le64_to_cpu(info->size));
-	ceph_fill_file_time(inode, issued,
-			    le32_to_cpu(info->time_warp_seq),
-			    &ctime, &mtime, &atime);
-
-	ci->i_layout = info->layout;
-	inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+	if (new_version || (new_issued & CEPH_CAP_ANY_RD)) {
+		/* be careful with mtime, atime, size */
+		ceph_decode_timespec(&atime, &info->atime);
+		ceph_decode_timespec(&mtime, &info->mtime);
+		ceph_decode_timespec(&ctime, &info->ctime);
+		ceph_fill_file_time(inode, issued,
+				le32_to_cpu(info->time_warp_seq),
+				&ctime, &mtime, &atime);
+	}
+
+	if (new_version ||
+	    (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+		ci->i_layout = info->layout;
+		queue_trunc = ceph_fill_file_size(inode, issued,
+					le32_to_cpu(info->truncate_seq),
+					le64_to_cpu(info->truncate_size),
+					le64_to_cpu(info->size));
+		/* only update max_size on auth cap */
+		if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+		    ci->i_max_size != le64_to_cpu(info->max_size)) {
+			dout("max_size %lld -> %llu\n", ci->i_max_size,
+					le64_to_cpu(info->max_size));
+			ci->i_max_size = le64_to_cpu(info->max_size);
+		}
+	}
 
 	/* xattrs */
 	/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
@@ -745,58 +847,6 @@ static int fill_inode(struct inode *inode,
 		dout(" marking %p complete (empty)\n", inode);
 		__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
 	}
-no_change:
-	/* only update max_size on auth cap */
-	if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
-	    ci->i_max_size != le64_to_cpu(info->max_size)) {
-		dout("max_size %lld -> %llu\n", ci->i_max_size,
-		     le64_to_cpu(info->max_size));
-		ci->i_max_size = le64_to_cpu(info->max_size);
-	}
-
-	spin_unlock(&ci->i_ceph_lock);
-
-	/* queue truncate if we saw i_size decrease */
-	if (queue_trunc)
-		ceph_queue_vmtruncate(inode);
-
-	/* populate frag tree */
-	/* FIXME: move me up, if/when version reflects fragtree changes */
-	nsplits = le32_to_cpu(info->fragtree.nsplits);
-	mutex_lock(&ci->i_fragtree_mutex);
-	rb_node = rb_first(&ci->i_fragtree);
-	for (i = 0; i < nsplits; i++) {
-		u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
-		frag = NULL;
-		while (rb_node) {
-			frag = rb_entry(rb_node, struct ceph_inode_frag, node);
-			if (ceph_frag_compare(frag->frag, id) >= 0) {
-				if (frag->frag != id)
-					frag = NULL;
-				else
-					rb_node = rb_next(rb_node);
-				break;
-			}
-			rb_node = rb_next(rb_node);
-			rb_erase(&frag->node, &ci->i_fragtree);
-			kfree(frag);
-			frag = NULL;
-		}
-		if (!frag) {
-			frag = __get_or_create_frag(ci, id);
-			if (IS_ERR(frag))
-				continue;
-		}
-		frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
-		dout(" frag %x split by %d\n", frag->frag, frag->split_by);
-	}
-	while (rb_node) {
-		frag = rb_entry(rb_node, struct ceph_inode_frag, node);
-		rb_node = rb_next(rb_node);
-		rb_erase(&frag->node, &ci->i_fragtree);
-		kfree(frag);
-	}
-	mutex_unlock(&ci->i_fragtree_mutex);
 
 	/* were we issued a capability? */
 	if (info->cap.caps) {
@@ -809,30 +859,41 @@ no_change:
 				     le32_to_cpu(info->cap.seq),
 				     le32_to_cpu(info->cap.mseq),
 				     le64_to_cpu(info->cap.realm),
-				     info->cap.flags,
-				     caps_reservation);
+				     info->cap.flags, &new_cap);
+			wake = true;
 		} else {
-			spin_lock(&ci->i_ceph_lock);
 			dout(" %p got snap_caps %s\n", inode,
 			     ceph_cap_string(le32_to_cpu(info->cap.caps)));
 			ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
 			if (cap_fmode >= 0)
 				__ceph_get_fmode(ci, cap_fmode);
-			spin_unlock(&ci->i_ceph_lock);
 		}
 	} else if (cap_fmode >= 0) {
 		pr_warn("mds issued no caps on %llx.%llx\n",
 			   ceph_vinop(inode));
 		__ceph_get_fmode(ci, cap_fmode);
 	}
+	spin_unlock(&ci->i_ceph_lock);
+
+	if (wake)
+		wake_up_all(&ci->i_cap_wq);
+
+	/* queue truncate if we saw i_size decrease */
+	if (queue_trunc)
+		ceph_queue_vmtruncate(inode);
+
+	/* populate frag tree */
+	if (S_ISDIR(inode->i_mode))
+		ceph_fill_fragtree(inode, &info->fragtree, dirinfo);
 
 	/* update delegation info? */
 	if (dirinfo)
 		ceph_fill_dirfrag(inode, dirinfo);
 
 	err = 0;
-
 out:
+	if (new_cap)
+		ceph_put_cap(mdsc, new_cap);
 	if (xattr_blob)
 		ceph_buffer_put(xattr_blob);
 	return err;
@@ -1485,7 +1546,7 @@ static void ceph_invalidate_work(struct work_struct *work)
 	orig_gen = ci->i_rdcache_gen;
 	spin_unlock(&ci->i_ceph_lock);
 
-	truncate_inode_pages(inode->i_mapping, 0);
+	truncate_pagecache(inode, 0);
 
 	spin_lock(&ci->i_ceph_lock);
 	if (orig_gen == ci->i_rdcache_gen &&
@@ -1588,7 +1649,7 @@ retry:
 	     ci->i_truncate_pending, to);
 	spin_unlock(&ci->i_ceph_lock);
 
-	truncate_inode_pages(inode->i_mapping, to);
+	truncate_pagecache(inode, to);
 
 	spin_lock(&ci->i_ceph_lock);
 	if (to == ci->i_truncate_size) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 9a33b98cb00..92a2548278f 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1558,6 +1558,8 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
 	init_completion(&req->r_safe_completion);
 	INIT_LIST_HEAD(&req->r_unsafe_item);
 
+	req->r_stamp = CURRENT_TIME;
+
 	req->r_op = op;
 	req->r_direct_mode = mode;
 	return req;
@@ -1783,7 +1785,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 	}
 
 	len = sizeof(*head) +
-		pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64));
+		pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
+		sizeof(struct timespec);
 
 	/* calculate (max) length for cap releases */
 	len += sizeof(struct ceph_mds_request_release) *
@@ -1800,6 +1803,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		goto out_free2;
 	}
 
+	msg->hdr.version = 2;
 	msg->hdr.tid = cpu_to_le64(req->r_tid);
 
 	head = msg->front.iov_base;
@@ -1836,6 +1840,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		      mds, req->r_old_inode_drop, req->r_old_inode_unless, 0);
 	head->num_releases = cpu_to_le16(releases);
 
+	/* time stamp */
+	ceph_encode_copy(&p, &req->r_stamp, sizeof(req->r_stamp));
+
 	BUG_ON(p > end);
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index e90cfccf93b..e00737cf523 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -194,6 +194,7 @@ struct ceph_mds_request {
 	int r_fmode;        /* file mode, if expecting cap */
 	kuid_t r_uid;
 	kgid_t r_gid;
+	struct timespec r_stamp;
 
 	/* for choosing which mds to send this request to */
 	int r_direct_mode;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index ead05cc1f44..12b20744e38 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -292,7 +292,6 @@ struct ceph_inode_info {
 	struct ceph_snap_context *i_head_snapc;  /* set if wr_buffer_head > 0 or
 						    dirty|flushing caps */
 	unsigned i_snap_caps;           /* cap bits for snapped files */
-	unsigned i_cap_exporting_issued;
 
 	int i_nr_by_mode[CEPH_FILE_MODE_NUM];  /* open file counts */
 
@@ -775,11 +774,13 @@ static inline void ceph_forget_all_cached_acls(struct inode *inode)
 extern const char *ceph_cap_string(int c);
 extern void ceph_handle_caps(struct ceph_mds_session *session,
 			     struct ceph_msg *msg);
-extern int ceph_add_cap(struct inode *inode,
-			struct ceph_mds_session *session, u64 cap_id,
-			int fmode, unsigned issued, unsigned wanted,
-			unsigned cap, unsigned seq, u64 realmino, int flags,
-			struct ceph_cap_reservation *caps_reservation);
+extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+				     struct ceph_cap_reservation *ctx);
+extern void ceph_add_cap(struct inode *inode,
+			 struct ceph_mds_session *session, u64 cap_id,
+			 int fmode, unsigned issued, unsigned wanted,
+			 unsigned cap, unsigned seq, u64 realmino, int flags,
+			 struct ceph_cap **new_cap);
 extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
 extern void ceph_put_cap(struct ceph_mds_client *mdsc,
 			 struct ceph_cap *cap);
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 0227b45ef00..15e9505aa35 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -290,7 +290,8 @@ int
 cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 		 const struct nls_table *cp, int mapChars)
 {
-	int i, j, charlen;
+	int i, charlen;
+	int j = 0;
 	char src_char;
 	__le16 dst_char;
 	wchar_t tmp;
@@ -298,12 +299,11 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	if (!mapChars)
 		return cifs_strtoUTF16(target, source, PATH_MAX, cp);
 
-	for (i = 0, j = 0; i < srclen; j++) {
+	for (i = 0; i < srclen; j++) {
 		src_char = source[i];
 		charlen = 1;
 		switch (src_char) {
 		case 0:
-			put_unaligned(0, &target[j]);
 			goto ctoUTF16_out;
 		case ':':
 			dst_char = cpu_to_le16(UNI_COLON);
@@ -350,6 +350,7 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
 	}
 
 ctoUTF16_out:
+	put_unaligned(0, &target[j]); /* Null terminate target unicode string */
 	return j;
 }
 
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 5be1f997ecd..88839806742 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -87,10 +87,6 @@ extern mempool_t *cifs_mid_poolp;
 
 struct workqueue_struct	*cifsiod_wq;
 
-#ifdef CONFIG_CIFS_SMB2
-__u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE];
-#endif
-
 /*
  * Bumps refcount for cifs super block.
  * Note that it should be only called if a referece to VFS super block is
@@ -251,11 +247,7 @@ cifs_alloc_inode(struct super_block *sb)
 	 * server, can not assume caching of file data or metadata.
 	 */
 	cifs_set_oplock_level(cifs_inode, 0);
-	cifs_inode->delete_pending = false;
-	cifs_inode->invalid_mapping = false;
-	clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cifs_inode->flags);
-	clear_bit(CIFS_INODE_PENDING_WRITERS, &cifs_inode->flags);
-	clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cifs_inode->flags);
+	cifs_inode->flags = 0;
 	spin_lock_init(&cifs_inode->writers_lock);
 	cifs_inode->writers = 0;
 	cifs_inode->vfs_inode.i_blkbits = 14;  /* 2**14 = CIFS_MAX_MSGSIZE */
@@ -302,7 +294,7 @@ cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server)
 	struct sockaddr_in *sa = (struct sockaddr_in *) &server->dstaddr;
 	struct sockaddr_in6 *sa6 = (struct sockaddr_in6 *) &server->dstaddr;
 
-	seq_printf(s, ",addr=");
+	seq_puts(s, ",addr=");
 
 	switch (server->dstaddr.ss_family) {
 	case AF_INET:
@@ -314,7 +306,7 @@ cifs_show_address(struct seq_file *s, struct TCP_Server_Info *server)
 			seq_printf(s, "%%%u", sa6->sin6_scope_id);
 		break;
 	default:
-		seq_printf(s, "(unknown)");
+		seq_puts(s, "(unknown)");
 	}
 }
 
@@ -324,45 +316,45 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses)
 	if (ses->sectype == Unspecified)
 		return;
 
-	seq_printf(s, ",sec=");
+	seq_puts(s, ",sec=");
 
 	switch (ses->sectype) {
 	case LANMAN:
-		seq_printf(s, "lanman");
+		seq_puts(s, "lanman");
 		break;
 	case NTLMv2:
-		seq_printf(s, "ntlmv2");
+		seq_puts(s, "ntlmv2");
 		break;
 	case NTLM:
-		seq_printf(s, "ntlm");
+		seq_puts(s, "ntlm");
 		break;
 	case Kerberos:
-		seq_printf(s, "krb5");
+		seq_puts(s, "krb5");
 		break;
 	case RawNTLMSSP:
-		seq_printf(s, "ntlmssp");
+		seq_puts(s, "ntlmssp");
 		break;
 	default:
 		/* shouldn't ever happen */
-		seq_printf(s, "unknown");
+		seq_puts(s, "unknown");
 		break;
 	}
 
 	if (ses->sign)
-		seq_printf(s, "i");
+		seq_puts(s, "i");
 }
 
 static void
 cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb)
 {
-	seq_printf(s, ",cache=");
+	seq_puts(s, ",cache=");
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
-		seq_printf(s, "strict");
+		seq_puts(s, "strict");
 	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO)
-		seq_printf(s, "none");
+		seq_puts(s, "none");
 	else
-		seq_printf(s, "loose");
+		seq_puts(s, "loose");
 }
 
 static void
@@ -395,7 +387,7 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	cifs_show_cache_flavor(s, cifs_sb);
 
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)
-		seq_printf(s, ",multiuser");
+		seq_puts(s, ",multiuser");
 	else if (tcon->ses->user_name)
 		seq_printf(s, ",username=%s", tcon->ses->user_name);
 
@@ -421,16 +413,16 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	seq_printf(s, ",uid=%u",
 		   from_kuid_munged(&init_user_ns, cifs_sb->mnt_uid));
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
-		seq_printf(s, ",forceuid");
+		seq_puts(s, ",forceuid");
 	else
-		seq_printf(s, ",noforceuid");
+		seq_puts(s, ",noforceuid");
 
 	seq_printf(s, ",gid=%u",
 		   from_kgid_munged(&init_user_ns, cifs_sb->mnt_gid));
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
-		seq_printf(s, ",forcegid");
+		seq_puts(s, ",forcegid");
 	else
-		seq_printf(s, ",noforcegid");
+		seq_puts(s, ",noforcegid");
 
 	cifs_show_address(s, tcon->ses->server);
 
@@ -442,47 +434,47 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	cifs_show_nls(s, cifs_sb->local_nls);
 
 	if (tcon->seal)
-		seq_printf(s, ",seal");
+		seq_puts(s, ",seal");
 	if (tcon->nocase)
-		seq_printf(s, ",nocase");
+		seq_puts(s, ",nocase");
 	if (tcon->retry)
-		seq_printf(s, ",hard");
+		seq_puts(s, ",hard");
 	if (tcon->unix_ext)
-		seq_printf(s, ",unix");
+		seq_puts(s, ",unix");
 	else
-		seq_printf(s, ",nounix");
+		seq_puts(s, ",nounix");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
-		seq_printf(s, ",posixpaths");
+		seq_puts(s, ",posixpaths");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
-		seq_printf(s, ",setuids");
+		seq_puts(s, ",setuids");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
-		seq_printf(s, ",serverino");
+		seq_puts(s, ",serverino");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
-		seq_printf(s, ",rwpidforward");
+		seq_puts(s, ",rwpidforward");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL)
-		seq_printf(s, ",forcemand");
+		seq_puts(s, ",forcemand");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
-		seq_printf(s, ",nouser_xattr");
+		seq_puts(s, ",nouser_xattr");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
-		seq_printf(s, ",mapchars");
+		seq_puts(s, ",mapchars");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
-		seq_printf(s, ",sfu");
+		seq_puts(s, ",sfu");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
-		seq_printf(s, ",nobrl");
+		seq_puts(s, ",nobrl");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL)
-		seq_printf(s, ",cifsacl");
+		seq_puts(s, ",cifsacl");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
-		seq_printf(s, ",dynperm");
+		seq_puts(s, ",dynperm");
 	if (root->d_sb->s_flags & MS_POSIXACL)
-		seq_printf(s, ",acl");
+		seq_puts(s, ",acl");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
-		seq_printf(s, ",mfsymlinks");
+		seq_puts(s, ",mfsymlinks");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE)
-		seq_printf(s, ",fsc");
+		seq_puts(s, ",fsc");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)
-		seq_printf(s, ",nostrictsync");
+		seq_puts(s, ",nostrictsync");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
-		seq_printf(s, ",noperm");
+		seq_puts(s, ",noperm");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID)
 		seq_printf(s, ",backupuid=%u",
 			   from_kuid_munged(&init_user_ns,
@@ -733,8 +725,20 @@ out_nls:
 	goto out;
 }
 
-static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				   unsigned long nr_segs, loff_t pos)
+static ssize_t
+cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	ssize_t rc;
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	rc = cifs_revalidate_mapping(inode);
+	if (rc)
+		return rc;
+
+	return generic_file_read_iter(iocb, iter);
+}
+
+static ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
@@ -745,14 +749,14 @@ static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (written)
 		return written;
 
-	written = generic_file_aio_write(iocb, iov, nr_segs, pos);
+	written = generic_file_write_iter(iocb, from);
 
 	if (CIFS_CACHE_WRITE(CIFS_I(inode)))
 		goto out;
 
 	rc = filemap_fdatawrite(inode->i_mapping);
 	if (rc)
-		cifs_dbg(FYI, "cifs_file_aio_write: %d rc on %p inode\n",
+		cifs_dbg(FYI, "cifs_file_write_iter: %d rc on %p inode\n",
 			 rc, inode);
 
 out:
@@ -888,10 +892,10 @@ const struct inode_operations cifs_symlink_inode_ops = {
 };
 
 const struct file_operations cifs_file_ops = {
-	.read = do_sync_read,
-	.write = do_sync_write,
-	.aio_read = generic_file_aio_read,
-	.aio_write = cifs_file_aio_write,
+	.read = new_sync_read,
+	.write = new_sync_write,
+	.read_iter = cifs_loose_read_iter,
+	.write_iter = cifs_file_write_iter,
 	.open = cifs_open,
 	.release = cifs_close,
 	.lock = cifs_lock,
@@ -907,10 +911,10 @@ const struct file_operations cifs_file_ops = {
 };
 
 const struct file_operations cifs_file_strict_ops = {
-	.read = do_sync_read,
-	.write = do_sync_write,
-	.aio_read = cifs_strict_readv,
-	.aio_write = cifs_strict_writev,
+	.read = new_sync_read,
+	.write = new_sync_write,
+	.read_iter = cifs_strict_readv,
+	.write_iter = cifs_strict_writev,
 	.open = cifs_open,
 	.release = cifs_close,
 	.lock = cifs_lock,
@@ -927,10 +931,10 @@ const struct file_operations cifs_file_strict_ops = {
 
 const struct file_operations cifs_file_direct_ops = {
 	/* BB reevaluate whether they can be done with directio, no cache */
-	.read = do_sync_read,
-	.write = do_sync_write,
-	.aio_read = cifs_user_readv,
-	.aio_write = cifs_user_writev,
+	.read = new_sync_read,
+	.write = new_sync_write,
+	.read_iter = cifs_user_readv,
+	.write_iter = cifs_user_writev,
 	.open = cifs_open,
 	.release = cifs_close,
 	.lock = cifs_lock,
@@ -946,10 +950,10 @@ const struct file_operations cifs_file_direct_ops = {
 };
 
 const struct file_operations cifs_file_nobrl_ops = {
-	.read = do_sync_read,
-	.write = do_sync_write,
-	.aio_read = generic_file_aio_read,
-	.aio_write = cifs_file_aio_write,
+	.read = new_sync_read,
+	.write = new_sync_write,
+	.read_iter = cifs_loose_read_iter,
+	.write_iter = cifs_file_write_iter,
 	.open = cifs_open,
 	.release = cifs_close,
 	.fsync = cifs_fsync,
@@ -964,10 +968,10 @@ const struct file_operations cifs_file_nobrl_ops = {
 };
 
 const struct file_operations cifs_file_strict_nobrl_ops = {
-	.read = do_sync_read,
-	.write = do_sync_write,
-	.aio_read = cifs_strict_readv,
-	.aio_write = cifs_strict_writev,
+	.read = new_sync_read,
+	.write = new_sync_write,
+	.read_iter = cifs_strict_readv,
+	.write_iter = cifs_strict_writev,
 	.open = cifs_open,
 	.release = cifs_close,
 	.fsync = cifs_strict_fsync,
@@ -983,10 +987,10 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
 
 const struct file_operations cifs_file_direct_nobrl_ops = {
 	/* BB reevaluate whether they can be done with directio, no cache */
-	.read = do_sync_read,
-	.write = do_sync_write,
-	.aio_read = cifs_user_readv,
-	.aio_write = cifs_user_writev,
+	.read = new_sync_read,
+	.write = new_sync_write,
+	.read_iter = cifs_user_readv,
+	.write_iter = cifs_user_writev,
 	.open = cifs_open,
 	.release = cifs_close,
 	.fsync = cifs_fsync,
@@ -1192,10 +1196,6 @@ init_cifs(void)
 	spin_lock_init(&cifs_file_list_lock);
 	spin_lock_init(&GlobalMid_Lock);
 
-#ifdef CONFIG_CIFS_SMB2
-	get_random_bytes(cifs_client_guid, SMB2_CLIENT_GUID_SIZE);
-#endif
-
 	if (cifs_max_pending < 2) {
 		cifs_max_pending = 2;
 		cifs_dbg(FYI, "cifs_max_pending set to min of 2\n");
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 26a754f49ba..70f178a7c75 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -22,20 +22,28 @@
 #ifndef _CIFSFS_H
 #define _CIFSFS_H
 
+#include <linux/hash.h>
+
 #define ROOT_I 2
 
 /*
  * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
- * so that it will fit.
+ * so that it will fit. We use hash_64 to convert the value to 31 bits, and
+ * then add 1, to ensure that we don't end up with a 0 as the value.
  */
+#if BITS_PER_LONG == 64
 static inline ino_t
 cifs_uniqueid_to_ino_t(u64 fileid)
 {
-	ino_t ino = (ino_t) fileid;
-	if (sizeof(ino_t) < sizeof(u64))
-		ino ^= fileid >> (sizeof(u64)-sizeof(ino_t)) * 8;
-	return ino;
+	return (ino_t)fileid;
 }
+#else
+static inline ino_t
+cifs_uniqueid_to_ino_t(u64 fileid)
+{
+	return (ino_t)hash_64(fileid, (sizeof(ino_t) * 8) - 1) + 1;
+}
+#endif
 
 extern struct file_system_type cifs_fs_type;
 extern const struct address_space_operations cifs_addr_ops;
@@ -67,6 +75,8 @@ extern int cifs_revalidate_dentry_attr(struct dentry *);
 extern int cifs_revalidate_file(struct file *filp);
 extern int cifs_revalidate_dentry(struct dentry *);
 extern int cifs_invalidate_mapping(struct inode *inode);
+extern int cifs_revalidate_mapping(struct inode *inode);
+extern int cifs_zap_mapping(struct inode *inode);
 extern int cifs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern int cifs_setattr(struct dentry *, struct iattr *);
 
@@ -85,14 +95,10 @@ extern const struct file_operations cifs_file_strict_nobrl_ops;
 extern int cifs_open(struct inode *inode, struct file *file);
 extern int cifs_close(struct inode *inode, struct file *file);
 extern int cifs_closedir(struct inode *inode, struct file *file);
-extern ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos);
-extern ssize_t cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov,
-				 unsigned long nr_segs, loff_t pos);
-extern ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos);
-extern ssize_t cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
-				  unsigned long nr_segs, loff_t pos);
+extern ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to);
+extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to);
+extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from);
+extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from);
 extern int cifs_lock(struct file *, int, struct file_lock *);
 extern int cifs_fsync(struct file *, loff_t, loff_t, int);
 extern int cifs_strict_fsync(struct file *, loff_t, loff_t, int);
@@ -130,5 +136,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "2.02"
+#define CIFS_VERSION   "2.03"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 30f6e9251a4..de6aed8c78e 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -559,6 +559,7 @@ struct TCP_Server_Info {
 	int echo_credits;  /* echo reserved slots */
 	int oplock_credits;  /* oplock break reserved slots */
 	bool echoes:1; /* enable echoes */
+	__u8 client_guid[SMB2_CLIENT_GUID_SIZE]; /* Client GUID */
 #endif
 	u16 dialect; /* dialect index that server chose */
 	bool oplocks:1; /* enable oplocks */
@@ -1113,12 +1114,13 @@ struct cifsInodeInfo {
 	__u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */
 	unsigned int oplock;		/* oplock/lease level we have */
 	unsigned int epoch;		/* used to track lease state changes */
-	bool delete_pending;		/* DELETE_ON_CLOSE is set */
-	bool invalid_mapping;		/* pagecache is invalid */
-	unsigned long flags;
 #define CIFS_INODE_PENDING_OPLOCK_BREAK   (0) /* oplock break in progress */
 #define CIFS_INODE_PENDING_WRITERS	  (1) /* Writes in progress */
 #define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2) /* Downgrade oplock to L2 */
+#define CIFS_INO_DELETE_PENDING		  (3) /* delete pending on server */
+#define CIFS_INO_INVALID_MAPPING	  (4) /* pagecache is invalid */
+#define CIFS_INO_LOCK			  (5) /* lock bit for synchronization */
+	unsigned long flags;
 	spinlock_t writers_lock;
 	unsigned int writers;		/* Number of writers on this inode */
 	unsigned long time;		/* jiffies of last update of inode */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 8813ff776ba..b98366f21f9 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2144,6 +2144,9 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	       sizeof(tcp_ses->srcaddr));
 	memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr,
 		sizeof(tcp_ses->dstaddr));
+#ifdef CONFIG_CIFS_SMB2
+	get_random_bytes(tcp_ses->client_guid, SMB2_CLIENT_GUID_SIZE);
+#endif
 	/*
 	 * at this point we are the only ones with the pointer
 	 * to the struct since the kernel thread not created yet
@@ -2225,7 +2228,7 @@ static int match_session(struct cifs_ses *ses, struct smb_vol *vol)
 			    vol->username ? vol->username : "",
 			    CIFS_MAX_USERNAME_LEN))
 			return 0;
-		if (strlen(vol->username) != 0 &&
+		if ((vol->username && strlen(vol->username) != 0) &&
 		    ses->password != NULL &&
 		    strncmp(ses->password,
 			    vol->password ? vol->password : "",
@@ -3931,13 +3934,6 @@ cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb)
 	return tlink_tcon(cifs_sb_master_tlink(cifs_sb));
 }
 
-static int
-cifs_sb_tcon_pending_wait(void *unused)
-{
-	schedule();
-	return signal_pending(current) ? -ERESTARTSYS : 0;
-}
-
 /* find and return a tlink with given uid */
 static struct tcon_link *
 tlink_rb_search(struct rb_root *root, kuid_t uid)
@@ -4036,11 +4032,10 @@ cifs_sb_tlink(struct cifs_sb_info *cifs_sb)
 	} else {
 wait_for_construction:
 		ret = wait_on_bit(&tlink->tl_flags, TCON_LINK_PENDING,
-				  cifs_sb_tcon_pending_wait,
 				  TASK_INTERRUPTIBLE);
 		if (ret) {
 			cifs_put_tlink(tlink);
-			return ERR_PTR(ret);
+			return ERR_PTR(-ERESTARTSYS);
 		}
 
 		/* if it's good, return it */
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 5ed03e0b8b4..b88b1ade4d3 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -335,7 +335,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	spin_unlock(&cifs_file_list_lock);
 
 	if (fid->purge_cache)
-		cifs_invalidate_mapping(inode);
+		cifs_zap_mapping(inode);
 
 	file->private_data = cfile;
 	return cfile;
@@ -392,7 +392,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 		 * again and get at least level II oplock.
 		 */
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
-			CIFS_I(inode)->invalid_mapping = true;
+			set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags);
 		cifs_set_oplock_level(cifsi, 0);
 	}
 	spin_unlock(&cifs_file_list_lock);
@@ -1529,7 +1529,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u32 type,
 		 */
 		if (!CIFS_CACHE_WRITE(CIFS_I(inode)) &&
 					CIFS_CACHE_READ(CIFS_I(inode))) {
-			cifs_invalidate_mapping(inode);
+			cifs_zap_mapping(inode);
 			cifs_dbg(FYI, "Set no oplock for inode=%p due to mand locks\n",
 				 inode);
 			CIFS_I(inode)->oplock = 0;
@@ -2218,7 +2218,7 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end,
 		 file->f_path.dentry->d_name.name, datasync);
 
 	if (!CIFS_CACHE_READ(CIFS_I(inode))) {
-		rc = cifs_invalidate_mapping(inode);
+		rc = cifs_zap_mapping(inode);
 		if (rc) {
 			cifs_dbg(FYI, "rc: %d during invalidate phase\n", rc);
 			rc = 0; /* don't care about it in fsync */
@@ -2385,14 +2385,12 @@ cifs_uncached_retry_writev(struct cifs_writedata *wdata)
 }
 
 static ssize_t
-cifs_iovec_write(struct file *file, const struct iovec *iov,
-		 unsigned long nr_segs, loff_t *poffset)
+cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset)
 {
 	unsigned long nr_pages, i;
 	size_t bytes, copied, len, cur_len;
 	ssize_t total_written = 0;
 	loff_t offset;
-	struct iov_iter it;
 	struct cifsFileInfo *open_file;
 	struct cifs_tcon *tcon;
 	struct cifs_sb_info *cifs_sb;
@@ -2401,14 +2399,16 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
 	int rc;
 	pid_t pid;
 
-	len = iov_length(iov, nr_segs);
-	if (!len)
-		return 0;
-
+	len = iov_iter_count(from);
 	rc = generic_write_checks(file, poffset, &len, 0);
 	if (rc)
 		return rc;
 
+	if (!len)
+		return 0;
+
+	iov_iter_truncate(from, len);
+
 	INIT_LIST_HEAD(&wdata_list);
 	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
 	open_file = file->private_data;
@@ -2424,7 +2424,6 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
 	else
 		pid = current->tgid;
 
-	iov_iter_init(&it, iov, nr_segs, len, 0);
 	do {
 		size_t save_len;
 
@@ -2444,11 +2443,10 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
 
 		save_len = cur_len;
 		for (i = 0; i < nr_pages; i++) {
-			bytes = min_t(const size_t, cur_len, PAGE_SIZE);
-			copied = iov_iter_copy_from_user(wdata->pages[i], &it,
-							 0, bytes);
+			bytes = min_t(size_t, cur_len, PAGE_SIZE);
+			copied = copy_page_from_iter(wdata->pages[i], 0, bytes,
+						     from);
 			cur_len -= copied;
-			iov_iter_advance(&it, copied);
 			/*
 			 * If we didn't copy as much as we expected, then that
 			 * may mean we trod into an unmapped area. Stop copying
@@ -2546,11 +2544,11 @@ restart_loop:
 	return total_written ? total_written : (ssize_t)rc;
 }
 
-ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
 {
 	ssize_t written;
 	struct inode *inode;
+	loff_t pos = iocb->ki_pos;
 
 	inode = file_inode(iocb->ki_filp);
 
@@ -2560,9 +2558,9 @@ ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
 	 * write request.
 	 */
 
-	written = cifs_iovec_write(iocb->ki_filp, iov, nr_segs, &pos);
+	written = cifs_iovec_write(iocb->ki_filp, from, &pos);
 	if (written > 0) {
-		CIFS_I(inode)->invalid_mapping = true;
+		set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(inode)->flags);
 		iocb->ki_pos = pos;
 	}
 
@@ -2570,8 +2568,7 @@ ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
 }
 
 static ssize_t
-cifs_writev(struct kiocb *iocb, const struct iovec *iov,
-	    unsigned long nr_segs, loff_t pos)
+cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
@@ -2589,10 +2586,10 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov,
 	mutex_lock(&inode->i_mutex);
 	if (file->f_flags & O_APPEND)
 		lock_pos = i_size_read(inode);
-	if (!cifs_find_lock_conflict(cfile, lock_pos, iov_length(iov, nr_segs),
+	if (!cifs_find_lock_conflict(cfile, lock_pos, iov_iter_count(from),
 				     server->vals->exclusive_lock_type, NULL,
 				     CIFS_WRITE_OP)) {
-		rc = __generic_file_aio_write(iocb, iov, nr_segs);
+		rc = __generic_file_write_iter(iocb, from);
 		mutex_unlock(&inode->i_mutex);
 
 		if (rc > 0) {
@@ -2610,8 +2607,7 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov,
 }
 
 ssize_t
-cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
-		   unsigned long nr_segs, loff_t pos)
+cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
@@ -2629,11 +2625,10 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
 		if (cap_unix(tcon->ses) &&
 		(CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))
 		  && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
-			written = generic_file_aio_write(
-					iocb, iov, nr_segs, pos);
+			written = generic_file_write_iter(iocb, from);
 			goto out;
 		}
-		written = cifs_writev(iocb, iov, nr_segs, pos);
+		written = cifs_writev(iocb, from);
 		goto out;
 	}
 	/*
@@ -2642,14 +2637,14 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
 	 * affected pages because it may cause a error with mandatory locks on
 	 * these pages but not on the region from pos to ppos+len-1.
 	 */
-	written = cifs_user_writev(iocb, iov, nr_segs, pos);
+	written = cifs_user_writev(iocb, from);
 	if (written > 0 && CIFS_CACHE_READ(cinode)) {
 		/*
 		 * Windows 7 server can delay breaking level2 oplock if a write
 		 * request comes - break it on the client to prevent reading
 		 * an old data.
 		 */
-		cifs_invalidate_mapping(inode);
+		cifs_zap_mapping(inode);
 		cifs_dbg(FYI, "Set no oplock for inode=%p after a write operation\n",
 			 inode);
 		cinode->oplock = 0;
@@ -2831,32 +2826,25 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
 	return total_read > 0 ? total_read : result;
 }
 
-ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos)
+ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	ssize_t rc;
 	size_t len, cur_len;
 	ssize_t total_read = 0;
-	loff_t offset = pos;
+	loff_t offset = iocb->ki_pos;
 	unsigned int npages;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
 	struct cifsFileInfo *open_file;
 	struct cifs_readdata *rdata, *tmp;
 	struct list_head rdata_list;
-	struct iov_iter to;
 	pid_t pid;
 
-	if (!nr_segs)
-		return 0;
-
-	len = iov_length(iov, nr_segs);
+	len = iov_iter_count(to);
 	if (!len)
 		return 0;
 
-	iov_iter_init(&to, iov, nr_segs, len, 0);
-
 	INIT_LIST_HEAD(&rdata_list);
 	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
 	open_file = file->private_data;
@@ -2914,7 +2902,7 @@ error:
 	if (!list_empty(&rdata_list))
 		rc = 0;
 
-	len = iov_iter_count(&to);
+	len = iov_iter_count(to);
 	/* the loop below should proceed in the order of increasing offsets */
 	list_for_each_entry_safe(rdata, tmp, &rdata_list, list) {
 	again:
@@ -2931,7 +2919,7 @@ error:
 					goto again;
 				}
 			} else {
-				rc = cifs_readdata_to_iov(rdata, &to);
+				rc = cifs_readdata_to_iov(rdata, to);
 			}
 
 		}
@@ -2939,7 +2927,7 @@ error:
 		kref_put(&rdata->refcount, cifs_uncached_readdata_release);
 	}
 
-	total_read = len - iov_iter_count(&to);
+	total_read = len - iov_iter_count(to);
 
 	cifs_stats_bytes_read(tcon, total_read);
 
@@ -2948,15 +2936,14 @@ error:
 		rc = 0;
 
 	if (total_read) {
-		iocb->ki_pos = pos + total_read;
+		iocb->ki_pos += total_read;
 		return total_read;
 	}
 	return rc;
 }
 
 ssize_t
-cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov,
-		  unsigned long nr_segs, loff_t pos)
+cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct cifsInodeInfo *cinode = CIFS_I(inode);
@@ -2975,22 +2962,22 @@ cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov,
 	 * pos+len-1.
 	 */
 	if (!CIFS_CACHE_READ(cinode))
-		return cifs_user_readv(iocb, iov, nr_segs, pos);
+		return cifs_user_readv(iocb, to);
 
 	if (cap_unix(tcon->ses) &&
 	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
 	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
-		return generic_file_aio_read(iocb, iov, nr_segs, pos);
+		return generic_file_read_iter(iocb, to);
 
 	/*
 	 * We need to hold the sem to be sure nobody modifies lock list
 	 * with a brlock that prevents reading.
 	 */
 	down_read(&cinode->lock_sem);
-	if (!cifs_find_lock_conflict(cfile, pos, iov_length(iov, nr_segs),
+	if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(to),
 				     tcon->ses->server->vals->shared_lock_type,
 				     NULL, CIFS_READ_OP))
-		rc = generic_file_aio_read(iocb, iov, nr_segs, pos);
+		rc = generic_file_read_iter(iocb, to);
 	up_read(&cinode->lock_sem);
 	return rc;
 }
@@ -3112,7 +3099,7 @@ int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)
 	xid = get_xid();
 
 	if (!CIFS_CACHE_READ(CIFS_I(inode))) {
-		rc = cifs_invalidate_mapping(inode);
+		rc = cifs_zap_mapping(inode);
 		if (rc)
 			return rc;
 	}
@@ -3631,13 +3618,6 @@ static int cifs_launder_page(struct page *page)
 	return rc;
 }
 
-static int
-cifs_pending_writers_wait(void *unused)
-{
-	schedule();
-	return 0;
-}
-
 void cifs_oplock_break(struct work_struct *work)
 {
 	struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
@@ -3649,7 +3629,7 @@ void cifs_oplock_break(struct work_struct *work)
 	int rc = 0;
 
 	wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
-			cifs_pending_writers_wait, TASK_UNINTERRUPTIBLE);
+			TASK_UNINTERRUPTIBLE);
 
 	server->ops->downgrade_oplock(server, cinode,
 		test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags));
@@ -3670,7 +3650,7 @@ void cifs_oplock_break(struct work_struct *work)
 		if (!CIFS_CACHE_READ(cinode)) {
 			rc = filemap_fdatawait(inode->i_mapping);
 			mapping_set_error(inode->i_mapping, rc);
-			cifs_invalidate_mapping(inode);
+			cifs_zap_mapping(inode);
 		}
 		cifs_dbg(FYI, "Oplock flush inode %p rc %d\n", inode, rc);
 	}
@@ -3703,8 +3683,8 @@ void cifs_oplock_break(struct work_struct *work)
  * Direct IO is not yet supported in the cached mode. 
  */
 static ssize_t
-cifs_direct_io(int rw, struct kiocb *iocb, const struct iovec *iov,
-               loff_t pos, unsigned long nr_segs)
+cifs_direct_io(int rw, struct kiocb *iocb, struct iov_iter *iter,
+               loff_t pos)
 {
         /*
          * FIXME
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a22d667f106..41de3935caa 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -22,6 +22,7 @@
 #include <linux/stat.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/freezer.h>
 #include <asm/div64.h>
 #include "cifsfs.h"
 #include "cifspdu.h"
@@ -117,7 +118,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 
 	cifs_dbg(FYI, "%s: invalidating inode %llu mapping\n",
 		 __func__, cifs_i->uniqueid);
-	cifs_i->invalid_mapping = true;
+	set_bit(CIFS_INO_INVALID_MAPPING, &cifs_i->flags);
 }
 
 /*
@@ -177,7 +178,10 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 	else
 		cifs_i->time = jiffies;
 
-	cifs_i->delete_pending = fattr->cf_flags & CIFS_FATTR_DELETE_PENDING;
+	if (fattr->cf_flags & CIFS_FATTR_DELETE_PENDING)
+		set_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags);
+	else
+		clear_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags);
 
 	cifs_i->server_eof = fattr->cf_eof;
 	/*
@@ -1121,7 +1125,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
 	}
 
 	/* try to set DELETE_ON_CLOSE */
-	if (!cifsInode->delete_pending) {
+	if (!test_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags)) {
 		rc = CIFSSMBSetFileDisposition(xid, tcon, true, fid.netfid,
 					       current->tgid);
 		/*
@@ -1138,7 +1142,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
 			rc = -EBUSY;
 			goto undo_rename;
 		}
-		cifsInode->delete_pending = true;
+		set_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags);
 	}
 
 out_close:
@@ -1759,23 +1763,62 @@ int
 cifs_invalidate_mapping(struct inode *inode)
 {
 	int rc = 0;
-	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
-
-	cifs_i->invalid_mapping = false;
 
 	if (inode->i_mapping && inode->i_mapping->nrpages != 0) {
 		rc = invalidate_inode_pages2(inode->i_mapping);
-		if (rc) {
+		if (rc)
 			cifs_dbg(VFS, "%s: could not invalidate inode %p\n",
 				 __func__, inode);
-			cifs_i->invalid_mapping = true;
-		}
 	}
 
 	cifs_fscache_reset_inode_cookie(inode);
 	return rc;
 }
 
+/**
+ * cifs_wait_bit_killable - helper for functions that are sleeping on bit locks
+ * @word: long word containing the bit lock
+ */
+static int
+cifs_wait_bit_killable(struct wait_bit_key *key)
+{
+	if (fatal_signal_pending(current))
+		return -ERESTARTSYS;
+	freezable_schedule_unsafe();
+	return 0;
+}
+
+int
+cifs_revalidate_mapping(struct inode *inode)
+{
+	int rc;
+	unsigned long *flags = &CIFS_I(inode)->flags;
+
+	rc = wait_on_bit_lock_action(flags, CIFS_INO_LOCK, cifs_wait_bit_killable,
+				     TASK_KILLABLE);
+	if (rc)
+		return rc;
+
+	if (test_and_clear_bit(CIFS_INO_INVALID_MAPPING, flags)) {
+		rc = cifs_invalidate_mapping(inode);
+		if (rc)
+			set_bit(CIFS_INO_INVALID_MAPPING, flags);
+	}
+
+	clear_bit_unlock(CIFS_INO_LOCK, flags);
+	smp_mb__after_atomic();
+	wake_up_bit(flags, CIFS_INO_LOCK);
+
+	return rc;
+}
+
+int
+cifs_zap_mapping(struct inode *inode)
+{
+	set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(inode)->flags);
+	return cifs_revalidate_mapping(inode);
+}
+
 int cifs_revalidate_file_attr(struct file *filp)
 {
 	int rc = 0;
@@ -1842,9 +1885,7 @@ int cifs_revalidate_file(struct file *filp)
 	if (rc)
 		return rc;
 
-	if (CIFS_I(inode)->invalid_mapping)
-		rc = cifs_invalidate_mapping(inode);
-	return rc;
+	return cifs_revalidate_mapping(inode);
 }
 
 /* revalidate a dentry's inode attributes */
@@ -1857,9 +1898,7 @@ int cifs_revalidate_dentry(struct dentry *dentry)
 	if (rc)
 		return rc;
 
-	if (CIFS_I(inode)->invalid_mapping)
-		rc = cifs_invalidate_mapping(inode);
-	return rc;
+	return cifs_revalidate_mapping(inode);
 }
 
 int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 77492301cc2..45cb59bcc79 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -85,7 +85,7 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
 		goto out_fput;
 	}
 
-	src_inode = src_file.file->f_dentry->d_inode;
+	src_inode = file_inode(src_file.file);
 
 	/*
 	 * Note: cifs case is easier than btrfs since server responsible for
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 264ece71bdb..68559fd557f 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -374,7 +374,7 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	oparms.cifs_sb = cifs_sb;
 	oparms.desired_access = GENERIC_WRITE;
 	oparms.create_options = create_options;
-	oparms.disposition = FILE_OPEN;
+	oparms.disposition = FILE_CREATE;
 	oparms.path = path;
 	oparms.fid = &fid;
 	oparms.reconnect = false;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 3b0c62e622d..6bf55d0ed49 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -582,7 +582,7 @@ int cifs_get_writer(struct cifsInodeInfo *cinode)
 
 start:
 	rc = wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_OPLOCK_BREAK,
-				   cifs_oplock_break_wait, TASK_KILLABLE);
+			 TASK_KILLABLE);
 	if (rc)
 		return rc;
 
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index 049884552e7..6834b9c3bec 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -795,8 +795,8 @@ cifs_print_status(__u32 status_code)
 	while (nt_errs[idx].nt_errstr != NULL) {
 		if (((nt_errs[idx].nt_errcode) & 0xFFFFFF) ==
 		    (status_code & 0xFFFFFF)) {
-			printk(KERN_NOTICE "Status code returned 0x%08x %s\n",
-				   status_code, nt_errs[idx].nt_errstr);
+			pr_notice("Status code returned 0x%08x %s\n",
+				  status_code, nt_errs[idx].nt_errstr);
 		}
 		idx++;
 	}
@@ -941,8 +941,9 @@ cifs_UnixTimeToNT(struct timespec t)
 	return (u64) t.tv_sec * 10000000 + t.tv_nsec/100 + NTFS_TIME_OFFSET;
 }
 
-static int total_days_of_prev_months[] =
-{0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334};
+static const int total_days_of_prev_months[] = {
+	0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334
+};
 
 struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
 {
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 35ddc3ed119..787844bde38 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1047,6 +1047,7 @@ smb2_create_lease_buf(u8 *lease_key, u8 oplock)
 	buf->ccontext.NameOffset = cpu_to_le16(offsetof
 				(struct create_lease, Name));
 	buf->ccontext.NameLength = cpu_to_le16(4);
+	/* SMB2_CREATE_REQUEST_LEASE is "RqLs" */
 	buf->Name[0] = 'R';
 	buf->Name[1] = 'q';
 	buf->Name[2] = 'L';
@@ -1073,6 +1074,7 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock)
 	buf->ccontext.NameOffset = cpu_to_le16(offsetof
 				(struct create_lease_v2, Name));
 	buf->ccontext.NameLength = cpu_to_le16(4);
+	/* SMB2_CREATE_REQUEST_LEASE is "RqLs" */
 	buf->Name[0] = 'R';
 	buf->Name[1] = 'q';
 	buf->Name[2] = 'L';
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 3802f8c94ac..b0b260dbb19 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -375,7 +375,12 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 
 	req->Capabilities = cpu_to_le32(ses->server->vals->req_capabilities);
 
-	memcpy(req->ClientGUID, cifs_client_guid, SMB2_CLIENT_GUID_SIZE);
+	/* ClientGUID must be zero for SMB2.02 dialect */
+	if (ses->server->vals->protocol_id == SMB20_PROT_ID)
+		memset(req->ClientGUID, 0, SMB2_CLIENT_GUID_SIZE);
+	else
+		memcpy(req->ClientGUID, server->client_guid,
+			SMB2_CLIENT_GUID_SIZE);
 
 	iov[0].iov_base = (char *)req;
 	/* 4 for rfc1002 length field */
@@ -478,7 +483,8 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 
 	vneg_inbuf.Capabilities =
 			cpu_to_le32(tcon->ses->server->vals->req_capabilities);
-	memcpy(vneg_inbuf.Guid, cifs_client_guid, SMB2_CLIENT_GUID_SIZE);
+	memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid,
+					SMB2_CLIENT_GUID_SIZE);
 
 	if (tcon->ses->sign)
 		vneg_inbuf.SecurityMode =
@@ -966,6 +972,7 @@ create_durable_buf(void)
 	buf->ccontext.NameOffset = cpu_to_le16(offsetof
 				(struct create_durable, Name));
 	buf->ccontext.NameLength = cpu_to_le16(4);
+	/* SMB2_CREATE_DURABLE_HANDLE_REQUEST is "DHnQ" */
 	buf->Name[0] = 'D';
 	buf->Name[1] = 'H';
 	buf->Name[2] = 'n';
@@ -990,6 +997,7 @@ create_reconnect_durable_buf(struct cifs_fid *fid)
 	buf->ccontext.NameLength = cpu_to_le16(4);
 	buf->Data.Fid.PersistentFileId = fid->persistent_fid;
 	buf->Data.Fid.VolatileFileId = fid->volatile_fid;
+	/* SMB2_CREATE_DURABLE_HANDLE_RECONNECT is "DHnC" */
 	buf->Name[0] = 'D';
 	buf->Name[1] = 'H';
 	buf->Name[2] = 'n';
@@ -1089,6 +1097,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	int rc = 0;
 	unsigned int num_iovecs = 2;
 	__u32 file_attributes = 0;
+	char *dhc_buf = NULL, *lc_buf = NULL;
 
 	cifs_dbg(FYI, "create/open\n");
 
@@ -1155,6 +1164,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 			kfree(copy_path);
 			return rc;
 		}
+		lc_buf = iov[num_iovecs-1].iov_base;
 	}
 
 	if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
@@ -1169,9 +1179,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		if (rc) {
 			cifs_small_buf_release(req);
 			kfree(copy_path);
-			kfree(iov[num_iovecs-1].iov_base);
+			kfree(lc_buf);
 			return rc;
 		}
+		dhc_buf = iov[num_iovecs-1].iov_base;
 	}
 
 	rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
@@ -1203,6 +1214,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		*oplock = rsp->OplockLevel;
 creat_exit:
 	kfree(copy_path);
+	kfree(lc_buf);
+	kfree(dhc_buf);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 2022c542ea3..69f3595d395 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -183,8 +183,6 @@ struct smb2_symlink_err_rsp {
 
 #define SMB2_CLIENT_GUID_SIZE 16
 
-extern __u8 cifs_client_guid[SMB2_CLIENT_GUID_SIZE];
-
 struct smb2_negotiate_req {
 	struct smb2_hdr hdr;
 	__le16 StructureSize; /* Must be 36 */
@@ -437,11 +435,15 @@ struct smb2_tree_disconnect_rsp {
 #define SMB2_CREATE_SD_BUFFER			"SecD" /* security descriptor */
 #define SMB2_CREATE_DURABLE_HANDLE_REQUEST	"DHnQ"
 #define SMB2_CREATE_DURABLE_HANDLE_RECONNECT	"DHnC"
-#define SMB2_CREATE_ALLOCATION_SIZE		"AlSi"
+#define SMB2_CREATE_ALLOCATION_SIZE		"AISi"
 #define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc"
 #define SMB2_CREATE_TIMEWARP_REQUEST		"TWrp"
 #define SMB2_CREATE_QUERY_ON_DISK_ID		"QFid"
 #define SMB2_CREATE_REQUEST_LEASE		"RqLs"
+#define SMB2_CREATE_DURABLE_HANDLE_REQUEST_V2	"DH2Q"
+#define SMB2_CREATE_DURABLE_HANDLE_RECONNECT_V2	"DH2C"
+#define SMB2_CREATE_APP_INSTANCE_ID	0x45BCA66AEFA7F74A9008FA462E144D74
+#define SVHDX_OPEN_DEVICE_CONTEXT	0x83CE6F1AD851E0986E34401CC9BCFCE9
 
 struct smb2_create_req {
 	struct smb2_hdr hdr;
diff --git a/fs/coredump.c b/fs/coredump.c
index 0b2528fb640..a93f7e6ea4c 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -306,7 +306,7 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm,
 	if (unlikely(nr < 0))
 		return nr;
 
-	tsk->flags = PF_DUMPCORE;
+	tsk->flags |= PF_DUMPCORE;
 	if (atomic_read(&mm->mm_users) == nr + 1)
 		goto done;
 	/*
diff --git a/fs/dcache.c b/fs/dcache.c
index 1792d6075b4..06f65857a85 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -532,10 +532,12 @@ static inline struct dentry *lock_parent(struct dentry *dentry)
 	struct dentry *parent = dentry->d_parent;
 	if (IS_ROOT(dentry))
 		return NULL;
+	if (unlikely((int)dentry->d_lockref.count < 0))
+		return NULL;
 	if (likely(spin_trylock(&parent->d_lock)))
 		return parent;
-	spin_unlock(&dentry->d_lock);
 	rcu_read_lock();
+	spin_unlock(&dentry->d_lock);
 again:
 	parent = ACCESS_ONCE(dentry->d_parent);
 	spin_lock(&parent->d_lock);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 31ba0935e32..17e39b047de 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -71,13 +71,11 @@ struct dio_submit {
 					   been performed at the start of a
 					   write */
 	int pages_in_io;		/* approximate total IO pages */
-	size_t	size;			/* total request size (doesn't change)*/
 	sector_t block_in_file;		/* Current offset into the underlying
 					   file in dio_block units. */
 	unsigned blocks_available;	/* At block_in_file.  changes */
 	int reap_counter;		/* rate limit reaping */
 	sector_t final_block_in_request;/* doesn't change */
-	unsigned first_block_in_page;	/* doesn't change, Used only once */
 	int boundary;			/* prev block is at a boundary */
 	get_block_t *get_block;		/* block mapping function */
 	dio_submit_t *submit_io;	/* IO submition function */
@@ -98,19 +96,14 @@ struct dio_submit {
 	sector_t cur_page_block;	/* Where it starts */
 	loff_t cur_page_fs_offset;	/* Offset in file */
 
-	/*
-	 * Page fetching state. These variables belong to dio_refill_pages().
-	 */
-	int curr_page;			/* changes */
-	int total_pages;		/* doesn't change */
-	unsigned long curr_user_address;/* changes */
-
+	struct iov_iter *iter;
 	/*
 	 * Page queue.  These variables belong to dio_refill_pages() and
 	 * dio_get_page().
 	 */
 	unsigned head;			/* next page to process */
 	unsigned tail;			/* last valid page + 1 */
+	size_t from, to;
 };
 
 /* dio_state communicated between submission path and end_io */
@@ -163,15 +156,10 @@ static inline unsigned dio_pages_present(struct dio_submit *sdio)
  */
 static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
 {
-	int ret;
-	int nr_pages;
+	ssize_t ret;
 
-	nr_pages = min(sdio->total_pages - sdio->curr_page, DIO_PAGES);
-	ret = get_user_pages_fast(
-		sdio->curr_user_address,		/* Where from? */
-		nr_pages,			/* How many pages? */
-		dio->rw == READ,		/* Write to memory? */
-		&dio->pages[0]);		/* Put results here */
+	ret = iov_iter_get_pages(sdio->iter, dio->pages, DIO_PAGES * PAGE_SIZE,
+				&sdio->from);
 
 	if (ret < 0 && sdio->blocks_available && (dio->rw & WRITE)) {
 		struct page *page = ZERO_PAGE(0);
@@ -186,18 +174,19 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
 		dio->pages[0] = page;
 		sdio->head = 0;
 		sdio->tail = 1;
-		ret = 0;
-		goto out;
+		sdio->from = 0;
+		sdio->to = PAGE_SIZE;
+		return 0;
 	}
 
 	if (ret >= 0) {
-		sdio->curr_user_address += ret * PAGE_SIZE;
-		sdio->curr_page += ret;
+		iov_iter_advance(sdio->iter, ret);
+		ret += sdio->from;
 		sdio->head = 0;
-		sdio->tail = ret;
-		ret = 0;
+		sdio->tail = (ret + PAGE_SIZE - 1) / PAGE_SIZE;
+		sdio->to = ((ret - 1) & (PAGE_SIZE - 1)) + 1;
+		return 0;
 	}
-out:
 	return ret;	
 }
 
@@ -208,7 +197,7 @@ out:
  * L1 cache.
  */
 static inline struct page *dio_get_page(struct dio *dio,
-		struct dio_submit *sdio)
+					struct dio_submit *sdio)
 {
 	if (dio_pages_present(sdio) == 0) {
 		int ret;
@@ -218,7 +207,7 @@ static inline struct page *dio_get_page(struct dio *dio,
 			return ERR_PTR(ret);
 		BUG_ON(dio_pages_present(sdio) == 0);
 	}
-	return dio->pages[sdio->head++];
+	return dio->pages[sdio->head];
 }
 
 /**
@@ -422,8 +411,8 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
  */
 static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio)
 {
-	while (dio_pages_present(sdio))
-		page_cache_release(dio_get_page(dio, sdio));
+	while (sdio->head < sdio->tail)
+		page_cache_release(dio->pages[sdio->head++]);
 }
 
 /*
@@ -912,23 +901,22 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio,
 			struct buffer_head *map_bh)
 {
 	const unsigned blkbits = sdio->blkbits;
-	const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
-	struct page *page;
-	unsigned block_in_page;
 	int ret = 0;
 
-	/* The I/O can start at any block offset within the first page */
-	block_in_page = sdio->first_block_in_page;
-
 	while (sdio->block_in_file < sdio->final_block_in_request) {
+		struct page *page;
+		size_t from, to;
+
 		page = dio_get_page(dio, sdio);
 		if (IS_ERR(page)) {
 			ret = PTR_ERR(page);
 			goto out;
 		}
+		from = sdio->head ? 0 : sdio->from;
+		to = (sdio->head == sdio->tail - 1) ? sdio->to : PAGE_SIZE;
+		sdio->head++;
 
-		while (block_in_page < blocks_per_page) {
-			unsigned offset_in_page = block_in_page << blkbits;
+		while (from < to) {
 			unsigned this_chunk_bytes;	/* # of bytes mapped */
 			unsigned this_chunk_blocks;	/* # of blocks */
 			unsigned u;
@@ -999,10 +987,10 @@ do_holes:
 					page_cache_release(page);
 					goto out;
 				}
-				zero_user(page, block_in_page << blkbits,
-						1 << blkbits);
+				zero_user(page, from, 1 << blkbits);
 				sdio->block_in_file++;
-				block_in_page++;
+				from += 1 << blkbits;
+				dio->result += 1 << blkbits;
 				goto next_block;
 			}
 
@@ -1019,7 +1007,7 @@ do_holes:
 			 * can add to this page
 			 */
 			this_chunk_blocks = sdio->blocks_available;
-			u = (PAGE_SIZE - offset_in_page) >> blkbits;
+			u = (to - from) >> blkbits;
 			if (this_chunk_blocks > u)
 				this_chunk_blocks = u;
 			u = sdio->final_block_in_request - sdio->block_in_file;
@@ -1031,7 +1019,7 @@ do_holes:
 			if (this_chunk_blocks == sdio->blocks_available)
 				sdio->boundary = buffer_boundary(map_bh);
 			ret = submit_page_section(dio, sdio, page,
-						  offset_in_page,
+						  from,
 						  this_chunk_bytes,
 						  sdio->next_block_for_io,
 						  map_bh);
@@ -1042,7 +1030,8 @@ do_holes:
 			sdio->next_block_for_io += this_chunk_blocks;
 
 			sdio->block_in_file += this_chunk_blocks;
-			block_in_page += this_chunk_blocks;
+			from += this_chunk_bytes;
+			dio->result += this_chunk_bytes;
 			sdio->blocks_available -= this_chunk_blocks;
 next_block:
 			BUG_ON(sdio->block_in_file > sdio->final_block_in_request);
@@ -1052,7 +1041,6 @@ next_block:
 
 		/* Drop the ref which was taken in get_user_pages() */
 		page_cache_release(page);
-		block_in_page = 0;
 	}
 out:
 	return ret;
@@ -1107,24 +1095,21 @@ static inline int drop_refcount(struct dio *dio)
  */
 static inline ssize_t
 do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
-	struct block_device *bdev, const struct iovec *iov, loff_t offset, 
-	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
+	struct block_device *bdev, struct iov_iter *iter, loff_t offset, 
+	get_block_t get_block, dio_iodone_t end_io,
 	dio_submit_t submit_io,	int flags)
 {
-	int seg;
-	size_t size;
-	unsigned long addr;
 	unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits);
 	unsigned blkbits = i_blkbits;
 	unsigned blocksize_mask = (1 << blkbits) - 1;
 	ssize_t retval = -EINVAL;
-	loff_t end = offset;
+	size_t count = iov_iter_count(iter);
+	loff_t end = offset + count;
 	struct dio *dio;
 	struct dio_submit sdio = { 0, };
-	unsigned long user_addr;
-	size_t bytes;
 	struct buffer_head map_bh = { 0, };
 	struct blk_plug plug;
+	unsigned long align = offset | iov_iter_alignment(iter);
 
 	if (rw & WRITE)
 		rw = WRITE_ODIRECT;
@@ -1134,32 +1119,16 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	 * the early prefetch in the caller enough time.
 	 */
 
-	if (offset & blocksize_mask) {
+	if (align & blocksize_mask) {
 		if (bdev)
 			blkbits = blksize_bits(bdev_logical_block_size(bdev));
 		blocksize_mask = (1 << blkbits) - 1;
-		if (offset & blocksize_mask)
+		if (align & blocksize_mask)
 			goto out;
 	}
 
-	/* Check the memory alignment.  Blocks cannot straddle pages */
-	for (seg = 0; seg < nr_segs; seg++) {
-		addr = (unsigned long)iov[seg].iov_base;
-		size = iov[seg].iov_len;
-		end += size;
-		if (unlikely((addr & blocksize_mask) ||
-			     (size & blocksize_mask))) {
-			if (bdev)
-				blkbits = blksize_bits(
-					 bdev_logical_block_size(bdev));
-			blocksize_mask = (1 << blkbits) - 1;
-			if ((addr & blocksize_mask) || (size & blocksize_mask))
-				goto out;
-		}
-	}
-
 	/* watch out for a 0 len io from a tricksy fs */
-	if (rw == READ && end == offset)
+	if (rw == READ && !iov_iter_count(iter))
 		return 0;
 
 	dio = kmem_cache_alloc(dio_cache, GFP_KERNEL);
@@ -1249,6 +1218,10 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	spin_lock_init(&dio->bio_lock);
 	dio->refcount = 1;
 
+	sdio.iter = iter;
+	sdio.final_block_in_request =
+		(offset + iov_iter_count(iter)) >> blkbits;
+
 	/*
 	 * In case of non-aligned buffers, we may need 2 more
 	 * pages since we need to zero out first and last block.
@@ -1256,47 +1229,13 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	if (unlikely(sdio.blkfactor))
 		sdio.pages_in_io = 2;
 
-	for (seg = 0; seg < nr_segs; seg++) {
-		user_addr = (unsigned long)iov[seg].iov_base;
-		sdio.pages_in_io +=
-			((user_addr + iov[seg].iov_len + PAGE_SIZE-1) /
-				PAGE_SIZE - user_addr / PAGE_SIZE);
-	}
+	sdio.pages_in_io += iov_iter_npages(iter, INT_MAX);
 
 	blk_start_plug(&plug);
 
-	for (seg = 0; seg < nr_segs; seg++) {
-		user_addr = (unsigned long)iov[seg].iov_base;
-		sdio.size += bytes = iov[seg].iov_len;
-
-		/* Index into the first page of the first block */
-		sdio.first_block_in_page = (user_addr & ~PAGE_MASK) >> blkbits;
-		sdio.final_block_in_request = sdio.block_in_file +
-						(bytes >> blkbits);
-		/* Page fetching state */
-		sdio.head = 0;
-		sdio.tail = 0;
-		sdio.curr_page = 0;
-
-		sdio.total_pages = 0;
-		if (user_addr & (PAGE_SIZE-1)) {
-			sdio.total_pages++;
-			bytes -= PAGE_SIZE - (user_addr & (PAGE_SIZE - 1));
-		}
-		sdio.total_pages += (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
-		sdio.curr_user_address = user_addr;
-
-		retval = do_direct_IO(dio, &sdio, &map_bh);
-
-		dio->result += iov[seg].iov_len -
-			((sdio.final_block_in_request - sdio.block_in_file) <<
-					blkbits);
-
-		if (retval) {
-			dio_cleanup(dio, &sdio);
-			break;
-		}
-	} /* end iovec loop */
+	retval = do_direct_IO(dio, &sdio, &map_bh);
+	if (retval)
+		dio_cleanup(dio, &sdio);
 
 	if (retval == -ENOTBLK) {
 		/*
@@ -1348,10 +1287,9 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	 */
 	BUG_ON(retval == -EIOCBQUEUED);
 	if (dio->is_async && retval == 0 && dio->result &&
-	    ((rw == READ) || (dio->result == sdio.size)))
+	    (rw == READ || dio->result == count))
 		retval = -EIOCBQUEUED;
-
-	if (retval != -EIOCBQUEUED)
+	else
 		dio_await_completion(dio);
 
 	if (drop_refcount(dio) == 0) {
@@ -1365,8 +1303,8 @@ out:
 
 ssize_t
 __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
-	struct block_device *bdev, const struct iovec *iov, loff_t offset,
-	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
+	struct block_device *bdev, struct iov_iter *iter, loff_t offset,
+	get_block_t get_block, dio_iodone_t end_io,
 	dio_submit_t submit_io,	int flags)
 {
 	/*
@@ -1381,9 +1319,8 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	prefetch(bdev->bd_queue);
 	prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);
 
-	return do_blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
-				     nr_segs, get_block, end_io,
-				     submit_io, flags);
+	return do_blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset,
+				     get_block, end_io, submit_io, flags);
 }
 
 EXPORT_SYMBOL(__blockdev_direct_IO);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 1e5b4535950..d08e079ea5d 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -617,6 +617,11 @@ static void retry_failed_sctp_send(struct connection *recv_con,
 	int nodeid = sn_send_failed->ssf_info.sinfo_ppid;
 
 	log_print("Retry sending %d bytes to node id %d", len, nodeid);
+	
+	if (!nodeid) {
+		log_print("Shouldn't resend data via listening connection.");
+		return;
+	}
 
 	con = nodeid2con(nodeid, 0);
 	if (!con) {
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index b1eaa7a1f82..db0fad3269c 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -45,14 +45,13 @@
  * The function to be used for directory reads is ecryptfs_read.
  */
 static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb,
-				const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos)
+				struct iov_iter *to)
 {
 	ssize_t rc;
 	struct path *path;
 	struct file *file = iocb->ki_filp;
 
-	rc = generic_file_aio_read(iocb, iov, nr_segs, pos);
+	rc = generic_file_read_iter(iocb, to);
 	/*
 	 * Even though this is a async interface, we need to wait
 	 * for IO to finish to update atime
@@ -352,10 +351,10 @@ const struct file_operations ecryptfs_dir_fops = {
 
 const struct file_operations ecryptfs_main_fops = {
 	.llseek = generic_file_llseek,
-	.read = do_sync_read,
-	.aio_read = ecryptfs_read_update_atime,
-	.write = do_sync_write,
-	.aio_write = generic_file_aio_write,
+	.read = new_sync_read,
+	.read_iter = ecryptfs_read_update_atime,
+	.write = new_sync_write,
+	.write_iter = generic_file_write_iter,
 	.iterate = ecryptfs_readdir,
 	.unlocked_ioctl = ecryptfs_unlocked_ioctl,
 #ifdef CONFIG_COMPAT
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index b73e0621ce9..b10b48c2a7a 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -910,7 +910,7 @@ static const struct file_operations eventpoll_fops = {
 void eventpoll_release_file(struct file *file)
 {
 	struct eventpoll *ep;
-	struct epitem *epi;
+	struct epitem *epi, *next;
 
 	/*
 	 * We don't want to get "file->f_lock" because it is not
@@ -926,7 +926,7 @@ void eventpoll_release_file(struct file *file)
 	 * Besides, ep_remove() acquires the lock, so we can't hold it here.
 	 */
 	mutex_lock(&epmutex);
-	list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
+	list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
 		ep = epi->ep;
 		mutex_lock_nested(&ep->mtx, 0);
 		ep_remove(ep, epi);
diff --git a/fs/exec.c b/fs/exec.c
index 238b7aa26f6..a3d33fe592d 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1046,13 +1046,13 @@ EXPORT_SYMBOL_GPL(get_task_comm);
  * so that a new one can be started
  */
 
-void set_task_comm(struct task_struct *tsk, const char *buf)
+void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec)
 {
 	task_lock(tsk);
 	trace_task_rename(tsk, buf);
 	strlcpy(tsk->comm, buf, sizeof(tsk->comm));
 	task_unlock(tsk);
-	perf_event_comm(tsk);
+	perf_event_comm(tsk, exec);
 }
 
 int flush_old_exec(struct linux_binprm * bprm)
@@ -1110,7 +1110,8 @@ void setup_new_exec(struct linux_binprm * bprm)
 	else
 		set_dumpable(current->mm, suid_dumpable);
 
-	set_task_comm(current, kbasename(bprm->filename));
+	perf_event_exec();
+	__set_task_comm(current, kbasename(bprm->filename), true);
 
 	/* Set the new mm task size. We have to do that late because it may
 	 * depend on TIF_32BIT which is only updated in flush_thread() on
diff --git a/fs/exofs/file.c b/fs/exofs/file.c
index 491c6c078e7..71bf8e4fb5d 100644
--- a/fs/exofs/file.c
+++ b/fs/exofs/file.c
@@ -67,17 +67,17 @@ static int exofs_flush(struct file *file, fl_owner_t id)
 
 const struct file_operations exofs_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.open		= generic_file_open,
 	.release	= exofs_release_file,
 	.fsync		= exofs_file_fsync,
 	.flush		= exofs_flush,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 };
 
 const struct inode_operations exofs_file_inode_operations = {
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index d1c244d6766..3f9cafd7393 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -964,7 +964,7 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset,
 
  /* TODO: Should be easy enough to do proprly */
 static ssize_t exofs_direct_IO(int rw, struct kiocb *iocb,
-		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+		struct iov_iter *iter, loff_t offset)
 {
 	return 0;
 }
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 44c36e59076..7c87b22a722 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -62,10 +62,10 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
  */
 const struct file_operations ext2_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.unlocked_ioctl = ext2_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext2_compat_ioctl,
@@ -75,7 +75,7 @@ const struct file_operations ext2_file_operations = {
 	.release	= ext2_release_file,
 	.fsync		= ext2_fsync,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 };
 
 #ifdef CONFIG_EXT2_FS_XIP
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index b1d2a4675d4..36d35c36311 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -850,18 +850,18 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
 }
 
 static ssize_t
-ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs)
+ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+			loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
-				 ext2_get_block);
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext2_get_block);
 	if (ret < 0 && (rw & WRITE))
-		ext2_write_failed(mapping, offset + iov_length(iov, nr_segs));
+		ext2_write_failed(mapping, offset + count);
 	return ret;
 }
 
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index aad05311392..a062fa1e1b1 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -50,10 +50,10 @@ static int ext3_release_file (struct inode * inode, struct file * filp)
 
 const struct file_operations ext3_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.unlocked_ioctl	= ext3_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext3_compat_ioctl,
@@ -63,7 +63,7 @@ const struct file_operations ext3_file_operations = {
 	.release	= ext3_release_file,
 	.fsync		= ext3_sync_file,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 };
 
 const struct inode_operations ext3_file_inode_operations = {
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index f5157d0d1b4..2c6ccc49ba2 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1716,17 +1716,17 @@ static int ext3_journalled_writepage(struct page *page,
 	WARN_ON_ONCE(IS_RDONLY(inode) &&
 		     !(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS));
 
-	if (ext3_journal_current_handle())
-		goto no_write;
-
 	trace_ext3_journalled_writepage(page);
-	handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode));
-	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		goto no_write;
-	}
-
 	if (!page_has_buffers(page) || PageChecked(page)) {
+		if (ext3_journal_current_handle())
+			goto no_write;
+
+		handle = ext3_journal_start(inode,
+					    ext3_writepage_trans_blocks(inode));
+		if (IS_ERR(handle)) {
+			ret = PTR_ERR(handle);
+			goto no_write;
+		}
 		/*
 		 * It's mmapped pagecache.  Add buffers and journal it.  There
 		 * doesn't seem much point in redirtying the page here.
@@ -1749,17 +1749,18 @@ static int ext3_journalled_writepage(struct page *page,
 		atomic_set(&EXT3_I(inode)->i_datasync_tid,
 			   handle->h_transaction->t_tid);
 		unlock_page(page);
+		err = ext3_journal_stop(handle);
+		if (!ret)
+			ret = err;
 	} else {
 		/*
-		 * It may be a page full of checkpoint-mode buffers.  We don't
-		 * really know unless we go poke around in the buffer_heads.
-		 * But block_write_full_page will do the right thing.
+		 * It is a page full of checkpoint-mode buffers. Go and write
+		 * them. They should have been already mapped when they went
+		 * to the journal so provide NULL get_block function to catch
+		 * errors.
 		 */
-		ret = block_write_full_page(page, ext3_get_block, wbc);
+		ret = block_write_full_page(page, NULL, wbc);
 	}
-	err = ext3_journal_stop(handle);
-	if (!ret)
-		ret = err;
 out:
 	return ret;
 
@@ -1820,8 +1821,7 @@ static int ext3_releasepage(struct page *page, gfp_t wait)
  * VFS code falls back into buffered path in that case so we are safe.
  */
 static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
-			const struct iovec *iov, loff_t offset,
-			unsigned long nr_segs)
+			struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -1829,10 +1829,10 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
 	handle_t *handle;
 	ssize_t ret;
 	int orphan = 0;
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(iter);
 	int retries = 0;
 
-	trace_ext3_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
+	trace_ext3_direct_IO_enter(inode, offset, count, rw);
 
 	if (rw == WRITE) {
 		loff_t final_size = offset + count;
@@ -1856,15 +1856,14 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retry:
-	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
-				 ext3_get_block);
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext3_get_block);
 	/*
 	 * In case of error extending write may have instantiated a few
 	 * blocks outside i_size. Trim these off again.
 	 */
 	if (unlikely((rw & WRITE) && ret < 0)) {
 		loff_t isize = i_size_read(inode);
-		loff_t end = offset + iov_length(iov, nr_segs);
+		loff_t end = offset + count;
 
 		if (end > isize)
 			ext3_truncate_failed_direct_write(inode);
@@ -1909,8 +1908,7 @@ retry:
 			ret = err;
 	}
 out:
-	trace_ext3_direct_IO_exit(inode, offset,
-				iov_length(iov, nr_segs), rw, ret);
+	trace_ext3_direct_IO_exit(inode, offset, count, rw, ret);
 	return ret;
 }
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 5c56785007e..fca382037dd 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -83,9 +83,9 @@ static inline int ext4_block_in_group(struct super_block *sb,
 /* Return the number of clusters used for file system metadata; this
  * represents the overhead needed by the file system.
  */
-unsigned ext4_num_overhead_clusters(struct super_block *sb,
-				    ext4_group_t block_group,
-				    struct ext4_group_desc *gdp)
+static unsigned ext4_num_overhead_clusters(struct super_block *sb,
+					   ext4_group_t block_group,
+					   struct ext4_group_desc *gdp)
 {
 	unsigned num_clusters;
 	int block_cluster = -1, inode_cluster = -1, itbl_cluster = -1, i, c;
@@ -176,9 +176,10 @@ static unsigned int num_clusters_in_group(struct super_block *sb,
 }
 
 /* Initializes an uninitialized block bitmap */
-void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
-			    ext4_group_t block_group,
-			    struct ext4_group_desc *gdp)
+static void ext4_init_block_bitmap(struct super_block *sb,
+				   struct buffer_head *bh,
+				   ext4_group_t block_group,
+				   struct ext4_group_desc *gdp)
 {
 	unsigned int bit, bit_max;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -193,7 +194,16 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
 		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, gdp);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
 		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return;
 	}
@@ -307,6 +317,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 					    ext4_group_t block_group,
 					    struct buffer_head *bh)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_grpblk_t offset;
 	ext4_grpblk_t next_zero_bit;
 	ext4_fsblk_t blk;
@@ -326,14 +337,14 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 	/* check whether block bitmap block number is set */
 	blk = ext4_block_bitmap(sb, desc);
 	offset = blk - group_first_block;
-	if (!ext4_test_bit(offset, bh->b_data))
+	if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
 		/* bad block bitmap */
 		return blk;
 
 	/* check whether the inode bitmap block number is set */
 	blk = ext4_inode_bitmap(sb, desc);
 	offset = blk - group_first_block;
-	if (!ext4_test_bit(offset, bh->b_data))
+	if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
 		/* bad block bitmap */
 		return blk;
 
@@ -341,21 +352,23 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
 	blk = ext4_inode_table(sb, desc);
 	offset = blk - group_first_block;
 	next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
-				offset + EXT4_SB(sb)->s_itb_per_group,
-				offset);
-	if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group)
+			EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group),
+			EXT4_B2C(sbi, offset));
+	if (next_zero_bit <
+	    EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group))
 		/* bad bitmap for inode tables */
 		return blk;
 	return 0;
 }
 
-void ext4_validate_block_bitmap(struct super_block *sb,
-			       struct ext4_group_desc *desc,
-			       ext4_group_t block_group,
-			       struct buffer_head *bh)
+static void ext4_validate_block_bitmap(struct super_block *sb,
+				       struct ext4_group_desc *desc,
+				       ext4_group_t block_group,
+				       struct buffer_head *bh)
 {
 	ext4_fsblk_t	blk;
 	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (buffer_verified(bh))
 		return;
@@ -366,6 +379,9 @@ void ext4_validate_block_bitmap(struct super_block *sb,
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
 			   block_group, blk);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return;
 	}
@@ -373,6 +389,9 @@ void ext4_validate_block_bitmap(struct super_block *sb,
 			desc, bh))) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return;
 	}
@@ -708,16 +727,6 @@ static inline int test_root(ext4_group_t a, int b)
 	}
 }
 
-static int ext4_group_sparse(ext4_group_t group)
-{
-	if (group <= 1)
-		return 1;
-	if (!(group & 1))
-		return 0;
-	return (test_root(group, 7) || test_root(group, 5) ||
-		test_root(group, 3));
-}
-
 /**
  *	ext4_bg_has_super - number of blocks used by the superblock in group
  *	@sb: superblock for filesystem
@@ -728,11 +737,26 @@ static int ext4_group_sparse(ext4_group_t group)
  */
 int ext4_bg_has_super(struct super_block *sb, ext4_group_t group)
 {
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
-				EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER) &&
-			!ext4_group_sparse(group))
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+	if (group == 0)
+		return 1;
+	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_SPARSE_SUPER2)) {
+		if (group == le32_to_cpu(es->s_backup_bgs[0]) ||
+		    group == le32_to_cpu(es->s_backup_bgs[1]))
+			return 1;
+		return 0;
+	}
+	if ((group <= 1) || !EXT4_HAS_RO_COMPAT_FEATURE(sb,
+					EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER))
+		return 1;
+	if (!(group & 1))
 		return 0;
-	return 1;
+	if (test_root(group, 3) || (test_root(group, 5)) ||
+	    test_root(group, 7))
+		return 1;
+
+	return 0;
 }
 
 static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index d638c57e996..ef1bed66c14 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -105,7 +105,7 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
 static int ext4_readdir(struct file *file, struct dir_context *ctx)
 {
 	unsigned int offset;
-	int i, stored;
+	int i;
 	struct ext4_dir_entry_2 *de;
 	int err;
 	struct inode *inode = file_inode(file);
@@ -133,7 +133,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
 			return ret;
 	}
 
-	stored = 0;
 	offset = ctx->pos & (sb->s_blocksize - 1);
 
 	while (ctx->pos < inode->i_size) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 66946aa6212..7cc5a0e2368 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -158,7 +158,6 @@ struct ext4_allocation_request {
 #define EXT4_MAP_MAPPED		(1 << BH_Mapped)
 #define EXT4_MAP_UNWRITTEN	(1 << BH_Unwritten)
 #define EXT4_MAP_BOUNDARY	(1 << BH_Boundary)
-#define EXT4_MAP_UNINIT		(1 << BH_Uninit)
 /* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of
  * ext4_map_blocks wants to know whether or not the underlying cluster has
  * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that
@@ -169,7 +168,7 @@ struct ext4_allocation_request {
 #define EXT4_MAP_FROM_CLUSTER	(1 << BH_AllocFromCluster)
 #define EXT4_MAP_FLAGS		(EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
 				 EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
-				 EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER)
+				 EXT4_MAP_FROM_CLUSTER)
 
 struct ext4_map_blocks {
 	ext4_fsblk_t m_pblk;
@@ -184,7 +183,7 @@ struct ext4_map_blocks {
 #define	EXT4_IO_END_UNWRITTEN	0x0001
 
 /*
- * For converting uninitialized extents on a work queue. 'handle' is used for
+ * For converting unwritten extents on a work queue. 'handle' is used for
  * buffered writeback.
  */
 typedef struct ext4_io_end {
@@ -537,26 +536,26 @@ enum {
 /*
  * Flags used by ext4_map_blocks()
  */
-	/* Allocate any needed blocks and/or convert an unitialized
+	/* Allocate any needed blocks and/or convert an unwritten
 	   extent to be an initialized ext4 */
 #define EXT4_GET_BLOCKS_CREATE			0x0001
-	/* Request the creation of an unitialized extent */
-#define EXT4_GET_BLOCKS_UNINIT_EXT		0x0002
-#define EXT4_GET_BLOCKS_CREATE_UNINIT_EXT	(EXT4_GET_BLOCKS_UNINIT_EXT|\
+	/* Request the creation of an unwritten extent */
+#define EXT4_GET_BLOCKS_UNWRIT_EXT		0x0002
+#define EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT	(EXT4_GET_BLOCKS_UNWRIT_EXT|\
 						 EXT4_GET_BLOCKS_CREATE)
 	/* Caller is from the delayed allocation writeout path
 	 * finally doing the actual allocation of delayed blocks */
 #define EXT4_GET_BLOCKS_DELALLOC_RESERVE	0x0004
 	/* caller is from the direct IO path, request to creation of an
-	unitialized extents if not allocated, split the uninitialized
+	unwritten extents if not allocated, split the unwritten
 	extent if blocks has been preallocated already*/
 #define EXT4_GET_BLOCKS_PRE_IO			0x0008
 #define EXT4_GET_BLOCKS_CONVERT			0x0010
 #define EXT4_GET_BLOCKS_IO_CREATE_EXT		(EXT4_GET_BLOCKS_PRE_IO|\
-					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
 	/* Convert extent to initialized after IO complete */
 #define EXT4_GET_BLOCKS_IO_CONVERT_EXT		(EXT4_GET_BLOCKS_CONVERT|\
-					 EXT4_GET_BLOCKS_CREATE_UNINIT_EXT)
+					 EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT)
 	/* Eventual metadata allocation (due to growing extent tree)
 	 * should not fail, so try to use reserved blocks for that.*/
 #define EXT4_GET_BLOCKS_METADATA_NOFAIL		0x0020
@@ -876,6 +875,8 @@ struct ext4_inode_info {
 	struct inode vfs_inode;
 	struct jbd2_inode *jinode;
 
+	spinlock_t i_raw_lock;	/* protects updates to the raw inode */
+
 	/*
 	 * File creation time. Its function is same as that of
 	 * struct timespec i_{a,c,m}time in the generic inode.
@@ -1159,7 +1160,8 @@ struct ext4_super_block {
 	__le32	s_usr_quota_inum;	/* inode for tracking user quota */
 	__le32	s_grp_quota_inum;	/* inode for tracking group quota */
 	__le32	s_overhead_clusters;	/* overhead blocks/clusters in fs */
-	__le32	s_reserved[108];	/* Padding to the end of the block */
+	__le32	s_backup_bgs[2];	/* groups with sparse_super2 SBs */
+	__le32	s_reserved[106];	/* Padding to the end of the block */
 	__le32	s_checksum;		/* crc32c(superblock) */
 };
 
@@ -1505,6 +1507,7 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_COMPAT_EXT_ATTR		0x0008
 #define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
 #define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
+#define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
 
 #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
@@ -1953,10 +1956,6 @@ extern void ext4_get_group_no_and_offset(struct super_block *sb,
 extern ext4_group_t ext4_get_group_number(struct super_block *sb,
 					  ext4_fsblk_t block);
 
-extern void ext4_validate_block_bitmap(struct super_block *sb,
-				       struct ext4_group_desc *desc,
-				       ext4_group_t block_group,
-				       struct buffer_head *bh);
 extern unsigned int ext4_block_group(struct super_block *sb,
 			ext4_fsblk_t blocknr);
 extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb,
@@ -1985,16 +1984,9 @@ extern int ext4_wait_block_bitmap(struct super_block *sb,
 				  struct buffer_head *bh);
 extern struct buffer_head *ext4_read_block_bitmap(struct super_block *sb,
 						  ext4_group_t block_group);
-extern void ext4_init_block_bitmap(struct super_block *sb,
-				   struct buffer_head *bh,
-				   ext4_group_t group,
-				   struct ext4_group_desc *desc);
 extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
 					      ext4_group_t block_group,
 					      struct ext4_group_desc *gdp);
-extern unsigned ext4_num_overhead_clusters(struct super_block *sb,
-					   ext4_group_t block_group,
-					   struct ext4_group_desc *gdp);
 ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
 
 /* dir.c */
@@ -2137,8 +2129,6 @@ extern int ext4_alloc_da_blocks(struct inode *inode);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);
 extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
-extern int ext4_block_truncate_page(handle_t *handle,
-		struct address_space *mapping, loff_t from);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
 extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
@@ -2150,8 +2140,7 @@ extern void ext4_da_update_reserve_space(struct inode *inode,
 extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 				struct ext4_map_blocks *map, int flags);
 extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
-				const struct iovec *iov, loff_t offset,
-				unsigned long nr_segs);
+				struct iov_iter *iter, loff_t offset);
 extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
 extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
 extern void ext4_ind_truncate(handle_t *, struct inode *inode);
@@ -2198,8 +2187,6 @@ extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
 
 /* super.c */
 extern int ext4_calculate_overhead(struct super_block *sb);
-extern int ext4_superblock_csum_verify(struct super_block *sb,
-				       struct ext4_super_block *es);
 extern void ext4_superblock_csum_set(struct super_block *sb);
 extern void *ext4_kvmalloc(size_t size, gfp_t flags);
 extern void *ext4_kvzalloc(size_t size, gfp_t flags);
@@ -2571,19 +2558,11 @@ extern const struct file_operations ext4_dir_operations;
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
 extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin);
-extern void ext4_unwritten_wait(struct inode *inode);
 
 /* inline.c */
 extern int ext4_has_inline_data(struct inode *inode);
-extern int ext4_get_inline_size(struct inode *inode);
 extern int ext4_get_max_inline_size(struct inode *inode);
 extern int ext4_find_inline_data_nolock(struct inode *inode);
-extern void ext4_write_inline_data(struct inode *inode,
-				   struct ext4_iloc *iloc,
-				   void *buffer, loff_t pos,
-				   unsigned int len);
-extern int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
-				    unsigned int len);
 extern int ext4_init_inline_data(handle_t *handle, struct inode *inode,
 				 unsigned int len);
 extern int ext4_destroy_inline_data(handle_t *handle, struct inode *inode);
@@ -2771,23 +2750,20 @@ extern void ext4_io_submit(struct ext4_io_submit *io);
 extern int ext4_bio_write_page(struct ext4_io_submit *io,
 			       struct page *page,
 			       int len,
-			       struct writeback_control *wbc);
+			       struct writeback_control *wbc,
+			       bool keep_towrite);
 
 /* mmp.c */
 extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
-extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp);
-extern int ext4_mmp_csum_verify(struct super_block *sb,
-				struct mmp_struct *mmp);
 
 /*
  * Note that these flags will never ever appear in a buffer_head's state flag.
  * See EXT4_MAP_... to see where this is used.
  */
 enum ext4_state_bits {
-	BH_Uninit	/* blocks are allocated but uninitialized on disk */
-	 = BH_JBDPrivateStart,
-	BH_AllocFromCluster,	/* allocated blocks were part of already
+	BH_AllocFromCluster	/* allocated blocks were part of already
 				 * allocated cluster. */
+	= BH_JBDPrivateStart
 };
 
 /*
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 5074fe23f19..a867f5ca999 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -137,21 +137,21 @@ struct ext4_ext_path {
  * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
  * initialized extent. This is 2^15 and not (2^16 - 1), since we use the
  * MSB of ee_len field in the extent datastructure to signify if this
- * particular extent is an initialized extent or an uninitialized (i.e.
+ * particular extent is an initialized extent or an unwritten (i.e.
  * preallocated).
- * EXT_UNINIT_MAX_LEN is the maximum number of blocks we can have in an
- * uninitialized extent.
+ * EXT_UNWRITTEN_MAX_LEN is the maximum number of blocks we can have in an
+ * unwritten extent.
  * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
- * uninitialized one. In other words, if MSB of ee_len is set, it is an
- * uninitialized extent with only one special scenario when ee_len = 0x8000.
- * In this case we can not have an uninitialized extent of zero length and
+ * unwritten one. In other words, if MSB of ee_len is set, it is an
+ * unwritten extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an unwritten extent of zero length and
  * thus we make it as a special case of initialized extent with 0x8000 length.
  * This way we get better extent-to-group alignment for initialized extents.
  * Hence, the maximum number of blocks we can have in an *initialized*
- * extent is 2^15 (32768) and in an *uninitialized* extent is 2^15-1 (32767).
+ * extent is 2^15 (32768) and in an *unwritten* extent is 2^15-1 (32767).
  */
 #define EXT_INIT_MAX_LEN	(1UL << 15)
-#define EXT_UNINIT_MAX_LEN	(EXT_INIT_MAX_LEN - 1)
+#define EXT_UNWRITTEN_MAX_LEN	(EXT_INIT_MAX_LEN - 1)
 
 
 #define EXT_FIRST_EXTENT(__hdr__) \
@@ -187,14 +187,14 @@ static inline unsigned short ext_depth(struct inode *inode)
 	return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
 }
 
-static inline void ext4_ext_mark_uninitialized(struct ext4_extent *ext)
+static inline void ext4_ext_mark_unwritten(struct ext4_extent *ext)
 {
-	/* We can not have an uninitialized extent of zero length! */
+	/* We can not have an unwritten extent of zero length! */
 	BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
 	ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
 }
 
-static inline int ext4_ext_is_uninitialized(struct ext4_extent *ext)
+static inline int ext4_ext_is_unwritten(struct ext4_extent *ext)
 {
 	/* Extent with ee_len of 0x8000 is treated as an initialized extent */
 	return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index c3fb607413e..0074e0d23d6 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -122,9 +122,10 @@ handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
 	return handle;
 }
 
-void ext4_journal_abort_handle(const char *caller, unsigned int line,
-			       const char *err_fn, struct buffer_head *bh,
-			       handle_t *handle, int err)
+static void ext4_journal_abort_handle(const char *caller, unsigned int line,
+				      const char *err_fn,
+				      struct buffer_head *bh,
+				      handle_t *handle, int err)
 {
 	char nbuf[16];
 	const char *errstr = ext4_decode_error(NULL, err, nbuf);
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 81cfefa9dc0..17c00ff202f 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -231,10 +231,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
 /*
  * Wrapper functions with which ext4 calls into JBD.
  */
-void ext4_journal_abort_handle(const char *caller, unsigned int line,
-			       const char *err_fn,
-		struct buffer_head *bh, handle_t *handle, int err);
-
 int __ext4_journal_get_write_access(const char *where, unsigned int line,
 				    handle_t *handle, struct buffer_head *bh);
 
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 01b0c208f62..4da228a0e6d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -50,8 +50,8 @@
  */
 #define EXT4_EXT_MAY_ZEROOUT	0x1  /* safe to zeroout if split fails \
 					due to ENOSPC */
-#define EXT4_EXT_MARK_UNINIT1	0x2  /* mark first half uninitialized */
-#define EXT4_EXT_MARK_UNINIT2	0x4  /* mark second half uninitialized */
+#define EXT4_EXT_MARK_UNWRIT1	0x2  /* mark first half unwritten */
+#define EXT4_EXT_MARK_UNWRIT2	0x4  /* mark second half unwritten */
 
 #define EXT4_EXT_DATA_VALID1	0x8  /* first half contains valid data */
 #define EXT4_EXT_DATA_VALID2	0x10 /* second half contains valid data */
@@ -143,6 +143,7 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
 {
 	if (path->p_bh) {
 		/* path points to block */
+		BUFFER_TRACE(path->p_bh, "get_write_access");
 		return ext4_journal_get_write_access(handle, path->p_bh);
 	}
 	/* path points to leaf/index in inode body */
@@ -524,7 +525,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
 						     lblk - prev, ~0,
 						     EXTENT_STATUS_HOLE);
 
-			if (ext4_ext_is_uninitialized(ex))
+			if (ext4_ext_is_unwritten(ex))
 				status = EXTENT_STATUS_UNWRITTEN;
 			ext4_es_cache_extent(inode, lblk, len,
 					     ext4_ext_pblock(ex), status);
@@ -620,7 +621,7 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
 		} else if (path->p_ext) {
 			ext_debug("  %d:[%d]%d:%llu ",
 				  le32_to_cpu(path->p_ext->ee_block),
-				  ext4_ext_is_uninitialized(path->p_ext),
+				  ext4_ext_is_unwritten(path->p_ext),
 				  ext4_ext_get_actual_len(path->p_ext),
 				  ext4_ext_pblock(path->p_ext));
 		} else
@@ -646,7 +647,7 @@ static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path)
 
 	for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) {
 		ext_debug("%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block),
-			  ext4_ext_is_uninitialized(ex),
+			  ext4_ext_is_unwritten(ex),
 			  ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex));
 	}
 	ext_debug("\n");
@@ -677,7 +678,7 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
 		ext_debug("move %d:%llu:[%d]%d in new leaf %llu\n",
 				le32_to_cpu(ex->ee_block),
 				ext4_ext_pblock(ex),
-				ext4_ext_is_uninitialized(ex),
+				ext4_ext_is_unwritten(ex),
 				ext4_ext_get_actual_len(ex),
 				newblock);
 		ex++;
@@ -802,7 +803,7 @@ ext4_ext_binsearch(struct inode *inode,
 	ext_debug("  -> %d:%llu:[%d]%d ",
 			le32_to_cpu(path->p_ext->ee_block),
 			ext4_ext_pblock(path->p_ext),
-			ext4_ext_is_uninitialized(path->p_ext),
+			ext4_ext_is_unwritten(path->p_ext),
 			ext4_ext_get_actual_len(path->p_ext));
 
 #ifdef CHECK_BINSEARCH
@@ -1686,11 +1687,11 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 
 	/*
 	 * Make sure that both extents are initialized. We don't merge
-	 * uninitialized extents so that we can be sure that end_io code has
+	 * unwritten extents so that we can be sure that end_io code has
 	 * the extent that was written properly split out and conversion to
 	 * initialized is trivial.
 	 */
-	if (ext4_ext_is_uninitialized(ex1) != ext4_ext_is_uninitialized(ex2))
+	if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2))
 		return 0;
 
 	ext1_ee_len = ext4_ext_get_actual_len(ex1);
@@ -1707,10 +1708,10 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 	 */
 	if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
 		return 0;
-	if (ext4_ext_is_uninitialized(ex1) &&
+	if (ext4_ext_is_unwritten(ex1) &&
 	    (ext4_test_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN) ||
 	     atomic_read(&EXT4_I(inode)->i_unwritten) ||
-	     (ext1_ee_len + ext2_ee_len > EXT_UNINIT_MAX_LEN)))
+	     (ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN)))
 		return 0;
 #ifdef AGGRESSIVE_TEST
 	if (ext1_ee_len >= 4)
@@ -1735,7 +1736,7 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
 {
 	struct ext4_extent_header *eh;
 	unsigned int depth, len;
-	int merge_done = 0, uninit;
+	int merge_done = 0, unwritten;
 
 	depth = ext_depth(inode);
 	BUG_ON(path[depth].p_hdr == NULL);
@@ -1745,11 +1746,11 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
 		if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
 			break;
 		/* merge with next extent! */
-		uninit = ext4_ext_is_uninitialized(ex);
+		unwritten = ext4_ext_is_unwritten(ex);
 		ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
 				+ ext4_ext_get_actual_len(ex + 1));
-		if (uninit)
-			ext4_ext_mark_uninitialized(ex);
+		if (unwritten)
+			ext4_ext_mark_unwritten(ex);
 
 		if (ex + 1 < EXT_LAST_EXTENT(eh)) {
 			len = (EXT_LAST_EXTENT(eh) - ex - 1)
@@ -1903,7 +1904,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	struct ext4_ext_path *npath = NULL;
 	int depth, len, err;
 	ext4_lblk_t next;
-	int mb_flags = 0, uninit;
+	int mb_flags = 0, unwritten;
 
 	if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
 		EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
@@ -1943,21 +1944,21 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 		if (ext4_can_extents_be_merged(inode, ex, newext)) {
 			ext_debug("append [%d]%d block to %u:[%d]%d"
 				  "(from %llu)\n",
-				  ext4_ext_is_uninitialized(newext),
+				  ext4_ext_is_unwritten(newext),
 				  ext4_ext_get_actual_len(newext),
 				  le32_to_cpu(ex->ee_block),
-				  ext4_ext_is_uninitialized(ex),
+				  ext4_ext_is_unwritten(ex),
 				  ext4_ext_get_actual_len(ex),
 				  ext4_ext_pblock(ex));
 			err = ext4_ext_get_access(handle, inode,
 						  path + depth);
 			if (err)
 				return err;
-			uninit = ext4_ext_is_uninitialized(ex);
+			unwritten = ext4_ext_is_unwritten(ex);
 			ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
 					+ ext4_ext_get_actual_len(newext));
-			if (uninit)
-				ext4_ext_mark_uninitialized(ex);
+			if (unwritten)
+				ext4_ext_mark_unwritten(ex);
 			eh = path[depth].p_hdr;
 			nearex = ex;
 			goto merge;
@@ -1969,10 +1970,10 @@ prepend:
 			ext_debug("prepend %u[%d]%d block to %u:[%d]%d"
 				  "(from %llu)\n",
 				  le32_to_cpu(newext->ee_block),
-				  ext4_ext_is_uninitialized(newext),
+				  ext4_ext_is_unwritten(newext),
 				  ext4_ext_get_actual_len(newext),
 				  le32_to_cpu(ex->ee_block),
-				  ext4_ext_is_uninitialized(ex),
+				  ext4_ext_is_unwritten(ex),
 				  ext4_ext_get_actual_len(ex),
 				  ext4_ext_pblock(ex));
 			err = ext4_ext_get_access(handle, inode,
@@ -1980,13 +1981,13 @@ prepend:
 			if (err)
 				return err;
 
-			uninit = ext4_ext_is_uninitialized(ex);
+			unwritten = ext4_ext_is_unwritten(ex);
 			ex->ee_block = newext->ee_block;
 			ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
 			ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
 					+ ext4_ext_get_actual_len(newext));
-			if (uninit)
-				ext4_ext_mark_uninitialized(ex);
+			if (unwritten)
+				ext4_ext_mark_unwritten(ex);
 			eh = path[depth].p_hdr;
 			nearex = ex;
 			goto merge;
@@ -2046,7 +2047,7 @@ has_space:
 		ext_debug("first extent in the leaf: %u:%llu:[%d]%d\n",
 				le32_to_cpu(newext->ee_block),
 				ext4_ext_pblock(newext),
-				ext4_ext_is_uninitialized(newext),
+				ext4_ext_is_unwritten(newext),
 				ext4_ext_get_actual_len(newext));
 		nearex = EXT_FIRST_EXTENT(eh);
 	} else {
@@ -2057,7 +2058,7 @@ has_space:
 					"nearest %p\n",
 					le32_to_cpu(newext->ee_block),
 					ext4_ext_pblock(newext),
-					ext4_ext_is_uninitialized(newext),
+					ext4_ext_is_unwritten(newext),
 					ext4_ext_get_actual_len(newext),
 					nearex);
 			nearex++;
@@ -2068,7 +2069,7 @@ has_space:
 					"nearest %p\n",
 					le32_to_cpu(newext->ee_block),
 					ext4_ext_pblock(newext),
-					ext4_ext_is_uninitialized(newext),
+					ext4_ext_is_unwritten(newext),
 					ext4_ext_get_actual_len(newext),
 					nearex);
 		}
@@ -2078,7 +2079,7 @@ has_space:
 					"move %d extents from 0x%p to 0x%p\n",
 					le32_to_cpu(newext->ee_block),
 					ext4_ext_pblock(newext),
-					ext4_ext_is_uninitialized(newext),
+					ext4_ext_is_unwritten(newext),
 					ext4_ext_get_actual_len(newext),
 					len, nearex, nearex + 1);
 			memmove(nearex + 1, nearex,
@@ -2200,7 +2201,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
 			es.es_lblk = le32_to_cpu(ex->ee_block);
 			es.es_len = ext4_ext_get_actual_len(ex);
 			es.es_pblk = ext4_ext_pblock(ex);
-			if (ext4_ext_is_uninitialized(ex))
+			if (ext4_ext_is_unwritten(ex))
 				flags |= FIEMAP_EXTENT_UNWRITTEN;
 		}
 
@@ -2576,7 +2577,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	unsigned num;
 	ext4_lblk_t ex_ee_block;
 	unsigned short ex_ee_len;
-	unsigned uninitialized = 0;
+	unsigned unwritten = 0;
 	struct ext4_extent *ex;
 	ext4_fsblk_t pblk;
 
@@ -2623,13 +2624,13 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 	while (ex >= EXT_FIRST_EXTENT(eh) &&
 			ex_ee_block + ex_ee_len > start) {
 
-		if (ext4_ext_is_uninitialized(ex))
-			uninitialized = 1;
+		if (ext4_ext_is_unwritten(ex))
+			unwritten = 1;
 		else
-			uninitialized = 0;
+			unwritten = 0;
 
 		ext_debug("remove ext %u:[%d]%d\n", ex_ee_block,
-			 uninitialized, ex_ee_len);
+			  unwritten, ex_ee_len);
 		path[depth].p_ext = ex;
 
 		a = ex_ee_block > start ? ex_ee_block : start;
@@ -2701,11 +2702,11 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 
 		ex->ee_len = cpu_to_le16(num);
 		/*
-		 * Do not mark uninitialized if all the blocks in the
+		 * Do not mark unwritten if all the blocks in the
 		 * extent have been removed.
 		 */
-		if (uninitialized && num)
-			ext4_ext_mark_uninitialized(ex);
+		if (unwritten && num)
+			ext4_ext_mark_unwritten(ex);
 		/*
 		 * If the extent was completely released,
 		 * we need to remove it from the leaf
@@ -2854,9 +2855,9 @@ again:
 		    end < ee_block + ext4_ext_get_actual_len(ex) - 1) {
 			int split_flag = 0;
 
-			if (ext4_ext_is_uninitialized(ex))
-				split_flag = EXT4_EXT_MARK_UNINIT1 |
-					     EXT4_EXT_MARK_UNINIT2;
+			if (ext4_ext_is_unwritten(ex))
+				split_flag = EXT4_EXT_MARK_UNWRIT1 |
+					     EXT4_EXT_MARK_UNWRIT2;
 
 			/*
 			 * Split the extent in two so that 'end' is the last
@@ -3113,7 +3114,7 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
  * @path: the path to the extent
  * @split: the logical block where the extent is splitted.
  * @split_flags: indicates if the extent could be zeroout if split fails, and
- *		 the states(init or uninit) of new extents.
+ *		 the states(init or unwritten) of new extents.
  * @flags: flags used to insert new extent to extent tree.
  *
  *
@@ -3155,10 +3156,10 @@ static int ext4_split_extent_at(handle_t *handle,
 	newblock = split - ee_block + ext4_ext_pblock(ex);
 
 	BUG_ON(split < ee_block || split >= (ee_block + ee_len));
-	BUG_ON(!ext4_ext_is_uninitialized(ex) &&
+	BUG_ON(!ext4_ext_is_unwritten(ex) &&
 	       split_flag & (EXT4_EXT_MAY_ZEROOUT |
-			     EXT4_EXT_MARK_UNINIT1 |
-			     EXT4_EXT_MARK_UNINIT2));
+			     EXT4_EXT_MARK_UNWRIT1 |
+			     EXT4_EXT_MARK_UNWRIT2));
 
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
@@ -3170,8 +3171,8 @@ static int ext4_split_extent_at(handle_t *handle,
 		 * then we just change the state of the extent, and splitting
 		 * is not needed.
 		 */
-		if (split_flag & EXT4_EXT_MARK_UNINIT2)
-			ext4_ext_mark_uninitialized(ex);
+		if (split_flag & EXT4_EXT_MARK_UNWRIT2)
+			ext4_ext_mark_unwritten(ex);
 		else
 			ext4_ext_mark_initialized(ex);
 
@@ -3185,8 +3186,8 @@ static int ext4_split_extent_at(handle_t *handle,
 	/* case a */
 	memcpy(&orig_ex, ex, sizeof(orig_ex));
 	ex->ee_len = cpu_to_le16(split - ee_block);
-	if (split_flag & EXT4_EXT_MARK_UNINIT1)
-		ext4_ext_mark_uninitialized(ex);
+	if (split_flag & EXT4_EXT_MARK_UNWRIT1)
+		ext4_ext_mark_unwritten(ex);
 
 	/*
 	 * path may lead to new leaf, not to original leaf any more
@@ -3200,8 +3201,8 @@ static int ext4_split_extent_at(handle_t *handle,
 	ex2->ee_block = cpu_to_le32(split);
 	ex2->ee_len   = cpu_to_le16(ee_len - (split - ee_block));
 	ext4_ext_store_pblock(ex2, newblock);
-	if (split_flag & EXT4_EXT_MARK_UNINIT2)
-		ext4_ext_mark_uninitialized(ex2);
+	if (split_flag & EXT4_EXT_MARK_UNWRIT2)
+		ext4_ext_mark_unwritten(ex2);
 
 	err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
 	if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
@@ -3278,7 +3279,7 @@ static int ext4_split_extent(handle_t *handle,
 	struct ext4_extent *ex;
 	unsigned int ee_len, depth;
 	int err = 0;
-	int uninitialized;
+	int unwritten;
 	int split_flag1, flags1;
 	int allocated = map->m_len;
 
@@ -3286,14 +3287,14 @@ static int ext4_split_extent(handle_t *handle,
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
-	uninitialized = ext4_ext_is_uninitialized(ex);
+	unwritten = ext4_ext_is_unwritten(ex);
 
 	if (map->m_lblk + map->m_len < ee_block + ee_len) {
 		split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
 		flags1 = flags | EXT4_GET_BLOCKS_PRE_IO;
-		if (uninitialized)
-			split_flag1 |= EXT4_EXT_MARK_UNINIT1 |
-				       EXT4_EXT_MARK_UNINIT2;
+		if (unwritten)
+			split_flag1 |= EXT4_EXT_MARK_UNWRIT1 |
+				       EXT4_EXT_MARK_UNWRIT2;
 		if (split_flag & EXT4_EXT_DATA_VALID2)
 			split_flag1 |= EXT4_EXT_DATA_VALID1;
 		err = ext4_split_extent_at(handle, inode, path,
@@ -3318,15 +3319,15 @@ static int ext4_split_extent(handle_t *handle,
 				 (unsigned long) map->m_lblk);
 		return -EIO;
 	}
-	uninitialized = ext4_ext_is_uninitialized(ex);
+	unwritten = ext4_ext_is_unwritten(ex);
 	split_flag1 = 0;
 
 	if (map->m_lblk >= ee_block) {
 		split_flag1 = split_flag & EXT4_EXT_DATA_VALID2;
-		if (uninitialized) {
-			split_flag1 |= EXT4_EXT_MARK_UNINIT1;
+		if (unwritten) {
+			split_flag1 |= EXT4_EXT_MARK_UNWRIT1;
 			split_flag1 |= split_flag & (EXT4_EXT_MAY_ZEROOUT |
-						     EXT4_EXT_MARK_UNINIT2);
+						     EXT4_EXT_MARK_UNWRIT2);
 		}
 		err = ext4_split_extent_at(handle, inode, path,
 				map->m_lblk, split_flag1, flags);
@@ -3341,16 +3342,16 @@ out:
 
 /*
  * This function is called by ext4_ext_map_blocks() if someone tries to write
- * to an uninitialized extent. It may result in splitting the uninitialized
+ * to an unwritten extent. It may result in splitting the unwritten
  * extent into multiple extents (up to three - one initialized and two
- * uninitialized).
+ * unwritten).
  * There are three possibilities:
  *   a> There is no split required: Entire extent should be initialized
  *   b> Splits in two extents: Write is happening at either end of the extent
  *   c> Splits in three extents: Somone is writing in middle of the extent
  *
  * Pre-conditions:
- *  - The extent pointed to by 'path' is uninitialized.
+ *  - The extent pointed to by 'path' is unwritten.
  *  - The extent pointed to by 'path' contains a superset
  *    of the logical span [map->m_lblk, map->m_lblk + map->m_len).
  *
@@ -3396,12 +3397,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
 
 	/* Pre-conditions */
-	BUG_ON(!ext4_ext_is_uninitialized(ex));
+	BUG_ON(!ext4_ext_is_unwritten(ex));
 	BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
 
 	/*
 	 * Attempt to transfer newly initialized blocks from the currently
-	 * uninitialized extent to its neighbor. This is much cheaper
+	 * unwritten extent to its neighbor. This is much cheaper
 	 * than an insertion followed by a merge as those involve costly
 	 * memmove() calls. Transferring to the left is the common case in
 	 * steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE)
@@ -3437,7 +3438,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		 * - C4: abut_ex can receive the additional blocks without
 		 *   overflowing the (initialized) length limit.
 		 */
-		if ((!ext4_ext_is_uninitialized(abut_ex)) &&		/*C1*/
+		if ((!ext4_ext_is_unwritten(abut_ex)) &&		/*C1*/
 			((prev_lblk + prev_len) == ee_block) &&		/*C2*/
 			((prev_pblk + prev_len) == ee_pblk) &&		/*C3*/
 			(prev_len < (EXT_INIT_MAX_LEN - map_len))) {	/*C4*/
@@ -3452,7 +3453,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 			ex->ee_block = cpu_to_le32(ee_block + map_len);
 			ext4_ext_store_pblock(ex, ee_pblk + map_len);
 			ex->ee_len = cpu_to_le16(ee_len - map_len);
-			ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+			ext4_ext_mark_unwritten(ex); /* Restore the flag */
 
 			/* Extend abut_ex by 'map_len' blocks */
 			abut_ex->ee_len = cpu_to_le16(prev_len + map_len);
@@ -3483,7 +3484,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		 * - C4: abut_ex can receive the additional blocks without
 		 *   overflowing the (initialized) length limit.
 		 */
-		if ((!ext4_ext_is_uninitialized(abut_ex)) &&		/*C1*/
+		if ((!ext4_ext_is_unwritten(abut_ex)) &&		/*C1*/
 		    ((map->m_lblk + map_len) == next_lblk) &&		/*C2*/
 		    ((ee_pblk + ee_len) == next_pblk) &&		/*C3*/
 		    (next_len < (EXT_INIT_MAX_LEN - map_len))) {	/*C4*/
@@ -3498,7 +3499,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 			abut_ex->ee_block = cpu_to_le32(next_lblk - map_len);
 			ext4_ext_store_pblock(abut_ex, next_pblk - map_len);
 			ex->ee_len = cpu_to_le16(ee_len - map_len);
-			ext4_ext_mark_uninitialized(ex); /* Restore the flag */
+			ext4_ext_mark_unwritten(ex); /* Restore the flag */
 
 			/* Extend abut_ex by 'map_len' blocks */
 			abut_ex->ee_len = cpu_to_le16(next_len + map_len);
@@ -3603,26 +3604,26 @@ out:
 /*
  * This function is called by ext4_ext_map_blocks() from
  * ext4_get_blocks_dio_write() when DIO to write
- * to an uninitialized extent.
+ * to an unwritten extent.
  *
- * Writing to an uninitialized extent may result in splitting the uninitialized
- * extent into multiple initialized/uninitialized extents (up to three)
+ * Writing to an unwritten extent may result in splitting the unwritten
+ * extent into multiple initialized/unwritten extents (up to three)
  * There are three possibilities:
- *   a> There is no split required: Entire extent should be uninitialized
+ *   a> There is no split required: Entire extent should be unwritten
  *   b> Splits in two extents: Write is happening at either end of the extent
  *   c> Splits in three extents: Somone is writing in middle of the extent
  *
  * This works the same way in the case of initialized -> unwritten conversion.
  *
  * One of more index blocks maybe needed if the extent tree grow after
- * the uninitialized extent split. To prevent ENOSPC occur at the IO
- * complete, we need to split the uninitialized extent before DIO submit
- * the IO. The uninitialized extent called at this time will be split
- * into three uninitialized extent(at most). After IO complete, the part
+ * the unwritten extent split. To prevent ENOSPC occur at the IO
+ * complete, we need to split the unwritten extent before DIO submit
+ * the IO. The unwritten extent called at this time will be split
+ * into three unwritten extent(at most). After IO complete, the part
  * being filled will be convert to initialized by the end_io callback function
  * via ext4_convert_unwritten_extents().
  *
- * Returns the size of uninitialized extent to be written on success.
+ * Returns the size of unwritten extent to be written on success.
  */
 static int ext4_split_convert_extents(handle_t *handle,
 					struct inode *inode,
@@ -3660,7 +3661,7 @@ static int ext4_split_convert_extents(handle_t *handle,
 	} else if (flags & EXT4_GET_BLOCKS_CONVERT) {
 		split_flag |= ee_block + ee_len <= eof_block ?
 			      EXT4_EXT_MAY_ZEROOUT : 0;
-		split_flag |= (EXT4_EXT_MARK_UNINIT2 | EXT4_EXT_DATA_VALID2);
+		split_flag |= (EXT4_EXT_MARK_UNWRIT2 | EXT4_EXT_DATA_VALID2);
 	}
 	flags |= EXT4_GET_BLOCKS_PRE_IO;
 	return ext4_split_extent(handle, inode, path, map, split_flag, flags);
@@ -3710,8 +3711,8 @@ static int ext4_convert_initialized_extents(handle_t *handle,
 	err = ext4_ext_get_access(handle, inode, path + depth);
 	if (err)
 		goto out;
-	/* first mark the extent as uninitialized */
-	ext4_ext_mark_uninitialized(ex);
+	/* first mark the extent as unwritten */
+	ext4_ext_mark_unwritten(ex);
 
 	/* note: ext4_ext_correct_indexes() isn't needed here because
 	 * borders are not changed
@@ -3971,10 +3972,10 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
 
 	/*
 	 * Make sure that the extent is no bigger than we support with
-	 * uninitialized extent
+	 * unwritten extent
 	 */
-	if (map->m_len > EXT_UNINIT_MAX_LEN)
-		map->m_len = EXT_UNINIT_MAX_LEN / 2;
+	if (map->m_len > EXT_UNWRITTEN_MAX_LEN)
+		map->m_len = EXT_UNWRITTEN_MAX_LEN / 2;
 
 	ret = ext4_convert_initialized_extents(handle, inode, map,
 						path);
@@ -3993,7 +3994,7 @@ ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
 }
 
 static int
-ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
+ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode,
 			struct ext4_map_blocks *map,
 			struct ext4_ext_path *path, int flags,
 			unsigned int allocated, ext4_fsblk_t newblock)
@@ -4002,23 +4003,23 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 	int err = 0;
 	ext4_io_end_t *io = ext4_inode_aio(inode);
 
-	ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical "
+	ext_debug("ext4_ext_handle_unwritten_extents: inode %lu, logical "
 		  "block %llu, max_blocks %u, flags %x, allocated %u\n",
 		  inode->i_ino, (unsigned long long)map->m_lblk, map->m_len,
 		  flags, allocated);
 	ext4_ext_show_leaf(inode, path);
 
 	/*
-	 * When writing into uninitialized space, we should not fail to
+	 * When writing into unwritten space, we should not fail to
 	 * allocate metadata blocks for the new extent block if needed.
 	 */
 	flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL;
 
-	trace_ext4_ext_handle_uninitialized_extents(inode, map, flags,
+	trace_ext4_ext_handle_unwritten_extents(inode, map, flags,
 						    allocated, newblock);
 
 	/* get_block() before submit the IO, split the extent */
-	if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
+	if (flags & EXT4_GET_BLOCKS_PRE_IO) {
 		ret = ext4_split_convert_extents(handle, inode, map,
 					 path, flags | EXT4_GET_BLOCKS_CONVERT);
 		if (ret <= 0)
@@ -4033,12 +4034,10 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 		else
 			ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
 		map->m_flags |= EXT4_MAP_UNWRITTEN;
-		if (ext4_should_dioread_nolock(inode))
-			map->m_flags |= EXT4_MAP_UNINIT;
 		goto out;
 	}
 	/* IO end_io complete, convert the filled extent to written */
-	if ((flags & EXT4_GET_BLOCKS_CONVERT)) {
+	if (flags & EXT4_GET_BLOCKS_CONVERT) {
 		ret = ext4_convert_unwritten_extents_endio(handle, inode, map,
 							path);
 		if (ret >= 0) {
@@ -4059,7 +4058,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 	 * repeat fallocate creation request
 	 * we already have an unwritten extent
 	 */
-	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT) {
+	if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) {
 		map->m_flags |= EXT4_MAP_UNWRITTEN;
 		goto map_out;
 	}
@@ -4310,7 +4309,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 
 
 		/*
-		 * Uninitialized extents are treated as holes, except that
+		 * unwritten extents are treated as holes, except that
 		 * we split out initialized portions during a write.
 		 */
 		ee_len = ext4_ext_get_actual_len(ex);
@@ -4329,16 +4328,16 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			 * If the extent is initialized check whether the
 			 * caller wants to convert it to unwritten.
 			 */
-			if ((!ext4_ext_is_uninitialized(ex)) &&
+			if ((!ext4_ext_is_unwritten(ex)) &&
 			    (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) {
 				allocated = ext4_ext_convert_initialized_extent(
 						handle, inode, map, path, flags,
 						allocated, newblock);
 				goto out2;
-			} else if (!ext4_ext_is_uninitialized(ex))
+			} else if (!ext4_ext_is_unwritten(ex))
 				goto out;
 
-			ret = ext4_ext_handle_uninitialized_extents(
+			ret = ext4_ext_handle_unwritten_extents(
 				handle, inode, map, path, flags,
 				allocated, newblock);
 			if (ret < 0)
@@ -4410,15 +4409,15 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	/*
 	 * See if request is beyond maximum number of blocks we can have in
 	 * a single extent. For an initialized extent this limit is
-	 * EXT_INIT_MAX_LEN and for an uninitialized extent this limit is
-	 * EXT_UNINIT_MAX_LEN.
+	 * EXT_INIT_MAX_LEN and for an unwritten extent this limit is
+	 * EXT_UNWRITTEN_MAX_LEN.
 	 */
 	if (map->m_len > EXT_INIT_MAX_LEN &&
-	    !(flags & EXT4_GET_BLOCKS_UNINIT_EXT))
+	    !(flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
 		map->m_len = EXT_INIT_MAX_LEN;
-	else if (map->m_len > EXT_UNINIT_MAX_LEN &&
-		 (flags & EXT4_GET_BLOCKS_UNINIT_EXT))
-		map->m_len = EXT_UNINIT_MAX_LEN;
+	else if (map->m_len > EXT_UNWRITTEN_MAX_LEN &&
+		 (flags & EXT4_GET_BLOCKS_UNWRIT_EXT))
+		map->m_len = EXT_UNWRITTEN_MAX_LEN;
 
 	/* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */
 	newex.ee_len = cpu_to_le16(map->m_len);
@@ -4466,21 +4465,19 @@ got_allocated_blocks:
 	/* try to insert new extent into found leaf and return */
 	ext4_ext_store_pblock(&newex, newblock + offset);
 	newex.ee_len = cpu_to_le16(ar.len);
-	/* Mark uninitialized */
-	if (flags & EXT4_GET_BLOCKS_UNINIT_EXT){
-		ext4_ext_mark_uninitialized(&newex);
+	/* Mark unwritten */
+	if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT){
+		ext4_ext_mark_unwritten(&newex);
 		map->m_flags |= EXT4_MAP_UNWRITTEN;
 		/*
 		 * io_end structure was created for every IO write to an
-		 * uninitialized extent. To avoid unnecessary conversion,
+		 * unwritten extent. To avoid unnecessary conversion,
 		 * here we flag the IO that really needs the conversion.
 		 * For non asycn direct IO case, flag the inode state
 		 * that we need to perform conversion when IO is done.
 		 */
-		if ((flags & EXT4_GET_BLOCKS_PRE_IO))
+		if (flags & EXT4_GET_BLOCKS_PRE_IO)
 			set_unwritten = 1;
-		if (ext4_should_dioread_nolock(inode))
-			map->m_flags |= EXT4_MAP_UNINIT;
 	}
 
 	err = 0;
@@ -4607,9 +4604,9 @@ got_allocated_blocks:
 
 	/*
 	 * Cache the extent and update transaction to commit on fdatasync only
-	 * when it is _not_ an uninitialized extent.
+	 * when it is _not_ an unwritten extent.
 	 */
-	if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
+	if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0)
 		ext4_update_inode_fsync_trans(handle, inode, 1);
 	else
 		ext4_update_inode_fsync_trans(handle, inode, 0);
@@ -4683,7 +4680,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	 * that it doesn't get unnecessarily split into multiple
 	 * extents.
 	 */
-	if (len <= EXT_UNINIT_MAX_LEN)
+	if (len <= EXT_UNWRITTEN_MAX_LEN)
 		flags |= EXT4_GET_BLOCKS_NO_NORMALIZE;
 
 	/*
@@ -4744,6 +4741,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	if (!S_ISREG(inode->i_mode))
 		return -EINVAL;
 
+	/* Call ext4_force_commit to flush all data in case of data=journal. */
+	if (ext4_should_journal_data(inode)) {
+		ret = ext4_force_commit(inode->i_sb);
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * Write out all dirty pages to avoid race conditions
 	 * Then release them.
@@ -4775,7 +4779,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	else
 		max_blocks -= lblk;
 
-	flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT |
+	flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT |
 		EXT4_GET_BLOCKS_CONVERT_UNWRITTEN;
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
@@ -4918,7 +4922,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
 		- lblk;
 
-	flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT;
+	flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
 	if (mode & FALLOC_FL_KEEP_SIZE)
 		flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
 
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 0ebc21204b5..0b7e28e7eaa 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -344,8 +344,14 @@ static int ext4_es_can_be_merged(struct extent_status *es1,
 	if (ext4_es_status(es1) != ext4_es_status(es2))
 		return 0;
 
-	if (((__u64) es1->es_len) + es2->es_len > 0xFFFFFFFFULL)
+	if (((__u64) es1->es_len) + es2->es_len > EXT_MAX_BLOCKS) {
+		pr_warn("ES assertion failed when merging extents. "
+			"The sum of lengths of es1 (%d) and es2 (%d) "
+			"is bigger than allowed file size (%d)\n",
+			es1->es_len, es2->es_len, EXT_MAX_BLOCKS);
+		WARN_ON(1);
 		return 0;
+	}
 
 	if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk)
 		return 0;
@@ -433,7 +439,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
 		ee_start = ext4_ext_pblock(ex);
 		ee_len = ext4_ext_get_actual_len(ex);
 
-		ee_status = ext4_ext_is_uninitialized(ex) ? 1 : 0;
+		ee_status = ext4_ext_is_unwritten(ex) ? 1 : 0;
 		es_status = ext4_es_is_unwritten(es) ? 1 : 0;
 
 		/*
@@ -960,10 +966,10 @@ retry:
 			continue;
 		}
 
-		if (ei->i_es_lru_nr == 0 || ei == locked_ei)
+		if (ei->i_es_lru_nr == 0 || ei == locked_ei ||
+		    !write_trylock(&ei->i_es_lock))
 			continue;
 
-		write_lock(&ei->i_es_lock);
 		shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
 		if (ei->i_es_lru_nr == 0)
 			list_del_init(&ei->i_es_lru);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 063fc153835..8695f70af1e 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -57,7 +57,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-void ext4_unwritten_wait(struct inode *inode)
+static void ext4_unwritten_wait(struct inode *inode)
 {
 	wait_queue_head_t *wq = ext4_ioend_wq(inode);
 
@@ -74,79 +74,105 @@ void ext4_unwritten_wait(struct inode *inode)
  * or one thread will zero the other's data, causing corruption.
  */
 static int
-ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
-		   unsigned long nr_segs, loff_t pos)
+ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
 {
 	struct super_block *sb = inode->i_sb;
 	int blockmask = sb->s_blocksize - 1;
-	size_t count = iov_length(iov, nr_segs);
-	loff_t final_size = pos + count;
 
 	if (pos >= i_size_read(inode))
 		return 0;
 
-	if ((pos & blockmask) || (final_size & blockmask))
+	if ((pos | iov_iter_alignment(from)) & blockmask)
 		return 1;
 
 	return 0;
 }
 
 static ssize_t
-ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
-		    unsigned long nr_segs, loff_t pos)
+ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct mutex *aio_mutex = NULL;
 	struct blk_plug plug;
-	int unaligned_aio = 0;
-	ssize_t ret;
+	int o_direct = file->f_flags & O_DIRECT;
 	int overwrite = 0;
-	size_t length = iov_length(iov, nr_segs);
-
-	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
-	    !is_sync_kiocb(iocb))
-		unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
+	size_t length = iov_iter_count(from);
+	ssize_t ret;
+	loff_t pos = iocb->ki_pos;
 
-	/* Unaligned direct AIO must be serialized; see comment above */
-	if (unaligned_aio) {
-		mutex_lock(ext4_aio_mutex(inode));
+	/*
+	 * Unaligned direct AIO must be serialized; see comment above
+	 * In the case of O_APPEND, assume that we must always serialize
+	 */
+	if (o_direct &&
+	    ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
+	    !is_sync_kiocb(iocb) &&
+	    (file->f_flags & O_APPEND ||
+	     ext4_unaligned_aio(inode, from, pos))) {
+		aio_mutex = ext4_aio_mutex(inode);
+		mutex_lock(aio_mutex);
 		ext4_unwritten_wait(inode);
 	}
 
-	BUG_ON(iocb->ki_pos != pos);
-
 	mutex_lock(&inode->i_mutex);
-	blk_start_plug(&plug);
+	if (file->f_flags & O_APPEND)
+		iocb->ki_pos = pos = i_size_read(inode);
+
+	/*
+	 * If we have encountered a bitmap-format file, the size limit
+	 * is smaller than s_maxbytes, which is for extent-mapped files.
+	 */
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
-	iocb->private = &overwrite;
+		if ((pos > sbi->s_bitmap_maxbytes) ||
+		    (pos == sbi->s_bitmap_maxbytes && length > 0)) {
+			mutex_unlock(&inode->i_mutex);
+			ret = -EFBIG;
+			goto errout;
+		}
 
-	/* check whether we do a DIO overwrite or not */
-	if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
-	    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
-		struct ext4_map_blocks map;
-		unsigned int blkbits = inode->i_blkbits;
-		int err, len;
+		if (pos + length > sbi->s_bitmap_maxbytes)
+			iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos);
+	}
 
-		map.m_lblk = pos >> blkbits;
-		map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
-			- map.m_lblk;
-		len = map.m_len;
+	if (o_direct) {
+		blk_start_plug(&plug);
 
-		err = ext4_map_blocks(NULL, inode, &map, 0);
-		/*
-		 * 'err==len' means that all of blocks has been preallocated no
-		 * matter they are initialized or not.  For excluding
-		 * uninitialized extents, we need to check m_flags.  There are
-		 * two conditions that indicate for initialized extents.
-		 * 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
-		 * 2) If we do a real lookup, non-flags are returned.
-		 * So we should check these two conditions.
-		 */
-		if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
-			overwrite = 1;
+		iocb->private = &overwrite;
+
+		/* check whether we do a DIO overwrite or not */
+		if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
+		    !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+			struct ext4_map_blocks map;
+			unsigned int blkbits = inode->i_blkbits;
+			int err, len;
+
+			map.m_lblk = pos >> blkbits;
+			map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
+				- map.m_lblk;
+			len = map.m_len;
+
+			err = ext4_map_blocks(NULL, inode, &map, 0);
+			/*
+			 * 'err==len' means that all of blocks has
+			 * been preallocated no matter they are
+			 * initialized or not.  For excluding
+			 * unwritten extents, we need to check
+			 * m_flags.  There are two conditions that
+			 * indicate for initialized extents.  1) If we
+			 * hit extent cache, EXT4_MAP_MAPPED flag is
+			 * returned; 2) If we do a real lookup,
+			 * non-flags are returned.  So we should check
+			 * these two conditions.
+			 */
+			if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
+				overwrite = 1;
+		}
 	}
 
-	ret = __generic_file_aio_write(iocb, iov, nr_segs);
+	ret = __generic_file_write_iter(iocb, from);
 	mutex_unlock(&inode->i_mutex);
 
 	if (ret > 0) {
@@ -156,45 +182,12 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
 		if (err < 0)
 			ret = err;
 	}
-	blk_finish_plug(&plug);
-
-	if (unaligned_aio)
-		mutex_unlock(ext4_aio_mutex(inode));
-
-	return ret;
-}
-
-static ssize_t
-ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	ssize_t ret;
-
-	/*
-	 * If we have encountered a bitmap-format file, the size limit
-	 * is smaller than s_maxbytes, which is for extent-mapped files.
-	 */
-
-	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
-		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-		size_t length = iov_length(iov, nr_segs);
-
-		if ((pos > sbi->s_bitmap_maxbytes ||
-		    (pos == sbi->s_bitmap_maxbytes && length > 0)))
-			return -EFBIG;
-
-		if (pos + length > sbi->s_bitmap_maxbytes) {
-			nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
-					      sbi->s_bitmap_maxbytes - pos);
-		}
-	}
-
-	if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
-		ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
-	else
-		ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+	if (o_direct)
+		blk_finish_plug(&plug);
 
+errout:
+	if (aio_mutex)
+		mutex_unlock(aio_mutex);
 	return ret;
 }
 
@@ -244,6 +237,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 			handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
 			if (IS_ERR(handle))
 				return PTR_ERR(handle);
+			BUFFER_TRACE(sbi->s_sbh, "get_write_access");
 			err = ext4_journal_get_write_access(handle, sbi->s_sbh);
 			if (err) {
 				ext4_journal_stop(handle);
@@ -593,10 +587,10 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
 
 const struct file_operations ext4_file_operations = {
 	.llseek		= ext4_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= ext4_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= ext4_file_write_iter,
 	.unlocked_ioctl = ext4_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext4_compat_ioctl,
@@ -606,7 +600,7 @@ const struct file_operations ext4_file_operations = {
 	.release	= ext4_release_file,
 	.fsync		= ext4_sync_file,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.fallocate	= ext4_fallocate,
 };
 
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 0ee59a6644e..5b87fc36aab 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -71,6 +71,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
 				       struct ext4_group_desc *gdp)
 {
 	struct ext4_group_info *grp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	J_ASSERT_BH(bh, buffer_locked(bh));
 
 	/* If checksum is bad mark all blocks and inodes use to prevent
@@ -78,7 +79,16 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
 	if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
 		ext4_error(sb, "Checksum bad for group %u", block_group);
 		grp = ext4_get_group_info(sb, block_group);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, gdp);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
 		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return 0;
 	}
@@ -116,6 +126,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	struct buffer_head *bh = NULL;
 	ext4_fsblk_t bitmap_blk;
 	struct ext4_group_info *grp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	desc = ext4_get_group_desc(sb, block_group, NULL);
 	if (!desc)
@@ -185,6 +196,12 @@ verify:
 		ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
 			   "inode_bitmap = %llu", block_group, bitmap_blk);
 		grp = ext4_get_group_info(sb, block_group);
+		if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, desc);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
 		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
 		return NULL;
 	}
@@ -321,6 +338,12 @@ out:
 			fatal = err;
 	} else {
 		ext4_error(sb, "bit already cleared for inode %lu", ino);
+		if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+			int count;
+			count = ext4_free_inodes_count(sb, gdp);
+			percpu_counter_sub(&sbi->s_freeinodes_counter,
+					   count);
+		}
 		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
 	}
 
@@ -851,6 +874,13 @@ got:
 		goto out;
 	}
 
+	BUFFER_TRACE(group_desc_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, group_desc_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
 	/* We may have to initialize the block bitmap if it isn't already */
 	if (ext4_has_group_desc_csum(sb) &&
 	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
@@ -887,13 +917,6 @@ got:
 		}
 	}
 
-	BUFFER_TRACE(group_desc_bh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, group_desc_bh);
-	if (err) {
-		ext4_std_error(sb, err);
-		goto out;
-	}
-
 	/* Update the relevant bg descriptor fields */
 	if (ext4_has_group_desc_csum(sb)) {
 		int free;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 594009f5f52..fd69da19482 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -389,7 +389,13 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 	return 0;
 failed:
 	for (; i >= 0; i--) {
-		if (i != indirect_blks && branch[i].bh)
+		/*
+		 * We want to ext4_forget() only freshly allocated indirect
+		 * blocks.  Buffer for new_blocks[i-1] is at branch[i].bh and
+		 * buffer at branch[0].bh is indirect block / inode already
+		 * existing before ext4_alloc_branch() was called.
+		 */
+		if (i > 0 && i != indirect_blks && branch[i].bh)
 			ext4_forget(handle, 1, inode, branch[i].bh,
 				    branch[i].bh->b_blocknr);
 		ext4_free_blocks(handle, inode, NULL, new_blocks[i],
@@ -639,8 +645,7 @@ out:
  * VFS code falls back into buffered path in that case so we are safe.
  */
 ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
-			   const struct iovec *iov, loff_t offset,
-			   unsigned long nr_segs)
+			   struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -648,7 +653,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 	handle_t *handle;
 	ssize_t ret;
 	int orphan = 0;
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(iter);
 	int retries = 0;
 
 	if (rw == WRITE) {
@@ -687,18 +692,17 @@ retry:
 			goto locked;
 		}
 		ret = __blockdev_direct_IO(rw, iocb, inode,
-				 inode->i_sb->s_bdev, iov,
-				 offset, nr_segs,
+				 inode->i_sb->s_bdev, iter, offset,
 				 ext4_get_block, NULL, NULL, 0);
 		inode_dio_done(inode);
 	} else {
 locked:
-		ret = blockdev_direct_IO(rw, iocb, inode, iov,
-				 offset, nr_segs, ext4_get_block);
+		ret = blockdev_direct_IO(rw, iocb, inode, iter,
+				 offset, ext4_get_block);
 
 		if (unlikely((rw & WRITE) && ret < 0)) {
 			loff_t isize = i_size_read(inode);
-			loff_t end = offset + iov_length(iov, nr_segs);
+			loff_t end = offset + count;
 
 			if (end > isize)
 				ext4_truncate_failed_write(inode);
@@ -1312,16 +1316,24 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode,
 		blk = *i_data;
 		if (level > 0) {
 			ext4_lblk_t first2;
+			ext4_lblk_t count2;
+
 			bh = sb_bread(inode->i_sb, le32_to_cpu(blk));
 			if (!bh) {
 				EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk),
 						       "Read failure");
 				return -EIO;
 			}
-			first2 = (first > offset) ? first - offset : 0;
+			if (first > offset) {
+				first2 = first - offset;
+				count2 = count;
+			} else {
+				first2 = 0;
+				count2 = count - (offset - first);
+			}
 			ret = free_hole_blocks(handle, inode, bh,
 					       (__le32 *)bh->b_data, level - 1,
-					       first2, count - offset,
+					       first2, count2,
 					       inode->i_sb->s_blocksize >> 2);
 			if (ret) {
 				brelse(bh);
@@ -1331,8 +1343,8 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode,
 		if (level == 0 ||
 		    (bh && all_zeroes((__le32 *)bh->b_data,
 				      (__le32 *)bh->b_data + addr_per_block))) {
-			ext4_free_data(handle, inode, parent_bh, &blk, &blk+1);
-			*i_data = 0;
+			ext4_free_data(handle, inode, parent_bh,
+				       i_data, i_data + 1);
 		}
 		brelse(bh);
 		bh = NULL;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 82edf5b9335..645205d8ada 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -22,7 +22,7 @@
 #define EXT4_INLINE_DOTDOT_OFFSET	2
 #define EXT4_INLINE_DOTDOT_SIZE		4
 
-int ext4_get_inline_size(struct inode *inode)
+static int ext4_get_inline_size(struct inode *inode)
 {
 	if (EXT4_I(inode)->i_inline_off)
 		return EXT4_I(inode)->i_inline_size;
@@ -211,8 +211,8 @@ out:
  * value since it is already handled by ext4_xattr_ibody_inline_set.
  * That saves us one memcpy.
  */
-void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
-			    void *buffer, loff_t pos, unsigned int len)
+static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
+				   void *buffer, loff_t pos, unsigned int len)
 {
 	struct ext4_xattr_entry *entry;
 	struct ext4_xattr_ibody_header *header;
@@ -264,6 +264,7 @@ static int ext4_create_inline_data(handle_t *handle,
 	if (error)
 		return error;
 
+	BUFFER_TRACE(is.iloc.bh, "get_write_access");
 	error = ext4_journal_get_write_access(handle, is.iloc.bh);
 	if (error)
 		goto out;
@@ -347,6 +348,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
 	if (error == -ENODATA)
 		goto out;
 
+	BUFFER_TRACE(is.iloc.bh, "get_write_access");
 	error = ext4_journal_get_write_access(handle, is.iloc.bh);
 	if (error)
 		goto out;
@@ -373,8 +375,8 @@ out:
 	return error;
 }
 
-int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
-			     unsigned int len)
+static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
+				    unsigned int len)
 {
 	int ret, size;
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -424,6 +426,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
 	if (error)
 		goto out;
 
+	BUFFER_TRACE(is.iloc.bh, "get_write_access");
 	error = ext4_journal_get_write_access(handle, is.iloc.bh);
 	if (error)
 		goto out;
@@ -1007,6 +1010,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
 	if (err)
 		return err;
 
+	BUFFER_TRACE(iloc->bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, iloc->bh);
 	if (err)
 		return err;
@@ -1669,6 +1673,7 @@ int ext4_delete_inline_entry(handle_t *handle,
 				EXT4_MIN_INLINE_DATA_SIZE;
 	}
 
+	BUFFER_TRACE(bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, bh);
 	if (err)
 		goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d7b7462a0e1..8a064734e6e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -148,6 +148,9 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
         int ea_blocks = EXT4_I(inode)->i_file_acl ?
 		EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
 
+	if (ext4_has_inline_data(inode))
+		return 0;
+
 	return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
 }
 
@@ -443,7 +446,7 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
 	 * could be converted.
 	 */
 	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
-		down_read((&EXT4_I(inode)->i_data_sem));
+		down_read(&EXT4_I(inode)->i_data_sem);
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		retval = ext4_ext_map_blocks(handle, inode, map, flags &
 					     EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -489,8 +492,8 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
  * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
  * based files
  *
- * On success, it returns the number of blocks being mapped or allocate.
- * if create==0 and the blocks are pre-allocated and uninitialized block,
+ * On success, it returns the number of blocks being mapped or allocated.
+ * if create==0 and the blocks are pre-allocated and unwritten block,
  * the result buffer head is unmapped. If the create ==1, it will make sure
  * the buffer head is mapped.
  *
@@ -555,7 +558,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	 * file system block.
 	 */
 	if (!(flags & EXT4_GET_BLOCKS_NO_LOCK))
-		down_read((&EXT4_I(inode)->i_data_sem));
+		down_read(&EXT4_I(inode)->i_data_sem);
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
 		retval = ext4_ext_map_blocks(handle, inode, map, flags &
 					     EXT4_GET_BLOCKS_KEEP_SIZE);
@@ -622,12 +625,12 @@ found:
 	map->m_flags &= ~EXT4_MAP_FLAGS;
 
 	/*
-	 * New blocks allocate and/or writing to uninitialized extent
+	 * New blocks allocate and/or writing to unwritten extent
 	 * will possibly result in updating i_data, so we take
 	 * the write lock of i_data_sem, and call get_blocks()
 	 * with create == 1 flag.
 	 */
-	down_write((&EXT4_I(inode)->i_data_sem));
+	down_write(&EXT4_I(inode)->i_data_sem);
 
 	/*
 	 * if the caller is from delayed allocation writeout path
@@ -922,6 +925,7 @@ int do_journal_get_write_access(handle_t *handle,
 	 */
 	if (dirty)
 		clear_buffer_dirty(bh);
+	BUFFER_TRACE(bh, "get write access");
 	ret = ext4_journal_get_write_access(handle, bh);
 	if (!ret && dirty)
 		ret = ext4_handle_dirty_metadata(handle, NULL, bh);
@@ -1540,7 +1544,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 		ext4_es_lru_add(inode);
 		if (ext4_es_is_hole(&es)) {
 			retval = 0;
-			down_read((&EXT4_I(inode)->i_data_sem));
+			down_read(&EXT4_I(inode)->i_data_sem);
 			goto add_delayed;
 		}
 
@@ -1577,7 +1581,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 	 * Try to see if we can get the block without requesting a new
 	 * file system block.
 	 */
-	down_read((&EXT4_I(inode)->i_data_sem));
+	down_read(&EXT4_I(inode)->i_data_sem);
 	if (ext4_has_inline_data(inode)) {
 		/*
 		 * We will soon create blocks for this page, and let
@@ -1769,6 +1773,7 @@ static int __ext4_journalled_writepage(struct page *page,
 	BUG_ON(!ext4_handle_valid(handle));
 
 	if (inline_data) {
+		BUFFER_TRACE(inode_bh, "get write access");
 		ret = ext4_journal_get_write_access(handle, inode_bh);
 
 		err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
@@ -1846,6 +1851,7 @@ static int ext4_writepage(struct page *page,
 	struct buffer_head *page_bufs = NULL;
 	struct inode *inode = page->mapping->host;
 	struct ext4_io_submit io_submit;
+	bool keep_towrite = false;
 
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
@@ -1876,6 +1882,7 @@ static int ext4_writepage(struct page *page,
 			unlock_page(page);
 			return 0;
 		}
+		keep_towrite = true;
 	}
 
 	if (PageChecked(page) && ext4_should_journal_data(inode))
@@ -1892,7 +1899,7 @@ static int ext4_writepage(struct page *page,
 		unlock_page(page);
 		return -ENOMEM;
 	}
-	ret = ext4_bio_write_page(&io_submit, page, len, wbc);
+	ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
 	ext4_io_submit(&io_submit);
 	/* Drop io_end reference we got from init */
 	ext4_put_io_end_defer(io_submit.io_end);
@@ -1911,7 +1918,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 	else
 		len = PAGE_CACHE_SIZE;
 	clear_page_dirty_for_io(page);
-	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
+	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
 	if (!err)
 		mpd->wbc->nr_to_write--;
 	mpd->first_page++;
@@ -2032,7 +2039,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
  * Scan buffers corresponding to changed extent (we expect corresponding pages
  * to be already locked) and update buffer state according to new extent state.
  * We map delalloc buffers to their physical location, clear unwritten bits,
- * and mark buffers as uninit when we perform writes to uninitialized extents
+ * and mark buffers as uninit when we perform writes to unwritten extents
  * and do extent conversion after IO is finished. If the last page is not fully
  * mapped, we update @map to the next extent in the last page that needs
  * mapping. Otherwise we submit the page for IO.
@@ -2126,12 +2133,12 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	struct inode *inode = mpd->inode;
 	struct ext4_map_blocks *map = &mpd->map;
 	int get_blocks_flags;
-	int err;
+	int err, dioread_nolock;
 
 	trace_ext4_da_write_pages_extent(inode, map);
 	/*
 	 * Call ext4_map_blocks() to allocate any delayed allocation blocks, or
-	 * to convert an uninitialized extent to be initialized (in the case
+	 * to convert an unwritten extent to be initialized (in the case
 	 * where we have written into one or more preallocated blocks).  It is
 	 * possible that we're going to need more metadata blocks than
 	 * previously reserved. However we must not fail because we're in
@@ -2148,7 +2155,8 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	 */
 	get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
 			   EXT4_GET_BLOCKS_METADATA_NOFAIL;
-	if (ext4_should_dioread_nolock(inode))
+	dioread_nolock = ext4_should_dioread_nolock(inode);
+	if (dioread_nolock)
 		get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
 	if (map->m_flags & (1 << BH_Delay))
 		get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
@@ -2156,7 +2164,7 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
 	err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
 	if (err < 0)
 		return err;
-	if (map->m_flags & EXT4_MAP_UNINIT) {
+	if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) {
 		if (!mpd->io_submit.io_end->handle &&
 		    ext4_handle_valid(handle)) {
 			mpd->io_submit.io_end->handle = handle->h_rsv_handle;
@@ -3070,9 +3078,9 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
  * preallocated extents, and those write extend the file, no need to
  * fall back to buffered IO.
  *
- * For holes, we fallocate those blocks, mark them as uninitialized
+ * For holes, we fallocate those blocks, mark them as unwritten
  * If those blocks were preallocated, we mark sure they are split, but
- * still keep the range to write as uninitialized.
+ * still keep the range to write as unwritten.
  *
  * The unwritten extents will be converted to written when DIO is completed.
  * For async direct IO, since the IO may still pending when return, we
@@ -3085,13 +3093,12 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
  *
  */
 static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
-			      const struct iovec *iov, loff_t offset,
-			      unsigned long nr_segs)
+			      struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	ssize_t ret;
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(iter);
 	int overwrite = 0;
 	get_block_t *get_block_func = NULL;
 	int dio_flags = 0;
@@ -3100,7 +3107,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 
 	/* Use the old path for reads and writes beyond i_size. */
 	if (rw != WRITE || final_size > inode->i_size)
-		return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
+		return ext4_ind_direct_IO(rw, iocb, iter, offset);
 
 	BUG_ON(iocb->private == NULL);
 
@@ -3124,12 +3131,12 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	 * We could direct write to holes and fallocate.
 	 *
 	 * Allocated blocks to fill the hole are marked as
-	 * uninitialized to prevent parallel buffered read to expose
+	 * unwritten to prevent parallel buffered read to expose
 	 * the stale data before DIO complete the data IO.
 	 *
 	 * As to previously fallocated extents, ext4 get_block will
 	 * just simply mark the buffer mapped but still keep the
-	 * extents uninitialized.
+	 * extents unwritten.
 	 *
 	 * For non AIO case, we will convert those unwritten extents
 	 * to written after return back from blockdev_direct_IO.
@@ -3167,8 +3174,8 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		dio_flags = DIO_LOCKING;
 	}
 	ret = __blockdev_direct_IO(rw, iocb, inode,
-				   inode->i_sb->s_bdev, iov,
-				   offset, nr_segs,
+				   inode->i_sb->s_bdev, iter,
+				   offset,
 				   get_block_func,
 				   ext4_end_io_dio,
 				   NULL,
@@ -3222,11 +3229,11 @@ retake_lock:
 }
 
 static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
-			      const struct iovec *iov, loff_t offset,
-			      unsigned long nr_segs)
+			      struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
 	/*
@@ -3239,13 +3246,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
 	if (ext4_has_inline_data(inode))
 		return 0;
 
-	trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
+	trace_ext4_direct_IO_enter(inode, offset, count, rw);
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs);
+		ret = ext4_ext_direct_IO(rw, iocb, iter, offset);
 	else
-		ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs);
-	trace_ext4_direct_IO_exit(inode, offset,
-				iov_length(iov, nr_segs), rw, ret);
+		ret = ext4_ind_direct_IO(rw, iocb, iter, offset);
+	trace_ext4_direct_IO_exit(inode, offset, count, rw, ret);
 	return ret;
 }
 
@@ -3440,7 +3446,7 @@ unlock:
  * This required during truncate. We need to physically zero the tail end
  * of that block so it doesn't yield old data if the file is later grown.
  */
-int ext4_block_truncate_page(handle_t *handle,
+static int ext4_block_truncate_page(handle_t *handle,
 		struct address_space *mapping, loff_t from)
 {
 	unsigned offset = from & (PAGE_CACHE_SIZE-1);
@@ -4304,12 +4310,15 @@ static int ext4_do_update_inode(handle_t *handle,
 	struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct buffer_head *bh = iloc->bh;
+	struct super_block *sb = inode->i_sb;
 	int err = 0, rc, block;
-	int need_datasync = 0;
+	int need_datasync = 0, set_large_file = 0;
 	uid_t i_uid;
 	gid_t i_gid;
 
-	/* For fields not not tracking in the in-memory inode,
+	spin_lock(&ei->i_raw_lock);
+
+	/* For fields not tracked in the in-memory inode,
 	 * initialise them to zero for new inodes. */
 	if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
 		memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
@@ -4347,8 +4356,10 @@ static int ext4_do_update_inode(handle_t *handle,
 	EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
 	EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
 
-	if (ext4_inode_blocks_set(handle, raw_inode, ei))
+	if (ext4_inode_blocks_set(handle, raw_inode, ei)) {
+		spin_unlock(&ei->i_raw_lock);
 		goto out_brelse;
+	}
 	raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
 	raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
 	if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
@@ -4360,24 +4371,11 @@ static int ext4_do_update_inode(handle_t *handle,
 		need_datasync = 1;
 	}
 	if (ei->i_disksize > 0x7fffffffULL) {
-		struct super_block *sb = inode->i_sb;
 		if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
 				EXT4_SB(sb)->s_es->s_rev_level ==
-				cpu_to_le32(EXT4_GOOD_OLD_REV)) {
-			/* If this is the first large file
-			 * created, add a flag to the superblock.
-			 */
-			err = ext4_journal_get_write_access(handle,
-					EXT4_SB(sb)->s_sbh);
-			if (err)
-				goto out_brelse;
-			ext4_update_dynamic_rev(sb);
-			EXT4_SET_RO_COMPAT_FEATURE(sb,
-					EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
-			ext4_handle_sync(handle);
-			err = ext4_handle_dirty_super(handle, sb);
-		}
+		    cpu_to_le32(EXT4_GOOD_OLD_REV))
+			set_large_file = 1;
 	}
 	raw_inode->i_generation = cpu_to_le32(inode->i_generation);
 	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
@@ -4409,12 +4407,24 @@ static int ext4_do_update_inode(handle_t *handle,
 
 	ext4_inode_csum_set(inode, raw_inode, ei);
 
+	spin_unlock(&ei->i_raw_lock);
+
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
 	rc = ext4_handle_dirty_metadata(handle, NULL, bh);
 	if (!err)
 		err = rc;
 	ext4_clear_inode_state(inode, EXT4_STATE_NEW);
-
+	if (set_large_file) {
+		BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
+		err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+		if (err)
+			goto out_brelse;
+		ext4_update_dynamic_rev(sb);
+		EXT4_SET_RO_COMPAT_FEATURE(sb,
+					   EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
+		ext4_handle_sync(handle);
+		err = ext4_handle_dirty_super(handle, sb);
+	}
 	ext4_update_inode_fsync_trans(handle, inode, need_datasync);
 out_brelse:
 	brelse(bh);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index afe8a133e3d..2dcb936be90 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -722,6 +722,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 				void *buddy, void *bitmap, ext4_group_t group)
 {
 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb);
 	ext4_grpblk_t i = 0;
 	ext4_grpblk_t first;
@@ -751,14 +752,17 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 
 	if (free != grp->bb_free) {
 		ext4_grp_locked_error(sb, group, 0, 0,
-				      "%u clusters in bitmap, %u in gd; "
-				      "block bitmap corrupt.",
+				      "block bitmap and bg descriptor "
+				      "inconsistent: %u vs %u free clusters",
 				      free, grp->bb_free);
 		/*
 		 * If we intend to continue, we consider group descriptor
 		 * corrupt and update bb_free using bitmap value
 		 */
 		grp->bb_free = free;
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
 	}
 	mb_set_largest_free_order(sb, grp);
@@ -1431,6 +1435,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 		right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap);
 
 	if (unlikely(block != -1)) {
+		struct ext4_sb_info *sbi = EXT4_SB(sb);
 		ext4_fsblk_t blocknr;
 
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
@@ -1441,6 +1446,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 				      "freeing already freed block "
 				      "(bit %u); block bitmap corrupt.",
 				      block);
+		if (!EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   e4b->bd_info->bb_free);
 		/* Mark the block group as corrupt. */
 		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
 			&e4b->bd_info->bb_state);
@@ -2619,7 +2627,7 @@ int ext4_mb_init(struct super_block *sb)
 	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
 	if (sbi->s_locality_groups == NULL) {
 		ret = -ENOMEM;
-		goto out_free_groupinfo_slab;
+		goto out;
 	}
 	for_each_possible_cpu(i) {
 		struct ext4_locality_group *lg;
@@ -2644,8 +2652,6 @@ int ext4_mb_init(struct super_block *sb)
 out_free_locality_groups:
 	free_percpu(sbi->s_locality_groups);
 	sbi->s_locality_groups = NULL;
-out_free_groupinfo_slab:
-	ext4_groupinfo_destroy_slabs();
 out:
 	kfree(sbi->s_mb_offsets);
 	sbi->s_mb_offsets = NULL;
@@ -2878,6 +2884,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	if (!bitmap_bh)
 		goto out_err;
 
+	BUFFER_TRACE(bitmap_bh, "getting write access");
 	err = ext4_journal_get_write_access(handle, bitmap_bh);
 	if (err)
 		goto out_err;
@@ -2890,6 +2897,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 	ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
 			ext4_free_group_clusters(sb, gdp));
 
+	BUFFER_TRACE(gdp_bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, gdp_bh);
 	if (err)
 		goto out_err;
@@ -3147,7 +3155,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	}
 	BUG_ON(start + size <= ac->ac_o_ex.fe_logical &&
 			start > ac->ac_o_ex.fe_logical);
-	BUG_ON(size <= 0 || size > EXT4_CLUSTERS_PER_GROUP(ac->ac_sb));
+	BUG_ON(size <= 0 || size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb));
 
 	/* now prepare goal request */
 
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 2ae73a80c19..ec092437d3e 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -505,7 +505,7 @@ int ext4_ext_migrate(struct inode *inode)
 	 * with i_data_sem held to prevent racing with block
 	 * allocation.
 	 */
-	down_read((&EXT4_I(inode)->i_data_sem));
+	down_read(&EXT4_I(inode)->i_data_sem);
 	ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
 	up_read((&EXT4_I(inode)->i_data_sem));
 
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 04434ad3e8e..32bce844c2e 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -18,7 +18,7 @@ static __le32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp)
 	return cpu_to_le32(csum);
 }
 
-int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
+static int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
 {
 	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
@@ -27,7 +27,7 @@ int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp)
 	return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp);
 }
 
-void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
+static void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp)
 {
 	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 58ee7dc8766..2484c7ec6a7 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -57,8 +57,8 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock,
 static void
 copy_extent_status(struct ext4_extent *src, struct ext4_extent *dest)
 {
-	if (ext4_ext_is_uninitialized(src))
-		ext4_ext_mark_uninitialized(dest);
+	if (ext4_ext_is_unwritten(src))
+		ext4_ext_mark_unwritten(dest);
 	else
 		dest->ee_len = cpu_to_le16(ext4_ext_get_actual_len(dest));
 }
@@ -391,6 +391,7 @@ mext_insert_extents(handle_t *handle, struct inode *orig_inode,
 
 	if (depth) {
 		/* Register to journal */
+		BUFFER_TRACE(orig_path->p_bh, "get_write_access");
 		ret = ext4_journal_get_write_access(handle, orig_path->p_bh);
 		if (ret)
 			return ret;
@@ -593,14 +594,14 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext,
  * @inode:		inode in question
  * @from:		block offset of inode
  * @count:		block count to be checked
- * @uninit:		extents expected to be uninitialized
+ * @unwritten:		extents expected to be unwritten
  * @err:		pointer to save error value
  *
  * Return 1 if all extents in range has expected type, and zero otherwise.
  */
 static int
 mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
-			  int uninit, int *err)
+		    int unwritten, int *err)
 {
 	struct ext4_ext_path *path = NULL;
 	struct ext4_extent *ext;
@@ -611,7 +612,7 @@ mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
 		if (*err)
 			goto out;
 		ext = path[ext_depth(inode)].p_ext;
-		if (uninit != ext4_ext_is_uninitialized(ext))
+		if (unwritten != ext4_ext_is_unwritten(ext))
 			goto out;
 		from += ext4_ext_get_actual_len(ext);
 		ext4_ext_drop_refs(path);
@@ -894,7 +895,7 @@ out:
  * @orig_page_offset:		page index on original file
  * @data_offset_in_page:	block index where data swapping starts
  * @block_len_in_page:		the number of blocks to be swapped
- * @uninit:			orig extent is uninitialized or not
+ * @unwritten:			orig extent is unwritten or not
  * @err:			pointer to save return value
  *
  * Save the data in original inode blocks and replace original inode extents
@@ -905,7 +906,7 @@ out:
 static int
 move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
 		  pgoff_t orig_page_offset, int data_offset_in_page,
-		  int block_len_in_page, int uninit, int *err)
+		  int block_len_in_page, int unwritten, int *err)
 {
 	struct inode *orig_inode = file_inode(o_filp);
 	struct page *pagep[2] = {NULL, NULL};
@@ -962,27 +963,27 @@ again:
 	if (unlikely(*err < 0))
 		goto stop_journal;
 	/*
-	 * If orig extent was uninitialized it can become initialized
+	 * If orig extent was unwritten it can become initialized
 	 * at any time after i_data_sem was dropped, in order to
 	 * serialize with delalloc we have recheck extent while we
 	 * hold page's lock, if it is still the case data copy is not
 	 * necessary, just swap data blocks between orig and donor.
 	 */
-	if (uninit) {
+	if (unwritten) {
 		ext4_double_down_write_data_sem(orig_inode, donor_inode);
 		/* If any of extents in range became initialized we have to
 		 * fallback to data copying */
-		uninit = mext_check_coverage(orig_inode, orig_blk_offset,
-					     block_len_in_page, 1, err);
+		unwritten = mext_check_coverage(orig_inode, orig_blk_offset,
+						block_len_in_page, 1, err);
 		if (*err)
 			goto drop_data_sem;
 
-		uninit &= mext_check_coverage(donor_inode, orig_blk_offset,
-					      block_len_in_page, 1, err);
+		unwritten &= mext_check_coverage(donor_inode, orig_blk_offset,
+						 block_len_in_page, 1, err);
 		if (*err)
 			goto drop_data_sem;
 
-		if (!uninit) {
+		if (!unwritten) {
 			ext4_double_up_write_data_sem(orig_inode, donor_inode);
 			goto data_copy;
 		}
@@ -1259,7 +1260,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 	int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits;
 	int data_offset_in_page;
 	int block_len_in_page;
-	int uninit;
+	int unwritten;
 
 	if (orig_inode->i_sb != donor_inode->i_sb) {
 		ext4_debug("ext4 move extent: The argument files "
@@ -1391,8 +1392,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 		    !last_extent)
 			continue;
 
-		/* Is original extent is uninitialized */
-		uninit = ext4_ext_is_uninitialized(ext_prev);
+		/* Is original extent is unwritten */
+		unwritten = ext4_ext_is_unwritten(ext_prev);
 
 		data_offset_in_page = seq_start % blocks_per_page;
 
@@ -1432,8 +1433,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
 						o_filp, donor_inode,
 						orig_page_offset,
 						data_offset_in_page,
-						block_len_in_page, uninit,
-						&ret);
+						block_len_in_page,
+						unwritten, &ret);
 
 			/* Count how many blocks we have exchanged */
 			*moved_len += block_len_in_page;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1cb84f78909..3520ab8a663 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -67,6 +67,7 @@ static struct buffer_head *ext4_append(handle_t *handle,
 		return ERR_PTR(err);
 	inode->i_size += inode->i_sb->s_blocksize;
 	EXT4_I(inode)->i_disksize = inode->i_size;
+	BUFFER_TRACE(bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, bh);
 	if (err) {
 		brelse(bh);
@@ -1778,6 +1779,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 
 	blocksize =  dir->i_sb->s_blocksize;
 	dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
+	BUFFER_TRACE(bh, "get_write_access");
 	retval = ext4_journal_get_write_access(handle, bh);
 	if (retval) {
 		ext4_std_error(dir->i_sb, retval);
@@ -2510,8 +2512,7 @@ static int empty_dir(struct inode *inode)
 		 ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize);
 	de = ext4_next_entry(de1, sb->s_blocksize);
 	while (offset < inode->i_size) {
-		if (!bh ||
-		    (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
+		if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
 			unsigned int lblock;
 			err = 0;
 			brelse(bh);
@@ -2539,26 +2540,37 @@ static int empty_dir(struct inode *inode)
 	return 1;
 }
 
-/* ext4_orphan_add() links an unlinked or truncated inode into a list of
+/*
+ * ext4_orphan_add() links an unlinked or truncated inode into a list of
  * such inodes, starting at the superblock, in case we crash before the
  * file is closed/deleted, or in case the inode truncate spans multiple
  * transactions and the last transaction is not recovered after a crash.
  *
  * At filesystem recovery time, we walk this list deleting unlinked
  * inodes and truncating linked inodes in ext4_orphan_cleanup().
+ *
+ * Orphan list manipulation functions must be called under i_mutex unless
+ * we are just creating the inode or deleting it.
  */
 int ext4_orphan_add(handle_t *handle, struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_iloc iloc;
 	int err = 0, rc;
+	bool dirty = false;
 
-	if (!EXT4_SB(sb)->s_journal)
+	if (!sbi->s_journal)
 		return 0;
 
-	mutex_lock(&EXT4_SB(sb)->s_orphan_lock);
+	WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
+		     !mutex_is_locked(&inode->i_mutex));
+	/*
+	 * Exit early if inode already is on orphan list. This is a big speedup
+	 * since we don't have to contend on the global s_orphan_lock.
+	 */
 	if (!list_empty(&EXT4_I(inode)->i_orphan))
-		goto out_unlock;
+		return 0;
 
 	/*
 	 * Orphan handling is only valid for files with data blocks
@@ -2569,48 +2581,51 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
 	J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 		  S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
 
-	BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
-	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
+	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
 	if (err)
-		goto out_unlock;
+		goto out;
 
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
 	if (err)
-		goto out_unlock;
+		goto out;
+
+	mutex_lock(&sbi->s_orphan_lock);
 	/*
 	 * Due to previous errors inode may be already a part of on-disk
 	 * orphan list. If so skip on-disk list modification.
 	 */
-	if (NEXT_ORPHAN(inode) && NEXT_ORPHAN(inode) <=
-		(le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)))
-			goto mem_insert;
-
-	/* Insert this inode at the head of the on-disk orphan list... */
-	NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan);
-	EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
-	err = ext4_handle_dirty_super(handle, sb);
-	rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
-	if (!err)
-		err = rc;
-
-	/* Only add to the head of the in-memory list if all the
-	 * previous operations succeeded.  If the orphan_add is going to
-	 * fail (possibly taking the journal offline), we can't risk
-	 * leaving the inode on the orphan list: stray orphan-list
-	 * entries can cause panics at unmount time.
-	 *
-	 * This is safe: on error we're going to ignore the orphan list
-	 * anyway on the next recovery. */
-mem_insert:
-	if (!err)
-		list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
-
+	if (!NEXT_ORPHAN(inode) || NEXT_ORPHAN(inode) >
+	    (le32_to_cpu(sbi->s_es->s_inodes_count))) {
+		/* Insert this inode at the head of the on-disk orphan list */
+		NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+		sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+		dirty = true;
+	}
+	list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
+	mutex_unlock(&sbi->s_orphan_lock);
+
+	if (dirty) {
+		err = ext4_handle_dirty_super(handle, sb);
+		rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
+		if (!err)
+			err = rc;
+		if (err) {
+			/*
+			 * We have to remove inode from in-memory list if
+			 * addition to on disk orphan list failed. Stray orphan
+			 * list entries can cause panics at unmount time.
+			 */
+			mutex_lock(&sbi->s_orphan_lock);
+			list_del(&EXT4_I(inode)->i_orphan);
+			mutex_unlock(&sbi->s_orphan_lock);
+		}
+	}
 	jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
 	jbd_debug(4, "orphan inode %lu will point to %d\n",
 			inode->i_ino, NEXT_ORPHAN(inode));
-out_unlock:
-	mutex_unlock(&EXT4_SB(sb)->s_orphan_lock);
-	ext4_std_error(inode->i_sb, err);
+out:
+	ext4_std_error(sb, err);
 	return err;
 }
 
@@ -2622,45 +2637,51 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 {
 	struct list_head *prev;
 	struct ext4_inode_info *ei = EXT4_I(inode);
-	struct ext4_sb_info *sbi;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	__u32 ino_next;
 	struct ext4_iloc iloc;
 	int err = 0;
 
-	if ((!EXT4_SB(inode->i_sb)->s_journal) &&
-	    !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS))
+	if (!sbi->s_journal && !(sbi->s_mount_state & EXT4_ORPHAN_FS))
 		return 0;
 
-	mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
+	WARN_ON_ONCE(!(inode->i_state & (I_NEW | I_FREEING)) &&
+		     !mutex_is_locked(&inode->i_mutex));
+	/* Do this quick check before taking global s_orphan_lock. */
 	if (list_empty(&ei->i_orphan))
-		goto out;
+		return 0;
 
-	ino_next = NEXT_ORPHAN(inode);
-	prev = ei->i_orphan.prev;
-	sbi = EXT4_SB(inode->i_sb);
+	if (handle) {
+		/* Grab inode buffer early before taking global s_orphan_lock */
+		err = ext4_reserve_inode_write(handle, inode, &iloc);
+	}
 
+	mutex_lock(&sbi->s_orphan_lock);
 	jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino);
 
+	prev = ei->i_orphan.prev;
 	list_del_init(&ei->i_orphan);
 
 	/* If we're on an error path, we may not have a valid
 	 * transaction handle with which to update the orphan list on
 	 * disk, but we still need to remove the inode from the linked
 	 * list in memory. */
-	if (!handle)
-		goto out;
-
-	err = ext4_reserve_inode_write(handle, inode, &iloc);
-	if (err)
+	if (!handle || err) {
+		mutex_unlock(&sbi->s_orphan_lock);
 		goto out_err;
+	}
 
+	ino_next = NEXT_ORPHAN(inode);
 	if (prev == &sbi->s_orphan) {
 		jbd_debug(4, "superblock will point to %u\n", ino_next);
 		BUFFER_TRACE(sbi->s_sbh, "get_write_access");
 		err = ext4_journal_get_write_access(handle, sbi->s_sbh);
-		if (err)
+		if (err) {
+			mutex_unlock(&sbi->s_orphan_lock);
 			goto out_brelse;
+		}
 		sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+		mutex_unlock(&sbi->s_orphan_lock);
 		err = ext4_handle_dirty_super(handle, inode->i_sb);
 	} else {
 		struct ext4_iloc iloc2;
@@ -2670,20 +2691,20 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
 		jbd_debug(4, "orphan inode %lu will point to %u\n",
 			  i_prev->i_ino, ino_next);
 		err = ext4_reserve_inode_write(handle, i_prev, &iloc2);
-		if (err)
+		if (err) {
+			mutex_unlock(&sbi->s_orphan_lock);
 			goto out_brelse;
+		}
 		NEXT_ORPHAN(i_prev) = ino_next;
 		err = ext4_mark_iloc_dirty(handle, i_prev, &iloc2);
+		mutex_unlock(&sbi->s_orphan_lock);
 	}
 	if (err)
 		goto out_brelse;
 	NEXT_ORPHAN(inode) = 0;
 	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
-
 out_err:
 	ext4_std_error(inode->i_sb, err);
-out:
-	mutex_unlock(&EXT4_SB(inode->i_sb)->s_orphan_lock);
 	return err;
 
 out_brelse:
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 1a64e7a52b8..b24a2541a9b 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -401,7 +401,8 @@ submit_and_retry:
 int ext4_bio_write_page(struct ext4_io_submit *io,
 			struct page *page,
 			int len,
-			struct writeback_control *wbc)
+			struct writeback_control *wbc,
+			bool keep_towrite)
 {
 	struct inode *inode = page->mapping->host;
 	unsigned block_start, blocksize;
@@ -414,10 +415,24 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	BUG_ON(!PageLocked(page));
 	BUG_ON(PageWriteback(page));
 
-	set_page_writeback(page);
+	if (keep_towrite)
+		set_page_writeback_keepwrite(page);
+	else
+		set_page_writeback(page);
 	ClearPageError(page);
 
 	/*
+	 * Comments copied from block_write_full_page:
+	 *
+	 * The page straddles i_size.  It must be zeroed out on each and every
+	 * writepage invocation because it may be mmapped.  "A file is mapped
+	 * in multiples of the page size.  For a file that is not a multiple of
+	 * the page size, the remaining memory is zeroed when mapped, and
+	 * writes to that region are not written out to the file."
+	 */
+	if (len < PAGE_CACHE_SIZE)
+		zero_user_segment(page, len, PAGE_CACHE_SIZE);
+	/*
 	 * In the first loop we prepare and mark buffers to submit. We have to
 	 * mark all buffers in the page before submitting so that
 	 * end_page_writeback() cannot be called from ext4_bio_end_io() when IO
@@ -428,19 +443,6 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	do {
 		block_start = bh_offset(bh);
 		if (block_start >= len) {
-			/*
-			 * Comments copied from block_write_full_page:
-			 *
-			 * The page straddles i_size.  It must be zeroed out on
-			 * each and every writepage invocation because it may
-			 * be mmapped.  "A file is mapped in multiples of the
-			 * page size.  For a file that is not a multiple of
-			 * the  page size, the remaining memory is zeroed when
-			 * mapped, and writes to that region are not written
-			 * out to the file."
-			 */
-			zero_user_segment(page, block_start,
-					  block_start + blocksize);
 			clear_buffer_dirty(bh);
 			set_buffer_uptodate(bh);
 			continue;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 08b3c116915..bb0e80f03e2 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -348,6 +348,7 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
 	bh = sb_getblk(sb, blk);
 	if (unlikely(!bh))
 		return ERR_PTR(-ENOMEM);
+	BUFFER_TRACE(bh, "get_write_access");
 	if ((err = ext4_journal_get_write_access(handle, bh))) {
 		brelse(bh);
 		bh = ERR_PTR(err);
@@ -426,6 +427,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
 		if (unlikely(!bh))
 			return -ENOMEM;
 
+		BUFFER_TRACE(bh, "get_write_access");
 		err = ext4_journal_get_write_access(handle, bh);
 		if (err)
 			return err;
@@ -518,6 +520,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
 				goto out;
 			}
 
+			BUFFER_TRACE(gdb, "get_write_access");
 			err = ext4_journal_get_write_access(handle, gdb);
 			if (err) {
 				brelse(gdb);
@@ -790,14 +793,17 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 		goto exit_dind;
 	}
 
+	BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
 	if (unlikely(err))
 		goto exit_dind;
 
+	BUFFER_TRACE(gdb_bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, gdb_bh);
 	if (unlikely(err))
 		goto exit_dind;
 
+	BUFFER_TRACE(dind, "get_write_access");
 	err = ext4_journal_get_write_access(handle, dind);
 	if (unlikely(err))
 		ext4_std_error(sb, err);
@@ -902,6 +908,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
 	EXT4_SB(sb)->s_group_desc = n_group_desc;
 	EXT4_SB(sb)->s_gdb_count++;
 	ext4_kvfree(o_group_desc);
+	BUFFER_TRACE(gdb_bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, gdb_bh);
 	if (unlikely(err))
 		brelse(gdb_bh);
@@ -977,6 +984,7 @@ static int reserve_backup_gdb(handle_t *handle, struct inode *inode,
 	}
 
 	for (i = 0; i < reserved_gdb; i++) {
+		BUFFER_TRACE(primary[i], "get_write_access");
 		if ((err = ext4_journal_get_write_access(handle, primary[i])))
 			goto exit_bh;
 	}
@@ -1084,6 +1092,7 @@ static void update_backups(struct super_block *sb, int blk_off, char *data,
 		ext4_debug("update metadata backup %llu(+%llu)\n",
 			   backup_block, backup_block -
 			   ext4_group_first_block_no(sb, group));
+		BUFFER_TRACE(bh, "get_write_access");
 		if ((err = ext4_journal_get_write_access(handle, bh)))
 			break;
 		lock_buffer(bh);
@@ -1163,6 +1172,7 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb,
 		 */
 		if (gdb_off) {
 			gdb_bh = sbi->s_group_desc[gdb_num];
+			BUFFER_TRACE(gdb_bh, "get_write_access");
 			err = ext4_journal_get_write_access(handle, gdb_bh);
 
 			if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group))
@@ -1433,6 +1443,7 @@ static int ext4_flex_group_add(struct super_block *sb,
 		goto exit;
 	}
 
+	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
 	if (err)
 		goto exit_journal;
@@ -1645,6 +1656,7 @@ static int ext4_group_extend_no_check(struct super_block *sb,
 		return err;
 	}
 
+	BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
 	if (err) {
 		ext4_warning(sb, "error %d on journal write access", err);
@@ -1804,6 +1816,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
+	BUFFER_TRACE(sbi->s_sbh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, sbi->s_sbh);
 	if (err)
 		goto errout;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6f9e6fadac0..6df7bc611db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -138,8 +138,8 @@ static __le32 ext4_superblock_csum(struct super_block *sb,
 	return cpu_to_le32(csum);
 }
 
-int ext4_superblock_csum_verify(struct super_block *sb,
-				struct ext4_super_block *es)
+static int ext4_superblock_csum_verify(struct super_block *sb,
+				       struct ext4_super_block *es)
 {
 	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
@@ -879,6 +879,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 		return NULL;
 
 	ei->vfs_inode.i_version = 1;
+	spin_lock_init(&ei->i_raw_lock);
 	INIT_LIST_HEAD(&ei->i_prealloc_list);
 	spin_lock_init(&ei->i_prealloc_lock);
 	ext4_es_init_tree(&ei->i_es_tree);
@@ -1524,8 +1525,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
 		sbi->s_commit_interval = HZ * arg;
 	} else if (token == Opt_max_batch_time) {
-		if (arg == 0)
-			arg = EXT4_DEF_MAX_BATCH_TIME;
 		sbi->s_max_batch_time = arg;
 	} else if (token == Opt_min_batch_time) {
 		sbi->s_min_batch_time = arg;
@@ -1903,7 +1902,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	if (!(sbi->s_mount_state & EXT4_VALID_FS))
 		ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
 			 "running e2fsck is recommended");
-	else if ((sbi->s_mount_state & EXT4_ERROR_FS))
+	else if (sbi->s_mount_state & EXT4_ERROR_FS)
 		ext4_msg(sb, KERN_WARNING,
 			 "warning: mounting fs with errors, "
 			 "running e2fsck is recommended");
@@ -2404,6 +2403,16 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb,
 	if (ext4_bg_has_super(sb, bg))
 		has_super = 1;
 
+	/*
+	 * If we have a meta_bg fs with 1k blocks, group 0's GDT is at
+	 * block 2, not 1.  If s_first_data_block == 0 (bigalloc is enabled
+	 * on modern mke2fs or blksize > 1k on older mke2fs) then we must
+	 * compensate.
+	 */
+	if (sb->s_blocksize == 1024 && nr == 0 &&
+	    le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) == 0)
+		has_super++;
+
 	return (has_super + ext4_group_first_block_no(sb, bg));
 }
 
@@ -2798,10 +2807,11 @@ static void print_daily_error_info(unsigned long arg)
 	es = sbi->s_es;
 
 	if (es->s_error_count)
-		ext4_msg(sb, KERN_NOTICE, "error count: %u",
+		/* fsck newer than v1.41.13 is needed to clean this condition. */
+		ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
 			 le32_to_cpu(es->s_error_count));
 	if (es->s_first_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_first_error_time),
 		       (int) sizeof(es->s_first_error_func),
 		       es->s_first_error_func,
@@ -2815,7 +2825,7 @@ static void print_daily_error_info(unsigned long arg)
 		printk("\n");
 	}
 	if (es->s_last_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
 		       sb->s_id, le32_to_cpu(es->s_last_error_time),
 		       (int) sizeof(es->s_last_error_func),
 		       es->s_last_error_func,
@@ -3337,7 +3347,7 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
 	 * By default we reserve 2% or 4096 clusters, whichever is smaller.
 	 * This should cover the situations where we can not afford to run
 	 * out of space like for example punch hole, or converting
-	 * uninitialized extents in delalloc path. In most cases such
+	 * unwritten extents in delalloc path. In most cases such
 	 * allocation would require 1, or 2 blocks, higher numbers are
 	 * very rare.
 	 */
@@ -3869,38 +3879,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount2;
 		}
 	}
-
-	/*
-	 * set up enough so that it can read an inode,
-	 * and create new inode for buddy allocator
-	 */
-	sbi->s_gdb_count = db_count;
-	if (!test_opt(sb, NOLOAD) &&
-	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
-		sb->s_op = &ext4_sops;
-	else
-		sb->s_op = &ext4_nojournal_sops;
-
-	ext4_ext_init(sb);
-	err = ext4_mb_init(sb);
-	if (err) {
-		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
-			 err);
-		goto failed_mount2;
-	}
-
 	if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
 		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
-		goto failed_mount2a;
+		goto failed_mount2;
 	}
 	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG))
 		if (!ext4_fill_flex_info(sb)) {
 			ext4_msg(sb, KERN_ERR,
 			       "unable to initialize "
 			       "flex_bg meta info!");
-			goto failed_mount2a;
+			goto failed_mount2;
 		}
 
+	sbi->s_gdb_count = db_count;
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 	spin_lock_init(&sbi->s_next_gen_lock);
 
@@ -3935,6 +3926,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_stripe = ext4_get_stripe_size(sbi);
 	sbi->s_extent_max_zeroout_kb = 32;
 
+	/*
+	 * set up enough so that it can read an inode
+	 */
+	if (!test_opt(sb, NOLOAD) &&
+	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+		sb->s_op = &ext4_sops;
+	else
+		sb->s_op = &ext4_nojournal_sops;
 	sb->s_export_op = &ext4_export_ops;
 	sb->s_xattr = ext4_xattr_handlers;
 #ifdef CONFIG_QUOTA
@@ -4124,13 +4123,21 @@ no_journal:
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
 			 "reserved pool", ext4_calculate_resv_clusters(sb));
-		goto failed_mount5;
+		goto failed_mount4a;
 	}
 
 	err = ext4_setup_system_zone(sb);
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "failed to initialize system "
 			 "zone (%d)", err);
+		goto failed_mount4a;
+	}
+
+	ext4_ext_init(sb);
+	err = ext4_mb_init(sb);
+	if (err) {
+		ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
+			 err);
 		goto failed_mount5;
 	}
 
@@ -4207,8 +4214,11 @@ failed_mount8:
 failed_mount7:
 	ext4_unregister_li_request(sb);
 failed_mount6:
-	ext4_release_system_zone(sb);
+	ext4_mb_release(sb);
 failed_mount5:
+	ext4_ext_release(sb);
+	ext4_release_system_zone(sb);
+failed_mount4a:
 	dput(sb->s_root);
 	sb->s_root = NULL;
 failed_mount4:
@@ -4232,14 +4242,11 @@ failed_mount3:
 	percpu_counter_destroy(&sbi->s_extent_cache_cnt);
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
-failed_mount2a:
-	ext4_mb_release(sb);
 failed_mount2:
 	for (i = 0; i < db_count; i++)
 		brelse(sbi->s_group_desc[i]);
 	ext4_kvfree(sbi->s_group_desc);
 failed_mount:
-	ext4_ext_release(sb);
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	if (sbi->s_proc) {
@@ -5370,6 +5377,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 	bh = ext4_bread(handle, inode, blk, 1, &err);
 	if (!bh)
 		goto out;
+	BUFFER_TRACE(bh, "get write access");
 	err = ext4_journal_get_write_access(handle, bh);
 	if (err) {
 		brelse(bh);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 4eec399ec80..e7387337060 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -369,6 +369,9 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
 {
 	int error;
 
+	if (strlen(name) > 255)
+		return -ERANGE;
+
 	down_read(&EXT4_I(inode)->xattr_sem);
 	error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
 				     buffer_size);
@@ -513,6 +516,7 @@ static void ext4_xattr_update_super_block(handle_t *handle,
 	if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR))
 		return;
 
+	BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
 	if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
 		EXT4_SET_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_EXT_ATTR);
 		ext4_handle_dirty_super(handle, sb);
@@ -532,6 +536,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 	ce = mb_cache_entry_get(ext4_mb_cache, bh->b_bdev, bh->b_blocknr);
+	BUFFER_TRACE(bh, "get_write_access");
 	error = ext4_journal_get_write_access(handle, bh);
 	if (error)
 		goto out;
@@ -774,6 +779,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 	if (s->base) {
 		ce = mb_cache_entry_get(ext4_mb_cache, bs->bh->b_bdev,
 					bs->bh->b_blocknr);
+		BUFFER_TRACE(bs->bh, "get_write_access");
 		error = ext4_journal_get_write_access(handle, bs->bh);
 		if (error)
 			goto cleanup;
@@ -859,6 +865,7 @@ inserted:
 						EXT4_C2B(EXT4_SB(sb), 1));
 				if (error)
 					goto cleanup;
+				BUFFER_TRACE(new_bh, "get_write_access");
 				error = ext4_journal_get_write_access(handle,
 								      new_bh);
 				if (error)
@@ -896,7 +903,7 @@ inserted:
 			 * take i_data_sem because we will test
 			 * i_delalloc_reserved_flag in ext4_mb_new_blocks
 			 */
-			down_read((&EXT4_I(inode)->i_data_sem));
+			down_read(&EXT4_I(inode)->i_data_sem);
 			block = ext4_new_meta_blocks(handle, inode, goal, 0,
 						     NULL, &error);
 			up_read((&EXT4_I(inode)->i_data_sem));
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index e93e4ec7d16..dbe2141d10a 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -240,7 +240,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 		}
 	}
 
-	error = f2fs_setxattr(inode, name_index, "", value, size, ipage);
+	error = f2fs_setxattr(inode, name_index, "", value, size, ipage, 0);
 
 	kfree(value);
 	if (!error)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index c405b8f1705..0b4710c1d37 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -33,12 +33,12 @@ struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	struct address_space *mapping = META_MAPPING(sbi);
 	struct page *page = NULL;
 repeat:
-	page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+	page = grab_cache_page(mapping, index);
 	if (!page) {
 		cond_resched();
 		goto repeat;
 	}
-
+	f2fs_wait_on_page_writeback(page, META);
 	SetPageUptodate(page);
 	return page;
 }
@@ -72,7 +72,7 @@ out:
 	return page;
 }
 
-inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
+static inline int get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
 {
 	switch (type) {
 	case META_NAT:
@@ -154,6 +154,8 @@ static int f2fs_write_meta_page(struct page *page,
 	struct inode *inode = page->mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
+	trace_f2fs_writepage(page, META);
+
 	if (unlikely(sbi->por_doing))
 		goto redirty_out;
 	if (wbc->for_reclaim)
@@ -171,10 +173,7 @@ no_write:
 	return 0;
 
 redirty_out:
-	dec_page_count(sbi, F2FS_DIRTY_META);
-	wbc->pages_skipped++;
-	account_page_redirty(page);
-	set_page_dirty(page);
+	redirty_page_for_writepage(wbc, page);
 	return AOP_WRITEPAGE_ACTIVATE;
 }
 
@@ -184,6 +183,8 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
 	long diff, written;
 
+	trace_f2fs_writepages(mapping->host, wbc, META);
+
 	/* collect a number of dirty meta pages and write together */
 	if (wbc->for_kupdate ||
 		get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
@@ -367,7 +368,9 @@ void recover_orphan_inodes(struct f2fs_sb_info *sbi)
 		return;
 
 	sbi->por_doing = true;
-	start_blk = __start_cp_addr(sbi) + 1;
+
+	start_blk = __start_cp_addr(sbi) + 1 +
+		le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
 	orphan_blkaddr = __start_sum_addr(sbi) - 1;
 
 	ra_meta_pages(sbi, start_blk, orphan_blkaddr, META_CP);
@@ -508,8 +511,11 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	unsigned long blk_size = sbi->blocksize;
 	unsigned long long cp1_version = 0, cp2_version = 0;
 	unsigned long long cp_start_blk_no;
+	unsigned int cp_blks = 1 + le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
+	block_t cp_blk_no;
+	int i;
 
-	sbi->ckpt = kzalloc(blk_size, GFP_KERNEL);
+	sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL);
 	if (!sbi->ckpt)
 		return -ENOMEM;
 	/*
@@ -540,6 +546,23 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
 	memcpy(sbi->ckpt, cp_block, blk_size);
 
+	if (cp_blks <= 1)
+		goto done;
+
+	cp_blk_no = le32_to_cpu(fsb->cp_blkaddr);
+	if (cur_page == cp2)
+		cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
+
+	for (i = 1; i < cp_blks; i++) {
+		void *sit_bitmap_ptr;
+		unsigned char *ckpt = (unsigned char *)sbi->ckpt;
+
+		cur_page = get_meta_page(sbi, cp_blk_no + i);
+		sit_bitmap_ptr = page_address(cur_page);
+		memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
+		f2fs_put_page(cur_page, 1);
+	}
+done:
 	f2fs_put_page(cp1, 1);
 	f2fs_put_page(cp2, 1);
 	return 0;
@@ -552,14 +575,13 @@ fail_no_cp:
 static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	struct list_head *head = &sbi->dir_inode_list;
-	struct dir_inode_entry *entry;
 
-	list_for_each_entry(entry, head, list)
-		if (unlikely(entry->inode == inode))
-			return -EEXIST;
+	if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))
+		return -EEXIST;
 
-	list_add_tail(&new->list, head);
+	set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
+	F2FS_I(inode)->dirty_dir = new;
+	list_add_tail(&new->list, &sbi->dir_inode_list);
 	stat_inc_dirty_dir(sbi);
 	return 0;
 }
@@ -608,31 +630,26 @@ void add_dirty_dir_inode(struct inode *inode)
 void remove_dirty_dir_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
-	struct list_head *head;
 	struct dir_inode_entry *entry;
 
 	if (!S_ISDIR(inode->i_mode))
 		return;
 
 	spin_lock(&sbi->dir_inode_lock);
-	if (get_dirty_dents(inode)) {
+	if (get_dirty_dents(inode) ||
+			!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {
 		spin_unlock(&sbi->dir_inode_lock);
 		return;
 	}
 
-	head = &sbi->dir_inode_list;
-	list_for_each_entry(entry, head, list) {
-		if (entry->inode == inode) {
-			list_del(&entry->list);
-			stat_dec_dirty_dir(sbi);
-			spin_unlock(&sbi->dir_inode_lock);
-			kmem_cache_free(inode_entry_slab, entry);
-			goto done;
-		}
-	}
+	entry = F2FS_I(inode)->dirty_dir;
+	list_del(&entry->list);
+	F2FS_I(inode)->dirty_dir = NULL;
+	clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
+	stat_dec_dirty_dir(sbi);
 	spin_unlock(&sbi->dir_inode_lock);
+	kmem_cache_free(inode_entry_slab, entry);
 
-done:
 	/* Only from the recovery routine */
 	if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
 		clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
@@ -640,26 +657,6 @@ done:
 	}
 }
 
-struct inode *check_dirty_dir_inode(struct f2fs_sb_info *sbi, nid_t ino)
-{
-
-	struct list_head *head;
-	struct inode *inode = NULL;
-	struct dir_inode_entry *entry;
-
-	spin_lock(&sbi->dir_inode_lock);
-
-	head = &sbi->dir_inode_list;
-	list_for_each_entry(entry, head, list) {
-		if (entry->inode->i_ino == ino) {
-			inode = entry->inode;
-			break;
-		}
-	}
-	spin_unlock(&sbi->dir_inode_lock);
-	return inode;
-}
-
 void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
 {
 	struct list_head *head;
@@ -758,6 +755,13 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	__u32 crc32 = 0;
 	void *kaddr;
 	int i;
+	int cp_payload_blks = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
+
+	/*
+	 * This avoids to conduct wrong roll-forward operations and uses
+	 * metapages, so should be called prior to sync_meta_pages below.
+	 */
+	discard_next_dnode(sbi);
 
 	/* Flush all the NAT/SIT pages */
 	while (get_pages(sbi, F2FS_DIRTY_META))
@@ -802,16 +806,19 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 
 	orphan_blocks = (sbi->n_orphans + F2FS_ORPHANS_PER_BLOCK - 1)
 					/ F2FS_ORPHANS_PER_BLOCK;
-	ckpt->cp_pack_start_sum = cpu_to_le32(1 + orphan_blocks);
+	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
+			orphan_blocks);
 
 	if (is_umount) {
 		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
 		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
-			data_sum_blocks + orphan_blocks + NR_CURSEG_NODE_TYPE);
+				cp_payload_blks + data_sum_blocks +
+				orphan_blocks + NR_CURSEG_NODE_TYPE);
 	} else {
 		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
 		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
-			data_sum_blocks + orphan_blocks);
+				cp_payload_blks + data_sum_blocks +
+				orphan_blocks);
 	}
 
 	if (sbi->n_orphans)
@@ -837,6 +844,15 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
 	set_page_dirty(cp_page);
 	f2fs_put_page(cp_page, 1);
 
+	for (i = 1; i < 1 + cp_payload_blks; i++) {
+		cp_page = grab_meta_page(sbi, start_blk++);
+		kaddr = page_address(cp_page);
+		memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE,
+				(1 << sbi->log_blocksize));
+		set_page_dirty(cp_page);
+		f2fs_put_page(cp_page, 1);
+	}
+
 	if (sbi->n_orphans) {
 		write_orphan_inodes(sbi, start_blk);
 		start_blk += orphan_blocks;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 45abd60e2bf..f8cf619edb5 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -417,7 +417,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	if (unlikely(dn.data_blkaddr == NEW_ADDR))
 		return ERR_PTR(-EINVAL);
 
-	page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+	page = grab_cache_page(mapping, index);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -455,7 +455,7 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	int err;
 
 repeat:
-	page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+	page = grab_cache_page(mapping, index);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -608,8 +608,8 @@ static int __allocate_data_block(struct dnode_of_data *dn)
  *     b. do not use extent cache for better performance
  *     c. give the block addresses to blockdev
  */
-static int get_data_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh_result, int create)
+static int __get_data_block(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh_result, int create, bool fiemap)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	unsigned int blkbits = inode->i_sb->s_blocksize_bits;
@@ -637,7 +637,7 @@ static int get_data_block(struct inode *inode, sector_t iblock,
 			err = 0;
 		goto unlock_out;
 	}
-	if (dn.data_blkaddr == NEW_ADDR)
+	if (dn.data_blkaddr == NEW_ADDR && !fiemap)
 		goto put_out;
 
 	if (dn.data_blkaddr != NULL_ADDR) {
@@ -652,8 +652,7 @@ static int get_data_block(struct inode *inode, sector_t iblock,
 		goto put_out;
 	}
 
-	end_offset = IS_INODE(dn.node_page) ?
-			ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+	end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 	bh_result->b_size = (((size_t)1) << blkbits);
 	dn.ofs_in_node++;
 	pgofs++;
@@ -672,11 +671,10 @@ get_next:
 				err = 0;
 			goto unlock_out;
 		}
-		if (dn.data_blkaddr == NEW_ADDR)
+		if (dn.data_blkaddr == NEW_ADDR && !fiemap)
 			goto put_out;
 
-		end_offset = IS_INODE(dn.node_page) ?
-			ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 	}
 
 	if (maxblocks > (bh_result->b_size >> blkbits)) {
@@ -710,11 +708,32 @@ out:
 	return err;
 }
 
+static int get_data_block(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh_result, int create)
+{
+	return __get_data_block(inode, iblock, bh_result, create, false);
+}
+
+static int get_data_block_fiemap(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh_result, int create)
+{
+	return __get_data_block(inode, iblock, bh_result, create, true);
+}
+
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+		u64 start, u64 len)
+{
+	return generic_block_fiemap(inode, fieinfo,
+				start, len, get_data_block_fiemap);
+}
+
 static int f2fs_read_data_page(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	int ret;
 
+	trace_f2fs_readpage(page, DATA);
+
 	/* If the file has inline data, try to read it directlly */
 	if (f2fs_has_inline_data(inode))
 		ret = f2fs_read_inline_data(inode, page);
@@ -790,6 +809,8 @@ static int f2fs_write_data_page(struct page *page,
 		.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
 	};
 
+	trace_f2fs_writepage(page, DATA);
+
 	if (page->index < end_index)
 		goto write;
 
@@ -798,10 +819,8 @@ static int f2fs_write_data_page(struct page *page,
 	 * this page does not have to be written to disk.
 	 */
 	offset = i_size & (PAGE_CACHE_SIZE - 1);
-	if ((page->index >= end_index + 1) || !offset) {
-		inode_dec_dirty_dents(inode);
+	if ((page->index >= end_index + 1) || !offset)
 		goto out;
-	}
 
 	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
 write:
@@ -810,7 +829,6 @@ write:
 
 	/* Dentry blocks are controlled by checkpoint */
 	if (S_ISDIR(inode->i_mode)) {
-		inode_dec_dirty_dents(inode);
 		err = do_write_data_page(page, &fio);
 		goto done;
 	}
@@ -832,15 +850,16 @@ done:
 
 	clear_cold_data(page);
 out:
+	inode_dec_dirty_dents(inode);
 	unlock_page(page);
 	if (need_balance_fs)
 		f2fs_balance_fs(sbi);
+	if (wbc->for_reclaim)
+		f2fs_submit_merged_bio(sbi, DATA, WRITE);
 	return 0;
 
 redirty_out:
-	wbc->pages_skipped++;
-	account_page_redirty(page);
-	set_page_dirty(page);
+	redirty_page_for_writepage(wbc, page);
 	return AOP_WRITEPAGE_ACTIVATE;
 }
 
@@ -862,12 +881,15 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	int ret;
 	long diff;
 
+	trace_f2fs_writepages(mapping->host, wbc, DATA);
+
 	/* deal with chardevs and other special file */
 	if (!mapping->a_ops->writepage)
 		return 0;
 
 	if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
-			get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA))
+			get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA) &&
+			available_free_memory(sbi, DIRTY_DENTS))
 		goto skip_write;
 
 	diff = nr_pages_to_write(sbi, DATA, wbc);
@@ -903,6 +925,8 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 	struct dnode_of_data dn;
 	int err = 0;
 
+	trace_f2fs_write_begin(inode, pos, len, flags);
+
 	f2fs_balance_fs(sbi);
 repeat:
 	err = f2fs_convert_inline_data(inode, pos + len);
@@ -912,6 +936,10 @@ repeat:
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
+
+	/* to avoid latency during memory pressure */
+	unlock_page(page);
+
 	*pagep = page;
 
 	if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
@@ -923,10 +951,18 @@ repeat:
 	f2fs_unlock_op(sbi);
 
 	if (err) {
-		f2fs_put_page(page, 1);
+		f2fs_put_page(page, 0);
 		return err;
 	}
 inline_data:
+	lock_page(page);
+	if (unlikely(page->mapping != mapping)) {
+		f2fs_put_page(page, 1);
+		goto repeat;
+	}
+
+	f2fs_wait_on_page_writeback(page, DATA);
+
 	if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
 		return 0;
 
@@ -978,6 +1014,8 @@ static int f2fs_write_end(struct file *file,
 {
 	struct inode *inode = page->mapping->host;
 
+	trace_f2fs_write_end(inode, pos, len, copied);
+
 	SetPageUptodate(page);
 	set_page_dirty(page);
 
@@ -992,10 +1030,9 @@ static int f2fs_write_end(struct file *file,
 }
 
 static int check_direct_IO(struct inode *inode, int rw,
-		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+		struct iov_iter *iter, loff_t offset)
 {
 	unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
-	int i;
 
 	if (rw == READ)
 		return 0;
@@ -1003,14 +1040,14 @@ static int check_direct_IO(struct inode *inode, int rw,
 	if (offset & blocksize_mask)
 		return -EINVAL;
 
-	for (i = 0; i < nr_segs; i++)
-		if (iov[i].iov_len & blocksize_mask)
-			return -EINVAL;
+	if (iov_iter_alignment(iter) & blocksize_mask)
+		return -EINVAL;
+
 	return 0;
 }
 
 static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
-		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+		struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -1019,11 +1056,14 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 	if (f2fs_has_inline_data(inode))
 		return 0;
 
-	if (check_direct_IO(inode, rw, iov, offset, nr_segs))
+	if (check_direct_IO(inode, rw, iter, offset))
 		return 0;
 
-	return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
-							get_data_block);
+	/* clear fsync mark to recover these blocks */
+	fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino);
+
+	return blockdev_direct_IO(rw, iocb, inode, iter, offset,
+				  get_data_block);
 }
 
 static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
@@ -1061,6 +1101,11 @@ static int f2fs_set_data_page_dirty(struct page *page)
 
 static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
 {
+	struct inode *inode = mapping->host;
+
+	if (f2fs_has_inline_data(inode))
+		return 0;
+
 	return generic_block_bmap(mapping, block, get_data_block);
 }
 
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 972fd0ef230..a4addd72ebb 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -23,10 +23,10 @@ static unsigned long dir_blocks(struct inode *inode)
 
 static unsigned int dir_buckets(unsigned int level, int dir_level)
 {
-	if (level < MAX_DIR_HASH_DEPTH / 2)
+	if (level + dir_level < MAX_DIR_HASH_DEPTH / 2)
 		return 1 << (level + dir_level);
 	else
-		return 1 << ((MAX_DIR_HASH_DEPTH / 2 + dir_level) - 1);
+		return MAX_DIR_BUCKETS;
 }
 
 static unsigned int bucket_blocks(unsigned int level)
@@ -268,6 +268,8 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
 {
 	struct f2fs_inode *ri;
 
+	f2fs_wait_on_page_writeback(ipage, NODE);
+
 	/* copy name info. to this inode page */
 	ri = F2FS_INODE(ipage);
 	ri->i_namelen = cpu_to_le32(name->len);
@@ -374,11 +376,11 @@ static struct page *init_inode_metadata(struct inode *inode,
 
 put_error:
 	f2fs_put_page(page, 1);
+error:
 	/* once the failed inode becomes a bad inode, i_mode is S_IFREG */
 	truncate_inode_pages(&inode->i_data, 0);
 	truncate_blocks(inode, 0);
 	remove_dirty_dir_inode(inode);
-error:
 	remove_inode_page(inode);
 	return ERR_PTR(err);
 }
@@ -637,11 +639,17 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	struct f2fs_dir_entry *de = NULL;
 	struct page *dentry_page = NULL;
+	struct file_ra_state *ra = &file->f_ra;
 	unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
 	unsigned char d_type = DT_UNKNOWN;
 
 	bit_pos = ((unsigned long)ctx->pos % NR_DENTRY_IN_BLOCK);
 
+	/* readahead for multi pages of dir */
+	if (npages - n > 1 && !ra_has_index(ra, n))
+		page_cache_sync_readahead(inode->i_mapping, ra, file, n,
+				min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
+
 	for (; n < npages; n++) {
 		dentry_page = get_lock_data_page(inode, n);
 		if (IS_ERR(dentry_page))
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2ecac831235..58df97e174d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -182,6 +182,8 @@ enum {
 
 #define F2FS_LINK_MAX		32000	/* maximum link count per file */
 
+#define MAX_DIR_RA_PAGES	4	/* maximum ra pages of dir */
+
 /* for in-memory extent cache entry */
 #define F2FS_MIN_EXTENT_LEN	16	/* minimum extent length */
 
@@ -218,6 +220,7 @@ struct f2fs_inode_info {
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
 	unsigned long long xattr_ver;	/* cp version of xattr modification */
 	struct extent_info ext;		/* in-memory extent cache entry */
+	struct dir_inode_entry *dirty_dir;	/* the pointer of dirty dir */
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -243,6 +246,7 @@ static inline void set_raw_extent(struct extent_info *ext,
 struct f2fs_nm_info {
 	block_t nat_blkaddr;		/* base disk address of NAT */
 	nid_t max_nid;			/* maximum possible node ids */
+	nid_t available_nids;		/* maximum available node ids */
 	nid_t next_scan_nid;		/* the next nid to be scanned */
 	unsigned int ram_thresh;	/* control the memory footprint */
 
@@ -323,15 +327,21 @@ struct flush_cmd {
 	int ret;
 };
 
+struct flush_cmd_control {
+	struct task_struct *f2fs_issue_flush;	/* flush thread */
+	wait_queue_head_t flush_wait_queue;	/* waiting queue for wake-up */
+	struct flush_cmd *issue_list;		/* list for command issue */
+	struct flush_cmd *dispatch_list;	/* list for command dispatch */
+	spinlock_t issue_lock;			/* for issue list lock */
+	struct flush_cmd *issue_tail;		/* list tail of issue list */
+};
+
 struct f2fs_sm_info {
 	struct sit_info *sit_info;		/* whole segment information */
 	struct free_segmap_info *free_info;	/* free segment information */
 	struct dirty_seglist_info *dirty_info;	/* dirty segment information */
 	struct curseg_info *curseg_array;	/* active segment information */
 
-	struct list_head wblist_head;	/* list of under-writeback pages */
-	spinlock_t wblist_lock;		/* lock for checkpoint */
-
 	block_t seg0_blkaddr;		/* block address of 0'th segment */
 	block_t main_blkaddr;		/* start block address of main area */
 	block_t ssa_blkaddr;		/* start block address of SSA area */
@@ -353,12 +363,8 @@ struct f2fs_sm_info {
 	unsigned int min_ipu_util;	/* in-place-update threshold */
 
 	/* for flush command control */
-	struct task_struct *f2fs_issue_flush;	/* flush thread */
-	wait_queue_head_t flush_wait_queue;	/* waiting queue for wake-up */
-	struct flush_cmd *issue_list;		/* list for command issue */
-	struct flush_cmd *dispatch_list;	/* list for command dispatch */
-	spinlock_t issue_lock;			/* for issue list lock */
-	struct flush_cmd *issue_tail;		/* list tail of issue list */
+	struct flush_cmd_control *cmd_control_info;
+
 };
 
 /*
@@ -635,7 +641,8 @@ static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
  */
 static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
 {
-	WARN_ON((nid >= NM_I(sbi)->max_nid));
+	if (unlikely(nid < F2FS_ROOT_INO(sbi)))
+		return -EINVAL;
 	if (unlikely(nid >= NM_I(sbi)->max_nid))
 		return -EINVAL;
 	return 0;
@@ -755,9 +762,18 @@ static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag)
 static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	int offset = (flag == NAT_BITMAP) ?
+	int offset;
+
+	if (le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload) > 0) {
+		if (flag == NAT_BITMAP)
+			return &ckpt->sit_nat_version_bitmap;
+		else
+			return ((unsigned char *)ckpt + F2FS_BLKSIZE);
+	} else {
+		offset = (flag == NAT_BITMAP) ?
 			le32_to_cpu(ckpt->sit_ver_bitmap_bytesize) : 0;
-	return &ckpt->sit_nat_version_bitmap + offset;
+		return &ckpt->sit_nat_version_bitmap + offset;
+	}
 }
 
 static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
@@ -958,6 +974,7 @@ static inline int f2fs_clear_bit(unsigned int nr, char *addr)
 enum {
 	FI_NEW_INODE,		/* indicate newly allocated inode */
 	FI_DIRTY_INODE,		/* indicate inode is dirty or not */
+	FI_DIRTY_DIR,		/* indicate directory has dirty pages */
 	FI_INC_LINK,		/* need to increment i_nlink */
 	FI_ACL_MODE,		/* indicate acl mode */
 	FI_NO_ALLOC,		/* should not allocate any blocks */
@@ -1071,6 +1088,12 @@ static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi)
 	((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
 
+/* get offset of first page in next direct node */
+#define PGOFS_OF_NEXT_DNODE(pgofs, fi)				\
+	((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) :	\
+	(pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) /	\
+	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
+
 /*
  * file.c
  */
@@ -1140,8 +1163,10 @@ f2fs_hash_t f2fs_dentry_hash(const char *, size_t);
 struct dnode_of_data;
 struct node_info;
 
+bool available_free_memory(struct f2fs_sb_info *, int);
 int is_checkpointed_node(struct f2fs_sb_info *, nid_t);
 bool fsync_mark_done(struct f2fs_sb_info *, nid_t);
+void fsync_mark_clear(struct f2fs_sb_info *, nid_t);
 void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
 int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
 int truncate_inode_blocks(struct inode *, pgoff_t);
@@ -1176,9 +1201,12 @@ void destroy_node_manager_caches(void);
 void f2fs_balance_fs(struct f2fs_sb_info *);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *);
 int f2fs_issue_flush(struct f2fs_sb_info *);
+int create_flush_cmd_control(struct f2fs_sb_info *);
+void destroy_flush_cmd_control(struct f2fs_sb_info *);
 void invalidate_blocks(struct f2fs_sb_info *, block_t);
 void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
 void clear_prefree_segments(struct f2fs_sb_info *);
+void discard_next_dnode(struct f2fs_sb_info *);
 int npages_for_summary_flush(struct f2fs_sb_info *);
 void allocate_new_segments(struct f2fs_sb_info *);
 struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
@@ -1221,7 +1249,6 @@ int get_valid_checkpoint(struct f2fs_sb_info *);
 void set_dirty_dir_page(struct inode *, struct page *);
 void add_dirty_dir_inode(struct inode *);
 void remove_dirty_dir_inode(struct inode *);
-struct inode *check_dirty_dir_inode(struct f2fs_sb_info *, nid_t);
 void sync_dirty_dir_inodes(struct f2fs_sb_info *);
 void write_checkpoint(struct f2fs_sb_info *, bool);
 void init_orphan_info(struct f2fs_sb_info *);
@@ -1242,6 +1269,7 @@ struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
 struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
 int do_write_data_page(struct page *, struct f2fs_io_info *);
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
 
 /*
  * gc.c
@@ -1391,5 +1419,6 @@ bool f2fs_may_inline(struct inode *);
 int f2fs_read_inline_data(struct inode *, struct page *);
 int f2fs_convert_inline_data(struct inode *, pgoff_t);
 int f2fs_write_inline_data(struct inode *, struct page *, unsigned int);
+void truncate_inline_data(struct inode *, u64);
 int recover_inline_data(struct inode *, struct page *);
 #endif
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 60e7d5448a1..7d8b9627509 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -19,6 +19,7 @@
 #include <linux/compat.h>
 #include <linux/uaccess.h>
 #include <linux/mount.h>
+#include <linux/pagevec.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -194,6 +195,132 @@ out:
 	return ret;
 }
 
+static pgoff_t __get_first_dirty_index(struct address_space *mapping,
+						pgoff_t pgofs, int whence)
+{
+	struct pagevec pvec;
+	int nr_pages;
+
+	if (whence != SEEK_DATA)
+		return 0;
+
+	/* find first dirty page index */
+	pagevec_init(&pvec, 0);
+	nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs, PAGECACHE_TAG_DIRTY, 1);
+	pgofs = nr_pages ? pvec.pages[0]->index: LONG_MAX;
+	pagevec_release(&pvec);
+	return pgofs;
+}
+
+static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
+							int whence)
+{
+	switch (whence) {
+	case SEEK_DATA:
+		if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
+			(blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
+			return true;
+		break;
+	case SEEK_HOLE:
+		if (blkaddr == NULL_ADDR)
+			return true;
+		break;
+	}
+	return false;
+}
+
+static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t maxbytes = inode->i_sb->s_maxbytes;
+	struct dnode_of_data dn;
+	pgoff_t pgofs, end_offset, dirty;
+	loff_t data_ofs = offset;
+	loff_t isize;
+	int err = 0;
+
+	mutex_lock(&inode->i_mutex);
+
+	isize = i_size_read(inode);
+	if (offset >= isize)
+		goto fail;
+
+	/* handle inline data case */
+	if (f2fs_has_inline_data(inode)) {
+		if (whence == SEEK_HOLE)
+			data_ofs = isize;
+		goto found;
+	}
+
+	pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
+
+	dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
+
+	for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
+		if (err && err != -ENOENT) {
+			goto fail;
+		} else if (err == -ENOENT) {
+			/* direct node is not exist */
+			if (whence == SEEK_DATA) {
+				pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
+							F2FS_I(inode));
+				continue;
+			} else {
+				goto found;
+			}
+		}
+
+		end_offset = IS_INODE(dn.node_page) ?
+			ADDRS_PER_INODE(F2FS_I(inode)) : ADDRS_PER_BLOCK;
+
+		/* find data/hole in dnode block */
+		for (; dn.ofs_in_node < end_offset;
+				dn.ofs_in_node++, pgofs++,
+				data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+			block_t blkaddr;
+			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+			if (__found_offset(blkaddr, dirty, pgofs, whence)) {
+				f2fs_put_dnode(&dn);
+				goto found;
+			}
+		}
+		f2fs_put_dnode(&dn);
+	}
+
+	if (whence == SEEK_DATA)
+		goto fail;
+found:
+	if (whence == SEEK_HOLE && data_ofs > isize)
+		data_ofs = isize;
+	mutex_unlock(&inode->i_mutex);
+	return vfs_setpos(file, data_ofs, maxbytes);
+fail:
+	mutex_unlock(&inode->i_mutex);
+	return -ENXIO;
+}
+
+static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file->f_mapping->host;
+	loff_t maxbytes = inode->i_sb->s_maxbytes;
+
+	switch (whence) {
+	case SEEK_SET:
+	case SEEK_CUR:
+	case SEEK_END:
+		return generic_file_llseek_size(file, offset, whence,
+						maxbytes, i_size_read(inode));
+	case SEEK_DATA:
+	case SEEK_HOLE:
+		return f2fs_seek_block(file, offset, whence);
+	}
+
+	return -EINVAL;
+}
+
 static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	file_accessed(file);
@@ -242,6 +369,9 @@ static void truncate_partial_data_page(struct inode *inode, u64 from)
 	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
 	struct page *page;
 
+	if (f2fs_has_inline_data(inode))
+		return truncate_inline_data(inode, from);
+
 	if (!offset)
 		return;
 
@@ -288,10 +418,7 @@ int truncate_blocks(struct inode *inode, u64 from)
 		return err;
 	}
 
-	if (IS_INODE(dn.node_page))
-		count = ADDRS_PER_INODE(F2FS_I(inode));
-	else
-		count = ADDRS_PER_BLOCK;
+	count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 
 	count -= dn.ofs_in_node;
 	f2fs_bug_on(count < 0);
@@ -413,6 +540,7 @@ const struct inode_operations f2fs_file_inode_operations = {
 	.listxattr	= f2fs_listxattr,
 	.removexattr	= generic_removexattr,
 #endif
+	.fiemap		= f2fs_fiemap,
 };
 
 static void fill_zero(struct inode *inode, pgoff_t index,
@@ -531,16 +659,19 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 	off_start = offset & (PAGE_CACHE_SIZE - 1);
 	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
 
+	f2fs_lock_op(sbi);
+
 	for (index = pg_start; index <= pg_end; index++) {
 		struct dnode_of_data dn;
 
-		f2fs_lock_op(sbi);
+		if (index == pg_end && !off_end)
+			goto noalloc;
+
 		set_new_dnode(&dn, inode, NULL, NULL, 0);
 		ret = f2fs_reserve_block(&dn, index);
-		f2fs_unlock_op(sbi);
 		if (ret)
 			break;
-
+noalloc:
 		if (pg_start == pg_end)
 			new_size = offset + len;
 		else if (index == pg_start && off_start)
@@ -555,7 +686,9 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 		i_size_read(inode) < new_size) {
 		i_size_write(inode, new_size);
 		mark_inode_dirty(inode);
+		update_inode_page(inode);
 	}
+	f2fs_unlock_op(sbi);
 
 	return ret;
 }
@@ -678,11 +811,11 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 #endif
 
 const struct file_operations f2fs_file_operations = {
-	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
+	.llseek		= f2fs_llseek,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.open		= generic_file_open,
 	.mmap		= f2fs_file_mmap,
 	.fsync		= f2fs_sync_file,
@@ -692,5 +825,5 @@ const struct file_operations f2fs_file_operations = {
 	.compat_ioctl	= f2fs_compat_ioctl,
 #endif
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 };
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 383db1fabcf..1bba5228c19 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -81,8 +81,10 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
 
 	f2fs_lock_op(sbi);
 	ipage = get_node_page(sbi, inode->i_ino);
-	if (IS_ERR(ipage))
-		return PTR_ERR(ipage);
+	if (IS_ERR(ipage)) {
+		err = PTR_ERR(ipage);
+		goto out;
+	}
 
 	/*
 	 * i_addr[0] is not used for inline data,
@@ -90,11 +92,10 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
 	 */
 	set_new_dnode(&dn, inode, ipage, NULL, 0);
 	err = f2fs_reserve_block(&dn, 0);
-	if (err) {
-		f2fs_unlock_op(sbi);
-		return err;
-	}
+	if (err)
+		goto out;
 
+	f2fs_wait_on_page_writeback(page, DATA);
 	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
 
 	/* Copy the whole inline data block */
@@ -118,6 +119,7 @@ static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
 
 	sync_inode_page(&dn);
 	f2fs_put_dnode(&dn);
+out:
 	f2fs_unlock_op(sbi);
 	return err;
 }
@@ -132,7 +134,7 @@ int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size)
 	else if (to_size <= MAX_INLINE_DATA)
 		return 0;
 
-	page = grab_cache_page_write_begin(inode->i_mapping, 0, AOP_FLAG_NOFS);
+	page = grab_cache_page(inode->i_mapping, 0);
 	if (!page)
 		return -ENOMEM;
 
@@ -155,6 +157,7 @@ int f2fs_write_inline_data(struct inode *inode,
 		return err;
 	ipage = dn.inode_page;
 
+	f2fs_wait_on_page_writeback(ipage, NODE);
 	zero_user_segment(ipage, INLINE_DATA_OFFSET,
 				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
 	src_addr = kmap(page);
@@ -175,6 +178,26 @@ int f2fs_write_inline_data(struct inode *inode,
 	return 0;
 }
 
+void truncate_inline_data(struct inode *inode, u64 from)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+	struct page *ipage;
+
+	if (from >= MAX_INLINE_DATA)
+		return;
+
+	ipage = get_node_page(sbi, inode->i_ino);
+	if (IS_ERR(ipage))
+		return;
+
+	f2fs_wait_on_page_writeback(ipage, NODE);
+
+	zero_user_segment(ipage, INLINE_DATA_OFFSET + from,
+				INLINE_DATA_OFFSET + MAX_INLINE_DATA);
+	set_page_dirty(ipage);
+	f2fs_put_page(ipage, 1);
+}
+
 int recover_inline_data(struct inode *inode, struct page *npage)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
@@ -199,6 +222,8 @@ process_inline:
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(IS_ERR(ipage));
 
+		f2fs_wait_on_page_writeback(ipage, NODE);
+
 		src_addr = inline_data_addr(npage);
 		dst_addr = inline_data_addr(ipage);
 		memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
@@ -210,6 +235,7 @@ process_inline:
 	if (f2fs_has_inline_data(inode)) {
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(IS_ERR(ipage));
+		f2fs_wait_on_page_writeback(ipage, NODE);
 		zero_user_segment(ipage, INLINE_DATA_OFFSET,
 				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
 		clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index ee829d36046..2cf6962f6cc 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -12,6 +12,7 @@
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
+#include <linux/bitops.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -21,20 +22,20 @@
 void f2fs_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = F2FS_I(inode)->i_flags;
-
-	inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE |
-			S_NOATIME | S_DIRSYNC);
+	unsigned int new_fl = 0;
 
 	if (flags & FS_SYNC_FL)
-		inode->i_flags |= S_SYNC;
+		new_fl |= S_SYNC;
 	if (flags & FS_APPEND_FL)
-		inode->i_flags |= S_APPEND;
+		new_fl |= S_APPEND;
 	if (flags & FS_IMMUTABLE_FL)
-		inode->i_flags |= S_IMMUTABLE;
+		new_fl |= S_IMMUTABLE;
 	if (flags & FS_NOATIME_FL)
-		inode->i_flags |= S_NOATIME;
+		new_fl |= S_NOATIME;
 	if (flags & FS_DIRSYNC_FL)
-		inode->i_flags |= S_DIRSYNC;
+		new_fl |= S_DIRSYNC;
+	set_mask_bits(&inode->i_flags,
+			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
 }
 
 static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -77,6 +78,7 @@ static int do_read_inode(struct inode *inode)
 	if (check_nid_range(sbi, inode->i_ino)) {
 		f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu",
 			 (unsigned long) inode->i_ino);
+		WARN_ON(1);
 		return -EINVAL;
 	}
 
@@ -294,4 +296,5 @@ void f2fs_evict_inode(struct inode *inode)
 	sb_end_intwrite(inode->i_sb);
 no_delete:
 	clear_inode(inode);
+	invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
 }
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index a9409d19dfd..a6bdddc33ce 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -41,18 +41,9 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	}
 	f2fs_unlock_op(sbi);
 
-	inode->i_uid = current_fsuid();
-
-	if (dir->i_mode & S_ISGID) {
-		inode->i_gid = dir->i_gid;
-		if (S_ISDIR(mode))
-			mode |= S_ISGID;
-	} else {
-		inode->i_gid = current_fsgid();
-	}
+	inode_init_owner(inode, dir, mode);
 
 	inode->i_ino = ino;
-	inode->i_mode = mode;
 	inode->i_blocks = 0;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	inode->i_generation = sbi->s_next_generation++;
@@ -426,9 +417,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 
 		f2fs_set_link(new_dir, new_entry, new_page, old_inode);
-		down_write(&F2FS_I(old_inode)->i_sem);
-		F2FS_I(old_inode)->i_pino = new_dir->i_ino;
-		up_write(&F2FS_I(old_inode)->i_sem);
 
 		new_inode->i_ctime = CURRENT_TIME;
 		down_write(&F2FS_I(new_inode)->i_sem);
@@ -457,6 +445,10 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
+	down_write(&F2FS_I(old_inode)->i_sem);
+	file_lost_pino(old_inode);
+	up_write(&F2FS_I(old_inode)->i_sem);
+
 	old_inode->i_ctime = CURRENT_TIME;
 	mark_inode_dirty(old_inode);
 
@@ -466,9 +458,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (old_dir != new_dir) {
 			f2fs_set_link(old_inode, old_dir_entry,
 						old_dir_page, new_dir);
-			down_write(&F2FS_I(old_inode)->i_sem);
-			F2FS_I(old_inode)->i_pino = new_dir->i_ino;
-			up_write(&F2FS_I(old_inode)->i_sem);
 			update_inode_page(old_inode);
 		} else {
 			kunmap(old_dir_page);
@@ -483,7 +472,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	return 0;
 
 put_out_dir:
-	f2fs_put_page(new_page, 1);
+	kunmap(new_page);
+	f2fs_put_page(new_page, 0);
 out_dir:
 	if (old_dir_entry) {
 		kunmap(old_dir_page);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 57caa6eaf47..4b697ccc9b0 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -26,20 +26,28 @@
 static struct kmem_cache *nat_entry_slab;
 static struct kmem_cache *free_nid_slab;
 
-static inline bool available_free_memory(struct f2fs_nm_info *nm_i, int type)
+bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct sysinfo val;
 	unsigned long mem_size = 0;
+	bool res = false;
 
 	si_meminfo(&val);
-	if (type == FREE_NIDS)
-		mem_size = nm_i->fcnt * sizeof(struct free_nid);
-	else if (type == NAT_ENTRIES)
-		mem_size += nm_i->nat_cnt * sizeof(struct nat_entry);
-	mem_size >>= 12;
-
-	/* give 50:50 memory for free nids and nat caches respectively */
-	return (mem_size < ((val.totalram * nm_i->ram_thresh) >> 11));
+	/* give 25%, 25%, 50% memory for each components respectively */
+	if (type == FREE_NIDS) {
+		mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> 12;
+		res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+	} else if (type == NAT_ENTRIES) {
+		mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12;
+		res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+	} else if (type == DIRTY_DENTS) {
+		if (sbi->sb->s_bdi->dirty_exceeded)
+			return false;
+		mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
+		res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1);
+	}
+	return res;
 }
 
 static void clear_node_page_dirty(struct page *page)
@@ -147,6 +155,18 @@ bool fsync_mark_done(struct f2fs_sb_info *sbi, nid_t nid)
 	return fsync_done;
 }
 
+void fsync_mark_clear(struct f2fs_sb_info *sbi, nid_t nid)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct nat_entry *e;
+
+	write_lock(&nm_i->nat_tree_lock);
+	e = __lookup_nat_cache(nm_i, nid);
+	if (e)
+		e->fsync_done = false;
+	write_unlock(&nm_i->nat_tree_lock);
+}
+
 static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
 {
 	struct nat_entry *new;
@@ -179,9 +199,7 @@ retry:
 			write_unlock(&nm_i->nat_tree_lock);
 			goto retry;
 		}
-		nat_set_blkaddr(e, le32_to_cpu(ne->block_addr));
-		nat_set_ino(e, le32_to_cpu(ne->ino));
-		nat_set_version(e, ne->version);
+		node_info_from_raw_nat(&e->ni, ne);
 	}
 	write_unlock(&nm_i->nat_tree_lock);
 }
@@ -243,7 +261,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
-	if (available_free_memory(nm_i, NAT_ENTRIES))
+	if (available_free_memory(sbi, NAT_ENTRIES))
 		return 0;
 
 	write_lock(&nm_i->nat_tree_lock);
@@ -849,8 +867,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return ERR_PTR(-EPERM);
 
-	page = grab_cache_page_write_begin(NODE_MAPPING(sbi),
-					dn->nid, AOP_FLAG_NOFS);
+	page = grab_cache_page(NODE_MAPPING(sbi), dn->nid);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -867,6 +884,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	new_ni.ino = dn->inode->i_ino;
 	set_node_addr(sbi, &new_ni, NEW_ADDR, false);
 
+	f2fs_wait_on_page_writeback(page, NODE);
 	fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
 	set_cold_node(dn->inode, page);
 	SetPageUptodate(page);
@@ -946,8 +964,7 @@ struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
 	struct page *page;
 	int err;
 repeat:
-	page = grab_cache_page_write_begin(NODE_MAPPING(sbi),
-					nid, AOP_FLAG_NOFS);
+	page = grab_cache_page(NODE_MAPPING(sbi), nid);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
@@ -1194,6 +1211,8 @@ static int f2fs_write_node_page(struct page *page,
 		.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
 	};
 
+	trace_f2fs_writepage(page, NODE);
+
 	if (unlikely(sbi->por_doing))
 		goto redirty_out;
 
@@ -1225,10 +1244,7 @@ static int f2fs_write_node_page(struct page *page,
 	return 0;
 
 redirty_out:
-	dec_page_count(sbi, F2FS_DIRTY_NODES);
-	wbc->pages_skipped++;
-	account_page_redirty(page);
-	set_page_dirty(page);
+	redirty_page_for_writepage(wbc, page);
 	return AOP_WRITEPAGE_ACTIVATE;
 }
 
@@ -1238,6 +1254,8 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
 	long diff;
 
+	trace_f2fs_writepages(mapping->host, wbc, NODE);
+
 	/* balancing f2fs's metadata in background */
 	f2fs_balance_fs_bg(sbi);
 
@@ -1313,13 +1331,14 @@ static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i,
 	radix_tree_delete(&nm_i->free_nid_root, i->nid);
 }
 
-static int add_free_nid(struct f2fs_nm_info *nm_i, nid_t nid, bool build)
+static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i;
 	struct nat_entry *ne;
 	bool allocated = false;
 
-	if (!available_free_memory(nm_i, FREE_NIDS))
+	if (!available_free_memory(sbi, FREE_NIDS))
 		return -1;
 
 	/* 0 nid should not be used */
@@ -1372,9 +1391,10 @@ static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
 		kmem_cache_free(free_nid_slab, i);
 }
 
-static void scan_nat_page(struct f2fs_nm_info *nm_i,
+static void scan_nat_page(struct f2fs_sb_info *sbi,
 			struct page *nat_page, nid_t start_nid)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct f2fs_nat_block *nat_blk = page_address(nat_page);
 	block_t blk_addr;
 	int i;
@@ -1389,7 +1409,7 @@ static void scan_nat_page(struct f2fs_nm_info *nm_i,
 		blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
 		f2fs_bug_on(blk_addr == NEW_ADDR);
 		if (blk_addr == NULL_ADDR) {
-			if (add_free_nid(nm_i, start_nid, true) < 0)
+			if (add_free_nid(sbi, start_nid, true) < 0)
 				break;
 		}
 	}
@@ -1413,7 +1433,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 	while (1) {
 		struct page *page = get_current_nat_page(sbi, nid);
 
-		scan_nat_page(nm_i, page, nid);
+		scan_nat_page(sbi, page, nid);
 		f2fs_put_page(page, 1);
 
 		nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK));
@@ -1433,7 +1453,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 		block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr);
 		nid = le32_to_cpu(nid_in_journal(sum, i));
 		if (addr == NULL_ADDR)
-			add_free_nid(nm_i, nid, true);
+			add_free_nid(sbi, nid, true);
 		else
 			remove_free_nid(nm_i, nid);
 	}
@@ -1450,7 +1470,7 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct free_nid *i = NULL;
 retry:
-	if (unlikely(sbi->total_valid_node_count + 1 >= nm_i->max_nid))
+	if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
 		return false;
 
 	spin_lock(&nm_i->free_nid_list_lock);
@@ -1510,7 +1530,7 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
 	spin_lock(&nm_i->free_nid_list_lock);
 	i = __lookup_free_nid_list(nm_i, nid);
 	f2fs_bug_on(!i || i->state != NID_ALLOC);
-	if (!available_free_memory(nm_i, FREE_NIDS)) {
+	if (!available_free_memory(sbi, FREE_NIDS)) {
 		__del_from_free_nid_list(nm_i, i);
 		need_free = true;
 	} else {
@@ -1532,7 +1552,7 @@ void recover_node_page(struct f2fs_sb_info *sbi, struct page *page,
 	clear_node_page_dirty(page);
 }
 
-void recover_inline_xattr(struct inode *inode, struct page *page)
+static void recover_inline_xattr(struct inode *inode, struct page *page)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	void *src_addr, *dst_addr;
@@ -1557,6 +1577,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
 	src_addr = inline_xattr_addr(page);
 	inline_size = inline_xattr_size(inode);
 
+	f2fs_wait_on_page_writeback(ipage, NODE);
 	memcpy(dst_addr, src_addr, inline_size);
 
 	update_inode(inode, ipage);
@@ -1612,6 +1633,11 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	struct node_info old_ni, new_ni;
 	struct page *ipage;
 
+	get_node_info(sbi, ino, &old_ni);
+
+	if (unlikely(old_ni.blk_addr != NULL_ADDR))
+		return -EINVAL;
+
 	ipage = grab_cache_page(NODE_MAPPING(sbi), ino);
 	if (!ipage)
 		return -ENOMEM;
@@ -1619,7 +1645,6 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	/* Should not use this inode  from free nid list */
 	remove_free_nid(NM_I(sbi), ino);
 
-	get_node_info(sbi, ino, &old_ni);
 	SetPageUptodate(ipage);
 	fill_node_footer(ipage, ino, ino, 0, true);
 
@@ -1645,35 +1670,29 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 
 /*
  * ra_sum_pages() merge contiguous pages into one bio and submit.
- * these pre-readed pages are linked in pages list.
+ * these pre-readed pages are alloced in bd_inode's mapping tree.
  */
-static int ra_sum_pages(struct f2fs_sb_info *sbi, struct list_head *pages,
+static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages,
 				int start, int nrpages)
 {
-	struct page *page;
-	int page_idx = start;
+	struct inode *inode = sbi->sb->s_bdev->bd_inode;
+	struct address_space *mapping = inode->i_mapping;
+	int i, page_idx = start;
 	struct f2fs_io_info fio = {
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO
 	};
 
-	for (; page_idx < start + nrpages; page_idx++) {
-		/* alloc temporal page for read node summary info*/
-		page = alloc_page(GFP_F2FS_ZERO);
-		if (!page)
+	for (i = 0; page_idx < start + nrpages; page_idx++, i++) {
+		/* alloc page in bd_inode for reading node summary info */
+		pages[i] = grab_cache_page(mapping, page_idx);
+		if (!pages[i])
 			break;
-
-		lock_page(page);
-		page->index = page_idx;
-		list_add_tail(&page->lru, pages);
+		f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio);
 	}
 
-	list_for_each_entry(page, pages, lru)
-		f2fs_submit_page_mbio(sbi, page, page->index, &fio);
-
 	f2fs_submit_merged_bio(sbi, META, READ);
-
-	return page_idx - start;
+	return i;
 }
 
 int restore_node_summary(struct f2fs_sb_info *sbi,
@@ -1681,11 +1700,11 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
 {
 	struct f2fs_node *rn;
 	struct f2fs_summary *sum_entry;
-	struct page *page, *tmp;
+	struct inode *inode = sbi->sb->s_bdev->bd_inode;
 	block_t addr;
 	int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
-	int i, last_offset, nrpages, err = 0;
-	LIST_HEAD(page_list);
+	struct page *pages[bio_blocks];
+	int i, idx, last_offset, nrpages, err = 0;
 
 	/* scan the node segment */
 	last_offset = sbi->blocks_per_seg;
@@ -1696,29 +1715,31 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
 		nrpages = min(last_offset - i, bio_blocks);
 
 		/* read ahead node pages */
-		nrpages = ra_sum_pages(sbi, &page_list, addr, nrpages);
+		nrpages = ra_sum_pages(sbi, pages, addr, nrpages);
 		if (!nrpages)
 			return -ENOMEM;
 
-		list_for_each_entry_safe(page, tmp, &page_list, lru) {
+		for (idx = 0; idx < nrpages; idx++) {
 			if (err)
 				goto skip;
 
-			lock_page(page);
-			if (unlikely(!PageUptodate(page))) {
+			lock_page(pages[idx]);
+			if (unlikely(!PageUptodate(pages[idx]))) {
 				err = -EIO;
 			} else {
-				rn = F2FS_NODE(page);
+				rn = F2FS_NODE(pages[idx]);
 				sum_entry->nid = rn->footer.nid;
 				sum_entry->version = 0;
 				sum_entry->ofs_in_node = 0;
 				sum_entry++;
 			}
-			unlock_page(page);
+			unlock_page(pages[idx]);
 skip:
-			list_del(&page->lru);
-			__free_pages(page, 0);
+			page_cache_release(pages[idx]);
 		}
+
+		invalidate_mapping_pages(inode->i_mapping, addr,
+							addr + nrpages);
 	}
 	return err;
 }
@@ -1756,9 +1777,7 @@ retry:
 			write_unlock(&nm_i->nat_tree_lock);
 			goto retry;
 		}
-		nat_set_blkaddr(ne, le32_to_cpu(raw_ne.block_addr));
-		nat_set_ino(ne, le32_to_cpu(raw_ne.ino));
-		nat_set_version(ne, raw_ne.version);
+		node_info_from_raw_nat(&ne->ni, &raw_ne);
 		__set_nat_cache_dirty(nm_i, ne);
 		write_unlock(&nm_i->nat_tree_lock);
 	}
@@ -1791,7 +1810,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 		nid_t nid;
 		struct f2fs_nat_entry raw_ne;
 		int offset = -1;
-		block_t new_blkaddr;
 
 		if (nat_get_blkaddr(ne) == NEW_ADDR)
 			continue;
@@ -1827,11 +1845,7 @@ to_nat_page:
 		f2fs_bug_on(!nat_blk);
 		raw_ne = nat_blk->entries[nid - start_nid];
 flush_now:
-		new_blkaddr = nat_get_blkaddr(ne);
-
-		raw_ne.ino = cpu_to_le32(nat_get_ino(ne));
-		raw_ne.block_addr = cpu_to_le32(new_blkaddr);
-		raw_ne.version = nat_get_version(ne);
+		raw_nat_from_node_info(&raw_ne, &ne->ni);
 
 		if (offset < 0) {
 			nat_blk->entries[nid - start_nid] = raw_ne;
@@ -1841,7 +1855,7 @@ flush_now:
 		}
 
 		if (nat_get_blkaddr(ne) == NULL_ADDR &&
-				add_free_nid(NM_I(sbi), nid, false) <= 0) {
+				add_free_nid(sbi, nid, false) <= 0) {
 			write_lock(&nm_i->nat_tree_lock);
 			__del_from_nat_cache(nm_i, ne);
 			write_unlock(&nm_i->nat_tree_lock);
@@ -1869,8 +1883,10 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1;
 	nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
 
+	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
+
 	/* not used nids: 0, node, meta, (and root counted as valid node) */
-	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks - 3;
+	nm_i->available_nids = nm_i->max_nid - 3;
 	nm_i->fcnt = 0;
 	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 5decc1a375f..7281112cd1c 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -59,12 +59,12 @@ struct nat_entry {
 	do {								\
 		ne->checkpointed = false;				\
 		list_move_tail(&ne->list, &nm_i->dirty_nat_entries);	\
-	} while (0);
+	} while (0)
 #define __clear_nat_cache_dirty(nm_i, ne)				\
 	do {								\
 		ne->checkpointed = true;				\
 		list_move_tail(&ne->list, &nm_i->nat_entries);		\
-	} while (0);
+	} while (0)
 #define inc_node_version(version)	(++version)
 
 static inline void node_info_from_raw_nat(struct node_info *ni,
@@ -75,9 +75,18 @@ static inline void node_info_from_raw_nat(struct node_info *ni,
 	ni->version = raw_ne->version;
 }
 
-enum nid_type {
+static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
+						struct node_info *ni)
+{
+	raw_ne->ino = cpu_to_le32(ni->ino);
+	raw_ne->block_addr = cpu_to_le32(ni->blk_addr);
+	raw_ne->version = ni->version;
+}
+
+enum mem_type {
 	FREE_NIDS,	/* indicates the free nid list */
-	NAT_ENTRIES	/* indicates the cached nat entry */
+	NAT_ENTRIES,	/* indicates the cached nat entry */
+	DIRTY_DENTS	/* indicates dirty dentry pages */
 };
 
 /*
@@ -263,7 +272,7 @@ static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
 {
 	struct f2fs_node *rn = F2FS_NODE(p);
 
-	wait_on_page_writeback(p);
+	f2fs_wait_on_page_writeback(p, NODE);
 
 	if (i)
 		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index b1ae89f0f44..a112368a4a8 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -46,15 +46,10 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
 	struct inode *dir, *einode;
 	int err = 0;
 
-	dir = check_dirty_dir_inode(F2FS_SB(inode->i_sb), pino);
-	if (!dir) {
-		dir = f2fs_iget(inode->i_sb, pino);
-		if (IS_ERR(dir)) {
-			err = PTR_ERR(dir);
-			goto out;
-		}
-		set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
-		add_dirty_dir_inode(dir);
+	dir = f2fs_iget(inode->i_sb, pino);
+	if (IS_ERR(dir)) {
+		err = PTR_ERR(dir);
+		goto out;
 	}
 
 	name.len = le32_to_cpu(raw_inode->i_namelen);
@@ -63,7 +58,7 @@ static int recover_dentry(struct page *ipage, struct inode *inode)
 	if (unlikely(name.len > F2FS_NAME_LEN)) {
 		WARN_ON(1);
 		err = -ENAMETOOLONG;
-		goto out;
+		goto out_err;
 	}
 retry:
 	de = f2fs_find_entry(dir, &name, &page);
@@ -73,7 +68,8 @@ retry:
 		einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino));
 		if (IS_ERR(einode)) {
 			WARN_ON(1);
-			if (PTR_ERR(einode) == -ENOENT)
+			err = PTR_ERR(einode);
+			if (err == -ENOENT)
 				err = -EEXIST;
 			goto out_unmap_put;
 		}
@@ -87,11 +83,23 @@ retry:
 		goto retry;
 	}
 	err = __f2fs_add_link(dir, &name, inode);
+	if (err)
+		goto out_err;
+
+	if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
+		iput(dir);
+	} else {
+		add_dirty_dir_inode(dir);
+		set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
+	}
+
 	goto out;
 
 out_unmap_put:
 	kunmap(page);
 	f2fs_put_page(page, 0);
+out_err:
+	iput(dir);
 out:
 	f2fs_msg(inode->i_sb, KERN_NOTICE,
 			"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -299,10 +307,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 		goto out;
 
 	start = start_bidx_of_node(ofs_of_node(page), fi);
-	if (IS_INODE(page))
-		end = start + ADDRS_PER_INODE(fi);
-	else
-		end = start + ADDRS_PER_BLOCK;
+	end = start + ADDRS_PER_PAGE(page, fi);
 
 	f2fs_lock_op(sbi);
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 085f548be7a..d04613df710 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -25,7 +25,6 @@
 #define __reverse_ffz(x) __reverse_ffs(~(x))
 
 static struct kmem_cache *discard_entry_slab;
-static struct kmem_cache *flush_cmd_slab;
 
 /*
  * __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
@@ -200,20 +199,20 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 static int issue_flush_thread(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
-	struct f2fs_sm_info *sm_i = SM_I(sbi);
-	wait_queue_head_t *q = &sm_i->flush_wait_queue;
+	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	wait_queue_head_t *q = &fcc->flush_wait_queue;
 repeat:
 	if (kthread_should_stop())
 		return 0;
 
-	spin_lock(&sm_i->issue_lock);
-	if (sm_i->issue_list) {
-		sm_i->dispatch_list = sm_i->issue_list;
-		sm_i->issue_list = sm_i->issue_tail = NULL;
+	spin_lock(&fcc->issue_lock);
+	if (fcc->issue_list) {
+		fcc->dispatch_list = fcc->issue_list;
+		fcc->issue_list = fcc->issue_tail = NULL;
 	}
-	spin_unlock(&sm_i->issue_lock);
+	spin_unlock(&fcc->issue_lock);
 
-	if (sm_i->dispatch_list) {
+	if (fcc->dispatch_list) {
 		struct bio *bio = bio_alloc(GFP_NOIO, 0);
 		struct flush_cmd *cmd, *next;
 		int ret;
@@ -221,47 +220,80 @@ repeat:
 		bio->bi_bdev = sbi->sb->s_bdev;
 		ret = submit_bio_wait(WRITE_FLUSH, bio);
 
-		for (cmd = sm_i->dispatch_list; cmd; cmd = next) {
+		for (cmd = fcc->dispatch_list; cmd; cmd = next) {
 			cmd->ret = ret;
 			next = cmd->next;
 			complete(&cmd->wait);
 		}
-		sm_i->dispatch_list = NULL;
+		bio_put(bio);
+		fcc->dispatch_list = NULL;
 	}
 
-	wait_event_interruptible(*q, kthread_should_stop() || sm_i->issue_list);
+	wait_event_interruptible(*q,
+			kthread_should_stop() || fcc->issue_list);
 	goto repeat;
 }
 
 int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 {
-	struct f2fs_sm_info *sm_i = SM_I(sbi);
-	struct flush_cmd *cmd;
-	int ret;
+	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	struct flush_cmd cmd;
 
 	if (!test_opt(sbi, FLUSH_MERGE))
 		return blkdev_issue_flush(sbi->sb->s_bdev, GFP_KERNEL, NULL);
 
-	cmd = f2fs_kmem_cache_alloc(flush_cmd_slab, GFP_ATOMIC);
-	cmd->next = NULL;
-	cmd->ret = 0;
-	init_completion(&cmd->wait);
+	init_completion(&cmd.wait);
+	cmd.next = NULL;
 
-	spin_lock(&sm_i->issue_lock);
-	if (sm_i->issue_list)
-		sm_i->issue_tail->next = cmd;
+	spin_lock(&fcc->issue_lock);
+	if (fcc->issue_list)
+		fcc->issue_tail->next = &cmd;
 	else
-		sm_i->issue_list = cmd;
-	sm_i->issue_tail = cmd;
-	spin_unlock(&sm_i->issue_lock);
+		fcc->issue_list = &cmd;
+	fcc->issue_tail = &cmd;
+	spin_unlock(&fcc->issue_lock);
 
-	if (!sm_i->dispatch_list)
-		wake_up(&sm_i->flush_wait_queue);
+	if (!fcc->dispatch_list)
+		wake_up(&fcc->flush_wait_queue);
 
-	wait_for_completion(&cmd->wait);
-	ret = cmd->ret;
-	kmem_cache_free(flush_cmd_slab, cmd);
-	return ret;
+	wait_for_completion(&cmd.wait);
+
+	return cmd.ret;
+}
+
+int create_flush_cmd_control(struct f2fs_sb_info *sbi)
+{
+	dev_t dev = sbi->sb->s_bdev->bd_dev;
+	struct flush_cmd_control *fcc;
+	int err = 0;
+
+	fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
+	if (!fcc)
+		return -ENOMEM;
+	spin_lock_init(&fcc->issue_lock);
+	init_waitqueue_head(&fcc->flush_wait_queue);
+	sbi->sm_info->cmd_control_info = fcc;
+	fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
+				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
+	if (IS_ERR(fcc->f2fs_issue_flush)) {
+		err = PTR_ERR(fcc->f2fs_issue_flush);
+		kfree(fcc);
+		sbi->sm_info->cmd_control_info = NULL;
+		return err;
+	}
+
+	return err;
+}
+
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi)
+{
+	struct flush_cmd_control *fcc =
+				sbi->sm_info->cmd_control_info;
+
+	if (fcc && fcc->f2fs_issue_flush)
+		kthread_stop(fcc->f2fs_issue_flush);
+	kfree(fcc);
+	sbi->sm_info->cmd_control_info = NULL;
 }
 
 static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
@@ -336,13 +368,26 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
-static void f2fs_issue_discard(struct f2fs_sb_info *sbi,
+static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 				block_t blkstart, block_t blklen)
 {
 	sector_t start = SECTOR_FROM_BLOCK(sbi, blkstart);
 	sector_t len = SECTOR_FROM_BLOCK(sbi, blklen);
-	blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
 	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
+	return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
+}
+
+void discard_next_dnode(struct f2fs_sb_info *sbi)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
+	block_t blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+
+	if (f2fs_issue_discard(sbi, blkaddr, 1)) {
+		struct page *page = grab_meta_page(sbi, blkaddr);
+		/* zero-filled page */
+		set_page_dirty(page);
+		f2fs_put_page(page, 1);
+	}
 }
 
 static void add_discard_addrs(struct f2fs_sb_info *sbi,
@@ -1832,7 +1877,6 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	dev_t dev = sbi->sb->s_bdev->bd_dev;
 	struct f2fs_sm_info *sm_info;
 	int err;
 
@@ -1842,8 +1886,6 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 
 	/* init sm info */
 	sbi->sm_info = sm_info;
-	INIT_LIST_HEAD(&sm_info->wblist_head);
-	spin_lock_init(&sm_info->wblist_lock);
 	sm_info->seg0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
 	sm_info->main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
 	sm_info->segment_count = le32_to_cpu(raw_super->segment_count);
@@ -1860,14 +1902,10 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->nr_discards = 0;
 	sm_info->max_discards = 0;
 
-	if (test_opt(sbi, FLUSH_MERGE)) {
-		spin_lock_init(&sm_info->issue_lock);
-		init_waitqueue_head(&sm_info->flush_wait_queue);
-
-		sm_info->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
-				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
-		if (IS_ERR(sm_info->f2fs_issue_flush))
-			return PTR_ERR(sm_info->f2fs_issue_flush);
+	if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
+		err = create_flush_cmd_control(sbi);
+		if (err)
+			return err;
 	}
 
 	err = build_sit_info(sbi);
@@ -1976,10 +2014,10 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 void destroy_segment_manager(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_sm_info *sm_info = SM_I(sbi);
+
 	if (!sm_info)
 		return;
-	if (sm_info->f2fs_issue_flush)
-		kthread_stop(sm_info->f2fs_issue_flush);
+	destroy_flush_cmd_control(sbi);
 	destroy_dirty_segmap(sbi);
 	destroy_curseg(sbi);
 	destroy_free_segmap(sbi);
@@ -1994,17 +2032,10 @@ int __init create_segment_manager_caches(void)
 			sizeof(struct discard_entry));
 	if (!discard_entry_slab)
 		return -ENOMEM;
-	flush_cmd_slab = f2fs_kmem_cache_create("flush_command",
-			sizeof(struct flush_cmd));
-	if (!flush_cmd_slab) {
-		kmem_cache_destroy(discard_entry_slab);
-		return -ENOMEM;
-	}
 	return 0;
 }
 
 void destroy_segment_manager_caches(void)
 {
 	kmem_cache_destroy(discard_entry_slab);
-	kmem_cache_destroy(flush_cmd_slab);
 }
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index c756923a730..8f96d9372ad 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -514,7 +514,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
 
-	if (!(root->d_sb->s_flags & MS_RDONLY) && test_opt(sbi, BG_GC))
+	if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC))
 		seq_printf(seq, ",background_gc=%s", "on");
 	else
 		seq_printf(seq, ",background_gc=%s", "off");
@@ -542,7 +542,7 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",disable_ext_identify");
 	if (test_opt(sbi, INLINE_DATA))
 		seq_puts(seq, ",inline_data");
-	if (test_opt(sbi, FLUSH_MERGE))
+	if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE))
 		seq_puts(seq, ",flush_merge");
 	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
 
@@ -594,6 +594,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct f2fs_mount_info org_mount_opt;
 	int err, active_logs;
+	bool need_restart_gc = false;
+	bool need_stop_gc = false;
 
 	sync_filesystem(sb);
 
@@ -611,7 +613,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 
 	/*
 	 * Previous and new state of filesystem is RO,
-	 * so no point in checking GC conditions.
+	 * so skip checking GC and FLUSH_MERGE conditions.
 	 */
 	if ((sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY))
 		goto skip;
@@ -625,18 +627,40 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 		if (sbi->gc_thread) {
 			stop_gc_thread(sbi);
 			f2fs_sync_fs(sb, 1);
+			need_restart_gc = true;
 		}
 	} else if (test_opt(sbi, BG_GC) && !sbi->gc_thread) {
 		err = start_gc_thread(sbi);
 		if (err)
 			goto restore_opts;
+		need_stop_gc = true;
+	}
+
+	/*
+	 * We stop issue flush thread if FS is mounted as RO
+	 * or if flush_merge is not passed in mount option.
+	 */
+	if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
+		destroy_flush_cmd_control(sbi);
+	} else if (test_opt(sbi, FLUSH_MERGE) &&
+					!sbi->sm_info->cmd_control_info) {
+		err = create_flush_cmd_control(sbi);
+		if (err)
+			goto restore_gc;
 	}
 skip:
 	/* Update the POSIXACL Flag */
 	 sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
 	return 0;
-
+restore_gc:
+	if (need_restart_gc) {
+		if (start_gc_thread(sbi))
+			f2fs_msg(sbi->sb, KERN_WARNING,
+				"background gc thread is stop");
+	} else if (need_stop_gc) {
+		stop_gc_thread(sbi);
+	}
 restore_opts:
 	sbi->mount_opt = org_mount_opt;
 	sbi->active_logs = active_logs;
@@ -665,9 +689,7 @@ static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct inode *inode;
 
-	if (unlikely(ino < F2FS_ROOT_INO(sbi)))
-		return ERR_PTR(-ESTALE);
-	if (unlikely(ino >= NM_I(sbi)->max_nid))
+	if (check_nid_range(sbi, ino))
 		return ERR_PTR(-ESTALE);
 
 	/*
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 503c2451131..8bea941ee30 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -26,7 +26,7 @@
 #include "xattr.h"
 
 static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
+		size_t list_size, const char *name, size_t len, int type)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
 	int total_len, prefix_len = 0;
@@ -53,11 +53,11 @@ static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
 		return -EINVAL;
 	}
 
-	total_len = prefix_len + name_len + 1;
+	total_len = prefix_len + len + 1;
 	if (list && total_len <= list_size) {
 		memcpy(list, prefix, prefix_len);
-		memcpy(list + prefix_len, name, name_len);
-		list[prefix_len + name_len] = '\0';
+		memcpy(list + prefix_len, name, len);
+		list[prefix_len + len] = '\0';
 	}
 	return total_len;
 }
@@ -108,11 +108,12 @@ static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
 
-	return f2fs_setxattr(dentry->d_inode, type, name, value, size, NULL);
+	return f2fs_setxattr(dentry->d_inode, type, name,
+					value, size, NULL, flags);
 }
 
 static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list,
-		size_t list_size, const char *name, size_t name_len, int type)
+		size_t list_size, const char *name, size_t len, int type)
 {
 	const char *xname = F2FS_SYSTEM_ADVISE_PREFIX;
 	size_t size;
@@ -155,9 +156,6 @@ static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name,
 }
 
 #ifdef CONFIG_F2FS_FS_SECURITY
-static int __f2fs_setxattr(struct inode *inode, int name_index,
-			const char *name, const void *value, size_t value_len,
-			struct page *ipage);
 static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 		void *page)
 {
@@ -165,9 +163,9 @@ static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 	int err = 0;
 
 	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
-		err = __f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY,
+		err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY,
 				xattr->name, xattr->value,
-				xattr->value_len, (struct page *)page);
+				xattr->value_len, (struct page *)page, 0);
 		if (err < 0)
 			break;
 	}
@@ -241,26 +239,26 @@ const struct xattr_handler *f2fs_xattr_handlers[] = {
 	NULL,
 };
 
-static inline const struct xattr_handler *f2fs_xattr_handler(int name_index)
+static inline const struct xattr_handler *f2fs_xattr_handler(int index)
 {
 	const struct xattr_handler *handler = NULL;
 
-	if (name_index > 0 && name_index < ARRAY_SIZE(f2fs_xattr_handler_map))
-		handler = f2fs_xattr_handler_map[name_index];
+	if (index > 0 && index < ARRAY_SIZE(f2fs_xattr_handler_map))
+		handler = f2fs_xattr_handler_map[index];
 	return handler;
 }
 
-static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int name_index,
-					size_t name_len, const char *name)
+static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index,
+					size_t len, const char *name)
 {
 	struct f2fs_xattr_entry *entry;
 
 	list_for_each_xattr(entry, base_addr) {
-		if (entry->e_name_index != name_index)
+		if (entry->e_name_index != index)
 			continue;
-		if (entry->e_name_len != name_len)
+		if (entry->e_name_len != len)
 			continue;
-		if (!memcmp(entry->e_name, name, name_len))
+		if (!memcmp(entry->e_name, name, len))
 			break;
 	}
 	return entry;
@@ -347,6 +345,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 
 		if (ipage) {
 			inline_addr = inline_xattr_addr(ipage);
+			f2fs_wait_on_page_writeback(ipage, NODE);
 		} else {
 			page = get_node_page(sbi, inode->i_ino);
 			if (IS_ERR(page)) {
@@ -354,6 +353,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 				return PTR_ERR(page);
 			}
 			inline_addr = inline_xattr_addr(page);
+			f2fs_wait_on_page_writeback(page, NODE);
 		}
 		memcpy(inline_addr, txattr_addr, inline_size);
 		f2fs_put_page(page, 1);
@@ -374,6 +374,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 			return PTR_ERR(xpage);
 		}
 		f2fs_bug_on(new_nid);
+		f2fs_wait_on_page_writeback(xpage, NODE);
 	} else {
 		struct dnode_of_data dn;
 		set_new_dnode(&dn, inode, NULL, NULL, new_nid);
@@ -396,42 +397,43 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 	return 0;
 }
 
-int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
+int f2fs_getxattr(struct inode *inode, int index, const char *name,
 		void *buffer, size_t buffer_size)
 {
 	struct f2fs_xattr_entry *entry;
 	void *base_addr;
 	int error = 0;
-	size_t value_len, name_len;
+	size_t size, len;
 
 	if (name == NULL)
 		return -EINVAL;
-	name_len = strlen(name);
-	if (name_len > F2FS_NAME_LEN)
+
+	len = strlen(name);
+	if (len > F2FS_NAME_LEN)
 		return -ERANGE;
 
 	base_addr = read_all_xattrs(inode, NULL);
 	if (!base_addr)
 		return -ENOMEM;
 
-	entry = __find_xattr(base_addr, name_index, name_len, name);
+	entry = __find_xattr(base_addr, index, len, name);
 	if (IS_XATTR_LAST_ENTRY(entry)) {
 		error = -ENODATA;
 		goto cleanup;
 	}
 
-	value_len = le16_to_cpu(entry->e_value_size);
+	size = le16_to_cpu(entry->e_value_size);
 
-	if (buffer && value_len > buffer_size) {
+	if (buffer && size > buffer_size) {
 		error = -ERANGE;
 		goto cleanup;
 	}
 
 	if (buffer) {
 		char *pval = entry->e_name + entry->e_name_len;
-		memcpy(buffer, pval, value_len);
+		memcpy(buffer, pval, size);
 	}
-	error = value_len;
+	error = size;
 
 cleanup:
 	kzfree(base_addr);
@@ -475,15 +477,15 @@ cleanup:
 	return error;
 }
 
-static int __f2fs_setxattr(struct inode *inode, int name_index,
-			const char *name, const void *value, size_t value_len,
-			struct page *ipage)
+static int __f2fs_setxattr(struct inode *inode, int index,
+			const char *name, const void *value, size_t size,
+			struct page *ipage, int flags)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_xattr_entry *here, *last;
 	void *base_addr;
 	int found, newsize;
-	size_t name_len;
+	size_t len;
 	__u32 new_hsize;
 	int error = -ENOMEM;
 
@@ -491,11 +493,11 @@ static int __f2fs_setxattr(struct inode *inode, int name_index,
 		return -EINVAL;
 
 	if (value == NULL)
-		value_len = 0;
+		size = 0;
 
-	name_len = strlen(name);
+	len = strlen(name);
 
-	if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN(inode))
+	if (len > F2FS_NAME_LEN || size > MAX_VALUE_LEN(inode))
 		return -ERANGE;
 
 	base_addr = read_all_xattrs(inode, ipage);
@@ -503,16 +505,23 @@ static int __f2fs_setxattr(struct inode *inode, int name_index,
 		goto exit;
 
 	/* find entry with wanted name. */
-	here = __find_xattr(base_addr, name_index, name_len, name);
+	here = __find_xattr(base_addr, index, len, name);
 
 	found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
-	last = here;
 
+	if ((flags & XATTR_REPLACE) && !found) {
+		error = -ENODATA;
+		goto exit;
+	} else if ((flags & XATTR_CREATE) && found) {
+		error = -EEXIST;
+		goto exit;
+	}
+
+	last = here;
 	while (!IS_XATTR_LAST_ENTRY(last))
 		last = XATTR_NEXT_ENTRY(last);
 
-	newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) +
-			name_len + value_len);
+	newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + len + size);
 
 	/* 1. Check space */
 	if (value) {
@@ -555,12 +564,12 @@ static int __f2fs_setxattr(struct inode *inode, int name_index,
 		 * We just write new entry.
 		 */
 		memset(last, 0, newsize);
-		last->e_name_index = name_index;
-		last->e_name_len = name_len;
-		memcpy(last->e_name, name, name_len);
-		pval = last->e_name + name_len;
-		memcpy(pval, value, value_len);
-		last->e_value_size = cpu_to_le16(value_len);
+		last->e_name_index = index;
+		last->e_name_len = len;
+		memcpy(last->e_name, name, len);
+		pval = last->e_name + len;
+		memcpy(pval, value, size);
+		last->e_value_size = cpu_to_le16(size);
 		new_hsize += newsize;
 	}
 
@@ -583,18 +592,23 @@ exit:
 	return error;
 }
 
-int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
-			const void *value, size_t value_len, struct page *ipage)
+int f2fs_setxattr(struct inode *inode, int index, const char *name,
+				const void *value, size_t size,
+				struct page *ipage, int flags)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 	int err;
 
+	/* this case is only from init_inode_metadata */
+	if (ipage)
+		return __f2fs_setxattr(inode, index, name, value,
+						size, ipage, flags);
 	f2fs_balance_fs(sbi);
 
 	f2fs_lock_op(sbi);
 	/* protect xattr_ver */
 	down_write(&F2FS_I(inode)->i_sem);
-	err = __f2fs_setxattr(inode, name_index, name, value, value_len, ipage);
+	err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags);
 	up_write(&F2FS_I(inode)->i_sem);
 	f2fs_unlock_op(sbi);
 
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index b21d9ebdeff..34ab7dbcf5e 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -114,18 +114,18 @@ extern const struct xattr_handler f2fs_xattr_security_handler;
 extern const struct xattr_handler *f2fs_xattr_handlers[];
 
 extern int f2fs_setxattr(struct inode *, int, const char *,
-				const void *, size_t, struct page *);
+				const void *, size_t, struct page *, int);
 extern int f2fs_getxattr(struct inode *, int, const char *, void *, size_t);
 extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
 #else
 
 #define f2fs_xattr_handlers	NULL
-static inline int f2fs_setxattr(struct inode *inode, int name_index,
-		const char *name, const void *value, size_t value_len)
+static inline int f2fs_setxattr(struct inode *inode, int index,
+		const char *name, const void *value, size_t size, int flags)
 {
 	return -EOPNOTSUPP;
 }
-static inline int f2fs_getxattr(struct inode *inode, int name_index,
+static inline int f2fs_getxattr(struct inode *inode, int index,
 		const char *name, void *buffer, size_t buffer_size)
 {
 	return -EOPNOTSUPP;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 9b104f54305..85f79a89e74 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -170,10 +170,10 @@ int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 
 const struct file_operations fat_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.release	= fat_file_release,
 	.unlocked_ioctl	= fat_generic_ioctl,
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 9c83594d7fb..756aead10d9 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -247,12 +247,13 @@ static int fat_write_end(struct file *file, struct address_space *mapping,
 }
 
 static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
-			     const struct iovec *iov,
-			     loff_t offset, unsigned long nr_segs)
+			     struct iov_iter *iter,
+			     loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
 	if (rw == WRITE) {
@@ -265,7 +266,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 		 *
 		 * Return 0, and fallback to normal buffered write.
 		 */
-		loff_t size = offset + iov_length(iov, nr_segs);
+		loff_t size = offset + count;
 		if (MSDOS_I(inode)->mmu_private < size)
 			return 0;
 	}
@@ -274,10 +275,9 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 	 * FAT need to use the DIO_LOCKING for avoiding the race
 	 * condition of fat_get_block() and ->truncate().
 	 */
-	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
-				 fat_get_block);
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, fat_get_block);
 	if (ret < 0 && (rw & WRITE))
-		fat_write_failed(mapping, offset + iov_length(iov, nr_segs));
+		fat_write_failed(mapping, offset + count);
 
 	return ret;
 }
diff --git a/fs/file.c b/fs/file.c
index 8f294cfac69..66923fe3176 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -44,15 +44,10 @@ static void *alloc_fdmem(size_t size)
 	return vmalloc(size);
 }
 
-static void free_fdmem(void *ptr)
-{
-	is_vmalloc_addr(ptr) ? vfree(ptr) : kfree(ptr);
-}
-
 static void __free_fdtable(struct fdtable *fdt)
 {
-	free_fdmem(fdt->fd);
-	free_fdmem(fdt->open_fds);
+	kvfree(fdt->fd);
+	kvfree(fdt->open_fds);
 	kfree(fdt);
 }
 
@@ -130,7 +125,7 @@ static struct fdtable * alloc_fdtable(unsigned int nr)
 	return fdt;
 
 out_arr:
-	free_fdmem(fdt->fd);
+	kvfree(fdt->fd);
 out_fdt:
 	kfree(fdt);
 out:
diff --git a/fs/file_table.c b/fs/file_table.c
index 40bf4660f0a..385bfd31512 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -175,6 +175,12 @@ struct file *alloc_file(struct path *path, fmode_t mode,
 	file->f_path = *path;
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
+	if ((mode & FMODE_READ) &&
+	     likely(fop->read || fop->aio_read || fop->read_iter))
+		mode |= FMODE_CAN_READ;
+	if ((mode & FMODE_WRITE) &&
+	     likely(fop->write || fop->aio_write || fop->write_iter))
+		mode |= FMODE_CAN_WRITE;
 	file->f_mode = mode;
 	file->f_op = fop;
 	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index be568b7311d..ef9bef11834 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -342,7 +342,8 @@ static void __inode_wait_for_writeback(struct inode *inode)
 	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
 	while (inode->i_state & I_SYNC) {
 		spin_unlock(&inode->i_lock);
-		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
+		__wait_on_bit(wqh, &wq, bit_wait,
+			      TASK_UNINTERRUPTIBLE);
 		spin_lock(&inode->i_lock);
 	}
 }
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index aec01be91b0..89acec742e0 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -160,7 +160,7 @@ void __fscache_enable_cookie(struct fscache_cookie *cookie,
 	_enter("%p", cookie);
 
 	wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK,
-			 fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			 TASK_UNINTERRUPTIBLE);
 
 	if (test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags))
 		goto out_unlock;
@@ -255,7 +255,7 @@ static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie)
 	if (!fscache_defer_lookup) {
 		_debug("non-deferred lookup %p", &cookie->flags);
 		wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP,
-			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			    TASK_UNINTERRUPTIBLE);
 		_debug("complete");
 		if (test_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags))
 			goto unavailable;
@@ -463,7 +463,6 @@ void __fscache_wait_on_invalidate(struct fscache_cookie *cookie)
 	_enter("%p", cookie);
 
 	wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING,
-		    fscache_wait_bit_interruptible,
 		    TASK_UNINTERRUPTIBLE);
 
 	_leave("");
@@ -525,7 +524,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
 	}
 
 	wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK,
-			 fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			 TASK_UNINTERRUPTIBLE);
 	if (!test_and_clear_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags))
 		goto out_unlock_enable;
 
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index bc6c08fcfdd..7872a62ef30 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -97,8 +97,6 @@ static inline bool fscache_object_congested(void)
 	return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq);
 }
 
-extern int fscache_wait_bit(void *);
-extern int fscache_wait_bit_interruptible(void *);
 extern int fscache_wait_atomic_t(atomic_t *);
 
 /*
diff --git a/fs/fscache/main.c b/fs/fscache/main.c
index 63f868e869b..a31b83c5cbd 100644
--- a/fs/fscache/main.c
+++ b/fs/fscache/main.c
@@ -197,24 +197,6 @@ static void __exit fscache_exit(void)
 module_exit(fscache_exit);
 
 /*
- * wait_on_bit() sleep function for uninterruptible waiting
- */
-int fscache_wait_bit(void *flags)
-{
-	schedule();
-	return 0;
-}
-
-/*
- * wait_on_bit() sleep function for interruptible waiting
- */
-int fscache_wait_bit_interruptible(void *flags)
-{
-	schedule();
-	return signal_pending(current);
-}
-
-/*
  * wait_on_atomic_t() sleep function for uninterruptible waiting
  */
 int fscache_wait_atomic_t(atomic_t *p)
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index ed70714503f..85332b9d19d 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -298,7 +298,6 @@ int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
 
 	jif = jiffies;
 	if (wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP,
-			fscache_wait_bit_interruptible,
 			TASK_INTERRUPTIBLE) != 0) {
 		fscache_stat(&fscache_n_retrievals_intr);
 		_leave(" = -ERESTARTSYS");
@@ -342,7 +341,6 @@ int fscache_wait_for_operation_activation(struct fscache_object *object,
 	if (stat_op_waits)
 		fscache_stat(stat_op_waits);
 	if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
-			fscache_wait_bit_interruptible,
 			TASK_INTERRUPTIBLE) != 0) {
 		ret = fscache_cancel_op(op, do_cancel);
 		if (ret == 0)
@@ -351,7 +349,7 @@ int fscache_wait_for_operation_activation(struct fscache_object *object,
 		/* it's been removed from the pending queue by another party,
 		 * so we should get to run shortly */
 		wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
-			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			    TASK_UNINTERRUPTIBLE);
 	}
 	_debug("<<< GO");
 
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 13b691a8a7d..966ace8b243 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -94,8 +94,10 @@ static ssize_t cuse_read(struct file *file, char __user *buf, size_t count,
 	loff_t pos = 0;
 	struct iovec iov = { .iov_base = buf, .iov_len = count };
 	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct iov_iter ii;
+	iov_iter_init(&ii, READ, &iov, 1, count);
 
-	return fuse_direct_io(&io, &iov, 1, count, &pos, FUSE_DIO_CUSE);
+	return fuse_direct_io(&io, &ii, &pos, FUSE_DIO_CUSE);
 }
 
 static ssize_t cuse_write(struct file *file, const char __user *buf,
@@ -104,12 +106,14 @@ static ssize_t cuse_write(struct file *file, const char __user *buf,
 	loff_t pos = 0;
 	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count };
 	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct iov_iter ii;
+	iov_iter_init(&ii, WRITE, &iov, 1, count);
 
 	/*
 	 * No locking or generic_write_checks(), the server is
 	 * responsible for locking and sanity checks.
 	 */
-	return fuse_direct_io(&io, &iov, 1, count, &pos,
+	return fuse_direct_io(&io, &ii, &pos,
 			      FUSE_DIO_WRITE | FUSE_DIO_CUSE);
 }
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 098f97bdcf1..ca887314aba 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -643,9 +643,8 @@ struct fuse_copy_state {
 	unsigned long seglen;
 	unsigned long addr;
 	struct page *pg;
-	void *mapaddr;
-	void *buf;
 	unsigned len;
+	unsigned offset;
 	unsigned move_pages:1;
 };
 
@@ -666,23 +665,17 @@ static void fuse_copy_finish(struct fuse_copy_state *cs)
 	if (cs->currbuf) {
 		struct pipe_buffer *buf = cs->currbuf;
 
-		if (!cs->write) {
-			kunmap_atomic(cs->mapaddr);
-		} else {
-			kunmap_atomic(cs->mapaddr);
+		if (cs->write)
 			buf->len = PAGE_SIZE - cs->len;
-		}
 		cs->currbuf = NULL;
-		cs->mapaddr = NULL;
-	} else if (cs->mapaddr) {
-		kunmap_atomic(cs->mapaddr);
+	} else if (cs->pg) {
 		if (cs->write) {
 			flush_dcache_page(cs->pg);
 			set_page_dirty_lock(cs->pg);
 		}
 		put_page(cs->pg);
-		cs->mapaddr = NULL;
 	}
+	cs->pg = NULL;
 }
 
 /*
@@ -691,7 +684,7 @@ static void fuse_copy_finish(struct fuse_copy_state *cs)
  */
 static int fuse_copy_fill(struct fuse_copy_state *cs)
 {
-	unsigned long offset;
+	struct page *page;
 	int err;
 
 	unlock_request(cs->fc, cs->req);
@@ -706,14 +699,12 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 
 			BUG_ON(!cs->nr_segs);
 			cs->currbuf = buf;
-			cs->mapaddr = kmap_atomic(buf->page);
+			cs->pg = buf->page;
+			cs->offset = buf->offset;
 			cs->len = buf->len;
-			cs->buf = cs->mapaddr + buf->offset;
 			cs->pipebufs++;
 			cs->nr_segs--;
 		} else {
-			struct page *page;
-
 			if (cs->nr_segs == cs->pipe->buffers)
 				return -EIO;
 
@@ -726,8 +717,8 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 			buf->len = 0;
 
 			cs->currbuf = buf;
-			cs->mapaddr = kmap_atomic(page);
-			cs->buf = cs->mapaddr;
+			cs->pg = page;
+			cs->offset = 0;
 			cs->len = PAGE_SIZE;
 			cs->pipebufs++;
 			cs->nr_segs++;
@@ -740,14 +731,13 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 			cs->iov++;
 			cs->nr_segs--;
 		}
-		err = get_user_pages_fast(cs->addr, 1, cs->write, &cs->pg);
+		err = get_user_pages_fast(cs->addr, 1, cs->write, &page);
 		if (err < 0)
 			return err;
 		BUG_ON(err != 1);
-		offset = cs->addr % PAGE_SIZE;
-		cs->mapaddr = kmap_atomic(cs->pg);
-		cs->buf = cs->mapaddr + offset;
-		cs->len = min(PAGE_SIZE - offset, cs->seglen);
+		cs->pg = page;
+		cs->offset = cs->addr % PAGE_SIZE;
+		cs->len = min(PAGE_SIZE - cs->offset, cs->seglen);
 		cs->seglen -= cs->len;
 		cs->addr += cs->len;
 	}
@@ -760,15 +750,20 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size)
 {
 	unsigned ncpy = min(*size, cs->len);
 	if (val) {
+		void *pgaddr = kmap_atomic(cs->pg);
+		void *buf = pgaddr + cs->offset;
+
 		if (cs->write)
-			memcpy(cs->buf, *val, ncpy);
+			memcpy(buf, *val, ncpy);
 		else
-			memcpy(*val, cs->buf, ncpy);
+			memcpy(*val, buf, ncpy);
+
+		kunmap_atomic(pgaddr);
 		*val += ncpy;
 	}
 	*size -= ncpy;
 	cs->len -= ncpy;
-	cs->buf += ncpy;
+	cs->offset += ncpy;
 	return ncpy;
 }
 
@@ -874,8 +869,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 out_fallback_unlock:
 	unlock_page(newpage);
 out_fallback:
-	cs->mapaddr = kmap_atomic(buf->page);
-	cs->buf = cs->mapaddr + buf->offset;
+	cs->pg = buf->page;
+	cs->offset = buf->offset;
 
 	err = lock_request(cs->fc, cs->req);
 	if (err)
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 42198359fa1..0c6048247a3 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -198,7 +198,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
 	inode = ACCESS_ONCE(entry->d_inode);
 	if (inode && is_bad_inode(inode))
 		goto invalid;
-	else if (fuse_dentry_time(entry) < get_jiffies_64()) {
+	else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) ||
+		 (flags & LOOKUP_REVAL)) {
 		int err;
 		struct fuse_entry_out outarg;
 		struct fuse_req *req;
@@ -814,13 +815,6 @@ static int fuse_rename_common(struct inode *olddir, struct dentry *oldent,
 	return err;
 }
 
-static int fuse_rename(struct inode *olddir, struct dentry *oldent,
-		       struct inode *newdir, struct dentry *newent)
-{
-	return fuse_rename_common(olddir, oldent, newdir, newent, 0,
-				  FUSE_RENAME, sizeof(struct fuse_rename_in));
-}
-
 static int fuse_rename2(struct inode *olddir, struct dentry *oldent,
 			struct inode *newdir, struct dentry *newent,
 			unsigned int flags)
@@ -831,17 +825,30 @@ static int fuse_rename2(struct inode *olddir, struct dentry *oldent,
 	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
 		return -EINVAL;
 
-	if (fc->no_rename2 || fc->minor < 23)
-		return -EINVAL;
+	if (flags) {
+		if (fc->no_rename2 || fc->minor < 23)
+			return -EINVAL;
 
-	err = fuse_rename_common(olddir, oldent, newdir, newent, flags,
-				 FUSE_RENAME2, sizeof(struct fuse_rename2_in));
-	if (err == -ENOSYS) {
-		fc->no_rename2 = 1;
-		err = -EINVAL;
+		err = fuse_rename_common(olddir, oldent, newdir, newent, flags,
+					 FUSE_RENAME2,
+					 sizeof(struct fuse_rename2_in));
+		if (err == -ENOSYS) {
+			fc->no_rename2 = 1;
+			err = -EINVAL;
+		}
+	} else {
+		err = fuse_rename_common(olddir, oldent, newdir, newent, 0,
+					 FUSE_RENAME,
+					 sizeof(struct fuse_rename_in));
 	}
+
 	return err;
+}
 
+static int fuse_rename(struct inode *olddir, struct dentry *oldent,
+		       struct inode *newdir, struct dentry *newent)
+{
+	return fuse_rename2(olddir, oldent, newdir, newent, 0);
 }
 
 static int fuse_link(struct dentry *entry, struct inode *newdir,
@@ -985,7 +992,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat,
 	int err;
 	bool r;
 
-	if (fi->i_time < get_jiffies_64()) {
+	if (time_before64(fi->i_time, get_jiffies_64())) {
 		r = true;
 		err = fuse_do_getattr(inode, stat, file);
 	} else {
@@ -1171,7 +1178,7 @@ static int fuse_permission(struct inode *inode, int mask)
 	    ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
 		struct fuse_inode *fi = get_fuse_inode(inode);
 
-		if (fi->i_time < get_jiffies_64()) {
+		if (time_before64(fi->i_time, get_jiffies_64())) {
 			refreshed = true;
 
 			err = fuse_perm_getattr(inode, mask);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 903cbc9cd6b..40ac2628ddc 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -933,8 +933,7 @@ out:
 	return err;
 }
 
-static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-				  unsigned long nr_segs, loff_t pos)
+static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	struct fuse_conn *fc = get_fuse_conn(inode);
@@ -945,14 +944,14 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 	 * i_size is up to date).
 	 */
 	if (fc->auto_inval_data ||
-	    (pos + iov_length(iov, nr_segs) > i_size_read(inode))) {
+	    (iocb->ki_pos + iov_iter_count(to) > i_size_read(inode))) {
 		int err;
 		err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL);
 		if (err)
 			return err;
 	}
 
-	return generic_file_aio_read(iocb, iov, nr_segs, pos);
+	return generic_file_read_iter(iocb, to);
 }
 
 static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff,
@@ -1181,19 +1180,17 @@ static ssize_t fuse_perform_write(struct file *file,
 	return res > 0 ? res : err;
 }
 
-static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				   unsigned long nr_segs, loff_t pos)
+static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
-	size_t count = 0;
-	size_t ocount = 0;
+	size_t count = iov_iter_count(from);
 	ssize_t written = 0;
 	ssize_t written_buffered = 0;
 	struct inode *inode = mapping->host;
 	ssize_t err;
-	struct iov_iter i;
 	loff_t endbyte = 0;
+	loff_t pos = iocb->ki_pos;
 
 	if (get_fuse_conn(inode)->writeback_cache) {
 		/* Update size (EOF optimization) and mode (SUID clearing) */
@@ -1201,17 +1198,9 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		if (err)
 			return err;
 
-		return generic_file_aio_write(iocb, iov, nr_segs, pos);
+		return generic_file_write_iter(iocb, from);
 	}
 
-	WARN_ON(iocb->ki_pos != pos);
-
-	ocount = 0;
-	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
-	if (err)
-		return err;
-
-	count = ocount;
 	mutex_lock(&inode->i_mutex);
 
 	/* We can write back this queue in page reclaim */
@@ -1224,6 +1213,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (count == 0)
 		goto out;
 
+	iov_iter_truncate(from, count);
 	err = file_remove_suid(file);
 	if (err)
 		goto out;
@@ -1233,16 +1223,13 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		goto out;
 
 	if (file->f_flags & O_DIRECT) {
-		written = generic_file_direct_write(iocb, iov, &nr_segs, pos, 
-						    count, ocount);
-		if (written < 0 || written == count)
+		written = generic_file_direct_write(iocb, from, pos);
+		if (written < 0 || !iov_iter_count(from))
 			goto out;
 
 		pos += written;
-		count -= written;
 
-		iov_iter_init(&i, iov, nr_segs, count, written);
-		written_buffered = fuse_perform_write(file, mapping, &i, pos);
+		written_buffered = fuse_perform_write(file, mapping, from, pos);
 		if (written_buffered < 0) {
 			err = written_buffered;
 			goto out;
@@ -1261,8 +1248,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		written += written_buffered;
 		iocb->ki_pos = pos + written_buffered;
 	} else {
-		iov_iter_init(&i, iov, nr_segs, count, 0);
-		written = fuse_perform_write(file, mapping, &i, pos);
+		written = fuse_perform_write(file, mapping, from, pos);
 		if (written >= 0)
 			iocb->ki_pos = pos + written;
 	}
@@ -1300,7 +1286,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 	size_t nbytes = 0;  /* # bytes already packed in req */
 
 	/* Special case for kernel I/O: can copy directly into the buffer */
-	if (segment_eq(get_fs(), KERNEL_DS)) {
+	if (ii->type & ITER_KVEC) {
 		unsigned long user_addr = fuse_get_user_addr(ii);
 		size_t frag_size = fuse_get_frag_size(ii, *nbytesp);
 
@@ -1316,35 +1302,26 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 
 	while (nbytes < *nbytesp && req->num_pages < req->max_pages) {
 		unsigned npages;
-		unsigned long user_addr = fuse_get_user_addr(ii);
-		unsigned offset = user_addr & ~PAGE_MASK;
-		size_t frag_size = fuse_get_frag_size(ii, *nbytesp - nbytes);
-		int ret;
-
+		size_t start;
 		unsigned n = req->max_pages - req->num_pages;
-		frag_size = min_t(size_t, frag_size, n << PAGE_SHIFT);
-
-		npages = (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		npages = clamp(npages, 1U, n);
-
-		ret = get_user_pages_fast(user_addr, npages, !write,
-					  &req->pages[req->num_pages]);
+		ssize_t ret = iov_iter_get_pages(ii,
+					&req->pages[req->num_pages],
+					n * PAGE_SIZE, &start);
 		if (ret < 0)
 			return ret;
 
-		npages = ret;
-		frag_size = min_t(size_t, frag_size,
-				  (npages << PAGE_SHIFT) - offset);
-		iov_iter_advance(ii, frag_size);
+		iov_iter_advance(ii, ret);
+		nbytes += ret;
+
+		ret += start;
+		npages = (ret + PAGE_SIZE - 1) / PAGE_SIZE;
 
-		req->page_descs[req->num_pages].offset = offset;
+		req->page_descs[req->num_pages].offset = start;
 		fuse_page_descs_length_init(req, req->num_pages, npages);
 
 		req->num_pages += npages;
 		req->page_descs[req->num_pages - 1].length -=
-			(npages << PAGE_SHIFT) - offset - frag_size;
-
-		nbytes += frag_size;
+			(PAGE_SIZE - ret) & (PAGE_SIZE - 1);
 	}
 
 	if (write)
@@ -1359,24 +1336,11 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii,
 
 static inline int fuse_iter_npages(const struct iov_iter *ii_p)
 {
-	struct iov_iter ii = *ii_p;
-	int npages = 0;
-
-	while (iov_iter_count(&ii) && npages < FUSE_MAX_PAGES_PER_REQ) {
-		unsigned long user_addr = fuse_get_user_addr(&ii);
-		unsigned offset = user_addr & ~PAGE_MASK;
-		size_t frag_size = iov_iter_single_seg_count(&ii);
-
-		npages += (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		iov_iter_advance(&ii, frag_size);
-	}
-
-	return min(npages, FUSE_MAX_PAGES_PER_REQ);
+	return iov_iter_npages(ii_p, FUSE_MAX_PAGES_PER_REQ);
 }
 
-ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
-		       unsigned long nr_segs, size_t count, loff_t *ppos,
-		       int flags)
+ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
+		       loff_t *ppos, int flags)
 {
 	int write = flags & FUSE_DIO_WRITE;
 	int cuse = flags & FUSE_DIO_CUSE;
@@ -1386,18 +1350,16 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
 	struct fuse_conn *fc = ff->fc;
 	size_t nmax = write ? fc->max_write : fc->max_read;
 	loff_t pos = *ppos;
+	size_t count = iov_iter_count(iter);
 	pgoff_t idx_from = pos >> PAGE_CACHE_SHIFT;
 	pgoff_t idx_to = (pos + count - 1) >> PAGE_CACHE_SHIFT;
 	ssize_t res = 0;
 	struct fuse_req *req;
-	struct iov_iter ii;
-
-	iov_iter_init(&ii, iov, nr_segs, count, 0);
 
 	if (io->async)
-		req = fuse_get_req_for_background(fc, fuse_iter_npages(&ii));
+		req = fuse_get_req_for_background(fc, fuse_iter_npages(iter));
 	else
-		req = fuse_get_req(fc, fuse_iter_npages(&ii));
+		req = fuse_get_req(fc, fuse_iter_npages(iter));
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
@@ -1413,7 +1375,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
 		size_t nres;
 		fl_owner_t owner = current->files;
 		size_t nbytes = min(count, nmax);
-		int err = fuse_get_user_pages(req, &ii, &nbytes, write);
+		int err = fuse_get_user_pages(req, iter, &nbytes, write);
 		if (err) {
 			res = err;
 			break;
@@ -1443,9 +1405,9 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
 			fuse_put_request(fc, req);
 			if (io->async)
 				req = fuse_get_req_for_background(fc,
-					fuse_iter_npages(&ii));
+					fuse_iter_npages(iter));
 			else
-				req = fuse_get_req(fc, fuse_iter_npages(&ii));
+				req = fuse_get_req(fc, fuse_iter_npages(iter));
 			if (IS_ERR(req))
 				break;
 		}
@@ -1460,9 +1422,8 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
 EXPORT_SYMBOL_GPL(fuse_direct_io);
 
 static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
-				  const struct iovec *iov,
-				  unsigned long nr_segs, loff_t *ppos,
-				  size_t count)
+				  struct iov_iter *iter,
+				  loff_t *ppos)
 {
 	ssize_t res;
 	struct file *file = io->file;
@@ -1471,7 +1432,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
 	if (is_bad_inode(inode))
 		return -EIO;
 
-	res = fuse_direct_io(io, iov, nr_segs, count, ppos, 0);
+	res = fuse_direct_io(io, iter, ppos, 0);
 
 	fuse_invalidate_attr(inode);
 
@@ -1483,22 +1444,26 @@ static ssize_t fuse_direct_read(struct file *file, char __user *buf,
 {
 	struct fuse_io_priv io = { .async = 0, .file = file };
 	struct iovec iov = { .iov_base = buf, .iov_len = count };
-	return __fuse_direct_read(&io, &iov, 1, ppos, count);
+	struct iov_iter ii;
+	iov_iter_init(&ii, READ, &iov, 1, count);
+	return __fuse_direct_read(&io, &ii, ppos);
 }
 
 static ssize_t __fuse_direct_write(struct fuse_io_priv *io,
-				   const struct iovec *iov,
-				   unsigned long nr_segs, loff_t *ppos)
+				   struct iov_iter *iter,
+				   loff_t *ppos)
 {
 	struct file *file = io->file;
 	struct inode *inode = file_inode(file);
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(iter);
 	ssize_t res;
 
+
 	res = generic_write_checks(file, ppos, &count, 0);
-	if (!res)
-		res = fuse_direct_io(io, iov, nr_segs, count, ppos,
-				     FUSE_DIO_WRITE);
+	if (!res) {
+		iov_iter_truncate(iter, count);
+		res = fuse_direct_io(io, iter, ppos, FUSE_DIO_WRITE);
+	}
 
 	fuse_invalidate_attr(inode);
 
@@ -1512,13 +1477,15 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf,
 	struct inode *inode = file_inode(file);
 	ssize_t res;
 	struct fuse_io_priv io = { .async = 0, .file = file };
+	struct iov_iter ii;
+	iov_iter_init(&ii, WRITE, &iov, 1, count);
 
 	if (is_bad_inode(inode))
 		return -EIO;
 
 	/* Don't allow parallel writes to the same file */
 	mutex_lock(&inode->i_mutex);
-	res = __fuse_direct_write(&io, &iov, 1, ppos);
+	res = __fuse_direct_write(&io, &ii, ppos);
 	if (res > 0)
 		fuse_write_update_size(inode, *ppos);
 	mutex_unlock(&inode->i_mutex);
@@ -1720,7 +1687,7 @@ static int fuse_writepage_locked(struct page *page)
 	error = -EIO;
 	req->ff = fuse_write_file_get(fc, fi);
 	if (!req->ff)
-		goto err_free;
+		goto err_nofile;
 
 	fuse_write_fill(req, req->ff, page_offset(page), 0);
 
@@ -1748,6 +1715,8 @@ static int fuse_writepage_locked(struct page *page)
 
 	return 0;
 
+err_nofile:
+	__free_page(tmp_page);
 err_free:
 	fuse_request_free(req);
 err:
@@ -1988,8 +1957,8 @@ static int fuse_writepages(struct address_space *mapping,
 	data.ff = NULL;
 
 	err = -ENOMEM;
-	data.orig_pages = kzalloc(sizeof(struct page *) *
-				  FUSE_MAX_PAGES_PER_REQ,
+	data.orig_pages = kcalloc(FUSE_MAX_PAGES_PER_REQ,
+				  sizeof(struct page *),
 				  GFP_NOFS);
 	if (!data.orig_pages)
 		goto out;
@@ -2372,7 +2341,7 @@ static int fuse_ioctl_copy_user(struct page **pages, struct iovec *iov,
 	if (!bytes)
 		return 0;
 
-	iov_iter_init(&ii, iov, nr_segs, bytes, 0);
+	iov_iter_init(&ii, to_user ? READ : WRITE, iov, nr_segs, bytes);
 
 	while (iov_iter_count(&ii)) {
 		struct page *page = pages[page_idx++];
@@ -2894,8 +2863,8 @@ static inline loff_t fuse_round_up(loff_t off)
 }
 
 static ssize_t
-fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs)
+fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+			loff_t offset)
 {
 	ssize_t ret = 0;
 	struct file *file = iocb->ki_filp;
@@ -2904,7 +2873,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	loff_t pos = 0;
 	struct inode *inode;
 	loff_t i_size;
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(iter);
 	struct fuse_io_priv *io;
 
 	pos = offset;
@@ -2919,6 +2888,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 		if (offset >= i_size)
 			return 0;
 		count = min_t(loff_t, count, fuse_round_up(i_size - offset));
+		iov_iter_truncate(iter, count);
 	}
 
 	io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL);
@@ -2948,9 +2918,9 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 		io->async = false;
 
 	if (rw == WRITE)
-		ret = __fuse_direct_write(io, iov, nr_segs, &pos);
+		ret = __fuse_direct_write(io, iter, &pos);
 	else
-		ret = __fuse_direct_read(io, iov, nr_segs, &pos, count);
+		ret = __fuse_direct_read(io, iter, &pos);
 
 	if (io->async) {
 		fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
@@ -3061,10 +3031,10 @@ out:
 
 static const struct file_operations fuse_file_operations = {
 	.llseek		= fuse_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= fuse_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= fuse_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= fuse_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= fuse_file_write_iter,
 	.mmap		= fuse_file_mmap,
 	.open		= fuse_open,
 	.flush		= fuse_flush,
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 7aa5c75e0de..e8e47a6ab51 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -880,9 +880,8 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
 /** CUSE pass fuse_direct_io() a file which f_mapping->host is not from FUSE */
 #define FUSE_DIO_CUSE  (1 << 1)
 
-ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov,
-		       unsigned long nr_segs, size_t count, loff_t *ppos,
-		       int flags);
+ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
+		       loff_t *ppos, int flags);
 long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 		   unsigned int flags);
 long fuse_ioctl_common(struct file *file, unsigned int cmd,
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 754dcf23de8..03246cd9d47 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -478,6 +478,17 @@ static const match_table_t tokens = {
 	{OPT_ERR,			NULL}
 };
 
+static int fuse_match_uint(substring_t *s, unsigned int *res)
+{
+	int err = -ENOMEM;
+	char *buf = match_strdup(s);
+	if (buf) {
+		err = kstrtouint(buf, 10, res);
+		kfree(buf);
+	}
+	return err;
+}
+
 static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 {
 	char *p;
@@ -488,6 +499,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 	while ((p = strsep(&opt, ",")) != NULL) {
 		int token;
 		int value;
+		unsigned uv;
 		substring_t args[MAX_OPT_ARGS];
 		if (!*p)
 			continue;
@@ -511,18 +523,18 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 			break;
 
 		case OPT_USER_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->user_id = make_kuid(current_user_ns(), value);
+			d->user_id = make_kuid(current_user_ns(), uv);
 			if (!uid_valid(d->user_id))
 				return 0;
 			d->user_id_present = 1;
 			break;
 
 		case OPT_GROUP_ID:
-			if (match_int(&args[0], &value))
+			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->group_id = make_kgid(current_user_ns(), value);
+			d->group_id = make_kgid(current_user_ns(), uv);
 			if (!gid_valid(d->group_id))
 				return 0;
 			d->group_id_present = 1;
@@ -895,9 +907,6 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 				fc->writeback_cache = 1;
 			if (arg->time_gran && arg->time_gran <= 1000000000)
 				fc->sb->s_time_gran = arg->time_gran;
-			else
-				fc->sb->s_time_gran = 1000000000;
-
 		} else {
 			ra_pages = fc->max_read / PAGE_CACHE_SIZE;
 			fc->no_lock = 1;
@@ -926,7 +935,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 		FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
 		FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
 		FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
-		FUSE_WRITEBACK_CACHE;
+		FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
@@ -1006,7 +1015,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION);
 
-	if (!parse_fuse_opt((char *) data, &d, is_bdev))
+	if (!parse_fuse_opt(data, &d, is_bdev))
 		goto err;
 
 	if (is_bdev) {
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 492123cda64..805b37fed63 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -1040,8 +1040,7 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
 
 
 static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
-			      const struct iovec *iov, loff_t offset,
-			      unsigned long nr_segs)
+			      struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -1081,7 +1080,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 	 */
 	if (mapping->nrpages) {
 		loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
-		loff_t len = iov_length(iov, nr_segs);
+		loff_t len = iov_iter_count(iter);
 		loff_t end = PAGE_ALIGN(offset + len) - 1;
 
 		rv = 0;
@@ -1096,9 +1095,9 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 			truncate_inode_pages_range(mapping, lstart, end);
 	}
 
-	rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
-				  offset, nr_segs, gfs2_get_block_direct,
-				  NULL, NULL, 0);
+	rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
+				  iter, offset,
+				  gfs2_get_block_direct, NULL, NULL, 0);
 out:
 	gfs2_glock_dq(&gh);
 	gfs2_holder_uninit(&gh);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 6ab0cfb2e89..26b3f952e6b 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -684,7 +684,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 }
 
 /**
- * gfs2_file_aio_write - Perform a write to a file
+ * gfs2_file_write_iter - Perform a write to a file
  * @iocb: The io context
  * @iov: The data to write
  * @nr_segs: Number of @iov segments
@@ -697,11 +697,9 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
  *
  */
 
-static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				   unsigned long nr_segs, loff_t pos)
+static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	size_t writesize = iov_length(iov, nr_segs);
 	struct gfs2_inode *ip = GFS2_I(file_inode(file));
 	int ret;
 
@@ -709,7 +707,7 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (ret)
 		return ret;
 
-	gfs2_size_hint(file, pos, writesize);
+	gfs2_size_hint(file, iocb->ki_pos, iov_iter_count(from));
 
 	if (file->f_flags & O_APPEND) {
 		struct gfs2_holder gh;
@@ -720,7 +718,7 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		gfs2_glock_dq_uninit(&gh);
 	}
 
-	return generic_file_aio_write(iocb, iov, nr_segs, pos);
+	return generic_file_write_iter(iocb, from);
 }
 
 static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
@@ -983,7 +981,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	int error = 0;
 
 	state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED;
-	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE;
+	flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT;
 
 	mutex_lock(&fp->f_fl_mutex);
 
@@ -993,7 +991,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 			goto out;
 		flock_lock_file_wait(file,
 				     &(struct file_lock){.fl_type = F_UNLCK});
-		gfs2_glock_dq_wait(fl_gh);
+		gfs2_glock_dq(fl_gh);
 		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {
 		error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr,
@@ -1058,10 +1056,10 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 
 const struct file_operations gfs2_file_fops = {
 	.llseek		= gfs2_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= gfs2_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= gfs2_file_write_iter,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
@@ -1070,7 +1068,7 @@ const struct file_operations gfs2_file_fops = {
 	.lock		= gfs2_lock,
 	.flock		= gfs2_flock,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.setlease	= gfs2_setlease,
 	.fallocate	= gfs2_fallocate,
 };
@@ -1090,17 +1088,17 @@ const struct file_operations gfs2_dir_fops = {
 
 const struct file_operations gfs2_file_fops_nolock = {
 	.llseek		= gfs2_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= gfs2_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= gfs2_file_write_iter,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
 	.release	= gfs2_release,
 	.fsync		= gfs2_fsync,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.setlease	= generic_setlease,
 	.fallocate	= gfs2_fallocate,
 };
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index c355f7320e4..7f513b1ceb2 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -731,14 +731,14 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		cachep = gfs2_glock_aspace_cachep;
 	else
 		cachep = gfs2_glock_cachep;
-	gl = kmem_cache_alloc(cachep, GFP_KERNEL);
+	gl = kmem_cache_alloc(cachep, GFP_NOFS);
 	if (!gl)
 		return -ENOMEM;
 
 	memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
 
 	if (glops->go_flags & GLOF_LVB) {
-		gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_KERNEL);
+		gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_NOFS);
 		if (!gl->gl_lksb.sb_lvbptr) {
 			kmem_cache_free(cachep, gl);
 			return -ENOMEM;
@@ -856,27 +856,6 @@ void gfs2_holder_uninit(struct gfs2_holder *gh)
 }
 
 /**
- * gfs2_glock_holder_wait
- * @word: unused
- *
- * This function and gfs2_glock_demote_wait both show up in the WCHAN
- * field. Thus I've separated these otherwise identical functions in
- * order to be more informative to the user.
- */
-
-static int gfs2_glock_holder_wait(void *word)
-{
-        schedule();
-        return 0;
-}
-
-static int gfs2_glock_demote_wait(void *word)
-{
-	schedule();
-	return 0;
-}
-
-/**
  * gfs2_glock_wait - wait on a glock acquisition
  * @gh: the glock holder
  *
@@ -888,7 +867,7 @@ int gfs2_glock_wait(struct gfs2_holder *gh)
 	unsigned long time1 = jiffies;
 
 	might_sleep();
-	wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&gh->gh_iflags, HIF_WAIT, TASK_UNINTERRUPTIBLE);
 	if (time_after(jiffies, time1 + HZ)) /* have we waited > a second? */
 		/* Lengthen the minimum hold time. */
 		gh->gh_gl->gl_hold_time = min(gh->gh_gl->gl_hold_time +
@@ -1128,7 +1107,7 @@ void gfs2_glock_dq_wait(struct gfs2_holder *gh)
 	struct gfs2_glock *gl = gh->gh_gl;
 	gfs2_glock_dq(gh);
 	might_sleep();
-	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, gfs2_glock_demote_wait, TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&gl->gl_flags, GLF_DEMOTE, TASK_UNINTERRUPTIBLE);
 }
 
 /**
@@ -1404,12 +1383,16 @@ __acquires(&lru_lock)
 		gl = list_entry(list->next, struct gfs2_glock, gl_lru);
 		list_del_init(&gl->gl_lru);
 		if (!spin_trylock(&gl->gl_spin)) {
+add_back_to_lru:
 			list_add(&gl->gl_lru, &lru_list);
 			atomic_inc(&lru_count);
 			continue;
 		}
+		if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
+			spin_unlock(&gl->gl_spin);
+			goto add_back_to_lru;
+		}
 		clear_bit(GLF_LRU, &gl->gl_flags);
-		spin_unlock(&lru_lock);
 		gl->gl_lockref.count++;
 		if (demote_ok(gl))
 			handle_callback(gl, LM_ST_UNLOCKED, 0, false);
@@ -1417,7 +1400,7 @@ __acquires(&lru_lock)
 		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 			gl->gl_lockref.count--;
 		spin_unlock(&gl->gl_spin);
-		spin_lock(&lru_lock);
+		cond_resched_lock(&lru_lock);
 	}
 }
 
@@ -1442,7 +1425,7 @@ static long gfs2_scan_glock_lru(int nr)
 		gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
 
 		/* Test for being demotable */
-		if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
+		if (!test_bit(GLF_LOCK, &gl->gl_flags)) {
 			list_move(&gl->gl_lru, &dispose);
 			atomic_dec(&lru_count);
 			freed++;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index fc1100781bb..2ffc67dce87 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -234,8 +234,8 @@ static void inode_go_sync(struct gfs2_glock *gl)
  * inode_go_inval - prepare a inode glock to be released
  * @gl: the glock
  * @flags:
- * 
- * Normally we invlidate everything, but if we are moving into
+ *
+ * Normally we invalidate everything, but if we are moving into
  * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we
  * can keep hold of the metadata, since it won't have changed.
  *
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 91f274de124..641383a9c1b 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -936,12 +936,6 @@ fail:
 	return error;
 }
 
-static int dlm_recovery_wait(void *word)
-{
-	schedule();
-	return 0;
-}
-
 static int control_first_done(struct gfs2_sbd *sdp)
 {
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
@@ -976,7 +970,7 @@ restart:
 		fs_info(sdp, "control_first_done wait gen %u\n", start_gen);
 
 		wait_on_bit(&ls->ls_recover_flags, DFL_DLM_RECOVERY,
-			    dlm_recovery_wait, TASK_UNINTERRUPTIBLE);
+			    TASK_UNINTERRUPTIBLE);
 		goto restart;
 	}
 
@@ -1036,8 +1030,8 @@ static int set_recover_size(struct gfs2_sbd *sdp, struct dlm_slot *slots,
 
 	new_size = old_size + RECOVER_SIZE_INC;
 
-	submit = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS);
-	result = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS);
+	submit = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS);
+	result = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS);
 	if (!submit || !result) {
 		kfree(submit);
 		kfree(result);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index bc564c0d6d1..d3eae244076 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1024,20 +1024,13 @@ void gfs2_lm_unmount(struct gfs2_sbd *sdp)
 		lm->lm_unmount(sdp);
 }
 
-static int gfs2_journalid_wait(void *word)
-{
-	if (signal_pending(current))
-		return -EINTR;
-	schedule();
-	return 0;
-}
-
 static int wait_on_journal(struct gfs2_sbd *sdp)
 {
 	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
 		return 0;
 
-	return wait_on_bit(&sdp->sd_flags, SDF_NOJOURNALID, gfs2_journalid_wait, TASK_INTERRUPTIBLE);
+	return wait_on_bit(&sdp->sd_flags, SDF_NOJOURNALID, TASK_INTERRUPTIBLE)
+		? -EINTR : 0;
 }
 
 void gfs2_online_uevent(struct gfs2_sbd *sdp)
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 94555d4c569..573bd3b758f 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -591,12 +591,6 @@ done:
 	wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
 }
 
-static int gfs2_recovery_wait(void *word)
-{
-	schedule();
-	return 0;
-}
-
 int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait)
 {
 	int rv;
@@ -609,7 +603,7 @@ int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait)
 	BUG_ON(!rv);
 
 	if (wait)
-		wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait,
+		wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
 			    TASK_UNINTERRUPTIBLE);
 
 	return wait ? jd->jd_recover_error : 0;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index db629d1bd1b..f4cb9c0d6bb 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -337,7 +337,7 @@ static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *le
 
 /**
  * gfs2_free_extlen - Return extent length of free blocks
- * @rbm: Starting position
+ * @rrbm: Starting position
  * @len: Max length to check
  *
  * Starting at the block specified by the rbm, see how many free blocks
@@ -2522,7 +2522,7 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state)
 
 /**
  * gfs2_rlist_free - free a resource group list
- * @list: the list of resource groups
+ * @rlist: the list of resource groups
  *
  */
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 1319b5c4ec6..2607ff13d48 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -864,12 +864,6 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 	return error;
 }
 
-static int gfs2_umount_recovery_wait(void *word)
-{
-	schedule();
-	return 0;
-}
-
 /**
  * gfs2_put_super - Unmount the filesystem
  * @sb: The VFS superblock
@@ -894,7 +888,7 @@ restart:
 			continue;
 		spin_unlock(&sdp->sd_jindex_spin);
 		wait_on_bit(&jd->jd_flags, JDF_RECOVERY,
-			    gfs2_umount_recovery_wait, TASK_UNINTERRUPTIBLE);
+			    TASK_UNINTERRUPTIBLE);
 		goto restart;
 	}
 	spin_unlock(&sdp->sd_jindex_spin);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 9e2fecd62f6..d0929bc8178 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -125,15 +125,15 @@ static int hfs_releasepage(struct page *page, gfp_t mask)
 }
 
 static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb,
-		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+		struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file_inode(file)->i_mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
-				 hfs_get_block);
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, hfs_get_block);
 
 	/*
 	 * In case of error extending write may have instantiated a few
@@ -141,7 +141,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb,
 	 */
 	if (unlikely((rw & WRITE) && ret < 0)) {
 		loff_t isize = i_size_read(inode);
-		loff_t end = offset + iov_length(iov, nr_segs);
+		loff_t end = offset + count;
 
 		if (end > isize)
 			hfs_write_failed(mapping, end);
@@ -674,10 +674,10 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 
 static const struct file_operations hfs_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.splice_read	= generic_file_splice_read,
 	.fsync		= hfs_file_fsync,
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index a4f45bd88a6..0cf786f2d04 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -123,14 +123,15 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
 }
 
 static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb,
-		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+		struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file_inode(file)->i_mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, 
 				 hfsplus_get_block);
 
 	/*
@@ -139,7 +140,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb,
 	 */
 	if (unlikely((rw & WRITE) && ret < 0)) {
 		loff_t isize = i_size_read(inode);
-		loff_t end = offset + iov_length(iov, nr_segs);
+		loff_t end = offset + count;
 
 		if (end > isize)
 			hfsplus_write_failed(mapping, end);
@@ -340,10 +341,10 @@ static const struct inode_operations hfsplus_file_inode_operations = {
 
 static const struct file_operations hfsplus_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.splice_read	= generic_file_splice_read,
 	.fsync		= hfsplus_file_fsync,
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 9c470fde987..bb529f3b7f2 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -378,11 +378,11 @@ static int hostfs_fsync(struct file *file, loff_t start, loff_t end,
 
 static const struct file_operations hostfs_file_fops = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
+	.read		= new_sync_read,
 	.splice_read	= generic_file_splice_read,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
-	.write		= do_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
+	.write		= new_sync_write,
 	.mmap		= generic_file_mmap,
 	.open		= hostfs_file_open,
 	.release	= hostfs_file_release,
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 67c1a61e095..7f54e5f76ce 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -197,10 +197,10 @@ const struct address_space_operations hpfs_aops = {
 const struct file_operations hpfs_file_ops =
 {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.release	= hpfs_file_release,
 	.fsync		= hpfs_file_fsync,
diff --git a/fs/inode.c b/fs/inode.c
index 2feb9b69f1b..5938f392894 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1695,13 +1695,6 @@ int inode_needs_sync(struct inode *inode)
 }
 EXPORT_SYMBOL(inode_needs_sync);
 
-int inode_wait(void *word)
-{
-	schedule();
-	return 0;
-}
-EXPORT_SYMBOL(inode_wait);
-
 /*
  * If we try to find an inode in the inode hash while it is being
  * deleted, we have to wait until the filesystem completes its
@@ -1839,14 +1832,18 @@ EXPORT_SYMBOL(inode_init_owner);
  * inode_owner_or_capable - check current task permissions to inode
  * @inode: inode being checked
  *
- * Return true if current either has CAP_FOWNER to the inode, or
- * owns the file.
+ * Return true if current either has CAP_FOWNER in a namespace with the
+ * inode owner uid mapped, or owns the file.
  */
 bool inode_owner_or_capable(const struct inode *inode)
 {
+	struct user_namespace *ns;
+
 	if (uid_eq(current_fsuid(), inode->i_uid))
 		return true;
-	if (inode_capable(inode, CAP_FOWNER))
+
+	ns = current_user_ns();
+	if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid))
 		return true;
 	return false;
 }
diff --git a/fs/jbd/revoke.c b/fs/jbd/revoke.c
index 25c713e7071..8898bbd2b61 100644
--- a/fs/jbd/revoke.c
+++ b/fs/jbd/revoke.c
@@ -231,19 +231,15 @@ record_cache_failure:
 
 static struct jbd_revoke_table_s *journal_init_revoke_table(int hash_size)
 {
-	int shift = 0;
-	int tmp = hash_size;
+	int i;
 	struct jbd_revoke_table_s *table;
 
 	table = kmem_cache_alloc(revoke_table_cache, GFP_KERNEL);
 	if (!table)
 		goto out;
 
-	while((tmp >>= 1UL) != 0UL)
-		shift++;
-
 	table->hash_size = hash_size;
-	table->hash_shift = shift;
+	table->hash_shift = ilog2(hash_size);
 	table->hash_table =
 		kmalloc(hash_size * sizeof(struct list_head), GFP_KERNEL);
 	if (!table->hash_table) {
@@ -252,8 +248,8 @@ static struct jbd_revoke_table_s *journal_init_revoke_table(int hash_size)
 		goto out;
 	}
 
-	for (tmp = 0; tmp < hash_size; tmp++)
-		INIT_LIST_HEAD(&table->hash_table[tmp]);
+	for (i = 0; i < hash_size; i++)
+		INIT_LIST_HEAD(&table->hash_table[i]);
 
 out:
 	return table;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 38cfcf5f6fc..5f09370c90a 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -763,12 +763,6 @@ static void warn_dirty_buffer(struct buffer_head *bh)
 	       bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr);
 }
 
-static int sleep_on_shadow_bh(void *word)
-{
-	io_schedule();
-	return 0;
-}
-
 /*
  * If the buffer is already part of the current transaction, then there
  * is nothing we need to do.  If it is already part of a prior
@@ -906,8 +900,8 @@ repeat:
 		if (buffer_shadow(bh)) {
 			JBUFFER_TRACE(jh, "on shadow: sleep");
 			jbd_unlock_bh_state(bh);
-			wait_on_bit(&bh->b_state, BH_Shadow,
-				    sleep_on_shadow_bh, TASK_UNINTERRUPTIBLE);
+			wait_on_bit_io(&bh->b_state, BH_Shadow,
+				       TASK_UNINTERRUPTIBLE);
 			goto repeat;
 		}
 
@@ -1588,9 +1582,12 @@ int jbd2_journal_stop(handle_t *handle)
 	 * to perform a synchronous write.  We do this to detect the
 	 * case where a single process is doing a stream of sync
 	 * writes.  No point in waiting for joiners in that case.
+	 *
+	 * Setting max_batch_time to 0 disables this completely.
 	 */
 	pid = current->pid;
-	if (handle->h_sync && journal->j_last_sync_writer != pid) {
+	if (handle->h_sync && journal->j_last_sync_writer != pid &&
+	    journal->j_max_batch_time) {
 		u64 commit_time, trans_time;
 
 		journal->j_last_sync_writer = pid;
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 256cd19a3b7..64989ca9ba9 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -51,10 +51,10 @@ const struct file_operations jffs2_file_operations =
 {
 	.llseek =	generic_file_llseek,
 	.open =		generic_file_open,
- 	.read =		do_sync_read,
- 	.aio_read =	generic_file_aio_read,
- 	.write =	do_sync_write,
- 	.aio_write =	generic_file_aio_write,
+ 	.read =		new_sync_read,
+ 	.read_iter =	generic_file_read_iter,
+ 	.write =	new_sync_write,
+ 	.write_iter =	generic_file_write_iter,
 	.unlocked_ioctl=jffs2_ioctl,
 	.mmap =		generic_file_readonly_mmap,
 	.fsync =	jffs2_fsync,
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index 794da944d5c..33aa0cc1f8b 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -151,13 +151,13 @@ const struct inode_operations jfs_file_inode_operations = {
 const struct file_operations jfs_file_operations = {
 	.open		= jfs_open,
 	.llseek		= generic_file_llseek,
-	.write		= do_sync_write,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
+	.write		= new_sync_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.fsync		= jfs_fsync,
 	.release	= jfs_release,
 	.unlocked_ioctl = jfs_ioctl,
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 6f8fe72c2a7..bd3df1ca3c9 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -331,15 +331,15 @@ static sector_t jfs_bmap(struct address_space *mapping, sector_t block)
 }
 
 static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
-	const struct iovec *iov, loff_t offset, unsigned long nr_segs)
+	struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file->f_mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
-				 jfs_get_block);
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, jfs_get_block);
 
 	/*
 	 * In case of error extending write may have instantiated a few
@@ -347,7 +347,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
 	 */
 	if (unlikely((rw & WRITE) && ret < 0)) {
 		loff_t isize = i_size_read(inode);
-		loff_t end = offset + iov_length(iov, nr_segs);
+		loff_t end = offset + count;
 
 		if (end > isize)
 			jfs_write_failed(mapping, end);
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e3d37f607f9..d895b4b7b66 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -39,6 +39,19 @@ struct kernfs_open_node {
 	struct list_head	files; /* goes through kernfs_open_file.list */
 };
 
+/*
+ * kernfs_notify() may be called from any context and bounces notifications
+ * through a work item.  To minimize space overhead in kernfs_node, the
+ * pending queue is implemented as a singly linked list of kernfs_nodes.
+ * The list is terminated with the self pointer so that whether a
+ * kernfs_node is on the list or not can be determined by testing the next
+ * pointer for NULL.
+ */
+#define KERNFS_NOTIFY_EOL			((void *)&kernfs_notify_list)
+
+static DEFINE_SPINLOCK(kernfs_notify_lock);
+static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL;
+
 static struct kernfs_open_file *kernfs_of(struct file *file)
 {
 	return ((struct seq_file *)file->private_data)->private;
@@ -783,24 +796,25 @@ static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait)
 	return DEFAULT_POLLMASK|POLLERR|POLLPRI;
 }
 
-/**
- * kernfs_notify - notify a kernfs file
- * @kn: file to notify
- *
- * Notify @kn such that poll(2) on @kn wakes up.
- */
-void kernfs_notify(struct kernfs_node *kn)
+static void kernfs_notify_workfn(struct work_struct *work)
 {
-	struct kernfs_root *root = kernfs_root(kn);
+	struct kernfs_node *kn;
 	struct kernfs_open_node *on;
 	struct kernfs_super_info *info;
-	unsigned long flags;
-
-	if (WARN_ON(kernfs_type(kn) != KERNFS_FILE))
+repeat:
+	/* pop one off the notify_list */
+	spin_lock_irq(&kernfs_notify_lock);
+	kn = kernfs_notify_list;
+	if (kn == KERNFS_NOTIFY_EOL) {
+		spin_unlock_irq(&kernfs_notify_lock);
 		return;
+	}
+	kernfs_notify_list = kn->attr.notify_next;
+	kn->attr.notify_next = NULL;
+	spin_unlock_irq(&kernfs_notify_lock);
 
 	/* kick poll */
-	spin_lock_irqsave(&kernfs_open_node_lock, flags);
+	spin_lock_irq(&kernfs_open_node_lock);
 
 	on = kn->attr.open;
 	if (on) {
@@ -808,12 +822,12 @@ void kernfs_notify(struct kernfs_node *kn)
 		wake_up_interruptible(&on->poll);
 	}
 
-	spin_unlock_irqrestore(&kernfs_open_node_lock, flags);
+	spin_unlock_irq(&kernfs_open_node_lock);
 
 	/* kick fsnotify */
 	mutex_lock(&kernfs_mutex);
 
-	list_for_each_entry(info, &root->supers, node) {
+	list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
 		struct inode *inode;
 		struct dentry *dentry;
 
@@ -833,6 +847,33 @@ void kernfs_notify(struct kernfs_node *kn)
 	}
 
 	mutex_unlock(&kernfs_mutex);
+	kernfs_put(kn);
+	goto repeat;
+}
+
+/**
+ * kernfs_notify - notify a kernfs file
+ * @kn: file to notify
+ *
+ * Notify @kn such that poll(2) on @kn wakes up.  Maybe be called from any
+ * context.
+ */
+void kernfs_notify(struct kernfs_node *kn)
+{
+	static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn);
+	unsigned long flags;
+
+	if (WARN_ON(kernfs_type(kn) != KERNFS_FILE))
+		return;
+
+	spin_lock_irqsave(&kernfs_notify_lock, flags);
+	if (!kn->attr.notify_next) {
+		kernfs_get(kn);
+		kn->attr.notify_next = kernfs_notify_list;
+		kernfs_notify_list = kn;
+		schedule_work(&kernfs_notify_work);
+	}
+	spin_unlock_irqrestore(&kernfs_notify_lock, flags);
 }
 EXPORT_SYMBOL_GPL(kernfs_notify);
 
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index d171b98a6cd..f973ae9b05f 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -211,6 +211,36 @@ void kernfs_kill_sb(struct super_block *sb)
 	kernfs_put(root_kn);
 }
 
+/**
+ * kernfs_pin_sb: try to pin the superblock associated with a kernfs_root
+ * @kernfs_root: the kernfs_root in question
+ * @ns: the namespace tag
+ *
+ * Pin the superblock so the superblock won't be destroyed in subsequent
+ * operations.  This can be used to block ->kill_sb() which may be useful
+ * for kernfs users which dynamically manage superblocks.
+ *
+ * Returns NULL if there's no superblock associated to this kernfs_root, or
+ * -EINVAL if the superblock is being freed.
+ */
+struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns)
+{
+	struct kernfs_super_info *info;
+	struct super_block *sb = NULL;
+
+	mutex_lock(&kernfs_mutex);
+	list_for_each_entry(info, &root->supers, node) {
+		if (info->ns == ns) {
+			sb = info->sb;
+			if (!atomic_inc_not_zero(&info->sb->s_active))
+				sb = ERR_PTR(-EINVAL);
+			break;
+		}
+	}
+	mutex_unlock(&kernfs_mutex);
+	return sb;
+}
+
 void __init kernfs_init(void)
 {
 	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index 00ec0b9c94d..d3e40db2893 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -14,6 +14,8 @@
 #include <linux/sunrpc/stats.h>
 #include <linux/lockd/lockd.h>
 
+#include <uapi/linux/nfs3.h>
+
 #define NLMDBG_FACILITY		NLMDBG_XDR
 
 #if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ)
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 9a55797a1cd..3e9f7874b97 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -15,6 +15,8 @@
 #include <linux/sunrpc/stats.h>
 #include <linux/lockd/lockd.h>
 
+#include <uapi/linux/nfs2.h>
+
 #define NLMDBG_FACILITY		NLMDBG_XDR
 
 #if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ)
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index de051cb1f55..8f27c93f8d2 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -622,8 +622,8 @@ static int __init init_nlm(void)
 err_pernet:
 #ifdef CONFIG_SYSCTL
 	unregister_sysctl_table(nlm_sysctl_table);
-#endif
 err_sysctl:
+#endif
 	return err;
 }
 
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index dc5c75930f0..b6f3b84b6e9 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -14,12 +14,11 @@
 #include <linux/mutex.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/addr.h>
-#include <linux/nfsd/nfsfh.h>
-#include <linux/nfsd/export.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
 #include <linux/module.h>
 #include <linux/mount.h>
+#include <uapi/linux/nfs2.h>
 
 #define NLMDBG_FACILITY		NLMDBG_SVCSUBS
 
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 964666c68a8..9340e7e10ef 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -16,6 +16,8 @@
 #include <linux/sunrpc/stats.h>
 #include <linux/lockd/lockd.h>
 
+#include <uapi/linux/nfs2.h>
+
 #define NLMDBG_FACILITY		NLMDBG_XDR
 
 
diff --git a/fs/locks.c b/fs/locks.c
index da57c9b7e84..a6f54802d27 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -325,7 +325,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock,
 		return -ENOMEM;
 
 	fl->fl_file = filp;
-	fl->fl_owner = (fl_owner_t)filp;
+	fl->fl_owner = filp;
 	fl->fl_pid = current->tgid;
 	fl->fl_flags = FL_FLOCK;
 	fl->fl_type = type;
@@ -431,7 +431,7 @@ static int lease_init(struct file *filp, long type, struct file_lock *fl)
 	if (assign_type(fl, type) != 0)
 		return -EINVAL;
 
-	fl->fl_owner = (fl_owner_t)filp;
+	fl->fl_owner = current->files;
 	fl->fl_pid = current->tgid;
 
 	fl->fl_file = filp;
@@ -1155,7 +1155,6 @@ EXPORT_SYMBOL(posix_lock_file_wait);
 int locks_mandatory_locked(struct file *file)
 {
 	struct inode *inode = file_inode(file);
-	fl_owner_t owner = current->files;
 	struct file_lock *fl;
 
 	/*
@@ -1165,7 +1164,8 @@ int locks_mandatory_locked(struct file *file)
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (!IS_POSIX(fl))
 			continue;
-		if (fl->fl_owner != owner && fl->fl_owner != (fl_owner_t)file)
+		if (fl->fl_owner != current->files &&
+		    fl->fl_owner != file)
 			break;
 	}
 	spin_unlock(&inode->i_lock);
@@ -1205,7 +1205,7 @@ int locks_mandatory_area(int read_write, struct inode *inode,
 
 	for (;;) {
 		if (filp) {
-			fl.fl_owner = (fl_owner_t)filp;
+			fl.fl_owner = filp;
 			fl.fl_flags &= ~FL_SLEEP;
 			error = __posix_lock_file(inode, &fl, NULL);
 			if (!error)
@@ -1948,7 +1948,7 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l)
 
 		cmd = F_GETLK;
 		file_lock.fl_flags |= FL_OFDLCK;
-		file_lock.fl_owner = (fl_owner_t)filp;
+		file_lock.fl_owner = filp;
 	}
 
 	error = vfs_test_lock(filp, &file_lock);
@@ -2103,7 +2103,7 @@ again:
 
 		cmd = F_SETLK;
 		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = (fl_owner_t)filp;
+		file_lock->fl_owner = filp;
 		break;
 	case F_OFD_SETLKW:
 		error = -EINVAL;
@@ -2112,7 +2112,7 @@ again:
 
 		cmd = F_SETLKW;
 		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = (fl_owner_t)filp;
+		file_lock->fl_owner = filp;
 		/* Fallthrough */
 	case F_SETLKW:
 		file_lock->fl_flags |= FL_SLEEP;
@@ -2170,7 +2170,7 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
 
 		cmd = F_GETLK64;
 		file_lock.fl_flags |= FL_OFDLCK;
-		file_lock.fl_owner = (fl_owner_t)filp;
+		file_lock.fl_owner = filp;
 	}
 
 	error = vfs_test_lock(filp, &file_lock);
@@ -2242,7 +2242,7 @@ again:
 
 		cmd = F_SETLK64;
 		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = (fl_owner_t)filp;
+		file_lock->fl_owner = filp;
 		break;
 	case F_OFD_SETLKW:
 		error = -EINVAL;
@@ -2251,7 +2251,7 @@ again:
 
 		cmd = F_SETLKW64;
 		file_lock->fl_flags |= FL_OFDLCK;
-		file_lock->fl_owner = (fl_owner_t)filp;
+		file_lock->fl_owner = filp;
 		/* Fallthrough */
 	case F_SETLKW64:
 		file_lock->fl_flags |= FL_SLEEP;
@@ -2324,11 +2324,11 @@ void locks_remove_file(struct file *filp)
 	if (!inode->i_flock)
 		return;
 
-	locks_remove_posix(filp, (fl_owner_t)filp);
+	locks_remove_posix(filp, filp);
 
 	if (filp->f_op->flock) {
 		struct file_lock fl = {
-			.fl_owner = (fl_owner_t)filp,
+			.fl_owner = filp,
 			.fl_pid = current->tgid,
 			.fl_file = filp,
 			.fl_flags = FL_FLOCK,
diff --git a/fs/logfs/file.c b/fs/logfs/file.c
index 57914fc32b6..8538752df2f 100644
--- a/fs/logfs/file.c
+++ b/fs/logfs/file.c
@@ -264,15 +264,15 @@ const struct inode_operations logfs_reg_iops = {
 };
 
 const struct file_operations logfs_reg_fops = {
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.fsync		= logfs_fsync,
 	.unlocked_ioctl	= logfs_ioctl,
 	.llseek		= generic_file_llseek,
 	.mmap		= generic_file_readonly_mmap,
 	.open		= generic_file_open,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
 };
 
 const struct address_space_operations logfs_reg_aops = {
diff --git a/fs/mbcache.c b/fs/mbcache.c
index bf166e388f0..187477ded6b 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -73,6 +73,7 @@
 #include <linux/mbcache.h>
 #include <linux/init.h>
 #include <linux/blockgroup_lock.h>
+#include <linux/log2.h>
 
 #ifdef MB_CACHE_DEBUG
 # define mb_debug(f...) do { \
@@ -93,7 +94,7 @@
 
 #define MB_CACHE_WRITER ((unsigned short)~0U >> 1)
 
-#define MB_CACHE_ENTRY_LOCK_BITS	__builtin_log2(NR_BG_LOCKS)
+#define MB_CACHE_ENTRY_LOCK_BITS	ilog2(NR_BG_LOCKS)
 #define	MB_CACHE_ENTRY_LOCK_INDEX(ce)			\
 	(hash_long((unsigned long)ce, MB_CACHE_ENTRY_LOCK_BITS))
 
diff --git a/fs/minix/file.c b/fs/minix/file.c
index adc6f549423..a967de085ac 100644
--- a/fs/minix/file.c
+++ b/fs/minix/file.c
@@ -14,10 +14,10 @@
  */
 const struct file_operations minix_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= generic_file_fsync,
 	.splice_read	= generic_file_splice_read,
diff --git a/fs/namei.c b/fs/namei.c
index 80168273396..9eb787e5c16 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -332,10 +332,11 @@ int generic_permission(struct inode *inode, int mask)
 
 	if (S_ISDIR(inode->i_mode)) {
 		/* DACs are overridable for directories */
-		if (inode_capable(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
 			return 0;
 		if (!(mask & MAY_WRITE))
-			if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+			if (capable_wrt_inode_uidgid(inode,
+						     CAP_DAC_READ_SEARCH))
 				return 0;
 		return -EACCES;
 	}
@@ -345,7 +346,7 @@ int generic_permission(struct inode *inode, int mask)
 	 * at least one exec bit set.
 	 */
 	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
-		if (inode_capable(inode, CAP_DAC_OVERRIDE))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
 			return 0;
 
 	/*
@@ -353,7 +354,7 @@ int generic_permission(struct inode *inode, int mask)
 	 */
 	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 	if (mask == MAY_READ)
-		if (inode_capable(inode, CAP_DAC_READ_SEARCH))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
 			return 0;
 
 	return -EACCES;
@@ -2255,9 +2256,10 @@ done:
 		goto out;
 	}
 	path->dentry = dentry;
-	path->mnt = mntget(nd->path.mnt);
+	path->mnt = nd->path.mnt;
 	if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW))
 		return 1;
+	mntget(path->mnt);
 	follow_mount(path);
 	error = 0;
 out:
@@ -2379,7 +2381,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode)
 		return 0;
 	if (uid_eq(dir->i_uid, fsuid))
 		return 0;
-	return !inode_capable(inode, CAP_FOWNER);
+	return !capable_wrt_inode_uidgid(inode, CAP_FOWNER);
 }
 
 /*
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 03192a66c14..4782e0840dc 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -29,8 +29,6 @@ nfsv4-$(CONFIG_NFS_USE_LEGACY_DNS) += cache_lib.o
 nfsv4-$(CONFIG_SYSCTL)	+= nfs4sysctl.o
 nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
 
-obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
-nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
-
+obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
 obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
 obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 65d849bdf77..9b431f44fad 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -210,7 +210,7 @@ static void bl_end_io_read(struct bio *bio, int err)
 			SetPageUptodate(bvec->bv_page);
 
 	if (err) {
-		struct nfs_read_data *rdata = par->data;
+		struct nfs_pgio_data *rdata = par->data;
 		struct nfs_pgio_header *header = rdata->header;
 
 		if (!header->pnfs_error)
@@ -224,17 +224,17 @@ static void bl_end_io_read(struct bio *bio, int err)
 static void bl_read_cleanup(struct work_struct *work)
 {
 	struct rpc_task *task;
-	struct nfs_read_data *rdata;
+	struct nfs_pgio_data *rdata;
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
-	rdata = container_of(task, struct nfs_read_data, task);
+	rdata = container_of(task, struct nfs_pgio_data, task);
 	pnfs_ld_read_done(rdata);
 }
 
 static void
 bl_end_par_io_read(void *data, int unused)
 {
-	struct nfs_read_data *rdata = data;
+	struct nfs_pgio_data *rdata = data;
 
 	rdata->task.tk_status = rdata->header->pnfs_error;
 	INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup);
@@ -242,7 +242,7 @@ bl_end_par_io_read(void *data, int unused)
 }
 
 static enum pnfs_try_status
-bl_read_pagelist(struct nfs_read_data *rdata)
+bl_read_pagelist(struct nfs_pgio_data *rdata)
 {
 	struct nfs_pgio_header *header = rdata->header;
 	int i, hole;
@@ -390,7 +390,7 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
 	}
 
 	if (unlikely(err)) {
-		struct nfs_write_data *data = par->data;
+		struct nfs_pgio_data *data = par->data;
 		struct nfs_pgio_header *header = data->header;
 
 		if (!header->pnfs_error)
@@ -405,7 +405,7 @@ static void bl_end_io_write(struct bio *bio, int err)
 {
 	struct parallel_io *par = bio->bi_private;
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct nfs_write_data *data = par->data;
+	struct nfs_pgio_data *data = par->data;
 	struct nfs_pgio_header *header = data->header;
 
 	if (!uptodate) {
@@ -423,10 +423,10 @@ static void bl_end_io_write(struct bio *bio, int err)
 static void bl_write_cleanup(struct work_struct *work)
 {
 	struct rpc_task *task;
-	struct nfs_write_data *wdata;
+	struct nfs_pgio_data *wdata;
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
-	wdata = container_of(task, struct nfs_write_data, task);
+	wdata = container_of(task, struct nfs_pgio_data, task);
 	if (likely(!wdata->header->pnfs_error)) {
 		/* Marks for LAYOUTCOMMIT */
 		mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg),
@@ -438,7 +438,7 @@ static void bl_write_cleanup(struct work_struct *work)
 /* Called when last of bios associated with a bl_write_pagelist call finishes */
 static void bl_end_par_io_write(void *data, int num_se)
 {
-	struct nfs_write_data *wdata = data;
+	struct nfs_pgio_data *wdata = data;
 
 	if (unlikely(wdata->header->pnfs_error)) {
 		bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval,
@@ -673,7 +673,7 @@ check_page:
 }
 
 static enum pnfs_try_status
-bl_write_pagelist(struct nfs_write_data *wdata, int sync)
+bl_write_pagelist(struct nfs_pgio_data *wdata, int sync)
 {
 	struct nfs_pgio_header *header = wdata->header;
 	int i, ret, npg_zero, pg_index, last = 0;
@@ -1189,13 +1189,17 @@ bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 		pnfs_generic_pg_init_read(pgio, req);
 }
 
-static bool
+/*
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+static size_t
 bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		struct nfs_page *req)
 {
 	if (pgio->pg_dreq != NULL &&
 	    !is_aligned_req(req, SECTOR_SIZE))
-		return false;
+		return 0;
 
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
@@ -1241,13 +1245,17 @@ bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 	}
 }
 
-static bool
+/*
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+static size_t
 bl_pg_test_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		 struct nfs_page *req)
 {
 	if (pgio->pg_dreq != NULL &&
 	    !is_aligned_req(req, PAGE_CACHE_SIZE))
-		return false;
+		return 0;
 
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index b8797ae6831..f11b9eed0de 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -108,6 +108,97 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
 	return atomic_dec_and_test(&dreq->io_count);
 }
 
+/*
+ * nfs_direct_select_verf - select the right verifier
+ * @dreq - direct request possibly spanning multiple servers
+ * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs
+ * @ds_idx - index of data server in data server list, only valid if ds_clp set
+ *
+ * returns the correct verifier to use given the role of the server
+ */
+static struct nfs_writeverf *
+nfs_direct_select_verf(struct nfs_direct_req *dreq,
+		       struct nfs_client *ds_clp,
+		       int ds_idx)
+{
+	struct nfs_writeverf *verfp = &dreq->verf;
+
+#ifdef CONFIG_NFS_V4_1
+	if (ds_clp) {
+		/* pNFS is in use, use the DS verf */
+		if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets)
+			verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf;
+		else
+			WARN_ON_ONCE(1);
+	}
+#endif
+	return verfp;
+}
+
+
+/*
+ * nfs_direct_set_hdr_verf - set the write/commit verifier
+ * @dreq - direct request possibly spanning multiple servers
+ * @hdr - pageio header to validate against previously seen verfs
+ *
+ * Set the server's (MDS or DS) "seen" verifier
+ */
+static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq,
+				    struct nfs_pgio_header *hdr)
+{
+	struct nfs_writeverf *verfp;
+
+	verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp,
+				      hdr->data->ds_idx);
+	WARN_ON_ONCE(verfp->committed >= 0);
+	memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
+	WARN_ON_ONCE(verfp->committed < 0);
+}
+
+/*
+ * nfs_direct_cmp_hdr_verf - compare verifier for pgio header
+ * @dreq - direct request possibly spanning multiple servers
+ * @hdr - pageio header to validate against previously seen verf
+ *
+ * set the server's "seen" verf if not initialized.
+ * returns result of comparison between @hdr->verf and the "seen"
+ * verf of the server used by @hdr (DS or MDS)
+ */
+static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
+					  struct nfs_pgio_header *hdr)
+{
+	struct nfs_writeverf *verfp;
+
+	verfp = nfs_direct_select_verf(dreq, hdr->data->ds_clp,
+					 hdr->data->ds_idx);
+	if (verfp->committed < 0) {
+		nfs_direct_set_hdr_verf(dreq, hdr);
+		return 0;
+	}
+	return memcmp(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
+}
+
+#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
+/*
+ * nfs_direct_cmp_commit_data_verf - compare verifier for commit data
+ * @dreq - direct request possibly spanning multiple servers
+ * @data - commit data to validate against previously seen verf
+ *
+ * returns result of comparison between @data->verf and the verf of
+ * the server used by @data (DS or MDS)
+ */
+static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
+					   struct nfs_commit_data *data)
+{
+	struct nfs_writeverf *verfp;
+
+	verfp = nfs_direct_select_verf(dreq, data->ds_clp,
+					 data->ds_commit_index);
+	WARN_ON_ONCE(verfp->committed < 0);
+	return memcmp(verfp, &data->verf, sizeof(struct nfs_writeverf));
+}
+#endif
+
 /**
  * nfs_direct_IO - NFS address space operation for direct I/O
  * @rw: direction (read or write)
@@ -121,20 +212,20 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
  * shunt off direct read and write requests before the VFS gets them,
  * so this method is only ever called for swap.
  */
-ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
+ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
 #ifndef CONFIG_NFS_SWAP
 	dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n",
-			iocb->ki_filp, (long long) pos, nr_segs);
+			iocb->ki_filp, (long long) pos, iter->nr_segs);
 
 	return -EINVAL;
 #else
 	VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
 
 	if (rw == READ || rw == KERNEL_READ)
-		return nfs_file_direct_read(iocb, iov, nr_segs, pos,
+		return nfs_file_direct_read(iocb, iter, pos,
 				rw == READ ? true : false);
-	return nfs_file_direct_write(iocb, iov, nr_segs, pos,
+	return nfs_file_direct_write(iocb, iter, pos,
 				rw == WRITE ? true : false);
 #endif /* CONFIG_NFS_SWAP */
 }
@@ -168,6 +259,7 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 	kref_get(&dreq->kref);
 	init_completion(&dreq->completion);
 	INIT_LIST_HEAD(&dreq->mds_cinfo.list);
+	dreq->verf.committed = NFS_INVALID_STABLE_HOW;	/* not set yet */
 	INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
 	spin_lock_init(&dreq->lock);
 
@@ -322,66 +414,42 @@ static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
  * handled automatically by nfs_direct_read_result().  Otherwise, if
  * no requests have been sent, just return an error.
  */
-static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc,
-						const struct iovec *iov,
-						loff_t pos, bool uio)
-{
-	struct nfs_direct_req *dreq = desc->pg_dreq;
-	struct nfs_open_context *ctx = dreq->ctx;
-	struct inode *inode = ctx->dentry->d_inode;
-	unsigned long user_addr = (unsigned long)iov->iov_base;
-	size_t count = iov->iov_len;
-	size_t rsize = NFS_SERVER(inode)->rsize;
-	unsigned int pgbase;
-	int result;
-	ssize_t started = 0;
-	struct page **pagevec = NULL;
-	unsigned int npages;
-
-	do {
-		size_t bytes;
-		int i;
 
-		pgbase = user_addr & ~PAGE_MASK;
-		bytes = min(max_t(size_t, rsize, PAGE_SIZE), count);
+static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
+					      struct iov_iter *iter,
+					      loff_t pos)
+{
+	struct nfs_pageio_descriptor desc;
+	struct inode *inode = dreq->inode;
+	ssize_t result = -EINVAL;
+	size_t requested_bytes = 0;
+	size_t rsize = max_t(size_t, NFS_SERVER(inode)->rsize, PAGE_SIZE);
 
-		result = -ENOMEM;
-		npages = nfs_page_array_len(pgbase, bytes);
-		if (!pagevec)
-			pagevec = kmalloc(npages * sizeof(struct page *),
-					  GFP_KERNEL);
-		if (!pagevec)
-			break;
-		if (uio) {
-			down_read(&current->mm->mmap_sem);
-			result = get_user_pages(current, current->mm, user_addr,
-					npages, 1, 0, pagevec, NULL);
-			up_read(&current->mm->mmap_sem);
-			if (result < 0)
-				break;
-		} else {
-			WARN_ON(npages != 1);
-			result = get_kernel_page(user_addr, 1, pagevec);
-			if (WARN_ON(result != 1))
-				break;
-		}
+	nfs_pageio_init_read(&desc, dreq->inode, false,
+			     &nfs_direct_read_completion_ops);
+	get_dreq(dreq);
+	desc.pg_dreq = dreq;
+	atomic_inc(&inode->i_dio_count);
 
-		if ((unsigned)result < npages) {
-			bytes = result * PAGE_SIZE;
-			if (bytes <= pgbase) {
-				nfs_direct_release_pages(pagevec, result);
-				break;
-			}
-			bytes -= pgbase;
-			npages = result;
-		}
+	while (iov_iter_count(iter)) {
+		struct page **pagevec;
+		size_t bytes;
+		size_t pgbase;
+		unsigned npages, i;
 
+		result = iov_iter_get_pages_alloc(iter, &pagevec, 
+						  rsize, &pgbase);
+		if (result < 0)
+			break;
+	
+		bytes = result;
+		iov_iter_advance(iter, bytes);
+		npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
 		for (i = 0; i < npages; i++) {
 			struct nfs_page *req;
 			unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
 			/* XXX do we need to do the eof zeroing found in async_filler? */
-			req = nfs_create_request(dreq->ctx, dreq->inode,
-						 pagevec[i],
+			req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
 						 pgbase, req_len);
 			if (IS_ERR(req)) {
 				result = PTR_ERR(req);
@@ -389,56 +457,21 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 			}
 			req->wb_index = pos >> PAGE_SHIFT;
 			req->wb_offset = pos & ~PAGE_MASK;
-			if (!nfs_pageio_add_request(desc, req)) {
-				result = desc->pg_error;
+			if (!nfs_pageio_add_request(&desc, req)) {
+				result = desc.pg_error;
 				nfs_release_request(req);
 				break;
 			}
 			pgbase = 0;
 			bytes -= req_len;
-			started += req_len;
-			user_addr += req_len;
+			requested_bytes += req_len;
 			pos += req_len;
-			count -= req_len;
 			dreq->bytes_left -= req_len;
 		}
-		/* The nfs_page now hold references to these pages */
 		nfs_direct_release_pages(pagevec, npages);
-	} while (count != 0 && result >= 0);
-
-	kfree(pagevec);
-
-	if (started)
-		return started;
-	return result < 0 ? (ssize_t) result : -EFAULT;
-}
-
-static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
-					      const struct iovec *iov,
-					      unsigned long nr_segs,
-					      loff_t pos, bool uio)
-{
-	struct nfs_pageio_descriptor desc;
-	struct inode *inode = dreq->inode;
-	ssize_t result = -EINVAL;
-	size_t requested_bytes = 0;
-	unsigned long seg;
-
-	NFS_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode,
-			     &nfs_direct_read_completion_ops);
-	get_dreq(dreq);
-	desc.pg_dreq = dreq;
-	atomic_inc(&inode->i_dio_count);
-
-	for (seg = 0; seg < nr_segs; seg++) {
-		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio);
+		kvfree(pagevec);
 		if (result < 0)
 			break;
-		requested_bytes += result;
-		if ((size_t)result < vec->iov_len)
-			break;
-		pos += vec->iov_len;
 	}
 
 	nfs_pageio_complete(&desc);
@@ -461,8 +494,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 /**
  * nfs_file_direct_read - file direct read operation for NFS files
  * @iocb: target I/O control block
- * @iov: vector of user buffers into which to read data
- * @nr_segs: size of iov vector
+ * @iter: vector of user buffers into which to read data
  * @pos: byte offset in file where reading starts
  *
  * We use this function for direct reads instead of calling
@@ -479,8 +511,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
  * client must read the updated atime from the server back into its
  * cache.
  */
-ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos, bool uio)
+ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
+				loff_t pos, bool uio)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
@@ -488,9 +520,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	struct nfs_direct_req *dreq;
 	struct nfs_lock_context *l_ctx;
 	ssize_t result = -EINVAL;
-	size_t count;
-
-	count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(iter);
 	nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
 
 	dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
@@ -513,7 +543,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 		goto out_unlock;
 
 	dreq->inode = inode;
-	dreq->bytes_left = iov_length(iov, nr_segs);
+	dreq->bytes_left = count;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {
@@ -524,8 +554,8 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	NFS_I(inode)->read_io += iov_length(iov, nr_segs);
-	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
+	NFS_I(inode)->read_io += count;
+	result = nfs_direct_read_schedule_iovec(dreq, iter, pos);
 
 	mutex_unlock(&inode->i_mutex);
 
@@ -564,7 +594,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	dreq->count = 0;
 	get_dreq(dreq);
 
-	NFS_PROTO(dreq->inode)->write_pageio_init(&desc, dreq->inode, FLUSH_STABLE,
+	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 
@@ -603,7 +633,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 		dprintk("NFS: %5u commit failed with error %d.\n",
 			data->task.tk_pid, status);
 		dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
-	} else if (memcmp(&dreq->verf, &data->verf, sizeof(data->verf))) {
+	} else if (nfs_direct_cmp_commit_data_verf(dreq, data)) {
 		dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid);
 		dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
 	}
@@ -681,109 +711,6 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
 }
 #endif
 
-/*
- * NB: Return the value of the first error return code.  Subsequent
- *     errors after the first one are ignored.
- */
-/*
- * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE
- * operation.  If nfs_writedata_alloc() or get_user_pages() fails,
- * bail and stop sending more writes.  Write length accounting is
- * handled automatically by nfs_direct_write_result().  Otherwise, if
- * no requests have been sent, just return an error.
- */
-static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc,
-						 const struct iovec *iov,
-						 loff_t pos, bool uio)
-{
-	struct nfs_direct_req *dreq = desc->pg_dreq;
-	struct nfs_open_context *ctx = dreq->ctx;
-	struct inode *inode = ctx->dentry->d_inode;
-	unsigned long user_addr = (unsigned long)iov->iov_base;
-	size_t count = iov->iov_len;
-	size_t wsize = NFS_SERVER(inode)->wsize;
-	unsigned int pgbase;
-	int result;
-	ssize_t started = 0;
-	struct page **pagevec = NULL;
-	unsigned int npages;
-
-	do {
-		size_t bytes;
-		int i;
-
-		pgbase = user_addr & ~PAGE_MASK;
-		bytes = min(max_t(size_t, wsize, PAGE_SIZE), count);
-
-		result = -ENOMEM;
-		npages = nfs_page_array_len(pgbase, bytes);
-		if (!pagevec)
-			pagevec = kmalloc(npages * sizeof(struct page *), GFP_KERNEL);
-		if (!pagevec)
-			break;
-
-		if (uio) {
-			down_read(&current->mm->mmap_sem);
-			result = get_user_pages(current, current->mm, user_addr,
-						npages, 0, 0, pagevec, NULL);
-			up_read(&current->mm->mmap_sem);
-			if (result < 0)
-				break;
-		} else {
-			WARN_ON(npages != 1);
-			result = get_kernel_page(user_addr, 0, pagevec);
-			if (WARN_ON(result != 1))
-				break;
-		}
-
-		if ((unsigned)result < npages) {
-			bytes = result * PAGE_SIZE;
-			if (bytes <= pgbase) {
-				nfs_direct_release_pages(pagevec, result);
-				break;
-			}
-			bytes -= pgbase;
-			npages = result;
-		}
-
-		for (i = 0; i < npages; i++) {
-			struct nfs_page *req;
-			unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
-
-			req = nfs_create_request(dreq->ctx, dreq->inode,
-						 pagevec[i],
-						 pgbase, req_len);
-			if (IS_ERR(req)) {
-				result = PTR_ERR(req);
-				break;
-			}
-			nfs_lock_request(req);
-			req->wb_index = pos >> PAGE_SHIFT;
-			req->wb_offset = pos & ~PAGE_MASK;
-			if (!nfs_pageio_add_request(desc, req)) {
-				result = desc->pg_error;
-				nfs_unlock_and_release_request(req);
-				break;
-			}
-			pgbase = 0;
-			bytes -= req_len;
-			started += req_len;
-			user_addr += req_len;
-			pos += req_len;
-			count -= req_len;
-			dreq->bytes_left -= req_len;
-		}
-		/* The nfs_page now hold references to these pages */
-		nfs_direct_release_pages(pagevec, npages);
-	} while (count != 0 && result >= 0);
-
-	kfree(pagevec);
-
-	if (started)
-		return started;
-	return result < 0 ? (ssize_t) result : -EFAULT;
-}
-
 static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_direct_req *dreq = hdr->dreq;
@@ -813,13 +740,13 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
 				bit = NFS_IOHDR_NEED_RESCHED;
 			else if (dreq->flags == 0) {
-				memcpy(&dreq->verf, hdr->verf,
-				       sizeof(dreq->verf));
+				nfs_direct_set_hdr_verf(dreq, hdr);
 				bit = NFS_IOHDR_NEED_COMMIT;
 				dreq->flags = NFS_ODIRECT_DO_COMMIT;
 			} else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) {
-				if (memcmp(&dreq->verf, hdr->verf, sizeof(dreq->verf))) {
-					dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+				if (nfs_direct_set_or_cmp_hdr_verf(dreq, hdr)) {
+					dreq->flags =
+						NFS_ODIRECT_RESCHED_WRITES;
 					bit = NFS_IOHDR_NEED_RESCHED;
 				} else
 					bit = NFS_IOHDR_NEED_COMMIT;
@@ -829,6 +756,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	spin_unlock(&dreq->lock);
 
 	while (!list_empty(&hdr->pages)) {
+
 		req = nfs_list_entry(hdr->pages.next);
 		nfs_list_remove_request(req);
 		switch (bit) {
@@ -863,33 +791,77 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
 	.completion = nfs_direct_write_completion,
 };
 
+
+/*
+ * NB: Return the value of the first error return code.  Subsequent
+ *     errors after the first one are ignored.
+ */
+/*
+ * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE
+ * operation.  If nfs_writedata_alloc() or get_user_pages() fails,
+ * bail and stop sending more writes.  Write length accounting is
+ * handled automatically by nfs_direct_write_result().  Otherwise, if
+ * no requests have been sent, just return an error.
+ */
 static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
-					       const struct iovec *iov,
-					       unsigned long nr_segs,
-					       loff_t pos, bool uio)
+					       struct iov_iter *iter,
+					       loff_t pos)
 {
 	struct nfs_pageio_descriptor desc;
 	struct inode *inode = dreq->inode;
 	ssize_t result = 0;
 	size_t requested_bytes = 0;
-	unsigned long seg;
+	size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE);
 
-	NFS_PROTO(inode)->write_pageio_init(&desc, inode, FLUSH_COND_STABLE,
+	nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 	get_dreq(dreq);
 	atomic_inc(&inode->i_dio_count);
 
-	NFS_I(dreq->inode)->write_io += iov_length(iov, nr_segs);
-	for (seg = 0; seg < nr_segs; seg++) {
-		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio);
+	NFS_I(inode)->write_io += iov_iter_count(iter);
+	while (iov_iter_count(iter)) {
+		struct page **pagevec;
+		size_t bytes;
+		size_t pgbase;
+		unsigned npages, i;
+
+		result = iov_iter_get_pages_alloc(iter, &pagevec, 
+						  wsize, &pgbase);
 		if (result < 0)
 			break;
-		requested_bytes += result;
-		if ((size_t)result < vec->iov_len)
+
+		bytes = result;
+		iov_iter_advance(iter, bytes);
+		npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
+		for (i = 0; i < npages; i++) {
+			struct nfs_page *req;
+			unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
+
+			req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
+						 pgbase, req_len);
+			if (IS_ERR(req)) {
+				result = PTR_ERR(req);
+				break;
+			}
+			nfs_lock_request(req);
+			req->wb_index = pos >> PAGE_SHIFT;
+			req->wb_offset = pos & ~PAGE_MASK;
+			if (!nfs_pageio_add_request(&desc, req)) {
+				result = desc.pg_error;
+				nfs_unlock_and_release_request(req);
+				break;
+			}
+			pgbase = 0;
+			bytes -= req_len;
+			requested_bytes += req_len;
+			pos += req_len;
+			dreq->bytes_left -= req_len;
+		}
+		nfs_direct_release_pages(pagevec, npages);
+		kvfree(pagevec);
+		if (result < 0)
 			break;
-		pos += vec->iov_len;
 	}
 	nfs_pageio_complete(&desc);
 
@@ -911,8 +883,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 /**
  * nfs_file_direct_write - file direct write operation for NFS files
  * @iocb: target I/O control block
- * @iov: vector of user buffers from which to write data
- * @nr_segs: size of iov vector
+ * @iter: vector of user buffers from which to write data
  * @pos: byte offset in file where writing starts
  *
  * We use this function for direct writes instead of calling
@@ -930,8 +901,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
  * Note that O_APPEND is not supported for NFS direct writes, as there
  * is no atomic O_APPEND write facility in the NFS protocol.
  */
-ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos, bool uio)
+ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
+				loff_t pos, bool uio)
 {
 	ssize_t result = -EINVAL;
 	struct file *file = iocb->ki_filp;
@@ -940,9 +911,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	struct nfs_direct_req *dreq;
 	struct nfs_lock_context *l_ctx;
 	loff_t end;
-	size_t count;
-
-	count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(iter);
 	end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
 
 	nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
@@ -993,7 +962,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
+	result = nfs_direct_write_schedule_iovec(dreq, iter, pos);
 
 	if (mapping->nrpages) {
 		invalidate_inode_pages2_range(mapping,
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index c1edf733631..524dd80d189 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -165,22 +165,21 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 EXPORT_SYMBOL_GPL(nfs_file_flush);
 
 ssize_t
-nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos)
+nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t result;
 
 	if (iocb->ki_filp->f_flags & O_DIRECT)
-		return nfs_file_direct_read(iocb, iov, nr_segs, pos, true);
+		return nfs_file_direct_read(iocb, to, iocb->ki_pos, true);
 
-	dprintk("NFS: read(%pD2, %lu@%lu)\n",
+	dprintk("NFS: read(%pD2, %zu@%lu)\n",
 		iocb->ki_filp,
-		(unsigned long) iov_length(iov, nr_segs), (unsigned long) pos);
+		iov_iter_count(to), (unsigned long) iocb->ki_pos);
 
 	result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping);
 	if (!result) {
-		result = generic_file_aio_read(iocb, iov, nr_segs, pos);
+		result = generic_file_read_iter(iocb, to);
 		if (result > 0)
 			nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result);
 	}
@@ -362,8 +361,8 @@ start:
 	 * Prevent starvation issues if someone is doing a consistency
 	 * sync-to-disk
 	 */
-	ret = wait_on_bit(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
+	ret = wait_on_bit_action(&NFS_I(mapping->host)->flags, NFS_INO_FLUSHING,
+				 nfs_wait_bit_killable, TASK_KILLABLE);
 	if (ret)
 		return ret;
 
@@ -635,24 +634,24 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode)
 	return 0;
 }
 
-ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
-		       unsigned long nr_segs, loff_t pos)
+ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	unsigned long written = 0;
 	ssize_t result;
-	size_t count = iov_length(iov, nr_segs);
+	size_t count = iov_iter_count(from);
+	loff_t pos = iocb->ki_pos;
 
 	result = nfs_key_timeout_notify(file, inode);
 	if (result)
 		return result;
 
 	if (file->f_flags & O_DIRECT)
-		return nfs_file_direct_write(iocb, iov, nr_segs, pos, true);
+		return nfs_file_direct_write(iocb, from, pos, true);
 
-	dprintk("NFS: write(%pD2, %lu@%Ld)\n",
-		file, (unsigned long) count, (long long) pos);
+	dprintk("NFS: write(%pD2, %zu@%Ld)\n",
+		file, count, (long long) pos);
 
 	result = -EBUSY;
 	if (IS_SWAPFILE(inode))
@@ -670,7 +669,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 	if (!count)
 		goto out;
 
-	result = generic_file_aio_write(iocb, iov, nr_segs, pos);
+	result = generic_file_write_iter(iocb, from);
 	if (result > 0)
 		written = result;
 
@@ -691,36 +690,6 @@ out_swapfile:
 }
 EXPORT_SYMBOL_GPL(nfs_file_write);
 
-ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
-			      struct file *filp, loff_t *ppos,
-			      size_t count, unsigned int flags)
-{
-	struct inode *inode = file_inode(filp);
-	unsigned long written = 0;
-	ssize_t ret;
-
-	dprintk("NFS splice_write(%pD2, %lu@%llu)\n",
-		filp, (unsigned long) count, (unsigned long long) *ppos);
-
-	/*
-	 * The combination of splice and an O_APPEND destination is disallowed.
-	 */
-
-	ret = generic_file_splice_write(pipe, filp, ppos, count, flags);
-	if (ret > 0)
-		written = ret;
-
-	if (ret >= 0 && nfs_need_sync_write(filp, inode)) {
-		int err = vfs_fsync(filp, 0);
-		if (err < 0)
-			ret = err;
-	}
-	if (ret > 0)
-		nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nfs_file_splice_write);
-
 static int
 do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 {
@@ -935,10 +904,10 @@ EXPORT_SYMBOL_GPL(nfs_setlease);
 
 const struct file_operations nfs_file_operations = {
 	.llseek		= nfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= nfs_file_read,
-	.aio_write	= nfs_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= nfs_file_read,
+	.write_iter	= nfs_file_write,
 	.mmap		= nfs_file_mmap,
 	.open		= nfs_file_open,
 	.flush		= nfs_file_flush,
@@ -947,7 +916,7 @@ const struct file_operations nfs_file_operations = {
 	.lock		= nfs_lock,
 	.flock		= nfs_flock,
 	.splice_read	= nfs_file_splice_read,
-	.splice_write	= nfs_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
 	.setlease	= nfs_setlease,
 };
diff --git a/fs/nfs/filelayout/Makefile b/fs/nfs/filelayout/Makefile
new file mode 100644
index 00000000000..8516cdffb9e
--- /dev/null
+++ b/fs/nfs/filelayout/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the pNFS Files Layout Driver kernel module
+#
+obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
+nfs_layout_nfsv41_files-y := filelayout.o filelayoutdev.o
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/filelayout/filelayout.c
index b9a35c05b60..d2eba1c13b7 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -35,11 +35,11 @@
 
 #include <linux/sunrpc/metrics.h>
 
-#include "nfs4session.h"
-#include "internal.h"
-#include "delegation.h"
-#include "nfs4filelayout.h"
-#include "nfs4trace.h"
+#include "../nfs4session.h"
+#include "../internal.h"
+#include "../delegation.h"
+#include "filelayout.h"
+#include "../nfs4trace.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
 
@@ -84,7 +84,7 @@ filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset)
 	BUG();
 }
 
-static void filelayout_reset_write(struct nfs_write_data *data)
+static void filelayout_reset_write(struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 	struct rpc_task *task = &data->task;
@@ -105,7 +105,7 @@ static void filelayout_reset_write(struct nfs_write_data *data)
 	}
 }
 
-static void filelayout_reset_read(struct nfs_read_data *data)
+static void filelayout_reset_read(struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 	struct rpc_task *task = &data->task;
@@ -243,7 +243,7 @@ wait_on_recovery:
 /* NFS_PROTO call done callback routines */
 
 static int filelayout_read_done_cb(struct rpc_task *task,
-				struct nfs_read_data *data)
+				struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 	int err;
@@ -270,7 +270,7 @@ static int filelayout_read_done_cb(struct rpc_task *task,
  * rfc5661 is not clear about which credential should be used.
  */
 static void
-filelayout_set_layoutcommit(struct nfs_write_data *wdata)
+filelayout_set_layoutcommit(struct nfs_pgio_data *wdata)
 {
 	struct nfs_pgio_header *hdr = wdata->header;
 
@@ -279,7 +279,7 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata)
 		return;
 
 	pnfs_set_layoutcommit(wdata);
-	dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
+	dprintk("%s inode %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
 		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
 
@@ -305,7 +305,7 @@ filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
  */
 static void filelayout_read_prepare(struct rpc_task *task, void *data)
 {
-	struct nfs_read_data *rdata = data;
+	struct nfs_pgio_data *rdata = data;
 
 	if (unlikely(test_bit(NFS_CONTEXT_BAD, &rdata->args.context->flags))) {
 		rpc_exit(task, -EIO);
@@ -317,7 +317,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
 		rpc_exit(task, 0);
 		return;
 	}
-	rdata->read_done_cb = filelayout_read_done_cb;
+	rdata->pgio_done_cb = filelayout_read_done_cb;
 
 	if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
 			&rdata->args.seq_args,
@@ -331,7 +331,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
 
 static void filelayout_read_call_done(struct rpc_task *task, void *data)
 {
-	struct nfs_read_data *rdata = data;
+	struct nfs_pgio_data *rdata = data;
 
 	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
 
@@ -347,14 +347,14 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
 
 static void filelayout_read_count_stats(struct rpc_task *task, void *data)
 {
-	struct nfs_read_data *rdata = data;
+	struct nfs_pgio_data *rdata = data;
 
 	rpc_count_iostats(task, NFS_SERVER(rdata->header->inode)->client->cl_metrics);
 }
 
 static void filelayout_read_release(void *data)
 {
-	struct nfs_read_data *rdata = data;
+	struct nfs_pgio_data *rdata = data;
 	struct pnfs_layout_hdr *lo = rdata->header->lseg->pls_layout;
 
 	filelayout_fenceme(lo->plh_inode, lo);
@@ -363,7 +363,7 @@ static void filelayout_read_release(void *data)
 }
 
 static int filelayout_write_done_cb(struct rpc_task *task,
-				struct nfs_write_data *data)
+				struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 	int err;
@@ -419,7 +419,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 
 static void filelayout_write_prepare(struct rpc_task *task, void *data)
 {
-	struct nfs_write_data *wdata = data;
+	struct nfs_pgio_data *wdata = data;
 
 	if (unlikely(test_bit(NFS_CONTEXT_BAD, &wdata->args.context->flags))) {
 		rpc_exit(task, -EIO);
@@ -443,7 +443,7 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
 
 static void filelayout_write_call_done(struct rpc_task *task, void *data)
 {
-	struct nfs_write_data *wdata = data;
+	struct nfs_pgio_data *wdata = data;
 
 	if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) &&
 	    task->tk_status == 0) {
@@ -457,14 +457,14 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
 
 static void filelayout_write_count_stats(struct rpc_task *task, void *data)
 {
-	struct nfs_write_data *wdata = data;
+	struct nfs_pgio_data *wdata = data;
 
 	rpc_count_iostats(task, NFS_SERVER(wdata->header->inode)->client->cl_metrics);
 }
 
 static void filelayout_write_release(void *data)
 {
-	struct nfs_write_data *wdata = data;
+	struct nfs_pgio_data *wdata = data;
 	struct pnfs_layout_hdr *lo = wdata->header->lseg->pls_layout;
 
 	filelayout_fenceme(lo->plh_inode, lo);
@@ -529,7 +529,7 @@ static const struct rpc_call_ops filelayout_commit_call_ops = {
 };
 
 static enum pnfs_try_status
-filelayout_read_pagelist(struct nfs_read_data *data)
+filelayout_read_pagelist(struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 	struct pnfs_layout_segment *lseg = hdr->lseg;
@@ -560,6 +560,7 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	/* No multipath support. Use first DS */
 	atomic_inc(&ds->ds_clp->cl_count);
 	data->ds_clp = ds->ds_clp;
+	data->ds_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
 		data->args.fh = fh;
@@ -568,14 +569,14 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	data->mds_offset = offset;
 
 	/* Perform an asynchronous read to ds */
-	nfs_initiate_read(ds_clnt, data,
-				  &filelayout_read_call_ops, RPC_TASK_SOFTCONN);
+	nfs_initiate_pgio(ds_clnt, data,
+			    &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
 }
 
 /* Perform async writes. */
 static enum pnfs_try_status
-filelayout_write_pagelist(struct nfs_write_data *data, int sync)
+filelayout_write_pagelist(struct nfs_pgio_data *data, int sync)
 {
 	struct nfs_pgio_header *hdr = data->header;
 	struct pnfs_layout_segment *lseg = hdr->lseg;
@@ -600,20 +601,18 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 		__func__, hdr->inode->i_ino, sync, (size_t) data->args.count,
 		offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
 
-	data->write_done_cb = filelayout_write_done_cb;
+	data->pgio_done_cb = filelayout_write_done_cb;
 	atomic_inc(&ds->ds_clp->cl_count);
 	data->ds_clp = ds->ds_clp;
+	data->ds_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
 		data->args.fh = fh;
-	/*
-	 * Get the file offset on the dserver. Set the write offset to
-	 * this offset and save the original offset.
-	 */
+
 	data->args.offset = filelayout_get_dserver_offset(lseg, offset);
 
 	/* Perform an asynchronous write */
-	nfs_initiate_write(ds_clnt, data,
+	nfs_initiate_pgio(ds_clnt, data,
 				    &filelayout_write_call_ops, sync,
 				    RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
@@ -637,7 +636,6 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 	struct nfs4_deviceid_node *d;
 	struct nfs4_file_layout_dsaddr *dsaddr;
 	int status = -EINVAL;
-	struct nfs_server *nfss = NFS_SERVER(lo->plh_inode);
 
 	dprintk("--> %s\n", __func__);
 
@@ -655,7 +653,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 		goto out;
 	}
 
-	if (!fl->stripe_unit || fl->stripe_unit % PAGE_SIZE) {
+	if (!fl->stripe_unit) {
 		dprintk("%s Invalid stripe unit (%u)\n",
 			__func__, fl->stripe_unit);
 		goto out;
@@ -692,12 +690,6 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 		goto out_put;
 	}
 
-	if (fl->stripe_unit % nfss->rsize || fl->stripe_unit % nfss->wsize) {
-		dprintk("%s Stripe unit (%u) not aligned with rsize %u "
-			"wsize %u\n", __func__, fl->stripe_unit, nfss->rsize,
-			nfss->wsize);
-	}
-
 	status = 0;
 out:
 	dprintk("--> %s returns %d\n", __func__, status);
@@ -850,11 +842,15 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
 {
 	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
 	struct pnfs_commit_bucket *buckets;
-	int size;
+	int size, i;
 
 	if (fl->commit_through_mds)
 		return 0;
-	if (cinfo->ds->nbuckets != 0) {
+
+	size = (fl->stripe_type == STRIPE_SPARSE) ?
+		fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
+
+	if (cinfo->ds->nbuckets >= size) {
 		/* This assumes there is only one IOMODE_RW lseg.  What
 		 * we really want to do is have a layout_hdr level
 		 * dictionary of <multipath_list4, fh> keys, each
@@ -864,30 +860,36 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
 		return 0;
 	}
 
-	size = (fl->stripe_type == STRIPE_SPARSE) ?
-		fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
-
 	buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket),
 			  gfp_flags);
 	if (!buckets)
 		return -ENOMEM;
-	else {
-		int i;
+	for (i = 0; i < size; i++) {
+		INIT_LIST_HEAD(&buckets[i].written);
+		INIT_LIST_HEAD(&buckets[i].committing);
+		/* mark direct verifier as unset */
+		buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW;
+	}
 
-		spin_lock(cinfo->lock);
-		if (cinfo->ds->nbuckets != 0)
-			kfree(buckets);
-		else {
-			cinfo->ds->buckets = buckets;
-			cinfo->ds->nbuckets = size;
-			for (i = 0; i < size; i++) {
-				INIT_LIST_HEAD(&buckets[i].written);
-				INIT_LIST_HEAD(&buckets[i].committing);
-			}
-		}
-		spin_unlock(cinfo->lock);
-		return 0;
+	spin_lock(cinfo->lock);
+	if (cinfo->ds->nbuckets >= size)
+		goto out;
+	for (i = 0; i < cinfo->ds->nbuckets; i++) {
+		list_splice(&cinfo->ds->buckets[i].written,
+			    &buckets[i].written);
+		list_splice(&cinfo->ds->buckets[i].committing,
+			    &buckets[i].committing);
+		buckets[i].direct_verf.committed =
+			cinfo->ds->buckets[i].direct_verf.committed;
+		buckets[i].wlseg = cinfo->ds->buckets[i].wlseg;
+		buckets[i].clseg = cinfo->ds->buckets[i].clseg;
 	}
+	swap(cinfo->ds->buckets, buckets);
+	cinfo->ds->nbuckets = size;
+out:
+	spin_unlock(cinfo->lock);
+	kfree(buckets);
+	return 0;
 }
 
 static struct pnfs_layout_segment *
@@ -915,47 +917,51 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 /*
  * filelayout_pg_test(). Called by nfs_can_coalesce_requests()
  *
- * return true  : coalesce page
- * return false : don't coalesce page
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
  */
-static bool
+static size_t
 filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		   struct nfs_page *req)
 {
+	unsigned int size;
 	u64 p_stripe, r_stripe;
-	u32 stripe_unit;
+	u32 stripe_offset;
+	u64 segment_offset = pgio->pg_lseg->pls_range.offset;
+	u32 stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;
 
-	if (!pnfs_generic_pg_test(pgio, prev, req) ||
-	    !nfs_generic_pg_test(pgio, prev, req))
-		return false;
+	/* calls nfs_generic_pg_test */
+	size = pnfs_generic_pg_test(pgio, prev, req);
+	if (!size)
+		return 0;
 
-	p_stripe = (u64)req_offset(prev);
-	r_stripe = (u64)req_offset(req);
-	stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;
+	/* see if req and prev are in the same stripe */
+	if (prev) {
+		p_stripe = (u64)req_offset(prev) - segment_offset;
+		r_stripe = (u64)req_offset(req) - segment_offset;
+		do_div(p_stripe, stripe_unit);
+		do_div(r_stripe, stripe_unit);
 
-	do_div(p_stripe, stripe_unit);
-	do_div(r_stripe, stripe_unit);
+		if (p_stripe != r_stripe)
+			return 0;
+	}
 
-	return (p_stripe == r_stripe);
+	/* calculate remaining bytes in the current stripe */
+	div_u64_rem((u64)req_offset(req) - segment_offset,
+			stripe_unit,
+			&stripe_offset);
+	WARN_ON_ONCE(stripe_offset > stripe_unit);
+	if (stripe_offset >= stripe_unit)
+		return 0;
+	return min(stripe_unit - (unsigned int)stripe_offset, size);
 }
 
 static void
 filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
 {
-	WARN_ON_ONCE(pgio->pg_lseg != NULL);
-
-	if (req->wb_offset != req->wb_pgbase) {
-		/*
-		 * Handling unaligned pages is difficult, because have to
-		 * somehow split a req in two in certain cases in the
-		 * pg.test code.  Avoid this by just not using pnfs
-		 * in this case.
-		 */
-		nfs_pageio_reset_read_mds(pgio);
-		return;
-	}
-	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+	if (!pgio->pg_lseg)
+		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   0,
 					   NFS4_MAX_UINT64,
@@ -973,11 +979,8 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	struct nfs_commit_info cinfo;
 	int status;
 
-	WARN_ON_ONCE(pgio->pg_lseg != NULL);
-
-	if (req->wb_offset != req->wb_pgbase)
-		goto out_mds;
-	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+	if (!pgio->pg_lseg)
+		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   0,
 					   NFS4_MAX_UINT64,
@@ -1067,6 +1070,7 @@ filelayout_choose_commit_list(struct nfs_page *req,
 	 */
 	j = nfs4_fl_calc_j_index(lseg, req_offset(req));
 	i = select_bucket_index(fl, j);
+	spin_lock(cinfo->lock);
 	buckets = cinfo->ds->buckets;
 	list = &buckets[i].written;
 	if (list_empty(list)) {
@@ -1080,6 +1084,7 @@ filelayout_choose_commit_list(struct nfs_page *req,
 	}
 	set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
 	cinfo->ds->nwritten++;
+	spin_unlock(cinfo->lock);
 	return list;
 }
 
@@ -1176,6 +1181,7 @@ transfer_commit_list(struct list_head *src, struct list_head *dst,
 	return ret;
 }
 
+/* Note called with cinfo->lock held. */
 static int
 filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
 			       struct nfs_commit_info *cinfo,
@@ -1220,15 +1226,18 @@ static void filelayout_recover_commit_reqs(struct list_head *dst,
 					   struct nfs_commit_info *cinfo)
 {
 	struct pnfs_commit_bucket *b;
+	struct pnfs_layout_segment *freeme;
 	int i;
 
+restart:
 	spin_lock(cinfo->lock);
 	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
 		if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
-			spin_unlock(cinfo->lock);
-			pnfs_put_lseg(b->wlseg);
+			freeme = b->wlseg;
 			b->wlseg = NULL;
-			spin_lock(cinfo->lock);
+			spin_unlock(cinfo->lock);
+			pnfs_put_lseg(freeme);
+			goto restart;
 		}
 	}
 	cinfo->ds->nwritten = 0;
@@ -1243,6 +1252,7 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
 	struct nfs_commit_data *data;
 	int i, j;
 	unsigned int nreq = 0;
+	struct pnfs_layout_segment *freeme;
 
 	fl_cinfo = cinfo->ds;
 	bucket = fl_cinfo->buckets;
@@ -1253,8 +1263,10 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
 		if (!data)
 			break;
 		data->ds_commit_index = i;
+		spin_lock(cinfo->lock);
 		data->lseg = bucket->clseg;
 		bucket->clseg = NULL;
+		spin_unlock(cinfo->lock);
 		list_add(&data->pages, list);
 		nreq++;
 	}
@@ -1264,8 +1276,11 @@ alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
 		if (list_empty(&bucket->committing))
 			continue;
 		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
-		pnfs_put_lseg(bucket->clseg);
+		spin_lock(cinfo->lock);
+		freeme = bucket->clseg;
 		bucket->clseg = NULL;
+		spin_unlock(cinfo->lock);
+		pnfs_put_lseg(freeme);
 	}
 	/* Caller will clean up entries put on list */
 	return nreq;
@@ -1330,7 +1345,7 @@ filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
 	struct nfs4_filelayout *flo;
 
 	flo = kzalloc(sizeof(*flo), gfp_flags);
-	return &flo->generic_hdr;
+	return flo != NULL ? &flo->generic_hdr : NULL;
 }
 
 static void
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/filelayout/filelayout.h
index cebd20e7e92..ffbddf2219e 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/filelayout/filelayout.h
@@ -30,7 +30,7 @@
 #ifndef FS_NFS_NFS4FILELAYOUT_H
 #define FS_NFS_NFS4FILELAYOUT_H
 
-#include "pnfs.h"
+#include "../pnfs.h"
 
 /*
  * Default data server connection timeout and retrans vaules.
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index b9c61efe966..e2a0361e24c 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -33,9 +33,9 @@
 #include <linux/module.h>
 #include <linux/sunrpc/addr.h>
 
-#include "internal.h"
-#include "nfs4session.h"
-#include "nfs4filelayout.h"
+#include "../internal.h"
+#include "../nfs4session.h"
+#include "filelayout.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
 
@@ -783,8 +783,8 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
 static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
 {
 	might_sleep();
-	wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
+	wait_on_bit_action(&ds->ds_state, NFS4DS_CONNECTING,
+			   nfs_wait_bit_killable, TASK_KILLABLE);
 }
 
 static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 66984a9aafa..b94f80420a5 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -120,7 +120,8 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh,
 
 	security_d_instantiate(ret, inode);
 	spin_lock(&ret->d_lock);
-	if (IS_ROOT(ret) && !(ret->d_flags & DCACHE_NFSFS_RENAMED)) {
+	if (IS_ROOT(ret) && !ret->d_fsdata &&
+	    !(ret->d_flags & DCACHE_NFSFS_RENAMED)) {
 		ret->d_fsdata = name;
 		name = NULL;
 	}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index e6f7398d2b3..abd37a38053 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -75,7 +75,7 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
  * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks
  * @word: long word containing the bit lock
  */
-int nfs_wait_bit_killable(void *word)
+int nfs_wait_bit_killable(struct wait_bit_key *key)
 {
 	if (fatal_signal_pending(current))
 		return -ERESTARTSYS;
@@ -147,6 +147,17 @@ int nfs_sync_mapping(struct address_space *mapping)
 	return ret;
 }
 
+static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	if (inode->i_mapping->nrpages == 0)
+		flags &= ~NFS_INO_INVALID_DATA;
+	nfsi->cache_validity |= flags;
+	if (flags & NFS_INO_INVALID_DATA)
+		nfs_fscache_invalidate(inode);
+}
+
 /*
  * Invalidate the local caches
  */
@@ -162,17 +173,16 @@ static void nfs_zap_caches_locked(struct inode *inode)
 
 	memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf));
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
-		nfs_fscache_invalidate(inode);
-		nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
 					| NFS_INO_INVALID_DATA
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
-					| NFS_INO_REVAL_PAGECACHE;
+					| NFS_INO_REVAL_PAGECACHE);
 	} else
-		nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
 					| NFS_INO_INVALID_ACCESS
 					| NFS_INO_INVALID_ACL
-					| NFS_INO_REVAL_PAGECACHE;
+					| NFS_INO_REVAL_PAGECACHE);
 	nfs_zap_label_cache_locked(nfsi);
 }
 
@@ -187,8 +197,7 @@ void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
 {
 	if (mapping->nrpages != 0) {
 		spin_lock(&inode->i_lock);
-		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
-		nfs_fscache_invalidate(inode);
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
 		spin_unlock(&inode->i_lock);
 	}
 }
@@ -209,7 +218,7 @@ EXPORT_SYMBOL_GPL(nfs_zap_acl_cache);
 void nfs_invalidate_atime(struct inode *inode)
 {
 	spin_lock(&inode->i_lock);
-	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME;
+	nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL_GPL(nfs_invalidate_atime);
@@ -369,7 +378,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		inode->i_mode = fattr->mode;
 		if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0
 				&& nfs_server_capable(inode, NFS_CAP_MODE))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		/* Why so? Because we want revalidate for devices/FIFOs, and
 		 * that's precisely what we have in nfs_file_inode_operations.
 		 */
@@ -415,36 +424,36 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 			inode->i_atime = fattr->atime;
 		else if (nfs_server_capable(inode, NFS_CAP_ATIME))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_MTIME)
 			inode->i_mtime = fattr->mtime;
 		else if (nfs_server_capable(inode, NFS_CAP_MTIME))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_CTIME)
 			inode->i_ctime = fattr->ctime;
 		else if (nfs_server_capable(inode, NFS_CAP_CTIME))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			inode->i_version = fattr->change_attr;
 		else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_SIZE)
 			inode->i_size = nfs_size_to_loff_t(fattr->size);
 		else
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-				| NFS_INO_REVAL_PAGECACHE;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
+				| NFS_INO_REVAL_PAGECACHE);
 		if (fattr->valid & NFS_ATTR_FATTR_NLINK)
 			set_nlink(inode, fattr->nlink);
 		else if (nfs_server_capable(inode, NFS_CAP_NLINK))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_OWNER)
 			inode->i_uid = fattr->uid;
 		else if (nfs_server_capable(inode, NFS_CAP_OWNER))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_GROUP)
 			inode->i_gid = fattr->gid;
 		else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
 			inode->i_blocks = fattr->du.nfs2.blocks;
 		if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
@@ -550,6 +559,9 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset)
 
 	spin_lock(&inode->i_lock);
 	i_size_write(inode, offset);
+	/* Optimisation */
+	if (offset == 0)
+		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA;
 	spin_unlock(&inode->i_lock);
 
 	truncate_pagecache(inode, offset);
@@ -578,7 +590,8 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 			inode->i_uid = attr->ia_uid;
 		if ((attr->ia_valid & ATTR_GID) != 0)
 			inode->i_gid = attr->ia_gid;
-		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
+		nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL);
 		spin_unlock(&inode->i_lock);
 	}
 	if ((attr->ia_valid & ATTR_SIZE) != 0) {
@@ -1061,8 +1074,8 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	 * the bit lock here if it looks like we're going to be doing that.
 	 */
 	for (;;) {
-		ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING,
-				  nfs_wait_bit_killable, TASK_KILLABLE);
+		ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING,
+					 nfs_wait_bit_killable, TASK_KILLABLE);
 		if (ret)
 			goto out;
 		spin_lock(&inode->i_lock);
@@ -1101,7 +1114,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr
 			&& inode->i_version == fattr->pre_change_attr) {
 		inode->i_version = fattr->change_attr;
 		if (S_ISDIR(inode->i_mode))
-			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
 		ret |= NFS_INO_INVALID_ATTR;
 	}
 	/* If we have atomic WCC data, we may update some attributes */
@@ -1117,7 +1130,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr
 			&& timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
 		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
 		if (S_ISDIR(inode->i_mode))
-			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
 		ret |= NFS_INO_INVALID_ATTR;
 	}
 	if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
@@ -1128,9 +1141,6 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr
 		ret |= NFS_INO_INVALID_ATTR;
 	}
 
-	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
-		nfs_fscache_invalidate(inode);
-
 	return ret;
 }
 
@@ -1189,7 +1199,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 		invalid |= NFS_INO_INVALID_ATIME;
 
 	if (invalid != 0)
-		nfsi->cache_validity |= invalid;
+		nfs_set_cache_invalid(inode, invalid);
 
 	nfsi->read_cache_jiffies = fattr->time_start;
 	return 0;
@@ -1402,13 +1412,11 @@ EXPORT_SYMBOL_GPL(nfs_refresh_inode);
 
 static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
+	unsigned long invalid = NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
 
-	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
-	if (S_ISDIR(inode->i_mode)) {
-		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
-		nfs_fscache_invalidate(inode);
-	}
+	if (S_ISDIR(inode->i_mode))
+		invalid |= NFS_INO_INVALID_DATA;
+	nfs_set_cache_invalid(inode, invalid);
 	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
 		return 0;
 	return nfs_refresh_inode_locked(inode, fattr);
@@ -1575,18 +1583,20 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_version = fattr->change_attr;
 		}
 	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
-		invalid |= save_cache_validity;
+		nfsi->cache_validity |= save_cache_validity;
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
 		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
 	} else if (server->caps & NFS_CAP_MTIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
 		memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
 	} else if (server->caps & NFS_CAP_CTIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	/* Check if our cached file size is stale */
@@ -1599,6 +1609,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			if ((nfsi->npages == 0) || new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
 				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
+				invalid &= ~NFS_INO_REVAL_PAGECACHE;
 			}
 			dprintk("NFS: isize change on server for file %s/%ld "
 					"(%Ld to %Ld)\n",
@@ -1608,7 +1619,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 					(long long)new_isize);
 		}
 	} else
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_PAGECACHE
 				| NFS_INO_REVAL_FORCED);
 
@@ -1616,7 +1628,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 		memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
 	else if (server->caps & NFS_CAP_ATIME)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATIME
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_MODE) {
@@ -1627,7 +1640,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 		}
 	} else if (server->caps & NFS_CAP_MODE)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1638,7 +1652,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_uid = fattr->uid;
 		}
 	} else if (server->caps & NFS_CAP_OWNER)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1649,7 +1664,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			inode->i_gid = fattr->gid;
 		}
 	} else if (server->caps & NFS_CAP_OWNER_GROUP)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_ACCESS
 				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
@@ -1662,7 +1678,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			set_nlink(inode, fattr->nlink);
 		}
 	} else if (server->caps & NFS_CAP_NLINK)
-		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+		nfsi->cache_validity |= save_cache_validity &
+				(NFS_INO_INVALID_ATTR
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
@@ -1694,10 +1711,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		invalid &= ~NFS_INO_INVALID_DATA;
 	if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) ||
 			(save_cache_validity & NFS_INO_REVAL_FORCED))
-		nfsi->cache_validity |= invalid;
-
-	if (invalid & NFS_INO_INVALID_DATA)
-		nfs_fscache_invalidate(inode);
+		nfs_set_cache_invalid(inode, invalid);
 
 	return 0;
  out_err:
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index dd8bfc2e246..617f36611d4 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -231,13 +231,21 @@ extern void nfs_destroy_writepagecache(void);
 
 extern int __init nfs_init_directcache(void);
 extern void nfs_destroy_directcache(void);
-extern bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount);
 extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 			      struct nfs_pgio_header *hdr,
 			      void (*release)(struct nfs_pgio_header *hdr));
 void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos);
 int nfs_iocounter_wait(struct nfs_io_counter *c);
 
+extern const struct nfs_pageio_ops nfs_pgio_rw_ops;
+struct nfs_rw_header *nfs_rw_header_alloc(const struct nfs_rw_ops *);
+void nfs_rw_header_free(struct nfs_pgio_header *);
+void nfs_pgio_data_release(struct nfs_pgio_data *);
+int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
+int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_data *,
+		      const struct rpc_call_ops *, int, int);
+void nfs_free_request(struct nfs_page *req);
+
 static inline void nfs_iocounter_init(struct nfs_io_counter *c)
 {
 	c->flags = 0;
@@ -320,16 +328,14 @@ int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *)
 int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int);
 loff_t nfs_file_llseek(struct file *, loff_t, int);
 int nfs_file_flush(struct file *, fl_owner_t);
-ssize_t nfs_file_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+ssize_t nfs_file_read(struct kiocb *, struct iov_iter *);
 ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *,
 			     size_t, unsigned int);
 int nfs_file_mmap(struct file *, struct vm_area_struct *);
-ssize_t nfs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
+ssize_t nfs_file_write(struct kiocb *, struct iov_iter *);
 int nfs_file_release(struct inode *, struct file *);
 int nfs_lock(struct file *, int, struct file_lock *);
 int nfs_flock(struct file *, int, struct file_lock *);
-ssize_t nfs_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *,
-			      size_t, unsigned int);
 int nfs_check_flags(int);
 int nfs_setlease(struct file *, long, struct file_lock **);
 
@@ -342,7 +348,7 @@ extern int nfs_drop_inode(struct inode *);
 extern void nfs_clear_inode(struct inode *);
 extern void nfs_evict_inode(struct inode *);
 void nfs_zap_acl_cache(struct inode *inode);
-extern int nfs_wait_bit_killable(void *word);
+extern int nfs_wait_bit_killable(struct wait_bit_key *key);
 
 /* super.c */
 extern const struct super_operations nfs_sops;
@@ -395,19 +401,11 @@ extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool
 
 struct nfs_pgio_completion_ops;
 /* read.c */
-extern struct nfs_read_header *nfs_readhdr_alloc(void);
-extern void nfs_readhdr_free(struct nfs_pgio_header *hdr);
 extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
-			struct inode *inode,
+			struct inode *inode, bool force_mds,
 			const struct nfs_pgio_completion_ops *compl_ops);
-extern int nfs_initiate_read(struct rpc_clnt *clnt,
-			     struct nfs_read_data *data,
-			     const struct rpc_call_ops *call_ops, int flags);
 extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
-extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
-			      struct nfs_pgio_header *hdr);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
-extern void nfs_readdata_release(struct nfs_read_data *rdata);
 
 /* super.c */
 void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
@@ -422,19 +420,10 @@ int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
 /* write.c */
 extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
-			struct inode *inode, int ioflags,
+			struct inode *inode, int ioflags, bool force_mds,
 			const struct nfs_pgio_completion_ops *compl_ops);
-extern struct nfs_write_header *nfs_writehdr_alloc(void);
-extern void nfs_writehdr_free(struct nfs_pgio_header *hdr);
-extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
-			     struct nfs_pgio_header *hdr);
 extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);
-extern void nfs_writedata_release(struct nfs_write_data *wdata);
 extern void nfs_commit_free(struct nfs_commit_data *p);
-extern int nfs_initiate_write(struct rpc_clnt *clnt,
-			      struct nfs_write_data *data,
-			      const struct rpc_call_ops *call_ops,
-			      int how, int flags);
 extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
 extern void nfs_commit_prepare(struct rpc_task *task, void *calldata);
 extern int nfs_initiate_commit(struct rpc_clnt *clnt,
@@ -447,6 +436,7 @@ extern void nfs_init_commit(struct nfs_commit_data *data,
 			    struct nfs_commit_info *cinfo);
 int nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
 			 struct nfs_commit_info *cinfo, int max);
+unsigned long nfs_reqs_to_commit(struct nfs_commit_info *);
 int nfs_scan_commit(struct inode *inode, struct list_head *dst,
 		    struct nfs_commit_info *cinfo);
 void nfs_mark_request_commit(struct nfs_page *req,
@@ -492,7 +482,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode)
 extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
 
 /* nfs4proc.c */
-extern void __nfs4_read_done_cb(struct nfs_read_data *);
+extern void __nfs4_read_done_cb(struct nfs_pgio_data *);
 extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 			    const struct rpc_timeout *timeparms,
 			    const char *ip_addr);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 62db136339e..5f61b83f4a1 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -103,7 +103,7 @@ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
 /*
  *	typedef opaque	nfsdata<>;
  */
-static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_readres *result)
+static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_pgio_res *result)
 {
 	u32 recvd, count;
 	__be32 *p;
@@ -613,7 +613,7 @@ static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req,
  *	};
  */
 static void encode_readargs(struct xdr_stream *xdr,
-			    const struct nfs_readargs *args)
+			    const struct nfs_pgio_args *args)
 {
 	u32 offset = args->offset;
 	u32 count = args->count;
@@ -629,7 +629,7 @@ static void encode_readargs(struct xdr_stream *xdr,
 
 static void nfs2_xdr_enc_readargs(struct rpc_rqst *req,
 				  struct xdr_stream *xdr,
-				  const struct nfs_readargs *args)
+				  const struct nfs_pgio_args *args)
 {
 	encode_readargs(xdr, args);
 	prepare_reply_buffer(req, args->pages, args->pgbase,
@@ -649,7 +649,7 @@ static void nfs2_xdr_enc_readargs(struct rpc_rqst *req,
  *	};
  */
 static void encode_writeargs(struct xdr_stream *xdr,
-			     const struct nfs_writeargs *args)
+			     const struct nfs_pgio_args *args)
 {
 	u32 offset = args->offset;
 	u32 count = args->count;
@@ -669,7 +669,7 @@ static void encode_writeargs(struct xdr_stream *xdr,
 
 static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   const struct nfs_writeargs *args)
+				   const struct nfs_pgio_args *args)
 {
 	encode_writeargs(xdr, args);
 	xdr->buf->flags |= XDRBUF_WRITE;
@@ -857,7 +857,7 @@ out_default:
  *	};
  */
 static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr,
-				struct nfs_readres *result)
+				struct nfs_pgio_res *result)
 {
 	enum nfs_stat status;
 	int error;
@@ -878,7 +878,7 @@ out_default:
 }
 
 static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 struct nfs_writeres *result)
+				 struct nfs_pgio_res *result)
 {
 	/* All NFSv2 writes are "file sync" writes */
 	result->verf->committed = NFS_FILE_SYNC;
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 871d6eda8db..8f854dde415 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -247,3 +247,46 @@ const struct xattr_handler *nfs3_xattr_handlers[] = {
 	&posix_acl_default_xattr_handler,
 	NULL,
 };
+
+static int
+nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data,
+		size_t size, ssize_t *result)
+{
+	struct posix_acl *acl;
+	char *p = data + *result;
+
+	acl = get_acl(inode, type);
+	if (!acl)
+		return 0;
+
+	posix_acl_release(acl);
+
+	*result += strlen(name);
+	*result += 1;
+	if (!size)
+		return 0;
+	if (*result > size)
+		return -ERANGE;
+
+	strcpy(p, name);
+	return 0;
+}
+
+ssize_t
+nfs3_listxattr(struct dentry *dentry, char *data, size_t size)
+{
+	struct inode *inode = dentry->d_inode;
+	ssize_t result = 0;
+	int error;
+
+	error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS,
+			POSIX_ACL_XATTR_ACCESS, data, size, &result);
+	if (error)
+		return error;
+
+	error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT,
+			POSIX_ACL_XATTR_DEFAULT, data, size, &result);
+	if (error)
+		return error;
+	return result;
+}
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index db60149c457..f0afa291fd5 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -795,7 +795,7 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 	return status;
 }
 
-static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	struct inode *inode = data->header->inode;
 
@@ -807,18 +807,18 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data)
 	return 0;
 }
 
-static void nfs3_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg)
+static void nfs3_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
 {
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_READ];
 }
 
-static int nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs3_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	rpc_call_start(task);
 	return 0;
 }
 
-static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	struct inode *inode = data->header->inode;
 
@@ -829,17 +829,11 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
 	return 0;
 }
 
-static void nfs3_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
+static void nfs3_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
 {
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_WRITE];
 }
 
-static int nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
-{
-	rpc_call_start(task);
-	return 0;
-}
-
 static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
 {
 	rpc_call_start(task);
@@ -891,7 +885,7 @@ static const struct inode_operations nfs3_dir_inode_operations = {
 	.getattr	= nfs_getattr,
 	.setattr	= nfs_setattr,
 #ifdef CONFIG_NFS_V3_ACL
-	.listxattr	= generic_listxattr,
+	.listxattr	= nfs3_listxattr,
 	.getxattr	= generic_getxattr,
 	.setxattr	= generic_setxattr,
 	.removexattr	= generic_removexattr,
@@ -905,7 +899,7 @@ static const struct inode_operations nfs3_file_inode_operations = {
 	.getattr	= nfs_getattr,
 	.setattr	= nfs_setattr,
 #ifdef CONFIG_NFS_V3_ACL
-	.listxattr	= generic_listxattr,
+	.listxattr	= nfs3_listxattr,
 	.getxattr	= generic_getxattr,
 	.setxattr	= generic_setxattr,
 	.removexattr	= generic_removexattr,
@@ -946,13 +940,10 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.fsinfo		= nfs3_proc_fsinfo,
 	.pathconf	= nfs3_proc_pathconf,
 	.decode_dirent	= nfs3_decode_dirent,
+	.pgio_rpc_prepare = nfs3_proc_pgio_rpc_prepare,
 	.read_setup	= nfs3_proc_read_setup,
-	.read_pageio_init = nfs_pageio_init_read,
-	.read_rpc_prepare = nfs3_proc_read_rpc_prepare,
 	.read_done	= nfs3_read_done,
 	.write_setup	= nfs3_proc_write_setup,
-	.write_pageio_init = nfs_pageio_init_write,
-	.write_rpc_prepare = nfs3_proc_write_rpc_prepare,
 	.write_done	= nfs3_write_done,
 	.commit_setup	= nfs3_proc_commit_setup,
 	.commit_rpc_prepare = nfs3_proc_commit_rpc_prepare,
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index fa6d72131c1..8f4cbe7f4aa 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -953,7 +953,7 @@ static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req,
  *	};
  */
 static void encode_read3args(struct xdr_stream *xdr,
-			     const struct nfs_readargs *args)
+			     const struct nfs_pgio_args *args)
 {
 	__be32 *p;
 
@@ -966,7 +966,7 @@ static void encode_read3args(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_read3args(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   const struct nfs_readargs *args)
+				   const struct nfs_pgio_args *args)
 {
 	encode_read3args(xdr, args);
 	prepare_reply_buffer(req, args->pages, args->pgbase,
@@ -992,7 +992,7 @@ static void nfs3_xdr_enc_read3args(struct rpc_rqst *req,
  *	};
  */
 static void encode_write3args(struct xdr_stream *xdr,
-			      const struct nfs_writeargs *args)
+			      const struct nfs_pgio_args *args)
 {
 	__be32 *p;
 
@@ -1008,7 +1008,7 @@ static void encode_write3args(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_write3args(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    const struct nfs_writeargs *args)
+				    const struct nfs_pgio_args *args)
 {
 	encode_write3args(xdr, args);
 	xdr->buf->flags |= XDRBUF_WRITE;
@@ -1589,7 +1589,7 @@ out_default:
  *	};
  */
 static int decode_read3resok(struct xdr_stream *xdr,
-			     struct nfs_readres *result)
+			     struct nfs_pgio_res *result)
 {
 	u32 eof, count, ocount, recvd;
 	__be32 *p;
@@ -1625,7 +1625,7 @@ out_overflow:
 }
 
 static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 struct nfs_readres *result)
+				 struct nfs_pgio_res *result)
 {
 	enum nfs_stat status;
 	int error;
@@ -1673,7 +1673,7 @@ out_status:
  *	};
  */
 static int decode_write3resok(struct xdr_stream *xdr,
-			      struct nfs_writeres *result)
+			      struct nfs_pgio_res *result)
 {
 	__be32 *p;
 
@@ -1697,7 +1697,7 @@ out_eio:
 }
 
 static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
-				  struct nfs_writeres *result)
+				  struct nfs_pgio_res *result)
 {
 	enum nfs_stat status;
 	int error;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index e1d1badbe53..ba2affa5194 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -230,7 +230,7 @@ int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
 extern struct file_system_type nfs4_fs_type;
 
 /* nfs4namespace.c */
-struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *);
+struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *, struct qstr *);
 struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *,
 			       struct nfs_fh *, struct nfs_fattr *);
 int nfs4_replace_transport(struct nfs_server *server,
@@ -337,7 +337,7 @@ nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode,
  */
 static inline void
 nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
-			 struct rpc_message *msg, struct nfs_write_data *wdata)
+			 struct rpc_message *msg, struct nfs_pgio_data *wdata)
 {
 	if (_nfs4_state_protect(clp, NFS_SP4_MACH_CRED_WRITE, clntp, msg) &&
 	    !test_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags))
@@ -369,7 +369,7 @@ nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_flags,
 
 static inline void
 nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
-			 struct rpc_message *msg, struct nfs_write_data *wdata)
+			 struct rpc_message *msg, struct nfs_pgio_data *wdata)
 {
 }
 #endif /* CONFIG_NFS_V4_1 */
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 8de3407e036..a816f0627a6 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -100,8 +100,7 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 			break;
 		mutex_lock(&inode->i_mutex);
 		ret = nfs_file_fsync_commit(file, start, end, datasync);
-		if (!ret && !datasync)
-			/* application has asked for meta-data sync */
+		if (!ret)
 			ret = pnfs_layoutcommit_inode(inode, true);
 		mutex_unlock(&inode->i_mutex);
 		/*
@@ -118,10 +117,10 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 const struct file_operations nfs4_file_operations = {
 	.llseek		= nfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= nfs_file_read,
-	.aio_write	= nfs_file_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= nfs_file_read,
+	.write_iter	= nfs_file_write,
 	.mmap		= nfs_file_mmap,
 	.open		= nfs4_file_open,
 	.flush		= nfs_file_flush,
@@ -130,7 +129,7 @@ const struct file_operations nfs4_file_operations = {
 	.lock		= nfs_lock,
 	.flock		= nfs_flock,
 	.splice_read	= nfs_file_splice_read,
-	.splice_write	= nfs_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.check_flags	= nfs_check_flags,
 	.setlease	= nfs_setlease,
 };
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 3d5dbf80d46..3d83cb1fdc7 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -139,16 +139,22 @@ static size_t nfs_parse_server_name(char *string, size_t len,
  * @server: NFS server struct
  * @flavors: List of security tuples returned by SECINFO procedure
  *
- * Return the pseudoflavor of the first security mechanism in
- * "flavors" that is locally supported.  Return RPC_AUTH_UNIX if
- * no matching flavor is found in the array.  The "flavors" array
+ * Return an rpc client that uses the first security mechanism in
+ * "flavors" that is locally supported.  The "flavors" array
  * is searched in the order returned from the server, per RFC 3530
- * recommendation.
+ * recommendation and each flavor is checked for membership in the
+ * sec= mount option list if it exists.
+ *
+ * Return -EPERM if no matching flavor is found in the array.
+ *
+ * Please call rpc_shutdown_client() when you are done with this rpc client.
+ *
  */
-static rpc_authflavor_t nfs_find_best_sec(struct nfs_server *server,
+static struct rpc_clnt *nfs_find_best_sec(struct rpc_clnt *clnt,
+					  struct nfs_server *server,
 					  struct nfs4_secinfo_flavors *flavors)
 {
-	rpc_authflavor_t pseudoflavor;
+	rpc_authflavor_t pflavor;
 	struct nfs4_secinfo4 *secinfo;
 	unsigned int i;
 
@@ -159,62 +165,73 @@ static rpc_authflavor_t nfs_find_best_sec(struct nfs_server *server,
 		case RPC_AUTH_NULL:
 		case RPC_AUTH_UNIX:
 		case RPC_AUTH_GSS:
-			pseudoflavor = rpcauth_get_pseudoflavor(secinfo->flavor,
+			pflavor = rpcauth_get_pseudoflavor(secinfo->flavor,
 							&secinfo->flavor_info);
-			/* make sure pseudoflavor matches sec= mount opt */
-			if (pseudoflavor != RPC_AUTH_MAXFLAVOR &&
-			    nfs_auth_info_match(&server->auth_info,
-						pseudoflavor))
-				return pseudoflavor;
-			break;
+			/* does the pseudoflavor match a sec= mount opt? */
+			if (pflavor != RPC_AUTH_MAXFLAVOR &&
+			    nfs_auth_info_match(&server->auth_info, pflavor)) {
+				struct rpc_clnt *new;
+				struct rpc_cred *cred;
+
+				/* Cloning creates an rpc_auth for the flavor */
+				new = rpc_clone_client_set_auth(clnt, pflavor);
+				if (IS_ERR(new))
+					continue;
+				/**
+				* Check that the user actually can use the
+				* flavor. This is mostly for RPC_AUTH_GSS
+				* where cr_init obtains a gss context
+				*/
+				cred = rpcauth_lookupcred(new->cl_auth, 0);
+				if (IS_ERR(cred)) {
+					rpc_shutdown_client(new);
+					continue;
+				}
+				put_rpccred(cred);
+				return new;
+			}
 		}
 	}
-
-	/* if there were any sec= options then nothing matched */
-	if (server->auth_info.flavor_len > 0)
-		return -EPERM;
-
-	return RPC_AUTH_UNIX;
+	return ERR_PTR(-EPERM);
 }
 
-static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name)
+/**
+ * nfs4_negotiate_security - in response to an NFS4ERR_WRONGSEC on lookup,
+ * return an rpc_clnt that uses the best available security flavor with
+ * respect to the secinfo flavor list and the sec= mount options.
+ *
+ * @clnt: RPC client to clone
+ * @inode: directory inode
+ * @name: lookup name
+ *
+ * Please call rpc_shutdown_client() when you are done with this rpc client.
+ */
+struct rpc_clnt *
+nfs4_negotiate_security(struct rpc_clnt *clnt, struct inode *inode,
+					struct qstr *name)
 {
 	struct page *page;
 	struct nfs4_secinfo_flavors *flavors;
-	rpc_authflavor_t flavor;
+	struct rpc_clnt *new;
 	int err;
 
 	page = alloc_page(GFP_KERNEL);
 	if (!page)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
+
 	flavors = page_address(page);
 
 	err = nfs4_proc_secinfo(inode, name, flavors);
 	if (err < 0) {
-		flavor = err;
+		new = ERR_PTR(err);
 		goto out;
 	}
 
-	flavor = nfs_find_best_sec(NFS_SERVER(inode), flavors);
+	new = nfs_find_best_sec(clnt, NFS_SERVER(inode), flavors);
 
 out:
 	put_page(page);
-	return flavor;
-}
-
-/*
- * Please call rpc_shutdown_client() when you are done with this client.
- */
-struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *inode,
-					struct qstr *name)
-{
-	rpc_authflavor_t flavor;
-
-	flavor = nfs4_negotiate_security(inode, name);
-	if ((int)flavor < 0)
-		return ERR_PTR((int)flavor);
-
-	return rpc_clone_client_set_auth(clnt, flavor);
+	return new;
 }
 
 static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
@@ -397,11 +414,6 @@ struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry,
 
 	if (client->cl_auth->au_flavor != flavor)
 		flavor = client->cl_auth->au_flavor;
-	else {
-		rpc_authflavor_t new = nfs4_negotiate_security(dir, name);
-		if ((int)new >= 0)
-			flavor = new;
-	}
 	mnt = nfs_do_submount(dentry, fh, fattr, flavor);
 out:
 	rpc_shutdown_client(client);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 397be39c6dc..4bf3d97cc5a 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2027,7 +2027,7 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 			return status;
 	}
 	if (!(o_res->f_attr->valid & NFS_ATTR_FATTR))
-		_nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label);
+		nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label);
 	return 0;
 }
 
@@ -2750,7 +2750,7 @@ static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
 
 #define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL)
 #define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL)
-#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_CHANGE_SECURITY_LABEL - 1UL)
+#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_SECURITY_LABEL - 1UL)
 
 static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
 {
@@ -3247,7 +3247,7 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir,
 			err = -EPERM;
 			if (client != *clnt)
 				goto out;
-			client = nfs4_create_sec_client(client, dir, name);
+			client = nfs4_negotiate_security(client, dir, name);
 			if (IS_ERR(client))
 				return PTR_ERR(client);
 
@@ -4033,12 +4033,12 @@ static bool nfs4_error_stateid_expired(int err)
 	return false;
 }
 
-void __nfs4_read_done_cb(struct nfs_read_data *data)
+void __nfs4_read_done_cb(struct nfs_pgio_data *data)
 {
 	nfs_invalidate_atime(data->header->inode);
 }
 
-static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	struct nfs_server *server = NFS_SERVER(data->header->inode);
 
@@ -4055,7 +4055,7 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
 }
 
 static bool nfs4_read_stateid_changed(struct rpc_task *task,
-		struct nfs_readargs *args)
+		struct nfs_pgio_args *args)
 {
 
 	if (!nfs4_error_stateid_expired(task->tk_status) ||
@@ -4068,7 +4068,7 @@ static bool nfs4_read_stateid_changed(struct rpc_task *task,
 	return true;
 }
 
-static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 
 	dprintk("--> %s\n", __func__);
@@ -4077,19 +4077,19 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
 		return -EAGAIN;
 	if (nfs4_read_stateid_changed(task, &data->args))
 		return -EAGAIN;
-	return data->read_done_cb ? data->read_done_cb(task, data) :
+	return data->pgio_done_cb ? data->pgio_done_cb(task, data) :
 				    nfs4_read_done_cb(task, data);
 }
 
-static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg)
+static void nfs4_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
 {
 	data->timestamp   = jiffies;
-	data->read_done_cb = nfs4_read_done_cb;
+	data->pgio_done_cb = nfs4_read_done_cb;
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
 	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
 }
 
-static int nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs4_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
 			&data->args.seq_args,
@@ -4097,14 +4097,14 @@ static int nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_dat
 			task))
 		return 0;
 	if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
-				data->args.lock_context, FMODE_READ) == -EIO)
+				data->args.lock_context, data->header->rw_ops->rw_mode) == -EIO)
 		return -EIO;
 	if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
 		return -EIO;
 	return 0;
 }
 
-static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	struct inode *inode = data->header->inode;
 	
@@ -4121,7 +4121,7 @@ static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data
 }
 
 static bool nfs4_write_stateid_changed(struct rpc_task *task,
-		struct nfs_writeargs *args)
+		struct nfs_pgio_args *args)
 {
 
 	if (!nfs4_error_stateid_expired(task->tk_status) ||
@@ -4134,18 +4134,18 @@ static bool nfs4_write_stateid_changed(struct rpc_task *task,
 	return true;
 }
 
-static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs4_write_done(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	if (!nfs4_sequence_done(task, &data->res.seq_res))
 		return -EAGAIN;
 	if (nfs4_write_stateid_changed(task, &data->args))
 		return -EAGAIN;
-	return data->write_done_cb ? data->write_done_cb(task, data) :
+	return data->pgio_done_cb ? data->pgio_done_cb(task, data) :
 		nfs4_write_done_cb(task, data);
 }
 
 static
-bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data)
+bool nfs4_write_need_cache_consistency_data(const struct nfs_pgio_data *data)
 {
 	const struct nfs_pgio_header *hdr = data->header;
 
@@ -4158,7 +4158,7 @@ bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data)
 	return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
 }
 
-static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
+static void nfs4_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
 {
 	struct nfs_server *server = NFS_SERVER(data->header->inode);
 
@@ -4168,8 +4168,8 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
 	} else
 		data->args.bitmask = server->cache_consistency_bitmask;
 
-	if (!data->write_done_cb)
-		data->write_done_cb = nfs4_write_done_cb;
+	if (!data->pgio_done_cb)
+		data->pgio_done_cb = nfs4_write_done_cb;
 	data->res.server = server;
 	data->timestamp   = jiffies;
 
@@ -4177,21 +4177,6 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
 	nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
 }
 
-static int nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
-{
-	if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
-			&data->args.seq_args,
-			&data->res.seq_res,
-			task))
-		return 0;
-	if (nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
-				data->args.lock_context, FMODE_WRITE) == -EIO)
-		return -EIO;
-	if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
-		return -EIO;
-	return 0;
-}
-
 static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
 {
 	nfs4_setup_sequence(NFS_SERVER(data->inode),
@@ -8432,13 +8417,10 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.pathconf	= nfs4_proc_pathconf,
 	.set_capabilities = nfs4_server_capabilities,
 	.decode_dirent	= nfs4_decode_dirent,
+	.pgio_rpc_prepare = nfs4_proc_pgio_rpc_prepare,
 	.read_setup	= nfs4_proc_read_setup,
-	.read_pageio_init = pnfs_pageio_init_read,
-	.read_rpc_prepare = nfs4_proc_read_rpc_prepare,
 	.read_done	= nfs4_read_done,
 	.write_setup	= nfs4_proc_write_setup,
-	.write_pageio_init = pnfs_pageio_init_write,
-	.write_rpc_prepare = nfs4_proc_write_rpc_prepare,
 	.write_done	= nfs4_write_done,
 	.commit_setup	= nfs4_proc_commit_setup,
 	.commit_rpc_prepare = nfs4_proc_commit_rpc_prepare,
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index c0583b9bef7..42f12118216 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1251,8 +1251,8 @@ int nfs4_wait_clnt_recover(struct nfs_client *clp)
 	might_sleep();
 
 	atomic_inc(&clp->cl_count);
-	res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
-			nfs_wait_bit_killable, TASK_KILLABLE);
+	res = wait_on_bit_action(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING,
+				 nfs_wait_bit_killable, TASK_KILLABLE);
 	if (res)
 		goto out;
 	if (clp->cl_cons_state < 0)
@@ -1456,7 +1456,7 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 	 * server that doesn't support a grace period.
 	 */
 	spin_lock(&sp->so_lock);
-	write_seqcount_begin(&sp->so_reclaim_seqcount);
+	raw_write_seqcount_begin(&sp->so_reclaim_seqcount);
 restart:
 	list_for_each_entry(state, &sp->so_states, open_states) {
 		if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
@@ -1519,13 +1519,13 @@ restart:
 		spin_lock(&sp->so_lock);
 		goto restart;
 	}
-	write_seqcount_end(&sp->so_reclaim_seqcount);
+	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
 	return 0;
 out_err:
 	nfs4_put_open_state(state);
 	spin_lock(&sp->so_lock);
-	write_seqcount_end(&sp->so_reclaim_seqcount);
+	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
 	return status;
 }
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 849cf146db3..0a744f3a86f 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -932,7 +932,7 @@ DEFINE_NFS4_IDMAP_EVENT(nfs4_map_gid_to_group);
 
 DECLARE_EVENT_CLASS(nfs4_read_event,
 		TP_PROTO(
-			const struct nfs_read_data *data,
+			const struct nfs_pgio_data *data,
 			int error
 		),
 
@@ -972,7 +972,7 @@ DECLARE_EVENT_CLASS(nfs4_read_event,
 #define DEFINE_NFS4_READ_EVENT(name) \
 	DEFINE_EVENT(nfs4_read_event, name, \
 			TP_PROTO( \
-				const struct nfs_read_data *data, \
+				const struct nfs_pgio_data *data, \
 				int error \
 			), \
 			TP_ARGS(data, error))
@@ -983,7 +983,7 @@ DEFINE_NFS4_READ_EVENT(nfs4_pnfs_read);
 
 DECLARE_EVENT_CLASS(nfs4_write_event,
 		TP_PROTO(
-			const struct nfs_write_data *data,
+			const struct nfs_pgio_data *data,
 			int error
 		),
 
@@ -1024,7 +1024,7 @@ DECLARE_EVENT_CLASS(nfs4_write_event,
 #define DEFINE_NFS4_WRITE_EVENT(name) \
 	DEFINE_EVENT(nfs4_write_event, name, \
 			TP_PROTO( \
-				const struct nfs_write_data *data, \
+				const struct nfs_pgio_data *data, \
 				int error \
 			), \
 			TP_ARGS(data, error))
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 73ce8d4fe2c..939ae606cfa 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1556,7 +1556,8 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 	encode_op_hdr(xdr, OP_PUTROOTFH, decode_putrootfh_maxsz, hdr);
 }
 
-static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr)
+static void encode_read(struct xdr_stream *xdr, const struct nfs_pgio_args *args,
+			struct compound_hdr *hdr)
 {
 	__be32 *p;
 
@@ -1701,7 +1702,8 @@ static void encode_setclientid_confirm(struct xdr_stream *xdr, const struct nfs4
 	encode_nfs4_verifier(xdr, &arg->confirm);
 }
 
-static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
+static void encode_write(struct xdr_stream *xdr, const struct nfs_pgio_args *args,
+			 struct compound_hdr *hdr)
 {
 	__be32 *p;
 
@@ -2451,7 +2453,7 @@ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode a READ request
  */
 static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr,
-			      struct nfs_readargs *args)
+			      struct nfs_pgio_args *args)
 {
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
@@ -2513,7 +2515,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode a WRITE request
  */
 static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr,
-			       struct nfs_writeargs *args)
+			       struct nfs_pgio_args *args)
 {
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
@@ -5085,7 +5087,8 @@ static int decode_putrootfh(struct xdr_stream *xdr)
 	return decode_op_hdr(xdr, OP_PUTROOTFH);
 }
 
-static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_readres *res)
+static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req,
+		       struct nfs_pgio_res *res)
 {
 	__be32 *p;
 	uint32_t count, eof, recvd;
@@ -5339,7 +5342,7 @@ static int decode_setclientid_confirm(struct xdr_stream *xdr)
 	return decode_op_hdr(xdr, OP_SETCLIENTID_CONFIRM);
 }
 
-static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res)
+static int decode_write(struct xdr_stream *xdr, struct nfs_pgio_res *res)
 {
 	__be32 *p;
 	int status;
@@ -6636,7 +6639,7 @@ out:
  * Decode Read response
  */
 static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			     struct nfs_readres *res)
+			     struct nfs_pgio_res *res)
 {
 	struct compound_hdr hdr;
 	int status;
@@ -6661,7 +6664,7 @@ out:
  * Decode WRITE response
  */
 static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			      struct nfs_writeres *res)
+			      struct nfs_pgio_res *res)
 {
 	struct compound_hdr hdr;
 	int status;
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 5457745dd4f..611320753db 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -439,7 +439,7 @@ static void _read_done(struct ore_io_state *ios, void *private)
 	objlayout_read_done(&objios->oir, status, objios->sync);
 }
 
-int objio_read_pagelist(struct nfs_read_data *rdata)
+int objio_read_pagelist(struct nfs_pgio_data *rdata)
 {
 	struct nfs_pgio_header *hdr = rdata->header;
 	struct objio_state *objios;
@@ -487,7 +487,7 @@ static void _write_done(struct ore_io_state *ios, void *private)
 static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
 {
 	struct objio_state *objios = priv;
-	struct nfs_write_data *wdata = objios->oir.rpcdata;
+	struct nfs_pgio_data *wdata = objios->oir.rpcdata;
 	struct address_space *mapping = wdata->header->inode->i_mapping;
 	pgoff_t index = offset / PAGE_SIZE;
 	struct page *page;
@@ -531,7 +531,7 @@ static const struct _ore_r4w_op _r4w_op = {
 	.put_page = &__r4w_put_page,
 };
 
-int objio_write_pagelist(struct nfs_write_data *wdata, int how)
+int objio_write_pagelist(struct nfs_pgio_data *wdata, int how)
 {
 	struct nfs_pgio_header *hdr = wdata->header;
 	struct objio_state *objios;
@@ -564,14 +564,22 @@ int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 	return 0;
 }
 
-static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
+/*
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
 			  struct nfs_page *prev, struct nfs_page *req)
 {
-	if (!pnfs_generic_pg_test(pgio, prev, req))
-		return false;
+	unsigned int size;
+
+	size = pnfs_generic_pg_test(pgio, prev, req);
+
+	if (!size || pgio->pg_count + req->wb_bytes >
+	    (unsigned long)pgio->pg_layout_private)
+		return 0;
 
-	return pgio->pg_count + req->wb_bytes <=
-			(unsigned long)pgio->pg_layout_private;
+	return min(size, req->wb_bytes);
 }
 
 static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index e4f9cbfec67..765d3f54e98 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -53,10 +53,10 @@ objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
 	struct objlayout *objlay;
 
 	objlay = kzalloc(sizeof(struct objlayout), gfp_flags);
-	if (objlay) {
-		spin_lock_init(&objlay->lock);
-		INIT_LIST_HEAD(&objlay->err_list);
-	}
+	if (!objlay)
+		return NULL;
+	spin_lock_init(&objlay->lock);
+	INIT_LIST_HEAD(&objlay->err_list);
 	dprintk("%s: Return %p\n", __func__, objlay);
 	return &objlay->pnfs_layout;
 }
@@ -229,11 +229,11 @@ objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index,
 static void _rpc_read_complete(struct work_struct *work)
 {
 	struct rpc_task *task;
-	struct nfs_read_data *rdata;
+	struct nfs_pgio_data *rdata;
 
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
-	rdata = container_of(task, struct nfs_read_data, task);
+	rdata = container_of(task, struct nfs_pgio_data, task);
 
 	pnfs_ld_read_done(rdata);
 }
@@ -241,7 +241,7 @@ static void _rpc_read_complete(struct work_struct *work)
 void
 objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 {
-	struct nfs_read_data *rdata = oir->rpcdata;
+	struct nfs_pgio_data *rdata = oir->rpcdata;
 
 	oir->status = rdata->task.tk_status = status;
 	if (status >= 0)
@@ -266,7 +266,7 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
  * Perform sync or async reads.
  */
 enum pnfs_try_status
-objlayout_read_pagelist(struct nfs_read_data *rdata)
+objlayout_read_pagelist(struct nfs_pgio_data *rdata)
 {
 	struct nfs_pgio_header *hdr = rdata->header;
 	struct inode *inode = hdr->inode;
@@ -312,11 +312,11 @@ objlayout_read_pagelist(struct nfs_read_data *rdata)
 static void _rpc_write_complete(struct work_struct *work)
 {
 	struct rpc_task *task;
-	struct nfs_write_data *wdata;
+	struct nfs_pgio_data *wdata;
 
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
-	wdata = container_of(task, struct nfs_write_data, task);
+	wdata = container_of(task, struct nfs_pgio_data, task);
 
 	pnfs_ld_write_done(wdata);
 }
@@ -324,7 +324,7 @@ static void _rpc_write_complete(struct work_struct *work)
 void
 objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 {
-	struct nfs_write_data *wdata = oir->rpcdata;
+	struct nfs_pgio_data *wdata = oir->rpcdata;
 
 	oir->status = wdata->task.tk_status = status;
 	if (status >= 0) {
@@ -351,7 +351,7 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
  * Perform sync or async writes.
  */
 enum pnfs_try_status
-objlayout_write_pagelist(struct nfs_write_data *wdata,
+objlayout_write_pagelist(struct nfs_pgio_data *wdata,
 			 int how)
 {
 	struct nfs_pgio_header *hdr = wdata->header;
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
index 87aa1dec612..01e041029a6 100644
--- a/fs/nfs/objlayout/objlayout.h
+++ b/fs/nfs/objlayout/objlayout.h
@@ -119,8 +119,8 @@ extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
  */
 extern void objio_free_result(struct objlayout_io_res *oir);
 
-extern int objio_read_pagelist(struct nfs_read_data *rdata);
-extern int objio_write_pagelist(struct nfs_write_data *wdata, int how);
+extern int objio_read_pagelist(struct nfs_pgio_data *rdata);
+extern int objio_write_pagelist(struct nfs_pgio_data *wdata, int how);
 
 /*
  * callback API
@@ -168,10 +168,10 @@ extern struct pnfs_layout_segment *objlayout_alloc_lseg(
 extern void objlayout_free_lseg(struct pnfs_layout_segment *);
 
 extern enum pnfs_try_status objlayout_read_pagelist(
-	struct nfs_read_data *);
+	struct nfs_pgio_data *);
 
 extern enum pnfs_try_status objlayout_write_pagelist(
-	struct nfs_write_data *,
+	struct nfs_pgio_data *,
 	int how);
 
 extern void objlayout_encode_layoutcommit(
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 03ed984ab4d..0be5050638f 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -24,9 +24,12 @@
 #include "internal.h"
 #include "pnfs.h"
 
+#define NFSDBG_FACILITY		NFSDBG_PAGECACHE
+
 static struct kmem_cache *nfs_page_cachep;
+static const struct rpc_call_ops nfs_pgio_common_ops;
 
-bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
+static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
 {
 	p->npages = pagecount;
 	if (pagecount <= ARRAY_SIZE(p->page_array))
@@ -112,7 +115,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c)
 		set_bit(NFS_IO_INPROGRESS, &c->flags);
 		if (atomic_read(&c->io_count) == 0)
 			break;
-		ret = nfs_wait_bit_killable(&c->flags);
+		ret = nfs_wait_bit_killable(&q.key);
 	} while (atomic_read(&c->io_count) != 0);
 	finish_wait(wq, &q.wait);
 	return ret;
@@ -133,11 +136,161 @@ nfs_iocounter_wait(struct nfs_io_counter *c)
 	return __nfs_iocounter_wait(c);
 }
 
+/*
+ * nfs_page_group_lock - lock the head of the page group
+ * @req - request in group that is to be locked
+ *
+ * this lock must be held if modifying the page group list
+ */
+void
+nfs_page_group_lock(struct nfs_page *req)
+{
+	struct nfs_page *head = req->wb_head;
+
+	WARN_ON_ONCE(head != head->wb_head);
+
+	wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
+			TASK_UNINTERRUPTIBLE);
+}
+
+/*
+ * nfs_page_group_unlock - unlock the head of the page group
+ * @req - request in group that is to be unlocked
+ */
+void
+nfs_page_group_unlock(struct nfs_page *req)
+{
+	struct nfs_page *head = req->wb_head;
+
+	WARN_ON_ONCE(head != head->wb_head);
+
+	smp_mb__before_atomic();
+	clear_bit(PG_HEADLOCK, &head->wb_flags);
+	smp_mb__after_atomic();
+	wake_up_bit(&head->wb_flags, PG_HEADLOCK);
+}
+
+/*
+ * nfs_page_group_sync_on_bit_locked
+ *
+ * must be called with page group lock held
+ */
+static bool
+nfs_page_group_sync_on_bit_locked(struct nfs_page *req, unsigned int bit)
+{
+	struct nfs_page *head = req->wb_head;
+	struct nfs_page *tmp;
+
+	WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_flags));
+	WARN_ON_ONCE(test_and_set_bit(bit, &req->wb_flags));
+
+	tmp = req->wb_this_page;
+	while (tmp != req) {
+		if (!test_bit(bit, &tmp->wb_flags))
+			return false;
+		tmp = tmp->wb_this_page;
+	}
+
+	/* true! reset all bits */
+	tmp = req;
+	do {
+		clear_bit(bit, &tmp->wb_flags);
+		tmp = tmp->wb_this_page;
+	} while (tmp != req);
+
+	return true;
+}
+
+/*
+ * nfs_page_group_sync_on_bit - set bit on current request, but only
+ *   return true if the bit is set for all requests in page group
+ * @req - request in page group
+ * @bit - PG_* bit that is used to sync page group
+ */
+bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit)
+{
+	bool ret;
+
+	nfs_page_group_lock(req);
+	ret = nfs_page_group_sync_on_bit_locked(req, bit);
+	nfs_page_group_unlock(req);
+
+	return ret;
+}
+
+/*
+ * nfs_page_group_init - Initialize the page group linkage for @req
+ * @req - a new nfs request
+ * @prev - the previous request in page group, or NULL if @req is the first
+ *         or only request in the group (the head).
+ */
+static inline void
+nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev)
+{
+	WARN_ON_ONCE(prev == req);
+
+	if (!prev) {
+		/* a head request */
+		req->wb_head = req;
+		req->wb_this_page = req;
+	} else {
+		/* a subrequest */
+		WARN_ON_ONCE(prev->wb_this_page != prev->wb_head);
+		WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &prev->wb_head->wb_flags));
+		req->wb_head = prev->wb_head;
+		req->wb_this_page = prev->wb_this_page;
+		prev->wb_this_page = req;
+
+		/* All subrequests take a ref on the head request until
+		 * nfs_page_group_destroy is called */
+		kref_get(&req->wb_head->wb_kref);
+
+		/* grab extra ref if head request has extra ref from
+		 * the write/commit path to handle handoff between write
+		 * and commit lists */
+		if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) {
+			set_bit(PG_INODE_REF, &req->wb_flags);
+			kref_get(&req->wb_kref);
+		}
+	}
+}
+
+/*
+ * nfs_page_group_destroy - sync the destruction of page groups
+ * @req - request that no longer needs the page group
+ *
+ * releases the page group reference from each member once all
+ * members have called this function.
+ */
+static void
+nfs_page_group_destroy(struct kref *kref)
+{
+	struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref);
+	struct nfs_page *tmp, *next;
+
+	/* subrequests must release the ref on the head request */
+	if (req->wb_head != req)
+		nfs_release_request(req->wb_head);
+
+	if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN))
+		return;
+
+	tmp = req;
+	do {
+		next = tmp->wb_this_page;
+		/* unlink and free */
+		tmp->wb_this_page = tmp;
+		tmp->wb_head = tmp;
+		nfs_free_request(tmp);
+		tmp = next;
+	} while (tmp != req);
+}
+
 /**
  * nfs_create_request - Create an NFS read/write request.
  * @ctx: open context to use
- * @inode: inode to which the request is attached
  * @page: page to write
+ * @last: last nfs request created for this page group or NULL if head
  * @offset: starting offset within the page for the write
  * @count: number of bytes to read/write
  *
@@ -146,9 +299,9 @@ nfs_iocounter_wait(struct nfs_io_counter *c)
  * User should ensure it is safe to sleep in this function.
  */
 struct nfs_page *
-nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
-		   struct page *page,
-		   unsigned int offset, unsigned int count)
+nfs_create_request(struct nfs_open_context *ctx, struct page *page,
+		   struct nfs_page *last, unsigned int offset,
+		   unsigned int count)
 {
 	struct nfs_page		*req;
 	struct nfs_lock_context *l_ctx;
@@ -180,6 +333,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 	req->wb_bytes   = count;
 	req->wb_context = get_nfs_open_context(ctx);
 	kref_init(&req->wb_kref);
+	nfs_page_group_init(req, last);
 	return req;
 }
 
@@ -237,16 +391,22 @@ static void nfs_clear_request(struct nfs_page *req)
 	}
 }
 
-
 /**
  * nfs_release_request - Release the count on an NFS read/write request
  * @req: request to release
  *
  * Note: Should never be called with the spinlock held!
  */
-static void nfs_free_request(struct kref *kref)
+void nfs_free_request(struct nfs_page *req)
 {
-	struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref);
+	WARN_ON_ONCE(req->wb_this_page != req);
+
+	/* extra debug: make sure no sync bits are still set */
+	WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags));
+	WARN_ON_ONCE(test_bit(PG_UNLOCKPAGE, &req->wb_flags));
+	WARN_ON_ONCE(test_bit(PG_UPTODATE, &req->wb_flags));
+	WARN_ON_ONCE(test_bit(PG_WB_END, &req->wb_flags));
+	WARN_ON_ONCE(test_bit(PG_REMOVE, &req->wb_flags));
 
 	/* Release struct file and open context */
 	nfs_clear_request(req);
@@ -255,13 +415,7 @@ static void nfs_free_request(struct kref *kref)
 
 void nfs_release_request(struct nfs_page *req)
 {
-	kref_put(&req->wb_kref, nfs_free_request);
-}
-
-static int nfs_wait_bit_uninterruptible(void *word)
-{
-	io_schedule();
-	return 0;
+	kref_put(&req->wb_kref, nfs_page_group_destroy);
 }
 
 /**
@@ -274,27 +428,253 @@ static int nfs_wait_bit_uninterruptible(void *word)
 int
 nfs_wait_on_request(struct nfs_page *req)
 {
-	return wait_on_bit(&req->wb_flags, PG_BUSY,
-			nfs_wait_bit_uninterruptible,
-			TASK_UNINTERRUPTIBLE);
+	return wait_on_bit_io(&req->wb_flags, PG_BUSY,
+			      TASK_UNINTERRUPTIBLE);
 }
 
-bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req)
+/*
+ * nfs_generic_pg_test - determine if requests can be coalesced
+ * @desc: pointer to descriptor
+ * @prev: previous request in desc, or NULL
+ * @req: this request
+ *
+ * Returns zero if @req can be coalesced into @desc, otherwise it returns
+ * the size of the request.
+ */
+size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
+			   struct nfs_page *prev, struct nfs_page *req)
 {
-	/*
-	 * FIXME: ideally we should be able to coalesce all requests
-	 * that are not block boundary aligned, but currently this
-	 * is problematic for the case of bsize < PAGE_CACHE_SIZE,
-	 * since nfs_flush_multi and nfs_pagein_multi assume you
-	 * can have only one struct nfs_page.
-	 */
-	if (desc->pg_bsize < PAGE_SIZE)
+	if (desc->pg_count > desc->pg_bsize) {
+		/* should never happen */
+		WARN_ON_ONCE(1);
 		return 0;
+	}
 
-	return desc->pg_count + req->wb_bytes <= desc->pg_bsize;
+	return min(desc->pg_bsize - desc->pg_count, (size_t)req->wb_bytes);
 }
 EXPORT_SYMBOL_GPL(nfs_generic_pg_test);
 
+static inline struct nfs_rw_header *NFS_RW_HEADER(struct nfs_pgio_header *hdr)
+{
+	return container_of(hdr, struct nfs_rw_header, header);
+}
+
+/**
+ * nfs_rw_header_alloc - Allocate a header for a read or write
+ * @ops: Read or write function vector
+ */
+struct nfs_rw_header *nfs_rw_header_alloc(const struct nfs_rw_ops *ops)
+{
+	struct nfs_rw_header *header = ops->rw_alloc_header();
+
+	if (header) {
+		struct nfs_pgio_header *hdr = &header->header;
+
+		INIT_LIST_HEAD(&hdr->pages);
+		spin_lock_init(&hdr->lock);
+		atomic_set(&hdr->refcnt, 0);
+		hdr->rw_ops = ops;
+	}
+	return header;
+}
+EXPORT_SYMBOL_GPL(nfs_rw_header_alloc);
+
+/*
+ * nfs_rw_header_free - Free a read or write header
+ * @hdr: The header to free
+ */
+void nfs_rw_header_free(struct nfs_pgio_header *hdr)
+{
+	hdr->rw_ops->rw_free_header(NFS_RW_HEADER(hdr));
+}
+EXPORT_SYMBOL_GPL(nfs_rw_header_free);
+
+/**
+ * nfs_pgio_data_alloc - Allocate pageio data
+ * @hdr: The header making a request
+ * @pagecount: Number of pages to create
+ */
+static struct nfs_pgio_data *nfs_pgio_data_alloc(struct nfs_pgio_header *hdr,
+						 unsigned int pagecount)
+{
+	struct nfs_pgio_data *data, *prealloc;
+
+	prealloc = &NFS_RW_HEADER(hdr)->rpc_data;
+	if (prealloc->header == NULL)
+		data = prealloc;
+	else
+		data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out;
+
+	if (nfs_pgarray_set(&data->pages, pagecount)) {
+		data->header = hdr;
+		atomic_inc(&hdr->refcnt);
+	} else {
+		if (data != prealloc)
+			kfree(data);
+		data = NULL;
+	}
+out:
+	return data;
+}
+
+/**
+ * nfs_pgio_data_release - Properly free pageio data
+ * @data: The data to release
+ */
+void nfs_pgio_data_release(struct nfs_pgio_data *data)
+{
+	struct nfs_pgio_header *hdr = data->header;
+	struct nfs_rw_header *pageio_header = NFS_RW_HEADER(hdr);
+
+	put_nfs_open_context(data->args.context);
+	if (data->pages.pagevec != data->pages.page_array)
+		kfree(data->pages.pagevec);
+	if (data == &pageio_header->rpc_data) {
+		data->header = NULL;
+		data = NULL;
+	}
+	if (atomic_dec_and_test(&hdr->refcnt))
+		hdr->completion_ops->completion(hdr);
+	/* Note: we only free the rpc_task after callbacks are done.
+	 * See the comment in rpc_free_task() for why
+	 */
+	kfree(data);
+}
+EXPORT_SYMBOL_GPL(nfs_pgio_data_release);
+
+/**
+ * nfs_pgio_rpcsetup - Set up arguments for a pageio call
+ * @data: The pageio data
+ * @count: Number of bytes to read
+ * @offset: Initial offset
+ * @how: How to commit data (writes only)
+ * @cinfo: Commit information for the call (writes only)
+ */
+static void nfs_pgio_rpcsetup(struct nfs_pgio_data *data,
+			      unsigned int count, unsigned int offset,
+			      int how, struct nfs_commit_info *cinfo)
+{
+	struct nfs_page *req = data->header->req;
+
+	/* Set up the RPC argument and reply structs
+	 * NB: take care not to mess about with data->commit et al. */
+
+	data->args.fh     = NFS_FH(data->header->inode);
+	data->args.offset = req_offset(req) + offset;
+	/* pnfs_set_layoutcommit needs this */
+	data->mds_offset = data->args.offset;
+	data->args.pgbase = req->wb_pgbase + offset;
+	data->args.pages  = data->pages.pagevec;
+	data->args.count  = count;
+	data->args.context = get_nfs_open_context(req->wb_context);
+	data->args.lock_context = req->wb_lock_context;
+	data->args.stable  = NFS_UNSTABLE;
+	switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) {
+	case 0:
+		break;
+	case FLUSH_COND_STABLE:
+		if (nfs_reqs_to_commit(cinfo))
+			break;
+	default:
+		data->args.stable = NFS_FILE_SYNC;
+	}
+
+	data->res.fattr   = &data->fattr;
+	data->res.count   = count;
+	data->res.eof     = 0;
+	data->res.verf    = &data->verf;
+	nfs_fattr_init(&data->fattr);
+}
+
+/**
+ * nfs_pgio_prepare - Prepare pageio data to go over the wire
+ * @task: The current task
+ * @calldata: pageio data to prepare
+ */
+static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs_pgio_data *data = calldata;
+	int err;
+	err = NFS_PROTO(data->header->inode)->pgio_rpc_prepare(task, data);
+	if (err)
+		rpc_exit(task, err);
+}
+
+int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_data *data,
+		      const struct rpc_call_ops *call_ops, int how, int flags)
+{
+	struct rpc_task *task;
+	struct rpc_message msg = {
+		.rpc_argp = &data->args,
+		.rpc_resp = &data->res,
+		.rpc_cred = data->header->cred,
+	};
+	struct rpc_task_setup task_setup_data = {
+		.rpc_client = clnt,
+		.task = &data->task,
+		.rpc_message = &msg,
+		.callback_ops = call_ops,
+		.callback_data = data,
+		.workqueue = nfsiod_workqueue,
+		.flags = RPC_TASK_ASYNC | flags,
+	};
+	int ret = 0;
+
+	data->header->rw_ops->rw_initiate(data, &msg, &task_setup_data, how);
+
+	dprintk("NFS: %5u initiated pgio call "
+		"(req %s/%llu, %u bytes @ offset %llu)\n",
+		data->task.tk_pid,
+		data->header->inode->i_sb->s_id,
+		(unsigned long long)NFS_FILEID(data->header->inode),
+		data->args.count,
+		(unsigned long long)data->args.offset);
+
+	task = rpc_run_task(&task_setup_data);
+	if (IS_ERR(task)) {
+		ret = PTR_ERR(task);
+		goto out;
+	}
+	if (how & FLUSH_SYNC) {
+		ret = rpc_wait_for_completion_task(task);
+		if (ret == 0)
+			ret = task->tk_status;
+	}
+	rpc_put_task(task);
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_initiate_pgio);
+
+/**
+ * nfs_pgio_error - Clean up from a pageio error
+ * @desc: IO descriptor
+ * @hdr: pageio header
+ */
+static int nfs_pgio_error(struct nfs_pageio_descriptor *desc,
+			  struct nfs_pgio_header *hdr)
+{
+	set_bit(NFS_IOHDR_REDO, &hdr->flags);
+	nfs_pgio_data_release(hdr->data);
+	hdr->data = NULL;
+	desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+	return -ENOMEM;
+}
+
+/**
+ * nfs_pgio_release - Release pageio data
+ * @calldata: The pageio data to release
+ */
+static void nfs_pgio_release(void *calldata)
+{
+	struct nfs_pgio_data *data = calldata;
+	if (data->header->rw_ops->rw_release)
+		data->header->rw_ops->rw_release(data);
+	nfs_pgio_data_release(data);
+}
+
 /**
  * nfs_pageio_init - initialise a page io descriptor
  * @desc: pointer to descriptor
@@ -307,6 +687,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 		     struct inode *inode,
 		     const struct nfs_pageio_ops *pg_ops,
 		     const struct nfs_pgio_completion_ops *compl_ops,
+		     const struct nfs_rw_ops *rw_ops,
 		     size_t bsize,
 		     int io_flags)
 {
@@ -320,6 +701,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_inode = inode;
 	desc->pg_ops = pg_ops;
 	desc->pg_completion_ops = compl_ops;
+	desc->pg_rw_ops = rw_ops;
 	desc->pg_ioflags = io_flags;
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
@@ -328,6 +710,94 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init);
 
+/**
+ * nfs_pgio_result - Basic pageio error handling
+ * @task: The task that ran
+ * @calldata: Pageio data to check
+ */
+static void nfs_pgio_result(struct rpc_task *task, void *calldata)
+{
+	struct nfs_pgio_data *data = calldata;
+	struct inode *inode = data->header->inode;
+
+	dprintk("NFS: %s: %5u, (status %d)\n", __func__,
+		task->tk_pid, task->tk_status);
+
+	if (data->header->rw_ops->rw_done(task, data, inode) != 0)
+		return;
+	if (task->tk_status < 0)
+		nfs_set_pgio_error(data->header, task->tk_status, data->args.offset);
+	else
+		data->header->rw_ops->rw_result(task, data);
+}
+
+/*
+ * Create an RPC task for the given read or write request and kick it.
+ * The page must have been locked by the caller.
+ *
+ * It may happen that the page we're passed is not marked dirty.
+ * This is the case if nfs_updatepage detects a conflicting request
+ * that has been written but not committed.
+ */
+int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
+		     struct nfs_pgio_header *hdr)
+{
+	struct nfs_page		*req;
+	struct page		**pages;
+	struct nfs_pgio_data	*data;
+	struct list_head *head = &desc->pg_list;
+	struct nfs_commit_info cinfo;
+
+	data = nfs_pgio_data_alloc(hdr, nfs_page_array_len(desc->pg_base,
+							   desc->pg_count));
+	if (!data)
+		return nfs_pgio_error(desc, hdr);
+
+	nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
+	pages = data->pages.pagevec;
+	while (!list_empty(head)) {
+		req = nfs_list_entry(head->next);
+		nfs_list_remove_request(req);
+		nfs_list_add_request(req, &hdr->pages);
+		*pages++ = req->wb_page;
+	}
+
+	if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
+	    (desc->pg_moreio || nfs_reqs_to_commit(&cinfo)))
+		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
+
+	/* Set up the argument struct */
+	nfs_pgio_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags, &cinfo);
+	hdr->data = data;
+	desc->pg_rpc_callops = &nfs_pgio_common_ops;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nfs_generic_pgio);
+
+static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
+{
+	struct nfs_rw_header *rw_hdr;
+	struct nfs_pgio_header *hdr;
+	int ret;
+
+	rw_hdr = nfs_rw_header_alloc(desc->pg_rw_ops);
+	if (!rw_hdr) {
+		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+		return -ENOMEM;
+	}
+	hdr = &rw_hdr->header;
+	nfs_pgheader_init(desc, hdr, nfs_rw_header_free);
+	atomic_inc(&hdr->refcnt);
+	ret = nfs_generic_pgio(desc, hdr);
+	if (ret == 0)
+		ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
+					hdr->data, desc->pg_rpc_callops,
+					desc->pg_ioflags, 0);
+	if (atomic_dec_and_test(&hdr->refcnt))
+		hdr->completion_ops->completion(hdr);
+	return ret;
+}
+
 static bool nfs_match_open_context(const struct nfs_open_context *ctx1,
 		const struct nfs_open_context *ctx2)
 {
@@ -356,18 +826,23 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 				      struct nfs_page *req,
 				      struct nfs_pageio_descriptor *pgio)
 {
-	if (!nfs_match_open_context(req->wb_context, prev->wb_context))
-		return false;
-	if (req->wb_context->dentry->d_inode->i_flock != NULL &&
-	    !nfs_match_lock_context(req->wb_lock_context, prev->wb_lock_context))
-		return false;
-	if (req->wb_pgbase != 0)
-		return false;
-	if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
-		return false;
-	if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
-		return false;
-	return pgio->pg_ops->pg_test(pgio, prev, req);
+	size_t size;
+
+	if (prev) {
+		if (!nfs_match_open_context(req->wb_context, prev->wb_context))
+			return false;
+		if (req->wb_context->dentry->d_inode->i_flock != NULL &&
+		    !nfs_match_lock_context(req->wb_lock_context,
+					    prev->wb_lock_context))
+			return false;
+		if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
+			return false;
+	}
+	size = pgio->pg_ops->pg_test(pgio, prev, req);
+	WARN_ON_ONCE(size > req->wb_bytes);
+	if (size && size < req->wb_bytes)
+		req->wb_bytes = size;
+	return size > 0;
 }
 
 /**
@@ -381,17 +856,16 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
 				     struct nfs_page *req)
 {
+	struct nfs_page *prev = NULL;
 	if (desc->pg_count != 0) {
-		struct nfs_page *prev;
-
 		prev = nfs_list_entry(desc->pg_list.prev);
-		if (!nfs_can_coalesce_requests(prev, req, desc))
-			return 0;
 	} else {
 		if (desc->pg_ops->pg_init)
 			desc->pg_ops->pg_init(desc, req);
 		desc->pg_base = req->wb_pgbase;
 	}
+	if (!nfs_can_coalesce_requests(prev, req, desc))
+		return 0;
 	nfs_list_remove_request(req);
 	nfs_list_add_request(req, &desc->pg_list);
 	desc->pg_count += req->wb_bytes;
@@ -421,22 +895,72 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
  * @desc: destination io descriptor
  * @req: request
  *
+ * This may split a request into subrequests which are all part of the
+ * same page group.
+ *
  * Returns true if the request 'req' was successfully coalesced into the
  * existing list of pages 'desc'.
  */
 static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			   struct nfs_page *req)
 {
-	while (!nfs_pageio_do_add_request(desc, req)) {
-		desc->pg_moreio = 1;
-		nfs_pageio_doio(desc);
-		if (desc->pg_error < 0)
-			return 0;
-		desc->pg_moreio = 0;
-		if (desc->pg_recoalesce)
-			return 0;
-	}
+	struct nfs_page *subreq;
+	unsigned int bytes_left = 0;
+	unsigned int offset, pgbase;
+
+	nfs_page_group_lock(req);
+
+	subreq = req;
+	bytes_left = subreq->wb_bytes;
+	offset = subreq->wb_offset;
+	pgbase = subreq->wb_pgbase;
+
+	do {
+		if (!nfs_pageio_do_add_request(desc, subreq)) {
+			/* make sure pg_test call(s) did nothing */
+			WARN_ON_ONCE(subreq->wb_bytes != bytes_left);
+			WARN_ON_ONCE(subreq->wb_offset != offset);
+			WARN_ON_ONCE(subreq->wb_pgbase != pgbase);
+
+			nfs_page_group_unlock(req);
+			desc->pg_moreio = 1;
+			nfs_pageio_doio(desc);
+			if (desc->pg_error < 0)
+				return 0;
+			if (desc->pg_recoalesce)
+				return 0;
+			/* retry add_request for this subreq */
+			nfs_page_group_lock(req);
+			continue;
+		}
+
+		/* check for buggy pg_test call(s) */
+		WARN_ON_ONCE(subreq->wb_bytes + subreq->wb_pgbase > PAGE_SIZE);
+		WARN_ON_ONCE(subreq->wb_bytes > bytes_left);
+		WARN_ON_ONCE(subreq->wb_bytes == 0);
+
+		bytes_left -= subreq->wb_bytes;
+		offset += subreq->wb_bytes;
+		pgbase += subreq->wb_bytes;
+
+		if (bytes_left) {
+			subreq = nfs_create_request(req->wb_context,
+					req->wb_page,
+					subreq, pgbase, bytes_left);
+			if (IS_ERR(subreq))
+				goto err_ptr;
+			nfs_lock_request(subreq);
+			subreq->wb_offset  = offset;
+			subreq->wb_index = req->wb_index;
+		}
+	} while (bytes_left > 0);
+
+	nfs_page_group_unlock(req);
 	return 1;
+err_ptr:
+	desc->pg_error = PTR_ERR(subreq);
+	nfs_page_group_unlock(req);
+	return 0;
 }
 
 static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
@@ -449,6 +973,7 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
 		desc->pg_count = 0;
 		desc->pg_base = 0;
 		desc->pg_recoalesce = 0;
+		desc->pg_moreio = 0;
 
 		while (!list_empty(&head)) {
 			struct nfs_page *req;
@@ -535,3 +1060,13 @@ void nfs_destroy_nfspagecache(void)
 	kmem_cache_destroy(nfs_page_cachep);
 }
 
+static const struct rpc_call_ops nfs_pgio_common_ops = {
+	.rpc_call_prepare = nfs_pgio_prepare,
+	.rpc_call_done = nfs_pgio_result,
+	.rpc_release = nfs_pgio_release,
+};
+
+const struct nfs_pageio_ops nfs_pgio_rw_ops = {
+	.pg_test = nfs_generic_pg_test,
+	.pg_doio = nfs_generic_pg_pgios,
+};
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index fd9536e494b..a8914b33561 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1388,11 +1388,6 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 
 	WARN_ON_ONCE(pgio->pg_lseg != NULL);
 
-	if (req->wb_offset != req->wb_pgbase) {
-		nfs_pageio_reset_read_mds(pgio);
-		return;
-	}
-
 	if (pgio->pg_dreq == NULL)
 		rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
 	else
@@ -1417,11 +1412,6 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 {
 	WARN_ON_ONCE(pgio->pg_lseg != NULL);
 
-	if (req->wb_offset != req->wb_pgbase) {
-		nfs_pageio_reset_write_mds(pgio);
-		return;
-	}
-
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   req_offset(req),
@@ -1434,56 +1424,49 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
 
-void
-pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
-		      const struct nfs_pgio_completion_ops *compl_ops)
-{
-	struct nfs_server *server = NFS_SERVER(inode);
-	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
-
-	if (ld == NULL)
-		nfs_pageio_init_read(pgio, inode, compl_ops);
-	else
-		nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, server->rsize, 0);
-}
-
-void
-pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
-		       int ioflags,
-		       const struct nfs_pgio_completion_ops *compl_ops)
-{
-	struct nfs_server *server = NFS_SERVER(inode);
-	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
-
-	if (ld == NULL)
-		nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
-	else
-		nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, server->wsize, ioflags);
-}
-
-bool
+/*
+ * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
+ * of bytes (maximum @req->wb_bytes) that can be coalesced.
+ */
+size_t
 pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		     struct nfs_page *req)
 {
-	if (pgio->pg_lseg == NULL)
-		return nfs_generic_pg_test(pgio, prev, req);
+	unsigned int size;
+	u64 seg_end, req_start, seg_left;
+
+	size = nfs_generic_pg_test(pgio, prev, req);
+	if (!size)
+		return 0;
 
 	/*
-	 * Test if a nfs_page is fully contained in the pnfs_layout_range.
-	 * Note that this test makes several assumptions:
-	 * - that the previous nfs_page in the struct nfs_pageio_descriptor
-	 *   is known to lie within the range.
-	 *   - that the nfs_page being tested is known to be contiguous with the
-	 *   previous nfs_page.
-	 *   - Layout ranges are page aligned, so we only have to test the
-	 *   start offset of the request.
+	 * 'size' contains the number of bytes left in the current page (up
+	 * to the original size asked for in @req->wb_bytes).
+	 *
+	 * Calculate how many bytes are left in the layout segment
+	 * and if there are less bytes than 'size', return that instead.
 	 *
 	 * Please also note that 'end_offset' is actually the offset of the
 	 * first byte that lies outside the pnfs_layout_range. FIXME?
 	 *
 	 */
-	return req_offset(req) < end_offset(pgio->pg_lseg->pls_range.offset,
-					 pgio->pg_lseg->pls_range.length);
+	if (pgio->pg_lseg) {
+		seg_end = end_offset(pgio->pg_lseg->pls_range.offset,
+				     pgio->pg_lseg->pls_range.length);
+		req_start = req_offset(req);
+		WARN_ON_ONCE(req_start > seg_end);
+		/* start of request is past the last byte of this segment */
+		if (req_start >= seg_end)
+			return 0;
+
+		/* adjust 'size' iff there are fewer bytes left in the
+		 * segment than what nfs_generic_pg_test returned */
+		seg_left = seg_end - req_start;
+		if (seg_left < size)
+			size = (unsigned int)seg_left;
+	}
+
+	return size;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
 
@@ -1496,7 +1479,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode,
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
-	nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, compl_ops);
+	nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, true, compl_ops);
 	pgio.pg_dreq = dreq;
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
@@ -1519,7 +1502,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode,
 }
 EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds);
 
-static void pnfs_ld_handle_write_error(struct nfs_write_data *data)
+static void pnfs_ld_handle_write_error(struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 
@@ -1538,7 +1521,7 @@ static void pnfs_ld_handle_write_error(struct nfs_write_data *data)
 /*
  * Called by non rpc-based layout drivers
  */
-void pnfs_ld_write_done(struct nfs_write_data *data)
+void pnfs_ld_write_done(struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 
@@ -1554,7 +1537,7 @@ EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
 
 static void
 pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
-		struct nfs_write_data *data)
+		struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 
@@ -1563,11 +1546,11 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
 		nfs_pageio_reset_write_mds(desc);
 		desc->pg_recoalesce = 1;
 	}
-	nfs_writedata_release(data);
+	nfs_pgio_data_release(data);
 }
 
 static enum pnfs_try_status
-pnfs_try_to_write_data(struct nfs_write_data *wdata,
+pnfs_try_to_write_data(struct nfs_pgio_data *wdata,
 			const struct rpc_call_ops *call_ops,
 			struct pnfs_layout_segment *lseg,
 			int how)
@@ -1589,41 +1572,36 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata,
 }
 
 static void
-pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *head, int how)
+pnfs_do_write(struct nfs_pageio_descriptor *desc,
+	      struct nfs_pgio_header *hdr, int how)
 {
-	struct nfs_write_data *data;
+	struct nfs_pgio_data *data = hdr->data;
 	const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
 	struct pnfs_layout_segment *lseg = desc->pg_lseg;
+	enum pnfs_try_status trypnfs;
 
 	desc->pg_lseg = NULL;
-	while (!list_empty(head)) {
-		enum pnfs_try_status trypnfs;
-
-		data = list_first_entry(head, struct nfs_write_data, list);
-		list_del_init(&data->list);
-
-		trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how);
-		if (trypnfs == PNFS_NOT_ATTEMPTED)
-			pnfs_write_through_mds(desc, data);
-	}
+	trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how);
+	if (trypnfs == PNFS_NOT_ATTEMPTED)
+		pnfs_write_through_mds(desc, data);
 	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
 {
 	pnfs_put_lseg(hdr->lseg);
-	nfs_writehdr_free(hdr);
+	nfs_rw_header_free(hdr);
 }
 EXPORT_SYMBOL_GPL(pnfs_writehdr_free);
 
 int
 pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 {
-	struct nfs_write_header *whdr;
+	struct nfs_rw_header *whdr;
 	struct nfs_pgio_header *hdr;
 	int ret;
 
-	whdr = nfs_writehdr_alloc();
+	whdr = nfs_rw_header_alloc(desc->pg_rw_ops);
 	if (!whdr) {
 		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
 		pnfs_put_lseg(desc->pg_lseg);
@@ -1634,12 +1612,12 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 	nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
 	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	atomic_inc(&hdr->refcnt);
-	ret = nfs_generic_flush(desc, hdr);
+	ret = nfs_generic_pgio(desc, hdr);
 	if (ret != 0) {
 		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 	} else
-		pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags);
+		pnfs_do_write(desc, hdr, desc->pg_ioflags);
 	if (atomic_dec_and_test(&hdr->refcnt))
 		hdr->completion_ops->completion(hdr);
 	return ret;
@@ -1655,7 +1633,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode,
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
-	nfs_pageio_init_read(&pgio, inode, compl_ops);
+	nfs_pageio_init_read(&pgio, inode, true, compl_ops);
 	pgio.pg_dreq = dreq;
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
@@ -1674,7 +1652,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode,
 }
 EXPORT_SYMBOL_GPL(pnfs_read_done_resend_to_mds);
 
-static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
+static void pnfs_ld_handle_read_error(struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 
@@ -1693,7 +1671,7 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
 /*
  * Called by non rpc-based layout drivers
  */
-void pnfs_ld_read_done(struct nfs_read_data *data)
+void pnfs_ld_read_done(struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 
@@ -1709,7 +1687,7 @@ EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
 
 static void
 pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
-		struct nfs_read_data *data)
+		struct nfs_pgio_data *data)
 {
 	struct nfs_pgio_header *hdr = data->header;
 
@@ -1718,14 +1696,14 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
 		nfs_pageio_reset_read_mds(desc);
 		desc->pg_recoalesce = 1;
 	}
-	nfs_readdata_release(data);
+	nfs_pgio_data_release(data);
 }
 
 /*
  * Call the appropriate parallel I/O subsystem read function.
  */
 static enum pnfs_try_status
-pnfs_try_to_read_data(struct nfs_read_data *rdata,
+pnfs_try_to_read_data(struct nfs_pgio_data *rdata,
 		       const struct rpc_call_ops *call_ops,
 		       struct pnfs_layout_segment *lseg)
 {
@@ -1747,41 +1725,35 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata,
 }
 
 static void
-pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *head)
+pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
 {
-	struct nfs_read_data *data;
+	struct nfs_pgio_data *data = hdr->data;
 	const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
 	struct pnfs_layout_segment *lseg = desc->pg_lseg;
+	enum pnfs_try_status trypnfs;
 
 	desc->pg_lseg = NULL;
-	while (!list_empty(head)) {
-		enum pnfs_try_status trypnfs;
-
-		data = list_first_entry(head, struct nfs_read_data, list);
-		list_del_init(&data->list);
-
-		trypnfs = pnfs_try_to_read_data(data, call_ops, lseg);
-		if (trypnfs == PNFS_NOT_ATTEMPTED)
-			pnfs_read_through_mds(desc, data);
-	}
+	trypnfs = pnfs_try_to_read_data(data, call_ops, lseg);
+	if (trypnfs == PNFS_NOT_ATTEMPTED)
+		pnfs_read_through_mds(desc, data);
 	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
 {
 	pnfs_put_lseg(hdr->lseg);
-	nfs_readhdr_free(hdr);
+	nfs_rw_header_free(hdr);
 }
 EXPORT_SYMBOL_GPL(pnfs_readhdr_free);
 
 int
 pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 {
-	struct nfs_read_header *rhdr;
+	struct nfs_rw_header *rhdr;
 	struct nfs_pgio_header *hdr;
 	int ret;
 
-	rhdr = nfs_readhdr_alloc();
+	rhdr = nfs_rw_header_alloc(desc->pg_rw_ops);
 	if (!rhdr) {
 		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
 		ret = -ENOMEM;
@@ -1793,12 +1765,12 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 	nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
 	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	atomic_inc(&hdr->refcnt);
-	ret = nfs_generic_pagein(desc, hdr);
+	ret = nfs_generic_pgio(desc, hdr);
 	if (ret != 0) {
 		pnfs_put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 	} else
-		pnfs_do_multiple_reads(desc, &hdr->rpc_list);
+		pnfs_do_read(desc, hdr);
 	if (atomic_dec_and_test(&hdr->refcnt))
 		hdr->completion_ops->completion(hdr);
 	return ret;
@@ -1848,7 +1820,7 @@ void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
 EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
 
 void
-pnfs_set_layoutcommit(struct nfs_write_data *wdata)
+pnfs_set_layoutcommit(struct nfs_pgio_data *wdata)
 {
 	struct nfs_pgio_header *hdr = wdata->header;
 	struct inode *inode = hdr->inode;
@@ -1913,7 +1885,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) {
 		if (!sync)
 			goto out;
-		status = wait_on_bit_lock(&nfsi->flags,
+		status = wait_on_bit_lock_action(&nfsi->flags,
 				NFS_INO_LAYOUTCOMMITTING,
 				nfs_wait_bit_killable,
 				TASK_KILLABLE);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index c3058a07659..4fb309a2b4c 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -113,8 +113,8 @@ struct pnfs_layoutdriver_type {
 	 * Return PNFS_ATTEMPTED to indicate the layout code has attempted
 	 * I/O, else return PNFS_NOT_ATTEMPTED to fall back to normal NFS
 	 */
-	enum pnfs_try_status (*read_pagelist) (struct nfs_read_data *nfs_data);
-	enum pnfs_try_status (*write_pagelist) (struct nfs_write_data *nfs_data, int how);
+	enum pnfs_try_status (*read_pagelist) (struct nfs_pgio_data *nfs_data);
+	enum pnfs_try_status (*write_pagelist) (struct nfs_pgio_data *nfs_data, int how);
 
 	void (*free_deviceid_node) (struct nfs4_deviceid_node *);
 
@@ -180,11 +180,6 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo);
 void pnfs_put_lseg(struct pnfs_layout_segment *lseg);
 
-void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
-			   const struct nfs_pgio_completion_ops *);
-void pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
-			    int, const struct nfs_pgio_completion_ops *);
-
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
 void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
@@ -192,7 +187,8 @@ int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
 void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			        struct nfs_page *req, u64 wb_size);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
-bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
+size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
+			    struct nfs_page *prev, struct nfs_page *req);
 void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg);
 struct pnfs_layout_segment *pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
@@ -217,13 +213,13 @@ bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task);
-void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
+void pnfs_set_layoutcommit(struct nfs_pgio_data *wdata);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
 int pnfs_commit_and_return_layout(struct inode *);
-void pnfs_ld_write_done(struct nfs_write_data *);
-void pnfs_ld_read_done(struct nfs_read_data *);
+void pnfs_ld_write_done(struct nfs_pgio_data *);
+void pnfs_ld_read_done(struct nfs_pgio_data *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       struct nfs_open_context *ctx,
 					       loff_t pos,
@@ -461,18 +457,6 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline void pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
-					 const struct nfs_pgio_completion_ops *compl_ops)
-{
-	nfs_pageio_init_read(pgio, inode, compl_ops);
-}
-
-static inline void pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
-					  const struct nfs_pgio_completion_ops *compl_ops)
-{
-	nfs_pageio_init_write(pgio, inode, ioflags, compl_ops);
-}
-
 static inline int
 pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how,
 		 struct nfs_commit_info *cinfo)
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index e55ce9e8b03..c171ce1a8a3 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -578,7 +578,7 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 	return 0;
 }
 
-static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs_read_done(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	struct inode *inode = data->header->inode;
 
@@ -594,18 +594,18 @@ static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data)
 	return 0;
 }
 
-static void nfs_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg)
+static void nfs_proc_read_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
 {
 	msg->rpc_proc = &nfs_procedures[NFSPROC_READ];
 }
 
-static int nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs_proc_pgio_rpc_prepare(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	rpc_call_start(task);
 	return 0;
 }
 
-static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_data *data)
 {
 	struct inode *inode = data->header->inode;
 
@@ -614,19 +614,13 @@ static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
 	return 0;
 }
 
-static void nfs_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
+static void nfs_proc_write_setup(struct nfs_pgio_data *data, struct rpc_message *msg)
 {
 	/* Note: NFSv2 ignores @stable and always uses NFS_FILE_SYNC */
 	data->args.stable = NFS_FILE_SYNC;
 	msg->rpc_proc = &nfs_procedures[NFSPROC_WRITE];
 }
 
-static int nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
-{
-	rpc_call_start(task);
-	return 0;
-}
-
 static void nfs_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
 {
 	BUG();
@@ -734,13 +728,10 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.fsinfo		= nfs_proc_fsinfo,
 	.pathconf	= nfs_proc_pathconf,
 	.decode_dirent	= nfs2_decode_dirent,
+	.pgio_rpc_prepare = nfs_proc_pgio_rpc_prepare,
 	.read_setup	= nfs_proc_read_setup,
-	.read_pageio_init = nfs_pageio_init_read,
-	.read_rpc_prepare = nfs_proc_read_rpc_prepare,
 	.read_done	= nfs_read_done,
 	.write_setup	= nfs_proc_write_setup,
-	.write_pageio_init = nfs_pageio_init_write,
-	.write_rpc_prepare = nfs_proc_write_rpc_prepare,
 	.write_done	= nfs_write_done,
 	.commit_setup	= nfs_proc_commit_setup,
 	.commit_rpc_prepare = nfs_proc_commit_rpc_prepare,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 411aedda14b..e818a475ca6 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -24,85 +24,24 @@
 #include "internal.h"
 #include "iostat.h"
 #include "fscache.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
-static const struct nfs_pageio_ops nfs_pageio_read_ops;
-static const struct rpc_call_ops nfs_read_common_ops;
 static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops;
+static const struct nfs_rw_ops nfs_rw_read_ops;
 
 static struct kmem_cache *nfs_rdata_cachep;
 
-struct nfs_read_header *nfs_readhdr_alloc(void)
+static struct nfs_rw_header *nfs_readhdr_alloc(void)
 {
-	struct nfs_read_header *rhdr;
-
-	rhdr = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
-	if (rhdr) {
-		struct nfs_pgio_header *hdr = &rhdr->header;
-
-		INIT_LIST_HEAD(&hdr->pages);
-		INIT_LIST_HEAD(&hdr->rpc_list);
-		spin_lock_init(&hdr->lock);
-		atomic_set(&hdr->refcnt, 0);
-	}
-	return rhdr;
+	return kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
 }
-EXPORT_SYMBOL_GPL(nfs_readhdr_alloc);
 
-static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr,
-						unsigned int pagecount)
+static void nfs_readhdr_free(struct nfs_rw_header *rhdr)
 {
-	struct nfs_read_data *data, *prealloc;
-
-	prealloc = &container_of(hdr, struct nfs_read_header, header)->rpc_data;
-	if (prealloc->header == NULL)
-		data = prealloc;
-	else
-		data = kzalloc(sizeof(*data), GFP_KERNEL);
-	if (!data)
-		goto out;
-
-	if (nfs_pgarray_set(&data->pages, pagecount)) {
-		data->header = hdr;
-		atomic_inc(&hdr->refcnt);
-	} else {
-		if (data != prealloc)
-			kfree(data);
-		data = NULL;
-	}
-out:
-	return data;
-}
-
-void nfs_readhdr_free(struct nfs_pgio_header *hdr)
-{
-	struct nfs_read_header *rhdr = container_of(hdr, struct nfs_read_header, header);
-
 	kmem_cache_free(nfs_rdata_cachep, rhdr);
 }
-EXPORT_SYMBOL_GPL(nfs_readhdr_free);
-
-void nfs_readdata_release(struct nfs_read_data *rdata)
-{
-	struct nfs_pgio_header *hdr = rdata->header;
-	struct nfs_read_header *read_header = container_of(hdr, struct nfs_read_header, header);
-
-	put_nfs_open_context(rdata->args.context);
-	if (rdata->pages.pagevec != rdata->pages.page_array)
-		kfree(rdata->pages.pagevec);
-	if (rdata == &read_header->rpc_data) {
-		rdata->header = NULL;
-		rdata = NULL;
-	}
-	if (atomic_dec_and_test(&hdr->refcnt))
-		hdr->completion_ops->completion(hdr);
-	/* Note: we only free the rpc_task after callbacks are done.
-	 * See the comment in rpc_free_task() for why
-	 */
-	kfree(rdata);
-}
-EXPORT_SYMBOL_GPL(nfs_readdata_release);
 
 static
 int nfs_return_empty_page(struct page *page)
@@ -114,17 +53,24 @@ int nfs_return_empty_page(struct page *page)
 }
 
 void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
-			      struct inode *inode,
+			      struct inode *inode, bool force_mds,
 			      const struct nfs_pgio_completion_ops *compl_ops)
 {
-	nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops,
-			NFS_SERVER(inode)->rsize, 0);
+	struct nfs_server *server = NFS_SERVER(inode);
+	const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops;
+
+#ifdef CONFIG_NFS_V4_1
+	if (server->pnfs_curr_ld && !force_mds)
+		pg_ops = server->pnfs_curr_ld->pg_read_ops;
+#endif
+	nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_read_ops,
+			server->rsize, 0);
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
 
 void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 {
-	pgio->pg_ops = &nfs_pageio_read_ops;
+	pgio->pg_ops = &nfs_pgio_rw_ops;
 	pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->rsize;
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
@@ -139,7 +85,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	len = nfs_page_length(page);
 	if (len == 0)
 		return nfs_return_empty_page(page);
-	new = nfs_create_request(ctx, inode, page, 0, len);
+	new = nfs_create_request(ctx, page, NULL, 0, len);
 	if (IS_ERR(new)) {
 		unlock_page(page);
 		return PTR_ERR(new);
@@ -147,7 +93,8 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	if (len < PAGE_CACHE_SIZE)
 		zero_user_segment(page, len, PAGE_CACHE_SIZE);
 
-	NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
+	nfs_pageio_init_read(&pgio, inode, false,
+			     &nfs_async_read_completion_ops);
 	nfs_pageio_add_request(&pgio, new);
 	nfs_pageio_complete(&pgio);
 	NFS_I(inode)->read_io += pgio.pg_bytes_written;
@@ -158,10 +105,16 @@ static void nfs_readpage_release(struct nfs_page *req)
 {
 	struct inode *d_inode = req->wb_context->dentry->d_inode;
 
-	if (PageUptodate(req->wb_page))
-		nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
+	dprintk("NFS: read done (%s/%llu %d@%lld)\n", d_inode->i_sb->s_id,
+		(unsigned long long)NFS_FILEID(d_inode), req->wb_bytes,
+		(long long)req_offset(req));
 
-	unlock_page(req->wb_page);
+	if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
+		if (PageUptodate(req->wb_page))
+			nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
+
+		unlock_page(req->wb_page);
+	}
 
 	dprintk("NFS: read done (%s/%Lu %d@%Ld)\n",
 			req->wb_context->dentry->d_inode->i_sb->s_id,
@@ -171,7 +124,12 @@ static void nfs_readpage_release(struct nfs_page *req)
 	nfs_release_request(req);
 }
 
-/* Note io was page aligned */
+static void nfs_page_group_set_uptodate(struct nfs_page *req)
+{
+	if (nfs_page_group_sync_on_bit(req, PG_UPTODATE))
+		SetPageUptodate(req->wb_page);
+}
+
 static void nfs_read_completion(struct nfs_pgio_header *hdr)
 {
 	unsigned long bytes = 0;
@@ -181,21 +139,32 @@ static void nfs_read_completion(struct nfs_pgio_header *hdr)
 	while (!list_empty(&hdr->pages)) {
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 		struct page *page = req->wb_page;
+		unsigned long start = req->wb_pgbase;
+		unsigned long end = req->wb_pgbase + req->wb_bytes;
 
 		if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) {
-			if (bytes > hdr->good_bytes)
-				zero_user(page, 0, PAGE_SIZE);
-			else if (hdr->good_bytes - bytes < PAGE_SIZE)
-				zero_user_segment(page,
-					hdr->good_bytes & ~PAGE_MASK,
-					PAGE_SIZE);
+			/* note: regions of the page not covered by a
+			 * request are zeroed in nfs_readpage_async /
+			 * readpage_async_filler */
+			if (bytes > hdr->good_bytes) {
+				/* nothing in this request was good, so zero
+				 * the full extent of the request */
+				zero_user_segment(page, start, end);
+
+			} else if (hdr->good_bytes - bytes < req->wb_bytes) {
+				/* part of this request has good bytes, but
+				 * not all. zero the bad bytes */
+				start += hdr->good_bytes - bytes;
+				WARN_ON(start < req->wb_pgbase);
+				zero_user_segment(page, start, end);
+			}
 		}
 		bytes += req->wb_bytes;
 		if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
 			if (bytes <= hdr->good_bytes)
-				SetPageUptodate(page);
+				nfs_page_group_set_uptodate(req);
 		} else
-			SetPageUptodate(page);
+			nfs_page_group_set_uptodate(req);
 		nfs_list_remove_request(req);
 		nfs_readpage_release(req);
 	}
@@ -203,95 +172,14 @@ out:
 	hdr->release(hdr);
 }
 
-int nfs_initiate_read(struct rpc_clnt *clnt,
-		      struct nfs_read_data *data,
-		      const struct rpc_call_ops *call_ops, int flags)
+static void nfs_initiate_read(struct nfs_pgio_data *data, struct rpc_message *msg,
+			      struct rpc_task_setup *task_setup_data, int how)
 {
 	struct inode *inode = data->header->inode;
 	int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
-	struct rpc_task *task;
-	struct rpc_message msg = {
-		.rpc_argp = &data->args,
-		.rpc_resp = &data->res,
-		.rpc_cred = data->header->cred,
-	};
-	struct rpc_task_setup task_setup_data = {
-		.task = &data->task,
-		.rpc_client = clnt,
-		.rpc_message = &msg,
-		.callback_ops = call_ops,
-		.callback_data = data,
-		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC | swap_flags | flags,
-	};
 
-	/* Set up the initial task struct. */
-	NFS_PROTO(inode)->read_setup(data, &msg);
-
-	dprintk("NFS: %5u initiated read call (req %s/%llu, %u bytes @ "
-			"offset %llu)\n",
-			data->task.tk_pid,
-			inode->i_sb->s_id,
-			(unsigned long long)NFS_FILEID(inode),
-			data->args.count,
-			(unsigned long long)data->args.offset);
-
-	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task))
-		return PTR_ERR(task);
-	rpc_put_task(task);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(nfs_initiate_read);
-
-/*
- * Set up the NFS read request struct
- */
-static void nfs_read_rpcsetup(struct nfs_read_data *data,
-		unsigned int count, unsigned int offset)
-{
-	struct nfs_page *req = data->header->req;
-
-	data->args.fh     = NFS_FH(data->header->inode);
-	data->args.offset = req_offset(req) + offset;
-	data->args.pgbase = req->wb_pgbase + offset;
-	data->args.pages  = data->pages.pagevec;
-	data->args.count  = count;
-	data->args.context = get_nfs_open_context(req->wb_context);
-	data->args.lock_context = req->wb_lock_context;
-
-	data->res.fattr   = &data->fattr;
-	data->res.count   = count;
-	data->res.eof     = 0;
-	nfs_fattr_init(&data->fattr);
-}
-
-static int nfs_do_read(struct nfs_read_data *data,
-		const struct rpc_call_ops *call_ops)
-{
-	struct inode *inode = data->header->inode;
-
-	return nfs_initiate_read(NFS_CLIENT(inode), data, call_ops, 0);
-}
-
-static int
-nfs_do_multiple_reads(struct list_head *head,
-		const struct rpc_call_ops *call_ops)
-{
-	struct nfs_read_data *data;
-	int ret = 0;
-
-	while (!list_empty(head)) {
-		int ret2;
-
-		data = list_first_entry(head, struct nfs_read_data, list);
-		list_del_init(&data->list);
-
-		ret2 = nfs_do_read(data, call_ops);
-		if (ret == 0)
-			ret = ret2;
-	}
-	return ret;
+	task_setup_data->flags |= swap_flags;
+	NFS_PROTO(inode)->read_setup(data, msg);
 }
 
 static void
@@ -311,143 +199,14 @@ static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = {
 	.completion = nfs_read_completion,
 };
 
-static void nfs_pagein_error(struct nfs_pageio_descriptor *desc,
-		struct nfs_pgio_header *hdr)
-{
-	set_bit(NFS_IOHDR_REDO, &hdr->flags);
-	while (!list_empty(&hdr->rpc_list)) {
-		struct nfs_read_data *data = list_first_entry(&hdr->rpc_list,
-				struct nfs_read_data, list);
-		list_del(&data->list);
-		nfs_readdata_release(data);
-	}
-	desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-}
-
-/*
- * Generate multiple requests to fill a single page.
- *
- * We optimize to reduce the number of read operations on the wire.  If we
- * detect that we're reading a page, or an area of a page, that is past the
- * end of file, we do not generate NFS read operations but just clear the
- * parts of the page that would have come back zero from the server anyway.
- *
- * We rely on the cached value of i_size to make this determination; another
- * client can fill pages on the server past our cached end-of-file, but we
- * won't see the new data until our attribute cache is updated.  This is more
- * or less conventional NFS client behavior.
- */
-static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc,
-			    struct nfs_pgio_header *hdr)
-{
-	struct nfs_page *req = hdr->req;
-	struct page *page = req->wb_page;
-	struct nfs_read_data *data;
-	size_t rsize = desc->pg_bsize, nbytes;
-	unsigned int offset;
-
-	offset = 0;
-	nbytes = desc->pg_count;
-	do {
-		size_t len = min(nbytes,rsize);
-
-		data = nfs_readdata_alloc(hdr, 1);
-		if (!data) {
-			nfs_pagein_error(desc, hdr);
-			return -ENOMEM;
-		}
-		data->pages.pagevec[0] = page;
-		nfs_read_rpcsetup(data, len, offset);
-		list_add(&data->list, &hdr->rpc_list);
-		nbytes -= len;
-		offset += len;
-	} while (nbytes != 0);
-
-	nfs_list_remove_request(req);
-	nfs_list_add_request(req, &hdr->pages);
-	desc->pg_rpc_callops = &nfs_read_common_ops;
-	return 0;
-}
-
-static int nfs_pagein_one(struct nfs_pageio_descriptor *desc,
-			  struct nfs_pgio_header *hdr)
-{
-	struct nfs_page		*req;
-	struct page		**pages;
-	struct nfs_read_data    *data;
-	struct list_head *head = &desc->pg_list;
-
-	data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base,
-							  desc->pg_count));
-	if (!data) {
-		nfs_pagein_error(desc, hdr);
-		return -ENOMEM;
-	}
-
-	pages = data->pages.pagevec;
-	while (!list_empty(head)) {
-		req = nfs_list_entry(head->next);
-		nfs_list_remove_request(req);
-		nfs_list_add_request(req, &hdr->pages);
-		*pages++ = req->wb_page;
-	}
-
-	nfs_read_rpcsetup(data, desc->pg_count, 0);
-	list_add(&data->list, &hdr->rpc_list);
-	desc->pg_rpc_callops = &nfs_read_common_ops;
-	return 0;
-}
-
-int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
-		       struct nfs_pgio_header *hdr)
-{
-	if (desc->pg_bsize < PAGE_CACHE_SIZE)
-		return nfs_pagein_multi(desc, hdr);
-	return nfs_pagein_one(desc, hdr);
-}
-EXPORT_SYMBOL_GPL(nfs_generic_pagein);
-
-static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
-{
-	struct nfs_read_header *rhdr;
-	struct nfs_pgio_header *hdr;
-	int ret;
-
-	rhdr = nfs_readhdr_alloc();
-	if (!rhdr) {
-		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-		return -ENOMEM;
-	}
-	hdr = &rhdr->header;
-	nfs_pgheader_init(desc, hdr, nfs_readhdr_free);
-	atomic_inc(&hdr->refcnt);
-	ret = nfs_generic_pagein(desc, hdr);
-	if (ret == 0)
-		ret = nfs_do_multiple_reads(&hdr->rpc_list,
-					    desc->pg_rpc_callops);
-	if (atomic_dec_and_test(&hdr->refcnt))
-		hdr->completion_ops->completion(hdr);
-	return ret;
-}
-
-static const struct nfs_pageio_ops nfs_pageio_read_ops = {
-	.pg_test = nfs_generic_pg_test,
-	.pg_doio = nfs_generic_pg_readpages,
-};
-
 /*
  * This is the callback from RPC telling us whether a reply was
  * received or some error occurred (timeout or socket shutdown).
  */
-int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
+static int nfs_readpage_done(struct rpc_task *task, struct nfs_pgio_data *data,
+			     struct inode *inode)
 {
-	struct inode *inode = data->header->inode;
-	int status;
-
-	dprintk("NFS: %s: %5u, (status %d)\n", __func__, task->tk_pid,
-			task->tk_status);
-
-	status = NFS_PROTO(inode)->read_done(task, data);
+	int status = NFS_PROTO(inode)->read_done(task, data);
 	if (status != 0)
 		return status;
 
@@ -460,10 +219,10 @@ int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
 	return 0;
 }
 
-static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data)
+static void nfs_readpage_retry(struct rpc_task *task, struct nfs_pgio_data *data)
 {
-	struct nfs_readargs *argp = &data->args;
-	struct nfs_readres *resp = &data->res;
+	struct nfs_pgio_args *argp = &data->args;
+	struct nfs_pgio_res  *resp = &data->res;
 
 	/* This is a short read! */
 	nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD);
@@ -480,17 +239,11 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data
 	rpc_restart_call_prepare(task);
 }
 
-static void nfs_readpage_result_common(struct rpc_task *task, void *calldata)
+static void nfs_readpage_result(struct rpc_task *task, struct nfs_pgio_data *data)
 {
-	struct nfs_read_data *data = calldata;
 	struct nfs_pgio_header *hdr = data->header;
 
-	/* Note the only returns of nfs_readpage_result are 0 and -EAGAIN */
-	if (nfs_readpage_result(task, data) != 0)
-		return;
-	if (task->tk_status < 0)
-		nfs_set_pgio_error(hdr, task->tk_status, data->args.offset);
-	else if (data->res.eof) {
+	if (data->res.eof) {
 		loff_t bound;
 
 		bound = data->args.offset + data->res.count;
@@ -505,26 +258,6 @@ static void nfs_readpage_result_common(struct rpc_task *task, void *calldata)
 		nfs_readpage_retry(task, data);
 }
 
-static void nfs_readpage_release_common(void *calldata)
-{
-	nfs_readdata_release(calldata);
-}
-
-void nfs_read_prepare(struct rpc_task *task, void *calldata)
-{
-	struct nfs_read_data *data = calldata;
-	int err;
-	err = NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data);
-	if (err)
-		rpc_exit(task, err);
-}
-
-static const struct rpc_call_ops nfs_read_common_ops = {
-	.rpc_call_prepare = nfs_read_prepare,
-	.rpc_call_done = nfs_readpage_result_common,
-	.rpc_release = nfs_readpage_release_common,
-};
-
 /*
  * Read a page over NFS.
  * We read the page synchronously in the following case:
@@ -592,7 +325,6 @@ static int
 readpage_async_filler(void *data, struct page *page)
 {
 	struct nfs_readdesc *desc = (struct nfs_readdesc *)data;
-	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *new;
 	unsigned int len;
 	int error;
@@ -601,7 +333,7 @@ readpage_async_filler(void *data, struct page *page)
 	if (len == 0)
 		return nfs_return_empty_page(page);
 
-	new = nfs_create_request(desc->ctx, inode, page, 0, len);
+	new = nfs_create_request(desc->ctx, page, NULL, 0, len);
 	if (IS_ERR(new))
 		goto out_error;
 
@@ -654,7 +386,8 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops);
+	nfs_pageio_init_read(&pgio, inode, false,
+			     &nfs_async_read_completion_ops);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
 
@@ -671,7 +404,7 @@ out:
 int __init nfs_init_readpagecache(void)
 {
 	nfs_rdata_cachep = kmem_cache_create("nfs_read_data",
-					     sizeof(struct nfs_read_header),
+					     sizeof(struct nfs_rw_header),
 					     0, SLAB_HWCACHE_ALIGN,
 					     NULL);
 	if (nfs_rdata_cachep == NULL)
@@ -684,3 +417,12 @@ void nfs_destroy_readpagecache(void)
 {
 	kmem_cache_destroy(nfs_rdata_cachep);
 }
+
+static const struct nfs_rw_ops nfs_rw_read_ops = {
+	.rw_mode		= FMODE_READ,
+	.rw_alloc_header	= nfs_readhdr_alloc,
+	.rw_free_header		= nfs_readhdr_free,
+	.rw_done		= nfs_readpage_done,
+	.rw_result		= nfs_readpage_result,
+	.rw_initiate		= nfs_initiate_read,
+};
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2cb56943e23..084af1060d7 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2180,11 +2180,23 @@ out_no_address:
 	return -EINVAL;
 }
 
+#define NFS_MOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \
+		| NFS_MOUNT_SECURE \
+		| NFS_MOUNT_TCP \
+		| NFS_MOUNT_VER3 \
+		| NFS_MOUNT_KERBEROS \
+		| NFS_MOUNT_NONLM \
+		| NFS_MOUNT_BROKEN_SUID \
+		| NFS_MOUNT_STRICTLOCK \
+		| NFS_MOUNT_UNSHARED \
+		| NFS_MOUNT_NORESVPORT \
+		| NFS_MOUNT_LEGACY_INTERFACE)
+
 static int
 nfs_compare_remount_data(struct nfs_server *nfss,
 			 struct nfs_parsed_mount_data *data)
 {
-	if (data->flags != nfss->flags ||
+	if ((data->flags ^ nfss->flags) & NFS_MOUNT_CMP_FLAGMASK ||
 	    data->rsize != nfss->rsize ||
 	    data->wsize != nfss->wsize ||
 	    data->version != nfss->nfs_client->rpc_ops->version ||
@@ -2248,6 +2260,7 @@ nfs_remount(struct super_block *sb, int *flags, char *raw_data)
 	data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen;
 	data->version = nfsvers;
 	data->minorversion = nfss->nfs_client->cl_minorversion;
+	data->net = current->nsproxy->net_ns;
 	memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr,
 		data->nfs_server.addrlen);
 
@@ -2347,18 +2360,6 @@ void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
  	nfs_initialise_sb(sb);
 }
 
-#define NFS_MOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \
-		| NFS_MOUNT_SECURE \
-		| NFS_MOUNT_TCP \
-		| NFS_MOUNT_VER3 \
-		| NFS_MOUNT_KERBEROS \
-		| NFS_MOUNT_NONLM \
-		| NFS_MOUNT_BROKEN_SUID \
-		| NFS_MOUNT_STRICTLOCK \
-		| NFS_MOUNT_UNSHARED \
-		| NFS_MOUNT_NORESVPORT \
-		| NFS_MOUNT_LEGACY_INTERFACE)
-
 static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
 {
 	const struct nfs_server *a = s->s_fs_info;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index ffb9459f180..962c9ee758b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -42,10 +42,11 @@
  * Local function declarations
  */
 static void nfs_redirty_request(struct nfs_page *req);
-static const struct rpc_call_ops nfs_write_common_ops;
 static const struct rpc_call_ops nfs_commit_ops;
 static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops;
 static const struct nfs_commit_completion_ops nfs_commit_completion_ops;
+static const struct nfs_rw_ops nfs_rw_write_ops;
+static void nfs_clear_request_commit(struct nfs_page *req);
 
 static struct kmem_cache *nfs_wdata_cachep;
 static mempool_t *nfs_wdata_mempool;
@@ -70,76 +71,19 @@ void nfs_commit_free(struct nfs_commit_data *p)
 }
 EXPORT_SYMBOL_GPL(nfs_commit_free);
 
-struct nfs_write_header *nfs_writehdr_alloc(void)
+static struct nfs_rw_header *nfs_writehdr_alloc(void)
 {
-	struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
-
-	if (p) {
-		struct nfs_pgio_header *hdr = &p->header;
+	struct nfs_rw_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
 
+	if (p)
 		memset(p, 0, sizeof(*p));
-		INIT_LIST_HEAD(&hdr->pages);
-		INIT_LIST_HEAD(&hdr->rpc_list);
-		spin_lock_init(&hdr->lock);
-		atomic_set(&hdr->refcnt, 0);
-		hdr->verf = &p->verf;
-	}
 	return p;
 }
-EXPORT_SYMBOL_GPL(nfs_writehdr_alloc);
 
-static struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr,
-						  unsigned int pagecount)
+static void nfs_writehdr_free(struct nfs_rw_header *whdr)
 {
-	struct nfs_write_data *data, *prealloc;
-
-	prealloc = &container_of(hdr, struct nfs_write_header, header)->rpc_data;
-	if (prealloc->header == NULL)
-		data = prealloc;
-	else
-		data = kzalloc(sizeof(*data), GFP_KERNEL);
-	if (!data)
-		goto out;
-
-	if (nfs_pgarray_set(&data->pages, pagecount)) {
-		data->header = hdr;
-		atomic_inc(&hdr->refcnt);
-	} else {
-		if (data != prealloc)
-			kfree(data);
-		data = NULL;
-	}
-out:
-	return data;
-}
-
-void nfs_writehdr_free(struct nfs_pgio_header *hdr)
-{
-	struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header);
 	mempool_free(whdr, nfs_wdata_mempool);
 }
-EXPORT_SYMBOL_GPL(nfs_writehdr_free);
-
-void nfs_writedata_release(struct nfs_write_data *wdata)
-{
-	struct nfs_pgio_header *hdr = wdata->header;
-	struct nfs_write_header *write_header = container_of(hdr, struct nfs_write_header, header);
-
-	put_nfs_open_context(wdata->args.context);
-	if (wdata->pages.pagevec != wdata->pages.page_array)
-		kfree(wdata->pages.pagevec);
-	if (wdata == &write_header->rpc_data) {
-		wdata->header = NULL;
-		wdata = NULL;
-	}
-	if (atomic_dec_and_test(&hdr->refcnt))
-		hdr->completion_ops->completion(hdr);
-	/* Note: we only free the rpc_task after callbacks are done.
-	 * See the comment in rpc_free_task() for why
-	 */
-	kfree(wdata);
-}
-EXPORT_SYMBOL_GPL(nfs_writedata_release);
 
 static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 {
@@ -148,8 +92,15 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 	set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 }
 
+/*
+ * nfs_page_find_head_request_locked - find head request associated with @page
+ *
+ * must be called while holding the inode lock.
+ *
+ * returns matching head request with reference held, or NULL if not found.
+ */
 static struct nfs_page *
-nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page)
+nfs_page_find_head_request_locked(struct nfs_inode *nfsi, struct page *page)
 {
 	struct nfs_page *req = NULL;
 
@@ -161,25 +112,33 @@ nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page)
 		/* Linearly search the commit list for the correct req */
 		list_for_each_entry_safe(freq, t, &nfsi->commit_info.list, wb_list) {
 			if (freq->wb_page == page) {
-				req = freq;
+				req = freq->wb_head;
 				break;
 			}
 		}
 	}
 
-	if (req)
+	if (req) {
+		WARN_ON_ONCE(req->wb_head != req);
+
 		kref_get(&req->wb_kref);
+	}
 
 	return req;
 }
 
-static struct nfs_page *nfs_page_find_request(struct page *page)
+/*
+ * nfs_page_find_head_request - find head request associated with @page
+ *
+ * returns matching head request with reference held, or NULL if not found.
+ */
+static struct nfs_page *nfs_page_find_head_request(struct page *page)
 {
 	struct inode *inode = page_file_mapping(page)->host;
 	struct nfs_page *req = NULL;
 
 	spin_lock(&inode->i_lock);
-	req = nfs_page_find_request_locked(NFS_I(inode), page);
+	req = nfs_page_find_head_request_locked(NFS_I(inode), page);
 	spin_unlock(&inode->i_lock);
 	return req;
 }
@@ -211,18 +170,78 @@ static void nfs_set_pageerror(struct page *page)
 	nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page));
 }
 
+/*
+ * nfs_page_group_search_locked
+ * @head - head request of page group
+ * @page_offset - offset into page
+ *
+ * Search page group with head @head to find a request that contains the
+ * page offset @page_offset.
+ *
+ * Returns a pointer to the first matching nfs request, or NULL if no
+ * match is found.
+ *
+ * Must be called with the page group lock held
+ */
+static struct nfs_page *
+nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset)
+{
+	struct nfs_page *req;
+
+	WARN_ON_ONCE(head != head->wb_head);
+	WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_head->wb_flags));
+
+	req = head;
+	do {
+		if (page_offset >= req->wb_pgbase &&
+		    page_offset < (req->wb_pgbase + req->wb_bytes))
+			return req;
+
+		req = req->wb_this_page;
+	} while (req != head);
+
+	return NULL;
+}
+
+/*
+ * nfs_page_group_covers_page
+ * @head - head request of page group
+ *
+ * Return true if the page group with head @head covers the whole page,
+ * returns false otherwise
+ */
+static bool nfs_page_group_covers_page(struct nfs_page *req)
+{
+	struct nfs_page *tmp;
+	unsigned int pos = 0;
+	unsigned int len = nfs_page_length(req->wb_page);
+
+	nfs_page_group_lock(req);
+
+	do {
+		tmp = nfs_page_group_search_locked(req->wb_head, pos);
+		if (tmp) {
+			/* no way this should happen */
+			WARN_ON_ONCE(tmp->wb_pgbase != pos);
+			pos += tmp->wb_bytes - (pos - tmp->wb_pgbase);
+		}
+	} while (tmp && pos < len);
+
+	nfs_page_group_unlock(req);
+	WARN_ON_ONCE(pos > len);
+	return pos == len;
+}
+
 /* We can set the PG_uptodate flag if we see that a write request
  * covers the full page.
  */
-static void nfs_mark_uptodate(struct page *page, unsigned int base, unsigned int count)
+static void nfs_mark_uptodate(struct nfs_page *req)
 {
-	if (PageUptodate(page))
-		return;
-	if (base != 0)
+	if (PageUptodate(req->wb_page))
 		return;
-	if (count != nfs_page_length(page))
+	if (!nfs_page_group_covers_page(req))
 		return;
-	SetPageUptodate(page);
+	SetPageUptodate(req->wb_page);
 }
 
 static int wb_priority(struct writeback_control *wbc)
@@ -258,46 +277,259 @@ static void nfs_set_page_writeback(struct page *page)
 	}
 }
 
-static void nfs_end_page_writeback(struct page *page)
+static void nfs_end_page_writeback(struct nfs_page *req)
 {
-	struct inode *inode = page_file_mapping(page)->host;
+	struct inode *inode = page_file_mapping(req->wb_page)->host;
 	struct nfs_server *nfss = NFS_SERVER(inode);
 
-	end_page_writeback(page);
+	if (!nfs_page_group_sync_on_bit(req, PG_WB_END))
+		return;
+
+	end_page_writeback(req->wb_page);
 	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
 		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 }
 
-static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
+
+/* nfs_page_group_clear_bits
+ *   @req - an nfs request
+ * clears all page group related bits from @req
+ */
+static void
+nfs_page_group_clear_bits(struct nfs_page *req)
+{
+	clear_bit(PG_TEARDOWN, &req->wb_flags);
+	clear_bit(PG_UNLOCKPAGE, &req->wb_flags);
+	clear_bit(PG_UPTODATE, &req->wb_flags);
+	clear_bit(PG_WB_END, &req->wb_flags);
+	clear_bit(PG_REMOVE, &req->wb_flags);
+}
+
+
+/*
+ * nfs_unroll_locks_and_wait -  unlock all newly locked reqs and wait on @req
+ *
+ * this is a helper function for nfs_lock_and_join_requests
+ *
+ * @inode - inode associated with request page group, must be holding inode lock
+ * @head  - head request of page group, must be holding head lock
+ * @req   - request that couldn't lock and needs to wait on the req bit lock
+ * @nonblock - if true, don't actually wait
+ *
+ * NOTE: this must be called holding page_group bit lock and inode spin lock
+ *       and BOTH will be released before returning.
+ *
+ * returns 0 on success, < 0 on error.
+ */
+static int
+nfs_unroll_locks_and_wait(struct inode *inode, struct nfs_page *head,
+			  struct nfs_page *req, bool nonblock)
+	__releases(&inode->i_lock)
+{
+	struct nfs_page *tmp;
+	int ret;
+
+	/* relinquish all the locks successfully grabbed this run */
+	for (tmp = head ; tmp != req; tmp = tmp->wb_this_page)
+		nfs_unlock_request(tmp);
+
+	WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags));
+
+	/* grab a ref on the request that will be waited on */
+	kref_get(&req->wb_kref);
+
+	nfs_page_group_unlock(head);
+	spin_unlock(&inode->i_lock);
+
+	/* release ref from nfs_page_find_head_request_locked */
+	nfs_release_request(head);
+
+	if (!nonblock)
+		ret = nfs_wait_on_request(req);
+	else
+		ret = -EAGAIN;
+	nfs_release_request(req);
+
+	return ret;
+}
+
+/*
+ * nfs_destroy_unlinked_subrequests - destroy recently unlinked subrequests
+ *
+ * @destroy_list - request list (using wb_this_page) terminated by @old_head
+ * @old_head - the old head of the list
+ *
+ * All subrequests must be locked and removed from all lists, so at this point
+ * they are only "active" in this function, and possibly in nfs_wait_on_request
+ * with a reference held by some other context.
+ */
+static void
+nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list,
+				 struct nfs_page *old_head)
+{
+	while (destroy_list) {
+		struct nfs_page *subreq = destroy_list;
+
+		destroy_list = (subreq->wb_this_page == old_head) ?
+				   NULL : subreq->wb_this_page;
+
+		WARN_ON_ONCE(old_head != subreq->wb_head);
+
+		/* make sure old group is not used */
+		subreq->wb_head = subreq;
+		subreq->wb_this_page = subreq;
+
+		nfs_clear_request_commit(subreq);
+
+		/* subreq is now totally disconnected from page group or any
+		 * write / commit lists. last chance to wake any waiters */
+		nfs_unlock_request(subreq);
+
+		if (!test_bit(PG_TEARDOWN, &subreq->wb_flags)) {
+			/* release ref on old head request */
+			nfs_release_request(old_head);
+
+			nfs_page_group_clear_bits(subreq);
+
+			/* release the PG_INODE_REF reference */
+			if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags))
+				nfs_release_request(subreq);
+			else
+				WARN_ON_ONCE(1);
+		} else {
+			WARN_ON_ONCE(test_bit(PG_CLEAN, &subreq->wb_flags));
+			/* zombie requests have already released the last
+			 * reference and were waiting on the rest of the
+			 * group to complete. Since it's no longer part of a
+			 * group, simply free the request */
+			nfs_page_group_clear_bits(subreq);
+			nfs_free_request(subreq);
+		}
+	}
+}
+
+/*
+ * nfs_lock_and_join_requests - join all subreqs to the head req and return
+ *                              a locked reference, cancelling any pending
+ *                              operations for this page.
+ *
+ * @page - the page used to lookup the "page group" of nfs_page structures
+ * @nonblock - if true, don't block waiting for request locks
+ *
+ * This function joins all sub requests to the head request by first
+ * locking all requests in the group, cancelling any pending operations
+ * and finally updating the head request to cover the whole range covered by
+ * the (former) group.  All subrequests are removed from any write or commit
+ * lists, unlinked from the group and destroyed.
+ *
+ * Returns a locked, referenced pointer to the head request - which after
+ * this call is guaranteed to be the only request associated with the page.
+ * Returns NULL if no requests are found for @page, or a ERR_PTR if an
+ * error was encountered.
+ */
+static struct nfs_page *
+nfs_lock_and_join_requests(struct page *page, bool nonblock)
 {
 	struct inode *inode = page_file_mapping(page)->host;
-	struct nfs_page *req;
+	struct nfs_page *head, *subreq;
+	struct nfs_page *destroy_list = NULL;
+	unsigned int total_bytes;
 	int ret;
 
+try_again:
+	total_bytes = 0;
+
+	WARN_ON_ONCE(destroy_list);
+
 	spin_lock(&inode->i_lock);
-	for (;;) {
-		req = nfs_page_find_request_locked(NFS_I(inode), page);
-		if (req == NULL)
-			break;
-		if (nfs_lock_request(req))
-			break;
-		/* Note: If we hold the page lock, as is the case in nfs_writepage,
-		 *	 then the call to nfs_lock_request() will always
-		 *	 succeed provided that someone hasn't already marked the
-		 *	 request as dirty (in which case we don't care).
-		 */
+
+	/*
+	 * A reference is taken only on the head request which acts as a
+	 * reference to the whole page group - the group will not be destroyed
+	 * until the head reference is released.
+	 */
+	head = nfs_page_find_head_request_locked(NFS_I(inode), page);
+
+	if (!head) {
 		spin_unlock(&inode->i_lock);
-		if (!nonblock)
-			ret = nfs_wait_on_request(req);
-		else
-			ret = -EAGAIN;
-		nfs_release_request(req);
-		if (ret != 0)
+		return NULL;
+	}
+
+	/* lock each request in the page group */
+	nfs_page_group_lock(head);
+	subreq = head;
+	do {
+		/*
+		 * Subrequests are always contiguous, non overlapping
+		 * and in order. If not, it's a programming error.
+		 */
+		WARN_ON_ONCE(subreq->wb_offset !=
+		     (head->wb_offset + total_bytes));
+
+		/* keep track of how many bytes this group covers */
+		total_bytes += subreq->wb_bytes;
+
+		if (!nfs_lock_request(subreq)) {
+			/* releases page group bit lock and
+			 * inode spin lock and all references */
+			ret = nfs_unroll_locks_and_wait(inode, head,
+				subreq, nonblock);
+
+			if (ret == 0)
+				goto try_again;
+
 			return ERR_PTR(ret);
-		spin_lock(&inode->i_lock);
+		}
+
+		subreq = subreq->wb_this_page;
+	} while (subreq != head);
+
+	/* Now that all requests are locked, make sure they aren't on any list.
+	 * Commit list removal accounting is done after locks are dropped */
+	subreq = head;
+	do {
+		nfs_list_remove_request(subreq);
+		subreq = subreq->wb_this_page;
+	} while (subreq != head);
+
+	/* unlink subrequests from head, destroy them later */
+	if (head->wb_this_page != head) {
+		/* destroy list will be terminated by head */
+		destroy_list = head->wb_this_page;
+		head->wb_this_page = head;
+
+		/* change head request to cover whole range that
+		 * the former page group covered */
+		head->wb_bytes = total_bytes;
 	}
+
+	/*
+	 * prepare head request to be added to new pgio descriptor
+	 */
+	nfs_page_group_clear_bits(head);
+
+	/*
+	 * some part of the group was still on the inode list - otherwise
+	 * the group wouldn't be involved in async write.
+	 * grab a reference for the head request, iff it needs one.
+	 */
+	if (!test_and_set_bit(PG_INODE_REF, &head->wb_flags))
+		kref_get(&head->wb_kref);
+
+	nfs_page_group_unlock(head);
+
+	/* drop lock to clear_request_commit the head req and clean up
+	 * requests on destroy list */
 	spin_unlock(&inode->i_lock);
-	return req;
+
+	nfs_destroy_unlinked_subrequests(destroy_list, head);
+
+	/* clean up commit list state */
+	nfs_clear_request_commit(head);
+
+	/* still holds ref on head from nfs_page_find_head_request_locked
+	 * and still has lock on head from lock loop */
+	return head;
 }
 
 /*
@@ -310,7 +542,7 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 	struct nfs_page *req;
 	int ret = 0;
 
-	req = nfs_find_and_lock_request(page, nonblock);
+	req = nfs_lock_and_join_requests(page, nonblock);
 	if (!req)
 		goto out;
 	ret = PTR_ERR(req);
@@ -354,10 +586,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
 	struct nfs_pageio_descriptor pgio;
 	int err;
 
-	NFS_PROTO(page_file_mapping(page)->host)->write_pageio_init(&pgio,
-							  page->mapping->host,
-							  wb_priority(wbc),
-							  &nfs_async_write_completion_ops);
+	nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc),
+				false, &nfs_async_write_completion_ops);
 	err = nfs_do_writepage(page, wbc, &pgio);
 	nfs_pageio_complete(&pgio);
 	if (err < 0)
@@ -393,14 +623,15 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	int err;
 
 	/* Stop dirtying of new pages while we sync */
-	err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING,
+	err = wait_on_bit_lock_action(bitlock, NFS_INO_FLUSHING,
 			nfs_wait_bit_killable, TASK_KILLABLE);
 	if (err)
 		goto out_err;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
-	NFS_PROTO(inode)->write_pageio_init(&pgio, inode, wb_priority(wbc), &nfs_async_write_completion_ops);
+	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false,
+				&nfs_async_write_completion_ops);
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
 	nfs_pageio_complete(&pgio);
 
@@ -425,6 +656,8 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 
+	WARN_ON_ONCE(req->wb_this_page != req);
+
 	/* Lock the request! */
 	nfs_lock_request(req);
 
@@ -441,6 +674,9 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 		set_page_private(req->wb_page, (unsigned long)req);
 	}
 	nfsi->npages++;
+	/* this a head request for a page group - mark it as having an
+	 * extra reference so sub groups can follow suit */
+	WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags));
 	kref_get(&req->wb_kref);
 	spin_unlock(&inode->i_lock);
 }
@@ -452,16 +688,23 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
 	struct nfs_inode *nfsi = NFS_I(inode);
+	struct nfs_page *head;
 
-	spin_lock(&inode->i_lock);
-	if (likely(!PageSwapCache(req->wb_page))) {
-		set_page_private(req->wb_page, 0);
-		ClearPagePrivate(req->wb_page);
-		clear_bit(PG_MAPPED, &req->wb_flags);
+	if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
+		head = req->wb_head;
+
+		spin_lock(&inode->i_lock);
+		if (likely(!PageSwapCache(head->wb_page))) {
+			set_page_private(head->wb_page, 0);
+			ClearPagePrivate(head->wb_page);
+			clear_bit(PG_MAPPED, &head->wb_flags);
+		}
+		nfsi->npages--;
+		spin_unlock(&inode->i_lock);
 	}
-	nfsi->npages--;
-	spin_unlock(&inode->i_lock);
-	nfs_release_request(req);
+
+	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags))
+		nfs_release_request(req);
 }
 
 static void
@@ -583,7 +826,7 @@ nfs_clear_request_commit(struct nfs_page *req)
 }
 
 static inline
-int nfs_write_need_commit(struct nfs_write_data *data)
+int nfs_write_need_commit(struct nfs_pgio_data *data)
 {
 	if (data->verf.committed == NFS_DATA_SYNC)
 		return data->header->lseg == NULL;
@@ -614,7 +857,7 @@ nfs_clear_request_commit(struct nfs_page *req)
 }
 
 static inline
-int nfs_write_need_commit(struct nfs_write_data *data)
+int nfs_write_need_commit(struct nfs_pgio_data *data)
 {
 	return 0;
 }
@@ -645,7 +888,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 			goto next;
 		}
 		if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) {
-			memcpy(&req->wb_verf, &hdr->verf->verifier, sizeof(req->wb_verf));
+			memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
 			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
 			goto next;
 		}
@@ -653,7 +896,7 @@ remove_req:
 		nfs_inode_remove_request(req);
 next:
 		nfs_unlock_request(req);
-		nfs_end_page_writeback(req->wb_page);
+		nfs_end_page_writeback(req);
 		nfs_release_request(req);
 	}
 out:
@@ -661,7 +904,7 @@ out:
 }
 
 #if  IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
-static unsigned long
+unsigned long
 nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
 {
 	return cinfo->mds->ncommit;
@@ -718,7 +961,7 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst,
 }
 
 #else
-static unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
+unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
 {
 	return 0;
 }
@@ -754,10 +997,14 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
 	spin_lock(&inode->i_lock);
 
 	for (;;) {
-		req = nfs_page_find_request_locked(NFS_I(inode), page);
+		req = nfs_page_find_head_request_locked(NFS_I(inode), page);
 		if (req == NULL)
 			goto out_unlock;
 
+		/* should be handled by nfs_flush_incompatible */
+		WARN_ON_ONCE(req->wb_head != req);
+		WARN_ON_ONCE(req->wb_this_page != req);
+
 		rqend = req->wb_offset + req->wb_bytes;
 		/*
 		 * Tell the caller to flush out the request if
@@ -819,7 +1066,7 @@ static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
 	req = nfs_try_to_update_request(inode, page, offset, bytes);
 	if (req != NULL)
 		goto out;
-	req = nfs_create_request(ctx, inode, page, offset, bytes);
+	req = nfs_create_request(ctx, page, NULL, offset, bytes);
 	if (IS_ERR(req))
 		goto out;
 	nfs_inode_add_request(inode, req);
@@ -837,7 +1084,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
 		return PTR_ERR(req);
 	/* Update file length */
 	nfs_grow_file(page, offset, count);
-	nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
+	nfs_mark_uptodate(req);
 	nfs_mark_request_dirty(req);
 	nfs_unlock_and_release_request(req);
 	return 0;
@@ -858,11 +1105,13 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 	 * dropped page.
 	 */
 	do {
-		req = nfs_page_find_request(page);
+		req = nfs_page_find_head_request(page);
 		if (req == NULL)
 			return 0;
 		l_ctx = req->wb_lock_context;
 		do_flush = req->wb_page != page || req->wb_context != ctx;
+		/* for now, flush if more than 1 request in page_group */
+		do_flush |= req->wb_this_page != req;
 		if (l_ctx && ctx->dentry->d_inode->i_flock != NULL) {
 			do_flush |= l_ctx->lockowner.l_owner != current->files
 				|| l_ctx->lockowner.l_pid != current->tgid;
@@ -913,12 +1162,14 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
 
 	if (nfs_have_delegated_attributes(inode))
 		goto out;
-	if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+	if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
 		return false;
 	smp_rmb();
 	if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags))
 		return false;
 out:
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+		return false;
 	return PageUptodate(page) != 0;
 }
 
@@ -990,126 +1241,17 @@ static int flush_task_priority(int how)
 	return RPC_PRIORITY_NORMAL;
 }
 
-int nfs_initiate_write(struct rpc_clnt *clnt,
-		       struct nfs_write_data *data,
-		       const struct rpc_call_ops *call_ops,
-		       int how, int flags)
+static void nfs_initiate_write(struct nfs_pgio_data *data, struct rpc_message *msg,
+			       struct rpc_task_setup *task_setup_data, int how)
 {
 	struct inode *inode = data->header->inode;
 	int priority = flush_task_priority(how);
-	struct rpc_task *task;
-	struct rpc_message msg = {
-		.rpc_argp = &data->args,
-		.rpc_resp = &data->res,
-		.rpc_cred = data->header->cred,
-	};
-	struct rpc_task_setup task_setup_data = {
-		.rpc_client = clnt,
-		.task = &data->task,
-		.rpc_message = &msg,
-		.callback_ops = call_ops,
-		.callback_data = data,
-		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC | flags,
-		.priority = priority,
-	};
-	int ret = 0;
-
-	/* Set up the initial task struct.  */
-	NFS_PROTO(inode)->write_setup(data, &msg);
 
-	dprintk("NFS: %5u initiated write call "
-		"(req %s/%llu, %u bytes @ offset %llu)\n",
-		data->task.tk_pid,
-		inode->i_sb->s_id,
-		(unsigned long long)NFS_FILEID(inode),
-		data->args.count,
-		(unsigned long long)data->args.offset);
+	task_setup_data->priority = priority;
+	NFS_PROTO(inode)->write_setup(data, msg);
 
 	nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client,
-				 &task_setup_data.rpc_client, &msg, data);
-
-	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task)) {
-		ret = PTR_ERR(task);
-		goto out;
-	}
-	if (how & FLUSH_SYNC) {
-		ret = rpc_wait_for_completion_task(task);
-		if (ret == 0)
-			ret = task->tk_status;
-	}
-	rpc_put_task(task);
-out:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(nfs_initiate_write);
-
-/*
- * Set up the argument/result storage required for the RPC call.
- */
-static void nfs_write_rpcsetup(struct nfs_write_data *data,
-		unsigned int count, unsigned int offset,
-		int how, struct nfs_commit_info *cinfo)
-{
-	struct nfs_page *req = data->header->req;
-
-	/* Set up the RPC argument and reply structs
-	 * NB: take care not to mess about with data->commit et al. */
-
-	data->args.fh     = NFS_FH(data->header->inode);
-	data->args.offset = req_offset(req) + offset;
-	/* pnfs_set_layoutcommit needs this */
-	data->mds_offset = data->args.offset;
-	data->args.pgbase = req->wb_pgbase + offset;
-	data->args.pages  = data->pages.pagevec;
-	data->args.count  = count;
-	data->args.context = get_nfs_open_context(req->wb_context);
-	data->args.lock_context = req->wb_lock_context;
-	data->args.stable  = NFS_UNSTABLE;
-	switch (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) {
-	case 0:
-		break;
-	case FLUSH_COND_STABLE:
-		if (nfs_reqs_to_commit(cinfo))
-			break;
-	default:
-		data->args.stable = NFS_FILE_SYNC;
-	}
-
-	data->res.fattr   = &data->fattr;
-	data->res.count   = count;
-	data->res.verf    = &data->verf;
-	nfs_fattr_init(&data->fattr);
-}
-
-static int nfs_do_write(struct nfs_write_data *data,
-		const struct rpc_call_ops *call_ops,
-		int how)
-{
-	struct inode *inode = data->header->inode;
-
-	return nfs_initiate_write(NFS_CLIENT(inode), data, call_ops, how, 0);
-}
-
-static int nfs_do_multiple_writes(struct list_head *head,
-		const struct rpc_call_ops *call_ops,
-		int how)
-{
-	struct nfs_write_data *data;
-	int ret = 0;
-
-	while (!list_empty(head)) {
-		int ret2;
-
-		data = list_first_entry(head, struct nfs_write_data, list);
-		list_del_init(&data->list);
-		
-		ret2 = nfs_do_write(data, call_ops, how);
-		 if (ret == 0)
-			 ret = ret2;
-	}
-	return ret;
+				 &task_setup_data->rpc_client, msg, data);
 }
 
 /* If a nfs_flush_* function fails, it should remove reqs from @head and
@@ -1120,7 +1262,7 @@ static void nfs_redirty_request(struct nfs_page *req)
 {
 	nfs_mark_request_dirty(req);
 	nfs_unlock_request(req);
-	nfs_end_page_writeback(req->wb_page);
+	nfs_end_page_writeback(req);
 	nfs_release_request(req);
 }
 
@@ -1140,173 +1282,30 @@ static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = {
 	.completion = nfs_write_completion,
 };
 
-static void nfs_flush_error(struct nfs_pageio_descriptor *desc,
-		struct nfs_pgio_header *hdr)
-{
-	set_bit(NFS_IOHDR_REDO, &hdr->flags);
-	while (!list_empty(&hdr->rpc_list)) {
-		struct nfs_write_data *data = list_first_entry(&hdr->rpc_list,
-				struct nfs_write_data, list);
-		list_del(&data->list);
-		nfs_writedata_release(data);
-	}
-	desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-}
-
-/*
- * Generate multiple small requests to write out a single
- * contiguous dirty area on one page.
- */
-static int nfs_flush_multi(struct nfs_pageio_descriptor *desc,
-			   struct nfs_pgio_header *hdr)
-{
-	struct nfs_page *req = hdr->req;
-	struct page *page = req->wb_page;
-	struct nfs_write_data *data;
-	size_t wsize = desc->pg_bsize, nbytes;
-	unsigned int offset;
-	int requests = 0;
-	struct nfs_commit_info cinfo;
-
-	nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
-
-	if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
-	    (desc->pg_moreio || nfs_reqs_to_commit(&cinfo) ||
-	     desc->pg_count > wsize))
-		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
-
-
-	offset = 0;
-	nbytes = desc->pg_count;
-	do {
-		size_t len = min(nbytes, wsize);
-
-		data = nfs_writedata_alloc(hdr, 1);
-		if (!data) {
-			nfs_flush_error(desc, hdr);
-			return -ENOMEM;
-		}
-		data->pages.pagevec[0] = page;
-		nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags, &cinfo);
-		list_add(&data->list, &hdr->rpc_list);
-		requests++;
-		nbytes -= len;
-		offset += len;
-	} while (nbytes != 0);
-	nfs_list_remove_request(req);
-	nfs_list_add_request(req, &hdr->pages);
-	desc->pg_rpc_callops = &nfs_write_common_ops;
-	return 0;
-}
-
-/*
- * Create an RPC task for the given write request and kick it.
- * The page must have been locked by the caller.
- *
- * It may happen that the page we're passed is not marked dirty.
- * This is the case if nfs_updatepage detects a conflicting request
- * that has been written but not committed.
- */
-static int nfs_flush_one(struct nfs_pageio_descriptor *desc,
-			 struct nfs_pgio_header *hdr)
-{
-	struct nfs_page		*req;
-	struct page		**pages;
-	struct nfs_write_data	*data;
-	struct list_head *head = &desc->pg_list;
-	struct nfs_commit_info cinfo;
-
-	data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base,
-							   desc->pg_count));
-	if (!data) {
-		nfs_flush_error(desc, hdr);
-		return -ENOMEM;
-	}
-
-	nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
-	pages = data->pages.pagevec;
-	while (!list_empty(head)) {
-		req = nfs_list_entry(head->next);
-		nfs_list_remove_request(req);
-		nfs_list_add_request(req, &hdr->pages);
-		*pages++ = req->wb_page;
-	}
-
-	if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
-	    (desc->pg_moreio || nfs_reqs_to_commit(&cinfo)))
-		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
-
-	/* Set up the argument struct */
-	nfs_write_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags, &cinfo);
-	list_add(&data->list, &hdr->rpc_list);
-	desc->pg_rpc_callops = &nfs_write_common_ops;
-	return 0;
-}
-
-int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
-		      struct nfs_pgio_header *hdr)
-{
-	if (desc->pg_bsize < PAGE_CACHE_SIZE)
-		return nfs_flush_multi(desc, hdr);
-	return nfs_flush_one(desc, hdr);
-}
-EXPORT_SYMBOL_GPL(nfs_generic_flush);
-
-static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
-{
-	struct nfs_write_header *whdr;
-	struct nfs_pgio_header *hdr;
-	int ret;
-
-	whdr = nfs_writehdr_alloc();
-	if (!whdr) {
-		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-		return -ENOMEM;
-	}
-	hdr = &whdr->header;
-	nfs_pgheader_init(desc, hdr, nfs_writehdr_free);
-	atomic_inc(&hdr->refcnt);
-	ret = nfs_generic_flush(desc, hdr);
-	if (ret == 0)
-		ret = nfs_do_multiple_writes(&hdr->rpc_list,
-					     desc->pg_rpc_callops,
-					     desc->pg_ioflags);
-	if (atomic_dec_and_test(&hdr->refcnt))
-		hdr->completion_ops->completion(hdr);
-	return ret;
-}
-
-static const struct nfs_pageio_ops nfs_pageio_write_ops = {
-	.pg_test = nfs_generic_pg_test,
-	.pg_doio = nfs_generic_pg_writepages,
-};
-
 void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
-			       struct inode *inode, int ioflags,
+			       struct inode *inode, int ioflags, bool force_mds,
 			       const struct nfs_pgio_completion_ops *compl_ops)
 {
-	nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops,
-				NFS_SERVER(inode)->wsize, ioflags);
+	struct nfs_server *server = NFS_SERVER(inode);
+	const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops;
+
+#ifdef CONFIG_NFS_V4_1
+	if (server->pnfs_curr_ld && !force_mds)
+		pg_ops = server->pnfs_curr_ld->pg_write_ops;
+#endif
+	nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_write_ops,
+			server->wsize, ioflags);
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init_write);
 
 void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 {
-	pgio->pg_ops = &nfs_pageio_write_ops;
+	pgio->pg_ops = &nfs_pgio_rw_ops;
 	pgio->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 
 
-void nfs_write_prepare(struct rpc_task *task, void *calldata)
-{
-	struct nfs_write_data *data = calldata;
-	int err;
-	err = NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data);
-	if (err)
-		rpc_exit(task, err);
-}
-
 void nfs_commit_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs_commit_data *data = calldata;
@@ -1314,23 +1313,8 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata)
 	NFS_PROTO(data->inode)->commit_rpc_prepare(task, data);
 }
 
-/*
- * Handle a write reply that flushes a whole page.
- *
- * FIXME: There is an inherent race with invalidate_inode_pages and
- *	  writebacks since the page->count is kept > 1 for as long
- *	  as the page has a write request pending.
- */
-static void nfs_writeback_done_common(struct rpc_task *task, void *calldata)
-{
-	struct nfs_write_data	*data = calldata;
-
-	nfs_writeback_done(task, data);
-}
-
-static void nfs_writeback_release_common(void *calldata)
+static void nfs_writeback_release_common(struct nfs_pgio_data *data)
 {
-	struct nfs_write_data	*data = calldata;
 	struct nfs_pgio_header *hdr = data->header;
 	int status = data->task.tk_status;
 
@@ -1339,34 +1323,46 @@ static void nfs_writeback_release_common(void *calldata)
 		if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags))
 			; /* Do nothing */
 		else if (!test_and_set_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags))
-			memcpy(hdr->verf, &data->verf, sizeof(*hdr->verf));
-		else if (memcmp(hdr->verf, &data->verf, sizeof(*hdr->verf)))
+			memcpy(&hdr->verf, &data->verf, sizeof(hdr->verf));
+		else if (memcmp(&hdr->verf, &data->verf, sizeof(hdr->verf)))
 			set_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags);
 		spin_unlock(&hdr->lock);
 	}
-	nfs_writedata_release(data);
 }
 
-static const struct rpc_call_ops nfs_write_common_ops = {
-	.rpc_call_prepare = nfs_write_prepare,
-	.rpc_call_done = nfs_writeback_done_common,
-	.rpc_release = nfs_writeback_release_common,
-};
+/*
+ * Special version of should_remove_suid() that ignores capabilities.
+ */
+static int nfs_should_remove_suid(const struct inode *inode)
+{
+	umode_t mode = inode->i_mode;
+	int kill = 0;
 
+	/* suid always must be killed */
+	if (unlikely(mode & S_ISUID))
+		kill = ATTR_KILL_SUID;
+
+	/*
+	 * sgid without any exec bits is just a mandatory locking mark; leave
+	 * it alone.  If some exec bits are set, it's a real sgid; kill it.
+	 */
+	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
+		kill |= ATTR_KILL_SGID;
+
+	if (unlikely(kill && S_ISREG(mode)))
+		return kill;
+
+	return 0;
+}
 
 /*
  * This function is called when the WRITE call is complete.
  */
-void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs_writeback_done(struct rpc_task *task, struct nfs_pgio_data *data,
+			      struct inode *inode)
 {
-	struct nfs_writeargs	*argp = &data->args;
-	struct nfs_writeres	*resp = &data->res;
-	struct inode		*inode = data->header->inode;
 	int status;
 
-	dprintk("NFS: %5u nfs_writeback_done (status %d)\n",
-		task->tk_pid, task->tk_status);
-
 	/*
 	 * ->write_done will attempt to use post-op attributes to detect
 	 * conflicting writes by other clients.  A strict interpretation
@@ -1376,11 +1372,11 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 	 */
 	status = NFS_PROTO(inode)->write_done(task, data);
 	if (status != 0)
-		return;
-	nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count);
+		return status;
+	nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, data->res.count);
 
 #if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4)
-	if (resp->verf->committed < argp->stable && task->tk_status >= 0) {
+	if (data->res.verf->committed < data->args.stable && task->tk_status >= 0) {
 		/* We tried a write call, but the server did not
 		 * commit data to stable storage even though we
 		 * requested it.
@@ -1396,18 +1392,31 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 			dprintk("NFS:       faulty NFS server %s:"
 				" (committed = %d) != (stable = %d)\n",
 				NFS_SERVER(inode)->nfs_client->cl_hostname,
-				resp->verf->committed, argp->stable);
+				data->res.verf->committed, data->args.stable);
 			complain = jiffies + 300 * HZ;
 		}
 	}
 #endif
-	if (task->tk_status < 0)
-		nfs_set_pgio_error(data->header, task->tk_status, argp->offset);
-	else if (resp->count < argp->count) {
+
+	/* Deal with the suid/sgid bit corner case */
+	if (nfs_should_remove_suid(inode))
+		nfs_mark_for_revalidate(inode);
+	return 0;
+}
+
+/*
+ * This function is called when the WRITE call is complete.
+ */
+static void nfs_writeback_result(struct rpc_task *task, struct nfs_pgio_data *data)
+{
+	struct nfs_pgio_args	*argp = &data->args;
+	struct nfs_pgio_res	*resp = &data->res;
+
+	if (resp->count < argp->count) {
 		static unsigned long    complain;
 
 		/* This a short write! */
-		nfs_inc_stats(inode, NFSIOS_SHORTWRITE);
+		nfs_inc_stats(data->header->inode, NFSIOS_SHORTWRITE);
 
 		/* Has the server at least made some progress? */
 		if (resp->count == 0) {
@@ -1694,7 +1703,7 @@ int nfs_commit_inode(struct inode *inode, int how)
 			return error;
 		if (!may_wait)
 			goto out_mark_dirty;
-		error = wait_on_bit(&NFS_I(inode)->flags,
+		error = wait_on_bit_action(&NFS_I(inode)->flags,
 				NFS_INO_COMMIT,
 				nfs_wait_bit_killable,
 				TASK_KILLABLE);
@@ -1788,27 +1797,28 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 	struct nfs_page *req;
 	int ret = 0;
 
-	for (;;) {
-		wait_on_page_writeback(page);
-		req = nfs_page_find_request(page);
-		if (req == NULL)
-			break;
-		if (nfs_lock_request(req)) {
-			nfs_clear_request_commit(req);
-			nfs_inode_remove_request(req);
-			/*
-			 * In case nfs_inode_remove_request has marked the
-			 * page as being dirty
-			 */
-			cancel_dirty_page(page, PAGE_CACHE_SIZE);
-			nfs_unlock_and_release_request(req);
-			break;
-		}
-		ret = nfs_wait_on_request(req);
-		nfs_release_request(req);
-		if (ret < 0)
-			break;
+	wait_on_page_writeback(page);
+
+	/* blocking call to cancel all requests and join to a single (head)
+	 * request */
+	req = nfs_lock_and_join_requests(page, false);
+
+	if (IS_ERR(req)) {
+		ret = PTR_ERR(req);
+	} else if (req) {
+		/* all requests from this page have been cancelled by
+		 * nfs_lock_and_join_requests, so just remove the head
+		 * request from the inode / page_private pointer and
+		 * release it */
+		nfs_inode_remove_request(req);
+		/*
+		 * In case nfs_inode_remove_request has marked the
+		 * page as being dirty
+		 */
+		cancel_dirty_page(page, PAGE_CACHE_SIZE);
+		nfs_unlock_and_release_request(req);
 	}
+
 	return ret;
 }
 
@@ -1874,7 +1884,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 int __init nfs_init_writepagecache(void)
 {
 	nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
-					     sizeof(struct nfs_write_header),
+					     sizeof(struct nfs_rw_header),
 					     0, SLAB_HWCACHE_ALIGN,
 					     NULL);
 	if (nfs_wdata_cachep == NULL)
@@ -1936,3 +1946,12 @@ void nfs_destroy_writepagecache(void)
 	kmem_cache_destroy(nfs_wdata_cachep);
 }
 
+static const struct nfs_rw_ops nfs_rw_write_ops = {
+	.rw_mode		= FMODE_WRITE,
+	.rw_alloc_header	= nfs_writehdr_alloc,
+	.rw_free_header		= nfs_writehdr_free,
+	.rw_release		= nfs_writeback_release_common,
+	.rw_done		= nfs_writeback_done,
+	.rw_result		= nfs_writeback_result,
+	.rw_initiate		= nfs_initiate_write,
+};
diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h
index b481e1f5eec..a986ceb6fd0 100644
--- a/fs/nfsd/acl.h
+++ b/fs/nfsd/acl.h
@@ -49,7 +49,7 @@ struct svc_rqst;
 
 struct nfs4_acl *nfs4_acl_new(int);
 int nfs4_acl_get_whotype(char *, u32);
-__be32 nfs4_acl_write_who(int who, __be32 **p, int *len);
+__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who);
 
 int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
 		struct nfs4_acl **acl);
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 2645be435e7..72f44823adb 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -1,7 +1,6 @@
 /* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */
 
 #include <linux/sched.h>
-#include <linux/user_namespace.h>
 #include "nfsd.h"
 #include "auth.h"
 
@@ -25,7 +24,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	struct cred *new;
 	int i;
 	int flags = nfsexp_flags(rqstp, exp);
-	int ret;
 
 	validate_process_creds();
 
@@ -86,8 +84,7 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	return 0;
 
 oom:
-	ret = -ENOMEM;
 	abort_creds(new);
-	return ret;
+	return -ENOMEM;
 }
 
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 8513c598fab..13b85f94d9e 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -17,17 +17,12 @@
 #include <linux/exportfs.h>
 #include <linux/sunrpc/svc_xprt.h>
 
-#include <net/ipv6.h>
-
 #include "nfsd.h"
 #include "nfsfh.h"
 #include "netns.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT
 
-typedef struct auth_domain	svc_client;
-typedef struct svc_export	svc_export;
-
 /*
  * We have two caches.
  * One maps client+vfsmnt+dentry to export options - the export map
@@ -73,7 +68,7 @@ static struct svc_expkey *svc_expkey_lookup(struct cache_detail *cd, struct svc_
 
 static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen)
 {
-	/* client fsidtype fsid [path] */
+	/* client fsidtype fsid expiry [path] */
 	char *buf;
 	int len;
 	struct auth_domain *dom = NULL;
@@ -295,13 +290,19 @@ svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new,
 
 static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc)
 {
+	struct nfsd4_fs_location *locations = fsloc->locations;
 	int i;
 
+	if (!locations)
+		return;
+
 	for (i = 0; i < fsloc->locations_count; i++) {
-		kfree(fsloc->locations[i].path);
-		kfree(fsloc->locations[i].hosts);
+		kfree(locations[i].path);
+		kfree(locations[i].hosts);
 	}
-	kfree(fsloc->locations);
+
+	kfree(locations);
+	fsloc->locations = NULL;
 }
 
 static void svc_export_put(struct kref *ref)
@@ -388,6 +389,10 @@ fsloc_parse(char **mesg, char *buf, struct nfsd4_fs_locations *fsloc)
 	int len;
 	int migrated, i, err;
 
+	/* more than one fsloc */
+	if (fsloc->locations)
+		return -EINVAL;
+
 	/* listsize */
 	err = get_uint(mesg, &fsloc->locations_count);
 	if (err)
@@ -437,13 +442,18 @@ out_free_all:
 
 static int secinfo_parse(char **mesg, char *buf, struct svc_export *exp)
 {
-	int listsize, err;
 	struct exp_flavor_info *f;
+	u32 listsize;
+	int err;
+
+	/* more than one secinfo */
+	if (exp->ex_nflavors)
+		return -EINVAL;
 
-	err = get_int(mesg, &listsize);
+	err = get_uint(mesg, &listsize);
 	if (err)
 		return err;
-	if (listsize < 0 || listsize > MAX_SECINFO_LIST)
+	if (listsize > MAX_SECINFO_LIST)
 		return -EINVAL;
 
 	for (f = exp->ex_flavors; f < exp->ex_flavors + listsize; f++) {
@@ -474,6 +484,27 @@ static inline int
 secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; }
 #endif
 
+static inline int
+uuid_parse(char **mesg, char *buf, unsigned char **puuid)
+{
+	int len;
+
+	/* more than one uuid */
+	if (*puuid)
+		return -EINVAL;
+
+	/* expect a 16 byte uuid encoded as \xXXXX... */
+	len = qword_get(mesg, buf, PAGE_SIZE);
+	if (len != EX_UUID_LEN)
+		return -EINVAL;
+
+	*puuid = kmemdup(buf, EX_UUID_LEN, GFP_KERNEL);
+	if (*puuid == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 {
 	/* client path expiry [flags anonuid anongid fsid] */
@@ -552,18 +583,9 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 		while ((len = qword_get(&mesg, buf, PAGE_SIZE)) > 0) {
 			if (strcmp(buf, "fsloc") == 0)
 				err = fsloc_parse(&mesg, buf, &exp.ex_fslocs);
-			else if (strcmp(buf, "uuid") == 0) {
-				/* expect a 16 byte uuid encoded as \xXXXX... */
-				len = qword_get(&mesg, buf, PAGE_SIZE);
-				if (len != 16)
-					err  = -EINVAL;
-				else {
-					exp.ex_uuid =
-						kmemdup(buf, 16, GFP_KERNEL);
-					if (exp.ex_uuid == NULL)
-						err = -ENOMEM;
-				}
-			} else if (strcmp(buf, "secinfo") == 0)
+			else if (strcmp(buf, "uuid") == 0)
+				err = uuid_parse(&mesg, buf, &exp.ex_uuid);
+			else if (strcmp(buf, "secinfo") == 0)
 				err = secinfo_parse(&mesg, buf, &exp);
 			else
 				/* quietly ignore unknown words and anything
@@ -649,7 +671,7 @@ static int svc_export_show(struct seq_file *m,
 		if (exp->ex_uuid) {
 			int i;
 			seq_puts(m, ",uuid=");
-			for (i=0; i<16; i++) {
+			for (i = 0; i < EX_UUID_LEN; i++) {
 				if ((i&3) == 0 && i)
 					seq_putc(m, ':');
 				seq_printf(m, "%02x", exp->ex_uuid[i]);
@@ -771,7 +793,7 @@ svc_export_update(struct svc_export *new, struct svc_export *old)
 
 
 static struct svc_expkey *
-exp_find_key(struct cache_detail *cd, svc_client *clp, int fsid_type,
+exp_find_key(struct cache_detail *cd, struct auth_domain *clp, int fsid_type,
 	     u32 *fsidv, struct cache_req *reqp)
 {
 	struct svc_expkey key, *ek;
@@ -793,9 +815,9 @@ exp_find_key(struct cache_detail *cd, svc_client *clp, int fsid_type,
 	return ek;
 }
 
-
-static svc_export *exp_get_by_name(struct cache_detail *cd, svc_client *clp,
-				   const struct path *path, struct cache_req *reqp)
+static struct svc_export *
+exp_get_by_name(struct cache_detail *cd, struct auth_domain *clp,
+		const struct path *path, struct cache_req *reqp)
 {
 	struct svc_export *exp, key;
 	int err;
@@ -819,11 +841,11 @@ static svc_export *exp_get_by_name(struct cache_detail *cd, svc_client *clp,
 /*
  * Find the export entry for a given dentry.
  */
-static struct svc_export *exp_parent(struct cache_detail *cd, svc_client *clp,
-				     struct path *path)
+static struct svc_export *
+exp_parent(struct cache_detail *cd, struct auth_domain *clp, struct path *path)
 {
 	struct dentry *saved = dget(path->dentry);
-	svc_export *exp = exp_get_by_name(cd, clp, path, NULL);
+	struct svc_export *exp = exp_get_by_name(cd, clp, path, NULL);
 
 	while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(path->dentry)) {
 		struct dentry *parent = dget_parent(path->dentry);
@@ -844,7 +866,7 @@ static struct svc_export *exp_parent(struct cache_detail *cd, svc_client *clp,
  * since its harder to fool a kernel module than a user space program.
  */
 int
-exp_rootfh(struct net *net, svc_client *clp, char *name,
+exp_rootfh(struct net *net, struct auth_domain *clp, char *name,
 	   struct knfsd_fh *f, int maxsize)
 {
 	struct svc_export	*exp;
diff --git a/include/linux/nfsd/export.h b/fs/nfsd/export.h
index 7898c997dfe..cfeea85c5be 100644
--- a/include/linux/nfsd/export.h
+++ b/fs/nfsd/export.h
@@ -1,17 +1,16 @@
 /*
- * include/linux/nfsd/export.h
- * 
- * Public declarations for NFS exports. The definitions for the
- * syscall interface are in nfsctl.h
- *
  * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
  */
 #ifndef NFSD_EXPORT_H
 #define NFSD_EXPORT_H
 
-# include <linux/nfsd/nfsfh.h>
+#include <linux/sunrpc/cache.h>
 #include <uapi/linux/nfsd/export.h>
 
+struct knfsd_fh;
+struct svc_fh;
+struct svc_rqst;
+
 /*
  * FS Locations
  */
@@ -38,6 +37,7 @@ struct nfsd4_fs_locations {
  * spkm3i, and spkm3p (and using all 8 at once should be rare).
  */
 #define MAX_SECINFO_LIST	8
+#define EX_UUID_LEN		16
 
 struct exp_flavor_info {
 	u32	pseudoflavor;
@@ -54,7 +54,7 @@ struct svc_export {
 	int			ex_fsid;
 	unsigned char *		ex_uuid; /* 16 byte fsid */
 	struct nfsd4_fs_locations ex_fslocs;
-	int			ex_nflavors;
+	uint32_t		ex_nflavors;
 	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
 	struct cache_detail	*cd;
 };
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index d620e7f8142..2ed05c3cd43 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -97,25 +97,14 @@ static ssize_t fault_inject_read(struct file *file, char __user *buf,
 {
 	static u64 val;
 	char read_buf[25];
-	size_t size, ret;
+	size_t size;
 	loff_t pos = *ppos;
 
 	if (!pos)
 		nfsd_inject_get(file_inode(file)->i_private, &val);
 	size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val);
 
-	if (pos < 0)
-		return -EINVAL;
-	if (pos >= size || !len)
-		return 0;
-	if (len > size - pos)
-		len = size - pos;
-	ret = copy_to_user(buf, read_buf + pos, len);
-	if (ret == len)
-		return -EFAULT;
-	len -= ret;
-	*ppos = pos + len;
-	return len;
+	return simple_read_from_buffer(buf, len, ppos, read_buf, size);
 }
 
 static ssize_t fault_inject_write(struct file *file, const char __user *buf,
diff --git a/fs/nfsd/idmap.h b/fs/nfsd/idmap.h
index 66e58db0193..a3f34900091 100644
--- a/fs/nfsd/idmap.h
+++ b/fs/nfsd/idmap.h
@@ -56,7 +56,7 @@ static inline void nfsd_idmap_shutdown(struct net *net)
 
 __be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, kuid_t *);
 __be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, kgid_t *);
-__be32 nfsd4_encode_user(struct svc_rqst *, kuid_t, __be32 **, int *);
-__be32 nfsd4_encode_group(struct svc_rqst *, kgid_t, __be32 **, int *);
+__be32 nfsd4_encode_user(struct xdr_stream *, struct svc_rqst *, kuid_t);
+__be32 nfsd4_encode_group(struct xdr_stream *, struct svc_rqst *, kgid_t);
 
 #endif /* LINUX_NFSD_IDMAP_H */
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 11c1fba2931..12b023a7ab7 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -182,7 +182,8 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessarg
 static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
 		struct nfsd3_getaclargs *argp)
 {
-	if (!(p = nfs2svc_decode_fh(p, &argp->fh)))
+	p = nfs2svc_decode_fh(p, &argp->fh);
+	if (!p)
 		return 0;
 	argp->mask = ntohl(*p); p++;
 
@@ -197,7 +198,8 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
 	unsigned int base;
 	int n;
 
-	if (!(p = nfs2svc_decode_fh(p, &argp->fh)))
+	p = nfs2svc_decode_fh(p, &argp->fh);
+	if (!p)
 		return 0;
 	argp->mask = ntohl(*p++);
 	if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) ||
@@ -218,7 +220,8 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
 static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p,
 		struct nfsd_fhandle *argp)
 {
-	if (!(p = nfs2svc_decode_fh(p, &argp->fh)))
+	p = nfs2svc_decode_fh(p, &argp->fh);
+	if (!p)
 		return 0;
 	return xdr_argsize_check(rqstp, p);
 }
@@ -226,7 +229,8 @@ static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p,
 static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
 		struct nfsd3_accessargs *argp)
 {
-	if (!(p = nfs2svc_decode_fh(p, &argp->fh)))
+	p = nfs2svc_decode_fh(p, &argp->fh);
+	if (!p)
 		return 0;
 	argp->access = ntohl(*p++);
 
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index adc5f1b1dc2..2a514e21dc7 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -128,7 +128,8 @@ out:
 static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
 		struct nfsd3_getaclargs *args)
 {
-	if (!(p = nfs3svc_decode_fh(p, &args->fh)))
+	p = nfs3svc_decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	args->mask = ntohl(*p); p++;
 
@@ -143,7 +144,8 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
 	unsigned int base;
 	int n;
 
-	if (!(p = nfs3svc_decode_fh(p, &args->fh)))
+	p = nfs3svc_decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	args->mask = ntohl(*p++);
 	if (args->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) ||
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index de6e39e12cb..e6c01e80325 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -278,7 +278,8 @@ void fill_post_wcc(struct svc_fh *fhp)
 int
 nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
 {
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	return xdr_argsize_check(rqstp, p);
 }
@@ -287,7 +288,8 @@ int
 nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_sattrargs *args)
 {
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	p = decode_sattr3(p, &args->attrs);
 
@@ -315,7 +317,8 @@ int
 nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_accessargs *args)
 {
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	args->access = ntohl(*p++);
 
@@ -330,7 +333,8 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 	int v;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	p = xdr_decode_hyper(p, &args->offset);
 
@@ -360,7 +364,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	unsigned int len, v, hdr, dlen;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	p = xdr_decode_hyper(p, &args->offset);
 
@@ -535,7 +540,8 @@ int
 nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_readlinkargs *args)
 {
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	args->buffer = page_address(*(rqstp->rq_next_page++));
 
@@ -558,7 +564,8 @@ int
 nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_readdirargs *args)
 {
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	p = xdr_decode_hyper(p, &args->cookie);
 	args->verf   = p; p += 2;
@@ -580,7 +587,8 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
 	int len;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	p = xdr_decode_hyper(p, &args->cookie);
 	args->verf     = p; p += 2;
@@ -605,7 +613,8 @@ int
 nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_commitargs *args)
 {
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	p = xdr_decode_hyper(p, &args->offset);
 	args->count = ntohl(*p++);
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index f66c66b9f18..d714156a19f 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -36,7 +36,6 @@
 
 #include <linux/slab.h>
 #include <linux/nfs_fs.h>
-#include <linux/export.h>
 #include "nfsfh.h"
 #include "nfsd.h"
 #include "acl.h"
@@ -920,20 +919,19 @@ nfs4_acl_get_whotype(char *p, u32 len)
 	return NFS4_ACL_WHO_NAMED;
 }
 
-__be32 nfs4_acl_write_who(int who, __be32 **p, int *len)
+__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who)
 {
+	__be32 *p;
 	int i;
-	int bytes;
 
 	for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
 		if (s2t_map[i].type != who)
 			continue;
-		bytes = 4 + (XDR_QUADLEN(s2t_map[i].stringlen) << 2);
-		if (bytes > *len)
+		p = xdr_reserve_space(xdr, s2t_map[i].stringlen + 4);
+		if (!p)
 			return nfserr_resource;
-		*p = xdr_encode_opaque(*p, s2t_map[i].string,
+		p = xdr_encode_opaque(p, s2t_map[i].string,
 					s2t_map[i].stringlen);
-		*len -= bytes;
 		return 0;
 	}
 	WARN_ON_ONCE(1);
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index c0dfde68742..a0ab0a847d6 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -551,44 +551,43 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen
 	return 0;
 }
 
-static __be32 encode_ascii_id(u32 id, __be32 **p, int *buflen)
+static __be32 encode_ascii_id(struct xdr_stream *xdr, u32 id)
 {
 	char buf[11];
 	int len;
-	int bytes;
+	__be32 *p;
 
 	len = sprintf(buf, "%u", id);
-	bytes = 4 + (XDR_QUADLEN(len) << 2);
-	if (bytes > *buflen)
+	p = xdr_reserve_space(xdr, len + 4);
+	if (!p)
 		return nfserr_resource;
-	*p = xdr_encode_opaque(*p, buf, len);
-	*buflen -= bytes;
+	p = xdr_encode_opaque(p, buf, len);
 	return 0;
 }
 
-static __be32 idmap_id_to_name(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen)
+static __be32 idmap_id_to_name(struct xdr_stream *xdr,
+			       struct svc_rqst *rqstp, int type, u32 id)
 {
 	struct ent *item, key = {
 		.id = id,
 		.type = type,
 	};
+	__be32 *p;
 	int ret;
-	int bytes;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
 	ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item);
 	if (ret == -ENOENT)
-		return encode_ascii_id(id, p, buflen);
+		return encode_ascii_id(xdr, id);
 	if (ret)
 		return nfserrno(ret);
 	ret = strlen(item->name);
 	WARN_ON_ONCE(ret > IDMAP_NAMESZ);
-	bytes = 4 + (XDR_QUADLEN(ret) << 2);
-	if (bytes > *buflen)
+	p = xdr_reserve_space(xdr, ret + 4);
+	if (!p)
 		return nfserr_resource;
-	*p = xdr_encode_opaque(*p, item->name, ret);
-	*buflen -= bytes;
+	p = xdr_encode_opaque(p, item->name, ret);
 	cache_put(&item->h, nn->idtoname_cache);
 	return 0;
 }
@@ -622,11 +621,12 @@ do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u
 	return idmap_name_to_id(rqstp, type, name, namelen, id);
 }
 
-static __be32 encode_name_from_id(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen)
+static __be32 encode_name_from_id(struct xdr_stream *xdr,
+				  struct svc_rqst *rqstp, int type, u32 id)
 {
 	if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
-		return encode_ascii_id(id, p, buflen);
-	return idmap_id_to_name(rqstp, type, id, p, buflen);
+		return encode_ascii_id(xdr, id);
+	return idmap_id_to_name(xdr, rqstp, type, id);
 }
 
 __be32
@@ -655,14 +655,16 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 	return status;
 }
 
-__be32 nfsd4_encode_user(struct svc_rqst *rqstp, kuid_t uid,  __be32 **p, int *buflen)
+__be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			 kuid_t uid)
 {
 	u32 id = from_kuid(&init_user_ns, uid);
-	return encode_name_from_id(rqstp, IDMAP_TYPE_USER, id, p, buflen);
+	return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id);
 }
 
-__be32 nfsd4_encode_group(struct svc_rqst *rqstp, kgid_t gid, __be32 **p, int *buflen)
+__be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			  kgid_t gid)
 {
 	u32 id = from_kgid(&init_user_ns, gid);
-	return encode_name_from_id(rqstp, IDMAP_TYPE_GROUP, id, p, buflen);
+	return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id);
 }
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index d543222babf..8f029db5d27 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -430,12 +430,12 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 				goto out;
 			break;
 		case NFS4_OPEN_CLAIM_PREVIOUS:
-			open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
 			status = nfs4_check_open_reclaim(&open->op_clientid,
 							 cstate->minorversion,
 							 nn);
 			if (status)
 				goto out;
+			open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
 		case NFS4_OPEN_CLAIM_FH:
 		case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
 			status = do_open_fhandle(rqstp, cstate, open);
@@ -445,7 +445,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			break;
 		case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
              	case NFS4_OPEN_CLAIM_DELEGATE_PREV:
-			open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
 			dprintk("NFSD: unsupported OPEN claim type %d\n",
 				open->op_claim_type);
 			status = nfserr_notsupp;
@@ -618,15 +617,6 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	switch (create->cr_type) {
 	case NF4LNK:
-		/* ugh! we have to null-terminate the linktext, or
-		 * vfs_symlink() will choke.  it is always safe to
-		 * null-terminate by brute force, since at worst we
-		 * will overwrite the first byte of the create namelen
-		 * in the XDR buffer, which has already been extracted
-		 * during XDR decode.
-		 */
-		create->cr_linkname[create->cr_linklen] = 0;
-
 		status = nfsd_symlink(rqstp, &cstate->current_fh,
 				      create->cr_name, create->cr_namelen,
 				      create->cr_linkname, create->cr_linklen,
@@ -786,7 +776,6 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (!nfsd4_last_compound_op(rqstp))
 		rqstp->rq_splice_ok = false;
 
-	nfs4_lock_state();
 	/* check stateid */
 	if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
 						 cstate, &read->rd_stateid,
@@ -794,11 +783,8 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		dprintk("NFSD: nfsd4_read: couldn't process stateid!\n");
 		goto out;
 	}
-	if (read->rd_filp)
-		get_file(read->rd_filp);
 	status = nfs_ok;
 out:
-	nfs4_unlock_state();
 	read->rd_rqstp = rqstp;
 	read->rd_fhp = &cstate->current_fh;
 	return status;
@@ -937,10 +923,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	int err;
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
-		nfs4_lock_state();
 		status = nfs4_preprocess_stateid_op(SVC_NET(rqstp), cstate,
 			&setattr->sa_stateid, WR_STATE, NULL);
-		nfs4_unlock_state();
 		if (status) {
 			dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n");
 			return status;
@@ -1006,17 +990,12 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (write->wr_offset >= OFFSET_MAX)
 		return nfserr_inval;
 
-	nfs4_lock_state();
 	status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
 					cstate, stateid, WR_STATE, &filp);
 	if (status) {
-		nfs4_unlock_state();
 		dprintk("NFSD: nfsd4_write: couldn't process stateid!\n");
 		return status;
 	}
-	if (filp)
-		get_file(filp);
-	nfs4_unlock_state();
 
 	cnt = write->wr_buflen;
 	write->wr_how_written = write->wr_stable_how;
@@ -1072,10 +1051,10 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		return nfserr_jukebox;
 
 	p = buf;
-	status = nfsd4_encode_fattr(&cstate->current_fh,
+	status = nfsd4_encode_fattr_to_buf(&p, count, &cstate->current_fh,
 				    cstate->current_fh.fh_export,
-				    cstate->current_fh.fh_dentry, &p,
-				    count, verify->ve_bmval,
+				    cstate->current_fh.fh_dentry,
+				    verify->ve_bmval,
 				    rqstp, 0);
 	/*
 	 * If nfsd4_encode_fattr() ran out of space, assume that's because
@@ -1182,9 +1161,7 @@ struct nfsd4_operation {
 
 static struct nfsd4_operation nfsd4_ops[];
 
-#ifdef NFSD_DEBUG
 static const char *nfsd4_op_name(unsigned opnum);
-#endif
 
 /*
  * Enforce NFSv4.1 COMPOUND ordering rules:
@@ -1226,6 +1203,8 @@ static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op)
 
 bool nfsd4_cache_this_op(struct nfsd4_op *op)
 {
+	if (op->opnum == OP_ILLEGAL)
+		return false;
 	return OPDESC(op)->op_flags & OP_CACHEME;
 }
 
@@ -1262,6 +1241,25 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp)
 	return !(nextd->op_flags & OP_HANDLES_WRONGSEC);
 }
 
+static void svcxdr_init_encode(struct svc_rqst *rqstp,
+			       struct nfsd4_compoundres *resp)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	struct xdr_buf *buf = &rqstp->rq_res;
+	struct kvec *head = buf->head;
+
+	xdr->buf = buf;
+	xdr->iov = head;
+	xdr->p   = head->iov_base + head->iov_len;
+	xdr->end = head->iov_base + PAGE_SIZE - rqstp->rq_auth_slack;
+	/* Tail and page_len should be zero at this point: */
+	buf->len = buf->head[0].iov_len;
+	xdr->scratch.iov_len = 0;
+	xdr->page_ptr = buf->pages - 1;
+	buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages)
+		- rqstp->rq_auth_slack;
+}
+
 /*
  * COMPOUND call.
  */
@@ -1275,24 +1273,16 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 	struct nfsd4_compound_state *cstate = &resp->cstate;
 	struct svc_fh *current_fh = &cstate->current_fh;
 	struct svc_fh *save_fh = &cstate->save_fh;
-	int		slack_bytes;
-	u32		plen = 0;
 	__be32		status;
 
-	resp->xbuf = &rqstp->rq_res;
-	resp->p = rqstp->rq_res.head[0].iov_base +
-						rqstp->rq_res.head[0].iov_len;
-	resp->tagp = resp->p;
+	svcxdr_init_encode(rqstp, resp);
+	resp->tagp = resp->xdr.p;
 	/* reserve space for: taglen, tag, and opcnt */
-	resp->p += 2 + XDR_QUADLEN(args->taglen);
-	resp->end = rqstp->rq_res.head[0].iov_base + PAGE_SIZE;
+	xdr_reserve_space(&resp->xdr, 8 + args->taglen);
 	resp->taglen = args->taglen;
 	resp->tag = args->tag;
-	resp->opcnt = 0;
 	resp->rqstp = rqstp;
 	cstate->minorversion = args->minorversion;
-	cstate->replay_owner = NULL;
-	cstate->session = NULL;
 	fh_init(current_fh, NFS4_FHSIZE);
 	fh_init(save_fh, NFS4_FHSIZE);
 	/*
@@ -1332,19 +1322,6 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			goto encode_op;
 		}
 
-		/* We must be able to encode a successful response to
-		 * this operation, with enough room left over to encode a
-		 * failed response to the next operation.  If we don't
-		 * have enough room, fail with ERR_RESOURCE.
-		 */
-		slack_bytes = (char *)resp->end - (char *)resp->p;
-		if (slack_bytes < COMPOUND_SLACK_SPACE
-				+ COMPOUND_ERR_SLACK_SPACE) {
-			BUG_ON(slack_bytes < COMPOUND_ERR_SLACK_SPACE);
-			op->status = nfserr_resource;
-			goto encode_op;
-		}
-
 		opdesc = OPDESC(op);
 
 		if (!current_fh->fh_dentry) {
@@ -1362,9 +1339,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 
 		/* If op is non-idempotent */
 		if (opdesc->op_flags & OP_MODIFIES_SOMETHING) {
-			plen = opdesc->op_rsize_bop(rqstp, op);
 			/*
-			 * If there's still another operation, make sure
+			 * Don't execute this op if we couldn't encode a
+			 * succesful reply:
+			 */
+			u32 plen = opdesc->op_rsize_bop(rqstp, op);
+			/*
+			 * Plus if there's another operation, make sure
 			 * we'll have space to at least encode an error:
 			 */
 			if (resp->opcnt < args->opcnt)
@@ -1399,7 +1380,7 @@ encode_op:
 		}
 		if (op->status == nfserr_replay_me) {
 			op->replay = &cstate->replay_owner->so_replay;
-			nfsd4_encode_replay(resp, op);
+			nfsd4_encode_replay(&resp->xdr, op);
 			status = op->status = op->replay->rp_status;
 		} else {
 			nfsd4_encode_operation(resp, op);
@@ -1438,7 +1419,8 @@ out:
 #define op_encode_change_info_maxsz	(5)
 #define nfs4_fattr_bitmap_maxsz		(4)
 
-#define op_encode_lockowner_maxsz	(1 + XDR_QUADLEN(IDMAP_NAMESZ))
+/* We'll fall back on returning no lockowner if run out of space: */
+#define op_encode_lockowner_maxsz	(0)
 #define op_encode_lock_denied_maxsz	(8 + op_encode_lockowner_maxsz)
 
 #define nfs4_owner_maxsz		(1 + XDR_QUADLEN(IDMAP_NAMESZ))
@@ -1470,6 +1452,49 @@ static inline u32 nfsd4_create_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op
 		+ nfs4_fattr_bitmap_maxsz) * sizeof(__be32);
 }
 
+/*
+ * Note since this is an idempotent operation we won't insist on failing
+ * the op prematurely if the estimate is too large.  We may turn off splice
+ * reads unnecessarily.
+ */
+static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp,
+				      struct nfsd4_op *op)
+{
+	u32 *bmap = op->u.getattr.ga_bmval;
+	u32 bmap0 = bmap[0], bmap1 = bmap[1], bmap2 = bmap[2];
+	u32 ret = 0;
+
+	if (bmap0 & FATTR4_WORD0_ACL)
+		return svc_max_payload(rqstp);
+	if (bmap0 & FATTR4_WORD0_FS_LOCATIONS)
+		return svc_max_payload(rqstp);
+
+	if (bmap1 & FATTR4_WORD1_OWNER) {
+		ret += IDMAP_NAMESZ + 4;
+		bmap1 &= ~FATTR4_WORD1_OWNER;
+	}
+	if (bmap1 & FATTR4_WORD1_OWNER_GROUP) {
+		ret += IDMAP_NAMESZ + 4;
+		bmap1 &= ~FATTR4_WORD1_OWNER_GROUP;
+	}
+	if (bmap0 & FATTR4_WORD0_FILEHANDLE) {
+		ret += NFS4_FHSIZE + 4;
+		bmap0 &= ~FATTR4_WORD0_FILEHANDLE;
+	}
+	if (bmap2 & FATTR4_WORD2_SECURITY_LABEL) {
+		ret += NFSD4_MAX_SEC_LABEL_LEN + 12;
+		bmap2 &= ~FATTR4_WORD2_SECURITY_LABEL;
+	}
+	/*
+	 * Largest of remaining attributes are 16 bytes (e.g.,
+	 * supported_attributes)
+	 */
+	ret += 16 * (hweight32(bmap0) + hweight32(bmap1) + hweight32(bmap2));
+	/* bitmask, length */
+	ret += 20;
+	return ret;
+}
+
 static inline u32 nfsd4_link_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_change_info_maxsz)
@@ -1500,18 +1525,19 @@ static inline u32 nfsd4_read_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 	if (rlen > maxcount)
 		rlen = maxcount;
 
-	return (op_encode_hdr_size + 2) * sizeof(__be32) + rlen;
+	return (op_encode_hdr_size + 2 + XDR_QUADLEN(rlen)) * sizeof(__be32);
 }
 
 static inline u32 nfsd4_readdir_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
+	u32 maxcount = svc_max_payload(rqstp);
 	u32 rlen = op->u.readdir.rd_maxcount;
 
-	if (rlen > PAGE_SIZE)
-		rlen = PAGE_SIZE;
+	if (rlen > maxcount)
+		rlen = maxcount;
 
-	return (op_encode_hdr_size + op_encode_verifier_maxsz)
-		 * sizeof(__be32) + rlen;
+	return (op_encode_hdr_size + op_encode_verifier_maxsz +
+		XDR_QUADLEN(rlen)) * sizeof(__be32);
 }
 
 static inline u32 nfsd4_remove_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
@@ -1526,6 +1552,12 @@ static inline u32 nfsd4_rename_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op
 		+ op_encode_change_info_maxsz) * sizeof(__be32);
 }
 
+static inline u32 nfsd4_sequence_rsize(struct svc_rqst *rqstp,
+				       struct nfsd4_op *op)
+{
+	return NFS4_MAX_SESSIONID_LEN + 20;
+}
+
 static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + nfs4_fattr_bitmap_maxsz) * sizeof(__be32);
@@ -1539,7 +1571,7 @@ static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_o
 
 static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
-	return (op_encode_hdr_size + op_encode_verifier_maxsz) * sizeof(__be32);
+	return (op_encode_hdr_size + 2 + op_encode_verifier_maxsz) * sizeof(__be32);
 }
 
 static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
@@ -1607,6 +1639,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	[OP_GETATTR] = {
 		.op_func = (nfsd4op_func)nfsd4_getattr,
 		.op_flags = ALLOWED_ON_ABSENT_FS,
+		.op_rsize_bop = nfsd4_getattr_rsize,
 		.op_name = "OP_GETATTR",
 	},
 	[OP_GETFH] = {
@@ -1676,37 +1709,32 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	[OP_PUTFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
-				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
-				| OP_CLEAR_STATEID,
+				| OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
 		.op_name = "OP_PUTFH",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
 	[OP_PUTPUBFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
-				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
-				| OP_CLEAR_STATEID,
+				| OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
 		.op_name = "OP_PUTPUBFH",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
 	[OP_PUTROOTFH] = {
 		.op_func = (nfsd4op_func)nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
-				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
-				| OP_CLEAR_STATEID,
+				| OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
 		.op_name = "OP_PUTROOTFH",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
 	},
 	[OP_READ] = {
 		.op_func = (nfsd4op_func)nfsd4_read,
-		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_READ",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize,
 		.op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid,
 	},
 	[OP_READDIR] = {
 		.op_func = (nfsd4op_func)nfsd4_readdir,
-		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_READDIR",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_readdir_rsize,
 	},
@@ -1864,14 +1892,33 @@ static struct nfsd4_operation nfsd4_ops[] = {
 	},
 };
 
-#ifdef NFSD_DEBUG
+int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	struct nfsd4_operation *opdesc;
+	nfsd4op_rsize estimator;
+
+	if (op->opnum == OP_ILLEGAL)
+		return op_encode_hdr_size * sizeof(__be32);
+	opdesc = OPDESC(op);
+	estimator = opdesc->op_rsize_bop;
+	return estimator ? estimator(rqstp, op) : PAGE_SIZE;
+}
+
+void warn_on_nonidempotent_op(struct nfsd4_op *op)
+{
+	if (OPDESC(op)->op_flags & OP_MODIFIES_SOMETHING) {
+		pr_err("unable to encode reply to nonidempotent op %d (%s)\n",
+			op->opnum, nfsd4_op_name(op->opnum));
+		WARN_ON_ONCE(1);
+	}
+}
+
 static const char *nfsd4_op_name(unsigned opnum)
 {
 	if (opnum < ARRAY_SIZE(nfsd4_ops))
 		return nfsd4_ops[opnum].op_name;
 	return "unknown_operation";
 }
-#endif
 
 #define nfsd4_voidres			nfsd4_voidargs
 struct nfsd4_voidargs { int dummy; };
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9a77a5a2155..2204e1fe572 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -41,6 +41,7 @@
 #include <linux/ratelimit.h>
 #include <linux/sunrpc/svcauth_gss.h>
 #include <linux/sunrpc/addr.h>
+#include <linux/hash.h>
 #include "xdr4.h"
 #include "xdr4cb.h"
 #include "vfs.h"
@@ -81,13 +82,13 @@ static DEFINE_MUTEX(client_mutex);
  * effort to decrease the scope of the client_mutex, this spinlock may
  * eventually cover more:
  */
-static DEFINE_SPINLOCK(recall_lock);
+static DEFINE_SPINLOCK(state_lock);
 
-static struct kmem_cache *openowner_slab = NULL;
-static struct kmem_cache *lockowner_slab = NULL;
-static struct kmem_cache *file_slab = NULL;
-static struct kmem_cache *stateid_slab = NULL;
-static struct kmem_cache *deleg_slab = NULL;
+static struct kmem_cache *openowner_slab;
+static struct kmem_cache *lockowner_slab;
+static struct kmem_cache *file_slab;
+static struct kmem_cache *stateid_slab;
+static struct kmem_cache *deleg_slab;
 
 void
 nfs4_lock_state(void)
@@ -235,9 +236,9 @@ static void nfsd4_free_file(struct nfs4_file *f)
 static inline void
 put_nfs4_file(struct nfs4_file *fi)
 {
-	if (atomic_dec_and_lock(&fi->fi_ref, &recall_lock)) {
+	if (atomic_dec_and_lock(&fi->fi_ref, &state_lock)) {
 		hlist_del(&fi->fi_hash);
-		spin_unlock(&recall_lock);
+		spin_unlock(&state_lock);
 		iput(fi->fi_inode);
 		nfsd4_free_file(fi);
 	}
@@ -364,6 +365,79 @@ static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp)
 	return openlockstateid(nfs4_alloc_stid(clp, stateid_slab));
 }
 
+/*
+ * When we recall a delegation, we should be careful not to hand it
+ * out again straight away.
+ * To ensure this we keep a pair of bloom filters ('new' and 'old')
+ * in which the filehandles of recalled delegations are "stored".
+ * If a filehandle appear in either filter, a delegation is blocked.
+ * When a delegation is recalled, the filehandle is stored in the "new"
+ * filter.
+ * Every 30 seconds we swap the filters and clear the "new" one,
+ * unless both are empty of course.
+ *
+ * Each filter is 256 bits.  We hash the filehandle to 32bit and use the
+ * low 3 bytes as hash-table indices.
+ *
+ * 'state_lock', which is always held when block_delegations() is called,
+ * is used to manage concurrent access.  Testing does not need the lock
+ * except when swapping the two filters.
+ */
+static struct bloom_pair {
+	int	entries, old_entries;
+	time_t	swap_time;
+	int	new; /* index into 'set' */
+	DECLARE_BITMAP(set[2], 256);
+} blocked_delegations;
+
+static int delegation_blocked(struct knfsd_fh *fh)
+{
+	u32 hash;
+	struct bloom_pair *bd = &blocked_delegations;
+
+	if (bd->entries == 0)
+		return 0;
+	if (seconds_since_boot() - bd->swap_time > 30) {
+		spin_lock(&state_lock);
+		if (seconds_since_boot() - bd->swap_time > 30) {
+			bd->entries -= bd->old_entries;
+			bd->old_entries = bd->entries;
+			memset(bd->set[bd->new], 0,
+			       sizeof(bd->set[0]));
+			bd->new = 1-bd->new;
+			bd->swap_time = seconds_since_boot();
+		}
+		spin_unlock(&state_lock);
+	}
+	hash = arch_fast_hash(&fh->fh_base, fh->fh_size, 0);
+	if (test_bit(hash&255, bd->set[0]) &&
+	    test_bit((hash>>8)&255, bd->set[0]) &&
+	    test_bit((hash>>16)&255, bd->set[0]))
+		return 1;
+
+	if (test_bit(hash&255, bd->set[1]) &&
+	    test_bit((hash>>8)&255, bd->set[1]) &&
+	    test_bit((hash>>16)&255, bd->set[1]))
+		return 1;
+
+	return 0;
+}
+
+static void block_delegations(struct knfsd_fh *fh)
+{
+	u32 hash;
+	struct bloom_pair *bd = &blocked_delegations;
+
+	hash = arch_fast_hash(&fh->fh_base, fh->fh_size, 0);
+
+	__set_bit(hash&255, bd->set[bd->new]);
+	__set_bit((hash>>8)&255, bd->set[bd->new]);
+	__set_bit((hash>>16)&255, bd->set[bd->new]);
+	if (bd->entries == 0)
+		bd->swap_time = seconds_since_boot();
+	bd->entries += 1;
+}
+
 static struct nfs4_delegation *
 alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh)
 {
@@ -372,10 +446,11 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
 	dprintk("NFSD alloc_init_deleg\n");
 	if (num_delegations > max_delegations)
 		return NULL;
+	if (delegation_blocked(&current_fh->fh_handle))
+		return NULL;
 	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
 	if (dp == NULL)
 		return dp;
-	dp->dl_stid.sc_type = NFS4_DELEG_STID;
 	/*
 	 * delegation seqid's are never incremented.  The 4.1 special
 	 * meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -418,6 +493,8 @@ nfs4_put_delegation(struct nfs4_delegation *dp)
 
 static void nfs4_put_deleg_lease(struct nfs4_file *fp)
 {
+	if (!fp->fi_lease)
+		return;
 	if (atomic_dec_and_test(&fp->fi_delegees)) {
 		vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease);
 		fp->fi_lease = NULL;
@@ -431,18 +508,30 @@ static void unhash_stid(struct nfs4_stid *s)
 	s->sc_type = 0;
 }
 
+static void
+hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
+{
+	lockdep_assert_held(&state_lock);
+
+	dp->dl_stid.sc_type = NFS4_DELEG_STID;
+	list_add(&dp->dl_perfile, &fp->fi_delegations);
+	list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
+}
+
 /* Called under the state lock. */
 static void
 unhash_delegation(struct nfs4_delegation *dp)
 {
+	spin_lock(&state_lock);
 	list_del_init(&dp->dl_perclnt);
-	spin_lock(&recall_lock);
 	list_del_init(&dp->dl_perfile);
 	list_del_init(&dp->dl_recall_lru);
-	spin_unlock(&recall_lock);
-	nfs4_put_deleg_lease(dp->dl_file);
-	put_nfs4_file(dp->dl_file);
-	dp->dl_file = NULL;
+	spin_unlock(&state_lock);
+	if (dp->dl_file) {
+		nfs4_put_deleg_lease(dp->dl_file);
+		put_nfs4_file(dp->dl_file);
+		dp->dl_file = NULL;
+	}
 }
 
 
@@ -645,6 +734,12 @@ static void unhash_lockowner(struct nfs4_lockowner *lo)
 	}
 }
 
+static void nfs4_free_lockowner(struct nfs4_lockowner *lo)
+{
+	kfree(lo->lo_owner.so_owner.data);
+	kmem_cache_free(lockowner_slab, lo);
+}
+
 static void release_lockowner(struct nfs4_lockowner *lo)
 {
 	unhash_lockowner(lo);
@@ -699,6 +794,12 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo)
 	}
 }
 
+static void nfs4_free_openowner(struct nfs4_openowner *oo)
+{
+	kfree(oo->oo_owner.so_owner.data);
+	kmem_cache_free(openowner_slab, oo);
+}
+
 static void release_openowner(struct nfs4_openowner *oo)
 {
 	unhash_openowner(oo);
@@ -1093,7 +1194,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 	return clp;
 }
 
-static inline void
+static void
 free_client(struct nfs4_client *clp)
 {
 	struct nfsd_net __maybe_unused *nn = net_generic(clp->net, nfsd_net_id);
@@ -1136,13 +1237,13 @@ destroy_client(struct nfs4_client *clp)
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
 
 	INIT_LIST_HEAD(&reaplist);
-	spin_lock(&recall_lock);
+	spin_lock(&state_lock);
 	while (!list_empty(&clp->cl_delegations)) {
 		dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
 		list_del_init(&dp->dl_perclnt);
 		list_move(&dp->dl_recall_lru, &reaplist);
 	}
-	spin_unlock(&recall_lock);
+	spin_unlock(&state_lock);
 	while (!list_empty(&reaplist)) {
 		dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
 		destroy_delegation(dp);
@@ -1544,6 +1645,7 @@ out_err:
 void
 nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
 {
+	struct xdr_buf *buf = resp->xdr.buf;
 	struct nfsd4_slot *slot = resp->cstate.slot;
 	unsigned int base;
 
@@ -1557,11 +1659,9 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
 		slot->sl_datalen = 0;
 		return;
 	}
-	slot->sl_datalen = (char *)resp->p - (char *)resp->cstate.datap;
-	base = (char *)resp->cstate.datap -
-					(char *)resp->xbuf->head[0].iov_base;
-	if (read_bytes_from_xdr_buf(resp->xbuf, base, slot->sl_data,
-				    slot->sl_datalen))
+	base = resp->cstate.data_offset;
+	slot->sl_datalen = buf->len - base;
+	if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen))
 		WARN("%s: sessions DRC could not cache compound\n", __func__);
 	return;
 }
@@ -1602,6 +1702,8 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
 			 struct nfsd4_sequence *seq)
 {
 	struct nfsd4_slot *slot = resp->cstate.slot;
+	struct xdr_stream *xdr = &resp->xdr;
+	__be32 *p;
 	__be32 status;
 
 	dprintk("--> %s slot %p\n", __func__, slot);
@@ -1610,14 +1712,16 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
 	if (status)
 		return status;
 
-	/* The sequence operation has been encoded, cstate->datap set. */
-	memcpy(resp->cstate.datap, slot->sl_data, slot->sl_datalen);
+	p = xdr_reserve_space(xdr, slot->sl_datalen);
+	if (!p) {
+		WARN_ON_ONCE(1);
+		return nfserr_serverfault;
+	}
+	xdr_encode_opaque_fixed(p, slot->sl_data, slot->sl_datalen);
+	xdr_commit_encode(xdr);
 
 	resp->opcnt = slot->sl_opcnt;
-	resp->p = resp->cstate.datap + XDR_QUADLEN(slot->sl_datalen);
-	status = slot->sl_status;
-
-	return status;
+	return slot->sl_status;
 }
 
 /*
@@ -2189,11 +2293,13 @@ nfsd4_sequence(struct svc_rqst *rqstp,
 	       struct nfsd4_sequence *seq)
 {
 	struct nfsd4_compoundres *resp = rqstp->rq_resp;
+	struct xdr_stream *xdr = &resp->xdr;
 	struct nfsd4_session *session;
 	struct nfs4_client *clp;
 	struct nfsd4_slot *slot;
 	struct nfsd4_conn *conn;
 	__be32 status;
+	int buflen;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	if (resp->opcnt != 1)
@@ -2262,6 +2368,16 @@ nfsd4_sequence(struct svc_rqst *rqstp,
 	if (status)
 		goto out_put_session;
 
+	buflen = (seq->cachethis) ?
+			session->se_fchannel.maxresp_cached :
+			session->se_fchannel.maxresp_sz;
+	status = (seq->cachethis) ? nfserr_rep_too_big_to_cache :
+				    nfserr_rep_too_big;
+	if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack))
+		goto out_put_session;
+	svc_reserve(rqstp, buflen);
+
+	status = nfs_ok;
 	/* Success! bump slot seqid */
 	slot->sl_seqid = seq->seqid;
 	slot->sl_flags |= NFSD4_SLOT_INUSE;
@@ -2499,28 +2615,19 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
 	fp->fi_lease = NULL;
 	memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
-	spin_lock(&recall_lock);
+	spin_lock(&state_lock);
 	hlist_add_head(&fp->fi_hash, &file_hashtbl[hashval]);
-	spin_unlock(&recall_lock);
-}
-
-static void
-nfsd4_free_slab(struct kmem_cache **slab)
-{
-	if (*slab == NULL)
-		return;
-	kmem_cache_destroy(*slab);
-	*slab = NULL;
+	spin_unlock(&state_lock);
 }
 
 void
 nfsd4_free_slabs(void)
 {
-	nfsd4_free_slab(&openowner_slab);
-	nfsd4_free_slab(&lockowner_slab);
-	nfsd4_free_slab(&file_slab);
-	nfsd4_free_slab(&stateid_slab);
-	nfsd4_free_slab(&deleg_slab);
+	kmem_cache_destroy(openowner_slab);
+	kmem_cache_destroy(lockowner_slab);
+	kmem_cache_destroy(file_slab);
+	kmem_cache_destroy(stateid_slab);
+	kmem_cache_destroy(deleg_slab);
 }
 
 int
@@ -2529,42 +2636,38 @@ nfsd4_init_slabs(void)
 	openowner_slab = kmem_cache_create("nfsd4_openowners",
 			sizeof(struct nfs4_openowner), 0, 0, NULL);
 	if (openowner_slab == NULL)
-		goto out_nomem;
+		goto out;
 	lockowner_slab = kmem_cache_create("nfsd4_lockowners",
 			sizeof(struct nfs4_lockowner), 0, 0, NULL);
 	if (lockowner_slab == NULL)
-		goto out_nomem;
+		goto out_free_openowner_slab;
 	file_slab = kmem_cache_create("nfsd4_files",
 			sizeof(struct nfs4_file), 0, 0, NULL);
 	if (file_slab == NULL)
-		goto out_nomem;
+		goto out_free_lockowner_slab;
 	stateid_slab = kmem_cache_create("nfsd4_stateids",
 			sizeof(struct nfs4_ol_stateid), 0, 0, NULL);
 	if (stateid_slab == NULL)
-		goto out_nomem;
+		goto out_free_file_slab;
 	deleg_slab = kmem_cache_create("nfsd4_delegations",
 			sizeof(struct nfs4_delegation), 0, 0, NULL);
 	if (deleg_slab == NULL)
-		goto out_nomem;
+		goto out_free_stateid_slab;
 	return 0;
-out_nomem:
-	nfsd4_free_slabs();
+
+out_free_stateid_slab:
+	kmem_cache_destroy(stateid_slab);
+out_free_file_slab:
+	kmem_cache_destroy(file_slab);
+out_free_lockowner_slab:
+	kmem_cache_destroy(lockowner_slab);
+out_free_openowner_slab:
+	kmem_cache_destroy(openowner_slab);
+out:
 	dprintk("nfsd4: out of memory while initializing nfsv4\n");
 	return -ENOMEM;
 }
 
-void nfs4_free_openowner(struct nfs4_openowner *oo)
-{
-	kfree(oo->oo_owner.so_owner.data);
-	kmem_cache_free(openowner_slab, oo);
-}
-
-void nfs4_free_lockowner(struct nfs4_lockowner *lo)
-{
-	kfree(lo->lo_owner.so_owner.data);
-	kmem_cache_free(lockowner_slab, lo);
-}
-
 static void init_nfs4_replay(struct nfs4_replay *rp)
 {
 	rp->rp_status = nfserr_serverfault;
@@ -2685,15 +2788,15 @@ find_file(struct inode *ino)
 	unsigned int hashval = file_hashval(ino);
 	struct nfs4_file *fp;
 
-	spin_lock(&recall_lock);
+	spin_lock(&state_lock);
 	hlist_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) {
 		if (fp->fi_inode == ino) {
 			get_nfs4_file(fp);
-			spin_unlock(&recall_lock);
+			spin_unlock(&state_lock);
 			return fp;
 		}
 	}
-	spin_unlock(&recall_lock);
+	spin_unlock(&state_lock);
 	return NULL;
 }
 
@@ -2730,6 +2833,7 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 	struct nfs4_client *clp = dp->dl_stid.sc_client;
 	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
 
+	lockdep_assert_held(&state_lock);
 	/* We're assuming the state code never drops its reference
 	 * without first removing the lease.  Since we're in this lease
 	 * callback (and since the lease code is serialized by the kernel
@@ -2742,6 +2846,8 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 	/* Only place dl_time is set; protected by i_lock: */
 	dp->dl_time = get_seconds();
 
+	block_delegations(&dp->dl_fh);
+
 	nfsd4_cb_recall(dp);
 }
 
@@ -2766,11 +2872,11 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
 	 */
 	fl->fl_break_time = 0;
 
-	spin_lock(&recall_lock);
+	spin_lock(&state_lock);
 	fp->fi_had_conflict = true;
 	list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
 		nfsd_break_one_deleg(dp);
-	spin_unlock(&recall_lock);
+	spin_unlock(&state_lock);
 }
 
 static
@@ -3047,11 +3153,12 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
 	status = vfs_setlease(fl->fl_file, fl->fl_type, &fl);
 	if (status)
 		goto out_free;
-	list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
 	fp->fi_lease = fl;
 	fp->fi_deleg_file = get_file(fl->fl_file);
 	atomic_set(&fp->fi_delegees, 1);
-	list_add(&dp->dl_perfile, &fp->fi_delegations);
+	spin_lock(&state_lock);
+	hash_delegation_locked(dp, fp);
+	spin_unlock(&state_lock);
 	return 0;
 out_free:
 	locks_free_lock(fl);
@@ -3060,33 +3167,21 @@ out_free:
 
 static int nfs4_set_delegation(struct nfs4_delegation *dp, struct nfs4_file *fp)
 {
-	int status;
-
 	if (fp->fi_had_conflict)
 		return -EAGAIN;
 	get_nfs4_file(fp);
 	dp->dl_file = fp;
-	if (!fp->fi_lease) {
-		status = nfs4_setlease(dp);
-		if (status)
-			goto out_free;
-		return 0;
-	}
-	spin_lock(&recall_lock);
+	if (!fp->fi_lease)
+		return nfs4_setlease(dp);
+	spin_lock(&state_lock);
+	atomic_inc(&fp->fi_delegees);
 	if (fp->fi_had_conflict) {
-		spin_unlock(&recall_lock);
-		status = -EAGAIN;
-		goto out_free;
+		spin_unlock(&state_lock);
+		return -EAGAIN;
 	}
-	atomic_inc(&fp->fi_delegees);
-	list_add(&dp->dl_perfile, &fp->fi_delegations);
-	spin_unlock(&recall_lock);
-	list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
+	hash_delegation_locked(dp, fp);
+	spin_unlock(&state_lock);
 	return 0;
-out_free:
-	put_nfs4_file(fp);
-	dp->dl_file = fp;
-	return status;
 }
 
 static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
@@ -3173,8 +3268,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh,
 	open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
 	return;
 out_free:
-	remove_stid(&dp->dl_stid);
-	nfs4_put_delegation(dp);
+	destroy_delegation(dp);
 out_no_deleg:
 	open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE;
 	if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
@@ -3391,8 +3485,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 	struct nfs4_delegation *dp;
 	struct list_head *pos, *next, reaplist;
 	time_t cutoff = get_seconds() - nn->nfsd4_lease;
-	time_t t, clientid_val = nn->nfsd4_lease;
-	time_t u, test_val = nn->nfsd4_lease;
+	time_t t, new_timeo = nn->nfsd4_lease;
 
 	nfs4_lock_state();
 
@@ -3404,8 +3497,7 @@ nfs4_laundromat(struct nfsd_net *nn)
 		clp = list_entry(pos, struct nfs4_client, cl_lru);
 		if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) {
 			t = clp->cl_time - cutoff;
-			if (clientid_val > t)
-				clientid_val = t;
+			new_timeo = min(new_timeo, t);
 			break;
 		}
 		if (mark_client_expired_locked(clp)) {
@@ -3422,39 +3514,35 @@ nfs4_laundromat(struct nfsd_net *nn)
 			clp->cl_clientid.cl_id);
 		expire_client(clp);
 	}
-	spin_lock(&recall_lock);
+	spin_lock(&state_lock);
 	list_for_each_safe(pos, next, &nn->del_recall_lru) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
 		if (net_generic(dp->dl_stid.sc_client->net, nfsd_net_id) != nn)
 			continue;
 		if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) {
-			u = dp->dl_time - cutoff;
-			if (test_val > u)
-				test_val = u;
+			t = dp->dl_time - cutoff;
+			new_timeo = min(new_timeo, t);
 			break;
 		}
 		list_move(&dp->dl_recall_lru, &reaplist);
 	}
-	spin_unlock(&recall_lock);
+	spin_unlock(&state_lock);
 	list_for_each_safe(pos, next, &reaplist) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
 		revoke_delegation(dp);
 	}
-	test_val = nn->nfsd4_lease;
 	list_for_each_safe(pos, next, &nn->close_lru) {
 		oo = container_of(pos, struct nfs4_openowner, oo_close_lru);
 		if (time_after((unsigned long)oo->oo_time, (unsigned long)cutoff)) {
-			u = oo->oo_time - cutoff;
-			if (test_val > u)
-				test_val = u;
+			t = oo->oo_time - cutoff;
+			new_timeo = min(new_timeo, t);
 			break;
 		}
 		release_openowner(oo);
 	}
-	if (clientid_val < NFSD_LAUNDROMAT_MINTIMEOUT)
-		clientid_val = NFSD_LAUNDROMAT_MINTIMEOUT;
+	new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
 	nfs4_unlock_state();
-	return clientid_val;
+	return new_timeo;
 }
 
 static struct workqueue_struct *laundry_wq;
@@ -3654,6 +3742,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
 	struct svc_fh *current_fh = &cstate->current_fh;
 	struct inode *ino = current_fh->fh_dentry->d_inode;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct file *file = NULL;
 	__be32 status;
 
 	if (filpp)
@@ -3665,10 +3754,12 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
 		return check_special_stateids(net, current_fh, stateid, flags);
 
+	nfs4_lock_state();
+
 	status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
 				      &s, cstate->minorversion, nn);
 	if (status)
-		return status;
+		goto out;
 	status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate));
 	if (status)
 		goto out;
@@ -3679,8 +3770,8 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
 		if (status)
 			goto out;
 		if (filpp) {
-			*filpp = dp->dl_file->fi_deleg_file;
-			if (!*filpp) {
+			file = dp->dl_file->fi_deleg_file;
+			if (!file) {
 				WARN_ON_ONCE(1);
 				status = nfserr_serverfault;
 				goto out;
@@ -3701,16 +3792,20 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
 			goto out;
 		if (filpp) {
 			if (flags & RD_STATE)
-				*filpp = find_readable_file(stp->st_file);
+				file = find_readable_file(stp->st_file);
 			else
-				*filpp = find_writeable_file(stp->st_file);
+				file = find_writeable_file(stp->st_file);
 		}
 		break;
 	default:
-		return nfserr_bad_stateid;
+		status = nfserr_bad_stateid;
+		goto out;
 	}
 	status = nfs_ok;
+	if (file)
+		*filpp = get_file(file);
 out:
+	nfs4_unlock_state();
 	return status;
 }
 
@@ -3726,7 +3821,7 @@ nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
 	 * correspondance, and we have to delete the lockowner when we
 	 * delete the lock stateid:
 	 */
-	unhash_lockowner(lo);
+	release_lockowner(lo);
 	return nfs_ok;
 }
 
@@ -4896,6 +4991,7 @@ static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max,
 	struct nfs4_delegation *dp, *next;
 	u64 count = 0;
 
+	lockdep_assert_held(&state_lock);
 	list_for_each_entry_safe(dp, next, &clp->cl_delegations, dl_perclnt) {
 		if (victims)
 			list_move(&dp->dl_recall_lru, victims);
@@ -4911,9 +5007,9 @@ u64 nfsd_forget_client_delegations(struct nfs4_client *clp, u64 max)
 	LIST_HEAD(victims);
 	u64 count;
 
-	spin_lock(&recall_lock);
+	spin_lock(&state_lock);
 	count = nfsd_find_all_delegations(clp, max, &victims);
-	spin_unlock(&recall_lock);
+	spin_unlock(&state_lock);
 
 	list_for_each_entry_safe(dp, next, &victims, dl_recall_lru)
 		revoke_delegation(dp);
@@ -4927,11 +5023,11 @@ u64 nfsd_recall_client_delegations(struct nfs4_client *clp, u64 max)
 	LIST_HEAD(victims);
 	u64 count;
 
-	spin_lock(&recall_lock);
+	spin_lock(&state_lock);
 	count = nfsd_find_all_delegations(clp, max, &victims);
 	list_for_each_entry_safe(dp, next, &victims, dl_recall_lru)
 		nfsd_break_one_deleg(dp);
-	spin_unlock(&recall_lock);
+	spin_unlock(&state_lock);
 
 	return count;
 }
@@ -4940,9 +5036,9 @@ u64 nfsd_print_client_delegations(struct nfs4_client *clp, u64 max)
 {
 	u64 count = 0;
 
-	spin_lock(&recall_lock);
+	spin_lock(&state_lock);
 	count = nfsd_find_all_delegations(clp, max, NULL);
-	spin_unlock(&recall_lock);
+	spin_unlock(&state_lock);
 
 	nfsd_print_count(clp, count, "delegations");
 	return count;
@@ -4983,13 +5079,6 @@ struct nfs4_client *nfsd_find_client(struct sockaddr_storage *addr, size_t addr_
 
 #endif /* CONFIG_NFSD_FAULT_INJECTION */
 
-/* initialization to perform at module load time: */
-
-void
-nfs4_state_init(void)
-{
-}
-
 /*
  * Since the lifetime of a delegation isn't limited to that of an open, a
  * client may quite reasonably hang on to a delegation as long as it has
@@ -5160,12 +5249,12 @@ nfs4_state_shutdown_net(struct net *net)
 
 	nfs4_lock_state();
 	INIT_LIST_HEAD(&reaplist);
-	spin_lock(&recall_lock);
+	spin_lock(&state_lock);
 	list_for_each_safe(pos, next, &nn->del_recall_lru) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
 		list_move(&dp->dl_recall_lru, &reaplist);
 	}
-	spin_unlock(&recall_lock);
+	spin_unlock(&state_lock);
 	list_for_each_safe(pos, next, &reaplist) {
 		dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
 		destroy_delegation(dp);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 18881f34737..944275c8f56 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -98,11 +98,6 @@ xdr_error:					\
 	status = nfserr_bad_xdr;		\
 	goto out
 
-#define READ32(x)         (x) = ntohl(*p++)
-#define READ64(x)         do {			\
-	(x) = (u64)ntohl(*p++) << 32;		\
-	(x) |= ntohl(*p++);			\
-} while (0)
 #define READMEM(x,nbytes) do {			\
 	x = (char *)p;				\
 	p += XDR_QUADLEN(nbytes);		\
@@ -248,17 +243,17 @@ nfsd4_decode_bitmap(struct nfsd4_compoundargs *argp, u32 *bmval)
 	bmval[2] = 0;
 
 	READ_BUF(4);
-	READ32(bmlen);
+	bmlen = be32_to_cpup(p++);
 	if (bmlen > 1000)
 		goto xdr_error;
 
 	READ_BUF(bmlen << 2);
 	if (bmlen > 0)
-		READ32(bmval[0]);
+		bmval[0] = be32_to_cpup(p++);
 	if (bmlen > 1)
-		READ32(bmval[1]);
+		bmval[1] = be32_to_cpup(p++);
 	if (bmlen > 2)
-		READ32(bmval[2]);
+		bmval[2] = be32_to_cpup(p++);
 
 	DECODE_TAIL;
 }
@@ -270,6 +265,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 {
 	int expected_len, len = 0;
 	u32 dummy32;
+	u64 sec;
 	char *buf;
 
 	DECODE_HEAD;
@@ -278,12 +274,12 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		return status;
 
 	READ_BUF(4);
-	READ32(expected_len);
+	expected_len = be32_to_cpup(p++);
 
 	if (bmval[0] & FATTR4_WORD0_SIZE) {
 		READ_BUF(8);
 		len += 8;
-		READ64(iattr->ia_size);
+		p = xdr_decode_hyper(p, &iattr->ia_size);
 		iattr->ia_valid |= ATTR_SIZE;
 	}
 	if (bmval[0] & FATTR4_WORD0_ACL) {
@@ -291,7 +287,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		struct nfs4_ace *ace;
 
 		READ_BUF(4); len += 4;
-		READ32(nace);
+		nace = be32_to_cpup(p++);
 
 		if (nace > NFS4_ACL_MAX)
 			return nfserr_fbig;
@@ -305,10 +301,10 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 		(*acl)->naces = nace;
 		for (ace = (*acl)->aces; ace < (*acl)->aces + nace; ace++) {
 			READ_BUF(16); len += 16;
-			READ32(ace->type);
-			READ32(ace->flag);
-			READ32(ace->access_mask);
-			READ32(dummy32);
+			ace->type = be32_to_cpup(p++);
+			ace->flag = be32_to_cpup(p++);
+			ace->access_mask = be32_to_cpup(p++);
+			dummy32 = be32_to_cpup(p++);
 			READ_BUF(dummy32);
 			len += XDR_QUADLEN(dummy32) << 2;
 			READMEM(buf, dummy32);
@@ -330,14 +326,14 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 	if (bmval[1] & FATTR4_WORD1_MODE) {
 		READ_BUF(4);
 		len += 4;
-		READ32(iattr->ia_mode);
+		iattr->ia_mode = be32_to_cpup(p++);
 		iattr->ia_mode &= (S_IFMT | S_IALLUGO);
 		iattr->ia_valid |= ATTR_MODE;
 	}
 	if (bmval[1] & FATTR4_WORD1_OWNER) {
 		READ_BUF(4);
 		len += 4;
-		READ32(dummy32);
+		dummy32 = be32_to_cpup(p++);
 		READ_BUF(dummy32);
 		len += (XDR_QUADLEN(dummy32) << 2);
 		READMEM(buf, dummy32);
@@ -348,7 +344,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 	if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) {
 		READ_BUF(4);
 		len += 4;
-		READ32(dummy32);
+		dummy32 = be32_to_cpup(p++);
 		READ_BUF(dummy32);
 		len += (XDR_QUADLEN(dummy32) << 2);
 		READMEM(buf, dummy32);
@@ -359,15 +355,16 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 	if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) {
 		READ_BUF(4);
 		len += 4;
-		READ32(dummy32);
+		dummy32 = be32_to_cpup(p++);
 		switch (dummy32) {
 		case NFS4_SET_TO_CLIENT_TIME:
 			/* We require the high 32 bits of 'seconds' to be 0, and we ignore
 			   all 32 bits of 'nseconds'. */
 			READ_BUF(12);
 			len += 12;
-			READ64(iattr->ia_atime.tv_sec);
-			READ32(iattr->ia_atime.tv_nsec);
+			p = xdr_decode_hyper(p, &sec);
+			iattr->ia_atime.tv_sec = (time_t)sec;
+			iattr->ia_atime.tv_nsec = be32_to_cpup(p++);
 			if (iattr->ia_atime.tv_nsec >= (u32)1000000000)
 				return nfserr_inval;
 			iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET);
@@ -382,15 +379,16 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 	if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) {
 		READ_BUF(4);
 		len += 4;
-		READ32(dummy32);
+		dummy32 = be32_to_cpup(p++);
 		switch (dummy32) {
 		case NFS4_SET_TO_CLIENT_TIME:
 			/* We require the high 32 bits of 'seconds' to be 0, and we ignore
 			   all 32 bits of 'nseconds'. */
 			READ_BUF(12);
 			len += 12;
-			READ64(iattr->ia_mtime.tv_sec);
-			READ32(iattr->ia_mtime.tv_nsec);
+			p = xdr_decode_hyper(p, &sec);
+			iattr->ia_mtime.tv_sec = sec;
+			iattr->ia_mtime.tv_nsec = be32_to_cpup(p++);
 			if (iattr->ia_mtime.tv_nsec >= (u32)1000000000)
 				return nfserr_inval;
 			iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET);
@@ -408,13 +406,13 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
 	if (bmval[2] & FATTR4_WORD2_SECURITY_LABEL) {
 		READ_BUF(4);
 		len += 4;
-		READ32(dummy32); /* lfs: we don't use it */
+		dummy32 = be32_to_cpup(p++); /* lfs: we don't use it */
 		READ_BUF(4);
 		len += 4;
-		READ32(dummy32); /* pi: we don't use it either */
+		dummy32 = be32_to_cpup(p++); /* pi: we don't use it either */
 		READ_BUF(4);
 		len += 4;
-		READ32(dummy32);
+		dummy32 = be32_to_cpup(p++);
 		READ_BUF(dummy32);
 		if (dummy32 > NFSD4_MAX_SEC_LABEL_LEN)
 			return nfserr_badlabel;
@@ -445,7 +443,7 @@ nfsd4_decode_stateid(struct nfsd4_compoundargs *argp, stateid_t *sid)
 	DECODE_HEAD;
 
 	READ_BUF(sizeof(stateid_t));
-	READ32(sid->si_generation);
+	sid->si_generation = be32_to_cpup(p++);
 	COPYMEM(&sid->si_opaque, sizeof(stateid_opaque_t));
 
 	DECODE_TAIL;
@@ -457,7 +455,7 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(access->ac_req_access);
+	access->ac_req_access = be32_to_cpup(p++);
 
 	DECODE_TAIL;
 }
@@ -472,7 +470,7 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_
 
 	/* callback_sec_params4 */
 	READ_BUF(4);
-	READ32(nr_secflavs);
+	nr_secflavs = be32_to_cpup(p++);
 	if (nr_secflavs)
 		cbs->flavor = (u32)(-1);
 	else
@@ -480,7 +478,7 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_
 		cbs->flavor = 0;
 	for (i = 0; i < nr_secflavs; ++i) {
 		READ_BUF(4);
-		READ32(dummy);
+		dummy = be32_to_cpup(p++);
 		switch (dummy) {
 		case RPC_AUTH_NULL:
 			/* Nothing to read */
@@ -490,21 +488,21 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_
 		case RPC_AUTH_UNIX:
 			READ_BUF(8);
 			/* stamp */
-			READ32(dummy);
+			dummy = be32_to_cpup(p++);
 
 			/* machine name */
-			READ32(dummy);
+			dummy = be32_to_cpup(p++);
 			READ_BUF(dummy);
 			SAVEMEM(machine_name, dummy);
 
 			/* uid, gid */
 			READ_BUF(8);
-			READ32(uid);
-			READ32(gid);
+			uid = be32_to_cpup(p++);
+			gid = be32_to_cpup(p++);
 
 			/* more gids */
 			READ_BUF(4);
-			READ32(dummy);
+			dummy = be32_to_cpup(p++);
 			READ_BUF(dummy * 4);
 			if (cbs->flavor == (u32)(-1)) {
 				kuid_t kuid = make_kuid(&init_user_ns, uid);
@@ -524,14 +522,14 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_
 				"not supported!\n");
 			READ_BUF(8);
 			/* gcbp_service */
-			READ32(dummy);
+			dummy = be32_to_cpup(p++);
 			/* gcbp_handle_from_server */
-			READ32(dummy);
+			dummy = be32_to_cpup(p++);
 			READ_BUF(dummy);
 			p += XDR_QUADLEN(dummy);
 			/* gcbp_handle_from_client */
 			READ_BUF(4);
-			READ32(dummy);
+			dummy = be32_to_cpup(p++);
 			READ_BUF(dummy);
 			break;
 		default:
@@ -547,7 +545,7 @@ static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, stru
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(bc->bc_cb_program);
+	bc->bc_cb_program = be32_to_cpup(p++);
 	nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec);
 
 	DECODE_TAIL;
@@ -559,7 +557,7 @@ static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp,
 
 	READ_BUF(NFS4_MAX_SESSIONID_LEN + 8);
 	COPYMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
-	READ32(bcts->dir);
+	bcts->dir = be32_to_cpup(p++);
 	/* XXX: skipping ctsa_use_conn_in_rdma_mode.  Perhaps Tom Tucker
 	 * could help us figure out we should be using it. */
 	DECODE_TAIL;
@@ -571,7 +569,7 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close)
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(close->cl_seqid);
+	close->cl_seqid = be32_to_cpup(p++);
 	return nfsd4_decode_stateid(argp, &close->cl_stateid);
 
 	DECODE_TAIL;
@@ -584,8 +582,8 @@ nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit
 	DECODE_HEAD;
 
 	READ_BUF(12);
-	READ64(commit->co_offset);
-	READ32(commit->co_count);
+	p = xdr_decode_hyper(p, &commit->co_offset);
+	commit->co_count = be32_to_cpup(p++);
 
 	DECODE_TAIL;
 }
@@ -596,19 +594,30 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(create->cr_type);
+	create->cr_type = be32_to_cpup(p++);
 	switch (create->cr_type) {
 	case NF4LNK:
 		READ_BUF(4);
-		READ32(create->cr_linklen);
+		create->cr_linklen = be32_to_cpup(p++);
 		READ_BUF(create->cr_linklen);
-		SAVEMEM(create->cr_linkname, create->cr_linklen);
+		/*
+		 * The VFS will want a null-terminated string, and
+		 * null-terminating in place isn't safe since this might
+		 * end on a page boundary:
+		 */
+		create->cr_linkname =
+				kmalloc(create->cr_linklen + 1, GFP_KERNEL);
+		if (!create->cr_linkname)
+			return nfserr_jukebox;
+		memcpy(create->cr_linkname, p, create->cr_linklen);
+		create->cr_linkname[create->cr_linklen] = '\0';
+		defer_free(argp, kfree, create->cr_linkname);
 		break;
 	case NF4BLK:
 	case NF4CHR:
 		READ_BUF(8);
-		READ32(create->cr_specdata1);
-		READ32(create->cr_specdata2);
+		create->cr_specdata1 = be32_to_cpup(p++);
+		create->cr_specdata2 = be32_to_cpup(p++);
 		break;
 	case NF4SOCK:
 	case NF4FIFO:
@@ -618,7 +627,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create
 	}
 
 	READ_BUF(4);
-	READ32(create->cr_namelen);
+	create->cr_namelen = be32_to_cpup(p++);
 	READ_BUF(create->cr_namelen);
 	SAVEMEM(create->cr_name, create->cr_namelen);
 	if ((status = check_filename(create->cr_name, create->cr_namelen)))
@@ -650,7 +659,7 @@ nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link)
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(link->li_namelen);
+	link->li_namelen = be32_to_cpup(p++);
 	READ_BUF(link->li_namelen);
 	SAVEMEM(link->li_name, link->li_namelen);
 	if ((status = check_filename(link->li_name, link->li_namelen)))
@@ -668,24 +677,24 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
 	* type, reclaim(boolean), offset, length, new_lock_owner(boolean)
 	*/
 	READ_BUF(28);
-	READ32(lock->lk_type);
+	lock->lk_type = be32_to_cpup(p++);
 	if ((lock->lk_type < NFS4_READ_LT) || (lock->lk_type > NFS4_WRITEW_LT))
 		goto xdr_error;
-	READ32(lock->lk_reclaim);
-	READ64(lock->lk_offset);
-	READ64(lock->lk_length);
-	READ32(lock->lk_is_new);
+	lock->lk_reclaim = be32_to_cpup(p++);
+	p = xdr_decode_hyper(p, &lock->lk_offset);
+	p = xdr_decode_hyper(p, &lock->lk_length);
+	lock->lk_is_new = be32_to_cpup(p++);
 
 	if (lock->lk_is_new) {
 		READ_BUF(4);
-		READ32(lock->lk_new_open_seqid);
+		lock->lk_new_open_seqid = be32_to_cpup(p++);
 		status = nfsd4_decode_stateid(argp, &lock->lk_new_open_stateid);
 		if (status)
 			return status;
 		READ_BUF(8 + sizeof(clientid_t));
-		READ32(lock->lk_new_lock_seqid);
+		lock->lk_new_lock_seqid = be32_to_cpup(p++);
 		COPYMEM(&lock->lk_new_clientid, sizeof(clientid_t));
-		READ32(lock->lk_new_owner.len);
+		lock->lk_new_owner.len = be32_to_cpup(p++);
 		READ_BUF(lock->lk_new_owner.len);
 		READMEM(lock->lk_new_owner.data, lock->lk_new_owner.len);
 	} else {
@@ -693,7 +702,7 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock)
 		if (status)
 			return status;
 		READ_BUF(4);
-		READ32(lock->lk_old_lock_seqid);
+		lock->lk_old_lock_seqid = be32_to_cpup(p++);
 	}
 
 	DECODE_TAIL;
@@ -705,13 +714,13 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt)
 	DECODE_HEAD;
 		        
 	READ_BUF(32);
-	READ32(lockt->lt_type);
+	lockt->lt_type = be32_to_cpup(p++);
 	if((lockt->lt_type < NFS4_READ_LT) || (lockt->lt_type > NFS4_WRITEW_LT))
 		goto xdr_error;
-	READ64(lockt->lt_offset);
-	READ64(lockt->lt_length);
+	p = xdr_decode_hyper(p, &lockt->lt_offset);
+	p = xdr_decode_hyper(p, &lockt->lt_length);
 	COPYMEM(&lockt->lt_clientid, 8);
-	READ32(lockt->lt_owner.len);
+	lockt->lt_owner.len = be32_to_cpup(p++);
 	READ_BUF(lockt->lt_owner.len);
 	READMEM(lockt->lt_owner.data, lockt->lt_owner.len);
 
@@ -724,16 +733,16 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku)
 	DECODE_HEAD;
 
 	READ_BUF(8);
-	READ32(locku->lu_type);
+	locku->lu_type = be32_to_cpup(p++);
 	if ((locku->lu_type < NFS4_READ_LT) || (locku->lu_type > NFS4_WRITEW_LT))
 		goto xdr_error;
-	READ32(locku->lu_seqid);
+	locku->lu_seqid = be32_to_cpup(p++);
 	status = nfsd4_decode_stateid(argp, &locku->lu_stateid);
 	if (status)
 		return status;
 	READ_BUF(16);
-	READ64(locku->lu_offset);
-	READ64(locku->lu_length);
+	p = xdr_decode_hyper(p, &locku->lu_offset);
+	p = xdr_decode_hyper(p, &locku->lu_length);
 
 	DECODE_TAIL;
 }
@@ -744,7 +753,7 @@ nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(lookup->lo_len);
+	lookup->lo_len = be32_to_cpup(p++);
 	READ_BUF(lookup->lo_len);
 	SAVEMEM(lookup->lo_name, lookup->lo_len);
 	if ((status = check_filename(lookup->lo_name, lookup->lo_len)))
@@ -759,7 +768,7 @@ static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *sh
 	u32 w;
 
 	READ_BUF(4);
-	READ32(w);
+	w = be32_to_cpup(p++);
 	*share_access = w & NFS4_SHARE_ACCESS_MASK;
 	*deleg_want = w & NFS4_SHARE_WANT_MASK;
 	if (deleg_when)
@@ -811,7 +820,7 @@ static __be32 nfsd4_decode_share_deny(struct nfsd4_compoundargs *argp, u32 *x)
 	__be32 *p;
 
 	READ_BUF(4);
-	READ32(*x);
+	*x = be32_to_cpup(p++);
 	/* Note: unlinke access bits, deny bits may be zero. */
 	if (*x & ~NFS4_SHARE_DENY_BOTH)
 		return nfserr_bad_xdr;
@@ -825,7 +834,7 @@ static __be32 nfsd4_decode_opaque(struct nfsd4_compoundargs *argp, struct xdr_ne
 	__be32 *p;
 
 	READ_BUF(4);
-	READ32(o->len);
+	o->len = be32_to_cpup(p++);
 
 	if (o->len == 0 || o->len > NFS4_OPAQUE_LIMIT)
 		return nfserr_bad_xdr;
@@ -850,7 +859,7 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 	open->op_xdr_error = 0;
 	/* seqid, share_access, share_deny, clientid, ownerlen */
 	READ_BUF(4);
-	READ32(open->op_seqid);
+	open->op_seqid = be32_to_cpup(p++);
 	/* decode, yet ignore deleg_when until supported */
 	status = nfsd4_decode_share_access(argp, &open->op_share_access,
 					   &open->op_deleg_want, &dummy);
@@ -865,13 +874,13 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 	if (status)
 		goto xdr_error;
 	READ_BUF(4);
-	READ32(open->op_create);
+	open->op_create = be32_to_cpup(p++);
 	switch (open->op_create) {
 	case NFS4_OPEN_NOCREATE:
 		break;
 	case NFS4_OPEN_CREATE:
 		READ_BUF(4);
-		READ32(open->op_createmode);
+		open->op_createmode = be32_to_cpup(p++);
 		switch (open->op_createmode) {
 		case NFS4_CREATE_UNCHECKED:
 		case NFS4_CREATE_GUARDED:
@@ -904,12 +913,12 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 
 	/* open_claim */
 	READ_BUF(4);
-	READ32(open->op_claim_type);
+	open->op_claim_type = be32_to_cpup(p++);
 	switch (open->op_claim_type) {
 	case NFS4_OPEN_CLAIM_NULL:
 	case NFS4_OPEN_CLAIM_DELEGATE_PREV:
 		READ_BUF(4);
-		READ32(open->op_fname.len);
+		open->op_fname.len = be32_to_cpup(p++);
 		READ_BUF(open->op_fname.len);
 		SAVEMEM(open->op_fname.data, open->op_fname.len);
 		if ((status = check_filename(open->op_fname.data, open->op_fname.len)))
@@ -917,14 +926,14 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
 		break;
 	case NFS4_OPEN_CLAIM_PREVIOUS:
 		READ_BUF(4);
-		READ32(open->op_delegate_type);
+		open->op_delegate_type = be32_to_cpup(p++);
 		break;
 	case NFS4_OPEN_CLAIM_DELEGATE_CUR:
 		status = nfsd4_decode_stateid(argp, &open->op_delegate_stateid);
 		if (status)
 			return status;
 		READ_BUF(4);
-		READ32(open->op_fname.len);
+		open->op_fname.len = be32_to_cpup(p++);
 		READ_BUF(open->op_fname.len);
 		SAVEMEM(open->op_fname.data, open->op_fname.len);
 		if ((status = check_filename(open->op_fname.data, open->op_fname.len)))
@@ -962,7 +971,7 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con
 	if (status)
 		return status;
 	READ_BUF(4);
-	READ32(open_conf->oc_seqid);
+	open_conf->oc_seqid = be32_to_cpup(p++);
 
 	DECODE_TAIL;
 }
@@ -976,7 +985,7 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d
 	if (status)
 		return status;
 	READ_BUF(4);
-	READ32(open_down->od_seqid);
+	open_down->od_seqid = be32_to_cpup(p++);
 	status = nfsd4_decode_share_access(argp, &open_down->od_share_access,
 					   &open_down->od_deleg_want, NULL);
 	if (status)
@@ -993,7 +1002,7 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh)
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(putfh->pf_fhlen);
+	putfh->pf_fhlen = be32_to_cpup(p++);
 	if (putfh->pf_fhlen > NFS4_FHSIZE)
 		goto xdr_error;
 	READ_BUF(putfh->pf_fhlen);
@@ -1019,8 +1028,8 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read)
 	if (status)
 		return status;
 	READ_BUF(12);
-	READ64(read->rd_offset);
-	READ32(read->rd_length);
+	p = xdr_decode_hyper(p, &read->rd_offset);
+	read->rd_length = be32_to_cpup(p++);
 
 	DECODE_TAIL;
 }
@@ -1031,10 +1040,10 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read
 	DECODE_HEAD;
 
 	READ_BUF(24);
-	READ64(readdir->rd_cookie);
+	p = xdr_decode_hyper(p, &readdir->rd_cookie);
 	COPYMEM(readdir->rd_verf.data, sizeof(readdir->rd_verf.data));
-	READ32(readdir->rd_dircount);    /* just in case you needed a useless field... */
-	READ32(readdir->rd_maxcount);
+	readdir->rd_dircount = be32_to_cpup(p++);
+	readdir->rd_maxcount = be32_to_cpup(p++);
 	if ((status = nfsd4_decode_bitmap(argp, readdir->rd_bmval)))
 		goto out;
 
@@ -1047,7 +1056,7 @@ nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(remove->rm_namelen);
+	remove->rm_namelen = be32_to_cpup(p++);
 	READ_BUF(remove->rm_namelen);
 	SAVEMEM(remove->rm_name, remove->rm_namelen);
 	if ((status = check_filename(remove->rm_name, remove->rm_namelen)))
@@ -1062,10 +1071,10 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(rename->rn_snamelen);
+	rename->rn_snamelen = be32_to_cpup(p++);
 	READ_BUF(rename->rn_snamelen + 4);
 	SAVEMEM(rename->rn_sname, rename->rn_snamelen);
-	READ32(rename->rn_tnamelen);
+	rename->rn_tnamelen = be32_to_cpup(p++);
 	READ_BUF(rename->rn_tnamelen);
 	SAVEMEM(rename->rn_tname, rename->rn_tnamelen);
 	if ((status = check_filename(rename->rn_sname, rename->rn_snamelen)))
@@ -1097,7 +1106,7 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp,
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(secinfo->si_namelen);
+	secinfo->si_namelen = be32_to_cpup(p++);
 	READ_BUF(secinfo->si_namelen);
 	SAVEMEM(secinfo->si_name, secinfo->si_namelen);
 	status = check_filename(secinfo->si_name, secinfo->si_namelen);
@@ -1113,7 +1122,7 @@ nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp,
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(sin->sin_style);
+	sin->sin_style = be32_to_cpup(p++);
 	DECODE_TAIL;
 }
 
@@ -1144,16 +1153,16 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient
 	if (status)
 		return nfserr_bad_xdr;
 	READ_BUF(8);
-	READ32(setclientid->se_callback_prog);
-	READ32(setclientid->se_callback_netid_len);
+	setclientid->se_callback_prog = be32_to_cpup(p++);
+	setclientid->se_callback_netid_len = be32_to_cpup(p++);
 
 	READ_BUF(setclientid->se_callback_netid_len + 4);
 	SAVEMEM(setclientid->se_callback_netid_val, setclientid->se_callback_netid_len);
-	READ32(setclientid->se_callback_addr_len);
+	setclientid->se_callback_addr_len = be32_to_cpup(p++);
 
 	READ_BUF(setclientid->se_callback_addr_len + 4);
 	SAVEMEM(setclientid->se_callback_addr_val, setclientid->se_callback_addr_len);
-	READ32(setclientid->se_callback_ident);
+	setclientid->se_callback_ident = be32_to_cpup(p++);
 
 	DECODE_TAIL;
 }
@@ -1186,7 +1195,7 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify
 	 * nfsd4_proc_verify */
 
 	READ_BUF(4);
-	READ32(verify->ve_attrlen);
+	verify->ve_attrlen = be32_to_cpup(p++);
 	READ_BUF(verify->ve_attrlen);
 	SAVEMEM(verify->ve_attrval, verify->ve_attrlen);
 
@@ -1204,11 +1213,11 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
 	if (status)
 		return status;
 	READ_BUF(16);
-	READ64(write->wr_offset);
-	READ32(write->wr_stable_how);
+	p = xdr_decode_hyper(p, &write->wr_offset);
+	write->wr_stable_how = be32_to_cpup(p++);
 	if (write->wr_stable_how > 2)
 		goto xdr_error;
-	READ32(write->wr_buflen);
+	write->wr_buflen = be32_to_cpup(p++);
 
 	/* Sorry .. no magic macros for this.. *
 	 * READ_BUF(write->wr_buflen);
@@ -1254,7 +1263,7 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel
 
 	READ_BUF(12);
 	COPYMEM(&rlockowner->rl_clientid, sizeof(clientid_t));
-	READ32(rlockowner->rl_owner.len);
+	rlockowner->rl_owner.len = be32_to_cpup(p++);
 	READ_BUF(rlockowner->rl_owner.len);
 	READMEM(rlockowner->rl_owner.data, rlockowner->rl_owner.len);
 
@@ -1278,63 +1287,63 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 		return nfserr_bad_xdr;
 
 	READ_BUF(4);
-	READ32(exid->flags);
+	exid->flags = be32_to_cpup(p++);
 
 	/* Ignore state_protect4_a */
 	READ_BUF(4);
-	READ32(exid->spa_how);
+	exid->spa_how = be32_to_cpup(p++);
 	switch (exid->spa_how) {
 	case SP4_NONE:
 		break;
 	case SP4_MACH_CRED:
 		/* spo_must_enforce */
 		READ_BUF(4);
-		READ32(dummy);
+		dummy = be32_to_cpup(p++);
 		READ_BUF(dummy * 4);
 		p += dummy;
 
 		/* spo_must_allow */
 		READ_BUF(4);
-		READ32(dummy);
+		dummy = be32_to_cpup(p++);
 		READ_BUF(dummy * 4);
 		p += dummy;
 		break;
 	case SP4_SSV:
 		/* ssp_ops */
 		READ_BUF(4);
-		READ32(dummy);
+		dummy = be32_to_cpup(p++);
 		READ_BUF(dummy * 4);
 		p += dummy;
 
 		READ_BUF(4);
-		READ32(dummy);
+		dummy = be32_to_cpup(p++);
 		READ_BUF(dummy * 4);
 		p += dummy;
 
 		/* ssp_hash_algs<> */
 		READ_BUF(4);
-		READ32(tmp);
+		tmp = be32_to_cpup(p++);
 		while (tmp--) {
 			READ_BUF(4);
-			READ32(dummy);
+			dummy = be32_to_cpup(p++);
 			READ_BUF(dummy);
 			p += XDR_QUADLEN(dummy);
 		}
 
 		/* ssp_encr_algs<> */
 		READ_BUF(4);
-		READ32(tmp);
+		tmp = be32_to_cpup(p++);
 		while (tmp--) {
 			READ_BUF(4);
-			READ32(dummy);
+			dummy = be32_to_cpup(p++);
 			READ_BUF(dummy);
 			p += XDR_QUADLEN(dummy);
 		}
 
 		/* ssp_window and ssp_num_gss_handles */
 		READ_BUF(8);
-		READ32(dummy);
-		READ32(dummy);
+		dummy = be32_to_cpup(p++);
+		dummy = be32_to_cpup(p++);
 		break;
 	default:
 		goto xdr_error;
@@ -1342,7 +1351,7 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 
 	/* Ignore Implementation ID */
 	READ_BUF(4);    /* nfs_impl_id4 array length */
-	READ32(dummy);
+	dummy = be32_to_cpup(p++);
 
 	if (dummy > 1)
 		goto xdr_error;
@@ -1350,13 +1359,13 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp,
 	if (dummy == 1) {
 		/* nii_domain */
 		READ_BUF(4);
-		READ32(dummy);
+		dummy = be32_to_cpup(p++);
 		READ_BUF(dummy);
 		p += XDR_QUADLEN(dummy);
 
 		/* nii_name */
 		READ_BUF(4);
-		READ32(dummy);
+		dummy = be32_to_cpup(p++);
 		READ_BUF(dummy);
 		p += XDR_QUADLEN(dummy);
 
@@ -1376,21 +1385,21 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
 
 	READ_BUF(16);
 	COPYMEM(&sess->clientid, 8);
-	READ32(sess->seqid);
-	READ32(sess->flags);
+	sess->seqid = be32_to_cpup(p++);
+	sess->flags = be32_to_cpup(p++);
 
 	/* Fore channel attrs */
 	READ_BUF(28);
-	READ32(dummy); /* headerpadsz is always 0 */
-	READ32(sess->fore_channel.maxreq_sz);
-	READ32(sess->fore_channel.maxresp_sz);
-	READ32(sess->fore_channel.maxresp_cached);
-	READ32(sess->fore_channel.maxops);
-	READ32(sess->fore_channel.maxreqs);
-	READ32(sess->fore_channel.nr_rdma_attrs);
+	dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */
+	sess->fore_channel.maxreq_sz = be32_to_cpup(p++);
+	sess->fore_channel.maxresp_sz = be32_to_cpup(p++);
+	sess->fore_channel.maxresp_cached = be32_to_cpup(p++);
+	sess->fore_channel.maxops = be32_to_cpup(p++);
+	sess->fore_channel.maxreqs = be32_to_cpup(p++);
+	sess->fore_channel.nr_rdma_attrs = be32_to_cpup(p++);
 	if (sess->fore_channel.nr_rdma_attrs == 1) {
 		READ_BUF(4);
-		READ32(sess->fore_channel.rdma_attrs);
+		sess->fore_channel.rdma_attrs = be32_to_cpup(p++);
 	} else if (sess->fore_channel.nr_rdma_attrs > 1) {
 		dprintk("Too many fore channel attr bitmaps!\n");
 		goto xdr_error;
@@ -1398,23 +1407,23 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp,
 
 	/* Back channel attrs */
 	READ_BUF(28);
-	READ32(dummy); /* headerpadsz is always 0 */
-	READ32(sess->back_channel.maxreq_sz);
-	READ32(sess->back_channel.maxresp_sz);
-	READ32(sess->back_channel.maxresp_cached);
-	READ32(sess->back_channel.maxops);
-	READ32(sess->back_channel.maxreqs);
-	READ32(sess->back_channel.nr_rdma_attrs);
+	dummy = be32_to_cpup(p++); /* headerpadsz is always 0 */
+	sess->back_channel.maxreq_sz = be32_to_cpup(p++);
+	sess->back_channel.maxresp_sz = be32_to_cpup(p++);
+	sess->back_channel.maxresp_cached = be32_to_cpup(p++);
+	sess->back_channel.maxops = be32_to_cpup(p++);
+	sess->back_channel.maxreqs = be32_to_cpup(p++);
+	sess->back_channel.nr_rdma_attrs = be32_to_cpup(p++);
 	if (sess->back_channel.nr_rdma_attrs == 1) {
 		READ_BUF(4);
-		READ32(sess->back_channel.rdma_attrs);
+		sess->back_channel.rdma_attrs = be32_to_cpup(p++);
 	} else if (sess->back_channel.nr_rdma_attrs > 1) {
 		dprintk("Too many back channel attr bitmaps!\n");
 		goto xdr_error;
 	}
 
 	READ_BUF(4);
-	READ32(sess->callback_prog);
+	sess->callback_prog = be32_to_cpup(p++);
 	nfsd4_decode_cb_sec(argp, &sess->cb_sec);
 	DECODE_TAIL;
 }
@@ -1437,7 +1446,7 @@ nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp,
 	DECODE_HEAD;
 
 	READ_BUF(sizeof(stateid_t));
-	READ32(free_stateid->fr_stateid.si_generation);
+	free_stateid->fr_stateid.si_generation = be32_to_cpup(p++);
 	COPYMEM(&free_stateid->fr_stateid.si_opaque, sizeof(stateid_opaque_t));
 
 	DECODE_TAIL;
@@ -1451,10 +1460,10 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp,
 
 	READ_BUF(NFS4_MAX_SESSIONID_LEN + 16);
 	COPYMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN);
-	READ32(seq->seqid);
-	READ32(seq->slotid);
-	READ32(seq->maxslots);
-	READ32(seq->cachethis);
+	seq->seqid = be32_to_cpup(p++);
+	seq->slotid = be32_to_cpup(p++);
+	seq->maxslots = be32_to_cpup(p++);
+	seq->cachethis = be32_to_cpup(p++);
 
 	DECODE_TAIL;
 }
@@ -1511,7 +1520,7 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, str
 	DECODE_HEAD;
 
 	READ_BUF(4);
-	READ32(rc->rca_one_fs);
+	rc->rca_one_fs = be32_to_cpup(p++);
 
 	DECODE_TAIL;
 }
@@ -1605,47 +1614,25 @@ nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op)
 	return true;
 }
 
-/*
- * Return a rough estimate of the maximum possible reply size.  Note the
- * estimate includes rpc headers so is meant to be passed to
- * svc_reserve, not svc_reserve_auth.
- *
- * Also note the current compound encoding permits only one operation to
- * use pages beyond the first one, so the maximum possible length is the
- * maximum over these values, not the sum.
- */
-static int nfsd4_max_reply(u32 opnum)
-{
-	switch (opnum) {
-	case OP_READLINK:
-	case OP_READDIR:
-		/*
-		 * Both of these ops take a single page for data and put
-		 * the head and tail in another page:
-		 */
-		return 2 * PAGE_SIZE;
-	case OP_READ:
-		return INT_MAX;
-	default:
-		return PAGE_SIZE;
-	}
-}
-
 static __be32
 nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 {
 	DECODE_HEAD;
 	struct nfsd4_op *op;
 	bool cachethis = false;
-	int max_reply = PAGE_SIZE;
+	int auth_slack= argp->rqstp->rq_auth_slack;
+	int max_reply = auth_slack + 8; /* opcnt, status */
+	int readcount = 0;
+	int readbytes = 0;
 	int i;
 
 	READ_BUF(4);
-	READ32(argp->taglen);
+	argp->taglen = be32_to_cpup(p++);
 	READ_BUF(argp->taglen + 8);
 	SAVEMEM(argp->tag, argp->taglen);
-	READ32(argp->minorversion);
-	READ32(argp->opcnt);
+	argp->minorversion = be32_to_cpup(p++);
+	argp->opcnt = be32_to_cpup(p++);
+	max_reply += 4 + (XDR_QUADLEN(argp->taglen) << 2);
 
 	if (argp->taglen > NFSD4_MAX_TAGLEN)
 		goto xdr_error;
@@ -1669,7 +1656,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 		op->replay = NULL;
 
 		READ_BUF(4);
-		READ32(op->opnum);
+		op->opnum = be32_to_cpup(p++);
 
 		if (nfsd4_opnum_in_range(argp, op))
 			op->status = nfsd4_dec_ops[op->opnum](argp, &op->u);
@@ -1677,97 +1664,82 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 			op->opnum = OP_ILLEGAL;
 			op->status = nfserr_op_illegal;
 		}
-
-		if (op->status) {
-			argp->opcnt = i+1;
-			break;
-		}
 		/*
 		 * We'll try to cache the result in the DRC if any one
 		 * op in the compound wants to be cached:
 		 */
 		cachethis |= nfsd4_cache_this_op(op);
 
-		max_reply = max(max_reply, nfsd4_max_reply(op->opnum));
+		if (op->opnum == OP_READ) {
+			readcount++;
+			readbytes += nfsd4_max_reply(argp->rqstp, op);
+		} else
+			max_reply += nfsd4_max_reply(argp->rqstp, op);
+
+		if (op->status) {
+			argp->opcnt = i+1;
+			break;
+		}
 	}
 	/* Sessions make the DRC unnecessary: */
 	if (argp->minorversion)
 		cachethis = false;
-	if (max_reply != INT_MAX)
-		svc_reserve(argp->rqstp, max_reply);
+	svc_reserve(argp->rqstp, max_reply + readbytes);
 	argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE;
 
-	DECODE_TAIL;
-}
-
-#define WRITE32(n)               *p++ = htonl(n)
-#define WRITE64(n)               do {				\
-	*p++ = htonl((u32)((n) >> 32));				\
-	*p++ = htonl((u32)(n));					\
-} while (0)
-#define WRITEMEM(ptr,nbytes)     do { if (nbytes > 0) {		\
-	*(p + XDR_QUADLEN(nbytes) -1) = 0;                      \
-	memcpy(p, ptr, nbytes);					\
-	p += XDR_QUADLEN(nbytes);				\
-}} while (0)
+	if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack)
+		argp->rqstp->rq_splice_ok = false;
 
-static void write32(__be32 **p, u32 n)
-{
-	*(*p)++ = htonl(n);
-}
-
-static void write64(__be32 **p, u64 n)
-{
-	write32(p, (n >> 32));
-	write32(p, (u32)n);
+	DECODE_TAIL;
 }
 
-static void write_change(__be32 **p, struct kstat *stat, struct inode *inode)
+static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode)
 {
 	if (IS_I_VERSION(inode)) {
-		write64(p, inode->i_version);
+		p = xdr_encode_hyper(p, inode->i_version);
 	} else {
-		write32(p, stat->ctime.tv_sec);
-		write32(p, stat->ctime.tv_nsec);
+		*p++ = cpu_to_be32(stat->ctime.tv_sec);
+		*p++ = cpu_to_be32(stat->ctime.tv_nsec);
 	}
+	return p;
 }
 
-static void write_cinfo(__be32 **p, struct nfsd4_change_info *c)
+static __be32 *encode_cinfo(__be32 *p, struct nfsd4_change_info *c)
 {
-	write32(p, c->atomic);
+	*p++ = cpu_to_be32(c->atomic);
 	if (c->change_supported) {
-		write64(p, c->before_change);
-		write64(p, c->after_change);
+		p = xdr_encode_hyper(p, c->before_change);
+		p = xdr_encode_hyper(p, c->after_change);
 	} else {
-		write32(p, c->before_ctime_sec);
-		write32(p, c->before_ctime_nsec);
-		write32(p, c->after_ctime_sec);
-		write32(p, c->after_ctime_nsec);
+		*p++ = cpu_to_be32(c->before_ctime_sec);
+		*p++ = cpu_to_be32(c->before_ctime_nsec);
+		*p++ = cpu_to_be32(c->after_ctime_sec);
+		*p++ = cpu_to_be32(c->after_ctime_nsec);
 	}
+	return p;
 }
 
-#define RESERVE_SPACE(nbytes)	do {				\
-	p = resp->p;						\
-	BUG_ON(p + XDR_QUADLEN(nbytes) > resp->end);		\
-} while (0)
-#define ADJUST_ARGS()		resp->p = p
-
 /* Encode as an array of strings the string given with components
  * separated @sep, escaped with esc_enter and esc_exit.
  */
-static __be32 nfsd4_encode_components_esc(char sep, char *components,
-				   __be32 **pp, int *buflen,
-				   char esc_enter, char esc_exit)
+static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep,
+					  char *components, char esc_enter,
+					  char esc_exit)
 {
-	__be32 *p = *pp;
-	__be32 *countp = p;
+	__be32 *p;
+	__be32 pathlen;
+	int pathlen_offset;
 	int strlen, count=0;
 	char *str, *end, *next;
 
 	dprintk("nfsd4_encode_components(%s)\n", components);
-	if ((*buflen -= 4) < 0)
+
+	pathlen_offset = xdr->buf->len;
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
 		return nfserr_resource;
-	WRITE32(0); /* We will fill this in with @count later */
+	p++; /* We will fill this in with @count later */
+
 	end = str = components;
 	while (*end) {
 		bool found_esc = false;
@@ -1789,59 +1761,57 @@ static __be32 nfsd4_encode_components_esc(char sep, char *components,
 
 		strlen = end - str;
 		if (strlen) {
-			if ((*buflen -= ((XDR_QUADLEN(strlen) << 2) + 4)) < 0)
+			p = xdr_reserve_space(xdr, strlen + 4);
+			if (!p)
 				return nfserr_resource;
-			WRITE32(strlen);
-			WRITEMEM(str, strlen);
+			p = xdr_encode_opaque(p, str, strlen);
 			count++;
 		}
 		else
 			end++;
 		str = end;
 	}
-	*pp = p;
-	p = countp;
-	WRITE32(count);
+	pathlen = htonl(xdr->buf->len - pathlen_offset);
+	write_bytes_to_xdr_buf(xdr->buf, pathlen_offset, &pathlen, 4);
 	return 0;
 }
 
 /* Encode as an array of strings the string given with components
  * separated @sep.
  */
-static __be32 nfsd4_encode_components(char sep, char *components,
-				   __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_components(struct xdr_stream *xdr, char sep,
+				      char *components)
 {
-	return nfsd4_encode_components_esc(sep, components, pp, buflen, 0, 0);
+	return nfsd4_encode_components_esc(xdr, sep, components, 0, 0);
 }
 
 /*
  * encode a location element of a fs_locations structure
  */
-static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location,
-				    __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_fs_location4(struct xdr_stream *xdr,
+					struct nfsd4_fs_location *location)
 {
 	__be32 status;
-	__be32 *p = *pp;
 
-	status = nfsd4_encode_components_esc(':', location->hosts, &p, buflen,
+	status = nfsd4_encode_components_esc(xdr, ':', location->hosts,
 						'[', ']');
 	if (status)
 		return status;
-	status = nfsd4_encode_components('/', location->path, &p, buflen);
+	status = nfsd4_encode_components(xdr, '/', location->path);
 	if (status)
 		return status;
-	*pp = p;
 	return 0;
 }
 
 /*
  * Encode a path in RFC3530 'pathname4' format
  */
-static __be32 nfsd4_encode_path(const struct path *root,
-		const struct path *path, __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_path(struct xdr_stream *xdr,
+				const struct path *root,
+				const struct path *path)
 {
 	struct path cur = *path;
-	__be32 *p = *pp;
+	__be32 *p;
 	struct dentry **components = NULL;
 	unsigned int ncomponents = 0;
 	__be32 err = nfserr_jukebox;
@@ -1872,11 +1842,11 @@ static __be32 nfsd4_encode_path(const struct path *root,
 		components[ncomponents++] = cur.dentry;
 		cur.dentry = dget_parent(cur.dentry);
 	}
-
-	*buflen -= 4;
-	if (*buflen < 0)
+	err = nfserr_resource;
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
 		goto out_free;
-	WRITE32(ncomponents);
+	*p++ = cpu_to_be32(ncomponents);
 
 	while (ncomponents) {
 		struct dentry *dentry = components[ncomponents - 1];
@@ -1884,20 +1854,18 @@ static __be32 nfsd4_encode_path(const struct path *root,
 
 		spin_lock(&dentry->d_lock);
 		len = dentry->d_name.len;
-		*buflen -= 4 + (XDR_QUADLEN(len) << 2);
-		if (*buflen < 0) {
+		p = xdr_reserve_space(xdr, len + 4);
+		if (!p) {
 			spin_unlock(&dentry->d_lock);
 			goto out_free;
 		}
-		WRITE32(len);
-		WRITEMEM(dentry->d_name.name, len);
+		p = xdr_encode_opaque(p, dentry->d_name.name, len);
 		dprintk("/%s", dentry->d_name.name);
 		spin_unlock(&dentry->d_lock);
 		dput(dentry);
 		ncomponents--;
 	}
 
-	*pp = p;
 	err = 0;
 out_free:
 	dprintk(")\n");
@@ -1908,8 +1876,8 @@ out_free:
 	return err;
 }
 
-static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp,
-		const struct path *path, __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_fsloc_fsroot(struct xdr_stream *xdr,
+			struct svc_rqst *rqstp, const struct path *path)
 {
 	struct svc_export *exp_ps;
 	__be32 res;
@@ -1917,7 +1885,7 @@ static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp,
 	exp_ps = rqst_find_fsidzero_export(rqstp);
 	if (IS_ERR(exp_ps))
 		return nfserrno(PTR_ERR(exp_ps));
-	res = nfsd4_encode_path(&exp_ps->ex_path, path, pp, buflen);
+	res = nfsd4_encode_path(xdr, &exp_ps->ex_path, path);
 	exp_put(exp_ps);
 	return res;
 }
@@ -1925,28 +1893,26 @@ static __be32 nfsd4_encode_fsloc_fsroot(struct svc_rqst *rqstp,
 /*
  *  encode a fs_locations structure
  */
-static __be32 nfsd4_encode_fs_locations(struct svc_rqst *rqstp,
-				     struct svc_export *exp,
-				     __be32 **pp, int *buflen)
+static __be32 nfsd4_encode_fs_locations(struct xdr_stream *xdr,
+			struct svc_rqst *rqstp, struct svc_export *exp)
 {
 	__be32 status;
 	int i;
-	__be32 *p = *pp;
+	__be32 *p;
 	struct nfsd4_fs_locations *fslocs = &exp->ex_fslocs;
 
-	status = nfsd4_encode_fsloc_fsroot(rqstp, &exp->ex_path, &p, buflen);
+	status = nfsd4_encode_fsloc_fsroot(xdr, rqstp, &exp->ex_path);
 	if (status)
 		return status;
-	if ((*buflen -= 4) < 0)
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
 		return nfserr_resource;
-	WRITE32(fslocs->locations_count);
+	*p++ = cpu_to_be32(fslocs->locations_count);
 	for (i=0; i<fslocs->locations_count; i++) {
-		status = nfsd4_encode_fs_location4(&fslocs->locations[i],
-						   &p, buflen);
+		status = nfsd4_encode_fs_location4(xdr, &fslocs->locations[i]);
 		if (status)
 			return status;
 	}
-	*pp = p;
 	return 0;
 }
 
@@ -1965,15 +1931,15 @@ static u32 nfs4_file_type(umode_t mode)
 }
 
 static inline __be32
-nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace,
-		__be32 **p, int *buflen)
+nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+		     struct nfs4_ace *ace)
 {
 	if (ace->whotype != NFS4_ACL_WHO_NAMED)
-		return nfs4_acl_write_who(ace->whotype, p, buflen);
+		return nfs4_acl_write_who(xdr, ace->whotype);
 	else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
-		return nfsd4_encode_group(rqstp, ace->who_gid, p, buflen);
+		return nfsd4_encode_group(xdr, rqstp, ace->who_gid);
 	else
-		return nfsd4_encode_user(rqstp, ace->who_uid, p, buflen);
+		return nfsd4_encode_user(xdr, rqstp, ace->who_uid);
 }
 
 #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
@@ -1982,31 +1948,28 @@ nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace,
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 static inline __be32
-nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen)
+nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			    void *context, int len)
 {
-	__be32 *p = *pp;
+	__be32 *p;
 
-	if (*buflen < ((XDR_QUADLEN(len) << 2) + 4 + 4 + 4))
+	p = xdr_reserve_space(xdr, len + 4 + 4 + 4);
+	if (!p)
 		return nfserr_resource;
 
 	/*
 	 * For now we use a 0 here to indicate the null translation; in
 	 * the future we may place a call to translation code here.
 	 */
-	if ((*buflen -= 8) < 0)
-		return nfserr_resource;
-
-	WRITE32(0); /* lfs */
-	WRITE32(0); /* pi */
+	*p++ = cpu_to_be32(0); /* lfs */
+	*p++ = cpu_to_be32(0); /* pi */
 	p = xdr_encode_opaque(p, context, len);
-	*buflen -= (XDR_QUADLEN(len) << 2) + 4;
-
-	*pp = p;
 	return 0;
 }
 #else
 static inline __be32
-nfsd4_encode_security_label(struct svc_rqst *rqstp, void *context, int len, __be32 **pp, int *buflen)
+nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			    void *context, int len)
 { return 0; }
 #endif
 
@@ -2045,12 +2008,11 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
 /*
  * Note: @fhp can be NULL; in this case, we might have to compose the filehandle
  * ourselves.
- *
- * countp is the buffer size in _words_
  */
-__be32
-nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
-		struct dentry *dentry, __be32 **buffer, int count, u32 *bmval,
+static __be32
+nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
+		struct svc_export *exp,
+		struct dentry *dentry, u32 *bmval,
 		struct svc_rqst *rqstp, int ignore_crossmnt)
 {
 	u32 bmval0 = bmval[0];
@@ -2059,12 +2021,13 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 	struct kstat stat;
 	struct svc_fh *tempfh = NULL;
 	struct kstatfs statfs;
-	int buflen = count << 2;
-	__be32 *attrlenp;
+	__be32 *p;
+	int starting_len = xdr->buf->len;
+	int attrlen_offset;
+	__be32 attrlen;
 	u32 dummy;
 	u64 dummy64;
 	u32 rdattr_err = 0;
-	__be32 *p = *buffer;
 	__be32 status;
 	int err;
 	int aclsupport = 0;
@@ -2095,8 +2058,8 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 	err = vfs_getattr(&path, &stat);
 	if (err)
 		goto out_nfserr;
-	if ((bmval0 & (FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL |
-			FATTR4_WORD0_MAXNAME)) ||
+	if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
+			FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) ||
 	    (bmval1 & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE |
 		       FATTR4_WORD1_SPACE_TOTAL))) {
 		err = vfs_statfs(&path, &statfs);
@@ -2145,25 +2108,33 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */
 
 	if (bmval2) {
-		if ((buflen -= 16) < 0)
+		p = xdr_reserve_space(xdr, 16);
+		if (!p)
 			goto out_resource;
-		WRITE32(3);
-		WRITE32(bmval0);
-		WRITE32(bmval1);
-		WRITE32(bmval2);
+		*p++ = cpu_to_be32(3);
+		*p++ = cpu_to_be32(bmval0);
+		*p++ = cpu_to_be32(bmval1);
+		*p++ = cpu_to_be32(bmval2);
 	} else if (bmval1) {
-		if ((buflen -= 12) < 0)
+		p = xdr_reserve_space(xdr, 12);
+		if (!p)
 			goto out_resource;
-		WRITE32(2);
-		WRITE32(bmval0);
-		WRITE32(bmval1);
+		*p++ = cpu_to_be32(2);
+		*p++ = cpu_to_be32(bmval0);
+		*p++ = cpu_to_be32(bmval1);
 	} else {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE32(1);
-		WRITE32(bmval0);
+		*p++ = cpu_to_be32(1);
+		*p++ = cpu_to_be32(bmval0);
 	}
-	attrlenp = p++;                /* to be backfilled later */
+
+	attrlen_offset = xdr->buf->len;
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		goto out_resource;
+	p++;                /* to be backfilled later */
 
 	if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
 		u32 word0 = nfsd_suppattrs0(minorversion);
@@ -2175,296 +2146,343 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 		if (!contextsupport)
 			word2 &= ~FATTR4_WORD2_SECURITY_LABEL;
 		if (!word2) {
-			if ((buflen -= 12) < 0)
+			p = xdr_reserve_space(xdr, 12);
+			if (!p)
 				goto out_resource;
-			WRITE32(2);
-			WRITE32(word0);
-			WRITE32(word1);
+			*p++ = cpu_to_be32(2);
+			*p++ = cpu_to_be32(word0);
+			*p++ = cpu_to_be32(word1);
 		} else {
-			if ((buflen -= 16) < 0)
+			p = xdr_reserve_space(xdr, 16);
+			if (!p)
 				goto out_resource;
-			WRITE32(3);
-			WRITE32(word0);
-			WRITE32(word1);
-			WRITE32(word2);
+			*p++ = cpu_to_be32(3);
+			*p++ = cpu_to_be32(word0);
+			*p++ = cpu_to_be32(word1);
+			*p++ = cpu_to_be32(word2);
 		}
 	}
 	if (bmval0 & FATTR4_WORD0_TYPE) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
 		dummy = nfs4_file_type(stat.mode);
 		if (dummy == NF4BAD) {
 			status = nfserr_serverfault;
 			goto out;
 		}
-		WRITE32(dummy);
+		*p++ = cpu_to_be32(dummy);
 	}
 	if (bmval0 & FATTR4_WORD0_FH_EXPIRE_TYPE) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
 		if (exp->ex_flags & NFSEXP_NOSUBTREECHECK)
-			WRITE32(NFS4_FH_PERSISTENT);
+			*p++ = cpu_to_be32(NFS4_FH_PERSISTENT);
 		else
-			WRITE32(NFS4_FH_PERSISTENT|NFS4_FH_VOL_RENAME);
+			*p++ = cpu_to_be32(NFS4_FH_PERSISTENT|
+						NFS4_FH_VOL_RENAME);
 	}
 	if (bmval0 & FATTR4_WORD0_CHANGE) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		write_change(&p, &stat, dentry->d_inode);
+		p = encode_change(p, &stat, dentry->d_inode);
 	}
 	if (bmval0 & FATTR4_WORD0_SIZE) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE64(stat.size);
+		p = xdr_encode_hyper(p, stat.size);
 	}
 	if (bmval0 & FATTR4_WORD0_LINK_SUPPORT) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(1);
+		*p++ = cpu_to_be32(1);
 	}
 	if (bmval0 & FATTR4_WORD0_SYMLINK_SUPPORT) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(1);
+		*p++ = cpu_to_be32(1);
 	}
 	if (bmval0 & FATTR4_WORD0_NAMED_ATTR) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(0);
+		*p++ = cpu_to_be32(0);
 	}
 	if (bmval0 & FATTR4_WORD0_FSID) {
-		if ((buflen -= 16) < 0)
+		p = xdr_reserve_space(xdr, 16);
+		if (!p)
 			goto out_resource;
 		if (exp->ex_fslocs.migrated) {
-			WRITE64(NFS4_REFERRAL_FSID_MAJOR);
-			WRITE64(NFS4_REFERRAL_FSID_MINOR);
+			p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MAJOR);
+			p = xdr_encode_hyper(p, NFS4_REFERRAL_FSID_MINOR);
 		} else switch(fsid_source(fhp)) {
 		case FSIDSOURCE_FSID:
-			WRITE64((u64)exp->ex_fsid);
-			WRITE64((u64)0);
+			p = xdr_encode_hyper(p, (u64)exp->ex_fsid);
+			p = xdr_encode_hyper(p, (u64)0);
 			break;
 		case FSIDSOURCE_DEV:
-			WRITE32(0);
-			WRITE32(MAJOR(stat.dev));
-			WRITE32(0);
-			WRITE32(MINOR(stat.dev));
+			*p++ = cpu_to_be32(0);
+			*p++ = cpu_to_be32(MAJOR(stat.dev));
+			*p++ = cpu_to_be32(0);
+			*p++ = cpu_to_be32(MINOR(stat.dev));
 			break;
 		case FSIDSOURCE_UUID:
-			WRITEMEM(exp->ex_uuid, 16);
+			p = xdr_encode_opaque_fixed(p, exp->ex_uuid,
+								EX_UUID_LEN);
 			break;
 		}
 	}
 	if (bmval0 & FATTR4_WORD0_UNIQUE_HANDLES) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(0);
+		*p++ = cpu_to_be32(0);
 	}
 	if (bmval0 & FATTR4_WORD0_LEASE_TIME) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(nn->nfsd4_lease);
+		*p++ = cpu_to_be32(nn->nfsd4_lease);
 	}
 	if (bmval0 & FATTR4_WORD0_RDATTR_ERROR) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(rdattr_err);
+		*p++ = cpu_to_be32(rdattr_err);
 	}
 	if (bmval0 & FATTR4_WORD0_ACL) {
 		struct nfs4_ace *ace;
 
 		if (acl == NULL) {
-			if ((buflen -= 4) < 0)
+			p = xdr_reserve_space(xdr, 4);
+			if (!p)
 				goto out_resource;
 
-			WRITE32(0);
+			*p++ = cpu_to_be32(0);
 			goto out_acl;
 		}
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(acl->naces);
+		*p++ = cpu_to_be32(acl->naces);
 
 		for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) {
-			if ((buflen -= 4*3) < 0)
+			p = xdr_reserve_space(xdr, 4*3);
+			if (!p)
 				goto out_resource;
-			WRITE32(ace->type);
-			WRITE32(ace->flag);
-			WRITE32(ace->access_mask & NFS4_ACE_MASK_ALL);
-			status = nfsd4_encode_aclname(rqstp, ace, &p, &buflen);
+			*p++ = cpu_to_be32(ace->type);
+			*p++ = cpu_to_be32(ace->flag);
+			*p++ = cpu_to_be32(ace->access_mask &
+							NFS4_ACE_MASK_ALL);
+			status = nfsd4_encode_aclname(xdr, rqstp, ace);
 			if (status)
 				goto out;
 		}
 	}
 out_acl:
 	if (bmval0 & FATTR4_WORD0_ACLSUPPORT) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(aclsupport ?
+		*p++ = cpu_to_be32(aclsupport ?
 			ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL : 0);
 	}
 	if (bmval0 & FATTR4_WORD0_CANSETTIME) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(1);
+		*p++ = cpu_to_be32(1);
 	}
 	if (bmval0 & FATTR4_WORD0_CASE_INSENSITIVE) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(0);
+		*p++ = cpu_to_be32(0);
 	}
 	if (bmval0 & FATTR4_WORD0_CASE_PRESERVING) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(1);
+		*p++ = cpu_to_be32(1);
 	}
 	if (bmval0 & FATTR4_WORD0_CHOWN_RESTRICTED) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(1);
+		*p++ = cpu_to_be32(1);
 	}
 	if (bmval0 & FATTR4_WORD0_FILEHANDLE) {
-		buflen -= (XDR_QUADLEN(fhp->fh_handle.fh_size) << 2) + 4;
-		if (buflen < 0)
+		p = xdr_reserve_space(xdr, fhp->fh_handle.fh_size + 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(fhp->fh_handle.fh_size);
-		WRITEMEM(&fhp->fh_handle.fh_base, fhp->fh_handle.fh_size);
+		p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base,
+					fhp->fh_handle.fh_size);
 	}
 	if (bmval0 & FATTR4_WORD0_FILEID) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE64(stat.ino);
+		p = xdr_encode_hyper(p, stat.ino);
 	}
 	if (bmval0 & FATTR4_WORD0_FILES_AVAIL) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE64((u64) statfs.f_ffree);
+		p = xdr_encode_hyper(p, (u64) statfs.f_ffree);
 	}
 	if (bmval0 & FATTR4_WORD0_FILES_FREE) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE64((u64) statfs.f_ffree);
+		p = xdr_encode_hyper(p, (u64) statfs.f_ffree);
 	}
 	if (bmval0 & FATTR4_WORD0_FILES_TOTAL) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE64((u64) statfs.f_files);
+		p = xdr_encode_hyper(p, (u64) statfs.f_files);
 	}
 	if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) {
-		status = nfsd4_encode_fs_locations(rqstp, exp, &p, &buflen);
+		status = nfsd4_encode_fs_locations(xdr, rqstp, exp);
 		if (status)
 			goto out;
 	}
 	if (bmval0 & FATTR4_WORD0_HOMOGENEOUS) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(1);
+		*p++ = cpu_to_be32(1);
 	}
 	if (bmval0 & FATTR4_WORD0_MAXFILESIZE) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE64(exp->ex_path.mnt->mnt_sb->s_maxbytes);
+		p = xdr_encode_hyper(p, exp->ex_path.mnt->mnt_sb->s_maxbytes);
 	}
 	if (bmval0 & FATTR4_WORD0_MAXLINK) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(255);
+		*p++ = cpu_to_be32(255);
 	}
 	if (bmval0 & FATTR4_WORD0_MAXNAME) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(statfs.f_namelen);
+		*p++ = cpu_to_be32(statfs.f_namelen);
 	}
 	if (bmval0 & FATTR4_WORD0_MAXREAD) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE64((u64) svc_max_payload(rqstp));
+		p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp));
 	}
 	if (bmval0 & FATTR4_WORD0_MAXWRITE) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE64((u64) svc_max_payload(rqstp));
+		p = xdr_encode_hyper(p, (u64) svc_max_payload(rqstp));
 	}
 	if (bmval1 & FATTR4_WORD1_MODE) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(stat.mode & S_IALLUGO);
+		*p++ = cpu_to_be32(stat.mode & S_IALLUGO);
 	}
 	if (bmval1 & FATTR4_WORD1_NO_TRUNC) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(1);
+		*p++ = cpu_to_be32(1);
 	}
 	if (bmval1 & FATTR4_WORD1_NUMLINKS) {
-		if ((buflen -= 4) < 0)
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
 			goto out_resource;
-		WRITE32(stat.nlink);
+		*p++ = cpu_to_be32(stat.nlink);
 	}
 	if (bmval1 & FATTR4_WORD1_OWNER) {
-		status = nfsd4_encode_user(rqstp, stat.uid, &p, &buflen);
+		status = nfsd4_encode_user(xdr, rqstp, stat.uid);
 		if (status)
 			goto out;
 	}
 	if (bmval1 & FATTR4_WORD1_OWNER_GROUP) {
-		status = nfsd4_encode_group(rqstp, stat.gid, &p, &buflen);
+		status = nfsd4_encode_group(xdr, rqstp, stat.gid);
 		if (status)
 			goto out;
 	}
 	if (bmval1 & FATTR4_WORD1_RAWDEV) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
-		WRITE32((u32) MAJOR(stat.rdev));
-		WRITE32((u32) MINOR(stat.rdev));
+		*p++ = cpu_to_be32((u32) MAJOR(stat.rdev));
+		*p++ = cpu_to_be32((u32) MINOR(stat.rdev));
 	}
 	if (bmval1 & FATTR4_WORD1_SPACE_AVAIL) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
 		dummy64 = (u64)statfs.f_bavail * (u64)statfs.f_bsize;
-		WRITE64(dummy64);
+		p = xdr_encode_hyper(p, dummy64);
 	}
 	if (bmval1 & FATTR4_WORD1_SPACE_FREE) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
 		dummy64 = (u64)statfs.f_bfree * (u64)statfs.f_bsize;
-		WRITE64(dummy64);
+		p = xdr_encode_hyper(p, dummy64);
 	}
 	if (bmval1 & FATTR4_WORD1_SPACE_TOTAL) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
 		dummy64 = (u64)statfs.f_blocks * (u64)statfs.f_bsize;
-		WRITE64(dummy64);
+		p = xdr_encode_hyper(p, dummy64);
 	}
 	if (bmval1 & FATTR4_WORD1_SPACE_USED) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
 			goto out_resource;
 		dummy64 = (u64)stat.blocks << 9;
-		WRITE64(dummy64);
+		p = xdr_encode_hyper(p, dummy64);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_ACCESS) {
-		if ((buflen -= 12) < 0)
+		p = xdr_reserve_space(xdr, 12);
+		if (!p)
 			goto out_resource;
-		WRITE64((s64)stat.atime.tv_sec);
-		WRITE32(stat.atime.tv_nsec);
+		p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec);
+		*p++ = cpu_to_be32(stat.atime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_DELTA) {
-		if ((buflen -= 12) < 0)
+		p = xdr_reserve_space(xdr, 12);
+		if (!p)
 			goto out_resource;
-		WRITE32(0);
-		WRITE32(1);
-		WRITE32(0);
+		*p++ = cpu_to_be32(0);
+		*p++ = cpu_to_be32(1);
+		*p++ = cpu_to_be32(0);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_METADATA) {
-		if ((buflen -= 12) < 0)
+		p = xdr_reserve_space(xdr, 12);
+		if (!p)
 			goto out_resource;
-		WRITE64((s64)stat.ctime.tv_sec);
-		WRITE32(stat.ctime.tv_nsec);
+		p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec);
+		*p++ = cpu_to_be32(stat.ctime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_MODIFY) {
-		if ((buflen -= 12) < 0)
+		p = xdr_reserve_space(xdr, 12);
+		if (!p)
 			goto out_resource;
-		WRITE64((s64)stat.mtime.tv_sec);
-		WRITE32(stat.mtime.tv_nsec);
+		p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec);
+		*p++ = cpu_to_be32(stat.mtime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
-		if ((buflen -= 8) < 0)
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
                 	goto out_resource;
 		/*
 		 * Get parent's attributes if not ignoring crossmount
@@ -2473,25 +2491,26 @@ out_acl:
 		if (ignore_crossmnt == 0 &&
 		    dentry == exp->ex_path.mnt->mnt_root)
 			get_parent_attributes(exp, &stat);
-		WRITE64(stat.ino);
+		p = xdr_encode_hyper(p, stat.ino);
 	}
 	if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
-		status = nfsd4_encode_security_label(rqstp, context,
-				contextlen, &p, &buflen);
+		status = nfsd4_encode_security_label(xdr, rqstp, context,
+								contextlen);
 		if (status)
 			goto out;
 	}
 	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
-		if ((buflen -= 16) < 0)
+		p = xdr_reserve_space(xdr, 16);
+		if (!p)
 			goto out_resource;
-		WRITE32(3);
-		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
-		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD1);
-		WRITE32(NFSD_SUPPATTR_EXCLCREAT_WORD2);
+		*p++ = cpu_to_be32(3);
+		*p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
+		*p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD1);
+		*p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD2);
 	}
 
-	*attrlenp = htonl((char *)p - (char *)attrlenp - 4);
-	*buffer = p;
+	attrlen = htonl(xdr->buf->len - attrlen_offset - 4);
+	write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4);
 	status = nfs_ok;
 
 out:
@@ -2504,6 +2523,8 @@ out:
 		fh_put(tempfh);
 		kfree(tempfh);
 	}
+	if (status)
+		xdr_truncate_encode(xdr, starting_len);
 	return status;
 out_nfserr:
 	status = nfserrno(err);
@@ -2513,6 +2534,37 @@ out_resource:
 	goto out;
 }
 
+static void svcxdr_init_encode_from_buffer(struct xdr_stream *xdr,
+				struct xdr_buf *buf, __be32 *p, int bytes)
+{
+	xdr->scratch.iov_len = 0;
+	memset(buf, 0, sizeof(struct xdr_buf));
+	buf->head[0].iov_base = p;
+	buf->head[0].iov_len = 0;
+	buf->len = 0;
+	xdr->buf = buf;
+	xdr->iov = buf->head;
+	xdr->p = p;
+	xdr->end = (void *)p + bytes;
+	buf->buflen = bytes;
+}
+
+__be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
+			struct svc_fh *fhp, struct svc_export *exp,
+			struct dentry *dentry, u32 *bmval,
+			struct svc_rqst *rqstp, int ignore_crossmnt)
+{
+	struct xdr_buf dummy;
+	struct xdr_stream xdr;
+	__be32 ret;
+
+	svcxdr_init_encode_from_buffer(&xdr, &dummy, *p, words << 2);
+	ret = nfsd4_encode_fattr(&xdr, fhp, exp, dentry, bmval, rqstp,
+							ignore_crossmnt);
+	*p = xdr.p;
+	return ret;
+}
+
 static inline int attributes_need_mount(u32 *bmval)
 {
 	if (bmval[0] & ~(FATTR4_WORD0_RDATTR_ERROR | FATTR4_WORD0_LEASE_TIME))
@@ -2523,8 +2575,8 @@ static inline int attributes_need_mount(u32 *bmval)
 }
 
 static __be32
-nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
-		const char *name, int namlen, __be32 **p, int buflen)
+nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd,
+			const char *name, int namlen)
 {
 	struct svc_export *exp = cd->rd_fhp->fh_export;
 	struct dentry *dentry;
@@ -2576,7 +2628,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
 
 	}
 out_encode:
-	nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval,
+	nfserr = nfsd4_encode_fattr(xdr, NULL, exp, dentry, cd->rd_bmval,
 					cd->rd_rqstp, ignore_crossmnt);
 out_put:
 	dput(dentry);
@@ -2585,9 +2637,12 @@ out_put:
 }
 
 static __be32 *
-nfsd4_encode_rdattr_error(__be32 *p, int buflen, __be32 nfserr)
+nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr)
 {
-	if (buflen < 6)
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, 20);
+	if (!p)
 		return NULL;
 	*p++ = htonl(2);
 	*p++ = htonl(FATTR4_WORD0_RDATTR_ERROR); /* bmval0 */
@@ -2604,10 +2659,13 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
 {
 	struct readdir_cd *ccd = ccdv;
 	struct nfsd4_readdir *cd = container_of(ccd, struct nfsd4_readdir, common);
-	int buflen;
-	__be32 *p = cd->buffer;
-	__be32 *cookiep;
+	struct xdr_stream *xdr = cd->xdr;
+	int start_offset = xdr->buf->len;
+	int cookie_offset;
+	int entry_bytes;
 	__be32 nfserr = nfserr_toosmall;
+	__be64 wire_offset;
+	__be32 *p;
 
 	/* In nfsv4, "." and ".." never make it onto the wire.. */
 	if (name && isdotent(name, namlen)) {
@@ -2615,19 +2673,24 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
 		return 0;
 	}
 
-	if (cd->offset)
-		xdr_encode_hyper(cd->offset, (u64) offset);
+	if (cd->cookie_offset) {
+		wire_offset = cpu_to_be64(offset);
+		write_bytes_to_xdr_buf(xdr->buf, cd->cookie_offset,
+							&wire_offset, 8);
+	}
 
-	buflen = cd->buflen - 4 - XDR_QUADLEN(namlen);
-	if (buflen < 0)
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
 		goto fail;
-
 	*p++ = xdr_one;                             /* mark entry present */
-	cookiep = p;
+	cookie_offset = xdr->buf->len;
+	p = xdr_reserve_space(xdr, 3*4 + namlen);
+	if (!p)
+		goto fail;
 	p = xdr_encode_hyper(p, NFS_OFFSET_MAX);    /* offset of next entry */
 	p = xdr_encode_array(p, name, namlen);      /* name length & name */
 
-	nfserr = nfsd4_encode_dirent_fattr(cd, name, namlen, &p, buflen);
+	nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen);
 	switch (nfserr) {
 	case nfs_ok:
 		break;
@@ -2635,6 +2698,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
 		nfserr = nfserr_toosmall;
 		goto fail;
 	case nfserr_noent:
+		xdr_truncate_encode(xdr, start_offset);
 		goto skip_entry;
 	default:
 		/*
@@ -2646,59 +2710,74 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
 		 */
 		if (!(cd->rd_bmval[0] & FATTR4_WORD0_RDATTR_ERROR))
 			goto fail;
-		p = nfsd4_encode_rdattr_error(p, buflen, nfserr);
+		p = nfsd4_encode_rdattr_error(xdr, nfserr);
 		if (p == NULL) {
 			nfserr = nfserr_toosmall;
 			goto fail;
 		}
 	}
-	cd->buflen -= (p - cd->buffer);
-	cd->buffer = p;
-	cd->offset = cookiep;
+	nfserr = nfserr_toosmall;
+	entry_bytes = xdr->buf->len - start_offset;
+	if (entry_bytes > cd->rd_maxcount)
+		goto fail;
+	cd->rd_maxcount -= entry_bytes;
+	if (!cd->rd_dircount)
+		goto fail;
+	cd->rd_dircount--;
+	cd->cookie_offset = cookie_offset;
 skip_entry:
 	cd->common.err = nfs_ok;
 	return 0;
 fail:
+	xdr_truncate_encode(xdr, start_offset);
 	cd->common.err = nfserr;
 	return -EINVAL;
 }
 
-static void
-nfsd4_encode_stateid(struct nfsd4_compoundres *resp, stateid_t *sid)
+static __be32
+nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid)
 {
 	__be32 *p;
 
-	RESERVE_SPACE(sizeof(stateid_t));
-	WRITE32(sid->si_generation);
-	WRITEMEM(&sid->si_opaque, sizeof(stateid_opaque_t));
-	ADJUST_ARGS();
+	p = xdr_reserve_space(xdr, sizeof(stateid_t));
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(sid->si_generation);
+	p = xdr_encode_opaque_fixed(p, &sid->si_opaque,
+					sizeof(stateid_opaque_t));
+	return 0;
 }
 
 static __be32
 nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(8);
-		WRITE32(access->ac_supported);
-		WRITE32(access->ac_resp_access);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
+			return nfserr_resource;
+		*p++ = cpu_to_be32(access->ac_supported);
+		*p++ = cpu_to_be32(access->ac_resp_access);
 	}
 	return nfserr;
 }
 
 static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 8);
-		WRITEMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
-		WRITE32(bcts->dir);
+		p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_opaque_fixed(p, bcts->sessionid.data,
+						NFS4_MAX_SESSIONID_LEN);
+		*p++ = cpu_to_be32(bcts->dir);
 		/* Sorry, we do not yet support RDMA over 4.1: */
-		WRITE32(0);
-		ADJUST_ARGS();
+		*p++ = cpu_to_be32(0);
 	}
 	return nfserr;
 }
@@ -2706,8 +2785,10 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp,
 static __be32
 nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close)
 {
+	struct xdr_stream *xdr = &resp->xdr;
+
 	if (!nfserr)
-		nfsd4_encode_stateid(resp, &close->cl_stateid);
+		nfserr = nfsd4_encode_stateid(xdr, &close->cl_stateid);
 
 	return nfserr;
 }
@@ -2716,12 +2797,15 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c
 static __be32
 nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(NFS4_VERIFIER_SIZE);
-		WRITEMEM(commit->co_verf.data, NFS4_VERIFIER_SIZE);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_opaque_fixed(p, commit->co_verf.data,
+						NFS4_VERIFIER_SIZE);
 	}
 	return nfserr;
 }
@@ -2729,15 +2813,17 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
 static __be32
 nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(32);
-		write_cinfo(&p, &create->cr_cinfo);
-		WRITE32(2);
-		WRITE32(create->cr_bmval[0]);
-		WRITE32(create->cr_bmval[1]);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 32);
+		if (!p)
+			return nfserr_resource;
+		p = encode_cinfo(p, &create->cr_cinfo);
+		*p++ = cpu_to_be32(2);
+		*p++ = cpu_to_be32(create->cr_bmval[0]);
+		*p++ = cpu_to_be32(create->cr_bmval[1]);
 	}
 	return nfserr;
 }
@@ -2746,14 +2832,13 @@ static __be32
 nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr)
 {
 	struct svc_fh *fhp = getattr->ga_fhp;
-	int buflen;
+	struct xdr_stream *xdr = &resp->xdr;
 
 	if (nfserr)
 		return nfserr;
 
-	buflen = resp->end - resp->p - (COMPOUND_ERR_SLACK_SPACE >> 2);
-	nfserr = nfsd4_encode_fattr(fhp, fhp->fh_export, fhp->fh_dentry,
-				    &resp->p, buflen, getattr->ga_bmval,
+	nfserr = nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry,
+				    getattr->ga_bmval,
 				    resp->rqstp, 0);
 	return nfserr;
 }
@@ -2761,16 +2846,17 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
 static __be32
 nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	struct svc_fh *fhp = *fhpp;
 	unsigned int len;
 	__be32 *p;
 
 	if (!nfserr) {
 		len = fhp->fh_handle.fh_size;
-		RESERVE_SPACE(len + 4);
-		WRITE32(len);
-		WRITEMEM(&fhp->fh_handle.fh_base, len);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, len + 4);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len);
 	}
 	return nfserr;
 }
@@ -2779,35 +2865,50 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh
 * Including all fields other than the name, a LOCK4denied structure requires
 *   8(clientid) + 4(namelen) + 8(offset) + 8(length) + 4(type) = 32 bytes.
 */
-static void
-nfsd4_encode_lock_denied(struct nfsd4_compoundres *resp, struct nfsd4_lock_denied *ld)
+static __be32
+nfsd4_encode_lock_denied(struct xdr_stream *xdr, struct nfsd4_lock_denied *ld)
 {
 	struct xdr_netobj *conf = &ld->ld_owner;
 	__be32 *p;
 
-	RESERVE_SPACE(32 + XDR_LEN(conf->len));
-	WRITE64(ld->ld_start);
-	WRITE64(ld->ld_length);
-	WRITE32(ld->ld_type);
+again:
+	p = xdr_reserve_space(xdr, 32 + XDR_LEN(conf->len));
+	if (!p) {
+		/*
+		 * Don't fail to return the result just because we can't
+		 * return the conflicting open:
+		 */
+		if (conf->len) {
+			kfree(conf->data);
+			conf->len = 0;
+			conf->data = NULL;
+			goto again;
+		}
+		return nfserr_resource;
+	}
+	p = xdr_encode_hyper(p, ld->ld_start);
+	p = xdr_encode_hyper(p, ld->ld_length);
+	*p++ = cpu_to_be32(ld->ld_type);
 	if (conf->len) {
-		WRITEMEM(&ld->ld_clientid, 8);
-		WRITE32(conf->len);
-		WRITEMEM(conf->data, conf->len);
+		p = xdr_encode_opaque_fixed(p, &ld->ld_clientid, 8);
+		p = xdr_encode_opaque(p, conf->data, conf->len);
 		kfree(conf->data);
 	}  else {  /* non - nfsv4 lock in conflict, no clientid nor owner */
-		WRITE64((u64)0); /* clientid */
-		WRITE32(0); /* length of owner name */
+		p = xdr_encode_hyper(p, (u64)0); /* clientid */
+		*p++ = cpu_to_be32(0); /* length of owner name */
 	}
-	ADJUST_ARGS();
+	return nfserr_denied;
 }
 
 static __be32
 nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock)
 {
+	struct xdr_stream *xdr = &resp->xdr;
+
 	if (!nfserr)
-		nfsd4_encode_stateid(resp, &lock->lk_resp_stateid);
+		nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid);
 	else if (nfserr == nfserr_denied)
-		nfsd4_encode_lock_denied(resp, &lock->lk_denied);
+		nfserr = nfsd4_encode_lock_denied(xdr, &lock->lk_denied);
 
 	return nfserr;
 }
@@ -2815,16 +2916,20 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo
 static __be32
 nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt)
 {
+	struct xdr_stream *xdr = &resp->xdr;
+
 	if (nfserr == nfserr_denied)
-		nfsd4_encode_lock_denied(resp, &lockt->lt_denied);
+		nfsd4_encode_lock_denied(xdr, &lockt->lt_denied);
 	return nfserr;
 }
 
 static __be32
 nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku)
 {
+	struct xdr_stream *xdr = &resp->xdr;
+
 	if (!nfserr)
-		nfsd4_encode_stateid(resp, &locku->lu_stateid);
+		nfserr = nfsd4_encode_stateid(xdr, &locku->lu_stateid);
 
 	return nfserr;
 }
@@ -2833,12 +2938,14 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l
 static __be32
 nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(20);
-		write_cinfo(&p, &link->li_cinfo);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 20);
+		if (!p)
+			return nfserr_resource;
+		p = encode_cinfo(p, &link->li_cinfo);
 	}
 	return nfserr;
 }
@@ -2847,72 +2954,86 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li
 static __be32
 nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (nfserr)
 		goto out;
 
-	nfsd4_encode_stateid(resp, &open->op_stateid);
-	RESERVE_SPACE(40);
-	write_cinfo(&p, &open->op_cinfo);
-	WRITE32(open->op_rflags);
-	WRITE32(2);
-	WRITE32(open->op_bmval[0]);
-	WRITE32(open->op_bmval[1]);
-	WRITE32(open->op_delegate_type);
-	ADJUST_ARGS();
+	nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid);
+	if (nfserr)
+		goto out;
+	p = xdr_reserve_space(xdr, 40);
+	if (!p)
+		return nfserr_resource;
+	p = encode_cinfo(p, &open->op_cinfo);
+	*p++ = cpu_to_be32(open->op_rflags);
+	*p++ = cpu_to_be32(2);
+	*p++ = cpu_to_be32(open->op_bmval[0]);
+	*p++ = cpu_to_be32(open->op_bmval[1]);
+	*p++ = cpu_to_be32(open->op_delegate_type);
 
 	switch (open->op_delegate_type) {
 	case NFS4_OPEN_DELEGATE_NONE:
 		break;
 	case NFS4_OPEN_DELEGATE_READ:
-		nfsd4_encode_stateid(resp, &open->op_delegate_stateid);
-		RESERVE_SPACE(20);
-		WRITE32(open->op_recall);
+		nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid);
+		if (nfserr)
+			return nfserr;
+		p = xdr_reserve_space(xdr, 20);
+		if (!p)
+			return nfserr_resource;
+		*p++ = cpu_to_be32(open->op_recall);
 
 		/*
 		 * TODO: ACE's in delegations
 		 */
-		WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
-		WRITE32(0);
-		WRITE32(0);
-		WRITE32(0);   /* XXX: is NULL principal ok? */
-		ADJUST_ARGS();
+		*p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
+		*p++ = cpu_to_be32(0);
+		*p++ = cpu_to_be32(0);
+		*p++ = cpu_to_be32(0);   /* XXX: is NULL principal ok? */
 		break;
 	case NFS4_OPEN_DELEGATE_WRITE:
-		nfsd4_encode_stateid(resp, &open->op_delegate_stateid);
-		RESERVE_SPACE(32);
-		WRITE32(0);
+		nfserr = nfsd4_encode_stateid(xdr, &open->op_delegate_stateid);
+		if (nfserr)
+			return nfserr;
+		p = xdr_reserve_space(xdr, 32);
+		if (!p)
+			return nfserr_resource;
+		*p++ = cpu_to_be32(0);
 
 		/*
 		 * TODO: space_limit's in delegations
 		 */
-		WRITE32(NFS4_LIMIT_SIZE);
-		WRITE32(~(u32)0);
-		WRITE32(~(u32)0);
+		*p++ = cpu_to_be32(NFS4_LIMIT_SIZE);
+		*p++ = cpu_to_be32(~(u32)0);
+		*p++ = cpu_to_be32(~(u32)0);
 
 		/*
 		 * TODO: ACE's in delegations
 		 */
-		WRITE32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
-		WRITE32(0);
-		WRITE32(0);
-		WRITE32(0);   /* XXX: is NULL principal ok? */
-		ADJUST_ARGS();
+		*p++ = cpu_to_be32(NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE);
+		*p++ = cpu_to_be32(0);
+		*p++ = cpu_to_be32(0);
+		*p++ = cpu_to_be32(0);   /* XXX: is NULL principal ok? */
 		break;
 	case NFS4_OPEN_DELEGATE_NONE_EXT: /* 4.1 */
 		switch (open->op_why_no_deleg) {
 		case WND4_CONTENTION:
 		case WND4_RESOURCE:
-			RESERVE_SPACE(8);
-			WRITE32(open->op_why_no_deleg);
-			WRITE32(0);	/* deleg signaling not supported yet */
+			p = xdr_reserve_space(xdr, 8);
+			if (!p)
+				return nfserr_resource;
+			*p++ = cpu_to_be32(open->op_why_no_deleg);
+			/* deleg signaling not supported yet: */
+			*p++ = cpu_to_be32(0);
 			break;
 		default:
-			RESERVE_SPACE(4);
-			WRITE32(open->op_why_no_deleg);
+			p = xdr_reserve_space(xdr, 4);
+			if (!p)
+				return nfserr_resource;
+			*p++ = cpu_to_be32(open->op_why_no_deleg);
 		}
-		ADJUST_ARGS();
 		break;
 	default:
 		BUG();
@@ -2925,8 +3046,10 @@ out:
 static __be32
 nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc)
 {
+	struct xdr_stream *xdr = &resp->xdr;
+
 	if (!nfserr)
-		nfsd4_encode_stateid(resp, &oc->oc_resp_stateid);
+		nfserr = nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid);
 
 	return nfserr;
 }
@@ -2934,127 +3057,233 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct
 static __be32
 nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od)
 {
+	struct xdr_stream *xdr = &resp->xdr;
+
 	if (!nfserr)
-		nfsd4_encode_stateid(resp, &od->od_stateid);
+		nfserr = nfsd4_encode_stateid(xdr, &od->od_stateid);
 
 	return nfserr;
 }
 
-static __be32
-nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
-		  struct nfsd4_read *read)
+static __be32 nfsd4_encode_splice_read(
+				struct nfsd4_compoundres *resp,
+				struct nfsd4_read *read,
+				struct file *file, unsigned long maxcount)
 {
+	struct xdr_stream *xdr = &resp->xdr;
+	struct xdr_buf *buf = xdr->buf;
 	u32 eof;
-	int v;
-	struct page *page;
-	unsigned long maxcount; 
-	long len;
-	__be32 *p;
+	int space_left;
+	__be32 nfserr;
+	__be32 *p = xdr->p - 2;
 
-	if (nfserr)
-		return nfserr;
-	if (resp->xbuf->page_len)
+	/*
+	 * Don't inline pages unless we know there's room for eof,
+	 * count, and possible padding:
+	 */
+	if (xdr->end - xdr->p < 3)
 		return nfserr_resource;
 
-	RESERVE_SPACE(8); /* eof flag and byte count */
+	nfserr = nfsd_splice_read(read->rd_rqstp, file,
+				  read->rd_offset, &maxcount);
+	if (nfserr) {
+		/*
+		 * nfsd_splice_actor may have already messed with the
+		 * page length; reset it so as not to confuse
+		 * xdr_truncate_encode:
+		 */
+		buf->page_len = 0;
+		return nfserr;
+	}
 
-	maxcount = svc_max_payload(resp->rqstp);
-	if (maxcount > read->rd_length)
-		maxcount = read->rd_length;
+	eof = (read->rd_offset + maxcount >=
+	       read->rd_fhp->fh_dentry->d_inode->i_size);
+
+	*(p++) = htonl(eof);
+	*(p++) = htonl(maxcount);
+
+	buf->page_len = maxcount;
+	buf->len += maxcount;
+	xdr->page_ptr += (maxcount + PAGE_SIZE - 1) / PAGE_SIZE;
+
+	/* Use rest of head for padding and remaining ops: */
+	buf->tail[0].iov_base = xdr->p;
+	buf->tail[0].iov_len = 0;
+	xdr->iov = buf->tail;
+	if (maxcount&3) {
+		int pad = 4 - (maxcount&3);
+
+		*(xdr->p++) = 0;
+
+		buf->tail[0].iov_base += maxcount&3;
+		buf->tail[0].iov_len = pad;
+		buf->len += pad;
+	}
+
+	space_left = min_t(int, (void *)xdr->end - (void *)xdr->p,
+				buf->buflen - buf->len);
+	buf->buflen = buf->len + space_left;
+	xdr->end = (__be32 *)((void *)xdr->end + space_left);
+
+	return 0;
+}
+
+static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
+				 struct nfsd4_read *read,
+				 struct file *file, unsigned long maxcount)
+{
+	struct xdr_stream *xdr = &resp->xdr;
+	u32 eof;
+	int v;
+	int starting_len = xdr->buf->len - 8;
+	long len;
+	int thislen;
+	__be32 nfserr;
+	__be32 tmp;
+	__be32 *p;
+	u32 zzz = 0;
+	int pad;
 
 	len = maxcount;
 	v = 0;
-	while (len > 0) {
-		page = *(resp->rqstp->rq_next_page);
-		if (!page) { /* ran out of pages */
-			maxcount -= len;
-			break;
-		}
-		resp->rqstp->rq_vec[v].iov_base = page_address(page);
-		resp->rqstp->rq_vec[v].iov_len =
-			len < PAGE_SIZE ? len : PAGE_SIZE;
-		resp->rqstp->rq_next_page++;
+
+	thislen = (void *)xdr->end - (void *)xdr->p;
+	if (len < thislen)
+		thislen = len;
+	p = xdr_reserve_space(xdr, (thislen+3)&~3);
+	WARN_ON_ONCE(!p);
+	resp->rqstp->rq_vec[v].iov_base = p;
+	resp->rqstp->rq_vec[v].iov_len = thislen;
+	v++;
+	len -= thislen;
+
+	while (len) {
+		thislen = min_t(long, len, PAGE_SIZE);
+		p = xdr_reserve_space(xdr, (thislen+3)&~3);
+		WARN_ON_ONCE(!p);
+		resp->rqstp->rq_vec[v].iov_base = p;
+		resp->rqstp->rq_vec[v].iov_len = thislen;
 		v++;
-		len -= PAGE_SIZE;
+		len -= thislen;
 	}
 	read->rd_vlen = v;
 
-	nfserr = nfsd_read_file(read->rd_rqstp, read->rd_fhp, read->rd_filp,
-			read->rd_offset, resp->rqstp->rq_vec, read->rd_vlen,
-			&maxcount);
-
+	nfserr = nfsd_readv(file, read->rd_offset, resp->rqstp->rq_vec,
+			read->rd_vlen, &maxcount);
 	if (nfserr)
 		return nfserr;
+	xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3));
+
 	eof = (read->rd_offset + maxcount >=
 	       read->rd_fhp->fh_dentry->d_inode->i_size);
 
-	WRITE32(eof);
-	WRITE32(maxcount);
-	ADJUST_ARGS();
-	resp->xbuf->head[0].iov_len = (char*)p
-					- (char*)resp->xbuf->head[0].iov_base;
-	resp->xbuf->page_len = maxcount;
+	tmp = htonl(eof);
+	write_bytes_to_xdr_buf(xdr->buf, starting_len    , &tmp, 4);
+	tmp = htonl(maxcount);
+	write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4);
 
-	/* Use rest of head for padding and remaining ops: */
-	resp->xbuf->tail[0].iov_base = p;
-	resp->xbuf->tail[0].iov_len = 0;
-	if (maxcount&3) {
-		RESERVE_SPACE(4);
-		WRITE32(0);
-		resp->xbuf->tail[0].iov_base += maxcount&3;
-		resp->xbuf->tail[0].iov_len = 4 - (maxcount&3);
-		ADJUST_ARGS();
-	}
+	pad = (maxcount&3) ? 4 - (maxcount&3) : 0;
+	write_bytes_to_xdr_buf(xdr->buf, starting_len + 8 + maxcount,
+								&zzz, pad);
 	return 0;
+
 }
 
 static __be32
-nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink)
+nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
+		  struct nfsd4_read *read)
 {
-	int maxcount;
-	char *page;
+	unsigned long maxcount;
+	struct xdr_stream *xdr = &resp->xdr;
+	struct file *file = read->rd_filp;
+	int starting_len = xdr->buf->len;
+	struct raparms *ra;
 	__be32 *p;
+	__be32 err;
 
 	if (nfserr)
 		return nfserr;
-	if (resp->xbuf->page_len)
+
+	p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */
+	if (!p) {
+		WARN_ON_ONCE(resp->rqstp->rq_splice_ok);
 		return nfserr_resource;
-	if (!*resp->rqstp->rq_next_page)
+	}
+	if (resp->xdr.buf->page_len && resp->rqstp->rq_splice_ok) {
+		WARN_ON_ONCE(1);
 		return nfserr_resource;
+	}
+	xdr_commit_encode(xdr);
+
+	maxcount = svc_max_payload(resp->rqstp);
+	if (maxcount > xdr->buf->buflen - xdr->buf->len)
+		maxcount = xdr->buf->buflen - xdr->buf->len;
+	if (maxcount > read->rd_length)
+		maxcount = read->rd_length;
+
+	if (!read->rd_filp) {
+		err = nfsd_get_tmp_read_open(resp->rqstp, read->rd_fhp,
+						&file, &ra);
+		if (err)
+			goto err_truncate;
+	}
+
+	if (file->f_op->splice_read && resp->rqstp->rq_splice_ok)
+		err = nfsd4_encode_splice_read(resp, read, file, maxcount);
+	else
+		err = nfsd4_encode_readv(resp, read, file, maxcount);
+
+	if (!read->rd_filp)
+		nfsd_put_tmp_read_open(file, ra);
+
+err_truncate:
+	if (err)
+		xdr_truncate_encode(xdr, starting_len);
+	return err;
+}
 
-	page = page_address(*(resp->rqstp->rq_next_page++));
+static __be32
+nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink)
+{
+	int maxcount;
+	__be32 wire_count;
+	int zero = 0;
+	struct xdr_stream *xdr = &resp->xdr;
+	int length_offset = xdr->buf->len;
+	__be32 *p;
 
+	if (nfserr)
+		return nfserr;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
 	maxcount = PAGE_SIZE;
-	RESERVE_SPACE(4);
 
+	p = xdr_reserve_space(xdr, maxcount);
+	if (!p)
+		return nfserr_resource;
 	/*
 	 * XXX: By default, the ->readlink() VFS op will truncate symlinks
 	 * if they would overflow the buffer.  Is this kosher in NFSv4?  If
 	 * not, one easy fix is: if ->readlink() precisely fills the buffer,
 	 * assume that truncation occurred, and return NFS4ERR_RESOURCE.
 	 */
-	nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp, page, &maxcount);
+	nfserr = nfsd_readlink(readlink->rl_rqstp, readlink->rl_fhp,
+						(char *)p, &maxcount);
 	if (nfserr == nfserr_isdir)
-		return nfserr_inval;
-	if (nfserr)
+		nfserr = nfserr_inval;
+	if (nfserr) {
+		xdr_truncate_encode(xdr, length_offset);
 		return nfserr;
-
-	WRITE32(maxcount);
-	ADJUST_ARGS();
-	resp->xbuf->head[0].iov_len = (char*)p
-				- (char*)resp->xbuf->head[0].iov_base;
-	resp->xbuf->page_len = maxcount;
-
-	/* Use rest of head for padding and remaining ops: */
-	resp->xbuf->tail[0].iov_base = p;
-	resp->xbuf->tail[0].iov_len = 0;
-	if (maxcount&3) {
-		RESERVE_SPACE(4);
-		WRITE32(0);
-		resp->xbuf->tail[0].iov_base += maxcount&3;
-		resp->xbuf->tail[0].iov_len = 4 - (maxcount&3);
-		ADJUST_ARGS();
 	}
+
+	wire_count = htonl(maxcount);
+	write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4);
+	xdr_truncate_encode(xdr, length_offset + 4 + ALIGN(maxcount, 4));
+	if (maxcount & 3)
+		write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount,
+						&zero, 4 - (maxcount&3));
 	return 0;
 }
 
@@ -3062,47 +3291,52 @@ static __be32
 nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readdir *readdir)
 {
 	int maxcount;
+	int bytes_left;
 	loff_t offset;
-	__be32 *page, *savep, *tailbase;
+	__be64 wire_offset;
+	struct xdr_stream *xdr = &resp->xdr;
+	int starting_len = xdr->buf->len;
 	__be32 *p;
 
 	if (nfserr)
 		return nfserr;
-	if (resp->xbuf->page_len)
-		return nfserr_resource;
-	if (!*resp->rqstp->rq_next_page)
-		return nfserr_resource;
 
-	RESERVE_SPACE(NFS4_VERIFIER_SIZE);
-	savep = p;
+	p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE);
+	if (!p)
+		return nfserr_resource;
 
 	/* XXX: Following NFSv3, we ignore the READDIR verifier for now. */
-	WRITE32(0);
-	WRITE32(0);
-	ADJUST_ARGS();
-	resp->xbuf->head[0].iov_len = ((char*)resp->p) - (char*)resp->xbuf->head[0].iov_base;
-	tailbase = p;
-
-	maxcount = PAGE_SIZE;
-	if (maxcount > readdir->rd_maxcount)
-		maxcount = readdir->rd_maxcount;
+	*p++ = cpu_to_be32(0);
+	*p++ = cpu_to_be32(0);
+	resp->xdr.buf->head[0].iov_len = ((char *)resp->xdr.p)
+				- (char *)resp->xdr.buf->head[0].iov_base;
 
 	/*
-	 * Convert from bytes to words, account for the two words already
-	 * written, make sure to leave two words at the end for the next
-	 * pointer and eof field.
+	 * Number of bytes left for directory entries allowing for the
+	 * final 8 bytes of the readdir and a following failed op:
+	 */
+	bytes_left = xdr->buf->buflen - xdr->buf->len
+			- COMPOUND_ERR_SLACK_SPACE - 8;
+	if (bytes_left < 0) {
+		nfserr = nfserr_resource;
+		goto err_no_verf;
+	}
+	maxcount = min_t(u32, readdir->rd_maxcount, INT_MAX);
+	/*
+	 * Note the rfc defines rd_maxcount as the size of the
+	 * READDIR4resok structure, which includes the verifier above
+	 * and the 8 bytes encoded at the end of this function:
 	 */
-	maxcount = (maxcount >> 2) - 4;
-	if (maxcount < 0) {
-		nfserr =  nfserr_toosmall;
+	if (maxcount < 16) {
+		nfserr = nfserr_toosmall;
 		goto err_no_verf;
 	}
+	maxcount = min_t(int, maxcount-16, bytes_left);
 
-	page = page_address(*(resp->rqstp->rq_next_page++));
+	readdir->xdr = xdr;
+	readdir->rd_maxcount = maxcount;
 	readdir->common.err = 0;
-	readdir->buflen = maxcount;
-	readdir->buffer = page;
-	readdir->offset = NULL;
+	readdir->cookie_offset = 0;
 
 	offset = readdir->rd_cookie;
 	nfserr = nfsd_readdir(readdir->rd_rqstp, readdir->rd_fhp,
@@ -3110,42 +3344,49 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
 			      &readdir->common, nfsd4_encode_dirent);
 	if (nfserr == nfs_ok &&
 	    readdir->common.err == nfserr_toosmall &&
-	    readdir->buffer == page) 
-		nfserr = nfserr_toosmall;
+	    xdr->buf->len == starting_len + 8) {
+		/* nothing encoded; which limit did we hit?: */
+		if (maxcount - 16 < bytes_left)
+			/* It was the fault of rd_maxcount: */
+			nfserr = nfserr_toosmall;
+		else
+			/* We ran out of buffer space: */
+			nfserr = nfserr_resource;
+	}
 	if (nfserr)
 		goto err_no_verf;
 
-	if (readdir->offset)
-		xdr_encode_hyper(readdir->offset, offset);
+	if (readdir->cookie_offset) {
+		wire_offset = cpu_to_be64(offset);
+		write_bytes_to_xdr_buf(xdr->buf, readdir->cookie_offset,
+							&wire_offset, 8);
+	}
 
-	p = readdir->buffer;
+	p = xdr_reserve_space(xdr, 8);
+	if (!p) {
+		WARN_ON_ONCE(1);
+		goto err_no_verf;
+	}
 	*p++ = 0;	/* no more entries */
 	*p++ = htonl(readdir->common.err == nfserr_eof);
-	resp->xbuf->page_len = ((char*)p) -
-		(char*)page_address(*(resp->rqstp->rq_next_page-1));
-
-	/* Use rest of head for padding and remaining ops: */
-	resp->xbuf->tail[0].iov_base = tailbase;
-	resp->xbuf->tail[0].iov_len = 0;
-	resp->p = resp->xbuf->tail[0].iov_base;
-	resp->end = resp->p + (PAGE_SIZE - resp->xbuf->head[0].iov_len)/4;
 
 	return 0;
 err_no_verf:
-	p = savep;
-	ADJUST_ARGS();
+	xdr_truncate_encode(xdr, starting_len);
 	return nfserr;
 }
 
 static __be32
 nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(20);
-		write_cinfo(&p, &remove->rm_cinfo);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 20);
+		if (!p)
+			return nfserr_resource;
+		p = encode_cinfo(p, &remove->rm_cinfo);
 	}
 	return nfserr;
 }
@@ -3153,19 +3394,21 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
 static __be32
 nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(40);
-		write_cinfo(&p, &rename->rn_sinfo);
-		write_cinfo(&p, &rename->rn_tinfo);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 40);
+		if (!p)
+			return nfserr_resource;
+		p = encode_cinfo(p, &rename->rn_sinfo);
+		p = encode_cinfo(p, &rename->rn_tinfo);
 	}
 	return nfserr;
 }
 
 static __be32
-nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
+nfsd4_do_encode_secinfo(struct xdr_stream *xdr,
 			 __be32 nfserr, struct svc_export *exp)
 {
 	u32 i, nflavs, supported;
@@ -3176,6 +3419,7 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
 
 	if (nfserr)
 		goto out;
+	nfserr = nfserr_resource;
 	if (exp->ex_nflavors) {
 		flavs = exp->ex_flavors;
 		nflavs = exp->ex_nflavors;
@@ -3197,9 +3441,10 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
 	}
 
 	supported = 0;
-	RESERVE_SPACE(4);
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		goto out;
 	flavorsp = p++;		/* to be backfilled later */
-	ADJUST_ARGS();
 
 	for (i = 0; i < nflavs; i++) {
 		rpc_authflavor_t pf = flavs[i].pseudoflavor;
@@ -3207,18 +3452,20 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
 
 		if (rpcauth_get_gssinfo(pf, &info) == 0) {
 			supported++;
-			RESERVE_SPACE(4 + 4 + XDR_LEN(info.oid.len) + 4 + 4);
-			WRITE32(RPC_AUTH_GSS);
-			WRITE32(info.oid.len);
-			WRITEMEM(info.oid.data, info.oid.len);
-			WRITE32(info.qop);
-			WRITE32(info.service);
-			ADJUST_ARGS();
+			p = xdr_reserve_space(xdr, 4 + 4 +
+					      XDR_LEN(info.oid.len) + 4 + 4);
+			if (!p)
+				goto out;
+			*p++ = cpu_to_be32(RPC_AUTH_GSS);
+			p = xdr_encode_opaque(p,  info.oid.data, info.oid.len);
+			*p++ = cpu_to_be32(info.qop);
+			*p++ = cpu_to_be32(info.service);
 		} else if (pf < RPC_AUTH_MAXFLAVOR) {
 			supported++;
-			RESERVE_SPACE(4);
-			WRITE32(pf);
-			ADJUST_ARGS();
+			p = xdr_reserve_space(xdr, 4);
+			if (!p)
+				goto out;
+			*p++ = cpu_to_be32(pf);
 		} else {
 			if (report)
 				pr_warn("NFS: SECINFO: security flavor %u "
@@ -3229,7 +3476,7 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
 	if (nflavs != supported)
 		report = false;
 	*flavorsp = htonl(supported);
-
+	nfserr = 0;
 out:
 	if (exp)
 		exp_put(exp);
@@ -3240,14 +3487,18 @@ static __be32
 nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
 		     struct nfsd4_secinfo *secinfo)
 {
-	return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->si_exp);
+	struct xdr_stream *xdr = &resp->xdr;
+
+	return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->si_exp);
 }
 
 static __be32
 nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
 		     struct nfsd4_secinfo_no_name *secinfo)
 {
-	return nfsd4_do_encode_secinfo(resp, nfserr, secinfo->sin_exp);
+	struct xdr_stream *xdr = &resp->xdr;
+
+	return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->sin_exp);
 }
 
 /*
@@ -3257,41 +3508,47 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
 static __be32
 nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
-	RESERVE_SPACE(16);
+	p = xdr_reserve_space(xdr, 16);
+	if (!p)
+		return nfserr_resource;
 	if (nfserr) {
-		WRITE32(3);
-		WRITE32(0);
-		WRITE32(0);
-		WRITE32(0);
+		*p++ = cpu_to_be32(3);
+		*p++ = cpu_to_be32(0);
+		*p++ = cpu_to_be32(0);
+		*p++ = cpu_to_be32(0);
 	}
 	else {
-		WRITE32(3);
-		WRITE32(setattr->sa_bmval[0]);
-		WRITE32(setattr->sa_bmval[1]);
-		WRITE32(setattr->sa_bmval[2]);
+		*p++ = cpu_to_be32(3);
+		*p++ = cpu_to_be32(setattr->sa_bmval[0]);
+		*p++ = cpu_to_be32(setattr->sa_bmval[1]);
+		*p++ = cpu_to_be32(setattr->sa_bmval[2]);
 	}
-	ADJUST_ARGS();
 	return nfserr;
 }
 
 static __be32
 nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(8 + NFS4_VERIFIER_SIZE);
-		WRITEMEM(&scd->se_clientid, 8);
-		WRITEMEM(&scd->se_confirm, NFS4_VERIFIER_SIZE);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 8 + NFS4_VERIFIER_SIZE);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_opaque_fixed(p, &scd->se_clientid, 8);
+		p = xdr_encode_opaque_fixed(p, &scd->se_confirm,
+						NFS4_VERIFIER_SIZE);
 	}
 	else if (nfserr == nfserr_clid_inuse) {
-		RESERVE_SPACE(8);
-		WRITE32(0);
-		WRITE32(0);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
+			return nfserr_resource;
+		*p++ = cpu_to_be32(0);
+		*p++ = cpu_to_be32(0);
 	}
 	return nfserr;
 }
@@ -3299,14 +3556,17 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n
 static __be32
 nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (!nfserr) {
-		RESERVE_SPACE(16);
-		WRITE32(write->wr_bytes_written);
-		WRITE32(write->wr_how_written);
-		WRITEMEM(write->wr_verifier.data, NFS4_VERIFIER_SIZE);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 16);
+		if (!p)
+			return nfserr_resource;
+		*p++ = cpu_to_be32(write->wr_bytes_written);
+		*p++ = cpu_to_be32(write->wr_how_written);
+		p = xdr_encode_opaque_fixed(p, write->wr_verifier.data,
+							NFS4_VERIFIER_SIZE);
 	}
 	return nfserr;
 }
@@ -3323,6 +3583,7 @@ static __be32
 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 			 struct nfsd4_exchange_id *exid)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 	char *major_id;
 	char *server_scope;
@@ -3338,60 +3599,61 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
 	server_scope = utsname()->nodename;
 	server_scope_sz = strlen(server_scope);
 
-	RESERVE_SPACE(
+	p = xdr_reserve_space(xdr,
 		8 /* eir_clientid */ +
 		4 /* eir_sequenceid */ +
 		4 /* eir_flags */ +
 		4 /* spr_how */);
+	if (!p)
+		return nfserr_resource;
 
-	WRITEMEM(&exid->clientid, 8);
-	WRITE32(exid->seqid);
-	WRITE32(exid->flags);
+	p = xdr_encode_opaque_fixed(p, &exid->clientid, 8);
+	*p++ = cpu_to_be32(exid->seqid);
+	*p++ = cpu_to_be32(exid->flags);
 
-	WRITE32(exid->spa_how);
-	ADJUST_ARGS();
+	*p++ = cpu_to_be32(exid->spa_how);
 
 	switch (exid->spa_how) {
 	case SP4_NONE:
 		break;
 	case SP4_MACH_CRED:
 		/* spo_must_enforce, spo_must_allow */
-		RESERVE_SPACE(16);
+		p = xdr_reserve_space(xdr, 16);
+		if (!p)
+			return nfserr_resource;
 
 		/* spo_must_enforce bitmap: */
-		WRITE32(2);
-		WRITE32(nfs4_minimal_spo_must_enforce[0]);
-		WRITE32(nfs4_minimal_spo_must_enforce[1]);
+		*p++ = cpu_to_be32(2);
+		*p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[0]);
+		*p++ = cpu_to_be32(nfs4_minimal_spo_must_enforce[1]);
 		/* empty spo_must_allow bitmap: */
-		WRITE32(0);
+		*p++ = cpu_to_be32(0);
 
-		ADJUST_ARGS();
 		break;
 	default:
 		WARN_ON_ONCE(1);
 	}
 
-	RESERVE_SPACE(
+	p = xdr_reserve_space(xdr,
 		8 /* so_minor_id */ +
 		4 /* so_major_id.len */ +
 		(XDR_QUADLEN(major_id_sz) * 4) +
 		4 /* eir_server_scope.len */ +
 		(XDR_QUADLEN(server_scope_sz) * 4) +
 		4 /* eir_server_impl_id.count (0) */);
+	if (!p)
+		return nfserr_resource;
 
 	/* The server_owner struct */
-	WRITE64(minor_id);      /* Minor id */
+	p = xdr_encode_hyper(p, minor_id);      /* Minor id */
 	/* major id */
-	WRITE32(major_id_sz);
-	WRITEMEM(major_id, major_id_sz);
+	p = xdr_encode_opaque(p, major_id, major_id_sz);
 
 	/* Server scope */
-	WRITE32(server_scope_sz);
-	WRITEMEM(server_scope, server_scope_sz);
+	p = xdr_encode_opaque(p, server_scope, server_scope_sz);
 
 	/* Implementation id */
-	WRITE32(0);	/* zero length nfs_impl_id4 array */
-	ADJUST_ARGS();
+	*p++ = cpu_to_be32(0);	/* zero length nfs_impl_id4 array */
 	return 0;
 }
 
@@ -3399,47 +3661,54 @@ static __be32
 nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr,
 			    struct nfsd4_create_session *sess)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (nfserr)
 		return nfserr;
 
-	RESERVE_SPACE(24);
-	WRITEMEM(sess->sessionid.data, NFS4_MAX_SESSIONID_LEN);
-	WRITE32(sess->seqid);
-	WRITE32(sess->flags);
-	ADJUST_ARGS();
-
-	RESERVE_SPACE(28);
-	WRITE32(0); /* headerpadsz */
-	WRITE32(sess->fore_channel.maxreq_sz);
-	WRITE32(sess->fore_channel.maxresp_sz);
-	WRITE32(sess->fore_channel.maxresp_cached);
-	WRITE32(sess->fore_channel.maxops);
-	WRITE32(sess->fore_channel.maxreqs);
-	WRITE32(sess->fore_channel.nr_rdma_attrs);
-	ADJUST_ARGS();
+	p = xdr_reserve_space(xdr, 24);
+	if (!p)
+		return nfserr_resource;
+	p = xdr_encode_opaque_fixed(p, sess->sessionid.data,
+					NFS4_MAX_SESSIONID_LEN);
+	*p++ = cpu_to_be32(sess->seqid);
+	*p++ = cpu_to_be32(sess->flags);
+
+	p = xdr_reserve_space(xdr, 28);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(0); /* headerpadsz */
+	*p++ = cpu_to_be32(sess->fore_channel.maxreq_sz);
+	*p++ = cpu_to_be32(sess->fore_channel.maxresp_sz);
+	*p++ = cpu_to_be32(sess->fore_channel.maxresp_cached);
+	*p++ = cpu_to_be32(sess->fore_channel.maxops);
+	*p++ = cpu_to_be32(sess->fore_channel.maxreqs);
+	*p++ = cpu_to_be32(sess->fore_channel.nr_rdma_attrs);
 
 	if (sess->fore_channel.nr_rdma_attrs) {
-		RESERVE_SPACE(4);
-		WRITE32(sess->fore_channel.rdma_attrs);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			return nfserr_resource;
+		*p++ = cpu_to_be32(sess->fore_channel.rdma_attrs);
 	}
 
-	RESERVE_SPACE(28);
-	WRITE32(0); /* headerpadsz */
-	WRITE32(sess->back_channel.maxreq_sz);
-	WRITE32(sess->back_channel.maxresp_sz);
-	WRITE32(sess->back_channel.maxresp_cached);
-	WRITE32(sess->back_channel.maxops);
-	WRITE32(sess->back_channel.maxreqs);
-	WRITE32(sess->back_channel.nr_rdma_attrs);
-	ADJUST_ARGS();
+	p = xdr_reserve_space(xdr, 28);
+	if (!p)
+		return nfserr_resource;
+	*p++ = cpu_to_be32(0); /* headerpadsz */
+	*p++ = cpu_to_be32(sess->back_channel.maxreq_sz);
+	*p++ = cpu_to_be32(sess->back_channel.maxresp_sz);
+	*p++ = cpu_to_be32(sess->back_channel.maxresp_cached);
+	*p++ = cpu_to_be32(sess->back_channel.maxops);
+	*p++ = cpu_to_be32(sess->back_channel.maxreqs);
+	*p++ = cpu_to_be32(sess->back_channel.nr_rdma_attrs);
 
 	if (sess->back_channel.nr_rdma_attrs) {
-		RESERVE_SPACE(4);
-		WRITE32(sess->back_channel.rdma_attrs);
-		ADJUST_ARGS();
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			return nfserr_resource;
+		*p++ = cpu_to_be32(sess->back_channel.rdma_attrs);
 	}
 	return 0;
 }
@@ -3448,22 +3717,25 @@ static __be32
 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr,
 		      struct nfsd4_sequence *seq)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	__be32 *p;
 
 	if (nfserr)
 		return nfserr;
 
-	RESERVE_SPACE(NFS4_MAX_SESSIONID_LEN + 20);
-	WRITEMEM(seq->sessionid.data, NFS4_MAX_SESSIONID_LEN);
-	WRITE32(seq->seqid);
-	WRITE32(seq->slotid);
+	p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 20);
+	if (!p)
+		return nfserr_resource;
+	p = xdr_encode_opaque_fixed(p, seq->sessionid.data,
+					NFS4_MAX_SESSIONID_LEN);
+	*p++ = cpu_to_be32(seq->seqid);
+	*p++ = cpu_to_be32(seq->slotid);
 	/* Note slotid's are numbered from zero: */
-	WRITE32(seq->maxslots - 1); /* sr_highest_slotid */
-	WRITE32(seq->maxslots - 1); /* sr_target_highest_slotid */
-	WRITE32(seq->status_flags);
+	*p++ = cpu_to_be32(seq->maxslots - 1); /* sr_highest_slotid */
+	*p++ = cpu_to_be32(seq->maxslots - 1); /* sr_target_highest_slotid */
+	*p++ = cpu_to_be32(seq->status_flags);
 
-	ADJUST_ARGS();
-	resp->cstate.datap = p; /* DRC cache data pointer */
+	resp->cstate.data_offset = xdr->buf->len; /* DRC cache data pointer */
 	return 0;
 }
 
@@ -3471,20 +3743,22 @@ static __be32
 nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
 			  struct nfsd4_test_stateid *test_stateid)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	struct nfsd4_test_stateid_id *stateid, *next;
 	__be32 *p;
 
 	if (nfserr)
 		return nfserr;
 
-	RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids));
+	p = xdr_reserve_space(xdr, 4 + (4 * test_stateid->ts_num_ids));
+	if (!p)
+		return nfserr_resource;
 	*p++ = htonl(test_stateid->ts_num_ids);
 
 	list_for_each_entry_safe(stateid, next, &test_stateid->ts_stateid_list, ts_id_list) {
 		*p++ = stateid->ts_id_status;
 	}
 
-	ADJUST_ARGS();
 	return nfserr;
 }
 
@@ -3563,81 +3837,99 @@ static nfsd4_enc nfsd4_enc_ops[] = {
 };
 
 /*
- * Calculate the total amount of memory that the compound response has taken
- * after encoding the current operation with pad.
- *
- * pad: if operation is non-idempotent, pad was calculate by op_rsize_bop()
- *      which was specified at nfsd4_operation, else pad is zero.
- *
- * Compare this length to the session se_fmaxresp_sz and se_fmaxresp_cached.
+ * Calculate whether we still have space to encode repsize bytes.
+ * There are two considerations:
+ *     - For NFS versions >=4.1, the size of the reply must stay within
+ *       session limits
+ *     - For all NFS versions, we must stay within limited preallocated
+ *       buffer space.
  *
- * Our se_fmaxresp_cached will always be a multiple of PAGE_SIZE, and so
- * will be at least a page and will therefore hold the xdr_buf head.
+ * This is called before the operation is processed, so can only provide
+ * an upper estimate.  For some nonidempotent operations (such as
+ * getattr), it's not necessarily a problem if that estimate is wrong,
+ * as we can fail it after processing without significant side effects.
  */
-__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 pad)
+__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 respsize)
 {
-	struct xdr_buf *xb = &resp->rqstp->rq_res;
-	struct nfsd4_session *session = NULL;
+	struct xdr_buf *buf = &resp->rqstp->rq_res;
 	struct nfsd4_slot *slot = resp->cstate.slot;
-	u32 length, tlen = 0;
 
+	if (buf->len + respsize <= buf->buflen)
+		return nfs_ok;
 	if (!nfsd4_has_session(&resp->cstate))
-		return 0;
-
-	session = resp->cstate.session;
-
-	if (xb->page_len == 0) {
-		length = (char *)resp->p - (char *)xb->head[0].iov_base + pad;
-	} else {
-		if (xb->tail[0].iov_base && xb->tail[0].iov_len > 0)
-			tlen = (char *)resp->p - (char *)xb->tail[0].iov_base;
-
-		length = xb->head[0].iov_len + xb->page_len + tlen + pad;
-	}
-	dprintk("%s length %u, xb->page_len %u tlen %u pad %u\n", __func__,
-		length, xb->page_len, tlen, pad);
-
-	if (length > session->se_fchannel.maxresp_sz)
-		return nfserr_rep_too_big;
-
-	if ((slot->sl_flags & NFSD4_SLOT_CACHETHIS) &&
-	    length > session->se_fchannel.maxresp_cached)
+		return nfserr_resource;
+	if (slot->sl_flags & NFSD4_SLOT_CACHETHIS) {
+		WARN_ON_ONCE(1);
 		return nfserr_rep_too_big_to_cache;
-
-	return 0;
+	}
+	return nfserr_rep_too_big;
 }
 
 void
 nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
 {
+	struct xdr_stream *xdr = &resp->xdr;
 	struct nfs4_stateowner *so = resp->cstate.replay_owner;
-	__be32 *statp;
+	struct svc_rqst *rqstp = resp->rqstp;
+	int post_err_offset;
+	nfsd4_enc encoder;
 	__be32 *p;
 
-	RESERVE_SPACE(8);
-	WRITE32(op->opnum);
-	statp = p++;	/* to be backfilled at the end */
-	ADJUST_ARGS();
+	p = xdr_reserve_space(xdr, 8);
+	if (!p) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+	*p++ = cpu_to_be32(op->opnum);
+	post_err_offset = xdr->buf->len;
 
 	if (op->opnum == OP_ILLEGAL)
 		goto status;
 	BUG_ON(op->opnum < 0 || op->opnum >= ARRAY_SIZE(nfsd4_enc_ops) ||
 	       !nfsd4_enc_ops[op->opnum]);
-	op->status = nfsd4_enc_ops[op->opnum](resp, op->status, &op->u);
+	encoder = nfsd4_enc_ops[op->opnum];
+	op->status = encoder(resp, op->status, &op->u);
+	xdr_commit_encode(xdr);
+
 	/* nfsd4_check_resp_size guarantees enough room for error status */
-	if (!op->status)
-		op->status = nfsd4_check_resp_size(resp, 0);
+	if (!op->status) {
+		int space_needed = 0;
+		if (!nfsd4_last_compound_op(rqstp))
+			space_needed = COMPOUND_ERR_SLACK_SPACE;
+		op->status = nfsd4_check_resp_size(resp, space_needed);
+	}
+	if (op->status == nfserr_resource && nfsd4_has_session(&resp->cstate)) {
+		struct nfsd4_slot *slot = resp->cstate.slot;
+
+		if (slot->sl_flags & NFSD4_SLOT_CACHETHIS)
+			op->status = nfserr_rep_too_big_to_cache;
+		else
+			op->status = nfserr_rep_too_big;
+	}
+	if (op->status == nfserr_resource ||
+	    op->status == nfserr_rep_too_big ||
+	    op->status == nfserr_rep_too_big_to_cache) {
+		/*
+		 * The operation may have already been encoded or
+		 * partially encoded.  No op returns anything additional
+		 * in the case of one of these three errors, so we can
+		 * just truncate back to after the status.  But it's a
+		 * bug if we had to do this on a non-idempotent op:
+		 */
+		warn_on_nonidempotent_op(op);
+		xdr_truncate_encode(xdr, post_err_offset);
+	}
 	if (so) {
+		int len = xdr->buf->len - post_err_offset;
+
 		so->so_replay.rp_status = op->status;
-		so->so_replay.rp_buflen = (char *)resp->p - (char *)(statp+1);
-		memcpy(so->so_replay.rp_buf, statp+1, so->so_replay.rp_buflen);
+		so->so_replay.rp_buflen = len;
+		read_bytes_from_xdr_buf(xdr->buf, post_err_offset,
+						so->so_replay.rp_buf, len);
 	}
 status:
-	/*
-	 * Note: We write the status directly, instead of using WRITE32(),
-	 * since it is already in network byte order.
-	 */
-	*statp = op->status;
+	/* Note that op->status is already in network byte order: */
+	write_bytes_to_xdr_buf(xdr->buf, post_err_offset - 4, &op->status, 4);
 }
 
 /* 
@@ -3649,21 +3941,22 @@ status:
  * called with nfs4_lock_state() held
  */
 void
-nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
+nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
 {
 	__be32 *p;
 	struct nfs4_replay *rp = op->replay;
 
 	BUG_ON(!rp);
 
-	RESERVE_SPACE(8);
-	WRITE32(op->opnum);
+	p = xdr_reserve_space(xdr, 8 + rp->rp_buflen);
+	if (!p) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+	*p++ = cpu_to_be32(op->opnum);
 	*p++ = rp->rp_status;  /* already xdr'ed */
-	ADJUST_ARGS();
 
-	RESERVE_SPACE(rp->rp_buflen);
-	WRITEMEM(rp->rp_buf, rp->rp_buflen);
-	ADJUST_ARGS();
+	p = xdr_encode_opaque_fixed(p, rp->rp_buf, rp->rp_buflen);
 }
 
 int
@@ -3720,19 +4013,19 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
 	 * All that remains is to write the tag and operation count...
 	 */
 	struct nfsd4_compound_state *cs = &resp->cstate;
-	struct kvec *iov;
+	struct xdr_buf *buf = resp->xdr.buf;
+
+	WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
+				 buf->tail[0].iov_len);
+
+	rqstp->rq_next_page = resp->xdr.page_ptr + 1;
+
 	p = resp->tagp;
 	*p++ = htonl(resp->taglen);
 	memcpy(p, resp->tag, resp->taglen);
 	p += XDR_QUADLEN(resp->taglen);
 	*p++ = htonl(resp->opcnt);
 
-	if (rqstp->rq_res.page_len) 
-		iov = &rqstp->rq_res.tail[0];
-	else
-		iov = &rqstp->rq_res.head[0];
-	iov->iov_len = ((char*)resp->p) - (char*)iov->iov_base;
-	BUG_ON(iov->iov_len > PAGE_SIZE);
 	if (nfsd4_has_session(cs)) {
 		struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 		struct nfs4_client *clp = cs->session->se_client;
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index f8f060ffbf4..6040da8830f 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -224,13 +224,6 @@ hash_refile(struct svc_cacherep *rp)
 	hlist_add_head(&rp->c_hash, cache_hash + hash_32(rp->c_xid, maskbits));
 }
 
-static inline bool
-nfsd_cache_entry_expired(struct svc_cacherep *rp)
-{
-	return rp->c_state != RC_INPROG &&
-	       time_after(jiffies, rp->c_timestamp + RC_EXPIRE);
-}
-
 /*
  * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
  * Also prune the oldest ones when the total exceeds the max number of entries.
@@ -242,8 +235,14 @@ prune_cache_entries(void)
 	long freed = 0;
 
 	list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
-		if (!nfsd_cache_entry_expired(rp) &&
-		    num_drc_entries <= max_drc_entries)
+		/*
+		 * Don't free entries attached to calls that are still
+		 * in-progress, but do keep scanning the list.
+		 */
+		if (rp->c_state == RC_INPROG)
+			continue;
+		if (num_drc_entries <= max_drc_entries &&
+		    time_before(jiffies, rp->c_timestamp + RC_EXPIRE))
 			break;
 		nfsd_reply_cache_free_locked(rp);
 		freed++;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index f34d9de802a..51844048937 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1179,7 +1179,6 @@ static int __init init_nfsd(void)
 	retval = nfsd4_init_slabs();
 	if (retval)
 		goto out_unregister_pernet;
-	nfs4_state_init();
 	retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */
 	if (retval)
 		goto out_free_slabs;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 479eb681c27..847daf37e56 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -15,11 +15,20 @@
 #include <linux/nfs2.h>
 #include <linux/nfs3.h>
 #include <linux/nfs4.h>
+#include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/msg_prot.h>
 
-#include <linux/nfsd/debug.h>
-#include <linux/nfsd/export.h>
-#include <linux/nfsd/stats.h>
+#include <uapi/linux/nfsd/debug.h>
+
+#include "stats.h"
+#include "export.h"
+
+#undef ifdebug
+#ifdef NFSD_DEBUG
+# define ifdebug(flag)		if (nfsd_debug & NFSDDBG_##flag)
+#else
+# define ifdebug(flag)		if (0)
+#endif
 
 /*
  * nfsd version
@@ -106,7 +115,6 @@ static inline int nfsd_v4client(struct svc_rqst *rq)
  */
 #ifdef CONFIG_NFSD_V4
 extern unsigned long max_delegations;
-void nfs4_state_init(void);
 int nfsd4_init_slabs(void);
 void nfsd4_free_slabs(void);
 int nfs4_state_start(void);
@@ -117,7 +125,6 @@ void nfs4_reset_lease(time_t leasetime);
 int nfs4_reset_recoverydir(char *recdir);
 char * nfs4_recoverydir(void);
 #else
-static inline void nfs4_state_init(void) { }
 static inline int nfsd4_init_slabs(void) { return 0; }
 static inline void nfsd4_free_slabs(void) { }
 static inline int nfs4_state_start(void) { return 0; }
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 3c37b160dca..ec839341815 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -88,9 +88,8 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
 	/* Check if the request originated from a secure port. */
 	if (!rqstp->rq_secure && !(flags & NFSEXP_INSECURE_PORT)) {
 		RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
-		dprintk(KERN_WARNING
-		       "nfsd: request from insecure port %s!\n",
-		       svc_print_addr(rqstp, buf, sizeof(buf)));
+		dprintk("nfsd: request from insecure port %s!\n",
+		        svc_print_addr(rqstp, buf, sizeof(buf)));
 		return nfserr_perm;
 	}
 
@@ -169,8 +168,8 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
 		data_left -= len;
 		if (data_left < 0)
 			return error;
-		exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_auth);
-		fid = (struct fid *)(fh->fh_auth + len);
+		exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_fsid);
+		fid = (struct fid *)(fh->fh_fsid + len);
 	} else {
 		__u32 tfh[2];
 		dev_t xdev;
@@ -385,7 +384,7 @@ static void _fh_update(struct svc_fh *fhp, struct svc_export *exp,
 {
 	if (dentry != exp->ex_path.dentry) {
 		struct fid *fid = (struct fid *)
-			(fhp->fh_handle.fh_auth + fhp->fh_handle.fh_size/4 - 1);
+			(fhp->fh_handle.fh_fsid + fhp->fh_handle.fh_size/4 - 1);
 		int maxsize = (fhp->fh_maxsize - fhp->fh_handle.fh_size)/4;
 		int subtreecheck = !(exp->ex_flags & NFSEXP_NOSUBTREECHECK);
 
@@ -513,7 +512,6 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 	 */
 
 	struct inode * inode = dentry->d_inode;
-	__u32 *datap;
 	dev_t ex_dev = exp_sb(exp)->s_dev;
 
 	dprintk("nfsd: fh_compose(exp %02x:%02x/%ld %pd2, ino=%ld)\n",
@@ -557,17 +555,16 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 		if (inode)
 			_fh_update_old(dentry, exp, &fhp->fh_handle);
 	} else {
-		int len;
+		fhp->fh_handle.fh_size =
+			key_len(fhp->fh_handle.fh_fsid_type) + 4;
 		fhp->fh_handle.fh_auth_type = 0;
-		datap = fhp->fh_handle.fh_auth+0;
-		mk_fsid(fhp->fh_handle.fh_fsid_type, datap, ex_dev,
+
+		mk_fsid(fhp->fh_handle.fh_fsid_type,
+			fhp->fh_handle.fh_fsid,
+			ex_dev,
 			exp->ex_path.dentry->d_inode->i_ino,
 			exp->ex_fsid, exp->ex_uuid);
 
-		len = key_len(fhp->fh_handle.fh_fsid_type);
-		datap += len/4;
-		fhp->fh_handle.fh_size = 4 + len;
-
 		if (inode)
 			_fh_update(fhp, exp, dentry);
 		if (fhp->fh_handle.fh_fileid_type == FILEID_INVALID) {
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index ad67964d0bb..2e89e70ac15 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -1,9 +1,58 @@
-/* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */
+/*
+ * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
+ *
+ * This file describes the layout of the file handles as passed
+ * over the wire.
+ */
+#ifndef _LINUX_NFSD_NFSFH_H
+#define _LINUX_NFSD_NFSFH_H
+
+#include <linux/sunrpc/svc.h>
+#include <uapi/linux/nfsd/nfsfh.h>
+
+static inline __u32 ino_t_to_u32(ino_t ino)
+{
+	return (__u32) ino;
+}
+
+static inline ino_t u32_to_ino_t(__u32 uino)
+{
+	return (ino_t) uino;
+}
 
-#ifndef _LINUX_NFSD_FH_INT_H
-#define _LINUX_NFSD_FH_INT_H
+/*
+ * This is the internal representation of an NFS handle used in knfsd.
+ * pre_mtime/post_version will be used to support wcc_attr's in NFSv3.
+ */
+typedef struct svc_fh {
+	struct knfsd_fh		fh_handle;	/* FH data */
+	struct dentry *		fh_dentry;	/* validated dentry */
+	struct svc_export *	fh_export;	/* export pointer */
+	int			fh_maxsize;	/* max size for fh_handle */
+
+	unsigned char		fh_locked;	/* inode locked by us */
+	unsigned char		fh_want_write;	/* remount protection taken */
+
+#ifdef CONFIG_NFSD_V3
+	unsigned char		fh_post_saved;	/* post-op attrs saved */
+	unsigned char		fh_pre_saved;	/* pre-op attrs saved */
+
+	/* Pre-op attributes saved during fh_lock */
+	__u64			fh_pre_size;	/* size before operation */
+	struct timespec		fh_pre_mtime;	/* mtime before oper */
+	struct timespec		fh_pre_ctime;	/* ctime before oper */
+	/*
+	 * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode)
+	 *  to find out if it is valid.
+	 */
+	u64			fh_pre_change;
+
+	/* Post-op attributes saved in fh_unlock */
+	struct kstat		fh_post_attr;	/* full attrs after operation */
+	u64			fh_post_change; /* nfsv4 change; see above */
+#endif /* CONFIG_NFSD_V3 */
 
-#include <linux/nfsd/nfsfh.h>
+} svc_fh;
 
 enum nfsd_fsid {
 	FSID_DEV = 0,
@@ -215,4 +264,4 @@ fh_unlock(struct svc_fh *fhp)
 	}
 }
 
-#endif /* _LINUX_NFSD_FH_INT_H */
+#endif /* _LINUX_NFSD_NFSFH_H */
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 9a4a5f9e746..1879e43f286 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -591,12 +591,6 @@ nfsd(void *vrqstp)
 	nfsdstats.th_cnt++;
 	mutex_unlock(&nfsd_mutex);
 
-	/*
-	 * We want less throttling in balance_dirty_pages() so that nfs to
-	 * localhost doesn't cause nfsd to lock up due to all the client's
-	 * dirty pages.
-	 */
-	current->flags |= PF_LESS_THROTTLE;
 	set_freezable();
 
 	/*
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 9c769a47ac5..1ac306b769d 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -214,7 +214,8 @@ nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
 int
 nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
 {
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	return xdr_argsize_check(rqstp, p);
 }
@@ -248,7 +249,8 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 {
 	unsigned int len;
 	int v;
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 
 	args->offset    = ntohl(*p++);
@@ -281,7 +283,8 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	unsigned int len, hdr, dlen;
 	int v;
 
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 
 	p++;				/* beginoffset */
@@ -355,7 +358,8 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
 int
 nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args)
 {
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	args->buffer = page_address(*(rqstp->rq_next_page++));
 
@@ -391,7 +395,8 @@ int
 nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd_readdirargs *args)
 {
-	if (!(p = decode_fh(p, &args->fh)))
+	p = decode_fh(p, &args->fh);
+	if (!p)
 		return 0;
 	args->cookie = ntohl(*p++);
 	args->count  = ntohl(*p++);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 424d8f5f231..374c66283ac 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -37,7 +37,6 @@
 
 #include <linux/idr.h>
 #include <linux/sunrpc/svc_xprt.h>
-#include <linux/nfsd/nfsfh.h>
 #include "nfsfh.h"
 
 typedef struct {
@@ -123,7 +122,7 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s)
 /* Maximum number of operations per session compound */
 #define NFSD_MAX_OPS_PER_COMPOUND	16
 /* Maximum  session per slot cache size */
-#define NFSD_SLOT_CACHE_SIZE		1024
+#define NFSD_SLOT_CACHE_SIZE		2048
 /* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
 #define NFSD_CACHE_SIZE_SLOTS_PER_SESSION	32
 #define NFSD_MAX_MEM_PER_SESSION  \
@@ -464,8 +463,6 @@ extern void nfs4_release_reclaim(struct nfsd_net *);
 extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
 							struct nfsd_net *nn);
 extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn);
-extern void nfs4_free_openowner(struct nfs4_openowner *);
-extern void nfs4_free_lockowner(struct nfs4_lockowner *);
 extern int set_callback_cred(void);
 extern void nfsd4_init_callback(struct nfsd4_callback *);
 extern void nfsd4_probe_callback(struct nfs4_client *clp);
diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c
index 6d4521feb6e..cd90878a76a 100644
--- a/fs/nfsd/stats.c
+++ b/fs/nfsd/stats.c
@@ -24,7 +24,6 @@
 #include <linux/seq_file.h>
 #include <linux/module.h>
 #include <linux/sunrpc/stats.h>
-#include <linux/nfsd/stats.h>
 #include <net/net_namespace.h>
 
 #include "nfsd.h"
diff --git a/include/linux/nfsd/stats.h b/fs/nfsd/stats.h
index e75b2544ff1..a5c944b771c 100644
--- a/include/linux/nfsd/stats.h
+++ b/fs/nfsd/stats.h
@@ -1,12 +1,10 @@
 /*
- * linux/include/linux/nfsd/stats.h
- *
  * Statistics for NFS server.
  *
  * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
  */
-#ifndef LINUX_NFSD_STATS_H
-#define LINUX_NFSD_STATS_H
+#ifndef _NFSD_STATS_H
+#define _NFSD_STATS_H
 
 #include <uapi/linux/nfsd/stats.h>
 
@@ -42,4 +40,4 @@ extern struct svc_stat		nfsd_svcstats;
 void	nfsd_stat_init(void);
 void	nfsd_stat_shutdown(void);
 
-#endif /* LINUX_NFSD_STATS_H */
+#endif /* _NFSD_STATS_H */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 16f0673a423..140c496f612 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -820,55 +820,54 @@ static int nfsd_direct_splice_actor(struct pipe_inode_info *pipe,
 	return __splice_from_pipe(pipe, sd, nfsd_splice_actor);
 }
 
-static __be32
-nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
-              loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+__be32 nfsd_finish_read(struct file *file, unsigned long *count, int host_err)
 {
-	mm_segment_t	oldfs;
-	__be32		err;
-	int		host_err;
-
-	err = nfserr_perm;
-
-	if (file->f_op->splice_read && rqstp->rq_splice_ok) {
-		struct splice_desc sd = {
-			.len		= 0,
-			.total_len	= *count,
-			.pos		= offset,
-			.u.data		= rqstp,
-		};
-
-		rqstp->rq_next_page = rqstp->rq_respages + 1;
-		host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
-	} else {
-		oldfs = get_fs();
-		set_fs(KERNEL_DS);
-		host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
-		set_fs(oldfs);
-	}
-
 	if (host_err >= 0) {
 		nfsdstats.io_read += host_err;
 		*count = host_err;
-		err = 0;
 		fsnotify_access(file);
+		return 0;
 	} else 
-		err = nfserrno(host_err);
-	return err;
+		return nfserrno(host_err);
+}
+
+int nfsd_splice_read(struct svc_rqst *rqstp,
+		     struct file *file, loff_t offset, unsigned long *count)
+{
+	struct splice_desc sd = {
+		.len		= 0,
+		.total_len	= *count,
+		.pos		= offset,
+		.u.data		= rqstp,
+	};
+	int host_err;
+
+	rqstp->rq_next_page = rqstp->rq_respages + 1;
+	host_err = splice_direct_to_actor(file, &sd, nfsd_direct_splice_actor);
+	return nfsd_finish_read(file, count, host_err);
 }
 
-static void kill_suid(struct dentry *dentry)
+int nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
+		unsigned long *count)
 {
-	struct iattr	ia;
-	ia.ia_valid = ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
+	mm_segment_t oldfs;
+	int host_err;
 
-	mutex_lock(&dentry->d_inode->i_mutex);
-	/*
-	 * Note we call this on write, so notify_change will not
-	 * encounter any conflicting delegations:
-	 */
-	notify_change(dentry, &ia, NULL);
-	mutex_unlock(&dentry->d_inode->i_mutex);
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
+	set_fs(oldfs);
+	return nfsd_finish_read(file, count, host_err);
+}
+
+static __be32
+nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file,
+	      loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+{
+	if (file->f_op->splice_read && rqstp->rq_splice_ok)
+		return nfsd_splice_read(rqstp, file, offset, count);
+	else
+		return nfsd_readv(file, offset, vec, vlen, count);
 }
 
 /*
@@ -922,6 +921,16 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	int			stable = *stablep;
 	int			use_wgather;
 	loff_t			pos = offset;
+	unsigned int		pflags = current->flags;
+
+	if (rqstp->rq_local)
+		/*
+		 * We want less throttling in balance_dirty_pages()
+		 * and shrink_inactive_list() so that nfs to
+		 * localhost doesn't cause nfsd to lock up due to all
+		 * the client's dirty pages or its congested queue.
+		 */
+		current->flags |= PF_LESS_THROTTLE;
 
 	dentry = file->f_path.dentry;
 	inode = dentry->d_inode;
@@ -942,10 +951,6 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	nfsdstats.io_write += host_err;
 	fsnotify_modify(file);
 
-	/* clear setuid/setgid flag after write */
-	if (inode->i_mode & (S_ISUID | S_ISGID))
-		kill_suid(dentry);
-
 	if (stable) {
 		if (use_wgather)
 			host_err = wait_for_concurrent_writes(file);
@@ -959,36 +964,33 @@ out_nfserr:
 		err = 0;
 	else
 		err = nfserrno(host_err);
+	if (rqstp->rq_local)
+		tsk_restore_flags(current, pflags, PF_LESS_THROTTLE);
 	return err;
 }
 
-/*
- * Read data from a file. count must contain the requested read count
- * on entry. On return, *count contains the number of bytes actually read.
- * N.B. After this call fhp needs an fh_put
- */
-__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
-	loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
+__be32 nfsd_get_tmp_read_open(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		struct file **file, struct raparms **ra)
 {
-	struct file *file;
 	struct inode *inode;
-	struct raparms	*ra;
 	__be32 err;
 
-	err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
+	err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, file);
 	if (err)
 		return err;
 
-	inode = file_inode(file);
+	inode = file_inode(*file);
 
 	/* Get readahead parameters */
-	ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
+	*ra = nfsd_get_raparms(inode->i_sb->s_dev, inode->i_ino);
 
-	if (ra && ra->p_set)
-		file->f_ra = ra->p_ra;
-
-	err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
+	if (*ra && (*ra)->p_set)
+		(*file)->f_ra = (*ra)->p_ra;
+	return nfs_ok;
+}
 
+void nfsd_put_tmp_read_open(struct file *file, struct raparms *ra)
+{
 	/* Write back readahead params */
 	if (ra) {
 		struct raparm_hbucket *rab = &raparm_hash[ra->p_hindex];
@@ -998,28 +1000,29 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		ra->p_count--;
 		spin_unlock(&rab->pb_lock);
 	}
-
 	nfsd_close(file);
-	return err;
 }
 
-/* As above, but use the provided file descriptor. */
-__be32
-nfsd_read_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
-		loff_t offset, struct kvec *vec, int vlen,
-		unsigned long *count)
+/*
+ * Read data from a file. count must contain the requested read count
+ * on entry. On return, *count contains the number of bytes actually read.
+ * N.B. After this call fhp needs an fh_put
+ */
+__be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
+	loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
 {
-	__be32		err;
+	struct file *file;
+	struct raparms	*ra;
+	__be32 err;
+
+	err = nfsd_get_tmp_read_open(rqstp, fhp, &file, &ra);
+	if (err)
+		return err;
+
+	err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count);
+
+	nfsd_put_tmp_read_open(file, ra);
 
-	if (file) {
-		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
-				NFSD_MAY_READ|NFSD_MAY_OWNER_OVERRIDE);
-		if (err)
-			goto out;
-		err = nfsd_vfs_read(rqstp, fhp, file, offset, vec, vlen, count);
-	} else /* Note file may still be NULL in NFSv4 special stateid case: */
-		err = nfsd_read(rqstp, fhp, offset, vec, vlen, count);
-out:
 	return err;
 }
 
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index fbe90bdb221..91b6ae3f658 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -70,10 +70,16 @@ __be32		nfsd_commit(struct svc_rqst *, struct svc_fh *,
 __be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
 				int, struct file **);
 void		nfsd_close(struct file *);
+struct raparms;
+__be32		nfsd_get_tmp_read_open(struct svc_rqst *, struct svc_fh *,
+				struct file **, struct raparms **);
+void		nfsd_put_tmp_read_open(struct file *, struct raparms *);
+int		nfsd_splice_read(struct svc_rqst *,
+				struct file *, loff_t, unsigned long *);
+int		nfsd_readv(struct file *, loff_t, struct kvec *, int,
+				unsigned long *);
 __be32 		nfsd_read(struct svc_rqst *, struct svc_fh *,
 				loff_t, struct kvec *, int, unsigned long *);
-__be32 		nfsd_read_file(struct svc_rqst *, struct svc_fh *, struct file *,
-				loff_t, struct kvec *, int, unsigned long *);
 __be32 		nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *,
 				loff_t, struct kvec *,int, unsigned long *, int *);
 __be32		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 5ea7df30508..18cbb6d9c8a 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -58,7 +58,7 @@ struct nfsd4_compound_state {
 	/* For sessions DRC */
 	struct nfsd4_session	*session;
 	struct nfsd4_slot	*slot;
-	__be32			*datap;
+	int			data_offset;
 	size_t			iovlen;
 	u32			minorversion;
 	__be32			status;
@@ -287,9 +287,8 @@ struct nfsd4_readdir {
 	struct svc_fh * rd_fhp;             /* response */
 
 	struct readdir_cd	common;
-	__be32 *		buffer;
-	int			buflen;
-	__be32 *		offset;
+	struct xdr_stream	*xdr;
+	int			cookie_offset;
 };
 
 struct nfsd4_release_lockowner {
@@ -506,9 +505,7 @@ struct nfsd4_compoundargs {
 
 struct nfsd4_compoundres {
 	/* scratch variables for XDR encode */
-	__be32 *			p;
-	__be32 *			end;
-	struct xdr_buf *		xbuf;
+	struct xdr_stream		xdr;
 	struct svc_rqst *		rqstp;
 
 	u32				taglen;
@@ -538,6 +535,9 @@ static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp)
 	return argp->opcnt == resp->opcnt;
 }
 
+int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op);
+void warn_on_nonidempotent_op(struct nfsd4_op *op);
+
 #define NFS4_SVC_XDRSIZE		sizeof(struct nfsd4_compoundargs)
 
 static inline void
@@ -563,10 +563,11 @@ int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *,
 		struct nfsd4_compoundres *);
 __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
 void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
-void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op);
-__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
-		       struct dentry *dentry, __be32 **buffer, int countp,
-		       u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
+void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op);
+__be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
+		struct svc_fh *fhp, struct svc_export *exp,
+		struct dentry *dentry,
+		u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
 extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *,
 		struct nfsd4_setclientid *setclid);
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index f3a82fbcae0..24978153c0c 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -152,10 +152,10 @@ static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma)
  */
 const struct file_operations nilfs_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= generic_file_aio_read,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= generic_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.unlocked_ioctl	= nilfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= nilfs_compat_ioctl,
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index b9c5726120e..6252b173a46 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -298,19 +298,20 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
 }
 
 static ssize_t
-nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
-		loff_t offset, unsigned long nr_segs)
+nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+		loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file->f_mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t size;
 
 	if (rw == WRITE)
 		return 0;
 
 	/* Needs synchronization with the cleaner */
-	size = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+	size = blockdev_direct_IO(rw, iocb, inode, iter, offset,
 				  nilfs_get_block);
 
 	/*
@@ -319,7 +320,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	 */
 	if (unlikely((rw & WRITE) && size < 0)) {
 		loff_t isize = i_size_read(inode);
-		loff_t end = offset + iov_length(iov, nr_segs);
+		loff_t end = offset + count;
 
 		if (end > isize)
 			nilfs_write_failed(mapping, end);
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 86ddab916b6..5c9e2c81cb1 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -2090,10 +2090,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb,
 	size_t count;		/* after file limit checks */
 	ssize_t written, err;
 
-	count = 0;
-	err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ);
-	if (err)
-		return err;
+	count = iov_length(iov, nr_segs);
 	pos = *ppos;
 	/* We can write back this queue in page reclaim. */
 	current->backing_dev_info = mapping->backing_dev_info;
@@ -2202,8 +2199,8 @@ static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end,
 
 const struct file_operations ntfs_file_ops = {
 	.llseek		= generic_file_llseek,	 /* Seek inside file. */
-	.read		= do_sync_read,		 /* Read from file. */
-	.aio_read	= generic_file_aio_read, /* Async read from file. */
+	.read		= new_sync_read,	 /* Read from file. */
+	.read_iter	= generic_file_read_iter, /* Async read from file. */
 #ifdef NTFS_RW
 	.write		= do_sync_write,	 /* Write to file. */
 	.aio_write	= ntfs_file_aio_write,	 /* Async write to file. */
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index d310d12a9ad..4a231a166cf 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -599,9 +599,8 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 
 static ssize_t ocfs2_direct_IO(int rw,
 			       struct kiocb *iocb,
-			       const struct iovec *iov,
-			       loff_t offset,
-			       unsigned long nr_segs)
+			       struct iov_iter *iter,
+			       loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file)->i_mapping->host;
@@ -618,7 +617,7 @@ static ssize_t ocfs2_direct_IO(int rw,
 		return 0;
 
 	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
-				    iov, offset, nr_segs,
+				    iter, offset,
 				    ocfs2_direct_IO_get_blocks,
 				    ocfs2_dio_end_io, NULL, 0);
 }
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index a68e07a9bd4..681691bc233 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1799,7 +1799,7 @@ int o2net_register_hb_callbacks(void)
 
 /* ------------------------------------------------------------ */
 
-static int o2net_accept_one(struct socket *sock)
+static int o2net_accept_one(struct socket *sock, int *more)
 {
 	int ret, slen;
 	struct sockaddr_in sin;
@@ -1810,6 +1810,7 @@ static int o2net_accept_one(struct socket *sock)
 	struct o2net_node *nn;
 
 	BUG_ON(sock == NULL);
+	*more = 0;
 	ret = sock_create_lite(sock->sk->sk_family, sock->sk->sk_type,
 			       sock->sk->sk_protocol, &new_sock);
 	if (ret)
@@ -1821,6 +1822,7 @@ static int o2net_accept_one(struct socket *sock)
 	if (ret < 0)
 		goto out;
 
+	*more = 1;
 	new_sock->sk->sk_allocation = GFP_ATOMIC;
 
 	ret = o2net_set_nodelay(new_sock);
@@ -1919,11 +1921,36 @@ out:
 	return ret;
 }
 
+/*
+ * This function is invoked in response to one or more
+ * pending accepts at softIRQ level. We must drain the
+ * entire que before returning.
+ */
+
 static void o2net_accept_many(struct work_struct *work)
 {
 	struct socket *sock = o2net_listen_sock;
-	while (o2net_accept_one(sock) == 0)
+	int	more;
+	int	err;
+
+	/*
+	 * It is critical to note that due to interrupt moderation
+	 * at the network driver level, we can't assume to get a
+	 * softIRQ for every single conn since tcp SYN packets
+	 * can arrive back-to-back, and therefore many pending
+	 * accepts may result in just 1 softIRQ. If we terminate
+	 * the o2net_accept_one() loop upon seeing an err, what happens
+	 * to the rest of the conns in the queue? If no new SYN
+	 * arrives for hours, no softIRQ  will be delivered,
+	 * and the connections will just sit in the queue.
+	 */
+
+	for (;;) {
+		err = o2net_accept_one(sock, &more);
+		if (!more)
+			break;
 		cond_resched();
+	}
 }
 
 static void o2net_listen_data_ready(struct sock *sk)
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index a106b3f2b22..fae17c640df 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -331,6 +331,7 @@ struct dlm_lock_resource
 	u16 state;
 	char lvb[DLM_LVB_LEN];
 	unsigned int inflight_locks;
+	unsigned int inflight_assert_workers;
 	unsigned long refmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
 };
 
@@ -910,6 +911,9 @@ void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
 void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
 				   struct dlm_lock_resource *res);
 
+void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res);
+
 void dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
 void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
 void __dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 3087a21d32f..82abf0cc9a1 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -581,6 +581,7 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
 	atomic_set(&res->asts_reserved, 0);
 	res->migration_pending = 0;
 	res->inflight_locks = 0;
+	res->inflight_assert_workers = 0;
 
 	res->dlm = dlm;
 
@@ -683,6 +684,43 @@ void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
 	wake_up(&res->wq);
 }
 
+void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res)
+{
+	assert_spin_locked(&res->spinlock);
+	res->inflight_assert_workers++;
+	mlog(0, "%s:%.*s: inflight assert worker++: now %u\n",
+			dlm->name, res->lockname.len, res->lockname.name,
+			res->inflight_assert_workers);
+}
+
+static void dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res)
+{
+	spin_lock(&res->spinlock);
+	__dlm_lockres_grab_inflight_worker(dlm, res);
+	spin_unlock(&res->spinlock);
+}
+
+static void __dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res)
+{
+	assert_spin_locked(&res->spinlock);
+	BUG_ON(res->inflight_assert_workers == 0);
+	res->inflight_assert_workers--;
+	mlog(0, "%s:%.*s: inflight assert worker--: now %u\n",
+			dlm->name, res->lockname.len, res->lockname.name,
+			res->inflight_assert_workers);
+}
+
+static void dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
+		struct dlm_lock_resource *res)
+{
+	spin_lock(&res->spinlock);
+	__dlm_lockres_drop_inflight_worker(dlm, res);
+	spin_unlock(&res->spinlock);
+}
+
 /*
  * lookup a lock resource by name.
  * may already exist in the hashtable.
@@ -1603,7 +1641,8 @@ send_response:
 			mlog(ML_ERROR, "failed to dispatch assert master work\n");
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
-		}
+		} else
+			dlm_lockres_grab_inflight_worker(dlm, res);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
@@ -2118,6 +2157,8 @@ static void dlm_assert_master_worker(struct dlm_work_item *item, void *data)
 	dlm_lockres_release_ast(dlm, res);
 
 put:
+	dlm_lockres_drop_inflight_worker(dlm, res);
+
 	dlm_lockres_put(res);
 
 	mlog(0, "finished with dlm_assert_master_worker\n");
@@ -3088,11 +3129,15 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm,
 			/* remove it so that only one mle will be found */
 			__dlm_unlink_mle(dlm, tmp);
 			__dlm_mle_detach_hb_events(dlm, tmp);
-			ret = DLM_MIGRATE_RESPONSE_MASTERY_REF;
-			mlog(0, "%s:%.*s: master=%u, newmaster=%u, "
-			    "telling master to get ref for cleared out mle "
-			    "during migration\n", dlm->name, namelen, name,
-			    master, new_master);
+			if (tmp->type == DLM_MLE_MASTER) {
+				ret = DLM_MIGRATE_RESPONSE_MASTERY_REF;
+				mlog(0, "%s:%.*s: master=%u, newmaster=%u, "
+						"telling master to get ref "
+						"for cleared out mle during "
+						"migration\n", dlm->name,
+						namelen, name, master,
+						new_master);
+			}
 		}
 		spin_unlock(&tmp->spinlock);
 	}
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 5de019437ea..45067faf569 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1708,7 +1708,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 				mlog_errno(-ENOMEM);
 				/* retry!? */
 				BUG();
-			}
+			} else
+				__dlm_lockres_grab_inflight_worker(dlm, res);
 		} else /* put.. incase we are not the master */
 			dlm_lockres_put(res);
 		spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 9db869de829..69aac6f088a 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -259,12 +259,15 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm,
 		 * refs on it. */
 		unused = __dlm_lockres_unused(lockres);
 		if (!unused ||
-		    (lockres->state & DLM_LOCK_RES_MIGRATING)) {
+		    (lockres->state & DLM_LOCK_RES_MIGRATING) ||
+		    (lockres->inflight_assert_workers != 0)) {
 			mlog(0, "%s: res %.*s is in use or being remastered, "
-			     "used %d, state %d\n", dlm->name,
-			     lockres->lockname.len, lockres->lockname.name,
-			     !unused, lockres->state);
-			list_move_tail(&dlm->purge_list, &lockres->purge);
+			     "used %d, state %d, assert master workers %u\n",
+			     dlm->name, lockres->lockname.len,
+			     lockres->lockname.name,
+			     !unused, lockres->state,
+			     lockres->inflight_assert_workers);
+			list_move_tail(&lockres->purge, &dlm->purge_list);
 			spin_unlock(&lockres->spinlock);
 			continue;
 		}
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 5698b52cf5c..2e3c9dbab68 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -191,7 +191,9 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
 				     DLM_UNLOCK_CLEAR_CONVERT_TYPE);
 		} else if (status == DLM_RECOVERING ||
 			   status == DLM_MIGRATING ||
-			   status == DLM_FORWARD) {
+			   status == DLM_FORWARD ||
+			   status == DLM_NOLOCKMGR
+			   ) {
 			/* must clear the actions because this unlock
 			 * is about to be retried.  cannot free or do
 			 * any list manipulation. */
@@ -200,7 +202,8 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
 			     res->lockname.name,
 			     status==DLM_RECOVERING?"recovering":
 			     (status==DLM_MIGRATING?"migrating":
-			      "forward"));
+				(status == DLM_FORWARD ? "forward" :
+						"nolockmanager")));
 			actions = 0;
 		}
 		if (flags & LKM_CANCEL)
@@ -364,7 +367,10 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm,
 			 * updated state to the recovery master.  this thread
 			 * just needs to finish out the operation and call
 			 * the unlockast. */
-			ret = DLM_NORMAL;
+			if (dlm_is_node_dead(dlm, owner))
+				ret = DLM_NORMAL;
+			else
+				ret = DLM_NOLOCKMGR;
 		} else {
 			/* something bad.  this will BUG in ocfs2 */
 			ret = dlm_err_to_dlm_status(tmpret);
@@ -638,7 +644,9 @@ retry:
 
 	if (status == DLM_RECOVERING ||
 	    status == DLM_MIGRATING ||
-	    status == DLM_FORWARD) {
+	    status == DLM_FORWARD ||
+	    status == DLM_NOLOCKMGR) {
+
 		/* We want to go away for a tiny bit to allow recovery
 		 * / migration to complete on this resource. I don't
 		 * know of any wait queue we could sleep on as this
@@ -650,7 +658,7 @@ retry:
 		msleep(50);
 
 		mlog(0, "retrying unlock due to pending recovery/"
-		     "migration/in-progress\n");
+		     "migration/in-progress/reconnect\n");
 		goto retry;
 	}
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 8eb6e5732d3..2930e231f3f 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2233,16 +2233,13 @@ out:
 	return ret;
 }
 
-static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
-				    const struct iovec *iov,
-				    unsigned long nr_segs,
-				    loff_t pos)
+static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
+				    struct iov_iter *from)
 {
 	int ret, direct_io, appending, rw_level, have_alloc_sem  = 0;
 	int can_do_direct, has_refcount = 0;
 	ssize_t written = 0;
-	size_t ocount;		/* original count */
-	size_t count;		/* after file limit checks */
+	size_t count = iov_iter_count(from);
 	loff_t old_size, *ppos = &iocb->ki_pos;
 	u32 old_clusters;
 	struct file *file = iocb->ki_filp;
@@ -2256,7 +2253,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 		(unsigned long long)OCFS2_I(inode)->ip_blkno,
 		file->f_path.dentry->d_name.len,
 		file->f_path.dentry->d_name.name,
-		(unsigned int)nr_segs);
+		(unsigned int)from->nr_segs);	/* GRRRRR */
 
 	if (iocb->ki_nbytes == 0)
 		return 0;
@@ -2354,29 +2351,21 @@ relock:
 	/* communicate with ocfs2_dio_end_io */
 	ocfs2_iocb_set_rw_locked(iocb, rw_level);
 
-	ret = generic_segment_checks(iov, &nr_segs, &ocount,
-				     VERIFY_READ);
-	if (ret)
-		goto out_dio;
-
-	count = ocount;
 	ret = generic_write_checks(file, ppos, &count,
 				   S_ISBLK(inode->i_mode));
 	if (ret)
 		goto out_dio;
 
+	iov_iter_truncate(from, count);
 	if (direct_io) {
-		written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos,
-						    count, ocount);
+		written = generic_file_direct_write(iocb, from, *ppos);
 		if (written < 0) {
 			ret = written;
 			goto out_dio;
 		}
 	} else {
-		struct iov_iter from;
-		iov_iter_init(&from, iov, nr_segs, count, 0);
 		current->backing_dev_info = file->f_mapping->backing_dev_info;
-		written = generic_perform_write(file, &from, *ppos);
+		written = generic_perform_write(file, from, *ppos);
 		if (likely(written >= 0))
 			iocb->ki_pos = *ppos + written;
 		current->backing_dev_info = NULL;
@@ -2441,84 +2430,6 @@ out_sems:
 	return ret;
 }
 
-static int ocfs2_splice_to_file(struct pipe_inode_info *pipe,
-				struct file *out,
-				struct splice_desc *sd)
-{
-	int ret;
-
-	ret = ocfs2_prepare_inode_for_write(out, &sd->pos,
-					    sd->total_len, 0, NULL, NULL);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return ret;
-	}
-
-	return splice_from_pipe_feed(pipe, sd, pipe_to_file);
-}
-
-static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
-				       struct file *out,
-				       loff_t *ppos,
-				       size_t len,
-				       unsigned int flags)
-{
-	int ret;
-	struct address_space *mapping = out->f_mapping;
-	struct inode *inode = mapping->host;
-	struct splice_desc sd = {
-		.total_len = len,
-		.flags = flags,
-		.pos = *ppos,
-		.u.file = out,
-	};
-
-
-	trace_ocfs2_file_splice_write(inode, out, out->f_path.dentry,
-			(unsigned long long)OCFS2_I(inode)->ip_blkno,
-			out->f_path.dentry->d_name.len,
-			out->f_path.dentry->d_name.name, len);
-
-	pipe_lock(pipe);
-
-	splice_from_pipe_begin(&sd);
-	do {
-		ret = splice_from_pipe_next(pipe, &sd);
-		if (ret <= 0)
-			break;
-
-		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
-		ret = ocfs2_rw_lock(inode, 1);
-		if (ret < 0)
-			mlog_errno(ret);
-		else {
-			ret = ocfs2_splice_to_file(pipe, out, &sd);
-			ocfs2_rw_unlock(inode, 1);
-		}
-		mutex_unlock(&inode->i_mutex);
-	} while (ret > 0);
-	splice_from_pipe_end(pipe, &sd);
-
-	pipe_unlock(pipe);
-
-	if (sd.num_spliced)
-		ret = sd.num_spliced;
-
-	if (ret > 0) {
-		int err;
-
-		err = generic_write_sync(out, *ppos, ret);
-		if (err)
-			ret = err;
-		else
-			*ppos += ret;
-
-		balance_dirty_pages_ratelimited(mapping);
-	}
-
-	return ret;
-}
-
 static ssize_t ocfs2_file_splice_read(struct file *in,
 				      loff_t *ppos,
 				      struct pipe_inode_info *pipe,
@@ -2534,7 +2445,7 @@ static ssize_t ocfs2_file_splice_read(struct file *in,
 			in->f_path.dentry->d_name.name, len);
 
 	/*
-	 * See the comment in ocfs2_file_aio_read()
+	 * See the comment in ocfs2_file_read_iter()
 	 */
 	ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level);
 	if (ret < 0) {
@@ -2549,10 +2460,8 @@ bail:
 	return ret;
 }
 
-static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
-				   const struct iovec *iov,
-				   unsigned long nr_segs,
-				   loff_t pos)
+static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
+				   struct iov_iter *to)
 {
 	int ret = 0, rw_level = -1, have_alloc_sem = 0, lock_level = 0;
 	struct file *filp = iocb->ki_filp;
@@ -2561,7 +2470,8 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 	trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry,
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
 			filp->f_path.dentry->d_name.len,
-			filp->f_path.dentry->d_name.name, nr_segs);
+			filp->f_path.dentry->d_name.name,
+			to->nr_segs);	/* GRRRRR */
 
 
 	if (!inode) {
@@ -2606,13 +2516,13 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 	}
 	ocfs2_inode_unlock(inode, lock_level);
 
-	ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos);
+	ret = generic_file_read_iter(iocb, to);
 	trace_generic_file_aio_read_ret(ret);
 
 	/* buffered aio wouldn't have proper lock coverage today */
 	BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT));
 
-	/* see ocfs2_file_aio_write */
+	/* see ocfs2_file_write_iter */
 	if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {
 		rw_level = -1;
 		have_alloc_sem = 0;
@@ -2705,14 +2615,14 @@ const struct inode_operations ocfs2_special_file_iops = {
  */
 const struct file_operations ocfs2_fops = {
 	.llseek		= ocfs2_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
 	.mmap		= ocfs2_mmap,
 	.fsync		= ocfs2_sync_file,
 	.release	= ocfs2_file_release,
 	.open		= ocfs2_file_open,
-	.aio_read	= ocfs2_file_aio_read,
-	.aio_write	= ocfs2_file_aio_write,
+	.read_iter	= ocfs2_file_read_iter,
+	.write_iter	= ocfs2_file_write_iter,
 	.unlocked_ioctl	= ocfs2_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = ocfs2_compat_ioctl,
@@ -2720,7 +2630,7 @@ const struct file_operations ocfs2_fops = {
 	.lock		= ocfs2_lock,
 	.flock		= ocfs2_flock,
 	.splice_read	= ocfs2_file_splice_read,
-	.splice_write	= ocfs2_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
 };
 
@@ -2753,21 +2663,21 @@ const struct file_operations ocfs2_dops = {
  */
 const struct file_operations ocfs2_fops_no_plocks = {
 	.llseek		= ocfs2_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
 	.mmap		= ocfs2_mmap,
 	.fsync		= ocfs2_sync_file,
 	.release	= ocfs2_file_release,
 	.open		= ocfs2_file_open,
-	.aio_read	= ocfs2_file_aio_read,
-	.aio_write	= ocfs2_file_aio_write,
+	.read_iter	= ocfs2_file_read_iter,
+	.write_iter	= ocfs2_file_write_iter,
 	.unlocked_ioctl	= ocfs2_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = ocfs2_compat_ioctl,
 #endif
 	.flock		= ocfs2_flock,
 	.splice_read	= ocfs2_file_splice_read,
-	.splice_write	= ocfs2_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
 };
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 2060fc39844..8add6f1030d 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -205,6 +205,21 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode)
 	return inode;
 }
 
+static void ocfs2_cleanup_add_entry_failure(struct ocfs2_super *osb,
+		struct dentry *dentry, struct inode *inode)
+{
+	struct ocfs2_dentry_lock *dl = dentry->d_fsdata;
+
+	ocfs2_simple_drop_lockres(osb, &dl->dl_lockres);
+	ocfs2_lock_res_free(&dl->dl_lockres);
+	BUG_ON(dl->dl_count != 1);
+	spin_lock(&dentry_attach_lock);
+	dentry->d_fsdata = NULL;
+	spin_unlock(&dentry_attach_lock);
+	kfree(dl);
+	iput(inode);
+}
+
 static int ocfs2_mknod(struct inode *dir,
 		       struct dentry *dentry,
 		       umode_t mode,
@@ -231,6 +246,7 @@ static int ocfs2_mknod(struct inode *dir,
 	sigset_t oldset;
 	int did_block_signals = 0;
 	struct posix_acl *default_acl = NULL, *acl = NULL;
+	struct ocfs2_dentry_lock *dl = NULL;
 
 	trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name,
 			  (unsigned long long)OCFS2_I(dir)->ip_blkno,
@@ -423,6 +439,8 @@ static int ocfs2_mknod(struct inode *dir,
 		goto leave;
 	}
 
+	dl = dentry->d_fsdata;
+
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 OCFS2_I(inode)->ip_blkno, parent_fe_bh,
 				 &lookup);
@@ -469,6 +487,9 @@ leave:
 	 * ocfs2_delete_inode will mutex_lock again.
 	 */
 	if ((status < 0) && inode) {
+		if (dl)
+			ocfs2_cleanup_add_entry_failure(osb, dentry, inode);
+
 		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
 		clear_nlink(inode);
 		iput(inode);
@@ -991,6 +1012,65 @@ leave:
 	return status;
 }
 
+static int ocfs2_check_if_ancestor(struct ocfs2_super *osb,
+		u64 src_inode_no, u64 dest_inode_no)
+{
+	int ret = 0, i = 0;
+	u64 parent_inode_no = 0;
+	u64 child_inode_no = src_inode_no;
+	struct inode *child_inode;
+
+#define MAX_LOOKUP_TIMES 32
+	while (1) {
+		child_inode = ocfs2_iget(osb, child_inode_no, 0, 0);
+		if (IS_ERR(child_inode)) {
+			ret = PTR_ERR(child_inode);
+			break;
+		}
+
+		ret = ocfs2_inode_lock(child_inode, NULL, 0);
+		if (ret < 0) {
+			iput(child_inode);
+			if (ret != -ENOENT)
+				mlog_errno(ret);
+			break;
+		}
+
+		ret = ocfs2_lookup_ino_from_name(child_inode, "..", 2,
+				&parent_inode_no);
+		ocfs2_inode_unlock(child_inode, 0);
+		iput(child_inode);
+		if (ret < 0) {
+			ret = -ENOENT;
+			break;
+		}
+
+		if (parent_inode_no == dest_inode_no) {
+			ret = 1;
+			break;
+		}
+
+		if (parent_inode_no == osb->root_inode->i_ino) {
+			ret = 0;
+			break;
+		}
+
+		child_inode_no = parent_inode_no;
+
+		if (++i >= MAX_LOOKUP_TIMES) {
+			mlog(ML_NOTICE, "max lookup times reached, filesystem "
+					"may have nested directories, "
+					"src inode: %llu, dest inode: %llu.\n",
+					(unsigned long long)src_inode_no,
+					(unsigned long long)dest_inode_no);
+			ret = 0;
+			break;
+		}
+	}
+
+	return ret;
+}
+
 /*
  * The only place this should be used is rename!
  * if they have the same id, then the 1st one is the only one locked.
@@ -1002,6 +1082,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 			     struct inode *inode2)
 {
 	int status;
+	int inode1_is_ancestor, inode2_is_ancestor;
 	struct ocfs2_inode_info *oi1 = OCFS2_I(inode1);
 	struct ocfs2_inode_info *oi2 = OCFS2_I(inode2);
 	struct buffer_head **tmpbh;
@@ -1015,9 +1096,26 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	if (*bh2)
 		*bh2 = NULL;
 
-	/* we always want to lock the one with the lower lockid first. */
+	/* we always want to lock the one with the lower lockid first.
+	 * and if they are nested, we lock ancestor first */
 	if (oi1->ip_blkno != oi2->ip_blkno) {
-		if (oi1->ip_blkno < oi2->ip_blkno) {
+		inode1_is_ancestor = ocfs2_check_if_ancestor(osb, oi2->ip_blkno,
+				oi1->ip_blkno);
+		if (inode1_is_ancestor < 0) {
+			status = inode1_is_ancestor;
+			goto bail;
+		}
+
+		inode2_is_ancestor = ocfs2_check_if_ancestor(osb, oi1->ip_blkno,
+				oi2->ip_blkno);
+		if (inode2_is_ancestor < 0) {
+			status = inode2_is_ancestor;
+			goto bail;
+		}
+
+		if ((inode1_is_ancestor == 1) ||
+				(oi1->ip_blkno < oi2->ip_blkno &&
+				inode2_is_ancestor == 0)) {
 			/* switch id1 and id2 around */
 			tmpbh = bh2;
 			bh2 = bh1;
@@ -1098,6 +1196,7 @@ static int ocfs2_rename(struct inode *old_dir,
 	struct ocfs2_dir_lookup_result old_entry_lookup = { NULL, };
 	struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
 	struct ocfs2_dir_lookup_result target_insert = { NULL, };
+	bool should_add_orphan = false;
 
 	/* At some point it might be nice to break this function up a
 	 * bit. */
@@ -1134,6 +1233,21 @@ static int ocfs2_rename(struct inode *old_dir,
 			goto bail;
 		}
 		rename_lock = 1;
+
+		/* here we cannot guarantee the inodes haven't just been
+		 * changed, so check if they are nested again */
+		status = ocfs2_check_if_ancestor(osb, new_dir->i_ino,
+				old_inode->i_ino);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		} else if (status == 1) {
+			status = -EPERM;
+			trace_ocfs2_rename_not_permitted(
+					(unsigned long long)old_inode->i_ino,
+					(unsigned long long)new_dir->i_ino);
+			goto bail;
+		}
 	}
 
 	/* if old and new are the same, this'll just do one lock. */
@@ -1304,6 +1418,7 @@ static int ocfs2_rename(struct inode *old_dir,
 				mlog_errno(status);
 				goto bail;
 			}
+			should_add_orphan = true;
 		}
 	} else {
 		BUG_ON(new_dentry->d_parent->d_inode != new_dir);
@@ -1348,17 +1463,6 @@ static int ocfs2_rename(struct inode *old_dir,
 			goto bail;
 		}
 
-		if (S_ISDIR(new_inode->i_mode) ||
-		    (ocfs2_read_links_count(newfe) == 1)) {
-			status = ocfs2_orphan_add(osb, handle, new_inode,
-						  newfe_bh, orphan_name,
-						  &orphan_insert, orphan_dir);
-			if (status < 0) {
-				mlog_errno(status);
-				goto bail;
-			}
-		}
-
 		/* change the dirent to point to the correct inode */
 		status = ocfs2_update_entry(new_dir, handle, &target_lookup_res,
 					    old_inode);
@@ -1373,6 +1477,15 @@ static int ocfs2_rename(struct inode *old_dir,
 		else
 			ocfs2_add_links_count(newfe, -1);
 		ocfs2_journal_dirty(handle, newfe_bh);
+		if (should_add_orphan) {
+			status = ocfs2_orphan_add(osb, handle, new_inode,
+					newfe_bh, orphan_name,
+					&orphan_insert, orphan_dir);
+			if (status < 0) {
+				mlog_errno(status);
+				goto bail;
+			}
+		}
 	} else {
 		/* if the name was not found in new_dir, add it now */
 		status = ocfs2_add_entry(handle, new_dentry, old_inode,
@@ -1642,6 +1755,7 @@ static int ocfs2_symlink(struct inode *dir,
 	struct ocfs2_dir_lookup_result lookup = { NULL, };
 	sigset_t oldset;
 	int did_block_signals = 0;
+	struct ocfs2_dentry_lock *dl = NULL;
 
 	trace_ocfs2_symlink_begin(dir, dentry, symname,
 				  dentry->d_name.len, dentry->d_name.name);
@@ -1830,6 +1944,8 @@ static int ocfs2_symlink(struct inode *dir,
 		goto bail;
 	}
 
+	dl = dentry->d_fsdata;
+
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 le64_to_cpu(fe->i_blkno), parent_fe_bh,
 				 &lookup);
@@ -1864,6 +1980,9 @@ bail:
 	if (xattr_ac)
 		ocfs2_free_alloc_context(xattr_ac);
 	if ((status < 0) && inode) {
+		if (dl)
+			ocfs2_cleanup_add_entry_failure(osb, dentry, inode);
+
 		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
 		clear_nlink(inode);
 		iput(inode);
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 1b60c62aa9d..6cb019b7c6a 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -2292,6 +2292,8 @@ TRACE_EVENT(ocfs2_rename,
 		  __entry->new_len, __get_str(new_name))
 );
 
+DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_rename_not_permitted);
+
 TRACE_EVENT(ocfs2_rename_target_exists,
 	TP_PROTO(int new_len, const char *new_name),
 	TP_ARGS(new_len, new_name),
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 714e53b9cc6..636aab69ead 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4288,9 +4288,16 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 		goto out;
 	}
 
+	error = ocfs2_rw_lock(inode, 1);
+	if (error) {
+		mlog_errno(error);
+		goto out;
+	}
+
 	error = ocfs2_inode_lock(inode, &old_bh, 1);
 	if (error) {
 		mlog_errno(error);
+		ocfs2_rw_unlock(inode, 1);
 		goto out;
 	}
 
@@ -4302,6 +4309,7 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir,
 	up_write(&OCFS2_I(inode)->ip_xattr_sem);
 
 	ocfs2_inode_unlock(inode, 1);
+	ocfs2_rw_unlock(inode, 1);
 	brelse(old_bh);
 
 	if (error) {
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index c7a89cea5c5..ddb662b3244 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1925,15 +1925,11 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	ocfs2_shutdown_local_alloc(osb);
 
+	ocfs2_truncate_log_shutdown(osb);
+
 	/* This will disable recovery and flush any recovery work. */
 	ocfs2_recovery_exit(osb);
 
-	/*
-	 * During dismount, when it recovers another node it will call
-	 * ocfs2_recover_orphans and queue delayed work osb_truncate_log_wq.
-	 */
-	ocfs2_truncate_log_shutdown(osb);
-
 	ocfs2_journal_shutdown(osb);
 
 	ocfs2_sync_blockdev(sb);
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index 54d57d6ba68..902e88527fc 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -337,10 +337,10 @@ static sector_t omfs_bmap(struct address_space *mapping, sector_t block)
 
 const struct file_operations omfs_file_operations = {
 	.llseek = generic_file_llseek,
-	.read = do_sync_read,
-	.write = do_sync_write,
-	.aio_read = generic_file_aio_read,
-	.aio_write = generic_file_aio_write,
+	.read = new_sync_read,
+	.write = new_sync_write,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
 	.mmap = generic_file_mmap,
 	.fsync = generic_file_fsync,
 	.splice_read = generic_file_splice_read,
diff --git a/fs/open.c b/fs/open.c
index 9d64679cec7..d6fd3acde13 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -263,11 +263,10 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		return -EPERM;
 
 	/*
-	 * We can not allow to do any fallocate operation on an active
-	 * swapfile
+	 * We cannot allow any fallocate operation on an active swapfile
 	 */
 	if (IS_SWAPFILE(inode))
-		ret = -ETXTBSY;
+		return -ETXTBSY;
 
 	/*
 	 * Revalidate the write permissions, in case security policy has
@@ -725,6 +724,12 @@ static int do_dentry_open(struct file *f,
 	}
 	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(inode);
+	if ((f->f_mode & FMODE_READ) &&
+	     likely(f->f_op->read || f->f_op->aio_read || f->f_op->read_iter))
+		f->f_mode |= FMODE_CAN_READ;
+	if ((f->f_mode & FMODE_WRITE) &&
+	     likely(f->f_op->write || f->f_op->aio_write || f->f_op->write_iter))
+		f->f_mode |= FMODE_CAN_WRITE;
 
 	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
 
diff --git a/fs/pipe.c b/fs/pipe.c
index 034bffac3f9..21981e58e2a 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -116,50 +116,6 @@ void pipe_wait(struct pipe_inode_info *pipe)
 	pipe_lock(pipe);
 }
 
-static int
-pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len,
-			int atomic)
-{
-	unsigned long copy;
-
-	while (len > 0) {
-		while (!iov->iov_len)
-			iov++;
-		copy = min_t(unsigned long, len, iov->iov_len);
-
-		if (atomic) {
-			if (__copy_from_user_inatomic(to, iov->iov_base, copy))
-				return -EFAULT;
-		} else {
-			if (copy_from_user(to, iov->iov_base, copy))
-				return -EFAULT;
-		}
-		to += copy;
-		len -= copy;
-		iov->iov_base += copy;
-		iov->iov_len -= copy;
-	}
-	return 0;
-}
-
-/*
- * Pre-fault in the user memory, so we can use atomic copies.
- */
-static void iov_fault_in_pages_read(struct iovec *iov, unsigned long len)
-{
-	while (!iov->iov_len)
-		iov++;
-
-	while (len > 0) {
-		unsigned long this_len;
-
-		this_len = min_t(unsigned long, len, iov->iov_len);
-		fault_in_pages_readable(iov->iov_base, this_len);
-		len -= this_len;
-		iov++;
-	}
-}
-
 static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
 				  struct pipe_buffer *buf)
 {
@@ -271,24 +227,18 @@ static const struct pipe_buf_operations packet_pipe_buf_ops = {
 };
 
 static ssize_t
-pipe_read(struct kiocb *iocb, const struct iovec *_iov,
-	   unsigned long nr_segs, loff_t pos)
+pipe_read(struct kiocb *iocb, struct iov_iter *to)
 {
+	size_t total_len = iov_iter_count(to);
 	struct file *filp = iocb->ki_filp;
 	struct pipe_inode_info *pipe = filp->private_data;
 	int do_wakeup;
 	ssize_t ret;
-	struct iovec *iov = (struct iovec *)_iov;
-	size_t total_len;
-	struct iov_iter iter;
 
-	total_len = iov_length(iov, nr_segs);
 	/* Null read succeeds. */
 	if (unlikely(total_len == 0))
 		return 0;
 
-	iov_iter_init(&iter, iov, nr_segs, total_len, 0);
-
 	do_wakeup = 0;
 	ret = 0;
 	__pipe_lock(pipe);
@@ -312,7 +262,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov,
 				break;
 			}
 
-			written = copy_page_to_iter(buf->page, buf->offset, chars, &iter);
+			written = copy_page_to_iter(buf->page, buf->offset, chars, to);
 			if (unlikely(written < chars)) {
 				if (!ret)
 					ret = -EFAULT;
@@ -386,24 +336,19 @@ static inline int is_packetized(struct file *file)
 }
 
 static ssize_t
-pipe_write(struct kiocb *iocb, const struct iovec *_iov,
-	    unsigned long nr_segs, loff_t ppos)
+pipe_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *filp = iocb->ki_filp;
 	struct pipe_inode_info *pipe = filp->private_data;
-	ssize_t ret;
-	int do_wakeup;
-	struct iovec *iov = (struct iovec *)_iov;
-	size_t total_len;
+	ssize_t ret = 0;
+	int do_wakeup = 0;
+	size_t total_len = iov_iter_count(from);
 	ssize_t chars;
 
-	total_len = iov_length(iov, nr_segs);
 	/* Null write succeeds. */
 	if (unlikely(total_len == 0))
 		return 0;
 
-	do_wakeup = 0;
-	ret = 0;
 	__pipe_lock(pipe);
 
 	if (!pipe->readers) {
@@ -422,38 +367,19 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov,
 		int offset = buf->offset + buf->len;
 
 		if (ops->can_merge && offset + chars <= PAGE_SIZE) {
-			int error, atomic = 1;
-			void *addr;
-
-			error = ops->confirm(pipe, buf);
+			int error = ops->confirm(pipe, buf);
 			if (error)
 				goto out;
 
-			iov_fault_in_pages_read(iov, chars);
-redo1:
-			if (atomic)
-				addr = kmap_atomic(buf->page);
-			else
-				addr = kmap(buf->page);
-			error = pipe_iov_copy_from_user(offset + addr, iov,
-							chars, atomic);
-			if (atomic)
-				kunmap_atomic(addr);
-			else
-				kunmap(buf->page);
-			ret = error;
-			do_wakeup = 1;
-			if (error) {
-				if (atomic) {
-					atomic = 0;
-					goto redo1;
-				}
+			ret = copy_page_from_iter(buf->page, offset, chars, from);
+			if (unlikely(ret < chars)) {
+				error = -EFAULT;
 				goto out;
 			}
+			do_wakeup = 1;
 			buf->len += chars;
-			total_len -= chars;
 			ret = chars;
-			if (!total_len)
+			if (!iov_iter_count(from))
 				goto out;
 		}
 	}
@@ -472,8 +398,7 @@ redo1:
 			int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1);
 			struct pipe_buffer *buf = pipe->bufs + newbuf;
 			struct page *page = pipe->tmp_page;
-			char *src;
-			int error, atomic = 1;
+			int copied;
 
 			if (!page) {
 				page = alloc_page(GFP_HIGHUSER);
@@ -489,40 +414,19 @@ redo1:
 			 * FIXME! Is this really true?
 			 */
 			do_wakeup = 1;
-			chars = PAGE_SIZE;
-			if (chars > total_len)
-				chars = total_len;
-
-			iov_fault_in_pages_read(iov, chars);
-redo2:
-			if (atomic)
-				src = kmap_atomic(page);
-			else
-				src = kmap(page);
-
-			error = pipe_iov_copy_from_user(src, iov, chars,
-							atomic);
-			if (atomic)
-				kunmap_atomic(src);
-			else
-				kunmap(page);
-
-			if (unlikely(error)) {
-				if (atomic) {
-					atomic = 0;
-					goto redo2;
-				}
+			copied = copy_page_from_iter(page, 0, PAGE_SIZE, from);
+			if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) {
 				if (!ret)
-					ret = error;
+					ret = -EFAULT;
 				break;
 			}
-			ret += chars;
+			ret += copied;
 
 			/* Insert it into the buffer array */
 			buf->page = page;
 			buf->ops = &anon_pipe_buf_ops;
 			buf->offset = 0;
-			buf->len = chars;
+			buf->len = copied;
 			buf->flags = 0;
 			if (is_packetized(filp)) {
 				buf->ops = &packet_pipe_buf_ops;
@@ -531,8 +435,7 @@ redo2:
 			pipe->nrbufs = ++bufs;
 			pipe->tmp_page = NULL;
 
-			total_len -= chars;
-			if (!total_len)
+			if (!iov_iter_count(from))
 				break;
 		}
 		if (bufs < pipe->buffers)
@@ -1044,10 +947,10 @@ err:
 const struct file_operations pipefifo_fops = {
 	.open		= fifo_open,
 	.llseek		= no_llseek,
-	.read		= do_sync_read,
-	.aio_read	= pipe_read,
-	.write		= do_sync_write,
-	.aio_write	= pipe_write,
+	.read		= new_sync_read,
+	.read_iter	= pipe_read,
+	.write		= new_sync_write,
+	.write_iter	= pipe_write,
 	.poll		= pipe_poll,
 	.unlocked_ioctl	= pipe_ioctl,
 	.release	= pipe_release,
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 9d231e9e5f0..bf2d03f8fd3 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -184,29 +184,11 @@ static int show_stat(struct seq_file *p, void *v)
 
 static int stat_open(struct inode *inode, struct file *file)
 {
-	size_t size = 1024 + 128 * num_possible_cpus();
-	char *buf;
-	struct seq_file *m;
-	int res;
+	size_t size = 1024 + 128 * num_online_cpus();
 
 	/* minimum size to display an interrupt count : 2 bytes */
 	size += 2 * nr_irqs;
-
-	/* don't ask for more than the kmalloc() max size */
-	if (size > KMALLOC_MAX_SIZE)
-		size = KMALLOC_MAX_SIZE;
-	buf = kmalloc(size, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	res = single_open(file, show_stat, NULL);
-	if (!res) {
-		m = file->private_data;
-		m->buf = buf;
-		m->size = ksize(buf);
-	} else
-		kfree(buf);
-	return res;
+	return single_open_size(file, show_stat, NULL, size);
 }
 
 static const struct file_operations proc_stat_operations = {
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 9cd5f63715c..7f30bdc57d1 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -702,6 +702,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	struct dquot *dquot;
 	unsigned long freed = 0;
 
+	spin_lock(&dq_list_lock);
 	head = free_dquots.prev;
 	while (head != &free_dquots && sc->nr_to_scan) {
 		dquot = list_entry(head, struct dquot, dq_free);
@@ -713,6 +714,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 		freed++;
 		head = free_dquots.prev;
 	}
+	spin_unlock(&dq_list_lock);
 	return freed;
 }
 
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 2b363e23f36..ff3f0b3cfdb 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -278,6 +278,17 @@ static int quota_getxquota(struct super_block *sb, int type, qid_t id,
 	return ret;
 }
 
+static int quota_rmxquota(struct super_block *sb, void __user *addr)
+{
+	__u32 flags;
+
+	if (copy_from_user(&flags, addr, sizeof(flags)))
+		return -EFAULT;
+	if (!sb->s_qcop->rm_xquota)
+		return -ENOSYS;
+	return sb->s_qcop->rm_xquota(sb, flags);
+}
+
 /* Copy parameters and call proper function */
 static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		       void __user *addr, struct path *path)
@@ -316,8 +327,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
 		return sb->s_qcop->quota_sync(sb, type);
 	case Q_XQUOTAON:
 	case Q_XQUOTAOFF:
-	case Q_XQUOTARM:
 		return quota_setxstate(sb, cmd, addr);
+	case Q_XQUOTARM:
+		return quota_rmxquota(sb, addr);
 	case Q_XGETQSTAT:
 		return quota_getxstate(sb, addr);
 	case Q_XGETQSTATV:
diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c
index 1e56a4e8cf7..4f56de822d2 100644
--- a/fs/ramfs/file-mmu.c
+++ b/fs/ramfs/file-mmu.c
@@ -31,14 +31,14 @@
 #include "internal.h"
 
 const struct file_operations ramfs_file_operations = {
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= noop_fsync,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.llseek		= generic_file_llseek,
 };
 
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 0b3d8e4cb2f..dda012ad420 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -37,13 +37,13 @@ static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma);
 const struct file_operations ramfs_file_operations = {
 	.mmap			= ramfs_nommu_mmap,
 	.get_unmapped_area	= ramfs_nommu_get_unmapped_area,
-	.read			= do_sync_read,
-	.aio_read		= generic_file_aio_read,
-	.write			= do_sync_write,
-	.aio_write		= generic_file_aio_write,
+	.read			= new_sync_read,
+	.read_iter		= generic_file_read_iter,
+	.write			= new_sync_write,
+	.write_iter		= generic_file_write_iter,
 	.fsync			= noop_fsync,
 	.splice_read		= generic_file_splice_read,
-	.splice_write		= generic_file_splice_write,
+	.splice_write		= iter_file_splice_write,
 	.llseek			= generic_file_llseek,
 };
 
diff --git a/fs/read_write.c b/fs/read_write.c
index 31c6efa4318..009d8542a88 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -25,11 +25,12 @@
 typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
 typedef ssize_t (*iov_fn_t)(struct kiocb *, const struct iovec *,
 		unsigned long, loff_t);
+typedef ssize_t (*iter_fn_t)(struct kiocb *, struct iov_iter *);
 
 const struct file_operations generic_ro_fops = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
 	.mmap		= generic_file_readonly_mmap,
 	.splice_read	= generic_file_splice_read,
 };
@@ -390,13 +391,34 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp
 
 EXPORT_SYMBOL(do_sync_read);
 
+ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
+{
+	struct iovec iov = { .iov_base = buf, .iov_len = len };
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, filp);
+	kiocb.ki_pos = *ppos;
+	kiocb.ki_nbytes = len;
+	iov_iter_init(&iter, READ, &iov, 1, len);
+
+	ret = filp->f_op->read_iter(&kiocb, &iter);
+	if (-EIOCBQUEUED == ret)
+		ret = wait_on_sync_kiocb(&kiocb);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+
+EXPORT_SYMBOL(new_sync_read);
+
 ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
 {
 	ssize_t ret;
 
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
-	if (!file->f_op->read && !file->f_op->aio_read)
+	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
 	if (unlikely(!access_ok(VERIFY_WRITE, buf, count)))
 		return -EFAULT;
@@ -406,8 +428,10 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
 		count = ret;
 		if (file->f_op->read)
 			ret = file->f_op->read(file, buf, count, pos);
-		else
+		else if (file->f_op->aio_read)
 			ret = do_sync_read(file, buf, count, pos);
+		else
+			ret = new_sync_read(file, buf, count, pos);
 		if (ret > 0) {
 			fsnotify_access(file);
 			add_rchar(current, ret);
@@ -439,13 +463,34 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof
 
 EXPORT_SYMBOL(do_sync_write);
 
+ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
+{
+	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, filp);
+	kiocb.ki_pos = *ppos;
+	kiocb.ki_nbytes = len;
+	iov_iter_init(&iter, WRITE, &iov, 1, len);
+
+	ret = filp->f_op->write_iter(&kiocb, &iter);
+	if (-EIOCBQUEUED == ret)
+		ret = wait_on_sync_kiocb(&kiocb);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+
+EXPORT_SYMBOL(new_sync_write);
+
 ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos)
 {
 	mm_segment_t old_fs;
 	const char __user *p;
 	ssize_t ret;
 
-	if (!file->f_op->write && !file->f_op->aio_write)
+	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
 	old_fs = get_fs();
@@ -455,8 +500,10 @@ ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t
 		count =  MAX_RW_COUNT;
 	if (file->f_op->write)
 		ret = file->f_op->write(file, p, count, pos);
-	else
+	else if (file->f_op->aio_write)
 		ret = do_sync_write(file, p, count, pos);
+	else
+		ret = new_sync_write(file, p, count, pos);
 	set_fs(old_fs);
 	if (ret > 0) {
 		fsnotify_modify(file);
@@ -472,7 +519,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
 
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
-	if (!file->f_op->write && !file->f_op->aio_write)
+	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 	if (unlikely(!access_ok(VERIFY_READ, buf, count)))
 		return -EFAULT;
@@ -483,8 +530,10 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
 		file_start_write(file);
 		if (file->f_op->write)
 			ret = file->f_op->write(file, buf, count, pos);
-		else
+		else if (file->f_op->aio_write)
 			ret = do_sync_write(file, buf, count, pos);
+		else
+			ret = new_sync_write(file, buf, count, pos);
 		if (ret > 0) {
 			fsnotify_modify(file);
 			add_wchar(current, ret);
@@ -601,6 +650,25 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 }
 EXPORT_SYMBOL(iov_shorten);
 
+static ssize_t do_iter_readv_writev(struct file *filp, int rw, const struct iovec *iov,
+		unsigned long nr_segs, size_t len, loff_t *ppos, iter_fn_t fn)
+{
+	struct kiocb kiocb;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, filp);
+	kiocb.ki_pos = *ppos;
+	kiocb.ki_nbytes = len;
+
+	iov_iter_init(&iter, rw, iov, nr_segs, len);
+	ret = fn(&kiocb, &iter);
+	if (ret == -EIOCBQUEUED)
+		ret = wait_on_sync_kiocb(&kiocb);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+
 static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov,
 		unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn)
 {
@@ -738,6 +806,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	ssize_t ret;
 	io_fn_t fn;
 	iov_fn_t fnv;
+	iter_fn_t iter_fn;
 
 	ret = rw_copy_check_uvector(type, uvector, nr_segs,
 				    ARRAY_SIZE(iovstack), iovstack, &iov);
@@ -753,13 +822,18 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	if (type == READ) {
 		fn = file->f_op->read;
 		fnv = file->f_op->aio_read;
+		iter_fn = file->f_op->read_iter;
 	} else {
 		fn = (io_fn_t)file->f_op->write;
 		fnv = file->f_op->aio_write;
+		iter_fn = file->f_op->write_iter;
 		file_start_write(file);
 	}
 
-	if (fnv)
+	if (iter_fn)
+		ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len,
+						pos, iter_fn);
+	else if (fnv)
 		ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
 						pos, fnv);
 	else
@@ -785,7 +859,7 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
 {
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
-	if (!file->f_op->aio_read && !file->f_op->read)
+	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
 
 	return do_readv_writev(READ, file, vec, vlen, pos);
@@ -798,7 +872,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
 {
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
-	if (!file->f_op->aio_write && !file->f_op->write)
+	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
 	return do_readv_writev(WRITE, file, vec, vlen, pos);
@@ -912,6 +986,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	ssize_t ret;
 	io_fn_t fn;
 	iov_fn_t fnv;
+	iter_fn_t iter_fn;
 
 	ret = compat_rw_copy_check_uvector(type, uvector, nr_segs,
 					       UIO_FASTIOV, iovstack, &iov);
@@ -927,13 +1002,18 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	if (type == READ) {
 		fn = file->f_op->read;
 		fnv = file->f_op->aio_read;
+		iter_fn = file->f_op->read_iter;
 	} else {
 		fn = (io_fn_t)file->f_op->write;
 		fnv = file->f_op->aio_write;
+		iter_fn = file->f_op->write_iter;
 		file_start_write(file);
 	}
 
-	if (fnv)
+	if (iter_fn)
+		ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len,
+						pos, iter_fn);
+	else if (fnv)
 		ret = do_sync_readv_writev(file, iov, nr_segs, tot_len,
 						pos, fnv);
 	else
@@ -964,7 +1044,7 @@ static size_t compat_readv(struct file *file,
 		goto out;
 
 	ret = -EINVAL;
-	if (!file->f_op->aio_read && !file->f_op->read)
+	if (!(file->f_mode & FMODE_CAN_READ))
 		goto out;
 
 	ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
@@ -1041,7 +1121,7 @@ static size_t compat_writev(struct file *file,
 		goto out;
 
 	ret = -EINVAL;
-	if (!file->f_op->aio_write && !file->f_op->write)
+	if (!(file->f_mode & FMODE_CAN_WRITE))
 		goto out;
 
 	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c
index 1bcffeab713..dc198bc64c6 100644
--- a/fs/reiserfs/bitmap.c
+++ b/fs/reiserfs/bitmap.c
@@ -50,8 +50,10 @@ static inline void get_bit_address(struct super_block *s,
 				   unsigned int *bmap_nr,
 				   unsigned int *offset)
 {
-	/* It is in the bitmap block number equal to the block
-	 * number divided by the number of bits in a block. */
+	/*
+	 * It is in the bitmap block number equal to the block
+	 * number divided by the number of bits in a block.
+	 */
 	*bmap_nr = block >> (s->s_blocksize_bits + 3);
 	/* Within that bitmap block it is located at bit offset *offset. */
 	*offset = block & ((s->s_blocksize << 3) - 1);
@@ -71,10 +73,12 @@ int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value)
 
 	get_bit_address(s, block, &bmap, &offset);
 
-	/* Old format filesystem? Unlikely, but the bitmaps are all up front so
-	 * we need to account for it. */
+	/*
+	 * Old format filesystem? Unlikely, but the bitmaps are all
+	 * up front so we need to account for it.
+	 */
 	if (unlikely(test_bit(REISERFS_OLD_FORMAT,
-			      &(REISERFS_SB(s)->s_properties)))) {
+			      &REISERFS_SB(s)->s_properties))) {
 		b_blocknr_t bmap1 = REISERFS_SB(s)->s_sbh->b_blocknr + 1;
 		if (block >= bmap1 &&
 		    block <= bmap1 + bmap_count) {
@@ -108,8 +112,11 @@ int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value)
 	return 1;
 }
 
-/* searches in journal structures for a given block number (bmap, off). If block
-   is found in reiserfs journal it suggests next free block candidate to test. */
+/*
+ * Searches in journal structures for a given block number (bmap, off).
+ * If block is found in reiserfs journal it suggests next free block
+ * candidate to test.
+ */
 static inline int is_block_in_journal(struct super_block *s, unsigned int bmap,
 				      int off, int *next)
 {
@@ -120,7 +127,7 @@ static inline int is_block_in_journal(struct super_block *s, unsigned int bmap,
 			*next = tmp;
 			PROC_INFO_INC(s, scan_bitmap.in_journal_hint);
 		} else {
-			(*next) = off + 1;	/* inc offset to avoid looping. */
+			(*next) = off + 1;  /* inc offset to avoid looping. */
 			PROC_INFO_INC(s, scan_bitmap.in_journal_nohint);
 		}
 		PROC_INFO_INC(s, scan_bitmap.retry);
@@ -129,8 +136,10 @@ static inline int is_block_in_journal(struct super_block *s, unsigned int bmap,
 	return 0;
 }
 
-/* it searches for a window of zero bits with given minimum and maximum lengths in one bitmap
- * block; */
+/*
+ * Searches for a window of zero bits with given minimum and maximum
+ * lengths in one bitmap block
+ */
 static int scan_bitmap_block(struct reiserfs_transaction_handle *th,
 			     unsigned int bmap_n, int *beg, int boundary,
 			     int min, int max, int unfm)
@@ -145,10 +154,6 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th,
 	RFALSE(bmap_n >= reiserfs_bmap_count(s), "Bitmap %u is out of "
 	       "range (0..%u)", bmap_n, reiserfs_bmap_count(s) - 1);
 	PROC_INFO_INC(s, scan_bitmap.bmap);
-/* this is unclear and lacks comments, explain how journal bitmaps
-   work here for the reader.  Convey a sense of the design here. What
-   is a window? */
-/* - I mean `a window of zero bits' as in description of this function - Zam. */
 
 	if (!bi) {
 		reiserfs_error(s, "jdm-4055", "NULL bitmap info pointer "
@@ -161,18 +166,21 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th,
 		return 0;
 
 	while (1) {
-	      cont:
+cont:
 		if (bi->free_count < min) {
 			brelse(bh);
-			return 0;	// No free blocks in this bitmap
+			return 0;	/* No free blocks in this bitmap */
 		}
 
 		/* search for a first zero bit -- beginning of a window */
 		*beg = reiserfs_find_next_zero_le_bit
 		    ((unsigned long *)(bh->b_data), boundary, *beg);
 
-		if (*beg + min > boundary) {	/* search for a zero bit fails or the rest of bitmap block
-						 * cannot contain a zero window of minimum size */
+		/*
+		 * search for a zero bit fails or the rest of bitmap block
+		 * cannot contain a zero window of minimum size
+		 */
+		if (*beg + min > boundary) {
 			brelse(bh);
 			return 0;
 		}
@@ -186,49 +194,75 @@ static int scan_bitmap_block(struct reiserfs_transaction_handle *th,
 				next = end;
 				break;
 			}
-			/* finding the other end of zero bit window requires looking into journal structures (in
-			 * case of searching for free blocks for unformatted nodes) */
+
+			/*
+			 * finding the other end of zero bit window requires
+			 * looking into journal structures (in case of
+			 * searching for free blocks for unformatted nodes)
+			 */
 			if (unfm && is_block_in_journal(s, bmap_n, end, &next))
 				break;
 		}
 
-		/* now (*beg) points to beginning of zero bits window,
-		 * (end) points to one bit after the window end */
-		if (end - *beg >= min) {	/* it seems we have found window of proper size */
+		/*
+		 * now (*beg) points to beginning of zero bits window,
+		 * (end) points to one bit after the window end
+		 */
+
+		/* found window of proper size */
+		if (end - *beg >= min) {
 			int i;
 			reiserfs_prepare_for_journal(s, bh, 1);
-			/* try to set all blocks used checking are they still free */
+			/*
+			 * try to set all blocks used checking are
+			 * they still free
+			 */
 			for (i = *beg; i < end; i++) {
-				/* It seems that we should not check in journal again. */
+				/* Don't check in journal again. */
 				if (reiserfs_test_and_set_le_bit
 				    (i, bh->b_data)) {
-					/* bit was set by another process
-					 * while we slept in prepare_for_journal() */
+					/*
+					 * bit was set by another process while
+					 * we slept in prepare_for_journal()
+					 */
 					PROC_INFO_INC(s, scan_bitmap.stolen);
-					if (i >= *beg + min) {	/* we can continue with smaller set of allocated blocks,
-								 * if length of this set is more or equal to `min' */
+
+					/*
+					 * we can continue with smaller set
+					 * of allocated blocks, if length of
+					 * this set is more or equal to `min'
+					 */
+					if (i >= *beg + min) {
 						end = i;
 						break;
 					}
-					/* otherwise we clear all bit were set ... */
+
+					/*
+					 * otherwise we clear all bit
+					 * were set ...
+					 */
 					while (--i >= *beg)
 						reiserfs_clear_le_bit
 						    (i, bh->b_data);
 					reiserfs_restore_prepared_buffer(s, bh);
 					*beg = org;
-					/* ... and search again in current block from beginning */
+
+					/*
+					 * Search again in current block
+					 * from beginning
+					 */
 					goto cont;
 				}
 			}
 			bi->free_count -= (end - *beg);
-			journal_mark_dirty(th, s, bh);
+			journal_mark_dirty(th, bh);
 			brelse(bh);
 
 			/* free block count calculation */
 			reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s),
 						     1);
 			PUT_SB_FREE_BLOCKS(s, SB_FREE_BLOCKS(s) - (end - *beg));
-			journal_mark_dirty(th, s, SB_BUFFER_WITH_SB(s));
+			journal_mark_dirty(th, SB_BUFFER_WITH_SB(s));
 
 			return end - (*beg);
 		} else {
@@ -267,11 +301,13 @@ static inline int block_group_used(struct super_block *s, u32 id)
 	int bm = bmap_hash_id(s, id);
 	struct reiserfs_bitmap_info *info = &SB_AP_BITMAP(s)[bm];
 
-	/* If we don't have cached information on this bitmap block, we're
+	/*
+	 * If we don't have cached information on this bitmap block, we're
 	 * going to have to load it later anyway. Loading it here allows us
 	 * to make a better decision. This favors long-term performance gain
 	 * with a better on-disk layout vs. a short term gain of skipping the
-	 * read and potentially having a bad placement. */
+	 * read and potentially having a bad placement.
+	 */
 	if (info->free_count == UINT_MAX) {
 		struct buffer_head *bh = reiserfs_read_bitmap_block(s, bm);
 		brelse(bh);
@@ -304,25 +340,26 @@ __le32 reiserfs_choose_packing(struct inode * dir)
 	return packing;
 }
 
-/* Tries to find contiguous zero bit window (given size) in given region of
- * bitmap and place new blocks there. Returns number of allocated blocks. */
+/*
+ * Tries to find contiguous zero bit window (given size) in given region of
+ * bitmap and place new blocks there. Returns number of allocated blocks.
+ */
 static int scan_bitmap(struct reiserfs_transaction_handle *th,
 		       b_blocknr_t * start, b_blocknr_t finish,
 		       int min, int max, int unfm, sector_t file_block)
 {
 	int nr_allocated = 0;
 	struct super_block *s = th->t_super;
-	/* find every bm and bmap and bmap_nr in this file, and change them all to bitmap_blocknr
-	 * - Hans, it is not a block number - Zam. */
-
 	unsigned int bm, off;
 	unsigned int end_bm, end_off;
 	unsigned int off_max = s->s_blocksize << 3;
 
 	BUG_ON(!th->t_trans_id);
 	PROC_INFO_INC(s, scan_bitmap.call);
+
+	/* No point in looking for more free blocks */
 	if (SB_FREE_BLOCKS(s) <= 0)
-		return 0;	// No point in looking for more free blocks
+		return 0;
 
 	get_bit_address(s, *start, &bm, &off);
 	get_bit_address(s, finish, &end_bm, &end_off);
@@ -331,7 +368,8 @@ static int scan_bitmap(struct reiserfs_transaction_handle *th,
 	if (end_bm > reiserfs_bmap_count(s))
 		end_bm = reiserfs_bmap_count(s);
 
-	/* When the bitmap is more than 10% free, anyone can allocate.
+	/*
+	 * When the bitmap is more than 10% free, anyone can allocate.
 	 * When it's less than 10% free, only files that already use the
 	 * bitmap are allowed. Once we pass 80% full, this restriction
 	 * is lifted.
@@ -369,7 +407,7 @@ static int scan_bitmap(struct reiserfs_transaction_handle *th,
 	nr_allocated =
 	    scan_bitmap_block(th, bm, &off, end_off + 1, min, max, unfm);
 
-      ret:
+ret:
 	*start = bm * off_max + off;
 	return nr_allocated;
 
@@ -411,14 +449,14 @@ static void _reiserfs_free_block(struct reiserfs_transaction_handle *th,
 			       "block %lu: bit already cleared", block);
 	}
 	apbi[nr].free_count++;
-	journal_mark_dirty(th, s, bmbh);
+	journal_mark_dirty(th, bmbh);
 	brelse(bmbh);
 
 	reiserfs_prepare_for_journal(s, sbh, 1);
 	/* update super block */
 	set_sb_free_blocks(rs, sb_free_blocks(rs) + 1);
 
-	journal_mark_dirty(th, s, sbh);
+	journal_mark_dirty(th, sbh);
 	if (for_unformatted) {
 		int depth = reiserfs_write_unlock_nested(s);
 		dquot_free_block_nodirty(inode, 1);
@@ -483,7 +521,7 @@ static void __discard_prealloc(struct reiserfs_transaction_handle *th,
 	if (dirty)
 		reiserfs_update_sd(th, inode);
 	ei->i_prealloc_block = save;
-	list_del_init(&(ei->i_prealloc_list));
+	list_del_init(&ei->i_prealloc_list);
 }
 
 /* FIXME: It should be inline function */
@@ -529,7 +567,8 @@ int reiserfs_parse_alloc_options(struct super_block *s, char *options)
 {
 	char *this_char, *value;
 
-	REISERFS_SB(s)->s_alloc_options.bits = 0;	/* clear default settings */
+	/* clear default settings */
+	REISERFS_SB(s)->s_alloc_options.bits = 0;
 
 	while ((this_char = strsep(&options, ":")) != NULL) {
 		if ((value = strchr(this_char, '=')) != NULL)
@@ -731,7 +770,7 @@ static inline void new_hashed_relocation(reiserfs_blocknr_hint_t * hint)
 		hash_in = (char *)&hint->key.k_dir_id;
 	} else {
 		if (!hint->inode) {
-			//hint->search_start = hint->beg;
+			/*hint->search_start = hint->beg;*/
 			hash_in = (char *)&hint->key.k_dir_id;
 		} else
 		    if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super))
@@ -785,7 +824,8 @@ static void oid_groups(reiserfs_blocknr_hint_t * hint)
 
 		dirid = le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id);
 
-		/* keep the root dir and it's first set of subdirs close to
+		/*
+		 * keep the root dir and it's first set of subdirs close to
 		 * the start of the disk
 		 */
 		if (dirid <= 2)
@@ -799,7 +839,8 @@ static void oid_groups(reiserfs_blocknr_hint_t * hint)
 	}
 }
 
-/* returns 1 if it finds an indirect item and gets valid hint info
+/*
+ * returns 1 if it finds an indirect item and gets valid hint info
  * from it, otherwise 0
  */
 static int get_left_neighbor(reiserfs_blocknr_hint_t * hint)
@@ -811,25 +852,29 @@ static int get_left_neighbor(reiserfs_blocknr_hint_t * hint)
 	__le32 *item;
 	int ret = 0;
 
-	if (!hint->path)	/* reiserfs code can call this function w/o pointer to path
-				 * structure supplied; then we rely on supplied search_start */
+	/*
+	 * reiserfs code can call this function w/o pointer to path
+	 * structure supplied; then we rely on supplied search_start
+	 */
+	if (!hint->path)
 		return 0;
 
 	path = hint->path;
 	bh = get_last_bh(path);
 	RFALSE(!bh, "green-4002: Illegal path specified to get_left_neighbor");
-	ih = get_ih(path);
+	ih = tp_item_head(path);
 	pos_in_item = path->pos_in_item;
-	item = get_item(path);
+	item = tp_item_body(path);
 
 	hint->search_start = bh->b_blocknr;
 
+	/*
+	 * for indirect item: go to left and look for the first non-hole entry
+	 * in the indirect item
+	 */
 	if (!hint->formatted_node && is_indirect_le_ih(ih)) {
-		/* for indirect item: go to left and look for the first non-hole entry
-		   in the indirect item */
 		if (pos_in_item == I_UNFM_NUM(ih))
 			pos_in_item--;
-//          pos_in_item = I_UNFM_NUM (ih) - 1;
 		while (pos_in_item >= 0) {
 			int t = get_block_num(item, pos_in_item);
 			if (t) {
@@ -845,10 +890,12 @@ static int get_left_neighbor(reiserfs_blocknr_hint_t * hint)
 	return ret;
 }
 
-/* should be, if formatted node, then try to put on first part of the device
-   specified as number of percent with mount option device, else try to put
-   on last of device.  This is not to say it is good code to do so,
-   but the effect should be measured.  */
+/*
+ * should be, if formatted node, then try to put on first part of the device
+ * specified as number of percent with mount option device, else try to put
+ * on last of device.  This is not to say it is good code to do so,
+ * but the effect should be measured.
+ */
 static inline void set_border_in_hint(struct super_block *s,
 				      reiserfs_blocknr_hint_t * hint)
 {
@@ -974,21 +1021,27 @@ static void determine_search_start(reiserfs_blocknr_hint_t * hint,
 		set_border_in_hint(s, hint);
 
 #ifdef DISPLACE_NEW_PACKING_LOCALITIES
-	/* whenever we create a new directory, we displace it.  At first we will
-	   hash for location, later we might look for a moderately empty place for
-	   it */
+	/*
+	 * whenever we create a new directory, we displace it.  At first
+	 * we will hash for location, later we might look for a moderately
+	 * empty place for it
+	 */
 	if (displacing_new_packing_localities(s)
 	    && hint->th->displace_new_blocks) {
 		displace_new_packing_locality(hint);
 
-		/* we do not continue determine_search_start,
-		 * if new packing locality is being displaced */
+		/*
+		 * we do not continue determine_search_start,
+		 * if new packing locality is being displaced
+		 */
 		return;
 	}
 #endif
 
-	/* all persons should feel encouraged to add more special cases here and
-	 * test them */
+	/*
+	 * all persons should feel encouraged to add more special cases
+	 * here and test them
+	 */
 
 	if (displacing_large_files(s) && !hint->formatted_node
 	    && this_blocknr_allocation_would_make_it_a_large_file(hint)) {
@@ -996,8 +1049,10 @@ static void determine_search_start(reiserfs_blocknr_hint_t * hint,
 		return;
 	}
 
-	/* if none of our special cases is relevant, use the left neighbor in the
-	   tree order of the new node we are allocating for */
+	/*
+	 * if none of our special cases is relevant, use the left
+	 * neighbor in the tree order of the new node we are allocating for
+	 */
 	if (hint->formatted_node && TEST_OPTION(hashed_formatted_nodes, s)) {
 		hash_formatted_node(hint);
 		return;
@@ -1005,10 +1060,13 @@ static void determine_search_start(reiserfs_blocknr_hint_t * hint,
 
 	unfm_hint = get_left_neighbor(hint);
 
-	/* Mimic old block allocator behaviour, that is if VFS allowed for preallocation,
-	   new blocks are displaced based on directory ID. Also, if suggested search_start
-	   is less than last preallocated block, we start searching from it, assuming that
-	   HDD dataflow is faster in forward direction */
+	/*
+	 * Mimic old block allocator behaviour, that is if VFS allowed for
+	 * preallocation, new blocks are displaced based on directory ID.
+	 * Also, if suggested search_start is less than last preallocated
+	 * block, we start searching from it, assuming that HDD dataflow
+	 * is faster in forward direction
+	 */
 	if (TEST_OPTION(old_way, s)) {
 		if (!hint->formatted_node) {
 			if (!reiserfs_hashed_relocation(s))
@@ -1037,11 +1095,13 @@ static void determine_search_start(reiserfs_blocknr_hint_t * hint,
 	    TEST_OPTION(old_hashed_relocation, s)) {
 		old_hashed_relocation(hint);
 	}
+
 	/* new_hashed_relocation works with both formatted/unformatted nodes */
 	if ((!unfm_hint || hint->formatted_node) &&
 	    TEST_OPTION(new_hashed_relocation, s)) {
 		new_hashed_relocation(hint);
 	}
+
 	/* dirid grouping works only on unformatted nodes */
 	if (!unfm_hint && !hint->formatted_node && TEST_OPTION(dirid_groups, s)) {
 		dirid_groups(hint);
@@ -1079,8 +1139,6 @@ static int determine_prealloc_size(reiserfs_blocknr_hint_t * hint)
 	return CARRY_ON;
 }
 
-/* XXX I know it could be merged with upper-level function;
-   but may be result function would be too complex. */
 static inline int allocate_without_wrapping_disk(reiserfs_blocknr_hint_t * hint,
 						 b_blocknr_t * new_blocknrs,
 						 b_blocknr_t start,
@@ -1108,7 +1166,10 @@ static inline int allocate_without_wrapping_disk(reiserfs_blocknr_hint_t * hint,
 
 		/* do we have something to fill prealloc. array also ? */
 		if (nr_allocated > 0) {
-			/* it means prealloc_size was greater that 0 and we do preallocation */
+			/*
+			 * it means prealloc_size was greater that 0 and
+			 * we do preallocation
+			 */
 			list_add(&REISERFS_I(hint->inode)->i_prealloc_list,
 				 &SB_JOURNAL(hint->th->t_super)->
 				 j_prealloc_list);
@@ -1176,7 +1237,8 @@ static inline int blocknrs_and_prealloc_arrays_from_search_start
 			start = 0;
 			finish = hint->beg;
 			break;
-		default:	/* We've tried searching everywhere, not enough space */
+		default:
+			/* We've tried searching everywhere, not enough space */
 			/* Free the blocks */
 			if (!hint->formatted_node) {
 #ifdef REISERQUOTA_DEBUG
@@ -1261,8 +1323,11 @@ static int use_preallocated_list_if_available(reiserfs_blocknr_hint_t * hint,
 	return amount_needed;
 }
 
-int reiserfs_allocate_blocknrs(reiserfs_blocknr_hint_t * hint, b_blocknr_t * new_blocknrs, int amount_needed, int reserved_by_us	/* Amount of blocks we have
-																	   already reserved */ )
+int reiserfs_allocate_blocknrs(reiserfs_blocknr_hint_t *hint,
+			       b_blocknr_t *new_blocknrs,
+			       int amount_needed,
+			       /* Amount of blocks we have already reserved */
+			       int reserved_by_us)
 {
 	int initial_amount_needed = amount_needed;
 	int ret;
@@ -1274,15 +1339,21 @@ int reiserfs_allocate_blocknrs(reiserfs_blocknr_hint_t * hint, b_blocknr_t * new
 		return NO_DISK_SPACE;
 	/* should this be if !hint->inode &&  hint->preallocate? */
 	/* do you mean hint->formatted_node can be removed ? - Zam */
-	/* hint->formatted_node cannot be removed because we try to access
-	   inode information here, and there is often no inode assotiated with
-	   metadata allocations - green */
+	/*
+	 * hint->formatted_node cannot be removed because we try to access
+	 * inode information here, and there is often no inode associated with
+	 * metadata allocations - green
+	 */
 
 	if (!hint->formatted_node && hint->preallocate) {
 		amount_needed = use_preallocated_list_if_available
 		    (hint, new_blocknrs, amount_needed);
-		if (amount_needed == 0)	/* all blocknrs we need we got from
-					   prealloc. list */
+
+		/*
+		 * We have all the block numbers we need from the
+		 * prealloc list
+		 */
+		if (amount_needed == 0)
 			return CARRY_ON;
 		new_blocknrs += (initial_amount_needed - amount_needed);
 	}
@@ -1296,10 +1367,12 @@ int reiserfs_allocate_blocknrs(reiserfs_blocknr_hint_t * hint, b_blocknr_t * new
 	ret = blocknrs_and_prealloc_arrays_from_search_start
 	    (hint, new_blocknrs, amount_needed);
 
-	/* we used prealloc. list to fill (partially) new_blocknrs array. If final allocation fails we
-	 * need to return blocks back to prealloc. list or just free them. -- Zam (I chose second
-	 * variant) */
-
+	/*
+	 * We used prealloc. list to fill (partially) new_blocknrs array.
+	 * If final allocation fails we need to return blocks back to
+	 * prealloc. list or just free them. -- Zam (I chose second
+	 * variant)
+	 */
 	if (ret != CARRY_ON) {
 		while (amount_needed++ < initial_amount_needed) {
 			reiserfs_free_block(hint->th, hint->inode,
@@ -1338,10 +1411,12 @@ struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb,
 	struct reiserfs_bitmap_info *info = SB_AP_BITMAP(sb) + bitmap;
 	struct buffer_head *bh;
 
-	/* Way old format filesystems had the bitmaps packed up front.
-	 * I doubt there are any of these left, but just in case... */
+	/*
+	 * Way old format filesystems had the bitmaps packed up front.
+	 * I doubt there are any of these left, but just in case...
+	 */
 	if (unlikely(test_bit(REISERFS_OLD_FORMAT,
-	                      &(REISERFS_SB(sb)->s_properties))))
+			      &REISERFS_SB(sb)->s_properties)))
 		block = REISERFS_SB(sb)->s_sbh->b_blocknr + 1 + bitmap;
 	else if (bitmap == 0)
 		block = (REISERFS_DISK_OFFSET_IN_BYTES >> sb->s_blocksize_bits) + 1;
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index af677353a3f..d9f5a60dd59 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -59,7 +59,10 @@ static inline bool is_privroot_deh(struct inode *dir, struct reiserfs_de_head *d
 
 int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 {
-	struct cpu_key pos_key;	/* key of current position in the directory (key of directory entry) */
+
+	/* key of current position in the directory (key of directory entry) */
+	struct cpu_key pos_key;
+
 	INITIALIZE_PATH(path_to_entry);
 	struct buffer_head *bh;
 	int item_num, entry_num;
@@ -77,21 +80,28 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 
 	reiserfs_check_lock_depth(inode->i_sb, "readdir");
 
-	/* form key for search the next directory entry using f_pos field of
-	   file structure */
+	/*
+	 * form key for search the next directory entry using
+	 * f_pos field of file structure
+	 */
 	make_cpu_key(&pos_key, inode, ctx->pos ?: DOT_OFFSET, TYPE_DIRENTRY, 3);
 	next_pos = cpu_key_k_offset(&pos_key);
 
 	path_to_entry.reada = PATH_READA;
 	while (1) {
-	      research:
-		/* search the directory item, containing entry with specified key */
+research:
+		/*
+		 * search the directory item, containing entry with
+		 * specified key
+		 */
 		search_res =
 		    search_by_entry_key(inode->i_sb, &pos_key, &path_to_entry,
 					&de);
 		if (search_res == IO_ERROR) {
-			// FIXME: we could just skip part of directory which could
-			// not be read
+			/*
+			 * FIXME: we could just skip part of directory
+			 * which could not be read
+			 */
 			ret = -EIO;
 			goto out;
 		}
@@ -102,41 +112,49 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 		store_ih(&tmp_ih, ih);
 
 		/* we must have found item, that is item of this directory, */
-		RFALSE(COMP_SHORT_KEYS(&(ih->ih_key), &pos_key),
+		RFALSE(COMP_SHORT_KEYS(&ih->ih_key, &pos_key),
 		       "vs-9000: found item %h does not match to dir we readdir %K",
 		       ih, &pos_key);
 		RFALSE(item_num > B_NR_ITEMS(bh) - 1,
 		       "vs-9005 item_num == %d, item amount == %d",
 		       item_num, B_NR_ITEMS(bh));
 
-		/* and entry must be not more than number of entries in the item */
-		RFALSE(I_ENTRY_COUNT(ih) < entry_num,
+		/*
+		 * and entry must be not more than number of entries
+		 * in the item
+		 */
+		RFALSE(ih_entry_count(ih) < entry_num,
 		       "vs-9010: entry number is too big %d (%d)",
-		       entry_num, I_ENTRY_COUNT(ih));
+		       entry_num, ih_entry_count(ih));
 
+		/*
+		 * go through all entries in the directory item beginning
+		 * from the entry, that has been found
+		 */
 		if (search_res == POSITION_FOUND
-		    || entry_num < I_ENTRY_COUNT(ih)) {
-			/* go through all entries in the directory item beginning from the entry, that has been found */
+		    || entry_num < ih_entry_count(ih)) {
 			struct reiserfs_de_head *deh =
 			    B_I_DEH(bh, ih) + entry_num;
 
-			for (; entry_num < I_ENTRY_COUNT(ih);
+			for (; entry_num < ih_entry_count(ih);
 			     entry_num++, deh++) {
 				int d_reclen;
 				char *d_name;
 				ino_t d_ino;
 				loff_t cur_pos = deh_offset(deh);
 
+				/* it is hidden entry */
 				if (!de_visible(deh))
-					/* it is hidden entry */
 					continue;
 				d_reclen = entry_length(bh, ih, entry_num);
 				d_name = B_I_DEH_ENTRY_FILE_NAME(bh, ih, deh);
 
 				if (d_reclen <= 0 ||
 				    d_name + d_reclen > bh->b_data + bh->b_size) {
-					/* There is corrupted data in entry,
-					 * We'd better stop here */
+					/*
+					 * There is corrupted data in entry,
+					 * We'd better stop here
+					 */
 					pathrelse(&path_to_entry);
 					ret = -EIO;
 					goto out;
@@ -145,10 +163,10 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 				if (!d_name[d_reclen - 1])
 					d_reclen = strlen(d_name);
 
+				/* too big to send back to VFS */
 				if (d_reclen >
 				    REISERFS_MAX_NAME(inode->i_sb->
 						      s_blocksize)) {
-					/* too big to send back to VFS */
 					continue;
 				}
 
@@ -173,10 +191,14 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 						goto research;
 					}
 				}
-				// Note, that we copy name to user space via temporary
-				// buffer (local_buf) because filldir will block if
-				// user space buffer is swapped out. At that time
-				// entry can move to somewhere else
+
+				/*
+				 * Note, that we copy name to user space via
+				 * temporary buffer (local_buf) because
+				 * filldir will block if user space buffer is
+				 * swapped out. At that time entry can move to
+				 * somewhere else
+				 */
 				memcpy(local_buf, d_name, d_reclen);
 
 				/*
@@ -209,22 +231,26 @@ int reiserfs_readdir_inode(struct inode *inode, struct dir_context *ctx)
 			}	/* for */
 		}
 
+		/* end of directory has been reached */
 		if (item_num != B_NR_ITEMS(bh) - 1)
-			// end of directory has been reached
 			goto end;
 
-		/* item we went through is last item of node. Using right
-		   delimiting key check is it directory end */
+		/*
+		 * item we went through is last item of node. Using right
+		 * delimiting key check is it directory end
+		 */
 		rkey = get_rkey(&path_to_entry, inode->i_sb);
 		if (!comp_le_keys(rkey, &MIN_KEY)) {
-			/* set pos_key to key, that is the smallest and greater
-			   that key of the last entry in the item */
+			/*
+			 * set pos_key to key, that is the smallest and greater
+			 * that key of the last entry in the item
+			 */
 			set_cpu_key_k_offset(&pos_key, next_pos);
 			continue;
 		}
 
+		/* end of directory has been reached */
 		if (COMP_SHORT_KEYS(rkey, &pos_key)) {
-			// end of directory has been reached
 			goto end;
 		}
 
@@ -248,71 +274,73 @@ static int reiserfs_readdir(struct file *file, struct dir_context *ctx)
 	return reiserfs_readdir_inode(file_inode(file), ctx);
 }
 
-/* compose directory item containing "." and ".." entries (entries are
-   not aligned to 4 byte boundary) */
-/* the last four params are LE */
+/*
+ * compose directory item containing "." and ".." entries (entries are
+ * not aligned to 4 byte boundary)
+ */
 void make_empty_dir_item_v1(char *body, __le32 dirid, __le32 objid,
 			    __le32 par_dirid, __le32 par_objid)
 {
-	struct reiserfs_de_head *deh;
+	struct reiserfs_de_head *dot, *dotdot;
 
 	memset(body, 0, EMPTY_DIR_SIZE_V1);
-	deh = (struct reiserfs_de_head *)body;
+	dot = (struct reiserfs_de_head *)body;
+	dotdot = dot + 1;
 
 	/* direntry header of "." */
-	put_deh_offset(&(deh[0]), DOT_OFFSET);
+	put_deh_offset(dot, DOT_OFFSET);
 	/* these two are from make_le_item_head, and are are LE */
-	deh[0].deh_dir_id = dirid;
-	deh[0].deh_objectid = objid;
-	deh[0].deh_state = 0;	/* Endian safe if 0 */
-	put_deh_location(&(deh[0]), EMPTY_DIR_SIZE_V1 - strlen("."));
-	mark_de_visible(&(deh[0]));
+	dot->deh_dir_id = dirid;
+	dot->deh_objectid = objid;
+	dot->deh_state = 0;	/* Endian safe if 0 */
+	put_deh_location(dot, EMPTY_DIR_SIZE_V1 - strlen("."));
+	mark_de_visible(dot);
 
 	/* direntry header of ".." */
-	put_deh_offset(&(deh[1]), DOT_DOT_OFFSET);
+	put_deh_offset(dotdot, DOT_DOT_OFFSET);
 	/* key of ".." for the root directory */
 	/* these two are from the inode, and are are LE */
-	deh[1].deh_dir_id = par_dirid;
-	deh[1].deh_objectid = par_objid;
-	deh[1].deh_state = 0;	/* Endian safe if 0 */
-	put_deh_location(&(deh[1]), deh_location(&(deh[0])) - strlen(".."));
-	mark_de_visible(&(deh[1]));
+	dotdot->deh_dir_id = par_dirid;
+	dotdot->deh_objectid = par_objid;
+	dotdot->deh_state = 0;	/* Endian safe if 0 */
+	put_deh_location(dotdot, deh_location(dot) - strlen(".."));
+	mark_de_visible(dotdot);
 
 	/* copy ".." and "." */
-	memcpy(body + deh_location(&(deh[0])), ".", 1);
-	memcpy(body + deh_location(&(deh[1])), "..", 2);
+	memcpy(body + deh_location(dot), ".", 1);
+	memcpy(body + deh_location(dotdot), "..", 2);
 }
 
 /* compose directory item containing "." and ".." entries */
 void make_empty_dir_item(char *body, __le32 dirid, __le32 objid,
 			 __le32 par_dirid, __le32 par_objid)
 {
-	struct reiserfs_de_head *deh;
+	struct reiserfs_de_head *dot, *dotdot;
 
 	memset(body, 0, EMPTY_DIR_SIZE);
-	deh = (struct reiserfs_de_head *)body;
+	dot = (struct reiserfs_de_head *)body;
+	dotdot = dot + 1;
 
 	/* direntry header of "." */
-	put_deh_offset(&(deh[0]), DOT_OFFSET);
+	put_deh_offset(dot, DOT_OFFSET);
 	/* these two are from make_le_item_head, and are are LE */
-	deh[0].deh_dir_id = dirid;
-	deh[0].deh_objectid = objid;
-	deh[0].deh_state = 0;	/* Endian safe if 0 */
-	put_deh_location(&(deh[0]), EMPTY_DIR_SIZE - ROUND_UP(strlen(".")));
-	mark_de_visible(&(deh[0]));
+	dot->deh_dir_id = dirid;
+	dot->deh_objectid = objid;
+	dot->deh_state = 0;	/* Endian safe if 0 */
+	put_deh_location(dot, EMPTY_DIR_SIZE - ROUND_UP(strlen(".")));
+	mark_de_visible(dot);
 
 	/* direntry header of ".." */
-	put_deh_offset(&(deh[1]), DOT_DOT_OFFSET);
+	put_deh_offset(dotdot, DOT_DOT_OFFSET);
 	/* key of ".." for the root directory */
 	/* these two are from the inode, and are are LE */
-	deh[1].deh_dir_id = par_dirid;
-	deh[1].deh_objectid = par_objid;
-	deh[1].deh_state = 0;	/* Endian safe if 0 */
-	put_deh_location(&(deh[1]),
-			 deh_location(&(deh[0])) - ROUND_UP(strlen("..")));
-	mark_de_visible(&(deh[1]));
+	dotdot->deh_dir_id = par_dirid;
+	dotdot->deh_objectid = par_objid;
+	dotdot->deh_state = 0;	/* Endian safe if 0 */
+	put_deh_location(dotdot, deh_location(dot) - ROUND_UP(strlen("..")));
+	mark_de_visible(dotdot);
 
 	/* copy ".." and "." */
-	memcpy(body + deh_location(&(deh[0])), ".", 1);
-	memcpy(body + deh_location(&(deh[1])), "..", 2);
+	memcpy(body + deh_location(dot), ".", 1);
+	memcpy(body + deh_location(dotdot), "..", 2);
 }
diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c
index 9a3c68cf602..54fdf196bfb 100644
--- a/fs/reiserfs/do_balan.c
+++ b/fs/reiserfs/do_balan.c
@@ -2,18 +2,13 @@
  * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
  */
 
-/* Now we have all buffers that must be used in balancing of the tree 	*/
-/* Further calculations can not cause schedule(), and thus the buffer 	*/
-/* tree will be stable until the balancing will be finished 		*/
-/* balance the tree according to the analysis made before,		*/
-/* and using buffers obtained after all above.				*/
-
-/**
- ** balance_leaf_when_delete
- ** balance_leaf
- ** do_balance
- **
- **/
+/*
+ * Now we have all buffers that must be used in balancing of the tree
+ * Further calculations can not cause schedule(), and thus the buffer
+ * tree will be stable until the balancing will be finished
+ * balance the tree according to the analysis made before,
+ * and using buffers obtained after all above.
+ */
 
 #include <asm/uaccess.h>
 #include <linux/time.h>
@@ -61,48 +56,190 @@ static inline void buffer_info_init_bh(struct tree_balance *tb,
 inline void do_balance_mark_leaf_dirty(struct tree_balance *tb,
 				       struct buffer_head *bh, int flag)
 {
-	journal_mark_dirty(tb->transaction_handle,
-			   tb->transaction_handle->t_super, bh);
+	journal_mark_dirty(tb->transaction_handle, bh);
 }
 
 #define do_balance_mark_internal_dirty do_balance_mark_leaf_dirty
 #define do_balance_mark_sb_dirty do_balance_mark_leaf_dirty
 
-/* summary:
- if deleting something ( tb->insert_size[0] < 0 )
-   return(balance_leaf_when_delete()); (flag d handled here)
- else
-   if lnum is larger than 0 we put items into the left node
-   if rnum is larger than 0 we put items into the right node
-   if snum1 is larger than 0 we put items into the new node s1
-   if snum2 is larger than 0 we put items into the new node s2
-Note that all *num* count new items being created.
-
-It would be easier to read balance_leaf() if each of these summary
-lines was a separate procedure rather than being inlined.  I think
-that there are many passages here and in balance_leaf_when_delete() in
-which two calls to one procedure can replace two passages, and it
-might save cache space and improve software maintenance costs to do so.
-
-Vladimir made the perceptive comment that we should offload most of
-the decision making in this function into fix_nodes/check_balance, and
-then create some sort of structure in tb that says what actions should
-be performed by do_balance.
-
--Hans */
-
-/* Balance leaf node in case of delete or cut: insert_size[0] < 0
+/*
+ * summary:
+ *  if deleting something ( tb->insert_size[0] < 0 )
+ *    return(balance_leaf_when_delete()); (flag d handled here)
+ *  else
+ *    if lnum is larger than 0 we put items into the left node
+ *    if rnum is larger than 0 we put items into the right node
+ *    if snum1 is larger than 0 we put items into the new node s1
+ *    if snum2 is larger than 0 we put items into the new node s2
+ * Note that all *num* count new items being created.
+ */
+
+static void balance_leaf_when_delete_del(struct tree_balance *tb)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int item_pos = PATH_LAST_POSITION(tb->tb_path);
+	struct buffer_info bi;
+#ifdef CONFIG_REISERFS_CHECK
+	struct item_head *ih = item_head(tbS0, item_pos);
+#endif
+
+	RFALSE(ih_item_len(ih) + IH_SIZE != -tb->insert_size[0],
+	       "vs-12013: mode Delete, insert size %d, ih to be deleted %h",
+	       -tb->insert_size[0], ih);
+
+	buffer_info_init_tbS0(tb, &bi);
+	leaf_delete_items(&bi, 0, item_pos, 1, -1);
+
+	if (!item_pos && tb->CFL[0]) {
+		if (B_NR_ITEMS(tbS0)) {
+			replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
+		} else {
+			if (!PATH_H_POSITION(tb->tb_path, 1))
+				replace_key(tb, tb->CFL[0], tb->lkey[0],
+					    PATH_H_PPARENT(tb->tb_path, 0), 0);
+		}
+	}
+
+	RFALSE(!item_pos && !tb->CFL[0],
+	       "PAP-12020: tb->CFL[0]==%p, tb->L[0]==%p", tb->CFL[0],
+	       tb->L[0]);
+}
+
+/* cut item in S[0] */
+static void balance_leaf_when_delete_cut(struct tree_balance *tb)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int item_pos = PATH_LAST_POSITION(tb->tb_path);
+	struct item_head *ih = item_head(tbS0, item_pos);
+	int pos_in_item = tb->tb_path->pos_in_item;
+	struct buffer_info bi;
+	buffer_info_init_tbS0(tb, &bi);
+
+	if (is_direntry_le_ih(ih)) {
+		/*
+		 * UFS unlink semantics are such that you can only
+		 * delete one directory entry at a time.
+		 *
+		 * when we cut a directory tb->insert_size[0] means
+		 * number of entries to be cut (always 1)
+		 */
+		tb->insert_size[0] = -1;
+		leaf_cut_from_buffer(&bi, item_pos, pos_in_item,
+				     -tb->insert_size[0]);
+
+		RFALSE(!item_pos && !pos_in_item && !tb->CFL[0],
+		       "PAP-12030: can not change delimiting key. CFL[0]=%p",
+		       tb->CFL[0]);
+
+		if (!item_pos && !pos_in_item && tb->CFL[0])
+			replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
+	} else {
+		leaf_cut_from_buffer(&bi, item_pos, pos_in_item,
+				     -tb->insert_size[0]);
+
+		RFALSE(!ih_item_len(ih),
+		       "PAP-12035: cut must leave non-zero dynamic "
+		       "length of item");
+	}
+}
+
+static int balance_leaf_when_delete_left(struct tree_balance *tb)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int n = B_NR_ITEMS(tbS0);
+
+	/* L[0] must be joined with S[0] */
+	if (tb->lnum[0] == -1) {
+		/* R[0] must be also joined with S[0] */
+		if (tb->rnum[0] == -1) {
+			if (tb->FR[0] == PATH_H_PPARENT(tb->tb_path, 0)) {
+				/*
+				 * all contents of all the
+				 * 3 buffers will be in L[0]
+				 */
+				if (PATH_H_POSITION(tb->tb_path, 1) == 0 &&
+				    1 < B_NR_ITEMS(tb->FR[0]))
+					replace_key(tb, tb->CFL[0],
+						    tb->lkey[0], tb->FR[0], 1);
+
+				leaf_move_items(LEAF_FROM_S_TO_L, tb, n, -1,
+						NULL);
+				leaf_move_items(LEAF_FROM_R_TO_L, tb,
+						B_NR_ITEMS(tb->R[0]), -1,
+						NULL);
+
+				reiserfs_invalidate_buffer(tb, tbS0);
+				reiserfs_invalidate_buffer(tb, tb->R[0]);
+
+				return 0;
+			}
+
+			/* all contents of all the 3 buffers will be in R[0] */
+			leaf_move_items(LEAF_FROM_S_TO_R, tb, n, -1, NULL);
+			leaf_move_items(LEAF_FROM_L_TO_R, tb,
+					B_NR_ITEMS(tb->L[0]), -1, NULL);
+
+			/* right_delimiting_key is correct in R[0] */
+			replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0);
+
+			reiserfs_invalidate_buffer(tb, tbS0);
+			reiserfs_invalidate_buffer(tb, tb->L[0]);
+
+			return -1;
+		}
+
+		RFALSE(tb->rnum[0] != 0,
+		       "PAP-12045: rnum must be 0 (%d)", tb->rnum[0]);
+		/* all contents of L[0] and S[0] will be in L[0] */
+		leaf_shift_left(tb, n, -1);
+
+		reiserfs_invalidate_buffer(tb, tbS0);
+
+		return 0;
+	}
+
+	/*
+	 * a part of contents of S[0] will be in L[0] and
+	 * the rest part of S[0] will be in R[0]
+	 */
+
+	RFALSE((tb->lnum[0] + tb->rnum[0] < n) ||
+	       (tb->lnum[0] + tb->rnum[0] > n + 1),
+	       "PAP-12050: rnum(%d) and lnum(%d) and item "
+	       "number(%d) in S[0] are not consistent",
+	       tb->rnum[0], tb->lnum[0], n);
+	RFALSE((tb->lnum[0] + tb->rnum[0] == n) &&
+	       (tb->lbytes != -1 || tb->rbytes != -1),
+	       "PAP-12055: bad rbytes (%d)/lbytes (%d) "
+	       "parameters when items are not split",
+	       tb->rbytes, tb->lbytes);
+	RFALSE((tb->lnum[0] + tb->rnum[0] == n + 1) &&
+	       (tb->lbytes < 1 || tb->rbytes != -1),
+	       "PAP-12060: bad rbytes (%d)/lbytes (%d) "
+	       "parameters when items are split",
+	       tb->rbytes, tb->lbytes);
+
+	leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
+	leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
+
+	reiserfs_invalidate_buffer(tb, tbS0);
+
+	return 0;
+}
+
+/*
+ * Balance leaf node in case of delete or cut: insert_size[0] < 0
  *
  * lnum, rnum can have values >= -1
  *	-1 means that the neighbor must be joined with S
  *	 0 means that nothing should be done with the neighbor
- *	>0 means to shift entirely or partly the specified number of items to the neighbor
+ *	>0 means to shift entirely or partly the specified number of items
+ *         to the neighbor
  */
 static int balance_leaf_when_delete(struct tree_balance *tb, int flag)
 {
 	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
 	int item_pos = PATH_LAST_POSITION(tb->tb_path);
-	int pos_in_item = tb->tb_path->pos_in_item;
 	struct buffer_info bi;
 	int n;
 	struct item_head *ih;
@@ -114,1022 +251,1202 @@ static int balance_leaf_when_delete(struct tree_balance *tb, int flag)
 	RFALSE(!tb->blknum[0] && !PATH_H_PPARENT(tb->tb_path, 0),
 	       "PAP-12010: tree can not be empty");
 
-	ih = B_N_PITEM_HEAD(tbS0, item_pos);
+	ih = item_head(tbS0, item_pos);
 	buffer_info_init_tbS0(tb, &bi);
 
 	/* Delete or truncate the item */
 
-	switch (flag) {
-	case M_DELETE:		/* delete item in S[0] */
+	BUG_ON(flag != M_DELETE && flag != M_CUT);
+	if (flag == M_DELETE)
+		balance_leaf_when_delete_del(tb);
+	else /* M_CUT */
+		balance_leaf_when_delete_cut(tb);
 
-		RFALSE(ih_item_len(ih) + IH_SIZE != -tb->insert_size[0],
-		       "vs-12013: mode Delete, insert size %d, ih to be deleted %h",
-		       -tb->insert_size[0], ih);
 
-		leaf_delete_items(&bi, 0, item_pos, 1, -1);
+	/*
+	 * the rule is that no shifting occurs unless by shifting
+	 * a node can be freed
+	 */
+	n = B_NR_ITEMS(tbS0);
 
-		if (!item_pos && tb->CFL[0]) {
-			if (B_NR_ITEMS(tbS0)) {
-				replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0,
-					    0);
-			} else {
-				if (!PATH_H_POSITION(tb->tb_path, 1))
-					replace_key(tb, tb->CFL[0], tb->lkey[0],
-						    PATH_H_PPARENT(tb->tb_path,
-								   0), 0);
-			}
-		}
 
-		RFALSE(!item_pos && !tb->CFL[0],
-		       "PAP-12020: tb->CFL[0]==%p, tb->L[0]==%p", tb->CFL[0],
-		       tb->L[0]);
+	/* L[0] takes part in balancing */
+	if (tb->lnum[0])
+		return balance_leaf_when_delete_left(tb);
 
-		break;
+	if (tb->rnum[0] == -1) {
+		/* all contents of R[0] and S[0] will be in R[0] */
+		leaf_shift_right(tb, n, -1);
+		reiserfs_invalidate_buffer(tb, tbS0);
+		return 0;
+	}
 
-	case M_CUT:{		/* cut item in S[0] */
-			if (is_direntry_le_ih(ih)) {
+	RFALSE(tb->rnum[0],
+	       "PAP-12065: bad rnum parameter must be 0 (%d)", tb->rnum[0]);
+	return 0;
+}
 
-				/* UFS unlink semantics are such that you can only delete one directory entry at a time. */
-				/* when we cut a directory tb->insert_size[0] means number of entries to be cut (always 1) */
-				tb->insert_size[0] = -1;
-				leaf_cut_from_buffer(&bi, item_pos, pos_in_item,
-						     -tb->insert_size[0]);
+static void balance_leaf_insert_left(struct tree_balance *tb,
+				     struct item_head *ih, const char *body)
+{
+	int ret;
+	struct buffer_info bi;
+	int n = B_NR_ITEMS(tb->L[0]);
+
+	if (tb->item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) {
+		/* part of new item falls into L[0] */
+		int new_item_len, shift;
+		int version;
+
+		ret = leaf_shift_left(tb, tb->lnum[0] - 1, -1);
+
+		/* Calculate item length to insert to S[0] */
+		new_item_len = ih_item_len(ih) - tb->lbytes;
+
+		/* Calculate and check item length to insert to L[0] */
+		put_ih_item_len(ih, ih_item_len(ih) - new_item_len);
+
+		RFALSE(ih_item_len(ih) <= 0,
+		       "PAP-12080: there is nothing to insert into L[0]: "
+		       "ih_item_len=%d", ih_item_len(ih));
+
+		/* Insert new item into L[0] */
+		buffer_info_init_left(tb, &bi);
+		leaf_insert_into_buf(&bi, n + tb->item_pos - ret, ih, body,
+			     min_t(int, tb->zeroes_num, ih_item_len(ih)));
+
+		version = ih_version(ih);
+
+		/*
+		 * Calculate key component, item length and body to
+		 * insert into S[0]
+		 */
+		shift = 0;
+		if (is_indirect_le_ih(ih))
+			shift = tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT;
+
+		add_le_ih_k_offset(ih, tb->lbytes << shift);
+
+		put_ih_item_len(ih, new_item_len);
+		if (tb->lbytes > tb->zeroes_num) {
+			body += (tb->lbytes - tb->zeroes_num);
+			tb->zeroes_num = 0;
+		} else
+			tb->zeroes_num -= tb->lbytes;
+
+		RFALSE(ih_item_len(ih) <= 0,
+		       "PAP-12085: there is nothing to insert into S[0]: "
+		       "ih_item_len=%d", ih_item_len(ih));
+	} else {
+		/* new item in whole falls into L[0] */
+		/* Shift lnum[0]-1 items to L[0] */
+		ret = leaf_shift_left(tb, tb->lnum[0] - 1, tb->lbytes);
+
+		/* Insert new item into L[0] */
+		buffer_info_init_left(tb, &bi);
+		leaf_insert_into_buf(&bi, n + tb->item_pos - ret, ih, body,
+				     tb->zeroes_num);
+		tb->insert_size[0] = 0;
+		tb->zeroes_num = 0;
+	}
+}
 
-				RFALSE(!item_pos && !pos_in_item && !tb->CFL[0],
-				       "PAP-12030: can not change delimiting key. CFL[0]=%p",
-				       tb->CFL[0]);
+static void balance_leaf_paste_left_shift_dirent(struct tree_balance *tb,
+						 struct item_head *ih,
+						 const char *body)
+{
+	int n = B_NR_ITEMS(tb->L[0]);
+	struct buffer_info bi;
 
-				if (!item_pos && !pos_in_item && tb->CFL[0]) {
-					replace_key(tb, tb->CFL[0], tb->lkey[0],
-						    tbS0, 0);
-				}
-			} else {
-				leaf_cut_from_buffer(&bi, item_pos, pos_in_item,
-						     -tb->insert_size[0]);
+	RFALSE(tb->zeroes_num,
+	       "PAP-12090: invalid parameter in case of a directory");
+
+	/* directory item */
+	if (tb->lbytes > tb->pos_in_item) {
+		/* new directory entry falls into L[0] */
+		struct item_head *pasted;
+		int ret, l_pos_in_item = tb->pos_in_item;
+
+		/*
+		 * Shift lnum[0] - 1 items in whole.
+		 * Shift lbytes - 1 entries from given directory item
+		 */
+		ret = leaf_shift_left(tb, tb->lnum[0], tb->lbytes - 1);
+		if (ret && !tb->item_pos) {
+			pasted = item_head(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1);
+			l_pos_in_item += ih_entry_count(pasted) -
+					 (tb->lbytes - 1);
+		}
 
-				RFALSE(!ih_item_len(ih),
-				       "PAP-12035: cut must leave non-zero dynamic length of item");
-			}
-			break;
+		/* Append given directory entry to directory item */
+		buffer_info_init_left(tb, &bi);
+		leaf_paste_in_buffer(&bi, n + tb->item_pos - ret,
+				     l_pos_in_item, tb->insert_size[0],
+				     body, tb->zeroes_num);
+
+		/*
+		 * previous string prepared space for pasting new entry,
+		 * following string pastes this entry
+		 */
+
+		/*
+		 * when we have merge directory item, pos_in_item
+		 * has been changed too
+		 */
+
+		/* paste new directory entry. 1 is entry number */
+		leaf_paste_entries(&bi, n + tb->item_pos - ret,
+				   l_pos_in_item, 1,
+				   (struct reiserfs_de_head *) body,
+				   body + DEH_SIZE, tb->insert_size[0]);
+		tb->insert_size[0] = 0;
+	} else {
+		/* new directory item doesn't fall into L[0] */
+		/*
+		 * Shift lnum[0]-1 items in whole. Shift lbytes
+		 * directory entries from directory item number lnum[0]
+		 */
+		leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
+	}
+
+	/* Calculate new position to append in item body */
+	tb->pos_in_item -= tb->lbytes;
+}
+
+static void balance_leaf_paste_left_shift(struct tree_balance *tb,
+					  struct item_head *ih,
+					  const char *body)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int n = B_NR_ITEMS(tb->L[0]);
+	struct buffer_info bi;
+
+	if (is_direntry_le_ih(item_head(tbS0, tb->item_pos))) {
+		balance_leaf_paste_left_shift_dirent(tb, ih, body);
+		return;
+	}
+
+	RFALSE(tb->lbytes <= 0,
+	       "PAP-12095: there is nothing to shift to L[0]. "
+	       "lbytes=%d", tb->lbytes);
+	RFALSE(tb->pos_in_item != ih_item_len(item_head(tbS0, tb->item_pos)),
+	       "PAP-12100: incorrect position to paste: "
+	       "item_len=%d, pos_in_item=%d",
+	       ih_item_len(item_head(tbS0, tb->item_pos)), tb->pos_in_item);
+
+	/* appended item will be in L[0] in whole */
+	if (tb->lbytes >= tb->pos_in_item) {
+		struct item_head *tbS0_pos_ih, *tbL0_ih;
+		struct item_head *tbS0_0_ih;
+		struct reiserfs_key *left_delim_key;
+		int ret, l_n, version, temp_l;
+
+		tbS0_pos_ih = item_head(tbS0, tb->item_pos);
+		tbS0_0_ih = item_head(tbS0, 0);
+
+		/*
+		 * this bytes number must be appended
+		 * to the last item of L[h]
+		 */
+		l_n = tb->lbytes - tb->pos_in_item;
+
+		/* Calculate new insert_size[0] */
+		tb->insert_size[0] -= l_n;
+
+		RFALSE(tb->insert_size[0] <= 0,
+		       "PAP-12105: there is nothing to paste into "
+		       "L[0]. insert_size=%d", tb->insert_size[0]);
+
+		ret = leaf_shift_left(tb, tb->lnum[0],
+				      ih_item_len(tbS0_pos_ih));
+
+		tbL0_ih = item_head(tb->L[0], n + tb->item_pos - ret);
+
+		/* Append to body of item in L[0] */
+		buffer_info_init_left(tb, &bi);
+		leaf_paste_in_buffer(&bi, n + tb->item_pos - ret,
+				     ih_item_len(tbL0_ih), l_n, body,
+				     min_t(int, l_n, tb->zeroes_num));
+
+		/*
+		 * 0-th item in S0 can be only of DIRECT type
+		 * when l_n != 0
+		 */
+		temp_l = l_n;
+
+		RFALSE(ih_item_len(tbS0_0_ih),
+		       "PAP-12106: item length must be 0");
+		RFALSE(comp_short_le_keys(&tbS0_0_ih->ih_key,
+		       leaf_key(tb->L[0], n + tb->item_pos - ret)),
+		       "PAP-12107: items must be of the same file");
+
+		if (is_indirect_le_ih(tbL0_ih)) {
+			int shift = tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT;
+			temp_l = l_n << shift;
 		}
+		/* update key of first item in S0 */
+		version = ih_version(tbS0_0_ih);
+		add_le_key_k_offset(version, &tbS0_0_ih->ih_key, temp_l);
+
+		/* update left delimiting key */
+		left_delim_key = internal_key(tb->CFL[0], tb->lkey[0]);
+		add_le_key_k_offset(version, left_delim_key, temp_l);
+
+		/*
+		 * Calculate new body, position in item and
+		 * insert_size[0]
+		 */
+		if (l_n > tb->zeroes_num) {
+			body += (l_n - tb->zeroes_num);
+			tb->zeroes_num = 0;
+		} else
+			tb->zeroes_num -= l_n;
+		tb->pos_in_item = 0;
+
+		RFALSE(comp_short_le_keys(&tbS0_0_ih->ih_key,
+					  leaf_key(tb->L[0],
+						 B_NR_ITEMS(tb->L[0]) - 1)) ||
+		       !op_is_left_mergeable(leaf_key(tbS0, 0), tbS0->b_size) ||
+		       !op_is_left_mergeable(left_delim_key, tbS0->b_size),
+		       "PAP-12120: item must be merge-able with left "
+		       "neighboring item");
+	} else {
+		/* only part of the appended item will be in L[0] */
+
+		/* Calculate position in item for append in S[0] */
+		tb->pos_in_item -= tb->lbytes;
+
+		RFALSE(tb->pos_in_item <= 0,
+		       "PAP-12125: no place for paste. pos_in_item=%d",
+		       tb->pos_in_item);
+
+		/*
+		 * Shift lnum[0] - 1 items in whole.
+		 * Shift lbytes - 1 byte from item number lnum[0]
+		 */
+		leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
+	}
+}
 
-	default:
-		print_cur_tb("12040");
-		reiserfs_panic(tb->tb_sb, "PAP-12040",
-			       "unexpected mode: %s(%d)",
-			       (flag ==
-				M_PASTE) ? "PASTE" : ((flag ==
-						       M_INSERT) ? "INSERT" :
-						      "UNKNOWN"), flag);
+
+/* appended item will be in L[0] in whole */
+static void balance_leaf_paste_left_whole(struct tree_balance *tb,
+					  struct item_head *ih,
+					  const char *body)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int n = B_NR_ITEMS(tb->L[0]);
+	struct buffer_info bi;
+	struct item_head *pasted;
+	int ret;
+
+	/* if we paste into first item of S[0] and it is left mergable */
+	if (!tb->item_pos &&
+	    op_is_left_mergeable(leaf_key(tbS0, 0), tbS0->b_size)) {
+		/*
+		 * then increment pos_in_item by the size of the
+		 * last item in L[0]
+		 */
+		pasted = item_head(tb->L[0], n - 1);
+		if (is_direntry_le_ih(pasted))
+			tb->pos_in_item += ih_entry_count(pasted);
+		else
+			tb->pos_in_item += ih_item_len(pasted);
 	}
 
-	/* the rule is that no shifting occurs unless by shifting a node can be freed */
-	n = B_NR_ITEMS(tbS0);
-	if (tb->lnum[0]) {	/* L[0] takes part in balancing */
-		if (tb->lnum[0] == -1) {	/* L[0] must be joined with S[0] */
-			if (tb->rnum[0] == -1) {	/* R[0] must be also joined with S[0] */
-				if (tb->FR[0] == PATH_H_PPARENT(tb->tb_path, 0)) {
-					/* all contents of all the 3 buffers will be in L[0] */
-					if (PATH_H_POSITION(tb->tb_path, 1) == 0
-					    && 1 < B_NR_ITEMS(tb->FR[0]))
-						replace_key(tb, tb->CFL[0],
-							    tb->lkey[0],
-							    tb->FR[0], 1);
-
-					leaf_move_items(LEAF_FROM_S_TO_L, tb, n,
-							-1, NULL);
-					leaf_move_items(LEAF_FROM_R_TO_L, tb,
-							B_NR_ITEMS(tb->R[0]),
-							-1, NULL);
-
-					reiserfs_invalidate_buffer(tb, tbS0);
-					reiserfs_invalidate_buffer(tb,
-								   tb->R[0]);
-
-					return 0;
-				}
-				/* all contents of all the 3 buffers will be in R[0] */
-				leaf_move_items(LEAF_FROM_S_TO_R, tb, n, -1,
-						NULL);
-				leaf_move_items(LEAF_FROM_L_TO_R, tb,
-						B_NR_ITEMS(tb->L[0]), -1, NULL);
+	/*
+	 * Shift lnum[0] - 1 items in whole.
+	 * Shift lbytes - 1 byte from item number lnum[0]
+	 */
+	ret = leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
+
+	/* Append to body of item in L[0] */
+	buffer_info_init_left(tb, &bi);
+	leaf_paste_in_buffer(&bi, n + tb->item_pos - ret, tb->pos_in_item,
+			     tb->insert_size[0], body, tb->zeroes_num);
+
+	/* if appended item is directory, paste entry */
+	pasted = item_head(tb->L[0], n + tb->item_pos - ret);
+	if (is_direntry_le_ih(pasted))
+		leaf_paste_entries(&bi, n + tb->item_pos - ret,
+				   tb->pos_in_item, 1,
+				   (struct reiserfs_de_head *)body,
+				   body + DEH_SIZE, tb->insert_size[0]);
+
+	/*
+	 * if appended item is indirect item, put unformatted node
+	 * into un list
+	 */
+	if (is_indirect_le_ih(pasted))
+		set_ih_free_space(pasted, 0);
 
-				/* right_delimiting_key is correct in R[0] */
-				replace_key(tb, tb->CFR[0], tb->rkey[0],
-					    tb->R[0], 0);
+	tb->insert_size[0] = 0;
+	tb->zeroes_num = 0;
+}
 
-				reiserfs_invalidate_buffer(tb, tbS0);
-				reiserfs_invalidate_buffer(tb, tb->L[0]);
+static void balance_leaf_paste_left(struct tree_balance *tb,
+				    struct item_head *ih, const char *body)
+{
+	/* we must shift the part of the appended item */
+	if (tb->item_pos == tb->lnum[0] - 1 && tb->lbytes != -1)
+		balance_leaf_paste_left_shift(tb, ih, body);
+	else
+		balance_leaf_paste_left_whole(tb, ih, body);
+}
 
-				return -1;
-			}
+/* Shift lnum[0] items from S[0] to the left neighbor L[0] */
+static void balance_leaf_left(struct tree_balance *tb, struct item_head *ih,
+			      const char *body, int flag)
+{
+	if (tb->lnum[0] <= 0)
+		return;
 
-			RFALSE(tb->rnum[0] != 0,
-			       "PAP-12045: rnum must be 0 (%d)", tb->rnum[0]);
-			/* all contents of L[0] and S[0] will be in L[0] */
-			leaf_shift_left(tb, n, -1);
+	/* new item or it part falls to L[0], shift it too */
+	if (tb->item_pos < tb->lnum[0]) {
+		BUG_ON(flag != M_INSERT && flag != M_PASTE);
+
+		if (flag == M_INSERT)
+			balance_leaf_insert_left(tb, ih, body);
+		else /* M_PASTE */
+			balance_leaf_paste_left(tb, ih, body);
+	} else
+		/* new item doesn't fall into L[0] */
+		leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
+}
 
-			reiserfs_invalidate_buffer(tb, tbS0);
 
-			return 0;
+static void balance_leaf_insert_right(struct tree_balance *tb,
+				      struct item_head *ih, const char *body)
+{
+
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int n = B_NR_ITEMS(tbS0);
+	struct buffer_info bi;
+	int ret;
+
+	/* new item or part of it doesn't fall into R[0] */
+	if (n - tb->rnum[0] >= tb->item_pos) {
+		leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
+		return;
+	}
+
+	/* new item or its part falls to R[0] */
+
+	/* part of new item falls into R[0] */
+	if (tb->item_pos == n - tb->rnum[0] + 1 && tb->rbytes != -1) {
+		loff_t old_key_comp, old_len, r_zeroes_number;
+		const char *r_body;
+		int version, shift;
+		loff_t offset;
+
+		leaf_shift_right(tb, tb->rnum[0] - 1, -1);
+
+		version = ih_version(ih);
+
+		/* Remember key component and item length */
+		old_key_comp = le_ih_k_offset(ih);
+		old_len = ih_item_len(ih);
+
+		/*
+		 * Calculate key component and item length to insert
+		 * into R[0]
+		 */
+		shift = 0;
+		if (is_indirect_le_ih(ih))
+			shift = tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT;
+		offset = le_ih_k_offset(ih) + ((old_len - tb->rbytes) << shift);
+		set_le_ih_k_offset(ih, offset);
+		put_ih_item_len(ih, tb->rbytes);
+
+		/* Insert part of the item into R[0] */
+		buffer_info_init_right(tb, &bi);
+		if ((old_len - tb->rbytes) > tb->zeroes_num) {
+			r_zeroes_number = 0;
+			r_body = body + (old_len - tb->rbytes) - tb->zeroes_num;
+		} else {
+			r_body = body;
+			r_zeroes_number = tb->zeroes_num -
+					  (old_len - tb->rbytes);
+			tb->zeroes_num -= r_zeroes_number;
 		}
-		/* a part of contents of S[0] will be in L[0] and the rest part of S[0] will be in R[0] */
-
-		RFALSE((tb->lnum[0] + tb->rnum[0] < n) ||
-		       (tb->lnum[0] + tb->rnum[0] > n + 1),
-		       "PAP-12050: rnum(%d) and lnum(%d) and item number(%d) in S[0] are not consistent",
-		       tb->rnum[0], tb->lnum[0], n);
-		RFALSE((tb->lnum[0] + tb->rnum[0] == n) &&
-		       (tb->lbytes != -1 || tb->rbytes != -1),
-		       "PAP-12055: bad rbytes (%d)/lbytes (%d) parameters when items are not split",
-		       tb->rbytes, tb->lbytes);
-		RFALSE((tb->lnum[0] + tb->rnum[0] == n + 1) &&
-		       (tb->lbytes < 1 || tb->rbytes != -1),
-		       "PAP-12060: bad rbytes (%d)/lbytes (%d) parameters when items are split",
-		       tb->rbytes, tb->lbytes);
 
-		leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
+		leaf_insert_into_buf(&bi, 0, ih, r_body, r_zeroes_number);
+
+		/* Replace right delimiting key by first key in R[0] */
+		replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0);
+
+		/*
+		 * Calculate key component and item length to
+		 * insert into S[0]
+		 */
+		set_le_ih_k_offset(ih, old_key_comp);
+		put_ih_item_len(ih, old_len - tb->rbytes);
+
+		tb->insert_size[0] -= tb->rbytes;
+
+	} else {
+		/* whole new item falls into R[0] */
+
+		/* Shift rnum[0]-1 items to R[0] */
+		ret = leaf_shift_right(tb, tb->rnum[0] - 1, tb->rbytes);
+
+		/* Insert new item into R[0] */
+		buffer_info_init_right(tb, &bi);
+		leaf_insert_into_buf(&bi, tb->item_pos - n + tb->rnum[0] - 1,
+				     ih, body, tb->zeroes_num);
+
+		if (tb->item_pos - n + tb->rnum[0] - 1 == 0)
+			replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0);
+
+		tb->zeroes_num = tb->insert_size[0] = 0;
+	}
+}
+
+
+static void balance_leaf_paste_right_shift_dirent(struct tree_balance *tb,
+				     struct item_head *ih, const char *body)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	struct buffer_info bi;
+	int entry_count;
+
+	RFALSE(tb->zeroes_num,
+	       "PAP-12145: invalid parameter in case of a directory");
+	entry_count = ih_entry_count(item_head(tbS0, tb->item_pos));
+
+	/* new directory entry falls into R[0] */
+	if (entry_count - tb->rbytes < tb->pos_in_item) {
+		int paste_entry_position;
+
+		RFALSE(tb->rbytes - 1 >= entry_count || !tb->insert_size[0],
+		       "PAP-12150: no enough of entries to shift to R[0]: "
+		       "rbytes=%d, entry_count=%d", tb->rbytes, entry_count);
+
+		/*
+		 * Shift rnum[0]-1 items in whole.
+		 * Shift rbytes-1 directory entries from directory
+		 * item number rnum[0]
+		 */
+		leaf_shift_right(tb, tb->rnum[0], tb->rbytes - 1);
+
+		/* Paste given directory entry to directory item */
+		paste_entry_position = tb->pos_in_item - entry_count +
+				       tb->rbytes - 1;
+		buffer_info_init_right(tb, &bi);
+		leaf_paste_in_buffer(&bi, 0, paste_entry_position,
+				     tb->insert_size[0], body, tb->zeroes_num);
+
+		/* paste entry */
+		leaf_paste_entries(&bi, 0, paste_entry_position, 1,
+				   (struct reiserfs_de_head *) body,
+				   body + DEH_SIZE, tb->insert_size[0]);
+
+		/* change delimiting keys */
+		if (paste_entry_position == 0)
+			replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0);
+
+		tb->insert_size[0] = 0;
+		tb->pos_in_item++;
+	} else {
+		/* new directory entry doesn't fall into R[0] */
 		leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
+	}
+}
 
-		reiserfs_invalidate_buffer(tb, tbS0);
+static void balance_leaf_paste_right_shift(struct tree_balance *tb,
+				     struct item_head *ih, const char *body)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int n_shift, n_rem, r_zeroes_number, version;
+	unsigned long temp_rem;
+	const char *r_body;
+	struct buffer_info bi;
 
-		return 0;
+	/* we append to directory item */
+	if (is_direntry_le_ih(item_head(tbS0, tb->item_pos))) {
+		balance_leaf_paste_right_shift_dirent(tb, ih, body);
+		return;
 	}
 
-	if (tb->rnum[0] == -1) {
-		/* all contents of R[0] and S[0] will be in R[0] */
-		leaf_shift_right(tb, n, -1);
-		reiserfs_invalidate_buffer(tb, tbS0);
-		return 0;
+	/* regular object */
+
+	/*
+	 * Calculate number of bytes which must be shifted
+	 * from appended item
+	 */
+	n_shift = tb->rbytes - tb->insert_size[0];
+	if (n_shift < 0)
+		n_shift = 0;
+
+	RFALSE(tb->pos_in_item != ih_item_len(item_head(tbS0, tb->item_pos)),
+	       "PAP-12155: invalid position to paste. ih_item_len=%d, "
+	       "pos_in_item=%d", tb->pos_in_item,
+	       ih_item_len(item_head(tbS0, tb->item_pos)));
+
+	leaf_shift_right(tb, tb->rnum[0], n_shift);
+
+	/*
+	 * Calculate number of bytes which must remain in body
+	 * after appending to R[0]
+	 */
+	n_rem = tb->insert_size[0] - tb->rbytes;
+	if (n_rem < 0)
+		n_rem = 0;
+
+	temp_rem = n_rem;
+
+	version = ih_version(item_head(tb->R[0], 0));
+
+	if (is_indirect_le_key(version, leaf_key(tb->R[0], 0))) {
+		int shift = tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT;
+		temp_rem = n_rem << shift;
 	}
 
-	RFALSE(tb->rnum[0],
-	       "PAP-12065: bad rnum parameter must be 0 (%d)", tb->rnum[0]);
-	return 0;
+	add_le_key_k_offset(version, leaf_key(tb->R[0], 0), temp_rem);
+	add_le_key_k_offset(version, internal_key(tb->CFR[0], tb->rkey[0]),
+			    temp_rem);
+
+	do_balance_mark_internal_dirty(tb, tb->CFR[0], 0);
+
+	/* Append part of body into R[0] */
+	buffer_info_init_right(tb, &bi);
+	if (n_rem > tb->zeroes_num) {
+		r_zeroes_number = 0;
+		r_body = body + n_rem - tb->zeroes_num;
+	} else {
+		r_body = body;
+		r_zeroes_number = tb->zeroes_num - n_rem;
+		tb->zeroes_num -= r_zeroes_number;
+	}
+
+	leaf_paste_in_buffer(&bi, 0, n_shift, tb->insert_size[0] - n_rem,
+			     r_body, r_zeroes_number);
+
+	if (is_indirect_le_ih(item_head(tb->R[0], 0)))
+		set_ih_free_space(item_head(tb->R[0], 0), 0);
+
+	tb->insert_size[0] = n_rem;
+	if (!n_rem)
+		tb->pos_in_item++;
 }
 
-static int balance_leaf(struct tree_balance *tb, struct item_head *ih,	/* item header of inserted item (this is on little endian) */
-			const char *body,	/* body  of inserted item or bytes to paste */
-			int flag,	/* i - insert, d - delete, c - cut, p - paste
-					   (see comment to do_balance) */
-			struct item_head *insert_key,	/* in our processing of one level we sometimes determine what
-							   must be inserted into the next higher level.  This insertion
-							   consists of a key or two keys and their corresponding
-							   pointers */
-			struct buffer_head **insert_ptr	/* inserted node-ptrs for the next level */
-    )
+static void balance_leaf_paste_right_whole(struct tree_balance *tb,
+				     struct item_head *ih, const char *body)
 {
 	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
-	int item_pos = PATH_LAST_POSITION(tb->tb_path);	/*  index into the array of item headers in S[0]
-							   of the affected item */
+	int n = B_NR_ITEMS(tbS0);
+	struct item_head *pasted;
 	struct buffer_info bi;
-	struct buffer_head *S_new[2];	/* new nodes allocated to hold what could not fit into S */
-	int snum[2];		/* number of items that will be placed
-				   into S_new (includes partially shifted
-				   items) */
-	int sbytes[2];		/* if an item is partially shifted into S_new then
-				   if it is a directory item
-				   it is the number of entries from the item that are shifted into S_new
-				   else
-				   it is the number of bytes from the item that are shifted into S_new
-				 */
-	int n, i;
-	int ret_val;
-	int pos_in_item;
-	int zeros_num;
 
-	PROC_INFO_INC(tb->tb_sb, balance_at[0]);
+							buffer_info_init_right(tb, &bi);
+	leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
+
+	/* append item in R[0] */
+	if (tb->pos_in_item >= 0) {
+		buffer_info_init_right(tb, &bi);
+		leaf_paste_in_buffer(&bi, tb->item_pos - n + tb->rnum[0],
+				     tb->pos_in_item, tb->insert_size[0], body,
+				     tb->zeroes_num);
+	}
 
-	/* Make balance in case insert_size[0] < 0 */
-	if (tb->insert_size[0] < 0)
-		return balance_leaf_when_delete(tb, flag);
+	/* paste new entry, if item is directory item */
+	pasted = item_head(tb->R[0], tb->item_pos - n + tb->rnum[0]);
+	if (is_direntry_le_ih(pasted) && tb->pos_in_item >= 0) {
+		leaf_paste_entries(&bi, tb->item_pos - n + tb->rnum[0],
+				   tb->pos_in_item, 1,
+				   (struct reiserfs_de_head *)body,
+				   body + DEH_SIZE, tb->insert_size[0]);
 
-	zeros_num = 0;
-	if (flag == M_INSERT && !body)
-		zeros_num = ih_item_len(ih);
+		if (!tb->pos_in_item) {
 
-	pos_in_item = tb->tb_path->pos_in_item;
-	/* for indirect item pos_in_item is measured in unformatted node
-	   pointers. Recalculate to bytes */
-	if (flag != M_INSERT
-	    && is_indirect_le_ih(B_N_PITEM_HEAD(tbS0, item_pos)))
-		pos_in_item *= UNFM_P_SIZE;
-
-	if (tb->lnum[0] > 0) {
-		/* Shift lnum[0] items from S[0] to the left neighbor L[0] */
-		if (item_pos < tb->lnum[0]) {
-			/* new item or it part falls to L[0], shift it too */
-			n = B_NR_ITEMS(tb->L[0]);
-
-			switch (flag) {
-			case M_INSERT:	/* insert item into L[0] */
-
-				if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) {
-					/* part of new item falls into L[0] */
-					int new_item_len;
-					int version;
-
-					ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, -1);
-
-					/* Calculate item length to insert to S[0] */
-					new_item_len = ih_item_len(ih) - tb->lbytes;
-					/* Calculate and check item length to insert to L[0] */
-					put_ih_item_len(ih, ih_item_len(ih) - new_item_len);
-
-					RFALSE(ih_item_len(ih) <= 0,
-					       "PAP-12080: there is nothing to insert into L[0]: ih_item_len=%d",
-					       ih_item_len(ih));
-
-					/* Insert new item into L[0] */
-					buffer_info_init_left(tb, &bi);
-					leaf_insert_into_buf(&bi,
-							n + item_pos - ret_val, ih, body,
-							zeros_num > ih_item_len(ih) ? ih_item_len(ih) : zeros_num);
-
-					version = ih_version(ih);
-
-					/* Calculate key component, item length and body to insert into S[0] */
-					set_le_ih_k_offset(ih, le_ih_k_offset(ih) +
-							(tb-> lbytes << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0)));
-
-					put_ih_item_len(ih, new_item_len);
-					if (tb->lbytes > zeros_num) {
-						body += (tb->lbytes - zeros_num);
-						zeros_num = 0;
-					} else
-						zeros_num -= tb->lbytes;
-
-					RFALSE(ih_item_len(ih) <= 0,
-					       "PAP-12085: there is nothing to insert into S[0]: ih_item_len=%d",
-					       ih_item_len(ih));
-				} else {
-					/* new item in whole falls into L[0] */
-					/* Shift lnum[0]-1 items to L[0] */
-					ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, tb->lbytes);
-					/* Insert new item into L[0] */
-					buffer_info_init_left(tb, &bi);
-					leaf_insert_into_buf(&bi, n + item_pos - ret_val, ih, body, zeros_num);
-					tb->insert_size[0] = 0;
-					zeros_num = 0;
-				}
-				break;
-
-			case M_PASTE:	/* append item in L[0] */
-
-				if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) {
-					/* we must shift the part of the appended item */
-					if (is_direntry_le_ih(B_N_PITEM_HEAD(tbS0, item_pos))) {
-
-						RFALSE(zeros_num,
-						       "PAP-12090: invalid parameter in case of a directory");
-						/* directory item */
-						if (tb->lbytes > pos_in_item) {
-							/* new directory entry falls into L[0] */
-							struct item_head *pasted;
-							int l_pos_in_item = pos_in_item;
-
-							/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 entries from given directory item */
-							ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes-1);
-							if (ret_val && !item_pos) {
-								pasted = B_N_PITEM_HEAD(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1);
-								l_pos_in_item += I_ENTRY_COUNT(pasted) - (tb->lbytes -1);
-							}
-
-							/* Append given directory entry to directory item */
-							buffer_info_init_left(tb, &bi);
-							leaf_paste_in_buffer(&bi, n + item_pos - ret_val, l_pos_in_item, tb->insert_size[0], body, zeros_num);
-
-							/* previous string prepared space for pasting new entry, following string pastes this entry */
-
-							/* when we have merge directory item, pos_in_item has been changed too */
-
-							/* paste new directory entry. 1 is entry number */
-							leaf_paste_entries(&bi, n + item_pos - ret_val, l_pos_in_item,
-									   1, (struct reiserfs_de_head *) body,
-									   body + DEH_SIZE, tb->insert_size[0]);
-							tb->insert_size[0] = 0;
-						} else {
-							/* new directory item doesn't fall into L[0] */
-							/* Shift lnum[0]-1 items in whole. Shift lbytes directory entries from directory item number lnum[0] */
-							leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
-						}
-						/* Calculate new position to append in item body */
-						pos_in_item -= tb->lbytes;
-					} else {
-						/* regular object */
-						RFALSE(tb->lbytes <= 0, "PAP-12095: there is nothing to shift to L[0]. lbytes=%d", tb->lbytes);
-						RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),
-						       "PAP-12100: incorrect position to paste: item_len=%d, pos_in_item=%d",
-						       ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),pos_in_item);
-
-						if (tb->lbytes >= pos_in_item) {
-							/* appended item will be in L[0] in whole */
-							int l_n;
-
-							/* this bytes number must be appended to the last item of L[h] */
-							l_n = tb->lbytes - pos_in_item;
-
-							/* Calculate new insert_size[0] */
-							tb->insert_size[0] -= l_n;
-
-							RFALSE(tb->insert_size[0] <= 0,
-							       "PAP-12105: there is nothing to paste into L[0]. insert_size=%d",
-							       tb->insert_size[0]);
-							ret_val = leaf_shift_left(tb, tb->lnum[0], ih_item_len
-									    (B_N_PITEM_HEAD(tbS0, item_pos)));
-							/* Append to body of item in L[0] */
-							buffer_info_init_left(tb, &bi);
-							leaf_paste_in_buffer
-							    (&bi, n + item_pos - ret_val, ih_item_len
-							     (B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val)),
-							     l_n, body,
-							     zeros_num > l_n ? l_n : zeros_num);
-							/* 0-th item in S0 can be only of DIRECT type when l_n != 0 */
-							{
-								int version;
-								int temp_l = l_n;
-
-								RFALSE(ih_item_len(B_N_PITEM_HEAD(tbS0, 0)),
-								     "PAP-12106: item length must be 0");
-								RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY
-								      (tb->L[0], n + item_pos - ret_val)),
-								     "PAP-12107: items must be of the same file");
-								if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val))) {
-									temp_l = l_n << (tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT);
-								}
-								/* update key of first item in S0 */
-								version = ih_version(B_N_PITEM_HEAD(tbS0, 0));
-								set_le_key_k_offset(version, B_N_PKEY(tbS0, 0),
-								     le_key_k_offset(version,B_N_PKEY(tbS0, 0)) + temp_l);
-								/* update left delimiting key */
-								set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]),
-								     le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0])) + temp_l);
-							}
-
-							/* Calculate new body, position in item and insert_size[0] */
-							if (l_n > zeros_num) {
-								body += (l_n - zeros_num);
-								zeros_num = 0;
-							} else
-								zeros_num -= l_n;
-							pos_in_item = 0;
-
-							RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1))
-							     || !op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)
-							     || !op_is_left_mergeable(B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]), tbS0->b_size),
-							     "PAP-12120: item must be merge-able with left neighboring item");
-						} else {	/* only part of the appended item will be in L[0] */
-
-							/* Calculate position in item for append in S[0] */
-							pos_in_item -= tb->lbytes;
-
-							RFALSE(pos_in_item <= 0, "PAP-12125: no place for paste. pos_in_item=%d", pos_in_item);
-
-							/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */
-							leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
-						}
-					}
-				} else {	/* appended item will be in L[0] in whole */
-
-					struct item_head *pasted;
-
-					if (!item_pos && op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)) {	/* if we paste into first item of S[0] and it is left mergable */
-						/* then increment pos_in_item by the size of the last item in L[0] */
-						pasted = B_N_PITEM_HEAD(tb->L[0], n - 1);
-						if (is_direntry_le_ih(pasted))
-							pos_in_item += ih_entry_count(pasted);
-						else
-							pos_in_item += ih_item_len(pasted);
-					}
-
-					/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */
-					ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
-					/* Append to body of item in L[0] */
-					buffer_info_init_left(tb, &bi);
-					leaf_paste_in_buffer(&bi, n + item_pos - ret_val,
-							     pos_in_item,
-							     tb->insert_size[0],
-							     body, zeros_num);
-
-					/* if appended item is directory, paste entry */
-					pasted = B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val);
-					if (is_direntry_le_ih(pasted))
-						leaf_paste_entries(&bi, n + item_pos - ret_val,
-								   pos_in_item, 1,
-								   (struct reiserfs_de_head *) body,
-								   body + DEH_SIZE,
-								   tb->insert_size[0]);
-					/* if appended item is indirect item, put unformatted node into un list */
-					if (is_indirect_le_ih(pasted))
-						set_ih_free_space(pasted, 0);
-					tb->insert_size[0] = 0;
-					zeros_num = 0;
-				}
-				break;
-			default:	/* cases d and t */
-				reiserfs_panic(tb->tb_sb, "PAP-12130",
-					       "lnum > 0: unexpected mode: "
-					       " %s(%d)",
-					       (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
-			}
-		} else {
-			/* new item doesn't fall into L[0] */
-			leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
+			RFALSE(tb->item_pos - n + tb->rnum[0],
+			       "PAP-12165: directory item must be first "
+			       "item of node when pasting is in 0th position");
+
+			/* update delimiting keys */
+			replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0);
 		}
 	}
 
-	/* tb->lnum[0] > 0 */
-	/* Calculate new item position */
-	item_pos -= (tb->lnum[0] - ((tb->lbytes != -1) ? 1 : 0));
-
-	if (tb->rnum[0] > 0) {
-		/* shift rnum[0] items from S[0] to the right neighbor R[0] */
-		n = B_NR_ITEMS(tbS0);
-		switch (flag) {
-
-		case M_INSERT:	/* insert item */
-			if (n - tb->rnum[0] < item_pos) {	/* new item or its part falls to R[0] */
-				if (item_pos == n - tb->rnum[0] + 1 && tb->rbytes != -1) {	/* part of new item falls into R[0] */
-					loff_t old_key_comp, old_len, r_zeros_number;
-					const char *r_body;
-					int version;
-					loff_t offset;
-
-					leaf_shift_right(tb, tb->rnum[0] - 1, -1);
-
-					version = ih_version(ih);
-					/* Remember key component and item length */
-					old_key_comp = le_ih_k_offset(ih);
-					old_len = ih_item_len(ih);
-
-					/* Calculate key component and item length to insert into R[0] */
-					offset = le_ih_k_offset(ih) + ((old_len - tb->rbytes) << (is_indirect_le_ih(ih) ? tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT : 0));
-					set_le_ih_k_offset(ih, offset);
-					put_ih_item_len(ih, tb->rbytes);
-					/* Insert part of the item into R[0] */
-					buffer_info_init_right(tb, &bi);
-					if ((old_len - tb->rbytes) > zeros_num) {
-						r_zeros_number = 0;
-						r_body = body + (old_len - tb->rbytes) - zeros_num;
-					} else {
-						r_body = body;
-						r_zeros_number = zeros_num - (old_len - tb->rbytes);
-						zeros_num -= r_zeros_number;
-					}
-
-					leaf_insert_into_buf(&bi, 0, ih, r_body,
-							     r_zeros_number);
-
-					/* Replace right delimiting key by first key in R[0] */
-					replace_key(tb, tb->CFR[0], tb->rkey[0],
-						    tb->R[0], 0);
-
-					/* Calculate key component and item length to insert into S[0] */
-					set_le_ih_k_offset(ih, old_key_comp);
-					put_ih_item_len(ih, old_len - tb->rbytes);
-
-					tb->insert_size[0] -= tb->rbytes;
-
-				} else {	/* whole new item falls into R[0] */
-
-					/* Shift rnum[0]-1 items to R[0] */
-					ret_val = leaf_shift_right(tb, tb->rnum[0] - 1, tb->rbytes);
-					/* Insert new item into R[0] */
-					buffer_info_init_right(tb, &bi);
-					leaf_insert_into_buf(&bi, item_pos - n + tb->rnum[0] - 1,
-							     ih, body, zeros_num);
-
-					if (item_pos - n + tb->rnum[0] - 1 == 0) {
-						replace_key(tb, tb->CFR[0],
-							    tb->rkey[0],
-							    tb->R[0], 0);
-
-					}
-					zeros_num = tb->insert_size[0] = 0;
-				}
-			} else {	/* new item or part of it doesn't fall into R[0] */
-
-				leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
-			}
-			break;
+	if (is_indirect_le_ih(pasted))
+		set_ih_free_space(pasted, 0);
+	tb->zeroes_num = tb->insert_size[0] = 0;
+}
 
-		case M_PASTE:	/* append item */
-
-			if (n - tb->rnum[0] <= item_pos) {	/* pasted item or part of it falls to R[0] */
-				if (item_pos == n - tb->rnum[0] && tb->rbytes != -1) {	/* we must shift the part of the appended item */
-					if (is_direntry_le_ih(B_N_PITEM_HEAD(tbS0, item_pos))) {	/* we append to directory item */
-						int entry_count;
-
-						RFALSE(zeros_num,
-						       "PAP-12145: invalid parameter in case of a directory");
-						entry_count = I_ENTRY_COUNT(B_N_PITEM_HEAD
-								  (tbS0, item_pos));
-						if (entry_count - tb->rbytes <
-						    pos_in_item)
-							/* new directory entry falls into R[0] */
-						{
-							int paste_entry_position;
-
-							RFALSE(tb->rbytes - 1 >= entry_count || !tb-> insert_size[0],
-							       "PAP-12150: no enough of entries to shift to R[0]: rbytes=%d, entry_count=%d",
-							       tb->rbytes, entry_count);
-							/* Shift rnum[0]-1 items in whole. Shift rbytes-1 directory entries from directory item number rnum[0] */
-							leaf_shift_right(tb, tb->rnum[0], tb->rbytes - 1);
-							/* Paste given directory entry to directory item */
-							paste_entry_position = pos_in_item - entry_count + tb->rbytes - 1;
-							buffer_info_init_right(tb, &bi);
-							leaf_paste_in_buffer(&bi, 0, paste_entry_position, tb->insert_size[0], body, zeros_num);
-							/* paste entry */
-							leaf_paste_entries(&bi, 0, paste_entry_position, 1,
-									   (struct reiserfs_de_head *) body,
-									   body + DEH_SIZE, tb->insert_size[0]);
-
-							if (paste_entry_position == 0) {
-								/* change delimiting keys */
-								replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0],0);
-							}
-
-							tb->insert_size[0] = 0;
-							pos_in_item++;
-						} else {	/* new directory entry doesn't fall into R[0] */
-
-							leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
-						}
-					} else {	/* regular object */
-
-						int n_shift, n_rem, r_zeros_number;
-						const char *r_body;
-
-						/* Calculate number of bytes which must be shifted from appended item */
-						if ((n_shift = tb->rbytes - tb->insert_size[0]) < 0)
-							n_shift = 0;
-
-						RFALSE(pos_in_item != ih_item_len
-						       (B_N_PITEM_HEAD(tbS0, item_pos)),
-						       "PAP-12155: invalid position to paste. ih_item_len=%d, pos_in_item=%d",
-						       pos_in_item, ih_item_len
-						       (B_N_PITEM_HEAD(tbS0, item_pos)));
-
-						leaf_shift_right(tb, tb->rnum[0], n_shift);
-						/* Calculate number of bytes which must remain in body after appending to R[0] */
-						if ((n_rem = tb->insert_size[0] - tb->rbytes) < 0)
-							n_rem = 0;
-
-						{
-							int version;
-							unsigned long temp_rem = n_rem;
-
-							version = ih_version(B_N_PITEM_HEAD(tb->R[0], 0));
-							if (is_indirect_le_key(version, B_N_PKEY(tb->R[0], 0))) {
-								temp_rem = n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT);
-							}
-							set_le_key_k_offset(version, B_N_PKEY(tb->R[0], 0),
-							     le_key_k_offset(version, B_N_PKEY(tb->R[0], 0)) + temp_rem);
-							set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0]),
-							     le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0])) + temp_rem);
-						}
-/*		  k_offset (B_N_PKEY(tb->R[0],0)) += n_rem;
-		  k_offset (B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) += n_rem;*/
-						do_balance_mark_internal_dirty(tb, tb->CFR[0], 0);
-
-						/* Append part of body into R[0] */
-						buffer_info_init_right(tb, &bi);
-						if (n_rem > zeros_num) {
-							r_zeros_number = 0;
-							r_body = body + n_rem - zeros_num;
-						} else {
-							r_body = body;
-							r_zeros_number = zeros_num - n_rem;
-							zeros_num -= r_zeros_number;
-						}
-
-						leaf_paste_in_buffer(&bi, 0, n_shift,
-								     tb->insert_size[0] - n_rem,
-								     r_body, r_zeros_number);
-
-						if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->R[0], 0))) {
-#if 0
-							RFALSE(n_rem,
-							       "PAP-12160: paste more than one unformatted node pointer");
-#endif
-							set_ih_free_space(B_N_PITEM_HEAD(tb->R[0], 0), 0);
-						}
-						tb->insert_size[0] = n_rem;
-						if (!n_rem)
-							pos_in_item++;
-					}
-				} else {	/* pasted item in whole falls into R[0] */
-
-					struct item_head *pasted;
-
-					ret_val = leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
-					/* append item in R[0] */
-					if (pos_in_item >= 0) {
-						buffer_info_init_right(tb, &bi);
-						leaf_paste_in_buffer(&bi, item_pos - n + tb->rnum[0], pos_in_item,
-								     tb->insert_size[0], body, zeros_num);
-					}
-
-					/* paste new entry, if item is directory item */
-					pasted = B_N_PITEM_HEAD(tb->R[0], item_pos - n + tb->rnum[0]);
-					if (is_direntry_le_ih(pasted) && pos_in_item >= 0) {
-						leaf_paste_entries(&bi, item_pos - n + tb->rnum[0],
-								   pos_in_item, 1,
-								   (struct reiserfs_de_head *) body,
-								   body + DEH_SIZE, tb->insert_size[0]);
-						if (!pos_in_item) {
-
-							RFALSE(item_pos - n + tb->rnum[0],
-							       "PAP-12165: directory item must be first item of node when pasting is in 0th position");
-
-							/* update delimiting keys */
-							replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0);
-						}
-					}
-
-					if (is_indirect_le_ih(pasted))
-						set_ih_free_space(pasted, 0);
-					zeros_num = tb->insert_size[0] = 0;
-				}
-			} else {	/* new item doesn't fall into R[0] */
-
-				leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
-			}
-			break;
-		default:	/* cases d and t */
-			reiserfs_panic(tb->tb_sb, "PAP-12175",
-				       "rnum > 0: unexpected mode: %s(%d)",
-				       (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
-		}
+static void balance_leaf_paste_right(struct tree_balance *tb,
+				     struct item_head *ih, const char *body)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int n = B_NR_ITEMS(tbS0);
 
+	/* new item doesn't fall into R[0] */
+	if (n - tb->rnum[0] > tb->item_pos) {
+		leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
+		return;
 	}
 
-	/* tb->rnum[0] > 0 */
-	RFALSE(tb->blknum[0] > 3,
-	       "PAP-12180: blknum can not be %d. It must be <= 3", tb->blknum[0]);
-	RFALSE(tb->blknum[0] < 0,
-	       "PAP-12185: blknum can not be %d. It must be >= 0", tb->blknum[0]);
+	/* pasted item or part of it falls to R[0] */
 
-	/* if while adding to a node we discover that it is possible to split
-	   it in two, and merge the left part into the left neighbor and the
-	   right part into the right neighbor, eliminating the node */
-	if (tb->blknum[0] == 0) {	/* node S[0] is empty now */
+	if (tb->item_pos == n - tb->rnum[0] && tb->rbytes != -1)
+		/* we must shift the part of the appended item */
+		balance_leaf_paste_right_shift(tb, ih, body);
+	else
+		/* pasted item in whole falls into R[0] */
+		balance_leaf_paste_right_whole(tb, ih, body);
+}
 
-		RFALSE(!tb->lnum[0] || !tb->rnum[0],
-		       "PAP-12190: lnum and rnum must not be zero");
-		/* if insertion was done before 0-th position in R[0], right
-		   delimiting key of the tb->L[0]'s and left delimiting key are
-		   not set correctly */
-		if (tb->CFL[0]) {
-			if (!tb->CFR[0])
-				reiserfs_panic(tb->tb_sb, "vs-12195",
-					       "CFR not initialized");
-			copy_key(B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]),
-				 B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0]));
-			do_balance_mark_internal_dirty(tb, tb->CFL[0], 0);
+/* shift rnum[0] items from S[0] to the right neighbor R[0] */
+static void balance_leaf_right(struct tree_balance *tb, struct item_head *ih,
+			       const char *body, int flag)
+{
+	if (tb->rnum[0] <= 0)
+		return;
+
+	BUG_ON(flag != M_INSERT && flag != M_PASTE);
+
+	if (flag == M_INSERT)
+		balance_leaf_insert_right(tb, ih, body);
+	else /* M_PASTE */
+		balance_leaf_paste_right(tb, ih, body);
+}
+
+static void balance_leaf_new_nodes_insert(struct tree_balance *tb,
+					  struct item_head *ih,
+					  const char *body,
+					  struct item_head *insert_key,
+					  struct buffer_head **insert_ptr,
+					  int i)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int n = B_NR_ITEMS(tbS0);
+	struct buffer_info bi;
+	int shift;
+
+	/* new item or it part don't falls into S_new[i] */
+	if (n - tb->snum[i] >= tb->item_pos) {
+		leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
+				tb->snum[i], tb->sbytes[i], tb->S_new[i]);
+		return;
+	}
+
+	/* new item or it's part falls to first new node S_new[i] */
+
+	/* part of new item falls into S_new[i] */
+	if (tb->item_pos == n - tb->snum[i] + 1 && tb->sbytes[i] != -1) {
+		int old_key_comp, old_len, r_zeroes_number;
+		const char *r_body;
+		int version;
+
+		/* Move snum[i]-1 items from S[0] to S_new[i] */
+		leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, tb->snum[i] - 1, -1,
+				tb->S_new[i]);
+
+		/* Remember key component and item length */
+		version = ih_version(ih);
+		old_key_comp = le_ih_k_offset(ih);
+		old_len = ih_item_len(ih);
+
+		/*
+		 * Calculate key component and item length to insert
+		 * into S_new[i]
+		 */
+		shift = 0;
+		if (is_indirect_le_ih(ih))
+			shift = tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT;
+		set_le_ih_k_offset(ih,
+				   le_ih_k_offset(ih) +
+				   ((old_len - tb->sbytes[i]) << shift));
+
+		put_ih_item_len(ih, tb->sbytes[i]);
+
+		/* Insert part of the item into S_new[i] before 0-th item */
+		buffer_info_init_bh(tb, &bi, tb->S_new[i]);
+
+		if ((old_len - tb->sbytes[i]) > tb->zeroes_num) {
+			r_zeroes_number = 0;
+			r_body = body + (old_len - tb->sbytes[i]) -
+					 tb->zeroes_num;
+		} else {
+			r_body = body;
+			r_zeroes_number = tb->zeroes_num - (old_len -
+					  tb->sbytes[i]);
+			tb->zeroes_num -= r_zeroes_number;
 		}
 
-		reiserfs_invalidate_buffer(tb, tbS0);
-		return 0;
+		leaf_insert_into_buf(&bi, 0, ih, r_body, r_zeroes_number);
+
+		/*
+		 * Calculate key component and item length to
+		 * insert into S[i]
+		 */
+		set_le_ih_k_offset(ih, old_key_comp);
+		put_ih_item_len(ih, old_len - tb->sbytes[i]);
+		tb->insert_size[0] -= tb->sbytes[i];
+	} else {
+		/* whole new item falls into S_new[i] */
+
+		/*
+		 * Shift snum[0] - 1 items to S_new[i]
+		 * (sbytes[i] of split item)
+		 */
+		leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
+				tb->snum[i] - 1, tb->sbytes[i], tb->S_new[i]);
+
+		/* Insert new item into S_new[i] */
+		buffer_info_init_bh(tb, &bi, tb->S_new[i]);
+		leaf_insert_into_buf(&bi, tb->item_pos - n + tb->snum[i] - 1,
+				     ih, body, tb->zeroes_num);
+
+		tb->zeroes_num = tb->insert_size[0] = 0;
 	}
+}
 
-	/* Fill new nodes that appear in place of S[0] */
+/* we append to directory item */
+static void balance_leaf_new_nodes_paste_dirent(struct tree_balance *tb,
+					 struct item_head *ih,
+					 const char *body,
+					 struct item_head *insert_key,
+					 struct buffer_head **insert_ptr,
+					 int i)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	struct item_head *aux_ih = item_head(tbS0, tb->item_pos);
+	int entry_count = ih_entry_count(aux_ih);
+	struct buffer_info bi;
+
+	if (entry_count - tb->sbytes[i] < tb->pos_in_item &&
+	    tb->pos_in_item <= entry_count) {
+		/* new directory entry falls into S_new[i] */
+
+		RFALSE(!tb->insert_size[0],
+		       "PAP-12215: insert_size is already 0");
+		RFALSE(tb->sbytes[i] - 1 >= entry_count,
+		       "PAP-12220: there are no so much entries (%d), only %d",
+		       tb->sbytes[i] - 1, entry_count);
+
+		/*
+		 * Shift snum[i]-1 items in whole.
+		 * Shift sbytes[i] directory entries
+		 * from directory item number snum[i]
+		 */
+		leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, tb->snum[i],
+				tb->sbytes[i] - 1, tb->S_new[i]);
+
+		/*
+		 * Paste given directory entry to
+		 * directory item
+		 */
+		buffer_info_init_bh(tb, &bi, tb->S_new[i]);
+		leaf_paste_in_buffer(&bi, 0, tb->pos_in_item - entry_count +
+				     tb->sbytes[i] - 1, tb->insert_size[0],
+				     body, tb->zeroes_num);
+
+		/* paste new directory entry */
+		leaf_paste_entries(&bi, 0, tb->pos_in_item - entry_count +
+				   tb->sbytes[i] - 1, 1,
+				   (struct reiserfs_de_head *) body,
+				   body + DEH_SIZE, tb->insert_size[0]);
+
+		tb->insert_size[0] = 0;
+		tb->pos_in_item++;
+	} else {
+		/* new directory entry doesn't fall into S_new[i] */
+		leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, tb->snum[i],
+				tb->sbytes[i], tb->S_new[i]);
+	}
+
+}
 
-	/* I am told that this copying is because we need an array to enable
-	   the looping code. -Hans */
-	snum[0] = tb->s1num, snum[1] = tb->s2num;
-	sbytes[0] = tb->s1bytes;
-	sbytes[1] = tb->s2bytes;
+static void balance_leaf_new_nodes_paste_shift(struct tree_balance *tb,
+					 struct item_head *ih,
+					 const char *body,
+					 struct item_head *insert_key,
+					 struct buffer_head **insert_ptr,
+					 int i)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	struct item_head *aux_ih = item_head(tbS0, tb->item_pos);
+	int n_shift, n_rem, r_zeroes_number, shift;
+	const char *r_body;
+	struct item_head *tmp;
+	struct buffer_info bi;
+
+	RFALSE(ih, "PAP-12210: ih must be 0");
+
+	if (is_direntry_le_ih(aux_ih)) {
+		balance_leaf_new_nodes_paste_dirent(tb, ih, body, insert_key,
+						    insert_ptr, i);
+		return;
+	}
+
+	/* regular object */
+
+
+	RFALSE(tb->pos_in_item != ih_item_len(item_head(tbS0, tb->item_pos)) ||
+	       tb->insert_size[0] <= 0,
+	       "PAP-12225: item too short or insert_size <= 0");
+
+	/*
+	 * Calculate number of bytes which must be shifted from appended item
+	 */
+	n_shift = tb->sbytes[i] - tb->insert_size[0];
+	if (n_shift < 0)
+		n_shift = 0;
+	leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, tb->snum[i], n_shift,
+			tb->S_new[i]);
+
+	/*
+	 * Calculate number of bytes which must remain in body after
+	 * append to S_new[i]
+	 */
+	n_rem = tb->insert_size[0] - tb->sbytes[i];
+	if (n_rem < 0)
+		n_rem = 0;
+
+	/* Append part of body into S_new[0] */
+	buffer_info_init_bh(tb, &bi, tb->S_new[i]);
+	if (n_rem > tb->zeroes_num) {
+		r_zeroes_number = 0;
+		r_body = body + n_rem - tb->zeroes_num;
+	} else {
+		r_body = body;
+		r_zeroes_number = tb->zeroes_num - n_rem;
+		tb->zeroes_num -= r_zeroes_number;
+	}
+
+	leaf_paste_in_buffer(&bi, 0, n_shift, tb->insert_size[0] - n_rem,
+			     r_body, r_zeroes_number);
+
+	tmp = item_head(tb->S_new[i], 0);
+	shift = 0;
+	if (is_indirect_le_ih(tmp)) {
+		set_ih_free_space(tmp, 0);
+		shift = tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT;
+	}
+	add_le_ih_k_offset(tmp, n_rem << shift);
+
+	tb->insert_size[0] = n_rem;
+	if (!n_rem)
+		tb->pos_in_item++;
+}
+
+static void balance_leaf_new_nodes_paste_whole(struct tree_balance *tb,
+					       struct item_head *ih,
+					       const char *body,
+					       struct item_head *insert_key,
+					       struct buffer_head **insert_ptr,
+					       int i)
+
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int n = B_NR_ITEMS(tbS0);
+	int leaf_mi;
+	struct item_head *pasted;
+	struct buffer_info bi;
+
+#ifdef CONFIG_REISERFS_CHECK
+	struct item_head *ih_check = item_head(tbS0, tb->item_pos);
+
+	if (!is_direntry_le_ih(ih_check) &&
+	    (tb->pos_in_item != ih_item_len(ih_check) ||
+	    tb->insert_size[0] <= 0))
+		reiserfs_panic(tb->tb_sb,
+			     "PAP-12235",
+			     "pos_in_item must be equal to ih_item_len");
+#endif
+
+	leaf_mi = leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, tb->snum[i],
+				  tb->sbytes[i], tb->S_new[i]);
+
+	RFALSE(leaf_mi,
+	       "PAP-12240: unexpected value returned by leaf_move_items (%d)",
+	       leaf_mi);
+
+	/* paste into item */
+	buffer_info_init_bh(tb, &bi, tb->S_new[i]);
+	leaf_paste_in_buffer(&bi, tb->item_pos - n + tb->snum[i],
+			     tb->pos_in_item, tb->insert_size[0],
+			     body, tb->zeroes_num);
+
+	pasted = item_head(tb->S_new[i], tb->item_pos - n +
+			   tb->snum[i]);
+	if (is_direntry_le_ih(pasted))
+		leaf_paste_entries(&bi, tb->item_pos - n + tb->snum[i],
+				   tb->pos_in_item, 1,
+				   (struct reiserfs_de_head *)body,
+				   body + DEH_SIZE, tb->insert_size[0]);
+
+	/* if we paste to indirect item update ih_free_space */
+	if (is_indirect_le_ih(pasted))
+		set_ih_free_space(pasted, 0);
+
+	tb->zeroes_num = tb->insert_size[0] = 0;
+
+}
+static void balance_leaf_new_nodes_paste(struct tree_balance *tb,
+					 struct item_head *ih,
+					 const char *body,
+					 struct item_head *insert_key,
+					 struct buffer_head **insert_ptr,
+					 int i)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	int n = B_NR_ITEMS(tbS0);
+
+	/* pasted item doesn't fall into S_new[i] */
+	if (n - tb->snum[i] > tb->item_pos) {
+		leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
+				tb->snum[i], tb->sbytes[i], tb->S_new[i]);
+		return;
+	}
+
+	/* pasted item or part if it falls to S_new[i] */
+
+	if (tb->item_pos == n - tb->snum[i] && tb->sbytes[i] != -1)
+		/* we must shift part of the appended item */
+		balance_leaf_new_nodes_paste_shift(tb, ih, body, insert_key,
+						   insert_ptr, i);
+	else
+		/* item falls wholly into S_new[i] */
+		balance_leaf_new_nodes_paste_whole(tb, ih, body, insert_key,
+						   insert_ptr, i);
+}
+
+/* Fill new nodes that appear in place of S[0] */
+static void balance_leaf_new_nodes(struct tree_balance *tb,
+				   struct item_head *ih,
+				   const char *body,
+				   struct item_head *insert_key,
+				   struct buffer_head **insert_ptr,
+				   int flag)
+{
+	int i;
 	for (i = tb->blknum[0] - 2; i >= 0; i--) {
+		BUG_ON(flag != M_INSERT && flag != M_PASTE);
 
-		RFALSE(!snum[i], "PAP-12200: snum[%d] == %d. Must be > 0", i,
-		       snum[i]);
+		RFALSE(!tb->snum[i],
+		       "PAP-12200: snum[%d] == %d. Must be > 0", i,
+		       tb->snum[i]);
 
 		/* here we shift from S to S_new nodes */
 
-		S_new[i] = get_FEB(tb);
+		tb->S_new[i] = get_FEB(tb);
 
 		/* initialized block type and tree level */
-		set_blkh_level(B_BLK_HEAD(S_new[i]), DISK_LEAF_NODE_LEVEL);
-
-		n = B_NR_ITEMS(tbS0);
-
-		switch (flag) {
-		case M_INSERT:	/* insert item */
-
-			if (n - snum[i] < item_pos) {	/* new item or it's part falls to first new node S_new[i] */
-				if (item_pos == n - snum[i] + 1 && sbytes[i] != -1) {	/* part of new item falls into S_new[i] */
-					int old_key_comp, old_len, r_zeros_number;
-					const char *r_body;
-					int version;
-
-					/* Move snum[i]-1 items from S[0] to S_new[i] */
-					leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
-							snum[i] - 1, -1,
-							S_new[i]);
-					/* Remember key component and item length */
-					version = ih_version(ih);
-					old_key_comp = le_ih_k_offset(ih);
-					old_len = ih_item_len(ih);
-
-					/* Calculate key component and item length to insert into S_new[i] */
-					set_le_ih_k_offset(ih, le_ih_k_offset(ih) +
-							   ((old_len - sbytes[i]) << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0)));
-
-					put_ih_item_len(ih, sbytes[i]);
-
-					/* Insert part of the item into S_new[i] before 0-th item */
-					buffer_info_init_bh(tb, &bi, S_new[i]);
-
-					if ((old_len - sbytes[i]) > zeros_num) {
-						r_zeros_number = 0;
-						r_body = body + (old_len - sbytes[i]) - zeros_num;
-					} else {
-						r_body = body;
-						r_zeros_number = zeros_num - (old_len - sbytes[i]);
-						zeros_num -= r_zeros_number;
-					}
-
-					leaf_insert_into_buf(&bi, 0, ih, r_body, r_zeros_number);
-
-					/* Calculate key component and item length to insert into S[i] */
-					set_le_ih_k_offset(ih, old_key_comp);
-					put_ih_item_len(ih, old_len - sbytes[i]);
-					tb->insert_size[0] -= sbytes[i];
-				} else {	/* whole new item falls into S_new[i] */
-
-					/* Shift snum[0] - 1 items to S_new[i] (sbytes[i] of split item) */
-					leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
-							snum[i] - 1, sbytes[i], S_new[i]);
-
-					/* Insert new item into S_new[i] */
-					buffer_info_init_bh(tb, &bi, S_new[i]);
-					leaf_insert_into_buf(&bi, item_pos - n + snum[i] - 1,
-							     ih, body, zeros_num);
-
-					zeros_num = tb->insert_size[0] = 0;
-				}
-			}
-
-			else {	/* new item or it part don't falls into S_new[i] */
+		set_blkh_level(B_BLK_HEAD(tb->S_new[i]), DISK_LEAF_NODE_LEVEL);
+
+		if (flag == M_INSERT)
+			balance_leaf_new_nodes_insert(tb, ih, body, insert_key,
+						      insert_ptr, i);
+		else /* M_PASTE */
+			balance_leaf_new_nodes_paste(tb, ih, body, insert_key,
+						     insert_ptr, i);
+
+		memcpy(insert_key + i, leaf_key(tb->S_new[i], 0), KEY_SIZE);
+		insert_ptr[i] = tb->S_new[i];
+
+		RFALSE(!buffer_journaled(tb->S_new[i])
+		       || buffer_journal_dirty(tb->S_new[i])
+		       || buffer_dirty(tb->S_new[i]),
+		       "PAP-12247: S_new[%d] : (%b)",
+		       i, tb->S_new[i]);
+	}
+}
 
-				leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
-						snum[i], sbytes[i], S_new[i]);
-			}
-			break;
+static void balance_leaf_finish_node_insert(struct tree_balance *tb,
+					    struct item_head *ih,
+					    const char *body)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	struct buffer_info bi;
+	buffer_info_init_tbS0(tb, &bi);
+	leaf_insert_into_buf(&bi, tb->item_pos, ih, body, tb->zeroes_num);
 
-		case M_PASTE:	/* append item */
-
-			if (n - snum[i] <= item_pos) {	/* pasted item or part if it falls to S_new[i] */
-				if (item_pos == n - snum[i] && sbytes[i] != -1) {	/* we must shift part of the appended item */
-					struct item_head *aux_ih;
-
-					RFALSE(ih, "PAP-12210: ih must be 0");
-
-					aux_ih = B_N_PITEM_HEAD(tbS0, item_pos);
-					if (is_direntry_le_ih(aux_ih)) {
-						/* we append to directory item */
-
-						int entry_count;
-
-						entry_count = ih_entry_count(aux_ih);
-
-						if (entry_count - sbytes[i] < pos_in_item && pos_in_item <= entry_count) {
-							/* new directory entry falls into S_new[i] */
-
-							RFALSE(!tb->insert_size[0], "PAP-12215: insert_size is already 0");
-							RFALSE(sbytes[i] - 1 >= entry_count,
-							       "PAP-12220: there are no so much entries (%d), only %d",
-							       sbytes[i] - 1, entry_count);
-
-							/* Shift snum[i]-1 items in whole. Shift sbytes[i] directory entries from directory item number snum[i] */
-							leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], sbytes[i] - 1, S_new[i]);
-							/* Paste given directory entry to directory item */
-							buffer_info_init_bh(tb, &bi, S_new[i]);
-							leaf_paste_in_buffer(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1,
-							     tb->insert_size[0], body, zeros_num);
-							/* paste new directory entry */
-							leaf_paste_entries(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1, 1,
-									   (struct reiserfs_de_head *) body,
-									   body + DEH_SIZE, tb->insert_size[0]);
-							tb->insert_size[0] = 0;
-							pos_in_item++;
-						} else {	/* new directory entry doesn't fall into S_new[i] */
-							leaf_move_items(LEAF_FROM_S_TO_SNEW,tb, snum[i], sbytes[i], S_new[i]);
-						}
-					} else {	/* regular object */
-
-						int n_shift, n_rem, r_zeros_number;
-						const char *r_body;
-
-						RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)) || tb->insert_size[0] <= 0,
-						       "PAP-12225: item too short or insert_size <= 0");
-
-						/* Calculate number of bytes which must be shifted from appended item */
-						n_shift = sbytes[i] - tb->insert_size[0];
-						if (n_shift < 0)
-							n_shift = 0;
-						leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], n_shift, S_new[i]);
-
-						/* Calculate number of bytes which must remain in body after append to S_new[i] */
-						n_rem = tb->insert_size[0] - sbytes[i];
-						if (n_rem < 0)
-							n_rem = 0;
-						/* Append part of body into S_new[0] */
-						buffer_info_init_bh(tb, &bi, S_new[i]);
-						if (n_rem > zeros_num) {
-							r_zeros_number = 0;
-							r_body = body + n_rem - zeros_num;
-						} else {
-							r_body = body;
-							r_zeros_number = zeros_num - n_rem;
-							zeros_num -= r_zeros_number;
-						}
-
-						leaf_paste_in_buffer(&bi, 0, n_shift,
-								     tb->insert_size[0] - n_rem,
-								     r_body, r_zeros_number);
-						{
-							struct item_head *tmp;
-
-							tmp = B_N_PITEM_HEAD(S_new[i], 0);
-							if (is_indirect_le_ih
-							    (tmp)) {
-								set_ih_free_space(tmp, 0);
-								set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + (n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT)));
-							} else {
-								set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + n_rem);
-							}
-						}
-
-						tb->insert_size[0] = n_rem;
-						if (!n_rem)
-							pos_in_item++;
-					}
-				} else
-					/* item falls wholly into S_new[i] */
-				{
-					int leaf_mi;
-					struct item_head *pasted;
+	/* If we insert the first key change the delimiting key */
+	if (tb->item_pos == 0) {
+		if (tb->CFL[0])	/* can be 0 in reiserfsck */
+			replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
 
-#ifdef CONFIG_REISERFS_CHECK
-					struct item_head *ih_check = B_N_PITEM_HEAD(tbS0, item_pos);
-
-					if (!is_direntry_le_ih(ih_check)
-					    && (pos_in_item != ih_item_len(ih_check)
-						|| tb->insert_size[0] <= 0))
-						reiserfs_panic(tb->tb_sb,
-							     "PAP-12235",
-							     "pos_in_item "
-							     "must be equal "
-							     "to ih_item_len");
-#endif				/* CONFIG_REISERFS_CHECK */
-
-					leaf_mi = leaf_move_items(LEAF_FROM_S_TO_SNEW,
-							    tb, snum[i],
-							    sbytes[i],
-							    S_new[i]);
-
-					RFALSE(leaf_mi,
-					       "PAP-12240: unexpected value returned by leaf_move_items (%d)",
-					       leaf_mi);
-
-					/* paste into item */
-					buffer_info_init_bh(tb, &bi, S_new[i]);
-					leaf_paste_in_buffer(&bi,
-							     item_pos - n + snum[i],
-							     pos_in_item,
-							     tb->insert_size[0],
-							     body, zeros_num);
-
-					pasted = B_N_PITEM_HEAD(S_new[i], item_pos - n + snum[i]);
-					if (is_direntry_le_ih(pasted)) {
-						leaf_paste_entries(&bi,
-								   item_pos - n + snum[i],
-								   pos_in_item, 1,
-								   (struct reiserfs_de_head *)body,
-								   body + DEH_SIZE,
-								   tb->insert_size[0]
-						    );
-					}
-
-					/* if we paste to indirect item update ih_free_space */
-					if (is_indirect_le_ih(pasted))
-						set_ih_free_space(pasted, 0);
-					zeros_num = tb->insert_size[0] = 0;
-				}
-			}
+	}
+}
 
-			else {	/* pasted item doesn't fall into S_new[i] */
+static void balance_leaf_finish_node_paste_dirent(struct tree_balance *tb,
+						  struct item_head *ih,
+						  const char *body)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	struct item_head *pasted = item_head(tbS0, tb->item_pos);
+	struct buffer_info bi;
 
-				leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
-						snum[i], sbytes[i], S_new[i]);
-			}
-			break;
-		default:	/* cases d and t */
-			reiserfs_panic(tb->tb_sb, "PAP-12245",
-				       "blknum > 2: unexpected mode: %s(%d)",
-				       (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
+	if (tb->pos_in_item >= 0 && tb->pos_in_item <= ih_entry_count(pasted)) {
+		RFALSE(!tb->insert_size[0],
+		       "PAP-12260: insert_size is 0 already");
+
+		/* prepare space */
+		buffer_info_init_tbS0(tb, &bi);
+		leaf_paste_in_buffer(&bi, tb->item_pos, tb->pos_in_item,
+				     tb->insert_size[0], body, tb->zeroes_num);
+
+		/* paste entry */
+		leaf_paste_entries(&bi, tb->item_pos, tb->pos_in_item, 1,
+				   (struct reiserfs_de_head *)body,
+				   body + DEH_SIZE, tb->insert_size[0]);
+
+		if (!tb->item_pos && !tb->pos_in_item) {
+			RFALSE(!tb->CFL[0] || !tb->L[0],
+			       "PAP-12270: CFL[0]/L[0] must  be specified");
+			if (tb->CFL[0])
+				replace_key(tb, tb->CFL[0], tb->lkey[0],
+					    tbS0, 0);
 		}
 
-		memcpy(insert_key + i, B_N_PKEY(S_new[i], 0), KEY_SIZE);
-		insert_ptr[i] = S_new[i];
+		tb->insert_size[0] = 0;
+	}
+}
+
+static void balance_leaf_finish_node_paste(struct tree_balance *tb,
+					   struct item_head *ih,
+					   const char *body)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+	struct buffer_info bi;
+	struct item_head *pasted = item_head(tbS0, tb->item_pos);
 
-		RFALSE(!buffer_journaled(S_new[i])
-		       || buffer_journal_dirty(S_new[i])
-		       || buffer_dirty(S_new[i]), "PAP-12247: S_new[%d] : (%b)",
-		       i, S_new[i]);
+	/* when directory, may be new entry already pasted */
+	if (is_direntry_le_ih(pasted)) {
+		balance_leaf_finish_node_paste_dirent(tb, ih, body);
+		return;
 	}
 
-	/* if the affected item was not wholly shifted then we perform all necessary operations on that part or whole of the
-	   affected item which remains in S */
-	if (0 <= item_pos && item_pos < tb->s0num) {	/* if we must insert or append into buffer S[0] */
+	/* regular object */
 
-		switch (flag) {
-		case M_INSERT:	/* insert item into S[0] */
-			buffer_info_init_tbS0(tb, &bi);
-			leaf_insert_into_buf(&bi, item_pos, ih, body,
-					     zeros_num);
+	if (tb->pos_in_item == ih_item_len(pasted)) {
+		RFALSE(tb->insert_size[0] <= 0,
+		       "PAP-12275: insert size must not be %d",
+		       tb->insert_size[0]);
+		buffer_info_init_tbS0(tb, &bi);
+		leaf_paste_in_buffer(&bi, tb->item_pos,
+				     tb->pos_in_item, tb->insert_size[0], body,
+				     tb->zeroes_num);
 
-			/* If we insert the first key change the delimiting key */
-			if (item_pos == 0) {
-				if (tb->CFL[0])	/* can be 0 in reiserfsck */
-					replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
-			}
-			break;
+		if (is_indirect_le_ih(pasted))
+			set_ih_free_space(pasted, 0);
 
-		case M_PASTE:{	/* append item in S[0] */
-				struct item_head *pasted;
-
-				pasted = B_N_PITEM_HEAD(tbS0, item_pos);
-				/* when directory, may be new entry already pasted */
-				if (is_direntry_le_ih(pasted)) {
-					if (pos_in_item >= 0 && pos_in_item <= ih_entry_count(pasted)) {
-
-						RFALSE(!tb->insert_size[0],
-						       "PAP-12260: insert_size is 0 already");
-
-						/* prepare space */
-						buffer_info_init_tbS0(tb, &bi);
-						leaf_paste_in_buffer(&bi, item_pos, pos_in_item,
-								     tb->insert_size[0], body,
-								     zeros_num);
-
-						/* paste entry */
-						leaf_paste_entries(&bi, item_pos, pos_in_item, 1,
-								   (struct reiserfs_de_head *)body,
-								   body + DEH_SIZE,
-								   tb->insert_size[0]);
-						if (!item_pos && !pos_in_item) {
-							RFALSE(!tb->CFL[0] || !tb->L[0],
-							       "PAP-12270: CFL[0]/L[0] must be specified");
-							if (tb->CFL[0])
-								replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
-						}
-						tb->insert_size[0] = 0;
-					}
-				} else {	/* regular object */
-					if (pos_in_item == ih_item_len(pasted)) {
-
-						RFALSE(tb->insert_size[0] <= 0,
-						       "PAP-12275: insert size must not be %d",
-						       tb->insert_size[0]);
-						buffer_info_init_tbS0(tb, &bi);
-						leaf_paste_in_buffer(&bi, item_pos, pos_in_item,
-								     tb->insert_size[0], body, zeros_num);
-
-						if (is_indirect_le_ih(pasted)) {
-#if 0
-							RFALSE(tb->
-							       insert_size[0] !=
-							       UNFM_P_SIZE,
-							       "PAP-12280: insert_size for indirect item must be %d, not %d",
-							       UNFM_P_SIZE,
-							       tb->
-							       insert_size[0]);
-#endif
-							set_ih_free_space(pasted, 0);
-						}
-						tb->insert_size[0] = 0;
-					}
+		tb->insert_size[0] = 0;
+	}
 #ifdef CONFIG_REISERFS_CHECK
-					else {
-						if (tb->insert_size[0]) {
-							print_cur_tb("12285");
-							reiserfs_panic(tb->tb_sb,
-							    "PAP-12285",
-							    "insert_size "
-							    "must be 0 "
-							    "(%d)",
-							    tb->insert_size[0]);
-						}
-					}
-#endif				/* CONFIG_REISERFS_CHECK */
-
-				}
-			}	/* case M_PASTE: */
+	else if (tb->insert_size[0]) {
+		print_cur_tb("12285");
+		reiserfs_panic(tb->tb_sb, "PAP-12285",
+		    "insert_size must be 0 (%d)", tb->insert_size[0]);
+	}
+#endif
+}
+
+/*
+ * if the affected item was not wholly shifted then we
+ * perform all necessary operations on that part or whole
+ * of the affected item which remains in S
+ */
+static void balance_leaf_finish_node(struct tree_balance *tb,
+				      struct item_head *ih,
+				      const char *body, int flag)
+{
+	/* if we must insert or append into buffer S[0] */
+	if (0 <= tb->item_pos && tb->item_pos < tb->s0num) {
+		if (flag == M_INSERT)
+			balance_leaf_finish_node_insert(tb, ih, body);
+		else /* M_PASTE */
+			balance_leaf_finish_node_paste(tb, ih, body);
+	}
+}
+
+/**
+ * balance_leaf - reiserfs tree balancing algorithm
+ * @tb: tree balance state
+ * @ih: item header of inserted item (little endian)
+ * @body: body of inserted item or bytes to paste
+ * @flag: i - insert, d - delete, c - cut, p - paste (see do_balance)
+ * passed back:
+ * @insert_key: key to insert new nodes
+ * @insert_ptr: array of nodes to insert at the next level
+ *
+ * In our processing of one level we sometimes determine what must be
+ * inserted into the next higher level.  This insertion consists of a
+ * key or two keys and their corresponding pointers.
+ */
+static int balance_leaf(struct tree_balance *tb, struct item_head *ih,
+			const char *body, int flag,
+			struct item_head *insert_key,
+			struct buffer_head **insert_ptr)
+{
+	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
+
+	PROC_INFO_INC(tb->tb_sb, balance_at[0]);
+
+	/* Make balance in case insert_size[0] < 0 */
+	if (tb->insert_size[0] < 0)
+		return balance_leaf_when_delete(tb, flag);
+
+	tb->item_pos = PATH_LAST_POSITION(tb->tb_path),
+	tb->pos_in_item = tb->tb_path->pos_in_item,
+	tb->zeroes_num = 0;
+	if (flag == M_INSERT && !body)
+		tb->zeroes_num = ih_item_len(ih);
+
+	/*
+	 * for indirect item pos_in_item is measured in unformatted node
+	 * pointers. Recalculate to bytes
+	 */
+	if (flag != M_INSERT
+	    && is_indirect_le_ih(item_head(tbS0, tb->item_pos)))
+		tb->pos_in_item *= UNFM_P_SIZE;
+
+	balance_leaf_left(tb, ih, body, flag);
+
+	/* tb->lnum[0] > 0 */
+	/* Calculate new item position */
+	tb->item_pos -= (tb->lnum[0] - ((tb->lbytes != -1) ? 1 : 0));
+
+	balance_leaf_right(tb, ih, body, flag);
+
+	/* tb->rnum[0] > 0 */
+	RFALSE(tb->blknum[0] > 3,
+	       "PAP-12180: blknum can not be %d. It must be <= 3", tb->blknum[0]);
+	RFALSE(tb->blknum[0] < 0,
+	       "PAP-12185: blknum can not be %d. It must be >= 0", tb->blknum[0]);
+
+	/*
+	 * if while adding to a node we discover that it is possible to split
+	 * it in two, and merge the left part into the left neighbor and the
+	 * right part into the right neighbor, eliminating the node
+	 */
+	if (tb->blknum[0] == 0) {	/* node S[0] is empty now */
+
+		RFALSE(!tb->lnum[0] || !tb->rnum[0],
+		       "PAP-12190: lnum and rnum must not be zero");
+		/*
+		 * if insertion was done before 0-th position in R[0], right
+		 * delimiting key of the tb->L[0]'s and left delimiting key are
+		 * not set correctly
+		 */
+		if (tb->CFL[0]) {
+			if (!tb->CFR[0])
+				reiserfs_panic(tb->tb_sb, "vs-12195",
+					       "CFR not initialized");
+			copy_key(internal_key(tb->CFL[0], tb->lkey[0]),
+				 internal_key(tb->CFR[0], tb->rkey[0]));
+			do_balance_mark_internal_dirty(tb, tb->CFL[0], 0);
 		}
+
+		reiserfs_invalidate_buffer(tb, tbS0);
+		return 0;
 	}
+
+	balance_leaf_new_nodes(tb, ih, body, insert_key, insert_ptr, flag);
+
+	balance_leaf_finish_node(tb, ih, body, flag);
+
 #ifdef CONFIG_REISERFS_CHECK
 	if (flag == M_PASTE && tb->insert_size[0]) {
 		print_cur_tb("12290");
@@ -1137,9 +1454,11 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih,	/* item h
 			       "PAP-12290", "insert_size is still not 0 (%d)",
 			       tb->insert_size[0]);
 	}
-#endif				/* CONFIG_REISERFS_CHECK */
+#endif
+
+	/* Leaf level of the tree is balanced (end of balance_leaf) */
 	return 0;
-}				/* Leaf level of the tree is balanced (end of balance_leaf) */
+}
 
 /* Make empty node */
 void make_empty_node(struct buffer_info *bi)
@@ -1178,9 +1497,7 @@ struct buffer_head *get_FEB(struct tree_balance *tb)
 	return tb->used[i];
 }
 
-/* This is now used because reiserfs_free_block has to be able to
-** schedule.
-*/
+/* This is now used because reiserfs_free_block has to be able to schedule. */
 static void store_thrown(struct tree_balance *tb, struct buffer_head *bh)
 {
 	int i;
@@ -1246,10 +1563,10 @@ void replace_key(struct tree_balance *tb, struct buffer_head *dest, int n_dest,
 
 	if (B_IS_ITEMS_LEVEL(src))
 		/* source buffer contains leaf node */
-		memcpy(B_N_PDELIM_KEY(dest, n_dest), B_N_PITEM_HEAD(src, n_src),
+		memcpy(internal_key(dest, n_dest), item_head(src, n_src),
 		       KEY_SIZE);
 	else
-		memcpy(B_N_PDELIM_KEY(dest, n_dest), B_N_PDELIM_KEY(src, n_src),
+		memcpy(internal_key(dest, n_dest), internal_key(src, n_src),
 		       KEY_SIZE);
 
 	do_balance_mark_internal_dirty(tb, dest, 0);
@@ -1335,8 +1652,10 @@ static int check_before_balancing(struct tree_balance *tb)
 			       "mount point.");
 	}
 
-	/* double check that buffers that we will modify are unlocked. (fix_nodes should already have
-	   prepped all of these for us). */
+	/*
+	 * double check that buffers that we will modify are unlocked.
+	 * (fix_nodes should already have prepped all of these for us).
+	 */
 	if (tb->lnum[0]) {
 		retval |= locked_or_not_in_tree(tb, tb->L[0], "L[0]");
 		retval |= locked_or_not_in_tree(tb, tb->FL[0], "FL[0]");
@@ -1429,49 +1748,51 @@ static void check_internal_levels(struct tree_balance *tb)
 
 #endif
 
-/* Now we have all of the buffers that must be used in balancing of
-   the tree.  We rely on the assumption that schedule() will not occur
-   while do_balance works. ( Only interrupt handlers are acceptable.)
-   We balance the tree according to the analysis made before this,
-   using buffers already obtained.  For SMP support it will someday be
-   necessary to add ordered locking of tb. */
-
-/* Some interesting rules of balancing:
-
-   we delete a maximum of two nodes per level per balancing: we never
-   delete R, when we delete two of three nodes L, S, R then we move
-   them into R.
-
-   we only delete L if we are deleting two nodes, if we delete only
-   one node we delete S
-
-   if we shift leaves then we shift as much as we can: this is a
-   deliberate policy of extremism in node packing which results in
-   higher average utilization after repeated random balance operations
-   at the cost of more memory copies and more balancing as a result of
-   small insertions to full nodes.
-
-   if we shift internal nodes we try to evenly balance the node
-   utilization, with consequent less balancing at the cost of lower
-   utilization.
-
-   one could argue that the policy for directories in leaves should be
-   that of internal nodes, but we will wait until another day to
-   evaluate this....  It would be nice to someday measure and prove
-   these assumptions as to what is optimal....
+/*
+ * Now we have all of the buffers that must be used in balancing of
+ * the tree.  We rely on the assumption that schedule() will not occur
+ * while do_balance works. ( Only interrupt handlers are acceptable.)
+ * We balance the tree according to the analysis made before this,
+ * using buffers already obtained.  For SMP support it will someday be
+ * necessary to add ordered locking of tb.
+ */
 
-*/
+/*
+ * Some interesting rules of balancing:
+ * we delete a maximum of two nodes per level per balancing: we never
+ * delete R, when we delete two of three nodes L, S, R then we move
+ * them into R.
+ *
+ * we only delete L if we are deleting two nodes, if we delete only
+ * one node we delete S
+ *
+ * if we shift leaves then we shift as much as we can: this is a
+ * deliberate policy of extremism in node packing which results in
+ * higher average utilization after repeated random balance operations
+ * at the cost of more memory copies and more balancing as a result of
+ * small insertions to full nodes.
+ *
+ * if we shift internal nodes we try to evenly balance the node
+ * utilization, with consequent less balancing at the cost of lower
+ * utilization.
+ *
+ * one could argue that the policy for directories in leaves should be
+ * that of internal nodes, but we will wait until another day to
+ * evaluate this....  It would be nice to someday measure and prove
+ * these assumptions as to what is optimal....
+ */
 
 static inline void do_balance_starts(struct tree_balance *tb)
 {
-	/* use print_cur_tb() to see initial state of struct
-	   tree_balance */
+	/* use print_cur_tb() to see initial state of struct tree_balance */
 
 	/* store_print_tb (tb); */
 
 	/* do not delete, just comment it out */
-/*    print_tb(flag, PATH_LAST_POSITION(tb->tb_path), tb->tb_path->pos_in_item, tb,
-	     "check");*/
+	/*
+	print_tb(flag, PATH_LAST_POSITION(tb->tb_path),
+		 tb->tb_path->pos_in_item, tb, "check");
+	*/
 	RFALSE(check_before_balancing(tb), "PAP-12340: locked buffers in TB");
 #ifdef CONFIG_REISERFS_CHECK
 	REISERFS_SB(tb->tb_sb)->cur_tb = tb;
@@ -1487,9 +1808,10 @@ static inline void do_balance_completed(struct tree_balance *tb)
 	REISERFS_SB(tb->tb_sb)->cur_tb = NULL;
 #endif
 
-	/* reiserfs_free_block is no longer schedule safe.  So, we need to
-	 ** put the buffers we want freed on the thrown list during do_balance,
-	 ** and then free them now
+	/*
+	 * reiserfs_free_block is no longer schedule safe.  So, we need to
+	 * put the buffers we want freed on the thrown list during do_balance,
+	 * and then free them now
 	 */
 
 	REISERFS_SB(tb->tb_sb)->s_do_balance++;
@@ -1500,36 +1822,40 @@ static inline void do_balance_completed(struct tree_balance *tb)
 	free_thrown(tb);
 }
 
-void do_balance(struct tree_balance *tb,	/* tree_balance structure */
-		struct item_head *ih,	/* item header of inserted item */
-		const char *body,	/* body  of inserted item or bytes to paste */
-		int flag)
-{				/* i - insert, d - delete
-				   c - cut, p - paste
-
-				   Cut means delete part of an item
-				   (includes removing an entry from a
-				   directory).
-
-				   Delete means delete whole item.
-
-				   Insert means add a new item into the
-				   tree.
-
-				   Paste means to append to the end of an
-				   existing file or to insert a directory
-				   entry.  */
-	int child_pos,		/* position of a child node in its parent */
-	 h;			/* level of the tree being processed */
-	struct item_head insert_key[2];	/* in our processing of one level
-					   we sometimes determine what
-					   must be inserted into the next
-					   higher level.  This insertion
-					   consists of a key or two keys
-					   and their corresponding
-					   pointers */
-	struct buffer_head *insert_ptr[2];	/* inserted node-ptrs for the next
-						   level */
+/*
+ * do_balance - balance the tree
+ *
+ * @tb: tree_balance structure
+ * @ih: item header of inserted item
+ * @body: body of inserted item or bytes to paste
+ * @flag: 'i' - insert, 'd' - delete, 'c' - cut, 'p' paste
+ *
+ * Cut means delete part of an item (includes removing an entry from a
+ * directory).
+ *
+ * Delete means delete whole item.
+ *
+ * Insert means add a new item into the tree.
+ *
+ * Paste means to append to the end of an existing file or to
+ * insert a directory entry.
+ */
+void do_balance(struct tree_balance *tb, struct item_head *ih,
+		const char *body, int flag)
+{
+	int child_pos;		/* position of a child node in its parent */
+	int h;			/* level of the tree being processed */
+
+	/*
+	 * in our processing of one level we sometimes determine what
+	 * must be inserted into the next higher level.  This insertion
+	 * consists of a key or two keys and their corresponding
+	 * pointers
+	 */
+	struct item_head insert_key[2];
+
+	/* inserted node-ptrs for the next level */
+	struct buffer_head *insert_ptr[2];
 
 	tb->tb_mode = flag;
 	tb->need_balance_dirty = 0;
@@ -1546,12 +1872,14 @@ void do_balance(struct tree_balance *tb,	/* tree_balance structure */
 		return;
 	}
 
-	atomic_inc(&(fs_generation(tb->tb_sb)));
+	atomic_inc(&fs_generation(tb->tb_sb));
 	do_balance_starts(tb);
 
-	/* balance leaf returns 0 except if combining L R and S into
-	   one node.  see balance_internal() for explanation of this
-	   line of code. */
+	/*
+	 * balance_leaf returns 0 except if combining L R and S into
+	 * one node.  see balance_internal() for explanation of this
+	 * line of code.
+	 */
 	child_pos = PATH_H_B_ITEM_ORDER(tb->tb_path, 0) +
 	    balance_leaf(tb, ih, body, flag, insert_key, insert_ptr);
 
@@ -1561,9 +1889,8 @@ void do_balance(struct tree_balance *tb,	/* tree_balance structure */
 
 	/* Balance internal level of the tree. */
 	for (h = 1; h < MAX_HEIGHT && tb->insert_size[h]; h++)
-		child_pos =
-		    balance_internal(tb, h, child_pos, insert_key, insert_ptr);
+		child_pos = balance_internal(tb, h, child_pos, insert_key,
+					     insert_ptr);
 
 	do_balance_completed(tb);
-
 }
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index ed58d843d57..db9e80ba53a 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -15,20 +15,20 @@
 #include <linux/quotaops.h>
 
 /*
-** We pack the tails of files on file close, not at the time they are written.
-** This implies an unnecessary copy of the tail and an unnecessary indirect item
-** insertion/balancing, for files that are written in one write.
-** It avoids unnecessary tail packings (balances) for files that are written in
-** multiple writes and are small enough to have tails.
-**
-** file_release is called by the VFS layer when the file is closed.  If
-** this is the last open file descriptor, and the file
-** small enough to have a tail, and the tail is currently in an
-** unformatted node, the tail is converted back into a direct item.
-**
-** We use reiserfs_truncate_file to pack the tail, since it already has
-** all the conditions coded.
-*/
+ * We pack the tails of files on file close, not at the time they are written.
+ * This implies an unnecessary copy of the tail and an unnecessary indirect item
+ * insertion/balancing, for files that are written in one write.
+ * It avoids unnecessary tail packings (balances) for files that are written in
+ * multiple writes and are small enough to have tails.
+ *
+ * file_release is called by the VFS layer when the file is closed.  If
+ * this is the last open file descriptor, and the file
+ * small enough to have a tail, and the tail is currently in an
+ * unformatted node, the tail is converted back into a direct item.
+ *
+ * We use reiserfs_truncate_file to pack the tail, since it already has
+ * all the conditions coded.
+ */
 static int reiserfs_file_release(struct inode *inode, struct file *filp)
 {
 
@@ -41,10 +41,10 @@ static int reiserfs_file_release(struct inode *inode, struct file *filp)
         if (atomic_add_unless(&REISERFS_I(inode)->openers, -1, 1))
 		return 0;
 
-	mutex_lock(&(REISERFS_I(inode)->tailpack));
+	mutex_lock(&REISERFS_I(inode)->tailpack);
 
         if (!atomic_dec_and_test(&REISERFS_I(inode)->openers)) {
-		mutex_unlock(&(REISERFS_I(inode)->tailpack));
+		mutex_unlock(&REISERFS_I(inode)->tailpack);
 		return 0;
 	}
 
@@ -52,31 +52,35 @@ static int reiserfs_file_release(struct inode *inode, struct file *filp)
 	if ((!(REISERFS_I(inode)->i_flags & i_pack_on_close_mask) ||
 	     !tail_has_to_be_packed(inode)) &&
 	    REISERFS_I(inode)->i_prealloc_count <= 0) {
-		mutex_unlock(&(REISERFS_I(inode)->tailpack));
+		mutex_unlock(&REISERFS_I(inode)->tailpack);
 		return 0;
 	}
 
 	reiserfs_write_lock(inode->i_sb);
-	/* freeing preallocation only involves relogging blocks that
+	/*
+	 * freeing preallocation only involves relogging blocks that
 	 * are already in the current transaction.  preallocation gets
 	 * freed at the end of each transaction, so it is impossible for
 	 * us to log any additional blocks (including quota blocks)
 	 */
 	err = journal_begin(&th, inode->i_sb, 1);
 	if (err) {
-		/* uh oh, we can't allow the inode to go away while there
+		/*
+		 * uh oh, we can't allow the inode to go away while there
 		 * is still preallocation blocks pending.  Try to join the
 		 * aborted transaction
 		 */
 		jbegin_failure = err;
-		err = journal_join_abort(&th, inode->i_sb, 1);
+		err = journal_join_abort(&th, inode->i_sb);
 
 		if (err) {
-			/* hmpf, our choices here aren't good.  We can pin the inode
-			 * which will disallow unmount from every happening, we can
-			 * do nothing, which will corrupt random memory on unmount,
-			 * or we can forcibly remove the file from the preallocation
-			 * list, which will leak blocks on disk.  Lets pin the inode
+			/*
+			 * hmpf, our choices here aren't good.  We can pin
+			 * the inode which will disallow unmount from ever
+			 * happening, we can do nothing, which will corrupt
+			 * random memory on unmount, or we can forcibly
+			 * remove the file from the preallocation list, which
+			 * will leak blocks on disk.  Lets pin the inode
 			 * and let the admin know what is going on.
 			 */
 			igrab(inode);
@@ -92,7 +96,7 @@ static int reiserfs_file_release(struct inode *inode, struct file *filp)
 #ifdef REISERFS_PREALLOCATE
 	reiserfs_discard_prealloc(&th, inode);
 #endif
-	err = journal_end(&th, inode->i_sb, 1);
+	err = journal_end(&th);
 
 	/* copy back the error code from journal_begin */
 	if (!err)
@@ -102,35 +106,38 @@ static int reiserfs_file_release(struct inode *inode, struct file *filp)
 	    (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) &&
 	    tail_has_to_be_packed(inode)) {
 
-		/* if regular file is released by last holder and it has been
-		   appended (we append by unformatted node only) or its direct
-		   item(s) had to be converted, then it may have to be
-		   indirect2direct converted */
+		/*
+		 * if regular file is released by last holder and it has been
+		 * appended (we append by unformatted node only) or its direct
+		 * item(s) had to be converted, then it may have to be
+		 * indirect2direct converted
+		 */
 		err = reiserfs_truncate_file(inode, 0);
 	}
-      out:
+out:
 	reiserfs_write_unlock(inode->i_sb);
-	mutex_unlock(&(REISERFS_I(inode)->tailpack));
+	mutex_unlock(&REISERFS_I(inode)->tailpack);
 	return err;
 }
 
 static int reiserfs_file_open(struct inode *inode, struct file *file)
 {
 	int err = dquot_file_open(inode, file);
+
+	/* somebody might be tailpacking on final close; wait for it */
         if (!atomic_inc_not_zero(&REISERFS_I(inode)->openers)) {
-		/* somebody might be tailpacking on final close; wait for it */
-		mutex_lock(&(REISERFS_I(inode)->tailpack));
+		mutex_lock(&REISERFS_I(inode)->tailpack);
 		atomic_inc(&REISERFS_I(inode)->openers);
-		mutex_unlock(&(REISERFS_I(inode)->tailpack));
+		mutex_unlock(&REISERFS_I(inode)->tailpack);
 	}
 	return err;
 }
 
 void reiserfs_vfs_truncate_file(struct inode *inode)
 {
-	mutex_lock(&(REISERFS_I(inode)->tailpack));
+	mutex_lock(&REISERFS_I(inode)->tailpack);
 	reiserfs_truncate_file(inode, 1);
-	mutex_unlock(&(REISERFS_I(inode)->tailpack));
+	mutex_unlock(&REISERFS_I(inode)->tailpack);
 }
 
 /* Sync a reiserfs file. */
@@ -205,10 +212,11 @@ int reiserfs_commit_page(struct inode *inode, struct page *page,
 			set_buffer_uptodate(bh);
 			if (logit) {
 				reiserfs_prepare_for_journal(s, bh, 1);
-				journal_mark_dirty(&th, s, bh);
+				journal_mark_dirty(&th, bh);
 			} else if (!buffer_dirty(bh)) {
 				mark_buffer_dirty(bh);
-				/* do data=ordered on any page past the end
+				/*
+				 * do data=ordered on any page past the end
 				 * of file and any buffer marked BH_New.
 				 */
 				if (reiserfs_data_ordered(inode->i_sb) &&
@@ -219,8 +227,8 @@ int reiserfs_commit_page(struct inode *inode, struct page *page,
 		}
 	}
 	if (logit) {
-		ret = journal_end(&th, s, bh_per_page + 1);
-	      drop_write_lock:
+		ret = journal_end(&th);
+drop_write_lock:
 		reiserfs_write_unlock(s);
 	}
 	/*
@@ -235,8 +243,8 @@ int reiserfs_commit_page(struct inode *inode, struct page *page,
 }
 
 const struct file_operations reiserfs_file_operations = {
-	.read = do_sync_read,
-	.write = do_sync_write,
+	.read = new_sync_read,
+	.write = new_sync_write,
 	.unlocked_ioctl = reiserfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = reiserfs_compat_ioctl,
@@ -245,10 +253,10 @@ const struct file_operations reiserfs_file_operations = {
 	.open = reiserfs_file_open,
 	.release = reiserfs_file_release,
 	.fsync = reiserfs_sync_file,
-	.aio_read = generic_file_aio_read,
-	.aio_write = generic_file_aio_write,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
 	.splice_read = generic_file_splice_read,
-	.splice_write = generic_file_splice_write,
+	.splice_write = iter_file_splice_write,
 	.llseek = generic_file_llseek,
 };
 
diff --git a/fs/reiserfs/fix_node.c b/fs/reiserfs/fix_node.c
index dc4d4153031..6b0ddb2a909 100644
--- a/fs/reiserfs/fix_node.c
+++ b/fs/reiserfs/fix_node.c
@@ -2,59 +2,32 @@
  * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
  */
 
-/**
- ** old_item_num
- ** old_entry_num
- ** set_entry_sizes
- ** create_virtual_node
- ** check_left
- ** check_right
- ** directory_part_size
- ** get_num_ver
- ** set_parameters
- ** is_leaf_removable
- ** are_leaves_removable
- ** get_empty_nodes
- ** get_lfree
- ** get_rfree
- ** is_left_neighbor_in_cache
- ** decrement_key
- ** get_far_parent
- ** get_parents
- ** can_node_be_removed
- ** ip_check_balance
- ** dc_check_balance_internal
- ** dc_check_balance_leaf
- ** dc_check_balance
- ** check_balance
- ** get_direct_parent
- ** get_neighbors
- ** fix_nodes
- **
- **
- **/
-
 #include <linux/time.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include "reiserfs.h"
 #include <linux/buffer_head.h>
 
-/* To make any changes in the tree we find a node, that contains item
-   to be changed/deleted or position in the node we insert a new item
-   to. We call this node S. To do balancing we need to decide what we
-   will shift to left/right neighbor, or to a new node, where new item
-   will be etc. To make this analysis simpler we build virtual
-   node. Virtual node is an array of items, that will replace items of
-   node S. (For instance if we are going to delete an item, virtual
-   node does not contain it). Virtual node keeps information about
-   item sizes and types, mergeability of first and last items, sizes
-   of all entries in directory item. We use this array of items when
-   calculating what we can shift to neighbors and how many nodes we
-   have to have if we do not any shiftings, if we shift to left/right
-   neighbor or to both. */
-
-/* taking item number in virtual node, returns number of item, that it has in source buffer */
+/*
+ * To make any changes in the tree we find a node that contains item
+ * to be changed/deleted or position in the node we insert a new item
+ * to. We call this node S. To do balancing we need to decide what we
+ * will shift to left/right neighbor, or to a new node, where new item
+ * will be etc. To make this analysis simpler we build virtual
+ * node. Virtual node is an array of items, that will replace items of
+ * node S. (For instance if we are going to delete an item, virtual
+ * node does not contain it). Virtual node keeps information about
+ * item sizes and types, mergeability of first and last items, sizes
+ * of all entries in directory item. We use this array of items when
+ * calculating what we can shift to neighbors and how many nodes we
+ * have to have if we do not any shiftings, if we shift to left/right
+ * neighbor or to both.
+ */
+
+/*
+ * Takes item number in virtual node, returns number of item
+ * that it has in source buffer
+ */
 static inline int old_item_num(int new_num, int affected_item_num, int mode)
 {
 	if (mode == M_PASTE || mode == M_CUT || new_num < affected_item_num)
@@ -105,14 +78,17 @@ static void create_virtual_node(struct tree_balance *tb, int h)
 	vn->vn_free_ptr += vn->vn_nr_item * sizeof(struct virtual_item);
 
 	/* first item in the node */
-	ih = B_N_PITEM_HEAD(Sh, 0);
+	ih = item_head(Sh, 0);
 
 	/* define the mergeability for 0-th item (if it is not being deleted) */
-	if (op_is_left_mergeable(&(ih->ih_key), Sh->b_size)
+	if (op_is_left_mergeable(&ih->ih_key, Sh->b_size)
 	    && (vn->vn_mode != M_DELETE || vn->vn_affected_item_num))
 		vn->vn_vi[0].vi_type |= VI_TYPE_LEFT_MERGEABLE;
 
-	/* go through all items those remain in the virtual node (except for the new (inserted) one) */
+	/*
+	 * go through all items that remain in the virtual
+	 * node (except for the new (inserted) one)
+	 */
 	for (new_num = 0; new_num < vn->vn_nr_item; new_num++) {
 		int j;
 		struct virtual_item *vi = vn->vn_vi + new_num;
@@ -128,11 +104,13 @@ static void create_virtual_node(struct tree_balance *tb, int h)
 
 		vi->vi_item_len += ih_item_len(ih + j) + IH_SIZE;
 		vi->vi_ih = ih + j;
-		vi->vi_item = B_I_PITEM(Sh, ih + j);
+		vi->vi_item = ih_item_body(Sh, ih + j);
 		vi->vi_uarea = vn->vn_free_ptr;
 
-		// FIXME: there is no check, that item operation did not
-		// consume too much memory
+		/*
+		 * FIXME: there is no check that item operation did not
+		 * consume too much memory
+		 */
 		vn->vn_free_ptr +=
 		    op_create_vi(vn, vi, is_affected, tb->insert_size[0]);
 		if (tb->vn_buf + tb->vn_buf_size < vn->vn_free_ptr)
@@ -145,7 +123,8 @@ static void create_virtual_node(struct tree_balance *tb, int h)
 
 		if (vn->vn_mode == M_PASTE || vn->vn_mode == M_CUT) {
 			vn->vn_vi[new_num].vi_item_len += tb->insert_size[0];
-			vi->vi_new_data = vn->vn_data;	// pointer to data which is going to be pasted
+			/* pointer to data which is going to be pasted */
+			vi->vi_new_data = vn->vn_data;
 		}
 	}
 
@@ -164,11 +143,14 @@ static void create_virtual_node(struct tree_balance *tb, int h)
 			     tb->insert_size[0]);
 	}
 
-	/* set right merge flag we take right delimiting key and check whether it is a mergeable item */
+	/*
+	 * set right merge flag we take right delimiting key and
+	 * check whether it is a mergeable item
+	 */
 	if (tb->CFR[0]) {
 		struct reiserfs_key *key;
 
-		key = B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0]);
+		key = internal_key(tb->CFR[0], tb->rkey[0]);
 		if (op_is_left_mergeable(key, Sh->b_size)
 		    && (vn->vn_mode != M_DELETE
 			|| vn->vn_affected_item_num != B_NR_ITEMS(Sh) - 1))
@@ -179,12 +161,19 @@ static void create_virtual_node(struct tree_balance *tb, int h)
 		if (op_is_left_mergeable(key, Sh->b_size) &&
 		    !(vn->vn_mode != M_DELETE
 		      || vn->vn_affected_item_num != B_NR_ITEMS(Sh) - 1)) {
-			/* we delete last item and it could be merged with right neighbor's first item */
+			/*
+			 * we delete last item and it could be merged
+			 * with right neighbor's first item
+			 */
 			if (!
 			    (B_NR_ITEMS(Sh) == 1
-			     && is_direntry_le_ih(B_N_PITEM_HEAD(Sh, 0))
-			     && I_ENTRY_COUNT(B_N_PITEM_HEAD(Sh, 0)) == 1)) {
-				/* node contains more than 1 item, or item is not directory item, or this item contains more than 1 entry */
+			     && is_direntry_le_ih(item_head(Sh, 0))
+			     && ih_entry_count(item_head(Sh, 0)) == 1)) {
+				/*
+				 * node contains more than 1 item, or item
+				 * is not directory item, or this item
+				 * contains more than 1 entry
+				 */
 				print_block(Sh, 0, -1, -1);
 				reiserfs_panic(tb->tb_sb, "vs-8045",
 					       "rdkey %k, affected item==%d "
@@ -198,8 +187,10 @@ static void create_virtual_node(struct tree_balance *tb, int h)
 	}
 }
 
-/* using virtual node check, how many items can be shifted to left
-   neighbor */
+/*
+ * Using virtual node check, how many items can be
+ * shifted to left neighbor
+ */
 static void check_left(struct tree_balance *tb, int h, int cur_free)
 {
 	int i;
@@ -259,9 +250,13 @@ static void check_left(struct tree_balance *tb, int h, int cur_free)
 		}
 
 		/* the item cannot be shifted entirely, try to split it */
-		/* check whether L[0] can hold ih and at least one byte of the item body */
+		/*
+		 * check whether L[0] can hold ih and at least one byte
+		 * of the item body
+		 */
+
+		/* cannot shift even a part of the current item */
 		if (cur_free <= ih_size) {
-			/* cannot shift even a part of the current item */
 			tb->lbytes = -1;
 			return;
 		}
@@ -278,8 +273,10 @@ static void check_left(struct tree_balance *tb, int h, int cur_free)
 	return;
 }
 
-/* using virtual node check, how many items can be shifted to right
-   neighbor */
+/*
+ * Using virtual node check, how many items can be
+ * shifted to right neighbor
+ */
 static void check_right(struct tree_balance *tb, int h, int cur_free)
 {
 	int i;
@@ -338,13 +335,21 @@ static void check_right(struct tree_balance *tb, int h, int cur_free)
 			continue;
 		}
 
-		/* check whether R[0] can hold ih and at least one byte of the item body */
-		if (cur_free <= ih_size) {	/* cannot shift even a part of the current item */
+		/*
+		 * check whether R[0] can hold ih and at least one
+		 * byte of the item body
+		 */
+
+		/* cannot shift even a part of the current item */
+		if (cur_free <= ih_size) {
 			tb->rbytes = -1;
 			return;
 		}
 
-		/* R[0] can hold the header of the item and at least one byte of its body */
+		/*
+		 * R[0] can hold the header of the item and at least
+		 * one byte of its body
+		 */
 		cur_free -= ih_size;	/* cur_free is still > 0 */
 
 		tb->rbytes = op_check_right(vi, cur_free);
@@ -361,45 +366,64 @@ static void check_right(struct tree_balance *tb, int h, int cur_free)
 /*
  * from - number of items, which are shifted to left neighbor entirely
  * to - number of item, which are shifted to right neighbor entirely
- * from_bytes - number of bytes of boundary item (or directory entries) which are shifted to left neighbor
- * to_bytes - number of bytes of boundary item (or directory entries) which are shifted to right neighbor */
+ * from_bytes - number of bytes of boundary item (or directory entries)
+ *              which are shifted to left neighbor
+ * to_bytes - number of bytes of boundary item (or directory entries)
+ *            which are shifted to right neighbor
+ */
 static int get_num_ver(int mode, struct tree_balance *tb, int h,
 		       int from, int from_bytes,
 		       int to, int to_bytes, short *snum012, int flow)
 {
 	int i;
 	int cur_free;
-	//    int bytes;
 	int units;
 	struct virtual_node *vn = tb->tb_vn;
-	//    struct virtual_item * vi;
-
 	int total_node_size, max_node_size, current_item_size;
 	int needed_nodes;
-	int start_item,		/* position of item we start filling node from */
-	 end_item,		/* position of item we finish filling node by */
-	 start_bytes,		/* number of first bytes (entries for directory) of start_item-th item
-				   we do not include into node that is being filled */
-	 end_bytes;		/* number of last bytes (entries for directory) of end_item-th item
-				   we do node include into node that is being filled */
-	int split_item_positions[2];	/* these are positions in virtual item of
-					   items, that are split between S[0] and
-					   S1new and S1new and S2new */
+
+	/* position of item we start filling node from */
+	int start_item;
+
+	/* position of item we finish filling node by */
+	int end_item;
+
+	/*
+	 * number of first bytes (entries for directory) of start_item-th item
+	 * we do not include into node that is being filled
+	 */
+	int start_bytes;
+
+	/*
+	 * number of last bytes (entries for directory) of end_item-th item
+	 * we do node include into node that is being filled
+	 */
+	int end_bytes;
+
+	/*
+	 * these are positions in virtual item of items, that are split
+	 * between S[0] and S1new and S1new and S2new
+	 */
+	int split_item_positions[2];
 
 	split_item_positions[0] = -1;
 	split_item_positions[1] = -1;
 
-	/* We only create additional nodes if we are in insert or paste mode
-	   or we are in replace mode at the internal level. If h is 0 and
-	   the mode is M_REPLACE then in fix_nodes we change the mode to
-	   paste or insert before we get here in the code.  */
+	/*
+	 * We only create additional nodes if we are in insert or paste mode
+	 * or we are in replace mode at the internal level. If h is 0 and
+	 * the mode is M_REPLACE then in fix_nodes we change the mode to
+	 * paste or insert before we get here in the code.
+	 */
 	RFALSE(tb->insert_size[h] < 0 || (mode != M_INSERT && mode != M_PASTE),
 	       "vs-8100: insert_size < 0 in overflow");
 
 	max_node_size = MAX_CHILD_SIZE(PATH_H_PBUFFER(tb->tb_path, h));
 
-	/* snum012 [0-2] - number of items, that lay
-	   to S[0], first new node and second new node */
+	/*
+	 * snum012 [0-2] - number of items, that lay
+	 * to S[0], first new node and second new node
+	 */
 	snum012[3] = -1;	/* s1bytes */
 	snum012[4] = -1;	/* s2bytes */
 
@@ -416,20 +440,22 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 	total_node_size = 0;
 	cur_free = max_node_size;
 
-	// start from 'from'-th item
+	/* start from 'from'-th item */
 	start_item = from;
-	// skip its first 'start_bytes' units
+	/* skip its first 'start_bytes' units */
 	start_bytes = ((from_bytes != -1) ? from_bytes : 0);
 
-	// last included item is the 'end_item'-th one
+	/* last included item is the 'end_item'-th one */
 	end_item = vn->vn_nr_item - to - 1;
-	// do not count last 'end_bytes' units of 'end_item'-th item
+	/* do not count last 'end_bytes' units of 'end_item'-th item */
 	end_bytes = (to_bytes != -1) ? to_bytes : 0;
 
-	/* go through all item beginning from the start_item-th item and ending by
-	   the end_item-th item. Do not count first 'start_bytes' units of
-	   'start_item'-th item and last 'end_bytes' of 'end_item'-th item */
-
+	/*
+	 * go through all item beginning from the start_item-th item
+	 * and ending by the end_item-th item. Do not count first
+	 * 'start_bytes' units of 'start_item'-th item and last
+	 * 'end_bytes' of 'end_item'-th item
+	 */
 	for (i = start_item; i <= end_item; i++) {
 		struct virtual_item *vi = vn->vn_vi + i;
 		int skip_from_end = ((i == end_item) ? end_bytes : 0);
@@ -439,7 +465,10 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 		/* get size of current item */
 		current_item_size = vi->vi_item_len;
 
-		/* do not take in calculation head part (from_bytes) of from-th item */
+		/*
+		 * do not take in calculation head part (from_bytes)
+		 * of from-th item
+		 */
 		current_item_size -=
 		    op_part_size(vi, 0 /*from start */ , start_bytes);
 
@@ -455,9 +484,11 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 			continue;
 		}
 
+		/*
+		 * virtual item length is longer, than max size of item in
+		 * a node. It is impossible for direct item
+		 */
 		if (current_item_size > max_node_size) {
-			/* virtual item length is longer, than max size of item in
-			   a node. It is impossible for direct item */
 			RFALSE(is_direct_le_ih(vi->vi_ih),
 			       "vs-8110: "
 			       "direct item length is %d. It can not be longer than %d",
@@ -466,15 +497,18 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 			flow = 1;
 		}
 
+		/* as we do not split items, take new node and continue */
 		if (!flow) {
-			/* as we do not split items, take new node and continue */
 			needed_nodes++;
 			i--;
 			total_node_size = 0;
 			continue;
 		}
-		// calculate number of item units which fit into node being
-		// filled
+
+		/*
+		 * calculate number of item units which fit into node being
+		 * filled
+		 */
 		{
 			int free_space;
 
@@ -482,17 +516,17 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 			units =
 			    op_check_left(vi, free_space, start_bytes,
 					  skip_from_end);
+			/*
+			 * nothing fits into current node, take new
+			 * node and continue
+			 */
 			if (units == -1) {
-				/* nothing fits into current node, take new node and continue */
 				needed_nodes++, i--, total_node_size = 0;
 				continue;
 			}
 		}
 
 		/* something fits into the current node */
-		//if (snum012[3] != -1 || needed_nodes != 1)
-		//  reiserfs_panic (tb->tb_sb, "vs-8115: get_num_ver: too many nodes required");
-		//snum012[needed_nodes - 1 + 3] = op_unit_num (vi) - start_bytes - units;
 		start_bytes += units;
 		snum012[needed_nodes - 1 + 3] = units;
 
@@ -508,9 +542,11 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 		total_node_size = 0;
 	}
 
-	// sum012[4] (if it is not -1) contains number of units of which
-	// are to be in S1new, snum012[3] - to be in S0. They are supposed
-	// to be S1bytes and S2bytes correspondingly, so recalculate
+	/*
+	 * sum012[4] (if it is not -1) contains number of units of which
+	 * are to be in S1new, snum012[3] - to be in S0. They are supposed
+	 * to be S1bytes and S2bytes correspondingly, so recalculate
+	 */
 	if (snum012[4] > 0) {
 		int split_item_num;
 		int bytes_to_r, bytes_to_l;
@@ -527,7 +563,7 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 		    ((split_item_positions[0] ==
 		      split_item_positions[1]) ? snum012[3] : 0);
 
-		// s2bytes
+		/* s2bytes */
 		snum012[4] =
 		    op_unit_num(&vn->vn_vi[split_item_num]) - snum012[4] -
 		    bytes_to_r - bytes_to_l - bytes_to_S1new;
@@ -555,7 +591,7 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 		    ((split_item_positions[0] == split_item_positions[1]
 		      && snum012[4] != -1) ? snum012[4] : 0);
 
-		// s1bytes
+		/* s1bytes */
 		snum012[3] =
 		    op_unit_num(&vn->vn_vi[split_item_num]) - snum012[3] -
 		    bytes_to_r - bytes_to_l - bytes_to_S2new;
@@ -565,7 +601,8 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
 }
 
 
-/* Set parameters for balancing.
+/*
+ * Set parameters for balancing.
  * Performs write of results of analysis of balancing into structure tb,
  * where it will later be used by the functions that actually do the balancing.
  * Parameters:
@@ -575,11 +612,12 @@ static int get_num_ver(int mode, struct tree_balance *tb, int h,
  *	rnum	number of items from S[h] that must be shifted to R[h];
  *	blk_num	number of blocks that S[h] will be splitted into;
  *	s012	number of items that fall into splitted nodes.
- *	lbytes	number of bytes which flow to the left neighbor from the item that is not
- *		not shifted entirely
- *	rbytes	number of bytes which flow to the right neighbor from the item that is not
- *		not shifted entirely
- *	s1bytes	number of bytes which flow to the first  new node when S[0] splits (this number is contained in s012 array)
+ *	lbytes	number of bytes which flow to the left neighbor from the
+ *              item that is not not shifted entirely
+ *	rbytes	number of bytes which flow to the right neighbor from the
+ *              item that is not not shifted entirely
+ *	s1bytes	number of bytes which flow to the first  new node when
+ *              S[0] splits (this number is contained in s012 array)
  */
 
 static void set_parameters(struct tree_balance *tb, int h, int lnum,
@@ -590,12 +628,14 @@ static void set_parameters(struct tree_balance *tb, int h, int lnum,
 	tb->rnum[h] = rnum;
 	tb->blknum[h] = blk_num;
 
-	if (h == 0) {		/* only for leaf level */
+	/* only for leaf level */
+	if (h == 0) {
 		if (s012 != NULL) {
-			tb->s0num = *s012++,
-			    tb->s1num = *s012++, tb->s2num = *s012++;
-			tb->s1bytes = *s012++;
-			tb->s2bytes = *s012;
+			tb->s0num = *s012++;
+			tb->snum[0] = *s012++;
+			tb->snum[1] = *s012++;
+			tb->sbytes[0] = *s012++;
+			tb->sbytes[1] = *s012;
 		}
 		tb->lbytes = lb;
 		tb->rbytes = rb;
@@ -607,8 +647,10 @@ static void set_parameters(struct tree_balance *tb, int h, int lnum,
 	PROC_INFO_ADD(tb->tb_sb, rbytes[h], rb);
 }
 
-/* check, does node disappear if we shift tb->lnum[0] items to left
-   neighbor and tb->rnum[0] to the right one. */
+/*
+ * check if node disappears if we shift tb->lnum[0] items to left
+ * neighbor and tb->rnum[0] to the right one.
+ */
 static int is_leaf_removable(struct tree_balance *tb)
 {
 	struct virtual_node *vn = tb->tb_vn;
@@ -616,8 +658,10 @@ static int is_leaf_removable(struct tree_balance *tb)
 	int size;
 	int remain_items;
 
-	/* number of items, that will be shifted to left (right) neighbor
-	   entirely */
+	/*
+	 * number of items that will be shifted to left (right) neighbor
+	 * entirely
+	 */
 	to_left = tb->lnum[0] - ((tb->lbytes != -1) ? 1 : 0);
 	to_right = tb->rnum[0] - ((tb->rbytes != -1) ? 1 : 0);
 	remain_items = vn->vn_nr_item;
@@ -625,21 +669,21 @@ static int is_leaf_removable(struct tree_balance *tb)
 	/* how many items remain in S[0] after shiftings to neighbors */
 	remain_items -= (to_left + to_right);
 
+	/* all content of node can be shifted to neighbors */
 	if (remain_items < 1) {
-		/* all content of node can be shifted to neighbors */
 		set_parameters(tb, 0, to_left, vn->vn_nr_item - to_left, 0,
 			       NULL, -1, -1);
 		return 1;
 	}
 
+	/* S[0] is not removable */
 	if (remain_items > 1 || tb->lbytes == -1 || tb->rbytes == -1)
-		/* S[0] is not removable */
 		return 0;
 
-	/* check, whether we can divide 1 remaining item between neighbors */
+	/* check whether we can divide 1 remaining item between neighbors */
 
 	/* get size of remaining item (in item units) */
-	size = op_unit_num(&(vn->vn_vi[to_left]));
+	size = op_unit_num(&vn->vn_vi[to_left]);
 
 	if (tb->lbytes + tb->rbytes >= size) {
 		set_parameters(tb, 0, to_left + 1, to_right + 1, 0, NULL,
@@ -675,23 +719,28 @@ static int are_leaves_removable(struct tree_balance *tb, int lfree, int rfree)
 		       "vs-8125: item number must be 1: it is %d",
 		       B_NR_ITEMS(S0));
 
-		ih = B_N_PITEM_HEAD(S0, 0);
+		ih = item_head(S0, 0);
 		if (tb->CFR[0]
-		    && !comp_short_le_keys(&(ih->ih_key),
-					   B_N_PDELIM_KEY(tb->CFR[0],
+		    && !comp_short_le_keys(&ih->ih_key,
+					   internal_key(tb->CFR[0],
 							  tb->rkey[0])))
+			/*
+			 * Directory must be in correct state here: that is
+			 * somewhere at the left side should exist first
+			 * directory item. But the item being deleted can
+			 * not be that first one because its right neighbor
+			 * is item of the same directory. (But first item
+			 * always gets deleted in last turn). So, neighbors
+			 * of deleted item can be merged, so we can save
+			 * ih_size
+			 */
 			if (is_direntry_le_ih(ih)) {
-				/* Directory must be in correct state here: that is
-				   somewhere at the left side should exist first directory
-				   item. But the item being deleted can not be that first
-				   one because its right neighbor is item of the same
-				   directory. (But first item always gets deleted in last
-				   turn). So, neighbors of deleted item can be merged, so
-				   we can save ih_size */
 				ih_size = IH_SIZE;
 
-				/* we might check that left neighbor exists and is of the
-				   same directory */
+				/*
+				 * we might check that left neighbor exists
+				 * and is of the same directory
+				 */
 				RFALSE(le_ih_k_offset(ih) == DOT_OFFSET,
 				       "vs-8130: first directory item can not be removed until directory is not empty");
 			}
@@ -770,7 +819,8 @@ static void free_buffers_in_tb(struct tree_balance *tb)
 	}
 }
 
-/* Get new buffers for storing new nodes that are created while balancing.
+/*
+ * Get new buffers for storing new nodes that are created while balancing.
  * Returns:	SCHEDULE_OCCURRED - schedule occurred while the function worked;
  *	        CARRY_ON - schedule didn't occur while the function worked;
  *	        NO_DISK_SPACE - no disk space.
@@ -778,28 +828,33 @@ static void free_buffers_in_tb(struct tree_balance *tb)
 /* The function is NOT SCHEDULE-SAFE! */
 static int get_empty_nodes(struct tree_balance *tb, int h)
 {
-	struct buffer_head *new_bh,
-	    *Sh = PATH_H_PBUFFER(tb->tb_path, h);
+	struct buffer_head *new_bh, *Sh = PATH_H_PBUFFER(tb->tb_path, h);
 	b_blocknr_t *blocknr, blocknrs[MAX_AMOUNT_NEEDED] = { 0, };
-	int counter, number_of_freeblk, amount_needed,	/* number of needed empty blocks */
-	 retval = CARRY_ON;
+	int counter, number_of_freeblk;
+	int  amount_needed;	/* number of needed empty blocks */
+	int  retval = CARRY_ON;
 	struct super_block *sb = tb->tb_sb;
 
-	/* number_of_freeblk is the number of empty blocks which have been
-	   acquired for use by the balancing algorithm minus the number of
-	   empty blocks used in the previous levels of the analysis,
-	   number_of_freeblk = tb->cur_blknum can be non-zero if a schedule occurs
-	   after empty blocks are acquired, and the balancing analysis is
-	   then restarted, amount_needed is the number needed by this level
-	   (h) of the balancing analysis.
-
-	   Note that for systems with many processes writing, it would be
-	   more layout optimal to calculate the total number needed by all
-	   levels and then to run reiserfs_new_blocks to get all of them at once.  */
-
-	/* Initiate number_of_freeblk to the amount acquired prior to the restart of
-	   the analysis or 0 if not restarted, then subtract the amount needed
-	   by all of the levels of the tree below h. */
+	/*
+	 * number_of_freeblk is the number of empty blocks which have been
+	 * acquired for use by the balancing algorithm minus the number of
+	 * empty blocks used in the previous levels of the analysis,
+	 * number_of_freeblk = tb->cur_blknum can be non-zero if a schedule
+	 * occurs after empty blocks are acquired, and the balancing analysis
+	 * is then restarted, amount_needed is the number needed by this
+	 * level (h) of the balancing analysis.
+	 *
+	 * Note that for systems with many processes writing, it would be
+	 * more layout optimal to calculate the total number needed by all
+	 * levels and then to run reiserfs_new_blocks to get all of them at
+	 * once.
+	 */
+
+	/*
+	 * Initiate number_of_freeblk to the amount acquired prior to the
+	 * restart of the analysis or 0 if not restarted, then subtract the
+	 * amount needed by all of the levels of the tree below h.
+	 */
 	/* blknum includes S[h], so we subtract 1 in this calculation */
 	for (counter = 0, number_of_freeblk = tb->cur_blknum;
 	     counter < h; counter++)
@@ -810,13 +865,19 @@ static int get_empty_nodes(struct tree_balance *tb, int h)
 	/* Allocate missing empty blocks. */
 	/* if Sh == 0  then we are getting a new root */
 	amount_needed = (Sh) ? (tb->blknum[h] - 1) : 1;
-	/*  Amount_needed = the amount that we need more than the amount that we have. */
+	/*
+	 * Amount_needed = the amount that we need more than the
+	 * amount that we have.
+	 */
 	if (amount_needed > number_of_freeblk)
 		amount_needed -= number_of_freeblk;
-	else			/* If we have enough already then there is nothing to do. */
+	else	/* If we have enough already then there is nothing to do. */
 		return CARRY_ON;
 
-	/* No need to check quota - is not allocated for blocks used for formatted nodes */
+	/*
+	 * No need to check quota - is not allocated for blocks used
+	 * for formatted nodes
+	 */
 	if (reiserfs_new_form_blocknrs(tb, blocknrs,
 				       amount_needed) == NO_DISK_SPACE)
 		return NO_DISK_SPACE;
@@ -849,8 +910,10 @@ static int get_empty_nodes(struct tree_balance *tb, int h)
 	return retval;
 }
 
-/* Get free space of the left neighbor, which is stored in the parent
- * node of the left neighbor.  */
+/*
+ * Get free space of the left neighbor, which is stored in the parent
+ * node of the left neighbor.
+ */
 static int get_lfree(struct tree_balance *tb, int h)
 {
 	struct buffer_head *l, *f;
@@ -870,7 +933,8 @@ static int get_lfree(struct tree_balance *tb, int h)
 	return (MAX_CHILD_SIZE(f) - dc_size(B_N_CHILD(f, order)));
 }
 
-/* Get free space of the right neighbor,
+/*
+ * Get free space of the right neighbor,
  * which is stored in the parent node of the right neighbor.
  */
 static int get_rfree(struct tree_balance *tb, int h)
@@ -916,7 +980,10 @@ static int is_left_neighbor_in_cache(struct tree_balance *tb, int h)
 	       "vs-8165: F[h] (%b) or FL[h] (%b) is invalid",
 	       father, tb->FL[h]);
 
-	/* Get position of the pointer to the left neighbor into the left father. */
+	/*
+	 * Get position of the pointer to the left neighbor
+	 * into the left father.
+	 */
 	left_neighbor_position = (father == tb->FL[h]) ?
 	    tb->lkey[h] : B_NR_ITEMS(tb->FL[h]);
 	/* Get left neighbor block number. */
@@ -940,17 +1007,20 @@ static int is_left_neighbor_in_cache(struct tree_balance *tb, int h)
 
 static void decrement_key(struct cpu_key *key)
 {
-	// call item specific function for this key
+	/* call item specific function for this key */
 	item_ops[cpu_key_k_type(key)]->decrement_key(key);
 }
 
-/* Calculate far left/right parent of the left/right neighbor of the current node, that
- * is calculate the left/right (FL[h]/FR[h]) neighbor of the parent F[h].
+/*
+ * Calculate far left/right parent of the left/right neighbor of the
+ * current node, that is calculate the left/right (FL[h]/FR[h]) neighbor
+ * of the parent F[h].
  * Calculate left/right common parent of the current node and L[h]/R[h].
  * Calculate left/right delimiting key position.
- * Returns:	PATH_INCORRECT   - path in the tree is not correct;
- 		SCHEDULE_OCCURRED - schedule occurred while the function worked;
- *	        CARRY_ON         - schedule didn't occur while the function worked;
+ * Returns:	PATH_INCORRECT    - path in the tree is not correct
+ *		SCHEDULE_OCCURRED - schedule occurred while the function worked
+ *	        CARRY_ON          - schedule didn't occur while the function
+ *				    worked
  */
 static int get_far_parent(struct tree_balance *tb,
 			  int h,
@@ -966,8 +1036,10 @@ static int get_far_parent(struct tree_balance *tb,
 	    first_last_position = 0,
 	    path_offset = PATH_H_PATH_OFFSET(path, h);
 
-	/* Starting from F[h] go upwards in the tree, and look for the common
-	   ancestor of F[h], and its neighbor l/r, that should be obtained. */
+	/*
+	 * Starting from F[h] go upwards in the tree, and look for the common
+	 * ancestor of F[h], and its neighbor l/r, that should be obtained.
+	 */
 
 	counter = path_offset;
 
@@ -975,21 +1047,33 @@ static int get_far_parent(struct tree_balance *tb,
 	       "PAP-8180: invalid path length");
 
 	for (; counter > FIRST_PATH_ELEMENT_OFFSET; counter--) {
-		/* Check whether parent of the current buffer in the path is really parent in the tree. */
+		/*
+		 * Check whether parent of the current buffer in the path
+		 * is really parent in the tree.
+		 */
 		if (!B_IS_IN_TREE
 		    (parent = PATH_OFFSET_PBUFFER(path, counter - 1)))
 			return REPEAT_SEARCH;
+
 		/* Check whether position in the parent is correct. */
 		if ((position =
 		     PATH_OFFSET_POSITION(path,
 					  counter - 1)) >
 		    B_NR_ITEMS(parent))
 			return REPEAT_SEARCH;
-		/* Check whether parent at the path really points to the child. */
+
+		/*
+		 * Check whether parent at the path really points
+		 * to the child.
+		 */
 		if (B_N_CHILD_NUM(parent, position) !=
 		    PATH_OFFSET_PBUFFER(path, counter)->b_blocknr)
 			return REPEAT_SEARCH;
-		/* Return delimiting key if position in the parent is not equal to first/last one. */
+
+		/*
+		 * Return delimiting key if position in the parent is not
+		 * equal to first/last one.
+		 */
 		if (c_lr_par == RIGHT_PARENTS)
 			first_last_position = B_NR_ITEMS(parent);
 		if (position != first_last_position) {
@@ -1002,7 +1086,10 @@ static int get_far_parent(struct tree_balance *tb,
 
 	/* if we are in the root of the tree, then there is no common father */
 	if (counter == FIRST_PATH_ELEMENT_OFFSET) {
-		/* Check whether first buffer in the path is the root of the tree. */
+		/*
+		 * Check whether first buffer in the path is the
+		 * root of the tree.
+		 */
 		if (PATH_OFFSET_PBUFFER
 		    (tb->tb_path,
 		     FIRST_PATH_ELEMENT_OFFSET)->b_blocknr ==
@@ -1031,12 +1118,15 @@ static int get_far_parent(struct tree_balance *tb,
 		}
 	}
 
-	/* So, we got common parent of the current node and its left/right neighbor.
-	   Now we are geting the parent of the left/right neighbor. */
+	/*
+	 * So, we got common parent of the current node and its
+	 * left/right neighbor.  Now we are getting the parent of the
+	 * left/right neighbor.
+	 */
 
 	/* Form key to get parent of the left/right neighbor. */
 	le_key2cpu_key(&s_lr_father_key,
-		       B_N_PDELIM_KEY(*pcom_father,
+		       internal_key(*pcom_father,
 				      (c_lr_par ==
 				       LEFT_PARENTS) ? (tb->lkey[h - 1] =
 							position -
@@ -1050,7 +1140,7 @@ static int get_far_parent(struct tree_balance *tb,
 	if (search_by_key
 	    (tb->tb_sb, &s_lr_father_key, &s_path_to_neighbor_father,
 	     h + 1) == IO_ERROR)
-		// path is released
+		/* path is released */
 		return IO_ERROR;
 
 	if (FILESYSTEM_CHANGED_TB(tb)) {
@@ -1071,12 +1161,15 @@ static int get_far_parent(struct tree_balance *tb,
 	return CARRY_ON;
 }
 
-/* Get parents of neighbors of node in the path(S[path_offset]) and common parents of
- * S[path_offset] and L[path_offset]/R[path_offset]: F[path_offset], FL[path_offset],
- * FR[path_offset], CFL[path_offset], CFR[path_offset].
- * Calculate numbers of left and right delimiting keys position: lkey[path_offset], rkey[path_offset].
- * Returns:	SCHEDULE_OCCURRED - schedule occurred while the function worked;
- *	        CARRY_ON - schedule didn't occur while the function worked;
+/*
+ * Get parents of neighbors of node in the path(S[path_offset]) and
+ * common parents of S[path_offset] and L[path_offset]/R[path_offset]:
+ * F[path_offset], FL[path_offset], FR[path_offset], CFL[path_offset],
+ * CFR[path_offset].
+ * Calculate numbers of left and right delimiting keys position:
+ * lkey[path_offset], rkey[path_offset].
+ * Returns:	SCHEDULE_OCCURRED - schedule occurred while the function worked
+ *	        CARRY_ON - schedule didn't occur while the function worked
  */
 static int get_parents(struct tree_balance *tb, int h)
 {
@@ -1088,8 +1181,11 @@ static int get_parents(struct tree_balance *tb, int h)
 
 	/* Current node is the root of the tree or will be root of the tree */
 	if (path_offset <= FIRST_PATH_ELEMENT_OFFSET) {
-		/* The root can not have parents.
-		   Release nodes which previously were obtained as parents of the current node neighbors. */
+		/*
+		 * The root can not have parents.
+		 * Release nodes which previously were obtained as
+		 * parents of the current node neighbors.
+		 */
 		brelse(tb->FL[h]);
 		brelse(tb->CFL[h]);
 		brelse(tb->FR[h]);
@@ -1111,10 +1207,14 @@ static int get_parents(struct tree_balance *tb, int h)
 		get_bh(curf);
 		tb->lkey[h] = position - 1;
 	} else {
-		/* Calculate current parent of L[path_offset], which is the left neighbor of the current node.
-		   Calculate current common parent of L[path_offset] and the current node. Note that
-		   CFL[path_offset] not equal FL[path_offset] and CFL[path_offset] not equal F[path_offset].
-		   Calculate lkey[path_offset]. */
+		/*
+		 * Calculate current parent of L[path_offset], which is the
+		 * left neighbor of the current node.  Calculate current
+		 * common parent of L[path_offset] and the current node.
+		 * Note that CFL[path_offset] not equal FL[path_offset] and
+		 * CFL[path_offset] not equal F[path_offset].
+		 * Calculate lkey[path_offset].
+		 */
 		if ((ret = get_far_parent(tb, h + 1, &curf,
 						  &curcf,
 						  LEFT_PARENTS)) != CARRY_ON)
@@ -1130,19 +1230,22 @@ static int get_parents(struct tree_balance *tb, int h)
 	       (curcf && !B_IS_IN_TREE(curcf)),
 	       "PAP-8195: FL (%b) or CFL (%b) is invalid", curf, curcf);
 
-/* Get parent FR[h] of R[h]. */
+	/* Get parent FR[h] of R[h]. */
 
-/* Current node is the last child of F[h]. FR[h] != F[h]. */
+	/* Current node is the last child of F[h]. FR[h] != F[h]. */
 	if (position == B_NR_ITEMS(PATH_H_PBUFFER(path, h + 1))) {
-/* Calculate current parent of R[h], which is the right neighbor of F[h].
-   Calculate current common parent of R[h] and current node. Note that CFR[h]
-   not equal FR[path_offset] and CFR[h] not equal F[h]. */
+		/*
+		 * Calculate current parent of R[h], which is the right
+		 * neighbor of F[h].  Calculate current common parent of
+		 * R[h] and current node. Note that CFR[h] not equal
+		 * FR[path_offset] and CFR[h] not equal F[h].
+		 */
 		if ((ret =
 		     get_far_parent(tb, h + 1, &curf, &curcf,
 				    RIGHT_PARENTS)) != CARRY_ON)
 			return ret;
 	} else {
-/* Current node is not the last child of its parent F[h]. */
+		/* Current node is not the last child of its parent F[h]. */
 		curf = PATH_OFFSET_PBUFFER(path, path_offset - 1);
 		curcf = PATH_OFFSET_PBUFFER(path, path_offset - 1);
 		get_bh(curf);
@@ -1165,8 +1268,10 @@ static int get_parents(struct tree_balance *tb, int h)
 	return CARRY_ON;
 }
 
-/* it is possible to remove node as result of shiftings to
-   neighbors even when we insert or paste item. */
+/*
+ * it is possible to remove node as result of shiftings to
+ * neighbors even when we insert or paste item.
+ */
 static inline int can_node_be_removed(int mode, int lfree, int sfree, int rfree,
 				      struct tree_balance *tb, int h)
 {
@@ -1175,21 +1280,22 @@ static inline int can_node_be_removed(int mode, int lfree, int sfree, int rfree,
 	struct item_head *ih;
 	struct reiserfs_key *r_key = NULL;
 
-	ih = B_N_PITEM_HEAD(Sh, 0);
+	ih = item_head(Sh, 0);
 	if (tb->CFR[h])
-		r_key = B_N_PDELIM_KEY(tb->CFR[h], tb->rkey[h]);
+		r_key = internal_key(tb->CFR[h], tb->rkey[h]);
 
 	if (lfree + rfree + sfree < MAX_CHILD_SIZE(Sh) + levbytes
 	    /* shifting may merge items which might save space */
 	    -
 	    ((!h
-	      && op_is_left_mergeable(&(ih->ih_key), Sh->b_size)) ? IH_SIZE : 0)
+	      && op_is_left_mergeable(&ih->ih_key, Sh->b_size)) ? IH_SIZE : 0)
 	    -
 	    ((!h && r_key
 	      && op_is_left_mergeable(r_key, Sh->b_size)) ? IH_SIZE : 0)
 	    + ((h) ? KEY_SIZE : 0)) {
 		/* node can not be removed */
-		if (sfree >= levbytes) {	/* new item fits into node S[h] without any shifting */
+		if (sfree >= levbytes) {
+			/* new item fits into node S[h] without any shifting */
 			if (!h)
 				tb->s0num =
 				    B_NR_ITEMS(Sh) +
@@ -1202,7 +1308,8 @@ static inline int can_node_be_removed(int mode, int lfree, int sfree, int rfree,
 	return !NO_BALANCING_NEEDED;
 }
 
-/* Check whether current node S[h] is balanced when increasing its size by
+/*
+ * Check whether current node S[h] is balanced when increasing its size by
  * Inserting or Pasting.
  * Calculate parameters for balancing for current level h.
  * Parameters:
@@ -1219,39 +1326,48 @@ static inline int can_node_be_removed(int mode, int lfree, int sfree, int rfree,
 static int ip_check_balance(struct tree_balance *tb, int h)
 {
 	struct virtual_node *vn = tb->tb_vn;
-	int levbytes,		/* Number of bytes that must be inserted into (value
-				   is negative if bytes are deleted) buffer which
-				   contains node being balanced.  The mnemonic is
-				   that the attempted change in node space used level
-				   is levbytes bytes. */
-	 ret;
+	/*
+	 * Number of bytes that must be inserted into (value is negative
+	 * if bytes are deleted) buffer which contains node being balanced.
+	 * The mnemonic is that the attempted change in node space used
+	 * level is levbytes bytes.
+	 */
+	int levbytes;
+	int ret;
 
 	int lfree, sfree, rfree /* free space in L, S and R */ ;
 
-	/* nver is short for number of vertixes, and lnver is the number if
-	   we shift to the left, rnver is the number if we shift to the
-	   right, and lrnver is the number if we shift in both directions.
-	   The goal is to minimize first the number of vertixes, and second,
-	   the number of vertixes whose contents are changed by shifting,
-	   and third the number of uncached vertixes whose contents are
-	   changed by shifting and must be read from disk.  */
+	/*
+	 * nver is short for number of vertixes, and lnver is the number if
+	 * we shift to the left, rnver is the number if we shift to the
+	 * right, and lrnver is the number if we shift in both directions.
+	 * The goal is to minimize first the number of vertixes, and second,
+	 * the number of vertixes whose contents are changed by shifting,
+	 * and third the number of uncached vertixes whose contents are
+	 * changed by shifting and must be read from disk.
+	 */
 	int nver, lnver, rnver, lrnver;
 
-	/* used at leaf level only, S0 = S[0] is the node being balanced,
-	   sInum [ I = 0,1,2 ] is the number of items that will
-	   remain in node SI after balancing.  S1 and S2 are new
-	   nodes that might be created. */
+	/*
+	 * used at leaf level only, S0 = S[0] is the node being balanced,
+	 * sInum [ I = 0,1,2 ] is the number of items that will
+	 * remain in node SI after balancing.  S1 and S2 are new
+	 * nodes that might be created.
+	 */
 
-	/* we perform 8 calls to get_num_ver().  For each call we calculate five parameters.
-	   where 4th parameter is s1bytes and 5th - s2bytes
+	/*
+	 * we perform 8 calls to get_num_ver().  For each call we
+	 * calculate five parameters.  where 4th parameter is s1bytes
+	 * and 5th - s2bytes
+	 *
+	 * s0num, s1num, s2num for 8 cases
+	 * 0,1 - do not shift and do not shift but bottle
+	 * 2   - shift only whole item to left
+	 * 3   - shift to left and bottle as much as possible
+	 * 4,5 - shift to right (whole items and as much as possible
+	 * 6,7 - shift to both directions (whole items and as much as possible)
 	 */
-	short snum012[40] = { 0, };	/* s0num, s1num, s2num for 8 cases
-					   0,1 - do not shift and do not shift but bottle
-					   2 - shift only whole item to left
-					   3 - shift to left and bottle as much as possible
-					   4,5 - shift to right (whole items and as much as possible
-					   6,7 - shift to both directions (whole items and as much as possible)
-					 */
+	short snum012[40] = { 0, };
 
 	/* Sh is the node whose balance is currently being checked */
 	struct buffer_head *Sh;
@@ -1265,9 +1381,10 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 			reiserfs_panic(tb->tb_sb, "vs-8210",
 				       "S[0] can not be 0");
 		switch (ret = get_empty_nodes(tb, h)) {
+		/* no balancing for higher levels needed */
 		case CARRY_ON:
 			set_parameters(tb, h, 0, 0, 1, NULL, -1, -1);
-			return NO_BALANCING_NEEDED;	/* no balancing for higher levels needed */
+			return NO_BALANCING_NEEDED;
 
 		case NO_DISK_SPACE:
 		case REPEAT_SEARCH:
@@ -1278,7 +1395,9 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 		}
 	}
 
-	if ((ret = get_parents(tb, h)) != CARRY_ON)	/* get parents of S[h] neighbors. */
+	/* get parents of S[h] neighbors. */
+	ret = get_parents(tb, h);
+	if (ret != CARRY_ON)
 		return ret;
 
 	sfree = B_FREE_SPACE(Sh);
@@ -1287,38 +1406,44 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 	rfree = get_rfree(tb, h);
 	lfree = get_lfree(tb, h);
 
+	/* and new item fits into node S[h] without any shifting */
 	if (can_node_be_removed(vn->vn_mode, lfree, sfree, rfree, tb, h) ==
 	    NO_BALANCING_NEEDED)
-		/* and new item fits into node S[h] without any shifting */
 		return NO_BALANCING_NEEDED;
 
 	create_virtual_node(tb, h);
 
 	/*
-	   determine maximal number of items we can shift to the left neighbor (in tb structure)
-	   and the maximal number of bytes that can flow to the left neighbor
-	   from the left most liquid item that cannot be shifted from S[0] entirely (returned value)
+	 * determine maximal number of items we can shift to the left
+	 * neighbor (in tb structure) and the maximal number of bytes
+	 * that can flow to the left neighbor from the left most liquid
+	 * item that cannot be shifted from S[0] entirely (returned value)
 	 */
 	check_left(tb, h, lfree);
 
 	/*
-	   determine maximal number of items we can shift to the right neighbor (in tb structure)
-	   and the maximal number of bytes that can flow to the right neighbor
-	   from the right most liquid item that cannot be shifted from S[0] entirely (returned value)
+	 * determine maximal number of items we can shift to the right
+	 * neighbor (in tb structure) and the maximal number of bytes
+	 * that can flow to the right neighbor from the right most liquid
+	 * item that cannot be shifted from S[0] entirely (returned value)
 	 */
 	check_right(tb, h, rfree);
 
-	/* all contents of internal node S[h] can be moved into its
-	   neighbors, S[h] will be removed after balancing */
+	/*
+	 * all contents of internal node S[h] can be moved into its
+	 * neighbors, S[h] will be removed after balancing
+	 */
 	if (h && (tb->rnum[h] + tb->lnum[h] >= vn->vn_nr_item + 1)) {
 		int to_r;
 
-		/* Since we are working on internal nodes, and our internal
-		   nodes have fixed size entries, then we can balance by the
-		   number of items rather than the space they consume.  In this
-		   routine we set the left node equal to the right node,
-		   allowing a difference of less than or equal to 1 child
-		   pointer. */
+		/*
+		 * Since we are working on internal nodes, and our internal
+		 * nodes have fixed size entries, then we can balance by the
+		 * number of items rather than the space they consume.  In this
+		 * routine we set the left node equal to the right node,
+		 * allowing a difference of less than or equal to 1 child
+		 * pointer.
+		 */
 		to_r =
 		    ((MAX_NR_KEY(Sh) << 1) + 2 - tb->lnum[h] - tb->rnum[h] +
 		     vn->vn_nr_item + 1) / 2 - (MAX_NR_KEY(Sh) + 1 -
@@ -1328,7 +1453,10 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 		return CARRY_ON;
 	}
 
-	/* this checks balance condition, that any two neighboring nodes can not fit in one node */
+	/*
+	 * this checks balance condition, that any two neighboring nodes
+	 * can not fit in one node
+	 */
 	RFALSE(h &&
 	       (tb->lnum[h] >= vn->vn_nr_item + 1 ||
 		tb->rnum[h] >= vn->vn_nr_item + 1),
@@ -1337,16 +1465,22 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 		      (tb->rnum[h] >= vn->vn_nr_item && (tb->rbytes == -1))),
 	       "vs-8225: tree is not balanced on leaf level");
 
-	/* all contents of S[0] can be moved into its neighbors
-	   S[0] will be removed after balancing. */
+	/*
+	 * all contents of S[0] can be moved into its neighbors
+	 * S[0] will be removed after balancing.
+	 */
 	if (!h && is_leaf_removable(tb))
 		return CARRY_ON;
 
-	/* why do we perform this check here rather than earlier??
-	   Answer: we can win 1 node in some cases above. Moreover we
-	   checked it above, when we checked, that S[0] is not removable
-	   in principle */
-	if (sfree >= levbytes) {	/* new item fits into node S[h] without any shifting */
+	/*
+	 * why do we perform this check here rather than earlier??
+	 * Answer: we can win 1 node in some cases above. Moreover we
+	 * checked it above, when we checked, that S[0] is not removable
+	 * in principle
+	 */
+
+	 /* new item fits into node S[h] without any shifting */
+	if (sfree >= levbytes) {
 		if (!h)
 			tb->s0num = vn->vn_nr_item;
 		set_parameters(tb, h, 0, 0, 1, NULL, -1, -1);
@@ -1355,18 +1489,19 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 
 	{
 		int lpar, rpar, nset, lset, rset, lrset;
-		/*
-		 * regular overflowing of the node
-		 */
+		/* regular overflowing of the node */
 
-		/* get_num_ver works in 2 modes (FLOW & NO_FLOW)
-		   lpar, rpar - number of items we can shift to left/right neighbor (including splitting item)
-		   nset, lset, rset, lrset - shows, whether flowing items give better packing
+		/*
+		 * get_num_ver works in 2 modes (FLOW & NO_FLOW)
+		 * lpar, rpar - number of items we can shift to left/right
+		 *              neighbor (including splitting item)
+		 * nset, lset, rset, lrset - shows, whether flowing items
+		 *                           give better packing
 		 */
 #define FLOW 1
 #define NO_FLOW 0		/* do not any splitting */
 
-		/* we choose one the following */
+		/* we choose one of the following */
 #define NOTHING_SHIFT_NO_FLOW	0
 #define NOTHING_SHIFT_FLOW	5
 #define LEFT_SHIFT_NO_FLOW	10
@@ -1379,10 +1514,13 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 		lpar = tb->lnum[h];
 		rpar = tb->rnum[h];
 
-		/* calculate number of blocks S[h] must be split into when
-		   nothing is shifted to the neighbors,
-		   as well as number of items in each part of the split node (s012 numbers),
-		   and number of bytes (s1bytes) of the shared drop which flow to S1 if any */
+		/*
+		 * calculate number of blocks S[h] must be split into when
+		 * nothing is shifted to the neighbors, as well as number of
+		 * items in each part of the split node (s012 numbers),
+		 * and number of bytes (s1bytes) of the shared drop which
+		 * flow to S1 if any
+		 */
 		nset = NOTHING_SHIFT_NO_FLOW;
 		nver = get_num_ver(vn->vn_mode, tb, h,
 				   0, -1, h ? vn->vn_nr_item : 0, -1,
@@ -1391,7 +1529,10 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 		if (!h) {
 			int nver1;
 
-			/* note, that in this case we try to bottle between S[0] and S1 (S1 - the first new node) */
+			/*
+			 * note, that in this case we try to bottle
+			 * between S[0] and S1 (S1 - the first new node)
+			 */
 			nver1 = get_num_ver(vn->vn_mode, tb, h,
 					    0, -1, 0, -1,
 					    snum012 + NOTHING_SHIFT_FLOW, FLOW);
@@ -1399,11 +1540,13 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 				nset = NOTHING_SHIFT_FLOW, nver = nver1;
 		}
 
-		/* calculate number of blocks S[h] must be split into when
-		   l_shift_num first items and l_shift_bytes of the right most
-		   liquid item to be shifted are shifted to the left neighbor,
-		   as well as number of items in each part of the splitted node (s012 numbers),
-		   and number of bytes (s1bytes) of the shared drop which flow to S1 if any
+		/*
+		 * calculate number of blocks S[h] must be split into when
+		 * l_shift_num first items and l_shift_bytes of the right
+		 * most liquid item to be shifted are shifted to the left
+		 * neighbor, as well as number of items in each part of the
+		 * splitted node (s012 numbers), and number of bytes
+		 * (s1bytes) of the shared drop which flow to S1 if any
 		 */
 		lset = LEFT_SHIFT_NO_FLOW;
 		lnver = get_num_ver(vn->vn_mode, tb, h,
@@ -1422,11 +1565,13 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 				lset = LEFT_SHIFT_FLOW, lnver = lnver1;
 		}
 
-		/* calculate number of blocks S[h] must be split into when
-		   r_shift_num first items and r_shift_bytes of the left most
-		   liquid item to be shifted are shifted to the right neighbor,
-		   as well as number of items in each part of the splitted node (s012 numbers),
-		   and number of bytes (s1bytes) of the shared drop which flow to S1 if any
+		/*
+		 * calculate number of blocks S[h] must be split into when
+		 * r_shift_num first items and r_shift_bytes of the left most
+		 * liquid item to be shifted are shifted to the right neighbor,
+		 * as well as number of items in each part of the splitted
+		 * node (s012 numbers), and number of bytes (s1bytes) of the
+		 * shared drop which flow to S1 if any
 		 */
 		rset = RIGHT_SHIFT_NO_FLOW;
 		rnver = get_num_ver(vn->vn_mode, tb, h,
@@ -1451,10 +1596,12 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 				rset = RIGHT_SHIFT_FLOW, rnver = rnver1;
 		}
 
-		/* calculate number of blocks S[h] must be split into when
-		   items are shifted in both directions,
-		   as well as number of items in each part of the splitted node (s012 numbers),
-		   and number of bytes (s1bytes) of the shared drop which flow to S1 if any
+		/*
+		 * calculate number of blocks S[h] must be split into when
+		 * items are shifted in both directions, as well as number
+		 * of items in each part of the splitted node (s012 numbers),
+		 * and number of bytes (s1bytes) of the shared drop which
+		 * flow to S1 if any
 		 */
 		lrset = LR_SHIFT_NO_FLOW;
 		lrnver = get_num_ver(vn->vn_mode, tb, h,
@@ -1481,10 +1628,12 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 				lrset = LR_SHIFT_FLOW, lrnver = lrnver1;
 		}
 
-		/* Our general shifting strategy is:
-		   1) to minimized number of new nodes;
-		   2) to minimized number of neighbors involved in shifting;
-		   3) to minimized number of disk reads; */
+		/*
+		 * Our general shifting strategy is:
+		 * 1) to minimized number of new nodes;
+		 * 2) to minimized number of neighbors involved in shifting;
+		 * 3) to minimized number of disk reads;
+		 */
 
 		/* we can win TWO or ONE nodes by shifting in both directions */
 		if (lrnver < lnver && lrnver < rnver) {
@@ -1508,42 +1657,59 @@ static int ip_check_balance(struct tree_balance *tb, int h)
 			return CARRY_ON;
 		}
 
-		/* if shifting doesn't lead to better packing then don't shift */
+		/*
+		 * if shifting doesn't lead to better packing
+		 * then don't shift
+		 */
 		if (nver == lrnver) {
 			set_parameters(tb, h, 0, 0, nver, snum012 + nset, -1,
 				       -1);
 			return CARRY_ON;
 		}
 
-		/* now we know that for better packing shifting in only one
-		   direction either to the left or to the right is required */
+		/*
+		 * now we know that for better packing shifting in only one
+		 * direction either to the left or to the right is required
+		 */
 
-		/*  if shifting to the left is better than shifting to the right */
+		/*
+		 * if shifting to the left is better than
+		 * shifting to the right
+		 */
 		if (lnver < rnver) {
 			SET_PAR_SHIFT_LEFT;
 			return CARRY_ON;
 		}
 
-		/* if shifting to the right is better than shifting to the left */
+		/*
+		 * if shifting to the right is better than
+		 * shifting to the left
+		 */
 		if (lnver > rnver) {
 			SET_PAR_SHIFT_RIGHT;
 			return CARRY_ON;
 		}
 
-		/* now shifting in either direction gives the same number
-		   of nodes and we can make use of the cached neighbors */
+		/*
+		 * now shifting in either direction gives the same number
+		 * of nodes and we can make use of the cached neighbors
+		 */
 		if (is_left_neighbor_in_cache(tb, h)) {
 			SET_PAR_SHIFT_LEFT;
 			return CARRY_ON;
 		}
 
-		/* shift to the right independently on whether the right neighbor in cache or not */
+		/*
+		 * shift to the right independently on whether the
+		 * right neighbor in cache or not
+		 */
 		SET_PAR_SHIFT_RIGHT;
 		return CARRY_ON;
 	}
 }
 
-/* Check whether current node S[h] is balanced when Decreasing its size by
+/*
+ * Check whether current node S[h] is balanced when Decreasing its size by
  * Deleting or Cutting for INTERNAL node of S+tree.
  * Calculate parameters for balancing for current level h.
  * Parameters:
@@ -1563,8 +1729,10 @@ static int dc_check_balance_internal(struct tree_balance *tb, int h)
 {
 	struct virtual_node *vn = tb->tb_vn;
 
-	/* Sh is the node whose balance is currently being checked,
-	   and Fh is its father.  */
+	/*
+	 * Sh is the node whose balance is currently being checked,
+	 * and Fh is its father.
+	 */
 	struct buffer_head *Sh, *Fh;
 	int maxsize, ret;
 	int lfree, rfree /* free space in L and R */ ;
@@ -1574,19 +1742,25 @@ static int dc_check_balance_internal(struct tree_balance *tb, int h)
 
 	maxsize = MAX_CHILD_SIZE(Sh);
 
-/*   using tb->insert_size[h], which is negative in this case, create_virtual_node calculates: */
-/*   new_nr_item = number of items node would have if operation is */
-/* 	performed without balancing (new_nr_item); */
+	/*
+	 * using tb->insert_size[h], which is negative in this case,
+	 * create_virtual_node calculates:
+	 * new_nr_item = number of items node would have if operation is
+	 * performed without balancing (new_nr_item);
+	 */
 	create_virtual_node(tb, h);
 
 	if (!Fh) {		/* S[h] is the root. */
+		/* no balancing for higher levels needed */
 		if (vn->vn_nr_item > 0) {
 			set_parameters(tb, h, 0, 0, 1, NULL, -1, -1);
-			return NO_BALANCING_NEEDED;	/* no balancing for higher levels needed */
+			return NO_BALANCING_NEEDED;
 		}
-		/* new_nr_item == 0.
+		/*
+		 * new_nr_item == 0.
 		 * Current root will be deleted resulting in
-		 * decrementing the tree height. */
+		 * decrementing the tree height.
+		 */
 		set_parameters(tb, h, 0, 0, 0, NULL, -1, -1);
 		return CARRY_ON;
 	}
@@ -1602,12 +1776,18 @@ static int dc_check_balance_internal(struct tree_balance *tb, int h)
 	check_left(tb, h, lfree);
 	check_right(tb, h, rfree);
 
-	if (vn->vn_nr_item >= MIN_NR_KEY(Sh)) {	/* Balance condition for the internal node is valid.
-						 * In this case we balance only if it leads to better packing. */
-		if (vn->vn_nr_item == MIN_NR_KEY(Sh)) {	/* Here we join S[h] with one of its neighbors,
-							 * which is impossible with greater values of new_nr_item. */
+	/*
+	 * Balance condition for the internal node is valid.
+	 * In this case we balance only if it leads to better packing.
+	 */
+	if (vn->vn_nr_item >= MIN_NR_KEY(Sh)) {
+		/*
+		 * Here we join S[h] with one of its neighbors,
+		 * which is impossible with greater values of new_nr_item.
+		 */
+		if (vn->vn_nr_item == MIN_NR_KEY(Sh)) {
+			/* All contents of S[h] can be moved to L[h]. */
 			if (tb->lnum[h] >= vn->vn_nr_item + 1) {
-				/* All contents of S[h] can be moved to L[h]. */
 				int n;
 				int order_L;
 
@@ -1623,8 +1803,8 @@ static int dc_check_balance_internal(struct tree_balance *tb, int h)
 				return CARRY_ON;
 			}
 
+			/* All contents of S[h] can be moved to R[h]. */
 			if (tb->rnum[h] >= vn->vn_nr_item + 1) {
-				/* All contents of S[h] can be moved to R[h]. */
 				int n;
 				int order_R;
 
@@ -1641,8 +1821,11 @@ static int dc_check_balance_internal(struct tree_balance *tb, int h)
 			}
 		}
 
+		/*
+		 * All contents of S[h] can be moved to the neighbors
+		 * (L[h] & R[h]).
+		 */
 		if (tb->rnum[h] + tb->lnum[h] >= vn->vn_nr_item + 1) {
-			/* All contents of S[h] can be moved to the neighbors (L[h] & R[h]). */
 			int to_r;
 
 			to_r =
@@ -1659,7 +1842,10 @@ static int dc_check_balance_internal(struct tree_balance *tb, int h)
 		return NO_BALANCING_NEEDED;
 	}
 
-	/* Current node contain insufficient number of items. Balancing is required. */
+	/*
+	 * Current node contain insufficient number of items.
+	 * Balancing is required.
+	 */
 	/* Check whether we can merge S[h] with left neighbor. */
 	if (tb->lnum[h] >= vn->vn_nr_item + 1)
 		if (is_left_neighbor_in_cache(tb, h)
@@ -1726,7 +1912,8 @@ static int dc_check_balance_internal(struct tree_balance *tb, int h)
 	return CARRY_ON;
 }
 
-/* Check whether current node S[h] is balanced when Decreasing its size by
+/*
+ * Check whether current node S[h] is balanced when Decreasing its size by
  * Deleting or Truncating for LEAF node of S+tree.
  * Calculate parameters for balancing for current level h.
  * Parameters:
@@ -1743,15 +1930,21 @@ static int dc_check_balance_leaf(struct tree_balance *tb, int h)
 {
 	struct virtual_node *vn = tb->tb_vn;
 
-	/* Number of bytes that must be deleted from
-	   (value is negative if bytes are deleted) buffer which
-	   contains node being balanced.  The mnemonic is that the
-	   attempted change in node space used level is levbytes bytes. */
+	/*
+	 * Number of bytes that must be deleted from
+	 * (value is negative if bytes are deleted) buffer which
+	 * contains node being balanced.  The mnemonic is that the
+	 * attempted change in node space used level is levbytes bytes.
+	 */
 	int levbytes;
+
 	/* the maximal item size */
 	int maxsize, ret;
-	/* S0 is the node whose balance is currently being checked,
-	   and F0 is its father.  */
+
+	/*
+	 * S0 is the node whose balance is currently being checked,
+	 * and F0 is its father.
+	 */
 	struct buffer_head *S0, *F0;
 	int lfree, rfree /* free space in L and R */ ;
 
@@ -1784,9 +1977,11 @@ static int dc_check_balance_leaf(struct tree_balance *tb, int h)
 	if (are_leaves_removable(tb, lfree, rfree))
 		return CARRY_ON;
 
-	/* determine maximal number of items we can shift to the left/right  neighbor
-	   and the maximal number of bytes that can flow to the left/right neighbor
-	   from the left/right most liquid item that cannot be shifted from S[0] entirely
+	/*
+	 * determine maximal number of items we can shift to the left/right
+	 * neighbor and the maximal number of bytes that can flow to the
+	 * left/right neighbor from the left/right most liquid item that
+	 * cannot be shifted from S[0] entirely
 	 */
 	check_left(tb, h, lfree);
 	check_right(tb, h, rfree);
@@ -1810,7 +2005,10 @@ static int dc_check_balance_leaf(struct tree_balance *tb, int h)
 		return CARRY_ON;
 	}
 
-	/* All contents of S[0] can be moved to the neighbors (L[0] & R[0]). Set parameters and return */
+	/*
+	 * All contents of S[0] can be moved to the neighbors (L[0] & R[0]).
+	 * Set parameters and return
+	 */
 	if (is_leaf_removable(tb))
 		return CARRY_ON;
 
@@ -1820,7 +2018,8 @@ static int dc_check_balance_leaf(struct tree_balance *tb, int h)
 	return NO_BALANCING_NEEDED;
 }
 
-/* Check whether current node S[h] is balanced when Decreasing its size by
+/*
+ * Check whether current node S[h] is balanced when Decreasing its size by
  * Deleting or Cutting.
  * Calculate parameters for balancing for current level h.
  * Parameters:
@@ -1844,15 +2043,16 @@ static int dc_check_balance(struct tree_balance *tb, int h)
 		return dc_check_balance_leaf(tb, h);
 }
 
-/* Check whether current node S[h] is balanced.
+/*
+ * Check whether current node S[h] is balanced.
  * Calculate parameters for balancing for current level h.
  * Parameters:
  *
  *	tb	tree_balance structure:
  *
- *              tb is a large structure that must be read about in the header file
- *              at the same time as this procedure if the reader is to successfully
- *              understand this procedure
+ *              tb is a large structure that must be read about in the header
+ *		file at the same time as this procedure if the reader is
+ *		to successfully understand this procedure
  *
  *	h	current level of the node;
  *	inum	item number in S[h];
@@ -1882,8 +2082,8 @@ static int check_balance(int mode,
 	RFALSE(mode == M_INSERT && !vn->vn_ins_ih,
 	       "vs-8255: ins_ih can not be 0 in insert mode");
 
+	/* Calculate balance parameters when size of node is increasing. */
 	if (tb->insert_size[h] > 0)
-		/* Calculate balance parameters when size of node is increasing. */
 		return ip_check_balance(tb, h);
 
 	/* Calculate balance parameters when  size of node is decreasing. */
@@ -1911,21 +2111,23 @@ static int get_direct_parent(struct tree_balance *tb, int h)
 			PATH_OFFSET_POSITION(path, path_offset - 1) = 0;
 			return CARRY_ON;
 		}
-		return REPEAT_SEARCH;	/* Root is changed and we must recalculate the path. */
+		/* Root is changed and we must recalculate the path. */
+		return REPEAT_SEARCH;
 	}
 
+	/* Parent in the path is not in the tree. */
 	if (!B_IS_IN_TREE
 	    (bh = PATH_OFFSET_PBUFFER(path, path_offset - 1)))
-		return REPEAT_SEARCH;	/* Parent in the path is not in the tree. */
+		return REPEAT_SEARCH;
 
 	if ((position =
 	     PATH_OFFSET_POSITION(path,
 				  path_offset - 1)) > B_NR_ITEMS(bh))
 		return REPEAT_SEARCH;
 
+	/* Parent in the path is not parent of the current node in the tree. */
 	if (B_N_CHILD_NUM(bh, position) !=
 	    PATH_OFFSET_PBUFFER(path, path_offset)->b_blocknr)
-		/* Parent in the path is not parent of the current node in the tree. */
 		return REPEAT_SEARCH;
 
 	if (buffer_locked(bh)) {
@@ -1936,10 +2138,15 @@ static int get_direct_parent(struct tree_balance *tb, int h)
 			return REPEAT_SEARCH;
 	}
 
-	return CARRY_ON;	/* Parent in the path is unlocked and really parent of the current node.  */
+	/*
+	 * Parent in the path is unlocked and really parent
+	 * of the current node.
+	 */
+	return CARRY_ON;
 }
 
-/* Using lnum[h] and rnum[h] we should determine what neighbors
+/*
+ * Using lnum[h] and rnum[h] we should determine what neighbors
  * of S[h] we
  * need in order to balance S[h], and get them if necessary.
  * Returns:	SCHEDULE_OCCURRED - schedule occurred while the function worked;
@@ -1997,7 +2204,7 @@ static int get_neighbors(struct tree_balance *tb, int h)
 	}
 
 	/* We need right neighbor to balance S[path_offset]. */
-	if (tb->rnum[h]) {	/* We need right neighbor to balance S[path_offset]. */
+	if (tb->rnum[h]) {
 		PROC_INFO_INC(sb, need_r_neighbor[h]);
 		bh = PATH_OFFSET_PBUFFER(tb->tb_path, path_offset);
 
@@ -2053,9 +2260,11 @@ static int get_virtual_node_size(struct super_block *sb, struct buffer_head *bh)
 		(max_num_of_entries - 1) * sizeof(__u16));
 }
 
-/* maybe we should fail balancing we are going to perform when kmalloc
-   fails several times. But now it will loop until kmalloc gets
-   required memory */
+/*
+ * maybe we should fail balancing we are going to perform when kmalloc
+ * fails several times. But now it will loop until kmalloc gets
+ * required memory
+ */
 static int get_mem_for_virtual_node(struct tree_balance *tb)
 {
 	int check_fs = 0;
@@ -2064,8 +2273,8 @@ static int get_mem_for_virtual_node(struct tree_balance *tb)
 
 	size = get_virtual_node_size(tb->tb_sb, PATH_PLAST_BUFFER(tb->tb_path));
 
+	/* we have to allocate more memory for virtual node */
 	if (size > tb->vn_buf_size) {
-		/* we have to allocate more memory for virtual node */
 		if (tb->vn_buf) {
 			/* free memory allocated before */
 			kfree(tb->vn_buf);
@@ -2079,10 +2288,12 @@ static int get_mem_for_virtual_node(struct tree_balance *tb)
 		/* get memory for virtual item */
 		buf = kmalloc(size, GFP_ATOMIC | __GFP_NOWARN);
 		if (!buf) {
-			/* getting memory with GFP_KERNEL priority may involve
-			   balancing now (due to indirect_to_direct conversion on
-			   dcache shrinking). So, release path and collected
-			   resources here */
+			/*
+			 * getting memory with GFP_KERNEL priority may involve
+			 * balancing now (due to indirect_to_direct conversion
+			 * on dcache shrinking). So, release path and collected
+			 * resources here
+			 */
 			free_buffers_in_tb(tb);
 			buf = kmalloc(size, GFP_NOFS);
 			if (!buf) {
@@ -2168,8 +2379,10 @@ static int wait_tb_buffers_until_unlocked(struct tree_balance *tb)
 		for (i = tb->tb_path->path_length;
 		     !locked && i > ILLEGAL_PATH_ELEMENT_OFFSET; i--) {
 			if (PATH_OFFSET_PBUFFER(tb->tb_path, i)) {
-				/* if I understand correctly, we can only be sure the last buffer
-				 ** in the path is in the tree --clm
+				/*
+				 * if I understand correctly, we can only
+				 * be sure the last buffer in the path is
+				 * in the tree --clm
 				 */
 #ifdef CONFIG_REISERFS_CHECK
 				if (PATH_PLAST_BUFFER(tb->tb_path) ==
@@ -2256,13 +2469,15 @@ static int wait_tb_buffers_until_unlocked(struct tree_balance *tb)
 				}
 			}
 		}
-		/* as far as I can tell, this is not required.  The FEB list seems
-		 ** to be full of newly allocated nodes, which will never be locked,
-		 ** dirty, or anything else.
-		 ** To be safe, I'm putting in the checks and waits in.  For the moment,
-		 ** they are needed to keep the code in journal.c from complaining
-		 ** about the buffer.  That code is inside CONFIG_REISERFS_CHECK as well.
-		 ** --clm
+
+		/*
+		 * as far as I can tell, this is not required.  The FEB list
+		 * seems to be full of newly allocated nodes, which will
+		 * never be locked, dirty, or anything else.
+		 * To be safe, I'm putting in the checks and waits in.
+		 * For the moment, they are needed to keep the code in
+		 * journal.c from complaining about the buffer.
+		 * That code is inside CONFIG_REISERFS_CHECK as well.  --clm
 		 */
 		for (i = 0; !locked && i < MAX_FEB_SIZE; i++) {
 			if (tb->FEB[i]) {
@@ -2300,7 +2515,8 @@ static int wait_tb_buffers_until_unlocked(struct tree_balance *tb)
 	return CARRY_ON;
 }
 
-/* Prepare for balancing, that is
+/*
+ * Prepare for balancing, that is
  *	get all necessary parents, and neighbors;
  *	analyze what and where should be moved;
  *	get sufficient number of new nodes;
@@ -2309,13 +2525,14 @@ static int wait_tb_buffers_until_unlocked(struct tree_balance *tb)
  * When ported to SMP kernels, only at the last moment after all needed nodes
  * are collected in cache, will the resources be locked using the usual
  * textbook ordered lock acquisition algorithms.  Note that ensuring that
- * this code neither write locks what it does not need to write lock nor locks out of order
- * will be a pain in the butt that could have been avoided.  Grumble grumble. -Hans
+ * this code neither write locks what it does not need to write lock nor locks
+ * out of order will be a pain in the butt that could have been avoided.
+ * Grumble grumble. -Hans
  *
  * fix is meant in the sense of render unchanging
  *
- * Latency might be improved by first gathering a list of what buffers are needed
- * and then getting as many of them in parallel as possible? -Hans
+ * Latency might be improved by first gathering a list of what buffers
+ * are needed and then getting as many of them in parallel as possible? -Hans
  *
  * Parameters:
  *	op_mode	i - insert, d - delete, c - cut (truncate), p - paste (append)
@@ -2335,8 +2552,9 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 	int ret, h, item_num = PATH_LAST_POSITION(tb->tb_path);
 	int pos_in_item;
 
-	/* we set wait_tb_buffers_run when we have to restore any dirty bits cleared
-	 ** during wait_tb_buffers_run
+	/*
+	 * we set wait_tb_buffers_run when we have to restore any dirty
+	 * bits cleared during wait_tb_buffers_run
 	 */
 	int wait_tb_buffers_run = 0;
 	struct buffer_head *tbS0 = PATH_PLAST_BUFFER(tb->tb_path);
@@ -2347,14 +2565,15 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 
 	tb->fs_gen = get_generation(tb->tb_sb);
 
-	/* we prepare and log the super here so it will already be in the
-	 ** transaction when do_balance needs to change it.
-	 ** This way do_balance won't have to schedule when trying to prepare
-	 ** the super for logging
+	/*
+	 * we prepare and log the super here so it will already be in the
+	 * transaction when do_balance needs to change it.
+	 * This way do_balance won't have to schedule when trying to prepare
+	 * the super for logging
 	 */
 	reiserfs_prepare_for_journal(tb->tb_sb,
 				     SB_BUFFER_WITH_SB(tb->tb_sb), 1);
-	journal_mark_dirty(tb->transaction_handle, tb->tb_sb,
+	journal_mark_dirty(tb->transaction_handle,
 			   SB_BUFFER_WITH_SB(tb->tb_sb));
 	if (FILESYSTEM_CHANGED_TB(tb))
 		return REPEAT_SEARCH;
@@ -2408,7 +2627,7 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 #endif
 
 	if (get_mem_for_virtual_node(tb) == REPEAT_SEARCH)
-		// FIXME: maybe -ENOMEM when tb->vn_buf == 0? Now just repeat
+		/* FIXME: maybe -ENOMEM when tb->vn_buf == 0? Now just repeat */
 		return REPEAT_SEARCH;
 
 	/* Starting from the leaf level; for all levels h of the tree. */
@@ -2427,7 +2646,10 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 					goto repeat;
 				if (h != MAX_HEIGHT - 1)
 					tb->insert_size[h + 1] = 0;
-				/* ok, analysis and resource gathering are complete */
+				/*
+				 * ok, analysis and resource gathering
+				 * are complete
+				 */
 				break;
 			}
 			goto repeat;
@@ -2437,15 +2659,19 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 		if (ret != CARRY_ON)
 			goto repeat;
 
-		/* No disk space, or schedule occurred and analysis may be
-		 * invalid and needs to be redone. */
+		/*
+		 * No disk space, or schedule occurred and analysis may be
+		 * invalid and needs to be redone.
+		 */
 		ret = get_empty_nodes(tb, h);
 		if (ret != CARRY_ON)
 			goto repeat;
 
+		/*
+		 * We have a positive insert size but no nodes exist on this
+		 * level, this means that we are creating a new root.
+		 */
 		if (!PATH_H_PBUFFER(tb->tb_path, h)) {
-			/* We have a positive insert size but no nodes exist on this
-			   level, this means that we are creating a new root. */
 
 			RFALSE(tb->blknum[h] != 1,
 			       "PAP-8350: creating new empty root");
@@ -2453,11 +2679,13 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 			if (h < MAX_HEIGHT - 1)
 				tb->insert_size[h + 1] = 0;
 		} else if (!PATH_H_PBUFFER(tb->tb_path, h + 1)) {
+			/*
+			 * The tree needs to be grown, so this node S[h]
+			 * which is the root node is split into two nodes,
+			 * and a new node (S[h+1]) will be created to
+			 * become the root node.
+			 */
 			if (tb->blknum[h] > 1) {
-				/* The tree needs to be grown, so this node S[h]
-				   which is the root node is split into two nodes,
-				   and a new node (S[h+1]) will be created to
-				   become the root node.  */
 
 				RFALSE(h == MAX_HEIGHT - 1,
 				       "PAP-8355: attempt to create too high of a tree");
@@ -2487,12 +2715,14 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 		goto repeat;
 	}
 
-      repeat:
-	// fix_nodes was unable to perform its calculation due to
-	// filesystem got changed under us, lack of free disk space or i/o
-	// failure. If the first is the case - the search will be
-	// repeated. For now - free all resources acquired so far except
-	// for the new allocated nodes
+repeat:
+	/*
+	 * fix_nodes was unable to perform its calculation due to
+	 * filesystem got changed under us, lack of free disk space or i/o
+	 * failure. If the first is the case - the search will be
+	 * repeated. For now - free all resources acquired so far except
+	 * for the new allocated nodes
+	 */
 	{
 		int i;
 
@@ -2548,8 +2778,6 @@ int fix_nodes(int op_mode, struct tree_balance *tb,
 
 }
 
-/* Anatoly will probably forgive me renaming tb to tb. I just
-   wanted to make lines shorter */
 void unfix_nodes(struct tree_balance *tb)
 {
 	int i;
@@ -2578,8 +2806,10 @@ void unfix_nodes(struct tree_balance *tb)
 	for (i = 0; i < MAX_FEB_SIZE; i++) {
 		if (tb->FEB[i]) {
 			b_blocknr_t blocknr = tb->FEB[i]->b_blocknr;
-			/* de-allocated block which was not used by balancing and
-			   bforget about buffer for it */
+			/*
+			 * de-allocated block which was not used by
+			 * balancing and bforget about buffer for it
+			 */
 			brelse(tb->FEB[i]);
 			reiserfs_free_block(tb->transaction_handle, NULL,
 					    blocknr, 0);
diff --git a/fs/reiserfs/hashes.c b/fs/reiserfs/hashes.c
index 91b0cc1242a..7a26c4fe6c4 100644
--- a/fs/reiserfs/hashes.c
+++ b/fs/reiserfs/hashes.c
@@ -12,12 +12,6 @@
  * Yura's function is added (04/07/2000)
  */
 
-//
-// keyed_hash
-// yura_hash
-// r5_hash
-//
-
 #include <linux/kernel.h>
 #include "reiserfs.h"
 #include <asm/types.h>
@@ -56,7 +50,7 @@ u32 keyed_hash(const signed char *msg, int len)
 	u32 pad;
 	int i;
 
-	//      assert(len >= 0 && len < 256);
+	/*      assert(len >= 0 && len < 256); */
 
 	pad = (u32) len | ((u32) len << 8);
 	pad |= pad << 16;
@@ -127,9 +121,10 @@ u32 keyed_hash(const signed char *msg, int len)
 	return h0 ^ h1;
 }
 
-/* What follows in this file is copyright 2000 by Hans Reiser, and the
- * licensing of what follows is governed by reiserfs/README */
-
+/*
+ * What follows in this file is copyright 2000 by Hans Reiser, and the
+ * licensing of what follows is governed by reiserfs/README
+ */
 u32 yura_hash(const signed char *msg, int len)
 {
 	int j, pow;
diff --git a/fs/reiserfs/ibalance.c b/fs/reiserfs/ibalance.c
index e1978fd895f..73231b1ebdb 100644
--- a/fs/reiserfs/ibalance.c
+++ b/fs/reiserfs/ibalance.c
@@ -12,7 +12,10 @@
 int balance_internal(struct tree_balance *,
 		     int, int, struct item_head *, struct buffer_head **);
 
-/* modes of internal_shift_left, internal_shift_right and internal_insert_childs */
+/*
+ * modes of internal_shift_left, internal_shift_right and
+ * internal_insert_childs
+ */
 #define INTERNAL_SHIFT_FROM_S_TO_L 0
 #define INTERNAL_SHIFT_FROM_R_TO_S 1
 #define INTERNAL_SHIFT_FROM_L_TO_S 2
@@ -32,7 +35,9 @@ static void internal_define_dest_src_infos(int shift_mode,
 	memset(src_bi, 0, sizeof(struct buffer_info));
 	/* define dest, src, dest parent, dest position */
 	switch (shift_mode) {
-	case INTERNAL_SHIFT_FROM_S_TO_L:	/* used in internal_shift_left */
+
+	/* used in internal_shift_left */
+	case INTERNAL_SHIFT_FROM_S_TO_L:
 		src_bi->tb = tb;
 		src_bi->bi_bh = PATH_H_PBUFFER(tb->tb_path, h);
 		src_bi->bi_parent = PATH_H_PPARENT(tb->tb_path, h);
@@ -52,12 +57,14 @@ static void internal_define_dest_src_infos(int shift_mode,
 		dest_bi->tb = tb;
 		dest_bi->bi_bh = PATH_H_PBUFFER(tb->tb_path, h);
 		dest_bi->bi_parent = PATH_H_PPARENT(tb->tb_path, h);
-		dest_bi->bi_position = PATH_H_POSITION(tb->tb_path, h + 1);	/* dest position is analog of dest->b_item_order */
+		/* dest position is analog of dest->b_item_order */
+		dest_bi->bi_position = PATH_H_POSITION(tb->tb_path, h + 1);
 		*d_key = tb->lkey[h];
 		*cf = tb->CFL[h];
 		break;
 
-	case INTERNAL_SHIFT_FROM_R_TO_S:	/* used in internal_shift_left */
+	/* used in internal_shift_left */
+	case INTERNAL_SHIFT_FROM_R_TO_S:
 		src_bi->tb = tb;
 		src_bi->bi_bh = tb->R[h];
 		src_bi->bi_parent = tb->FR[h];
@@ -111,7 +118,8 @@ static void internal_define_dest_src_infos(int shift_mode,
 	}
 }
 
-/* Insert count node pointers into buffer cur before position to + 1.
+/*
+ * Insert count node pointers into buffer cur before position to + 1.
  * Insert count items into buffer cur before position to.
  * Items and node pointers are specified by inserted and bh respectively.
  */
@@ -146,14 +154,14 @@ static void internal_insert_childs(struct buffer_info *cur_bi,
 
 	/* copy to_be_insert disk children */
 	for (i = 0; i < count; i++) {
-		put_dc_size(&(new_dc[i]),
+		put_dc_size(&new_dc[i],
 			    MAX_CHILD_SIZE(bh[i]) - B_FREE_SPACE(bh[i]));
-		put_dc_block_number(&(new_dc[i]), bh[i]->b_blocknr);
+		put_dc_block_number(&new_dc[i], bh[i]->b_blocknr);
 	}
 	memcpy(dc, new_dc, DC_SIZE * count);
 
 	/* prepare space for count items  */
-	ih = B_N_PDELIM_KEY(cur, ((to == -1) ? 0 : to));
+	ih = internal_key(cur, ((to == -1) ? 0 : to));
 
 	memmove(ih + count, ih,
 		(nr - to) * KEY_SIZE + (nr + 1 + count) * DC_SIZE);
@@ -190,8 +198,10 @@ static void internal_insert_childs(struct buffer_info *cur_bi,
 
 }
 
-/* Delete del_num items and node pointers from buffer cur starting from *
- * the first_i'th item and first_p'th pointers respectively.		*/
+/*
+ * Delete del_num items and node pointers from buffer cur starting from
+ * the first_i'th item and first_p'th pointers respectively.
+ */
 static void internal_delete_pointers_items(struct buffer_info *cur_bi,
 					   int first_p,
 					   int first_i, int del_num)
@@ -233,7 +243,7 @@ static void internal_delete_pointers_items(struct buffer_info *cur_bi,
 	dc = B_N_CHILD(cur, first_p);
 
 	memmove(dc, dc + del_num, (nr + 1 - first_p - del_num) * DC_SIZE);
-	key = B_N_PDELIM_KEY(cur, first_i);
+	key = internal_key(cur, first_i);
 	memmove(key, key + del_num,
 		(nr - first_i - del_num) * KEY_SIZE + (nr + 1 -
 						       del_num) * DC_SIZE);
@@ -270,22 +280,30 @@ static void internal_delete_childs(struct buffer_info *cur_bi, int from, int n)
 
 	i_from = (from == 0) ? from : from - 1;
 
-	/* delete n pointers starting from `from' position in CUR;
-	   delete n keys starting from 'i_from' position in CUR;
+	/*
+	 * delete n pointers starting from `from' position in CUR;
+	 * delete n keys starting from 'i_from' position in CUR;
 	 */
 	internal_delete_pointers_items(cur_bi, from, i_from, n);
 }
 
-/* copy cpy_num node pointers and cpy_num - 1 items from buffer src to buffer dest
-* last_first == FIRST_TO_LAST means, that we copy first items from src to tail of dest
- * last_first == LAST_TO_FIRST means, that we copy last items from src to head of dest
+/*
+ * copy cpy_num node pointers and cpy_num - 1 items from buffer src to buffer
+ * dest
+ * last_first == FIRST_TO_LAST means that we copy first items
+ *                             from src to tail of dest
+ * last_first == LAST_TO_FIRST means that we copy last items
+ *                             from src to head of dest
  */
 static void internal_copy_pointers_items(struct buffer_info *dest_bi,
 					 struct buffer_head *src,
 					 int last_first, int cpy_num)
 {
-	/* ATTENTION! Number of node pointers in DEST is equal to number of items in DEST *
-	 * as delimiting key have already inserted to buffer dest.*/
+	/*
+	 * ATTENTION! Number of node pointers in DEST is equal to number
+	 * of items in DEST  as delimiting key have already inserted to
+	 * buffer dest.
+	 */
 	struct buffer_head *dest = dest_bi->bi_bh;
 	int nr_dest, nr_src;
 	int dest_order, src_order;
@@ -330,13 +348,13 @@ static void internal_copy_pointers_items(struct buffer_info *dest_bi,
 	memcpy(dc, B_N_CHILD(src, src_order), DC_SIZE * cpy_num);
 
 	/* prepare space for cpy_num - 1 item headers */
-	key = B_N_PDELIM_KEY(dest, dest_order);
+	key = internal_key(dest, dest_order);
 	memmove(key + cpy_num - 1, key,
 		KEY_SIZE * (nr_dest - dest_order) + DC_SIZE * (nr_dest +
 							       cpy_num));
 
 	/* insert headers */
-	memcpy(key, B_N_PDELIM_KEY(src, src_order), KEY_SIZE * (cpy_num - 1));
+	memcpy(key, internal_key(src, src_order), KEY_SIZE * (cpy_num - 1));
 
 	/* sizes, item number */
 	set_blkh_nr_item(blkh, blkh_nr_item(blkh) + (cpy_num - 1));
@@ -366,7 +384,9 @@ static void internal_copy_pointers_items(struct buffer_info *dest_bi,
 
 }
 
-/* Copy cpy_num node pointers and cpy_num - 1 items from buffer src to buffer dest.
+/*
+ * Copy cpy_num node pointers and cpy_num - 1 items from buffer src to
+ * buffer dest.
  * Delete cpy_num - del_par items and node pointers from buffer src.
  * last_first == FIRST_TO_LAST means, that we copy/delete first items from src.
  * last_first == LAST_TO_FIRST means, that we copy/delete last items from src.
@@ -385,8 +405,10 @@ static void internal_move_pointers_items(struct buffer_info *dest_bi,
 	if (last_first == FIRST_TO_LAST) {	/* shift_left occurs */
 		first_pointer = 0;
 		first_item = 0;
-		/* delete cpy_num - del_par pointers and keys starting for pointers with first_pointer,
-		   for key - with first_item */
+		/*
+		 * delete cpy_num - del_par pointers and keys starting for
+		 * pointers with first_pointer, for key - with first_item
+		 */
 		internal_delete_pointers_items(src_bi, first_pointer,
 					       first_item, cpy_num - del_par);
 	} else {		/* shift_right occurs */
@@ -404,7 +426,9 @@ static void internal_move_pointers_items(struct buffer_info *dest_bi,
 }
 
 /* Insert n_src'th key of buffer src before n_dest'th key of buffer dest. */
-static void internal_insert_key(struct buffer_info *dest_bi, int dest_position_before,	/* insert key before key with n_dest number */
+static void internal_insert_key(struct buffer_info *dest_bi,
+				/* insert key before key with n_dest number */
+				int dest_position_before,
 				struct buffer_head *src, int src_position)
 {
 	struct buffer_head *dest = dest_bi->bi_bh;
@@ -429,12 +453,12 @@ static void internal_insert_key(struct buffer_info *dest_bi, int dest_position_b
 	nr = blkh_nr_item(blkh);
 
 	/* prepare space for inserting key */
-	key = B_N_PDELIM_KEY(dest, dest_position_before);
+	key = internal_key(dest, dest_position_before);
 	memmove(key + 1, key,
 		(nr - dest_position_before) * KEY_SIZE + (nr + 1) * DC_SIZE);
 
 	/* insert key */
-	memcpy(key, B_N_PDELIM_KEY(src, src_position), KEY_SIZE);
+	memcpy(key, internal_key(src, src_position), KEY_SIZE);
 
 	/* Change dirt, free space, item number fields. */
 
@@ -453,13 +477,19 @@ static void internal_insert_key(struct buffer_info *dest_bi, int dest_position_b
 	}
 }
 
-/* Insert d_key'th (delimiting) key from buffer cfl to tail of dest.
- * Copy pointer_amount node pointers and pointer_amount - 1 items from buffer src to buffer dest.
+/*
+ * Insert d_key'th (delimiting) key from buffer cfl to tail of dest.
+ * Copy pointer_amount node pointers and pointer_amount - 1 items from
+ * buffer src to buffer dest.
  * Replace  d_key'th key in buffer cfl.
  * Delete pointer_amount items and node pointers from buffer src.
  */
 /* this can be invoked both to shift from S to L and from R to S */
-static void internal_shift_left(int mode,	/* INTERNAL_FROM_S_TO_L | INTERNAL_FROM_R_TO_S */
+static void internal_shift_left(
+				/*
+				 * INTERNAL_FROM_S_TO_L | INTERNAL_FROM_R_TO_S
+				 */
+				int mode,
 				struct tree_balance *tb,
 				int h, int pointer_amount)
 {
@@ -473,7 +503,10 @@ static void internal_shift_left(int mode,	/* INTERNAL_FROM_S_TO_L | INTERNAL_FRO
 	/*printk("pointer_amount = %d\n",pointer_amount); */
 
 	if (pointer_amount) {
-		/* insert delimiting key from common father of dest and src to node dest into position B_NR_ITEM(dest) */
+		/*
+		 * insert delimiting key from common father of dest and
+		 * src to node dest into position B_NR_ITEM(dest)
+		 */
 		internal_insert_key(&dest_bi, B_NR_ITEMS(dest_bi.bi_bh), cf,
 				    d_key_position);
 
@@ -492,7 +525,8 @@ static void internal_shift_left(int mode,	/* INTERNAL_FROM_S_TO_L | INTERNAL_FRO
 
 }
 
-/* Insert delimiting key to L[h].
+/*
+ * Insert delimiting key to L[h].
  * Copy n node pointers and n - 1 items from buffer S[h] to L[h].
  * Delete n - 1 items and node pointers from buffer S[h].
  */
@@ -507,23 +541,27 @@ static void internal_shift1_left(struct tree_balance *tb,
 	internal_define_dest_src_infos(INTERNAL_SHIFT_FROM_S_TO_L, tb, h,
 				       &dest_bi, &src_bi, &d_key_position, &cf);
 
-	if (pointer_amount > 0)	/* insert lkey[h]-th key  from CFL[h] to left neighbor L[h] */
+	/* insert lkey[h]-th key  from CFL[h] to left neighbor L[h] */
+	if (pointer_amount > 0)
 		internal_insert_key(&dest_bi, B_NR_ITEMS(dest_bi.bi_bh), cf,
 				    d_key_position);
-	/*            internal_insert_key (tb->L[h], B_NR_ITEM(tb->L[h]), tb->CFL[h], tb->lkey[h]); */
 
 	/* last parameter is del_parameter */
 	internal_move_pointers_items(&dest_bi, &src_bi, FIRST_TO_LAST,
 				     pointer_amount, 1);
-	/*    internal_move_pointers_items (tb->L[h], tb->S[h], FIRST_TO_LAST, pointer_amount, 1); */
 }
 
-/* Insert d_key'th (delimiting) key from buffer cfr to head of dest.
+/*
+ * Insert d_key'th (delimiting) key from buffer cfr to head of dest.
  * Copy n node pointers and n - 1 items from buffer src to buffer dest.
  * Replace  d_key'th key in buffer cfr.
  * Delete n items and node pointers from buffer src.
  */
-static void internal_shift_right(int mode,	/* INTERNAL_FROM_S_TO_R | INTERNAL_FROM_L_TO_S */
+static void internal_shift_right(
+				 /*
+				  * INTERNAL_FROM_S_TO_R | INTERNAL_FROM_L_TO_S
+				  */
+				 int mode,
 				 struct tree_balance *tb,
 				 int h, int pointer_amount)
 {
@@ -538,7 +576,10 @@ static void internal_shift_right(int mode,	/* INTERNAL_FROM_S_TO_R | INTERNAL_FR
 	nr = B_NR_ITEMS(src_bi.bi_bh);
 
 	if (pointer_amount > 0) {
-		/* insert delimiting key from common father of dest and src to dest node into position 0 */
+		/*
+		 * insert delimiting key from common father of dest
+		 * and src to dest node into position 0
+		 */
 		internal_insert_key(&dest_bi, 0, cf, d_key_position);
 		if (nr == pointer_amount - 1) {
 			RFALSE(src_bi.bi_bh != PATH_H_PBUFFER(tb->tb_path, h) /*tb->S[h] */ ||
@@ -559,7 +600,8 @@ static void internal_shift_right(int mode,	/* INTERNAL_FROM_S_TO_R | INTERNAL_FR
 				     pointer_amount, 0);
 }
 
-/* Insert delimiting key to R[h].
+/*
+ * Insert delimiting key to R[h].
  * Copy n node pointers and n - 1 items from buffer S[h] to R[h].
  * Delete n - 1 items and node pointers from buffer S[h].
  */
@@ -574,18 +616,19 @@ static void internal_shift1_right(struct tree_balance *tb,
 	internal_define_dest_src_infos(INTERNAL_SHIFT_FROM_S_TO_R, tb, h,
 				       &dest_bi, &src_bi, &d_key_position, &cf);
 
-	if (pointer_amount > 0)	/* insert rkey from CFR[h] to right neighbor R[h] */
+	/* insert rkey from CFR[h] to right neighbor R[h] */
+	if (pointer_amount > 0)
 		internal_insert_key(&dest_bi, 0, cf, d_key_position);
-	/*            internal_insert_key (tb->R[h], 0, tb->CFR[h], tb->rkey[h]); */
 
 	/* last parameter is del_parameter */
 	internal_move_pointers_items(&dest_bi, &src_bi, LAST_TO_FIRST,
 				     pointer_amount, 1);
-	/*    internal_move_pointers_items (tb->R[h], tb->S[h], LAST_TO_FIRST, pointer_amount, 1); */
 }
 
-/* Delete insert_num node pointers together with their left items
- * and balance current node.*/
+/*
+ * Delete insert_num node pointers together with their left items
+ * and balance current node.
+ */
 static void balance_internal_when_delete(struct tree_balance *tb,
 					 int h, int child_pos)
 {
@@ -626,9 +669,11 @@ static void balance_internal_when_delete(struct tree_balance *tb,
 				new_root = tb->R[h - 1];
 			else
 				new_root = tb->L[h - 1];
-			/* switch super block's tree root block number to the new value */
+			/*
+			 * switch super block's tree root block
+			 * number to the new value */
 			PUT_SB_ROOT_BLOCK(tb->tb_sb, new_root->b_blocknr);
-			//REISERFS_SB(tb->tb_sb)->s_rs->s_tree_height --;
+			/*REISERFS_SB(tb->tb_sb)->s_rs->s_tree_height --; */
 			PUT_SB_TREE_HEIGHT(tb->tb_sb,
 					   SB_TREE_HEIGHT(tb->tb_sb) - 1);
 
@@ -636,8 +681,8 @@ static void balance_internal_when_delete(struct tree_balance *tb,
 						 REISERFS_SB(tb->tb_sb)->s_sbh,
 						 1);
 			/*&&&&&&&&&&&&&&&&&&&&&& */
+			/* use check_internal if new root is an internal node */
 			if (h > 1)
-				/* use check_internal if new root is an internal node */
 				check_internal(new_root);
 			/*&&&&&&&&&&&&&&&&&&&&&& */
 
@@ -648,7 +693,8 @@ static void balance_internal_when_delete(struct tree_balance *tb,
 		return;
 	}
 
-	if (tb->L[h] && tb->lnum[h] == -B_NR_ITEMS(tb->L[h]) - 1) {	/* join S[h] with L[h] */
+	/* join S[h] with L[h] */
+	if (tb->L[h] && tb->lnum[h] == -B_NR_ITEMS(tb->L[h]) - 1) {
 
 		RFALSE(tb->rnum[h] != 0,
 		       "invalid tb->rnum[%d]==%d when joining S[h] with L[h]",
@@ -660,7 +706,8 @@ static void balance_internal_when_delete(struct tree_balance *tb,
 		return;
 	}
 
-	if (tb->R[h] && tb->rnum[h] == -B_NR_ITEMS(tb->R[h]) - 1) {	/* join S[h] with R[h] */
+	/* join S[h] with R[h] */
+	if (tb->R[h] && tb->rnum[h] == -B_NR_ITEMS(tb->R[h]) - 1) {
 		RFALSE(tb->lnum[h] != 0,
 		       "invalid tb->lnum[%d]==%d when joining S[h] with R[h]",
 		       h, tb->lnum[h]);
@@ -671,17 +718,18 @@ static void balance_internal_when_delete(struct tree_balance *tb,
 		return;
 	}
 
-	if (tb->lnum[h] < 0) {	/* borrow from left neighbor L[h] */
+	/* borrow from left neighbor L[h] */
+	if (tb->lnum[h] < 0) {
 		RFALSE(tb->rnum[h] != 0,
 		       "wrong tb->rnum[%d]==%d when borrow from L[h]", h,
 		       tb->rnum[h]);
-		/*internal_shift_right (tb, h, tb->L[h], tb->CFL[h], tb->lkey[h], tb->S[h], -tb->lnum[h]); */
 		internal_shift_right(INTERNAL_SHIFT_FROM_L_TO_S, tb, h,
 				     -tb->lnum[h]);
 		return;
 	}
 
-	if (tb->rnum[h] < 0) {	/* borrow from right neighbor R[h] */
+	/* borrow from right neighbor R[h] */
+	if (tb->rnum[h] < 0) {
 		RFALSE(tb->lnum[h] != 0,
 		       "invalid tb->lnum[%d]==%d when borrow from R[h]",
 		       h, tb->lnum[h]);
@@ -689,7 +737,8 @@ static void balance_internal_when_delete(struct tree_balance *tb,
 		return;
 	}
 
-	if (tb->lnum[h] > 0) {	/* split S[h] into two parts and put them into neighbors */
+	/* split S[h] into two parts and put them into neighbors */
+	if (tb->lnum[h] > 0) {
 		RFALSE(tb->rnum[h] == 0 || tb->lnum[h] + tb->rnum[h] != n + 1,
 		       "invalid tb->lnum[%d]==%d or tb->rnum[%d]==%d when S[h](item number == %d) is split between them",
 		       h, tb->lnum[h], h, tb->rnum[h], n);
@@ -717,7 +766,7 @@ static void replace_lkey(struct tree_balance *tb, int h, struct item_head *key)
 	if (B_NR_ITEMS(PATH_H_PBUFFER(tb->tb_path, h)) == 0)
 		return;
 
-	memcpy(B_N_PDELIM_KEY(tb->CFL[h], tb->lkey[h]), key, KEY_SIZE);
+	memcpy(internal_key(tb->CFL[h], tb->lkey[h]), key, KEY_SIZE);
 
 	do_balance_mark_internal_dirty(tb, tb->CFL[h], 0);
 }
@@ -732,34 +781,41 @@ static void replace_rkey(struct tree_balance *tb, int h, struct item_head *key)
 	       "R[h] can not be empty if it exists (item number=%d)",
 	       B_NR_ITEMS(tb->R[h]));
 
-	memcpy(B_N_PDELIM_KEY(tb->CFR[h], tb->rkey[h]), key, KEY_SIZE);
+	memcpy(internal_key(tb->CFR[h], tb->rkey[h]), key, KEY_SIZE);
 
 	do_balance_mark_internal_dirty(tb, tb->CFR[h], 0);
 }
 
-int balance_internal(struct tree_balance *tb,	/* tree_balance structure               */
-		     int h,	/* level of the tree                    */
-		     int child_pos, struct item_head *insert_key,	/* key for insertion on higher level    */
-		     struct buffer_head **insert_ptr	/* node for insertion on higher level */
-    )
-    /* if inserting/pasting
-       {
-       child_pos is the position of the node-pointer in S[h] that        *
-       pointed to S[h-1] before balancing of the h-1 level;              *
-       this means that new pointers and items must be inserted AFTER *
-       child_pos
-       }
-       else
-       {
-       it is the position of the leftmost pointer that must be deleted (together with
-       its corresponding key to the left of the pointer)
-       as a result of the previous level's balancing.
-       }
-     */
+
+/*
+ * if inserting/pasting {
+ *   child_pos is the position of the node-pointer in S[h] that
+ *   pointed to S[h-1] before balancing of the h-1 level;
+ *   this means that new pointers and items must be inserted AFTER
+ *   child_pos
+ * } else {
+ *   it is the position of the leftmost pointer that must be deleted
+ *   (together with its corresponding key to the left of the pointer)
+ *   as a result of the previous level's balancing.
+ * }
+ */
+
+int balance_internal(struct tree_balance *tb,
+		     int h,	/* level of the tree */
+		     int child_pos,
+		     /* key for insertion on higher level    */
+		     struct item_head *insert_key,
+		     /* node for insertion on higher level */
+		     struct buffer_head **insert_ptr)
 {
 	struct buffer_head *tbSh = PATH_H_PBUFFER(tb->tb_path, h);
 	struct buffer_info bi;
-	int order;		/* we return this: it is 0 if there is no S[h], else it is tb->S[h]->b_item_order */
+
+	/*
+	 * we return this: it is 0 if there is no S[h],
+	 * else it is tb->S[h]->b_item_order
+	 */
+	int order;
 	int insert_num, n, k;
 	struct buffer_head *S_new;
 	struct item_head new_insert_key;
@@ -774,8 +830,10 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 	    (tbSh) ? PATH_H_POSITION(tb->tb_path,
 				     h + 1) /*tb->S[h]->b_item_order */ : 0;
 
-	/* Using insert_size[h] calculate the number insert_num of items
-	   that must be inserted to or deleted from S[h]. */
+	/*
+	 * Using insert_size[h] calculate the number insert_num of items
+	 * that must be inserted to or deleted from S[h].
+	 */
 	insert_num = tb->insert_size[h] / ((int)(KEY_SIZE + DC_SIZE));
 
 	/* Check whether insert_num is proper * */
@@ -794,23 +852,21 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 
 	k = 0;
 	if (tb->lnum[h] > 0) {
-		/* shift lnum[h] items from S[h] to the left neighbor L[h].
-		   check how many of new items fall into L[h] or CFL[h] after
-		   shifting */
+		/*
+		 * shift lnum[h] items from S[h] to the left neighbor L[h].
+		 * check how many of new items fall into L[h] or CFL[h] after
+		 * shifting
+		 */
 		n = B_NR_ITEMS(tb->L[h]);	/* number of items in L[h] */
 		if (tb->lnum[h] <= child_pos) {
 			/* new items don't fall into L[h] or CFL[h] */
 			internal_shift_left(INTERNAL_SHIFT_FROM_S_TO_L, tb, h,
 					    tb->lnum[h]);
-			/*internal_shift_left (tb->L[h],tb->CFL[h],tb->lkey[h],tbSh,tb->lnum[h]); */
 			child_pos -= tb->lnum[h];
 		} else if (tb->lnum[h] > child_pos + insert_num) {
 			/* all new items fall into L[h] */
 			internal_shift_left(INTERNAL_SHIFT_FROM_S_TO_L, tb, h,
 					    tb->lnum[h] - insert_num);
-			/*                  internal_shift_left(tb->L[h],tb->CFL[h],tb->lkey[h],tbSh,
-			   tb->lnum[h]-insert_num);
-			 */
 			/* insert insert_num keys and node-pointers into L[h] */
 			bi.tb = tb;
 			bi.bi_bh = tb->L[h];
@@ -826,7 +882,10 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 		} else {
 			struct disk_child *dc;
 
-			/* some items fall into L[h] or CFL[h], but some don't fall */
+			/*
+			 * some items fall into L[h] or CFL[h],
+			 * but some don't fall
+			 */
 			internal_shift1_left(tb, h, child_pos + 1);
 			/* calculate number of new items that fall into L[h] */
 			k = tb->lnum[h] - child_pos - 1;
@@ -841,7 +900,10 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 
 			replace_lkey(tb, h, insert_key + k);
 
-			/* replace the first node-ptr in S[h] by node-ptr to insert_ptr[k] */
+			/*
+			 * replace the first node-ptr in S[h] by
+			 * node-ptr to insert_ptr[k]
+			 */
 			dc = B_N_CHILD(tbSh, 0);
 			put_dc_size(dc,
 				    MAX_CHILD_SIZE(insert_ptr[k]) -
@@ -860,17 +922,17 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 	/* tb->lnum[h] > 0 */
 	if (tb->rnum[h] > 0) {
 		/*shift rnum[h] items from S[h] to the right neighbor R[h] */
-		/* check how many of new items fall into R or CFR after shifting */
+		/*
+		 * check how many of new items fall into R or CFR
+		 * after shifting
+		 */
 		n = B_NR_ITEMS(tbSh);	/* number of items in S[h] */
 		if (n - tb->rnum[h] >= child_pos)
 			/* new items fall into S[h] */
-			/*internal_shift_right(tb,h,tbSh,tb->CFR[h],tb->rkey[h],tb->R[h],tb->rnum[h]); */
 			internal_shift_right(INTERNAL_SHIFT_FROM_S_TO_R, tb, h,
 					     tb->rnum[h]);
 		else if (n + insert_num - tb->rnum[h] < child_pos) {
 			/* all new items fall into R[h] */
-			/*internal_shift_right(tb,h,tbSh,tb->CFR[h],tb->rkey[h],tb->R[h],
-			   tb->rnum[h] - insert_num); */
 			internal_shift_right(INTERNAL_SHIFT_FROM_S_TO_R, tb, h,
 					     tb->rnum[h] - insert_num);
 
@@ -904,7 +966,10 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 
 			replace_rkey(tb, h, insert_key + insert_num - k - 1);
 
-			/* replace the first node-ptr in R[h] by node-ptr insert_ptr[insert_num-k-1] */
+			/*
+			 * replace the first node-ptr in R[h] by
+			 * node-ptr insert_ptr[insert_num-k-1]
+			 */
 			dc = B_N_CHILD(tb->R[h], 0);
 			put_dc_size(dc,
 				    MAX_CHILD_SIZE(insert_ptr
@@ -921,7 +986,7 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 		}
 	}
 
-    /** Fill new node that appears instead of S[h] **/
+	/** Fill new node that appears instead of S[h] **/
 	RFALSE(tb->blknum[h] > 2, "blknum can not be > 2 for internal level");
 	RFALSE(tb->blknum[h] < 0, "blknum can not be < 0");
 
@@ -997,26 +1062,30 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 			/* new items don't fall into S_new */
 			/*  store the delimiting key for the next level */
 			/* new_insert_key = (n - snum)'th key in S[h] */
-			memcpy(&new_insert_key, B_N_PDELIM_KEY(tbSh, n - snum),
+			memcpy(&new_insert_key, internal_key(tbSh, n - snum),
 			       KEY_SIZE);
 			/* last parameter is del_par */
 			internal_move_pointers_items(&dest_bi, &src_bi,
 						     LAST_TO_FIRST, snum, 0);
-			/*            internal_move_pointers_items(S_new, tbSh, LAST_TO_FIRST, snum, 0); */
 		} else if (n + insert_num - snum < child_pos) {
 			/* all new items fall into S_new */
 			/*  store the delimiting key for the next level */
-			/* new_insert_key = (n + insert_item - snum)'th key in S[h] */
+			/*
+			 * new_insert_key = (n + insert_item - snum)'th
+			 * key in S[h]
+			 */
 			memcpy(&new_insert_key,
-			       B_N_PDELIM_KEY(tbSh, n + insert_num - snum),
+			       internal_key(tbSh, n + insert_num - snum),
 			       KEY_SIZE);
 			/* last parameter is del_par */
 			internal_move_pointers_items(&dest_bi, &src_bi,
 						     LAST_TO_FIRST,
 						     snum - insert_num, 0);
-			/*                  internal_move_pointers_items(S_new,tbSh,1,snum - insert_num,0); */
 
-			/* insert insert_num keys and node-pointers into S_new */
+			/*
+			 * insert insert_num keys and node-pointers
+			 * into S_new
+			 */
 			internal_insert_childs(&dest_bi,
 					       /*S_new,tb->S[h-1]->b_next, */
 					       child_pos - n - insert_num +
@@ -1033,7 +1102,6 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 			internal_move_pointers_items(&dest_bi, &src_bi,
 						     LAST_TO_FIRST,
 						     n - child_pos + 1, 1);
-			/*                  internal_move_pointers_items(S_new,tbSh,1,n - child_pos + 1,1); */
 			/* calculate number of new items that fall into S_new */
 			k = snum - n + child_pos - 1;
 
@@ -1043,7 +1111,10 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 			/* new_insert_key = insert_key[insert_num - k - 1] */
 			memcpy(&new_insert_key, insert_key + insert_num - k - 1,
 			       KEY_SIZE);
-			/* replace first node-ptr in S_new by node-ptr to insert_ptr[insert_num-k-1] */
+			/*
+			 * replace first node-ptr in S_new by node-ptr
+			 * to insert_ptr[insert_num-k-1]
+			 */
 
 			dc = B_N_CHILD(S_new, 0);
 			put_dc_size(dc,
@@ -1066,7 +1137,7 @@ int balance_internal(struct tree_balance *tb,	/* tree_balance structure
 		       || buffer_dirty(S_new), "cm-00001: bad S_new (%b)",
 		       S_new);
 
-		// S_new is released in unfix_nodes
+		/* S_new is released in unfix_nodes */
 	}
 
 	n = B_NR_ITEMS(tbSh);	/*number of items in S[h] */
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index bc8b8009897..63b2b0ec49e 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -25,7 +25,10 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 
 void reiserfs_evict_inode(struct inode *inode)
 {
-	/* We need blocks for transaction + (user+group) quota update (possibly delete) */
+	/*
+	 * We need blocks for transaction + (user+group) quota
+	 * update (possibly delete)
+	 */
 	int jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 2 +
 	    2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb);
@@ -39,8 +42,12 @@ void reiserfs_evict_inode(struct inode *inode)
 	if (inode->i_nlink)
 		goto no_delete;
 
-	/* The = 0 happens when we abort creating a new inode for some reason like lack of space.. */
-	if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) {	/* also handles bad_inode case */
+	/*
+	 * The = 0 happens when we abort creating a new inode
+	 * for some reason like lack of space..
+	 * also handles bad_inode case
+	 */
+	if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) {
 
 		reiserfs_delete_xattrs(inode);
 
@@ -54,34 +61,43 @@ void reiserfs_evict_inode(struct inode *inode)
 
 		err = reiserfs_delete_object(&th, inode);
 
-		/* Do quota update inside a transaction for journaled quotas. We must do that
-		 * after delete_object so that quota updates go into the same transaction as
-		 * stat data deletion */
+		/*
+		 * Do quota update inside a transaction for journaled quotas.
+		 * We must do that after delete_object so that quota updates
+		 * go into the same transaction as stat data deletion
+		 */
 		if (!err) {
 			int depth = reiserfs_write_unlock_nested(inode->i_sb);
 			dquot_free_inode(inode);
 			reiserfs_write_lock_nested(inode->i_sb, depth);
 		}
 
-		if (journal_end(&th, inode->i_sb, jbegin_count))
+		if (journal_end(&th))
 			goto out;
 
-		/* check return value from reiserfs_delete_object after
+		/*
+		 * check return value from reiserfs_delete_object after
 		 * ending the transaction
 		 */
 		if (err)
 		    goto out;
 
-		/* all items of file are deleted, so we can remove "save" link */
-		remove_save_link(inode, 0 /* not truncate */ );	/* we can't do anything
-								 * about an error here */
+		/*
+		 * all items of file are deleted, so we can remove
+		 * "save" link
+		 * we can't do anything about an error here
+		 */
+		remove_save_link(inode, 0 /* not truncate */);
 out:
 		reiserfs_write_unlock(inode->i_sb);
 	} else {
 		/* no object items are in the tree */
 		;
 	}
-	clear_inode(inode);	/* note this must go after the journal_end to prevent deadlock */
+
+	/* note this must go after the journal_end to prevent deadlock */
+	clear_inode(inode);
+
 	dquot_drop(inode);
 	inode->i_blocks = 0;
 	return;
@@ -103,8 +119,10 @@ static void _make_cpu_key(struct cpu_key *key, int version, __u32 dirid,
 	key->key_length = length;
 }
 
-/* take base of inode_key (it comes from inode always) (dirid, objectid) and version from an inode, set
-   offset and type of key */
+/*
+ * take base of inode_key (it comes from inode always) (dirid, objectid)
+ * and version from an inode, set offset and type of key
+ */
 void make_cpu_key(struct cpu_key *key, struct inode *inode, loff_t offset,
 		  int type, int length)
 {
@@ -114,9 +132,7 @@ void make_cpu_key(struct cpu_key *key, struct inode *inode, loff_t offset,
 		      length);
 }
 
-//
-// when key is 0, do not set version and short key
-//
+/* when key is 0, do not set version and short key */
 inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key,
 			      int version,
 			      loff_t offset, int type, int length,
@@ -132,43 +148,47 @@ inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key,
 	set_le_ih_k_type(ih, type);
 	put_ih_item_len(ih, length);
 	/*    set_ih_free_space (ih, 0); */
-	// for directory items it is entry count, for directs and stat
-	// datas - 0xffff, for indirects - 0
+	/*
+	 * for directory items it is entry count, for directs and stat
+	 * datas - 0xffff, for indirects - 0
+	 */
 	put_ih_entry_count(ih, entry_count);
 }
 
-//
-// FIXME: we might cache recently accessed indirect item
-
-// Ugh.  Not too eager for that....
-//  I cut the code until such time as I see a convincing argument (benchmark).
-// I don't want a bloated inode struct..., and I don't like code complexity....
-
-/* cutting the code is fine, since it really isn't in use yet and is easy
-** to add back in.  But, Vladimir has a really good idea here.  Think
-** about what happens for reading a file.  For each page,
-** The VFS layer calls reiserfs_readpage, who searches the tree to find
-** an indirect item.  This indirect item has X number of pointers, where
-** X is a big number if we've done the block allocation right.  But,
-** we only use one or two of these pointers during each call to readpage,
-** needlessly researching again later on.
-**
-** The size of the cache could be dynamic based on the size of the file.
-**
-** I'd also like to see us cache the location the stat data item, since
-** we are needlessly researching for that frequently.
-**
-** --chris
-*/
+/*
+ * FIXME: we might cache recently accessed indirect item
+ * Ugh.  Not too eager for that....
+ * I cut the code until such time as I see a convincing argument (benchmark).
+ * I don't want a bloated inode struct..., and I don't like code complexity....
+ */
 
-/* If this page has a file tail in it, and
-** it was read in by get_block_create_0, the page data is valid,
-** but tail is still sitting in a direct item, and we can't write to
-** it.  So, look through this page, and check all the mapped buffers
-** to make sure they have valid block numbers.  Any that don't need
-** to be unmapped, so that __block_write_begin will correctly call
-** reiserfs_get_block to convert the tail into an unformatted node
-*/
+/*
+ * cutting the code is fine, since it really isn't in use yet and is easy
+ * to add back in.  But, Vladimir has a really good idea here.  Think
+ * about what happens for reading a file.  For each page,
+ * The VFS layer calls reiserfs_readpage, who searches the tree to find
+ * an indirect item.  This indirect item has X number of pointers, where
+ * X is a big number if we've done the block allocation right.  But,
+ * we only use one or two of these pointers during each call to readpage,
+ * needlessly researching again later on.
+ *
+ * The size of the cache could be dynamic based on the size of the file.
+ *
+ * I'd also like to see us cache the location the stat data item, since
+ * we are needlessly researching for that frequently.
+ *
+ * --chris
+ */
+
+/*
+ * If this page has a file tail in it, and
+ * it was read in by get_block_create_0, the page data is valid,
+ * but tail is still sitting in a direct item, and we can't write to
+ * it.  So, look through this page, and check all the mapped buffers
+ * to make sure they have valid block numbers.  Any that don't need
+ * to be unmapped, so that __block_write_begin will correctly call
+ * reiserfs_get_block to convert the tail into an unformatted node
+ */
 static inline void fix_tail_page_for_writing(struct page *page)
 {
 	struct buffer_head *head, *next, *bh;
@@ -186,8 +206,10 @@ static inline void fix_tail_page_for_writing(struct page *page)
 	}
 }
 
-/* reiserfs_get_block does not need to allocate a block only if it has been
-   done already or non-hole position has been found in the indirect item */
+/*
+ * reiserfs_get_block does not need to allocate a block only if it has been
+ * done already or non-hole position has been found in the indirect item
+ */
 static inline int allocation_needed(int retval, b_blocknr_t allocated,
 				    struct item_head *ih,
 				    __le32 * item, int pos_in_item)
@@ -211,14 +233,16 @@ static inline void set_block_dev_mapped(struct buffer_head *bh,
 	map_bh(bh, inode->i_sb, block);
 }
 
-//
-// files which were created in the earlier version can not be longer,
-// than 2 gb
-//
+/*
+ * files which were created in the earlier version can not be longer,
+ * than 2 gb
+ */
 static int file_capable(struct inode *inode, sector_t block)
 {
-	if (get_inode_item_key_version(inode) != KEY_FORMAT_3_5 ||	// it is new file.
-	    block < (1 << (31 - inode->i_sb->s_blocksize_bits)))	// old file, but 'block' is inside of 2gb
+	/* it is new file. */
+	if (get_inode_item_key_version(inode) != KEY_FORMAT_3_5 ||
+	    /* old file, but 'block' is inside of 2gb */
+	    block < (1 << (31 - inode->i_sb->s_blocksize_bits)))
 		return 1;
 
 	return 0;
@@ -228,7 +252,6 @@ static int restart_transaction(struct reiserfs_transaction_handle *th,
 			       struct inode *inode, struct treepath *path)
 {
 	struct super_block *s = th->t_super;
-	int len = th->t_blocks_allocated;
 	int err;
 
 	BUG_ON(!th->t_trans_id);
@@ -241,7 +264,7 @@ static int restart_transaction(struct reiserfs_transaction_handle *th,
 		return 0;
 	}
 	reiserfs_update_sd(th, inode);
-	err = journal_end(th, s, len);
+	err = journal_end(th);
 	if (!err) {
 		err = journal_begin(th, s, JOURNAL_PER_BALANCE_CNT * 6);
 		if (!err)
@@ -250,14 +273,14 @@ static int restart_transaction(struct reiserfs_transaction_handle *th,
 	return err;
 }
 
-// it is called by get_block when create == 0. Returns block number
-// for 'block'-th logical block of file. When it hits direct item it
-// returns 0 (being called from bmap) or read direct item into piece
-// of page (bh_result)
-
-// Please improve the english/clarity in the comment above, as it is
-// hard to understand.
-
+/*
+ * it is called by get_block when create == 0. Returns block number
+ * for 'block'-th logical block of file. When it hits direct item it
+ * returns 0 (being called from bmap) or read direct item into piece
+ * of page (bh_result)
+ * Please improve the english/clarity in the comment above, as it is
+ * hard to understand.
+ */
 static int _get_block_create_0(struct inode *inode, sector_t block,
 			       struct buffer_head *bh_result, int args)
 {
@@ -273,7 +296,7 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 	int done = 0;
 	unsigned long offset;
 
-	// prepare the key to look for the 'block'-th block of file
+	/* prepare the key to look for the 'block'-th block of file */
 	make_cpu_key(&key, inode,
 		     (loff_t) block * inode->i_sb->s_blocksize + 1, TYPE_ANY,
 		     3);
@@ -285,23 +308,28 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 			kunmap(bh_result->b_page);
 		if (result == IO_ERROR)
 			return -EIO;
-		// We do not return -ENOENT if there is a hole but page is uptodate, because it means
-		// That there is some MMAPED data associated with it that is yet to be written to disk.
+		/*
+		 * We do not return -ENOENT if there is a hole but page is
+		 * uptodate, because it means that there is some MMAPED data
+		 * associated with it that is yet to be written to disk.
+		 */
 		if ((args & GET_BLOCK_NO_HOLE)
 		    && !PageUptodate(bh_result->b_page)) {
 			return -ENOENT;
 		}
 		return 0;
 	}
-	//
+
 	bh = get_last_bh(&path);
-	ih = get_ih(&path);
+	ih = tp_item_head(&path);
 	if (is_indirect_le_ih(ih)) {
-		__le32 *ind_item = (__le32 *) B_I_PITEM(bh, ih);
+		__le32 *ind_item = (__le32 *) ih_item_body(bh, ih);
 
-		/* FIXME: here we could cache indirect item or part of it in
-		   the inode to avoid search_by_key in case of subsequent
-		   access to file */
+		/*
+		 * FIXME: here we could cache indirect item or part of it in
+		 * the inode to avoid search_by_key in case of subsequent
+		 * access to file
+		 */
 		blocknr = get_block_num(ind_item, path.pos_in_item);
 		ret = 0;
 		if (blocknr) {
@@ -311,8 +339,12 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 				set_buffer_boundary(bh_result);
 			}
 		} else
-			// We do not return -ENOENT if there is a hole but page is uptodate, because it means
-			// That there is some MMAPED data associated with it that is yet to  be written to disk.
+			/*
+			 * We do not return -ENOENT if there is a hole but
+			 * page is uptodate, because it means that there is
+			 * some MMAPED data associated with it that is
+			 * yet to be written to disk.
+			 */
 		if ((args & GET_BLOCK_NO_HOLE)
 			    && !PageUptodate(bh_result->b_page)) {
 			ret = -ENOENT;
@@ -323,41 +355,45 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 			kunmap(bh_result->b_page);
 		return ret;
 	}
-	// requested data are in direct item(s)
+	/* requested data are in direct item(s) */
 	if (!(args & GET_BLOCK_READ_DIRECT)) {
-		// we are called by bmap. FIXME: we can not map block of file
-		// when it is stored in direct item(s)
+		/*
+		 * we are called by bmap. FIXME: we can not map block of file
+		 * when it is stored in direct item(s)
+		 */
 		pathrelse(&path);
 		if (p)
 			kunmap(bh_result->b_page);
 		return -ENOENT;
 	}
 
-	/* if we've got a direct item, and the buffer or page was uptodate,
-	 ** we don't want to pull data off disk again.  skip to the
-	 ** end, where we map the buffer and return
+	/*
+	 * if we've got a direct item, and the buffer or page was uptodate,
+	 * we don't want to pull data off disk again.  skip to the
+	 * end, where we map the buffer and return
 	 */
 	if (buffer_uptodate(bh_result)) {
 		goto finished;
 	} else
 		/*
-		 ** grab_tail_page can trigger calls to reiserfs_get_block on up to date
-		 ** pages without any buffers.  If the page is up to date, we don't want
-		 ** read old data off disk.  Set the up to date bit on the buffer instead
-		 ** and jump to the end
+		 * grab_tail_page can trigger calls to reiserfs_get_block on
+		 * up to date pages without any buffers.  If the page is up
+		 * to date, we don't want read old data off disk.  Set the up
+		 * to date bit on the buffer instead and jump to the end
 		 */
 	if (!bh_result->b_page || PageUptodate(bh_result->b_page)) {
 		set_buffer_uptodate(bh_result);
 		goto finished;
 	}
-	// read file tail into part of page
+	/* read file tail into part of page */
 	offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1);
 	copy_item_head(&tmp_ih, ih);
 
-	/* we only want to kmap if we are reading the tail into the page.
-	 ** this is not the common case, so we don't kmap until we are
-	 ** sure we need to.  But, this means the item might move if
-	 ** kmap schedules
+	/*
+	 * we only want to kmap if we are reading the tail into the page.
+	 * this is not the common case, so we don't kmap until we are
+	 * sure we need to.  But, this means the item might move if
+	 * kmap schedules
 	 */
 	if (!p)
 		p = (char *)kmap(bh_result->b_page);
@@ -368,10 +404,11 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 		if (!is_direct_le_ih(ih)) {
 			BUG();
 		}
-		/* make sure we don't read more bytes than actually exist in
-		 ** the file.  This can happen in odd cases where i_size isn't
-		 ** correct, and when direct item padding results in a few
-		 ** extra bytes at the end of the direct item
+		/*
+		 * make sure we don't read more bytes than actually exist in
+		 * the file.  This can happen in odd cases where i_size isn't
+		 * correct, and when direct item padding results in a few
+		 * extra bytes at the end of the direct item
 		 */
 		if ((le_ih_k_offset(ih) + path.pos_in_item) > inode->i_size)
 			break;
@@ -383,40 +420,43 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 		} else {
 			chars = ih_item_len(ih) - path.pos_in_item;
 		}
-		memcpy(p, B_I_PITEM(bh, ih) + path.pos_in_item, chars);
+		memcpy(p, ih_item_body(bh, ih) + path.pos_in_item, chars);
 
 		if (done)
 			break;
 
 		p += chars;
 
+		/*
+		 * we done, if read direct item is not the last item of
+		 * node FIXME: we could try to check right delimiting key
+		 * to see whether direct item continues in the right
+		 * neighbor or rely on i_size
+		 */
 		if (PATH_LAST_POSITION(&path) != (B_NR_ITEMS(bh) - 1))
-			// we done, if read direct item is not the last item of
-			// node FIXME: we could try to check right delimiting key
-			// to see whether direct item continues in the right
-			// neighbor or rely on i_size
 			break;
 
-		// update key to look for the next piece
+		/* update key to look for the next piece */
 		set_cpu_key_k_offset(&key, cpu_key_k_offset(&key) + chars);
 		result = search_for_position_by_key(inode->i_sb, &key, &path);
 		if (result != POSITION_FOUND)
-			// i/o error most likely
+			/* i/o error most likely */
 			break;
 		bh = get_last_bh(&path);
-		ih = get_ih(&path);
+		ih = tp_item_head(&path);
 	} while (1);
 
 	flush_dcache_page(bh_result->b_page);
 	kunmap(bh_result->b_page);
 
-      finished:
+finished:
 	pathrelse(&path);
 
 	if (result == IO_ERROR)
 		return -EIO;
 
-	/* this buffer has valid data, but isn't valid for io.  mapping it to
+	/*
+	 * this buffer has valid data, but isn't valid for io.  mapping it to
 	 * block #0 tells the rest of reiserfs it just has a tail in it
 	 */
 	map_bh(bh_result, inode->i_sb, 0);
@@ -424,8 +464,10 @@ static int _get_block_create_0(struct inode *inode, sector_t block,
 	return 0;
 }
 
-// this is called to create file map. So, _get_block_create_0 will not
-// read direct item
+/*
+ * this is called to create file map. So, _get_block_create_0 will not
+ * read direct item
+ */
 static int reiserfs_bmap(struct inode *inode, sector_t block,
 			 struct buffer_head *bh_result, int create)
 {
@@ -439,22 +481,23 @@ static int reiserfs_bmap(struct inode *inode, sector_t block,
 	return 0;
 }
 
-/* special version of get_block that is only used by grab_tail_page right
-** now.  It is sent to __block_write_begin, and when you try to get a
-** block past the end of the file (or a block from a hole) it returns
-** -ENOENT instead of a valid buffer.  __block_write_begin expects to
-** be able to do i/o on the buffers returned, unless an error value
-** is also returned.
-**
-** So, this allows __block_write_begin to be used for reading a single block
-** in a page.  Where it does not produce a valid page for holes, or past the
-** end of the file.  This turns out to be exactly what we need for reading
-** tails for conversion.
-**
-** The point of the wrapper is forcing a certain value for create, even
-** though the VFS layer is calling this function with create==1.  If you
-** don't want to send create == GET_BLOCK_NO_HOLE to reiserfs_get_block,
-** don't use this function.
+/*
+ * special version of get_block that is only used by grab_tail_page right
+ * now.  It is sent to __block_write_begin, and when you try to get a
+ * block past the end of the file (or a block from a hole) it returns
+ * -ENOENT instead of a valid buffer.  __block_write_begin expects to
+ * be able to do i/o on the buffers returned, unless an error value
+ * is also returned.
+ *
+ * So, this allows __block_write_begin to be used for reading a single block
+ * in a page.  Where it does not produce a valid page for holes, or past the
+ * end of the file.  This turns out to be exactly what we need for reading
+ * tails for conversion.
+ *
+ * The point of the wrapper is forcing a certain value for create, even
+ * though the VFS layer is calling this function with create==1.  If you
+ * don't want to send create == GET_BLOCK_NO_HOLE to reiserfs_get_block,
+ * don't use this function.
 */
 static int reiserfs_get_block_create_0(struct inode *inode, sector_t block,
 				       struct buffer_head *bh_result,
@@ -463,8 +506,10 @@ static int reiserfs_get_block_create_0(struct inode *inode, sector_t block,
 	return reiserfs_get_block(inode, block, bh_result, GET_BLOCK_NO_HOLE);
 }
 
-/* This is special helper for reiserfs_get_block in case we are executing
-   direct_IO request. */
+/*
+ * This is special helper for reiserfs_get_block in case we are executing
+ * direct_IO request.
+ */
 static int reiserfs_get_blocks_direct_io(struct inode *inode,
 					 sector_t iblock,
 					 struct buffer_head *bh_result,
@@ -474,9 +519,11 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode,
 
 	bh_result->b_page = NULL;
 
-	/* We set the b_size before reiserfs_get_block call since it is
-	   referenced in convert_tail_for_hole() that may be called from
-	   reiserfs_get_block() */
+	/*
+	 * We set the b_size before reiserfs_get_block call since it is
+	 * referenced in convert_tail_for_hole() that may be called from
+	 * reiserfs_get_block()
+	 */
 	bh_result->b_size = (1 << inode->i_blkbits);
 
 	ret = reiserfs_get_block(inode, iblock, bh_result,
@@ -486,14 +533,18 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode,
 
 	/* don't allow direct io onto tail pages */
 	if (buffer_mapped(bh_result) && bh_result->b_blocknr == 0) {
-		/* make sure future calls to the direct io funcs for this offset
-		 ** in the file fail by unmapping the buffer
+		/*
+		 * make sure future calls to the direct io funcs for this
+		 * offset in the file fail by unmapping the buffer
 		 */
 		clear_buffer_mapped(bh_result);
 		ret = -EINVAL;
 	}
-	/* Possible unpacked tail. Flush the data before pages have
-	   disappeared */
+
+	/*
+	 * Possible unpacked tail. Flush the data before pages have
+	 * disappeared
+	 */
 	if (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) {
 		int err;
 
@@ -507,20 +558,20 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode,
 		if (err < 0)
 			ret = err;
 	}
-      out:
+out:
 	return ret;
 }
 
 /*
-** helper function for when reiserfs_get_block is called for a hole
-** but the file tail is still in a direct item
-** bh_result is the buffer head for the hole
-** tail_offset is the offset of the start of the tail in the file
-**
-** This calls prepare_write, which will start a new transaction
-** you should not be in a transaction, or have any paths held when you
-** call this.
-*/
+ * helper function for when reiserfs_get_block is called for a hole
+ * but the file tail is still in a direct item
+ * bh_result is the buffer head for the hole
+ * tail_offset is the offset of the start of the tail in the file
+ *
+ * This calls prepare_write, which will start a new transaction
+ * you should not be in a transaction, or have any paths held when you
+ * call this.
+ */
 static int convert_tail_for_hole(struct inode *inode,
 				 struct buffer_head *bh_result,
 				 loff_t tail_offset)
@@ -540,9 +591,10 @@ static int convert_tail_for_hole(struct inode *inode,
 	tail_end = (tail_start | (bh_result->b_size - 1)) + 1;
 
 	index = tail_offset >> PAGE_CACHE_SHIFT;
-	/* hole_page can be zero in case of direct_io, we are sure
-	   that we cannot get here if we write with O_DIRECT into
-	   tail page */
+	/*
+	 * hole_page can be zero in case of direct_io, we are sure
+	 * that we cannot get here if we write with O_DIRECT into tail page
+	 */
 	if (!hole_page || index != hole_page->index) {
 		tail_page = grab_cache_page(inode->i_mapping, index);
 		retval = -ENOMEM;
@@ -553,14 +605,15 @@ static int convert_tail_for_hole(struct inode *inode,
 		tail_page = hole_page;
 	}
 
-	/* we don't have to make sure the conversion did not happen while
-	 ** we were locking the page because anyone that could convert
-	 ** must first take i_mutex.
-	 **
-	 ** We must fix the tail page for writing because it might have buffers
-	 ** that are mapped, but have a block number of 0.  This indicates tail
-	 ** data that has been read directly into the page, and
-	 ** __block_write_begin won't trigger a get_block in this case.
+	/*
+	 * we don't have to make sure the conversion did not happen while
+	 * we were locking the page because anyone that could convert
+	 * must first take i_mutex.
+	 *
+	 * We must fix the tail page for writing because it might have buffers
+	 * that are mapped, but have a block number of 0.  This indicates tail
+	 * data that has been read directly into the page, and
+	 * __block_write_begin won't trigger a get_block in this case.
 	 */
 	fix_tail_page_for_writing(tail_page);
 	retval = __reiserfs_write_begin(tail_page, tail_start,
@@ -573,12 +626,12 @@ static int convert_tail_for_hole(struct inode *inode,
 
 	retval = reiserfs_commit_write(NULL, tail_page, tail_start, tail_end);
 
-      unlock:
+unlock:
 	if (tail_page != hole_page) {
 		unlock_page(tail_page);
 		page_cache_release(tail_page);
 	}
-      out:
+out:
 	return retval;
 }
 
@@ -604,7 +657,8 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		       struct buffer_head *bh_result, int create)
 {
 	int repeat, retval = 0;
-	b_blocknr_t allocated_block_nr = 0;	// b_blocknr_t is (unsigned) 32 bit int
+	/* b_blocknr_t is (unsigned) 32 bit int*/
+	b_blocknr_t allocated_block_nr = 0;
 	INITIALIZE_PATH(path);
 	int pos_in_item;
 	struct cpu_key key;
@@ -614,12 +668,14 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 	int done;
 	int fs_gen;
 	struct reiserfs_transaction_handle *th = NULL;
-	/* space reserved in transaction batch:
-	   . 3 balancings in direct->indirect conversion
-	   . 1 block involved into reiserfs_update_sd()
-	   XXX in practically impossible worst case direct2indirect()
-	   can incur (much) more than 3 balancings.
-	   quota update for user, group */
+	/*
+	 * space reserved in transaction batch:
+	 * . 3 balancings in direct->indirect conversion
+	 * . 1 block involved into reiserfs_update_sd()
+	 * XXX in practically impossible worst case direct2indirect()
+	 * can incur (much) more than 3 balancings.
+	 * quota update for user, group
+	 */
 	int jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 3 + 1 +
 	    2 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb);
@@ -636,8 +692,9 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		return -EFBIG;
 	}
 
-	/* if !create, we aren't changing the FS, so we don't need to
-	 ** log anything, so we don't need to start a transaction
+	/*
+	 * if !create, we aren't changing the FS, so we don't need to
+	 * log anything, so we don't need to start a transaction
 	 */
 	if (!(create & GET_BLOCK_CREATE)) {
 		int ret;
@@ -647,6 +704,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		reiserfs_write_unlock(inode->i_sb);
 		return ret;
 	}
+
 	/*
 	 * if we're already in a transaction, make sure to close
 	 * any new transactions we start in this func
@@ -655,8 +713,10 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 	    reiserfs_transaction_running(inode->i_sb))
 		dangle = 0;
 
-	/* If file is of such a size, that it might have a tail and tails are enabled
-	 ** we should mark it as possibly needing tail packing on close
+	/*
+	 * If file is of such a size, that it might have a tail and
+	 * tails are enabled  we should mark it as possibly needing
+	 * tail packing on close
 	 */
 	if ((have_large_tails(inode->i_sb)
 	     && inode->i_size < i_block_size(inode) * 4)
@@ -667,7 +727,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 	/* set the key of the first byte in the 'block'-th block of file */
 	make_cpu_key(&key, inode, new_offset, TYPE_ANY, 3 /*key length */ );
 	if ((new_offset + inode->i_sb->s_blocksize - 1) > inode->i_size) {
-	      start_trans:
+start_trans:
 		th = reiserfs_persistent_transaction(inode->i_sb, jbegin_count);
 		if (!th) {
 			retval = -ENOMEM;
@@ -675,7 +735,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		}
 		reiserfs_update_inode_transaction(inode);
 	}
-      research:
+research:
 
 	retval = search_for_position_by_key(inode->i_sb, &key, &path);
 	if (retval == IO_ERROR) {
@@ -684,8 +744,8 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 	}
 
 	bh = get_last_bh(&path);
-	ih = get_ih(&path);
-	item = get_item(&path);
+	ih = tp_item_head(&path);
+	item = tp_item_body(&path);
 	pos_in_item = path.pos_in_item;
 
 	fs_gen = get_generation(inode->i_sb);
@@ -703,11 +763,12 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		    _allocate_block(th, block, inode, &allocated_block_nr,
 				    &path, create);
 
+		/*
+		 * restart the transaction to give the journal a chance to free
+		 * some blocks.  releases the path, so we have to go back to
+		 * research if we succeed on the second try
+		 */
 		if (repeat == NO_DISK_SPACE || repeat == QUOTA_EXCEEDED) {
-			/* restart the transaction to give the journal a chance to free
-			 ** some blocks.  releases the path, so we have to go back to
-			 ** research if we succeed on the second try
-			 */
 			SB_JOURNAL(inode->i_sb)->j_next_async_flush = 1;
 			retval = restart_transaction(th, inode, &path);
 			if (retval)
@@ -734,9 +795,11 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 
 	if (indirect_item_found(retval, ih)) {
 		b_blocknr_t unfm_ptr;
-		/* 'block'-th block is in the file already (there is
-		   corresponding cell in some indirect item). But it may be
-		   zero unformatted node pointer (hole) */
+		/*
+		 * 'block'-th block is in the file already (there is
+		 * corresponding cell in some indirect item). But it may be
+		 * zero unformatted node pointer (hole)
+		 */
 		unfm_ptr = get_block_num(item, pos_in_item);
 		if (unfm_ptr == 0) {
 			/* use allocated block to plug the hole */
@@ -753,7 +816,7 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 				reiserfs_add_ordered_list(inode, bh_result);
 			put_block_num(item, pos_in_item, allocated_block_nr);
 			unfm_ptr = allocated_block_nr;
-			journal_mark_dirty(th, inode->i_sb, bh);
+			journal_mark_dirty(th, bh);
 			reiserfs_update_sd(th, inode);
 		}
 		set_block_dev_mapped(bh_result, unfm_ptr, inode);
@@ -764,9 +827,10 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 
 		reiserfs_write_unlock(inode->i_sb);
 
-		/* the item was found, so new blocks were not added to the file
-		 ** there is no need to make sure the inode is updated with this
-		 ** transaction
+		/*
+		 * the item was found, so new blocks were not added to the file
+		 * there is no need to make sure the inode is updated with this
+		 * transaction
 		 */
 		return retval;
 	}
@@ -776,9 +840,11 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		goto start_trans;
 	}
 
-	/* desired position is not found or is in the direct item. We have
-	   to append file with holes up to 'block'-th block converting
-	   direct items to indirect one if necessary */
+	/*
+	 * desired position is not found or is in the direct item. We have
+	 * to append file with holes up to 'block'-th block converting
+	 * direct items to indirect one if necessary
+	 */
 	done = 0;
 	do {
 		if (is_statdata_le_ih(ih)) {
@@ -790,16 +856,18 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 					  TYPE_INDIRECT, UNFM_P_SIZE,
 					  0 /* free_space */ );
 
+			/*
+			 * we are going to add 'block'-th block to the file.
+			 * Use allocated block for that
+			 */
 			if (cpu_key_k_offset(&key) == 1) {
-				/* we are going to add 'block'-th block to the file. Use
-				   allocated block for that */
 				unp = cpu_to_le32(allocated_block_nr);
 				set_block_dev_mapped(bh_result,
 						     allocated_block_nr, inode);
 				set_buffer_new(bh_result);
 				done = 1;
 			}
-			tmp_key = key;	// ;)
+			tmp_key = key;	/* ;) */
 			set_cpu_key_k_offset(&tmp_key, 1);
 			PATH_LAST_POSITION(&path)++;
 
@@ -809,9 +877,12 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 			if (retval) {
 				reiserfs_free_block(th, inode,
 						    allocated_block_nr, 1);
-				goto failure;	// retval == -ENOSPC, -EDQUOT or -EIO or -EEXIST
+				/*
+				 * retval == -ENOSPC, -EDQUOT or -EIO
+				 * or -EEXIST
+				 */
+				goto failure;
 			}
-			//mark_tail_converted (inode);
 		} else if (is_direct_le_ih(ih)) {
 			/* direct item has to be converted */
 			loff_t tail_offset;
@@ -819,18 +890,24 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 			tail_offset =
 			    ((le_ih_k_offset(ih) -
 			      1) & ~(inode->i_sb->s_blocksize - 1)) + 1;
+
+			/*
+			 * direct item we just found fits into block we have
+			 * to map. Convert it into unformatted node: use
+			 * bh_result for the conversion
+			 */
 			if (tail_offset == cpu_key_k_offset(&key)) {
-				/* direct item we just found fits into block we have
-				   to map. Convert it into unformatted node: use
-				   bh_result for the conversion */
 				set_block_dev_mapped(bh_result,
 						     allocated_block_nr, inode);
 				unbh = bh_result;
 				done = 1;
 			} else {
-				/* we have to padd file tail stored in direct item(s)
-				   up to block size and convert it to unformatted
-				   node. FIXME: this should also get into page cache */
+				/*
+				 * we have to pad file tail stored in direct
+				 * item(s) up to block size and convert it
+				 * to unformatted node. FIXME: this should
+				 * also get into page cache
+				 */
 
 				pathrelse(&path);
 				/*
@@ -859,7 +936,10 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 							inode->i_ino,
 							retval);
 					if (allocated_block_nr) {
-						/* the bitmap, the super, and the stat data == 3 */
+						/*
+						 * the bitmap, the super,
+						 * and the stat data == 3
+						 */
 						if (!th)
 							th = reiserfs_persistent_transaction(inode->i_sb, 3);
 						if (th)
@@ -881,43 +961,57 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 						    allocated_block_nr, 1);
 				goto failure;
 			}
-			/* it is important the set_buffer_uptodate is done after
-			 ** the direct2indirect.  The buffer might contain valid
-			 ** data newer than the data on disk (read by readpage, changed,
-			 ** and then sent here by writepage).  direct2indirect needs
-			 ** to know if unbh was already up to date, so it can decide
-			 ** if the data in unbh needs to be replaced with data from
-			 ** the disk
+			/*
+			 * it is important the set_buffer_uptodate is done
+			 * after the direct2indirect.  The buffer might
+			 * contain valid data newer than the data on disk
+			 * (read by readpage, changed, and then sent here by
+			 * writepage).  direct2indirect needs to know if unbh
+			 * was already up to date, so it can decide if the
+			 * data in unbh needs to be replaced with data from
+			 * the disk
 			 */
 			set_buffer_uptodate(unbh);
 
-			/* unbh->b_page == NULL in case of DIRECT_IO request, this means
-			   buffer will disappear shortly, so it should not be added to
+			/*
+			 * unbh->b_page == NULL in case of DIRECT_IO request,
+			 * this means buffer will disappear shortly, so it
+			 * should not be added to
 			 */
 			if (unbh->b_page) {
-				/* we've converted the tail, so we must
-				 ** flush unbh before the transaction commits
+				/*
+				 * we've converted the tail, so we must
+				 * flush unbh before the transaction commits
 				 */
 				reiserfs_add_tail_list(inode, unbh);
 
-				/* mark it dirty now to prevent commit_write from adding
-				 ** this buffer to the inode's dirty buffer list
+				/*
+				 * mark it dirty now to prevent commit_write
+				 * from adding this buffer to the inode's
+				 * dirty buffer list
 				 */
 				/*
-				 * AKPM: changed __mark_buffer_dirty to mark_buffer_dirty().
-				 * It's still atomic, but it sets the page dirty too,
-				 * which makes it eligible for writeback at any time by the
-				 * VM (which was also the case with __mark_buffer_dirty())
+				 * AKPM: changed __mark_buffer_dirty to
+				 * mark_buffer_dirty().  It's still atomic,
+				 * but it sets the page dirty too, which makes
+				 * it eligible for writeback at any time by the
+				 * VM (which was also the case with
+				 * __mark_buffer_dirty())
 				 */
 				mark_buffer_dirty(unbh);
 			}
 		} else {
-			/* append indirect item with holes if needed, when appending
-			   pointer to 'block'-th block use block, which is already
-			   allocated */
+			/*
+			 * append indirect item with holes if needed, when
+			 * appending pointer to 'block'-th block use block,
+			 * which is already allocated
+			 */
 			struct cpu_key tmp_key;
-			unp_t unf_single = 0;	// We use this in case we need to allocate only
-			// one block which is a fastpath
+			/*
+			 * We use this in case we need to allocate
+			 * only one block which is a fastpath
+			 */
+			unp_t unf_single = 0;
 			unp_t *un;
 			__u64 max_to_insert =
 			    MAX_ITEM_LEN(inode->i_sb->s_blocksize) /
@@ -926,14 +1020,17 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 
 			RFALSE(pos_in_item != ih_item_len(ih) / UNFM_P_SIZE,
 			       "vs-804: invalid position for append");
-			/* indirect item has to be appended, set up key of that position */
+			/*
+			 * indirect item has to be appended,
+			 * set up key of that position
+			 * (key type is unimportant)
+			 */
 			make_cpu_key(&tmp_key, inode,
 				     le_key_k_offset(version,
-						     &(ih->ih_key)) +
+						     &ih->ih_key) +
 				     op_bytes_number(ih,
 						     inode->i_sb->s_blocksize),
-				     //pos_in_item * inode->i_sb->s_blocksize,
-				     TYPE_INDIRECT, 3);	// key type is unimportant
+				     TYPE_INDIRECT, 3);
 
 			RFALSE(cpu_key_k_offset(&tmp_key) > cpu_key_k_offset(&key),
 			       "green-805: invalid offset");
@@ -954,8 +1051,10 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 				}
 			}
 			if (blocks_needed <= max_to_insert) {
-				/* we are going to add target block to the file. Use allocated
-				   block for that */
+				/*
+				 * we are going to add target block to
+				 * the file. Use allocated block for that
+				 */
 				un[blocks_needed - 1] =
 				    cpu_to_le32(allocated_block_nr);
 				set_block_dev_mapped(bh_result,
@@ -964,8 +1063,11 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 				done = 1;
 			} else {
 				/* paste hole to the indirect item */
-				/* If kmalloc failed, max_to_insert becomes zero and it means we
-				   only have space for one block */
+				/*
+				 * If kmalloc failed, max_to_insert becomes
+				 * zero and it means we only have space for
+				 * one block
+				 */
 				blocks_needed =
 				    max_to_insert ? max_to_insert : 1;
 			}
@@ -984,9 +1086,12 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 				goto failure;
 			}
 			if (!done) {
-				/* We need to mark new file size in case this function will be
-				   interrupted/aborted later on. And we may do this only for
-				   holes. */
+				/*
+				 * We need to mark new file size in case
+				 * this function will be interrupted/aborted
+				 * later on. And we may do this only for
+				 * holes.
+				 */
 				inode->i_size +=
 				    inode->i_sb->s_blocksize * blocks_needed;
 			}
@@ -995,13 +1100,13 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 		if (done == 1)
 			break;
 
-		/* this loop could log more blocks than we had originally asked
-		 ** for.  So, we have to allow the transaction to end if it is
-		 ** too big or too full.  Update the inode so things are
-		 ** consistent if we crash before the function returns
-		 **
-		 ** release the path so that anybody waiting on the path before
-		 ** ending their transaction will be able to continue.
+		/*
+		 * this loop could log more blocks than we had originally
+		 * asked for.  So, we have to allow the transaction to end
+		 * if it is too big or too full.  Update the inode so things
+		 * are consistent if we crash before the function returns
+		 * release the path so that anybody waiting on the path before
+		 * ending their transaction will be able to continue.
 		 */
 		if (journal_transaction_should_end(th, th->t_blocks_allocated)) {
 			retval = restart_transaction(th, inode, &path);
@@ -1031,14 +1136,14 @@ int reiserfs_get_block(struct inode *inode, sector_t block,
 			goto failure;
 		}
 		bh = get_last_bh(&path);
-		ih = get_ih(&path);
-		item = get_item(&path);
+		ih = tp_item_head(&path);
+		item = tp_item_body(&path);
 		pos_in_item = path.pos_in_item;
 	} while (1);
 
 	retval = 0;
 
-      failure:
+failure:
 	if (th && (!dangle || (retval && !th->t_trans_id))) {
 		int err;
 		if (th->t_trans_id)
@@ -1060,8 +1165,10 @@ reiserfs_readpages(struct file *file, struct address_space *mapping,
 	return mpage_readpages(mapping, pages, nr_pages, reiserfs_get_block);
 }
 
-/* Compute real number of used bytes by file
- * Following three functions can go away when we'll have enough space in stat item
+/*
+ * Compute real number of used bytes by file
+ * Following three functions can go away when we'll have enough space in
+ * stat item
  */
 static int real_space_diff(struct inode *inode, int sd_size)
 {
@@ -1071,13 +1178,14 @@ static int real_space_diff(struct inode *inode, int sd_size)
 	if (S_ISLNK(inode->i_mode) || S_ISDIR(inode->i_mode))
 		return sd_size;
 
-	/* End of file is also in full block with indirect reference, so round
-	 ** up to the next block.
-	 **
-	 ** there is just no way to know if the tail is actually packed
-	 ** on the file, so we have to assume it isn't.  When we pack the
-	 ** tail, we add 4 bytes to pretend there really is an unformatted
-	 ** node pointer
+	/*
+	 * End of file is also in full block with indirect reference, so round
+	 * up to the next block.
+	 *
+	 * there is just no way to know if the tail is actually packed
+	 * on the file, so we have to assume it isn't.  When we pack the
+	 * tail, we add 4 bytes to pretend there really is an unformatted
+	 * node pointer
 	 */
 	bytes =
 	    ((inode->i_size +
@@ -1108,36 +1216,36 @@ static inline ulong to_fake_used_blocks(struct inode *inode, int sd_size)
 		bytes += (loff_t) 511;
 	}
 
-	/* files from before the quota patch might i_blocks such that
-	 ** bytes < real_space.  Deal with that here to prevent it from
-	 ** going negative.
+	/*
+	 * files from before the quota patch might i_blocks such that
+	 * bytes < real_space.  Deal with that here to prevent it from
+	 * going negative.
 	 */
 	if (bytes < real_space)
 		return 0;
 	return (bytes - real_space) >> 9;
 }
 
-//
-// BAD: new directories have stat data of new type and all other items
-// of old type. Version stored in the inode says about body items, so
-// in update_stat_data we can not rely on inode, but have to check
-// item version directly
-//
+/*
+ * BAD: new directories have stat data of new type and all other items
+ * of old type. Version stored in the inode says about body items, so
+ * in update_stat_data we can not rely on inode, but have to check
+ * item version directly
+ */
 
-// called by read_locked_inode
+/* called by read_locked_inode */
 static void init_inode(struct inode *inode, struct treepath *path)
 {
 	struct buffer_head *bh;
 	struct item_head *ih;
 	__u32 rdev;
-	//int version = ITEM_VERSION_1;
 
 	bh = PATH_PLAST_BUFFER(path);
-	ih = PATH_PITEM_HEAD(path);
+	ih = tp_item_head(path);
 
-	copy_key(INODE_PKEY(inode), &(ih->ih_key));
+	copy_key(INODE_PKEY(inode), &ih->ih_key);
 
-	INIT_LIST_HEAD(&(REISERFS_I(inode)->i_prealloc_list));
+	INIT_LIST_HEAD(&REISERFS_I(inode)->i_prealloc_list);
 	REISERFS_I(inode)->i_flags = 0;
 	REISERFS_I(inode)->i_prealloc_block = 0;
 	REISERFS_I(inode)->i_prealloc_count = 0;
@@ -1147,7 +1255,7 @@ static void init_inode(struct inode *inode, struct treepath *path)
 
 	if (stat_data_v1(ih)) {
 		struct stat_data_v1 *sd =
-		    (struct stat_data_v1 *)B_I_PITEM(bh, ih);
+		    (struct stat_data_v1 *)ih_item_body(bh, ih);
 		unsigned long blocks;
 
 		set_inode_item_key_version(inode, KEY_FORMAT_3_5);
@@ -1168,20 +1276,26 @@ static void init_inode(struct inode *inode, struct treepath *path)
 		inode->i_generation = le32_to_cpu(INODE_PKEY(inode)->k_dir_id);
 		blocks = (inode->i_size + 511) >> 9;
 		blocks = _ROUND_UP(blocks, inode->i_sb->s_blocksize >> 9);
+
+		/*
+		 * there was a bug in <=3.5.23 when i_blocks could take
+		 * negative values. Starting from 3.5.17 this value could
+		 * even be stored in stat data. For such files we set
+		 * i_blocks based on file size. Just 2 notes: this can be
+		 * wrong for sparse files. On-disk value will be only
+		 * updated if file's inode will ever change
+		 */
 		if (inode->i_blocks > blocks) {
-			// there was a bug in <=3.5.23 when i_blocks could take negative
-			// values. Starting from 3.5.17 this value could even be stored in
-			// stat data. For such files we set i_blocks based on file
-			// size. Just 2 notes: this can be wrong for sparce files. On-disk value will be
-			// only updated if file's inode will ever change
 			inode->i_blocks = blocks;
 		}
 
 		rdev = sd_v1_rdev(sd);
 		REISERFS_I(inode)->i_first_direct_byte =
 		    sd_v1_first_direct_byte(sd);
-		/* an early bug in the quota code can give us an odd number for the
-		 ** block count.  This is incorrect, fix it here.
+
+		/*
+		 * an early bug in the quota code can give us an odd
+		 * number for the block count.  This is incorrect, fix it here.
 		 */
 		if (inode->i_blocks & 1) {
 			inode->i_blocks++;
@@ -1189,13 +1303,17 @@ static void init_inode(struct inode *inode, struct treepath *path)
 		inode_set_bytes(inode,
 				to_real_used_space(inode, inode->i_blocks,
 						   SD_V1_SIZE));
-		/* nopack is initially zero for v1 objects. For v2 objects,
-		   nopack is initialised from sd_attrs */
+		/*
+		 * nopack is initially zero for v1 objects. For v2 objects,
+		 * nopack is initialised from sd_attrs
+		 */
 		REISERFS_I(inode)->i_flags &= ~i_nopack_mask;
 	} else {
-		// new stat data found, but object may have old items
-		// (directories and symlinks)
-		struct stat_data *sd = (struct stat_data *)B_I_PITEM(bh, ih);
+		/*
+		 * new stat data found, but object may have old items
+		 * (directories and symlinks)
+		 */
+		struct stat_data *sd = (struct stat_data *)ih_item_body(bh, ih);
 
 		inode->i_mode = sd_v2_mode(sd);
 		set_nlink(inode, sd_v2_nlink(sd));
@@ -1225,8 +1343,10 @@ static void init_inode(struct inode *inode, struct treepath *path)
 		inode_set_bytes(inode,
 				to_real_used_space(inode, inode->i_blocks,
 						   SD_V2_SIZE));
-		/* read persistent inode attributes from sd and initialise
-		   generic inode flags from them */
+		/*
+		 * read persistent inode attributes from sd and initialise
+		 * generic inode flags from them
+		 */
 		REISERFS_I(inode)->i_attrs = sd_v2_attrs(sd);
 		sd_attrs_to_i_attrs(sd_v2_attrs(sd), inode);
 	}
@@ -1249,7 +1369,7 @@ static void init_inode(struct inode *inode, struct treepath *path)
 	}
 }
 
-// update new stat data with inode fields
+/* update new stat data with inode fields */
 static void inode2sd(void *sd, struct inode *inode, loff_t size)
 {
 	struct stat_data *sd_v2 = (struct stat_data *)sd;
@@ -1273,7 +1393,7 @@ static void inode2sd(void *sd, struct inode *inode, loff_t size)
 	set_sd_v2_attrs(sd_v2, flags);
 }
 
-// used to copy inode's fields to old stat data
+/* used to copy inode's fields to old stat data */
 static void inode2sd_v1(void *sd, struct inode *inode, loff_t size)
 {
 	struct stat_data_v1 *sd_v1 = (struct stat_data_v1 *)sd;
@@ -1292,14 +1412,15 @@ static void inode2sd_v1(void *sd, struct inode *inode, loff_t size)
 	else
 		set_sd_v1_blocks(sd_v1, to_fake_used_blocks(inode, SD_V1_SIZE));
 
-	// Sigh. i_first_direct_byte is back
+	/* Sigh. i_first_direct_byte is back */
 	set_sd_v1_first_direct_byte(sd_v1,
 				    REISERFS_I(inode)->i_first_direct_byte);
 }
 
-/* NOTE, you must prepare the buffer head before sending it here,
-** and then log it after the call
-*/
+/*
+ * NOTE, you must prepare the buffer head before sending it here,
+ * and then log it after the call
+ */
 static void update_stat_data(struct treepath *path, struct inode *inode,
 			     loff_t size)
 {
@@ -1307,17 +1428,17 @@ static void update_stat_data(struct treepath *path, struct inode *inode,
 	struct item_head *ih;
 
 	bh = PATH_PLAST_BUFFER(path);
-	ih = PATH_PITEM_HEAD(path);
+	ih = tp_item_head(path);
 
 	if (!is_statdata_le_ih(ih))
 		reiserfs_panic(inode->i_sb, "vs-13065", "key %k, found item %h",
 			       INODE_PKEY(inode), ih);
 
+	/* path points to old stat data */
 	if (stat_data_v1(ih)) {
-		// path points to old stat data
-		inode2sd_v1(B_I_PITEM(bh, ih), inode, size);
+		inode2sd_v1(ih_item_body(bh, ih), inode, size);
 	} else {
-		inode2sd(B_I_PITEM(bh, ih), inode, size);
+		inode2sd(ih_item_body(bh, ih), inode, size);
 	}
 
 	return;
@@ -1335,7 +1456,8 @@ void reiserfs_update_sd_size(struct reiserfs_transaction_handle *th,
 
 	BUG_ON(!th->t_trans_id);
 
-	make_cpu_key(&key, inode, SD_OFFSET, TYPE_STAT_DATA, 3);	//key type is unimportant
+	/* key type is unimportant */
+	make_cpu_key(&key, inode, SD_OFFSET, TYPE_STAT_DATA, 3);
 
 	for (;;) {
 		int pos;
@@ -1363,45 +1485,48 @@ void reiserfs_update_sd_size(struct reiserfs_transaction_handle *th,
 			return;
 		}
 
-		/* sigh, prepare_for_journal might schedule.  When it schedules the
-		 ** FS might change.  We have to detect that, and loop back to the
-		 ** search if the stat data item has moved
+		/*
+		 * sigh, prepare_for_journal might schedule.  When it
+		 * schedules the FS might change.  We have to detect that,
+		 * and loop back to the search if the stat data item has moved
 		 */
 		bh = get_last_bh(&path);
-		ih = get_ih(&path);
+		ih = tp_item_head(&path);
 		copy_item_head(&tmp_ih, ih);
 		fs_gen = get_generation(inode->i_sb);
 		reiserfs_prepare_for_journal(inode->i_sb, bh, 1);
+
+		/* Stat_data item has been moved after scheduling. */
 		if (fs_changed(fs_gen, inode->i_sb)
 		    && item_moved(&tmp_ih, &path)) {
 			reiserfs_restore_prepared_buffer(inode->i_sb, bh);
-			continue;	/* Stat_data item has been moved after scheduling. */
+			continue;
 		}
 		break;
 	}
 	update_stat_data(&path, inode, size);
-	journal_mark_dirty(th, th->t_super, bh);
+	journal_mark_dirty(th, bh);
 	pathrelse(&path);
 	return;
 }
 
-/* reiserfs_read_locked_inode is called to read the inode off disk, and it
-** does a make_bad_inode when things go wrong.  But, we need to make sure
-** and clear the key in the private portion of the inode, otherwise a
-** corresponding iput might try to delete whatever object the inode last
-** represented.
-*/
+/*
+ * reiserfs_read_locked_inode is called to read the inode off disk, and it
+ * does a make_bad_inode when things go wrong.  But, we need to make sure
+ * and clear the key in the private portion of the inode, otherwise a
+ * corresponding iput might try to delete whatever object the inode last
+ * represented.
+ */
 static void reiserfs_make_bad_inode(struct inode *inode)
 {
 	memset(INODE_PKEY(inode), 0, KEY_SIZE);
 	make_bad_inode(inode);
 }
 
-//
-// initially this function was derived from minix or ext2's analog and
-// evolved as the prototype did
-//
-
+/*
+ * initially this function was derived from minix or ext2's analog and
+ * evolved as the prototype did
+ */
 int reiserfs_init_locked_inode(struct inode *inode, void *p)
 {
 	struct reiserfs_iget_args *args = (struct reiserfs_iget_args *)p;
@@ -1410,8 +1535,10 @@ int reiserfs_init_locked_inode(struct inode *inode, void *p)
 	return 0;
 }
 
-/* looks for stat data in the tree, and fills up the fields of in-core
-   inode stat data fields */
+/*
+ * looks for stat data in the tree, and fills up the fields of in-core
+ * inode stat data fields
+ */
 void reiserfs_read_locked_inode(struct inode *inode,
 				struct reiserfs_iget_args *args)
 {
@@ -1422,8 +1549,10 @@ void reiserfs_read_locked_inode(struct inode *inode,
 
 	dirino = args->dirid;
 
-	/* set version 1, version 2 could be used too, because stat data
-	   key is the same in both versions */
+	/*
+	 * set version 1, version 2 could be used too, because stat data
+	 * key is the same in both versions
+	 */
 	key.version = KEY_FORMAT_3_5;
 	key.on_disk_key.k_dir_id = dirino;
 	key.on_disk_key.k_objectid = inode->i_ino;
@@ -1439,8 +1568,9 @@ void reiserfs_read_locked_inode(struct inode *inode,
 		reiserfs_make_bad_inode(inode);
 		return;
 	}
+
+	/* a stale NFS handle can trigger this without it being an error */
 	if (retval != ITEM_FOUND) {
-		/* a stale NFS handle can trigger this without it being an error */
 		pathrelse(&path_to_sd);
 		reiserfs_make_bad_inode(inode);
 		clear_nlink(inode);
@@ -1449,20 +1579,25 @@ void reiserfs_read_locked_inode(struct inode *inode,
 
 	init_inode(inode, &path_to_sd);
 
-	/* It is possible that knfsd is trying to access inode of a file
-	   that is being removed from the disk by some other thread. As we
-	   update sd on unlink all that is required is to check for nlink
-	   here. This bug was first found by Sizif when debugging
-	   SquidNG/Butterfly, forgotten, and found again after Philippe
-	   Gramoulle <philippe.gramoulle@mmania.com> reproduced it.
-
-	   More logical fix would require changes in fs/inode.c:iput() to
-	   remove inode from hash-table _after_ fs cleaned disk stuff up and
-	   in iget() to return NULL if I_FREEING inode is found in
-	   hash-table. */
-	/* Currently there is one place where it's ok to meet inode with
-	   nlink==0: processing of open-unlinked and half-truncated files
-	   during mount (fs/reiserfs/super.c:finish_unfinished()). */
+	/*
+	 * It is possible that knfsd is trying to access inode of a file
+	 * that is being removed from the disk by some other thread. As we
+	 * update sd on unlink all that is required is to check for nlink
+	 * here. This bug was first found by Sizif when debugging
+	 * SquidNG/Butterfly, forgotten, and found again after Philippe
+	 * Gramoulle <philippe.gramoulle@mmania.com> reproduced it.
+
+	 * More logical fix would require changes in fs/inode.c:iput() to
+	 * remove inode from hash-table _after_ fs cleaned disk stuff up and
+	 * in iget() to return NULL if I_FREEING inode is found in
+	 * hash-table.
+	 */
+
+	/*
+	 * Currently there is one place where it's ok to meet inode with
+	 * nlink==0: processing of open-unlinked and half-truncated files
+	 * during mount (fs/reiserfs/super.c:finish_unfinished()).
+	 */
 	if ((inode->i_nlink == 0) &&
 	    !REISERFS_SB(inode->i_sb)->s_is_unlinked_ok) {
 		reiserfs_warning(inode->i_sb, "vs-13075",
@@ -1472,7 +1607,8 @@ void reiserfs_read_locked_inode(struct inode *inode,
 		reiserfs_make_bad_inode(inode);
 	}
 
-	reiserfs_check_path(&path_to_sd);	/* init inode should be relsing */
+	/* init inode should be relsing */
+	reiserfs_check_path(&path_to_sd);
 
 	/*
 	 * Stat data v1 doesn't support ACLs.
@@ -1481,7 +1617,7 @@ void reiserfs_read_locked_inode(struct inode *inode,
 		cache_no_acl(inode);
 }
 
-/**
+/*
  * reiserfs_find_actor() - "find actor" reiserfs supplies to iget5_locked().
  *
  * @inode:    inode from hash table to check
@@ -1556,7 +1692,8 @@ static struct dentry *reiserfs_get_dentry(struct super_block *sb,
 struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 		int fh_len, int fh_type)
 {
-	/* fhtype happens to reflect the number of u32s encoded.
+	/*
+	 * fhtype happens to reflect the number of u32s encoded.
 	 * due to a bug in earlier code, fhtype might indicate there
 	 * are more u32s then actually fitted.
 	 * so if fhtype seems to be more than len, reduce fhtype.
@@ -1625,13 +1762,16 @@ int reiserfs_encode_fh(struct inode *inode, __u32 * data, int *lenp,
 	return *lenp;
 }
 
-/* looks for stat data, then copies fields to it, marks the buffer
-   containing stat data as dirty */
-/* reiserfs inodes are never really dirty, since the dirty inode call
-** always logs them.  This call allows the VFS inode marking routines
-** to properly mark inodes for datasync and such, but only actually
-** does something when called for a synchronous update.
-*/
+/*
+ * looks for stat data, then copies fields to it, marks the buffer
+ * containing stat data as dirty
+ */
+/*
+ * reiserfs inodes are never really dirty, since the dirty inode call
+ * always logs them.  This call allows the VFS inode marking routines
+ * to properly mark inodes for datasync and such, but only actually
+ * does something when called for a synchronous update.
+ */
 int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 {
 	struct reiserfs_transaction_handle th;
@@ -1639,24 +1779,28 @@ int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 
 	if (inode->i_sb->s_flags & MS_RDONLY)
 		return -EROFS;
-	/* memory pressure can sometimes initiate write_inode calls with sync == 1,
-	 ** these cases are just when the system needs ram, not when the
-	 ** inode needs to reach disk for safety, and they can safely be
-	 ** ignored because the altered inode has already been logged.
+	/*
+	 * memory pressure can sometimes initiate write_inode calls with
+	 * sync == 1,
+	 * these cases are just when the system needs ram, not when the
+	 * inode needs to reach disk for safety, and they can safely be
+	 * ignored because the altered inode has already been logged.
 	 */
 	if (wbc->sync_mode == WB_SYNC_ALL && !(current->flags & PF_MEMALLOC)) {
 		reiserfs_write_lock(inode->i_sb);
 		if (!journal_begin(&th, inode->i_sb, jbegin_count)) {
 			reiserfs_update_sd(&th, inode);
-			journal_end_sync(&th, inode->i_sb, jbegin_count);
+			journal_end_sync(&th);
 		}
 		reiserfs_write_unlock(inode->i_sb);
 	}
 	return 0;
 }
 
-/* stat data of new object is inserted already, this inserts the item
-   containing "." and ".." entries */
+/*
+ * stat data of new object is inserted already, this inserts the item
+ * containing "." and ".." entries
+ */
 static int reiserfs_new_directory(struct reiserfs_transaction_handle *th,
 				  struct inode *inode,
 				  struct item_head *ih, struct treepath *path,
@@ -1674,9 +1818,11 @@ static int reiserfs_new_directory(struct reiserfs_transaction_handle *th,
 		      le32_to_cpu(ih->ih_key.k_objectid), DOT_OFFSET,
 		      TYPE_DIRENTRY, 3 /*key length */ );
 
-	/* compose item head for new item. Directories consist of items of
-	   old type (ITEM_VERSION_1). Do not set key (second arg is 0), it
-	   is done by reiserfs_new_inode */
+	/*
+	 * compose item head for new item. Directories consist of items of
+	 * old type (ITEM_VERSION_1). Do not set key (second arg is 0), it
+	 * is done by reiserfs_new_inode
+	 */
 	if (old_format_only(sb)) {
 		make_le_item_head(ih, NULL, KEY_FORMAT_3_5, DOT_OFFSET,
 				  TYPE_DIRENTRY, EMPTY_DIR_SIZE_V1, 2);
@@ -1714,9 +1860,12 @@ static int reiserfs_new_directory(struct reiserfs_transaction_handle *th,
 	return reiserfs_insert_item(th, path, &key, ih, inode, body);
 }
 
-/* stat data of object has been inserted, this inserts the item
-   containing the body of symlink */
-static int reiserfs_new_symlink(struct reiserfs_transaction_handle *th, struct inode *inode,	/* Inode of symlink */
+/*
+ * stat data of object has been inserted, this inserts the item
+ * containing the body of symlink
+ */
+static int reiserfs_new_symlink(struct reiserfs_transaction_handle *th,
+				struct inode *inode,
 				struct item_head *ih,
 				struct treepath *path, const char *symname,
 				int item_len)
@@ -1754,15 +1903,26 @@ static int reiserfs_new_symlink(struct reiserfs_transaction_handle *th, struct i
 	return reiserfs_insert_item(th, path, &key, ih, inode, symname);
 }
 
-/* inserts the stat data into the tree, and then calls
-   reiserfs_new_directory (to insert ".", ".." item if new object is
-   directory) or reiserfs_new_symlink (to insert symlink body if new
-   object is symlink) or nothing (if new object is regular file)
-
-   NOTE! uid and gid must already be set in the inode.  If we return
-   non-zero due to an error, we have to drop the quota previously allocated
-   for the fresh inode.  This can only be done outside a transaction, so
-   if we return non-zero, we also end the transaction.  */
+/*
+ * inserts the stat data into the tree, and then calls
+ * reiserfs_new_directory (to insert ".", ".." item if new object is
+ * directory) or reiserfs_new_symlink (to insert symlink body if new
+ * object is symlink) or nothing (if new object is regular file)
+
+ * NOTE! uid and gid must already be set in the inode.  If we return
+ * non-zero due to an error, we have to drop the quota previously allocated
+ * for the fresh inode.  This can only be done outside a transaction, so
+ * if we return non-zero, we also end the transaction.
+ *
+ * @th: active transaction handle
+ * @dir: parent directory for new inode
+ * @mode: mode of new inode
+ * @symname: symlink contents if inode is symlink
+ * @isize: 0 for regular file, EMPTY_DIR_SIZE for dirs, strlen(symname) for
+ *         symlinks
+ * @inode: inode to be filled
+ * @security: optional security context to associate with this inode
+ */
 int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 		       struct inode *dir, umode_t mode, const char *symname,
 		       /* 0 for regular, EMTRY_DIR_SIZE for dirs,
@@ -1807,7 +1967,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 	else
 		make_le_item_head(&ih, NULL, KEY_FORMAT_3_6, SD_OFFSET,
 				  TYPE_STAT_DATA, SD_SIZE, MAX_US_INT);
-	memcpy(INODE_PKEY(inode), &(ih.ih_key), KEY_SIZE);
+	memcpy(INODE_PKEY(inode), &ih.ih_key, KEY_SIZE);
 	args.dirid = le32_to_cpu(ih.ih_key.k_dir_id);
 
 	depth = reiserfs_write_unlock_nested(inode->i_sb);
@@ -1820,10 +1980,11 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 	}
 
 	if (old_format_only(sb))
-		/* not a perfect generation count, as object ids can be reused, but
-		 ** this is as good as reiserfs can do right now.
-		 ** note that the private part of inode isn't filled in yet, we have
-		 ** to use the directory.
+		/*
+		 * not a perfect generation count, as object ids can be reused,
+		 * but this is as good as reiserfs can do right now.
+		 * note that the private part of inode isn't filled in yet,
+		 * we have to use the directory.
 		 */
 		inode->i_generation = le32_to_cpu(INODE_PKEY(dir)->k_objectid);
 	else
@@ -1850,7 +2011,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 	REISERFS_I(inode)->i_first_direct_byte = S_ISLNK(mode) ? 1 :
 	    U32_MAX /*NO_BYTES_IN_DIRECT_ITEM */ ;
 
-	INIT_LIST_HEAD(&(REISERFS_I(inode)->i_prealloc_list));
+	INIT_LIST_HEAD(&REISERFS_I(inode)->i_prealloc_list);
 	REISERFS_I(inode)->i_flags = 0;
 	REISERFS_I(inode)->i_prealloc_block = 0;
 	REISERFS_I(inode)->i_prealloc_count = 0;
@@ -1878,9 +2039,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 		goto out_bad_inode;
 	}
 	if (old_format_only(sb)) {
+		/* i_uid or i_gid is too big to be stored in stat data v3.5 */
 		if (i_uid_read(inode) & ~0xffff || i_gid_read(inode) & ~0xffff) {
 			pathrelse(&path_to_key);
-			/* i_uid or i_gid is too big to be stored in stat data v3.5 */
 			err = -EINVAL;
 			goto out_bad_inode;
 		}
@@ -1888,9 +2049,11 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 	} else {
 		inode2sd(&sd, inode, inode->i_size);
 	}
-	// store in in-core inode the key of stat data and version all
-	// object items will have (directory items will have old offset
-	// format, other new objects will consist of new items)
+	/*
+	 * store in in-core inode the key of stat data and version all
+	 * object items will have (directory items will have old offset
+	 * format, other new objects will consist of new items)
+	 */
 	if (old_format_only(sb) || S_ISDIR(mode) || S_ISLNK(mode))
 		set_inode_item_key_version(inode, KEY_FORMAT_3_5);
 	else
@@ -1934,7 +2097,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 	if (retval) {
 		err = retval;
 		reiserfs_check_path(&path_to_key);
-		journal_end(th, th->t_super, th->t_blocks_allocated);
+		journal_end(th);
 		goto out_inserted_sd;
 	}
 
@@ -1945,7 +2108,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 		if (retval) {
 			err = retval;
 			reiserfs_check_path(&path_to_key);
-			journal_end(th, th->t_super, th->t_blocks_allocated);
+			journal_end(th);
 			goto out_inserted_sd;
 		}
 	} else if (inode->i_sb->s_flags & MS_POSIXACL) {
@@ -1962,8 +2125,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 		if (retval) {
 			err = retval;
 			reiserfs_check_path(&path_to_key);
-			retval = journal_end(th, th->t_super,
-					     th->t_blocks_allocated);
+			retval = journal_end(th);
 			if (retval)
 				err = retval;
 			goto out_inserted_sd;
@@ -1975,11 +2137,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 
 	return 0;
 
-/* it looks like you can easily compress these two goto targets into
- * one.  Keeping it like this doesn't actually hurt anything, and they
- * are place holders for what the quota code actually needs.
- */
-      out_bad_inode:
+out_bad_inode:
 	/* Invalidate the object, nothing was inserted yet */
 	INODE_PKEY(inode)->k_objectid = 0;
 
@@ -1988,16 +2146,19 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 	dquot_free_inode(inode);
 	reiserfs_write_lock_nested(inode->i_sb, depth);
 
-      out_end_trans:
-	journal_end(th, th->t_super, th->t_blocks_allocated);
-	/* Drop can be outside and it needs more credits so it's better to have it outside */
+out_end_trans:
+	journal_end(th);
+	/*
+	 * Drop can be outside and it needs more credits so it's better
+	 * to have it outside
+	 */
 	depth = reiserfs_write_unlock_nested(inode->i_sb);
 	dquot_drop(inode);
 	reiserfs_write_lock_nested(inode->i_sb, depth);
 	inode->i_flags |= S_NOQUOTA;
 	make_bad_inode(inode);
 
-      out_inserted_sd:
+out_inserted_sd:
 	clear_nlink(inode);
 	th->t_trans_id = 0;	/* so the caller can't use this handle later */
 	unlock_new_inode(inode); /* OK to do even if we hadn't locked it */
@@ -2006,25 +2167,26 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 }
 
 /*
-** finds the tail page in the page cache,
-** reads the last block in.
-**
-** On success, page_result is set to a locked, pinned page, and bh_result
-** is set to an up to date buffer for the last block in the file.  returns 0.
-**
-** tail conversion is not done, so bh_result might not be valid for writing
-** check buffer_mapped(bh_result) and bh_result->b_blocknr != 0 before
-** trying to write the block.
-**
-** on failure, nonzero is returned, page_result and bh_result are untouched.
-*/
+ * finds the tail page in the page cache,
+ * reads the last block in.
+ *
+ * On success, page_result is set to a locked, pinned page, and bh_result
+ * is set to an up to date buffer for the last block in the file.  returns 0.
+ *
+ * tail conversion is not done, so bh_result might not be valid for writing
+ * check buffer_mapped(bh_result) and bh_result->b_blocknr != 0 before
+ * trying to write the block.
+ *
+ * on failure, nonzero is returned, page_result and bh_result are untouched.
+ */
 static int grab_tail_page(struct inode *inode,
 			  struct page **page_result,
 			  struct buffer_head **bh_result)
 {
 
-	/* we want the page with the last byte in the file,
-	 ** not the page that will hold the next byte for appending
+	/*
+	 * we want the page with the last byte in the file,
+	 * not the page that will hold the next byte for appending
 	 */
 	unsigned long index = (inode->i_size - 1) >> PAGE_CACHE_SHIFT;
 	unsigned long pos = 0;
@@ -2036,10 +2198,11 @@ static int grab_tail_page(struct inode *inode,
 	struct page *page;
 	int error;
 
-	/* we know that we are only called with inode->i_size > 0.
-	 ** we also know that a file tail can never be as big as a block
-	 ** If i_size % blocksize == 0, our file is currently block aligned
-	 ** and it won't need converting or zeroing after a truncate.
+	/*
+	 * we know that we are only called with inode->i_size > 0.
+	 * we also know that a file tail can never be as big as a block
+	 * If i_size % blocksize == 0, our file is currently block aligned
+	 * and it won't need converting or zeroing after a truncate.
 	 */
 	if ((offset & (blocksize - 1)) == 0) {
 		return -ENOENT;
@@ -2068,10 +2231,11 @@ static int grab_tail_page(struct inode *inode,
 	} while (bh != head);
 
 	if (!buffer_uptodate(bh)) {
-		/* note, this should never happen, prepare_write should
-		 ** be taking care of this for us.  If the buffer isn't up to date,
-		 ** I've screwed up the code to find the buffer, or the code to
-		 ** call prepare_write
+		/*
+		 * note, this should never happen, prepare_write should be
+		 * taking care of this for us.  If the buffer isn't up to
+		 * date, I've screwed up the code to find the buffer, or the
+		 * code to call prepare_write
 		 */
 		reiserfs_error(inode->i_sb, "clm-6000",
 			       "error reading block %lu", bh->b_blocknr);
@@ -2081,21 +2245,21 @@ static int grab_tail_page(struct inode *inode,
 	*bh_result = bh;
 	*page_result = page;
 
-      out:
+out:
 	return error;
 
-      unlock:
+unlock:
 	unlock_page(page);
 	page_cache_release(page);
 	return error;
 }
 
 /*
-** vfs version of truncate file.  Must NOT be called with
-** a transaction already started.
-**
-** some code taken from block_truncate_page
-*/
+ * vfs version of truncate file.  Must NOT be called with
+ * a transaction already started.
+ *
+ * some code taken from block_truncate_page
+ */
 int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 {
 	struct reiserfs_transaction_handle th;
@@ -2113,9 +2277,11 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 	if (inode->i_size > 0) {
 		error = grab_tail_page(inode, &page, &bh);
 		if (error) {
-			// -ENOENT means we truncated past the end of the file,
-			// and get_block_create_0 could not find a block to read in,
-			// which is ok.
+			/*
+			 * -ENOENT means we truncated past the end of the
+			 * file, and get_block_create_0 could not find a
+			 * block to read in, which is ok.
+			 */
 			if (error != -ENOENT)
 				reiserfs_error(inode->i_sb, "clm-6001",
 					       "grab_tail_page failed %d",
@@ -2125,29 +2291,33 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 		}
 	}
 
-	/* so, if page != NULL, we have a buffer head for the offset at
-	 ** the end of the file. if the bh is mapped, and bh->b_blocknr != 0,
-	 ** then we have an unformatted node.  Otherwise, we have a direct item,
-	 ** and no zeroing is required on disk.  We zero after the truncate,
-	 ** because the truncate might pack the item anyway
-	 ** (it will unmap bh if it packs).
+	/*
+	 * so, if page != NULL, we have a buffer head for the offset at
+	 * the end of the file. if the bh is mapped, and bh->b_blocknr != 0,
+	 * then we have an unformatted node.  Otherwise, we have a direct item,
+	 * and no zeroing is required on disk.  We zero after the truncate,
+	 * because the truncate might pack the item anyway
+	 * (it will unmap bh if it packs).
+	 *
+	 * it is enough to reserve space in transaction for 2 balancings:
+	 * one for "save" link adding and another for the first
+	 * cut_from_item. 1 is for update_sd
 	 */
-	/* it is enough to reserve space in transaction for 2 balancings:
-	   one for "save" link adding and another for the first
-	   cut_from_item. 1 is for update_sd */
 	error = journal_begin(&th, inode->i_sb,
 			      JOURNAL_PER_BALANCE_CNT * 2 + 1);
 	if (error)
 		goto out;
 	reiserfs_update_inode_transaction(inode);
 	if (update_timestamps)
-		/* we are doing real truncate: if the system crashes before the last
-		   transaction of truncating gets committed - on reboot the file
-		   either appears truncated properly or not truncated at all */
+		/*
+		 * we are doing real truncate: if the system crashes
+		 * before the last transaction of truncating gets committed
+		 * - on reboot the file either appears truncated properly
+		 * or not truncated at all
+		 */
 		add_save_link(&th, inode, 1);
 	err2 = reiserfs_do_truncate(&th, inode, page, update_timestamps);
-	error =
-	    journal_end(&th, inode->i_sb, JOURNAL_PER_BALANCE_CNT * 2 + 1);
+	error = journal_end(&th);
 	if (error)
 		goto out;
 
@@ -2180,7 +2350,7 @@ int reiserfs_truncate_file(struct inode *inode, int update_timestamps)
 	reiserfs_write_unlock(inode->i_sb);
 
 	return 0;
-      out:
+out:
 	if (page) {
 		unlock_page(page);
 		page_cache_release(page);
@@ -2212,7 +2382,10 @@ static int map_block_for_writepage(struct inode *inode,
 	int copy_size;
 	int trans_running = 0;
 
-	/* catch places below that try to log something without starting a trans */
+	/*
+	 * catch places below that try to log something without
+	 * starting a trans
+	 */
 	th.t_trans_id = 0;
 
 	if (!buffer_uptodate(bh_result)) {
@@ -2220,11 +2393,11 @@ static int map_block_for_writepage(struct inode *inode,
 	}
 
 	kmap(bh_result->b_page);
-      start_over:
+start_over:
 	reiserfs_write_lock(inode->i_sb);
 	make_cpu_key(&key, inode, byte_offset, TYPE_ANY, 3);
 
-      research:
+research:
 	retval = search_for_position_by_key(inode->i_sb, &key, &path);
 	if (retval != POSITION_FOUND) {
 		use_get_block = 1;
@@ -2232,8 +2405,8 @@ static int map_block_for_writepage(struct inode *inode,
 	}
 
 	bh = get_last_bh(&path);
-	ih = get_ih(&path);
-	item = get_item(&path);
+	ih = tp_item_head(&path);
+	item = tp_item_body(&path);
 	pos_in_item = path.pos_in_item;
 
 	/* we've found an unformatted node */
@@ -2281,10 +2454,10 @@ static int map_block_for_writepage(struct inode *inode,
 			goto research;
 		}
 
-		memcpy(B_I_PITEM(bh, ih) + pos_in_item, p + bytes_copied,
+		memcpy(ih_item_body(bh, ih) + pos_in_item, p + bytes_copied,
 		       copy_size);
 
-		journal_mark_dirty(&th, inode->i_sb, bh);
+		journal_mark_dirty(&th, bh);
 		bytes_copied += copy_size;
 		set_block_dev_mapped(bh_result, 0, inode);
 
@@ -2304,10 +2477,10 @@ static int map_block_for_writepage(struct inode *inode,
 	}
 	retval = 0;
 
-      out:
+out:
 	pathrelse(&path);
 	if (trans_running) {
-		int err = journal_end(&th, inode->i_sb, jbegin_count);
+		int err = journal_end(&th);
 		if (err)
 			retval = err;
 		trans_running = 0;
@@ -2331,7 +2504,8 @@ static int map_block_for_writepage(struct inode *inode,
 	kunmap(bh_result->b_page);
 
 	if (!retval && buffer_mapped(bh_result) && bh_result->b_blocknr == 0) {
-		/* we've copied data from the page into the direct item, so the
+		/*
+		 * we've copied data from the page into the direct item, so the
 		 * buffer in the page is now clean, mark it to reflect that.
 		 */
 		lock_buffer(bh_result);
@@ -2370,7 +2544,8 @@ static int reiserfs_write_full_page(struct page *page,
 		return 0;
 	}
 
-	/* The page dirty bit is cleared before writepage is called, which
+	/*
+	 * The page dirty bit is cleared before writepage is called, which
 	 * means we have to tell create_empty_buffers to make dirty buffers
 	 * The page really should be up to date at this point, so tossing
 	 * in the BH_Uptodate is just a sanity check.
@@ -2381,8 +2556,9 @@ static int reiserfs_write_full_page(struct page *page,
 	}
 	head = page_buffers(page);
 
-	/* last page in the file, zero out any contents past the
-	 ** last byte in the file
+	/*
+	 * last page in the file, zero out any contents past the
+	 * last byte in the file
 	 */
 	if (page->index >= end_index) {
 		unsigned last_offset;
@@ -2412,7 +2588,8 @@ static int reiserfs_write_full_page(struct page *page,
 		           (!buffer_mapped(bh) || (buffer_mapped(bh)
 						       && bh->b_blocknr ==
 						       0))) {
-			/* not mapped yet, or it points to a direct item, search
+			/*
+			 * not mapped yet, or it points to a direct item, search
 			 * the btree for the mapping info, and log any direct
 			 * items found
 			 */
@@ -2450,10 +2627,11 @@ static int reiserfs_write_full_page(struct page *page,
 
 		if (checked) {
 			reiserfs_prepare_for_journal(s, bh, 1);
-			journal_mark_dirty(&th, s, bh);
+			journal_mark_dirty(&th, bh);
 			continue;
 		}
-		/* from this point on, we know the buffer is mapped to a
+		/*
+		 * from this point on, we know the buffer is mapped to a
 		 * real block and not a direct item
 		 */
 		if (wbc->sync_mode != WB_SYNC_NONE) {
@@ -2472,7 +2650,7 @@ static int reiserfs_write_full_page(struct page *page,
 	} while ((bh = bh->b_this_page) != head);
 
 	if (checked) {
-		error = journal_end(&th, s, bh_per_page + 1);
+		error = journal_end(&th);
 		reiserfs_write_unlock(s);
 		if (error)
 			goto fail;
@@ -2497,7 +2675,7 @@ static int reiserfs_write_full_page(struct page *page,
 	} while (bh != head);
 
 	error = 0;
-      done:
+done:
 	if (nr == 0) {
 		/*
 		 * if this page only had a direct item, it is very possible for
@@ -2519,8 +2697,9 @@ static int reiserfs_write_full_page(struct page *page,
 	}
 	return error;
 
-      fail:
-	/* catches various errors, we need to make sure any valid dirty blocks
+fail:
+	/*
+	 * catches various errors, we need to make sure any valid dirty blocks
 	 * get to the media.  The page is currently locked and not marked for
 	 * writeback
 	 */
@@ -2533,8 +2712,8 @@ static int reiserfs_write_full_page(struct page *page,
 			mark_buffer_async_write(bh);
 		} else {
 			/*
-			 * clear any dirty bits that might have come from getting
-			 * attached to a dirty page
+			 * clear any dirty bits that might have come from
+			 * getting attached to a dirty page
 			 */
 			clear_buffer_dirty(bh);
 		}
@@ -2614,15 +2793,18 @@ static int reiserfs_write_begin(struct file *file,
 	ret = __block_write_begin(page, pos, len, reiserfs_get_block);
 	if (ret && reiserfs_transaction_running(inode->i_sb)) {
 		struct reiserfs_transaction_handle *th = current->journal_info;
-		/* this gets a little ugly.  If reiserfs_get_block returned an
-		 * error and left a transacstion running, we've got to close it,
-		 * and we've got to free handle if it was a persistent transaction.
+		/*
+		 * this gets a little ugly.  If reiserfs_get_block returned an
+		 * error and left a transacstion running, we've got to close
+		 * it, and we've got to free handle if it was a persistent
+		 * transaction.
 		 *
 		 * But, if we had nested into an existing transaction, we need
 		 * to just drop the ref count on the handle.
 		 *
 		 * If old_ref == 0, the transaction is from reiserfs_get_block,
-		 * and it was a persistent trans.  Otherwise, it was nested above.
+		 * and it was a persistent trans.  Otherwise, it was nested
+		 * above.
 		 */
 		if (th->t_refcount > old_ref) {
 			if (old_ref)
@@ -2671,15 +2853,18 @@ int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len)
 	ret = __block_write_begin(page, from, len, reiserfs_get_block);
 	if (ret && reiserfs_transaction_running(inode->i_sb)) {
 		struct reiserfs_transaction_handle *th = current->journal_info;
-		/* this gets a little ugly.  If reiserfs_get_block returned an
-		 * error and left a transacstion running, we've got to close it,
-		 * and we've got to free handle if it was a persistent transaction.
+		/*
+		 * this gets a little ugly.  If reiserfs_get_block returned an
+		 * error and left a transacstion running, we've got to close
+		 * it, and we've got to free handle if it was a persistent
+		 * transaction.
 		 *
 		 * But, if we had nested into an existing transaction, we need
 		 * to just drop the ref count on the handle.
 		 *
 		 * If old_ref == 0, the transaction is from reiserfs_get_block,
-		 * and it was a persistent trans.  Otherwise, it was nested above.
+		 * and it was a persistent trans.  Otherwise, it was nested
+		 * above.
 		 */
 		if (th->t_refcount > old_ref) {
 			if (old_ref)
@@ -2734,17 +2919,20 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 
 	reiserfs_commit_page(inode, page, start, start + copied);
 
-	/* generic_commit_write does this for us, but does not update the
-	 ** transaction tracking stuff when the size changes.  So, we have
-	 ** to do the i_size updates here.
+	/*
+	 * generic_commit_write does this for us, but does not update the
+	 * transaction tracking stuff when the size changes.  So, we have
+	 * to do the i_size updates here.
 	 */
 	if (pos + copied > inode->i_size) {
 		struct reiserfs_transaction_handle myth;
 		reiserfs_write_lock(inode->i_sb);
 		locked = true;
-		/* If the file have grown beyond the border where it
-		   can have a tail, unmark it as needing a tail
-		   packing */
+		/*
+		 * If the file have grown beyond the border where it
+		 * can have a tail, unmark it as needing a tail
+		 * packing
+		 */
 		if ((have_large_tails(inode->i_sb)
 		     && inode->i_size > i_block_size(inode) * 4)
 		    || (have_small_tails(inode->i_sb)
@@ -2759,13 +2947,13 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 		inode->i_size = pos + copied;
 		/*
 		 * this will just nest into our transaction.  It's important
-		 * to use mark_inode_dirty so the inode gets pushed around on the
-		 * dirty lists, and so that O_SYNC works as expected
+		 * to use mark_inode_dirty so the inode gets pushed around on
+		 * the dirty lists, and so that O_SYNC works as expected
 		 */
 		mark_inode_dirty(inode);
 		reiserfs_update_sd(&myth, inode);
 		update_sd = 1;
-		ret = journal_end(&myth, inode->i_sb, 1);
+		ret = journal_end(&myth);
 		if (ret)
 			goto journal_error;
 	}
@@ -2781,7 +2969,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 			goto out;
 	}
 
-      out:
+out:
 	if (locked)
 		reiserfs_write_unlock(inode->i_sb);
 	unlock_page(page);
@@ -2792,7 +2980,7 @@ static int reiserfs_write_end(struct file *file, struct address_space *mapping,
 
 	return ret == 0 ? copied : ret;
 
-      journal_error:
+journal_error:
 	reiserfs_write_unlock(inode->i_sb);
 	locked = false;
 	if (th) {
@@ -2822,15 +3010,18 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 	}
 	reiserfs_commit_page(inode, page, from, to);
 
-	/* generic_commit_write does this for us, but does not update the
-	 ** transaction tracking stuff when the size changes.  So, we have
-	 ** to do the i_size updates here.
+	/*
+	 * generic_commit_write does this for us, but does not update the
+	 * transaction tracking stuff when the size changes.  So, we have
+	 * to do the i_size updates here.
 	 */
 	if (pos > inode->i_size) {
 		struct reiserfs_transaction_handle myth;
-		/* If the file have grown beyond the border where it
-		   can have a tail, unmark it as needing a tail
-		   packing */
+		/*
+		 * If the file have grown beyond the border where it
+		 * can have a tail, unmark it as needing a tail
+		 * packing
+		 */
 		if ((have_large_tails(inode->i_sb)
 		     && inode->i_size > i_block_size(inode) * 4)
 		    || (have_small_tails(inode->i_sb)
@@ -2845,13 +3036,13 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 		inode->i_size = pos;
 		/*
 		 * this will just nest into our transaction.  It's important
-		 * to use mark_inode_dirty so the inode gets pushed around on the
-		 * dirty lists, and so that O_SYNC works as expected
+		 * to use mark_inode_dirty so the inode gets pushed around
+		 * on the dirty lists, and so that O_SYNC works as expected
 		 */
 		mark_inode_dirty(inode);
 		reiserfs_update_sd(&myth, inode);
 		update_sd = 1;
-		ret = journal_end(&myth, inode->i_sb, 1);
+		ret = journal_end(&myth);
 		if (ret)
 			goto journal_error;
 	}
@@ -2863,10 +3054,10 @@ int reiserfs_commit_write(struct file *f, struct page *page,
 			goto out;
 	}
 
-      out:
+out:
 	return ret;
 
-      journal_error:
+journal_error:
 	if (th) {
 		if (!update_sd)
 			reiserfs_update_sd(th, inode);
@@ -2924,9 +3115,10 @@ void i_attrs_to_sd_attrs(struct inode *inode, __u16 * sd_attrs)
 	}
 }
 
-/* decide if this buffer needs to stay around for data logging or ordered
-** write purposes
-*/
+/*
+ * decide if this buffer needs to stay around for data logging or ordered
+ * write purposes
+ */
 static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
 {
 	int ret = 1;
@@ -2937,7 +3129,8 @@ static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
 	if (!buffer_mapped(bh)) {
 		goto free_jh;
 	}
-	/* the page is locked, and the only places that log a data buffer
+	/*
+	 * the page is locked, and the only places that log a data buffer
 	 * also lock the page.
 	 */
 	if (reiserfs_file_data_log(inode)) {
@@ -2952,7 +3145,8 @@ static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
 		struct reiserfs_journal_list *jl;
 		struct reiserfs_jh *jh = bh->b_private;
 
-		/* why is this safe?
+		/*
+		 * why is this safe?
 		 * reiserfs_setattr updates i_size in the on disk
 		 * stat data before allowing vmtruncate to be called.
 		 *
@@ -2969,7 +3163,7 @@ static int invalidatepage_can_drop(struct inode *inode, struct buffer_head *bh)
 		    && jl != SB_JOURNAL(inode->i_sb)->j_current_jl)
 			ret = 0;
 	}
-      free_jh:
+free_jh:
 	if (ret && bh->b_private) {
 		reiserfs_free_jh(bh);
 	}
@@ -3028,7 +3222,7 @@ static void reiserfs_invalidatepage(struct page *page, unsigned int offset,
 		ret = try_to_release_page(page, 0);
 		/* maybe should BUG_ON(!ret); - neilb */
 	}
-      out:
+out:
 	return;
 }
 
@@ -3080,18 +3274,20 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags)
 	return ret;
 }
 
-/* We thank Mingming Cao for helping us understand in great detail what
-   to do in this section of the code. */
+/*
+ * We thank Mingming Cao for helping us understand in great detail what
+ * to do in this section of the code.
+ */
 static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
-				  const struct iovec *iov, loff_t offset,
-				  unsigned long nr_segs)
+				  struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
-				  reiserfs_get_blocks_direct_io);
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
+				 reiserfs_get_blocks_direct_io);
 
 	/*
 	 * In case of error extending write may have instantiated a few
@@ -3099,7 +3295,7 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
 	 */
 	if (unlikely((rw & WRITE) && ret < 0)) {
 		loff_t isize = i_size_read(inode);
-		loff_t end = offset + iov_length(iov, nr_segs);
+		loff_t end = offset + count;
 
 		if ((end > isize) && inode_newsize_ok(inode, isize) == 0) {
 			truncate_setsize(inode, isize);
@@ -3127,8 +3323,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 		dquot_initialize(inode);
 	reiserfs_write_lock(inode->i_sb);
 	if (attr->ia_valid & ATTR_SIZE) {
-		/* version 2 items will be caught by the s_maxbytes check
-		 ** done for us in vmtruncate
+		/*
+		 * version 2 items will be caught by the s_maxbytes check
+		 * done for us in vmtruncate
 		 */
 		if (get_inode_item_key_version(inode) == KEY_FORMAT_3_5 &&
 		    attr->ia_size > MAX_NON_LFS) {
@@ -3149,7 +3346,7 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 				err = journal_begin(&th, inode->i_sb, 4);
 				if (!err) {
 					reiserfs_discard_prealloc(&th, inode);
-					err = journal_end(&th, inode->i_sb, 4);
+					err = journal_end(&th);
 				}
 				if (err)
 					error = err;
@@ -3189,7 +3386,10 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 		if (error)
 			return error;
 
-		/* (user+group)*(old+new) structure - we count quota info and , inode write (sb, inode) */
+		/*
+		 * (user+group)*(old+new) structure - we count quota
+		 * info and , inode write (sb, inode)
+		 */
 		reiserfs_write_lock(inode->i_sb);
 		error = journal_begin(&th, inode->i_sb, jbegin_count);
 		reiserfs_write_unlock(inode->i_sb);
@@ -3198,19 +3398,21 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 		error = dquot_transfer(inode, attr);
 		reiserfs_write_lock(inode->i_sb);
 		if (error) {
-			journal_end(&th, inode->i_sb, jbegin_count);
+			journal_end(&th);
 			reiserfs_write_unlock(inode->i_sb);
 			goto out;
 		}
 
-		/* Update corresponding info in inode so that everything is in
-		 * one transaction */
+		/*
+		 * Update corresponding info in inode so that everything
+		 * is in one transaction
+		 */
 		if (attr->ia_valid & ATTR_UID)
 			inode->i_uid = attr->ia_uid;
 		if (attr->ia_valid & ATTR_GID)
 			inode->i_gid = attr->ia_gid;
 		mark_inode_dirty(inode);
-		error = journal_end(&th, inode->i_sb, jbegin_count);
+		error = journal_end(&th);
 		reiserfs_write_unlock(inode->i_sb);
 		if (error)
 			goto out;
@@ -3220,8 +3422,14 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 	    attr->ia_size != i_size_read(inode)) {
 		error = inode_newsize_ok(inode, attr->ia_size);
 		if (!error) {
+			/*
+			 * Could race against reiserfs_file_release
+			 * if called from NFS, so take tailpack mutex.
+			 */
+			mutex_lock(&REISERFS_I(inode)->tailpack);
 			truncate_setsize(inode, attr->ia_size);
-			reiserfs_vfs_truncate_file(inode);
+			reiserfs_truncate_file(inode, 1);
+			mutex_unlock(&REISERFS_I(inode)->tailpack);
 		}
 	}
 
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 946ccbf5b5a..501ed6811a2 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -15,7 +15,8 @@
  * reiserfs_ioctl - handler for ioctl for inode
  * supported commands:
  *  1) REISERFS_IOC_UNPACK - try to unpack tail from direct item into indirect
- *                           and prevent packing file (argument arg has to be non-zero)
+ *                           and prevent packing file (argument arg has t
+ *			      be non-zero)
  *  2) REISERFS_IOC_[GS]ETFLAGS, REISERFS_IOC_[GS]ETVERSION
  *  3) That's all for a while ...
  */
@@ -132,7 +133,10 @@ setversion_out:
 long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg)
 {
-	/* These are just misnamed, they actually get/put from/to user an int */
+	/*
+	 * These are just misnamed, they actually
+	 * get/put from/to user an int
+	 */
 	switch (cmd) {
 	case REISERFS_IOC32_UNPACK:
 		cmd = REISERFS_IOC_UNPACK;
@@ -160,10 +164,10 @@ long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
 int reiserfs_commit_write(struct file *f, struct page *page,
 			  unsigned from, unsigned to);
 /*
-** reiserfs_unpack
-** Function try to convert tail from direct item into indirect.
-** It set up nopack attribute in the REISERFS_I(inode)->nopack
-*/
+ * reiserfs_unpack
+ * Function try to convert tail from direct item into indirect.
+ * It set up nopack attribute in the REISERFS_I(inode)->nopack
+ */
 int reiserfs_unpack(struct inode *inode, struct file *filp)
 {
 	int retval = 0;
@@ -194,9 +198,10 @@ int reiserfs_unpack(struct inode *inode, struct file *filp)
 		goto out;
 	}
 
-	/* we unpack by finding the page with the tail, and calling
-	 ** __reiserfs_write_begin on that page.  This will force a
-	 ** reiserfs_get_block to unpack the tail for us.
+	/*
+	 * we unpack by finding the page with the tail, and calling
+	 * __reiserfs_write_begin on that page.  This will force a
+	 * reiserfs_get_block to unpack the tail for us.
 	 */
 	index = inode->i_size >> PAGE_CACHE_SHIFT;
 	mapping = inode->i_mapping;
@@ -214,11 +219,11 @@ int reiserfs_unpack(struct inode *inode, struct file *filp)
 	retval = reiserfs_commit_write(NULL, page, write_from, write_from);
 	REISERFS_I(inode)->i_flags |= i_nopack_mask;
 
-      out_unlock:
+out_unlock:
 	unlock_page(page);
 	page_cache_release(page);
 
-      out:
+out:
 	mutex_unlock(&inode->i_mutex);
 	reiserfs_write_unlock(inode->i_sb);
 	return retval;
diff --git a/fs/reiserfs/item_ops.c b/fs/reiserfs/item_ops.c
index ee382ef3d30..cfaee912ee0 100644
--- a/fs/reiserfs/item_ops.c
+++ b/fs/reiserfs/item_ops.c
@@ -5,15 +5,17 @@
 #include <linux/time.h>
 #include "reiserfs.h"
 
-// this contains item handlers for old item types: sd, direct,
-// indirect, directory
+/*
+ * this contains item handlers for old item types: sd, direct,
+ * indirect, directory
+ */
 
-/* and where are the comments? how about saying where we can find an
-   explanation of each item handler method? -Hans */
+/*
+ * and where are the comments? how about saying where we can find an
+ * explanation of each item handler method? -Hans
+ */
 
-//////////////////////////////////////////////////////////////////////////////
-// stat data functions
-//
+/* stat data functions */
 static int sd_bytes_number(struct item_head *ih, int block_size)
 {
 	return 0;
@@ -60,7 +62,7 @@ static void sd_print_item(struct item_head *ih, char *item)
 
 static void sd_check_item(struct item_head *ih, char *item)
 {
-	// FIXME: type something here!
+	/* unused */
 }
 
 static int sd_create_vi(struct virtual_node *vn,
@@ -68,7 +70,6 @@ static int sd_create_vi(struct virtual_node *vn,
 			int is_affected, int insert_size)
 {
 	vi->vi_index = TYPE_STAT_DATA;
-	//vi->vi_type |= VI_TYPE_STAT_DATA;// not needed?
 	return 0;
 }
 
@@ -117,15 +118,13 @@ static struct item_operations stat_data_ops = {
 	.print_vi = sd_print_vi
 };
 
-//////////////////////////////////////////////////////////////////////////////
-// direct item functions
-//
+/* direct item functions */
 static int direct_bytes_number(struct item_head *ih, int block_size)
 {
 	return ih_item_len(ih);
 }
 
-// FIXME: this should probably switch to indirect as well
+/* FIXME: this should probably switch to indirect as well */
 static void direct_decrement_key(struct cpu_key *key)
 {
 	cpu_key_k_offset_dec(key);
@@ -144,7 +143,7 @@ static void direct_print_item(struct item_head *ih, char *item)
 {
 	int j = 0;
 
-//    return;
+/*    return; */
 	printk("\"");
 	while (j < ih_item_len(ih))
 		printk("%c", item[j++]);
@@ -153,7 +152,7 @@ static void direct_print_item(struct item_head *ih, char *item)
 
 static void direct_check_item(struct item_head *ih, char *item)
 {
-	// FIXME: type something here!
+	/* unused */
 }
 
 static int direct_create_vi(struct virtual_node *vn,
@@ -161,7 +160,6 @@ static int direct_create_vi(struct virtual_node *vn,
 			    int is_affected, int insert_size)
 {
 	vi->vi_index = TYPE_DIRECT;
-	//vi->vi_type |= VI_TYPE_DIRECT;
 	return 0;
 }
 
@@ -211,16 +209,13 @@ static struct item_operations direct_ops = {
 	.print_vi = direct_print_vi
 };
 
-//////////////////////////////////////////////////////////////////////////////
-// indirect item functions
-//
-
+/* indirect item functions */
 static int indirect_bytes_number(struct item_head *ih, int block_size)
 {
-	return ih_item_len(ih) / UNFM_P_SIZE * block_size;	//- get_ih_free_space (ih);
+	return ih_item_len(ih) / UNFM_P_SIZE * block_size;
 }
 
-// decrease offset, if it becomes 0, change type to stat data
+/* decrease offset, if it becomes 0, change type to stat data */
 static void indirect_decrement_key(struct cpu_key *key)
 {
 	cpu_key_k_offset_dec(key);
@@ -228,7 +223,7 @@ static void indirect_decrement_key(struct cpu_key *key)
 		set_cpu_key_k_type(key, TYPE_STAT_DATA);
 }
 
-// if it is not first item of the body, then it is mergeable
+/* if it is not first item of the body, then it is mergeable */
 static int indirect_is_left_mergeable(struct reiserfs_key *key,
 				      unsigned long bsize)
 {
@@ -236,7 +231,7 @@ static int indirect_is_left_mergeable(struct reiserfs_key *key,
 	return (le_key_k_offset(version, key) != 1);
 }
 
-// printing of indirect item
+/* printing of indirect item */
 static void start_new_sequence(__u32 * start, int *len, __u32 new)
 {
 	*start = new;
@@ -295,7 +290,7 @@ static void indirect_print_item(struct item_head *ih, char *item)
 
 static void indirect_check_item(struct item_head *ih, char *item)
 {
-	// FIXME: type something here!
+	/* unused */
 }
 
 static int indirect_create_vi(struct virtual_node *vn,
@@ -303,7 +298,6 @@ static int indirect_create_vi(struct virtual_node *vn,
 			      int is_affected, int insert_size)
 {
 	vi->vi_index = TYPE_INDIRECT;
-	//vi->vi_type |= VI_TYPE_INDIRECT;
 	return 0;
 }
 
@@ -321,16 +315,19 @@ static int indirect_check_right(struct virtual_item *vi, int free)
 	return indirect_check_left(vi, free, 0, 0);
 }
 
-// return size in bytes of 'units' units. If first == 0 - calculate from the head (left), otherwise - from tail (right)
+/*
+ * return size in bytes of 'units' units. If first == 0 - calculate
+ * from the head (left), otherwise - from tail (right)
+ */
 static int indirect_part_size(struct virtual_item *vi, int first, int units)
 {
-	// unit of indirect item is byte (yet)
+	/* unit of indirect item is byte (yet) */
 	return units;
 }
 
 static int indirect_unit_num(struct virtual_item *vi)
 {
-	// unit of indirect item is byte (yet)
+	/* unit of indirect item is byte (yet) */
 	return vi->vi_item_len - IH_SIZE;
 }
 
@@ -356,10 +353,7 @@ static struct item_operations indirect_ops = {
 	.print_vi = indirect_print_vi
 };
 
-//////////////////////////////////////////////////////////////////////////////
-// direntry functions
-//
-
+/* direntry functions */
 static int direntry_bytes_number(struct item_head *ih, int block_size)
 {
 	reiserfs_warning(NULL, "vs-16090",
@@ -396,7 +390,7 @@ static void direntry_print_item(struct item_head *ih, char *item)
 
 	deh = (struct reiserfs_de_head *)item;
 
-	for (i = 0; i < I_ENTRY_COUNT(ih); i++, deh++) {
+	for (i = 0; i < ih_entry_count(ih); i++, deh++) {
 		namelen =
 		    (i ? (deh_location(deh - 1)) : ih_item_len(ih)) -
 		    deh_location(deh);
@@ -428,9 +422,9 @@ static void direntry_check_item(struct item_head *ih, char *item)
 	int i;
 	struct reiserfs_de_head *deh;
 
-	// FIXME: type something here!
+	/* unused */
 	deh = (struct reiserfs_de_head *)item;
-	for (i = 0; i < I_ENTRY_COUNT(ih); i++, deh++) {
+	for (i = 0; i < ih_entry_count(ih); i++, deh++) {
 		;
 	}
 }
@@ -439,7 +433,8 @@ static void direntry_check_item(struct item_head *ih, char *item)
 
 /*
  * function returns old entry number in directory item in real node
- * using new entry number in virtual item in virtual node */
+ * using new entry number in virtual item in virtual node
+ */
 static inline int old_entry_num(int is_affected, int virtual_entry_num,
 				int pos_in_item, int mode)
 {
@@ -463,9 +458,11 @@ static inline int old_entry_num(int is_affected, int virtual_entry_num,
 	return virtual_entry_num - 1;
 }
 
-/* Create an array of sizes of directory entries for virtual
-   item. Return space used by an item. FIXME: no control over
-   consuming of space used by this item handler */
+/*
+ * Create an array of sizes of directory entries for virtual
+ * item. Return space used by an item. FIXME: no control over
+ * consuming of space used by this item handler
+ */
 static int direntry_create_vi(struct virtual_node *vn,
 			      struct virtual_item *vi,
 			      int is_affected, int insert_size)
@@ -494,8 +491,8 @@ static int direntry_create_vi(struct virtual_node *vn,
 		j = old_entry_num(is_affected, i, vn->vn_pos_in_item,
 				  vn->vn_mode);
 		dir_u->entry_sizes[i] =
-		    (j ? deh_location(&(deh[j - 1])) : ih_item_len(vi->vi_ih)) -
-		    deh_location(&(deh[j])) + DEH_SIZE;
+		    (j ? deh_location(&deh[j - 1]) : ih_item_len(vi->vi_ih)) -
+		    deh_location(&deh[j]) + DEH_SIZE;
 	}
 
 	size += (dir_u->entry_count * sizeof(short));
@@ -529,10 +526,10 @@ static int direntry_create_vi(struct virtual_node *vn,
 
 }
 
-//
-// return number of entries which may fit into specified amount of
-// free space, or -1 if free space is not enough even for 1 entry
-//
+/*
+ * return number of entries which may fit into specified amount of
+ * free space, or -1 if free space is not enough even for 1 entry
+ */
 static int direntry_check_left(struct virtual_item *vi, int free,
 			       int start_skip, int end_skip)
 {
@@ -541,8 +538,8 @@ static int direntry_check_left(struct virtual_item *vi, int free,
 	struct direntry_uarea *dir_u = vi->vi_uarea;
 
 	for (i = start_skip; i < dir_u->entry_count - end_skip; i++) {
+		/* i-th entry doesn't fit into the remaining free space */
 		if (dir_u->entry_sizes[i] > free)
-			/* i-th entry doesn't fit into the remaining free space */
 			break;
 
 		free -= dir_u->entry_sizes[i];
@@ -570,8 +567,8 @@ static int direntry_check_right(struct virtual_item *vi, int free)
 	struct direntry_uarea *dir_u = vi->vi_uarea;
 
 	for (i = dir_u->entry_count - 1; i >= 0; i--) {
+		/* i-th entry doesn't fit into the remaining free space */
 		if (dir_u->entry_sizes[i] > free)
-			/* i-th entry doesn't fit into the remaining free space */
 			break;
 
 		free -= dir_u->entry_sizes[i];
@@ -643,9 +640,7 @@ static struct item_operations direntry_ops = {
 	.print_vi = direntry_print_vi
 };
 
-//////////////////////////////////////////////////////////////////////////////
-// Error catching functions to catch errors caused by incorrect item types.
-//
+/* Error catching functions to catch errors caused by incorrect item types. */
 static int errcatch_bytes_number(struct item_head *ih, int block_size)
 {
 	reiserfs_warning(NULL, "green-16001",
@@ -685,8 +680,12 @@ static int errcatch_create_vi(struct virtual_node *vn,
 {
 	reiserfs_warning(NULL, "green-16006",
 			 "Invalid item type observed, run fsck ASAP");
-	return 0;		// We might return -1 here as well, but it won't help as create_virtual_node() from where
-	// this operation is called from is of return type void.
+	/*
+	 * We might return -1 here as well, but it won't help as
+	 * create_virtual_node() from where this operation is called
+	 * from is of return type void.
+	 */
+	return 0;
 }
 
 static int errcatch_check_left(struct virtual_item *vi, int free,
@@ -739,9 +738,6 @@ static struct item_operations errcatch_ops = {
 	errcatch_print_vi
 };
 
-//////////////////////////////////////////////////////////////////////////////
-//
-//
 #if ! (TYPE_STAT_DATA == 0 && TYPE_INDIRECT == 1 && TYPE_DIRECT == 2 && TYPE_DIRENTRY == 3)
 #error Item types must use disk-format assigned values.
 #endif
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index fd777032c2b..e8870de4627 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -1,38 +1,38 @@
 /*
-** Write ahead logging implementation copyright Chris Mason 2000
-**
-** The background commits make this code very interrelated, and
-** overly complex.  I need to rethink things a bit....The major players:
-**
-** journal_begin -- call with the number of blocks you expect to log.
-**                  If the current transaction is too
-** 		    old, it will block until the current transaction is
-** 		    finished, and then start a new one.
-**		    Usually, your transaction will get joined in with
-**                  previous ones for speed.
-**
-** journal_join  -- same as journal_begin, but won't block on the current
-**                  transaction regardless of age.  Don't ever call
-**                  this.  Ever.  There are only two places it should be
-**                  called from, and they are both inside this file.
-**
-** journal_mark_dirty -- adds blocks into this transaction.  clears any flags
-**                       that might make them get sent to disk
-**                       and then marks them BH_JDirty.  Puts the buffer head
-**                       into the current transaction hash.
-**
-** journal_end -- if the current transaction is batchable, it does nothing
-**                   otherwise, it could do an async/synchronous commit, or
-**                   a full flush of all log and real blocks in the
-**                   transaction.
-**
-** flush_old_commits -- if the current transaction is too old, it is ended and
-**                      commit blocks are sent to disk.  Forces commit blocks
-**                      to disk for all backgrounded commits that have been
-**                      around too long.
-**		     -- Note, if you call this as an immediate flush from
-**		        from within kupdate, it will ignore the immediate flag
-*/
+ * Write ahead logging implementation copyright Chris Mason 2000
+ *
+ * The background commits make this code very interrelated, and
+ * overly complex.  I need to rethink things a bit....The major players:
+ *
+ * journal_begin -- call with the number of blocks you expect to log.
+ *                  If the current transaction is too
+ *		    old, it will block until the current transaction is
+ *		    finished, and then start a new one.
+ *		    Usually, your transaction will get joined in with
+ *                  previous ones for speed.
+ *
+ * journal_join  -- same as journal_begin, but won't block on the current
+ *                  transaction regardless of age.  Don't ever call
+ *                  this.  Ever.  There are only two places it should be
+ *                  called from, and they are both inside this file.
+ *
+ * journal_mark_dirty -- adds blocks into this transaction.  clears any flags
+ *                       that might make them get sent to disk
+ *                       and then marks them BH_JDirty.  Puts the buffer head
+ *                       into the current transaction hash.
+ *
+ * journal_end -- if the current transaction is batchable, it does nothing
+ *                   otherwise, it could do an async/synchronous commit, or
+ *                   a full flush of all log and real blocks in the
+ *                   transaction.
+ *
+ * flush_old_commits -- if the current transaction is too old, it is ended and
+ *                      commit blocks are sent to disk.  Forces commit blocks
+ *                      to disk for all backgrounded commits that have been
+ *                      around too long.
+ *		     -- Note, if you call this as an immediate flush from
+ *		        from within kupdate, it will ignore the immediate flag
+ */
 
 #include <linux/time.h>
 #include <linux/semaphore.h>
@@ -58,23 +58,19 @@
 #define JOURNAL_WORK_ENTRY(h) (list_entry((h), struct reiserfs_journal_list, \
                                j_working_list))
 
-/* the number of mounted filesystems.  This is used to decide when to
-** start and kill the commit workqueue
-*/
-static int reiserfs_mounted_fs_count;
-
-static struct workqueue_struct *commit_wq;
-
-#define JOURNAL_TRANS_HALF 1018	/* must be correct to keep the desc and commit
-				   structs at 4k */
+/* must be correct to keep the desc and commit structs at 4k */
+#define JOURNAL_TRANS_HALF 1018
 #define BUFNR 64		/*read ahead */
 
 /* cnode stat bits.  Move these into reiserfs_fs.h */
 
-#define BLOCK_FREED 2		/* this block was freed, and can't be written.  */
-#define BLOCK_FREED_HOLDER 3	/* this block was freed during this transaction, and can't be written */
+/* this block was freed, and can't be written.  */
+#define BLOCK_FREED 2
+/* this block was freed during this transaction, and can't be written */
+#define BLOCK_FREED_HOLDER 3
 
-#define BLOCK_NEEDS_FLUSH 4	/* used in flush_journal_list */
+/* used in flush_journal_list */
+#define BLOCK_NEEDS_FLUSH 4
 #define BLOCK_DIRTIED 5
 
 /* journal list state bits */
@@ -87,16 +83,14 @@ static struct workqueue_struct *commit_wq;
 #define COMMIT_NOW  2		/* end and commit this transaction */
 #define WAIT        4		/* wait for the log blocks to hit the disk */
 
-static int do_journal_end(struct reiserfs_transaction_handle *,
-			  struct super_block *, unsigned long nblocks,
-			  int flags);
+static int do_journal_end(struct reiserfs_transaction_handle *, int flags);
 static int flush_journal_list(struct super_block *s,
 			      struct reiserfs_journal_list *jl, int flushall);
 static int flush_commit_list(struct super_block *s,
 			     struct reiserfs_journal_list *jl, int flushall);
 static int can_dirty(struct reiserfs_journal_cnode *cn);
 static int journal_join(struct reiserfs_transaction_handle *th,
-			struct super_block *sb, unsigned long nblocks);
+			struct super_block *sb);
 static void release_journal_dev(struct super_block *super,
 			       struct reiserfs_journal *journal);
 static int dirty_one_transaction(struct super_block *s,
@@ -107,8 +101,10 @@ static void queue_log_writer(struct super_block *s);
 /* values for join in do_journal_begin_r */
 enum {
 	JBEGIN_REG = 0,		/* regular journal begin */
-	JBEGIN_JOIN = 1,	/* join the running transaction if at all possible */
-	JBEGIN_ABORT = 2,	/* called from cleanup code, ignores aborted flag */
+	/* join the running transaction if at all possible */
+	JBEGIN_JOIN = 1,
+	/* called from cleanup code, ignores aborted flag */
+	JBEGIN_ABORT = 2,
 };
 
 static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
@@ -123,10 +119,11 @@ static void init_journal_hash(struct super_block *sb)
 }
 
 /*
-** clears BH_Dirty and sticks the buffer on the clean list.  Called because I can't allow refile_buffer to
-** make schedule happen after I've freed a block.  Look at remove_from_transaction and journal_mark_freed for
-** more details.
-*/
+ * clears BH_Dirty and sticks the buffer on the clean list.  Called because
+ * I can't allow refile_buffer to make schedule happen after I've freed a
+ * block.  Look at remove_from_transaction and journal_mark_freed for
+ * more details.
+ */
 static int reiserfs_clean_and_file_buffer(struct buffer_head *bh)
 {
 	if (bh) {
@@ -163,7 +160,7 @@ static struct reiserfs_bitmap_node *get_bitmap_node(struct super_block *sb)
 	struct list_head *entry = journal->j_bitmap_nodes.next;
 
 	journal->j_used_bitmap_nodes++;
-      repeat:
+repeat:
 
 	if (entry != &journal->j_bitmap_nodes) {
 		bn = list_entry(entry, struct reiserfs_bitmap_node, list);
@@ -204,7 +201,8 @@ static void allocate_bitmap_nodes(struct super_block *sb)
 			list_add(&bn->list, &journal->j_bitmap_nodes);
 			journal->j_free_bitmap_nodes++;
 		} else {
-			break;	/* this is ok, we'll try again when more are needed */
+			/* this is ok, we'll try again when more are needed */
+			break;
 		}
 	}
 }
@@ -239,8 +237,8 @@ static void cleanup_bitmap_list(struct super_block *sb,
 }
 
 /*
-** only call this on FS unmount.
-*/
+ * only call this on FS unmount.
+ */
 static int free_list_bitmaps(struct super_block *sb,
 			     struct reiserfs_list_bitmap *jb_array)
 {
@@ -275,9 +273,9 @@ static int free_bitmap_nodes(struct super_block *sb)
 }
 
 /*
-** get memory for JOURNAL_NUM_BITMAPS worth of bitmaps.
-** jb_array is the array to be filled in.
-*/
+ * get memory for JOURNAL_NUM_BITMAPS worth of bitmaps.
+ * jb_array is the array to be filled in.
+ */
 int reiserfs_allocate_list_bitmaps(struct super_block *sb,
 				   struct reiserfs_list_bitmap *jb_array,
 				   unsigned int bmap_nr)
@@ -306,9 +304,9 @@ int reiserfs_allocate_list_bitmaps(struct super_block *sb,
 }
 
 /*
-** find an available list bitmap.  If you can't find one, flush a commit list
-** and try again
-*/
+ * find an available list bitmap.  If you can't find one, flush a commit list
+ * and try again
+ */
 static struct reiserfs_list_bitmap *get_list_bitmap(struct super_block *sb,
 						    struct reiserfs_journal_list
 						    *jl)
@@ -332,18 +330,18 @@ static struct reiserfs_list_bitmap *get_list_bitmap(struct super_block *sb,
 			break;
 		}
 	}
-	if (jb->journal_list) {	/* double check to make sure if flushed correctly */
+	/* double check to make sure if flushed correctly */
+	if (jb->journal_list)
 		return NULL;
-	}
 	jb->journal_list = jl;
 	return jb;
 }
 
 /*
-** allocates a new chunk of X nodes, and links them all together as a list.
-** Uses the cnode->next and cnode->prev pointers
-** returns NULL on failure
-*/
+ * allocates a new chunk of X nodes, and links them all together as a list.
+ * Uses the cnode->next and cnode->prev pointers
+ * returns NULL on failure
+ */
 static struct reiserfs_journal_cnode *allocate_cnodes(int num_cnodes)
 {
 	struct reiserfs_journal_cnode *head;
@@ -365,9 +363,7 @@ static struct reiserfs_journal_cnode *allocate_cnodes(int num_cnodes)
 	return head;
 }
 
-/*
-** pulls a cnode off the free list, or returns NULL on failure
-*/
+/* pulls a cnode off the free list, or returns NULL on failure */
 static struct reiserfs_journal_cnode *get_cnode(struct super_block *sb)
 {
 	struct reiserfs_journal_cnode *cn;
@@ -393,8 +389,8 @@ static struct reiserfs_journal_cnode *get_cnode(struct super_block *sb)
 }
 
 /*
-** returns a cnode to the free list
-*/
+ * returns a cnode to the free list
+ */
 static void free_cnode(struct super_block *sb,
 		       struct reiserfs_journal_cnode *cn)
 {
@@ -419,7 +415,10 @@ static void clear_prepared_bits(struct buffer_head *bh)
 	clear_buffer_journal_restore_dirty(bh);
 }
 
-/* return a cnode with same dev, block number and size in table, or null if not found */
+/*
+ * return a cnode with same dev, block number and size in table,
+ * or null if not found
+ */
 static inline struct reiserfs_journal_cnode *get_journal_hash_dev(struct
 								  super_block
 								  *sb,
@@ -439,23 +438,24 @@ static inline struct reiserfs_journal_cnode *get_journal_hash_dev(struct
 }
 
 /*
-** this actually means 'can this block be reallocated yet?'.  If you set search_all, a block can only be allocated
-** if it is not in the current transaction, was not freed by the current transaction, and has no chance of ever
-** being overwritten by a replay after crashing.
-**
-** If you don't set search_all, a block can only be allocated if it is not in the current transaction.  Since deleting
-** a block removes it from the current transaction, this case should never happen.  If you don't set search_all, make
-** sure you never write the block without logging it.
-**
-** next_zero_bit is a suggestion about the next block to try for find_forward.
-** when bl is rejected because it is set in a journal list bitmap, we search
-** for the next zero bit in the bitmap that rejected bl.  Then, we return that
-** through next_zero_bit for find_forward to try.
-**
-** Just because we return something in next_zero_bit does not mean we won't
-** reject it on the next call to reiserfs_in_journal
-**
-*/
+ * this actually means 'can this block be reallocated yet?'.  If you set
+ * search_all, a block can only be allocated if it is not in the current
+ * transaction, was not freed by the current transaction, and has no chance
+ * of ever being overwritten by a replay after crashing.
+ *
+ * If you don't set search_all, a block can only be allocated if it is not
+ * in the current transaction.  Since deleting a block removes it from the
+ * current transaction, this case should never happen.  If you don't set
+ * search_all, make sure you never write the block without logging it.
+ *
+ * next_zero_bit is a suggestion about the next block to try for find_forward.
+ * when bl is rejected because it is set in a journal list bitmap, we search
+ * for the next zero bit in the bitmap that rejected bl.  Then, we return
+ * that through next_zero_bit for find_forward to try.
+ *
+ * Just because we return something in next_zero_bit does not mean we won't
+ * reject it on the next call to reiserfs_in_journal
+ */
 int reiserfs_in_journal(struct super_block *sb,
 			unsigned int bmap_nr, int bit_nr, int search_all,
 			b_blocknr_t * next_zero_bit)
@@ -469,9 +469,11 @@ int reiserfs_in_journal(struct super_block *sb,
 	*next_zero_bit = 0;	/* always start this at zero. */
 
 	PROC_INFO_INC(sb, journal.in_journal);
-	/* If we aren't doing a search_all, this is a metablock, and it will be logged before use.
-	 ** if we crash before the transaction that freed it commits,  this transaction won't
-	 ** have committed either, and the block will never be written
+	/*
+	 * If we aren't doing a search_all, this is a metablock, and it
+	 * will be logged before use.  if we crash before the transaction
+	 * that freed it commits,  this transaction won't have committed
+	 * either, and the block will never be written
 	 */
 	if (search_all) {
 		for (i = 0; i < JOURNAL_NUM_BITMAPS; i++) {
@@ -511,8 +513,7 @@ int reiserfs_in_journal(struct super_block *sb,
 	return 0;
 }
 
-/* insert cn into table
-*/
+/* insert cn into table */
 static inline void insert_journal_hash(struct reiserfs_journal_cnode **table,
 				       struct reiserfs_journal_cnode *cn)
 {
@@ -558,10 +559,10 @@ static inline void put_journal_list(struct super_block *s,
 }
 
 /*
-** this used to be much more involved, and I'm keeping it just in case things get ugly again.
-** it gets called by flush_commit_list, and cleans up any data stored about blocks freed during a
-** transaction.
-*/
+ * this used to be much more involved, and I'm keeping it just in case
+ * things get ugly again.  it gets called by flush_commit_list, and
+ * cleans up any data stored about blocks freed during a transaction.
+ */
 static void cleanup_freed_for_journal_list(struct super_block *sb,
 					   struct reiserfs_journal_list *jl)
 {
@@ -756,11 +757,12 @@ static inline int __add_jh(struct reiserfs_journal *j, struct buffer_head *bh,
 		jh = bh->b_private;
 		list_del_init(&jh->list);
 	} else {
-	      no_jh:
+no_jh:
 		get_bh(bh);
 		jh = alloc_jh();
 		spin_lock(&j->j_dirty_buffers_lock);
-		/* buffer must be locked for __add_jh, should be able to have
+		/*
+		 * buffer must be locked for __add_jh, should be able to have
 		 * two adds at the same time
 		 */
 		BUG_ON(bh->b_private);
@@ -818,7 +820,8 @@ static int write_ordered_buffers(spinlock_t * lock,
 			spin_lock(lock);
 			goto loop_next;
 		}
-		/* in theory, dirty non-uptodate buffers should never get here,
+		/*
+		 * in theory, dirty non-uptodate buffers should never get here,
 		 * but the upper layer io error paths still have a few quirks.
 		 * Handle them here as gracefully as we can
 		 */
@@ -833,7 +836,7 @@ static int write_ordered_buffers(spinlock_t * lock,
 			reiserfs_free_jh(bh);
 			unlock_buffer(bh);
 		}
-	      loop_next:
+loop_next:
 		put_bh(bh);
 		cond_resched_lock(lock);
 	}
@@ -856,13 +859,14 @@ static int write_ordered_buffers(spinlock_t * lock,
 		if (!buffer_uptodate(bh)) {
 			ret = -EIO;
 		}
-		/* ugly interaction with invalidatepage here.
-		 * reiserfs_invalidate_page will pin any buffer that has a valid
-		 * journal head from an older transaction.  If someone else sets
-		 * our buffer dirty after we write it in the first loop, and
-		 * then someone truncates the page away, nobody will ever write
-		 * the buffer. We're safe if we write the page one last time
-		 * after freeing the journal header.
+		/*
+		 * ugly interaction with invalidatepage here.
+		 * reiserfs_invalidate_page will pin any buffer that has a
+		 * valid journal head from an older transaction.  If someone
+		 * else sets our buffer dirty after we write it in the first
+		 * loop, and then someone truncates the page away, nobody
+		 * will ever write the buffer. We're safe if we write the
+		 * page one last time after freeing the journal header.
 		 */
 		if (buffer_dirty(bh) && unlikely(bh->b_page->mapping == NULL)) {
 			spin_unlock(lock);
@@ -887,7 +891,7 @@ static int flush_older_commits(struct super_block *s,
 	unsigned int other_trans_id;
 	unsigned int first_trans_id;
 
-      find_first:
+find_first:
 	/*
 	 * first we walk backwards to find the oldest uncommitted transation
 	 */
@@ -923,9 +927,11 @@ static int flush_older_commits(struct super_block *s,
 				if (!journal_list_still_alive(s, trans_id))
 					return 1;
 
-				/* the one we just flushed is gone, this means all
-				 * older lists are also gone, so first_jl is no longer
-				 * valid either.  Go back to the beginning.
+				/*
+				 * the one we just flushed is gone, this means
+				 * all older lists are also gone, so first_jl
+				 * is no longer valid either.  Go back to the
+				 * beginning.
 				 */
 				if (!journal_list_still_alive
 				    (s, other_trans_id)) {
@@ -958,12 +964,12 @@ static int reiserfs_async_progress_wait(struct super_block *s)
 }
 
 /*
-** if this journal list still has commit blocks unflushed, send them to disk.
-**
-** log areas must be flushed in order (transaction 2 can't commit before transaction 1)
-** Before the commit block can by written, every other log block must be safely on disk
-**
-*/
+ * if this journal list still has commit blocks unflushed, send them to disk.
+ *
+ * log areas must be flushed in order (transaction 2 can't commit before
+ * transaction 1) Before the commit block can by written, every other log
+ * block must be safely on disk
+ */
 static int flush_commit_list(struct super_block *s,
 			     struct reiserfs_journal_list *jl, int flushall)
 {
@@ -982,8 +988,9 @@ static int flush_commit_list(struct super_block *s,
 		return 0;
 	}
 
-	/* before we can put our commit blocks on disk, we have to make sure everyone older than
-	 ** us is on disk too
+	/*
+	 * before we can put our commit blocks on disk, we have to make
+	 * sure everyone older than us is on disk too
 	 */
 	BUG_ON(jl->j_len <= 0);
 	BUG_ON(trans_id == journal->j_trans_id);
@@ -991,7 +998,10 @@ static int flush_commit_list(struct super_block *s,
 	get_journal_list(jl);
 	if (flushall) {
 		if (flush_older_commits(s, jl) == 1) {
-			/* list disappeared during flush_older_commits.  return */
+			/*
+			 * list disappeared during flush_older_commits.
+			 * return
+			 */
 			goto put_jl;
 		}
 	}
@@ -1006,9 +1016,9 @@ static int flush_commit_list(struct super_block *s,
 	BUG_ON(jl->j_trans_id == 0);
 
 	/* this commit is done, exit */
-	if (atomic_read(&(jl->j_commit_left)) <= 0) {
+	if (atomic_read(&jl->j_commit_left) <= 0) {
 		if (flushall) {
-			atomic_set(&(jl->j_older_commits_done), 1);
+			atomic_set(&jl->j_older_commits_done, 1);
 		}
 		mutex_unlock(&jl->j_commit_mutex);
 		goto put_jl;
@@ -1063,9 +1073,10 @@ static int flush_commit_list(struct super_block *s,
 		depth = reiserfs_write_unlock_nested(s);
 		__wait_on_buffer(tbh);
 		reiserfs_write_lock_nested(s, depth);
-		// since we're using ll_rw_blk above, it might have skipped over
-		// a locked buffer.  Double check here
-		//
+		/*
+		 * since we're using ll_rw_blk above, it might have skipped
+		 * over a locked buffer.  Double check here
+		 */
 		/* redundant, sync_dirty_buffer() checks */
 		if (buffer_dirty(tbh)) {
 			depth = reiserfs_write_unlock_nested(s);
@@ -1079,17 +1090,21 @@ static int flush_commit_list(struct super_block *s,
 #endif
 			retval = -EIO;
 		}
-		put_bh(tbh);	/* once for journal_find_get_block */
-		put_bh(tbh);	/* once due to original getblk in do_journal_end */
-		atomic_dec(&(jl->j_commit_left));
+		/* once for journal_find_get_block */
+		put_bh(tbh);
+		/* once due to original getblk in do_journal_end */
+		put_bh(tbh);
+		atomic_dec(&jl->j_commit_left);
 	}
 
-	BUG_ON(atomic_read(&(jl->j_commit_left)) != 1);
+	BUG_ON(atomic_read(&jl->j_commit_left) != 1);
 
-	/* If there was a write error in the journal - we can't commit
+	/*
+	 * If there was a write error in the journal - we can't commit
 	 * this transaction - it will be invalid and, if successful,
 	 * will just end up propagating the write error out to
-	 * the file system. */
+	 * the file system.
+	 */
 	if (likely(!retval && !reiserfs_is_journal_aborted (journal))) {
 		if (buffer_dirty(jl->j_commit_bh))
 			BUG();
@@ -1102,9 +1117,11 @@ static int flush_commit_list(struct super_block *s,
 		reiserfs_write_lock_nested(s, depth);
 	}
 
-	/* If there was a write error in the journal - we can't commit this
+	/*
+	 * If there was a write error in the journal - we can't commit this
 	 * transaction - it will be invalid and, if successful, will just end
-	 * up propagating the write error out to the filesystem. */
+	 * up propagating the write error out to the filesystem.
+	 */
 	if (unlikely(!buffer_uptodate(jl->j_commit_bh))) {
 #ifdef CONFIG_REISERFS_CHECK
 		reiserfs_warning(s, "journal-615", "buffer write failed");
@@ -1119,7 +1136,10 @@ static int flush_commit_list(struct super_block *s,
 	}
 	journal->j_last_commit_id = jl->j_trans_id;
 
-	/* now, every commit block is on the disk.  It is safe to allow blocks freed during this transaction to be reallocated */
+	/*
+	 * now, every commit block is on the disk.  It is safe to allow
+	 * blocks freed during this transaction to be reallocated
+	 */
 	cleanup_freed_for_journal_list(s, jl);
 
 	retval = retval ? retval : journal->j_errno;
@@ -1127,13 +1147,13 @@ static int flush_commit_list(struct super_block *s,
 	/* mark the metadata dirty */
 	if (!retval)
 		dirty_one_transaction(s, jl);
-	atomic_dec(&(jl->j_commit_left));
+	atomic_dec(&jl->j_commit_left);
 
 	if (flushall) {
-		atomic_set(&(jl->j_older_commits_done), 1);
+		atomic_set(&jl->j_older_commits_done, 1);
 	}
 	mutex_unlock(&jl->j_commit_mutex);
-      put_jl:
+put_jl:
 	put_journal_list(s, jl);
 
 	if (retval)
@@ -1143,9 +1163,9 @@ static int flush_commit_list(struct super_block *s,
 }
 
 /*
-** flush_journal_list frequently needs to find a newer transaction for a given block.  This does that, or
-** returns NULL if it can't find anything
-*/
+ * flush_journal_list frequently needs to find a newer transaction for a
+ * given block.  This does that, or returns NULL if it can't find anything
+ */
 static struct reiserfs_journal_list *find_newer_jl_for_cn(struct
 							  reiserfs_journal_cnode
 							  *cn)
@@ -1169,10 +1189,11 @@ static void remove_journal_hash(struct super_block *,
 				int);
 
 /*
-** once all the real blocks have been flushed, it is safe to remove them from the
-** journal list for this transaction.  Aside from freeing the cnode, this also allows the
-** block to be reallocated for data blocks if it had been deleted.
-*/
+ * once all the real blocks have been flushed, it is safe to remove them
+ * from the journal list for this transaction.  Aside from freeing the
+ * cnode, this also allows the block to be reallocated for data blocks
+ * if it had been deleted.
+ */
 static void remove_all_from_journal_list(struct super_block *sb,
 					 struct reiserfs_journal_list *jl,
 					 int debug)
@@ -1181,8 +1202,9 @@ static void remove_all_from_journal_list(struct super_block *sb,
 	struct reiserfs_journal_cnode *cn, *last;
 	cn = jl->j_realblock;
 
-	/* which is better, to lock once around the whole loop, or
-	 ** to lock for each call to remove_journal_hash?
+	/*
+	 * which is better, to lock once around the whole loop, or
+	 * to lock for each call to remove_journal_hash?
 	 */
 	while (cn) {
 		if (cn->blocknr != 0) {
@@ -1204,12 +1226,13 @@ static void remove_all_from_journal_list(struct super_block *sb,
 }
 
 /*
-** if this timestamp is greater than the timestamp we wrote last to the header block, write it to the header block.
-** once this is done, I can safely say the log area for this transaction won't ever be replayed, and I can start
-** releasing blocks in this transaction for reuse as data blocks.
-** called by flush_journal_list, before it calls remove_all_from_journal_list
-**
-*/
+ * if this timestamp is greater than the timestamp we wrote last to the
+ * header block, write it to the header block.  once this is done, I can
+ * safely say the log area for this transaction won't ever be replayed,
+ * and I can start releasing blocks in this transaction for reuse as data
+ * blocks.  called by flush_journal_list, before it calls
+ * remove_all_from_journal_list
+ */
 static int _update_journal_header_block(struct super_block *sb,
 					unsigned long offset,
 					unsigned int trans_id)
@@ -1279,10 +1302,11 @@ static int flush_older_journal_lists(struct super_block *sb,
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
 	unsigned int trans_id = jl->j_trans_id;
 
-	/* we know we are the only ones flushing things, no extra race
+	/*
+	 * we know we are the only ones flushing things, no extra race
 	 * protection is required.
 	 */
-      restart:
+restart:
 	entry = journal->j_journal_list.next;
 	/* Did we wrap? */
 	if (entry == &journal->j_journal_list)
@@ -1309,15 +1333,16 @@ static void del_from_work_list(struct super_block *s,
 	}
 }
 
-/* flush a journal list, both commit and real blocks
-**
-** always set flushall to 1, unless you are calling from inside
-** flush_journal_list
-**
-** IMPORTANT.  This can only be called while there are no journal writers,
-** and the journal is locked.  That means it can only be called from
-** do_journal_end, or by journal_release
-*/
+/*
+ * flush a journal list, both commit and real blocks
+ *
+ * always set flushall to 1, unless you are calling from inside
+ * flush_journal_list
+ *
+ * IMPORTANT.  This can only be called while there are no journal writers,
+ * and the journal is locked.  That means it can only be called from
+ * do_journal_end, or by journal_release
+ */
 static int flush_journal_list(struct super_block *s,
 			      struct reiserfs_journal_list *jl, int flushall)
 {
@@ -1354,13 +1379,14 @@ static int flush_journal_list(struct super_block *s,
 	}
 
 	/* if all the work is already done, get out of here */
-	if (atomic_read(&(jl->j_nonzerolen)) <= 0 &&
-	    atomic_read(&(jl->j_commit_left)) <= 0) {
+	if (atomic_read(&jl->j_nonzerolen) <= 0 &&
+	    atomic_read(&jl->j_commit_left) <= 0) {
 		goto flush_older_and_return;
 	}
 
-	/* start by putting the commit list on disk.  This will also flush
-	 ** the commit lists of any olders transactions
+	/*
+	 * start by putting the commit list on disk.  This will also flush
+	 * the commit lists of any olders transactions
 	 */
 	flush_commit_list(s, jl, 1);
 
@@ -1369,15 +1395,16 @@ static int flush_journal_list(struct super_block *s,
 		BUG();
 
 	/* are we done now? */
-	if (atomic_read(&(jl->j_nonzerolen)) <= 0 &&
-	    atomic_read(&(jl->j_commit_left)) <= 0) {
+	if (atomic_read(&jl->j_nonzerolen) <= 0 &&
+	    atomic_read(&jl->j_commit_left) <= 0) {
 		goto flush_older_and_return;
 	}
 
-	/* loop through each cnode, see if we need to write it,
-	 ** or wait on a more recent transaction, or just ignore it
+	/*
+	 * loop through each cnode, see if we need to write it,
+	 * or wait on a more recent transaction, or just ignore it
 	 */
-	if (atomic_read(&(journal->j_wcount)) != 0) {
+	if (atomic_read(&journal->j_wcount) != 0) {
 		reiserfs_panic(s, "journal-844", "journal list is flushing, "
 			       "wcount is not 0");
 	}
@@ -1391,20 +1418,25 @@ static int flush_journal_list(struct super_block *s,
 			goto free_cnode;
 		}
 
-		/* This transaction failed commit. Don't write out to the disk */
+		/*
+		 * This transaction failed commit.
+		 * Don't write out to the disk
+		 */
 		if (!(jl->j_state & LIST_DIRTY))
 			goto free_cnode;
 
 		pjl = find_newer_jl_for_cn(cn);
-		/* the order is important here.  We check pjl to make sure we
-		 ** don't clear BH_JDirty_wait if we aren't the one writing this
-		 ** block to disk
+		/*
+		 * the order is important here.  We check pjl to make sure we
+		 * don't clear BH_JDirty_wait if we aren't the one writing this
+		 * block to disk
 		 */
 		if (!pjl && cn->bh) {
 			saved_bh = cn->bh;
 
-			/* we do this to make sure nobody releases the buffer while
-			 ** we are working with it
+			/*
+			 * we do this to make sure nobody releases the
+			 * buffer while we are working with it
 			 */
 			get_bh(saved_bh);
 
@@ -1413,13 +1445,17 @@ static int flush_journal_list(struct super_block *s,
 				was_jwait = 1;
 				was_dirty = 1;
 			} else if (can_dirty(cn)) {
-				/* everything with !pjl && jwait should be writable */
+				/*
+				 * everything with !pjl && jwait
+				 * should be writable
+				 */
 				BUG();
 			}
 		}
 
-		/* if someone has this block in a newer transaction, just make
-		 ** sure they are committed, and don't try writing it to disk
+		/*
+		 * if someone has this block in a newer transaction, just make
+		 * sure they are committed, and don't try writing it to disk
 		 */
 		if (pjl) {
 			if (atomic_read(&pjl->j_commit_left))
@@ -1427,16 +1463,18 @@ static int flush_journal_list(struct super_block *s,
 			goto free_cnode;
 		}
 
-		/* bh == NULL when the block got to disk on its own, OR,
-		 ** the block got freed in a future transaction
+		/*
+		 * bh == NULL when the block got to disk on its own, OR,
+		 * the block got freed in a future transaction
 		 */
 		if (saved_bh == NULL) {
 			goto free_cnode;
 		}
 
-		/* this should never happen.  kupdate_one_transaction has this list
-		 ** locked while it works, so we should never see a buffer here that
-		 ** is not marked JDirty_wait
+		/*
+		 * this should never happen.  kupdate_one_transaction has
+		 * this list locked while it works, so we should never see a
+		 * buffer here that is not marked JDirty_wait
 		 */
 		if ((!was_jwait) && !buffer_locked(saved_bh)) {
 			reiserfs_warning(s, "journal-813",
@@ -1447,7 +1485,10 @@ static int flush_journal_list(struct super_block *s,
 					 was_jwait ? ' ' : '!');
 		}
 		if (was_dirty) {
-			/* we inc again because saved_bh gets decremented at free_cnode */
+			/*
+			 * we inc again because saved_bh gets decremented
+			 * at free_cnode
+			 */
 			get_bh(saved_bh);
 			set_bit(BLOCK_NEEDS_FLUSH, &cn->state);
 			lock_buffer(saved_bh);
@@ -1463,13 +1504,16 @@ static int flush_journal_list(struct super_block *s,
 					 (unsigned long long)saved_bh->
 					 b_blocknr, __func__);
 		}
-	      free_cnode:
+free_cnode:
 		last = cn;
 		cn = cn->next;
 		if (saved_bh) {
-			/* we incremented this to keep others from taking the buffer head away */
+			/*
+			 * we incremented this to keep others from
+			 * taking the buffer head away
+			 */
 			put_bh(saved_bh);
-			if (atomic_read(&(saved_bh->b_count)) < 0) {
+			if (atomic_read(&saved_bh->b_count) < 0) {
 				reiserfs_warning(s, "journal-945",
 						 "saved_bh->b_count < 0");
 			}
@@ -1499,8 +1543,10 @@ static int flush_journal_list(struct super_block *s,
 #endif
 					err = -EIO;
 				}
-				/* note, we must clear the JDirty_wait bit after the up to date
-				 ** check, otherwise we race against our flushpage routine
+				/*
+				 * note, we must clear the JDirty_wait bit
+				 * after the up to date check, otherwise we
+				 * race against our flushpage routine
 				 */
 				BUG_ON(!test_clear_buffer_journal_dirty
 				       (cn->bh));
@@ -1518,25 +1564,27 @@ static int flush_journal_list(struct super_block *s,
 		reiserfs_abort(s, -EIO,
 			       "Write error while pushing transaction to disk in %s",
 			       __func__);
-      flush_older_and_return:
+flush_older_and_return:
 
-	/* before we can update the journal header block, we _must_ flush all
-	 ** real blocks from all older transactions to disk.  This is because
-	 ** once the header block is updated, this transaction will not be
-	 ** replayed after a crash
+	/*
+	 * before we can update the journal header block, we _must_ flush all
+	 * real blocks from all older transactions to disk.  This is because
+	 * once the header block is updated, this transaction will not be
+	 * replayed after a crash
 	 */
 	if (flushall) {
 		flush_older_journal_lists(s, jl);
 	}
 
 	err = journal->j_errno;
-	/* before we can remove everything from the hash tables for this
-	 ** transaction, we must make sure it can never be replayed
-	 **
-	 ** since we are only called from do_journal_end, we know for sure there
-	 ** are no allocations going on while we are flushing journal lists.  So,
-	 ** we only need to update the journal header block for the last list
-	 ** being flushed
+	/*
+	 * before we can remove everything from the hash tables for this
+	 * transaction, we must make sure it can never be replayed
+	 *
+	 * since we are only called from do_journal_end, we know for sure there
+	 * are no allocations going on while we are flushing journal lists.  So,
+	 * we only need to update the journal header block for the last list
+	 * being flushed
 	 */
 	if (!err && flushall) {
 		err =
@@ -1561,11 +1609,12 @@ static int flush_journal_list(struct super_block *s,
 	}
 	journal->j_last_flush_id = jl->j_trans_id;
 
-	/* not strictly required since we are freeing the list, but it should
+	/*
+	 * not strictly required since we are freeing the list, but it should
 	 * help find code using dead lists later on
 	 */
 	jl->j_len = 0;
-	atomic_set(&(jl->j_nonzerolen), 0);
+	atomic_set(&jl->j_nonzerolen, 0);
 	jl->j_start = 0;
 	jl->j_realblock = NULL;
 	jl->j_commit_bh = NULL;
@@ -1592,15 +1641,17 @@ static int write_one_transaction(struct super_block *s,
 
 	cn = jl->j_realblock;
 	while (cn) {
-		/* if the blocknr == 0, this has been cleared from the hash,
-		 ** skip it
+		/*
+		 * if the blocknr == 0, this has been cleared from the hash,
+		 * skip it
 		 */
 		if (cn->blocknr == 0) {
 			goto next;
 		}
 		if (cn->bh && can_dirty(cn) && buffer_dirty(cn->bh)) {
 			struct buffer_head *tmp_bh;
-			/* we can race against journal_mark_freed when we try
+			/*
+			 * we can race against journal_mark_freed when we try
 			 * to lock_buffer(cn->bh), so we have to inc the buffer
 			 * count, and recheck things after locking
 			 */
@@ -1619,7 +1670,7 @@ static int write_one_transaction(struct super_block *s,
 			}
 			put_bh(tmp_bh);
 		}
-	      next:
+next:
 		cn = cn->next;
 		cond_resched();
 	}
@@ -1637,15 +1688,17 @@ static int dirty_one_transaction(struct super_block *s,
 	jl->j_state |= LIST_DIRTY;
 	cn = jl->j_realblock;
 	while (cn) {
-		/* look for a more recent transaction that logged this
-		 ** buffer.  Only the most recent transaction with a buffer in
-		 ** it is allowed to send that buffer to disk
+		/*
+		 * look for a more recent transaction that logged this
+		 * buffer.  Only the most recent transaction with a buffer in
+		 * it is allowed to send that buffer to disk
 		 */
 		pjl = find_newer_jl_for_cn(cn);
 		if (!pjl && cn->blocknr && cn->bh
 		    && buffer_journal_dirty(cn->bh)) {
 			BUG_ON(!can_dirty(cn));
-			/* if the buffer is prepared, it will either be logged
+			/*
+			 * if the buffer is prepared, it will either be logged
 			 * or restored.  If restored, we need to make sure
 			 * it actually gets marked dirty
 			 */
@@ -1682,7 +1735,8 @@ static int kupdate_transactions(struct super_block *s,
 		goto done;
 	}
 
-	/* we've got j_flush_mutex held, nobody is going to delete any
+	/*
+	 * we've got j_flush_mutex held, nobody is going to delete any
 	 * of these lists out from underneath us
 	 */
 	while ((num_trans && transactions_flushed < num_trans) ||
@@ -1716,20 +1770,21 @@ static int kupdate_transactions(struct super_block *s,
 		write_chunk(&chunk);
 	}
 
-      done:
+done:
 	mutex_unlock(&journal->j_flush_mutex);
 	return ret;
 }
 
-/* for o_sync and fsync heavy applications, they tend to use
-** all the journa list slots with tiny transactions.  These
-** trigger lots and lots of calls to update the header block, which
-** adds seeks and slows things down.
-**
-** This function tries to clear out a large chunk of the journal lists
-** at once, which makes everything faster since only the newest journal
-** list updates the header block
-*/
+/*
+ * for o_sync and fsync heavy applications, they tend to use
+ * all the journa list slots with tiny transactions.  These
+ * trigger lots and lots of calls to update the header block, which
+ * adds seeks and slows things down.
+ *
+ * This function tries to clear out a large chunk of the journal lists
+ * at once, which makes everything faster since only the newest journal
+ * list updates the header block
+ */
 static int flush_used_journal_lists(struct super_block *s,
 				    struct reiserfs_journal_list *jl)
 {
@@ -1766,9 +1821,11 @@ static int flush_used_journal_lists(struct super_block *s,
 	}
 	get_journal_list(jl);
 	get_journal_list(flush_jl);
-	/* try to find a group of blocks we can flush across all the
-	 ** transactions, but only bother if we've actually spanned
-	 ** across multiple lists
+
+	/*
+	 * try to find a group of blocks we can flush across all the
+	 * transactions, but only bother if we've actually spanned
+	 * across multiple lists
 	 */
 	if (flush_jl != jl) {
 		ret = kupdate_transactions(s, jl, &tjl, &trans_id, len, i);
@@ -1780,9 +1837,9 @@ static int flush_used_journal_lists(struct super_block *s,
 }
 
 /*
-** removes any nodes in table with name block and dev as bh.
-** only touchs the hnext and hprev pointers.
-*/
+ * removes any nodes in table with name block and dev as bh.
+ * only touchs the hnext and hprev pointers.
+ */
 void remove_journal_hash(struct super_block *sb,
 			 struct reiserfs_journal_cnode **table,
 			 struct reiserfs_journal_list *jl,
@@ -1811,8 +1868,12 @@ void remove_journal_hash(struct super_block *sb,
 			cur->blocknr = 0;
 			cur->sb = NULL;
 			cur->state = 0;
-			if (cur->bh && cur->jlist)	/* anybody who clears the cur->bh will also dec the nonzerolen */
-				atomic_dec(&(cur->jlist->j_nonzerolen));
+			/*
+			 * anybody who clears the cur->bh will also
+			 * dec the nonzerolen
+			 */
+			if (cur->bh && cur->jlist)
+				atomic_dec(&cur->jlist->j_nonzerolen);
 			cur->bh = NULL;
 			cur->jlist = NULL;
 		}
@@ -1832,17 +1893,18 @@ static void free_journal_ram(struct super_block *sb)
 	if (journal->j_header_bh) {
 		brelse(journal->j_header_bh);
 	}
-	/* j_header_bh is on the journal dev, make sure not to release the journal
-	 * dev until we brelse j_header_bh
+	/*
+	 * j_header_bh is on the journal dev, make sure
+	 * not to release the journal dev until we brelse j_header_bh
 	 */
 	release_journal_dev(sb, journal);
 	vfree(journal);
 }
 
 /*
-** call on unmount.  Only set error to 1 if you haven't made your way out
-** of read_super() yet.  Any other caller must keep error at 0.
-*/
+ * call on unmount.  Only set error to 1 if you haven't made your way out
+ * of read_super() yet.  Any other caller must keep error at 0.
+ */
 static int do_journal_release(struct reiserfs_transaction_handle *th,
 			      struct super_block *sb, int error)
 {
@@ -1850,21 +1912,25 @@ static int do_journal_release(struct reiserfs_transaction_handle *th,
 	int flushed = 0;
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
 
-	/* we only want to flush out transactions if we were called with error == 0
+	/*
+	 * we only want to flush out transactions if we were
+	 * called with error == 0
 	 */
 	if (!error && !(sb->s_flags & MS_RDONLY)) {
 		/* end the current trans */
 		BUG_ON(!th->t_trans_id);
-		do_journal_end(th, sb, 10, FLUSH_ALL);
+		do_journal_end(th, FLUSH_ALL);
 
-		/* make sure something gets logged to force our way into the flush code */
-		if (!journal_join(&myth, sb, 1)) {
+		/*
+		 * make sure something gets logged to force
+		 * our way into the flush code
+		 */
+		if (!journal_join(&myth, sb)) {
 			reiserfs_prepare_for_journal(sb,
 						     SB_BUFFER_WITH_SB(sb),
 						     1);
-			journal_mark_dirty(&myth, sb,
-					   SB_BUFFER_WITH_SB(sb));
-			do_journal_end(&myth, sb, 1, FLUSH_ALL);
+			journal_mark_dirty(&myth, SB_BUFFER_WITH_SB(sb));
+			do_journal_end(&myth, FLUSH_ALL);
 			flushed = 1;
 		}
 	}
@@ -1872,17 +1938,15 @@ static int do_journal_release(struct reiserfs_transaction_handle *th,
 	/* this also catches errors during the do_journal_end above */
 	if (!error && reiserfs_is_journal_aborted(journal)) {
 		memset(&myth, 0, sizeof(myth));
-		if (!journal_join_abort(&myth, sb, 1)) {
+		if (!journal_join_abort(&myth, sb)) {
 			reiserfs_prepare_for_journal(sb,
 						     SB_BUFFER_WITH_SB(sb),
 						     1);
-			journal_mark_dirty(&myth, sb,
-					   SB_BUFFER_WITH_SB(sb));
-			do_journal_end(&myth, sb, 1, FLUSH_ALL);
+			journal_mark_dirty(&myth, SB_BUFFER_WITH_SB(sb));
+			do_journal_end(&myth, FLUSH_ALL);
 		}
 	}
 
-	reiserfs_mounted_fs_count--;
 	/* wait for all commits to finish */
 	cancel_delayed_work(&SB_JOURNAL(sb)->j_work);
 
@@ -1893,12 +1957,7 @@ static int do_journal_release(struct reiserfs_transaction_handle *th,
 	reiserfs_write_unlock(sb);
 
 	cancel_delayed_work_sync(&REISERFS_SB(sb)->old_work);
-	flush_workqueue(commit_wq);
-
-	if (!reiserfs_mounted_fs_count) {
-		destroy_workqueue(commit_wq);
-		commit_wq = NULL;
-	}
+	flush_workqueue(REISERFS_SB(sb)->commit_wq);
 
 	free_journal_ram(sb);
 
@@ -1907,25 +1966,24 @@ static int do_journal_release(struct reiserfs_transaction_handle *th,
 	return 0;
 }
 
-/*
-** call on unmount.  flush all journal trans, release all alloc'd ram
-*/
+/* * call on unmount.  flush all journal trans, release all alloc'd ram */
 int journal_release(struct reiserfs_transaction_handle *th,
 		    struct super_block *sb)
 {
 	return do_journal_release(th, sb, 0);
 }
 
-/*
-** only call from an error condition inside reiserfs_read_super!
-*/
+/* only call from an error condition inside reiserfs_read_super!  */
 int journal_release_error(struct reiserfs_transaction_handle *th,
 			  struct super_block *sb)
 {
 	return do_journal_release(th, sb, 1);
 }
 
-/* compares description block with commit block.  returns 1 if they differ, 0 if they are the same */
+/*
+ * compares description block with commit block.
+ * returns 1 if they differ, 0 if they are the same
+ */
 static int journal_compare_desc_commit(struct super_block *sb,
 				       struct reiserfs_journal_desc *desc,
 				       struct reiserfs_journal_commit *commit)
@@ -1939,11 +1997,12 @@ static int journal_compare_desc_commit(struct super_block *sb,
 	return 0;
 }
 
-/* returns 0 if it did not find a description block
-** returns -1 if it found a corrupt commit block
-** returns 1 if both desc and commit were valid
-** NOTE: only called during fs mount
-*/
+/*
+ * returns 0 if it did not find a description block
+ * returns -1 if it found a corrupt commit block
+ * returns 1 if both desc and commit were valid
+ * NOTE: only called during fs mount
+ */
 static int journal_transaction_is_valid(struct super_block *sb,
 					struct buffer_head *d_bh,
 					unsigned int *oldest_invalid_trans_id,
@@ -1989,7 +2048,10 @@ static int journal_transaction_is_valid(struct super_block *sb,
 		}
 		offset = d_bh->b_blocknr - SB_ONDISK_JOURNAL_1st_BLOCK(sb);
 
-		/* ok, we have a journal description block, lets see if the transaction was valid */
+		/*
+		 * ok, we have a journal description block,
+		 * let's see if the transaction was valid
+		 */
 		c_bh =
 		    journal_bread(sb,
 				  SB_ONDISK_JOURNAL_1st_BLOCK(sb) +
@@ -2041,11 +2103,11 @@ static void brelse_array(struct buffer_head **heads, int num)
 }
 
 /*
-** given the start, and values for the oldest acceptable transactions,
-** this either reads in a replays a transaction, or returns because the
-** transaction is invalid, or too old.
-** NOTE: only called during fs mount
-*/
+ * given the start, and values for the oldest acceptable transactions,
+ * this either reads in a replays a transaction, or returns because the
+ * transaction is invalid, or too old.
+ * NOTE: only called during fs mount
+ */
 static int journal_read_transaction(struct super_block *sb,
 				    unsigned long cur_dblock,
 				    unsigned long oldest_start,
@@ -2119,7 +2181,10 @@ static int journal_read_transaction(struct super_block *sb,
 	}
 
 	trans_id = get_desc_trans_id(desc);
-	/* now we know we've got a good transaction, and it was inside the valid time ranges */
+	/*
+	 * now we know we've got a good transaction, and it was
+	 * inside the valid time ranges
+	 */
 	log_blocks = kmalloc(get_desc_trans_len(desc) *
 			     sizeof(struct buffer_head *), GFP_NOFS);
 	real_blocks = kmalloc(get_desc_trans_len(desc) *
@@ -2164,7 +2229,7 @@ static int journal_read_transaction(struct super_block *sb,
 			reiserfs_warning(sb, "journal-1204",
 					 "REPLAY FAILURE fsck required! "
 					 "Trying to replay onto a log block");
-		      abort_replay:
+abort_replay:
 			brelse_array(log_blocks, i);
 			brelse_array(real_blocks, i);
 			brelse(c_bh);
@@ -2226,7 +2291,10 @@ static int journal_read_transaction(struct super_block *sb,
 		       "journal-1095: setting journal " "start to offset %ld",
 		       cur_dblock - SB_ONDISK_JOURNAL_1st_BLOCK(sb));
 
-	/* init starting values for the first transaction, in case this is the last transaction to be replayed. */
+	/*
+	 * init starting values for the first transaction, in case
+	 * this is the last transaction to be replayed.
+	 */
 	journal->j_start = cur_dblock - SB_ONDISK_JOURNAL_1st_BLOCK(sb);
 	journal->j_last_flush_trans_id = trans_id;
 	journal->j_trans_id = trans_id + 1;
@@ -2240,12 +2308,14 @@ static int journal_read_transaction(struct super_block *sb,
 	return 0;
 }
 
-/* This function reads blocks starting from block and to max_block of bufsize
-   size (but no more than BUFNR blocks at a time). This proved to improve
-   mounting speed on self-rebuilding raid5 arrays at least.
-   Right now it is only used from journal code. But later we might use it
-   from other places.
-   Note: Do not use journal_getblk/sb_getblk functions here! */
+/*
+ * This function reads blocks starting from block and to max_block of bufsize
+ * size (but no more than BUFNR blocks at a time). This proved to improve
+ * mounting speed on self-rebuilding raid5 arrays at least.
+ * Right now it is only used from journal code. But later we might use it
+ * from other places.
+ * Note: Do not use journal_getblk/sb_getblk functions here!
+ */
 static struct buffer_head *reiserfs_breada(struct block_device *dev,
 					   b_blocknr_t block, int bufsize,
 					   b_blocknr_t max_block)
@@ -2284,15 +2354,17 @@ static struct buffer_head *reiserfs_breada(struct block_device *dev,
 }
 
 /*
-** read and replay the log
-** on a clean unmount, the journal header's next unflushed pointer will
-** be to an invalid transaction.  This tests that before finding all the
-** transactions in the log, which makes normal mount times fast.
-** After a crash, this starts with the next unflushed transaction, and
-** replays until it finds one too old, or invalid.
-** On exit, it sets things up so the first transaction will work correctly.
-** NOTE: only called during fs mount
-*/
+ * read and replay the log
+ * on a clean unmount, the journal header's next unflushed pointer will be
+ * to an invalid transaction.  This tests that before finding all the
+ * transactions in the log, which makes normal mount times fast.
+ *
+ * After a crash, this starts with the next unflushed transaction, and
+ * replays until it finds one too old, or invalid.
+ *
+ * On exit, it sets things up so the first transaction will work correctly.
+ * NOTE: only called during fs mount
+ */
 static int journal_read(struct super_block *sb)
 {
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
@@ -2316,9 +2388,10 @@ static int journal_read(struct super_block *sb)
 		      bdevname(journal->j_dev_bd, b));
 	start = get_seconds();
 
-	/* step 1, read in the journal header block.  Check the transaction it says
-	 ** is the first unflushed, and if that transaction is not valid,
-	 ** replay is done
+	/*
+	 * step 1, read in the journal header block.  Check the transaction
+	 * it says is the first unflushed, and if that transaction is not
+	 * valid, replay is done
 	 */
 	journal->j_header_bh = journal_bread(sb,
 					     SB_ONDISK_JOURNAL_1st_BLOCK(sb)
@@ -2342,9 +2415,10 @@ static int journal_read(struct super_block *sb)
 			       le32_to_cpu(jh->j_last_flush_trans_id));
 		valid_journal_header = 1;
 
-		/* now, we try to read the first unflushed offset.  If it is not valid,
-		 ** there is nothing more we can do, and it makes no sense to read
-		 ** through the whole log.
+		/*
+		 * now, we try to read the first unflushed offset.  If it
+		 * is not valid, there is nothing more we can do, and it
+		 * makes no sense to read through the whole log.
 		 */
 		d_bh =
 		    journal_bread(sb,
@@ -2358,15 +2432,19 @@ static int journal_read(struct super_block *sb)
 		goto start_log_replay;
 	}
 
-	/* ok, there are transactions that need to be replayed.  start with the first log block, find
-	 ** all the valid transactions, and pick out the oldest.
+	/*
+	 * ok, there are transactions that need to be replayed.  start
+	 * with the first log block, find all the valid transactions, and
+	 * pick out the oldest.
 	 */
 	while (continue_replay
 	       && cur_dblock <
 	       (SB_ONDISK_JOURNAL_1st_BLOCK(sb) +
 		SB_ONDISK_JOURNAL_SIZE(sb))) {
-		/* Note that it is required for blocksize of primary fs device and journal
-		   device to be the same */
+		/*
+		 * Note that it is required for blocksize of primary fs
+		 * device and journal device to be the same
+		 */
 		d_bh =
 		    reiserfs_breada(journal->j_dev_bd, cur_dblock,
 				    sb->s_blocksize,
@@ -2413,7 +2491,7 @@ static int journal_read(struct super_block *sb)
 		brelse(d_bh);
 	}
 
-      start_log_replay:
+start_log_replay:
 	cur_dblock = oldest_start;
 	if (oldest_trans_id) {
 		reiserfs_debug(sb, REISERFS_DEBUG_CODE,
@@ -2444,9 +2522,11 @@ static int journal_read(struct super_block *sb)
 		reiserfs_debug(sb, REISERFS_DEBUG_CODE,
 			       "journal-1225: No valid " "transactions found");
 	}
-	/* j_start does not get set correctly if we don't replay any transactions.
-	 ** if we had a valid journal_header, set j_start to the first unflushed transaction value,
-	 ** copy the trans_id from the header
+	/*
+	 * j_start does not get set correctly if we don't replay any
+	 * transactions.  if we had a valid journal_header, set j_start
+	 * to the first unflushed transaction value, copy the trans_id
+	 * from the header
 	 */
 	if (valid_journal_header && replay_count == 0) {
 		journal->j_start = le32_to_cpu(jh->j_first_unflushed_offset);
@@ -2475,8 +2555,9 @@ static int journal_read(struct super_block *sb)
 	    _update_journal_header_block(sb, journal->j_start,
 					 journal->j_last_flush_trans_id)) {
 		reiserfs_write_unlock(sb);
-		/* replay failed, caller must call free_journal_ram and abort
-		 ** the mount
+		/*
+		 * replay failed, caller must call free_journal_ram and abort
+		 * the mount
 		 */
 		return -1;
 	}
@@ -2569,7 +2650,7 @@ static int journal_init_dev(struct super_block *super,
 	return 0;
 }
 
-/**
+/*
  * When creating/tuning a file system user can assign some
  * journal params within boundaries which depend on the ratio
  * blocksize/standard_blocksize.
@@ -2587,8 +2668,7 @@ static int check_advise_trans_params(struct super_block *sb,
 				     struct reiserfs_journal *journal)
 {
         if (journal->j_trans_max) {
-	        /* Non-default journal params.
-		   Do sanity check for them. */
+		/* Non-default journal params.  Do sanity check for them. */
 	        int ratio = 1;
 		if (sb->s_blocksize < REISERFS_STANDARD_BLKSIZE)
 		        ratio = REISERFS_STANDARD_BLKSIZE / sb->s_blocksize;
@@ -2610,10 +2690,12 @@ static int check_advise_trans_params(struct super_block *sb,
 			return 1;
 		}
 	} else {
-		/* Default journal params.
-                   The file system was created by old version
-		   of mkreiserfs, so some fields contain zeros,
-		   and we need to advise proper values for them */
+		/*
+		 * Default journal params.
+		 * The file system was created by old version
+		 * of mkreiserfs, so some fields contain zeros,
+		 * and we need to advise proper values for them
+		 */
 		if (sb->s_blocksize != REISERFS_STANDARD_BLKSIZE) {
 			reiserfs_warning(sb, "sh-464", "bad blocksize (%u)",
 					 sb->s_blocksize);
@@ -2626,9 +2708,7 @@ static int check_advise_trans_params(struct super_block *sb,
 	return 0;
 }
 
-/*
-** must be called once on fs mount.  calls journal_read for you
-*/
+/* must be called once on fs mount.  calls journal_read for you */
 int journal_init(struct super_block *sb, const char *j_dev_name,
 		 int old_format, unsigned int commit_max_age)
 {
@@ -2667,8 +2747,10 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 						 REISERFS_DISK_OFFSET_IN_BYTES /
 						 sb->s_blocksize + 2);
 
-	/* Sanity check to see is the standard journal fitting within first bitmap
-	   (actual for small blocksizes) */
+	/*
+	 * Sanity check to see is the standard journal fitting
+	 * within first bitmap (actual for small blocksizes)
+	 */
 	if (!SB_ONDISK_JOURNAL_DEVICE(sb) &&
 	    (SB_JOURNAL_1st_RESERVED_BLOCK(sb) +
 	     SB_ONDISK_JOURNAL_SIZE(sb) > sb->s_blocksize * 8)) {
@@ -2754,20 +2836,20 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 	journal->j_start = 0;
 	journal->j_len = 0;
 	journal->j_len_alloc = 0;
-	atomic_set(&(journal->j_wcount), 0);
-	atomic_set(&(journal->j_async_throttle), 0);
+	atomic_set(&journal->j_wcount, 0);
+	atomic_set(&journal->j_async_throttle, 0);
 	journal->j_bcount = 0;
 	journal->j_trans_start_time = 0;
 	journal->j_last = NULL;
 	journal->j_first = NULL;
-	init_waitqueue_head(&(journal->j_join_wait));
+	init_waitqueue_head(&journal->j_join_wait);
 	mutex_init(&journal->j_mutex);
 	mutex_init(&journal->j_flush_mutex);
 
 	journal->j_trans_id = 10;
 	journal->j_mount_id = 10;
 	journal->j_state = 0;
-	atomic_set(&(journal->j_jlock), 0);
+	atomic_set(&journal->j_jlock, 0);
 	journal->j_cnode_free_list = allocate_cnodes(num_cnodes);
 	journal->j_cnode_free_orig = journal->j_cnode_free_list;
 	journal->j_cnode_free = journal->j_cnode_free_list ? num_cnodes : 0;
@@ -2807,23 +2889,19 @@ int journal_init(struct super_block *sb, const char *j_dev_name,
 		goto free_and_return;
 	}
 
-	reiserfs_mounted_fs_count++;
-	if (reiserfs_mounted_fs_count <= 1)
-		commit_wq = alloc_workqueue("reiserfs", WQ_MEM_RECLAIM, 0);
-
 	INIT_DELAYED_WORK(&journal->j_work, flush_async_commits);
 	journal->j_work_sb = sb;
 	return 0;
-      free_and_return:
+free_and_return:
 	free_journal_ram(sb);
 	return 1;
 }
 
 /*
-** test for a polite end of the current transaction.  Used by file_write, and should
-** be used by delete to make sure they don't write more than can fit inside a single
-** transaction
-*/
+ * test for a polite end of the current transaction.  Used by file_write,
+ * and should be used by delete to make sure they don't write more than
+ * can fit inside a single transaction
+ */
 int journal_transaction_should_end(struct reiserfs_transaction_handle *th,
 				   int new_alloc)
 {
@@ -2835,7 +2913,7 @@ int journal_transaction_should_end(struct reiserfs_transaction_handle *th,
 		return 0;
 	if (journal->j_must_wait > 0 ||
 	    (journal->j_len_alloc + new_alloc) >= journal->j_max_batch ||
-	    atomic_read(&(journal->j_jlock)) ||
+	    atomic_read(&journal->j_jlock) ||
 	    (now - journal->j_trans_start_time) > journal->j_max_trans_age ||
 	    journal->j_cnode_free < (journal->j_trans_max * 3)) {
 		return 1;
@@ -2846,8 +2924,7 @@ int journal_transaction_should_end(struct reiserfs_transaction_handle *th,
 	return 0;
 }
 
-/* this must be called inside a transaction
-*/
+/* this must be called inside a transaction */
 void reiserfs_block_writes(struct reiserfs_transaction_handle *th)
 {
 	struct reiserfs_journal *journal = SB_JOURNAL(th->t_super);
@@ -2857,8 +2934,7 @@ void reiserfs_block_writes(struct reiserfs_transaction_handle *th)
 	return;
 }
 
-/* this must be called without a transaction started
-*/
+/* this must be called without a transaction started */
 void reiserfs_allow_writes(struct super_block *s)
 {
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
@@ -2866,8 +2942,7 @@ void reiserfs_allow_writes(struct super_block *s)
 	wake_up(&journal->j_join_wait);
 }
 
-/* this must be called without a transaction started
-*/
+/* this must be called without a transaction started */
 void reiserfs_wait_on_write_block(struct super_block *s)
 {
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
@@ -2929,11 +3004,12 @@ static void let_transaction_grow(struct super_block *sb, unsigned int trans_id)
 	}
 }
 
-/* join == true if you must join an existing transaction.
-** join == false if you can deal with waiting for others to finish
-**
-** this will block until the transaction is joinable.  send the number of blocks you
-** expect to use in nblocks.
+/*
+ * join == true if you must join an existing transaction.
+ * join == false if you can deal with waiting for others to finish
+ *
+ * this will block until the transaction is joinable.  send the number of
+ * blocks you expect to use in nblocks.
 */
 static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
 			      struct super_block *sb, unsigned long nblocks,
@@ -2955,7 +3031,7 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
 	th->t_refcount = 1;
 	th->t_super = sb;
 
-      relock:
+relock:
 	lock_journal(sb);
 	if (join != JBEGIN_ABORT && reiserfs_is_journal_aborted(journal)) {
 		unlock_journal(sb);
@@ -2974,9 +3050,11 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
 	}
 	now = get_seconds();
 
-	/* if there is no room in the journal OR
-	 ** if this transaction is too old, and we weren't called joinable, wait for it to finish before beginning
-	 ** we don't sleep if there aren't other writers
+	/*
+	 * if there is no room in the journal OR
+	 * if this transaction is too old, and we weren't called joinable,
+	 * wait for it to finish before beginning we don't sleep if there
+	 * aren't other writers
 	 */
 
 	if ((!join && journal->j_must_wait > 0) ||
@@ -2990,7 +3068,8 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
 	    || (!join && journal->j_cnode_free < (journal->j_trans_max * 3))) {
 
 		old_trans_id = journal->j_trans_id;
-		unlock_journal(sb);	/* allow others to finish this transaction */
+		/* allow others to finish this transaction */
+		unlock_journal(sb);
 
 		if (!join && (journal->j_len_alloc + nblocks + 2) >=
 		    journal->j_max_batch &&
@@ -3002,8 +3081,9 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
 				goto relock;
 			}
 		}
-		/* don't mess with joining the transaction if all we have to do is
-		 * wait for someone else to do a commit
+		/*
+		 * don't mess with joining the transaction if all we
+		 * have to do is wait for someone else to do a commit
 		 */
 		if (atomic_read(&journal->j_jlock)) {
 			while (journal->j_trans_id == old_trans_id &&
@@ -3012,15 +3092,15 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
 			}
 			goto relock;
 		}
-		retval = journal_join(&myth, sb, 1);
+		retval = journal_join(&myth, sb);
 		if (retval)
 			goto out_fail;
 
 		/* someone might have ended the transaction while we joined */
 		if (old_trans_id != journal->j_trans_id) {
-			retval = do_journal_end(&myth, sb, 1, 0);
+			retval = do_journal_end(&myth, 0);
 		} else {
-			retval = do_journal_end(&myth, sb, 1, COMMIT_NOW);
+			retval = do_journal_end(&myth, COMMIT_NOW);
 		}
 
 		if (retval)
@@ -3033,7 +3113,7 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
 	if (journal->j_trans_start_time == 0) {
 		journal->j_trans_start_time = get_seconds();
 	}
-	atomic_inc(&(journal->j_wcount));
+	atomic_inc(&journal->j_wcount);
 	journal->j_len_alloc += nblocks;
 	th->t_blocks_logged = 0;
 	th->t_blocks_allocated = nblocks;
@@ -3042,11 +3122,13 @@ static int do_journal_begin_r(struct reiserfs_transaction_handle *th,
 	INIT_LIST_HEAD(&th->t_list);
 	return 0;
 
-      out_fail:
+out_fail:
 	memset(th, 0, sizeof(*th));
-	/* Re-set th->t_super, so we can properly keep track of how many
+	/*
+	 * Re-set th->t_super, so we can properly keep track of how many
 	 * persistent transactions there are. We need to do this so if this
-	 * call is part of a failed restart_transaction, we can free it later */
+	 * call is part of a failed restart_transaction, we can free it later
+	 */
 	th->t_super = sb;
 	return retval;
 }
@@ -3059,14 +3141,15 @@ struct reiserfs_transaction_handle *reiserfs_persistent_transaction(struct
 	int ret;
 	struct reiserfs_transaction_handle *th;
 
-	/* if we're nesting into an existing transaction.  It will be
-	 ** persistent on its own
+	/*
+	 * if we're nesting into an existing transaction.  It will be
+	 * persistent on its own
 	 */
 	if (reiserfs_transaction_running(s)) {
 		th = current->journal_info;
 		th->t_refcount++;
 		BUG_ON(th->t_refcount < 2);
-		
+
 		return th;
 	}
 	th = kmalloc(sizeof(struct reiserfs_transaction_handle), GFP_NOFS);
@@ -3087,7 +3170,7 @@ int reiserfs_end_persistent_transaction(struct reiserfs_transaction_handle *th)
 	struct super_block *s = th->t_super;
 	int ret = 0;
 	if (th->t_trans_id)
-		ret = journal_end(th, th->t_super, th->t_blocks_allocated);
+		ret = journal_end(th);
 	else
 		ret = -EIO;
 	if (th->t_refcount == 0) {
@@ -3098,29 +3181,31 @@ int reiserfs_end_persistent_transaction(struct reiserfs_transaction_handle *th)
 }
 
 static int journal_join(struct reiserfs_transaction_handle *th,
-			struct super_block *sb, unsigned long nblocks)
+			struct super_block *sb)
 {
 	struct reiserfs_transaction_handle *cur_th = current->journal_info;
 
-	/* this keeps do_journal_end from NULLing out the current->journal_info
-	 ** pointer
+	/*
+	 * this keeps do_journal_end from NULLing out the
+	 * current->journal_info pointer
 	 */
 	th->t_handle_save = cur_th;
 	BUG_ON(cur_th && cur_th->t_refcount > 1);
-	return do_journal_begin_r(th, sb, nblocks, JBEGIN_JOIN);
+	return do_journal_begin_r(th, sb, 1, JBEGIN_JOIN);
 }
 
 int journal_join_abort(struct reiserfs_transaction_handle *th,
-		       struct super_block *sb, unsigned long nblocks)
+		       struct super_block *sb)
 {
 	struct reiserfs_transaction_handle *cur_th = current->journal_info;
 
-	/* this keeps do_journal_end from NULLing out the current->journal_info
-	 ** pointer
+	/*
+	 * this keeps do_journal_end from NULLing out the
+	 * current->journal_info pointer
 	 */
 	th->t_handle_save = cur_th;
 	BUG_ON(cur_th && cur_th->t_refcount > 1);
-	return do_journal_begin_r(th, sb, nblocks, JBEGIN_ABORT);
+	return do_journal_begin_r(th, sb, 1, JBEGIN_ABORT);
 }
 
 int journal_begin(struct reiserfs_transaction_handle *th,
@@ -3142,9 +3227,10 @@ int journal_begin(struct reiserfs_transaction_handle *th,
 						 "journal_info != 0");
 			return 0;
 		} else {
-			/* we've ended up with a handle from a different filesystem.
-			 ** save it and restore on journal_end.  This should never
-			 ** really happen...
+			/*
+			 * we've ended up with a handle from a different
+			 * filesystem.  save it and restore on journal_end.
+			 * This should never really happen...
 			 */
 			reiserfs_warning(sb, "clm-2100",
 					 "nesting info a different FS");
@@ -3157,9 +3243,10 @@ int journal_begin(struct reiserfs_transaction_handle *th,
 	ret = do_journal_begin_r(th, sb, nblocks, JBEGIN_REG);
 	BUG_ON(current->journal_info != th);
 
-	/* I guess this boils down to being the reciprocal of clm-2100 above.
-	 * If do_journal_begin_r fails, we need to put it back, since journal_end
-	 * won't be called to do it. */
+	/*
+	 * I guess this boils down to being the reciprocal of clm-2100 above.
+	 * If do_journal_begin_r fails, we need to put it back, since
+	 * journal_end won't be called to do it. */
 	if (ret)
 		current->journal_info = th->t_handle_save;
 	else
@@ -3169,17 +3256,19 @@ int journal_begin(struct reiserfs_transaction_handle *th,
 }
 
 /*
-** puts bh into the current transaction.  If it was already there, reorders removes the
-** old pointers from the hash, and puts new ones in (to make sure replay happen in the right order).
-**
-** if it was dirty, cleans and files onto the clean list.  I can't let it be dirty again until the
-** transaction is committed.
-**
-** if j_len, is bigger than j_len_alloc, it pushes j_len_alloc to 10 + j_len.
-*/
+ * puts bh into the current transaction.  If it was already there, reorders
+ * removes the old pointers from the hash, and puts new ones in (to make
+ * sure replay happen in the right order).
+ *
+ * if it was dirty, cleans and files onto the clean list.  I can't let it
+ * be dirty again until the transaction is committed.
+ *
+ * if j_len, is bigger than j_len_alloc, it pushes j_len_alloc to 10 + j_len.
+ */
 int journal_mark_dirty(struct reiserfs_transaction_handle *th,
-		       struct super_block *sb, struct buffer_head *bh)
+		       struct buffer_head *bh)
 {
+	struct super_block *sb = th->t_super;
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
 	struct reiserfs_journal_cnode *cn = NULL;
 	int count_already_incd = 0;
@@ -3201,9 +3290,10 @@ int journal_mark_dirty(struct reiserfs_transaction_handle *th,
 		return 0;
 	}
 
-	/* this must be turned into a panic instead of a warning.  We can't allow
-	 ** a dirty or journal_dirty or locked buffer to be logged, as some changes
-	 ** could get to disk too early.  NOT GOOD.
+	/*
+	 * this must be turned into a panic instead of a warning.  We can't
+	 * allow a dirty or journal_dirty or locked buffer to be logged, as
+	 * some changes could get to disk too early.  NOT GOOD.
 	 */
 	if (!prepared || buffer_dirty(bh)) {
 		reiserfs_warning(sb, "journal-1777",
@@ -3216,14 +3306,16 @@ int journal_mark_dirty(struct reiserfs_transaction_handle *th,
 				 buffer_journal_dirty(bh) ? ' ' : '!');
 	}
 
-	if (atomic_read(&(journal->j_wcount)) <= 0) {
+	if (atomic_read(&journal->j_wcount) <= 0) {
 		reiserfs_warning(sb, "journal-1409",
 				 "returning because j_wcount was %d",
-				 atomic_read(&(journal->j_wcount)));
+				 atomic_read(&journal->j_wcount));
 		return 1;
 	}
-	/* this error means I've screwed up, and we've overflowed the transaction.
-	 ** Nothing can be done here, except make the FS readonly or panic.
+	/*
+	 * this error means I've screwed up, and we've overflowed
+	 * the transaction.  Nothing can be done here, except make the
+	 * FS readonly or panic.
 	 */
 	if (journal->j_len >= journal->j_trans_max) {
 		reiserfs_panic(th->t_super, "journal-1413",
@@ -3280,9 +3372,9 @@ int journal_mark_dirty(struct reiserfs_transaction_handle *th,
 	return 0;
 }
 
-int journal_end(struct reiserfs_transaction_handle *th,
-		struct super_block *sb, unsigned long nblocks)
+int journal_end(struct reiserfs_transaction_handle *th)
 {
+	struct super_block *sb = th->t_super;
 	if (!current->journal_info && th->t_refcount > 1)
 		reiserfs_warning(sb, "REISER-NESTING",
 				 "th NULL, refcount %d", th->t_refcount);
@@ -3297,8 +3389,9 @@ int journal_end(struct reiserfs_transaction_handle *th,
 		struct reiserfs_transaction_handle *cur_th =
 		    current->journal_info;
 
-		/* we aren't allowed to close a nested transaction on a different
-		 ** filesystem from the one in the task struct
+		/*
+		 * we aren't allowed to close a nested transaction on a
+		 * different filesystem from the one in the task struct
 		 */
 		BUG_ON(cur_th->t_super != th->t_super);
 
@@ -3308,17 +3401,18 @@ int journal_end(struct reiserfs_transaction_handle *th,
 		}
 		return 0;
 	} else {
-		return do_journal_end(th, sb, nblocks, 0);
+		return do_journal_end(th, 0);
 	}
 }
 
-/* removes from the current transaction, relsing and descrementing any counters.
-** also files the removed buffer directly onto the clean list
-**
-** called by journal_mark_freed when a block has been deleted
-**
-** returns 1 if it cleaned and relsed the buffer. 0 otherwise
-*/
+/*
+ * removes from the current transaction, relsing and descrementing any counters.
+ * also files the removed buffer directly onto the clean list
+ *
+ * called by journal_mark_freed when a block has been deleted
+ *
+ * returns 1 if it cleaned and relsed the buffer. 0 otherwise
+ */
 static int remove_from_transaction(struct super_block *sb,
 				   b_blocknr_t blocknr, int already_cleaned)
 {
@@ -3354,7 +3448,7 @@ static int remove_from_transaction(struct super_block *sb,
 		clear_buffer_dirty(bh);
 		clear_buffer_journal_test(bh);
 		put_bh(bh);
-		if (atomic_read(&(bh->b_count)) < 0) {
+		if (atomic_read(&bh->b_count) < 0) {
 			reiserfs_warning(sb, "journal-1752",
 					 "b_count < 0");
 		}
@@ -3367,15 +3461,16 @@ static int remove_from_transaction(struct super_block *sb,
 }
 
 /*
-** for any cnode in a journal list, it can only be dirtied of all the
-** transactions that include it are committed to disk.
-** this checks through each transaction, and returns 1 if you are allowed to dirty,
-** and 0 if you aren't
-**
-** it is called by dirty_journal_list, which is called after flush_commit_list has gotten all the log
-** blocks for a given transaction on disk
-**
-*/
+ * for any cnode in a journal list, it can only be dirtied of all the
+ * transactions that include it are committed to disk.
+ * this checks through each transaction, and returns 1 if you are allowed
+ * to dirty, and 0 if you aren't
+ *
+ * it is called by dirty_journal_list, which is called after
+ * flush_commit_list has gotten all the log blocks for a given
+ * transaction on disk
+ *
+ */
 static int can_dirty(struct reiserfs_journal_cnode *cn)
 {
 	struct super_block *sb = cn->sb;
@@ -3383,9 +3478,10 @@ static int can_dirty(struct reiserfs_journal_cnode *cn)
 	struct reiserfs_journal_cnode *cur = cn->hprev;
 	int can_dirty = 1;
 
-	/* first test hprev.  These are all newer than cn, so any node here
-	 ** with the same block number and dev means this node can't be sent
-	 ** to disk right now.
+	/*
+	 * first test hprev.  These are all newer than cn, so any node here
+	 * with the same block number and dev means this node can't be sent
+	 * to disk right now.
 	 */
 	while (cur && can_dirty) {
 		if (cur->jlist && cur->bh && cur->blocknr && cur->sb == sb &&
@@ -3394,13 +3490,14 @@ static int can_dirty(struct reiserfs_journal_cnode *cn)
 		}
 		cur = cur->hprev;
 	}
-	/* then test hnext.  These are all older than cn.  As long as they
-	 ** are committed to the log, it is safe to write cn to disk
+	/*
+	 * then test hnext.  These are all older than cn.  As long as they
+	 * are committed to the log, it is safe to write cn to disk
 	 */
 	cur = cn->hnext;
 	while (cur && can_dirty) {
 		if (cur->jlist && cur->jlist->j_len > 0 &&
-		    atomic_read(&(cur->jlist->j_commit_left)) > 0 && cur->bh &&
+		    atomic_read(&cur->jlist->j_commit_left) > 0 && cur->bh &&
 		    cur->blocknr && cur->sb == sb && cur->blocknr == blocknr) {
 			can_dirty = 0;
 		}
@@ -3409,12 +3506,13 @@ static int can_dirty(struct reiserfs_journal_cnode *cn)
 	return can_dirty;
 }
 
-/* syncs the commit blocks, but does not force the real buffers to disk
-** will wait until the current transaction is done/committed before returning
-*/
-int journal_end_sync(struct reiserfs_transaction_handle *th,
-		     struct super_block *sb, unsigned long nblocks)
+/*
+ * syncs the commit blocks, but does not force the real buffers to disk
+ * will wait until the current transaction is done/committed before returning
+ */
+int journal_end_sync(struct reiserfs_transaction_handle *th)
 {
+	struct super_block *sb = th->t_super;
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
 
 	BUG_ON(!th->t_trans_id);
@@ -3423,14 +3521,12 @@ int journal_end_sync(struct reiserfs_transaction_handle *th,
 	if (journal->j_len == 0) {
 		reiserfs_prepare_for_journal(sb, SB_BUFFER_WITH_SB(sb),
 					     1);
-		journal_mark_dirty(th, sb, SB_BUFFER_WITH_SB(sb));
+		journal_mark_dirty(th, SB_BUFFER_WITH_SB(sb));
 	}
-	return do_journal_end(th, sb, nblocks, COMMIT_NOW | WAIT);
+	return do_journal_end(th, COMMIT_NOW | WAIT);
 }
 
-/*
-** writeback the pending async commits to disk
-*/
+/* writeback the pending async commits to disk */
 static void flush_async_commits(struct work_struct *work)
 {
 	struct reiserfs_journal *journal =
@@ -3450,9 +3546,9 @@ static void flush_async_commits(struct work_struct *work)
 }
 
 /*
-** flushes any old transactions to disk
-** ends the current transaction if it is too old
-*/
+ * flushes any old transactions to disk
+ * ends the current transaction if it is too old
+ */
 void reiserfs_flush_old_commits(struct super_block *sb)
 {
 	time_t now;
@@ -3460,48 +3556,53 @@ void reiserfs_flush_old_commits(struct super_block *sb)
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
 
 	now = get_seconds();
-	/* safety check so we don't flush while we are replaying the log during
+	/*
+	 * safety check so we don't flush while we are replaying the log during
 	 * mount
 	 */
 	if (list_empty(&journal->j_journal_list))
 		return;
 
-	/* check the current transaction.  If there are no writers, and it is
+	/*
+	 * check the current transaction.  If there are no writers, and it is
 	 * too old, finish it, and force the commit blocks to disk
 	 */
 	if (atomic_read(&journal->j_wcount) <= 0 &&
 	    journal->j_trans_start_time > 0 &&
 	    journal->j_len > 0 &&
 	    (now - journal->j_trans_start_time) > journal->j_max_trans_age) {
-		if (!journal_join(&th, sb, 1)) {
+		if (!journal_join(&th, sb)) {
 			reiserfs_prepare_for_journal(sb,
 						     SB_BUFFER_WITH_SB(sb),
 						     1);
-			journal_mark_dirty(&th, sb,
-					   SB_BUFFER_WITH_SB(sb));
+			journal_mark_dirty(&th, SB_BUFFER_WITH_SB(sb));
 
-			/* we're only being called from kreiserfsd, it makes no sense to do
-			 ** an async commit so that kreiserfsd can do it later
+			/*
+			 * we're only being called from kreiserfsd, it makes
+			 * no sense to do an async commit so that kreiserfsd
+			 * can do it later
 			 */
-			do_journal_end(&th, sb, 1, COMMIT_NOW | WAIT);
+			do_journal_end(&th, COMMIT_NOW | WAIT);
 		}
 	}
 }
 
 /*
-** returns 0 if do_journal_end should return right away, returns 1 if do_journal_end should finish the commit
-**
-** if the current transaction is too old, but still has writers, this will wait on j_join_wait until all
-** the writers are done.  By the time it wakes up, the transaction it was called has already ended, so it just
-** flushes the commit list and returns 0.
-**
-** Won't batch when flush or commit_now is set.  Also won't batch when others are waiting on j_join_wait.
-**
-** Note, we can't allow the journal_end to proceed while there are still writers in the log.
-*/
-static int check_journal_end(struct reiserfs_transaction_handle *th,
-			     struct super_block *sb, unsigned long nblocks,
-			     int flags)
+ * returns 0 if do_journal_end should return right away, returns 1 if
+ * do_journal_end should finish the commit
+ *
+ * if the current transaction is too old, but still has writers, this will
+ * wait on j_join_wait until all the writers are done.  By the time it
+ * wakes up, the transaction it was called has already ended, so it just
+ * flushes the commit list and returns 0.
+ *
+ * Won't batch when flush or commit_now is set.  Also won't batch when
+ * others are waiting on j_join_wait.
+ *
+ * Note, we can't allow the journal_end to proceed while there are still
+ * writers in the log.
+ */
+static int check_journal_end(struct reiserfs_transaction_handle *th, int flags)
 {
 
 	time_t now;
@@ -3509,6 +3610,7 @@ static int check_journal_end(struct reiserfs_transaction_handle *th,
 	int commit_now = flags & COMMIT_NOW;
 	int wait_on_commit = flags & WAIT;
 	struct reiserfs_journal_list *jl;
+	struct super_block *sb = th->t_super;
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
 
 	BUG_ON(!th->t_trans_id);
@@ -3520,23 +3622,27 @@ static int check_journal_end(struct reiserfs_transaction_handle *th,
 	}
 
 	journal->j_len_alloc -= (th->t_blocks_allocated - th->t_blocks_logged);
-	if (atomic_read(&(journal->j_wcount)) > 0) {	/* <= 0 is allowed.  unmounting might not call begin */
-		atomic_dec(&(journal->j_wcount));
-	}
+	/* <= 0 is allowed.  unmounting might not call begin */
+	if (atomic_read(&journal->j_wcount) > 0)
+		atomic_dec(&journal->j_wcount);
 
-	/* BUG, deal with case where j_len is 0, but people previously freed blocks need to be released
-	 ** will be dealt with by next transaction that actually writes something, but should be taken
-	 ** care of in this trans
+	/*
+	 * BUG, deal with case where j_len is 0, but people previously
+	 * freed blocks need to be released will be dealt with by next
+	 * transaction that actually writes something, but should be taken
+	 * care of in this trans
 	 */
 	BUG_ON(journal->j_len == 0);
 
-	/* if wcount > 0, and we are called to with flush or commit_now,
-	 ** we wait on j_join_wait.  We will wake up when the last writer has
-	 ** finished the transaction, and started it on its way to the disk.
-	 ** Then, we flush the commit or journal list, and just return 0
-	 ** because the rest of journal end was already done for this transaction.
+	/*
+	 * if wcount > 0, and we are called to with flush or commit_now,
+	 * we wait on j_join_wait.  We will wake up when the last writer has
+	 * finished the transaction, and started it on its way to the disk.
+	 * Then, we flush the commit or journal list, and just return 0
+	 * because the rest of journal end was already done for this
+	 * transaction.
 	 */
-	if (atomic_read(&(journal->j_wcount)) > 0) {
+	if (atomic_read(&journal->j_wcount) > 0) {
 		if (flush || commit_now) {
 			unsigned trans_id;
 
@@ -3544,27 +3650,30 @@ static int check_journal_end(struct reiserfs_transaction_handle *th,
 			trans_id = jl->j_trans_id;
 			if (wait_on_commit)
 				jl->j_state |= LIST_COMMIT_PENDING;
-			atomic_set(&(journal->j_jlock), 1);
+			atomic_set(&journal->j_jlock, 1);
 			if (flush) {
 				journal->j_next_full_flush = 1;
 			}
 			unlock_journal(sb);
 
-			/* sleep while the current transaction is still j_jlocked */
+			/*
+			 * sleep while the current transaction is
+			 * still j_jlocked
+			 */
 			while (journal->j_trans_id == trans_id) {
 				if (atomic_read(&journal->j_jlock)) {
 					queue_log_writer(sb);
 				} else {
 					lock_journal(sb);
 					if (journal->j_trans_id == trans_id) {
-						atomic_set(&(journal->j_jlock),
+						atomic_set(&journal->j_jlock,
 							   1);
 					}
 					unlock_journal(sb);
 				}
 			}
 			BUG_ON(journal->j_trans_id == trans_id);
-			
+
 			if (commit_now
 			    && journal_list_still_alive(sb, trans_id)
 			    && wait_on_commit) {
@@ -3584,7 +3693,7 @@ static int check_journal_end(struct reiserfs_transaction_handle *th,
 	}
 	/* don't batch when someone is waiting on j_join_wait */
 	/* don't batch when syncing the commit or flushing the whole trans */
-	if (!(journal->j_must_wait > 0) && !(atomic_read(&(journal->j_jlock)))
+	if (!(journal->j_must_wait > 0) && !(atomic_read(&journal->j_jlock))
 	    && !flush && !commit_now && (journal->j_len < journal->j_max_batch)
 	    && journal->j_len_alloc < journal->j_max_batch
 	    && journal->j_cnode_free > (journal->j_trans_max * 3)) {
@@ -3602,19 +3711,22 @@ static int check_journal_end(struct reiserfs_transaction_handle *th,
 }
 
 /*
-** Does all the work that makes deleting blocks safe.
-** when deleting a block mark BH_JNew, just remove it from the current transaction, clean it's buffer_head and move on.
-**
-** otherwise:
-** set a bit for the block in the journal bitmap.  That will prevent it from being allocated for unformatted nodes
-** before this transaction has finished.
-**
-** mark any cnodes for this block as BLOCK_FREED, and clear their bh pointers.  That will prevent any old transactions with
-** this block from trying to flush to the real location.  Since we aren't removing the cnode from the journal_list_hash,
-** the block can't be reallocated yet.
-**
-** Then remove it from the current transaction, decrementing any counters and filing it on the clean list.
-*/
+ * Does all the work that makes deleting blocks safe.
+ * when deleting a block mark BH_JNew, just remove it from the current
+ * transaction, clean it's buffer_head and move on.
+ *
+ * otherwise:
+ * set a bit for the block in the journal bitmap.  That will prevent it from
+ * being allocated for unformatted nodes before this transaction has finished.
+ *
+ * mark any cnodes for this block as BLOCK_FREED, and clear their bh pointers.
+ * That will prevent any old transactions with this block from trying to flush
+ * to the real location.  Since we aren't removing the cnode from the
+ * journal_list_hash, *the block can't be reallocated yet.
+ *
+ * Then remove it from the current transaction, decrementing any counters and
+ * filing it on the clean list.
+ */
 int journal_mark_freed(struct reiserfs_transaction_handle *th,
 		       struct super_block *sb, b_blocknr_t blocknr)
 {
@@ -3637,7 +3749,10 @@ int journal_mark_freed(struct reiserfs_transaction_handle *th,
 		reiserfs_clean_and_file_buffer(bh);
 		cleaned = remove_from_transaction(sb, blocknr, cleaned);
 	} else {
-		/* set the bit for this block in the journal bitmap for this transaction */
+		/*
+		 * set the bit for this block in the journal bitmap
+		 * for this transaction
+		 */
 		jb = journal->j_current_jl->j_list_bitmap;
 		if (!jb) {
 			reiserfs_panic(sb, "journal-1702",
@@ -3653,17 +3768,22 @@ int journal_mark_freed(struct reiserfs_transaction_handle *th,
 		}
 		cleaned = remove_from_transaction(sb, blocknr, cleaned);
 
-		/* find all older transactions with this block, make sure they don't try to write it out */
+		/*
+		 * find all older transactions with this block,
+		 * make sure they don't try to write it out
+		 */
 		cn = get_journal_hash_dev(sb, journal->j_list_hash_table,
 					  blocknr);
 		while (cn) {
 			if (sb == cn->sb && blocknr == cn->blocknr) {
 				set_bit(BLOCK_FREED, &cn->state);
 				if (cn->bh) {
+					/*
+					 * remove_from_transaction will brelse
+					 * the buffer if it was in the current
+					 * trans
+					 */
 					if (!cleaned) {
-						/* remove_from_transaction will brelse the buffer if it was 
-						 ** in the current trans
-						 */
 						clear_buffer_journal_dirty(cn->
 									   bh);
 						clear_buffer_dirty(cn->bh);
@@ -3672,16 +3792,19 @@ int journal_mark_freed(struct reiserfs_transaction_handle *th,
 						cleaned = 1;
 						put_bh(cn->bh);
 						if (atomic_read
-						    (&(cn->bh->b_count)) < 0) {
+						    (&cn->bh->b_count) < 0) {
 							reiserfs_warning(sb,
 								 "journal-2138",
 								 "cn->bh->b_count < 0");
 						}
 					}
-					if (cn->jlist) {	/* since we are clearing the bh, we MUST dec nonzerolen */
-						atomic_dec(&
-							   (cn->jlist->
-							    j_nonzerolen));
+					/*
+					 * since we are clearing the bh,
+					 * we MUST dec nonzerolen
+					 */
+					if (cn->jlist) {
+						atomic_dec(&cn->jlist->
+							   j_nonzerolen);
 					}
 					cn->bh = NULL;
 				}
@@ -3714,10 +3837,16 @@ static int __commit_trans_jl(struct inode *inode, unsigned long id,
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
 	int ret = 0;
 
-	/* is it from the current transaction, or from an unknown transaction? */
+	/*
+	 * is it from the current transaction,
+	 * or from an unknown transaction?
+	 */
 	if (id == journal->j_trans_id) {
 		jl = journal->j_current_jl;
-		/* try to let other writers come in and grow this transaction */
+		/*
+		 * try to let other writers come in and
+		 * grow this transaction
+		 */
 		let_transaction_grow(sb, id);
 		if (journal->j_trans_id != id) {
 			goto flush_commit_only;
@@ -3731,21 +3860,22 @@ static int __commit_trans_jl(struct inode *inode, unsigned long id,
 		if (journal->j_trans_id != id) {
 			reiserfs_prepare_for_journal(sb, SB_BUFFER_WITH_SB(sb),
 						     1);
-			journal_mark_dirty(&th, sb, SB_BUFFER_WITH_SB(sb));
-			ret = journal_end(&th, sb, 1);
+			journal_mark_dirty(&th, SB_BUFFER_WITH_SB(sb));
+			ret = journal_end(&th);
 			goto flush_commit_only;
 		}
 
-		ret = journal_end_sync(&th, sb, 1);
+		ret = journal_end_sync(&th);
 		if (!ret)
 			ret = 1;
 
 	} else {
-		/* this gets tricky, we have to make sure the journal list in
+		/*
+		 * this gets tricky, we have to make sure the journal list in
 		 * the inode still exists.  We know the list is still around
 		 * if we've got a larger transaction id than the oldest list
 		 */
-	      flush_commit_only:
+flush_commit_only:
 		if (journal_list_still_alive(inode->i_sb, id)) {
 			/*
 			 * we only set ret to 1 when we know for sure
@@ -3768,7 +3898,8 @@ int reiserfs_commit_for_inode(struct inode *inode)
 	unsigned int id = REISERFS_I(inode)->i_trans_id;
 	struct reiserfs_journal_list *jl = REISERFS_I(inode)->i_jl;
 
-	/* for the whole inode, assume unset id means it was
+	/*
+	 * for the whole inode, assume unset id means it was
 	 * changed in the current transaction.  More conservative
 	 */
 	if (!id || !jl) {
@@ -3806,12 +3937,11 @@ void reiserfs_restore_prepared_buffer(struct super_block *sb,
 
 extern struct tree_balance *cur_tb;
 /*
-** before we can change a metadata block, we have to make sure it won't
-** be written to disk while we are altering it.  So, we must:
-** clean it
-** wait on it.
-**
-*/
+ * before we can change a metadata block, we have to make sure it won't
+ * be written to disk while we are altering it.  So, we must:
+ * clean it
+ * wait on it.
+ */
 int reiserfs_prepare_for_journal(struct super_block *sb,
 				 struct buffer_head *bh, int wait)
 {
@@ -3832,19 +3962,18 @@ int reiserfs_prepare_for_journal(struct super_block *sb,
 }
 
 /*
-** long and ugly.  If flush, will not return until all commit
-** blocks and all real buffers in the trans are on disk.
-** If no_async, won't return until all commit blocks are on disk.
-**
-** keep reading, there are comments as you go along
-**
-** If the journal is aborted, we just clean up. Things like flushing
-** journal lists, etc just won't happen.
-*/
-static int do_journal_end(struct reiserfs_transaction_handle *th,
-			  struct super_block *sb, unsigned long nblocks,
-			  int flags)
+ * long and ugly.  If flush, will not return until all commit
+ * blocks and all real buffers in the trans are on disk.
+ * If no_async, won't return until all commit blocks are on disk.
+ *
+ * keep reading, there are comments as you go along
+ *
+ * If the journal is aborted, we just clean up. Things like flushing
+ * journal lists, etc just won't happen.
+ */
+static int do_journal_end(struct reiserfs_transaction_handle *th, int flags)
 {
+	struct super_block *sb = th->t_super;
 	struct reiserfs_journal *journal = SB_JOURNAL(sb);
 	struct reiserfs_journal_cnode *cn, *next, *jl_cn;
 	struct reiserfs_journal_cnode *last_cn = NULL;
@@ -3866,9 +3995,12 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 
 	BUG_ON(th->t_refcount > 1);
 	BUG_ON(!th->t_trans_id);
+	BUG_ON(!th->t_super);
 
-	/* protect flush_older_commits from doing mistakes if the
-           transaction ID counter gets overflowed.  */
+	/*
+	 * protect flush_older_commits from doing mistakes if the
+	 * transaction ID counter gets overflowed.
+	 */
 	if (th->t_trans_id == ~0U)
 		flags |= FLUSH_ALL | COMMIT_NOW | WAIT;
 	flush = flags & FLUSH_ALL;
@@ -3879,7 +4011,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	if (journal->j_len == 0) {
 		reiserfs_prepare_for_journal(sb, SB_BUFFER_WITH_SB(sb),
 					     1);
-		journal_mark_dirty(th, sb, SB_BUFFER_WITH_SB(sb));
+		journal_mark_dirty(th, SB_BUFFER_WITH_SB(sb));
 	}
 
 	lock_journal(sb);
@@ -3892,10 +4024,12 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 		wait_on_commit = 1;
 	}
 
-	/* check_journal_end locks the journal, and unlocks if it does not return 1
-	 ** it tells us if we should continue with the journal_end, or just return
+	/*
+	 * check_journal_end locks the journal, and unlocks if it does
+	 * not return 1 it tells us if we should continue with the
+	 * journal_end, or just return
 	 */
-	if (!check_journal_end(th, sb, nblocks, flags)) {
+	if (!check_journal_end(th, flags)) {
 		reiserfs_schedule_old_flush(sb);
 		wake_queued_writers(sb);
 		reiserfs_async_progress_wait(sb);
@@ -3908,19 +4042,23 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	}
 
 	/*
-	 ** j must wait means we have to flush the log blocks, and the real blocks for
-	 ** this transaction
+	 * j must wait means we have to flush the log blocks, and the
+	 * real blocks for this transaction
 	 */
 	if (journal->j_must_wait > 0) {
 		flush = 1;
 	}
 #ifdef REISERFS_PREALLOCATE
-	/* quota ops might need to nest, setup the journal_info pointer for them
-	 * and raise the refcount so that it is > 0. */
+	/*
+	 * quota ops might need to nest, setup the journal_info pointer
+	 * for them and raise the refcount so that it is > 0.
+	 */
 	current->journal_info = th;
 	th->t_refcount++;
-	reiserfs_discard_all_prealloc(th);	/* it should not involve new blocks into
-						 * the transaction */
+
+	/* it should not involve new blocks into the transaction */
+	reiserfs_discard_all_prealloc(th);
+
 	th->t_refcount--;
 	current->journal_info = th->t_handle_save;
 #endif
@@ -3936,7 +4074,10 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	memcpy(get_journal_desc_magic(d_bh), JOURNAL_DESC_MAGIC, 8);
 	set_desc_trans_id(desc, journal->j_trans_id);
 
-	/* setup commit block.  Don't write (keep it clean too) this one until after everyone else is written */
+	/*
+	 * setup commit block.  Don't write (keep it clean too) this one
+	 * until after everyone else is written
+	 */
 	c_bh = journal_getblk(sb, SB_ONDISK_JOURNAL_1st_BLOCK(sb) +
 			      ((journal->j_start + journal->j_len +
 				1) % SB_ONDISK_JOURNAL_SIZE(sb)));
@@ -3948,7 +4089,8 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	/* init this journal list */
 	jl = journal->j_current_jl;
 
-	/* we lock the commit before doing anything because
+	/*
+	 * we lock the commit before doing anything because
 	 * we want to make sure nobody tries to run flush_commit_list until
 	 * the new transaction is fully setup, and we've already flushed the
 	 * ordered bh list
@@ -3968,9 +4110,10 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	atomic_set(&jl->j_commit_left, journal->j_len + 2);
 	jl->j_realblock = NULL;
 
-	/* The ENTIRE FOR LOOP MUST not cause schedule to occur.
-	 **  for each real block, add it to the journal list hash,
-	 ** copy into real block index array in the commit or desc block
+	/*
+	 * The ENTIRE FOR LOOP MUST not cause schedule to occur.
+	 * for each real block, add it to the journal list hash,
+	 * copy into real block index array in the commit or desc block
 	 */
 	trans_half = journal_trans_half(sb->s_blocksize);
 	for (i = 0, cn = journal->j_first; cn; cn = cn->next, i++) {
@@ -3989,9 +4132,10 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 				last_cn->next = jl_cn;
 			}
 			last_cn = jl_cn;
-			/* make sure the block we are trying to log is not a block
-			   of journal or reserved area */
-
+			/*
+			 * make sure the block we are trying to log
+			 * is not a block of journal or reserved area
+			 */
 			if (is_block_in_log_or_reserved_area
 			    (sb, cn->bh->b_blocknr)) {
 				reiserfs_panic(sb, "journal-2332",
@@ -4021,19 +4165,26 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	set_desc_trans_id(desc, journal->j_trans_id);
 	set_commit_trans_len(commit, journal->j_len);
 
-	/* special check in case all buffers in the journal were marked for not logging */
+	/*
+	 * special check in case all buffers in the journal
+	 * were marked for not logging
+	 */
 	BUG_ON(journal->j_len == 0);
 
-	/* we're about to dirty all the log blocks, mark the description block
+	/*
+	 * we're about to dirty all the log blocks, mark the description block
 	 * dirty now too.  Don't mark the commit block dirty until all the
 	 * others are on disk
 	 */
 	mark_buffer_dirty(d_bh);
 
-	/* first data block is j_start + 1, so add one to cur_write_start wherever you use it */
+	/*
+	 * first data block is j_start + 1, so add one to
+	 * cur_write_start wherever you use it
+	 */
 	cur_write_start = journal->j_start;
 	cn = journal->j_first;
-	jindex = 1;		/* start at one so we don't get the desc again */
+	jindex = 1;	/* start at one so we don't get the desc again */
 	while (cn) {
 		clear_buffer_journal_new(cn->bh);
 		/* copy all the real blocks into log area.  dirty log blocks */
@@ -4059,7 +4210,10 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 			set_buffer_journal_dirty(cn->bh);
 			clear_buffer_journaled(cn->bh);
 		} else {
-			/* JDirty cleared sometime during transaction.  don't log this one */
+			/*
+			 * JDirty cleared sometime during transaction.
+			 * don't log this one
+			 */
 			reiserfs_warning(sb, "journal-2048",
 					 "BAD, buffer in journal hash, "
 					 "but not JDirty!");
@@ -4071,9 +4225,10 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 		reiserfs_cond_resched(sb);
 	}
 
-	/* we are done  with both the c_bh and d_bh, but
-	 ** c_bh must be written after all other commit blocks,
-	 ** so we dirty/relse c_bh in flush_commit_list, with commit_left <= 1.
+	/*
+	 * we are done with both the c_bh and d_bh, but
+	 * c_bh must be written after all other commit blocks,
+	 * so we dirty/relse c_bh in flush_commit_list, with commit_left <= 1.
 	 */
 
 	journal->j_current_jl = alloc_journal_list(sb);
@@ -4088,7 +4243,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	journal->j_start =
 	    (journal->j_start + journal->j_len +
 	     2) % SB_ONDISK_JOURNAL_SIZE(sb);
-	atomic_set(&(journal->j_wcount), 0);
+	atomic_set(&journal->j_wcount, 0);
 	journal->j_bcount = 0;
 	journal->j_last = NULL;
 	journal->j_first = NULL;
@@ -4104,15 +4259,18 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	journal->j_next_async_flush = 0;
 	init_journal_hash(sb);
 
-	// make sure reiserfs_add_jh sees the new current_jl before we
-	// write out the tails
+	/*
+	 * make sure reiserfs_add_jh sees the new current_jl before we
+	 * write out the tails
+	 */
 	smp_mb();
 
-	/* tail conversion targets have to hit the disk before we end the
+	/*
+	 * tail conversion targets have to hit the disk before we end the
 	 * transaction.  Otherwise a later transaction might repack the tail
-	 * before this transaction commits, leaving the data block unflushed and
-	 * clean, if we crash before the later transaction commits, the data block
-	 * is lost.
+	 * before this transaction commits, leaving the data block unflushed
+	 * and clean, if we crash before the later transaction commits, the
+	 * data block is lost.
 	 */
 	if (!list_empty(&jl->j_tail_bh_list)) {
 		depth = reiserfs_write_unlock_nested(sb);
@@ -4123,24 +4281,27 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 	BUG_ON(!list_empty(&jl->j_tail_bh_list));
 	mutex_unlock(&jl->j_commit_mutex);
 
-	/* honor the flush wishes from the caller, simple commits can
-	 ** be done outside the journal lock, they are done below
-	 **
-	 ** if we don't flush the commit list right now, we put it into
-	 ** the work queue so the people waiting on the async progress work
-	 ** queue don't wait for this proc to flush journal lists and such.
+	/*
+	 * honor the flush wishes from the caller, simple commits can
+	 * be done outside the journal lock, they are done below
+	 *
+	 * if we don't flush the commit list right now, we put it into
+	 * the work queue so the people waiting on the async progress work
+	 * queue don't wait for this proc to flush journal lists and such.
 	 */
 	if (flush) {
 		flush_commit_list(sb, jl, 1);
 		flush_journal_list(sb, jl, 1);
 	} else if (!(jl->j_state & LIST_COMMIT_PENDING))
-		queue_delayed_work(commit_wq, &journal->j_work, HZ / 10);
+		queue_delayed_work(REISERFS_SB(sb)->commit_wq,
+				   &journal->j_work, HZ / 10);
 
-	/* if the next transaction has any chance of wrapping, flush
-	 ** transactions that might get overwritten.  If any journal lists are very
-	 ** old flush them as well.
+	/*
+	 * if the next transaction has any chance of wrapping, flush
+	 * transactions that might get overwritten.  If any journal lists
+	 * are very old flush them as well.
 	 */
-      first_jl:
+first_jl:
 	list_for_each_safe(entry, safe, &journal->j_journal_list) {
 		temp_jl = JOURNAL_LIST_ENTRY(entry);
 		if (journal->j_start <= temp_jl->j_start) {
@@ -4151,8 +4312,10 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 			} else if ((journal->j_start +
 				    journal->j_trans_max + 1) <
 				   SB_ONDISK_JOURNAL_SIZE(sb)) {
-				/* if we don't cross into the next transaction and we don't
-				 * wrap, there is no way we can overlap any later transactions
+				/*
+				 * if we don't cross into the next
+				 * transaction and we don't wrap, there is
+				 * no way we can overlap any later transactions
 				 * break now
 				 */
 				break;
@@ -4166,10 +4329,12 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 				flush_used_journal_lists(sb, temp_jl);
 				goto first_jl;
 			} else {
-				/* we don't overlap anything from out start to the end of the
-				 * log, and our wrapped portion doesn't overlap anything at
-				 * the start of the log.  We can break
-				 */
+				/*
+				* we don't overlap anything from out start
+				* to the end of the log, and our wrapped
+				* portion doesn't overlap anything at
+				* the start of the log.  We can break
+				*/
 				break;
 			}
 		}
@@ -4183,23 +4348,25 @@ static int do_journal_end(struct reiserfs_transaction_handle *th,
 			       "could not get a list bitmap");
 	}
 
-	atomic_set(&(journal->j_jlock), 0);
+	atomic_set(&journal->j_jlock, 0);
 	unlock_journal(sb);
 	/* wake up any body waiting to join. */
 	clear_bit(J_WRITERS_QUEUED, &journal->j_state);
-	wake_up(&(journal->j_join_wait));
+	wake_up(&journal->j_join_wait);
 
 	if (!flush && wait_on_commit &&
 	    journal_list_still_alive(sb, commit_trans_id)) {
 		flush_commit_list(sb, jl, 1);
 	}
-      out:
+out:
 	reiserfs_check_lock_depth(sb, "journal end2");
 
 	memset(th, 0, sizeof(*th));
-	/* Re-set th->t_super, so we can properly keep track of how many
+	/*
+	 * Re-set th->t_super, so we can properly keep track of how many
 	 * persistent transactions there are. We need to do this so if this
-	 * call is part of a failed restart_transaction, we can free it later */
+	 * call is part of a failed restart_transaction, we can free it later
+	 */
 	th->t_super = sb;
 
 	return journal->j_errno;
diff --git a/fs/reiserfs/lbalance.c b/fs/reiserfs/lbalance.c
index 79e5a8b4c22..d6744c8b24e 100644
--- a/fs/reiserfs/lbalance.c
+++ b/fs/reiserfs/lbalance.c
@@ -8,46 +8,42 @@
 #include "reiserfs.h"
 #include <linux/buffer_head.h>
 
-/* these are used in do_balance.c */
-
-/* leaf_move_items
-   leaf_shift_left
-   leaf_shift_right
-   leaf_delete_items
-   leaf_insert_into_buf
-   leaf_paste_in_buffer
-   leaf_cut_from_buffer
-   leaf_paste_entries
-   */
-
-/* copy copy_count entries from source directory item to dest buffer (creating new item if needed) */
+/*
+ * copy copy_count entries from source directory item to dest buffer
+ * (creating new item if needed)
+ */
 static void leaf_copy_dir_entries(struct buffer_info *dest_bi,
 				  struct buffer_head *source, int last_first,
 				  int item_num, int from, int copy_count)
 {
 	struct buffer_head *dest = dest_bi->bi_bh;
-	int item_num_in_dest;	/* either the number of target item,
-				   or if we must create a new item,
-				   the number of the item we will
-				   create it next to */
+	/*
+	 * either the number of target item, or if we must create a
+	 * new item, the number of the item we will create it next to
+	 */
+	int item_num_in_dest;
+
 	struct item_head *ih;
 	struct reiserfs_de_head *deh;
 	int copy_records_len;	/* length of all records in item to be copied */
 	char *records;
 
-	ih = B_N_PITEM_HEAD(source, item_num);
+	ih = item_head(source, item_num);
 
 	RFALSE(!is_direntry_le_ih(ih), "vs-10000: item must be directory item");
 
-	/* length of all record to be copied and first byte of the last of them */
+	/*
+	 * length of all record to be copied and first byte of
+	 * the last of them
+	 */
 	deh = B_I_DEH(source, ih);
 	if (copy_count) {
-		copy_records_len = (from ? deh_location(&(deh[from - 1])) :
+		copy_records_len = (from ? deh_location(&deh[from - 1]) :
 				    ih_item_len(ih)) -
-		    deh_location(&(deh[from + copy_count - 1]));
+		    deh_location(&deh[from + copy_count - 1]);
 		records =
 		    source->b_data + ih_location(ih) +
-		    deh_location(&(deh[from + copy_count - 1]));
+		    deh_location(&deh[from + copy_count - 1]);
 	} else {
 		copy_records_len = 0;
 		records = NULL;
@@ -59,12 +55,15 @@ static void leaf_copy_dir_entries(struct buffer_info *dest_bi,
 	     LAST_TO_FIRST) ? ((B_NR_ITEMS(dest)) ? 0 : -1) : (B_NR_ITEMS(dest)
 							       - 1);
 
-	/* if there are no items in dest or the first/last item in dest is not item of the same directory */
+	/*
+	 * if there are no items in dest or the first/last item in
+	 * dest is not item of the same directory
+	 */
 	if ((item_num_in_dest == -1) ||
 	    (last_first == FIRST_TO_LAST && le_ih_k_offset(ih) == DOT_OFFSET) ||
 	    (last_first == LAST_TO_FIRST
 	     && comp_short_le_keys /*COMP_SHORT_KEYS */ (&ih->ih_key,
-							 B_N_PKEY(dest,
+							 leaf_key(dest,
 								  item_num_in_dest))))
 	{
 		/* create new item in dest */
@@ -80,16 +79,22 @@ static void leaf_copy_dir_entries(struct buffer_info *dest_bi,
 
 		if (last_first == LAST_TO_FIRST) {
 			/* form key by the following way */
-			if (from < I_ENTRY_COUNT(ih)) {
+			if (from < ih_entry_count(ih)) {
 				set_le_ih_k_offset(&new_ih,
-						   deh_offset(&(deh[from])));
-				/*memcpy (&new_ih.ih_key.k_offset, &deh[from].deh_offset, SHORT_KEY_SIZE); */
+						   deh_offset(&deh[from]));
 			} else {
-				/* no entries will be copied to this item in this function */
+				/*
+				 * no entries will be copied to this
+				 * item in this function
+				 */
 				set_le_ih_k_offset(&new_ih, U32_MAX);
-				/* this item is not yet valid, but we want I_IS_DIRECTORY_ITEM to return 1 for it, so we -1 */
+				/*
+				 * this item is not yet valid, but we
+				 * want I_IS_DIRECTORY_ITEM to return 1
+				 * for it, so we -1
+				 */
 			}
-			set_le_key_k_type(KEY_FORMAT_3_5, &(new_ih.ih_key),
+			set_le_key_k_type(KEY_FORMAT_3_5, &new_ih.ih_key,
 					  TYPE_DIRENTRY);
 		}
 
@@ -113,36 +118,44 @@ static void leaf_copy_dir_entries(struct buffer_info *dest_bi,
 
 	leaf_paste_entries(dest_bi, item_num_in_dest,
 			   (last_first ==
-			    FIRST_TO_LAST) ? I_ENTRY_COUNT(B_N_PITEM_HEAD(dest,
+			    FIRST_TO_LAST) ? ih_entry_count(item_head(dest,
 									  item_num_in_dest))
 			   : 0, copy_count, deh + from, records,
 			   DEH_SIZE * copy_count + copy_records_len);
 }
 
-/* Copy the first (if last_first == FIRST_TO_LAST) or last (last_first == LAST_TO_FIRST) item or
-   part of it or nothing (see the return 0 below) from SOURCE to the end
-   (if last_first) or beginning (!last_first) of the DEST */
+/*
+ * Copy the first (if last_first == FIRST_TO_LAST) or last
+ * (last_first == LAST_TO_FIRST) item or part of it or nothing
+ * (see the return 0 below) from SOURCE to the end (if last_first)
+ * or beginning (!last_first) of the DEST
+ */
 /* returns 1 if anything was copied, else 0 */
 static int leaf_copy_boundary_item(struct buffer_info *dest_bi,
 				   struct buffer_head *src, int last_first,
 				   int bytes_or_entries)
 {
 	struct buffer_head *dest = dest_bi->bi_bh;
-	int dest_nr_item, src_nr_item;	/* number of items in the source and destination buffers */
+	/* number of items in the source and destination buffers */
+	int dest_nr_item, src_nr_item;
 	struct item_head *ih;
 	struct item_head *dih;
 
 	dest_nr_item = B_NR_ITEMS(dest);
 
+	/*
+	 * if ( DEST is empty or first item of SOURCE and last item of
+	 * DEST are the items of different objects or of different types )
+	 * then there is no need to treat this item differently from the
+	 * other items that we copy, so we return
+	 */
 	if (last_first == FIRST_TO_LAST) {
-		/* if ( DEST is empty or first item of SOURCE and last item of DEST are the items of different objects
-		   or of different types ) then there is no need to treat this item differently from the other items
-		   that we copy, so we return */
-		ih = B_N_PITEM_HEAD(src, 0);
-		dih = B_N_PITEM_HEAD(dest, dest_nr_item - 1);
+		ih = item_head(src, 0);
+		dih = item_head(dest, dest_nr_item - 1);
+
+		/* there is nothing to merge */
 		if (!dest_nr_item
-		    || (!op_is_left_mergeable(&(ih->ih_key), src->b_size)))
-			/* there is nothing to merge */
+		    || (!op_is_left_mergeable(&ih->ih_key, src->b_size)))
 			return 0;
 
 		RFALSE(!ih_item_len(ih),
@@ -157,8 +170,11 @@ static int leaf_copy_boundary_item(struct buffer_info *dest_bi,
 			return 1;
 		}
 
-		/* copy part of the body of the first item of SOURCE to the end of the body of the last item of the DEST
-		   part defined by 'bytes_or_entries'; if bytes_or_entries == -1 copy whole body; don't create new item header
+		/*
+		 * copy part of the body of the first item of SOURCE
+		 * to the end of the body of the last item of the DEST
+		 * part defined by 'bytes_or_entries'; if bytes_or_entries
+		 * == -1 copy whole body; don't create new item header
 		 */
 		if (bytes_or_entries == -1)
 			bytes_or_entries = ih_item_len(ih);
@@ -176,11 +192,13 @@ static int leaf_copy_boundary_item(struct buffer_info *dest_bi,
 		}
 #endif
 
-		/* merge first item (or its part) of src buffer with the last
-		   item of dest buffer. Both are of the same file */
+		/*
+		 * merge first item (or its part) of src buffer with the last
+		 * item of dest buffer. Both are of the same file
+		 */
 		leaf_paste_in_buffer(dest_bi,
 				     dest_nr_item - 1, ih_item_len(dih),
-				     bytes_or_entries, B_I_PITEM(src, ih), 0);
+				     bytes_or_entries, ih_item_body(src, ih), 0);
 
 		if (is_indirect_le_ih(dih)) {
 			RFALSE(get_ih_free_space(dih),
@@ -195,19 +213,23 @@ static int leaf_copy_boundary_item(struct buffer_info *dest_bi,
 
 	/* copy boundary item to right (last_first == LAST_TO_FIRST) */
 
-	/* ( DEST is empty or last item of SOURCE and first item of DEST
-	   are the items of different object or of different types )
+	/*
+	 * (DEST is empty or last item of SOURCE and first item of DEST
+	 * are the items of different object or of different types)
 	 */
 	src_nr_item = B_NR_ITEMS(src);
-	ih = B_N_PITEM_HEAD(src, src_nr_item - 1);
-	dih = B_N_PITEM_HEAD(dest, 0);
+	ih = item_head(src, src_nr_item - 1);
+	dih = item_head(dest, 0);
 
-	if (!dest_nr_item || !op_is_left_mergeable(&(dih->ih_key), src->b_size))
+	if (!dest_nr_item || !op_is_left_mergeable(&dih->ih_key, src->b_size))
 		return 0;
 
 	if (is_direntry_le_ih(ih)) {
+		/*
+		 * bytes_or_entries = entries number in last
+		 * item body of SOURCE
+		 */
 		if (bytes_or_entries == -1)
-			/* bytes_or_entries = entries number in last item body of SOURCE */
 			bytes_or_entries = ih_entry_count(ih);
 
 		leaf_copy_dir_entries(dest_bi, src, LAST_TO_FIRST,
@@ -217,9 +239,11 @@ static int leaf_copy_boundary_item(struct buffer_info *dest_bi,
 		return 1;
 	}
 
-	/* copy part of the body of the last item of SOURCE to the begin of the body of the first item of the DEST;
-	   part defined by 'bytes_or_entries'; if byte_or_entriess == -1 copy whole body; change first item key of the DEST;
-	   don't create new item header
+	/*
+	 * copy part of the body of the last item of SOURCE to the
+	 * begin of the body of the first item of the DEST; part defined
+	 * by 'bytes_or_entries'; if byte_or_entriess == -1 copy whole body;
+	 * change first item key of the DEST; don't create new item header
 	 */
 
 	RFALSE(is_indirect_le_ih(ih) && get_ih_free_space(ih),
@@ -270,15 +294,18 @@ static int leaf_copy_boundary_item(struct buffer_info *dest_bi,
 	}
 
 	leaf_paste_in_buffer(dest_bi, 0, 0, bytes_or_entries,
-			     B_I_PITEM(src,
+			     ih_item_body(src,
 				       ih) + ih_item_len(ih) - bytes_or_entries,
 			     0);
 	return 1;
 }
 
-/* copy cpy_mun items from buffer src to buffer dest
- * last_first == FIRST_TO_LAST means, that we copy cpy_num  items beginning from first-th item in src to tail of dest
- * last_first == LAST_TO_FIRST means, that we copy cpy_num  items beginning from first-th item in src to head of dest
+/*
+ * copy cpy_mun items from buffer src to buffer dest
+ * last_first == FIRST_TO_LAST means, that we copy cpy_num items beginning
+ *                             from first-th item in src to tail of dest
+ * last_first == LAST_TO_FIRST means, that we copy cpy_num items beginning
+ *                             from first-th item in src to head of dest
  */
 static void leaf_copy_items_entirely(struct buffer_info *dest_bi,
 				     struct buffer_head *src, int last_first,
@@ -311,11 +338,14 @@ static void leaf_copy_items_entirely(struct buffer_info *dest_bi,
 	nr = blkh_nr_item(blkh);
 	free_space = blkh_free_space(blkh);
 
-	/* we will insert items before 0-th or nr-th item in dest buffer. It depends of last_first parameter */
+	/*
+	 * we will insert items before 0-th or nr-th item in dest buffer.
+	 * It depends of last_first parameter
+	 */
 	dest_before = (last_first == LAST_TO_FIRST) ? 0 : nr;
 
 	/* location of head of first new item */
-	ih = B_N_PITEM_HEAD(dest, dest_before);
+	ih = item_head(dest, dest_before);
 
 	RFALSE(blkh_free_space(blkh) < cpy_num * IH_SIZE,
 	       "vs-10140: not enough free space for headers %d (needed %d)",
@@ -325,7 +355,7 @@ static void leaf_copy_items_entirely(struct buffer_info *dest_bi,
 	memmove(ih + cpy_num, ih, (nr - dest_before) * IH_SIZE);
 
 	/* copy item headers */
-	memcpy(ih, B_N_PITEM_HEAD(src, first), cpy_num * IH_SIZE);
+	memcpy(ih, item_head(src, first), cpy_num * IH_SIZE);
 
 	free_space -= (IH_SIZE * cpy_num);
 	set_blkh_free_space(blkh, free_space);
@@ -338,8 +368,8 @@ static void leaf_copy_items_entirely(struct buffer_info *dest_bi,
 	}
 
 	/* prepare space for items */
-	last_loc = ih_location(&(ih[nr + cpy_num - 1 - dest_before]));
-	last_inserted_loc = ih_location(&(ih[cpy_num - 1]));
+	last_loc = ih_location(&ih[nr + cpy_num - 1 - dest_before]);
+	last_inserted_loc = ih_location(&ih[cpy_num - 1]);
 
 	/* check free space */
 	RFALSE(free_space < j - last_inserted_loc,
@@ -352,7 +382,8 @@ static void leaf_copy_items_entirely(struct buffer_info *dest_bi,
 
 	/* copy items */
 	memcpy(dest->b_data + last_inserted_loc,
-	       B_N_PITEM(src, (first + cpy_num - 1)), j - last_inserted_loc);
+	       item_body(src, (first + cpy_num - 1)),
+	       j - last_inserted_loc);
 
 	/* sizes, item number */
 	set_blkh_nr_item(blkh, nr + cpy_num);
@@ -376,8 +407,10 @@ static void leaf_copy_items_entirely(struct buffer_info *dest_bi,
 	}
 }
 
-/* This function splits the (liquid) item into two items (useful when
-   shifting part of an item into another node.) */
+/*
+ * This function splits the (liquid) item into two items (useful when
+ * shifting part of an item into another node.)
+ */
 static void leaf_item_bottle(struct buffer_info *dest_bi,
 			     struct buffer_head *src, int last_first,
 			     int item_num, int cpy_bytes)
@@ -389,17 +422,22 @@ static void leaf_item_bottle(struct buffer_info *dest_bi,
 	       "vs-10170: bytes == - 1 means: do not split item");
 
 	if (last_first == FIRST_TO_LAST) {
-		/* if ( if item in position item_num in buffer SOURCE is directory item ) */
-		ih = B_N_PITEM_HEAD(src, item_num);
+		/*
+		 * if ( if item in position item_num in buffer SOURCE
+		 * is directory item )
+		 */
+		ih = item_head(src, item_num);
 		if (is_direntry_le_ih(ih))
 			leaf_copy_dir_entries(dest_bi, src, FIRST_TO_LAST,
 					      item_num, 0, cpy_bytes);
 		else {
 			struct item_head n_ih;
 
-			/* copy part of the body of the item number 'item_num' of SOURCE to the end of the DEST
-			   part defined by 'cpy_bytes'; create new item header; change old item_header (????);
-			   n_ih = new item_header;
+			/*
+			 * copy part of the body of the item number 'item_num'
+			 * of SOURCE to the end of the DEST part defined by
+			 * 'cpy_bytes'; create new item header; change old
+			 * item_header (????); n_ih = new item_header;
 			 */
 			memcpy(&n_ih, ih, IH_SIZE);
 			put_ih_item_len(&n_ih, cpy_bytes);
@@ -411,30 +449,36 @@ static void leaf_item_bottle(struct buffer_info *dest_bi,
 				set_ih_free_space(&n_ih, 0);
 			}
 
-			RFALSE(op_is_left_mergeable(&(ih->ih_key), src->b_size),
+			RFALSE(op_is_left_mergeable(&ih->ih_key, src->b_size),
 			       "vs-10190: bad mergeability of item %h", ih);
 			n_ih.ih_version = ih->ih_version;	/* JDM Endian safe, both le */
 			leaf_insert_into_buf(dest_bi, B_NR_ITEMS(dest), &n_ih,
-					     B_N_PITEM(src, item_num), 0);
+					     item_body(src, item_num), 0);
 		}
 	} else {
-		/*  if ( if item in position item_num in buffer SOURCE is directory item ) */
-		ih = B_N_PITEM_HEAD(src, item_num);
+		/*
+		 * if ( if item in position item_num in buffer
+		 * SOURCE is directory item )
+		 */
+		ih = item_head(src, item_num);
 		if (is_direntry_le_ih(ih))
 			leaf_copy_dir_entries(dest_bi, src, LAST_TO_FIRST,
 					      item_num,
-					      I_ENTRY_COUNT(ih) - cpy_bytes,
+					      ih_entry_count(ih) - cpy_bytes,
 					      cpy_bytes);
 		else {
 			struct item_head n_ih;
 
-			/* copy part of the body of the item number 'item_num' of SOURCE to the begin of the DEST
-			   part defined by 'cpy_bytes'; create new item header;
-			   n_ih = new item_header;
+			/*
+			 * copy part of the body of the item number 'item_num'
+			 * of SOURCE to the begin of the DEST part defined by
+			 * 'cpy_bytes'; create new item header;
+			 * n_ih = new item_header;
 			 */
 			memcpy(&n_ih, ih, SHORT_KEY_SIZE);
 
-			n_ih.ih_version = ih->ih_version;	/* JDM Endian safe, both le */
+			/* Endian safe, both le */
+			n_ih.ih_version = ih->ih_version;
 
 			if (is_direct_le_ih(ih)) {
 				set_le_ih_k_offset(&n_ih,
@@ -458,20 +502,22 @@ static void leaf_item_bottle(struct buffer_info *dest_bi,
 			/* set item length */
 			put_ih_item_len(&n_ih, cpy_bytes);
 
-			n_ih.ih_version = ih->ih_version;	/* JDM Endian safe, both le */
+			/* Endian safe, both le */
+			n_ih.ih_version = ih->ih_version;
 
 			leaf_insert_into_buf(dest_bi, 0, &n_ih,
-					     B_N_PITEM(src,
-						       item_num) +
-					     ih_item_len(ih) - cpy_bytes, 0);
+					     item_body(src, item_num) +
+						ih_item_len(ih) - cpy_bytes, 0);
 		}
 	}
 }
 
-/* If cpy_bytes equals minus one than copy cpy_num whole items from SOURCE to DEST.
-   If cpy_bytes not equal to minus one than copy cpy_num-1 whole items from SOURCE to DEST.
-   From last item copy cpy_num bytes for regular item and cpy_num directory entries for
-   directory item. */
+/*
+ * If cpy_bytes equals minus one than copy cpy_num whole items from SOURCE
+ * to DEST.  If cpy_bytes not equal to minus one than copy cpy_num-1 whole
+ * items from SOURCE to DEST.  From last item copy cpy_num bytes for regular
+ * item and cpy_num directory entries for directory item.
+ */
 static int leaf_copy_items(struct buffer_info *dest_bi, struct buffer_head *src,
 			   int last_first, int cpy_num, int cpy_bytes)
 {
@@ -498,22 +544,34 @@ static int leaf_copy_items(struct buffer_info *dest_bi, struct buffer_head *src,
 		else
 			bytes = -1;
 
-		/* copy the first item or it part or nothing to the end of the DEST (i = leaf_copy_boundary_item(DEST,SOURCE,0,bytes)) */
+		/*
+		 * copy the first item or it part or nothing to the end of
+		 * the DEST (i = leaf_copy_boundary_item(DEST,SOURCE,0,bytes))
+		 */
 		i = leaf_copy_boundary_item(dest_bi, src, FIRST_TO_LAST, bytes);
 		cpy_num -= i;
 		if (cpy_num == 0)
 			return i;
 		pos += i;
 		if (cpy_bytes == -1)
-			/* copy first cpy_num items starting from position 'pos' of SOURCE to end of DEST */
+			/*
+			 * copy first cpy_num items starting from position
+			 * 'pos' of SOURCE to end of DEST
+			 */
 			leaf_copy_items_entirely(dest_bi, src, FIRST_TO_LAST,
 						 pos, cpy_num);
 		else {
-			/* copy first cpy_num-1 items starting from position 'pos-1' of the SOURCE to the end of the DEST */
+			/*
+			 * copy first cpy_num-1 items starting from position
+			 * 'pos-1' of the SOURCE to the end of the DEST
+			 */
 			leaf_copy_items_entirely(dest_bi, src, FIRST_TO_LAST,
 						 pos, cpy_num - 1);
 
-			/* copy part of the item which number is cpy_num+pos-1 to the end of the DEST */
+			/*
+			 * copy part of the item which number is
+			 * cpy_num+pos-1 to the end of the DEST
+			 */
 			leaf_item_bottle(dest_bi, src, FIRST_TO_LAST,
 					 cpy_num + pos - 1, cpy_bytes);
 		}
@@ -525,7 +583,11 @@ static int leaf_copy_items(struct buffer_info *dest_bi, struct buffer_head *src,
 		else
 			bytes = -1;
 
-		/* copy the last item or it part or nothing to the begin of the DEST (i = leaf_copy_boundary_item(DEST,SOURCE,1,bytes)); */
+		/*
+		 * copy the last item or it part or nothing to the
+		 * begin of the DEST
+		 * (i = leaf_copy_boundary_item(DEST,SOURCE,1,bytes));
+		 */
 		i = leaf_copy_boundary_item(dest_bi, src, LAST_TO_FIRST, bytes);
 
 		cpy_num -= i;
@@ -534,15 +596,24 @@ static int leaf_copy_items(struct buffer_info *dest_bi, struct buffer_head *src,
 
 		pos = src_nr_item - cpy_num - i;
 		if (cpy_bytes == -1) {
-			/* starting from position 'pos' copy last cpy_num items of SOURCE to begin of DEST */
+			/*
+			 * starting from position 'pos' copy last cpy_num
+			 * items of SOURCE to begin of DEST
+			 */
 			leaf_copy_items_entirely(dest_bi, src, LAST_TO_FIRST,
 						 pos, cpy_num);
 		} else {
-			/* copy last cpy_num-1 items starting from position 'pos+1' of the SOURCE to the begin of the DEST; */
+			/*
+			 * copy last cpy_num-1 items starting from position
+			 * 'pos+1' of the SOURCE to the begin of the DEST;
+			 */
 			leaf_copy_items_entirely(dest_bi, src, LAST_TO_FIRST,
 						 pos + 1, cpy_num - 1);
 
-			/* copy part of the item which number is pos to the begin of the DEST */
+			/*
+			 * copy part of the item which number is pos to
+			 * the begin of the DEST
+			 */
 			leaf_item_bottle(dest_bi, src, LAST_TO_FIRST, pos,
 					 cpy_bytes);
 		}
@@ -550,9 +621,11 @@ static int leaf_copy_items(struct buffer_info *dest_bi, struct buffer_head *src,
 	return i;
 }
 
-/* there are types of coping: from S[0] to L[0], from S[0] to R[0],
-   from R[0] to L[0]. for each of these we have to define parent and
-   positions of destination and source buffers */
+/*
+ * there are types of coping: from S[0] to L[0], from S[0] to R[0],
+ * from R[0] to L[0]. for each of these we have to define parent and
+ * positions of destination and source buffers
+ */
 static void leaf_define_dest_src_infos(int shift_mode, struct tree_balance *tb,
 				       struct buffer_info *dest_bi,
 				       struct buffer_info *src_bi,
@@ -568,7 +641,9 @@ static void leaf_define_dest_src_infos(int shift_mode, struct tree_balance *tb,
 		src_bi->tb = tb;
 		src_bi->bi_bh = PATH_PLAST_BUFFER(tb->tb_path);
 		src_bi->bi_parent = PATH_H_PPARENT(tb->tb_path, 0);
-		src_bi->bi_position = PATH_H_B_ITEM_ORDER(tb->tb_path, 0);	/* src->b_item_order */
+
+		/* src->b_item_order */
+		src_bi->bi_position = PATH_H_B_ITEM_ORDER(tb->tb_path, 0);
 		dest_bi->tb = tb;
 		dest_bi->bi_bh = tb->L[0];
 		dest_bi->bi_parent = tb->FL[0];
@@ -633,8 +708,10 @@ static void leaf_define_dest_src_infos(int shift_mode, struct tree_balance *tb,
 	       shift_mode, src_bi->bi_bh, dest_bi->bi_bh);
 }
 
-/* copy mov_num items and mov_bytes of the (mov_num-1)th item to
-   neighbor. Delete them from source */
+/*
+ * copy mov_num items and mov_bytes of the (mov_num-1)th item to
+ * neighbor. Delete them from source
+ */
 int leaf_move_items(int shift_mode, struct tree_balance *tb, int mov_num,
 		    int mov_bytes, struct buffer_head *Snew)
 {
@@ -657,18 +734,24 @@ int leaf_move_items(int shift_mode, struct tree_balance *tb, int mov_num,
 	return ret_value;
 }
 
-/* Shift shift_num items (and shift_bytes of last shifted item if shift_bytes != -1)
-   from S[0] to L[0] and replace the delimiting key */
+/*
+ * Shift shift_num items (and shift_bytes of last shifted item if
+ * shift_bytes != -1) from S[0] to L[0] and replace the delimiting key
+ */
 int leaf_shift_left(struct tree_balance *tb, int shift_num, int shift_bytes)
 {
 	struct buffer_head *S0 = PATH_PLAST_BUFFER(tb->tb_path);
 	int i;
 
-	/* move shift_num (and shift_bytes bytes) items from S[0] to left neighbor L[0] */
+	/*
+	 * move shift_num (and shift_bytes bytes) items from S[0]
+	 * to left neighbor L[0]
+	 */
 	i = leaf_move_items(LEAF_FROM_S_TO_L, tb, shift_num, shift_bytes, NULL);
 
 	if (shift_num) {
-		if (B_NR_ITEMS(S0) == 0) {	/* number of items in S[0] == 0 */
+		/* number of items in S[0] == 0 */
+		if (B_NR_ITEMS(S0) == 0) {
 
 			RFALSE(shift_bytes != -1,
 			       "vs-10270: S0 is empty now, but shift_bytes != -1 (%d)",
@@ -691,10 +774,10 @@ int leaf_shift_left(struct tree_balance *tb, int shift_num, int shift_bytes)
 			replace_key(tb, tb->CFL[0], tb->lkey[0], S0, 0);
 
 			RFALSE((shift_bytes != -1 &&
-				!(is_direntry_le_ih(B_N_PITEM_HEAD(S0, 0))
-				  && !I_ENTRY_COUNT(B_N_PITEM_HEAD(S0, 0)))) &&
+				!(is_direntry_le_ih(item_head(S0, 0))
+				  && !ih_entry_count(item_head(S0, 0)))) &&
 			       (!op_is_left_mergeable
-				(B_N_PKEY(S0, 0), S0->b_size)),
+				(leaf_key(S0, 0), S0->b_size)),
 			       "vs-10280: item must be mergeable");
 		}
 	}
@@ -704,13 +787,18 @@ int leaf_shift_left(struct tree_balance *tb, int shift_num, int shift_bytes)
 
 /* CLEANING STOPPED HERE */
 
-/* Shift shift_num (shift_bytes) items from S[0] to the right neighbor, and replace the delimiting key */
+/*
+ * Shift shift_num (shift_bytes) items from S[0] to the right neighbor,
+ * and replace the delimiting key
+ */
 int leaf_shift_right(struct tree_balance *tb, int shift_num, int shift_bytes)
 {
-	//  struct buffer_head * S0 = PATH_PLAST_BUFFER (tb->tb_path);
 	int ret_value;
 
-	/* move shift_num (and shift_bytes) items from S[0] to right neighbor R[0] */
+	/*
+	 * move shift_num (and shift_bytes) items from S[0] to
+	 * right neighbor R[0]
+	 */
 	ret_value =
 	    leaf_move_items(LEAF_FROM_S_TO_R, tb, shift_num, shift_bytes, NULL);
 
@@ -725,12 +813,16 @@ int leaf_shift_right(struct tree_balance *tb, int shift_num, int shift_bytes)
 
 static void leaf_delete_items_entirely(struct buffer_info *bi,
 				       int first, int del_num);
-/*  If del_bytes == -1, starting from position 'first' delete del_num items in whole in buffer CUR.
-    If not.
-    If last_first == 0. Starting from position 'first' delete del_num-1 items in whole. Delete part of body of
-    the first item. Part defined by del_bytes. Don't delete first item header
-    If last_first == 1. Starting from position 'first+1' delete del_num-1 items in whole. Delete part of body of
-    the last item . Part defined by del_bytes. Don't delete last item header.
+/*
+ * If del_bytes == -1, starting from position 'first' delete del_num
+ * items in whole in buffer CUR.
+ *   If not.
+ *   If last_first == 0. Starting from position 'first' delete del_num-1
+ *   items in whole. Delete part of body of the first item. Part defined by
+ *   del_bytes. Don't delete first item header
+ *   If last_first == 1. Starting from position 'first+1' delete del_num-1
+ *   items in whole. Delete part of body of the last item . Part defined by
+ *   del_bytes. Don't delete last item header.
 */
 void leaf_delete_items(struct buffer_info *cur_bi, int last_first,
 		       int first, int del_num, int del_bytes)
@@ -761,32 +853,43 @@ void leaf_delete_items(struct buffer_info *cur_bi, int last_first,
 		leaf_delete_items_entirely(cur_bi, first, del_num);
 	else {
 		if (last_first == FIRST_TO_LAST) {
-			/* delete del_num-1 items beginning from item in position first  */
+			/*
+			 * delete del_num-1 items beginning from
+			 * item in position first
+			 */
 			leaf_delete_items_entirely(cur_bi, first, del_num - 1);
 
-			/* delete the part of the first item of the bh
-			   do not delete item header
+			/*
+			 * delete the part of the first item of the bh
+			 * do not delete item header
 			 */
 			leaf_cut_from_buffer(cur_bi, 0, 0, del_bytes);
 		} else {
 			struct item_head *ih;
 			int len;
 
-			/* delete del_num-1 items beginning from item in position first+1  */
+			/*
+			 * delete del_num-1 items beginning from
+			 * item in position first+1
+			 */
 			leaf_delete_items_entirely(cur_bi, first + 1,
 						   del_num - 1);
 
-			ih = B_N_PITEM_HEAD(bh, B_NR_ITEMS(bh) - 1);
+			ih = item_head(bh, B_NR_ITEMS(bh) - 1);
 			if (is_direntry_le_ih(ih))
 				/* the last item is directory  */
-				/* len = numbers of directory entries in this item */
+				/*
+				 * len = numbers of directory entries
+				 * in this item
+				 */
 				len = ih_entry_count(ih);
 			else
 				/* len = body len of item */
 				len = ih_item_len(ih);
 
-			/* delete the part of the last item of the bh
-			   do not delete item header
+			/*
+			 * delete the part of the last item of the bh
+			 * do not delete item header
 			 */
 			leaf_cut_from_buffer(cur_bi, B_NR_ITEMS(bh) - 1,
 					     len - del_bytes, del_bytes);
@@ -820,10 +923,10 @@ void leaf_insert_into_buf(struct buffer_info *bi, int before,
 	       zeros_number, ih_item_len(inserted_item_ih));
 
 	/* get item new item must be inserted before */
-	ih = B_N_PITEM_HEAD(bh, before);
+	ih = item_head(bh, before);
 
 	/* prepare space for the body of new item */
-	last_loc = nr ? ih_location(&(ih[nr - before - 1])) : bh->b_size;
+	last_loc = nr ? ih_location(&ih[nr - before - 1]) : bh->b_size;
 	unmoved_loc = before ? ih_location(ih - 1) : bh->b_size;
 
 	memmove(bh->b_data + last_loc - ih_item_len(inserted_item_ih),
@@ -846,8 +949,8 @@ void leaf_insert_into_buf(struct buffer_info *bi, int before,
 
 	/* change locations */
 	for (i = before; i < nr + 1; i++) {
-		unmoved_loc -= ih_item_len(&(ih[i - before]));
-		put_ih_location(&(ih[i - before]), unmoved_loc);
+		unmoved_loc -= ih_item_len(&ih[i - before]);
+		put_ih_location(&ih[i - before], unmoved_loc);
 	}
 
 	/* sizes, free space, item number */
@@ -867,8 +970,10 @@ void leaf_insert_into_buf(struct buffer_info *bi, int before,
 	}
 }
 
-/* paste paste_size bytes to affected_item_num-th item.
-   When item is a directory, this only prepare space for new entries */
+/*
+ * paste paste_size bytes to affected_item_num-th item.
+ * When item is a directory, this only prepare space for new entries
+ */
 void leaf_paste_in_buffer(struct buffer_info *bi, int affected_item_num,
 			  int pos_in_item, int paste_size,
 			  const char *body, int zeros_number)
@@ -902,9 +1007,9 @@ void leaf_paste_in_buffer(struct buffer_info *bi, int affected_item_num,
 #endif				/* CONFIG_REISERFS_CHECK */
 
 	/* item to be appended */
-	ih = B_N_PITEM_HEAD(bh, affected_item_num);
+	ih = item_head(bh, affected_item_num);
 
-	last_loc = ih_location(&(ih[nr - affected_item_num - 1]));
+	last_loc = ih_location(&ih[nr - affected_item_num - 1]);
 	unmoved_loc = affected_item_num ? ih_location(ih - 1) : bh->b_size;
 
 	/* prepare space */
@@ -913,8 +1018,8 @@ void leaf_paste_in_buffer(struct buffer_info *bi, int affected_item_num,
 
 	/* change locations */
 	for (i = affected_item_num; i < nr; i++)
-		put_ih_location(&(ih[i - affected_item_num]),
-				ih_location(&(ih[i - affected_item_num])) -
+		put_ih_location(&ih[i - affected_item_num],
+				ih_location(&ih[i - affected_item_num]) -
 				paste_size);
 
 	if (body) {
@@ -957,10 +1062,12 @@ void leaf_paste_in_buffer(struct buffer_info *bi, int affected_item_num,
 	}
 }
 
-/* cuts DEL_COUNT entries beginning from FROM-th entry. Directory item
-   does not have free space, so it moves DEHs and remaining records as
-   necessary. Return value is size of removed part of directory item
-   in bytes. */
+/*
+ * cuts DEL_COUNT entries beginning from FROM-th entry. Directory item
+ * does not have free space, so it moves DEHs and remaining records as
+ * necessary. Return value is size of removed part of directory item
+ * in bytes.
+ */
 static int leaf_cut_entries(struct buffer_head *bh,
 			    struct item_head *ih, int from, int del_count)
 {
@@ -971,12 +1078,14 @@ static int leaf_cut_entries(struct buffer_head *bh,
 	int cut_records_len;	/* length of all removed records */
 	int i;
 
-	/* make sure, that item is directory and there are enough entries to
-	   remove */
+	/*
+	 * make sure that item is directory and there are enough entries to
+	 * remove
+	 */
 	RFALSE(!is_direntry_le_ih(ih), "10180: item is not directory item");
-	RFALSE(I_ENTRY_COUNT(ih) < from + del_count,
+	RFALSE(ih_entry_count(ih) < from + del_count,
 	       "10185: item contains not enough entries: entry_count = %d, from = %d, to delete = %d",
-	       I_ENTRY_COUNT(ih), from, del_count);
+	       ih_entry_count(ih), from, del_count);
 
 	if (del_count == 0)
 		return 0;
@@ -987,22 +1096,24 @@ static int leaf_cut_entries(struct buffer_head *bh,
 	/* entry head array */
 	deh = B_I_DEH(bh, ih);
 
-	/* first byte of remaining entries, those are BEFORE cut entries
-	   (prev_record) and length of all removed records (cut_records_len) */
+	/*
+	 * first byte of remaining entries, those are BEFORE cut entries
+	 * (prev_record) and length of all removed records (cut_records_len)
+	 */
 	prev_record_offset =
-	    (from ? deh_location(&(deh[from - 1])) : ih_item_len(ih));
+	    (from ? deh_location(&deh[from - 1]) : ih_item_len(ih));
 	cut_records_len = prev_record_offset /*from_record */  -
-	    deh_location(&(deh[from + del_count - 1]));
+	    deh_location(&deh[from + del_count - 1]);
 	prev_record = item + prev_record_offset;
 
 	/* adjust locations of remaining entries */
-	for (i = I_ENTRY_COUNT(ih) - 1; i > from + del_count - 1; i--)
-		put_deh_location(&(deh[i]),
+	for (i = ih_entry_count(ih) - 1; i > from + del_count - 1; i--)
+		put_deh_location(&deh[i],
 				 deh_location(&deh[i]) -
 				 (DEH_SIZE * del_count));
 
 	for (i = 0; i < from; i++)
-		put_deh_location(&(deh[i]),
+		put_deh_location(&deh[i],
 				 deh_location(&deh[i]) - (DEH_SIZE * del_count +
 							  cut_records_len));
 
@@ -1021,14 +1132,15 @@ static int leaf_cut_entries(struct buffer_head *bh,
 	return DEH_SIZE * del_count + cut_records_len;
 }
 
-/*  when cut item is part of regular file
-        pos_in_item - first byte that must be cut
-        cut_size - number of bytes to be cut beginning from pos_in_item
-
-   when cut item is part of directory
-        pos_in_item - number of first deleted entry
-        cut_size - count of deleted entries
-    */
+/*
+ * when cut item is part of regular file
+ *      pos_in_item - first byte that must be cut
+ *      cut_size - number of bytes to be cut beginning from pos_in_item
+ *
+ * when cut item is part of directory
+ *      pos_in_item - number of first deleted entry
+ *      cut_size - count of deleted entries
+ */
 void leaf_cut_from_buffer(struct buffer_info *bi, int cut_item_num,
 			  int pos_in_item, int cut_size)
 {
@@ -1043,7 +1155,7 @@ void leaf_cut_from_buffer(struct buffer_info *bi, int cut_item_num,
 	nr = blkh_nr_item(blkh);
 
 	/* item head of truncated item */
-	ih = B_N_PITEM_HEAD(bh, cut_item_num);
+	ih = item_head(bh, cut_item_num);
 
 	if (is_direntry_le_ih(ih)) {
 		/* first cut entry () */
@@ -1055,7 +1167,6 @@ void leaf_cut_from_buffer(struct buffer_info *bi, int cut_item_num,
 			       cut_item_num);
 			/* change item key by key of first entry in the item */
 			set_le_ih_k_offset(ih, deh_offset(B_I_DEH(bh, ih)));
-			/*memcpy (&ih->ih_key.k_offset, &(B_I_DEH (bh, ih)->deh_offset), SHORT_KEY_SIZE); */
 		}
 	} else {
 		/* item is direct or indirect */
@@ -1089,7 +1200,7 @@ void leaf_cut_from_buffer(struct buffer_info *bi, int cut_item_num,
 	}
 
 	/* location of the last item */
-	last_loc = ih_location(&(ih[nr - cut_item_num - 1]));
+	last_loc = ih_location(&ih[nr - cut_item_num - 1]);
 
 	/* location of the item, which is remaining at the same place */
 	unmoved_loc = cut_item_num ? ih_location(ih - 1) : bh->b_size;
@@ -1108,7 +1219,7 @@ void leaf_cut_from_buffer(struct buffer_info *bi, int cut_item_num,
 
 	/* change locations */
 	for (i = cut_item_num; i < nr; i++)
-		put_ih_location(&(ih[i - cut_item_num]),
+		put_ih_location(&ih[i - cut_item_num],
 				ih_location(&ih[i - cut_item_num]) + cut_size);
 
 	/* size, free space */
@@ -1156,14 +1267,14 @@ static void leaf_delete_items_entirely(struct buffer_info *bi,
 		return;
 	}
 
-	ih = B_N_PITEM_HEAD(bh, first);
+	ih = item_head(bh, first);
 
 	/* location of unmovable item */
 	j = (first == 0) ? bh->b_size : ih_location(ih - 1);
 
 	/* delete items */
-	last_loc = ih_location(&(ih[nr - 1 - first]));
-	last_removed_loc = ih_location(&(ih[del_num - 1]));
+	last_loc = ih_location(&ih[nr - 1 - first]);
+	last_removed_loc = ih_location(&ih[del_num - 1]);
 
 	memmove(bh->b_data + last_loc + j - last_removed_loc,
 		bh->b_data + last_loc, last_removed_loc - last_loc);
@@ -1173,8 +1284,8 @@ static void leaf_delete_items_entirely(struct buffer_info *bi,
 
 	/* change item location */
 	for (i = first; i < nr - del_num; i++)
-		put_ih_location(&(ih[i - first]),
-				ih_location(&(ih[i - first])) + (j -
+		put_ih_location(&ih[i - first],
+				ih_location(&ih[i - first]) + (j -
 								 last_removed_loc));
 
 	/* sizes, item number */
@@ -1195,7 +1306,10 @@ static void leaf_delete_items_entirely(struct buffer_info *bi,
 	}
 }
 
-/* paste new_entry_count entries (new_dehs, records) into position before to item_num-th item */
+/*
+ * paste new_entry_count entries (new_dehs, records) into position
+ * before to item_num-th item
+ */
 void leaf_paste_entries(struct buffer_info *bi,
 			int item_num,
 			int before,
@@ -1213,13 +1327,16 @@ void leaf_paste_entries(struct buffer_info *bi,
 	if (new_entry_count == 0)
 		return;
 
-	ih = B_N_PITEM_HEAD(bh, item_num);
+	ih = item_head(bh, item_num);
 
-	/* make sure, that item is directory, and there are enough records in it */
+	/*
+	 * make sure, that item is directory, and there are enough
+	 * records in it
+	 */
 	RFALSE(!is_direntry_le_ih(ih), "10225: item is not directory item");
-	RFALSE(I_ENTRY_COUNT(ih) < before,
+	RFALSE(ih_entry_count(ih) < before,
 	       "10230: there are no entry we paste entries before. entry_count = %d, before = %d",
-	       I_ENTRY_COUNT(ih), before);
+	       ih_entry_count(ih), before);
 
 	/* first byte of dest item */
 	item = bh->b_data + ih_location(ih);
@@ -1230,21 +1347,21 @@ void leaf_paste_entries(struct buffer_info *bi,
 	/* new records will be pasted at this point */
 	insert_point =
 	    item +
-	    (before ? deh_location(&(deh[before - 1]))
+	    (before ? deh_location(&deh[before - 1])
 	     : (ih_item_len(ih) - paste_size));
 
 	/* adjust locations of records that will be AFTER new records */
-	for (i = I_ENTRY_COUNT(ih) - 1; i >= before; i--)
-		put_deh_location(&(deh[i]),
-				 deh_location(&(deh[i])) +
+	for (i = ih_entry_count(ih) - 1; i >= before; i--)
+		put_deh_location(&deh[i],
+				 deh_location(&deh[i]) +
 				 (DEH_SIZE * new_entry_count));
 
 	/* adjust locations of records that will be BEFORE new records */
 	for (i = 0; i < before; i++)
-		put_deh_location(&(deh[i]),
-				 deh_location(&(deh[i])) + paste_size);
+		put_deh_location(&deh[i],
+				 deh_location(&deh[i]) + paste_size);
 
-	old_entry_num = I_ENTRY_COUNT(ih);
+	old_entry_num = ih_entry_count(ih);
 	put_ih_entry_count(ih, ih_entry_count(ih) + new_entry_count);
 
 	/* prepare space for pasted records */
@@ -1266,10 +1383,10 @@ void leaf_paste_entries(struct buffer_info *bi,
 
 	/* set locations of new records */
 	for (i = 0; i < new_entry_count; i++) {
-		put_deh_location(&(deh[i]),
-				 deh_location(&(deh[i])) +
+		put_deh_location(&deh[i],
+				 deh_location(&deh[i]) +
 				 (-deh_location
-				  (&(new_dehs[new_entry_count - 1])) +
+				  (&new_dehs[new_entry_count - 1]) +
 				  insert_point + DEH_SIZE * new_entry_count -
 				  item));
 	}
@@ -1277,28 +1394,26 @@ void leaf_paste_entries(struct buffer_info *bi,
 	/* change item key if necessary (when we paste before 0-th entry */
 	if (!before) {
 		set_le_ih_k_offset(ih, deh_offset(new_dehs));
-/*      memcpy (&ih->ih_key.k_offset,
-		       &new_dehs->deh_offset, SHORT_KEY_SIZE);*/
 	}
 #ifdef CONFIG_REISERFS_CHECK
 	{
 		int prev, next;
 		/* check record locations */
 		deh = B_I_DEH(bh, ih);
-		for (i = 0; i < I_ENTRY_COUNT(ih); i++) {
+		for (i = 0; i < ih_entry_count(ih); i++) {
 			next =
 			    (i <
-			     I_ENTRY_COUNT(ih) -
-			     1) ? deh_location(&(deh[i + 1])) : 0;
-			prev = (i != 0) ? deh_location(&(deh[i - 1])) : 0;
+			     ih_entry_count(ih) -
+			     1) ? deh_location(&deh[i + 1]) : 0;
+			prev = (i != 0) ? deh_location(&deh[i - 1]) : 0;
 
-			if (prev && prev <= deh_location(&(deh[i])))
+			if (prev && prev <= deh_location(&deh[i]))
 				reiserfs_error(sb_from_bi(bi), "vs-10240",
 					       "directory item (%h) "
 					       "corrupted (prev %a, "
 					       "cur(%d) %a)",
 					       ih, deh + i - 1, i, deh + i);
-			if (next && next >= deh_location(&(deh[i])))
+			if (next && next >= deh_location(&deh[i]))
 				reiserfs_error(sb_from_bi(bi), "vs-10250",
 					       "directory item (%h) "
 					       "corrupted (cur(%d) %a, "
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index e825f8b63e6..cd11358b10c 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -22,8 +22,10 @@
 #define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { inc_nlink(i); if (i->i_nlink >= REISERFS_LINK_MAX) set_nlink(i, 1); }
 #define DEC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) drop_nlink(i);
 
-// directory item contains array of entry headers. This performs
-// binary search through that array
+/*
+ * directory item contains array of entry headers. This performs
+ * binary search through that array
+ */
 static int bin_search_in_dir_item(struct reiserfs_dir_entry *de, loff_t off)
 {
 	struct item_head *ih = de->de_ih;
@@ -31,7 +33,7 @@ static int bin_search_in_dir_item(struct reiserfs_dir_entry *de, loff_t off)
 	int rbound, lbound, j;
 
 	lbound = 0;
-	rbound = I_ENTRY_COUNT(ih) - 1;
+	rbound = ih_entry_count(ih) - 1;
 
 	for (j = (rbound + lbound) / 2; lbound <= rbound;
 	     j = (rbound + lbound) / 2) {
@@ -43,7 +45,7 @@ static int bin_search_in_dir_item(struct reiserfs_dir_entry *de, loff_t off)
 			lbound = j + 1;
 			continue;
 		}
-		// this is not name found, but matched third key component
+		/* this is not name found, but matched third key component */
 		de->de_entry_num = j;
 		return NAME_FOUND;
 	}
@@ -52,17 +54,21 @@ static int bin_search_in_dir_item(struct reiserfs_dir_entry *de, loff_t off)
 	return NAME_NOT_FOUND;
 }
 
-// comment?  maybe something like set de to point to what the path points to?
+/*
+ * comment?  maybe something like set de to point to what the path points to?
+ */
 static inline void set_de_item_location(struct reiserfs_dir_entry *de,
 					struct treepath *path)
 {
 	de->de_bh = get_last_bh(path);
-	de->de_ih = get_ih(path);
+	de->de_ih = tp_item_head(path);
 	de->de_deh = B_I_DEH(de->de_bh, de->de_ih);
 	de->de_item_num = PATH_LAST_POSITION(path);
 }
 
-// de_bh, de_ih, de_deh (points to first element of array), de_item_num is set
+/*
+ * de_bh, de_ih, de_deh (points to first element of array), de_item_num is set
+ */
 inline void set_de_name_and_namelen(struct reiserfs_dir_entry *de)
 {
 	struct reiserfs_de_head *deh = de->de_deh + de->de_entry_num;
@@ -71,17 +77,17 @@ inline void set_de_name_and_namelen(struct reiserfs_dir_entry *de)
 
 	de->de_entrylen = entry_length(de->de_bh, de->de_ih, de->de_entry_num);
 	de->de_namelen = de->de_entrylen - (de_with_sd(deh) ? SD_SIZE : 0);
-	de->de_name = B_I_PITEM(de->de_bh, de->de_ih) + deh_location(deh);
+	de->de_name = ih_item_body(de->de_bh, de->de_ih) + deh_location(deh);
 	if (de->de_name[de->de_namelen - 1] == 0)
 		de->de_namelen = strlen(de->de_name);
 }
 
-// what entry points to
+/* what entry points to */
 static inline void set_de_object_key(struct reiserfs_dir_entry *de)
 {
 	BUG_ON(de->de_entry_num >= ih_entry_count(de->de_ih));
-	de->de_dir_id = deh_dir_id(&(de->de_deh[de->de_entry_num]));
-	de->de_objectid = deh_objectid(&(de->de_deh[de->de_entry_num]));
+	de->de_dir_id = deh_dir_id(&de->de_deh[de->de_entry_num]);
+	de->de_objectid = deh_objectid(&de->de_deh[de->de_entry_num]);
 }
 
 static inline void store_de_entry_key(struct reiserfs_dir_entry *de)
@@ -96,21 +102,20 @@ static inline void store_de_entry_key(struct reiserfs_dir_entry *de)
 	    le32_to_cpu(de->de_ih->ih_key.k_dir_id);
 	de->de_entry_key.on_disk_key.k_objectid =
 	    le32_to_cpu(de->de_ih->ih_key.k_objectid);
-	set_cpu_key_k_offset(&(de->de_entry_key), deh_offset(deh));
-	set_cpu_key_k_type(&(de->de_entry_key), TYPE_DIRENTRY);
+	set_cpu_key_k_offset(&de->de_entry_key, deh_offset(deh));
+	set_cpu_key_k_type(&de->de_entry_key, TYPE_DIRENTRY);
 }
 
-/* We assign a key to each directory item, and place multiple entries
-in a single directory item.  A directory item has a key equal to the
-key of the first directory entry in it.
-
-This function first calls search_by_key, then, if item whose first
-entry matches is not found it looks for the entry inside directory
-item found by search_by_key. Fills the path to the entry, and to the
-entry position in the item
-
-*/
-
+/*
+ * We assign a key to each directory item, and place multiple entries in a
+ * single directory item.  A directory item has a key equal to the key of
+ * the first directory entry in it.
+
+ * This function first calls search_by_key, then, if item whose first entry
+ * matches is not found it looks for the entry inside directory item found
+ * by search_by_key. Fills the path to the entry, and to the entry position
+ * in the item
+ */
 /* The function is NOT SCHEDULE-SAFE! */
 int search_by_entry_key(struct super_block *sb, const struct cpu_key *key,
 			struct treepath *path, struct reiserfs_dir_entry *de)
@@ -144,7 +149,7 @@ int search_by_entry_key(struct super_block *sb, const struct cpu_key *key,
 
 #ifdef CONFIG_REISERFS_CHECK
 	if (!is_direntry_le_ih(de->de_ih) ||
-	    COMP_SHORT_KEYS(&(de->de_ih->ih_key), key)) {
+	    COMP_SHORT_KEYS(&de->de_ih->ih_key, key)) {
 		print_block(de->de_bh, 0, -1, -1);
 		reiserfs_panic(sb, "vs-7005", "found item %h is not directory "
 			       "item or does not belong to the same directory "
@@ -152,12 +157,17 @@ int search_by_entry_key(struct super_block *sb, const struct cpu_key *key,
 	}
 #endif				/* CONFIG_REISERFS_CHECK */
 
-	/* binary search in directory item by third componen t of the
-	   key. sets de->de_entry_num of de */
+	/*
+	 * binary search in directory item by third component of the
+	 * key. sets de->de_entry_num of de
+	 */
 	retval = bin_search_in_dir_item(de, cpu_key_k_offset(key));
 	path->pos_in_item = de->de_entry_num;
 	if (retval != NAME_NOT_FOUND) {
-		// ugly, but rename needs de_bh, de_deh, de_name, de_namelen, de_objectid set
+		/*
+		 * ugly, but rename needs de_bh, de_deh, de_name,
+		 * de_namelen, de_objectid set
+		 */
 		set_de_name_and_namelen(de);
 		set_de_object_key(de);
 	}
@@ -166,11 +176,12 @@ int search_by_entry_key(struct super_block *sb, const struct cpu_key *key,
 
 /* Keyed 32-bit hash function using TEA in a Davis-Meyer function */
 
-/* The third component is hashed, and you can choose from more than
-   one hash function.  Per directory hashes are not yet implemented
-   but are thought about. This function should be moved to hashes.c
-   Jedi, please do so.  -Hans */
-
+/*
+ * The third component is hashed, and you can choose from more than
+ * one hash function.  Per directory hashes are not yet implemented
+ * but are thought about. This function should be moved to hashes.c
+ * Jedi, please do so.  -Hans
+ */
 static __u32 get_third_component(struct super_block *s,
 				 const char *name, int len)
 {
@@ -183,11 +194,13 @@ static __u32 get_third_component(struct super_block *s,
 
 	res = REISERFS_SB(s)->s_hash_function(name, len);
 
-	// take bits from 7-th to 30-th including both bounds
+	/* take bits from 7-th to 30-th including both bounds */
 	res = GET_HASH_VALUE(res);
 	if (res == 0)
-		// needed to have no names before "." and ".." those have hash
-		// value == 0 and generation conters 1 and 2 accordingly
+		/*
+		 * needed to have no names before "." and ".." those have hash
+		 * value == 0 and generation conters 1 and 2 accordingly
+		 */
 		res = 128;
 	return res + MAX_GENERATION_NUMBER;
 }
@@ -208,7 +221,7 @@ static int reiserfs_match(struct reiserfs_dir_entry *de,
 
 /* de's de_bh, de_ih, de_deh, de_item_num, de_entry_num are set already */
 
-				/* used when hash collisions exist */
+/* used when hash collisions exist */
 
 static int linear_search_in_dir_item(struct cpu_key *key,
 				     struct reiserfs_dir_entry *de,
@@ -220,7 +233,7 @@ static int linear_search_in_dir_item(struct cpu_key *key,
 
 	i = de->de_entry_num;
 
-	if (i == I_ENTRY_COUNT(de->de_ih) ||
+	if (i == ih_entry_count(de->de_ih) ||
 	    GET_HASH_VALUE(deh_offset(deh + i)) !=
 	    GET_HASH_VALUE(cpu_key_k_offset(key))) {
 		i--;
@@ -232,43 +245,50 @@ static int linear_search_in_dir_item(struct cpu_key *key,
 	deh += i;
 
 	for (; i >= 0; i--, deh--) {
+		/* hash value does not match, no need to check whole name */
 		if (GET_HASH_VALUE(deh_offset(deh)) !=
 		    GET_HASH_VALUE(cpu_key_k_offset(key))) {
-			// hash value does not match, no need to check whole name
 			return NAME_NOT_FOUND;
 		}
 
-		/* mark, that this generation number is used */
+		/* mark that this generation number is used */
 		if (de->de_gen_number_bit_string)
 			set_bit(GET_GENERATION_NUMBER(deh_offset(deh)),
 				de->de_gen_number_bit_string);
 
-		// calculate pointer to name and namelen
+		/* calculate pointer to name and namelen */
 		de->de_entry_num = i;
 		set_de_name_and_namelen(de);
 
+		/*
+		 * de's de_name, de_namelen, de_recordlen are set.
+		 * Fill the rest.
+		 */
 		if ((retval =
 		     reiserfs_match(de, name, namelen)) != NAME_NOT_FOUND) {
-			// de's de_name, de_namelen, de_recordlen are set. Fill the rest:
 
-			// key of pointed object
+			/* key of pointed object */
 			set_de_object_key(de);
 
 			store_de_entry_key(de);
 
-			// retval can be NAME_FOUND or NAME_FOUND_INVISIBLE
+			/* retval can be NAME_FOUND or NAME_FOUND_INVISIBLE */
 			return retval;
 		}
 	}
 
 	if (GET_GENERATION_NUMBER(le_ih_k_offset(de->de_ih)) == 0)
-		/* we have reached left most entry in the node. In common we
-		   have to go to the left neighbor, but if generation counter
-		   is 0 already, we know for sure, that there is no name with
-		   the same hash value */
-		// FIXME: this work correctly only because hash value can not
-		// be 0. Btw, in case of Yura's hash it is probably possible,
-		// so, this is a bug
+		/*
+		 * we have reached left most entry in the node. In common we
+		 * have to go to the left neighbor, but if generation counter
+		 * is 0 already, we know for sure, that there is no name with
+		 * the same hash value
+		 */
+		/*
+		 * FIXME: this work correctly only because hash value can not
+		 *  be 0. Btw, in case of Yura's hash it is probably possible,
+		 * so, this is a bug
+		 */
 		return NAME_NOT_FOUND;
 
 	RFALSE(de->de_item_num,
@@ -277,8 +297,10 @@ static int linear_search_in_dir_item(struct cpu_key *key,
 	return GOTO_PREVIOUS_ITEM;
 }
 
-// may return NAME_FOUND, NAME_FOUND_INVISIBLE, NAME_NOT_FOUND
-// FIXME: should add something like IOERROR
+/*
+ * may return NAME_FOUND, NAME_FOUND_INVISIBLE, NAME_NOT_FOUND
+ * FIXME: should add something like IOERROR
+ */
 static int reiserfs_find_entry(struct inode *dir, const char *name, int namelen,
 			       struct treepath *path_to_entry,
 			       struct reiserfs_dir_entry *de)
@@ -307,13 +329,19 @@ static int reiserfs_find_entry(struct inode *dir, const char *name, int namelen,
 		retval =
 		    linear_search_in_dir_item(&key_to_search, de, name,
 					      namelen);
+		/*
+		 * there is no need to scan directory anymore.
+		 * Given entry found or does not exist
+		 */
 		if (retval != GOTO_PREVIOUS_ITEM) {
-			/* there is no need to scan directory anymore. Given entry found or does not exist */
 			path_to_entry->pos_in_item = de->de_entry_num;
 			return retval;
 		}
 
-		/* there is left neighboring item of this directory and given entry can be there */
+		/*
+		 * there is left neighboring item of this directory
+		 * and given entry can be there
+		 */
 		set_cpu_key_k_offset(&key_to_search,
 				     le_ih_k_offset(de->de_ih) - 1);
 		pathrelse(path_to_entry);
@@ -341,14 +369,16 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
 	pathrelse(&path_to_entry);
 	if (retval == NAME_FOUND) {
 		inode = reiserfs_iget(dir->i_sb,
-				      (struct cpu_key *)&(de.de_dir_id));
+				      (struct cpu_key *)&de.de_dir_id);
 		if (!inode || IS_ERR(inode)) {
 			reiserfs_write_unlock(dir->i_sb);
 			return ERR_PTR(-EACCES);
 		}
 
-		/* Propagate the private flag so we know we're
-		 * in the priv tree */
+		/*
+		 * Propagate the private flag so we know we're
+		 * in the priv tree
+		 */
 		if (IS_PRIVATE(dir))
 			inode->i_flags |= S_PRIVATE;
 	}
@@ -361,9 +391,9 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
 }
 
 /*
-** looks up the dentry of the parent directory for child.
-** taken from ext2_get_parent
-*/
+ * looks up the dentry of the parent directory for child.
+ * taken from ext2_get_parent
+ */
 struct dentry *reiserfs_get_parent(struct dentry *child)
 {
 	int retval;
@@ -384,7 +414,7 @@ struct dentry *reiserfs_get_parent(struct dentry *child)
 		reiserfs_write_unlock(dir->i_sb);
 		return ERR_PTR(-ENOENT);
 	}
-	inode = reiserfs_iget(dir->i_sb, (struct cpu_key *)&(de.de_dir_id));
+	inode = reiserfs_iget(dir->i_sb, (struct cpu_key *)&de.de_dir_id);
 	reiserfs_write_unlock(dir->i_sb);
 
 	return d_obtain_alias(inode);
@@ -406,8 +436,13 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 	struct reiserfs_dir_entry de;
 	DECLARE_BITMAP(bit_string, MAX_GENERATION_NUMBER + 1);
 	int gen_number;
-	char small_buf[32 + DEH_SIZE];	/* 48 bytes now and we avoid kmalloc
-					   if we create file with short name */
+
+	/*
+	 * 48 bytes now and we avoid kmalloc if we
+	 * create file with short name
+	 */
+	char small_buf[32 + DEH_SIZE];
+
 	char *buffer;
 	int buflen, paste_size;
 	int retval;
@@ -439,21 +474,30 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 	    (get_inode_sd_version(dir) ==
 	     STAT_DATA_V1) ? (DEH_SIZE + namelen) : buflen;
 
-	/* fill buffer : directory entry head, name[, dir objectid | , stat data | ,stat data, dir objectid ] */
+	/*
+	 * fill buffer : directory entry head, name[, dir objectid | ,
+	 * stat data | ,stat data, dir objectid ]
+	 */
 	deh = (struct reiserfs_de_head *)buffer;
 	deh->deh_location = 0;	/* JDM Endian safe if 0 */
 	put_deh_offset(deh, cpu_key_k_offset(&entry_key));
 	deh->deh_state = 0;	/* JDM Endian safe if 0 */
 	/* put key (ino analog) to de */
-	deh->deh_dir_id = INODE_PKEY(inode)->k_dir_id;	/* safe: k_dir_id is le */
-	deh->deh_objectid = INODE_PKEY(inode)->k_objectid;	/* safe: k_objectid is le */
+
+	/* safe: k_dir_id is le */
+	deh->deh_dir_id = INODE_PKEY(inode)->k_dir_id;
+	/* safe: k_objectid is le */
+	deh->deh_objectid = INODE_PKEY(inode)->k_objectid;
 
 	/* copy name */
 	memcpy((char *)(deh + 1), name, namelen);
 	/* padd by 0s to the 4 byte boundary */
 	padd_item((char *)(deh + 1), ROUND_UP(namelen), namelen);
 
-	/* entry is ready to be pasted into tree, set 'visibility' and 'stat data in entry' attributes */
+	/*
+	 * entry is ready to be pasted into tree, set 'visibility'
+	 * and 'stat data in entry' attributes
+	 */
 	mark_de_without_sd(deh);
 	visible ? mark_de_visible(deh) : mark_de_hidden(deh);
 
@@ -499,7 +543,8 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 	/* update max-hash-collisions counter in reiserfs_sb_info */
 	PROC_INFO_MAX(th->t_super, max_hash_collisions, gen_number);
 
-	if (gen_number != 0) {	/* we need to re-search for the insertion point */
+	/* we need to re-search for the insertion point */
+	if (gen_number != 0) {
 		if (search_by_entry_key(dir->i_sb, &entry_key, &path, &de) !=
 		    NAME_NOT_FOUND) {
 			reiserfs_warning(dir->i_sb, "vs-7032",
@@ -527,18 +572,19 @@ static int reiserfs_add_entry(struct reiserfs_transaction_handle *th,
 	dir->i_size += paste_size;
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
 	if (!S_ISDIR(inode->i_mode) && visible)
-		// reiserfs_mkdir or reiserfs_rename will do that by itself
+		/* reiserfs_mkdir or reiserfs_rename will do that by itself */
 		reiserfs_update_sd(th, dir);
 
 	reiserfs_check_path(&path);
 	return 0;
 }
 
-/* quota utility function, call if you've had to abort after calling
-** new_inode_init, and have not called reiserfs_new_inode yet.
-** This should only be called on inodes that do not have stat data
-** inserted into the tree yet.
-*/
+/*
+ * quota utility function, call if you've had to abort after calling
+ * new_inode_init, and have not called reiserfs_new_inode yet.
+ * This should only be called on inodes that do not have stat data
+ * inserted into the tree yet.
+ */
 static int drop_new_inode(struct inode *inode)
 {
 	dquot_drop(inode);
@@ -548,18 +594,23 @@ static int drop_new_inode(struct inode *inode)
 	return 0;
 }
 
-/* utility function that does setup for reiserfs_new_inode.
-** dquot_initialize needs lots of credits so it's better to have it
-** outside of a transaction, so we had to pull some bits of
-** reiserfs_new_inode out into this func.
-*/
+/*
+ * utility function that does setup for reiserfs_new_inode.
+ * dquot_initialize needs lots of credits so it's better to have it
+ * outside of a transaction, so we had to pull some bits of
+ * reiserfs_new_inode out into this func.
+ */
 static int new_inode_init(struct inode *inode, struct inode *dir, umode_t mode)
 {
-	/* Make inode invalid - just in case we are going to drop it before
-	 * the initialization happens */
+	/*
+	 * Make inode invalid - just in case we are going to drop it before
+	 * the initialization happens
+	 */
 	INODE_PKEY(inode)->k_objectid = 0;
-	/* the quota init calls have to know who to charge the quota to, so
-	 ** we have to set uid and gid here
+
+	/*
+	 * the quota init calls have to know who to charge the quota to, so
+	 * we have to set uid and gid here
 	 */
 	inode_init_owner(inode, dir, mode);
 	dquot_initialize(inode);
@@ -571,7 +622,10 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod
 {
 	int retval;
 	struct inode *inode;
-	/* We need blocks for transaction + (user+group)*(quotas for new inode + update of quota for directory owner) */
+	/*
+	 * We need blocks for transaction + (user+group)*(quotas
+	 * for new inode + update of quota for directory owner)
+	 */
 	int jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 2 +
 	    2 * (REISERFS_QUOTA_INIT_BLOCKS(dir->i_sb) +
@@ -618,7 +672,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod
 		int err;
 		drop_nlink(inode);
 		reiserfs_update_sd(&th, inode);
-		err = journal_end(&th, dir->i_sb, jbegin_count);
+		err = journal_end(&th);
 		if (err)
 			retval = err;
 		unlock_new_inode(inode);
@@ -630,9 +684,9 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod
 
 	unlock_new_inode(inode);
 	d_instantiate(dentry, inode);
-	retval = journal_end(&th, dir->i_sb, jbegin_count);
+	retval = journal_end(&th);
 
-      out_failed:
+out_failed:
 	reiserfs_write_unlock(dir->i_sb);
 	return retval;
 }
@@ -644,7 +698,10 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
 	struct inode *inode;
 	struct reiserfs_transaction_handle th;
 	struct reiserfs_security_handle security;
-	/* We need blocks for transaction + (user+group)*(quotas for new inode + update of quota for directory owner) */
+	/*
+	 * We need blocks for transaction + (user+group)*(quotas
+	 * for new inode + update of quota for directory owner)
+	 */
 	int jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 3 +
 	    2 * (REISERFS_QUOTA_INIT_BLOCKS(dir->i_sb) +
@@ -685,7 +742,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
 	inode->i_op = &reiserfs_special_inode_operations;
 	init_special_inode(inode, inode->i_mode, rdev);
 
-	//FIXME: needed for block and char devices only
+	/* FIXME: needed for block and char devices only */
 	reiserfs_update_sd(&th, inode);
 
 	reiserfs_update_inode_transaction(inode);
@@ -698,7 +755,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
 		int err;
 		drop_nlink(inode);
 		reiserfs_update_sd(&th, inode);
-		err = journal_end(&th, dir->i_sb, jbegin_count);
+		err = journal_end(&th);
 		if (err)
 			retval = err;
 		unlock_new_inode(inode);
@@ -708,9 +765,9 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
 
 	unlock_new_inode(inode);
 	d_instantiate(dentry, inode);
-	retval = journal_end(&th, dir->i_sb, jbegin_count);
+	retval = journal_end(&th);
 
-      out_failed:
+out_failed:
 	reiserfs_write_unlock(dir->i_sb);
 	return retval;
 }
@@ -721,7 +778,10 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 	struct inode *inode;
 	struct reiserfs_transaction_handle th;
 	struct reiserfs_security_handle security;
-	/* We need blocks for transaction + (user+group)*(quotas for new inode + update of quota for directory owner) */
+	/*
+	 * We need blocks for transaction + (user+group)*(quotas
+	 * for new inode + update of quota for directory owner)
+	 */
 	int jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 3 +
 	    2 * (REISERFS_QUOTA_INIT_BLOCKS(dir->i_sb) +
@@ -730,7 +790,10 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 	dquot_initialize(dir);
 
 #ifdef DISPLACE_NEW_PACKING_LOCALITIES
-	/* set flag that new packing locality created and new blocks for the content     * of that directory are not displaced yet */
+	/*
+	 * set flag that new packing locality created and new blocks
+	 * for the content of that directory are not displaced yet
+	 */
 	REISERFS_I(dir)->new_packing_locality = 1;
 #endif
 	mode = S_IFDIR | mode;
@@ -754,8 +817,9 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 		goto out_failed;
 	}
 
-	/* inc the link count now, so another writer doesn't overflow it while
-	 ** we sleep later on.
+	/*
+	 * inc the link count now, so another writer doesn't overflow
+	 * it while we sleep later on.
 	 */
 	INC_DIR_INODE_NLINK(dir)
 
@@ -774,7 +838,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 	inode->i_op = &reiserfs_dir_inode_operations;
 	inode->i_fop = &reiserfs_dir_operations;
 
-	// note, _this_ add_entry will not update dir's stat data
+	/* note, _this_ add_entry will not update dir's stat data */
 	retval =
 	    reiserfs_add_entry(&th, dir, dentry->d_name.name,
 			       dentry->d_name.len, inode, 1 /*visible */ );
@@ -783,19 +847,19 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 		clear_nlink(inode);
 		DEC_DIR_INODE_NLINK(dir);
 		reiserfs_update_sd(&th, inode);
-		err = journal_end(&th, dir->i_sb, jbegin_count);
+		err = journal_end(&th);
 		if (err)
 			retval = err;
 		unlock_new_inode(inode);
 		iput(inode);
 		goto out_failed;
 	}
-	// the above add_entry did not update dir's stat data
+	/* the above add_entry did not update dir's stat data */
 	reiserfs_update_sd(&th, dir);
 
 	unlock_new_inode(inode);
 	d_instantiate(dentry, inode);
-	retval = journal_end(&th, dir->i_sb, jbegin_count);
+	retval = journal_end(&th);
 out_failed:
 	reiserfs_write_unlock(dir->i_sb);
 	return retval;
@@ -803,10 +867,11 @@ out_failed:
 
 static inline int reiserfs_empty_dir(struct inode *inode)
 {
-	/* we can cheat because an old format dir cannot have
-	 ** EMPTY_DIR_SIZE, and a new format dir cannot have
-	 ** EMPTY_DIR_SIZE_V1.  So, if the inode is either size,
-	 ** regardless of disk format version, the directory is empty.
+	/*
+	 * we can cheat because an old format dir cannot have
+	 * EMPTY_DIR_SIZE, and a new format dir cannot have
+	 * EMPTY_DIR_SIZE_V1.  So, if the inode is either size,
+	 * regardless of disk format version, the directory is empty.
 	 */
 	if (inode->i_size != EMPTY_DIR_SIZE &&
 	    inode->i_size != EMPTY_DIR_SIZE_V1) {
@@ -824,10 +889,12 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry)
 	INITIALIZE_PATH(path);
 	struct reiserfs_dir_entry de;
 
-	/* we will be doing 2 balancings and update 2 stat data, we change quotas
-	 * of the owner of the directory and of the owner of the parent directory.
-	 * The quota structure is possibly deleted only on last iput => outside
-	 * of this transaction */
+	/*
+	 * we will be doing 2 balancings and update 2 stat data, we
+	 * change quotas of the owner of the directory and of the owner
+	 * of the parent directory.  The quota structure is possibly
+	 * deleted only on last iput => outside of this transaction
+	 */
 	jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 2 + 2 +
 	    4 * REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb);
@@ -856,8 +923,9 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry)
 	reiserfs_update_inode_transaction(dir);
 
 	if (de.de_objectid != inode->i_ino) {
-		// FIXME: compare key of an object and a key found in the
-		// entry
+		/*
+		 * FIXME: compare key of an object and a key found in the entry
+		 */
 		retval = -EIO;
 		goto end_rmdir;
 	}
@@ -867,7 +935,8 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry)
 	}
 
 	/* cut entry from dir directory */
-	retval = reiserfs_cut_from_item(&th, &path, &(de.de_entry_key), dir, NULL,	/* page */
+	retval = reiserfs_cut_from_item(&th, &path, &de.de_entry_key,
+					dir, NULL,	/* page */
 					0 /*new file size - not used here */ );
 	if (retval < 0)
 		goto end_rmdir;
@@ -888,18 +957,20 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry)
 	/* prevent empty directory from getting lost */
 	add_save_link(&th, inode, 0 /* not truncate */ );
 
-	retval = journal_end(&th, dir->i_sb, jbegin_count);
+	retval = journal_end(&th);
 	reiserfs_check_path(&path);
-      out_rmdir:
+out_rmdir:
 	reiserfs_write_unlock(dir->i_sb);
 	return retval;
 
-      end_rmdir:
-	/* we must release path, because we did not call
-	   reiserfs_cut_from_item, or reiserfs_cut_from_item does not
-	   release path if operation was not complete */
+end_rmdir:
+	/*
+	 * we must release path, because we did not call
+	 * reiserfs_cut_from_item, or reiserfs_cut_from_item does not
+	 * release path if operation was not complete
+	 */
 	pathrelse(&path);
-	err = journal_end(&th, dir->i_sb, jbegin_count);
+	err = journal_end(&th);
 	reiserfs_write_unlock(dir->i_sb);
 	return err ? err : retval;
 }
@@ -918,10 +989,13 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
 
 	inode = dentry->d_inode;
 
-	/* in this transaction we can be doing at max two balancings and update
-	 * two stat datas, we change quotas of the owner of the directory and of
-	 * the owner of the parent directory. The quota structure is possibly
-	 * deleted only on iput => outside of this transaction */
+	/*
+	 * in this transaction we can be doing at max two balancings and
+	 * update two stat datas, we change quotas of the owner of the
+	 * directory and of the owner of the parent directory. The quota
+	 * structure is possibly deleted only on iput => outside of
+	 * this transaction
+	 */
 	jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 2 + 2 +
 	    4 * REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb);
@@ -946,8 +1020,9 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
 	reiserfs_update_inode_transaction(dir);
 
 	if (de.de_objectid != inode->i_ino) {
-		// FIXME: compare key of an object and a key found in the
-		// entry
+		/*
+		 * FIXME: compare key of an object and a key found in the entry
+		 */
 		retval = -EIO;
 		goto end_unlink;
 	}
@@ -968,7 +1043,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
 	savelink = inode->i_nlink;
 
 	retval =
-	    reiserfs_cut_from_item(&th, &path, &(de.de_entry_key), dir, NULL,
+	    reiserfs_cut_from_item(&th, &path, &de.de_entry_key, dir, NULL,
 				   0);
 	if (retval < 0) {
 		inc_nlink(inode);
@@ -985,18 +1060,18 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry)
 		/* prevent file from getting lost */
 		add_save_link(&th, inode, 0 /* not truncate */ );
 
-	retval = journal_end(&th, dir->i_sb, jbegin_count);
+	retval = journal_end(&th);
 	reiserfs_check_path(&path);
 	reiserfs_write_unlock(dir->i_sb);
 	return retval;
 
-      end_unlink:
+end_unlink:
 	pathrelse(&path);
-	err = journal_end(&th, dir->i_sb, jbegin_count);
+	err = journal_end(&th);
 	reiserfs_check_path(&path);
 	if (err)
 		retval = err;
-      out_unlink:
+out_unlink:
 	reiserfs_write_unlock(dir->i_sb);
 	return retval;
 }
@@ -1011,7 +1086,10 @@ static int reiserfs_symlink(struct inode *parent_dir,
 	struct reiserfs_transaction_handle th;
 	struct reiserfs_security_handle security;
 	int mode = S_IFLNK | S_IRWXUGO;
-	/* We need blocks for transaction + (user+group)*(quotas for new inode + update of quota for directory owner) */
+	/*
+	 * We need blocks for transaction + (user+group)*(quotas for
+	 * new inode + update of quota for directory owner)
+	 */
 	int jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 3 +
 	    2 * (REISERFS_QUOTA_INIT_BLOCKS(parent_dir->i_sb) +
@@ -1070,17 +1148,13 @@ static int reiserfs_symlink(struct inode *parent_dir,
 	inode->i_op = &reiserfs_symlink_inode_operations;
 	inode->i_mapping->a_ops = &reiserfs_address_space_operations;
 
-	// must be sure this inode is written with this transaction
-	//
-	//reiserfs_update_sd (&th, inode, READ_BLOCKS);
-
 	retval = reiserfs_add_entry(&th, parent_dir, dentry->d_name.name,
 				    dentry->d_name.len, inode, 1 /*visible */ );
 	if (retval) {
 		int err;
 		drop_nlink(inode);
 		reiserfs_update_sd(&th, inode);
-		err = journal_end(&th, parent_dir->i_sb, jbegin_count);
+		err = journal_end(&th);
 		if (err)
 			retval = err;
 		unlock_new_inode(inode);
@@ -1090,8 +1164,8 @@ static int reiserfs_symlink(struct inode *parent_dir,
 
 	unlock_new_inode(inode);
 	d_instantiate(dentry, inode);
-	retval = journal_end(&th, parent_dir->i_sb, jbegin_count);
-      out_failed:
+	retval = journal_end(&th);
+out_failed:
 	reiserfs_write_unlock(parent_dir->i_sb);
 	return retval;
 }
@@ -1102,7 +1176,10 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir,
 	int retval;
 	struct inode *inode = old_dentry->d_inode;
 	struct reiserfs_transaction_handle th;
-	/* We need blocks for transaction + update of quotas for the owners of the directory */
+	/*
+	 * We need blocks for transaction + update of quotas for
+	 * the owners of the directory
+	 */
 	int jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 3 +
 	    2 * REISERFS_QUOTA_TRANS_BLOCKS(dir->i_sb);
@@ -1111,7 +1188,7 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir,
 
 	reiserfs_write_lock(dir->i_sb);
 	if (inode->i_nlink >= REISERFS_LINK_MAX) {
-		//FIXME: sd_nlink is 32 bit for new files
+		/* FIXME: sd_nlink is 32 bit for new files */
 		reiserfs_write_unlock(dir->i_sb);
 		return -EMLINK;
 	}
@@ -1137,7 +1214,7 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir,
 	if (retval) {
 		int err;
 		drop_nlink(inode);
-		err = journal_end(&th, dir->i_sb, jbegin_count);
+		err = journal_end(&th);
 		reiserfs_write_unlock(dir->i_sb);
 		return err ? err : retval;
 	}
@@ -1147,7 +1224,7 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir,
 
 	ihold(inode);
 	d_instantiate(dentry, inode);
-	retval = journal_end(&th, dir->i_sb, jbegin_count);
+	retval = journal_end(&th);
 	reiserfs_write_unlock(dir->i_sb);
 	return retval;
 }
@@ -1158,9 +1235,9 @@ static int de_still_valid(const char *name, int len,
 {
 	struct reiserfs_dir_entry tmp = *de;
 
-	// recalculate pointer to name and name length
+	/* recalculate pointer to name and name length */
 	set_de_name_and_namelen(&tmp);
-	// FIXME: could check more
+	/* FIXME: could check more */
 	if (tmp.de_namelen != len || memcmp(name, de->de_name, len))
 		return 0;
 	return 1;
@@ -1217,14 +1294,16 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	unsigned long savelink = 1;
 	struct timespec ctime;
 
-	/* three balancings: (1) old name removal, (2) new name insertion
-	   and (3) maybe "save" link insertion
-	   stat data updates: (1) old directory,
-	   (2) new directory and (3) maybe old object stat data (when it is
-	   directory) and (4) maybe stat data of object to which new entry
-	   pointed initially and (5) maybe block containing ".." of
-	   renamed directory
-	   quota updates: two parent directories */
+	/*
+	 * three balancings: (1) old name removal, (2) new name insertion
+	 * and (3) maybe "save" link insertion
+	 * stat data updates: (1) old directory,
+	 * (2) new directory and (3) maybe old object stat data (when it is
+	 * directory) and (4) maybe stat data of object to which new entry
+	 * pointed initially and (5) maybe block containing ".." of
+	 * renamed directory
+	 * quota updates: two parent directories
+	 */
 	jbegin_count =
 	    JOURNAL_PER_BALANCE_CNT * 3 + 5 +
 	    4 * REISERFS_QUOTA_TRANS_BLOCKS(old_dir->i_sb);
@@ -1235,8 +1314,10 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	old_inode = old_dentry->d_inode;
 	new_dentry_inode = new_dentry->d_inode;
 
-	// make sure, that oldname still exists and points to an object we
-	// are going to rename
+	/*
+	 * make sure that oldname still exists and points to an object we
+	 * are going to rename
+	 */
 	old_de.de_gen_number_bit_string = NULL;
 	reiserfs_write_lock(old_dir->i_sb);
 	retval =
@@ -1256,10 +1337,11 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	old_inode_mode = old_inode->i_mode;
 	if (S_ISDIR(old_inode_mode)) {
-		// make sure, that directory being renamed has correct ".."
-		// and that its new parent directory has not too many links
-		// already
-
+		/*
+		 * make sure that directory being renamed has correct ".."
+		 * and that its new parent directory has not too many links
+		 * already
+		 */
 		if (new_dentry_inode) {
 			if (!reiserfs_empty_dir(new_dentry_inode)) {
 				reiserfs_write_unlock(old_dir->i_sb);
@@ -1267,8 +1349,9 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			}
 		}
 
-		/* directory is renamed, its parent directory will be changed,
-		 ** so find ".." entry
+		/*
+		 * directory is renamed, its parent directory will be changed,
+		 * so find ".." entry
 		 */
 		dot_dot_de.de_gen_number_bit_string = NULL;
 		retval =
@@ -1303,7 +1386,7 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 				       "new entry is found, new inode == 0");
 		}
 	} else if (retval) {
-		int err = journal_end(&th, old_dir->i_sb, jbegin_count);
+		int err = journal_end(&th);
 		reiserfs_write_unlock(old_dir->i_sb);
 		return err ? err : retval;
 	}
@@ -1311,8 +1394,9 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	reiserfs_update_inode_transaction(old_dir);
 	reiserfs_update_inode_transaction(new_dir);
 
-	/* this makes it so an fsync on an open fd for the old name will
-	 ** commit the rename operation
+	/*
+	 * this makes it so an fsync on an open fd for the old name will
+	 * commit the rename operation
 	 */
 	reiserfs_update_inode_transaction(old_inode);
 
@@ -1320,38 +1404,45 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		reiserfs_update_inode_transaction(new_dentry_inode);
 
 	while (1) {
-		// look for old name using corresponding entry key (found by reiserfs_find_entry)
+		/*
+		 * look for old name using corresponding entry key
+		 * (found by reiserfs_find_entry)
+		 */
 		if ((retval =
 		     search_by_entry_key(new_dir->i_sb, &old_de.de_entry_key,
 					 &old_entry_path,
 					 &old_de)) != NAME_FOUND) {
 			pathrelse(&old_entry_path);
-			journal_end(&th, old_dir->i_sb, jbegin_count);
+			journal_end(&th);
 			reiserfs_write_unlock(old_dir->i_sb);
 			return -EIO;
 		}
 
-		copy_item_head(&old_entry_ih, get_ih(&old_entry_path));
+		copy_item_head(&old_entry_ih, tp_item_head(&old_entry_path));
 
 		reiserfs_prepare_for_journal(old_inode->i_sb, old_de.de_bh, 1);
 
-		// look for new name by reiserfs_find_entry
+		/* look for new name by reiserfs_find_entry */
 		new_de.de_gen_number_bit_string = NULL;
 		retval =
 		    reiserfs_find_entry(new_dir, new_dentry->d_name.name,
 					new_dentry->d_name.len, &new_entry_path,
 					&new_de);
-		// reiserfs_add_entry should not return IO_ERROR, because it is called with essentially same parameters from
-		// reiserfs_add_entry above, and we'll catch any i/o errors before we get here.
+		/*
+		 * reiserfs_add_entry should not return IO_ERROR,
+		 * because it is called with essentially same parameters from
+		 * reiserfs_add_entry above, and we'll catch any i/o errors
+		 * before we get here.
+		 */
 		if (retval != NAME_FOUND_INVISIBLE && retval != NAME_FOUND) {
 			pathrelse(&new_entry_path);
 			pathrelse(&old_entry_path);
-			journal_end(&th, old_dir->i_sb, jbegin_count);
+			journal_end(&th);
 			reiserfs_write_unlock(old_dir->i_sb);
 			return -EIO;
 		}
 
-		copy_item_head(&new_entry_ih, get_ih(&new_entry_path));
+		copy_item_head(&new_entry_ih, tp_item_head(&new_entry_path));
 
 		reiserfs_prepare_for_journal(old_inode->i_sb, new_de.de_bh, 1);
 
@@ -1364,28 +1455,32 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 				pathrelse(&dot_dot_entry_path);
 				pathrelse(&new_entry_path);
 				pathrelse(&old_entry_path);
-				journal_end(&th, old_dir->i_sb, jbegin_count);
+				journal_end(&th);
 				reiserfs_write_unlock(old_dir->i_sb);
 				return -EIO;
 			}
 			copy_item_head(&dot_dot_ih,
-				       get_ih(&dot_dot_entry_path));
-			// node containing ".." gets into transaction
+				       tp_item_head(&dot_dot_entry_path));
+			/* node containing ".." gets into transaction */
 			reiserfs_prepare_for_journal(old_inode->i_sb,
 						     dot_dot_de.de_bh, 1);
 		}
-		/* we should check seals here, not do
-		   this stuff, yes? Then, having
-		   gathered everything into RAM we
-		   should lock the buffers, yes?  -Hans */
-		/* probably.  our rename needs to hold more
-		 ** than one path at once.  The seals would
-		 ** have to be written to deal with multi-path
-		 ** issues -chris
+		/*
+		 * we should check seals here, not do
+		 * this stuff, yes? Then, having
+		 * gathered everything into RAM we
+		 * should lock the buffers, yes?  -Hans
+		 */
+		/*
+		 * probably.  our rename needs to hold more
+		 * than one path at once.  The seals would
+		 * have to be written to deal with multi-path
+		 * issues -chris
 		 */
-		/* sanity checking before doing the rename - avoid races many
-		 ** of the above checks could have scheduled.  We have to be
-		 ** sure our items haven't been shifted by another process.
+		/*
+		 * sanity checking before doing the rename - avoid races many
+		 * of the above checks could have scheduled.  We have to be
+		 * sure our items haven't been shifted by another process.
 		 */
 		if (item_moved(&new_entry_ih, &new_entry_path) ||
 		    !entry_points_to_object(new_dentry->d_name.name,
@@ -1430,24 +1525,28 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		break;
 	}
 
-	/* ok, all the changes can be done in one fell swoop when we
-	   have claimed all the buffers needed. */
+	/*
+	 * ok, all the changes can be done in one fell swoop when we
+	 * have claimed all the buffers needed.
+	 */
 
 	mark_de_visible(new_de.de_deh + new_de.de_entry_num);
 	set_ino_in_dir_entry(&new_de, INODE_PKEY(old_inode));
-	journal_mark_dirty(&th, old_dir->i_sb, new_de.de_bh);
+	journal_mark_dirty(&th, new_de.de_bh);
 
 	mark_de_hidden(old_de.de_deh + old_de.de_entry_num);
-	journal_mark_dirty(&th, old_dir->i_sb, old_de.de_bh);
+	journal_mark_dirty(&th, old_de.de_bh);
 	ctime = CURRENT_TIME_SEC;
 	old_dir->i_ctime = old_dir->i_mtime = ctime;
 	new_dir->i_ctime = new_dir->i_mtime = ctime;
-	/* thanks to Alex Adriaanse <alex_a@caltech.edu> for patch which adds ctime update of
-	   renamed object */
+	/*
+	 * thanks to Alex Adriaanse <alex_a@caltech.edu> for patch
+	 * which adds ctime update of renamed object
+	 */
 	old_inode->i_ctime = ctime;
 
 	if (new_dentry_inode) {
-		// adjust link number of the victim
+		/* adjust link number of the victim */
 		if (S_ISDIR(new_dentry_inode->i_mode)) {
 			clear_nlink(new_dentry_inode);
 		} else {
@@ -1460,25 +1559,32 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (S_ISDIR(old_inode_mode)) {
 		/* adjust ".." of renamed directory */
 		set_ino_in_dir_entry(&dot_dot_de, INODE_PKEY(new_dir));
-		journal_mark_dirty(&th, new_dir->i_sb, dot_dot_de.de_bh);
+		journal_mark_dirty(&th, dot_dot_de.de_bh);
 
+		/*
+		 * there (in new_dir) was no directory, so it got new link
+		 * (".."  of renamed directory)
+		 */
 		if (!new_dentry_inode)
-			/* there (in new_dir) was no directory, so it got new link
-			   (".."  of renamed directory) */
 			INC_DIR_INODE_NLINK(new_dir);
 
 		/* old directory lost one link - ".. " of renamed directory */
 		DEC_DIR_INODE_NLINK(old_dir);
 	}
-	// looks like in 2.3.99pre3 brelse is atomic. so we can use pathrelse
+	/*
+	 * looks like in 2.3.99pre3 brelse is atomic.
+	 * so we can use pathrelse
+	 */
 	pathrelse(&new_entry_path);
 	pathrelse(&dot_dot_entry_path);
 
-	// FIXME: this reiserfs_cut_from_item's return value may screw up
-	// anybody, but it will panic if will not be able to find the
-	// entry. This needs one more clean up
+	/*
+	 * FIXME: this reiserfs_cut_from_item's return value may screw up
+	 * anybody, but it will panic if will not be able to find the
+	 * entry. This needs one more clean up
+	 */
 	if (reiserfs_cut_from_item
-	    (&th, &old_entry_path, &(old_de.de_entry_key), old_dir, NULL,
+	    (&th, &old_entry_path, &old_de.de_entry_key, old_dir, NULL,
 	     0) < 0)
 		reiserfs_error(old_dir->i_sb, "vs-7060",
 			       "couldn't not cut old name. Fsck later?");
@@ -1496,16 +1602,13 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		reiserfs_update_sd(&th, new_dentry_inode);
 	}
 
-	retval = journal_end(&th, old_dir->i_sb, jbegin_count);
+	retval = journal_end(&th);
 	reiserfs_write_unlock(old_dir->i_sb);
 	return retval;
 }
 
-/*
- * directories can handle most operations...
- */
+/* directories can handle most operations...  */
 const struct inode_operations reiserfs_dir_inode_operations = {
-	//&reiserfs_dir_operations,   /* default_file_ops */
 	.create = reiserfs_create,
 	.lookup = reiserfs_lookup,
 	.link = reiserfs_link,
diff --git a/fs/reiserfs/objectid.c b/fs/reiserfs/objectid.c
index f732d6a5251..99a5d5dae46 100644
--- a/fs/reiserfs/objectid.c
+++ b/fs/reiserfs/objectid.c
@@ -7,7 +7,7 @@
 #include <linux/time.h>
 #include "reiserfs.h"
 
-// find where objectid map starts
+/* find where objectid map starts */
 #define objectid_map(s,rs) (old_format_only (s) ? \
                          (__le32 *)((struct reiserfs_super_block_v1 *)(rs) + 1) :\
 			 (__le32 *)((rs) + 1))
@@ -20,7 +20,7 @@ static void check_objectid_map(struct super_block *s, __le32 * map)
 		reiserfs_panic(s, "vs-15010", "map corrupted: %lx",
 			       (long unsigned int)le32_to_cpu(map[0]));
 
-	// FIXME: add something else here
+	/* FIXME: add something else here */
 }
 
 #else
@@ -29,19 +29,21 @@ static void check_objectid_map(struct super_block *s, __le32 * map)
 }
 #endif
 
-/* When we allocate objectids we allocate the first unused objectid.
-   Each sequence of objectids in use (the odd sequences) is followed
-   by a sequence of objectids not in use (the even sequences).  We
-   only need to record the last objectid in each of these sequences
-   (both the odd and even sequences) in order to fully define the
-   boundaries of the sequences.  A consequence of allocating the first
-   objectid not in use is that under most conditions this scheme is
-   extremely compact.  The exception is immediately after a sequence
-   of operations which deletes a large number of objects of
-   non-sequential objectids, and even then it will become compact
-   again as soon as more objects are created.  Note that many
-   interesting optimizations of layout could result from complicating
-   objectid assignment, but we have deferred making them for now. */
+/*
+ * When we allocate objectids we allocate the first unused objectid.
+ * Each sequence of objectids in use (the odd sequences) is followed
+ * by a sequence of objectids not in use (the even sequences).  We
+ * only need to record the last objectid in each of these sequences
+ * (both the odd and even sequences) in order to fully define the
+ * boundaries of the sequences.  A consequence of allocating the first
+ * objectid not in use is that under most conditions this scheme is
+ * extremely compact.  The exception is immediately after a sequence
+ * of operations which deletes a large number of objects of
+ * non-sequential objectids, and even then it will become compact
+ * again as soon as more objects are created.  Note that many
+ * interesting optimizations of layout could result from complicating
+ * objectid assignment, but we have deferred making them for now.
+ */
 
 /* get unique object identifier */
 __u32 reiserfs_get_unused_objectid(struct reiserfs_transaction_handle *th)
@@ -64,26 +66,30 @@ __u32 reiserfs_get_unused_objectid(struct reiserfs_transaction_handle *th)
 		return 0;
 	}
 
-	/* This incrementation allocates the first unused objectid. That
-	   is to say, the first entry on the objectid map is the first
-	   unused objectid, and by incrementing it we use it.  See below
-	   where we check to see if we eliminated a sequence of unused
-	   objectids.... */
+	/*
+	 * This incrementation allocates the first unused objectid. That
+	 * is to say, the first entry on the objectid map is the first
+	 * unused objectid, and by incrementing it we use it.  See below
+	 * where we check to see if we eliminated a sequence of unused
+	 * objectids....
+	 */
 	map[1] = cpu_to_le32(unused_objectid + 1);
 
-	/* Now we check to see if we eliminated the last remaining member of
-	   the first even sequence (and can eliminate the sequence by
-	   eliminating its last objectid from oids), and can collapse the
-	   first two odd sequences into one sequence.  If so, then the net
-	   result is to eliminate a pair of objectids from oids.  We do this
-	   by shifting the entire map to the left. */
+	/*
+	 * Now we check to see if we eliminated the last remaining member of
+	 * the first even sequence (and can eliminate the sequence by
+	 * eliminating its last objectid from oids), and can collapse the
+	 * first two odd sequences into one sequence.  If so, then the net
+	 * result is to eliminate a pair of objectids from oids.  We do this
+	 * by shifting the entire map to the left.
+	 */
 	if (sb_oid_cursize(rs) > 2 && map[1] == map[2]) {
 		memmove(map + 1, map + 3,
 			(sb_oid_cursize(rs) - 3) * sizeof(__u32));
 		set_sb_oid_cursize(rs, sb_oid_cursize(rs) - 2);
 	}
 
-	journal_mark_dirty(th, s, SB_BUFFER_WITH_SB(s));
+	journal_mark_dirty(th, SB_BUFFER_WITH_SB(s));
 	return unused_objectid;
 }
 
@@ -97,30 +103,33 @@ void reiserfs_release_objectid(struct reiserfs_transaction_handle *th,
 	int i = 0;
 
 	BUG_ON(!th->t_trans_id);
-	//return;
+	/*return; */
 	check_objectid_map(s, map);
 
 	reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
-	journal_mark_dirty(th, s, SB_BUFFER_WITH_SB(s));
-
-	/* start at the beginning of the objectid map (i = 0) and go to
-	   the end of it (i = disk_sb->s_oid_cursize).  Linear search is
-	   what we use, though it is possible that binary search would be
-	   more efficient after performing lots of deletions (which is
-	   when oids is large.)  We only check even i's. */
+	journal_mark_dirty(th, SB_BUFFER_WITH_SB(s));
+
+	/*
+	 * start at the beginning of the objectid map (i = 0) and go to
+	 * the end of it (i = disk_sb->s_oid_cursize).  Linear search is
+	 * what we use, though it is possible that binary search would be
+	 * more efficient after performing lots of deletions (which is
+	 * when oids is large.)  We only check even i's.
+	 */
 	while (i < sb_oid_cursize(rs)) {
 		if (objectid_to_release == le32_to_cpu(map[i])) {
 			/* This incrementation unallocates the objectid. */
-			//map[i]++;
 			le32_add_cpu(&map[i], 1);
 
-			/* Did we unallocate the last member of an odd sequence, and can shrink oids? */
+			/*
+			 * Did we unallocate the last member of an
+			 * odd sequence, and can shrink oids?
+			 */
 			if (map[i] == map[i + 1]) {
 				/* shrink objectid map */
 				memmove(map + i, map + i + 2,
 					(sb_oid_cursize(rs) - i -
 					 2) * sizeof(__u32));
-				//disk_sb->s_oid_cursize -= 2;
 				set_sb_oid_cursize(rs, sb_oid_cursize(rs) - 2);
 
 				RFALSE(sb_oid_cursize(rs) < 2 ||
@@ -135,14 +144,19 @@ void reiserfs_release_objectid(struct reiserfs_transaction_handle *th,
 		    objectid_to_release < le32_to_cpu(map[i + 1])) {
 			/* size of objectid map is not changed */
 			if (objectid_to_release + 1 == le32_to_cpu(map[i + 1])) {
-				//objectid_map[i+1]--;
 				le32_add_cpu(&map[i + 1], -1);
 				return;
 			}
 
-			/* JDM comparing two little-endian values for equality -- safe */
+			/*
+			 * JDM comparing two little-endian values for
+			 * equality -- safe
+			 */
+			/*
+			 * objectid map must be expanded, but
+			 * there is no space
+			 */
 			if (sb_oid_cursize(rs) == sb_oid_maxsize(rs)) {
-				/* objectid map must be expanded, but there is no space */
 				PROC_INFO_INC(s, leaked_oid);
 				return;
 			}
@@ -178,8 +192,9 @@ int reiserfs_convert_objectid_map_v1(struct super_block *s)
 	new_objectid_map = (__le32 *) (disk_sb + 1);
 
 	if (cur_size > new_size) {
-		/* mark everyone used that was listed as free at the end of the objectid
-		 ** map
+		/*
+		 * mark everyone used that was listed as free at
+		 * the end of the objectid map
 		 */
 		objectid_map[new_size - 1] = objectid_map[cur_size - 1];
 		set_sb_oid_cursize(disk_sb, new_size);
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index 54944d5a4a6..c9b47e91baf 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -172,18 +172,19 @@ static char *is_there_reiserfs_struct(char *fmt, int *what)
 	return k;
 }
 
-/* debugging reiserfs we used to print out a lot of different
-   variables, like keys, item headers, buffer heads etc. Values of
-   most fields matter. So it took a long time just to write
-   appropriative printk. With this reiserfs_warning you can use format
-   specification for complex structures like you used to do with
-   printfs for integers, doubles and pointers. For instance, to print
-   out key structure you have to write just:
-   reiserfs_warning ("bad key %k", key);
-   instead of
-   printk ("bad key %lu %lu %lu %lu", key->k_dir_id, key->k_objectid,
-           key->k_offset, key->k_uniqueness);
-*/
+/*
+ * debugging reiserfs we used to print out a lot of different
+ * variables, like keys, item headers, buffer heads etc. Values of
+ * most fields matter. So it took a long time just to write
+ * appropriative printk. With this reiserfs_warning you can use format
+ * specification for complex structures like you used to do with
+ * printfs for integers, doubles and pointers. For instance, to print
+ * out key structure you have to write just:
+ * reiserfs_warning ("bad key %k", key);
+ * instead of
+ * printk ("bad key %lu %lu %lu %lu", key->k_dir_id, key->k_objectid,
+ *         key->k_offset, key->k_uniqueness);
+ */
 static DEFINE_SPINLOCK(error_lock);
 static void prepare_error_buf(const char *fmt, va_list args)
 {
@@ -243,15 +244,16 @@ static void prepare_error_buf(const char *fmt, va_list args)
 
 }
 
-/* in addition to usual conversion specifiers this accepts reiserfs
-   specific conversion specifiers:
-   %k to print little endian key,
-   %K to print cpu key,
-   %h to print item_head,
-   %t to print directory entry
-   %z to print block head (arg must be struct buffer_head *
-   %b to print buffer_head
-*/
+/*
+ * in addition to usual conversion specifiers this accepts reiserfs
+ * specific conversion specifiers:
+ * %k to print little endian key,
+ * %K to print cpu key,
+ * %h to print item_head,
+ * %t to print directory entry
+ * %z to print block head (arg must be struct buffer_head *
+ * %b to print buffer_head
+ */
 
 #define do_reiserfs_warning(fmt)\
 {\
@@ -304,50 +306,52 @@ void reiserfs_debug(struct super_block *s, int level, const char *fmt, ...)
 #endif
 }
 
-/* The format:
-
-           maintainer-errorid: [function-name:] message
-
-    where errorid is unique to the maintainer and function-name is
-    optional, is recommended, so that anyone can easily find the bug
-    with a simple grep for the short to type string
-    maintainer-errorid.  Don't bother with reusing errorids, there are
-    lots of numbers out there.
-
-    Example:
-
-    reiserfs_panic(
-	p_sb, "reiser-29: reiserfs_new_blocknrs: "
-	"one of search_start or rn(%d) is equal to MAX_B_NUM,"
-	"which means that we are optimizing location based on the bogus location of a temp buffer (%p).",
-	rn, bh
-    );
-
-    Regular panic()s sometimes clear the screen before the message can
-    be read, thus the need for the while loop.
-
-    Numbering scheme for panic used by Vladimir and Anatoly( Hans completely ignores this scheme, and considers it
-    pointless complexity):
-
-    panics in reiserfs.h have numbers from 1000 to 1999
-    super.c				        2000 to 2999
-    preserve.c (unused)			    3000 to 3999
-    bitmap.c				    4000 to 4999
-    stree.c				        5000 to 5999
-    prints.c				    6000 to 6999
-    namei.c                     7000 to 7999
-    fix_nodes.c                 8000 to 8999
-    dir.c                       9000 to 9999
-	lbalance.c					10000 to 10999
-	ibalance.c		11000 to 11999 not ready
-	do_balan.c		12000 to 12999
-	inode.c			13000 to 13999
-	file.c			14000 to 14999
-    objectid.c                       15000 - 15999
-    buffer.c                         16000 - 16999
-    symlink.c                        17000 - 17999
-
-   .  */
+/*
+ * The format:
+ *
+ *          maintainer-errorid: [function-name:] message
+ *
+ *   where errorid is unique to the maintainer and function-name is
+ *   optional, is recommended, so that anyone can easily find the bug
+ *   with a simple grep for the short to type string
+ *   maintainer-errorid.  Don't bother with reusing errorids, there are
+ *   lots of numbers out there.
+ *
+ *   Example:
+ *
+ *   reiserfs_panic(
+ *     p_sb, "reiser-29: reiserfs_new_blocknrs: "
+ *     "one of search_start or rn(%d) is equal to MAX_B_NUM,"
+ *     "which means that we are optimizing location based on the "
+ *     "bogus location of a temp buffer (%p).",
+ *     rn, bh
+ *   );
+ *
+ *   Regular panic()s sometimes clear the screen before the message can
+ *   be read, thus the need for the while loop.
+ *
+ *   Numbering scheme for panic used by Vladimir and Anatoly( Hans completely
+ *   ignores this scheme, and considers it pointless complexity):
+ *
+ *   panics in reiserfs_fs.h have numbers from 1000 to 1999
+ *   super.c			2000 to 2999
+ *   preserve.c (unused)	3000 to 3999
+ *   bitmap.c			4000 to 4999
+ *   stree.c			5000 to 5999
+ *   prints.c			6000 to 6999
+ *   namei.c			7000 to 7999
+ *   fix_nodes.c		8000 to 8999
+ *   dir.c			9000 to 9999
+ *   lbalance.c			10000 to 10999
+ *   ibalance.c			11000 to 11999 not ready
+ *   do_balan.c			12000 to 12999
+ *   inode.c			13000 to 13999
+ *   file.c			14000 to 14999
+ *   objectid.c			15000 - 15999
+ *   buffer.c			16000 - 16999
+ *   symlink.c			17000 - 17999
+ *
+ *  .  */
 
 void __reiserfs_panic(struct super_block *sb, const char *id,
 		      const char *function, const char *fmt, ...)
@@ -411,9 +415,11 @@ void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...)
 	reiserfs_abort_journal(sb, errno);
 }
 
-/* this prints internal nodes (4 keys/items in line) (dc_number,
-   dc_size)[k_dirid, k_objectid, k_offset, k_uniqueness](dc_number,
-   dc_size)...*/
+/*
+ * this prints internal nodes (4 keys/items in line) (dc_number,
+ * dc_size)[k_dirid, k_objectid, k_offset, k_uniqueness](dc_number,
+ * dc_size)...
+ */
 static int print_internal(struct buffer_head *bh, int first, int last)
 {
 	struct reiserfs_key *key;
@@ -439,7 +445,7 @@ static int print_internal(struct buffer_head *bh, int first, int last)
 	dc = B_N_CHILD(bh, from);
 	reiserfs_printk("PTR %d: %y ", from, dc);
 
-	for (i = from, key = B_N_PDELIM_KEY(bh, from), dc++; i < to;
+	for (i = from, key = internal_key(bh, from), dc++; i < to;
 	     i++, key++, dc++) {
 		reiserfs_printk("KEY %d: %k PTR %d: %y ", i, key, i + 1, dc);
 		if (i && i % 4 == 0)
@@ -463,7 +469,7 @@ static int print_leaf(struct buffer_head *bh, int print_mode, int first,
 	check_leaf(bh);
 
 	blkh = B_BLK_HEAD(bh);
-	ih = B_N_PITEM_HEAD(bh, 0);
+	ih = item_head(bh, 0);
 	nr = blkh_nr_item(blkh);
 
 	printk
@@ -496,7 +502,7 @@ static int print_leaf(struct buffer_head *bh, int print_mode, int first,
 		    ("-------------------------------------------------------------------------------\n");
 		reiserfs_printk("|%2d| %h |\n", i, ih);
 		if (print_mode & PRINT_LEAF_ITEMS)
-			op_print_item(ih, B_I_PITEM(bh, ih));
+			op_print_item(ih, ih_item_body(bh, ih));
 	}
 
 	printk
@@ -543,9 +549,11 @@ static int print_super_block(struct buffer_head *bh)
 	printk("Block count %u\n", sb_block_count(rs));
 	printk("Blocksize %d\n", sb_blocksize(rs));
 	printk("Free blocks %u\n", sb_free_blocks(rs));
-	// FIXME: this would be confusing if
-	// someone stores reiserfs super block in some data block ;)
+	/*
+	 * FIXME: this would be confusing if
+	 * someone stores reiserfs super block in some data block ;)
 //    skipped = (bh->b_blocknr * bh->b_size) / sb_blocksize(rs);
+	 */
 	skipped = bh->b_blocknr;
 	data_blocks = sb_block_count(rs) - skipped - 1 - sb_bmap_nr(rs) -
 	    (!is_reiserfs_jr(rs) ? sb_jp_journal_size(rs) +
@@ -581,8 +589,8 @@ static int print_desc_block(struct buffer_head *bh)
 
 	return 0;
 }
-
-void print_block(struct buffer_head *bh, ...)	//int print_mode, int first, int last)
+/* ..., int print_mode, int first, int last) */
+void print_block(struct buffer_head *bh, ...)
 {
 	va_list args;
 	int mode, first, last;
@@ -644,11 +652,11 @@ void store_print_tb(struct tree_balance *tb)
 			"* %d * %3lld(%2d) * %3lld(%2d) * %3lld(%2d) * %5lld * %5lld * %5lld * %5lld * %5lld *\n",
 			h,
 			(tbSh) ? (long long)(tbSh->b_blocknr) : (-1LL),
-			(tbSh) ? atomic_read(&(tbSh->b_count)) : -1,
+			(tbSh) ? atomic_read(&tbSh->b_count) : -1,
 			(tb->L[h]) ? (long long)(tb->L[h]->b_blocknr) : (-1LL),
-			(tb->L[h]) ? atomic_read(&(tb->L[h]->b_count)) : -1,
+			(tb->L[h]) ? atomic_read(&tb->L[h]->b_count) : -1,
 			(tb->R[h]) ? (long long)(tb->R[h]->b_blocknr) : (-1LL),
-			(tb->R[h]) ? atomic_read(&(tb->R[h]->b_count)) : -1,
+			(tb->R[h]) ? atomic_read(&tb->R[h]->b_count) : -1,
 			(tbFh) ? (long long)(tbFh->b_blocknr) : (-1LL),
 			(tb->FL[h]) ? (long long)(tb->FL[h]->
 						  b_blocknr) : (-1LL),
@@ -665,9 +673,9 @@ void store_print_tb(struct tree_balance *tb)
 		"* h * size * ln * lb * rn * rb * blkn * s0 * s1 * s1b * s2 * s2b * curb * lk * rk *\n"
 		"* 0 * %4d * %2d * %2d * %2d * %2d * %4d * %2d * %2d * %3d * %2d * %3d * %4d * %2d * %2d *\n",
 		tb->insert_size[0], tb->lnum[0], tb->lbytes, tb->rnum[0],
-		tb->rbytes, tb->blknum[0], tb->s0num, tb->s1num, tb->s1bytes,
-		tb->s2num, tb->s2bytes, tb->cur_blknum, tb->lkey[0],
-		tb->rkey[0]);
+		tb->rbytes, tb->blknum[0], tb->s0num, tb->snum[0],
+		tb->sbytes[0], tb->snum[1], tb->sbytes[1],
+		tb->cur_blknum, tb->lkey[0], tb->rkey[0]);
 
 	/* this prints balance parameters for non-leaf levels */
 	h = 0;
@@ -690,7 +698,7 @@ void store_print_tb(struct tree_balance *tb)
 			"%p (%llu %d)%s", tb->FEB[i],
 			tb->FEB[i] ? (unsigned long long)tb->FEB[i]->
 			b_blocknr : 0ULL,
-			tb->FEB[i] ? atomic_read(&(tb->FEB[i]->b_count)) : 0,
+			tb->FEB[i] ? atomic_read(&tb->FEB[i]->b_count) : 0,
 			(i == ARRAY_SIZE(tb->FEB) - 1) ? "\n" : ", ");
 
 	sprintf(print_tb_buf + strlen(print_tb_buf),
@@ -744,8 +752,8 @@ void check_leaf(struct buffer_head *bh)
 	if (!bh)
 		return;
 	check_leaf_block_head(bh);
-	for (i = 0, ih = B_N_PITEM_HEAD(bh, 0); i < B_NR_ITEMS(bh); i++, ih++)
-		op_check_item(ih, B_I_PITEM(bh, ih));
+	for (i = 0, ih = item_head(bh, 0); i < B_NR_ITEMS(bh); i++, ih++)
+		op_check_item(ih, ih_item_body(bh, ih));
 }
 
 void check_internal(struct buffer_head *bh)
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 83d4eac8059..bf53888c7f5 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -1,5 +1,6 @@
 /*
- * Copyright 1996, 1997, 1998 Hans Reiser, see reiserfs/README for licensing and copyright details
+ * Copyright 1996, 1997, 1998 Hans Reiser, see reiserfs/README for
+ * licensing and copyright details
  */
 
 #include <linux/reiserfs_fs.h>
@@ -23,52 +24,73 @@
 
 struct reiserfs_journal_list;
 
-/** bitmasks for i_flags field in reiserfs-specific part of inode */
+/* bitmasks for i_flags field in reiserfs-specific part of inode */
 typedef enum {
-    /** this says what format of key do all items (but stat data) of
-      an object have.  If this is set, that format is 3.6 otherwise
-      - 3.5 */
+	/*
+	 * this says what format of key do all items (but stat data) of
+	 * an object have.  If this is set, that format is 3.6 otherwise - 3.5
+	 */
 	i_item_key_version_mask = 0x0001,
-    /** If this is unset, object has 3.5 stat data, otherwise, it has
-      3.6 stat data with 64bit size, 32bit nlink etc. */
+
+	/*
+	 * If this is unset, object has 3.5 stat data, otherwise,
+	 * it has 3.6 stat data with 64bit size, 32bit nlink etc.
+	 */
 	i_stat_data_version_mask = 0x0002,
-    /** file might need tail packing on close */
+
+	/* file might need tail packing on close */
 	i_pack_on_close_mask = 0x0004,
-    /** don't pack tail of file */
+
+	/* don't pack tail of file */
 	i_nopack_mask = 0x0008,
-    /** If those is set, "safe link" was created for this file during
-      truncate or unlink. Safe link is used to avoid leakage of disk
-      space on crash with some files open, but unlinked. */
+
+	/*
+	 * If either of these are set, "safe link" was created for this
+	 * file during truncate or unlink. Safe link is used to avoid
+	 * leakage of disk space on crash with some files open, but unlinked.
+	 */
 	i_link_saved_unlink_mask = 0x0010,
 	i_link_saved_truncate_mask = 0x0020,
+
 	i_has_xattr_dir = 0x0040,
 	i_data_log = 0x0080,
 } reiserfs_inode_flags;
 
 struct reiserfs_inode_info {
 	__u32 i_key[4];		/* key is still 4 32 bit integers */
-    /** transient inode flags that are never stored on disk. Bitmasks
-      for this field are defined above. */
+
+	/*
+	 * transient inode flags that are never stored on disk. Bitmasks
+	 * for this field are defined above.
+	 */
 	__u32 i_flags;
 
-	__u32 i_first_direct_byte;	// offset of first byte stored in direct item.
+	/* offset of first byte stored in direct item. */
+	__u32 i_first_direct_byte;
 
 	/* copy of persistent inode flags read from sd_attrs. */
 	__u32 i_attrs;
 
-	int i_prealloc_block;	/* first unused block of a sequence of unused blocks */
+	/* first unused block of a sequence of unused blocks */
+	int i_prealloc_block;
 	int i_prealloc_count;	/* length of that sequence */
-	struct list_head i_prealloc_list;	/* per-transaction list of inodes which
-						 * have preallocated blocks */
 
-	unsigned new_packing_locality:1;	/* new_packig_locality is created; new blocks
-						 * for the contents of this directory should be
-						 * displaced */
+	/* per-transaction list of inodes which  have preallocated blocks */
+	struct list_head i_prealloc_list;
 
-	/* we use these for fsync or O_SYNC to decide which transaction
-	 ** needs to be committed in order for this inode to be properly
-	 ** flushed */
+	/*
+	 * new_packing_locality is created; new blocks for the contents
+	 * of this directory should be displaced
+	 */
+	unsigned new_packing_locality:1;
+
+	/*
+	 * we use these for fsync or O_SYNC to decide which transaction
+	 * needs to be committed in order for this inode to be properly
+	 * flushed
+	 */
 	unsigned int i_trans_id;
+
 	struct reiserfs_journal_list *i_jl;
 	atomic_t openers;
 	struct mutex tailpack;
@@ -82,9 +104,10 @@ typedef enum {
 	reiserfs_attrs_cleared = 0x00000001,
 } reiserfs_super_block_flags;
 
-/* struct reiserfs_super_block accessors/mutators
- * since this is a disk structure, it will always be in
- * little endian format. */
+/*
+ * struct reiserfs_super_block accessors/mutators since this is a disk
+ * structure, it will always be in little endian format.
+ */
 #define sb_block_count(sbp)         (le32_to_cpu((sbp)->s_v1.s_block_count))
 #define set_sb_block_count(sbp,v)   ((sbp)->s_v1.s_block_count = cpu_to_le32(v))
 #define sb_free_blocks(sbp)         (le32_to_cpu((sbp)->s_v1.s_free_blocks))
@@ -152,48 +175,61 @@ typedef enum {
 
 /* LOGGING -- */
 
-/* These all interelate for performance.
-**
-** If the journal block count is smaller than n transactions, you lose speed.
-** I don't know what n is yet, I'm guessing 8-16.
-**
-** typical transaction size depends on the application, how often fsync is
-** called, and how many metadata blocks you dirty in a 30 second period.
-** The more small files (<16k) you use, the larger your transactions will
-** be.
-**
-** If your journal fills faster than dirty buffers get flushed to disk, it must flush them before allowing the journal
-** to wrap, which slows things down.  If you need high speed meta data updates, the journal should be big enough
-** to prevent wrapping before dirty meta blocks get to disk.
-**
-** If the batch max is smaller than the transaction max, you'll waste space at the end of the journal
-** because journal_end sets the next transaction to start at 0 if the next transaction has any chance of wrapping.
-**
-** The large the batch max age, the better the speed, and the more meta data changes you'll lose after a crash.
-**
-*/
+/*
+ * These all interelate for performance.
+ *
+ * If the journal block count is smaller than n transactions, you lose speed.
+ * I don't know what n is yet, I'm guessing 8-16.
+ *
+ * typical transaction size depends on the application, how often fsync is
+ * called, and how many metadata blocks you dirty in a 30 second period.
+ * The more small files (<16k) you use, the larger your transactions will
+ * be.
+ *
+ * If your journal fills faster than dirty buffers get flushed to disk, it
+ * must flush them before allowing the journal to wrap, which slows things
+ * down.  If you need high speed meta data updates, the journal should be
+ * big enough to prevent wrapping before dirty meta blocks get to disk.
+ *
+ * If the batch max is smaller than the transaction max, you'll waste space
+ * at the end of the journal because journal_end sets the next transaction
+ * to start at 0 if the next transaction has any chance of wrapping.
+ *
+ * The large the batch max age, the better the speed, and the more meta
+ * data changes you'll lose after a crash.
+ */
 
 /* don't mess with these for a while */
-				/* we have a node size define somewhere in reiserfs_fs.h. -Hans */
+/* we have a node size define somewhere in reiserfs_fs.h. -Hans */
 #define JOURNAL_BLOCK_SIZE  4096	/* BUG gotta get rid of this */
 #define JOURNAL_MAX_CNODE   1500	/* max cnodes to allocate. */
 #define JOURNAL_HASH_SIZE 8192
-#define JOURNAL_NUM_BITMAPS 5	/* number of copies of the bitmaps to have floating.  Must be >= 2 */
-
-/* One of these for every block in every transaction
-** Each one is in two hash tables.  First, a hash of the current transaction, and after journal_end, a
-** hash of all the in memory transactions.
-** next and prev are used by the current transaction (journal_hash).
-** hnext and hprev are used by journal_list_hash.  If a block is in more than one transaction, the journal_list_hash
-** links it in multiple times.  This allows flush_journal_list to remove just the cnode belonging
-** to a given transaction.
-*/
+
+/* number of copies of the bitmaps to have floating.  Must be >= 2 */
+#define JOURNAL_NUM_BITMAPS 5
+
+/*
+ * One of these for every block in every transaction
+ * Each one is in two hash tables.  First, a hash of the current transaction,
+ * and after journal_end, a hash of all the in memory transactions.
+ * next and prev are used by the current transaction (journal_hash).
+ * hnext and hprev are used by journal_list_hash.  If a block is in more
+ * than one transaction, the journal_list_hash links it in multiple times.
+ * This allows flush_journal_list to remove just the cnode belonging to a
+ * given transaction.
+ */
 struct reiserfs_journal_cnode {
 	struct buffer_head *bh;	/* real buffer head */
 	struct super_block *sb;	/* dev of real buffer head */
-	__u32 blocknr;		/* block number of real buffer head, == 0 when buffer on disk */
+
+	/* block number of real buffer head, == 0 when buffer on disk */
+	__u32 blocknr;
+
 	unsigned long state;
-	struct reiserfs_journal_list *jlist;	/* journal list this cnode lives in */
+
+	/* journal list this cnode lives in */
+	struct reiserfs_journal_list *jlist;
+
 	struct reiserfs_journal_cnode *next;	/* next in transaction list */
 	struct reiserfs_journal_cnode *prev;	/* prev in transaction list */
 	struct reiserfs_journal_cnode *hprev;	/* prev in hash list */
@@ -212,18 +248,22 @@ struct reiserfs_list_bitmap {
 };
 
 /*
-** one of these for each transaction.  The most important part here is the j_realblock.
-** this list of cnodes is used to hash all the blocks in all the commits, to mark all the
-** real buffer heads dirty once all the commits hit the disk,
-** and to make sure every real block in a transaction is on disk before allowing the log area
-** to be overwritten */
+ * one of these for each transaction.  The most important part here is the
+ * j_realblock.  this list of cnodes is used to hash all the blocks in all
+ * the commits, to mark all the real buffer heads dirty once all the commits
+ * hit the disk, and to make sure every real block in a transaction is on
+ * disk before allowing the log area to be overwritten
+ */
 struct reiserfs_journal_list {
 	unsigned long j_start;
 	unsigned long j_state;
 	unsigned long j_len;
 	atomic_t j_nonzerolen;
 	atomic_t j_commit_left;
-	atomic_t j_older_commits_done;	/* all commits older than this on disk */
+
+	/* all commits older than this on disk */
+	atomic_t j_older_commits_done;
+
 	struct mutex j_commit_mutex;
 	unsigned int j_trans_id;
 	time_t j_timestamp;
@@ -234,11 +274,15 @@ struct reiserfs_journal_list {
 	/* time ordered list of all active transactions */
 	struct list_head j_list;
 
-	/* time ordered list of all transactions we haven't tried to flush yet */
+	/*
+	 * time ordered list of all transactions we haven't tried
+	 * to flush yet
+	 */
 	struct list_head j_working_list;
 
 	/* list of tail conversion targets in need of flush before commit */
 	struct list_head j_tail_bh_list;
+
 	/* list of data=ordered buffers in need of flush before commit */
 	struct list_head j_bh_list;
 	int j_refcount;
@@ -246,46 +290,83 @@ struct reiserfs_journal_list {
 
 struct reiserfs_journal {
 	struct buffer_head **j_ap_blocks;	/* journal blocks on disk */
-	struct reiserfs_journal_cnode *j_last;	/* newest journal block */
-	struct reiserfs_journal_cnode *j_first;	/*  oldest journal block.  start here for traverse */
+	/* newest journal block */
+	struct reiserfs_journal_cnode *j_last;
+
+	/* oldest journal block.  start here for traverse */
+	struct reiserfs_journal_cnode *j_first;
 
 	struct block_device *j_dev_bd;
 	fmode_t j_dev_mode;
-	int j_1st_reserved_block;	/* first block on s_dev of reserved area journal */
+
+	/* first block on s_dev of reserved area journal */
+	int j_1st_reserved_block;
 
 	unsigned long j_state;
 	unsigned int j_trans_id;
 	unsigned long j_mount_id;
-	unsigned long j_start;	/* start of current waiting commit (index into j_ap_blocks) */
+
+	/* start of current waiting commit (index into j_ap_blocks) */
+	unsigned long j_start;
 	unsigned long j_len;	/* length of current waiting commit */
-	unsigned long j_len_alloc;	/* number of buffers requested by journal_begin() */
+
+	/* number of buffers requested by journal_begin() */
+	unsigned long j_len_alloc;
+
 	atomic_t j_wcount;	/* count of writers for current commit */
-	unsigned long j_bcount;	/* batch count. allows turning X transactions into 1 */
-	unsigned long j_first_unflushed_offset;	/* first unflushed transactions offset */
-	unsigned j_last_flush_trans_id;	/* last fully flushed journal timestamp */
+
+	/* batch count. allows turning X transactions into 1 */
+	unsigned long j_bcount;
+
+	/* first unflushed transactions offset */
+	unsigned long j_first_unflushed_offset;
+
+	/* last fully flushed journal timestamp */
+	unsigned j_last_flush_trans_id;
+
 	struct buffer_head *j_header_bh;
 
 	time_t j_trans_start_time;	/* time this transaction started */
 	struct mutex j_mutex;
 	struct mutex j_flush_mutex;
-	wait_queue_head_t j_join_wait;	/* wait for current transaction to finish before starting new one */
-	atomic_t j_jlock;	/* lock for j_join_wait */
+
+	/* wait for current transaction to finish before starting new one */
+	wait_queue_head_t j_join_wait;
+
+	atomic_t j_jlock;		/* lock for j_join_wait */
 	int j_list_bitmap_index;	/* number of next list bitmap to use */
-	int j_must_wait;	/* no more journal begins allowed. MUST sleep on j_join_wait */
-	int j_next_full_flush;	/* next journal_end will flush all journal list */
-	int j_next_async_flush;	/* next journal_end will flush all async commits */
+
+	/* no more journal begins allowed. MUST sleep on j_join_wait */
+	int j_must_wait;
+
+	/* next journal_end will flush all journal list */
+	int j_next_full_flush;
+
+	/* next journal_end will flush all async commits */
+	int j_next_async_flush;
 
 	int j_cnode_used;	/* number of cnodes on the used list */
 	int j_cnode_free;	/* number of cnodes on the free list */
 
-	unsigned int j_trans_max;	/* max number of blocks in a transaction.  */
-	unsigned int j_max_batch;	/* max number of blocks to batch into a trans */
-	unsigned int j_max_commit_age;	/* in seconds, how old can an async commit be */
-	unsigned int j_max_trans_age;	/* in seconds, how old can a transaction be */
-	unsigned int j_default_max_commit_age;	/* the default for the max commit age */
+	/* max number of blocks in a transaction.  */
+	unsigned int j_trans_max;
+
+	/* max number of blocks to batch into a trans */
+	unsigned int j_max_batch;
+
+	/* in seconds, how old can an async commit be */
+	unsigned int j_max_commit_age;
+
+	/* in seconds, how old can a transaction be */
+	unsigned int j_max_trans_age;
+
+	/* the default for the max commit age */
+	unsigned int j_default_max_commit_age;
 
 	struct reiserfs_journal_cnode *j_cnode_free_list;
-	struct reiserfs_journal_cnode *j_cnode_free_orig;	/* orig pointer returned from vmalloc */
+
+	/* orig pointer returned from vmalloc */
+	struct reiserfs_journal_cnode *j_cnode_free_orig;
 
 	struct reiserfs_journal_list *j_current_jl;
 	int j_free_bitmap_nodes;
@@ -306,14 +387,21 @@ struct reiserfs_journal {
 
 	/* list of all active transactions */
 	struct list_head j_journal_list;
+
 	/* lists that haven't been touched by writeback attempts */
 	struct list_head j_working_list;
 
-	struct reiserfs_list_bitmap j_list_bitmap[JOURNAL_NUM_BITMAPS];	/* array of bitmaps to record the deleted blocks */
-	struct reiserfs_journal_cnode *j_hash_table[JOURNAL_HASH_SIZE];	/* hash table for real buffer heads in current trans */
-	struct reiserfs_journal_cnode *j_list_hash_table[JOURNAL_HASH_SIZE];	/* hash table for all the real buffer heads in all
-										   the transactions */
-	struct list_head j_prealloc_list;	/* list of inodes which have preallocated blocks */
+	/* hash table for real buffer heads in current trans */
+	struct reiserfs_journal_cnode *j_hash_table[JOURNAL_HASH_SIZE];
+
+	/* hash table for all the real buffer heads in all the transactions */
+	struct reiserfs_journal_cnode *j_list_hash_table[JOURNAL_HASH_SIZE];
+
+	/* array of bitmaps to record the deleted blocks */
+	struct reiserfs_list_bitmap j_list_bitmap[JOURNAL_NUM_BITMAPS];
+
+	/* list of inodes which have preallocated blocks */
+	struct list_head j_prealloc_list;
 	int j_persistent_trans;
 	unsigned long j_max_trans_size;
 	unsigned long j_max_batch_size;
@@ -328,11 +416,12 @@ struct reiserfs_journal {
 
 enum journal_state_bits {
 	J_WRITERS_BLOCKED = 1,	/* set when new writers not allowed */
-	J_WRITERS_QUEUED,	/* set when log is full due to too many writers */
-	J_ABORTED,		/* set when log is aborted */
+	J_WRITERS_QUEUED,    /* set when log is full due to too many writers */
+	J_ABORTED,           /* set when log is aborted */
 };
 
-#define JOURNAL_DESC_MAGIC "ReIsErLB"	/* ick.  magic string to find desc blocks in the journal */
+/* ick.  magic string to find desc blocks in the journal */
+#define JOURNAL_DESC_MAGIC "ReIsErLB"
 
 typedef __u32(*hashf_t) (const signed char *, int);
 
@@ -364,7 +453,10 @@ typedef struct reiserfs_proc_info_data {
 	stat_cnt_t leaked_oid;
 	stat_cnt_t leaves_removable;
 
-	/* balances per level. Use explicit 5 as MAX_HEIGHT is not visible yet. */
+	/*
+	 * balances per level.
+	 * Use explicit 5 as MAX_HEIGHT is not visible yet.
+	 */
 	stat_cnt_t balance_at[5];	/* XXX */
 	/* sbk == search_by_key */
 	stat_cnt_t sbk_read_at[5];	/* XXX */
@@ -416,47 +508,75 @@ typedef struct reiserfs_proc_info_data {
 
 /* reiserfs union of in-core super block data */
 struct reiserfs_sb_info {
-	struct buffer_head *s_sbh;	/* Buffer containing the super block */
-	/* both the comment and the choice of
-	   name are unclear for s_rs -Hans */
-	struct reiserfs_super_block *s_rs;	/* Pointer to the super block in the buffer */
+	/* Buffer containing the super block */
+	struct buffer_head *s_sbh;
+
+	/* Pointer to the on-disk super block in the buffer */
+	struct reiserfs_super_block *s_rs;
 	struct reiserfs_bitmap_info *s_ap_bitmap;
-	struct reiserfs_journal *s_journal;	/* pointer to journal information */
+
+	/* pointer to journal information */
+	struct reiserfs_journal *s_journal;
+
 	unsigned short s_mount_state;	/* reiserfs state (valid, invalid) */
 
 	/* Serialize writers access, replace the old bkl */
 	struct mutex lock;
+
 	/* Owner of the lock (can be recursive) */
 	struct task_struct *lock_owner;
+
 	/* Depth of the lock, start from -1 like the bkl */
 	int lock_depth;
 
+	struct workqueue_struct *commit_wq;
+
 	/* Comment? -Hans */
 	void (*end_io_handler) (struct buffer_head *, int);
-	hashf_t s_hash_function;	/* pointer to function which is used
-					   to sort names in directory. Set on
-					   mount */
-	unsigned long s_mount_opt;	/* reiserfs's mount options are set
-					   here (currently - NOTAIL, NOLOG,
-					   REPLAYONLY) */
-
-	struct {		/* This is a structure that describes block allocator options */
-		unsigned long bits;	/* Bitfield for enable/disable kind of options */
-		unsigned long large_file_size;	/* size started from which we consider file to be a large one(in blocks) */
+
+	/*
+	 * pointer to function which is used to sort names in directory.
+	 * Set on mount
+	 */
+	hashf_t s_hash_function;
+
+	/* reiserfs's mount options are set here */
+	unsigned long s_mount_opt;
+
+	/* This is a structure that describes block allocator options */
+	struct {
+		/* Bitfield for enable/disable kind of options */
+		unsigned long bits;
+
+		/*
+		 * size started from which we consider file
+		 * to be a large one (in blocks)
+		 */
+		unsigned long large_file_size;
+
 		int border;	/* percentage of disk, border takes */
-		int preallocmin;	/* Minimal file size (in blocks) starting from which we do preallocations */
-		int preallocsize;	/* Number of blocks we try to prealloc when file
-					   reaches preallocmin size (in blocks) or
-					   prealloc_list is empty. */
+
+		/*
+		 * Minimal file size (in blocks) starting
+		 * from which we do preallocations
+		 */
+		int preallocmin;
+
+		/*
+		 * Number of blocks we try to prealloc when file
+		 * reaches preallocmin size (in blocks) or prealloc_list
+		 is empty.
+		 */
+		int preallocsize;
 	} s_alloc_options;
 
 	/* Comment? -Hans */
 	wait_queue_head_t s_wait;
-	/* To be obsoleted soon by per buffer seals.. -Hans */
-	atomic_t s_generation_counter;	// increased by one every time the
-	// tree gets re-balanced
-	unsigned long s_properties;	/* File system properties. Currently holds
-					   on-disk FS format */
+	/* increased by one every time the  tree gets re-balanced */
+	atomic_t s_generation_counter;
+
+	/* File system properties. Currently holds on-disk FS format */
+	unsigned long s_properties;
 
 	/* session statistics */
 	int s_disk_reads;
@@ -469,14 +589,23 @@ struct reiserfs_sb_info {
 	int s_bmaps_without_search;
 	int s_direct2indirect;
 	int s_indirect2direct;
-	/* set up when it's ok for reiserfs_read_inode2() to read from
-	   disk inode with nlink==0. Currently this is only used during
-	   finish_unfinished() processing at mount time */
+
+	/*
+	 * set up when it's ok for reiserfs_read_inode2() to read from
+	 * disk inode with nlink==0. Currently this is only used during
+	 * finish_unfinished() processing at mount time
+	 */
 	int s_is_unlinked_ok;
+
 	reiserfs_proc_info_data_t s_proc_info_data;
 	struct proc_dir_entry *procdir;
-	int reserved_blocks;	/* amount of blocks reserved for further allocations */
-	spinlock_t bitmap_lock;	/* this lock on now only used to protect reserved_blocks variable */
+
+	/* amount of blocks reserved for further allocations */
+	int reserved_blocks;
+
+
+	/* this lock on now only used to protect reserved_blocks variable */
+	spinlock_t bitmap_lock;
 	struct dentry *priv_root;	/* root of /.reiserfs_priv */
 	struct dentry *xattr_root;	/* root of /.reiserfs_priv/xattrs */
 	int j_errno;
@@ -492,14 +621,13 @@ struct reiserfs_sb_info {
 	char *s_jdev;		/* Stored jdev for mount option showing */
 #ifdef CONFIG_REISERFS_CHECK
 
-	struct tree_balance *cur_tb;	/*
-					 * Detects whether more than one
-					 * copy of tb exists per superblock
-					 * as a means of checking whether
-					 * do_balance is executing concurrently
-					 * against another tree reader/writer
-					 * on a same mount point.
-					 */
+	/*
+	 * Detects whether more than one copy of tb exists per superblock
+	 * as a means of checking whether do_balance is executing
+	 * concurrently against another tree reader/writer on a same
+	 * mount point.
+	 */
+	struct tree_balance *cur_tb;
 #endif
 };
 
@@ -508,25 +636,36 @@ struct reiserfs_sb_info {
 #define REISERFS_3_6 1
 #define REISERFS_OLD_FORMAT 2
 
-enum reiserfs_mount_options {
 /* Mount options */
-	REISERFS_LARGETAIL,	/* large tails will be created in a session */
-	REISERFS_SMALLTAIL,	/* small (for files less than block size) tails will be created in a session */
-	REPLAYONLY,		/* replay journal and return 0. Use by fsck */
-	REISERFS_CONVERT,	/* -o conv: causes conversion of old
-				   format super block to the new
-				   format. If not specified - old
-				   partition will be dealt with in a
-				   manner of 3.5.x */
-
-/* -o hash={tea, rupasov, r5, detect} is meant for properly mounting
-** reiserfs disks from 3.5.19 or earlier.  99% of the time, this option
-** is not required.  If the normal autodection code can't determine which
-** hash to use (because both hashes had the same value for a file)
-** use this option to force a specific hash.  It won't allow you to override
-** the existing hash on the FS, so if you have a tea hash disk, and mount
-** with -o hash=rupasov, the mount will fail.
-*/
+enum reiserfs_mount_options {
+	/* large tails will be created in a session */
+	REISERFS_LARGETAIL,
+	/*
+	 * small (for files less than block size) tails will
+	 * be created in a session
+	 */
+	REISERFS_SMALLTAIL,
+
+	/* replay journal and return 0. Use by fsck */
+	REPLAYONLY,
+
+	/*
+	 * -o conv: causes conversion of old format super block to the
+	 * new format. If not specified - old partition will be dealt
+	 * with in a manner of 3.5.x
+	 */
+	REISERFS_CONVERT,
+
+	/*
+	 * -o hash={tea, rupasov, r5, detect} is meant for properly mounting
+	 * reiserfs disks from 3.5.19 or earlier.  99% of the time, this
+	 * option is not required.  If the normal autodection code can't
+	 * determine which hash to use (because both hashes had the same
+	 * value for a file) use this option to force a specific hash.
+	 * It won't allow you to override the existing hash on the FS, so
+	 * if you have a tea hash disk, and mount with -o hash=rupasov,
+	 * the mount will fail.
+	 */
 	FORCE_TEA_HASH,		/* try to force tea hash on mount */
 	FORCE_RUPASOV_HASH,	/* try to force rupasov hash on mount */
 	FORCE_R5_HASH,		/* try to force rupasov hash on mount */
@@ -536,9 +675,11 @@ enum reiserfs_mount_options {
 	REISERFS_DATA_ORDERED,
 	REISERFS_DATA_WRITEBACK,
 
-/* used for testing experimental features, makes benchmarking new
-   features with and without more convenient, should never be used by
-   users in any code shipped to users (ideally) */
+	/*
+	 * used for testing experimental features, makes benchmarking new
+	 * features with and without more convenient, should never be used by
+	 * users in any code shipped to users (ideally)
+	 */
 
 	REISERFS_NO_BORDER,
 	REISERFS_NO_UNHASHED_RELOCATION,
@@ -705,28 +846,28 @@ static inline void reiserfs_cond_resched(struct super_block *s)
 
 struct fid;
 
-/* in reading the #defines, it may help to understand that they employ
-   the following abbreviations:
-
-   B = Buffer
-   I = Item header
-   H = Height within the tree (should be changed to LEV)
-   N = Number of the item in the node
-   STAT = stat data
-   DEH = Directory Entry Header
-   EC = Entry Count
-   E = Entry number
-   UL = Unsigned Long
-   BLKH = BLocK Header
-   UNFM = UNForMatted node
-   DC = Disk Child
-   P = Path
-
-   These #defines are named by concatenating these abbreviations,
-   where first comes the arguments, and last comes the return value,
-   of the macro.
-
-*/
+/*
+ * in reading the #defines, it may help to understand that they employ
+ *  the following abbreviations:
+ *
+ *  B = Buffer
+ *  I = Item header
+ *  H = Height within the tree (should be changed to LEV)
+ *  N = Number of the item in the node
+ *  STAT = stat data
+ *  DEH = Directory Entry Header
+ *  EC = Entry Count
+ *  E = Entry number
+ *  UL = Unsigned Long
+ *  BLKH = BLocK Header
+ *  UNFM = UNForMatted node
+ *  DC = Disk Child
+ *  P = Path
+ *
+ *  These #defines are named by concatenating these abbreviations,
+ *  where first comes the arguments, and last comes the return value,
+ *  of the macro.
+ */
 
 #define USE_INODE_GENERATION_COUNTER
 
@@ -737,14 +878,17 @@ struct fid;
 /* n must be power of 2 */
 #define _ROUND_UP(x,n) (((x)+(n)-1u) & ~((n)-1u))
 
-// to be ok for alpha and others we have to align structures to 8 byte
-// boundary.
-// FIXME: do not change 4 by anything else: there is code which relies on that
+/*
+ * to be ok for alpha and others we have to align structures to 8 byte
+ * boundary.
+ * FIXME: do not change 4 by anything else: there is code which relies on that
+ */
 #define ROUND_UP(x) _ROUND_UP(x,8LL)
 
-/* debug levels.  Right now, CONFIG_REISERFS_CHECK means print all debug
-** messages.
-*/
+/*
+ * debug levels.  Right now, CONFIG_REISERFS_CHECK means print all debug
+ * messages.
+ */
 #define REISERFS_DEBUG_CODE 5	/* extra messages to help find/debug errors */
 
 void __reiserfs_warning(struct super_block *s, const char *id,
@@ -753,7 +897,7 @@ void __reiserfs_warning(struct super_block *s, const char *id,
 	 __reiserfs_warning(s, id, __func__, fmt, ##args)
 /* assertions handling */
 
-/** always check a condition and panic if it's false. */
+/* always check a condition and panic if it's false. */
 #define __RASSERT(cond, scond, format, args...)			\
 do {									\
 	if (!(cond))							\
@@ -776,35 +920,48 @@ do {									\
  * Disk Data Structures
  */
 
-/***************************************************************************/
-/*                             SUPER BLOCK                                 */
-/***************************************************************************/
+/***************************************************************************
+ *                             SUPER BLOCK                                 *
+ ***************************************************************************/
 
 /*
- * Structure of super block on disk, a version of which in RAM is often accessed as REISERFS_SB(s)->s_rs
- * the version in RAM is part of a larger structure containing fields never written to disk.
+ * Structure of super block on disk, a version of which in RAM is often
+ * accessed as REISERFS_SB(s)->s_rs. The version in RAM is part of a larger
+ * structure containing fields never written to disk.
  */
-#define UNSET_HASH 0		// read_super will guess about, what hash names
-		     // in directories were sorted with
+#define UNSET_HASH 0	/* Detect hash on disk */
 #define TEA_HASH  1
 #define YURA_HASH 2
 #define R5_HASH   3
 #define DEFAULT_HASH R5_HASH
 
 struct journal_params {
-	__le32 jp_journal_1st_block;	/* where does journal start from on its
-					 * device */
-	__le32 jp_journal_dev;	/* journal device st_rdev */
-	__le32 jp_journal_size;	/* size of the journal */
-	__le32 jp_journal_trans_max;	/* max number of blocks in a transaction. */
-	__le32 jp_journal_magic;	/* random value made on fs creation (this
-					 * was sb_journal_block_count) */
-	__le32 jp_journal_max_batch;	/* max number of blocks to batch into a
-					 * trans */
-	__le32 jp_journal_max_commit_age;	/* in seconds, how old can an async
-						 * commit be */
-	__le32 jp_journal_max_trans_age;	/* in seconds, how old can a transaction
-						 * be */
+	/* where does journal start from on its * device */
+	__le32 jp_journal_1st_block;
+
+	/* journal device st_rdev */
+	__le32 jp_journal_dev;
+
+	/* size of the journal */
+	__le32 jp_journal_size;
+
+	/* max number of blocks in a transaction. */
+	__le32 jp_journal_trans_max;
+
+	/*
+	 * random value made on fs creation
+	 * (this was sb_journal_block_count)
+	 */
+	__le32 jp_journal_magic;
+
+	/* max number of blocks to batch into a trans */
+	__le32 jp_journal_max_batch;
+
+	/* in seconds, how old can an async  commit be */
+	__le32 jp_journal_max_commit_age;
+
+	/* in seconds, how old can a transaction be */
+	__le32 jp_journal_max_trans_age;
 };
 
 /* this is the super from 3.5.X, where X >= 10 */
@@ -814,26 +971,48 @@ struct reiserfs_super_block_v1 {
 	__le32 s_root_block;	/* root block number    */
 	struct journal_params s_journal;
 	__le16 s_blocksize;	/* block size */
-	__le16 s_oid_maxsize;	/* max size of object id array, see
-				 * get_objectid() commentary  */
+
+	/* max size of object id array, see get_objectid() commentary  */
+	__le16 s_oid_maxsize;
 	__le16 s_oid_cursize;	/* current size of object id array */
-	__le16 s_umount_state;	/* this is set to 1 when filesystem was
-				 * umounted, to 2 - when not */
-	char s_magic[10];	/* reiserfs magic string indicates that
-				 * file system is reiserfs:
-				 * "ReIsErFs" or "ReIsEr2Fs" or "ReIsEr3Fs" */
-	__le16 s_fs_state;	/* it is set to used by fsck to mark which
-				 * phase of rebuilding is done */
-	__le32 s_hash_function_code;	/* indicate, what hash function is being use
-					 * to sort names in a directory*/
+
+	/* this is set to 1 when filesystem was umounted, to 2 - when not */
+	__le16 s_umount_state;
+
+	/*
+	 * reiserfs magic string indicates that file system is reiserfs:
+	 * "ReIsErFs" or "ReIsEr2Fs" or "ReIsEr3Fs"
+	 */
+	char s_magic[10];
+
+	/*
+	 * it is set to used by fsck to mark which
+	 * phase of rebuilding is done
+	 */
+	__le16 s_fs_state;
+	/*
+	 * indicate, what hash function is being use
+	 * to sort names in a directory
+	 */
+	__le32 s_hash_function_code;
 	__le16 s_tree_height;	/* height of disk tree */
-	__le16 s_bmap_nr;	/* amount of bitmap blocks needed to address
-				 * each block of file system */
-	__le16 s_version;	/* this field is only reliable on filesystem
-				 * with non-standard journal */
-	__le16 s_reserved_for_journal;	/* size in blocks of journal area on main
-					 * device, we need to keep after
-					 * making fs with non-standard journal */
+
+	/*
+	 * amount of bitmap blocks needed to address
+	 * each block of file system
+	 */
+	__le16 s_bmap_nr;
+
+	/*
+	 * this field is only reliable on filesystem with non-standard journal
+	 */
+	__le16 s_version;
+
+	/*
+	 * size in blocks of journal area on main device, we need to
+	 * keep after making fs with non-standard journal
+	 */
+	__le16 s_reserved_for_journal;
 } __attribute__ ((__packed__));
 
 #define SB_SIZE_V1 (sizeof(struct reiserfs_super_block_v1))
@@ -842,17 +1021,21 @@ struct reiserfs_super_block_v1 {
 struct reiserfs_super_block {
 	struct reiserfs_super_block_v1 s_v1;
 	__le32 s_inode_generation;
-	__le32 s_flags;		/* Right now used only by inode-attributes, if enabled */
+
+	/* Right now used only by inode-attributes, if enabled */
+	__le32 s_flags;
+
 	unsigned char s_uuid[16];	/* filesystem unique identifier */
 	unsigned char s_label[16];	/* filesystem volume label */
 	__le16 s_mnt_count;		/* Count of mounts since last fsck */
 	__le16 s_max_mnt_count;		/* Maximum mounts before check */
 	__le32 s_lastcheck;		/* Timestamp of last fsck */
 	__le32 s_check_interval;	/* Interval between checks */
-	char s_unused[76];	/* zero filled by mkreiserfs and
-				 * reiserfs_convert_objectid_map_v1()
-				 * so any additions must be updated
-				 * there as well. */
+
+	/*
+	 * zero filled by mkreiserfs and reiserfs_convert_objectid_map_v1()
+	 * so any additions must be updated there as well. */
+	char s_unused[76];
 } __attribute__ ((__packed__));
 
 #define SB_SIZE (sizeof(struct reiserfs_super_block))
@@ -860,7 +1043,7 @@ struct reiserfs_super_block {
 #define REISERFS_VERSION_1 0
 #define REISERFS_VERSION_2 2
 
-// on-disk super block fields converted to cpu form
+/* on-disk super block fields converted to cpu form */
 #define SB_DISK_SUPER_BLOCK(s) (REISERFS_SB(s)->s_rs)
 #define SB_V1_DISK_SUPER_BLOCK(s) (&(SB_DISK_SUPER_BLOCK(s)->s_v1))
 #define SB_BLOCKSIZE(s) \
@@ -915,11 +1098,13 @@ int is_reiserfs_3_5(struct reiserfs_super_block *rs);
 int is_reiserfs_3_6(struct reiserfs_super_block *rs);
 int is_reiserfs_jr(struct reiserfs_super_block *rs);
 
-/* ReiserFS leaves the first 64k unused, so that partition labels have
-   enough space.  If someone wants to write a fancy bootloader that
-   needs more than 64k, let us know, and this will be increased in size.
-   This number must be larger than than the largest block size on any
-   platform, or code will break.  -Hans */
+/*
+ * ReiserFS leaves the first 64k unused, so that partition labels have
+ * enough space.  If someone wants to write a fancy bootloader that
+ * needs more than 64k, let us know, and this will be increased in size.
+ * This number must be larger than than the largest block size on any
+ * platform, or code will break.  -Hans
+ */
 #define REISERFS_DISK_OFFSET_IN_BYTES (64 * 1024)
 #define REISERFS_FIRST_BLOCK unused_define
 #define REISERFS_JOURNAL_OFFSET_IN_BYTES REISERFS_DISK_OFFSET_IN_BYTES
@@ -944,8 +1129,7 @@ struct unfm_nodeinfo {
 	unsigned short unfm_freespace;
 };
 
-/* there are two formats of keys: 3.5 and 3.6
- */
+/* there are two formats of keys: 3.5 and 3.6 */
 #define KEY_FORMAT_3_5 0
 #define KEY_FORMAT_3_6 1
 
@@ -963,8 +1147,10 @@ static inline struct reiserfs_sb_info *REISERFS_SB(const struct super_block *sb)
 	return sb->s_fs_info;
 }
 
-/* Don't trust REISERFS_SB(sb)->s_bmap_nr, it's a u16
- * which overflows on large file systems. */
+/*
+ * Don't trust REISERFS_SB(sb)->s_bmap_nr, it's a u16
+ * which overflows on large file systems.
+ */
 static inline __u32 reiserfs_bmap_count(struct super_block *sb)
 {
 	return (SB_BLOCK_COUNT(sb) - 1) / (sb->s_blocksize * 8) + 1;
@@ -975,8 +1161,10 @@ static inline int bmap_would_wrap(unsigned bmap_nr)
 	return bmap_nr > ((1LL << 16) - 1);
 }
 
-/** this says about version of key of all items (but stat data) the
-    object consists of */
+/*
+ * this says about version of key of all items (but stat data) the
+ * object consists of
+ */
 #define get_inode_item_key_version( inode )                                    \
     ((REISERFS_I(inode)->i_flags & i_item_key_version_mask) ? KEY_FORMAT_3_6 : KEY_FORMAT_3_5)
 
@@ -995,16 +1183,18 @@ static inline int bmap_would_wrap(unsigned bmap_nr)
             else                                                               \
                 REISERFS_I(inode)->i_flags &= ~i_stat_data_version_mask; })
 
-/* This is an aggressive tail suppression policy, I am hoping it
-   improves our benchmarks. The principle behind it is that percentage
-   space saving is what matters, not absolute space saving.  This is
-   non-intuitive, but it helps to understand it if you consider that the
-   cost to access 4 blocks is not much more than the cost to access 1
-   block, if you have to do a seek and rotate.  A tail risks a
-   non-linear disk access that is significant as a percentage of total
-   time cost for a 4 block file and saves an amount of space that is
-   less significant as a percentage of space, or so goes the hypothesis.
-   -Hans */
+/*
+ * This is an aggressive tail suppression policy, I am hoping it
+ * improves our benchmarks. The principle behind it is that percentage
+ * space saving is what matters, not absolute space saving.  This is
+ * non-intuitive, but it helps to understand it if you consider that the
+ * cost to access 4 blocks is not much more than the cost to access 1
+ * block, if you have to do a seek and rotate.  A tail risks a
+ * non-linear disk access that is significant as a percentage of total
+ * time cost for a 4 block file and saves an amount of space that is
+ * less significant as a percentage of space, or so goes the hypothesis.
+ * -Hans
+ */
 #define STORE_TAIL_IN_UNFM_S1(n_file_size,n_tail_size,n_block_size) \
 (\
   (!(n_tail_size)) || \
@@ -1018,10 +1208,11 @@ static inline int bmap_would_wrap(unsigned bmap_nr)
      ( (n_tail_size) >=   (MAX_DIRECT_ITEM_LEN(n_block_size) * 3)/4) ) ) \
 )
 
-/* Another strategy for tails, this one means only create a tail if all the
-   file would fit into one DIRECT item.
-   Primary intention for this one is to increase performance by decreasing
-   seeking.
+/*
+ * Another strategy for tails, this one means only create a tail if all the
+ * file would fit into one DIRECT item.
+ * Primary intention for this one is to increase performance by decreasing
+ * seeking.
 */
 #define STORE_TAIL_IN_UNFM_S2(n_file_size,n_tail_size,n_block_size) \
 (\
@@ -1035,23 +1226,21 @@ static inline int bmap_would_wrap(unsigned bmap_nr)
 #define REISERFS_VALID_FS    1
 #define REISERFS_ERROR_FS    2
 
-//
-// there are 5 item types currently
-//
+/*
+ * there are 5 item types currently
+ */
 #define TYPE_STAT_DATA 0
 #define TYPE_INDIRECT 1
 #define TYPE_DIRECT 2
 #define TYPE_DIRENTRY 3
 #define TYPE_MAXTYPE 3
-#define TYPE_ANY 15		// FIXME: comment is required
+#define TYPE_ANY 15		/* FIXME: comment is required */
 
-/***************************************************************************/
-/*                       KEY & ITEM HEAD                                   */
-/***************************************************************************/
+/***************************************************************************
+ *                       KEY & ITEM HEAD                                   *
+ ***************************************************************************/
 
-//
-// directories use this key as well as old files
-//
+/* * directories use this key as well as old files */
 struct offset_v1 {
 	__le32 k_offset;
 	__le32 k_uniqueness;
@@ -1084,11 +1273,14 @@ static inline void set_offset_v2_k_offset(struct offset_v2 *v2, loff_t offset)
 	v2->v = (v2->v & cpu_to_le64(15ULL << 60)) | cpu_to_le64(offset);
 }
 
-/* Key of an item determines its location in the S+tree, and
-   is composed of 4 components */
+/*
+ * Key of an item determines its location in the S+tree, and
+ * is composed of 4 components
+ */
 struct reiserfs_key {
-	__le32 k_dir_id;	/* packing locality: by default parent
-				   directory object id */
+	/* packing locality: by default parent directory object id */
+	__le32 k_dir_id;
+
 	__le32 k_objectid;	/* object identifier */
 	union {
 		struct offset_v1 k_offset_v1;
@@ -1097,8 +1289,8 @@ struct reiserfs_key {
 } __attribute__ ((__packed__));
 
 struct in_core_key {
-	__u32 k_dir_id;		/* packing locality: by default parent
-				   directory object id */
+	/* packing locality: by default parent directory object id */
+	__u32 k_dir_id;
 	__u32 k_objectid;	/* object identifier */
 	__u64 k_offset;
 	__u8 k_type;
@@ -1107,14 +1299,16 @@ struct in_core_key {
 struct cpu_key {
 	struct in_core_key on_disk_key;
 	int version;
-	int key_length;		/* 3 in all cases but direct2indirect and
-				   indirect2direct conversion */
+	/* 3 in all cases but direct2indirect and indirect2direct conversion */
+	int key_length;
 };
 
-/* Our function for comparing keys can compare keys of different
-   lengths.  It takes as a parameter the length of the keys it is to
-   compare.  These defines are used in determining what is to be passed
-   to it as that parameter. */
+/*
+ * Our function for comparing keys can compare keys of different
+ * lengths.  It takes as a parameter the length of the keys it is to
+ * compare.  These defines are used in determining what is to be passed
+ * to it as that parameter.
+ */
 #define REISERFS_FULL_KEY_LEN     4
 #define REISERFS_SHORT_KEY_LEN    2
 
@@ -1143,40 +1337,52 @@ struct cpu_key {
 #define POSITION_FOUND 1
 #define POSITION_NOT_FOUND 0
 
-// return values for reiserfs_find_entry and search_by_entry_key
+/* return values for reiserfs_find_entry and search_by_entry_key */
 #define NAME_FOUND 1
 #define NAME_NOT_FOUND 0
 #define GOTO_PREVIOUS_ITEM 2
 #define NAME_FOUND_INVISIBLE 3
 
-/*  Everything in the filesystem is stored as a set of items.  The
-    item head contains the key of the item, its free space (for
-    indirect items) and specifies the location of the item itself
-    within the block.  */
+/*
+ * Everything in the filesystem is stored as a set of items.  The
+ * item head contains the key of the item, its free space (for
+ * indirect items) and specifies the location of the item itself
+ * within the block.
+ */
 
 struct item_head {
-	/* Everything in the tree is found by searching for it based on
-	 * its key.*/
+	/*
+	 * Everything in the tree is found by searching for it based on
+	 * its key.
+	 */
 	struct reiserfs_key ih_key;
 	union {
-		/* The free space in the last unformatted node of an
-		   indirect item if this is an indirect item.  This
-		   equals 0xFFFF iff this is a direct item or stat data
-		   item. Note that the key, not this field, is used to
-		   determine the item type, and thus which field this
-		   union contains. */
+		/*
+		 * The free space in the last unformatted node of an
+		 * indirect item if this is an indirect item.  This
+		 * equals 0xFFFF iff this is a direct item or stat data
+		 * item. Note that the key, not this field, is used to
+		 * determine the item type, and thus which field this
+		 * union contains.
+		 */
 		__le16 ih_free_space_reserved;
-		/* Iff this is a directory item, this field equals the
-		   number of directory entries in the directory item. */
+
+		/*
+		 * Iff this is a directory item, this field equals the
+		 * number of directory entries in the directory item.
+		 */
 		__le16 ih_entry_count;
 	} __attribute__ ((__packed__)) u;
 	__le16 ih_item_len;	/* total size of the item body */
-	__le16 ih_item_location;	/* an offset to the item body
-					 * within the block */
-	__le16 ih_version;	/* 0 for all old items, 2 for new
-				   ones. Highest bit is set by fsck
-				   temporary, cleaned after all
-				   done */
+
+	/* an offset to the item body within the block */
+	__le16 ih_item_location;
+
+	/*
+	 * 0 for all old items, 2 for new ones. Highest bit is set by fsck
+	 * temporary, cleaned after all done
+	 */
+	__le16 ih_version;
 } __attribute__ ((__packed__));
 /* size of item header     */
 #define IH_SIZE (sizeof(struct item_head))
@@ -1198,27 +1404,24 @@ struct item_head {
 #define get_ih_free_space(ih) (ih_version (ih) == KEY_FORMAT_3_6 ? 0 : ih_free_space (ih))
 #define set_ih_free_space(ih,val) put_ih_free_space((ih), ((ih_version(ih) == KEY_FORMAT_3_6) ? 0 : (val)))
 
-/* these operate on indirect items, where you've got an array of ints
-** at a possibly unaligned location.  These are a noop on ia32
-** 
-** p is the array of __u32, i is the index into the array, v is the value
-** to store there.
-*/
+/*
+ * these operate on indirect items, where you've got an array of ints
+ * at a possibly unaligned location.  These are a noop on ia32
+ *
+ * p is the array of __u32, i is the index into the array, v is the value
+ * to store there.
+ */
 #define get_block_num(p, i) get_unaligned_le32((p) + (i))
 #define put_block_num(p, i, v) put_unaligned_le32((v), (p) + (i))
 
-//
-// in old version uniqueness field shows key type
-//
+/* * in old version uniqueness field shows key type */
 #define V1_SD_UNIQUENESS 0
 #define V1_INDIRECT_UNIQUENESS 0xfffffffe
 #define V1_DIRECT_UNIQUENESS 0xffffffff
 #define V1_DIRENTRY_UNIQUENESS 500
-#define V1_ANY_UNIQUENESS 555	// FIXME: comment is required
+#define V1_ANY_UNIQUENESS 555	/* FIXME: comment is required */
 
-//
-// here are conversion routines
-//
+/* here are conversion routines */
 static inline int uniqueness2type(__u32 uniqueness) CONSTF;
 static inline int uniqueness2type(__u32 uniqueness)
 {
@@ -1255,11 +1458,11 @@ static inline __u32 type2uniqueness(int type)
 	}
 }
 
-//
-// key is pointer to on disk key which is stored in le, result is cpu,
-// there is no way to get version of object from key, so, provide
-// version to these defines
-//
+/*
+ * key is pointer to on disk key which is stored in le, result is cpu,
+ * there is no way to get version of object from key, so, provide
+ * version to these defines
+ */
 static inline loff_t le_key_k_offset(int version,
 				     const struct reiserfs_key *key)
 {
@@ -1275,9 +1478,11 @@ static inline loff_t le_ih_k_offset(const struct item_head *ih)
 
 static inline loff_t le_key_k_type(int version, const struct reiserfs_key *key)
 {
-	return (version == KEY_FORMAT_3_5) ?
-	    uniqueness2type(le32_to_cpu(key->u.k_offset_v1.k_uniqueness)) :
-	    offset_v2_k_type(&(key->u.k_offset_v2));
+	if (version == KEY_FORMAT_3_5) {
+		loff_t val = le32_to_cpu(key->u.k_offset_v1.k_uniqueness);
+		return uniqueness2type(val);
+	} else
+		return offset_v2_k_type(&(key->u.k_offset_v2));
 }
 
 static inline loff_t le_ih_k_type(const struct item_head *ih)
@@ -1288,8 +1493,22 @@ static inline loff_t le_ih_k_type(const struct item_head *ih)
 static inline void set_le_key_k_offset(int version, struct reiserfs_key *key,
 				       loff_t offset)
 {
-	(version == KEY_FORMAT_3_5) ? (void)(key->u.k_offset_v1.k_offset = cpu_to_le32(offset)) :	/* jdm check */
-	    (void)(set_offset_v2_k_offset(&(key->u.k_offset_v2), offset));
+	if (version == KEY_FORMAT_3_5)
+		key->u.k_offset_v1.k_offset = cpu_to_le32(offset);
+	else
+		set_offset_v2_k_offset(&key->u.k_offset_v2, offset);
+}
+
+static inline void add_le_key_k_offset(int version, struct reiserfs_key *key,
+				       loff_t offset)
+{
+	set_le_key_k_offset(version, key,
+			    le_key_k_offset(version, key) + offset);
+}
+
+static inline void add_le_ih_k_offset(struct item_head *ih, loff_t offset)
+{
+	add_le_key_k_offset(ih_version(ih), &(ih->ih_key), offset);
 }
 
 static inline void set_le_ih_k_offset(struct item_head *ih, loff_t offset)
@@ -1300,10 +1519,11 @@ static inline void set_le_ih_k_offset(struct item_head *ih, loff_t offset)
 static inline void set_le_key_k_type(int version, struct reiserfs_key *key,
 				     int type)
 {
-	(version == KEY_FORMAT_3_5) ?
-	    (void)(key->u.k_offset_v1.k_uniqueness =
-		   cpu_to_le32(type2uniqueness(type)))
-	    : (void)(set_offset_v2_k_type(&(key->u.k_offset_v2), type));
+	if (version == KEY_FORMAT_3_5) {
+		type = type2uniqueness(type);
+		key->u.k_offset_v1.k_uniqueness = cpu_to_le32(type);
+	} else
+	       set_offset_v2_k_type(&key->u.k_offset_v2, type);
 }
 
 static inline void set_le_ih_k_type(struct item_head *ih, int type)
@@ -1331,9 +1551,7 @@ static inline int is_statdata_le_key(int version, struct reiserfs_key *key)
 	return le_key_k_type(version, key) == TYPE_STAT_DATA;
 }
 
-//
-// item header has version.
-//
+/* item header has version.  */
 static inline int is_direntry_le_ih(struct item_head *ih)
 {
 	return is_direntry_le_key(ih_version(ih), &ih->ih_key);
@@ -1354,9 +1572,7 @@ static inline int is_statdata_le_ih(struct item_head *ih)
 	return is_statdata_le_key(ih_version(ih), &ih->ih_key);
 }
 
-//
-// key is pointer to cpu key, result is cpu
-//
+/* key is pointer to cpu key, result is cpu */
 static inline loff_t cpu_key_k_offset(const struct cpu_key *key)
 {
 	return key->on_disk_key.k_offset;
@@ -1407,7 +1623,7 @@ static inline void cpu_key_k_offset_dec(struct cpu_key *key)
 
 extern struct reiserfs_key root_key;
 
-/* 
+/*
  * Picture represents a leaf of the S+tree
  *  ______________________________________________________
  * |      |  Array of     |                   |           |
@@ -1416,15 +1632,19 @@ extern struct reiserfs_key root_key;
  * |______|_______________|___________________|___________|
  */
 
-/* Header of a disk block.  More precisely, header of a formatted leaf
-   or internal node, and not the header of an unformatted node. */
+/*
+ * Header of a disk block.  More precisely, header of a formatted leaf
+ * or internal node, and not the header of an unformatted node.
+ */
 struct block_head {
 	__le16 blk_level;	/* Level of a block in the tree. */
 	__le16 blk_nr_item;	/* Number of keys/items in a block. */
 	__le16 blk_free_space;	/* Block free space in bytes. */
 	__le16 blk_reserved;
 	/* dump this in v4/planA */
-	struct reiserfs_key blk_right_delim_key;	/* kept only for compatibility */
+
+	/* kept only for compatibility */
+	struct reiserfs_key blk_right_delim_key;
 };
 
 #define BLKH_SIZE                     (sizeof(struct block_head))
@@ -1439,18 +1659,20 @@ struct block_head {
 #define blkh_right_delim_key(p_blkh)  ((p_blkh)->blk_right_delim_key)
 #define set_blkh_right_delim_key(p_blkh,val)  ((p_blkh)->blk_right_delim_key = val)
 
+/* values for blk_level field of the struct block_head */
+
 /*
- * values for blk_level field of the struct block_head
+ * When node gets removed from the tree its blk_level is set to FREE_LEVEL.
+ * It is then  used to see whether the node is still in the tree
  */
-
-#define FREE_LEVEL 0		/* when node gets removed from the tree its
-				   blk_level is set to FREE_LEVEL. It is then
-				   used to see whether the node is still in the
-				   tree */
+#define FREE_LEVEL 0
 
 #define DISK_LEAF_NODE_LEVEL  1	/* Leaf node level. */
 
-/* Given the buffer head of a formatted node, resolve to the block head of that node. */
+/*
+ * Given the buffer head of a formatted node, resolve to the
+ * block head of that node.
+ */
 #define B_BLK_HEAD(bh)			((struct block_head *)((bh)->b_data))
 /* Number of items that are in buffer. */
 #define B_NR_ITEMS(bh)			(blkh_nr_item(B_BLK_HEAD(bh)))
@@ -1471,14 +1693,14 @@ struct block_head {
 #define B_IS_KEYS_LEVEL(bh)      (B_LEVEL(bh) > DISK_LEAF_NODE_LEVEL \
 					    && B_LEVEL(bh) <= MAX_HEIGHT)
 
-/***************************************************************************/
-/*                             STAT DATA                                   */
-/***************************************************************************/
+/***************************************************************************
+ *                             STAT DATA                                   *
+ ***************************************************************************/
 
-//
-// old stat data is 32 bytes long. We are going to distinguish new one by
-// different size
-//
+/*
+ * old stat data is 32 bytes long. We are going to distinguish new one by
+ * different size
+*/
 struct stat_data_v1 {
 	__le16 sd_mode;		/* file type, permissions */
 	__le16 sd_nlink;	/* number of hard links */
@@ -1487,20 +1709,25 @@ struct stat_data_v1 {
 	__le32 sd_size;		/* file size */
 	__le32 sd_atime;	/* time of last access */
 	__le32 sd_mtime;	/* time file was last modified  */
-	__le32 sd_ctime;	/* time inode (stat data) was last changed (except changes to sd_atime and sd_mtime) */
+
+	/*
+	 * time inode (stat data) was last changed
+	 * (except changes to sd_atime and sd_mtime)
+	 */
+	__le32 sd_ctime;
 	union {
 		__le32 sd_rdev;
 		__le32 sd_blocks;	/* number of blocks file uses */
 	} __attribute__ ((__packed__)) u;
-	__le32 sd_first_direct_byte;	/* first byte of file which is stored
-					   in a direct item: except that if it
-					   equals 1 it is a symlink and if it
-					   equals ~(__u32)0 there is no
-					   direct item.  The existence of this
-					   field really grates on me. Let's
-					   replace it with a macro based on
-					   sd_size and our tail suppression
-					   policy.  Someday.  -Hans */
+
+	/*
+	 * first byte of file which is stored in a direct item: except that if
+	 * it equals 1 it is a symlink and if it equals ~(__u32)0 there is no
+	 * direct item.  The existence of this field really grates on me.
+	 * Let's replace it with a macro based on sd_size and our tail
+	 * suppression policy.  Someday.  -Hans
+	 */
+	__le32 sd_first_direct_byte;
 } __attribute__ ((__packed__));
 
 #define SD_V1_SIZE              (sizeof(struct stat_data_v1))
@@ -1532,8 +1759,10 @@ struct stat_data_v1 {
 
 /* inode flags stored in sd_attrs (nee sd_reserved) */
 
-/* we want common flags to have the same values as in ext2,
-   so chattr(1) will work without problems */
+/*
+ * we want common flags to have the same values as in ext2,
+ * so chattr(1) will work without problems
+ */
 #define REISERFS_IMMUTABLE_FL FS_IMMUTABLE_FL
 #define REISERFS_APPEND_FL    FS_APPEND_FL
 #define REISERFS_SYNC_FL      FS_SYNC_FL
@@ -1553,8 +1782,10 @@ struct stat_data_v1 {
 				REISERFS_COMPR_FL |	\
 				REISERFS_NOTAIL_FL )
 
-/* Stat Data on disk (reiserfs version of UFS disk inode minus the
-   address blocks) */
+/*
+ * Stat Data on disk (reiserfs version of UFS disk inode minus the
+ * address blocks)
+ */
 struct stat_data {
 	__le16 sd_mode;		/* file type, permissions */
 	__le16 sd_attrs;	/* persistent inode flags */
@@ -1564,25 +1795,20 @@ struct stat_data {
 	__le32 sd_gid;		/* group */
 	__le32 sd_atime;	/* time of last access */
 	__le32 sd_mtime;	/* time file was last modified  */
-	__le32 sd_ctime;	/* time inode (stat data) was last changed (except changes to sd_atime and sd_mtime) */
+
+	/*
+	 * time inode (stat data) was last changed
+	 * (except changes to sd_atime and sd_mtime)
+	 */
+	__le32 sd_ctime;
 	__le32 sd_blocks;
 	union {
 		__le32 sd_rdev;
 		__le32 sd_generation;
-		//__le32 sd_first_direct_byte;
-		/* first byte of file which is stored in a
-		   direct item: except that if it equals 1
-		   it is a symlink and if it equals
-		   ~(__u32)0 there is no direct item.  The
-		   existence of this field really grates
-		   on me. Let's replace it with a macro
-		   based on sd_size and our tail
-		   suppression policy? */
 	} __attribute__ ((__packed__)) u;
 } __attribute__ ((__packed__));
-//
-// this is 44 bytes long
-//
+
+/* this is 44 bytes long */
 #define SD_SIZE (sizeof(struct stat_data))
 #define SD_V2_SIZE              SD_SIZE
 #define stat_data_v2(ih)        (ih_version (ih) == KEY_FORMAT_3_6)
@@ -1613,48 +1839,61 @@ struct stat_data {
 #define sd_v2_attrs(sdp)         (le16_to_cpu((sdp)->sd_attrs))
 #define set_sd_v2_attrs(sdp,v)   ((sdp)->sd_attrs = cpu_to_le16(v))
 
-/***************************************************************************/
-/*                      DIRECTORY STRUCTURE                                */
-/***************************************************************************/
-/* 
-   Picture represents the structure of directory items
-   ________________________________________________
-   |  Array of     |   |     |        |       |   |
-   | directory     |N-1| N-2 | ....   |   1st |0th|
-   | entry headers |   |     |        |       |   |
-   |_______________|___|_____|________|_______|___|
-                    <----   directory entries         ------>
-
- First directory item has k_offset component 1. We store "." and ".."
- in one item, always, we never split "." and ".." into differing
- items.  This makes, among other things, the code for removing
- directories simpler. */
+/***************************************************************************
+ *                      DIRECTORY STRUCTURE                                *
+ ***************************************************************************/
+/*
+ * Picture represents the structure of directory items
+ * ________________________________________________
+ * |  Array of     |   |     |        |       |   |
+ * | directory     |N-1| N-2 | ....   |   1st |0th|
+ * | entry headers |   |     |        |       |   |
+ * |_______________|___|_____|________|_______|___|
+ *                  <----   directory entries         ------>
+ *
+ * First directory item has k_offset component 1. We store "." and ".."
+ * in one item, always, we never split "." and ".." into differing
+ * items.  This makes, among other things, the code for removing
+ * directories simpler.
+ */
 #define SD_OFFSET  0
 #define SD_UNIQUENESS 0
 #define DOT_OFFSET 1
 #define DOT_DOT_OFFSET 2
 #define DIRENTRY_UNIQUENESS 500
 
-/* */
 #define FIRST_ITEM_OFFSET 1
 
 /*
-   Q: How to get key of object pointed to by entry from entry?  
-
-   A: Each directory entry has its header. This header has deh_dir_id and deh_objectid fields, those are key
-      of object, entry points to */
+ * Q: How to get key of object pointed to by entry from entry?
+ *
+ * A: Each directory entry has its header. This header has deh_dir_id
+ *    and deh_objectid fields, those are key of object, entry points to
+ */
 
-/* NOT IMPLEMENTED:   
-   Directory will someday contain stat data of object */
+/*
+ * NOT IMPLEMENTED:
+ * Directory will someday contain stat data of object
+ */
 
 struct reiserfs_de_head {
 	__le32 deh_offset;	/* third component of the directory entry key */
-	__le32 deh_dir_id;	/* objectid of the parent directory of the object, that is referenced
-				   by directory entry */
-	__le32 deh_objectid;	/* objectid of the object, that is referenced by directory entry */
+
+	/*
+	 * objectid of the parent directory of the object, that is referenced
+	 * by directory entry
+	 */
+	__le32 deh_dir_id;
+
+	/* objectid of the object, that is referenced by directory entry */
+	__le32 deh_objectid;
 	__le16 deh_location;	/* offset of name in the whole item */
-	__le16 deh_state;	/* whether 1) entry contains stat data (for future), and 2) whether
-				   entry is hidden (unlinked) */
+
+	/*
+	 * whether 1) entry contains stat data (for future), and
+	 * 2) whether entry is hidden (unlinked)
+	 */
+	__le16 deh_state;
 } __attribute__ ((__packed__));
 #define DEH_SIZE                  sizeof(struct reiserfs_de_head)
 #define deh_offset(p_deh)         (le32_to_cpu((p_deh)->deh_offset))
@@ -1684,9 +1923,11 @@ struct reiserfs_de_head {
 #   define ADDR_UNALIGNED_BITS  (3)
 #endif
 
-/* These are only used to manipulate deh_state.
+/*
+ * These are only used to manipulate deh_state.
  * Because of this, we'll use the ext2_ bit routines,
- * since they are little endian */
+ * since they are little endian
+ */
 #ifdef ADDR_UNALIGNED_BITS
 
 #   define aligned_address(addr)           ((void *)((long)(addr) & ~((1UL << ADDR_UNALIGNED_BITS) - 1)))
@@ -1721,46 +1962,16 @@ extern void make_empty_dir_item_v1(char *body, __le32 dirid, __le32 objid,
 extern void make_empty_dir_item(char *body, __le32 dirid, __le32 objid,
 				__le32 par_dirid, __le32 par_objid);
 
-/* array of the entry headers */
- /* get item body */
-#define B_I_PITEM(bh,ih) ( (bh)->b_data + ih_location(ih) )
-#define B_I_DEH(bh,ih) ((struct reiserfs_de_head *)(B_I_PITEM(bh,ih)))
-
-/* length of the directory entry in directory item. This define
-   calculates length of i-th directory entry using directory entry
-   locations from dir entry head. When it calculates length of 0-th
-   directory entry, it uses length of whole item in place of entry
-   location of the non-existent following entry in the calculation.
-   See picture above.*/
-/*
-#define I_DEH_N_ENTRY_LENGTH(ih,deh,i) \
-((i) ? (deh_location((deh)-1) - deh_location((deh))) : (ih_item_len((ih)) - deh_location((deh))))
-*/
-static inline int entry_length(const struct buffer_head *bh,
-			       const struct item_head *ih, int pos_in_item)
-{
-	struct reiserfs_de_head *deh;
-
-	deh = B_I_DEH(bh, ih) + pos_in_item;
-	if (pos_in_item)
-		return deh_location(deh - 1) - deh_location(deh);
-
-	return ih_item_len(ih) - deh_location(deh);
-}
-
-/* number of entries in the directory item, depends on ENTRY_COUNT being at the start of directory dynamic data. */
-#define I_ENTRY_COUNT(ih) (ih_entry_count((ih)))
-
-/* name by bh, ih and entry_num */
-#define B_I_E_NAME(bh,ih,entry_num) ((char *)(bh->b_data + ih_location(ih) + deh_location(B_I_DEH(bh,ih)+(entry_num))))
-
-// two entries per block (at least)
+/* two entries per block (at least) */
 #define REISERFS_MAX_NAME(block_size) 255
 
-/* this structure is used for operations on directory entries. It is
-   not a disk structure. */
-/* When reiserfs_find_entry or search_by_entry_key find directory
-   entry, they return filled reiserfs_dir_entry structure */
+/*
+ * this structure is used for operations on directory entries. It is
+ * not a disk structure.
+ *
+ * When reiserfs_find_entry or search_by_entry_key find directory
+ * entry, they return filled reiserfs_dir_entry structure
+ */
 struct reiserfs_dir_entry {
 	struct buffer_head *de_bh;
 	int de_item_num;
@@ -1778,10 +1989,14 @@ struct reiserfs_dir_entry {
 	struct cpu_key de_entry_key;
 };
 
-/* these defines are useful when a particular member of a reiserfs_dir_entry is needed */
+/*
+ * these defines are useful when a particular member of
+ * a reiserfs_dir_entry is needed
+ */
 
 /* pointer to file name, stored in entry */
-#define B_I_DEH_ENTRY_FILE_NAME(bh,ih,deh) (B_I_PITEM (bh, ih) + deh_location(deh))
+#define B_I_DEH_ENTRY_FILE_NAME(bh, ih, deh) \
+				(ih_item_body(bh, ih) + deh_location(deh))
 
 /* length of name */
 #define I_DEH_N_ENTRY_FILE_NAME_LENGTH(ih,deh,entry_num) \
@@ -1804,11 +2019,13 @@ struct reiserfs_dir_entry {
  * |______|_______________|___________________|___________|
  */
 
-/***************************************************************************/
-/*                      DISK CHILD                                         */
-/***************************************************************************/
-/* Disk child pointer: The pointer from an internal node of the tree
-   to a node that is on disk. */
+/***************************************************************************
+ *                      DISK CHILD                                         *
+ ***************************************************************************/
+/*
+ * Disk child pointer:
+ * The pointer from an internal node of the tree to a node that is on disk.
+ */
 struct disk_child {
 	__le32 dc_block_number;	/* Disk child's block number. */
 	__le16 dc_size;		/* Disk child's used space.   */
@@ -1841,47 +2058,66 @@ struct disk_child {
 #define MAX_NR_KEY(bh) ( (MAX_CHILD_SIZE(bh)-DC_SIZE)/(KEY_SIZE+DC_SIZE) )
 #define MIN_NR_KEY(bh)    (MAX_NR_KEY(bh)/2)
 
-/***************************************************************************/
-/*                      PATH STRUCTURES AND DEFINES                        */
-/***************************************************************************/
+/***************************************************************************
+ *                      PATH STRUCTURES AND DEFINES                        *
+ ***************************************************************************/
 
-/* Search_by_key fills up the path from the root to the leaf as it descends the tree looking for the
-   key.  It uses reiserfs_bread to try to find buffers in the cache given their block number.  If it
-   does not find them in the cache it reads them from disk.  For each node search_by_key finds using
-   reiserfs_bread it then uses bin_search to look through that node.  bin_search will find the
-   position of the block_number of the next node if it is looking through an internal node.  If it
-   is looking through a leaf node bin_search will find the position of the item which has key either
-   equal to given key, or which is the maximal key less than the given key. */
+/*
+ * search_by_key fills up the path from the root to the leaf as it descends
+ * the tree looking for the key.  It uses reiserfs_bread to try to find
+ * buffers in the cache given their block number.  If it does not find
+ * them in the cache it reads them from disk.  For each node search_by_key
+ * finds using reiserfs_bread it then uses bin_search to look through that
+ * node.  bin_search will find the position of the block_number of the next
+ * node if it is looking through an internal node.  If it is looking through
+ * a leaf node bin_search will find the position of the item which has key
+ * either equal to given key, or which is the maximal key less than the
+ * given key.
+ */
 
 struct path_element {
-	struct buffer_head *pe_buffer;	/* Pointer to the buffer at the path in the tree. */
-	int pe_position;	/* Position in the tree node which is placed in the */
-	/* buffer above.                                  */
+	/* Pointer to the buffer at the path in the tree. */
+	struct buffer_head *pe_buffer;
+	/* Position in the tree node which is placed in the buffer above. */
+	int pe_position;
 };
 
-#define MAX_HEIGHT 5		/* maximal height of a tree. don't change this without changing JOURNAL_PER_BALANCE_CNT */
-#define EXTENDED_MAX_HEIGHT         7	/* Must be equals MAX_HEIGHT + FIRST_PATH_ELEMENT_OFFSET */
-#define FIRST_PATH_ELEMENT_OFFSET   2	/* Must be equal to at least 2. */
-
-#define ILLEGAL_PATH_ELEMENT_OFFSET 1	/* Must be equal to FIRST_PATH_ELEMENT_OFFSET - 1 */
-#define MAX_FEB_SIZE 6		/* this MUST be MAX_HEIGHT + 1. See about FEB below */
-
-/* We need to keep track of who the ancestors of nodes are.  When we
-   perform a search we record which nodes were visited while
-   descending the tree looking for the node we searched for. This list
-   of nodes is called the path.  This information is used while
-   performing balancing.  Note that this path information may become
-   invalid, and this means we must check it when using it to see if it
-   is still valid. You'll need to read search_by_key and the comments
-   in it, especially about decrement_counters_in_path(), to understand
-   this structure.  
-
-Paths make the code so much harder to work with and debug.... An
-enormous number of bugs are due to them, and trying to write or modify
-code that uses them just makes my head hurt.  They are based on an
-excessive effort to avoid disturbing the precious VFS code.:-( The
-gods only know how we are going to SMP the code that uses them.
-znodes are the way! */
+/*
+ * maximal height of a tree. don't change this without
+ * changing JOURNAL_PER_BALANCE_CNT
+ */
+#define MAX_HEIGHT 5
+
+/* Must be equals MAX_HEIGHT + FIRST_PATH_ELEMENT_OFFSET */
+#define EXTENDED_MAX_HEIGHT         7
+
+/* Must be equal to at least 2. */
+#define FIRST_PATH_ELEMENT_OFFSET   2
+
+/* Must be equal to FIRST_PATH_ELEMENT_OFFSET - 1 */
+#define ILLEGAL_PATH_ELEMENT_OFFSET 1
+
+/* this MUST be MAX_HEIGHT + 1. See about FEB below */
+#define MAX_FEB_SIZE 6
+
+/*
+ * We need to keep track of who the ancestors of nodes are.  When we
+ * perform a search we record which nodes were visited while
+ * descending the tree looking for the node we searched for. This list
+ * of nodes is called the path.  This information is used while
+ * performing balancing.  Note that this path information may become
+ * invalid, and this means we must check it when using it to see if it
+ * is still valid. You'll need to read search_by_key and the comments
+ * in it, especially about decrement_counters_in_path(), to understand
+ * this structure.
+ *
+ * Paths make the code so much harder to work with and debug.... An
+ * enormous number of bugs are due to them, and trying to write or modify
+ * code that uses them just makes my head hurt.  They are based on an
+ * excessive effort to avoid disturbing the precious VFS code.:-( The
+ * gods only know how we are going to SMP the code that uses them.
+ * znodes are the way!
+ */
 
 #define PATH_READA	0x1	/* do read ahead */
 #define PATH_READA_BACK 0x2	/* read backwards */
@@ -1889,7 +2125,8 @@ znodes are the way! */
 struct treepath {
 	int path_length;	/* Length of the array above.   */
 	int reada;
-	struct path_element path_elements[EXTENDED_MAX_HEIGHT];	/* Array of the path elements.  */
+	/* Array of the path elements.  */
+	struct path_element path_elements[EXTENDED_MAX_HEIGHT];
 	int pos_in_item;
 };
 
@@ -1908,41 +2145,124 @@ struct treepath var = {.path_length = ILLEGAL_PATH_ELEMENT_OFFSET, .reada = 0,}
 #define PATH_OFFSET_POSITION(path, n_offset) (PATH_OFFSET_PELEMENT(path, n_offset)->pe_position)
 
 #define PATH_PLAST_BUFFER(path) (PATH_OFFSET_PBUFFER((path), (path)->path_length))
-				/* you know, to the person who didn't
-				   write this the macro name does not
-				   at first suggest what it does.
-				   Maybe POSITION_FROM_PATH_END? Or
-				   maybe we should just focus on
-				   dumping paths... -Hans */
+
+/*
+ * you know, to the person who didn't write this the macro name does not
+ * at first suggest what it does.  Maybe POSITION_FROM_PATH_END? Or
+ * maybe we should just focus on dumping paths... -Hans
+ */
 #define PATH_LAST_POSITION(path) (PATH_OFFSET_POSITION((path), (path)->path_length))
 
-#define PATH_PITEM_HEAD(path)    B_N_PITEM_HEAD(PATH_PLAST_BUFFER(path), PATH_LAST_POSITION(path))
+/*
+ * in do_balance leaf has h == 0 in contrast with path structure,
+ * where root has level == 0. That is why we need these defines
+ */
+
+/* tb->S[h] */
+#define PATH_H_PBUFFER(path, h) \
+			PATH_OFFSET_PBUFFER(path, path->path_length - (h))
+
+/* tb->F[h] or tb->S[0]->b_parent */
+#define PATH_H_PPARENT(path, h) PATH_H_PBUFFER(path, (h) + 1)
+
+#define PATH_H_POSITION(path, h) \
+			PATH_OFFSET_POSITION(path, path->path_length - (h))
 
-/* in do_balance leaf has h == 0 in contrast with path structure,
-   where root has level == 0. That is why we need these defines */
-#define PATH_H_PBUFFER(path, h) PATH_OFFSET_PBUFFER (path, path->path_length - (h))	/* tb->S[h] */
-#define PATH_H_PPARENT(path, h) PATH_H_PBUFFER (path, (h) + 1)	/* tb->F[h] or tb->S[0]->b_parent */
-#define PATH_H_POSITION(path, h) PATH_OFFSET_POSITION (path, path->path_length - (h))
-#define PATH_H_B_ITEM_ORDER(path, h) PATH_H_POSITION(path, h + 1)	/* tb->S[h]->b_item_order */
+/* tb->S[h]->b_item_order */
+#define PATH_H_B_ITEM_ORDER(path, h) PATH_H_POSITION(path, h + 1)
 
 #define PATH_H_PATH_OFFSET(path, n_h) ((path)->path_length - (n_h))
 
+static inline void *reiserfs_node_data(const struct buffer_head *bh)
+{
+	return bh->b_data + sizeof(struct block_head);
+}
+
+/* get key from internal node */
+static inline struct reiserfs_key *internal_key(struct buffer_head *bh,
+						int item_num)
+{
+	struct reiserfs_key *key = reiserfs_node_data(bh);
+
+	return &key[item_num];
+}
+
+/* get the item header from leaf node */
+static inline struct item_head *item_head(const struct buffer_head *bh,
+					  int item_num)
+{
+	struct item_head *ih = reiserfs_node_data(bh);
+
+	return &ih[item_num];
+}
+
+/* get the key from leaf node */
+static inline struct reiserfs_key *leaf_key(const struct buffer_head *bh,
+					    int item_num)
+{
+	return &item_head(bh, item_num)->ih_key;
+}
+
+static inline void *ih_item_body(const struct buffer_head *bh,
+				 const struct item_head *ih)
+{
+	return bh->b_data + ih_location(ih);
+}
+
+/* get item body from leaf node */
+static inline void *item_body(const struct buffer_head *bh, int item_num)
+{
+	return ih_item_body(bh, item_head(bh, item_num));
+}
+
+static inline struct item_head *tp_item_head(const struct treepath *path)
+{
+	return item_head(PATH_PLAST_BUFFER(path), PATH_LAST_POSITION(path));
+}
+
+static inline void *tp_item_body(const struct treepath *path)
+{
+	return item_body(PATH_PLAST_BUFFER(path), PATH_LAST_POSITION(path));
+}
+
 #define get_last_bh(path) PATH_PLAST_BUFFER(path)
-#define get_ih(path) PATH_PITEM_HEAD(path)
 #define get_item_pos(path) PATH_LAST_POSITION(path)
-#define get_item(path) ((void *)B_N_PITEM(PATH_PLAST_BUFFER(path), PATH_LAST_POSITION (path)))
 #define item_moved(ih,path) comp_items(ih, path)
 #define path_changed(ih,path) comp_items (ih, path)
 
-/***************************************************************************/
-/*                       MISC                                              */
-/***************************************************************************/
+/* array of the entry headers */
+ /* get item body */
+#define B_I_DEH(bh, ih) ((struct reiserfs_de_head *)(ih_item_body(bh, ih)))
+
+/*
+ * length of the directory entry in directory item. This define
+ * calculates length of i-th directory entry using directory entry
+ * locations from dir entry head. When it calculates length of 0-th
+ * directory entry, it uses length of whole item in place of entry
+ * location of the non-existent following entry in the calculation.
+ * See picture above.
+ */
+static inline int entry_length(const struct buffer_head *bh,
+			       const struct item_head *ih, int pos_in_item)
+{
+	struct reiserfs_de_head *deh;
+
+	deh = B_I_DEH(bh, ih) + pos_in_item;
+	if (pos_in_item)
+		return deh_location(deh - 1) - deh_location(deh);
+
+	return ih_item_len(ih) - deh_location(deh);
+}
+
+/***************************************************************************
+ *                       MISC                                              *
+ ***************************************************************************/
 
 /* Size of pointer to the unformatted node. */
 #define UNFM_P_SIZE (sizeof(unp_t))
 #define UNFM_P_SHIFT 2
 
-// in in-core inode key is stored on le form
+/* in in-core inode key is stored on le form */
 #define INODE_PKEY(inode) ((struct reiserfs_key *)(REISERFS_I(inode)->i_key))
 
 #define MAX_UL_INT 0xffffffff
@@ -1958,7 +2278,6 @@ static inline loff_t max_reiserfs_offset(struct inode *inode)
 	return (loff_t) ((~(__u64) 0) >> 4);
 }
 
-/*#define MAX_KEY_UNIQUENESS	MAX_UL_INT*/
 #define MAX_KEY_OBJECTID	MAX_UL_INT
 
 #define MAX_B_NUM  MAX_UL_INT
@@ -1967,9 +2286,12 @@ static inline loff_t max_reiserfs_offset(struct inode *inode)
 /* the purpose is to detect overflow of an unsigned short */
 #define REISERFS_LINK_MAX (MAX_US_INT - 1000)
 
-/* The following defines are used in reiserfs_insert_item and reiserfs_append_item  */
-#define REISERFS_KERNEL_MEM		0	/* reiserfs kernel memory mode  */
-#define REISERFS_USER_MEM		1	/* reiserfs user memory mode            */
+/*
+ * The following defines are used in reiserfs_insert_item
+ * and reiserfs_append_item
+ */
+#define REISERFS_KERNEL_MEM		0	/* kernel memory mode */
+#define REISERFS_USER_MEM		1	/* user memory mode */
 
 #define fs_generation(s) (REISERFS_SB(s)->s_generation_counter)
 #define get_generation(s) atomic_read (&fs_generation(s))
@@ -1981,46 +2303,65 @@ static inline loff_t max_reiserfs_offset(struct inode *inode)
 	__fs_changed(gen, s);		\
 })
 
-/***************************************************************************/
-/*                  FIXATE NODES                                           */
-/***************************************************************************/
+/***************************************************************************
+ *                  FIXATE NODES                                           *
+ ***************************************************************************/
 
 #define VI_TYPE_LEFT_MERGEABLE 1
 #define VI_TYPE_RIGHT_MERGEABLE 2
 
-/* To make any changes in the tree we always first find node, that
-   contains item to be changed/deleted or place to insert a new
-   item. We call this node S. To do balancing we need to decide what
-   we will shift to left/right neighbor, or to a new node, where new
-   item will be etc. To make this analysis simpler we build virtual
-   node. Virtual node is an array of items, that will replace items of
-   node S. (For instance if we are going to delete an item, virtual
-   node does not contain it). Virtual node keeps information about
-   item sizes and types, mergeability of first and last items, sizes
-   of all entries in directory item. We use this array of items when
-   calculating what we can shift to neighbors and how many nodes we
-   have to have if we do not any shiftings, if we shift to left/right
-   neighbor or to both. */
+/*
+ * To make any changes in the tree we always first find node, that
+ * contains item to be changed/deleted or place to insert a new
+ * item. We call this node S. To do balancing we need to decide what
+ * we will shift to left/right neighbor, or to a new node, where new
+ * item will be etc. To make this analysis simpler we build virtual
+ * node. Virtual node is an array of items, that will replace items of
+ * node S. (For instance if we are going to delete an item, virtual
+ * node does not contain it). Virtual node keeps information about
+ * item sizes and types, mergeability of first and last items, sizes
+ * of all entries in directory item. We use this array of items when
+ * calculating what we can shift to neighbors and how many nodes we
+ * have to have if we do not any shiftings, if we shift to left/right
+ * neighbor or to both.
+ */
 struct virtual_item {
-	int vi_index;		// index in the array of item operations
-	unsigned short vi_type;	// left/right mergeability
-	unsigned short vi_item_len;	/* length of item that it will have after balancing */
+	int vi_index;		/* index in the array of item operations */
+	unsigned short vi_type;	/* left/right mergeability */
+
+	/* length of item that it will have after balancing */
+	unsigned short vi_item_len;
+
 	struct item_head *vi_ih;
-	const char *vi_item;	// body of item (old or new)
-	const void *vi_new_data;	// 0 always but paste mode
-	void *vi_uarea;		// item specific area
+	const char *vi_item;	/* body of item (old or new) */
+	const void *vi_new_data;	/* 0 always but paste mode */
+	void *vi_uarea;		/* item specific area */
 };
 
 struct virtual_node {
-	char *vn_free_ptr;	/* this is a pointer to the free space in the buffer */
+	/* this is a pointer to the free space in the buffer */
+	char *vn_free_ptr;
+
 	unsigned short vn_nr_item;	/* number of items in virtual node */
-	short vn_size;		/* size of node , that node would have if it has unlimited size and no balancing is performed */
-	short vn_mode;		/* mode of balancing (paste, insert, delete, cut) */
+
+	/*
+	 * size of node , that node would have if it has
+	 * unlimited size and no balancing is performed
+	 */
+	short vn_size;
+
+	/* mode of balancing (paste, insert, delete, cut) */
+	short vn_mode;
+
 	short vn_affected_item_num;
 	short vn_pos_in_item;
-	struct item_head *vn_ins_ih;	/* item header of inserted item, 0 for other modes */
+
+	/* item header of inserted item, 0 for other modes */
+	struct item_head *vn_ins_ih;
 	const void *vn_data;
-	struct virtual_item *vn_vi;	/* array of items (including a new one, excluding item to be deleted) */
+
+	/* array of items (including a new one, excluding item to be deleted) */
+	struct virtual_item *vn_vi;
 };
 
 /* used by directory items when creating virtual nodes */
@@ -2030,22 +2371,25 @@ struct direntry_uarea {
 	__u16 entry_sizes[1];
 } __attribute__ ((__packed__));
 
-/***************************************************************************/
-/*                  TREE BALANCE                                           */
-/***************************************************************************/
+/***************************************************************************
+ *                  TREE BALANCE                                           *
+ ***************************************************************************/
 
-/* This temporary structure is used in tree balance algorithms, and
-   constructed as we go to the extent that its various parts are
-   needed.  It contains arrays of nodes that can potentially be
-   involved in the balancing of node S, and parameters that define how
-   each of the nodes must be balanced.  Note that in these algorithms
-   for balancing the worst case is to need to balance the current node
-   S and the left and right neighbors and all of their parents plus
-   create a new node.  We implement S1 balancing for the leaf nodes
-   and S0 balancing for the internal nodes (S1 and S0 are defined in
-   our papers.)*/
+/*
+ * This temporary structure is used in tree balance algorithms, and
+ * constructed as we go to the extent that its various parts are
+ * needed.  It contains arrays of nodes that can potentially be
+ * involved in the balancing of node S, and parameters that define how
+ * each of the nodes must be balanced.  Note that in these algorithms
+ * for balancing the worst case is to need to balance the current node
+ * S and the left and right neighbors and all of their parents plus
+ * create a new node.  We implement S1 balancing for the leaf nodes
+ * and S0 balancing for the internal nodes (S1 and S0 are defined in
+ * our papers.)
+ */
 
-#define MAX_FREE_BLOCK 7	/* size of the array of buffers to free at end of do_balance */
+/* size of the array of buffers to free at end of do_balance */
+#define MAX_FREE_BLOCK 7
 
 /* maximum number of FEB blocknrs on a single level */
 #define MAX_AMOUNT_NEEDED 2
@@ -2057,64 +2401,144 @@ struct tree_balance {
 	struct super_block *tb_sb;
 	struct reiserfs_transaction_handle *transaction_handle;
 	struct treepath *tb_path;
-	struct buffer_head *L[MAX_HEIGHT];	/* array of left neighbors of nodes in the path */
-	struct buffer_head *R[MAX_HEIGHT];	/* array of right neighbors of nodes in the path */
-	struct buffer_head *FL[MAX_HEIGHT];	/* array of fathers of the left  neighbors      */
-	struct buffer_head *FR[MAX_HEIGHT];	/* array of fathers of the right neighbors      */
-	struct buffer_head *CFL[MAX_HEIGHT];	/* array of common parents of center node and its left neighbor  */
-	struct buffer_head *CFR[MAX_HEIGHT];	/* array of common parents of center node and its right neighbor */
-
-	struct buffer_head *FEB[MAX_FEB_SIZE];	/* array of empty buffers. Number of buffers in array equals
-						   cur_blknum. */
+
+	/* array of left neighbors of nodes in the path */
+	struct buffer_head *L[MAX_HEIGHT];
+
+	/* array of right neighbors of nodes in the path */
+	struct buffer_head *R[MAX_HEIGHT];
+
+	/* array of fathers of the left neighbors */
+	struct buffer_head *FL[MAX_HEIGHT];
+
+	/* array of fathers of the right neighbors */
+	struct buffer_head *FR[MAX_HEIGHT];
+	/* array of common parents of center node and its left neighbor */
+	struct buffer_head *CFL[MAX_HEIGHT];
+
+	/* array of common parents of center node and its right neighbor */
+	struct buffer_head *CFR[MAX_HEIGHT];
+
+	/*
+	 * array of empty buffers. Number of buffers in array equals
+	 * cur_blknum.
+	 */
+	struct buffer_head *FEB[MAX_FEB_SIZE];
 	struct buffer_head *used[MAX_FEB_SIZE];
 	struct buffer_head *thrown[MAX_FEB_SIZE];
-	int lnum[MAX_HEIGHT];	/* array of number of items which must be
-				   shifted to the left in order to balance the
-				   current node; for leaves includes item that
-				   will be partially shifted; for internal
-				   nodes, it is the number of child pointers
-				   rather than items. It includes the new item
-				   being created. The code sometimes subtracts
-				   one to get the number of wholly shifted
-				   items for other purposes. */
-	int rnum[MAX_HEIGHT];	/* substitute right for left in comment above */
-	int lkey[MAX_HEIGHT];	/* array indexed by height h mapping the key delimiting L[h] and
-				   S[h] to its item number within the node CFL[h] */
-	int rkey[MAX_HEIGHT];	/* substitute r for l in comment above */
-	int insert_size[MAX_HEIGHT];	/* the number of bytes by we are trying to add or remove from
-					   S[h]. A negative value means removing.  */
-	int blknum[MAX_HEIGHT];	/* number of nodes that will replace node S[h] after
-				   balancing on the level h of the tree.  If 0 then S is
-				   being deleted, if 1 then S is remaining and no new nodes
-				   are being created, if 2 or 3 then 1 or 2 new nodes is
-				   being created */
+
+	/*
+	 * array of number of items which must be shifted to the left in
+	 * order to balance the current node; for leaves includes item that
+	 * will be partially shifted; for internal nodes, it is the number
+	 * of child pointers rather than items. It includes the new item
+	 * being created. The code sometimes subtracts one to get the
+	 * number of wholly shifted items for other purposes.
+	 */
+	int lnum[MAX_HEIGHT];
+
+	/* substitute right for left in comment above */
+	int rnum[MAX_HEIGHT];
+
+	/*
+	 * array indexed by height h mapping the key delimiting L[h] and
+	 * S[h] to its item number within the node CFL[h]
+	 */
+	int lkey[MAX_HEIGHT];
+
+	/* substitute r for l in comment above */
+	int rkey[MAX_HEIGHT];
+
+	/*
+	 * the number of bytes by we are trying to add or remove from
+	 * S[h]. A negative value means removing.
+	 */
+	int insert_size[MAX_HEIGHT];
+
+	/*
+	 * number of nodes that will replace node S[h] after balancing
+	 * on the level h of the tree.  If 0 then S is being deleted,
+	 * if 1 then S is remaining and no new nodes are being created,
+	 * if 2 or 3 then 1 or 2 new nodes is being created
+	 */
+	int blknum[MAX_HEIGHT];
 
 	/* fields that are used only for balancing leaves of the tree */
-	int cur_blknum;		/* number of empty blocks having been already allocated                 */
-	int s0num;		/* number of items that fall into left most  node when S[0] splits     */
-	int s1num;		/* number of items that fall into first  new node when S[0] splits     */
-	int s2num;		/* number of items that fall into second new node when S[0] splits     */
-	int lbytes;		/* number of bytes which can flow to the left neighbor from the        left    */
-	/* most liquid item that cannot be shifted from S[0] entirely         */
-	/* if -1 then nothing will be partially shifted */
-	int rbytes;		/* number of bytes which will flow to the right neighbor from the right        */
-	/* most liquid item that cannot be shifted from S[0] entirely         */
-	/* if -1 then nothing will be partially shifted                           */
-	int s1bytes;		/* number of bytes which flow to the first  new node when S[0] splits   */
-	/* note: if S[0] splits into 3 nodes, then items do not need to be cut  */
-	int s2bytes;
-	struct buffer_head *buf_to_free[MAX_FREE_BLOCK];	/* buffers which are to be freed after do_balance finishes by unfix_nodes */
-	char *vn_buf;		/* kmalloced memory. Used to create
-				   virtual node and keep map of
-				   dirtied bitmap blocks */
+
+	/* number of empty blocks having been already allocated */
+	int cur_blknum;
+
+	/* number of items that fall into left most node when S[0] splits */
+	int s0num;
+
+	/*
+	 * number of bytes which can flow to the left neighbor from the left
+	 * most liquid item that cannot be shifted from S[0] entirely
+	 * if -1 then nothing will be partially shifted
+	 */
+	int lbytes;
+
+	/*
+	 * number of bytes which will flow to the right neighbor from the right
+	 * most liquid item that cannot be shifted from S[0] entirely
+	 * if -1 then nothing will be partially shifted
+	 */
+	int rbytes;
+
+
+	/*
+	 * index into the array of item headers in
+	 * S[0] of the affected item
+	 */
+	int item_pos;
+
+	/* new nodes allocated to hold what could not fit into S */
+	struct buffer_head *S_new[2];
+
+	/*
+	 * number of items that will be placed into nodes in S_new
+	 * when S[0] splits
+	 */
+	int snum[2];
+
+	/*
+	 * number of bytes which flow to nodes in S_new when S[0] splits
+	 * note: if S[0] splits into 3 nodes, then items do not need to be cut
+	 */
+	int sbytes[2];
+
+	int pos_in_item;
+	int zeroes_num;
+
+	/*
+	 * buffers which are to be freed after do_balance finishes
+	 * by unfix_nodes
+	 */
+	struct buffer_head *buf_to_free[MAX_FREE_BLOCK];
+
+	/*
+	 * kmalloced memory. Used to create virtual node and keep
+	 * map of dirtied bitmap blocks
+	 */
+	char *vn_buf;
+
 	int vn_buf_size;	/* size of the vn_buf */
-	struct virtual_node *tb_vn;	/* VN starts after bitmap of bitmap blocks */
 
-	int fs_gen;		/* saved value of `reiserfs_generation' counter
-				   see FILESYSTEM_CHANGED() macro in reiserfs_fs.h */
+	/* VN starts after bitmap of bitmap blocks */
+	struct virtual_node *tb_vn;
+
+	/*
+	 * saved value of `reiserfs_generation' counter see
+	 * FILESYSTEM_CHANGED() macro in reiserfs_fs.h
+	 */
+	int fs_gen;
+
 #ifdef DISPLACE_NEW_PACKING_LOCALITIES
-	struct in_core_key key;	/* key pointer, to pass to block allocator or
-				   another low-level subsystem */
+	/*
+	 * key pointer, to pass to block allocator or
+	 * another low-level subsystem
+	 */
+	struct in_core_key key;
 #endif
 };
 
@@ -2122,20 +2546,24 @@ struct tree_balance {
 
 /* When inserting an item. */
 #define M_INSERT	'i'
-/* When inserting into (directories only) or appending onto an already
-   existent item. */
+/*
+ * When inserting into (directories only) or appending onto an already
+ * existent item.
+ */
 #define M_PASTE		'p'
 /* When deleting an item. */
 #define M_DELETE	'd'
 /* When truncating an item or removing an entry from a (directory) item. */
-#define M_CUT 		'c'
+#define M_CUT		'c'
 
 /* used when balancing on leaf level skipped (in reiserfsck) */
 #define M_INTERNAL	'n'
 
-/* When further balancing is not needed, then do_balance does not need
-   to be called. */
-#define M_SKIP_BALANCING 		's'
+/*
+ * When further balancing is not needed, then do_balance does not need
+ * to be called.
+ */
+#define M_SKIP_BALANCING		's'
 #define M_CONVERT	'v'
 
 /* modes of leaf_move_items */
@@ -2148,8 +2576,10 @@ struct tree_balance {
 #define FIRST_TO_LAST 0
 #define LAST_TO_FIRST 1
 
-/* used in do_balance for passing parent of node information that has
-   been gotten from tb struct */
+/*
+ * used in do_balance for passing parent of node information that has
+ * been gotten from tb struct
+ */
 struct buffer_info {
 	struct tree_balance *tb;
 	struct buffer_head *bi_bh;
@@ -2167,20 +2597,24 @@ static inline struct super_block *sb_from_bi(struct buffer_info *bi)
 	return bi ? sb_from_tb(bi->tb) : NULL;
 }
 
-/* there are 4 types of items: stat data, directory item, indirect, direct.
-+-------------------+------------+--------------+------------+
-|	            |  k_offset  | k_uniqueness | mergeable? |
-+-------------------+------------+--------------+------------+
-|     stat data     |	0        |      0       |   no       |
-+-------------------+------------+--------------+------------+
-| 1st directory item| DOT_OFFSET |DIRENTRY_UNIQUENESS|   no       | 
-| non 1st directory | hash value |              |   yes      |
-|     item          |            |              |            |
-+-------------------+------------+--------------+------------+
-| indirect item     | offset + 1 |TYPE_INDIRECT |   if this is not the first indirect item of the object
-+-------------------+------------+--------------+------------+
-| direct item       | offset + 1 |TYPE_DIRECT   | if not this is not the first direct item of the object
-+-------------------+------------+--------------+------------+
+/*
+ * there are 4 types of items: stat data, directory item, indirect, direct.
+ * +-------------------+------------+--------------+------------+
+ * |                   |  k_offset  | k_uniqueness | mergeable? |
+ * +-------------------+------------+--------------+------------+
+ * |     stat data     |     0      |      0       |   no       |
+ * +-------------------+------------+--------------+------------+
+ * | 1st directory item| DOT_OFFSET | DIRENTRY_ .. |   no       |
+ * | non 1st directory | hash value | UNIQUENESS   |   yes      |
+ * |     item          |            |              |            |
+ * +-------------------+------------+--------------+------------+
+ * | indirect item     | offset + 1 |TYPE_INDIRECT |    [1]	|
+ * +-------------------+------------+--------------+------------+
+ * | direct item       | offset + 1 |TYPE_DIRECT   |    [2]     |
+ * +-------------------+------------+--------------+------------+
+ *
+ * [1] if this is not the first indirect item of the object
+ * [2] if this is not the first direct item of the object
 */
 
 struct item_operations {
@@ -2219,49 +2653,43 @@ extern struct item_operations *item_ops[TYPE_ANY + 1];
 /* number of blocks pointed to by the indirect item */
 #define I_UNFM_NUM(ih)	(ih_item_len(ih) / UNFM_P_SIZE)
 
-/* the used space within the unformatted node corresponding to pos within the item pointed to by ih */
+/*
+ * the used space within the unformatted node corresponding
+ * to pos within the item pointed to by ih
+ */
 #define I_POS_UNFM_SIZE(ih,pos,size) (((pos) == I_UNFM_NUM(ih) - 1 ) ? (size) - ih_free_space(ih) : (size))
 
-/* number of bytes contained by the direct item or the unformatted nodes the indirect item points to */
-
-/* get the item header */
-#define B_N_PITEM_HEAD(bh,item_num) ( (struct item_head * )((bh)->b_data + BLKH_SIZE) + (item_num) )
-
-/* get key */
-#define B_N_PDELIM_KEY(bh,item_num) ( (struct reiserfs_key * )((bh)->b_data + BLKH_SIZE) + (item_num) )
-
-/* get the key */
-#define B_N_PKEY(bh,item_num) ( &(B_N_PITEM_HEAD(bh,item_num)->ih_key) )
-
-/* get item body */
-#define B_N_PITEM(bh,item_num) ( (bh)->b_data + ih_location(B_N_PITEM_HEAD((bh),(item_num))))
-
-/* get the stat data by the buffer header and the item order */
-#define B_N_STAT_DATA(bh,nr) \
-( (struct stat_data *)((bh)->b_data + ih_location(B_N_PITEM_HEAD((bh),(nr))) ) )
+/*
+ * number of bytes contained by the direct item or the
+ * unformatted nodes the indirect item points to
+ */
 
-    /* following defines use reiserfs buffer header and item header */
+/* following defines use reiserfs buffer header and item header */
 
 /* get stat-data */
 #define B_I_STAT_DATA(bh, ih) ( (struct stat_data * )((bh)->b_data + ih_location(ih)) )
 
-// this is 3976 for size==4096
+/* this is 3976 for size==4096 */
 #define MAX_DIRECT_ITEM_LEN(size) ((size) - BLKH_SIZE - 2*IH_SIZE - SD_SIZE - UNFM_P_SIZE)
 
-/* indirect items consist of entries which contain blocknrs, pos
-   indicates which entry, and B_I_POS_UNFM_POINTER resolves to the
-   blocknr contained by the entry pos points to */
-#define B_I_POS_UNFM_POINTER(bh,ih,pos) le32_to_cpu(*(((unp_t *)B_I_PITEM(bh,ih)) + (pos)))
-#define PUT_B_I_POS_UNFM_POINTER(bh,ih,pos, val) do {*(((unp_t *)B_I_PITEM(bh,ih)) + (pos)) = cpu_to_le32(val); } while (0)
+/*
+ * indirect items consist of entries which contain blocknrs, pos
+ * indicates which entry, and B_I_POS_UNFM_POINTER resolves to the
+ * blocknr contained by the entry pos points to
+ */
+#define B_I_POS_UNFM_POINTER(bh, ih, pos)				\
+	le32_to_cpu(*(((unp_t *)ih_item_body(bh, ih)) + (pos)))
+#define PUT_B_I_POS_UNFM_POINTER(bh, ih, pos, val)			\
+	(*(((unp_t *)ih_item_body(bh, ih)) + (pos)) = cpu_to_le32(val))
 
 struct reiserfs_iget_args {
 	__u32 objectid;
 	__u32 dirid;
 };
 
-/***************************************************************************/
-/*                    FUNCTION DECLARATIONS                                */
-/***************************************************************************/
+/***************************************************************************
+ *                    FUNCTION DECLARATIONS                                *
+ ***************************************************************************/
 
 #define get_journal_desc_magic(bh) (bh->b_data + bh->b_size - 12)
 
@@ -2273,7 +2701,10 @@ struct reiserfs_iget_args {
 /* first block written in a commit.  */
 struct reiserfs_journal_desc {
 	__le32 j_trans_id;	/* id of commit */
-	__le32 j_len;		/* length of commit. len +1 is the commit block */
+
+	/* length of commit. len +1 is the commit block */
+	__le32 j_len;
+
 	__le32 j_mount_id;	/* mount id of this trans */
 	__le32 j_realblock[1];	/* real locations for each block */
 };
@@ -2300,22 +2731,35 @@ struct reiserfs_journal_commit {
 #define set_commit_trans_id(c,val)     do { (c)->j_trans_id = cpu_to_le32 (val); } while (0)
 #define set_commit_trans_len(c,val)    do { (c)->j_len = cpu_to_le32 (val); } while (0)
 
-/* this header block gets written whenever a transaction is considered fully flushed, and is more recent than the
-** last fully flushed transaction.  fully flushed means all the log blocks and all the real blocks are on disk,
-** and this transaction does not need to be replayed.
-*/
+/*
+ * this header block gets written whenever a transaction is considered
+ * fully flushed, and is more recent than the last fully flushed transaction.
+ * fully flushed means all the log blocks and all the real blocks are on
+ * disk, and this transaction does not need to be replayed.
+ */
 struct reiserfs_journal_header {
-	__le32 j_last_flush_trans_id;	/* id of last fully flushed transaction */
-	__le32 j_first_unflushed_offset;	/* offset in the log of where to start replay after a crash */
+	/* id of last fully flushed transaction */
+	__le32 j_last_flush_trans_id;
+
+	/* offset in the log of where to start replay after a crash */
+	__le32 j_first_unflushed_offset;
+
 	__le32 j_mount_id;
 	/* 12 */ struct journal_params jh_journal;
 };
 
 /* biggest tunable defines are right here */
 #define JOURNAL_BLOCK_COUNT 8192	/* number of blocks in the journal */
-#define JOURNAL_TRANS_MAX_DEFAULT 1024	/* biggest possible single transaction, don't change for now (8/3/99) */
+
+/* biggest possible single transaction, don't change for now (8/3/99) */
+#define JOURNAL_TRANS_MAX_DEFAULT 1024
 #define JOURNAL_TRANS_MIN_DEFAULT 256
-#define JOURNAL_MAX_BATCH_DEFAULT   900	/* max blocks to batch into one transaction, don't make this any bigger than 900 */
+
+/*
+ * max blocks to batch into one transaction,
+ * don't make this any bigger than 900
+ */
+#define JOURNAL_MAX_BATCH_DEFAULT   900
 #define JOURNAL_MIN_RATIO 2
 #define JOURNAL_MAX_COMMIT_AGE 30
 #define JOURNAL_MAX_TRANS_AGE 30
@@ -2340,16 +2784,18 @@ struct reiserfs_journal_header {
 #define REISERFS_QUOTA_DEL_BLOCKS(s) 0
 #endif
 
-/* both of these can be as low as 1, or as high as you want.  The min is the
-** number of 4k bitmap nodes preallocated on mount. New nodes are allocated
-** as needed, and released when transactions are committed.  On release, if 
-** the current number of nodes is > max, the node is freed, otherwise, 
-** it is put on a free list for faster use later.
+/*
+ * both of these can be as low as 1, or as high as you want.  The min is the
+ * number of 4k bitmap nodes preallocated on mount. New nodes are allocated
+ * as needed, and released when transactions are committed.  On release, if
+ * the current number of nodes is > max, the node is freed, otherwise,
+ * it is put on a free list for faster use later.
 */
 #define REISERFS_MIN_BITMAP_NODES 10
 #define REISERFS_MAX_BITMAP_NODES 100
 
-#define JBH_HASH_SHIFT 13	/* these are based on journal hash size of 8192 */
+/* these are based on journal hash size of 8192 */
+#define JBH_HASH_SHIFT 13
 #define JBH_HASH_MASK 8191
 
 #define _jhashfn(sb,block)	\
@@ -2357,7 +2803,7 @@ struct reiserfs_journal_header {
 	 (((block)<<(JBH_HASH_SHIFT - 6)) ^ ((block) >> 13) ^ ((block) << (JBH_HASH_SHIFT - 12))))
 #define journal_hash(t,sb,block) ((t)[_jhashfn((sb),(block)) & JBH_HASH_MASK])
 
-// We need these to make journal.c code more readable
+/* We need these to make journal.c code more readable */
 #define journal_find_get_block(s, block) __find_get_block(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize)
 #define journal_getblk(s, block) __getblk(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize)
 #define journal_bread(s, block) __bread(SB_JOURNAL(s)->j_dev_bd, block, s->s_blocksize)
@@ -2365,12 +2811,14 @@ struct reiserfs_journal_header {
 enum reiserfs_bh_state_bits {
 	BH_JDirty = BH_PrivateStart,	/* buffer is in current transaction */
 	BH_JDirty_wait,
-	BH_JNew,		/* disk block was taken off free list before
-				 * being in a finished transaction, or
-				 * written to disk. Can be reused immed. */
+	/*
+	 * disk block was taken off free list before being in a
+	 * finished transaction, or written to disk. Can be reused immed.
+	 */
+	BH_JNew,
 	BH_JPrepared,
 	BH_JRestore_dirty,
-	BH_JTest,		// debugging only will go away
+	BH_JTest,		/* debugging only will go away */
 };
 
 BUFFER_FNS(JDirty, journaled);
@@ -2386,27 +2834,36 @@ TAS_BUFFER_FNS(JRestore_dirty, journal_restore_dirty);
 BUFFER_FNS(JTest, journal_test);
 TAS_BUFFER_FNS(JTest, journal_test);
 
-/*
-** transaction handle which is passed around for all journal calls
-*/
+/* transaction handle which is passed around for all journal calls */
 struct reiserfs_transaction_handle {
-	struct super_block *t_super;	/* super for this FS when journal_begin was
-					   called. saves calls to reiserfs_get_super
-					   also used by nested transactions to make
-					   sure they are nesting on the right FS
-					   _must_ be first in the handle
-					 */
+	/*
+	 * super for this FS when journal_begin was called. saves calls to
+	 * reiserfs_get_super also used by nested transactions to make
+	 * sure they are nesting on the right FS _must_ be first
+	 * in the handle
+	 */
+	struct super_block *t_super;
+
 	int t_refcount;
 	int t_blocks_logged;	/* number of blocks this writer has logged */
 	int t_blocks_allocated;	/* number of blocks this writer allocated */
-	unsigned int t_trans_id;	/* sanity check, equals the current trans id */
+
+	/* sanity check, equals the current trans id */
+	unsigned int t_trans_id;
+
 	void *t_handle_save;	/* save existing current->journal_info */
-	unsigned displace_new_blocks:1;	/* if new block allocation occurres, that block
-					   should be displaced from others */
+
+	/*
+	 * if new block allocation occurres, that block
+	 * should be displaced from others
+	 */
+	unsigned displace_new_blocks:1;
+
 	struct list_head t_list;
 };
 
-/* used to keep track of ordered and tail writes, attached to the buffer
+/*
+ * used to keep track of ordered and tail writes, attached to the buffer
  * head through b_journal_head.
  */
 struct reiserfs_jh {
@@ -2419,7 +2876,7 @@ void reiserfs_free_jh(struct buffer_head *bh);
 int reiserfs_add_tail_list(struct inode *inode, struct buffer_head *bh);
 int reiserfs_add_ordered_list(struct inode *inode, struct buffer_head *bh);
 int journal_mark_dirty(struct reiserfs_transaction_handle *,
-		       struct super_block *, struct buffer_head *bh);
+		       struct buffer_head *bh);
 
 static inline int reiserfs_file_data_log(struct inode *inode)
 {
@@ -2469,10 +2926,8 @@ int journal_init(struct super_block *, const char *j_dev_name, int old_format,
 int journal_release(struct reiserfs_transaction_handle *, struct super_block *);
 int journal_release_error(struct reiserfs_transaction_handle *,
 			  struct super_block *);
-int journal_end(struct reiserfs_transaction_handle *, struct super_block *,
-		unsigned long);
-int journal_end_sync(struct reiserfs_transaction_handle *, struct super_block *,
-		     unsigned long);
+int journal_end(struct reiserfs_transaction_handle *);
+int journal_end_sync(struct reiserfs_transaction_handle *);
 int journal_mark_freed(struct reiserfs_transaction_handle *,
 		       struct super_block *, b_blocknr_t blocknr);
 int journal_transaction_should_end(struct reiserfs_transaction_handle *, int);
@@ -2481,7 +2936,7 @@ int reiserfs_in_journal(struct super_block *sb, unsigned int bmap_nr,
 int journal_begin(struct reiserfs_transaction_handle *,
 		  struct super_block *sb, unsigned long);
 int journal_join_abort(struct reiserfs_transaction_handle *,
-		       struct super_block *sb, unsigned long);
+		       struct super_block *sb);
 void reiserfs_abort_journal(struct super_block *sb, int errno);
 void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...);
 int reiserfs_allocate_list_bitmaps(struct super_block *s,
@@ -2503,20 +2958,18 @@ int B_IS_IN_TREE(const struct buffer_head *);
 extern void copy_item_head(struct item_head *to,
 			   const struct item_head *from);
 
-// first key is in cpu form, second - le
+/* first key is in cpu form, second - le */
 extern int comp_short_keys(const struct reiserfs_key *le_key,
 			   const struct cpu_key *cpu_key);
 extern void le_key2cpu_key(struct cpu_key *to, const struct reiserfs_key *from);
 
-// both are in le form
+/* both are in le form */
 extern int comp_le_keys(const struct reiserfs_key *,
 			const struct reiserfs_key *);
 extern int comp_short_le_keys(const struct reiserfs_key *,
 			      const struct reiserfs_key *);
 
-//
-// get key version from on disk key - kludge
-//
+/* * get key version from on disk key - kludge */
 static inline int le_key_version(const struct reiserfs_key *key)
 {
 	int type;
@@ -2593,12 +3046,12 @@ void padd_item(char *item, int total_length, int length);
 
 /* inode.c */
 /* args for the create parameter of reiserfs_get_block */
-#define GET_BLOCK_NO_CREATE 0	/* don't create new blocks or convert tails */
-#define GET_BLOCK_CREATE 1	/* add anything you need to find block */
-#define GET_BLOCK_NO_HOLE 2	/* return -ENOENT for file holes */
-#define GET_BLOCK_READ_DIRECT 4	/* read the tail if indirect item not found */
-#define GET_BLOCK_NO_IMUX     8	/* i_mutex is not held, don't preallocate */
-#define GET_BLOCK_NO_DANGLE   16	/* don't leave any transactions running */
+#define GET_BLOCK_NO_CREATE 0	 /* don't create new blocks or convert tails */
+#define GET_BLOCK_CREATE 1	 /* add anything you need to find block */
+#define GET_BLOCK_NO_HOLE 2	 /* return -ENOENT for file holes */
+#define GET_BLOCK_READ_DIRECT 4	 /* read the tail if indirect item not found */
+#define GET_BLOCK_NO_IMUX     8	 /* i_mutex is not held, don't preallocate */
+#define GET_BLOCK_NO_DANGLE   16 /* don't leave any transactions running */
 
 void reiserfs_read_locked_inode(struct inode *inode,
 				struct reiserfs_iget_args *args);
@@ -2797,25 +3250,49 @@ struct buffer_head *get_FEB(struct tree_balance *);
 
 /* bitmap.c */
 
-/* structure contains hints for block allocator, and it is a container for
- * arguments, such as node, search path, transaction_handle, etc. */
+/*
+ * structure contains hints for block allocator, and it is a container for
+ * arguments, such as node, search path, transaction_handle, etc.
+ */
 struct __reiserfs_blocknr_hint {
-	struct inode *inode;	/* inode passed to allocator, if we allocate unf. nodes */
+	/* inode passed to allocator, if we allocate unf. nodes */
+	struct inode *inode;
+
 	sector_t block;		/* file offset, in blocks */
 	struct in_core_key key;
-	struct treepath *path;	/* search path, used by allocator to deternine search_start by
-				 * various ways */
-	struct reiserfs_transaction_handle *th;	/* transaction handle is needed to log super blocks and
-						 * bitmap blocks changes  */
+
+	/*
+	 * search path, used by allocator to deternine search_start by
+	 * various ways
+	 */
+	struct treepath *path;
+
+	/*
+	 * transaction handle is needed to log super blocks
+	 * and bitmap blocks changes
+	 */
+	struct reiserfs_transaction_handle *th;
+
 	b_blocknr_t beg, end;
-	b_blocknr_t search_start;	/* a field used to transfer search start value (block number)
-					 * between different block allocator procedures
-					 * (determine_search_start() and others) */
-	int prealloc_size;	/* is set in determine_prealloc_size() function, used by underlayed
-				 * function that do actual allocation */
-
-	unsigned formatted_node:1;	/* the allocator uses different polices for getting disk space for
-					 * formatted/unformatted blocks with/without preallocation */
+
+	/*
+	 * a field used to transfer search start value (block number)
+	 * between different block allocator procedures
+	 * (determine_search_start() and others)
+	 */
+	b_blocknr_t search_start;
+
+	/*
+	 * is set in determine_prealloc_size() function,
+	 * used by underlayed function that do actual allocation
+	 */
+	int prealloc_size;
+
+	/*
+	 * the allocator uses different polices for getting disk
+	 * space for formatted/unformatted blocks with/without preallocation
+	 */
+	unsigned formatted_node:1;
 	unsigned preallocate:1;
 };
 
@@ -2909,13 +3386,15 @@ __u32 r5_hash(const signed char *msg, int len);
 #define reiserfs_test_le_bit		test_bit_le
 #define reiserfs_find_next_zero_le_bit	find_next_zero_bit_le
 
-/* sometimes reiserfs_truncate may require to allocate few new blocks
-   to perform indirect2direct conversion. People probably used to
-   think, that truncate should work without problems on a filesystem
-   without free disk space. They may complain that they can not
-   truncate due to lack of free disk space. This spare space allows us
-   to not worry about it. 500 is probably too much, but it should be
-   absolutely safe */
+/*
+ * sometimes reiserfs_truncate may require to allocate few new blocks
+ * to perform indirect2direct conversion. People probably used to
+ * think, that truncate should work without problems on a filesystem
+ * without free disk space. They may complain that they can not
+ * truncate due to lack of free disk space. This spare space allows us
+ * to not worry about it. 500 is probably too much, but it should be
+ * absolutely safe
+ */
 #define SPARE_SPACE 500
 
 /* prototypes from ioctl.c */
diff --git a/fs/reiserfs/resize.c b/fs/reiserfs/resize.c
index a4ef5cd606e..6052d323bc9 100644
--- a/fs/reiserfs/resize.c
+++ b/fs/reiserfs/resize.c
@@ -53,8 +53,10 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 	}
 	bforget(bh);
 
-	/* old disk layout detection; those partitions can be mounted, but
-	 * cannot be resized */
+	/*
+	 * old disk layout detection; those partitions can be mounted, but
+	 * cannot be resized
+	 */
 	if (SB_BUFFER_WITH_SB(s)->b_blocknr * SB_BUFFER_WITH_SB(s)->b_size
 	    != REISERFS_DISK_OFFSET_IN_BYTES) {
 		printk
@@ -86,12 +88,14 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 			    ("reiserfs_resize: unable to allocate memory for journal bitmaps\n");
 			return -ENOMEM;
 		}
-		/* the new journal bitmaps are zero filled, now we copy in the bitmap
-		 ** node pointers from the old journal bitmap structs, and then
-		 ** transfer the new data structures into the journal struct.
-		 **
-		 ** using the copy_size var below allows this code to work for
-		 ** both shrinking and expanding the FS.
+		/*
+		 * the new journal bitmaps are zero filled, now we copy i
+		 * the bitmap node pointers from the old journal bitmap
+		 * structs, and then transfer the new data structures
+		 * into the journal struct.
+		 *
+		 * using the copy_size var below allows this code to work for
+		 * both shrinking and expanding the FS.
 		 */
 		copy_size = bmap_nr_new < bmap_nr ? bmap_nr_new : bmap_nr;
 		copy_size =
@@ -101,36 +105,45 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 			jb = SB_JOURNAL(s)->j_list_bitmap + i;
 			memcpy(jbitmap[i].bitmaps, jb->bitmaps, copy_size);
 
-			/* just in case vfree schedules on us, copy the new
-			 ** pointer into the journal struct before freeing the
-			 ** old one
+			/*
+			 * just in case vfree schedules on us, copy the new
+			 * pointer into the journal struct before freeing the
+			 * old one
 			 */
 			node_tmp = jb->bitmaps;
 			jb->bitmaps = jbitmap[i].bitmaps;
 			vfree(node_tmp);
 		}
 
-		/* allocate additional bitmap blocks, reallocate array of bitmap
-		 * block pointers */
+		/*
+		 * allocate additional bitmap blocks, reallocate
+		 * array of bitmap block pointers
+		 */
 		bitmap =
 		    vzalloc(sizeof(struct reiserfs_bitmap_info) * bmap_nr_new);
 		if (!bitmap) {
-			/* Journal bitmaps are still supersized, but the memory isn't
-			 * leaked, so I guess it's ok */
+			/*
+			 * Journal bitmaps are still supersized, but the
+			 * memory isn't leaked, so I guess it's ok
+			 */
 			printk("reiserfs_resize: unable to allocate memory.\n");
 			return -ENOMEM;
 		}
 		for (i = 0; i < bmap_nr; i++)
 			bitmap[i] = old_bitmap[i];
 
-		/* This doesn't go through the journal, but it doesn't have to.
-		 * The changes are still atomic: We're synced up when the journal
-		 * transaction begins, and the new bitmaps don't matter if the
-		 * transaction fails. */
+		/*
+		 * This doesn't go through the journal, but it doesn't have to.
+		 * The changes are still atomic: We're synced up when the
+		 * journal transaction begins, and the new bitmaps don't
+		 * matter if the transaction fails.
+		 */
 		for (i = bmap_nr; i < bmap_nr_new; i++) {
 			int depth;
-			/* don't use read_bitmap_block since it will cache
-			 * the uninitialized bitmap */
+			/*
+			 * don't use read_bitmap_block since it will cache
+			 * the uninitialized bitmap
+			 */
 			depth = reiserfs_write_unlock_nested(s);
 			bh = sb_bread(s, i * s->s_blocksize * 8);
 			reiserfs_write_lock_nested(s, depth);
@@ -147,7 +160,7 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 			depth = reiserfs_write_unlock_nested(s);
 			sync_dirty_buffer(bh);
 			reiserfs_write_lock_nested(s, depth);
-			// update bitmap_info stuff
+			/* update bitmap_info stuff */
 			bitmap[i].free_count = sb_blocksize(sb) * 8 - 1;
 			brelse(bh);
 		}
@@ -156,9 +169,11 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 		vfree(old_bitmap);
 	}
 
-	/* begin transaction, if there was an error, it's fine. Yes, we have
+	/*
+	 * begin transaction, if there was an error, it's fine. Yes, we have
 	 * incorrect bitmaps now, but none of it is ever going to touch the
-	 * disk anyway. */
+	 * disk anyway.
+	 */
 	err = journal_begin(&th, s, 10);
 	if (err)
 		return err;
@@ -167,7 +182,7 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 	info = SB_AP_BITMAP(s) + bmap_nr - 1;
 	bh = reiserfs_read_bitmap_block(s, bmap_nr - 1);
 	if (!bh) {
-		int jerr = journal_end(&th, s, 10);
+		int jerr = journal_end(&th);
 		if (jerr)
 			return jerr;
 		return -EIO;
@@ -178,14 +193,14 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 		reiserfs_clear_le_bit(i, bh->b_data);
 	info->free_count += s->s_blocksize * 8 - block_r;
 
-	journal_mark_dirty(&th, s, bh);
+	journal_mark_dirty(&th, bh);
 	brelse(bh);
 
 	/* Correct new last bitmap block - It may not be full */
 	info = SB_AP_BITMAP(s) + bmap_nr_new - 1;
 	bh = reiserfs_read_bitmap_block(s, bmap_nr_new - 1);
 	if (!bh) {
-		int jerr = journal_end(&th, s, 10);
+		int jerr = journal_end(&th);
 		if (jerr)
 			return jerr;
 		return -EIO;
@@ -194,7 +209,7 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 	reiserfs_prepare_for_journal(s, bh, 1);
 	for (i = block_r_new; i < s->s_blocksize * 8; i++)
 		reiserfs_set_le_bit(i, bh->b_data);
-	journal_mark_dirty(&th, s, bh);
+	journal_mark_dirty(&th, bh);
 	brelse(bh);
 
 	info->free_count -= s->s_blocksize * 8 - block_r_new;
@@ -207,8 +222,8 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new)
 	PUT_SB_BLOCK_COUNT(s, block_count_new);
 	PUT_SB_BMAP_NR(s, bmap_would_wrap(bmap_nr_new) ? : bmap_nr_new);
 
-	journal_mark_dirty(&th, s, SB_BUFFER_WITH_SB(s));
+	journal_mark_dirty(&th, SB_BUFFER_WITH_SB(s));
 
 	SB_JOURNAL(s)->j_must_wait = 1;
-	return journal_end(&th, s, 10);
+	return journal_end(&th);
 }
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 615cd9ab794..dd44468edc2 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -8,46 +8,6 @@
  *  Pereslavl-Zalessky Russia
  */
 
-/*
- *  This file contains functions dealing with S+tree
- *
- * B_IS_IN_TREE
- * copy_item_head
- * comp_short_keys
- * comp_keys
- * comp_short_le_keys
- * le_key2cpu_key
- * comp_le_keys
- * bin_search
- * get_lkey
- * get_rkey
- * key_in_buffer
- * decrement_bcount
- * reiserfs_check_path
- * pathrelse_and_restore
- * pathrelse
- * search_by_key_reada
- * search_by_key
- * search_for_position_by_key
- * comp_items
- * prepare_for_direct_item
- * prepare_for_direntry_item
- * prepare_for_delete_or_cut
- * calc_deleted_bytes_number
- * init_tb_struct
- * padd_item
- * reiserfs_delete_item
- * reiserfs_delete_solid_item
- * reiserfs_delete_object
- * maybe_indirect_to_direct
- * indirect_to_direct_roll_back
- * reiserfs_cut_from_item
- * truncate_directory
- * reiserfs_do_truncate
- * reiserfs_paste_into_item
- * reiserfs_insert_item
- */
-
 #include <linux/time.h>
 #include <linux/string.h>
 #include <linux/pagemap.h>
@@ -65,21 +25,21 @@ inline int B_IS_IN_TREE(const struct buffer_head *bh)
 	return (B_LEVEL(bh) != FREE_LEVEL);
 }
 
-//
-// to gets item head in le form
-//
+/* to get item head in le form */
 inline void copy_item_head(struct item_head *to,
 			   const struct item_head *from)
 {
 	memcpy(to, from, IH_SIZE);
 }
 
-/* k1 is pointer to on-disk structure which is stored in little-endian
-   form. k2 is pointer to cpu variable. For key of items of the same
-   object this returns 0.
-   Returns: -1 if key1 < key2
-   0 if key1 == key2
-   1 if key1 > key2 */
+/*
+ * k1 is pointer to on-disk structure which is stored in little-endian
+ * form. k2 is pointer to cpu variable. For key of items of the same
+ * object this returns 0.
+ * Returns: -1 if key1 < key2
+ * 0 if key1 == key2
+ * 1 if key1 > key2
+ */
 inline int comp_short_keys(const struct reiserfs_key *le_key,
 			   const struct cpu_key *cpu_key)
 {
@@ -97,11 +57,13 @@ inline int comp_short_keys(const struct reiserfs_key *le_key,
 	return 0;
 }
 
-/* k1 is pointer to on-disk structure which is stored in little-endian
-   form. k2 is pointer to cpu variable.
-   Compare keys using all 4 key fields.
-   Returns: -1 if key1 < key2 0
-   if key1 = key2 1 if key1 > key2 */
+/*
+ * k1 is pointer to on-disk structure which is stored in little-endian
+ * form. k2 is pointer to cpu variable.
+ * Compare keys using all 4 key fields.
+ * Returns: -1 if key1 < key2 0
+ * if key1 = key2 1 if key1 > key2
+ */
 static inline int comp_keys(const struct reiserfs_key *le_key,
 			    const struct cpu_key *cpu_key)
 {
@@ -155,15 +117,17 @@ inline void le_key2cpu_key(struct cpu_key *to, const struct reiserfs_key *from)
 	to->on_disk_key.k_dir_id = le32_to_cpu(from->k_dir_id);
 	to->on_disk_key.k_objectid = le32_to_cpu(from->k_objectid);
 
-	// find out version of the key
+	/* find out version of the key */
 	version = le_key_version(from);
 	to->version = version;
 	to->on_disk_key.k_offset = le_key_k_offset(version, from);
 	to->on_disk_key.k_type = le_key_k_type(version, from);
 }
 
-// this does not say which one is bigger, it only returns 1 if keys
-// are not equal, 0 otherwise
+/*
+ * this does not say which one is bigger, it only returns 1 if keys
+ * are not equal, 0 otherwise
+ */
 inline int comp_le_keys(const struct reiserfs_key *k1,
 			const struct reiserfs_key *k2)
 {
@@ -177,24 +141,27 @@ inline int comp_le_keys(const struct reiserfs_key *k1,
  *        *pos = number of the searched element if found, else the        *
  *        number of the first element that is larger than key.            *
  **************************************************************************/
-/* For those not familiar with binary search: lbound is the leftmost item that it
- could be, rbound the rightmost item that it could be.  We examine the item
- halfway between lbound and rbound, and that tells us either that we can increase
- lbound, or decrease rbound, or that we have found it, or if lbound <= rbound that
- there are no possible items, and we have not found it. With each examination we
- cut the number of possible items it could be by one more than half rounded down,
- or we find it. */
+/*
+ * For those not familiar with binary search: lbound is the leftmost item
+ * that it could be, rbound the rightmost item that it could be.  We examine
+ * the item halfway between lbound and rbound, and that tells us either
+ * that we can increase lbound, or decrease rbound, or that we have found it,
+ * or if lbound <= rbound that there are no possible items, and we have not
+ * found it. With each examination we cut the number of possible items it
+ * could be by one more than half rounded down, or we find it.
+ */
 static inline int bin_search(const void *key,	/* Key to search for. */
 			     const void *base,	/* First item in the array. */
 			     int num,	/* Number of items in the array. */
-			     int width,	/* Item size in the array.
-					   searched. Lest the reader be
-					   confused, note that this is crafted
-					   as a general function, and when it
-					   is applied specifically to the array
-					   of item headers in a node, width
-					   is actually the item header size not
-					   the item size. */
+			     /*
+			      * Item size in the array.  searched. Lest the
+			      * reader be confused, note that this is crafted
+			      * as a general function, and when it is applied
+			      * specifically to the array of item headers in a
+			      * node, width is actually the item header size
+			      * not the item size.
+			      */
+			     int width,
 			     int *pos /* Number of the searched for element. */
     )
 {
@@ -216,8 +183,10 @@ static inline int bin_search(const void *key,	/* Key to search for. */
 			return ITEM_FOUND;	/* Key found in the array.  */
 		}
 
-	/* bin_search did not find given key, it returns position of key,
-	   that is minimal and greater than the given one. */
+	/*
+	 * bin_search did not find given key, it returns position of key,
+	 * that is minimal and greater than the given one.
+	 */
 	*pos = lbound;
 	return ITEM_NOT_FOUND;
 }
@@ -234,10 +203,14 @@ static const struct reiserfs_key MAX_KEY = {
 	  cpu_to_le32(0xffffffff)},}
 };
 
-/* Get delimiting key of the buffer by looking for it in the buffers in the path, starting from the bottom
-   of the path, and going upwards.  We must check the path's validity at each step.  If the key is not in
-   the path, there is no delimiting key in the tree (buffer is first or last buffer in tree), and in this
-   case we return a special key, either MIN_KEY or MAX_KEY. */
+/*
+ * Get delimiting key of the buffer by looking for it in the buffers in the
+ * path, starting from the bottom of the path, and going upwards.  We must
+ * check the path's validity at each step.  If the key is not in the path,
+ * there is no delimiting key in the tree (buffer is first or last buffer
+ * in tree), and in this case we return a special key, either MIN_KEY or
+ * MAX_KEY.
+ */
 static inline const struct reiserfs_key *get_lkey(const struct treepath *chk_path,
 						  const struct super_block *sb)
 {
@@ -270,9 +243,12 @@ static inline const struct reiserfs_key *get_lkey(const struct treepath *chk_pat
 		    PATH_OFFSET_PBUFFER(chk_path,
 					path_offset + 1)->b_blocknr)
 			return &MAX_KEY;
-		/* Return delimiting key if position in the parent is not equal to zero. */
+		/*
+		 * Return delimiting key if position in the parent
+		 * is not equal to zero.
+		 */
 		if (position)
-			return B_N_PDELIM_KEY(parent, position - 1);
+			return internal_key(parent, position - 1);
 	}
 	/* Return MIN_KEY if we are in the root of the buffer tree. */
 	if (PATH_OFFSET_PBUFFER(chk_path, FIRST_PATH_ELEMENT_OFFSET)->
@@ -308,15 +284,23 @@ inline const struct reiserfs_key *get_rkey(const struct treepath *chk_path,
 					  path_offset)) >
 		    B_NR_ITEMS(parent))
 			return &MIN_KEY;
-		/* Check whether parent at the path really points to the child. */
+		/*
+		 * Check whether parent at the path really points
+		 * to the child.
+		 */
 		if (B_N_CHILD_NUM(parent, position) !=
 		    PATH_OFFSET_PBUFFER(chk_path,
 					path_offset + 1)->b_blocknr)
 			return &MIN_KEY;
-		/* Return delimiting key if position in the parent is not the last one. */
+
+		/*
+		 * Return delimiting key if position in the parent
+		 * is not the last one.
+		 */
 		if (position != B_NR_ITEMS(parent))
-			return B_N_PDELIM_KEY(parent, position);
+			return internal_key(parent, position);
 	}
+
 	/* Return MAX_KEY if we are in the root of the buffer tree. */
 	if (PATH_OFFSET_PBUFFER(chk_path, FIRST_PATH_ELEMENT_OFFSET)->
 	    b_blocknr == SB_ROOT_BLOCK(sb))
@@ -324,13 +308,20 @@ inline const struct reiserfs_key *get_rkey(const struct treepath *chk_path,
 	return &MIN_KEY;
 }
 
-/* Check whether a key is contained in the tree rooted from a buffer at a path. */
-/* This works by looking at the left and right delimiting keys for the buffer in the last path_element in
-   the path.  These delimiting keys are stored at least one level above that buffer in the tree. If the
-   buffer is the first or last node in the tree order then one of the delimiting keys may be absent, and in
-   this case get_lkey and get_rkey return a special key which is MIN_KEY or MAX_KEY. */
-static inline int key_in_buffer(struct treepath *chk_path,	/* Path which should be checked.  */
-				const struct cpu_key *key,	/* Key which should be checked.   */
+/*
+ * Check whether a key is contained in the tree rooted from a buffer at a path.
+ * This works by looking at the left and right delimiting keys for the buffer
+ * in the last path_element in the path.  These delimiting keys are stored
+ * at least one level above that buffer in the tree. If the buffer is the
+ * first or last node in the tree order then one of the delimiting keys may
+ * be absent, and in this case get_lkey and get_rkey return a special key
+ * which is MIN_KEY or MAX_KEY.
+ */
+static inline int key_in_buffer(
+				/* Path which should be checked. */
+				struct treepath *chk_path,
+				/* Key which should be checked. */
+				const struct cpu_key *key,
 				struct super_block *sb
     )
 {
@@ -359,9 +350,11 @@ int reiserfs_check_path(struct treepath *p)
 	return 0;
 }
 
-/* Drop the reference to each buffer in a path and restore
+/*
+ * Drop the reference to each buffer in a path and restore
  * dirty bits clean when preparing the buffer for the log.
- * This version should only be called from fix_nodes() */
+ * This version should only be called from fix_nodes()
+ */
 void pathrelse_and_restore(struct super_block *sb,
 			   struct treepath *search_path)
 {
@@ -418,14 +411,17 @@ static int is_leaf(char *buf, int blocksize, struct buffer_head *bh)
 	}
 	ih = (struct item_head *)(buf + BLKH_SIZE) + nr - 1;
 	used_space = BLKH_SIZE + IH_SIZE * nr + (blocksize - ih_location(ih));
+
+	/* free space does not match to calculated amount of use space */
 	if (used_space != blocksize - blkh_free_space(blkh)) {
-		/* free space does not match to calculated amount of use space */
 		reiserfs_warning(NULL, "reiserfs-5082",
 				 "free space seems wrong: %z", bh);
 		return 0;
 	}
-	// FIXME: it is_leaf will hit performance too much - we may have
-	// return 1 here
+	/*
+	 * FIXME: it is_leaf will hit performance too much - we may have
+	 * return 1 here
+	 */
 
 	/* check tables of item heads */
 	ih = (struct item_head *)(buf + BLKH_SIZE);
@@ -460,7 +456,7 @@ static int is_leaf(char *buf, int blocksize, struct buffer_head *bh)
 		prev_location = ih_location(ih);
 	}
 
-	// one may imagine much more checks
+	/* one may imagine many more checks */
 	return 1;
 }
 
@@ -481,8 +477,8 @@ static int is_internal(char *buf, int blocksize, struct buffer_head *bh)
 	}
 
 	nr = blkh_nr_item(blkh);
+	/* for internal which is not root we might check min number of keys */
 	if (nr > (blocksize - BLKH_SIZE - DC_SIZE) / (KEY_SIZE + DC_SIZE)) {
-		/* for internal which is not root we might check min number of keys */
 		reiserfs_warning(NULL, "reiserfs-5088",
 				 "number of key seems wrong: %z", bh);
 		return 0;
@@ -494,12 +490,15 @@ static int is_internal(char *buf, int blocksize, struct buffer_head *bh)
 				 "free space seems wrong: %z", bh);
 		return 0;
 	}
-	// one may imagine much more checks
+
+	/* one may imagine many more checks */
 	return 1;
 }
 
-// make sure that bh contains formatted node of reiserfs tree of
-// 'level'-th level
+/*
+ * make sure that bh contains formatted node of reiserfs tree of
+ * 'level'-th level
+ */
 static int is_tree_node(struct buffer_head *bh, int level)
 {
 	if (B_LEVEL(bh) != level) {
@@ -546,7 +545,8 @@ static int search_by_key_reada(struct super_block *s,
 	for (j = 0; j < i; j++) {
 		/*
 		 * note, this needs attention if we are getting rid of the BKL
-		 * you have to make sure the prepared bit isn't set on this buffer
+		 * you have to make sure the prepared bit isn't set on this
+		 * buffer
 		 */
 		if (!buffer_uptodate(bh[j])) {
 			if (depth == -1)
@@ -558,39 +558,34 @@ static int search_by_key_reada(struct super_block *s,
 	return depth;
 }
 
-/**************************************************************************
- * Algorithm   SearchByKey                                                *
- *             look for item in the Disk S+Tree by its key                *
- * Input:  sb   -  super block                                            *
- *         key  - pointer to the key to search                            *
- * Output: ITEM_FOUND, ITEM_NOT_FOUND or IO_ERROR                         *
- *         search_path - path from the root to the needed leaf            *
- **************************************************************************/
-
-/* This function fills up the path from the root to the leaf as it
-   descends the tree looking for the key.  It uses reiserfs_bread to
-   try to find buffers in the cache given their block number.  If it
-   does not find them in the cache it reads them from disk.  For each
-   node search_by_key finds using reiserfs_bread it then uses
-   bin_search to look through that node.  bin_search will find the
-   position of the block_number of the next node if it is looking
-   through an internal node.  If it is looking through a leaf node
-   bin_search will find the position of the item which has key either
-   equal to given key, or which is the maximal key less than the given
-   key.  search_by_key returns a path that must be checked for the
-   correctness of the top of the path but need not be checked for the
-   correctness of the bottom of the path */
-/* The function is NOT SCHEDULE-SAFE! */
-int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to search. */
-		  struct treepath *search_path,/* This structure was
-						   allocated and initialized
-						   by the calling
-						   function. It is filled up
-						   by this function.  */
-		  int stop_level	/* How far down the tree to search. To
-					   stop at leaf level - set to
-					   DISK_LEAF_NODE_LEVEL */
-    )
+/*
+ * This function fills up the path from the root to the leaf as it
+ * descends the tree looking for the key.  It uses reiserfs_bread to
+ * try to find buffers in the cache given their block number.  If it
+ * does not find them in the cache it reads them from disk.  For each
+ * node search_by_key finds using reiserfs_bread it then uses
+ * bin_search to look through that node.  bin_search will find the
+ * position of the block_number of the next node if it is looking
+ * through an internal node.  If it is looking through a leaf node
+ * bin_search will find the position of the item which has key either
+ * equal to given key, or which is the maximal key less than the given
+ * key.  search_by_key returns a path that must be checked for the
+ * correctness of the top of the path but need not be checked for the
+ * correctness of the bottom of the path
+ */
+/*
+ * search_by_key - search for key (and item) in stree
+ * @sb: superblock
+ * @key: pointer to key to search for
+ * @search_path: Allocated and initialized struct treepath; Returned filled
+ *		 on success.
+ * @stop_level: How far down the tree to search, Use DISK_LEAF_NODE_LEVEL to
+ *		stop at leaf level.
+ *
+ * The function is NOT SCHEDULE-SAFE!
+ */
+int search_by_key(struct super_block *sb, const struct cpu_key *key,
+		  struct treepath *search_path, int stop_level)
 {
 	b_blocknr_t block_number;
 	int expected_level;
@@ -609,17 +604,22 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 
 	PROC_INFO_INC(sb, search_by_key);
 
-	/* As we add each node to a path we increase its count.  This means that
-	   we must be careful to release all nodes in a path before we either
-	   discard the path struct or re-use the path struct, as we do here. */
+	/*
+	 * As we add each node to a path we increase its count.  This means
+	 * that we must be careful to release all nodes in a path before we
+	 * either discard the path struct or re-use the path struct, as we
+	 * do here.
+	 */
 
 	pathrelse(search_path);
 
 	right_neighbor_of_leaf_node = 0;
 
-	/* With each iteration of this loop we search through the items in the
-	   current node, and calculate the next current node(next path element)
-	   for the next iteration of this loop.. */
+	/*
+	 * With each iteration of this loop we search through the items in the
+	 * current node, and calculate the next current node(next path element)
+	 * for the next iteration of this loop..
+	 */
 	block_number = SB_ROOT_BLOCK(sb);
 	expected_level = -1;
 	while (1) {
@@ -639,8 +639,10 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 					 ++search_path->path_length);
 		fs_gen = get_generation(sb);
 
-		/* Read the next tree node, and set the last element in the path to
-		   have a pointer to it. */
+		/*
+		 * Read the next tree node, and set the last element
+		 * in the path to have a pointer to it.
+		 */
 		if ((bh = last_element->pe_buffer =
 		     sb_getblk(sb, block_number))) {
 
@@ -666,7 +668,7 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 			if (!buffer_uptodate(bh))
 				goto io_error;
 		} else {
-		      io_error:
+io_error:
 			search_path->path_length--;
 			pathrelse(search_path);
 			return IO_ERROR;
@@ -676,9 +678,12 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 			expected_level = SB_TREE_HEIGHT(sb);
 		expected_level--;
 
-		/* It is possible that schedule occurred. We must check whether the key
-		   to search is still in the tree rooted from the current buffer. If
-		   not then repeat search from the root. */
+		/*
+		 * It is possible that schedule occurred. We must check
+		 * whether the key to search is still in the tree rooted
+		 * from the current buffer. If not then repeat search
+		 * from the root.
+		 */
 		if (fs_changed(fs_gen, sb) &&
 		    (!B_IS_IN_TREE(bh) ||
 		     B_LEVEL(bh) != expected_level ||
@@ -689,8 +694,10 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 				      sbk_restarted[expected_level - 1]);
 			pathrelse(search_path);
 
-			/* Get the root block number so that we can repeat the search
-			   starting from the root. */
+			/*
+			 * Get the root block number so that we can
+			 * repeat the search starting from the root.
+			 */
 			block_number = SB_ROOT_BLOCK(sb);
 			expected_level = -1;
 			right_neighbor_of_leaf_node = 0;
@@ -699,9 +706,11 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 			continue;
 		}
 
-		/* only check that the key is in the buffer if key is not
-		   equal to the MAX_KEY. Latter case is only possible in
-		   "finish_unfinished()" processing during mount. */
+		/*
+		 * only check that the key is in the buffer if key is not
+		 * equal to the MAX_KEY. Latter case is only possible in
+		 * "finish_unfinished()" processing during mount.
+		 */
 		RFALSE(comp_keys(&MAX_KEY, key) &&
 		       !key_in_buffer(search_path, key, sb),
 		       "PAP-5130: key is not in the buffer");
@@ -713,8 +722,10 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 		}
 #endif
 
-		// make sure, that the node contents look like a node of
-		// certain level
+		/*
+		 * make sure, that the node contents look like a node of
+		 * certain level
+		 */
 		if (!is_tree_node(bh, expected_level)) {
 			reiserfs_error(sb, "vs-5150",
 				       "invalid format found in block %ld. "
@@ -732,32 +743,42 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 		       "vs-5152: tree level (%d) is less than stop level (%d)",
 		       node_level, stop_level);
 
-		retval = bin_search(key, B_N_PITEM_HEAD(bh, 0),
+		retval = bin_search(key, item_head(bh, 0),
 				      B_NR_ITEMS(bh),
 				      (node_level ==
 				       DISK_LEAF_NODE_LEVEL) ? IH_SIZE :
 				      KEY_SIZE,
-				      &(last_element->pe_position));
+				      &last_element->pe_position);
 		if (node_level == stop_level) {
 			return retval;
 		}
 
 		/* we are not in the stop level */
+		/*
+		 * item has been found, so we choose the pointer which
+		 * is to the right of the found one
+		 */
 		if (retval == ITEM_FOUND)
-			/* item has been found, so we choose the pointer which is to the right of the found one */
 			last_element->pe_position++;
 
-		/* if item was not found we choose the position which is to
-		   the left of the found item. This requires no code,
-		   bin_search did it already. */
+		/*
+		 * if item was not found we choose the position which is to
+		 * the left of the found item. This requires no code,
+		 * bin_search did it already.
+		 */
 
-		/* So we have chosen a position in the current node which is
-		   an internal node.  Now we calculate child block number by
-		   position in the node. */
+		/*
+		 * So we have chosen a position in the current node which is
+		 * an internal node.  Now we calculate child block number by
+		 * position in the node.
+		 */
 		block_number =
 		    B_N_CHILD_NUM(bh, last_element->pe_position);
 
-		/* if we are going to read leaf nodes, try for read ahead as well */
+		/*
+		 * if we are going to read leaf nodes, try for read
+		 * ahead as well
+		 */
 		if ((search_path->reada & PATH_READA) &&
 		    node_level == DISK_LEAF_NODE_LEVEL + 1) {
 			int pos = last_element->pe_position;
@@ -779,7 +800,7 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 				/*
 				 * check to make sure we're in the same object
 				 */
-				le_key = B_N_PDELIM_KEY(bh, pos);
+				le_key = internal_key(bh, pos);
 				if (le32_to_cpu(le_key->k_objectid) !=
 				    key->on_disk_key.k_objectid) {
 					break;
@@ -789,26 +810,28 @@ int search_by_key(struct super_block *sb, const struct cpu_key *key,	/* Key to s
 	}
 }
 
-/* Form the path to an item and position in this item which contains
-   file byte defined by key. If there is no such item
-   corresponding to the key, we point the path to the item with
-   maximal key less than key, and *pos_in_item is set to one
-   past the last entry/byte in the item.  If searching for entry in a
-   directory item, and it is not found, *pos_in_item is set to one
-   entry more than the entry with maximal key which is less than the
-   sought key.
-
-   Note that if there is no entry in this same node which is one more,
-   then we point to an imaginary entry.  for direct items, the
-   position is in units of bytes, for indirect items the position is
-   in units of blocknr entries, for directory items the position is in
-   units of directory entries.  */
-
+/*
+ * Form the path to an item and position in this item which contains
+ * file byte defined by key. If there is no such item
+ * corresponding to the key, we point the path to the item with
+ * maximal key less than key, and *pos_in_item is set to one
+ * past the last entry/byte in the item.  If searching for entry in a
+ * directory item, and it is not found, *pos_in_item is set to one
+ * entry more than the entry with maximal key which is less than the
+ * sought key.
+ *
+ * Note that if there is no entry in this same node which is one more,
+ * then we point to an imaginary entry.  for direct items, the
+ * position is in units of bytes, for indirect items the position is
+ * in units of blocknr entries, for directory items the position is in
+ * units of directory entries.
+ */
 /* The function is NOT SCHEDULE-SAFE! */
-int search_for_position_by_key(struct super_block *sb,	/* Pointer to the super block.          */
-			       const struct cpu_key *p_cpu_key,	/* Key to search (cpu variable)         */
-			       struct treepath *search_path	/* Filled up by this function.          */
-    )
+int search_for_position_by_key(struct super_block *sb,
+			       /* Key to search (cpu variable) */
+			       const struct cpu_key *p_cpu_key,
+			       /* Filled up by this function. */
+			       struct treepath *search_path)
 {
 	struct item_head *p_le_ih;	/* pointer to on-disk structure */
 	int blk_size;
@@ -830,7 +853,7 @@ int search_for_position_by_key(struct super_block *sb,	/* Pointer to the super b
 	if (retval == ITEM_FOUND) {
 
 		RFALSE(!ih_item_len
-		       (B_N_PITEM_HEAD
+		       (item_head
 			(PATH_PLAST_BUFFER(search_path),
 			 PATH_LAST_POSITION(search_path))),
 		       "PAP-5165: item length equals zero");
@@ -844,14 +867,14 @@ int search_for_position_by_key(struct super_block *sb,	/* Pointer to the super b
 
 	/* Item is not found. Set path to the previous item. */
 	p_le_ih =
-	    B_N_PITEM_HEAD(PATH_PLAST_BUFFER(search_path),
+	    item_head(PATH_PLAST_BUFFER(search_path),
 			   --PATH_LAST_POSITION(search_path));
 	blk_size = sb->s_blocksize;
 
-	if (comp_short_keys(&(p_le_ih->ih_key), p_cpu_key)) {
+	if (comp_short_keys(&p_le_ih->ih_key, p_cpu_key))
 		return FILE_NOT_FOUND;
-	}
-	// FIXME: quite ugly this far
+
+	/* FIXME: quite ugly this far */
 
 	item_offset = le_ih_k_offset(p_le_ih);
 	offset = cpu_key_k_offset(p_cpu_key);
@@ -866,8 +889,10 @@ int search_for_position_by_key(struct super_block *sb,	/* Pointer to the super b
 		return POSITION_FOUND;
 	}
 
-	/* Needed byte is not contained in the item pointed to by the
-	   path. Set pos_in_item out of the item. */
+	/*
+	 * Needed byte is not contained in the item pointed to by the
+	 * path. Set pos_in_item out of the item.
+	 */
 	if (is_indirect_le_ih(p_le_ih))
 		pos_in_item(search_path) =
 		    ih_item_len(p_le_ih) / UNFM_P_SIZE;
@@ -892,19 +917,17 @@ int comp_items(const struct item_head *stored_ih, const struct treepath *path)
 		return 1;
 
 	/* we need only to know, whether it is the same item */
-	ih = get_ih(path);
+	ih = tp_item_head(path);
 	return memcmp(stored_ih, ih, IH_SIZE);
 }
 
-/* unformatted nodes are not logged anymore, ever.  This is safe
-** now
-*/
+/* unformatted nodes are not logged anymore, ever.  This is safe now */
 #define held_by_others(bh) (atomic_read(&(bh)->b_count) > 1)
 
-// block can not be forgotten as it is in I/O or held by someone
+/* block can not be forgotten as it is in I/O or held by someone */
 #define block_in_use(bh) (buffer_locked(bh) || (held_by_others(bh)))
 
-// prepare for delete or cut of direct item
+/* prepare for delete or cut of direct item */
 static inline int prepare_for_direct_item(struct treepath *path,
 					  struct item_head *le_ih,
 					  struct inode *inode,
@@ -917,9 +940,8 @@ static inline int prepare_for_direct_item(struct treepath *path,
 		*cut_size = -(IH_SIZE + ih_item_len(le_ih));
 		return M_DELETE;
 	}
-	// new file gets truncated
+	/* new file gets truncated */
 	if (get_inode_item_key_version(inode) == KEY_FORMAT_3_6) {
-		//
 		round_len = ROUND_UP(new_file_length);
 		/* this was new_file_length < le_ih ... */
 		if (round_len < le_ih_k_offset(le_ih)) {
@@ -933,12 +955,13 @@ static inline int prepare_for_direct_item(struct treepath *path,
 		return M_CUT;	/* Cut from this item. */
 	}
 
-	// old file: items may have any length
+	/* old file: items may have any length */
 
 	if (new_file_length < le_ih_k_offset(le_ih)) {
 		*cut_size = -(IH_SIZE + ih_item_len(le_ih));
 		return M_DELETE;	/* Delete this item. */
 	}
+
 	/* Calculate first position and size for cutting from item. */
 	*cut_size = -(ih_item_len(le_ih) -
 		      (pos_in_item(path) =
@@ -957,12 +980,15 @@ static inline int prepare_for_direntry_item(struct treepath *path,
 		RFALSE(ih_entry_count(le_ih) != 2,
 		       "PAP-5220: incorrect empty directory item (%h)", le_ih);
 		*cut_size = -(IH_SIZE + ih_item_len(le_ih));
-		return M_DELETE;	/* Delete the directory item containing "." and ".." entry. */
+		/* Delete the directory item containing "." and ".." entry. */
+		return M_DELETE;
 	}
 
 	if (ih_entry_count(le_ih) == 1) {
-		/* Delete the directory item such as there is one record only
-		   in this item */
+		/*
+		 * Delete the directory item such as there is one record only
+		 * in this item
+		 */
 		*cut_size = -(IH_SIZE + ih_item_len(le_ih));
 		return M_DELETE;
 	}
@@ -976,18 +1002,34 @@ static inline int prepare_for_direntry_item(struct treepath *path,
 
 #define JOURNAL_FOR_FREE_BLOCK_AND_UPDATE_SD (2 * JOURNAL_PER_BALANCE_CNT + 1)
 
-/*  If the path points to a directory or direct item, calculate mode and the size cut, for balance.
-    If the path points to an indirect item, remove some number of its unformatted nodes.
-    In case of file truncate calculate whether this item must be deleted/truncated or last
-    unformatted node of this item will be converted to a direct item.
-    This function returns a determination of what balance mode the calling function should employ. */
-static char prepare_for_delete_or_cut(struct reiserfs_transaction_handle *th, struct inode *inode, struct treepath *path, const struct cpu_key *item_key, int *removed,	/* Number of unformatted nodes which were removed
-																						   from end of the file. */
-				      int *cut_size, unsigned long long new_file_length	/* MAX_KEY_OFFSET in case of delete. */
+/*
+ * If the path points to a directory or direct item, calculate mode
+ * and the size cut, for balance.
+ * If the path points to an indirect item, remove some number of its
+ * unformatted nodes.
+ * In case of file truncate calculate whether this item must be
+ * deleted/truncated or last unformatted node of this item will be
+ * converted to a direct item.
+ * This function returns a determination of what balance mode the
+ * calling function should employ.
+ */
+static char prepare_for_delete_or_cut(struct reiserfs_transaction_handle *th,
+				      struct inode *inode,
+				      struct treepath *path,
+				      const struct cpu_key *item_key,
+				      /*
+				       * Number of unformatted nodes
+				       * which were removed from end
+				       * of the file.
+				       */
+				      int *removed,
+				      int *cut_size,
+				      /* MAX_KEY_OFFSET in case of delete. */
+				      unsigned long long new_file_length
     )
 {
 	struct super_block *sb = inode->i_sb;
-	struct item_head *p_le_ih = PATH_PITEM_HEAD(path);
+	struct item_head *p_le_ih = tp_item_head(path);
 	struct buffer_head *bh = PATH_PLAST_BUFFER(path);
 
 	BUG_ON(!th->t_trans_id);
@@ -1023,8 +1065,10 @@ static char prepare_for_delete_or_cut(struct reiserfs_transaction_handle *th, st
 	    int pos = 0;
 
 	    if ( new_file_length == max_reiserfs_offset (inode) ) {
-		/* prepare_for_delete_or_cut() is called by
-		 * reiserfs_delete_item() */
+		/*
+		 * prepare_for_delete_or_cut() is called by
+		 * reiserfs_delete_item()
+		 */
 		new_file_length = 0;
 		delete = 1;
 	    }
@@ -1033,27 +1077,30 @@ static char prepare_for_delete_or_cut(struct reiserfs_transaction_handle *th, st
 		need_re_search = 0;
 		*cut_size = 0;
 		bh = PATH_PLAST_BUFFER(path);
-		copy_item_head(&s_ih, PATH_PITEM_HEAD(path));
+		copy_item_head(&s_ih, tp_item_head(path));
 		pos = I_UNFM_NUM(&s_ih);
 
 		while (le_ih_k_offset (&s_ih) + (pos - 1) * blk_size > new_file_length) {
 		    __le32 *unfm;
 		    __u32 block;
 
-		    /* Each unformatted block deletion may involve one additional
-		     * bitmap block into the transaction, thereby the initial
-		     * journal space reservation might not be enough. */
+		    /*
+		     * Each unformatted block deletion may involve
+		     * one additional bitmap block into the transaction,
+		     * thereby the initial journal space reservation
+		     * might not be enough.
+		     */
 		    if (!delete && (*cut_size) != 0 &&
 			reiserfs_transaction_free_space(th) < JOURNAL_FOR_FREE_BLOCK_AND_UPDATE_SD)
 			break;
 
-		    unfm = (__le32 *)B_I_PITEM(bh, &s_ih) + pos - 1;
+		    unfm = (__le32 *)ih_item_body(bh, &s_ih) + pos - 1;
 		    block = get_block_num(unfm, 0);
 
 		    if (block != 0) {
 			reiserfs_prepare_for_journal(sb, bh, 1);
 			put_block_num(unfm, 0, 0);
-			journal_mark_dirty(th, sb, bh);
+			journal_mark_dirty(th, bh);
 			reiserfs_free_block(th, inode, block, 1);
 		    }
 
@@ -1074,17 +1121,21 @@ static char prepare_for_delete_or_cut(struct reiserfs_transaction_handle *th, st
 			break;
 		    }
 		}
-		/* a trick.  If the buffer has been logged, this will do nothing.  If
-		** we've broken the loop without logging it, it will restore the
-		** buffer */
+		/*
+		 * a trick.  If the buffer has been logged, this will
+		 * do nothing.  If we've broken the loop without logging
+		 * it, it will restore the buffer
+		 */
 		reiserfs_restore_prepared_buffer(sb, bh);
 	    } while (need_re_search &&
 		     search_for_position_by_key(sb, item_key, path) == POSITION_FOUND);
 	    pos_in_item(path) = pos * UNFM_P_SIZE;
 
 	    if (*cut_size == 0) {
-		/* Nothing were cut. maybe convert last unformatted node to the
-		 * direct item? */
+		/*
+		 * Nothing was cut. maybe convert last unformatted node to the
+		 * direct item?
+		 */
 		result = M_CONVERT;
 	    }
 	    return result;
@@ -1095,7 +1146,7 @@ static char prepare_for_delete_or_cut(struct reiserfs_transaction_handle *th, st
 static int calc_deleted_bytes_number(struct tree_balance *tb, char mode)
 {
 	int del_size;
-	struct item_head *p_le_ih = PATH_PITEM_HEAD(tb->tb_path);
+	struct item_head *p_le_ih = tp_item_head(tb->tb_path);
 
 	if (is_statdata_le_ih(p_le_ih))
 		return 0;
@@ -1104,9 +1155,11 @@ static int calc_deleted_bytes_number(struct tree_balance *tb, char mode)
 	    (mode ==
 	     M_DELETE) ? ih_item_len(p_le_ih) : -tb->insert_size[0];
 	if (is_direntry_le_ih(p_le_ih)) {
-		/* return EMPTY_DIR_SIZE; We delete emty directoris only.
-		 * we can't use EMPTY_DIR_SIZE, as old format dirs have a different
-		 * empty size.  ick. FIXME, is this right? */
+		/*
+		 * return EMPTY_DIR_SIZE; We delete emty directories only.
+		 * we can't use EMPTY_DIR_SIZE, as old format dirs have a
+		 * different empty size.  ick. FIXME, is this right?
+		 */
 		return del_size;
 	}
 
@@ -1169,7 +1222,8 @@ char head2type(struct item_head *ih)
 }
 #endif
 
-/* Delete object item.
+/*
+ * Delete object item.
  * th       - active transaction handle
  * path     - path to the deleted item
  * item_key - key to search for the deleted item
@@ -1212,7 +1266,7 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th,
 
 		RFALSE(mode != M_DELETE, "PAP-5320: mode must be M_DELETE");
 
-		copy_item_head(&s_ih, PATH_PITEM_HEAD(path));
+		copy_item_head(&s_ih, tp_item_head(path));
 		s_del_balance.insert_size[0] = del_size;
 
 		ret_value = fix_nodes(M_DELETE, &s_del_balance, NULL, NULL);
@@ -1221,7 +1275,7 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th,
 
 		PROC_INFO_INC(sb, delete_item_restarted);
 
-		// file system changed, repeat search
+		/* file system changed, repeat search */
 		ret_value =
 		    search_for_position_by_key(sb, item_key, path);
 		if (ret_value == IO_ERROR)
@@ -1238,16 +1292,18 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th,
 		unfix_nodes(&s_del_balance);
 		return 0;
 	}
-	// reiserfs_delete_item returns item length when success
+
+	/* reiserfs_delete_item returns item length when success */
 	ret_value = calc_deleted_bytes_number(&s_del_balance, M_DELETE);
-	q_ih = get_ih(path);
+	q_ih = tp_item_head(path);
 	quota_cut_bytes = ih_item_len(q_ih);
 
-	/* hack so the quota code doesn't have to guess if the file
-	 ** has a tail.  On tail insert, we allocate quota for 1 unformatted node.
-	 ** We test the offset because the tail might have been
-	 ** split into multiple items, and we only want to decrement for
-	 ** the unfm node once
+	/*
+	 * hack so the quota code doesn't have to guess if the file has a
+	 * tail.  On tail insert, we allocate quota for 1 unformatted node.
+	 * We test the offset because the tail might have been
+	 * split into multiple items, and we only want to decrement for
+	 * the unfm node once
 	 */
 	if (!S_ISLNK(inode->i_mode) && is_direct_le_ih(q_ih)) {
 		if ((le_ih_k_offset(q_ih) & (sb->s_blocksize - 1)) == 1) {
@@ -1261,33 +1317,38 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th,
 		int off;
 		char *data;
 
-		/* We are in direct2indirect conversion, so move tail contents
-		   to the unformatted node */
-		/* note, we do the copy before preparing the buffer because we
-		 ** don't care about the contents of the unformatted node yet.
-		 ** the only thing we really care about is the direct item's data
-		 ** is in the unformatted node.
-		 **
-		 ** Otherwise, we would have to call reiserfs_prepare_for_journal on
-		 ** the unformatted node, which might schedule, meaning we'd have to
-		 ** loop all the way back up to the start of the while loop.
-		 **
-		 ** The unformatted node must be dirtied later on.  We can't be
-		 ** sure here if the entire tail has been deleted yet.
-		 **
-		 ** un_bh is from the page cache (all unformatted nodes are
-		 ** from the page cache) and might be a highmem page.  So, we
-		 ** can't use un_bh->b_data.
-		 ** -clm
+		/*
+		 * We are in direct2indirect conversion, so move tail contents
+		 * to the unformatted node
+		 */
+		/*
+		 * note, we do the copy before preparing the buffer because we
+		 * don't care about the contents of the unformatted node yet.
+		 * the only thing we really care about is the direct item's
+		 * data is in the unformatted node.
+		 *
+		 * Otherwise, we would have to call
+		 * reiserfs_prepare_for_journal on the unformatted node,
+		 * which might schedule, meaning we'd have to loop all the
+		 * way back up to the start of the while loop.
+		 *
+		 * The unformatted node must be dirtied later on.  We can't be
+		 * sure here if the entire tail has been deleted yet.
+		 *
+		 * un_bh is from the page cache (all unformatted nodes are
+		 * from the page cache) and might be a highmem page.  So, we
+		 * can't use un_bh->b_data.
+		 * -clm
 		 */
 
 		data = kmap_atomic(un_bh->b_page);
 		off = ((le_ih_k_offset(&s_ih) - 1) & (PAGE_CACHE_SIZE - 1));
 		memcpy(data + off,
-		       B_I_PITEM(PATH_PLAST_BUFFER(path), &s_ih),
+		       ih_item_body(PATH_PLAST_BUFFER(path), &s_ih),
 		       ret_value);
 		kunmap_atomic(data);
 	}
+
 	/* Perform balancing after all resources have been collected at once. */
 	do_balance(&s_del_balance, NULL, NULL, M_DELETE);
 
@@ -1304,20 +1365,21 @@ int reiserfs_delete_item(struct reiserfs_transaction_handle *th,
 	return ret_value;
 }
 
-/* Summary Of Mechanisms For Handling Collisions Between Processes:
-
- deletion of the body of the object is performed by iput(), with the
- result that if multiple processes are operating on a file, the
- deletion of the body of the file is deferred until the last process
- that has an open inode performs its iput().
-
- writes and truncates are protected from collisions by use of
- semaphores.
-
- creates, linking, and mknod are protected from collisions with other
- processes by making the reiserfs_add_entry() the last step in the
- creation, and then rolling back all changes if there was a collision.
- - Hans
+/*
+ * Summary Of Mechanisms For Handling Collisions Between Processes:
+ *
+ *  deletion of the body of the object is performed by iput(), with the
+ *  result that if multiple processes are operating on a file, the
+ *  deletion of the body of the file is deferred until the last process
+ *  that has an open inode performs its iput().
+ *
+ *  writes and truncates are protected from collisions by use of
+ *  semaphores.
+ *
+ *  creates, linking, and mknod are protected from collisions with other
+ *  processes by making the reiserfs_add_entry() the last step in the
+ *  creation, and then rolling back all changes if there was a collision.
+ *  - Hans
 */
 
 /* this deletes item which never gets split */
@@ -1347,7 +1409,11 @@ void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th,
 		}
 		if (retval != ITEM_FOUND) {
 			pathrelse(&path);
-			// No need for a warning, if there is just no free space to insert '..' item into the newly-created subdir
+			/*
+			 * No need for a warning, if there is just no free
+			 * space to insert '..' item into the
+			 * newly-created subdir
+			 */
 			if (!
 			    ((unsigned long long)
 			     GET_HASH_VALUE(le_key_k_offset
@@ -1362,11 +1428,11 @@ void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th,
 		}
 		if (!tb_init) {
 			tb_init = 1;
-			item_len = ih_item_len(PATH_PITEM_HEAD(&path));
+			item_len = ih_item_len(tp_item_head(&path));
 			init_tb_struct(th, &tb, th->t_super, &path,
 				       -(IH_SIZE + item_len));
 		}
-		quota_cut_bytes = ih_item_len(PATH_PITEM_HEAD(&path));
+		quota_cut_bytes = ih_item_len(tp_item_head(&path));
 
 		retval = fix_nodes(M_DELETE, &tb, NULL, NULL);
 		if (retval == REPEAT_SEARCH) {
@@ -1376,7 +1442,11 @@ void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th,
 
 		if (retval == CARRY_ON) {
 			do_balance(&tb, NULL, NULL, M_DELETE);
-			if (inode) {	/* Should we count quota for item? (we don't count quotas for save-links) */
+			/*
+			 * Should we count quota for item? (we don't
+			 * count quotas for save-links)
+			 */
+			if (inode) {
 				int depth;
 #ifdef REISERQUOTA_DEBUG
 				reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
@@ -1391,7 +1461,8 @@ void reiserfs_delete_solid_item(struct reiserfs_transaction_handle *th,
 			}
 			break;
 		}
-		// IO_ERROR, NO_DISK_SPACE, etc
+
+		/* IO_ERROR, NO_DISK_SPACE, etc */
 		reiserfs_warning(th->t_super, "vs-5360",
 				 "could not delete %K due to fix_nodes failure",
 				 &cpu_key);
@@ -1447,11 +1518,13 @@ static void unmap_buffers(struct page *page, loff_t pos)
 			do {
 				next = bh->b_this_page;
 
-				/* we want to unmap the buffers that contain the tail, and
-				 ** all the buffers after it (since the tail must be at the
-				 ** end of the file).  We don't want to unmap file data
-				 ** before the tail, since it might be dirty and waiting to
-				 ** reach disk
+				/*
+				 * we want to unmap the buffers that contain
+				 * the tail, and all the buffers after it
+				 * (since the tail must be at the end of the
+				 * file).  We don't want to unmap file data
+				 * before the tail, since it might be dirty
+				 * and waiting to reach disk
 				 */
 				cur_index += bh->b_size;
 				if (cur_index > tail_index) {
@@ -1476,9 +1549,10 @@ static int maybe_indirect_to_direct(struct reiserfs_transaction_handle *th,
 	BUG_ON(!th->t_trans_id);
 	BUG_ON(new_file_size != inode->i_size);
 
-	/* the page being sent in could be NULL if there was an i/o error
-	 ** reading in the last block.  The user will hit problems trying to
-	 ** read the file, but for now we just skip the indirect2direct
+	/*
+	 * the page being sent in could be NULL if there was an i/o error
+	 * reading in the last block.  The user will hit problems trying to
+	 * read the file, but for now we just skip the indirect2direct
 	 */
 	if (atomic_read(&inode->i_count) > 1 ||
 	    !tail_has_to_be_packed(inode) ||
@@ -1490,17 +1564,18 @@ static int maybe_indirect_to_direct(struct reiserfs_transaction_handle *th,
 		pathrelse(path);
 		return cut_bytes;
 	}
+
 	/* Perform the conversion to a direct_item. */
-	/* return indirect_to_direct(inode, path, item_key,
-				  new_file_size, mode); */
 	return indirect2direct(th, inode, page, path, item_key,
 			       new_file_size, mode);
 }
 
-/* we did indirect_to_direct conversion. And we have inserted direct
-   item successesfully, but there were no disk space to cut unfm
-   pointer being converted. Therefore we have to delete inserted
-   direct item(s) */
+/*
+ * we did indirect_to_direct conversion. And we have inserted direct
+ * item successesfully, but there were no disk space to cut unfm
+ * pointer being converted. Therefore we have to delete inserted
+ * direct item(s)
+ */
 static void indirect_to_direct_roll_back(struct reiserfs_transaction_handle *th,
 					 struct inode *inode, struct treepath *path)
 {
@@ -1509,7 +1584,7 @@ static void indirect_to_direct_roll_back(struct reiserfs_transaction_handle *th,
 	int removed;
 	BUG_ON(!th->t_trans_id);
 
-	make_cpu_key(&tail_key, inode, inode->i_size + 1, TYPE_DIRECT, 4);	// !!!!
+	make_cpu_key(&tail_key, inode, inode->i_size + 1, TYPE_DIRECT, 4);
 	tail_key.key_length = 4;
 
 	tail_len =
@@ -1521,7 +1596,7 @@ static void indirect_to_direct_roll_back(struct reiserfs_transaction_handle *th,
 			reiserfs_panic(inode->i_sb, "vs-5615",
 				       "found invalid item");
 		RFALSE(path->pos_in_item !=
-		       ih_item_len(PATH_PITEM_HEAD(path)) - 1,
+		       ih_item_len(tp_item_head(path)) - 1,
 		       "vs-5616: appended bytes found");
 		PATH_LAST_POSITION(path)--;
 
@@ -1539,7 +1614,6 @@ static void indirect_to_direct_roll_back(struct reiserfs_transaction_handle *th,
 	reiserfs_warning(inode->i_sb, "reiserfs-5091", "indirect_to_direct "
 			 "conversion has been rolled back due to "
 			 "lack of disk space");
-	//mark_file_without_tail (inode);
 	mark_inode_dirty(inode);
 }
 
@@ -1551,15 +1625,18 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th,
 			   struct page *page, loff_t new_file_size)
 {
 	struct super_block *sb = inode->i_sb;
-	/* Every function which is going to call do_balance must first
-	   create a tree_balance structure.  Then it must fill up this
-	   structure by using the init_tb_struct and fix_nodes functions.
-	   After that we can make tree balancing. */
+	/*
+	 * Every function which is going to call do_balance must first
+	 * create a tree_balance structure.  Then it must fill up this
+	 * structure by using the init_tb_struct and fix_nodes functions.
+	 * After that we can make tree balancing.
+	 */
 	struct tree_balance s_cut_balance;
 	struct item_head *p_le_ih;
-	int cut_size = 0,	/* Amount to be cut. */
-	    ret_value = CARRY_ON, removed = 0,	/* Number of the removed unformatted nodes. */
-	    is_inode_locked = 0;
+	int cut_size = 0;	/* Amount to be cut. */
+	int ret_value = CARRY_ON;
+	int removed = 0;	/* Number of the removed unformatted nodes. */
+	int is_inode_locked = 0;
 	char mode;		/* Mode of the balance. */
 	int retval2 = -1;
 	int quota_cut_bytes;
@@ -1571,21 +1648,27 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th,
 	init_tb_struct(th, &s_cut_balance, inode->i_sb, path,
 		       cut_size);
 
-	/* Repeat this loop until we either cut the item without needing
-	   to balance, or we fix_nodes without schedule occurring */
+	/*
+	 * Repeat this loop until we either cut the item without needing
+	 * to balance, or we fix_nodes without schedule occurring
+	 */
 	while (1) {
-		/* Determine the balance mode, position of the first byte to
-		   be cut, and size to be cut.  In case of the indirect item
-		   free unformatted nodes which are pointed to by the cut
-		   pointers. */
+		/*
+		 * Determine the balance mode, position of the first byte to
+		 * be cut, and size to be cut.  In case of the indirect item
+		 * free unformatted nodes which are pointed to by the cut
+		 * pointers.
+		 */
 
 		mode =
 		    prepare_for_delete_or_cut(th, inode, path,
 					      item_key, &removed,
 					      &cut_size, new_file_size);
 		if (mode == M_CONVERT) {
-			/* convert last unformatted node to direct item or leave
-			   tail in the unformatted node */
+			/*
+			 * convert last unformatted node to direct item or
+			 * leave tail in the unformatted node
+			 */
 			RFALSE(ret_value != CARRY_ON,
 			       "PAP-5570: can not convert twice");
 
@@ -1599,15 +1682,20 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th,
 
 			is_inode_locked = 1;
 
-			/* removing of last unformatted node will change value we
-			   have to return to truncate. Save it */
+			/*
+			 * removing of last unformatted node will
+			 * change value we have to return to truncate.
+			 * Save it
+			 */
 			retval2 = ret_value;
-			/*retval2 = sb->s_blocksize - (new_file_size & (sb->s_blocksize - 1)); */
 
-			/* So, we have performed the first part of the conversion:
-			   inserting the new direct item.  Now we are removing the
-			   last unformatted node pointer. Set key to search for
-			   it. */
+			/*
+			 * So, we have performed the first part of the
+			 * conversion:
+			 * inserting the new direct item.  Now we are
+			 * removing the last unformatted node pointer.
+			 * Set key to search for it.
+			 */
 			set_cpu_key_k_type(item_key, TYPE_INDIRECT);
 			item_key->key_length = 4;
 			new_file_size -=
@@ -1650,11 +1738,13 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th,
 		return (ret_value == IO_ERROR) ? -EIO : -ENOENT;
 	}			/* while */
 
-	// check fix_nodes results (IO_ERROR or NO_DISK_SPACE)
+	/* check fix_nodes results (IO_ERROR or NO_DISK_SPACE) */
 	if (ret_value != CARRY_ON) {
 		if (is_inode_locked) {
-			// FIXME: this seems to be not needed: we are always able
-			// to cut item
+			/*
+			 * FIXME: this seems to be not needed: we are always
+			 * able to cut item
+			 */
 			indirect_to_direct_roll_back(th, inode, path);
 		}
 		if (ret_value == NO_DISK_SPACE)
@@ -1671,22 +1761,23 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th,
 	/* Calculate number of bytes that need to be cut from the item. */
 	quota_cut_bytes =
 	    (mode ==
-	     M_DELETE) ? ih_item_len(get_ih(path)) : -s_cut_balance.
+	     M_DELETE) ? ih_item_len(tp_item_head(path)) : -s_cut_balance.
 	    insert_size[0];
 	if (retval2 == -1)
 		ret_value = calc_deleted_bytes_number(&s_cut_balance, mode);
 	else
 		ret_value = retval2;
 
-	/* For direct items, we only change the quota when deleting the last
-	 ** item.
+	/*
+	 * For direct items, we only change the quota when deleting the last
+	 * item.
 	 */
-	p_le_ih = PATH_PITEM_HEAD(s_cut_balance.tb_path);
+	p_le_ih = tp_item_head(s_cut_balance.tb_path);
 	if (!S_ISLNK(inode->i_mode) && is_direct_le_ih(p_le_ih)) {
 		if (mode == M_DELETE &&
 		    (le_ih_k_offset(p_le_ih) & (sb->s_blocksize - 1)) ==
 		    1) {
-			// FIXME: this is to keep 3.5 happy
+			/* FIXME: this is to keep 3.5 happy */
 			REISERFS_I(inode)->i_first_direct_byte = U32_MAX;
 			quota_cut_bytes = sb->s_blocksize + UNFM_P_SIZE;
 		} else {
@@ -1696,10 +1787,12 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th,
 #ifdef CONFIG_REISERFS_CHECK
 	if (is_inode_locked) {
 		struct item_head *le_ih =
-		    PATH_PITEM_HEAD(s_cut_balance.tb_path);
-		/* we are going to complete indirect2direct conversion. Make
-		   sure, that we exactly remove last unformatted node pointer
-		   of the item */
+		    tp_item_head(s_cut_balance.tb_path);
+		/*
+		 * we are going to complete indirect2direct conversion. Make
+		 * sure, that we exactly remove last unformatted node pointer
+		 * of the item
+		 */
 		if (!is_indirect_le_ih(le_ih))
 			reiserfs_panic(sb, "vs-5652",
 				       "item must be indirect %h", le_ih);
@@ -1717,17 +1810,20 @@ int reiserfs_cut_from_item(struct reiserfs_transaction_handle *th,
 				       "(CUT, insert_size==%d)",
 				       le_ih, s_cut_balance.insert_size[0]);
 		}
-		/* it would be useful to make sure, that right neighboring
-		   item is direct item of this file */
+		/*
+		 * it would be useful to make sure, that right neighboring
+		 * item is direct item of this file
+		 */
 	}
 #endif
 
 	do_balance(&s_cut_balance, NULL, NULL, mode);
 	if (is_inode_locked) {
-		/* we've done an indirect->direct conversion.  when the data block
-		 ** was freed, it was removed from the list of blocks that must
-		 ** be flushed before the transaction commits, make sure to
-		 ** unmap and invalidate it
+		/*
+		 * we've done an indirect->direct conversion.  when the
+		 * data block was freed, it was removed from the list of
+		 * blocks that must be flushed before the transaction
+		 * commits, make sure to unmap and invalidate it
 		 */
 		unmap_buffers(page, tail_pos);
 		REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
@@ -1758,20 +1854,25 @@ static void truncate_directory(struct reiserfs_transaction_handle *th,
 	set_le_key_k_type(KEY_FORMAT_3_5, INODE_PKEY(inode), TYPE_STAT_DATA);
 }
 
-/* Truncate file to the new size. Note, this must be called with a transaction
-   already started */
+/*
+ * Truncate file to the new size. Note, this must be called with a
+ * transaction already started
+ */
 int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
-			  struct inode *inode,	/* ->i_size contains new size */
+			 struct inode *inode,	/* ->i_size contains new size */
 			 struct page *page,	/* up to date for last block */
-			 int update_timestamps	/* when it is called by
-						   file_release to convert
-						   the tail - no timestamps
-						   should be updated */
+			 /*
+			  * when it is called by file_release to convert
+			  * the tail - no timestamps should be updated
+			  */
+			 int update_timestamps
     )
 {
 	INITIALIZE_PATH(s_search_path);	/* Path to the current object item. */
 	struct item_head *p_le_ih;	/* Pointer to an item header. */
-	struct cpu_key s_item_key;	/* Key to search for a previous file item. */
+
+	/* Key to search for a previous file item. */
+	struct cpu_key s_item_key;
 	loff_t file_size,	/* Old file size. */
 	 new_file_size;	/* New file size. */
 	int deleted;		/* Number of deleted or truncated bytes. */
@@ -1784,8 +1885,8 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
 	     || S_ISLNK(inode->i_mode)))
 		return 0;
 
+	/* deletion of directory - no need to update timestamps */
 	if (S_ISDIR(inode->i_mode)) {
-		// deletion of directory - no need to update timestamps
 		truncate_directory(th, inode);
 		return 0;
 	}
@@ -1793,7 +1894,7 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
 	/* Get new file size. */
 	new_file_size = inode->i_size;
 
-	// FIXME: note, that key type is unimportant here
+	/* FIXME: note, that key type is unimportant here */
 	make_cpu_key(&s_item_key, inode, max_reiserfs_offset(inode),
 		     TYPE_DIRECT, 3);
 
@@ -1819,7 +1920,7 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
 	s_search_path.pos_in_item--;
 
 	/* Get real file size (total length of all file items) */
-	p_le_ih = PATH_PITEM_HEAD(&s_search_path);
+	p_le_ih = tp_item_head(&s_search_path);
 	if (is_statdata_le_ih(p_le_ih))
 		file_size = 0;
 	else {
@@ -1827,9 +1928,11 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
 		int bytes =
 		    op_bytes_number(p_le_ih, inode->i_sb->s_blocksize);
 
-		/* this may mismatch with real file size: if last direct item
-		   had no padding zeros and last unformatted node had no free
-		   space, this file would have this file size */
+		/*
+		 * this may mismatch with real file size: if last direct item
+		 * had no padding zeros and last unformatted node had no free
+		 * space, this file would have this file size
+		 */
 		file_size = offset + bytes - 1;
 	}
 	/*
@@ -1867,18 +1970,20 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
 
 		set_cpu_key_k_offset(&s_item_key, file_size);
 
-		/* While there are bytes to truncate and previous file item is presented in the tree. */
+		/*
+		 * While there are bytes to truncate and previous
+		 * file item is presented in the tree.
+		 */
 
 		/*
-		 ** This loop could take a really long time, and could log
-		 ** many more blocks than a transaction can hold.  So, we do a polite
-		 ** journal end here, and if the transaction needs ending, we make
-		 ** sure the file is consistent before ending the current trans
-		 ** and starting a new one
+		 * This loop could take a really long time, and could log
+		 * many more blocks than a transaction can hold.  So, we do
+		 * a polite journal end here, and if the transaction needs
+		 * ending, we make sure the file is consistent before ending
+		 * the current trans and starting a new one
 		 */
 		if (journal_transaction_should_end(th, 0) ||
 		    reiserfs_transaction_free_space(th) <= JOURNAL_FOR_FREE_BLOCK_AND_UPDATE_SD) {
-			int orig_len_alloc = th->t_blocks_allocated;
 			pathrelse(&s_search_path);
 
 			if (update_timestamps) {
@@ -1887,7 +1992,7 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
 			}
 			reiserfs_update_sd(th, inode);
 
-			err = journal_end(th, inode->i_sb, orig_len_alloc);
+			err = journal_end(th);
 			if (err)
 				goto out;
 			err = journal_begin(th, inode->i_sb,
@@ -1904,25 +2009,25 @@ int reiserfs_do_truncate(struct reiserfs_transaction_handle *th,
 	       "PAP-5680: truncate did not finish: new_file_size %Ld, current %Ld, oid %d",
 	       new_file_size, file_size, s_item_key.on_disk_key.k_objectid);
 
-      update_and_out:
+update_and_out:
 	if (update_timestamps) {
-		// this is truncate, not file closing
+		/* this is truncate, not file closing */
 		inode->i_mtime = CURRENT_TIME_SEC;
 		inode->i_ctime = CURRENT_TIME_SEC;
 	}
 	reiserfs_update_sd(th, inode);
 
-      out:
+out:
 	pathrelse(&s_search_path);
 	return err;
 }
 
 #ifdef CONFIG_REISERFS_CHECK
-// this makes sure, that we __append__, not overwrite or add holes
+/* this makes sure, that we __append__, not overwrite or add holes */
 static void check_research_for_paste(struct treepath *path,
 				     const struct cpu_key *key)
 {
-	struct item_head *found_ih = get_ih(path);
+	struct item_head *found_ih = tp_item_head(path);
 
 	if (is_direct_le_ih(found_ih)) {
 		if (le_ih_k_offset(found_ih) +
@@ -1952,13 +2057,22 @@ static void check_research_for_paste(struct treepath *path,
 }
 #endif				/* config reiserfs check */
 
-/* Paste bytes to the existing item. Returns bytes number pasted into the item. */
-int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct treepath *search_path,	/* Path to the pasted item.	  */
-			     const struct cpu_key *key,	/* Key to search for the needed item. */
-			     struct inode *inode,	/* Inode item belongs to */
-			     const char *body,	/* Pointer to the bytes to paste.    */
+/*
+ * Paste bytes to the existing item.
+ * Returns bytes number pasted into the item.
+ */
+int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th,
+			     /* Path to the pasted item. */
+			     struct treepath *search_path,
+			     /* Key to search for the needed item. */
+			     const struct cpu_key *key,
+			     /* Inode item belongs to */
+			     struct inode *inode,
+			     /* Pointer to the bytes to paste. */
+			     const char *body,
+			     /* Size of pasted bytes. */
 			     int pasted_size)
-{				/* Size of pasted bytes.             */
+{
 	struct super_block *sb = inode->i_sb;
 	struct tree_balance s_paste_balance;
 	int retval;
@@ -1973,7 +2087,7 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree
 	reiserfs_debug(inode->i_sb, REISERFS_DEBUG_CODE,
 		       "reiserquota paste_into_item(): allocating %u id=%u type=%c",
 		       pasted_size, inode->i_uid,
-		       key2type(&(key->on_disk_key)));
+		       key2type(&key->on_disk_key));
 #endif
 
 	depth = reiserfs_write_unlock_nested(sb);
@@ -1997,7 +2111,7 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree
 	while ((retval =
 		fix_nodes(M_PASTE, &s_paste_balance, NULL,
 			  body)) == REPEAT_SEARCH) {
-	      search_again:
+search_again:
 		/* file system changed while we were in the fix_nodes */
 		PROC_INFO_INC(th->t_super, paste_into_item_restarted);
 		retval =
@@ -2019,21 +2133,23 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree
 #endif
 	}
 
-	/* Perform balancing after all resources are collected by fix_nodes, and
-	   accessing them will not risk triggering schedule. */
+	/*
+	 * Perform balancing after all resources are collected by fix_nodes,
+	 * and accessing them will not risk triggering schedule.
+	 */
 	if (retval == CARRY_ON) {
 		do_balance(&s_paste_balance, NULL /*ih */ , body, M_PASTE);
 		return 0;
 	}
 	retval = (retval == NO_DISK_SPACE) ? -ENOSPC : -EIO;
-      error_out:
+error_out:
 	/* this also releases the path */
 	unfix_nodes(&s_paste_balance);
 #ifdef REISERQUOTA_DEBUG
 	reiserfs_debug(inode->i_sb, REISERFS_DEBUG_CODE,
 		       "reiserquota paste_into_item(): freeing %u id=%u type=%c",
 		       pasted_size, inode->i_uid,
-		       key2type(&(key->on_disk_key)));
+		       key2type(&key->on_disk_key));
 #endif
 	depth = reiserfs_write_unlock_nested(sb);
 	dquot_free_space_nodirty(inode, pasted_size);
@@ -2041,7 +2157,8 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree
 	return retval;
 }
 
-/* Insert new item into the buffer at the path.
+/*
+ * Insert new item into the buffer at the path.
  * th   - active transaction handle
  * path - path to the inserted item
  * ih   - pointer to the item header to insert
@@ -2064,8 +2181,10 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th,
 		fs_gen = get_generation(inode->i_sb);
 		quota_bytes = ih_item_len(ih);
 
-		/* hack so the quota code doesn't have to guess if the file has
-		 ** a tail, links are always tails, so there's no guessing needed
+		/*
+		 * hack so the quota code doesn't have to guess
+		 * if the file has a tail, links are always tails,
+		 * so there's no guessing needed
 		 */
 		if (!S_ISLNK(inode->i_mode) && is_direct_le_ih(ih))
 			quota_bytes = inode->i_sb->s_blocksize + UNFM_P_SIZE;
@@ -2074,8 +2193,10 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th,
 			       "reiserquota insert_item(): allocating %u id=%u type=%c",
 			       quota_bytes, inode->i_uid, head2type(ih));
 #endif
-		/* We can't dirty inode here. It would be immediately written but
-		 * appropriate stat item isn't inserted yet... */
+		/*
+		 * We can't dirty inode here. It would be immediately
+		 * written but appropriate stat item isn't inserted yet...
+		 */
 		depth = reiserfs_write_unlock_nested(inode->i_sb);
 		retval = dquot_alloc_space_nodirty(inode, quota_bytes);
 		reiserfs_write_lock_nested(inode->i_sb, depth);
@@ -2089,7 +2210,10 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th,
 #ifdef DISPLACE_NEW_PACKING_LOCALITIES
 	s_ins_balance.key = key->on_disk_key;
 #endif
-	/* DQUOT_* can schedule, must check to be sure calling fix_nodes is safe */
+	/*
+	 * DQUOT_* can schedule, must check to be sure calling
+	 * fix_nodes is safe
+	 */
 	if (inode && fs_changed(fs_gen, inode->i_sb)) {
 		goto search_again;
 	}
@@ -2097,7 +2221,7 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th,
 	while ((retval =
 		fix_nodes(M_INSERT, &s_ins_balance, ih,
 			  body)) == REPEAT_SEARCH) {
-	      search_again:
+search_again:
 		/* file system changed while we were in the fix_nodes */
 		PROC_INFO_INC(th->t_super, insert_item_restarted);
 		retval = search_item(th->t_super, key, path);
@@ -2121,7 +2245,7 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th,
 	}
 
 	retval = (retval == NO_DISK_SPACE) ? -ENOSPC : -EIO;
-      error_out:
+error_out:
 	/* also releases the path */
 	unfix_nodes(&s_ins_balance);
 #ifdef REISERQUOTA_DEBUG
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 9fb20426005..a392cef6acc 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -74,7 +74,7 @@ static int reiserfs_sync_fs(struct super_block *s, int wait)
 	dquot_writeback_dquots(s, -1);
 	reiserfs_write_lock(s);
 	if (!journal_begin(&th, s, 1))
-		if (!journal_end_sync(&th, s, 1))
+		if (!journal_end_sync(&th))
 			reiserfs_flush_old_commits(s);
 	reiserfs_write_unlock(s);
 	return 0;
@@ -136,9 +136,9 @@ static int reiserfs_freeze(struct super_block *s)
 		} else {
 			reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s),
 						     1);
-			journal_mark_dirty(&th, s, SB_BUFFER_WITH_SB(s));
+			journal_mark_dirty(&th, SB_BUFFER_WITH_SB(s));
 			reiserfs_block_writes(&th);
-			journal_end_sync(&th, s, 1);
+			journal_end_sync(&th);
 		}
 	}
 	reiserfs_write_unlock(s);
@@ -153,13 +153,15 @@ static int reiserfs_unfreeze(struct super_block *s)
 
 extern const struct in_core_key MAX_IN_CORE_KEY;
 
-/* this is used to delete "save link" when there are no items of a
-   file it points to. It can either happen if unlink is completed but
-   "save unlink" removal, or if file has both unlink and truncate
-   pending and as unlink completes first (because key of "save link"
-   protecting unlink is bigger that a key lf "save link" which
-   protects truncate), so there left no items to make truncate
-   completion on */
+/*
+ * this is used to delete "save link" when there are no items of a
+ * file it points to. It can either happen if unlink is completed but
+ * "save unlink" removal, or if file has both unlink and truncate
+ * pending and as unlink completes first (because key of "save link"
+ * protecting unlink is bigger that a key lf "save link" which
+ * protects truncate), so there left no items to make truncate
+ * completion on
+ */
 static int remove_save_link_only(struct super_block *s,
 				 struct reiserfs_key *key, int oid_free)
 {
@@ -176,7 +178,7 @@ static int remove_save_link_only(struct super_block *s,
 		/* removals are protected by direct items */
 		reiserfs_release_objectid(&th, le32_to_cpu(key->k_objectid));
 
-	return journal_end(&th, s, JOURNAL_PER_BALANCE_CNT);
+	return journal_end(&th);
 }
 
 #ifdef CONFIG_QUOTA
@@ -258,7 +260,7 @@ static int finish_unfinished(struct super_block *s)
 			break;
 		}
 		item_pos--;
-		ih = B_N_PITEM_HEAD(bh, item_pos);
+		ih = item_head(bh, item_pos);
 
 		if (le32_to_cpu(ih->ih_key.k_dir_id) != MAX_KEY_OBJECTID)
 			/* there are no "save" links anymore */
@@ -271,7 +273,7 @@ static int finish_unfinished(struct super_block *s)
 			truncate = 0;
 
 		/* reiserfs_iget needs k_dirid and k_objectid only */
-		item = B_I_PITEM(bh, ih);
+		item = ih_item_body(bh, ih);
 		obj_key.on_disk_key.k_dir_id = le32_to_cpu(*(__le32 *) item);
 		obj_key.on_disk_key.k_objectid =
 		    le32_to_cpu(ih->ih_key.k_objectid);
@@ -282,8 +284,10 @@ static int finish_unfinished(struct super_block *s)
 
 		inode = reiserfs_iget(s, &obj_key);
 		if (!inode) {
-			/* the unlink almost completed, it just did not manage to remove
-			   "save" link and release objectid */
+			/*
+			 * the unlink almost completed, it just did not
+			 * manage to remove "save" link and release objectid
+			 */
 			reiserfs_warning(s, "vs-2180", "iget failed for %K",
 					 &obj_key);
 			retval = remove_save_link_only(s, &save_link_key, 1);
@@ -303,10 +307,13 @@ static int finish_unfinished(struct super_block *s)
 		reiserfs_write_lock_nested(inode->i_sb, depth);
 
 		if (truncate && S_ISDIR(inode->i_mode)) {
-			/* We got a truncate request for a dir which is impossible.
-			   The only imaginable way is to execute unfinished truncate request
-			   then boot into old kernel, remove the file and create dir with
-			   the same key. */
+			/*
+			 * We got a truncate request for a dir which
+			 * is impossible.  The only imaginable way is to
+			 * execute unfinished truncate request then boot
+			 * into old kernel, remove the file and create dir
+			 * with the same key.
+			 */
 			reiserfs_warning(s, "green-2101",
 					 "impossible truncate on a "
 					 "directory %k. Please report",
@@ -320,14 +327,16 @@ static int finish_unfinished(struct super_block *s)
 		if (truncate) {
 			REISERFS_I(inode)->i_flags |=
 			    i_link_saved_truncate_mask;
-			/* not completed truncate found. New size was committed together
-			   with "save" link */
+			/*
+			 * not completed truncate found. New size was
+			 * committed together with "save" link
+			 */
 			reiserfs_info(s, "Truncating %k to %Ld ..",
 				      INODE_PKEY(inode), inode->i_size);
-			reiserfs_truncate_file(inode,
-					       0
-					       /*don't update modification time */
-					       );
+
+			/* don't update modification time */
+			reiserfs_truncate_file(inode, 0);
+
 			retval = remove_save_link(inode, truncate);
 		} else {
 			REISERFS_I(inode)->i_flags |= i_link_saved_unlink_mask;
@@ -373,10 +382,12 @@ static int finish_unfinished(struct super_block *s)
 	return retval;
 }
 
-/* to protect file being unlinked from getting lost we "safe" link files
-   being unlinked. This link will be deleted in the same transaction with last
-   item of file. mounting the filesystem we scan all these links and remove
-   files which almost got lost */
+/*
+ * to protect file being unlinked from getting lost we "safe" link files
+ * being unlinked. This link will be deleted in the same transaction with last
+ * item of file. mounting the filesystem we scan all these links and remove
+ * files which almost got lost
+ */
 void add_save_link(struct reiserfs_transaction_handle *th,
 		   struct inode *inode, int truncate)
 {
@@ -495,7 +506,7 @@ int remove_save_link(struct inode *inode, int truncate)
 	} else
 		REISERFS_I(inode)->i_flags &= ~i_link_saved_truncate_mask;
 
-	return journal_end(&th, inode->i_sb, JOURNAL_PER_BALANCE_CNT);
+	return journal_end(&th);
 }
 
 static void reiserfs_kill_sb(struct super_block *s)
@@ -530,19 +541,23 @@ static void reiserfs_put_super(struct super_block *s)
 
 	reiserfs_write_lock(s);
 
-	/* change file system state to current state if it was mounted with read-write permissions */
+	/*
+	 * change file system state to current state if it was mounted
+	 * with read-write permissions
+	 */
 	if (!(s->s_flags & MS_RDONLY)) {
 		if (!journal_begin(&th, s, 10)) {
 			reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s),
 						     1);
 			set_sb_umount_state(SB_DISK_SUPER_BLOCK(s),
 					    REISERFS_SB(s)->s_mount_state);
-			journal_mark_dirty(&th, s, SB_BUFFER_WITH_SB(s));
+			journal_mark_dirty(&th, SB_BUFFER_WITH_SB(s));
 		}
 	}
 
-	/* note, journal_release checks for readonly mount, and can decide not
-	 ** to do a journal_end
+	/*
+	 * note, journal_release checks for readonly mount, and can
+	 * decide not to do a journal_end
 	 */
 	journal_release(&th, s);
 
@@ -559,6 +574,7 @@ static void reiserfs_put_super(struct super_block *s)
 
 	reiserfs_write_unlock(s);
 	mutex_destroy(&REISERFS_SB(s)->lock);
+	destroy_workqueue(REISERFS_SB(s)->commit_wq);
 	kfree(s->s_fs_info);
 	s->s_fs_info = NULL;
 }
@@ -634,15 +650,16 @@ static void reiserfs_dirty_inode(struct inode *inode, int flags)
 	}
 	reiserfs_write_lock(inode->i_sb);
 
-	/* this is really only used for atime updates, so they don't have
-	 ** to be included in O_SYNC or fsync
+	/*
+	 * this is really only used for atime updates, so they don't have
+	 * to be included in O_SYNC or fsync
 	 */
 	err = journal_begin(&th, inode->i_sb, 1);
 	if (err)
 		goto out;
 
 	reiserfs_update_sd(&th, inode);
-	journal_end(&th, inode->i_sb, 1);
+	journal_end(&th);
 
 out:
 	reiserfs_write_unlock(inode->i_sb);
@@ -788,31 +805,53 @@ static const struct export_operations reiserfs_export_ops = {
 	.get_parent = reiserfs_get_parent,
 };
 
-/* this struct is used in reiserfs_getopt () for containing the value for those
-   mount options that have values rather than being toggles. */
+/*
+ * this struct is used in reiserfs_getopt () for containing the value for
+ * those mount options that have values rather than being toggles.
+ */
 typedef struct {
 	char *value;
-	int setmask;		/* bitmask which is to set on mount_options bitmask when this
-				   value is found, 0 is no bits are to be changed. */
-	int clrmask;		/* bitmask which is to clear on mount_options bitmask when  this
-				   value is found, 0 is no bits are to be changed. This is
-				   applied BEFORE setmask */
+	/*
+	 * bitmask which is to set on mount_options bitmask
+	 * when this value is found, 0 is no bits are to be changed.
+	 */
+	int setmask;
+	/*
+	 * bitmask which is to clear on mount_options bitmask
+	 * when this value is found, 0 is no bits are to be changed.
+	 * This is applied BEFORE setmask
+	 */
+	int clrmask;
 } arg_desc_t;
 
 /* Set this bit in arg_required to allow empty arguments */
 #define REISERFS_OPT_ALLOWEMPTY 31
 
-/* this struct is used in reiserfs_getopt() for describing the set of reiserfs
-   mount options */
+/*
+ * this struct is used in reiserfs_getopt() for describing the
+ * set of reiserfs mount options
+ */
 typedef struct {
 	char *option_name;
-	int arg_required;	/* 0 if argument is not required, not 0 otherwise */
-	const arg_desc_t *values;	/* list of values accepted by an option */
-	int setmask;		/* bitmask which is to set on mount_options bitmask when this
-				   value is found, 0 is no bits are to be changed. */
-	int clrmask;		/* bitmask which is to clear on mount_options bitmask when  this
-				   value is found, 0 is no bits are to be changed. This is
-				   applied BEFORE setmask */
+
+	/* 0 if argument is not required, not 0 otherwise */
+	int arg_required;
+
+	/* list of values accepted by an option */
+	const arg_desc_t *values;
+
+	/*
+	 * bitmask which is to set on mount_options bitmask
+	 * when this value is found, 0 is no bits are to be changed.
+	 */
+	int setmask;
+
+	/*
+	 * bitmask which is to clear on mount_options bitmask
+	 * when this value is found, 0 is no bits are to be changed.
+	 * This is applied BEFORE setmask
+	 */
+	int clrmask;
 } opt_desc_t;
 
 /* possible values for -o data= */
@@ -833,8 +872,10 @@ static const arg_desc_t barrier_mode[] = {
 	{.value = NULL}
 };
 
-/* possible values for "-o block-allocator=" and bits which are to be set in
-   s_mount_opt of reiserfs specific part of in-core super block */
+/*
+ * possible values for "-o block-allocator=" and bits which are to be set in
+ * s_mount_opt of reiserfs specific part of in-core super block
+ */
 static const arg_desc_t balloc[] = {
 	{"noborder", 1 << REISERFS_NO_BORDER, 0},
 	{"border", 0, 1 << REISERFS_NO_BORDER},
@@ -864,21 +905,25 @@ static const arg_desc_t error_actions[] = {
 	{NULL, 0, 0},
 };
 
-/* proceed only one option from a list *cur - string containing of mount options
-   opts - array of options which are accepted
-   opt_arg - if option is found and requires an argument and if it is specifed
-   in the input - pointer to the argument is stored here
-   bit_flags - if option requires to set a certain bit - it is set here
-   return -1 if unknown option is found, opt->arg_required otherwise */
+/*
+ * proceed only one option from a list *cur - string containing of mount
+ * options
+ * opts - array of options which are accepted
+ * opt_arg - if option is found and requires an argument and if it is specifed
+ * in the input - pointer to the argument is stored here
+ * bit_flags - if option requires to set a certain bit - it is set here
+ * return -1 if unknown option is found, opt->arg_required otherwise
+ */
 static int reiserfs_getopt(struct super_block *s, char **cur, opt_desc_t * opts,
 			   char **opt_arg, unsigned long *bit_flags)
 {
 	char *p;
-	/* foo=bar,
-	   ^   ^  ^
-	   |   |  +-- option_end
-	   |   +-- arg_start
-	   +-- option_start
+	/*
+	 * foo=bar,
+	 * ^   ^  ^
+	 * |   |  +-- option_end
+	 * |   +-- arg_start
+	 * +-- option_start
 	 */
 	const opt_desc_t *opt;
 	const arg_desc_t *arg;
@@ -893,9 +938,12 @@ static int reiserfs_getopt(struct super_block *s, char **cur, opt_desc_t * opts,
 	}
 
 	if (!strncmp(p, "alloc=", 6)) {
-		/* Ugly special case, probably we should redo options parser so that
-		   it can understand several arguments for some options, also so that
-		   it can fill several bitfields with option values. */
+		/*
+		 * Ugly special case, probably we should redo options
+		 * parser so that it can understand several arguments for
+		 * some options, also so that it can fill several bitfields
+		 * with option values.
+		 */
 		if (reiserfs_parse_alloc_options(s, p + 6)) {
 			return -1;
 		} else {
@@ -958,7 +1006,10 @@ static int reiserfs_getopt(struct super_block *s, char **cur, opt_desc_t * opts,
 		return -1;
 	}
 
-	/* move to the argument, or to next option if argument is not required */
+	/*
+	 * move to the argument, or to next option if argument is not
+	 * required
+	 */
 	p++;
 
 	if (opt->arg_required
@@ -995,12 +1046,20 @@ static int reiserfs_getopt(struct super_block *s, char **cur, opt_desc_t * opts,
 }
 
 /* returns 0 if something is wrong in option string, 1 - otherwise */
-static int reiserfs_parse_options(struct super_block *s, char *options,	/* string given via mount's -o */
+static int reiserfs_parse_options(struct super_block *s,
+
+				  /* string given via mount's -o */
+				  char *options,
+
+				  /*
+				   * after the parsing phase, contains the
+				   * collection of bitflags defining what
+				   * mount options were selected.
+				   */
 				  unsigned long *mount_options,
-				  /* after the parsing phase, contains the
-				     collection of bitflags defining what
-				     mount options were selected. */
-				  unsigned long *blocks,	/* strtol-ed from NNN of resize=NNN */
+
+				  /* strtol-ed from NNN of resize=NNN */
+				  unsigned long *blocks,
 				  char **jdev_name,
 				  unsigned int *commit_max_age,
 				  char **qf_names,
@@ -1010,7 +1069,10 @@ static int reiserfs_parse_options(struct super_block *s, char *options,	/* strin
 	char *arg = NULL;
 	char *pos;
 	opt_desc_t opts[] = {
-		/* Compatibility stuff, so that -o notail for old setups still work */
+		/*
+		 * Compatibility stuff, so that -o notail for old
+		 * setups still work
+		 */
 		{"tails",.arg_required = 't',.values = tails},
 		{"notail",.clrmask =
 		 (1 << REISERFS_LARGETAIL) | (1 << REISERFS_SMALLTAIL)},
@@ -1055,8 +1117,10 @@ static int reiserfs_parse_options(struct super_block *s, char *options,	/* strin
 
 	*blocks = 0;
 	if (!options || !*options)
-		/* use default configuration: create tails, journaling on, no
-		   conversion to newest format */
+		/*
+		 * use default configuration: create tails, journaling on, no
+		 * conversion to newest format
+		 */
 		return 1;
 
 	for (pos = options; pos;) {
@@ -1109,7 +1173,8 @@ static int reiserfs_parse_options(struct super_block *s, char *options,	/* strin
 
 		if (c == 'j') {
 			if (arg && *arg && jdev_name) {
-				if (*jdev_name) {	//Hm, already assigned?
+				/* Hm, already assigned? */
+				if (*jdev_name) {
 					reiserfs_warning(s, "super-6510",
 							 "journal device was "
 							 "already specified to "
@@ -1362,8 +1427,10 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	safe_mask |= 1 << REISERFS_USRQUOTA;
 	safe_mask |= 1 << REISERFS_GRPQUOTA;
 
-	/* Update the bitmask, taking care to keep
-	 * the bits we're not allowed to change here */
+	/*
+	 * Update the bitmask, taking care to keep
+	 * the bits we're not allowed to change here
+	 */
 	REISERFS_SB(s)->s_mount_opt =
 	    (REISERFS_SB(s)->
 	     s_mount_opt & ~safe_mask) | (mount_options & safe_mask);
@@ -1410,7 +1477,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 		/* Mounting a rw partition read-only. */
 		reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1);
 		set_sb_umount_state(rs, REISERFS_SB(s)->s_mount_state);
-		journal_mark_dirty(&th, s, SB_BUFFER_WITH_SB(s));
+		journal_mark_dirty(&th, SB_BUFFER_WITH_SB(s));
 	} else {
 		/* remount read-write */
 		if (!(s->s_flags & MS_RDONLY)) {
@@ -1427,7 +1494,9 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 		handle_data_mode(s, mount_options);
 		handle_barrier_mode(s, mount_options);
 		REISERFS_SB(s)->s_mount_state = sb_umount_state(rs);
-		s->s_flags &= ~MS_RDONLY;	/* now it is safe to call journal_begin */
+
+		/* now it is safe to call journal_begin */
+		s->s_flags &= ~MS_RDONLY;
 		err = journal_begin(&th, s, 10);
 		if (err)
 			goto out_err_unlock;
@@ -1440,12 +1509,12 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 		if (!old_format_only(s))
 			set_sb_mnt_count(rs, sb_mnt_count(rs) + 1);
 		/* mark_buffer_dirty (SB_BUFFER_WITH_SB (s), 1); */
-		journal_mark_dirty(&th, s, SB_BUFFER_WITH_SB(s));
+		journal_mark_dirty(&th, SB_BUFFER_WITH_SB(s));
 		REISERFS_SB(s)->s_mount_state = REISERFS_VALID_FS;
 	}
 	/* this will force a full flush of all journal lists */
 	SB_JOURNAL(s)->j_must_wait = 1;
-	err = journal_end(&th, s, 10);
+	err = journal_end(&th);
 	if (err)
 		goto out_err_unlock;
 
@@ -1489,9 +1558,9 @@ static int read_super_block(struct super_block *s, int offset)
 		brelse(bh);
 		return 1;
 	}
-	//
-	// ok, reiserfs signature (old or new) found in at the given offset
-	//
+	/*
+	 * ok, reiserfs signature (old or new) found in at the given offset
+	 */
 	fs_blocksize = sb_blocksize(rs);
 	brelse(bh);
 	sb_set_blocksize(s, fs_blocksize);
@@ -1529,9 +1598,11 @@ static int read_super_block(struct super_block *s, int offset)
 	SB_BUFFER_WITH_SB(s) = bh;
 	SB_DISK_SUPER_BLOCK(s) = rs;
 
+	/*
+	 * magic is of non-standard journal filesystem, look at s_version to
+	 * find which format is in use
+	 */
 	if (is_reiserfs_jr(rs)) {
-		/* magic is of non-standard journal filesystem, look at s_version to
-		   find which format is in use */
 		if (sb_version(rs) == REISERFS_VERSION_2)
 			reiserfs_info(s, "found reiserfs format \"3.6\""
 				      " with non-standard journal\n");
@@ -1545,8 +1616,10 @@ static int read_super_block(struct super_block *s, int offset)
 			return 1;
 		}
 	} else
-		/* s_version of standard format may contain incorrect information,
-		   so we just look at the magic string */
+		/*
+		 * s_version of standard format may contain incorrect
+		 * information, so we just look at the magic string
+		 */
 		reiserfs_info(s,
 			      "found reiserfs format \"%s\" with standard journal\n",
 			      is_reiserfs_3_5(rs) ? "3.5" : "3.6");
@@ -1558,8 +1631,9 @@ static int read_super_block(struct super_block *s, int offset)
 	s->dq_op = &reiserfs_quota_operations;
 #endif
 
-	/* new format is limited by the 32 bit wide i_blocks field, want to
-	 ** be one full block below that.
+	/*
+	 * new format is limited by the 32 bit wide i_blocks field, want to
+	 * be one full block below that.
 	 */
 	s->s_maxbytes = (512LL << 32) - s->s_blocksize;
 	return 0;
@@ -1568,7 +1642,7 @@ static int read_super_block(struct super_block *s, int offset)
 /* after journal replay, reread all bitmap and super blocks */
 static int reread_meta_blocks(struct super_block *s)
 {
-	ll_rw_block(READ, 1, &(SB_BUFFER_WITH_SB(s)));
+	ll_rw_block(READ, 1, &SB_BUFFER_WITH_SB(s));
 	wait_on_buffer(SB_BUFFER_WITH_SB(s));
 	if (!buffer_uptodate(SB_BUFFER_WITH_SB(s))) {
 		reiserfs_warning(s, "reiserfs-2504", "error reading the super");
@@ -1578,14 +1652,15 @@ static int reread_meta_blocks(struct super_block *s)
 	return 0;
 }
 
-/////////////////////////////////////////////////////
-// hash detection stuff
+/* hash detection stuff */
 
-// if root directory is empty - we set default - Yura's - hash and
-// warn about it
-// FIXME: we look for only one name in a directory. If tea and yura
-// bith have the same value - we ask user to send report to the
-// mailing list
+/*
+ * if root directory is empty - we set default - Yura's - hash and
+ * warn about it
+ * FIXME: we look for only one name in a directory. If tea and yura
+ * both have the same value - we ask user to send report to the
+ * mailing list
+ */
 static __u32 find_hash_out(struct super_block *s)
 {
 	int retval;
@@ -1593,92 +1668,83 @@ static __u32 find_hash_out(struct super_block *s)
 	struct cpu_key key;
 	INITIALIZE_PATH(path);
 	struct reiserfs_dir_entry de;
+	struct reiserfs_de_head *deh;
 	__u32 hash = DEFAULT_HASH;
+	__u32 deh_hashval, teahash, r5hash, yurahash;
 
 	inode = s->s_root->d_inode;
 
-	do {			// Some serious "goto"-hater was there ;)
-		u32 teahash, r5hash, yurahash;
+	make_cpu_key(&key, inode, ~0, TYPE_DIRENTRY, 3);
+	retval = search_by_entry_key(s, &key, &path, &de);
+	if (retval == IO_ERROR) {
+		pathrelse(&path);
+		return UNSET_HASH;
+	}
+	if (retval == NAME_NOT_FOUND)
+		de.de_entry_num--;
+
+	set_de_name_and_namelen(&de);
+	deh = de.de_deh + de.de_entry_num;
 
-		make_cpu_key(&key, inode, ~0, TYPE_DIRENTRY, 3);
-		retval = search_by_entry_key(s, &key, &path, &de);
-		if (retval == IO_ERROR) {
-			pathrelse(&path);
-			return UNSET_HASH;
-		}
-		if (retval == NAME_NOT_FOUND)
-			de.de_entry_num--;
-		set_de_name_and_namelen(&de);
-		if (deh_offset(&(de.de_deh[de.de_entry_num])) == DOT_DOT_OFFSET) {
-			/* allow override in this case */
-			if (reiserfs_rupasov_hash(s)) {
-				hash = YURA_HASH;
-			}
-			reiserfs_info(s, "FS seems to be empty, autodetect "
-					 "is using the default hash\n");
-			break;
-		}
-		r5hash = GET_HASH_VALUE(r5_hash(de.de_name, de.de_namelen));
-		teahash = GET_HASH_VALUE(keyed_hash(de.de_name, de.de_namelen));
-		yurahash = GET_HASH_VALUE(yura_hash(de.de_name, de.de_namelen));
-		if (((teahash == r5hash)
-		     &&
-		     (GET_HASH_VALUE(deh_offset(&(de.de_deh[de.de_entry_num])))
-		      == r5hash)) || ((teahash == yurahash)
-				      && (yurahash ==
-					  GET_HASH_VALUE(deh_offset
-							 (&
-							  (de.
-							   de_deh[de.
-								  de_entry_num])))))
-		    || ((r5hash == yurahash)
-			&& (yurahash ==
-			    GET_HASH_VALUE(deh_offset
-					   (&(de.de_deh[de.de_entry_num])))))) {
-			reiserfs_warning(s, "reiserfs-2506", "Unable to "
-					 "automatically detect hash function. "
-					 "Please mount with -o "
-					 "hash={tea,rupasov,r5}");
-			hash = UNSET_HASH;
-			break;
-		}
-		if (GET_HASH_VALUE(deh_offset(&(de.de_deh[de.de_entry_num]))) ==
-		    yurahash)
+	if (deh_offset(deh) == DOT_DOT_OFFSET) {
+		/* allow override in this case */
+		if (reiserfs_rupasov_hash(s))
 			hash = YURA_HASH;
-		else if (GET_HASH_VALUE
-			 (deh_offset(&(de.de_deh[de.de_entry_num]))) == teahash)
-			hash = TEA_HASH;
-		else if (GET_HASH_VALUE
-			 (deh_offset(&(de.de_deh[de.de_entry_num]))) == r5hash)
-			hash = R5_HASH;
-		else {
-			reiserfs_warning(s, "reiserfs-2506",
-					 "Unrecognised hash function");
-			hash = UNSET_HASH;
-		}
-	} while (0);
+		reiserfs_info(s, "FS seems to be empty, autodetect is using the default hash\n");
+		goto out;
+	}
+
+	deh_hashval = GET_HASH_VALUE(deh_offset(deh));
+	r5hash = GET_HASH_VALUE(r5_hash(de.de_name, de.de_namelen));
+	teahash = GET_HASH_VALUE(keyed_hash(de.de_name, de.de_namelen));
+	yurahash = GET_HASH_VALUE(yura_hash(de.de_name, de.de_namelen));
+
+	if ((teahash == r5hash && deh_hashval == r5hash) ||
+	    (teahash == yurahash && deh_hashval == yurahash) ||
+	    (r5hash == yurahash && deh_hashval == yurahash)) {
+		reiserfs_warning(s, "reiserfs-2506",
+				 "Unable to automatically detect hash "
+				 "function. Please mount with -o "
+				 "hash={tea,rupasov,r5}");
+		hash = UNSET_HASH;
+		goto out;
+	}
 
+	if (deh_hashval == yurahash)
+		hash = YURA_HASH;
+	else if (deh_hashval == teahash)
+		hash = TEA_HASH;
+	else if (deh_hashval == r5hash)
+		hash = R5_HASH;
+	else {
+		reiserfs_warning(s, "reiserfs-2506",
+				 "Unrecognised hash function");
+		hash = UNSET_HASH;
+	}
+out:
 	pathrelse(&path);
 	return hash;
 }
 
-// finds out which hash names are sorted with
+/* finds out which hash names are sorted with */
 static int what_hash(struct super_block *s)
 {
 	__u32 code;
 
 	code = sb_hash_function_code(SB_DISK_SUPER_BLOCK(s));
 
-	/* reiserfs_hash_detect() == true if any of the hash mount options
-	 ** were used.  We must check them to make sure the user isn't
-	 ** using a bad hash value
+	/*
+	 * reiserfs_hash_detect() == true if any of the hash mount options
+	 * were used.  We must check them to make sure the user isn't
+	 * using a bad hash value
 	 */
 	if (code == UNSET_HASH || reiserfs_hash_detect(s))
 		code = find_hash_out(s);
 
 	if (code != UNSET_HASH && reiserfs_hash_detect(s)) {
-		/* detection has found the hash, and we must check against the
-		 ** mount options
+		/*
+		 * detection has found the hash, and we must check against the
+		 * mount options
 		 */
 		if (reiserfs_rupasov_hash(s) && code != YURA_HASH) {
 			reiserfs_warning(s, "reiserfs-2507",
@@ -1700,7 +1766,10 @@ static int what_hash(struct super_block *s)
 			code = UNSET_HASH;
 		}
 	} else {
-		/* find_hash_out was not called or could not determine the hash */
+		/*
+		 * find_hash_out was not called or
+		 * could not determine the hash
+		 */
 		if (reiserfs_rupasov_hash(s)) {
 			code = YURA_HASH;
 		} else if (reiserfs_tea_hash(s)) {
@@ -1710,8 +1779,9 @@ static int what_hash(struct super_block *s)
 		}
 	}
 
-	/* if we are mounted RW, and we have a new valid hash code, update
-	 ** the super
+	/*
+	 * if we are mounted RW, and we have a new valid hash code, update
+	 * the super
 	 */
 	if (code != UNSET_HASH &&
 	    !(s->s_flags & MS_RDONLY) &&
@@ -1721,7 +1791,7 @@ static int what_hash(struct super_block *s)
 	return code;
 }
 
-// return pointer to appropriate function
+/* return pointer to appropriate function */
 static hashf_t hash_function(struct super_block *s)
 {
 	switch (what_hash(s)) {
@@ -1738,7 +1808,7 @@ static hashf_t hash_function(struct super_block *s)
 	return NULL;
 }
 
-// this is used to set up correct value for old partitions
+/* this is used to set up correct value for old partitions */
 static int function2code(hashf_t func)
 {
 	if (func == keyed_hash)
@@ -1748,7 +1818,7 @@ static int function2code(hashf_t func)
 	if (func == r5_hash)
 		return R5_HASH;
 
-	BUG();			// should never happen
+	BUG();			/* should never happen */
 
 	return 0;
 }
@@ -1783,8 +1853,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	sbi->s_mount_opt |= (1 << REISERFS_SMALLTAIL);
 	sbi->s_mount_opt |= (1 << REISERFS_ERROR_RO);
 	sbi->s_mount_opt |= (1 << REISERFS_BARRIER_FLUSH);
-	/* no preallocation minimum, be smart in
-	   reiserfs_file_write instead */
+	/* no preallocation minimum, be smart in reiserfs_file_write instead */
 	sbi->s_alloc_options.preallocmin = 0;
 	/* Preallocate by 16 blocks (17-1) at once */
 	sbi->s_alloc_options.preallocsize = 17;
@@ -1796,9 +1865,17 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	mutex_init(&sbi->lock);
 	sbi->lock_depth = -1;
 
+	sbi->commit_wq = alloc_workqueue("reiserfs/%s", WQ_MEM_RECLAIM, 0,
+					 s->s_id);
+	if (!sbi->commit_wq) {
+		SWARN(silent, s, "", "Cannot allocate commit workqueue");
+		errval = -ENOMEM;
+		goto error_unlocked;
+	}
+
 	jdev_name = NULL;
 	if (reiserfs_parse_options
-	    (s, (char *)data, &(sbi->s_mount_opt), &blocks, &jdev_name,
+	    (s, (char *)data, &sbi->s_mount_opt, &blocks, &jdev_name,
 	     &commit_max_age, qf_names, &qfmt) == 0) {
 		goto error_unlocked;
 	}
@@ -1819,10 +1896,17 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 		goto error_unlocked;
 	}
 
-	/* try old format (undistributed bitmap, super block in 8-th 1k block of a device) */
+	/*
+	 * try old format (undistributed bitmap, super block in 8-th 1k
+	 * block of a device)
+	 */
 	if (!read_super_block(s, REISERFS_OLD_DISK_OFFSET_IN_BYTES))
 		old_format = 1;
-	/* try new format (64-th 1k block), which can contain reiserfs super block */
+
+	/*
+	 * try new format (64-th 1k block), which can contain reiserfs
+	 * super block
+	 */
 	else if (read_super_block(s, REISERFS_DISK_OFFSET_IN_BYTES)) {
 		SWARN(silent, s, "sh-2021", "can not find reiserfs on %s",
 		      s->s_id);
@@ -1830,9 +1914,11 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	}
 
 	rs = SB_DISK_SUPER_BLOCK(s);
-	/* Let's do basic sanity check to verify that underlying device is not
-	   smaller than the filesystem. If the check fails then abort and scream,
-	   because bad stuff will happen otherwise. */
+	/*
+	 * Let's do basic sanity check to verify that underlying device is not
+	 * smaller than the filesystem. If the check fails then abort and
+	 * scream, because bad stuff will happen otherwise.
+	 */
 	if (s->s_bdev && s->s_bdev->bd_inode
 	    && i_size_read(s->s_bdev->bd_inode) <
 	    sb_block_count(rs) * sb_blocksize(rs)) {
@@ -1876,15 +1962,16 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 		printk("reiserfs: using flush barriers\n");
 	}
 
-	// set_device_ro(s->s_dev, 1) ;
 	if (journal_init(s, jdev_name, old_format, commit_max_age)) {
 		SWARN(silent, s, "sh-2022",
 		      "unable to initialize journal space");
 		goto error_unlocked;
 	} else {
-		jinit_done = 1;	/* once this is set, journal_release must be called
-				 ** if we error out of the mount
-				 */
+		/*
+		 * once this is set, journal_release must be called
+		 * if we error out of the mount
+		 */
+		jinit_done = 1;
 	}
 
 	if (reread_meta_blocks(s)) {
@@ -1905,7 +1992,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	args.dirid = REISERFS_ROOT_PARENT_OBJECTID;
 	root_inode =
 	    iget5_locked(s, REISERFS_ROOT_OBJECTID, reiserfs_find_actor,
-			 reiserfs_init_locked_inode, (void *)(&args));
+			 reiserfs_init_locked_inode, (void *)&args);
 	if (!root_inode) {
 		SWARN(silent, s, "jmacd-10", "get root inode failed");
 		goto error_unlocked;
@@ -1929,7 +2016,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	s->s_root = d_make_root(root_inode);
 	if (!s->s_root)
 		goto error;
-	// define and initialize hash function
+	/* define and initialize hash function */
 	sbi->s_hash_function = hash_function(s);
 	if (sbi->s_hash_function == NULL) {
 		dput(s->s_root);
@@ -1939,11 +2026,11 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 
 	if (is_reiserfs_3_5(rs)
 	    || (is_reiserfs_jr(rs) && SB_VERSION(s) == REISERFS_VERSION_1))
-		set_bit(REISERFS_3_5, &(sbi->s_properties));
+		set_bit(REISERFS_3_5, &sbi->s_properties);
 	else if (old_format)
-		set_bit(REISERFS_OLD_FORMAT, &(sbi->s_properties));
+		set_bit(REISERFS_OLD_FORMAT, &sbi->s_properties);
 	else
-		set_bit(REISERFS_3_6, &(sbi->s_properties));
+		set_bit(REISERFS_3_6, &sbi->s_properties);
 
 	if (!(s->s_flags & MS_RDONLY)) {
 
@@ -1958,10 +2045,12 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 		set_sb_umount_state(rs, REISERFS_ERROR_FS);
 		set_sb_fs_state(rs, 0);
 
-		/* Clear out s_bmap_nr if it would wrap. We can handle this
+		/*
+		 * Clear out s_bmap_nr if it would wrap. We can handle this
 		 * case, but older revisions can't. This will cause the
 		 * file system to fail mount on those older implementations,
-		 * avoiding corruption. -jeffm */
+		 * avoiding corruption. -jeffm
+		 */
 		if (bmap_would_wrap(reiserfs_bmap_count(s)) &&
 		    sb_bmap_nr(rs) != 0) {
 			reiserfs_warning(s, "super-2030", "This file system "
@@ -1974,8 +2063,10 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 		}
 
 		if (old_format_only(s)) {
-			/* filesystem of format 3.5 either with standard or non-standard
-			   journal */
+			/*
+			 * filesystem of format 3.5 either with standard
+			 * or non-standard journal
+			 */
 			if (convert_reiserfs(s)) {
 				/* and -o conv is given */
 				if (!silent)
@@ -1983,8 +2074,11 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 						      "converting 3.5 filesystem to the 3.6 format");
 
 				if (is_reiserfs_3_5(rs))
-					/* put magic string of 3.6 format. 2.2 will not be able to
-					   mount this filesystem anymore */
+					/*
+					 * put magic string of 3.6 format.
+					 * 2.2 will not be able to
+					 * mount this filesystem anymore
+					 */
 					memcpy(rs->s_v1.s_magic,
 					       reiserfs_3_6_magic_string,
 					       sizeof
@@ -1992,8 +2086,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 
 				set_sb_version(rs, REISERFS_VERSION_2);
 				reiserfs_convert_objectid_map_v1(s);
-				set_bit(REISERFS_3_6, &(sbi->s_properties));
-				clear_bit(REISERFS_3_5, &(sbi->s_properties));
+				set_bit(REISERFS_3_6, &sbi->s_properties);
+				clear_bit(REISERFS_3_5, &sbi->s_properties);
 			} else if (!silent) {
 				reiserfs_info(s, "using 3.5.x disk format\n");
 			}
@@ -2001,8 +2095,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 			set_sb_mnt_count(rs, sb_mnt_count(rs) + 1);
 
 
-		journal_mark_dirty(&th, s, SB_BUFFER_WITH_SB(s));
-		errval = journal_end(&th, s, 1);
+		journal_mark_dirty(&th, SB_BUFFER_WITH_SB(s));
+		errval = journal_end(&th);
 		if (errval) {
 			dput(s->s_root);
 			s->s_root = NULL;
@@ -2018,7 +2112,9 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 		}
 		reiserfs_write_lock(s);
 
-		/* look for files which were to be removed in previous session */
+		/*
+		 * look for files which were to be removed in previous session
+		 */
 		finish_unfinished(s);
 	} else {
 		if (old_format_only(s) && !silent) {
@@ -2034,7 +2130,9 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 		}
 		reiserfs_write_lock(s);
 	}
-	// mark hash in super block: it could be unset. overwrite should be ok
+	/*
+	 * mark hash in super block: it could be unset. overwrite should be ok
+	 */
 	set_sb_hash_function_code(rs, function2code(sbi->s_hash_function));
 
 	handle_attrs(s);
@@ -2111,9 +2209,7 @@ static int reiserfs_write_dquot(struct dquot *dquot)
 	depth = reiserfs_write_unlock_nested(dquot->dq_sb);
 	ret = dquot_commit(dquot);
 	reiserfs_write_lock_nested(dquot->dq_sb, depth);
-	err =
-	    journal_end(&th, dquot->dq_sb,
-			REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb));
+	err = journal_end(&th);
 	if (!ret && err)
 		ret = err;
 out:
@@ -2136,9 +2232,7 @@ static int reiserfs_acquire_dquot(struct dquot *dquot)
 	depth = reiserfs_write_unlock_nested(dquot->dq_sb);
 	ret = dquot_acquire(dquot);
 	reiserfs_write_lock_nested(dquot->dq_sb, depth);
-	err =
-	    journal_end(&th, dquot->dq_sb,
-			REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb));
+	err = journal_end(&th);
 	if (!ret && err)
 		ret = err;
 out:
@@ -2163,9 +2257,7 @@ static int reiserfs_release_dquot(struct dquot *dquot)
 	}
 	ret = dquot_release(dquot);
 	reiserfs_write_lock(dquot->dq_sb);
-	err =
-	    journal_end(&th, dquot->dq_sb,
-			REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb));
+	err = journal_end(&th);
 	if (!ret && err)
 		ret = err;
 	reiserfs_write_unlock(dquot->dq_sb);
@@ -2198,7 +2290,7 @@ static int reiserfs_write_info(struct super_block *sb, int type)
 	depth = reiserfs_write_unlock_nested(sb);
 	ret = dquot_commit_info(sb, type);
 	reiserfs_write_lock_nested(sb, depth);
-	err = journal_end(&th, sb, 2);
+	err = journal_end(&th);
 	if (!ret && err)
 		ret = err;
 out:
@@ -2238,7 +2330,10 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 		goto out;
 	}
 	inode = path->dentry->d_inode;
-	/* We must not pack tails for quota files on reiserfs for quota IO to work */
+	/*
+	 * We must not pack tails for quota files on reiserfs for quota
+	 * IO to work
+	 */
 	if (!(REISERFS_I(inode)->i_flags & i_nopack_mask)) {
 		err = reiserfs_unpack(inode, NULL);
 		if (err) {
@@ -2268,7 +2363,7 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 		err = journal_begin(&th, sb, 1);
 		if (err)
 			goto out;
-		err = journal_end_sync(&th, sb, 1);
+		err = journal_end_sync(&th);
 		if (err)
 			goto out;
 	}
@@ -2279,10 +2374,12 @@ out:
 	return err;
 }
 
-/* Read data from quotafile - avoid pagecache and such because we cannot afford
+/*
+ * Read data from quotafile - avoid pagecache and such because we cannot afford
  * acquiring the locks... As quota files are never truncated and quota code
  * itself serializes the operations (and no one else should touch the files)
- * we don't have to be afraid of races */
+ * we don't have to be afraid of races
+ */
 static ssize_t reiserfs_quota_read(struct super_block *sb, int type, char *data,
 				   size_t len, loff_t off)
 {
@@ -2303,7 +2400,10 @@ static ssize_t reiserfs_quota_read(struct super_block *sb, int type, char *data,
 		    sb->s_blocksize - offset <
 		    toread ? sb->s_blocksize - offset : toread;
 		tmp_bh.b_state = 0;
-		/* Quota files are without tails so we can safely use this function */
+		/*
+		 * Quota files are without tails so we can safely
+		 * use this function
+		 */
 		reiserfs_write_lock(sb);
 		err = reiserfs_get_block(inode, blk, &tmp_bh, 0);
 		reiserfs_write_unlock(sb);
@@ -2326,8 +2426,10 @@ static ssize_t reiserfs_quota_read(struct super_block *sb, int type, char *data,
 	return len;
 }
 
-/* Write to quotafile (we know the transaction is already started and has
- * enough credits) */
+/*
+ * Write to quotafile (we know the transaction is already started and has
+ * enough credits)
+ */
 static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
 				    const char *data, size_t len, loff_t off)
 {
@@ -2368,7 +2470,7 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type,
 		unlock_buffer(bh);
 		reiserfs_write_lock(sb);
 		reiserfs_prepare_for_journal(sb, bh, 1);
-		journal_mark_dirty(current->journal_info, sb, bh);
+		journal_mark_dirty(current->journal_info, bh);
 		if (!journal_quota)
 			reiserfs_add_ordered_list(inode, bh);
 		reiserfs_write_unlock(sb);
@@ -2402,18 +2504,18 @@ static int __init init_reiserfs_fs(void)
 {
 	int ret;
 
-	if ((ret = init_inodecache())) {
+	ret = init_inodecache();
+	if (ret)
 		return ret;
-	}
 
 	reiserfs_proc_info_global_init();
 
 	ret = register_filesystem(&reiserfs_fs_type);
+	if (ret)
+		goto out;
 
-	if (ret == 0) {
-		return 0;
-	}
-
+	return 0;
+out:
 	reiserfs_proc_info_global_done();
 	destroy_inodecache();
 
diff --git a/fs/reiserfs/tail_conversion.c b/fs/reiserfs/tail_conversion.c
index 5e2624d12f7..f41e19b4bb4 100644
--- a/fs/reiserfs/tail_conversion.c
+++ b/fs/reiserfs/tail_conversion.c
@@ -1,5 +1,6 @@
 /*
- * Copyright 1999 Hans Reiser, see reiserfs/README for licensing and copyright details
+ * Copyright 1999 Hans Reiser, see reiserfs/README for licensing and copyright
+ * details
  */
 
 #include <linux/time.h>
@@ -7,29 +8,41 @@
 #include <linux/buffer_head.h>
 #include "reiserfs.h"
 
-/* access to tail : when one is going to read tail it must make sure, that is not running.
- direct2indirect and indirect2direct can not run concurrently */
+/*
+ * access to tail : when one is going to read tail it must make sure, that is
+ * not running.  direct2indirect and indirect2direct can not run concurrently
+ */
 
-/* Converts direct items to an unformatted node. Panics if file has no
-   tail. -ENOSPC if no disk space for conversion */
-/* path points to first direct item of the file regarless of how many of
-   them are there */
+/*
+ * Converts direct items to an unformatted node. Panics if file has no
+ * tail. -ENOSPC if no disk space for conversion
+ */
+/*
+ * path points to first direct item of the file regardless of how many of
+ * them are there
+ */
 int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode,
 		    struct treepath *path, struct buffer_head *unbh,
 		    loff_t tail_offset)
 {
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *up_to_date_bh;
-	struct item_head *p_le_ih = PATH_PITEM_HEAD(path);
+	struct item_head *p_le_ih = tp_item_head(path);
 	unsigned long total_tail = 0;
-	struct cpu_key end_key;	/* Key to search for the last byte of the
-				   converted item. */
-	struct item_head ind_ih;	/* new indirect item to be inserted or
-					   key of unfm pointer to be pasted */
-	int blk_size, retval;	/* returned value for reiserfs_insert_item and clones */
-	unp_t unfm_ptr;		/* Handle on an unformatted node
-				   that will be inserted in the
-				   tree. */
+
+	/* Key to search for the last byte of the converted item. */
+	struct cpu_key end_key;
+
+	/*
+	 * new indirect item to be inserted or key
+	 * of unfm pointer to be pasted
+	 */
+	struct item_head ind_ih;
+	int blk_size;
+	/* returned value for reiserfs_insert_item and clones */
+	int  retval;
+	/* Handle on an unformatted node that will be inserted in the tree. */
+	unp_t unfm_ptr;
 
 	BUG_ON(!th->t_trans_id);
 
@@ -37,8 +50,10 @@ int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode,
 
 	blk_size = sb->s_blocksize;
 
-	/* and key to search for append or insert pointer to the new
-	   unformatted node. */
+	/*
+	 * and key to search for append or insert pointer to the new
+	 * unformatted node.
+	 */
 	copy_item_head(&ind_ih, p_le_ih);
 	set_le_ih_k_offset(&ind_ih, tail_offset);
 	set_le_ih_k_type(&ind_ih, TYPE_INDIRECT);
@@ -55,7 +70,7 @@ int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode,
 		return -EIO;
 	}
 
-	p_le_ih = PATH_PITEM_HEAD(path);
+	p_le_ih = tp_item_head(path);
 
 	unfm_ptr = cpu_to_le32(unbh->b_blocknr);
 
@@ -76,36 +91,43 @@ int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode,
 	if (retval) {
 		return retval;
 	}
-	// note: from here there are two keys which have matching first
-	// three key components. They only differ by the fourth one.
+	/*
+	 * note: from here there are two keys which have matching first
+	 *  three key components. They only differ by the fourth one.
+	 */
 
 	/* Set the key to search for the direct items of the file */
 	make_cpu_key(&end_key, inode, max_reiserfs_offset(inode), TYPE_DIRECT,
 		     4);
 
-	/* Move bytes from the direct items to the new unformatted node
-	   and delete them. */
+	/*
+	 * Move bytes from the direct items to the new unformatted node
+	 * and delete them.
+	 */
 	while (1) {
 		int tail_size;
 
-		/* end_key.k_offset is set so, that we will always have found
-		   last item of the file */
+		/*
+		 * end_key.k_offset is set so, that we will always have found
+		 * last item of the file
+		 */
 		if (search_for_position_by_key(sb, &end_key, path) ==
 		    POSITION_FOUND)
 			reiserfs_panic(sb, "PAP-14050",
 				       "direct item (%K) not found", &end_key);
-		p_le_ih = PATH_PITEM_HEAD(path);
+		p_le_ih = tp_item_head(path);
 		RFALSE(!is_direct_le_ih(p_le_ih),
 		       "vs-14055: direct item expected(%K), found %h",
 		       &end_key, p_le_ih);
 		tail_size = (le_ih_k_offset(p_le_ih) & (blk_size - 1))
 		    + ih_item_len(p_le_ih) - 1;
 
-		/* we only send the unbh pointer if the buffer is not up to date.
-		 ** this avoids overwriting good data from writepage() with old data
-		 ** from the disk or buffer cache
-		 ** Special case: unbh->b_page will be NULL if we are coming through
-		 ** DIRECT_IO handler here.
+		/*
+		 * we only send the unbh pointer if the buffer is not
+		 * up to date.  this avoids overwriting good data from
+		 * writepage() with old data from the disk or buffer cache
+		 * Special case: unbh->b_page will be NULL if we are coming
+		 * through DIRECT_IO handler here.
 		 */
 		if (!unbh->b_page || buffer_uptodate(unbh)
 		    || PageUptodate(unbh->b_page)) {
@@ -117,13 +139,15 @@ int direct2indirect(struct reiserfs_transaction_handle *th, struct inode *inode,
 						up_to_date_bh);
 
 		total_tail += retval;
+
+		/* done: file does not have direct items anymore */
 		if (tail_size == retval)
-			// done: file does not have direct items anymore
 			break;
 
 	}
-	/* if we've copied bytes from disk into the page, we need to zero
-	 ** out the unused part of the block (it was not up to date before)
+	/*
+	 * if we've copied bytes from disk into the page, we need to zero
+	 * out the unused part of the block (it was not up to date before)
 	 */
 	if (up_to_date_bh) {
 		unsigned pgoff =
@@ -146,9 +170,11 @@ void reiserfs_unmap_buffer(struct buffer_head *bh)
 		BUG();
 	}
 	clear_buffer_dirty(bh);
-	/* Remove the buffer from whatever list it belongs to. We are mostly
-	   interested in removing it from per-sb j_dirty_buffers list, to avoid
-	   BUG() on attempt to write not mapped buffer */
+	/*
+	 * Remove the buffer from whatever list it belongs to. We are mostly
+	 * interested in removing it from per-sb j_dirty_buffers list, to avoid
+	 * BUG() on attempt to write not mapped buffer
+	 */
 	if ((!list_empty(&bh->b_assoc_buffers) || bh->b_private) && bh->b_page) {
 		struct inode *inode = bh->b_page->mapping->host;
 		struct reiserfs_journal *j = SB_JOURNAL(inode->i_sb);
@@ -164,12 +190,14 @@ void reiserfs_unmap_buffer(struct buffer_head *bh)
 	unlock_buffer(bh);
 }
 
-/* this first locks inode (neither reads nor sync are permitted),
-   reads tail through page cache, insert direct item. When direct item
-   inserted successfully inode is left locked. Return value is always
-   what we expect from it (number of cut bytes). But when tail remains
-   in the unformatted node, we set mode to SKIP_BALANCING and unlock
-   inode */
+/*
+ * this first locks inode (neither reads nor sync are permitted),
+ * reads tail through page cache, insert direct item. When direct item
+ * inserted successfully inode is left locked. Return value is always
+ * what we expect from it (number of cut bytes). But when tail remains
+ * in the unformatted node, we set mode to SKIP_BALANCING and unlock
+ * inode
+ */
 int indirect2direct(struct reiserfs_transaction_handle *th,
 		    struct inode *inode, struct page *page,
 		    struct treepath *path,	/* path to the indirect item. */
@@ -194,7 +222,7 @@ int indirect2direct(struct reiserfs_transaction_handle *th,
 	*mode = M_SKIP_BALANCING;
 
 	/* store item head path points to. */
-	copy_item_head(&s_ih, PATH_PITEM_HEAD(path));
+	copy_item_head(&s_ih, tp_item_head(path));
 
 	tail_len = (n_new_file_size & (block_size - 1));
 	if (get_inode_sd_version(inode) == STAT_DATA_V2)
@@ -207,9 +235,11 @@ int indirect2direct(struct reiserfs_transaction_handle *th,
 					 1) * sb->s_blocksize;
 	pos1 = pos;
 
-	// we are protected by i_mutex. The tail can not disapper, not
-	// append can be done either
-	// we are in truncate or packing tail in file_release
+	/*
+	 * we are protected by i_mutex. The tail can not disapper, not
+	 * append can be done either
+	 * we are in truncate or packing tail in file_release
+	 */
 
 	tail = (char *)kmap(page);	/* this can schedule */
 
@@ -220,7 +250,7 @@ int indirect2direct(struct reiserfs_transaction_handle *th,
 			reiserfs_panic(sb, "PAP-5520",
 				       "item to be converted %K does not exist",
 				       item_key);
-		copy_item_head(&s_ih, PATH_PITEM_HEAD(path));
+		copy_item_head(&s_ih, tp_item_head(path));
 #ifdef CONFIG_REISERFS_CHECK
 		pos = le_ih_k_offset(&s_ih) - 1 +
 		    (ih_item_len(&s_ih) / UNFM_P_SIZE -
@@ -236,9 +266,10 @@ int indirect2direct(struct reiserfs_transaction_handle *th,
 			  pos1 + 1, TYPE_DIRECT, round_tail_len,
 			  0xffff /*ih_free_space */ );
 
-	/* we want a pointer to the first byte of the tail in the page.
-	 ** the page was locked and this part of the page was up to date when
-	 ** indirect2direct was called, so we know the bytes are still valid
+	/*
+	 * we want a pointer to the first byte of the tail in the page.
+	 * the page was locked and this part of the page was up to date when
+	 * indirect2direct was called, so we know the bytes are still valid
 	 */
 	tail = tail + (pos & (PAGE_CACHE_SIZE - 1));
 
@@ -250,12 +281,14 @@ int indirect2direct(struct reiserfs_transaction_handle *th,
 	/* Insert tail as new direct item in the tree */
 	if (reiserfs_insert_item(th, path, &key, &s_ih, inode,
 				 tail ? tail : NULL) < 0) {
-		/* No disk memory. So we can not convert last unformatted node
-		   to the direct item.  In this case we used to adjust
-		   indirect items's ih_free_space. Now ih_free_space is not
-		   used, it would be ideal to write zeros to corresponding
-		   unformatted node. For now i_size is considered as guard for
-		   going out of file size */
+		/*
+		 * No disk memory. So we can not convert last unformatted node
+		 * to the direct item.  In this case we used to adjust
+		 * indirect items's ih_free_space. Now ih_free_space is not
+		 * used, it would be ideal to write zeros to corresponding
+		 * unformatted node. For now i_size is considered as guard for
+		 * going out of file size
+		 */
 		kunmap(page);
 		return block_size - round_tail_len;
 	}
@@ -264,12 +297,16 @@ int indirect2direct(struct reiserfs_transaction_handle *th,
 	/* make sure to get the i_blocks changes from reiserfs_insert_item */
 	reiserfs_update_sd(th, inode);
 
-	// note: we have now the same as in above direct2indirect
-	// conversion: there are two keys which have matching first three
-	// key components. They only differ by the fouhth one.
+	/*
+	 * note: we have now the same as in above direct2indirect
+	 * conversion: there are two keys which have matching first three
+	 * key components. They only differ by the fourth one.
+	 */
 
-	/* We have inserted new direct item and must remove last
-	   unformatted node. */
+	/*
+	 * We have inserted new direct item and must remove last
+	 * unformatted node.
+	 */
 	*mode = M_CUT;
 
 	/* we store position of first direct item in the in-core inode */
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 5cdfbd638b5..ca416d099e7 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -56,9 +56,11 @@
 #define XAROOT_NAME   "xattrs"
 
 
-/* Helpers for inode ops. We do this so that we don't have all the VFS
+/*
+ * Helpers for inode ops. We do this so that we don't have all the VFS
  * overhead and also for proper i_mutex annotation.
- * dir->i_mutex must be held for all of them. */
+ * dir->i_mutex must be held for all of them.
+ */
 #ifdef CONFIG_REISERFS_FS_XATTR
 static int xattr_create(struct inode *dir, struct dentry *dentry, int mode)
 {
@@ -73,10 +75,12 @@ static int xattr_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	return dir->i_op->mkdir(dir, dentry, mode);
 }
 
-/* We use I_MUTEX_CHILD here to silence lockdep. It's safe because xattr
+/*
+ * We use I_MUTEX_CHILD here to silence lockdep. It's safe because xattr
  * mutation ops aren't called during rename or splace, which are the
  * only other users of I_MUTEX_CHILD. It violates the ordering, but that's
- * better than allocating another subclass just for this code. */
+ * better than allocating another subclass just for this code.
+ */
 static int xattr_unlink(struct inode *dir, struct dentry *dentry)
 {
 	int error;
@@ -166,9 +170,11 @@ static struct dentry *open_xa_dir(const struct inode *inode, int flags)
 	return xadir;
 }
 
-/* The following are side effects of other operations that aren't explicitly
+/*
+ * The following are side effects of other operations that aren't explicitly
  * modifying extended attributes. This includes operations such as permissions
- * or ownership changes, object deletions, etc. */
+ * or ownership changes, object deletions, etc.
+ */
 struct reiserfs_dentry_buf {
 	struct dir_context ctx;
 	struct dentry *xadir;
@@ -267,11 +273,13 @@ static int reiserfs_for_each_xattr(struct inode *inode,
 	cleanup_dentry_buf(&buf);
 
 	if (!err) {
-		/* We start a transaction here to avoid a ABBA situation
+		/*
+		 * We start a transaction here to avoid a ABBA situation
 		 * between the xattr root's i_mutex and the journal lock.
 		 * This doesn't incur much additional overhead since the
 		 * new transaction will just nest inside the
-		 * outer transaction. */
+		 * outer transaction.
+		 */
 		int blocks = JOURNAL_PER_BALANCE_CNT * 2 + 2 +
 			     4 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb);
 		struct reiserfs_transaction_handle th;
@@ -284,7 +292,7 @@ static int reiserfs_for_each_xattr(struct inode *inode,
 					  I_MUTEX_XATTR);
 			err = action(dir, data);
 			reiserfs_write_lock(inode->i_sb);
-			jerror = journal_end(&th, inode->i_sb, blocks);
+			jerror = journal_end(&th);
 			reiserfs_write_unlock(inode->i_sb);
 			mutex_unlock(&dir->d_parent->d_inode->i_mutex);
 			err = jerror ?: err;
@@ -349,9 +357,11 @@ int reiserfs_chown_xattrs(struct inode *inode, struct iattr *attrs)
 }
 
 #ifdef CONFIG_REISERFS_FS_XATTR
-/* Returns a dentry corresponding to a specific extended attribute file
+/*
+ * Returns a dentry corresponding to a specific extended attribute file
  * for the inode. If flags allow, the file is created. Otherwise, a
- * valid or negative dentry, or an error is returned. */
+ * valid or negative dentry, or an error is returned.
+ */
 static struct dentry *xattr_lookup(struct inode *inode, const char *name,
 				    int flags)
 {
@@ -400,8 +410,10 @@ static struct page *reiserfs_get_page(struct inode *dir, size_t n)
 {
 	struct address_space *mapping = dir->i_mapping;
 	struct page *page;
-	/* We can deadlock if we try to free dentries,
-	   and an unlink/rmdir has just occurred - GFP_NOFS avoids this */
+	/*
+	 * We can deadlock if we try to free dentries,
+	 * and an unlink/rmdir has just occurred - GFP_NOFS avoids this
+	 */
 	mapping_set_gfp_mask(mapping, GFP_NOFS);
 	page = read_mapping_page(mapping, n >> PAGE_CACHE_SHIFT, NULL);
 	if (!IS_ERR(page)) {
@@ -411,7 +423,7 @@ static struct page *reiserfs_get_page(struct inode *dir, size_t n)
 	}
 	return page;
 
-      fail:
+fail:
 	reiserfs_put_page(page);
 	return ERR_PTR(-EIO);
 }
@@ -589,7 +601,7 @@ int reiserfs_xattr_set(struct inode *inode, const char *name,
 					  buffer, buffer_size, flags);
 
 	reiserfs_write_lock(inode->i_sb);
-	error2 = journal_end(&th, inode->i_sb, jbegin_count);
+	error2 = journal_end(&th);
 	reiserfs_write_unlock(inode->i_sb);
 	if (error == 0)
 		error = error2;
@@ -615,8 +627,10 @@ reiserfs_xattr_get(struct inode *inode, const char *name, void *buffer,
 	if (name == NULL)
 		return -EINVAL;
 
-	/* We can't have xattrs attached to v1 items since they don't have
-	 * generation numbers */
+	/*
+	 * We can't have xattrs attached to v1 items since they don't have
+	 * generation numbers
+	 */
 	if (get_inode_sd_version(inode) == STAT_DATA_V1)
 		return -EOPNOTSUPP;
 
@@ -913,12 +927,16 @@ static const struct xattr_handler *reiserfs_xattr_handlers[] = {
 
 static int xattr_mount_check(struct super_block *s)
 {
-	/* We need generation numbers to ensure that the oid mapping is correct
-	 * v3.5 filesystems don't have them. */
+	/*
+	 * We need generation numbers to ensure that the oid mapping is correct
+	 * v3.5 filesystems don't have them.
+	 */
 	if (old_format_only(s)) {
 		if (reiserfs_xattrs_optional(s)) {
-			/* Old format filesystem, but optional xattrs have
-			 * been enabled. Error out. */
+			/*
+			 * Old format filesystem, but optional xattrs have
+			 * been enabled. Error out.
+			 */
 			reiserfs_warning(s, "jdm-2005",
 					 "xattrs/ACLs not supported "
 					 "on pre-v3.6 format filesystems. "
@@ -972,9 +990,11 @@ int reiserfs_lookup_privroot(struct super_block *s)
 	return err;
 }
 
-/* We need to take a copy of the mount flags since things like
+/*
+ * We need to take a copy of the mount flags since things like
  * MS_RDONLY don't get set until *after* we're called.
- * mount_flags != mount_options */
+ * mount_flags != mount_options
+ */
 int reiserfs_xattr_init(struct super_block *s, int mount_flags)
 {
 	int err = 0;
@@ -1007,8 +1027,8 @@ int reiserfs_xattr_init(struct super_block *s, int mount_flags)
 
 error:
 	if (err) {
-		clear_bit(REISERFS_XATTRS_USER, &(REISERFS_SB(s)->s_mount_opt));
-		clear_bit(REISERFS_POSIXACL, &(REISERFS_SB(s)->s_mount_opt));
+		clear_bit(REISERFS_XATTRS_USER, &REISERFS_SB(s)->s_mount_opt);
+		clear_bit(REISERFS_POSIXACL, &REISERFS_SB(s)->s_mount_opt);
 	}
 
 	/* The super_block MS_POSIXACL must mirror the (no)acl mount option. */
diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h
index f59626c5d33..857ec7e3016 100644
--- a/fs/reiserfs/xattr.h
+++ b/fs/reiserfs/xattr.h
@@ -61,7 +61,8 @@ static inline loff_t reiserfs_xattr_nblocks(struct inode *inode, loff_t size)
 	return ret;
 }
 
-/* We may have to create up to 3 objects: xattr root, xattr dir, xattr file.
+/*
+ * We may have to create up to 3 objects: xattr root, xattr dir, xattr file.
  * Let's try to be smart about it.
  * xattr root: We cache it. If it's not cached, we may need to create it.
  * xattr dir: If anything has been loaded for this inode, we can set a flag
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index a6ce532402d..44503e29379 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -25,8 +25,10 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	int size = acl ? posix_acl_xattr_size(acl->a_count) : 0;
 
 
-	/* Pessimism: We can't assume that anything from the xattr root up
-	 * has been created. */
+	/*
+	 * Pessimism: We can't assume that anything from the xattr root up
+	 * has been created.
+	 */
 
 	jcreate_blocks = reiserfs_xattr_jcreate_nblocks(inode) +
 			 reiserfs_xattr_nblocks(inode, size) * 2;
@@ -37,7 +39,7 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	if (error == 0) {
 		error = __reiserfs_set_acl(&th, inode, type, acl);
 		reiserfs_write_lock(inode->i_sb);
-		error2 = journal_end(&th, inode->i_sb, jcreate_blocks);
+		error2 = journal_end(&th);
 		reiserfs_write_unlock(inode->i_sb);
 		if (error2)
 			error = error2;
@@ -111,7 +113,7 @@ static struct posix_acl *reiserfs_posix_acl_from_disk(const void *value, size_t
 		goto fail;
 	return acl;
 
-      fail:
+fail:
 	posix_acl_release(acl);
 	return ERR_PTR(-EINVAL);
 }
@@ -164,7 +166,7 @@ static void *reiserfs_posix_acl_to_disk(const struct posix_acl *acl, size_t * si
 	}
 	return (char *)ext_acl;
 
-      fail:
+fail:
 	kfree(ext_acl);
 	return ERR_PTR(-EINVAL);
 }
@@ -208,8 +210,10 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type)
 
 	retval = reiserfs_xattr_get(inode, name, value, size);
 	if (retval == -ENODATA || retval == -ENOSYS) {
-		/* This shouldn't actually happen as it should have
-		   been caught above.. but just in case */
+		/*
+		 * This shouldn't actually happen as it should have
+		 * been caught above.. but just in case
+		 */
 		acl = NULL;
 	} else if (retval < 0) {
 		acl = ERR_PTR(retval);
@@ -290,8 +294,10 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode,
 	return error;
 }
 
-/* dir->i_mutex: locked,
- * inode is new and not released into the wild yet */
+/*
+ * dir->i_mutex: locked,
+ * inode is new and not released into the wild yet
+ */
 int
 reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th,
 			     struct inode *dir, struct dentry *dentry,
@@ -304,14 +310,18 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th,
 	if (S_ISLNK(inode->i_mode))
 		return 0;
 
-	/* ACLs can only be used on "new" objects, so if it's an old object
-	 * there is nothing to inherit from */
+	/*
+	 * ACLs can only be used on "new" objects, so if it's an old object
+	 * there is nothing to inherit from
+	 */
 	if (get_inode_sd_version(dir) == STAT_DATA_V1)
 		goto apply_umask;
 
-	/* Don't apply ACLs to objects in the .reiserfs_priv tree.. This
+	/*
+	 * Don't apply ACLs to objects in the .reiserfs_priv tree.. This
 	 * would be useless since permissions are ignored, and a pain because
-	 * it introduces locking cycles */
+	 * it introduces locking cycles
+	 */
 	if (IS_PRIVATE(dir)) {
 		inode->i_flags |= S_PRIVATE;
 		goto apply_umask;
@@ -335,7 +345,7 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th,
 
 	return err;
 
-      apply_umask:
+apply_umask:
 	/* no ACL, apply umask */
 	inode->i_mode &= ~current_umask();
 	return err;
diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c
index f373bde8f54..ea06c755486 100644
--- a/fs/romfs/mmap-nommu.c
+++ b/fs/romfs/mmap-nommu.c
@@ -72,8 +72,8 @@ static int romfs_mmap(struct file *file, struct vm_area_struct *vma)
 
 const struct file_operations romfs_ro_fops = {
 	.llseek			= generic_file_llseek,
-	.read			= do_sync_read,
-	.aio_read		= generic_file_aio_read,
+	.read			= new_sync_read,
+	.read_iter		= generic_file_read_iter,
 	.splice_read		= generic_file_splice_read,
 	.mmap			= romfs_mmap,
 	.get_unmapped_area	= romfs_get_unmapped_area,
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 1d641bb108d..3857b720cb1 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -8,8 +8,10 @@
 #include <linux/fs.h>
 #include <linux/export.h>
 #include <linux/seq_file.h>
+#include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/cred.h>
+#include <linux/mm.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -30,6 +32,16 @@ static void seq_set_overflow(struct seq_file *m)
 	m->count = m->size;
 }
 
+static void *seq_buf_alloc(unsigned long size)
+{
+	void *buf;
+
+	buf = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
+	if (!buf && size > PAGE_SIZE)
+		buf = vmalloc(size);
+	return buf;
+}
+
 /**
  *	seq_open -	initialize sequential file
  *	@file: file we initialize
@@ -96,7 +108,7 @@ static int traverse(struct seq_file *m, loff_t offset)
 		return 0;
 	}
 	if (!m->buf) {
-		m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
+		m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
 		if (!m->buf)
 			return -ENOMEM;
 	}
@@ -135,9 +147,9 @@ static int traverse(struct seq_file *m, loff_t offset)
 
 Eoverflow:
 	m->op->stop(m, p);
-	kfree(m->buf);
+	kvfree(m->buf);
 	m->count = 0;
-	m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
+	m->buf = seq_buf_alloc(m->size <<= 1);
 	return !m->buf ? -ENOMEM : -EAGAIN;
 }
 
@@ -192,7 +204,7 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 
 	/* grab buffer if we didn't have one */
 	if (!m->buf) {
-		m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL);
+		m->buf = seq_buf_alloc(m->size = PAGE_SIZE);
 		if (!m->buf)
 			goto Enomem;
 	}
@@ -232,9 +244,9 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 		if (m->count < m->size)
 			goto Fill;
 		m->op->stop(m, p);
-		kfree(m->buf);
+		kvfree(m->buf);
 		m->count = 0;
-		m->buf = kmalloc(m->size <<= 1, GFP_KERNEL);
+		m->buf = seq_buf_alloc(m->size <<= 1);
 		if (!m->buf)
 			goto Enomem;
 		m->version = 0;
@@ -350,7 +362,7 @@ EXPORT_SYMBOL(seq_lseek);
 int seq_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = file->private_data;
-	kfree(m->buf);
+	kvfree(m->buf);
 	kfree(m);
 	return 0;
 }
@@ -605,13 +617,13 @@ EXPORT_SYMBOL(single_open);
 int single_open_size(struct file *file, int (*show)(struct seq_file *, void *),
 		void *data, size_t size)
 {
-	char *buf = kmalloc(size, GFP_KERNEL);
+	char *buf = seq_buf_alloc(size);
 	int ret;
 	if (!buf)
 		return -ENOMEM;
 	ret = single_open(file, show, data);
 	if (ret) {
-		kfree(buf);
+		kvfree(buf);
 		return ret;
 	}
 	((struct seq_file *)file->private_data)->buf = buf;
diff --git a/fs/splice.c b/fs/splice.c
index e246954ea48..f5cb9ba8451 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -32,6 +32,7 @@
 #include <linux/gfp.h>
 #include <linux/socket.h>
 #include <linux/compat.h>
+#include <linux/aio.h>
 #include "internal.h"
 
 /*
@@ -717,63 +718,6 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe,
 				    sd->len, &pos, more);
 }
 
-/*
- * This is a little more tricky than the file -> pipe splicing. There are
- * basically three cases:
- *
- *	- Destination page already exists in the address space and there
- *	  are users of it. For that case we have no other option that
- *	  copying the data. Tough luck.
- *	- Destination page already exists in the address space, but there
- *	  are no users of it. Make sure it's uptodate, then drop it. Fall
- *	  through to last case.
- *	- Destination page does not exist, we can add the pipe page to
- *	  the page cache and avoid the copy.
- *
- * If asked to move pages to the output file (SPLICE_F_MOVE is set in
- * sd->flags), we attempt to migrate pages from the pipe to the output
- * file address space page cache. This is possible if no one else has
- * the pipe page referenced outside of the pipe and page cache. If
- * SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create
- * a new page in the output file page cache and fill/dirty that.
- */
-int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
-		 struct splice_desc *sd)
-{
-	struct file *file = sd->u.file;
-	struct address_space *mapping = file->f_mapping;
-	unsigned int offset, this_len;
-	struct page *page;
-	void *fsdata;
-	int ret;
-
-	offset = sd->pos & ~PAGE_CACHE_MASK;
-
-	this_len = sd->len;
-	if (this_len + offset > PAGE_CACHE_SIZE)
-		this_len = PAGE_CACHE_SIZE - offset;
-
-	ret = pagecache_write_begin(file, mapping, sd->pos, this_len,
-				AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
-	if (unlikely(ret))
-		goto out;
-
-	if (buf->page != page) {
-		char *src = kmap_atomic(buf->page);
-		char *dst = kmap_atomic(page);
-
-		memcpy(dst + offset, src + buf->offset, this_len);
-		flush_dcache_page(page);
-		kunmap_atomic(dst);
-		kunmap_atomic(src);
-	}
-	ret = pagecache_write_end(file, mapping, sd->pos, this_len, this_len,
-				page, fsdata);
-out:
-	return ret;
-}
-EXPORT_SYMBOL(pipe_to_file);
-
 static void wakeup_pipe_writers(struct pipe_inode_info *pipe)
 {
 	smp_mb();
@@ -802,7 +746,7 @@ static void wakeup_pipe_writers(struct pipe_inode_info *pipe)
  *    locking is required around copying the pipe buffers to the
  *    destination.
  */
-int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
+static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
 			  splice_actor *actor)
 {
 	int ret;
@@ -849,7 +793,6 @@ int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd,
 
 	return 1;
 }
-EXPORT_SYMBOL(splice_from_pipe_feed);
 
 /**
  * splice_from_pipe_next - wait for some data to splice from
@@ -861,7 +804,7 @@ EXPORT_SYMBOL(splice_from_pipe_feed);
  *    value (one) if pipe buffers are available.  It will return zero
  *    or -errno if no more data needs to be spliced.
  */
-int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd)
+static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd)
 {
 	while (!pipe->nrbufs) {
 		if (!pipe->writers)
@@ -886,7 +829,6 @@ int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd)
 
 	return 1;
 }
-EXPORT_SYMBOL(splice_from_pipe_next);
 
 /**
  * splice_from_pipe_begin - start splicing from pipe
@@ -897,12 +839,11 @@ EXPORT_SYMBOL(splice_from_pipe_next);
  *    splice_from_pipe_next() and splice_from_pipe_feed() to
  *    initialize the necessary fields of @sd.
  */
-void splice_from_pipe_begin(struct splice_desc *sd)
+static void splice_from_pipe_begin(struct splice_desc *sd)
 {
 	sd->num_spliced = 0;
 	sd->need_wakeup = false;
 }
-EXPORT_SYMBOL(splice_from_pipe_begin);
 
 /**
  * splice_from_pipe_end - finish splicing from pipe
@@ -914,12 +855,11 @@ EXPORT_SYMBOL(splice_from_pipe_begin);
  *    be called after a loop containing splice_from_pipe_next() and
  *    splice_from_pipe_feed().
  */
-void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd)
+static void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd)
 {
 	if (sd->need_wakeup)
 		wakeup_pipe_writers(pipe);
 }
-EXPORT_SYMBOL(splice_from_pipe_end);
 
 /**
  * __splice_from_pipe - splice data from a pipe to given actor
@@ -985,7 +925,7 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
 }
 
 /**
- * generic_file_splice_write - splice data from a pipe to a file
+ * iter_file_splice_write - splice data from a pipe to a file
  * @pipe:	pipe info
  * @out:	file to write to
  * @ppos:	position in @out
@@ -995,40 +935,122 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
  * Description:
  *    Will either move or copy pages (determined by @flags options) from
  *    the given pipe inode to the given file.
+ *    This one is ->write_iter-based.
  *
  */
 ssize_t
-generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
+iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 			  loff_t *ppos, size_t len, unsigned int flags)
 {
-	struct address_space *mapping = out->f_mapping;
-	struct inode *inode = mapping->host;
 	struct splice_desc sd = {
 		.total_len = len,
 		.flags = flags,
 		.pos = *ppos,
 		.u.file = out,
 	};
+	int nbufs = pipe->buffers;
+	struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec),
+					GFP_KERNEL);
 	ssize_t ret;
 
+	if (unlikely(!array))
+		return -ENOMEM;
+
 	pipe_lock(pipe);
 
 	splice_from_pipe_begin(&sd);
-	do {
+	while (sd.total_len) {
+		struct iov_iter from;
+		struct kiocb kiocb;
+		size_t left;
+		int n, idx;
+
 		ret = splice_from_pipe_next(pipe, &sd);
 		if (ret <= 0)
 			break;
 
-		mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
-		ret = file_remove_suid(out);
-		if (!ret) {
-			ret = file_update_time(out);
-			if (!ret)
-				ret = splice_from_pipe_feed(pipe, &sd,
-							    pipe_to_file);
+		if (unlikely(nbufs < pipe->buffers)) {
+			kfree(array);
+			nbufs = pipe->buffers;
+			array = kcalloc(nbufs, sizeof(struct bio_vec),
+					GFP_KERNEL);
+			if (!array) {
+				ret = -ENOMEM;
+				break;
+			}
 		}
-		mutex_unlock(&inode->i_mutex);
-	} while (ret > 0);
+
+		/* build the vector */
+		left = sd.total_len;
+		for (n = 0, idx = pipe->curbuf; left && n < pipe->nrbufs; n++, idx++) {
+			struct pipe_buffer *buf = pipe->bufs + idx;
+			size_t this_len = buf->len;
+
+			if (this_len > left)
+				this_len = left;
+
+			if (idx == pipe->buffers - 1)
+				idx = -1;
+
+			ret = buf->ops->confirm(pipe, buf);
+			if (unlikely(ret)) {
+				if (ret == -ENODATA)
+					ret = 0;
+				goto done;
+			}
+
+			array[n].bv_page = buf->page;
+			array[n].bv_len = this_len;
+			array[n].bv_offset = buf->offset;
+			left -= this_len;
+		}
+
+		/* ... iov_iter */
+		from.type = ITER_BVEC | WRITE;
+		from.bvec = array;
+		from.nr_segs = n;
+		from.count = sd.total_len - left;
+		from.iov_offset = 0;
+
+		/* ... and iocb */
+		init_sync_kiocb(&kiocb, out);
+		kiocb.ki_pos = sd.pos;
+		kiocb.ki_nbytes = sd.total_len - left;
+
+		/* now, send it */
+		ret = out->f_op->write_iter(&kiocb, &from);
+		if (-EIOCBQUEUED == ret)
+			ret = wait_on_sync_kiocb(&kiocb);
+
+		if (ret <= 0)
+			break;
+
+		sd.num_spliced += ret;
+		sd.total_len -= ret;
+		*ppos = sd.pos = kiocb.ki_pos;
+
+		/* dismiss the fully eaten buffers, adjust the partial one */
+		while (ret) {
+			struct pipe_buffer *buf = pipe->bufs + pipe->curbuf;
+			if (ret >= buf->len) {
+				const struct pipe_buf_operations *ops = buf->ops;
+				ret -= buf->len;
+				buf->len = 0;
+				buf->ops = NULL;
+				ops->release(pipe, buf);
+				pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
+				pipe->nrbufs--;
+				if (pipe->files)
+					sd.need_wakeup = true;
+			} else {
+				buf->offset += ret;
+				buf->len -= ret;
+				ret = 0;
+			}
+		}
+	}
+done:
+	kfree(array);
 	splice_from_pipe_end(pipe, &sd);
 
 	pipe_unlock(pipe);
@@ -1036,21 +1058,10 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 	if (sd.num_spliced)
 		ret = sd.num_spliced;
 
-	if (ret > 0) {
-		int err;
-
-		err = generic_write_sync(out, *ppos, ret);
-		if (err)
-			ret = err;
-		else
-			*ppos += ret;
-		balance_dirty_pages_ratelimited(mapping);
-	}
-
 	return ret;
 }
 
-EXPORT_SYMBOL(generic_file_splice_write);
+EXPORT_SYMBOL(iter_file_splice_write);
 
 static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 			  struct splice_desc *sd)
@@ -1549,7 +1560,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov,
 		goto out;
 
 	count = ret;
-	iov_iter_init(&iter, iov, nr_segs, count, 0);
+	iov_iter_init(&iter, READ, iov, nr_segs, count);
 
 	sd.len = 0;
 	sd.total_len = count;
diff --git a/fs/sysv/file.c b/fs/sysv/file.c
index 9d4dc683179..b00811c75b2 100644
--- a/fs/sysv/file.c
+++ b/fs/sysv/file.c
@@ -21,10 +21,10 @@
  */
 const struct file_operations sysv_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.fsync		= generic_file_fsync,
 	.splice_read	= generic_file_splice_read,
diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index e8e01d74dc0..eb997e9c4ab 100644
--- a/fs/ubifs/budget.c
+++ b/fs/ubifs/budget.c
@@ -437,7 +437,6 @@ static int calc_dd_growth(const struct ubifs_info *c,
  */
 int ubifs_budget_space(struct ubifs_info *c, struct ubifs_budget_req *req)
 {
-	int uninitialized_var(cmt_retries), uninitialized_var(wb_retries);
 	int err, idx_growth, data_growth, dd_growth, retried = 0;
 
 	ubifs_assert(req->new_page <= 1);
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 5157b866a85..177b0152fef 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -745,8 +745,10 @@ void ubifs_dump_lprops(struct ubifs_info *c)
 
 	for (lnum = c->main_first; lnum < c->leb_cnt; lnum++) {
 		err = ubifs_read_one_lp(c, lnum, &lp);
-		if (err)
+		if (err) {
 			ubifs_err("cannot read lprops for LEB %d", lnum);
+			continue;
+		}
 
 		ubifs_dump_lprop(c, &lp);
 	}
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 4f34dbae823..b5b593c4527 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -903,8 +903,9 @@ static int do_writepage(struct page *page, int len)
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
 
 #ifdef UBIFS_DEBUG
+	struct ubifs_inode *ui = ubifs_inode(inode);
 	spin_lock(&ui->ui_lock);
-	ubifs_assert(page->index <= ui->synced_i_size << PAGE_CACHE_SIZE);
+	ubifs_assert(page->index <= ui->synced_i_size >> PAGE_CACHE_SHIFT);
 	spin_unlock(&ui->ui_lock);
 #endif
 
@@ -1363,17 +1364,17 @@ static inline int mctime_update_needed(const struct inode *inode,
 
 /**
  * update_ctime - update mtime and ctime of an inode.
- * @c: UBIFS file-system description object
  * @inode: inode to update
  *
  * This function updates mtime and ctime of the inode if it is not equivalent to
  * current time. Returns zero in case of success and a negative error code in
  * case of failure.
  */
-static int update_mctime(struct ubifs_info *c, struct inode *inode)
+static int update_mctime(struct inode *inode)
 {
 	struct timespec now = ubifs_current_time(inode);
 	struct ubifs_inode *ui = ubifs_inode(inode);
+	struct ubifs_info *c = inode->i_sb->s_fs_info;
 
 	if (mctime_update_needed(inode, &now)) {
 		int err, release;
@@ -1396,18 +1397,13 @@ static int update_mctime(struct ubifs_info *c, struct inode *inode)
 	return 0;
 }
 
-static ssize_t ubifs_aio_write(struct kiocb *iocb, const struct iovec *iov,
-			       unsigned long nr_segs, loff_t pos)
+static ssize_t ubifs_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
-	int err;
-	struct inode *inode = iocb->ki_filp->f_mapping->host;
-	struct ubifs_info *c = inode->i_sb->s_fs_info;
-
-	err = update_mctime(c, inode);
+	int err = update_mctime(file_inode(iocb->ki_filp));
 	if (err)
 		return err;
 
-	return generic_file_aio_write(iocb, iov, nr_segs, pos);
+	return generic_file_write_iter(iocb, from);
 }
 
 static int ubifs_set_page_dirty(struct page *page)
@@ -1525,8 +1521,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma,
 	}
 
 	wait_for_stable_page(page);
-	unlock_page(page);
-	return 0;
+	return VM_FAULT_LOCKED;
 
 out_unlock:
 	unlock_page(page);
@@ -1582,15 +1577,15 @@ const struct inode_operations ubifs_symlink_inode_operations = {
 
 const struct file_operations ubifs_file_operations = {
 	.llseek         = generic_file_llseek,
-	.read           = do_sync_read,
-	.write          = do_sync_write,
-	.aio_read       = generic_file_aio_read,
-	.aio_write      = ubifs_aio_write,
+	.read           = new_sync_read,
+	.write          = new_sync_write,
+	.read_iter      = generic_file_read_iter,
+	.write_iter     = ubifs_write_iter,
 	.mmap           = ubifs_file_mmap,
 	.fsync          = ubifs_fsync,
 	.unlocked_ioctl = ubifs_ioctl,
 	.splice_read	= generic_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = ubifs_compat_ioctl,
 #endif
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index e18b9889a51..2290d586672 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -988,30 +988,32 @@ int ubifs_read_node(const struct ubifs_info *c, void *buf, int type, int len,
 		return err;
 
 	if (type != ch->node_type) {
-		ubifs_err("bad node type (%d but expected %d)",
-			  ch->node_type, type);
+		ubifs_errc(c, "bad node type (%d but expected %d)",
+			   ch->node_type, type);
 		goto out;
 	}
 
 	err = ubifs_check_node(c, buf, lnum, offs, 0, 0);
 	if (err) {
-		ubifs_err("expected node type %d", type);
+		ubifs_errc(c, "expected node type %d", type);
 		return err;
 	}
 
 	l = le32_to_cpu(ch->len);
 	if (l != len) {
-		ubifs_err("bad node length %d, expected %d", l, len);
+		ubifs_errc(c, "bad node length %d, expected %d", l, len);
 		goto out;
 	}
 
 	return 0;
 
 out:
-	ubifs_err("bad node at LEB %d:%d, LEB mapping status %d", lnum, offs,
-		  ubi_is_mapped(c->ubi, lnum));
-	ubifs_dump_node(c, buf);
-	dump_stack();
+	ubifs_errc(c, "bad node at LEB %d:%d, LEB mapping status %d", lnum,
+		   offs, ubi_is_mapped(c->ubi, lnum));
+	if (!c->probing) {
+		ubifs_dump_node(c, buf);
+		dump_stack();
+	}
 	return -EINVAL;
 }
 
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index f35135e28e9..9a9fb94a41c 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -128,7 +128,6 @@ static int shrink_tnc(struct ubifs_info *c, int nr, int age, int *contention)
 			freed = ubifs_destroy_tnc_subtree(znode);
 			atomic_long_sub(freed, &ubifs_clean_zn_cnt);
 			atomic_long_sub(freed, &c->clean_zn_cnt);
-			ubifs_assert(atomic_long_read(&c->clean_zn_cnt) >= 0);
 			total_freed += freed;
 			znode = zprev;
 		}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index a81c7b55689..3904c8574ef 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1149,6 +1149,9 @@ static int mount_ubifs(struct ubifs_info *c)
 	size_t sz;
 
 	c->ro_mount = !!(c->vfs_sb->s_flags & MS_RDONLY);
+	/* Suppress error messages while probing if MS_SILENT is set */
+	c->probing = !!(c->vfs_sb->s_flags & MS_SILENT);
+
 	err = init_constants_early(c);
 	if (err)
 		return err;
@@ -1214,6 +1217,8 @@ static int mount_ubifs(struct ubifs_info *c)
 	if (err)
 		goto out_free;
 
+	c->probing = 0;
+
 	/*
 	 * Make sure the compressor which is set as default in the superblock
 	 * or overridden by mount options is actually compiled in.
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 9083bc7ed4a..8a40cf9c02d 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -2859,10 +2859,11 @@ void ubifs_tnc_close(struct ubifs_info *c)
 {
 	tnc_destroy_cnext(c);
 	if (c->zroot.znode) {
-		long n;
+		long n, freed;
 
-		ubifs_destroy_tnc_subtree(c->zroot.znode);
 		n = atomic_long_read(&c->clean_zn_cnt);
+		freed = ubifs_destroy_tnc_subtree(c->zroot.znode);
+		ubifs_assert(freed == n);
 		atomic_long_sub(n, &ubifs_clean_zn_cnt);
 	}
 	kfree(c->gap_lebs);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index e8c8cfe1435..c1f71fe17cc 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -51,6 +51,15 @@
 #define ubifs_warn(fmt, ...)                                        \
 	pr_warn("UBIFS warning (pid %d): %s: " fmt "\n",            \
 		current->pid, __func__, ##__VA_ARGS__)
+/*
+ * A variant of 'ubifs_err()' which takes the UBIFS file-sytem description
+ * object as an argument.
+ */
+#define ubifs_errc(c, fmt, ...)                                     \
+	do {                                                        \
+		if (!(c)->probing)                                  \
+			ubifs_err(fmt, ##__VA_ARGS__);              \
+	} while (0)
 
 /* UBIFS file system VFS magic number */
 #define UBIFS_SUPER_MAGIC 0x24051905
@@ -1209,6 +1218,7 @@ struct ubifs_debug_info;
  * @need_recovery: %1 if the file-system needs recovery
  * @replaying: %1 during journal replay
  * @mounting: %1 while mounting
+ * @probing: %1 while attempting to mount if MS_SILENT mount flag is set
  * @remounting_rw: %1 while re-mounting from R/O mode to R/W mode
  * @replay_list: temporary list used during journal replay
  * @replay_buds: list of buds to replay
@@ -1441,6 +1451,7 @@ struct ubifs_info {
 	unsigned int replaying:1;
 	unsigned int mounting:1;
 	unsigned int remounting_rw:1;
+	unsigned int probing:1;
 	struct list_head replay_list;
 	struct list_head replay_buds;
 	unsigned long long cs_sqnum;
diff --git a/fs/udf/file.c b/fs/udf/file.c
index d2c170f8b03..d80738fdf42 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -119,8 +119,8 @@ static int udf_adinicb_write_end(struct file *file,
 }
 
 static ssize_t udf_adinicb_direct_IO(int rw, struct kiocb *iocb,
-				     const struct iovec *iov,
-				     loff_t offset, unsigned long nr_segs)
+				     struct iov_iter *iter,
+				     loff_t offset)
 {
 	/* Fallback to buffered I/O. */
 	return 0;
@@ -134,8 +134,7 @@ const struct address_space_operations udf_adinicb_aops = {
 	.direct_IO	= udf_adinicb_direct_IO,
 };
 
-static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				  unsigned long nr_segs, loff_t ppos)
+static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	ssize_t retval;
 	struct file *file = iocb->ki_filp;
@@ -150,7 +149,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		if (file->f_flags & O_APPEND)
 			pos = inode->i_size;
 		else
-			pos = ppos;
+			pos = iocb->ki_pos;
 
 		if (inode->i_sb->s_blocksize <
 				(udf_file_entry_alloc_offset(inode) +
@@ -171,7 +170,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	} else
 		up_write(&iinfo->i_data_sem);
 
-	retval = __generic_file_aio_write(iocb, iov, nr_segs);
+	retval = __generic_file_write_iter(iocb, from);
 	mutex_unlock(&inode->i_mutex);
 
 	if (retval > 0) {
@@ -252,13 +251,13 @@ static int udf_release_file(struct inode *inode, struct file *filp)
 }
 
 const struct file_operations udf_file_operations = {
-	.read			= do_sync_read,
-	.aio_read		= generic_file_aio_read,
+	.read			= new_sync_read,
+	.read_iter		= generic_file_read_iter,
 	.unlocked_ioctl		= udf_ioctl,
 	.open			= generic_file_open,
 	.mmap			= generic_file_mmap,
-	.write			= do_sync_write,
-	.aio_write		= udf_file_aio_write,
+	.write			= new_sync_write,
+	.write_iter		= udf_file_write_iter,
 	.release		= udf_release_file,
 	.fsync			= generic_file_fsync,
 	.splice_read		= generic_file_splice_read,
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 5d643706212..236cd48184c 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -217,18 +217,18 @@ static int udf_write_begin(struct file *file, struct address_space *mapping,
 }
 
 static ssize_t udf_direct_IO(int rw, struct kiocb *iocb,
-			     const struct iovec *iov,
-			     loff_t offset, unsigned long nr_segs)
+			     struct iov_iter *iter,
+			     loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
+	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
-				  udf_get_block);
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, udf_get_block);
 	if (unlikely(ret < 0 && (rw & WRITE)))
-		udf_write_failed(mapping, offset + iov_length(iov, nr_segs));
+		udf_write_failed(mapping, offset + count);
 	return ret;
 }
 
diff --git a/fs/ufs/file.c b/fs/ufs/file.c
index 33afa20d450..c84ec010a67 100644
--- a/fs/ufs/file.c
+++ b/fs/ufs/file.c
@@ -35,10 +35,10 @@
  
 const struct file_operations ufs_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= do_sync_read,
-	.aio_read	= generic_file_aio_read,
-	.write		= do_sync_write,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
 	.mmap		= generic_file_mmap,
 	.open           = generic_file_open,
 	.fsync		= generic_file_fsync,
diff --git a/fs/xattr.c b/fs/xattr.c
index 3377dff1840..c69e6d43a0d 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -843,7 +843,7 @@ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size)
 
 	/* wrap around? */
 	len = sizeof(*new_xattr) + size;
-	if (len <= sizeof(*new_xattr))
+	if (len < sizeof(*new_xattr))
 		return NULL;
 
 	new_xattr = kmalloc(len, GFP_KERNEL);
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 0fdd4109c62..6e247a99f5d 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -160,30 +160,38 @@ typedef struct xfs_agi {
 	 * still being referenced.
 	 */
 	__be32		agi_unlinked[XFS_AGI_UNLINKED_BUCKETS];
-
+	/*
+	 * This marks the end of logging region 1 and start of logging region 2.
+	 */
 	uuid_t		agi_uuid;	/* uuid of filesystem */
 	__be32		agi_crc;	/* crc of agi sector */
 	__be32		agi_pad32;
 	__be64		agi_lsn;	/* last write sequence */
 
+	__be32		agi_free_root; /* root of the free inode btree */
+	__be32		agi_free_level;/* levels in free inode btree */
+
 	/* structure must be padded to 64 bit alignment */
 } xfs_agi_t;
 
 #define XFS_AGI_CRC_OFF		offsetof(struct xfs_agi, agi_crc)
 
-#define	XFS_AGI_MAGICNUM	0x00000001
-#define	XFS_AGI_VERSIONNUM	0x00000002
-#define	XFS_AGI_SEQNO		0x00000004
-#define	XFS_AGI_LENGTH		0x00000008
-#define	XFS_AGI_COUNT		0x00000010
-#define	XFS_AGI_ROOT		0x00000020
-#define	XFS_AGI_LEVEL		0x00000040
-#define	XFS_AGI_FREECOUNT	0x00000080
-#define	XFS_AGI_NEWINO		0x00000100
-#define	XFS_AGI_DIRINO		0x00000200
-#define	XFS_AGI_UNLINKED	0x00000400
-#define	XFS_AGI_NUM_BITS	11
-#define	XFS_AGI_ALL_BITS	((1 << XFS_AGI_NUM_BITS) - 1)
+#define	XFS_AGI_MAGICNUM	(1 << 0)
+#define	XFS_AGI_VERSIONNUM	(1 << 1)
+#define	XFS_AGI_SEQNO		(1 << 2)
+#define	XFS_AGI_LENGTH		(1 << 3)
+#define	XFS_AGI_COUNT		(1 << 4)
+#define	XFS_AGI_ROOT		(1 << 5)
+#define	XFS_AGI_LEVEL		(1 << 6)
+#define	XFS_AGI_FREECOUNT	(1 << 7)
+#define	XFS_AGI_NEWINO		(1 << 8)
+#define	XFS_AGI_DIRINO		(1 << 9)
+#define	XFS_AGI_UNLINKED	(1 << 10)
+#define	XFS_AGI_NUM_BITS_R1	11	/* end of the 1st agi logging region */
+#define	XFS_AGI_ALL_BITS_R1	((1 << XFS_AGI_NUM_BITS_R1) - 1)
+#define	XFS_AGI_FREE_ROOT	(1 << 11)
+#define	XFS_AGI_FREE_LEVEL	(1 << 12)
+#define	XFS_AGI_NUM_BITS_R2	13
 
 /* disk block (xfs_daddr_t) in the AG */
 #define XFS_AGI_DADDR(mp)	((xfs_daddr_t)(2 << (mp)->m_sectbb_log))
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index c1cf6a336a7..d43813267a8 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -257,16 +257,14 @@ xfs_alloc_fix_len(
 	k = rlen % args->prod;
 	if (k == args->mod)
 		return;
-	if (k > args->mod) {
-		if ((int)(rlen = rlen - k - args->mod) < (int)args->minlen)
-			return;
-	} else {
-		if ((int)(rlen = rlen - args->prod - (args->mod - k)) <
-		    (int)args->minlen)
-			return;
-	}
-	ASSERT(rlen >= args->minlen);
-	ASSERT(rlen <= args->maxlen);
+	if (k > args->mod)
+		rlen = rlen - (k - args->mod);
+	else
+		rlen = rlen - args->prod + (args->mod - k);
+	if ((int)rlen < (int)args->minlen)
+		return;
+	ASSERT(rlen >= args->minlen && rlen <= args->maxlen);
+	ASSERT(rlen % args->prod == args->mod);
 	args->len = rlen;
 }
 
@@ -541,7 +539,6 @@ xfs_alloc_read_agfl(
 			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
 	if (error)
 		return error;
-	ASSERT(!xfs_buf_geterror(bp));
 	xfs_buf_set_ref(bp, XFS_AGFL_REF);
 	*bpp = bp;
 	return 0;
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index cc1eadcbb04..8358f1ded94 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -70,7 +70,6 @@ xfs_allocbt_alloc_block(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*start,
 	union xfs_btree_ptr	*new,
-	int			length,
 	int			*stat)
 {
 	int			error;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0479c32c5eb..faaf716e208 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -975,14 +975,39 @@ xfs_vm_writepage(
 	 * Given that we do not allow direct reclaim to call us, we should
 	 * never be called while in a filesystem transaction.
 	 */
-	if (WARN_ON(current->flags & PF_FSTRANS))
+	if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
 		goto redirty;
 
 	/* Is this page beyond the end of the file? */
 	offset = i_size_read(inode);
 	end_index = offset >> PAGE_CACHE_SHIFT;
 	last_index = (offset - 1) >> PAGE_CACHE_SHIFT;
-	if (page->index >= end_index) {
+
+	/*
+	 * The page index is less than the end_index, adjust the end_offset
+	 * to the highest offset that this page should represent.
+	 * -----------------------------------------------------
+	 * |			file mapping	       | <EOF> |
+	 * -----------------------------------------------------
+	 * | Page ... | Page N-2 | Page N-1 |  Page N  |       |
+	 * ^--------------------------------^----------|--------
+	 * |     desired writeback range    |      see else    |
+	 * ---------------------------------^------------------|
+	 */
+	if (page->index < end_index)
+		end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT;
+	else {
+		/*
+		 * Check whether the page to write out is beyond or straddles
+		 * i_size or not.
+		 * -------------------------------------------------------
+		 * |		file mapping		        | <EOF>  |
+		 * -------------------------------------------------------
+		 * | Page ... | Page N-2 | Page N-1 |  Page N   | Beyond |
+		 * ^--------------------------------^-----------|---------
+		 * |				    |      Straddles     |
+		 * ---------------------------------^-----------|--------|
+		 */
 		unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1);
 
 		/*
@@ -990,24 +1015,36 @@ xfs_vm_writepage(
 		 * truncate operation that is in progress. We must redirty the
 		 * page so that reclaim stops reclaiming it. Otherwise
 		 * xfs_vm_releasepage() is called on it and gets confused.
+		 *
+		 * Note that the end_index is unsigned long, it would overflow
+		 * if the given offset is greater than 16TB on 32-bit system
+		 * and if we do check the page is fully outside i_size or not
+		 * via "if (page->index >= end_index + 1)" as "end_index + 1"
+		 * will be evaluated to 0.  Hence this page will be redirtied
+		 * and be written out repeatedly which would result in an
+		 * infinite loop, the user program that perform this operation
+		 * will hang.  Instead, we can verify this situation by checking
+		 * if the page to write is totally beyond the i_size or if it's
+		 * offset is just equal to the EOF.
 		 */
-		if (page->index >= end_index + 1 || offset_into_page == 0)
+		if (page->index > end_index ||
+		    (page->index == end_index && offset_into_page == 0))
 			goto redirty;
 
 		/*
 		 * The page straddles i_size.  It must be zeroed out on each
 		 * and every writepage invocation because it may be mmapped.
 		 * "A file is mapped in multiples of the page size.  For a file
-		 * that is not a multiple of the  page size, the remaining
+		 * that is not a multiple of the page size, the remaining
 		 * memory is zeroed when mapped, and writes to that region are
 		 * not written out to the file."
 		 */
 		zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE);
+
+		/* Adjust the end_offset to the end of file */
+		end_offset = offset;
 	}
 
-	end_offset = min_t(unsigned long long,
-			(xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
-			offset);
 	len = 1 << inode->i_blkbits;
 
 	bh = head = page_buffers(page);
@@ -1188,9 +1225,9 @@ xfs_vm_releasepage(
 
 	xfs_count_page_state(page, &delalloc, &unwritten);
 
-	if (WARN_ON(delalloc))
+	if (WARN_ON_ONCE(delalloc))
 		return 0;
-	if (WARN_ON(unwritten))
+	if (WARN_ON_ONCE(unwritten))
 		return 0;
 
 	return try_to_free_buffers(page);
@@ -1449,9 +1486,8 @@ STATIC ssize_t
 xfs_vm_direct_IO(
 	int			rw,
 	struct kiocb		*iocb,
-	const struct iovec	*iov,
-	loff_t			offset,
-	unsigned long		nr_segs)
+	struct iov_iter		*iter,
+	loff_t			offset)
 {
 	struct inode		*inode = iocb->ki_filp->f_mapping->host;
 	struct block_device	*bdev = xfs_find_bdev_for_inode(inode);
@@ -1459,7 +1495,7 @@ xfs_vm_direct_IO(
 	ssize_t			ret;
 
 	if (rw & WRITE) {
-		size_t size = iov_length(iov, nr_segs);
+		size_t size = iov_iter_count(iter);
 
 		/*
 		 * We cannot preallocate a size update transaction here as we
@@ -1471,17 +1507,15 @@ xfs_vm_direct_IO(
 		if (offset + size > XFS_I(inode)->i_d.di_size)
 			ioend->io_isdirect = 1;
 
-		ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
-					    offset, nr_segs,
-					    xfs_get_blocks_direct,
+		ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+					    offset, xfs_get_blocks_direct,
 					    xfs_end_io_direct_write, NULL,
 					    DIO_ASYNC_EXTEND);
 		if (ret != -EIOCBQUEUED && iocb->private)
 			goto out_destroy_ioend;
 	} else {
-		ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov,
-					    offset, nr_segs,
-					    xfs_get_blocks_direct,
+		ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
+					    offset, xfs_get_blocks_direct,
 					    NULL, NULL, 0);
 	}
 
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index abda1124a70..bfe36fc2cdc 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -77,17 +77,27 @@ STATIC int xfs_attr_refillstate(xfs_da_state_t *state);
 
 
 STATIC int
-xfs_attr_name_to_xname(
-	struct xfs_name	*xname,
-	const unsigned char *aname)
+xfs_attr_args_init(
+	struct xfs_da_args	*args,
+	struct xfs_inode	*dp,
+	const unsigned char	*name,
+	int			flags)
 {
-	if (!aname)
+
+	if (!name)
 		return EINVAL;
-	xname->name = aname;
-	xname->len = strlen((char *)aname);
-	if (xname->len >= MAXNAMELEN)
+
+	memset(args, 0, sizeof(*args));
+	args->geo = dp->i_mount->m_attr_geo;
+	args->whichfork = XFS_ATTR_FORK;
+	args->dp = dp;
+	args->flags = flags;
+	args->name = name;
+	args->namelen = strlen((const char *)name);
+	if (args->namelen >= MAXNAMELEN)
 		return EFAULT;		/* match IRIX behaviour */
 
+	args->hashval = xfs_da_hashname(args->name, args->namelen);
 	return 0;
 }
 
@@ -106,79 +116,46 @@ xfs_inode_hasattr(
  * Overall external interface routines.
  *========================================================================*/
 
-STATIC int
-xfs_attr_get_int(
+int
+xfs_attr_get(
 	struct xfs_inode	*ip,
-	struct xfs_name		*name,
+	const unsigned char	*name,
 	unsigned char		*value,
 	int			*valuelenp,
 	int			flags)
 {
-	xfs_da_args_t   args;
-	int             error;
+	struct xfs_da_args	args;
+	uint			lock_mode;
+	int			error;
+
+	XFS_STATS_INC(xs_attr_get);
+
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return EIO;
 
 	if (!xfs_inode_hasattr(ip))
 		return ENOATTR;
 
-	/*
-	 * Fill in the arg structure for this request.
-	 */
-	memset((char *)&args, 0, sizeof(args));
-	args.name = name->name;
-	args.namelen = name->len;
+	error = xfs_attr_args_init(&args, ip, name, flags);
+	if (error)
+		return error;
+
 	args.value = value;
 	args.valuelen = *valuelenp;
-	args.flags = flags;
-	args.hashval = xfs_da_hashname(args.name, args.namelen);
-	args.dp = ip;
-	args.whichfork = XFS_ATTR_FORK;
 
-	/*
-	 * Decide on what work routines to call based on the inode size.
-	 */
-	if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+	lock_mode = xfs_ilock_attr_map_shared(ip);
+	if (!xfs_inode_hasattr(ip))
+		error = ENOATTR;
+	else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
 		error = xfs_attr_shortform_getvalue(&args);
-	} else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK)) {
+	else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
 		error = xfs_attr_leaf_get(&args);
-	} else {
+	else
 		error = xfs_attr_node_get(&args);
-	}
+	xfs_iunlock(ip, lock_mode);
 
-	/*
-	 * Return the number of bytes in the value to the caller.
-	 */
 	*valuelenp = args.valuelen;
-
-	if (error == EEXIST)
-		error = 0;
-	return(error);
-}
-
-int
-xfs_attr_get(
-	xfs_inode_t	*ip,
-	const unsigned char *name,
-	unsigned char	*value,
-	int		*valuelenp,
-	int		flags)
-{
-	int		error;
-	struct xfs_name	xname;
-	uint		lock_mode;
-
-	XFS_STATS_INC(xs_attr_get);
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return(EIO);
-
-	error = xfs_attr_name_to_xname(&xname, name);
-	if (error)
-		return error;
-
-	lock_mode = xfs_ilock_attr_map_shared(ip);
-	error = xfs_attr_get_int(ip, &xname, value, valuelenp, flags);
-	xfs_iunlock(ip, lock_mode);
-	return(error);
+	return error == EEXIST ? 0 : error;
 }
 
 /*
@@ -186,12 +163,10 @@ xfs_attr_get(
  */
 STATIC int
 xfs_attr_calc_size(
-	struct xfs_inode 	*ip,
-	int			namelen,
-	int			valuelen,
+	struct xfs_da_args	*args,
 	int			*local)
 {
-	struct xfs_mount 	*mp = ip->i_mount;
+	struct xfs_mount	*mp = args->dp->i_mount;
 	int			size;
 	int			nblks;
 
@@ -199,12 +174,10 @@ xfs_attr_calc_size(
 	 * Determine space new attribute will use, and if it would be
 	 * "local" or "remote" (note: local != inline).
 	 */
-	size = xfs_attr_leaf_newentsize(namelen, valuelen,
-					mp->m_sb.sb_blocksize, local);
-
+	size = xfs_attr_leaf_newentsize(args, local);
 	nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK);
 	if (*local) {
-		if (size > (mp->m_sb.sb_blocksize >> 1)) {
+		if (size > (args->geo->blksize / 2)) {
 			/* Double split possible */
 			nblks *= 2;
 		}
@@ -213,7 +186,7 @@ xfs_attr_calc_size(
 		 * Out of line attribute, cannot double split, but
 		 * make room for the attribute value itself.
 		 */
-		uint	dblocks = xfs_attr3_rmt_blocks(mp, valuelen);
+		uint	dblocks = xfs_attr3_rmt_blocks(mp, args->valuelen);
 		nblks += dblocks;
 		nblks += XFS_NEXTENTADD_SPACE_RES(mp, dblocks, XFS_ATTR_FORK);
 	}
@@ -221,26 +194,38 @@ xfs_attr_calc_size(
 	return nblks;
 }
 
-STATIC int
-xfs_attr_set_int(
-	struct xfs_inode *dp,
-	struct xfs_name	*name,
-	unsigned char	*value,
-	int		valuelen,
-	int		flags)
+int
+xfs_attr_set(
+	struct xfs_inode	*dp,
+	const unsigned char	*name,
+	unsigned char		*value,
+	int			valuelen,
+	int			flags)
 {
-	xfs_da_args_t		args;
-	xfs_fsblock_t		firstblock;
-	xfs_bmap_free_t		flist;
-	int			error, err2, committed;
 	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_da_args	args;
+	struct xfs_bmap_free	flist;
 	struct xfs_trans_res	tres;
+	xfs_fsblock_t		firstblock;
 	int			rsvd = (flags & ATTR_ROOT) != 0;
-	int			local;
+	int			error, err2, committed, local;
+
+	XFS_STATS_INC(xs_attr_set);
+
+	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
+		return EIO;
+
+	error = xfs_attr_args_init(&args, dp, name, flags);
+	if (error)
+		return error;
+
+	args.value = value;
+	args.valuelen = valuelen;
+	args.firstblock = &firstblock;
+	args.flist = &flist;
+	args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
+	args.total = xfs_attr_calc_size(&args, &local);
 
-	/*
-	 * Attach the dquots to the inode.
-	 */
 	error = xfs_qm_dqattach(dp, 0);
 	if (error)
 		return error;
@@ -251,32 +236,14 @@ xfs_attr_set_int(
 	 */
 	if (XFS_IFORK_Q(dp) == 0) {
 		int sf_size = sizeof(xfs_attr_sf_hdr_t) +
-			      XFS_ATTR_SF_ENTSIZE_BYNAME(name->len, valuelen);
+			XFS_ATTR_SF_ENTSIZE_BYNAME(args.namelen, valuelen);
 
-		if ((error = xfs_bmap_add_attrfork(dp, sf_size, rsvd)))
-			return(error);
+		error = xfs_bmap_add_attrfork(dp, sf_size, rsvd);
+		if (error)
+			return error;
 	}
 
 	/*
-	 * Fill in the arg structure for this request.
-	 */
-	memset((char *)&args, 0, sizeof(args));
-	args.name = name->name;
-	args.namelen = name->len;
-	args.value = value;
-	args.valuelen = valuelen;
-	args.flags = flags;
-	args.hashval = xfs_da_hashname(args.name, args.namelen);
-	args.dp = dp;
-	args.firstblock = &firstblock;
-	args.flist = &flist;
-	args.whichfork = XFS_ATTR_FORK;
-	args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
-
-	/* Size is now blocks for attribute data */
-	args.total = xfs_attr_calc_size(dp, name->len, valuelen, &local);
-
-	/*
 	 * Start our first transaction of the day.
 	 *
 	 * All future transactions during this code must be "chained" off
@@ -303,7 +270,7 @@ xfs_attr_set_int(
 	error = xfs_trans_reserve(args.trans, &tres, args.total, 0);
 	if (error) {
 		xfs_trans_cancel(args.trans, 0);
-		return(error);
+		return error;
 	}
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 
@@ -313,7 +280,7 @@ xfs_attr_set_int(
 	if (error) {
 		xfs_iunlock(dp, XFS_ILOCK_EXCL);
 		xfs_trans_cancel(args.trans, XFS_TRANS_RELEASE_LOG_RES);
-		return (error);
+		return error;
 	}
 
 	xfs_trans_ijoin(args.trans, dp, 0);
@@ -322,9 +289,9 @@ xfs_attr_set_int(
 	 * If the attribute list is non-existent or a shortform list,
 	 * upgrade it to a single-leaf-block attribute list.
 	 */
-	if ((dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) ||
-	    ((dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS) &&
-	     (dp->i_d.di_anextents == 0))) {
+	if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
+	    (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
+	     dp->i_d.di_anextents == 0)) {
 
 		/*
 		 * Build initial attribute list (if required).
@@ -349,9 +316,8 @@ xfs_attr_set_int(
 			 * the transaction goes to disk before returning
 			 * to the user.
 			 */
-			if (mp->m_flags & XFS_MOUNT_WSYNC) {
+			if (mp->m_flags & XFS_MOUNT_WSYNC)
 				xfs_trans_set_sync(args.trans);
-			}
 
 			if (!error && (flags & ATTR_KERNOTIME) == 0) {
 				xfs_trans_ichgtime(args.trans, dp,
@@ -361,7 +327,7 @@ xfs_attr_set_int(
 						 XFS_TRANS_RELEASE_LOG_RES);
 			xfs_iunlock(dp, XFS_ILOCK_EXCL);
 
-			return(error == 0 ? err2 : error);
+			return error ? error : err2;
 		}
 
 		/*
@@ -399,22 +365,19 @@ xfs_attr_set_int(
 
 	}
 
-	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
 		error = xfs_attr_leaf_addname(&args);
-	} else {
+	else
 		error = xfs_attr_node_addname(&args);
-	}
-	if (error) {
+	if (error)
 		goto out;
-	}
 
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * transaction goes to disk before returning to the user.
 	 */
-	if (mp->m_flags & XFS_MOUNT_WSYNC) {
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
 		xfs_trans_set_sync(args.trans);
-	}
 
 	if ((flags & ATTR_KERNOTIME) == 0)
 		xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
@@ -426,65 +389,47 @@ xfs_attr_set_int(
 	error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
 
-	return(error);
+	return error;
 
 out:
-	if (args.trans)
+	if (args.trans) {
 		xfs_trans_cancel(args.trans,
 			XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
+	}
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
-	return(error);
+	return error;
 }
 
+/*
+ * Generic handler routine to remove a name from an attribute list.
+ * Transitions attribute list from Btree to shortform as necessary.
+ */
 int
-xfs_attr_set(
-	xfs_inode_t	*dp,
-	const unsigned char *name,
-	unsigned char	*value,
-	int		valuelen,
-	int		flags)
+xfs_attr_remove(
+	struct xfs_inode	*dp,
+	const unsigned char	*name,
+	int			flags)
 {
-	int             error;
-	struct xfs_name	xname;
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_da_args	args;
+	struct xfs_bmap_free	flist;
+	xfs_fsblock_t		firstblock;
+	int			error;
 
-	XFS_STATS_INC(xs_attr_set);
+	XFS_STATS_INC(xs_attr_remove);
 
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
-		return (EIO);
+		return EIO;
+
+	if (!xfs_inode_hasattr(dp))
+		return ENOATTR;
 
-	error = xfs_attr_name_to_xname(&xname, name);
+	error = xfs_attr_args_init(&args, dp, name, flags);
 	if (error)
 		return error;
 
-	return xfs_attr_set_int(dp, &xname, value, valuelen, flags);
-}
-
-/*
- * Generic handler routine to remove a name from an attribute list.
- * Transitions attribute list from Btree to shortform as necessary.
- */
-STATIC int
-xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
-{
-	xfs_da_args_t	args;
-	xfs_fsblock_t	firstblock;
-	xfs_bmap_free_t	flist;
-	int		error;
-	xfs_mount_t	*mp = dp->i_mount;
-
-	/*
-	 * Fill in the arg structure for this request.
-	 */
-	memset((char *)&args, 0, sizeof(args));
-	args.name = name->name;
-	args.namelen = name->len;
-	args.flags = flags;
-	args.hashval = xfs_da_hashname(args.name, args.namelen);
-	args.dp = dp;
 	args.firstblock = &firstblock;
 	args.flist = &flist;
-	args.total = 0;
-	args.whichfork = XFS_ATTR_FORK;
 
 	/*
 	 * we have no control over the attribute names that userspace passes us
@@ -493,9 +438,6 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
 	 */
 	args.op_flags = XFS_DA_OP_OKNOENT;
 
-	/*
-	 * Attach the dquots to the inode.
-	 */
 	error = xfs_qm_dqattach(dp, 0);
 	if (error)
 		return error;
@@ -524,7 +466,7 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
 				  XFS_ATTRRM_SPACE_RES(mp), 0);
 	if (error) {
 		xfs_trans_cancel(args.trans, 0);
-		return(error);
+		return error;
 	}
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
@@ -534,35 +476,26 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
 	 */
 	xfs_trans_ijoin(args.trans, dp, 0);
 
-	/*
-	 * Decide on what work routines to call based on the inode size.
-	 */
 	if (!xfs_inode_hasattr(dp)) {
 		error = XFS_ERROR(ENOATTR);
-		goto out;
-	}
-	if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+	} else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
 		ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
 		error = xfs_attr_shortform_remove(&args);
-		if (error) {
-			goto out;
-		}
 	} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
 		error = xfs_attr_leaf_removename(&args);
 	} else {
 		error = xfs_attr_node_removename(&args);
 	}
-	if (error) {
+
+	if (error)
 		goto out;
-	}
 
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * transaction goes to disk before returning to the user.
 	 */
-	if (mp->m_flags & XFS_MOUNT_WSYNC) {
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
 		xfs_trans_set_sync(args.trans);
-	}
 
 	if ((flags & ATTR_KERNOTIME) == 0)
 		xfs_trans_ichgtime(args.trans, dp, XFS_ICHGTIME_CHG);
@@ -574,45 +507,17 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags)
 	error = xfs_trans_commit(args.trans, XFS_TRANS_RELEASE_LOG_RES);
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
 
-	return(error);
+	return error;
 
 out:
-	if (args.trans)
+	if (args.trans) {
 		xfs_trans_cancel(args.trans,
 			XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
-	xfs_iunlock(dp, XFS_ILOCK_EXCL);
-	return(error);
-}
-
-int
-xfs_attr_remove(
-	xfs_inode_t	*dp,
-	const unsigned char *name,
-	int		flags)
-{
-	int		error;
-	struct xfs_name	xname;
-
-	XFS_STATS_INC(xs_attr_remove);
-
-	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
-		return (EIO);
-
-	error = xfs_attr_name_to_xname(&xname, name);
-	if (error)
-		return error;
-
-	xfs_ilock(dp, XFS_ILOCK_SHARED);
-	if (!xfs_inode_hasattr(dp)) {
-		xfs_iunlock(dp, XFS_ILOCK_SHARED);
-		return XFS_ERROR(ENOATTR);
 	}
-	xfs_iunlock(dp, XFS_ILOCK_SHARED);
-
-	return xfs_attr_remove_int(dp, &xname, flags);
+	xfs_iunlock(dp, XFS_ILOCK_EXCL);
+	return error;
 }
 
-
 /*========================================================================
  * External routines when attribute list is inside the inode
  *========================================================================*/
@@ -958,7 +863,7 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
 }
 
 /*========================================================================
- * External routines when attribute list size > XFS_LBSIZE(mp).
+ * External routines when attribute list size > geo->blksize
  *========================================================================*/
 
 /*
@@ -991,8 +896,6 @@ restart:
 	state = xfs_da_state_alloc();
 	state->args = args;
 	state->mp = mp;
-	state->blocksize = state->mp->m_sb.sb_blocksize;
-	state->node_ents = state->mp->m_attr_node_ents;
 
 	/*
 	 * Search to see if name already exists, and get back a pointer
@@ -1170,8 +1073,6 @@ restart:
 		state = xfs_da_state_alloc();
 		state->args = args;
 		state->mp = mp;
-		state->blocksize = state->mp->m_sb.sb_blocksize;
-		state->node_ents = state->mp->m_attr_node_ents;
 		state->inleaf = 0;
 		error = xfs_da3_node_lookup_int(state, &retval);
 		if (error)
@@ -1262,8 +1163,6 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	state = xfs_da_state_alloc();
 	state->args = args;
 	state->mp = dp->i_mount;
-	state->blocksize = state->mp->m_sb.sb_blocksize;
-	state->node_ents = state->mp->m_attr_node_ents;
 
 	/*
 	 * Search to see if name exists, and get back a pointer to it.
@@ -1525,8 +1424,6 @@ xfs_attr_node_get(xfs_da_args_t *args)
 	state = xfs_da_state_alloc();
 	state->args = args;
 	state->mp = args->dp->i_mount;
-	state->blocksize = state->mp->m_sb.sb_blocksize;
-	state->node_ents = state->mp->m_attr_node_ents;
 
 	/*
 	 * Search to see if name exists, and get back a pointer to it.
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 511c283459b..28712d29e43 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -80,11 +80,12 @@ STATIC int xfs_attr3_leaf_figure_balance(xfs_da_state_t *state,
 /*
  * Utility routines.
  */
-STATIC void xfs_attr3_leaf_moveents(struct xfs_attr_leafblock *src_leaf,
+STATIC void xfs_attr3_leaf_moveents(struct xfs_da_args *args,
+			struct xfs_attr_leafblock *src_leaf,
 			struct xfs_attr3_icleaf_hdr *src_ichdr, int src_start,
 			struct xfs_attr_leafblock *dst_leaf,
 			struct xfs_attr3_icleaf_hdr *dst_ichdr, int dst_start,
-			int move_count, struct xfs_mount *mp);
+			int move_count);
 STATIC int xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index);
 
 void
@@ -711,6 +712,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 
 	memset((char *)&nargs, 0, sizeof(nargs));
 	nargs.dp = dp;
+	nargs.geo = args->geo;
 	nargs.firstblock = args->firstblock;
 	nargs.flist = args->flist;
 	nargs.total = args->total;
@@ -805,18 +807,18 @@ xfs_attr3_leaf_to_shortform(
 
 	trace_xfs_attr_leaf_to_sf(args);
 
-	tmpbuffer = kmem_alloc(XFS_LBSIZE(dp->i_mount), KM_SLEEP);
+	tmpbuffer = kmem_alloc(args->geo->blksize, KM_SLEEP);
 	if (!tmpbuffer)
 		return ENOMEM;
 
-	memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(dp->i_mount));
+	memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
 
 	leaf = (xfs_attr_leafblock_t *)tmpbuffer;
 	xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
 	entry = xfs_attr3_leaf_entryp(leaf);
 
 	/* XXX (dgc): buffer is about to be marked stale - why zero it? */
-	memset(bp->b_addr, 0, XFS_LBSIZE(dp->i_mount));
+	memset(bp->b_addr, 0, args->geo->blksize);
 
 	/*
 	 * Clean out the prior contents of the attribute list.
@@ -838,6 +840,7 @@ xfs_attr3_leaf_to_shortform(
 	 * Copy the attributes
 	 */
 	memset((char *)&nargs, 0, sizeof(nargs));
+	nargs.geo = args->geo;
 	nargs.dp = dp;
 	nargs.firstblock = args->firstblock;
 	nargs.flist = args->flist;
@@ -904,12 +907,12 @@ xfs_attr3_leaf_to_node(
 	/* copy leaf to new buffer, update identifiers */
 	xfs_trans_buf_set_type(args->trans, bp2, XFS_BLFT_ATTR_LEAF_BUF);
 	bp2->b_ops = bp1->b_ops;
-	memcpy(bp2->b_addr, bp1->b_addr, XFS_LBSIZE(mp));
+	memcpy(bp2->b_addr, bp1->b_addr, args->geo->blksize);
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		struct xfs_da3_blkinfo *hdr3 = bp2->b_addr;
 		hdr3->blkno = cpu_to_be64(bp2->b_bn);
 	}
-	xfs_trans_log_buf(args->trans, bp2, 0, XFS_LBSIZE(mp) - 1);
+	xfs_trans_log_buf(args->trans, bp2, 0, args->geo->blksize - 1);
 
 	/*
 	 * Set up the new root node.
@@ -930,7 +933,7 @@ xfs_attr3_leaf_to_node(
 	btree[0].before = cpu_to_be32(blkno);
 	icnodehdr.count = 1;
 	dp->d_ops->node_hdr_to_disk(node, &icnodehdr);
-	xfs_trans_log_buf(args->trans, bp1, 0, XFS_LBSIZE(mp) - 1);
+	xfs_trans_log_buf(args->trans, bp1, 0, args->geo->blksize - 1);
 	error = 0;
 out:
 	return error;
@@ -966,10 +969,10 @@ xfs_attr3_leaf_create(
 	bp->b_ops = &xfs_attr3_leaf_buf_ops;
 	xfs_trans_buf_set_type(args->trans, bp, XFS_BLFT_ATTR_LEAF_BUF);
 	leaf = bp->b_addr;
-	memset(leaf, 0, XFS_LBSIZE(mp));
+	memset(leaf, 0, args->geo->blksize);
 
 	memset(&ichdr, 0, sizeof(ichdr));
-	ichdr.firstused = XFS_LBSIZE(mp);
+	ichdr.firstused = args->geo->blksize;
 
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		struct xfs_da3_blkinfo *hdr3 = bp->b_addr;
@@ -988,7 +991,7 @@ xfs_attr3_leaf_create(
 	ichdr.freemap[0].size = ichdr.firstused - ichdr.freemap[0].base;
 
 	xfs_attr3_leaf_hdr_to_disk(leaf, &ichdr);
-	xfs_trans_log_buf(args->trans, bp, 0, XFS_LBSIZE(mp) - 1);
+	xfs_trans_log_buf(args->trans, bp, 0, args->geo->blksize - 1);
 
 	*bpp = bp;
 	return 0;
@@ -1074,8 +1077,7 @@ xfs_attr3_leaf_add(
 	leaf = bp->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
 	ASSERT(args->index >= 0 && args->index <= ichdr.count);
-	entsize = xfs_attr_leaf_newentsize(args->namelen, args->valuelen,
-			   args->trans->t_mountp->m_sb.sb_blocksize, NULL);
+	entsize = xfs_attr_leaf_newentsize(args, NULL);
 
 	/*
 	 * Search through freemap for first-fit on new name length.
@@ -1174,17 +1176,14 @@ xfs_attr3_leaf_add_work(
 	 * Allocate space for the new string (at the end of the run).
 	 */
 	mp = args->trans->t_mountp;
-	ASSERT(ichdr->freemap[mapindex].base < XFS_LBSIZE(mp));
+	ASSERT(ichdr->freemap[mapindex].base < args->geo->blksize);
 	ASSERT((ichdr->freemap[mapindex].base & 0x3) == 0);
 	ASSERT(ichdr->freemap[mapindex].size >=
-		xfs_attr_leaf_newentsize(args->namelen, args->valuelen,
-					 mp->m_sb.sb_blocksize, NULL));
-	ASSERT(ichdr->freemap[mapindex].size < XFS_LBSIZE(mp));
+		xfs_attr_leaf_newentsize(args, NULL));
+	ASSERT(ichdr->freemap[mapindex].size < args->geo->blksize);
 	ASSERT((ichdr->freemap[mapindex].size & 0x3) == 0);
 
-	ichdr->freemap[mapindex].size -=
-			xfs_attr_leaf_newentsize(args->namelen, args->valuelen,
-						 mp->m_sb.sb_blocksize, &tmp);
+	ichdr->freemap[mapindex].size -= xfs_attr_leaf_newentsize(args, &tmp);
 
 	entry->nameidx = cpu_to_be16(ichdr->freemap[mapindex].base +
 				     ichdr->freemap[mapindex].size);
@@ -1269,14 +1268,13 @@ xfs_attr3_leaf_compact(
 	struct xfs_attr_leafblock *leaf_dst;
 	struct xfs_attr3_icleaf_hdr ichdr_src;
 	struct xfs_trans	*trans = args->trans;
-	struct xfs_mount	*mp = trans->t_mountp;
 	char			*tmpbuffer;
 
 	trace_xfs_attr_leaf_compact(args);
 
-	tmpbuffer = kmem_alloc(XFS_LBSIZE(mp), KM_SLEEP);
-	memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(mp));
-	memset(bp->b_addr, 0, XFS_LBSIZE(mp));
+	tmpbuffer = kmem_alloc(args->geo->blksize, KM_SLEEP);
+	memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
+	memset(bp->b_addr, 0, args->geo->blksize);
 	leaf_src = (xfs_attr_leafblock_t *)tmpbuffer;
 	leaf_dst = bp->b_addr;
 
@@ -1289,7 +1287,7 @@ xfs_attr3_leaf_compact(
 
 	/* Initialise the incore headers */
 	ichdr_src = *ichdr_dst;	/* struct copy */
-	ichdr_dst->firstused = XFS_LBSIZE(mp);
+	ichdr_dst->firstused = args->geo->blksize;
 	ichdr_dst->usedbytes = 0;
 	ichdr_dst->count = 0;
 	ichdr_dst->holes = 0;
@@ -1304,13 +1302,13 @@ xfs_attr3_leaf_compact(
 	 * Copy all entry's in the same (sorted) order,
 	 * but allocate name/value pairs packed and in sequence.
 	 */
-	xfs_attr3_leaf_moveents(leaf_src, &ichdr_src, 0, leaf_dst, ichdr_dst, 0,
-				ichdr_src.count, mp);
+	xfs_attr3_leaf_moveents(args, leaf_src, &ichdr_src, 0,
+				leaf_dst, ichdr_dst, 0, ichdr_src.count);
 	/*
 	 * this logs the entire buffer, but the caller must write the header
 	 * back to the buffer when it is finished modifying it.
 	 */
-	xfs_trans_log_buf(trans, bp, 0, XFS_LBSIZE(mp) - 1);
+	xfs_trans_log_buf(trans, bp, 0, args->geo->blksize - 1);
 
 	kmem_free(tmpbuffer);
 }
@@ -1461,8 +1459,8 @@ xfs_attr3_leaf_rebalance(
 		/*
 		 * Move high entries from leaf1 to low end of leaf2.
 		 */
-		xfs_attr3_leaf_moveents(leaf1, &ichdr1, ichdr1.count - count,
-				leaf2, &ichdr2, 0, count, state->mp);
+		xfs_attr3_leaf_moveents(args, leaf1, &ichdr1,
+				ichdr1.count - count, leaf2, &ichdr2, 0, count);
 
 	} else if (count > ichdr1.count) {
 		/*
@@ -1490,14 +1488,14 @@ xfs_attr3_leaf_rebalance(
 		/*
 		 * Move low entries from leaf2 to high end of leaf1.
 		 */
-		xfs_attr3_leaf_moveents(leaf2, &ichdr2, 0, leaf1, &ichdr1,
-					ichdr1.count, count, state->mp);
+		xfs_attr3_leaf_moveents(args, leaf2, &ichdr2, 0, leaf1, &ichdr1,
+					ichdr1.count, count);
 	}
 
 	xfs_attr3_leaf_hdr_to_disk(leaf1, &ichdr1);
 	xfs_attr3_leaf_hdr_to_disk(leaf2, &ichdr2);
-	xfs_trans_log_buf(args->trans, blk1->bp, 0, state->blocksize-1);
-	xfs_trans_log_buf(args->trans, blk2->bp, 0, state->blocksize-1);
+	xfs_trans_log_buf(args->trans, blk1->bp, 0, args->geo->blksize - 1);
+	xfs_trans_log_buf(args->trans, blk2->bp, 0, args->geo->blksize - 1);
 
 	/*
 	 * Copy out last hashval in each block for B-tree code.
@@ -1592,11 +1590,9 @@ xfs_attr3_leaf_figure_balance(
 	max = ichdr1->count + ichdr2->count;
 	half = (max + 1) * sizeof(*entry);
 	half += ichdr1->usedbytes + ichdr2->usedbytes +
-			xfs_attr_leaf_newentsize(state->args->namelen,
-						 state->args->valuelen,
-						 state->blocksize, NULL);
+			xfs_attr_leaf_newentsize(state->args, NULL);
 	half /= 2;
-	lastdelta = state->blocksize;
+	lastdelta = state->args->geo->blksize;
 	entry = xfs_attr3_leaf_entryp(leaf1);
 	for (count = index = 0; count < max; entry++, index++, count++) {
 
@@ -1606,10 +1602,7 @@ xfs_attr3_leaf_figure_balance(
 		 */
 		if (count == blk1->index) {
 			tmp = totallen + sizeof(*entry) +
-				xfs_attr_leaf_newentsize(
-						state->args->namelen,
-						state->args->valuelen,
-						state->blocksize, NULL);
+				xfs_attr_leaf_newentsize(state->args, NULL);
 			if (XFS_ATTR_ABS(half - tmp) > lastdelta)
 				break;
 			lastdelta = XFS_ATTR_ABS(half - tmp);
@@ -1645,10 +1638,7 @@ xfs_attr3_leaf_figure_balance(
 	totallen -= count * sizeof(*entry);
 	if (foundit) {
 		totallen -= sizeof(*entry) +
-				xfs_attr_leaf_newentsize(
-						state->args->namelen,
-						state->args->valuelen,
-						state->blocksize, NULL);
+				xfs_attr_leaf_newentsize(state->args, NULL);
 	}
 
 	*countarg = count;
@@ -1700,7 +1690,7 @@ xfs_attr3_leaf_toosmall(
 	bytes = xfs_attr3_leaf_hdr_size(leaf) +
 		ichdr.count * sizeof(xfs_attr_leaf_entry_t) +
 		ichdr.usedbytes;
-	if (bytes > (state->blocksize >> 1)) {
+	if (bytes > (state->args->geo->blksize >> 1)) {
 		*action = 0;	/* blk over 50%, don't try to join */
 		return(0);
 	}
@@ -1754,7 +1744,8 @@ xfs_attr3_leaf_toosmall(
 
 		xfs_attr3_leaf_hdr_from_disk(&ichdr2, bp->b_addr);
 
-		bytes = state->blocksize - (state->blocksize >> 2) -
+		bytes = state->args->geo->blksize -
+			(state->args->geo->blksize >> 2) -
 			ichdr.usedbytes - ichdr2.usedbytes -
 			((ichdr.count + ichdr2.count) *
 					sizeof(xfs_attr_leaf_entry_t)) -
@@ -1805,7 +1796,6 @@ xfs_attr3_leaf_remove(
 	struct xfs_attr_leafblock *leaf;
 	struct xfs_attr3_icleaf_hdr ichdr;
 	struct xfs_attr_leaf_entry *entry;
-	struct xfs_mount	*mp = args->trans->t_mountp;
 	int			before;
 	int			after;
 	int			smallest;
@@ -1819,7 +1809,7 @@ xfs_attr3_leaf_remove(
 	leaf = bp->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
 
-	ASSERT(ichdr.count > 0 && ichdr.count < XFS_LBSIZE(mp) / 8);
+	ASSERT(ichdr.count > 0 && ichdr.count < args->geo->blksize / 8);
 	ASSERT(args->index >= 0 && args->index < ichdr.count);
 	ASSERT(ichdr.firstused >= ichdr.count * sizeof(*entry) +
 					xfs_attr3_leaf_hdr_size(leaf));
@@ -1827,7 +1817,7 @@ xfs_attr3_leaf_remove(
 	entry = &xfs_attr3_leaf_entryp(leaf)[args->index];
 
 	ASSERT(be16_to_cpu(entry->nameidx) >= ichdr.firstused);
-	ASSERT(be16_to_cpu(entry->nameidx) < XFS_LBSIZE(mp));
+	ASSERT(be16_to_cpu(entry->nameidx) < args->geo->blksize);
 
 	/*
 	 * Scan through free region table:
@@ -1842,8 +1832,8 @@ xfs_attr3_leaf_remove(
 	smallest = XFS_ATTR_LEAF_MAPSIZE - 1;
 	entsize = xfs_attr_leaf_entsize(leaf, args->index);
 	for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
-		ASSERT(ichdr.freemap[i].base < XFS_LBSIZE(mp));
-		ASSERT(ichdr.freemap[i].size < XFS_LBSIZE(mp));
+		ASSERT(ichdr.freemap[i].base < args->geo->blksize);
+		ASSERT(ichdr.freemap[i].size < args->geo->blksize);
 		if (ichdr.freemap[i].base == tablesize) {
 			ichdr.freemap[i].base -= sizeof(xfs_attr_leaf_entry_t);
 			ichdr.freemap[i].size += sizeof(xfs_attr_leaf_entry_t);
@@ -1920,11 +1910,11 @@ xfs_attr3_leaf_remove(
 	 * removing the name.
 	 */
 	if (smallest) {
-		tmp = XFS_LBSIZE(mp);
+		tmp = args->geo->blksize;
 		entry = xfs_attr3_leaf_entryp(leaf);
 		for (i = ichdr.count - 1; i >= 0; entry++, i--) {
 			ASSERT(be16_to_cpu(entry->nameidx) >= ichdr.firstused);
-			ASSERT(be16_to_cpu(entry->nameidx) < XFS_LBSIZE(mp));
+			ASSERT(be16_to_cpu(entry->nameidx) < args->geo->blksize);
 
 			if (be16_to_cpu(entry->nameidx) < tmp)
 				tmp = be16_to_cpu(entry->nameidx);
@@ -1947,7 +1937,7 @@ xfs_attr3_leaf_remove(
 	tmp = ichdr.usedbytes + xfs_attr3_leaf_hdr_size(leaf) +
 	      ichdr.count * sizeof(xfs_attr_leaf_entry_t);
 
-	return tmp < mp->m_attr_magicpct; /* leaf is < 37% full */
+	return tmp < args->geo->magicpct; /* leaf is < 37% full */
 }
 
 /*
@@ -1964,7 +1954,6 @@ xfs_attr3_leaf_unbalance(
 	struct xfs_attr3_icleaf_hdr drophdr;
 	struct xfs_attr3_icleaf_hdr savehdr;
 	struct xfs_attr_leaf_entry *entry;
-	struct xfs_mount	*mp = state->mp;
 
 	trace_xfs_attr_leaf_unbalance(state->args);
 
@@ -1991,13 +1980,15 @@ xfs_attr3_leaf_unbalance(
 		 */
 		if (xfs_attr3_leaf_order(save_blk->bp, &savehdr,
 					 drop_blk->bp, &drophdr)) {
-			xfs_attr3_leaf_moveents(drop_leaf, &drophdr, 0,
+			xfs_attr3_leaf_moveents(state->args,
+						drop_leaf, &drophdr, 0,
 						save_leaf, &savehdr, 0,
-						drophdr.count, mp);
+						drophdr.count);
 		} else {
-			xfs_attr3_leaf_moveents(drop_leaf, &drophdr, 0,
+			xfs_attr3_leaf_moveents(state->args,
+						drop_leaf, &drophdr, 0,
 						save_leaf, &savehdr,
-						savehdr.count, drophdr.count, mp);
+						savehdr.count, drophdr.count);
 		}
 	} else {
 		/*
@@ -2007,7 +1998,7 @@ xfs_attr3_leaf_unbalance(
 		struct xfs_attr_leafblock *tmp_leaf;
 		struct xfs_attr3_icleaf_hdr tmphdr;
 
-		tmp_leaf = kmem_zalloc(state->blocksize, KM_SLEEP);
+		tmp_leaf = kmem_zalloc(state->args->geo->blksize, KM_SLEEP);
 
 		/*
 		 * Copy the header into the temp leaf so that all the stuff
@@ -2020,35 +2011,39 @@ xfs_attr3_leaf_unbalance(
 		tmphdr.magic = savehdr.magic;
 		tmphdr.forw = savehdr.forw;
 		tmphdr.back = savehdr.back;
-		tmphdr.firstused = state->blocksize;
+		tmphdr.firstused = state->args->geo->blksize;
 
 		/* write the header to the temp buffer to initialise it */
 		xfs_attr3_leaf_hdr_to_disk(tmp_leaf, &tmphdr);
 
 		if (xfs_attr3_leaf_order(save_blk->bp, &savehdr,
 					 drop_blk->bp, &drophdr)) {
-			xfs_attr3_leaf_moveents(drop_leaf, &drophdr, 0,
+			xfs_attr3_leaf_moveents(state->args,
+						drop_leaf, &drophdr, 0,
 						tmp_leaf, &tmphdr, 0,
-						drophdr.count, mp);
-			xfs_attr3_leaf_moveents(save_leaf, &savehdr, 0,
+						drophdr.count);
+			xfs_attr3_leaf_moveents(state->args,
+						save_leaf, &savehdr, 0,
 						tmp_leaf, &tmphdr, tmphdr.count,
-						savehdr.count, mp);
+						savehdr.count);
 		} else {
-			xfs_attr3_leaf_moveents(save_leaf, &savehdr, 0,
+			xfs_attr3_leaf_moveents(state->args,
+						save_leaf, &savehdr, 0,
 						tmp_leaf, &tmphdr, 0,
-						savehdr.count, mp);
-			xfs_attr3_leaf_moveents(drop_leaf, &drophdr, 0,
+						savehdr.count);
+			xfs_attr3_leaf_moveents(state->args,
+						drop_leaf, &drophdr, 0,
 						tmp_leaf, &tmphdr, tmphdr.count,
-						drophdr.count, mp);
+						drophdr.count);
 		}
-		memcpy(save_leaf, tmp_leaf, state->blocksize);
+		memcpy(save_leaf, tmp_leaf, state->args->geo->blksize);
 		savehdr = tmphdr; /* struct copy */
 		kmem_free(tmp_leaf);
 	}
 
 	xfs_attr3_leaf_hdr_to_disk(save_leaf, &savehdr);
 	xfs_trans_log_buf(state->args->trans, save_blk->bp, 0,
-					   state->blocksize - 1);
+					   state->args->geo->blksize - 1);
 
 	/*
 	 * Copy out last hashval in each block for B-tree code.
@@ -2094,7 +2089,7 @@ xfs_attr3_leaf_lookup_int(
 	leaf = bp->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
 	entries = xfs_attr3_leaf_entryp(leaf);
-	ASSERT(ichdr.count < XFS_LBSIZE(args->dp->i_mount) / 8);
+	ASSERT(ichdr.count < args->geo->blksize / 8);
 
 	/*
 	 * Binary search.  (note: small blocks will skip this loop)
@@ -2198,7 +2193,7 @@ xfs_attr3_leaf_getvalue(
 
 	leaf = bp->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);
-	ASSERT(ichdr.count < XFS_LBSIZE(args->dp->i_mount) / 8);
+	ASSERT(ichdr.count < args->geo->blksize / 8);
 	ASSERT(args->index < ichdr.count);
 
 	entry = &xfs_attr3_leaf_entryp(leaf)[args->index];
@@ -2249,14 +2244,14 @@ xfs_attr3_leaf_getvalue(
 /*ARGSUSED*/
 STATIC void
 xfs_attr3_leaf_moveents(
+	struct xfs_da_args		*args,
 	struct xfs_attr_leafblock	*leaf_s,
 	struct xfs_attr3_icleaf_hdr	*ichdr_s,
 	int				start_s,
 	struct xfs_attr_leafblock	*leaf_d,
 	struct xfs_attr3_icleaf_hdr	*ichdr_d,
 	int				start_d,
-	int				count,
-	struct xfs_mount		*mp)
+	int				count)
 {
 	struct xfs_attr_leaf_entry	*entry_s;
 	struct xfs_attr_leaf_entry	*entry_d;
@@ -2276,10 +2271,10 @@ xfs_attr3_leaf_moveents(
 	ASSERT(ichdr_s->magic == XFS_ATTR_LEAF_MAGIC ||
 	       ichdr_s->magic == XFS_ATTR3_LEAF_MAGIC);
 	ASSERT(ichdr_s->magic == ichdr_d->magic);
-	ASSERT(ichdr_s->count > 0 && ichdr_s->count < XFS_LBSIZE(mp) / 8);
+	ASSERT(ichdr_s->count > 0 && ichdr_s->count < args->geo->blksize / 8);
 	ASSERT(ichdr_s->firstused >= (ichdr_s->count * sizeof(*entry_s))
 					+ xfs_attr3_leaf_hdr_size(leaf_s));
-	ASSERT(ichdr_d->count < XFS_LBSIZE(mp) / 8);
+	ASSERT(ichdr_d->count < args->geo->blksize / 8);
 	ASSERT(ichdr_d->firstused >= (ichdr_d->count * sizeof(*entry_d))
 					+ xfs_attr3_leaf_hdr_size(leaf_d));
 
@@ -2331,11 +2326,11 @@ xfs_attr3_leaf_moveents(
 			entry_d->nameidx = cpu_to_be16(ichdr_d->firstused);
 			entry_d->flags = entry_s->flags;
 			ASSERT(be16_to_cpu(entry_d->nameidx) + tmp
-							<= XFS_LBSIZE(mp));
+							<= args->geo->blksize);
 			memmove(xfs_attr3_leaf_name(leaf_d, desti),
 				xfs_attr3_leaf_name(leaf_s, start_s + i), tmp);
 			ASSERT(be16_to_cpu(entry_s->nameidx) + tmp
-							<= XFS_LBSIZE(mp));
+							<= args->geo->blksize);
 			memset(xfs_attr3_leaf_name(leaf_s, start_s + i), 0, tmp);
 			ichdr_s->usedbytes -= tmp;
 			ichdr_d->usedbytes += tmp;
@@ -2356,7 +2351,7 @@ xfs_attr3_leaf_moveents(
 		tmp = count * sizeof(xfs_attr_leaf_entry_t);
 		entry_s = &xfs_attr3_leaf_entryp(leaf_s)[start_s];
 		ASSERT(((char *)entry_s + tmp) <=
-		       ((char *)leaf_s + XFS_LBSIZE(mp)));
+		       ((char *)leaf_s + args->geo->blksize));
 		memset(entry_s, 0, tmp);
 	} else {
 		/*
@@ -2371,7 +2366,7 @@ xfs_attr3_leaf_moveents(
 		tmp = count * sizeof(xfs_attr_leaf_entry_t);
 		entry_s = &xfs_attr3_leaf_entryp(leaf_s)[ichdr_s->count];
 		ASSERT(((char *)entry_s + tmp) <=
-		       ((char *)leaf_s + XFS_LBSIZE(mp)));
+		       ((char *)leaf_s + args->geo->blksize));
 		memset(entry_s, 0, tmp);
 	}
 
@@ -2439,22 +2434,21 @@ xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index)
  * a "local" or a "remote" attribute.
  */
 int
-xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize, int *local)
+xfs_attr_leaf_newentsize(
+	struct xfs_da_args	*args,
+	int			*local)
 {
-	int size;
+	int			size;
 
-	size = xfs_attr_leaf_entsize_local(namelen, valuelen);
-	if (size < xfs_attr_leaf_entsize_local_max(blocksize)) {
-		if (local) {
+	size = xfs_attr_leaf_entsize_local(args->namelen, args->valuelen);
+	if (size < xfs_attr_leaf_entsize_local_max(args->geo->blksize)) {
+		if (local)
 			*local = 1;
-		}
-	} else {
-		size = xfs_attr_leaf_entsize_remote(namelen);
-		if (local) {
-			*local = 0;
-		}
+		return size;
 	}
-	return size;
+	if (local)
+		*local = 0;
+	return xfs_attr_leaf_entsize_remote(args->namelen);
 }
 
 
diff --git a/fs/xfs/xfs_attr_leaf.h b/fs/xfs/xfs_attr_leaf.h
index 3ec5ec0b867..e2929da7c3b 100644
--- a/fs/xfs/xfs_attr_leaf.h
+++ b/fs/xfs/xfs_attr_leaf.h
@@ -96,8 +96,7 @@ int	xfs_attr3_root_inactive(struct xfs_trans **trans, struct xfs_inode *dp);
 xfs_dahash_t	xfs_attr_leaf_lasthash(struct xfs_buf *bp, int *count);
 int	xfs_attr_leaf_order(struct xfs_buf *leaf1_bp,
 				   struct xfs_buf *leaf2_bp);
-int	xfs_attr_leaf_newentsize(int namelen, int valuelen, int blocksize,
-					int *local);
+int	xfs_attr_leaf_newentsize(struct xfs_da_args *args, int *local);
 int	xfs_attr3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
 			xfs_dablk_t bno, xfs_daddr_t mappedbno,
 			struct xfs_buf **bpp);
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 833fe5d98d8..90e2eeb2120 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -444,6 +444,7 @@ xfs_attr3_leaf_list_int(
 				xfs_da_args_t args;
 
 				memset((char *)&args, 0, sizeof(args));
+				args.geo = context->dp->i_mount->m_attr_geo;
 				args.dp = context->dp;
 				args.whichfork = XFS_ATTR_FORK;
 				args.valuelen = valuelen;
diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c
index d2e6e948cec..b5adfecbb8e 100644
--- a/fs/xfs/xfs_attr_remote.c
+++ b/fs/xfs/xfs_attr_remote.c
@@ -68,7 +68,6 @@ xfs_attr3_rmt_blocks(
  */
 static bool
 xfs_attr3_rmt_hdr_ok(
-	struct xfs_mount	*mp,
 	void			*ptr,
 	xfs_ino_t		ino,
 	uint32_t		offset,
@@ -126,6 +125,7 @@ xfs_attr3_rmt_read_verify(
 	char		*ptr;
 	int		len;
 	xfs_daddr_t	bno;
+	int		blksize = mp->m_attr_geo->blksize;
 
 	/* no verification of non-crc buffers */
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -134,21 +134,20 @@ xfs_attr3_rmt_read_verify(
 	ptr = bp->b_addr;
 	bno = bp->b_bn;
 	len = BBTOB(bp->b_length);
-	ASSERT(len >= XFS_LBSIZE(mp));
+	ASSERT(len >= blksize);
 
 	while (len > 0) {
-		if (!xfs_verify_cksum(ptr, XFS_LBSIZE(mp),
-				      XFS_ATTR3_RMT_CRC_OFF)) {
+		if (!xfs_verify_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF)) {
 			xfs_buf_ioerror(bp, EFSBADCRC);
 			break;
 		}
-		if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
+		if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
 			xfs_buf_ioerror(bp, EFSCORRUPTED);
 			break;
 		}
-		len -= XFS_LBSIZE(mp);
-		ptr += XFS_LBSIZE(mp);
-		bno += mp->m_bsize;
+		len -= blksize;
+		ptr += blksize;
+		bno += BTOBB(blksize);
 	}
 
 	if (bp->b_error)
@@ -166,6 +165,7 @@ xfs_attr3_rmt_write_verify(
 	char		*ptr;
 	int		len;
 	xfs_daddr_t	bno;
+	int		blksize = mp->m_attr_geo->blksize;
 
 	/* no verification of non-crc buffers */
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -174,10 +174,10 @@ xfs_attr3_rmt_write_verify(
 	ptr = bp->b_addr;
 	bno = bp->b_bn;
 	len = BBTOB(bp->b_length);
-	ASSERT(len >= XFS_LBSIZE(mp));
+	ASSERT(len >= blksize);
 
 	while (len > 0) {
-		if (!xfs_attr3_rmt_verify(mp, ptr, XFS_LBSIZE(mp), bno)) {
+		if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
 			xfs_buf_ioerror(bp, EFSCORRUPTED);
 			xfs_verifier_error(bp);
 			return;
@@ -188,11 +188,11 @@ xfs_attr3_rmt_write_verify(
 			rmt = (struct xfs_attr3_rmt_hdr *)ptr;
 			rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
 		}
-		xfs_update_cksum(ptr, XFS_LBSIZE(mp), XFS_ATTR3_RMT_CRC_OFF);
+		xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
 
-		len -= XFS_LBSIZE(mp);
-		ptr += XFS_LBSIZE(mp);
-		bno += mp->m_bsize;
+		len -= blksize;
+		ptr += blksize;
+		bno += BTOBB(blksize);
 	}
 	ASSERT(len == 0);
 }
@@ -241,17 +241,18 @@ xfs_attr_rmtval_copyout(
 	char		*src = bp->b_addr;
 	xfs_daddr_t	bno = bp->b_bn;
 	int		len = BBTOB(bp->b_length);
+	int		blksize = mp->m_attr_geo->blksize;
 
-	ASSERT(len >= XFS_LBSIZE(mp));
+	ASSERT(len >= blksize);
 
 	while (len > 0 && *valuelen > 0) {
 		int hdr_size = 0;
-		int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, XFS_LBSIZE(mp));
+		int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
 
 		byte_cnt = min(*valuelen, byte_cnt);
 
 		if (xfs_sb_version_hascrc(&mp->m_sb)) {
-			if (!xfs_attr3_rmt_hdr_ok(mp, src, ino, *offset,
+			if (!xfs_attr3_rmt_hdr_ok(src, ino, *offset,
 						  byte_cnt, bno)) {
 				xfs_alert(mp,
 "remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
@@ -264,9 +265,9 @@ xfs_attr_rmtval_copyout(
 		memcpy(*dst, src + hdr_size, byte_cnt);
 
 		/* roll buffer forwards */
-		len -= XFS_LBSIZE(mp);
-		src += XFS_LBSIZE(mp);
-		bno += mp->m_bsize;
+		len -= blksize;
+		src += blksize;
+		bno += BTOBB(blksize);
 
 		/* roll attribute data forwards */
 		*valuelen -= byte_cnt;
@@ -288,12 +289,13 @@ xfs_attr_rmtval_copyin(
 	char		*dst = bp->b_addr;
 	xfs_daddr_t	bno = bp->b_bn;
 	int		len = BBTOB(bp->b_length);
+	int		blksize = mp->m_attr_geo->blksize;
 
-	ASSERT(len >= XFS_LBSIZE(mp));
+	ASSERT(len >= blksize);
 
 	while (len > 0 && *valuelen > 0) {
 		int hdr_size;
-		int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, XFS_LBSIZE(mp));
+		int byte_cnt = XFS_ATTR3_RMT_BUF_SPACE(mp, blksize);
 
 		byte_cnt = min(*valuelen, byte_cnt);
 		hdr_size = xfs_attr3_rmt_hdr_set(mp, dst, ino, *offset,
@@ -305,17 +307,17 @@ xfs_attr_rmtval_copyin(
 		 * If this is the last block, zero the remainder of it.
 		 * Check that we are actually the last block, too.
 		 */
-		if (byte_cnt + hdr_size < XFS_LBSIZE(mp)) {
+		if (byte_cnt + hdr_size < blksize) {
 			ASSERT(*valuelen - byte_cnt == 0);
-			ASSERT(len == XFS_LBSIZE(mp));
+			ASSERT(len == blksize);
 			memset(dst + hdr_size + byte_cnt, 0,
-					XFS_LBSIZE(mp) - hdr_size - byte_cnt);
+					blksize - hdr_size - byte_cnt);
 		}
 
 		/* roll buffer forwards */
-		len -= XFS_LBSIZE(mp);
-		dst += XFS_LBSIZE(mp);
-		bno += mp->m_bsize;
+		len -= blksize;
+		dst += blksize;
+		bno += BTOBB(blksize);
 
 		/* roll attribute data forwards */
 		*valuelen -= byte_cnt;
diff --git a/fs/xfs/xfs_bit.h b/fs/xfs/xfs_bit.h
index f1e3c907044..e1649c0d3e0 100644
--- a/fs/xfs/xfs_bit.h
+++ b/fs/xfs/xfs_bit.h
@@ -66,8 +66,11 @@ static inline int xfs_lowbit64(__uint64_t v)
 		n = ffs(w);
 	} else {	/* upper bits */
 		w = (__uint32_t)(v >> 32);
-		if (w && (n = ffs(w)))
-		n += 32;
+		if (w) {
+			n = ffs(w);
+			if (n)
+				n += 32;
+		}
 	}
 	return n - 1;
 }
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index f0efc7e970e..75c3fe5f3d9 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -94,7 +94,7 @@ xfs_bmap_compute_maxlevels(
 		maxleafents = MAXAEXTNUM;
 		sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
 	}
-	maxrootrecs = xfs_bmdr_maxrecs(mp, sz, 0);
+	maxrootrecs = xfs_bmdr_maxrecs(sz, 0);
 	minleafrecs = mp->m_bmap_dmnr[0];
 	minnoderecs = mp->m_bmap_dmnr[1];
 	maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
@@ -233,7 +233,6 @@ xfs_default_attroffset(
  */
 STATIC void
 xfs_bmap_forkoff_reset(
-	xfs_mount_t	*mp,
 	xfs_inode_t	*ip,
 	int		whichfork)
 {
@@ -905,7 +904,7 @@ xfs_bmap_local_to_extents_empty(
 	ASSERT(ifp->if_bytes == 0);
 	ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) == 0);
 
-	xfs_bmap_forkoff_reset(ip->i_mount, ip, whichfork);
+	xfs_bmap_forkoff_reset(ip, whichfork);
 	ifp->if_flags &= ~XFS_IFINLINE;
 	ifp->if_flags |= XFS_IFEXTENTS;
 	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
@@ -1099,10 +1098,11 @@ xfs_bmap_add_attrfork_local(
 
 	if (S_ISDIR(ip->i_d.di_mode)) {
 		memset(&dargs, 0, sizeof(dargs));
+		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
 		dargs.firstblock = firstblock;
 		dargs.flist = flist;
-		dargs.total = ip->i_mount->m_dirblkfsbs;
+		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
 		return xfs_dir2_sf_to_block(&dargs);
@@ -1675,7 +1675,6 @@ xfs_bmap_isaeof(
  */
 int
 xfs_bmap_last_offset(
-	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		*last_block,
 	int			whichfork)
@@ -3517,6 +3516,67 @@ xfs_bmap_adjacent(
 #undef ISVALID
 }
 
+static int
+xfs_bmap_longest_free_extent(
+	struct xfs_trans	*tp,
+	xfs_agnumber_t		ag,
+	xfs_extlen_t		*blen,
+	int			*notinit)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_perag	*pag;
+	xfs_extlen_t		longest;
+	int			error = 0;
+
+	pag = xfs_perag_get(mp, ag);
+	if (!pag->pagf_init) {
+		error = xfs_alloc_pagf_init(mp, tp, ag, XFS_ALLOC_FLAG_TRYLOCK);
+		if (error)
+			goto out;
+
+		if (!pag->pagf_init) {
+			*notinit = 1;
+			goto out;
+		}
+	}
+
+	longest = xfs_alloc_longest_free_extent(mp, pag);
+	if (*blen < longest)
+		*blen = longest;
+
+out:
+	xfs_perag_put(pag);
+	return error;
+}
+
+static void
+xfs_bmap_select_minlen(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	xfs_extlen_t		*blen,
+	int			notinit)
+{
+	if (notinit || *blen < ap->minlen) {
+		/*
+		 * Since we did a BUF_TRYLOCK above, it is possible that
+		 * there is space for this request.
+		 */
+		args->minlen = ap->minlen;
+	} else if (*blen < args->maxlen) {
+		/*
+		 * If the best seen length is less than the request length,
+		 * use the best as the minimum.
+		 */
+		args->minlen = *blen;
+	} else {
+		/*
+		 * Otherwise we've seen an extent as big as maxlen, use that
+		 * as the minimum.
+		 */
+		args->minlen = args->maxlen;
+	}
+}
+
 STATIC int
 xfs_bmap_btalloc_nullfb(
 	struct xfs_bmalloca	*ap,
@@ -3524,111 +3584,74 @@ xfs_bmap_btalloc_nullfb(
 	xfs_extlen_t		*blen)
 {
 	struct xfs_mount	*mp = ap->ip->i_mount;
-	struct xfs_perag	*pag;
 	xfs_agnumber_t		ag, startag;
 	int			notinit = 0;
 	int			error;
 
-	if (ap->userdata && xfs_inode_is_filestream(ap->ip))
-		args->type = XFS_ALLOCTYPE_NEAR_BNO;
-	else
-		args->type = XFS_ALLOCTYPE_START_BNO;
+	args->type = XFS_ALLOCTYPE_START_BNO;
 	args->total = ap->total;
 
-	/*
-	 * Search for an allocation group with a single extent large enough
-	 * for the request.  If one isn't found, then adjust the minimum
-	 * allocation size to the largest space found.
-	 */
 	startag = ag = XFS_FSB_TO_AGNO(mp, args->fsbno);
 	if (startag == NULLAGNUMBER)
 		startag = ag = 0;
 
-	pag = xfs_perag_get(mp, ag);
 	while (*blen < args->maxlen) {
-		if (!pag->pagf_init) {
-			error = xfs_alloc_pagf_init(mp, args->tp, ag,
-						    XFS_ALLOC_FLAG_TRYLOCK);
-			if (error) {
-				xfs_perag_put(pag);
-				return error;
-			}
-		}
-
-		/*
-		 * See xfs_alloc_fix_freelist...
-		 */
-		if (pag->pagf_init) {
-			xfs_extlen_t	longest;
-			longest = xfs_alloc_longest_free_extent(mp, pag);
-			if (*blen < longest)
-				*blen = longest;
-		} else
-			notinit = 1;
-
-		if (xfs_inode_is_filestream(ap->ip)) {
-			if (*blen >= args->maxlen)
-				break;
-
-			if (ap->userdata) {
-				/*
-				 * If startag is an invalid AG, we've
-				 * come here once before and
-				 * xfs_filestream_new_ag picked the
-				 * best currently available.
-				 *
-				 * Don't continue looping, since we
-				 * could loop forever.
-				 */
-				if (startag == NULLAGNUMBER)
-					break;
-
-				error = xfs_filestream_new_ag(ap, &ag);
-				xfs_perag_put(pag);
-				if (error)
-					return error;
+		error = xfs_bmap_longest_free_extent(args->tp, ag, blen,
+						     &notinit);
+		if (error)
+			return error;
 
-				/* loop again to set 'blen'*/
-				startag = NULLAGNUMBER;
-				pag = xfs_perag_get(mp, ag);
-				continue;
-			}
-		}
 		if (++ag == mp->m_sb.sb_agcount)
 			ag = 0;
 		if (ag == startag)
 			break;
-		xfs_perag_put(pag);
-		pag = xfs_perag_get(mp, ag);
 	}
-	xfs_perag_put(pag);
 
-	/*
-	 * Since the above loop did a BUF_TRYLOCK, it is
-	 * possible that there is space for this request.
-	 */
-	if (notinit || *blen < ap->minlen)
-		args->minlen = ap->minlen;
-	/*
-	 * If the best seen length is less than the request
-	 * length, use the best as the minimum.
-	 */
-	else if (*blen < args->maxlen)
-		args->minlen = *blen;
-	/*
-	 * Otherwise we've seen an extent as big as maxlen,
-	 * use that as the minimum.
-	 */
-	else
-		args->minlen = args->maxlen;
+	xfs_bmap_select_minlen(ap, args, blen, notinit);
+	return 0;
+}
+
+STATIC int
+xfs_bmap_btalloc_filestreams(
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args,
+	xfs_extlen_t		*blen)
+{
+	struct xfs_mount	*mp = ap->ip->i_mount;
+	xfs_agnumber_t		ag;
+	int			notinit = 0;
+	int			error;
+
+	args->type = XFS_ALLOCTYPE_NEAR_BNO;
+	args->total = ap->total;
+
+	ag = XFS_FSB_TO_AGNO(mp, args->fsbno);
+	if (ag == NULLAGNUMBER)
+		ag = 0;
+
+	error = xfs_bmap_longest_free_extent(args->tp, ag, blen, &notinit);
+	if (error)
+		return error;
+
+	if (*blen < args->maxlen) {
+		error = xfs_filestream_new_ag(ap, &ag);
+		if (error)
+			return error;
+
+		error = xfs_bmap_longest_free_extent(args->tp, ag, blen,
+						     &notinit);
+		if (error)
+			return error;
+
+	}
+
+	xfs_bmap_select_minlen(ap, args, blen, notinit);
 
 	/*
-	 * set the failure fallback case to look in the selected
-	 * AG as the stream may have moved.
+	 * Set the failure fallback case to look in the selected AG as stream
+	 * may have moved.
 	 */
-	if (xfs_inode_is_filestream(ap->ip))
-		ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0);
-
+	ap->blkno = args->fsbno = XFS_AGB_TO_FSB(mp, ag, 0);
 	return 0;
 }
 
@@ -3708,7 +3731,15 @@ xfs_bmap_btalloc(
 	args.firstblock = *ap->firstblock;
 	blen = 0;
 	if (nullfb) {
-		error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
+		/*
+		 * Search for an allocation group with a single extent large
+		 * enough for the request.  If one isn't found, then adjust
+		 * the minimum allocation size to the largest space found.
+		 */
+		if (ap->userdata && xfs_inode_is_filestream(ap->ip))
+			error = xfs_bmap_btalloc_filestreams(ap, &args, &blen);
+		else
+			error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
 		if (error)
 			return error;
 	} else if (ap->flist->xbf_low) {
@@ -4267,8 +4298,8 @@ xfs_bmapi_delay(
 }
 
 
-int
-__xfs_bmapi_allocate(
+static int
+xfs_bmapi_allocate(
 	struct xfs_bmalloca	*bma)
 {
 	struct xfs_mount	*mp = bma->ip->i_mount;
@@ -4547,9 +4578,6 @@ xfs_bmapi_write(
 	bma.flist = flist;
 	bma.firstblock = firstblock;
 
-	if (flags & XFS_BMAPI_STACK_SWITCH)
-		bma.stack_switch = 1;
-
 	while (bno < end && n < *nmap) {
 		inhole = eof || bma.got.br_startoff > bno;
 		wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index f84bd7af43b..b879ca56a64 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -77,7 +77,6 @@ typedef	struct xfs_bmap_free
  * from written to unwritten, otherwise convert from unwritten to written.
  */
 #define XFS_BMAPI_CONVERT	0x040
-#define XFS_BMAPI_STACK_SWITCH	0x080
 
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
@@ -86,8 +85,7 @@ typedef	struct xfs_bmap_free
 	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \
 	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \
 	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \
-	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
-	{ XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" }
+	{ XFS_BMAPI_CONVERT,	"CONVERT" }
 
 
 static inline int xfs_bmapi_aflag(int w)
@@ -156,8 +154,8 @@ int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
 int	xfs_bmap_last_before(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *last_block, int whichfork);
-int	xfs_bmap_last_offset(struct xfs_trans *tp, struct xfs_inode *ip,
-		xfs_fileoff_t *unused, int whichfork);
+int	xfs_bmap_last_offset(struct xfs_inode *ip, xfs_fileoff_t *unused,
+		int whichfork);
 int	xfs_bmap_one_block(struct xfs_inode *ip, int whichfork);
 int	xfs_bmap_read_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		int whichfork);
diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c
index 818d546664e..948836c4fd9 100644
--- a/fs/xfs/xfs_bmap_btree.c
+++ b/fs/xfs/xfs_bmap_btree.c
@@ -84,7 +84,7 @@ xfs_bmdr_to_bmbt(
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
 	rblock->bb_numrecs = dblock->bb_numrecs;
-	dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
+	dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
 	fkp = XFS_BMDR_KEY_ADDR(dblock, 1);
 	tkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
 	fpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
@@ -443,7 +443,7 @@ xfs_bmbt_to_bmdr(
 	ASSERT(rblock->bb_level != 0);
 	dblock->bb_level = rblock->bb_level;
 	dblock->bb_numrecs = rblock->bb_numrecs;
-	dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
+	dmxr = xfs_bmdr_maxrecs(dblocklen, 0);
 	fkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
 	tkp = XFS_BMDR_KEY_ADDR(dblock, 1);
 	fpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
@@ -519,7 +519,6 @@ xfs_bmbt_alloc_block(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*start,
 	union xfs_btree_ptr	*new,
-	int			length,
 	int			*stat)
 {
 	xfs_alloc_arg_t		args;		/* block allocation args */
@@ -672,8 +671,7 @@ xfs_bmbt_get_dmaxrecs(
 {
 	if (level != cur->bc_nlevels - 1)
 		return cur->bc_mp->m_bmap_dmxr[level != 0];
-	return xfs_bmdr_maxrecs(cur->bc_mp, cur->bc_private.b.forksize,
-				level == 0);
+	return xfs_bmdr_maxrecs(cur->bc_private.b.forksize, level == 0);
 }
 
 STATIC void
@@ -914,7 +912,6 @@ xfs_bmbt_maxrecs(
  */
 int
 xfs_bmdr_maxrecs(
-	struct xfs_mount	*mp,
 	int			blocklen,
 	int			leaf)
 {
diff --git a/fs/xfs/xfs_bmap_btree.h b/fs/xfs/xfs_bmap_btree.h
index 6e42e1e50b8..819a8a4dee9 100644
--- a/fs/xfs/xfs_bmap_btree.h
+++ b/fs/xfs/xfs_bmap_btree.h
@@ -130,7 +130,7 @@ extern void xfs_bmbt_to_bmdr(struct xfs_mount *, struct xfs_btree_block *, int,
 			xfs_bmdr_block_t *, int);
 
 extern int xfs_bmbt_get_maxrecs(struct xfs_btree_cur *, int level);
-extern int xfs_bmdr_maxrecs(struct xfs_mount *, int blocklen, int leaf);
+extern int xfs_bmdr_maxrecs(int blocklen, int leaf);
 extern int xfs_bmbt_maxrecs(struct xfs_mount *, int blocklen, int leaf);
 
 extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 296160b8e78..64731ef3324 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -249,49 +249,6 @@ xfs_bmap_rtalloc(
 }
 
 /*
- * Stack switching interfaces for allocation
- */
-static void
-xfs_bmapi_allocate_worker(
-	struct work_struct	*work)
-{
-	struct xfs_bmalloca	*args = container_of(work,
-						struct xfs_bmalloca, work);
-	unsigned long		pflags;
-
-	/* we are in a transaction context here */
-	current_set_flags_nested(&pflags, PF_FSTRANS);
-
-	args->result = __xfs_bmapi_allocate(args);
-	complete(args->done);
-
-	current_restore_flags_nested(&pflags, PF_FSTRANS);
-}
-
-/*
- * Some allocation requests often come in with little stack to work on. Push
- * them off to a worker thread so there is lots of stack to use. Otherwise just
- * call directly to avoid the context switch overhead here.
- */
-int
-xfs_bmapi_allocate(
-	struct xfs_bmalloca	*args)
-{
-	DECLARE_COMPLETION_ONSTACK(done);
-
-	if (!args->stack_switch)
-		return __xfs_bmapi_allocate(args);
-
-
-	args->done = &done;
-	INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
-	queue_work(xfs_alloc_wq, &args->work);
-	wait_for_completion(&done);
-	destroy_work_on_stack(&args->work);
-	return args->result;
-}
-
-/*
  * Check if the endoff is outside the last extent. If so the caller will grow
  * the allocation to a stripe unit boundary.  All offsets are considered outside
  * the end of file for an empty fork, so 1 is returned in *eof in that case.
@@ -1519,7 +1476,6 @@ xfs_collapse_file_space(
 
 	while (!error && !done) {
 		tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
-		tp->t_flags |= XFS_TRANS_RESERVE;
 		/*
 		 * We would need to reserve permanent block for transaction.
 		 * This will come into picture when after shifting extent into
@@ -1529,7 +1485,6 @@ xfs_collapse_file_space(
 		error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
 				XFS_DIOSTRAT_SPACE_RES(mp, 0), 0);
 		if (error) {
-			ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
 			xfs_trans_cancel(tp, 0);
 			break;
 		}
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 935ed2b24ed..2fdb72d2c90 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -50,12 +50,11 @@ struct xfs_bmalloca {
 	xfs_extlen_t		total;	/* total blocks needed for xaction */
 	xfs_extlen_t		minlen;	/* minimum allocation size (blocks) */
 	xfs_extlen_t		minleft; /* amount must be left after alloc */
-	char			eof;	/* set if allocating past last extent */
-	char			wasdel;	/* replacing a delayed allocation */
-	char			userdata;/* set if is user data */
-	char			aeof;	/* allocated space at eof */
-	char			conv;	/* overwriting unwritten extents */
-	char			stack_switch;
+	bool			eof;	/* set if allocating past last extent */
+	bool			wasdel;	/* replacing a delayed allocation */
+	bool			userdata;/* set if is user data */
+	bool			aeof;	/* allocated space at eof */
+	bool			conv;	/* overwriting unwritten extents */
 	int			flags;
 	struct completion	*done;
 	struct work_struct	work;
@@ -65,8 +64,6 @@ struct xfs_bmalloca {
 int	xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist,
 			int *committed);
 int	xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
-int	xfs_bmapi_allocate(struct xfs_bmalloca *args);
-int	__xfs_bmapi_allocate(struct xfs_bmalloca *args);
 int	xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
 		     int whichfork, int *eof);
 int	xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index e80d59fdf89..cf893bc1e37 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -33,6 +33,7 @@
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_cksum.h"
+#include "xfs_alloc.h"
 
 /*
  * Cursor allocation zone.
@@ -43,9 +44,10 @@ kmem_zone_t	*xfs_btree_cur_zone;
  * Btree magic numbers.
  */
 static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
-	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC },
+	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
+	  XFS_FIBT_MAGIC },
 	{ XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC,
-	  XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC }
+	  XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC }
 };
 #define xfs_btree_magic(cur) \
 	xfs_magics[!!((cur)->bc_flags & XFS_BTREE_CRC_BLOCKS)][cur->bc_btnum]
@@ -552,14 +554,11 @@ xfs_btree_get_bufl(
 	xfs_fsblock_t	fsbno,		/* file system block number */
 	uint		lock)		/* lock flags for get_buf */
 {
-	xfs_buf_t	*bp;		/* buffer pointer (return value) */
 	xfs_daddr_t		d;		/* real disk block address */
 
 	ASSERT(fsbno != NULLFSBLOCK);
 	d = XFS_FSB_TO_DADDR(mp, fsbno);
-	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
-	ASSERT(!xfs_buf_geterror(bp));
-	return bp;
+	return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
 }
 
 /*
@@ -574,15 +573,12 @@ xfs_btree_get_bufs(
 	xfs_agblock_t	agbno,		/* allocation group block number */
 	uint		lock)		/* lock flags for get_buf */
 {
-	xfs_buf_t	*bp;		/* buffer pointer (return value) */
 	xfs_daddr_t		d;		/* real disk block address */
 
 	ASSERT(agno != NULLAGNUMBER);
 	ASSERT(agbno != NULLAGBLOCK);
 	d = XFS_AGB_TO_DADDR(mp, agno, agbno);
-	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
-	ASSERT(!xfs_buf_geterror(bp));
-	return bp;
+	return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock);
 }
 
 /*
@@ -722,7 +718,6 @@ xfs_btree_read_bufl(
 				   mp->m_bsize, lock, &bp, ops);
 	if (error)
 		return error;
-	ASSERT(!xfs_buf_geterror(bp));
 	if (bp)
 		xfs_buf_set_ref(bp, refval);
 	*bpp = bp;
@@ -1115,6 +1110,7 @@ xfs_btree_set_refs(
 		xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF);
 		break;
 	case XFS_BTNUM_INO:
+	case XFS_BTNUM_FINO:
 		xfs_buf_set_ref(bp, XFS_INO_BTREE_REF);
 		break;
 	case XFS_BTNUM_BMAP:
@@ -1159,7 +1155,6 @@ STATIC int
 xfs_btree_read_buf_block(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*ptr,
-	int			level,
 	int			flags,
 	struct xfs_btree_block	**block,
 	struct xfs_buf		**bpp)
@@ -1178,7 +1173,6 @@ xfs_btree_read_buf_block(
 	if (error)
 		return error;
 
-	ASSERT(!xfs_buf_geterror(*bpp));
 	xfs_btree_set_refs(cur, *bpp);
 	*block = XFS_BUF_TO_BLOCK(*bpp);
 	return 0;
@@ -1517,8 +1511,8 @@ xfs_btree_increment(
 		union xfs_btree_ptr	*ptrp;
 
 		ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
-		error = xfs_btree_read_buf_block(cur, ptrp, --lev,
-							0, &block, &bp);
+		--lev;
+		error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
 		if (error)
 			goto error0;
 
@@ -1616,8 +1610,8 @@ xfs_btree_decrement(
 		union xfs_btree_ptr	*ptrp;
 
 		ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
-		error = xfs_btree_read_buf_block(cur, ptrp, --lev,
-							0, &block, &bp);
+		--lev;
+		error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
 		if (error)
 			goto error0;
 		xfs_btree_setbuf(cur, lev, bp);
@@ -1667,7 +1661,7 @@ xfs_btree_lookup_get_block(
 		return 0;
 	}
 
-	error = xfs_btree_read_buf_block(cur, pp, level, 0, blkp, &bp);
+	error = xfs_btree_read_buf_block(cur, pp, 0, blkp, &bp);
 	if (error)
 		return error;
 
@@ -2018,7 +2012,7 @@ xfs_btree_lshift(
 		goto out0;
 
 	/* Set up the left neighbor as "left". */
-	error = xfs_btree_read_buf_block(cur, &lptr, level, 0, &left, &lbp);
+	error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
 	if (error)
 		goto error0;
 
@@ -2202,7 +2196,7 @@ xfs_btree_rshift(
 		goto out0;
 
 	/* Set up the right neighbor as "right". */
-	error = xfs_btree_read_buf_block(cur, &rptr, level, 0, &right, &rbp);
+	error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
 	if (error)
 		goto error0;
 
@@ -2330,7 +2324,7 @@ error1:
  * record (to be inserted into parent).
  */
 STATIC int					/* error */
-xfs_btree_split(
+__xfs_btree_split(
 	struct xfs_btree_cur	*cur,
 	int			level,
 	union xfs_btree_ptr	*ptrp,
@@ -2372,7 +2366,7 @@ xfs_btree_split(
 	xfs_btree_buf_to_ptr(cur, lbp, &lptr);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, 1, stat);
+	error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
@@ -2470,7 +2464,7 @@ xfs_btree_split(
 	 * point back to right instead of to left.
 	 */
 	if (!xfs_btree_ptr_is_null(cur, &rrptr)) {
-		error = xfs_btree_read_buf_block(cur, &rrptr, level,
+		error = xfs_btree_read_buf_block(cur, &rrptr,
 							0, &rrblock, &rrbp);
 		if (error)
 			goto error0;
@@ -2510,6 +2504,85 @@ error0:
 	return error;
 }
 
+struct xfs_btree_split_args {
+	struct xfs_btree_cur	*cur;
+	int			level;
+	union xfs_btree_ptr	*ptrp;
+	union xfs_btree_key	*key;
+	struct xfs_btree_cur	**curp;
+	int			*stat;		/* success/failure */
+	int			result;
+	bool			kswapd;	/* allocation in kswapd context */
+	struct completion	*done;
+	struct work_struct	work;
+};
+
+/*
+ * Stack switching interfaces for allocation
+ */
+static void
+xfs_btree_split_worker(
+	struct work_struct	*work)
+{
+	struct xfs_btree_split_args	*args = container_of(work,
+						struct xfs_btree_split_args, work);
+	unsigned long		pflags;
+	unsigned long		new_pflags = PF_FSTRANS;
+
+	/*
+	 * we are in a transaction context here, but may also be doing work
+	 * in kswapd context, and hence we may need to inherit that state
+	 * temporarily to ensure that we don't block waiting for memory reclaim
+	 * in any way.
+	 */
+	if (args->kswapd)
+		new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+
+	current_set_flags_nested(&pflags, new_pflags);
+
+	args->result = __xfs_btree_split(args->cur, args->level, args->ptrp,
+					 args->key, args->curp, args->stat);
+	complete(args->done);
+
+	current_restore_flags_nested(&pflags, new_pflags);
+}
+
+/*
+ * BMBT split requests often come in with little stack to work on. Push
+ * them off to a worker thread so there is lots of stack to use. For the other
+ * btree types, just call directly to avoid the context switch overhead here.
+ */
+STATIC int					/* error */
+xfs_btree_split(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	union xfs_btree_ptr	*ptrp,
+	union xfs_btree_key	*key,
+	struct xfs_btree_cur	**curp,
+	int			*stat)		/* success/failure */
+{
+	struct xfs_btree_split_args	args;
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	if (cur->bc_btnum != XFS_BTNUM_BMAP)
+		return __xfs_btree_split(cur, level, ptrp, key, curp, stat);
+
+	args.cur = cur;
+	args.level = level;
+	args.ptrp = ptrp;
+	args.key = key;
+	args.curp = curp;
+	args.stat = stat;
+	args.done = &done;
+	args.kswapd = current_is_kswapd();
+	INIT_WORK_ONSTACK(&args.work, xfs_btree_split_worker);
+	queue_work(xfs_alloc_wq, &args.work);
+	wait_for_completion(&done);
+	destroy_work_on_stack(&args.work);
+	return args.result;
+}
+
+
 /*
  * Copy the old inode root contents into a real block and make the
  * broot point to it.
@@ -2545,7 +2618,7 @@ xfs_btree_new_iroot(
 	pp = xfs_btree_ptr_addr(cur, 1, block);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, pp, &nptr, 1, stat);
+	error = cur->bc_ops->alloc_block(cur, pp, &nptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0) {
@@ -2649,7 +2722,7 @@ xfs_btree_new_root(
 	cur->bc_ops->init_ptr_from_cur(cur, &rptr);
 
 	/* Allocate the new block. If we can't do it, we're toast. Give up. */
-	error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, 1, stat);
+	error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, stat);
 	if (error)
 		goto error0;
 	if (*stat == 0)
@@ -2684,8 +2757,7 @@ xfs_btree_new_root(
 		lbp = bp;
 		xfs_btree_buf_to_ptr(cur, lbp, &lptr);
 		left = block;
-		error = xfs_btree_read_buf_block(cur, &rptr,
-					cur->bc_nlevels - 1, 0, &right, &rbp);
+		error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
 		if (error)
 			goto error0;
 		bp = rbp;
@@ -2696,8 +2768,7 @@ xfs_btree_new_root(
 		xfs_btree_buf_to_ptr(cur, rbp, &rptr);
 		right = block;
 		xfs_btree_get_sibling(cur, right, &lptr, XFS_BB_LEFTSIB);
-		error = xfs_btree_read_buf_block(cur, &lptr,
-					cur->bc_nlevels - 1, 0, &left, &lbp);
+		error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
 		if (error)
 			goto error0;
 		bp = lbp;
@@ -3649,8 +3720,7 @@ xfs_btree_delrec(
 		rptr = cptr;
 		right = block;
 		rbp = bp;
-		error = xfs_btree_read_buf_block(cur, &lptr, level,
-							0, &left, &lbp);
+		error = xfs_btree_read_buf_block(cur, &lptr, 0, &left, &lbp);
 		if (error)
 			goto error0;
 
@@ -3667,8 +3737,7 @@ xfs_btree_delrec(
 		lptr = cptr;
 		left = block;
 		lbp = bp;
-		error = xfs_btree_read_buf_block(cur, &rptr, level,
-							0, &right, &rbp);
+		error = xfs_btree_read_buf_block(cur, &rptr, 0, &right, &rbp);
 		if (error)
 			goto error0;
 
@@ -3740,8 +3809,7 @@ xfs_btree_delrec(
 	/* If there is a right sibling, point it to the remaining block. */
 	xfs_btree_get_sibling(cur, left, &cptr, XFS_BB_RIGHTSIB);
 	if (!xfs_btree_ptr_is_null(cur, &cptr)) {
-		error = xfs_btree_read_buf_block(cur, &cptr, level,
-							0, &rrblock, &rrbp);
+		error = xfs_btree_read_buf_block(cur, &cptr, 0, &rrblock, &rrbp);
 		if (error)
 			goto error0;
 		xfs_btree_set_sibling(cur, rrblock, &lptr, XFS_BB_LEFTSIB);
diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h
index 91e34f21bac..a04b69422f6 100644
--- a/fs/xfs/xfs_btree.h
+++ b/fs/xfs/xfs_btree.h
@@ -62,6 +62,7 @@ union xfs_btree_rec {
 #define	XFS_BTNUM_CNT	((xfs_btnum_t)XFS_BTNUM_CNTi)
 #define	XFS_BTNUM_BMAP	((xfs_btnum_t)XFS_BTNUM_BMAPi)
 #define	XFS_BTNUM_INO	((xfs_btnum_t)XFS_BTNUM_INOi)
+#define	XFS_BTNUM_FINO	((xfs_btnum_t)XFS_BTNUM_FINOi)
 
 /*
  * For logging record fields.
@@ -92,6 +93,7 @@ do {    \
 	case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(abtc, stat); break;	\
 	case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(bmbt, stat); break;	\
 	case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(ibt, stat); break;	\
+	case XFS_BTNUM_FINO: __XFS_BTREE_STATS_INC(fibt, stat); break;	\
 	case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break;	\
 	}       \
 } while (0)
@@ -105,6 +107,7 @@ do {    \
 	case XFS_BTNUM_CNT: __XFS_BTREE_STATS_ADD(abtc, stat, val); break; \
 	case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_ADD(bmbt, stat, val); break; \
 	case XFS_BTNUM_INO: __XFS_BTREE_STATS_ADD(ibt, stat, val); break; \
+	case XFS_BTNUM_FINO: __XFS_BTREE_STATS_ADD(fibt, stat, val); break; \
 	case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break;	\
 	}       \
 } while (0)
@@ -129,7 +132,7 @@ struct xfs_btree_ops {
 	int	(*alloc_block)(struct xfs_btree_cur *cur,
 			       union xfs_btree_ptr *start_bno,
 			       union xfs_btree_ptr *new_bno,
-			       int length, int *stat);
+			       int *stat);
 	int	(*free_block)(struct xfs_btree_cur *cur, struct xfs_buf *bp);
 
 	/* update last record information */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index cb10a0aaab3..7a34a1ae655 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -216,8 +216,7 @@ _xfs_buf_alloc(
 STATIC int
 _xfs_buf_get_pages(
 	xfs_buf_t		*bp,
-	int			page_count,
-	xfs_buf_flags_t		flags)
+	int			page_count)
 {
 	/* Make sure that we have a page list */
 	if (bp->b_pages == NULL) {
@@ -330,7 +329,7 @@ use_alloc_page:
 	end = (BBTOB(bp->b_maps[0].bm_bn + bp->b_length) + PAGE_SIZE - 1)
 								>> PAGE_SHIFT;
 	page_count = end - start;
-	error = _xfs_buf_get_pages(bp, page_count, flags);
+	error = _xfs_buf_get_pages(bp, page_count);
 	if (unlikely(error))
 		return error;
 
@@ -778,7 +777,7 @@ xfs_buf_associate_memory(
 	bp->b_pages = NULL;
 	bp->b_addr = mem;
 
-	rval = _xfs_buf_get_pages(bp, page_count, 0);
+	rval = _xfs_buf_get_pages(bp, page_count);
 	if (rval)
 		return rval;
 
@@ -811,7 +810,7 @@ xfs_buf_get_uncached(
 		goto fail;
 
 	page_count = PAGE_ALIGN(numblks << BBSHIFT) >> PAGE_SHIFT;
-	error = _xfs_buf_get_pages(bp, page_count, 0);
+	error = _xfs_buf_get_pages(bp, page_count);
 	if (error)
 		goto fail_free_buf;
 
@@ -1615,7 +1614,6 @@ xfs_free_buftarg(
 int
 xfs_setsize_buftarg(
 	xfs_buftarg_t		*btp,
-	unsigned int		blocksize,
 	unsigned int		sectorsize)
 {
 	/* Set up metadata sector size info */
@@ -1650,16 +1648,13 @@ xfs_setsize_buftarg_early(
 	xfs_buftarg_t		*btp,
 	struct block_device	*bdev)
 {
-	return xfs_setsize_buftarg(btp, PAGE_SIZE,
-				   bdev_logical_block_size(bdev));
+	return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev));
 }
 
 xfs_buftarg_t *
 xfs_alloc_buftarg(
 	struct xfs_mount	*mp,
-	struct block_device	*bdev,
-	int			external,
-	const char		*fsname)
+	struct block_device	*bdev)
 {
 	xfs_buftarg_t		*btp;
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index b8a3abf6cf4..3a7a5523d3d 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -298,11 +298,6 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 
 extern int xfs_bioerror_relse(struct xfs_buf *);
 
-static inline int xfs_buf_geterror(xfs_buf_t *bp)
-{
-	return bp ? bp->b_error : ENOMEM;
-}
-
 /* Buffer Utility Routines */
 extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
 
@@ -387,10 +382,10 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
  *	Handling of buftargs.
  */
 extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *,
-			struct block_device *, int, const char *);
+			struct block_device *);
 extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
 extern void xfs_wait_buftarg(xfs_buftarg_t *);
-extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
+extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int);
 
 #define xfs_getsize_buftarg(buftarg)	block_size((buftarg)->bt_bdev)
 #define xfs_readonly_buftarg(buftarg)	bdev_read_only((buftarg)->bt_bdev)
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 8752821443b..4654338b03f 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -812,7 +812,6 @@ xfs_buf_item_init(
  */
 static void
 xfs_buf_item_log_segment(
-	struct xfs_buf_log_item	*bip,
 	uint			first,
 	uint			last,
 	uint			*map)
@@ -920,7 +919,7 @@ xfs_buf_item_log(
 		if (end > last)
 			end = last;
 
-		xfs_buf_item_log_segment(bip, first, end,
+		xfs_buf_item_log_segment(first, end,
 					 &bip->bli_formats[i].blf_data_map[0]);
 
 		start += bp->b_maps[i].bm_len;
@@ -1053,7 +1052,7 @@ xfs_buf_iodone_callbacks(
 	static ulong		lasttime;
 	static xfs_buftarg_t	*lasttarg;
 
-	if (likely(!xfs_buf_geterror(bp)))
+	if (likely(!bp->b_error))
 		goto do_callbacks;
 
 	/*
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 6cc5f6785a7..a514ab61665 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -167,8 +167,8 @@ xfs_da3_node_verify(
 	 * we don't know if the node is for and attribute or directory tree,
 	 * so only fail if the count is outside both bounds
 	 */
-	if (ichdr.count > mp->m_dir_node_ents &&
-	    ichdr.count > mp->m_attr_node_ents)
+	if (ichdr.count > mp->m_dir_geo->node_ents &&
+	    ichdr.count > mp->m_attr_geo->node_ents)
 		return false;
 
 	/* XXX: hash order check? */
@@ -598,7 +598,7 @@ xfs_da3_root_split(
 	 * Set up the new root node.
 	 */
 	error = xfs_da3_node_create(args,
-		(args->whichfork == XFS_DATA_FORK) ? mp->m_dirleafblk : 0,
+		(args->whichfork == XFS_DATA_FORK) ? args->geo->leafblk : 0,
 		level + 1, &bp, args->whichfork);
 	if (error)
 		return error;
@@ -616,10 +616,10 @@ xfs_da3_root_split(
 #ifdef DEBUG
 	if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
 	    oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC)) {
-		ASSERT(blk1->blkno >= mp->m_dirleafblk &&
-		       blk1->blkno < mp->m_dirfreeblk);
-		ASSERT(blk2->blkno >= mp->m_dirleafblk &&
-		       blk2->blkno < mp->m_dirfreeblk);
+		ASSERT(blk1->blkno >= args->geo->leafblk &&
+		       blk1->blkno < args->geo->freeblk);
+		ASSERT(blk2->blkno >= args->geo->leafblk &&
+		       blk2->blkno < args->geo->freeblk);
 	}
 #endif
 
@@ -663,7 +663,7 @@ xfs_da3_node_split(
 	/*
 	 * Do we have to split the node?
 	 */
-	if (nodehdr.count + newcount > state->node_ents) {
+	if (nodehdr.count + newcount > state->args->geo->node_ents) {
 		/*
 		 * Allocate a new node, add to the doubly linked chain of
 		 * nodes, then move some of our excess entries into it.
@@ -894,8 +894,8 @@ xfs_da3_node_add(
 	ASSERT(oldblk->index >= 0 && oldblk->index <= nodehdr.count);
 	ASSERT(newblk->blkno != 0);
 	if (state->args->whichfork == XFS_DATA_FORK)
-		ASSERT(newblk->blkno >= state->mp->m_dirleafblk &&
-		       newblk->blkno < state->mp->m_dirfreeblk);
+		ASSERT(newblk->blkno >= state->args->geo->leafblk &&
+		       newblk->blkno < state->args->geo->freeblk);
 
 	/*
 	 * We may need to make some room before we insert the new node.
@@ -1089,14 +1089,15 @@ xfs_da3_root_join(
 	 * that could occur. For dir3 blocks we also need to update the block
 	 * number in the buffer header.
 	 */
-	memcpy(root_blk->bp->b_addr, bp->b_addr, state->blocksize);
+	memcpy(root_blk->bp->b_addr, bp->b_addr, args->geo->blksize);
 	root_blk->bp->b_ops = bp->b_ops;
 	xfs_trans_buf_copy_type(root_blk->bp, bp);
 	if (oldroothdr.magic == XFS_DA3_NODE_MAGIC) {
 		struct xfs_da3_blkinfo *da3 = root_blk->bp->b_addr;
 		da3->blkno = cpu_to_be64(root_blk->bp->b_bn);
 	}
-	xfs_trans_log_buf(args->trans, root_blk->bp, 0, state->blocksize - 1);
+	xfs_trans_log_buf(args->trans, root_blk->bp, 0,
+			  args->geo->blksize - 1);
 	error = xfs_da_shrink_inode(args, child, bp);
 	return(error);
 }
@@ -1139,7 +1140,7 @@ xfs_da3_node_toosmall(
 	info = blk->bp->b_addr;
 	node = (xfs_da_intnode_t *)info;
 	dp->d_ops->node_hdr_from_disk(&nodehdr, node);
-	if (nodehdr.count > (state->node_ents >> 1)) {
+	if (nodehdr.count > (state->args->geo->node_ents >> 1)) {
 		*action = 0;	/* blk over 50%, don't try to join */
 		return(0);	/* blk over 50%, don't try to join */
 	}
@@ -1176,8 +1177,8 @@ xfs_da3_node_toosmall(
 	 * We prefer coalescing with the lower numbered sibling so as
 	 * to shrink a directory over time.
 	 */
-	count  = state->node_ents;
-	count -= state->node_ents >> 2;
+	count  = state->args->geo->node_ents;
+	count -= state->args->geo->node_ents >> 2;
 	count -= nodehdr.count;
 
 	/* start with smaller blk num */
@@ -1472,7 +1473,7 @@ xfs_da3_node_lookup_int(
 	 * Descend thru the B-tree searching each level for the right
 	 * node to use, until the right hashval is found.
 	 */
-	blkno = (args->whichfork == XFS_DATA_FORK)? state->mp->m_dirleafblk : 0;
+	blkno = (args->whichfork == XFS_DATA_FORK)? args->geo->leafblk : 0;
 	for (blk = &state->path.blk[0], state->path.active = 1;
 			 state->path.active <= XFS_DA_NODE_MAXDEPTH;
 			 blk++, state->path.active++) {
@@ -2090,20 +2091,12 @@ xfs_da_grow_inode(
 	xfs_dablk_t		*new_blkno)
 {
 	xfs_fileoff_t		bno;
-	int			count;
 	int			error;
 
 	trace_xfs_da_grow_inode(args);
 
-	if (args->whichfork == XFS_DATA_FORK) {
-		bno = args->dp->i_mount->m_dirleafblk;
-		count = args->dp->i_mount->m_dirblkfsbs;
-	} else {
-		bno = 0;
-		count = 1;
-	}
-
-	error = xfs_da_grow_inode_int(args, &bno, count);
+	bno = args->geo->leafblk;
+	error = xfs_da_grow_inode_int(args, &bno, args->geo->fsbcount);
 	if (!error)
 		*new_blkno = (xfs_dablk_t)bno;
 	return error;
@@ -2158,7 +2151,7 @@ xfs_da3_swap_lastblock(
 	w = args->whichfork;
 	ASSERT(w == XFS_DATA_FORK);
 	mp = dp->i_mount;
-	lastoff = mp->m_dirfreeblk;
+	lastoff = args->geo->freeblk;
 	error = xfs_bmap_last_before(tp, dp, &lastoff, w);
 	if (error)
 		return error;
@@ -2170,15 +2163,15 @@ xfs_da3_swap_lastblock(
 	/*
 	 * Read the last block in the btree space.
 	 */
-	last_blkno = (xfs_dablk_t)lastoff - mp->m_dirblkfsbs;
+	last_blkno = (xfs_dablk_t)lastoff - args->geo->fsbcount;
 	error = xfs_da3_node_read(tp, dp, last_blkno, -1, &last_buf, w);
 	if (error)
 		return error;
 	/*
 	 * Copy the last block into the dead buffer and log it.
 	 */
-	memcpy(dead_buf->b_addr, last_buf->b_addr, mp->m_dirblksize);
-	xfs_trans_log_buf(tp, dead_buf, 0, mp->m_dirblksize - 1);
+	memcpy(dead_buf->b_addr, last_buf->b_addr, args->geo->blksize);
+	xfs_trans_log_buf(tp, dead_buf, 0, args->geo->blksize - 1);
 	dead_info = dead_buf->b_addr;
 	/*
 	 * Get values from the moved block.
@@ -2247,7 +2240,7 @@ xfs_da3_swap_lastblock(
 					sizeof(sib_info->back)));
 		sib_buf = NULL;
 	}
-	par_blkno = mp->m_dirleafblk;
+	par_blkno = args->geo->leafblk;
 	level = -1;
 	/*
 	 * Walk down the tree looking for the parent of the moved block.
@@ -2357,10 +2350,7 @@ xfs_da_shrink_inode(
 	w = args->whichfork;
 	tp = args->trans;
 	mp = dp->i_mount;
-	if (w == XFS_DATA_FORK)
-		count = mp->m_dirblkfsbs;
-	else
-		count = 1;
+	count = args->geo->fsbcount;
 	for (;;) {
 		/*
 		 * Remove extents.  If we get ENOSPC for a dir we have to move
@@ -2462,7 +2452,6 @@ xfs_buf_map_from_irec(
  */
 static int
 xfs_dabuf_map(
-	struct xfs_trans	*trans,
 	struct xfs_inode	*dp,
 	xfs_dablk_t		bno,
 	xfs_daddr_t		mappedbno,
@@ -2480,7 +2469,10 @@ xfs_dabuf_map(
 	ASSERT(map && *map);
 	ASSERT(*nmaps == 1);
 
-	nfsb = (whichfork == XFS_DATA_FORK) ? mp->m_dirblkfsbs : 1;
+	if (whichfork == XFS_DATA_FORK)
+		nfsb = mp->m_dir_geo->fsbcount;
+	else
+		nfsb = mp->m_attr_geo->fsbcount;
 
 	/*
 	 * Caller doesn't have a mapping.  -2 means don't complain
@@ -2558,7 +2550,7 @@ xfs_da_get_buf(
 	*bpp = NULL;
 	mapp = &map;
 	nmap = 1;
-	error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+	error = xfs_dabuf_map(dp, bno, mappedbno, whichfork,
 				&mapp, &nmap);
 	if (error) {
 		/* mapping a hole is not an error, but we don't continue */
@@ -2606,7 +2598,7 @@ xfs_da_read_buf(
 	*bpp = NULL;
 	mapp = &map;
 	nmap = 1;
-	error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+	error = xfs_dabuf_map(dp, bno, mappedbno, whichfork,
 				&mapp, &nmap);
 	if (error) {
 		/* mapping a hole is not an error, but we don't continue */
@@ -2625,47 +2617,6 @@ xfs_da_read_buf(
 		xfs_buf_set_ref(bp, XFS_ATTR_BTREE_REF);
 	else
 		xfs_buf_set_ref(bp, XFS_DIR_BTREE_REF);
-
-	/*
-	 * This verification code will be moved to a CRC verification callback
-	 * function so just leave it here unchanged until then.
-	 */
-	{
-		xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
-		xfs_dir2_free_t		*free = bp->b_addr;
-		xfs_da_blkinfo_t	*info = bp->b_addr;
-		uint			magic, magic1;
-		struct xfs_mount	*mp = dp->i_mount;
-
-		magic = be16_to_cpu(info->magic);
-		magic1 = be32_to_cpu(hdr->magic);
-		if (unlikely(
-		    XFS_TEST_ERROR((magic != XFS_DA_NODE_MAGIC) &&
-				   (magic != XFS_DA3_NODE_MAGIC) &&
-				   (magic != XFS_ATTR_LEAF_MAGIC) &&
-				   (magic != XFS_ATTR3_LEAF_MAGIC) &&
-				   (magic != XFS_DIR2_LEAF1_MAGIC) &&
-				   (magic != XFS_DIR3_LEAF1_MAGIC) &&
-				   (magic != XFS_DIR2_LEAFN_MAGIC) &&
-				   (magic != XFS_DIR3_LEAFN_MAGIC) &&
-				   (magic1 != XFS_DIR2_BLOCK_MAGIC) &&
-				   (magic1 != XFS_DIR3_BLOCK_MAGIC) &&
-				   (magic1 != XFS_DIR2_DATA_MAGIC) &&
-				   (magic1 != XFS_DIR3_DATA_MAGIC) &&
-				   (free->hdr.magic !=
-					cpu_to_be32(XFS_DIR2_FREE_MAGIC)) &&
-				   (free->hdr.magic !=
-					cpu_to_be32(XFS_DIR3_FREE_MAGIC)),
-				mp, XFS_ERRTAG_DA_READ_BUF,
-				XFS_RANDOM_DA_READ_BUF))) {
-			trace_xfs_da_btree_corrupt(bp, _RET_IP_);
-			XFS_CORRUPTION_ERROR("xfs_da_do_buf(2)",
-					     XFS_ERRLEVEL_LOW, mp, info);
-			error = XFS_ERROR(EFSCORRUPTED);
-			xfs_trans_brelse(trans, bp);
-			goto out_free;
-		}
-	}
 	*bpp = bp;
 out_free:
 	if (mapp != &map)
@@ -2679,7 +2630,6 @@ out_free:
  */
 xfs_daddr_t
 xfs_da_reada_buf(
-	struct xfs_trans	*trans,
 	struct xfs_inode	*dp,
 	xfs_dablk_t		bno,
 	xfs_daddr_t		mappedbno,
@@ -2693,7 +2643,7 @@ xfs_da_reada_buf(
 
 	mapp = &map;
 	nmap = 1;
-	error = xfs_dabuf_map(trans, dp, bno, mappedbno, whichfork,
+	error = xfs_dabuf_map(dp, bno, mappedbno, whichfork,
 				&mapp, &nmap);
 	if (error) {
 		/* mapping a hole is not an error, but we don't continue */
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index 201c6091d26..6e153e399a7 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -25,6 +25,23 @@ struct xfs_trans;
 struct zone;
 struct xfs_dir_ops;
 
+/*
+ * Directory/attribute geometry information. There will be one of these for each
+ * data fork type, and it will be passed around via the xfs_da_args. Global
+ * structures will be attached to the xfs_mount.
+ */
+struct xfs_da_geometry {
+	int		blksize;	/* da block size in bytes */
+	int		fsbcount;	/* da block size in filesystem blocks */
+	uint8_t		fsblog;		/* log2 of _filesystem_ block size */
+	uint8_t		blklog;		/* log2 of da block size */
+	uint		node_ents;	/* # of entries in a danode */
+	int		magicpct;	/* 37% of block size in bytes */
+	xfs_dablk_t	datablk;	/* blockno of dir data v2 */
+	xfs_dablk_t	leafblk;	/* blockno of leaf data v2 */
+	xfs_dablk_t	freeblk;	/* blockno of free data v2 */
+};
+
 /*========================================================================
  * Btree searching and modification structure definitions.
  *========================================================================*/
@@ -42,6 +59,7 @@ enum xfs_dacmp {
  * Structure to ease passing around component names.
  */
 typedef struct xfs_da_args {
+	struct xfs_da_geometry *geo;	/* da block geometry */
 	const __uint8_t	*name;		/* string (maybe not NULL terminated) */
 	int		namelen;	/* length of string (maybe no NULL) */
 	__uint8_t	filetype;	/* filetype of inode for directories */
@@ -110,8 +128,6 @@ typedef struct xfs_da_state_path {
 typedef struct xfs_da_state {
 	xfs_da_args_t		*args;		/* filename arguments */
 	struct xfs_mount	*mp;		/* filesystem mount point */
-	unsigned int		blocksize;	/* logical block size */
-	unsigned int		node_ents;	/* how many entries in danode */
 	xfs_da_state_path_t	path;		/* search/split paths */
 	xfs_da_state_path_t	altpath;	/* alternate path for join */
 	unsigned char		inleaf;		/* insert into 1->lf, 0->splf */
@@ -185,9 +201,9 @@ int	xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			       xfs_dablk_t bno, xfs_daddr_t mappedbno,
 			       struct xfs_buf **bpp, int whichfork,
 			       const struct xfs_buf_ops *ops);
-xfs_daddr_t	xfs_da_reada_buf(struct xfs_trans *trans, struct xfs_inode *dp,
-				xfs_dablk_t bno, xfs_daddr_t mapped_bno,
-				int whichfork, const struct xfs_buf_ops *ops);
+xfs_daddr_t	xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
+				xfs_daddr_t mapped_bno, int whichfork,
+				const struct xfs_buf_ops *ops);
 int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 					  struct xfs_buf *dead_buf);
 
diff --git a/fs/xfs/xfs_da_format.c b/fs/xfs/xfs_da_format.c
index e6c83e1fbc8..c9aee52a37e 100644
--- a/fs/xfs/xfs_da_format.c
+++ b/fs/xfs/xfs_da_format.c
@@ -26,8 +26,10 @@
 #include "xfs_ag.h"
 #include "xfs_mount.h"
 #include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_inode.h"
 #include "xfs_dir2.h"
+#include "xfs_dir2_priv.h"
 
 /*
  * Shortform directory ops
@@ -425,9 +427,9 @@ xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
  * Directory Leaf block operations
  */
 static int
-xfs_dir2_max_leaf_ents(struct xfs_mount *mp)
+xfs_dir2_max_leaf_ents(struct xfs_da_geometry *geo)
 {
-	return (mp->m_dirblksize - sizeof(struct xfs_dir2_leaf_hdr)) /
+	return (geo->blksize - sizeof(struct xfs_dir2_leaf_hdr)) /
 		(uint)sizeof(struct xfs_dir2_leaf_entry);
 }
 
@@ -438,9 +440,9 @@ xfs_dir2_leaf_ents_p(struct xfs_dir2_leaf *lp)
 }
 
 static int
-xfs_dir3_max_leaf_ents(struct xfs_mount *mp)
+xfs_dir3_max_leaf_ents(struct xfs_da_geometry *geo)
 {
-	return (mp->m_dirblksize - sizeof(struct xfs_dir3_leaf_hdr)) /
+	return (geo->blksize - sizeof(struct xfs_dir3_leaf_hdr)) /
 		(uint)sizeof(struct xfs_dir2_leaf_entry);
 }
 
@@ -591,9 +593,9 @@ xfs_da3_node_hdr_to_disk(
  * Directory free space block operations
  */
 static int
-xfs_dir2_free_max_bests(struct xfs_mount *mp)
+xfs_dir2_free_max_bests(struct xfs_da_geometry *geo)
 {
-	return (mp->m_dirblksize - sizeof(struct xfs_dir2_free_hdr)) /
+	return (geo->blksize - sizeof(struct xfs_dir2_free_hdr)) /
 		sizeof(xfs_dir2_data_off_t);
 }
 
@@ -607,24 +609,25 @@ xfs_dir2_free_bests_p(struct xfs_dir2_free *free)
  * Convert data space db to the corresponding free db.
  */
 static xfs_dir2_db_t
-xfs_dir2_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
+xfs_dir2_db_to_fdb(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
 {
-	return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir2_free_max_bests(mp);
+	return xfs_dir2_byte_to_db(geo, XFS_DIR2_FREE_OFFSET) +
+			(db / xfs_dir2_free_max_bests(geo));
 }
 
 /*
  * Convert data space db to the corresponding index in a free db.
  */
 static int
-xfs_dir2_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
+xfs_dir2_db_to_fdindex(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
 {
-	return db % xfs_dir2_free_max_bests(mp);
+	return db % xfs_dir2_free_max_bests(geo);
 }
 
 static int
-xfs_dir3_free_max_bests(struct xfs_mount *mp)
+xfs_dir3_free_max_bests(struct xfs_da_geometry *geo)
 {
-	return (mp->m_dirblksize - sizeof(struct xfs_dir3_free_hdr)) /
+	return (geo->blksize - sizeof(struct xfs_dir3_free_hdr)) /
 		sizeof(xfs_dir2_data_off_t);
 }
 
@@ -638,18 +641,19 @@ xfs_dir3_free_bests_p(struct xfs_dir2_free *free)
  * Convert data space db to the corresponding free db.
  */
 static xfs_dir2_db_t
-xfs_dir3_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db)
+xfs_dir3_db_to_fdb(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
 {
-	return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir3_free_max_bests(mp);
+	return xfs_dir2_byte_to_db(geo, XFS_DIR2_FREE_OFFSET) +
+			(db / xfs_dir3_free_max_bests(geo));
 }
 
 /*
  * Convert data space db to the corresponding index in a free db.
  */
 static int
-xfs_dir3_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db)
+xfs_dir3_db_to_fdindex(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
 {
-	return db % xfs_dir3_free_max_bests(mp);
+	return db % xfs_dir3_free_max_bests(geo);
 }
 
 static void
diff --git a/fs/xfs/xfs_da_format.h b/fs/xfs/xfs_da_format.h
index a19d3f8f639..0a49b028637 100644
--- a/fs/xfs/xfs_da_format.h
+++ b/fs/xfs/xfs_da_format.h
@@ -19,10 +19,6 @@
 #ifndef __XFS_DA_FORMAT_H__
 #define __XFS_DA_FORMAT_H__
 
-/*========================================================================
- * Directory Structure when greater than XFS_LBSIZE(mp) bytes.
- *========================================================================*/
-
 /*
  * This structure is common to both leaf nodes and non-leaf nodes in the Btree.
  *
@@ -122,8 +118,6 @@ struct xfs_da3_icnode_hdr {
 	__uint16_t	level;
 };
 
-#define	XFS_LBSIZE(mp)	(mp)->m_sb.sb_blocksize
-
 /*
  * Directory version 2.
  *
@@ -330,8 +324,6 @@ xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
 #define	XFS_DIR2_SPACE_SIZE	(1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
 #define	XFS_DIR2_DATA_SPACE	0
 #define	XFS_DIR2_DATA_OFFSET	(XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE)
-#define	XFS_DIR2_DATA_FIRSTDB(mp)	\
-	xfs_dir2_byte_to_db(mp, XFS_DIR2_DATA_OFFSET)
 
 /*
  * Describe a free area in the data block.
@@ -456,8 +448,6 @@ xfs_dir2_data_unused_tag_p(struct xfs_dir2_data_unused *dup)
  */
 #define	XFS_DIR2_LEAF_SPACE	1
 #define	XFS_DIR2_LEAF_OFFSET	(XFS_DIR2_LEAF_SPACE * XFS_DIR2_SPACE_SIZE)
-#define	XFS_DIR2_LEAF_FIRSTDB(mp)	\
-	xfs_dir2_byte_to_db(mp, XFS_DIR2_LEAF_OFFSET)
 
 /*
  * Leaf block header.
@@ -514,17 +504,6 @@ struct xfs_dir3_leaf {
 #define XFS_DIR3_LEAF_CRC_OFF  offsetof(struct xfs_dir3_leaf_hdr, info.crc)
 
 /*
- * Get address of the bestcount field in the single-leaf block.
- */
-static inline struct xfs_dir2_leaf_tail *
-xfs_dir2_leaf_tail_p(struct xfs_mount *mp, struct xfs_dir2_leaf *lp)
-{
-	return (struct xfs_dir2_leaf_tail *)
-		((char *)lp + mp->m_dirblksize -
-		  sizeof(struct xfs_dir2_leaf_tail));
-}
-
-/*
  * Get address of the bests array in the single-leaf block.
  */
 static inline __be16 *
@@ -534,123 +513,6 @@ xfs_dir2_leaf_bests_p(struct xfs_dir2_leaf_tail *ltp)
 }
 
 /*
- * DB blocks here are logical directory block numbers, not filesystem blocks.
- */
-
-/*
- * Convert dataptr to byte in file space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_dataptr_to_byte(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
-	return (xfs_dir2_off_t)dp << XFS_DIR2_DATA_ALIGN_LOG;
-}
-
-/*
- * Convert byte in file space to dataptr.  It had better be aligned.
- */
-static inline xfs_dir2_dataptr_t
-xfs_dir2_byte_to_dataptr(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
-	return (xfs_dir2_dataptr_t)(by >> XFS_DIR2_DATA_ALIGN_LOG);
-}
-
-/*
- * Convert byte in space to (DB) block
- */
-static inline xfs_dir2_db_t
-xfs_dir2_byte_to_db(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
-	return (xfs_dir2_db_t)
-		(by >> (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog));
-}
-
-/*
- * Convert dataptr to a block number
- */
-static inline xfs_dir2_db_t
-xfs_dir2_dataptr_to_db(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
-	return xfs_dir2_byte_to_db(mp, xfs_dir2_dataptr_to_byte(mp, dp));
-}
-
-/*
- * Convert byte in space to offset in a block
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_byte_to_off(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
-	return (xfs_dir2_data_aoff_t)(by &
-		((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) - 1));
-}
-
-/*
- * Convert dataptr to a byte offset in a block
- */
-static inline xfs_dir2_data_aoff_t
-xfs_dir2_dataptr_to_off(struct xfs_mount *mp, xfs_dir2_dataptr_t dp)
-{
-	return xfs_dir2_byte_to_off(mp, xfs_dir2_dataptr_to_byte(mp, dp));
-}
-
-/*
- * Convert block and offset to byte in space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_db_off_to_byte(struct xfs_mount *mp, xfs_dir2_db_t db,
-			xfs_dir2_data_aoff_t o)
-{
-	return ((xfs_dir2_off_t)db <<
-		(mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) + o;
-}
-
-/*
- * Convert block (DB) to block (dablk)
- */
-static inline xfs_dablk_t
-xfs_dir2_db_to_da(struct xfs_mount *mp, xfs_dir2_db_t db)
-{
-	return (xfs_dablk_t)(db << mp->m_sb.sb_dirblklog);
-}
-
-/*
- * Convert byte in space to (DA) block
- */
-static inline xfs_dablk_t
-xfs_dir2_byte_to_da(struct xfs_mount *mp, xfs_dir2_off_t by)
-{
-	return xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, by));
-}
-
-/*
- * Convert block and offset to dataptr
- */
-static inline xfs_dir2_dataptr_t
-xfs_dir2_db_off_to_dataptr(struct xfs_mount *mp, xfs_dir2_db_t db,
-			   xfs_dir2_data_aoff_t o)
-{
-	return xfs_dir2_byte_to_dataptr(mp, xfs_dir2_db_off_to_byte(mp, db, o));
-}
-
-/*
- * Convert block (dablk) to block (DB)
- */
-static inline xfs_dir2_db_t
-xfs_dir2_da_to_db(struct xfs_mount *mp, xfs_dablk_t da)
-{
-	return (xfs_dir2_db_t)(da >> mp->m_sb.sb_dirblklog);
-}
-
-/*
- * Convert block (dablk) to byte offset in space
- */
-static inline xfs_dir2_off_t
-xfs_dir2_da_to_byte(struct xfs_mount *mp, xfs_dablk_t da)
-{
-	return xfs_dir2_db_off_to_byte(mp, xfs_dir2_da_to_db(mp, da), 0);
-}
-
-/*
  * Free space block defintions for the node format.
  */
 
@@ -659,8 +521,6 @@ xfs_dir2_da_to_byte(struct xfs_mount *mp, xfs_dablk_t da)
  */
 #define	XFS_DIR2_FREE_SPACE	2
 #define	XFS_DIR2_FREE_OFFSET	(XFS_DIR2_FREE_SPACE * XFS_DIR2_SPACE_SIZE)
-#define	XFS_DIR2_FREE_FIRSTDB(mp)	\
-	xfs_dir2_byte_to_db(mp, XFS_DIR2_FREE_OFFSET)
 
 typedef	struct xfs_dir2_free_hdr {
 	__be32			magic;		/* XFS_DIR2_FREE_MAGIC */
@@ -736,16 +596,6 @@ typedef struct xfs_dir2_block_tail {
 } xfs_dir2_block_tail_t;
 
 /*
- * Pointer to the leaf header embedded in a data block (1-block format)
- */
-static inline struct xfs_dir2_block_tail *
-xfs_dir2_block_tail_p(struct xfs_mount *mp, struct xfs_dir2_data_hdr *hdr)
-{
-	return ((struct xfs_dir2_block_tail *)
-		((char *)hdr + mp->m_dirblksize)) - 1;
-}
-
-/*
  * Pointer to the leaf entries embedded in a data block (1-block format)
  */
 static inline struct xfs_dir2_leaf_entry *
@@ -764,10 +614,6 @@ xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp)
  * of an attribute name may not be unique, we may have duplicate keys.  The
  * internal links in the Btree are logical block offsets into the file.
  *
- *========================================================================
- * Attribute structure when equal to XFS_LBSIZE(mp) bytes.
- *========================================================================
- *
  * Struct leaf_entry's are packed from the top.  Name/values grow from the
  * bottom but are not packed.  The freemap contains run-length-encoded entries
  * for the free bytes after the leaf_entry's, but only the N largest such,
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index fda46253966..79670cda48a 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -85,38 +85,74 @@ static struct xfs_nameops xfs_ascii_ci_nameops = {
 	.compname	= xfs_ascii_ci_compname,
 };
 
-void
-xfs_dir_mount(
-	xfs_mount_t	*mp)
+int
+xfs_da_mount(
+	struct xfs_mount	*mp)
 {
-	int	nodehdr_size;
+	struct xfs_da_geometry	*dageo;
+	int			nodehdr_size;
 
 
-	ASSERT(xfs_sb_version_hasdirv2(&mp->m_sb));
+	ASSERT(mp->m_sb.sb_versionnum & XFS_SB_VERSION_DIRV2BIT);
 	ASSERT((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) <=
 	       XFS_MAX_BLOCKSIZE);
 
 	mp->m_dir_inode_ops = xfs_dir_get_ops(mp, NULL);
 	mp->m_nondir_inode_ops = xfs_nondir_get_ops(mp, NULL);
 
-	mp->m_dirblksize = 1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog);
-	mp->m_dirblkfsbs = 1 << mp->m_sb.sb_dirblklog;
-	mp->m_dirdatablk = xfs_dir2_db_to_da(mp, XFS_DIR2_DATA_FIRSTDB(mp));
-	mp->m_dirleafblk = xfs_dir2_db_to_da(mp, XFS_DIR2_LEAF_FIRSTDB(mp));
-	mp->m_dirfreeblk = xfs_dir2_db_to_da(mp, XFS_DIR2_FREE_FIRSTDB(mp));
-
 	nodehdr_size = mp->m_dir_inode_ops->node_hdr_size;
-	mp->m_attr_node_ents = (mp->m_sb.sb_blocksize - nodehdr_size) /
+	mp->m_dir_geo = kmem_zalloc(sizeof(struct xfs_da_geometry),
+				    KM_SLEEP | KM_MAYFAIL);
+	mp->m_attr_geo = kmem_zalloc(sizeof(struct xfs_da_geometry),
+				     KM_SLEEP | KM_MAYFAIL);
+	if (!mp->m_dir_geo || !mp->m_attr_geo) {
+		kmem_free(mp->m_dir_geo);
+		kmem_free(mp->m_attr_geo);
+		return ENOMEM;
+	}
+
+	/* set up directory geometry */
+	dageo = mp->m_dir_geo;
+	dageo->blklog = mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog;
+	dageo->fsblog = mp->m_sb.sb_blocklog;
+	dageo->blksize = 1 << dageo->blklog;
+	dageo->fsbcount = 1 << mp->m_sb.sb_dirblklog;
+
+	/*
+	 * Now we've set up the block conversion variables, we can calculate the
+	 * segment block constants using the geometry structure.
+	 */
+	dageo->datablk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_DATA_OFFSET);
+	dageo->leafblk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_LEAF_OFFSET);
+	dageo->freeblk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_FREE_OFFSET);
+	dageo->node_ents = (dageo->blksize - nodehdr_size) /
 				(uint)sizeof(xfs_da_node_entry_t);
-	mp->m_dir_node_ents = (mp->m_dirblksize - nodehdr_size) /
+	dageo->magicpct = (dageo->blksize * 37) / 100;
+
+	/* set up attribute geometry - single fsb only */
+	dageo = mp->m_attr_geo;
+	dageo->blklog = mp->m_sb.sb_blocklog;
+	dageo->fsblog = mp->m_sb.sb_blocklog;
+	dageo->blksize = 1 << dageo->blklog;
+	dageo->fsbcount = 1;
+	dageo->node_ents = (dageo->blksize - nodehdr_size) /
 				(uint)sizeof(xfs_da_node_entry_t);
+	dageo->magicpct = (dageo->blksize * 37) / 100;
 
-	mp->m_dir_magicpct = (mp->m_dirblksize * 37) / 100;
 	if (xfs_sb_version_hasasciici(&mp->m_sb))
 		mp->m_dirnameops = &xfs_ascii_ci_nameops;
 	else
 		mp->m_dirnameops = &xfs_default_nameops;
 
+	return 0;
+}
+
+void
+xfs_da_unmount(
+	struct xfs_mount	*mp)
+{
+	kmem_free(mp->m_dir_geo);
+	kmem_free(mp->m_attr_geo);
 }
 
 /*
@@ -192,6 +228,7 @@ xfs_dir_init(
 	if (!args)
 		return ENOMEM;
 
+	args->geo = dp->i_mount->m_dir_geo;
 	args->dp = dp;
 	args->trans = tp;
 	error = xfs_dir2_sf_create(args, pdp->i_ino);
@@ -226,6 +263,7 @@ xfs_dir_createname(
 	if (!args)
 		return ENOMEM;
 
+	args->geo = dp->i_mount->m_dir_geo;
 	args->name = name->name;
 	args->namelen = name->len;
 	args->filetype = name->type;
@@ -244,7 +282,7 @@ xfs_dir_createname(
 		goto out_free;
 	}
 
-	rval = xfs_dir2_isblock(tp, dp, &v);
+	rval = xfs_dir2_isblock(args, &v);
 	if (rval)
 		goto out_free;
 	if (v) {
@@ -252,7 +290,7 @@ xfs_dir_createname(
 		goto out_free;
 	}
 
-	rval = xfs_dir2_isleaf(tp, dp, &v);
+	rval = xfs_dir2_isleaf(args, &v);
 	if (rval)
 		goto out_free;
 	if (v)
@@ -320,6 +358,7 @@ xfs_dir_lookup(
 	 * annotations into the reclaim path for the ilock.
 	 */
 	args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
+	args->geo = dp->i_mount->m_dir_geo;
 	args->name = name->name;
 	args->namelen = name->len;
 	args->filetype = name->type;
@@ -336,7 +375,7 @@ xfs_dir_lookup(
 		goto out_check_rval;
 	}
 
-	rval = xfs_dir2_isblock(tp, dp, &v);
+	rval = xfs_dir2_isblock(args, &v);
 	if (rval)
 		goto out_free;
 	if (v) {
@@ -344,7 +383,7 @@ xfs_dir_lookup(
 		goto out_check_rval;
 	}
 
-	rval = xfs_dir2_isleaf(tp, dp, &v);
+	rval = xfs_dir2_isleaf(args, &v);
 	if (rval)
 		goto out_free;
 	if (v)
@@ -391,6 +430,7 @@ xfs_dir_removename(
 	if (!args)
 		return ENOMEM;
 
+	args->geo = dp->i_mount->m_dir_geo;
 	args->name = name->name;
 	args->namelen = name->len;
 	args->filetype = name->type;
@@ -408,7 +448,7 @@ xfs_dir_removename(
 		goto out_free;
 	}
 
-	rval = xfs_dir2_isblock(tp, dp, &v);
+	rval = xfs_dir2_isblock(args, &v);
 	if (rval)
 		goto out_free;
 	if (v) {
@@ -416,7 +456,7 @@ xfs_dir_removename(
 		goto out_free;
 	}
 
-	rval = xfs_dir2_isleaf(tp, dp, &v);
+	rval = xfs_dir2_isleaf(args, &v);
 	if (rval)
 		goto out_free;
 	if (v)
@@ -455,6 +495,7 @@ xfs_dir_replace(
 	if (!args)
 		return ENOMEM;
 
+	args->geo = dp->i_mount->m_dir_geo;
 	args->name = name->name;
 	args->namelen = name->len;
 	args->filetype = name->type;
@@ -472,7 +513,7 @@ xfs_dir_replace(
 		goto out_free;
 	}
 
-	rval = xfs_dir2_isblock(tp, dp, &v);
+	rval = xfs_dir2_isblock(args, &v);
 	if (rval)
 		goto out_free;
 	if (v) {
@@ -480,7 +521,7 @@ xfs_dir_replace(
 		goto out_free;
 	}
 
-	rval = xfs_dir2_isleaf(tp, dp, &v);
+	rval = xfs_dir2_isleaf(args, &v);
 	if (rval)
 		goto out_free;
 	if (v)
@@ -516,6 +557,7 @@ xfs_dir_canenter(
 	if (!args)
 		return ENOMEM;
 
+	args->geo = dp->i_mount->m_dir_geo;
 	args->name = name->name;
 	args->namelen = name->len;
 	args->filetype = name->type;
@@ -531,7 +573,7 @@ xfs_dir_canenter(
 		goto out_free;
 	}
 
-	rval = xfs_dir2_isblock(tp, dp, &v);
+	rval = xfs_dir2_isblock(args, &v);
 	if (rval)
 		goto out_free;
 	if (v) {
@@ -539,7 +581,7 @@ xfs_dir_canenter(
 		goto out_free;
 	}
 
-	rval = xfs_dir2_isleaf(tp, dp, &v);
+	rval = xfs_dir2_isleaf(args, &v);
 	if (rval)
 		goto out_free;
 	if (v)
@@ -579,13 +621,13 @@ xfs_dir2_grow_inode(
 	 * Set lowest possible block in the space requested.
 	 */
 	bno = XFS_B_TO_FSBT(mp, space * XFS_DIR2_SPACE_SIZE);
-	count = mp->m_dirblkfsbs;
+	count = args->geo->fsbcount;
 
 	error = xfs_da_grow_inode_int(args, &bno, count);
 	if (error)
 		return error;
 
-	*dbp = xfs_dir2_da_to_db(mp, (xfs_dablk_t)bno);
+	*dbp = xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)bno);
 
 	/*
 	 * Update file's size if this is the data space and it grew.
@@ -607,19 +649,16 @@ xfs_dir2_grow_inode(
  */
 int
 xfs_dir2_isblock(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*dp,
-	int		*vp)		/* out: 1 is block, 0 is not block */
+	struct xfs_da_args	*args,
+	int			*vp)	/* out: 1 is block, 0 is not block */
 {
-	xfs_fileoff_t	last;		/* last file offset */
-	xfs_mount_t	*mp;
-	int		rval;
+	xfs_fileoff_t		last;	/* last file offset */
+	int			rval;
 
-	mp = dp->i_mount;
-	if ((rval = xfs_bmap_last_offset(tp, dp, &last, XFS_DATA_FORK)))
+	if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
 		return rval;
-	rval = XFS_FSB_TO_B(mp, last) == mp->m_dirblksize;
-	ASSERT(rval == 0 || dp->i_d.di_size == mp->m_dirblksize);
+	rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize;
+	ASSERT(rval == 0 || args->dp->i_d.di_size == args->geo->blksize);
 	*vp = rval;
 	return 0;
 }
@@ -629,18 +668,15 @@ xfs_dir2_isblock(
  */
 int
 xfs_dir2_isleaf(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*dp,
-	int		*vp)		/* out: 1 is leaf, 0 is not leaf */
+	struct xfs_da_args	*args,
+	int			*vp)	/* out: 1 is block, 0 is not block */
 {
-	xfs_fileoff_t	last;		/* last file offset */
-	xfs_mount_t	*mp;
-	int		rval;
+	xfs_fileoff_t		last;	/* last file offset */
+	int			rval;
 
-	mp = dp->i_mount;
-	if ((rval = xfs_bmap_last_offset(tp, dp, &last, XFS_DATA_FORK)))
+	if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
 		return rval;
-	*vp = last == mp->m_dirleafblk + (1 << mp->m_sb.sb_dirblklog);
+	*vp = last == args->geo->leafblk + args->geo->fsbcount;
 	return 0;
 }
 
@@ -668,11 +704,11 @@ xfs_dir2_shrink_inode(
 	dp = args->dp;
 	mp = dp->i_mount;
 	tp = args->trans;
-	da = xfs_dir2_db_to_da(mp, db);
+	da = xfs_dir2_db_to_da(args->geo, db);
 	/*
 	 * Unmap the fsblock(s).
 	 */
-	if ((error = xfs_bunmapi(tp, dp, da, mp->m_dirblkfsbs,
+	if ((error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount,
 			XFS_BMAPI_METADATA, 0, args->firstblock, args->flist,
 			&done))) {
 		/*
@@ -699,12 +735,12 @@ xfs_dir2_shrink_inode(
 	/*
 	 * If it's not a data block, we're done.
 	 */
-	if (db >= XFS_DIR2_LEAF_FIRSTDB(mp))
+	if (db >= xfs_dir2_byte_to_db(args->geo, XFS_DIR2_LEAF_OFFSET))
 		return 0;
 	/*
 	 * If the block isn't the last one in the directory, we're done.
 	 */
-	if (dp->i_d.di_size > xfs_dir2_db_off_to_byte(mp, db + 1, 0))
+	if (dp->i_d.di_size > xfs_dir2_db_off_to_byte(args->geo, db + 1, 0))
 		return 0;
 	bno = da;
 	if ((error = xfs_bmap_last_before(tp, dp, &bno, XFS_DATA_FORK))) {
@@ -713,7 +749,7 @@ xfs_dir2_shrink_inode(
 		 */
 		return error;
 	}
-	if (db == mp->m_dirdatablk)
+	if (db == args->geo->datablk)
 		ASSERT(bno == 0);
 	else
 		ASSERT(bno > 0);
diff --git a/fs/xfs/xfs_dir2.h b/fs/xfs/xfs_dir2.h
index cec70e0781a..c8e86b0b5e9 100644
--- a/fs/xfs/xfs_dir2.h
+++ b/fs/xfs/xfs_dir2.h
@@ -80,7 +80,7 @@ struct xfs_dir_ops {
 				    struct xfs_dir3_icleaf_hdr *from);
 	void	(*leaf_hdr_from_disk)(struct xfs_dir3_icleaf_hdr *to,
 				      struct xfs_dir2_leaf *from);
-	int	(*leaf_max_ents)(struct xfs_mount *mp);
+	int	(*leaf_max_ents)(struct xfs_da_geometry *geo);
 	struct xfs_dir2_leaf_entry *
 		(*leaf_ents_p)(struct xfs_dir2_leaf *lp);
 
@@ -97,10 +97,12 @@ struct xfs_dir_ops {
 				    struct xfs_dir3_icfree_hdr *from);
 	void	(*free_hdr_from_disk)(struct xfs_dir3_icfree_hdr *to,
 				      struct xfs_dir2_free *from);
-	int	(*free_max_bests)(struct xfs_mount *mp);
+	int	(*free_max_bests)(struct xfs_da_geometry *geo);
 	__be16 * (*free_bests_p)(struct xfs_dir2_free *free);
-	xfs_dir2_db_t (*db_to_fdb)(struct xfs_mount *mp, xfs_dir2_db_t db);
-	int	(*db_to_fdindex)(struct xfs_mount *mp, xfs_dir2_db_t db);
+	xfs_dir2_db_t (*db_to_fdb)(struct xfs_da_geometry *geo,
+				   xfs_dir2_db_t db);
+	int	(*db_to_fdindex)(struct xfs_da_geometry *geo,
+				 xfs_dir2_db_t db);
 };
 
 extern const struct xfs_dir_ops *
@@ -112,7 +114,9 @@ extern const struct xfs_dir_ops *
  * Generic directory interface routines
  */
 extern void xfs_dir_startup(void);
-extern void xfs_dir_mount(struct xfs_mount *mp);
+extern int xfs_da_mount(struct xfs_mount *mp);
+extern void xfs_da_unmount(struct xfs_mount *mp);
+
 extern int xfs_dir_isempty(struct xfs_inode *dp);
 extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_inode *pdp);
@@ -142,23 +146,23 @@ extern int xfs_dir2_sf_to_block(struct xfs_da_args *args);
 /*
  * Interface routines used by userspace utilities
  */
-extern int xfs_dir2_isblock(struct xfs_trans *tp, struct xfs_inode *dp, int *r);
-extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp, int *r);
+extern int xfs_dir2_isblock(struct xfs_da_args *args, int *r);
+extern int xfs_dir2_isleaf(struct xfs_da_args *args, int *r);
 extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
 				struct xfs_buf *bp);
 
 extern void xfs_dir2_data_freescan(struct xfs_inode *dp,
 		struct xfs_dir2_data_hdr *hdr, int *loghead);
-extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir2_data_log_entry(struct xfs_da_args *args,
 		struct xfs_buf *bp, struct xfs_dir2_data_entry *dep);
-extern void xfs_dir2_data_log_header(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir2_data_log_header(struct xfs_da_args *args,
 		struct xfs_buf *bp);
-extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_buf *bp,
-		struct xfs_dir2_data_unused *dup);
-extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir2_data_log_unused(struct xfs_da_args *args,
+		struct xfs_buf *bp, struct xfs_dir2_data_unused *dup);
+extern void xfs_dir2_data_make_free(struct xfs_da_args *args,
 		struct xfs_buf *bp, xfs_dir2_data_aoff_t offset,
 		xfs_dir2_data_aoff_t len, int *needlogp, int *needscanp);
-extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir2_data_use_free(struct xfs_da_args *args,
 		struct xfs_buf *bp, struct xfs_dir2_data_unused *dup,
 		xfs_dir2_data_aoff_t offset, xfs_dir2_data_aoff_t len,
 		int *needlogp, int *needscanp);
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 4f6a38cb83a..c7cd3154026 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -136,7 +136,7 @@ xfs_dir3_block_read(
 	struct xfs_mount	*mp = dp->i_mount;
 	int			err;
 
-	err = xfs_da_read_buf(tp, dp, mp->m_dirdatablk, -1, bpp,
+	err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp,
 				XFS_DATA_FORK, &xfs_dir3_block_buf_ops);
 	if (!err && tp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF);
@@ -281,8 +281,7 @@ out:
  */
 static void
 xfs_dir2_block_compact(
-	struct xfs_trans		*tp,
-	struct xfs_inode		*dp,
+	struct xfs_da_args		*args,
 	struct xfs_buf			*bp,
 	struct xfs_dir2_data_hdr	*hdr,
 	struct xfs_dir2_block_tail	*btp,
@@ -315,18 +314,17 @@ xfs_dir2_block_compact(
 	*lfloglow = toidx + 1 - (be32_to_cpu(btp->stale) - 1);
 	*lfloghigh -= be32_to_cpu(btp->stale) - 1;
 	be32_add_cpu(&btp->count, -(be32_to_cpu(btp->stale) - 1));
-	xfs_dir2_data_make_free(tp, dp, bp,
+	xfs_dir2_data_make_free(args, bp,
 		(xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
 		(xfs_dir2_data_aoff_t)((be32_to_cpu(btp->stale) - 1) * sizeof(*blp)),
 		needlog, &needscan);
-	blp += be32_to_cpu(btp->stale) - 1;
 	btp->stale = cpu_to_be32(1);
 	/*
 	 * If we now need to rebuild the bestfree map, do so.
 	 * This needs to happen before the next call to use_free.
 	 */
 	if (needscan)
-		xfs_dir2_data_freescan(dp, hdr, needlog);
+		xfs_dir2_data_freescan(args->dp, hdr, needlog);
 }
 
 /*
@@ -378,7 +376,7 @@ xfs_dir2_block_addname(
 	 * Set up pointers to parts of the block.
 	 */
 	hdr = bp->b_addr;
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(args->geo, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 
 	/*
@@ -421,7 +419,7 @@ xfs_dir2_block_addname(
 	 * If need to compact the leaf entries, do it now.
 	 */
 	if (compact) {
-		xfs_dir2_block_compact(tp, dp, bp, hdr, btp, blp, &needlog,
+		xfs_dir2_block_compact(args, bp, hdr, btp, blp, &needlog,
 				      &lfloghigh, &lfloglow);
 		/* recalculate blp post-compaction */
 		blp = xfs_dir2_block_leaf_p(btp);
@@ -456,7 +454,7 @@ xfs_dir2_block_addname(
 		/*
 		 * Mark the space needed for the new leaf entry, now in use.
 		 */
-		xfs_dir2_data_use_free(tp, dp, bp, enddup,
+		xfs_dir2_data_use_free(args, bp, enddup,
 			(xfs_dir2_data_aoff_t)
 			((char *)enddup - (char *)hdr + be16_to_cpu(enddup->length) -
 			 sizeof(*blp)),
@@ -537,13 +535,13 @@ xfs_dir2_block_addname(
 	 * Fill in the leaf entry.
 	 */
 	blp[mid].hashval = cpu_to_be32(args->hashval);
-	blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+	blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
 				(char *)dep - (char *)hdr));
 	xfs_dir2_block_log_leaf(tp, bp, lfloglow, lfloghigh);
 	/*
 	 * Mark space for the data entry used.
 	 */
-	xfs_dir2_data_use_free(tp, dp, bp, dup,
+	xfs_dir2_data_use_free(args, bp, dup,
 		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
 		(xfs_dir2_data_aoff_t)len, &needlog, &needscan);
 	/*
@@ -561,9 +559,9 @@ xfs_dir2_block_addname(
 	if (needscan)
 		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dp, bp);
+		xfs_dir2_data_log_header(args, bp);
 	xfs_dir2_block_log_tail(tp, bp);
-	xfs_dir2_data_log_entry(tp, dp, bp, dep);
+	xfs_dir2_data_log_entry(args, bp, dep);
 	xfs_dir3_data_check(dp, bp);
 	return 0;
 }
@@ -582,7 +580,7 @@ xfs_dir2_block_log_leaf(
 	xfs_dir2_leaf_entry_t	*blp;
 	xfs_dir2_block_tail_t	*btp;
 
-	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
+	btp = xfs_dir2_block_tail_p(tp->t_mountp->m_dir_geo, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	xfs_trans_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr),
 		(uint)((char *)&blp[last + 1] - (char *)hdr - 1));
@@ -599,7 +597,7 @@ xfs_dir2_block_log_tail(
 	xfs_dir2_data_hdr_t	*hdr = bp->b_addr;
 	xfs_dir2_block_tail_t	*btp;
 
-	btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr);
+	btp = xfs_dir2_block_tail_p(tp->t_mountp->m_dir_geo, hdr);
 	xfs_trans_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr),
 		(uint)((char *)(btp + 1) - (char *)hdr - 1));
 }
@@ -634,13 +632,14 @@ xfs_dir2_block_lookup(
 	mp = dp->i_mount;
 	hdr = bp->b_addr;
 	xfs_dir3_data_check(dp, bp);
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(args->geo, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
 	 * Get the offset from the leaf entry, to point to the data.
 	 */
 	dep = (xfs_dir2_data_entry_t *)((char *)hdr +
-		xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+			xfs_dir2_dataptr_to_off(args->geo,
+						be32_to_cpu(blp[ent].address)));
 	/*
 	 * Fill in inode number, CI name if appropriate, release the block.
 	 */
@@ -686,7 +685,7 @@ xfs_dir2_block_lookup_int(
 
 	hdr = bp->b_addr;
 	xfs_dir3_data_check(dp, bp);
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(args->geo, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
 	 * Loop doing a binary search for our hash value.
@@ -724,7 +723,7 @@ xfs_dir2_block_lookup_int(
 		 * Get pointer to the entry from the leaf.
 		 */
 		dep = (xfs_dir2_data_entry_t *)
-			((char *)hdr + xfs_dir2_dataptr_to_off(mp, addr));
+			((char *)hdr + xfs_dir2_dataptr_to_off(args->geo, addr));
 		/*
 		 * Compare name and if it's an exact match, return the index
 		 * and buffer. If it's the first case-insensitive match, store
@@ -791,18 +790,19 @@ xfs_dir2_block_removename(
 	tp = args->trans;
 	mp = dp->i_mount;
 	hdr = bp->b_addr;
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(args->geo, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
 	 * Point to the data entry using the leaf entry.
 	 */
-	dep = (xfs_dir2_data_entry_t *)
-	      ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+	dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+			xfs_dir2_dataptr_to_off(args->geo,
+						be32_to_cpu(blp[ent].address)));
 	/*
 	 * Mark the data entry's space free.
 	 */
 	needlog = needscan = 0;
-	xfs_dir2_data_make_free(tp, dp, bp,
+	xfs_dir2_data_make_free(args, bp,
 		(xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr),
 		dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
 	/*
@@ -821,7 +821,7 @@ xfs_dir2_block_removename(
 	if (needscan)
 		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dp, bp);
+		xfs_dir2_data_log_header(args, bp);
 	xfs_dir3_data_check(dp, bp);
 	/*
 	 * See if the size as a shortform is good enough.
@@ -866,20 +866,21 @@ xfs_dir2_block_replace(
 	dp = args->dp;
 	mp = dp->i_mount;
 	hdr = bp->b_addr;
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(args->geo, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	/*
 	 * Point to the data entry we need to change.
 	 */
-	dep = (xfs_dir2_data_entry_t *)
-	      ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address)));
+	dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+			xfs_dir2_dataptr_to_off(args->geo,
+						be32_to_cpu(blp[ent].address)));
 	ASSERT(be64_to_cpu(dep->inumber) != args->inumber);
 	/*
 	 * Change the inode number to the new value.
 	 */
 	dep->inumber = cpu_to_be64(args->inumber);
 	dp->d_ops->data_put_ftype(dep, args->filetype);
-	xfs_dir2_data_log_entry(args->trans, dp, bp, dep);
+	xfs_dir2_data_log_entry(args, bp, dep);
 	xfs_dir3_data_check(dp, bp);
 	return 0;
 }
@@ -939,7 +940,7 @@ xfs_dir2_leaf_to_block(
 	leaf = lbp->b_addr;
 	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 	ents = dp->d_ops->leaf_ents_p(leaf);
-	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
 
 	ASSERT(leafhdr.magic == XFS_DIR2_LEAF1_MAGIC ||
 	       leafhdr.magic == XFS_DIR3_LEAF1_MAGIC);
@@ -949,13 +950,13 @@ xfs_dir2_leaf_to_block(
 	 * been left behind during no-space-reservation operations.
 	 * These will show up in the leaf bests table.
 	 */
-	while (dp->i_d.di_size > mp->m_dirblksize) {
+	while (dp->i_d.di_size > args->geo->blksize) {
 		int hdrsz;
 
 		hdrsz = dp->d_ops->data_entry_offset;
 		bestsp = xfs_dir2_leaf_bests_p(ltp);
 		if (be16_to_cpu(bestsp[be32_to_cpu(ltp->bestcount) - 1]) ==
-					    mp->m_dirblksize - hdrsz) {
+					    args->geo->blksize - hdrsz) {
 			if ((error =
 			    xfs_dir2_leaf_trim_data(args, lbp,
 				    (xfs_dir2_db_t)(be32_to_cpu(ltp->bestcount) - 1))))
@@ -967,7 +968,7 @@ xfs_dir2_leaf_to_block(
 	 * Read the data block if we don't already have it, give up if it fails.
 	 */
 	if (!dbp) {
-		error = xfs_dir3_data_read(tp, dp, mp->m_dirdatablk, -1, &dbp);
+		error = xfs_dir3_data_read(tp, dp, args->geo->datablk, -1, &dbp);
 		if (error)
 			return error;
 	}
@@ -983,7 +984,7 @@ xfs_dir2_leaf_to_block(
 	/*
 	 * Look at the last data entry.
 	 */
-	tagp = (__be16 *)((char *)hdr + mp->m_dirblksize) - 1;
+	tagp = (__be16 *)((char *)hdr + args->geo->blksize) - 1;
 	dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp));
 	/*
 	 * If it's not free or is too short we can't do it.
@@ -1002,12 +1003,12 @@ xfs_dir2_leaf_to_block(
 	/*
 	 * Use up the space at the end of the block (blp/btp).
 	 */
-	xfs_dir2_data_use_free(tp, dp, dbp, dup, mp->m_dirblksize - size, size,
+	xfs_dir2_data_use_free(args, dbp, dup, args->geo->blksize - size, size,
 		&needlog, &needscan);
 	/*
 	 * Initialize the block tail.
 	 */
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(args->geo, hdr);
 	btp->count = cpu_to_be32(leafhdr.count - leafhdr.stale);
 	btp->stale = 0;
 	xfs_dir2_block_log_tail(tp, dbp);
@@ -1028,11 +1029,11 @@ xfs_dir2_leaf_to_block(
 	if (needscan)
 		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dp, dbp);
+		xfs_dir2_data_log_header(args, dbp);
 	/*
 	 * Pitch the old leaf block.
 	 */
-	error = xfs_da_shrink_inode(args, mp->m_dirleafblk, lbp);
+	error = xfs_da_shrink_inode(args, args->geo->leafblk, lbp);
 	if (error)
 		return error;
 
@@ -1141,13 +1142,13 @@ xfs_dir2_sf_to_block(
 	 */
 	dup = dp->d_ops->data_unused_p(hdr);
 	needlog = needscan = 0;
-	xfs_dir2_data_use_free(tp, dp, bp, dup, mp->m_dirblksize - i, i, &needlog,
-		&needscan);
+	xfs_dir2_data_use_free(args, bp, dup, args->geo->blksize - i,
+			       i, &needlog, &needscan);
 	ASSERT(needscan == 0);
 	/*
 	 * Fill in the tail.
 	 */
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(args->geo, hdr);
 	btp->count = cpu_to_be32(sfp->count + 2);	/* ., .. */
 	btp->stale = 0;
 	blp = xfs_dir2_block_leaf_p(btp);
@@ -1155,7 +1156,7 @@ xfs_dir2_sf_to_block(
 	/*
 	 * Remove the freespace, we'll manage it.
 	 */
-	xfs_dir2_data_use_free(tp, dp, bp, dup,
+	xfs_dir2_data_use_free(args, bp, dup,
 		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr),
 		be16_to_cpu(dup->length), &needlog, &needscan);
 	/*
@@ -1168,9 +1169,9 @@ xfs_dir2_sf_to_block(
 	dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
 	tagp = dp->d_ops->data_entry_tag_p(dep);
 	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
-	xfs_dir2_data_log_entry(tp, dp, bp, dep);
+	xfs_dir2_data_log_entry(args, bp, dep);
 	blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot);
-	blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+	blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
 				(char *)dep - (char *)hdr));
 	/*
 	 * Create entry for ..
@@ -1182,9 +1183,9 @@ xfs_dir2_sf_to_block(
 	dp->d_ops->data_put_ftype(dep, XFS_DIR3_FT_DIR);
 	tagp = dp->d_ops->data_entry_tag_p(dep);
 	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
-	xfs_dir2_data_log_entry(tp, dp, bp, dep);
+	xfs_dir2_data_log_entry(args, bp, dep);
 	blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
-	blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+	blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
 				(char *)dep - (char *)hdr));
 	offset = dp->d_ops->data_first_offset;
 	/*
@@ -1216,7 +1217,7 @@ xfs_dir2_sf_to_block(
 			dup->length = cpu_to_be16(newoffset - offset);
 			*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16(
 				((char *)dup - (char *)hdr));
-			xfs_dir2_data_log_unused(tp, bp, dup);
+			xfs_dir2_data_log_unused(args, bp, dup);
 			xfs_dir2_data_freeinsert(hdr,
 						 dp->d_ops->data_bestfree_p(hdr),
 						 dup, &dummy);
@@ -1233,12 +1234,12 @@ xfs_dir2_sf_to_block(
 		memcpy(dep->name, sfep->name, dep->namelen);
 		tagp = dp->d_ops->data_entry_tag_p(dep);
 		*tagp = cpu_to_be16((char *)dep - (char *)hdr);
-		xfs_dir2_data_log_entry(tp, dp, bp, dep);
+		xfs_dir2_data_log_entry(args, bp, dep);
 		name.name = sfep->name;
 		name.len = sfep->namelen;
 		blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops->
 							hashname(&name));
-		blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
+		blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(
 						 (char *)dep - (char *)hdr));
 		offset = (int)((char *)(tagp + 1) - (char *)hdr);
 		if (++i == sfp->count)
diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c
index afa4ad523f3..8c2f6422648 100644
--- a/fs/xfs/xfs_dir2_data.c
+++ b/fs/xfs/xfs_dir2_data.c
@@ -63,8 +63,10 @@ __xfs_dir3_data_check(
 	int			stale;		/* count of stale leaves */
 	struct xfs_name		name;
 	const struct xfs_dir_ops *ops;
+	struct xfs_da_geometry	*geo;
 
 	mp = bp->b_target->bt_mount;
+	geo = mp->m_dir_geo;
 
 	/*
 	 * We can be passed a null dp here from a verifier, so we need to go the
@@ -78,7 +80,7 @@ __xfs_dir3_data_check(
 	switch (hdr->magic) {
 	case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
 	case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
-		btp = xfs_dir2_block_tail_p(mp, hdr);
+		btp = xfs_dir2_block_tail_p(geo, hdr);
 		lep = xfs_dir2_block_leaf_p(btp);
 		endp = (char *)lep;
 
@@ -94,7 +96,7 @@ __xfs_dir3_data_check(
 		break;
 	case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
 	case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
-		endp = (char *)hdr + mp->m_dirblksize;
+		endp = (char *)hdr + geo->blksize;
 		break;
 	default:
 		XFS_ERROR_REPORT("Bad Magic", XFS_ERRLEVEL_LOW, mp);
@@ -172,9 +174,9 @@ __xfs_dir3_data_check(
 		lastfree = 0;
 		if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
 		    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
-			addr = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
-				(xfs_dir2_data_aoff_t)
-				((char *)dep - (char *)hdr));
+			addr = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
+						(xfs_dir2_data_aoff_t)
+						((char *)dep - (char *)hdr));
 			name.name = dep->name;
 			name.len = dep->namelen;
 			hash = mp->m_dirnameops->hashname(&name);
@@ -329,12 +331,11 @@ xfs_dir3_data_read(
 
 int
 xfs_dir3_data_readahead(
-	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
 	xfs_dablk_t		bno,
 	xfs_daddr_t		mapped_bno)
 {
-	return xfs_da_reada_buf(tp, dp, bno, mapped_bno,
+	return xfs_da_reada_buf(dp, bno, mapped_bno,
 				XFS_DATA_FORK, &xfs_dir3_data_reada_buf_ops);
 }
 
@@ -510,6 +511,7 @@ xfs_dir2_data_freescan(
 	struct xfs_dir2_data_free *bf;
 	char			*endp;		/* end of block's data */
 	char			*p;		/* current entry pointer */
+	struct xfs_da_geometry	*geo = dp->i_mount->m_dir_geo;
 
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
@@ -528,10 +530,10 @@ xfs_dir2_data_freescan(
 	p = (char *)dp->d_ops->data_entry_p(hdr);
 	if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
 	    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
-		btp = xfs_dir2_block_tail_p(dp->i_mount, hdr);
+		btp = xfs_dir2_block_tail_p(geo, hdr);
 		endp = (char *)xfs_dir2_block_leaf_p(btp);
 	} else
-		endp = (char *)hdr + dp->i_mount->m_dirblksize;
+		endp = (char *)hdr + geo->blksize;
 	/*
 	 * Loop over the block's entries.
 	 */
@@ -585,8 +587,8 @@ xfs_dir3_data_init(
 	/*
 	 * Get the buffer set up for the block.
 	 */
-	error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(mp, blkno), -1, &bp,
-		XFS_DATA_FORK);
+	error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, blkno),
+			       -1, &bp, XFS_DATA_FORK);
 	if (error)
 		return error;
 	bp->b_ops = &xfs_dir3_data_buf_ops;
@@ -621,15 +623,15 @@ xfs_dir3_data_init(
 	dup = dp->d_ops->data_unused_p(hdr);
 	dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
 
-	t = mp->m_dirblksize - (uint)dp->d_ops->data_entry_offset;
+	t = args->geo->blksize - (uint)dp->d_ops->data_entry_offset;
 	bf[0].length = cpu_to_be16(t);
 	dup->length = cpu_to_be16(t);
 	*xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16((char *)dup - (char *)hdr);
 	/*
 	 * Log it and return it.
 	 */
-	xfs_dir2_data_log_header(tp, dp, bp);
-	xfs_dir2_data_log_unused(tp, bp, dup);
+	xfs_dir2_data_log_header(args, bp);
+	xfs_dir2_data_log_unused(args, bp, dup);
 	*bpp = bp;
 	return 0;
 }
@@ -639,8 +641,7 @@ xfs_dir3_data_init(
  */
 void
 xfs_dir2_data_log_entry(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*dp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp,
 	xfs_dir2_data_entry_t	*dep)		/* data entry pointer */
 {
@@ -651,8 +652,8 @@ xfs_dir2_data_log_entry(
 	       hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
 
-	xfs_trans_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr),
-		(uint)((char *)(dp->d_ops->data_entry_tag_p(dep) + 1) -
+	xfs_trans_log_buf(args->trans, bp, (uint)((char *)dep - (char *)hdr),
+		(uint)((char *)(args->dp->d_ops->data_entry_tag_p(dep) + 1) -
 		       (char *)hdr - 1));
 }
 
@@ -661,8 +662,7 @@ xfs_dir2_data_log_entry(
  */
 void
 xfs_dir2_data_log_header(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*dp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp)
 {
 #ifdef DEBUG
@@ -674,7 +674,8 @@ xfs_dir2_data_log_header(
 	       hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
 #endif
 
-	xfs_trans_log_buf(tp, bp, 0, dp->d_ops->data_entry_offset - 1);
+	xfs_trans_log_buf(args->trans, bp, 0,
+			  args->dp->d_ops->data_entry_offset - 1);
 }
 
 /*
@@ -682,7 +683,7 @@ xfs_dir2_data_log_header(
  */
 void
 xfs_dir2_data_log_unused(
-	struct xfs_trans	*tp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp,
 	xfs_dir2_data_unused_t	*dup)		/* data unused pointer */
 {
@@ -696,13 +697,13 @@ xfs_dir2_data_log_unused(
 	/*
 	 * Log the first part of the unused entry.
 	 */
-	xfs_trans_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr),
+	xfs_trans_log_buf(args->trans, bp, (uint)((char *)dup - (char *)hdr),
 		(uint)((char *)&dup->length + sizeof(dup->length) -
 		       1 - (char *)hdr));
 	/*
 	 * Log the end (tag) of the unused entry.
 	 */
-	xfs_trans_log_buf(tp, bp,
+	xfs_trans_log_buf(args->trans, bp,
 		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr),
 		(uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr +
 		       sizeof(xfs_dir2_data_off_t) - 1));
@@ -714,8 +715,7 @@ xfs_dir2_data_log_unused(
  */
 void
 xfs_dir2_data_make_free(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*dp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp,
 	xfs_dir2_data_aoff_t	offset,		/* starting byte offset */
 	xfs_dir2_data_aoff_t	len,		/* length in bytes */
@@ -725,14 +725,12 @@ xfs_dir2_data_make_free(
 	xfs_dir2_data_hdr_t	*hdr;		/* data block pointer */
 	xfs_dir2_data_free_t	*dfp;		/* bestfree pointer */
 	char			*endptr;	/* end of data area */
-	xfs_mount_t		*mp;		/* filesystem mount point */
 	int			needscan;	/* need to regen bestfree */
 	xfs_dir2_data_unused_t	*newdup;	/* new unused entry */
 	xfs_dir2_data_unused_t	*postdup;	/* unused entry after us */
 	xfs_dir2_data_unused_t	*prevdup;	/* unused entry before us */
 	struct xfs_dir2_data_free *bf;
 
-	mp = tp->t_mountp;
 	hdr = bp->b_addr;
 
 	/*
@@ -740,20 +738,20 @@ xfs_dir2_data_make_free(
 	 */
 	if (hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	    hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC))
-		endptr = (char *)hdr + mp->m_dirblksize;
+		endptr = (char *)hdr + args->geo->blksize;
 	else {
 		xfs_dir2_block_tail_t	*btp;	/* block tail */
 
 		ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
 			hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
-		btp = xfs_dir2_block_tail_p(mp, hdr);
+		btp = xfs_dir2_block_tail_p(args->geo, hdr);
 		endptr = (char *)xfs_dir2_block_leaf_p(btp);
 	}
 	/*
 	 * If this isn't the start of the block, then back up to
 	 * the previous entry and see if it's free.
 	 */
-	if (offset > dp->d_ops->data_entry_offset) {
+	if (offset > args->dp->d_ops->data_entry_offset) {
 		__be16			*tagp;	/* tag just before us */
 
 		tagp = (__be16 *)((char *)hdr + offset) - 1;
@@ -779,7 +777,7 @@ xfs_dir2_data_make_free(
 	 * Previous and following entries are both free,
 	 * merge everything into a single free entry.
 	 */
-	bf = dp->d_ops->data_bestfree_p(hdr);
+	bf = args->dp->d_ops->data_bestfree_p(hdr);
 	if (prevdup && postdup) {
 		xfs_dir2_data_free_t	*dfp2;	/* another bestfree pointer */
 
@@ -801,7 +799,7 @@ xfs_dir2_data_make_free(
 		be16_add_cpu(&prevdup->length, len + be16_to_cpu(postdup->length));
 		*xfs_dir2_data_unused_tag_p(prevdup) =
 			cpu_to_be16((char *)prevdup - (char *)hdr);
-		xfs_dir2_data_log_unused(tp, bp, prevdup);
+		xfs_dir2_data_log_unused(args, bp, prevdup);
 		if (!needscan) {
 			/*
 			 * Has to be the case that entries 0 and 1 are
@@ -836,7 +834,7 @@ xfs_dir2_data_make_free(
 		be16_add_cpu(&prevdup->length, len);
 		*xfs_dir2_data_unused_tag_p(prevdup) =
 			cpu_to_be16((char *)prevdup - (char *)hdr);
-		xfs_dir2_data_log_unused(tp, bp, prevdup);
+		xfs_dir2_data_log_unused(args, bp, prevdup);
 		/*
 		 * If the previous entry was in the table, the new entry
 		 * is longer, so it will be in the table too.  Remove
@@ -864,7 +862,7 @@ xfs_dir2_data_make_free(
 		newdup->length = cpu_to_be16(len + be16_to_cpu(postdup->length));
 		*xfs_dir2_data_unused_tag_p(newdup) =
 			cpu_to_be16((char *)newdup - (char *)hdr);
-		xfs_dir2_data_log_unused(tp, bp, newdup);
+		xfs_dir2_data_log_unused(args, bp, newdup);
 		/*
 		 * If the following entry was in the table, the new entry
 		 * is longer, so it will be in the table too.  Remove
@@ -891,7 +889,7 @@ xfs_dir2_data_make_free(
 		newdup->length = cpu_to_be16(len);
 		*xfs_dir2_data_unused_tag_p(newdup) =
 			cpu_to_be16((char *)newdup - (char *)hdr);
-		xfs_dir2_data_log_unused(tp, bp, newdup);
+		xfs_dir2_data_log_unused(args, bp, newdup);
 		xfs_dir2_data_freeinsert(hdr, bf, newdup, needlogp);
 	}
 	*needscanp = needscan;
@@ -902,8 +900,7 @@ xfs_dir2_data_make_free(
  */
 void
 xfs_dir2_data_use_free(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*dp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp,
 	xfs_dir2_data_unused_t	*dup,		/* unused entry */
 	xfs_dir2_data_aoff_t	offset,		/* starting offset to use */
@@ -934,7 +931,7 @@ xfs_dir2_data_use_free(
 	 * Look up the entry in the bestfree table.
 	 */
 	oldlen = be16_to_cpu(dup->length);
-	bf = dp->d_ops->data_bestfree_p(hdr);
+	bf = args->dp->d_ops->data_bestfree_p(hdr);
 	dfp = xfs_dir2_data_freefind(hdr, bf, dup);
 	ASSERT(dfp || oldlen <= be16_to_cpu(bf[2].length));
 	/*
@@ -966,7 +963,7 @@ xfs_dir2_data_use_free(
 		newdup->length = cpu_to_be16(oldlen - len);
 		*xfs_dir2_data_unused_tag_p(newdup) =
 			cpu_to_be16((char *)newdup - (char *)hdr);
-		xfs_dir2_data_log_unused(tp, bp, newdup);
+		xfs_dir2_data_log_unused(args, bp, newdup);
 		/*
 		 * If it was in the table, remove it and add the new one.
 		 */
@@ -994,7 +991,7 @@ xfs_dir2_data_use_free(
 		newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup);
 		*xfs_dir2_data_unused_tag_p(newdup) =
 			cpu_to_be16((char *)newdup - (char *)hdr);
-		xfs_dir2_data_log_unused(tp, bp, newdup);
+		xfs_dir2_data_log_unused(args, bp, newdup);
 		/*
 		 * If it was in the table, remove it and add the new one.
 		 */
@@ -1022,13 +1019,13 @@ xfs_dir2_data_use_free(
 		newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup);
 		*xfs_dir2_data_unused_tag_p(newdup) =
 			cpu_to_be16((char *)newdup - (char *)hdr);
-		xfs_dir2_data_log_unused(tp, bp, newdup);
+		xfs_dir2_data_log_unused(args, bp, newdup);
 		newdup2 = (xfs_dir2_data_unused_t *)((char *)hdr + offset + len);
 		newdup2->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG);
 		newdup2->length = cpu_to_be16(oldlen - len - be16_to_cpu(newdup->length));
 		*xfs_dir2_data_unused_tag_p(newdup2) =
 			cpu_to_be16((char *)newdup2 - (char *)hdr);
-		xfs_dir2_data_log_unused(tp, bp, newdup2);
+		xfs_dir2_data_log_unused(args, bp, newdup2);
 		/*
 		 * If the old entry was in the table, we need to scan
 		 * if the 3rd entry was valid, since these entries
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index d36e97df118..fb0aad4440c 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -41,9 +41,10 @@
  */
 static int xfs_dir2_leaf_lookup_int(xfs_da_args_t *args, struct xfs_buf **lbpp,
 				    int *indexp, struct xfs_buf **dbpp);
-static void xfs_dir3_leaf_log_bests(struct xfs_trans *tp, struct xfs_buf *bp,
-				    int first, int last);
-static void xfs_dir3_leaf_log_tail(struct xfs_trans *tp, struct xfs_buf *bp);
+static void xfs_dir3_leaf_log_bests(struct xfs_da_args *args,
+				    struct xfs_buf *bp, int first, int last);
+static void xfs_dir3_leaf_log_tail(struct xfs_da_args *args,
+				   struct xfs_buf *bp);
 
 /*
  * Check the internal consistency of a leaf1 block.
@@ -92,6 +93,7 @@ xfs_dir3_leaf_check_int(
 	int			i;
 	const struct xfs_dir_ops *ops;
 	struct xfs_dir3_icleaf_hdr leafhdr;
+	struct xfs_da_geometry	*geo = mp->m_dir_geo;
 
 	/*
 	 * we can be passed a null dp here from a verifier, so we need to go the
@@ -105,14 +107,14 @@ xfs_dir3_leaf_check_int(
 	}
 
 	ents = ops->leaf_ents_p(leaf);
-	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+	ltp = xfs_dir2_leaf_tail_p(geo, leaf);
 
 	/*
 	 * XXX (dgc): This value is not restrictive enough.
 	 * Should factor in the size of the bests table as well.
 	 * We can deduce a value for that from di_size.
 	 */
-	if (hdr->count > ops->leaf_max_ents(mp))
+	if (hdr->count > ops->leaf_max_ents(geo))
 		return false;
 
 	/* Leaves and bests don't overlap in leaf format. */
@@ -323,7 +325,7 @@ xfs_dir3_leaf_init(
 	if (type == XFS_DIR2_LEAF1_MAGIC) {
 		struct xfs_dir2_leaf_tail *ltp;
 
-		ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+		ltp = xfs_dir2_leaf_tail_p(mp->m_dir_geo, leaf);
 		ltp->bestcount = 0;
 		bp->b_ops = &xfs_dir3_leaf1_buf_ops;
 		xfs_trans_buf_set_type(tp, bp, XFS_BLFT_DIR_LEAF1_BUF);
@@ -347,18 +349,18 @@ xfs_dir3_leaf_get_buf(
 	int			error;
 
 	ASSERT(magic == XFS_DIR2_LEAF1_MAGIC || magic == XFS_DIR2_LEAFN_MAGIC);
-	ASSERT(bno >= XFS_DIR2_LEAF_FIRSTDB(mp) &&
-	       bno < XFS_DIR2_FREE_FIRSTDB(mp));
+	ASSERT(bno >= xfs_dir2_byte_to_db(args->geo, XFS_DIR2_LEAF_OFFSET) &&
+	       bno < xfs_dir2_byte_to_db(args->geo, XFS_DIR2_FREE_OFFSET));
 
-	error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(mp, bno), -1, &bp,
-			       XFS_DATA_FORK);
+	error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, bno),
+			       -1, &bp, XFS_DATA_FORK);
 	if (error)
 		return error;
 
 	xfs_dir3_leaf_init(mp, tp, bp, dp->i_ino, magic);
-	xfs_dir3_leaf_log_header(tp, dp, bp);
+	xfs_dir3_leaf_log_header(args, bp);
 	if (magic == XFS_DIR2_LEAF1_MAGIC)
-		xfs_dir3_leaf_log_tail(tp, bp);
+		xfs_dir3_leaf_log_tail(args, bp);
 	*bpp = bp;
 	return 0;
 }
@@ -403,8 +405,8 @@ xfs_dir2_block_to_leaf(
 	if ((error = xfs_da_grow_inode(args, &blkno))) {
 		return error;
 	}
-	ldb = xfs_dir2_da_to_db(mp, blkno);
-	ASSERT(ldb == XFS_DIR2_LEAF_FIRSTDB(mp));
+	ldb = xfs_dir2_da_to_db(args->geo, blkno);
+	ASSERT(ldb == xfs_dir2_byte_to_db(args->geo, XFS_DIR2_LEAF_OFFSET));
 	/*
 	 * Initialize the leaf block, get a buffer for it.
 	 */
@@ -415,7 +417,7 @@ xfs_dir2_block_to_leaf(
 	leaf = lbp->b_addr;
 	hdr = dbp->b_addr;
 	xfs_dir3_data_check(dp, dbp);
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(args->geo, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 	bf = dp->d_ops->data_bestfree_p(hdr);
 	ents = dp->d_ops->leaf_ents_p(leaf);
@@ -427,23 +429,23 @@ xfs_dir2_block_to_leaf(
 	leafhdr.count = be32_to_cpu(btp->count);
 	leafhdr.stale = be32_to_cpu(btp->stale);
 	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, dp, lbp);
+	xfs_dir3_leaf_log_header(args, lbp);
 
 	/*
 	 * Could compact these but I think we always do the conversion
 	 * after squeezing out stale entries.
 	 */
 	memcpy(ents, blp, be32_to_cpu(btp->count) * sizeof(xfs_dir2_leaf_entry_t));
-	xfs_dir3_leaf_log_ents(tp, dp, lbp, 0, leafhdr.count - 1);
+	xfs_dir3_leaf_log_ents(args, lbp, 0, leafhdr.count - 1);
 	needscan = 0;
 	needlog = 1;
 	/*
 	 * Make the space formerly occupied by the leaf entries and block
 	 * tail be free.
 	 */
-	xfs_dir2_data_make_free(tp, dp, dbp,
+	xfs_dir2_data_make_free(args, dbp,
 		(xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr),
-		(xfs_dir2_data_aoff_t)((char *)hdr + mp->m_dirblksize -
+		(xfs_dir2_data_aoff_t)((char *)hdr + args->geo->blksize -
 				       (char *)blp),
 		&needlog, &needscan);
 	/*
@@ -461,7 +463,7 @@ xfs_dir2_block_to_leaf(
 	/*
 	 * Set up leaf tail and bests table.
 	 */
-	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
 	ltp->bestcount = cpu_to_be32(1);
 	bestsp = xfs_dir2_leaf_bests_p(ltp);
 	bestsp[0] =  bf[0].length;
@@ -469,10 +471,10 @@ xfs_dir2_block_to_leaf(
 	 * Log the data header and leaf bests table.
 	 */
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dp, dbp);
+		xfs_dir2_data_log_header(args, dbp);
 	xfs_dir3_leaf_check(dp, lbp);
 	xfs_dir3_data_check(dp, dbp);
-	xfs_dir3_leaf_log_bests(tp, lbp, 0, 0);
+	xfs_dir3_leaf_log_bests(args, lbp, 0, 0);
 	return 0;
 }
 
@@ -641,7 +643,7 @@ xfs_dir2_leaf_addname(
 	tp = args->trans;
 	mp = dp->i_mount;
 
-	error = xfs_dir3_leaf_read(tp, dp, mp->m_dirleafblk, -1, &lbp);
+	error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, -1, &lbp);
 	if (error)
 		return error;
 
@@ -653,7 +655,7 @@ xfs_dir2_leaf_addname(
 	 */
 	index = xfs_dir2_leaf_search_hash(args, lbp);
 	leaf = lbp->b_addr;
-	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
 	ents = dp->d_ops->leaf_ents_p(leaf);
 	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 	bestsp = xfs_dir2_leaf_bests_p(ltp);
@@ -670,7 +672,7 @@ xfs_dir2_leaf_addname(
 	     index++, lep++) {
 		if (be32_to_cpu(lep->address) == XFS_DIR2_NULL_DATAPTR)
 			continue;
-		i = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+		i = xfs_dir2_dataptr_to_db(args->geo, be32_to_cpu(lep->address));
 		ASSERT(i < be32_to_cpu(ltp->bestcount));
 		ASSERT(bestsp[i] != cpu_to_be16(NULLDATAOFF));
 		if (be16_to_cpu(bestsp[i]) >= length) {
@@ -810,14 +812,15 @@ xfs_dir2_leaf_addname(
 			memmove(&bestsp[0], &bestsp[1],
 				be32_to_cpu(ltp->bestcount) * sizeof(bestsp[0]));
 			be32_add_cpu(&ltp->bestcount, 1);
-			xfs_dir3_leaf_log_tail(tp, lbp);
-			xfs_dir3_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+			xfs_dir3_leaf_log_tail(args, lbp);
+			xfs_dir3_leaf_log_bests(args, lbp, 0,
+						be32_to_cpu(ltp->bestcount) - 1);
 		}
 		/*
 		 * If we're filling in a previously empty block just log it.
 		 */
 		else
-			xfs_dir3_leaf_log_bests(tp, lbp, use_block, use_block);
+			xfs_dir3_leaf_log_bests(args, lbp, use_block, use_block);
 		hdr = dbp->b_addr;
 		bf = dp->d_ops->data_bestfree_p(hdr);
 		bestsp[use_block] = bf[0].length;
@@ -828,8 +831,8 @@ xfs_dir2_leaf_addname(
 		 * Just read that one in.
 		 */
 		error = xfs_dir3_data_read(tp, dp,
-					   xfs_dir2_db_to_da(mp, use_block),
-					   -1, &dbp);
+				   xfs_dir2_db_to_da(args->geo, use_block),
+				   -1, &dbp);
 		if (error) {
 			xfs_trans_brelse(tp, lbp);
 			return error;
@@ -848,7 +851,7 @@ xfs_dir2_leaf_addname(
 	/*
 	 * Mark the initial part of our freespace in use for the new entry.
 	 */
-	xfs_dir2_data_use_free(tp, dp, dbp, dup,
+	xfs_dir2_data_use_free(args, dbp, dup,
 		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
 		&needlog, &needscan);
 	/*
@@ -870,8 +873,8 @@ xfs_dir2_leaf_addname(
 	 * Need to log the data block's header.
 	 */
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dp, dbp);
-	xfs_dir2_data_log_entry(tp, dp, dbp, dep);
+		xfs_dir2_data_log_header(args, dbp);
+	xfs_dir2_data_log_entry(args, dbp, dep);
 	/*
 	 * If the bests table needs to be changed, do it.
 	 * Log the change unless we've already done that.
@@ -879,7 +882,7 @@ xfs_dir2_leaf_addname(
 	if (be16_to_cpu(bestsp[use_block]) != be16_to_cpu(bf[0].length)) {
 		bestsp[use_block] = bf[0].length;
 		if (!grown)
-			xfs_dir3_leaf_log_bests(tp, lbp, use_block, use_block);
+			xfs_dir3_leaf_log_bests(args, lbp, use_block, use_block);
 	}
 
 	lep = xfs_dir3_leaf_find_entry(&leafhdr, ents, index, compact, lowstale,
@@ -889,14 +892,15 @@ xfs_dir2_leaf_addname(
 	 * Fill in the new leaf entry.
 	 */
 	lep->hashval = cpu_to_be32(args->hashval);
-	lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(mp, use_block,
+	lep->address = cpu_to_be32(
+				xfs_dir2_db_off_to_dataptr(args->geo, use_block,
 				be16_to_cpu(*tagp)));
 	/*
 	 * Log the leaf fields and give up the buffers.
 	 */
 	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, dp, lbp);
-	xfs_dir3_leaf_log_ents(tp, dp, lbp, lfloglow, lfloghigh);
+	xfs_dir3_leaf_log_header(args, lbp);
+	xfs_dir3_leaf_log_ents(args, lbp, lfloglow, lfloghigh);
 	xfs_dir3_leaf_check(dp, lbp);
 	xfs_dir3_data_check(dp, dbp);
 	return 0;
@@ -948,9 +952,9 @@ xfs_dir3_leaf_compact(
 	leafhdr->stale = 0;
 
 	dp->d_ops->leaf_hdr_to_disk(leaf, leafhdr);
-	xfs_dir3_leaf_log_header(args->trans, dp, bp);
+	xfs_dir3_leaf_log_header(args, bp);
 	if (loglow != -1)
-		xfs_dir3_leaf_log_ents(args->trans, dp, bp, loglow, to - 1);
+		xfs_dir3_leaf_log_ents(args, bp, loglow, to - 1);
 }
 
 /*
@@ -1052,7 +1056,7 @@ xfs_dir3_leaf_compact_x1(
  */
 static void
 xfs_dir3_leaf_log_bests(
-	xfs_trans_t		*tp,		/* transaction pointer */
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp,		/* leaf buffer */
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
@@ -1065,10 +1069,11 @@ xfs_dir3_leaf_log_bests(
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC));
 
-	ltp = xfs_dir2_leaf_tail_p(tp->t_mountp, leaf);
+	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
 	firstb = xfs_dir2_leaf_bests_p(ltp) + first;
 	lastb = xfs_dir2_leaf_bests_p(ltp) + last;
-	xfs_trans_log_buf(tp, bp, (uint)((char *)firstb - (char *)leaf),
+	xfs_trans_log_buf(args->trans, bp,
+		(uint)((char *)firstb - (char *)leaf),
 		(uint)((char *)lastb - (char *)leaf + sizeof(*lastb) - 1));
 }
 
@@ -1077,8 +1082,7 @@ xfs_dir3_leaf_log_bests(
  */
 void
 xfs_dir3_leaf_log_ents(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*dp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp,
 	int			first,
 	int			last)
@@ -1093,10 +1097,11 @@ xfs_dir3_leaf_log_ents(
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
 
-	ents = dp->d_ops->leaf_ents_p(leaf);
+	ents = args->dp->d_ops->leaf_ents_p(leaf);
 	firstlep = &ents[first];
 	lastlep = &ents[last];
-	xfs_trans_log_buf(tp, bp, (uint)((char *)firstlep - (char *)leaf),
+	xfs_trans_log_buf(args->trans, bp,
+		(uint)((char *)firstlep - (char *)leaf),
 		(uint)((char *)lastlep - (char *)leaf + sizeof(*lastlep) - 1));
 }
 
@@ -1105,8 +1110,7 @@ xfs_dir3_leaf_log_ents(
  */
 void
 xfs_dir3_leaf_log_header(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*dp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp)
 {
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
@@ -1116,8 +1120,9 @@ xfs_dir3_leaf_log_header(
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
 
-	xfs_trans_log_buf(tp, bp, (uint)((char *)&leaf->hdr - (char *)leaf),
-			  dp->d_ops->leaf_hdr_size - 1);
+	xfs_trans_log_buf(args->trans, bp,
+			  (uint)((char *)&leaf->hdr - (char *)leaf),
+			  args->dp->d_ops->leaf_hdr_size - 1);
 }
 
 /*
@@ -1125,21 +1130,20 @@ xfs_dir3_leaf_log_header(
  */
 STATIC void
 xfs_dir3_leaf_log_tail(
-	struct xfs_trans	*tp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp)
 {
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
 	xfs_dir2_leaf_tail_t	*ltp;		/* leaf tail structure */
-	struct xfs_mount	*mp = tp->t_mountp;
 
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAF1_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) ||
 	       leaf->hdr.info.magic == cpu_to_be16(XFS_DIR3_LEAFN_MAGIC));
 
-	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
-	xfs_trans_log_buf(tp, bp, (uint)((char *)ltp - (char *)leaf),
-		(uint)(mp->m_dirblksize - 1));
+	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
+	xfs_trans_log_buf(args->trans, bp, (uint)((char *)ltp - (char *)leaf),
+		(uint)(args->geo->blksize - 1));
 }
 
 /*
@@ -1185,7 +1189,7 @@ xfs_dir2_leaf_lookup(
 	 */
 	dep = (xfs_dir2_data_entry_t *)
 	      ((char *)dbp->b_addr +
-	       xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
+	       xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address)));
 	/*
 	 * Return the found inode number & CI name if appropriate
 	 */
@@ -1231,7 +1235,7 @@ xfs_dir2_leaf_lookup_int(
 	tp = args->trans;
 	mp = dp->i_mount;
 
-	error = xfs_dir3_leaf_read(tp, dp, mp->m_dirleafblk, -1, &lbp);
+	error = xfs_dir3_leaf_read(tp, dp, args->geo->leafblk, -1, &lbp);
 	if (error)
 		return error;
 
@@ -1260,7 +1264,8 @@ xfs_dir2_leaf_lookup_int(
 		/*
 		 * Get the new data block number.
 		 */
-		newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+		newdb = xfs_dir2_dataptr_to_db(args->geo,
+					       be32_to_cpu(lep->address));
 		/*
 		 * If it's not the same as the old data block number,
 		 * need to pitch the old one and read the new one.
@@ -1269,8 +1274,8 @@ xfs_dir2_leaf_lookup_int(
 			if (dbp)
 				xfs_trans_brelse(tp, dbp);
 			error = xfs_dir3_data_read(tp, dp,
-						   xfs_dir2_db_to_da(mp, newdb),
-						   -1, &dbp);
+					   xfs_dir2_db_to_da(args->geo, newdb),
+					   -1, &dbp);
 			if (error) {
 				xfs_trans_brelse(tp, lbp);
 				return error;
@@ -1281,7 +1286,8 @@ xfs_dir2_leaf_lookup_int(
 		 * Point to the data entry.
 		 */
 		dep = (xfs_dir2_data_entry_t *)((char *)dbp->b_addr +
-			xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+			xfs_dir2_dataptr_to_off(args->geo,
+						be32_to_cpu(lep->address)));
 		/*
 		 * Compare name and if it's an exact match, return the index
 		 * and buffer. If it's the first case-insensitive match, store
@@ -1310,8 +1316,8 @@ xfs_dir2_leaf_lookup_int(
 		if (cidb != curdb) {
 			xfs_trans_brelse(tp, dbp);
 			error = xfs_dir3_data_read(tp, dp,
-						   xfs_dir2_db_to_da(mp, cidb),
-						   -1, &dbp);
+					   xfs_dir2_db_to_da(args->geo, cidb),
+					   -1, &dbp);
 			if (error) {
 				xfs_trans_brelse(tp, lbp);
 				return error;
@@ -1380,18 +1386,18 @@ xfs_dir2_leaf_removename(
 	 * Point to the leaf entry, use that to point to the data entry.
 	 */
 	lep = &ents[index];
-	db = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
-	dep = (xfs_dir2_data_entry_t *)
-	      ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+	db = xfs_dir2_dataptr_to_db(args->geo, be32_to_cpu(lep->address));
+	dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+		xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address)));
 	needscan = needlog = 0;
 	oldbest = be16_to_cpu(bf[0].length);
-	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
 	bestsp = xfs_dir2_leaf_bests_p(ltp);
 	ASSERT(be16_to_cpu(bestsp[db]) == oldbest);
 	/*
 	 * Mark the former data entry unused.
 	 */
-	xfs_dir2_data_make_free(tp, dp, dbp,
+	xfs_dir2_data_make_free(args, dbp,
 		(xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr),
 		dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
 	/*
@@ -1399,10 +1405,10 @@ xfs_dir2_leaf_removename(
 	 */
 	leafhdr.stale++;
 	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, dp, lbp);
+	xfs_dir3_leaf_log_header(args, lbp);
 
 	lep->address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
-	xfs_dir3_leaf_log_ents(tp, dp, lbp, index, index);
+	xfs_dir3_leaf_log_ents(args, lbp, index, index);
 
 	/*
 	 * Scan the freespace in the data block again if necessary,
@@ -1411,22 +1417,22 @@ xfs_dir2_leaf_removename(
 	if (needscan)
 		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dp, dbp);
+		xfs_dir2_data_log_header(args, dbp);
 	/*
 	 * If the longest freespace in the data block has changed,
 	 * put the new value in the bests table and log that.
 	 */
 	if (be16_to_cpu(bf[0].length) != oldbest) {
 		bestsp[db] = bf[0].length;
-		xfs_dir3_leaf_log_bests(tp, lbp, db, db);
+		xfs_dir3_leaf_log_bests(args, lbp, db, db);
 	}
 	xfs_dir3_data_check(dp, dbp);
 	/*
 	 * If the data block is now empty then get rid of the data block.
 	 */
 	if (be16_to_cpu(bf[0].length) ==
-			mp->m_dirblksize - dp->d_ops->data_entry_offset) {
-		ASSERT(db != mp->m_dirdatablk);
+			args->geo->blksize - dp->d_ops->data_entry_offset) {
+		ASSERT(db != args->geo->datablk);
 		if ((error = xfs_dir2_shrink_inode(args, db, dbp))) {
 			/*
 			 * Nope, can't get rid of it because it caused
@@ -1459,15 +1465,16 @@ xfs_dir2_leaf_removename(
 			memmove(&bestsp[db - i], bestsp,
 				(be32_to_cpu(ltp->bestcount) - (db - i)) * sizeof(*bestsp));
 			be32_add_cpu(&ltp->bestcount, -(db - i));
-			xfs_dir3_leaf_log_tail(tp, lbp);
-			xfs_dir3_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+			xfs_dir3_leaf_log_tail(args, lbp);
+			xfs_dir3_leaf_log_bests(args, lbp, 0,
+						be32_to_cpu(ltp->bestcount) - 1);
 		} else
 			bestsp[db] = cpu_to_be16(NULLDATAOFF);
 	}
 	/*
 	 * If the data block was not the first one, drop it.
 	 */
-	else if (db != mp->m_dirdatablk)
+	else if (db != args->geo->datablk)
 		dbp = NULL;
 
 	xfs_dir3_leaf_check(dp, lbp);
@@ -1515,7 +1522,7 @@ xfs_dir2_leaf_replace(
 	 */
 	dep = (xfs_dir2_data_entry_t *)
 	      ((char *)dbp->b_addr +
-	       xfs_dir2_dataptr_to_off(dp->i_mount, be32_to_cpu(lep->address)));
+	       xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address)));
 	ASSERT(args->inumber != be64_to_cpu(dep->inumber));
 	/*
 	 * Put the new inode number in, log it.
@@ -1523,7 +1530,7 @@ xfs_dir2_leaf_replace(
 	dep->inumber = cpu_to_be64(args->inumber);
 	dp->d_ops->data_put_ftype(dep, args->filetype);
 	tp = args->trans;
-	xfs_dir2_data_log_entry(tp, dp, dbp, dep);
+	xfs_dir2_data_log_entry(args, dbp, dep);
 	xfs_dir3_leaf_check(dp, lbp);
 	xfs_trans_brelse(tp, lbp);
 	return 0;
@@ -1609,12 +1616,13 @@ xfs_dir2_leaf_trim_data(
 	/*
 	 * Read the offending data block.  We need its buffer.
 	 */
-	error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(mp, db), -1, &dbp);
+	error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(args->geo, db),
+				   -1, &dbp);
 	if (error)
 		return error;
 
 	leaf = lbp->b_addr;
-	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
 
 #ifdef DEBUG
 {
@@ -1624,7 +1632,7 @@ xfs_dir2_leaf_trim_data(
 	ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
 	       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
 	ASSERT(be16_to_cpu(bf[0].length) ==
-	       mp->m_dirblksize - dp->d_ops->data_entry_offset);
+	       args->geo->blksize - dp->d_ops->data_entry_offset);
 	ASSERT(db == be32_to_cpu(ltp->bestcount) - 1);
 }
 #endif
@@ -1643,8 +1651,8 @@ xfs_dir2_leaf_trim_data(
 	bestsp = xfs_dir2_leaf_bests_p(ltp);
 	be32_add_cpu(&ltp->bestcount, -1);
 	memmove(&bestsp[1], &bestsp[0], be32_to_cpu(ltp->bestcount) * sizeof(*bestsp));
-	xfs_dir3_leaf_log_tail(tp, lbp);
-	xfs_dir3_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+	xfs_dir3_leaf_log_tail(args, lbp);
+	xfs_dir3_leaf_log_bests(args, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
 	return 0;
 }
 
@@ -1708,22 +1716,22 @@ xfs_dir2_node_to_leaf(
 	/*
 	 * Get the last offset in the file.
 	 */
-	if ((error = xfs_bmap_last_offset(tp, dp, &fo, XFS_DATA_FORK))) {
+	if ((error = xfs_bmap_last_offset(dp, &fo, XFS_DATA_FORK))) {
 		return error;
 	}
-	fo -= mp->m_dirblkfsbs;
+	fo -= args->geo->fsbcount;
 	/*
 	 * If there are freespace blocks other than the first one,
 	 * take this opportunity to remove trailing empty freespace blocks
 	 * that may have been left behind during no-space-reservation
 	 * operations.
 	 */
-	while (fo > mp->m_dirfreeblk) {
+	while (fo > args->geo->freeblk) {
 		if ((error = xfs_dir2_node_trim_free(args, fo, &rval))) {
 			return error;
 		}
 		if (rval)
-			fo -= mp->m_dirblkfsbs;
+			fo -= args->geo->fsbcount;
 		else
 			return 0;
 	}
@@ -1736,7 +1744,7 @@ xfs_dir2_node_to_leaf(
 	/*
 	 * If it's not the single leaf block, give up.
 	 */
-	if (XFS_FSB_TO_B(mp, fo) > XFS_DIR2_LEAF_OFFSET + mp->m_dirblksize)
+	if (XFS_FSB_TO_B(mp, fo) > XFS_DIR2_LEAF_OFFSET + args->geo->blksize)
 		return 0;
 	lbp = state->path.blk[0].bp;
 	leaf = lbp->b_addr;
@@ -1748,7 +1756,7 @@ xfs_dir2_node_to_leaf(
 	/*
 	 * Read the freespace block.
 	 */
-	error = xfs_dir2_free_read(tp, dp,  mp->m_dirfreeblk, &fbp);
+	error = xfs_dir2_free_read(tp, dp,  args->geo->freeblk, &fbp);
 	if (error)
 		return error;
 	free = fbp->b_addr;
@@ -1760,7 +1768,7 @@ xfs_dir2_node_to_leaf(
 	 * Now see if the leafn and free data will fit in a leaf1.
 	 * If not, release the buffer and give up.
 	 */
-	if (xfs_dir3_leaf_size(&leafhdr, freehdr.nvalid) > mp->m_dirblksize) {
+	if (xfs_dir3_leaf_size(&leafhdr, freehdr.nvalid) > args->geo->blksize) {
 		xfs_trans_brelse(tp, fbp);
 		return 0;
 	}
@@ -1780,7 +1788,7 @@ xfs_dir2_node_to_leaf(
 	/*
 	 * Set up the leaf tail from the freespace block.
 	 */
-	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
 	ltp->bestcount = cpu_to_be32(freehdr.nvalid);
 
 	/*
@@ -1790,15 +1798,17 @@ xfs_dir2_node_to_leaf(
 		freehdr.nvalid * sizeof(xfs_dir2_data_off_t));
 
 	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, dp, lbp);
-	xfs_dir3_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
-	xfs_dir3_leaf_log_tail(tp, lbp);
+	xfs_dir3_leaf_log_header(args, lbp);
+	xfs_dir3_leaf_log_bests(args, lbp, 0, be32_to_cpu(ltp->bestcount) - 1);
+	xfs_dir3_leaf_log_tail(args, lbp);
 	xfs_dir3_leaf_check(dp, lbp);
 
 	/*
 	 * Get rid of the freespace block.
 	 */
-	error = xfs_dir2_shrink_inode(args, XFS_DIR2_FREE_FIRSTDB(mp), fbp);
+	error = xfs_dir2_shrink_inode(args,
+			xfs_dir2_byte_to_db(args->geo, XFS_DIR2_FREE_OFFSET),
+			fbp);
 	if (error) {
 		/*
 		 * This can't fail here because it can only happen when
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index cb434d73268..da43d304fca 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -195,17 +195,18 @@ xfs_dir2_free_try_read(
 
 static int
 xfs_dir3_free_get_buf(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*dp,
+	xfs_da_args_t		*args,
 	xfs_dir2_db_t		fbno,
 	struct xfs_buf		**bpp)
 {
+	struct xfs_trans	*tp = args->trans;
+	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_buf		*bp;
 	int			error;
 	struct xfs_dir3_icfree_hdr hdr;
 
-	error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(mp, fbno),
+	error = xfs_da_get_buf(tp, dp, xfs_dir2_db_to_da(args->geo, fbno),
 				   -1, &bp, XFS_DATA_FORK);
 	if (error)
 		return error;
@@ -240,8 +241,7 @@ xfs_dir3_free_get_buf(
  */
 STATIC void
 xfs_dir2_free_log_bests(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*dp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp,
 	int			first,		/* first entry to log */
 	int			last)		/* last entry to log */
@@ -250,10 +250,10 @@ xfs_dir2_free_log_bests(
 	__be16			*bests;
 
 	free = bp->b_addr;
-	bests = dp->d_ops->free_bests_p(free);
+	bests = args->dp->d_ops->free_bests_p(free);
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
 	       free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
-	xfs_trans_log_buf(tp, bp,
+	xfs_trans_log_buf(args->trans, bp,
 		(uint)((char *)&bests[first] - (char *)free),
 		(uint)((char *)&bests[last] - (char *)free +
 		       sizeof(bests[0]) - 1));
@@ -264,8 +264,7 @@ xfs_dir2_free_log_bests(
  */
 static void
 xfs_dir2_free_log_header(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*dp,
+	struct xfs_da_args	*args,
 	struct xfs_buf		*bp)
 {
 #ifdef DEBUG
@@ -275,7 +274,8 @@ xfs_dir2_free_log_header(
 	ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC) ||
 	       free->hdr.magic == cpu_to_be32(XFS_DIR3_FREE_MAGIC));
 #endif
-	xfs_trans_log_buf(tp, bp, 0, dp->d_ops->free_hdr_size - 1);
+	xfs_trans_log_buf(args->trans, bp, 0,
+			  args->dp->d_ops->free_hdr_size - 1);
 }
 
 /*
@@ -315,20 +315,20 @@ xfs_dir2_leaf_to_node(
 	if ((error = xfs_dir2_grow_inode(args, XFS_DIR2_FREE_SPACE, &fdb))) {
 		return error;
 	}
-	ASSERT(fdb == XFS_DIR2_FREE_FIRSTDB(mp));
+	ASSERT(fdb == xfs_dir2_byte_to_db(args->geo, XFS_DIR2_FREE_OFFSET));
 	/*
 	 * Get the buffer for the new freespace block.
 	 */
-	error = xfs_dir3_free_get_buf(tp, dp, fdb, &fbp);
+	error = xfs_dir3_free_get_buf(args, fdb, &fbp);
 	if (error)
 		return error;
 
 	free = fbp->b_addr;
 	dp->d_ops->free_hdr_from_disk(&freehdr, free);
 	leaf = lbp->b_addr;
-	ltp = xfs_dir2_leaf_tail_p(mp, leaf);
+	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
 	ASSERT(be32_to_cpu(ltp->bestcount) <=
-				(uint)dp->i_d.di_size / mp->m_dirblksize);
+				(uint)dp->i_d.di_size / args->geo->blksize);
 
 	/*
 	 * Copy freespace entries from the leaf block to the new block.
@@ -349,8 +349,8 @@ xfs_dir2_leaf_to_node(
 	freehdr.nvalid = be32_to_cpu(ltp->bestcount);
 
 	dp->d_ops->free_hdr_to_disk(fbp->b_addr, &freehdr);
-	xfs_dir2_free_log_bests(tp, dp, fbp, 0, freehdr.nvalid - 1);
-	xfs_dir2_free_log_header(tp, dp, fbp);
+	xfs_dir2_free_log_bests(args, fbp, 0, freehdr.nvalid - 1);
+	xfs_dir2_free_log_header(args, fbp);
 
 	/*
 	 * Converting the leaf to a leafnode is just a matter of changing the
@@ -364,7 +364,7 @@ xfs_dir2_leaf_to_node(
 		leaf->hdr.info.magic = cpu_to_be16(XFS_DIR3_LEAFN_MAGIC);
 	lbp->b_ops = &xfs_dir3_leafn_buf_ops;
 	xfs_trans_buf_set_type(tp, lbp, XFS_BLFT_DIR_LEAFN_BUF);
-	xfs_dir3_leaf_log_header(tp, dp, lbp);
+	xfs_dir3_leaf_log_header(args, lbp);
 	xfs_dir3_leaf_check(dp, lbp);
 	return 0;
 }
@@ -415,7 +415,7 @@ xfs_dir2_leafn_add(
 	 * a compact.
 	 */
 
-	if (leafhdr.count == dp->d_ops->leaf_max_ents(mp)) {
+	if (leafhdr.count == dp->d_ops->leaf_max_ents(args->geo)) {
 		if (!leafhdr.stale)
 			return XFS_ERROR(ENOSPC);
 		compact = leafhdr.stale > 1;
@@ -450,12 +450,12 @@ xfs_dir2_leafn_add(
 				       highstale, &lfloglow, &lfloghigh);
 
 	lep->hashval = cpu_to_be32(args->hashval);
-	lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(mp,
+	lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(args->geo,
 				args->blkno, args->index));
 
 	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, dp, bp);
-	xfs_dir3_leaf_log_ents(tp, dp, bp, lfloglow, lfloghigh);
+	xfs_dir3_leaf_log_header(args, bp);
+	xfs_dir3_leaf_log_ents(args, bp, lfloglow, lfloghigh);
 	xfs_dir3_leaf_check(dp, bp);
 	return 0;
 }
@@ -471,7 +471,8 @@ xfs_dir2_free_hdr_check(
 
 	dp->d_ops->free_hdr_from_disk(&hdr, bp->b_addr);
 
-	ASSERT((hdr.firstdb % dp->d_ops->free_max_bests(dp->i_mount)) == 0);
+	ASSERT((hdr.firstdb %
+		dp->d_ops->free_max_bests(dp->i_mount->m_dir_geo)) == 0);
 	ASSERT(hdr.firstdb <= db);
 	ASSERT(db < hdr.firstdb + hdr.nvalid);
 }
@@ -576,7 +577,8 @@ xfs_dir2_leafn_lookup_for_addname(
 		/*
 		 * Pull the data block number from the entry.
 		 */
-		newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+		newdb = xfs_dir2_dataptr_to_db(args->geo,
+					       be32_to_cpu(lep->address));
 		/*
 		 * For addname, we're looking for a place to put the new entry.
 		 * We want to use a data block with an entry of equal
@@ -593,7 +595,7 @@ xfs_dir2_leafn_lookup_for_addname(
 			 * Convert the data block to the free block
 			 * holding its freespace information.
 			 */
-			newfdb = dp->d_ops->db_to_fdb(mp, newdb);
+			newfdb = dp->d_ops->db_to_fdb(args->geo, newdb);
 			/*
 			 * If it's not the one we have in hand, read it in.
 			 */
@@ -605,7 +607,8 @@ xfs_dir2_leafn_lookup_for_addname(
 					xfs_trans_brelse(tp, curbp);
 
 				error = xfs_dir2_free_read(tp, dp,
-						xfs_dir2_db_to_da(mp, newfdb),
+						xfs_dir2_db_to_da(args->geo,
+								  newfdb),
 						&curbp);
 				if (error)
 					return error;
@@ -616,7 +619,7 @@ xfs_dir2_leafn_lookup_for_addname(
 			/*
 			 * Get the index for our entry.
 			 */
-			fi = dp->d_ops->db_to_fdindex(mp, curdb);
+			fi = dp->d_ops->db_to_fdindex(args->geo, curdb);
 			/*
 			 * If it has room, return it.
 			 */
@@ -721,7 +724,8 @@ xfs_dir2_leafn_lookup_for_entry(
 		/*
 		 * Pull the data block number from the entry.
 		 */
-		newdb = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+		newdb = xfs_dir2_dataptr_to_db(args->geo,
+					       be32_to_cpu(lep->address));
 		/*
 		 * Not adding a new entry, so we really want to find
 		 * the name given to us.
@@ -746,7 +750,8 @@ xfs_dir2_leafn_lookup_for_entry(
 				curbp = state->extrablk.bp;
 			} else {
 				error = xfs_dir3_data_read(tp, dp,
-						xfs_dir2_db_to_da(mp, newdb),
+						xfs_dir2_db_to_da(args->geo,
+								  newdb),
 						-1, &curbp);
 				if (error)
 					return error;
@@ -758,7 +763,8 @@ xfs_dir2_leafn_lookup_for_entry(
 		 * Point to the data entry.
 		 */
 		dep = (xfs_dir2_data_entry_t *)((char *)curbp->b_addr +
-			xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address)));
+			xfs_dir2_dataptr_to_off(args->geo,
+						be32_to_cpu(lep->address)));
 		/*
 		 * Compare the entry and if it's an exact match, return
 		 * EEXIST immediately. If it's the first case-insensitive
@@ -844,7 +850,6 @@ xfs_dir3_leafn_moveents(
 	int				start_d,/* destination leaf index */
 	int				count)	/* count of leaves to copy */
 {
-	struct xfs_trans		*tp = args->trans;
 	int				stale;	/* count stale leaves copied */
 
 	trace_xfs_dir2_leafn_moveents(args, start_s, start_d, count);
@@ -863,7 +868,7 @@ xfs_dir3_leafn_moveents(
 	if (start_d < dhdr->count) {
 		memmove(&dents[start_d + count], &dents[start_d],
 			(dhdr->count - start_d) * sizeof(xfs_dir2_leaf_entry_t));
-		xfs_dir3_leaf_log_ents(tp, args->dp, bp_d, start_d + count,
+		xfs_dir3_leaf_log_ents(args, bp_d, start_d + count,
 				       count + dhdr->count - 1);
 	}
 	/*
@@ -885,8 +890,7 @@ xfs_dir3_leafn_moveents(
 	 */
 	memcpy(&dents[start_d], &sents[start_s],
 		count * sizeof(xfs_dir2_leaf_entry_t));
-	xfs_dir3_leaf_log_ents(tp, args->dp, bp_d,
-			       start_d, start_d + count - 1);
+	xfs_dir3_leaf_log_ents(args, bp_d, start_d, start_d + count - 1);
 
 	/*
 	 * If there are source entries after the ones we copied,
@@ -895,8 +899,7 @@ xfs_dir3_leafn_moveents(
 	if (start_s + count < shdr->count) {
 		memmove(&sents[start_s], &sents[start_s + count],
 			count * sizeof(xfs_dir2_leaf_entry_t));
-		xfs_dir3_leaf_log_ents(tp, args->dp, bp_s,
-				       start_s, start_s + count - 1);
+		xfs_dir3_leaf_log_ents(args, bp_s, start_s, start_s + count - 1);
 	}
 
 	/*
@@ -1032,8 +1035,8 @@ xfs_dir2_leafn_rebalance(
 	/* log the changes made when moving the entries */
 	dp->d_ops->leaf_hdr_to_disk(leaf1, &hdr1);
 	dp->d_ops->leaf_hdr_to_disk(leaf2, &hdr2);
-	xfs_dir3_leaf_log_header(args->trans, dp, blk1->bp);
-	xfs_dir3_leaf_log_header(args->trans, dp, blk2->bp);
+	xfs_dir3_leaf_log_header(args, blk1->bp);
+	xfs_dir3_leaf_log_header(args, blk2->bp);
 
 	xfs_dir3_leaf_check(dp, blk1->bp);
 	xfs_dir3_leaf_check(dp, blk2->bp);
@@ -1076,7 +1079,6 @@ xfs_dir3_data_block_free(
 	struct xfs_buf		*fbp,
 	int			longest)
 {
-	struct xfs_trans	*tp = args->trans;
 	int			logfree = 0;
 	__be16			*bests;
 	struct xfs_dir3_icfree_hdr freehdr;
@@ -1090,7 +1092,7 @@ xfs_dir3_data_block_free(
 		 * value.
 		 */
 		bests[findex] = cpu_to_be16(longest);
-		xfs_dir2_free_log_bests(tp, dp, fbp, findex, findex);
+		xfs_dir2_free_log_bests(args, fbp, findex, findex);
 		return 0;
 	}
 
@@ -1118,7 +1120,7 @@ xfs_dir3_data_block_free(
 	}
 
 	dp->d_ops->free_hdr_to_disk(free, &freehdr);
-	xfs_dir2_free_log_header(tp, dp, fbp);
+	xfs_dir2_free_log_header(args, fbp);
 
 	/*
 	 * If there are no useful entries left in the block, get rid of the
@@ -1142,7 +1144,7 @@ xfs_dir3_data_block_free(
 
 	/* Log the free entry that changed, unless we got rid of it.  */
 	if (logfree)
-		xfs_dir2_free_log_bests(tp, dp, fbp, findex, findex);
+		xfs_dir2_free_log_bests(args, fbp, findex, findex);
 	return 0;
 }
 
@@ -1193,9 +1195,9 @@ xfs_dir2_leafn_remove(
 	/*
 	 * Extract the data block and offset from the entry.
 	 */
-	db = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address));
+	db = xfs_dir2_dataptr_to_db(args->geo, be32_to_cpu(lep->address));
 	ASSERT(dblk->blkno == db);
-	off = xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address));
+	off = xfs_dir2_dataptr_to_off(args->geo, be32_to_cpu(lep->address));
 	ASSERT(dblk->index == off);
 
 	/*
@@ -1204,10 +1206,10 @@ xfs_dir2_leafn_remove(
 	 */
 	leafhdr.stale++;
 	dp->d_ops->leaf_hdr_to_disk(leaf, &leafhdr);
-	xfs_dir3_leaf_log_header(tp, dp, bp);
+	xfs_dir3_leaf_log_header(args, bp);
 
 	lep->address = cpu_to_be32(XFS_DIR2_NULL_DATAPTR);
-	xfs_dir3_leaf_log_ents(tp, dp, bp, index, index);
+	xfs_dir3_leaf_log_ents(args, bp, index, index);
 
 	/*
 	 * Make the data entry free.  Keep track of the longest freespace
@@ -1219,7 +1221,7 @@ xfs_dir2_leafn_remove(
 	bf = dp->d_ops->data_bestfree_p(hdr);
 	longest = be16_to_cpu(bf[0].length);
 	needlog = needscan = 0;
-	xfs_dir2_data_make_free(tp, dp, dbp, off,
+	xfs_dir2_data_make_free(args, dbp, off,
 		dp->d_ops->data_entsize(dep->namelen), &needlog, &needscan);
 	/*
 	 * Rescan the data block freespaces for bestfree.
@@ -1228,7 +1230,7 @@ xfs_dir2_leafn_remove(
 	if (needscan)
 		xfs_dir2_data_freescan(dp, hdr, &needlog);
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dp, dbp);
+		xfs_dir2_data_log_header(args, dbp);
 	xfs_dir3_data_check(dp, dbp);
 	/*
 	 * If the longest data block freespace changes, need to update
@@ -1245,8 +1247,9 @@ xfs_dir2_leafn_remove(
 		 * Convert the data block number to a free block,
 		 * read in the free block.
 		 */
-		fdb = dp->d_ops->db_to_fdb(mp, db);
-		error = xfs_dir2_free_read(tp, dp, xfs_dir2_db_to_da(mp, fdb),
+		fdb = dp->d_ops->db_to_fdb(args->geo, db);
+		error = xfs_dir2_free_read(tp, dp,
+					   xfs_dir2_db_to_da(args->geo, fdb),
 					   &fbp);
 		if (error)
 			return error;
@@ -1255,20 +1258,21 @@ xfs_dir2_leafn_remove(
 	{
 		struct xfs_dir3_icfree_hdr freehdr;
 		dp->d_ops->free_hdr_from_disk(&freehdr, free);
-		ASSERT(freehdr.firstdb == dp->d_ops->free_max_bests(mp) *
-					  (fdb - XFS_DIR2_FREE_FIRSTDB(mp)));
+		ASSERT(freehdr.firstdb == dp->d_ops->free_max_bests(args->geo) *
+			(fdb - xfs_dir2_byte_to_db(args->geo,
+						   XFS_DIR2_FREE_OFFSET)));
 	}
 #endif
 		/*
 		 * Calculate which entry we need to fix.
 		 */
-		findex = dp->d_ops->db_to_fdindex(mp, db);
+		findex = dp->d_ops->db_to_fdindex(args->geo, db);
 		longest = be16_to_cpu(bf[0].length);
 		/*
 		 * If the data block is now empty we can get rid of it
 		 * (usually).
 		 */
-		if (longest == mp->m_dirblksize -
+		if (longest == args->geo->blksize -
 			       dp->d_ops->data_entry_offset) {
 			/*
 			 * Try to punch out the data block.
@@ -1303,7 +1307,7 @@ xfs_dir2_leafn_remove(
 	 */
 	*rval = (dp->d_ops->leaf_hdr_size +
 		 (uint)sizeof(ents[0]) * (leafhdr.count - leafhdr.stale)) <
-		mp->m_dir_magicpct;
+		args->geo->magicpct;
 	return 0;
 }
 
@@ -1336,7 +1340,7 @@ xfs_dir2_leafn_split(
 	/*
 	 * Initialize the new leaf block.
 	 */
-	error = xfs_dir3_leaf_get_buf(args, xfs_dir2_da_to_db(mp, blkno),
+	error = xfs_dir3_leaf_get_buf(args, xfs_dir2_da_to_db(args->geo, blkno),
 				      &newblk->bp, XFS_DIR2_LEAFN_MAGIC);
 	if (error)
 		return error;
@@ -1410,7 +1414,7 @@ xfs_dir2_leafn_toosmall(
 
 	count = leafhdr.count - leafhdr.stale;
 	bytes = dp->d_ops->leaf_hdr_size + count * sizeof(ents[0]);
-	if (bytes > (state->blocksize >> 1)) {
+	if (bytes > (state->args->geo->blksize >> 1)) {
 		/*
 		 * Blk over 50%, don't try to join.
 		 */
@@ -1463,7 +1467,8 @@ xfs_dir2_leafn_toosmall(
 		 * Count bytes in the two blocks combined.
 		 */
 		count = leafhdr.count - leafhdr.stale;
-		bytes = state->blocksize - (state->blocksize >> 2);
+		bytes = state->args->geo->blksize -
+			(state->args->geo->blksize >> 2);
 
 		leaf = bp->b_addr;
 		dp->d_ops->leaf_hdr_from_disk(&hdr2, leaf);
@@ -1560,8 +1565,8 @@ xfs_dir2_leafn_unbalance(
 	/* log the changes made when moving the entries */
 	dp->d_ops->leaf_hdr_to_disk(save_leaf, &savehdr);
 	dp->d_ops->leaf_hdr_to_disk(drop_leaf, &drophdr);
-	xfs_dir3_leaf_log_header(args->trans, dp, save_blk->bp);
-	xfs_dir3_leaf_log_header(args->trans, dp, drop_blk->bp);
+	xfs_dir3_leaf_log_header(args, save_blk->bp);
+	xfs_dir3_leaf_log_header(args, drop_blk->bp);
 
 	xfs_dir3_leaf_check(dp, save_blk->bp);
 	xfs_dir3_leaf_check(dp, drop_blk->bp);
@@ -1587,8 +1592,6 @@ xfs_dir2_node_addname(
 	state = xfs_da_state_alloc();
 	state->args = args;
 	state->mp = args->dp->i_mount;
-	state->blocksize = state->mp->m_dirblksize;
-	state->node_ents = state->mp->m_dir_node_ents;
 	/*
 	 * Look up the name.  We're not supposed to find it, but
 	 * this gives us the insertion point.
@@ -1727,9 +1730,9 @@ xfs_dir2_node_addname_int(
 	if (dbno == -1) {
 		xfs_fileoff_t	fo;		/* freespace block number */
 
-		if ((error = xfs_bmap_last_offset(tp, dp, &fo, XFS_DATA_FORK)))
+		if ((error = xfs_bmap_last_offset(dp, &fo, XFS_DATA_FORK)))
 			return error;
-		lastfbno = xfs_dir2_da_to_db(mp, (xfs_dablk_t)fo);
+		lastfbno = xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)fo);
 		fbno = ifbno;
 	}
 	/*
@@ -1747,7 +1750,8 @@ xfs_dir2_node_addname_int(
 			 * us a freespace block to start with.
 			 */
 			if (++fbno == 0)
-				fbno = XFS_DIR2_FREE_FIRSTDB(mp);
+				fbno = xfs_dir2_byte_to_db(args->geo,
+							XFS_DIR2_FREE_OFFSET);
 			/*
 			 * If it's ifbno we already looked at it.
 			 */
@@ -1765,8 +1769,8 @@ xfs_dir2_node_addname_int(
 			 * to avoid it.
 			 */
 			error = xfs_dir2_free_try_read(tp, dp,
-						xfs_dir2_db_to_da(mp, fbno),
-						&fbp);
+					xfs_dir2_db_to_da(args->geo, fbno),
+					&fbp);
 			if (error)
 				return error;
 			if (!fbp)
@@ -1834,10 +1838,10 @@ xfs_dir2_node_addname_int(
 		 * Get the freespace block corresponding to the data block
 		 * that was just allocated.
 		 */
-		fbno = dp->d_ops->db_to_fdb(mp, dbno);
+		fbno = dp->d_ops->db_to_fdb(args->geo, dbno);
 		error = xfs_dir2_free_try_read(tp, dp,
-					       xfs_dir2_db_to_da(mp, fbno),
-					       &fbp);
+				       xfs_dir2_db_to_da(args->geo, fbno),
+				       &fbp);
 		if (error)
 			return error;
 
@@ -1851,12 +1855,13 @@ xfs_dir2_node_addname_int(
 			if (error)
 				return error;
 
-			if (unlikely(dp->d_ops->db_to_fdb(mp, dbno) != fbno)) {
+			if (dp->d_ops->db_to_fdb(args->geo, dbno) != fbno) {
 				xfs_alert(mp,
 			"%s: dir ino %llu needed freesp block %lld for\n"
 			"  data block %lld, got %lld ifbno %llu lastfbno %d",
 					__func__, (unsigned long long)dp->i_ino,
-					(long long)dp->d_ops->db_to_fdb(mp, dbno),
+					(long long)dp->d_ops->db_to_fdb(
+								args->geo, dbno),
 					(long long)dbno, (long long)fbno,
 					(unsigned long long)ifbno, lastfbno);
 				if (fblk) {
@@ -1877,7 +1882,7 @@ xfs_dir2_node_addname_int(
 			/*
 			 * Get a buffer for the new block.
 			 */
-			error = xfs_dir3_free_get_buf(tp, dp, fbno, &fbp);
+			error = xfs_dir3_free_get_buf(args, fbno, &fbp);
 			if (error)
 				return error;
 			free = fbp->b_addr;
@@ -1887,8 +1892,10 @@ xfs_dir2_node_addname_int(
 			/*
 			 * Remember the first slot as our empty slot.
 			 */
-			freehdr.firstdb = (fbno - XFS_DIR2_FREE_FIRSTDB(mp)) *
-					dp->d_ops->free_max_bests(mp);
+			freehdr.firstdb =
+				(fbno - xfs_dir2_byte_to_db(args->geo,
+							XFS_DIR2_FREE_OFFSET)) *
+					dp->d_ops->free_max_bests(args->geo);
 		} else {
 			free = fbp->b_addr;
 			bests = dp->d_ops->free_bests_p(free);
@@ -1898,13 +1905,13 @@ xfs_dir2_node_addname_int(
 		/*
 		 * Set the freespace block index from the data block number.
 		 */
-		findex = dp->d_ops->db_to_fdindex(mp, dbno);
+		findex = dp->d_ops->db_to_fdindex(args->geo, dbno);
 		/*
 		 * If it's after the end of the current entries in the
 		 * freespace block, extend that table.
 		 */
 		if (findex >= freehdr.nvalid) {
-			ASSERT(findex < dp->d_ops->free_max_bests(mp));
+			ASSERT(findex < dp->d_ops->free_max_bests(args->geo));
 			freehdr.nvalid = findex + 1;
 			/*
 			 * Tag new entry so nused will go up.
@@ -1918,7 +1925,7 @@ xfs_dir2_node_addname_int(
 		if (bests[findex] == cpu_to_be16(NULLDATAOFF)) {
 			freehdr.nused++;
 			dp->d_ops->free_hdr_to_disk(fbp->b_addr, &freehdr);
-			xfs_dir2_free_log_header(tp, dp, fbp);
+			xfs_dir2_free_log_header(args, fbp);
 		}
 		/*
 		 * Update the real value in the table.
@@ -1943,7 +1950,8 @@ xfs_dir2_node_addname_int(
 		/*
 		 * Read the data block in.
 		 */
-		error = xfs_dir3_data_read(tp, dp, xfs_dir2_db_to_da(mp, dbno),
+		error = xfs_dir3_data_read(tp, dp,
+					   xfs_dir2_db_to_da(args->geo, dbno),
 					   -1, &dbp);
 		if (error)
 			return error;
@@ -1961,7 +1969,7 @@ xfs_dir2_node_addname_int(
 	/*
 	 * Mark the first part of the unused space, inuse for us.
 	 */
-	xfs_dir2_data_use_free(tp, dp, dbp, dup,
+	xfs_dir2_data_use_free(args, dbp, dup,
 		(xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length,
 		&needlog, &needscan);
 	/*
@@ -1974,7 +1982,7 @@ xfs_dir2_node_addname_int(
 	dp->d_ops->data_put_ftype(dep, args->filetype);
 	tagp = dp->d_ops->data_entry_tag_p(dep);
 	*tagp = cpu_to_be16((char *)dep - (char *)hdr);
-	xfs_dir2_data_log_entry(tp, dp, dbp, dep);
+	xfs_dir2_data_log_entry(args, dbp, dep);
 	/*
 	 * Rescan the block for bestfree if needed.
 	 */
@@ -1984,7 +1992,7 @@ xfs_dir2_node_addname_int(
 	 * Log the data block header if needed.
 	 */
 	if (needlog)
-		xfs_dir2_data_log_header(tp, dp, dbp);
+		xfs_dir2_data_log_header(args, dbp);
 	/*
 	 * If the freespace entry is now wrong, update it.
 	 */
@@ -1997,7 +2005,7 @@ xfs_dir2_node_addname_int(
 	 * Log the freespace entry if needed.
 	 */
 	if (logfree)
-		xfs_dir2_free_log_bests(tp, dp, fbp, findex, findex);
+		xfs_dir2_free_log_bests(args, fbp, findex, findex);
 	/*
 	 * Return the data block and offset in args, then drop the data block.
 	 */
@@ -2028,8 +2036,6 @@ xfs_dir2_node_lookup(
 	state = xfs_da_state_alloc();
 	state->args = args;
 	state->mp = args->dp->i_mount;
-	state->blocksize = state->mp->m_dirblksize;
-	state->node_ents = state->mp->m_dir_node_ents;
 	/*
 	 * Fill in the path to the entry in the cursor.
 	 */
@@ -2083,8 +2089,6 @@ xfs_dir2_node_removename(
 	state = xfs_da_state_alloc();
 	state->args = args;
 	state->mp = args->dp->i_mount;
-	state->blocksize = state->mp->m_dirblksize;
-	state->node_ents = state->mp->m_dir_node_ents;
 
 	/* Look up the entry we're deleting, set up the cursor. */
 	error = xfs_da3_node_lookup_int(state, &rval);
@@ -2153,8 +2157,6 @@ xfs_dir2_node_replace(
 	state = xfs_da_state_alloc();
 	state->args = args;
 	state->mp = args->dp->i_mount;
-	state->blocksize = state->mp->m_dirblksize;
-	state->node_ents = state->mp->m_dir_node_ents;
 	inum = args->inumber;
 	/*
 	 * Lookup the entry to change in the btree.
@@ -2186,15 +2188,15 @@ xfs_dir2_node_replace(
 		       hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC));
 		dep = (xfs_dir2_data_entry_t *)
 		      ((char *)hdr +
-		       xfs_dir2_dataptr_to_off(state->mp, be32_to_cpu(lep->address)));
+		       xfs_dir2_dataptr_to_off(args->geo,
+					       be32_to_cpu(lep->address)));
 		ASSERT(inum != be64_to_cpu(dep->inumber));
 		/*
 		 * Fill in the new inode number and log the entry.
 		 */
 		dep->inumber = cpu_to_be64(inum);
 		args->dp->d_ops->data_put_ftype(dep, args->filetype);
-		xfs_dir2_data_log_entry(args->trans, args->dp,
-					state->extrablk.bp, dep);
+		xfs_dir2_data_log_entry(args, state->extrablk.bp, dep);
 		rval = 0;
 	}
 	/*
@@ -2262,9 +2264,9 @@ xfs_dir2_node_trim_free(
 	/*
 	 * Blow the block away.
 	 */
-	if ((error =
-	    xfs_dir2_shrink_inode(args, xfs_dir2_da_to_db(mp, (xfs_dablk_t)fo),
-		    bp))) {
+	error = xfs_dir2_shrink_inode(args,
+			xfs_dir2_da_to_db(args->geo, (xfs_dablk_t)fo), bp);
+	if (error) {
 		/*
 		 * Can't fail with ENOSPC since that only happens with no
 		 * space reservation, when breaking up an extent into two
diff --git a/fs/xfs/xfs_dir2_priv.h b/fs/xfs/xfs_dir2_priv.h
index 8b9d2281f85..27ce0794d19 100644
--- a/fs/xfs/xfs_dir2_priv.h
+++ b/fs/xfs/xfs_dir2_priv.h
@@ -20,6 +20,140 @@
 
 struct dir_context;
 
+/*
+ * Directory offset/block conversion functions.
+ *
+ * DB blocks here are logical directory block numbers, not filesystem blocks.
+ */
+
+/*
+ * Convert dataptr to byte in file space
+ */
+static inline xfs_dir2_off_t
+xfs_dir2_dataptr_to_byte(xfs_dir2_dataptr_t dp)
+{
+	return (xfs_dir2_off_t)dp << XFS_DIR2_DATA_ALIGN_LOG;
+}
+
+/*
+ * Convert byte in file space to dataptr.  It had better be aligned.
+ */
+static inline xfs_dir2_dataptr_t
+xfs_dir2_byte_to_dataptr(xfs_dir2_off_t by)
+{
+	return (xfs_dir2_dataptr_t)(by >> XFS_DIR2_DATA_ALIGN_LOG);
+}
+
+/*
+ * Convert byte in space to (DB) block
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_byte_to_db(struct xfs_da_geometry *geo, xfs_dir2_off_t by)
+{
+	return (xfs_dir2_db_t)(by >> geo->blklog);
+}
+
+/*
+ * Convert dataptr to a block number
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_dataptr_to_db(struct xfs_da_geometry *geo, xfs_dir2_dataptr_t dp)
+{
+	return xfs_dir2_byte_to_db(geo, xfs_dir2_dataptr_to_byte(dp));
+}
+
+/*
+ * Convert byte in space to offset in a block
+ */
+static inline xfs_dir2_data_aoff_t
+xfs_dir2_byte_to_off(struct xfs_da_geometry *geo, xfs_dir2_off_t by)
+{
+	return (xfs_dir2_data_aoff_t)(by & (geo->blksize - 1));
+}
+
+/*
+ * Convert dataptr to a byte offset in a block
+ */
+static inline xfs_dir2_data_aoff_t
+xfs_dir2_dataptr_to_off(struct xfs_da_geometry *geo, xfs_dir2_dataptr_t dp)
+{
+	return xfs_dir2_byte_to_off(geo, xfs_dir2_dataptr_to_byte(dp));
+}
+
+/*
+ * Convert block and offset to byte in space
+ */
+static inline xfs_dir2_off_t
+xfs_dir2_db_off_to_byte(struct xfs_da_geometry *geo, xfs_dir2_db_t db,
+			xfs_dir2_data_aoff_t o)
+{
+	return ((xfs_dir2_off_t)db << geo->blklog) + o;
+}
+
+/*
+ * Convert block (DB) to block (dablk)
+ */
+static inline xfs_dablk_t
+xfs_dir2_db_to_da(struct xfs_da_geometry *geo, xfs_dir2_db_t db)
+{
+	return (xfs_dablk_t)(db << (geo->blklog - geo->fsblog));
+}
+
+/*
+ * Convert byte in space to (DA) block
+ */
+static inline xfs_dablk_t
+xfs_dir2_byte_to_da(struct xfs_da_geometry *geo, xfs_dir2_off_t by)
+{
+	return xfs_dir2_db_to_da(geo, xfs_dir2_byte_to_db(geo, by));
+}
+
+/*
+ * Convert block and offset to dataptr
+ */
+static inline xfs_dir2_dataptr_t
+xfs_dir2_db_off_to_dataptr(struct xfs_da_geometry *geo, xfs_dir2_db_t db,
+			   xfs_dir2_data_aoff_t o)
+{
+	return xfs_dir2_byte_to_dataptr(xfs_dir2_db_off_to_byte(geo, db, o));
+}
+
+/*
+ * Convert block (dablk) to block (DB)
+ */
+static inline xfs_dir2_db_t
+xfs_dir2_da_to_db(struct xfs_da_geometry *geo, xfs_dablk_t da)
+{
+	return (xfs_dir2_db_t)(da >> (geo->blklog - geo->fsblog));
+}
+
+/*
+ * Convert block (dablk) to byte offset in space
+ */
+static inline xfs_dir2_off_t
+xfs_dir2_da_to_byte(struct xfs_da_geometry *geo, xfs_dablk_t da)
+{
+	return xfs_dir2_db_off_to_byte(geo, xfs_dir2_da_to_db(geo, da), 0);
+}
+
+/*
+ * Directory tail pointer accessor functions. Based on block geometry.
+ */
+static inline struct xfs_dir2_block_tail *
+xfs_dir2_block_tail_p(struct xfs_da_geometry *geo, struct xfs_dir2_data_hdr *hdr)
+{
+	return ((struct xfs_dir2_block_tail *)
+		((char *)hdr + geo->blksize)) - 1;
+}
+
+static inline struct xfs_dir2_leaf_tail *
+xfs_dir2_leaf_tail_p(struct xfs_da_geometry *geo, struct xfs_dir2_leaf *lp)
+{
+	return (struct xfs_dir2_leaf_tail *)
+		((char *)lp + geo->blksize -
+		  sizeof(struct xfs_dir2_leaf_tail));
+}
+
 /* xfs_dir2.c */
 extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino);
 extern int xfs_dir2_grow_inode(struct xfs_da_args *args, int space,
@@ -54,8 +188,8 @@ extern int xfs_dir2_leaf_to_block(struct xfs_da_args *args,
 extern int __xfs_dir3_data_check(struct xfs_inode *dp, struct xfs_buf *bp);
 extern int xfs_dir3_data_read(struct xfs_trans *tp, struct xfs_inode *dp,
 		xfs_dablk_t bno, xfs_daddr_t mapped_bno, struct xfs_buf **bpp);
-extern int xfs_dir3_data_readahead(struct xfs_trans *tp, struct xfs_inode *dp,
-		xfs_dablk_t bno, xfs_daddr_t mapped_bno);
+extern int xfs_dir3_data_readahead(struct xfs_inode *dp, xfs_dablk_t bno,
+		xfs_daddr_t mapped_bno);
 
 extern struct xfs_dir2_data_free *
 xfs_dir2_data_freeinsert(struct xfs_dir2_data_hdr *hdr,
@@ -77,9 +211,9 @@ extern void xfs_dir3_leaf_compact_x1(struct xfs_dir3_icleaf_hdr *leafhdr,
 		int *lowstalep, int *highstalep, int *lowlogp, int *highlogp);
 extern int xfs_dir3_leaf_get_buf(struct xfs_da_args *args, xfs_dir2_db_t bno,
 		struct xfs_buf **bpp, __uint16_t magic);
-extern void xfs_dir3_leaf_log_ents(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir3_leaf_log_ents(struct xfs_da_args *args,
 		struct xfs_buf *bp, int first, int last);
-extern void xfs_dir3_leaf_log_header(struct xfs_trans *tp, struct xfs_inode *dp,
+extern void xfs_dir3_leaf_log_header(struct xfs_da_args *args,
 		struct xfs_buf *bp);
 extern int xfs_dir2_leaf_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_leaf_removename(struct xfs_da_args *args);
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index aead369e1c3..48e99afb9cb 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -76,26 +76,25 @@ const unsigned char xfs_mode_to_ftype[S_IFMT >> S_SHIFT] = {
 
 STATIC int
 xfs_dir2_sf_getdents(
-	xfs_inode_t		*dp,		/* incore directory inode */
+	struct xfs_da_args	*args,
 	struct dir_context	*ctx)
 {
 	int			i;		/* shortform entry number */
-	xfs_mount_t		*mp;		/* filesystem mount point */
+	struct xfs_inode	*dp = args->dp;	/* incore directory inode */
 	xfs_dir2_dataptr_t	off;		/* current entry's offset */
 	xfs_dir2_sf_entry_t	*sfep;		/* shortform directory entry */
 	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 	xfs_dir2_dataptr_t	dot_offset;
 	xfs_dir2_dataptr_t	dotdot_offset;
 	xfs_ino_t		ino;
-
-	mp = dp->i_mount;
+	struct xfs_da_geometry	*geo = args->geo;
 
 	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
 	/*
 	 * Give up if the directory is way too short.
 	 */
 	if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
-		ASSERT(XFS_FORCED_SHUTDOWN(mp));
+		ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount));
 		return XFS_ERROR(EIO);
 	}
 
@@ -109,18 +108,18 @@ xfs_dir2_sf_getdents(
 	/*
 	 * If the block number in the offset is out of range, we're done.
 	 */
-	if (xfs_dir2_dataptr_to_db(mp, ctx->pos) > mp->m_dirdatablk)
+	if (xfs_dir2_dataptr_to_db(geo, ctx->pos) > geo->datablk)
 		return 0;
 
 	/*
 	 * Precalculate offsets for . and .. as we will always need them.
 	 *
 	 * XXX(hch): the second argument is sometimes 0 and sometimes
-	 * mp->m_dirdatablk.
+	 * geo->datablk
 	 */
-	dot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
+	dot_offset = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
 						dp->d_ops->data_dot_offset);
-	dotdot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
+	dotdot_offset = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
 						dp->d_ops->data_dotdot_offset);
 
 	/*
@@ -149,7 +148,7 @@ xfs_dir2_sf_getdents(
 	for (i = 0; i < sfp->count; i++) {
 		__uint8_t filetype;
 
-		off = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
+		off = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
 				xfs_dir2_sf_get_offset(sfep));
 
 		if (ctx->pos > off) {
@@ -161,13 +160,13 @@ xfs_dir2_sf_getdents(
 		filetype = dp->d_ops->sf_get_ftype(sfep);
 		ctx->pos = off & 0x7fffffff;
 		if (!dir_emit(ctx, (char *)sfep->name, sfep->namelen, ino,
-			    xfs_dir3_get_dtype(mp, filetype)))
+			    xfs_dir3_get_dtype(dp->i_mount, filetype)))
 			return 0;
 		sfep = dp->d_ops->sf_nextentry(sfp, sfep);
 	}
 
-	ctx->pos = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
-			0x7fffffff;
+	ctx->pos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk + 1, 0) &
+								0x7fffffff;
 	return 0;
 }
 
@@ -176,9 +175,10 @@ xfs_dir2_sf_getdents(
  */
 STATIC int
 xfs_dir2_block_getdents(
-	xfs_inode_t		*dp,		/* incore inode */
+	struct xfs_da_args	*args,
 	struct dir_context	*ctx)
 {
+	struct xfs_inode	*dp = args->dp;	/* incore directory inode */
 	xfs_dir2_data_hdr_t	*hdr;		/* block header */
 	struct xfs_buf		*bp;		/* buffer for block */
 	xfs_dir2_block_tail_t	*btp;		/* block tail */
@@ -186,16 +186,15 @@ xfs_dir2_block_getdents(
 	xfs_dir2_data_unused_t	*dup;		/* block unused entry */
 	char			*endptr;	/* end of the data entries */
 	int			error;		/* error return value */
-	xfs_mount_t		*mp;		/* filesystem mount point */
 	char			*ptr;		/* current data entry */
 	int			wantoff;	/* starting block offset */
 	xfs_off_t		cook;
+	struct xfs_da_geometry	*geo = args->geo;
 
-	mp = dp->i_mount;
 	/*
 	 * If the block number in the offset is out of range, we're done.
 	 */
-	if (xfs_dir2_dataptr_to_db(mp, ctx->pos) > mp->m_dirdatablk)
+	if (xfs_dir2_dataptr_to_db(geo, ctx->pos) > geo->datablk)
 		return 0;
 
 	error = xfs_dir3_block_read(NULL, dp, &bp);
@@ -206,13 +205,13 @@ xfs_dir2_block_getdents(
 	 * Extract the byte offset we start at from the seek pointer.
 	 * We'll skip entries before this.
 	 */
-	wantoff = xfs_dir2_dataptr_to_off(mp, ctx->pos);
+	wantoff = xfs_dir2_dataptr_to_off(geo, ctx->pos);
 	hdr = bp->b_addr;
 	xfs_dir3_data_check(dp, bp);
 	/*
 	 * Set up values for the loop.
 	 */
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(geo, hdr);
 	ptr = (char *)dp->d_ops->data_entry_p(hdr);
 	endptr = (char *)xfs_dir2_block_leaf_p(btp);
 
@@ -244,7 +243,7 @@ xfs_dir2_block_getdents(
 		if ((char *)dep - (char *)hdr < wantoff)
 			continue;
 
-		cook = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
+		cook = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
 					    (char *)dep - (char *)hdr);
 
 		ctx->pos = cook & 0x7fffffff;
@@ -254,7 +253,7 @@ xfs_dir2_block_getdents(
 		 */
 		if (!dir_emit(ctx, (char *)dep->name, dep->namelen,
 			    be64_to_cpu(dep->inumber),
-			    xfs_dir3_get_dtype(mp, filetype))) {
+			    xfs_dir3_get_dtype(dp->i_mount, filetype))) {
 			xfs_trans_brelse(NULL, bp);
 			return 0;
 		}
@@ -264,8 +263,8 @@ xfs_dir2_block_getdents(
 	 * Reached the end of the block.
 	 * Set the offset to a non-existent block 1 and return.
 	 */
-	ctx->pos = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk + 1, 0) &
-			0x7fffffff;
+	ctx->pos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk + 1, 0) &
+								0x7fffffff;
 	xfs_trans_brelse(NULL, bp);
 	return 0;
 }
@@ -286,13 +285,13 @@ struct xfs_dir2_leaf_map_info {
 
 STATIC int
 xfs_dir2_leaf_readbuf(
-	struct xfs_inode	*dp,
+	struct xfs_da_args	*args,
 	size_t			bufsize,
 	struct xfs_dir2_leaf_map_info *mip,
 	xfs_dir2_off_t		*curoff,
 	struct xfs_buf		**bpp)
 {
-	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_inode	*dp = args->dp;
 	struct xfs_buf		*bp = *bpp;
 	struct xfs_bmbt_irec	*map = mip->map;
 	struct blk_plug		plug;
@@ -300,6 +299,7 @@ xfs_dir2_leaf_readbuf(
 	int			length;
 	int			i;
 	int			j;
+	struct xfs_da_geometry	*geo = args->geo;
 
 	/*
 	 * If we have a buffer, we need to release it and
@@ -309,12 +309,12 @@ xfs_dir2_leaf_readbuf(
 	if (bp) {
 		xfs_trans_brelse(NULL, bp);
 		bp = NULL;
-		mip->map_blocks -= mp->m_dirblkfsbs;
+		mip->map_blocks -= geo->fsbcount;
 		/*
 		 * Loop to get rid of the extents for the
 		 * directory block.
 		 */
-		for (i = mp->m_dirblkfsbs; i > 0; ) {
+		for (i = geo->fsbcount; i > 0; ) {
 			j = min_t(int, map->br_blockcount, i);
 			map->br_blockcount -= j;
 			map->br_startblock += j;
@@ -333,8 +333,7 @@ xfs_dir2_leaf_readbuf(
 	/*
 	 * Recalculate the readahead blocks wanted.
 	 */
-	mip->ra_want = howmany(bufsize + mp->m_dirblksize,
-			       mp->m_sb.sb_blocksize) - 1;
+	mip->ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog)) - 1;
 	ASSERT(mip->ra_want >= 0);
 
 	/*
@@ -342,14 +341,14 @@ xfs_dir2_leaf_readbuf(
 	 * run out of data blocks, get some more mappings.
 	 */
 	if (1 + mip->ra_want > mip->map_blocks &&
-	    mip->map_off < xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET)) {
+	    mip->map_off < xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET)) {
 		/*
 		 * Get more bmaps, fill in after the ones
 		 * we already have in the table.
 		 */
 		mip->nmap = mip->map_size - mip->map_valid;
 		error = xfs_bmapi_read(dp, mip->map_off,
-				xfs_dir2_byte_to_da(mp, XFS_DIR2_LEAF_OFFSET) -
+				xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET) -
 								mip->map_off,
 				&map[mip->map_valid], &mip->nmap, 0);
 
@@ -370,7 +369,7 @@ xfs_dir2_leaf_readbuf(
 			i = mip->map_valid + mip->nmap - 1;
 			mip->map_off = map[i].br_startoff + map[i].br_blockcount;
 		} else
-			mip->map_off = xfs_dir2_byte_to_da(mp,
+			mip->map_off = xfs_dir2_byte_to_da(geo,
 							XFS_DIR2_LEAF_OFFSET);
 
 		/*
@@ -396,18 +395,18 @@ xfs_dir2_leaf_readbuf(
 	 * No valid mappings, so no more data blocks.
 	 */
 	if (!mip->map_valid) {
-		*curoff = xfs_dir2_da_to_byte(mp, mip->map_off);
+		*curoff = xfs_dir2_da_to_byte(geo, mip->map_off);
 		goto out;
 	}
 
 	/*
 	 * Read the directory block starting at the first mapping.
 	 */
-	mip->curdb = xfs_dir2_da_to_db(mp, map->br_startoff);
+	mip->curdb = xfs_dir2_da_to_db(geo, map->br_startoff);
 	error = xfs_dir3_data_read(NULL, dp, map->br_startoff,
-			map->br_blockcount >= mp->m_dirblkfsbs ?
-			    XFS_FSB_TO_DADDR(mp, map->br_startblock) : -1, &bp);
-
+			map->br_blockcount >= geo->fsbcount ?
+			    XFS_FSB_TO_DADDR(dp->i_mount, map->br_startblock) :
+			    -1, &bp);
 	/*
 	 * Should just skip over the data block instead of giving up.
 	 */
@@ -419,7 +418,7 @@ xfs_dir2_leaf_readbuf(
 	 * was previously ra.
 	 */
 	if (mip->ra_current)
-		mip->ra_current -= mp->m_dirblkfsbs;
+		mip->ra_current -= geo->fsbcount;
 
 	/*
 	 * Do we need more readahead?
@@ -427,16 +426,16 @@ xfs_dir2_leaf_readbuf(
 	blk_start_plug(&plug);
 	for (mip->ra_index = mip->ra_offset = i = 0;
 	     mip->ra_want > mip->ra_current && i < mip->map_blocks;
-	     i += mp->m_dirblkfsbs) {
+	     i += geo->fsbcount) {
 		ASSERT(mip->ra_index < mip->map_valid);
 		/*
 		 * Read-ahead a contiguous directory block.
 		 */
 		if (i > mip->ra_current &&
-		    map[mip->ra_index].br_blockcount >= mp->m_dirblkfsbs) {
-			xfs_dir3_data_readahead(NULL, dp,
+		    map[mip->ra_index].br_blockcount >= geo->fsbcount) {
+			xfs_dir3_data_readahead(dp,
 				map[mip->ra_index].br_startoff + mip->ra_offset,
-				XFS_FSB_TO_DADDR(mp,
+				XFS_FSB_TO_DADDR(dp->i_mount,
 					map[mip->ra_index].br_startblock +
 							mip->ra_offset));
 			mip->ra_current = i;
@@ -447,7 +446,7 @@ xfs_dir2_leaf_readbuf(
 		 * use our mapping, but this is a very rare case.
 		 */
 		else if (i > mip->ra_current) {
-			xfs_dir3_data_readahead(NULL, dp,
+			xfs_dir3_data_readahead(dp,
 					map[mip->ra_index].br_startoff +
 							mip->ra_offset, -1);
 			mip->ra_current = i;
@@ -456,15 +455,14 @@ xfs_dir2_leaf_readbuf(
 		/*
 		 * Advance offset through the mapping table.
 		 */
-		for (j = 0; j < mp->m_dirblkfsbs; j++) {
+		for (j = 0; j < geo->fsbcount; j += length ) {
 			/*
 			 * The rest of this extent but not more than a dir
 			 * block.
 			 */
-			length = min_t(int, mp->m_dirblkfsbs,
+			length = min_t(int, geo->fsbcount,
 					map[mip->ra_index].br_blockcount -
 							mip->ra_offset);
-			j += length;
 			mip->ra_offset += length;
 
 			/*
@@ -489,22 +487,23 @@ out:
  */
 STATIC int
 xfs_dir2_leaf_getdents(
-	xfs_inode_t		*dp,		/* incore directory inode */
+	struct xfs_da_args	*args,
 	struct dir_context	*ctx,
 	size_t			bufsize)
 {
+	struct xfs_inode	*dp = args->dp;
 	struct xfs_buf		*bp = NULL;	/* data block buffer */
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_data_entry_t	*dep;		/* data entry */
 	xfs_dir2_data_unused_t	*dup;		/* unused entry */
 	int			error = 0;	/* error return value */
 	int			length;		/* temporary length value */
-	xfs_mount_t		*mp;		/* filesystem mount point */
 	int			byteoff;	/* offset in current block */
 	xfs_dir2_off_t		curoff;		/* current overall offset */
 	xfs_dir2_off_t		newoff;		/* new curoff after new blk */
 	char			*ptr = NULL;	/* pointer to current data */
 	struct xfs_dir2_leaf_map_info *map_info;
+	struct xfs_da_geometry	*geo = args->geo;
 
 	/*
 	 * If the offset is at or past the largest allowed value,
@@ -513,15 +512,12 @@ xfs_dir2_leaf_getdents(
 	if (ctx->pos >= XFS_DIR2_MAX_DATAPTR)
 		return 0;
 
-	mp = dp->i_mount;
-
 	/*
 	 * Set up to bmap a number of blocks based on the caller's
 	 * buffer size, the directory block size, and the filesystem
 	 * block size.
 	 */
-	length = howmany(bufsize + mp->m_dirblksize,
-				     mp->m_sb.sb_blocksize);
+	length = howmany(bufsize + geo->blksize, (1 << geo->fsblog));
 	map_info = kmem_zalloc(offsetof(struct xfs_dir2_leaf_map_info, map) +
 				(length * sizeof(struct xfs_bmbt_irec)),
 			       KM_SLEEP | KM_NOFS);
@@ -531,14 +527,14 @@ xfs_dir2_leaf_getdents(
 	 * Inside the loop we keep the main offset value as a byte offset
 	 * in the directory file.
 	 */
-	curoff = xfs_dir2_dataptr_to_byte(mp, ctx->pos);
+	curoff = xfs_dir2_dataptr_to_byte(ctx->pos);
 
 	/*
 	 * Force this conversion through db so we truncate the offset
 	 * down to get the start of the data block.
 	 */
-	map_info->map_off = xfs_dir2_db_to_da(mp,
-					      xfs_dir2_byte_to_db(mp, curoff));
+	map_info->map_off = xfs_dir2_db_to_da(geo,
+					      xfs_dir2_byte_to_db(geo, curoff));
 
 	/*
 	 * Loop over directory entries until we reach the end offset.
@@ -551,9 +547,9 @@ xfs_dir2_leaf_getdents(
 		 * If we have no buffer, or we're off the end of the
 		 * current buffer, need to get another one.
 		 */
-		if (!bp || ptr >= (char *)bp->b_addr + mp->m_dirblksize) {
+		if (!bp || ptr >= (char *)bp->b_addr + geo->blksize) {
 
-			error = xfs_dir2_leaf_readbuf(dp, bufsize, map_info,
+			error = xfs_dir2_leaf_readbuf(args, bufsize, map_info,
 						      &curoff, &bp);
 			if (error || !map_info->map_valid)
 				break;
@@ -561,7 +557,8 @@ xfs_dir2_leaf_getdents(
 			/*
 			 * Having done a read, we need to set a new offset.
 			 */
-			newoff = xfs_dir2_db_off_to_byte(mp, map_info->curdb, 0);
+			newoff = xfs_dir2_db_off_to_byte(geo,
+							 map_info->curdb, 0);
 			/*
 			 * Start of the current block.
 			 */
@@ -571,7 +568,7 @@ xfs_dir2_leaf_getdents(
 			 * Make sure we're in the right block.
 			 */
 			else if (curoff > newoff)
-				ASSERT(xfs_dir2_byte_to_db(mp, curoff) ==
+				ASSERT(xfs_dir2_byte_to_db(geo, curoff) ==
 				       map_info->curdb);
 			hdr = bp->b_addr;
 			xfs_dir3_data_check(dp, bp);
@@ -579,7 +576,7 @@ xfs_dir2_leaf_getdents(
 			 * Find our position in the block.
 			 */
 			ptr = (char *)dp->d_ops->data_entry_p(hdr);
-			byteoff = xfs_dir2_byte_to_off(mp, curoff);
+			byteoff = xfs_dir2_byte_to_off(geo, curoff);
 			/*
 			 * Skip past the header.
 			 */
@@ -608,10 +605,10 @@ xfs_dir2_leaf_getdents(
 				 * Now set our real offset.
 				 */
 				curoff =
-					xfs_dir2_db_off_to_byte(mp,
-					    xfs_dir2_byte_to_db(mp, curoff),
+					xfs_dir2_db_off_to_byte(geo,
+					    xfs_dir2_byte_to_db(geo, curoff),
 					    (char *)ptr - (char *)hdr);
-				if (ptr >= (char *)hdr + mp->m_dirblksize) {
+				if (ptr >= (char *)hdr + geo->blksize) {
 					continue;
 				}
 			}
@@ -635,10 +632,10 @@ xfs_dir2_leaf_getdents(
 		length = dp->d_ops->data_entsize(dep->namelen);
 		filetype = dp->d_ops->data_get_ftype(dep);
 
-		ctx->pos = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
+		ctx->pos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff;
 		if (!dir_emit(ctx, (char *)dep->name, dep->namelen,
 			    be64_to_cpu(dep->inumber),
-			    xfs_dir3_get_dtype(mp, filetype)))
+			    xfs_dir3_get_dtype(dp->i_mount, filetype)))
 			break;
 
 		/*
@@ -653,10 +650,10 @@ xfs_dir2_leaf_getdents(
 	/*
 	 * All done.  Set output offset value to current offset.
 	 */
-	if (curoff > xfs_dir2_dataptr_to_byte(mp, XFS_DIR2_MAX_DATAPTR))
+	if (curoff > xfs_dir2_dataptr_to_byte(XFS_DIR2_MAX_DATAPTR))
 		ctx->pos = XFS_DIR2_MAX_DATAPTR & 0x7fffffff;
 	else
-		ctx->pos = xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff;
+		ctx->pos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff;
 	kmem_free(map_info);
 	if (bp)
 		xfs_trans_brelse(NULL, bp);
@@ -668,13 +665,14 @@ xfs_dir2_leaf_getdents(
  */
 int
 xfs_readdir(
-	xfs_inode_t	*dp,
-	struct dir_context *ctx,
-	size_t		bufsize)
+	struct xfs_inode	*dp,
+	struct dir_context	*ctx,
+	size_t			bufsize)
 {
-	int		rval;		/* return value */
-	int		v;		/* type-checking value */
-	uint		lock_mode;
+	struct xfs_da_args	args = { NULL };
+	int			rval;
+	int			v;
+	uint			lock_mode;
 
 	trace_xfs_readdir(dp);
 
@@ -684,15 +682,18 @@ xfs_readdir(
 	ASSERT(S_ISDIR(dp->i_d.di_mode));
 	XFS_STATS_INC(xs_dir_getdents);
 
+	args.dp = dp;
+	args.geo = dp->i_mount->m_dir_geo;
+
 	lock_mode = xfs_ilock_data_map_shared(dp);
 	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
-		rval = xfs_dir2_sf_getdents(dp, ctx);
-	else if ((rval = xfs_dir2_isblock(NULL, dp, &v)))
+		rval = xfs_dir2_sf_getdents(&args, ctx);
+	else if ((rval = xfs_dir2_isblock(&args, &v)))
 		;
 	else if (v)
-		rval = xfs_dir2_block_getdents(dp, ctx);
+		rval = xfs_dir2_block_getdents(&args, ctx);
 	else
-		rval = xfs_dir2_leaf_getdents(dp, ctx, bufsize);
+		rval = xfs_dir2_leaf_getdents(&args, ctx, bufsize);
 	xfs_iunlock(dp, lock_mode);
 
 	return rval;
diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c
index 3725fb1b902..53c3be619db 100644
--- a/fs/xfs/xfs_dir2_sf.c
+++ b/fs/xfs/xfs_dir2_sf.c
@@ -82,8 +82,10 @@ xfs_dir2_block_sfsize(
 	xfs_ino_t		parent = 0;	/* parent inode number */
 	int			size=0;		/* total computed size */
 	int			has_ftype;
+	struct xfs_da_geometry	*geo;
 
 	mp = dp->i_mount;
+	geo = mp->m_dir_geo;
 
 	/*
 	 * if there is a filetype field, add the extra byte to the namelen
@@ -92,7 +94,7 @@ xfs_dir2_block_sfsize(
 	has_ftype = xfs_sb_version_hasftype(&mp->m_sb) ? 1 : 0;
 
 	count = i8count = namelen = 0;
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(geo, hdr);
 	blp = xfs_dir2_block_leaf_p(btp);
 
 	/*
@@ -104,8 +106,8 @@ xfs_dir2_block_sfsize(
 		/*
 		 * Calculate the pointer to the entry at hand.
 		 */
-		dep = (xfs_dir2_data_entry_t *)
-		      ((char *)hdr + xfs_dir2_dataptr_to_off(mp, addr));
+		dep = (xfs_dir2_data_entry_t *)((char *)hdr +
+				xfs_dir2_dataptr_to_off(geo, addr));
 		/*
 		 * Detect . and .., so we can special-case them.
 		 * . is not included in sf directories.
@@ -195,7 +197,7 @@ xfs_dir2_block_to_sf(
 	/*
 	 * Set up to loop over the block's entries.
 	 */
-	btp = xfs_dir2_block_tail_p(mp, hdr);
+	btp = xfs_dir2_block_tail_p(args->geo, hdr);
 	ptr = (char *)dp->d_ops->data_entry_p(hdr);
 	endptr = (char *)xfs_dir2_block_leaf_p(btp);
 	sfep = xfs_dir2_sf_firstentry(sfp);
@@ -247,7 +249,7 @@ xfs_dir2_block_to_sf(
 
 	/* now we are done with the block, we can shrink the inode */
 	logflags = XFS_ILOG_CORE;
-	error = xfs_dir2_shrink_inode(args, mp->m_dirdatablk, bp);
+	error = xfs_dir2_shrink_inode(args, args->geo->datablk, bp);
 	if (error) {
 		ASSERT(error != ENOSPC);
 		goto out;
@@ -285,14 +287,12 @@ int						/* error */
 xfs_dir2_sf_addname(
 	xfs_da_args_t		*args)		/* operation arguments */
 {
-	int			add_entsize;	/* size of the new entry */
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return value */
 	int			incr_isize;	/* total change in size */
 	int			new_isize;	/* di_size after adding name */
 	int			objchange;	/* changing to 8-byte inodes */
 	xfs_dir2_data_aoff_t	offset = 0;	/* offset for new entry */
-	int			old_isize;	/* di_size before adding name */
 	int			pick;		/* which algorithm to use */
 	xfs_dir2_sf_hdr_t	*sfp;		/* shortform structure */
 	xfs_dir2_sf_entry_t	*sfep = NULL;	/* shortform entry */
@@ -316,8 +316,7 @@ xfs_dir2_sf_addname(
 	/*
 	 * Compute entry (and change in) size.
 	 */
-	add_entsize = dp->d_ops->sf_entsize(sfp, args->namelen);
-	incr_isize = add_entsize;
+	incr_isize = dp->d_ops->sf_entsize(sfp, args->namelen);
 	objchange = 0;
 #if XFS_BIG_INUMS
 	/*
@@ -325,11 +324,8 @@ xfs_dir2_sf_addname(
 	 */
 	if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0) {
 		/*
-		 * Yes, adjust the entry size and the total size.
+		 * Yes, adjust the inode size.  old count + (parent + new)
 		 */
-		add_entsize +=
-			(uint)sizeof(xfs_dir2_ino8_t) -
-			(uint)sizeof(xfs_dir2_ino4_t);
 		incr_isize +=
 			(sfp->count + 2) *
 			((uint)sizeof(xfs_dir2_ino8_t) -
@@ -337,8 +333,7 @@ xfs_dir2_sf_addname(
 		objchange = 1;
 	}
 #endif
-	old_isize = (int)dp->i_d.di_size;
-	new_isize = old_isize + incr_isize;
+	new_isize = (int)dp->i_d.di_size + incr_isize;
 	/*
 	 * Won't fit as shortform any more (due to size),
 	 * or the pick routine says it won't (due to offset values).
@@ -593,7 +588,7 @@ xfs_dir2_sf_addname_pick(
 	 * we'll go back, convert to block, then try the insert and convert
 	 * to leaf.
 	 */
-	if (used + (holefit ? 0 : size) > mp->m_dirblksize)
+	if (used + (holefit ? 0 : size) > args->geo->blksize)
 		return 0;
 	/*
 	 * If changing the inode number size, do it the hard way.
@@ -608,7 +603,7 @@ xfs_dir2_sf_addname_pick(
 	/*
 	 * If it won't fit at the end then do it the hard way (use the hole).
 	 */
-	if (used + size > mp->m_dirblksize)
+	if (used + size > args->geo->blksize)
 		return 2;
 	/*
 	 * Do it the easy way.
@@ -659,7 +654,7 @@ xfs_dir2_sf_check(
 	ASSERT((char *)sfep - (char *)sfp == dp->i_d.di_size);
 	ASSERT(offset +
 	       (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
-	       (uint)sizeof(xfs_dir2_block_tail_t) <= mp->m_dirblksize);
+	       (uint)sizeof(xfs_dir2_block_tail_t) <= args->geo->blksize);
 }
 #endif	/* DEBUG */
 
@@ -1110,9 +1105,9 @@ xfs_dir2_sf_toino4(
 }
 
 /*
- * Convert from 4-byte inode numbers to 8-byte inode numbers.
- * The new 8-byte inode number is not there yet, we leave with the
- * count 1 but no corresponding entry.
+ * Convert existing entries from 4-byte inode numbers to 8-byte inode numbers.
+ * The new entry w/ an 8-byte inode number is not there yet; we leave with
+ * i8count set to 1, but no corresponding 8-byte entry.
  */
 static void
 xfs_dir2_sf_toino8(
@@ -1145,7 +1140,7 @@ xfs_dir2_sf_toino8(
 	ASSERT(oldsfp->i8count == 0);
 	memcpy(buf, oldsfp, oldsize);
 	/*
-	 * Compute the new inode size.
+	 * Compute the new inode size (nb: entry count + 1 for parent)
 	 */
 	newsize =
 		oldsize +
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 868b19f096b..3ee0cd43edc 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -353,10 +353,10 @@ xfs_qm_dqalloc(
 			       dqp->q_blkno,
 			       mp->m_quotainfo->qi_dqchunklen,
 			       0);
-
-	error = xfs_buf_geterror(bp);
-	if (error)
+	if (!bp) {
+		error = ENOMEM;
 		goto error1;
+	}
 	bp->b_ops = &xfs_dquot_buf_ops;
 
 	/*
@@ -832,47 +832,6 @@ restart:
 	return (0);
 }
 
-
-STATIC void
-xfs_qm_dqput_final(
-	struct xfs_dquot	*dqp)
-{
-	struct xfs_quotainfo	*qi = dqp->q_mount->m_quotainfo;
-	struct xfs_dquot	*gdqp;
-	struct xfs_dquot	*pdqp;
-
-	trace_xfs_dqput_free(dqp);
-
-	if (list_lru_add(&qi->qi_lru, &dqp->q_lru))
-		XFS_STATS_INC(xs_qm_dquot_unused);
-
-	/*
-	 * If we just added a udquot to the freelist, then we want to release
-	 * the gdquot/pdquot reference that it (probably) has. Otherwise it'll
-	 * keep the gdquot/pdquot from getting reclaimed.
-	 */
-	gdqp = dqp->q_gdquot;
-	if (gdqp) {
-		xfs_dqlock(gdqp);
-		dqp->q_gdquot = NULL;
-	}
-
-	pdqp = dqp->q_pdquot;
-	if (pdqp) {
-		xfs_dqlock(pdqp);
-		dqp->q_pdquot = NULL;
-	}
-	xfs_dqunlock(dqp);
-
-	/*
-	 * If we had a group/project quota hint, release it now.
-	 */
-	if (gdqp)
-		xfs_qm_dqput(gdqp);
-	if (pdqp)
-		xfs_qm_dqput(pdqp);
-}
-
 /*
  * Release a reference to the dquot (decrement ref-count) and unlock it.
  *
@@ -888,10 +847,14 @@ xfs_qm_dqput(
 
 	trace_xfs_dqput(dqp);
 
-	if (--dqp->q_nrefs > 0)
-		xfs_dqunlock(dqp);
-	else
-		xfs_qm_dqput_final(dqp);
+	if (--dqp->q_nrefs == 0) {
+		struct xfs_quotainfo	*qi = dqp->q_mount->m_quotainfo;
+		trace_xfs_dqput_free(dqp);
+
+		if (list_lru_add(&qi->qi_lru, &dqp->q_lru))
+			XFS_STATS_INC(xs_qm_dquot_unused);
+	}
+	xfs_dqunlock(dqp);
 }
 
 /*
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index d22ed0053c3..68a68f70483 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -52,8 +52,6 @@ typedef struct xfs_dquot {
 	int		 q_bufoffset;	/* off of dq in buffer (# dquots) */
 	xfs_fileoff_t	 q_fileoffset;	/* offset in quotas file */
 
-	struct xfs_dquot*q_gdquot;	/* group dquot, hint only */
-	struct xfs_dquot*q_pdquot;	/* project dquot, hint only */
 	xfs_disk_dquot_t q_core;	/* actual usage & quotas */
 	xfs_dq_logitem_t q_logitem;	/* dquot log item */
 	xfs_qcnt_t	 q_res_bcount;	/* total regular nblks used+reserved */
diff --git a/fs/xfs/xfs_dquot_buf.c b/fs/xfs/xfs_dquot_buf.c
index 610da817773..c2ac0c611ad 100644
--- a/fs/xfs/xfs_dquot_buf.c
+++ b/fs/xfs/xfs_dquot_buf.c
@@ -35,7 +35,6 @@
 
 int
 xfs_calc_dquots_per_chunk(
-	struct xfs_mount	*mp,
 	unsigned int		nbblks)	/* basic block units */
 {
 	unsigned int	ndquots;
@@ -194,7 +193,7 @@ xfs_dquot_buf_verify_crc(
 	if (mp->m_quotainfo)
 		ndquots = mp->m_quotainfo->qi_dqperchunk;
 	else
-		ndquots = xfs_calc_dquots_per_chunk(mp,
+		ndquots = xfs_calc_dquots_per_chunk(
 					XFS_BB_TO_FSB(mp, bp->b_length));
 
 	for (i = 0; i < ndquots; i++, d++) {
@@ -225,7 +224,7 @@ xfs_dquot_buf_verify(
 	if (mp->m_quotainfo)
 		ndquots = mp->m_quotainfo->qi_dqperchunk;
 	else
-		ndquots = xfs_calc_dquots_per_chunk(mp, bp->b_length);
+		ndquots = xfs_calc_dquots_per_chunk(bp->b_length);
 
 	/*
 	 * On the first read of the buffer, verify that each dquot is valid.
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 830c1c937b8..1f66779d7a4 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -229,34 +229,27 @@ xfs_file_fsync(
 }
 
 STATIC ssize_t
-xfs_file_aio_read(
+xfs_file_read_iter(
 	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos)
+	struct iov_iter		*to)
 {
 	struct file		*file = iocb->ki_filp;
 	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	size_t			size = 0;
+	size_t			size = iov_iter_count(to);
 	ssize_t			ret = 0;
 	int			ioflags = 0;
 	xfs_fsize_t		n;
+	loff_t			pos = iocb->ki_pos;
 
 	XFS_STATS_INC(xs_read_calls);
 
-	BUG_ON(iocb->ki_pos != pos);
-
 	if (unlikely(file->f_flags & O_DIRECT))
 		ioflags |= IO_ISDIRECT;
 	if (file->f_mode & FMODE_NOCMTIME)
 		ioflags |= IO_INVIS;
 
-	ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE);
-	if (ret < 0)
-		return ret;
-
 	if (unlikely(ioflags & IO_ISDIRECT)) {
 		xfs_buftarg_t	*target =
 			XFS_IS_REALTIME_INODE(ip) ?
@@ -309,7 +302,7 @@ xfs_file_aio_read(
 
 	trace_xfs_file_read(ip, size, pos, ioflags);
 
-	ret = generic_file_aio_read(iocb, iovp, nr_segs, pos);
+	ret = generic_file_read_iter(iocb, to);
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 
@@ -350,47 +343,6 @@ xfs_file_splice_read(
 }
 
 /*
- * xfs_file_splice_write() does not use xfs_rw_ilock() because
- * generic_file_splice_write() takes the i_mutex itself. This, in theory,
- * couuld cause lock inversions between the aio_write path and the splice path
- * if someone is doing concurrent splice(2) based writes and write(2) based
- * writes to the same inode. The only real way to fix this is to re-implement
- * the generic code here with correct locking orders.
- */
-STATIC ssize_t
-xfs_file_splice_write(
-	struct pipe_inode_info	*pipe,
-	struct file		*outfilp,
-	loff_t			*ppos,
-	size_t			count,
-	unsigned int		flags)
-{
-	struct inode		*inode = outfilp->f_mapping->host;
-	struct xfs_inode	*ip = XFS_I(inode);
-	int			ioflags = 0;
-	ssize_t			ret;
-
-	XFS_STATS_INC(xs_write_calls);
-
-	if (outfilp->f_mode & FMODE_NOCMTIME)
-		ioflags |= IO_INVIS;
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return -EIO;
-
-	xfs_ilock(ip, XFS_IOLOCK_EXCL);
-
-	trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
-
-	ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
-	if (ret > 0)
-		XFS_STATS_ADD(xs_write_bytes, ret);
-
-	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-	return ret;
-}
-
-/*
  * This routine is called to handle zeroing any space in the last block of the
  * file that is beyond the EOF.  We do this since the size is being increased
  * without writing anything to that block and we don't want to read the
@@ -625,10 +577,7 @@ restart:
 STATIC ssize_t
 xfs_file_dio_aio_write(
 	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos,
-	size_t			ocount)
+	struct iov_iter		*from)
 {
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
@@ -636,9 +585,10 @@ xfs_file_dio_aio_write(
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	ssize_t			ret = 0;
-	size_t			count = ocount;
 	int			unaligned_io = 0;
 	int			iolock;
+	size_t			count = iov_iter_count(from);
+	loff_t			pos = iocb->ki_pos;
 	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
 					mp->m_rtdev_targp : mp->m_ddev_targp;
 
@@ -677,6 +627,7 @@ xfs_file_dio_aio_write(
 	ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
 	if (ret)
 		goto out;
+	iov_iter_truncate(from, count);
 
 	if (mapping->nrpages) {
 		ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
@@ -698,8 +649,7 @@ xfs_file_dio_aio_write(
 	}
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
-	ret = generic_file_direct_write(iocb, iovp,
-			&nr_segs, pos, count, ocount);
+	ret = generic_file_direct_write(iocb, from, pos);
 
 out:
 	xfs_rw_iunlock(ip, iolock);
@@ -712,10 +662,7 @@ out:
 STATIC ssize_t
 xfs_file_buffered_aio_write(
 	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos,
-	size_t			count)
+	struct iov_iter		*from)
 {
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
@@ -724,7 +671,8 @@ xfs_file_buffered_aio_write(
 	ssize_t			ret;
 	int			enospc = 0;
 	int			iolock = XFS_IOLOCK_EXCL;
-	struct iov_iter		from;
+	loff_t			pos = iocb->ki_pos;
+	size_t			count = iov_iter_count(from);
 
 	xfs_rw_ilock(ip, iolock);
 
@@ -732,13 +680,13 @@ xfs_file_buffered_aio_write(
 	if (ret)
 		goto out;
 
-	iov_iter_init(&from, iovp, nr_segs, count, 0);
+	iov_iter_truncate(from, count);
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
 
 write_retry:
 	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
-	ret = generic_perform_write(file, &from, pos);
+	ret = generic_perform_write(file, from, pos);
 	if (likely(ret >= 0))
 		iocb->ki_pos = pos + ret;
 	/*
@@ -759,40 +707,29 @@ out:
 }
 
 STATIC ssize_t
-xfs_file_aio_write(
+xfs_file_write_iter(
 	struct kiocb		*iocb,
-	const struct iovec	*iovp,
-	unsigned long		nr_segs,
-	loff_t			pos)
+	struct iov_iter		*from)
 {
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
 	struct inode		*inode = mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			ret;
-	size_t			ocount = 0;
+	size_t			ocount = iov_iter_count(from);
 
 	XFS_STATS_INC(xs_write_calls);
 
-	BUG_ON(iocb->ki_pos != pos);
-
-	ret = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
-	if (ret)
-		return ret;
-
 	if (ocount == 0)
 		return 0;
 
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-		ret = -EIO;
-		goto out;
-	}
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+		return -EIO;
 
 	if (unlikely(file->f_flags & O_DIRECT))
-		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
+		ret = xfs_file_dio_aio_write(iocb, from);
 	else
-		ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos,
-						  ocount);
+		ret = xfs_file_buffered_aio_write(iocb, from);
 
 	if (ret > 0) {
 		ssize_t err;
@@ -804,8 +741,6 @@ xfs_file_aio_write(
 		if (err < 0)
 			ret = err;
 	}
-
-out:
 	return ret;
 }
 
@@ -944,7 +879,7 @@ xfs_dir_open(
 	 */
 	mode = xfs_ilock_data_map_shared(ip);
 	if (ip->i_d.di_nextents > 0)
-		xfs_dir3_data_readahead(NULL, ip, 0, -1);
+		xfs_dir3_data_readahead(ip, 0, -1);
 	xfs_iunlock(ip, mode);
 	return 0;
 }
@@ -1461,12 +1396,12 @@ xfs_file_llseek(
 
 const struct file_operations xfs_file_operations = {
 	.llseek		= xfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= xfs_file_aio_read,
-	.aio_write	= xfs_file_aio_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= xfs_file_read_iter,
+	.write_iter	= xfs_file_write_iter,
 	.splice_read	= xfs_file_splice_read,
-	.splice_write	= xfs_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.unlocked_ioctl	= xfs_file_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= xfs_file_compat_ioctl,
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 12b6e770198..8ec81bed799 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2006-2007 Silicon Graphics, Inc.
+ * Copyright (c) 2014 Christoph Hellwig.
  * All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -32,100 +33,20 @@
 #include "xfs_filestream.h"
 #include "xfs_trace.h"
 
-#ifdef XFS_FILESTREAMS_TRACE
-
-ktrace_t *xfs_filestreams_trace_buf;
-
-STATIC void
-xfs_filestreams_trace(
-	xfs_mount_t	*mp,	/* mount point */
-	int		type,	/* type of trace */
-	const char	*func,	/* source function */
-	int		line,	/* source line number */
-	__psunsigned_t	arg0,
-	__psunsigned_t	arg1,
-	__psunsigned_t	arg2,
-	__psunsigned_t	arg3,
-	__psunsigned_t	arg4,
-	__psunsigned_t	arg5)
-{
-	ktrace_enter(xfs_filestreams_trace_buf,
-		(void *)(__psint_t)(type | (line << 16)),
-		(void *)func,
-		(void *)(__psunsigned_t)current_pid(),
-		(void *)mp,
-		(void *)(__psunsigned_t)arg0,
-		(void *)(__psunsigned_t)arg1,
-		(void *)(__psunsigned_t)arg2,
-		(void *)(__psunsigned_t)arg3,
-		(void *)(__psunsigned_t)arg4,
-		(void *)(__psunsigned_t)arg5,
-		NULL, NULL, NULL, NULL, NULL, NULL);
-}
-
-#define TRACE0(mp,t)			TRACE6(mp,t,0,0,0,0,0,0)
-#define TRACE1(mp,t,a0)			TRACE6(mp,t,a0,0,0,0,0,0)
-#define TRACE2(mp,t,a0,a1)		TRACE6(mp,t,a0,a1,0,0,0,0)
-#define TRACE3(mp,t,a0,a1,a2)		TRACE6(mp,t,a0,a1,a2,0,0,0)
-#define TRACE4(mp,t,a0,a1,a2,a3)	TRACE6(mp,t,a0,a1,a2,a3,0,0)
-#define TRACE5(mp,t,a0,a1,a2,a3,a4)	TRACE6(mp,t,a0,a1,a2,a3,a4,0)
-#define TRACE6(mp,t,a0,a1,a2,a3,a4,a5) \
-	xfs_filestreams_trace(mp, t, __func__, __LINE__, \
-				(__psunsigned_t)a0, (__psunsigned_t)a1, \
-				(__psunsigned_t)a2, (__psunsigned_t)a3, \
-				(__psunsigned_t)a4, (__psunsigned_t)a5)
-
-#define TRACE_AG_SCAN(mp, ag, ag2) \
-		TRACE2(mp, XFS_FSTRM_KTRACE_AGSCAN, ag, ag2);
-#define TRACE_AG_PICK1(mp, max_ag, maxfree) \
-		TRACE2(mp, XFS_FSTRM_KTRACE_AGPICK1, max_ag, maxfree);
-#define TRACE_AG_PICK2(mp, ag, ag2, cnt, free, scan, flag) \
-		TRACE6(mp, XFS_FSTRM_KTRACE_AGPICK2, ag, ag2, \
-			 cnt, free, scan, flag)
-#define TRACE_UPDATE(mp, ip, ag, cnt, ag2, cnt2) \
-		TRACE5(mp, XFS_FSTRM_KTRACE_UPDATE, ip, ag, cnt, ag2, cnt2)
-#define TRACE_FREE(mp, ip, pip, ag, cnt) \
-		TRACE4(mp, XFS_FSTRM_KTRACE_FREE, ip, pip, ag, cnt)
-#define TRACE_LOOKUP(mp, ip, pip, ag, cnt) \
-		TRACE4(mp, XFS_FSTRM_KTRACE_ITEM_LOOKUP, ip, pip, ag, cnt)
-#define TRACE_ASSOCIATE(mp, ip, pip, ag, cnt) \
-		TRACE4(mp, XFS_FSTRM_KTRACE_ASSOCIATE, ip, pip, ag, cnt)
-#define TRACE_MOVEAG(mp, ip, pip, oag, ocnt, nag, ncnt) \
-		TRACE6(mp, XFS_FSTRM_KTRACE_MOVEAG, ip, pip, oag, ocnt, nag, ncnt)
-#define TRACE_ORPHAN(mp, ip, ag) \
-		TRACE2(mp, XFS_FSTRM_KTRACE_ORPHAN, ip, ag);
-
-
-#else
-#define TRACE_AG_SCAN(mp, ag, ag2)
-#define TRACE_AG_PICK1(mp, max_ag, maxfree)
-#define TRACE_AG_PICK2(mp, ag, ag2, cnt, free, scan, flag)
-#define TRACE_UPDATE(mp, ip, ag, cnt, ag2, cnt2)
-#define TRACE_FREE(mp, ip, pip, ag, cnt)
-#define TRACE_LOOKUP(mp, ip, pip, ag, cnt)
-#define TRACE_ASSOCIATE(mp, ip, pip, ag, cnt)
-#define TRACE_MOVEAG(mp, ip, pip, oag, ocnt, nag, ncnt)
-#define TRACE_ORPHAN(mp, ip, ag)
-#endif
-
-static kmem_zone_t *item_zone;
+struct xfs_fstrm_item {
+	struct xfs_mru_cache_elem	mru;
+	struct xfs_inode		*ip;
+	xfs_agnumber_t			ag; /* AG in use for this directory */
+};
 
-/*
- * Structure for associating a file or a directory with an allocation group.
- * The parent directory pointer is only needed for files, but since there will
- * generally be vastly more files than directories in the cache, using the same
- * data structure simplifies the code with very little memory overhead.
- */
-typedef struct fstrm_item
-{
-	xfs_agnumber_t	ag;	/* AG currently in use for the file/directory. */
-	xfs_inode_t	*ip;	/* inode self-pointer. */
-	xfs_inode_t	*pip;	/* Parent directory inode pointer. */
-} fstrm_item_t;
+enum xfs_fstrm_alloc {
+	XFS_PICK_USERDATA = 1,
+	XFS_PICK_LOWSPACE = 2,
+};
 
 /*
  * Allocation group filestream associations are tracked with per-ag atomic
- * counters.  These counters allow _xfs_filestream_pick_ag() to tell whether a
+ * counters.  These counters allow xfs_filestream_pick_ag() to tell whether a
  * particular AG already has active filestreams associated with it. The mount
  * point's m_peraglock is used to protect these counters from per-ag array
  * re-allocation during a growfs operation.  When xfs_growfs_data_private() is
@@ -160,7 +81,7 @@ typedef struct fstrm_item
  * the cache that reference per-ag array elements that have since been
  * reallocated.
  */
-static int
+int
 xfs_filestream_peek_ag(
 	xfs_mount_t	*mp,
 	xfs_agnumber_t	agno)
@@ -200,23 +121,40 @@ xfs_filestream_put_ag(
 	xfs_perag_put(pag);
 }
 
+static void
+xfs_fstrm_free_func(
+	struct xfs_mru_cache_elem *mru)
+{
+	struct xfs_fstrm_item	*item =
+		container_of(mru, struct xfs_fstrm_item, mru);
+
+	xfs_filestream_put_ag(item->ip->i_mount, item->ag);
+
+	trace_xfs_filestream_free(item->ip, item->ag);
+
+	kmem_free(item);
+}
+
 /*
  * Scan the AGs starting at startag looking for an AG that isn't in use and has
  * at least minlen blocks free.
  */
 static int
-_xfs_filestream_pick_ag(
-	xfs_mount_t	*mp,
-	xfs_agnumber_t	startag,
-	xfs_agnumber_t	*agp,
-	int		flags,
-	xfs_extlen_t	minlen)
+xfs_filestream_pick_ag(
+	struct xfs_inode	*ip,
+	xfs_agnumber_t		startag,
+	xfs_agnumber_t		*agp,
+	int			flags,
+	xfs_extlen_t		minlen)
 {
-	int		streams, max_streams;
-	int		err, trylock, nscan;
-	xfs_extlen_t	longest, free, minfree, maxfree = 0;
-	xfs_agnumber_t	ag, max_ag = NULLAGNUMBER;
-	struct xfs_perag *pag;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_fstrm_item	*item;
+	struct xfs_perag	*pag;
+	xfs_extlen_t		longest, free = 0, minfree, maxfree = 0;
+	xfs_agnumber_t		ag, max_ag = NULLAGNUMBER;
+	int			err, trylock, nscan;
+
+	ASSERT(S_ISDIR(ip->i_d.di_mode));
 
 	/* 2% of an AG's blocks must be free for it to be chosen. */
 	minfree = mp->m_sb.sb_agblocks / 50;
@@ -228,8 +166,9 @@ _xfs_filestream_pick_ag(
 	trylock = XFS_ALLOC_FLAG_TRYLOCK;
 
 	for (nscan = 0; 1; nscan++) {
+		trace_xfs_filestream_scan(ip, ag);
+
 		pag = xfs_perag_get(mp, ag);
-		TRACE_AG_SCAN(mp, ag, atomic_read(&pag->pagf_fstrms));
 
 		if (!pag->pagf_init) {
 			err = xfs_alloc_pagf_init(mp, NULL, ag, trylock);
@@ -246,7 +185,6 @@ _xfs_filestream_pick_ag(
 		/* Keep track of the AG with the most free blocks. */
 		if (pag->pagf_freeblks > maxfree) {
 			maxfree = pag->pagf_freeblks;
-			max_streams = atomic_read(&pag->pagf_fstrms);
 			max_ag = ag;
 		}
 
@@ -269,7 +207,6 @@ _xfs_filestream_pick_ag(
 
 			/* Break out, retaining the reference on the AG. */
 			free = pag->pagf_freeblks;
-			streams = atomic_read(&pag->pagf_fstrms);
 			xfs_perag_put(pag);
 			*agp = ag;
 			break;
@@ -305,317 +242,98 @@ next_ag:
 		 */
 		if (max_ag != NULLAGNUMBER) {
 			xfs_filestream_get_ag(mp, max_ag);
-			TRACE_AG_PICK1(mp, max_ag, maxfree);
-			streams = max_streams;
 			free = maxfree;
 			*agp = max_ag;
 			break;
 		}
 
 		/* take AG 0 if none matched */
-		TRACE_AG_PICK1(mp, max_ag, maxfree);
+		trace_xfs_filestream_pick(ip, *agp, free, nscan);
 		*agp = 0;
 		return 0;
 	}
 
-	TRACE_AG_PICK2(mp, startag, *agp, streams, free, nscan, flags);
-
-	return 0;
-}
+	trace_xfs_filestream_pick(ip, *agp, free, nscan);
 
-/*
- * Set the allocation group number for a file or a directory, updating inode
- * references and per-AG references as appropriate.
- */
-static int
-_xfs_filestream_update_ag(
-	xfs_inode_t	*ip,
-	xfs_inode_t	*pip,
-	xfs_agnumber_t	ag)
-{
-	int		err = 0;
-	xfs_mount_t	*mp;
-	xfs_mru_cache_t	*cache;
-	fstrm_item_t	*item;
-	xfs_agnumber_t	old_ag;
-	xfs_inode_t	*old_pip;
-
-	/*
-	 * Either ip is a regular file and pip is a directory, or ip is a
-	 * directory and pip is NULL.
-	 */
-	ASSERT(ip && ((S_ISREG(ip->i_d.di_mode) && pip &&
-	               S_ISDIR(pip->i_d.di_mode)) ||
-	              (S_ISDIR(ip->i_d.di_mode) && !pip)));
-
-	mp = ip->i_mount;
-	cache = mp->m_filestream;
-
-	item = xfs_mru_cache_lookup(cache, ip->i_ino);
-	if (item) {
-		ASSERT(item->ip == ip);
-		old_ag = item->ag;
-		item->ag = ag;
-		old_pip = item->pip;
-		item->pip = pip;
-		xfs_mru_cache_done(cache);
-
-		/*
-		 * If the AG has changed, drop the old ref and take a new one,
-		 * effectively transferring the reference from old to new AG.
-		 */
-		if (ag != old_ag) {
-			xfs_filestream_put_ag(mp, old_ag);
-			xfs_filestream_get_ag(mp, ag);
-		}
-
-		/*
-		 * If ip is a file and its pip has changed, drop the old ref and
-		 * take a new one.
-		 */
-		if (pip && pip != old_pip) {
-			IRELE(old_pip);
-			IHOLD(pip);
-		}
-
-		TRACE_UPDATE(mp, ip, old_ag, xfs_filestream_peek_ag(mp, old_ag),
-				ag, xfs_filestream_peek_ag(mp, ag));
+	if (*agp == NULLAGNUMBER)
 		return 0;
-	}
 
-	item = kmem_zone_zalloc(item_zone, KM_MAYFAIL);
+	err = ENOMEM;
+	item = kmem_alloc(sizeof(*item), KM_MAYFAIL);
 	if (!item)
-		return ENOMEM;
+		goto out_put_ag;
 
-	item->ag = ag;
+	item->ag = *agp;
 	item->ip = ip;
-	item->pip = pip;
 
-	err = xfs_mru_cache_insert(cache, ip->i_ino, item);
+	err = xfs_mru_cache_insert(mp->m_filestream, ip->i_ino, &item->mru);
 	if (err) {
-		kmem_zone_free(item_zone, item);
-		return err;
+		if (err == EEXIST)
+			err = 0;
+		goto out_free_item;
 	}
 
-	/* Take a reference on the AG. */
-	xfs_filestream_get_ag(mp, ag);
-
-	/*
-	 * Take a reference on the inode itself regardless of whether it's a
-	 * regular file or a directory.
-	 */
-	IHOLD(ip);
-
-	/*
-	 * In the case of a regular file, take a reference on the parent inode
-	 * as well to ensure it remains in-core.
-	 */
-	if (pip)
-		IHOLD(pip);
-
-	TRACE_UPDATE(mp, ip, ag, xfs_filestream_peek_ag(mp, ag),
-			ag, xfs_filestream_peek_ag(mp, ag));
-
 	return 0;
-}
-
-/* xfs_fstrm_free_func(): callback for freeing cached stream items. */
-STATIC void
-xfs_fstrm_free_func(
-	unsigned long	ino,
-	void		*data)
-{
-	fstrm_item_t	*item  = (fstrm_item_t *)data;
-	xfs_inode_t	*ip = item->ip;
-
-	ASSERT(ip->i_ino == ino);
-
-	xfs_iflags_clear(ip, XFS_IFILESTREAM);
-
-	/* Drop the reference taken on the AG when the item was added. */
-	xfs_filestream_put_ag(ip->i_mount, item->ag);
-
-	TRACE_FREE(ip->i_mount, ip, item->pip, item->ag,
-		xfs_filestream_peek_ag(ip->i_mount, item->ag));
-
-	/*
-	 * _xfs_filestream_update_ag() always takes a reference on the inode
-	 * itself, whether it's a file or a directory.  Release it here.
-	 * This can result in the inode being freed and so we must
-	 * not hold any inode locks when freeing filesstreams objects
-	 * otherwise we can deadlock here.
-	 */
-	IRELE(ip);
-
-	/*
-	 * In the case of a regular file, _xfs_filestream_update_ag() also
-	 * takes a ref on the parent inode to keep it in-core.  Release that
-	 * too.
-	 */
-	if (item->pip)
-		IRELE(item->pip);
-
-	/* Finally, free the memory allocated for the item. */
-	kmem_zone_free(item_zone, item);
-}
-
-/*
- * xfs_filestream_init() is called at xfs initialisation time to set up the
- * memory zone that will be used for filestream data structure allocation.
- */
-int
-xfs_filestream_init(void)
-{
-	item_zone = kmem_zone_init(sizeof(fstrm_item_t), "fstrm_item");
-	if (!item_zone)
-		return -ENOMEM;
-
-	return 0;
-}
-
-/*
- * xfs_filestream_uninit() is called at xfs termination time to destroy the
- * memory zone that was used for filestream data structure allocation.
- */
-void
-xfs_filestream_uninit(void)
-{
-	kmem_zone_destroy(item_zone);
-}
-
-/*
- * xfs_filestream_mount() is called when a file system is mounted with the
- * filestream option.  It is responsible for allocating the data structures
- * needed to track the new file system's file streams.
- */
-int
-xfs_filestream_mount(
-	xfs_mount_t	*mp)
-{
-	int		err;
-	unsigned int	lifetime, grp_count;
-
-	/*
-	 * The filestream timer tunable is currently fixed within the range of
-	 * one second to four minutes, with five seconds being the default.  The
-	 * group count is somewhat arbitrary, but it'd be nice to adhere to the
-	 * timer tunable to within about 10 percent.  This requires at least 10
-	 * groups.
-	 */
-	lifetime  = xfs_fstrm_centisecs * 10;
-	grp_count = 10;
-
-	err = xfs_mru_cache_create(&mp->m_filestream, lifetime, grp_count,
-	                     xfs_fstrm_free_func);
 
+out_free_item:
+	kmem_free(item);
+out_put_ag:
+	xfs_filestream_put_ag(mp, *agp);
 	return err;
 }
 
-/*
- * xfs_filestream_unmount() is called when a file system that was mounted with
- * the filestream option is unmounted.  It drains the data structures created
- * to track the file system's file streams and frees all the memory that was
- * allocated.
- */
-void
-xfs_filestream_unmount(
-	xfs_mount_t	*mp)
+static struct xfs_inode *
+xfs_filestream_get_parent(
+	struct xfs_inode	*ip)
 {
-	xfs_mru_cache_destroy(mp->m_filestream);
-}
+	struct inode		*inode = VFS_I(ip), *dir = NULL;
+	struct dentry		*dentry, *parent;
 
-/*
- * Return the AG of the filestream the file or directory belongs to, or
- * NULLAGNUMBER otherwise.
- */
-xfs_agnumber_t
-xfs_filestream_lookup_ag(
-	xfs_inode_t	*ip)
-{
-	xfs_mru_cache_t	*cache;
-	fstrm_item_t	*item;
-	xfs_agnumber_t	ag;
-	int		ref;
-
-	if (!S_ISREG(ip->i_d.di_mode) && !S_ISDIR(ip->i_d.di_mode)) {
-		ASSERT(0);
-		return NULLAGNUMBER;
-	}
+	dentry = d_find_alias(inode);
+	if (!dentry)
+		goto out;
 
-	cache = ip->i_mount->m_filestream;
-	item = xfs_mru_cache_lookup(cache, ip->i_ino);
-	if (!item) {
-		TRACE_LOOKUP(ip->i_mount, ip, NULL, NULLAGNUMBER, 0);
-		return NULLAGNUMBER;
-	}
+	parent = dget_parent(dentry);
+	if (!parent)
+		goto out_dput;
 
-	ASSERT(ip == item->ip);
-	ag = item->ag;
-	ref = xfs_filestream_peek_ag(ip->i_mount, ag);
-	xfs_mru_cache_done(cache);
+	dir = igrab(parent->d_inode);
+	dput(parent);
 
-	TRACE_LOOKUP(ip->i_mount, ip, item->pip, ag, ref);
-	return ag;
+out_dput:
+	dput(dentry);
+out:
+	return dir ? XFS_I(dir) : NULL;
 }
 
 /*
- * xfs_filestream_associate() should only be called to associate a regular file
- * with its parent directory.  Calling it with a child directory isn't
- * appropriate because filestreams don't apply to entire directory hierarchies.
- * Creating a file in a child directory of an existing filestream directory
- * starts a new filestream with its own allocation group association.
+ * Find the right allocation group for a file, either by finding an
+ * existing file stream or creating a new one.
  *
- * Returns < 0 on error, 0 if successful association occurred, > 0 if
- * we failed to get an association because of locking issues.
+ * Returns NULLAGNUMBER in case of an error.
  */
-int
-xfs_filestream_associate(
-	xfs_inode_t	*pip,
-	xfs_inode_t	*ip)
+xfs_agnumber_t
+xfs_filestream_lookup_ag(
+	struct xfs_inode	*ip)
 {
-	xfs_mount_t	*mp;
-	xfs_mru_cache_t	*cache;
-	fstrm_item_t	*item;
-	xfs_agnumber_t	ag, rotorstep, startag;
-	int		err = 0;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_inode	*pip = NULL;
+	xfs_agnumber_t		startag, ag = NULLAGNUMBER;
+	struct xfs_mru_cache_elem *mru;
 
-	ASSERT(S_ISDIR(pip->i_d.di_mode));
 	ASSERT(S_ISREG(ip->i_d.di_mode));
-	if (!S_ISDIR(pip->i_d.di_mode) || !S_ISREG(ip->i_d.di_mode))
-		return -EINVAL;
 
-	mp = pip->i_mount;
-	cache = mp->m_filestream;
+	pip = xfs_filestream_get_parent(ip);
+	if (!pip)
+		goto out;
 
-	/*
-	 * We have a problem, Houston.
-	 *
-	 * Taking the iolock here violates inode locking order - we already
-	 * hold the ilock. Hence if we block getting this lock we may never
-	 * wake. Unfortunately, that means if we can't get the lock, we're
-	 * screwed in terms of getting a stream association - we can't spin
-	 * waiting for the lock because someone else is waiting on the lock we
-	 * hold and we cannot drop that as we are in a transaction here.
-	 *
-	 * Lucky for us, this inversion is not a problem because it's a
-	 * directory inode that we are trying to lock here.
-	 *
-	 * So, if we can't get the iolock without sleeping then just give up
-	 */
-	if (!xfs_ilock_nowait(pip, XFS_IOLOCK_EXCL))
-		return 1;
-
-	/* If the parent directory is already in the cache, use its AG. */
-	item = xfs_mru_cache_lookup(cache, pip->i_ino);
-	if (item) {
-		ASSERT(item->ip == pip);
-		ag = item->ag;
-		xfs_mru_cache_done(cache);
-
-		TRACE_LOOKUP(mp, pip, pip, ag, xfs_filestream_peek_ag(mp, ag));
-		err = _xfs_filestream_update_ag(ip, pip, ag);
+	mru = xfs_mru_cache_lookup(mp->m_filestream, pip->i_ino);
+	if (mru) {
+		ag = container_of(mru, struct xfs_fstrm_item, mru)->ag;
+		xfs_mru_cache_done(mp->m_filestream);
 
-		goto exit;
+		trace_xfs_filestream_lookup(ip, ag);
+		goto out;
 	}
 
 	/*
@@ -623,202 +341,94 @@ xfs_filestream_associate(
 	 * use the directory inode's AG.
 	 */
 	if (mp->m_flags & XFS_MOUNT_32BITINODES) {
-		rotorstep = xfs_rotorstep;
+		xfs_agnumber_t	 rotorstep = xfs_rotorstep;
 		startag = (mp->m_agfrotor / rotorstep) % mp->m_sb.sb_agcount;
 		mp->m_agfrotor = (mp->m_agfrotor + 1) %
 		                 (mp->m_sb.sb_agcount * rotorstep);
 	} else
 		startag = XFS_INO_TO_AGNO(mp, pip->i_ino);
 
-	/* Pick a new AG for the parent inode starting at startag. */
-	err = _xfs_filestream_pick_ag(mp, startag, &ag, 0, 0);
-	if (err || ag == NULLAGNUMBER)
-		goto exit_did_pick;
-
-	/* Associate the parent inode with the AG. */
-	err = _xfs_filestream_update_ag(pip, NULL, ag);
-	if (err)
-		goto exit_did_pick;
-
-	/* Associate the file inode with the AG. */
-	err = _xfs_filestream_update_ag(ip, pip, ag);
-	if (err)
-		goto exit_did_pick;
-
-	TRACE_ASSOCIATE(mp, ip, pip, ag, xfs_filestream_peek_ag(mp, ag));
-
-exit_did_pick:
-	/*
-	 * If _xfs_filestream_pick_ag() returned a valid AG, remove the
-	 * reference it took on it, since the file and directory will have taken
-	 * their own now if they were successfully cached.
-	 */
-	if (ag != NULLAGNUMBER)
-		xfs_filestream_put_ag(mp, ag);
-
-exit:
-	xfs_iunlock(pip, XFS_IOLOCK_EXCL);
-	return -err;
+	if (xfs_filestream_pick_ag(pip, startag, &ag, 0, 0))
+		ag = NULLAGNUMBER;
+out:
+	IRELE(pip);
+	return ag;
 }
 
 /*
- * Pick a new allocation group for the current file and its file stream.  This
- * function is called by xfs_bmap_filestreams() with the mount point's per-ag
- * lock held.
+ * Pick a new allocation group for the current file and its file stream.
+ *
+ * This is called when the allocator can't find a suitable extent in the
+ * current AG, and we have to move the stream into a new AG with more space.
  */
 int
 xfs_filestream_new_ag(
 	struct xfs_bmalloca	*ap,
 	xfs_agnumber_t		*agp)
 {
-	int		flags, err;
-	xfs_inode_t	*ip, *pip = NULL;
-	xfs_mount_t	*mp;
-	xfs_mru_cache_t	*cache;
-	xfs_extlen_t	minlen;
-	fstrm_item_t	*dir, *file;
-	xfs_agnumber_t	ag = NULLAGNUMBER;
-
-	ip = ap->ip;
-	mp = ip->i_mount;
-	cache = mp->m_filestream;
-	minlen = ap->length;
-	*agp = NULLAGNUMBER;
+	struct xfs_inode	*ip = ap->ip, *pip;
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_extlen_t		minlen = ap->length;
+	xfs_agnumber_t		startag = 0;
+	int			flags, err = 0;
+	struct xfs_mru_cache_elem *mru;
 
-	/*
-	 * Look for the file in the cache, removing it if it's found.  Doing
-	 * this allows it to be held across the dir lookup that follows.
-	 */
-	file = xfs_mru_cache_remove(cache, ip->i_ino);
-	if (file) {
-		ASSERT(ip == file->ip);
-
-		/* Save the file's parent inode and old AG number for later. */
-		pip = file->pip;
-		ag = file->ag;
-
-		/* Look for the file's directory in the cache. */
-		dir = xfs_mru_cache_lookup(cache, pip->i_ino);
-		if (dir) {
-			ASSERT(pip == dir->ip);
-
-			/*
-			 * If the directory has already moved on to a new AG,
-			 * use that AG as the new AG for the file. Don't
-			 * forget to twiddle the AG refcounts to match the
-			 * movement.
-			 */
-			if (dir->ag != file->ag) {
-				xfs_filestream_put_ag(mp, file->ag);
-				xfs_filestream_get_ag(mp, dir->ag);
-				*agp = file->ag = dir->ag;
-			}
-
-			xfs_mru_cache_done(cache);
-		}
+	*agp = NULLAGNUMBER;
 
-		/*
-		 * Put the file back in the cache.  If this fails, the free
-		 * function needs to be called to tidy up in the same way as if
-		 * the item had simply expired from the cache.
-		 */
-		err = xfs_mru_cache_insert(cache, ip->i_ino, file);
-		if (err) {
-			xfs_fstrm_free_func(ip->i_ino, file);
-			return err;
-		}
+	pip = xfs_filestream_get_parent(ip);
+	if (!pip)
+		goto exit;
 
-		/*
-		 * If the file's AG was moved to the directory's new AG, there's
-		 * nothing more to be done.
-		 */
-		if (*agp != NULLAGNUMBER) {
-			TRACE_MOVEAG(mp, ip, pip,
-					ag, xfs_filestream_peek_ag(mp, ag),
-					*agp, xfs_filestream_peek_ag(mp, *agp));
-			return 0;
-		}
+	mru = xfs_mru_cache_remove(mp->m_filestream, pip->i_ino);
+	if (mru) {
+		struct xfs_fstrm_item *item =
+			container_of(mru, struct xfs_fstrm_item, mru);
+		startag = (item->ag + 1) % mp->m_sb.sb_agcount;
 	}
 
-	/*
-	 * If the file's parent directory is known, take its iolock in exclusive
-	 * mode to prevent two sibling files from racing each other to migrate
-	 * themselves and their parent to different AGs.
-	 *
-	 * Note that we lock the parent directory iolock inside the child
-	 * iolock here.  That's fine as we never hold both parent and child
-	 * iolock in any other place.  This is different from the ilock,
-	 * which requires locking of the child after the parent for namespace
-	 * operations.
-	 */
-	if (pip)
-		xfs_ilock(pip, XFS_IOLOCK_EXCL | XFS_IOLOCK_PARENT);
-
-	/*
-	 * A new AG needs to be found for the file.  If the file's parent
-	 * directory is also known, it will be moved to the new AG as well to
-	 * ensure that files created inside it in future use the new AG.
-	 */
-	ag = (ag == NULLAGNUMBER) ? 0 : (ag + 1) % mp->m_sb.sb_agcount;
 	flags = (ap->userdata ? XFS_PICK_USERDATA : 0) |
 	        (ap->flist->xbf_low ? XFS_PICK_LOWSPACE : 0);
 
-	err = _xfs_filestream_pick_ag(mp, ag, agp, flags, minlen);
-	if (err || *agp == NULLAGNUMBER)
-		goto exit;
+	err = xfs_filestream_pick_ag(pip, startag, agp, flags, minlen);
 
 	/*
-	 * If the file wasn't found in the file cache, then its parent directory
-	 * inode isn't known.  For this to have happened, the file must either
-	 * be pre-existing, or it was created long enough ago that its cache
-	 * entry has expired.  This isn't the sort of usage that the filestreams
-	 * allocator is trying to optimise, so there's no point trying to track
-	 * its new AG somehow in the filestream data structures.
+	 * Only free the item here so we skip over the old AG earlier.
 	 */
-	if (!pip) {
-		TRACE_ORPHAN(mp, ip, *agp);
-		goto exit;
-	}
-
-	/* Associate the parent inode with the AG. */
-	err = _xfs_filestream_update_ag(pip, NULL, *agp);
-	if (err)
-		goto exit;
-
-	/* Associate the file inode with the AG. */
-	err = _xfs_filestream_update_ag(ip, pip, *agp);
-	if (err)
-		goto exit;
-
-	TRACE_MOVEAG(mp, ip, pip, NULLAGNUMBER, 0,
-			*agp, xfs_filestream_peek_ag(mp, *agp));
+	if (mru)
+		xfs_fstrm_free_func(mru);
 
+	IRELE(pip);
 exit:
-	/*
-	 * If _xfs_filestream_pick_ag() returned a valid AG, remove the
-	 * reference it took on it, since the file and directory will have taken
-	 * their own now if they were successfully cached.
-	 */
-	if (*agp != NULLAGNUMBER)
-		xfs_filestream_put_ag(mp, *agp);
-	else
+	if (*agp == NULLAGNUMBER)
 		*agp = 0;
-
-	if (pip)
-		xfs_iunlock(pip, XFS_IOLOCK_EXCL);
-
 	return err;
 }
 
-/*
- * Remove an association between an inode and a filestream object.
- * Typically this is done on last close of an unlinked file.
- */
 void
 xfs_filestream_deassociate(
-	xfs_inode_t	*ip)
+	struct xfs_inode	*ip)
 {
-	xfs_mru_cache_t	*cache = ip->i_mount->m_filestream;
+	xfs_mru_cache_delete(ip->i_mount->m_filestream, ip->i_ino);
+}
+
+int
+xfs_filestream_mount(
+	xfs_mount_t	*mp)
+{
+	/*
+	 * The filestream timer tunable is currently fixed within the range of
+	 * one second to four minutes, with five seconds being the default.  The
+	 * group count is somewhat arbitrary, but it'd be nice to adhere to the
+	 * timer tunable to within about 10 percent.  This requires at least 10
+	 * groups.
+	 */
+	return xfs_mru_cache_create(&mp->m_filestream, xfs_fstrm_centisecs * 10,
+				    10, xfs_fstrm_free_func);
+}
 
-	xfs_mru_cache_delete(cache, ip->i_ino);
+void
+xfs_filestream_unmount(
+	xfs_mount_t	*mp)
+{
+	xfs_mru_cache_destroy(mp->m_filestream);
 }
diff --git a/fs/xfs/xfs_filestream.h b/fs/xfs/xfs_filestream.h
index 6d61dbee856..2ef43406e53 100644
--- a/fs/xfs/xfs_filestream.h
+++ b/fs/xfs/xfs_filestream.h
@@ -20,50 +20,20 @@
 
 struct xfs_mount;
 struct xfs_inode;
-struct xfs_perag;
 struct xfs_bmalloca;
 
-#ifdef XFS_FILESTREAMS_TRACE
-#define XFS_FSTRM_KTRACE_INFO		1
-#define XFS_FSTRM_KTRACE_AGSCAN		2
-#define XFS_FSTRM_KTRACE_AGPICK1	3
-#define XFS_FSTRM_KTRACE_AGPICK2	4
-#define XFS_FSTRM_KTRACE_UPDATE		5
-#define XFS_FSTRM_KTRACE_FREE		6
-#define	XFS_FSTRM_KTRACE_ITEM_LOOKUP	7
-#define	XFS_FSTRM_KTRACE_ASSOCIATE	8
-#define	XFS_FSTRM_KTRACE_MOVEAG		9
-#define	XFS_FSTRM_KTRACE_ORPHAN		10
-
-#define XFS_FSTRM_KTRACE_SIZE	16384
-extern ktrace_t *xfs_filestreams_trace_buf;
-
-#endif
-
-/* allocation selection flags */
-typedef enum xfs_fstrm_alloc {
-	XFS_PICK_USERDATA = 1,
-	XFS_PICK_LOWSPACE = 2,
-} xfs_fstrm_alloc_t;
-
-/* prototypes for filestream.c */
-int xfs_filestream_init(void);
-void xfs_filestream_uninit(void);
 int xfs_filestream_mount(struct xfs_mount *mp);
 void xfs_filestream_unmount(struct xfs_mount *mp);
-xfs_agnumber_t xfs_filestream_lookup_ag(struct xfs_inode *ip);
-int xfs_filestream_associate(struct xfs_inode *dip, struct xfs_inode *ip);
 void xfs_filestream_deassociate(struct xfs_inode *ip);
+xfs_agnumber_t xfs_filestream_lookup_ag(struct xfs_inode *ip);
 int xfs_filestream_new_ag(struct xfs_bmalloca *ap, xfs_agnumber_t *agp);
+int xfs_filestream_peek_ag(struct xfs_mount *mp, xfs_agnumber_t agno);
 
-
-/* filestreams for the inode? */
 static inline int
 xfs_inode_is_filestream(
 	struct xfs_inode	*ip)
 {
 	return (ip->i_mount->m_flags & XFS_MOUNT_FILESTREAMS) ||
-		xfs_iflags_test(ip, XFS_IFILESTREAM) ||
 		(ip->i_d.di_flags & XFS_DIFLAG_FILESTREAM);
 }
 
diff --git a/fs/xfs/xfs_format.h b/fs/xfs/xfs_format.h
index 9898f31d05d..34d85aca305 100644
--- a/fs/xfs/xfs_format.h
+++ b/fs/xfs/xfs_format.h
@@ -202,6 +202,8 @@ typedef __be32 xfs_alloc_ptr_t;
  */
 #define	XFS_IBT_MAGIC		0x49414254	/* 'IABT' */
 #define	XFS_IBT_CRC_MAGIC	0x49414233	/* 'IAB3' */
+#define	XFS_FIBT_MAGIC		0x46494254	/* 'FIBT' */
+#define	XFS_FIBT_CRC_MAGIC	0x46494233	/* 'FIB3' */
 
 typedef	__uint64_t	xfs_inofree_t;
 #define	XFS_INODES_PER_CHUNK		(NBBY * sizeof(xfs_inofree_t))
@@ -244,7 +246,17 @@ typedef __be32 xfs_inobt_ptr_t;
  * block numbers in the AG.
  */
 #define	XFS_IBT_BLOCK(mp)		((xfs_agblock_t)(XFS_CNT_BLOCK(mp) + 1))
-#define	XFS_PREALLOC_BLOCKS(mp)		((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
+#define	XFS_FIBT_BLOCK(mp)		((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
+
+/*
+ * The first data block of an AG depends on whether the filesystem was formatted
+ * with the finobt feature. If so, account for the finobt reserved root btree
+ * block.
+ */
+#define XFS_PREALLOC_BLOCKS(mp) \
+	(xfs_sb_version_hasfinobt(&((mp)->m_sb)) ? \
+	 XFS_FIBT_BLOCK(mp) + 1 : \
+	 XFS_IBT_BLOCK(mp) + 1)
 
 
 
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index c5fc116dfaa..d34703dbcb4 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -238,6 +238,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_LAZYSB	0x4000	/* lazy superblock counters */
 #define XFS_FSOP_GEOM_FLAGS_V5SB	0x8000	/* version 5 superblock */
 #define XFS_FSOP_GEOM_FLAGS_FTYPE	0x10000	/* inode directory types */
+#define XFS_FSOP_GEOM_FLAGS_FINOBT	0x20000	/* free inode btree */
 
 /*
  * Minimum and maximum sizes need for growth checks.
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 02fb943cbf2..d2295561570 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -24,6 +24,8 @@
 #include "xfs_sb.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_inode.h"
 #include "xfs_trans.h"
 #include "xfs_inode_item.h"
@@ -74,23 +76,18 @@ xfs_fs_geometry(
 	}
 	if (new_version >= 3) {
 		geo->version = XFS_FSOP_GEOM_VERSION;
-		geo->flags =
+		geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK |
+			     XFS_FSOP_GEOM_FLAGS_DIRV2 |
 			(xfs_sb_version_hasattr(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_ATTR : 0) |
-			(xfs_sb_version_hasnlink(&mp->m_sb) ?
-				XFS_FSOP_GEOM_FLAGS_NLINK : 0) |
 			(xfs_sb_version_hasquota(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_QUOTA : 0) |
 			(xfs_sb_version_hasalign(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_IALIGN : 0) |
 			(xfs_sb_version_hasdalign(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_DALIGN : 0) |
-			(xfs_sb_version_hasshared(&mp->m_sb) ?
-				XFS_FSOP_GEOM_FLAGS_SHARED : 0) |
 			(xfs_sb_version_hasextflgbit(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_EXTFLG : 0) |
-			(xfs_sb_version_hasdirv2(&mp->m_sb) ?
-				XFS_FSOP_GEOM_FLAGS_DIRV2 : 0) |
 			(xfs_sb_version_hassector(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_SECTOR : 0) |
 			(xfs_sb_version_hasasciici(&mp->m_sb) ?
@@ -104,11 +101,13 @@ xfs_fs_geometry(
 			(xfs_sb_version_hascrc(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_V5SB : 0) |
 			(xfs_sb_version_hasftype(&mp->m_sb) ?
-				XFS_FSOP_GEOM_FLAGS_FTYPE : 0);
+				XFS_FSOP_GEOM_FLAGS_FTYPE : 0) |
+			(xfs_sb_version_hasfinobt(&mp->m_sb) ?
+				XFS_FSOP_GEOM_FLAGS_FINOBT : 0);
 		geo->logsectsize = xfs_sb_version_hassector(&mp->m_sb) ?
 				mp->m_sb.sb_logsectsize : BBSIZE;
 		geo->rtsectsize = mp->m_sb.sb_blocksize;
-		geo->dirblocksize = mp->m_dirblksize;
+		geo->dirblocksize = mp->m_dir_geo->blksize;
 	}
 	if (new_version >= 4) {
 		geo->flags |=
@@ -316,6 +315,10 @@ xfs_growfs_data_private(
 		agi->agi_dirino = cpu_to_be32(NULLAGINO);
 		if (xfs_sb_version_hascrc(&mp->m_sb))
 			uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_uuid);
+		if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+			agi->agi_free_root = cpu_to_be32(XFS_FIBT_BLOCK(mp));
+			agi->agi_free_level = cpu_to_be32(1);
+		}
 		for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++)
 			agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
 
@@ -407,6 +410,34 @@ xfs_growfs_data_private(
 		xfs_buf_relse(bp);
 		if (error)
 			goto error0;
+
+		/*
+		 * FINO btree root block
+		 */
+		if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+			bp = xfs_growfs_get_hdr_buf(mp,
+				XFS_AGB_TO_DADDR(mp, agno, XFS_FIBT_BLOCK(mp)),
+				BTOBB(mp->m_sb.sb_blocksize), 0,
+				&xfs_inobt_buf_ops);
+			if (!bp) {
+				error = ENOMEM;
+				goto error0;
+			}
+
+			if (xfs_sb_version_hascrc(&mp->m_sb))
+				xfs_btree_init_block(mp, bp, XFS_FIBT_CRC_MAGIC,
+						     0, 0, agno,
+						     XFS_BTREE_CRC_BLOCKS);
+			else
+				xfs_btree_init_block(mp, bp, XFS_FIBT_MAGIC, 0,
+						     0, agno, 0);
+
+			error = xfs_bwrite(bp);
+			xfs_buf_relse(bp);
+			if (error)
+				goto error0;
+		}
+
 	}
 	xfs_trans_agblocks_delta(tp, nfree);
 	/*
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index 8f711db61a0..5960e5593fe 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -112,6 +112,66 @@ xfs_inobt_get_rec(
 }
 
 /*
+ * Insert a single inobt record. Cursor must already point to desired location.
+ */
+STATIC int
+xfs_inobt_insert_rec(
+	struct xfs_btree_cur	*cur,
+	__int32_t		freecount,
+	xfs_inofree_t		free,
+	int			*stat)
+{
+	cur->bc_rec.i.ir_freecount = freecount;
+	cur->bc_rec.i.ir_free = free;
+	return xfs_btree_insert(cur, stat);
+}
+
+/*
+ * Insert records describing a newly allocated inode chunk into the inobt.
+ */
+STATIC int
+xfs_inobt_insert(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	xfs_agino_t		newino,
+	xfs_agino_t		newlen,
+	xfs_btnum_t		btnum)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t		agno = be32_to_cpu(agi->agi_seqno);
+	xfs_agino_t		thisino;
+	int			i;
+	int			error;
+
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, btnum);
+
+	for (thisino = newino;
+	     thisino < newino + newlen;
+	     thisino += XFS_INODES_PER_CHUNK) {
+		error = xfs_inobt_lookup(cur, thisino, XFS_LOOKUP_EQ, &i);
+		if (error) {
+			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+			return error;
+		}
+		ASSERT(i == 0);
+
+		error = xfs_inobt_insert_rec(cur, XFS_INODES_PER_CHUNK,
+					     XFS_INOBT_ALL_FREE, &i);
+		if (error) {
+			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+			return error;
+		}
+		ASSERT(i == 1);
+	}
+
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+
+	return 0;
+}
+
+/*
  * Verify that the number of free inodes in the AGI is correct.
  */
 #ifdef DEBUG
@@ -220,10 +280,8 @@ xfs_ialloc_inode_init(
 		if (tp)
 			xfs_icreate_log(tp, agno, agbno, mp->m_ialloc_inos,
 					mp->m_sb.sb_inodesize, length, gen);
-	} else if (xfs_sb_version_hasnlink(&mp->m_sb))
+	} else
 		version = 2;
-	else
-		version = 1;
 
 	for (j = 0; j < nbufs; j++) {
 		/*
@@ -303,13 +361,10 @@ xfs_ialloc_ag_alloc(
 {
 	xfs_agi_t	*agi;		/* allocation group header */
 	xfs_alloc_arg_t	args;		/* allocation argument structure */
-	xfs_btree_cur_t	*cur;		/* inode btree cursor */
 	xfs_agnumber_t	agno;
 	int		error;
-	int		i;
 	xfs_agino_t	newino;		/* new first inode's number */
 	xfs_agino_t	newlen;		/* new number of inodes */
-	xfs_agino_t	thisino;	/* current inode number, for loop */
 	int		isaligned = 0;	/* inode allocation at stripe unit */
 					/* boundary */
 	struct xfs_perag *pag;
@@ -459,29 +514,19 @@ xfs_ialloc_ag_alloc(
 	agi->agi_newino = cpu_to_be32(newino);
 
 	/*
-	 * Insert records describing the new inode chunk into the btree.
+	 * Insert records describing the new inode chunk into the btrees.
 	 */
-	cur = xfs_inobt_init_cursor(args.mp, tp, agbp, agno);
-	for (thisino = newino;
-	     thisino < newino + newlen;
-	     thisino += XFS_INODES_PER_CHUNK) {
-		cur->bc_rec.i.ir_startino = thisino;
-		cur->bc_rec.i.ir_freecount = XFS_INODES_PER_CHUNK;
-		cur->bc_rec.i.ir_free = XFS_INOBT_ALL_FREE;
-		error = xfs_btree_lookup(cur, XFS_LOOKUP_EQ, &i);
-		if (error) {
-			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-			return error;
-		}
-		ASSERT(i == 0);
-		error = xfs_btree_insert(cur, &i);
-		if (error) {
-			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	error = xfs_inobt_insert(args.mp, tp, agbp, newino, newlen,
+				 XFS_BTNUM_INO);
+	if (error)
+		return error;
+
+	if (xfs_sb_version_hasfinobt(&args.mp->m_sb)) {
+		error = xfs_inobt_insert(args.mp, tp, agbp, newino, newlen,
+					 XFS_BTNUM_FINO);
+		if (error)
 			return error;
-		}
-		ASSERT(i == 1);
 	}
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 	/*
 	 * Log allocation group header fields
 	 */
@@ -675,13 +720,10 @@ xfs_ialloc_get_rec(
 }
 
 /*
- * Allocate an inode.
- *
- * The caller selected an AG for us, and made sure that free inodes are
- * available.
+ * Allocate an inode using the inobt-only algorithm.
  */
 STATIC int
-xfs_dialloc_ag(
+xfs_dialloc_ag_inobt(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
 	xfs_ino_t		parent,
@@ -707,7 +749,7 @@ xfs_dialloc_ag(
 	ASSERT(pag->pagi_freecount > 0);
 
  restart_pagno:
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
 	/*
 	 * If pagino is 0 (this is the root inode allocation) use newino.
 	 * This must work because we've just allocated some.
@@ -940,6 +982,294 @@ error0:
 }
 
 /*
+ * Use the free inode btree to allocate an inode based on distance from the
+ * parent. Note that the provided cursor may be deleted and replaced.
+ */
+STATIC int
+xfs_dialloc_ag_finobt_near(
+	xfs_agino_t			pagino,
+	struct xfs_btree_cur		**ocur,
+	struct xfs_inobt_rec_incore	*rec)
+{
+	struct xfs_btree_cur		*lcur = *ocur;	/* left search cursor */
+	struct xfs_btree_cur		*rcur;	/* right search cursor */
+	struct xfs_inobt_rec_incore	rrec;
+	int				error;
+	int				i, j;
+
+	error = xfs_inobt_lookup(lcur, pagino, XFS_LOOKUP_LE, &i);
+	if (error)
+		return error;
+
+	if (i == 1) {
+		error = xfs_inobt_get_rec(lcur, rec, &i);
+		if (error)
+			return error;
+		XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+		/*
+		 * See if we've landed in the parent inode record. The finobt
+		 * only tracks chunks with at least one free inode, so record
+		 * existence is enough.
+		 */
+		if (pagino >= rec->ir_startino &&
+		    pagino < (rec->ir_startino + XFS_INODES_PER_CHUNK))
+			return 0;
+	}
+
+	error = xfs_btree_dup_cursor(lcur, &rcur);
+	if (error)
+		return error;
+
+	error = xfs_inobt_lookup(rcur, pagino, XFS_LOOKUP_GE, &j);
+	if (error)
+		goto error_rcur;
+	if (j == 1) {
+		error = xfs_inobt_get_rec(rcur, &rrec, &j);
+		if (error)
+			goto error_rcur;
+		XFS_WANT_CORRUPTED_GOTO(j == 1, error_rcur);
+	}
+
+	XFS_WANT_CORRUPTED_GOTO(i == 1 || j == 1, error_rcur);
+	if (i == 1 && j == 1) {
+		/*
+		 * Both the left and right records are valid. Choose the closer
+		 * inode chunk to the target.
+		 */
+		if ((pagino - rec->ir_startino + XFS_INODES_PER_CHUNK - 1) >
+		    (rrec.ir_startino - pagino)) {
+			*rec = rrec;
+			xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR);
+			*ocur = rcur;
+		} else {
+			xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR);
+		}
+	} else if (j == 1) {
+		/* only the right record is valid */
+		*rec = rrec;
+		xfs_btree_del_cursor(lcur, XFS_BTREE_NOERROR);
+		*ocur = rcur;
+	} else if (i == 1) {
+		/* only the left record is valid */
+		xfs_btree_del_cursor(rcur, XFS_BTREE_NOERROR);
+	}
+
+	return 0;
+
+error_rcur:
+	xfs_btree_del_cursor(rcur, XFS_BTREE_ERROR);
+	return error;
+}
+
+/*
+ * Use the free inode btree to find a free inode based on a newino hint. If
+ * the hint is NULL, find the first free inode in the AG.
+ */
+STATIC int
+xfs_dialloc_ag_finobt_newino(
+	struct xfs_agi			*agi,
+	struct xfs_btree_cur		*cur,
+	struct xfs_inobt_rec_incore	*rec)
+{
+	int error;
+	int i;
+
+	if (agi->agi_newino != cpu_to_be32(NULLAGINO)) {
+		error = xfs_inobt_lookup(cur, agi->agi_newino, XFS_LOOKUP_EQ,
+					 &i);
+		if (error)
+			return error;
+		if (i == 1) {
+			error = xfs_inobt_get_rec(cur, rec, &i);
+			if (error)
+				return error;
+			XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+			return 0;
+		}
+	}
+
+	/*
+	 * Find the first inode available in the AG.
+	 */
+	error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
+	if (error)
+		return error;
+	XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+	error = xfs_inobt_get_rec(cur, rec, &i);
+	if (error)
+		return error;
+	XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+	return 0;
+}
+
+/*
+ * Update the inobt based on a modification made to the finobt. Also ensure that
+ * the records from both trees are equivalent post-modification.
+ */
+STATIC int
+xfs_dialloc_ag_update_inobt(
+	struct xfs_btree_cur		*cur,	/* inobt cursor */
+	struct xfs_inobt_rec_incore	*frec,	/* finobt record */
+	int				offset) /* inode offset */
+{
+	struct xfs_inobt_rec_incore	rec;
+	int				error;
+	int				i;
+
+	error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i);
+	if (error)
+		return error;
+	XFS_WANT_CORRUPTED_RETURN(i == 1);
+
+	error = xfs_inobt_get_rec(cur, &rec, &i);
+	if (error)
+		return error;
+	XFS_WANT_CORRUPTED_RETURN(i == 1);
+	ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) %
+				   XFS_INODES_PER_CHUNK) == 0);
+
+	rec.ir_free &= ~XFS_INOBT_MASK(offset);
+	rec.ir_freecount--;
+
+	XFS_WANT_CORRUPTED_RETURN((rec.ir_free == frec->ir_free) &&
+				  (rec.ir_freecount == frec->ir_freecount));
+
+	error = xfs_inobt_update(cur, &rec);
+	if (error)
+		return error;
+
+	return 0;
+}
+
+/*
+ * Allocate an inode using the free inode btree, if available. Otherwise, fall
+ * back to the inobt search algorithm.
+ *
+ * The caller selected an AG for us, and made sure that free inodes are
+ * available.
+ */
+STATIC int
+xfs_dialloc_ag(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	xfs_ino_t		parent,
+	xfs_ino_t		*inop)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_agi			*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t			agno = be32_to_cpu(agi->agi_seqno);
+	xfs_agnumber_t			pagno = XFS_INO_TO_AGNO(mp, parent);
+	xfs_agino_t			pagino = XFS_INO_TO_AGINO(mp, parent);
+	struct xfs_perag		*pag;
+	struct xfs_btree_cur		*cur;	/* finobt cursor */
+	struct xfs_btree_cur		*icur;	/* inobt cursor */
+	struct xfs_inobt_rec_incore	rec;
+	xfs_ino_t			ino;
+	int				error;
+	int				offset;
+	int				i;
+
+	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+		return xfs_dialloc_ag_inobt(tp, agbp, parent, inop);
+
+	pag = xfs_perag_get(mp, agno);
+
+	/*
+	 * If pagino is 0 (this is the root inode allocation) use newino.
+	 * This must work because we've just allocated some.
+	 */
+	if (!pagino)
+		pagino = be32_to_cpu(agi->agi_newino);
+
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_FINO);
+
+	error = xfs_check_agi_freecount(cur, agi);
+	if (error)
+		goto error_cur;
+
+	/*
+	 * The search algorithm depends on whether we're in the same AG as the
+	 * parent. If so, find the closest available inode to the parent. If
+	 * not, consider the agi hint or find the first free inode in the AG.
+	 */
+	if (agno == pagno)
+		error = xfs_dialloc_ag_finobt_near(pagino, &cur, &rec);
+	else
+		error = xfs_dialloc_ag_finobt_newino(agi, cur, &rec);
+	if (error)
+		goto error_cur;
+
+	offset = xfs_lowbit64(rec.ir_free);
+	ASSERT(offset >= 0);
+	ASSERT(offset < XFS_INODES_PER_CHUNK);
+	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
+				   XFS_INODES_PER_CHUNK) == 0);
+	ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino + offset);
+
+	/*
+	 * Modify or remove the finobt record.
+	 */
+	rec.ir_free &= ~XFS_INOBT_MASK(offset);
+	rec.ir_freecount--;
+	if (rec.ir_freecount)
+		error = xfs_inobt_update(cur, &rec);
+	else
+		error = xfs_btree_delete(cur, &i);
+	if (error)
+		goto error_cur;
+
+	/*
+	 * The finobt has now been updated appropriately. We haven't updated the
+	 * agi and superblock yet, so we can create an inobt cursor and validate
+	 * the original freecount. If all is well, make the equivalent update to
+	 * the inobt using the finobt record and offset information.
+	 */
+	icur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
+
+	error = xfs_check_agi_freecount(icur, agi);
+	if (error)
+		goto error_icur;
+
+	error = xfs_dialloc_ag_update_inobt(icur, &rec, offset);
+	if (error)
+		goto error_icur;
+
+	/*
+	 * Both trees have now been updated. We must update the perag and
+	 * superblock before we can check the freecount for each btree.
+	 */
+	be32_add_cpu(&agi->agi_freecount, -1);
+	xfs_ialloc_log_agi(tp, agbp, XFS_AGI_FREECOUNT);
+	pag->pagi_freecount--;
+
+	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -1);
+
+	error = xfs_check_agi_freecount(icur, agi);
+	if (error)
+		goto error_icur;
+	error = xfs_check_agi_freecount(cur, agi);
+	if (error)
+		goto error_icur;
+
+	xfs_btree_del_cursor(icur, XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	xfs_perag_put(pag);
+	*inop = ino;
+	return 0;
+
+error_icur:
+	xfs_btree_del_cursor(icur, XFS_BTREE_ERROR);
+error_cur:
+	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	xfs_perag_put(pag);
+	return error;
+}
+
+/*
  * Allocate an inode on disk.
  *
  * Mode is used to tell whether the new inode will need space, and whether it
@@ -1098,78 +1428,34 @@ out_error:
 	return XFS_ERROR(error);
 }
 
-/*
- * Free disk inode.  Carefully avoids touching the incore inode, all
- * manipulations incore are the caller's responsibility.
- * The on-disk inode is not changed by this operation, only the
- * btree (free inode mask) is changed.
- */
-int
-xfs_difree(
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_ino_t	inode,		/* inode to be freed */
-	xfs_bmap_free_t	*flist,		/* extents to free */
-	int		*delete,	/* set if inode cluster was deleted */
-	xfs_ino_t	*first_ino)	/* first inode in deleted cluster */
+STATIC int
+xfs_difree_inobt(
+	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
+	struct xfs_buf			*agbp,
+	xfs_agino_t			agino,
+	struct xfs_bmap_free		*flist,
+	int				*deleted,
+	xfs_ino_t			*first_ino,
+	struct xfs_inobt_rec_incore	*orec)
 {
-	/* REFERENCED */
-	xfs_agblock_t	agbno;	/* block number containing inode */
-	xfs_buf_t	*agbp;	/* buffer containing allocation group header */
-	xfs_agino_t	agino;	/* inode number relative to allocation group */
-	xfs_agnumber_t	agno;	/* allocation group number */
-	xfs_agi_t	*agi;	/* allocation group header */
-	xfs_btree_cur_t	*cur;	/* inode btree cursor */
-	int		error;	/* error return value */
-	int		i;	/* result code */
-	int		ilen;	/* inodes in an inode cluster */
-	xfs_mount_t	*mp;	/* mount structure for filesystem */
-	int		off;	/* offset of inode in inode chunk */
-	xfs_inobt_rec_incore_t rec;	/* btree record */
-	struct xfs_perag *pag;
+	struct xfs_agi			*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t			agno = be32_to_cpu(agi->agi_seqno);
+	struct xfs_perag		*pag;
+	struct xfs_btree_cur		*cur;
+	struct xfs_inobt_rec_incore	rec;
+	int				ilen;
+	int				error;
+	int				i;
+	int				off;
 
-	mp = tp->t_mountp;
-
-	/*
-	 * Break up inode number into its components.
-	 */
-	agno = XFS_INO_TO_AGNO(mp, inode);
-	if (agno >= mp->m_sb.sb_agcount)  {
-		xfs_warn(mp, "%s: agno >= mp->m_sb.sb_agcount (%d >= %d).",
-			__func__, agno, mp->m_sb.sb_agcount);
-		ASSERT(0);
-		return XFS_ERROR(EINVAL);
-	}
-	agino = XFS_INO_TO_AGINO(mp, inode);
-	if (inode != XFS_AGINO_TO_INO(mp, agno, agino))  {
-		xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
-			__func__, (unsigned long long)inode,
-			(unsigned long long)XFS_AGINO_TO_INO(mp, agno, agino));
-		ASSERT(0);
-		return XFS_ERROR(EINVAL);
-	}
-	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
-	if (agbno >= mp->m_sb.sb_agblocks)  {
-		xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).",
-			__func__, agbno, mp->m_sb.sb_agblocks);
-		ASSERT(0);
-		return XFS_ERROR(EINVAL);
-	}
-	/*
-	 * Get the allocation group header.
-	 */
-	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
-	if (error) {
-		xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
-			__func__, error);
-		return error;
-	}
-	agi = XFS_BUF_TO_AGI(agbp);
 	ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
-	ASSERT(agbno < be32_to_cpu(agi->agi_length));
+	ASSERT(XFS_AGINO_TO_AGBNO(mp, agino) < be32_to_cpu(agi->agi_length));
+
 	/*
 	 * Initialize the cursor.
 	 */
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
 
 	error = xfs_check_agi_freecount(cur, agi);
 	if (error)
@@ -1209,7 +1495,7 @@ xfs_difree(
 	if (!(mp->m_flags & XFS_MOUNT_IKEEP) &&
 	    (rec.ir_freecount == mp->m_ialloc_inos)) {
 
-		*delete = 1;
+		*deleted = 1;
 		*first_ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino);
 
 		/*
@@ -1237,7 +1523,7 @@ xfs_difree(
 				  XFS_AGINO_TO_AGBNO(mp, rec.ir_startino)),
 				  mp->m_ialloc_blks, flist, mp);
 	} else {
-		*delete = 0;
+		*deleted = 0;
 
 		error = xfs_inobt_update(cur, &rec);
 		if (error) {
@@ -1261,6 +1547,7 @@ xfs_difree(
 	if (error)
 		goto error0;
 
+	*orec = rec;
 	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 	return 0;
 
@@ -1269,6 +1556,182 @@ error0:
 	return error;
 }
 
+/*
+ * Free an inode in the free inode btree.
+ */
+STATIC int
+xfs_difree_finobt(
+	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
+	struct xfs_buf			*agbp,
+	xfs_agino_t			agino,
+	struct xfs_inobt_rec_incore	*ibtrec) /* inobt record */
+{
+	struct xfs_agi			*agi = XFS_BUF_TO_AGI(agbp);
+	xfs_agnumber_t			agno = be32_to_cpu(agi->agi_seqno);
+	struct xfs_btree_cur		*cur;
+	struct xfs_inobt_rec_incore	rec;
+	int				offset = agino - ibtrec->ir_startino;
+	int				error;
+	int				i;
+
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_FINO);
+
+	error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i);
+	if (error)
+		goto error;
+	if (i == 0) {
+		/*
+		 * If the record does not exist in the finobt, we must have just
+		 * freed an inode in a previously fully allocated chunk. If not,
+		 * something is out of sync.
+		 */
+		XFS_WANT_CORRUPTED_GOTO(ibtrec->ir_freecount == 1, error);
+
+		error = xfs_inobt_insert_rec(cur, ibtrec->ir_freecount,
+					     ibtrec->ir_free, &i);
+		if (error)
+			goto error;
+		ASSERT(i == 1);
+
+		goto out;
+	}
+
+	/*
+	 * Read and update the existing record. We could just copy the ibtrec
+	 * across here, but that would defeat the purpose of having redundant
+	 * metadata. By making the modifications independently, we can catch
+	 * corruptions that we wouldn't see if we just copied from one record
+	 * to another.
+	 */
+	error = xfs_inobt_get_rec(cur, &rec, &i);
+	if (error)
+		goto error;
+	XFS_WANT_CORRUPTED_GOTO(i == 1, error);
+
+	rec.ir_free |= XFS_INOBT_MASK(offset);
+	rec.ir_freecount++;
+
+	XFS_WANT_CORRUPTED_GOTO((rec.ir_free == ibtrec->ir_free) &&
+				(rec.ir_freecount == ibtrec->ir_freecount),
+				error);
+
+	/*
+	 * The content of inobt records should always match between the inobt
+	 * and finobt. The lifecycle of records in the finobt is different from
+	 * the inobt in that the finobt only tracks records with at least one
+	 * free inode. Hence, if all of the inodes are free and we aren't
+	 * keeping inode chunks permanently on disk, remove the record.
+	 * Otherwise, update the record with the new information.
+	 */
+	if (rec.ir_freecount == mp->m_ialloc_inos &&
+	    !(mp->m_flags & XFS_MOUNT_IKEEP)) {
+		error = xfs_btree_delete(cur, &i);
+		if (error)
+			goto error;
+		ASSERT(i == 1);
+	} else {
+		error = xfs_inobt_update(cur, &rec);
+		if (error)
+			goto error;
+	}
+
+out:
+	error = xfs_check_agi_freecount(cur, agi);
+	if (error)
+		goto error;
+
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	return 0;
+
+error:
+	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	return error;
+}
+
+/*
+ * Free disk inode.  Carefully avoids touching the incore inode, all
+ * manipulations incore are the caller's responsibility.
+ * The on-disk inode is not changed by this operation, only the
+ * btree (free inode mask) is changed.
+ */
+int
+xfs_difree(
+	struct xfs_trans	*tp,		/* transaction pointer */
+	xfs_ino_t		inode,		/* inode to be freed */
+	struct xfs_bmap_free	*flist,		/* extents to free */
+	int			*deleted,/* set if inode cluster was deleted */
+	xfs_ino_t		*first_ino)/* first inode in deleted cluster */
+{
+	/* REFERENCED */
+	xfs_agblock_t		agbno;	/* block number containing inode */
+	struct xfs_buf		*agbp;	/* buffer for allocation group header */
+	xfs_agino_t		agino;	/* allocation group inode number */
+	xfs_agnumber_t		agno;	/* allocation group number */
+	int			error;	/* error return value */
+	struct xfs_mount	*mp;	/* mount structure for filesystem */
+	struct xfs_inobt_rec_incore rec;/* btree record */
+
+	mp = tp->t_mountp;
+
+	/*
+	 * Break up inode number into its components.
+	 */
+	agno = XFS_INO_TO_AGNO(mp, inode);
+	if (agno >= mp->m_sb.sb_agcount)  {
+		xfs_warn(mp, "%s: agno >= mp->m_sb.sb_agcount (%d >= %d).",
+			__func__, agno, mp->m_sb.sb_agcount);
+		ASSERT(0);
+		return XFS_ERROR(EINVAL);
+	}
+	agino = XFS_INO_TO_AGINO(mp, inode);
+	if (inode != XFS_AGINO_TO_INO(mp, agno, agino))  {
+		xfs_warn(mp, "%s: inode != XFS_AGINO_TO_INO() (%llu != %llu).",
+			__func__, (unsigned long long)inode,
+			(unsigned long long)XFS_AGINO_TO_INO(mp, agno, agino));
+		ASSERT(0);
+		return XFS_ERROR(EINVAL);
+	}
+	agbno = XFS_AGINO_TO_AGBNO(mp, agino);
+	if (agbno >= mp->m_sb.sb_agblocks)  {
+		xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).",
+			__func__, agbno, mp->m_sb.sb_agblocks);
+		ASSERT(0);
+		return XFS_ERROR(EINVAL);
+	}
+	/*
+	 * Get the allocation group header.
+	 */
+	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
+	if (error) {
+		xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
+			__func__, error);
+		return error;
+	}
+
+	/*
+	 * Fix up the inode allocation btree.
+	 */
+	error = xfs_difree_inobt(mp, tp, agbp, agino, flist, deleted, first_ino,
+				 &rec);
+	if (error)
+		goto error0;
+
+	/*
+	 * Fix up the free inode btree.
+	 */
+	if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
+		error = xfs_difree_finobt(mp, tp, agbp, agino, &rec);
+		if (error)
+			goto error0;
+	}
+
+	return 0;
+
+error0:
+	return error;
+}
+
 STATIC int
 xfs_imap_lookup(
 	struct xfs_mount	*mp,
@@ -1300,7 +1763,7 @@ xfs_imap_lookup(
 	 * we have a record, we need to ensure it contains the inode number
 	 * we are looking up.
 	 */
-	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO);
 	error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
 	if (!error) {
 		if (i)
@@ -1488,7 +1951,16 @@ xfs_ialloc_compute_maxlevels(
 }
 
 /*
- * Log specified fields for the ag hdr (inode section)
+ * Log specified fields for the ag hdr (inode section). The growth of the agi
+ * structure over time requires that we interpret the buffer as two logical
+ * regions delineated by the end of the unlinked list. This is due to the size
+ * of the hash table and its location in the middle of the agi.
+ *
+ * For example, a request to log a field before agi_unlinked and a field after
+ * agi_unlinked could cause us to log the entire hash table and use an excessive
+ * amount of log space. To avoid this behavior, log the region up through
+ * agi_unlinked in one call and the region after agi_unlinked through the end of
+ * the structure in another.
  */
 void
 xfs_ialloc_log_agi(
@@ -1511,6 +1983,8 @@ xfs_ialloc_log_agi(
 		offsetof(xfs_agi_t, agi_newino),
 		offsetof(xfs_agi_t, agi_dirino),
 		offsetof(xfs_agi_t, agi_unlinked),
+		offsetof(xfs_agi_t, agi_free_root),
+		offsetof(xfs_agi_t, agi_free_level),
 		sizeof(xfs_agi_t)
 	};
 #ifdef DEBUG
@@ -1519,15 +1993,30 @@ xfs_ialloc_log_agi(
 	agi = XFS_BUF_TO_AGI(bp);
 	ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC));
 #endif
+
+	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGI_BUF);
+
 	/*
-	 * Compute byte offsets for the first and last fields.
+	 * Compute byte offsets for the first and last fields in the first
+	 * region and log the agi buffer. This only logs up through
+	 * agi_unlinked.
 	 */
-	xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS, &first, &last);
+	if (fields & XFS_AGI_ALL_BITS_R1) {
+		xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R1,
+				  &first, &last);
+		xfs_trans_log_buf(tp, bp, first, last);
+	}
+
 	/*
-	 * Log the allocation group inode header buffer.
+	 * Mask off the bits in the first region and calculate the first and
+	 * last field offsets for any bits in the second region.
 	 */
-	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGI_BUF);
-	xfs_trans_log_buf(tp, bp, first, last);
+	fields &= ~XFS_AGI_ALL_BITS_R1;
+	if (fields) {
+		xfs_btree_offsets(fields, offsets, XFS_AGI_NUM_BITS_R2,
+				  &first, &last);
+		xfs_trans_log_buf(tp, bp, first, last);
+	}
 }
 
 #ifdef DEBUG
@@ -1640,7 +2129,6 @@ xfs_read_agi(
 	if (error)
 		return error;
 
-	ASSERT(!xfs_buf_geterror(*bpp));
 	xfs_buf_set_ref(*bpp, XFS_AGI_REF);
 	return 0;
 }
diff --git a/fs/xfs/xfs_ialloc.h b/fs/xfs/xfs_ialloc.h
index 812365d17e6..95ad1c002d6 100644
--- a/fs/xfs/xfs_ialloc.h
+++ b/fs/xfs/xfs_ialloc.h
@@ -90,7 +90,7 @@ xfs_difree(
 	struct xfs_trans *tp,		/* transaction pointer */
 	xfs_ino_t	inode,		/* inode to be freed */
 	struct xfs_bmap_free *flist,	/* extents to free */
-	int		*delete,	/* set if inode cluster was deleted */
+	int		*deleted,	/* set if inode cluster was deleted */
 	xfs_ino_t	*first_ino);	/* first inode in deleted cluster */
 
 /*
diff --git a/fs/xfs/xfs_ialloc_btree.c b/fs/xfs/xfs_ialloc_btree.c
index 7e309b11e87..726f83a681a 100644
--- a/fs/xfs/xfs_ialloc_btree.c
+++ b/fs/xfs/xfs_ialloc_btree.c
@@ -49,7 +49,8 @@ xfs_inobt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_inobt_init_cursor(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agbp, cur->bc_private.a.agno);
+			cur->bc_private.a.agbp, cur->bc_private.a.agno,
+			cur->bc_btnum);
 }
 
 STATIC void
@@ -66,12 +67,26 @@ xfs_inobt_set_root(
 	xfs_ialloc_log_agi(cur->bc_tp, agbp, XFS_AGI_ROOT | XFS_AGI_LEVEL);
 }
 
+STATIC void
+xfs_finobt_set_root(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*nptr,
+	int			inc)	/* level change */
+{
+	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
+
+	agi->agi_free_root = nptr->s;
+	be32_add_cpu(&agi->agi_free_level, inc);
+	xfs_ialloc_log_agi(cur->bc_tp, agbp,
+			   XFS_AGI_FREE_ROOT | XFS_AGI_FREE_LEVEL);
+}
+
 STATIC int
 xfs_inobt_alloc_block(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*start,
 	union xfs_btree_ptr	*new,
-	int			length,
 	int			*stat)
 {
 	xfs_alloc_arg_t		args;		/* block allocation args */
@@ -173,6 +188,17 @@ xfs_inobt_init_ptr_from_cur(
 	ptr->s = agi->agi_root;
 }
 
+STATIC void
+xfs_finobt_init_ptr_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr)
+{
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(cur->bc_private.a.agbp);
+
+	ASSERT(cur->bc_private.a.agno == be32_to_cpu(agi->agi_seqno));
+	ptr->s = agi->agi_free_root;
+}
+
 STATIC __int64_t
 xfs_inobt_key_diff(
 	struct xfs_btree_cur	*cur,
@@ -203,6 +229,7 @@ xfs_inobt_verify(
 	 */
 	switch (block->bb_magic) {
 	case cpu_to_be32(XFS_IBT_CRC_MAGIC):
+	case cpu_to_be32(XFS_FIBT_CRC_MAGIC):
 		if (!xfs_sb_version_hascrc(&mp->m_sb))
 			return false;
 		if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_uuid))
@@ -214,6 +241,7 @@ xfs_inobt_verify(
 			return false;
 		/* fall through */
 	case cpu_to_be32(XFS_IBT_MAGIC):
+	case cpu_to_be32(XFS_FIBT_MAGIC):
 		break;
 	default:
 		return 0;
@@ -317,6 +345,28 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
 #endif
 };
 
+static const struct xfs_btree_ops xfs_finobt_ops = {
+	.rec_len		= sizeof(xfs_inobt_rec_t),
+	.key_len		= sizeof(xfs_inobt_key_t),
+
+	.dup_cursor		= xfs_inobt_dup_cursor,
+	.set_root		= xfs_finobt_set_root,
+	.alloc_block		= xfs_inobt_alloc_block,
+	.free_block		= xfs_inobt_free_block,
+	.get_minrecs		= xfs_inobt_get_minrecs,
+	.get_maxrecs		= xfs_inobt_get_maxrecs,
+	.init_key_from_rec	= xfs_inobt_init_key_from_rec,
+	.init_rec_from_key	= xfs_inobt_init_rec_from_key,
+	.init_rec_from_cur	= xfs_inobt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfs_finobt_init_ptr_from_cur,
+	.key_diff		= xfs_inobt_key_diff,
+	.buf_ops		= &xfs_inobt_buf_ops,
+#if defined(DEBUG) || defined(XFS_WARN)
+	.keys_inorder		= xfs_inobt_keys_inorder,
+	.recs_inorder		= xfs_inobt_recs_inorder,
+#endif
+};
+
 /*
  * Allocate a new inode btree cursor.
  */
@@ -325,7 +375,8 @@ xfs_inobt_init_cursor(
 	struct xfs_mount	*mp,		/* file system mount point */
 	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_buf		*agbp,		/* buffer for agi structure */
-	xfs_agnumber_t		agno)		/* allocation group number */
+	xfs_agnumber_t		agno,		/* allocation group number */
+	xfs_btnum_t		btnum)		/* ialloc or free ino btree */
 {
 	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
 	struct xfs_btree_cur	*cur;
@@ -334,11 +385,17 @@ xfs_inobt_init_cursor(
 
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;
-	cur->bc_nlevels = be32_to_cpu(agi->agi_level);
-	cur->bc_btnum = XFS_BTNUM_INO;
+	cur->bc_btnum = btnum;
+	if (btnum == XFS_BTNUM_INO) {
+		cur->bc_nlevels = be32_to_cpu(agi->agi_level);
+		cur->bc_ops = &xfs_inobt_ops;
+	} else {
+		cur->bc_nlevels = be32_to_cpu(agi->agi_free_level);
+		cur->bc_ops = &xfs_finobt_ops;
+	}
+
 	cur->bc_blocklog = mp->m_sb.sb_blocklog;
 
-	cur->bc_ops = &xfs_inobt_ops;
 	if (xfs_sb_version_hascrc(&mp->m_sb))
 		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
diff --git a/fs/xfs/xfs_ialloc_btree.h b/fs/xfs/xfs_ialloc_btree.h
index f38b22011c4..d7ebea72c2d 100644
--- a/fs/xfs/xfs_ialloc_btree.h
+++ b/fs/xfs/xfs_ialloc_btree.h
@@ -58,7 +58,8 @@ struct xfs_mount;
 		 ((index) - 1) * sizeof(xfs_inobt_ptr_t)))
 
 extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_mount *,
-		struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t);
+		struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t,
+		xfs_btnum_t);
 extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int);
 
 #endif	/* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 98d35244eec..c48df5f25b9 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -507,8 +507,7 @@ STATIC int
 xfs_inode_ag_walk(
 	struct xfs_mount	*mp,
 	struct xfs_perag	*pag,
-	int			(*execute)(struct xfs_inode *ip,
-					   struct xfs_perag *pag, int flags,
+	int			(*execute)(struct xfs_inode *ip, int flags,
 					   void *args),
 	int			flags,
 	void			*args,
@@ -582,7 +581,7 @@ restart:
 		for (i = 0; i < nr_found; i++) {
 			if (!batch[i])
 				continue;
-			error = execute(batch[i], pag, flags, args);
+			error = execute(batch[i], flags, args);
 			IRELE(batch[i]);
 			if (error == EAGAIN) {
 				skipped++;
@@ -636,8 +635,7 @@ xfs_eofblocks_worker(
 int
 xfs_inode_ag_iterator(
 	struct xfs_mount	*mp,
-	int			(*execute)(struct xfs_inode *ip,
-					   struct xfs_perag *pag, int flags,
+	int			(*execute)(struct xfs_inode *ip, int flags,
 					   void *args),
 	int			flags,
 	void			*args)
@@ -664,8 +662,7 @@ xfs_inode_ag_iterator(
 int
 xfs_inode_ag_iterator_tag(
 	struct xfs_mount	*mp,
-	int			(*execute)(struct xfs_inode *ip,
-					   struct xfs_perag *pag, int flags,
+	int			(*execute)(struct xfs_inode *ip, int flags,
 					   void *args),
 	int			flags,
 	void			*args,
@@ -1209,7 +1206,6 @@ xfs_inode_match_id(
 STATIC int
 xfs_inode_free_eofblocks(
 	struct xfs_inode	*ip,
-	struct xfs_perag	*pag,
 	int			flags,
 	void			*args)
 {
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 9ed68bb750f..9cf017b899b 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -60,12 +60,10 @@ int xfs_icache_free_eofblocks(struct xfs_mount *, struct xfs_eofblocks *);
 void xfs_eofblocks_worker(struct work_struct *);
 
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
-	int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag,
-		int flags, void *args),
+	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args);
 int xfs_inode_ag_iterator_tag(struct xfs_mount *mp,
-	int (*execute)(struct xfs_inode *ip, struct xfs_perag *pag,
-		int flags, void *args),
+	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args, int tag);
 
 static inline int
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 768087bedba..a6115fe1ac9 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -655,7 +655,6 @@ xfs_ialloc(
 	uint		flags;
 	int		error;
 	timespec_t	tv;
-	int		filestreams = 0;
 
 	/*
 	 * Call the space management code to pick
@@ -682,6 +681,14 @@ xfs_ialloc(
 		return error;
 	ASSERT(ip != NULL);
 
+	/*
+	 * We always convert v1 inodes to v2 now - we only support filesystems
+	 * with >= v2 inode capability, so there is no reason for ever leaving
+	 * an inode in v1 format.
+	 */
+	if (ip->i_d.di_version == 1)
+		ip->i_d.di_version = 2;
+
 	ip->i_d.di_mode = mode;
 	ip->i_d.di_onlink = 0;
 	ip->i_d.di_nlink = nlink;
@@ -691,27 +698,6 @@ xfs_ialloc(
 	xfs_set_projid(ip, prid);
 	memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
 
-	/*
-	 * If the superblock version is up to where we support new format
-	 * inodes and this is currently an old format inode, then change
-	 * the inode version number now.  This way we only do the conversion
-	 * here rather than here and in the flush/logging code.
-	 */
-	if (xfs_sb_version_hasnlink(&mp->m_sb) &&
-	    ip->i_d.di_version == 1) {
-		ip->i_d.di_version = 2;
-		/*
-		 * We've already zeroed the old link count, the projid field,
-		 * and the pad field.
-		 */
-	}
-
-	/*
-	 * Project ids won't be stored on disk if we are using a version 1 inode.
-	 */
-	if ((prid != 0) && (ip->i_d.di_version == 1))
-		xfs_bump_ino_vers2(tp, ip);
-
 	if (pip && XFS_INHERIT_GID(pip)) {
 		ip->i_d.di_gid = pip->i_d.di_gid;
 		if ((pip->i_d.di_mode & S_ISGID) && S_ISDIR(mode)) {
@@ -772,13 +758,6 @@ xfs_ialloc(
 		flags |= XFS_ILOG_DEV;
 		break;
 	case S_IFREG:
-		/*
-		 * we can't set up filestreams until after the VFS inode
-		 * is set up properly.
-		 */
-		if (pip && xfs_inode_is_filestream(pip))
-			filestreams = 1;
-		/* fall through */
 	case S_IFDIR:
 		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
 			uint	di_flags = 0;
@@ -844,15 +823,6 @@ xfs_ialloc(
 	/* now that we have an i_mode we can setup inode ops and unlock */
 	xfs_setup_inode(ip);
 
-	/* now we have set up the vfs inode we can associate the filestream */
-	if (filestreams) {
-		error = xfs_filestream_associate(pip, ip);
-		if (error < 0)
-			return -error;
-		if (!error)
-			xfs_iflags_set(ip, XFS_IFILESTREAM);
-	}
-
 	*ipp = ip;
 	return 0;
 }
@@ -1073,40 +1043,6 @@ xfs_droplink(
 }
 
 /*
- * This gets called when the inode's version needs to be changed from 1 to 2.
- * Currently this happens when the nlink field overflows the old 16-bit value
- * or when chproj is called to change the project for the first time.
- * As a side effect the superblock version will also get rev'd
- * to contain the NLINK bit.
- */
-void
-xfs_bump_ino_vers2(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip)
-{
-	xfs_mount_t	*mp;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	ASSERT(ip->i_d.di_version == 1);
-
-	ip->i_d.di_version = 2;
-	ip->i_d.di_onlink = 0;
-	memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
-	mp = tp->t_mountp;
-	if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
-		spin_lock(&mp->m_sb_lock);
-		if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
-			xfs_sb_version_addnlink(&mp->m_sb);
-			spin_unlock(&mp->m_sb_lock);
-			xfs_mod_sb(tp, XFS_SB_VERSIONNUM);
-		} else {
-			spin_unlock(&mp->m_sb_lock);
-		}
-	}
-	/* Caller must log the inode */
-}
-
-/*
  * Increment the link count on an inode & log the change.
  */
 int
@@ -1116,22 +1052,10 @@ xfs_bumplink(
 {
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
+	ASSERT(ip->i_d.di_version > 1);
 	ASSERT(ip->i_d.di_nlink > 0 || (VFS_I(ip)->i_state & I_LINKABLE));
 	ip->i_d.di_nlink++;
 	inc_nlink(VFS_I(ip));
-	if ((ip->i_d.di_version == 1) &&
-	    (ip->i_d.di_nlink > XFS_MAXLINK_1)) {
-		/*
-		 * The inode has increased its number of links beyond
-		 * what can fit in an old format inode.  It now needs
-		 * to be converted to a version 2 inode with a 32 bit
-		 * link count.  If this is the first inode in the file
-		 * system to do this, then we need to bump the superblock
-		 * version number as well.
-		 */
-		xfs_bump_ino_vers2(tp, ip);
-	}
-
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	return 0;
 }
@@ -1699,16 +1623,6 @@ xfs_release(
 		int truncated;
 
 		/*
-		 * If we are using filestreams, and we have an unlinked
-		 * file that we are processing the last close on, then nothing
-		 * will be able to reopen and write to this file. Purge this
-		 * inode from the filestreams cache so that it doesn't delay
-		 * teardown of the inode.
-		 */
-		if ((ip->i_d.di_nlink == 0) && xfs_inode_is_filestream(ip))
-			xfs_filestream_deassociate(ip);
-
-		/*
 		 * If we previously truncated this file and removed old data
 		 * in the process, we want to initiate "early" writeout on
 		 * the last close.  This is an attempt to combat the notorious
@@ -1838,9 +1752,33 @@ xfs_inactive_ifree(
 	int			error;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree, 0, 0);
+
+	/*
+	 * The ifree transaction might need to allocate blocks for record
+	 * insertion to the finobt. We don't want to fail here at ENOSPC, so
+	 * allow ifree to dip into the reserved block pool if necessary.
+	 *
+	 * Freeing large sets of inodes generally means freeing inode chunks,
+	 * directory and file data blocks, so this should be relatively safe.
+	 * Only under severe circumstances should it be possible to free enough
+	 * inodes to exhaust the reserve block pool via finobt expansion while
+	 * at the same time not creating free space in the filesystem.
+	 *
+	 * Send a warning if the reservation does happen to fail, as the inode
+	 * now remains allocated and sits on the unlinked list until the fs is
+	 * repaired.
+	 */
+	tp->t_flags |= XFS_TRANS_RESERVE;
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ifree,
+				  XFS_IFREE_SPACE_RES(mp), 0);
 	if (error) {
-		ASSERT(XFS_FORCED_SHUTDOWN(mp));
+		if (error == ENOSPC) {
+			xfs_warn_ratelimited(mp,
+			"Failed to remove inode(s) from unlinked list. "
+			"Please free space, unmount and run xfs_repair.");
+		} else {
+			ASSERT(XFS_FORCED_SHUTDOWN(mp));
+		}
 		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES);
 		return error;
 	}
@@ -2664,13 +2602,7 @@ xfs_remove(
 	if (error)
 		goto std_return;
 
-	/*
-	 * If we are using filestreams, kill the stream association.
-	 * If the file is still open it may get a new one but that
-	 * will get killed on last close in xfs_close() so we don't
-	 * have to worry about that.
-	 */
-	if (!is_dir && link_zero && xfs_inode_is_filestream(ip))
+	if (is_dir && xfs_inode_is_filestream(ip))
 		xfs_filestream_deassociate(ip);
 
 	return 0;
@@ -3258,6 +3190,7 @@ xfs_iflush_int(
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
 	ASSERT(iip != NULL && iip->ili_fields != 0);
+	ASSERT(ip->i_d.di_version > 1);
 
 	/* set *dip = inode's place in the buffer */
 	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
@@ -3318,7 +3251,7 @@ xfs_iflush_int(
 	}
 
 	/*
-	 * Inode item log recovery for v1/v2 inodes are dependent on the
+	 * Inode item log recovery for v2 inodes are dependent on the
 	 * di_flushiter count for correct sequencing. We bump the flush
 	 * iteration count so we can detect flushes which postdate a log record
 	 * during recovery. This is redundant as we now log every change and
@@ -3341,40 +3274,9 @@ xfs_iflush_int(
 	if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
 		ip->i_d.di_flushiter = 0;
 
-	/*
-	 * If this is really an old format inode and the superblock version
-	 * has not been updated to support only new format inodes, then
-	 * convert back to the old inode format.  If the superblock version
-	 * has been updated, then make the conversion permanent.
-	 */
-	ASSERT(ip->i_d.di_version == 1 || xfs_sb_version_hasnlink(&mp->m_sb));
-	if (ip->i_d.di_version == 1) {
-		if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
-			/*
-			 * Convert it back.
-			 */
-			ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1);
-			dip->di_onlink = cpu_to_be16(ip->i_d.di_nlink);
-		} else {
-			/*
-			 * The superblock version has already been bumped,
-			 * so just make the conversion to the new inode
-			 * format permanent.
-			 */
-			ip->i_d.di_version = 2;
-			dip->di_version = 2;
-			ip->i_d.di_onlink = 0;
-			dip->di_onlink = 0;
-			memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
-			memset(&(dip->di_pad[0]), 0,
-			      sizeof(dip->di_pad));
-			ASSERT(xfs_get_projid(ip) == 0);
-		}
-	}
-
-	xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK, bp);
+	xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
 	if (XFS_IFORK_Q(ip))
-		xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK, bp);
+		xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
 	xfs_inobp_check(mp, bp);
 
 	/*
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index f2fcde52b66..f72bffa6726 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -209,7 +209,6 @@ xfs_get_initial_prid(struct xfs_inode *dp)
 #define XFS_ISTALE		(1 << 1) /* inode has been staled */
 #define XFS_IRECLAIMABLE	(1 << 2) /* inode can be reclaimed */
 #define XFS_INEW		(1 << 3) /* inode has just been allocated */
-#define XFS_IFILESTREAM		(1 << 4) /* inode is in a filestream dir. */
 #define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
 #define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
 #define __XFS_IFLOCK_BIT	7	 /* inode is being flushed right now */
@@ -225,8 +224,7 @@ xfs_get_initial_prid(struct xfs_inode *dp)
  */
 #define XFS_IRECLAIM_RESET_FLAGS	\
 	(XFS_IRECLAIMABLE | XFS_IRECLAIM | \
-	 XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | \
-	 XFS_IFILESTREAM);
+	 XFS_IDIRTY_RELEASE | XFS_ITRUNCATED)
 
 /*
  * Synchronize processes attempting to flush the in-core inode back to disk.
@@ -379,7 +377,6 @@ int		xfs_dir_ialloc(struct xfs_trans **, struct xfs_inode *, umode_t,
 			       struct xfs_inode **, int *);
 int		xfs_droplink(struct xfs_trans *, struct xfs_inode *);
 int		xfs_bumplink(struct xfs_trans *, struct xfs_inode *);
-void		xfs_bump_ino_vers2(struct xfs_trans *, struct xfs_inode *);
 
 /* from xfs_file.c */
 int		xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
diff --git a/fs/xfs/xfs_inode_buf.c b/fs/xfs/xfs_inode_buf.c
index 24e993996bd..cb35ae41d4a 100644
--- a/fs/xfs/xfs_inode_buf.c
+++ b/fs/xfs/xfs_inode_buf.c
@@ -437,17 +437,16 @@ xfs_iread(
 	}
 
 	/*
-	 * The inode format changed when we moved the link count and
-	 * made it 32 bits long.  If this is an old format inode,
-	 * convert it in memory to look like a new one.  If it gets
-	 * flushed to disk we will convert back before flushing or
-	 * logging it.  We zero out the new projid field and the old link
-	 * count field.  We'll handle clearing the pad field (the remains
-	 * of the old uuid field) when we actually convert the inode to
-	 * the new format. We don't change the version number so that we
-	 * can distinguish this from a real new format inode.
+	 * Automatically convert version 1 inode formats in memory to version 2
+	 * inode format. If the inode is modified, it will get logged and
+	 * rewritten as a version 2 inode. We can do this because we set the
+	 * superblock feature bit for v2 inodes unconditionally during mount
+	 * and it means the reast of the code can assume the inode version is 2
+	 * or higher.
 	 */
 	if (ip->i_d.di_version == 1) {
+		ip->i_d.di_version = 2;
+		memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
 		ip->i_d.di_nlink = ip->i_d.di_onlink;
 		ip->i_d.di_onlink = 0;
 		xfs_set_projid(ip, 0);
diff --git a/fs/xfs/xfs_inode_fork.c b/fs/xfs/xfs_inode_fork.c
index 73514c0486b..b031e8d0d92 100644
--- a/fs/xfs/xfs_inode_fork.c
+++ b/fs/xfs/xfs_inode_fork.c
@@ -798,8 +798,7 @@ xfs_iflush_fork(
 	xfs_inode_t		*ip,
 	xfs_dinode_t		*dip,
 	xfs_inode_log_item_t	*iip,
-	int			whichfork,
-	xfs_buf_t		*bp)
+	int			whichfork)
 {
 	char			*cp;
 	xfs_ifork_t		*ifp;
diff --git a/fs/xfs/xfs_inode_fork.h b/fs/xfs/xfs_inode_fork.h
index eb329a1ea88..7d3b1ed6dcb 100644
--- a/fs/xfs/xfs_inode_fork.h
+++ b/fs/xfs/xfs_inode_fork.h
@@ -127,8 +127,7 @@ typedef struct xfs_ifork {
 
 int		xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *);
 void		xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
-				struct xfs_inode_log_item *, int,
-				struct xfs_buf *);
+				struct xfs_inode_log_item *, int);
 void		xfs_idestroy_fork(struct xfs_inode *, int);
 void		xfs_idata_realloc(struct xfs_inode *, int, int);
 void		xfs_iroot_realloc(struct xfs_inode *, int, int);
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 686889b4a1e..a640137b357 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -145,34 +145,6 @@ xfs_inode_item_size(
 		xfs_inode_item_attr_fork_size(iip, nvecs, nbytes);
 }
 
-/*
- * If this is a v1 format inode, then we need to log it as such.  This means
- * that we have to copy the link count from the new field to the old.  We
- * don't have to worry about the new fields, because nothing trusts them as
- * long as the old inode version number is there.
- */
-STATIC void
-xfs_inode_item_format_v1_inode(
-	struct xfs_inode	*ip)
-{
-	if (!xfs_sb_version_hasnlink(&ip->i_mount->m_sb)) {
-		/*
-		 * Convert it back.
-		 */
-		ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1);
-		ip->i_d.di_onlink = ip->i_d.di_nlink;
-	} else {
-		/*
-		 * The superblock version has already been bumped,
-		 * so just make the conversion to the new inode
-		 * format permanent.
-		 */
-		ip->i_d.di_version = 2;
-		ip->i_d.di_onlink = 0;
-		memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
-	}
-}
-
 STATIC void
 xfs_inode_item_format_data_fork(
 	struct xfs_inode_log_item *iip,
@@ -370,6 +342,8 @@ xfs_inode_item_format(
 	struct xfs_inode_log_format *ilf;
 	struct xfs_log_iovec	*vecp = NULL;
 
+	ASSERT(ip->i_d.di_version > 1);
+
 	ilf = xlog_prepare_iovec(lv, &vecp, XLOG_REG_TYPE_IFORMAT);
 	ilf->ilf_type = XFS_LI_INODE;
 	ilf->ilf_ino = ip->i_ino;
@@ -380,8 +354,6 @@ xfs_inode_item_format(
 	ilf->ilf_size = 2; /* format + core */
 	xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
 
-	if (ip->i_d.di_version == 1)
-		xfs_inode_item_format_v1_inode(ip);
 	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ICORE,
 			&ip->i_d,
 			xfs_icdinode_size(ip->i_d.di_version));
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 0b18776b075..8bc1bbce745 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -543,10 +543,11 @@ xfs_attrmulti_by_handle(
 
 	ops = memdup_user(am_hreq.ops, size);
 	if (IS_ERR(ops)) {
-		error = PTR_ERR(ops);
+		error = -PTR_ERR(ops);
 		goto out_dput;
 	}
 
+	error = ENOMEM;
 	attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
 	if (!attr_name)
 		goto out_kfree_ops;
@@ -556,7 +557,7 @@ xfs_attrmulti_by_handle(
 		ops[i].am_error = strncpy_from_user((char *)attr_name,
 				ops[i].am_attrname, MAXNAMELEN);
 		if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
-			error = -ERANGE;
+			error = ERANGE;
 		if (ops[i].am_error < 0)
 			break;
 
@@ -1215,7 +1216,7 @@ xfs_ioctl_setattr(
 		 * cleared upon successful return from chown()
 		 */
 		if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
-		    !inode_capable(VFS_I(ip), CAP_FSETID))
+		    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
 			ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
 
 		/*
@@ -1227,15 +1228,8 @@ xfs_ioctl_setattr(
 				olddquot = xfs_qm_vop_chown(tp, ip,
 							&ip->i_pdquot, pdqp);
 			}
+			ASSERT(ip->i_d.di_version > 1);
 			xfs_set_projid(ip, fa->fsx_projid);
-
-			/*
-			 * We may have to rev the inode as well as
-			 * the superblock version number since projids didn't
-			 * exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
-			 */
-			if (ip->i_d.di_version == 1)
-				xfs_bump_ino_vers2(tp, ip);
 		}
 
 	}
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index a7992f8de9d..944d5baa710 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -424,10 +424,11 @@ xfs_compat_attrmulti_by_handle(
 
 	ops = memdup_user(compat_ptr(am_hreq.ops), size);
 	if (IS_ERR(ops)) {
-		error = PTR_ERR(ops);
+		error = -PTR_ERR(ops);
 		goto out_dput;
 	}
 
+	error = ENOMEM;
 	attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
 	if (!attr_name)
 		goto out_kfree_ops;
@@ -438,7 +439,7 @@ xfs_compat_attrmulti_by_handle(
 				compat_ptr(ops[i].am_attrname),
 				MAXNAMELEN);
 		if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
-			error = -ERANGE;
+			error = ERANGE;
 		if (ops[i].am_error < 0)
 			break;
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 3b80ebae05f..6d3ec2b6ee2 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -730,7 +730,7 @@ xfs_iomap_write_allocate(
 			 */
 			nimaps = 1;
 			end_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
-			error = xfs_bmap_last_offset(NULL, ip, &last_block,
+			error = xfs_bmap_last_offset(ip, &last_block,
 							XFS_DATA_FORK);
 			if (error)
 				goto trans_cancel;
@@ -749,8 +749,7 @@ xfs_iomap_write_allocate(
 			 * pointer that the caller gave to us.
 			 */
 			error = xfs_bmapi_write(tp, ip, map_start_fsb,
-						count_fsb,
-						XFS_BMAPI_STACK_SWITCH,
+						count_fsb, 0,
 						&first_block, 1,
 						imap, &nimaps, &free_list);
 			if (error)
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 36d630319a2..205613a0606 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -829,22 +829,34 @@ xfs_setattr_size(
 	 */
 	inode_dio_wait(inode);
 
+	/*
+	 * Do all the page cache truncate work outside the transaction context
+	 * as the "lock" order is page lock->log space reservation.  i.e.
+	 * locking pages inside the transaction can ABBA deadlock with
+	 * writeback. We have to do the VFS inode size update before we truncate
+	 * the pagecache, however, to avoid racing with page faults beyond the
+	 * new EOF they are not serialised against truncate operations except by
+	 * page locks and size updates.
+	 *
+	 * Hence we are in a situation where a truncate can fail with ENOMEM
+	 * from xfs_trans_reserve(), but having already truncated the in-memory
+	 * version of the file (i.e. made user visible changes). There's not
+	 * much we can do about this, except to hope that the caller sees ENOMEM
+	 * and retries the truncate operation.
+	 */
 	error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
 	if (error)
 		return error;
+	truncate_setsize(inode, newsize);
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
 	if (error)
 		goto out_trans_cancel;
 
-	truncate_setsize(inode, newsize);
-
 	commit_flags = XFS_TRANS_RELEASE_LOG_RES;
 	lock_flags |= XFS_ILOCK_EXCL;
-
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-
 	xfs_trans_ijoin(tp, ip, 0);
 
 	/*
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index f4633828515..cb64f222d60 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -270,7 +270,8 @@ xfs_bulkstat(
 		/*
 		 * Allocate and initialize a btree cursor for ialloc btree.
 		 */
-		cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
+		cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno,
+					    XFS_BTNUM_INO);
 		irbp = irbuf;
 		irbufend = irbuf + nirbuf;
 		end_of_ag = 0;
@@ -621,7 +622,8 @@ xfs_inumbers(
 				agino = 0;
 				continue;
 			}
-			cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
+			cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno,
+						    XFS_BTNUM_INO);
 			error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_GE,
 						 &tmp);
 			if (error) {
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index a5f8bd9899d..292308dede6 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1165,7 +1165,7 @@ xlog_iodone(xfs_buf_t *bp)
 	/*
 	 * Race to shutdown the filesystem if we see an error.
 	 */
-	if (XFS_TEST_ERROR((xfs_buf_geterror(bp)), l->l_mp,
+	if (XFS_TEST_ERROR(bp->b_error, l->l_mp,
 			XFS_ERRTAG_IODONE_IOERR, XFS_RANDOM_IODONE_IOERR)) {
 		xfs_buf_ioerror_alert(bp, __func__);
 		xfs_buf_stale(bp);
@@ -3952,11 +3952,14 @@ xfs_log_force_umount(
 		retval = xlog_state_ioerror(log);
 		spin_unlock(&log->l_icloglock);
 	}
+
 	/*
-	 * Wake up everybody waiting on xfs_log_force.
-	 * Callback all log item committed functions as if the
-	 * log writes were completed.
+	 * Wake up everybody waiting on xfs_log_force. Wake the CIL push first
+	 * as if the log writes were completed. The abort handling in the log
+	 * item committed callback functions will do this again under lock to
+	 * avoid races.
 	 */
+	wake_up_all(&log->l_cilp->xc_commit_wait);
 	xlog_state_do_callback(log, XFS_LI_ABORTED, NULL);
 
 #ifdef XFSERRORDEBUG
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 2c4004475e7..84e0deb95ab 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -24,7 +24,8 @@ struct xfs_log_vec {
 	struct xfs_log_iovec	*lv_iovecp;	/* iovec array */
 	struct xfs_log_item	*lv_item;	/* owner */
 	char			*lv_buf;	/* formatted buffer */
-	int			lv_buf_len;	/* size of formatted buffer */
+	int			lv_bytes;	/* accounted space in buffer */
+	int			lv_buf_len;	/* aligned size of buffer */
 	int			lv_size;	/* size of allocated lv */
 };
 
@@ -52,15 +53,21 @@ xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
 	return vec->i_addr;
 }
 
+/*
+ * We need to make sure the next buffer is naturally aligned for the biggest
+ * basic data type we put into it.  We already accounted for this padding when
+ * sizing the buffer.
+ *
+ * However, this padding does not get written into the log, and hence we have to
+ * track the space used by the log vectors separately to prevent log space hangs
+ * due to inaccurate accounting (i.e. a leak) of the used log space through the
+ * CIL context ticket.
+ */
 static inline void
 xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec, int len)
 {
-	/*
-	 * We need to make sure the next buffer is naturally aligned for the
-	 * biggest basic data type we put into it.  We already accounted for
-	 * this when sizing the buffer.
-	 */
 	lv->lv_buf_len += round_up(len, sizeof(uint64_t));
+	lv->lv_bytes += len;
 	vec->i_len = len;
 }
 
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 7e545539117..b3425b34e3d 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -97,7 +97,7 @@ xfs_cil_prepare_item(
 {
 	/* Account for the new LV being passed in */
 	if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) {
-		*diff_len += lv->lv_buf_len;
+		*diff_len += lv->lv_bytes;
 		*diff_iovecs += lv->lv_niovecs;
 	}
 
@@ -111,7 +111,7 @@ xfs_cil_prepare_item(
 	else if (old_lv != lv) {
 		ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED);
 
-		*diff_len -= old_lv->lv_buf_len;
+		*diff_len -= old_lv->lv_bytes;
 		*diff_iovecs -= old_lv->lv_niovecs;
 		kmem_free(old_lv);
 	}
@@ -239,7 +239,7 @@ xlog_cil_insert_format_items(
 			 * that the space reservation accounting is correct.
 			 */
 			*diff_iovecs -= lv->lv_niovecs;
-			*diff_len -= lv->lv_buf_len;
+			*diff_len -= lv->lv_bytes;
 		} else {
 			/* allocate new data chunk */
 			lv = kmem_zalloc(buf_size, KM_SLEEP|KM_NOFS);
@@ -259,6 +259,7 @@ xlog_cil_insert_format_items(
 
 		/* The allocated data region lies beyond the iovec region */
 		lv->lv_buf_len = 0;
+		lv->lv_bytes = 0;
 		lv->lv_buf = (char *)lv + buf_size - nbytes;
 		ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
 
@@ -385,7 +386,15 @@ xlog_cil_committed(
 	xfs_extent_busy_clear(mp, &ctx->busy_extents,
 			     (mp->m_flags & XFS_MOUNT_DISCARD) && !abort);
 
+	/*
+	 * If we are aborting the commit, wake up anyone waiting on the
+	 * committing list.  If we don't, then a shutdown we can leave processes
+	 * waiting in xlog_cil_force_lsn() waiting on a sequence commit that
+	 * will never happen because we aborted it.
+	 */
 	spin_lock(&ctx->cil->xc_push_lock);
+	if (abort)
+		wake_up_all(&ctx->cil->xc_commit_wait);
 	list_del(&ctx->committing);
 	spin_unlock(&ctx->cil->xc_push_lock);
 
@@ -564,8 +573,18 @@ restart:
 	spin_lock(&cil->xc_push_lock);
 	list_for_each_entry(new_ctx, &cil->xc_committing, committing) {
 		/*
+		 * Avoid getting stuck in this loop because we were woken by the
+		 * shutdown, but then went back to sleep once already in the
+		 * shutdown state.
+		 */
+		if (XLOG_FORCED_SHUTDOWN(log)) {
+			spin_unlock(&cil->xc_push_lock);
+			goto out_abort_free_ticket;
+		}
+
+		/*
 		 * Higher sequences will wait for this one so skip them.
-		 * Don't wait for own own sequence, either.
+		 * Don't wait for our own sequence, either.
 		 */
 		if (new_ctx->sequence >= ctx->sequence)
 			continue;
@@ -810,6 +829,13 @@ restart:
 	 */
 	spin_lock(&cil->xc_push_lock);
 	list_for_each_entry(ctx, &cil->xc_committing, committing) {
+		/*
+		 * Avoid getting stuck in this loop because we were woken by the
+		 * shutdown, but then went back to sleep once already in the
+		 * shutdown state.
+		 */
+		if (XLOG_FORCED_SHUTDOWN(log))
+			goto out_shutdown;
 		if (ctx->sequence > sequence)
 			continue;
 		if (!ctx->commit_lsn) {
@@ -833,14 +859,12 @@ restart:
 	 * push sequence after the above wait loop and the CIL still contains
 	 * dirty objects.
 	 *
-	 * When the push occurs, it will empty the CIL and
-	 * atomically increment the currect sequence past the push sequence and
-	 * move it into the committing list. Of course, if the CIL is clean at
-	 * the time of the push, it won't have pushed the CIL at all, so in that
-	 * case we should try the push for this sequence again from the start
-	 * just in case.
+	 * When the push occurs, it will empty the CIL and atomically increment
+	 * the currect sequence past the push sequence and move it into the
+	 * committing list. Of course, if the CIL is clean at the time of the
+	 * push, it won't have pushed the CIL at all, so in that case we should
+	 * try the push for this sequence again from the start just in case.
 	 */
-
 	if (sequence == cil->xc_current_sequence &&
 	    !list_empty(&cil->xc_cil)) {
 		spin_unlock(&cil->xc_push_lock);
@@ -849,6 +873,17 @@ restart:
 
 	spin_unlock(&cil->xc_push_lock);
 	return commit_lsn;
+
+	/*
+	 * We detected a shutdown in progress. We need to trigger the log force
+	 * to pass through it's iclog state machine error handling, even though
+	 * we are already in a shutdown state. Hence we can't return
+	 * NULLCOMMITLSN here as that has special meaning to log forces (i.e.
+	 * LSN is already stable), so we return a zero LSN instead.
+	 */
+out_shutdown:
+	spin_unlock(&cil->xc_push_lock);
+	return 0;
 }
 
 /*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index bce53ac8109..981af0f6504 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2138,7 +2138,9 @@ xlog_recover_validate_buf_type(
 			bp->b_ops = &xfs_allocbt_buf_ops;
 			break;
 		case XFS_IBT_CRC_MAGIC:
+		case XFS_FIBT_CRC_MAGIC:
 		case XFS_IBT_MAGIC:
+		case XFS_FIBT_MAGIC:
 			bp->b_ops = &xfs_inobt_buf_ops;
 			break;
 		case XFS_BMAP_CRC_MAGIC:
@@ -3145,7 +3147,7 @@ xlog_recover_efd_pass2(
 		}
 		lip = xfs_trans_ail_cursor_next(ailp, &cur);
 	}
-	xfs_trans_ail_cursor_done(ailp, &cur);
+	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->xa_lock);
 
 	return 0;
@@ -3520,8 +3522,7 @@ out:
 
 STATIC int
 xlog_recover_unmount_trans(
-	struct xlog		*log,
-	struct xlog_recover	*trans)
+	struct xlog		*log)
 {
 	/* Do nothing now */
 	xfs_warn(log->l_mp, "%s: Unmount LR", __func__);
@@ -3595,7 +3596,7 @@ xlog_recover_process_data(
 								trans, pass);
 				break;
 			case XLOG_UNMOUNT_TRANS:
-				error = xlog_recover_unmount_trans(log, trans);
+				error = xlog_recover_unmount_trans(log);
 				break;
 			case XLOG_WAS_CONT_TRANS:
 				error = xlog_recover_add_to_cont_trans(log,
@@ -3757,7 +3758,7 @@ xlog_recover_process_efis(
 		lip = xfs_trans_ail_cursor_next(ailp, &cur);
 	}
 out:
-	xfs_trans_ail_cursor_done(ailp, &cur);
+	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->xa_lock);
 	return error;
 }
diff --git a/fs/xfs/xfs_log_rlimit.c b/fs/xfs/xfs_log_rlimit.c
index 2af1a0a4d0f..ee7e0e80246 100644
--- a/fs/xfs/xfs_log_rlimit.c
+++ b/fs/xfs/xfs_log_rlimit.c
@@ -42,7 +42,7 @@ xfs_log_calc_max_attrsetm_res(
 	int			size;
 	int			nblks;
 
-	size = xfs_attr_leaf_entsize_local_max(mp->m_sb.sb_blocksize) -
+	size = xfs_attr_leaf_entsize_local_max(mp->m_attr_geo->blksize) -
 	       MAXNAMELEN - 1;
 	nblks = XFS_DAENTER_SPACE_RES(mp, XFS_ATTR_FORK);
 	nblks += XFS_B_TO_FSB(mp, size);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 944f3d9456a..3507cd0ec40 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -323,8 +323,19 @@ reread:
 	/*
 	 * Initialize the mount structure from the superblock.
 	 */
-	xfs_sb_from_disk(&mp->m_sb, XFS_BUF_TO_SBP(bp));
-	xfs_sb_quota_from_disk(&mp->m_sb);
+	xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));
+	xfs_sb_quota_from_disk(sbp);
+
+	/*
+	 * If we haven't validated the superblock, do so now before we try
+	 * to check the sector size and reread the superblock appropriately.
+	 */
+	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
+		if (loud)
+			xfs_warn(mp, "Invalid superblock magic number");
+		error = EINVAL;
+		goto release_buf;
+	}
 
 	/*
 	 * We must be able to do sector-sized and sector-aligned IO.
@@ -337,11 +348,11 @@ reread:
 		goto release_buf;
 	}
 
-	/*
-	 * Re-read the superblock so the buffer is correctly sized,
-	 * and properly verified.
-	 */
 	if (buf_ops == NULL) {
+		/*
+		 * Re-read the superblock so the buffer is correctly sized,
+		 * and properly verified.
+		 */
 		xfs_buf_relse(bp);
 		sector_size = sbp->sb_sectsize;
 		buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
@@ -697,6 +708,12 @@ xfs_mountfs(
 			mp->m_update_flags |= XFS_SB_VERSIONNUM;
 	}
 
+	/* always use v2 inodes by default now */
+	if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) {
+		mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
+		mp->m_update_flags |= XFS_SB_VERSIONNUM;
+	}
+
 	/*
 	 * Check if sb_agblocks is aligned at stripe boundary
 	 * If sb_agblocks is NOT aligned turn off m_dalign since
@@ -774,12 +791,11 @@ xfs_mountfs(
 
 	mp->m_dmevmask = 0;	/* not persistent; set after each mount */
 
-	xfs_dir_mount(mp);
-
-	/*
-	 * Initialize the attribute manager's entries.
-	 */
-	mp->m_attr_magicpct = (mp->m_sb.sb_blocksize * 37) / 100;
+	error = xfs_da_mount(mp);
+	if (error) {
+		xfs_warn(mp, "Failed dir/attr init: %d", error);
+		goto out_remove_uuid;
+	}
 
 	/*
 	 * Initialize the precomputed transaction reservations values.
@@ -794,7 +810,7 @@ xfs_mountfs(
 	error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
 	if (error) {
 		xfs_warn(mp, "Failed per-ag init: %d", error);
-		goto out_remove_uuid;
+		goto out_free_dir;
 	}
 
 	if (!sbp->sb_logblocks) {
@@ -969,6 +985,8 @@ xfs_mountfs(
 	xfs_wait_buftarg(mp->m_ddev_targp);
  out_free_perag:
 	xfs_free_perag(mp);
+ out_free_dir:
+	xfs_da_unmount(mp);
  out_remove_uuid:
 	xfs_uuid_unmount(mp);
  out:
@@ -1046,6 +1064,7 @@ xfs_unmountfs(
 				"Freespace may not be correct on next mount.");
 
 	xfs_log_unmount(mp);
+	xfs_da_unmount(mp);
 	xfs_uuid_unmount(mp);
 
 #if defined(DEBUG)
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index a466c5e5826..7295a0b7c34 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -27,6 +27,7 @@ struct xfs_nameops;
 struct xfs_ail;
 struct xfs_quotainfo;
 struct xfs_dir_ops;
+struct xfs_da_geometry;
 
 #ifdef HAVE_PERCPU_SB
 
@@ -96,6 +97,8 @@ typedef struct xfs_mount {
 	uint			m_readio_blocks; /* min read size blocks */
 	uint			m_writeio_log;	/* min write size log bytes */
 	uint			m_writeio_blocks; /* min write size blocks */
+	struct xfs_da_geometry	*m_dir_geo;	/* directory block geometry */
+	struct xfs_da_geometry	*m_attr_geo;	/* attribute block geometry */
 	struct xlog		*m_log;		/* log specific stuff */
 	int			m_logbufs;	/* number of log buffers */
 	int			m_logbsize;	/* size of each log buffer */
@@ -131,8 +134,6 @@ typedef struct xfs_mount {
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_dmevmask;	/* DMI events for this FS */
 	__uint64_t		m_flags;	/* global mount flags */
-	uint			m_dir_node_ents; /* #entries in a dir danode */
-	uint			m_attr_node_ents; /* #entries in attr danode */
 	int			m_ialloc_inos;	/* inodes in inode allocation */
 	int			m_ialloc_blks;	/* blocks in inode allocation */
 	int			m_inoalign_mask;/* mask sb_inoalignmt if used */
@@ -145,17 +146,10 @@ typedef struct xfs_mount {
 	int			m_dalign;	/* stripe unit */
 	int			m_swidth;	/* stripe width */
 	int			m_sinoalign;	/* stripe unit inode alignment */
-	int			m_attr_magicpct;/* 37% of the blocksize */
-	int			m_dir_magicpct;	/* 37% of the dir blocksize */
 	__uint8_t		m_sectbb_log;	/* sectlog - BBSHIFT */
 	const struct xfs_nameops *m_dirnameops;	/* vector of dir name ops */
 	const struct xfs_dir_ops *m_dir_inode_ops; /* vector of dir inode ops */
 	const struct xfs_dir_ops *m_nondir_inode_ops; /* !dir inode ops */
-	int			m_dirblksize;	/* directory block sz--bytes */
-	int			m_dirblkfsbs;	/* directory block sz--fsbs */
-	xfs_dablk_t		m_dirdatablk;	/* blockno of dir data v2 */
-	xfs_dablk_t		m_dirleafblk;	/* blockno of dir non-data v2 */
-	xfs_dablk_t		m_dirfreeblk;	/* blockno of dirfreeindex v2 */
 	uint			m_chsize;	/* size of next field */
 	atomic_t		m_active_trans;	/* number trans frozen */
 #ifdef HAVE_PERCPU_SB
diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index 4aff5639573..f99b4933dc2 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -100,14 +100,20 @@
  * likely result in a loop in one of the lists.  That's a sure-fire recipe for
  * an infinite loop in the code.
  */
-typedef struct xfs_mru_cache_elem
-{
-	struct list_head list_node;
-	unsigned long	key;
-	void		*value;
-} xfs_mru_cache_elem_t;
+struct xfs_mru_cache {
+	struct radix_tree_root	store;     /* Core storage data structure.  */
+	struct list_head	*lists;    /* Array of lists, one per grp.  */
+	struct list_head	reap_list; /* Elements overdue for reaping. */
+	spinlock_t		lock;      /* Lock to protect this struct.  */
+	unsigned int		grp_count; /* Number of discrete groups.    */
+	unsigned int		grp_time;  /* Time period spanned by grps.  */
+	unsigned int		lru_grp;   /* Group containing time zero.   */
+	unsigned long		time_zero; /* Time first element was added. */
+	xfs_mru_cache_free_func_t free_func; /* Function pointer for freeing. */
+	struct delayed_work	work;      /* Workqueue data for reaping.   */
+	unsigned int		queued;	   /* work has been queued */
+};
 
-static kmem_zone_t		*xfs_mru_elem_zone;
 static struct workqueue_struct	*xfs_mru_reap_wq;
 
 /*
@@ -129,12 +135,12 @@ static struct workqueue_struct	*xfs_mru_reap_wq;
  */
 STATIC unsigned long
 _xfs_mru_cache_migrate(
-	xfs_mru_cache_t	*mru,
-	unsigned long	now)
+	struct xfs_mru_cache	*mru,
+	unsigned long		now)
 {
-	unsigned int	grp;
-	unsigned int	migrated = 0;
-	struct list_head *lru_list;
+	unsigned int		grp;
+	unsigned int		migrated = 0;
+	struct list_head	*lru_list;
 
 	/* Nothing to do if the data store is empty. */
 	if (!mru->time_zero)
@@ -193,11 +199,11 @@ _xfs_mru_cache_migrate(
  */
 STATIC void
 _xfs_mru_cache_list_insert(
-	xfs_mru_cache_t		*mru,
-	xfs_mru_cache_elem_t	*elem)
+	struct xfs_mru_cache	*mru,
+	struct xfs_mru_cache_elem *elem)
 {
-	unsigned int	grp = 0;
-	unsigned long	now = jiffies;
+	unsigned int		grp = 0;
+	unsigned long		now = jiffies;
 
 	/*
 	 * If the data store is empty, initialise time zero, leave grp set to
@@ -231,10 +237,10 @@ _xfs_mru_cache_list_insert(
  */
 STATIC void
 _xfs_mru_cache_clear_reap_list(
-	xfs_mru_cache_t		*mru) __releases(mru->lock) __acquires(mru->lock)
-
+	struct xfs_mru_cache	*mru)
+		__releases(mru->lock) __acquires(mru->lock)
 {
-	xfs_mru_cache_elem_t	*elem, *next;
+	struct xfs_mru_cache_elem *elem, *next;
 	struct list_head	tmp;
 
 	INIT_LIST_HEAD(&tmp);
@@ -252,15 +258,8 @@ _xfs_mru_cache_clear_reap_list(
 	spin_unlock(&mru->lock);
 
 	list_for_each_entry_safe(elem, next, &tmp, list_node) {
-
-		/* Remove the element from the reap list. */
 		list_del_init(&elem->list_node);
-
-		/* Call the client's free function with the key and value pointer. */
-		mru->free_func(elem->key, elem->value);
-
-		/* Free the element structure. */
-		kmem_zone_free(xfs_mru_elem_zone, elem);
+		mru->free_func(elem);
 	}
 
 	spin_lock(&mru->lock);
@@ -277,7 +276,8 @@ STATIC void
 _xfs_mru_cache_reap(
 	struct work_struct	*work)
 {
-	xfs_mru_cache_t		*mru = container_of(work, xfs_mru_cache_t, work.work);
+	struct xfs_mru_cache	*mru =
+		container_of(work, struct xfs_mru_cache, work.work);
 	unsigned long		now, next;
 
 	ASSERT(mru && mru->lists);
@@ -304,28 +304,16 @@ _xfs_mru_cache_reap(
 int
 xfs_mru_cache_init(void)
 {
-	xfs_mru_elem_zone = kmem_zone_init(sizeof(xfs_mru_cache_elem_t),
-	                                 "xfs_mru_cache_elem");
-	if (!xfs_mru_elem_zone)
-		goto out;
-
 	xfs_mru_reap_wq = alloc_workqueue("xfs_mru_cache", WQ_MEM_RECLAIM, 1);
 	if (!xfs_mru_reap_wq)
-		goto out_destroy_mru_elem_zone;
-
+		return -ENOMEM;
 	return 0;
-
- out_destroy_mru_elem_zone:
-	kmem_zone_destroy(xfs_mru_elem_zone);
- out:
-	return -ENOMEM;
 }
 
 void
 xfs_mru_cache_uninit(void)
 {
 	destroy_workqueue(xfs_mru_reap_wq);
-	kmem_zone_destroy(xfs_mru_elem_zone);
 }
 
 /*
@@ -336,14 +324,14 @@ xfs_mru_cache_uninit(void)
  */
 int
 xfs_mru_cache_create(
-	xfs_mru_cache_t		**mrup,
+	struct xfs_mru_cache	**mrup,
 	unsigned int		lifetime_ms,
 	unsigned int		grp_count,
 	xfs_mru_cache_free_func_t free_func)
 {
-	xfs_mru_cache_t	*mru = NULL;
-	int		err = 0, grp;
-	unsigned int	grp_time;
+	struct xfs_mru_cache	*mru = NULL;
+	int			err = 0, grp;
+	unsigned int		grp_time;
 
 	if (mrup)
 		*mrup = NULL;
@@ -400,7 +388,7 @@ exit:
  */
 static void
 xfs_mru_cache_flush(
-	xfs_mru_cache_t		*mru)
+	struct xfs_mru_cache	*mru)
 {
 	if (!mru || !mru->lists)
 		return;
@@ -420,7 +408,7 @@ xfs_mru_cache_flush(
 
 void
 xfs_mru_cache_destroy(
-	xfs_mru_cache_t		*mru)
+	struct xfs_mru_cache	*mru)
 {
 	if (!mru || !mru->lists)
 		return;
@@ -438,38 +426,30 @@ xfs_mru_cache_destroy(
  */
 int
 xfs_mru_cache_insert(
-	xfs_mru_cache_t	*mru,
-	unsigned long	key,
-	void		*value)
+	struct xfs_mru_cache	*mru,
+	unsigned long		key,
+	struct xfs_mru_cache_elem *elem)
 {
-	xfs_mru_cache_elem_t *elem;
+	int			error;
 
 	ASSERT(mru && mru->lists);
 	if (!mru || !mru->lists)
 		return EINVAL;
 
-	elem = kmem_zone_zalloc(xfs_mru_elem_zone, KM_SLEEP);
-	if (!elem)
+	if (radix_tree_preload(GFP_KERNEL))
 		return ENOMEM;
 
-	if (radix_tree_preload(GFP_KERNEL)) {
-		kmem_zone_free(xfs_mru_elem_zone, elem);
-		return ENOMEM;
-	}
-
 	INIT_LIST_HEAD(&elem->list_node);
 	elem->key = key;
-	elem->value = value;
 
 	spin_lock(&mru->lock);
-
-	radix_tree_insert(&mru->store, key, elem);
+	error = -radix_tree_insert(&mru->store, key, elem);
 	radix_tree_preload_end();
-	_xfs_mru_cache_list_insert(mru, elem);
-
+	if (!error)
+		_xfs_mru_cache_list_insert(mru, elem);
 	spin_unlock(&mru->lock);
 
-	return 0;
+	return error;
 }
 
 /*
@@ -478,13 +458,12 @@ xfs_mru_cache_insert(
  * the client data pointer for the removed element is returned, otherwise this
  * function will return a NULL pointer.
  */
-void *
+struct xfs_mru_cache_elem *
 xfs_mru_cache_remove(
-	xfs_mru_cache_t	*mru,
-	unsigned long	key)
+	struct xfs_mru_cache	*mru,
+	unsigned long		key)
 {
-	xfs_mru_cache_elem_t *elem;
-	void		*value = NULL;
+	struct xfs_mru_cache_elem *elem;
 
 	ASSERT(mru && mru->lists);
 	if (!mru || !mru->lists)
@@ -492,17 +471,11 @@ xfs_mru_cache_remove(
 
 	spin_lock(&mru->lock);
 	elem = radix_tree_delete(&mru->store, key);
-	if (elem) {
-		value = elem->value;
+	if (elem)
 		list_del(&elem->list_node);
-	}
-
 	spin_unlock(&mru->lock);
 
-	if (elem)
-		kmem_zone_free(xfs_mru_elem_zone, elem);
-
-	return value;
+	return elem;
 }
 
 /*
@@ -511,13 +484,14 @@ xfs_mru_cache_remove(
  */
 void
 xfs_mru_cache_delete(
-	xfs_mru_cache_t	*mru,
-	unsigned long	key)
+	struct xfs_mru_cache	*mru,
+	unsigned long		key)
 {
-	void		*value = xfs_mru_cache_remove(mru, key);
+	struct xfs_mru_cache_elem *elem;
 
-	if (value)
-		mru->free_func(key, value);
+	elem = xfs_mru_cache_remove(mru, key);
+	if (elem)
+		mru->free_func(elem);
 }
 
 /*
@@ -540,12 +514,12 @@ xfs_mru_cache_delete(
  * status, we need to help it get it right by annotating the path that does
  * not release the lock.
  */
-void *
+struct xfs_mru_cache_elem *
 xfs_mru_cache_lookup(
-	xfs_mru_cache_t	*mru,
-	unsigned long	key)
+	struct xfs_mru_cache	*mru,
+	unsigned long		key)
 {
-	xfs_mru_cache_elem_t *elem;
+	struct xfs_mru_cache_elem *elem;
 
 	ASSERT(mru && mru->lists);
 	if (!mru || !mru->lists)
@@ -560,7 +534,7 @@ xfs_mru_cache_lookup(
 	} else
 		spin_unlock(&mru->lock);
 
-	return elem ? elem->value : NULL;
+	return elem;
 }
 
 /*
@@ -570,7 +544,8 @@ xfs_mru_cache_lookup(
  */
 void
 xfs_mru_cache_done(
-	xfs_mru_cache_t	*mru) __releases(mru->lock)
+	struct xfs_mru_cache	*mru)
+		__releases(mru->lock)
 {
 	spin_unlock(&mru->lock);
 }
diff --git a/fs/xfs/xfs_mru_cache.h b/fs/xfs/xfs_mru_cache.h
index 36dd3ec8b4e..fb5245ba5ff 100644
--- a/fs/xfs/xfs_mru_cache.h
+++ b/fs/xfs/xfs_mru_cache.h
@@ -18,24 +18,15 @@
 #ifndef __XFS_MRU_CACHE_H__
 #define __XFS_MRU_CACHE_H__
 
+struct xfs_mru_cache;
 
-/* Function pointer type for callback to free a client's data pointer. */
-typedef void (*xfs_mru_cache_free_func_t)(unsigned long, void*);
+struct xfs_mru_cache_elem {
+	struct list_head list_node;
+	unsigned long	key;
+};
 
-typedef struct xfs_mru_cache
-{
-	struct radix_tree_root	store;     /* Core storage data structure.  */
-	struct list_head	*lists;    /* Array of lists, one per grp.  */
-	struct list_head	reap_list; /* Elements overdue for reaping. */
-	spinlock_t		lock;      /* Lock to protect this struct.  */
-	unsigned int		grp_count; /* Number of discrete groups.    */
-	unsigned int		grp_time;  /* Time period spanned by grps.  */
-	unsigned int		lru_grp;   /* Group containing time zero.   */
-	unsigned long		time_zero; /* Time first element was added. */
-	xfs_mru_cache_free_func_t free_func; /* Function pointer for freeing. */
-	struct delayed_work	work;      /* Workqueue data for reaping.   */
-	unsigned int		queued;	   /* work has been queued */
-} xfs_mru_cache_t;
+/* Function pointer type for callback to free a client's data pointer. */
+typedef void (*xfs_mru_cache_free_func_t)(struct xfs_mru_cache_elem *elem);
 
 int xfs_mru_cache_init(void);
 void xfs_mru_cache_uninit(void);
@@ -44,10 +35,12 @@ int xfs_mru_cache_create(struct xfs_mru_cache **mrup, unsigned int lifetime_ms,
 			     xfs_mru_cache_free_func_t free_func);
 void xfs_mru_cache_destroy(struct xfs_mru_cache *mru);
 int xfs_mru_cache_insert(struct xfs_mru_cache *mru, unsigned long key,
-				void *value);
-void * xfs_mru_cache_remove(struct xfs_mru_cache *mru, unsigned long key);
+		struct xfs_mru_cache_elem *elem);
+struct xfs_mru_cache_elem *
+xfs_mru_cache_remove(struct xfs_mru_cache *mru, unsigned long key);
 void xfs_mru_cache_delete(struct xfs_mru_cache *mru, unsigned long key);
-void *xfs_mru_cache_lookup(struct xfs_mru_cache *mru, unsigned long key);
+struct xfs_mru_cache_elem *
+xfs_mru_cache_lookup(struct xfs_mru_cache *mru, unsigned long key);
 void xfs_mru_cache_done(struct xfs_mru_cache *mru);
 
 #endif /* __XFS_MRU_CACHE_H__ */
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index dc977b6e6a3..6d26759c779 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -193,47 +193,6 @@ xfs_qm_dqpurge(
 }
 
 /*
- * Release the group or project dquot pointers the user dquots maybe carrying
- * around as a hint, and proceed to purge the user dquot cache if requested.
-*/
-STATIC int
-xfs_qm_dqpurge_hints(
-	struct xfs_dquot	*dqp,
-	void			*data)
-{
-	struct xfs_dquot	*gdqp = NULL;
-	struct xfs_dquot	*pdqp = NULL;
-	uint			flags = *((uint *)data);
-
-	xfs_dqlock(dqp);
-	if (dqp->dq_flags & XFS_DQ_FREEING) {
-		xfs_dqunlock(dqp);
-		return EAGAIN;
-	}
-
-	/* If this quota has a hint attached, prepare for releasing it now */
-	gdqp = dqp->q_gdquot;
-	if (gdqp)
-		dqp->q_gdquot = NULL;
-
-	pdqp = dqp->q_pdquot;
-	if (pdqp)
-		dqp->q_pdquot = NULL;
-
-	xfs_dqunlock(dqp);
-
-	if (gdqp)
-		xfs_qm_dqrele(gdqp);
-	if (pdqp)
-		xfs_qm_dqrele(pdqp);
-
-	if (flags & XFS_QMOPT_UQUOTA)
-		return xfs_qm_dqpurge(dqp, NULL);
-
-	return 0;
-}
-
-/*
  * Purge the dquot cache.
  */
 void
@@ -241,18 +200,8 @@ xfs_qm_dqpurge_all(
 	struct xfs_mount	*mp,
 	uint			flags)
 {
-	/*
-	 * We have to release group/project dquot hint(s) from the user dquot
-	 * at first if they are there, otherwise we would run into an infinite
-	 * loop while walking through radix tree to purge other type of dquots
-	 * since their refcount is not zero if the user dquot refers to them
-	 * as hint.
-	 *
-	 * Call the special xfs_qm_dqpurge_hints() will end up go through the
-	 * general xfs_qm_dqpurge() against user dquot cache if requested.
-	 */
-	xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge_hints, &flags);
-
+	if (flags & XFS_QMOPT_UQUOTA)
+		xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
 	if (flags & XFS_QMOPT_GQUOTA)
 		xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
 	if (flags & XFS_QMOPT_PQUOTA)
@@ -409,7 +358,6 @@ xfs_qm_dqattach_one(
 	xfs_dqid_t	id,
 	uint		type,
 	uint		doalloc,
-	xfs_dquot_t	*udqhint, /* hint */
 	xfs_dquot_t	**IO_idqpp)
 {
 	xfs_dquot_t	*dqp;
@@ -419,9 +367,9 @@ xfs_qm_dqattach_one(
 	error = 0;
 
 	/*
-	 * See if we already have it in the inode itself. IO_idqpp is
-	 * &i_udquot or &i_gdquot. This made the code look weird, but
-	 * made the logic a lot simpler.
+	 * See if we already have it in the inode itself. IO_idqpp is &i_udquot
+	 * or &i_gdquot. This made the code look weird, but made the logic a lot
+	 * simpler.
 	 */
 	dqp = *IO_idqpp;
 	if (dqp) {
@@ -430,49 +378,10 @@ xfs_qm_dqattach_one(
 	}
 
 	/*
-	 * udqhint is the i_udquot field in inode, and is non-NULL only
-	 * when the type arg is group/project. Its purpose is to save a
-	 * lookup by dqid (xfs_qm_dqget) by caching a group dquot inside
-	 * the user dquot.
-	 */
-	if (udqhint) {
-		ASSERT(type == XFS_DQ_GROUP || type == XFS_DQ_PROJ);
-		xfs_dqlock(udqhint);
-
-		/*
-		 * No need to take dqlock to look at the id.
-		 *
-		 * The ID can't change until it gets reclaimed, and it won't
-		 * be reclaimed as long as we have a ref from inode and we
-		 * hold the ilock.
-		 */
-		if (type == XFS_DQ_GROUP)
-			dqp = udqhint->q_gdquot;
-		else
-			dqp = udqhint->q_pdquot;
-		if (dqp && be32_to_cpu(dqp->q_core.d_id) == id) {
-			ASSERT(*IO_idqpp == NULL);
-
-			*IO_idqpp = xfs_qm_dqhold(dqp);
-			xfs_dqunlock(udqhint);
-			return 0;
-		}
-
-		/*
-		 * We can't hold a dquot lock when we call the dqget code.
-		 * We'll deadlock in no time, because of (not conforming to)
-		 * lock ordering - the inodelock comes before any dquot lock,
-		 * and we may drop and reacquire the ilock in xfs_qm_dqget().
-		 */
-		xfs_dqunlock(udqhint);
-	}
-
-	/*
-	 * Find the dquot from somewhere. This bumps the
-	 * reference count of dquot and returns it locked.
-	 * This can return ENOENT if dquot didn't exist on
-	 * disk and we didn't ask it to allocate;
-	 * ESRCH if quotas got turned off suddenly.
+	 * Find the dquot from somewhere. This bumps the reference count of
+	 * dquot and returns it locked.  This can return ENOENT if dquot didn't
+	 * exist on disk and we didn't ask it to allocate; ESRCH if quotas got
+	 * turned off suddenly.
 	 */
 	error = xfs_qm_dqget(ip->i_mount, ip, id, type,
 			     doalloc | XFS_QMOPT_DOWARN, &dqp);
@@ -490,48 +399,6 @@ xfs_qm_dqattach_one(
 	return 0;
 }
 
-
-/*
- * Given a udquot and group/project type, attach the group/project
- * dquot pointer to the udquot as a hint for future lookups.
- */
-STATIC void
-xfs_qm_dqattach_hint(
-	struct xfs_inode	*ip,
-	int			type)
-{
-	struct xfs_dquot **dqhintp;
-	struct xfs_dquot *dqp;
-	struct xfs_dquot *udq = ip->i_udquot;
-
-	ASSERT(type == XFS_DQ_GROUP || type == XFS_DQ_PROJ);
-
-	xfs_dqlock(udq);
-
-	if (type == XFS_DQ_GROUP) {
-		dqp = ip->i_gdquot;
-		dqhintp = &udq->q_gdquot;
-	} else {
-		dqp = ip->i_pdquot;
-		dqhintp = &udq->q_pdquot;
-	}
-
-	if (*dqhintp) {
-		struct xfs_dquot *tmp;
-
-		if (*dqhintp == dqp)
-			goto done;
-
-		tmp = *dqhintp;
-		*dqhintp = NULL;
-		xfs_qm_dqrele(tmp);
-	}
-
-	*dqhintp = xfs_qm_dqhold(dqp);
-done:
-	xfs_dqunlock(udq);
-}
-
 static bool
 xfs_qm_need_dqattach(
 	struct xfs_inode	*ip)
@@ -562,7 +429,6 @@ xfs_qm_dqattach_locked(
 	uint		flags)
 {
 	xfs_mount_t	*mp = ip->i_mount;
-	uint		nquotas = 0;
 	int		error = 0;
 
 	if (!xfs_qm_need_dqattach(ip))
@@ -570,77 +436,39 @@ xfs_qm_dqattach_locked(
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
-	if (XFS_IS_UQUOTA_ON(mp)) {
+	if (XFS_IS_UQUOTA_ON(mp) && !ip->i_udquot) {
 		error = xfs_qm_dqattach_one(ip, ip->i_d.di_uid, XFS_DQ_USER,
 						flags & XFS_QMOPT_DQALLOC,
-						NULL, &ip->i_udquot);
+						&ip->i_udquot);
 		if (error)
 			goto done;
-		nquotas++;
+		ASSERT(ip->i_udquot);
 	}
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	if (XFS_IS_GQUOTA_ON(mp)) {
+	if (XFS_IS_GQUOTA_ON(mp) && !ip->i_gdquot) {
 		error = xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP,
 						flags & XFS_QMOPT_DQALLOC,
-						ip->i_udquot, &ip->i_gdquot);
-		/*
-		 * Don't worry about the udquot that we may have
-		 * attached above. It'll get detached, if not already.
-		 */
+						&ip->i_gdquot);
 		if (error)
 			goto done;
-		nquotas++;
+		ASSERT(ip->i_gdquot);
 	}
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	if (XFS_IS_PQUOTA_ON(mp)) {
+	if (XFS_IS_PQUOTA_ON(mp) && !ip->i_pdquot) {
 		error = xfs_qm_dqattach_one(ip, xfs_get_projid(ip), XFS_DQ_PROJ,
 						flags & XFS_QMOPT_DQALLOC,
-						ip->i_udquot, &ip->i_pdquot);
-		/*
-		 * Don't worry about the udquot that we may have
-		 * attached above. It'll get detached, if not already.
-		 */
+						&ip->i_pdquot);
 		if (error)
 			goto done;
-		nquotas++;
+		ASSERT(ip->i_pdquot);
 	}
 
+done:
 	/*
-	 * Attach this group/project quota to the user quota as a hint.
-	 * This WON'T, in general, result in a thrash.
+	 * Don't worry about the dquots that we may have attached before any
+	 * error - they'll get detached later if it has not already been done.
 	 */
-	if (nquotas > 1 && ip->i_udquot) {
-		ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-		ASSERT(ip->i_gdquot || !XFS_IS_GQUOTA_ON(mp));
-		ASSERT(ip->i_pdquot || !XFS_IS_PQUOTA_ON(mp));
-
-		/*
-		 * We do not have i_udquot locked at this point, but this check
-		 * is OK since we don't depend on the i_gdquot to be accurate
-		 * 100% all the time. It is just a hint, and this will
-		 * succeed in general.
-		 */
-		if (ip->i_udquot->q_gdquot != ip->i_gdquot)
-			xfs_qm_dqattach_hint(ip, XFS_DQ_GROUP);
-
-		if (ip->i_udquot->q_pdquot != ip->i_pdquot)
-			xfs_qm_dqattach_hint(ip, XFS_DQ_PROJ);
-	}
-
- done:
-#ifdef DEBUG
-	if (!error) {
-		if (XFS_IS_UQUOTA_ON(mp))
-			ASSERT(ip->i_udquot);
-		if (XFS_IS_GQUOTA_ON(mp))
-			ASSERT(ip->i_gdquot);
-		if (XFS_IS_PQUOTA_ON(mp))
-			ASSERT(ip->i_pdquot);
-	}
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-#endif
 	return error;
 }
 
@@ -865,8 +693,7 @@ xfs_qm_init_quotainfo(
 
 	/* Precalc some constants */
 	qinf->qi_dqchunklen = XFS_FSB_TO_BB(mp, XFS_DQUOT_CLUSTER_SIZE_FSB);
-	qinf->qi_dqperchunk = xfs_calc_dquots_per_chunk(mp,
-							qinf->qi_dqchunklen);
+	qinf->qi_dqperchunk = xfs_calc_dquots_per_chunk(qinf->qi_dqchunklen);
 
 	mp->m_qflags |= (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_CHKD);
 
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 3daf5ea1eb8..bbc813caba4 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -278,9 +278,10 @@ xfs_qm_scall_trunc_qfiles(
 	xfs_mount_t	*mp,
 	uint		flags)
 {
-	int		error;
+	int		error = EINVAL;
 
-	if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0) {
+	if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0 ||
+	    (flags & ~XFS_DQ_ALLTYPES)) {
 		xfs_debug(mp, "%s: flags=%x m_qflags=%x",
 			__func__, flags, mp->m_qflags);
 		return XFS_ERROR(EINVAL);
@@ -959,7 +960,6 @@ xfs_qm_export_flags(
 STATIC int
 xfs_dqrele_inode(
 	struct xfs_inode	*ip,
-	struct xfs_perag	*pag,
 	int			flags,
 	void			*args)
 {
diff --git a/fs/xfs/xfs_quota_defs.h b/fs/xfs/xfs_quota_defs.h
index b3b2b1065c0..137e2093707 100644
--- a/fs/xfs/xfs_quota_defs.h
+++ b/fs/xfs/xfs_quota_defs.h
@@ -156,6 +156,6 @@ typedef __uint16_t	xfs_qwarncnt_t;
 
 extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq,
 		       xfs_dqid_t id, uint type, uint flags, char *str);
-extern int xfs_calc_dquots_per_chunk(struct xfs_mount *mp, unsigned int nbblks);
+extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
 
 #endif	/* __XFS_QUOTA_H__ */
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index af33cafe69b..2ad1b9822e9 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -100,16 +100,36 @@ xfs_fs_set_xstate(
 		if (!XFS_IS_QUOTA_ON(mp))
 			return -EINVAL;
 		return -xfs_qm_scall_quotaoff(mp, flags);
-	case Q_XQUOTARM:
-		if (XFS_IS_QUOTA_ON(mp))
-			return -EINVAL;
-		return -xfs_qm_scall_trunc_qfiles(mp, flags);
 	}
 
 	return -EINVAL;
 }
 
 STATIC int
+xfs_fs_rm_xquota(
+	struct super_block	*sb,
+	unsigned int		uflags)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+	unsigned int		flags = 0;
+	
+	if (sb->s_flags & MS_RDONLY)
+		return -EROFS;
+
+	if (XFS_IS_QUOTA_ON(mp))
+		return -EINVAL;
+
+	if (uflags & FS_USER_QUOTA)
+		flags |= XFS_DQ_USER;
+	if (uflags & FS_GROUP_QUOTA)
+		flags |= XFS_DQ_GROUP;
+	if (uflags & FS_USER_QUOTA)
+		flags |= XFS_DQ_PROJ;
+
+	return -xfs_qm_scall_trunc_qfiles(mp, flags);
+}	
+
+STATIC int
 xfs_fs_get_dqblk(
 	struct super_block	*sb,
 	struct kqid		qid,
@@ -149,6 +169,7 @@ const struct quotactl_ops xfs_quotactl_operations = {
 	.get_xstatev		= xfs_fs_get_xstatev,
 	.get_xstate		= xfs_fs_get_xstate,
 	.set_xstate		= xfs_fs_set_xstate,
+	.rm_xquota		= xfs_fs_rm_xquota,
 	.get_dqblk		= xfs_fs_get_dqblk,
 	.set_dqblk		= xfs_fs_set_dqblk,
 };
diff --git a/fs/xfs/xfs_rtbitmap.c b/fs/xfs/xfs_rtbitmap.c
index b1f2fe8af4a..f4dd697cac0 100644
--- a/fs/xfs/xfs_rtbitmap.c
+++ b/fs/xfs/xfs_rtbitmap.c
@@ -74,7 +74,6 @@ xfs_rtbuf_get(
 				   mp->m_bsize, 0, &bp, NULL);
 	if (error)
 		return error;
-	ASSERT(!xfs_buf_geterror(bp));
 	*bpp = bp;
 	return 0;
 }
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index 8baf61afae1..7703fa6770f 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -291,7 +291,8 @@ xfs_mount_validate_sb(
 	    (sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */)	||
 	    sbp->sb_dblocks == 0					||
 	    sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp)			||
-	    sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) {
+	    sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp)			||
+	    sbp->sb_shared_vn != 0)) {
 		xfs_notice(mp, "SB sanity check failed");
 		return XFS_ERROR(EFSCORRUPTED);
 	}
@@ -333,15 +334,6 @@ xfs_mount_validate_sb(
 		xfs_warn(mp, "Offline file system operation in progress!");
 		return XFS_ERROR(EFSCORRUPTED);
 	}
-
-	/*
-	 * Version 1 directory format has never worked on Linux.
-	 */
-	if (unlikely(!xfs_sb_version_hasdirv2(sbp))) {
-		xfs_warn(mp, "file system using version 1 directory format");
-		return XFS_ERROR(ENOSYS);
-	}
-
 	return 0;
 }
 
@@ -491,10 +483,16 @@ xfs_sb_quota_to_disk(
 	}
 
 	/*
-	 * GQUOTINO and PQUOTINO cannot be used together in versions
-	 * of superblock that do not have pquotino. from->sb_flags
-	 * tells us which quota is active and should be copied to
-	 * disk.
+	 * GQUOTINO and PQUOTINO cannot be used together in versions of
+	 * superblock that do not have pquotino. from->sb_flags tells us which
+	 * quota is active and should be copied to disk. If neither are active,
+	 * make sure we write NULLFSINO to the sb_gquotino field as a quota
+	 * inode value of "0" is invalid when the XFS_SB_VERSION_QUOTA feature
+	 * bit is set.
+	 *
+	 * Note that we don't need to handle the sb_uquotino or sb_pquotino here
+	 * as they do not require any translation. Hence the main sb field loop
+	 * will write them appropriately from the in-core superblock.
 	 */
 	if ((*fields & XFS_SB_GQUOTINO) &&
 				(from->sb_qflags & XFS_GQUOTA_ACCT))
@@ -502,6 +500,17 @@ xfs_sb_quota_to_disk(
 	else if ((*fields & XFS_SB_PQUOTINO) &&
 				(from->sb_qflags & XFS_PQUOTA_ACCT))
 		to->sb_gquotino = cpu_to_be64(from->sb_pquotino);
+	else {
+		/*
+		 * We can't rely on just the fields being logged to tell us
+		 * that it is safe to write NULLFSINO - we should only do that
+		 * if quotas are not actually enabled. Hence only write
+		 * NULLFSINO if both in-core quota inodes are NULL.
+		 */
+		if (from->sb_gquotino == NULLFSINO &&
+		    from->sb_pquotino == NULLFSINO)
+			to->sb_gquotino = cpu_to_be64(NULLFSINO);
+	}
 
 	*fields &= ~(XFS_SB_PQUOTINO | XFS_SB_GQUOTINO);
 }
diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h
index f7b2fe77c5a..c43c2d609a2 100644
--- a/fs/xfs/xfs_sb.h
+++ b/fs/xfs/xfs_sb.h
@@ -36,8 +36,6 @@ struct xfs_trans;
 #define	XFS_SB_VERSION_5	5		/* CRC enabled filesystem */
 #define	XFS_SB_VERSION_NUMBITS		0x000f
 #define	XFS_SB_VERSION_ALLFBITS		0xfff0
-#define	XFS_SB_VERSION_SASHFBITS	0xf000
-#define	XFS_SB_VERSION_REALFBITS	0x0ff0
 #define	XFS_SB_VERSION_ATTRBIT		0x0010
 #define	XFS_SB_VERSION_NLINKBIT		0x0020
 #define	XFS_SB_VERSION_QUOTABIT		0x0040
@@ -50,24 +48,15 @@ struct xfs_trans;
 #define	XFS_SB_VERSION_DIRV2BIT		0x2000
 #define	XFS_SB_VERSION_BORGBIT		0x4000	/* ASCII only case-insens. */
 #define	XFS_SB_VERSION_MOREBITSBIT	0x8000
-#define	XFS_SB_VERSION_OKSASHFBITS	\
-	(XFS_SB_VERSION_EXTFLGBIT | \
-	 XFS_SB_VERSION_DIRV2BIT | \
-	 XFS_SB_VERSION_BORGBIT)
-#define	XFS_SB_VERSION_OKREALFBITS	\
-	(XFS_SB_VERSION_ATTRBIT | \
-	 XFS_SB_VERSION_NLINKBIT | \
-	 XFS_SB_VERSION_QUOTABIT | \
-	 XFS_SB_VERSION_ALIGNBIT | \
-	 XFS_SB_VERSION_DALIGNBIT | \
-	 XFS_SB_VERSION_SHAREDBIT | \
-	 XFS_SB_VERSION_LOGV2BIT | \
-	 XFS_SB_VERSION_SECTORBIT | \
-	 XFS_SB_VERSION_MOREBITSBIT)
-#define	XFS_SB_VERSION_OKREALBITS	\
-	(XFS_SB_VERSION_NUMBITS | \
-	 XFS_SB_VERSION_OKREALFBITS | \
-	 XFS_SB_VERSION_OKSASHFBITS)
+
+/*
+ * Supported feature bit list is just all bits in the versionnum field because
+ * we've used them all up and understand them all. Except, of course, for the
+ * shared superblock bit, which nobody knows what it does and so is unsupported.
+ */
+#define	XFS_SB_VERSION_OKBITS		\
+	((XFS_SB_VERSION_NUMBITS | XFS_SB_VERSION_ALLFBITS) & \
+		~XFS_SB_VERSION_SHAREDBIT)
 
 /*
  * There are two words to hold XFS "feature" bits: the original
@@ -76,7 +65,6 @@ struct xfs_trans;
  *
  * These defines represent bits in sb_features2.
  */
-#define XFS_SB_VERSION2_REALFBITS	0x00ffffff	/* Mask: features */
 #define XFS_SB_VERSION2_RESERVED1BIT	0x00000001
 #define XFS_SB_VERSION2_LAZYSBCOUNTBIT	0x00000002	/* Superblk counters */
 #define XFS_SB_VERSION2_RESERVED4BIT	0x00000004
@@ -86,16 +74,11 @@ struct xfs_trans;
 #define XFS_SB_VERSION2_CRCBIT		0x00000100	/* metadata CRCs */
 #define XFS_SB_VERSION2_FTYPE		0x00000200	/* inode type in dir */
 
-#define	XFS_SB_VERSION2_OKREALFBITS	\
+#define	XFS_SB_VERSION2_OKBITS		\
 	(XFS_SB_VERSION2_LAZYSBCOUNTBIT	| \
 	 XFS_SB_VERSION2_ATTR2BIT	| \
 	 XFS_SB_VERSION2_PROJID32BIT	| \
 	 XFS_SB_VERSION2_FTYPE)
-#define	XFS_SB_VERSION2_OKSASHFBITS	\
-	(0)
-#define XFS_SB_VERSION2_OKREALBITS	\
-	(XFS_SB_VERSION2_OKREALFBITS |	\
-	 XFS_SB_VERSION2_OKSASHFBITS )
 
 /*
  * Superblock - in core version.  Must match the ondisk version below.
@@ -345,214 +328,140 @@ typedef enum {
 
 #define	XFS_SB_VERSION_NUM(sbp)	((sbp)->sb_versionnum & XFS_SB_VERSION_NUMBITS)
 
-static inline int xfs_sb_good_version(xfs_sb_t *sbp)
-{
-	/* We always support version 1-3 */
-	if (sbp->sb_versionnum >= XFS_SB_VERSION_1 &&
-	    sbp->sb_versionnum <= XFS_SB_VERSION_3)
-		return 1;
-
-	/* We support version 4 if all feature bits are supported */
-	if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) {
-		if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKREALBITS) ||
-		    ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
-		     (sbp->sb_features2 & ~XFS_SB_VERSION2_OKREALBITS)))
-			return 0;
-
-		if (sbp->sb_shared_vn > XFS_SB_MAX_SHARED_VN)
-			return 0;
-		return 1;
-	}
-	if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5)
-		return 1;
-
-	return 0;
-}
-
 /*
- * Detect a mismatched features2 field.  Older kernels read/wrote
- * this into the wrong slot, so to be safe we keep them in sync.
+ * The first XFS version we support is a v4 superblock with V2 directories.
  */
-static inline int xfs_sb_has_mismatched_features2(xfs_sb_t *sbp)
+static inline bool xfs_sb_good_v4_features(struct xfs_sb *sbp)
 {
-	return (sbp->sb_bad_features2 != sbp->sb_features2);
-}
-
-static inline unsigned xfs_sb_version_tonew(unsigned v)
-{
-	if (v == XFS_SB_VERSION_1)
-		return XFS_SB_VERSION_4;
+	if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT))
+		return false;
 
-	if (v == XFS_SB_VERSION_2)
-		return XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT;
+	/* check for unknown features in the fs */
+	if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) ||
+	    ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
+	     (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS)))
+		return false;
 
-	return XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT |
-		XFS_SB_VERSION_NLINKBIT;
+	return true;
 }
 
-static inline unsigned xfs_sb_version_toold(unsigned v)
+static inline bool xfs_sb_good_version(struct xfs_sb *sbp)
 {
-	if (v & (XFS_SB_VERSION_QUOTABIT | XFS_SB_VERSION_ALIGNBIT))
-		return 0;
-	if (v & XFS_SB_VERSION_NLINKBIT)
-		return XFS_SB_VERSION_3;
-	if (v & XFS_SB_VERSION_ATTRBIT)
-		return XFS_SB_VERSION_2;
-	return XFS_SB_VERSION_1;
-}
-
-static inline int xfs_sb_version_hasattr(xfs_sb_t *sbp)
-{
-	return sbp->sb_versionnum == XFS_SB_VERSION_2 ||
-		sbp->sb_versionnum == XFS_SB_VERSION_3 ||
-		(XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
-		 (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT));
+	if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5)
+		return true;
+	if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4)
+		return xfs_sb_good_v4_features(sbp);
+	return false;
 }
 
-static inline void xfs_sb_version_addattr(xfs_sb_t *sbp)
+/*
+ * Detect a mismatched features2 field.  Older kernels read/wrote
+ * this into the wrong slot, so to be safe we keep them in sync.
+ */
+static inline bool xfs_sb_has_mismatched_features2(struct xfs_sb *sbp)
 {
-	if (sbp->sb_versionnum == XFS_SB_VERSION_1)
-		sbp->sb_versionnum = XFS_SB_VERSION_2;
-	else if (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4)
-		sbp->sb_versionnum |= XFS_SB_VERSION_ATTRBIT;
-	else
-		sbp->sb_versionnum = XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT;
+	return sbp->sb_bad_features2 != sbp->sb_features2;
 }
 
-static inline int xfs_sb_version_hasnlink(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasattr(struct xfs_sb *sbp)
 {
-	return sbp->sb_versionnum == XFS_SB_VERSION_3 ||
-		 (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
-		  (sbp->sb_versionnum & XFS_SB_VERSION_NLINKBIT));
+	return (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT);
 }
 
-static inline void xfs_sb_version_addnlink(xfs_sb_t *sbp)
+static inline void xfs_sb_version_addattr(struct xfs_sb *sbp)
 {
-	if (sbp->sb_versionnum <= XFS_SB_VERSION_2)
-		sbp->sb_versionnum = XFS_SB_VERSION_3;
-	else
-		sbp->sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
+	sbp->sb_versionnum |= XFS_SB_VERSION_ATTRBIT;
 }
 
-static inline int xfs_sb_version_hasquota(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasquota(struct xfs_sb *sbp)
 {
-	return XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
-		(sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT);
+	return (sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT);
 }
 
-static inline void xfs_sb_version_addquota(xfs_sb_t *sbp)
+static inline void xfs_sb_version_addquota(struct xfs_sb *sbp)
 {
-	if (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4)
-		sbp->sb_versionnum |= XFS_SB_VERSION_QUOTABIT;
-	else
-		sbp->sb_versionnum = xfs_sb_version_tonew(sbp->sb_versionnum) |
-					XFS_SB_VERSION_QUOTABIT;
+	sbp->sb_versionnum |= XFS_SB_VERSION_QUOTABIT;
 }
 
-static inline int xfs_sb_version_hasalign(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasalign(struct xfs_sb *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
-	       (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
+	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
 		(sbp->sb_versionnum & XFS_SB_VERSION_ALIGNBIT));
 }
 
-static inline int xfs_sb_version_hasdalign(xfs_sb_t *sbp)
-{
-	return XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
-		(sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT);
-}
-
-static inline int xfs_sb_version_hasshared(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasdalign(struct xfs_sb *sbp)
 {
-	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
-		(sbp->sb_versionnum & XFS_SB_VERSION_SHAREDBIT);
+	return (sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT);
 }
 
-static inline int xfs_sb_version_hasdirv2(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_haslogv2(struct xfs_sb *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
-	       (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
-		(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT));
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
+	       (sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT);
 }
 
-static inline int xfs_sb_version_haslogv2(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasextflgbit(struct xfs_sb *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
-	       (XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
-		(sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT));
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
+	       (sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT);
 }
 
-static inline int xfs_sb_version_hasextflgbit(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hassector(struct xfs_sb *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
-	       (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
-		(sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT));
+	return (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT);
 }
 
-static inline int xfs_sb_version_hassector(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasasciici(struct xfs_sb *sbp)
 {
-	return XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
-		(sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT);
+	return (sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT);
 }
 
-static inline int xfs_sb_version_hasasciici(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasmorebits(struct xfs_sb *sbp)
 {
-	return XFS_SB_VERSION_NUM(sbp) >= XFS_SB_VERSION_4 &&
-		(sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT);
-}
-
-static inline int xfs_sb_version_hasmorebits(xfs_sb_t *sbp)
-{
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
-	       (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
-		(sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT));
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
+	       (sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT);
 }
 
 /*
  * sb_features2 bit version macros.
- *
- * For example, for a bit defined as XFS_SB_VERSION2_FUNBIT, has a macro:
- *
- * SB_VERSION_HASFUNBIT(xfs_sb_t *sbp)
- *	((xfs_sb_version_hasmorebits(sbp) &&
- *	 ((sbp)->sb_features2 & XFS_SB_VERSION2_FUNBIT)
  */
-
-static inline int xfs_sb_version_haslazysbcount(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_haslazysbcount(struct xfs_sb *sbp)
 {
 	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
 	       (xfs_sb_version_hasmorebits(sbp) &&
 		(sbp->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT));
 }
 
-static inline int xfs_sb_version_hasattr2(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasattr2(struct xfs_sb *sbp)
 {
 	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
 	       (xfs_sb_version_hasmorebits(sbp) &&
 		(sbp->sb_features2 & XFS_SB_VERSION2_ATTR2BIT));
 }
 
-static inline void xfs_sb_version_addattr2(xfs_sb_t *sbp)
+static inline void xfs_sb_version_addattr2(struct xfs_sb *sbp)
 {
 	sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT;
 	sbp->sb_features2 |= XFS_SB_VERSION2_ATTR2BIT;
+	sbp->sb_bad_features2 |= XFS_SB_VERSION2_ATTR2BIT;
 }
 
-static inline void xfs_sb_version_removeattr2(xfs_sb_t *sbp)
+static inline void xfs_sb_version_removeattr2(struct xfs_sb *sbp)
 {
 	sbp->sb_features2 &= ~XFS_SB_VERSION2_ATTR2BIT;
+	sbp->sb_bad_features2 &= ~XFS_SB_VERSION2_ATTR2BIT;
 	if (!sbp->sb_features2)
 		sbp->sb_versionnum &= ~XFS_SB_VERSION_MOREBITSBIT;
 }
 
-static inline int xfs_sb_version_hasprojid32bit(xfs_sb_t *sbp)
+static inline bool xfs_sb_version_hasprojid32bit(struct xfs_sb *sbp)
 {
 	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) ||
 	       (xfs_sb_version_hasmorebits(sbp) &&
 		(sbp->sb_features2 & XFS_SB_VERSION2_PROJID32BIT));
 }
 
-static inline void xfs_sb_version_addprojid32bit(xfs_sb_t *sbp)
+static inline void xfs_sb_version_addprojid32bit(struct xfs_sb *sbp)
 {
 	sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT;
 	sbp->sb_features2 |= XFS_SB_VERSION2_PROJID32BIT;
@@ -587,7 +496,9 @@ xfs_sb_has_compat_feature(
 	return (sbp->sb_features_compat & feature) != 0;
 }
 
-#define XFS_SB_FEAT_RO_COMPAT_ALL 0
+#define XFS_SB_FEAT_RO_COMPAT_FINOBT   (1 << 0)		/* free inode btree */
+#define XFS_SB_FEAT_RO_COMPAT_ALL \
+		(XFS_SB_FEAT_RO_COMPAT_FINOBT)
 #define XFS_SB_FEAT_RO_COMPAT_UNKNOWN	~XFS_SB_FEAT_RO_COMPAT_ALL
 static inline bool
 xfs_sb_has_ro_compat_feature(
@@ -623,12 +534,12 @@ xfs_sb_has_incompat_log_feature(
 /*
  * V5 superblock specific feature checks
  */
-static inline int xfs_sb_version_hascrc(xfs_sb_t *sbp)
+static inline int xfs_sb_version_hascrc(struct xfs_sb *sbp)
 {
 	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5;
 }
 
-static inline int xfs_sb_version_has_pquotino(xfs_sb_t *sbp)
+static inline int xfs_sb_version_has_pquotino(struct xfs_sb *sbp)
 {
 	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5;
 }
@@ -641,6 +552,12 @@ static inline int xfs_sb_version_hasftype(struct xfs_sb *sbp)
 		 (sbp->sb_features2 & XFS_SB_VERSION2_FTYPE));
 }
 
+static inline int xfs_sb_version_hasfinobt(xfs_sb_t *sbp)
+{
+	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) &&
+		(sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FINOBT);
+}
+
 /*
  * end of superblock version macros
  */
diff --git a/fs/xfs/xfs_shared.h b/fs/xfs/xfs_shared.h
index 4484e515139..82404da2ca6 100644
--- a/fs/xfs/xfs_shared.h
+++ b/fs/xfs/xfs_shared.h
@@ -238,7 +238,7 @@ int	xfs_log_calc_minimum_size(struct xfs_mount *);
 int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
 int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
 			uint32_t size, struct xfs_buf *bp);
-bool xfs_symlink_hdr_ok(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
+bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
 			uint32_t size, struct xfs_buf *bp);
 void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
 				 struct xfs_inode *ip, struct xfs_ifork *ifp);
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index ce372b7d564..f2240383d4b 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -59,6 +59,7 @@ static int xfs_stat_proc_show(struct seq_file *m, void *v)
 		{ "abtc2",		XFSSTAT_END_ABTC_V2		},
 		{ "bmbt2",		XFSSTAT_END_BMBT_V2		},
 		{ "ibt2",		XFSSTAT_END_IBT_V2		},
+		{ "fibt2",		XFSSTAT_END_FIBT_V2		},
 		/* we print both series of quota information together */
 		{ "qm",			XFSSTAT_END_QM			},
 	};
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index c03ad38ceae..c8f238b8299 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -183,7 +183,23 @@ struct xfsstats {
 	__uint32_t		xs_ibt_2_alloc;
 	__uint32_t		xs_ibt_2_free;
 	__uint32_t		xs_ibt_2_moves;
-#define XFSSTAT_END_XQMSTAT		(XFSSTAT_END_IBT_V2+6)
+#define XFSSTAT_END_FIBT_V2		(XFSSTAT_END_IBT_V2+15)
+	__uint32_t		xs_fibt_2_lookup;
+	__uint32_t		xs_fibt_2_compare;
+	__uint32_t		xs_fibt_2_insrec;
+	__uint32_t		xs_fibt_2_delrec;
+	__uint32_t		xs_fibt_2_newroot;
+	__uint32_t		xs_fibt_2_killroot;
+	__uint32_t		xs_fibt_2_increment;
+	__uint32_t		xs_fibt_2_decrement;
+	__uint32_t		xs_fibt_2_lshift;
+	__uint32_t		xs_fibt_2_rshift;
+	__uint32_t		xs_fibt_2_split;
+	__uint32_t		xs_fibt_2_join;
+	__uint32_t		xs_fibt_2_alloc;
+	__uint32_t		xs_fibt_2_free;
+	__uint32_t		xs_fibt_2_moves;
+#define XFSSTAT_END_XQMSTAT		(XFSSTAT_END_FIBT_V2+6)
 	__uint32_t		xs_qm_dqreclaims;
 	__uint32_t		xs_qm_dqreclaim_misses;
 	__uint32_t		xs_qm_dquot_dups;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 3494eff8e4e..8f0333b3f7a 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -765,20 +765,18 @@ xfs_open_devices(
 	 * Setup xfs_mount buffer target pointers
 	 */
 	error = ENOMEM;
-	mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, 0, mp->m_fsname);
+	mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev);
 	if (!mp->m_ddev_targp)
 		goto out_close_rtdev;
 
 	if (rtdev) {
-		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, 1,
-							mp->m_fsname);
+		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev);
 		if (!mp->m_rtdev_targp)
 			goto out_free_ddev_targ;
 	}
 
 	if (logdev && logdev != ddev) {
-		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, 1,
-							mp->m_fsname);
+		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev);
 		if (!mp->m_logdev_targp)
 			goto out_free_rtdev_targ;
 	} else {
@@ -811,8 +809,7 @@ xfs_setup_devices(
 {
 	int			error;
 
-	error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_blocksize,
-				    mp->m_sb.sb_sectsize);
+	error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_sectsize);
 	if (error)
 		return error;
 
@@ -822,14 +819,12 @@ xfs_setup_devices(
 		if (xfs_sb_version_hassector(&mp->m_sb))
 			log_sector_size = mp->m_sb.sb_logsectsize;
 		error = xfs_setsize_buftarg(mp->m_logdev_targp,
-					    mp->m_sb.sb_blocksize,
 					    log_sector_size);
 		if (error)
 			return error;
 	}
 	if (mp->m_rtdev_targp) {
 		error = xfs_setsize_buftarg(mp->m_rtdev_targp,
-					    mp->m_sb.sb_blocksize,
 					    mp->m_sb.sb_sectsize);
 		if (error)
 			return error;
@@ -1754,13 +1749,9 @@ init_xfs_fs(void)
 	if (error)
 		goto out_destroy_wq;
 
-	error = xfs_filestream_init();
-	if (error)
-		goto out_mru_cache_uninit;
-
 	error = xfs_buf_init();
 	if (error)
-		goto out_filestream_uninit;
+		goto out_mru_cache_uninit;
 
 	error = xfs_init_procfs();
 	if (error)
@@ -1787,8 +1778,6 @@ init_xfs_fs(void)
 	xfs_cleanup_procfs();
  out_buf_terminate:
 	xfs_buf_terminate();
- out_filestream_uninit:
-	xfs_filestream_uninit();
  out_mru_cache_uninit:
 	xfs_mru_cache_uninit();
  out_destroy_wq:
@@ -1807,7 +1796,6 @@ exit_xfs_fs(void)
 	xfs_sysctl_unregister();
 	xfs_cleanup_procfs();
 	xfs_buf_terminate();
-	xfs_filestream_uninit();
 	xfs_mru_cache_uninit();
 	xfs_destroy_workqueues();
 	xfs_destroy_zones();
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 52979aa9098..d69363c833e 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -27,6 +27,7 @@
 #include "xfs_ag.h"
 #include "xfs_mount.h"
 #include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_dir2.h"
 #include "xfs_inode.h"
 #include "xfs_ialloc.h"
@@ -92,7 +93,7 @@ xfs_readlink_bmap(
 
 		cur_chunk = bp->b_addr;
 		if (xfs_sb_version_hascrc(&mp->m_sb)) {
-			if (!xfs_symlink_hdr_ok(mp, ip->i_ino, offset,
+			if (!xfs_symlink_hdr_ok(ip->i_ino, offset,
 							byte_cnt, bp)) {
 				error = EFSCORRUPTED;
 				xfs_alert(mp,
diff --git a/fs/xfs/xfs_symlink_remote.c b/fs/xfs/xfs_symlink_remote.c
index 9b32052ff65..23c2f2577c8 100644
--- a/fs/xfs/xfs_symlink_remote.c
+++ b/fs/xfs/xfs_symlink_remote.c
@@ -80,7 +80,6 @@ xfs_symlink_hdr_set(
  */
 bool
 xfs_symlink_hdr_ok(
-	struct xfs_mount	*mp,
 	xfs_ino_t		ino,
 	uint32_t		offset,
 	uint32_t		size,
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index dee3279c095..1e85bcd0e41 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -46,6 +46,7 @@
 #include "xfs_log_recover.h"
 #include "xfs_inode_item.h"
 #include "xfs_bmap_btree.h"
+#include "xfs_filestream.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 65d8c793a25..152f8278263 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -538,6 +538,64 @@ DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold_release);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_binval);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_buf_ordered);
 
+DECLARE_EVENT_CLASS(xfs_filestream_class,
+	TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno),
+	TP_ARGS(ip, agno),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_agnumber_t, agno)
+		__field(int, streams)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->agno = agno;
+		__entry->streams = xfs_filestream_peek_ag(ip->i_mount, agno);
+	),
+	TP_printk("dev %d:%d ino 0x%llx agno %u streams %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->agno,
+		  __entry->streams)
+)
+#define DEFINE_FILESTREAM_EVENT(name) \
+DEFINE_EVENT(xfs_filestream_class, name, \
+	TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno), \
+	TP_ARGS(ip, agno))
+DEFINE_FILESTREAM_EVENT(xfs_filestream_free);
+DEFINE_FILESTREAM_EVENT(xfs_filestream_lookup);
+DEFINE_FILESTREAM_EVENT(xfs_filestream_scan);
+
+TRACE_EVENT(xfs_filestream_pick,
+	TP_PROTO(struct xfs_inode *ip, xfs_agnumber_t agno,
+		 xfs_extlen_t free, int nscan),
+	TP_ARGS(ip, agno, free, nscan),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_agnumber_t, agno)
+		__field(int, streams)
+		__field(xfs_extlen_t, free)
+		__field(int, nscan)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->agno = agno;
+		__entry->streams = xfs_filestream_peek_ag(ip->i_mount, agno);
+		__entry->free = free;
+		__entry->nscan = nscan;
+	),
+	TP_printk("dev %d:%d ino 0x%llx agno %u streams %d free %d nscan %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->agno,
+		  __entry->streams,
+		  __entry->free,
+		  __entry->nscan)
+);
+
 DECLARE_EVENT_CLASS(xfs_lock_class,
 	TP_PROTO(struct xfs_inode *ip, unsigned lock_flags,
 		 unsigned long caller_ip),
@@ -1060,7 +1118,6 @@ DEFINE_RW_EVENT(xfs_file_read);
 DEFINE_RW_EVENT(xfs_file_buffered_write);
 DEFINE_RW_EVENT(xfs_file_direct_write);
 DEFINE_RW_EVENT(xfs_file_splice_read);
-DEFINE_RW_EVENT(xfs_file_splice_write);
 
 DECLARE_EVENT_CLASS(xfs_page_class,
 	TP_PROTO(struct inode *inode, struct page *page, unsigned long off,
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 54a57326d85..d03932564cc 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -827,7 +827,7 @@ xfs_trans_committed_bulk(
 		xfs_log_item_batch_insert(ailp, &cur, log_items, i, commit_lsn);
 
 	spin_lock(&ailp->xa_lock);
-	xfs_trans_ail_cursor_done(ailp, &cur);
+	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->xa_lock);
 }
 
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index a7287354e53..cb0f3a84cc6 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -173,7 +173,6 @@ xfs_trans_ail_cursor_next(
  */
 void
 xfs_trans_ail_cursor_done(
-	struct xfs_ail		*ailp,
 	struct xfs_ail_cursor	*cur)
 {
 	cur->item = NULL;
@@ -368,7 +367,7 @@ xfsaild_push(
 		 * If the AIL is empty or our push has reached the end we are
 		 * done now.
 		 */
-		xfs_trans_ail_cursor_done(ailp, &cur);
+		xfs_trans_ail_cursor_done(&cur);
 		spin_unlock(&ailp->xa_lock);
 		goto out_done;
 	}
@@ -453,7 +452,7 @@ xfsaild_push(
 			break;
 		lsn = lip->li_lsn;
 	}
-	xfs_trans_ail_cursor_done(ailp, &cur);
+	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->xa_lock);
 
 	if (xfs_buf_delwri_submit_nowait(&ailp->xa_buf_list))
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 12e86af9d9b..bd1281862ad 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -133,8 +133,7 @@ struct xfs_log_item *	xfs_trans_ail_cursor_last(struct xfs_ail *ailp,
 					xfs_lsn_t lsn);
 struct xfs_log_item *	xfs_trans_ail_cursor_next(struct xfs_ail *ailp,
 					struct xfs_ail_cursor *cur);
-void			xfs_trans_ail_cursor_done(struct xfs_ail *ailp,
-					struct xfs_ail_cursor *cur);
+void			xfs_trans_ail_cursor_done(struct xfs_ail_cursor *cur);
 
 #if BITS_PER_LONG != 64
 static inline void
diff --git a/fs/xfs/xfs_trans_resv.c b/fs/xfs/xfs_trans_resv.c
index ae368165244..f2bda7c76b8 100644
--- a/fs/xfs/xfs_trans_resv.c
+++ b/fs/xfs/xfs_trans_resv.c
@@ -26,6 +26,7 @@
 #include "xfs_ag.h"
 #include "xfs_mount.h"
 #include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_inode.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_ialloc.h"
@@ -106,6 +107,47 @@ xfs_calc_inode_res(
 }
 
 /*
+ * The free inode btree is a conditional feature and the log reservation
+ * requirements differ slightly from that of the traditional inode allocation
+ * btree. The finobt tracks records for inode chunks with at least one free
+ * inode. A record can be removed from the tree for an inode allocation
+ * or free and thus the finobt reservation is unconditional across:
+ *
+ * 	- inode allocation
+ * 	- inode free
+ * 	- inode chunk allocation
+ *
+ * The 'modify' param indicates to include the record modification scenario. The
+ * 'alloc' param indicates to include the reservation for free space btree
+ * modifications on behalf of finobt modifications. This is required only for
+ * transactions that do not already account for free space btree modifications.
+ *
+ * the free inode btree: max depth * block size
+ * the allocation btrees: 2 trees * (max depth - 1) * block size
+ * the free inode btree entry: block size
+ */
+STATIC uint
+xfs_calc_finobt_res(
+	struct xfs_mount 	*mp,
+	int			alloc,
+	int			modify)
+{
+	uint res;
+
+	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+		return 0;
+
+	res = xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1));
+	if (alloc)
+		res += xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1), 
+					XFS_FSB_TO_B(mp, 1));
+	if (modify)
+		res += (uint)XFS_FSB_TO_B(mp, 1);
+
+	return res;
+}
+
+/*
  * Various log reservation values.
  *
  * These are based on the size of the file system block because that is what
@@ -302,6 +344,7 @@ xfs_calc_remove_reservation(
  *    the superblock for the nlink flag: sector size
  *    the directory btree: (max depth + v2) * dir block size
  *    the directory inode's bmap btree: (max depth + v2) * block size
+ *    the finobt (record modification and allocation btrees)
  */
 STATIC uint
 xfs_calc_create_resv_modify(
@@ -310,7 +353,8 @@ xfs_calc_create_resv_modify(
 	return xfs_calc_inode_res(mp, 2) +
 		xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
 		(uint)XFS_FSB_TO_B(mp, 1) +
-		xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1));
+		xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1)) +
+		xfs_calc_finobt_res(mp, 1, 1);
 }
 
 /*
@@ -348,6 +392,7 @@ __xfs_calc_create_reservation(
  *    the superblock for the nlink flag: sector size
  *    the inode btree: max depth * blocksize
  *    the allocation btrees: 2 trees * (max depth - 1) * block size
+ *    the finobt (record insertion)
  */
 STATIC uint
 xfs_calc_icreate_resv_alloc(
@@ -357,7 +402,8 @@ xfs_calc_icreate_resv_alloc(
 		mp->m_sb.sb_sectsize +
 		xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
 		xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
-				 XFS_FSB_TO_B(mp, 1));
+				 XFS_FSB_TO_B(mp, 1)) +
+		xfs_calc_finobt_res(mp, 0, 0);
 }
 
 STATIC uint
@@ -425,6 +471,7 @@ xfs_calc_symlink_reservation(
  *    the on disk inode before ours in the agi hash list: inode cluster size
  *    the inode btree: max depth * blocksize
  *    the allocation btrees: 2 trees * (max depth - 1) * block size
+ *    the finobt (record insertion, removal or modification)
  */
 STATIC uint
 xfs_calc_ifree_reservation(
@@ -439,7 +486,8 @@ xfs_calc_ifree_reservation(
 		xfs_calc_buf_res(2 + mp->m_ialloc_blks +
 				 mp->m_in_maxlevels, 0) +
 		xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
-				 XFS_FSB_TO_B(mp, 1));
+				 XFS_FSB_TO_B(mp, 1)) +
+		xfs_calc_finobt_res(mp, 0, 1);
 }
 
 /*
@@ -562,7 +610,7 @@ xfs_calc_addafork_reservation(
 	return XFS_DQUOT_LOGRES(mp) +
 		xfs_calc_inode_res(mp, 1) +
 		xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
-		xfs_calc_buf_res(1, mp->m_dirblksize) +
+		xfs_calc_buf_res(1, mp->m_dir_geo->blksize) +
 		xfs_calc_buf_res(XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK) + 1,
 				 XFS_FSB_TO_B(mp, 1)) +
 		xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
diff --git a/fs/xfs/xfs_trans_space.h b/fs/xfs/xfs_trans_space.h
index af5dbe06cb6..bf9c4579334 100644
--- a/fs/xfs/xfs_trans_space.h
+++ b/fs/xfs/xfs_trans_space.h
@@ -28,7 +28,8 @@
 	(((b + XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp) - 1) / \
 	  XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
 	  XFS_EXTENTADD_SPACE_RES(mp,w))
-#define	XFS_DAENTER_1B(mp,w)	((w) == XFS_DATA_FORK ? (mp)->m_dirblkfsbs : 1)
+#define	XFS_DAENTER_1B(mp,w)	\
+	((w) == XFS_DATA_FORK ? (mp)->m_dir_geo->fsbcount : 1)
 #define	XFS_DAENTER_DBS(mp,w)	\
 	(XFS_DA_NODE_MAXDEPTH + (((w) == XFS_DATA_FORK) ? 2 : 0))
 #define	XFS_DAENTER_BLOCKS(mp,w)	\
@@ -47,13 +48,15 @@
 #define	XFS_DIRREMOVE_SPACE_RES(mp)	\
 	XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK)
 #define	XFS_IALLOC_SPACE_RES(mp)	\
-	((mp)->m_ialloc_blks + (mp)->m_in_maxlevels - 1)
+	((mp)->m_ialloc_blks + \
+	 (xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1 * \
+	  ((mp)->m_in_maxlevels - 1)))
 
 /*
  * Space reservation values for various transactions.
  */
 #define	XFS_ADDAFORK_SPACE_RES(mp)	\
-	((mp)->m_dirblkfsbs + XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK))
+	((mp)->m_dir_geo->fsbcount + XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK))
 #define	XFS_ATTRRM_SPACE_RES(mp)	\
 	XFS_DAREMOVE_SPACE_RES(mp, XFS_ATTR_FORK)
 /* This macro is not used - see inline code in xfs_attr_set */
@@ -82,5 +85,8 @@
 	(XFS_DIRREMOVE_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl))
 #define	XFS_SYMLINK_SPACE_RES(mp,nl,b)	\
 	(XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl) + (b))
+#define XFS_IFREE_SPACE_RES(mp)		\
+	(xfs_sb_version_hasfinobt(&mp->m_sb) ? (mp)->m_in_maxlevels : 0)
+
 
 #endif	/* __XFS_TRANS_SPACE_H__ */
diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h
index 82bbc34d54a..65c6e6650b1 100644
--- a/fs/xfs/xfs_types.h
+++ b/fs/xfs/xfs_types.h
@@ -134,7 +134,7 @@ typedef enum {
 
 typedef enum {
 	XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_BMAPi, XFS_BTNUM_INOi,
-	XFS_BTNUM_MAX
+	XFS_BTNUM_FINOi, XFS_BTNUM_MAX
 } xfs_btnum_t;
 
 struct xfs_name {
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 6eb1d3cb510..9b9b6f29bbf 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -53,7 +53,7 @@ struct acpi_power_register {
 	u8 bit_offset;
 	u8 access_size;
 	u64 address;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_processor_cx {
 	u8 valid;
@@ -83,7 +83,7 @@ struct acpi_psd_package {
 	u64 domain;
 	u64 coord_type;
 	u64 num_processors;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_pct_register {
 	u8 descriptor;
@@ -93,7 +93,7 @@ struct acpi_pct_register {
 	u8 bit_offset;
 	u8 reserved;
 	u64 address;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_processor_px {
 	u64 core_frequency;	/* megahertz */
@@ -124,7 +124,7 @@ struct acpi_tsd_package {
 	u64 domain;
 	u64 coord_type;
 	u64 num_processors;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_ptc_register {
 	u8 descriptor;
@@ -134,7 +134,7 @@ struct acpi_ptc_register {
 	u8 bit_offset;
 	u8 reserved;
 	u64 address;
-} __attribute__ ((packed));
+} __packed;
 
 struct acpi_processor_tx_tss {
 	u64 freqpercentage;	/* */
diff --git a/include/acpi/video.h b/include/acpi/video.h
index ea4c7bbded4..843ef1adfbf 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -22,6 +22,7 @@ extern void acpi_video_unregister(void);
 extern void acpi_video_unregister_backlight(void);
 extern int acpi_video_get_edid(struct acpi_device *device, int type,
 			       int device_id, void **edid);
+extern bool acpi_video_verify_backlight_support(void);
 #else
 static inline int acpi_video_register(void) { return 0; }
 static inline void acpi_video_unregister(void) { return; }
@@ -31,6 +32,7 @@ static inline int acpi_video_get_edid(struct acpi_device *device, int type,
 {
 	return -ENODEV;
 }
+static inline bool acpi_video_verify_backlight_support(void) { return false; }
 #endif
 
 #endif
diff --git a/include/asm-generic/io-64-nonatomic-hi-lo.h b/include/asm-generic/io-64-nonatomic-hi-lo.h
index a6806a94250..2e29d13fc15 100644
--- a/include/asm-generic/io-64-nonatomic-hi-lo.h
+++ b/include/asm-generic/io-64-nonatomic-hi-lo.h
@@ -4,8 +4,7 @@
 #include <linux/io.h>
 #include <asm-generic/int-ll64.h>
 
-#ifndef readq
-static inline __u64 readq(const volatile void __iomem *addr)
+static inline __u64 hi_lo_readq(const volatile void __iomem *addr)
 {
 	const volatile u32 __iomem *p = addr;
 	u32 low, high;
@@ -15,14 +14,19 @@ static inline __u64 readq(const volatile void __iomem *addr)
 
 	return low + ((u64)high << 32);
 }
-#endif
 
-#ifndef writeq
-static inline void writeq(__u64 val, volatile void __iomem *addr)
+static inline void hi_lo_writeq(__u64 val, volatile void __iomem *addr)
 {
 	writel(val >> 32, addr + 4);
 	writel(val, addr);
 }
+
+#ifndef readq
+#define readq hi_lo_readq
+#endif
+
+#ifndef writeq
+#define writeq hi_lo_writeq
 #endif
 
 #endif	/* _ASM_IO_64_NONATOMIC_HI_LO_H_ */
diff --git a/include/asm-generic/io-64-nonatomic-lo-hi.h b/include/asm-generic/io-64-nonatomic-lo-hi.h
index ca546b1ff8b..0efacff0a1c 100644
--- a/include/asm-generic/io-64-nonatomic-lo-hi.h
+++ b/include/asm-generic/io-64-nonatomic-lo-hi.h
@@ -4,8 +4,7 @@
 #include <linux/io.h>
 #include <asm-generic/int-ll64.h>
 
-#ifndef readq
-static inline __u64 readq(const volatile void __iomem *addr)
+static inline __u64 lo_hi_readq(const volatile void __iomem *addr)
 {
 	const volatile u32 __iomem *p = addr;
 	u32 low, high;
@@ -15,14 +14,19 @@ static inline __u64 readq(const volatile void __iomem *addr)
 
 	return low + ((u64)high << 32);
 }
-#endif
 
-#ifndef writeq
-static inline void writeq(__u64 val, volatile void __iomem *addr)
+static inline void lo_hi_writeq(__u64 val, volatile void __iomem *addr)
 {
 	writel(val, addr);
 	writel(val >> 32, addr + 4);
 }
+
+#ifndef readq
+#define readq lo_hi_readq
+#endif
+
+#ifndef writeq
+#define writeq lo_hi_writeq
 #endif
 
 #endif	/* _ASM_IO_64_NONATOMIC_LO_HI_H_ */
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 0703aa75b5e..4d9f233c4ba 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -36,93 +36,385 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 #endif
 
 /*
- * Add a offset to a pointer but keep the pointer as is.
- *
- * Only S390 provides its own means of moving the pointer.
+ * Arch may define arch_raw_cpu_ptr() to provide more efficient address
+ * translations for raw_cpu_ptr().
  */
-#ifndef SHIFT_PERCPU_PTR
-/* Weird cast keeps both GCC and sparse happy. */
-#define SHIFT_PERCPU_PTR(__p, __offset)	({				\
-	__verify_pcpu_ptr((__p));					\
-	RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset)); \
-})
+#ifndef arch_raw_cpu_ptr
+#define arch_raw_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
 #endif
 
-/*
- * A percpu variable may point to a discarded regions. The following are
- * established ways to produce a usable pointer from the percpu variable
- * offset.
- */
-#define per_cpu(var, cpu) \
-	(*SHIFT_PERCPU_PTR(&(var), per_cpu_offset(cpu)))
-
-#ifndef raw_cpu_ptr
-#define raw_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+extern void setup_per_cpu_areas(void);
 #endif
-#ifdef CONFIG_DEBUG_PREEMPT
-#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+
+#endif	/* SMP */
+
+#ifndef PER_CPU_BASE_SECTION
+#ifdef CONFIG_SMP
+#define PER_CPU_BASE_SECTION ".data..percpu"
 #else
-#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr)
+#define PER_CPU_BASE_SECTION ".data"
+#endif
 #endif
 
-#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
-#define __raw_get_cpu_var(var) (*raw_cpu_ptr(&(var)))
+#ifndef PER_CPU_ATTRIBUTES
+#define PER_CPU_ATTRIBUTES
+#endif
 
-#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
-extern void setup_per_cpu_areas(void);
+#ifndef PER_CPU_DEF_ATTRIBUTES
+#define PER_CPU_DEF_ATTRIBUTES
 #endif
 
-#else /* ! SMP */
+#define raw_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	*raw_cpu_ptr(&(pcp)) op val;					\
+} while (0)
 
-#define VERIFY_PERCPU_PTR(__p) ({			\
-	__verify_pcpu_ptr((__p));			\
-	(typeof(*(__p)) __kernel __force *)(__p);	\
+#define raw_cpu_generic_add_return(pcp, val)				\
+({									\
+	raw_cpu_add(pcp, val);						\
+	raw_cpu_read(pcp);						\
 })
 
-#define per_cpu(var, cpu)	(*((void)(cpu), VERIFY_PERCPU_PTR(&(var))))
-#define __get_cpu_var(var)	(*VERIFY_PERCPU_PTR(&(var)))
-#define __raw_get_cpu_var(var)	(*VERIFY_PERCPU_PTR(&(var)))
-#define this_cpu_ptr(ptr)	per_cpu_ptr(ptr, 0)
-#define raw_cpu_ptr(ptr)	this_cpu_ptr(ptr)
+#define raw_cpu_generic_xchg(pcp, nval)					\
+({									\
+	typeof(pcp) __ret;						\
+	__ret = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
+	__ret;								\
+})
 
-#endif	/* SMP */
+#define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) __ret;						\
+	__ret = raw_cpu_read(pcp);					\
+	if (__ret == (oval))						\
+		raw_cpu_write(pcp, nval);				\
+	__ret;								\
+})
 
-#ifndef PER_CPU_BASE_SECTION
-#ifdef CONFIG_SMP
-#define PER_CPU_BASE_SECTION ".data..percpu"
-#else
-#define PER_CPU_BASE_SECTION ".data"
+#define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+({									\
+	int __ret = 0;							\
+	if (raw_cpu_read(pcp1) == (oval1) &&				\
+			 raw_cpu_read(pcp2)  == (oval2)) {		\
+		raw_cpu_write(pcp1, nval1);				\
+		raw_cpu_write(pcp2, nval2);				\
+		__ret = 1;						\
+	}								\
+	(__ret);							\
+})
+
+#define this_cpu_generic_read(pcp)					\
+({									\
+	typeof(pcp) __ret;						\
+	preempt_disable();						\
+	__ret = *this_cpu_ptr(&(pcp));					\
+	preempt_enable();						\
+	__ret;								\
+})
+
+#define this_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	*raw_cpu_ptr(&(pcp)) op val;					\
+	raw_local_irq_restore(__flags);					\
+} while (0)
+
+#define this_cpu_generic_add_return(pcp, val)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	raw_cpu_add(pcp, val);						\
+	__ret = raw_cpu_read(pcp);					\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_xchg(pcp, nval)				\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) __ret;						\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_read(pcp);					\
+	if (__ret == (oval))						\
+		raw_cpu_write(pcp, nval);				\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#define this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+({									\
+	int __ret;							\
+	unsigned long __flags;						\
+	raw_local_irq_save(__flags);					\
+	__ret = raw_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
+			oval1, oval2, nval1, nval2);			\
+	raw_local_irq_restore(__flags);					\
+	__ret;								\
+})
+
+#ifndef raw_cpu_read_1
+#define raw_cpu_read_1(pcp)		(*raw_cpu_ptr(&(pcp)))
 #endif
+#ifndef raw_cpu_read_2
+#define raw_cpu_read_2(pcp)		(*raw_cpu_ptr(&(pcp)))
+#endif
+#ifndef raw_cpu_read_4
+#define raw_cpu_read_4(pcp)		(*raw_cpu_ptr(&(pcp)))
+#endif
+#ifndef raw_cpu_read_8
+#define raw_cpu_read_8(pcp)		(*raw_cpu_ptr(&(pcp)))
 #endif
 
-#ifdef CONFIG_SMP
+#ifndef raw_cpu_write_1
+#define raw_cpu_write_1(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef raw_cpu_write_2
+#define raw_cpu_write_2(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef raw_cpu_write_4
+#define raw_cpu_write_4(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef raw_cpu_write_8
+#define raw_cpu_write_8(pcp, val)	raw_cpu_generic_to_op(pcp, val, =)
+#endif
 
-#ifdef MODULE
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#define PER_CPU_ALIGNED_SECTION ""
-#else
-#define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
+#ifndef raw_cpu_add_1
+#define raw_cpu_add_1(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef raw_cpu_add_2
+#define raw_cpu_add_2(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef raw_cpu_add_4
+#define raw_cpu_add_4(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef raw_cpu_add_8
+#define raw_cpu_add_8(pcp, val)		raw_cpu_generic_to_op(pcp, val, +=)
 #endif
-#define PER_CPU_FIRST_SECTION "..first"
 
-#else
+#ifndef raw_cpu_and_1
+#define raw_cpu_and_1(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef raw_cpu_and_2
+#define raw_cpu_and_2(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef raw_cpu_and_4
+#define raw_cpu_and_4(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef raw_cpu_and_8
+#define raw_cpu_and_8(pcp, val)		raw_cpu_generic_to_op(pcp, val, &=)
+#endif
+
+#ifndef raw_cpu_or_1
+#define raw_cpu_or_1(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef raw_cpu_or_2
+#define raw_cpu_or_2(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef raw_cpu_or_4
+#define raw_cpu_or_4(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef raw_cpu_or_8
+#define raw_cpu_or_8(pcp, val)		raw_cpu_generic_to_op(pcp, val, |=)
+#endif
 
-#define PER_CPU_SHARED_ALIGNED_SECTION ""
-#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_FIRST_SECTION ""
+#ifndef raw_cpu_add_return_1
+#define raw_cpu_add_return_1(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef raw_cpu_add_return_2
+#define raw_cpu_add_return_2(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef raw_cpu_add_return_4
+#define raw_cpu_add_return_4(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef raw_cpu_add_return_8
+#define raw_cpu_add_return_8(pcp, val)	raw_cpu_generic_add_return(pcp, val)
+#endif
 
+#ifndef raw_cpu_xchg_1
+#define raw_cpu_xchg_1(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef raw_cpu_xchg_2
+#define raw_cpu_xchg_2(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef raw_cpu_xchg_4
+#define raw_cpu_xchg_4(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef raw_cpu_xchg_8
+#define raw_cpu_xchg_8(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 #endif
 
-#ifndef PER_CPU_ATTRIBUTES
-#define PER_CPU_ATTRIBUTES
+#ifndef raw_cpu_cmpxchg_1
+#define raw_cpu_cmpxchg_1(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg_2
+#define raw_cpu_cmpxchg_2(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg_4
+#define raw_cpu_cmpxchg_4(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef raw_cpu_cmpxchg_8
+#define raw_cpu_cmpxchg_8(pcp, oval, nval) \
+	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 #endif
 
-#ifndef PER_CPU_DEF_ATTRIBUTES
-#define PER_CPU_DEF_ATTRIBUTES
+#ifndef raw_cpu_cmpxchg_double_1
+#define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef raw_cpu_cmpxchg_double_2
+#define raw_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef raw_cpu_cmpxchg_double_4
+#define raw_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef raw_cpu_cmpxchg_double_8
+#define raw_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+
+#ifndef this_cpu_read_1
+#define this_cpu_read_1(pcp)		this_cpu_generic_read(pcp)
+#endif
+#ifndef this_cpu_read_2
+#define this_cpu_read_2(pcp)		this_cpu_generic_read(pcp)
+#endif
+#ifndef this_cpu_read_4
+#define this_cpu_read_4(pcp)		this_cpu_generic_read(pcp)
+#endif
+#ifndef this_cpu_read_8
+#define this_cpu_read_8(pcp)		this_cpu_generic_read(pcp)
 #endif
 
-/* Keep until we have removed all uses of __this_cpu_ptr */
-#define __this_cpu_ptr raw_cpu_ptr
+#ifndef this_cpu_write_1
+#define this_cpu_write_1(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef this_cpu_write_2
+#define this_cpu_write_2(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef this_cpu_write_4
+#define this_cpu_write_4(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+#ifndef this_cpu_write_8
+#define this_cpu_write_8(pcp, val)	this_cpu_generic_to_op(pcp, val, =)
+#endif
+
+#ifndef this_cpu_add_1
+#define this_cpu_add_1(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef this_cpu_add_2
+#define this_cpu_add_2(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef this_cpu_add_4
+#define this_cpu_add_4(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+#ifndef this_cpu_add_8
+#define this_cpu_add_8(pcp, val)	this_cpu_generic_to_op(pcp, val, +=)
+#endif
+
+#ifndef this_cpu_and_1
+#define this_cpu_and_1(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef this_cpu_and_2
+#define this_cpu_and_2(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef this_cpu_and_4
+#define this_cpu_and_4(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+#ifndef this_cpu_and_8
+#define this_cpu_and_8(pcp, val)	this_cpu_generic_to_op(pcp, val, &=)
+#endif
+
+#ifndef this_cpu_or_1
+#define this_cpu_or_1(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef this_cpu_or_2
+#define this_cpu_or_2(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef this_cpu_or_4
+#define this_cpu_or_4(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+#ifndef this_cpu_or_8
+#define this_cpu_or_8(pcp, val)		this_cpu_generic_to_op(pcp, val, |=)
+#endif
+
+#ifndef this_cpu_add_return_1
+#define this_cpu_add_return_1(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef this_cpu_add_return_2
+#define this_cpu_add_return_2(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef this_cpu_add_return_4
+#define this_cpu_add_return_4(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+#ifndef this_cpu_add_return_8
+#define this_cpu_add_return_8(pcp, val)	this_cpu_generic_add_return(pcp, val)
+#endif
+
+#ifndef this_cpu_xchg_1
+#define this_cpu_xchg_1(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef this_cpu_xchg_2
+#define this_cpu_xchg_2(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef this_cpu_xchg_4
+#define this_cpu_xchg_4(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+#ifndef this_cpu_xchg_8
+#define this_cpu_xchg_8(pcp, nval)	this_cpu_generic_xchg(pcp, nval)
+#endif
+
+#ifndef this_cpu_cmpxchg_1
+#define this_cpu_cmpxchg_1(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg_2
+#define this_cpu_cmpxchg_2(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg_4
+#define this_cpu_cmpxchg_4(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+#ifndef this_cpu_cmpxchg_8
+#define this_cpu_cmpxchg_8(pcp, oval, nval) \
+	this_cpu_generic_cmpxchg(pcp, oval, nval)
+#endif
+
+#ifndef this_cpu_cmpxchg_double_1
+#define this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef this_cpu_cmpxchg_double_2
+#define this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef this_cpu_cmpxchg_double_4
+#define this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
+#ifndef this_cpu_cmpxchg_double_8
+#define this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#endif
 
 #endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
new file mode 100644
index 00000000000..6383d54bf98
--- /dev/null
+++ b/include/asm-generic/qrwlock.h
@@ -0,0 +1,166 @@
+/*
+ * Queue read/write lock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#ifndef __ASM_GENERIC_QRWLOCK_H
+#define __ASM_GENERIC_QRWLOCK_H
+
+#include <linux/atomic.h>
+#include <asm/barrier.h>
+#include <asm/processor.h>
+
+#include <asm-generic/qrwlock_types.h>
+
+/*
+ * Writer states & reader shift and bias
+ */
+#define	_QW_WAITING	1		/* A writer is waiting	   */
+#define	_QW_LOCKED	0xff		/* A writer holds the lock */
+#define	_QW_WMASK	0xff		/* Writer mask		   */
+#define	_QR_SHIFT	8		/* Reader count shift	   */
+#define _QR_BIAS	(1U << _QR_SHIFT)
+
+/*
+ * External function declarations
+ */
+extern void queue_read_lock_slowpath(struct qrwlock *lock);
+extern void queue_write_lock_slowpath(struct qrwlock *lock);
+
+/**
+ * queue_read_can_lock- would read_trylock() succeed?
+ * @lock: Pointer to queue rwlock structure
+ */
+static inline int queue_read_can_lock(struct qrwlock *lock)
+{
+	return !(atomic_read(&lock->cnts) & _QW_WMASK);
+}
+
+/**
+ * queue_write_can_lock- would write_trylock() succeed?
+ * @lock: Pointer to queue rwlock structure
+ */
+static inline int queue_write_can_lock(struct qrwlock *lock)
+{
+	return !atomic_read(&lock->cnts);
+}
+
+/**
+ * queue_read_trylock - try to acquire read lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static inline int queue_read_trylock(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	cnts = atomic_read(&lock->cnts);
+	if (likely(!(cnts & _QW_WMASK))) {
+		cnts = (u32)atomic_add_return(_QR_BIAS, &lock->cnts);
+		if (likely(!(cnts & _QW_WMASK)))
+			return 1;
+		atomic_sub(_QR_BIAS, &lock->cnts);
+	}
+	return 0;
+}
+
+/**
+ * queue_write_trylock - try to acquire write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static inline int queue_write_trylock(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	cnts = atomic_read(&lock->cnts);
+	if (unlikely(cnts))
+		return 0;
+
+	return likely(atomic_cmpxchg(&lock->cnts,
+				     cnts, cnts | _QW_LOCKED) == cnts);
+}
+/**
+ * queue_read_lock - acquire read lock of a queue rwlock
+ * @lock: Pointer to queue rwlock structure
+ */
+static inline void queue_read_lock(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	cnts = atomic_add_return(_QR_BIAS, &lock->cnts);
+	if (likely(!(cnts & _QW_WMASK)))
+		return;
+
+	/* The slowpath will decrement the reader count, if necessary. */
+	queue_read_lock_slowpath(lock);
+}
+
+/**
+ * queue_write_lock - acquire write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+static inline void queue_write_lock(struct qrwlock *lock)
+{
+	/* Optimize for the unfair lock case where the fair flag is 0. */
+	if (atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0)
+		return;
+
+	queue_write_lock_slowpath(lock);
+}
+
+/**
+ * queue_read_unlock - release read lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+static inline void queue_read_unlock(struct qrwlock *lock)
+{
+	/*
+	 * Atomically decrement the reader count
+	 */
+	smp_mb__before_atomic();
+	atomic_sub(_QR_BIAS, &lock->cnts);
+}
+
+#ifndef queue_write_unlock
+/**
+ * queue_write_unlock - release write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+static inline void queue_write_unlock(struct qrwlock *lock)
+{
+	/*
+	 * If the writer field is atomic, it can be cleared directly.
+	 * Otherwise, an atomic subtraction will be used to clear it.
+	 */
+	smp_mb__before_atomic();
+	atomic_sub(_QW_LOCKED, &lock->cnts);
+}
+#endif
+
+/*
+ * Remapping rwlock architecture specific functions to the corresponding
+ * queue rwlock functions.
+ */
+#define arch_read_can_lock(l)	queue_read_can_lock(l)
+#define arch_write_can_lock(l)	queue_write_can_lock(l)
+#define arch_read_lock(l)	queue_read_lock(l)
+#define arch_write_lock(l)	queue_write_lock(l)
+#define arch_read_trylock(l)	queue_read_trylock(l)
+#define arch_write_trylock(l)	queue_write_trylock(l)
+#define arch_read_unlock(l)	queue_read_unlock(l)
+#define arch_write_unlock(l)	queue_write_unlock(l)
+
+#endif /* __ASM_GENERIC_QRWLOCK_H */
diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h
new file mode 100644
index 00000000000..4d76f24df51
--- /dev/null
+++ b/include/asm-generic/qrwlock_types.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_GENERIC_QRWLOCK_TYPES_H
+#define __ASM_GENERIC_QRWLOCK_TYPES_H
+
+#include <linux/types.h>
+#include <asm/spinlock_types.h>
+
+/*
+ * The queue read/write lock data structure
+ */
+
+typedef struct qrwlock {
+	atomic_t		cnts;
+	arch_spinlock_t		lock;
+} arch_rwlock_t;
+
+#define	__ARCH_RW_LOCK_UNLOCKED {		\
+	.cnts = ATOMIC_INIT(0),			\
+	.lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
+}
+
+#endif /* __ASM_GENERIC_QRWLOCK_TYPES_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index d647637cd69..c1c0b0cf39b 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -109,6 +109,15 @@
 #define BRANCH_PROFILE()
 #endif
 
+#ifdef CONFIG_KPROBES
+#define KPROBE_BLACKLIST()	. = ALIGN(8);				      \
+				VMLINUX_SYMBOL(__start_kprobe_blacklist) = .; \
+				*(_kprobe_blacklist)			      \
+				VMLINUX_SYMBOL(__stop_kprobe_blacklist) = .;
+#else
+#define KPROBE_BLACKLIST()
+#endif
+
 #ifdef CONFIG_EVENT_TRACING
 #define FTRACE_EVENTS()	. = ALIGN(8);					\
 			VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
@@ -478,6 +487,7 @@
 	*(.init.rodata)							\
 	FTRACE_EVENTS()							\
 	TRACE_SYSCALLS()						\
+	KPROBE_BLACKLIST()						\
 	MEM_DISCARD(init.rodata)					\
 	CLK_OF_TABLES()							\
 	RESERVEDMEM_OF_TABLES()						\
@@ -683,7 +693,7 @@
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
 	. = ALIGN(cacheline);						\
-	*(.data..percpu..readmostly)					\
+	*(.data..percpu..read_mostly)					\
 	. = ALIGN(cacheline);						\
 	*(.data..percpu)						\
 	*(.data..percpu..shared_aligned)				\
diff --git a/include/crypto/aead.h b/include/crypto/aead.h
index 0edf949f636..94b19be6757 100644
--- a/include/crypto/aead.h
+++ b/include/crypto/aead.h
@@ -75,9 +75,9 @@ static inline void aead_givcrypt_free(struct aead_givcrypt_request *req)
 
 static inline void aead_givcrypt_set_callback(
 	struct aead_givcrypt_request *req, u32 flags,
-	crypto_completion_t complete, void *data)
+	crypto_completion_t compl, void *data)
 {
-	aead_request_set_callback(&req->areq, flags, complete, data);
+	aead_request_set_callback(&req->areq, flags, compl, data);
 }
 
 static inline void aead_givcrypt_set_crypt(struct aead_givcrypt_request *req,
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 016c2f110f6..623a59c1ff5 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -410,4 +410,10 @@ static inline int crypto_memneq(const void *a, const void *b, size_t size)
 	return __crypto_memneq(a, b, size) != 0UL ? 1 : 0;
 }
 
+static inline void crypto_yield(u32 flags)
+{
+	if (flags & CRYPTO_TFM_REQ_MAY_SLEEP)
+		cond_resched();
+}
+
 #endif	/* _CRYPTO_ALGAPI_H */
diff --git a/include/crypto/des.h b/include/crypto/des.h
index 2971c6304ad..fc6274c6bb2 100644
--- a/include/crypto/des.h
+++ b/include/crypto/des.h
@@ -16,4 +16,7 @@
 
 extern unsigned long des_ekey(u32 *pe, const u8 *k);
 
+extern int __des3_ede_setkey(u32 *expkey, u32 *flags, const u8 *key,
+			     unsigned int keylen);
+
 #endif /* __CRYPTO_DES_H */
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
new file mode 100644
index 00000000000..831d786976c
--- /dev/null
+++ b/include/crypto/drbg.h
@@ -0,0 +1,290 @@
+/*
+ * DRBG based on NIST SP800-90A
+ *
+ * Copyright Stephan Mueller <smueller@chronox.de>, 2014
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, and the entire permission notice in its entirety,
+ *    including the disclaimer of warranties.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. The name of the author may not be used to endorse or promote
+ *    products derived from this software without specific prior
+ *    written permission.
+ *
+ * ALTERNATIVELY, this product may be distributed under the terms of
+ * the GNU General Public License, in which case the provisions of the GPL are
+ * required INSTEAD OF the above restrictions.  (This clause is
+ * necessary due to a potential bad interaction between the GPL and
+ * the restrictions contained in a BSD-style copyright.)
+ *
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF
+ * WHICH ARE HEREBY DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
+ * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OF THIS SOFTWARE, EVEN IF NOT ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ */
+
+#ifndef _DRBG_H
+#define _DRBG_H
+
+
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <crypto/hash.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/slab.h>
+#include <crypto/internal/rng.h>
+#include <crypto/rng.h>
+#include <linux/fips.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+
+/*
+ * Concatenation Helper and string operation helper
+ *
+ * SP800-90A requires the concatenation of different data. To avoid copying
+ * buffers around or allocate additional memory, the following data structure
+ * is used to point to the original memory with its size. In addition, it
+ * is used to build a linked list. The linked list defines the concatenation
+ * of individual buffers. The order of memory block referenced in that
+ * linked list determines the order of concatenation.
+ */
+struct drbg_string {
+	const unsigned char *buf;
+	size_t len;
+	struct list_head list;
+};
+
+static inline void drbg_string_fill(struct drbg_string *string,
+				    const unsigned char *buf, size_t len)
+{
+	string->buf = buf;
+	string->len = len;
+	INIT_LIST_HEAD(&string->list);
+}
+
+struct drbg_state;
+typedef uint32_t drbg_flag_t;
+
+struct drbg_core {
+	drbg_flag_t flags;	/* flags for the cipher */
+	__u8 statelen;		/* maximum state length */
+	/*
+	 * maximum length of personalization string or additional input
+	 * string -- exponent for base 2
+	 */
+	__u8 max_addtllen;
+	/* maximum bits per RNG request -- exponent for base 2*/
+	__u8 max_bits;
+	/* maximum number of requests -- exponent for base 2 */
+	__u8 max_req;
+	__u8 blocklen_bytes;	/* block size of output in bytes */
+	char cra_name[CRYPTO_MAX_ALG_NAME]; /* mapping to kernel crypto API */
+	 /* kernel crypto API backend cipher name */
+	char backend_cra_name[CRYPTO_MAX_ALG_NAME];
+};
+
+struct drbg_state_ops {
+	int (*update)(struct drbg_state *drbg, struct list_head *seed,
+		      int reseed);
+	int (*generate)(struct drbg_state *drbg,
+			unsigned char *buf, unsigned int buflen,
+			struct list_head *addtl);
+	int (*crypto_init)(struct drbg_state *drbg);
+	int (*crypto_fini)(struct drbg_state *drbg);
+
+};
+
+struct drbg_test_data {
+	struct drbg_string *testentropy; /* TEST PARAMETER: test entropy */
+};
+
+struct drbg_state {
+	spinlock_t drbg_lock;	/* lock around DRBG */
+	unsigned char *V;	/* internal state 10.1.1.1 1a) */
+	/* hash: static value 10.1.1.1 1b) hmac / ctr: key */
+	unsigned char *C;
+	/* Number of RNG requests since last reseed -- 10.1.1.1 1c) */
+	size_t reseed_ctr;
+	 /* some memory the DRBG can use for its operation */
+	unsigned char *scratchpad;
+	void *priv_data;	/* Cipher handle */
+	bool seeded;		/* DRBG fully seeded? */
+	bool pr;		/* Prediction resistance enabled? */
+#ifdef CONFIG_CRYPTO_FIPS
+	bool fips_primed;	/* Continuous test primed? */
+	unsigned char *prev;	/* FIPS 140-2 continuous test value */
+#endif
+	const struct drbg_state_ops *d_ops;
+	const struct drbg_core *core;
+	struct drbg_test_data *test_data;
+};
+
+static inline __u8 drbg_statelen(struct drbg_state *drbg)
+{
+	if (drbg && drbg->core)
+		return drbg->core->statelen;
+	return 0;
+}
+
+static inline __u8 drbg_blocklen(struct drbg_state *drbg)
+{
+	if (drbg && drbg->core)
+		return drbg->core->blocklen_bytes;
+	return 0;
+}
+
+static inline __u8 drbg_keylen(struct drbg_state *drbg)
+{
+	if (drbg && drbg->core)
+		return (drbg->core->statelen - drbg->core->blocklen_bytes);
+	return 0;
+}
+
+static inline size_t drbg_max_request_bytes(struct drbg_state *drbg)
+{
+	/* max_bits is in bits, but buflen is in bytes */
+	return (1 << (drbg->core->max_bits - 3));
+}
+
+static inline size_t drbg_max_addtl(struct drbg_state *drbg)
+{
+	return (1UL<<(drbg->core->max_addtllen));
+}
+
+static inline size_t drbg_max_requests(struct drbg_state *drbg)
+{
+	return (1UL<<(drbg->core->max_req));
+}
+
+/*
+ * kernel crypto API input data structure for DRBG generate in case dlen
+ * is set to 0
+ */
+struct drbg_gen {
+	unsigned char *outbuf;	/* output buffer for random numbers */
+	unsigned int outlen;	/* size of output buffer */
+	struct drbg_string *addtl;	/* additional information string */
+	struct drbg_test_data *test_data;	/* test data */
+};
+
+/*
+ * This is a wrapper to the kernel crypto API function of
+ * crypto_rng_get_bytes() to allow the caller to provide additional data.
+ *
+ * @drng DRBG handle -- see crypto_rng_get_bytes
+ * @outbuf output buffer -- see crypto_rng_get_bytes
+ * @outlen length of output buffer -- see crypto_rng_get_bytes
+ * @addtl_input additional information string input buffer
+ * @addtllen length of additional information string buffer
+ *
+ * return
+ *	see crypto_rng_get_bytes
+ */
+static inline int crypto_drbg_get_bytes_addtl(struct crypto_rng *drng,
+			unsigned char *outbuf, unsigned int outlen,
+			struct drbg_string *addtl)
+{
+	int ret;
+	struct drbg_gen genbuf;
+	genbuf.outbuf = outbuf;
+	genbuf.outlen = outlen;
+	genbuf.addtl = addtl;
+	genbuf.test_data = NULL;
+	ret = crypto_rng_get_bytes(drng, (u8 *)&genbuf, 0);
+	return ret;
+}
+
+/*
+ * TEST code
+ *
+ * This is a wrapper to the kernel crypto API function of
+ * crypto_rng_get_bytes() to allow the caller to provide additional data and
+ * allow furnishing of test_data
+ *
+ * @drng DRBG handle -- see crypto_rng_get_bytes
+ * @outbuf output buffer -- see crypto_rng_get_bytes
+ * @outlen length of output buffer -- see crypto_rng_get_bytes
+ * @addtl_input additional information string input buffer
+ * @addtllen length of additional information string buffer
+ * @test_data filled test data
+ *
+ * return
+ *	see crypto_rng_get_bytes
+ */
+static inline int crypto_drbg_get_bytes_addtl_test(struct crypto_rng *drng,
+			unsigned char *outbuf, unsigned int outlen,
+			struct drbg_string *addtl,
+			struct drbg_test_data *test_data)
+{
+	int ret;
+	struct drbg_gen genbuf;
+	genbuf.outbuf = outbuf;
+	genbuf.outlen = outlen;
+	genbuf.addtl = addtl;
+	genbuf.test_data = test_data;
+	ret = crypto_rng_get_bytes(drng, (u8 *)&genbuf, 0);
+	return ret;
+}
+
+/*
+ * TEST code
+ *
+ * This is a wrapper to the kernel crypto API function of
+ * crypto_rng_reset() to allow the caller to provide test_data
+ *
+ * @drng DRBG handle -- see crypto_rng_reset
+ * @pers personalization string input buffer
+ * @perslen length of additional information string buffer
+ * @test_data filled test data
+ *
+ * return
+ *	see crypto_rng_reset
+ */
+static inline int crypto_drbg_reset_test(struct crypto_rng *drng,
+					 struct drbg_string *pers,
+					 struct drbg_test_data *test_data)
+{
+	int ret;
+	struct drbg_gen genbuf;
+	genbuf.outbuf = NULL;
+	genbuf.outlen = 0;
+	genbuf.addtl = pers;
+	genbuf.test_data = test_data;
+	ret = crypto_rng_reset(drng, (u8 *)&genbuf, 0);
+	return ret;
+}
+
+/* DRBG type flags */
+#define DRBG_CTR	((drbg_flag_t)1<<0)
+#define DRBG_HMAC	((drbg_flag_t)1<<1)
+#define DRBG_HASH	((drbg_flag_t)1<<2)
+#define DRBG_TYPE_MASK	(DRBG_CTR | DRBG_HMAC | DRBG_HASH)
+/* DRBG strength flags */
+#define DRBG_STRENGTH128	((drbg_flag_t)1<<3)
+#define DRBG_STRENGTH192	((drbg_flag_t)1<<4)
+#define DRBG_STRENGTH256	((drbg_flag_t)1<<5)
+#define DRBG_STRENGTH_MASK	(DRBG_STRENGTH128 | DRBG_STRENGTH192 | \
+				 DRBG_STRENGTH256)
+
+enum drbg_prefixes {
+	DRBG_PREFIX0 = 0x00,
+	DRBG_PREFIX1,
+	DRBG_PREFIX2,
+	DRBG_PREFIX3
+};
+
+#endif /* _DRBG_H */
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 26cb1eb16f4..a3919553960 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -238,10 +238,10 @@ static inline struct ahash_request *ahash_request_cast(
 
 static inline void ahash_request_set_callback(struct ahash_request *req,
 					      u32 flags,
-					      crypto_completion_t complete,
+					      crypto_completion_t compl,
 					      void *data)
 {
-	req->base.complete = complete;
+	req->base.complete = compl;
 	req->base.data = data;
 	req->base.flags = flags;
 }
diff --git a/include/crypto/internal/skcipher.h b/include/crypto/internal/skcipher.h
index 06e8b32d541..b3a46c515d1 100644
--- a/include/crypto/internal/skcipher.h
+++ b/include/crypto/internal/skcipher.h
@@ -81,8 +81,7 @@ static inline int skcipher_enqueue_givcrypt(
 static inline struct skcipher_givcrypt_request *skcipher_dequeue_givcrypt(
 	struct crypto_queue *queue)
 {
-	return __crypto_dequeue_request(
-		queue, offsetof(struct skcipher_givcrypt_request, creq.base));
+	return skcipher_givcrypt_cast(crypto_dequeue_request(queue));
 }
 
 static inline void *skcipher_givcrypt_reqctx(
diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h
index 6a626a507b8..7ef512f8631 100644
--- a/include/crypto/scatterwalk.h
+++ b/include/crypto/scatterwalk.h
@@ -25,12 +25,6 @@
 #include <linux/scatterlist.h>
 #include <linux/sched.h>
 
-static inline void crypto_yield(u32 flags)
-{
-	if (flags & CRYPTO_TFM_REQ_MAY_SLEEP)
-		cond_resched();
-}
-
 static inline void scatterwalk_sg_chain(struct scatterlist *sg1, int num,
 					struct scatterlist *sg2)
 {
diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h
index 25fd6126522..07d245f073d 100644
--- a/include/crypto/skcipher.h
+++ b/include/crypto/skcipher.h
@@ -86,9 +86,9 @@ static inline void skcipher_givcrypt_free(struct skcipher_givcrypt_request *req)
 
 static inline void skcipher_givcrypt_set_callback(
 	struct skcipher_givcrypt_request *req, u32 flags,
-	crypto_completion_t complete, void *data)
+	crypto_completion_t compl, void *data)
 {
-	ablkcipher_request_set_callback(&req->creq, flags, complete, data);
+	ablkcipher_request_set_callback(&req->creq, flags, compl, data);
 }
 
 static inline void skcipher_givcrypt_set_crypt(
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index a7c2a862b4f..8af71a8e2c0 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -143,11 +143,6 @@ int drm_err(const char *func, const char *format, ...);
 #define DRIVER_PRIME       0x4000
 #define DRIVER_RENDER      0x8000
 
-#define DRIVER_BUS_PCI 0x1
-#define DRIVER_BUS_PLATFORM 0x2
-#define DRIVER_BUS_USB 0x3
-#define DRIVER_BUS_HOST1X 0x4
-
 /***********************************************************************/
 /** \name Begin the DRM... */
 /*@{*/
@@ -239,8 +234,6 @@ int drm_err(const char *func, const char *format, ...);
 /** \name Internal types and structures */
 /*@{*/
 
-#define DRM_ARRAY_SIZE(x) ARRAY_SIZE(x)
-
 #define DRM_IF_VERSION(maj, min) (maj << 16 | min)
 
 /**
@@ -731,13 +724,7 @@ struct drm_master {
 #define DRM_SCANOUTPOS_ACCURATE     (1 << 2)
 
 struct drm_bus {
-	int bus_type;
-	int (*get_irq)(struct drm_device *dev);
-	const char *(*get_name)(struct drm_device *dev);
 	int (*set_busid)(struct drm_device *dev, struct drm_master *master);
-	int (*set_unique)(struct drm_device *dev, struct drm_master *master,
-			  struct drm_unique *unique);
-	int (*irq_by_busid)(struct drm_device *dev, struct drm_irq_busid *p);
 };
 
 /**
@@ -974,11 +961,6 @@ struct drm_driver {
 	const struct drm_ioctl_desc *ioctls;
 	int num_ioctls;
 	const struct file_operations *fops;
-	union {
-		struct pci_driver *pci;
-		struct platform_device *platform_device;
-		struct usb_driver *usb;
-	} kdriver;
 	struct drm_bus *bus;
 
 	/* List of devices hanging off this driver with stealth attach. */
@@ -1040,14 +1022,17 @@ struct drm_pending_vblank_event {
 };
 
 struct drm_vblank_crtc {
+	struct drm_device *dev;		/* pointer to the drm_device */
 	wait_queue_head_t queue;	/**< VBLANK wait queue */
 	struct timeval time[DRM_VBLANKTIME_RBSIZE];	/**< timestamp of current count */
+	struct timer_list disable_timer;		/* delayed disable timer */
 	atomic_t count;			/**< number of VBLANK interrupts */
 	atomic_t refcount;		/* number of users of vblank interruptsper crtc */
 	u32 last;			/* protected by dev->vbl_lock, used */
 					/* for wraparound handling */
 	u32 last_wait;			/* Last vblank seqno waited per CRTC */
 	unsigned int inmodeset;		/* Display driver is setting mode */
+	int crtc;			/* crtc index */
 	bool enabled;			/* so we don't call enable more than
 					   once per disable */
 };
@@ -1058,7 +1043,6 @@ struct drm_vblank_crtc {
  */
 struct drm_device {
 	struct list_head legacy_dev_list;/**< list of devices per driver for stealth attach cleanup */
-	char *devname;			/**< For /proc/interrupts */
 	int if_version;			/**< Highest interface version set */
 
 	/** \name Lifetime Management */
@@ -1072,18 +1056,19 @@ struct drm_device {
 	struct drm_minor *render;		/**< Render node */
 	atomic_t unplugged;			/**< Flag whether dev is dead */
 	struct inode *anon_inode;		/**< inode for private address-space */
+	char *unique;				/**< unique name of the device */
 	/*@} */
 
 	/** \name Locks */
 	/*@{ */
-	spinlock_t count_lock;		/**< For inuse, drm_device::open_count, drm_device::buf_use */
 	struct mutex struct_mutex;	/**< For others */
 	struct mutex master_mutex;      /**< For drm_minor::master and drm_file::is_master */
 	/*@} */
 
 	/** \name Usage Counters */
 	/*@{ */
-	int open_count;			/**< Outstanding files open */
+	int open_count;			/**< Outstanding files open, protected by drm_global_mutex. */
+	spinlock_t buf_lock;		/**< For drm_device::buf_use and a few other things. */
 	int buf_use;			/**< Buffers in use -- cannot alloc */
 	atomic_t buf_alloc;		/**< Buffer allocation in progress */
 	/*@} */
@@ -1114,6 +1099,8 @@ struct drm_device {
 	/** \name Context support */
 	/*@{ */
 	bool irq_enabled;		/**< True if irq handler is enabled */
+	int irq;
+
 	__volatile__ long context_flag;	/**< Context swapping flag */
 	int last_context;		/**< Last current context */
 	/*@} */
@@ -1134,7 +1121,6 @@ struct drm_device {
 
 	spinlock_t vblank_time_lock;    /**< Protects vblank count and time updates during vblank enable/disable */
 	spinlock_t vbl_lock;
-	struct timer_list vblank_disable_timer;
 
 	u32 max_vblank_count;           /**< size of vblank counter register */
 
@@ -1186,11 +1172,6 @@ static __inline__ int drm_core_check_feature(struct drm_device *dev,
 	return ((dev->driver->driver_features & feature) ? 1 : 0);
 }
 
-static inline int drm_dev_to_irq(struct drm_device *dev)
-{
-	return dev->driver->bus->get_irq(dev);
-}
-
 static inline void drm_device_set_unplugged(struct drm_device *dev)
 {
 	smp_wmb();
@@ -1204,11 +1185,6 @@ static inline int drm_device_is_unplugged(struct drm_device *dev)
 	return ret;
 }
 
-static inline bool drm_modeset_is_locked(struct drm_device *dev)
-{
-	return mutex_is_locked(&dev->mode_config.mutex);
-}
-
 static inline bool drm_is_render_client(const struct drm_file *file_priv)
 {
 	return file_priv->minor->type == DRM_MINOR_RENDER;
@@ -1310,7 +1286,7 @@ extern int drm_remove_magic(struct drm_master *master, drm_magic_t magic);
 /* Cache management (drm_cache.c) */
 void drm_clflush_pages(struct page *pages[], unsigned long num_pages);
 void drm_clflush_sg(struct sg_table *st);
-void drm_clflush_virt_range(char *addr, unsigned long length);
+void drm_clflush_virt_range(void *addr, unsigned long length);
 
 				/* Locking IOCTL support (drm_lock.h) */
 extern int drm_lock(struct drm_device *dev, void *data,
@@ -1363,7 +1339,7 @@ extern void drm_core_reclaim_buffers(struct drm_device *dev,
 				/* IRQ support (drm_irq.h) */
 extern int drm_control(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
-extern int drm_irq_install(struct drm_device *dev);
+extern int drm_irq_install(struct drm_device *dev, int irq);
 extern int drm_irq_uninstall(struct drm_device *dev);
 
 extern int drm_vblank_init(struct drm_device *dev, int num_crtcs);
@@ -1377,8 +1353,14 @@ extern void drm_send_vblank_event(struct drm_device *dev, int crtc,
 extern bool drm_handle_vblank(struct drm_device *dev, int crtc);
 extern int drm_vblank_get(struct drm_device *dev, int crtc);
 extern void drm_vblank_put(struct drm_device *dev, int crtc);
+extern int drm_crtc_vblank_get(struct drm_crtc *crtc);
+extern void drm_crtc_vblank_put(struct drm_crtc *crtc);
 extern void drm_vblank_off(struct drm_device *dev, int crtc);
+extern void drm_vblank_on(struct drm_device *dev, int crtc);
+extern void drm_crtc_vblank_off(struct drm_crtc *crtc);
+extern void drm_crtc_vblank_on(struct drm_crtc *crtc);
 extern void drm_vblank_cleanup(struct drm_device *dev);
+
 extern u32 drm_get_last_vbltimestamp(struct drm_device *dev, int crtc,
 				     struct timeval *tvblank, unsigned flags);
 extern int drm_calc_vbltimestamp_from_scanoutpos(struct drm_device *dev,
@@ -1522,6 +1504,9 @@ extern drm_dma_handle_t *drm_pci_alloc(struct drm_device *dev, size_t size,
 				       size_t align);
 extern void __drm_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
 extern void drm_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
+extern int drm_pci_set_unique(struct drm_device *dev,
+			      struct drm_master *master,
+			      struct drm_unique *u);
 
 			       /* sysfs support (drm_sysfs.c) */
 struct drm_sysfs_class;
@@ -1631,6 +1616,7 @@ void drm_dev_ref(struct drm_device *dev);
 void drm_dev_unref(struct drm_device *dev);
 int drm_dev_register(struct drm_device *dev, unsigned long flags);
 void drm_dev_unregister(struct drm_device *dev);
+int drm_dev_set_unique(struct drm_device *dev, const char *fmt, ...);
 
 struct drm_minor *drm_minor_acquire(unsigned int minor_id);
 void drm_minor_release(struct drm_minor *minor);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index e55fccbe7c4..251b75e6bf7 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -33,6 +33,7 @@
 #include <linux/hdmi.h>
 #include <drm/drm_mode.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_modeset_lock.h>
 
 struct drm_device;
 struct drm_mode_set;
@@ -50,6 +51,7 @@ struct drm_clip_rect;
 #define DRM_MODE_OBJECT_BLOB 0xbbbbbbbb
 #define DRM_MODE_OBJECT_PLANE 0xeeeeeeee
 #define DRM_MODE_OBJECT_BRIDGE 0xbdbdbdbd
+#define DRM_MODE_OBJECT_ANY 0
 
 struct drm_mode_object {
 	uint32_t id;
@@ -64,6 +66,15 @@ struct drm_object_properties {
 	uint64_t values[DRM_OBJECT_MAX_PROPERTY];
 };
 
+static inline int64_t U642I64(uint64_t val)
+{
+	return (int64_t)*((int64_t *)&val);
+}
+static inline uint64_t I642U64(int64_t val)
+{
+	return (uint64_t)*((uint64_t *)&val);
+}
+
 enum drm_connector_force {
 	DRM_FORCE_UNSPECIFIED,
 	DRM_FORCE_OFF,
@@ -110,6 +121,9 @@ struct drm_display_info {
 	enum subpixel_order subpixel_order;
 	u32 color_formats;
 
+	/* Mask of supported hdmi deep color modes */
+	u8 edid_hdmi_dc_modes;
+
 	u8 cea_rev;
 };
 
@@ -190,10 +204,15 @@ struct drm_property {
 	char name[DRM_PROP_NAME_LEN];
 	uint32_t num_values;
 	uint64_t *values;
+	struct drm_device *dev;
 
 	struct list_head enum_blob_list;
 };
 
+void drm_modeset_lock_all(struct drm_device *dev);
+void drm_modeset_unlock_all(struct drm_device *dev);
+void drm_warn_on_modeset_not_all_locked(struct drm_device *dev);
+
 struct drm_crtc;
 struct drm_connector;
 struct drm_encoder;
@@ -269,6 +288,7 @@ struct drm_crtc_funcs {
  * drm_crtc - central CRTC control structure
  * @dev: parent DRM device
  * @head: list management
+ * @mutex: per-CRTC locking
  * @base: base KMS object for ID tracking etc.
  * @primary: primary plane for this CRTC
  * @cursor: cursor plane for this CRTC
@@ -303,7 +323,7 @@ struct drm_crtc {
 	 * state, ...) and a write lock for everything which can be update
 	 * without a full modeset (fb, cursor data, ...)
 	 */
-	struct mutex mutex;
+	struct drm_modeset_lock mutex;
 
 	struct drm_mode_object base;
 
@@ -400,6 +420,7 @@ struct drm_encoder_funcs {
  * @dev: parent DRM device
  * @head: list management
  * @base: base KMS object
+ * @name: encoder name
  * @encoder_type: one of the %DRM_MODE_ENCODER_<foo> types in drm_mode.h
  * @possible_crtcs: bitmask of potential CRTC bindings
  * @possible_clones: bitmask of potential sibling encoders for cloning
@@ -416,6 +437,7 @@ struct drm_encoder {
 	struct list_head head;
 
 	struct drm_mode_object base;
+	char *name;
 	int encoder_type;
 	uint32_t possible_crtcs;
 	uint32_t possible_clones;
@@ -444,6 +466,7 @@ struct drm_encoder {
  * @attr: sysfs attributes
  * @head: list management
  * @base: base KMS object
+ * @name: connector name
  * @connector_type: one of the %DRM_MODE_CONNECTOR_<foo> types from drm_mode.h
  * @connector_type_id: index into connector type enum
  * @interlace_allowed: can this connector handle interlaced modes?
@@ -482,6 +505,7 @@ struct drm_connector {
 
 	struct drm_mode_object base;
 
+	char *name;
 	int connector_type;
 	int connector_type_id;
 	bool interlace_allowed;
@@ -723,6 +747,8 @@ struct drm_mode_group {
  */
 struct drm_mode_config {
 	struct mutex mutex; /* protects configuration (mode lists etc.) */
+	struct drm_modeset_lock connection_mutex; /* protects connector->encoder and encoder->crtc links */
+	struct drm_modeset_acquire_ctx *acquire_ctx; /* for legacy _lock_all() / _unlock_all() */
 	struct mutex idr_mutex; /* for IDR management */
 	struct idr crtc_idr; /* use this idr for all IDs, fb, crtc, connector, modes - just makes life easier */
 	/* this is limited to one for now */
@@ -823,10 +849,6 @@ struct drm_prop_enum_list {
 	char *name;
 };
 
-extern void drm_modeset_lock_all(struct drm_device *dev);
-extern void drm_modeset_unlock_all(struct drm_device *dev);
-extern void drm_warn_on_modeset_not_all_locked(struct drm_device *dev);
-
 extern int drm_crtc_init_with_planes(struct drm_device *dev,
 				     struct drm_crtc *crtc,
 				     struct drm_plane *primary,
@@ -905,7 +927,6 @@ extern int drm_crtc_check_viewport(const struct drm_crtc *crtc,
 
 extern void drm_encoder_cleanup(struct drm_encoder *encoder);
 
-extern const char *drm_get_connector_name(const struct drm_connector *connector);
 extern const char *drm_get_connector_status_name(enum drm_connector_status status);
 extern const char *drm_get_subpixel_order_name(enum subpixel_order order);
 extern const char *drm_get_dpms_name(int val);
@@ -915,6 +936,7 @@ extern const char *drm_get_tv_subconnector_name(int val);
 extern const char *drm_get_tv_select_name(int val);
 extern void drm_fb_release(struct drm_file *file_priv);
 extern int drm_mode_group_init_legacy_group(struct drm_device *dev, struct drm_mode_group *group);
+extern void drm_mode_group_destroy(struct drm_mode_group *group);
 extern bool drm_probe_ddc(struct i2c_adapter *adapter);
 extern struct edid *drm_get_edid(struct drm_connector *connector,
 				 struct i2c_adapter *adapter);
@@ -926,6 +948,23 @@ extern void drm_mode_config_cleanup(struct drm_device *dev);
 
 extern int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 						struct edid *edid);
+
+static inline bool drm_property_type_is(struct drm_property *property,
+		uint32_t type)
+{
+	/* instanceof for props.. handles extended type vs original types: */
+	if (property->flags & DRM_MODE_PROP_EXTENDED_TYPE)
+		return (property->flags & DRM_MODE_PROP_EXTENDED_TYPE) == type;
+	return property->flags & type;
+}
+
+static inline bool drm_property_type_valid(struct drm_property *property)
+{
+	if (property->flags & DRM_MODE_PROP_EXTENDED_TYPE)
+		return !(property->flags & DRM_MODE_PROP_LEGACY_TYPE);
+	return !!(property->flags & DRM_MODE_PROP_LEGACY_TYPE);
+}
+
 extern int drm_object_property_set_value(struct drm_mode_object *obj,
 					 struct drm_property *property,
 					 uint64_t val);
@@ -959,6 +998,11 @@ struct drm_property *drm_property_create_bitmask(struct drm_device *dev,
 struct drm_property *drm_property_create_range(struct drm_device *dev, int flags,
 					 const char *name,
 					 uint64_t min, uint64_t max);
+struct drm_property *drm_property_create_signed_range(struct drm_device *dev,
+					 int flags, const char *name,
+					 int64_t min, int64_t max);
+struct drm_property *drm_property_create_object(struct drm_device *dev,
+					 int flags, const char *name, uint32_t type);
 extern void drm_property_destroy(struct drm_device *dev, struct drm_property *property);
 extern int drm_property_add_enum(struct drm_property *property, int index,
 				 uint64_t value, const char *name);
@@ -967,7 +1011,6 @@ extern int drm_mode_create_tv_properties(struct drm_device *dev, int num_formats
 				     char *formats[]);
 extern int drm_mode_create_scaling_mode_property(struct drm_device *dev);
 extern int drm_mode_create_dirty_info_property(struct drm_device *dev);
-extern const char *drm_get_encoder_name(const struct drm_encoder *encoder);
 
 extern int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 					     struct drm_encoder *encoder);
@@ -975,6 +1018,7 @@ extern int drm_mode_crtc_set_gamma_size(struct drm_crtc *crtc,
 					 int gamma_size);
 extern struct drm_mode_object *drm_mode_object_find(struct drm_device *dev,
 		uint32_t id, uint32_t type);
+
 /* IOCTLs */
 extern int drm_mode_getresources(struct drm_device *dev,
 				 void *data, struct drm_file *file_priv);
@@ -1020,6 +1064,7 @@ extern int drm_mode_gamma_get_ioctl(struct drm_device *dev,
 extern int drm_mode_gamma_set_ioctl(struct drm_device *dev,
 				    void *data, struct drm_file *file_priv);
 extern u8 drm_match_cea_mode(const struct drm_display_mode *to_match);
+extern enum hdmi_picture_aspect drm_get_cea_aspect_ratio(const u8 video_code);
 extern bool drm_detect_hdmi_monitor(struct edid *edid);
 extern bool drm_detect_monitor_audio(struct edid *edid);
 extern bool drm_rgb_quant_range_selectable(struct edid *edid);
@@ -1057,6 +1102,15 @@ extern int drm_format_vert_chroma_subsampling(uint32_t format);
 extern const char *drm_get_format_name(uint32_t format);
 
 /* Helpers */
+
+static inline struct drm_plane *drm_plane_find(struct drm_device *dev,
+		uint32_t id)
+{
+	struct drm_mode_object *mo;
+	mo = drm_mode_object_find(dev, id, DRM_MODE_OBJECT_PLANE);
+	return mo ? obj_to_plane(mo) : NULL;
+}
+
 static inline struct drm_crtc *drm_crtc_find(struct drm_device *dev,
 	uint32_t id)
 {
@@ -1073,6 +1127,30 @@ static inline struct drm_encoder *drm_encoder_find(struct drm_device *dev,
 	return mo ? obj_to_encoder(mo) : NULL;
 }
 
+static inline struct drm_connector *drm_connector_find(struct drm_device *dev,
+		uint32_t id)
+{
+	struct drm_mode_object *mo;
+	mo = drm_mode_object_find(dev, id, DRM_MODE_OBJECT_CONNECTOR);
+	return mo ? obj_to_connector(mo) : NULL;
+}
+
+static inline struct drm_property *drm_property_find(struct drm_device *dev,
+		uint32_t id)
+{
+	struct drm_mode_object *mo;
+	mo = drm_mode_object_find(dev, id, DRM_MODE_OBJECT_PROPERTY);
+	return mo ? obj_to_property(mo) : NULL;
+}
+
+static inline struct drm_property_blob *
+drm_property_blob_find(struct drm_device *dev, uint32_t id)
+{
+	struct drm_mode_object *mo;
+	mo = drm_mode_object_find(dev, id, DRM_MODE_OBJECT_BLOB);
+	return mo ? obj_to_blob(mo) : NULL;
+}
+
 /* Plane list iterator for legacy (overlay only) planes. */
 #define drm_for_each_legacy_plane(plane, planelist) \
 	list_for_each_entry(plane, planelist, head) \
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index 36a5febac2a..a3d75fefd01 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -114,7 +114,7 @@ struct drm_encoder_helper_funcs {
 /**
  * drm_connector_helper_funcs - helper operations for connectors
  * @get_modes: get mode list for this connector
- * @mode_valid: is this mode valid on the given connector?
+ * @mode_valid (optional): is this mode valid on the given connector?
  *
  * The helper operations are called by the mid-layer CRTC helper.
  */
@@ -165,6 +165,10 @@ extern void drm_helper_resume_force_mode(struct drm_device *dev);
 extern int drm_helper_probe_single_connector_modes(struct drm_connector
 						   *connector, uint32_t maxX,
 						   uint32_t maxY);
+extern int drm_helper_probe_single_connector_modes_nomerge(struct drm_connector
+							   *connector,
+							   uint32_t maxX,
+							   uint32_t maxY);
 extern void drm_kms_helper_poll_init(struct drm_device *dev);
 extern void drm_kms_helper_poll_fini(struct drm_device *dev);
 extern bool drm_helper_hpd_irq_event(struct drm_device *dev);
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index cfcacec5b89..a21568bf151 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -37,6 +37,7 @@
  * eDP: Embedded DisplayPort version 1
  * DPI: DisplayPort Interoperability Guideline v1.1a
  * 1.2: DisplayPort 1.2
+ * MST: Multistream Transport - part of DP 1.2a
  *
  * 1.2 formally includes both eDP and DPI definitions.
  */
@@ -103,9 +104,14 @@
 #define DP_TRAINING_AUX_RD_INTERVAL         0x00e   /* XXX 1.2? */
 
 /* Multiple stream transport */
+#define DP_FAUX_CAP			    0x020   /* 1.2 */
+# define DP_FAUX_CAP_1			    (1 << 0)
+
 #define DP_MSTM_CAP			    0x021   /* 1.2 */
 # define DP_MST_CAP			    (1 << 0)
 
+#define DP_GUID				    0x030   /* 1.2 */
+
 #define DP_PSR_SUPPORT                      0x070   /* XXX 1.2? */
 # define DP_PSR_IS_SUPPORTED                1
 #define DP_PSR_CAPS                         0x071   /* XXX 1.2? */
@@ -221,6 +227,16 @@
 # define DP_PSR_CRC_VERIFICATION	    (1 << 2)
 # define DP_PSR_FRAME_CAPTURE		    (1 << 3)
 
+#define DP_ADAPTER_CTRL			    0x1a0
+# define DP_ADAPTER_CTRL_FORCE_LOAD_SENSE   (1 << 0)
+
+#define DP_BRANCH_DEVICE_CTRL		    0x1a1
+# define DP_BRANCH_DEVICE_IRQ_HPD	    (1 << 0)
+
+#define DP_PAYLOAD_ALLOCATE_SET		    0x1c0
+#define DP_PAYLOAD_ALLOCATE_START_TIME_SLOT 0x1c1
+#define DP_PAYLOAD_ALLOCATE_TIME_SLOT_COUNT 0x1c2
+
 #define DP_SINK_COUNT			    0x200
 /* prior to 1.2 bit 7 was reserved mbz */
 # define DP_GET_SINK_COUNT(x)		    ((((x) & 0x80) >> 1) | ((x) & 0x3f))
@@ -230,6 +246,9 @@
 # define DP_REMOTE_CONTROL_COMMAND_PENDING  (1 << 0)
 # define DP_AUTOMATED_TEST_REQUEST	    (1 << 1)
 # define DP_CP_IRQ			    (1 << 2)
+# define DP_MCCS_IRQ			    (1 << 3)
+# define DP_DOWN_REP_MSG_RDY		    (1 << 4) /* 1.2 MST */
+# define DP_UP_REQ_MSG_RDY		    (1 << 5) /* 1.2 MST */
 # define DP_SINK_SPECIFIC_IRQ		    (1 << 6)
 
 #define DP_LANE0_1_STATUS		    0x202
@@ -291,9 +310,18 @@
 # define DP_TEST_NAK			    (1 << 1)
 # define DP_TEST_EDID_CHECKSUM_WRITE	    (1 << 2)
 
+#define DP_TEST_EDID_CHECKSUM		    0x261
+
 #define DP_TEST_SINK			    0x270
 #define DP_TEST_SINK_START	    (1 << 0)
 
+#define DP_PAYLOAD_TABLE_UPDATE_STATUS      0x2c0   /* 1.2 MST */
+# define DP_PAYLOAD_TABLE_UPDATED           (1 << 0)
+# define DP_PAYLOAD_ACT_HANDLED             (1 << 1)
+
+#define DP_VC_PAYLOAD_ID_SLOT_1             0x2c1   /* 1.2 MST */
+/* up to ID_SLOT_63 at 0x2ff */
+
 #define DP_SOURCE_OUI			    0x300
 #define DP_SINK_OUI			    0x400
 #define DP_BRANCH_OUI			    0x500
@@ -303,6 +331,21 @@
 # define DP_SET_POWER_D3                    0x2
 # define DP_SET_POWER_MASK                  0x3
 
+#define DP_SIDEBAND_MSG_DOWN_REQ_BASE	    0x1000   /* 1.2 MST */
+#define DP_SIDEBAND_MSG_UP_REP_BASE	    0x1200   /* 1.2 MST */
+#define DP_SIDEBAND_MSG_DOWN_REP_BASE	    0x1400   /* 1.2 MST */
+#define DP_SIDEBAND_MSG_UP_REQ_BASE	    0x1600   /* 1.2 MST */
+
+#define DP_SINK_COUNT_ESI		    0x2002   /* 1.2 */
+/* 0-5 sink count */
+# define DP_SINK_COUNT_CP_READY             (1 << 6)
+
+#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0   0x2003   /* 1.2 */
+
+#define DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1   0x2004   /* 1.2 */
+
+#define DP_LINK_SERVICE_IRQ_VECTOR_ESI0     0x2005   /* 1.2 */
+
 #define DP_PSR_ERROR_STATUS                 0x2006  /* XXX 1.2? */
 # define DP_PSR_LINK_CRC_ERROR              (1 << 0)
 # define DP_PSR_RFB_STORAGE_ERROR           (1 << 1)
@@ -319,6 +362,43 @@
 # define DP_PSR_SINK_INTERNAL_ERROR         7
 # define DP_PSR_SINK_STATE_MASK             0x07
 
+/* DP 1.2 Sideband message defines */
+/* peer device type - DP 1.2a Table 2-92 */
+#define DP_PEER_DEVICE_NONE		0x0
+#define DP_PEER_DEVICE_SOURCE_OR_SST	0x1
+#define DP_PEER_DEVICE_MST_BRANCHING	0x2
+#define DP_PEER_DEVICE_SST_SINK		0x3
+#define DP_PEER_DEVICE_DP_LEGACY_CONV	0x4
+
+/* DP 1.2 MST sideband request names DP 1.2a Table 2-80 */
+#define DP_LINK_ADDRESS			0x01
+#define DP_CONNECTION_STATUS_NOTIFY	0x02
+#define DP_ENUM_PATH_RESOURCES		0x10
+#define DP_ALLOCATE_PAYLOAD		0x11
+#define DP_QUERY_PAYLOAD		0x12
+#define DP_RESOURCE_STATUS_NOTIFY	0x13
+#define DP_CLEAR_PAYLOAD_ID_TABLE	0x14
+#define DP_REMOTE_DPCD_READ		0x20
+#define DP_REMOTE_DPCD_WRITE		0x21
+#define DP_REMOTE_I2C_READ		0x22
+#define DP_REMOTE_I2C_WRITE		0x23
+#define DP_POWER_UP_PHY			0x24
+#define DP_POWER_DOWN_PHY		0x25
+#define DP_SINK_EVENT_NOTIFY		0x30
+#define DP_QUERY_STREAM_ENC_STATUS	0x38
+
+/* DP 1.2 MST sideband nak reasons - table 2.84 */
+#define DP_NAK_WRITE_FAILURE		0x01
+#define DP_NAK_INVALID_READ		0x02
+#define DP_NAK_CRC_FAILURE		0x03
+#define DP_NAK_BAD_PARAM		0x04
+#define DP_NAK_DEFER			0x05
+#define DP_NAK_LINK_FAILURE		0x06
+#define DP_NAK_NO_RESOURCES		0x07
+#define DP_NAK_DPCD_FAIL		0x08
+#define DP_NAK_I2C_NAK			0x09
+#define DP_NAK_ALLOCATE_FAIL		0x0a
+
 #define MODE_I2C_START	1
 #define MODE_I2C_WRITE	2
 #define MODE_I2C_READ	4
@@ -431,8 +511,10 @@ struct drm_dp_aux_msg {
 
 /**
  * struct drm_dp_aux - DisplayPort AUX channel
+ * @name: user-visible name of this AUX channel and the I2C-over-AUX adapter
  * @ddc: I2C adapter that can be used for I2C-over-AUX communication
  * @dev: pointer to struct device that is the parent for this AUX channel
+ * @hw_mutex: internal mutex used for locking transfers
  * @transfer: transfers a message representing a single AUX transaction
  *
  * The .dev field should be set to a pointer to the device that implements
@@ -465,7 +547,7 @@ struct drm_dp_aux {
 	const char *name;
 	struct i2c_adapter ddc;
 	struct device *dev;
-
+	struct mutex hw_mutex;
 	ssize_t (*transfer)(struct drm_dp_aux *aux,
 			    struct drm_dp_aux_msg *msg);
 };
@@ -524,7 +606,7 @@ int drm_dp_link_probe(struct drm_dp_aux *aux, struct drm_dp_link *link);
 int drm_dp_link_power_up(struct drm_dp_aux *aux, struct drm_dp_link *link);
 int drm_dp_link_configure(struct drm_dp_aux *aux, struct drm_dp_link *link);
 
-int drm_dp_aux_register_i2c_bus(struct drm_dp_aux *aux);
-void drm_dp_aux_unregister_i2c_bus(struct drm_dp_aux *aux);
+int drm_dp_aux_register(struct drm_dp_aux *aux);
+void drm_dp_aux_unregister(struct drm_dp_aux *aux);
 
 #endif /* _DRM_DP_HELPER_H_ */
diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index a1441c5ac63..b96031d947a 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -202,6 +202,11 @@ struct detailed_timing {
 #define DRM_EDID_FEATURE_PM_SUSPEND       (1 << 6)
 #define DRM_EDID_FEATURE_PM_STANDBY       (1 << 7)
 
+#define DRM_EDID_HDMI_DC_48               (1 << 6)
+#define DRM_EDID_HDMI_DC_36               (1 << 5)
+#define DRM_EDID_HDMI_DC_30               (1 << 4)
+#define DRM_EDID_HDMI_DC_Y444             (1 << 3)
+
 struct edid {
 	u8 header[8];
 	/* Vendor & product info */
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index 6e622f7d481..7997246d403 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -108,7 +108,7 @@ int drm_fb_helper_set_par(struct fb_info *info);
 int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 			    struct fb_info *info);
 
-bool drm_fb_helper_restore_fbdev_mode(struct drm_fb_helper *fb_helper);
+bool drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper);
 void drm_fb_helper_fill_var(struct fb_info *info, struct drm_fb_helper *fb_helper,
 			    uint32_t fb_width, uint32_t fb_height);
 void drm_fb_helper_fill_fix(struct fb_info *info, uint32_t pitch,
diff --git a/include/drm/drm_flip_work.h b/include/drm/drm_flip_work.h
index 35c776ae7d3..9eed34dcd6a 100644
--- a/include/drm/drm_flip_work.h
+++ b/include/drm/drm_flip_work.h
@@ -57,6 +57,7 @@ typedef void (*drm_flip_func_t)(struct drm_flip_work *work, void *val);
  * @count: number of committed items
  * @func: callback fxn called for each committed item
  * @worker: worker which calls @func
+ * @fifo: queue of committed items
  */
 struct drm_flip_work {
 	const char *name;
diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h
index 7209df15a3c..944f33f8ba3 100644
--- a/include/drm/drm_mipi_dsi.h
+++ b/include/drm/drm_mipi_dsi.h
@@ -135,11 +135,13 @@ ssize_t mipi_dsi_dcs_read(struct mipi_dsi_device *dsi, unsigned int channel,
  * @driver: device driver model driver
  * @probe: callback for device binding
  * @remove: callback for device unbinding
+ * @shutdown: called at shutdown time to quiesce the device
  */
 struct mipi_dsi_driver {
 	struct device_driver driver;
 	int(*probe)(struct mipi_dsi_device *dsi);
 	int(*remove)(struct mipi_dsi_device *dsi);
+	void (*shutdown)(struct mipi_dsi_device *dsi);
 };
 
 #define to_mipi_dsi_driver(d) container_of(d, struct mipi_dsi_driver, driver)
diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
index 2dbbf997666..91d0582f924 100644
--- a/include/drm/drm_modes.h
+++ b/include/drm/drm_modes.h
@@ -223,7 +223,7 @@ void drm_mode_validate_size(struct drm_device *dev,
 void drm_mode_prune_invalid(struct drm_device *dev,
 			    struct list_head *mode_list, bool verbose);
 void drm_mode_sort(struct list_head *mode_list);
-void drm_mode_connector_list_update(struct drm_connector *connector);
+void drm_mode_connector_list_update(struct drm_connector *connector, bool merge_type_bits);
 
 /* parsing cmdline modes */
 bool
diff --git a/include/drm/drm_modeset_lock.h b/include/drm/drm_modeset_lock.h
new file mode 100644
index 00000000000..402aa7a6a05
--- /dev/null
+++ b/include/drm/drm_modeset_lock.h
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2014 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef DRM_MODESET_LOCK_H_
+#define DRM_MODESET_LOCK_H_
+
+#include <linux/ww_mutex.h>
+
+struct drm_modeset_lock;
+
+/**
+ * drm_modeset_acquire_ctx - locking context (see ww_acquire_ctx)
+ * @ww_ctx: base acquire ctx
+ * @contended: used internally for -EDEADLK handling
+ * @locked: list of held locks
+ *
+ * Each thread competing for a set of locks must use one acquire
+ * ctx.  And if any lock fxn returns -EDEADLK, it must backoff and
+ * retry.
+ */
+struct drm_modeset_acquire_ctx {
+
+	struct ww_acquire_ctx ww_ctx;
+
+	/**
+	 * Contended lock: if a lock is contended you should only call
+	 * drm_modeset_backoff() which drops locks and slow-locks the
+	 * contended lock.
+	 */
+	struct drm_modeset_lock *contended;
+
+	/**
+	 * list of held locks (drm_modeset_lock)
+	 */
+	struct list_head locked;
+};
+
+/**
+ * drm_modeset_lock - used for locking modeset resources.
+ * @mutex: resource locking
+ * @head: used to hold it's place on state->locked list when
+ *    part of an atomic update
+ *
+ * Used for locking CRTCs and other modeset resources.
+ */
+struct drm_modeset_lock {
+	/**
+	 * modeset lock
+	 */
+	struct ww_mutex mutex;
+
+	/**
+	 * Resources that are locked as part of an atomic update are added
+	 * to a list (so we know what to unlock at the end).
+	 */
+	struct list_head head;
+};
+
+extern struct ww_class crtc_ww_class;
+
+void drm_modeset_acquire_init(struct drm_modeset_acquire_ctx *ctx,
+		uint32_t flags);
+void drm_modeset_acquire_fini(struct drm_modeset_acquire_ctx *ctx);
+void drm_modeset_drop_locks(struct drm_modeset_acquire_ctx *ctx);
+void drm_modeset_backoff(struct drm_modeset_acquire_ctx *ctx);
+int drm_modeset_backoff_interruptible(struct drm_modeset_acquire_ctx *ctx);
+
+/**
+ * drm_modeset_lock_init - initialize lock
+ * @lock: lock to init
+ */
+static inline void drm_modeset_lock_init(struct drm_modeset_lock *lock)
+{
+	ww_mutex_init(&lock->mutex, &crtc_ww_class);
+	INIT_LIST_HEAD(&lock->head);
+}
+
+/**
+ * drm_modeset_lock_fini - cleanup lock
+ * @lock: lock to cleanup
+ */
+static inline void drm_modeset_lock_fini(struct drm_modeset_lock *lock)
+{
+	WARN_ON(!list_empty(&lock->head));
+}
+
+/**
+ * drm_modeset_is_locked - equivalent to mutex_is_locked()
+ * @lock: lock to check
+ */
+static inline bool drm_modeset_is_locked(struct drm_modeset_lock *lock)
+{
+	return ww_mutex_is_locked(&lock->mutex);
+}
+
+int drm_modeset_lock(struct drm_modeset_lock *lock,
+		struct drm_modeset_acquire_ctx *ctx);
+int drm_modeset_lock_interruptible(struct drm_modeset_lock *lock,
+		struct drm_modeset_acquire_ctx *ctx);
+void drm_modeset_unlock(struct drm_modeset_lock *lock);
+
+struct drm_device;
+int drm_modeset_lock_all_crtcs(struct drm_device *dev,
+		struct drm_modeset_acquire_ctx *ctx);
+
+#endif /* DRM_MODESET_LOCK_H_ */
diff --git a/include/drm/drm_plane_helper.h b/include/drm/drm_plane_helper.h
index 09824becee3..52e6870534b 100644
--- a/include/drm/drm_plane_helper.h
+++ b/include/drm/drm_plane_helper.h
@@ -24,6 +24,17 @@
 #ifndef DRM_PLANE_HELPER_H
 #define DRM_PLANE_HELPER_H
 
+#include <drm/drm_rect.h>
+
+/*
+ * Drivers that don't allow primary plane scaling may pass this macro in place
+ * of the min/max scale parameters of the update checker function.
+ *
+ * Due to src being in 16.16 fixed point and dest being in integer pixels,
+ * 1<<16 represents no scaling.
+ */
+#define DRM_PLANE_HELPER_NO_SCALING (1<<16)
+
 /**
  * DOC: plane helpers
  *
@@ -31,6 +42,17 @@
  * planes.
  */
 
+extern int drm_plane_helper_check_update(struct drm_plane *plane,
+					 struct drm_crtc *crtc,
+					 struct drm_framebuffer *fb,
+					 struct drm_rect *src,
+					 struct drm_rect *dest,
+					 const struct drm_rect *clip,
+					 int min_scale,
+					 int max_scale,
+					 bool can_position,
+					 bool can_update_disabled,
+					 bool *visible);
 extern int drm_primary_helper_update(struct drm_plane *plane,
 				     struct drm_crtc *crtc,
 				     struct drm_framebuffer *fb,
@@ -42,7 +64,7 @@ extern int drm_primary_helper_disable(struct drm_plane *plane);
 extern void drm_primary_helper_destroy(struct drm_plane *plane);
 extern const struct drm_plane_funcs drm_primary_helper_funcs;
 extern struct drm_plane *drm_primary_helper_create_plane(struct drm_device *dev,
-							 uint32_t *formats,
+							 const uint32_t *formats,
 							 int num_formats);
 
 
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 012d58fa8ff..a70d4564789 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -223,14 +223,40 @@
 	_INTEL_BDW_D(gt, 0x160A, info), /* Server */ \
 	_INTEL_BDW_D(gt, 0x160D, info) /* Workstation */
 
-#define INTEL_BDW_M_IDS(info) \
+#define INTEL_BDW_GT12M_IDS(info) \
 	_INTEL_BDW_M_IDS(1, info), \
-	_INTEL_BDW_M_IDS(2, info), \
-	_INTEL_BDW_M_IDS(3, info)
+	_INTEL_BDW_M_IDS(2, info)
 
-#define INTEL_BDW_D_IDS(info) \
+#define INTEL_BDW_GT12D_IDS(info) \
 	_INTEL_BDW_D_IDS(1, info), \
-	_INTEL_BDW_D_IDS(2, info), \
+	_INTEL_BDW_D_IDS(2, info)
+
+#define INTEL_BDW_GT3M_IDS(info) \
+	_INTEL_BDW_M_IDS(3, info)
+
+#define INTEL_BDW_GT3D_IDS(info) \
 	_INTEL_BDW_D_IDS(3, info)
 
+#define INTEL_BDW_RSVDM_IDS(info) \
+	_INTEL_BDW_M_IDS(4, info)
+
+#define INTEL_BDW_RSVDD_IDS(info) \
+	_INTEL_BDW_D_IDS(4, info)
+
+#define INTEL_BDW_M_IDS(info) \
+	INTEL_BDW_GT12M_IDS(info), \
+	INTEL_BDW_GT3M_IDS(info), \
+	INTEL_BDW_RSVDM_IDS(info)
+
+#define INTEL_BDW_D_IDS(info) \
+	INTEL_BDW_GT12D_IDS(info), \
+	INTEL_BDW_GT3D_IDS(info), \
+	INTEL_BDW_RSVDD_IDS(info)
+
+#define INTEL_CHV_IDS(info) \
+	INTEL_VGA_DEVICE(0x22b0, info), \
+	INTEL_VGA_DEVICE(0x22b1, info), \
+	INTEL_VGA_DEVICE(0x22b2, info), \
+	INTEL_VGA_DEVICE(0x22b3, info)
+
 #endif /* _I915_PCIIDS_H */
diff --git a/include/drm/i915_powerwell.h b/include/drm/i915_powerwell.h
index cfdc884405b..baa6f11b183 100644
--- a/include/drm/i915_powerwell.h
+++ b/include/drm/i915_powerwell.h
@@ -30,7 +30,8 @@
 #define _I915_POWERWELL_H_
 
 /* For use by hda_i915 driver */
-extern void i915_request_power_well(void);
-extern void i915_release_power_well(void);
+extern int i915_request_power_well(void);
+extern int i915_release_power_well(void);
+extern int i915_get_cdclk_freq(void);
 
 #endif				/* _I915_POWERWELL_H_ */
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index ee127ec33c6..7526c5bf561 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -485,13 +485,12 @@ extern int ttm_bo_init(struct ttm_bo_device *bdev,
 			void (*destroy) (struct ttm_buffer_object *));
 
 /**
- * ttm_bo_synccpu_object_init
+ * ttm_bo_create
  *
  * @bdev: Pointer to a ttm_bo_device struct.
- * @bo: Pointer to a ttm_buffer_object to be initialized.
  * @size: Requested size of buffer object.
  * @type: Requested type of buffer object.
- * @flags: Initial placement flags.
+ * @placement: Initial placement.
  * @page_alignment: Data alignment in pages.
  * @interruptible: If needing to sleep while waiting for GPU resources,
  * sleep interruptible.
diff --git a/include/dt-bindings/clk/ti-dra7-atl.h b/include/dt-bindings/clk/ti-dra7-atl.h
new file mode 100644
index 00000000000..42dd4164f6f
--- /dev/null
+++ b/include/dt-bindings/clk/ti-dra7-atl.h
@@ -0,0 +1,40 @@
+/*
+ * This header provides constants for DRA7 ATL (Audio Tracking Logic)
+ *
+ * The constants defined in this header are used in dts files
+ *
+ * Copyright (C) 2013 Texas Instruments, Inc.
+ *
+ * Peter Ujfalusi <peter.ujfalusi@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_CLK_DRA7_ATL_H
+#define _DT_BINDINGS_CLK_DRA7_ATL_H
+
+#define DRA7_ATL_WS_MCASP1_FSR		0
+#define DRA7_ATL_WS_MCASP1_FSX		1
+#define DRA7_ATL_WS_MCASP2_FSR		2
+#define DRA7_ATL_WS_MCASP2_FSX		3
+#define DRA7_ATL_WS_MCASP3_FSX		4
+#define DRA7_ATL_WS_MCASP4_FSX		5
+#define DRA7_ATL_WS_MCASP5_FSX		6
+#define DRA7_ATL_WS_MCASP6_FSX		7
+#define DRA7_ATL_WS_MCASP7_FSX		8
+#define DRA7_ATL_WS_MCASP8_FSX		9
+#define DRA7_ATL_WS_MCASP8_AHCLKX	10
+#define DRA7_ATL_WS_XREF_CLK3		11
+#define DRA7_ATL_WS_XREF_CLK0		12
+#define DRA7_ATL_WS_XREF_CLK1		13
+#define DRA7_ATL_WS_XREF_CLK2		14
+#define DRA7_ATL_WS_OSC1_X1		15
+
+#endif
diff --git a/include/dt-bindings/clock/clps711x-clock.h b/include/dt-bindings/clock/clps711x-clock.h
new file mode 100644
index 00000000000..0c4c80b6324
--- /dev/null
+++ b/include/dt-bindings/clock/clps711x-clock.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2014 Alexander Shiyan <shc_work@mail.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_CLPS711X_H
+#define __DT_BINDINGS_CLOCK_CLPS711X_H
+
+#define CLPS711X_CLK_DUMMY	0
+#define CLPS711X_CLK_CPU	1
+#define CLPS711X_CLK_BUS	2
+#define CLPS711X_CLK_PLL	3
+#define CLPS711X_CLK_TIMERREF	4
+#define CLPS711X_CLK_TIMER1	5
+#define CLPS711X_CLK_TIMER2	6
+#define CLPS711X_CLK_PWM	7
+#define CLPS711X_CLK_SPIREF	8
+#define CLPS711X_CLK_SPI	9
+#define CLPS711X_CLK_UART	10
+#define CLPS711X_CLK_TICK	11
+#define CLPS711X_CLK_MAX	12
+
+#endif
diff --git a/include/dt-bindings/clock/exynos4.h b/include/dt-bindings/clock/exynos4.h
index 1106ca540a9..459bd2bd411 100644
--- a/include/dt-bindings/clock/exynos4.h
+++ b/include/dt-bindings/clock/exynos4.h
@@ -1,6 +1,6 @@
 /*
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
- * Author: Andrzej Haja <a.hajda@samsung.com>
+ * Author: Andrzej Hajda <a.hajda@samsung.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -34,6 +34,11 @@
 #define CLK_MOUT_CORE		19
 #define CLK_MOUT_APLL		20
 #define CLK_SCLK_HDMIPHY	22
+#define CLK_OUT_DMC		23
+#define CLK_OUT_TOP		24
+#define CLK_OUT_LEFTBUS		25
+#define CLK_OUT_RIGHTBUS	26
+#define CLK_OUT_CPU		27
 
 /* gate for special clocks (sclk) */
 #define CLK_SCLK_FIMC0		128
@@ -230,6 +235,24 @@
 #define CLK_MOUT_G3D		394
 #define CLK_ACLK400_MCUISP	395 /* Exynos4x12 only */
 
+/* gate clocks - ppmu */
+#define CLK_PPMULEFT		400
+#define CLK_PPMURIGHT		401
+#define CLK_PPMUCAMIF		402
+#define CLK_PPMUTV		403
+#define CLK_PPMUMFC_L		404
+#define CLK_PPMUMFC_R		405
+#define CLK_PPMUG3D		406
+#define CLK_PPMUIMAGE		407
+#define CLK_PPMULCD0		408
+#define CLK_PPMULCD1		409 /* Exynos4210 only */
+#define CLK_PPMUFILE		410
+#define CLK_PPMUGPS		411
+#define CLK_PPMUDMC0		412
+#define CLK_PPMUDMC1		413
+#define CLK_PPMUCPU		414
+#define CLK_PPMUACP		415
+
 /* div clocks */
 #define CLK_DIV_ISP0		450 /* Exynos4x12 only */
 #define CLK_DIV_ISP1		451 /* Exynos4x12 only */
diff --git a/include/dt-bindings/clock/exynos5250.h b/include/dt-bindings/clock/exynos5250.h
index be6e97c54f5..4273891dc78 100644
--- a/include/dt-bindings/clock/exynos5250.h
+++ b/include/dt-bindings/clock/exynos5250.h
@@ -1,6 +1,6 @@
 /*
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
- * Author: Andrzej Haja <a.hajda@samsung.com>
+ * Author: Andrzej Hajda <a.hajda@samsung.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/include/dt-bindings/clock/exynos5420.h b/include/dt-bindings/clock/exynos5420.h
index 97dcb89d37d..8dc0913f177 100644
--- a/include/dt-bindings/clock/exynos5420.h
+++ b/include/dt-bindings/clock/exynos5420.h
@@ -1,6 +1,6 @@
 /*
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
- * Author: Andrzej Haja <a.hajda@samsung.com>
+ * Author: Andrzej Hajda <a.hajda@samsung.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -63,7 +63,6 @@
 #define CLK_SCLK_MPHY_IXTAL24	161
 
 /* gate clocks */
-#define CLK_ACLK66_PERIC	256
 #define CLK_UART0		257
 #define CLK_UART1		258
 #define CLK_UART2		259
@@ -203,6 +202,8 @@
 #define CLK_MOUT_G3D		641
 #define CLK_MOUT_VPLL		642
 #define CLK_MOUT_MAUDIO0	643
+#define CLK_MOUT_USER_ACLK333	644
+#define CLK_MOUT_SW_ACLK333	645
 
 /* divider clocks */
 #define CLK_DOUT_PIXEL		768
diff --git a/include/dt-bindings/clock/exynos5440.h b/include/dt-bindings/clock/exynos5440.h
index 70cd85077fa..c66fc405a79 100644
--- a/include/dt-bindings/clock/exynos5440.h
+++ b/include/dt-bindings/clock/exynos5440.h
@@ -1,6 +1,6 @@
 /*
  * Copyright (c) 2013 Samsung Electronics Co., Ltd.
- * Author: Andrzej Haja <a.hajda-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>
+ * Author: Andrzej Hajda <a.hajda@samsung.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/include/dt-bindings/clock/imx6sl-clock.h b/include/dt-bindings/clock/imx6sl-clock.h
index 7cf5c996933..b91dd462ba8 100644
--- a/include/dt-bindings/clock/imx6sl-clock.h
+++ b/include/dt-bindings/clock/imx6sl-clock.h
@@ -145,6 +145,7 @@
 #define IMX6SL_CLK_USDHC4		132
 #define IMX6SL_CLK_PLL4_AUDIO_DIV	133
 #define IMX6SL_CLK_SPBA			134
-#define IMX6SL_CLK_END			135
+#define IMX6SL_CLK_ENET			135
+#define IMX6SL_CLK_END			136
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6SL_H */
diff --git a/include/dt-bindings/clock/qcom,gcc-apq8084.h b/include/dt-bindings/clock/qcom,gcc-apq8084.h
new file mode 100644
index 00000000000..2c0da566c46
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,gcc-apq8084.h
@@ -0,0 +1,351 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_CLK_APQ_GCC_8084_H
+#define _DT_BINDINGS_CLK_APQ_GCC_8084_H
+
+#define GPLL0						0
+#define GPLL0_VOTE					1
+#define GPLL1						2
+#define GPLL1_VOTE					3
+#define GPLL2						4
+#define GPLL2_VOTE					5
+#define GPLL3						6
+#define GPLL3_VOTE					7
+#define GPLL4						8
+#define GPLL4_VOTE					9
+#define CONFIG_NOC_CLK_SRC				10
+#define PERIPH_NOC_CLK_SRC				11
+#define SYSTEM_NOC_CLK_SRC				12
+#define BLSP_UART_SIM_CLK_SRC				13
+#define QDSS_TSCTR_CLK_SRC				14
+#define UFS_AXI_CLK_SRC					15
+#define RPM_CLK_SRC					16
+#define KPSS_AHB_CLK_SRC				17
+#define QDSS_AT_CLK_SRC					18
+#define BIMC_DDR_CLK_SRC				19
+#define USB30_MASTER_CLK_SRC				20
+#define USB30_SEC_MASTER_CLK_SRC			21
+#define USB_HSIC_AHB_CLK_SRC				22
+#define MMSS_BIMC_GFX_CLK_SRC				23
+#define QDSS_STM_CLK_SRC				24
+#define ACC_CLK_SRC					25
+#define SEC_CTRL_CLK_SRC				26
+#define BLSP1_QUP1_I2C_APPS_CLK_SRC			27
+#define BLSP1_QUP1_SPI_APPS_CLK_SRC			28
+#define BLSP1_QUP2_I2C_APPS_CLK_SRC			29
+#define BLSP1_QUP2_SPI_APPS_CLK_SRC			30
+#define BLSP1_QUP3_I2C_APPS_CLK_SRC			31
+#define BLSP1_QUP3_SPI_APPS_CLK_SRC			32
+#define BLSP1_QUP4_I2C_APPS_CLK_SRC			33
+#define BLSP1_QUP4_SPI_APPS_CLK_SRC			34
+#define BLSP1_QUP5_I2C_APPS_CLK_SRC			35
+#define BLSP1_QUP5_SPI_APPS_CLK_SRC			36
+#define BLSP1_QUP6_I2C_APPS_CLK_SRC			37
+#define BLSP1_QUP6_SPI_APPS_CLK_SRC			38
+#define BLSP1_UART1_APPS_CLK_SRC			39
+#define BLSP1_UART2_APPS_CLK_SRC			40
+#define BLSP1_UART3_APPS_CLK_SRC			41
+#define BLSP1_UART4_APPS_CLK_SRC			42
+#define BLSP1_UART5_APPS_CLK_SRC			43
+#define BLSP1_UART6_APPS_CLK_SRC			44
+#define BLSP2_QUP1_I2C_APPS_CLK_SRC			45
+#define BLSP2_QUP1_SPI_APPS_CLK_SRC			46
+#define BLSP2_QUP2_I2C_APPS_CLK_SRC			47
+#define BLSP2_QUP2_SPI_APPS_CLK_SRC			48
+#define BLSP2_QUP3_I2C_APPS_CLK_SRC			49
+#define BLSP2_QUP3_SPI_APPS_CLK_SRC			50
+#define BLSP2_QUP4_I2C_APPS_CLK_SRC			51
+#define BLSP2_QUP4_SPI_APPS_CLK_SRC			52
+#define BLSP2_QUP5_I2C_APPS_CLK_SRC			53
+#define BLSP2_QUP5_SPI_APPS_CLK_SRC			54
+#define BLSP2_QUP6_I2C_APPS_CLK_SRC			55
+#define BLSP2_QUP6_SPI_APPS_CLK_SRC			56
+#define BLSP2_UART1_APPS_CLK_SRC			57
+#define BLSP2_UART2_APPS_CLK_SRC			58
+#define BLSP2_UART3_APPS_CLK_SRC			59
+#define BLSP2_UART4_APPS_CLK_SRC			60
+#define BLSP2_UART5_APPS_CLK_SRC			61
+#define BLSP2_UART6_APPS_CLK_SRC			62
+#define CE1_CLK_SRC					63
+#define CE2_CLK_SRC					64
+#define CE3_CLK_SRC					65
+#define GP1_CLK_SRC					66
+#define GP2_CLK_SRC					67
+#define GP3_CLK_SRC					68
+#define PDM2_CLK_SRC					69
+#define QDSS_TRACECLKIN_CLK_SRC				70
+#define RBCPR_CLK_SRC					71
+#define SATA_ASIC0_CLK_SRC				72
+#define SATA_PMALIVE_CLK_SRC				73
+#define SATA_RX_CLK_SRC					74
+#define SATA_RX_OOB_CLK_SRC				75
+#define SDCC1_APPS_CLK_SRC				76
+#define SDCC2_APPS_CLK_SRC				77
+#define SDCC3_APPS_CLK_SRC				78
+#define SDCC4_APPS_CLK_SRC				79
+#define GCC_SNOC_BUS_TIMEOUT0_AHB_CLK			80
+#define SPMI_AHB_CLK_SRC				81
+#define SPMI_SER_CLK_SRC				82
+#define TSIF_REF_CLK_SRC				83
+#define USB30_MOCK_UTMI_CLK_SRC				84
+#define USB30_SEC_MOCK_UTMI_CLK_SRC			85
+#define USB_HS_SYSTEM_CLK_SRC				86
+#define USB_HSIC_CLK_SRC				87
+#define USB_HSIC_IO_CAL_CLK_SRC				88
+#define USB_HSIC_MOCK_UTMI_CLK_SRC			89
+#define USB_HSIC_SYSTEM_CLK_SRC				90
+#define GCC_BAM_DMA_AHB_CLK				91
+#define GCC_BAM_DMA_INACTIVITY_TIMERS_CLK		92
+#define DDR_CLK_SRC					93
+#define GCC_BIMC_CFG_AHB_CLK				94
+#define GCC_BIMC_CLK					95
+#define GCC_BIMC_KPSS_AXI_CLK				96
+#define GCC_BIMC_SLEEP_CLK				97
+#define GCC_BIMC_SYSNOC_AXI_CLK				98
+#define GCC_BIMC_XO_CLK					99
+#define GCC_BLSP1_AHB_CLK				100
+#define GCC_BLSP1_SLEEP_CLK				101
+#define GCC_BLSP1_QUP1_I2C_APPS_CLK			102
+#define GCC_BLSP1_QUP1_SPI_APPS_CLK			103
+#define GCC_BLSP1_QUP2_I2C_APPS_CLK			104
+#define GCC_BLSP1_QUP2_SPI_APPS_CLK			105
+#define GCC_BLSP1_QUP3_I2C_APPS_CLK			106
+#define GCC_BLSP1_QUP3_SPI_APPS_CLK			107
+#define GCC_BLSP1_QUP4_I2C_APPS_CLK			108
+#define GCC_BLSP1_QUP4_SPI_APPS_CLK			109
+#define GCC_BLSP1_QUP5_I2C_APPS_CLK			110
+#define GCC_BLSP1_QUP5_SPI_APPS_CLK			111
+#define GCC_BLSP1_QUP6_I2C_APPS_CLK			112
+#define GCC_BLSP1_QUP6_SPI_APPS_CLK			113
+#define GCC_BLSP1_UART1_APPS_CLK			114
+#define GCC_BLSP1_UART1_SIM_CLK				115
+#define GCC_BLSP1_UART2_APPS_CLK			116
+#define GCC_BLSP1_UART2_SIM_CLK				117
+#define GCC_BLSP1_UART3_APPS_CLK			118
+#define GCC_BLSP1_UART3_SIM_CLK				119
+#define GCC_BLSP1_UART4_APPS_CLK			120
+#define GCC_BLSP1_UART4_SIM_CLK				121
+#define GCC_BLSP1_UART5_APPS_CLK			122
+#define GCC_BLSP1_UART5_SIM_CLK				123
+#define GCC_BLSP1_UART6_APPS_CLK			124
+#define GCC_BLSP1_UART6_SIM_CLK				125
+#define GCC_BLSP2_AHB_CLK				126
+#define GCC_BLSP2_SLEEP_CLK				127
+#define GCC_BLSP2_QUP1_I2C_APPS_CLK			128
+#define GCC_BLSP2_QUP1_SPI_APPS_CLK			129
+#define GCC_BLSP2_QUP2_I2C_APPS_CLK			130
+#define GCC_BLSP2_QUP2_SPI_APPS_CLK			131
+#define GCC_BLSP2_QUP3_I2C_APPS_CLK			132
+#define GCC_BLSP2_QUP3_SPI_APPS_CLK			133
+#define GCC_BLSP2_QUP4_I2C_APPS_CLK			134
+#define GCC_BLSP2_QUP4_SPI_APPS_CLK			135
+#define GCC_BLSP2_QUP5_I2C_APPS_CLK			136
+#define GCC_BLSP2_QUP5_SPI_APPS_CLK			137
+#define GCC_BLSP2_QUP6_I2C_APPS_CLK			138
+#define GCC_BLSP2_QUP6_SPI_APPS_CLK			139
+#define GCC_BLSP2_UART1_APPS_CLK			140
+#define GCC_BLSP2_UART1_SIM_CLK				141
+#define GCC_BLSP2_UART2_APPS_CLK			142
+#define GCC_BLSP2_UART2_SIM_CLK				143
+#define GCC_BLSP2_UART3_APPS_CLK			144
+#define GCC_BLSP2_UART3_SIM_CLK				145
+#define GCC_BLSP2_UART4_APPS_CLK			146
+#define GCC_BLSP2_UART4_SIM_CLK				147
+#define GCC_BLSP2_UART5_APPS_CLK			148
+#define GCC_BLSP2_UART5_SIM_CLK				149
+#define GCC_BLSP2_UART6_APPS_CLK			150
+#define GCC_BLSP2_UART6_SIM_CLK				151
+#define GCC_BOOT_ROM_AHB_CLK				152
+#define GCC_CE1_AHB_CLK					153
+#define GCC_CE1_AXI_CLK					154
+#define GCC_CE1_CLK					155
+#define GCC_CE2_AHB_CLK					156
+#define GCC_CE2_AXI_CLK					157
+#define GCC_CE2_CLK					158
+#define GCC_CE3_AHB_CLK					159
+#define GCC_CE3_AXI_CLK					160
+#define GCC_CE3_CLK					161
+#define GCC_CNOC_BUS_TIMEOUT0_AHB_CLK			162
+#define GCC_CNOC_BUS_TIMEOUT1_AHB_CLK			163
+#define GCC_CNOC_BUS_TIMEOUT2_AHB_CLK			164
+#define GCC_CNOC_BUS_TIMEOUT3_AHB_CLK			165
+#define GCC_CNOC_BUS_TIMEOUT4_AHB_CLK			166
+#define GCC_CNOC_BUS_TIMEOUT5_AHB_CLK			167
+#define GCC_CNOC_BUS_TIMEOUT6_AHB_CLK			168
+#define GCC_CNOC_BUS_TIMEOUT7_AHB_CLK			169
+#define GCC_CFG_NOC_AHB_CLK				170
+#define GCC_CFG_NOC_DDR_CFG_CLK				171
+#define GCC_CFG_NOC_RPM_AHB_CLK				172
+#define GCC_COPSS_SMMU_AHB_CLK				173
+#define GCC_COPSS_SMMU_AXI_CLK				174
+#define GCC_DCD_XO_CLK					175
+#define GCC_BIMC_DDR_CH0_CLK				176
+#define GCC_BIMC_DDR_CH1_CLK				177
+#define GCC_BIMC_DDR_CPLL0_CLK				178
+#define GCC_BIMC_DDR_CPLL1_CLK				179
+#define GCC_BIMC_GFX_CLK				180
+#define GCC_DDR_DIM_CFG_CLK				181
+#define GCC_DDR_DIM_SLEEP_CLK				182
+#define GCC_DEHR_CLK					183
+#define GCC_AHB_CLK					184
+#define GCC_IM_SLEEP_CLK				185
+#define GCC_XO_CLK					186
+#define GCC_XO_DIV4_CLK					187
+#define GCC_GP1_CLK					188
+#define GCC_GP2_CLK					189
+#define GCC_GP3_CLK					190
+#define GCC_IMEM_AXI_CLK				191
+#define GCC_IMEM_CFG_AHB_CLK				192
+#define GCC_KPSS_AHB_CLK				193
+#define GCC_KPSS_AXI_CLK				194
+#define GCC_LPASS_MPORT_AXI_CLK				195
+#define GCC_LPASS_Q6_AXI_CLK				196
+#define GCC_LPASS_SWAY_CLK				197
+#define GCC_MMSS_BIMC_GFX_CLK				198
+#define GCC_MMSS_NOC_AT_CLK				199
+#define GCC_MMSS_NOC_CFG_AHB_CLK			200
+#define GCC_MMSS_VPU_MAPLE_SYS_NOC_AXI_CLK		201
+#define GCC_OCMEM_NOC_CFG_AHB_CLK			202
+#define GCC_OCMEM_SYS_NOC_AXI_CLK			203
+#define GCC_MPM_AHB_CLK					204
+#define GCC_MSG_RAM_AHB_CLK				205
+#define GCC_NOC_CONF_XPU_AHB_CLK			206
+#define GCC_PDM2_CLK					207
+#define GCC_PDM_AHB_CLK					208
+#define GCC_PDM_XO4_CLK					209
+#define GCC_PERIPH_NOC_AHB_CLK				210
+#define GCC_PERIPH_NOC_AT_CLK				211
+#define GCC_PERIPH_NOC_CFG_AHB_CLK			212
+#define GCC_PERIPH_NOC_USB_HSIC_AHB_CLK			213
+#define GCC_PERIPH_NOC_MPU_CFG_AHB_CLK			214
+#define GCC_PERIPH_XPU_AHB_CLK				215
+#define GCC_PNOC_BUS_TIMEOUT0_AHB_CLK			216
+#define GCC_PNOC_BUS_TIMEOUT1_AHB_CLK			217
+#define GCC_PNOC_BUS_TIMEOUT2_AHB_CLK			218
+#define GCC_PNOC_BUS_TIMEOUT3_AHB_CLK			219
+#define GCC_PNOC_BUS_TIMEOUT4_AHB_CLK			220
+#define GCC_PRNG_AHB_CLK				221
+#define GCC_QDSS_AT_CLK					222
+#define GCC_QDSS_CFG_AHB_CLK				223
+#define GCC_QDSS_DAP_AHB_CLK				224
+#define GCC_QDSS_DAP_CLK				225
+#define GCC_QDSS_ETR_USB_CLK				226
+#define GCC_QDSS_STM_CLK				227
+#define GCC_QDSS_TRACECLKIN_CLK				228
+#define GCC_QDSS_TSCTR_DIV16_CLK			229
+#define GCC_QDSS_TSCTR_DIV2_CLK				230
+#define GCC_QDSS_TSCTR_DIV3_CLK				231
+#define GCC_QDSS_TSCTR_DIV4_CLK				232
+#define GCC_QDSS_TSCTR_DIV8_CLK				233
+#define GCC_QDSS_RBCPR_XPU_AHB_CLK			234
+#define GCC_RBCPR_AHB_CLK				235
+#define GCC_RBCPR_CLK					236
+#define GCC_RPM_BUS_AHB_CLK				237
+#define GCC_RPM_PROC_HCLK				238
+#define GCC_RPM_SLEEP_CLK				239
+#define GCC_RPM_TIMER_CLK				240
+#define GCC_SATA_ASIC0_CLK				241
+#define GCC_SATA_AXI_CLK				242
+#define GCC_SATA_CFG_AHB_CLK				243
+#define GCC_SATA_PMALIVE_CLK				244
+#define GCC_SATA_RX_CLK					245
+#define GCC_SATA_RX_OOB_CLK				246
+#define GCC_SDCC1_AHB_CLK				247
+#define GCC_SDCC1_APPS_CLK				248
+#define GCC_SDCC1_CDCCAL_FF_CLK				249
+#define GCC_SDCC1_CDCCAL_SLEEP_CLK			250
+#define GCC_SDCC2_AHB_CLK				251
+#define GCC_SDCC2_APPS_CLK				252
+#define GCC_SDCC2_INACTIVITY_TIMERS_CLK			253
+#define GCC_SDCC3_AHB_CLK				254
+#define GCC_SDCC3_APPS_CLK				255
+#define GCC_SDCC3_INACTIVITY_TIMERS_CLK			256
+#define GCC_SDCC4_AHB_CLK				257
+#define GCC_SDCC4_APPS_CLK				258
+#define GCC_SDCC4_INACTIVITY_TIMERS_CLK			259
+#define GCC_SEC_CTRL_ACC_CLK				260
+#define GCC_SEC_CTRL_AHB_CLK				261
+#define GCC_SEC_CTRL_BOOT_ROM_PATCH_CLK			262
+#define GCC_SEC_CTRL_CLK				263
+#define GCC_SEC_CTRL_SENSE_CLK				264
+#define GCC_SNOC_BUS_TIMEOUT2_AHB_CLK			265
+#define GCC_SNOC_BUS_TIMEOUT3_AHB_CLK			266
+#define GCC_SPDM_BIMC_CY_CLK				267
+#define GCC_SPDM_CFG_AHB_CLK				268
+#define GCC_SPDM_DEBUG_CY_CLK				269
+#define GCC_SPDM_FF_CLK					270
+#define GCC_SPDM_MSTR_AHB_CLK				271
+#define GCC_SPDM_PNOC_CY_CLK				272
+#define GCC_SPDM_RPM_CY_CLK				273
+#define GCC_SPDM_SNOC_CY_CLK				274
+#define GCC_SPMI_AHB_CLK				275
+#define GCC_SPMI_CNOC_AHB_CLK				276
+#define GCC_SPMI_SER_CLK				277
+#define GCC_SPSS_AHB_CLK				278
+#define GCC_SNOC_CNOC_AHB_CLK				279
+#define GCC_SNOC_PNOC_AHB_CLK				280
+#define GCC_SYS_NOC_AT_CLK				281
+#define GCC_SYS_NOC_AXI_CLK				282
+#define GCC_SYS_NOC_KPSS_AHB_CLK			283
+#define GCC_SYS_NOC_QDSS_STM_AXI_CLK			284
+#define GCC_SYS_NOC_UFS_AXI_CLK				285
+#define GCC_SYS_NOC_USB3_AXI_CLK			286
+#define GCC_SYS_NOC_USB3_SEC_AXI_CLK			287
+#define GCC_TCSR_AHB_CLK				288
+#define GCC_TLMM_AHB_CLK				289
+#define GCC_TLMM_CLK					290
+#define GCC_TSIF_AHB_CLK				291
+#define GCC_TSIF_INACTIVITY_TIMERS_CLK			292
+#define GCC_TSIF_REF_CLK				293
+#define GCC_UFS_AHB_CLK					294
+#define GCC_UFS_AXI_CLK					295
+#define GCC_UFS_RX_CFG_CLK				296
+#define GCC_UFS_RX_SYMBOL_0_CLK				297
+#define GCC_UFS_RX_SYMBOL_1_CLK				298
+#define GCC_UFS_TX_CFG_CLK				299
+#define GCC_UFS_TX_SYMBOL_0_CLK				300
+#define GCC_UFS_TX_SYMBOL_1_CLK				301
+#define GCC_USB2A_PHY_SLEEP_CLK				302
+#define GCC_USB2B_PHY_SLEEP_CLK				303
+#define GCC_USB30_MASTER_CLK				304
+#define GCC_USB30_MOCK_UTMI_CLK				305
+#define GCC_USB30_SLEEP_CLK				306
+#define GCC_USB30_SEC_MASTER_CLK			307
+#define GCC_USB30_SEC_MOCK_UTMI_CLK			308
+#define GCC_USB30_SEC_SLEEP_CLK				309
+#define GCC_USB_HS_AHB_CLK				310
+#define GCC_USB_HS_INACTIVITY_TIMERS_CLK		311
+#define GCC_USB_HS_SYSTEM_CLK				312
+#define GCC_USB_HSIC_AHB_CLK				313
+#define GCC_USB_HSIC_CLK				314
+#define GCC_USB_HSIC_IO_CAL_CLK				315
+#define GCC_USB_HSIC_IO_CAL_SLEEP_CLK			316
+#define GCC_USB_HSIC_MOCK_UTMI_CLK			317
+#define GCC_USB_HSIC_SYSTEM_CLK				318
+#define PCIE_0_AUX_CLK_SRC				319
+#define PCIE_0_PIPE_CLK_SRC				320
+#define PCIE_1_AUX_CLK_SRC				321
+#define PCIE_1_PIPE_CLK_SRC				322
+#define GCC_PCIE_0_AUX_CLK				323
+#define GCC_PCIE_0_CFG_AHB_CLK				324
+#define GCC_PCIE_0_MSTR_AXI_CLK				325
+#define GCC_PCIE_0_PIPE_CLK				326
+#define GCC_PCIE_0_SLV_AXI_CLK				327
+#define GCC_PCIE_1_AUX_CLK				328
+#define GCC_PCIE_1_CFG_AHB_CLK				329
+#define GCC_PCIE_1_MSTR_AXI_CLK				330
+#define GCC_PCIE_1_PIPE_CLK				331
+#define GCC_PCIE_1_SLV_AXI_CLK				332
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,gcc-ipq806x.h b/include/dt-bindings/clock/qcom,gcc-ipq806x.h
new file mode 100644
index 00000000000..b857cadb0bd
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,gcc-ipq806x.h
@@ -0,0 +1,293 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_CLK_GCC_IPQ806X_H
+#define _DT_BINDINGS_CLK_GCC_IPQ806X_H
+
+#define AFAB_CLK_SRC				0
+#define QDSS_STM_CLK				1
+#define SCSS_A_CLK				2
+#define SCSS_H_CLK				3
+#define AFAB_CORE_CLK				4
+#define SCSS_XO_SRC_CLK				5
+#define AFAB_EBI1_CH0_A_CLK			6
+#define AFAB_EBI1_CH1_A_CLK			7
+#define AFAB_AXI_S0_FCLK			8
+#define AFAB_AXI_S1_FCLK			9
+#define AFAB_AXI_S2_FCLK			10
+#define AFAB_AXI_S3_FCLK			11
+#define AFAB_AXI_S4_FCLK			12
+#define SFAB_CORE_CLK				13
+#define SFAB_AXI_S0_FCLK			14
+#define SFAB_AXI_S1_FCLK			15
+#define SFAB_AXI_S2_FCLK			16
+#define SFAB_AXI_S3_FCLK			17
+#define SFAB_AXI_S4_FCLK			18
+#define SFAB_AXI_S5_FCLK			19
+#define SFAB_AHB_S0_FCLK			20
+#define SFAB_AHB_S1_FCLK			21
+#define SFAB_AHB_S2_FCLK			22
+#define SFAB_AHB_S3_FCLK			23
+#define SFAB_AHB_S4_FCLK			24
+#define SFAB_AHB_S5_FCLK			25
+#define SFAB_AHB_S6_FCLK			26
+#define SFAB_AHB_S7_FCLK			27
+#define QDSS_AT_CLK_SRC				28
+#define QDSS_AT_CLK				29
+#define QDSS_TRACECLKIN_CLK_SRC			30
+#define QDSS_TRACECLKIN_CLK			31
+#define QDSS_TSCTR_CLK_SRC			32
+#define QDSS_TSCTR_CLK				33
+#define SFAB_ADM0_M0_A_CLK			34
+#define SFAB_ADM0_M1_A_CLK			35
+#define SFAB_ADM0_M2_H_CLK			36
+#define ADM0_CLK				37
+#define ADM0_PBUS_CLK				38
+#define IMEM0_A_CLK				39
+#define QDSS_H_CLK				40
+#define PCIE_A_CLK				41
+#define PCIE_AUX_CLK				42
+#define PCIE_H_CLK				43
+#define PCIE_PHY_CLK				44
+#define SFAB_CLK_SRC				45
+#define SFAB_LPASS_Q6_A_CLK			46
+#define SFAB_AFAB_M_A_CLK			47
+#define AFAB_SFAB_M0_A_CLK			48
+#define AFAB_SFAB_M1_A_CLK			49
+#define SFAB_SATA_S_H_CLK			50
+#define DFAB_CLK_SRC				51
+#define DFAB_CLK				52
+#define SFAB_DFAB_M_A_CLK			53
+#define DFAB_SFAB_M_A_CLK			54
+#define DFAB_SWAY0_H_CLK			55
+#define DFAB_SWAY1_H_CLK			56
+#define DFAB_ARB0_H_CLK				57
+#define DFAB_ARB1_H_CLK				58
+#define PPSS_H_CLK				59
+#define PPSS_PROC_CLK				60
+#define PPSS_TIMER0_CLK				61
+#define PPSS_TIMER1_CLK				62
+#define PMEM_A_CLK				63
+#define DMA_BAM_H_CLK				64
+#define SIC_H_CLK				65
+#define SPS_TIC_H_CLK				66
+#define CFPB_2X_CLK_SRC				67
+#define CFPB_CLK				68
+#define CFPB0_H_CLK				69
+#define CFPB1_H_CLK				70
+#define CFPB2_H_CLK				71
+#define SFAB_CFPB_M_H_CLK			72
+#define CFPB_MASTER_H_CLK			73
+#define SFAB_CFPB_S_H_CLK			74
+#define CFPB_SPLITTER_H_CLK			75
+#define TSIF_H_CLK				76
+#define TSIF_INACTIVITY_TIMERS_CLK		77
+#define TSIF_REF_SRC				78
+#define TSIF_REF_CLK				79
+#define CE1_H_CLK				80
+#define CE1_CORE_CLK				81
+#define CE1_SLEEP_CLK				82
+#define CE2_H_CLK				83
+#define CE2_CORE_CLK				84
+#define SFPB_H_CLK_SRC				85
+#define SFPB_H_CLK				86
+#define SFAB_SFPB_M_H_CLK			87
+#define SFAB_SFPB_S_H_CLK			88
+#define RPM_PROC_CLK				89
+#define RPM_BUS_H_CLK				90
+#define RPM_SLEEP_CLK				91
+#define RPM_TIMER_CLK				92
+#define RPM_MSG_RAM_H_CLK			93
+#define PMIC_ARB0_H_CLK				94
+#define PMIC_ARB1_H_CLK				95
+#define PMIC_SSBI2_SRC				96
+#define PMIC_SSBI2_CLK				97
+#define SDC1_H_CLK				98
+#define SDC2_H_CLK				99
+#define SDC3_H_CLK				100
+#define SDC4_H_CLK				101
+#define SDC1_SRC				102
+#define SDC1_CLK				103
+#define SDC2_SRC				104
+#define SDC2_CLK				105
+#define SDC3_SRC				106
+#define SDC3_CLK				107
+#define SDC4_SRC				108
+#define SDC4_CLK				109
+#define USB_HS1_H_CLK				110
+#define USB_HS1_XCVR_SRC			111
+#define USB_HS1_XCVR_CLK			112
+#define USB_HSIC_H_CLK				113
+#define USB_HSIC_XCVR_SRC			114
+#define USB_HSIC_XCVR_CLK			115
+#define USB_HSIC_SYSTEM_CLK_SRC			116
+#define USB_HSIC_SYSTEM_CLK			117
+#define CFPB0_C0_H_CLK				118
+#define CFPB0_D0_H_CLK				119
+#define CFPB0_C1_H_CLK				120
+#define CFPB0_D1_H_CLK				121
+#define USB_FS1_H_CLK				122
+#define USB_FS1_XCVR_SRC			123
+#define USB_FS1_XCVR_CLK			124
+#define USB_FS1_SYSTEM_CLK			125
+#define GSBI_COMMON_SIM_SRC			126
+#define GSBI1_H_CLK				127
+#define GSBI2_H_CLK				128
+#define GSBI3_H_CLK				129
+#define GSBI4_H_CLK				130
+#define GSBI5_H_CLK				131
+#define GSBI6_H_CLK				132
+#define GSBI7_H_CLK				133
+#define GSBI1_QUP_SRC				134
+#define GSBI1_QUP_CLK				135
+#define GSBI2_QUP_SRC				136
+#define GSBI2_QUP_CLK				137
+#define GSBI3_QUP_SRC				138
+#define GSBI3_QUP_CLK				139
+#define GSBI4_QUP_SRC				140
+#define GSBI4_QUP_CLK				141
+#define GSBI5_QUP_SRC				142
+#define GSBI5_QUP_CLK				143
+#define GSBI6_QUP_SRC				144
+#define GSBI6_QUP_CLK				145
+#define GSBI7_QUP_SRC				146
+#define GSBI7_QUP_CLK				147
+#define GSBI1_UART_SRC				148
+#define GSBI1_UART_CLK				149
+#define GSBI2_UART_SRC				150
+#define GSBI2_UART_CLK				151
+#define GSBI3_UART_SRC				152
+#define GSBI3_UART_CLK				153
+#define GSBI4_UART_SRC				154
+#define GSBI4_UART_CLK				155
+#define GSBI5_UART_SRC				156
+#define GSBI5_UART_CLK				157
+#define GSBI6_UART_SRC				158
+#define GSBI6_UART_CLK				159
+#define GSBI7_UART_SRC				160
+#define GSBI7_UART_CLK				161
+#define GSBI1_SIM_CLK				162
+#define GSBI2_SIM_CLK				163
+#define GSBI3_SIM_CLK				164
+#define GSBI4_SIM_CLK				165
+#define GSBI5_SIM_CLK				166
+#define GSBI6_SIM_CLK				167
+#define GSBI7_SIM_CLK				168
+#define USB_HSIC_HSIC_CLK_SRC			169
+#define USB_HSIC_HSIC_CLK			170
+#define USB_HSIC_HSIO_CAL_CLK			171
+#define SPDM_CFG_H_CLK				172
+#define SPDM_MSTR_H_CLK				173
+#define SPDM_FF_CLK_SRC				174
+#define SPDM_FF_CLK				175
+#define SEC_CTRL_CLK				176
+#define SEC_CTRL_ACC_CLK_SRC			177
+#define SEC_CTRL_ACC_CLK			178
+#define TLMM_H_CLK				179
+#define TLMM_CLK				180
+#define SATA_H_CLK				181
+#define SATA_CLK_SRC				182
+#define SATA_RXOOB_CLK				183
+#define SATA_PMALIVE_CLK			184
+#define SATA_PHY_REF_CLK			185
+#define SATA_A_CLK				186
+#define SATA_PHY_CFG_CLK			187
+#define TSSC_CLK_SRC				188
+#define TSSC_CLK				189
+#define PDM_SRC					190
+#define PDM_CLK					191
+#define GP0_SRC					192
+#define GP0_CLK					193
+#define GP1_SRC					194
+#define GP1_CLK					195
+#define GP2_SRC					196
+#define GP2_CLK					197
+#define MPM_CLK					198
+#define EBI1_CLK_SRC				199
+#define EBI1_CH0_CLK				200
+#define EBI1_CH1_CLK				201
+#define EBI1_2X_CLK				202
+#define EBI1_CH0_DQ_CLK				203
+#define EBI1_CH1_DQ_CLK				204
+#define EBI1_CH0_CA_CLK				205
+#define EBI1_CH1_CA_CLK				206
+#define EBI1_XO_CLK				207
+#define SFAB_SMPSS_S_H_CLK			208
+#define PRNG_SRC				209
+#define PRNG_CLK				210
+#define PXO_SRC					211
+#define SPDM_CY_PORT0_CLK			212
+#define SPDM_CY_PORT1_CLK			213
+#define SPDM_CY_PORT2_CLK			214
+#define SPDM_CY_PORT3_CLK			215
+#define SPDM_CY_PORT4_CLK			216
+#define SPDM_CY_PORT5_CLK			217
+#define SPDM_CY_PORT6_CLK			218
+#define SPDM_CY_PORT7_CLK			219
+#define PLL0					220
+#define PLL0_VOTE				221
+#define PLL3					222
+#define PLL3_VOTE				223
+#define PLL4					224
+#define PLL4_VOTE				225
+#define PLL8					226
+#define PLL8_VOTE				227
+#define PLL9					228
+#define PLL10					229
+#define PLL11					230
+#define PLL12					231
+#define PLL14					232
+#define PLL14_VOTE				233
+#define PLL18					234
+#define CE5_SRC					235
+#define CE5_H_CLK				236
+#define CE5_CORE_CLK				237
+#define CE3_SLEEP_CLK				238
+#define SFAB_AHB_S8_FCLK			239
+#define SPDM_CY_PORT8_CLK			246
+#define PCIE_ALT_REF_SRC			247
+#define PCIE_ALT_REF_CLK			248
+#define PCIE_1_A_CLK				249
+#define PCIE_1_AUX_CLK				250
+#define PCIE_1_H_CLK				251
+#define PCIE_1_PHY_CLK				252
+#define PCIE_1_ALT_REF_SRC			253
+#define PCIE_1_ALT_REF_CLK			254
+#define PCIE_2_A_CLK				255
+#define PCIE_2_AUX_CLK				256
+#define PCIE_2_H_CLK				257
+#define PCIE_2_PHY_CLK				258
+#define PCIE_2_ALT_REF_SRC			259
+#define PCIE_2_ALT_REF_CLK			260
+#define EBI2_CLK				261
+#define USB30_SLEEP_CLK				262
+#define USB30_UTMI_SRC				263
+#define USB30_0_UTMI_CLK			264
+#define USB30_1_UTMI_CLK			265
+#define USB30_MASTER_SRC			266
+#define USB30_0_MASTER_CLK			267
+#define USB30_1_MASTER_CLK			268
+#define GMAC_CORE1_CLK_SRC			269
+#define GMAC_CORE2_CLK_SRC			270
+#define GMAC_CORE3_CLK_SRC			271
+#define GMAC_CORE4_CLK_SRC			272
+#define GMAC_CORE1_CLK				273
+#define GMAC_CORE2_CLK				274
+#define GMAC_CORE3_CLK				275
+#define GMAC_CORE4_CLK				276
+#define UBI32_CORE1_CLK_SRC			277
+#define UBI32_CORE2_CLK_SRC			278
+#define UBI32_CORE1_CLK				279
+#define UBI32_CORE2_CLK				280
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,gcc-msm8960.h b/include/dt-bindings/clock/qcom,gcc-msm8960.h
index f9f547146a1..7d20eedfee9 100644
--- a/include/dt-bindings/clock/qcom,gcc-msm8960.h
+++ b/include/dt-bindings/clock/qcom,gcc-msm8960.h
@@ -308,5 +308,16 @@
 #define PLL13					292
 #define PLL14					293
 #define PLL14_VOTE				294
+#define USB_HS3_H_CLK				295
+#define USB_HS3_XCVR_SRC			296
+#define USB_HS3_XCVR_CLK			297
+#define USB_HS4_H_CLK				298
+#define USB_HS4_XCVR_SRC			299
+#define USB_HS4_XCVR_CLK			300
+#define SATA_PHY_CFG_CLK			301
+#define SATA_A_CLK				302
+#define CE3_SRC					303
+#define CE3_CORE_CLK				304
+#define CE3_H_CLK				305
 
 #endif
diff --git a/include/dt-bindings/clock/qcom,mmcc-apq8084.h b/include/dt-bindings/clock/qcom,mmcc-apq8084.h
new file mode 100644
index 00000000000..a929f86d0dd
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,mmcc-apq8084.h
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_CLK_APQ_MMCC_8084_H
+#define _DT_BINDINGS_CLK_APQ_MMCC_8084_H
+
+#define MMSS_AHB_CLK_SRC		0
+#define MMSS_AXI_CLK_SRC		1
+#define MMPLL0				2
+#define MMPLL0_VOTE			3
+#define MMPLL1				4
+#define MMPLL1_VOTE			5
+#define MMPLL2				6
+#define MMPLL3				7
+#define MMPLL4				8
+#define CSI0_CLK_SRC			9
+#define CSI1_CLK_SRC			10
+#define CSI2_CLK_SRC			11
+#define CSI3_CLK_SRC			12
+#define VCODEC0_CLK_SRC			13
+#define VFE0_CLK_SRC			14
+#define VFE1_CLK_SRC			15
+#define MDP_CLK_SRC			16
+#define PCLK0_CLK_SRC			17
+#define PCLK1_CLK_SRC			18
+#define OCMEMNOC_CLK_SRC		19
+#define GFX3D_CLK_SRC			20
+#define JPEG0_CLK_SRC			21
+#define JPEG1_CLK_SRC			22
+#define JPEG2_CLK_SRC			23
+#define EDPPIXEL_CLK_SRC		24
+#define EXTPCLK_CLK_SRC			25
+#define VP_CLK_SRC			26
+#define CCI_CLK_SRC			27
+#define CAMSS_GP0_CLK_SRC		28
+#define CAMSS_GP1_CLK_SRC		29
+#define MCLK0_CLK_SRC			30
+#define MCLK1_CLK_SRC			31
+#define MCLK2_CLK_SRC			32
+#define MCLK3_CLK_SRC			33
+#define CSI0PHYTIMER_CLK_SRC		34
+#define CSI1PHYTIMER_CLK_SRC		35
+#define CSI2PHYTIMER_CLK_SRC		36
+#define CPP_CLK_SRC			37
+#define BYTE0_CLK_SRC			38
+#define BYTE1_CLK_SRC			39
+#define EDPAUX_CLK_SRC			40
+#define EDPLINK_CLK_SRC			41
+#define ESC0_CLK_SRC			42
+#define ESC1_CLK_SRC			43
+#define HDMI_CLK_SRC			44
+#define VSYNC_CLK_SRC			45
+#define RBCPR_CLK_SRC			46
+#define RBBMTIMER_CLK_SRC		47
+#define MAPLE_CLK_SRC			48
+#define VDP_CLK_SRC			49
+#define VPU_BUS_CLK_SRC			50
+#define MMSS_CXO_CLK			51
+#define MMSS_SLEEPCLK_CLK		52
+#define AVSYNC_AHB_CLK			53
+#define AVSYNC_EDPPIXEL_CLK		54
+#define AVSYNC_EXTPCLK_CLK		55
+#define AVSYNC_PCLK0_CLK		56
+#define AVSYNC_PCLK1_CLK		57
+#define AVSYNC_VP_CLK			58
+#define CAMSS_AHB_CLK			59
+#define CAMSS_CCI_CCI_AHB_CLK		60
+#define CAMSS_CCI_CCI_CLK		61
+#define CAMSS_CSI0_AHB_CLK		62
+#define CAMSS_CSI0_CLK			63
+#define CAMSS_CSI0PHY_CLK		64
+#define CAMSS_CSI0PIX_CLK		65
+#define CAMSS_CSI0RDI_CLK		66
+#define CAMSS_CSI1_AHB_CLK		67
+#define CAMSS_CSI1_CLK			68
+#define CAMSS_CSI1PHY_CLK		69
+#define CAMSS_CSI1PIX_CLK		70
+#define CAMSS_CSI1RDI_CLK		71
+#define CAMSS_CSI2_AHB_CLK		72
+#define CAMSS_CSI2_CLK			73
+#define CAMSS_CSI2PHY_CLK		74
+#define CAMSS_CSI2PIX_CLK		75
+#define CAMSS_CSI2RDI_CLK		76
+#define CAMSS_CSI3_AHB_CLK		77
+#define CAMSS_CSI3_CLK			78
+#define CAMSS_CSI3PHY_CLK		79
+#define CAMSS_CSI3PIX_CLK		80
+#define CAMSS_CSI3RDI_CLK		81
+#define CAMSS_CSI_VFE0_CLK		82
+#define CAMSS_CSI_VFE1_CLK		83
+#define CAMSS_GP0_CLK			84
+#define CAMSS_GP1_CLK			85
+#define CAMSS_ISPIF_AHB_CLK		86
+#define CAMSS_JPEG_JPEG0_CLK		87
+#define CAMSS_JPEG_JPEG1_CLK		88
+#define CAMSS_JPEG_JPEG2_CLK		89
+#define CAMSS_JPEG_JPEG_AHB_CLK		90
+#define CAMSS_JPEG_JPEG_AXI_CLK		91
+#define CAMSS_MCLK0_CLK			92
+#define CAMSS_MCLK1_CLK			93
+#define CAMSS_MCLK2_CLK			94
+#define CAMSS_MCLK3_CLK			95
+#define CAMSS_MICRO_AHB_CLK		96
+#define CAMSS_PHY0_CSI0PHYTIMER_CLK	97
+#define CAMSS_PHY1_CSI1PHYTIMER_CLK	98
+#define CAMSS_PHY2_CSI2PHYTIMER_CLK	99
+#define CAMSS_TOP_AHB_CLK		100
+#define CAMSS_VFE_CPP_AHB_CLK		101
+#define CAMSS_VFE_CPP_CLK		102
+#define CAMSS_VFE_VFE0_CLK		103
+#define CAMSS_VFE_VFE1_CLK		104
+#define CAMSS_VFE_VFE_AHB_CLK		105
+#define CAMSS_VFE_VFE_AXI_CLK		106
+#define MDSS_AHB_CLK			107
+#define MDSS_AXI_CLK			108
+#define MDSS_BYTE0_CLK			109
+#define MDSS_BYTE1_CLK			110
+#define MDSS_EDPAUX_CLK			111
+#define MDSS_EDPLINK_CLK		112
+#define MDSS_EDPPIXEL_CLK		113
+#define MDSS_ESC0_CLK			114
+#define MDSS_ESC1_CLK			115
+#define MDSS_EXTPCLK_CLK		116
+#define MDSS_HDMI_AHB_CLK		117
+#define MDSS_HDMI_CLK			118
+#define MDSS_MDP_CLK			119
+#define MDSS_MDP_LUT_CLK		120
+#define MDSS_PCLK0_CLK			121
+#define MDSS_PCLK1_CLK			122
+#define MDSS_VSYNC_CLK			123
+#define MMSS_RBCPR_AHB_CLK		124
+#define MMSS_RBCPR_CLK			125
+#define MMSS_SPDM_AHB_CLK		126
+#define MMSS_SPDM_AXI_CLK		127
+#define MMSS_SPDM_CSI0_CLK		128
+#define MMSS_SPDM_GFX3D_CLK		129
+#define MMSS_SPDM_JPEG0_CLK		130
+#define MMSS_SPDM_JPEG1_CLK		131
+#define MMSS_SPDM_JPEG2_CLK		132
+#define MMSS_SPDM_MDP_CLK		133
+#define MMSS_SPDM_PCLK0_CLK		134
+#define MMSS_SPDM_PCLK1_CLK		135
+#define MMSS_SPDM_VCODEC0_CLK		136
+#define MMSS_SPDM_VFE0_CLK		137
+#define MMSS_SPDM_VFE1_CLK		138
+#define MMSS_SPDM_RM_AXI_CLK		139
+#define MMSS_SPDM_RM_OCMEMNOC_CLK	140
+#define MMSS_MISC_AHB_CLK		141
+#define MMSS_MMSSNOC_AHB_CLK		142
+#define MMSS_MMSSNOC_BTO_AHB_CLK	143
+#define MMSS_MMSSNOC_AXI_CLK		144
+#define MMSS_S0_AXI_CLK			145
+#define OCMEMCX_AHB_CLK			146
+#define OCMEMCX_OCMEMNOC_CLK		147
+#define OXILI_OCMEMGX_CLK		148
+#define OXILI_GFX3D_CLK			149
+#define OXILI_RBBMTIMER_CLK		150
+#define OXILICX_AHB_CLK			151
+#define VENUS0_AHB_CLK			152
+#define VENUS0_AXI_CLK			153
+#define VENUS0_CORE0_VCODEC_CLK		154
+#define VENUS0_CORE1_VCODEC_CLK		155
+#define VENUS0_OCMEMNOC_CLK		156
+#define VENUS0_VCODEC0_CLK		157
+#define VPU_AHB_CLK			158
+#define VPU_AXI_CLK			159
+#define VPU_BUS_CLK			160
+#define VPU_CXO_CLK			161
+#define VPU_MAPLE_CLK			162
+#define VPU_SLEEP_CLK			163
+#define VPU_VDP_CLK			164
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,mmcc-msm8960.h b/include/dt-bindings/clock/qcom,mmcc-msm8960.h
index 5868ef14a77..85041b28f97 100644
--- a/include/dt-bindings/clock/qcom,mmcc-msm8960.h
+++ b/include/dt-bindings/clock/qcom,mmcc-msm8960.h
@@ -133,5 +133,13 @@
 #define CSIPHY0_TIMER_CLK				116
 #define PLL1						117
 #define PLL2						118
+#define RGB_TV_CLK					119
+#define NPL_TV_CLK					120
+#define VCAP_AHB_CLK					121
+#define VCAP_AXI_CLK					122
+#define VCAP_SRC					123
+#define VCAP_CLK					124
+#define VCAP_NPL_CLK					125
+#define PLL15						126
 
 #endif
diff --git a/include/dt-bindings/clock/rk3066a-cru.h b/include/dt-bindings/clock/rk3066a-cru.h
new file mode 100644
index 00000000000..bc1ed1dbd85
--- /dev/null
+++ b/include/dt-bindings/clock/rk3066a-cru.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <dt-bindings/clock/rk3188-cru-common.h>
+
+/* soft-reset indices */
+#define SRST_SRST1		0
+#define SRST_SRST2		1
+
+#define SRST_L2MEM		18
+#define SRST_I2S0		23
+#define SRST_I2S1		24
+#define SRST_I2S2		25
+#define SRST_TIMER2		29
+
+#define SRST_GPIO4		36
+#define SRST_GPIO6		38
+
+#define SRST_TSADC		92
+
+#define SRST_HDMI		96
+#define SRST_HDMI_APB		97
+#define SRST_CIF1		111
diff --git a/include/dt-bindings/clock/rk3188-cru-common.h b/include/dt-bindings/clock/rk3188-cru-common.h
new file mode 100644
index 00000000000..750ee60e75f
--- /dev/null
+++ b/include/dt-bindings/clock/rk3188-cru-common.h
@@ -0,0 +1,249 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/* core clocks from */
+#define PLL_APLL		1
+#define PLL_DPLL		2
+#define PLL_CPLL		3
+#define PLL_GPLL		4
+#define CORE_PERI		5
+#define CORE_L2C		6
+
+/* sclk gates (special clocks) */
+#define SCLK_UART0		64
+#define SCLK_UART1		65
+#define SCLK_UART2		66
+#define SCLK_UART3		67
+#define SCLK_MAC		68
+#define SCLK_SPI0		69
+#define SCLK_SPI1		70
+#define SCLK_SARADC		71
+#define SCLK_SDMMC		72
+#define SCLK_SDIO		73
+#define SCLK_EMMC		74
+#define SCLK_I2S0		75
+#define SCLK_I2S1		76
+#define SCLK_I2S2		77
+#define SCLK_SPDIF		78
+#define SCLK_CIF0		79
+#define SCLK_CIF1		80
+#define SCLK_OTGPHY0		81
+#define SCLK_OTGPHY1		82
+#define SCLK_HSADC		83
+#define SCLK_TIMER0		84
+#define SCLK_TIMER1		85
+#define SCLK_TIMER2		86
+#define SCLK_TIMER3		87
+#define SCLK_TIMER4		88
+#define SCLK_TIMER5		89
+#define SCLK_TIMER6		90
+#define SCLK_JTAG		91
+#define SCLK_SMC		92
+
+#define DCLK_LCDC0		190
+#define DCLK_LCDC1		191
+
+/* aclk gates */
+#define ACLK_DMA1		192
+#define ACLK_DMA2		193
+#define ACLK_GPS		194
+#define ACLK_LCDC0		195
+#define ACLK_LCDC1		196
+#define ACLK_GPU		197
+#define ACLK_SMC		198
+#define ACLK_CIF		199
+#define ACLK_IPP		200
+#define ACLK_RGA		201
+#define ACLK_CIF0		202
+
+/* pclk gates */
+#define PCLK_GRF		320
+#define PCLK_PMU		321
+#define PCLK_TIMER0		322
+#define PCLK_TIMER1		323
+#define PCLK_TIMER2		324
+#define PCLK_TIMER3		325
+#define PCLK_PWM01		326
+#define PCLK_PWM23		327
+#define PCLK_SPI0		328
+#define PCLK_SPI1		329
+#define PCLK_SARADC		330
+#define PCLK_WDT		331
+#define PCLK_UART0		332
+#define PCLK_UART1		333
+#define PCLK_UART2		334
+#define PCLK_UART3		335
+#define PCLK_I2C0		336
+#define PCLK_I2C1		337
+#define PCLK_I2C2		338
+#define PCLK_I2C3		339
+#define PCLK_I2C4		340
+#define PCLK_GPIO0		341
+#define PCLK_GPIO1		342
+#define PCLK_GPIO2		343
+#define PCLK_GPIO3		344
+#define PCLK_GPIO4		345
+#define PCLK_GPIO6		346
+#define PCLK_EFUSE		347
+#define PCLK_TZPC		348
+#define PCLK_TSADC		349
+
+/* hclk gates */
+#define HCLK_SDMMC		448
+#define HCLK_SDIO		449
+#define HCLK_EMMC		450
+#define HCLK_OTG0		451
+#define HCLK_EMAC		452
+#define HCLK_SPDIF		453
+#define HCLK_I2S0		454
+#define HCLK_I2S1		455
+#define HCLK_I2S2		456
+#define HCLK_OTG1		457
+#define HCLK_HSIC		458
+#define HCLK_HSADC		459
+#define HCLK_PIDF		460
+#define HCLK_LCDC0		461
+#define HCLK_LCDC1		462
+#define HCLK_ROM		463
+#define HCLK_CIF0		464
+#define HCLK_IPP		465
+#define HCLK_RGA		466
+#define HCLK_NANDC0		467
+
+#define CLK_NR_CLKS		(HCLK_NANDC0 + 1)
+
+/* soft-reset indices */
+#define SRST_MCORE		2
+#define SRST_CORE0		3
+#define SRST_CORE1		4
+#define SRST_MCORE_DBG		7
+#define SRST_CORE0_DBG		8
+#define SRST_CORE1_DBG		9
+#define SRST_CORE0_WDT		12
+#define SRST_CORE1_WDT		13
+#define SRST_STRC_SYS		14
+#define SRST_L2C		15
+
+#define SRST_CPU_AHB		17
+#define SRST_AHB2APB		19
+#define SRST_DMA1		20
+#define SRST_INTMEM		21
+#define SRST_ROM		22
+#define SRST_SPDIF		26
+#define SRST_TIMER0		27
+#define SRST_TIMER1		28
+#define SRST_EFUSE		30
+
+#define SRST_GPIO0		32
+#define SRST_GPIO1		33
+#define SRST_GPIO2		34
+#define SRST_GPIO3		35
+
+#define SRST_UART0		39
+#define SRST_UART1		40
+#define SRST_UART2		41
+#define SRST_UART3		42
+#define SRST_I2C0		43
+#define SRST_I2C1		44
+#define SRST_I2C2		45
+#define SRST_I2C3		46
+#define SRST_I2C4		47
+
+#define SRST_PWM0		48
+#define SRST_PWM1		49
+#define SRST_DAP_PO		50
+#define SRST_DAP		51
+#define SRST_DAP_SYS		52
+#define SRST_TPIU_ATB		53
+#define SRST_PMU_APB		54
+#define SRST_GRF		55
+#define SRST_PMU		56
+#define SRST_PERI_AXI		57
+#define SRST_PERI_AHB		58
+#define SRST_PERI_APB		59
+#define SRST_PERI_NIU		60
+#define SRST_CPU_PERI		61
+#define SRST_EMEM_PERI		62
+#define SRST_USB_PERI		63
+
+#define SRST_DMA2		64
+#define SRST_SMC		65
+#define SRST_MAC		66
+#define SRST_NANC0		68
+#define SRST_USBOTG0		69
+#define SRST_USBPHY0		70
+#define SRST_OTGC0		71
+#define SRST_USBOTG1		72
+#define SRST_USBPHY1		73
+#define SRST_OTGC1		74
+#define SRST_HSADC		76
+#define SRST_PIDFILTER		77
+#define SRST_DDR_MSCH		79
+
+#define SRST_TZPC		80
+#define SRST_SDMMC		81
+#define SRST_SDIO		82
+#define SRST_EMMC		83
+#define SRST_SPI0		84
+#define SRST_SPI1		85
+#define SRST_WDT		86
+#define SRST_SARADC		87
+#define SRST_DDRPHY		88
+#define SRST_DDRPHY_APB		89
+#define SRST_DDRCTL		90
+#define SRST_DDRCTL_APB		91
+#define SRST_DDRPUB		93
+
+#define SRST_VIO0_AXI		98
+#define SRST_VIO0_AHB		99
+#define SRST_LCDC0_AXI		100
+#define SRST_LCDC0_AHB		101
+#define SRST_LCDC0_DCLK		102
+#define SRST_LCDC1_AXI		103
+#define SRST_LCDC1_AHB		104
+#define SRST_LCDC1_DCLK		105
+#define SRST_IPP_AXI		106
+#define SRST_IPP_AHB		107
+#define SRST_RGA_AXI		108
+#define SRST_RGA_AHB		109
+#define SRST_CIF0		110
+
+#define SRST_VCODEC_AXI		112
+#define SRST_VCODEC_AHB		113
+#define SRST_VIO1_AXI		114
+#define SRST_VCODEC_CPU		115
+#define SRST_VCODEC_NIU		116
+#define SRST_GPU		120
+#define SRST_GPU_NIU		122
+#define SRST_TFUN_ATB		125
+#define SRST_TFUN_APB		126
+#define SRST_CTI4_APB		127
+
+#define SRST_TPIU_APB		128
+#define SRST_TRACE		129
+#define SRST_CORE_DBG		130
+#define SRST_DBG_APB		131
+#define SRST_CTI0		132
+#define SRST_CTI0_APB		133
+#define SRST_CTI1		134
+#define SRST_CTI1_APB		135
+#define SRST_PTM_CORE0		136
+#define SRST_PTM_CORE1		137
+#define SRST_PTM0		138
+#define SRST_PTM0_ATB		139
+#define SRST_PTM1		140
+#define SRST_PTM1_ATB		141
+#define SRST_CTM		142
+#define SRST_TS			143
diff --git a/include/dt-bindings/clock/rk3188-cru.h b/include/dt-bindings/clock/rk3188-cru.h
new file mode 100644
index 00000000000..9fac8edd3f9
--- /dev/null
+++ b/include/dt-bindings/clock/rk3188-cru.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <dt-bindings/clock/rk3188-cru-common.h>
+
+/* soft-reset indices */
+#define SRST_PTM_CORE2		0
+#define SRST_PTM_CORE3		1
+#define SRST_CORE2		5
+#define SRST_CORE3		6
+#define SRST_CORE2_DBG		10
+#define SRST_CORE3_DBG		11
+
+#define SRST_TIMER2		16
+#define SRST_TIMER4		23
+#define SRST_I2S0		24
+#define SRST_TIMER5		25
+#define SRST_TIMER3		29
+#define SRST_TIMER6		31
+
+#define SRST_PTM3		36
+#define SRST_PTM3_ATB		37
+
+#define SRST_GPS		67
+#define SRST_HSICPHY		75
+#define SRST_TIMER		78
+
+#define SRST_PTM2		92
+#define SRST_CORE2_WDT		94
+#define SRST_CORE3_WDT		95
+
+#define SRST_PTM2_ATB		111
+
+#define SRST_HSIC		117
+#define SRST_CTI2		118
+#define SRST_CTI2_APB		119
+#define SRST_GPU_BRIDGE		121
+#define SRST_CTI3		123
+#define SRST_CTI3_APB		124
diff --git a/include/dt-bindings/clock/rk3288-cru.h b/include/dt-bindings/clock/rk3288-cru.h
new file mode 100644
index 00000000000..ebcb460ea4a
--- /dev/null
+++ b/include/dt-bindings/clock/rk3288-cru.h
@@ -0,0 +1,278 @@
+/*
+ * Copyright (c) 2014 MundoReader S.L.
+ * Author: Heiko Stuebner <heiko@sntech.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/* core clocks */
+#define PLL_APLL		1
+#define PLL_DPLL		2
+#define PLL_CPLL		3
+#define PLL_GPLL		4
+#define PLL_NPLL		5
+
+/* sclk gates (special clocks) */
+#define SCLK_GPU		64
+#define SCLK_SPI0		65
+#define SCLK_SPI1		66
+#define SCLK_SPI2		67
+#define SCLK_SDMMC		68
+#define SCLK_SDIO0		69
+#define SCLK_SDIO1		70
+#define SCLK_EMMC		71
+#define SCLK_TSADC		72
+#define SCLK_SARADC		73
+#define SCLK_PS2C		74
+#define SCLK_NANDC0		75
+#define SCLK_NANDC1		76
+#define SCLK_UART0		77
+#define SCLK_UART1		78
+#define SCLK_UART2		79
+#define SCLK_UART3		80
+#define SCLK_UART4		81
+#define SCLK_I2S0		82
+#define SCLK_SPDIF		83
+#define SCLK_SPDIF8CH		84
+#define SCLK_TIMER0		85
+#define SCLK_TIMER1		86
+#define SCLK_TIMER2		87
+#define SCLK_TIMER3		88
+#define SCLK_TIMER4		89
+#define SCLK_TIMER5		90
+#define SCLK_TIMER6		91
+#define SCLK_HSADC		92
+#define SCLK_OTGPHY0		93
+#define SCLK_OTGPHY1		94
+#define SCLK_OTGPHY2		95
+#define SCLK_OTG_ADP		96
+#define SCLK_HSICPHY480M	97
+#define SCLK_HSICPHY12M		98
+#define SCLK_MACREF		99
+#define SCLK_LCDC_PWM0		100
+#define SCLK_LCDC_PWM1		101
+#define SCLK_MAC_RX		102
+#define SCLK_MAC_TX		103
+
+#define DCLK_VOP0		190
+#define DCLK_VOP1		191
+
+/* aclk gates */
+#define ACLK_GPU		192
+#define ACLK_DMAC1		193
+#define ACLK_DMAC2		194
+#define ACLK_MMU		195
+#define ACLK_GMAC		196
+#define ACLK_VOP0		197
+#define ACLK_VOP1		198
+#define ACLK_CRYPTO		199
+#define ACLK_RGA		200
+
+/* pclk gates */
+#define PCLK_GPIO0		320
+#define PCLK_GPIO1		321
+#define PCLK_GPIO2		322
+#define PCLK_GPIO3		323
+#define PCLK_GPIO4		324
+#define PCLK_GPIO5		325
+#define PCLK_GPIO6		326
+#define PCLK_GPIO7		327
+#define PCLK_GPIO8		328
+#define PCLK_GRF		329
+#define PCLK_SGRF		330
+#define PCLK_PMU		331
+#define PCLK_I2C0		332
+#define PCLK_I2C1		333
+#define PCLK_I2C2		334
+#define PCLK_I2C3		335
+#define PCLK_I2C4		336
+#define PCLK_I2C5		337
+#define PCLK_SPI0		338
+#define PCLK_SPI1		339
+#define PCLK_SPI2		340
+#define PCLK_UART0		341
+#define PCLK_UART1		342
+#define PCLK_UART2		343
+#define PCLK_UART3		344
+#define PCLK_UART4		345
+#define PCLK_TSADC		346
+#define PCLK_SARADC		347
+#define PCLK_SIM		348
+#define PCLK_GMAC		349
+#define PCLK_PWM		350
+#define PCLK_RKPWM		351
+#define PCLK_PS2C		352
+#define PCLK_TIMER		353
+#define PCLK_TZPC		354
+
+/* hclk gates */
+#define HCLK_GPS		448
+#define HCLK_OTG0		449
+#define HCLK_USBHOST0		450
+#define HCLK_USBHOST1		451
+#define HCLK_HSIC		452
+#define HCLK_NANDC0		453
+#define HCLK_NANDC1		454
+#define HCLK_TSP		455
+#define HCLK_SDMMC		456
+#define HCLK_SDIO0		457
+#define HCLK_SDIO1		458
+#define HCLK_EMMC		459
+#define HCLK_HSADC		460
+#define HCLK_CRYPTO		461
+#define HCLK_I2S0		462
+#define HCLK_SPDIF		463
+#define HCLK_SPDIF8CH		464
+#define HCLK_VOP0		465
+#define HCLK_VOP1		466
+#define HCLK_ROM		467
+#define HCLK_IEP		468
+#define HCLK_ISP		469
+#define HCLK_RGA		470
+
+#define CLK_NR_CLKS		(HCLK_RGA + 1)
+
+/* soft-reset indices */
+#define SRST_CORE0		0
+#define SRST_CORE1		1
+#define SRST_CORE2		2
+#define SRST_CORE3		3
+#define SRST_CORE0_PO		4
+#define SRST_CORE1_PO		5
+#define SRST_CORE2_PO		6
+#define SRST_CORE3_PO		7
+#define SRST_PDCORE_STRSYS	8
+#define SRST_PDBUS_STRSYS	9
+#define SRST_L2C		10
+#define SRST_TOPDBG		11
+#define SRST_CORE0_DBG		12
+#define SRST_CORE1_DBG		13
+#define SRST_CORE2_DBG		14
+#define SRST_CORE3_DBG		15
+
+#define SRST_PDBUG_AHB_ARBITOR	16
+#define SRST_EFUSE256		17
+#define SRST_DMAC1		18
+#define SRST_INTMEM		19
+#define SRST_ROM		20
+#define SRST_SPDIF8CH		21
+#define SRST_TIMER		22
+#define SRST_I2S0		23
+#define SRST_SPDIF		24
+#define SRST_TIMER0		25
+#define SRST_TIMER1		26
+#define SRST_TIMER2		27
+#define SRST_TIMER3		28
+#define SRST_TIMER4		29
+#define SRST_TIMER5		30
+#define SRST_EFUSE		31
+
+#define SRST_GPIO0		32
+#define SRST_GPIO1		33
+#define SRST_GPIO2		34
+#define SRST_GPIO3		35
+#define SRST_GPIO4		36
+#define SRST_GPIO5		37
+#define SRST_GPIO6		38
+#define SRST_GPIO7		39
+#define SRST_GPIO8		40
+#define SRST_I2C0		42
+#define SRST_I2C1		43
+#define SRST_I2C2		44
+#define SRST_I2C3		45
+#define SRST_I2C4		46
+#define SRST_I2C5		47
+
+#define SRST_DWPWM		48
+#define SRST_MMC_PERI		49
+#define SRST_PERIPH_MMU		50
+#define SRST_DAP		51
+#define SRST_DAP_SYS		52
+#define SRST_TPIU		53
+#define SRST_PMU_APB		54
+#define SRST_GRF		55
+#define SRST_PMU		56
+#define SRST_PERIPH_AXI		57
+#define SRST_PERIPH_AHB		58
+#define SRST_PERIPH_APB		59
+#define SRST_PERIPH_NIU		60
+#define SRST_PDPERI_AHB_ARBI	61
+#define SRST_EMEM		62
+#define SRST_USB_PERI		63
+
+#define SRST_DMAC2		64
+#define SRST_MAC		66
+#define SRST_GPS		67
+#define SRST_RKPWM		69
+#define SRST_CCP		71
+#define SRST_USBHOST0		72
+#define SRST_HSIC		73
+#define SRST_HSIC_AUX		74
+#define SRST_HSIC_PHY		75
+#define SRST_HSADC		76
+#define SRST_NANDC0		77
+#define SRST_NANDC1		78
+
+#define SRST_TZPC		80
+#define SRST_SPI0		83
+#define SRST_SPI1		84
+#define SRST_SPI2		85
+#define SRST_SARADC		87
+#define SRST_PDALIVE_NIU	88
+#define SRST_PDPMU_INTMEM	89
+#define SRST_PDPMU_NIU		90
+#define SRST_SGRF		91
+
+#define SRST_VIO_ARBI		96
+#define SRST_RGA_NIU		97
+#define SRST_VIO0_NIU_AXI	98
+#define SRST_VIO_NIU_AHB	99
+#define SRST_LCDC0_AXI		100
+#define SRST_LCDC0_AHB		101
+#define SRST_LCDC0_DCLK		102
+#define SRST_VIO1_NIU_AXI	103
+#define SRST_VIP		104
+#define SRST_RGA_CORE		105
+#define SRST_IEP_AXI		106
+#define SRST_IEP_AHB		107
+#define SRST_RGA_AXI		108
+#define SRST_RGA_AHB		109
+#define SRST_ISP		110
+#define SRST_EDP		111
+
+#define SRST_VCODEC_AXI		112
+#define SRST_VCODEC_AHB		113
+#define SRST_VIO_H2P		114
+#define SRST_MIPIDSI0		115
+#define SRST_MIPIDSI1		116
+#define SRST_MIPICSI		117
+#define SRST_LVDS_PHY		118
+#define SRST_LVDS_CON		119
+#define SRST_GPU		120
+#define SRST_HDMI		121
+#define SRST_CORE_PVTM		124
+#define SRST_GPU_PVTM		125
+
+#define SRST_MMC0		128
+#define SRST_SDIO0		129
+#define SRST_SDIO1		130
+#define SRST_EMMC		131
+#define SRST_USBOTG_AHB		132
+#define SRST_USBOTG_PHY		133
+#define SRST_USBOTG_CON		134
+#define SRST_USBHOST0_AHB	135
+#define SRST_USBHOST0_PHY	136
+#define SRST_USBHOST0_CON	137
+#define SRST_USBHOST1_AHB	138
+#define SRST_USBHOST1_PHY	139
+#define SRST_USBHOST1_CON	140
+#define SRST_USB_ADP		141
+#define SRST_ACC_EFUSE		142
diff --git a/include/dt-bindings/clock/stih415-clks.h b/include/dt-bindings/clock/stih415-clks.h
index 0d2c7397e02..d80caa68aeb 100644
--- a/include/dt-bindings/clock/stih415-clks.h
+++ b/include/dt-bindings/clock/stih415-clks.h
@@ -10,6 +10,7 @@
 #define CLK_ETH1_PHY		4
 
 /* CLOCKGEN A1 */
+#define CLK_ICN_IF_2		0
 #define CLK_GMAC0_PHY		3
 
 #endif
diff --git a/include/dt-bindings/clock/stih416-clks.h b/include/dt-bindings/clock/stih416-clks.h
index 552c779eb6a..f9bdbd13568 100644
--- a/include/dt-bindings/clock/stih416-clks.h
+++ b/include/dt-bindings/clock/stih416-clks.h
@@ -10,6 +10,7 @@
 #define CLK_ETH1_PHY		4
 
 /* CLOCKGEN A1 */
+#define CLK_ICN_IF_2		0
 #define CLK_GMAC0_PHY		3
 
 #endif
diff --git a/include/dt-bindings/mfd/palmas.h b/include/dt-bindings/mfd/palmas.h
new file mode 100644
index 00000000000..2c8ac484138
--- /dev/null
+++ b/include/dt-bindings/mfd/palmas.h
@@ -0,0 +1,18 @@
+/*
+ * This header provides macros for Palmas device bindings.
+ *
+ * Copyright (c) 2013, NVIDIA Corporation.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ */
+
+#ifndef __DT_BINDINGS_PALMAS_H__
+#define __DT_BINDINGS_PALMAS_H
+
+/* External control pins */
+#define PALMAS_EXT_CONTROL_PIN_ENABLE1	1
+#define PALMAS_EXT_CONTROL_PIN_ENABLE2	2
+#define PALMAS_EXT_CONTROL_PIN_NSLEEP	3
+
+#endif /* __DT_BINDINGS_PALMAS_H */
diff --git a/include/dt-bindings/pinctrl/dra.h b/include/dt-bindings/pinctrl/dra.h
index 002a2855c04..3d33794e4f3 100644
--- a/include/dt-bindings/pinctrl/dra.h
+++ b/include/dt-bindings/pinctrl/dra.h
@@ -30,7 +30,8 @@
 #define MUX_MODE14	0xe
 #define MUX_MODE15	0xf
 
-#define PULL_ENA		(1 << 16)
+#define PULL_ENA		(0 << 16)
+#define PULL_DIS		(1 << 16)
 #define PULL_UP			(1 << 17)
 #define INPUT_EN		(1 << 18)
 #define SLEWCONTROL		(1 << 19)
@@ -38,10 +39,10 @@
 #define WAKEUP_EVENT		(1 << 25)
 
 /* Active pin states */
-#define PIN_OUTPUT		0
+#define PIN_OUTPUT		(0 | PULL_DIS)
 #define PIN_OUTPUT_PULLUP	(PIN_OUTPUT | PULL_ENA | PULL_UP)
 #define PIN_OUTPUT_PULLDOWN	(PIN_OUTPUT | PULL_ENA)
-#define PIN_INPUT		INPUT_EN
+#define PIN_INPUT		(INPUT_EN | PULL_DIS)
 #define PIN_INPUT_SLEW		(INPUT_EN | SLEWCONTROL)
 #define PIN_INPUT_PULLUP	(PULL_ENA | INPUT_EN | PULL_UP)
 #define PIN_INPUT_PULLDOWN	(PULL_ENA | INPUT_EN)
diff --git a/include/dt-bindings/reset/qcom,gcc-apq8084.h b/include/dt-bindings/reset/qcom,gcc-apq8084.h
new file mode 100644
index 00000000000..527caaf48e3
--- /dev/null
+++ b/include/dt-bindings/reset/qcom,gcc-apq8084.h
@@ -0,0 +1,109 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_RESET_APQ_GCC_8084_H
+#define _DT_BINDINGS_RESET_APQ_GCC_8084_H
+
+#define GCC_SYSTEM_NOC_BCR		0
+#define GCC_CONFIG_NOC_BCR		1
+#define GCC_PERIPH_NOC_BCR		2
+#define GCC_IMEM_BCR			3
+#define GCC_MMSS_BCR			4
+#define GCC_QDSS_BCR			5
+#define GCC_USB_30_BCR			6
+#define GCC_USB3_PHY_BCR		7
+#define GCC_USB_HS_HSIC_BCR		8
+#define GCC_USB_HS_BCR			9
+#define GCC_USB2A_PHY_BCR		10
+#define GCC_USB2B_PHY_BCR		11
+#define GCC_SDCC1_BCR			12
+#define GCC_SDCC2_BCR			13
+#define GCC_SDCC3_BCR			14
+#define GCC_SDCC4_BCR			15
+#define GCC_BLSP1_BCR			16
+#define GCC_BLSP1_QUP1_BCR		17
+#define GCC_BLSP1_UART1_BCR		18
+#define GCC_BLSP1_QUP2_BCR		19
+#define GCC_BLSP1_UART2_BCR		20
+#define GCC_BLSP1_QUP3_BCR		21
+#define GCC_BLSP1_UART3_BCR		22
+#define GCC_BLSP1_QUP4_BCR		23
+#define GCC_BLSP1_UART4_BCR		24
+#define GCC_BLSP1_QUP5_BCR		25
+#define GCC_BLSP1_UART5_BCR		26
+#define GCC_BLSP1_QUP6_BCR		27
+#define GCC_BLSP1_UART6_BCR		28
+#define GCC_BLSP2_BCR			29
+#define GCC_BLSP2_QUP1_BCR		30
+#define GCC_BLSP2_UART1_BCR		31
+#define GCC_BLSP2_QUP2_BCR		32
+#define GCC_BLSP2_UART2_BCR		33
+#define GCC_BLSP2_QUP3_BCR		34
+#define GCC_BLSP2_UART3_BCR		35
+#define GCC_BLSP2_QUP4_BCR		36
+#define GCC_BLSP2_UART4_BCR		37
+#define GCC_BLSP2_QUP5_BCR		38
+#define GCC_BLSP2_UART5_BCR		39
+#define GCC_BLSP2_QUP6_BCR		40
+#define GCC_BLSP2_UART6_BCR		41
+#define GCC_PDM_BCR			42
+#define GCC_PRNG_BCR			43
+#define GCC_BAM_DMA_BCR			44
+#define GCC_TSIF_BCR			45
+#define GCC_TCSR_BCR			46
+#define GCC_BOOT_ROM_BCR		47
+#define GCC_MSG_RAM_BCR			48
+#define GCC_TLMM_BCR			49
+#define GCC_MPM_BCR			50
+#define GCC_MPM_AHB_RESET		51
+#define GCC_MPM_NON_AHB_RESET		52
+#define GCC_SEC_CTRL_BCR		53
+#define GCC_SPMI_BCR			54
+#define GCC_SPDM_BCR			55
+#define GCC_CE1_BCR			56
+#define GCC_CE2_BCR			57
+#define GCC_BIMC_BCR			58
+#define GCC_SNOC_BUS_TIMEOUT0_BCR	59
+#define GCC_SNOC_BUS_TIMEOUT2_BCR	60
+#define GCC_PNOC_BUS_TIMEOUT0_BCR	61
+#define GCC_PNOC_BUS_TIMEOUT1_BCR	62
+#define GCC_PNOC_BUS_TIMEOUT2_BCR	63
+#define GCC_PNOC_BUS_TIMEOUT3_BCR	64
+#define GCC_PNOC_BUS_TIMEOUT4_BCR	65
+#define GCC_CNOC_BUS_TIMEOUT0_BCR	66
+#define GCC_CNOC_BUS_TIMEOUT1_BCR	67
+#define GCC_CNOC_BUS_TIMEOUT2_BCR	68
+#define GCC_CNOC_BUS_TIMEOUT3_BCR	69
+#define GCC_CNOC_BUS_TIMEOUT4_BCR	70
+#define GCC_CNOC_BUS_TIMEOUT5_BCR	71
+#define GCC_CNOC_BUS_TIMEOUT6_BCR	72
+#define GCC_DEHR_BCR			73
+#define GCC_RBCPR_BCR			74
+#define GCC_MSS_RESTART			75
+#define GCC_LPASS_RESTART		76
+#define GCC_WCSS_RESTART		77
+#define GCC_VENUS_RESTART		78
+#define GCC_COPSS_SMMU_BCR		79
+#define GCC_SPSS_BCR			80
+#define GCC_PCIE_0_BCR			81
+#define GCC_PCIE_0_PHY_BCR		82
+#define GCC_PCIE_1_BCR			83
+#define GCC_PCIE_1_PHY_BCR		84
+#define GCC_USB_30_SEC_BCR		85
+#define GCC_USB3_SEC_PHY_BCR		86
+#define GCC_SATA_BCR			87
+#define GCC_CE3_BCR			88
+#define GCC_UFS_BCR			89
+#define GCC_USB30_PHY_COM_BCR		90
+
+#endif
diff --git a/include/dt-bindings/reset/qcom,gcc-ipq806x.h b/include/dt-bindings/reset/qcom,gcc-ipq806x.h
new file mode 100644
index 00000000000..0ad5ef930b5
--- /dev/null
+++ b/include/dt-bindings/reset/qcom,gcc-ipq806x.h
@@ -0,0 +1,132 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_RESET_IPQ_806X_H
+#define _DT_BINDINGS_RESET_IPQ_806X_H
+
+#define QDSS_STM_RESET					0
+#define AFAB_SMPSS_S_RESET				1
+#define AFAB_SMPSS_M1_RESET				2
+#define AFAB_SMPSS_M0_RESET				3
+#define AFAB_EBI1_CH0_RESET				4
+#define AFAB_EBI1_CH1_RESET				5
+#define SFAB_ADM0_M0_RESET				6
+#define SFAB_ADM0_M1_RESET				7
+#define SFAB_ADM0_M2_RESET				8
+#define ADM0_C2_RESET					9
+#define ADM0_C1_RESET					10
+#define ADM0_C0_RESET					11
+#define ADM0_PBUS_RESET					12
+#define ADM0_RESET					13
+#define QDSS_CLKS_SW_RESET				14
+#define QDSS_POR_RESET					15
+#define QDSS_TSCTR_RESET				16
+#define QDSS_HRESET_RESET				17
+#define QDSS_AXI_RESET					18
+#define QDSS_DBG_RESET					19
+#define SFAB_PCIE_M_RESET				20
+#define SFAB_PCIE_S_RESET				21
+#define PCIE_EXT_RESET					22
+#define PCIE_PHY_RESET					23
+#define PCIE_PCI_RESET					24
+#define PCIE_POR_RESET					25
+#define PCIE_HCLK_RESET					26
+#define PCIE_ACLK_RESET					27
+#define SFAB_LPASS_RESET				28
+#define SFAB_AFAB_M_RESET				29
+#define AFAB_SFAB_M0_RESET				30
+#define AFAB_SFAB_M1_RESET				31
+#define SFAB_SATA_S_RESET				32
+#define SFAB_DFAB_M_RESET				33
+#define DFAB_SFAB_M_RESET				34
+#define DFAB_SWAY0_RESET				35
+#define DFAB_SWAY1_RESET				36
+#define DFAB_ARB0_RESET					37
+#define DFAB_ARB1_RESET					38
+#define PPSS_PROC_RESET					39
+#define PPSS_RESET					40
+#define DMA_BAM_RESET					41
+#define SPS_TIC_H_RESET					42
+#define SFAB_CFPB_M_RESET				43
+#define SFAB_CFPB_S_RESET				44
+#define TSIF_H_RESET					45
+#define CE1_H_RESET					46
+#define CE1_CORE_RESET					47
+#define CE1_SLEEP_RESET					48
+#define CE2_H_RESET					49
+#define CE2_CORE_RESET					50
+#define SFAB_SFPB_M_RESET				51
+#define SFAB_SFPB_S_RESET				52
+#define RPM_PROC_RESET					53
+#define PMIC_SSBI2_RESET				54
+#define SDC1_RESET					55
+#define SDC2_RESET					56
+#define SDC3_RESET					57
+#define SDC4_RESET					58
+#define USB_HS1_RESET					59
+#define USB_HSIC_RESET					60
+#define USB_FS1_XCVR_RESET				61
+#define USB_FS1_RESET					62
+#define GSBI1_RESET					63
+#define GSBI2_RESET					64
+#define GSBI3_RESET					65
+#define GSBI4_RESET					66
+#define GSBI5_RESET					67
+#define GSBI6_RESET					68
+#define GSBI7_RESET					69
+#define SPDM_RESET					70
+#define SEC_CTRL_RESET					71
+#define TLMM_H_RESET					72
+#define SFAB_SATA_M_RESET				73
+#define SATA_RESET					74
+#define TSSC_RESET					75
+#define PDM_RESET					76
+#define MPM_H_RESET					77
+#define MPM_RESET					78
+#define SFAB_SMPSS_S_RESET				79
+#define PRNG_RESET					80
+#define SFAB_CE3_M_RESET				81
+#define SFAB_CE3_S_RESET				82
+#define CE3_SLEEP_RESET					83
+#define PCIE_1_M_RESET					84
+#define PCIE_1_S_RESET					85
+#define PCIE_1_EXT_RESET				86
+#define PCIE_1_PHY_RESET				87
+#define PCIE_1_PCI_RESET				88
+#define PCIE_1_POR_RESET				89
+#define PCIE_1_HCLK_RESET				90
+#define PCIE_1_ACLK_RESET				91
+#define PCIE_2_M_RESET					92
+#define PCIE_2_S_RESET					93
+#define PCIE_2_EXT_RESET				94
+#define PCIE_2_PHY_RESET				95
+#define PCIE_2_PCI_RESET				96
+#define PCIE_2_POR_RESET				97
+#define PCIE_2_HCLK_RESET				98
+#define PCIE_2_ACLK_RESET				99
+#define SFAB_USB30_S_RESET				100
+#define SFAB_USB30_M_RESET				101
+#define USB30_0_PORT2_HS_PHY_RESET			102
+#define USB30_0_MASTER_RESET				103
+#define USB30_0_SLEEP_RESET				104
+#define USB30_0_UTMI_PHY_RESET				105
+#define USB30_0_POWERON_RESET				106
+#define USB30_0_PHY_RESET				107
+#define USB30_1_MASTER_RESET				108
+#define USB30_1_SLEEP_RESET				109
+#define USB30_1_UTMI_PHY_RESET				110
+#define USB30_1_POWERON_RESET				111
+#define USB30_1_PHY_RESET				112
+#define NSSFB0_RESET					113
+#define NSSFB1_RESET					114
+#endif
diff --git a/include/dt-bindings/reset/qcom,gcc-msm8960.h b/include/dt-bindings/reset/qcom,gcc-msm8960.h
index 07edd0e65ee..47c8686955d 100644
--- a/include/dt-bindings/reset/qcom,gcc-msm8960.h
+++ b/include/dt-bindings/reset/qcom,gcc-msm8960.h
@@ -114,5 +114,21 @@
 #define SFAB_SMPSS_S_RESET				97
 #define PRNG_RESET					98
 #define RIVA_RESET					99
+#define USB_HS3_RESET					100
+#define USB_HS4_RESET					101
+#define CE3_RESET					102
+#define PCIE_EXT_PCI_RESET				103
+#define PCIE_PHY_RESET					104
+#define PCIE_PCI_RESET					105
+#define PCIE_POR_RESET					106
+#define PCIE_HCLK_RESET					107
+#define PCIE_ACLK_RESET					108
+#define CE3_H_RESET					109
+#define SFAB_CE3_M_RESET				110
+#define SFAB_CE3_S_RESET				111
+#define SATA_RESET					112
+#define CE3_SLEEP_RESET					113
+#define GSS_SLP_RESET					114
+#define GSS_RESET					115
 
 #endif
diff --git a/include/dt-bindings/reset/qcom,mmcc-apq8084.h b/include/dt-bindings/reset/qcom,mmcc-apq8084.h
new file mode 100644
index 00000000000..c1671396531
--- /dev/null
+++ b/include/dt-bindings/reset/qcom,mmcc-apq8084.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_RESET_APQ_MMCC_8084_H
+#define _DT_BINDINGS_RESET_APQ_MMCC_8084_H
+
+#define MMSS_SPDM_RESET			0
+#define MMSS_SPDM_RM_RESET		1
+#define VENUS0_RESET			2
+#define VPU_RESET			3
+#define MDSS_RESET			4
+#define AVSYNC_RESET			5
+#define CAMSS_PHY0_RESET		6
+#define CAMSS_PHY1_RESET		7
+#define CAMSS_PHY2_RESET		8
+#define CAMSS_CSI0_RESET		9
+#define CAMSS_CSI0PHY_RESET		10
+#define CAMSS_CSI0RDI_RESET		11
+#define CAMSS_CSI0PIX_RESET		12
+#define CAMSS_CSI1_RESET		13
+#define CAMSS_CSI1PHY_RESET		14
+#define CAMSS_CSI1RDI_RESET		15
+#define CAMSS_CSI1PIX_RESET		16
+#define CAMSS_CSI2_RESET		17
+#define CAMSS_CSI2PHY_RESET		18
+#define CAMSS_CSI2RDI_RESET		19
+#define CAMSS_CSI2PIX_RESET		20
+#define CAMSS_CSI3_RESET		21
+#define CAMSS_CSI3PHY_RESET		22
+#define CAMSS_CSI3RDI_RESET		23
+#define CAMSS_CSI3PIX_RESET		24
+#define CAMSS_ISPIF_RESET		25
+#define CAMSS_CCI_RESET			26
+#define CAMSS_MCLK0_RESET		27
+#define CAMSS_MCLK1_RESET		28
+#define CAMSS_MCLK2_RESET		29
+#define CAMSS_MCLK3_RESET		30
+#define CAMSS_GP0_RESET			31
+#define CAMSS_GP1_RESET			32
+#define CAMSS_TOP_RESET			33
+#define CAMSS_AHB_RESET			34
+#define CAMSS_MICRO_RESET		35
+#define CAMSS_JPEG_RESET		36
+#define CAMSS_VFE_RESET			37
+#define CAMSS_CSI_VFE0_RESET		38
+#define CAMSS_CSI_VFE1_RESET		39
+#define OXILI_RESET			40
+#define OXILICX_RESET			41
+#define OCMEMCX_RESET			42
+#define MMSS_RBCRP_RESET		43
+#define MMSSNOCAHB_RESET		44
+#define MMSSNOCAXI_RESET		45
+
+#endif
diff --git a/include/dt-bindings/reset/qcom,mmcc-msm8960.h b/include/dt-bindings/reset/qcom,mmcc-msm8960.h
index ba36ec68011..11741113a84 100644
--- a/include/dt-bindings/reset/qcom,mmcc-msm8960.h
+++ b/include/dt-bindings/reset/qcom,mmcc-msm8960.h
@@ -89,5 +89,13 @@
 #define CSI2_RESET					72
 #define CSI_RDI1_RESET					73
 #define CSI_RDI2_RESET					74
+#define GFX3D_AXI_RESET					75
+#define VCAP_AXI_RESET					76
+#define SMMU_VCAP_AHB_RESET				77
+#define VCAP_AHB_RESET					78
+#define CSI_RDI_RESET					79
+#define CSI_PIX_RESET					80
+#define VCAP_NPL_RESET					81
+#define VCAP_RESET					82
 
 #endif
diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h
index 1f16d502600..09a947e8bc8 100644
--- a/include/linux/ahci_platform.h
+++ b/include/linux/ahci_platform.h
@@ -43,9 +43,7 @@ struct ahci_host_priv *ahci_platform_get_resources(
 	struct platform_device *pdev);
 int ahci_platform_init_host(struct platform_device *pdev,
 			    struct ahci_host_priv *hpriv,
-			    const struct ata_port_info *pi_template,
-			    unsigned int force_port_map,
-			    unsigned int mask_port_map);
+			    const struct ata_port_info *pi_template);
 
 int ahci_platform_suspend_host(struct device *dev);
 int ahci_platform_resume_host(struct device *dev);
diff --git a/include/linux/amba/xilinx_dma.h b/include/linux/amba/xilinx_dma.h
new file mode 100644
index 00000000000..34b98f276ed
--- /dev/null
+++ b/include/linux/amba/xilinx_dma.h
@@ -0,0 +1,47 @@
+/*
+ * Xilinx DMA Engine drivers support header file
+ *
+ * Copyright (C) 2010-2014 Xilinx, Inc. All rights reserved.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __DMA_XILINX_DMA_H
+#define __DMA_XILINX_DMA_H
+
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+
+/**
+ * struct xilinx_vdma_config - VDMA Configuration structure
+ * @frm_dly: Frame delay
+ * @gen_lock: Whether in gen-lock mode
+ * @master: Master that it syncs to
+ * @frm_cnt_en: Enable frame count enable
+ * @park: Whether wants to park
+ * @park_frm: Frame to park on
+ * @coalesc: Interrupt coalescing threshold
+ * @delay: Delay counter
+ * @reset: Reset Channel
+ * @ext_fsync: External Frame Sync source
+ */
+struct xilinx_vdma_config {
+	int frm_dly;
+	int gen_lock;
+	int master;
+	int frm_cnt_en;
+	int park;
+	int park_frm;
+	int coalesc;
+	int delay;
+	int reset;
+	int ext_fsync;
+};
+
+int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
+					struct xilinx_vdma_config *cfg);
+
+#endif
diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h
index 8598f8eacb2..a495a959e8a 100644
--- a/include/linux/ath9k_platform.h
+++ b/include/linux/ath9k_platform.h
@@ -36,6 +36,8 @@ struct ath9k_platform_data {
 
 	int (*get_mac_revision)(void);
 	int (*external_reset)(void);
+
+	bool use_eeprom;
 };
 
 #endif /* _LINUX_ATH9K_PLATFORM_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5a645769f02..d2633ee099d 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -186,6 +186,15 @@ static inline void *bio_data(struct bio *bio)
 #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
 	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q)))
 
+/*
+ * Check if adding a bio_vec after bprv with offset would create a gap in
+ * the SG list. Most drivers don't care about this, but some do.
+ */
+static inline bool bvec_gap_to_prev(struct bio_vec *bprv, unsigned int offset)
+{
+	return offset || ((bprv->bv_offset + bprv->bv_len) & (PAGE_SIZE - 1));
+}
+
 #define bio_io_error(bio) bio_endio((bio), -EIO)
 
 /*
@@ -644,10 +653,6 @@ struct biovec_slab {
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
-
-
-#define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))
-
 #define bip_for_each_vec(bvl, bip, iter)				\
 	for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter)
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 0feedebfde4..eb726b9c576 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -42,7 +42,7 @@ struct blk_mq_hw_ctx {
 	unsigned int		nr_ctx;
 	struct blk_mq_ctx	**ctxs;
 
-	unsigned int		wait_index;
+	atomic_t		wait_index;
 
 	struct blk_mq_tags	*tags;
 
@@ -135,7 +135,7 @@ enum {
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
 
-	BLK_MQ_MAX_DEPTH	= 2048,
+	BLK_MQ_MAX_DEPTH	= 10240,
 
 	BLK_MQ_CPU_WORK_BATCH	= 8,
 };
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d8e4cea23a2..66c2167f04a 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -5,8 +5,6 @@
 #ifndef __LINUX_BLK_TYPES_H
 #define __LINUX_BLK_TYPES_H
 
-#ifdef CONFIG_BLOCK
-
 #include <linux/types.h>
 
 struct bio_set;
@@ -28,6 +26,8 @@ struct bio_vec {
 	unsigned int	bv_offset;
 };
 
+#ifdef CONFIG_BLOCK
+
 struct bvec_iter {
 	sector_t		bi_sector;	/* device address in 512 byte
 						   sectors */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3cd426e971d..8699bcf5f09 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -280,6 +280,7 @@ struct queue_limits {
 	unsigned long		seg_boundary_mask;
 
 	unsigned int		max_hw_sectors;
+	unsigned int		chunk_sectors;
 	unsigned int		max_sectors;
 	unsigned int		max_segment_size;
 	unsigned int		physical_block_size;
@@ -511,6 +512,7 @@ struct request_queue {
 #define QUEUE_FLAG_DEAD        19	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE   20	/* queue is initialized */
 #define QUEUE_FLAG_NO_SG_MERGE 21	/* don't attempt to merge SG segments*/
+#define QUEUE_FLAG_SG_GAPS     22	/* queue doesn't support SG gaps */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -795,6 +797,7 @@ extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
 extern struct request *blk_make_request(struct request_queue *, struct bio *,
 					gfp_t);
+extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern void blk_add_request_payload(struct request *rq, struct page *page,
 		unsigned int len);
@@ -910,6 +913,20 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 	return q->limits.max_sectors;
 }
 
+/*
+ * Return maximum size of a request at given offset. Only valid for
+ * file system requests.
+ */
+static inline unsigned int blk_max_size_offset(struct request_queue *q,
+					       sector_t offset)
+{
+	if (!q->limits.chunk_sectors)
+		return q->limits.max_sectors;
+
+	return q->limits.chunk_sectors -
+			(offset & (q->limits.chunk_sectors - 1));
+}
+
 static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -917,7 +934,11 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq)
 	if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC))
 		return q->limits.max_hw_sectors;
 
-	return blk_queue_get_max_sectors(q, rq->cmd_flags);
+	if (!q->limits.chunk_sectors)
+		return blk_queue_get_max_sectors(q, rq->cmd_flags);
+
+	return min(blk_max_size_offset(q, blk_rq_pos(rq)),
+			blk_queue_get_max_sectors(q, rq->cmd_flags));
 }
 
 static inline unsigned int blk_rq_count_bios(struct request *rq)
@@ -983,6 +1004,7 @@ extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
 extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
+extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_discard_sectors(struct request_queue *q,
diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index 78c6c52073a..a0875001b13 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -10,8 +10,8 @@
  *
  */
 
-#ifndef CAN_CORE_H
-#define CAN_CORE_H
+#ifndef _CAN_CORE_H
+#define _CAN_CORE_H
 
 #include <linux/can.h>
 #include <linux/skbuff.h>
@@ -58,4 +58,4 @@ extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
 extern int can_send(struct sk_buff *skb, int loop);
 extern int can_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
 
-#endif /* CAN_CORE_H */
+#endif /* !_CAN_CORE_H */
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 3ce5e526525..6992afc6ba7 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -10,8 +10,8 @@
  *
  */
 
-#ifndef CAN_DEV_H
-#define CAN_DEV_H
+#ifndef _CAN_DEV_H
+#define _CAN_DEV_H
 
 #include <linux/can.h>
 #include <linux/can/netlink.h>
@@ -132,4 +132,4 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev,
 struct sk_buff *alloc_can_err_skb(struct net_device *dev,
 				  struct can_frame **cf);
 
-#endif /* CAN_DEV_H */
+#endif /* !_CAN_DEV_H */
diff --git a/include/linux/can/led.h b/include/linux/can/led.h
index 9c1167baf27..e0475c5cbb9 100644
--- a/include/linux/can/led.h
+++ b/include/linux/can/led.h
@@ -6,8 +6,8 @@
  * published by the Free Software Foundation.
  */
 
-#ifndef CAN_LED_H
-#define CAN_LED_H
+#ifndef _CAN_LED_H
+#define _CAN_LED_H
 
 #include <linux/if.h>
 #include <linux/leds.h>
@@ -48,4 +48,4 @@ static inline void can_led_notifier_exit(void)
 
 #endif
 
-#endif
+#endif /* !_CAN_LED_H */
diff --git a/include/linux/can/platform/cc770.h b/include/linux/can/platform/cc770.h
index 7702641f87e..78b2d44f04c 100644
--- a/include/linux/can/platform/cc770.h
+++ b/include/linux/can/platform/cc770.h
@@ -1,5 +1,5 @@
-#ifndef _CAN_PLATFORM_CC770_H_
-#define _CAN_PLATFORM_CC770_H_
+#ifndef _CAN_PLATFORM_CC770_H
+#define _CAN_PLATFORM_CC770_H
 
 /* CPU Interface Register (0x02) */
 #define CPUIF_CEN	0x01	/* Clock Out Enable */
@@ -30,4 +30,4 @@ struct cc770_platform_data {
 	u8 bcr;		/* Bus Configuration Register */
 };
 
-#endif	/* !_CAN_PLATFORM_CC770_H_ */
+#endif	/* !_CAN_PLATFORM_CC770_H */
diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h
index dc029dba7a0..d44fcae274f 100644
--- a/include/linux/can/platform/mcp251x.h
+++ b/include/linux/can/platform/mcp251x.h
@@ -1,5 +1,5 @@
-#ifndef __CAN_PLATFORM_MCP251X_H__
-#define __CAN_PLATFORM_MCP251X_H__
+#ifndef _CAN_PLATFORM_MCP251X_H
+#define _CAN_PLATFORM_MCP251X_H
 
 /*
  *
@@ -18,4 +18,4 @@ struct mcp251x_platform_data {
 	unsigned long oscillator_frequency;
 };
 
-#endif /* __CAN_PLATFORM_MCP251X_H__ */
+#endif /* !_CAN_PLATFORM_MCP251X_H */
diff --git a/include/linux/can/platform/rcar_can.h b/include/linux/can/platform/rcar_can.h
new file mode 100644
index 00000000000..0f4a2f3df50
--- /dev/null
+++ b/include/linux/can/platform/rcar_can.h
@@ -0,0 +1,17 @@
+#ifndef _CAN_PLATFORM_RCAR_CAN_H_
+#define _CAN_PLATFORM_RCAR_CAN_H_
+
+#include <linux/types.h>
+
+/* Clock Select Register settings */
+enum CLKR {
+	CLKR_CLKP1 = 0,	/* Peripheral clock (clkp1) */
+	CLKR_CLKP2 = 1,	/* Peripheral clock (clkp2) */
+	CLKR_CLKEXT = 3	/* Externally input clock */
+};
+
+struct rcar_can_platform_data {
+	enum CLKR clock_select;	/* Clock source select */
+};
+
+#endif	/* !_CAN_PLATFORM_RCAR_CAN_H_ */
diff --git a/include/linux/can/platform/sja1000.h b/include/linux/can/platform/sja1000.h
index 96f8fcc78d7..93570b61ec6 100644
--- a/include/linux/can/platform/sja1000.h
+++ b/include/linux/can/platform/sja1000.h
@@ -1,5 +1,5 @@
-#ifndef _CAN_PLATFORM_SJA1000_H_
-#define _CAN_PLATFORM_SJA1000_H_
+#ifndef _CAN_PLATFORM_SJA1000_H
+#define _CAN_PLATFORM_SJA1000_H
 
 /* clock divider register */
 #define CDR_CLKOUT_MASK 0x07
@@ -32,4 +32,4 @@ struct sja1000_platform_data {
 	u8 cdr;		/* clock divider register */
 };
 
-#endif	/* !_CAN_PLATFORM_SJA1000_H_ */
+#endif	/* !_CAN_PLATFORM_SJA1000_H */
diff --git a/include/linux/can/platform/ti_hecc.h b/include/linux/can/platform/ti_hecc.h
index af17cb3f7a8..a52f47ca6c8 100644
--- a/include/linux/can/platform/ti_hecc.h
+++ b/include/linux/can/platform/ti_hecc.h
@@ -1,5 +1,5 @@
-#ifndef __CAN_PLATFORM_TI_HECC_H__
-#define __CAN_PLATFORM_TI_HECC_H__
+#ifndef _CAN_PLATFORM_TI_HECC_H
+#define _CAN_PLATFORM_TI_HECC_H
 
 /*
  * TI HECC (High End CAN Controller) driver platform header
@@ -41,4 +41,4 @@ struct ti_hecc_platform_data {
 	u32 version;
 	void (*transceiver_switch) (int);
 };
-#endif
+#endif /* !_CAN_PLATFORM_TI_HECC_H */
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index f9bbbb47266..cc00d15c610 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -7,8 +7,8 @@
  *
  */
 
-#ifndef CAN_SKB_H
-#define CAN_SKB_H
+#ifndef _CAN_SKB_H
+#define _CAN_SKB_H
 
 #include <linux/types.h>
 #include <linux/skbuff.h>
@@ -80,4 +80,4 @@ static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb)
 	return skb;
 }
 
-#endif /* CAN_SKB_H */
+#endif /* !_CAN_SKB_H */
diff --git a/include/linux/capability.h b/include/linux/capability.h
index a6ee1f9a501..84b13ad67c1 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -210,7 +210,7 @@ extern bool has_ns_capability_noaudit(struct task_struct *t,
 				      struct user_namespace *ns, int cap);
 extern bool capable(int cap);
 extern bool ns_capable(struct user_namespace *ns, int cap);
-extern bool inode_capable(const struct inode *inode, int cap);
+extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
 extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
 
 /* audit system wants to get cap info from files as well */
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 5f6db18d72e..3c97d5e9b95 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -625,6 +625,8 @@ int ceph_flags_to_mode(int flags);
 			   CEPH_CAP_LINK_EXCL |		\
 			   CEPH_CAP_XATTR_EXCL |	\
 			   CEPH_CAP_FILE_EXCL)
+#define CEPH_CAP_ANY_FILE_RD (CEPH_CAP_FILE_RD | CEPH_CAP_FILE_CACHE | \
+			      CEPH_CAP_FILE_SHARED)
 #define CEPH_CAP_ANY_FILE_WR (CEPH_CAP_FILE_WR | CEPH_CAP_FILE_BUFFER |	\
 			      CEPH_CAP_FILE_EXCL)
 #define CEPH_CAP_ANY_WR   (CEPH_CAP_ANY_EXCL | CEPH_CAP_ANY_FILE_WR)
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 2f49aa4c4f7..279b0afac1c 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -222,8 +222,6 @@ extern void ceph_copy_to_page_vector(struct page **pages,
 extern void ceph_copy_from_page_vector(struct page **pages,
 				    void *data,
 				    loff_t off, size_t len);
-extern int ceph_copy_page_vector_to_user(struct page **pages, void __user *data,
-				    loff_t off, size_t len);
 extern void ceph_zero_page_vector_range(int off, int len, struct page **pages);
 
 
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index a486f390dfb..deb47e45ac7 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -40,9 +40,9 @@ struct ceph_mon_request {
 };
 
 /*
- * ceph_mon_generic_request is being used for the statfs and poolop requests
- * which are bening done a bit differently because we need to get data back
- * to the caller
+ * ceph_mon_generic_request is being used for the statfs, poolop and
+ * mon_get_version requests which are being done a bit differently
+ * because we need to get data back to the caller
  */
 struct ceph_mon_generic_request {
 	struct kref kref;
@@ -104,10 +104,15 @@ extern int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 have);
 extern int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 have);
 
 extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc);
+extern int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
+				 unsigned long timeout);
 
 extern int ceph_monc_do_statfs(struct ceph_mon_client *monc,
 			       struct ceph_statfs *buf);
 
+extern int ceph_monc_do_get_version(struct ceph_mon_client *monc,
+				    const char *what, u64 *newest);
+
 extern int ceph_monc_open_session(struct ceph_mon_client *monc);
 
 extern int ceph_monc_validate_auth(struct ceph_mon_client *monc);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index d60904b9e50..b5223c570eb 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -21,6 +21,7 @@
 #include <linux/percpu-refcount.h>
 #include <linux/seq_file.h>
 #include <linux/kernfs.h>
+#include <linux/wait.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -47,21 +48,45 @@ enum cgroup_subsys_id {
 };
 #undef SUBSYS
 
-/* Per-subsystem/per-cgroup state maintained by the system. */
+/*
+ * Per-subsystem/per-cgroup state maintained by the system.  This is the
+ * fundamental structural building block that controllers deal with.
+ *
+ * Fields marked with "PI:" are public and immutable and may be accessed
+ * directly without synchronization.
+ */
 struct cgroup_subsys_state {
-	/* the cgroup that this css is attached to */
+	/* PI: the cgroup that this css is attached to */
 	struct cgroup *cgroup;
 
-	/* the cgroup subsystem that this css is attached to */
+	/* PI: the cgroup subsystem that this css is attached to */
 	struct cgroup_subsys *ss;
 
 	/* reference count - access via css_[try]get() and css_put() */
 	struct percpu_ref refcnt;
 
-	/* the parent css */
+	/* PI: the parent css */
 	struct cgroup_subsys_state *parent;
 
-	unsigned long flags;
+	/* siblings list anchored at the parent's ->children */
+	struct list_head sibling;
+	struct list_head children;
+
+	/*
+	 * PI: Subsys-unique ID.  0 is unused and root is always 1.  The
+	 * matching css can be looked up using css_from_id().
+	 */
+	int id;
+
+	unsigned int flags;
+
+	/*
+	 * Monotonically increasing unique serial number which defines a
+	 * uniform order among all csses.  It's guaranteed that all
+	 * ->children lists are in the ascending order of ->serial_nr and
+	 * used to allow interrupting and resuming iterations.
+	 */
+	u64 serial_nr;
 
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
@@ -70,8 +95,9 @@ struct cgroup_subsys_state {
 
 /* bits in struct cgroup_subsys_state flags field */
 enum {
-	CSS_ROOT	= (1 << 0), /* this CSS is the root of the subsystem */
+	CSS_NO_REF	= (1 << 0), /* no reference counting for this css */
 	CSS_ONLINE	= (1 << 1), /* between ->css_online() and ->css_offline() */
+	CSS_RELEASED	= (1 << 2), /* refcnt reached zero, released */
 };
 
 /**
@@ -82,8 +108,7 @@ enum {
  */
 static inline void css_get(struct cgroup_subsys_state *css)
 {
-	/* We don't need to reference count the root state */
-	if (!(css->flags & CSS_ROOT))
+	if (!(css->flags & CSS_NO_REF))
 		percpu_ref_get(&css->refcnt);
 }
 
@@ -91,35 +116,51 @@ static inline void css_get(struct cgroup_subsys_state *css)
  * css_tryget - try to obtain a reference on the specified css
  * @css: target css
  *
- * Obtain a reference on @css if it's alive.  The caller naturally needs to
- * ensure that @css is accessible but doesn't have to be holding a
+ * Obtain a reference on @css unless it already has reached zero and is
+ * being released.  This function doesn't care whether @css is on or
+ * offline.  The caller naturally needs to ensure that @css is accessible
+ * but doesn't have to be holding a reference on it - IOW, RCU protected
+ * access is good enough for this function.  Returns %true if a reference
+ * count was successfully obtained; %false otherwise.
+ */
+static inline bool css_tryget(struct cgroup_subsys_state *css)
+{
+	if (!(css->flags & CSS_NO_REF))
+		return percpu_ref_tryget(&css->refcnt);
+	return true;
+}
+
+/**
+ * css_tryget_online - try to obtain a reference on the specified css if online
+ * @css: target css
+ *
+ * Obtain a reference on @css if it's online.  The caller naturally needs
+ * to ensure that @css is accessible but doesn't have to be holding a
  * reference on it - IOW, RCU protected access is good enough for this
  * function.  Returns %true if a reference count was successfully obtained;
  * %false otherwise.
  */
-static inline bool css_tryget(struct cgroup_subsys_state *css)
+static inline bool css_tryget_online(struct cgroup_subsys_state *css)
 {
-	if (css->flags & CSS_ROOT)
-		return true;
-	return percpu_ref_tryget(&css->refcnt);
+	if (!(css->flags & CSS_NO_REF))
+		return percpu_ref_tryget_live(&css->refcnt);
+	return true;
 }
 
 /**
  * css_put - put a css reference
  * @css: target css
  *
- * Put a reference obtained via css_get() and css_tryget().
+ * Put a reference obtained via css_get() and css_tryget_online().
  */
 static inline void css_put(struct cgroup_subsys_state *css)
 {
-	if (!(css->flags & CSS_ROOT))
+	if (!(css->flags & CSS_NO_REF))
 		percpu_ref_put(&css->refcnt);
 }
 
 /* bits in struct cgroup flags field */
 enum {
-	/* Control Group is dead */
-	CGRP_DEAD,
 	/*
 	 * Control Group has previously had a child cgroup or a task,
 	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
@@ -133,48 +174,45 @@ enum {
 	 * specified at mount time and thus is implemented here.
 	 */
 	CGRP_CPUSET_CLONE_CHILDREN,
-	/* see the comment above CGRP_ROOT_SANE_BEHAVIOR for details */
-	CGRP_SANE_BEHAVIOR,
 };
 
 struct cgroup {
+	/* self css with NULL ->ss, points back to this cgroup */
+	struct cgroup_subsys_state self;
+
 	unsigned long flags;		/* "unsigned long" so bitops work */
 
 	/*
 	 * idr allocated in-hierarchy ID.
 	 *
-	 * The ID of the root cgroup is always 0, and a new cgroup
-	 * will be assigned with a smallest available ID.
+	 * ID 0 is not used, the ID of the root cgroup is always 1, and a
+	 * new cgroup will be assigned with a smallest available ID.
 	 *
 	 * Allocating/Removing ID must be protected by cgroup_mutex.
 	 */
 	int id;
 
-	/* the number of attached css's */
-	int nr_css;
-
-	atomic_t refcnt;
-
 	/*
-	 * We link our 'sibling' struct into our parent's 'children'.
-	 * Our children link their 'sibling' into our 'children'.
+	 * If this cgroup contains any tasks, it contributes one to
+	 * populated_cnt.  All children with non-zero popuplated_cnt of
+	 * their own contribute one.  The count is zero iff there's no task
+	 * in this cgroup or its subtree.
 	 */
-	struct list_head sibling;	/* my parent's children */
-	struct list_head children;	/* my children */
+	int populated_cnt;
 
-	struct cgroup *parent;		/* my parent */
 	struct kernfs_node *kn;		/* cgroup kernfs entry */
+	struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */
 
 	/*
-	 * Monotonically increasing unique serial number which defines a
-	 * uniform order among all cgroups.  It's guaranteed that all
-	 * ->children lists are in the ascending order of ->serial_nr.
-	 * It's used to allow interrupting and resuming iterations.
+	 * The bitmask of subsystems enabled on the child cgroups.
+	 * ->subtree_control is the one configured through
+	 * "cgroup.subtree_control" while ->child_subsys_mask is the
+	 * effective one which may have more subsystems enabled.
+	 * Controller knobs are made available iff it's enabled in
+	 * ->subtree_control.
 	 */
-	u64 serial_nr;
-
-	/* The bitmask of subsystems attached to this cgroup */
-	unsigned long subsys_mask;
+	unsigned int subtree_control;
+	unsigned int child_subsys_mask;
 
 	/* Private pointers for each registered subsystem */
 	struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
@@ -188,6 +226,15 @@ struct cgroup {
 	struct list_head cset_links;
 
 	/*
+	 * On the default hierarchy, a css_set for a cgroup with some
+	 * susbsys disabled will point to css's which are associated with
+	 * the closest ancestor which has the subsys enabled.  The
+	 * following lists all css_sets which point to this cgroup's css
+	 * for the given subsystem.
+	 */
+	struct list_head e_csets[CGROUP_SUBSYS_COUNT];
+
+	/*
 	 * Linked list running through all cgroups that can
 	 * potentially be reaped by the release agent. Protected by
 	 * release_list_lock
@@ -201,77 +248,17 @@ struct cgroup {
 	struct list_head pidlists;
 	struct mutex pidlist_mutex;
 
-	/* dummy css with NULL ->ss, points back to this cgroup */
-	struct cgroup_subsys_state dummy_css;
-
-	/* For css percpu_ref killing and RCU-protected deletion */
-	struct rcu_head rcu_head;
-	struct work_struct destroy_work;
+	/* used to wait for offlining of csses */
+	wait_queue_head_t offline_waitq;
 };
 
 #define MAX_CGROUP_ROOT_NAMELEN 64
 
 /* cgroup_root->flags */
 enum {
-	/*
-	 * Unfortunately, cgroup core and various controllers are riddled
-	 * with idiosyncrasies and pointless options.  The following flag,
-	 * when set, will force sane behavior - some options are forced on,
-	 * others are disallowed, and some controllers will change their
-	 * hierarchical or other behaviors.
-	 *
-	 * The set of behaviors affected by this flag are still being
-	 * determined and developed and the mount option for this flag is
-	 * prefixed with __DEVEL__.  The prefix will be dropped once we
-	 * reach the point where all behaviors are compatible with the
-	 * planned unified hierarchy, which will automatically turn on this
-	 * flag.
-	 *
-	 * The followings are the behaviors currently affected this flag.
-	 *
-	 * - Mount options "noprefix", "xattr", "clone_children",
-	 *   "release_agent" and "name" are disallowed.
-	 *
-	 * - When mounting an existing superblock, mount options should
-	 *   match.
-	 *
-	 * - Remount is disallowed.
-	 *
-	 * - rename(2) is disallowed.
-	 *
-	 * - "tasks" is removed.  Everything should be at process
-	 *   granularity.  Use "cgroup.procs" instead.
-	 *
-	 * - "cgroup.procs" is not sorted.  pids will be unique unless they
-	 *   got recycled inbetween reads.
-	 *
-	 * - "release_agent" and "notify_on_release" are removed.
-	 *   Replacement notification mechanism will be implemented.
-	 *
-	 * - "cgroup.clone_children" is removed.
-	 *
-	 * - If mount is requested with sane_behavior but without any
-	 *   subsystem, the default unified hierarchy is mounted.
-	 *
-	 * - cpuset: tasks will be kept in empty cpusets when hotplug happens
-	 *   and take masks of ancestors with non-empty cpus/mems, instead of
-	 *   being moved to an ancestor.
-	 *
-	 * - cpuset: a task can be moved into an empty cpuset, and again it
-	 *   takes masks of ancestors.
-	 *
-	 * - memcg: use_hierarchy is on by default and the cgroup file for
-	 *   the flag is not created.
-	 *
-	 * - blkcg: blk-throttle becomes properly hierarchical.
-	 */
-	CGRP_ROOT_SANE_BEHAVIOR	= (1 << 0),
-
+	CGRP_ROOT_SANE_BEHAVIOR	= (1 << 0), /* __DEVEL__sane_behavior specified */
 	CGRP_ROOT_NOPREFIX	= (1 << 1), /* mounted subsystems have no named prefix */
 	CGRP_ROOT_XATTR		= (1 << 2), /* supports extended attributes */
-
-	/* mount options live below bit 16 */
-	CGRP_ROOT_OPTION_MASK	= (1 << 16) - 1,
 };
 
 /*
@@ -282,6 +269,9 @@ enum {
 struct cgroup_root {
 	struct kernfs_root *kf_root;
 
+	/* The bitmask of subsystems attached to this hierarchy */
+	unsigned int subsys_mask;
+
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
@@ -295,7 +285,7 @@ struct cgroup_root {
 	struct list_head root_list;
 
 	/* Hierarchy-specific flags */
-	unsigned long flags;
+	unsigned int flags;
 
 	/* IDs for cgroups in this hierarchy */
 	struct idr cgroup_idr;
@@ -342,6 +332,9 @@ struct css_set {
 	 */
 	struct list_head cgrp_links;
 
+	/* the default cgroup associated with this css_set */
+	struct cgroup *dfl_cgrp;
+
 	/*
 	 * Set of subsystem states, one for each subsystem. This array is
 	 * immutable after creation apart from the init_css_set during
@@ -366,6 +359,15 @@ struct css_set {
 	struct cgroup *mg_src_cgrp;
 	struct css_set *mg_dst_cset;
 
+	/*
+	 * On the default hierarhcy, ->subsys[ssid] may point to a css
+	 * attached to an ancestor instead of the cgroup this css_set is
+	 * associated with.  The following node is anchored at
+	 * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to
+	 * iterate through all css's attached to a given cgroup.
+	 */
+	struct list_head e_cset_node[CGROUP_SUBSYS_COUNT];
+
 	/* For RCU-protected deletion */
 	struct rcu_head rcu_head;
 };
@@ -382,9 +384,11 @@ struct css_set {
 enum {
 	CFTYPE_ONLY_ON_ROOT	= (1 << 0),	/* only create on root cgrp */
 	CFTYPE_NOT_ON_ROOT	= (1 << 1),	/* don't create on root cgrp */
-	CFTYPE_INSANE		= (1 << 2),	/* don't create if sane_behavior */
 	CFTYPE_NO_PREFIX	= (1 << 3),	/* (DON'T USE FOR NEW FILES) no subsys prefix */
-	CFTYPE_ONLY_ON_DFL	= (1 << 4),	/* only on default hierarchy */
+
+	/* internal flags, do not use outside cgroup core proper */
+	__CFTYPE_ONLY_ON_DFL	= (1 << 16),	/* only on default hierarchy */
+	__CFTYPE_NOT_ON_DFL	= (1 << 17),	/* not on default hierarchy */
 };
 
 #define MAX_CFTYPE_NAME		64
@@ -405,8 +409,7 @@ struct cftype {
 
 	/*
 	 * The maximum length of string, excluding trailing nul, that can
-	 * be passed to write_string.  If < PAGE_SIZE-1, PAGE_SIZE-1 is
-	 * assumed.
+	 * be passed to write.  If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed.
 	 */
 	size_t max_write_len;
 
@@ -453,19 +456,13 @@ struct cftype {
 			 s64 val);
 
 	/*
-	 * write_string() is passed a nul-terminated kernelspace
-	 * buffer of maximum length determined by max_write_len.
-	 * Returns 0 or -ve error code.
+	 * write() is the generic write callback which maps directly to
+	 * kernfs write operation and overrides all other operations.
+	 * Maximum write size is determined by ->max_write_len.  Use
+	 * of_css/cft() to access the associated css and cft.
 	 */
-	int (*write_string)(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buffer);
-	/*
-	 * trigger() callback can be used to get some kick from the
-	 * userspace, when the actual string written is not important
-	 * at all. The private field can be used to determine the
-	 * kick type for multiplexing.
-	 */
-	int (*trigger)(struct cgroup_subsys_state *css, unsigned int event);
+	ssize_t (*write)(struct kernfs_open_file *of,
+			 char *buf, size_t nbytes, loff_t off);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lock_class_key	lockdep_key;
@@ -475,20 +472,64 @@ struct cftype {
 extern struct cgroup_root cgrp_dfl_root;
 extern struct css_set init_css_set;
 
+/**
+ * cgroup_on_dfl - test whether a cgroup is on the default hierarchy
+ * @cgrp: the cgroup of interest
+ *
+ * The default hierarchy is the v2 interface of cgroup and this function
+ * can be used to test whether a cgroup is on the default hierarchy for
+ * cases where a subsystem should behave differnetly depending on the
+ * interface version.
+ *
+ * The set of behaviors which change on the default hierarchy are still
+ * being determined and the mount option is prefixed with __DEVEL__.
+ *
+ * List of changed behaviors:
+ *
+ * - Mount options "noprefix", "xattr", "clone_children", "release_agent"
+ *   and "name" are disallowed.
+ *
+ * - When mounting an existing superblock, mount options should match.
+ *
+ * - Remount is disallowed.
+ *
+ * - rename(2) is disallowed.
+ *
+ * - "tasks" is removed.  Everything should be at process granularity.  Use
+ *   "cgroup.procs" instead.
+ *
+ * - "cgroup.procs" is not sorted.  pids will be unique unless they got
+ *   recycled inbetween reads.
+ *
+ * - "release_agent" and "notify_on_release" are removed.  Replacement
+ *   notification mechanism will be implemented.
+ *
+ * - "cgroup.clone_children" is removed.
+ *
+ * - "cgroup.subtree_populated" is available.  Its value is 0 if the cgroup
+ *   and its descendants contain no task; otherwise, 1.  The file also
+ *   generates kernfs notification which can be monitored through poll and
+ *   [di]notify when the value of the file changes.
+ *
+ * - cpuset: tasks will be kept in empty cpusets when hotplug happens and
+ *   take masks of ancestors with non-empty cpus/mems, instead of being
+ *   moved to an ancestor.
+ *
+ * - cpuset: a task can be moved into an empty cpuset, and again it takes
+ *   masks of ancestors.
+ *
+ * - memcg: use_hierarchy is on by default and the cgroup file for the flag
+ *   is not created.
+ *
+ * - blkcg: blk-throttle becomes properly hierarchical.
+ *
+ * - debug: disallowed on the default hierarchy.
+ */
 static inline bool cgroup_on_dfl(const struct cgroup *cgrp)
 {
 	return cgrp->root == &cgrp_dfl_root;
 }
 
-/*
- * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details.  This
- * function can be called as long as @cgrp is accessible.
- */
-static inline bool cgroup_sane_behavior(const struct cgroup *cgrp)
-{
-	return cgrp->root->flags & CGRP_ROOT_SANE_BEHAVIOR;
-}
-
 /* no synchronization, the result can only be used as a hint */
 static inline bool cgroup_has_tasks(struct cgroup *cgrp)
 {
@@ -504,14 +545,24 @@ static inline ino_t cgroup_ino(struct cgroup *cgrp)
 		return 0;
 }
 
-static inline struct cftype *seq_cft(struct seq_file *seq)
+/* cft/css accessors for cftype->write() operation */
+static inline struct cftype *of_cft(struct kernfs_open_file *of)
 {
-	struct kernfs_open_file *of = seq->private;
-
 	return of->kn->priv;
 }
 
-struct cgroup_subsys_state *seq_css(struct seq_file *seq);
+struct cgroup_subsys_state *of_css(struct kernfs_open_file *of);
+
+/* cft/css accessors for cftype->seq_*() operations */
+static inline struct cftype *seq_cft(struct seq_file *seq)
+{
+	return of_cft(seq->private);
+}
+
+static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+{
+	return of_css(seq->private);
+}
 
 /*
  * Name / path handling functions.  All are thin wrappers around the kernfs
@@ -541,7 +592,8 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 
 char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
 
-int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
+int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
+int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
 
 bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor);
@@ -573,6 +625,7 @@ struct cgroup_subsys {
 	int (*css_online)(struct cgroup_subsys_state *css);
 	void (*css_offline)(struct cgroup_subsys_state *css);
 	void (*css_free)(struct cgroup_subsys_state *css);
+	void (*css_reset)(struct cgroup_subsys_state *css);
 
 	int (*can_attach)(struct cgroup_subsys_state *css,
 			  struct cgroup_taskset *tset);
@@ -612,14 +665,30 @@ struct cgroup_subsys {
 	/* link to parent, protected by cgroup_lock() */
 	struct cgroup_root *root;
 
+	/* idr for css->id */
+	struct idr css_idr;
+
 	/*
 	 * List of cftypes.  Each entry is the first entry of an array
 	 * terminated by zero length name.
 	 */
 	struct list_head cfts;
 
-	/* base cftypes, automatically registered with subsys itself */
-	struct cftype *base_cftypes;
+	/*
+	 * Base cftypes which are automatically registered.  The two can
+	 * point to the same array.
+	 */
+	struct cftype *dfl_cftypes;	/* for the default hierarchy */
+	struct cftype *legacy_cftypes;	/* for the legacy hierarchies */
+
+	/*
+	 * A subsystem may depend on other subsystems.  When such subsystem
+	 * is enabled on a cgroup, the depended-upon subsystems are enabled
+	 * together if available.  Subsystems enabled due to dependency are
+	 * not visible to userland until explicitly enabled.  The following
+	 * specifies the mask of subsystems that this one depends on.
+	 */
+	unsigned int depends_on;
 };
 
 #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
@@ -627,19 +696,6 @@ struct cgroup_subsys {
 #undef SUBSYS
 
 /**
- * css_parent - find the parent css
- * @css: the target cgroup_subsys_state
- *
- * Return the parent css of @css.  This function is guaranteed to return
- * non-NULL parent as long as @css isn't the root.
- */
-static inline
-struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css)
-{
-	return css->parent;
-}
-
-/**
  * task_css_set_check - obtain a task's css_set with extra access conditions
  * @task: the task to obtain css_set for
  * @__c: extra condition expression to be passed to rcu_dereference_check()
@@ -731,14 +787,14 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
  * @pos: the css * to use as the loop cursor
  * @parent: css whose children to walk
  *
- * Walk @parent's children.  Must be called under rcu_read_lock().  A child
- * css which hasn't finished ->css_online() or already has finished
- * ->css_offline() may show up during traversal and it's each subsystem's
- * responsibility to verify that each @pos is alive.
+ * Walk @parent's children.  Must be called under rcu_read_lock().
  *
- * If a subsystem synchronizes against the parent in its ->css_online() and
- * before starting iterating, a css which finished ->css_online() is
- * guaranteed to be visible in the future iterations.
+ * If a subsystem synchronizes ->css_online() and the start of iteration, a
+ * css which finished ->css_online() is guaranteed to be visible in the
+ * future iterations and will stay visible until the last reference is put.
+ * A css which hasn't finished ->css_online() or already finished
+ * ->css_offline() may show up during traversal.  It's each subsystem's
+ * responsibility to synchronize against on/offlining.
  *
  * It is allowed to temporarily drop RCU read lock during iteration.  The
  * caller is responsible for ensuring that @pos remains accessible until
@@ -761,17 +817,16 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos);
  * @root: css whose descendants to walk
  *
  * Walk @root's descendants.  @root is included in the iteration and the
- * first node to be visited.  Must be called under rcu_read_lock().  A
- * descendant css which hasn't finished ->css_online() or already has
- * finished ->css_offline() may show up during traversal and it's each
- * subsystem's responsibility to verify that each @pos is alive.
+ * first node to be visited.  Must be called under rcu_read_lock().
  *
- * If a subsystem synchronizes against the parent in its ->css_online() and
- * before starting iterating, and synchronizes against @pos on each
- * iteration, any descendant css which finished ->css_online() is
- * guaranteed to be visible in the future iterations.
+ * If a subsystem synchronizes ->css_online() and the start of iteration, a
+ * css which finished ->css_online() is guaranteed to be visible in the
+ * future iterations and will stay visible until the last reference is put.
+ * A css which hasn't finished ->css_online() or already finished
+ * ->css_offline() may show up during traversal.  It's each subsystem's
+ * responsibility to synchronize against on/offlining.
  *
- * In other words, the following guarantees that a descendant can't escape
+ * For example, the following guarantees that a descendant can't escape
  * state updates of its ancestors.
  *
  * my_online(@css)
@@ -827,18 +882,34 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
  *
  * Similar to css_for_each_descendant_pre() but performs post-order
  * traversal instead.  @root is included in the iteration and the last
- * node to be visited.  Note that the walk visibility guarantee described
- * in pre-order walk doesn't apply the same to post-order walks.
+ * node to be visited.
+ *
+ * If a subsystem synchronizes ->css_online() and the start of iteration, a
+ * css which finished ->css_online() is guaranteed to be visible in the
+ * future iterations and will stay visible until the last reference is put.
+ * A css which hasn't finished ->css_online() or already finished
+ * ->css_offline() may show up during traversal.  It's each subsystem's
+ * responsibility to synchronize against on/offlining.
+ *
+ * Note that the walk visibility guarantee example described in pre-order
+ * walk doesn't apply the same to post-order walks.
  */
 #define css_for_each_descendant_post(pos, css)				\
 	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
 	     (pos) = css_next_descendant_post((pos), (css)))
 
+bool css_has_online_children(struct cgroup_subsys_state *css);
+
 /* A css_task_iter should be treated as an opaque object */
 struct css_task_iter {
-	struct cgroup_subsys_state	*origin_css;
-	struct list_head		*cset_link;
-	struct list_head		*task;
+	struct cgroup_subsys		*ss;
+
+	struct list_head		*cset_pos;
+	struct list_head		*cset_head;
+
+	struct list_head		*task_pos;
+	struct list_head		*tasks_head;
+	struct list_head		*mg_tasks_head;
 };
 
 void css_task_iter_start(struct cgroup_subsys_state *css,
@@ -849,8 +920,8 @@ void css_task_iter_end(struct css_task_iter *it);
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
-struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
-						struct cgroup_subsys *ss);
+struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
+						       struct cgroup_subsys *ss);
 
 #else /* !CONFIG_CGROUPS */
 
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 768fe44e19f..98c4f9b12b0 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -7,10 +7,6 @@
 SUBSYS(cpuset)
 #endif
 
-#if IS_ENABLED(CONFIG_CGROUP_DEBUG)
-SUBSYS(debug)
-#endif
-
 #if IS_ENABLED(CONFIG_CGROUP_SCHED)
 SUBSYS(cpu)
 #endif
@@ -50,6 +46,13 @@ SUBSYS(net_prio)
 #if IS_ENABLED(CONFIG_CGROUP_HUGETLB)
 SUBSYS(hugetlb)
 #endif
+
+/*
+ * The following subsystems are not supported on the default hierarchy.
+ */
+#if IS_ENABLED(CONFIG_CGROUP_DEBUG)
+SUBSYS(debug)
+#endif
 /*
  * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS.
  */
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 0c287dbbb14..411dd7eb265 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -619,5 +619,10 @@ static inline void clk_writel(u32 val, u32 __iomem *reg)
 
 #endif	/* platform dependent I/O accessors */
 
+#ifdef CONFIG_DEBUG_FS
+struct dentry *clk_debugfs_add_file(struct clk *clk, char *name, umode_t mode,
+				void *data, const struct file_operations *fops);
+#endif
+
 #endif /* CONFIG_COMMON_CLK */
 #endif /* CLK_PROVIDER_H */
diff --git a/include/linux/clk/clk-conf.h b/include/linux/clk/clk-conf.h
new file mode 100644
index 00000000000..f3050e15f83
--- /dev/null
+++ b/include/linux/clk/clk-conf.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2014 Samsung Electronics Co., Ltd.
+ * Sylwester Nawrocki <s.nawrocki@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+struct device_node;
+
+#if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK)
+int of_clk_set_defaults(struct device_node *node, bool clk_supplier);
+#else
+static inline int of_clk_set_defaults(struct device_node *node,
+				      bool clk_supplier)
+{
+	return 0;
+}
+#endif
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index 4a21a872dbb..e8d8a35034a 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -41,6 +41,8 @@
  * @idlest_reg: register containing the DPLL idle status bitfield
  * @autoidle_mask: mask of the DPLL autoidle mode bitfield in @autoidle_reg
  * @freqsel_mask: mask of the DPLL jitter correction bitfield in @control_reg
+ * @dcc_mask: mask of the DPLL DCC correction bitfield @mult_div1_reg
+ * @dcc_rate: rate atleast which DCC @dcc_mask must be set
  * @idlest_mask: mask of the DPLL idle status bitfield in @idlest_reg
  * @lpmode_mask: mask of the DPLL low-power mode bitfield in @control_reg
  * @m4xen_mask: mask of the DPLL M4X multiplier bitfield in @control_reg
@@ -86,6 +88,8 @@ struct dpll_data {
 	u32			idlest_mask;
 	u32			dco_mask;
 	u32			sddiv_mask;
+	u32			dcc_mask;
+	unsigned long		dcc_rate;
 	u32			lpmode_mask;
 	u32			m4xen_mask;
 	u8			auto_recal_bit;
@@ -94,7 +98,26 @@ struct dpll_data {
 	u8			flags;
 };
 
-struct clk_hw_omap_ops;
+struct clk_hw_omap;
+
+/**
+ * struct clk_hw_omap_ops - OMAP clk ops
+ * @find_idlest: find idlest register information for a clock
+ * @find_companion: find companion clock register information for a clock,
+ *		    basically converts CM_ICLKEN* <-> CM_FCLKEN*
+ * @allow_idle: enables autoidle hardware functionality for a clock
+ * @deny_idle: prevent autoidle hardware functionality for a clock
+ */
+struct clk_hw_omap_ops {
+	void	(*find_idlest)(struct clk_hw_omap *oclk,
+			       void __iomem **idlest_reg,
+			       u8 *idlest_bit, u8 *idlest_val);
+	void	(*find_companion)(struct clk_hw_omap *oclk,
+				  void __iomem **other_reg,
+				  u8 *other_bit);
+	void	(*allow_idle)(struct clk_hw_omap *oclk);
+	void	(*deny_idle)(struct clk_hw_omap *oclk);
+};
 
 /**
  * struct clk_hw_omap - OMAP struct clk
@@ -259,6 +282,12 @@ int omap2_dflt_clk_enable(struct clk_hw *hw);
 void omap2_dflt_clk_disable(struct clk_hw *hw);
 int omap2_dflt_clk_is_enabled(struct clk_hw *hw);
 void omap3_clk_lock_dpll5(void);
+unsigned long omap2_dpllcore_recalc(struct clk_hw *hw,
+				    unsigned long parent_rate);
+int omap2_reprogram_dpllcore(struct clk_hw *clk, unsigned long rate,
+			     unsigned long parent_rate);
+void omap2xxx_clkt_dpllcore_init(struct clk_hw *hw);
+void omap2xxx_clkt_vps_init(void);
 
 void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index);
 void ti_dt_clocks_register(struct ti_dt_clk *oclks);
@@ -278,6 +307,8 @@ int omap5xxx_dt_clk_init(void);
 int dra7xx_dt_clk_init(void);
 int am33xx_dt_clk_init(void);
 int am43xx_dt_clk_init(void);
+int omap2420_dt_clk_init(void);
+int omap2430_dt_clk_init(void);
 
 #ifdef CONFIG_OF
 void of_ti_clk_allow_autoidle_all(void);
@@ -287,6 +318,8 @@ static inline void of_ti_clk_allow_autoidle_all(void) { }
 static inline void of_ti_clk_deny_autoidle_all(void) { }
 #endif
 
+extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll;
+extern const struct clk_hw_omap_ops clkhwops_omap2430_i2chs_wait;
 extern const struct clk_hw_omap_ops clkhwops_omap3_dpll;
 extern const struct clk_hw_omap_ops clkhwops_omap4_dpllmx;
 extern const struct clk_hw_omap_ops clkhwops_wait;
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 64fdfe1cfcf..d5ad7b1118f 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -383,7 +383,9 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 /* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */
 #ifdef CONFIG_KPROBES
 # define __kprobes	__attribute__((__section__(".kprobes.text")))
+# define nokprobe_inline	__always_inline
 #else
 # define __kprobes
+# define nokprobe_inline	inline
 #endif
 #endif /* __LINUX_COMPILER_H */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 3f458896d45..8f8ae95c6e2 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -75,6 +75,7 @@ struct cpufreq_policy {
 	unsigned int		max;    /* in kHz */
 	unsigned int		cur;    /* in kHz, only needed if cpufreq
 					 * governors are used */
+	unsigned int		restore_freq; /* = policy->cur before transition */
 	unsigned int		suspend_freq; /* freq to set during suspend */
 
 	unsigned int		policy; /* see above */
@@ -221,11 +222,35 @@ struct cpufreq_driver {
 
 	/* define one out of two */
 	int	(*setpolicy)	(struct cpufreq_policy *policy);
+
+	/*
+	 * On failure, should always restore frequency to policy->restore_freq
+	 * (i.e. old freq).
+	 */
 	int	(*target)	(struct cpufreq_policy *policy,	/* Deprecated */
 				 unsigned int target_freq,
 				 unsigned int relation);
 	int	(*target_index)	(struct cpufreq_policy *policy,
 				 unsigned int index);
+	/*
+	 * Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION
+	 * unset.
+	 *
+	 * get_intermediate should return a stable intermediate frequency
+	 * platform wants to switch to and target_intermediate() should set CPU
+	 * to to that frequency, before jumping to the frequency corresponding
+	 * to 'index'. Core will take care of sending notifications and driver
+	 * doesn't have to handle them in target_intermediate() or
+	 * target_index().
+	 *
+	 * Drivers can return '0' from get_intermediate() in case they don't
+	 * wish to switch to intermediate frequency for some target frequency.
+	 * In that case core will directly call ->target_index().
+	 */
+	unsigned int (*get_intermediate)(struct cpufreq_policy *policy,
+					 unsigned int index);
+	int	(*target_intermediate)(struct cpufreq_policy *policy,
+				       unsigned int index);
 
 	/* should be defined, if possible */
 	unsigned int	(*get)	(unsigned int cpu);
@@ -457,8 +482,8 @@ extern struct cpufreq_governor cpufreq_gov_conservative;
  *********************************************************************/
 
 /* Special Values of .frequency field */
-#define CPUFREQ_ENTRY_INVALID	~0
-#define CPUFREQ_TABLE_END	~1
+#define CPUFREQ_ENTRY_INVALID	~0u
+#define CPUFREQ_TABLE_END	~1u
 /* Special Values of .flags field */
 #define CPUFREQ_BOOST_FREQ	(1 << 0)
 
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index c51a436135c..25e0df6155a 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -84,6 +84,7 @@ struct cpuidle_device {
 };
 
 DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices);
+DECLARE_PER_CPU(struct cpuidle_device, cpuidle_dev);
 
 /**
  * cpuidle_get_last_residency - retrieves the last state's residency time
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index d08e4d2a9b9..2997af6d2cc 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -142,6 +142,13 @@ static inline unsigned int cpumask_any_but(const struct cpumask *mask,
 	return 1;
 }
 
+static inline int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
+{
+	set_bit(0, cpumask_bits(dstp));
+
+	return 0;
+}
+
 #define for_each_cpu(cpu, mask)			\
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
 #define for_each_cpu_not(cpu, mask)		\
@@ -192,6 +199,7 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 
 int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *);
 int cpumask_any_but(const struct cpumask *mask, unsigned int cpu);
+int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp);
 
 /**
  * for_each_cpu - iterate over every cpu in a mask
@@ -600,7 +608,7 @@ static inline int cpulist_scnprintf(char *buf, int len,
 static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 {
 	char *nl = strchr(buf, '\n');
-	int len = nl ? nl - buf : strlen(buf);
+	unsigned int len = nl ? (unsigned int)(nl - buf) : strlen(buf);
 
 	return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
diff --git a/include/linux/crc7.h b/include/linux/crc7.h
index 1786e772d5c..d590765106f 100644
--- a/include/linux/crc7.h
+++ b/include/linux/crc7.h
@@ -2,13 +2,13 @@
 #define _LINUX_CRC7_H
 #include <linux/types.h>
 
-extern const u8 crc7_syndrome_table[256];
+extern const u8 crc7_be_syndrome_table[256];
 
-static inline u8 crc7_byte(u8 crc, u8 data)
+static inline u8 crc7_be_byte(u8 crc, u8 data)
 {
-	return crc7_syndrome_table[(crc << 1) ^ data];
+	return crc7_be_syndrome_table[crc ^ data];
 }
 
-extern u8 crc7(u8 crc, const u8 *buffer, size_t len);
+extern u8 crc7_be(u8 crc, const u8 *buffer, size_t len);
 
 #endif
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index b92eadf92d7..d45e949699e 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -710,9 +710,9 @@ static inline void ablkcipher_request_free(struct ablkcipher_request *req)
 
 static inline void ablkcipher_request_set_callback(
 	struct ablkcipher_request *req,
-	u32 flags, crypto_completion_t complete, void *data)
+	u32 flags, crypto_completion_t compl, void *data)
 {
-	req->base.complete = complete;
+	req->base.complete = compl;
 	req->base.data = data;
 	req->base.flags = flags;
 }
@@ -841,10 +841,10 @@ static inline void aead_request_free(struct aead_request *req)
 
 static inline void aead_request_set_callback(struct aead_request *req,
 					     u32 flags,
-					     crypto_completion_t complete,
+					     crypto_completion_t compl,
 					     void *data)
 {
-	req->base.complete = complete;
+	req->base.complete = compl;
 	req->base.data = data;
 	req->base.flags = flags;
 }
diff --git a/include/linux/dell-led.h b/include/linux/dell-led.h
new file mode 100644
index 00000000000..7009b8bec77
--- /dev/null
+++ b/include/linux/dell-led.h
@@ -0,0 +1,10 @@
+#ifndef __DELL_LED_H__
+#define __DELL_LED_H__
+
+enum {
+	DELL_LED_MICMUTE,
+};
+
+int dell_app_wmi_led_set(int whichled, int on);
+
+#endif
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 63da56ed979..e1707de043a 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -115,12 +115,6 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
 
 void dm_error(const char *message);
 
-/*
- * Combine device limits.
- */
-int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
-			 sector_t start, sector_t len, void *data);
-
 struct dm_dev {
 	struct block_device *bdev;
 	fmode_t mode;
@@ -132,7 +126,7 @@ struct dm_dev {
  * are opened/closed correctly.
  */
 int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
-						 struct dm_dev **result);
+		  struct dm_dev **result);
 void dm_put_device(struct dm_target *ti, struct dm_dev *d);
 
 /*
@@ -291,6 +285,7 @@ struct dm_target_io {
 	struct dm_io *io;
 	struct dm_target *ti;
 	unsigned target_bio_nr;
+	unsigned *len_ptr;
 	struct bio clone;
 };
 
@@ -401,6 +396,7 @@ int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid);
 struct gendisk *dm_disk(struct mapped_device *md);
 int dm_suspended(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
+void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
 union map_info *dm_get_rq_mapinfo(struct request *rq);
 
 struct queue_limits *dm_get_queue_limits(struct mapped_device *md);
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 72cb0ddb967..d2c5cc7c583 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -292,7 +292,7 @@ struct dma_chan_dev {
 };
 
 /**
- * enum dma_slave_buswidth - defines bus with of the DMA slave
+ * enum dma_slave_buswidth - defines bus width of the DMA slave
  * device, source or target buses
  */
 enum dma_slave_buswidth {
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 41bbf8ba4ba..efc681fd589 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -20,6 +20,7 @@
 #include <linux/ioport.h>
 #include <linux/pfn.h>
 #include <linux/pstore.h>
+#include <linux/reboot.h>
 
 #include <asm/page.h>
 
@@ -521,6 +522,8 @@ typedef efi_status_t efi_query_capsule_caps_t(efi_capsule_header_t **capsules,
 					      int *reset_type);
 typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size);
 
+void efi_native_runtime_setup(void);
+
 /*
  *  EFI Configuration Table and GUID definitions
  */
@@ -870,11 +873,13 @@ extern int __init efi_uart_console_only (void);
 extern void efi_initialize_iomem_resources(struct resource *code_resource,
 		struct resource *data_resource, struct resource *bss_resource);
 extern void efi_get_time(struct timespec *now);
-extern int efi_set_rtc_mmss(const struct timespec *now);
 extern void efi_reserve_boot_services(void);
 extern int efi_get_fdt_params(struct efi_fdt_params *params, int verbose);
 extern struct efi_memory_map memmap;
 
+extern int efi_reboot_quirk_mode;
+extern bool efi_poweroff_required(void);
+
 /* Iterate through an efi_memory_map */
 #define for_each_efi_memory_desc(m, md)					   \
 	for ((md) = (m)->map;						   \
@@ -916,7 +921,8 @@ extern int __init efi_setup_pcdp_console(char *);
 #define EFI_RUNTIME_SERVICES	3	/* Can we use runtime services? */
 #define EFI_MEMMAP		4	/* Can we use EFI memory map? */
 #define EFI_64BIT		5	/* Is the firmware 64-bit? */
-#define EFI_ARCH_1		6	/* First arch-specific bit */
+#define EFI_PARAVIRT		6	/* Access is via a paravirt interface */
+#define EFI_ARCH_1		7	/* First arch-specific bit */
 
 #ifdef CONFIG_EFI
 /*
@@ -926,11 +932,14 @@ static inline bool efi_enabled(int feature)
 {
 	return test_bit(feature, &efi.flags) != 0;
 }
+extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused);
 #else
 static inline bool efi_enabled(int feature)
 {
 	return false;
 }
+static inline void
+efi_reboot(enum reboot_mode reboot_mode, const char *__unused) {}
 #endif
 
 /*
@@ -1031,12 +1040,8 @@ struct efivar_operations {
 struct efivars {
 	/*
 	 * ->lock protects two things:
-	 * 1) ->list - adds, removals, reads, writes
-	 * 2) ops.[gs]et_variable() calls.
-	 * It must not be held when creating sysfs entries or calling kmalloc.
-	 * ops.get_next_variable() is only called from register_efivars()
-	 * or efivar_update_sysfs_entries(),
-	 * which is protected by the BKL, so that path is safe.
+	 * 1) efivarfs_list and efivars_sysfs_list
+	 * 2) ->ops calls
 	 */
 	spinlock_t lock;
 	struct kset *kset;
@@ -1161,4 +1166,46 @@ static inline void
 efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size) {}
 #endif
 
+/* prototypes shared between arch specific and generic stub code */
+
+#define pr_efi(sys_table, msg)     efi_printk(sys_table, "EFI stub: "msg)
+#define pr_efi_err(sys_table, msg) efi_printk(sys_table, "EFI stub: ERROR: "msg)
+
+void efi_printk(efi_system_table_t *sys_table_arg, char *str);
+
+void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
+	      unsigned long addr);
+
+char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
+			  efi_loaded_image_t *image, int *cmd_line_len);
+
+efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
+				efi_memory_desc_t **map,
+				unsigned long *map_size,
+				unsigned long *desc_size,
+				u32 *desc_ver,
+				unsigned long *key_ptr);
+
+efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
+			   unsigned long size, unsigned long align,
+			   unsigned long *addr);
+
+efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
+			    unsigned long size, unsigned long align,
+			    unsigned long *addr, unsigned long max);
+
+efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
+				 unsigned long *image_addr,
+				 unsigned long image_size,
+				 unsigned long alloc_size,
+				 unsigned long preferred_addr,
+				 unsigned long alignment);
+
+efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
+				  efi_loaded_image_t *image,
+				  char *cmd_line, char *option_string,
+				  unsigned long max_addr,
+				  unsigned long *load_addr,
+				  unsigned long *load_size);
+
 #endif /* _LINUX_EFI_H */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index df63bd3a8cf..45a91474487 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -133,7 +133,6 @@ extern struct request *elv_latter_request(struct request_queue *, struct request
 extern int elv_register_queue(struct request_queue *q);
 extern void elv_unregister_queue(struct request_queue *q);
 extern int elv_may_queue(struct request_queue *, int);
-extern void elv_abort_queue(struct request_queue *);
 extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *q, struct request *rq,
 			   struct bio *bio, gfp_t gfp_mask);
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 0a114d05f68..e658229fee3 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -154,13 +154,20 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
  * @reset: Reset (part of) the device, as specified by a bitmask of
  *	flags from &enum ethtool_reset_flags.  Returns a negative
  *	error code or zero.
+ * @get_rxfh_key_size: Get the size of the RX flow hash key.
+ *	Returns zero if not supported for this specific device.
  * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table.
  *	Returns zero if not supported for this specific device.
- * @get_rxfh_indir: Get the contents of the RX flow hash indirection table.
- *	Will not be called if @get_rxfh_indir_size returns zero.
+ * @get_rxfh: Get the contents of the RX flow hash indirection table and hash
+ *	key.
+ *	Will only be called if one or both of @get_rxfh_indir_size and
+ *	@get_rxfh_key_size are implemented and return non-zero.
  *	Returns a negative error code or zero.
- * @set_rxfh_indir: Set the contents of the RX flow hash indirection table.
- *	Will not be called if @get_rxfh_indir_size returns zero.
+ * @set_rxfh: Set the contents of the RX flow hash indirection table and/or
+ *	hash key.  In case only the indirection table or hash key is to be
+ *	changed, the other argument will be %NULL.
+ *	Will only be called if one or both of @get_rxfh_indir_size and
+ *	@get_rxfh_key_size are implemented and return non-zero.
  *	Returns a negative error code or zero.
  * @get_channels: Get number of channels.
  * @set_channels: Set number of channels.  Returns a negative error code or
@@ -232,9 +239,11 @@ struct ethtool_ops {
 	int	(*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *);
 	int	(*flash_device)(struct net_device *, struct ethtool_flash *);
 	int	(*reset)(struct net_device *, u32 *);
+	u32	(*get_rxfh_key_size)(struct net_device *);
 	u32	(*get_rxfh_indir_size)(struct net_device *);
-	int	(*get_rxfh_indir)(struct net_device *, u32 *);
-	int	(*set_rxfh_indir)(struct net_device *, const u32 *);
+	int	(*get_rxfh)(struct net_device *, u32 *indir, u8 *key);
+	int	(*set_rxfh)(struct net_device *, const u32 *indir,
+			    const u8 *key);
 	void	(*get_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*set_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*get_dump_flag)(struct net_device *, struct ethtool_dump *);
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index df53e1753a7..6ff0b0b42d4 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -19,6 +19,7 @@
 #define F2FS_LOG_SECTORS_PER_BLOCK	3	/* 4KB: F2FS_BLKSIZE */
 #define F2FS_BLKSIZE			4096	/* support only 4KB block */
 #define F2FS_MAX_EXTENSION		64	/* # of extension entries */
+#define F2FS_BLK_ALIGN(x)	(((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE)
 
 #define NULL_ADDR		((block_t)0)	/* used as block_t addresses */
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
@@ -75,6 +76,7 @@ struct f2fs_super_block {
 	__le16 volume_name[512];	/* volume name */
 	__le32 extension_count;		/* # of extensions below */
 	__u8 extension_list[F2FS_MAX_EXTENSION][8];	/* extension array */
+	__le32 cp_payload;
 } __packed;
 
 /*
@@ -146,6 +148,9 @@ struct f2fs_extent {
 #define ADDRS_PER_BLOCK		1018	/* Address Pointers in a Direct Block */
 #define NIDS_PER_BLOCK		1018	/* Node IDs in an Indirect Block */
 
+#define ADDRS_PER_PAGE(page, fi)	\
+	(IS_INODE(page) ? ADDRS_PER_INODE(fi) : ADDRS_PER_BLOCK)
+
 #define	NODE_DIR1_BLOCK		(DEF_ADDRS_PER_INODE + 1)
 #define	NODE_DIR2_BLOCK		(DEF_ADDRS_PER_INODE + 2)
 #define	NODE_IND1_BLOCK		(DEF_ADDRS_PER_INODE + 3)
@@ -391,6 +396,9 @@ typedef __le32	f2fs_hash_t;
 /* MAX level for dir lookup */
 #define MAX_DIR_HASH_DEPTH	63
 
+/* MAX buckets in one level of dir */
+#define MAX_DIR_BUCKETS		(1 << ((MAX_DIR_HASH_DEPTH / 2) - 1))
+
 #define SIZE_OF_DIR_ENTRY	11	/* by byte */
 #define SIZE_OF_DENTRY_BITMAP	((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \
 					BITS_PER_BYTE)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 024fd03e5d1..a7e3c48d73a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -37,21 +37,270 @@
 #define BPF_CALL	0x80	/* function call */
 #define BPF_EXIT	0x90	/* function return */
 
+/* Register numbers */
+enum {
+	BPF_REG_0 = 0,
+	BPF_REG_1,
+	BPF_REG_2,
+	BPF_REG_3,
+	BPF_REG_4,
+	BPF_REG_5,
+	BPF_REG_6,
+	BPF_REG_7,
+	BPF_REG_8,
+	BPF_REG_9,
+	BPF_REG_10,
+	__MAX_BPF_REG,
+};
+
 /* BPF has 10 general purpose 64-bit registers and stack frame. */
-#define MAX_BPF_REG	11
+#define MAX_BPF_REG	__MAX_BPF_REG
+
+/* ArgX, context and stack frame pointer register positions. Note,
+ * Arg1, Arg2, Arg3, etc are used as argument mappings of function
+ * calls in BPF_CALL instruction.
+ */
+#define BPF_REG_ARG1	BPF_REG_1
+#define BPF_REG_ARG2	BPF_REG_2
+#define BPF_REG_ARG3	BPF_REG_3
+#define BPF_REG_ARG4	BPF_REG_4
+#define BPF_REG_ARG5	BPF_REG_5
+#define BPF_REG_CTX	BPF_REG_6
+#define BPF_REG_FP	BPF_REG_10
+
+/* Additional register mappings for converted user programs. */
+#define BPF_REG_A	BPF_REG_0
+#define BPF_REG_X	BPF_REG_7
+#define BPF_REG_TMP	BPF_REG_8
 
 /* BPF program can access up to 512 bytes of stack space. */
 #define MAX_BPF_STACK	512
 
-/* Arg1, context and stack frame pointer register positions. */
-#define ARG1_REG	1
-#define CTX_REG		6
-#define FP_REG		10
+/* Helper macros for filter block array initializers. */
+
+/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
+
+#define BPF_ALU64_REG(OP, DST, SRC)				\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_X,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#define BPF_ALU32_REG(OP, DST, SRC)				\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU | BPF_OP(OP) | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
+
+#define BPF_ALU64_IMM(OP, DST, IMM)				\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+#define BPF_ALU32_IMM(OP, DST, IMM)				\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */
+
+#define BPF_ENDIAN(TYPE, DST, LEN)				\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU | BPF_END | BPF_SRC(TYPE),	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = LEN })
+
+/* Short form of mov, dst_reg = src_reg */
+
+#define BPF_MOV64_REG(DST, SRC)					\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#define BPF_MOV32_REG(DST, SRC)					\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+/* Short form of mov, dst_reg = imm32 */
+
+#define BPF_MOV64_IMM(DST, IMM)					\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+#define BPF_MOV32_IMM(DST, IMM)					\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU | BPF_MOV | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */
+
+#define BPF_MOV64_RAW(TYPE, DST, SRC, IMM)			\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE),	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+#define BPF_MOV32_RAW(TYPE, DST, SRC, IMM)			\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ALU | BPF_MOV | BPF_SRC(TYPE),	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */
+
+#define BPF_LD_ABS(SIZE, IMM)					\
+	((struct sock_filter_int) {				\
+		.code  = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS,	\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */
+
+#define BPF_LD_IND(SIZE, SRC, IMM)				\
+	((struct sock_filter_int) {				\
+		.code  = BPF_LD | BPF_SIZE(SIZE) | BPF_IND,	\
+		.dst_reg = 0,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
+
+#define BPF_LDX_MEM(SIZE, DST, SRC, OFF)			\
+	((struct sock_filter_int) {				\
+		.code  = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = src_reg */
+
+#define BPF_STX_MEM(SIZE, DST, SRC, OFF)			\
+	((struct sock_filter_int) {				\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
+
+#define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
+	((struct sock_filter_int) {				\
+		.code  = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */
+
+#define BPF_JMP_REG(OP, DST, SRC, OFF)				\
+	((struct sock_filter_int) {				\
+		.code  = BPF_JMP | BPF_OP(OP) | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
+
+#define BPF_JMP_IMM(OP, DST, IMM, OFF)				\
+	((struct sock_filter_int) {				\
+		.code  = BPF_JMP | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Function call */
+
+#define BPF_EMIT_CALL(FUNC)					\
+	((struct sock_filter_int) {				\
+		.code  = BPF_JMP | BPF_CALL,			\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = ((FUNC) - __bpf_call_base) })
+
+/* Raw code statement block */
+
+#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
+	((struct sock_filter_int) {				\
+		.code  = CODE,					\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Program exit */
+
+#define BPF_EXIT_INSN()						\
+	((struct sock_filter_int) {				\
+		.code  = BPF_JMP | BPF_EXIT,			\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#define bytes_to_bpf_size(bytes)				\
+({								\
+	int bpf_size = -EINVAL;					\
+								\
+	if (bytes == sizeof(u8))				\
+		bpf_size = BPF_B;				\
+	else if (bytes == sizeof(u16))				\
+		bpf_size = BPF_H;				\
+	else if (bytes == sizeof(u32))				\
+		bpf_size = BPF_W;				\
+	else if (bytes == sizeof(u64))				\
+		bpf_size = BPF_DW;				\
+								\
+	bpf_size;						\
+})
+
+/* Macro to invoke filter function. */
+#define SK_RUN_FILTER(filter, ctx)  (*filter->bpf_func)(ctx, filter->insnsi)
 
 struct sock_filter_int {
 	__u8	code;		/* opcode */
-	__u8	a_reg:4;	/* dest register */
-	__u8	x_reg:4;	/* source register */
+	__u8	dst_reg:4;	/* dest register */
+	__u8	src_reg:4;	/* source register */
 	__s16	off;		/* signed offset */
 	__s32	imm;		/* signed immediate constant */
 };
@@ -97,21 +346,16 @@ static inline unsigned int sk_filter_size(unsigned int proglen)
 #define sk_filter_proglen(fprog)			\
 		(fprog->len * sizeof(fprog->filter[0]))
 
-#define SK_RUN_FILTER(filter, ctx)			\
-		(*filter->bpf_func)(ctx, filter->insnsi)
-
 int sk_filter(struct sock *sk, struct sk_buff *skb);
 
-u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx,
-			      const struct sock_filter_int *insni);
-u32 sk_run_filter_int_skb(const struct sk_buff *ctx,
-			  const struct sock_filter_int *insni);
+void sk_filter_select_runtime(struct sk_filter *fp);
+void sk_filter_free(struct sk_filter *fp);
 
 int sk_convert_filter(struct sock_filter *prog, int len,
 		      struct sock_filter_int *new_prog, int *new_len);
 
 int sk_unattached_filter_create(struct sk_filter **pfp,
-				struct sock_fprog *fprog);
+				struct sock_fprog_kern *fprog);
 void sk_unattached_filter_destroy(struct sk_filter *fp);
 
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
@@ -120,11 +364,48 @@ int sk_detach_filter(struct sock *sk);
 int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
 int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
 		  unsigned int len);
-void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
 
 void sk_filter_charge(struct sock *sk, struct sk_filter *fp);
 void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 
+u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+void bpf_int_jit_compile(struct sk_filter *fp);
+
+#define BPF_ANC		BIT(15)
+
+static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
+{
+	BUG_ON(ftest->code & BPF_ANC);
+
+	switch (ftest->code) {
+	case BPF_LD | BPF_W | BPF_ABS:
+	case BPF_LD | BPF_H | BPF_ABS:
+	case BPF_LD | BPF_B | BPF_ABS:
+#define BPF_ANCILLARY(CODE)	case SKF_AD_OFF + SKF_AD_##CODE:	\
+				return BPF_ANC | SKF_AD_##CODE
+		switch (ftest->k) {
+		BPF_ANCILLARY(PROTOCOL);
+		BPF_ANCILLARY(PKTTYPE);
+		BPF_ANCILLARY(IFINDEX);
+		BPF_ANCILLARY(NLATTR);
+		BPF_ANCILLARY(NLATTR_NEST);
+		BPF_ANCILLARY(MARK);
+		BPF_ANCILLARY(QUEUE);
+		BPF_ANCILLARY(HATYPE);
+		BPF_ANCILLARY(RXHASH);
+		BPF_ANCILLARY(CPU);
+		BPF_ANCILLARY(ALU_XOR_X);
+		BPF_ANCILLARY(VLAN_TAG);
+		BPF_ANCILLARY(VLAN_TAG_PRESENT);
+		BPF_ANCILLARY(PAY_OFFSET);
+		BPF_ANCILLARY(RANDOM);
+		}
+		/* Fallthrough. */
+	default:
+		return ftest->code;
+	}
+}
+
 #ifdef CONFIG_BPF_JIT
 #include <stdarg.h>
 #include <linux/linkage.h>
@@ -144,85 +425,20 @@ static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
 }
 #else
 #include <linux/slab.h>
+
 static inline void bpf_jit_compile(struct sk_filter *fp)
 {
 }
+
 static inline void bpf_jit_free(struct sk_filter *fp)
 {
 	kfree(fp);
 }
-#endif
+#endif /* CONFIG_BPF_JIT */
 
 static inline int bpf_tell_extensions(void)
 {
 	return SKF_AD_MAX;
 }
 
-enum {
-	BPF_S_RET_K = 1,
-	BPF_S_RET_A,
-	BPF_S_ALU_ADD_K,
-	BPF_S_ALU_ADD_X,
-	BPF_S_ALU_SUB_K,
-	BPF_S_ALU_SUB_X,
-	BPF_S_ALU_MUL_K,
-	BPF_S_ALU_MUL_X,
-	BPF_S_ALU_DIV_X,
-	BPF_S_ALU_MOD_K,
-	BPF_S_ALU_MOD_X,
-	BPF_S_ALU_AND_K,
-	BPF_S_ALU_AND_X,
-	BPF_S_ALU_OR_K,
-	BPF_S_ALU_OR_X,
-	BPF_S_ALU_XOR_K,
-	BPF_S_ALU_XOR_X,
-	BPF_S_ALU_LSH_K,
-	BPF_S_ALU_LSH_X,
-	BPF_S_ALU_RSH_K,
-	BPF_S_ALU_RSH_X,
-	BPF_S_ALU_NEG,
-	BPF_S_LD_W_ABS,
-	BPF_S_LD_H_ABS,
-	BPF_S_LD_B_ABS,
-	BPF_S_LD_W_LEN,
-	BPF_S_LD_W_IND,
-	BPF_S_LD_H_IND,
-	BPF_S_LD_B_IND,
-	BPF_S_LD_IMM,
-	BPF_S_LDX_W_LEN,
-	BPF_S_LDX_B_MSH,
-	BPF_S_LDX_IMM,
-	BPF_S_MISC_TAX,
-	BPF_S_MISC_TXA,
-	BPF_S_ALU_DIV_K,
-	BPF_S_LD_MEM,
-	BPF_S_LDX_MEM,
-	BPF_S_ST,
-	BPF_S_STX,
-	BPF_S_JMP_JA,
-	BPF_S_JMP_JEQ_K,
-	BPF_S_JMP_JEQ_X,
-	BPF_S_JMP_JGE_K,
-	BPF_S_JMP_JGE_X,
-	BPF_S_JMP_JGT_K,
-	BPF_S_JMP_JGT_X,
-	BPF_S_JMP_JSET_K,
-	BPF_S_JMP_JSET_X,
-	/* Ancillary data */
-	BPF_S_ANC_PROTOCOL,
-	BPF_S_ANC_PKTTYPE,
-	BPF_S_ANC_IFINDEX,
-	BPF_S_ANC_NLATTR,
-	BPF_S_ANC_NLATTR_NEST,
-	BPF_S_ANC_MARK,
-	BPF_S_ANC_QUEUE,
-	BPF_S_ANC_HATYPE,
-	BPF_S_ANC_RXHASH,
-	BPF_S_ANC_CPU,
-	BPF_S_ANC_ALU_XOR_X,
-	BPF_S_ANC_VLAN_TAG,
-	BPF_S_ANC_VLAN_TAG_PRESENT,
-	BPF_S_ANC_PAY_OFFSET,
-};
-
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c3f46e499dd..2daccaf4b54 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -128,6 +128,10 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
 /* Write access to underlying fs */
 #define FMODE_WRITER		((__force fmode_t)0x10000)
+/* Has read method(s) */
+#define FMODE_CAN_READ          ((__force fmode_t)0x20000)
+/* Has write method(s) */
+#define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
 
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
@@ -343,8 +347,7 @@ struct address_space_operations {
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, gfp_t);
 	void (*freepage)(struct page *);
-	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
-			loff_t offset, unsigned long nr_segs);
+	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
 	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
 						void **, unsigned long *);
 	/*
@@ -830,7 +833,7 @@ static inline struct file *get_file(struct file *f)
  *
  * Lockd stuffs a "host" pointer into this.
  */
-typedef struct files_struct *fl_owner_t;
+typedef void *fl_owner_t;
 
 struct file_lock_operations {
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
@@ -1448,6 +1451,8 @@ struct block_device_operations;
 #define HAVE_COMPAT_IOCTL 1
 #define HAVE_UNLOCKED_IOCTL 1
 
+struct iov_iter;
+
 struct file_operations {
 	struct module *owner;
 	loff_t (*llseek) (struct file *, loff_t, int);
@@ -1455,6 +1460,8 @@ struct file_operations {
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
 	ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
 	ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
+	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
+	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iterate) (struct file *, struct dir_context *);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
@@ -1914,6 +1921,12 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 
 static inline int break_deleg(struct inode *inode, unsigned int mode)
 {
+	/*
+	 * Since this check is lockless, we must ensure that any refcounts
+	 * taken are done before checking inode->i_flock. Otherwise, we could
+	 * end up racing with tasks trying to set a new lease on this file.
+	 */
+	smp_mb();
 	if (inode->i_flock)
 		return __break_lease(inode, mode, FL_DELEG);
 	return 0;
@@ -2404,20 +2417,18 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
 		unsigned long size, pgoff_t pgoff);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
-extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
-extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long);
-extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
-extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
-		unsigned long *, loff_t, size_t, size_t);
+extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
+extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
+extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
+extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, loff_t);
 extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
 extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
 extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
-extern int generic_segment_checks(const struct iovec *iov,
-		unsigned long *nr_segs, size_t *count, int access_flags);
+extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
+extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 
 /* fs/block_dev.c */
-extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos);
+extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
 extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
 			int datasync);
 extern void block_sync_page(struct page *page);
@@ -2427,7 +2438,7 @@ extern ssize_t generic_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);
 extern ssize_t default_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);
-extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
+extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
 		struct file *out, loff_t *, size_t len, unsigned int flags);
@@ -2477,16 +2488,16 @@ enum {
 void dio_end_io(struct bio *bio, int error);
 
 ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
-	struct block_device *bdev, const struct iovec *iov, loff_t offset,
-	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
+	struct block_device *bdev, struct iov_iter *iter, loff_t offset,
+	get_block_t get_block, dio_iodone_t end_io,
 	dio_submit_t submit_io,	int flags);
 
 static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
-		struct inode *inode, const struct iovec *iov, loff_t offset,
-		unsigned long nr_segs, get_block_t get_block)
+		struct inode *inode, struct iov_iter *iter, loff_t offset,
+		get_block_t get_block)
 {
-	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
-				    offset, nr_segs, get_block, NULL, NULL,
+	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter,
+				    offset, get_block, NULL, NULL,
 				    DIO_LOCKING | DIO_SKIP_HOLES);
 }
 #endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 2018751cad9..6bb5e3f2a3b 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -33,8 +33,7 @@
  * features, then it must call an indirect function that
  * does. Or at least does enough to prevent any unwelcomed side effects.
  */
-#if !defined(CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST) || \
-	!ARCH_SUPPORTS_FTRACE_OPS
+#if !ARCH_SUPPORTS_FTRACE_OPS
 # define FTRACE_FORCE_LIST_FUNC 1
 #else
 # define FTRACE_FORCE_LIST_FUNC 0
@@ -62,9 +61,6 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  * set in the flags member.
  *
  * ENABLED - set/unset when ftrace_ops is registered/unregistered
- * GLOBAL  - set manualy by ftrace_ops user to denote the ftrace_ops
- *           is part of the global tracers sharing the same filter
- *           via set_ftrace_* debugfs files.
  * DYNAMIC - set when ftrace_ops is registered to denote dynamically
  *           allocated ftrace_ops which need special care
  * CONTROL - set manualy by ftrace_ops user to denote the ftrace_ops
@@ -96,15 +92,14 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
-	FTRACE_OPS_FL_GLOBAL			= 1 << 1,
-	FTRACE_OPS_FL_DYNAMIC			= 1 << 2,
-	FTRACE_OPS_FL_CONTROL			= 1 << 3,
-	FTRACE_OPS_FL_SAVE_REGS			= 1 << 4,
-	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= 1 << 5,
-	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 6,
-	FTRACE_OPS_FL_STUB			= 1 << 7,
-	FTRACE_OPS_FL_INITIALIZED		= 1 << 8,
-	FTRACE_OPS_FL_DELETED			= 1 << 9,
+	FTRACE_OPS_FL_DYNAMIC			= 1 << 1,
+	FTRACE_OPS_FL_CONTROL			= 1 << 2,
+	FTRACE_OPS_FL_SAVE_REGS			= 1 << 3,
+	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= 1 << 4,
+	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 5,
+	FTRACE_OPS_FL_STUB			= 1 << 6,
+	FTRACE_OPS_FL_INITIALIZED		= 1 << 7,
+	FTRACE_OPS_FL_DELETED			= 1 << 8,
 };
 
 /*
@@ -122,17 +117,18 @@ struct ftrace_ops {
 	ftrace_func_t			func;
 	struct ftrace_ops		*next;
 	unsigned long			flags;
-	int __percpu			*disabled;
 	void				*private;
+	int __percpu			*disabled;
 #ifdef CONFIG_DYNAMIC_FTRACE
+	int				nr_trampolines;
 	struct ftrace_hash		*notrace_hash;
 	struct ftrace_hash		*filter_hash;
+	struct ftrace_hash		*tramp_hash;
 	struct mutex			regex_lock;
+	unsigned long			trampoline;
 #endif
 };
 
-extern int function_trace_stop;
-
 /*
  * Type of the current tracing.
  */
@@ -144,32 +140,6 @@ enum ftrace_tracing_type_t {
 /* Current tracing type, default is FTRACE_TYPE_ENTER */
 extern enum ftrace_tracing_type_t ftrace_tracing_type;
 
-/**
- * ftrace_stop - stop function tracer.
- *
- * A quick way to stop the function tracer. Note this an on off switch,
- * it is not something that is recursive like preempt_disable.
- * This does not disable the calling of mcount, it only stops the
- * calling of functions from mcount.
- */
-static inline void ftrace_stop(void)
-{
-	function_trace_stop = 1;
-}
-
-/**
- * ftrace_start - start the function tracer.
- *
- * This function is the inverse of ftrace_stop. This does not enable
- * the function tracing if the function tracer is disabled. This only
- * sets the function tracer flag to continue calling the functions
- * from mcount.
- */
-static inline void ftrace_start(void)
-{
-	function_trace_stop = 0;
-}
-
 /*
  * The ftrace_ops must be a static and should also
  * be read_mostly.  These functions do modify read_mostly variables
@@ -246,8 +216,6 @@ static inline int ftrace_nr_registered_ops(void)
 }
 static inline void clear_ftrace_function(void) { }
 static inline void ftrace_kill(void) { }
-static inline void ftrace_stop(void) { }
-static inline void ftrace_start(void) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_STACK_TRACER
@@ -321,13 +289,20 @@ extern int ftrace_nr_registered_ops(void);
  * from tracing that function.
  */
 enum {
-	FTRACE_FL_ENABLED	= (1UL << 29),
+	FTRACE_FL_ENABLED	= (1UL << 31),
 	FTRACE_FL_REGS		= (1UL << 30),
-	FTRACE_FL_REGS_EN	= (1UL << 31)
+	FTRACE_FL_REGS_EN	= (1UL << 29),
+	FTRACE_FL_TRAMP		= (1UL << 28),
+	FTRACE_FL_TRAMP_EN	= (1UL << 27),
 };
 
-#define FTRACE_FL_MASK		(0x7UL << 29)
-#define FTRACE_REF_MAX		((1UL << 29) - 1)
+#define FTRACE_REF_MAX_SHIFT	27
+#define FTRACE_FL_BITS		5
+#define FTRACE_FL_MASKED_BITS	((1UL << FTRACE_FL_BITS) - 1)
+#define FTRACE_FL_MASK		(FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT)
+#define FTRACE_REF_MAX		((1UL << FTRACE_REF_MAX_SHIFT) - 1)
+
+#define ftrace_rec_count(rec)	((rec)->flags & ~FTRACE_FL_MASK)
 
 struct dyn_ftrace {
 	unsigned long		ip; /* address of mcount call-site */
@@ -366,14 +341,12 @@ enum {
  *  IGNORE           - The function is already what we want it to be
  *  MAKE_CALL        - Start tracing the function
  *  MODIFY_CALL      - Stop saving regs for the function
- *  MODIFY_CALL_REGS - Start saving regs for the function
  *  MAKE_NOP         - Stop tracing the function
  */
 enum {
 	FTRACE_UPDATE_IGNORE,
 	FTRACE_UPDATE_MAKE_CALL,
 	FTRACE_UPDATE_MODIFY_CALL,
-	FTRACE_UPDATE_MODIFY_CALL_REGS,
 	FTRACE_UPDATE_MAKE_NOP,
 };
 
@@ -404,6 +377,8 @@ int ftrace_update_record(struct dyn_ftrace *rec, int enable);
 int ftrace_test_record(struct dyn_ftrace *rec, int enable);
 void ftrace_run_stop_machine(int command);
 unsigned long ftrace_location(unsigned long ip);
+unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec);
+unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec);
 
 extern ftrace_func_t ftrace_trace_function;
 
@@ -435,6 +410,10 @@ void ftrace_modify_all_code(int command);
 #define FTRACE_ADDR ((unsigned long)ftrace_caller)
 #endif
 
+#ifndef FTRACE_GRAPH_ADDR
+#define FTRACE_GRAPH_ADDR ((unsigned long)ftrace_graph_caller)
+#endif
+
 #ifndef FTRACE_REGS_ADDR
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 # define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller)
@@ -443,6 +422,16 @@ void ftrace_modify_all_code(int command);
 #endif
 #endif
 
+/*
+ * If an arch would like functions that are only traced
+ * by the function graph tracer to jump directly to its own
+ * trampoline, then they can define FTRACE_GRAPH_TRAMP_ADDR
+ * to be that address to jump to.
+ */
+#ifndef FTRACE_GRAPH_TRAMP_ADDR
+#define FTRACE_GRAPH_TRAMP_ADDR ((unsigned long) 0)
+#endif
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern void ftrace_graph_caller(void);
 extern int ftrace_enable_ftrace_graph_caller(void);
@@ -740,6 +729,7 @@ extern char __irqentry_text_end[];
 extern int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 				trace_func_graph_ent_t entryfunc);
 
+extern bool ftrace_graph_is_dead(void);
 extern void ftrace_graph_stop(void);
 
 /* The current handlers in use */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index d16da3e53bc..06c6faa9e5c 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -38,6 +38,9 @@ const char *ftrace_print_symbols_seq_u64(struct trace_seq *p,
 								 *symbol_array);
 #endif
 
+const char *ftrace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr,
+				     unsigned int bitmask_size);
+
 const char *ftrace_print_hex_seq(struct trace_seq *p,
 				 const unsigned char *buf, int len);
 
@@ -269,7 +272,6 @@ struct ftrace_event_call {
 	struct trace_event	event;
 	const char		*print_fmt;
 	struct event_filter	*filter;
-	struct list_head	*files;
 	void			*mod;
 	void			*data;
 	/*
@@ -401,8 +403,6 @@ enum event_trigger_type {
 	ETT_EVENT_ENABLE	= (1 << 3),
 };
 
-extern void destroy_preds(struct ftrace_event_file *file);
-extern void destroy_call_preds(struct ftrace_event_call *call);
 extern int filter_match_preds(struct event_filter *filter, void *rec);
 
 extern int filter_check_discard(struct ftrace_event_file *file, void *rec,
diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h
index a7e977ff4ab..8b622468952 100644
--- a/include/linux/gpio_keys.h
+++ b/include/linux/gpio_keys.h
@@ -3,29 +3,53 @@
 
 struct device;
 
+/**
+ * struct gpio_keys_button - configuration parameters
+ * @code:		input event code (KEY_*, SW_*)
+ * @gpio:		%-1 if this key does not support gpio
+ * @active_low:		%true indicates that button is considered
+ *			depressed when gpio is low
+ * @desc:		label that will be attached to button's gpio
+ * @type:		input event type (%EV_KEY, %EV_SW, %EV_ABS)
+ * @wakeup:		configure the button as a wake-up source
+ * @debounce_interval:	debounce ticks interval in msecs
+ * @can_disable:	%true indicates that userspace is allowed to
+ *			disable button via sysfs
+ * @value:		axis value for %EV_ABS
+ * @irq:		Irq number in case of interrupt keys
+ */
 struct gpio_keys_button {
-	/* Configuration parameters */
-	unsigned int code;	/* input event code (KEY_*, SW_*) */
-	int gpio;		/* -1 if this key does not support gpio */
+	unsigned int code;
+	int gpio;
 	int active_low;
 	const char *desc;
-	unsigned int type;	/* input event type (EV_KEY, EV_SW, EV_ABS) */
-	int wakeup;		/* configure the button as a wake-up source */
-	int debounce_interval;	/* debounce ticks interval in msecs */
+	unsigned int type;
+	int wakeup;
+	int debounce_interval;
 	bool can_disable;
-	int value;		/* axis value for EV_ABS */
-	unsigned int irq;	/* Irq number in case of interrupt keys */
+	int value;
+	unsigned int irq;
 };
 
+/**
+ * struct gpio_keys_platform_data - platform data for gpio_keys driver
+ * @buttons:		pointer to array of &gpio_keys_button structures
+ *			describing buttons attached to the device
+ * @nbuttons:		number of elements in @buttons array
+ * @poll_interval:	polling interval in msecs - for polling driver only
+ * @rep:		enable input subsystem auto repeat
+ * @enable:		platform hook for enabling the device
+ * @disable:		platform hook for disabling the device
+ * @name:		input device name
+ */
 struct gpio_keys_platform_data {
 	struct gpio_keys_button *buttons;
 	int nbuttons;
-	unsigned int poll_interval;	/* polling interval in msecs -
-					   for polling driver only */
-	unsigned int rep:1;		/* enable input subsystem auto repeat */
+	unsigned int poll_interval;
+	unsigned int rep:1;
 	int (*enable)(struct device *dev);
 	void (*disable)(struct device *dev);
-	const char *name;		/* input device name */
+	const char *name;
 };
 
 #endif
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 255cd5cc075..a23c096b308 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -80,6 +80,7 @@ int dequeue_hwpoisoned_huge_page(struct page *page);
 bool isolate_huge_page(struct page *page, struct list_head *list);
 void putback_active_hugepage(struct page *page);
 bool is_hugepage_active(struct page *page);
+void free_huge_page(struct page *page);
 
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
diff --git a/include/linux/i2c/atmel_mxt_ts.h b/include/linux/i2c/atmel_mxt_ts.h
index 99e379b7439..3891dc1de21 100644
--- a/include/linux/i2c/atmel_mxt_ts.h
+++ b/include/linux/i2c/atmel_mxt_ts.h
@@ -15,35 +15,14 @@
 
 #include <linux/types.h>
 
-/* For key_map array */
-#define MXT_NUM_GPIO		4
-
-/* Orient */
-#define MXT_NORMAL		0x0
-#define MXT_DIAGONAL		0x1
-#define MXT_HORIZONTAL_FLIP	0x2
-#define MXT_ROTATED_90_COUNTER	0x3
-#define MXT_VERTICAL_FLIP	0x4
-#define MXT_ROTATED_90		0x5
-#define MXT_ROTATED_180		0x6
-#define MXT_DIAGONAL_COUNTER	0x7
-
 /* The platform data for the Atmel maXTouch touchscreen driver */
 struct mxt_platform_data {
 	const u8 *config;
 	size_t config_length;
-
-	unsigned int x_line;
-	unsigned int y_line;
-	unsigned int x_size;
-	unsigned int y_size;
-	unsigned int blen;
-	unsigned int threshold;
-	unsigned int voltage;
-	unsigned char orient;
+	u32 config_crc;
 	unsigned long irqflags;
-	bool is_tp;
-	const unsigned int key_map[MXT_NUM_GPIO];
+	u8 t19_num_keys;
+	const unsigned int *t19_keymap;
 };
 
 #endif /* __LINUX_ATMEL_MXT_TS_H */
diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h
index d2b16704624..8cfb50f3852 100644
--- a/include/linux/i2c/twl.h
+++ b/include/linux/i2c/twl.h
@@ -498,7 +498,10 @@ static inline int twl6030_mmc_card_detect(struct device *dev, int slot)
 #define RES_GRP_ALL		0x7	/* All resource groups */
 
 #define RES_TYPE2_R0		0x0
+#define RES_TYPE2_R1		0x1
+#define RES_TYPE2_R2		0x2
 
+#define RES_TYPE_R0		0x0
 #define RES_TYPE_ALL		0x7
 
 /* Resource states */
@@ -671,6 +674,7 @@ struct twl4030_power_data {
 	struct twl4030_script **scripts;
 	unsigned num;
 	struct twl4030_resconfig *resource_config;
+	struct twl4030_resconfig *board_config;
 #define TWL4030_RESCONFIG_UNDEF	((u8)-1)
 	bool use_poweroff;	/* Board is wired for TWL poweroff */
 };
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index f194ccb8539..6bff13f7405 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1711,6 +1711,7 @@ enum ieee80211_eid {
 	WLAN_EID_RRM_ENABLED_CAPABILITIES = 70,
 	WLAN_EID_MULTIPLE_BSSID = 71,
 	WLAN_EID_BSS_COEX_2040 = 72,
+	WLAN_EID_BSS_INTOLERANT_CHL_REPORT = 73,
 	WLAN_EID_OVERLAP_BSS_SCAN_PARAM = 74,
 	WLAN_EID_RIC_DESCRIPTOR = 75,
 	WLAN_EID_MMIE = 76,
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 1085ffeef95..fd22789d7b2 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -16,9 +16,28 @@
 #include <linux/netdevice.h>
 #include <uapi/linux/if_bridge.h>
 
+struct br_ip {
+	union {
+		__be32	ip4;
+#if IS_ENABLED(CONFIG_IPV6)
+		struct in6_addr ip6;
+#endif
+	} u;
+	__be16		proto;
+	__u16           vid;
+};
+
+struct br_ip_list {
+	struct list_head list;
+	struct br_ip addr;
+};
+
 extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
 
 typedef int br_should_route_hook_t(struct sk_buff *skb);
 extern br_should_route_hook_t __rcu *br_should_route_hook;
+int br_multicast_list_adjacent(struct net_device *dev,
+			       struct list_head *br_ip_list);
+bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto);
 
 #endif
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index a86784dec3d..119130e9298 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -10,8 +10,9 @@ struct ifla_vf_info {
 	__u8 mac[32];
 	__u32 vlan;
 	__u32 qos;
-	__u32 tx_rate;
 	__u32 spoofchk;
 	__u32 linkstate;
+	__u32 min_tx_rate;
+	__u32 max_tx_rate;
 };
 #endif /* _LINUX_IF_LINK_H */
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index a9a53b12397..6b2c7cf352a 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -57,6 +57,9 @@ struct macvlan_dev {
 	netdev_features_t	tap_features;
 	int			minor;
 	int			nest_level;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	struct netpoll		*netpoll;
+#endif
 };
 
 static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b2acc4a1b13..4967916fe4a 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -106,7 +106,7 @@ struct vlan_pcpu_stats {
 
 #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
 
-extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev,
+extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev,
 					       __be16 vlan_proto, u16 vlan_id);
 extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
 extern u16 vlan_dev_vlan_id(const struct net_device *dev);
@@ -206,7 +206,7 @@ static inline int vlan_get_encap_level(struct net_device *dev)
 }
 #else
 static inline struct net_device *
-__vlan_find_dev_deep(struct net_device *real_dev,
+__vlan_find_dev_deep_rcu(struct net_device *real_dev,
 		     __be16 vlan_proto, u16 vlan_id)
 {
 	return NULL;
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 6df7f9fe0d0..2bb4c4f3531 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -102,12 +102,6 @@ extern struct group_info init_groups;
 #define INIT_IDS
 #endif
 
-#ifdef CONFIG_RCU_BOOST
-#define INIT_TASK_RCU_BOOST()						\
-	.rcu_boost_mutex = NULL,
-#else
-#define INIT_TASK_RCU_BOOST()
-#endif
 #ifdef CONFIG_TREE_PREEMPT_RCU
 #define INIT_TASK_RCU_TREE_PREEMPT()					\
 	.rcu_blocked_node = NULL,
@@ -119,8 +113,7 @@ extern struct group_info init_groups;
 	.rcu_read_lock_nesting = 0,					\
 	.rcu_read_unlock_special = 0,					\
 	.rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),		\
-	INIT_TASK_RCU_TREE_PREEMPT()					\
-	INIT_TASK_RCU_BOOST()
+	INIT_TASK_RCU_TREE_PREEMPT()
 #else
 #define INIT_TASK_RCU_PREEMPT(tsk)
 #endif
diff --git a/include/linux/input-polldev.h b/include/linux/input-polldev.h
index ce0b72464eb..2465182670d 100644
--- a/include/linux/input-polldev.h
+++ b/include/linux/input-polldev.h
@@ -48,9 +48,12 @@ struct input_polled_dev {
 
 /* private: */
 	struct delayed_work work;
+
+	bool devres_managed;
 };
 
 struct input_polled_dev *input_allocate_polled_device(void);
+struct input_polled_dev *devm_input_allocate_polled_device(struct device *dev);
 void input_free_polled_device(struct input_polled_dev *dev);
 int input_register_polled_device(struct input_polled_dev *dev);
 void input_unregister_polled_device(struct input_polled_dev *dev);
diff --git a/include/linux/input/pixcir_ts.h b/include/linux/input/pixcir_ts.h
index 7163d91c037..160cf353aa3 100644
--- a/include/linux/input/pixcir_ts.h
+++ b/include/linux/input/pixcir_ts.h
@@ -1,10 +1,52 @@
 #ifndef	_PIXCIR_I2C_TS_H
 #define	_PIXCIR_I2C_TS_H
 
+/*
+ * Register map
+ */
+#define PIXCIR_REG_POWER_MODE	51
+#define PIXCIR_REG_INT_MODE	52
+
+/*
+ * Power modes:
+ * active: max scan speed
+ * idle: lower scan speed with automatic transition to active on touch
+ * halt: datasheet says sleep but this is more like halt as the chip
+ *       clocks are cut and it can only be brought out of this mode
+ *	 using the RESET pin.
+ */
+enum pixcir_power_mode {
+	PIXCIR_POWER_ACTIVE,
+	PIXCIR_POWER_IDLE,
+	PIXCIR_POWER_HALT,
+};
+
+#define PIXCIR_POWER_MODE_MASK	0x03
+#define PIXCIR_POWER_ALLOW_IDLE (1UL << 2)
+
+/*
+ * Interrupt modes:
+ * periodical: interrupt is asserted periodicaly
+ * diff coordinates: interrupt is asserted when coordinates change
+ * level on touch: interrupt level asserted during touch
+ * pulse on touch: interrupt pulse asserted druing touch
+ *
+ */
+enum pixcir_int_mode {
+	PIXCIR_INT_PERIODICAL,
+	PIXCIR_INT_DIFF_COORD,
+	PIXCIR_INT_LEVEL_TOUCH,
+	PIXCIR_INT_PULSE_TOUCH,
+};
+
+#define PIXCIR_INT_MODE_MASK	0x03
+#define PIXCIR_INT_ENABLE	(1UL << 3)
+#define PIXCIR_INT_POL_HIGH	(1UL << 2)
+
 struct pixcir_ts_platform_data {
-	int (*attb_read_val)(void);
 	int x_max;
 	int y_max;
+	int gpio_attb;		/* GPIO connected to ATTB line */
 };
 
 #endif
diff --git a/include/linux/input/touchscreen.h b/include/linux/input/touchscreen.h
new file mode 100644
index 00000000000..08a5ef6e8f2
--- /dev/null
+++ b/include/linux/input/touchscreen.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (c) 2014 Sebastian Reichel <sre@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef _TOUCHSCREEN_H
+#define _TOUCHSCREEN_H
+
+#include <linux/input.h>
+
+#ifdef CONFIG_OF
+void touchscreen_parse_of_params(struct input_dev *dev);
+#else
+static inline void touchscreen_parse_of_params(struct input_dev *dev)
+{
+}
+#endif
+
+#endif
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 19ae05d4b8e..bf9422c3aef 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -33,6 +33,11 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *))
 #define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), }
 
 bool irq_work_queue(struct irq_work *work);
+
+#ifdef CONFIG_SMP
+bool irq_work_queue_on(struct irq_work *work, int cpu);
+#endif
+
 void irq_work_run(void);
 void irq_work_sync(struct irq_work *work);
 
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
new file mode 100644
index 00000000000..03a4ea37ba8
--- /dev/null
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -0,0 +1,200 @@
+/*
+ * Copyright (C) 2013, 2014 ARM Limited, All Rights Reserved.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __LINUX_IRQCHIP_ARM_GIC_V3_H
+#define __LINUX_IRQCHIP_ARM_GIC_V3_H
+
+#include <asm/sysreg.h>
+
+/*
+ * Distributor registers. We assume we're running non-secure, with ARE
+ * being set. Secure-only and non-ARE registers are not described.
+ */
+#define GICD_CTLR			0x0000
+#define GICD_TYPER			0x0004
+#define GICD_IIDR			0x0008
+#define GICD_STATUSR			0x0010
+#define GICD_SETSPI_NSR			0x0040
+#define GICD_CLRSPI_NSR			0x0048
+#define GICD_SETSPI_SR			0x0050
+#define GICD_CLRSPI_SR			0x0058
+#define GICD_SEIR			0x0068
+#define GICD_ISENABLER			0x0100
+#define GICD_ICENABLER			0x0180
+#define GICD_ISPENDR			0x0200
+#define GICD_ICPENDR			0x0280
+#define GICD_ISACTIVER			0x0300
+#define GICD_ICACTIVER			0x0380
+#define GICD_IPRIORITYR			0x0400
+#define GICD_ICFGR			0x0C00
+#define GICD_IROUTER			0x6000
+#define GICD_PIDR2			0xFFE8
+
+#define GICD_CTLR_RWP			(1U << 31)
+#define GICD_CTLR_ARE_NS		(1U << 4)
+#define GICD_CTLR_ENABLE_G1A		(1U << 1)
+#define GICD_CTLR_ENABLE_G1		(1U << 0)
+
+#define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
+#define GICD_IROUTER_SPI_MODE_ANY	(1U << 31)
+
+#define GIC_PIDR2_ARCH_MASK		0xf0
+#define GIC_PIDR2_ARCH_GICv3		0x30
+#define GIC_PIDR2_ARCH_GICv4		0x40
+
+/*
+ * Re-Distributor registers, offsets from RD_base
+ */
+#define GICR_CTLR			GICD_CTLR
+#define GICR_IIDR			0x0004
+#define GICR_TYPER			0x0008
+#define GICR_STATUSR			GICD_STATUSR
+#define GICR_WAKER			0x0014
+#define GICR_SETLPIR			0x0040
+#define GICR_CLRLPIR			0x0048
+#define GICR_SEIR			GICD_SEIR
+#define GICR_PROPBASER			0x0070
+#define GICR_PENDBASER			0x0078
+#define GICR_INVLPIR			0x00A0
+#define GICR_INVALLR			0x00B0
+#define GICR_SYNCR			0x00C0
+#define GICR_MOVLPIR			0x0100
+#define GICR_MOVALLR			0x0110
+#define GICR_PIDR2			GICD_PIDR2
+
+#define GICR_WAKER_ProcessorSleep	(1U << 1)
+#define GICR_WAKER_ChildrenAsleep	(1U << 2)
+
+/*
+ * Re-Distributor registers, offsets from SGI_base
+ */
+#define GICR_ISENABLER0			GICD_ISENABLER
+#define GICR_ICENABLER0			GICD_ICENABLER
+#define GICR_ISPENDR0			GICD_ISPENDR
+#define GICR_ICPENDR0			GICD_ICPENDR
+#define GICR_ISACTIVER0			GICD_ISACTIVER
+#define GICR_ICACTIVER0			GICD_ICACTIVER
+#define GICR_IPRIORITYR0		GICD_IPRIORITYR
+#define GICR_ICFGR0			GICD_ICFGR
+
+#define GICR_TYPER_VLPIS		(1U << 1)
+#define GICR_TYPER_LAST			(1U << 4)
+
+/*
+ * CPU interface registers
+ */
+#define ICC_CTLR_EL1_EOImode_drop_dir	(0U << 1)
+#define ICC_CTLR_EL1_EOImode_drop	(1U << 1)
+#define ICC_SRE_EL1_SRE			(1U << 0)
+
+/*
+ * Hypervisor interface registers (SRE only)
+ */
+#define ICH_LR_VIRTUAL_ID_MASK		((1UL << 32) - 1)
+
+#define ICH_LR_EOI			(1UL << 41)
+#define ICH_LR_GROUP			(1UL << 60)
+#define ICH_LR_STATE			(3UL << 62)
+#define ICH_LR_PENDING_BIT		(1UL << 62)
+#define ICH_LR_ACTIVE_BIT		(1UL << 63)
+
+#define ICH_MISR_EOI			(1 << 0)
+#define ICH_MISR_U			(1 << 1)
+
+#define ICH_HCR_EN			(1 << 0)
+#define ICH_HCR_UIE			(1 << 1)
+
+#define ICH_VMCR_CTLR_SHIFT		0
+#define ICH_VMCR_CTLR_MASK		(0x21f << ICH_VMCR_CTLR_SHIFT)
+#define ICH_VMCR_BPR1_SHIFT		18
+#define ICH_VMCR_BPR1_MASK		(7 << ICH_VMCR_BPR1_SHIFT)
+#define ICH_VMCR_BPR0_SHIFT		21
+#define ICH_VMCR_BPR0_MASK		(7 << ICH_VMCR_BPR0_SHIFT)
+#define ICH_VMCR_PMR_SHIFT		24
+#define ICH_VMCR_PMR_MASK		(0xffUL << ICH_VMCR_PMR_SHIFT)
+
+#define ICC_EOIR1_EL1			sys_reg(3, 0, 12, 12, 1)
+#define ICC_IAR1_EL1			sys_reg(3, 0, 12, 12, 0)
+#define ICC_SGI1R_EL1			sys_reg(3, 0, 12, 11, 5)
+#define ICC_PMR_EL1			sys_reg(3, 0, 4, 6, 0)
+#define ICC_CTLR_EL1			sys_reg(3, 0, 12, 12, 4)
+#define ICC_SRE_EL1			sys_reg(3, 0, 12, 12, 5)
+#define ICC_GRPEN1_EL1			sys_reg(3, 0, 12, 12, 7)
+
+#define ICC_IAR1_EL1_SPURIOUS		0x3ff
+
+#define ICC_SRE_EL2			sys_reg(3, 4, 12, 9, 5)
+
+#define ICC_SRE_EL2_SRE			(1 << 0)
+#define ICC_SRE_EL2_ENABLE		(1 << 3)
+
+/*
+ * System register definitions
+ */
+#define ICH_VSEIR_EL2			sys_reg(3, 4, 12, 9, 4)
+#define ICH_HCR_EL2			sys_reg(3, 4, 12, 11, 0)
+#define ICH_VTR_EL2			sys_reg(3, 4, 12, 11, 1)
+#define ICH_MISR_EL2			sys_reg(3, 4, 12, 11, 2)
+#define ICH_EISR_EL2			sys_reg(3, 4, 12, 11, 3)
+#define ICH_ELSR_EL2			sys_reg(3, 4, 12, 11, 5)
+#define ICH_VMCR_EL2			sys_reg(3, 4, 12, 11, 7)
+
+#define __LR0_EL2(x)			sys_reg(3, 4, 12, 12, x)
+#define __LR8_EL2(x)			sys_reg(3, 4, 12, 13, x)
+
+#define ICH_LR0_EL2			__LR0_EL2(0)
+#define ICH_LR1_EL2			__LR0_EL2(1)
+#define ICH_LR2_EL2			__LR0_EL2(2)
+#define ICH_LR3_EL2			__LR0_EL2(3)
+#define ICH_LR4_EL2			__LR0_EL2(4)
+#define ICH_LR5_EL2			__LR0_EL2(5)
+#define ICH_LR6_EL2			__LR0_EL2(6)
+#define ICH_LR7_EL2			__LR0_EL2(7)
+#define ICH_LR8_EL2			__LR8_EL2(0)
+#define ICH_LR9_EL2			__LR8_EL2(1)
+#define ICH_LR10_EL2			__LR8_EL2(2)
+#define ICH_LR11_EL2			__LR8_EL2(3)
+#define ICH_LR12_EL2			__LR8_EL2(4)
+#define ICH_LR13_EL2			__LR8_EL2(5)
+#define ICH_LR14_EL2			__LR8_EL2(6)
+#define ICH_LR15_EL2			__LR8_EL2(7)
+
+#define __AP0Rx_EL2(x)			sys_reg(3, 4, 12, 8, x)
+#define ICH_AP0R0_EL2			__AP0Rx_EL2(0)
+#define ICH_AP0R1_EL2			__AP0Rx_EL2(1)
+#define ICH_AP0R2_EL2			__AP0Rx_EL2(2)
+#define ICH_AP0R3_EL2			__AP0Rx_EL2(3)
+
+#define __AP1Rx_EL2(x)			sys_reg(3, 4, 12, 9, x)
+#define ICH_AP1R0_EL2			__AP1Rx_EL2(0)
+#define ICH_AP1R1_EL2			__AP1Rx_EL2(1)
+#define ICH_AP1R2_EL2			__AP1Rx_EL2(2)
+#define ICH_AP1R3_EL2			__AP1Rx_EL2(3)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+
+static inline void gic_write_eoir(u64 irq)
+{
+	asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" (irq));
+	isb();
+}
+
+#endif
+
+#endif
diff --git a/include/linux/isdn/capiutil.h b/include/linux/isdn/capiutil.h
index 5a52f2c94f3..44bd6046e6e 100644
--- a/include/linux/isdn/capiutil.h
+++ b/include/linux/isdn/capiutil.h
@@ -164,11 +164,6 @@ unsigned capi_cmsg_header(_cmsg * cmsg, __u16 _ApplId,
 			  __u8 _Command, __u8 _Subcommand,
 			  __u16 _Messagenumber, __u32 _Controller);
 
-/*
- * capi_info2str generated a readable string for Capi2.0 reasons.
- */
-char *capi_info2str(__u16 reason);
-
 /*-----------------------------------------------------------------------*/
 
 /*
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 17aa1cce6f8..30faf797c2c 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -91,6 +91,7 @@ struct kernfs_elem_attr {
 	const struct kernfs_ops	*ops;
 	struct kernfs_open_node	*open;
 	loff_t			size;
+	struct kernfs_node	*notify_next;	/* for kernfs_notify() */
 };
 
 /*
@@ -304,6 +305,7 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
 			       struct kernfs_root *root, unsigned long magic,
 			       bool *new_sb_created, const void *ns);
 void kernfs_kill_sb(struct super_block *sb);
+struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns);
 
 void kernfs_init(void);
 
diff --git a/include/linux/key.h b/include/linux/key.h
index 3ae45f09589..017b0826642 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -309,6 +309,17 @@ static inline key_serial_t key_serial(const struct key *key)
 
 extern void key_set_timeout(struct key *, unsigned);
 
+/*
+ * The permissions required on a key that we're looking up.
+ */
+#define	KEY_NEED_VIEW	0x01	/* Require permission to view attributes */
+#define	KEY_NEED_READ	0x02	/* Require permission to read content */
+#define	KEY_NEED_WRITE	0x04	/* Require permission to update / modify */
+#define	KEY_NEED_SEARCH	0x08	/* Require permission to search (keyring) or find (key) */
+#define	KEY_NEED_LINK	0x10	/* Require permission to link */
+#define	KEY_NEED_SETATTR 0x20	/* Require permission to change attributes */
+#define	KEY_NEED_ALL	0x3f	/* All the above permissions */
+
 /**
  * key_is_instantiated - Determine if a key has been positively instantiated
  * @key: The key to check.
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 925eaf28fca..f7296e57d61 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -205,10 +205,10 @@ struct kretprobe_blackpoint {
 	void *addr;
 };
 
-struct kprobe_blackpoint {
-	const char *name;
+struct kprobe_blacklist_entry {
+	struct list_head list;
 	unsigned long start_addr;
-	unsigned long range;
+	unsigned long end_addr;
 };
 
 #ifdef CONFIG_KPROBES
@@ -265,6 +265,7 @@ extern void arch_disarm_kprobe(struct kprobe *p);
 extern int arch_init_kprobes(void);
 extern void show_registers(struct pt_regs *regs);
 extern void kprobes_inc_nmissed_count(struct kprobe *p);
+extern bool arch_within_kprobe_blacklist(unsigned long addr);
 
 struct kprobe_insn_cache {
 	struct mutex mutex;
@@ -355,7 +356,7 @@ static inline void reset_current_kprobe(void)
 
 static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
 {
-	return (&__get_cpu_var(kprobe_ctlblk));
+	return this_cpu_ptr(&kprobe_ctlblk);
 }
 
 int register_kprobe(struct kprobe *p);
@@ -476,4 +477,18 @@ static inline int enable_jprobe(struct jprobe *jp)
 	return enable_kprobe(&jp->kp);
 }
 
+#ifdef CONFIG_KPROBES
+/*
+ * Blacklist ganerating macro. Specify functions which is not probed
+ * by using this macro.
+ */
+#define __NOKPROBE_SYMBOL(fname)			\
+static unsigned long __used				\
+	__attribute__((section("_kprobe_blacklist")))	\
+	_kbl_addr_##fname = (unsigned long)fname;
+#define NOKPROBE_SYMBOL(fname)	__NOKPROBE_SYMBOL(fname)
+#else
+#define NOKPROBE_SYMBOL(fname)
+#endif
+
 #endif /* _LINUX_KPROBES_H */
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 7dcef331768..13d55206ccf 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -73,7 +73,6 @@ struct kthread_worker {
 struct kthread_work {
 	struct list_head	node;
 	kthread_work_func_t	func;
-	wait_queue_head_t	done;
 	struct kthread_worker	*worker;
 };
 
@@ -85,7 +84,6 @@ struct kthread_work {
 #define KTHREAD_WORK_INIT(work, fn)	{				\
 	.node = LIST_HEAD_INIT((work).node),				\
 	.func = (fn),							\
-	.done = __WAIT_QUEUE_HEAD_INITIALIZER((work).done),		\
 	}
 
 #define DEFINE_KTHREAD_WORKER(worker)					\
@@ -95,22 +93,16 @@ struct kthread_work {
 	struct kthread_work work = KTHREAD_WORK_INIT(work, fn)
 
 /*
- * kthread_worker.lock and kthread_work.done need their own lockdep class
- * keys if they are defined on stack with lockdep enabled.  Use the
- * following macros when defining them on stack.
+ * kthread_worker.lock needs its own lockdep class key when defined on
+ * stack with lockdep enabled.  Use the following macros in such cases.
  */
 #ifdef CONFIG_LOCKDEP
 # define KTHREAD_WORKER_INIT_ONSTACK(worker)				\
 	({ init_kthread_worker(&worker); worker; })
 # define DEFINE_KTHREAD_WORKER_ONSTACK(worker)				\
 	struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker)
-# define KTHREAD_WORK_INIT_ONSTACK(work, fn)				\
-	({ init_kthread_work((&work), fn); work; })
-# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn)				\
-	struct kthread_work work = KTHREAD_WORK_INIT_ONSTACK(work, fn)
 #else
 # define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker)
-# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn) DEFINE_KTHREAD_WORK(work, fn)
 #endif
 
 extern void __init_kthread_worker(struct kthread_worker *worker,
@@ -127,7 +119,6 @@ extern void __init_kthread_worker(struct kthread_worker *worker,
 		memset((work), 0, sizeof(struct kthread_work));		\
 		INIT_LIST_HEAD(&(work)->node);				\
 		(work)->func = (fn);					\
-		init_waitqueue_head(&(work)->done);			\
 	} while (0)
 
 int kthread_worker_fn(void *worker_ptr);
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 31c0cd1c941..de9e46e6bcc 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -304,6 +304,30 @@ static inline int ktime_compare(const ktime_t cmp1, const ktime_t cmp2)
 	return 0;
 }
 
+/**
+ * ktime_after - Compare if a ktime_t value is bigger than another one.
+ * @cmp1:	comparable1
+ * @cmp2:	comparable2
+ *
+ * Return: true if cmp1 happened after cmp2.
+ */
+static inline bool ktime_after(const ktime_t cmp1, const ktime_t cmp2)
+{
+	return ktime_compare(cmp1, cmp2) > 0;
+}
+
+/**
+ * ktime_before - Compare if a ktime_t value is smaller than another one.
+ * @cmp1:	comparable1
+ * @cmp2:	comparable2
+ *
+ * Return: true if cmp1 happened before cmp2.
+ */
+static inline bool ktime_before(const ktime_t cmp1, const ktime_t cmp2)
+{
+	return ktime_compare(cmp1, cmp2) < 0;
+}
+
 static inline s64 ktime_to_us(const ktime_t kt)
 {
 	struct timeval tv = ktime_to_timeval(kt);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 970c68197c6..ec4e3bd83d4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -586,7 +586,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 void kvm_vcpu_block(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
-bool kvm_vcpu_yield_to(struct kvm_vcpu *target);
+int kvm_vcpu_yield_to(struct kvm_vcpu *target);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 5ab4e3a7672..92abb497ab1 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -593,6 +593,7 @@ struct ata_host {
 	struct device 		*dev;
 	void __iomem * const	*iomap;
 	unsigned int		n_ports;
+	unsigned int		n_tags;			/* nr of NCQ tags */
 	void			*private_data;
 	struct ata_port_operations *ops;
 	unsigned long		flags;
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index dcaad79f54e..219d79627c0 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -17,13 +17,13 @@
 #include <linux/fs.h>
 #include <linux/kref.h>
 #include <linux/utsname.h>
-#include <linux/nfsd/nfsfh.h>
 #include <linux/lockd/bind.h>
 #include <linux/lockd/xdr.h>
 #ifdef CONFIG_LOCKD_V4
 #include <linux/lockd/xdr4.h>
 #endif
 #include <linux/lockd/debug.h>
+#include <linux/sunrpc/svc.h>
 
 /*
  * Version string
diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h
index 3e02b768d53..b6401e7661c 100644
--- a/include/linux/mfd/samsung/rtc.h
+++ b/include/linux/mfd/samsung/rtc.h
@@ -18,38 +18,38 @@
 #ifndef __LINUX_MFD_SEC_RTC_H
 #define __LINUX_MFD_SEC_RTC_H
 
-enum sec_rtc_reg {
-	SEC_RTC_SEC,
-	SEC_RTC_MIN,
-	SEC_RTC_HOUR,
-	SEC_RTC_WEEKDAY,
-	SEC_RTC_DATE,
-	SEC_RTC_MONTH,
-	SEC_RTC_YEAR1,
-	SEC_RTC_YEAR2,
-	SEC_ALARM0_SEC,
-	SEC_ALARM0_MIN,
-	SEC_ALARM0_HOUR,
-	SEC_ALARM0_WEEKDAY,
-	SEC_ALARM0_DATE,
-	SEC_ALARM0_MONTH,
-	SEC_ALARM0_YEAR1,
-	SEC_ALARM0_YEAR2,
-	SEC_ALARM1_SEC,
-	SEC_ALARM1_MIN,
-	SEC_ALARM1_HOUR,
-	SEC_ALARM1_WEEKDAY,
-	SEC_ALARM1_DATE,
-	SEC_ALARM1_MONTH,
-	SEC_ALARM1_YEAR1,
-	SEC_ALARM1_YEAR2,
-	SEC_ALARM0_CONF,
-	SEC_ALARM1_CONF,
-	SEC_RTC_STATUS,
-	SEC_WTSR_SMPL_CNTL,
-	SEC_RTC_UDR_CON,
+enum s5m_rtc_reg {
+	S5M_RTC_SEC,
+	S5M_RTC_MIN,
+	S5M_RTC_HOUR,
+	S5M_RTC_WEEKDAY,
+	S5M_RTC_DATE,
+	S5M_RTC_MONTH,
+	S5M_RTC_YEAR1,
+	S5M_RTC_YEAR2,
+	S5M_ALARM0_SEC,
+	S5M_ALARM0_MIN,
+	S5M_ALARM0_HOUR,
+	S5M_ALARM0_WEEKDAY,
+	S5M_ALARM0_DATE,
+	S5M_ALARM0_MONTH,
+	S5M_ALARM0_YEAR1,
+	S5M_ALARM0_YEAR2,
+	S5M_ALARM1_SEC,
+	S5M_ALARM1_MIN,
+	S5M_ALARM1_HOUR,
+	S5M_ALARM1_WEEKDAY,
+	S5M_ALARM1_DATE,
+	S5M_ALARM1_MONTH,
+	S5M_ALARM1_YEAR1,
+	S5M_ALARM1_YEAR2,
+	S5M_ALARM0_CONF,
+	S5M_ALARM1_CONF,
+	S5M_RTC_STATUS,
+	S5M_WTSR_SMPL_CNTL,
+	S5M_RTC_UDR_CON,
 
-	SEC_RTC_REG_MAX,
+	S5M_RTC_REG_MAX,
 };
 
 enum s2mps_rtc_reg {
@@ -88,9 +88,9 @@ enum s2mps_rtc_reg {
 #define HOUR_12			(1 << 7)
 #define HOUR_AMPM		(1 << 6)
 #define HOUR_PM			(1 << 5)
-#define ALARM0_STATUS		(1 << 1)
-#define ALARM1_STATUS		(1 << 2)
-#define UPDATE_AD		(1 << 0)
+#define S5M_ALARM0_STATUS	(1 << 1)
+#define S5M_ALARM1_STATUS	(1 << 2)
+#define S5M_UPDATE_AD		(1 << 0)
 
 #define S2MPS_ALARM0_STATUS	(1 << 2)
 #define S2MPS_ALARM1_STATUS	(1 << 1)
@@ -101,16 +101,26 @@ enum s2mps_rtc_reg {
 #define MODEL24_SHIFT		1
 #define MODEL24_MASK		(1 << MODEL24_SHIFT)
 /* RTC Update Register1 */
-#define RTC_UDR_SHIFT		0
-#define RTC_UDR_MASK		(1 << RTC_UDR_SHIFT)
+#define S5M_RTC_UDR_SHIFT	0
+#define S5M_RTC_UDR_MASK	(1 << S5M_RTC_UDR_SHIFT)
 #define S2MPS_RTC_WUDR_SHIFT	4
 #define S2MPS_RTC_WUDR_MASK	(1 << S2MPS_RTC_WUDR_SHIFT)
 #define S2MPS_RTC_RUDR_SHIFT	0
 #define S2MPS_RTC_RUDR_MASK	(1 << S2MPS_RTC_RUDR_SHIFT)
 #define RTC_TCON_SHIFT		1
 #define RTC_TCON_MASK		(1 << RTC_TCON_SHIFT)
-#define RTC_TIME_EN_SHIFT	3
-#define RTC_TIME_EN_MASK	(1 << RTC_TIME_EN_SHIFT)
+#define S5M_RTC_TIME_EN_SHIFT	3
+#define S5M_RTC_TIME_EN_MASK	(1 << S5M_RTC_TIME_EN_SHIFT)
+/*
+ * UDR_T field in S5M_RTC_UDR_CON register determines the time needed
+ * for updating alarm and time registers. Default is 7.32 ms.
+ */
+#define S5M_RTC_UDR_T_SHIFT	6
+#define S5M_RTC_UDR_T_MASK	(0x3 << S5M_RTC_UDR_T_SHIFT)
+#define S5M_RTC_UDR_T_7320_US	(0x0 << S5M_RTC_UDR_T_SHIFT)
+#define S5M_RTC_UDR_T_1830_US	(0x1 << S5M_RTC_UDR_T_SHIFT)
+#define S5M_RTC_UDR_T_3660_US	(0x2 << S5M_RTC_UDR_T_SHIFT)
+#define S5M_RTC_UDR_T_450_US	(0x3 << S5M_RTC_UDR_T_SHIFT)
 
 /* RTC Hour register */
 #define HOUR_PM_SHIFT		6
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index ba87bd21295..35b51e7af88 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -401,6 +401,7 @@ struct mlx4_caps {
 	int			max_rq_desc_sz;
 	int			max_qp_init_rdma;
 	int			max_qp_dest_rdma;
+	u32			*qp0_qkey;
 	u32			*qp0_proxy;
 	u32			*qp1_proxy;
 	u32			*qp0_tunnel;
@@ -449,7 +450,6 @@ struct mlx4_caps {
 	int                     reserved_qps_base[MLX4_NUM_QP_REGION];
 	int                     log_num_macs;
 	int                     log_num_vlans;
-	int                     log_num_prios;
 	enum mlx4_port_type	port_type[MLX4_MAX_PORTS + 1];
 	u8			supported_type[MLX4_MAX_PORTS + 1];
 	u8                      suggested_type[MLX4_MAX_PORTS + 1];
@@ -577,6 +577,7 @@ struct mlx4_cq {
 
 	u32			cons_index;
 
+	u16                     irq;
 	__be32		       *set_ci_db;
 	__be32		       *arm_db;
 	int			arm_sn;
@@ -837,7 +838,7 @@ static inline int mlx4_is_slave(struct mlx4_dev *dev)
 }
 
 int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
-		   struct mlx4_buf *buf);
+		   struct mlx4_buf *buf, gfp_t gfp);
 void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf);
 static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset)
 {
@@ -874,9 +875,10 @@ int mlx4_mw_enable(struct mlx4_dev *dev, struct mlx4_mw *mw);
 int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		   int start_index, int npages, u64 *page_list);
 int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
-		       struct mlx4_buf *buf);
+		       struct mlx4_buf *buf, gfp_t gfp);
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order);
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order,
+		  gfp_t gfp);
 void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
 
 int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
@@ -892,7 +894,8 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);
 int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base);
 void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
 
-int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp);
+int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp,
+		  gfp_t gfp);
 void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp);
 
 int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcdn,
@@ -1162,6 +1165,8 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 		   int *vector);
 void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
+int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec);
+
 int mlx4_get_phys_port_id(struct mlx4_dev *dev);
 int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
 int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
@@ -1234,4 +1239,8 @@ int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port);
 int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port);
 
 int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port);
+int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port);
+int mlx4_vf_get_enable_smi_admin(struct mlx4_dev *dev, int slave, int port);
+int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port,
+				 int enable);
 #endif /* MLX4_DEVICE_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 93cef6313e7..2bce4aad257 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -427,7 +427,6 @@ struct mlx5_core_mr {
 	u64			size;
 	u32			key;
 	u32			pd;
-	u32			access;
 };
 
 struct mlx5_core_srq {
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index b73027298b3..d424b9de3af 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -63,12 +63,12 @@ struct mmc_ext_csd {
 	unsigned int            power_off_longtime;     /* Units: ms */
 	u8			power_off_notification;	/* state */
 	unsigned int		hs_max_dtr;
+	unsigned int		hs200_max_dtr;
 #define MMC_HIGH_26_MAX_DTR	26000000
 #define MMC_HIGH_52_MAX_DTR	52000000
 #define MMC_HIGH_DDR_MAX_DTR	52000000
 #define MMC_HS200_MAX_DTR	200000000
 	unsigned int		sectors;
-	unsigned int		card_type;
 	unsigned int		hc_erase_size;		/* In sectors */
 	unsigned int		hc_erase_timeout;	/* In milliseconds */
 	unsigned int		sec_trim_mult;	/* Secure trim multiplier  */
@@ -110,6 +110,7 @@ struct mmc_ext_csd {
 	u8			raw_pwr_cl_200_360;	/* 237 */
 	u8			raw_pwr_cl_ddr_52_195;	/* 238 */
 	u8			raw_pwr_cl_ddr_52_360;	/* 239 */
+	u8			raw_pwr_cl_ddr_200_360;	/* 253 */
 	u8			raw_bkops_status;	/* 246 */
 	u8			raw_sectors[4];		/* 212 - 4 bytes */
 
@@ -194,6 +195,7 @@ struct sdio_cis {
 };
 
 struct mmc_host;
+struct mmc_ios;
 struct sdio_func;
 struct sdio_func_tuple;
 
@@ -250,15 +252,11 @@ struct mmc_card {
 	unsigned int		state;		/* (our) card state */
 #define MMC_STATE_PRESENT	(1<<0)		/* present in sysfs */
 #define MMC_STATE_READONLY	(1<<1)		/* card is read-only */
-#define MMC_STATE_HIGHSPEED	(1<<2)		/* card is in high speed mode */
-#define MMC_STATE_BLOCKADDR	(1<<3)		/* card uses block-addressing */
-#define MMC_STATE_HIGHSPEED_DDR (1<<4)		/* card is in high speed mode */
-#define MMC_STATE_ULTRAHIGHSPEED (1<<5)		/* card is in ultra high speed mode */
-#define MMC_CARD_SDXC		(1<<6)		/* card is SDXC */
-#define MMC_CARD_REMOVED	(1<<7)		/* card has been removed */
-#define MMC_STATE_HIGHSPEED_200	(1<<8)		/* card is in HS200 mode */
-#define MMC_STATE_DOING_BKOPS	(1<<10)		/* card is doing BKOPS */
-#define MMC_STATE_SUSPENDED	(1<<11)		/* card is suspended */
+#define MMC_STATE_BLOCKADDR	(1<<2)		/* card uses block-addressing */
+#define MMC_CARD_SDXC		(1<<3)		/* card is SDXC */
+#define MMC_CARD_REMOVED	(1<<4)		/* card has been removed */
+#define MMC_STATE_DOING_BKOPS	(1<<5)		/* card is doing BKOPS */
+#define MMC_STATE_SUSPENDED	(1<<6)		/* card is suspended */
 	unsigned int		quirks; 	/* card quirks */
 #define MMC_QUIRK_LENIENT_FN0	(1<<0)		/* allow SDIO FN0 writes outside of the VS CCCR range */
 #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1)	/* use func->cur_blksize */
@@ -301,6 +299,7 @@ struct mmc_card {
 	struct sdio_func_tuple	*tuples;	/* unknown common tuples */
 
 	unsigned int		sd_bus_speed;	/* Bus Speed Mode set for the card */
+	unsigned int		mmc_avail_type;	/* supported device type by both host and card */
 
 	struct dentry		*debugfs_root;
 	struct mmc_part	part[MMC_NUM_PHY_PARTITION]; /* physical partitions */
@@ -353,7 +352,7 @@ struct mmc_fixup {
 #define CID_OEMID_ANY ((unsigned short) -1)
 #define CID_NAME_ANY (NULL)
 
-#define END_FIXUP { 0 }
+#define END_FIXUP { NULL }
 
 #define _FIXUP_EXT(_name, _manfid, _oemid, _rev_start, _rev_end,	\
 		   _cis_vendor, _cis_device,				\
@@ -418,11 +417,7 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data)
 
 #define mmc_card_present(c)	((c)->state & MMC_STATE_PRESENT)
 #define mmc_card_readonly(c)	((c)->state & MMC_STATE_READONLY)
-#define mmc_card_highspeed(c)	((c)->state & MMC_STATE_HIGHSPEED)
-#define mmc_card_hs200(c)	((c)->state & MMC_STATE_HIGHSPEED_200)
 #define mmc_card_blockaddr(c)	((c)->state & MMC_STATE_BLOCKADDR)
-#define mmc_card_ddr_mode(c)	((c)->state & MMC_STATE_HIGHSPEED_DDR)
-#define mmc_card_uhs(c)		((c)->state & MMC_STATE_ULTRAHIGHSPEED)
 #define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC)
 #define mmc_card_removed(c)	((c) && ((c)->state & MMC_CARD_REMOVED))
 #define mmc_card_doing_bkops(c)	((c)->state & MMC_STATE_DOING_BKOPS)
@@ -430,11 +425,7 @@ static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data)
 
 #define mmc_card_set_present(c)	((c)->state |= MMC_STATE_PRESENT)
 #define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY)
-#define mmc_card_set_highspeed(c) ((c)->state |= MMC_STATE_HIGHSPEED)
-#define mmc_card_set_hs200(c)	((c)->state |= MMC_STATE_HIGHSPEED_200)
 #define mmc_card_set_blockaddr(c) ((c)->state |= MMC_STATE_BLOCKADDR)
-#define mmc_card_set_ddr_mode(c) ((c)->state |= MMC_STATE_HIGHSPEED_DDR)
-#define mmc_card_set_uhs(c) ((c)->state |= MMC_STATE_ULTRAHIGHSPEED)
 #define mmc_card_set_ext_capacity(c) ((c)->state |= MMC_CARD_SDXC)
 #define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED)
 #define mmc_card_set_doing_bkops(c)	((c)->state |= MMC_STATE_DOING_BKOPS)
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 6ce7d2cd3c7..babaea93bca 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -248,20 +248,6 @@ struct dw_mci_board {
 	/* delay in mS before detecting cards after interrupt */
 	u32 detect_delay_ms;
 
-	int (*init)(u32 slot_id, irq_handler_t , void *);
-	int (*get_ro)(u32 slot_id);
-	int (*get_cd)(u32 slot_id);
-	int (*get_ocr)(u32 slot_id);
-	int (*get_bus_wd)(u32 slot_id);
-	/*
-	 * Enable power to selected slot and set voltage to desired level.
-	 * Voltage levels are specified using MMC_VDD_xxx defines defined
-	 * in linux/mmc/host.h file.
-	 */
-	void (*setpower)(u32 slot_id, u32 volt);
-	void (*exit)(u32 slot_id);
-	void (*select_slot)(u32 slot_id);
-
 	struct dw_mci_dma_ops *dma_ops;
 	struct dma_pdata *data;
 	struct block_settings *blk_settings;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index cb61ea4d694..7960424d0bc 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -17,6 +17,7 @@
 #include <linux/fault-inject.h>
 
 #include <linux/mmc/core.h>
+#include <linux/mmc/card.h>
 #include <linux/mmc/pm.h>
 
 struct mmc_ios {
@@ -58,13 +59,9 @@ struct mmc_ios {
 #define MMC_TIMING_UHS_SDR50	5
 #define MMC_TIMING_UHS_SDR104	6
 #define MMC_TIMING_UHS_DDR50	7
-#define MMC_TIMING_MMC_HS200	8
-
-#define MMC_SDR_MODE		0
-#define MMC_1_2V_DDR_MODE	1
-#define MMC_1_8V_DDR_MODE	2
-#define MMC_1_2V_SDR_MODE	3
-#define MMC_1_8V_SDR_MODE	4
+#define MMC_TIMING_MMC_DDR52	8
+#define MMC_TIMING_MMC_HS200	9
+#define MMC_TIMING_MMC_HS400	10
 
 	unsigned char	signal_voltage;		/* signalling voltage (1.8V or 3.3V) */
 
@@ -136,6 +133,9 @@ struct mmc_host_ops {
 
 	/* The tuning command opcode value is different for SD and eMMC cards */
 	int	(*execute_tuning)(struct mmc_host *host, u32 opcode);
+
+	/* Prepare HS400 target operating frequency depending host driver */
+	int	(*prepare_hs400_tuning)(struct mmc_host *host, struct mmc_ios *ios);
 	int	(*select_drive_strength)(unsigned int max_dtr, int host_drv, int card_drv);
 	void	(*hw_reset)(struct mmc_host *host);
 	void	(*card_event)(struct mmc_host *host);
@@ -278,6 +278,11 @@ struct mmc_host {
 #define MMC_CAP2_PACKED_CMD	(MMC_CAP2_PACKED_RD | \
 				 MMC_CAP2_PACKED_WR)
 #define MMC_CAP2_NO_PRESCAN_POWERUP (1 << 14)	/* Don't power up before scan */
+#define MMC_CAP2_HS400_1_8V	(1 << 15)	/* Can support HS400 1.8V */
+#define MMC_CAP2_HS400_1_2V	(1 << 16)	/* Can support HS400 1.2V */
+#define MMC_CAP2_HS400		(MMC_CAP2_HS400_1_8V | \
+				 MMC_CAP2_HS400_1_2V)
+#define MMC_CAP2_SDIO_IRQ_NOTHREAD (1 << 17)
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
 
@@ -318,6 +323,8 @@ struct mmc_host {
 	int			rescan_disable;	/* disable card detection */
 	int			rescan_entered;	/* used with nonremovable devices */
 
+	bool			trigger_card_event; /* card_event necessary */
+
 	struct mmc_card		*card;		/* device attached to this host */
 
 	wait_queue_head_t	wq;
@@ -391,12 +398,13 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host)
 	wake_up_process(host->sdio_irq_thread);
 }
 
+void sdio_run_irqs(struct mmc_host *host);
+
 #ifdef CONFIG_REGULATOR
 int mmc_regulator_get_ocrmask(struct regulator *supply);
 int mmc_regulator_set_ocr(struct mmc_host *mmc,
 			struct regulator *supply,
 			unsigned short vdd_bit);
-int mmc_regulator_get_supply(struct mmc_host *mmc);
 #else
 static inline int mmc_regulator_get_ocrmask(struct regulator *supply)
 {
@@ -409,13 +417,10 @@ static inline int mmc_regulator_set_ocr(struct mmc_host *mmc,
 {
 	return 0;
 }
-
-static inline int mmc_regulator_get_supply(struct mmc_host *mmc)
-{
-	return 0;
-}
 #endif
 
+int mmc_regulator_get_supply(struct mmc_host *mmc);
+
 int mmc_pm_notify(struct notifier_block *notify_block, unsigned long, void *);
 
 static inline int mmc_card_is_removable(struct mmc_host *host)
@@ -475,4 +480,32 @@ static inline unsigned int mmc_host_clk_rate(struct mmc_host *host)
 	return host->ios.clock;
 }
 #endif
+
+static inline int mmc_card_hs(struct mmc_card *card)
+{
+	return card->host->ios.timing == MMC_TIMING_SD_HS ||
+		card->host->ios.timing == MMC_TIMING_MMC_HS;
+}
+
+static inline int mmc_card_uhs(struct mmc_card *card)
+{
+	return card->host->ios.timing >= MMC_TIMING_UHS_SDR12 &&
+		card->host->ios.timing <= MMC_TIMING_UHS_DDR50;
+}
+
+static inline bool mmc_card_hs200(struct mmc_card *card)
+{
+	return card->host->ios.timing == MMC_TIMING_MMC_HS200;
+}
+
+static inline bool mmc_card_ddr52(struct mmc_card *card)
+{
+	return card->host->ios.timing == MMC_TIMING_MMC_DDR52;
+}
+
+static inline bool mmc_card_hs400(struct mmc_card *card)
+{
+	return card->host->ios.timing == MMC_TIMING_MMC_HS400;
+}
+
 #endif /* LINUX_MMC_HOST_H */
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 50bcde3677c..64ec963ed34 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -325,6 +325,7 @@ struct _mmc_csd {
 #define EXT_CSD_POWER_OFF_LONG_TIME	247	/* RO */
 #define EXT_CSD_GENERIC_CMD6_TIME	248	/* RO */
 #define EXT_CSD_CACHE_SIZE		249	/* RO, 4 bytes */
+#define EXT_CSD_PWR_CL_DDR_200_360	253	/* RO */
 #define EXT_CSD_TAG_UNIT_SIZE		498	/* RO */
 #define EXT_CSD_DATA_TAG_SUPPORT	499	/* RO */
 #define EXT_CSD_MAX_PACKED_WRITES	500	/* RO */
@@ -354,18 +355,25 @@ struct _mmc_csd {
 #define EXT_CSD_CMD_SET_SECURE		(1<<1)
 #define EXT_CSD_CMD_SET_CPSECURE	(1<<2)
 
-#define EXT_CSD_CARD_TYPE_26	(1<<0)	/* Card can run at 26MHz */
-#define EXT_CSD_CARD_TYPE_52	(1<<1)	/* Card can run at 52MHz */
-#define EXT_CSD_CARD_TYPE_MASK	0x3F	/* Mask out reserved bits */
+#define EXT_CSD_CARD_TYPE_HS_26	(1<<0)	/* Card can run at 26MHz */
+#define EXT_CSD_CARD_TYPE_HS_52	(1<<1)	/* Card can run at 52MHz */
+#define EXT_CSD_CARD_TYPE_HS	(EXT_CSD_CARD_TYPE_HS_26 | \
+				 EXT_CSD_CARD_TYPE_HS_52)
 #define EXT_CSD_CARD_TYPE_DDR_1_8V  (1<<2)   /* Card can run at 52MHz */
 					     /* DDR mode @1.8V or 3V I/O */
 #define EXT_CSD_CARD_TYPE_DDR_1_2V  (1<<3)   /* Card can run at 52MHz */
 					     /* DDR mode @1.2V I/O */
 #define EXT_CSD_CARD_TYPE_DDR_52       (EXT_CSD_CARD_TYPE_DDR_1_8V  \
 					| EXT_CSD_CARD_TYPE_DDR_1_2V)
-#define EXT_CSD_CARD_TYPE_SDR_1_8V	(1<<4)	/* Card can run at 200MHz */
-#define EXT_CSD_CARD_TYPE_SDR_1_2V	(1<<5)	/* Card can run at 200MHz */
+#define EXT_CSD_CARD_TYPE_HS200_1_8V	(1<<4)	/* Card can run at 200MHz */
+#define EXT_CSD_CARD_TYPE_HS200_1_2V	(1<<5)	/* Card can run at 200MHz */
 						/* SDR mode @1.2V I/O */
+#define EXT_CSD_CARD_TYPE_HS200		(EXT_CSD_CARD_TYPE_HS200_1_8V | \
+					 EXT_CSD_CARD_TYPE_HS200_1_2V)
+#define EXT_CSD_CARD_TYPE_HS400_1_8V	(1<<6)	/* Card can run at 200MHz DDR, 1.8V */
+#define EXT_CSD_CARD_TYPE_HS400_1_2V	(1<<7)	/* Card can run at 200MHz DDR, 1.2V */
+#define EXT_CSD_CARD_TYPE_HS400		(EXT_CSD_CARD_TYPE_HS400_1_8V | \
+					 EXT_CSD_CARD_TYPE_HS400_1_2V)
 
 #define EXT_CSD_BUS_WIDTH_1	0	/* Card is in 1 bit mode */
 #define EXT_CSD_BUS_WIDTH_4	1	/* Card is in 4 bit mode */
@@ -373,6 +381,11 @@ struct _mmc_csd {
 #define EXT_CSD_DDR_BUS_WIDTH_4	5	/* Card is in 4 bit DDR mode */
 #define EXT_CSD_DDR_BUS_WIDTH_8	6	/* Card is in 8 bit DDR mode */
 
+#define EXT_CSD_TIMING_BC	0	/* Backwards compatility */
+#define EXT_CSD_TIMING_HS	1	/* High speed */
+#define EXT_CSD_TIMING_HS200	2	/* HS200 */
+#define EXT_CSD_TIMING_HS400	3	/* HS400 */
+
 #define EXT_CSD_SEC_ER_EN	BIT(0)
 #define EXT_CSD_SEC_BD_BLK_EN	BIT(2)
 #define EXT_CSD_SEC_GB_CL_EN	BIT(4)
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 7be12b88348..08abe994188 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -57,12 +57,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK_BROKEN_CARD_DETECTION		(1<<15)
 /* Controller reports inverted write-protect state */
 #define SDHCI_QUIRK_INVERTED_WRITE_PROTECT		(1<<16)
-/* Controller has nonstandard clock management */
-#define SDHCI_QUIRK_NONSTANDARD_CLOCK			(1<<17)
 /* Controller does not like fast PIO transfers */
 #define SDHCI_QUIRK_PIO_NEEDS_DELAY			(1<<18)
-/* Controller losing signal/interrupt enable states after reset */
-#define SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET		(1<<19)
 /* Controller has to be forced to use block size of 2048 bytes */
 #define SDHCI_QUIRK_FORCE_BLK_SZ_2048			(1<<20)
 /* Controller cannot do multi-block transfers */
@@ -147,6 +143,7 @@ struct sdhci_host {
 
 	bool runtime_suspended;	/* Host is runtime suspended */
 	bool bus_on;		/* Bus power prevents runtime suspend */
+	bool preset_enabled;	/* Preset is enabled */
 
 	struct mmc_request *mrq;	/* Current request */
 	struct mmc_command *cmd;	/* Current command */
@@ -164,8 +161,7 @@ struct sdhci_host {
 	dma_addr_t adma_addr;	/* Mapped ADMA descr. table */
 	dma_addr_t align_addr;	/* Mapped bounce buffer */
 
-	struct tasklet_struct card_tasklet;	/* Tasklet structures */
-	struct tasklet_struct finish_tasklet;
+	struct tasklet_struct finish_tasklet;	/* Tasklet structures */
 
 	struct timer_list timer;	/* Timer for timeouts */
 
@@ -177,6 +173,13 @@ struct sdhci_host {
 	unsigned int            ocr_avail_mmc;
 	u32 ocr_mask;		/* available voltages */
 
+	unsigned		timing;		/* Current timing */
+
+	u32			thread_isr;
+
+	/* cached registers */
+	u32			ier;
+
 	wait_queue_head_t	buf_ready_int;	/* Waitqueue for Buffer Read Ready interrupt */
 	unsigned int		tuning_done;	/* Condition flag set when CMD19 succeeds */
 
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 204a6774380..b1990c5524e 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -321,7 +321,7 @@ extern bool parameq(const char *name1, const char *name2);
 extern bool parameqn(const char *name1, const char *name2, size_t n);
 
 /* Called on module insert or kernel boot */
-extern int parse_args(const char *name,
+extern char *parse_args(const char *name,
 		      char *args,
 		      const struct kernel_param *params,
 		      unsigned num,
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 92a2f991262..8103f32f6d8 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -25,7 +25,8 @@ void write_msi_msg(unsigned int irq, struct msi_msg *msg);
 struct msi_desc {
 	struct {
 		__u8	is_msix	: 1;
-		__u8	multiple: 3;	/* log2 number of messages */
+		__u8	multiple: 3;	/* log2 num of messages allocated */
+		__u8	multi_cap : 3;	/* log2 num of messages supported */
 		__u8	maskbit	: 1;	/* mask-pending bit supported ? */
 		__u8	is_64	: 1;	/* Address size: 0=32bit 1=64bit */
 		__u8	pos;		/* Location of the msi capability */
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 450d61ec7f0..2f0af2891f0 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -176,6 +176,11 @@ typedef enum {
 /* Chip may not exist, so silence any errors in scan */
 #define NAND_SCAN_SILENT_NODEV	0x00040000
 /*
+ * This option could be defined by controller drivers to protect against
+ * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers
+ */
+#define NAND_USE_BOUNCE_BUFFER	0x00080000
+/*
  * Autodetect nand buswidth with readid/onfi.
  * This suppose the driver will configure the hardware in 8 bits mode
  * when calling nand_scan_ident, and update its configuration
@@ -552,8 +557,7 @@ struct nand_buffers {
  * @ecc:		[BOARDSPECIFIC] ECC control structure
  * @buffers:		buffer structure for read/write
  * @hwcontrol:		platform-specific hardware control structure
- * @erase_cmd:		[INTERN] erase command write function, selectable due
- *			to AND support.
+ * @erase:		[REPLACEABLE] erase function
  * @scan_bbt:		[REPLACEABLE] function to scan bad block table
  * @chip_delay:		[BOARDSPECIFIC] chip dependent delay for transferring
  *			data from array to read regs (tR).
@@ -637,7 +641,7 @@ struct nand_chip {
 	void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column,
 			int page_addr);
 	int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this);
-	void (*erase_cmd)(struct mtd_info *mtd, int page);
+	int (*erase)(struct mtd_info *mtd, int page);
 	int (*scan_bbt)(struct mtd_info *mtd);
 	int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state,
 			int status, int page);
diff --git a/include/linux/mtd/pfow.h b/include/linux/mtd/pfow.h
index b730d4f8465..42ff7ff09bf 100644
--- a/include/linux/mtd/pfow.h
+++ b/include/linux/mtd/pfow.h
@@ -101,9 +101,6 @@ static inline void send_pfow_command(struct map_info *map,
 				unsigned long len, map_word *datum)
 {
 	int bits_per_chip = map_bankwidth(map) * 8;
-	int chipnum;
-	struct lpddr_private *lpddr = map->fldrv_priv;
-	chipnum = adr >> lpddr->chipshift;
 
 	map_write(map, CMD(cmd_code), map->pfow_base + PFOW_COMMAND_CODE);
 	map_write(map, CMD(adr & ((1<<bits_per_chip) - 1)),
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
new file mode 100644
index 00000000000..53241842a7a
--- /dev/null
+++ b/include/linux/mtd/spi-nor.h
@@ -0,0 +1,214 @@
+/*
+ * Copyright (C) 2014 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_MTD_SPI_NOR_H
+#define __LINUX_MTD_SPI_NOR_H
+
+/*
+ * Note on opcode nomenclature: some opcodes have a format like
+ * SPINOR_OP_FUNCTION{4,}_x_y_z. The numbers x, y, and z stand for the number
+ * of I/O lines used for the opcode, address, and data (respectively). The
+ * FUNCTION has an optional suffix of '4', to represent an opcode which
+ * requires a 4-byte (32-bit) address.
+ */
+
+/* Flash opcodes. */
+#define SPINOR_OP_WREN		0x06	/* Write enable */
+#define SPINOR_OP_RDSR		0x05	/* Read status register */
+#define SPINOR_OP_WRSR		0x01	/* Write status register 1 byte */
+#define SPINOR_OP_READ		0x03	/* Read data bytes (low frequency) */
+#define SPINOR_OP_READ_FAST	0x0b	/* Read data bytes (high frequency) */
+#define SPINOR_OP_READ_1_1_2	0x3b	/* Read data bytes (Dual SPI) */
+#define SPINOR_OP_READ_1_1_4	0x6b	/* Read data bytes (Quad SPI) */
+#define SPINOR_OP_PP		0x02	/* Page program (up to 256 bytes) */
+#define SPINOR_OP_BE_4K		0x20	/* Erase 4KiB block */
+#define SPINOR_OP_BE_4K_PMC	0xd7	/* Erase 4KiB block on PMC chips */
+#define SPINOR_OP_BE_32K	0x52	/* Erase 32KiB block */
+#define SPINOR_OP_CHIP_ERASE	0xc7	/* Erase whole flash chip */
+#define SPINOR_OP_SE		0xd8	/* Sector erase (usually 64KiB) */
+#define SPINOR_OP_RDID		0x9f	/* Read JEDEC ID */
+#define SPINOR_OP_RDCR		0x35	/* Read configuration register */
+
+/* 4-byte address opcodes - used on Spansion and some Macronix flashes. */
+#define SPINOR_OP_READ4		0x13	/* Read data bytes (low frequency) */
+#define SPINOR_OP_READ4_FAST	0x0c	/* Read data bytes (high frequency) */
+#define SPINOR_OP_READ4_1_1_2	0x3c	/* Read data bytes (Dual SPI) */
+#define SPINOR_OP_READ4_1_1_4	0x6c	/* Read data bytes (Quad SPI) */
+#define SPINOR_OP_PP_4B		0x12	/* Page program (up to 256 bytes) */
+#define SPINOR_OP_SE_4B		0xdc	/* Sector erase (usually 64KiB) */
+
+/* Used for SST flashes only. */
+#define SPINOR_OP_BP		0x02	/* Byte program */
+#define SPINOR_OP_WRDI		0x04	/* Write disable */
+#define SPINOR_OP_AAI_WP	0xad	/* Auto address increment word program */
+
+/* Used for Macronix and Winbond flashes. */
+#define SPINOR_OP_EN4B		0xb7	/* Enter 4-byte mode */
+#define SPINOR_OP_EX4B		0xe9	/* Exit 4-byte mode */
+
+/* Used for Spansion flashes only. */
+#define SPINOR_OP_BRWR		0x17	/* Bank register write */
+
+/* Status Register bits. */
+#define SR_WIP			1	/* Write in progress */
+#define SR_WEL			2	/* Write enable latch */
+/* meaning of other SR_* bits may differ between vendors */
+#define SR_BP0			4	/* Block protect 0 */
+#define SR_BP1			8	/* Block protect 1 */
+#define SR_BP2			0x10	/* Block protect 2 */
+#define SR_SRWD			0x80	/* SR write protect */
+
+#define SR_QUAD_EN_MX		0x40	/* Macronix Quad I/O */
+
+/* Configuration Register bits. */
+#define CR_QUAD_EN_SPAN		0x2	/* Spansion Quad I/O */
+
+enum read_mode {
+	SPI_NOR_NORMAL = 0,
+	SPI_NOR_FAST,
+	SPI_NOR_DUAL,
+	SPI_NOR_QUAD,
+};
+
+/**
+ * struct spi_nor_xfer_cfg - Structure for defining a Serial Flash transfer
+ * @wren:		command for "Write Enable", or 0x00 for not required
+ * @cmd:		command for operation
+ * @cmd_pins:		number of pins to send @cmd (1, 2, 4)
+ * @addr:		address for operation
+ * @addr_pins:		number of pins to send @addr (1, 2, 4)
+ * @addr_width:		number of address bytes
+ *			(3,4, or 0 for address not required)
+ * @mode:		mode data
+ * @mode_pins:		number of pins to send @mode (1, 2, 4)
+ * @mode_cycles:	number of mode cycles (0 for mode not required)
+ * @dummy_cycles:	number of dummy cycles (0 for dummy not required)
+ */
+struct spi_nor_xfer_cfg {
+	u8		wren;
+	u8		cmd;
+	u8		cmd_pins;
+	u32		addr;
+	u8		addr_pins;
+	u8		addr_width;
+	u8		mode;
+	u8		mode_pins;
+	u8		mode_cycles;
+	u8		dummy_cycles;
+};
+
+#define SPI_NOR_MAX_CMD_SIZE	8
+enum spi_nor_ops {
+	SPI_NOR_OPS_READ = 0,
+	SPI_NOR_OPS_WRITE,
+	SPI_NOR_OPS_ERASE,
+	SPI_NOR_OPS_LOCK,
+	SPI_NOR_OPS_UNLOCK,
+};
+
+/**
+ * struct spi_nor - Structure for defining a the SPI NOR layer
+ * @mtd:		point to a mtd_info structure
+ * @lock:		the lock for the read/write/erase/lock/unlock operations
+ * @dev:		point to a spi device, or a spi nor controller device.
+ * @page_size:		the page size of the SPI NOR
+ * @addr_width:		number of address bytes
+ * @erase_opcode:	the opcode for erasing a sector
+ * @read_opcode:	the read opcode
+ * @read_dummy:		the dummy needed by the read operation
+ * @program_opcode:	the program opcode
+ * @flash_read:		the mode of the read
+ * @sst_write_second:	used by the SST write operation
+ * @cfg:		used by the read_xfer/write_xfer
+ * @cmd_buf:		used by the write_reg
+ * @prepare:		[OPTIONAL] do some preparations for the
+ *			read/write/erase/lock/unlock operations
+ * @unprepare:		[OPTIONAL] do some post work after the
+ *			read/write/erase/lock/unlock operations
+ * @read_xfer:		[OPTIONAL] the read fundamental primitive
+ * @write_xfer:		[OPTIONAL] the writefundamental primitive
+ * @read_reg:		[DRIVER-SPECIFIC] read out the register
+ * @write_reg:		[DRIVER-SPECIFIC] write data to the register
+ * @read_id:		[REPLACEABLE] read out the ID data, and find
+ *			the proper spi_device_id
+ * @wait_till_ready:	[REPLACEABLE] wait till the NOR becomes ready
+ * @read:		[DRIVER-SPECIFIC] read data from the SPI NOR
+ * @write:		[DRIVER-SPECIFIC] write data to the SPI NOR
+ * @erase:		[DRIVER-SPECIFIC] erase a sector of the SPI NOR
+ *			at the offset @offs
+ * @priv:		the private data
+ */
+struct spi_nor {
+	struct mtd_info		*mtd;
+	struct mutex		lock;
+	struct device		*dev;
+	u32			page_size;
+	u8			addr_width;
+	u8			erase_opcode;
+	u8			read_opcode;
+	u8			read_dummy;
+	u8			program_opcode;
+	enum read_mode		flash_read;
+	bool			sst_write_second;
+	struct spi_nor_xfer_cfg	cfg;
+	u8			cmd_buf[SPI_NOR_MAX_CMD_SIZE];
+
+	int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops);
+	void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops);
+	int (*read_xfer)(struct spi_nor *nor, struct spi_nor_xfer_cfg *cfg,
+			 u8 *buf, size_t len);
+	int (*write_xfer)(struct spi_nor *nor, struct spi_nor_xfer_cfg *cfg,
+			  u8 *buf, size_t len);
+	int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len);
+	int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len,
+			int write_enable);
+	const struct spi_device_id *(*read_id)(struct spi_nor *nor);
+	int (*wait_till_ready)(struct spi_nor *nor);
+
+	int (*read)(struct spi_nor *nor, loff_t from,
+			size_t len, size_t *retlen, u_char *read_buf);
+	void (*write)(struct spi_nor *nor, loff_t to,
+			size_t len, size_t *retlen, const u_char *write_buf);
+	int (*erase)(struct spi_nor *nor, loff_t offs);
+
+	void *priv;
+};
+
+/**
+ * spi_nor_scan() - scan the SPI NOR
+ * @nor:	the spi_nor structure
+ * @id:		the spi_device_id provided by the driver
+ * @mode:	the read mode supported by the driver
+ *
+ * The drivers can use this fuction to scan the SPI NOR.
+ * In the scanning, it will try to get all the necessary information to
+ * fill the mtd_info{} and the spi_nor{}.
+ *
+ * The board may assigns a spi_device_id with @id which be used to compared with
+ * the spi_device_id detected by the scanning.
+ *
+ * Return: 0 for success, others for failure.
+ */
+int spi_nor_scan(struct spi_nor *nor, const struct spi_device_id *id,
+			enum read_mode mode);
+extern const struct spi_device_id spi_nor_ids[];
+
+/**
+ * spi_nor_match_id() - find the spi_device_id by the name
+ * @name:	the name of the spi_device_id
+ *
+ * The drivers use this function to find the spi_device_id
+ * specified by the @name.
+ *
+ * Return: returns the right spi_device_id pointer on success,
+ *         and returns NULL on failure.
+ */
+const struct spi_device_id *spi_nor_match_id(char *name);
+
+#endif
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 11692dea18a..8d5535c58cc 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -17,6 +17,7 @@
 #include <linux/lockdep.h>
 #include <linux/atomic.h>
 #include <asm/processor.h>
+#include <linux/osq_lock.h>
 
 /*
  * Simple, straightforward mutexes with strict semantics:
@@ -46,7 +47,6 @@
  * - detects multi-task circular deadlocks and prints out all affected
  *   locks and tasks (and only those tasks)
  */
-struct optimistic_spin_queue;
 struct mutex {
 	/* 1: unlocked, 0: locked, negative: locked, possible waiters */
 	atomic_t		count;
@@ -56,7 +56,7 @@ struct mutex {
 	struct task_struct	*owner;
 #endif
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	struct optimistic_spin_queue	*osq;	/* Spinner MCS lock */
+	struct optimistic_spin_queue osq; /* Spinner MCS lock */
 #endif
 #ifdef CONFIG_DEBUG_MUTEXES
 	const char 		*name;
@@ -176,8 +176,4 @@ extern void mutex_unlock(struct mutex *lock);
 
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
-#ifndef arch_mutex_cpu_relax
-# define arch_mutex_cpu_relax() cpu_relax()
-#endif
-
 #endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index c26d0ec2ef3..d99800cbdcf 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -42,9 +42,11 @@ enum {
 	NETIF_F_TSO6_BIT,		/* ... TCPv6 segmentation */
 	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
 	NETIF_F_GSO_GRE_BIT,		/* ... GRE with TSO */
+	NETIF_F_GSO_GRE_CSUM_BIT,	/* ... GRE with csum with TSO */
 	NETIF_F_GSO_IPIP_BIT,		/* ... IPIP tunnel with TSO */
 	NETIF_F_GSO_SIT_BIT,		/* ... SIT tunnel with TSO */
 	NETIF_F_GSO_UDP_TUNNEL_BIT,	/* ... UDP TUNNEL with TSO */
+	NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT,/* ... UDP TUNNEL with TSO & CSUM */
 	NETIF_F_GSO_MPLS_BIT,		/* ... MPLS segmentation */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
 		NETIF_F_GSO_MPLS_BIT,
@@ -111,9 +113,11 @@ enum {
 #define NETIF_F_RXFCS		__NETIF_F(RXFCS)
 #define NETIF_F_RXALL		__NETIF_F(RXALL)
 #define NETIF_F_GSO_GRE		__NETIF_F(GSO_GRE)
+#define NETIF_F_GSO_GRE_CSUM	__NETIF_F(GSO_GRE_CSUM)
 #define NETIF_F_GSO_IPIP	__NETIF_F(GSO_IPIP)
 #define NETIF_F_GSO_SIT		__NETIF_F(GSO_SIT)
 #define NETIF_F_GSO_UDP_TUNNEL	__NETIF_F(GSO_UDP_TUNNEL)
+#define NETIF_F_GSO_UDP_TUNNEL_CSUM __NETIF_F(GSO_UDP_TUNNEL_CSUM)
 #define NETIF_F_GSO_MPLS	__NETIF_F(GSO_MPLS)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6c1ae9fd950..66f9a04ec27 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -56,9 +56,6 @@ struct device;
 struct phy_device;
 /* 802.11 specific */
 struct wireless_dev;
-					/* source back-compat hooks */
-#define SET_ETHTOOL_OPS(netdev,ops) \
-	( (netdev)->ethtool_ops = (ops) )
 
 void netdev_set_default_ethtool_ops(struct net_device *dev,
 				    const struct ethtool_ops *ops);
@@ -853,7 +850,8 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  *	SR-IOV management functions.
  * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac);
  * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos);
- * int (*ndo_set_vf_tx_rate)(struct net_device *dev, int vf, int rate);
+ * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate,
+ *			  int max_tx_rate);
  * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);
  * int (*ndo_get_vf_config)(struct net_device *dev,
  *			    int vf, struct ifla_vf_info *ivf);
@@ -1047,8 +1045,9 @@ struct net_device_ops {
 						  int queue, u8 *mac);
 	int			(*ndo_set_vf_vlan)(struct net_device *dev,
 						   int queue, u16 vlan, u8 qos);
-	int			(*ndo_set_vf_tx_rate)(struct net_device *dev,
-						      int vf, int rate);
+	int			(*ndo_set_vf_rate)(struct net_device *dev,
+						   int vf, int min_tx_rate,
+						   int max_tx_rate);
 	int			(*ndo_set_vf_spoofchk)(struct net_device *dev,
 						       int vf, bool setting);
 	int			(*ndo_get_vf_config)(struct net_device *dev,
@@ -2634,6 +2633,7 @@ int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_port_id *ppid);
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			struct netdev_queue *txq);
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb);
 
@@ -3003,6 +3003,15 @@ int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
 		   struct netdev_hw_addr_list *from_list, int addr_len);
 void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
 		      struct netdev_hw_addr_list *from_list, int addr_len);
+int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
+		       struct net_device *dev,
+		       int (*sync)(struct net_device *, const unsigned char *),
+		       int (*unsync)(struct net_device *,
+				     const unsigned char *));
+void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
+			  struct net_device *dev,
+			  int (*unsync)(struct net_device *,
+					const unsigned char *));
 void __hw_addr_init(struct netdev_hw_addr_list *list);
 
 /* Functions used for device addresses handling */
@@ -3023,6 +3032,38 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from);
 void dev_uc_flush(struct net_device *dev);
 void dev_uc_init(struct net_device *dev);
 
+/**
+ *  __dev_uc_sync - Synchonize device's unicast list
+ *  @dev:  device to sync
+ *  @sync: function to call if address should be added
+ *  @unsync: function to call if address should be removed
+ *
+ *  Add newly added addresses to the interface, and release
+ *  addresses that have been deleted.
+ **/
+static inline int __dev_uc_sync(struct net_device *dev,
+				int (*sync)(struct net_device *,
+					    const unsigned char *),
+				int (*unsync)(struct net_device *,
+					      const unsigned char *))
+{
+	return __hw_addr_sync_dev(&dev->uc, dev, sync, unsync);
+}
+
+/**
+ *  __dev_uc_unsync - Remove synchonized addresses from device
+ *  @dev:  device to sync
+ *  @unsync: function to call if address should be removed
+ *
+ *  Remove all addresses that were added to the device by dev_uc_sync().
+ **/
+static inline void __dev_uc_unsync(struct net_device *dev,
+				   int (*unsync)(struct net_device *,
+						 const unsigned char *))
+{
+	__hw_addr_unsync_dev(&dev->uc, dev, unsync);
+}
+
 /* Functions used for multicast addresses handling */
 int dev_mc_add(struct net_device *dev, const unsigned char *addr);
 int dev_mc_add_global(struct net_device *dev, const unsigned char *addr);
@@ -3035,6 +3076,38 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from);
 void dev_mc_flush(struct net_device *dev);
 void dev_mc_init(struct net_device *dev);
 
+/**
+ *  __dev_mc_sync - Synchonize device's multicast list
+ *  @dev:  device to sync
+ *  @sync: function to call if address should be added
+ *  @unsync: function to call if address should be removed
+ *
+ *  Add newly added addresses to the interface, and release
+ *  addresses that have been deleted.
+ **/
+static inline int __dev_mc_sync(struct net_device *dev,
+				int (*sync)(struct net_device *,
+					    const unsigned char *),
+				int (*unsync)(struct net_device *,
+					      const unsigned char *))
+{
+	return __hw_addr_sync_dev(&dev->mc, dev, sync, unsync);
+}
+
+/**
+ *  __dev_mc_unsync - Remove synchonized addresses from device
+ *  @dev:  device to sync
+ *  @unsync: function to call if address should be removed
+ *
+ *  Remove all addresses that were added to the device by dev_mc_sync().
+ **/
+static inline void __dev_mc_unsync(struct net_device *dev,
+				   int (*unsync)(struct net_device *,
+						 const unsigned char *))
+{
+	__hw_addr_unsync_dev(&dev->mc, dev, unsync);
+}
+
 /* Functions used for secondary unicast and multicast support */
 void dev_set_rx_mode(struct net_device *dev);
 void __dev_set_rx_mode(struct net_device *dev);
@@ -3180,6 +3253,20 @@ const char *netdev_drivername(const struct net_device *dev);
 
 void linkwatch_run_queue(void);
 
+static inline netdev_features_t netdev_intersect_features(netdev_features_t f1,
+							  netdev_features_t f2)
+{
+	if (f1 & NETIF_F_GEN_CSUM)
+		f1 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);
+	if (f2 & NETIF_F_GEN_CSUM)
+		f2 |= (NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);
+	f1 &= f2;
+	if (f1 & NETIF_F_GEN_CSUM)
+		f1 &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);
+
+	return f1;
+}
+
 static inline netdev_features_t netdev_get_wanted_features(
 	struct net_device *dev)
 {
@@ -3218,6 +3305,13 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_IPIP    != (NETIF_F_GSO_IPIP >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_SIT     != (NETIF_F_GSO_SIT >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_MPLS    != (NETIF_F_GSO_MPLS >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h
index b2e85e59f76..6ec97574874 100644
--- a/include/linux/netfilter/nfnetlink_acct.h
+++ b/include/linux/netfilter/nfnetlink_acct.h
@@ -3,11 +3,17 @@
 
 #include <uapi/linux/netfilter/nfnetlink_acct.h>
 
+enum {
+	NFACCT_NO_QUOTA		= -1,
+	NFACCT_UNDERQUOTA,
+	NFACCT_OVERQUOTA,
+};
 
 struct nf_acct;
 
 struct nf_acct *nfnl_acct_find_get(const char *filter_name);
 void nfnl_acct_put(struct nf_acct *acct);
 void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct);
-
+extern int nfnl_acct_overquota(const struct sk_buff *skb,
+			      struct nf_acct *nfacct);
 #endif /* _NFNL_ACCT_H */
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 034cda789a1..9e572daa15d 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -46,7 +46,8 @@ struct netlink_kernel_cfg {
 	unsigned int	flags;
 	void		(*input)(struct sk_buff *skb);
 	struct mutex	*cb_mutex;
-	void		(*bind)(int group);
+	int		(*bind)(int group);
+	void		(*unbind)(int group);
 	bool		(*compare)(struct net *net, struct sock *sk);
 };
 
diff --git a/include/linux/nfs.h b/include/linux/nfs.h
index 3e794c12e90..610af5155ef 100644
--- a/include/linux/nfs.h
+++ b/include/linux/nfs.h
@@ -46,6 +46,9 @@ static inline void nfs_copy_fh(struct nfs_fh *target, const struct nfs_fh *sourc
 enum nfs3_stable_how {
 	NFS_UNSTABLE = 0,
 	NFS_DATA_SYNC = 1,
-	NFS_FILE_SYNC = 2
+	NFS_FILE_SYNC = 2,
+
+	/* used by direct.c to mark verf as invalid */
+	NFS_INVALID_STABLE_HOW = -1
 };
 #endif /* _LINUX_NFS_H */
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 12c2cb947df..a1e3064a8d9 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -399,8 +399,6 @@ enum lock_type4 {
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
 #define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
 #define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
-#define FATTR4_WORD2_CHANGE_SECURITY_LABEL \
-					(1UL << 17)
 
 /* MDS threshold bitmap bits */
 #define THRESHOLD_RD                    (1UL << 0)
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index fa6918b0f82..e30f6059ecd 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -459,13 +459,12 @@ extern int nfs3_removexattr (struct dentry *, const char *name);
 /*
  * linux/fs/nfs/direct.c
  */
-extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t,
-			unsigned long);
+extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t);
 extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
-			const struct iovec *iov, unsigned long nr_segs,
+			struct iov_iter *iter,
 			loff_t pos, bool uio);
 extern ssize_t nfs_file_direct_write(struct kiocb *iocb,
-			const struct iovec *iov, unsigned long nr_segs,
+			struct iov_iter *iter,
 			loff_t pos, bool uio);
 
 /*
@@ -520,7 +519,6 @@ extern int  nfs_writepage(struct page *page, struct writeback_control *wbc);
 extern int  nfs_writepages(struct address_space *, struct writeback_control *);
 extern int  nfs_flush_incompatible(struct file *file, struct page *page);
 extern int  nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int);
-extern void nfs_writeback_done(struct rpc_task *, struct nfs_write_data *);
 
 /*
  * Try to write back everything synchronously (but check the
@@ -553,7 +551,6 @@ nfs_have_writebacks(struct inode *inode)
 extern int  nfs_readpage(struct file *, struct page *);
 extern int  nfs_readpages(struct file *, struct address_space *,
 		struct list_head *, unsigned);
-extern int  nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
 extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
 			       struct page *);
 
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 92ce5783b70..7d9096d95d4 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -22,12 +22,17 @@
  * Valid flags for a dirty buffer
  */
 enum {
-	PG_BUSY = 0,
-	PG_MAPPED,
-	PG_CLEAN,
-	PG_NEED_COMMIT,
-	PG_NEED_RESCHED,
-	PG_COMMIT_TO_DS,
+	PG_BUSY = 0,		/* nfs_{un}lock_request */
+	PG_MAPPED,		/* page private set for buffered io */
+	PG_CLEAN,		/* write succeeded */
+	PG_COMMIT_TO_DS,	/* used by pnfs layouts */
+	PG_INODE_REF,		/* extra ref held by inode (head req only) */
+	PG_HEADLOCK,		/* page group lock of wb_head */
+	PG_TEARDOWN,		/* page group sync for destroy */
+	PG_UNLOCKPAGE,		/* page group sync bit in read path */
+	PG_UPTODATE,		/* page group sync bit in read path */
+	PG_WB_END,		/* page group sync bit in write path */
+	PG_REMOVE,		/* page group sync bit in write path */
 };
 
 struct nfs_inode;
@@ -43,15 +48,29 @@ struct nfs_page {
 	struct kref		wb_kref;	/* reference count */
 	unsigned long		wb_flags;
 	struct nfs_write_verifier	wb_verf;	/* Commit cookie */
+	struct nfs_page		*wb_this_page;  /* list of reqs for this page */
+	struct nfs_page		*wb_head;       /* head pointer for req list */
 };
 
 struct nfs_pageio_descriptor;
 struct nfs_pageio_ops {
 	void	(*pg_init)(struct nfs_pageio_descriptor *, struct nfs_page *);
-	bool	(*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
+	size_t	(*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *,
+			   struct nfs_page *);
 	int	(*pg_doio)(struct nfs_pageio_descriptor *);
 };
 
+struct nfs_rw_ops {
+	const fmode_t rw_mode;
+	struct nfs_rw_header *(*rw_alloc_header)(void);
+	void (*rw_free_header)(struct nfs_rw_header *);
+	void (*rw_release)(struct nfs_pgio_data *);
+	int  (*rw_done)(struct rpc_task *, struct nfs_pgio_data *, struct inode *);
+	void (*rw_result)(struct rpc_task *, struct nfs_pgio_data *);
+	void (*rw_initiate)(struct nfs_pgio_data *, struct rpc_message *,
+			    struct rpc_task_setup *, int);
+};
+
 struct nfs_pageio_descriptor {
 	struct list_head	pg_list;
 	unsigned long		pg_bytes_written;
@@ -63,6 +82,7 @@ struct nfs_pageio_descriptor {
 
 	struct inode		*pg_inode;
 	const struct nfs_pageio_ops *pg_ops;
+	const struct nfs_rw_ops *pg_rw_ops;
 	int 			pg_ioflags;
 	int			pg_error;
 	const struct rpc_call_ops *pg_rpc_callops;
@@ -75,29 +95,33 @@ struct nfs_pageio_descriptor {
 #define NFS_WBACK_BUSY(req)	(test_bit(PG_BUSY,&(req)->wb_flags))
 
 extern	struct nfs_page *nfs_create_request(struct nfs_open_context *ctx,
-					    struct inode *inode,
 					    struct page *page,
+					    struct nfs_page *last,
 					    unsigned int offset,
 					    unsigned int count);
-extern	void nfs_release_request(struct nfs_page *req);
+extern	void nfs_release_request(struct nfs_page *);
 
 
 extern	void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 			     struct inode *inode,
 			     const struct nfs_pageio_ops *pg_ops,
 			     const struct nfs_pgio_completion_ops *compl_ops,
+			     const struct nfs_rw_ops *rw_ops,
 			     size_t bsize,
 			     int how);
 extern	int nfs_pageio_add_request(struct nfs_pageio_descriptor *,
 				   struct nfs_page *);
 extern	void nfs_pageio_complete(struct nfs_pageio_descriptor *desc);
 extern	void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t);
-extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
+extern size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 				struct nfs_page *prev,
 				struct nfs_page *req);
 extern  int nfs_wait_on_request(struct nfs_page *);
 extern	void nfs_unlock_request(struct nfs_page *req);
-extern	void nfs_unlock_and_release_request(struct nfs_page *req);
+extern	void nfs_unlock_and_release_request(struct nfs_page *);
+extern void nfs_page_group_lock(struct nfs_page *);
+extern void nfs_page_group_unlock(struct nfs_page *);
+extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int);
 
 /*
  * Lock the page of an asynchronous request
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 6fb5b2335b5..9a1396e7031 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -489,31 +489,21 @@ struct nfs4_delegreturnres {
 };
 
 /*
- * Arguments to the read call.
+ * Arguments to the write call.
  */
-struct nfs_readargs {
-	struct nfs4_sequence_args	seq_args;
-	struct nfs_fh *		fh;
-	struct nfs_open_context *context;
-	struct nfs_lock_context *lock_context;
-	nfs4_stateid		stateid;
-	__u64			offset;
-	__u32			count;
-	unsigned int		pgbase;
-	struct page **		pages;
+struct nfs_write_verifier {
+	char			data[8];
 };
 
-struct nfs_readres {
-	struct nfs4_sequence_res	seq_res;
-	struct nfs_fattr *	fattr;
-	__u32			count;
-	int                     eof;
+struct nfs_writeverf {
+	struct nfs_write_verifier verifier;
+	enum nfs3_stable_how	committed;
 };
 
 /*
- * Arguments to the write call.
+ * Arguments shared by the read and write call.
  */
-struct nfs_writeargs {
+struct nfs_pgio_args {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh *		fh;
 	struct nfs_open_context *context;
@@ -521,27 +511,20 @@ struct nfs_writeargs {
 	nfs4_stateid		stateid;
 	__u64			offset;
 	__u32			count;
-	enum nfs3_stable_how	stable;
 	unsigned int		pgbase;
 	struct page **		pages;
-	const u32 *		bitmask;
-};
-
-struct nfs_write_verifier {
-	char			data[8];
+	const u32 *		bitmask;	/* used by write */
+	enum nfs3_stable_how	stable;		/* used by write */
 };
 
-struct nfs_writeverf {
-	struct nfs_write_verifier verifier;
-	enum nfs3_stable_how	committed;
-};
-
-struct nfs_writeres {
+struct nfs_pgio_res {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *	fattr;
-	struct nfs_writeverf *	verf;
 	__u32			count;
-	const struct nfs_server *server;
+	int			eof;		/* used by read */
+	struct nfs_writeverf *	verf;		/* used by write */
+	const struct nfs_server *server;	/* used by write */
+
 };
 
 /*
@@ -1129,6 +1112,7 @@ struct pnfs_commit_bucket {
 	struct list_head committing;
 	struct pnfs_layout_segment *wlseg;
 	struct pnfs_layout_segment *clseg;
+	struct nfs_writeverf direct_verf;
 };
 
 struct pnfs_ds_commit_info {
@@ -1264,20 +1248,6 @@ struct nfs_page_array {
 	struct page		*page_array[NFS_PAGEVEC_SIZE];
 };
 
-struct nfs_read_data {
-	struct nfs_pgio_header	*header;
-	struct list_head	list;
-	struct rpc_task		task;
-	struct nfs_fattr	fattr;	/* fattr storage */
-	struct nfs_readargs args;
-	struct nfs_readres  res;
-	unsigned long		timestamp;	/* For lease renewal */
-	int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data);
-	__u64			mds_offset;
-	struct nfs_page_array	pages;
-	struct nfs_client	*ds_clp;	/* pNFS data server */
-};
-
 /* used as flag bits in nfs_pgio_header */
 enum {
 	NFS_IOHDR_ERROR = 0,
@@ -1287,19 +1257,22 @@ enum {
 	NFS_IOHDR_NEED_RESCHED,
 };
 
+struct nfs_pgio_data;
+
 struct nfs_pgio_header {
 	struct inode		*inode;
 	struct rpc_cred		*cred;
 	struct list_head	pages;
-	struct list_head	rpc_list;
+	struct nfs_pgio_data	*data;
 	atomic_t		refcnt;
 	struct nfs_page		*req;
-	struct nfs_writeverf	*verf;
+	struct nfs_writeverf	verf;		/* Used for writes */
 	struct pnfs_layout_segment *lseg;
 	loff_t			io_start;
 	const struct rpc_call_ops *mds_ops;
 	void (*release) (struct nfs_pgio_header *hdr);
 	const struct nfs_pgio_completion_ops *completion_ops;
+	const struct nfs_rw_ops	*rw_ops;
 	struct nfs_direct_req	*dreq;
 	void			*layout_private;
 	spinlock_t		lock;
@@ -1310,30 +1283,24 @@ struct nfs_pgio_header {
 	unsigned long		flags;
 };
 
-struct nfs_read_header {
-	struct nfs_pgio_header	header;
-	struct nfs_read_data	rpc_data;
-};
-
-struct nfs_write_data {
+struct nfs_pgio_data {
 	struct nfs_pgio_header	*header;
-	struct list_head	list;
 	struct rpc_task		task;
 	struct nfs_fattr	fattr;
-	struct nfs_writeverf	verf;
-	struct nfs_writeargs	args;		/* argument struct */
-	struct nfs_writeres	res;		/* result struct */
+	struct nfs_writeverf	verf;		/* Used for writes */
+	struct nfs_pgio_args	args;		/* argument struct */
+	struct nfs_pgio_res	res;		/* result struct */
 	unsigned long		timestamp;	/* For lease renewal */
-	int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data);
+	int (*pgio_done_cb) (struct rpc_task *task, struct nfs_pgio_data *data);
 	__u64			mds_offset;	/* Filelayout dense stripe */
 	struct nfs_page_array	pages;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
+	int			ds_idx;		/* ds index if ds_clp is set */
 };
 
-struct nfs_write_header {
+struct nfs_rw_header {
 	struct nfs_pgio_header	header;
-	struct nfs_write_data	rpc_data;
-	struct nfs_writeverf	verf;
+	struct nfs_pgio_data	rpc_data;
 };
 
 struct nfs_mds_commit_info {
@@ -1465,16 +1432,11 @@ struct nfs_rpc_ops {
 			     struct nfs_pathconf *);
 	int	(*set_capabilities)(struct nfs_server *, struct nfs_fh *);
 	int	(*decode_dirent)(struct xdr_stream *, struct nfs_entry *, int);
-	void	(*read_setup)   (struct nfs_read_data *, struct rpc_message *);
-	void	(*read_pageio_init)(struct nfs_pageio_descriptor *, struct inode *,
-				    const struct nfs_pgio_completion_ops *);
-	int	(*read_rpc_prepare)(struct rpc_task *, struct nfs_read_data *);
-	int	(*read_done)  (struct rpc_task *, struct nfs_read_data *);
-	void	(*write_setup)  (struct nfs_write_data *, struct rpc_message *);
-	void	(*write_pageio_init)(struct nfs_pageio_descriptor *, struct inode *, int,
-				     const struct nfs_pgio_completion_ops *);
-	int	(*write_rpc_prepare)(struct rpc_task *, struct nfs_write_data *);
-	int	(*write_done)  (struct rpc_task *, struct nfs_write_data *);
+	int	(*pgio_rpc_prepare)(struct rpc_task *, struct nfs_pgio_data *);
+	void	(*read_setup)   (struct nfs_pgio_data *, struct rpc_message *);
+	int	(*read_done)  (struct rpc_task *, struct nfs_pgio_data *);
+	void	(*write_setup)  (struct nfs_pgio_data *, struct rpc_message *);
+	int	(*write_done)  (struct rpc_task *, struct nfs_pgio_data *);
 	void	(*commit_setup) (struct nfs_commit_data *, struct rpc_message *);
 	void	(*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *);
 	int	(*commit_done) (struct rpc_task *, struct nfs_commit_data *);
diff --git a/include/linux/nfsd/debug.h b/include/linux/nfsd/debug.h
deleted file mode 100644
index 19ef8375b57..00000000000
--- a/include/linux/nfsd/debug.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * linux/include/linux/nfsd/debug.h
- *
- * Debugging-related stuff for nfsd
- *
- * Copyright (C) 1995 Olaf Kirch <okir@monad.swb.de>
- */
-#ifndef LINUX_NFSD_DEBUG_H
-#define LINUX_NFSD_DEBUG_H
-
-#include <uapi/linux/nfsd/debug.h>
-
-# undef ifdebug
-# ifdef NFSD_DEBUG
-#  define ifdebug(flag)		if (nfsd_debug & NFSDDBG_##flag)
-# else
-#  define ifdebug(flag)		if (0)
-# endif
-#endif /* LINUX_NFSD_DEBUG_H */
diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h
deleted file mode 100644
index a93593f1fa4..00000000000
--- a/include/linux/nfsd/nfsfh.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * include/linux/nfsd/nfsfh.h
- *
- * This file describes the layout of the file handles as passed
- * over the wire.
- *
- * Earlier versions of knfsd used to sign file handles using keyed MD5
- * or SHA. I've removed this code, because it doesn't give you more
- * security than blocking external access to port 2049 on your firewall.
- *
- * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
- */
-#ifndef _LINUX_NFSD_FH_H
-#define _LINUX_NFSD_FH_H
-
-# include <linux/sunrpc/svc.h>
-#include <uapi/linux/nfsd/nfsfh.h>
-
-static inline __u32 ino_t_to_u32(ino_t ino)
-{
-	return (__u32) ino;
-}
-
-static inline ino_t u32_to_ino_t(__u32 uino)
-{
-	return (ino_t) uino;
-}
-
-/*
- * This is the internal representation of an NFS handle used in knfsd.
- * pre_mtime/post_version will be used to support wcc_attr's in NFSv3.
- */
-typedef struct svc_fh {
-	struct knfsd_fh		fh_handle;	/* FH data */
-	struct dentry *		fh_dentry;	/* validated dentry */
-	struct svc_export *	fh_export;	/* export pointer */
-	int			fh_maxsize;	/* max size for fh_handle */
-
-	unsigned char		fh_locked;	/* inode locked by us */
-	unsigned char		fh_want_write;	/* remount protection taken */
-
-#ifdef CONFIG_NFSD_V3
-	unsigned char		fh_post_saved;	/* post-op attrs saved */
-	unsigned char		fh_pre_saved;	/* pre-op attrs saved */
-
-	/* Pre-op attributes saved during fh_lock */
-	__u64			fh_pre_size;	/* size before operation */
-	struct timespec		fh_pre_mtime;	/* mtime before oper */
-	struct timespec		fh_pre_ctime;	/* ctime before oper */
-	/*
-	 * pre-op nfsv4 change attr: note must check IS_I_VERSION(inode)
-	 *  to find out if it is valid.
-	 */
-	u64			fh_pre_change;
-
-	/* Post-op attributes saved in fh_unlock */
-	struct kstat		fh_post_attr;	/* full attrs after operation */
-	u64			fh_post_change; /* nfsv4 change; see above */
-#endif /* CONFIG_NFSD_V3 */
-
-} svc_fh;
-
-#endif /* _LINUX_NFSD_FH_H */
diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h
index c8d7f3965ff..20163b9a0ea 100644
--- a/include/linux/nl802154.h
+++ b/include/linux/nl802154.h
@@ -80,6 +80,22 @@ enum {
 
 	IEEE802154_ATTR_FRAME_RETRIES,
 
+	IEEE802154_ATTR_LLSEC_ENABLED,
+	IEEE802154_ATTR_LLSEC_SECLEVEL,
+	IEEE802154_ATTR_LLSEC_KEY_MODE,
+	IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT,
+	IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED,
+	IEEE802154_ATTR_LLSEC_KEY_ID,
+	IEEE802154_ATTR_LLSEC_FRAME_COUNTER,
+	IEEE802154_ATTR_LLSEC_KEY_BYTES,
+	IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES,
+	IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS,
+	IEEE802154_ATTR_LLSEC_FRAME_TYPE,
+	IEEE802154_ATTR_LLSEC_CMD_FRAME_ID,
+	IEEE802154_ATTR_LLSEC_SECLEVELS,
+	IEEE802154_ATTR_LLSEC_DEV_OVERRIDE,
+	IEEE802154_ATTR_LLSEC_DEV_KEY_MODE,
+
 	__IEEE802154_ATTR_MAX,
 };
 
@@ -134,6 +150,21 @@ enum {
 
 	IEEE802154_SET_MACPARAMS,
 
+	IEEE802154_LLSEC_GETPARAMS,
+	IEEE802154_LLSEC_SETPARAMS,
+	IEEE802154_LLSEC_LIST_KEY,
+	IEEE802154_LLSEC_ADD_KEY,
+	IEEE802154_LLSEC_DEL_KEY,
+	IEEE802154_LLSEC_LIST_DEV,
+	IEEE802154_LLSEC_ADD_DEV,
+	IEEE802154_LLSEC_DEL_DEV,
+	IEEE802154_LLSEC_LIST_DEVKEY,
+	IEEE802154_LLSEC_ADD_DEVKEY,
+	IEEE802154_LLSEC_DEL_DEVKEY,
+	IEEE802154_LLSEC_LIST_SECLEVEL,
+	IEEE802154_LLSEC_ADD_SECLEVEL,
+	IEEE802154_LLSEC_DEL_SECLEVEL,
+
 	__IEEE802154_CMD_MAX,
 };
 
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 6a45fb583ff..447775ee2c4 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -32,15 +32,24 @@ static inline void touch_nmi_watchdog(void)
 #ifdef arch_trigger_all_cpu_backtrace
 static inline bool trigger_all_cpu_backtrace(void)
 {
-	arch_trigger_all_cpu_backtrace();
+	arch_trigger_all_cpu_backtrace(true);
 
 	return true;
 }
+static inline bool trigger_allbutself_cpu_backtrace(void)
+{
+	arch_trigger_all_cpu_backtrace(false);
+	return true;
+}
 #else
 static inline bool trigger_all_cpu_backtrace(void)
 {
 	return false;
 }
+static inline bool trigger_allbutself_cpu_backtrace(void)
+{
+	return false;
+}
 #endif
 
 #ifdef CONFIG_LOCKUP_DETECTOR
@@ -48,6 +57,7 @@ int hw_nmi_is_cpu_stuck(struct pt_regs *);
 u64 hw_nmi_get_sample_period(int watchdog_thresh);
 extern int watchdog_user_enabled;
 extern int watchdog_thresh;
+extern int sysctl_softlockup_all_cpu_backtrace;
 struct ctl_table;
 extern int proc_dowatchdog(struct ctl_table *, int ,
 			   void __user *, size_t *, loff_t *);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index a50173ca1d7..2bf403195c0 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -1,6 +1,6 @@
 /*
  * Definitions for the NVM Express interface
- * Copyright (c) 2011-2013, Intel Corporation.
+ * Copyright (c) 2011-2014, Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -10,10 +10,6 @@
  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef _LINUX_NVME_H
@@ -66,8 +62,8 @@ enum {
 
 #define NVME_VS(major, minor)	(major << 16 | minor)
 
-extern unsigned char io_timeout;
-#define NVME_IO_TIMEOUT	(io_timeout * HZ)
+extern unsigned char nvme_io_timeout;
+#define NVME_IO_TIMEOUT	(nvme_io_timeout * HZ)
 
 /*
  * Represents an NVM Express device.  Each nvme_dev is a PCI function.
@@ -94,7 +90,7 @@ struct nvme_dev {
 	struct miscdevice miscdev;
 	work_func_t reset_workfn;
 	struct work_struct reset_work;
-	struct notifier_block nb;
+	struct work_struct cpu_work;
 	char name[12];
 	char serial[20];
 	char model[40];
@@ -103,6 +99,7 @@ struct nvme_dev {
 	u32 stripe_size;
 	u16 oncs;
 	u16 abort_limit;
+	u8 vwc;
 	u8 initialized;
 };
 
@@ -159,7 +156,6 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
 			struct nvme_iod *iod);
 int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_command *, u32 *);
-int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns);
 int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *,
 							u32 *result);
 int nvme_identify(struct nvme_dev *, unsigned nsid, unsigned cns,
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 05117899fcb..0ff360d5b3b 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -73,6 +73,8 @@ extern int early_init_dt_scan_root(unsigned long node, const char *uname,
 				   int depth, void *data);
 
 extern bool early_init_dt_scan(void *params);
+extern bool early_init_dt_verify(void *params);
+extern void early_init_dt_scan_nodes(void);
 
 extern const char *of_flat_dt_get_machine_name(void);
 extern const void *of_flat_dt_match_machine(const void *default_match,
@@ -84,6 +86,7 @@ extern void unflatten_and_copy_device_tree(void);
 extern void early_init_devtree(void *);
 extern void early_get_first_memblock_info(void *, phys_addr_t *);
 extern u64 fdt_translate_address(const void *blob, int node_offset);
+extern void of_fdt_limit_memory(int limit);
 #else /* CONFIG_OF_FLATTREE */
 static inline void early_init_fdt_scan_reserved_mem(void) {}
 static inline const char *of_flat_dt_get_machine_name(void) { return NULL; }
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 881a7c3571f..d449018d072 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -22,9 +22,6 @@ extern struct phy_device *of_phy_connect(struct net_device *dev,
 struct phy_device *of_phy_attach(struct net_device *dev,
 				 struct device_node *phy_np, u32 flags,
 				 phy_interface_t iface);
-extern struct phy_device *of_phy_connect_fixed_link(struct net_device *dev,
-					 void (*hndlr)(struct net_device *),
-					 phy_interface_t iface);
 
 extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np);
 
@@ -59,17 +56,25 @@ static inline struct phy_device *of_phy_attach(struct net_device *dev,
 	return NULL;
 }
 
-static inline struct phy_device *of_phy_connect_fixed_link(struct net_device *dev,
-							   void (*hndlr)(struct net_device *),
-							   phy_interface_t iface)
+static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np)
 {
 	return NULL;
 }
+#endif /* CONFIG_OF */
 
-static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np)
+#if defined(CONFIG_OF) && defined(CONFIG_FIXED_PHY)
+extern int of_phy_register_fixed_link(struct device_node *np);
+extern bool of_phy_is_fixed_link(struct device_node *np);
+#else
+static inline int of_phy_register_fixed_link(struct device_node *np)
 {
-	return NULL;
+	return -ENOSYS;
 }
-#endif /* CONFIG_OF */
+static inline bool of_phy_is_fixed_link(struct device_node *np)
+{
+	return false;
+}
+#endif
+
 
 #endif /* __LINUX_OF_MDIO_H */
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index c29a6dee6be..88e6ea4a5d3 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -1,23 +1,6 @@
-/*
- * OMAP DMA Engine support
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
 #ifndef __LINUX_OMAP_DMA_H
 #define __LINUX_OMAP_DMA_H
-
-struct dma_chan;
-
-#if defined(CONFIG_DMA_OMAP) || (defined(CONFIG_DMA_OMAP_MODULE) && defined(MODULE))
-bool omap_dma_filter_fn(struct dma_chan *, void *);
-#else
-static inline bool omap_dma_filter_fn(struct dma_chan *c, void *d)
-{
-	return false;
-}
-#endif
+#include <linux/omap-dmaengine.h>
 
 /*
  *  Legacy OMAP DMA handling defines and functions
diff --git a/include/linux/omap-dmaengine.h b/include/linux/omap-dmaengine.h
new file mode 100644
index 00000000000..8e6906c72e9
--- /dev/null
+++ b/include/linux/omap-dmaengine.h
@@ -0,0 +1,21 @@
+/*
+ * OMAP DMA Engine support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __LINUX_OMAP_DMAENGINE_H
+#define __LINUX_OMAP_DMAENGINE_H
+
+struct dma_chan;
+
+#if defined(CONFIG_DMA_OMAP) || (defined(CONFIG_DMA_OMAP_MODULE) && defined(MODULE))
+bool omap_dma_filter_fn(struct dma_chan *, void *);
+#else
+static inline bool omap_dma_filter_fn(struct dma_chan *c, void *d)
+{
+	return false;
+}
+#endif
+#endif /* __LINUX_OMAP_DMAENGINE_H */
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
new file mode 100644
index 00000000000..90230d5811c
--- /dev/null
+++ b/include/linux/osq_lock.h
@@ -0,0 +1,27 @@
+#ifndef __LINUX_OSQ_LOCK_H
+#define __LINUX_OSQ_LOCK_H
+
+/*
+ * An MCS like lock especially tailored for optimistic spinning for sleeping
+ * lock implementations (mutex, rwsem, etc).
+ */
+
+#define OSQ_UNLOCKED_VAL (0)
+
+struct optimistic_spin_queue {
+	/*
+	 * Stores an encoded value of the CPU # of the tail node in the queue.
+	 * If the queue is empty, then it's set to OSQ_UNLOCKED_VAL.
+	 */
+	atomic_t tail;
+};
+
+/* Init macro and function. */
+#define OSQ_LOCK_UNLOCKED { ATOMIC_INIT(OSQ_UNLOCKED_VAL) }
+
+static inline void osq_lock_init(struct optimistic_spin_queue *lock)
+{
+	atomic_set(&lock->tail, OSQ_UNLOCKED_VAL);
+}
+
+#endif
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 2093eb72785..8304959ad33 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -319,13 +319,23 @@ CLEARPAGEFLAG(Uptodate, uptodate)
 extern void cancel_dirty_page(struct page *page, unsigned int account_size);
 
 int test_clear_page_writeback(struct page *page);
-int test_set_page_writeback(struct page *page);
+int __test_set_page_writeback(struct page *page, bool keep_write);
+
+#define test_set_page_writeback(page)			\
+	__test_set_page_writeback(page, false)
+#define test_set_page_writeback_keepwrite(page)	\
+	__test_set_page_writeback(page, true)
 
 static inline void set_page_writeback(struct page *page)
 {
 	test_set_page_writeback(page);
 }
 
+static inline void set_page_writeback_keepwrite(struct page *page)
+{
+	test_set_page_writeback_keepwrite(page);
+}
+
 #ifdef CONFIG_PAGEFLAGS_EXTENDED
 /*
  * System with lots of page flags available. This allows separate
@@ -350,6 +360,9 @@ static inline void ClearPageCompound(struct page *page)
 	ClearPageHead(page);
 }
 #endif
+
+#define PG_head_mask ((1L << PG_head))
+
 #else
 /*
  * Reduce page flag use as much as possible by overlapping
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 0a97b583ee8..e1474ae18c8 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -399,6 +399,18 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
 }
 
 /*
+ * Get the offset in PAGE_SIZE.
+ * (TODO: hugepage should have ->index in PAGE_SIZE)
+ */
+static inline pgoff_t page_to_pgoff(struct page *page)
+{
+	if (unlikely(PageHeadHuge(page)))
+		return page->index << compound_order(page);
+	else
+		return page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+}
+
+/*
  * Return byte-offset into filesystem object for page.
  */
 static inline loff_t page_offset(struct page *page)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 71d9673c1b2..6ed3647b38d 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -164,13 +164,17 @@ enum pci_dev_flags {
 	/* INTX_DISABLE in PCI_COMMAND register disables MSI
 	 * generation too.
 	 */
-	PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG = (__force pci_dev_flags_t) 1,
+	PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG = (__force pci_dev_flags_t) (1 << 0),
 	/* Device configuration is irrevocably lost if disabled into D3 */
-	PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2,
+	PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) (1 << 1),
 	/* Provide indication device is assigned by a Virtual Machine Manager */
-	PCI_DEV_FLAGS_ASSIGNED = (__force pci_dev_flags_t) 4,
+	PCI_DEV_FLAGS_ASSIGNED = (__force pci_dev_flags_t) (1 << 2),
 	/* Flag for quirk use to store if quirk-specific ACS is enabled */
-	PCI_DEV_FLAGS_ACS_ENABLED_QUIRK = (__force pci_dev_flags_t) 8,
+	PCI_DEV_FLAGS_ACS_ENABLED_QUIRK = (__force pci_dev_flags_t) (1 << 3),
+	/* Flag to indicate the device uses dma_alias_devfn */
+	PCI_DEV_FLAGS_DMA_ALIAS_DEVFN = (__force pci_dev_flags_t) (1 << 4),
+	/* Use a PCIe-to-PCI bridge alias even if !pci_is_pcie */
+	PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5),
 };
 
 enum pci_irq_reroute_variant {
@@ -268,6 +272,7 @@ struct pci_dev {
 	u8		rom_base_reg;	/* which config register controls the ROM */
 	u8		pin;		/* which interrupt pin this device uses */
 	u16		pcie_flags_reg;	/* cached PCIe Capabilities Register */
+	u8		dma_alias_devfn;/* devfn of DMA alias, if any */
 
 	struct pci_driver *driver;	/* which driver has allocated this device */
 	u64		dma_mask;	/* Mask of the bits of bus address this
@@ -973,6 +978,8 @@ int pci_try_reset_slot(struct pci_slot *slot);
 int pci_probe_reset_bus(struct pci_bus *bus);
 int pci_reset_bus(struct pci_bus *bus);
 int pci_try_reset_bus(struct pci_bus *bus);
+void pci_reset_secondary_bus(struct pci_dev *dev);
+void pcibios_reset_secondary_bus(struct pci_dev *dev);
 void pci_reset_bridge_secondary_bus(struct pci_dev *dev);
 void pci_update_resource(struct pci_dev *dev, int resno);
 int __must_check pci_assign_resource(struct pci_dev *dev, int i);
@@ -1181,7 +1188,6 @@ int pci_msix_vec_count(struct pci_dev *dev);
 int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec);
 void pci_msix_shutdown(struct pci_dev *dev);
 void pci_disable_msix(struct pci_dev *dev);
-void msi_remove_pci_irq_vectors(struct pci_dev *dev);
 void pci_restore_msi_state(struct pci_dev *dev);
 int pci_msi_enabled(void);
 int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec);
@@ -1212,7 +1218,6 @@ static inline int pci_enable_msix(struct pci_dev *dev,
 { return -ENOSYS; }
 static inline void pci_msix_shutdown(struct pci_dev *dev) { }
 static inline void pci_disable_msix(struct pci_dev *dev) { }
-static inline void msi_remove_pci_irq_vectors(struct pci_dev *dev) { }
 static inline void pci_restore_msi_state(struct pci_dev *dev) { }
 static inline int pci_msi_enabled(void) { return 0; }
 static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec,
@@ -1809,6 +1814,10 @@ static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev)
 }
 #endif
 
+int pci_for_each_dma_alias(struct pci_dev *pdev,
+			   int (*fn)(struct pci_dev *pdev,
+				     u16 alias, void *data), void *data);
+
 /**
  * pci_find_upstream_pcie_bridge - find upstream PCIe-to-PCI bridge of a device
  * @pdev: the PCI device
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 7fa31731c85..6ed0bb73a86 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -6,6 +6,8 @@
  *	Do not add new entries to this file unless the definitions
  *	are shared between multiple drivers.
  */
+#ifndef _LINUX_PCI_IDS_H
+#define _LINUX_PCI_IDS_H
 
 /* Device classes and subclasses */
 
@@ -2968,3 +2970,5 @@
 #define PCI_DEVICE_ID_XEN_PLATFORM	0x0001
 
 #define PCI_VENDOR_ID_OCZ		0x1b85
+
+#endif /* _LINUX_PCI_IDS_H */
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index a5fc7d01aad..cfd56046ece 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -1,6 +1,40 @@
+/*
+ * linux/percpu-defs.h - basic definitions for percpu areas
+ *
+ * DO NOT INCLUDE DIRECTLY OUTSIDE PERCPU IMPLEMENTATION PROPER.
+ *
+ * This file is separate from linux/percpu.h to avoid cyclic inclusion
+ * dependency from arch header files.  Only to be included from
+ * asm/percpu.h.
+ *
+ * This file includes macros necessary to declare percpu sections and
+ * variables, and definitions of percpu accessors and operations.  It
+ * should provide enough percpu features to arch header files even when
+ * they can only include asm/percpu.h to avoid cyclic inclusion dependency.
+ */
+
 #ifndef _LINUX_PERCPU_DEFS_H
 #define _LINUX_PERCPU_DEFS_H
 
+#ifdef CONFIG_SMP
+
+#ifdef MODULE
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
+#define PER_CPU_ALIGNED_SECTION ""
+#else
+#define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
+#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
+#endif
+#define PER_CPU_FIRST_SECTION "..first"
+
+#else
+
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
+#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
+#define PER_CPU_FIRST_SECTION ""
+
+#endif
+
 /*
  * Base implementations of per-CPU variable declarations and definitions, where
  * the section in which the variable is to be placed is provided by the
@@ -19,19 +53,6 @@
 	__attribute__((section(".discard"), unused))
 
 /*
- * Macro which verifies @ptr is a percpu pointer without evaluating
- * @ptr.  This is to be used in percpu accessors to verify that the
- * input parameter is a percpu pointer.
- *
- * + 0 is required in order to convert the pointer type from a
- * potential array type to a pointer to a single item of the array.
- */
-#define __verify_pcpu_ptr(ptr)	do {					\
-	const void __percpu *__vpp_verify = (typeof((ptr) + 0))NULL;	\
-	(void)__vpp_verify;						\
-} while (0)
-
-/*
  * s390 and alpha modules require percpu variables to be defined as
  * weak to force the compiler to generate GOT based external
  * references for them.  This is necessary because percpu sections
@@ -146,10 +167,10 @@
  * Declaration/definition used for per-CPU variables that must be read mostly.
  */
 #define DECLARE_PER_CPU_READ_MOSTLY(type, name)			\
-	DECLARE_PER_CPU_SECTION(type, name, "..readmostly")
+	DECLARE_PER_CPU_SECTION(type, name, "..read_mostly")
 
 #define DEFINE_PER_CPU_READ_MOSTLY(type, name)				\
-	DEFINE_PER_CPU_SECTION(type, name, "..readmostly")
+	DEFINE_PER_CPU_SECTION(type, name, "..read_mostly")
 
 /*
  * Intermodule exports for per-CPU variables.  sparse forgets about
@@ -164,4 +185,337 @@
 #define EXPORT_PER_CPU_SYMBOL_GPL(var)
 #endif
 
+/*
+ * Accessors and operations.
+ */
+#ifndef __ASSEMBLY__
+
+/*
+ * __verify_pcpu_ptr() verifies @ptr is a percpu pointer without evaluating
+ * @ptr and is invoked once before a percpu area is accessed by all
+ * accessors and operations.  This is performed in the generic part of
+ * percpu and arch overrides don't need to worry about it; however, if an
+ * arch wants to implement an arch-specific percpu accessor or operation,
+ * it may use __verify_pcpu_ptr() to verify the parameters.
+ *
+ * + 0 is required in order to convert the pointer type from a
+ * potential array type to a pointer to a single item of the array.
+ */
+#define __verify_pcpu_ptr(ptr)						\
+do {									\
+	const void __percpu *__vpp_verify = (typeof((ptr) + 0))NULL;	\
+	(void)__vpp_verify;						\
+} while (0)
+
+#ifdef CONFIG_SMP
+
+/*
+ * Add an offset to a pointer but keep the pointer as-is.  Use RELOC_HIDE()
+ * to prevent the compiler from making incorrect assumptions about the
+ * pointer value.  The weird cast keeps both GCC and sparse happy.
+ */
+#define SHIFT_PERCPU_PTR(__p, __offset)					\
+	RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset))
+
+#define per_cpu_ptr(ptr, cpu)						\
+({									\
+	__verify_pcpu_ptr(ptr);						\
+	SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)));			\
+})
+
+#define raw_cpu_ptr(ptr)						\
+({									\
+	__verify_pcpu_ptr(ptr);						\
+	arch_raw_cpu_ptr(ptr);						\
+})
+
+#ifdef CONFIG_DEBUG_PREEMPT
+#define this_cpu_ptr(ptr)						\
+({									\
+	__verify_pcpu_ptr(ptr);						\
+	SHIFT_PERCPU_PTR(ptr, my_cpu_offset);				\
+})
+#else
+#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr)
+#endif
+
+#else	/* CONFIG_SMP */
+
+#define VERIFY_PERCPU_PTR(__p)						\
+({									\
+	__verify_pcpu_ptr(__p);						\
+	(typeof(*(__p)) __kernel __force *)(__p);			\
+})
+
+#define per_cpu_ptr(ptr, cpu)	({ (void)(cpu); VERIFY_PERCPU_PTR(ptr); })
+#define raw_cpu_ptr(ptr)	per_cpu_ptr(ptr, 0)
+#define this_cpu_ptr(ptr)	raw_cpu_ptr(ptr)
+
+#endif	/* CONFIG_SMP */
+
+#define per_cpu(var, cpu)	(*per_cpu_ptr(&(var), cpu))
+#define __raw_get_cpu_var(var)	(*raw_cpu_ptr(&(var)))
+#define __get_cpu_var(var)	(*this_cpu_ptr(&(var)))
+
+/* keep until we have removed all uses of __this_cpu_ptr */
+#define __this_cpu_ptr(ptr)	raw_cpu_ptr(ptr)
+
+/*
+ * Must be an lvalue. Since @var must be a simple identifier,
+ * we force a syntax error here if it isn't.
+ */
+#define get_cpu_var(var)						\
+(*({									\
+	preempt_disable();						\
+	this_cpu_ptr(&var);						\
+}))
+
+/*
+ * The weird & is necessary because sparse considers (void)(var) to be
+ * a direct dereference of percpu variable (var).
+ */
+#define put_cpu_var(var)						\
+do {									\
+	(void)&(var);							\
+	preempt_enable();						\
+} while (0)
+
+#define get_cpu_ptr(var)						\
+({									\
+	preempt_disable();						\
+	this_cpu_ptr(var);						\
+})
+
+#define put_cpu_ptr(var)						\
+do {									\
+	(void)(var);							\
+	preempt_enable();						\
+} while (0)
+
+/*
+ * Branching function to split up a function into a set of functions that
+ * are called for different scalar sizes of the objects handled.
+ */
+
+extern void __bad_size_call_parameter(void);
+
+#ifdef CONFIG_DEBUG_PREEMPT
+extern void __this_cpu_preempt_check(const char *op);
+#else
+static inline void __this_cpu_preempt_check(const char *op) { }
+#endif
+
+#define __pcpu_size_call_return(stem, variable)				\
+({									\
+	typeof(variable) pscr_ret__;					\
+	__verify_pcpu_ptr(&(variable));					\
+	switch(sizeof(variable)) {					\
+	case 1: pscr_ret__ = stem##1(variable); break;			\
+	case 2: pscr_ret__ = stem##2(variable); break;			\
+	case 4: pscr_ret__ = stem##4(variable); break;			\
+	case 8: pscr_ret__ = stem##8(variable); break;			\
+	default:							\
+		__bad_size_call_parameter(); break;			\
+	}								\
+	pscr_ret__;							\
+})
+
+#define __pcpu_size_call_return2(stem, variable, ...)			\
+({									\
+	typeof(variable) pscr2_ret__;					\
+	__verify_pcpu_ptr(&(variable));					\
+	switch(sizeof(variable)) {					\
+	case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break;	\
+	case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break;	\
+	case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break;	\
+	case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break;	\
+	default:							\
+		__bad_size_call_parameter(); break;			\
+	}								\
+	pscr2_ret__;							\
+})
+
+/*
+ * Special handling for cmpxchg_double.  cmpxchg_double is passed two
+ * percpu variables.  The first has to be aligned to a double word
+ * boundary and the second has to follow directly thereafter.
+ * We enforce this on all architectures even if they don't support
+ * a double cmpxchg instruction, since it's a cheap requirement, and it
+ * avoids breaking the requirement for architectures with the instruction.
+ */
+#define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...)		\
+({									\
+	bool pdcrb_ret__;						\
+	__verify_pcpu_ptr(&(pcp1));					\
+	BUILD_BUG_ON(sizeof(pcp1) != sizeof(pcp2));			\
+	VM_BUG_ON((unsigned long)(&(pcp1)) % (2 * sizeof(pcp1)));	\
+	VM_BUG_ON((unsigned long)(&(pcp2)) !=				\
+		  (unsigned long)(&(pcp1)) + sizeof(pcp1));		\
+	switch(sizeof(pcp1)) {						\
+	case 1: pdcrb_ret__ = stem##1(pcp1, pcp2, __VA_ARGS__); break;	\
+	case 2: pdcrb_ret__ = stem##2(pcp1, pcp2, __VA_ARGS__); break;	\
+	case 4: pdcrb_ret__ = stem##4(pcp1, pcp2, __VA_ARGS__); break;	\
+	case 8: pdcrb_ret__ = stem##8(pcp1, pcp2, __VA_ARGS__); break;	\
+	default:							\
+		__bad_size_call_parameter(); break;			\
+	}								\
+	pdcrb_ret__;							\
+})
+
+#define __pcpu_size_call(stem, variable, ...)				\
+do {									\
+	__verify_pcpu_ptr(&(variable));					\
+	switch(sizeof(variable)) {					\
+		case 1: stem##1(variable, __VA_ARGS__);break;		\
+		case 2: stem##2(variable, __VA_ARGS__);break;		\
+		case 4: stem##4(variable, __VA_ARGS__);break;		\
+		case 8: stem##8(variable, __VA_ARGS__);break;		\
+		default: 						\
+			__bad_size_call_parameter();break;		\
+	}								\
+} while (0)
+
+/*
+ * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@linux.com>
+ *
+ * Optimized manipulation for memory allocated through the per cpu
+ * allocator or for addresses of per cpu variables.
+ *
+ * These operation guarantee exclusivity of access for other operations
+ * on the *same* processor. The assumption is that per cpu data is only
+ * accessed by a single processor instance (the current one).
+ *
+ * The arch code can provide optimized implementation by defining macros
+ * for certain scalar sizes. F.e. provide this_cpu_add_2() to provide per
+ * cpu atomic operations for 2 byte sized RMW actions. If arch code does
+ * not provide operations for a scalar size then the fallback in the
+ * generic code will be used.
+ *
+ * cmpxchg_double replaces two adjacent scalars at once.  The first two
+ * parameters are per cpu variables which have to be of the same size.  A
+ * truth value is returned to indicate success or failure (since a double
+ * register result is difficult to handle).  There is very limited hardware
+ * support for these operations, so only certain sizes may work.
+ */
+
+/*
+ * Operations for contexts where we do not want to do any checks for
+ * preemptions.  Unless strictly necessary, always use [__]this_cpu_*()
+ * instead.
+ *
+ * If there is no other protection through preempt disable and/or disabling
+ * interupts then one of these RMW operations can show unexpected behavior
+ * because the execution thread was rescheduled on another processor or an
+ * interrupt occurred and the same percpu variable was modified from the
+ * interrupt context.
+ */
+#define raw_cpu_read(pcp)		__pcpu_size_call_return(raw_cpu_read_, pcp)
+#define raw_cpu_write(pcp, val)		__pcpu_size_call(raw_cpu_write_, pcp, val)
+#define raw_cpu_add(pcp, val)		__pcpu_size_call(raw_cpu_add_, pcp, val)
+#define raw_cpu_and(pcp, val)		__pcpu_size_call(raw_cpu_and_, pcp, val)
+#define raw_cpu_or(pcp, val)		__pcpu_size_call(raw_cpu_or_, pcp, val)
+#define raw_cpu_add_return(pcp, val)	__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val)
+#define raw_cpu_xchg(pcp, nval)		__pcpu_size_call_return2(raw_cpu_xchg_, pcp, nval)
+#define raw_cpu_cmpxchg(pcp, oval, nval) \
+	__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
+#define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)
+
+#define raw_cpu_sub(pcp, val)		raw_cpu_add(pcp, -(val))
+#define raw_cpu_inc(pcp)		raw_cpu_add(pcp, 1)
+#define raw_cpu_dec(pcp)		raw_cpu_sub(pcp, 1)
+#define raw_cpu_sub_return(pcp, val)	raw_cpu_add_return(pcp, -(typeof(pcp))(val))
+#define raw_cpu_inc_return(pcp)		raw_cpu_add_return(pcp, 1)
+#define raw_cpu_dec_return(pcp)		raw_cpu_add_return(pcp, -1)
+
+/*
+ * Operations for contexts that are safe from preemption/interrupts.  These
+ * operations verify that preemption is disabled.
+ */
+#define __this_cpu_read(pcp)						\
+({									\
+	__this_cpu_preempt_check("read");				\
+	raw_cpu_read(pcp);						\
+})
+
+#define __this_cpu_write(pcp, val)					\
+({									\
+	__this_cpu_preempt_check("write");				\
+	raw_cpu_write(pcp, val);					\
+})
+
+#define __this_cpu_add(pcp, val)					\
+({									\
+	__this_cpu_preempt_check("add");				\
+	raw_cpu_add(pcp, val);						\
+})
+
+#define __this_cpu_and(pcp, val)					\
+({									\
+	__this_cpu_preempt_check("and");				\
+	raw_cpu_and(pcp, val);						\
+})
+
+#define __this_cpu_or(pcp, val)						\
+({									\
+	__this_cpu_preempt_check("or");					\
+	raw_cpu_or(pcp, val);						\
+})
+
+#define __this_cpu_add_return(pcp, val)					\
+({									\
+	__this_cpu_preempt_check("add_return");				\
+	raw_cpu_add_return(pcp, val);					\
+})
+
+#define __this_cpu_xchg(pcp, nval)					\
+({									\
+	__this_cpu_preempt_check("xchg");				\
+	raw_cpu_xchg(pcp, nval);					\
+})
+
+#define __this_cpu_cmpxchg(pcp, oval, nval)				\
+({									\
+	__this_cpu_preempt_check("cmpxchg");				\
+	raw_cpu_cmpxchg(pcp, oval, nval);				\
+})
+
+#define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+({	__this_cpu_preempt_check("cmpxchg_double");			\
+	raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2);	\
+})
+
+#define __this_cpu_sub(pcp, val)	__this_cpu_add(pcp, -(typeof(pcp))(val))
+#define __this_cpu_inc(pcp)		__this_cpu_add(pcp, 1)
+#define __this_cpu_dec(pcp)		__this_cpu_sub(pcp, 1)
+#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(typeof(pcp))(val))
+#define __this_cpu_inc_return(pcp)	__this_cpu_add_return(pcp, 1)
+#define __this_cpu_dec_return(pcp)	__this_cpu_add_return(pcp, -1)
+
+/*
+ * Operations with implied preemption protection.  These operations can be
+ * used without worrying about preemption.  Note that interrupts may still
+ * occur while an operation is in progress and if the interrupt modifies
+ * the variable too then RMW actions may not be reliable.
+ */
+#define this_cpu_read(pcp)		__pcpu_size_call_return(this_cpu_read_, pcp)
+#define this_cpu_write(pcp, val)	__pcpu_size_call(this_cpu_write_, pcp, val)
+#define this_cpu_add(pcp, val)		__pcpu_size_call(this_cpu_add_, pcp, val)
+#define this_cpu_and(pcp, val)		__pcpu_size_call(this_cpu_and_, pcp, val)
+#define this_cpu_or(pcp, val)		__pcpu_size_call(this_cpu_or_, pcp, val)
+#define this_cpu_add_return(pcp, val)	__pcpu_size_call_return2(this_cpu_add_return_, pcp, val)
+#define this_cpu_xchg(pcp, nval)	__pcpu_size_call_return2(this_cpu_xchg_, pcp, nval)
+#define this_cpu_cmpxchg(pcp, oval, nval) \
+	__pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
+#define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
+	__pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)
+
+#define this_cpu_sub(pcp, val)		this_cpu_add(pcp, -(typeof(pcp))(val))
+#define this_cpu_inc(pcp)		this_cpu_add(pcp, 1)
+#define this_cpu_dec(pcp)		this_cpu_sub(pcp, 1)
+#define this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(typeof(pcp))(val))
+#define this_cpu_inc_return(pcp)	this_cpu_add_return(pcp, 1)
+#define this_cpu_dec_return(pcp)	this_cpu_add_return(pcp, -1)
+
+#endif /* __ASSEMBLY__ */
 #endif /* _LINUX_PERCPU_DEFS_H */
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 0afb48fd449..3dfbf237cd8 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -57,11 +57,9 @@ struct percpu_ref {
 	atomic_t		count;
 	/*
 	 * The low bit of the pointer indicates whether the ref is in percpu
-	 * mode; if set, then get/put will manipulate the atomic_t (this is a
-	 * hack because we need to keep the pointer around for
-	 * percpu_ref_kill_rcu())
+	 * mode; if set, then get/put will manipulate the atomic_t.
 	 */
-	unsigned __percpu	*pcpu_count;
+	unsigned long		pcpu_count_ptr;
 	percpu_ref_func_t	*release;
 	percpu_ref_func_t	*confirm_kill;
 	struct rcu_head		rcu;
@@ -69,7 +67,8 @@ struct percpu_ref {
 
 int __must_check percpu_ref_init(struct percpu_ref *ref,
 				 percpu_ref_func_t *release);
-void percpu_ref_cancel_init(struct percpu_ref *ref);
+void percpu_ref_reinit(struct percpu_ref *ref);
+void percpu_ref_exit(struct percpu_ref *ref);
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill);
 
@@ -88,12 +87,28 @@ static inline void percpu_ref_kill(struct percpu_ref *ref)
 	return percpu_ref_kill_and_confirm(ref, NULL);
 }
 
-#define PCPU_STATUS_BITS	2
-#define PCPU_STATUS_MASK	((1 << PCPU_STATUS_BITS) - 1)
-#define PCPU_REF_PTR		0
 #define PCPU_REF_DEAD		1
 
-#define REF_STATUS(count)	(((unsigned long) count) & PCPU_STATUS_MASK)
+/*
+ * Internal helper.  Don't use outside percpu-refcount proper.  The
+ * function doesn't return the pointer and let the caller test it for NULL
+ * because doing so forces the compiler to generate two conditional
+ * branches as it can't assume that @ref->pcpu_count is not NULL.
+ */
+static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
+				    unsigned __percpu **pcpu_countp)
+{
+	unsigned long pcpu_ptr = ACCESS_ONCE(ref->pcpu_count_ptr);
+
+	/* paired with smp_store_release() in percpu_ref_reinit() */
+	smp_read_barrier_depends();
+
+	if (unlikely(pcpu_ptr & PCPU_REF_DEAD))
+		return false;
+
+	*pcpu_countp = (unsigned __percpu *)pcpu_ptr;
+	return true;
+}
 
 /**
  * percpu_ref_get - increment a percpu refcount
@@ -107,9 +122,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
 
 	rcu_read_lock_sched();
 
-	pcpu_count = ACCESS_ONCE(ref->pcpu_count);
-
-	if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR))
+	if (__pcpu_ref_alive(ref, &pcpu_count))
 		this_cpu_inc(*pcpu_count);
 	else
 		atomic_inc(&ref->count);
@@ -121,6 +134,34 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
  * percpu_ref_tryget - try to increment a percpu refcount
  * @ref: percpu_ref to try-get
  *
+ * Increment a percpu refcount unless its count already reached zero.
+ * Returns %true on success; %false on failure.
+ *
+ * The caller is responsible for ensuring that @ref stays accessible.
+ */
+static inline bool percpu_ref_tryget(struct percpu_ref *ref)
+{
+	unsigned __percpu *pcpu_count;
+	int ret = false;
+
+	rcu_read_lock_sched();
+
+	if (__pcpu_ref_alive(ref, &pcpu_count)) {
+		this_cpu_inc(*pcpu_count);
+		ret = true;
+	} else {
+		ret = atomic_inc_not_zero(&ref->count);
+	}
+
+	rcu_read_unlock_sched();
+
+	return ret;
+}
+
+/**
+ * percpu_ref_tryget_live - try to increment a live percpu refcount
+ * @ref: percpu_ref to try-get
+ *
  * Increment a percpu refcount unless it has already been killed.  Returns
  * %true on success; %false on failure.
  *
@@ -128,17 +169,17 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
  * will fail.  For such guarantee, percpu_ref_kill_and_confirm() should be
  * used.  After the confirm_kill callback is invoked, it's guaranteed that
  * no new reference will be given out by percpu_ref_tryget().
+ *
+ * The caller is responsible for ensuring that @ref stays accessible.
  */
-static inline bool percpu_ref_tryget(struct percpu_ref *ref)
+static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 {
 	unsigned __percpu *pcpu_count;
 	int ret = false;
 
 	rcu_read_lock_sched();
 
-	pcpu_count = ACCESS_ONCE(ref->pcpu_count);
-
-	if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) {
+	if (__pcpu_ref_alive(ref, &pcpu_count)) {
 		this_cpu_inc(*pcpu_count);
 		ret = true;
 	}
@@ -161,9 +202,7 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
 
 	rcu_read_lock_sched();
 
-	pcpu_count = ACCESS_ONCE(ref->pcpu_count);
-
-	if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR))
+	if (__pcpu_ref_alive(ref, &pcpu_count))
 		this_cpu_dec(*pcpu_count);
 	else if (unlikely(atomic_dec_and_test(&ref->count)))
 		ref->release(ref);
@@ -171,4 +210,19 @@ static inline void percpu_ref_put(struct percpu_ref *ref)
 	rcu_read_unlock_sched();
 }
 
+/**
+ * percpu_ref_is_zero - test whether a percpu refcount reached zero
+ * @ref: percpu_ref to test
+ *
+ * Returns %true if @ref reached zero.
+ */
+static inline bool percpu_ref_is_zero(struct percpu_ref *ref)
+{
+	unsigned __percpu *pcpu_count;
+
+	if (__pcpu_ref_alive(ref, &pcpu_count))
+		return false;
+	return !atomic_read(&ref->count);
+}
+
 #endif
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 495c6543a8f..6f61b61b799 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -23,32 +23,6 @@
 	 PERCPU_MODULE_RESERVE)
 #endif
 
-/*
- * Must be an lvalue. Since @var must be a simple identifier,
- * we force a syntax error here if it isn't.
- */
-#define get_cpu_var(var) (*({				\
-	preempt_disable();				\
-	&__get_cpu_var(var); }))
-
-/*
- * The weird & is necessary because sparse considers (void)(var) to be
- * a direct dereference of percpu variable (var).
- */
-#define put_cpu_var(var) do {				\
-	(void)&(var);					\
-	preempt_enable();				\
-} while (0)
-
-#define get_cpu_ptr(var) ({				\
-	preempt_disable();				\
-	this_cpu_ptr(var); })
-
-#define put_cpu_ptr(var) do {				\
-	(void)(var);					\
-	preempt_enable();				\
-} while (0)
-
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(32 << 10)
 
@@ -140,17 +114,6 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
 				pcpu_fc_populate_pte_fn_t populate_pte_fn);
 #endif
 
-/*
- * Use this to get to a cpu's version of the per-cpu object
- * dynamically allocated. Non-atomic access to the current CPU's
- * version should probably be combined with get_cpu()/put_cpu().
- */
-#ifdef CONFIG_SMP
-#define per_cpu_ptr(ptr, cpu)	SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
-#else
-#define per_cpu_ptr(ptr, cpu)	({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); })
-#endif
-
 extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
 extern bool is_kernel_percpu_address(unsigned long addr);
 
@@ -166,640 +129,4 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
 #define alloc_percpu(type)	\
 	(typeof(type) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type))
 
-/*
- * Branching function to split up a function into a set of functions that
- * are called for different scalar sizes of the objects handled.
- */
-
-extern void __bad_size_call_parameter(void);
-
-#ifdef CONFIG_DEBUG_PREEMPT
-extern void __this_cpu_preempt_check(const char *op);
-#else
-static inline void __this_cpu_preempt_check(const char *op) { }
-#endif
-
-#define __pcpu_size_call_return(stem, variable)				\
-({	typeof(variable) pscr_ret__;					\
-	__verify_pcpu_ptr(&(variable));					\
-	switch(sizeof(variable)) {					\
-	case 1: pscr_ret__ = stem##1(variable);break;			\
-	case 2: pscr_ret__ = stem##2(variable);break;			\
-	case 4: pscr_ret__ = stem##4(variable);break;			\
-	case 8: pscr_ret__ = stem##8(variable);break;			\
-	default:							\
-		__bad_size_call_parameter();break;			\
-	}								\
-	pscr_ret__;							\
-})
-
-#define __pcpu_size_call_return2(stem, variable, ...)			\
-({									\
-	typeof(variable) pscr2_ret__;					\
-	__verify_pcpu_ptr(&(variable));					\
-	switch(sizeof(variable)) {					\
-	case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break;	\
-	case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break;	\
-	case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break;	\
-	case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break;	\
-	default:							\
-		__bad_size_call_parameter(); break;			\
-	}								\
-	pscr2_ret__;							\
-})
-
-/*
- * Special handling for cmpxchg_double.  cmpxchg_double is passed two
- * percpu variables.  The first has to be aligned to a double word
- * boundary and the second has to follow directly thereafter.
- * We enforce this on all architectures even if they don't support
- * a double cmpxchg instruction, since it's a cheap requirement, and it
- * avoids breaking the requirement for architectures with the instruction.
- */
-#define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...)		\
-({									\
-	bool pdcrb_ret__;						\
-	__verify_pcpu_ptr(&pcp1);					\
-	BUILD_BUG_ON(sizeof(pcp1) != sizeof(pcp2));			\
-	VM_BUG_ON((unsigned long)(&pcp1) % (2 * sizeof(pcp1)));		\
-	VM_BUG_ON((unsigned long)(&pcp2) !=				\
-		  (unsigned long)(&pcp1) + sizeof(pcp1));		\
-	switch(sizeof(pcp1)) {						\
-	case 1: pdcrb_ret__ = stem##1(pcp1, pcp2, __VA_ARGS__); break;	\
-	case 2: pdcrb_ret__ = stem##2(pcp1, pcp2, __VA_ARGS__); break;	\
-	case 4: pdcrb_ret__ = stem##4(pcp1, pcp2, __VA_ARGS__); break;	\
-	case 8: pdcrb_ret__ = stem##8(pcp1, pcp2, __VA_ARGS__); break;	\
-	default:							\
-		__bad_size_call_parameter(); break;			\
-	}								\
-	pdcrb_ret__;							\
-})
-
-#define __pcpu_size_call(stem, variable, ...)				\
-do {									\
-	__verify_pcpu_ptr(&(variable));					\
-	switch(sizeof(variable)) {					\
-		case 1: stem##1(variable, __VA_ARGS__);break;		\
-		case 2: stem##2(variable, __VA_ARGS__);break;		\
-		case 4: stem##4(variable, __VA_ARGS__);break;		\
-		case 8: stem##8(variable, __VA_ARGS__);break;		\
-		default: 						\
-			__bad_size_call_parameter();break;		\
-	}								\
-} while (0)
-
-/*
- * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@linux.com>
- *
- * Optimized manipulation for memory allocated through the per cpu
- * allocator or for addresses of per cpu variables.
- *
- * These operation guarantee exclusivity of access for other operations
- * on the *same* processor. The assumption is that per cpu data is only
- * accessed by a single processor instance (the current one).
- *
- * The first group is used for accesses that must be done in a
- * preemption safe way since we know that the context is not preempt
- * safe. Interrupts may occur. If the interrupt modifies the variable
- * too then RMW actions will not be reliable.
- *
- * The arch code can provide optimized functions in two ways:
- *
- * 1. Override the function completely. F.e. define this_cpu_add().
- *    The arch must then ensure that the various scalar format passed
- *    are handled correctly.
- *
- * 2. Provide functions for certain scalar sizes. F.e. provide
- *    this_cpu_add_2() to provide per cpu atomic operations for 2 byte
- *    sized RMW actions. If arch code does not provide operations for
- *    a scalar size then the fallback in the generic code will be
- *    used.
- */
-
-#define _this_cpu_generic_read(pcp)					\
-({	typeof(pcp) ret__;						\
-	preempt_disable();						\
-	ret__ = *this_cpu_ptr(&(pcp));					\
-	preempt_enable();						\
-	ret__;								\
-})
-
-#ifndef this_cpu_read
-# ifndef this_cpu_read_1
-#  define this_cpu_read_1(pcp)	_this_cpu_generic_read(pcp)
-# endif
-# ifndef this_cpu_read_2
-#  define this_cpu_read_2(pcp)	_this_cpu_generic_read(pcp)
-# endif
-# ifndef this_cpu_read_4
-#  define this_cpu_read_4(pcp)	_this_cpu_generic_read(pcp)
-# endif
-# ifndef this_cpu_read_8
-#  define this_cpu_read_8(pcp)	_this_cpu_generic_read(pcp)
-# endif
-# define this_cpu_read(pcp)	__pcpu_size_call_return(this_cpu_read_, (pcp))
-#endif
-
-#define _this_cpu_generic_to_op(pcp, val, op)				\
-do {									\
-	unsigned long flags;						\
-	raw_local_irq_save(flags);					\
-	*raw_cpu_ptr(&(pcp)) op val;					\
-	raw_local_irq_restore(flags);					\
-} while (0)
-
-#ifndef this_cpu_write
-# ifndef this_cpu_write_1
-#  define this_cpu_write_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
-# endif
-# ifndef this_cpu_write_2
-#  define this_cpu_write_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
-# endif
-# ifndef this_cpu_write_4
-#  define this_cpu_write_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
-# endif
-# ifndef this_cpu_write_8
-#  define this_cpu_write_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
-# endif
-# define this_cpu_write(pcp, val)	__pcpu_size_call(this_cpu_write_, (pcp), (val))
-#endif
-
-#ifndef this_cpu_add
-# ifndef this_cpu_add_1
-#  define this_cpu_add_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# ifndef this_cpu_add_2
-#  define this_cpu_add_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# ifndef this_cpu_add_4
-#  define this_cpu_add_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# ifndef this_cpu_add_8
-#  define this_cpu_add_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# define this_cpu_add(pcp, val)		__pcpu_size_call(this_cpu_add_, (pcp), (val))
-#endif
-
-#ifndef this_cpu_sub
-# define this_cpu_sub(pcp, val)		this_cpu_add((pcp), -(typeof(pcp))(val))
-#endif
-
-#ifndef this_cpu_inc
-# define this_cpu_inc(pcp)		this_cpu_add((pcp), 1)
-#endif
-
-#ifndef this_cpu_dec
-# define this_cpu_dec(pcp)		this_cpu_sub((pcp), 1)
-#endif
-
-#ifndef this_cpu_and
-# ifndef this_cpu_and_1
-#  define this_cpu_and_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# ifndef this_cpu_and_2
-#  define this_cpu_and_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# ifndef this_cpu_and_4
-#  define this_cpu_and_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# ifndef this_cpu_and_8
-#  define this_cpu_and_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# define this_cpu_and(pcp, val)		__pcpu_size_call(this_cpu_and_, (pcp), (val))
-#endif
-
-#ifndef this_cpu_or
-# ifndef this_cpu_or_1
-#  define this_cpu_or_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# ifndef this_cpu_or_2
-#  define this_cpu_or_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# ifndef this_cpu_or_4
-#  define this_cpu_or_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# ifndef this_cpu_or_8
-#  define this_cpu_or_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# define this_cpu_or(pcp, val)		__pcpu_size_call(this_cpu_or_, (pcp), (val))
-#endif
-
-#define _this_cpu_generic_add_return(pcp, val)				\
-({									\
-	typeof(pcp) ret__;						\
-	unsigned long flags;						\
-	raw_local_irq_save(flags);					\
-	raw_cpu_add(pcp, val);					\
-	ret__ = raw_cpu_read(pcp);					\
-	raw_local_irq_restore(flags);					\
-	ret__;								\
-})
-
-#ifndef this_cpu_add_return
-# ifndef this_cpu_add_return_1
-#  define this_cpu_add_return_1(pcp, val)	_this_cpu_generic_add_return(pcp, val)
-# endif
-# ifndef this_cpu_add_return_2
-#  define this_cpu_add_return_2(pcp, val)	_this_cpu_generic_add_return(pcp, val)
-# endif
-# ifndef this_cpu_add_return_4
-#  define this_cpu_add_return_4(pcp, val)	_this_cpu_generic_add_return(pcp, val)
-# endif
-# ifndef this_cpu_add_return_8
-#  define this_cpu_add_return_8(pcp, val)	_this_cpu_generic_add_return(pcp, val)
-# endif
-# define this_cpu_add_return(pcp, val)	__pcpu_size_call_return2(this_cpu_add_return_, pcp, val)
-#endif
-
-#define this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(typeof(pcp))(val))
-#define this_cpu_inc_return(pcp)	this_cpu_add_return(pcp, 1)
-#define this_cpu_dec_return(pcp)	this_cpu_add_return(pcp, -1)
-
-#define _this_cpu_generic_xchg(pcp, nval)				\
-({	typeof(pcp) ret__;						\
-	unsigned long flags;						\
-	raw_local_irq_save(flags);					\
-	ret__ = raw_cpu_read(pcp);					\
-	raw_cpu_write(pcp, nval);					\
-	raw_local_irq_restore(flags);					\
-	ret__;								\
-})
-
-#ifndef this_cpu_xchg
-# ifndef this_cpu_xchg_1
-#  define this_cpu_xchg_1(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
-# endif
-# ifndef this_cpu_xchg_2
-#  define this_cpu_xchg_2(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
-# endif
-# ifndef this_cpu_xchg_4
-#  define this_cpu_xchg_4(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
-# endif
-# ifndef this_cpu_xchg_8
-#  define this_cpu_xchg_8(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
-# endif
-# define this_cpu_xchg(pcp, nval)	\
-	__pcpu_size_call_return2(this_cpu_xchg_, (pcp), nval)
-#endif
-
-#define _this_cpu_generic_cmpxchg(pcp, oval, nval)			\
-({									\
-	typeof(pcp) ret__;						\
-	unsigned long flags;						\
-	raw_local_irq_save(flags);					\
-	ret__ = raw_cpu_read(pcp);					\
-	if (ret__ == (oval))						\
-		raw_cpu_write(pcp, nval);				\
-	raw_local_irq_restore(flags);					\
-	ret__;								\
-})
-
-#ifndef this_cpu_cmpxchg
-# ifndef this_cpu_cmpxchg_1
-#  define this_cpu_cmpxchg_1(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
-# endif
-# ifndef this_cpu_cmpxchg_2
-#  define this_cpu_cmpxchg_2(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
-# endif
-# ifndef this_cpu_cmpxchg_4
-#  define this_cpu_cmpxchg_4(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
-# endif
-# ifndef this_cpu_cmpxchg_8
-#  define this_cpu_cmpxchg_8(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
-# endif
-# define this_cpu_cmpxchg(pcp, oval, nval)	\
-	__pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
-#endif
-
-/*
- * cmpxchg_double replaces two adjacent scalars at once.  The first
- * two parameters are per cpu variables which have to be of the same
- * size.  A truth value is returned to indicate success or failure
- * (since a double register result is difficult to handle).  There is
- * very limited hardware support for these operations, so only certain
- * sizes may work.
- */
-#define _this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-({									\
-	int ret__;							\
-	unsigned long flags;						\
-	raw_local_irq_save(flags);					\
-	ret__ = raw_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
-			oval1, oval2, nval1, nval2);			\
-	raw_local_irq_restore(flags);					\
-	ret__;								\
-})
-
-#ifndef this_cpu_cmpxchg_double
-# ifndef this_cpu_cmpxchg_double_1
-#  define this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# ifndef this_cpu_cmpxchg_double_2
-#  define this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# ifndef this_cpu_cmpxchg_double_4
-#  define this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# ifndef this_cpu_cmpxchg_double_8
-#  define this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	_this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
-#endif
-
-/*
- * Generic percpu operations for contexts where we do not want to do
- * any checks for preemptiosn.
- *
- * If there is no other protection through preempt disable and/or
- * disabling interupts then one of these RMW operations can show unexpected
- * behavior because the execution thread was rescheduled on another processor
- * or an interrupt occurred and the same percpu variable was modified from
- * the interrupt context.
- */
-#ifndef raw_cpu_read
-# ifndef raw_cpu_read_1
-#  define raw_cpu_read_1(pcp)	(*raw_cpu_ptr(&(pcp)))
-# endif
-# ifndef raw_cpu_read_2
-#  define raw_cpu_read_2(pcp)	(*raw_cpu_ptr(&(pcp)))
-# endif
-# ifndef raw_cpu_read_4
-#  define raw_cpu_read_4(pcp)	(*raw_cpu_ptr(&(pcp)))
-# endif
-# ifndef raw_cpu_read_8
-#  define raw_cpu_read_8(pcp)	(*raw_cpu_ptr(&(pcp)))
-# endif
-# define raw_cpu_read(pcp)	__pcpu_size_call_return(raw_cpu_read_, (pcp))
-#endif
-
-#define raw_cpu_generic_to_op(pcp, val, op)				\
-do {									\
-	*raw_cpu_ptr(&(pcp)) op val;					\
-} while (0)
-
-
-#ifndef raw_cpu_write
-# ifndef raw_cpu_write_1
-#  define raw_cpu_write_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
-# endif
-# ifndef raw_cpu_write_2
-#  define raw_cpu_write_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
-# endif
-# ifndef raw_cpu_write_4
-#  define raw_cpu_write_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
-# endif
-# ifndef raw_cpu_write_8
-#  define raw_cpu_write_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
-# endif
-# define raw_cpu_write(pcp, val)	__pcpu_size_call(raw_cpu_write_, (pcp), (val))
-#endif
-
-#ifndef raw_cpu_add
-# ifndef raw_cpu_add_1
-#  define raw_cpu_add_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# ifndef raw_cpu_add_2
-#  define raw_cpu_add_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# ifndef raw_cpu_add_4
-#  define raw_cpu_add_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# ifndef raw_cpu_add_8
-#  define raw_cpu_add_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# define raw_cpu_add(pcp, val)	__pcpu_size_call(raw_cpu_add_, (pcp), (val))
-#endif
-
-#ifndef raw_cpu_sub
-# define raw_cpu_sub(pcp, val)	raw_cpu_add((pcp), -(val))
-#endif
-
-#ifndef raw_cpu_inc
-# define raw_cpu_inc(pcp)		raw_cpu_add((pcp), 1)
-#endif
-
-#ifndef raw_cpu_dec
-# define raw_cpu_dec(pcp)		raw_cpu_sub((pcp), 1)
-#endif
-
-#ifndef raw_cpu_and
-# ifndef raw_cpu_and_1
-#  define raw_cpu_and_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# ifndef raw_cpu_and_2
-#  define raw_cpu_and_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# ifndef raw_cpu_and_4
-#  define raw_cpu_and_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# ifndef raw_cpu_and_8
-#  define raw_cpu_and_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# define raw_cpu_and(pcp, val)	__pcpu_size_call(raw_cpu_and_, (pcp), (val))
-#endif
-
-#ifndef raw_cpu_or
-# ifndef raw_cpu_or_1
-#  define raw_cpu_or_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# ifndef raw_cpu_or_2
-#  define raw_cpu_or_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# ifndef raw_cpu_or_4
-#  define raw_cpu_or_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# ifndef raw_cpu_or_8
-#  define raw_cpu_or_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# define raw_cpu_or(pcp, val)	__pcpu_size_call(raw_cpu_or_, (pcp), (val))
-#endif
-
-#define raw_cpu_generic_add_return(pcp, val)				\
-({									\
-	raw_cpu_add(pcp, val);						\
-	raw_cpu_read(pcp);						\
-})
-
-#ifndef raw_cpu_add_return
-# ifndef raw_cpu_add_return_1
-#  define raw_cpu_add_return_1(pcp, val)	raw_cpu_generic_add_return(pcp, val)
-# endif
-# ifndef raw_cpu_add_return_2
-#  define raw_cpu_add_return_2(pcp, val)	raw_cpu_generic_add_return(pcp, val)
-# endif
-# ifndef raw_cpu_add_return_4
-#  define raw_cpu_add_return_4(pcp, val)	raw_cpu_generic_add_return(pcp, val)
-# endif
-# ifndef raw_cpu_add_return_8
-#  define raw_cpu_add_return_8(pcp, val)	raw_cpu_generic_add_return(pcp, val)
-# endif
-# define raw_cpu_add_return(pcp, val)	\
-	__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val)
-#endif
-
-#define raw_cpu_sub_return(pcp, val)	raw_cpu_add_return(pcp, -(typeof(pcp))(val))
-#define raw_cpu_inc_return(pcp)	raw_cpu_add_return(pcp, 1)
-#define raw_cpu_dec_return(pcp)	raw_cpu_add_return(pcp, -1)
-
-#define raw_cpu_generic_xchg(pcp, nval)					\
-({	typeof(pcp) ret__;						\
-	ret__ = raw_cpu_read(pcp);					\
-	raw_cpu_write(pcp, nval);					\
-	ret__;								\
-})
-
-#ifndef raw_cpu_xchg
-# ifndef raw_cpu_xchg_1
-#  define raw_cpu_xchg_1(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
-# endif
-# ifndef raw_cpu_xchg_2
-#  define raw_cpu_xchg_2(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
-# endif
-# ifndef raw_cpu_xchg_4
-#  define raw_cpu_xchg_4(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
-# endif
-# ifndef raw_cpu_xchg_8
-#  define raw_cpu_xchg_8(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
-# endif
-# define raw_cpu_xchg(pcp, nval)	\
-	__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval)
-#endif
-
-#define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
-({									\
-	typeof(pcp) ret__;						\
-	ret__ = raw_cpu_read(pcp);					\
-	if (ret__ == (oval))						\
-		raw_cpu_write(pcp, nval);				\
-	ret__;								\
-})
-
-#ifndef raw_cpu_cmpxchg
-# ifndef raw_cpu_cmpxchg_1
-#  define raw_cpu_cmpxchg_1(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
-# endif
-# ifndef raw_cpu_cmpxchg_2
-#  define raw_cpu_cmpxchg_2(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
-# endif
-# ifndef raw_cpu_cmpxchg_4
-#  define raw_cpu_cmpxchg_4(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
-# endif
-# ifndef raw_cpu_cmpxchg_8
-#  define raw_cpu_cmpxchg_8(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
-# endif
-# define raw_cpu_cmpxchg(pcp, oval, nval)	\
-	__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
-#endif
-
-#define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-({									\
-	int __ret = 0;							\
-	if (raw_cpu_read(pcp1) == (oval1) &&				\
-			 raw_cpu_read(pcp2)  == (oval2)) {		\
-		raw_cpu_write(pcp1, (nval1));				\
-		raw_cpu_write(pcp2, (nval2));				\
-		__ret = 1;						\
-	}								\
-	(__ret);							\
-})
-
-#ifndef raw_cpu_cmpxchg_double
-# ifndef raw_cpu_cmpxchg_double_1
-#  define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# ifndef raw_cpu_cmpxchg_double_2
-#  define raw_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# ifndef raw_cpu_cmpxchg_double_4
-#  define raw_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# ifndef raw_cpu_cmpxchg_double_8
-#  define raw_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
-#endif
-
-/*
- * Generic percpu operations for context that are safe from preemption/interrupts.
- */
-#ifndef __this_cpu_read
-# define __this_cpu_read(pcp) \
-	(__this_cpu_preempt_check("read"),__pcpu_size_call_return(raw_cpu_read_, (pcp)))
-#endif
-
-#ifndef __this_cpu_write
-# define __this_cpu_write(pcp, val)					\
-do { __this_cpu_preempt_check("write");					\
-     __pcpu_size_call(raw_cpu_write_, (pcp), (val));			\
-} while (0)
-#endif
-
-#ifndef __this_cpu_add
-# define __this_cpu_add(pcp, val)					 \
-do { __this_cpu_preempt_check("add");					\
-	__pcpu_size_call(raw_cpu_add_, (pcp), (val));			\
-} while (0)
-#endif
-
-#ifndef __this_cpu_sub
-# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(typeof(pcp))(val))
-#endif
-
-#ifndef __this_cpu_inc
-# define __this_cpu_inc(pcp)		__this_cpu_add((pcp), 1)
-#endif
-
-#ifndef __this_cpu_dec
-# define __this_cpu_dec(pcp)		__this_cpu_sub((pcp), 1)
-#endif
-
-#ifndef __this_cpu_and
-# define __this_cpu_and(pcp, val)					\
-do { __this_cpu_preempt_check("and");					\
-	__pcpu_size_call(raw_cpu_and_, (pcp), (val));			\
-} while (0)
-
-#endif
-
-#ifndef __this_cpu_or
-# define __this_cpu_or(pcp, val)					\
-do { __this_cpu_preempt_check("or");					\
-	__pcpu_size_call(raw_cpu_or_, (pcp), (val));			\
-} while (0)
-#endif
-
-#ifndef __this_cpu_add_return
-# define __this_cpu_add_return(pcp, val)	\
-	(__this_cpu_preempt_check("add_return"),__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val))
-#endif
-
-#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(typeof(pcp))(val))
-#define __this_cpu_inc_return(pcp)	__this_cpu_add_return(pcp, 1)
-#define __this_cpu_dec_return(pcp)	__this_cpu_add_return(pcp, -1)
-
-#ifndef __this_cpu_xchg
-# define __this_cpu_xchg(pcp, nval)	\
-	(__this_cpu_preempt_check("xchg"),__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval))
-#endif
-
-#ifndef __this_cpu_cmpxchg
-# define __this_cpu_cmpxchg(pcp, oval, nval)	\
-	(__this_cpu_preempt_check("cmpxchg"),__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval))
-#endif
-
-#ifndef __this_cpu_cmpxchg_double
-# define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	(__this_cpu_preempt_check("cmpxchg_double"),__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2)))
-#endif
-
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a9209118d80..707617a8c0f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -167,6 +167,11 @@ struct perf_event;
 #define PERF_EVENT_TXN 0x1
 
 /**
+ * pmu::capabilities flags
+ */
+#define PERF_PMU_CAP_NO_INTERRUPT		0x01
+
+/**
  * struct pmu - generic performance monitoring unit
  */
 struct pmu {
@@ -178,6 +183,11 @@ struct pmu {
 	const char			*name;
 	int				type;
 
+	/*
+	 * various common per-pmu feature flags
+	 */
+	int				capabilities;
+
 	int * __percpu			pmu_disable_count;
 	struct perf_cpu_context * __percpu pmu_cpu_context;
 	int				task_ctx_nr;
@@ -696,7 +706,8 @@ extern struct perf_guest_info_callbacks *perf_guest_cbs;
 extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
 extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
 
-extern void perf_event_comm(struct task_struct *tsk);
+extern void perf_event_exec(void);
+extern void perf_event_comm(struct task_struct *tsk, bool exec);
 extern void perf_event_fork(struct task_struct *tsk);
 
 /* Callchains */
@@ -773,7 +784,7 @@ extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern int __perf_event_disable(void *info);
 extern void perf_event_task_tick(void);
-#else
+#else /* !CONFIG_PERF_EVENTS: */
 static inline void
 perf_event_task_sched_in(struct task_struct *prev,
 			 struct task_struct *task)			{ }
@@ -803,7 +814,8 @@ static inline int perf_unregister_guest_info_callbacks
 (struct perf_guest_info_callbacks *callbacks)				{ return 0; }
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
-static inline void perf_event_comm(struct task_struct *tsk)		{ }
+static inline void perf_event_exec(void)				{ }
+static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
 static inline void perf_event_init(void)				{ }
 static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 4d0221fd068..68041446c45 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -198,6 +198,13 @@ static inline struct mii_bus *mdiobus_alloc(void)
 int mdiobus_register(struct mii_bus *bus);
 void mdiobus_unregister(struct mii_bus *bus);
 void mdiobus_free(struct mii_bus *bus);
+struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv);
+static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev)
+{
+	return devm_mdiobus_alloc_size(dev, 0);
+}
+
+void devm_mdiobus_free(struct device *dev, struct mii_bus *bus);
 struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr);
 int mdiobus_read(struct mii_bus *bus, int addr, u32 regnum);
 int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val);
@@ -529,6 +536,15 @@ struct phy_driver {
 	/* See set_wol, but for checking whether Wake on LAN is enabled. */
 	void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
 
+	/*
+	 * Called to inform a PHY device driver when the core is about to
+	 * change the link state. This callback is supposed to be used as
+	 * fixup hook for drivers that need to take action when the link
+	 * state changes. Drivers are by no means allowed to mess with the
+	 * PHY device structure in their implementations.
+	 */
+	void (*link_change_notify)(struct phy_device *dev);
+
 	struct device_driver driver;
 };
 #define to_phy_driver(d) container_of(d, struct phy_driver, driver)
@@ -666,6 +682,7 @@ static inline int phy_read_status(struct phy_device *phydev)
 	return phydev->drv->read_status(phydev);
 }
 
+int genphy_config_init(struct phy_device *phydev);
 int genphy_setup_forced(struct phy_device *phydev);
 int genphy_restart_aneg(struct phy_device *phydev);
 int genphy_config_aneg(struct phy_device *phydev);
diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h
index 509d8f5f984..ae612acebb5 100644
--- a/include/linux/phy_fixed.h
+++ b/include/linux/phy_fixed.h
@@ -9,15 +9,31 @@ struct fixed_phy_status {
 	int asym_pause;
 };
 
+struct device_node;
+
 #ifdef CONFIG_FIXED_PHY
 extern int fixed_phy_add(unsigned int irq, int phy_id,
 			 struct fixed_phy_status *status);
+extern int fixed_phy_register(unsigned int irq,
+			      struct fixed_phy_status *status,
+			      struct device_node *np);
+extern void fixed_phy_del(int phy_addr);
 #else
 static inline int fixed_phy_add(unsigned int irq, int phy_id,
 				struct fixed_phy_status *status)
 {
 	return -ENODEV;
 }
+static inline int fixed_phy_register(unsigned int irq,
+				     struct fixed_phy_status *status,
+				     struct device_node *np)
+{
+	return -ENODEV;
+}
+static inline int fixed_phy_del(int phy_addr)
+{
+	return -ENODEV;
+}
 #endif /* CONFIG_FIXED_PHY */
 
 /*
diff --git a/include/linux/platform_data/ata-samsung_cf.h b/include/linux/platform_data/ata-samsung_cf.h
index c2049e3d744..748e71642c4 100644
--- a/include/linux/platform_data/ata-samsung_cf.h
+++ b/include/linux/platform_data/ata-samsung_cf.h
@@ -29,7 +29,6 @@ extern void s3c_ide_set_platdata(struct s3c_ide_platdata *pdata);
 
 /* architecture-specific IDE configuration */
 extern void s3c64xx_ide_setup_gpio(void);
-extern void s5pc100_ide_setup_gpio(void);
 extern void s5pv210_ide_setup_gpio(void);
 
 #endif /*__ATA_SAMSUNG_CF_H */
diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h
index 4edb40676b3..780d1e97f62 100644
--- a/include/linux/platform_data/elm.h
+++ b/include/linux/platform_data/elm.h
@@ -21,6 +21,7 @@
 enum bch_ecc {
 	BCH4_ECC = 0,
 	BCH8_ECC,
+	BCH16_ECC,
 };
 
 /* ELM support 8 error syndrome process */
@@ -38,7 +39,7 @@ struct elm_errorvec {
 	bool error_reported;
 	bool error_uncorrectable;
 	int error_count;
-	int error_loc[ERROR_VECTOR_MAX];
+	int error_loc[16];
 };
 
 void elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc,
diff --git a/include/linux/platform_data/intel-mid_wdt.h b/include/linux/platform_data/intel-mid_wdt.h
new file mode 100644
index 00000000000..b98253466ac
--- /dev/null
+++ b/include/linux/platform_data/intel-mid_wdt.h
@@ -0,0 +1,22 @@
+/*
+ *      intel-mid_wdt: generic Intel MID SCU watchdog driver
+ *
+ *      Copyright (C) 2014 Intel Corporation. All rights reserved.
+ *      Contact: David Cohen <david.a.cohen@linux.intel.com>
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of version 2 of the GNU General
+ *      Public License as published by the Free Software Foundation.
+ */
+
+#ifndef __INTEL_MID_WDT_H__
+#define __INTEL_MID_WDT_H__
+
+#include <linux/platform_device.h>
+
+struct intel_mid_wdt_pdata {
+	int irq;
+	int (*probe)(struct platform_device *pdev);
+};
+
+#endif /*__INTEL_MID_WDT_H__*/
diff --git a/include/linux/platform_data/leds-pca9685.h b/include/linux/platform_data/leds-pca9685.h
deleted file mode 100644
index 778e9e4249c..00000000000
--- a/include/linux/platform_data/leds-pca9685.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright 2013 Maximilian Güntner <maximilian.guentner@gmail.com>
- *
- * This file is subject to the terms and conditions of version 2 of
- * the GNU General Public License.  See the file COPYING in the main
- * directory of this archive for more details.
- *
- * Based on leds-pca963x.h by Peter Meerwald <p.meerwald@bct-electronic.com>
- *
- * LED driver for the NXP PCA9685 PWM chip
- *
- */
-
-#ifndef __LINUX_PCA9685_H
-#define __LINUX_PCA9685_H
-
-#include <linux/leds.h>
-
-enum pca9685_outdrv {
-	PCA9685_OPEN_DRAIN,
-	PCA9685_TOTEM_POLE,
-};
-
-enum pca9685_inverted {
-	PCA9685_NOT_INVERTED,
-	PCA9685_INVERTED,
-};
-
-struct pca9685_platform_data {
-	struct led_platform_data leds;
-	enum pca9685_outdrv outdrv;
-	enum pca9685_inverted inverted;
-};
-
-#endif /* __LINUX_PCA9685_H */
diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h
index 3e9dd6676b9..660c029d694 100644
--- a/include/linux/platform_data/mtd-nand-omap2.h
+++ b/include/linux/platform_data/mtd-nand-omap2.h
@@ -31,6 +31,8 @@ enum omap_ecc {
 	OMAP_ECC_BCH8_CODE_HW_DETECTION_SW,
 	/* 8-bit  ECC calculation by GPMC, Error detection by ELM */
 	OMAP_ECC_BCH8_CODE_HW,
+	/* 16-bit ECC calculation by GPMC, Error detection by ELM */
+	OMAP_ECC_BCH16_CODE_HW,
 };
 
 struct gpmc_nand_regs {
@@ -50,6 +52,9 @@ struct gpmc_nand_regs {
 	void __iomem	*gpmc_bch_result1[GPMC_BCH_NUM_REMAINDER];
 	void __iomem	*gpmc_bch_result2[GPMC_BCH_NUM_REMAINDER];
 	void __iomem	*gpmc_bch_result3[GPMC_BCH_NUM_REMAINDER];
+	void __iomem	*gpmc_bch_result4[GPMC_BCH_NUM_REMAINDER];
+	void __iomem	*gpmc_bch_result5[GPMC_BCH_NUM_REMAINDER];
+	void __iomem	*gpmc_bch_result6[GPMC_BCH_NUM_REMAINDER];
 };
 
 struct omap_nand_platform_data {
diff --git a/include/linux/platform_data/mtd-nand-pxa3xx.h b/include/linux/platform_data/mtd-nand-pxa3xx.h
index a9414712492..ac4ea2e641c 100644
--- a/include/linux/platform_data/mtd-nand-pxa3xx.h
+++ b/include/linux/platform_data/mtd-nand-pxa3xx.h
@@ -58,6 +58,9 @@ struct pxa3xx_nand_platform_data {
 	/* use an flash-based bad block table */
 	bool	flash_bbt;
 
+	/* requested ECC strength and ECC step size */
+	int ecc_strength, ecc_step_size;
+
 	const struct mtd_partition		*parts[NUM_CHIP_SELECT];
 	unsigned int				nr_parts[NUM_CHIP_SELECT];
 
diff --git a/include/linux/platform_data/omap4-keypad.h b/include/linux/platform_data/omap4-keypad.h
deleted file mode 100644
index 4eef5fb05a1..00000000000
--- a/include/linux/platform_data/omap4-keypad.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __LINUX_INPUT_OMAP4_KEYPAD_H
-#define __LINUX_INPUT_OMAP4_KEYPAD_H
-
-#include <linux/input/matrix_keypad.h>
-
-struct omap4_keypad_platform_data {
-	const struct matrix_keymap_data *keymap_data;
-
-	u8 rows;
-	u8 cols;
-};
-
-#endif /* __LINUX_INPUT_OMAP4_KEYPAD_H */
diff --git a/include/linux/platform_data/pwm-renesas-tpu.h b/include/linux/platform_data/pwm-renesas-tpu.h
deleted file mode 100644
index a7220b10dda..00000000000
--- a/include/linux/platform_data/pwm-renesas-tpu.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __PWM_RENESAS_TPU_H__
-#define __PWM_RENESAS_TPU_H__
-
-#include <linux/pwm.h>
-
-#define TPU_CHANNEL_MAX		4
-
-struct tpu_pwm_channel_data {
-	enum pwm_polarity polarity;
-};
-
-struct tpu_pwm_platform_data {
-	struct tpu_pwm_channel_data channels[TPU_CHANNEL_MAX];
-};
-
-#endif /* __PWM_RENESAS_TPU_H__ */
diff --git a/include/linux/platform_data/shtc1.h b/include/linux/platform_data/shtc1.h
new file mode 100644
index 00000000000..7b8c353f7dc
--- /dev/null
+++ b/include/linux/platform_data/shtc1.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2014 Sensirion AG, Switzerland
+ * Author: Johannes Winkelmann <johannes.winkelmann@sensirion.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __SHTC1_H_
+#define __SHTC1_H_
+
+struct shtc1_platform_data {
+	bool blocking_io;
+	bool high_precision;
+};
+#endif /* __SHTC1_H_ */
diff --git a/include/linux/platform_data/st21nfca.h b/include/linux/platform_data/st21nfca.h
new file mode 100644
index 00000000000..1730312398f
--- /dev/null
+++ b/include/linux/platform_data/st21nfca.h
@@ -0,0 +1,32 @@
+/*
+ * Driver include for the ST21NFCA NFC chip.
+ *
+ * Copyright (C) 2014  STMicroelectronics SAS. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _ST21NFCA_HCI_H_
+#define _ST21NFCA_HCI_H_
+
+#include <linux/i2c.h>
+
+#define ST21NFCA_HCI_DRIVER_NAME "st21nfca_hci"
+
+struct st21nfca_nfc_platform_data {
+	unsigned int gpio_irq;
+	unsigned int gpio_ena;
+	unsigned int irq_polarity;
+};
+
+#endif /* _ST21NFCA_HCI_H_ */
diff --git a/include/linux/profile.h b/include/linux/profile.h
index aaad3861beb..b537a25ffa1 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -44,6 +44,7 @@ extern int prof_on __read_mostly;
 int profile_init(void);
 int profile_setup(char *str);
 void profile_tick(int type);
+int setup_profiling_timer(unsigned int multiplier);
 
 /*
  * Add multiple profiler hits to a given address:
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 077904c8b70..cc79eff4a1a 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -334,6 +334,9 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
  * calling arch_ptrace_stop() when it would be superfluous.  For example,
  * if the thread has not been back to user mode since the last stop, the
  * thread state might indicate that nothing needs to be done.
+ *
+ * This is guaranteed to be invoked once before a task stops for ptrace and
+ * may include arch-specific operations necessary prior to a ptrace stop.
  */
 #define arch_ptrace_stop_needed(code, info)	(0)
 #endif
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 4717f54051c..e90628cac8f 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -274,14 +274,18 @@ struct pwm_lookup {
 	unsigned int index;
 	const char *dev_id;
 	const char *con_id;
+	unsigned int period;
+	enum pwm_polarity polarity;
 };
 
-#define PWM_LOOKUP(_provider, _index, _dev_id, _con_id)	\
+#define PWM_LOOKUP(_provider, _index, _dev_id, _con_id, _period, _polarity) \
 	{						\
 		.provider = _provider,			\
 		.index = _index,			\
 		.dev_id = _dev_id,			\
 		.con_id = _con_id,			\
+		.period = _period,			\
+		.polarity = _polarity			\
 	}
 
 #if IS_ENABLED(CONFIG_PWM)
diff --git a/include/linux/pwm_backlight.h b/include/linux/pwm_backlight.h
index 2de2e275b2c..efdd9227a49 100644
--- a/include/linux/pwm_backlight.h
+++ b/include/linux/pwm_backlight.h
@@ -6,9 +6,6 @@
 
 #include <linux/backlight.h>
 
-/* TODO: convert to gpiod_*() API once it has been merged */
-#define PWM_BACKLIGHT_GPIO_ACTIVE_LOW	(1 << 0)
-
 struct platform_pwm_backlight_data {
 	int pwm_id;
 	unsigned int max_brightness;
@@ -16,8 +13,8 @@ struct platform_pwm_backlight_data {
 	unsigned int lth_brightness;
 	unsigned int pwm_period_ns;
 	unsigned int *levels;
+	/* TODO remove once all users are switched to gpiod_* API */
 	int enable_gpio;
-	unsigned long enable_gpio_flags;
 	int (*init)(struct device *dev);
 	int (*notify)(struct device *dev, int brightness);
 	void (*notify_after)(struct device *dev, int brightness);
diff --git a/include/linux/quota.h b/include/linux/quota.h
index cc7494a3542..0f3c5d38da1 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -329,6 +329,7 @@ struct quotactl_ops {
 	int (*get_xstate)(struct super_block *, struct fs_quota_stat *);
 	int (*set_xstate)(struct super_block *, unsigned int, int);
 	int (*get_xstatev)(struct super_block *, struct fs_quota_statv *);
+	int (*rm_xquota)(struct super_block *, unsigned int);
 };
 
 struct quota_format_type {
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 5a75d19aa66..d231aa17b1d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -44,7 +44,6 @@
 #include <linux/debugobjects.h>
 #include <linux/bug.h>
 #include <linux/compiler.h>
-#include <linux/percpu.h>
 #include <asm/barrier.h>
 
 extern int rcu_expedited; /* for sysctl */
@@ -300,41 +299,6 @@ bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
 
 /*
- * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
- */
-
-#define RCU_COND_RESCHED_LIM 256	/* ms vs. 100s of ms. */
-DECLARE_PER_CPU(int, rcu_cond_resched_count);
-void rcu_resched(void);
-
-/*
- * Is it time to report RCU quiescent states?
- *
- * Note unsynchronized access to rcu_cond_resched_count.  Yes, we might
- * increment some random CPU's count, and possibly also load the result from
- * yet another CPU's count.  We might even clobber some other CPU's attempt
- * to zero its counter.  This is all OK because the goal is not precision,
- * but rather reasonable amortization of rcu_note_context_switch() overhead
- * and extremely high probability of avoiding RCU CPU stall warnings.
- * Note that this function has to be preempted in just the wrong place,
- * many thousands of times in a row, for anything bad to happen.
- */
-static inline bool rcu_should_resched(void)
-{
-	return raw_cpu_inc_return(rcu_cond_resched_count) >=
-	       RCU_COND_RESCHED_LIM;
-}
-
-/*
- * Report quiscent states to RCU if it is time to do so.
- */
-static inline void rcu_cond_resched(void)
-{
-	if (unlikely(rcu_should_resched()))
-		rcu_resched();
-}
-
-/*
  * Infrastructure to implement the synchronize_() primitives in
  * TREE_RCU and rcu_barrier_() primitives in TINY_RCU.
  */
@@ -358,9 +322,19 @@ void wait_rcu_gp(call_rcu_func_t crf);
  * initialization.
  */
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+void init_rcu_head(struct rcu_head *head);
+void destroy_rcu_head(struct rcu_head *head);
 void init_rcu_head_on_stack(struct rcu_head *head);
 void destroy_rcu_head_on_stack(struct rcu_head *head);
 #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+static inline void init_rcu_head(struct rcu_head *head)
+{
+}
+
+static inline void destroy_rcu_head(struct rcu_head *head)
+{
+}
+
 static inline void init_rcu_head_on_stack(struct rcu_head *head)
 {
 }
@@ -852,15 +826,14 @@ static inline void rcu_preempt_sleep_check(void)
  * read-side critical section that would block in a !PREEMPT kernel.
  * But if you want the full story, read on!
  *
- * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), it
- * is illegal to block while in an RCU read-side critical section.  In
- * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU)
- * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may
- * be preempted, but explicit blocking is illegal.  Finally, in preemptible
- * RCU implementations in real-time (with -rt patchset) kernel builds,
- * RCU read-side critical sections may be preempted and they may also
- * block, but only when acquiring spinlocks that are subject to priority
- * inheritance.
+ * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU),
+ * it is illegal to block while in an RCU read-side critical section.
+ * In preemptible RCU implementations (TREE_PREEMPT_RCU) in CONFIG_PREEMPT
+ * kernel builds, RCU read-side critical sections may be preempted,
+ * but explicit blocking is illegal.  Finally, in preemptible RCU
+ * implementations in real-time (with -rt patchset) kernel builds, RCU
+ * read-side critical sections may be preempted and they may also block, but
+ * only when acquiring spinlocks that are subject to priority inheritance.
  */
 static inline void rcu_read_lock(void)
 {
@@ -884,6 +857,34 @@ static inline void rcu_read_lock(void)
 /**
  * rcu_read_unlock() - marks the end of an RCU read-side critical section.
  *
+ * In most situations, rcu_read_unlock() is immune from deadlock.
+ * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock()
+ * is responsible for deboosting, which it does via rt_mutex_unlock().
+ * Unfortunately, this function acquires the scheduler's runqueue and
+ * priority-inheritance spinlocks.  This means that deadlock could result
+ * if the caller of rcu_read_unlock() already holds one of these locks or
+ * any lock that is ever acquired while holding them.
+ *
+ * That said, RCU readers are never priority boosted unless they were
+ * preempted.  Therefore, one way to avoid deadlock is to make sure
+ * that preemption never happens within any RCU read-side critical
+ * section whose outermost rcu_read_unlock() is called with one of
+ * rt_mutex_unlock()'s locks held.  Such preemption can be avoided in
+ * a number of ways, for example, by invoking preempt_disable() before
+ * critical section's outermost rcu_read_lock().
+ *
+ * Given that the set of locks acquired by rt_mutex_unlock() might change
+ * at any time, a somewhat more future-proofed approach is to make sure
+ * that that preemption never happens within any RCU read-side critical
+ * section whose outermost rcu_read_unlock() is called with irqs disabled.
+ * This approach relies on the fact that rt_mutex_unlock() currently only
+ * acquires irq-disabled locks.
+ *
+ * The second of these two approaches is best in most situations,
+ * however, the first approach can also be useful, at least to those
+ * developers willing to keep abreast of the set of locks acquired by
+ * rt_mutex_unlock().
+ *
  * See rcu_read_lock() for more information.
  */
 static inline void rcu_read_unlock(void)
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index a2d9d81038d..14ec18d5e18 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -395,6 +395,11 @@ static inline void regulator_bulk_free(int num_consumers,
 {
 }
 
+static inline int regulator_can_change_voltage(struct regulator *regulator)
+{
+	return 0;
+}
+
 static inline int regulator_set_voltage(struct regulator *regulator,
 					int min_uV, int max_uV)
 {
diff --git a/include/linux/rfkill-gpio.h b/include/linux/rfkill-gpio.h
index 4d09f6eab35..20bcb55498c 100644
--- a/include/linux/rfkill-gpio.h
+++ b/include/linux/rfkill-gpio.h
@@ -27,21 +27,11 @@
  * struct rfkill_gpio_platform_data - platform data for rfkill gpio device.
  * for unused gpio's, the expected value is -1.
  * @name:		name for the gpio rf kill instance
- * @reset_gpio:		GPIO which is used for reseting rfkill switch
- * @shutdown_gpio:	GPIO which is used for shutdown of rfkill switch
- * @power_clk_name:	[optional] name of clk to turn off while blocked
- * @gpio_runtime_close:	clean up platform specific gpio configuration
- * @gpio_runtime_setup:	set up platform specific gpio configuration
  */
 
 struct rfkill_gpio_platform_data {
 	char			*name;
-	int			reset_gpio;
-	int			shutdown_gpio;
-	const char		*power_clk_name;
 	enum rfkill_type	type;
-	void	(*gpio_runtime_close)(struct platform_device *);
-	int	(*gpio_runtime_setup)(struct platform_device *);
 };
 
 #endif /* __RFKILL_GPIO_H */
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index d69cf637a15..49a4d6f5910 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -97,7 +97,7 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k
 	__ring_buffer_alloc((size), (flags), &__key);	\
 })
 
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu);
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu);
 int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table);
 
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 3aed8d737e1..1abba5ce2a2 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -90,11 +90,9 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name);
 extern void rt_mutex_destroy(struct rt_mutex *lock);
 
 extern void rt_mutex_lock(struct rt_mutex *lock);
-extern int rt_mutex_lock_interruptible(struct rt_mutex *lock,
-						int detect_deadlock);
+extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
 extern int rt_mutex_timed_lock(struct rt_mutex *lock,
-					struct hrtimer_sleeper *timeout,
-					int detect_deadlock);
+			       struct hrtimer_sleeper *timeout);
 
 extern int rt_mutex_trylock(struct rt_mutex *lock);
 
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index d5b13bc07a0..561e8615528 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -15,13 +15,13 @@
 #ifdef __KERNEL__
 /*
  * the rw-semaphore definition
- * - if activity is 0 then there are no active readers or writers
- * - if activity is +ve then that is the number of active readers
- * - if activity is -1 then there is one active writer
+ * - if count is 0 then there are no active readers or writers
+ * - if count is +ve then that is the number of active readers
+ * - if count is -1 then there is one active writer
  * - if wait_list is not empty, then there are processes waiting for the semaphore
  */
 struct rw_semaphore {
-	__s32			activity;
+	__s32			count;
 	raw_spinlock_t		wait_lock;
 	struct list_head	wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 03f3b05e8ec..035d3c57fc8 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -13,8 +13,10 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
-
 #include <linux/atomic.h>
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+#include <linux/osq_lock.h>
+#endif
 
 struct rw_semaphore;
 
@@ -23,9 +25,17 @@ struct rw_semaphore;
 #else
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
-	long			count;
-	raw_spinlock_t		wait_lock;
-	struct list_head	wait_list;
+	long count;
+	struct list_head wait_list;
+	raw_spinlock_t wait_lock;
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+	struct optimistic_spin_queue osq; /* spinner MCS lock */
+	/*
+	 * Write owner. Used as a speculative check to see
+	 * if the owner is running on the cpu.
+	 */
+	struct task_struct *owner;
+#endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
@@ -55,10 +65,17 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
-#define __RWSEM_INITIALIZER(name)			\
-	{ RWSEM_UNLOCKED_VALUE,				\
-	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
-	  LIST_HEAD_INIT((name).wait_list)		\
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL
+#else
+#define __RWSEM_OPT_INIT(lockname)
+#endif
+
+#define __RWSEM_INITIALIZER(name)				\
+	{ .count = RWSEM_UNLOCKED_VALUE,			\
+	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
+	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock)	\
+	  __RWSEM_OPT_INIT(name)				\
 	  __RWSEM_DEP_MAP_INIT(name) }
 
 #define DECLARE_RWSEM(name) \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ea74596014a..42cac4dc215 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -847,10 +847,10 @@ enum cpu_idle_type {
 };
 
 /*
- * Increase resolution of cpu_power calculations
+ * Increase resolution of cpu_capacity calculations
  */
-#define SCHED_POWER_SHIFT	10
-#define SCHED_POWER_SCALE	(1L << SCHED_POWER_SHIFT)
+#define SCHED_CAPACITY_SHIFT	10
+#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
 
 /*
  * sched-domains (multiprocessor balancing) declarations:
@@ -862,7 +862,7 @@ enum cpu_idle_type {
 #define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
 #define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
 #define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
-#define SD_SHARE_CPUPOWER	0x0080	/* Domain members share cpu power */
+#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu power */
 #define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
 #define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
@@ -872,21 +872,21 @@ enum cpu_idle_type {
 #define SD_NUMA			0x4000	/* cross-node balancing */
 
 #ifdef CONFIG_SCHED_SMT
-static inline const int cpu_smt_flags(void)
+static inline int cpu_smt_flags(void)
 {
-	return SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES;
+	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
 }
 #endif
 
 #ifdef CONFIG_SCHED_MC
-static inline const int cpu_core_flags(void)
+static inline int cpu_core_flags(void)
 {
 	return SD_SHARE_PKG_RESOURCES;
 }
 #endif
 
 #ifdef CONFIG_NUMA
-static inline const int cpu_numa_flags(void)
+static inline int cpu_numa_flags(void)
 {
 	return SD_NUMA;
 }
@@ -999,14 +999,14 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 bool cpus_share_cache(int this_cpu, int that_cpu);
 
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
-typedef const int (*sched_domain_flags_f)(void);
+typedef int (*sched_domain_flags_f)(void);
 
 #define SDTL_OVERLAP	0x01
 
 struct sd_data {
 	struct sched_domain **__percpu sd;
 	struct sched_group **__percpu sg;
-	struct sched_group_power **__percpu sgp;
+	struct sched_group_capacity **__percpu sgc;
 };
 
 struct sched_domain_topology_level {
@@ -1270,9 +1270,6 @@ struct task_struct {
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-#ifdef CONFIG_RCU_BOOST
-	struct rt_mutex *rcu_boost_mutex;
-#endif /* #ifdef CONFIG_RCU_BOOST */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
 	struct sched_info sched_info;
@@ -1440,8 +1437,6 @@ struct task_struct {
 	struct rb_node *pi_waiters_leftmost;
 	/* Deadlock detection and priority inheritance handling */
 	struct rt_mutex_waiter *pi_blocked_on;
-	/* Top pi_waiters task */
-	struct task_struct *pi_top_task;
 #endif
 
 #ifdef CONFIG_DEBUG_MUTEXES
@@ -2009,9 +2004,6 @@ static inline void rcu_copy_process(struct task_struct *p)
 #ifdef CONFIG_TREE_PREEMPT_RCU
 	p->rcu_blocked_node = NULL;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-#ifdef CONFIG_RCU_BOOST
-	p->rcu_boost_mutex = NULL;
-#endif /* #ifdef CONFIG_RCU_BOOST */
 	INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
@@ -2173,7 +2165,7 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { }
 static inline void sched_autogroup_exit(struct signal_struct *sig) { }
 #endif
 
-extern bool yield_to(struct task_struct *p, bool preempt);
+extern int yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
 /**
@@ -2421,7 +2413,11 @@ extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, i
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 
-extern void set_task_comm(struct task_struct *tsk, const char *from);
+extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
+static inline void set_task_comm(struct task_struct *tsk, const char *from)
+{
+	__set_task_comm(tsk, from, false);
+}
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
@@ -2784,7 +2780,7 @@ static inline bool __must_check current_set_polling_and_test(void)
 
 	/*
 	 * Polling state must be visible before we test NEED_RESCHED,
-	 * paired by resched_task()
+	 * paired by resched_curr()
 	 */
 	smp_mb__after_atomic();
 
@@ -2802,7 +2798,7 @@ static inline bool __must_check current_clr_polling_and_test(void)
 
 	/*
 	 * Polling state must be visible before we test NEED_RESCHED,
-	 * paired by resched_task()
+	 * paired by resched_curr()
 	 */
 	smp_mb__after_atomic();
 
@@ -2834,7 +2830,7 @@ static inline void current_clr_polling(void)
 	 * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
 	 * fold.
 	 */
-	smp_mb(); /* paired with resched_task() */
+	smp_mb(); /* paired with resched_curr() */
 
 	preempt_fold_need_resched();
 }
diff --git a/include/linux/security.h b/include/linux/security.h
index 6478ce3252c..9c6b9722ff4 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1708,7 +1708,7 @@ struct security_operations {
 	void (*key_free) (struct key *key);
 	int (*key_permission) (key_ref_t key_ref,
 			       const struct cred *cred,
-			       key_perm_t perm);
+			       unsigned perm);
 	int (*key_getsecurity)(struct key *key, char **_buffer);
 #endif	/* CONFIG_KEYS */
 
@@ -3034,7 +3034,7 @@ static inline int security_path_chroot(struct path *path)
 int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags);
 void security_key_free(struct key *key);
 int security_key_permission(key_ref_t key_ref,
-			    const struct cred *cred, key_perm_t perm);
+			    const struct cred *cred, unsigned perm);
 int security_key_getsecurity(struct key *key, char **_buffer);
 
 #else
@@ -3052,7 +3052,7 @@ static inline void security_key_free(struct key *key)
 
 static inline int security_key_permission(key_ref_t key_ref,
 					  const struct cred *cred,
-					  key_perm_t perm)
+					  unsigned perm)
 {
 	return 0;
 }
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 535f158977b..8cf350325dc 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -164,8 +164,6 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
 static inline unsigned raw_seqcount_begin(const seqcount_t *s)
 {
 	unsigned ret = ACCESS_ONCE(s->sequence);
-
-	seqcount_lockdep_reader_access(s);
 	smp_rmb();
 	return ret & ~1;
 }
diff --git a/include/linux/shdma-base.h b/include/linux/shdma-base.h
index f92c0a43c54..abdf1f229dc 100644
--- a/include/linux/shdma-base.h
+++ b/include/linux/shdma-base.h
@@ -54,6 +54,7 @@ struct shdma_desc {
 	dma_cookie_t cookie;
 	int chunks;
 	int mark;
+	bool cyclic;			/* used as cyclic transfer */
 };
 
 struct shdma_chan {
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 08074a81016..ec89301ada4 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -338,13 +338,18 @@ enum {
 
 	SKB_GSO_GRE = 1 << 6,
 
-	SKB_GSO_IPIP = 1 << 7,
+	SKB_GSO_GRE_CSUM = 1 << 7,
 
-	SKB_GSO_SIT = 1 << 8,
+	SKB_GSO_IPIP = 1 << 8,
 
-	SKB_GSO_UDP_TUNNEL = 1 << 9,
+	SKB_GSO_SIT = 1 << 9,
+
+	SKB_GSO_UDP_TUNNEL = 1 << 10,
+
+	SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11,
+
+	SKB_GSO_MPLS = 1 << 12,
 
-	SKB_GSO_MPLS = 1 << 10,
 };
 
 #if BITS_PER_LONG > 32
@@ -426,7 +431,7 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
  *	@csum_start: Offset from skb->head where checksumming should start
  *	@csum_offset: Offset from csum_start where checksum should be stored
  *	@priority: Packet queueing priority
- *	@local_df: allow local fragmentation
+ *	@ignore_df: allow local fragmentation
  *	@cloned: Head may be cloned (check refcnt to be sure)
  *	@ip_summed: Driver fed us an IP checksum
  *	@nohdr: Payload reference only, must not modify header
@@ -514,7 +519,7 @@ struct sk_buff {
 	};
 	__u32			priority;
 	kmemcheck_bitfield_begin(flags1);
-	__u8			local_df:1,
+	__u8			ignore_df:1,
 				cloned:1,
 				ip_summed:2,
 				nohdr:1,
@@ -567,7 +572,10 @@ struct sk_buff {
 	 * headers if needed
 	 */
 	__u8			encapsulation:1;
-	/* 6/8 bit hole (depending on ndisc_nodetype presence) */
+	__u8			encap_hdr_csum:1;
+	__u8			csum_valid:1;
+	__u8			csum_complete_sw:1;
+	/* 3/5 bit hole (depending on ndisc_nodetype presence) */
 	kmemcheck_bitfield_end(flags2);
 
 #if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL
@@ -739,7 +747,13 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
 int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
 struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority);
 struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority);
-struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask);
+struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom,
+				   gfp_t gfp_mask, bool fclone);
+static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom,
+					  gfp_t gfp_mask)
+{
+	return __pskb_copy_fclone(skb, headroom, gfp_mask, false);
+}
 
 int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask);
 struct sk_buff *skb_realloc_headroom(struct sk_buff *skb,
@@ -1840,6 +1854,18 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
 	return pskb_may_pull(skb, skb_network_offset(skb) + len);
 }
 
+static inline void skb_pop_rcv_encapsulation(struct sk_buff *skb)
+{
+	/* Only continue with checksum unnecessary if device indicated
+	 * it is valid across encapsulation (skb->encapsulation was set).
+	 */
+	if (skb->ip_summed == CHECKSUM_UNNECESSARY && !skb->encapsulation)
+		skb->ip_summed = CHECKSUM_NONE;
+
+	skb->encapsulation = 0;
+	skb->csum_valid = 0;
+}
+
 /*
  * CPUs often take a performance hit when accessing unaligned memory
  * locations. The actual performance hit varies, it can be small if the
@@ -2233,6 +2259,14 @@ static inline struct sk_buff *pskb_copy(struct sk_buff *skb,
 	return __pskb_copy(skb, skb_headroom(skb), gfp_mask);
 }
 
+
+static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb,
+						  gfp_t gfp_mask)
+{
+	return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true);
+}
+
+
 /**
  *	skb_clone_writable - is the header of a clone writable
  *	@skb: buffer to check
@@ -2716,7 +2750,7 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb);
 
 static inline int skb_csum_unnecessary(const struct sk_buff *skb)
 {
-	return skb->ip_summed & CHECKSUM_UNNECESSARY;
+	return ((skb->ip_summed & CHECKSUM_UNNECESSARY) || skb->csum_valid);
 }
 
 /**
@@ -2741,6 +2775,103 @@ static inline __sum16 skb_checksum_complete(struct sk_buff *skb)
 	       0 : __skb_checksum_complete(skb);
 }
 
+/* Check if we need to perform checksum complete validation.
+ *
+ * Returns true if checksum complete is needed, false otherwise
+ * (either checksum is unnecessary or zero checksum is allowed).
+ */
+static inline bool __skb_checksum_validate_needed(struct sk_buff *skb,
+						  bool zero_okay,
+						  __sum16 check)
+{
+	if (skb_csum_unnecessary(skb) || (zero_okay && !check)) {
+		skb->csum_valid = 1;
+		return false;
+	}
+
+	return true;
+}
+
+/* For small packets <= CHECKSUM_BREAK peform checksum complete directly
+ * in checksum_init.
+ */
+#define CHECKSUM_BREAK 76
+
+/* Validate (init) checksum based on checksum complete.
+ *
+ * Return values:
+ *   0: checksum is validated or try to in skb_checksum_complete. In the latter
+ *	case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo
+ *	checksum is stored in skb->csum for use in __skb_checksum_complete
+ *   non-zero: value of invalid checksum
+ *
+ */
+static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb,
+						       bool complete,
+						       __wsum psum)
+{
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		if (!csum_fold(csum_add(psum, skb->csum))) {
+			skb->csum_valid = 1;
+			return 0;
+		}
+	}
+
+	skb->csum = psum;
+
+	if (complete || skb->len <= CHECKSUM_BREAK) {
+		__sum16 csum;
+
+		csum = __skb_checksum_complete(skb);
+		skb->csum_valid = !csum;
+		return csum;
+	}
+
+	return 0;
+}
+
+static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto)
+{
+	return 0;
+}
+
+/* Perform checksum validate (init). Note that this is a macro since we only
+ * want to calculate the pseudo header which is an input function if necessary.
+ * First we try to validate without any computation (checksum unnecessary) and
+ * then calculate based on checksum complete calling the function to compute
+ * pseudo header.
+ *
+ * Return values:
+ *   0: checksum is validated or try to in skb_checksum_complete
+ *   non-zero: value of invalid checksum
+ */
+#define __skb_checksum_validate(skb, proto, complete,			\
+				zero_okay, check, compute_pseudo)	\
+({									\
+	__sum16 __ret = 0;						\
+	skb->csum_valid = 0;						\
+	if (__skb_checksum_validate_needed(skb, zero_okay, check))	\
+		__ret = __skb_checksum_validate_complete(skb,		\
+				complete, compute_pseudo(skb, proto));	\
+	__ret;								\
+})
+
+#define skb_checksum_init(skb, proto, compute_pseudo)			\
+	__skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo)
+
+#define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo)	\
+	__skb_checksum_validate(skb, proto, false, true, check, compute_pseudo)
+
+#define skb_checksum_validate(skb, proto, compute_pseudo)		\
+	__skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo)
+
+#define skb_checksum_validate_zero_check(skb, proto, check,		\
+					 compute_pseudo)		\
+	__skb_checksum_validate_(skb, proto, true, true, check, compute_pseudo)
+
+#define skb_checksum_simple_validate(skb)				\
+	__skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo)
+
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 void nf_conntrack_destroy(struct nf_conntrack *nfct);
 static inline void nf_conntrack_put(struct nf_conntrack *nfct)
@@ -2895,6 +3026,7 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb)
 struct skb_gso_cb {
 	int	mac_offset;
 	int	encap_level;
+	__u16	csum_start;
 };
 #define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb)
 
@@ -2919,6 +3051,28 @@ static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra)
 	return 0;
 }
 
+/* Compute the checksum for a gso segment. First compute the checksum value
+ * from the start of transport header to SKB_GSO_CB(skb)->csum_start, and
+ * then add in skb->csum (checksum from csum_start to end of packet).
+ * skb->csum and csum_start are then updated to reflect the checksum of the
+ * resultant packet starting from the transport header-- the resultant checksum
+ * is in the res argument (i.e. normally zero or ~ of checksum of a pseudo
+ * header.
+ */
+static inline __sum16 gso_make_checksum(struct sk_buff *skb, __wsum res)
+{
+	int plen = SKB_GSO_CB(skb)->csum_start - skb_headroom(skb) -
+	    skb_transport_offset(skb);
+	__u16 csum;
+
+	csum = csum_fold(csum_partial(skb_transport_header(skb),
+				      plen, skb->csum));
+	skb->csum = res;
+	SKB_GSO_CB(skb)->csum_start -= plen;
+
+	return csum;
+}
+
 static inline bool skb_is_gso(const struct sk_buff *skb)
 {
 	return skb_shinfo(skb)->gso_size;
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 8e98297f138..ec538fc287a 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -305,8 +305,6 @@ struct ucred {
 /* IPX options */
 #define IPX_TYPE	1
 
-extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
-			       int offset, int len);
 extern int csum_partial_copy_fromiovecend(unsigned char *kdata, 
 					  struct iovec *iov, 
 					  int offset, 
@@ -315,8 +313,6 @@ extern unsigned long iov_pages(const struct iovec *iov, int offset,
 			       unsigned long nr_segs);
 
 extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode);
-extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
-			     int offset, int len);
 extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
 extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
 
diff --git a/include/linux/spi/at86rf230.h b/include/linux/spi/at86rf230.h
index aa327a8105a..b2b1afbb320 100644
--- a/include/linux/spi/at86rf230.h
+++ b/include/linux/spi/at86rf230.h
@@ -26,20 +26,6 @@ struct at86rf230_platform_data {
 	int rstn;
 	int slp_tr;
 	int dig2;
-
-	/* Setting the irq_type will configure the driver to request
-	 * the platform irq trigger type according to the given value
-	 * and configure the interrupt polarity of the device to the
-	 * corresponding polarity.
-	 *
-	 * Allowed values are: IRQF_TRIGGER_RISING, IRQF_TRIGGER_FALLING,
-	 *                     IRQF_TRIGGER_HIGH and IRQF_TRIGGER_LOW
-	 *
-	 * Setting it to 0, the driver does not touch the trigger type
-	 * configuration of the interrupt and sets the interrupt polarity
-	 * of the device to high active (the default value).
-	 */
-	int irq_type;
 };
 
 #endif
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 0e43906d2fd..da2751d3b93 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -70,16 +70,6 @@ extern ssize_t splice_from_pipe(struct pipe_inode_info *, struct file *,
 				splice_actor *);
 extern ssize_t __splice_from_pipe(struct pipe_inode_info *,
 				  struct splice_desc *, splice_actor *);
-extern int splice_from_pipe_feed(struct pipe_inode_info *, struct splice_desc *,
-				 splice_actor *);
-extern int splice_from_pipe_next(struct pipe_inode_info *,
-				 struct splice_desc *);
-extern void splice_from_pipe_begin(struct splice_desc *);
-extern void splice_from_pipe_end(struct pipe_inode_info *,
-				 struct splice_desc *);
-extern int pipe_to_file(struct pipe_inode_info *, struct pipe_buffer *,
-			struct splice_desc *);
-
 extern ssize_t splice_to_pipe(struct pipe_inode_info *,
 			      struct splice_pipe_desc *);
 extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h
index 07ef9b82b66..4568a5cc9ab 100644
--- a/include/linux/ssb/ssb.h
+++ b/include/linux/ssb/ssb.h
@@ -33,6 +33,7 @@ struct ssb_sprom {
 	u8 et1phyaddr;		/* MII address for enet1 */
 	u8 et0mdcport;		/* MDIO for enet0 */
 	u8 et1mdcport;		/* MDIO for enet1 */
+	u16 dev_id;		/* Device ID overriding e.g. PCI ID */
 	u16 board_rev;		/* Board revision number from SPROM. */
 	u16 board_num;		/* Board number from SPROM. */
 	u16 board_type;		/* Board type from SPROM. */
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index ad7dbe2cfec..1a8959944c5 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -236,7 +236,7 @@ void *		rpc_malloc(struct rpc_task *, size_t);
 void		rpc_free(void *);
 int		rpciod_up(void);
 void		rpciod_down(void);
-int		__rpc_wait_for_completion_task(struct rpc_task *task, int (*)(void *));
+int		__rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *);
 #ifdef RPC_DEBUG
 struct net;
 void		rpc_show_tasks(struct net *);
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 04e76322124..1bc7cd05b22 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -244,6 +244,7 @@ struct svc_rqst {
 	struct page *		rq_pages[RPCSVC_MAXPAGES];
 	struct page *		*rq_respages;	/* points into rq_pages */
 	struct page *		*rq_next_page; /* next reply page to use */
+	struct page *		*rq_page_end;  /* one past the last page */
 
 	struct kvec		rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */
 
@@ -254,11 +255,15 @@ struct svc_rqst {
 	u32			rq_prot;	/* IP protocol */
 	unsigned short
 				rq_secure  : 1;	/* secure port */
+	unsigned short		rq_local   : 1;	/* local request */
 
 	void *			rq_argp;	/* decoded arguments */
 	void *			rq_resp;	/* xdr'd results */
 	void *			rq_auth_data;	/* flavor-specific data */
-
+	int			rq_auth_slack;	/* extra space xdr code
+						 * should leave in head
+						 * for krb5i, krb5p.
+						 */
 	int			rq_reserved;	/* space on socket outq
 						 * reserved for this request
 						 */
@@ -454,11 +459,7 @@ char *		   svc_print_addr(struct svc_rqst *, char *, size_t);
  */
 static inline void svc_reserve_auth(struct svc_rqst *rqstp, int space)
 {
-	int added_space = 0;
-
-	if (rqstp->rq_authop->flavour)
-		added_space = RPC_MAX_AUTH_SIZE;
-	svc_reserve(rqstp, space + added_space);
+	svc_reserve(rqstp, space + rqstp->rq_auth_slack);
 }
 
 #endif /* SUNRPC_SVC_H */
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 0b8e3e6bdac..5cf99a01636 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -115,14 +115,13 @@ struct svc_rdma_fastreg_mr {
 	struct list_head frmr_list;
 };
 struct svc_rdma_req_map {
-	struct svc_rdma_fastreg_mr *frmr;
 	unsigned long count;
 	union {
 		struct kvec sge[RPCSVC_MAXPAGES];
 		struct svc_rdma_chunk_sge ch[RPCSVC_MAXPAGES];
+		unsigned long lkey[RPCSVC_MAXPAGES];
 	};
 };
-#define RDMACTXT_F_FAST_UNREG	1
 #define RDMACTXT_F_LAST_CTXT	2
 
 #define	SVCRDMA_DEVCAP_FAST_REG		1	/* fast mr registration */
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index b05963f09eb..7235040a19b 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -24,6 +24,7 @@ struct svc_xprt_ops {
 	void		(*xpo_release_rqst)(struct svc_rqst *);
 	void		(*xpo_detach)(struct svc_xprt *);
 	void		(*xpo_free)(struct svc_xprt *);
+	int		(*xpo_secure_port)(struct svc_rqst *);
 };
 
 struct svc_xprt_class {
@@ -63,6 +64,7 @@ struct svc_xprt {
 #define	XPT_DETACHED	10		/* detached from tempsocks list */
 #define XPT_LISTENER	11		/* listening endpoint */
 #define XPT_CACHE_AUTH	12		/* cache auth info */
+#define XPT_LOCAL	13		/* connection from loopback interface */
 
 	struct svc_serv		*xpt_server;	/* service for transport */
 	atomic_t    	    	xpt_reserved;	/* space on outq that is rsvd */
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 15f9204ee70..70c6b92e15a 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -215,6 +215,9 @@ typedef int	(*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj);
 
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
+extern void xdr_commit_encode(struct xdr_stream *xdr);
+extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len);
+extern int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
 		unsigned int base, unsigned int len);
 extern unsigned int xdr_stream_pos(const struct xdr_stream *xdr);
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 3876f0f1dfd..fcbfe878324 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -24,6 +24,12 @@
 #define RPC_MAX_SLOT_TABLE_LIMIT	(65536U)
 #define RPC_MAX_SLOT_TABLE	RPC_MAX_SLOT_TABLE_LIMIT
 
+#define RPC_CWNDSHIFT		(8U)
+#define RPC_CWNDSCALE		(1U << RPC_CWNDSHIFT)
+#define RPC_INITCWND		RPC_CWNDSCALE
+#define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)
+#define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
+
 /*
  * This describes a timeout strategy
  */
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index f76994b9396..519064e0c94 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -327,6 +327,7 @@ extern unsigned long get_safe_page(gfp_t gfp_mask);
 extern void hibernation_set_ops(const struct platform_hibernation_ops *ops);
 extern int hibernate(void);
 extern bool system_entering_hibernation(void);
+extern bool hibernation_available(void);
 asmlinkage int swsusp_save(void);
 extern struct pbe *restore_pblist;
 #else /* CONFIG_HIBERNATION */
@@ -339,6 +340,7 @@ static inline void swsusp_unset_page_free(struct page *p) {}
 static inline void hibernation_set_ops(const struct platform_hibernation_ops *ops) {}
 static inline int hibernate(void) { return -ENOSYS; }
 static inline bool system_entering_hibernation(void) { return false; }
+static inline bool hibernation_available(void) { return false; }
 #endif /* CONFIG_HIBERNATION */
 
 /* Hibernation and suspend events */
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 23994686814..a0513210798 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -197,7 +197,8 @@ struct tcp_sock {
 	u8	do_early_retrans:1,/* Enable RFC5827 early-retransmit  */
 		syn_data:1,	/* SYN includes data */
 		syn_fastopen:1,	/* SYN includes Fast Open option */
-		syn_data_acked:1;/* data in SYN is acked by SYN-ACK */
+		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
+		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
 	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */
 
 /* RTT measurement */
@@ -209,6 +210,8 @@ struct tcp_sock {
 
 	u32	packets_out;	/* Packets which are "in flight"	*/
 	u32	retrans_out;	/* Retransmitted packets out		*/
+	u32	max_packets_out;  /* max packets_out in last window */
+	u32	max_packets_seq;  /* right edge of max_packets_out flight */
 
 	u16	urg_data;	/* Saved octet of OOB data and control flags */
 	u8	ecn_flags;	/* ECN status bits.			*/
@@ -365,11 +368,6 @@ static inline bool tcp_passive_fastopen(const struct sock *sk)
 		tcp_sk(sk)->fastopen_rsk != NULL);
 }
 
-static inline bool fastopen_cookie_present(struct tcp_fastopen_cookie *foc)
-{
-	return foc->len != -1;
-}
-
 extern void tcp_sock_destruct(struct sock *sk);
 
 static inline int fastopen_init_queue(struct sock *sk, int backlog)
diff --git a/include/linux/tick.h b/include/linux/tick.h
index b84773cb9f4..05905230683 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -12,6 +12,7 @@
 #include <linux/hrtimer.h>
 #include <linux/context_tracking_state.h>
 #include <linux/cpumask.h>
+#include <linux/sched.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
@@ -162,6 +163,7 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
 #ifdef CONFIG_NO_HZ_FULL
 extern bool tick_nohz_full_running;
 extern cpumask_var_t tick_nohz_full_mask;
+extern cpumask_var_t housekeeping_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {
@@ -181,7 +183,13 @@ static inline bool tick_nohz_full_cpu(int cpu)
 
 extern void tick_nohz_init(void);
 extern void __tick_nohz_full_check(void);
-extern void tick_nohz_full_kick(void);
+extern void tick_nohz_full_kick_cpu(int cpu);
+
+static inline void tick_nohz_full_kick(void)
+{
+	tick_nohz_full_kick_cpu(smp_processor_id());
+}
+
 extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(struct task_struct *tsk);
 #else
@@ -189,11 +197,30 @@ static inline void tick_nohz_init(void) { }
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void __tick_nohz_full_check(void) { }
+static inline void tick_nohz_full_kick_cpu(int cpu) { }
 static inline void tick_nohz_full_kick(void) { }
 static inline void tick_nohz_full_kick_all(void) { }
 static inline void __tick_nohz_task_switch(struct task_struct *tsk) { }
 #endif
 
+static inline bool is_housekeeping_cpu(int cpu)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	if (tick_nohz_full_enabled())
+		return cpumask_test_cpu(cpu, housekeeping_mask);
+#endif
+	return true;
+}
+
+static inline void housekeeping_affine(struct task_struct *t)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	if (tick_nohz_full_enabled())
+		set_cpus_allowed_ptr(t, housekeeping_mask);
+
+#endif
+}
+
 static inline void tick_nohz_full_check(void)
 {
 	if (tick_nohz_full_enabled())
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index a32d86ec8bf..ea6c9dea79e 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -25,6 +25,21 @@ trace_seq_init(struct trace_seq *s)
 	s->full = 0;
 }
 
+/**
+ * trace_seq_buffer_ptr - return pointer to next location in buffer
+ * @s: trace sequence descriptor
+ *
+ * Returns the pointer to the buffer where the next write to
+ * the buffer will happen. This is useful to save the location
+ * that is about to be written to and then return the result
+ * of that write.
+ */
+static inline unsigned char *
+trace_seq_buffer_ptr(struct trace_seq *s)
+{
+	return s->buffer + s->len;
+}
+
 /*
  * Currently only defined when tracing is enabled.
  */
@@ -36,16 +51,18 @@ int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args);
 extern int
 trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
 extern int trace_print_seq(struct seq_file *m, struct trace_seq *s);
-extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
-				 size_t cnt);
+extern int trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+			     int cnt);
 extern int trace_seq_puts(struct trace_seq *s, const char *str);
 extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
-extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
+extern int trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len);
 extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
-				size_t len);
-extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
+				unsigned int len);
 extern int trace_seq_path(struct trace_seq *s, const struct path *path);
 
+extern int trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
+			     int nmaskbits);
+
 #else /* CONFIG_TRACING */
 static inline int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 {
@@ -57,12 +74,19 @@ trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
 	return 0;
 }
 
+static inline int
+trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
+		  int nmaskbits)
+{
+	return 0;
+}
+
 static inline int trace_print_seq(struct seq_file *m, struct trace_seq *s)
 {
 	return 0;
 }
-static inline ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
-				 size_t cnt)
+static inline int trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+				    int cnt)
 {
 	return 0;
 }
@@ -75,19 +99,15 @@ static inline int trace_seq_putc(struct trace_seq *s, unsigned char c)
 	return 0;
 }
 static inline int
-trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
+trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len)
 {
 	return 0;
 }
 static inline int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
-				       size_t len)
+				       unsigned int len)
 {
 	return 0;
 }
-static inline void *trace_seq_reserve(struct trace_seq *s, size_t len)
-{
-	return NULL;
-}
 static inline int trace_seq_path(struct trace_seq *s, const struct path *path)
 {
 	return 0;
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 9d30ee469c2..2e2a5f7717e 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -185,6 +185,11 @@ extern void syscall_unregfunc(void);
 	static inline void						\
 	check_trace_callback_type_##name(void (*cb)(data_proto))	\
 	{								\
+	}								\
+	static inline bool						\
+	trace_##name##_enabled(void)					\
+	{								\
+		return static_key_false(&__tracepoint_##name.key);	\
 	}
 
 /*
@@ -230,6 +235,11 @@ extern void syscall_unregfunc(void);
 	}								\
 	static inline void check_trace_callback_type_##name(void (*cb)(data_proto)) \
 	{								\
+	}								\
+	static inline bool						\
+	trace_##name##_enabled(void)					\
+	{								\
+		return false;						\
 	}
 
 #define DEFINE_TRACE_FN(name, reg, unreg)
diff --git a/include/linux/udp.h b/include/linux/udp.h
index 42278bbf7a8..247cfdcc4b0 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -47,7 +47,9 @@ struct udp_sock {
 #define udp_portaddr_node	inet.sk.__sk_common.skc_portaddr_node
 	int		 pending;	/* Any pending frames ? */
 	unsigned int	 corkflag;	/* Cork is required */
-  	__u16		 encap_type;	/* Is this an Encapsulation socket? */
+	__u8		 encap_type;	/* Is this an Encapsulation socket? */
+	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
+			 no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
@@ -76,6 +78,26 @@ static inline struct udp_sock *udp_sk(const struct sock *sk)
 	return (struct udp_sock *)sk;
 }
 
+static inline void udp_set_no_check6_tx(struct sock *sk, bool val)
+{
+	udp_sk(sk)->no_check6_tx = val;
+}
+
+static inline void udp_set_no_check6_rx(struct sock *sk, bool val)
+{
+	udp_sk(sk)->no_check6_rx = val;
+}
+
+static inline bool udp_get_no_check6_tx(struct sock *sk)
+{
+	return udp_sk(sk)->no_check6_tx;
+}
+
+static inline bool udp_get_no_check6_rx(struct sock *sk)
+{
+	return udp_sk(sk)->no_check6_rx;
+}
+
 #define udp_portaddr_for_each_entry(__sk, node, list) \
 	hlist_nulls_for_each_entry(__sk, node, list, __sk_common.skc_portaddr_node)
 
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 199bcc34241..09a7cffc224 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -19,11 +19,21 @@ struct kvec {
 	size_t iov_len;
 };
 
+enum {
+	ITER_IOVEC = 0,
+	ITER_KVEC = 2,
+	ITER_BVEC = 4,
+};
+
 struct iov_iter {
-	const struct iovec *iov;
-	unsigned long nr_segs;
+	int type;
 	size_t iov_offset;
 	size_t count;
+	union {
+		const struct iovec *iov;
+		const struct bio_vec *bvec;
+	};
+	unsigned long nr_segs;
 };
 
 /*
@@ -53,6 +63,7 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
 }
 
 #define iov_for_each(iov, iter, start)				\
+	if (!((start).type & ITER_BVEC))			\
 	for (iter = (start);					\
 	     (iter).count &&					\
 	     ((iov = iov_iter_iovec(&(iter))), 1);		\
@@ -62,32 +73,59 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to);
 
 size_t iov_iter_copy_from_user_atomic(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes);
-size_t iov_iter_copy_from_user(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(const struct iov_iter *i);
 size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i);
+size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i);
+unsigned long iov_iter_alignment(const struct iov_iter *i);
+void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov,
+			unsigned long nr_segs, size_t count);
+ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
+			size_t maxsize, size_t *start);
+ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
+			size_t maxsize, size_t *start);
+int iov_iter_npages(const struct iov_iter *i, int maxpages);
 
-static inline void iov_iter_init(struct iov_iter *i,
-			const struct iovec *iov, unsigned long nr_segs,
-			size_t count, size_t written)
+static inline size_t iov_iter_count(struct iov_iter *i)
 {
-	i->iov = iov;
-	i->nr_segs = nr_segs;
-	i->iov_offset = 0;
-	i->count = count + written;
+	return i->count;
+}
 
-	iov_iter_advance(i, written);
+/*
+ * Cap the iov_iter by given limit; note that the second argument is
+ * *not* the new size - it's upper limit for such.  Passing it a value
+ * greater than the amount of data in iov_iter is fine - it'll just do
+ * nothing in that case.
+ */
+static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
+{
+	/*
+	 * count doesn't have to fit in size_t - comparison extends both
+	 * operands to u64 here and any value that would be truncated by
+	 * conversion in assignement is by definition greater than all
+	 * values of size_t, including old i->count.
+	 */
+	if (i->count > count)
+		i->count = count;
 }
 
-static inline size_t iov_iter_count(struct iov_iter *i)
+/*
+ * reexpand a previously truncated iterator; count must be no more than how much
+ * we had shrunk it.
+ */
+static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 {
-	return i->count;
+	i->count = count;
 }
 
 int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
 int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len);
+int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
+			int offset, int len);
+int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
+		      int offset, int len);
 
 #endif
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index c52f827ba6c..4f844c6b03e 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -103,6 +103,7 @@ extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, u
 extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
 extern bool __weak is_trap_insn(uprobe_opcode_t *insn);
 extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
+extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
@@ -133,6 +134,9 @@ extern void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
+
+#define uprobe_get_trap_addr(regs)	instruction_pointer(regs)
+
 static inline int
 uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
 {
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 44b38b92236..7c9b484735c 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -52,6 +52,10 @@
 #define	CDC_NCM_NTB_MAX_SIZE_TX			32768	/* bytes */
 #define	CDC_NCM_NTB_MAX_SIZE_RX			32768	/* bytes */
 
+/* Initial NTB length */
+#define	CDC_NCM_NTB_DEF_SIZE_TX			16384	/* bytes */
+#define	CDC_NCM_NTB_DEF_SIZE_RX			16384	/* bytes */
+
 /* Minimum value for MaxDatagramSize, ch. 6.2.9 */
 #define	CDC_NCM_MIN_DATAGRAM_SIZE		1514	/* bytes */
 
@@ -72,16 +76,9 @@
 /* Restart the timer, if amount of datagrams is less than given value */
 #define	CDC_NCM_RESTART_TIMER_DATAGRAM_CNT	3
 #define	CDC_NCM_TIMER_PENDING_CNT		2
-#define CDC_NCM_TIMER_INTERVAL			(400UL * NSEC_PER_USEC)
-
-/* The following macro defines the minimum header space */
-#define	CDC_NCM_MIN_HDR_SIZE \
-	(sizeof(struct usb_cdc_ncm_nth16) + sizeof(struct usb_cdc_ncm_ndp16) + \
-	(CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16))
-
-#define CDC_NCM_NDP_SIZE \
-	(sizeof(struct usb_cdc_ncm_ndp16) +				\
-	      (CDC_NCM_DPT_DATAGRAMS_MAX + 1) * sizeof(struct usb_cdc_ncm_dpe16))
+#define CDC_NCM_TIMER_INTERVAL_USEC		400UL
+#define CDC_NCM_TIMER_INTERVAL_MIN		5UL
+#define CDC_NCM_TIMER_INTERVAL_MAX		(U32_MAX / NSEC_PER_USEC)
 
 #define cdc_ncm_comm_intf_is_mbim(x)  ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \
 				       (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE)
@@ -107,6 +104,9 @@ struct cdc_ncm_ctx {
 	spinlock_t mtx;
 	atomic_t stop;
 
+	u32 timer_interval;
+	u32 max_ndp_size;
+
 	u32 tx_timer_pending;
 	u32 tx_curr_frame_num;
 	u32 rx_max;
@@ -118,10 +118,21 @@ struct cdc_ncm_ctx {
 	u16 tx_ndp_modulus;
 	u16 tx_seq;
 	u16 rx_seq;
-	u16 connected;
+	u16 min_tx_pkt;
+
+	/* statistics */
+	u32 tx_curr_frame_payload;
+	u32 tx_reason_ntb_full;
+	u32 tx_reason_ndp_full;
+	u32 tx_reason_timeout;
+	u32 tx_reason_max_datagram;
+	u64 tx_overhead;
+	u64 tx_ntbs;
+	u64 rx_overhead;
+	u64 rx_ntbs;
 };
 
-u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf);
+u8 cdc_ncm_select_altsetting(struct usb_interface *intf);
 int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting);
 void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
 struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 1a64b26046e..9b7de1b4643 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -70,7 +70,9 @@
 	US_FLAG(NEEDS_CAP16,	0x00400000)			\
 		/* cannot handle READ_CAPACITY_10 */		\
 	US_FLAG(IGNORE_UAS,	0x00800000)			\
-		/* Device advertises UAS but it is broken */
+		/* Device advertises UAS but it is broken */	\
+	US_FLAG(BROKEN_FUA,	0x01000000)			\
+		/* Cannot handle FUA in WRITE or READ CDBs */	\
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index e4abb84199b..b46671e28de 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -106,6 +106,8 @@ static inline struct virtio_device *dev_to_virtio(struct device *_dev)
 int register_virtio_device(struct virtio_device *dev);
 void unregister_virtio_device(struct virtio_device *dev);
 
+void virtio_break_device(struct virtio_device *dev);
+
 /**
  * virtio_driver - operations for a virtio I/O driver
  * @driver: underlying device driver (populate name and owner).
diff --git a/include/linux/virtio_scsi.h b/include/linux/virtio_scsi.h
index 4195b97a3de..de429d1f435 100644
--- a/include/linux/virtio_scsi.h
+++ b/include/linux/virtio_scsi.h
@@ -35,11 +35,23 @@ struct virtio_scsi_cmd_req {
 	u8 lun[8];		/* Logical Unit Number */
 	u64 tag;		/* Command identifier */
 	u8 task_attr;		/* Task attribute */
-	u8 prio;
+	u8 prio;		/* SAM command priority field */
 	u8 crn;
 	u8 cdb[VIRTIO_SCSI_CDB_SIZE];
 } __packed;
 
+/* SCSI command request, followed by protection information */
+struct virtio_scsi_cmd_req_pi {
+	u8 lun[8];		/* Logical Unit Number */
+	u64 tag;		/* Command identifier */
+	u8 task_attr;		/* Task attribute */
+	u8 prio;		/* SAM command priority field */
+	u8 crn;
+	u32 pi_bytesout;	/* DataOUT PI Number of bytes */
+	u32 pi_bytesin;		/* DataIN PI Number of bytes */
+	u8 cdb[VIRTIO_SCSI_CDB_SIZE];
+} __packed;
+
 /* Response, followed by sense data and data-in */
 struct virtio_scsi_cmd_resp {
 	u32 sense_len;		/* Sense data length */
@@ -97,6 +109,7 @@ struct virtio_scsi_config {
 #define VIRTIO_SCSI_F_INOUT                    0
 #define VIRTIO_SCSI_F_HOTPLUG                  1
 #define VIRTIO_SCSI_F_CHANGE                   2
+#define VIRTIO_SCSI_F_T10_PI                   3
 
 /* Response codes */
 #define VIRTIO_SCSI_S_OK                       0
diff --git a/include/linux/wait.h b/include/linux/wait.h
index bd68819f081..6fb1ba5f9b2 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -25,6 +25,7 @@ struct wait_bit_key {
 	void			*flags;
 	int			bit_nr;
 #define WAIT_ATOMIC_T_BIT_NR	-1
+	unsigned long		private;
 };
 
 struct wait_bit_queue {
@@ -141,18 +142,19 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old)
 	list_del(&old->task_list);
 }
 
+typedef int wait_bit_action_f(struct wait_bit_key *);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_bit(wait_queue_head_t *, void *, int);
-int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
-int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
+int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
+int __wait_on_bit_lock(wait_queue_head_t *, struct wait_bit_queue *, wait_bit_action_f *, unsigned);
 void wake_up_bit(void *, int);
 void wake_up_atomic_t(atomic_t *);
-int out_of_line_wait_on_bit(void *, int, int (*)(void *), unsigned);
-int out_of_line_wait_on_bit_lock(void *, int, int (*)(void *), unsigned);
+int out_of_line_wait_on_bit(void *, int, wait_bit_action_f *, unsigned);
+int out_of_line_wait_on_bit_lock(void *, int, wait_bit_action_f *, unsigned);
 int out_of_line_wait_on_atomic_t(atomic_t *, int (*)(atomic_t *), unsigned);
 wait_queue_head_t *bit_waitqueue(void *, int);
 
@@ -854,11 +856,14 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 		(wait)->flags = 0;					\
 	} while (0)
 
+
+extern int bit_wait(struct wait_bit_key *);
+extern int bit_wait_io(struct wait_bit_key *);
+
 /**
  * wait_on_bit - wait for a bit to be cleared
  * @word: the word being waited on, a kernel virtual address
  * @bit: the bit of the word being waited on
- * @action: the function used to sleep, which may take special actions
  * @mode: the task state to sleep in
  *
  * There is a standard hashed waitqueue table for generic use. This
@@ -867,9 +872,62 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
  * call wait_on_bit() in threads waiting for the bit to clear.
  * One uses wait_on_bit() where one is waiting for the bit to clear,
  * but has no intention of setting it.
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit(void *word, int bit, unsigned mode)
+{
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit,
+				       bit_wait,
+				       mode);
+}
+
+/**
+ * wait_on_bit_io - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared.  This is similar to wait_on_bit(), but calls
+ * io_schedule() instead of schedule() for the actual waiting.
+ *
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
+ */
+static inline int
+wait_on_bit_io(void *word, int bit, unsigned mode)
+{
+	if (!test_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit(word, bit,
+				       bit_wait_io,
+				       mode);
+}
+
+/**
+ * wait_on_bit_action - wait for a bit to be cleared
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared, and allow the waiting action to be specified.
+ * This is like wait_on_bit() but allows fine control of how the waiting
+ * is done.
+ *
+ * Returned value will be zero if the bit was cleared, or non-zero
+ * if the process received a signal and the mode permitted wakeup
+ * on that signal.
  */
 static inline int
-wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode)
+wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
 {
 	if (!test_bit(bit, word))
 		return 0;
@@ -880,7 +938,6 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode)
  * wait_on_bit_lock - wait for a bit to be cleared, when wanting to set it
  * @word: the word being waited on, a kernel virtual address
  * @bit: the bit of the word being waited on
- * @action: the function used to sleep, which may take special actions
  * @mode: the task state to sleep in
  *
  * There is a standard hashed waitqueue table for generic use. This
@@ -891,9 +948,61 @@ wait_on_bit(void *word, int bit, int (*action)(void *), unsigned mode)
  * wait_on_bit() in threads waiting to be able to set the bit.
  * One uses wait_on_bit_lock() where one is waiting for the bit to
  * clear with the intention of setting it, and when done, clearing it.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock(void *word, int bit, unsigned mode)
+{
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode);
+}
+
+/**
+ * wait_on_bit_lock_io - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared and then to atomically set it.  This is similar
+ * to wait_on_bit(), but calls io_schedule() instead of schedule()
+ * for the actual waiting.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
+ */
+static inline int
+wait_on_bit_lock_io(void *word, int bit, unsigned mode)
+{
+	if (!test_and_set_bit(bit, word))
+		return 0;
+	return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode);
+}
+
+/**
+ * wait_on_bit_lock_action - wait for a bit to be cleared, when wanting to set it
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ * @action: the function used to sleep, which may take special actions
+ * @mode: the task state to sleep in
+ *
+ * Use the standard hashed waitqueue table to wait for a bit
+ * to be cleared and then to set it, and allow the waiting action
+ * to be specified.
+ * This is like wait_on_bit() but allows fine control of how the waiting
+ * is done.
+ *
+ * Returns zero if the bit was (eventually) found to be clear and was
+ * set.  Returns non-zero if a signal was delivered to the process and
+ * the @mode allows that signal to wake the process.
  */
 static inline int
-wait_on_bit_lock(void *word, int bit, int (*action)(void *), unsigned mode)
+wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
 {
 	if (!test_and_set_bit(bit, word))
 		return 0;
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 1b22c42e9c2..a0cc2e95ed1 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -56,9 +56,8 @@ enum {
 	WORK_NR_COLORS		= (1 << WORK_STRUCT_COLOR_BITS) - 1,
 	WORK_NO_COLOR		= WORK_NR_COLORS,
 
-	/* special cpu IDs */
+	/* not bound to any CPU, prefer the local CPU */
 	WORK_CPU_UNBOUND	= NR_CPUS,
-	WORK_CPU_END		= NR_CPUS + 1,
 
 	/*
 	 * Reserve 7 bits off of pwq pointer w/ debugobjects turned off.
@@ -274,13 +273,6 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; }
 #define delayed_work_pending(w) \
 	work_pending(&(w)->work)
 
-/**
- * work_clear_pending - for internal use only, mark a work item as not pending
- * @work: The work item in question
- */
-#define work_clear_pending(work) \
-	clear_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))
-
 /*
  * Workqueue flags and constants.  For details, please refer to
  * Documentation/workqueue.txt.
@@ -340,6 +332,9 @@ enum {
  * short queue flush time.  Don't queue works which can run for too
  * long.
  *
+ * system_highpri_wq is similar to system_wq but for work items which
+ * require WQ_HIGHPRI.
+ *
  * system_long_wq is similar to system_wq but may host long running
  * works.  Queue flushing might take relatively long.
  *
@@ -358,26 +353,13 @@ enum {
  * 'wq_power_efficient' is disabled.  See WQ_POWER_EFFICIENT for more info.
  */
 extern struct workqueue_struct *system_wq;
+extern struct workqueue_struct *system_highpri_wq;
 extern struct workqueue_struct *system_long_wq;
 extern struct workqueue_struct *system_unbound_wq;
 extern struct workqueue_struct *system_freezable_wq;
 extern struct workqueue_struct *system_power_efficient_wq;
 extern struct workqueue_struct *system_freezable_power_efficient_wq;
 
-static inline struct workqueue_struct * __deprecated __system_nrt_wq(void)
-{
-	return system_wq;
-}
-
-static inline struct workqueue_struct * __deprecated __system_nrt_freezable_wq(void)
-{
-	return system_freezable_wq;
-}
-
-/* equivlalent to system_wq and system_freezable_wq, deprecated */
-#define system_nrt_wq			__system_nrt_wq()
-#define system_nrt_freezable_wq		__system_nrt_freezable_wq()
-
 extern struct workqueue_struct *
 __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 	struct lock_class_key *key, const char *lock_name, ...) __printf(1, 6);
@@ -587,18 +569,6 @@ static inline bool keventd_up(void)
 	return system_wq != NULL;
 }
 
-/* used to be different but now identical to flush_work(), deprecated */
-static inline bool __deprecated flush_work_sync(struct work_struct *work)
-{
-	return flush_work(work);
-}
-
-/* used to be different but now identical to flush_delayed_work(), deprecated */
-static inline bool __deprecated flush_delayed_work_sync(struct delayed_work *dwork)
-{
-	return flush_delayed_work(dwork);
-}
-
 #ifndef CONFIG_SMP
 static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg)
 {
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 5777c13849b..a219be961c0 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -90,7 +90,6 @@ struct writeback_control {
  * fs/fs-writeback.c
  */	
 struct bdi_writeback;
-int inode_wait(void *);
 void writeback_inodes_sb(struct super_block *, enum wb_reason reason);
 void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
 							enum wb_reason reason);
@@ -105,7 +104,7 @@ void inode_wait_for_writeback(struct inode *inode);
 static inline void wait_on_inode(struct inode *inode)
 {
 	might_sleep();
-	wait_on_bit(&inode->i_state, __I_NEW, inode_wait, TASK_UNINTERRUPTIBLE);
+	wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE);
 }
 
 /*
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index bca25dc53f9..8fab6fa0dbf 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -432,6 +432,7 @@ void *vb2_plane_vaddr(struct vb2_buffer *vb, unsigned int plane_no);
 void *vb2_plane_cookie(struct vb2_buffer *vb, unsigned int plane_no);
 
 void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state);
+void vb2_discard_done(struct vb2_queue *q);
 int vb2_wait_for_all_buffers(struct vb2_queue *q);
 
 int vb2_querybuf(struct vb2_queue *q, struct v4l2_buffer *b);
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
index f7d372b7d4f..79b530fb2c4 100644
--- a/include/net/6lowpan.h
+++ b/include/net/6lowpan.h
@@ -54,6 +54,7 @@
 #define __6LOWPAN_H__
 
 #include <net/ipv6.h>
+#include <net/net_namespace.h>
 
 #define UIP_802154_SHORTADDR_LEN	2  /* compressed ipv6 address length */
 #define UIP_IPH_LEN			40 /* ipv6 fixed header size */
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 933a9f22a05..f679877bb60 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -306,11 +306,6 @@ static inline void addrconf_addr_solict_mult(const struct in6_addr *addr,
 		      htonl(0xFF000000) | addr->s6_addr32[3]);
 }
 
-static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr)
-{
-	return (addr->s6_addr32[0] & htonl(0xFF000000)) == htonl(0xFF000000);
-}
-
 static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr)
 {
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
diff --git a/include/net/af_ieee802154.h b/include/net/af_ieee802154.h
index f79ae2aa76d..085940f7eee 100644
--- a/include/net/af_ieee802154.h
+++ b/include/net/af_ieee802154.h
@@ -57,6 +57,14 @@ struct sockaddr_ieee802154 {
 /* get/setsockopt */
 #define SOL_IEEE802154	0
 
-#define WPAN_WANTACK	0
+#define WPAN_WANTACK		0
+#define WPAN_SECURITY		1
+#define WPAN_SECURITY_LEVEL	2
+
+#define WPAN_SECURITY_DEFAULT	0
+#define WPAN_SECURITY_OFF	1
+#define WPAN_SECURITY_ON	2
+
+#define WPAN_SECURITY_LEVEL_DEFAULT	(-1)
 
 #endif
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index be150cf8cd4..16587dcd6a9 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -367,6 +367,7 @@ enum {
 #define HCI_ERROR_REMOTE_POWER_OFF	0x15
 #define HCI_ERROR_LOCAL_HOST_TERM	0x16
 #define HCI_ERROR_PAIRING_NOT_ALLOWED	0x18
+#define HCI_ERROR_ADVERTISING_TIMEOUT	0x3c
 
 /* Flow control modes */
 #define HCI_FLOW_CTL_MODE_PACKET_BASED	0x00
@@ -1053,6 +1054,17 @@ struct hci_cp_write_page_scan_activity {
 	__le16   window;
 } __packed;
 
+#define HCI_OP_READ_TX_POWER		0x0c2d
+struct hci_cp_read_tx_power {
+	__le16   handle;
+	__u8     type;
+} __packed;
+struct hci_rp_read_tx_power {
+	__u8     status;
+	__le16   handle;
+	__s8     tx_power;
+} __packed;
+
 #define HCI_OP_READ_PAGE_SCAN_TYPE	0x0c46
 struct hci_rp_read_page_scan_type {
 	__u8     status;
@@ -1063,6 +1075,16 @@ struct hci_rp_read_page_scan_type {
 	#define PAGE_SCAN_TYPE_STANDARD		0x00
 	#define PAGE_SCAN_TYPE_INTERLACED	0x01
 
+#define HCI_OP_READ_RSSI		0x1405
+struct hci_cp_read_rssi {
+	__le16   handle;
+} __packed;
+struct hci_rp_read_rssi {
+	__u8     status;
+	__le16   handle;
+	__s8     rssi;
+} __packed;
+
 #define HCI_OP_READ_LOCAL_AMP_INFO	0x1409
 struct hci_rp_read_local_amp_info {
 	__u8     status;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 5f8bc05694a..b386bf17e6c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -68,6 +68,11 @@ struct discovery_state {
 	struct list_head	unknown;	/* Name state not known */
 	struct list_head	resolve;	/* Name needs to be resolved */
 	__u32			timestamp;
+	bdaddr_t		last_adv_addr;
+	u8			last_adv_addr_type;
+	s8			last_adv_rssi;
+	u8			last_adv_data[HCI_MAX_AD_LENGTH];
+	u8			last_adv_data_len;
 };
 
 struct hci_conn_hash {
@@ -140,6 +145,10 @@ struct oob_data {
 /* Default LE RPA expiry time, 15 minutes */
 #define HCI_DEFAULT_RPA_TIMEOUT		(15 * 60)
 
+/* Default min/max age of connection information (1s/3s) */
+#define DEFAULT_CONN_INFO_MIN_AGE	1000
+#define DEFAULT_CONN_INFO_MAX_AGE	3000
+
 struct amp_assoc {
 	__u16	len;
 	__u16	offset;
@@ -194,6 +203,9 @@ struct hci_dev {
 	__u16		le_scan_window;
 	__u16		le_conn_min_interval;
 	__u16		le_conn_max_interval;
+	__u16		discov_interleaved_timeout;
+	__u16		conn_info_min_age;
+	__u16		conn_info_max_age;
 	__u8		ssp_debug_mode;
 
 	__u16		devid_source;
@@ -368,8 +380,13 @@ struct hci_conn {
 	__u16		setting;
 	__u16		le_conn_min_interval;
 	__u16		le_conn_max_interval;
+	__s8		rssi;
+	__s8		tx_power;
+	__s8		max_tx_power;
 	unsigned long	flags;
 
+	unsigned long	conn_info_timestamp;
+
 	__u8		remote_cap;
 	__u8		remote_auth;
 	__u8		remote_id;
@@ -1204,8 +1221,8 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event);
  */
 #define DISCOV_LE_SCAN_WIN		0x12
 #define DISCOV_LE_SCAN_INT		0x12
-#define DISCOV_LE_TIMEOUT		msecs_to_jiffies(10240)
-#define DISCOV_INTERLEAVED_TIMEOUT	msecs_to_jiffies(5120)
+#define DISCOV_LE_TIMEOUT		10240	/* msec */
+#define DISCOV_INTERLEAVED_TIMEOUT	5120	/* msec */
 #define DISCOV_INTERLEAVED_INQUIRY_LEN	0x04
 #define DISCOV_BREDR_INQUIRY_LEN	0x08
 
@@ -1265,7 +1282,8 @@ void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
 				       u8 *randomizer256, u8 status);
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		       u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name,
-		       u8 ssp, u8 *eir, u16 eir_len);
+		       u8 ssp, u8 *eir, u16 eir_len, u8 *scan_rsp,
+		       u8 scan_rsp_len);
 void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		      u8 addr_type, s8 rssi, u8 *name, u8 name_len);
 void mgmt_discovering(struct hci_dev *hdev, u8 discovering);
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index d4b571c2f9f..bcffc9ae0c8 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -181,6 +181,9 @@ struct mgmt_cp_load_link_keys {
 } __packed;
 #define MGMT_LOAD_LINK_KEYS_SIZE	3
 
+#define MGMT_LTK_UNAUTHENTICATED	0x00
+#define MGMT_LTK_AUTHENTICATED		0x01
+
 struct mgmt_ltk_info {
 	struct mgmt_addr_info addr;
 	__u8	type;
@@ -409,6 +412,18 @@ struct mgmt_cp_load_irks {
 } __packed;
 #define MGMT_LOAD_IRKS_SIZE		2
 
+#define MGMT_OP_GET_CONN_INFO		0x0031
+struct mgmt_cp_get_conn_info {
+	struct mgmt_addr_info addr;
+} __packed;
+#define MGMT_GET_CONN_INFO_SIZE		MGMT_ADDR_INFO_SIZE
+struct mgmt_rp_get_conn_info {
+	struct mgmt_addr_info addr;
+	__s8	rssi;
+	__s8	tx_power;
+	__s8	max_tx_power;
+} __packed;
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16	opcode;
diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h
index 2611cc389d7..578b83127af 100644
--- a/include/net/bluetooth/rfcomm.h
+++ b/include/net/bluetooth/rfcomm.h
@@ -173,7 +173,7 @@ struct rfcomm_dlc {
 	struct sk_buff_head   tx_queue;
 	struct timer_list     timer;
 
-	spinlock_t    lock;
+	struct mutex  lock;
 	unsigned long state;
 	unsigned long flags;
 	atomic_t      refcnt;
@@ -244,8 +244,8 @@ int  rfcomm_dlc_get_modem_status(struct rfcomm_dlc *d, u8 *v24_sig);
 void rfcomm_dlc_accept(struct rfcomm_dlc *d);
 struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel);
 
-#define rfcomm_dlc_lock(d)     spin_lock(&d->lock)
-#define rfcomm_dlc_unlock(d)   spin_unlock(&d->lock)
+#define rfcomm_dlc_lock(d)     mutex_lock(&d->lock)
+#define rfcomm_dlc_unlock(d)   mutex_unlock(&d->lock)
 
 static inline void rfcomm_dlc_hold(struct rfcomm_dlc *d)
 {
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index f856e5a746f..e46c437944f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -109,6 +109,13 @@ enum ieee80211_band {
  *	channel as the control or any of the secondary channels.
  *	This may be due to the driver or due to regulatory bandwidth
  *	restrictions.
+ * @IEEE80211_CHAN_INDOOR_ONLY: see %NL80211_FREQUENCY_ATTR_INDOOR_ONLY
+ * @IEEE80211_CHAN_GO_CONCURRENT: see %NL80211_FREQUENCY_ATTR_GO_CONCURRENT
+ * @IEEE80211_CHAN_NO_20MHZ: 20 MHz bandwidth is not permitted
+ *	on this channel.
+ * @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted
+ *	on this channel.
+ *
  */
 enum ieee80211_channel_flags {
 	IEEE80211_CHAN_DISABLED		= 1<<0,
@@ -120,6 +127,10 @@ enum ieee80211_channel_flags {
 	IEEE80211_CHAN_NO_OFDM		= 1<<6,
 	IEEE80211_CHAN_NO_80MHZ		= 1<<7,
 	IEEE80211_CHAN_NO_160MHZ	= 1<<8,
+	IEEE80211_CHAN_INDOOR_ONLY	= 1<<9,
+	IEEE80211_CHAN_GO_CONCURRENT	= 1<<10,
+	IEEE80211_CHAN_NO_20MHZ		= 1<<11,
+	IEEE80211_CHAN_NO_10MHZ		= 1<<12,
 };
 
 #define IEEE80211_CHAN_NO_HT40 \
@@ -330,8 +341,8 @@ struct vif_params {
  * @seq_len: length of @seq.
  */
 struct key_params {
-	u8 *key;
-	u8 *seq;
+	const u8 *key;
+	const u8 *seq;
 	int key_len;
 	int seq_len;
 	u32 cipher;
@@ -441,10 +452,13 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
  * cfg80211_chandef_dfs_required - checks if radar detection is required
  * @wiphy: the wiphy to validate against
  * @chandef: the channel definition to check
- * Return: 1 if radar detection is required, 0 if it is not, < 0 on error
+ * @iftype: the interface type as specified in &enum nl80211_iftype
+ * Returns:
+ *	1 if radar detection is required, 0 if it is not, < 0 on error
  */
 int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
-				  const struct cfg80211_chan_def *chandef);
+				  const struct cfg80211_chan_def *chandef,
+				  enum nl80211_iftype iftype);
 
 /**
  * ieee80211_chandef_rate_flags - returns rate flags for a channel
@@ -654,7 +668,6 @@ struct cfg80211_acl_data {
  * @p2p_opp_ps: P2P opportunistic PS
  * @acl: ACL configuration used by the drivers which has support for
  *	MAC address based access control
- * @radar_required: set if radar detection is required
  */
 struct cfg80211_ap_settings {
 	struct cfg80211_chan_def chandef;
@@ -672,7 +685,6 @@ struct cfg80211_ap_settings {
 	u8 p2p_ctwindow;
 	bool p2p_opp_ps;
 	const struct cfg80211_acl_data *acl;
-	bool radar_required;
 };
 
 /**
@@ -682,8 +694,10 @@ struct cfg80211_ap_settings {
  *
  * @chandef: defines the channel to use after the switch
  * @beacon_csa: beacon data while performing the switch
- * @counter_offset_beacon: offset for the counter within the beacon (tail)
- * @counter_offset_presp: offset for the counter within the probe response
+ * @counter_offsets_beacon: offsets of the counters within the beacon (tail)
+ * @counter_offsets_presp: offsets of the counters within the probe response
+ * @n_counter_offsets_beacon: number of csa counters the beacon (tail)
+ * @n_counter_offsets_presp: number of csa counters in the probe response
  * @beacon_after: beacon data to be used on the new channel
  * @radar_required: whether radar detection is required on the new channel
  * @block_tx: whether transmissions should be blocked while changing
@@ -692,7 +706,10 @@ struct cfg80211_ap_settings {
 struct cfg80211_csa_settings {
 	struct cfg80211_chan_def chandef;
 	struct cfg80211_beacon_data beacon_csa;
-	u16 counter_offset_beacon, counter_offset_presp;
+	const u16 *counter_offsets_beacon;
+	const u16 *counter_offsets_presp;
+	unsigned int n_counter_offsets_beacon;
+	unsigned int n_counter_offsets_presp;
 	struct cfg80211_beacon_data beacon_after;
 	bool radar_required;
 	bool block_tx;
@@ -856,36 +873,38 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
  * @STATION_INFO_NONPEER_PM: @nonpeer_pm filled
  * @STATION_INFO_CHAIN_SIGNAL: @chain_signal filled
  * @STATION_INFO_CHAIN_SIGNAL_AVG: @chain_signal_avg filled
+ * @STATION_INFO_EXPECTED_THROUGHPUT: @expected_throughput filled
  */
 enum station_info_flags {
-	STATION_INFO_INACTIVE_TIME	= 1<<0,
-	STATION_INFO_RX_BYTES		= 1<<1,
-	STATION_INFO_TX_BYTES		= 1<<2,
-	STATION_INFO_LLID		= 1<<3,
-	STATION_INFO_PLID		= 1<<4,
-	STATION_INFO_PLINK_STATE	= 1<<5,
-	STATION_INFO_SIGNAL		= 1<<6,
-	STATION_INFO_TX_BITRATE		= 1<<7,
-	STATION_INFO_RX_PACKETS		= 1<<8,
-	STATION_INFO_TX_PACKETS		= 1<<9,
-	STATION_INFO_TX_RETRIES		= 1<<10,
-	STATION_INFO_TX_FAILED		= 1<<11,
-	STATION_INFO_RX_DROP_MISC	= 1<<12,
-	STATION_INFO_SIGNAL_AVG		= 1<<13,
-	STATION_INFO_RX_BITRATE		= 1<<14,
-	STATION_INFO_BSS_PARAM          = 1<<15,
-	STATION_INFO_CONNECTED_TIME	= 1<<16,
-	STATION_INFO_ASSOC_REQ_IES	= 1<<17,
-	STATION_INFO_STA_FLAGS		= 1<<18,
-	STATION_INFO_BEACON_LOSS_COUNT	= 1<<19,
-	STATION_INFO_T_OFFSET		= 1<<20,
-	STATION_INFO_LOCAL_PM		= 1<<21,
-	STATION_INFO_PEER_PM		= 1<<22,
-	STATION_INFO_NONPEER_PM		= 1<<23,
-	STATION_INFO_RX_BYTES64		= 1<<24,
-	STATION_INFO_TX_BYTES64		= 1<<25,
-	STATION_INFO_CHAIN_SIGNAL	= 1<<26,
-	STATION_INFO_CHAIN_SIGNAL_AVG	= 1<<27,
+	STATION_INFO_INACTIVE_TIME		= BIT(0),
+	STATION_INFO_RX_BYTES			= BIT(1),
+	STATION_INFO_TX_BYTES			= BIT(2),
+	STATION_INFO_LLID			= BIT(3),
+	STATION_INFO_PLID			= BIT(4),
+	STATION_INFO_PLINK_STATE		= BIT(5),
+	STATION_INFO_SIGNAL			= BIT(6),
+	STATION_INFO_TX_BITRATE			= BIT(7),
+	STATION_INFO_RX_PACKETS			= BIT(8),
+	STATION_INFO_TX_PACKETS			= BIT(9),
+	STATION_INFO_TX_RETRIES			= BIT(10),
+	STATION_INFO_TX_FAILED			= BIT(11),
+	STATION_INFO_RX_DROP_MISC		= BIT(12),
+	STATION_INFO_SIGNAL_AVG			= BIT(13),
+	STATION_INFO_RX_BITRATE			= BIT(14),
+	STATION_INFO_BSS_PARAM			= BIT(15),
+	STATION_INFO_CONNECTED_TIME		= BIT(16),
+	STATION_INFO_ASSOC_REQ_IES		= BIT(17),
+	STATION_INFO_STA_FLAGS			= BIT(18),
+	STATION_INFO_BEACON_LOSS_COUNT		= BIT(19),
+	STATION_INFO_T_OFFSET			= BIT(20),
+	STATION_INFO_LOCAL_PM			= BIT(21),
+	STATION_INFO_PEER_PM			= BIT(22),
+	STATION_INFO_NONPEER_PM			= BIT(23),
+	STATION_INFO_RX_BYTES64			= BIT(24),
+	STATION_INFO_TX_BYTES64			= BIT(25),
+	STATION_INFO_CHAIN_SIGNAL		= BIT(26),
+	STATION_INFO_CHAIN_SIGNAL_AVG		= BIT(27),
+	STATION_INFO_EXPECTED_THROUGHPUT	= BIT(28),
 };
 
 /**
@@ -1007,6 +1026,8 @@ struct sta_bss_parameters {
  * @local_pm: local mesh STA power save mode
  * @peer_pm: peer mesh STA power save mode
  * @nonpeer_pm: non-peer mesh STA power save mode
+ * @expected_throughput: expected throughput in kbps (including 802.11 headers)
+ *	towards this station.
  */
 struct station_info {
 	u32 filled;
@@ -1045,6 +1066,8 @@ struct station_info {
 	enum nl80211_mesh_power_mode peer_pm;
 	enum nl80211_mesh_power_mode nonpeer_pm;
 
+	u32 expected_throughput;
+
 	/*
 	 * Note: Add a new enum station_info_flags value for each new field and
 	 * use it to check which fields are initialized.
@@ -1052,6 +1075,19 @@ struct station_info {
 };
 
 /**
+ * cfg80211_get_station - retrieve information about a given station
+ * @dev: the device where the station is supposed to be connected to
+ * @mac_addr: the mac address of the station of interest
+ * @sinfo: pointer to the structure to fill with the information
+ *
+ * Returns 0 on success and sinfo is filled with the available information
+ * otherwise returns a negative error code and the content of sinfo has to be
+ * considered undefined.
+ */
+int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr,
+			 struct station_info *sinfo);
+
+/**
  * enum monitor_flags - monitor flags
  *
  * Monitor interface configuration flags. Note that these must be the bits
@@ -1152,7 +1188,7 @@ struct bss_parameters {
 	int use_cts_prot;
 	int use_short_preamble;
 	int use_short_slot_time;
-	u8 *basic_rates;
+	const u8 *basic_rates;
 	u8 basic_rates_len;
 	int ap_isolate;
 	int ht_opmode;
@@ -1682,10 +1718,10 @@ struct cfg80211_disassoc_request {
  * @ht_capa_mask:  The bits of ht_capa which are to be used.
  */
 struct cfg80211_ibss_params {
-	u8 *ssid;
-	u8 *bssid;
+	const u8 *ssid;
+	const u8 *bssid;
 	struct cfg80211_chan_def chandef;
-	u8 *ie;
+	const u8 *ie;
 	u8 ssid_len, ie_len;
 	u16 beacon_interval;
 	u32 basic_rates;
@@ -1794,8 +1830,8 @@ struct cfg80211_bitrate_mask {
  * @pmkid: The PMK material itself.
  */
 struct cfg80211_pmksa {
-	u8 *bssid;
-	u8 *pmkid;
+	const u8 *bssid;
+	const u8 *pmkid;
 };
 
 /**
@@ -1810,7 +1846,7 @@ struct cfg80211_pmksa {
  * memory, free @mask only!
  */
 struct cfg80211_pkt_pattern {
-	u8 *mask, *pattern;
+	const u8 *mask, *pattern;
 	int pattern_len;
 	int pkt_offset;
 };
@@ -1974,6 +2010,8 @@ struct cfg80211_update_ft_ies_params {
  * @len: buffer length
  * @no_cck: don't use cck rates for this frame
  * @dont_wait_for_ack: tells the low level not to wait for an ack
+ * @n_csa_offsets: length of csa_offsets array
+ * @csa_offsets: array of all the csa offsets in the frame
  */
 struct cfg80211_mgmt_tx_params {
 	struct ieee80211_channel *chan;
@@ -1983,6 +2021,8 @@ struct cfg80211_mgmt_tx_params {
 	size_t len;
 	bool no_cck;
 	bool dont_wait_for_ack;
+	int n_csa_offsets;
+	const u16 *csa_offsets;
 };
 
 /**
@@ -2278,6 +2318,10 @@ struct cfg80211_qos_map {
  * @channel_switch: initiate channel-switch procedure (with CSA)
  *
  * @set_qos_map: Set QoS mapping information to the driver
+ *
+ * @set_ap_chanwidth: Set the AP (including P2P GO) mode channel width for the
+ *	given interface This is used e.g. for dynamic HT 20/40 MHz channel width
+ *	changes during the lifetime of the BSS.
  */
 struct cfg80211_ops {
 	int	(*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow);
@@ -2320,28 +2364,29 @@ struct cfg80211_ops {
 
 
 	int	(*add_station)(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *mac, struct station_parameters *params);
+			       const u8 *mac,
+			       struct station_parameters *params);
 	int	(*del_station)(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *mac);
+			       const u8 *mac);
 	int	(*change_station)(struct wiphy *wiphy, struct net_device *dev,
-				  u8 *mac, struct station_parameters *params);
+				  const u8 *mac,
+				  struct station_parameters *params);
 	int	(*get_station)(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *mac, struct station_info *sinfo);
+			       const u8 *mac, struct station_info *sinfo);
 	int	(*dump_station)(struct wiphy *wiphy, struct net_device *dev,
-			       int idx, u8 *mac, struct station_info *sinfo);
+				int idx, u8 *mac, struct station_info *sinfo);
 
 	int	(*add_mpath)(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *dst, u8 *next_hop);
+			       const u8 *dst, const u8 *next_hop);
 	int	(*del_mpath)(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *dst);
+			       const u8 *dst);
 	int	(*change_mpath)(struct wiphy *wiphy, struct net_device *dev,
-				  u8 *dst, u8 *next_hop);
+				  const u8 *dst, const u8 *next_hop);
 	int	(*get_mpath)(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *dst, u8 *next_hop,
-			       struct mpath_info *pinfo);
+			     u8 *dst, u8 *next_hop, struct mpath_info *pinfo);
 	int	(*dump_mpath)(struct wiphy *wiphy, struct net_device *dev,
-			       int idx, u8 *dst, u8 *next_hop,
-			       struct mpath_info *pinfo);
+			      int idx, u8 *dst, u8 *next_hop,
+			      struct mpath_info *pinfo);
 	int	(*get_mesh_config)(struct wiphy *wiphy,
 				struct net_device *dev,
 				struct mesh_config *conf);
@@ -2471,11 +2516,11 @@ struct cfg80211_ops {
 				  struct cfg80211_gtk_rekey_data *data);
 
 	int	(*tdls_mgmt)(struct wiphy *wiphy, struct net_device *dev,
-			     u8 *peer, u8 action_code,  u8 dialog_token,
+			     const u8 *peer, u8 action_code,  u8 dialog_token,
 			     u16 status_code, u32 peer_capability,
 			     const u8 *buf, size_t len);
 	int	(*tdls_oper)(struct wiphy *wiphy, struct net_device *dev,
-			     u8 *peer, enum nl80211_tdls_operation oper);
+			     const u8 *peer, enum nl80211_tdls_operation oper);
 
 	int	(*probe_client)(struct wiphy *wiphy, struct net_device *dev,
 				const u8 *peer, u64 *cookie);
@@ -2521,9 +2566,13 @@ struct cfg80211_ops {
 	int	(*channel_switch)(struct wiphy *wiphy,
 				  struct net_device *dev,
 				  struct cfg80211_csa_settings *params);
+
 	int     (*set_qos_map)(struct wiphy *wiphy,
 			       struct net_device *dev,
 			       struct cfg80211_qos_map *qos_map);
+
+	int	(*set_ap_chanwidth)(struct wiphy *wiphy, struct net_device *dev,
+				    struct cfg80211_chan_def *chandef);
 };
 
 /*
@@ -2618,6 +2667,7 @@ struct ieee80211_iface_limit {
  *	between infrastructure and AP types must match. This is required
  *	only in special cases.
  * @radar_detect_widths: bitmap of channel widths supported for radar detection
+ * @radar_detect_regions: bitmap of regions supported for radar detection
  *
  * With this structure the driver can describe which interface
  * combinations it supports concurrently.
@@ -2675,6 +2725,7 @@ struct ieee80211_iface_combination {
 	u8 n_limits;
 	bool beacon_int_infra_match;
 	u8 radar_detect_widths;
+	u8 radar_detect_regions;
 };
 
 struct ieee80211_txrx_stypes {
@@ -2905,6 +2956,17 @@ struct wiphy_vendor_command {
  *	(including P2P GO) or 0 to indicate no such limit is advertised. The
  *	driver is allowed to advertise a theoretical limit that it can reach in
  *	some cases, but may not always reach.
+ *
+ * @max_num_csa_counters: Number of supported csa_counters in beacons
+ *	and probe responses.  This value should be set if the driver
+ *	wishes to limit the number of csa counters. Default (0) means
+ *	infinite.
+ * @max_adj_channel_rssi_comp: max offset of between the channel on which the
+ *	frame was sent and the channel on which the frame was heard for which
+ *	the reported rssi is still valid. If a driver is able to compensate the
+ *	low rssi when a frame is heard on different channel, then it should set
+ *	this variable to the maximal offset for which it can compensate.
+ *	This value should be set in MHz.
  */
 struct wiphy {
 	/* assign these fields before you register the wiphy */
@@ -3022,6 +3084,9 @@ struct wiphy {
 
 	u16 max_ap_assoc_sta;
 
+	u8 max_num_csa_counters;
+	u8 max_adj_channel_rssi_comp;
+
 	char priv[0] __aligned(NETDEV_ALIGN);
 };
 
@@ -3194,6 +3259,7 @@ struct cfg80211_cached_keys;
  * @ibss_dfs_possible: (private) IBSS may change to a DFS channel
  * @event_list: (private) list for internal event processing
  * @event_lock: (private) lock for event list
+ * @owner_nlportid: (private) owner socket port ID
  */
 struct wireless_dev {
 	struct wiphy *wiphy;
@@ -3241,13 +3307,15 @@ struct wireless_dev {
 	unsigned long cac_start_time;
 	unsigned int cac_time_ms;
 
+	u32 owner_nlportid;
+
 #ifdef CONFIG_CFG80211_WEXT
 	/* wext data */
 	struct {
 		struct cfg80211_ibss_params ibss;
 		struct cfg80211_connect_params connect;
 		struct cfg80211_cached_keys *keys;
-		u8 *ie;
+		const u8 *ie;
 		size_t ie_len;
 		u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN];
 		u8 ssid[IEEE80211_MAX_SSID_LEN];
@@ -3488,7 +3556,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
  * Return: 0 on success, or a negative error code.
  */
 int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
-			     enum nl80211_iftype iftype, u8 *bssid, bool qos);
+			     enum nl80211_iftype iftype, const u8 *bssid,
+			     bool qos);
 
 /**
  * ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame
@@ -3600,7 +3669,7 @@ int regulatory_hint(struct wiphy *wiphy, const char *alpha2);
  * default channel settings will be disregarded. If no rule is found for a
  * channel on the regulatory domain the channel will be disabled.
  * Drivers using this for a wiphy should also set the wiphy flag
- * WIPHY_FLAG_CUSTOM_REGULATORY or cfg80211 will set it for the wiphy
+ * REGULATORY_CUSTOM_REG or cfg80211 will set it for the wiphy
  * that called this helper.
  */
 void wiphy_apply_custom_regulatory(struct wiphy *wiphy,
@@ -4289,7 +4358,7 @@ void cfg80211_roamed_bss(struct net_device *dev, struct cfg80211_bss *bss,
  * and not try to connect to any AP any more.
  */
 void cfg80211_disconnected(struct net_device *dev, u16 reason,
-			   u8 *ie, size_t ie_len, gfp_t gfp);
+			   const u8 *ie, size_t ie_len, gfp_t gfp);
 
 /**
  * cfg80211_ready_on_channel - notification of remain_on_channel start
@@ -4543,12 +4612,14 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy,
  * cfg80211_reg_can_beacon - check if beaconing is allowed
  * @wiphy: the wiphy
  * @chandef: the channel definition
+ * @iftype: interface type
  *
  * Return: %true if there is no secondary channel or the secondary channel(s)
  * can be used for beaconing (i.e. is not a radar channel etc.)
  */
 bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
-			     struct cfg80211_chan_def *chandef);
+			     struct cfg80211_chan_def *chandef,
+			     enum nl80211_iftype iftype);
 
 /*
  * cfg80211_ch_switch_notify - update wdev channel and notify userspace
@@ -4694,6 +4765,84 @@ void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp);
  */
 unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy);
 
+/**
+ * cfg80211_check_combinations - check interface combinations
+ *
+ * @wiphy: the wiphy
+ * @num_different_channels: the number of different channels we want
+ *	to use for verification
+ * @radar_detect: a bitmap where each bit corresponds to a channel
+ *	width where radar detection is needed, as in the definition of
+ *	&struct ieee80211_iface_combination.@radar_detect_widths
+ * @iftype_num: array with the numbers of interfaces of each interface
+ *	type.  The index is the interface type as specified in &enum
+ *	nl80211_iftype.
+ *
+ * This function can be called by the driver to check whether a
+ * combination of interfaces and their types are allowed according to
+ * the interface combinations.
+ */
+int cfg80211_check_combinations(struct wiphy *wiphy,
+				const int num_different_channels,
+				const u8 radar_detect,
+				const int iftype_num[NUM_NL80211_IFTYPES]);
+
+/**
+ * cfg80211_iter_combinations - iterate over matching combinations
+ *
+ * @wiphy: the wiphy
+ * @num_different_channels: the number of different channels we want
+ *	to use for verification
+ * @radar_detect: a bitmap where each bit corresponds to a channel
+ *	width where radar detection is needed, as in the definition of
+ *	&struct ieee80211_iface_combination.@radar_detect_widths
+ * @iftype_num: array with the numbers of interfaces of each interface
+ *	type.  The index is the interface type as specified in &enum
+ *	nl80211_iftype.
+ * @iter: function to call for each matching combination
+ * @data: pointer to pass to iter function
+ *
+ * This function can be called by the driver to check what possible
+ * combinations it fits in at a given moment, e.g. for channel switching
+ * purposes.
+ */
+int cfg80211_iter_combinations(struct wiphy *wiphy,
+			       const int num_different_channels,
+			       const u8 radar_detect,
+			       const int iftype_num[NUM_NL80211_IFTYPES],
+			       void (*iter)(const struct ieee80211_iface_combination *c,
+					    void *data),
+			       void *data);
+
+/*
+ * cfg80211_stop_iface - trigger interface disconnection
+ *
+ * @wiphy: the wiphy
+ * @wdev: wireless device
+ * @gfp: context flags
+ *
+ * Trigger interface to be stopped as if AP was stopped, IBSS/mesh left, STA
+ * disconnected.
+ *
+ * Note: This doesn't need any locks and is asynchronous.
+ */
+void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev,
+			 gfp_t gfp);
+
+/**
+ * cfg80211_shutdown_all_interfaces - shut down all interfaces for a wiphy
+ * @wiphy: the wiphy to shut down
+ *
+ * This function shuts down all interfaces belonging to this wiphy by
+ * calling dev_close() (and treating non-netdev interfaces as needed).
+ * It shouldn't really be used unless there are some fatal device errors
+ * that really can't be recovered in any other way.
+ *
+ * Callers must hold the RTNL and be able to deal with callbacks into
+ * the driver while the function is running.
+ */
+void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy);
+
 /* Logging, debugging and troubleshooting/diagnostic helpers. */
 
 /* wiphy_printk helpers, similar to dev_printk */
diff --git a/include/net/checksum.h b/include/net/checksum.h
index a28f4e0f625..87cb1903640 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -57,12 +57,14 @@ static __inline__ __wsum csum_and_copy_to_user
 }
 #endif
 
+#ifndef HAVE_ARCH_CSUM_ADD
 static inline __wsum csum_add(__wsum csum, __wsum addend)
 {
 	u32 res = (__force u32)csum;
 	res += (__force u32)addend;
 	return (__force __wsum)(res + (res < (__force u32)addend));
 }
+#endif
 
 static inline __wsum csum_sub(__wsum csum, __wsum addend)
 {
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 7828ebf99ee..6efce384451 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -181,6 +181,11 @@ struct dsa_switch_driver {
 void register_switch_driver(struct dsa_switch_driver *type);
 void unregister_switch_driver(struct dsa_switch_driver *type);
 
+static inline void *ds_to_priv(struct dsa_switch *ds)
+{
+	return (void *)(ds + 1);
+}
+
 /*
  * The original DSA tag format and some other tag formats have no
  * ethertype, which means that we need to add a little hack to the
diff --git a/include/net/gre.h b/include/net/gre.h
index 70046a0b0b8..b5318201874 100644
--- a/include/net/gre.h
+++ b/include/net/gre.h
@@ -37,9 +37,10 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 		      int hdr_len);
 
 static inline struct sk_buff *gre_handle_offloads(struct sk_buff *skb,
-						  bool gre_csum)
+						  bool csum)
 {
-	return iptunnel_handle_offloads(skb, gre_csum, SKB_GSO_GRE);
+	return iptunnel_handle_offloads(skb, csum,
+					csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE);
 }
 
 
diff --git a/include/net/ieee802154.h b/include/net/ieee802154.h
index c7ae0ac528d..0aa7122e8f1 100644
--- a/include/net/ieee802154.h
+++ b/include/net/ieee802154.h
@@ -79,6 +79,15 @@
 #define IEEE802154_SCF_KEY_SHORT_INDEX		2
 #define IEEE802154_SCF_KEY_HW_INDEX		3
 
+#define IEEE802154_SCF_SECLEVEL_NONE		0
+#define IEEE802154_SCF_SECLEVEL_MIC32		1
+#define IEEE802154_SCF_SECLEVEL_MIC64		2
+#define IEEE802154_SCF_SECLEVEL_MIC128		3
+#define IEEE802154_SCF_SECLEVEL_ENC		4
+#define IEEE802154_SCF_SECLEVEL_ENC_MIC32	5
+#define IEEE802154_SCF_SECLEVEL_ENC_MIC64	6
+#define IEEE802154_SCF_SECLEVEL_ENC_MIC128	7
+
 /* MAC footer size */
 #define IEEE802154_MFR_SIZE	2 /* 2 octets */
 
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index 5a719ca892f..3b53c8e405e 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -27,6 +27,7 @@
 #ifndef IEEE802154_NETDEVICE_H
 #define IEEE802154_NETDEVICE_H
 
+#include <net/ieee802154.h>
 #include <net/af_ieee802154.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
@@ -114,6 +115,34 @@ int ieee802154_hdr_pull(struct sk_buff *skb, struct ieee802154_hdr *hdr);
 int ieee802154_hdr_peek_addrs(const struct sk_buff *skb,
 			      struct ieee802154_hdr *hdr);
 
+/* parses the full 802.15.4 header a given skb and stores them into hdr,
+ * performing pan id decompression and length checks to be suitable for use in
+ * header_ops.parse
+ */
+int ieee802154_hdr_peek(const struct sk_buff *skb, struct ieee802154_hdr *hdr);
+
+int ieee802154_max_payload(const struct ieee802154_hdr *hdr);
+
+static inline int
+ieee802154_sechdr_authtag_len(const struct ieee802154_sechdr *sec)
+{
+	switch (sec->level) {
+	case IEEE802154_SCF_SECLEVEL_MIC32:
+	case IEEE802154_SCF_SECLEVEL_ENC_MIC32:
+		return 4;
+	case IEEE802154_SCF_SECLEVEL_MIC64:
+	case IEEE802154_SCF_SECLEVEL_ENC_MIC64:
+		return 8;
+	case IEEE802154_SCF_SECLEVEL_MIC128:
+	case IEEE802154_SCF_SECLEVEL_ENC_MIC128:
+		return 16;
+	case IEEE802154_SCF_SECLEVEL_NONE:
+	case IEEE802154_SCF_SECLEVEL_ENC:
+	default:
+		return 0;
+	}
+}
+
 static inline int ieee802154_hdr_length(struct sk_buff *skb)
 {
 	struct ieee802154_hdr hdr;
@@ -193,8 +222,12 @@ static inline void ieee802154_addr_to_sa(struct ieee802154_addr_sa *sa,
  */
 struct ieee802154_mac_cb {
 	u8 lqi;
-	u8 flags;
-	u8 seq;
+	u8 type;
+	bool ackreq;
+	bool secen;
+	bool secen_override;
+	u8 seclevel;
+	bool seclevel_override;
 	struct ieee802154_addr source;
 	struct ieee802154_addr dest;
 };
@@ -204,25 +237,96 @@ static inline struct ieee802154_mac_cb *mac_cb(struct sk_buff *skb)
 	return (struct ieee802154_mac_cb *)skb->cb;
 }
 
-#define MAC_CB_FLAG_TYPEMASK		((1 << 3) - 1)
-
-#define MAC_CB_FLAG_ACKREQ		(1 << 3)
-#define MAC_CB_FLAG_SECEN		(1 << 4)
-
-static inline bool mac_cb_is_ackreq(struct sk_buff *skb)
+static inline struct ieee802154_mac_cb *mac_cb_init(struct sk_buff *skb)
 {
-	return mac_cb(skb)->flags & MAC_CB_FLAG_ACKREQ;
-}
+	BUILD_BUG_ON(sizeof(struct ieee802154_mac_cb) > sizeof(skb->cb));
 
-static inline bool mac_cb_is_secen(struct sk_buff *skb)
-{
-	return mac_cb(skb)->flags & MAC_CB_FLAG_SECEN;
+	memset(skb->cb, 0, sizeof(struct ieee802154_mac_cb));
+	return mac_cb(skb);
 }
 
-static inline int mac_cb_type(struct sk_buff *skb)
-{
-	return mac_cb(skb)->flags & MAC_CB_FLAG_TYPEMASK;
-}
+#define IEEE802154_LLSEC_KEY_SIZE 16
+
+struct ieee802154_llsec_key_id {
+	u8 mode;
+	u8 id;
+	union {
+		struct ieee802154_addr device_addr;
+		__le32 short_source;
+		__le64 extended_source;
+	};
+};
+
+struct ieee802154_llsec_key {
+	u8 frame_types;
+	u32 cmd_frame_ids;
+	u8 key[IEEE802154_LLSEC_KEY_SIZE];
+};
+
+struct ieee802154_llsec_key_entry {
+	struct list_head list;
+
+	struct ieee802154_llsec_key_id id;
+	struct ieee802154_llsec_key *key;
+};
+
+struct ieee802154_llsec_device_key {
+	struct list_head list;
+
+	struct ieee802154_llsec_key_id key_id;
+	u32 frame_counter;
+};
+
+enum {
+	IEEE802154_LLSEC_DEVKEY_IGNORE,
+	IEEE802154_LLSEC_DEVKEY_RESTRICT,
+	IEEE802154_LLSEC_DEVKEY_RECORD,
+
+	__IEEE802154_LLSEC_DEVKEY_MAX,
+};
+
+struct ieee802154_llsec_device {
+	struct list_head list;
+
+	__le16 pan_id;
+	__le16 short_addr;
+	__le64 hwaddr;
+	u32 frame_counter;
+	bool seclevel_exempt;
+
+	u8 key_mode;
+	struct list_head keys;
+};
+
+struct ieee802154_llsec_seclevel {
+	struct list_head list;
+
+	u8 frame_type;
+	u8 cmd_frame_id;
+	bool device_override;
+	u32 sec_levels;
+};
+
+struct ieee802154_llsec_params {
+	bool enabled;
+
+	__be32 frame_counter;
+	u8 out_level;
+	struct ieee802154_llsec_key_id out_key;
+
+	__le64 default_key_source;
+
+	__le16 pan_id;
+	__le64 hwaddr;
+	__le64 coord_hwaddr;
+	__le16 coord_shortaddr;
+};
+
+struct ieee802154_llsec_table {
+	struct list_head keys;
+	struct list_head devices;
+	struct list_head security_levels;
+};
 
 #define IEEE802154_MAC_SCAN_ED		0
 #define IEEE802154_MAC_SCAN_ACTIVE	1
@@ -242,6 +346,53 @@ struct ieee802154_mac_params {
 };
 
 struct wpan_phy;
+
+enum {
+	IEEE802154_LLSEC_PARAM_ENABLED = 1 << 0,
+	IEEE802154_LLSEC_PARAM_FRAME_COUNTER = 1 << 1,
+	IEEE802154_LLSEC_PARAM_OUT_LEVEL = 1 << 2,
+	IEEE802154_LLSEC_PARAM_OUT_KEY = 1 << 3,
+	IEEE802154_LLSEC_PARAM_KEY_SOURCE = 1 << 4,
+	IEEE802154_LLSEC_PARAM_PAN_ID = 1 << 5,
+	IEEE802154_LLSEC_PARAM_HWADDR = 1 << 6,
+	IEEE802154_LLSEC_PARAM_COORD_HWADDR = 1 << 7,
+	IEEE802154_LLSEC_PARAM_COORD_SHORTADDR = 1 << 8,
+};
+
+struct ieee802154_llsec_ops {
+	int (*get_params)(struct net_device *dev,
+			  struct ieee802154_llsec_params *params);
+	int (*set_params)(struct net_device *dev,
+			  const struct ieee802154_llsec_params *params,
+			  int changed);
+
+	int (*add_key)(struct net_device *dev,
+		       const struct ieee802154_llsec_key_id *id,
+		       const struct ieee802154_llsec_key *key);
+	int (*del_key)(struct net_device *dev,
+		       const struct ieee802154_llsec_key_id *id);
+
+	int (*add_dev)(struct net_device *dev,
+		       const struct ieee802154_llsec_device *llsec_dev);
+	int (*del_dev)(struct net_device *dev, __le64 dev_addr);
+
+	int (*add_devkey)(struct net_device *dev,
+			  __le64 device_addr,
+			  const struct ieee802154_llsec_device_key *key);
+	int (*del_devkey)(struct net_device *dev,
+			  __le64 device_addr,
+			  const struct ieee802154_llsec_device_key *key);
+
+	int (*add_seclevel)(struct net_device *dev,
+			    const struct ieee802154_llsec_seclevel *sl);
+	int (*del_seclevel)(struct net_device *dev,
+			    const struct ieee802154_llsec_seclevel *sl);
+
+	void (*lock_table)(struct net_device *dev);
+	void (*get_table)(struct net_device *dev,
+			  struct ieee802154_llsec_table **t);
+	void (*unlock_table)(struct net_device *dev);
+};
 /*
  * This should be located at net_device->ml_priv
  *
@@ -272,6 +423,8 @@ struct ieee802154_mlme_ops {
 	void (*get_mac_params)(struct net_device *dev,
 			       struct ieee802154_mac_params *params);
 
+	struct ieee802154_llsec_ops *llsec;
+
 	/* The fields below are required. */
 
 	struct wpan_phy *(*get_phy)(const struct net_device *dev);
diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h
index 3bd22795c3e..84b20835b73 100644
--- a/include/net/inet_ecn.h
+++ b/include/net/inet_ecn.h
@@ -150,7 +150,7 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb)
 }
 
 /*
- * RFC 6080 4.2
+ * RFC 6040 4.2
  *  To decapsulate the inner header at the tunnel egress, a compliant
  *  tunnel egress MUST set the outgoing ECN field to the codepoint at the
  *  intersection of the appropriate arriving inner header (row) and outer
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 1bdb47715de..dd1950a7e27 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -292,12 +292,12 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
 	const __addrpair __name = (__force __addrpair) ( \
 				   (((__force __u64)(__be32)(__saddr)) << 32) | \
-				   ((__force __u64)(__be32)(__daddr)));
+				   ((__force __u64)(__be32)(__daddr)))
 #else /* __LITTLE_ENDIAN */
 #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
 	const __addrpair __name = (__force __addrpair) ( \
 				   (((__force __u64)(__be32)(__daddr)) << 32) | \
-				   ((__force __u64)(__be32)(__saddr)));
+				   ((__force __u64)(__be32)(__saddr)))
 #endif /* __BIG_ENDIAN */
 #define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif)	\
 	(((__sk)->sk_portpair == (__ports))			&&	\
@@ -306,7 +306,9 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 	   ((__sk)->sk_bound_dev_if == (__dif))) 		&& 	\
 	 net_eq(sock_net(__sk), (__net)))
 #else /* 32-bit arch */
-#define INET_ADDR_COOKIE(__name, __saddr, __daddr)
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
+	const int __name __deprecated __attribute__((unused))
+
 #define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \
 	(((__sk)->sk_portpair == (__ports))		&&		\
 	 ((__sk)->sk_daddr	== (__saddr))		&&		\
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 1833c3f389e..b1edf17bec0 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -90,6 +90,7 @@ struct inet_request_sock {
 	kmemcheck_bitfield_end(flags);
 	struct ip_options_rcu	*opt;
 	struct sk_buff		*pktopts;
+	u32                     ir_mark;
 };
 
 static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
@@ -97,6 +98,15 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
 	return (struct inet_request_sock *)sk;
 }
 
+static inline u32 inet_request_mark(struct sock *sk, struct sk_buff *skb)
+{
+	if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept) {
+		return skb->mark;
+	} else {
+		return sk->sk_mark;
+	}
+}
+
 struct inet_cork {
 	unsigned int		flags;
 	__be32			addr;
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 058271bde27..01d590ee5e7 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -41,14 +41,13 @@ struct inet_peer {
 		struct rcu_head     gc_rcu;
 	};
 	/*
-	 * Once inet_peer is queued for deletion (refcnt == -1), following fields
-	 * are not available: rid, ip_id_count
+	 * Once inet_peer is queued for deletion (refcnt == -1), following field
+	 * is not available: rid
 	 * We can share memory with rcu_head to help keep inet_peer small.
 	 */
 	union {
 		struct {
 			atomic_t			rid;		/* Frag reception counter */
-			atomic_t			ip_id_count;	/* IP ID for the next packet */
 		};
 		struct rcu_head         rcu;
 		struct inet_peer	*gc_next;
@@ -165,21 +164,11 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout);
 void inetpeer_invalidate_tree(struct inet_peer_base *);
 
 /*
- * temporary check to make sure we dont access rid, ip_id_count, tcp_ts,
+ * temporary check to make sure we dont access rid, tcp_ts,
  * tcp_ts_stamp if no refcount is taken on inet_peer
  */
 static inline void inet_peer_refcheck(const struct inet_peer *p)
 {
 	WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0);
 }
-
-
-/* can be called with or without local BH being disabled */
-static inline int inet_getid(struct inet_peer *p, int more)
-{
-	more++;
-	inet_peer_refcheck(p);
-	return atomic_add_return(more, &p->ip_id_count) - more;
-}
-
 #endif /* _NET_INETPEER_H */
diff --git a/include/net/ip.h b/include/net/ip.h
index 3ec2b0fb9d8..7596eb22e1c 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -196,35 +196,31 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 #define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd)
 #define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd)
 
-unsigned long snmp_fold_field(void __percpu *mib[], int offt);
+unsigned long snmp_fold_field(void __percpu *mib, int offt);
 #if BITS_PER_LONG==32
-u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t sync_off);
+u64 snmp_fold_field64(void __percpu *mib, int offt, size_t sync_off);
 #else
-static inline u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_off)
+static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_off)
 {
 	return snmp_fold_field(mib, offt);
 }
 #endif
-int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align);
-
-static inline void snmp_mib_free(void __percpu *ptr[SNMP_ARRAY_SZ])
-{
-	int i;
-
-	BUG_ON(ptr == NULL);
-	for (i = 0; i < SNMP_ARRAY_SZ; i++) {
-		free_percpu(ptr[i]);
-		ptr[i] = NULL;
-	}
-}
 
 void inet_get_local_port_range(struct net *net, int *low, int *high);
 
-extern unsigned long *sysctl_local_reserved_ports;
-static inline int inet_is_reserved_local_port(int port)
+#ifdef CONFIG_SYSCTL
+static inline int inet_is_local_reserved_port(struct net *net, int port)
 {
-	return test_bit(port, sysctl_local_reserved_ports);
+	if (!net->ipv4.sysctl_local_reserved_ports)
+		return 0;
+	return test_bit(port, net->ipv4.sysctl_local_reserved_ports);
 }
+#else
+static inline int inet_is_local_reserved_port(struct net *net, int port)
+{
+	return 0;
+}
+#endif
 
 extern int sysctl_ip_nonlocal_bind;
 
@@ -243,6 +239,9 @@ void ipfrag_init(void);
 
 void ip_static_sysctl_init(void);
 
+#define IP4_REPLY_MARK(net, mark) \
+	((net)->ipv4.sysctl_fwmark_reflect ? (mark) : 0)
+
 static inline bool ip_is_fragment(const struct iphdr *iph)
 {
 	return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0;
@@ -281,7 +280,7 @@ static inline bool ip_sk_use_pmtu(const struct sock *sk)
 	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
 }
 
-static inline bool ip_sk_local_df(const struct sock *sk)
+static inline bool ip_sk_ignore_df(const struct sock *sk)
 {
 	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO ||
 	       inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT;
@@ -310,36 +309,39 @@ static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)
 	}
 }
 
-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);
+u32 ip_idents_reserve(u32 hash, int segs);
+void __ip_select_ident(struct iphdr *iph, int segs);
 
-static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk)
+static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
-	if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) {
+	if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) {
 		/* This is only to work around buggy Windows95/2000
 		 * VJ compression implementations.  If the ID field
 		 * does not change, they drop every other packet in
 		 * a TCP stream using header compression.
 		 */
-		iph->id = (sk && inet_sk(sk)->inet_daddr) ?
-					htons(inet_sk(sk)->inet_id++) : 0;
-	} else
-		__ip_select_ident(iph, dst, 0);
+		if (sk && inet_sk(sk)->inet_daddr) {
+			iph->id = htons(inet_sk(sk)->inet_id);
+			inet_sk(sk)->inet_id += segs;
+		} else {
+			iph->id = 0;
+		}
+	} else {
+		__ip_select_ident(iph, segs);
+	}
 }
 
-static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more)
+static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk)
 {
-	struct iphdr *iph = ip_hdr(skb);
+	ip_select_ident_segs(skb, sk, 1);
+}
 
-	if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) {
-		if (sk && inet_sk(sk)->inet_daddr) {
-			iph->id = htons(inet_sk(sk)->inet_id);
-			inet_sk(sk)->inet_id += 1 + more;
-		} else
-			iph->id = 0;
-	} else
-		__ip_select_ident(iph, dst, more);
+static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto)
+{
+	return csum_tcpudp_nofold(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
+				  skb->len, proto, 0);
 }
 
 /*
diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h
index 9e3c540c1b1..55236cb7117 100644
--- a/include/net/ip6_checksum.h
+++ b/include/net/ip6_checksum.h
@@ -41,6 +41,13 @@ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 			__wsum csum);
 #endif
 
+static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto)
+{
+	return ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+					    &ipv6_hdr(skb)->daddr,
+					    skb->len, proto, 0));
+}
+
 static __inline__ __sum16 tcp_v6_check(int len,
 				   const struct in6_addr *saddr,
 				   const struct in6_addr *daddr,
@@ -75,5 +82,17 @@ static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb)
 }
 #endif
 
+static inline __sum16 udp_v6_check(int len,
+				   const struct in6_addr *saddr,
+				   const struct in6_addr *daddr,
+				   __wsum base)
+{
+	return csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, base);
+}
+
+void udp6_set_csum(bool nocheck, struct sk_buff *skb,
+		   const struct in6_addr *saddr,
+		   const struct in6_addr *daddr, int len);
+
 int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto);
 #endif
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 216cecce65e..1d09b46c1e4 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -186,7 +186,7 @@ static inline bool ip6_sk_accept_pmtu(const struct sock *sk)
 	       inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_OMIT;
 }
 
-static inline bool ip6_sk_local_df(const struct sock *sk)
+static inline bool ip6_sk_ignore_df(const struct sock *sk)
 {
 	return inet6_sk(sk)->pmtudisc < IPV6_PMTUDISC_DO ||
 	       inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d640925bc45..574337fe72d 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -113,6 +113,9 @@ struct frag_hdr {
 #define	IP6_MF		0x0001
 #define	IP6_OFFSET	0xFFF8
 
+#define IP6_REPLY_MARK(net, mark) \
+	((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0)
+
 #include <net/sock.h>
 
 /* sysctls */
@@ -583,6 +586,11 @@ static inline bool ipv6_addr_orchid(const struct in6_addr *a)
 	return (a->s6_addr32[0] & htonl(0xfffffff0)) == htonl(0x20010010);
 }
 
+static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr)
+{
+	return (addr->s6_addr32[0] & htonl(0xFF000000)) == htonl(0xFF000000);
+}
+
 static inline void ipv6_addr_set_v4mapped(const __be32 addr,
 					  struct in6_addr *v4mapped)
 {
@@ -660,10 +668,22 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
-
 int ip6_dst_hoplimit(struct dst_entry *dst);
 
+static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6,
+				      struct dst_entry *dst)
+{
+	int hlimit;
+
+	if (ipv6_addr_is_multicast(&fl6->daddr))
+		hlimit = np->mcast_hops;
+	else
+		hlimit = np->hop_limit;
+	if (hlimit < 0)
+		hlimit = ip6_dst_hoplimit(dst);
+	return hlimit;
+}
+
 /*
  *	Header manipulation
  */
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 8248e3909fd..421b6ecb4b2 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -189,6 +189,43 @@ struct ieee80211_chanctx_conf {
 };
 
 /**
+ * enum ieee80211_chanctx_switch_mode - channel context switch mode
+ * @CHANCTX_SWMODE_REASSIGN_VIF: Both old and new contexts already
+ *	exist (and will continue to exist), but the virtual interface
+ *	needs to be switched from one to the other.
+ * @CHANCTX_SWMODE_SWAP_CONTEXTS: The old context exists but will stop
+ *      to exist with this call, the new context doesn't exist but
+ *      will be active after this call, the virtual interface switches
+ *      from the old to the new (note that the driver may of course
+ *      implement this as an on-the-fly chandef switch of the existing
+ *      hardware context, but the mac80211 pointer for the old context
+ *      will cease to exist and only the new one will later be used
+ *      for changes/removal.)
+ */
+enum ieee80211_chanctx_switch_mode {
+	CHANCTX_SWMODE_REASSIGN_VIF,
+	CHANCTX_SWMODE_SWAP_CONTEXTS,
+};
+
+/**
+ * struct ieee80211_vif_chanctx_switch - vif chanctx switch information
+ *
+ * This is structure is used to pass information about a vif that
+ * needs to switch from one chanctx to another.  The
+ * &ieee80211_chanctx_switch_mode defines how the switch should be
+ * done.
+ *
+ * @vif: the vif that should be switched from old_ctx to new_ctx
+ * @old_ctx: the old context to which the vif was assigned
+ * @new_ctx: the new context to which the vif must be assigned
+ */
+struct ieee80211_vif_chanctx_switch {
+	struct ieee80211_vif *vif;
+	struct ieee80211_chanctx_conf *old_ctx;
+	struct ieee80211_chanctx_conf *new_ctx;
+};
+
+/**
  * enum ieee80211_bss_change - BSS change notification flags
  *
  * These flags are used with the bss_info_changed() callback
@@ -1113,7 +1150,9 @@ enum ieee80211_vif_flags {
  * @addr: address of this interface
  * @p2p: indicates whether this AP or STA interface is a p2p
  *	interface, i.e. a GO or p2p-sta respectively
- * @csa_active: marks whether a channel switch is going on
+ * @csa_active: marks whether a channel switch is going on. Internally it is
+ *	write-protected by sdata_lock and local->mtx so holding either is fine
+ *	for read access.
  * @driver_flags: flags/capabilities the driver has for this interface,
  *	these need to be set (or cleared) when the interface is added
  *	or, if supported by the driver, the interface type is changed
@@ -1202,14 +1241,18 @@ struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev);
  *	fall back to software crypto. Note that this flag deals only with
  *	RX, if your crypto engine can't deal with TX you can also set the
  *	%IEEE80211_KEY_FLAG_SW_MGMT_TX flag to encrypt such frames in SW.
+ * @IEEE80211_KEY_FLAG_GENERATE_IV_MGMT: This flag should be set by the
+ *	driver for a CCMP key to indicate that is requires IV generation
+ *	only for managment frames (MFP).
  */
 enum ieee80211_key_flags {
-	IEEE80211_KEY_FLAG_GENERATE_IV	= 1<<1,
-	IEEE80211_KEY_FLAG_GENERATE_MMIC= 1<<2,
-	IEEE80211_KEY_FLAG_PAIRWISE	= 1<<3,
-	IEEE80211_KEY_FLAG_SW_MGMT_TX	= 1<<4,
-	IEEE80211_KEY_FLAG_PUT_IV_SPACE = 1<<5,
-	IEEE80211_KEY_FLAG_RX_MGMT	= 1<<6,
+	IEEE80211_KEY_FLAG_GENERATE_IV_MGMT	= BIT(0),
+	IEEE80211_KEY_FLAG_GENERATE_IV		= BIT(1),
+	IEEE80211_KEY_FLAG_GENERATE_MMIC	= BIT(2),
+	IEEE80211_KEY_FLAG_PAIRWISE		= BIT(3),
+	IEEE80211_KEY_FLAG_SW_MGMT_TX		= BIT(4),
+	IEEE80211_KEY_FLAG_PUT_IV_SPACE		= BIT(5),
+	IEEE80211_KEY_FLAG_RX_MGMT		= BIT(6),
 };
 
 /**
@@ -1370,6 +1413,7 @@ struct ieee80211_sta_rates {
  *	the station moves to associated state.
  * @smps_mode: current SMPS mode (off, static or dynamic)
  * @rates: rate control selection table
+ * @tdls: indicates whether the STA is a TDLS peer
  */
 struct ieee80211_sta {
 	u32 supp_rates[IEEE80211_NUM_BANDS];
@@ -1384,6 +1428,7 @@ struct ieee80211_sta {
 	enum ieee80211_sta_rx_bandwidth bandwidth;
 	enum ieee80211_smps_mode smps_mode;
 	struct ieee80211_sta_rates __rcu *rates;
+	bool tdls;
 
 	/* must be last */
 	u8 drv_priv[0] __aligned(sizeof(void *));
@@ -1555,6 +1600,12 @@ struct ieee80211_tx_control {
  *	for a single active channel while using channel contexts. When support
  *	is not enabled the default action is to disconnect when getting the
  *	CSA frame.
+ *
+ * @IEEE80211_HW_CHANGE_RUNNING_CHANCTX: The hardware can change a
+ *	channel context on-the-fly.  This is needed for channel switch
+ *	on single-channel hardware.  It can also be used as an
+ *	optimization in certain channel switch cases with
+ *	multi-channel.
  */
 enum ieee80211_hw_flags {
 	IEEE80211_HW_HAS_RATE_CONTROL			= 1<<0,
@@ -1586,6 +1637,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_TIMING_BEACON_ONLY			= 1<<26,
 	IEEE80211_HW_SUPPORTS_HT_CCK_RATES		= 1<<27,
 	IEEE80211_HW_CHANCTX_STA_CSA			= 1<<28,
+	IEEE80211_HW_CHANGE_RUNNING_CHANCTX		= 1<<29,
 };
 
 /**
@@ -2609,6 +2661,7 @@ enum ieee80211_roc_type {
  *	of queues to flush, which is useful if different virtual interfaces
  *	use different hardware queues; it may also indicate all queues.
  *	If the parameter @drop is set to %true, pending frames may be dropped.
+ *	Note that vif can be NULL.
  *	The callback can sleep.
  *
  * @channel_switch: Drivers that need (or want) to offload the channel
@@ -2720,6 +2773,11 @@ enum ieee80211_roc_type {
  *	to vif. Possible use is for hw queue remapping.
  * @unassign_vif_chanctx: Notifies device driver about channel context being
  *	unbound from vif.
+ * @switch_vif_chanctx: switch a number of vifs from one chanctx to
+ *	another, as specified in the list of
+ *	@ieee80211_vif_chanctx_switch passed to the driver, according
+ *	to the mode defined in &ieee80211_chanctx_switch_mode.
+ *
  * @start_ap: Start operation on the AP interface, this is called after all the
  *	information in bss_conf is set and beacon can be retrieved. A channel
  *	context is bound before this is called. Note that if the driver uses
@@ -2753,6 +2811,10 @@ enum ieee80211_roc_type {
  *	information in bss_conf is set up and the beacon can be retrieved. A
  *	channel context is bound before this is called.
  * @leave_ibss: Leave the IBSS again.
+ *
+ * @get_expected_throughput: extract the expected throughput towards the
+ *	specified station. The returned value is expressed in Kbps. It returns 0
+ *	if the RC algorithm does not have proper data to provide.
  */
 struct ieee80211_ops {
 	void (*tx)(struct ieee80211_hw *hw,
@@ -2871,7 +2933,8 @@ struct ieee80211_ops {
 			     struct netlink_callback *cb,
 			     void *data, int len);
 #endif
-	void (*flush)(struct ieee80211_hw *hw, u32 queues, bool drop);
+	void (*flush)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      u32 queues, bool drop);
 	void (*channel_switch)(struct ieee80211_hw *hw,
 			       struct ieee80211_channel_switch *ch_switch);
 	int (*set_antenna)(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant);
@@ -2931,6 +2994,10 @@ struct ieee80211_ops {
 	void (*unassign_vif_chanctx)(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif,
 				     struct ieee80211_chanctx_conf *ctx);
+	int (*switch_vif_chanctx)(struct ieee80211_hw *hw,
+				  struct ieee80211_vif_chanctx_switch *vifs,
+				  int n_vifs,
+				  enum ieee80211_chanctx_switch_mode mode);
 
 	void (*restart_complete)(struct ieee80211_hw *hw);
 
@@ -2945,6 +3012,7 @@ struct ieee80211_ops {
 
 	int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
 	void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
+	u32 (*get_expected_throughput)(struct ieee80211_sta *sta);
 };
 
 /**
@@ -3394,6 +3462,47 @@ void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw,
  */
 void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets);
 
+#define IEEE80211_MAX_CSA_COUNTERS_NUM 2
+
+/**
+ * struct ieee80211_mutable_offsets - mutable beacon offsets
+ * @tim_offset: position of TIM element
+ * @tim_length: size of TIM element
+ * @csa_counter_offs: array of IEEE80211_MAX_CSA_COUNTERS_NUM offsets
+ *	to CSA counters.  This array can contain zero values which
+ *	should be ignored.
+ */
+struct ieee80211_mutable_offsets {
+	u16 tim_offset;
+	u16 tim_length;
+
+	u16 csa_counter_offs[IEEE80211_MAX_CSA_COUNTERS_NUM];
+};
+
+/**
+ * ieee80211_beacon_get_template - beacon template generation function
+ * @hw: pointer obtained from ieee80211_alloc_hw().
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ * @offs: &struct ieee80211_mutable_offsets pointer to struct that will
+ *	receive the offsets that may be updated by the driver.
+ *
+ * If the driver implements beaconing modes, it must use this function to
+ * obtain the beacon template.
+ *
+ * This function should be used if the beacon frames are generated by the
+ * device, and then the driver must use the returned beacon as the template
+ * The driver or the device are responsible to update the DTIM and, when
+ * applicable, the CSA count.
+ *
+ * The driver is responsible for freeing the returned skb.
+ *
+ * Return: The beacon template. %NULL on error.
+ */
+struct sk_buff *
+ieee80211_beacon_get_template(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_mutable_offsets *offs);
+
 /**
  * ieee80211_beacon_get_tim - beacon generation function
  * @hw: pointer obtained from ieee80211_alloc_hw().
@@ -3405,16 +3514,12 @@ void ieee80211_report_low_ack(struct ieee80211_sta *sta, u32 num_packets);
  *	Set to 0 if invalid (in non-AP modes).
  *
  * If the driver implements beaconing modes, it must use this function to
- * obtain the beacon frame/template.
+ * obtain the beacon frame.
  *
  * If the beacon frames are generated by the host system (i.e., not in
  * hardware/firmware), the driver uses this function to get each beacon
- * frame from mac80211 -- it is responsible for calling this function
- * before the beacon is needed (e.g. based on hardware interrupt).
- *
- * If the beacon frames are generated by the device, then the driver
- * must use the returned beacon as the template and change the TIM IE
- * according to the current DTIM parameters/TIM bitmap.
+ * frame from mac80211 -- it is responsible for calling this function exactly
+ * once before the beacon is needed (e.g. based on hardware interrupt).
  *
  * The driver is responsible for freeing the returned skb.
  *
@@ -3440,6 +3545,20 @@ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw,
 }
 
 /**
+ * ieee80211_csa_update_counter - request mac80211 to decrement the csa counter
+ * @vif: &struct ieee80211_vif pointer from the add_interface callback.
+ *
+ * The csa counter should be updated after each beacon transmission.
+ * This function is called implicitly when
+ * ieee80211_beacon_get/ieee80211_beacon_get_tim are called, however if the
+ * beacon frames are generated by the device, the driver should call this
+ * function after each beacon transmission to sync mac80211's csa counters.
+ *
+ * Return: new csa counter value
+ */
+u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif);
+
+/**
  * ieee80211_csa_finish - notify mac80211 about channel switch
  * @vif: &struct ieee80211_vif pointer from the add_interface callback.
  *
@@ -4467,6 +4586,8 @@ struct rate_control_ops {
 	void (*add_sta_debugfs)(void *priv, void *priv_sta,
 				struct dentry *dir);
 	void (*remove_sta_debugfs)(void *priv, void *priv_sta);
+
+	u32 (*get_expected_throughput)(void *priv_sta);
 };
 
 static inline int rate_supported(struct ieee80211_sta *sta,
@@ -4576,7 +4697,9 @@ conf_is_ht40(struct ieee80211_conf *conf)
 static inline bool
 conf_is_ht(struct ieee80211_conf *conf)
 {
-	return conf->chandef.width != NL80211_CHAN_WIDTH_20_NOHT;
+	return (conf->chandef.width != NL80211_CHAN_WIDTH_5) &&
+		(conf->chandef.width != NL80211_CHAN_WIDTH_10) &&
+		(conf->chandef.width != NL80211_CHAN_WIDTH_20_NOHT);
 }
 
 static inline enum nl80211_iftype
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 7277caf3743..47f425464f8 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -203,7 +203,6 @@ struct neigh_table {
 	void			(*proxy_redo)(struct sk_buff *skb);
 	char			*id;
 	struct neigh_parms	parms;
-	/* HACK. gc_* should follow parms without a gap! */
 	int			gc_interval;
 	int			gc_thresh1;
 	int			gc_thresh2;
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 5f9eb260990..361d2607719 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -373,6 +373,14 @@ static inline void rt_genid_bump_ipv6(struct net *net)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
+static inline struct netns_ieee802154_lowpan *
+net_ieee802154_lowpan(struct net *net)
+{
+	return &net->ieee802154_lowpan;
+}
+#endif
+
 /* For callers who don't really care about whether it's IPv4 or IPv6 */
 static inline void rt_genid_bump_all(struct net *net)
 {
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index 07eaaf60409..a71dd333ac6 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -48,6 +48,8 @@ unsigned int nf_nat_setup_info(struct nf_conn *ct,
 extern unsigned int nf_nat_alloc_null_binding(struct nf_conn *ct,
 					      unsigned int hooknum);
 
+struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct);
+
 /* Is this tuple already taken? (not by us)*/
 int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple,
 		      const struct nf_conn *ignored_conntrack);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index e6bc14d8fa9..c4d86198d3d 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -6,6 +6,7 @@
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/nf_tables.h>
+#include <linux/u64_stats_sync.h>
 #include <net/netlink.h>
 
 #define NFT_JUMP_STACK_SIZE	16
@@ -72,21 +73,23 @@ static inline void nft_data_debug(const struct nft_data *data)
  *	struct nft_ctx - nf_tables rule/set context
  *
  *	@net: net namespace
- * 	@skb: netlink skb
- * 	@nlh: netlink message header
  * 	@afi: address family info
  * 	@table: the table the chain is contained in
  * 	@chain: the chain the rule is contained in
  *	@nla: netlink attributes
+ *	@portid: netlink portID of the original message
+ *	@seq: netlink sequence number
+ *	@report: notify via unicast netlink message
  */
 struct nft_ctx {
 	struct net			*net;
-	const struct sk_buff		*skb;
-	const struct nlmsghdr		*nlh;
-	const struct nft_af_info	*afi;
-	const struct nft_table		*table;
-	const struct nft_chain		*chain;
+	struct nft_af_info		*afi;
+	struct nft_table		*table;
+	struct nft_chain		*chain;
 	const struct nlattr * const 	*nla;
+	u32				portid;
+	u32				seq;
+	bool				report;
 };
 
 struct nft_data_desc {
@@ -146,6 +149,44 @@ struct nft_set_iter {
 };
 
 /**
+ *	struct nft_set_desc - description of set elements
+ *
+ *	@klen: key length
+ *	@dlen: data length
+ *	@size: number of set elements
+ */
+struct nft_set_desc {
+	unsigned int		klen;
+	unsigned int		dlen;
+	unsigned int		size;
+};
+
+/**
+ *	enum nft_set_class - performance class
+ *
+ *	@NFT_LOOKUP_O_1: constant, O(1)
+ *	@NFT_LOOKUP_O_LOG_N: logarithmic, O(log N)
+ *	@NFT_LOOKUP_O_N: linear, O(N)
+ */
+enum nft_set_class {
+	NFT_SET_CLASS_O_1,
+	NFT_SET_CLASS_O_LOG_N,
+	NFT_SET_CLASS_O_N,
+};
+
+/**
+ *	struct nft_set_estimate - estimation of memory and performance
+ *				  characteristics
+ *
+ *	@size: required memory
+ *	@class: lookup performance class
+ */
+struct nft_set_estimate {
+	unsigned int		size;
+	enum nft_set_class	class;
+};
+
+/**
  *	struct nft_set_ops - nf_tables set operations
  *
  *	@lookup: look up an element within the set
@@ -174,7 +215,11 @@ struct nft_set_ops {
 						struct nft_set_iter *iter);
 
 	unsigned int			(*privsize)(const struct nlattr * const nla[]);
+	bool				(*estimate)(const struct nft_set_desc *desc,
+						    u32 features,
+						    struct nft_set_estimate *est);
 	int				(*init)(const struct nft_set *set,
+						const struct nft_set_desc *desc,
 						const struct nlattr * const nla[]);
 	void				(*destroy)(const struct nft_set *set);
 
@@ -194,6 +239,8 @@ void nft_unregister_set(struct nft_set_ops *ops);
  * 	@name: name of the set
  * 	@ktype: key type (numeric type defined by userspace, not used in the kernel)
  * 	@dtype: data type (verdict or numeric type defined by userspace)
+ * 	@size: maximum set size
+ * 	@nelems: number of elements
  * 	@ops: set ops
  * 	@flags: set flags
  * 	@klen: key length
@@ -206,6 +253,8 @@ struct nft_set {
 	char				name[IFNAMSIZ];
 	u32				ktype;
 	u32				dtype;
+	u32				size;
+	u32				nelems;
 	/* runtime data below here */
 	const struct nft_set_ops	*ops ____cacheline_aligned;
 	u16				flags;
@@ -222,6 +271,8 @@ static inline void *nft_set_priv(const struct nft_set *set)
 
 struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
 				     const struct nlattr *nla);
+struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
+					  const struct nlattr *nla);
 
 /**
  *	struct nft_set_binding - nf_tables set binding
@@ -341,18 +392,75 @@ struct nft_rule {
 };
 
 /**
- *	struct nft_rule_trans - nf_tables rule update in transaction
+ *	struct nft_trans - nf_tables object update in transaction
  *
+ *	@rcu_head: rcu head to defer release of transaction data
  *	@list: used internally
- *	@ctx: rule context
- *	@rule: rule that needs to be updated
+ *	@msg_type: message type
+ *	@ctx: transaction context
+ *	@data: internal information related to the transaction
  */
-struct nft_rule_trans {
+struct nft_trans {
+	struct rcu_head			rcu_head;
 	struct list_head		list;
+	int				msg_type;
 	struct nft_ctx			ctx;
+	char				data[0];
+};
+
+struct nft_trans_rule {
 	struct nft_rule			*rule;
 };
 
+#define nft_trans_rule(trans)	\
+	(((struct nft_trans_rule *)trans->data)->rule)
+
+struct nft_trans_set {
+	struct nft_set	*set;
+	u32		set_id;
+};
+
+#define nft_trans_set(trans)	\
+	(((struct nft_trans_set *)trans->data)->set)
+#define nft_trans_set_id(trans)	\
+	(((struct nft_trans_set *)trans->data)->set_id)
+
+struct nft_trans_chain {
+	bool		update;
+	char		name[NFT_CHAIN_MAXNAMELEN];
+	struct nft_stats __percpu *stats;
+	u8		policy;
+};
+
+#define nft_trans_chain_update(trans)	\
+	(((struct nft_trans_chain *)trans->data)->update)
+#define nft_trans_chain_name(trans)	\
+	(((struct nft_trans_chain *)trans->data)->name)
+#define nft_trans_chain_stats(trans)	\
+	(((struct nft_trans_chain *)trans->data)->stats)
+#define nft_trans_chain_policy(trans)	\
+	(((struct nft_trans_chain *)trans->data)->policy)
+
+struct nft_trans_table {
+	bool		update;
+	bool		enable;
+};
+
+#define nft_trans_table_update(trans)	\
+	(((struct nft_trans_table *)trans->data)->update)
+#define nft_trans_table_enable(trans)	\
+	(((struct nft_trans_table *)trans->data)->enable)
+
+struct nft_trans_elem {
+	struct nft_set		*set;
+	struct nft_set_elem	elem;
+};
+
+#define nft_trans_elem_set(trans)	\
+	(((struct nft_trans_elem *)trans->data)->set)
+#define nft_trans_elem(trans)	\
+	(((struct nft_trans_elem *)trans->data)->elem)
+
 static inline struct nft_expr *nft_expr_first(const struct nft_rule *rule)
 {
 	return (struct nft_expr *)&rule->data[0];
@@ -385,6 +493,7 @@ static inline void *nft_userdata(const struct nft_rule *rule)
 
 enum nft_chain_flags {
 	NFT_BASE_CHAIN			= 0x1,
+	NFT_CHAIN_INACTIVE		= 0x2,
 };
 
 /**
@@ -395,9 +504,9 @@ enum nft_chain_flags {
  *	@net: net namespace that this chain belongs to
  *	@table: table that this chain belongs to
  *	@handle: chain handle
- *	@flags: bitmask of enum nft_chain_flags
  *	@use: number of jump references to this chain
  *	@level: length of longest path to this chain
+ *	@flags: bitmask of enum nft_chain_flags
  *	@name: name of the chain
  */
 struct nft_chain {
@@ -406,9 +515,9 @@ struct nft_chain {
 	struct net			*net;
 	struct nft_table		*table;
 	u64				handle;
-	u8				flags;
-	u16				use;
+	u32				use;
 	u16				level;
+	u8				flags;
 	char				name[NFT_CHAIN_MAXNAMELEN];
 };
 
@@ -420,8 +529,9 @@ enum nft_chain_type {
 };
 
 struct nft_stats {
-	u64 bytes;
-	u64 pkts;
+	u64			bytes;
+	u64			pkts;
+	struct u64_stats_sync	syncp;
 };
 
 #define NFT_HOOK_OPS_MAX		2
diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h
new file mode 100644
index 00000000000..0ee47c3e2e3
--- /dev/null
+++ b/include/net/netfilter/nft_meta.h
@@ -0,0 +1,36 @@
+#ifndef _NFT_META_H_
+#define _NFT_META_H_
+
+struct nft_meta {
+	enum nft_meta_keys	key:8;
+	union {
+		enum nft_registers	dreg:8;
+		enum nft_registers	sreg:8;
+	};
+};
+
+extern const struct nla_policy nft_meta_policy[];
+
+int nft_meta_get_init(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nlattr * const tb[]);
+
+int nft_meta_set_init(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nlattr * const tb[]);
+
+int nft_meta_get_dump(struct sk_buff *skb,
+		      const struct nft_expr *expr);
+
+int nft_meta_set_dump(struct sk_buff *skb,
+		      const struct nft_expr *expr);
+
+void nft_meta_get_eval(const struct nft_expr *expr,
+		       struct nft_data data[NFT_REG_MAX + 1],
+		       const struct nft_pktinfo *pkt);
+
+void nft_meta_set_eval(const struct nft_expr *expr,
+		       struct nft_data data[NFT_REG_MAX + 1],
+		       const struct nft_pktinfo *pkt);
+
+#endif
diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h
index 079030c853d..e2070960bac 100644
--- a/include/net/netns/ieee802154_6lowpan.h
+++ b/include/net/netns/ieee802154_6lowpan.h
@@ -16,7 +16,7 @@ struct netns_sysctl_lowpan {
 struct netns_ieee802154_lowpan {
 	struct netns_sysctl_lowpan sysctl;
 	struct netns_frags	frags;
-	u16			max_dsize;
+	int			max_dsize;
 };
 
 #endif
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index b2704fd0ec8..aec5e12f9f1 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -77,10 +77,17 @@ struct netns_ipv4 {
 	int sysctl_ip_no_pmtu_disc;
 	int sysctl_ip_fwd_use_pmtu;
 
+	int sysctl_fwmark_reflect;
+	int sysctl_tcp_fwmark_accept;
+
 	struct ping_group_range ping_group_range;
 
 	atomic_t dev_addr_genid;
 
+#ifdef CONFIG_SYSCTL
+	unsigned long *sysctl_local_reserved_ports;
+#endif
+
 #ifdef CONFIG_IP_MROUTE
 #ifndef CONFIG_IP_MROUTE_MULTIPLE_TABLES
 	struct mr_table		*mrt;
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 21edaf1f791..19d3446e59d 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -30,6 +30,7 @@ struct netns_sysctl_ipv6 {
 	int flowlabel_consistency;
 	int icmpv6_time;
 	int anycast_src_echo_reply;
+	int fwmark_reflect;
 };
 
 struct netns_ipv6 {
diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 26a394cb91a..eee608b12cc 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -13,8 +13,8 @@ struct netns_nftables {
 	struct nft_af_info	*inet;
 	struct nft_af_info	*arp;
 	struct nft_af_info	*bridge;
+	unsigned int		base_seq;
 	u8			gencursor;
-	u8			genctr;
 };
 
 #endif
diff --git a/include/net/nfc/digital.h b/include/net/nfc/digital.h
index 7655cfe27c3..bdf55c3b7a1 100644
--- a/include/net/nfc/digital.h
+++ b/include/net/nfc/digital.h
@@ -36,6 +36,7 @@ enum {
 	NFC_DIGITAL_RF_TECH_212F,
 	NFC_DIGITAL_RF_TECH_424F,
 	NFC_DIGITAL_RF_TECH_ISO15693,
+	NFC_DIGITAL_RF_TECH_106B,
 
 	NFC_DIGITAL_RF_TECH_LAST,
 };
@@ -62,6 +63,9 @@ enum {
 	NFC_DIGITAL_FRAMING_ISO15693_INVENTORY,
 	NFC_DIGITAL_FRAMING_ISO15693_T5T,
 
+	NFC_DIGITAL_FRAMING_NFCB,
+	NFC_DIGITAL_FRAMING_NFCB_T4T,
+
 	NFC_DIGITAL_FRAMING_LAST,
 };
 
diff --git a/include/net/nfc/hci.h b/include/net/nfc/hci.h
index 03c4650b548..61286db5438 100644
--- a/include/net/nfc/hci.h
+++ b/include/net/nfc/hci.h
@@ -27,6 +27,7 @@ struct nfc_hci_dev;
 struct nfc_hci_ops {
 	int (*open) (struct nfc_hci_dev *hdev);
 	void (*close) (struct nfc_hci_dev *hdev);
+	int (*load_session) (struct nfc_hci_dev *hdev);
 	int (*hci_ready) (struct nfc_hci_dev *hdev);
 	/*
 	 * xmit must always send the complete buffer before
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index 2e8b40c1627..6c583e244de 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -264,4 +264,7 @@ int nfc_add_se(struct nfc_dev *dev, u32 se_idx, u16 type);
 int nfc_remove_se(struct nfc_dev *dev, u32 se_idx);
 struct nfc_se *nfc_find_se(struct nfc_dev *dev, u32 se_idx);
 
+void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb,
+			  u8 payload_type, u8 direction);
+
 #endif /* __NET_NFC_H */
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a2441fb1428..6da46dcf104 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -136,7 +136,7 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts,
 
 int tcf_exts_validate(struct net *net, struct tcf_proto *tp,
 		      struct nlattr **tb, struct nlattr *rate_tlv,
-		      struct tcf_exts *exts);
+		      struct tcf_exts *exts, bool ovr);
 void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts);
 void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
 		     struct tcf_exts *src);
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 891d80d2c4d..ec030cd7661 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -96,7 +96,7 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
 					struct nlattr *tab);
 void qdisc_put_rtab(struct qdisc_rate_table *tab);
 void qdisc_put_stab(struct qdisc_size_table *tab);
-void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc);
+void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc);
 int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 		    struct net_device *dev, struct netdev_queue *txq,
 		    spinlock_t *root_lock);
diff --git a/include/net/protocol.h b/include/net/protocol.h
index a7e986b0814..d6fcc1fcdb5 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -86,7 +86,6 @@ struct inet_protosw {
 	struct proto	 *prot;
 	const struct proto_ops *ops;
   
-	char             no_check;   /* checksum on rcv/xmit/none? */
 	unsigned char	 flags;      /* See INET_PROTOSW_* below.  */
 };
 #define INET_PROTOSW_REUSE 0x01	     /* Are ports automatically reusable? */
diff --git a/include/net/regulatory.h b/include/net/regulatory.h
index 75fc1f5a948..259992444e8 100644
--- a/include/net/regulatory.h
+++ b/include/net/regulatory.h
@@ -131,6 +131,11 @@ struct regulatory_request {
  * 	all country IE information processed by the regulatory core. This will
  * 	override %REGULATORY_COUNTRY_IE_FOLLOW_POWER as all country IEs will
  * 	be ignored.
+ * @REGULATORY_ENABLE_RELAX_NO_IR: for devices that wish to allow the
+ *      NO_IR relaxation, which enables transmissions on channels on which
+ *      otherwise initiating radiation is not allowed. This will enable the
+ *      relaxations enabled under the CFG80211_REG_RELAX_NO_IR configuration
+ *      option
  */
 enum ieee80211_regulatory_flags {
 	REGULATORY_CUSTOM_REG			= BIT(0),
@@ -138,6 +143,7 @@ enum ieee80211_regulatory_flags {
 	REGULATORY_DISABLE_BEACON_HINTS		= BIT(2),
 	REGULATORY_COUNTRY_IE_FOLLOW_POWER	= BIT(3),
 	REGULATORY_COUNTRY_IE_IGNORE		= BIT(4),
+	REGULATORY_ENABLE_RELAX_NO_IR           = BIT(5),
 };
 
 struct ieee80211_freq_range {
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d062f81c692..624f9857c83 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -199,7 +199,7 @@ struct tcf_proto_ops {
 	int			(*change)(struct net *net, struct sk_buff *,
 					struct tcf_proto*, unsigned long,
 					u32 handle, struct nlattr **,
-					unsigned long *);
+					unsigned long *, bool);
 	int			(*delete)(struct tcf_proto*, unsigned long);
 	void			(*walk)(struct tcf_proto*, struct tcf_walker *arg);
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 0dfcc92600e..f38588bf346 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -838,10 +838,10 @@ struct sctp_transport {
 	unsigned long sackdelay;
 	__u32 sackfreq;
 
-	/* When was the last time (in jiffies) that we heard from this
-	 * transport?  We use this to pick new active and retran paths.
+	/* When was the last time that we heard from this transport? We use
+	 * this to pick new active and retran paths.
 	 */
-	unsigned long last_time_heard;
+	ktime_t last_time_heard;
 
 	/* Last time(in jiffies) when cwnd is reduced due to the congestion
 	 * indication based on ECNE chunk.
diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h
index f257486f17b..3f36d45b714 100644
--- a/include/net/secure_seq.h
+++ b/include/net/secure_seq.h
@@ -3,8 +3,6 @@
 
 #include <linux/types.h>
 
-__u32 secure_ip_id(__be32 daddr);
-__u32 secure_ipv6_id(const __be32 daddr[4]);
 u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
 u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
 			       __be16 dport);
diff --git a/include/net/snmp.h b/include/net/snmp.h
index 71596261fa9..f1f27fdbb0d 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -116,51 +116,49 @@ struct linux_xfrm_mib {
 	unsigned long	mibs[LINUX_MIB_XFRMMAX];
 };
 
-#define SNMP_ARRAY_SZ 1
-
 #define DEFINE_SNMP_STAT(type, name)	\
-	__typeof__(type) __percpu *name[SNMP_ARRAY_SZ]
+	__typeof__(type) __percpu *name
 #define DEFINE_SNMP_STAT_ATOMIC(type, name)	\
 	__typeof__(type) *name
 #define DECLARE_SNMP_STAT(type, name)	\
-	extern __typeof__(type) __percpu *name[SNMP_ARRAY_SZ]
+	extern __typeof__(type) __percpu *name
 
 #define SNMP_INC_STATS_BH(mib, field)	\
-			__this_cpu_inc(mib[0]->mibs[field])
+			__this_cpu_inc(mib->mibs[field])
 
 #define SNMP_INC_STATS_USER(mib, field)	\
-			this_cpu_inc(mib[0]->mibs[field])
+			this_cpu_inc(mib->mibs[field])
 
 #define SNMP_INC_STATS_ATOMIC_LONG(mib, field)	\
 			atomic_long_inc(&mib->mibs[field])
 
 #define SNMP_INC_STATS(mib, field)	\
-			this_cpu_inc(mib[0]->mibs[field])
+			this_cpu_inc(mib->mibs[field])
 
 #define SNMP_DEC_STATS(mib, field)	\
-			this_cpu_dec(mib[0]->mibs[field])
+			this_cpu_dec(mib->mibs[field])
 
 #define SNMP_ADD_STATS_BH(mib, field, addend)	\
-			__this_cpu_add(mib[0]->mibs[field], addend)
+			__this_cpu_add(mib->mibs[field], addend)
 
 #define SNMP_ADD_STATS_USER(mib, field, addend)	\
-			this_cpu_add(mib[0]->mibs[field], addend)
+			this_cpu_add(mib->mibs[field], addend)
 
 #define SNMP_ADD_STATS(mib, field, addend)	\
-			this_cpu_add(mib[0]->mibs[field], addend)
+			this_cpu_add(mib->mibs[field], addend)
 /*
- * Use "__typeof__(*mib[0]) *ptr" instead of "__typeof__(mib[0]) ptr"
+ * Use "__typeof__(*mib) *ptr" instead of "__typeof__(mib) ptr"
  * to make @ptr a non-percpu pointer.
  */
 #define SNMP_UPD_PO_STATS(mib, basefield, addend)	\
 	do { \
-		__typeof__(*mib[0]->mibs) *ptr = mib[0]->mibs;	\
+		__typeof__(*mib->mibs) *ptr = mib->mibs;	\
 		this_cpu_inc(ptr[basefield##PKTS]);		\
 		this_cpu_add(ptr[basefield##OCTETS], addend);	\
 	} while (0)
 #define SNMP_UPD_PO_STATS_BH(mib, basefield, addend)	\
 	do { \
-		__typeof__(*mib[0]->mibs) *ptr = mib[0]->mibs;	\
+		__typeof__(*mib->mibs) *ptr = mib->mibs;	\
 		__this_cpu_inc(ptr[basefield##PKTS]);		\
 		__this_cpu_add(ptr[basefield##OCTETS], addend);	\
 	} while (0)
@@ -170,7 +168,7 @@ struct linux_xfrm_mib {
 
 #define SNMP_ADD_STATS64_BH(mib, field, addend) 			\
 	do {								\
-		__typeof__(*mib[0]) *ptr = __this_cpu_ptr((mib)[0]);	\
+		__typeof__(*mib) *ptr = __this_cpu_ptr(mib);		\
 		u64_stats_update_begin(&ptr->syncp);			\
 		ptr->mibs[field] += addend;				\
 		u64_stats_update_end(&ptr->syncp);			\
@@ -191,8 +189,8 @@ struct linux_xfrm_mib {
 #define SNMP_INC_STATS64(mib, field) SNMP_ADD_STATS64(mib, field, 1)
 #define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend)			\
 	do {								\
-		__typeof__(*mib[0]) *ptr;				\
-		ptr = __this_cpu_ptr((mib)[0]);				\
+		__typeof__(*mib) *ptr;					\
+		ptr = __this_cpu_ptr(mib);				\
 		u64_stats_update_begin(&ptr->syncp);			\
 		ptr->mibs[basefield##PKTS]++;				\
 		ptr->mibs[basefield##OCTETS] += addend;			\
diff --git a/include/net/sock.h b/include/net/sock.h
index 21569cf456e..15635074570 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -243,7 +243,8 @@ struct cg_proto;
   *	@sk_sndbuf: size of send buffer in bytes
   *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
   *		   %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
-  *	@sk_no_check: %SO_NO_CHECK setting, whether or not checkup packets
+  *	@sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
+  *	@sk_no_check_rx: allow zero checksum in RX packets
   *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
   *	@sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
   *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
@@ -371,7 +372,8 @@ struct sock {
 	struct sk_buff_head	sk_write_queue;
 	kmemcheck_bitfield_begin(flags);
 	unsigned int		sk_shutdown  : 2,
-				sk_no_check  : 2,
+				sk_no_check_tx : 1,
+				sk_no_check_rx : 1,
 				sk_userlocks : 4,
 				sk_protocol  : 8,
 				sk_type      : 16;
@@ -1728,8 +1730,8 @@ sk_dst_get(struct sock *sk)
 
 	rcu_read_lock();
 	dst = rcu_dereference(sk->sk_dst_cache);
-	if (dst)
-		dst_hold(dst);
+	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+		dst = NULL;
 	rcu_read_unlock();
 	return dst;
 }
@@ -1766,9 +1768,11 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst)
 static inline void
 sk_dst_set(struct sock *sk, struct dst_entry *dst)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_set(sk, dst);
-	spin_unlock(&sk->sk_dst_lock);
+	struct dst_entry *old_dst;
+
+	sk_tx_queue_clear(sk);
+	old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst);
+	dst_release(old_dst);
 }
 
 static inline void
@@ -1780,9 +1784,7 @@ __sk_dst_reset(struct sock *sk)
 static inline void
 sk_dst_reset(struct sock *sk)
 {
-	spin_lock(&sk->sk_dst_lock);
-	__sk_dst_reset(sk);
-	spin_unlock(&sk->sk_dst_lock);
+	sk_dst_set(sk, NULL);
 }
 
 struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 87d87740818..7286db80e8b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -220,8 +220,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define	TFO_SERVER_ENABLE	2
 #define	TFO_CLIENT_NO_COOKIE	4	/* Data in SYN w/o cookie option */
 
-/* Process SYN data but skip cookie validation */
-#define	TFO_SERVER_COOKIE_NOT_CHKED	0x100
 /* Accept SYN data w/o any cookie option */
 #define	TFO_SERVER_COOKIE_NOT_REQD	0x200
 
@@ -230,10 +228,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
  */
 #define	TFO_SERVER_WO_SOCKOPT1	0x400
 #define	TFO_SERVER_WO_SOCKOPT2	0x800
-/* Always create TFO child sockets on a TFO listener even when
- * cookie/data not present. (For testing purpose!)
- */
-#define	TFO_SERVER_ALWAYS	0x1000
 
 extern struct inet_timewait_death_row tcp_death_row;
 
@@ -541,7 +535,7 @@ void tcp_retransmit_timer(struct sock *sk);
 void tcp_xmit_retransmit_queue(struct sock *);
 void tcp_simple_retransmit(struct sock *);
 int tcp_trim_head(struct sock *, struct sk_buff *, u32);
-int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int);
+int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int, gfp_t);
 
 void tcp_send_probe0(struct sock *);
 void tcp_send_partial(struct sock *);
@@ -558,7 +552,6 @@ void tcp_send_loss_probe(struct sock *sk);
 bool tcp_schedule_loss_probe(struct sock *sk);
 
 /* tcp_input.c */
-void tcp_cwnd_application_limited(struct sock *sk);
 void tcp_resume_early_retransmit(struct sock *sk);
 void tcp_rearm_rto(struct sock *sk);
 void tcp_reset(struct sock *sk);
@@ -797,7 +790,7 @@ struct tcp_congestion_ops {
 	/* return slow start threshold (required) */
 	u32 (*ssthresh)(struct sock *sk);
 	/* do new cwnd calculation (required) */
-	void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked, u32 in_flight);
+	void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked);
 	/* call before changing ca_state (optional) */
 	void (*set_state)(struct sock *sk, u8 new_state);
 	/* call when cwnd event occurs (optional) */
@@ -829,7 +822,7 @@ void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
 
 extern struct tcp_congestion_ops tcp_init_congestion_ops;
 u32 tcp_reno_ssthresh(struct sock *sk);
-void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight);
+void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
 extern struct tcp_congestion_ops tcp_reno;
 
 static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
@@ -975,7 +968,30 @@ static inline u32 tcp_wnd_end(const struct tcp_sock *tp)
 {
 	return tp->snd_una + tp->snd_wnd;
 }
-bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight);
+
+/* We follow the spirit of RFC2861 to validate cwnd but implement a more
+ * flexible approach. The RFC suggests cwnd should not be raised unless
+ * it was fully used previously. And that's exactly what we do in
+ * congestion avoidance mode. But in slow start we allow cwnd to grow
+ * as long as the application has used half the cwnd.
+ * Example :
+ *    cwnd is 10 (IW10), but application sends 9 frames.
+ *    We allow cwnd to reach 18 when all frames are ACKed.
+ * This check is safe because it's as aggressive as slow start which already
+ * risks 100% overshoot. The advantage is that we discourage application to
+ * either send more filler packets or data to artificially blow up the cwnd
+ * usage, and allow application-limited process to probe bw more aggressively.
+ */
+static inline bool tcp_is_cwnd_limited(const struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+
+	/* If in slow start, ensure cwnd grows to twice what was ACKed. */
+	if (tp->snd_cwnd <= tp->snd_ssthresh)
+		return tp->snd_cwnd < 2 * tp->max_packets_out;
+
+	return tp->is_cwnd_limited;
+}
 
 static inline void tcp_check_probe_timer(struct sock *sk)
 {
@@ -1103,6 +1119,9 @@ static inline void tcp_openreq_init(struct request_sock *req,
 	ireq->ir_num = ntohs(tcp_hdr(skb)->dest);
 }
 
+extern void tcp_openreq_init_rwin(struct request_sock *req,
+				  struct sock *sk, struct dst_entry *dst);
+
 void tcp_enter_memory_pressure(struct sock *sk);
 
 static inline int keepalive_intvl_when(const struct tcp_sock *tp)
@@ -1312,8 +1331,10 @@ void tcp_free_fastopen_req(struct tcp_sock *tp);
 
 extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
 int tcp_fastopen_reset_cipher(void *key, unsigned int len);
-void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
-			     struct tcp_fastopen_cookie *foc);
+bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
+		      struct request_sock *req,
+		      struct tcp_fastopen_cookie *foc,
+		      struct dst_entry *dst);
 void tcp_fastopen_init_key_once(bool publish);
 #define TCP_FASTOPEN_KEY_LENGTH 16
 
diff --git a/include/net/tso.h b/include/net/tso.h
new file mode 100644
index 00000000000..47e5444f7d1
--- /dev/null
+++ b/include/net/tso.h
@@ -0,0 +1,20 @@
+#ifndef _TSO_H
+#define _TSO_H
+
+#include <net/ip.h>
+
+struct tso_t {
+	int next_frag_idx;
+	void *data;
+	size_t size;
+	u16 ip_id;
+	u32 tcp_seq;
+};
+
+int tso_count_descs(struct sk_buff *skb);
+void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
+		   int size, bool is_last);
+void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size);
+void tso_start(struct sk_buff *skb, struct tso_t *tso);
+
+#endif	/* _TSO_H */
diff --git a/include/net/udp.h b/include/net/udp.h
index a24f0f3e107..68a1fefe3df 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -95,15 +95,6 @@ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table,
 	return &table->hash2[hash & table->mask];
 }
 
-/* Note: this must match 'valbool' in sock_setsockopt */
-#define UDP_CSUM_NOXMIT		1
-
-/* Used by SunRPC/xprt layer. */
-#define UDP_CSUM_NORCV		2
-
-/* Default, as per the RFC, is to always do csums. */
-#define UDP_CSUM_DEFAULT	0
-
 extern struct proto udp_prot;
 
 extern atomic_long_t udp_memory_allocated;
@@ -120,7 +111,9 @@ struct sk_buff;
  */
 static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb)
 {
-	return __skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov);
+	return (UDP_SKB_CB(skb)->cscov == skb->len ?
+		__skb_checksum_complete(skb) :
+		__skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov));
 }
 
 static inline int udp_lib_checksum_complete(struct sk_buff *skb)
@@ -156,6 +149,15 @@ static inline __wsum udp_csum(struct sk_buff *skb)
 	return csum;
 }
 
+static inline __sum16 udp_v4_check(int len, __be32 saddr,
+				   __be32 daddr, __wsum base)
+{
+	return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base);
+}
+
+void udp_set_csum(bool nocheck, struct sk_buff *skb,
+		  __be32 saddr, __be32 daddr, int len);
+
 /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
 static inline void udp_lib_hash(struct sock *sk)
 {
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 5deef1ae78c..12196ce661d 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -24,16 +24,26 @@ struct vxlan_sock {
 	struct udp_offload udp_offloads;
 };
 
+#define VXLAN_F_LEARN			0x01
+#define VXLAN_F_PROXY			0x02
+#define VXLAN_F_RSC			0x04
+#define VXLAN_F_L2MISS			0x08
+#define VXLAN_F_L3MISS			0x10
+#define VXLAN_F_IPV6			0x20
+#define VXLAN_F_UDP_CSUM		0x40
+#define VXLAN_F_UDP_ZERO_CSUM6_TX	0x80
+#define VXLAN_F_UDP_ZERO_CSUM6_RX	0x100
+
 struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
 				  vxlan_rcv_t *rcv, void *data,
-				  bool no_share, bool ipv6);
+				  bool no_share, u32 flags);
 
 void vxlan_sock_release(struct vxlan_sock *vs);
 
 int vxlan_xmit_skb(struct vxlan_sock *vs,
 		   struct rtable *rt, struct sk_buff *skb,
 		   __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
-		   __be16 src_port, __be16 dst_port, __be32 vni);
+		   __be16 src_port, __be16 dst_port, __be32 vni, bool xnet);
 
 __be16 vxlan_src_port(__u16 port_min, __u16 port_max, struct sk_buff *skb);
 
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 116e9c7e19c..721e9c3b11b 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -691,13 +691,6 @@ struct xfrm_spi_skb_cb {
 
 #define XFRM_SPI_SKB_CB(__skb) ((struct xfrm_spi_skb_cb *)&((__skb)->cb[0]))
 
-/* Audit Information */
-struct xfrm_audit {
-	u32	secid;
-	kuid_t	loginuid;
-	unsigned int sessionid;
-};
-
 #ifdef CONFIG_AUDITSYSCALL
 static inline struct audit_buffer *xfrm_audit_start(const char *op)
 {
@@ -713,30 +706,24 @@ static inline struct audit_buffer *xfrm_audit_start(const char *op)
 	return audit_buf;
 }
 
-static inline void xfrm_audit_helper_usrinfo(kuid_t auid, unsigned int ses, u32 secid,
+static inline void xfrm_audit_helper_usrinfo(bool task_valid,
 					     struct audit_buffer *audit_buf)
 {
-	char *secctx;
-	u32 secctx_len;
-
-	audit_log_format(audit_buf, " auid=%u ses=%u",
-			 from_kuid(&init_user_ns, auid), ses);
-	if (secid != 0 &&
-	    security_secid_to_secctx(secid, &secctx, &secctx_len) == 0) {
-		audit_log_format(audit_buf, " subj=%s", secctx);
-		security_release_secctx(secctx, secctx_len);
-	} else
-		audit_log_task_context(audit_buf);
-}
-
-void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, kuid_t auid,
-			   unsigned int ses, u32 secid);
-void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, kuid_t auid,
-			      unsigned int ses, u32 secid);
-void xfrm_audit_state_add(struct xfrm_state *x, int result, kuid_t auid,
-			  unsigned int ses, u32 secid);
-void xfrm_audit_state_delete(struct xfrm_state *x, int result, kuid_t auid,
-			     unsigned int ses, u32 secid);
+	const unsigned int auid = from_kuid(&init_user_ns, task_valid ?
+					    audit_get_loginuid(current) :
+					    INVALID_UID);
+	const unsigned int ses = task_valid ? audit_get_sessionid(current) :
+		(unsigned int) -1;
+
+	audit_log_format(audit_buf, " auid=%u ses=%u", auid, ses);
+	audit_log_task_context(audit_buf);
+}
+
+void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid);
+void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
+			      bool task_valid);
+void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid);
+void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid);
 void xfrm_audit_state_replay_overflow(struct xfrm_state *x,
 				      struct sk_buff *skb);
 void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb,
@@ -749,22 +736,22 @@ void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb,
 #else
 
 static inline void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
-				  kuid_t auid, unsigned int ses, u32 secid)
+					 bool task_valid)
 {
 }
 
 static inline void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
-				  kuid_t auid, unsigned int ses, u32 secid)
+					    bool task_valid)
 {
 }
 
 static inline void xfrm_audit_state_add(struct xfrm_state *x, int result,
-				 kuid_t auid, unsigned int ses, u32 secid)
+					bool task_valid)
 {
 }
 
 static inline void xfrm_audit_state_delete(struct xfrm_state *x, int result,
-				    kuid_t auid, unsigned int ses, u32 secid)
+					   bool task_valid)
 {
 }
 
@@ -1508,7 +1495,7 @@ struct xfrmk_spdinfo {
 
 struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq);
 int xfrm_state_delete(struct xfrm_state *x);
-int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info);
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid);
 void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
 u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
@@ -1603,7 +1590,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark,
 					  int *err);
 struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir,
 				     u32 id, int delete, int *err);
-int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info);
+int xfrm_policy_flush(struct net *net, u8 type, bool task_valid);
 u32 xfrm_get_acqseq(void);
 int verify_spi_info(u8 proto, u32 min, u32 max);
 int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index acd82518297..7ccef342f72 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -80,8 +80,8 @@ enum rdma_transport_type {
 	RDMA_TRANSPORT_USNIC_UDP
 };
 
-enum rdma_transport_type
-rdma_node_get_transport(enum rdma_node_type node_type) __attribute_const__;
+__attribute_const__ enum rdma_transport_type
+rdma_node_get_transport(enum rdma_node_type node_type);
 
 enum rdma_link_layer {
 	IB_LINK_LAYER_UNSPECIFIED,
@@ -466,14 +466,14 @@ enum ib_rate {
  * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec.
  * @rate: rate to convert.
  */
-int ib_rate_to_mult(enum ib_rate rate) __attribute_const__;
+__attribute_const__ int ib_rate_to_mult(enum ib_rate rate);
 
 /**
  * ib_rate_to_mbps - Convert the IB rate enum to Mbps.
  * For example, IB_RATE_2_5_GBPS will be converted to 2500.
  * @rate: rate to convert.
  */
-int ib_rate_to_mbps(enum ib_rate rate) __attribute_const__;
+__attribute_const__ int ib_rate_to_mbps(enum ib_rate rate);
 
 enum ib_mr_create_flags {
 	IB_MR_SIGNATURE_EN = 1,
@@ -604,7 +604,7 @@ struct ib_mr_status {
  * enum.
  * @mult: multiple to convert.
  */
-enum ib_rate mult_to_ib_rate(int mult) __attribute_const__;
+__attribute_const__ enum ib_rate mult_to_ib_rate(int mult);
 
 struct ib_ah_attr {
 	struct ib_global_route	grh;
@@ -783,6 +783,7 @@ enum ib_qp_create_flags {
 	IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK	= 1 << 1,
 	IB_QP_CREATE_NETIF_QP			= 1 << 5,
 	IB_QP_CREATE_SIGNATURE_EN		= 1 << 6,
+	IB_QP_CREATE_USE_GFP_NOIO		= 1 << 7,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
diff --git a/include/rdma/iw_portmap.h b/include/rdma/iw_portmap.h
new file mode 100644
index 00000000000..928b2775e99
--- /dev/null
+++ b/include/rdma/iw_portmap.h
@@ -0,0 +1,199 @@
+/*
+ * Copyright (c) 2014 Intel Corporation. All rights reserved.
+ * Copyright (c) 2014 Chelsio, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *	  copyright notice, this list of conditions and the following
+ *	  disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *	  copyright notice, this list of conditions and the following
+ *	  disclaimer in the documentation and/or other materials
+ *	  provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef _IW_PORTMAP_H
+#define _IW_PORTMAP_H
+
+#define IWPM_ULIBNAME_SIZE	32
+#define IWPM_DEVNAME_SIZE	32
+#define IWPM_IFNAME_SIZE	16
+#define IWPM_IPADDR_SIZE	16
+
+enum {
+	IWPM_INVALID_NLMSG_ERR = 10,
+	IWPM_CREATE_MAPPING_ERR,
+	IWPM_DUPLICATE_MAPPING_ERR,
+	IWPM_UNKNOWN_MAPPING_ERR,
+	IWPM_CLIENT_DEV_INFO_ERR,
+	IWPM_USER_LIB_INFO_ERR,
+	IWPM_REMOTE_QUERY_REJECT
+};
+
+struct iwpm_dev_data {
+	char dev_name[IWPM_DEVNAME_SIZE];
+	char if_name[IWPM_IFNAME_SIZE];
+};
+
+struct iwpm_sa_data {
+	struct sockaddr_storage loc_addr;
+	struct sockaddr_storage mapped_loc_addr;
+	struct sockaddr_storage rem_addr;
+	struct sockaddr_storage mapped_rem_addr;
+};
+
+/**
+ * iwpm_init - Allocate resources for the iwarp port mapper
+ *
+ * Should be called when network interface goes up.
+ */
+int iwpm_init(u8);
+
+/**
+ * iwpm_exit - Deallocate resources for the iwarp port mapper
+ *
+ * Should be called when network interface goes down.
+ */
+int iwpm_exit(u8);
+
+/**
+ * iwpm_valid_pid - Check if the userspace iwarp port mapper pid is valid
+ *
+ * Returns true if the pid is greater than zero, otherwise returns false
+ */
+int iwpm_valid_pid(void);
+
+/**
+ * iwpm_register_pid - Send a netlink query to userspace
+ *                     to get the iwarp port mapper pid
+ * @pm_msg: Contains driver info to send to the userspace port mapper
+ * @nl_client: The index of the netlink client
+ */
+int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client);
+
+/**
+ * iwpm_add_mapping - Send a netlink add mapping request to
+ *                    the userspace port mapper
+ * @pm_msg: Contains the local ip/tcp address info to send
+ * @nl_client: The index of the netlink client
+ *
+ * If the request is successful, the pm_msg stores
+ * the port mapper response (mapped address info)
+ */
+int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client);
+
+/**
+ * iwpm_add_and_query_mapping - Send a netlink add and query mapping request
+ *				 to the userspace port mapper
+ * @pm_msg: Contains the local and remote ip/tcp address info to send
+ * @nl_client: The index of the netlink client
+ *
+ * If the request is successful, the pm_msg stores the
+ * port mapper response (mapped local and remote address info)
+ */
+int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client);
+
+/**
+ * iwpm_remove_mapping - Send a netlink remove mapping request
+ *                       to the userspace port mapper
+ *
+ * @local_addr: Local ip/tcp address to remove
+ * @nl_client: The index of the netlink client
+ */
+int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client);
+
+/**
+ * iwpm_register_pid_cb - Process the port mapper response to
+ *                        iwpm_register_pid query
+ * @skb:
+ * @cb: Contains the received message (payload and netlink header)
+ *
+ * If successful, the function receives the userspace port mapper pid
+ * which is used in future communication with the port mapper
+ */
+int iwpm_register_pid_cb(struct sk_buff *, struct netlink_callback *);
+
+/**
+ * iwpm_add_mapping_cb - Process the port mapper response to
+ *                       iwpm_add_mapping request
+ * @skb:
+ * @cb: Contains the received message (payload and netlink header)
+ */
+int iwpm_add_mapping_cb(struct sk_buff *, struct netlink_callback *);
+
+/**
+ * iwpm_add_and_query_mapping_cb - Process the port mapper response to
+ *                                 iwpm_add_and_query_mapping request
+ * @skb:
+ * @cb: Contains the received message (payload and netlink header)
+ */
+int iwpm_add_and_query_mapping_cb(struct sk_buff *, struct netlink_callback *);
+
+/**
+ * iwpm_mapping_error_cb - Process port mapper notification for error
+ *
+ * @skb:
+ * @cb: Contains the received message (payload and netlink header)
+ */
+int iwpm_mapping_error_cb(struct sk_buff *, struct netlink_callback *);
+
+/**
+ * iwpm_mapping_info_cb - Process a notification that the userspace
+ *                        port mapper daemon is started
+ * @skb:
+ * @cb: Contains the received message (payload and netlink header)
+ *
+ * Using the received port mapper pid, send all the local mapping
+ * info records to the userspace port mapper
+ */
+int iwpm_mapping_info_cb(struct sk_buff *, struct netlink_callback *);
+
+/**
+ * iwpm_ack_mapping_info_cb - Process the port mapper ack for
+ *                            the provided local mapping info records
+ * @skb:
+ * @cb: Contains the received message (payload and netlink header)
+ */
+int iwpm_ack_mapping_info_cb(struct sk_buff *, struct netlink_callback *);
+
+/**
+ * iwpm_create_mapinfo - Store local and mapped IPv4/IPv6 address
+ *                       info in a hash table
+ * @local_addr: Local ip/tcp address
+ * @mapped_addr: Mapped local ip/tcp address
+ * @nl_client: The index of the netlink client
+ */
+int iwpm_create_mapinfo(struct sockaddr_storage *local_addr,
+			struct sockaddr_storage *mapped_addr, u8 nl_client);
+
+/**
+ * iwpm_remove_mapinfo - Remove local and mapped IPv4/IPv6 address
+ *                       info from the hash table
+ * @local_addr: Local ip/tcp address
+ * @mapped_addr: Mapped local ip/tcp address
+ *
+ * Returns err code if mapping info is not found in the hash table,
+ * otherwise returns 0
+ */
+int iwpm_remove_mapinfo(struct sockaddr_storage *local_addr,
+			struct sockaddr_storage *mapped_addr);
+
+#endif /* _IW_PORTMAP_H */
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index e38de79eeb4..0790882e0c9 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -43,7 +43,7 @@ int ibnl_remove_client(int index);
  * Returns the allocated buffer on success and NULL on failure.
  */
 void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
-		   int len, int client, int op);
+		   int len, int client, int op, int flags);
 /**
  * Put a new attribute in a supplied skb.
  * @skb: The netlink skb.
@@ -56,4 +56,25 @@ void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
 int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		  int len, void *data, int type);
 
+/**
+ * Send the supplied skb to a specific userspace PID.
+ * @skb: The netlink skb
+ * @nlh: Header of the netlink message to send
+ * @pid: Userspace netlink process ID
+ * Returns 0 on success or a negative error code.
+ */
+int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
+			__u32 pid);
+
+/**
+ * Send the supplied skb to a netlink group.
+ * @skb: The netlink skb
+ * @nlh: Header of the netlink message to send
+ * @group: Netlink group ID
+ * @flags: allocation flags
+ * Returns 0 on success or a negative error code.
+ */
+int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
+			unsigned int group, gfp_t flags);
+
 #endif /* _RDMA_NETLINK_H */
diff --git a/include/scsi/osd_protocol.h b/include/scsi/osd_protocol.h
index 25ac6283b9c..a2594afe05c 100644
--- a/include/scsi/osd_protocol.h
+++ b/include/scsi/osd_protocol.h
@@ -263,16 +263,16 @@ static inline struct osd_cdb_head *osd_cdb_head(struct osd_cdb *ocdb)
  * Ex name = FORMAT_OSD we have OSD_ACT_FORMAT_OSD && OSDv1_ACT_FORMAT_OSD
  */
 #define OSD_ACT___(Name, Num) \
-	OSD_ACT_##Name = __constant_cpu_to_be16(0x8880 + Num), \
-	OSDv1_ACT_##Name = __constant_cpu_to_be16(0x8800 + Num),
+	OSD_ACT_##Name = cpu_to_be16(0x8880 + Num), \
+	OSDv1_ACT_##Name = cpu_to_be16(0x8800 + Num),
 
 /* V2 only actions */
 #define OSD_ACT_V2(Name, Num) \
-	OSD_ACT_##Name = __constant_cpu_to_be16(0x8880 + Num),
+	OSD_ACT_##Name = cpu_to_be16(0x8880 + Num),
 
 #define OSD_ACT_V1_V2(Name, Num1, Num2) \
-	OSD_ACT_##Name = __constant_cpu_to_be16(Num2), \
-	OSDv1_ACT_##Name = __constant_cpu_to_be16(Num1),
+	OSD_ACT_##Name = cpu_to_be16(Num2), \
+	OSDv1_ACT_##Name = cpu_to_be16(Num1),
 
 enum osd_service_actions {
 	OSD_ACT_V2(OBJECT_STRUCTURE_CHECK,	0x00)
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index dd7c998221b..e0ae7109814 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 #include <linux/timer.h>
 #include <linux/scatterlist.h>
+#include <scsi/scsi_device.h>
 
 struct Scsi_Host;
 struct scsi_device;
@@ -133,6 +134,15 @@ struct scsi_cmnd {
 	unsigned char tag;	/* SCSI-II queued command tag */
 };
 
+/*
+ * Return the driver private allocation behind the command.
+ * Only works if cmd_size is set in the host template.
+ */
+static inline void *scsi_cmd_priv(struct scsi_cmnd *cmd)
+{
+	return cmd + 1;
+}
+
 /* make sure not to use it with REQ_TYPE_BLOCK_PC commands */
 static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd)
 {
@@ -306,4 +316,20 @@ static inline void set_driver_byte(struct scsi_cmnd *cmd, char status)
 	cmd->result = (cmd->result & 0x00ffffff) | (status << 24);
 }
 
+static inline unsigned scsi_transfer_length(struct scsi_cmnd *scmd)
+{
+	unsigned int xfer_len = scsi_out(scmd)->length;
+	unsigned int prot_op = scsi_get_prot_op(scmd);
+	unsigned int sector_size = scmd->device->sector_size;
+
+	switch (prot_op) {
+	case SCSI_PROT_NORMAL:
+	case SCSI_PROT_WRITE_STRIP:
+	case SCSI_PROT_READ_INSERT:
+		return xfer_len;
+	}
+
+	return xfer_len + (xfer_len >> ilog2(sector_size)) * 8;
+}
+
 #endif /* _SCSI_SCSI_CMND_H */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 5853c913d2b..27ab31017f0 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -173,6 +173,7 @@ struct scsi_device {
 	unsigned is_visible:1;	/* is the device visible in sysfs */
 	unsigned wce_default_on:1;	/* Cache is ON by default */
 	unsigned no_dif:1;	/* T10 PI (DIF) should be disabled */
+	unsigned broken_fua:1;		/* Don't set FUA bit */
 
 	atomic_t disk_events_disable_depth; /* disable depth for disk events */
 
diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h
index 20fdfc2526a..36c4114ed9b 100644
--- a/include/scsi/scsi_driver.h
+++ b/include/scsi/scsi_driver.h
@@ -4,17 +4,17 @@
 #include <linux/device.h>
 
 struct module;
+struct request;
 struct scsi_cmnd;
 struct scsi_device;
-struct request;
-struct request_queue;
-
 
 struct scsi_driver {
 	struct module		*owner;
 	struct device_driver	gendrv;
 
 	void (*rescan)(struct device *);
+	int (*init_command)(struct scsi_cmnd *);
+	void (*uninit_command)(struct scsi_cmnd *);
 	int (*done)(struct scsi_cmnd *);
 	int (*eh_action)(struct scsi_cmnd *, int);
 };
@@ -31,8 +31,5 @@ extern int scsi_register_interface(struct class_interface *);
 
 int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req);
 int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req);
-int scsi_prep_state_check(struct scsi_device *sdev, struct request *req);
-int scsi_prep_return(struct request_queue *q, struct request *req, int ret);
-int scsi_prep_fn(struct request_queue *, struct request *);
 
 #endif /* _SCSI_SCSI_DRIVER_H */
diff --git a/include/sound/core.h b/include/sound/core.h
index eedda2cdfe5..1df3f2fe535 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -116,6 +116,8 @@ struct snd_card {
 	int user_ctl_count;		/* count of all user controls */
 	struct list_head controls;	/* all controls for this card */
 	struct list_head ctl_files;	/* active control files */
+	struct mutex user_ctl_lock;	/* protects user controls against
+					   concurrent access */
 
 	struct snd_info_entry *proc_root;	/* root for soundcard specific files */
 	struct snd_info_entry *proc_id;	/* the card id */
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index b4d6697085f..d854fb31c00 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -932,7 +932,7 @@ static inline void snd_pcm_gettime(struct snd_pcm_runtime *runtime,
 				   struct timespec *tv)
 {
 	if (runtime->tstamp_type == SNDRV_PCM_TSTAMP_TYPE_MONOTONIC)
-		do_posix_clock_monotonic_gettime(tv);
+		ktime_get_ts(tv);
 	else
 		getnstimeofday(tv);
 }
diff --git a/include/target/iscsi/iscsi_transport.h b/include/target/iscsi/iscsi_transport.h
index 33b487b5da9..daef9daa500 100644
--- a/include/target/iscsi/iscsi_transport.h
+++ b/include/target/iscsi/iscsi_transport.h
@@ -70,7 +70,8 @@ extern void iscsit_build_nopin_rsp(struct iscsi_cmd *, struct iscsi_conn *,
 extern void iscsit_build_task_mgt_rsp(struct iscsi_cmd *, struct iscsi_conn *,
 				struct iscsi_tm_rsp *);
 extern int iscsit_build_text_rsp(struct iscsi_cmd *, struct iscsi_conn *,
-				struct iscsi_text_rsp *);
+				struct iscsi_text_rsp *,
+				enum iscsit_transport_type);
 extern void iscsit_build_reject(struct iscsi_cmd *, struct iscsi_conn *,
 				struct iscsi_reject *);
 extern int iscsit_build_logout_rsp(struct iscsi_cmd *, struct iscsi_conn *,
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 3a1c1eea1ff..9adc1bca117 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -59,6 +59,7 @@ int	transport_subsystem_register(struct se_subsystem_api *);
 void	transport_subsystem_release(struct se_subsystem_api *);
 
 void	target_complete_cmd(struct se_cmd *, u8);
+void	target_complete_cmd_with_length(struct se_cmd *, u8, int);
 
 sense_reason_t	spc_parse_cdb(struct se_cmd *cmd, unsigned int *size);
 sense_reason_t	spc_emulate_report_luns(struct se_cmd *cmd);
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 6a1a0245474..d4f70a7fe87 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -36,7 +36,7 @@ struct extent_status;
 
 #define show_map_flags(flags) __print_flags(flags, "|",			\
 	{ EXT4_GET_BLOCKS_CREATE,		"CREATE" },		\
-	{ EXT4_GET_BLOCKS_UNINIT_EXT,		"UNINIT" },		\
+	{ EXT4_GET_BLOCKS_UNWRIT_EXT,		"UNWRIT" },		\
 	{ EXT4_GET_BLOCKS_DELALLOC_RESERVE,	"DELALLOC" },		\
 	{ EXT4_GET_BLOCKS_PRE_IO,		"PRE_IO" },		\
 	{ EXT4_GET_BLOCKS_CONVERT,		"CONVERT" },		\
@@ -51,7 +51,6 @@ struct extent_status;
 	{ EXT4_MAP_MAPPED,	"M" },			\
 	{ EXT4_MAP_UNWRITTEN,	"U" },			\
 	{ EXT4_MAP_BOUNDARY,	"B" },			\
-	{ EXT4_MAP_UNINIT,	"u" },			\
 	{ EXT4_MAP_FROM_CLUSTER, "C" })
 
 #define show_free_flags(flags) __print_flags(flags, "|",	\
@@ -1497,7 +1496,7 @@ DEFINE_EVENT(ext4__truncate, ext4_truncate_exit,
 	TP_ARGS(inode)
 );
 
-/* 'ux' is the uninitialized extent. */
+/* 'ux' is the unwritten extent. */
 TRACE_EVENT(ext4_ext_convert_to_initialized_enter,
 	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map,
 		 struct ext4_extent *ux),
@@ -1533,7 +1532,7 @@ TRACE_EVENT(ext4_ext_convert_to_initialized_enter,
 );
 
 /*
- * 'ux' is the uninitialized extent.
+ * 'ux' is the unwritten extent.
  * 'ix' is the initialized extent to which blocks are transferred.
  */
 TRACE_EVENT(ext4_ext_convert_to_initialized_fastpath,
@@ -1811,7 +1810,7 @@ DEFINE_EVENT(ext4__trim, ext4_trim_all_free,
 	TP_ARGS(sb, group, start, len)
 );
 
-TRACE_EVENT(ext4_ext_handle_uninitialized_extents,
+TRACE_EVENT(ext4_ext_handle_unwritten_extents,
 	TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int flags,
 		 unsigned int allocated, ext4_fsblk_t newblock),
 
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 67f38faac58..b983990b4a9 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -659,6 +659,66 @@ DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
 	TP_CONDITION(bio)
 );
 
+TRACE_EVENT(f2fs_write_begin,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+				unsigned int flags),
+
+	TP_ARGS(inode, pos, len, flags),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t,	pos)
+		__field(unsigned int, len)
+		__field(unsigned int, flags)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->flags	= flags;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, flags = %u",
+		show_dev_ino(__entry),
+		(unsigned long long)__entry->pos,
+		__entry->len,
+		__entry->flags)
+);
+
+TRACE_EVENT(f2fs_write_end,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+				unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(loff_t,	pos)
+		__field(unsigned int, len)
+		__field(unsigned int, copied)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->pos	= pos;
+		__entry->len	= len;
+		__entry->copied	= copied;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pos = %llu, len = %u, copied = %u",
+		show_dev_ino(__entry),
+		(unsigned long long)__entry->pos,
+		__entry->len,
+		__entry->copied)
+);
+
 DECLARE_EVENT_CLASS(f2fs__page,
 
 	TP_PROTO(struct page *page, int type),
@@ -672,6 +732,7 @@ DECLARE_EVENT_CLASS(f2fs__page,
 		__field(int, dir)
 		__field(pgoff_t, index)
 		__field(int, dirty)
+		__field(int, uptodate)
 	),
 
 	TP_fast_assign(
@@ -681,14 +742,31 @@ DECLARE_EVENT_CLASS(f2fs__page,
 		__entry->dir	= S_ISDIR(page->mapping->host->i_mode);
 		__entry->index	= page->index;
 		__entry->dirty	= PageDirty(page);
+		__entry->uptodate = PageUptodate(page);
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, %s, %s, index = %lu, dirty = %d",
+	TP_printk("dev = (%d,%d), ino = %lu, %s, %s, index = %lu, "
+		"dirty = %d, uptodate = %d",
 		show_dev_ino(__entry),
 		show_block_type(__entry->type),
 		show_file_type(__entry->dir),
 		(unsigned long)__entry->index,
-		__entry->dirty)
+		__entry->dirty,
+		__entry->uptodate)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_writepage,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_readpage,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
 );
 
 DEFINE_EVENT(f2fs__page, f2fs_set_page_dirty,
@@ -705,6 +783,70 @@ DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite,
 	TP_ARGS(page, type)
 );
 
+TRACE_EVENT(f2fs_writepages,
+
+	TP_PROTO(struct inode *inode, struct writeback_control *wbc, int type),
+
+	TP_ARGS(inode, wbc, type),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(int,	type)
+		__field(int,	dir)
+		__field(long,	nr_to_write)
+		__field(long,	pages_skipped)
+		__field(loff_t,	range_start)
+		__field(loff_t,	range_end)
+		__field(pgoff_t, writeback_index)
+		__field(int,	sync_mode)
+		__field(char,	for_kupdate)
+		__field(char,	for_background)
+		__field(char,	tagged_writepages)
+		__field(char,	for_reclaim)
+		__field(char,	range_cyclic)
+		__field(char,	for_sync)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= inode->i_sb->s_dev;
+		__entry->ino		= inode->i_ino;
+		__entry->type		= type;
+		__entry->dir		= S_ISDIR(inode->i_mode);
+		__entry->nr_to_write	= wbc->nr_to_write;
+		__entry->pages_skipped	= wbc->pages_skipped;
+		__entry->range_start	= wbc->range_start;
+		__entry->range_end	= wbc->range_end;
+		__entry->writeback_index = inode->i_mapping->writeback_index;
+		__entry->sync_mode	= wbc->sync_mode;
+		__entry->for_kupdate	= wbc->for_kupdate;
+		__entry->for_background	= wbc->for_background;
+		__entry->tagged_writepages	= wbc->tagged_writepages;
+		__entry->for_reclaim	= wbc->for_reclaim;
+		__entry->range_cyclic	= wbc->range_cyclic;
+		__entry->for_sync	= wbc->for_sync;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, %s, %s, nr_to_write %ld, "
+		"skipped %ld, start %lld, end %lld, wb_idx %lu, sync_mode %d, "
+		"kupdate %u background %u tagged %u reclaim %u cyclic %u sync %u",
+		show_dev_ino(__entry),
+		show_block_type(__entry->type),
+		show_file_type(__entry->dir),
+		__entry->nr_to_write,
+		__entry->pages_skipped,
+		__entry->range_start,
+		__entry->range_end,
+		(unsigned long)__entry->writeback_index,
+		__entry->sync_mode,
+		__entry->for_kupdate,
+		__entry->for_background,
+		__entry->tagged_writepages,
+		__entry->for_reclaim,
+		__entry->range_cyclic,
+		__entry->for_sync)
+);
+
 TRACE_EVENT(f2fs_submit_page_mbio,
 
 	TP_PROTO(struct page *page, int rw, int type, block_t blk_addr),
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 9a7e08d6125..d19840b0cac 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -7,6 +7,9 @@
 #include <linux/ktime.h>
 #include <linux/pm_qos.h>
 #include <linux/tracepoint.h>
+#include <linux/ftrace_event.h>
+
+#define TPS(x)  tracepoint_string(x)
 
 DECLARE_EVENT_CLASS(cpu,
 
@@ -90,6 +93,17 @@ TRACE_EVENT(pstate_sample,
 #define PWR_EVENT_EXIT -1
 #endif
 
+#define pm_verb_symbolic(event) \
+	__print_symbolic(event, \
+		{ PM_EVENT_SUSPEND, "suspend" }, \
+		{ PM_EVENT_RESUME, "resume" }, \
+		{ PM_EVENT_FREEZE, "freeze" }, \
+		{ PM_EVENT_QUIESCE, "quiesce" }, \
+		{ PM_EVENT_HIBERNATE, "hibernate" }, \
+		{ PM_EVENT_THAW, "thaw" }, \
+		{ PM_EVENT_RESTORE, "restore" }, \
+		{ PM_EVENT_RECOVER, "recover" })
+
 DEFINE_EVENT(cpu, cpu_frequency,
 
 	TP_PROTO(unsigned int frequency, unsigned int cpu_id),
@@ -97,58 +111,76 @@ DEFINE_EVENT(cpu, cpu_frequency,
 	TP_ARGS(frequency, cpu_id)
 );
 
-TRACE_EVENT(machine_suspend,
+TRACE_EVENT(device_pm_callback_start,
 
-	TP_PROTO(unsigned int state),
+	TP_PROTO(struct device *dev, const char *pm_ops, int event),
 
-	TP_ARGS(state),
+	TP_ARGS(dev, pm_ops, event),
 
 	TP_STRUCT__entry(
-		__field(	u32,		state		)
+		__string(device, dev_name(dev))
+		__string(driver, dev_driver_string(dev))
+		__string(parent, dev->parent ? dev_name(dev->parent) : "none")
+		__string(pm_ops, pm_ops ? pm_ops : "none ")
+		__field(int, event)
 	),
 
 	TP_fast_assign(
-		__entry->state = state;
+		__assign_str(device, dev_name(dev));
+		__assign_str(driver, dev_driver_string(dev));
+		__assign_str(parent,
+			dev->parent ? dev_name(dev->parent) : "none");
+		__assign_str(pm_ops, pm_ops ? pm_ops : "none ");
+		__entry->event = event;
 	),
 
-	TP_printk("state=%lu", (unsigned long)__entry->state)
+	TP_printk("%s %s, parent: %s, %s[%s]", __get_str(driver),
+		__get_str(device), __get_str(parent), __get_str(pm_ops),
+		pm_verb_symbolic(__entry->event))
 );
 
-TRACE_EVENT(device_pm_report_time,
+TRACE_EVENT(device_pm_callback_end,
 
-	TP_PROTO(struct device *dev, const char *pm_ops, s64 ops_time,
-		 char *pm_event_str, int error),
+	TP_PROTO(struct device *dev, int error),
 
-	TP_ARGS(dev, pm_ops, ops_time, pm_event_str, error),
+	TP_ARGS(dev, error),
 
 	TP_STRUCT__entry(
 		__string(device, dev_name(dev))
 		__string(driver, dev_driver_string(dev))
-		__string(parent, dev->parent ? dev_name(dev->parent) : "none")
-		__string(pm_ops, pm_ops ? pm_ops : "none ")
-		__string(pm_event_str, pm_event_str)
-		__field(s64, ops_time)
 		__field(int, error)
 	),
 
 	TP_fast_assign(
-		const char *tmp = dev->parent ? dev_name(dev->parent) : "none";
-		const char *tmp_i = pm_ops ? pm_ops : "none ";
-
 		__assign_str(device, dev_name(dev));
 		__assign_str(driver, dev_driver_string(dev));
-		__assign_str(parent, tmp);
-		__assign_str(pm_ops, tmp_i);
-		__assign_str(pm_event_str, pm_event_str);
-		__entry->ops_time = ops_time;
 		__entry->error = error;
 	),
 
-	/* ops_str has an extra space at the end */
-	TP_printk("%s %s parent=%s state=%s ops=%snsecs=%lld err=%d",
-		__get_str(driver), __get_str(device), __get_str(parent),
-		__get_str(pm_event_str), __get_str(pm_ops),
-		__entry->ops_time, __entry->error)
+	TP_printk("%s %s, err=%d",
+		__get_str(driver), __get_str(device), __entry->error)
+);
+
+TRACE_EVENT(suspend_resume,
+
+	TP_PROTO(const char *action, int val, bool start),
+
+	TP_ARGS(action, val, start),
+
+	TP_STRUCT__entry(
+		__field(const char *, action)
+		__field(int, val)
+		__field(bool, start)
+	),
+
+	TP_fast_assign(
+		__entry->action = action;
+		__entry->val = val;
+		__entry->start = start;
+	),
+
+	TP_printk("%s[%u] %s", __entry->action, (unsigned int)__entry->val,
+		(__entry->start)?"begin":"end")
 );
 
 DECLARE_EVENT_CLASS(wakeup_source,
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 67e1bbf8369..0a68d5ae584 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -530,6 +530,26 @@ TRACE_EVENT(sched_swap_numa,
 			__entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid,
 			__entry->dst_cpu, __entry->dst_nid)
 );
+
+/*
+ * Tracepoint for waking a polling cpu without an IPI.
+ */
+TRACE_EVENT(sched_wake_idle_without_ipi,
+
+	TP_PROTO(int cpu),
+
+	TP_ARGS(cpu),
+
+	TP_STRUCT__entry(
+		__field(	int,	cpu	)
+	),
+
+	TP_fast_assign(
+		__entry->cpu	= cpu;
+	),
+
+	TP_printk("cpu=%d", __entry->cpu)
+);
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 0a1a4f7caf0..26b4f2e1327 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -44,6 +44,12 @@
 #undef __field_ext
 #define __field_ext(type, item, filter_type)	type	item;
 
+#undef __field_struct
+#define __field_struct(type, item)	type	item;
+
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)	type	item;
+
 #undef __array
 #define __array(type, item, len)	type	item[len];
 
@@ -53,6 +59,9 @@
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
 
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1)
+
 #undef TP_STRUCT__entry
 #define TP_STRUCT__entry(args...) args
 
@@ -119,6 +128,12 @@
 #undef __field_ext
 #define __field_ext(type, item, filter_type)
 
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)
+
 #undef __array
 #define __array(type, item, len)
 
@@ -128,6 +143,9 @@
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
 
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 	struct ftrace_data_offsets_##call {				\
@@ -197,9 +215,22 @@
 #define __get_dynamic_array(field)	\
 		((void *)__entry + (__entry->__data_loc_##field & 0xffff))
 
+#undef __get_dynamic_array_len
+#define __get_dynamic_array_len(field)	\
+		((__entry->__data_loc_##field >> 16) & 0xffff)
+
 #undef __get_str
 #define __get_str(field) (char *)__get_dynamic_array(field)
 
+#undef __get_bitmask
+#define __get_bitmask(field)						\
+	({								\
+		void *__bitmask = __get_dynamic_array(field);		\
+		unsigned int __bitmask_size;				\
+		__bitmask_size = __get_dynamic_array_len(field);	\
+		ftrace_print_bitmask_seq(p, __bitmask, __bitmask_size);	\
+	})
+
 #undef __print_flags
 #define __print_flags(flag, delim, flag_array...)			\
 	({								\
@@ -296,9 +327,21 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 	if (ret)							\
 		return ret;
 
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)			\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item),			\
+				 0, filter_type);			\
+	if (ret)							\
+		return ret;
+
 #undef __field
 #define __field(type, item)	__field_ext(type, item, FILTER_OTHER)
 
+#undef __field_struct
+#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER)
+
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
@@ -322,6 +365,9 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
 
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
 static int notrace __init						\
@@ -357,6 +403,12 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 #undef __field_ext
 #define __field_ext(type, item, filter_type)
 
+#undef __field_struct
+#define __field_struct(type, item)
+
+#undef __field_struct_ext
+#define __field_struct_ext(type, item, filter_type)
+
 #undef __array
 #define __array(type, item, len)
 
@@ -372,6 +424,29 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 #define __string(item, src) __dynamic_array(char, item,			\
 		    strlen((src) ? (const char *)(src) : "(null)") + 1)
 
+/*
+ * __bitmask_size_in_bytes_raw is the number of bytes needed to hold
+ * num_possible_cpus().
+ */
+#define __bitmask_size_in_bytes_raw(nr_bits)	\
+	(((nr_bits) + 7) / 8)
+
+#define __bitmask_size_in_longs(nr_bits)			\
+	((__bitmask_size_in_bytes_raw(nr_bits) +		\
+	  ((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8))
+
+/*
+ * __bitmask_size_in_bytes is the number of bytes needed to hold
+ * num_possible_cpus() padded out to the nearest long. This is what
+ * is saved in the buffer, just to be consistent.
+ */
+#define __bitmask_size_in_bytes(nr_bits)				\
+	(__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8))
+
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item,	\
+					 __bitmask_size_in_longs(nr_bits))
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static inline notrace int ftrace_get_offsets_##call(			\
@@ -505,6 +580,9 @@ static inline notrace int ftrace_get_offsets_##call(			\
 #undef __field
 #define __field(type, item)
 
+#undef __field_struct
+#define __field_struct(type, item)
+
 #undef __array
 #define __array(type, item, len)
 
@@ -513,12 +591,22 @@ static inline notrace int ftrace_get_offsets_##call(			\
 	__entry->__data_loc_##item = __data_offsets.item;
 
 #undef __string
-#define __string(item, src) __dynamic_array(char, item, -1)       	\
+#define __string(item, src) __dynamic_array(char, item, -1)
 
 #undef __assign_str
 #define __assign_str(dst, src)						\
 	strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
 
+#undef __bitmask
+#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
+
+#undef __get_bitmask
+#define __get_bitmask(field) (char *)__get_dynamic_array(field)
+
+#undef __assign_bitmask
+#define __assign_bitmask(dst, src, nr_bits)					\
+	memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
+
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args
 
@@ -585,7 +673,9 @@ static inline void ftrace_test_probe_##call(void)			\
 #undef __print_symbolic
 #undef __print_hex
 #undef __get_dynamic_array
+#undef __get_dynamic_array_len
 #undef __get_str
+#undef __get_bitmask
 
 #undef TP_printk
 #define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
@@ -648,9 +738,16 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 #define __get_dynamic_array(field)	\
 		((void *)__entry + (__entry->__data_loc_##field & 0xffff))
 
+#undef __get_dynamic_array_len
+#define __get_dynamic_array_len(field)	\
+		((__entry->__data_loc_##field >> 16) & 0xffff)
+
 #undef __get_str
 #define __get_str(field) (char *)__get_dynamic_array(field)
 
+#undef __get_bitmask
+#define __get_bitmask(field) (char *)__get_dynamic_array(field)
+
 #undef __perf_addr
 #define __perf_addr(a)	(__addr = (a))
 
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index fed853f3d7a..9674145e2f6 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -4,6 +4,7 @@
 #include <linux/tracepoint.h>
 #include <linux/unistd.h>
 #include <linux/ftrace_event.h>
+#include <linux/thread_info.h>
 
 #include <asm/ptrace.h>
 
@@ -32,4 +33,18 @@ struct syscall_metadata {
 	struct ftrace_event_call *exit_event;
 };
 
+#if defined(CONFIG_TRACEPOINTS) && defined(CONFIG_HAVE_SYSCALL_TRACEPOINTS)
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+		set_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+	else
+		clear_tsk_thread_flag(p, TIF_SYSCALL_TRACEPOINT);
+}
+#else
+static inline void syscall_tracepoint_update(struct task_struct *p)
+{
+}
+#endif
+
 #endif /* _TRACE_SYSCALL_H */
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index f104c2603eb..def54f9e07c 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -181,6 +181,7 @@ struct drm_mode_get_plane_res {
 #define DRM_MODE_ENCODER_TVDAC	4
 #define DRM_MODE_ENCODER_VIRTUAL 5
 #define DRM_MODE_ENCODER_DSI	6
+#define DRM_MODE_ENCODER_DPMST	7
 
 struct drm_mode_get_encoder {
 	__u32 encoder_id;
@@ -251,6 +252,21 @@ struct drm_mode_get_connector {
 #define DRM_MODE_PROP_BLOB	(1<<4)
 #define DRM_MODE_PROP_BITMASK	(1<<5) /* bitmask of enumerated types */
 
+/* non-extended types: legacy bitmask, one bit per type: */
+#define DRM_MODE_PROP_LEGACY_TYPE  ( \
+		DRM_MODE_PROP_RANGE | \
+		DRM_MODE_PROP_ENUM | \
+		DRM_MODE_PROP_BLOB | \
+		DRM_MODE_PROP_BITMASK)
+
+/* extended-types: rather than continue to consume a bit per type,
+ * grab a chunk of the bits to use as integer type id.
+ */
+#define DRM_MODE_PROP_EXTENDED_TYPE	0x0000ffc0
+#define DRM_MODE_PROP_TYPE(n)		((n) << 6)
+#define DRM_MODE_PROP_OBJECT		DRM_MODE_PROP_TYPE(1)
+#define DRM_MODE_PROP_SIGNED_RANGE	DRM_MODE_PROP_TYPE(2)
+
 struct drm_mode_property_enum {
 	__u64 value;
 	char name[DRM_PROP_NAME_LEN];
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 126bfaa8bb6..ff57f07c324 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -223,6 +223,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_GEM_GET_CACHING	0x30
 #define DRM_I915_REG_READ		0x31
 #define DRM_I915_GET_RESET_STATS	0x32
+#define DRM_I915_GEM_USERPTR		0x33
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -273,6 +274,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy)
 #define DRM_IOCTL_I915_REG_READ			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read)
 #define DRM_IOCTL_I915_GET_RESET_STATS		DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats)
+#define DRM_IOCTL_I915_GEM_USERPTR			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -337,6 +339,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_EXEC_NO_RELOC	 25
 #define I915_PARAM_HAS_EXEC_HANDLE_LUT   26
 #define I915_PARAM_HAS_WT     	 	 27
+#define I915_PARAM_CMD_PARSER_VERSION	 28
 
 typedef struct drm_i915_getparam {
 	int param;
@@ -1049,4 +1052,18 @@ struct drm_i915_reset_stats {
 	__u32 pad;
 };
 
+struct drm_i915_gem_userptr {
+	__u64 user_ptr;
+	__u64 user_size;
+	__u32 flags;
+#define I915_USERPTR_READ_ONLY 0x1
+#define I915_USERPTR_UNSYNCHRONIZED 0x80000000
+	/**
+	 * Returned handle for the object.
+	 *
+	 * Object handles are nonzero.
+	 */
+	__u32 handle;
+};
+
 #endif /* _UAPI_I915_DRM_H_ */
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index aefa2f6afa3..1cc0b610f16 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -1007,7 +1007,7 @@ struct drm_radeon_cs {
 #define RADEON_INFO_NUM_BYTES_MOVED	0x1d
 #define RADEON_INFO_VRAM_USAGE		0x1e
 #define RADEON_INFO_GTT_USAGE		0x1f
-
+#define RADEON_INFO_ACTIVE_CU_COUNT	0x20
 
 struct drm_radeon_info {
 	uint32_t		request;
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 4c31a366be1..3b9ff33e176 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -342,6 +342,7 @@ enum {
 #define __AUDIT_ARCH_64BIT 0x80000000
 #define __AUDIT_ARCH_LE	   0x40000000
 
+#define AUDIT_ARCH_AARCH64	(EM_AARCH64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_ALPHA	(EM_ALPHA|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_ARM		(EM_ARM|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_ARMEB	(EM_ARM)
@@ -385,6 +386,14 @@ enum {
  */
 #define AUDIT_MESSAGE_TEXT_MAX	8560
 
+/* Multicast Netlink socket groups (default up to 32) */
+enum audit_nlgrps {
+	AUDIT_NLGRP_NONE,	/* Group 0 not used */
+	AUDIT_NLGRP_READLOG,	/* "best effort" read only socket */
+	__AUDIT_NLGRP_MAX
+};
+#define AUDIT_NLGRP_MAX                (__AUDIT_NLGRP_MAX - 1)
+
 struct audit_status {
 	__u32		mask;		/* Bit mask for valid entries */
 	__u32		enabled;	/* 1 = enabled, 0 = disabled */
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index b4d69092fbd..2f47824e7a3 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -38,6 +38,7 @@ struct btrfs_ioctl_vol_args {
 #define BTRFS_SUBVOL_QGROUP_INHERIT	(1ULL << 2)
 #define BTRFS_FSID_SIZE 16
 #define BTRFS_UUID_SIZE 16
+#define BTRFS_UUID_UNPARSED_SIZE	37
 
 #define BTRFS_QGROUP_INHERIT_SET_LIMITS	(1ULL << 0)
 
@@ -181,7 +182,11 @@ struct btrfs_ioctl_fs_info_args {
 	__u64 max_id;				/* out */
 	__u64 num_devices;			/* out */
 	__u8 fsid[BTRFS_FSID_SIZE];		/* out */
-	__u64 reserved[124];			/* pad to 1k */
+	__u32 nodesize;				/* out */
+	__u32 sectorsize;			/* out */
+	__u32 clone_alignment;			/* out */
+	__u32 reserved32;
+	__u64 reserved[122];			/* pad to 1k */
 };
 
 struct btrfs_ioctl_feature_flags {
@@ -211,7 +216,8 @@ struct btrfs_balance_args {
 
 	__u64 flags;
 
-	__u64 unused[8];
+	__u64 limit;		/* limit number of processed chunks */
+	__u64 unused[7];
 } __attribute__ ((__packed__));
 
 /* report balance progress to userspace */
@@ -301,6 +307,14 @@ struct btrfs_ioctl_search_args {
 	char buf[BTRFS_SEARCH_ARGS_BUFSIZE];
 };
 
+struct btrfs_ioctl_search_args_v2 {
+	struct btrfs_ioctl_search_key key; /* in/out - search parameters */
+	__u64 buf_size;		   /* in - size of buffer
+					    * out - on EOVERFLOW: needed size
+					    *       to store item */
+	__u64 buf[0];                       /* out - found items */
+};
+
 struct btrfs_ioctl_clone_range_args {
   __s64 src_fd;
   __u64 src_offset, src_length;
@@ -553,6 +567,8 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code)
 				struct btrfs_ioctl_defrag_range_args)
 #define BTRFS_IOC_TREE_SEARCH _IOWR(BTRFS_IOCTL_MAGIC, 17, \
 				   struct btrfs_ioctl_search_args)
+#define BTRFS_IOC_TREE_SEARCH_V2 _IOWR(BTRFS_IOCTL_MAGIC, 17, \
+					   struct btrfs_ioctl_search_args_v2)
 #define BTRFS_IOC_INO_LOOKUP _IOWR(BTRFS_IOCTL_MAGIC, 18, \
 				   struct btrfs_ioctl_ino_lookup_args)
 #define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, __u64)
diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index 5d9d1d14071..41892f72005 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -42,8 +42,8 @@
  * DAMAGE.
  */
 
-#ifndef CAN_H
-#define CAN_H
+#ifndef _UAPI_CAN_H
+#define _UAPI_CAN_H
 
 #include <linux/types.h>
 #include <linux/socket.h>
@@ -191,4 +191,4 @@ struct can_filter {
 
 #define CAN_INV_FILTER 0x20000000U /* to be set in can_filter.can_id */
 
-#endif /* CAN_H */
+#endif /* !_UAPI_CAN_H */
diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h
index 382251a1d21..89ddb9dc9bd 100644
--- a/include/uapi/linux/can/bcm.h
+++ b/include/uapi/linux/can/bcm.h
@@ -41,8 +41,8 @@
  * DAMAGE.
  */
 
-#ifndef CAN_BCM_H
-#define CAN_BCM_H
+#ifndef _UAPI_CAN_BCM_H
+#define _UAPI_CAN_BCM_H
 
 #include <linux/types.h>
 #include <linux/can.h>
@@ -95,4 +95,4 @@ enum {
 #define TX_RESET_MULTI_IDX  0x0200
 #define RX_RTR_FRAME        0x0400
 
-#endif /* CAN_BCM_H */
+#endif /* !_UAPI_CAN_BCM_H */
diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h
index b6320454532..c247446ab25 100644
--- a/include/uapi/linux/can/error.h
+++ b/include/uapi/linux/can/error.h
@@ -41,8 +41,8 @@
  * DAMAGE.
  */
 
-#ifndef CAN_ERROR_H
-#define CAN_ERROR_H
+#ifndef _UAPI_CAN_ERROR_H
+#define _UAPI_CAN_ERROR_H
 
 #define CAN_ERR_DLC 8 /* dlc for error message frames */
 
@@ -120,4 +120,4 @@
 
 /* controller specific additional information / data[5..7] */
 
-#endif /* CAN_ERROR_H */
+#endif /* _UAPI_CAN_ERROR_H */
diff --git a/include/uapi/linux/can/gw.h b/include/uapi/linux/can/gw.h
index 844c8964bdf..3e6184cf2f6 100644
--- a/include/uapi/linux/can/gw.h
+++ b/include/uapi/linux/can/gw.h
@@ -41,8 +41,8 @@
  * DAMAGE.
  */
 
-#ifndef CAN_GW_H
-#define CAN_GW_H
+#ifndef _UAPI_CAN_GW_H
+#define _UAPI_CAN_GW_H
 
 #include <linux/types.h>
 #include <linux/can.h>
@@ -200,4 +200,4 @@ enum {
  *         Beware of sending unpacked or aligned structs!
  */
 
-#endif
+#endif /* !_UAPI_CAN_GW_H */
diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h
index 7e2e1863db1..813d11f5497 100644
--- a/include/uapi/linux/can/netlink.h
+++ b/include/uapi/linux/can/netlink.h
@@ -15,8 +15,8 @@
  * GNU General Public License for more details.
  */
 
-#ifndef CAN_NETLINK_H
-#define CAN_NETLINK_H
+#ifndef _UAPI_CAN_NETLINK_H
+#define _UAPI_CAN_NETLINK_H
 
 #include <linux/types.h>
 
@@ -130,4 +130,4 @@ enum {
 
 #define IFLA_CAN_MAX	(__IFLA_CAN_MAX - 1)
 
-#endif /* CAN_NETLINK_H */
+#endif /* !_UAPI_CAN_NETLINK_H */
diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h
index c7d8c334e0c..78ec76fd89a 100644
--- a/include/uapi/linux/can/raw.h
+++ b/include/uapi/linux/can/raw.h
@@ -42,8 +42,8 @@
  * DAMAGE.
  */
 
-#ifndef CAN_RAW_H
-#define CAN_RAW_H
+#ifndef _UAPI_CAN_RAW_H
+#define _UAPI_CAN_RAW_H
 
 #include <linux/can.h>
 
@@ -59,4 +59,4 @@ enum {
 	CAN_RAW_FD_FRAMES,	/* allow CAN FD frames (default:off) */
 };
 
-#endif
+#endif /* !_UAPI_CAN_RAW_H */
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 154dd6d3c8f..12c37a197d2 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -347,7 +347,12 @@ struct vfs_cap_data {
 
 #define CAP_BLOCK_SUSPEND    36
 
-#define CAP_LAST_CAP         CAP_BLOCK_SUSPEND
+/* Allow reading the audit log via multicast netlink socket */
+
+#define CAP_AUDIT_READ		37
+
+
+#define CAP_LAST_CAP         CAP_AUDIT_READ
 
 #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
 
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index fd161e91b6d..e3c7a719c76 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -847,6 +847,38 @@ struct ethtool_rxfh_indir {
 };
 
 /**
+ * struct ethtool_rxfh - command to get/set RX flow hash indir or/and hash key.
+ * @cmd: Specific command number - %ETHTOOL_GRSSH or %ETHTOOL_SRSSH
+ * @rss_context: RSS context identifier.
+ * @indir_size: On entry, the array size of the user buffer for the
+ *	indirection table, which may be zero, or (for %ETHTOOL_SRSSH),
+ *	%ETH_RXFH_INDIR_NO_CHANGE.  On return from %ETHTOOL_GRSSH,
+ *	the array size of the hardware indirection table.
+ * @key_size: On entry, the array size of the user buffer for the hash key,
+ *	which may be zero.  On return from %ETHTOOL_GRSSH, the size of the
+ *	hardware hash key.
+ * @rsvd:	Reserved for future extensions.
+ * @rss_config: RX ring/queue index for each hash value i.e., indirection table
+ *	of @indir_size __u32 elements, followed by hash key of @key_size
+ *	bytes.
+ *
+ * For %ETHTOOL_GRSSH, a @indir_size and key_size of zero means that only the
+ * size should be returned.  For %ETHTOOL_SRSSH, an @indir_size of
+ * %ETH_RXFH_INDIR_NO_CHANGE means that indir table setting is not requested
+ * and a @indir_size of zero means the indir table should be reset to default
+ * values.
+ */
+struct ethtool_rxfh {
+	__u32   cmd;
+	__u32	rss_context;
+	__u32   indir_size;
+	__u32   key_size;
+	__u32	rsvd[2];
+	__u32   rss_config[0];
+};
+#define ETH_RXFH_INDIR_NO_CHANGE	0xffffffff
+
+/**
  * struct ethtool_rx_ntuple_flow_spec - specification for RX flow filter
  * @flow_type: Type of match to perform, e.g. %TCP_V4_FLOW
  * @h_u: Flow field values to match (dependent on @flow_type)
@@ -1118,6 +1150,9 @@ enum ethtool_sfeatures_retval_bits {
 #define ETHTOOL_GEEE		0x00000044 /* Get EEE settings */
 #define ETHTOOL_SEEE		0x00000045 /* Set EEE settings */
 
+#define ETHTOOL_GRSSH		0x00000046 /* Get RX flow hash configuration */
+#define ETHTOOL_SRSSH		0x00000047 /* Set RX flow hash configuration */
+
 /* compatibility with older code */
 #define SPARC_ETH_GSET		ETHTOOL_GSET
 #define SPARC_ETH_SSET		ETHTOOL_SSET
diff --git a/include/uapi/linux/filter.h b/include/uapi/linux/filter.h
index 8eb9ccaa5b4..253b4d42cf2 100644
--- a/include/uapi/linux/filter.h
+++ b/include/uapi/linux/filter.h
@@ -130,7 +130,8 @@ struct sock_fprog {	/* Required for SO_ATTACH_FILTER. */
 #define SKF_AD_VLAN_TAG	44
 #define SKF_AD_VLAN_TAG_PRESENT 48
 #define SKF_AD_PAY_OFFSET	52
-#define SKF_AD_MAX	56
+#define SKF_AD_RANDOM	56
+#define SKF_AD_MAX	60
 #define SKF_NET_OFF   (-0x100000)
 #define SKF_LL_OFF    (-0x200000)
 
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 40b5ca8a1b1..25084a052a1 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -101,6 +101,7 @@
  *  - add FATTR_CTIME
  *  - add ctime and ctimensec to fuse_setattr_in
  *  - add FUSE_RENAME2 request
+ *  - add FUSE_NO_OPEN_SUPPORT flag
  */
 
 #ifndef _LINUX_FUSE_H
@@ -229,6 +230,7 @@ struct fuse_file_lock {
  * FUSE_READDIRPLUS_AUTO: adaptive readdirplus
  * FUSE_ASYNC_DIO: asynchronous direct I/O submission
  * FUSE_WRITEBACK_CACHE: use writeback cache for buffered writes
+ * FUSE_NO_OPEN_SUPPORT: kernel supports zero-message opens
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -247,6 +249,7 @@ struct fuse_file_lock {
 #define FUSE_READDIRPLUS_AUTO	(1 << 14)
 #define FUSE_ASYNC_DIO		(1 << 15)
 #define FUSE_WRITEBACK_CACHE	(1 << 16)
+#define FUSE_NO_OPEN_SUPPORT	(1 << 17)
 
 /**
  * CUSE INIT request/reply flags
diff --git a/include/uapi/linux/if_fddi.h b/include/uapi/linux/if_fddi.h
index 0d36909c3ae..1086cd9f675 100644
--- a/include/uapi/linux/if_fddi.h
+++ b/include/uapi/linux/if_fddi.h
@@ -30,74 +30,76 @@
  *  Define max and min legal sizes.  The frame sizes do not include
  *  4 byte FCS/CRC (frame check sequence).
  */
-#define FDDI_K_ALEN			6		/* Octets in one FDDI address */
-#define FDDI_K_8022_HLEN	16		/* Total octets in 802.2 header */
-#define FDDI_K_SNAP_HLEN	21		/* Total octets in 802.2 SNAP header */
-#define FDDI_K_8022_ZLEN	16		/* Min octets in 802.2 frame sans FCS */
-#define FDDI_K_SNAP_ZLEN	21		/* Min octets in 802.2 SNAP frame sans FCS */
+#define FDDI_K_ALEN		6	/* Octets in one FDDI address */
+#define FDDI_K_8022_HLEN	16	/* Total octets in 802.2 header */
+#define FDDI_K_SNAP_HLEN	21	/* Total octets in 802.2 SNAP header */
+#define FDDI_K_8022_ZLEN	16	/* Min octets in 802.2 frame sans
+					   FCS */
+#define FDDI_K_SNAP_ZLEN	21	/* Min octets in 802.2 SNAP frame sans
+					   FCS */
 #define FDDI_K_8022_DLEN	4475	/* Max octets in 802.2 payload */
 #define FDDI_K_SNAP_DLEN	4470	/* Max octets in 802.2 SNAP payload */
-#define FDDI_K_LLC_ZLEN		13		/* Min octets in LLC frame sans FCS */
+#define FDDI_K_LLC_ZLEN		13	/* Min octets in LLC frame sans FCS */
 #define FDDI_K_LLC_LEN		4491	/* Max octets in LLC frame sans FCS */
+#define FDDI_K_OUI_LEN		3	/* Octets in OUI in 802.2 SNAP
+					   header */
 
 /* Define FDDI Frame Control (FC) Byte values */
-#define FDDI_FC_K_VOID					0x00	
-#define FDDI_FC_K_NON_RESTRICTED_TOKEN	0x80	
-#define FDDI_FC_K_RESTRICTED_TOKEN		0xC0	
-#define FDDI_FC_K_SMT_MIN				0x41
-#define FDDI_FC_K_SMT_MAX		   		0x4F
-#define FDDI_FC_K_MAC_MIN				0xC1
-#define FDDI_FC_K_MAC_MAX		  		0xCF	
-#define FDDI_FC_K_ASYNC_LLC_MIN			0x50
-#define FDDI_FC_K_ASYNC_LLC_DEF			0x54
-#define FDDI_FC_K_ASYNC_LLC_MAX			0x5F
-#define FDDI_FC_K_SYNC_LLC_MIN			0xD0
-#define FDDI_FC_K_SYNC_LLC_MAX			0xD7
-#define FDDI_FC_K_IMPLEMENTOR_MIN		0x60
-#define FDDI_FC_K_IMPLEMENTOR_MAX  		0x6F
-#define FDDI_FC_K_RESERVED_MIN			0x70
-#define FDDI_FC_K_RESERVED_MAX			0x7F
+#define FDDI_FC_K_VOID			0x00
+#define FDDI_FC_K_NON_RESTRICTED_TOKEN	0x80
+#define FDDI_FC_K_RESTRICTED_TOKEN	0xC0
+#define FDDI_FC_K_SMT_MIN		0x41
+#define FDDI_FC_K_SMT_MAX		0x4F
+#define FDDI_FC_K_MAC_MIN		0xC1
+#define FDDI_FC_K_MAC_MAX		0xCF
+#define FDDI_FC_K_ASYNC_LLC_MIN		0x50
+#define FDDI_FC_K_ASYNC_LLC_DEF		0x54
+#define FDDI_FC_K_ASYNC_LLC_MAX		0x5F
+#define FDDI_FC_K_SYNC_LLC_MIN		0xD0
+#define FDDI_FC_K_SYNC_LLC_MAX		0xD7
+#define FDDI_FC_K_IMPLEMENTOR_MIN	0x60
+#define FDDI_FC_K_IMPLEMENTOR_MAX	0x6F
+#define FDDI_FC_K_RESERVED_MIN		0x70
+#define FDDI_FC_K_RESERVED_MAX		0x7F
 
 /* Define LLC and SNAP constants */
-#define FDDI_EXTENDED_SAP	0xAA
+#define FDDI_EXTENDED_SAP		0xAA
 #define FDDI_UI_CMD			0x03
 
 /* Define 802.2 Type 1 header */
 struct fddi_8022_1_hdr {
-	__u8	dsap;					/* destination service access point */
-	__u8	ssap;					/* source service access point */
-	__u8	ctrl;					/* control byte #1 */
+	__u8	dsap;			/* destination service access point */
+	__u8	ssap;			/* source service access point */
+	__u8	ctrl;			/* control byte #1 */
 } __attribute__((packed));
 
 /* Define 802.2 Type 2 header */
 struct fddi_8022_2_hdr {
-	__u8	dsap;					/* destination service access point */
-	__u8	ssap;					/* source service access point */
-	__u8	ctrl_1;					/* control byte #1 */
-	__u8	ctrl_2;					/* control byte #2 */
+	__u8	dsap;			/* destination service access point */
+	__u8	ssap;			/* source service access point */
+	__u8	ctrl_1;			/* control byte #1 */
+	__u8	ctrl_2;			/* control byte #2 */
 } __attribute__((packed));
 
 /* Define 802.2 SNAP header */
-#define FDDI_K_OUI_LEN	3
 struct fddi_snap_hdr {
-	__u8	dsap;					/* always 0xAA */
-	__u8	ssap;					/* always 0xAA */
-	__u8	ctrl;					/* always 0x03 */
+	__u8	dsap;			/* always 0xAA */
+	__u8	ssap;			/* always 0xAA */
+	__u8	ctrl;			/* always 0x03 */
 	__u8	oui[FDDI_K_OUI_LEN];	/* organizational universal id */
-	__be16	ethertype;				/* packet type ID field */
+	__be16	ethertype;		/* packet type ID field */
 } __attribute__((packed));
 
 /* Define FDDI LLC frame header */
 struct fddihdr {
-	__u8	fc;						/* frame control */
-	__u8	daddr[FDDI_K_ALEN];		/* destination address */
-	__u8	saddr[FDDI_K_ALEN];		/* source address */
-	union
-		{
-		struct fddi_8022_1_hdr		llc_8022_1;
-		struct fddi_8022_2_hdr		llc_8022_2;
-		struct fddi_snap_hdr		llc_snap;
-		} hdr;
+	__u8	fc;			/* frame control */
+	__u8	daddr[FDDI_K_ALEN];	/* destination address */
+	__u8	saddr[FDDI_K_ALEN];	/* source address */
+	union {
+		struct fddi_8022_1_hdr	llc_8022_1;
+		struct fddi_8022_2_hdr	llc_8022_2;
+		struct fddi_snap_hdr	llc_snap;
+	} hdr;
 } __attribute__((packed));
 
 
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 9a7f7ace664..b38534895db 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -319,6 +319,9 @@ enum {
 	IFLA_VXLAN_PORT,	/* destination port */
 	IFLA_VXLAN_GROUP6,
 	IFLA_VXLAN_LOCAL6,
+	IFLA_VXLAN_UDP_CSUM,
+	IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
+	IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
 	__IFLA_VXLAN_MAX
 };
 #define IFLA_VXLAN_MAX	(__IFLA_VXLAN_MAX - 1)
@@ -399,9 +402,10 @@ enum {
 	IFLA_VF_UNSPEC,
 	IFLA_VF_MAC,		/* Hardware queue specific attributes */
 	IFLA_VF_VLAN,
-	IFLA_VF_TX_RATE,	/* TX Bandwidth Allocation */
+	IFLA_VF_TX_RATE,	/* Max TX Bandwidth Allocation */
 	IFLA_VF_SPOOFCHK,	/* Spoof Checking on/off switch */
 	IFLA_VF_LINK_STATE,	/* link state enable/disable/auto switch */
+	IFLA_VF_RATE,		/* Min and Max TX Bandwidth Allocation */
 	__IFLA_VF_MAX,
 };
 
@@ -423,6 +427,12 @@ struct ifla_vf_tx_rate {
 	__u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */
 };
 
+struct ifla_vf_rate {
+	__u32 vf;
+	__u32 min_tx_rate; /* Min Bandwidth in Mbps */
+	__u32 max_tx_rate; /* Max Bandwidth in Mbps */
+};
+
 struct ifla_vf_spoofchk {
 	__u32 vf;
 	__u32 setting;
diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h
index aee73d0611f..3bce9e9d9f7 100644
--- a/include/uapi/linux/if_tunnel.h
+++ b/include/uapi/linux/if_tunnel.h
@@ -100,7 +100,7 @@ enum {
 #define IFLA_GRE_MAX	(__IFLA_GRE_MAX - 1)
 
 /* VTI-mode i_flags */
-#define VTI_ISVTI 0x0001
+#define VTI_ISVTI ((__force __be16)0x0001)
 
 enum {
 	IFLA_VTI_UNSPEC,
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e11d8f170a6..9b744af871d 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -399,13 +399,18 @@ struct kvm_vapic_addr {
 	__u64 vapic_addr;
 };
 
-/* for KVM_SET_MPSTATE */
+/* for KVM_SET_MP_STATE */
 
+/* not all states are valid on all architectures */
 #define KVM_MP_STATE_RUNNABLE          0
 #define KVM_MP_STATE_UNINITIALIZED     1
 #define KVM_MP_STATE_INIT_RECEIVED     2
 #define KVM_MP_STATE_HALTED            3
 #define KVM_MP_STATE_SIPI_RECEIVED     4
+#define KVM_MP_STATE_STOPPED           5
+#define KVM_MP_STATE_CHECK_STOP        6
+#define KVM_MP_STATE_OPERATING         7
+#define KVM_MP_STATE_LOAD              8
 
 struct kvm_mp_state {
 	__u32 mp_state;
diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h
index 2841f86eae0..bf6cd7d5cac 100644
--- a/include/uapi/linux/kvm_para.h
+++ b/include/uapi/linux/kvm_para.h
@@ -20,6 +20,9 @@
 #define KVM_HC_FEATURES			3
 #define KVM_HC_PPC_MAP_MAGIC_PAGE	4
 #define KVM_HC_KICK_CPU			5
+#define KVM_HC_MIPS_GET_CLOCK_FREQ	6
+#define KVM_HC_MIPS_EXIT_VM		7
+#define KVM_HC_MIPS_CONSOLE_OUTPUT	8
 
 /*
  * hypercalls use architecture specific
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 8adb6816032..21caa2631c2 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -124,6 +124,8 @@ enum {
 	L2TP_ATTR_STATS,		/* nested */
 	L2TP_ATTR_IP6_SADDR,		/* struct in6_addr */
 	L2TP_ATTR_IP6_DADDR,		/* struct in6_addr */
+	L2TP_ATTR_UDP_ZERO_CSUM6_TX,	/* u8 */
+	L2TP_ATTR_UDP_ZERO_CSUM6_RX,	/* u8 */
 	__L2TP_ATTR_MAX,
 };
 
diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h
index d3ef583104e..4a1d7e96dfe 100644
--- a/include/uapi/linux/neighbour.h
+++ b/include/uapi/linux/neighbour.h
@@ -24,6 +24,7 @@ enum {
 	NDA_PORT,
 	NDA_VNI,
 	NDA_IFINDEX,
+	NDA_MASTER,
 	__NDA_MAX
 };
 
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index c88ccbfda5f..2a88f645a5d 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -212,6 +212,29 @@ enum nft_set_flags {
 };
 
 /**
+ * enum nft_set_policies - set selection policy
+ *
+ * @NFT_SET_POL_PERFORMANCE: prefer high performance over low memory use
+ * @NFT_SET_POL_MEMORY: prefer low memory use over high performance
+ */
+enum nft_set_policies {
+	NFT_SET_POL_PERFORMANCE,
+	NFT_SET_POL_MEMORY,
+};
+
+/**
+ * enum nft_set_desc_attributes - set element description
+ *
+ * @NFTA_SET_DESC_SIZE: number of elements in set (NLA_U32)
+ */
+enum nft_set_desc_attributes {
+	NFTA_SET_DESC_UNSPEC,
+	NFTA_SET_DESC_SIZE,
+	__NFTA_SET_DESC_MAX
+};
+#define NFTA_SET_DESC_MAX	(__NFTA_SET_DESC_MAX - 1)
+
+/**
  * enum nft_set_attributes - nf_tables set netlink attributes
  *
  * @NFTA_SET_TABLE: table name (NLA_STRING)
@@ -221,6 +244,9 @@ enum nft_set_flags {
  * @NFTA_SET_KEY_LEN: key data length (NLA_U32)
  * @NFTA_SET_DATA_TYPE: mapping data type (NLA_U32)
  * @NFTA_SET_DATA_LEN: mapping data length (NLA_U32)
+ * @NFTA_SET_POLICY: selection policy (NLA_U32)
+ * @NFTA_SET_DESC: set description (NLA_NESTED)
+ * @NFTA_SET_ID: uniquely identifies a set in a transaction (NLA_U32)
  */
 enum nft_set_attributes {
 	NFTA_SET_UNSPEC,
@@ -231,6 +257,9 @@ enum nft_set_attributes {
 	NFTA_SET_KEY_LEN,
 	NFTA_SET_DATA_TYPE,
 	NFTA_SET_DATA_LEN,
+	NFTA_SET_POLICY,
+	NFTA_SET_DESC,
+	NFTA_SET_ID,
 	__NFTA_SET_MAX
 };
 #define NFTA_SET_MAX		(__NFTA_SET_MAX - 1)
@@ -266,12 +295,14 @@ enum nft_set_elem_attributes {
  * @NFTA_SET_ELEM_LIST_TABLE: table of the set to be changed (NLA_STRING)
  * @NFTA_SET_ELEM_LIST_SET: name of the set to be changed (NLA_STRING)
  * @NFTA_SET_ELEM_LIST_ELEMENTS: list of set elements (NLA_NESTED: nft_set_elem_attributes)
+ * @NFTA_SET_ELEM_LIST_SET_ID: uniquely identifies a set in a transaction (NLA_U32)
  */
 enum nft_set_elem_list_attributes {
 	NFTA_SET_ELEM_LIST_UNSPEC,
 	NFTA_SET_ELEM_LIST_TABLE,
 	NFTA_SET_ELEM_LIST_SET,
 	NFTA_SET_ELEM_LIST_ELEMENTS,
+	NFTA_SET_ELEM_LIST_SET_ID,
 	__NFTA_SET_ELEM_LIST_MAX
 };
 #define NFTA_SET_ELEM_LIST_MAX	(__NFTA_SET_ELEM_LIST_MAX - 1)
@@ -457,12 +488,14 @@ enum nft_cmp_attributes {
  * @NFTA_LOOKUP_SET: name of the set where to look for (NLA_STRING)
  * @NFTA_LOOKUP_SREG: source register of the data to look for (NLA_U32: nft_registers)
  * @NFTA_LOOKUP_DREG: destination register (NLA_U32: nft_registers)
+ * @NFTA_LOOKUP_SET_ID: uniquely identifies a set in a transaction (NLA_U32)
  */
 enum nft_lookup_attributes {
 	NFTA_LOOKUP_UNSPEC,
 	NFTA_LOOKUP_SET,
 	NFTA_LOOKUP_SREG,
 	NFTA_LOOKUP_DREG,
+	NFTA_LOOKUP_SET_ID,
 	__NFTA_LOOKUP_MAX
 };
 #define NFTA_LOOKUP_MAX		(__NFTA_LOOKUP_MAX - 1)
@@ -536,6 +569,8 @@ enum nft_exthdr_attributes {
  * @NFT_META_SECMARK: packet secmark (skb->secmark)
  * @NFT_META_NFPROTO: netfilter protocol
  * @NFT_META_L4PROTO: layer 4 protocol number
+ * @NFT_META_BRI_IIFNAME: packet input bridge interface name
+ * @NFT_META_BRI_OIFNAME: packet output bridge interface name
  */
 enum nft_meta_keys {
 	NFT_META_LEN,
@@ -555,6 +590,8 @@ enum nft_meta_keys {
 	NFT_META_SECMARK,
 	NFT_META_NFPROTO,
 	NFT_META_L4PROTO,
+	NFT_META_BRI_IIFNAME,
+	NFT_META_BRI_OIFNAME,
 };
 
 /**
diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h
index 596ddd45253..354a7e5e50f 100644
--- a/include/uapi/linux/netfilter/nfnetlink.h
+++ b/include/uapi/linux/netfilter/nfnetlink.h
@@ -20,6 +20,8 @@ enum nfnetlink_groups {
 #define NFNLGRP_CONNTRACK_EXP_DESTROY	NFNLGRP_CONNTRACK_EXP_DESTROY
 	NFNLGRP_NFTABLES,
 #define NFNLGRP_NFTABLES                NFNLGRP_NFTABLES
+	NFNLGRP_ACCT_QUOTA,
+#define NFNLGRP_ACCT_QUOTA		NFNLGRP_ACCT_QUOTA
 	__NFNLGRP_MAX,
 };
 #define NFNLGRP_MAX	(__NFNLGRP_MAX - 1)
diff --git a/include/uapi/linux/netfilter/nfnetlink_acct.h b/include/uapi/linux/netfilter/nfnetlink_acct.h
index c7b6269e760..51404ec1902 100644
--- a/include/uapi/linux/netfilter/nfnetlink_acct.h
+++ b/include/uapi/linux/netfilter/nfnetlink_acct.h
@@ -10,15 +10,24 @@ enum nfnl_acct_msg_types {
 	NFNL_MSG_ACCT_GET,
 	NFNL_MSG_ACCT_GET_CTRZERO,
 	NFNL_MSG_ACCT_DEL,
+	NFNL_MSG_ACCT_OVERQUOTA,
 	NFNL_MSG_ACCT_MAX
 };
 
+enum nfnl_acct_flags {
+	NFACCT_F_QUOTA_PKTS	= (1 << 0),
+	NFACCT_F_QUOTA_BYTES	= (1 << 1),
+	NFACCT_F_OVERQUOTA	= (1 << 2), /* can't be set from userspace */
+};
+
 enum nfnl_acct_type {
 	NFACCT_UNSPEC,
 	NFACCT_NAME,
 	NFACCT_PKTS,
 	NFACCT_BYTES,
 	NFACCT_USE,
+	NFACCT_FLAGS,
+	NFACCT_QUOTA,
 	__NFACCT_MAX
 };
 #define NFACCT_MAX (__NFACCT_MAX - 1)
diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h
index 9789dc95b6a..9b19b446192 100644
--- a/include/uapi/linux/nfc.h
+++ b/include/uapi/linux/nfc.h
@@ -273,11 +273,19 @@ struct sockaddr_nfc_llcp {
  * First byte is the adapter index
  * Second byte contains flags
  *  - 0x01 - Direction (0=RX, 1=TX)
- *  - 0x02-0x80 - Reserved
+ *  - 0x02-0x04 - Payload type (000=LLCP, 001=NCI, 010=HCI, 011=Digital,
+ *                              100=Proprietary)
+ *  - 0x05-0x80 - Reserved
  **/
-#define NFC_LLCP_RAW_HEADER_SIZE	2
-#define NFC_LLCP_DIRECTION_RX		0x00
-#define NFC_LLCP_DIRECTION_TX		0x01
+#define NFC_RAW_HEADER_SIZE	2
+#define NFC_DIRECTION_RX		0x00
+#define NFC_DIRECTION_TX		0x01
+
+#define RAW_PAYLOAD_LLCP 0
+#define RAW_PAYLOAD_NCI	1
+#define RAW_PAYLOAD_HCI	2
+#define RAW_PAYLOAD_DIGITAL	3
+#define RAW_PAYLOAD_PROPRIETARY	4
 
 /* socket option names */
 #define NFC_LLCP_RW		0
diff --git a/include/uapi/linux/nfsd/nfsfh.h b/include/uapi/linux/nfsd/nfsfh.h
index 616e3b39647..20391235d08 100644
--- a/include/uapi/linux/nfsd/nfsfh.h
+++ b/include/uapi/linux/nfsd/nfsfh.h
@@ -1,13 +1,7 @@
 /*
- * include/linux/nfsd/nfsfh.h
- *
  * This file describes the layout of the file handles as passed
  * over the wire.
  *
- * Earlier versions of knfsd used to sign file handles using keyed MD5
- * or SHA. I've removed this code, because it doesn't give you more
- * security than blocking external access to port 2049 on your firewall.
- *
  * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
  */
 
@@ -37,7 +31,7 @@ struct nfs_fhbase_old {
 };
 
 /*
- * This is the new flexible, extensible style NFSv2/v3 file handle.
+ * This is the new flexible, extensible style NFSv2/v3/v4 file handle.
  * by Neil Brown <neilb@cse.unsw.edu.au> - March 2000
  *
  * The file handle starts with a sequence of four-byte words.
@@ -47,14 +41,7 @@ struct nfs_fhbase_old {
  *
  * All four-byte values are in host-byte-order.
  *
- * The auth_type field specifies how the filehandle can be authenticated
- * This might allow a file to be confirmed to be in a writable part of a
- * filetree without checking the path from it up to the root.
- * Current values:
- *     0  - No authentication.  fb_auth is 0 bytes long
- * Possible future values:
- *     1  - 4 bytes taken from MD5 hash of the remainer of the file handle
- *          prefixed by a secret and with the important export flags.
+ * The auth_type field is deprecated and must be set to 0.
  *
  * The fsid_type identifies how the filesystem (or export point) is
  *    encoded.
@@ -71,14 +58,9 @@ struct nfs_fhbase_old {
  *     7  - 8 byte inode number and 16 byte uuid
  *
  * The fileid_type identified how the file within the filesystem is encoded.
- * This is (will be) passed to, and set by, the underlying filesystem if it supports
- * filehandle operations.  The filesystem must not use the value '0' or '0xff' and may
- * only use the values 1 and 2 as defined below:
- *  Current values:
- *    0   - The root, or export point, of the filesystem.  fb_fileid is 0 bytes.
- *    1   - 32bit inode number, 32 bit generation number.
- *    2   - 32bit inode number, 32 bit generation number, 32 bit parent directory inode number.
- *
+ *   The values for this field are filesystem specific, exccept that
+ *   filesystems must not use the values '0' or '0xff'. 'See enum fid_type'
+ *   in include/linux/exportfs.h for currently registered values.
  */
 struct nfs_fhbase_new {
 	__u8		fb_version;	/* == 1, even => nfs_fhbase_old */
@@ -114,9 +96,9 @@ struct knfsd_fh {
 #define	fh_fsid_type		fh_base.fh_new.fb_fsid_type
 #define	fh_auth_type		fh_base.fh_new.fb_auth_type
 #define	fh_fileid_type		fh_base.fh_new.fb_fileid_type
-#define	fh_auth			fh_base.fh_new.fb_auth
 #define	fh_fsid			fh_base.fh_new.fb_auth
 
-
+/* Do not use, provided for userspace compatiblity. */
+#define	fh_auth			fh_base.fh_new.fb_auth
 
 #endif /* _UAPI_LINUX_NFSD_FH_H */
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 194c1eab04d..be9519b52bb 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -503,6 +503,9 @@
  *	TX status event pertaining to the TX request.
  *	%NL80211_ATTR_TX_NO_CCK_RATE is used to decide whether to send the
  *	management frames at CCK rate or not in 2GHz band.
+ *	%NL80211_ATTR_CSA_C_OFFSETS_TX is an array of offsets to CSA
+ *	counters which will be updated to the current value. This attribute
+ *	is used during CSA period.
  * @NL80211_CMD_FRAME_WAIT_CANCEL: When an off-channel TX was requested, this
  *	command may be used with the corresponding cookie to cancel the wait
  *	time if it is known that it is no longer necessary.
@@ -1525,10 +1528,10 @@ enum nl80211_commands {
  *	operation).
  * @NL80211_ATTR_CSA_IES: Nested set of attributes containing the IE information
  *	for the time while performing a channel switch.
- * @NL80211_ATTR_CSA_C_OFF_BEACON: Offset of the channel switch counter
- *	field in the beacons tail (%NL80211_ATTR_BEACON_TAIL).
- * @NL80211_ATTR_CSA_C_OFF_PRESP: Offset of the channel switch counter
- *	field in the probe response (%NL80211_ATTR_PROBE_RESP).
+ * @NL80211_ATTR_CSA_C_OFF_BEACON: An array of offsets (u16) to the channel
+ *	switch counters in the beacons tail (%NL80211_ATTR_BEACON_TAIL).
+ * @NL80211_ATTR_CSA_C_OFF_PRESP: An array of offsets (u16) to the channel
+ *	switch counters in the probe response (%NL80211_ATTR_PROBE_RESP).
  *
  * @NL80211_ATTR_RXMGMT_FLAGS: flags for nl80211_send_mgmt(), u32.
  *	As specified in the &enum nl80211_rxmgmt_flags.
@@ -1576,9 +1579,18 @@ enum nl80211_commands {
  *	advertise values that cannot always be met. In such cases, an attempt
  *	to add a new station entry with @NL80211_CMD_NEW_STATION may fail.
  *
+ * @NL80211_ATTR_CSA_C_OFFSETS_TX: An array of csa counter offsets (u16) which
+ *	should be updated when the frame is transmitted.
+ * @NL80211_ATTR_MAX_CSA_COUNTERS: U8 attribute used to advertise the maximum
+ *	supported number of csa counters.
+ *
  * @NL80211_ATTR_TDLS_PEER_CAPABILITY: flags for TDLS peer capabilities, u32.
  *	As specified in the &enum nl80211_tdls_peer_capability.
  *
+ * @NL80211_ATTR_IFACE_SOCKET_OWNER: flag attribute, if set during interface
+ *	creation then the new interface will be owned by the netlink socket
+ *	that created it and will be destroyed when the socket is closed
+ *
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
  */
@@ -1914,6 +1926,11 @@ enum nl80211_attrs {
 
 	NL80211_ATTR_TDLS_PEER_CAPABILITY,
 
+	NL80211_ATTR_IFACE_SOCKET_OWNER,
+
+	NL80211_ATTR_CSA_C_OFFSETS_TX,
+	NL80211_ATTR_MAX_CSA_COUNTERS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -2182,6 +2199,8 @@ enum nl80211_sta_bss_param {
  *	Contains a nested array of signal strength attributes (u8, dBm)
  * @NL80211_STA_INFO_CHAIN_SIGNAL_AVG: per-chain signal strength average
  *	Same format as NL80211_STA_INFO_CHAIN_SIGNAL.
+ * @NL80211_STA_EXPECTED_THROUGHPUT: expected throughput considering also the
+ *	802.11 header (u32, kbps)
  * @__NL80211_STA_INFO_AFTER_LAST: internal
  * @NL80211_STA_INFO_MAX: highest possible station info attribute
  */
@@ -2213,6 +2232,7 @@ enum nl80211_sta_info {
 	NL80211_STA_INFO_TX_BYTES64,
 	NL80211_STA_INFO_CHAIN_SIGNAL,
 	NL80211_STA_INFO_CHAIN_SIGNAL_AVG,
+	NL80211_STA_INFO_EXPECTED_THROUGHPUT,
 
 	/* keep last */
 	__NL80211_STA_INFO_AFTER_LAST,
@@ -2336,9 +2356,34 @@ enum nl80211_band_attr {
  *	using this channel as the primary or any of the secondary channels
  *	isn't possible
  * @NL80211_FREQUENCY_ATTR_DFS_CAC_TIME: DFS CAC time in milliseconds.
+ * @NL80211_FREQUENCY_ATTR_INDOOR_ONLY: Only indoor use is permitted on this
+ *	channel. A channel that has the INDOOR_ONLY attribute can only be
+ *	used when there is a clear assessment that the device is operating in
+ *	an indoor surroundings, i.e., it is connected to AC power (and not
+ *	through portable DC inverters) or is under the control of a master
+ *	that is acting as an AP and is connected to AC power.
+ * @NL80211_FREQUENCY_ATTR_GO_CONCURRENT: GO operation is allowed on this
+ *	channel if it's connected concurrently to a BSS on the same channel on
+ *	the 2 GHz band or to a channel in the same UNII band (on the 5 GHz
+ *	band), and IEEE80211_CHAN_RADAR is not set. Instantiating a GO on a
+ *	channel that has the GO_CONCURRENT attribute set can be done when there
+ *	is a clear assessment that the device is operating under the guidance of
+ *	an authorized master, i.e., setting up a GO while the device is also
+ *	connected to an AP with DFS and radar detection on the UNII band (it is
+ *	up to user-space, i.e., wpa_supplicant to perform the required
+ *	verifications)
+ * @NL80211_FREQUENCY_ATTR_NO_20MHZ: 20 MHz operation is not allowed
+ *	on this channel in current regulatory domain.
+ * @NL80211_FREQUENCY_ATTR_NO_10MHZ: 10 MHz operation is not allowed
+ *	on this channel in current regulatory domain.
  * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number
  *	currently defined
  * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use
+ *
+ * See https://apps.fcc.gov/eas/comments/GetPublishedDocument.html?id=327&tn=528122
+ * for more information on the FCC description of the relaxations allowed
+ * by NL80211_FREQUENCY_ATTR_INDOOR_ONLY and
+ * NL80211_FREQUENCY_ATTR_GO_CONCURRENT.
  */
 enum nl80211_frequency_attr {
 	__NL80211_FREQUENCY_ATTR_INVALID,
@@ -2355,6 +2400,10 @@ enum nl80211_frequency_attr {
 	NL80211_FREQUENCY_ATTR_NO_80MHZ,
 	NL80211_FREQUENCY_ATTR_NO_160MHZ,
 	NL80211_FREQUENCY_ATTR_DFS_CAC_TIME,
+	NL80211_FREQUENCY_ATTR_INDOOR_ONLY,
+	NL80211_FREQUENCY_ATTR_GO_CONCURRENT,
+	NL80211_FREQUENCY_ATTR_NO_20MHZ,
+	NL80211_FREQUENCY_ATTR_NO_10MHZ,
 
 	/* keep last */
 	__NL80211_FREQUENCY_ATTR_AFTER_LAST,
@@ -2573,10 +2622,13 @@ enum nl80211_dfs_regions {
  *	present has been registered with the wireless core that
  *	has listed NL80211_FEATURE_CELL_BASE_REG_HINTS as a
  *	supported feature.
+ * @NL80211_USER_REG_HINT_INDOOR: a user sent an hint indicating that the
+ *	platform is operating in an indoor environment.
  */
 enum nl80211_user_reg_hint_type {
 	NL80211_USER_REG_HINT_USER	= 0,
 	NL80211_USER_REG_HINT_CELL_BASE = 1,
+	NL80211_USER_REG_HINT_INDOOR    = 2,
 };
 
 /**
@@ -3650,6 +3702,8 @@ enum nl80211_iface_limit_attrs {
  *	different channels may be used within this group.
  * @NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS: u32 attribute containing the bitmap
  *	of supported channel widths for radar detection.
+ * @NL80211_IFACE_COMB_RADAR_DETECT_REGIONS: u32 attribute containing the bitmap
+ *	of supported regulatory regions for radar detection.
  * @NUM_NL80211_IFACE_COMB: number of attributes
  * @MAX_NL80211_IFACE_COMB: highest attribute number
  *
@@ -3683,6 +3737,7 @@ enum nl80211_if_combination_attrs {
 	NL80211_IFACE_COMB_STA_AP_BI_MATCH,
 	NL80211_IFACE_COMB_NUM_CHANNELS,
 	NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS,
+	NL80211_IFACE_COMB_RADAR_DETECT_REGIONS,
 
 	/* keep last */
 	NUM_NL80211_IFACE_COMB,
@@ -3893,6 +3948,9 @@ enum nl80211_ap_sme_features {
  *	interface. An active monitor interface behaves like a normal monitor
  *	interface, but gets added to the driver. It ensures that incoming
  *	unicast packets directed at the configured interface address get ACKed.
+ * @NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE: This driver supports dynamic
+ *	channel bandwidth change (e.g., HT 20 <-> 40 MHz channel) during the
+ *	lifetime of a BSS.
  */
 enum nl80211_feature_flags {
 	NL80211_FEATURE_SK_TX_STATUS			= 1 << 0,
@@ -3913,6 +3971,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_FULL_AP_CLIENT_STATE		= 1 << 15,
 	NL80211_FEATURE_USERSPACE_MPM			= 1 << 16,
 	NL80211_FEATURE_ACTIVE_MONITOR			= 1 << 17,
+	NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE	= 1 << 18,
 };
 
 /**
diff --git a/include/uapi/linux/nvme.h b/include/uapi/linux/nvme.h
index 096fe1c6f83..29a7d8619d8 100644
--- a/include/uapi/linux/nvme.h
+++ b/include/uapi/linux/nvme.h
@@ -1,6 +1,6 @@
 /*
  * Definitions for the NVM Express interface
- * Copyright (c) 2011-2013, Intel Corporation.
+ * Copyright (c) 2011-2014, Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -10,10 +10,6 @@
  * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
  * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifndef _UAPI_LINUX_NVME_H
@@ -31,7 +27,12 @@ struct nvme_id_power_state {
 	__u8			read_lat;
 	__u8			write_tput;
 	__u8			write_lat;
-	__u8			rsvd16[16];
+	__le16			idle_power;
+	__u8			idle_scale;
+	__u8			rsvd19;
+	__le16			active_power;
+	__u8			active_work_scale;
+	__u8			rsvd23[9];
 };
 
 enum {
@@ -49,7 +50,9 @@ struct nvme_id_ctrl {
 	__u8			ieee[3];
 	__u8			mic;
 	__u8			mdts;
-	__u8			rsvd78[178];
+	__u16			cntlid;
+	__u32			ver;
+	__u8			rsvd84[172];
 	__le16			oacs;
 	__u8			acl;
 	__u8			aerl;
@@ -57,7 +60,11 @@ struct nvme_id_ctrl {
 	__u8			lpa;
 	__u8			elpe;
 	__u8			npss;
-	__u8			rsvd264[248];
+	__u8			avscc;
+	__u8			apsta;
+	__le16			wctemp;
+	__le16			cctemp;
+	__u8			rsvd270[242];
 	__u8			sqes;
 	__u8			cqes;
 	__u8			rsvd514[2];
@@ -68,7 +75,12 @@ struct nvme_id_ctrl {
 	__u8			vwc;
 	__le16			awun;
 	__le16			awupf;
-	__u8			rsvd530[1518];
+	__u8			nvscc;
+	__u8			rsvd531;
+	__le16			acwu;
+	__u8			rsvd534[2];
+	__le32			sgls;
+	__u8			rsvd540[1508];
 	struct nvme_id_power_state	psd[32];
 	__u8			vs[1024];
 };
@@ -77,6 +89,7 @@ enum {
 	NVME_CTRL_ONCS_COMPARE			= 1 << 0,
 	NVME_CTRL_ONCS_WRITE_UNCORRECTABLE	= 1 << 1,
 	NVME_CTRL_ONCS_DSM			= 1 << 2,
+	NVME_CTRL_VWC_PRESENT			= 1 << 0,
 };
 
 struct nvme_lbaf {
@@ -95,7 +108,15 @@ struct nvme_id_ns {
 	__u8			mc;
 	__u8			dpc;
 	__u8			dps;
-	__u8			rsvd30[98];
+	__u8			nmic;
+	__u8			rescap;
+	__u8			fpi;
+	__u8			rsvd33;
+	__le16			nawun;
+	__le16			nawupf;
+	__le16			nacwu;
+	__u8			rsvd40[80];
+	__u8			eui64[8];
 	struct nvme_lbaf	lbaf[16];
 	__u8			rsvd192[192];
 	__u8			vs[3712];
@@ -126,7 +147,10 @@ struct nvme_smart_log {
 	__u8			unsafe_shutdowns[16];
 	__u8			media_errors[16];
 	__u8			num_err_log_entries[16];
-	__u8			rsvd192[320];
+	__le32			warning_temp_time;
+	__le32			critical_comp_time;
+	__le16			temp_sensor[8];
+	__u8			rsvd216[296];
 };
 
 enum {
@@ -282,6 +306,10 @@ enum {
 	NVME_FEAT_WRITE_ATOMIC	= 0x0a,
 	NVME_FEAT_ASYNC_EVENT	= 0x0b,
 	NVME_FEAT_SW_PROGRESS	= 0x0c,
+	NVME_LOG_ERROR		= 0x01,
+	NVME_LOG_SMART		= 0x02,
+	NVME_LOG_FW_SLOT	= 0x03,
+	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
 	NVME_FWACT_REPL_ACTV	= (1 << 3),
 	NVME_FWACT_ACTV		= (2 << 3),
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 970553cbbc8..0b979ee4bfc 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -395,7 +395,9 @@ struct ovs_key_nd {
  * @OVS_FLOW_ATTR_ACTIONS: Nested %OVS_ACTION_ATTR_* attributes specifying
  * the actions to take for packets that match the key.  Always present in
  * notifications.  Required for %OVS_FLOW_CMD_NEW requests, optional for
- * %OVS_FLOW_CMD_SET requests.
+ * %OVS_FLOW_CMD_SET requests.  An %OVS_FLOW_CMD_SET without
+ * %OVS_FLOW_ATTR_ACTIONS will not modify the actions.  To clear the actions,
+ * an %OVS_FLOW_ATTR_ACTIONS without any nested attributes must be given.
  * @OVS_FLOW_ATTR_STATS: &struct ovs_flow_stats giving statistics for this
  * flow.  Present in notifications if the stats would be nonzero.  Ignored in
  * requests.
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index e3fc8f09d11..9269de25487 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -163,8 +163,9 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_ABORT_TX	= 1U << 7, /* transaction aborts */
 	PERF_SAMPLE_BRANCH_IN_TX	= 1U << 8, /* in transaction */
 	PERF_SAMPLE_BRANCH_NO_TX	= 1U << 9, /* not in transaction */
+	PERF_SAMPLE_BRANCH_COND		= 1U << 10, /* conditional branches */
 
-	PERF_SAMPLE_BRANCH_MAX		= 1U << 10, /* non-ABI */
+	PERF_SAMPLE_BRANCH_MAX		= 1U << 11, /* non-ABI */
 };
 
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
@@ -301,8 +302,8 @@ struct perf_event_attr {
 				exclude_callchain_kernel : 1, /* exclude kernel callchains */
 				exclude_callchain_user   : 1, /* exclude user callchains */
 				mmap2          :  1, /* include mmap with inode data     */
-
-				__reserved_1   : 40;
+				comm_exec      :  1, /* flag comm events that are due to an exec */
+				__reserved_1   : 39;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -501,7 +502,12 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
 #define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
 
+/*
+ * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
+ * different events so can reuse the same bit position.
+ */
 #define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
+#define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
 /*
  * Indicates that the content of PERF_SAMPLE_IP points to
  * the actual instruction that triggered the event. See also
@@ -699,6 +705,7 @@ enum perf_event_type {
 	 *	u32				min;
 	 *	u64				ino;
 	 *	u64				ino_generation;
+	 *	u32				prot, flags;
 	 *	char				filename[];
 	 * 	struct sample_id		sample_id;
 	 * };
diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h
index 852373d27db..6f71b9b4159 100644
--- a/include/uapi/linux/tipc.h
+++ b/include/uapi/linux/tipc.h
@@ -38,6 +38,7 @@
 #define _LINUX_TIPC_H_
 
 #include <linux/types.h>
+#include <linux/sockios.h>
 
 /*
  * TIPC addressing primitives
@@ -87,6 +88,7 @@ static inline unsigned int tipc_node(__u32 addr)
 
 #define TIPC_CFG_SRV		0	/* configuration service name type */
 #define TIPC_TOP_SRV		1	/* topology service name type */
+#define TIPC_LINK_STATE		2	/* link state name type */
 #define TIPC_RESERVED_TYPES	64	/* lowest user-publishable name type */
 
 /*
@@ -206,4 +208,25 @@ struct sockaddr_tipc {
 #define TIPC_NODE_RECVQ_DEPTH	131	/* Default: none (read only) */
 #define TIPC_SOCK_RECVQ_DEPTH	132	/* Default: none (read only) */
 
+/*
+ * Maximum sizes of TIPC bearer-related names (including terminating NULL)
+ * The string formatting for each name element is:
+ * media: media
+ * interface: media:interface name
+ * link: Z.C.N:interface-Z.C.N:interface
+ *
+ */
+
+#define TIPC_MAX_MEDIA_NAME	16
+#define TIPC_MAX_IF_NAME	16
+#define TIPC_MAX_BEARER_NAME	32
+#define TIPC_MAX_LINK_NAME	60
+
+#define SIOCGETLINKNAME		SIOCPROTOPRIVATE
+
+struct tipc_sioc_ln_req {
+	__u32 peer;
+	__u32 bearer_id;
+	char linkname[TIPC_MAX_LINK_NAME];
+};
 #endif
diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h
index 6b0bff09b3a..41a76acbb30 100644
--- a/include/uapi/linux/tipc_config.h
+++ b/include/uapi/linux/tipc_config.h
@@ -39,6 +39,7 @@
 
 #include <linux/types.h>
 #include <linux/string.h>
+#include <linux/tipc.h>
 #include <asm/byteorder.h>
 
 #ifndef __KERNEL__
@@ -155,15 +156,6 @@
 #define TIPC_TLV_PORT_REF	26	/* 32-bit port reference */
 
 /*
- * Maximum sizes of TIPC bearer-related names (including terminating NUL)
- */
-
-#define TIPC_MAX_MEDIA_NAME	16	/* format = media */
-#define TIPC_MAX_IF_NAME	16	/* format = interface */
-#define TIPC_MAX_BEARER_NAME	32	/* format = media:interface */
-#define TIPC_MAX_LINK_NAME	60	/* format = Z.C.N:interface-Z.C.N:interface */
-
-/*
  * Link priority limits (min, default, max, media default)
  */
 
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index e2bcfd75a30..16574ea18f0 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -29,6 +29,8 @@ struct udphdr {
 /* UDP socket options */
 #define UDP_CORK	1	/* Never send partially complete segments */
 #define UDP_ENCAP	100	/* Set the socket to accept encapsulated packets */
+#define UDP_NO_CHECK6_TX 101	/* Disable sending checksum for UDP6X */
+#define UDP_NO_CHECK6_RX 102	/* Disable accpeting checksum for UDP6 */
 
 /* UDP encapsulation types */
 #define UDP_ENCAP_ESPINUDP_NON_IKE	1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h
index 2a4b4a72a4f..24b68c59dcf 100644
--- a/include/uapi/linux/usb/functionfs.h
+++ b/include/uapi/linux/usb/functionfs.h
@@ -33,6 +33,13 @@ struct usb_endpoint_descriptor_no_audio {
 	__u8  bInterval;
 } __attribute__((packed));
 
+/* Legacy format, deprecated as of 3.14. */
+struct usb_functionfs_descs_head {
+	__le32 magic;
+	__le32 length;
+	__le32 fs_count;
+	__le32 hs_count;
+} __attribute__((packed, deprecated));
 
 /*
  * Descriptors format:
diff --git a/include/uapi/mtd/mtd-abi.h b/include/uapi/mtd/mtd-abi.h
index e272ea060e3..763bb695040 100644
--- a/include/uapi/mtd/mtd-abi.h
+++ b/include/uapi/mtd/mtd-abi.h
@@ -109,6 +109,7 @@ struct mtd_write_req {
 #define MTD_CAP_RAM		(MTD_WRITEABLE | MTD_BIT_WRITEABLE | MTD_NO_ERASE)
 #define MTD_CAP_NORFLASH	(MTD_WRITEABLE | MTD_BIT_WRITEABLE)
 #define MTD_CAP_NANDFLASH	(MTD_WRITEABLE)
+#define MTD_CAP_NVRAM		(MTD_WRITEABLE | MTD_BIT_WRITEABLE | MTD_NO_ERASE)
 
 /* Obsolete ECC byte placement modes (used with obsolete MEMGETOOBSEL) */
 #define MTD_NANDECC_OFF		0	// Switch off ECC (Not recommended)
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 8297285b628..de69170a30c 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -4,7 +4,16 @@
 #include <linux/types.h>
 
 enum {
-	RDMA_NL_RDMA_CM = 1
+	RDMA_NL_RDMA_CM = 1,
+	RDMA_NL_NES,
+	RDMA_NL_C4IW,
+	RDMA_NL_NUM_CLIENTS
+};
+
+enum {
+	RDMA_NL_GROUP_CM = 1,
+	RDMA_NL_GROUP_IWPM,
+	RDMA_NL_NUM_GROUPS
 };
 
 #define RDMA_NL_GET_CLIENT(type) ((type & (((1 << 6) - 1) << 10)) >> 10)
@@ -22,6 +31,18 @@ enum {
 	RDMA_NL_RDMA_CM_NUM_ATTR,
 };
 
+/* iwarp port mapper op-codes */
+enum {
+	RDMA_NL_IWPM_REG_PID = 0,
+	RDMA_NL_IWPM_ADD_MAPPING,
+	RDMA_NL_IWPM_QUERY_MAPPING,
+	RDMA_NL_IWPM_REMOVE_MAPPING,
+	RDMA_NL_IWPM_HANDLE_ERR,
+	RDMA_NL_IWPM_MAPINFO,
+	RDMA_NL_IWPM_MAPINFO_NUM,
+	RDMA_NL_IWPM_NUM_OPS
+};
+
 struct rdma_cm_id_stats {
 	__u32	qp_num;
 	__u32	bound_dev_if;
@@ -33,5 +54,78 @@ struct rdma_cm_id_stats {
 	__u8	qp_type;
 };
 
+enum {
+	IWPM_NLA_REG_PID_UNSPEC = 0,
+	IWPM_NLA_REG_PID_SEQ,
+	IWPM_NLA_REG_IF_NAME,
+	IWPM_NLA_REG_IBDEV_NAME,
+	IWPM_NLA_REG_ULIB_NAME,
+	IWPM_NLA_REG_PID_MAX
+};
+
+enum {
+	IWPM_NLA_RREG_PID_UNSPEC = 0,
+	IWPM_NLA_RREG_PID_SEQ,
+	IWPM_NLA_RREG_IBDEV_NAME,
+	IWPM_NLA_RREG_ULIB_NAME,
+	IWPM_NLA_RREG_ULIB_VER,
+	IWPM_NLA_RREG_PID_ERR,
+	IWPM_NLA_RREG_PID_MAX
+
+};
+
+enum {
+	IWPM_NLA_MANAGE_MAPPING_UNSPEC = 0,
+	IWPM_NLA_MANAGE_MAPPING_SEQ,
+	IWPM_NLA_MANAGE_ADDR,
+	IWPM_NLA_MANAGE_MAPPED_LOC_ADDR,
+	IWPM_NLA_RMANAGE_MAPPING_ERR,
+	IWPM_NLA_RMANAGE_MAPPING_MAX
+};
+
+#define IWPM_NLA_MANAGE_MAPPING_MAX 3
+#define IWPM_NLA_QUERY_MAPPING_MAX  4
+#define IWPM_NLA_MAPINFO_SEND_MAX   3
+
+enum {
+	IWPM_NLA_QUERY_MAPPING_UNSPEC = 0,
+	IWPM_NLA_QUERY_MAPPING_SEQ,
+	IWPM_NLA_QUERY_LOCAL_ADDR,
+	IWPM_NLA_QUERY_REMOTE_ADDR,
+	IWPM_NLA_RQUERY_MAPPED_LOC_ADDR,
+	IWPM_NLA_RQUERY_MAPPED_REM_ADDR,
+	IWPM_NLA_RQUERY_MAPPING_ERR,
+	IWPM_NLA_RQUERY_MAPPING_MAX
+};
+
+enum {
+	IWPM_NLA_MAPINFO_REQ_UNSPEC = 0,
+	IWPM_NLA_MAPINFO_ULIB_NAME,
+	IWPM_NLA_MAPINFO_ULIB_VER,
+	IWPM_NLA_MAPINFO_REQ_MAX
+};
+
+enum {
+	IWPM_NLA_MAPINFO_UNSPEC = 0,
+	IWPM_NLA_MAPINFO_LOCAL_ADDR,
+	IWPM_NLA_MAPINFO_MAPPED_ADDR,
+	IWPM_NLA_MAPINFO_MAX
+};
+
+enum {
+	IWPM_NLA_MAPINFO_NUM_UNSPEC = 0,
+	IWPM_NLA_MAPINFO_SEQ,
+	IWPM_NLA_MAPINFO_SEND_NUM,
+	IWPM_NLA_MAPINFO_ACK_NUM,
+	IWPM_NLA_MAPINFO_NUM_MAX
+};
+
+enum {
+	IWPM_NLA_ERR_UNSPEC = 0,
+	IWPM_NLA_ERR_SEQ,
+	IWPM_NLA_ERR_CODE,
+	IWPM_NLA_ERR_MAX
+};
+
 
 #endif /* _UAPI_RDMA_NETLINK_H */
diff --git a/include/uapi/sound/compress_offload.h b/include/uapi/sound/compress_offload.h
index 5759810e1c1..1964026b5e0 100644
--- a/include/uapi/sound/compress_offload.h
+++ b/include/uapi/sound/compress_offload.h
@@ -39,7 +39,7 @@
 struct snd_compressed_buffer {
 	__u32 fragment_size;
 	__u32 fragments;
-};
+} __attribute__((packed, aligned(4)));
 
 /**
  * struct snd_compr_params: compressed stream params
@@ -51,7 +51,7 @@ struct snd_compr_params {
 	struct snd_compressed_buffer buffer;
 	struct snd_codec codec;
 	__u8 no_wake_mode;
-};
+} __attribute__((packed, aligned(4)));
 
 /**
  * struct snd_compr_tstamp: timestamp descriptor
@@ -70,7 +70,7 @@ struct snd_compr_tstamp {
 	__u32 pcm_frames;
 	__u32 pcm_io_frames;
 	__u32 sampling_rate;
-};
+} __attribute__((packed, aligned(4)));
 
 /**
  * struct snd_compr_avail: avail descriptor
@@ -80,7 +80,7 @@ struct snd_compr_tstamp {
 struct snd_compr_avail {
 	__u64 avail;
 	struct snd_compr_tstamp tstamp;
-};
+} __attribute__((packed, aligned(4)));
 
 enum snd_compr_direction {
 	SND_COMPRESS_PLAYBACK = 0,
@@ -107,7 +107,7 @@ struct snd_compr_caps {
 	__u32 max_fragments;
 	__u32 codecs[MAX_NUM_CODECS];
 	__u32 reserved[11];
-};
+} __attribute__((packed, aligned(4)));
 
 /**
  * struct snd_compr_codec_caps: query capability of codec
@@ -119,7 +119,7 @@ struct snd_compr_codec_caps {
 	__u32 codec;
 	__u32 num_descriptors;
 	struct snd_codec_desc descriptor[MAX_NUM_CODEC_DESCRIPTORS];
-};
+} __attribute__((packed, aligned(4)));
 
 /**
  * @SNDRV_COMPRESS_ENCODER_PADDING: no of samples appended by the encoder at the
@@ -140,7 +140,7 @@ enum {
 struct snd_compr_metadata {
 	 __u32 key;
 	 __u32 value[8];
-};
+} __attribute__((packed, aligned(4)));
 
 /**
  * compress path ioctl definitions
diff --git a/include/uapi/sound/compress_params.h b/include/uapi/sound/compress_params.h
index 165e7059de7..d9bd9ca0d5b 100644
--- a/include/uapi/sound/compress_params.h
+++ b/include/uapi/sound/compress_params.h
@@ -268,7 +268,7 @@ struct snd_enc_vorbis {
 	__u32 max_bit_rate;
 	__u32 min_bit_rate;
 	__u32 downmix;
-};
+} __attribute__((packed, aligned(4)));
 
 
 /**
@@ -284,7 +284,7 @@ struct snd_enc_real {
 	__u32 quant_bits;
 	__u32 start_region;
 	__u32 num_regions;
-};
+} __attribute__((packed, aligned(4)));
 
 /**
  * struct snd_enc_flac
@@ -308,12 +308,12 @@ struct snd_enc_real {
 struct snd_enc_flac {
 	__u32 num;
 	__u32 gain;
-};
+} __attribute__((packed, aligned(4)));
 
 struct snd_enc_generic {
 	__u32 bw;	/* encoder bandwidth */
 	__s32 reserved[15];
-};
+} __attribute__((packed, aligned(4)));
 
 union snd_codec_options {
 	struct snd_enc_wma wma;
@@ -321,7 +321,7 @@ union snd_codec_options {
 	struct snd_enc_real real;
 	struct snd_enc_flac flac;
 	struct snd_enc_generic generic;
-};
+} __attribute__((packed, aligned(4)));
 
 /** struct snd_codec_desc - description of codec capabilities
  * @max_ch: Maximum number of audio channels
@@ -358,7 +358,7 @@ struct snd_codec_desc {
 	__u32 formats;
 	__u32 min_buffer;
 	__u32 reserved[15];
-};
+} __attribute__((packed, aligned(4)));
 
 /** struct snd_codec
  * @id: Identifies the supported audio encoder/decoder.
@@ -399,6 +399,6 @@ struct snd_codec {
 	__u32 align;
 	union snd_codec_options options;
 	__u32 reserved[3];
-};
+} __attribute__((packed, aligned(4)));
 
 #endif
diff --git a/drivers/staging/imx-drm/ipu-v3/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index c2c6fab05ea..3e43e22cdff 100644
--- a/drivers/staging/imx-drm/ipu-v3/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -104,6 +104,7 @@ int ipu_idmac_wait_busy(struct ipuv3_channel *channel, int ms);
 
 void ipu_idmac_set_double_buffer(struct ipuv3_channel *channel,
 		bool doublebuffer);
+int ipu_idmac_get_current_buffer(struct ipuv3_channel *channel);
 void ipu_idmac_select_buffer(struct ipuv3_channel *channel, u32 buf_num);
 
 /*
@@ -165,6 +166,20 @@ int ipu_dp_set_window_pos(struct ipu_dp *, u16 x_pos, u16 y_pos);
 int ipu_dp_set_global_alpha(struct ipu_dp *dp, bool enable, u8 alpha,
 		bool bg_chan);
 
+/*
+ * IPU CMOS Sensor Interface (csi) functions
+ */
+int ipu_csi_enable(struct ipu_soc *ipu, int csi);
+int ipu_csi_disable(struct ipu_soc *ipu, int csi);
+
+/*
+ * IPU Sensor Multiple FIFO Controller (SMFC) functions
+ */
+int ipu_smfc_enable(struct ipu_soc *ipu);
+int ipu_smfc_disable(struct ipu_soc *ipu);
+int ipu_smfc_map_channel(struct ipu_soc *ipu, int channel, int csi_id, int mipi_id);
+int ipu_smfc_set_burstsize(struct ipu_soc *ipu, int channel, int burstsize);
+
 #define IPU_CPMEM_WORD(word, ofs, size) ((((word) * 160 + (ofs)) << 8) | (size))
 
 #define IPU_FIELD_UBO		IPU_CPMEM_WORD(0, 46, 22)
@@ -321,6 +336,7 @@ static inline void ipu_cpmem_set_burstsize(struct ipu_ch_param __iomem *p,
 };
 
 struct ipu_client_platformdata {
+	int csi;
 	int di;
 	int dc;
 	int dp;
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index a5af2a26d94..5c1aba154b6 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -170,6 +170,7 @@ gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, phys_addr_t addr,
 	unmap->dev_bus_addr = 0;
 }
 
+int arch_gnttab_init(unsigned long nr_shared, unsigned long nr_status);
 int arch_gnttab_map_shared(xen_pfn_t *frames, unsigned long nr_gframes,
 			   unsigned long max_nr_gframes,
 			   void **__shared);
diff --git a/include/xen/interface/io/netif.h b/include/xen/interface/io/netif.h
index c50061db609..70054cc0708 100644
--- a/include/xen/interface/io/netif.h
+++ b/include/xen/interface/io/netif.h
@@ -51,6 +51,59 @@
  */
 
 /*
+ * Multiple transmit and receive queues:
+ * If supported, the backend will write the key "multi-queue-max-queues" to
+ * the directory for that vif, and set its value to the maximum supported
+ * number of queues.
+ * Frontends that are aware of this feature and wish to use it can write the
+ * key "multi-queue-num-queues", set to the number they wish to use, which
+ * must be greater than zero, and no more than the value reported by the backend
+ * in "multi-queue-max-queues".
+ *
+ * Queues replicate the shared rings and event channels.
+ * "feature-split-event-channels" may optionally be used when using
+ * multiple queues, but is not mandatory.
+ *
+ * Each queue consists of one shared ring pair, i.e. there must be the same
+ * number of tx and rx rings.
+ *
+ * For frontends requesting just one queue, the usual event-channel and
+ * ring-ref keys are written as before, simplifying the backend processing
+ * to avoid distinguishing between a frontend that doesn't understand the
+ * multi-queue feature, and one that does, but requested only one queue.
+ *
+ * Frontends requesting two or more queues must not write the toplevel
+ * event-channel (or event-channel-{tx,rx}) and {tx,rx}-ring-ref keys,
+ * instead writing those keys under sub-keys having the name "queue-N" where
+ * N is the integer ID of the queue for which those keys belong. Queues
+ * are indexed from zero. For example, a frontend with two queues and split
+ * event channels must write the following set of queue-related keys:
+ *
+ * /local/domain/1/device/vif/0/multi-queue-num-queues = "2"
+ * /local/domain/1/device/vif/0/queue-0 = ""
+ * /local/domain/1/device/vif/0/queue-0/tx-ring-ref = "<ring-ref-tx0>"
+ * /local/domain/1/device/vif/0/queue-0/rx-ring-ref = "<ring-ref-rx0>"
+ * /local/domain/1/device/vif/0/queue-0/event-channel-tx = "<evtchn-tx0>"
+ * /local/domain/1/device/vif/0/queue-0/event-channel-rx = "<evtchn-rx0>"
+ * /local/domain/1/device/vif/0/queue-1 = ""
+ * /local/domain/1/device/vif/0/queue-1/tx-ring-ref = "<ring-ref-tx1>"
+ * /local/domain/1/device/vif/0/queue-1/rx-ring-ref = "<ring-ref-rx1"
+ * /local/domain/1/device/vif/0/queue-1/event-channel-tx = "<evtchn-tx1>"
+ * /local/domain/1/device/vif/0/queue-1/event-channel-rx = "<evtchn-rx1>"
+ *
+ * If there is any inconsistency in the XenStore data, the backend may
+ * choose not to connect any queues, instead treating the request as an
+ * error. This includes scenarios where more (or fewer) queues were
+ * requested than the frontend provided details for.
+ *
+ * Mapping of packets to queues is considered to be a function of the
+ * transmitting system (backend or frontend) and is not negotiated
+ * between the two. Guests are free to transmit packets on any queue
+ * they choose, provided it has been set up correctly. Guests must be
+ * prepared to receive packets on any queue they have requested be set up.
+ */
+
+/*
  * "feature-no-csum-offload" should be used to turn IPv4 TCP/UDP checksum
  * offload off or on. If it is missing then the feature is assumed to be on.
  * "feature-ipv6-csum-offload" should be used to turn IPv6 TCP/UDP checksum
diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h
index f1331e3e727..5cc49ea8d84 100644
--- a/include/xen/interface/platform.h
+++ b/include/xen/interface/platform.h
@@ -108,11 +108,113 @@ struct xenpf_platform_quirk {
 };
 DEFINE_GUEST_HANDLE_STRUCT(xenpf_platform_quirk_t);
 
+#define XENPF_efi_runtime_call    49
+#define XEN_EFI_get_time                      1
+#define XEN_EFI_set_time                      2
+#define XEN_EFI_get_wakeup_time               3
+#define XEN_EFI_set_wakeup_time               4
+#define XEN_EFI_get_next_high_monotonic_count 5
+#define XEN_EFI_get_variable                  6
+#define XEN_EFI_set_variable                  7
+#define XEN_EFI_get_next_variable_name        8
+#define XEN_EFI_query_variable_info           9
+#define XEN_EFI_query_capsule_capabilities   10
+#define XEN_EFI_update_capsule               11
+
+struct xenpf_efi_runtime_call {
+	uint32_t function;
+	/*
+	 * This field is generally used for per sub-function flags (defined
+	 * below), except for the XEN_EFI_get_next_high_monotonic_count case,
+	 * where it holds the single returned value.
+	 */
+	uint32_t misc;
+	xen_ulong_t status;
+	union {
+#define XEN_EFI_GET_TIME_SET_CLEARS_NS 0x00000001
+		struct {
+			struct xenpf_efi_time {
+				uint16_t year;
+				uint8_t month;
+				uint8_t day;
+				uint8_t hour;
+				uint8_t min;
+				uint8_t sec;
+				uint32_t ns;
+				int16_t tz;
+				uint8_t daylight;
+			} time;
+			uint32_t resolution;
+			uint32_t accuracy;
+		} get_time;
+
+		struct xenpf_efi_time set_time;
+
+#define XEN_EFI_GET_WAKEUP_TIME_ENABLED 0x00000001
+#define XEN_EFI_GET_WAKEUP_TIME_PENDING 0x00000002
+		struct xenpf_efi_time get_wakeup_time;
+
+#define XEN_EFI_SET_WAKEUP_TIME_ENABLE      0x00000001
+#define XEN_EFI_SET_WAKEUP_TIME_ENABLE_ONLY 0x00000002
+		struct xenpf_efi_time set_wakeup_time;
+
+#define XEN_EFI_VARIABLE_NON_VOLATILE       0x00000001
+#define XEN_EFI_VARIABLE_BOOTSERVICE_ACCESS 0x00000002
+#define XEN_EFI_VARIABLE_RUNTIME_ACCESS     0x00000004
+		struct {
+			GUEST_HANDLE(void) name;  /* UCS-2/UTF-16 string */
+			xen_ulong_t size;
+			GUEST_HANDLE(void) data;
+			struct xenpf_efi_guid {
+				uint32_t data1;
+				uint16_t data2;
+				uint16_t data3;
+				uint8_t data4[8];
+			} vendor_guid;
+		} get_variable, set_variable;
+
+		struct {
+			xen_ulong_t size;
+			GUEST_HANDLE(void) name;  /* UCS-2/UTF-16 string */
+			struct xenpf_efi_guid vendor_guid;
+		} get_next_variable_name;
+
+		struct {
+			uint32_t attr;
+			uint64_t max_store_size;
+			uint64_t remain_store_size;
+			uint64_t max_size;
+		} query_variable_info;
+
+		struct {
+			GUEST_HANDLE(void) capsule_header_array;
+			xen_ulong_t capsule_count;
+			uint64_t max_capsule_size;
+			uint32_t reset_type;
+		} query_capsule_capabilities;
+
+		struct {
+			GUEST_HANDLE(void) capsule_header_array;
+			xen_ulong_t capsule_count;
+			uint64_t sg_list; /* machine address */
+		} update_capsule;
+	} u;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xenpf_efi_runtime_call);
+
+#define  XEN_FW_EFI_VERSION        0
+#define  XEN_FW_EFI_CONFIG_TABLE   1
+#define  XEN_FW_EFI_VENDOR         2
+#define  XEN_FW_EFI_MEM_INFO       3
+#define  XEN_FW_EFI_RT_VERSION     4
+
 #define XENPF_firmware_info       50
 #define XEN_FW_DISK_INFO          1 /* from int 13 AH=08/41/48 */
 #define XEN_FW_DISK_MBR_SIGNATURE 2 /* from MBR offset 0x1b8 */
 #define XEN_FW_VBEDDC_INFO        3 /* from int 10 AX=4f15 */
+#define XEN_FW_EFI_INFO           4 /* from EFI */
 #define XEN_FW_KBD_SHIFT_FLAGS    5 /* Int16, Fn02: Get keyboard shift flags. */
+
 struct xenpf_firmware_info {
 	/* IN variables. */
 	uint32_t type;
@@ -144,6 +246,26 @@ struct xenpf_firmware_info {
 			GUEST_HANDLE(uchar) edid;
 		} vbeddc_info; /* XEN_FW_VBEDDC_INFO */
 
+		union xenpf_efi_info {
+			uint32_t version;
+			struct {
+				uint64_t addr;   /* EFI_CONFIGURATION_TABLE */
+				uint32_t nent;
+			} cfg;
+			struct {
+				uint32_t revision;
+				uint32_t bufsz;  /* input, in bytes */
+				GUEST_HANDLE(void) name;
+				/* UCS-2/UTF-16 string */
+			} vendor;
+			struct {
+				uint64_t addr;
+				uint64_t size;
+				uint64_t attr;
+				uint32_t type;
+			} mem;
+		} efi_info; /* XEN_FW_EFI_INFO */
+
 		uint8_t kbd_shift_flags; /* XEN_FW_KBD_SHIFT_FLAGS */
 	} u;
 };
@@ -362,6 +484,7 @@ struct xen_platform_op {
 		struct xenpf_read_memtype      read_memtype;
 		struct xenpf_microcode_update  microcode;
 		struct xenpf_platform_quirk    platform_quirk;
+		struct xenpf_efi_runtime_call  efi_runtime_call;
 		struct xenpf_firmware_info     firmware_info;
 		struct xenpf_enter_acpi_sleep  enter_acpi_sleep;
 		struct xenpf_change_freq       change_freq;
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 0b3149ed7ea..7491ee5d816 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -3,6 +3,7 @@
 
 #include <linux/percpu.h>
 #include <linux/notifier.h>
+#include <linux/efi.h>
 #include <asm/xen/interface.h>
 
 DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
@@ -35,4 +36,14 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
 			       int numpgs, struct page **pages);
 
 bool xen_running_on_version_or_later(unsigned int major, unsigned int minor);
+
+#ifdef CONFIG_XEN_EFI
+extern efi_system_table_t *xen_efi_probe(void);
+#else
+static inline efi_system_table_t __init *xen_efi_probe(void)
+{
+	return NULL;
+}
+#endif
+
 #endif /* INCLUDE_XEN_OPS_H */
diff --git a/init/Kconfig b/init/Kconfig
index 9d76b99af1b..41066e49e88 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -505,7 +505,7 @@ config PREEMPT_RCU
 	def_bool TREE_PREEMPT_RCU
 	help
 	  This option enables preemptible-RCU code that is common between
-	  the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
+	  TREE_PREEMPT_RCU and, in the old days, TINY_PREEMPT_RCU.
 
 config RCU_STALL_COMMON
 	def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE )
@@ -737,7 +737,7 @@ choice
 
 config RCU_NOCB_CPU_NONE
 	bool "No build_forced no-CBs CPUs"
-	depends on RCU_NOCB_CPU && !NO_HZ_FULL
+	depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL
 	help
 	  This option does not force any of the CPUs to be no-CBs CPUs.
 	  Only CPUs designated by the rcu_nocbs= boot parameter will be
@@ -751,7 +751,7 @@ config RCU_NOCB_CPU_NONE
 
 config RCU_NOCB_CPU_ZERO
 	bool "CPU 0 is a build_forced no-CBs CPU"
-	depends on RCU_NOCB_CPU && !NO_HZ_FULL
+	depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL
 	help
 	  This option forces CPU 0 to be a no-CBs CPU, so that its RCU
 	  callbacks are invoked by a per-CPU kthread whose name begins
diff --git a/init/main.c b/init/main.c
index 0ec25157dee..e8ae1fef090 100644
--- a/init/main.c
+++ b/init/main.c
@@ -253,6 +253,27 @@ static int __init repair_env_string(char *param, char *val, const char *unused)
 	return 0;
 }
 
+/* Anything after -- gets handed straight to init. */
+static int __init set_init_arg(char *param, char *val, const char *unused)
+{
+	unsigned int i;
+
+	if (panic_later)
+		return 0;
+
+	repair_env_string(param, val, unused);
+
+	for (i = 0; argv_init[i]; i++) {
+		if (i == MAX_INIT_ARGS) {
+			panic_later = "init";
+			panic_param = param;
+			return 0;
+		}
+	}
+	argv_init[i] = param;
+	return 0;
+}
+
 /*
  * Unknown boot options get handed to init, unless they look like
  * unused parameters (modprobe will find them in /proc/cmdline).
@@ -479,7 +500,7 @@ static void __init mm_init(void)
 
 asmlinkage __visible void __init start_kernel(void)
 {
-	char * command_line;
+	char * command_line, *after_dashes;
 	extern const struct kernel_param __start___param[], __stop___param[];
 
 	/*
@@ -519,9 +540,13 @@ asmlinkage __visible void __init start_kernel(void)
 
 	pr_notice("Kernel command line: %s\n", boot_command_line);
 	parse_early_param();
-	parse_args("Booting kernel", static_command_line, __start___param,
-		   __stop___param - __start___param,
-		   -1, -1, &unknown_bootoption);
+	after_dashes = parse_args("Booting kernel",
+				  static_command_line, __start___param,
+				  __stop___param - __start___param,
+				  -1, -1, &unknown_bootoption);
+	if (after_dashes)
+		parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
+			   set_init_arg);
 
 	jump_label_init();
 
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index d2b32ac27a3..76768ee812b 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -220,6 +220,20 @@ config INLINE_WRITE_UNLOCK_IRQRESTORE
 
 endif
 
+config ARCH_SUPPORTS_ATOMIC_RMW
+	bool
+
 config MUTEX_SPIN_ON_OWNER
 	def_bool y
-	depends on SMP && !DEBUG_MUTEXES
+	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
+
+config RWSEM_SPIN_ON_OWNER
+       def_bool y
+       depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
+
+config ARCH_USE_QUEUE_RWLOCK
+	bool
+
+config QUEUE_RWLOCK
+	def_bool y if ARCH_USE_QUEUE_RWLOCK
+	depends on SMP
diff --git a/kernel/audit.c b/kernel/audit.c
index f30106459a3..3ef2e0e797e 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -424,6 +424,38 @@ static void kauditd_send_skb(struct sk_buff *skb)
 }
 
 /*
+ * kauditd_send_multicast_skb - send the skb to multicast userspace listeners
+ *
+ * This function doesn't consume an skb as might be expected since it has to
+ * copy it anyways.
+ */
+static void kauditd_send_multicast_skb(struct sk_buff *skb)
+{
+	struct sk_buff		*copy;
+	struct audit_net	*aunet = net_generic(&init_net, audit_net_id);
+	struct sock		*sock = aunet->nlsk;
+
+	if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG))
+		return;
+
+	/*
+	 * The seemingly wasteful skb_copy() rather than bumping the refcount
+	 * using skb_get() is necessary because non-standard mods are made to
+	 * the skb by the original kaudit unicast socket send routine.  The
+	 * existing auditd daemon assumes this breakage.  Fixing this would
+	 * require co-ordinating a change in the established protocol between
+	 * the kaudit kernel subsystem and the auditd userspace code.  There is
+	 * no reason for new multicast clients to continue with this
+	 * non-compliance.
+	 */
+	copy = skb_copy(skb, GFP_KERNEL);
+	if (!copy)
+		return;
+
+	nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL);
+}
+
+/*
  * flush_hold_queue - empty the hold queue if auditd appears
  *
  * If auditd just started, drain the queue of messages already
@@ -1076,10 +1108,22 @@ static void audit_receive(struct sk_buff  *skb)
 	mutex_unlock(&audit_cmd_mutex);
 }
 
+/* Run custom bind function on netlink socket group connect or bind requests. */
+static int audit_bind(int group)
+{
+	if (!capable(CAP_AUDIT_READ))
+		return -EPERM;
+
+	return 0;
+}
+
 static int __net_init audit_net_init(struct net *net)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input	= audit_receive,
+		.bind	= audit_bind,
+		.flags	= NL_CFG_F_NONROOT_RECV,
+		.groups	= AUDIT_NLGRP_MAX,
 	};
 
 	struct audit_net *aunet = net_generic(net, audit_net_id);
@@ -1901,10 +1945,10 @@ out:
  * audit_log_end - end one audit record
  * @ab: the audit_buffer
  *
- * The netlink_* functions cannot be called inside an irq context, so
- * the audit buffer is placed on a queue and a tasklet is scheduled to
- * remove them from the queue outside the irq context.  May be called in
- * any context.
+ * netlink_unicast() cannot be called inside an irq context because it blocks
+ * (last arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed
+ * on a queue and a tasklet is scheduled to remove them from the queue outside
+ * the irq context.  May be called in any context.
  */
 void audit_log_end(struct audit_buffer *ab)
 {
@@ -1914,6 +1958,18 @@ void audit_log_end(struct audit_buffer *ab)
 		audit_log_lost("rate limit exceeded");
 	} else {
 		struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
+
+		kauditd_send_multicast_skb(ab->skb);
+
+		/*
+		 * The original kaudit unicast socket sends up messages with
+		 * nlmsg_len set to the payload length rather than the entire
+		 * message length.  This breaks the standard set by netlink.
+		 * The existing auditd daemon assumes this breakage.  Fixing
+		 * this would require co-ordinating a change in the established
+		 * protocol between the kaudit kernel subsystem and the auditd
+		 * userspace code.
+		 */
 		nlh->nlmsg_len = ab->skb->len - NLMSG_HDRLEN;
 
 		if (audit_pid) {
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index f251a5e8d17..21eae3c05ec 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -728,6 +728,22 @@ static enum audit_state audit_filter_task(struct task_struct *tsk, char **key)
 	return AUDIT_BUILD_CONTEXT;
 }
 
+static int audit_in_mask(const struct audit_krule *rule, unsigned long val)
+{
+	int word, bit;
+
+	if (val > 0xffffffff)
+		return false;
+
+	word = AUDIT_WORD(val);
+	if (word >= AUDIT_BITMASK_SIZE)
+		return false;
+
+	bit = AUDIT_BIT(val);
+
+	return rule->mask[word] & bit;
+}
+
 /* At syscall entry and exit time, this filter is called if the
  * audit_state is not low enough that auditing cannot take place, but is
  * also not high enough that we already know we have to write an audit
@@ -745,11 +761,8 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 
 	rcu_read_lock();
 	if (!list_empty(list)) {
-		int word = AUDIT_WORD(ctx->major);
-		int bit  = AUDIT_BIT(ctx->major);
-
 		list_for_each_entry_rcu(e, list, list) {
-			if ((e->rule.mask[word] & bit) == bit &&
+			if (audit_in_mask(&e->rule, ctx->major) &&
 			    audit_filter_rules(tsk, &e->rule, ctx, NULL,
 					       &state, false)) {
 				rcu_read_unlock();
@@ -769,20 +782,16 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 static int audit_filter_inode_name(struct task_struct *tsk,
 				   struct audit_names *n,
 				   struct audit_context *ctx) {
-	int word, bit;
 	int h = audit_hash_ino((u32)n->ino);
 	struct list_head *list = &audit_inode_hash[h];
 	struct audit_entry *e;
 	enum audit_state state;
 
-	word = AUDIT_WORD(ctx->major);
-	bit  = AUDIT_BIT(ctx->major);
-
 	if (list_empty(list))
 		return 0;
 
 	list_for_each_entry_rcu(e, list, list) {
-		if ((e->rule.mask[word] & bit) == bit &&
+		if (audit_in_mask(&e->rule, ctx->major) &&
 		    audit_filter_rules(tsk, &e->rule, ctx, n, &state, false)) {
 			ctx->current_state = state;
 			return 1;
diff --git a/kernel/capability.c b/kernel/capability.c
index 84b2bbf443e..a5cf13c018c 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -424,23 +424,19 @@ bool capable(int cap)
 EXPORT_SYMBOL(capable);
 
 /**
- * inode_capable - Check superior capability over inode
+ * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
  * @inode: The inode in question
  * @cap: The capability in question
  *
- * Return true if the current task has the given superior capability
- * targeted at it's own user namespace and that the given inode is owned
- * by the current user namespace or a child namespace.
- *
- * Currently we check to see if an inode is owned by the current
- * user namespace by seeing if the inode's owner maps into the
- * current user namespace.
- *
+ * Return true if the current task has the given capability targeted at
+ * its own user namespace and that the given inode's uid and gid are
+ * mapped into the current user namespace.
  */
-bool inode_capable(const struct inode *inode, int cap)
+bool capable_wrt_inode_uidgid(const struct inode *inode, int cap)
 {
 	struct user_namespace *ns = current_user_ns();
 
-	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid);
+	return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid) &&
+		kgid_has_mapping(ns, inode->i_gid);
 }
-EXPORT_SYMBOL(inode_capable);
+EXPORT_SYMBOL(capable_wrt_inode_uidgid);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ceee0c54c6a..7dc8788cfd5 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -26,6 +26,8 @@
  *  distribution for more details.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/cgroup.h>
 #include <linux/cred.h>
 #include <linux/ctype.h>
@@ -70,15 +72,6 @@
 					 MAX_CFTYPE_NAME + 2)
 
 /*
- * cgroup_tree_mutex nests above cgroup_mutex and protects cftypes, file
- * creation/removal and hierarchy changing operations including cgroup
- * creation, removal, css association and controller rebinding.  This outer
- * lock is needed mainly to resolve the circular dependency between kernfs
- * active ref and cgroup_mutex.  cgroup_tree_mutex nests above both.
- */
-static DEFINE_MUTEX(cgroup_tree_mutex);
-
-/*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
  *
@@ -99,16 +92,21 @@ static DECLARE_RWSEM(css_set_rwsem);
 #endif
 
 /*
+ * Protects cgroup_idr and css_idr so that IDs can be released without
+ * grabbing cgroup_mutex.
+ */
+static DEFINE_SPINLOCK(cgroup_idr_lock);
+
+/*
  * Protects cgroup_subsys->release_agent_path.  Modifying it also requires
  * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
  */
 static DEFINE_SPINLOCK(release_agent_path_lock);
 
-#define cgroup_assert_mutexes_or_rcu_locked()				\
+#define cgroup_assert_mutex_or_rcu_locked()				\
 	rcu_lockdep_assert(rcu_read_lock_held() ||			\
-			   lockdep_is_held(&cgroup_tree_mutex) ||	\
 			   lockdep_is_held(&cgroup_mutex),		\
-			   "cgroup_[tree_]mutex or RCU read lock required");
+			   "cgroup_mutex or RCU read lock required");
 
 /*
  * cgroup destruction makes heavy use of work items and there can be a lot
@@ -151,6 +149,15 @@ struct cgroup_root cgrp_dfl_root;
  */
 static bool cgrp_dfl_root_visible;
 
+/*
+ * Set by the boot param of the same name and makes subsystems with NULL
+ * ->dfl_files to use ->legacy_files on the default hierarchy.
+ */
+static bool cgroup_legacy_files_on_dfl;
+
+/* some controllers are not supported in the default hierarchy */
+static unsigned int cgrp_dfl_root_inhibit_ss_mask;
+
 /* The list of hierarchy roots */
 
 static LIST_HEAD(cgroup_roots);
@@ -160,14 +167,13 @@ static int cgroup_root_count;
 static DEFINE_IDR(cgroup_hierarchy_idr);
 
 /*
- * Assign a monotonically increasing serial number to cgroups.  It
- * guarantees cgroups with bigger numbers are newer than those with smaller
- * numbers.  Also, as cgroups are always appended to the parent's
- * ->children list, it guarantees that sibling cgroups are always sorted in
- * the ascending serial number order on the list.  Protected by
- * cgroup_mutex.
+ * Assign a monotonically increasing serial number to csses.  It guarantees
+ * cgroups with bigger numbers are newer than those with smaller numbers.
+ * Also, as csses are always appended to the parent's ->children list, it
+ * guarantees that sibling csses are always sorted in the ascending serial
+ * number order on the list.  Protected by cgroup_mutex.
  */
-static u64 cgroup_serial_nr_next = 1;
+static u64 css_serial_nr_next = 1;
 
 /* This flag indicates whether tasks in the fork and exit paths should
  * check for fork/exit handlers to call. This avoids us having to do
@@ -176,21 +182,65 @@ static u64 cgroup_serial_nr_next = 1;
  */
 static int need_forkexit_callback __read_mostly;
 
-static struct cftype cgroup_base_files[];
+static struct cftype cgroup_dfl_base_files[];
+static struct cftype cgroup_legacy_base_files[];
 
 static void cgroup_put(struct cgroup *cgrp);
 static int rebind_subsystems(struct cgroup_root *dst_root,
-			     unsigned long ss_mask);
-static void cgroup_destroy_css_killed(struct cgroup *cgrp);
+			     unsigned int ss_mask);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
+static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
+		      bool visible);
+static void css_release(struct percpu_ref *ref);
+static void kill_css(struct cgroup_subsys_state *css);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 			      bool is_add);
 static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
 
+/* IDR wrappers which synchronize using cgroup_idr_lock */
+static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end,
+			    gfp_t gfp_mask)
+{
+	int ret;
+
+	idr_preload(gfp_mask);
+	spin_lock_bh(&cgroup_idr_lock);
+	ret = idr_alloc(idr, ptr, start, end, gfp_mask);
+	spin_unlock_bh(&cgroup_idr_lock);
+	idr_preload_end();
+	return ret;
+}
+
+static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id)
+{
+	void *ret;
+
+	spin_lock_bh(&cgroup_idr_lock);
+	ret = idr_replace(idr, ptr, id);
+	spin_unlock_bh(&cgroup_idr_lock);
+	return ret;
+}
+
+static void cgroup_idr_remove(struct idr *idr, int id)
+{
+	spin_lock_bh(&cgroup_idr_lock);
+	idr_remove(idr, id);
+	spin_unlock_bh(&cgroup_idr_lock);
+}
+
+static struct cgroup *cgroup_parent(struct cgroup *cgrp)
+{
+	struct cgroup_subsys_state *parent_css = cgrp->self.parent;
+
+	if (parent_css)
+		return container_of(parent_css, struct cgroup, self);
+	return NULL;
+}
+
 /**
  * cgroup_css - obtain a cgroup's css for the specified subsystem
  * @cgrp: the cgroup of interest
- * @ss: the subsystem of interest (%NULL returns the dummy_css)
+ * @ss: the subsystem of interest (%NULL returns @cgrp->self)
  *
  * Return @cgrp's css (cgroup_subsys_state) associated with @ss.  This
  * function must be called either under cgroup_mutex or rcu_read_lock() and
@@ -203,23 +253,49 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
 {
 	if (ss)
 		return rcu_dereference_check(cgrp->subsys[ss->id],
-					lockdep_is_held(&cgroup_tree_mutex) ||
 					lockdep_is_held(&cgroup_mutex));
 	else
-		return &cgrp->dummy_css;
+		return &cgrp->self;
+}
+
+/**
+ * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest (%NULL returns @cgrp->self)
+ *
+ * Similar to cgroup_css() but returns the effctive css, which is defined
+ * as the matching css of the nearest ancestor including self which has @ss
+ * enabled.  If @ss is associated with the hierarchy @cgrp is on, this
+ * function is guaranteed to return non-NULL css.
+ */
+static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
+						struct cgroup_subsys *ss)
+{
+	lockdep_assert_held(&cgroup_mutex);
+
+	if (!ss)
+		return &cgrp->self;
+
+	if (!(cgrp->root->subsys_mask & (1 << ss->id)))
+		return NULL;
+
+	while (cgroup_parent(cgrp) &&
+	       !(cgroup_parent(cgrp)->child_subsys_mask & (1 << ss->id)))
+		cgrp = cgroup_parent(cgrp);
+
+	return cgroup_css(cgrp, ss);
 }
 
 /* convenient tests for these bits */
 static inline bool cgroup_is_dead(const struct cgroup *cgrp)
 {
-	return test_bit(CGRP_DEAD, &cgrp->flags);
+	return !(cgrp->self.flags & CSS_ONLINE);
 }
 
-struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 {
-	struct kernfs_open_file *of = seq->private;
 	struct cgroup *cgrp = of->kn->parent->priv;
-	struct cftype *cft = seq_cft(seq);
+	struct cftype *cft = of_cft(of);
 
 	/*
 	 * This is open and unprotected implementation of cgroup_css().
@@ -232,9 +308,9 @@ struct cgroup_subsys_state *seq_css(struct seq_file *seq)
 	if (cft->ss)
 		return rcu_dereference_raw(cgrp->subsys[cft->ss->id]);
 	else
-		return &cgrp->dummy_css;
+		return &cgrp->self;
 }
-EXPORT_SYMBOL_GPL(seq_css);
+EXPORT_SYMBOL_GPL(of_css);
 
 /**
  * cgroup_is_descendant - test ancestry
@@ -250,7 +326,7 @@ bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
 	while (cgrp) {
 		if (cgrp == ancestor)
 			return true;
-		cgrp = cgrp->parent;
+		cgrp = cgroup_parent(cgrp);
 	}
 	return false;
 }
@@ -274,17 +350,30 @@ static int notify_on_release(const struct cgroup *cgrp)
  * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
  * @cgrp: the target cgroup to iterate css's of
  *
- * Should be called under cgroup_mutex.
+ * Should be called under cgroup_[tree_]mutex.
  */
 #define for_each_css(css, ssid, cgrp)					\
 	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	\
 		if (!((css) = rcu_dereference_check(			\
 				(cgrp)->subsys[(ssid)],			\
-				lockdep_is_held(&cgroup_tree_mutex) ||	\
 				lockdep_is_held(&cgroup_mutex)))) { }	\
 		else
 
 /**
+ * for_each_e_css - iterate all effective css's of a cgroup
+ * @css: the iteration cursor
+ * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end
+ * @cgrp: the target cgroup to iterate css's of
+ *
+ * Should be called under cgroup_[tree_]mutex.
+ */
+#define for_each_e_css(css, ssid, cgrp)					\
+	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	\
+		if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \
+			;						\
+		else
+
+/**
  * for_each_subsys - iterate all enabled cgroup subsystems
  * @ss: the iteration cursor
  * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
@@ -297,22 +386,13 @@ static int notify_on_release(const struct cgroup *cgrp)
 #define for_each_root(root)						\
 	list_for_each_entry((root), &cgroup_roots, root_list)
 
-/**
- * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
- * @cgrp: the cgroup to be checked for liveness
- *
- * On success, returns true; the mutex should be later unlocked.  On
- * failure returns false with no lock held.
- */
-static bool cgroup_lock_live_group(struct cgroup *cgrp)
-{
-	mutex_lock(&cgroup_mutex);
-	if (cgroup_is_dead(cgrp)) {
-		mutex_unlock(&cgroup_mutex);
-		return false;
-	}
-	return true;
-}
+/* iterate over child cgrps, lock should be held throughout iteration */
+#define cgroup_for_each_live_child(child, cgrp)				\
+	list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \
+		if (({ lockdep_assert_held(&cgroup_mutex);		\
+		       cgroup_is_dead(child); }))			\
+			;						\
+		else
 
 /* the list of cgroups eligible for automatic release. Protected by
  * release_list_lock */
@@ -360,6 +440,43 @@ struct css_set init_css_set = {
 
 static int css_set_count	= 1;	/* 1 for init_css_set */
 
+/**
+ * cgroup_update_populated - updated populated count of a cgroup
+ * @cgrp: the target cgroup
+ * @populated: inc or dec populated count
+ *
+ * @cgrp is either getting the first task (css_set) or losing the last.
+ * Update @cgrp->populated_cnt accordingly.  The count is propagated
+ * towards root so that a given cgroup's populated_cnt is zero iff the
+ * cgroup and all its descendants are empty.
+ *
+ * @cgrp's interface file "cgroup.populated" is zero if
+ * @cgrp->populated_cnt is zero and 1 otherwise.  When @cgrp->populated_cnt
+ * changes from or to zero, userland is notified that the content of the
+ * interface file has changed.  This can be used to detect when @cgrp and
+ * its descendants become populated or empty.
+ */
+static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
+{
+	lockdep_assert_held(&css_set_rwsem);
+
+	do {
+		bool trigger;
+
+		if (populated)
+			trigger = !cgrp->populated_cnt++;
+		else
+			trigger = !--cgrp->populated_cnt;
+
+		if (!trigger)
+			break;
+
+		if (cgrp->populated_kn)
+			kernfs_notify(cgrp->populated_kn);
+		cgrp = cgroup_parent(cgrp);
+	} while (cgrp);
+}
+
 /*
  * hash table for cgroup groups. This improves the performance to find
  * an existing css_set. This hash doesn't (currently) take into
@@ -384,6 +501,8 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
 static void put_css_set_locked(struct css_set *cset, bool taskexit)
 {
 	struct cgrp_cset_link *link, *tmp_link;
+	struct cgroup_subsys *ss;
+	int ssid;
 
 	lockdep_assert_held(&css_set_rwsem);
 
@@ -391,6 +510,8 @@ static void put_css_set_locked(struct css_set *cset, bool taskexit)
 		return;
 
 	/* This css_set is dead. unlink it and release cgroup refcounts */
+	for_each_subsys(ss, ssid)
+		list_del(&cset->e_cset_node[ssid]);
 	hash_del(&cset->hlist);
 	css_set_count--;
 
@@ -401,10 +522,13 @@ static void put_css_set_locked(struct css_set *cset, bool taskexit)
 		list_del(&link->cgrp_link);
 
 		/* @cgrp can't go away while we're holding css_set_rwsem */
-		if (list_empty(&cgrp->cset_links) && notify_on_release(cgrp)) {
-			if (taskexit)
-				set_bit(CGRP_RELEASABLE, &cgrp->flags);
-			check_for_release(cgrp);
+		if (list_empty(&cgrp->cset_links)) {
+			cgroup_update_populated(cgrp, false);
+			if (notify_on_release(cgrp)) {
+				if (taskexit)
+					set_bit(CGRP_RELEASABLE, &cgrp->flags);
+				check_for_release(cgrp);
+			}
 		}
 
 		kfree(link);
@@ -453,20 +577,20 @@ static bool compare_css_sets(struct css_set *cset,
 {
 	struct list_head *l1, *l2;
 
-	if (memcmp(template, cset->subsys, sizeof(cset->subsys))) {
-		/* Not all subsystems matched */
+	/*
+	 * On the default hierarchy, there can be csets which are
+	 * associated with the same set of cgroups but different csses.
+	 * Let's first ensure that csses match.
+	 */
+	if (memcmp(template, cset->subsys, sizeof(cset->subsys)))
 		return false;
-	}
 
 	/*
 	 * Compare cgroup pointers in order to distinguish between
-	 * different cgroups in heirarchies with no subsystems. We
-	 * could get by with just this check alone (and skip the
-	 * memcmp above) but on most setups the memcmp check will
-	 * avoid the need for this more expensive check on almost all
-	 * candidates.
+	 * different cgroups in hierarchies.  As different cgroups may
+	 * share the same effective css, this comparison is always
+	 * necessary.
 	 */
-
 	l1 = &cset->cgrp_links;
 	l2 = &old_cset->cgrp_links;
 	while (1) {
@@ -530,14 +654,17 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
 	 * won't change, so no need for locking.
 	 */
 	for_each_subsys(ss, i) {
-		if (root->cgrp.subsys_mask & (1UL << i)) {
-			/* Subsystem is in this hierarchy. So we want
-			 * the subsystem state from the new
-			 * cgroup */
-			template[i] = cgroup_css(cgrp, ss);
+		if (root->subsys_mask & (1UL << i)) {
+			/*
+			 * @ss is in this hierarchy, so we want the
+			 * effective css from @cgrp.
+			 */
+			template[i] = cgroup_e_css(cgrp, ss);
 		} else {
-			/* Subsystem is not in this hierarchy, so we
-			 * don't want to change the subsystem state */
+			/*
+			 * @ss is not in this hierarchy, so we don't want
+			 * to change the css.
+			 */
 			template[i] = old_cset->subsys[i];
 		}
 	}
@@ -603,10 +730,18 @@ static void link_css_set(struct list_head *tmp_links, struct css_set *cset,
 	struct cgrp_cset_link *link;
 
 	BUG_ON(list_empty(tmp_links));
+
+	if (cgroup_on_dfl(cgrp))
+		cset->dfl_cgrp = cgrp;
+
 	link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link);
 	link->cset = cset;
 	link->cgrp = cgrp;
+
+	if (list_empty(&cgrp->cset_links))
+		cgroup_update_populated(cgrp, true);
 	list_move(&link->cset_link, &cgrp->cset_links);
+
 	/*
 	 * Always add links to the tail of the list so that the list
 	 * is sorted by order of hierarchy creation
@@ -629,7 +764,9 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	struct css_set *cset;
 	struct list_head tmp_links;
 	struct cgrp_cset_link *link;
+	struct cgroup_subsys *ss;
 	unsigned long key;
+	int ssid;
 
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -680,10 +817,14 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 
 	css_set_count++;
 
-	/* Add this cgroup group to the hash table */
+	/* Add @cset to the hash table */
 	key = css_set_hash(cset->subsys);
 	hash_add(css_set_table, &cset->hlist, key);
 
+	for_each_subsys(ss, ssid)
+		list_add_tail(&cset->e_cset_node[ssid],
+			      &cset->subsys[ssid]->cgroup->e_csets[ssid]);
+
 	up_write(&css_set_rwsem);
 
 	return cset;
@@ -736,14 +877,13 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 	struct cgroup *cgrp = &root->cgrp;
 	struct cgrp_cset_link *link, *tmp_link;
 
-	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
 	BUG_ON(atomic_read(&root->nr_cgrps));
-	BUG_ON(!list_empty(&cgrp->children));
+	BUG_ON(!list_empty(&cgrp->self.children));
 
 	/* Rebind all subsystems back to the default hierarchy */
-	rebind_subsystems(&cgrp_dfl_root, cgrp->subsys_mask);
+	rebind_subsystems(&cgrp_dfl_root, root->subsys_mask);
 
 	/*
 	 * Release all the links from cset_links to this hierarchy's
@@ -766,7 +906,6 @@ static void cgroup_destroy_root(struct cgroup_root *root)
 	cgroup_exit_root_id(root);
 
 	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
 
 	kernfs_destroy_root(root->kf_root);
 	cgroup_free_root(root);
@@ -849,7 +988,7 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * update of a tasks cgroup pointer by cgroup_attach_task()
  */
 
-static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask);
+static int cgroup_populate_dir(struct cgroup *cgrp, unsigned int subsys_mask);
 static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
 static const struct file_operations proc_cgroupstats_operations;
 
@@ -884,79 +1023,147 @@ static umode_t cgroup_file_mode(const struct cftype *cft)
 	if (cft->read_u64 || cft->read_s64 || cft->seq_show)
 		mode |= S_IRUGO;
 
-	if (cft->write_u64 || cft->write_s64 || cft->write_string ||
-	    cft->trigger)
+	if (cft->write_u64 || cft->write_s64 || cft->write)
 		mode |= S_IWUSR;
 
 	return mode;
 }
 
-static void cgroup_free_fn(struct work_struct *work)
+static void cgroup_get(struct cgroup *cgrp)
 {
-	struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work);
+	WARN_ON_ONCE(cgroup_is_dead(cgrp));
+	css_get(&cgrp->self);
+}
 
-	atomic_dec(&cgrp->root->nr_cgrps);
-	cgroup_pidlist_destroy_all(cgrp);
+static void cgroup_put(struct cgroup *cgrp)
+{
+	css_put(&cgrp->self);
+}
+
+/**
+ * cgroup_refresh_child_subsys_mask - update child_subsys_mask
+ * @cgrp: the target cgroup
+ *
+ * On the default hierarchy, a subsystem may request other subsystems to be
+ * enabled together through its ->depends_on mask.  In such cases, more
+ * subsystems than specified in "cgroup.subtree_control" may be enabled.
+ *
+ * This function determines which subsystems need to be enabled given the
+ * current @cgrp->subtree_control and records it in
+ * @cgrp->child_subsys_mask.  The resulting mask is always a superset of
+ * @cgrp->subtree_control and follows the usual hierarchy rules.
+ */
+static void cgroup_refresh_child_subsys_mask(struct cgroup *cgrp)
+{
+	struct cgroup *parent = cgroup_parent(cgrp);
+	unsigned int cur_ss_mask = cgrp->subtree_control;
+	struct cgroup_subsys *ss;
+	int ssid;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	if (!cgroup_on_dfl(cgrp)) {
+		cgrp->child_subsys_mask = cur_ss_mask;
+		return;
+	}
+
+	while (true) {
+		unsigned int new_ss_mask = cur_ss_mask;
+
+		for_each_subsys(ss, ssid)
+			if (cur_ss_mask & (1 << ssid))
+				new_ss_mask |= ss->depends_on;
 
-	if (cgrp->parent) {
-		/*
-		 * We get a ref to the parent, and put the ref when this
-		 * cgroup is being freed, so it's guaranteed that the
-		 * parent won't be destroyed before its children.
-		 */
-		cgroup_put(cgrp->parent);
-		kernfs_put(cgrp->kn);
-		kfree(cgrp);
-	} else {
 		/*
-		 * This is root cgroup's refcnt reaching zero, which
-		 * indicates that the root should be released.
+		 * Mask out subsystems which aren't available.  This can
+		 * happen only if some depended-upon subsystems were bound
+		 * to non-default hierarchies.
 		 */
-		cgroup_destroy_root(cgrp->root);
+		if (parent)
+			new_ss_mask &= parent->child_subsys_mask;
+		else
+			new_ss_mask &= cgrp->root->subsys_mask;
+
+		if (new_ss_mask == cur_ss_mask)
+			break;
+		cur_ss_mask = new_ss_mask;
 	}
+
+	cgrp->child_subsys_mask = cur_ss_mask;
 }
 
-static void cgroup_free_rcu(struct rcu_head *head)
+/**
+ * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods
+ * @kn: the kernfs_node being serviced
+ *
+ * This helper undoes cgroup_kn_lock_live() and should be invoked before
+ * the method finishes if locking succeeded.  Note that once this function
+ * returns the cgroup returned by cgroup_kn_lock_live() may become
+ * inaccessible any time.  If the caller intends to continue to access the
+ * cgroup, it should pin it before invoking this function.
+ */
+static void cgroup_kn_unlock(struct kernfs_node *kn)
 {
-	struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head);
+	struct cgroup *cgrp;
 
-	INIT_WORK(&cgrp->destroy_work, cgroup_free_fn);
-	queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
-}
+	if (kernfs_type(kn) == KERNFS_DIR)
+		cgrp = kn->priv;
+	else
+		cgrp = kn->parent->priv;
 
-static void cgroup_get(struct cgroup *cgrp)
-{
-	WARN_ON_ONCE(cgroup_is_dead(cgrp));
-	WARN_ON_ONCE(atomic_read(&cgrp->refcnt) <= 0);
-	atomic_inc(&cgrp->refcnt);
+	mutex_unlock(&cgroup_mutex);
+
+	kernfs_unbreak_active_protection(kn);
+	cgroup_put(cgrp);
 }
 
-static void cgroup_put(struct cgroup *cgrp)
+/**
+ * cgroup_kn_lock_live - locking helper for cgroup kernfs methods
+ * @kn: the kernfs_node being serviced
+ *
+ * This helper is to be used by a cgroup kernfs method currently servicing
+ * @kn.  It breaks the active protection, performs cgroup locking and
+ * verifies that the associated cgroup is alive.  Returns the cgroup if
+ * alive; otherwise, %NULL.  A successful return should be undone by a
+ * matching cgroup_kn_unlock() invocation.
+ *
+ * Any cgroup kernfs method implementation which requires locking the
+ * associated cgroup should use this helper.  It avoids nesting cgroup
+ * locking under kernfs active protection and allows all kernfs operations
+ * including self-removal.
+ */
+static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn)
 {
-	if (!atomic_dec_and_test(&cgrp->refcnt))
-		return;
-	if (WARN_ON_ONCE(cgrp->parent && !cgroup_is_dead(cgrp)))
-		return;
+	struct cgroup *cgrp;
+
+	if (kernfs_type(kn) == KERNFS_DIR)
+		cgrp = kn->priv;
+	else
+		cgrp = kn->parent->priv;
 
 	/*
-	 * XXX: cgrp->id is only used to look up css's.  As cgroup and
-	 * css's lifetimes will be decoupled, it should be made
-	 * per-subsystem and moved to css->id so that lookups are
-	 * successful until the target css is released.
+	 * We're gonna grab cgroup_mutex which nests outside kernfs
+	 * active_ref.  cgroup liveliness check alone provides enough
+	 * protection against removal.  Ensure @cgrp stays accessible and
+	 * break the active_ref protection.
 	 */
+	cgroup_get(cgrp);
+	kernfs_break_active_protection(kn);
+
 	mutex_lock(&cgroup_mutex);
-	idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
-	mutex_unlock(&cgroup_mutex);
-	cgrp->id = -1;
 
-	call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
+	if (!cgroup_is_dead(cgrp))
+		return cgrp;
+
+	cgroup_kn_unlock(kn);
+	return NULL;
 }
 
 static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 {
 	char name[CGROUP_FILE_NAME_MAX];
 
-	lockdep_assert_held(&cgroup_tree_mutex);
+	lockdep_assert_held(&cgroup_mutex);
 	kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
 }
 
@@ -965,7 +1172,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
  * @cgrp: target cgroup
  * @subsys_mask: mask of the subsystem ids whose files should be removed
  */
-static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask)
+static void cgroup_clear_dir(struct cgroup *cgrp, unsigned int subsys_mask)
 {
 	struct cgroup_subsys *ss;
 	int i;
@@ -973,40 +1180,40 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 	for_each_subsys(ss, i) {
 		struct cftype *cfts;
 
-		if (!test_bit(i, &subsys_mask))
+		if (!(subsys_mask & (1 << i)))
 			continue;
 		list_for_each_entry(cfts, &ss->cfts, node)
 			cgroup_addrm_files(cgrp, cfts, false);
 	}
 }
 
-static int rebind_subsystems(struct cgroup_root *dst_root,
-			     unsigned long ss_mask)
+static int rebind_subsystems(struct cgroup_root *dst_root, unsigned int ss_mask)
 {
 	struct cgroup_subsys *ss;
-	int ssid, ret;
+	unsigned int tmp_ss_mask;
+	int ssid, i, ret;
 
-	lockdep_assert_held(&cgroup_tree_mutex);
 	lockdep_assert_held(&cgroup_mutex);
 
 	for_each_subsys(ss, ssid) {
 		if (!(ss_mask & (1 << ssid)))
 			continue;
 
-		/* if @ss is on the dummy_root, we can always move it */
-		if (ss->root == &cgrp_dfl_root)
-			continue;
-
-		/* if @ss has non-root cgroups attached to it, can't move */
-		if (!list_empty(&ss->root->cgrp.children))
+		/* if @ss has non-root csses attached to it, can't move */
+		if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)))
 			return -EBUSY;
 
 		/* can't move between two non-dummy roots either */
-		if (dst_root != &cgrp_dfl_root)
+		if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root)
 			return -EBUSY;
 	}
 
-	ret = cgroup_populate_dir(&dst_root->cgrp, ss_mask);
+	/* skip creating root files on dfl_root for inhibited subsystems */
+	tmp_ss_mask = ss_mask;
+	if (dst_root == &cgrp_dfl_root)
+		tmp_ss_mask &= ~cgrp_dfl_root_inhibit_ss_mask;
+
+	ret = cgroup_populate_dir(&dst_root->cgrp, tmp_ss_mask);
 	if (ret) {
 		if (dst_root != &cgrp_dfl_root)
 			return ret;
@@ -1018,9 +1225,9 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
 		 * Just warn about it and continue.
 		 */
 		if (cgrp_dfl_root_visible) {
-			pr_warning("cgroup: failed to create files (%d) while rebinding 0x%lx to default root\n",
-				   ret, ss_mask);
-			pr_warning("cgroup: you may retry by moving them to a different hierarchy and unbinding\n");
+			pr_warn("failed to create files (%d) while rebinding 0x%x to default root\n",
+				ret, ss_mask);
+			pr_warn("you may retry by moving them to a different hierarchy and unbinding\n");
 		}
 	}
 
@@ -1028,15 +1235,14 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
 	 * Nothing can fail from this point on.  Remove files for the
 	 * removed subsystems and rebind each subsystem.
 	 */
-	mutex_unlock(&cgroup_mutex);
 	for_each_subsys(ss, ssid)
 		if (ss_mask & (1 << ssid))
 			cgroup_clear_dir(&ss->root->cgrp, 1 << ssid);
-	mutex_lock(&cgroup_mutex);
 
 	for_each_subsys(ss, ssid) {
 		struct cgroup_root *src_root;
 		struct cgroup_subsys_state *css;
+		struct css_set *cset;
 
 		if (!(ss_mask & (1 << ssid)))
 			continue;
@@ -1051,8 +1257,22 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
 		ss->root = dst_root;
 		css->cgroup = &dst_root->cgrp;
 
-		src_root->cgrp.subsys_mask &= ~(1 << ssid);
-		dst_root->cgrp.subsys_mask |= 1 << ssid;
+		down_write(&css_set_rwsem);
+		hash_for_each(css_set_table, i, cset, hlist)
+			list_move_tail(&cset->e_cset_node[ss->id],
+				       &dst_root->cgrp.e_csets[ss->id]);
+		up_write(&css_set_rwsem);
+
+		src_root->subsys_mask &= ~(1 << ssid);
+		src_root->cgrp.subtree_control &= ~(1 << ssid);
+		cgroup_refresh_child_subsys_mask(&src_root->cgrp);
+
+		/* default hierarchy doesn't enable controllers by default */
+		dst_root->subsys_mask |= 1 << ssid;
+		if (dst_root != &cgrp_dfl_root) {
+			dst_root->cgrp.subtree_control |= 1 << ssid;
+			cgroup_refresh_child_subsys_mask(&dst_root->cgrp);
+		}
 
 		if (ss->bind)
 			ss->bind(css);
@@ -1070,10 +1290,8 @@ static int cgroup_show_options(struct seq_file *seq,
 	int ssid;
 
 	for_each_subsys(ss, ssid)
-		if (root->cgrp.subsys_mask & (1 << ssid))
+		if (root->subsys_mask & (1 << ssid))
 			seq_printf(seq, ",%s", ss->name);
-	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
-		seq_puts(seq, ",sane_behavior");
 	if (root->flags & CGRP_ROOT_NOPREFIX)
 		seq_puts(seq, ",noprefix");
 	if (root->flags & CGRP_ROOT_XATTR)
@@ -1092,8 +1310,8 @@ static int cgroup_show_options(struct seq_file *seq,
 }
 
 struct cgroup_sb_opts {
-	unsigned long subsys_mask;
-	unsigned long flags;
+	unsigned int subsys_mask;
+	unsigned int flags;
 	char *release_agent;
 	bool cpuset_clone_children;
 	char *name;
@@ -1101,29 +1319,24 @@ struct cgroup_sb_opts {
 	bool none;
 };
 
-/*
- * Convert a hierarchy specifier into a bitmask of subsystems and
- * flags. Call with cgroup_mutex held to protect the cgroup_subsys[]
- * array. This function takes refcounts on subsystems to be used, unless it
- * returns error, in which case no refcounts are taken.
- */
 static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 {
 	char *token, *o = data;
 	bool all_ss = false, one_ss = false;
-	unsigned long mask = (unsigned long)-1;
+	unsigned int mask = -1U;
 	struct cgroup_subsys *ss;
+	int nr_opts = 0;
 	int i;
 
-	BUG_ON(!mutex_is_locked(&cgroup_mutex));
-
 #ifdef CONFIG_CPUSETS
-	mask = ~(1UL << cpuset_cgrp_id);
+	mask = ~(1U << cpuset_cgrp_id);
 #endif
 
 	memset(opts, 0, sizeof(*opts));
 
 	while ((token = strsep(&o, ",")) != NULL) {
+		nr_opts++;
+
 		if (!*token)
 			return -EINVAL;
 		if (!strcmp(token, "none")) {
@@ -1199,7 +1412,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			/* Mutually exclusive option 'all' + subsystem name */
 			if (all_ss)
 				return -EINVAL;
-			set_bit(i, &opts->subsys_mask);
+			opts->subsys_mask |= (1 << i);
 			one_ss = true;
 
 			break;
@@ -1208,37 +1421,33 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			return -ENOENT;
 	}
 
-	/* Consistency checks */
-
 	if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
-		pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
-
-		if ((opts->flags & (CGRP_ROOT_NOPREFIX | CGRP_ROOT_XATTR)) ||
-		    opts->cpuset_clone_children || opts->release_agent ||
-		    opts->name) {
-			pr_err("cgroup: sane_behavior: noprefix, xattr, clone_children, release_agent and name are not allowed\n");
+		pr_warn("sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
+		if (nr_opts != 1) {
+			pr_err("sane_behavior: no other mount options allowed\n");
 			return -EINVAL;
 		}
-	} else {
-		/*
-		 * If the 'all' option was specified select all the
-		 * subsystems, otherwise if 'none', 'name=' and a subsystem
-		 * name options were not specified, let's default to 'all'
-		 */
-		if (all_ss || (!one_ss && !opts->none && !opts->name))
-			for_each_subsys(ss, i)
-				if (!ss->disabled)
-					set_bit(i, &opts->subsys_mask);
-
-		/*
-		 * We either have to specify by name or by subsystems. (So
-		 * all empty hierarchies must have a name).
-		 */
-		if (!opts->subsys_mask && !opts->name)
-			return -EINVAL;
+		return 0;
 	}
 
 	/*
+	 * If the 'all' option was specified select all the subsystems,
+	 * otherwise if 'none', 'name=' and a subsystem name options were
+	 * not specified, let's default to 'all'
+	 */
+	if (all_ss || (!one_ss && !opts->none && !opts->name))
+		for_each_subsys(ss, i)
+			if (!ss->disabled)
+				opts->subsys_mask |= (1 << i);
+
+	/*
+	 * We either have to specify by name or by subsystems. (So all
+	 * empty hierarchies must have a name).
+	 */
+	if (!opts->subsys_mask && !opts->name)
+		return -EINVAL;
+
+	/*
 	 * Option noprefix was introduced just for backward compatibility
 	 * with the old cpuset, so we allow noprefix only if mounting just
 	 * the cpuset subsystem.
@@ -1246,7 +1455,6 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask))
 		return -EINVAL;
 
-
 	/* Can't specify "none" and some subsystems */
 	if (opts->subsys_mask && opts->none)
 		return -EINVAL;
@@ -1259,14 +1467,13 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 	int ret = 0;
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 	struct cgroup_sb_opts opts;
-	unsigned long added_mask, removed_mask;
+	unsigned int added_mask, removed_mask;
 
-	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR) {
-		pr_err("cgroup: sane_behavior: remount is not allowed\n");
+	if (root == &cgrp_dfl_root) {
+		pr_err("remount is not allowed\n");
 		return -EINVAL;
 	}
 
-	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
 	/* See what subsystems are wanted */
@@ -1274,25 +1481,24 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 	if (ret)
 		goto out_unlock;
 
-	if (opts.subsys_mask != root->cgrp.subsys_mask || opts.release_agent)
-		pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n",
-			   task_tgid_nr(current), current->comm);
+	if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
+		pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n",
+			task_tgid_nr(current), current->comm);
 
-	added_mask = opts.subsys_mask & ~root->cgrp.subsys_mask;
-	removed_mask = root->cgrp.subsys_mask & ~opts.subsys_mask;
+	added_mask = opts.subsys_mask & ~root->subsys_mask;
+	removed_mask = root->subsys_mask & ~opts.subsys_mask;
 
 	/* Don't allow flags or name to change at remount */
-	if (((opts.flags ^ root->flags) & CGRP_ROOT_OPTION_MASK) ||
+	if ((opts.flags ^ root->flags) ||
 	    (opts.name && strcmp(opts.name, root->name))) {
-		pr_err("cgroup: option or name mismatch, new: 0x%lx \"%s\", old: 0x%lx \"%s\"\n",
-		       opts.flags & CGRP_ROOT_OPTION_MASK, opts.name ?: "",
-		       root->flags & CGRP_ROOT_OPTION_MASK, root->name);
+		pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n",
+		       opts.flags, opts.name ?: "", root->flags, root->name);
 		ret = -EINVAL;
 		goto out_unlock;
 	}
 
 	/* remounting is not allowed for populated hierarchies */
-	if (!list_empty(&root->cgrp.children)) {
+	if (!list_empty(&root->cgrp.self.children)) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -1312,7 +1518,6 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 	kfree(opts.release_agent);
 	kfree(opts.name);
 	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
 	return ret;
 }
 
@@ -1370,14 +1575,22 @@ out_unlock:
 
 static void init_cgroup_housekeeping(struct cgroup *cgrp)
 {
-	atomic_set(&cgrp->refcnt, 1);
-	INIT_LIST_HEAD(&cgrp->sibling);
-	INIT_LIST_HEAD(&cgrp->children);
+	struct cgroup_subsys *ss;
+	int ssid;
+
+	INIT_LIST_HEAD(&cgrp->self.sibling);
+	INIT_LIST_HEAD(&cgrp->self.children);
 	INIT_LIST_HEAD(&cgrp->cset_links);
 	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
-	cgrp->dummy_css.cgroup = cgrp;
+	cgrp->self.cgroup = cgrp;
+	cgrp->self.flags |= CSS_ONLINE;
+
+	for_each_subsys(ss, ssid)
+		INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
+
+	init_waitqueue_head(&cgrp->offline_waitq);
 }
 
 static void init_cgroup_root(struct cgroup_root *root,
@@ -1400,21 +1613,25 @@ static void init_cgroup_root(struct cgroup_root *root,
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
 
-static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
+static int cgroup_setup_root(struct cgroup_root *root, unsigned int ss_mask)
 {
 	LIST_HEAD(tmp_links);
 	struct cgroup *root_cgrp = &root->cgrp;
+	struct cftype *base_files;
 	struct css_set *cset;
 	int i, ret;
 
-	lockdep_assert_held(&cgroup_tree_mutex);
 	lockdep_assert_held(&cgroup_mutex);
 
-	ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
+	ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_NOWAIT);
 	if (ret < 0)
 		goto out;
 	root_cgrp->id = ret;
 
+	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release);
+	if (ret)
+		goto out;
+
 	/*
 	 * We're accessing css_set_count without locking css_set_rwsem here,
 	 * but that's OK - it can only be increased by someone holding
@@ -1423,11 +1640,11 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 	 */
 	ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
 	if (ret)
-		goto out;
+		goto cancel_ref;
 
 	ret = cgroup_init_root_id(root);
 	if (ret)
-		goto out;
+		goto cancel_ref;
 
 	root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
 					   KERNFS_ROOT_CREATE_DEACTIVATED,
@@ -1438,7 +1655,12 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 	}
 	root_cgrp->kn = root->kf_root->kn;
 
-	ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
+	if (root == &cgrp_dfl_root)
+		base_files = cgroup_dfl_base_files;
+	else
+		base_files = cgroup_legacy_base_files;
+
+	ret = cgroup_addrm_files(root_cgrp, base_files, true);
 	if (ret)
 		goto destroy_root;
 
@@ -1463,7 +1685,7 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 		link_css_set(&tmp_links, cset, root_cgrp);
 	up_write(&css_set_rwsem);
 
-	BUG_ON(!list_empty(&root_cgrp->children));
+	BUG_ON(!list_empty(&root_cgrp->self.children));
 	BUG_ON(atomic_read(&root->nr_cgrps) != 1);
 
 	kernfs_activate(root_cgrp->kn);
@@ -1475,6 +1697,8 @@ destroy_root:
 	root->kf_root = NULL;
 exit_root_id:
 	cgroup_exit_root_id(root);
+cancel_ref:
+	percpu_ref_exit(&root_cgrp->self.refcnt);
 out:
 	free_cgrp_cset_links(&tmp_links);
 	return ret;
@@ -1484,10 +1708,13 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 			 int flags, const char *unused_dev_name,
 			 void *data)
 {
+	struct super_block *pinned_sb = NULL;
+	struct cgroup_subsys *ss;
 	struct cgroup_root *root;
 	struct cgroup_sb_opts opts;
 	struct dentry *dentry;
 	int ret;
+	int i;
 	bool new_sb;
 
 	/*
@@ -1497,16 +1724,15 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	if (!use_task_css_set_links)
 		cgroup_enable_task_cg_lists();
 
-	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
 	/* First find the desired set of subsystems */
 	ret = parse_cgroupfs_options(data, &opts);
 	if (ret)
 		goto out_unlock;
-retry:
+
 	/* look for a matching existing root */
-	if (!opts.subsys_mask && !opts.none && !opts.name) {
+	if (opts.flags & CGRP_ROOT_SANE_BEHAVIOR) {
 		cgrp_dfl_root_visible = true;
 		root = &cgrp_dfl_root;
 		cgroup_get(&root->cgrp);
@@ -1514,6 +1740,27 @@ retry:
 		goto out_unlock;
 	}
 
+	/*
+	 * Destruction of cgroup root is asynchronous, so subsystems may
+	 * still be dying after the previous unmount.  Let's drain the
+	 * dying subsystems.  We just need to ensure that the ones
+	 * unmounted previously finish dying and don't care about new ones
+	 * starting.  Testing ref liveliness is good enough.
+	 */
+	for_each_subsys(ss, i) {
+		if (!(opts.subsys_mask & (1 << i)) ||
+		    ss->root == &cgrp_dfl_root)
+			continue;
+
+		if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) {
+			mutex_unlock(&cgroup_mutex);
+			msleep(10);
+			ret = restart_syscall();
+			goto out_free;
+		}
+		cgroup_put(&ss->root->cgrp);
+	}
+
 	for_each_root(root) {
 		bool name_match = false;
 
@@ -1536,37 +1783,37 @@ retry:
 		 * subsystems) then they must match.
 		 */
 		if ((opts.subsys_mask || opts.none) &&
-		    (opts.subsys_mask != root->cgrp.subsys_mask)) {
+		    (opts.subsys_mask != root->subsys_mask)) {
 			if (!name_match)
 				continue;
 			ret = -EBUSY;
 			goto out_unlock;
 		}
 
-		if ((root->flags ^ opts.flags) & CGRP_ROOT_OPTION_MASK) {
-			if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) {
-				pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
-				ret = -EINVAL;
-				goto out_unlock;
-			} else {
-				pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
-			}
-		}
+		if (root->flags ^ opts.flags)
+			pr_warn("new mount options do not match the existing superblock, will be ignored\n");
 
 		/*
-		 * A root's lifetime is governed by its root cgroup.  Zero
-		 * ref indicate that the root is being destroyed.  Wait for
-		 * destruction to complete so that the subsystems are free.
-		 * We can use wait_queue for the wait but this path is
-		 * super cold.  Let's just sleep for a bit and retry.
+		 * We want to reuse @root whose lifetime is governed by its
+		 * ->cgrp.  Let's check whether @root is alive and keep it
+		 * that way.  As cgroup_kill_sb() can happen anytime, we
+		 * want to block it by pinning the sb so that @root doesn't
+		 * get killed before mount is complete.
+		 *
+		 * With the sb pinned, tryget_live can reliably indicate
+		 * whether @root can be reused.  If it's being killed,
+		 * drain it.  We can use wait_queue for the wait but this
+		 * path is super cold.  Let's just sleep a bit and retry.
 		 */
-		if (!atomic_inc_not_zero(&root->cgrp.refcnt)) {
+		pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
+		if (IS_ERR(pinned_sb) ||
+		    !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
 			mutex_unlock(&cgroup_mutex);
-			mutex_unlock(&cgroup_tree_mutex);
+			if (!IS_ERR_OR_NULL(pinned_sb))
+				deactivate_super(pinned_sb);
 			msleep(10);
-			mutex_lock(&cgroup_tree_mutex);
-			mutex_lock(&cgroup_mutex);
-			goto retry;
+			ret = restart_syscall();
+			goto out_free;
 		}
 
 		ret = 0;
@@ -1597,8 +1844,7 @@ retry:
 
 out_unlock:
 	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
-
+out_free:
 	kfree(opts.release_agent);
 	kfree(opts.name);
 
@@ -1609,6 +1855,16 @@ out_unlock:
 				CGROUP_SUPER_MAGIC, &new_sb);
 	if (IS_ERR(dentry) || !new_sb)
 		cgroup_put(&root->cgrp);
+
+	/*
+	 * If @pinned_sb, we're reusing an existing root and holding an
+	 * extra ref on its sb.  Mount is complete.  Put the extra ref.
+	 */
+	if (pinned_sb) {
+		WARN_ON(new_sb);
+		deactivate_super(pinned_sb);
+	}
+
 	return dentry;
 }
 
@@ -1617,7 +1873,19 @@ static void cgroup_kill_sb(struct super_block *sb)
 	struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 
-	cgroup_put(&root->cgrp);
+	/*
+	 * If @root doesn't have any mounts or children, start killing it.
+	 * This prevents new mounts by disabling percpu_ref_tryget_live().
+	 * cgroup_mount() may wait for @root's release.
+	 *
+	 * And don't kill the default root.
+	 */
+	if (css_has_online_children(&root->cgrp.self) ||
+	    root == &cgrp_dfl_root)
+		cgroup_put(&root->cgrp);
+	else
+		percpu_ref_kill(&root->cgrp.self.refcnt);
+
 	kernfs_kill_sb(sb);
 }
 
@@ -1739,7 +2007,7 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
 
 /**
  * cgroup_task_migrate - move a task from one cgroup to another.
- * @old_cgrp; the cgroup @tsk is being migrated from
+ * @old_cgrp: the cgroup @tsk is being migrated from
  * @tsk: the task being migrated
  * @new_cset: the new css_set @tsk is being attached to
  *
@@ -1831,10 +2099,6 @@ static void cgroup_migrate_add_src(struct css_set *src_cset,
 
 	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
 
-	/* nothing to do if this cset already belongs to the cgroup */
-	if (src_cgrp == dst_cgrp)
-		return;
-
 	if (!list_empty(&src_cset->mg_preload_node))
 		return;
 
@@ -1849,13 +2113,14 @@ static void cgroup_migrate_add_src(struct css_set *src_cset,
 
 /**
  * cgroup_migrate_prepare_dst - prepare destination css_sets for migration
- * @dst_cgrp: the destination cgroup
+ * @dst_cgrp: the destination cgroup (may be %NULL)
  * @preloaded_csets: list of preloaded source css_sets
  *
  * Tasks are about to be moved to @dst_cgrp and all the source css_sets
  * have been preloaded to @preloaded_csets.  This function looks up and
- * pins all destination css_sets, links each to its source, and put them on
- * @preloaded_csets.
+ * pins all destination css_sets, links each to its source, and append them
+ * to @preloaded_csets.  If @dst_cgrp is %NULL, the destination of each
+ * source css_set is assumed to be its cgroup on the default hierarchy.
  *
  * This function must be called after cgroup_migrate_add_src() has been
  * called on each migration source css_set.  After migration is performed
@@ -1866,19 +2131,42 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
 				      struct list_head *preloaded_csets)
 {
 	LIST_HEAD(csets);
-	struct css_set *src_cset;
+	struct css_set *src_cset, *tmp_cset;
 
 	lockdep_assert_held(&cgroup_mutex);
 
+	/*
+	 * Except for the root, child_subsys_mask must be zero for a cgroup
+	 * with tasks so that child cgroups don't compete against tasks.
+	 */
+	if (dst_cgrp && cgroup_on_dfl(dst_cgrp) && cgroup_parent(dst_cgrp) &&
+	    dst_cgrp->child_subsys_mask)
+		return -EBUSY;
+
 	/* look up the dst cset for each src cset and link it to src */
-	list_for_each_entry(src_cset, preloaded_csets, mg_preload_node) {
+	list_for_each_entry_safe(src_cset, tmp_cset, preloaded_csets, mg_preload_node) {
 		struct css_set *dst_cset;
 
-		dst_cset = find_css_set(src_cset, dst_cgrp);
+		dst_cset = find_css_set(src_cset,
+					dst_cgrp ?: src_cset->dfl_cgrp);
 		if (!dst_cset)
 			goto err;
 
 		WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
+
+		/*
+		 * If src cset equals dst, it's noop.  Drop the src.
+		 * cgroup_migrate() will skip the cset too.  Note that we
+		 * can't handle src == dst as some nodes are used by both.
+		 */
+		if (src_cset == dst_cset) {
+			src_cset->mg_src_cgrp = NULL;
+			list_del_init(&src_cset->mg_preload_node);
+			put_css_set(src_cset, false);
+			put_css_set(dst_cset, false);
+			continue;
+		}
+
 		src_cset->mg_dst_cset = dst_cset;
 
 		if (list_empty(&dst_cset->mg_preload_node))
@@ -1887,7 +2175,7 @@ static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
 			put_css_set(dst_cset, false);
 	}
 
-	list_splice(&csets, preloaded_csets);
+	list_splice_tail(&csets, preloaded_csets);
 	return 0;
 err:
 	cgroup_migrate_finish(&csets);
@@ -1968,7 +2256,7 @@ static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader,
 		return 0;
 
 	/* check that we can legitimately attach to the cgroup */
-	for_each_css(css, i, cgrp) {
+	for_each_e_css(css, i, cgrp) {
 		if (css->ss->can_attach) {
 			ret = css->ss->can_attach(css, &tset);
 			if (ret) {
@@ -1998,7 +2286,7 @@ static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader,
 	 */
 	tset.csets = &tset.dst_csets;
 
-	for_each_css(css, i, cgrp)
+	for_each_e_css(css, i, cgrp)
 		if (css->ss->attach)
 			css->ss->attach(css, &tset);
 
@@ -2006,7 +2294,7 @@ static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader,
 	goto out_release_tset;
 
 out_cancel_attach:
-	for_each_css(css, i, cgrp) {
+	for_each_e_css(css, i, cgrp) {
 		if (css == failed_css)
 			break;
 		if (css->ss->cancel_attach)
@@ -2065,13 +2353,20 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
  * function to attach either it or all tasks in its threadgroup. Will lock
  * cgroup_mutex and threadgroup.
  */
-static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
+static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
+				    size_t nbytes, loff_t off, bool threadgroup)
 {
 	struct task_struct *tsk;
 	const struct cred *cred = current_cred(), *tcred;
+	struct cgroup *cgrp;
+	pid_t pid;
 	int ret;
 
-	if (!cgroup_lock_live_group(cgrp))
+	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
+		return -EINVAL;
+
+	cgrp = cgroup_kn_lock_live(of->kn);
+	if (!cgrp)
 		return -ENODEV;
 
 retry_find_task:
@@ -2137,8 +2432,8 @@ retry_find_task:
 
 	put_task_struct(tsk);
 out_unlock_cgroup:
-	mutex_unlock(&cgroup_mutex);
-	return ret;
+	cgroup_kn_unlock(of->kn);
+	return ret ?: nbytes;
 }
 
 /**
@@ -2172,51 +2467,418 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 }
 EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
 
-static int cgroup_tasks_write(struct cgroup_subsys_state *css,
-			      struct cftype *cft, u64 pid)
+static ssize_t cgroup_tasks_write(struct kernfs_open_file *of,
+				  char *buf, size_t nbytes, loff_t off)
 {
-	return attach_task_by_pid(css->cgroup, pid, false);
+	return __cgroup_procs_write(of, buf, nbytes, off, false);
 }
 
-static int cgroup_procs_write(struct cgroup_subsys_state *css,
-			      struct cftype *cft, u64 tgid)
+static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
+				  char *buf, size_t nbytes, loff_t off)
 {
-	return attach_task_by_pid(css->cgroup, tgid, true);
+	return __cgroup_procs_write(of, buf, nbytes, off, true);
 }
 
-static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
-				      struct cftype *cft, char *buffer)
+static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of,
+					  char *buf, size_t nbytes, loff_t off)
 {
-	struct cgroup_root *root = css->cgroup->root;
+	struct cgroup *cgrp;
 
-	BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX);
-	if (!cgroup_lock_live_group(css->cgroup))
+	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
+
+	cgrp = cgroup_kn_lock_live(of->kn);
+	if (!cgrp)
 		return -ENODEV;
 	spin_lock(&release_agent_path_lock);
-	strlcpy(root->release_agent_path, buffer,
-		sizeof(root->release_agent_path));
+	strlcpy(cgrp->root->release_agent_path, strstrip(buf),
+		sizeof(cgrp->root->release_agent_path));
 	spin_unlock(&release_agent_path_lock);
-	mutex_unlock(&cgroup_mutex);
-	return 0;
+	cgroup_kn_unlock(of->kn);
+	return nbytes;
 }
 
 static int cgroup_release_agent_show(struct seq_file *seq, void *v)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
 
-	if (!cgroup_lock_live_group(cgrp))
-		return -ENODEV;
+	spin_lock(&release_agent_path_lock);
 	seq_puts(seq, cgrp->root->release_agent_path);
+	spin_unlock(&release_agent_path_lock);
 	seq_putc(seq, '\n');
-	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
 
 static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
 {
+	seq_puts(seq, "0\n");
+	return 0;
+}
+
+static void cgroup_print_ss_mask(struct seq_file *seq, unsigned int ss_mask)
+{
+	struct cgroup_subsys *ss;
+	bool printed = false;
+	int ssid;
+
+	for_each_subsys(ss, ssid) {
+		if (ss_mask & (1 << ssid)) {
+			if (printed)
+				seq_putc(seq, ' ');
+			seq_printf(seq, "%s", ss->name);
+			printed = true;
+		}
+	}
+	if (printed)
+		seq_putc(seq, '\n');
+}
+
+/* show controllers which are currently attached to the default hierarchy */
+static int cgroup_root_controllers_show(struct seq_file *seq, void *v)
+{
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
 
-	seq_printf(seq, "%d\n", cgroup_sane_behavior(cgrp));
+	cgroup_print_ss_mask(seq, cgrp->root->subsys_mask &
+			     ~cgrp_dfl_root_inhibit_ss_mask);
+	return 0;
+}
+
+/* show controllers which are enabled from the parent */
+static int cgroup_controllers_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+
+	cgroup_print_ss_mask(seq, cgroup_parent(cgrp)->subtree_control);
+	return 0;
+}
+
+/* show controllers which are enabled for a given cgroup's children */
+static int cgroup_subtree_control_show(struct seq_file *seq, void *v)
+{
+	struct cgroup *cgrp = seq_css(seq)->cgroup;
+
+	cgroup_print_ss_mask(seq, cgrp->subtree_control);
+	return 0;
+}
+
+/**
+ * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy
+ * @cgrp: root of the subtree to update csses for
+ *
+ * @cgrp's child_subsys_mask has changed and its subtree's (self excluded)
+ * css associations need to be updated accordingly.  This function looks up
+ * all css_sets which are attached to the subtree, creates the matching
+ * updated css_sets and migrates the tasks to the new ones.
+ */
+static int cgroup_update_dfl_csses(struct cgroup *cgrp)
+{
+	LIST_HEAD(preloaded_csets);
+	struct cgroup_subsys_state *css;
+	struct css_set *src_cset;
+	int ret;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	/* look up all csses currently attached to @cgrp's subtree */
+	down_read(&css_set_rwsem);
+	css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
+		struct cgrp_cset_link *link;
+
+		/* self is not affected by child_subsys_mask change */
+		if (css->cgroup == cgrp)
+			continue;
+
+		list_for_each_entry(link, &css->cgroup->cset_links, cset_link)
+			cgroup_migrate_add_src(link->cset, cgrp,
+					       &preloaded_csets);
+	}
+	up_read(&css_set_rwsem);
+
+	/* NULL dst indicates self on default hierarchy */
+	ret = cgroup_migrate_prepare_dst(NULL, &preloaded_csets);
+	if (ret)
+		goto out_finish;
+
+	list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) {
+		struct task_struct *last_task = NULL, *task;
+
+		/* src_csets precede dst_csets, break on the first dst_cset */
+		if (!src_cset->mg_src_cgrp)
+			break;
+
+		/*
+		 * All tasks in src_cset need to be migrated to the
+		 * matching dst_cset.  Empty it process by process.  We
+		 * walk tasks but migrate processes.  The leader might even
+		 * belong to a different cset but such src_cset would also
+		 * be among the target src_csets because the default
+		 * hierarchy enforces per-process membership.
+		 */
+		while (true) {
+			down_read(&css_set_rwsem);
+			task = list_first_entry_or_null(&src_cset->tasks,
+						struct task_struct, cg_list);
+			if (task) {
+				task = task->group_leader;
+				WARN_ON_ONCE(!task_css_set(task)->mg_src_cgrp);
+				get_task_struct(task);
+			}
+			up_read(&css_set_rwsem);
+
+			if (!task)
+				break;
+
+			/* guard against possible infinite loop */
+			if (WARN(last_task == task,
+				 "cgroup: update_dfl_csses failed to make progress, aborting in inconsistent state\n"))
+				goto out_finish;
+			last_task = task;
+
+			threadgroup_lock(task);
+			/* raced against de_thread() from another thread? */
+			if (!thread_group_leader(task)) {
+				threadgroup_unlock(task);
+				put_task_struct(task);
+				continue;
+			}
+
+			ret = cgroup_migrate(src_cset->dfl_cgrp, task, true);
+
+			threadgroup_unlock(task);
+			put_task_struct(task);
+
+			if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret))
+				goto out_finish;
+		}
+	}
+
+out_finish:
+	cgroup_migrate_finish(&preloaded_csets);
+	return ret;
+}
+
+/* change the enabled child controllers for a cgroup in the default hierarchy */
+static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
+					    char *buf, size_t nbytes,
+					    loff_t off)
+{
+	unsigned int enable = 0, disable = 0;
+	unsigned int css_enable, css_disable, old_ctrl, new_ctrl;
+	struct cgroup *cgrp, *child;
+	struct cgroup_subsys *ss;
+	char *tok;
+	int ssid, ret;
+
+	/*
+	 * Parse input - space separated list of subsystem names prefixed
+	 * with either + or -.
+	 */
+	buf = strstrip(buf);
+	while ((tok = strsep(&buf, " "))) {
+		if (tok[0] == '\0')
+			continue;
+		for_each_subsys(ss, ssid) {
+			if (ss->disabled || strcmp(tok + 1, ss->name) ||
+			    ((1 << ss->id) & cgrp_dfl_root_inhibit_ss_mask))
+				continue;
+
+			if (*tok == '+') {
+				enable |= 1 << ssid;
+				disable &= ~(1 << ssid);
+			} else if (*tok == '-') {
+				disable |= 1 << ssid;
+				enable &= ~(1 << ssid);
+			} else {
+				return -EINVAL;
+			}
+			break;
+		}
+		if (ssid == CGROUP_SUBSYS_COUNT)
+			return -EINVAL;
+	}
+
+	cgrp = cgroup_kn_lock_live(of->kn);
+	if (!cgrp)
+		return -ENODEV;
+
+	for_each_subsys(ss, ssid) {
+		if (enable & (1 << ssid)) {
+			if (cgrp->subtree_control & (1 << ssid)) {
+				enable &= ~(1 << ssid);
+				continue;
+			}
+
+			/* unavailable or not enabled on the parent? */
+			if (!(cgrp_dfl_root.subsys_mask & (1 << ssid)) ||
+			    (cgroup_parent(cgrp) &&
+			     !(cgroup_parent(cgrp)->subtree_control & (1 << ssid)))) {
+				ret = -ENOENT;
+				goto out_unlock;
+			}
+
+			/*
+			 * @ss is already enabled through dependency and
+			 * we'll just make it visible.  Skip draining.
+			 */
+			if (cgrp->child_subsys_mask & (1 << ssid))
+				continue;
+
+			/*
+			 * Because css offlining is asynchronous, userland
+			 * might try to re-enable the same controller while
+			 * the previous instance is still around.  In such
+			 * cases, wait till it's gone using offline_waitq.
+			 */
+			cgroup_for_each_live_child(child, cgrp) {
+				DEFINE_WAIT(wait);
+
+				if (!cgroup_css(child, ss))
+					continue;
+
+				cgroup_get(child);
+				prepare_to_wait(&child->offline_waitq, &wait,
+						TASK_UNINTERRUPTIBLE);
+				cgroup_kn_unlock(of->kn);
+				schedule();
+				finish_wait(&child->offline_waitq, &wait);
+				cgroup_put(child);
+
+				return restart_syscall();
+			}
+		} else if (disable & (1 << ssid)) {
+			if (!(cgrp->subtree_control & (1 << ssid))) {
+				disable &= ~(1 << ssid);
+				continue;
+			}
+
+			/* a child has it enabled? */
+			cgroup_for_each_live_child(child, cgrp) {
+				if (child->subtree_control & (1 << ssid)) {
+					ret = -EBUSY;
+					goto out_unlock;
+				}
+			}
+		}
+	}
+
+	if (!enable && !disable) {
+		ret = 0;
+		goto out_unlock;
+	}
+
+	/*
+	 * Except for the root, subtree_control must be zero for a cgroup
+	 * with tasks so that child cgroups don't compete against tasks.
+	 */
+	if (enable && cgroup_parent(cgrp) && !list_empty(&cgrp->cset_links)) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	/*
+	 * Update subsys masks and calculate what needs to be done.  More
+	 * subsystems than specified may need to be enabled or disabled
+	 * depending on subsystem dependencies.
+	 */
+	cgrp->subtree_control |= enable;
+	cgrp->subtree_control &= ~disable;
+
+	old_ctrl = cgrp->child_subsys_mask;
+	cgroup_refresh_child_subsys_mask(cgrp);
+	new_ctrl = cgrp->child_subsys_mask;
+
+	css_enable = ~old_ctrl & new_ctrl;
+	css_disable = old_ctrl & ~new_ctrl;
+	enable |= css_enable;
+	disable |= css_disable;
+
+	/*
+	 * Create new csses or make the existing ones visible.  A css is
+	 * created invisible if it's being implicitly enabled through
+	 * dependency.  An invisible css is made visible when the userland
+	 * explicitly enables it.
+	 */
+	for_each_subsys(ss, ssid) {
+		if (!(enable & (1 << ssid)))
+			continue;
+
+		cgroup_for_each_live_child(child, cgrp) {
+			if (css_enable & (1 << ssid))
+				ret = create_css(child, ss,
+					cgrp->subtree_control & (1 << ssid));
+			else
+				ret = cgroup_populate_dir(child, 1 << ssid);
+			if (ret)
+				goto err_undo_css;
+		}
+	}
+
+	/*
+	 * At this point, cgroup_e_css() results reflect the new csses
+	 * making the following cgroup_update_dfl_csses() properly update
+	 * css associations of all tasks in the subtree.
+	 */
+	ret = cgroup_update_dfl_csses(cgrp);
+	if (ret)
+		goto err_undo_css;
+
+	/*
+	 * All tasks are migrated out of disabled csses.  Kill or hide
+	 * them.  A css is hidden when the userland requests it to be
+	 * disabled while other subsystems are still depending on it.  The
+	 * css must not actively control resources and be in the vanilla
+	 * state if it's made visible again later.  Controllers which may
+	 * be depended upon should provide ->css_reset() for this purpose.
+	 */
+	for_each_subsys(ss, ssid) {
+		if (!(disable & (1 << ssid)))
+			continue;
+
+		cgroup_for_each_live_child(child, cgrp) {
+			struct cgroup_subsys_state *css = cgroup_css(child, ss);
+
+			if (css_disable & (1 << ssid)) {
+				kill_css(css);
+			} else {
+				cgroup_clear_dir(child, 1 << ssid);
+				if (ss->css_reset)
+					ss->css_reset(css);
+			}
+		}
+	}
+
+	kernfs_activate(cgrp->kn);
+	ret = 0;
+out_unlock:
+	cgroup_kn_unlock(of->kn);
+	return ret ?: nbytes;
+
+err_undo_css:
+	cgrp->subtree_control &= ~enable;
+	cgrp->subtree_control |= disable;
+	cgroup_refresh_child_subsys_mask(cgrp);
+
+	for_each_subsys(ss, ssid) {
+		if (!(enable & (1 << ssid)))
+			continue;
+
+		cgroup_for_each_live_child(child, cgrp) {
+			struct cgroup_subsys_state *css = cgroup_css(child, ss);
+
+			if (!css)
+				continue;
+
+			if (css_enable & (1 << ssid))
+				kill_css(css);
+			else
+				cgroup_clear_dir(child, 1 << ssid);
+		}
+	}
+	goto out_unlock;
+}
+
+static int cgroup_populated_show(struct seq_file *seq, void *v)
+{
+	seq_printf(seq, "%d\n", (bool)seq_css(seq)->cgroup->populated_cnt);
 	return 0;
 }
 
@@ -2228,6 +2890,9 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	struct cgroup_subsys_state *css;
 	int ret;
 
+	if (cft->write)
+		return cft->write(of, buf, nbytes, off);
+
 	/*
 	 * kernfs guarantees that a file isn't deleted with operations in
 	 * flight, which means that the matching css is and stays alive and
@@ -2238,9 +2903,7 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	css = cgroup_css(cgrp, cft->ss);
 	rcu_read_unlock();
 
-	if (cft->write_string) {
-		ret = cft->write_string(css, cft, strstrip(buf));
-	} else if (cft->write_u64) {
+	if (cft->write_u64) {
 		unsigned long long v;
 		ret = kstrtoull(buf, 0, &v);
 		if (!ret)
@@ -2250,8 +2913,6 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 		ret = kstrtoll(buf, 0, &v);
 		if (!ret)
 			ret = cft->write_s64(css, cft, v);
-	} else if (cft->trigger) {
-		ret = cft->trigger(css, (unsigned int)cft->private);
 	} else {
 		ret = -EINVAL;
 	}
@@ -2322,26 +2983,24 @@ static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
 
 	/*
 	 * This isn't a proper migration and its usefulness is very
-	 * limited.  Disallow if sane_behavior.
+	 * limited.  Disallow on the default hierarchy.
 	 */
-	if (cgroup_sane_behavior(cgrp))
+	if (cgroup_on_dfl(cgrp))
 		return -EPERM;
 
 	/*
-	 * We're gonna grab cgroup_tree_mutex which nests outside kernfs
+	 * We're gonna grab cgroup_mutex which nests outside kernfs
 	 * active_ref.  kernfs_rename() doesn't require active_ref
-	 * protection.  Break them before grabbing cgroup_tree_mutex.
+	 * protection.  Break them before grabbing cgroup_mutex.
 	 */
 	kernfs_break_active_protection(new_parent);
 	kernfs_break_active_protection(kn);
 
-	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
 	ret = kernfs_rename(kn, new_parent, new_name_str);
 
 	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
 
 	kernfs_unbreak_active_protection(kn);
 	kernfs_unbreak_active_protection(new_parent);
@@ -2379,9 +3038,14 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft)
 		return PTR_ERR(kn);
 
 	ret = cgroup_kn_set_ugid(kn);
-	if (ret)
+	if (ret) {
 		kernfs_remove(kn);
-	return ret;
+		return ret;
+	}
+
+	if (cft->seq_show == cgroup_populated_show)
+		cgrp->populated_kn = kn;
+	return 0;
 }
 
 /**
@@ -2401,24 +3065,24 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 	struct cftype *cft;
 	int ret;
 
-	lockdep_assert_held(&cgroup_tree_mutex);
+	lockdep_assert_held(&cgroup_mutex);
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
 		/* does cft->flags tell us to skip this file on @cgrp? */
-		if ((cft->flags & CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
+		if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
 			continue;
-		if ((cft->flags & CFTYPE_INSANE) && cgroup_sane_behavior(cgrp))
+		if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp))
 			continue;
-		if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
+		if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp))
 			continue;
-		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent)
+		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp))
 			continue;
 
 		if (is_add) {
 			ret = cgroup_add_file(cgrp, cft);
 			if (ret) {
-				pr_warn("cgroup_addrm_files: failed to add %s, err=%d\n",
-					cft->name, ret);
+				pr_warn("%s: failed to add %s, err=%d\n",
+					__func__, cft->name, ret);
 				return ret;
 			}
 		} else {
@@ -2436,11 +3100,7 @@ static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add)
 	struct cgroup_subsys_state *css;
 	int ret = 0;
 
-	lockdep_assert_held(&cgroup_tree_mutex);
-
-	/* don't bother if @ss isn't attached */
-	if (ss->root == &cgrp_dfl_root)
-		return 0;
+	lockdep_assert_held(&cgroup_mutex);
 
 	/* add/rm files for all cgroups created before */
 	css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
@@ -2469,6 +3129,9 @@ static void cgroup_exit_cftypes(struct cftype *cfts)
 			kfree(cft->kf_ops);
 		cft->kf_ops = NULL;
 		cft->ss = NULL;
+
+		/* revert flags set by cgroup core while adding @cfts */
+		cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL);
 	}
 }
 
@@ -2508,7 +3171,7 @@ static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 
 static int cgroup_rm_cftypes_locked(struct cftype *cfts)
 {
-	lockdep_assert_held(&cgroup_tree_mutex);
+	lockdep_assert_held(&cgroup_mutex);
 
 	if (!cfts || !cfts[0].ss)
 		return -ENOENT;
@@ -2534,9 +3197,9 @@ int cgroup_rm_cftypes(struct cftype *cfts)
 {
 	int ret;
 
-	mutex_lock(&cgroup_tree_mutex);
+	mutex_lock(&cgroup_mutex);
 	ret = cgroup_rm_cftypes_locked(cfts);
-	mutex_unlock(&cgroup_tree_mutex);
+	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
 
@@ -2554,10 +3217,13 @@ int cgroup_rm_cftypes(struct cftype *cfts)
  * function currently returns 0 as long as @cfts registration is successful
  * even if some file creation attempts on existing cgroups fail.
  */
-int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
 	int ret;
 
+	if (ss->disabled)
+		return 0;
+
 	if (!cfts || cfts[0].name[0] == '\0')
 		return 0;
 
@@ -2565,18 +3231,52 @@ int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 	if (ret)
 		return ret;
 
-	mutex_lock(&cgroup_tree_mutex);
+	mutex_lock(&cgroup_mutex);
 
 	list_add_tail(&cfts->node, &ss->cfts);
 	ret = cgroup_apply_cftypes(cfts, true);
 	if (ret)
 		cgroup_rm_cftypes_locked(cfts);
 
-	mutex_unlock(&cgroup_tree_mutex);
+	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
 
 /**
+ * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy
+ * @ss: target cgroup subsystem
+ * @cfts: zero-length name terminated array of cftypes
+ *
+ * Similar to cgroup_add_cftypes() but the added files are only used for
+ * the default hierarchy.
+ */
+int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+{
+	struct cftype *cft;
+
+	for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
+		cft->flags |= __CFTYPE_ONLY_ON_DFL;
+	return cgroup_add_cftypes(ss, cfts);
+}
+
+/**
+ * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies
+ * @ss: target cgroup subsystem
+ * @cfts: zero-length name terminated array of cftypes
+ *
+ * Similar to cgroup_add_cftypes() but the added files are only used for
+ * the legacy hierarchies.
+ */
+int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+{
+	struct cftype *cft;
+
+	for (cft = cfts; cft && cft->name[0] != '\0'; cft++)
+		cft->flags |= __CFTYPE_NOT_ON_DFL;
+	return cgroup_add_cftypes(ss, cfts);
+}
+
+/**
  * cgroup_task_count - count the number of tasks in a cgroup.
  * @cgrp: the cgroup in question
  *
@@ -2596,57 +3296,65 @@ static int cgroup_task_count(const struct cgroup *cgrp)
 
 /**
  * css_next_child - find the next child of a given css
- * @pos_css: the current position (%NULL to initiate traversal)
- * @parent_css: css whose children to walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @parent: css whose children to walk
  *
- * This function returns the next child of @parent_css and should be called
+ * This function returns the next child of @parent and should be called
  * under either cgroup_mutex or RCU read lock.  The only requirement is
- * that @parent_css and @pos_css are accessible.  The next sibling is
- * guaranteed to be returned regardless of their states.
+ * that @parent and @pos are accessible.  The next sibling is guaranteed to
+ * be returned regardless of their states.
+ *
+ * If a subsystem synchronizes ->css_online() and the start of iteration, a
+ * css which finished ->css_online() is guaranteed to be visible in the
+ * future iterations and will stay visible until the last reference is put.
+ * A css which hasn't finished ->css_online() or already finished
+ * ->css_offline() may show up during traversal.  It's each subsystem's
+ * responsibility to synchronize against on/offlining.
  */
-struct cgroup_subsys_state *
-css_next_child(struct cgroup_subsys_state *pos_css,
-	       struct cgroup_subsys_state *parent_css)
+struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
+					   struct cgroup_subsys_state *parent)
 {
-	struct cgroup *pos = pos_css ? pos_css->cgroup : NULL;
-	struct cgroup *cgrp = parent_css->cgroup;
-	struct cgroup *next;
+	struct cgroup_subsys_state *next;
 
-	cgroup_assert_mutexes_or_rcu_locked();
+	cgroup_assert_mutex_or_rcu_locked();
 
 	/*
-	 * @pos could already have been removed.  Once a cgroup is removed,
-	 * its ->sibling.next is no longer updated when its next sibling
-	 * changes.  As CGRP_DEAD assertion is serialized and happens
-	 * before the cgroup is taken off the ->sibling list, if we see it
-	 * unasserted, it's guaranteed that the next sibling hasn't
-	 * finished its grace period even if it's already removed, and thus
-	 * safe to dereference from this RCU critical section.  If
-	 * ->sibling.next is inaccessible, cgroup_is_dead() is guaranteed
-	 * to be visible as %true here.
+	 * @pos could already have been unlinked from the sibling list.
+	 * Once a cgroup is removed, its ->sibling.next is no longer
+	 * updated when its next sibling changes.  CSS_RELEASED is set when
+	 * @pos is taken off list, at which time its next pointer is valid,
+	 * and, as releases are serialized, the one pointed to by the next
+	 * pointer is guaranteed to not have started release yet.  This
+	 * implies that if we observe !CSS_RELEASED on @pos in this RCU
+	 * critical section, the one pointed to by its next pointer is
+	 * guaranteed to not have finished its RCU grace period even if we
+	 * have dropped rcu_read_lock() inbetween iterations.
 	 *
-	 * If @pos is dead, its next pointer can't be dereferenced;
-	 * however, as each cgroup is given a monotonically increasing
-	 * unique serial number and always appended to the sibling list,
-	 * the next one can be found by walking the parent's children until
-	 * we see a cgroup with higher serial number than @pos's.  While
-	 * this path can be slower, it's taken only when either the current
-	 * cgroup is removed or iteration and removal race.
+	 * If @pos has CSS_RELEASED set, its next pointer can't be
+	 * dereferenced; however, as each css is given a monotonically
+	 * increasing unique serial number and always appended to the
+	 * sibling list, the next one can be found by walking the parent's
+	 * children until the first css with higher serial number than
+	 * @pos's.  While this path can be slower, it happens iff iteration
+	 * races against release and the race window is very small.
 	 */
 	if (!pos) {
-		next = list_entry_rcu(cgrp->children.next, struct cgroup, sibling);
-	} else if (likely(!cgroup_is_dead(pos))) {
-		next = list_entry_rcu(pos->sibling.next, struct cgroup, sibling);
+		next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling);
+	} else if (likely(!(pos->flags & CSS_RELEASED))) {
+		next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling);
 	} else {
-		list_for_each_entry_rcu(next, &cgrp->children, sibling)
+		list_for_each_entry_rcu(next, &parent->children, sibling)
 			if (next->serial_nr > pos->serial_nr)
 				break;
 	}
 
-	if (&next->sibling == &cgrp->children)
-		return NULL;
-
-	return cgroup_css(next, parent_css->ss);
+	/*
+	 * @next, if not pointing to the head, can be dereferenced and is
+	 * the next sibling.
+	 */
+	if (&next->sibling != &parent->children)
+		return next;
+	return NULL;
 }
 
 /**
@@ -2662,6 +3370,13 @@ css_next_child(struct cgroup_subsys_state *pos_css,
  * doesn't require the whole traversal to be contained in a single critical
  * section.  This function will return the correct next descendant as long
  * as both @pos and @root are accessible and @pos is a descendant of @root.
+ *
+ * If a subsystem synchronizes ->css_online() and the start of iteration, a
+ * css which finished ->css_online() is guaranteed to be visible in the
+ * future iterations and will stay visible until the last reference is put.
+ * A css which hasn't finished ->css_online() or already finished
+ * ->css_offline() may show up during traversal.  It's each subsystem's
+ * responsibility to synchronize against on/offlining.
  */
 struct cgroup_subsys_state *
 css_next_descendant_pre(struct cgroup_subsys_state *pos,
@@ -2669,7 +3384,7 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos,
 {
 	struct cgroup_subsys_state *next;
 
-	cgroup_assert_mutexes_or_rcu_locked();
+	cgroup_assert_mutex_or_rcu_locked();
 
 	/* if first iteration, visit @root */
 	if (!pos)
@@ -2682,10 +3397,10 @@ css_next_descendant_pre(struct cgroup_subsys_state *pos,
 
 	/* no child, visit my or the closest ancestor's next sibling */
 	while (pos != root) {
-		next = css_next_child(pos, css_parent(pos));
+		next = css_next_child(pos, pos->parent);
 		if (next)
 			return next;
-		pos = css_parent(pos);
+		pos = pos->parent;
 	}
 
 	return NULL;
@@ -2709,7 +3424,7 @@ css_rightmost_descendant(struct cgroup_subsys_state *pos)
 {
 	struct cgroup_subsys_state *last, *tmp;
 
-	cgroup_assert_mutexes_or_rcu_locked();
+	cgroup_assert_mutex_or_rcu_locked();
 
 	do {
 		last = pos;
@@ -2749,6 +3464,13 @@ css_leftmost_descendant(struct cgroup_subsys_state *pos)
  * section.  This function will return the correct next descendant as long
  * as both @pos and @cgroup are accessible and @pos is a descendant of
  * @cgroup.
+ *
+ * If a subsystem synchronizes ->css_online() and the start of iteration, a
+ * css which finished ->css_online() is guaranteed to be visible in the
+ * future iterations and will stay visible until the last reference is put.
+ * A css which hasn't finished ->css_online() or already finished
+ * ->css_offline() may show up during traversal.  It's each subsystem's
+ * responsibility to synchronize against on/offlining.
  */
 struct cgroup_subsys_state *
 css_next_descendant_post(struct cgroup_subsys_state *pos,
@@ -2756,7 +3478,7 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 {
 	struct cgroup_subsys_state *next;
 
-	cgroup_assert_mutexes_or_rcu_locked();
+	cgroup_assert_mutex_or_rcu_locked();
 
 	/* if first iteration, visit leftmost descendant which may be @root */
 	if (!pos)
@@ -2767,12 +3489,36 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 		return NULL;
 
 	/* if there's an unvisited sibling, visit its leftmost descendant */
-	next = css_next_child(pos, css_parent(pos));
+	next = css_next_child(pos, pos->parent);
 	if (next)
 		return css_leftmost_descendant(next);
 
 	/* no sibling left, visit parent */
-	return css_parent(pos);
+	return pos->parent;
+}
+
+/**
+ * css_has_online_children - does a css have online children
+ * @css: the target css
+ *
+ * Returns %true if @css has any online children; otherwise, %false.  This
+ * function can be called from any context but the caller is responsible
+ * for synchronizing against on/offlining as necessary.
+ */
+bool css_has_online_children(struct cgroup_subsys_state *css)
+{
+	struct cgroup_subsys_state *child;
+	bool ret = false;
+
+	rcu_read_lock();
+	css_for_each_child(child, css) {
+		if (child->flags & CSS_ONLINE) {
+			ret = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	return ret;
 }
 
 /**
@@ -2783,27 +3529,36 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
  */
 static void css_advance_task_iter(struct css_task_iter *it)
 {
-	struct list_head *l = it->cset_link;
+	struct list_head *l = it->cset_pos;
 	struct cgrp_cset_link *link;
 	struct css_set *cset;
 
 	/* Advance to the next non-empty css_set */
 	do {
 		l = l->next;
-		if (l == &it->origin_css->cgroup->cset_links) {
-			it->cset_link = NULL;
+		if (l == it->cset_head) {
+			it->cset_pos = NULL;
 			return;
 		}
-		link = list_entry(l, struct cgrp_cset_link, cset_link);
-		cset = link->cset;
+
+		if (it->ss) {
+			cset = container_of(l, struct css_set,
+					    e_cset_node[it->ss->id]);
+		} else {
+			link = list_entry(l, struct cgrp_cset_link, cset_link);
+			cset = link->cset;
+		}
 	} while (list_empty(&cset->tasks) && list_empty(&cset->mg_tasks));
 
-	it->cset_link = l;
+	it->cset_pos = l;
 
 	if (!list_empty(&cset->tasks))
-		it->task = cset->tasks.next;
+		it->task_pos = cset->tasks.next;
 	else
-		it->task = cset->mg_tasks.next;
+		it->task_pos = cset->mg_tasks.next;
+
+	it->tasks_head = &cset->tasks;
+	it->mg_tasks_head = &cset->mg_tasks;
 }
 
 /**
@@ -2829,8 +3584,14 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
 
 	down_read(&css_set_rwsem);
 
-	it->origin_css = css;
-	it->cset_link = &css->cgroup->cset_links;
+	it->ss = css->ss;
+
+	if (it->ss)
+		it->cset_pos = &css->cgroup->e_csets[css->ss->id];
+	else
+		it->cset_pos = &css->cgroup->cset_links;
+
+	it->cset_head = it->cset_pos;
 
 	css_advance_task_iter(it);
 }
@@ -2846,12 +3607,10 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
 struct task_struct *css_task_iter_next(struct css_task_iter *it)
 {
 	struct task_struct *res;
-	struct list_head *l = it->task;
-	struct cgrp_cset_link *link = list_entry(it->cset_link,
-					struct cgrp_cset_link, cset_link);
+	struct list_head *l = it->task_pos;
 
 	/* If the iterator cg is NULL, we have no tasks */
-	if (!it->cset_link)
+	if (!it->cset_pos)
 		return NULL;
 	res = list_entry(l, struct task_struct, cg_list);
 
@@ -2862,13 +3621,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 	 */
 	l = l->next;
 
-	if (l == &link->cset->tasks)
-		l = link->cset->mg_tasks.next;
+	if (l == it->tasks_head)
+		l = it->mg_tasks_head->next;
 
-	if (l == &link->cset->mg_tasks)
+	if (l == it->mg_tasks_head)
 		css_advance_task_iter(it);
 	else
-		it->task = l;
+		it->task_pos = l;
 
 	return res;
 }
@@ -2921,7 +3680,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	 * ->can_attach() fails.
 	 */
 	do {
-		css_task_iter_start(&from->dummy_css, &it);
+		css_task_iter_start(&from->self, &it);
 		task = css_task_iter_next(&it);
 		if (task)
 			get_task_struct(task);
@@ -3082,8 +3841,9 @@ after:
  *
  * All this extra complexity was caused by the original implementation
  * committing to an entirely unnecessary property.  In the long term, we
- * want to do away with it.  Explicitly scramble sort order if
- * sane_behavior so that no such expectation exists in the new interface.
+ * want to do away with it.  Explicitly scramble sort order if on the
+ * default hierarchy so that no such expectation exists in the new
+ * interface.
  *
  * Scrambling is done by swapping every two consecutive bits, which is
  * non-identity one-to-one mapping which disturbs sort order sufficiently.
@@ -3098,7 +3858,7 @@ static pid_t pid_fry(pid_t pid)
 
 static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid)
 {
-	if (cgroup_sane_behavior(cgrp))
+	if (cgroup_on_dfl(cgrp))
 		return pid_fry(pid);
 	else
 		return pid;
@@ -3186,7 +3946,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	if (!array)
 		return -ENOMEM;
 	/* now, populate the array */
-	css_task_iter_start(&cgrp->dummy_css, &it);
+	css_task_iter_start(&cgrp->self, &it);
 	while ((tsk = css_task_iter_next(&it))) {
 		if (unlikely(n == length))
 			break;
@@ -3201,7 +3961,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	css_task_iter_end(&it);
 	length = n;
 	/* now sort & (if procs) strip out duplicates */
-	if (cgroup_sane_behavior(cgrp))
+	if (cgroup_on_dfl(cgrp))
 		sort(array, length, sizeof(pid_t), fried_cmppid, NULL);
 	else
 		sort(array, length, sizeof(pid_t), cmppid, NULL);
@@ -3248,7 +4008,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 
 	/*
 	 * We aren't being called from kernfs and there's no guarantee on
-	 * @kn->priv's validity.  For this and css_tryget_from_dir(),
+	 * @kn->priv's validity.  For this and css_tryget_online_from_dir(),
 	 * @kn->priv is RCU safe.  Let's do the RCU dancing.
 	 */
 	rcu_read_lock();
@@ -3260,7 +4020,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	}
 	rcu_read_unlock();
 
-	css_task_iter_start(&cgrp->dummy_css, &it);
+	css_task_iter_start(&cgrp->self, &it);
 	while ((tsk = css_task_iter_next(&it))) {
 		switch (tsk->state) {
 		case TASK_RUNNING:
@@ -3390,17 +4150,6 @@ static int cgroup_pidlist_show(struct seq_file *s, void *v)
 	return seq_printf(s, "%d\n", *(int *)v);
 }
 
-/*
- * seq_operations functions for iterating on pidlists through seq_file -
- * independent of whether it's tasks or procs
- */
-static const struct seq_operations cgroup_pidlist_seq_operations = {
-	.start = cgroup_pidlist_start,
-	.stop = cgroup_pidlist_stop,
-	.next = cgroup_pidlist_next,
-	.show = cgroup_pidlist_show,
-};
-
 static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css,
 					 struct cftype *cft)
 {
@@ -3434,7 +4183,8 @@ static int cgroup_clone_children_write(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static struct cftype cgroup_base_files[] = {
+/* cgroup core interface files for the default hierarchy */
+static struct cftype cgroup_dfl_base_files[] = {
 	{
 		.name = "cgroup.procs",
 		.seq_start = cgroup_pidlist_start,
@@ -3442,12 +4192,46 @@ static struct cftype cgroup_base_files[] = {
 		.seq_stop = cgroup_pidlist_stop,
 		.seq_show = cgroup_pidlist_show,
 		.private = CGROUP_FILE_PROCS,
-		.write_u64 = cgroup_procs_write,
+		.write = cgroup_procs_write,
+		.mode = S_IRUGO | S_IWUSR,
+	},
+	{
+		.name = "cgroup.controllers",
+		.flags = CFTYPE_ONLY_ON_ROOT,
+		.seq_show = cgroup_root_controllers_show,
+	},
+	{
+		.name = "cgroup.controllers",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_controllers_show,
+	},
+	{
+		.name = "cgroup.subtree_control",
+		.seq_show = cgroup_subtree_control_show,
+		.write = cgroup_subtree_control_write,
+	},
+	{
+		.name = "cgroup.populated",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cgroup_populated_show,
+	},
+	{ }	/* terminate */
+};
+
+/* cgroup core interface files for the legacy hierarchies */
+static struct cftype cgroup_legacy_base_files[] = {
+	{
+		.name = "cgroup.procs",
+		.seq_start = cgroup_pidlist_start,
+		.seq_next = cgroup_pidlist_next,
+		.seq_stop = cgroup_pidlist_stop,
+		.seq_show = cgroup_pidlist_show,
+		.private = CGROUP_FILE_PROCS,
+		.write = cgroup_procs_write,
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	{
 		.name = "cgroup.clone_children",
-		.flags = CFTYPE_INSANE,
 		.read_u64 = cgroup_clone_children_read,
 		.write_u64 = cgroup_clone_children_write,
 	},
@@ -3456,34 +4240,26 @@ static struct cftype cgroup_base_files[] = {
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cgroup_sane_behavior_show,
 	},
-
-	/*
-	 * Historical crazy stuff.  These don't have "cgroup."  prefix and
-	 * don't exist if sane_behavior.  If you're depending on these, be
-	 * prepared to be burned.
-	 */
 	{
 		.name = "tasks",
-		.flags = CFTYPE_INSANE,		/* use "procs" instead */
 		.seq_start = cgroup_pidlist_start,
 		.seq_next = cgroup_pidlist_next,
 		.seq_stop = cgroup_pidlist_stop,
 		.seq_show = cgroup_pidlist_show,
 		.private = CGROUP_FILE_TASKS,
-		.write_u64 = cgroup_tasks_write,
+		.write = cgroup_tasks_write,
 		.mode = S_IRUGO | S_IWUSR,
 	},
 	{
 		.name = "notify_on_release",
-		.flags = CFTYPE_INSANE,
 		.read_u64 = cgroup_read_notify_on_release,
 		.write_u64 = cgroup_write_notify_on_release,
 	},
 	{
 		.name = "release_agent",
-		.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
+		.flags = CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cgroup_release_agent_show,
-		.write_string = cgroup_release_agent_write,
+		.write = cgroup_release_agent_write,
 		.max_write_len = PATH_MAX - 1,
 	},
 	{ }	/* terminate */
@@ -3496,7 +4272,7 @@ static struct cftype cgroup_base_files[] = {
  *
  * On failure, no file is added.
  */
-static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask)
+static int cgroup_populate_dir(struct cgroup *cgrp, unsigned int subsys_mask)
 {
 	struct cgroup_subsys *ss;
 	int i, ret = 0;
@@ -3505,7 +4281,7 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 	for_each_subsys(ss, i) {
 		struct cftype *cfts;
 
-		if (!test_bit(i, &subsys_mask))
+		if (!(subsys_mask & (1 << i)))
 			continue;
 
 		list_for_each_entry(cfts, &ss->cfts, node) {
@@ -3527,9 +4303,9 @@ err:
  *    Implemented in kill_css().
  *
  * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs
- *    and thus css_tryget() is guaranteed to fail, the css can be offlined
- *    by invoking offline_css().  After offlining, the base ref is put.
- *    Implemented in css_killed_work_fn().
+ *    and thus css_tryget_online() is guaranteed to fail, the css can be
+ *    offlined by invoking offline_css().  After offlining, the base ref is
+ *    put.  Implemented in css_killed_work_fn().
  *
  * 3. When the percpu_ref reaches zero, the only possible remaining
  *    accessors are inside RCU read sections.  css_release() schedules the
@@ -3548,11 +4324,39 @@ static void css_free_work_fn(struct work_struct *work)
 		container_of(work, struct cgroup_subsys_state, destroy_work);
 	struct cgroup *cgrp = css->cgroup;
 
-	if (css->parent)
-		css_put(css->parent);
+	percpu_ref_exit(&css->refcnt);
 
-	css->ss->css_free(css);
-	cgroup_put(cgrp);
+	if (css->ss) {
+		/* css free path */
+		if (css->parent)
+			css_put(css->parent);
+
+		css->ss->css_free(css);
+		cgroup_put(cgrp);
+	} else {
+		/* cgroup free path */
+		atomic_dec(&cgrp->root->nr_cgrps);
+		cgroup_pidlist_destroy_all(cgrp);
+
+		if (cgroup_parent(cgrp)) {
+			/*
+			 * We get a ref to the parent, and put the ref when
+			 * this cgroup is being freed, so it's guaranteed
+			 * that the parent won't be destroyed before its
+			 * children.
+			 */
+			cgroup_put(cgroup_parent(cgrp));
+			kernfs_put(cgrp->kn);
+			kfree(cgrp);
+		} else {
+			/*
+			 * This is root cgroup's refcnt reaching zero,
+			 * which indicates that the root should be
+			 * released.
+			 */
+			cgroup_destroy_root(cgrp->root);
+		}
+	}
 }
 
 static void css_free_rcu_fn(struct rcu_head *rcu_head)
@@ -3564,26 +4368,59 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
 	queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
+static void css_release_work_fn(struct work_struct *work)
+{
+	struct cgroup_subsys_state *css =
+		container_of(work, struct cgroup_subsys_state, destroy_work);
+	struct cgroup_subsys *ss = css->ss;
+	struct cgroup *cgrp = css->cgroup;
+
+	mutex_lock(&cgroup_mutex);
+
+	css->flags |= CSS_RELEASED;
+	list_del_rcu(&css->sibling);
+
+	if (ss) {
+		/* css release path */
+		cgroup_idr_remove(&ss->css_idr, css->id);
+	} else {
+		/* cgroup release path */
+		cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+		cgrp->id = -1;
+	}
+
+	mutex_unlock(&cgroup_mutex);
+
+	call_rcu(&css->rcu_head, css_free_rcu_fn);
+}
+
 static void css_release(struct percpu_ref *ref)
 {
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
-	RCU_INIT_POINTER(css->cgroup->subsys[css->ss->id], NULL);
-	call_rcu(&css->rcu_head, css_free_rcu_fn);
+	INIT_WORK(&css->destroy_work, css_release_work_fn);
+	queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
-static void init_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss,
-		     struct cgroup *cgrp)
+static void init_and_link_css(struct cgroup_subsys_state *css,
+			      struct cgroup_subsys *ss, struct cgroup *cgrp)
 {
+	lockdep_assert_held(&cgroup_mutex);
+
+	cgroup_get(cgrp);
+
+	memset(css, 0, sizeof(*css));
 	css->cgroup = cgrp;
 	css->ss = ss;
-	css->flags = 0;
+	INIT_LIST_HEAD(&css->sibling);
+	INIT_LIST_HEAD(&css->children);
+	css->serial_nr = css_serial_nr_next++;
 
-	if (cgrp->parent)
-		css->parent = cgroup_css(cgrp->parent, ss);
-	else
-		css->flags |= CSS_ROOT;
+	if (cgroup_parent(cgrp)) {
+		css->parent = cgroup_css(cgroup_parent(cgrp), ss);
+		css_get(css->parent);
+	}
 
 	BUG_ON(cgroup_css(cgrp, ss));
 }
@@ -3594,14 +4431,12 @@ static int online_css(struct cgroup_subsys_state *css)
 	struct cgroup_subsys *ss = css->ss;
 	int ret = 0;
 
-	lockdep_assert_held(&cgroup_tree_mutex);
 	lockdep_assert_held(&cgroup_mutex);
 
 	if (ss->css_online)
 		ret = ss->css_online(css);
 	if (!ret) {
 		css->flags |= CSS_ONLINE;
-		css->cgroup->nr_css++;
 		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
 	}
 	return ret;
@@ -3612,7 +4447,6 @@ static void offline_css(struct cgroup_subsys_state *css)
 {
 	struct cgroup_subsys *ss = css->ss;
 
-	lockdep_assert_held(&cgroup_tree_mutex);
 	lockdep_assert_held(&cgroup_mutex);
 
 	if (!(css->flags & CSS_ONLINE))
@@ -3622,126 +4456,123 @@ static void offline_css(struct cgroup_subsys_state *css)
 		ss->css_offline(css);
 
 	css->flags &= ~CSS_ONLINE;
-	css->cgroup->nr_css--;
-	RCU_INIT_POINTER(css->cgroup->subsys[ss->id], css);
+	RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL);
+
+	wake_up_all(&css->cgroup->offline_waitq);
 }
 
 /**
  * create_css - create a cgroup_subsys_state
  * @cgrp: the cgroup new css will be associated with
  * @ss: the subsys of new css
+ * @visible: whether to create control knobs for the new css or not
  *
  * Create a new css associated with @cgrp - @ss pair.  On success, the new
- * css is online and installed in @cgrp with all interface files created.
- * Returns 0 on success, -errno on failure.
+ * css is online and installed in @cgrp with all interface files created if
+ * @visible.  Returns 0 on success, -errno on failure.
  */
-static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
+static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
+		      bool visible)
 {
-	struct cgroup *parent = cgrp->parent;
+	struct cgroup *parent = cgroup_parent(cgrp);
+	struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss);
 	struct cgroup_subsys_state *css;
 	int err;
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	css = ss->css_alloc(cgroup_css(parent, ss));
+	css = ss->css_alloc(parent_css);
 	if (IS_ERR(css))
 		return PTR_ERR(css);
 
+	init_and_link_css(css, ss, cgrp);
+
 	err = percpu_ref_init(&css->refcnt, css_release);
 	if (err)
 		goto err_free_css;
 
-	init_css(css, ss, cgrp);
-
-	err = cgroup_populate_dir(cgrp, 1 << ss->id);
-	if (err)
+	err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_NOWAIT);
+	if (err < 0)
 		goto err_free_percpu_ref;
+	css->id = err;
 
-	err = online_css(css);
-	if (err)
-		goto err_clear_dir;
+	if (visible) {
+		err = cgroup_populate_dir(cgrp, 1 << ss->id);
+		if (err)
+			goto err_free_id;
+	}
 
-	cgroup_get(cgrp);
-	css_get(css->parent);
+	/* @css is ready to be brought online now, make it visible */
+	list_add_tail_rcu(&css->sibling, &parent_css->children);
+	cgroup_idr_replace(&ss->css_idr, css, css->id);
 
-	cgrp->subsys_mask |= 1 << ss->id;
+	err = online_css(css);
+	if (err)
+		goto err_list_del;
 
 	if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
-	    parent->parent) {
-		pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
-			   current->comm, current->pid, ss->name);
+	    cgroup_parent(parent)) {
+		pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
+			current->comm, current->pid, ss->name);
 		if (!strcmp(ss->name, "memory"))
-			pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n");
+			pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n");
 		ss->warned_broken_hierarchy = true;
 	}
 
 	return 0;
 
-err_clear_dir:
+err_list_del:
+	list_del_rcu(&css->sibling);
 	cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
+err_free_id:
+	cgroup_idr_remove(&ss->css_idr, css->id);
 err_free_percpu_ref:
-	percpu_ref_cancel_init(&css->refcnt);
+	percpu_ref_exit(&css->refcnt);
 err_free_css:
-	ss->css_free(css);
+	call_rcu(&css->rcu_head, css_free_rcu_fn);
 	return err;
 }
 
-/**
- * cgroup_create - create a cgroup
- * @parent: cgroup that will be parent of the new cgroup
- * @name: name of the new cgroup
- * @mode: mode to set on new cgroup
- */
-static long cgroup_create(struct cgroup *parent, const char *name,
-			  umode_t mode)
+static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+			umode_t mode)
 {
-	struct cgroup *cgrp;
-	struct cgroup_root *root = parent->root;
-	int ssid, err;
+	struct cgroup *parent, *cgrp;
+	struct cgroup_root *root;
 	struct cgroup_subsys *ss;
 	struct kernfs_node *kn;
+	struct cftype *base_files;
+	int ssid, ret;
 
-	/*
-	 * XXX: The default hierarchy isn't fully implemented yet.  Block
-	 * !root cgroup creation on it for now.
-	 */
-	if (root == &cgrp_dfl_root)
-		return -EINVAL;
+	parent = cgroup_kn_lock_live(parent_kn);
+	if (!parent)
+		return -ENODEV;
+	root = parent->root;
 
 	/* allocate the cgroup and its ID, 0 is reserved for the root */
 	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
-	if (!cgrp)
-		return -ENOMEM;
-
-	mutex_lock(&cgroup_tree_mutex);
-
-	/*
-	 * Only live parents can have children.  Note that the liveliness
-	 * check isn't strictly necessary because cgroup_mkdir() and
-	 * cgroup_rmdir() are fully synchronized by i_mutex; however, do it
-	 * anyway so that locking is contained inside cgroup proper and we
-	 * don't get nasty surprises if we ever grow another caller.
-	 */
-	if (!cgroup_lock_live_group(parent)) {
-		err = -ENODEV;
-		goto err_unlock_tree;
+	if (!cgrp) {
+		ret = -ENOMEM;
+		goto out_unlock;
 	}
 
+	ret = percpu_ref_init(&cgrp->self.refcnt, css_release);
+	if (ret)
+		goto out_free_cgrp;
+
 	/*
 	 * Temporarily set the pointer to NULL, so idr_find() won't return
 	 * a half-baked cgroup.
 	 */
-	cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL);
+	cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_NOWAIT);
 	if (cgrp->id < 0) {
-		err = -ENOMEM;
-		goto err_unlock;
+		ret = -ENOMEM;
+		goto out_cancel_ref;
 	}
 
 	init_cgroup_housekeeping(cgrp);
 
-	cgrp->parent = parent;
-	cgrp->dummy_css.parent = &parent->dummy_css;
-	cgrp->root = parent->root;
+	cgrp->self.parent = &parent->self;
+	cgrp->root = root;
 
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -3752,8 +4583,8 @@ static long cgroup_create(struct cgroup *parent, const char *name,
 	/* create the directory */
 	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
 	if (IS_ERR(kn)) {
-		err = PTR_ERR(kn);
-		goto err_free_id;
+		ret = PTR_ERR(kn);
+		goto out_free_id;
 	}
 	cgrp->kn = kn;
 
@@ -3763,10 +4594,10 @@ static long cgroup_create(struct cgroup *parent, const char *name,
 	 */
 	kernfs_get(kn);
 
-	cgrp->serial_nr = cgroup_serial_nr_next++;
+	cgrp->self.serial_nr = css_serial_nr_next++;
 
 	/* allocation complete, commit to creation */
-	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
+	list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children);
 	atomic_inc(&root->nr_cgrps);
 	cgroup_get(parent);
 
@@ -3774,107 +4605,74 @@ static long cgroup_create(struct cgroup *parent, const char *name,
 	 * @cgrp is now fully operational.  If something fails after this
 	 * point, it'll be released via the normal destruction path.
 	 */
-	idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
+	cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
 
-	err = cgroup_kn_set_ugid(kn);
-	if (err)
-		goto err_destroy;
+	ret = cgroup_kn_set_ugid(kn);
+	if (ret)
+		goto out_destroy;
 
-	err = cgroup_addrm_files(cgrp, cgroup_base_files, true);
-	if (err)
-		goto err_destroy;
+	if (cgroup_on_dfl(cgrp))
+		base_files = cgroup_dfl_base_files;
+	else
+		base_files = cgroup_legacy_base_files;
+
+	ret = cgroup_addrm_files(cgrp, base_files, true);
+	if (ret)
+		goto out_destroy;
 
 	/* let's create and online css's */
 	for_each_subsys(ss, ssid) {
-		if (root->cgrp.subsys_mask & (1 << ssid)) {
-			err = create_css(cgrp, ss);
-			if (err)
-				goto err_destroy;
+		if (parent->child_subsys_mask & (1 << ssid)) {
+			ret = create_css(cgrp, ss,
+					 parent->subtree_control & (1 << ssid));
+			if (ret)
+				goto out_destroy;
 		}
 	}
 
-	kernfs_activate(kn);
+	/*
+	 * On the default hierarchy, a child doesn't automatically inherit
+	 * subtree_control from the parent.  Each is configured manually.
+	 */
+	if (!cgroup_on_dfl(cgrp)) {
+		cgrp->subtree_control = parent->subtree_control;
+		cgroup_refresh_child_subsys_mask(cgrp);
+	}
 
-	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
+	kernfs_activate(kn);
 
-	return 0;
+	ret = 0;
+	goto out_unlock;
 
-err_free_id:
-	idr_remove(&root->cgroup_idr, cgrp->id);
-err_unlock:
-	mutex_unlock(&cgroup_mutex);
-err_unlock_tree:
-	mutex_unlock(&cgroup_tree_mutex);
+out_free_id:
+	cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
+out_cancel_ref:
+	percpu_ref_exit(&cgrp->self.refcnt);
+out_free_cgrp:
 	kfree(cgrp);
-	return err;
+out_unlock:
+	cgroup_kn_unlock(parent_kn);
+	return ret;
 
-err_destroy:
+out_destroy:
 	cgroup_destroy_locked(cgrp);
-	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
-	return err;
-}
-
-static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
-			umode_t mode)
-{
-	struct cgroup *parent = parent_kn->priv;
-	int ret;
-
-	/*
-	 * cgroup_create() grabs cgroup_tree_mutex which nests outside
-	 * kernfs active_ref and cgroup_create() already synchronizes
-	 * properly against removal through cgroup_lock_live_group().
-	 * Break it before calling cgroup_create().
-	 */
-	cgroup_get(parent);
-	kernfs_break_active_protection(parent_kn);
-
-	ret = cgroup_create(parent, name, mode);
-
-	kernfs_unbreak_active_protection(parent_kn);
-	cgroup_put(parent);
-	return ret;
+	goto out_unlock;
 }
 
 /*
  * This is called when the refcnt of a css is confirmed to be killed.
- * css_tryget() is now guaranteed to fail.
+ * css_tryget_online() is now guaranteed to fail.  Tell the subsystem to
+ * initate destruction and put the css ref from kill_css().
  */
 static void css_killed_work_fn(struct work_struct *work)
 {
 	struct cgroup_subsys_state *css =
 		container_of(work, struct cgroup_subsys_state, destroy_work);
-	struct cgroup *cgrp = css->cgroup;
 
-	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
-
-	/*
-	 * css_tryget() is guaranteed to fail now.  Tell subsystems to
-	 * initate destruction.
-	 */
 	offline_css(css);
-
-	/*
-	 * If @cgrp is marked dead, it's waiting for refs of all css's to
-	 * be disabled before proceeding to the second phase of cgroup
-	 * destruction.  If we are the last one, kick it off.
-	 */
-	if (!cgrp->nr_css && cgroup_is_dead(cgrp))
-		cgroup_destroy_css_killed(cgrp);
-
 	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
 
-	/*
-	 * Put the css refs from kill_css().  Each css holds an extra
-	 * reference to the cgroup's dentry and cgroup removal proceeds
-	 * regardless of css refs.  On the last put of each css, whenever
-	 * that may be, the extra dentry ref is put so that dentry
-	 * destruction happens only after all css's are released.
-	 */
 	css_put(css);
 }
 
@@ -3888,9 +4686,18 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 	queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
-static void __kill_css(struct cgroup_subsys_state *css)
+/**
+ * kill_css - destroy a css
+ * @css: css to destroy
+ *
+ * This function initiates destruction of @css by removing cgroup interface
+ * files and putting its base reference.  ->css_offline() will be invoked
+ * asynchronously once css_tryget_online() is guaranteed to fail and when
+ * the reference count reaches zero, @css will be released.
+ */
+static void kill_css(struct cgroup_subsys_state *css)
 {
-	lockdep_assert_held(&cgroup_tree_mutex);
+	lockdep_assert_held(&cgroup_mutex);
 
 	/*
 	 * This must happen before css is disassociated with its cgroup.
@@ -3907,7 +4714,7 @@ static void __kill_css(struct cgroup_subsys_state *css)
 	/*
 	 * cgroup core guarantees that, by the time ->css_offline() is
 	 * invoked, no new css reference will be given out via
-	 * css_tryget().  We can't simply call percpu_ref_kill() and
+	 * css_tryget_online().  We can't simply call percpu_ref_kill() and
 	 * proceed to offlining css's because percpu_ref_kill() doesn't
 	 * guarantee that the ref is seen as killed on all CPUs on return.
 	 *
@@ -3918,36 +4725,14 @@ static void __kill_css(struct cgroup_subsys_state *css)
 }
 
 /**
- * kill_css - destroy a css
- * @css: css to destroy
- *
- * This function initiates destruction of @css by removing cgroup interface
- * files and putting its base reference.  ->css_offline() will be invoked
- * asynchronously once css_tryget() is guaranteed to fail and when the
- * reference count reaches zero, @css will be released.
- */
-static void kill_css(struct cgroup_subsys_state *css)
-{
-	struct cgroup *cgrp = css->cgroup;
-
-	lockdep_assert_held(&cgroup_tree_mutex);
-
-	/* if already killed, noop */
-	if (cgrp->subsys_mask & (1 << css->ss->id)) {
-		cgrp->subsys_mask &= ~(1 << css->ss->id);
-		__kill_css(css);
-	}
-}
-
-/**
  * cgroup_destroy_locked - the first stage of cgroup destruction
  * @cgrp: cgroup to be destroyed
  *
  * css's make use of percpu refcnts whose killing latency shouldn't be
  * exposed to userland and are RCU protected.  Also, cgroup core needs to
- * guarantee that css_tryget() won't succeed by the time ->css_offline() is
- * invoked.  To satisfy all the requirements, destruction is implemented in
- * the following two steps.
+ * guarantee that css_tryget_online() won't succeed by the time
+ * ->css_offline() is invoked.  To satisfy all the requirements,
+ * destruction is implemented in the following two steps.
  *
  * s1. Verify @cgrp can be destroyed and mark it dying.  Remove all
  *     userland visible parts and start killing the percpu refcnts of
@@ -3966,12 +4751,10 @@ static void kill_css(struct cgroup_subsys_state *css)
 static int cgroup_destroy_locked(struct cgroup *cgrp)
 	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
-	struct cgroup *child;
 	struct cgroup_subsys_state *css;
 	bool empty;
 	int ssid;
 
-	lockdep_assert_held(&cgroup_tree_mutex);
 	lockdep_assert_held(&cgroup_mutex);
 
 	/*
@@ -3985,127 +4768,68 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 		return -EBUSY;
 
 	/*
-	 * Make sure there's no live children.  We can't test ->children
-	 * emptiness as dead children linger on it while being destroyed;
-	 * otherwise, "rmdir parent/child parent" may fail with -EBUSY.
+	 * Make sure there's no live children.  We can't test emptiness of
+	 * ->self.children as dead children linger on it while being
+	 * drained; otherwise, "rmdir parent/child parent" may fail.
 	 */
-	empty = true;
-	rcu_read_lock();
-	list_for_each_entry_rcu(child, &cgrp->children, sibling) {
-		empty = cgroup_is_dead(child);
-		if (!empty)
-			break;
-	}
-	rcu_read_unlock();
-	if (!empty)
+	if (css_has_online_children(&cgrp->self))
 		return -EBUSY;
 
 	/*
 	 * Mark @cgrp dead.  This prevents further task migration and child
-	 * creation by disabling cgroup_lock_live_group().  Note that
-	 * CGRP_DEAD assertion is depended upon by css_next_child() to
-	 * resume iteration after dropping RCU read lock.  See
-	 * css_next_child() for details.
+	 * creation by disabling cgroup_lock_live_group().
 	 */
-	set_bit(CGRP_DEAD, &cgrp->flags);
+	cgrp->self.flags &= ~CSS_ONLINE;
 
-	/*
-	 * Initiate massacre of all css's.  cgroup_destroy_css_killed()
-	 * will be invoked to perform the rest of destruction once the
-	 * percpu refs of all css's are confirmed to be killed.  This
-	 * involves removing the subsystem's files, drop cgroup_mutex.
-	 */
-	mutex_unlock(&cgroup_mutex);
+	/* initiate massacre of all css's */
 	for_each_css(css, ssid, cgrp)
 		kill_css(css);
-	mutex_lock(&cgroup_mutex);
 
-	/* CGRP_DEAD is set, remove from ->release_list for the last time */
+	/* CSS_ONLINE is clear, remove from ->release_list for the last time */
 	raw_spin_lock(&release_list_lock);
 	if (!list_empty(&cgrp->release_list))
 		list_del_init(&cgrp->release_list);
 	raw_spin_unlock(&release_list_lock);
 
 	/*
-	 * If @cgrp has css's attached, the second stage of cgroup
-	 * destruction is kicked off from css_killed_work_fn() after the
-	 * refs of all attached css's are killed.  If @cgrp doesn't have
-	 * any css, we kick it off here.
+	 * Remove @cgrp directory along with the base files.  @cgrp has an
+	 * extra ref on its kn.
 	 */
-	if (!cgrp->nr_css)
-		cgroup_destroy_css_killed(cgrp);
+	kernfs_remove(cgrp->kn);
 
-	/* remove @cgrp directory along with the base files */
-	mutex_unlock(&cgroup_mutex);
-
-	/*
-	 * There are two control paths which try to determine cgroup from
-	 * dentry without going through kernfs - cgroupstats_build() and
-	 * css_tryget_from_dir().  Those are supported by RCU protecting
-	 * clearing of cgrp->kn->priv backpointer, which should happen
-	 * after all files under it have been removed.
-	 */
-	kernfs_remove(cgrp->kn);	/* @cgrp has an extra ref on its kn */
-	RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
+	set_bit(CGRP_RELEASABLE, &cgroup_parent(cgrp)->flags);
+	check_for_release(cgroup_parent(cgrp));
 
-	mutex_lock(&cgroup_mutex);
+	/* put the base reference */
+	percpu_ref_kill(&cgrp->self.refcnt);
 
 	return 0;
 };
 
-/**
- * cgroup_destroy_css_killed - the second step of cgroup destruction
- * @work: cgroup->destroy_free_work
- *
- * This function is invoked from a work item for a cgroup which is being
- * destroyed after all css's are offlined and performs the rest of
- * destruction.  This is the second step of destruction described in the
- * comment above cgroup_destroy_locked().
- */
-static void cgroup_destroy_css_killed(struct cgroup *cgrp)
-{
-	struct cgroup *parent = cgrp->parent;
-
-	lockdep_assert_held(&cgroup_tree_mutex);
-	lockdep_assert_held(&cgroup_mutex);
-
-	/* delete this cgroup from parent->children */
-	list_del_rcu(&cgrp->sibling);
-
-	cgroup_put(cgrp);
-
-	set_bit(CGRP_RELEASABLE, &parent->flags);
-	check_for_release(parent);
-}
-
 static int cgroup_rmdir(struct kernfs_node *kn)
 {
-	struct cgroup *cgrp = kn->priv;
+	struct cgroup *cgrp;
 	int ret = 0;
 
-	/*
-	 * This is self-destruction but @kn can't be removed while this
-	 * callback is in progress.  Let's break active protection.  Once
-	 * the protection is broken, @cgrp can be destroyed at any point.
-	 * Pin it so that it stays accessible.
-	 */
-	cgroup_get(cgrp);
-	kernfs_break_active_protection(kn);
+	cgrp = cgroup_kn_lock_live(kn);
+	if (!cgrp)
+		return 0;
+	cgroup_get(cgrp);	/* for @kn->priv clearing */
 
-	mutex_lock(&cgroup_tree_mutex);
-	mutex_lock(&cgroup_mutex);
+	ret = cgroup_destroy_locked(cgrp);
+
+	cgroup_kn_unlock(kn);
 
 	/*
-	 * @cgrp might already have been destroyed while we're trying to
-	 * grab the mutexes.
+	 * There are two control paths which try to determine cgroup from
+	 * dentry without going through kernfs - cgroupstats_build() and
+	 * css_tryget_online_from_dir().  Those are supported by RCU
+	 * protecting clearing of cgrp->kn->priv backpointer, which should
+	 * happen after all files under it have been removed.
 	 */
-	if (!cgroup_is_dead(cgrp))
-		ret = cgroup_destroy_locked(cgrp);
-
-	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
+	if (!ret)
+		RCU_INIT_POINTER(*(void __rcu __force **)&kn->priv, NULL);
 
-	kernfs_unbreak_active_protection(kn);
 	cgroup_put(cgrp);
 	return ret;
 }
@@ -4118,15 +4842,15 @@ static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
 	.rename			= cgroup_rename,
 };
 
-static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
+static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
 {
 	struct cgroup_subsys_state *css;
 
 	printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
 
-	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
+	idr_init(&ss->css_idr);
 	INIT_LIST_HEAD(&ss->cfts);
 
 	/* Create the root cgroup state for this subsystem */
@@ -4134,7 +4858,21 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
 	/* We don't handle early failures gracefully */
 	BUG_ON(IS_ERR(css));
-	init_css(css, ss, &cgrp_dfl_root.cgrp);
+	init_and_link_css(css, ss, &cgrp_dfl_root.cgrp);
+
+	/*
+	 * Root csses are never destroyed and we can't initialize
+	 * percpu_ref during early init.  Disable refcnting.
+	 */
+	css->flags |= CSS_NO_REF;
+
+	if (early) {
+		/* allocation can't be done safely during early init */
+		css->id = 1;
+	} else {
+		css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL);
+		BUG_ON(css->id < 0);
+	}
 
 	/* Update the init_css_set to contain a subsys
 	 * pointer to this state - since the subsystem is
@@ -4151,10 +4889,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 
 	BUG_ON(online_css(css));
 
-	cgrp_dfl_root.cgrp.subsys_mask |= 1 << ss->id;
-
 	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
 }
 
 /**
@@ -4165,12 +4900,13 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
  */
 int __init cgroup_init_early(void)
 {
-	static struct cgroup_sb_opts __initdata opts =
-		{ .flags = CGRP_ROOT_SANE_BEHAVIOR };
+	static struct cgroup_sb_opts __initdata opts;
 	struct cgroup_subsys *ss;
 	int i;
 
 	init_cgroup_root(&cgrp_dfl_root, &opts);
+	cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF;
+
 	RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
 
 	for_each_subsys(ss, i) {
@@ -4185,7 +4921,7 @@ int __init cgroup_init_early(void)
 		ss->name = cgroup_subsys_name[i];
 
 		if (ss->early_init)
-			cgroup_init_subsys(ss);
+			cgroup_init_subsys(ss, true);
 	}
 	return 0;
 }
@@ -4202,9 +4938,9 @@ int __init cgroup_init(void)
 	unsigned long key;
 	int ssid, err;
 
-	BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
+	BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
+	BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
 
-	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
 	/* Add init_css_set to the hash table */
@@ -4214,18 +4950,44 @@ int __init cgroup_init(void)
 	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
 
 	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
 
 	for_each_subsys(ss, ssid) {
-		if (!ss->early_init)
-			cgroup_init_subsys(ss);
+		if (ss->early_init) {
+			struct cgroup_subsys_state *css =
+				init_css_set.subsys[ss->id];
+
+			css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2,
+						   GFP_KERNEL);
+			BUG_ON(css->id < 0);
+		} else {
+			cgroup_init_subsys(ss, false);
+		}
+
+		list_add_tail(&init_css_set.e_cset_node[ssid],
+			      &cgrp_dfl_root.cgrp.e_csets[ssid]);
 
 		/*
-		 * cftype registration needs kmalloc and can't be done
-		 * during early_init.  Register base cftypes separately.
+		 * Setting dfl_root subsys_mask needs to consider the
+		 * disabled flag and cftype registration needs kmalloc,
+		 * both of which aren't available during early_init.
 		 */
-		if (ss->base_cftypes)
-			WARN_ON(cgroup_add_cftypes(ss, ss->base_cftypes));
+		if (ss->disabled)
+			continue;
+
+		cgrp_dfl_root.subsys_mask |= 1 << ss->id;
+
+		if (cgroup_legacy_files_on_dfl && !ss->dfl_cftypes)
+			ss->dfl_cftypes = ss->legacy_cftypes;
+
+		if (!ss->dfl_cftypes)
+			cgrp_dfl_root_inhibit_ss_mask |= 1 << ss->id;
+
+		if (ss->dfl_cftypes == ss->legacy_cftypes) {
+			WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes));
+		} else {
+			WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes));
+			WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes));
+		}
 	}
 
 	cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
@@ -4308,7 +5070,7 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 
 		seq_printf(m, "%d:", root->hierarchy_id);
 		for_each_subsys(ss, ssid)
-			if (root->cgrp.subsys_mask & (1 << ssid))
+			if (root->subsys_mask & (1 << ssid))
 				seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
 		if (strlen(root->name))
 			seq_printf(m, "%sname=%s", count ? "," : "",
@@ -4503,8 +5265,8 @@ void cgroup_exit(struct task_struct *tsk)
 
 static void check_for_release(struct cgroup *cgrp)
 {
-	if (cgroup_is_releasable(cgrp) &&
-	    list_empty(&cgrp->cset_links) && list_empty(&cgrp->children)) {
+	if (cgroup_is_releasable(cgrp) && list_empty(&cgrp->cset_links) &&
+	    !css_has_online_children(&cgrp->self)) {
 		/*
 		 * Control Group is currently removeable. If it's not
 		 * already queued for a userspace notification, queue
@@ -4620,8 +5382,16 @@ static int __init cgroup_disable(char *str)
 }
 __setup("cgroup_disable=", cgroup_disable);
 
+static int __init cgroup_set_legacy_files_on_dfl(char *str)
+{
+	printk("cgroup: using legacy files on the default hierarchy\n");
+	cgroup_legacy_files_on_dfl = true;
+	return 0;
+}
+__setup("cgroup__DEVEL__legacy_files_on_dfl", cgroup_set_legacy_files_on_dfl);
+
 /**
- * css_tryget_from_dir - get corresponding css from the dentry of a cgroup dir
+ * css_tryget_online_from_dir - get corresponding css from a cgroup dentry
  * @dentry: directory dentry of interest
  * @ss: subsystem of interest
  *
@@ -4629,8 +5399,8 @@ __setup("cgroup_disable=", cgroup_disable);
  * to get the corresponding css and return it.  If such css doesn't exist
  * or can't be pinned, an ERR_PTR value is returned.
  */
-struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
-						struct cgroup_subsys *ss)
+struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
+						       struct cgroup_subsys *ss)
 {
 	struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
 	struct cgroup_subsys_state *css = NULL;
@@ -4646,13 +5416,13 @@ struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
 	/*
 	 * This path doesn't originate from kernfs and @kn could already
 	 * have been or be removed at any point.  @kn->priv is RCU
-	 * protected for this access.  See destroy_locked() for details.
+	 * protected for this access.  See cgroup_rmdir() for details.
 	 */
 	cgrp = rcu_dereference(kn->priv);
 	if (cgrp)
 		css = cgroup_css(cgrp, ss);
 
-	if (!css || !css_tryget(css))
+	if (!css || !css_tryget_online(css))
 		css = ERR_PTR(-ENOENT);
 
 	rcu_read_unlock();
@@ -4669,14 +5439,8 @@ struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
  */
 struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
 {
-	struct cgroup *cgrp;
-
-	cgroup_assert_mutexes_or_rcu_locked();
-
-	cgrp = idr_find(&ss->root->cgroup_idr, id);
-	if (cgrp)
-		return cgroup_css(cgrp, ss);
-	return NULL;
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return idr_find(&ss->css_idr, id);
 }
 
 #ifdef CONFIG_CGROUP_DEBUG
@@ -4820,6 +5584,6 @@ static struct cftype debug_files[] =  {
 struct cgroup_subsys debug_cgrp_subsys = {
 	.css_alloc = debug_css_alloc,
 	.css_free = debug_css_free,
-	.base_cftypes = debug_files,
+	.legacy_cftypes = debug_files,
 };
 #endif /* CONFIG_CGROUP_DEBUG */
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 345628c78b5..92b98cc0ee7 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -59,7 +59,7 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 
 static struct freezer *parent_freezer(struct freezer *freezer)
 {
-	return css_freezer(css_parent(&freezer->css));
+	return css_freezer(freezer->css.parent);
 }
 
 bool cgroup_freezing(struct task_struct *task)
@@ -73,10 +73,6 @@ bool cgroup_freezing(struct task_struct *task)
 	return ret;
 }
 
-/*
- * cgroups_write_string() limits the size of freezer state strings to
- * CGROUP_LOCAL_BUFFER_SIZE
- */
 static const char *freezer_state_strs(unsigned int state)
 {
 	if (state & CGROUP_FROZEN)
@@ -304,7 +300,7 @@ static int freezer_read(struct seq_file *m, void *v)
 
 	/* update states bottom-up */
 	css_for_each_descendant_post(pos, css) {
-		if (!css_tryget(pos))
+		if (!css_tryget_online(pos))
 			continue;
 		rcu_read_unlock();
 
@@ -404,7 +400,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 		struct freezer *pos_f = css_freezer(pos);
 		struct freezer *parent = parent_freezer(pos_f);
 
-		if (!css_tryget(pos))
+		if (!css_tryget_online(pos))
 			continue;
 		rcu_read_unlock();
 
@@ -423,20 +419,22 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 	mutex_unlock(&freezer_mutex);
 }
 
-static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			 char *buffer)
+static ssize_t freezer_write(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
 {
 	bool freeze;
 
-	if (strcmp(buffer, freezer_state_strs(0)) == 0)
+	buf = strstrip(buf);
+
+	if (strcmp(buf, freezer_state_strs(0)) == 0)
 		freeze = false;
-	else if (strcmp(buffer, freezer_state_strs(CGROUP_FROZEN)) == 0)
+	else if (strcmp(buf, freezer_state_strs(CGROUP_FROZEN)) == 0)
 		freeze = true;
 	else
 		return -EINVAL;
 
-	freezer_change_state(css_freezer(css), freeze);
-	return 0;
+	freezer_change_state(css_freezer(of_css(of)), freeze);
+	return nbytes;
 }
 
 static u64 freezer_self_freezing_read(struct cgroup_subsys_state *css,
@@ -460,7 +458,7 @@ static struct cftype files[] = {
 		.name = "state",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = freezer_read,
-		.write_string = freezer_write,
+		.write = freezer_write,
 	},
 	{
 		.name = "self_freezing",
@@ -482,5 +480,5 @@ struct cgroup_subsys freezer_cgrp_subsys = {
 	.css_free	= freezer_css_free,
 	.attach		= freezer_attach,
 	.fork		= freezer_fork,
-	.base_cftypes	= files,
+	.legacy_cftypes	= files,
 };
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 019d4500844..5664985c46a 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/hardirq.h>
 #include <linux/export.h>
+#include <linux/kprobes.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/context_tracking.h>
@@ -104,6 +105,7 @@ void context_tracking_user_enter(void)
 	}
 	local_irq_restore(flags);
 }
+NOKPROBE_SYMBOL(context_tracking_user_enter);
 
 #ifdef CONFIG_PREEMPT
 /**
@@ -181,6 +183,7 @@ void context_tracking_user_exit(void)
 	}
 	local_irq_restore(flags);
 }
+NOKPROBE_SYMBOL(context_tracking_user_exit);
 
 /**
  * __context_tracking_task_switch - context switch the syscall callbacks
diff --git a/kernel/cpu.c b/kernel/cpu.c
index acf791c55b7..81e2a388a0f 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -20,6 +20,7 @@
 #include <linux/gfp.h>
 #include <linux/suspend.h>
 #include <linux/lockdep.h>
+#include <trace/events/power.h>
 
 #include "smpboot.h"
 
@@ -273,21 +274,28 @@ void clear_tasks_mm_cpumask(int cpu)
 	rcu_read_unlock();
 }
 
-static inline void check_for_tasks(int cpu)
+static inline void check_for_tasks(int dead_cpu)
 {
-	struct task_struct *p;
-	cputime_t utime, stime;
+	struct task_struct *g, *p;
 
-	write_lock_irq(&tasklist_lock);
-	for_each_process(p) {
-		task_cputime(p, &utime, &stime);
-		if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&
-		    (utime || stime))
-			pr_warn("Task %s (pid = %d) is on cpu %d (state = %ld, flags = %x)\n",
-				p->comm, task_pid_nr(p), cpu,
-				p->state, p->flags);
-	}
-	write_unlock_irq(&tasklist_lock);
+	read_lock_irq(&tasklist_lock);
+	do_each_thread(g, p) {
+		if (!p->on_rq)
+			continue;
+		/*
+		 * We do the check with unlocked task_rq(p)->lock.
+		 * Order the reading to do not warn about a task,
+		 * which was running on this cpu in the past, and
+		 * it's just been woken on another cpu.
+		 */
+		rmb();
+		if (task_cpu(p) != dead_cpu)
+			continue;
+
+		pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n",
+			p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags);
+	} while_each_thread(g, p);
+	read_unlock_irq(&tasklist_lock);
 }
 
 struct take_cpu_down_param {
@@ -520,7 +528,9 @@ int disable_nonboot_cpus(void)
 	for_each_online_cpu(cpu) {
 		if (cpu == first_cpu)
 			continue;
+		trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
 		error = _cpu_down(cpu, 1);
+		trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
 		if (!error)
 			cpumask_set_cpu(cpu, frozen_cpus);
 		else {
@@ -563,7 +573,9 @@ void __ref enable_nonboot_cpus(void)
 	arch_enable_nonboot_cpus_begin();
 
 	for_each_cpu(cpu, frozen_cpus) {
+		trace_suspend_resume(TPS("CPU_ON"), cpu, true);
 		error = _cpu_up(cpu, 1);
+		trace_suspend_resume(TPS("CPU_ON"), cpu, false);
 		if (!error) {
 			pr_info("CPU%d is up\n", cpu);
 			continue;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 13001784389..22874d7cf2c 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -76,8 +76,34 @@ struct cpuset {
 	struct cgroup_subsys_state css;
 
 	unsigned long flags;		/* "unsigned long" so bitops work */
-	cpumask_var_t cpus_allowed;	/* CPUs allowed to tasks in cpuset */
-	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */
+
+	/*
+	 * On default hierarchy:
+	 *
+	 * The user-configured masks can only be changed by writing to
+	 * cpuset.cpus and cpuset.mems, and won't be limited by the
+	 * parent masks.
+	 *
+	 * The effective masks is the real masks that apply to the tasks
+	 * in the cpuset. They may be changed if the configured masks are
+	 * changed or hotplug happens.
+	 *
+	 * effective_mask == configured_mask & parent's effective_mask,
+	 * and if it ends up empty, it will inherit the parent's mask.
+	 *
+	 *
+	 * On legacy hierachy:
+	 *
+	 * The user-configured masks are always the same with effective masks.
+	 */
+
+	/* user-configured CPUs and Memory Nodes allow to tasks */
+	cpumask_var_t cpus_allowed;
+	nodemask_t mems_allowed;
+
+	/* effective CPUs and Memory Nodes allow to tasks */
+	cpumask_var_t effective_cpus;
+	nodemask_t effective_mems;
 
 	/*
 	 * This is old Memory Nodes tasks took on.
@@ -119,7 +145,7 @@ static inline struct cpuset *task_cs(struct task_struct *task)
 
 static inline struct cpuset *parent_cs(struct cpuset *cs)
 {
-	return css_cs(css_parent(&cs->css));
+	return css_cs(cs->css.parent);
 }
 
 #ifdef CONFIG_NUMA
@@ -307,9 +333,9 @@ static struct file_system_type cpuset_fs_type = {
  */
 static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 {
-	while (!cpumask_intersects(cs->cpus_allowed, cpu_online_mask))
+	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask))
 		cs = parent_cs(cs);
-	cpumask_and(pmask, cs->cpus_allowed, cpu_online_mask);
+	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
 }
 
 /*
@@ -325,9 +351,9 @@ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
  */
 static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask)
 {
-	while (!nodes_intersects(cs->mems_allowed, node_states[N_MEMORY]))
+	while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY]))
 		cs = parent_cs(cs);
-	nodes_and(*pmask, cs->mems_allowed, node_states[N_MEMORY]);
+	nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]);
 }
 
 /*
@@ -376,13 +402,20 @@ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs)
 	if (!trial)
 		return NULL;
 
-	if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL)) {
-		kfree(trial);
-		return NULL;
-	}
-	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
+	if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL))
+		goto free_cs;
+	if (!alloc_cpumask_var(&trial->effective_cpus, GFP_KERNEL))
+		goto free_cpus;
 
+	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
+	cpumask_copy(trial->effective_cpus, cs->effective_cpus);
 	return trial;
+
+free_cpus:
+	free_cpumask_var(trial->cpus_allowed);
+free_cs:
+	kfree(trial);
+	return NULL;
 }
 
 /**
@@ -391,6 +424,7 @@ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs)
  */
 static void free_trial_cpuset(struct cpuset *trial)
 {
+	free_cpumask_var(trial->effective_cpus);
 	free_cpumask_var(trial->cpus_allowed);
 	kfree(trial);
 }
@@ -436,9 +470,9 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 
 	par = parent_cs(cur);
 
-	/* We must be a subset of our parent cpuset */
+	/* On legacy hiearchy, we must be a subset of our parent cpuset. */
 	ret = -EACCES;
-	if (!is_cpuset_subset(trial, par))
+	if (!cgroup_on_dfl(cur->css.cgroup) && !is_cpuset_subset(trial, par))
 		goto out;
 
 	/*
@@ -480,11 +514,11 @@ out:
 #ifdef CONFIG_SMP
 /*
  * Helper routine for generate_sched_domains().
- * Do cpusets a, b have overlapping cpus_allowed masks?
+ * Do cpusets a, b have overlapping effective cpus_allowed masks?
  */
 static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
 {
-	return cpumask_intersects(a->cpus_allowed, b->cpus_allowed);
+	return cpumask_intersects(a->effective_cpus, b->effective_cpus);
 }
 
 static void
@@ -601,7 +635,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		cpumask_copy(doms[0], top_cpuset.cpus_allowed);
+		cpumask_copy(doms[0], top_cpuset.effective_cpus);
 
 		goto done;
 	}
@@ -691,11 +725,8 @@ restart:
 		if (nslot == ndoms) {
 			static int warnings = 10;
 			if (warnings) {
-				printk(KERN_WARNING
-				 "rebuild_sched_domains confused:"
-				  " nslot %d, ndoms %d, csn %d, i %d,"
-				  " apn %d\n",
-				  nslot, ndoms, csn, i, apn);
+				pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n",
+					nslot, ndoms, csn, i, apn);
 				warnings--;
 			}
 			continue;
@@ -708,7 +739,7 @@ restart:
 			struct cpuset *b = csa[j];
 
 			if (apn == b->pn) {
-				cpumask_or(dp, dp, b->cpus_allowed);
+				cpumask_or(dp, dp, b->effective_cpus);
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
@@ -760,7 +791,7 @@ static void rebuild_sched_domains_locked(void)
 	 * passing doms with offlined cpu to partition_sched_domains().
 	 * Anyways, hotplug work item will rebuild sched domains.
 	 */
-	if (!cpumask_equal(top_cpuset.cpus_allowed, cpu_active_mask))
+	if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
 		goto out;
 
 	/* Generate domain masks and attrs */
@@ -784,45 +815,6 @@ void rebuild_sched_domains(void)
 	mutex_unlock(&cpuset_mutex);
 }
 
-/*
- * effective_cpumask_cpuset - return nearest ancestor with non-empty cpus
- * @cs: the cpuset in interest
- *
- * A cpuset's effective cpumask is the cpumask of the nearest ancestor
- * with non-empty cpus. We use effective cpumask whenever:
- * - we update tasks' cpus_allowed. (they take on the ancestor's cpumask
- *   if the cpuset they reside in has no cpus)
- * - we want to retrieve task_cs(tsk)'s cpus_allowed.
- *
- * Called with cpuset_mutex held. cpuset_cpus_allowed_fallback() is an
- * exception. See comments there.
- */
-static struct cpuset *effective_cpumask_cpuset(struct cpuset *cs)
-{
-	while (cpumask_empty(cs->cpus_allowed))
-		cs = parent_cs(cs);
-	return cs;
-}
-
-/*
- * effective_nodemask_cpuset - return nearest ancestor with non-empty mems
- * @cs: the cpuset in interest
- *
- * A cpuset's effective nodemask is the nodemask of the nearest ancestor
- * with non-empty memss. We use effective nodemask whenever:
- * - we update tasks' mems_allowed. (they take on the ancestor's nodemask
- *   if the cpuset they reside in has no mems)
- * - we want to retrieve task_cs(tsk)'s mems_allowed.
- *
- * Called with cpuset_mutex held.
- */
-static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs)
-{
-	while (nodes_empty(cs->mems_allowed))
-		cs = parent_cs(cs);
-	return cs;
-}
-
 /**
  * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
@@ -833,65 +825,92 @@ static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs)
  */
 static void update_tasks_cpumask(struct cpuset *cs)
 {
-	struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
 	struct css_task_iter it;
 	struct task_struct *task;
 
 	css_task_iter_start(&cs->css, &it);
 	while ((task = css_task_iter_next(&it)))
-		set_cpus_allowed_ptr(task, cpus_cs->cpus_allowed);
+		set_cpus_allowed_ptr(task, cs->effective_cpus);
 	css_task_iter_end(&it);
 }
 
 /*
- * update_tasks_cpumask_hier - Update the cpumasks of tasks in the hierarchy.
- * @root_cs: the root cpuset of the hierarchy
- * @update_root: update root cpuset or not?
+ * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
+ * @cs: the cpuset to consider
+ * @new_cpus: temp variable for calculating new effective_cpus
+ *
+ * When congifured cpumask is changed, the effective cpumasks of this cpuset
+ * and all its descendants need to be updated.
  *
- * This will update cpumasks of tasks in @root_cs and all other empty cpusets
- * which take on cpumask of @root_cs.
+ * On legacy hierachy, effective_cpus will be the same with cpu_allowed.
  *
  * Called with cpuset_mutex held
  */
-static void update_tasks_cpumask_hier(struct cpuset *root_cs, bool update_root)
+static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 {
 	struct cpuset *cp;
 	struct cgroup_subsys_state *pos_css;
+	bool need_rebuild_sched_domains = false;
 
 	rcu_read_lock();
-	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
-		if (cp == root_cs) {
-			if (!update_root)
-				continue;
-		} else {
-			/* skip the whole subtree if @cp have some CPU */
-			if (!cpumask_empty(cp->cpus_allowed)) {
-				pos_css = css_rightmost_descendant(pos_css);
-				continue;
-			}
+	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
+		struct cpuset *parent = parent_cs(cp);
+
+		cpumask_and(new_cpus, cp->cpus_allowed, parent->effective_cpus);
+
+		/*
+		 * If it becomes empty, inherit the effective mask of the
+		 * parent, which is guaranteed to have some CPUs.
+		 */
+		if (cpumask_empty(new_cpus))
+			cpumask_copy(new_cpus, parent->effective_cpus);
+
+		/* Skip the whole subtree if the cpumask remains the same. */
+		if (cpumask_equal(new_cpus, cp->effective_cpus)) {
+			pos_css = css_rightmost_descendant(pos_css);
+			continue;
 		}
-		if (!css_tryget(&cp->css))
+
+		if (!css_tryget_online(&cp->css))
 			continue;
 		rcu_read_unlock();
 
+		mutex_lock(&callback_mutex);
+		cpumask_copy(cp->effective_cpus, new_cpus);
+		mutex_unlock(&callback_mutex);
+
+		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
+
 		update_tasks_cpumask(cp);
 
+		/*
+		 * If the effective cpumask of any non-empty cpuset is changed,
+		 * we need to rebuild sched domains.
+		 */
+		if (!cpumask_empty(cp->cpus_allowed) &&
+		    is_sched_load_balance(cp))
+			need_rebuild_sched_domains = true;
+
 		rcu_read_lock();
 		css_put(&cp->css);
 	}
 	rcu_read_unlock();
+
+	if (need_rebuild_sched_domains)
+		rebuild_sched_domains_locked();
 }
 
 /**
  * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it
  * @cs: the cpuset to consider
+ * @trialcs: trial cpuset
  * @buf: buffer of cpu numbers written to this cpuset
  */
 static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 			  const char *buf)
 {
 	int retval;
-	int is_load_balanced;
 
 	/* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
 	if (cs == &top_cpuset)
@@ -910,7 +929,8 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		if (retval < 0)
 			return retval;
 
-		if (!cpumask_subset(trialcs->cpus_allowed, cpu_active_mask))
+		if (!cpumask_subset(trialcs->cpus_allowed,
+				    top_cpuset.cpus_allowed))
 			return -EINVAL;
 	}
 
@@ -922,16 +942,12 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval < 0)
 		return retval;
 
-	is_load_balanced = is_sched_load_balance(trialcs);
-
 	mutex_lock(&callback_mutex);
 	cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
 	mutex_unlock(&callback_mutex);
 
-	update_tasks_cpumask_hier(cs, true);
-
-	if (is_load_balanced)
-		rebuild_sched_domains_locked();
+	/* use trialcs->cpus_allowed as a temp variable */
+	update_cpumasks_hier(cs, trialcs->cpus_allowed);
 	return 0;
 }
 
@@ -953,15 +969,13 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 							const nodemask_t *to)
 {
 	struct task_struct *tsk = current;
-	struct cpuset *mems_cs;
 
 	tsk->mems_allowed = *to;
 
 	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
 
 	rcu_read_lock();
-	mems_cs = effective_nodemask_cpuset(task_cs(tsk));
-	guarantee_online_mems(mems_cs, &tsk->mems_allowed);
+	guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
 	rcu_read_unlock();
 }
 
@@ -1030,13 +1044,12 @@ static void *cpuset_being_rebound;
 static void update_tasks_nodemask(struct cpuset *cs)
 {
 	static nodemask_t newmems;	/* protected by cpuset_mutex */
-	struct cpuset *mems_cs = effective_nodemask_cpuset(cs);
 	struct css_task_iter it;
 	struct task_struct *task;
 
 	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */
 
-	guarantee_online_mems(mems_cs, &newmems);
+	guarantee_online_mems(cs, &newmems);
 
 	/*
 	 * The mpol_rebind_mm() call takes mmap_sem, which we couldn't
@@ -1079,36 +1092,52 @@ static void update_tasks_nodemask(struct cpuset *cs)
 }
 
 /*
- * update_tasks_nodemask_hier - Update the nodemasks of tasks in the hierarchy.
- * @cs: the root cpuset of the hierarchy
- * @update_root: update the root cpuset or not?
+ * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree
+ * @cs: the cpuset to consider
+ * @new_mems: a temp variable for calculating new effective_mems
+ *
+ * When configured nodemask is changed, the effective nodemasks of this cpuset
+ * and all its descendants need to be updated.
  *
- * This will update nodemasks of tasks in @root_cs and all other empty cpusets
- * which take on nodemask of @root_cs.
+ * On legacy hiearchy, effective_mems will be the same with mems_allowed.
  *
  * Called with cpuset_mutex held
  */
-static void update_tasks_nodemask_hier(struct cpuset *root_cs, bool update_root)
+static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 {
 	struct cpuset *cp;
 	struct cgroup_subsys_state *pos_css;
 
 	rcu_read_lock();
-	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
-		if (cp == root_cs) {
-			if (!update_root)
-				continue;
-		} else {
-			/* skip the whole subtree if @cp have some CPU */
-			if (!nodes_empty(cp->mems_allowed)) {
-				pos_css = css_rightmost_descendant(pos_css);
-				continue;
-			}
+	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
+		struct cpuset *parent = parent_cs(cp);
+
+		nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems);
+
+		/*
+		 * If it becomes empty, inherit the effective mask of the
+		 * parent, which is guaranteed to have some MEMs.
+		 */
+		if (nodes_empty(*new_mems))
+			*new_mems = parent->effective_mems;
+
+		/* Skip the whole subtree if the nodemask remains the same. */
+		if (nodes_equal(*new_mems, cp->effective_mems)) {
+			pos_css = css_rightmost_descendant(pos_css);
+			continue;
 		}
-		if (!css_tryget(&cp->css))
+
+		if (!css_tryget_online(&cp->css))
 			continue;
 		rcu_read_unlock();
 
+		mutex_lock(&callback_mutex);
+		cp->effective_mems = *new_mems;
+		mutex_unlock(&callback_mutex);
+
+		WARN_ON(!cgroup_on_dfl(cp->css.cgroup) &&
+			!nodes_equal(cp->mems_allowed, cp->effective_mems));
+
 		update_tasks_nodemask(cp);
 
 		rcu_read_lock();
@@ -1158,8 +1187,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 			goto done;
 
 		if (!nodes_subset(trialcs->mems_allowed,
-				node_states[N_MEMORY])) {
-			retval =  -EINVAL;
+				  top_cpuset.mems_allowed)) {
+			retval = -EINVAL;
 			goto done;
 		}
 	}
@@ -1176,14 +1205,21 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	cs->mems_allowed = trialcs->mems_allowed;
 	mutex_unlock(&callback_mutex);
 
-	update_tasks_nodemask_hier(cs, true);
+	/* use trialcs->mems_allowed as a temp variable */
+	update_nodemasks_hier(cs, &cs->mems_allowed);
 done:
 	return retval;
 }
 
 int current_cpuset_is_being_rebound(void)
 {
-	return task_cs(current) == cpuset_being_rebound;
+	int ret;
+
+	rcu_read_lock();
+	ret = task_cs(current) == cpuset_being_rebound;
+	rcu_read_unlock();
+
+	return ret;
 }
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
@@ -1385,12 +1421,9 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 
 	mutex_lock(&cpuset_mutex);
 
-	/*
-	 * We allow to move tasks into an empty cpuset if sane_behavior
-	 * flag is set.
-	 */
+	/* allow moving tasks into an empty cpuset if on default hierarchy */
 	ret = -ENOSPC;
-	if (!cgroup_sane_behavior(css->cgroup) &&
+	if (!cgroup_on_dfl(css->cgroup) &&
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
@@ -1448,8 +1481,6 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	struct task_struct *leader = cgroup_taskset_first(tset);
 	struct cpuset *cs = css_cs(css);
 	struct cpuset *oldcs = cpuset_attach_old_cs;
-	struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
-	struct cpuset *mems_cs = effective_nodemask_cpuset(cs);
 
 	mutex_lock(&cpuset_mutex);
 
@@ -1457,9 +1488,9 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	if (cs == &top_cpuset)
 		cpumask_copy(cpus_attach, cpu_possible_mask);
 	else
-		guarantee_online_cpus(cpus_cs, cpus_attach);
+		guarantee_online_cpus(cs, cpus_attach);
 
-	guarantee_online_mems(mems_cs, &cpuset_attach_nodemask_to);
+	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
 	cgroup_taskset_for_each(task, tset) {
 		/*
@@ -1476,11 +1507,9 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	 * Change mm, possibly for multiple threads in a threadgroup. This is
 	 * expensive and may sleep.
 	 */
-	cpuset_attach_nodemask_to = cs->mems_allowed;
+	cpuset_attach_nodemask_to = cs->effective_mems;
 	mm = get_task_mm(leader);
 	if (mm) {
-		struct cpuset *mems_oldcs = effective_nodemask_cpuset(oldcs);
-
 		mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
 
 		/*
@@ -1491,7 +1520,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 		 * mm from.
 		 */
 		if (is_memory_migrate(cs)) {
-			cpuset_migrate_mm(mm, &mems_oldcs->old_mems_allowed,
+			cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
 					  &cpuset_attach_nodemask_to);
 		}
 		mmput(mm);
@@ -1512,6 +1541,8 @@ typedef enum {
 	FILE_MEMORY_MIGRATE,
 	FILE_CPULIST,
 	FILE_MEMLIST,
+	FILE_EFFECTIVE_CPULIST,
+	FILE_EFFECTIVE_MEMLIST,
 	FILE_CPU_EXCLUSIVE,
 	FILE_MEM_EXCLUSIVE,
 	FILE_MEM_HARDWALL,
@@ -1600,13 +1631,15 @@ out_unlock:
 /*
  * Common handling for a write to a "cpus" or "mems" file.
  */
-static int cpuset_write_resmask(struct cgroup_subsys_state *css,
-				struct cftype *cft, char *buf)
+static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
 {
-	struct cpuset *cs = css_cs(css);
+	struct cpuset *cs = css_cs(of_css(of));
 	struct cpuset *trialcs;
 	int retval = -ENODEV;
 
+	buf = strstrip(buf);
+
 	/*
 	 * CPU or memory hotunplug may leave @cs w/o any execution
 	 * resources, in which case the hotplug code asynchronously updates
@@ -1617,7 +1650,17 @@ static int cpuset_write_resmask(struct cgroup_subsys_state *css,
 	 * resources, wait for the previously scheduled operations before
 	 * proceeding, so that we don't end up keep removing tasks added
 	 * after execution capability is restored.
+	 *
+	 * cpuset_hotplug_work calls back into cgroup core via
+	 * cgroup_transfer_tasks() and waiting for it from a cgroupfs
+	 * operation like this one can lead to a deadlock through kernfs
+	 * active_ref protection.  Let's break the protection.  Losing the
+	 * protection is okay as we check whether @cs is online after
+	 * grabbing cpuset_mutex anyway.  This only happens on the legacy
+	 * hierarchies.
 	 */
+	css_get(&cs->css);
+	kernfs_break_active_protection(of->kn);
 	flush_work(&cpuset_hotplug_work);
 
 	mutex_lock(&cpuset_mutex);
@@ -1630,7 +1673,7 @@ static int cpuset_write_resmask(struct cgroup_subsys_state *css,
 		goto out_unlock;
 	}
 
-	switch (cft->private) {
+	switch (of_cft(of)->private) {
 	case FILE_CPULIST:
 		retval = update_cpumask(cs, trialcs, buf);
 		break;
@@ -1645,7 +1688,9 @@ static int cpuset_write_resmask(struct cgroup_subsys_state *css,
 	free_trial_cpuset(trialcs);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
-	return retval;
+	kernfs_unbreak_active_protection(of->kn);
+	css_put(&cs->css);
+	return retval ?: nbytes;
 }
 
 /*
@@ -1676,6 +1721,12 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	case FILE_MEMLIST:
 		s += nodelist_scnprintf(s, count, cs->mems_allowed);
 		break;
+	case FILE_EFFECTIVE_CPULIST:
+		s += cpulist_scnprintf(s, count, cs->effective_cpus);
+		break;
+	case FILE_EFFECTIVE_MEMLIST:
+		s += nodelist_scnprintf(s, count, cs->effective_mems);
+		break;
 	default:
 		ret = -EINVAL;
 		goto out_unlock;
@@ -1747,7 +1798,7 @@ static struct cftype files[] = {
 	{
 		.name = "cpus",
 		.seq_show = cpuset_common_seq_show,
-		.write_string = cpuset_write_resmask,
+		.write = cpuset_write_resmask,
 		.max_write_len = (100U + 6 * NR_CPUS),
 		.private = FILE_CPULIST,
 	},
@@ -1755,12 +1806,24 @@ static struct cftype files[] = {
 	{
 		.name = "mems",
 		.seq_show = cpuset_common_seq_show,
-		.write_string = cpuset_write_resmask,
+		.write = cpuset_write_resmask,
 		.max_write_len = (100U + 6 * MAX_NUMNODES),
 		.private = FILE_MEMLIST,
 	},
 
 	{
+		.name = "effective_cpus",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_EFFECTIVE_CPULIST,
+	},
+
+	{
+		.name = "effective_mems",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_EFFECTIVE_MEMLIST,
+	},
+
+	{
 		.name = "cpu_exclusive",
 		.read_u64 = cpuset_read_u64,
 		.write_u64 = cpuset_write_u64,
@@ -1851,18 +1914,26 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
-	if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) {
-		kfree(cs);
-		return ERR_PTR(-ENOMEM);
-	}
+	if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL))
+		goto free_cs;
+	if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL))
+		goto free_cpus;
 
 	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
 	cpumask_clear(cs->cpus_allowed);
 	nodes_clear(cs->mems_allowed);
+	cpumask_clear(cs->effective_cpus);
+	nodes_clear(cs->effective_mems);
 	fmeter_init(&cs->fmeter);
 	cs->relax_domain_level = -1;
 
 	return &cs->css;
+
+free_cpus:
+	free_cpumask_var(cs->cpus_allowed);
+free_cs:
+	kfree(cs);
+	return ERR_PTR(-ENOMEM);
 }
 
 static int cpuset_css_online(struct cgroup_subsys_state *css)
@@ -1885,6 +1956,13 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 
 	cpuset_inc();
 
+	mutex_lock(&callback_mutex);
+	if (cgroup_on_dfl(cs->css.cgroup)) {
+		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
+		cs->effective_mems = parent->effective_mems;
+	}
+	mutex_unlock(&callback_mutex);
+
 	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
 		goto out_unlock;
 
@@ -1944,20 +2022,40 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
 
+	free_cpumask_var(cs->effective_cpus);
 	free_cpumask_var(cs->cpus_allowed);
 	kfree(cs);
 }
 
+static void cpuset_bind(struct cgroup_subsys_state *root_css)
+{
+	mutex_lock(&cpuset_mutex);
+	mutex_lock(&callback_mutex);
+
+	if (cgroup_on_dfl(root_css->cgroup)) {
+		cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
+		top_cpuset.mems_allowed = node_possible_map;
+	} else {
+		cpumask_copy(top_cpuset.cpus_allowed,
+			     top_cpuset.effective_cpus);
+		top_cpuset.mems_allowed = top_cpuset.effective_mems;
+	}
+
+	mutex_unlock(&callback_mutex);
+	mutex_unlock(&cpuset_mutex);
+}
+
 struct cgroup_subsys cpuset_cgrp_subsys = {
-	.css_alloc = cpuset_css_alloc,
-	.css_online = cpuset_css_online,
-	.css_offline = cpuset_css_offline,
-	.css_free = cpuset_css_free,
-	.can_attach = cpuset_can_attach,
-	.cancel_attach = cpuset_cancel_attach,
-	.attach = cpuset_attach,
-	.base_cftypes = files,
-	.early_init = 1,
+	.css_alloc	= cpuset_css_alloc,
+	.css_online	= cpuset_css_online,
+	.css_offline	= cpuset_css_offline,
+	.css_free	= cpuset_css_free,
+	.can_attach	= cpuset_can_attach,
+	.cancel_attach	= cpuset_cancel_attach,
+	.attach		= cpuset_attach,
+	.bind		= cpuset_bind,
+	.legacy_cftypes	= files,
+	.early_init	= 1,
 };
 
 /**
@@ -1972,9 +2070,13 @@ int __init cpuset_init(void)
 
 	if (!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL))
 		BUG();
+	if (!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL))
+		BUG();
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
+	cpumask_setall(top_cpuset.effective_cpus);
+	nodes_setall(top_cpuset.effective_mems);
 
 	fmeter_init(&top_cpuset.fmeter);
 	set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags);
@@ -2011,12 +2113,72 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
 		parent = parent_cs(parent);
 
 	if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) {
-		printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset ");
+		pr_err("cpuset: failed to transfer tasks out of empty cpuset ");
 		pr_cont_cgroup_name(cs->css.cgroup);
 		pr_cont("\n");
 	}
 }
 
+static void
+hotplug_update_tasks_legacy(struct cpuset *cs,
+			    struct cpumask *new_cpus, nodemask_t *new_mems,
+			    bool cpus_updated, bool mems_updated)
+{
+	bool is_empty;
+
+	mutex_lock(&callback_mutex);
+	cpumask_copy(cs->cpus_allowed, new_cpus);
+	cpumask_copy(cs->effective_cpus, new_cpus);
+	cs->mems_allowed = *new_mems;
+	cs->effective_mems = *new_mems;
+	mutex_unlock(&callback_mutex);
+
+	/*
+	 * Don't call update_tasks_cpumask() if the cpuset becomes empty,
+	 * as the tasks will be migratecd to an ancestor.
+	 */
+	if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
+		update_tasks_cpumask(cs);
+	if (mems_updated && !nodes_empty(cs->mems_allowed))
+		update_tasks_nodemask(cs);
+
+	is_empty = cpumask_empty(cs->cpus_allowed) ||
+		   nodes_empty(cs->mems_allowed);
+
+	mutex_unlock(&cpuset_mutex);
+
+	/*
+	 * Move tasks to the nearest ancestor with execution resources,
+	 * This is full cgroup operation which will also call back into
+	 * cpuset. Should be done outside any lock.
+	 */
+	if (is_empty)
+		remove_tasks_in_empty_cpuset(cs);
+
+	mutex_lock(&cpuset_mutex);
+}
+
+static void
+hotplug_update_tasks(struct cpuset *cs,
+		     struct cpumask *new_cpus, nodemask_t *new_mems,
+		     bool cpus_updated, bool mems_updated)
+{
+	if (cpumask_empty(new_cpus))
+		cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus);
+	if (nodes_empty(*new_mems))
+		*new_mems = parent_cs(cs)->effective_mems;
+
+	mutex_lock(&callback_mutex);
+	cpumask_copy(cs->effective_cpus, new_cpus);
+	cs->effective_mems = *new_mems;
+	mutex_unlock(&callback_mutex);
+
+	if (cpus_updated)
+		update_tasks_cpumask(cs);
+	if (mems_updated)
+		update_tasks_nodemask(cs);
+}
+
 /**
  * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug
  * @cs: cpuset in interest
@@ -2027,11 +2189,10 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
  */
 static void cpuset_hotplug_update_tasks(struct cpuset *cs)
 {
-	static cpumask_t off_cpus;
-	static nodemask_t off_mems;
-	bool is_empty;
-	bool sane = cgroup_sane_behavior(cs->css.cgroup);
-
+	static cpumask_t new_cpus;
+	static nodemask_t new_mems;
+	bool cpus_updated;
+	bool mems_updated;
 retry:
 	wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
 
@@ -2046,51 +2207,20 @@ retry:
 		goto retry;
 	}
 
-	cpumask_andnot(&off_cpus, cs->cpus_allowed, top_cpuset.cpus_allowed);
-	nodes_andnot(off_mems, cs->mems_allowed, top_cpuset.mems_allowed);
+	cpumask_and(&new_cpus, cs->cpus_allowed, parent_cs(cs)->effective_cpus);
+	nodes_and(new_mems, cs->mems_allowed, parent_cs(cs)->effective_mems);
 
-	mutex_lock(&callback_mutex);
-	cpumask_andnot(cs->cpus_allowed, cs->cpus_allowed, &off_cpus);
-	mutex_unlock(&callback_mutex);
-
-	/*
-	 * If sane_behavior flag is set, we need to update tasks' cpumask
-	 * for empty cpuset to take on ancestor's cpumask. Otherwise, don't
-	 * call update_tasks_cpumask() if the cpuset becomes empty, as
-	 * the tasks in it will be migrated to an ancestor.
-	 */
-	if ((sane && cpumask_empty(cs->cpus_allowed)) ||
-	    (!cpumask_empty(&off_cpus) && !cpumask_empty(cs->cpus_allowed)))
-		update_tasks_cpumask(cs);
+	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
+	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
 
-	mutex_lock(&callback_mutex);
-	nodes_andnot(cs->mems_allowed, cs->mems_allowed, off_mems);
-	mutex_unlock(&callback_mutex);
-
-	/*
-	 * If sane_behavior flag is set, we need to update tasks' nodemask
-	 * for empty cpuset to take on ancestor's nodemask. Otherwise, don't
-	 * call update_tasks_nodemask() if the cpuset becomes empty, as
-	 * the tasks in it will be migratd to an ancestor.
-	 */
-	if ((sane && nodes_empty(cs->mems_allowed)) ||
-	    (!nodes_empty(off_mems) && !nodes_empty(cs->mems_allowed)))
-		update_tasks_nodemask(cs);
-
-	is_empty = cpumask_empty(cs->cpus_allowed) ||
-		nodes_empty(cs->mems_allowed);
+	if (cgroup_on_dfl(cs->css.cgroup))
+		hotplug_update_tasks(cs, &new_cpus, &new_mems,
+				     cpus_updated, mems_updated);
+	else
+		hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems,
+					    cpus_updated, mems_updated);
 
 	mutex_unlock(&cpuset_mutex);
-
-	/*
-	 * If sane_behavior flag is set, we'll keep tasks in empty cpusets.
-	 *
-	 * Otherwise move tasks to the nearest ancestor with execution
-	 * resources.  This is full cgroup operation which will
-	 * also call back into cpuset.  Should be done outside any lock.
-	 */
-	if (!sane && is_empty)
-		remove_tasks_in_empty_cpuset(cs);
 }
 
 /**
@@ -2114,6 +2244,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
+	bool on_dfl = cgroup_on_dfl(top_cpuset.css.cgroup);
 
 	mutex_lock(&cpuset_mutex);
 
@@ -2121,13 +2252,15 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	cpumask_copy(&new_cpus, cpu_active_mask);
 	new_mems = node_states[N_MEMORY];
 
-	cpus_updated = !cpumask_equal(top_cpuset.cpus_allowed, &new_cpus);
-	mems_updated = !nodes_equal(top_cpuset.mems_allowed, new_mems);
+	cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus);
+	mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems);
 
 	/* synchronize cpus_allowed to cpu_active_mask */
 	if (cpus_updated) {
 		mutex_lock(&callback_mutex);
-		cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
+		if (!on_dfl)
+			cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
+		cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
 		mutex_unlock(&callback_mutex);
 		/* we don't mess with cpumasks of tasks in top_cpuset */
 	}
@@ -2135,7 +2268,9 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	/* synchronize mems_allowed to N_MEMORY */
 	if (mems_updated) {
 		mutex_lock(&callback_mutex);
-		top_cpuset.mems_allowed = new_mems;
+		if (!on_dfl)
+			top_cpuset.mems_allowed = new_mems;
+		top_cpuset.effective_mems = new_mems;
 		mutex_unlock(&callback_mutex);
 		update_tasks_nodemask(&top_cpuset);
 	}
@@ -2149,7 +2284,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 
 		rcu_read_lock();
 		cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
-			if (cs == &top_cpuset || !css_tryget(&cs->css))
+			if (cs == &top_cpuset || !css_tryget_online(&cs->css))
 				continue;
 			rcu_read_unlock();
 
@@ -2210,6 +2345,9 @@ void __init cpuset_init_smp(void)
 	top_cpuset.mems_allowed = node_states[N_MEMORY];
 	top_cpuset.old_mems_allowed = top_cpuset.mems_allowed;
 
+	cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask);
+	top_cpuset.effective_mems = node_states[N_MEMORY];
+
 	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
 }
 
@@ -2226,23 +2364,17 @@ void __init cpuset_init_smp(void)
 
 void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
-	struct cpuset *cpus_cs;
-
 	mutex_lock(&callback_mutex);
 	rcu_read_lock();
-	cpus_cs = effective_cpumask_cpuset(task_cs(tsk));
-	guarantee_online_cpus(cpus_cs, pmask);
+	guarantee_online_cpus(task_cs(tsk), pmask);
 	rcu_read_unlock();
 	mutex_unlock(&callback_mutex);
 }
 
 void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 {
-	struct cpuset *cpus_cs;
-
 	rcu_read_lock();
-	cpus_cs = effective_cpumask_cpuset(task_cs(tsk));
-	do_set_cpus_allowed(tsk, cpus_cs->cpus_allowed);
+	do_set_cpus_allowed(tsk, task_cs(tsk)->effective_cpus);
 	rcu_read_unlock();
 
 	/*
@@ -2281,13 +2413,11 @@ void cpuset_init_current_mems_allowed(void)
 
 nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
 {
-	struct cpuset *mems_cs;
 	nodemask_t mask;
 
 	mutex_lock(&callback_mutex);
 	rcu_read_lock();
-	mems_cs = effective_nodemask_cpuset(task_cs(tsk));
-	guarantee_online_mems(mems_cs, &mask);
+	guarantee_online_mems(task_cs(tsk), &mask);
 	rcu_read_unlock();
 	mutex_unlock(&callback_mutex);
 
@@ -2530,7 +2660,7 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 
 /**
  * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed
- * @task: pointer to task_struct of some task.
+ * @tsk: pointer to task_struct of some task.
  *
  * Description: Prints @task's name, cpuset name, and cached copy of its
  * mems_allowed to the kernel log.
@@ -2548,7 +2678,7 @@ void cpuset_print_task_mems_allowed(struct task_struct *tsk)
 	cgrp = task_cs(tsk)->css.cgroup;
 	nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN,
 			   tsk->mems_allowed);
-	printk(KERN_INFO "%s cpuset=", tsk->comm);
+	pr_info("%s cpuset=", tsk->comm);
 	pr_cont_cgroup_name(cgrp);
 	pr_cont(" mems_allowed=%s\n", cpuset_nodelist);
 
@@ -2640,10 +2770,10 @@ out:
 /* Display task mems_allowed in /proc/<pid>/status file. */
 void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
 {
-	seq_printf(m, "Mems_allowed:\t");
+	seq_puts(m, "Mems_allowed:\t");
 	seq_nodemask(m, &task->mems_allowed);
-	seq_printf(m, "\n");
-	seq_printf(m, "Mems_allowed_list:\t");
+	seq_puts(m, "\n");
+	seq_puts(m, "Mems_allowed_list:\t");
 	seq_nodemask_list(m, &task->mems_allowed);
-	seq_printf(m, "\n");
+	seq_puts(m, "\n");
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 689237a0c5e..1cf24b3e42e 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -40,6 +40,7 @@
 #include <linux/mm_types.h>
 #include <linux/cgroup.h>
 #include <linux/module.h>
+#include <linux/mman.h>
 
 #include "internal.h"
 
@@ -608,7 +609,8 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	if (!f.file)
 		return -EBADF;
 
-	css = css_tryget_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys);
+	css = css_tryget_online_from_dir(f.file->f_dentry,
+					 &perf_event_cgrp_subsys);
 	if (IS_ERR(css)) {
 		ret = PTR_ERR(css);
 		goto out;
@@ -2318,7 +2320,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	next_parent = rcu_dereference(next_ctx->parent_ctx);
 
 	/* If neither context have a parent context; they cannot be clones. */
-	if (!parent && !next_parent)
+	if (!parent || !next_parent)
 		goto unlock;
 
 	if (next_parent == ctx || next_ctx == parent || next_parent == parent) {
@@ -2973,6 +2975,22 @@ out:
 	local_irq_restore(flags);
 }
 
+void perf_event_exec(void)
+{
+	struct perf_event_context *ctx;
+	int ctxn;
+
+	rcu_read_lock();
+	for_each_task_context_nr(ctxn) {
+		ctx = current->perf_event_ctxp[ctxn];
+		if (!ctx)
+			continue;
+
+		perf_event_enable_on_exec(ctx);
+	}
+	rcu_read_unlock();
+}
+
 /*
  * Cross CPU call to read the hardware event
  */
@@ -5074,21 +5092,9 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 		       NULL);
 }
 
-void perf_event_comm(struct task_struct *task)
+void perf_event_comm(struct task_struct *task, bool exec)
 {
 	struct perf_comm_event comm_event;
-	struct perf_event_context *ctx;
-	int ctxn;
-
-	rcu_read_lock();
-	for_each_task_context_nr(ctxn) {
-		ctx = task->perf_event_ctxp[ctxn];
-		if (!ctx)
-			continue;
-
-		perf_event_enable_on_exec(ctx);
-	}
-	rcu_read_unlock();
 
 	if (!atomic_read(&nr_comm_events))
 		return;
@@ -5100,7 +5106,7 @@ void perf_event_comm(struct task_struct *task)
 		.event_id  = {
 			.header = {
 				.type = PERF_RECORD_COMM,
-				.misc = 0,
+				.misc = exec ? PERF_RECORD_MISC_COMM_EXEC : 0,
 				/* .size */
 			},
 			/* .pid */
@@ -5123,6 +5129,7 @@ struct perf_mmap_event {
 	int			maj, min;
 	u64			ino;
 	u64			ino_generation;
+	u32			prot, flags;
 
 	struct {
 		struct perf_event_header	header;
@@ -5164,6 +5171,8 @@ static void perf_event_mmap_output(struct perf_event *event,
 		mmap_event->event_id.header.size += sizeof(mmap_event->min);
 		mmap_event->event_id.header.size += sizeof(mmap_event->ino);
 		mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation);
+		mmap_event->event_id.header.size += sizeof(mmap_event->prot);
+		mmap_event->event_id.header.size += sizeof(mmap_event->flags);
 	}
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
@@ -5182,6 +5191,8 @@ static void perf_event_mmap_output(struct perf_event *event,
 		perf_output_put(&handle, mmap_event->min);
 		perf_output_put(&handle, mmap_event->ino);
 		perf_output_put(&handle, mmap_event->ino_generation);
+		perf_output_put(&handle, mmap_event->prot);
+		perf_output_put(&handle, mmap_event->flags);
 	}
 
 	__output_copy(&handle, mmap_event->file_name,
@@ -5200,6 +5211,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	struct file *file = vma->vm_file;
 	int maj = 0, min = 0;
 	u64 ino = 0, gen = 0;
+	u32 prot = 0, flags = 0;
 	unsigned int size;
 	char tmp[16];
 	char *buf = NULL;
@@ -5230,8 +5242,36 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		gen = inode->i_generation;
 		maj = MAJOR(dev);
 		min = MINOR(dev);
+
+		if (vma->vm_flags & VM_READ)
+			prot |= PROT_READ;
+		if (vma->vm_flags & VM_WRITE)
+			prot |= PROT_WRITE;
+		if (vma->vm_flags & VM_EXEC)
+			prot |= PROT_EXEC;
+
+		if (vma->vm_flags & VM_MAYSHARE)
+			flags = MAP_SHARED;
+		else
+			flags = MAP_PRIVATE;
+
+		if (vma->vm_flags & VM_DENYWRITE)
+			flags |= MAP_DENYWRITE;
+		if (vma->vm_flags & VM_MAYEXEC)
+			flags |= MAP_EXECUTABLE;
+		if (vma->vm_flags & VM_LOCKED)
+			flags |= MAP_LOCKED;
+		if (vma->vm_flags & VM_HUGETLB)
+			flags |= MAP_HUGETLB;
+
 		goto got_name;
 	} else {
+		if (vma->vm_ops && vma->vm_ops->name) {
+			name = (char *) vma->vm_ops->name(vma);
+			if (name)
+				goto cpy_name;
+		}
+
 		name = (char *)arch_vma_name(vma);
 		if (name)
 			goto cpy_name;
@@ -5270,6 +5310,8 @@ got_name:
 	mmap_event->min = min;
 	mmap_event->ino = ino;
 	mmap_event->ino_generation = gen;
+	mmap_event->prot = prot;
+	mmap_event->flags = flags;
 
 	if (!(vma->vm_flags & VM_EXEC))
 		mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA;
@@ -5310,6 +5352,8 @@ void perf_event_mmap(struct vm_area_struct *vma)
 		/* .min (attr_mmap2 only) */
 		/* .ino (attr_mmap2 only) */
 		/* .ino_generation (attr_mmap2 only) */
+		/* .prot (attr_mmap2 only) */
+		/* .flags (attr_mmap2 only) */
 	};
 
 	perf_event_mmap_event(&mmap_event);
@@ -6892,10 +6936,6 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (ret)
 		return -EFAULT;
 
-	/* disabled for now */
-	if (attr->mmap2)
-		return -EINVAL;
-
 	if (attr->__reserved_1)
 		return -EINVAL;
 
@@ -7121,6 +7161,13 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
+	if (is_sampling_event(event)) {
+		if (event->pmu->capabilities & PERF_PMU_CAP_NO_INTERRUPT) {
+			err = -ENOTSUPP;
+			goto err_alloc;
+		}
+	}
+
 	account_event(event);
 
 	/*
@@ -7417,7 +7464,19 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	perf_remove_from_context(child_event, true);
+	/*
+	 * Do not destroy the 'original' grouping; because of the context
+	 * switch optimization the original events could've ended up in a
+	 * random child task.
+	 *
+	 * If we were to destroy the original group, all group related
+	 * operations would cease to function properly after this random
+	 * child dies.
+	 *
+	 * Do destroy all inherited groups, we don't care about those
+	 * and being thorough is better.
+	 */
+	perf_remove_from_context(child_event, !!child_event->parent);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7432,8 +7491,8 @@ __perf_event_exit_task(struct perf_event *child_event,
 
 static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 {
-	struct perf_event *child_event;
-	struct perf_event_context *child_ctx;
+	struct perf_event *child_event, *next;
+	struct perf_event_context *child_ctx, *parent_ctx;
 	unsigned long flags;
 
 	if (likely(!child->perf_event_ctxp[ctxn])) {
@@ -7458,6 +7517,15 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	raw_spin_lock(&child_ctx->lock);
 	task_ctx_sched_out(child_ctx);
 	child->perf_event_ctxp[ctxn] = NULL;
+
+	/*
+	 * In order to avoid freeing: child_ctx->parent_ctx->task
+	 * under perf_event_context::lock, grab another reference.
+	 */
+	parent_ctx = child_ctx->parent_ctx;
+	if (parent_ctx)
+		get_ctx(parent_ctx);
+
 	/*
 	 * If this context is a clone; unclone it so it can't get
 	 * swapped to another process while we're removing all
@@ -7468,6 +7536,13 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	raw_spin_unlock_irqrestore(&child_ctx->lock, flags);
 
 	/*
+	 * Now that we no longer hold perf_event_context::lock, drop
+	 * our extra child_ctx->parent_ctx reference.
+	 */
+	if (parent_ctx)
+		put_ctx(parent_ctx);
+
+	/*
 	 * Report the task dead after unscheduling the events so that we
 	 * won't get any samples after PERF_RECORD_EXIT. We can however still
 	 * get a few PERF_RECORD_READ events.
@@ -7486,7 +7561,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 */
 	mutex_lock(&child_ctx->mutex);
 
-	list_for_each_entry_rcu(child_event, &child_ctx->event_list, event_entry)
+	list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry)
 		__perf_event_exit_task(child_event, child_ctx, child);
 
 	mutex_unlock(&child_ctx->mutex);
@@ -7735,7 +7810,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 /*
  * Initialize the perf_event context in task_struct
  */
-int perf_event_init_context(struct task_struct *child, int ctxn)
+static int perf_event_init_context(struct task_struct *child, int ctxn)
 {
 	struct perf_event_context *child_ctx, *parent_ctx;
 	struct perf_event_context *cloned_ctx;
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index adcd76a9683..6f3254e8c13 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -36,6 +36,7 @@
 #include "../../mm/internal.h"	/* munlock_vma_page */
 #include <linux/percpu-rwsem.h>
 #include <linux/task_work.h>
+#include <linux/shmem_fs.h>
 
 #include <linux/uprobes.h>
 
@@ -127,7 +128,7 @@ struct xol_area {
  */
 static bool valid_vma(struct vm_area_struct *vma, bool is_register)
 {
-	vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_SHARED;
+	vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE;
 
 	if (is_register)
 		flags |= VM_WRITE;
@@ -279,18 +280,13 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t
  * supported by that architecture then we need to modify is_trap_at_addr and
  * uprobe_write_opcode accordingly. This would never be a problem for archs
  * that have fixed length instructions.
- */
-
-/*
+ *
  * uprobe_write_opcode - write the opcode at a given virtual address.
  * @mm: the probed process address space.
  * @vaddr: the virtual address to store the opcode.
  * @opcode: opcode to be written at @vaddr.
  *
- * Called with mm->mmap_sem held (for read and with a reference to
- * mm).
- *
- * For mm @mm, write the opcode at @vaddr.
+ * Called with mm->mmap_sem held for write.
  * Return 0 (success) or a negative errno.
  */
 int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr,
@@ -310,21 +306,25 @@ retry:
 	if (ret <= 0)
 		goto put_old;
 
+	ret = anon_vma_prepare(vma);
+	if (ret)
+		goto put_old;
+
 	ret = -ENOMEM;
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
 	if (!new_page)
 		goto put_old;
 
-	__SetPageUptodate(new_page);
+	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))
+		goto put_new;
 
+	__SetPageUptodate(new_page);
 	copy_highpage(new_page, old_page);
 	copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE);
 
-	ret = anon_vma_prepare(vma);
-	if (ret)
-		goto put_new;
-
 	ret = __replace_page(vma, vaddr, old_page, new_page);
+	if (ret)
+		mem_cgroup_uncharge_page(new_page);
 
 put_new:
 	page_cache_release(new_page);
@@ -537,14 +537,15 @@ static int __copy_insn(struct address_space *mapping, struct file *filp,
 			void *insn, int nbytes, loff_t offset)
 {
 	struct page *page;
-
-	if (!mapping->a_ops->readpage)
-		return -EIO;
 	/*
-	 * Ensure that the page that has the original instruction is
-	 * populated and in page-cache.
+	 * Ensure that the page that has the original instruction is populated
+	 * and in page-cache. If ->readpage == NULL it must be shmem_mapping(),
+	 * see uprobe_register().
 	 */
-	page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp);
+	if (mapping->a_ops->readpage)
+		page = read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT, filp);
+	else
+		page = shmem_read_mapping_page(mapping, offset >> PAGE_CACHE_SHIFT);
 	if (IS_ERR(page))
 		return PTR_ERR(page);
 
@@ -845,7 +846,7 @@ static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *u
 {
 	int err;
 
-	if (!consumer_del(uprobe, uc))	/* WARN? */
+	if (WARN_ON(!consumer_del(uprobe, uc)))
 		return;
 
 	err = register_for_each_vma(uprobe, NULL);
@@ -880,6 +881,9 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 	if (!uc->handler && !uc->ret_handler)
 		return -EINVAL;
 
+	/* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */
+	if (!inode->i_mapping->a_ops->readpage && !shmem_mapping(inode->i_mapping))
+		return -EIO;
 	/* Racy, just to catch the obvious mistakes */
 	if (offset > i_size_read(inode))
 		return -EINVAL;
@@ -923,7 +927,7 @@ int uprobe_apply(struct inode *inode, loff_t offset,
 	int ret = -ENOENT;
 
 	uprobe = find_uprobe(inode, offset);
-	if (!uprobe)
+	if (WARN_ON(!uprobe))
 		return ret;
 
 	down_write(&uprobe->register_rwsem);
@@ -948,7 +952,7 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume
 	struct uprobe *uprobe;
 
 	uprobe = find_uprobe(inode, offset);
-	if (!uprobe)
+	if (WARN_ON(!uprobe))
 		return;
 
 	down_write(&uprobe->register_rwsem);
@@ -1361,6 +1365,16 @@ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs)
 	return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE;
 }
 
+unsigned long uprobe_get_trap_addr(struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	if (unlikely(utask && utask->active_uprobe))
+		return utask->vaddr;
+
+	return instruction_pointer(regs);
+}
+
 /*
  * Called with no locks held.
  * Called in context of a exiting or a exec-ing thread.
diff --git a/kernel/fork.c b/kernel/fork.c
index d2799d1fc95..962885edbe5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1095,7 +1095,6 @@ static void rt_mutex_init_task(struct task_struct *p)
 	p->pi_waiters = RB_ROOT;
 	p->pi_waiters_leftmost = NULL;
 	p->pi_blocked_on = NULL;
-	p->pi_top_task = NULL;
 #endif
 }
 
@@ -1487,7 +1486,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	total_forks++;
 	spin_unlock(&current->sighand->siglock);
+	syscall_tracepoint_update(p);
 	write_unlock_irq(&tasklist_lock);
+
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
 	if (clone_flags & CLONE_THREAD)
diff --git a/kernel/futex.c b/kernel/futex.c
index b632b5f3f09..d3a9d946d0b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -792,94 +792,91 @@ void exit_pi_state_list(struct task_struct *curr)
  * [10] There is no transient state which leaves owner and user space
  *	TID out of sync.
  */
-static int
-lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
-		union futex_key *key, struct futex_pi_state **ps)
+
+/*
+ * Validate that the existing waiter has a pi_state and sanity check
+ * the pi_state against the user space value. If correct, attach to
+ * it.
+ */
+static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+			      struct futex_pi_state **ps)
 {
-	struct futex_pi_state *pi_state = NULL;
-	struct futex_q *this, *next;
-	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
 
-	plist_for_each_entry_safe(this, next, &hb->chain, list) {
-		if (match_futex(&this->key, key)) {
-			/*
-			 * Sanity check the waiter before increasing
-			 * the refcount and attaching to it.
-			 */
-			pi_state = this->pi_state;
-			/*
-			 * Userspace might have messed up non-PI and
-			 * PI futexes [3]
-			 */
-			if (unlikely(!pi_state))
-				return -EINVAL;
+	/*
+	 * Userspace might have messed up non-PI and PI futexes [3]
+	 */
+	if (unlikely(!pi_state))
+		return -EINVAL;
 
-			WARN_ON(!atomic_read(&pi_state->refcount));
+	WARN_ON(!atomic_read(&pi_state->refcount));
 
+	/*
+	 * Handle the owner died case:
+	 */
+	if (uval & FUTEX_OWNER_DIED) {
+		/*
+		 * exit_pi_state_list sets owner to NULL and wakes the
+		 * topmost waiter. The task which acquires the
+		 * pi_state->rt_mutex will fixup owner.
+		 */
+		if (!pi_state->owner) {
 			/*
-			 * Handle the owner died case:
+			 * No pi state owner, but the user space TID
+			 * is not 0. Inconsistent state. [5]
 			 */
-			if (uval & FUTEX_OWNER_DIED) {
-				/*
-				 * exit_pi_state_list sets owner to NULL and
-				 * wakes the topmost waiter. The task which
-				 * acquires the pi_state->rt_mutex will fixup
-				 * owner.
-				 */
-				if (!pi_state->owner) {
-					/*
-					 * No pi state owner, but the user
-					 * space TID is not 0. Inconsistent
-					 * state. [5]
-					 */
-					if (pid)
-						return -EINVAL;
-					/*
-					 * Take a ref on the state and
-					 * return. [4]
-					 */
-					goto out_state;
-				}
-
-				/*
-				 * If TID is 0, then either the dying owner
-				 * has not yet executed exit_pi_state_list()
-				 * or some waiter acquired the rtmutex in the
-				 * pi state, but did not yet fixup the TID in
-				 * user space.
-				 *
-				 * Take a ref on the state and return. [6]
-				 */
-				if (!pid)
-					goto out_state;
-			} else {
-				/*
-				 * If the owner died bit is not set,
-				 * then the pi_state must have an
-				 * owner. [7]
-				 */
-				if (!pi_state->owner)
-					return -EINVAL;
-			}
-
+			if (pid)
+				return -EINVAL;
 			/*
-			 * Bail out if user space manipulated the
-			 * futex value. If pi state exists then the
-			 * owner TID must be the same as the user
-			 * space TID. [9/10]
+			 * Take a ref on the state and return success. [4]
 			 */
-			if (pid != task_pid_vnr(pi_state->owner))
-				return -EINVAL;
-
-		out_state:
-			atomic_inc(&pi_state->refcount);
-			*ps = pi_state;
-			return 0;
+			goto out_state;
 		}
+
+		/*
+		 * If TID is 0, then either the dying owner has not
+		 * yet executed exit_pi_state_list() or some waiter
+		 * acquired the rtmutex in the pi state, but did not
+		 * yet fixup the TID in user space.
+		 *
+		 * Take a ref on the state and return success. [6]
+		 */
+		if (!pid)
+			goto out_state;
+	} else {
+		/*
+		 * If the owner died bit is not set, then the pi_state
+		 * must have an owner. [7]
+		 */
+		if (!pi_state->owner)
+			return -EINVAL;
 	}
 
 	/*
+	 * Bail out if user space manipulated the futex value. If pi
+	 * state exists then the owner TID must be the same as the
+	 * user space TID. [9/10]
+	 */
+	if (pid != task_pid_vnr(pi_state->owner))
+		return -EINVAL;
+out_state:
+	atomic_inc(&pi_state->refcount);
+	*ps = pi_state;
+	return 0;
+}
+
+/*
+ * Lookup the task for the TID provided from user space and attach to
+ * it after doing proper sanity checks.
+ */
+static int attach_to_pi_owner(u32 uval, union futex_key *key,
+			      struct futex_pi_state **ps)
+{
+	pid_t pid = uval & FUTEX_TID_MASK;
+	struct futex_pi_state *pi_state;
+	struct task_struct *p;
+
+	/*
 	 * We are the first waiter - try to look up the real owner and attach
 	 * the new pi_state to it, but bail out when TID = 0 [1]
 	 */
@@ -920,7 +917,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	pi_state = alloc_pi_state();
 
 	/*
-	 * Initialize the pi_mutex in locked state and make 'p'
+	 * Initialize the pi_mutex in locked state and make @p
 	 * the owner of it:
 	 */
 	rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);
@@ -940,6 +937,36 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	return 0;
 }
 
+static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+			   union futex_key *key, struct futex_pi_state **ps)
+{
+	struct futex_q *match = futex_top_waiter(hb, key);
+
+	/*
+	 * If there is a waiter on that futex, validate it and
+	 * attach to the pi_state when the validation succeeds.
+	 */
+	if (match)
+		return attach_to_pi_state(uval, match->pi_state, ps);
+
+	/*
+	 * We are the first waiter - try to look up the owner based on
+	 * @uval and attach to it.
+	 */
+	return attach_to_pi_owner(uval, key, ps);
+}
+
+static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
+{
+	u32 uninitialized_var(curval);
+
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
+		return -EFAULT;
+
+	/*If user space value changed, let the caller retry */
+	return curval != uval ? -EAGAIN : 0;
+}
+
 /**
  * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex
  * @uaddr:		the pi futex user address
@@ -963,113 +990,69 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 				struct futex_pi_state **ps,
 				struct task_struct *task, int set_waiters)
 {
-	int lock_taken, ret, force_take = 0;
-	u32 uval, newval, curval, vpid = task_pid_vnr(task);
-
-retry:
-	ret = lock_taken = 0;
+	u32 uval, newval, vpid = task_pid_vnr(task);
+	struct futex_q *match;
+	int ret;
 
 	/*
-	 * To avoid races, we attempt to take the lock here again
-	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
-	 * the locks. It will most likely not succeed.
+	 * Read the user space value first so we can validate a few
+	 * things before proceeding further.
 	 */
-	newval = vpid;
-	if (set_waiters)
-		newval |= FUTEX_WAITERS;
-
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
+	if (get_futex_value_locked(&uval, uaddr))
 		return -EFAULT;
 
 	/*
 	 * Detect deadlocks.
 	 */
-	if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
+	if ((unlikely((uval & FUTEX_TID_MASK) == vpid)))
 		return -EDEADLK;
 
 	/*
-	 * Surprise - we got the lock, but we do not trust user space at all.
-	 */
-	if (unlikely(!curval)) {
-		/*
-		 * We verify whether there is kernel state for this
-		 * futex. If not, we can safely assume, that the 0 ->
-		 * TID transition is correct. If state exists, we do
-		 * not bother to fixup the user space state as it was
-		 * corrupted already.
-		 */
-		return futex_top_waiter(hb, key) ? -EINVAL : 1;
-	}
-
-	uval = curval;
-
-	/*
-	 * Set the FUTEX_WAITERS flag, so the owner will know it has someone
-	 * to wake at the next unlock.
+	 * Lookup existing state first. If it exists, try to attach to
+	 * its pi_state.
 	 */
-	newval = curval | FUTEX_WAITERS;
+	match = futex_top_waiter(hb, key);
+	if (match)
+		return attach_to_pi_state(uval, match->pi_state, ps);
 
 	/*
-	 * Should we force take the futex? See below.
+	 * No waiter and user TID is 0. We are here because the
+	 * waiters or the owner died bit is set or called from
+	 * requeue_cmp_pi or for whatever reason something took the
+	 * syscall.
 	 */
-	if (unlikely(force_take)) {
+	if (!(uval & FUTEX_TID_MASK)) {
 		/*
-		 * Keep the OWNER_DIED and the WAITERS bit and set the
-		 * new TID value.
+		 * We take over the futex. No other waiters and the user space
+		 * TID is 0. We preserve the owner died bit.
 		 */
-		newval = (curval & ~FUTEX_TID_MASK) | vpid;
-		force_take = 0;
-		lock_taken = 1;
-	}
+		newval = uval & FUTEX_OWNER_DIED;
+		newval |= vpid;
 
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
-		return -EFAULT;
-	if (unlikely(curval != uval))
-		goto retry;
+		/* The futex requeue_pi code can enforce the waiters bit */
+		if (set_waiters)
+			newval |= FUTEX_WAITERS;
+
+		ret = lock_pi_update_atomic(uaddr, uval, newval);
+		/* If the take over worked, return 1 */
+		return ret < 0 ? ret : 1;
+	}
 
 	/*
-	 * We took the lock due to forced take over.
+	 * First waiter. Set the waiters bit before attaching ourself to
+	 * the owner. If owner tries to unlock, it will be forced into
+	 * the kernel and blocked on hb->lock.
 	 */
-	if (unlikely(lock_taken))
-		return 1;
-
+	newval = uval | FUTEX_WAITERS;
+	ret = lock_pi_update_atomic(uaddr, uval, newval);
+	if (ret)
+		return ret;
 	/*
-	 * We dont have the lock. Look up the PI state (or create it if
-	 * we are the first waiter):
+	 * If the update of the user space value succeeded, we try to
+	 * attach to the owner. If that fails, no harm done, we only
+	 * set the FUTEX_WAITERS bit in the user space variable.
 	 */
-	ret = lookup_pi_state(uval, hb, key, ps);
-
-	if (unlikely(ret)) {
-		switch (ret) {
-		case -ESRCH:
-			/*
-			 * We failed to find an owner for this
-			 * futex. So we have no pi_state to block
-			 * on. This can happen in two cases:
-			 *
-			 * 1) The owner died
-			 * 2) A stale FUTEX_WAITERS bit
-			 *
-			 * Re-read the futex value.
-			 */
-			if (get_futex_value_locked(&curval, uaddr))
-				return -EFAULT;
-
-			/*
-			 * If the owner died or we have a stale
-			 * WAITERS bit the owner TID in the user space
-			 * futex is 0.
-			 */
-			if (!(curval & FUTEX_TID_MASK)) {
-				force_take = 1;
-				goto retry;
-			}
-		default:
-			break;
-		}
-	}
-
-	return ret;
+	return attach_to_pi_owner(uval, key, ps);
 }
 
 /**
@@ -1186,22 +1169,6 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	return 0;
 }
 
-static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
-{
-	u32 uninitialized_var(oldval);
-
-	/*
-	 * There is no waiter, so we unlock the futex. The owner died
-	 * bit has not to be preserved here. We are the owner:
-	 */
-	if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
-		return -EFAULT;
-	if (oldval != uval)
-		return -EAGAIN;
-
-	return 0;
-}
-
 /*
  * Express the locking dependencies for lockdep:
  */
@@ -1659,7 +1626,12 @@ retry_private:
 				goto retry;
 			goto out;
 		case -EAGAIN:
-			/* The owner was exiting, try again. */
+			/*
+			 * Two reasons for this:
+			 * - Owner is exiting and we just wait for the
+			 *   exit to complete.
+			 * - The user space value changed.
+			 */
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
@@ -1718,7 +1690,7 @@ retry_private:
 			this->pi_state = pi_state;
 			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
 							this->rt_waiter,
-							this->task, 1);
+							this->task);
 			if (ret == 1) {
 				/* We got the lock. */
 				requeue_pi_wake_futex(this, &key2, hb2);
@@ -2316,8 +2288,10 @@ retry_private:
 			goto uaddr_faulted;
 		case -EAGAIN:
 			/*
-			 * Task is exiting and we just wait for the
-			 * exit to complete.
+			 * Two reasons for this:
+			 * - Task is exiting and we just wait for the
+			 *   exit to complete.
+			 * - The user space value changed.
 			 */
 			queue_unlock(hb);
 			put_futex_key(&q.key);
@@ -2337,9 +2311,9 @@ retry_private:
 	/*
 	 * Block on the PI mutex:
 	 */
-	if (!trylock)
-		ret = rt_mutex_timed_lock(&q.pi_state->pi_mutex, to, 1);
-	else {
+	if (!trylock) {
+		ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
+	} else {
 		ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
 		/* Fixup the trylock return value: */
 		ret = ret ? 0 : -EWOULDBLOCK;
@@ -2401,10 +2375,10 @@ uaddr_faulted:
  */
 static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
-	struct futex_hash_bucket *hb;
-	struct futex_q *this, *next;
+	u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
 	union futex_key key = FUTEX_KEY_INIT;
-	u32 uval, vpid = task_pid_vnr(current);
+	struct futex_hash_bucket *hb;
+	struct futex_q *match;
 	int ret;
 
 retry:
@@ -2417,57 +2391,47 @@ retry:
 		return -EPERM;
 
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE);
-	if (unlikely(ret != 0))
-		goto out;
+	if (ret)
+		return ret;
 
 	hb = hash_futex(&key);
 	spin_lock(&hb->lock);
 
 	/*
-	 * To avoid races, try to do the TID -> 0 atomic transition
-	 * again. If it succeeds then we can return without waking
-	 * anyone else up. We only try this if neither the waiters nor
-	 * the owner died bit are set.
-	 */
-	if (!(uval & ~FUTEX_TID_MASK) &&
-	    cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
-		goto pi_faulted;
-	/*
-	 * Rare case: we managed to release the lock atomically,
-	 * no need to wake anyone else up:
-	 */
-	if (unlikely(uval == vpid))
-		goto out_unlock;
-
-	/*
-	 * Ok, other tasks may need to be woken up - check waiters
-	 * and do the wakeup if necessary:
+	 * Check waiters first. We do not trust user space values at
+	 * all and we at least want to know if user space fiddled
+	 * with the futex value instead of blindly unlocking.
 	 */
-	plist_for_each_entry_safe(this, next, &hb->chain, list) {
-		if (!match_futex (&this->key, &key))
-			continue;
-		ret = wake_futex_pi(uaddr, uval, this);
+	match = futex_top_waiter(hb, &key);
+	if (match) {
+		ret = wake_futex_pi(uaddr, uval, match);
 		/*
-		 * The atomic access to the futex value
-		 * generated a pagefault, so retry the
-		 * user-access and the wakeup:
+		 * The atomic access to the futex value generated a
+		 * pagefault, so retry the user-access and the wakeup:
 		 */
 		if (ret == -EFAULT)
 			goto pi_faulted;
 		goto out_unlock;
 	}
+
 	/*
-	 * No waiters - kernel unlocks the futex:
+	 * We have no kernel internal state, i.e. no waiters in the
+	 * kernel. Waiters which are about to queue themselves are stuck
+	 * on hb->lock. So we can safely ignore them. We do neither
+	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
+	 * owner.
 	 */
-	ret = unlock_futex_pi(uaddr, uval);
-	if (ret == -EFAULT)
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))
 		goto pi_faulted;
 
+	/*
+	 * If uval has changed, let user space handle it.
+	 */
+	ret = (curval == uval) ? 0 : -EAGAIN;
+
 out_unlock:
 	spin_unlock(&hb->lock);
 	put_futex_key(&key);
-
-out:
 	return ret;
 
 pi_faulted:
@@ -2669,7 +2633,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		 */
 		WARN_ON(!q.pi_state);
 		pi_mutex = &q.pi_state->pi_mutex;
-		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
+		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
 		debug_rt_mutex_free_waiter(&rt_waiter);
 
 		spin_lock(q.lock_ptr);
diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c
index f45b75b713c..b358a802fd1 100644
--- a/kernel/gcov/base.c
+++ b/kernel/gcov/base.c
@@ -85,6 +85,12 @@ void __gcov_merge_ior(gcov_type *counters, unsigned int n_counters)
 }
 EXPORT_SYMBOL(__gcov_merge_ior);
 
+void __gcov_merge_time_profile(gcov_type *counters, unsigned int n_counters)
+{
+	/* Unused. */
+}
+EXPORT_SYMBOL(__gcov_merge_time_profile);
+
 /**
  * gcov_enable_events - enable event reporting through gcov_event()
  *
diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c
index 2c6e4631c81..826ba9fb5e3 100644
--- a/kernel/gcov/gcc_4_7.c
+++ b/kernel/gcov/gcc_4_7.c
@@ -18,7 +18,12 @@
 #include <linux/vmalloc.h>
 #include "gcov.h"
 
+#if __GNUC__ == 4 && __GNUC_MINOR__ >= 9
+#define GCOV_COUNTERS			9
+#else
 #define GCOV_COUNTERS			8
+#endif
+
 #define GCOV_TAG_FUNCTION_LENGTH	3
 
 static struct gcov_info *gcov_info_head;
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 7339e42a85a..1487a123db5 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -455,9 +455,9 @@ EXPORT_SYMBOL_GPL(irq_alloc_hwirqs);
  */
 void irq_free_hwirqs(unsigned int from, int cnt)
 {
-	int i;
+	int i, j;
 
-	for (i = from; cnt > 0; i++, cnt--) {
+	for (i = from, j = cnt; j > 0; i++, j--) {
 		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
 		arch_teardown_hwirq(i);
 	}
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index a82170e2fa7..e6bcbe75666 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -16,11 +16,12 @@
 #include <linux/tick.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
+#include <linux/smp.h>
 #include <asm/processor.h>
 
 
-static DEFINE_PER_CPU(struct llist_head, irq_work_list);
-static DEFINE_PER_CPU(int, irq_work_raised);
+static DEFINE_PER_CPU(struct llist_head, raised_list);
+static DEFINE_PER_CPU(struct llist_head, lazy_list);
 
 /*
  * Claim the entry so that no one else will poke at it.
@@ -55,12 +56,34 @@ void __weak arch_irq_work_raise(void)
 	 */
 }
 
+#ifdef CONFIG_SMP
 /*
- * Enqueue the irq_work @entry unless it's already pending
+ * Enqueue the irq_work @work on @cpu unless it's already pending
  * somewhere.
  *
  * Can be re-enqueued while the callback is still in progress.
  */
+bool irq_work_queue_on(struct irq_work *work, int cpu)
+{
+	/* All work should have been flushed before going offline */
+	WARN_ON_ONCE(cpu_is_offline(cpu));
+
+	/* Arch remote IPI send/receive backend aren't NMI safe */
+	WARN_ON_ONCE(in_nmi());
+
+	/* Only queue if not already pending */
+	if (!irq_work_claim(work))
+		return false;
+
+	if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
+		arch_send_call_function_single_ipi(cpu);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(irq_work_queue_on);
+#endif
+
+/* Enqueue the irq work @work on the current CPU */
 bool irq_work_queue(struct irq_work *work)
 {
 	/* Only queue if not already pending */
@@ -70,15 +93,13 @@ bool irq_work_queue(struct irq_work *work)
 	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
 
-	llist_add(&work->llnode, &__get_cpu_var(irq_work_list));
-
-	/*
-	 * If the work is not "lazy" or the tick is stopped, raise the irq
-	 * work interrupt (if supported by the arch), otherwise, just wait
-	 * for the next tick.
-	 */
-	if (!(work->flags & IRQ_WORK_LAZY) || tick_nohz_tick_stopped()) {
-		if (!this_cpu_cmpxchg(irq_work_raised, 0, 1))
+	/* If the work is "lazy", handle it from next tick if any */
+	if (work->flags & IRQ_WORK_LAZY) {
+		if (llist_add(&work->llnode, &__get_cpu_var(lazy_list)) &&
+		    tick_nohz_tick_stopped())
+			arch_irq_work_raise();
+	} else {
+		if (llist_add(&work->llnode, &__get_cpu_var(raised_list)))
 			arch_irq_work_raise();
 	}
 
@@ -90,10 +111,11 @@ EXPORT_SYMBOL_GPL(irq_work_queue);
 
 bool irq_work_needs_cpu(void)
 {
-	struct llist_head *this_list;
+	struct llist_head *raised, *lazy;
 
-	this_list = &__get_cpu_var(irq_work_list);
-	if (llist_empty(this_list))
+	raised = &__get_cpu_var(raised_list);
+	lazy = &__get_cpu_var(lazy_list);
+	if (llist_empty(raised) && llist_empty(lazy))
 		return false;
 
 	/* All work should have been flushed before going offline */
@@ -102,28 +124,18 @@ bool irq_work_needs_cpu(void)
 	return true;
 }
 
-static void __irq_work_run(void)
+static void irq_work_run_list(struct llist_head *list)
 {
 	unsigned long flags;
 	struct irq_work *work;
-	struct llist_head *this_list;
 	struct llist_node *llnode;
 
+	BUG_ON(!irqs_disabled());
 
-	/*
-	 * Reset the "raised" state right before we check the list because
-	 * an NMI may enqueue after we find the list empty from the runner.
-	 */
-	__this_cpu_write(irq_work_raised, 0);
-	barrier();
-
-	this_list = &__get_cpu_var(irq_work_list);
-	if (llist_empty(this_list))
+	if (llist_empty(list))
 		return;
 
-	BUG_ON(!irqs_disabled());
-
-	llnode = llist_del_all(this_list);
+	llnode = llist_del_all(list);
 	while (llnode != NULL) {
 		work = llist_entry(llnode, struct irq_work, llnode);
 
@@ -149,13 +161,13 @@ static void __irq_work_run(void)
 }
 
 /*
- * Run the irq_work entries on this cpu. Requires to be ran from hardirq
- * context with local IRQs disabled.
+ * hotplug calls this through:
+ *  hotplug_cfd() -> flush_smp_call_function_queue()
  */
 void irq_work_run(void)
 {
-	BUG_ON(!in_irq());
-	__irq_work_run();
+	irq_work_run_list(&__get_cpu_var(raised_list));
+	irq_work_run_list(&__get_cpu_var(lazy_list));
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
@@ -171,35 +183,3 @@ void irq_work_sync(struct irq_work *work)
 		cpu_relax();
 }
 EXPORT_SYMBOL_GPL(irq_work_sync);
-
-#ifdef CONFIG_HOTPLUG_CPU
-static int irq_work_cpu_notify(struct notifier_block *self,
-			       unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_DYING:
-		/* Called from stop_machine */
-		if (WARN_ON_ONCE(cpu != smp_processor_id()))
-			break;
-		__irq_work_run();
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block cpu_notify;
-
-static __init int irq_work_init_cpu_notifier(void)
-{
-	cpu_notify.notifier_call = irq_work_cpu_notify;
-	cpu_notify.priority = 0;
-	register_cpu_notifier(&cpu_notify);
-	return 0;
-}
-device_initcall(irq_work_init_cpu_notifier);
-
-#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 6748688813d..4b8f0c92588 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -33,6 +33,7 @@
 #include <linux/swap.h>
 #include <linux/syscore_ops.h>
 #include <linux/compiler.h>
+#include <linux/hugetlb.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -1617,7 +1618,11 @@ static int __init crash_save_vmcoreinfo_init(void)
 #ifdef CONFIG_MEMORY_FAILURE
 	VMCOREINFO_NUMBER(PG_hwpoison);
 #endif
+	VMCOREINFO_NUMBER(PG_head_mask);
 	VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
+#ifdef CONFIG_HUGETLBFS
+	VMCOREINFO_SYMBOL(free_huge_page);
+#endif
 
 	arch_crash_save_vmcoreinfo();
 	update_vmcoreinfo_note();
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ceeadfcabb7..734e9a7d280 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -86,21 +86,8 @@ static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
 	return &(kretprobe_table_locks[hash].lock);
 }
 
-/*
- * Normally, functions that we'd want to prohibit kprobes in, are marked
- * __kprobes. But, there are cases where such functions already belong to
- * a different section (__sched for preempt_schedule)
- *
- * For such cases, we now have a blacklist
- */
-static struct kprobe_blackpoint kprobe_blacklist[] = {
-	{"preempt_schedule",},
-	{"native_get_debugreg",},
-	{"irq_entries_start",},
-	{"common_interrupt",},
-	{"mcount",},	/* mcount can be called from everywhere */
-	{NULL}    /* Terminator */
-};
+/* Blacklist -- list of struct kprobe_blacklist_entry */
+static LIST_HEAD(kprobe_blacklist);
 
 #ifdef __ARCH_WANT_KPROBES_INSN_SLOT
 /*
@@ -151,13 +138,13 @@ struct kprobe_insn_cache kprobe_insn_slots = {
 	.insn_size = MAX_INSN_SIZE,
 	.nr_garbage = 0,
 };
-static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c);
+static int collect_garbage_slots(struct kprobe_insn_cache *c);
 
 /**
  * __get_insn_slot() - Find a slot on an executable page for an instruction.
  * We allocate an executable page if there's no room on existing ones.
  */
-kprobe_opcode_t __kprobes *__get_insn_slot(struct kprobe_insn_cache *c)
+kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 {
 	struct kprobe_insn_page *kip;
 	kprobe_opcode_t *slot = NULL;
@@ -214,7 +201,7 @@ out:
 }
 
 /* Return 1 if all garbages are collected, otherwise 0. */
-static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
+static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 {
 	kip->slot_used[idx] = SLOT_CLEAN;
 	kip->nused--;
@@ -235,7 +222,7 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 	return 0;
 }
 
-static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c)
+static int collect_garbage_slots(struct kprobe_insn_cache *c)
 {
 	struct kprobe_insn_page *kip, *next;
 
@@ -257,8 +244,8 @@ static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c)
 	return 0;
 }
 
-void __kprobes __free_insn_slot(struct kprobe_insn_cache *c,
-				kprobe_opcode_t *slot, int dirty)
+void __free_insn_slot(struct kprobe_insn_cache *c,
+		      kprobe_opcode_t *slot, int dirty)
 {
 	struct kprobe_insn_page *kip;
 
@@ -314,7 +301,7 @@ static inline void reset_kprobe_instance(void)
  * 				OR
  * 	- with preemption disabled - from arch/xxx/kernel/kprobes.c
  */
-struct kprobe __kprobes *get_kprobe(void *addr)
+struct kprobe *get_kprobe(void *addr)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
@@ -327,8 +314,9 @@ struct kprobe __kprobes *get_kprobe(void *addr)
 
 	return NULL;
 }
+NOKPROBE_SYMBOL(get_kprobe);
 
-static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs);
+static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs);
 
 /* Return true if the kprobe is an aggregator */
 static inline int kprobe_aggrprobe(struct kprobe *p)
@@ -360,7 +348,7 @@ static bool kprobes_allow_optimization;
  * Call all pre_handler on the list, but ignores its return value.
  * This must be called from arch-dep optimized caller.
  */
-void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs)
+void opt_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe *kp;
 
@@ -372,9 +360,10 @@ void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs)
 		reset_kprobe_instance();
 	}
 }
+NOKPROBE_SYMBOL(opt_pre_handler);
 
 /* Free optimized instructions and optimized_kprobe */
-static __kprobes void free_aggr_kprobe(struct kprobe *p)
+static void free_aggr_kprobe(struct kprobe *p)
 {
 	struct optimized_kprobe *op;
 
@@ -412,7 +401,7 @@ static inline int kprobe_disarmed(struct kprobe *p)
 }
 
 /* Return true(!0) if the probe is queued on (un)optimizing lists */
-static int __kprobes kprobe_queued(struct kprobe *p)
+static int kprobe_queued(struct kprobe *p)
 {
 	struct optimized_kprobe *op;
 
@@ -428,7 +417,7 @@ static int __kprobes kprobe_queued(struct kprobe *p)
  * Return an optimized kprobe whose optimizing code replaces
  * instructions including addr (exclude breakpoint).
  */
-static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
+static struct kprobe *get_optimized_kprobe(unsigned long addr)
 {
 	int i;
 	struct kprobe *p = NULL;
@@ -460,7 +449,7 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
  * Optimize (replace a breakpoint with a jump) kprobes listed on
  * optimizing_list.
  */
-static __kprobes void do_optimize_kprobes(void)
+static void do_optimize_kprobes(void)
 {
 	/* Optimization never be done when disarmed */
 	if (kprobes_all_disarmed || !kprobes_allow_optimization ||
@@ -488,7 +477,7 @@ static __kprobes void do_optimize_kprobes(void)
  * Unoptimize (replace a jump with a breakpoint and remove the breakpoint
  * if need) kprobes listed on unoptimizing_list.
  */
-static __kprobes void do_unoptimize_kprobes(void)
+static void do_unoptimize_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
@@ -520,7 +509,7 @@ static __kprobes void do_unoptimize_kprobes(void)
 }
 
 /* Reclaim all kprobes on the free_list */
-static __kprobes void do_free_cleaned_kprobes(void)
+static void do_free_cleaned_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
@@ -532,13 +521,13 @@ static __kprobes void do_free_cleaned_kprobes(void)
 }
 
 /* Start optimizer after OPTIMIZE_DELAY passed */
-static __kprobes void kick_kprobe_optimizer(void)
+static void kick_kprobe_optimizer(void)
 {
 	schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
 }
 
 /* Kprobe jump optimizer */
-static __kprobes void kprobe_optimizer(struct work_struct *work)
+static void kprobe_optimizer(struct work_struct *work)
 {
 	mutex_lock(&kprobe_mutex);
 	/* Lock modules while optimizing kprobes */
@@ -574,7 +563,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
 }
 
 /* Wait for completing optimization and unoptimization */
-static __kprobes void wait_for_kprobe_optimizer(void)
+static void wait_for_kprobe_optimizer(void)
 {
 	mutex_lock(&kprobe_mutex);
 
@@ -593,7 +582,7 @@ static __kprobes void wait_for_kprobe_optimizer(void)
 }
 
 /* Optimize kprobe if p is ready to be optimized */
-static __kprobes void optimize_kprobe(struct kprobe *p)
+static void optimize_kprobe(struct kprobe *p)
 {
 	struct optimized_kprobe *op;
 
@@ -627,7 +616,7 @@ static __kprobes void optimize_kprobe(struct kprobe *p)
 }
 
 /* Short cut to direct unoptimizing */
-static __kprobes void force_unoptimize_kprobe(struct optimized_kprobe *op)
+static void force_unoptimize_kprobe(struct optimized_kprobe *op)
 {
 	get_online_cpus();
 	arch_unoptimize_kprobe(op);
@@ -637,7 +626,7 @@ static __kprobes void force_unoptimize_kprobe(struct optimized_kprobe *op)
 }
 
 /* Unoptimize a kprobe if p is optimized */
-static __kprobes void unoptimize_kprobe(struct kprobe *p, bool force)
+static void unoptimize_kprobe(struct kprobe *p, bool force)
 {
 	struct optimized_kprobe *op;
 
@@ -697,7 +686,7 @@ static void reuse_unused_kprobe(struct kprobe *ap)
 }
 
 /* Remove optimized instructions */
-static void __kprobes kill_optimized_kprobe(struct kprobe *p)
+static void kill_optimized_kprobe(struct kprobe *p)
 {
 	struct optimized_kprobe *op;
 
@@ -723,7 +712,7 @@ static void __kprobes kill_optimized_kprobe(struct kprobe *p)
 }
 
 /* Try to prepare optimized instructions */
-static __kprobes void prepare_optimized_kprobe(struct kprobe *p)
+static void prepare_optimized_kprobe(struct kprobe *p)
 {
 	struct optimized_kprobe *op;
 
@@ -732,7 +721,7 @@ static __kprobes void prepare_optimized_kprobe(struct kprobe *p)
 }
 
 /* Allocate new optimized_kprobe and try to prepare optimized instructions */
-static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
+static struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
 {
 	struct optimized_kprobe *op;
 
@@ -747,13 +736,13 @@ static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
 	return &op->kp;
 }
 
-static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p);
+static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p);
 
 /*
  * Prepare an optimized_kprobe and optimize it
  * NOTE: p must be a normal registered kprobe
  */
-static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
+static void try_to_optimize_kprobe(struct kprobe *p)
 {
 	struct kprobe *ap;
 	struct optimized_kprobe *op;
@@ -787,7 +776,7 @@ out:
 }
 
 #ifdef CONFIG_SYSCTL
-static void __kprobes optimize_all_kprobes(void)
+static void optimize_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
@@ -810,7 +799,7 @@ out:
 	mutex_unlock(&kprobe_mutex);
 }
 
-static void __kprobes unoptimize_all_kprobes(void)
+static void unoptimize_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
@@ -861,7 +850,7 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
 #endif /* CONFIG_SYSCTL */
 
 /* Put a breakpoint for a probe. Must be called with text_mutex locked */
-static void __kprobes __arm_kprobe(struct kprobe *p)
+static void __arm_kprobe(struct kprobe *p)
 {
 	struct kprobe *_p;
 
@@ -876,7 +865,7 @@ static void __kprobes __arm_kprobe(struct kprobe *p)
 }
 
 /* Remove the breakpoint of a probe. Must be called with text_mutex locked */
-static void __kprobes __disarm_kprobe(struct kprobe *p, bool reopt)
+static void __disarm_kprobe(struct kprobe *p, bool reopt)
 {
 	struct kprobe *_p;
 
@@ -911,13 +900,13 @@ static void reuse_unused_kprobe(struct kprobe *ap)
 	BUG_ON(kprobe_unused(ap));
 }
 
-static __kprobes void free_aggr_kprobe(struct kprobe *p)
+static void free_aggr_kprobe(struct kprobe *p)
 {
 	arch_remove_kprobe(p);
 	kfree(p);
 }
 
-static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
+static struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
 {
 	return kzalloc(sizeof(struct kprobe), GFP_KERNEL);
 }
@@ -931,7 +920,7 @@ static struct ftrace_ops kprobe_ftrace_ops __read_mostly = {
 static int kprobe_ftrace_enabled;
 
 /* Must ensure p->addr is really on ftrace */
-static int __kprobes prepare_kprobe(struct kprobe *p)
+static int prepare_kprobe(struct kprobe *p)
 {
 	if (!kprobe_ftrace(p))
 		return arch_prepare_kprobe(p);
@@ -940,7 +929,7 @@ static int __kprobes prepare_kprobe(struct kprobe *p)
 }
 
 /* Caller must lock kprobe_mutex */
-static void __kprobes arm_kprobe_ftrace(struct kprobe *p)
+static void arm_kprobe_ftrace(struct kprobe *p)
 {
 	int ret;
 
@@ -955,7 +944,7 @@ static void __kprobes arm_kprobe_ftrace(struct kprobe *p)
 }
 
 /* Caller must lock kprobe_mutex */
-static void __kprobes disarm_kprobe_ftrace(struct kprobe *p)
+static void disarm_kprobe_ftrace(struct kprobe *p)
 {
 	int ret;
 
@@ -975,7 +964,7 @@ static void __kprobes disarm_kprobe_ftrace(struct kprobe *p)
 #endif
 
 /* Arm a kprobe with text_mutex */
-static void __kprobes arm_kprobe(struct kprobe *kp)
+static void arm_kprobe(struct kprobe *kp)
 {
 	if (unlikely(kprobe_ftrace(kp))) {
 		arm_kprobe_ftrace(kp);
@@ -992,7 +981,7 @@ static void __kprobes arm_kprobe(struct kprobe *kp)
 }
 
 /* Disarm a kprobe with text_mutex */
-static void __kprobes disarm_kprobe(struct kprobe *kp, bool reopt)
+static void disarm_kprobe(struct kprobe *kp, bool reopt)
 {
 	if (unlikely(kprobe_ftrace(kp))) {
 		disarm_kprobe_ftrace(kp);
@@ -1008,7 +997,7 @@ static void __kprobes disarm_kprobe(struct kprobe *kp, bool reopt)
  * Aggregate handlers for multiple kprobes support - these handlers
  * take care of invoking the individual kprobe handlers on p->list
  */
-static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
+static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe *kp;
 
@@ -1022,9 +1011,10 @@ static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	}
 	return 0;
 }
+NOKPROBE_SYMBOL(aggr_pre_handler);
 
-static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
-					unsigned long flags)
+static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
+			      unsigned long flags)
 {
 	struct kprobe *kp;
 
@@ -1036,9 +1026,10 @@ static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
 		}
 	}
 }
+NOKPROBE_SYMBOL(aggr_post_handler);
 
-static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
-					int trapnr)
+static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
+			      int trapnr)
 {
 	struct kprobe *cur = __this_cpu_read(kprobe_instance);
 
@@ -1052,8 +1043,9 @@ static int __kprobes aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
 	}
 	return 0;
 }
+NOKPROBE_SYMBOL(aggr_fault_handler);
 
-static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
+static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe *cur = __this_cpu_read(kprobe_instance);
 	int ret = 0;
@@ -1065,9 +1057,10 @@ static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
 	reset_kprobe_instance();
 	return ret;
 }
+NOKPROBE_SYMBOL(aggr_break_handler);
 
 /* Walks the list and increments nmissed count for multiprobe case */
-void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
+void kprobes_inc_nmissed_count(struct kprobe *p)
 {
 	struct kprobe *kp;
 	if (!kprobe_aggrprobe(p)) {
@@ -1078,9 +1071,10 @@ void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
 	}
 	return;
 }
+NOKPROBE_SYMBOL(kprobes_inc_nmissed_count);
 
-void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
-				struct hlist_head *head)
+void recycle_rp_inst(struct kretprobe_instance *ri,
+		     struct hlist_head *head)
 {
 	struct kretprobe *rp = ri->rp;
 
@@ -1095,8 +1089,9 @@ void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
 		/* Unregistering */
 		hlist_add_head(&ri->hlist, head);
 }
+NOKPROBE_SYMBOL(recycle_rp_inst);
 
-void __kprobes kretprobe_hash_lock(struct task_struct *tsk,
+void kretprobe_hash_lock(struct task_struct *tsk,
 			 struct hlist_head **head, unsigned long *flags)
 __acquires(hlist_lock)
 {
@@ -1107,17 +1102,19 @@ __acquires(hlist_lock)
 	hlist_lock = kretprobe_table_lock_ptr(hash);
 	raw_spin_lock_irqsave(hlist_lock, *flags);
 }
+NOKPROBE_SYMBOL(kretprobe_hash_lock);
 
-static void __kprobes kretprobe_table_lock(unsigned long hash,
-	unsigned long *flags)
+static void kretprobe_table_lock(unsigned long hash,
+				 unsigned long *flags)
 __acquires(hlist_lock)
 {
 	raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
 	raw_spin_lock_irqsave(hlist_lock, *flags);
 }
+NOKPROBE_SYMBOL(kretprobe_table_lock);
 
-void __kprobes kretprobe_hash_unlock(struct task_struct *tsk,
-	unsigned long *flags)
+void kretprobe_hash_unlock(struct task_struct *tsk,
+			   unsigned long *flags)
 __releases(hlist_lock)
 {
 	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
@@ -1126,14 +1123,16 @@ __releases(hlist_lock)
 	hlist_lock = kretprobe_table_lock_ptr(hash);
 	raw_spin_unlock_irqrestore(hlist_lock, *flags);
 }
+NOKPROBE_SYMBOL(kretprobe_hash_unlock);
 
-static void __kprobes kretprobe_table_unlock(unsigned long hash,
-       unsigned long *flags)
+static void kretprobe_table_unlock(unsigned long hash,
+				   unsigned long *flags)
 __releases(hlist_lock)
 {
 	raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
 	raw_spin_unlock_irqrestore(hlist_lock, *flags);
 }
+NOKPROBE_SYMBOL(kretprobe_table_unlock);
 
 /*
  * This function is called from finish_task_switch when task tk becomes dead,
@@ -1141,7 +1140,7 @@ __releases(hlist_lock)
  * with this task. These left over instances represent probed functions
  * that have been called but will never return.
  */
-void __kprobes kprobe_flush_task(struct task_struct *tk)
+void kprobe_flush_task(struct task_struct *tk)
 {
 	struct kretprobe_instance *ri;
 	struct hlist_head *head, empty_rp;
@@ -1166,6 +1165,7 @@ void __kprobes kprobe_flush_task(struct task_struct *tk)
 		kfree(ri);
 	}
 }
+NOKPROBE_SYMBOL(kprobe_flush_task);
 
 static inline void free_rp_inst(struct kretprobe *rp)
 {
@@ -1178,7 +1178,7 @@ static inline void free_rp_inst(struct kretprobe *rp)
 	}
 }
 
-static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
+static void cleanup_rp_inst(struct kretprobe *rp)
 {
 	unsigned long flags, hash;
 	struct kretprobe_instance *ri;
@@ -1197,12 +1197,13 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
 	}
 	free_rp_inst(rp);
 }
+NOKPROBE_SYMBOL(cleanup_rp_inst);
 
 /*
 * Add the new probe to ap->list. Fail if this is the
 * second jprobe at the address - two jprobes can't coexist
 */
-static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
+static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
 	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
 
@@ -1226,7 +1227,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
  * Fill in the required fields of the "manager kprobe". Replace the
  * earlier kprobe in the hlist with the manager kprobe
  */
-static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
+static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 {
 	/* Copy p's insn slot to ap */
 	copy_kprobe(p, ap);
@@ -1252,8 +1253,7 @@ static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
  * This is the second or subsequent kprobe at the address - handle
  * the intricacies
  */
-static int __kprobes register_aggr_kprobe(struct kprobe *orig_p,
-					  struct kprobe *p)
+static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
 {
 	int ret = 0;
 	struct kprobe *ap = orig_p;
@@ -1324,25 +1324,29 @@ out:
 	return ret;
 }
 
-static int __kprobes in_kprobes_functions(unsigned long addr)
+bool __weak arch_within_kprobe_blacklist(unsigned long addr)
 {
-	struct kprobe_blackpoint *kb;
+	/* The __kprobes marked functions and entry code must not be probed */
+	return addr >= (unsigned long)__kprobes_text_start &&
+	       addr < (unsigned long)__kprobes_text_end;
+}
 
-	if (addr >= (unsigned long)__kprobes_text_start &&
-	    addr < (unsigned long)__kprobes_text_end)
-		return -EINVAL;
+static bool within_kprobe_blacklist(unsigned long addr)
+{
+	struct kprobe_blacklist_entry *ent;
+
+	if (arch_within_kprobe_blacklist(addr))
+		return true;
 	/*
 	 * If there exists a kprobe_blacklist, verify and
 	 * fail any probe registration in the prohibited area
 	 */
-	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
-		if (kb->start_addr) {
-			if (addr >= kb->start_addr &&
-			    addr < (kb->start_addr + kb->range))
-				return -EINVAL;
-		}
+	list_for_each_entry(ent, &kprobe_blacklist, list) {
+		if (addr >= ent->start_addr && addr < ent->end_addr)
+			return true;
 	}
-	return 0;
+
+	return false;
 }
 
 /*
@@ -1351,7 +1355,7 @@ static int __kprobes in_kprobes_functions(unsigned long addr)
  * This returns encoded errors if it fails to look up symbol or invalid
  * combination of parameters.
  */
-static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
+static kprobe_opcode_t *kprobe_addr(struct kprobe *p)
 {
 	kprobe_opcode_t *addr = p->addr;
 
@@ -1374,7 +1378,7 @@ invalid:
 }
 
 /* Check passed kprobe is valid and return kprobe in kprobe_table. */
-static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
+static struct kprobe *__get_valid_kprobe(struct kprobe *p)
 {
 	struct kprobe *ap, *list_p;
 
@@ -1406,8 +1410,8 @@ static inline int check_kprobe_rereg(struct kprobe *p)
 	return ret;
 }
 
-static __kprobes int check_kprobe_address_safe(struct kprobe *p,
-					       struct module **probed_mod)
+static int check_kprobe_address_safe(struct kprobe *p,
+				     struct module **probed_mod)
 {
 	int ret = 0;
 	unsigned long ftrace_addr;
@@ -1433,7 +1437,7 @@ static __kprobes int check_kprobe_address_safe(struct kprobe *p,
 
 	/* Ensure it is not in reserved area nor out of text */
 	if (!kernel_text_address((unsigned long) p->addr) ||
-	    in_kprobes_functions((unsigned long) p->addr) ||
+	    within_kprobe_blacklist((unsigned long) p->addr) ||
 	    jump_label_text_reserved(p->addr, p->addr)) {
 		ret = -EINVAL;
 		goto out;
@@ -1469,7 +1473,7 @@ out:
 	return ret;
 }
 
-int __kprobes register_kprobe(struct kprobe *p)
+int register_kprobe(struct kprobe *p)
 {
 	int ret;
 	struct kprobe *old_p;
@@ -1531,7 +1535,7 @@ out:
 EXPORT_SYMBOL_GPL(register_kprobe);
 
 /* Check if all probes on the aggrprobe are disabled */
-static int __kprobes aggr_kprobe_disabled(struct kprobe *ap)
+static int aggr_kprobe_disabled(struct kprobe *ap)
 {
 	struct kprobe *kp;
 
@@ -1547,7 +1551,7 @@ static int __kprobes aggr_kprobe_disabled(struct kprobe *ap)
 }
 
 /* Disable one kprobe: Make sure called under kprobe_mutex is locked */
-static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p)
+static struct kprobe *__disable_kprobe(struct kprobe *p)
 {
 	struct kprobe *orig_p;
 
@@ -1574,7 +1578,7 @@ static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p)
 /*
  * Unregister a kprobe without a scheduler synchronization.
  */
-static int __kprobes __unregister_kprobe_top(struct kprobe *p)
+static int __unregister_kprobe_top(struct kprobe *p)
 {
 	struct kprobe *ap, *list_p;
 
@@ -1631,7 +1635,7 @@ disarmed:
 	return 0;
 }
 
-static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
+static void __unregister_kprobe_bottom(struct kprobe *p)
 {
 	struct kprobe *ap;
 
@@ -1647,7 +1651,7 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
 	/* Otherwise, do nothing. */
 }
 
-int __kprobes register_kprobes(struct kprobe **kps, int num)
+int register_kprobes(struct kprobe **kps, int num)
 {
 	int i, ret = 0;
 
@@ -1665,13 +1669,13 @@ int __kprobes register_kprobes(struct kprobe **kps, int num)
 }
 EXPORT_SYMBOL_GPL(register_kprobes);
 
-void __kprobes unregister_kprobe(struct kprobe *p)
+void unregister_kprobe(struct kprobe *p)
 {
 	unregister_kprobes(&p, 1);
 }
 EXPORT_SYMBOL_GPL(unregister_kprobe);
 
-void __kprobes unregister_kprobes(struct kprobe **kps, int num)
+void unregister_kprobes(struct kprobe **kps, int num)
 {
 	int i;
 
@@ -1700,7 +1704,7 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 	return (unsigned long)entry;
 }
 
-int __kprobes register_jprobes(struct jprobe **jps, int num)
+int register_jprobes(struct jprobe **jps, int num)
 {
 	struct jprobe *jp;
 	int ret = 0, i;
@@ -1731,19 +1735,19 @@ int __kprobes register_jprobes(struct jprobe **jps, int num)
 }
 EXPORT_SYMBOL_GPL(register_jprobes);
 
-int __kprobes register_jprobe(struct jprobe *jp)
+int register_jprobe(struct jprobe *jp)
 {
 	return register_jprobes(&jp, 1);
 }
 EXPORT_SYMBOL_GPL(register_jprobe);
 
-void __kprobes unregister_jprobe(struct jprobe *jp)
+void unregister_jprobe(struct jprobe *jp)
 {
 	unregister_jprobes(&jp, 1);
 }
 EXPORT_SYMBOL_GPL(unregister_jprobe);
 
-void __kprobes unregister_jprobes(struct jprobe **jps, int num)
+void unregister_jprobes(struct jprobe **jps, int num)
 {
 	int i;
 
@@ -1768,8 +1772,7 @@ EXPORT_SYMBOL_GPL(unregister_jprobes);
  * This kprobe pre_handler is registered with every kretprobe. When probe
  * hits it will set up the return probe.
  */
-static int __kprobes pre_handler_kretprobe(struct kprobe *p,
-					   struct pt_regs *regs)
+static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
 	unsigned long hash, flags = 0;
@@ -1807,8 +1810,9 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
 	}
 	return 0;
 }
+NOKPROBE_SYMBOL(pre_handler_kretprobe);
 
-int __kprobes register_kretprobe(struct kretprobe *rp)
+int register_kretprobe(struct kretprobe *rp)
 {
 	int ret = 0;
 	struct kretprobe_instance *inst;
@@ -1861,7 +1865,7 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
 }
 EXPORT_SYMBOL_GPL(register_kretprobe);
 
-int __kprobes register_kretprobes(struct kretprobe **rps, int num)
+int register_kretprobes(struct kretprobe **rps, int num)
 {
 	int ret = 0, i;
 
@@ -1879,13 +1883,13 @@ int __kprobes register_kretprobes(struct kretprobe **rps, int num)
 }
 EXPORT_SYMBOL_GPL(register_kretprobes);
 
-void __kprobes unregister_kretprobe(struct kretprobe *rp)
+void unregister_kretprobe(struct kretprobe *rp)
 {
 	unregister_kretprobes(&rp, 1);
 }
 EXPORT_SYMBOL_GPL(unregister_kretprobe);
 
-void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
+void unregister_kretprobes(struct kretprobe **rps, int num)
 {
 	int i;
 
@@ -1908,38 +1912,38 @@ void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
 EXPORT_SYMBOL_GPL(unregister_kretprobes);
 
 #else /* CONFIG_KRETPROBES */
-int __kprobes register_kretprobe(struct kretprobe *rp)
+int register_kretprobe(struct kretprobe *rp)
 {
 	return -ENOSYS;
 }
 EXPORT_SYMBOL_GPL(register_kretprobe);
 
-int __kprobes register_kretprobes(struct kretprobe **rps, int num)
+int register_kretprobes(struct kretprobe **rps, int num)
 {
 	return -ENOSYS;
 }
 EXPORT_SYMBOL_GPL(register_kretprobes);
 
-void __kprobes unregister_kretprobe(struct kretprobe *rp)
+void unregister_kretprobe(struct kretprobe *rp)
 {
 }
 EXPORT_SYMBOL_GPL(unregister_kretprobe);
 
-void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
+void unregister_kretprobes(struct kretprobe **rps, int num)
 {
 }
 EXPORT_SYMBOL_GPL(unregister_kretprobes);
 
-static int __kprobes pre_handler_kretprobe(struct kprobe *p,
-					   struct pt_regs *regs)
+static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
 {
 	return 0;
 }
+NOKPROBE_SYMBOL(pre_handler_kretprobe);
 
 #endif /* CONFIG_KRETPROBES */
 
 /* Set the kprobe gone and remove its instruction buffer. */
-static void __kprobes kill_kprobe(struct kprobe *p)
+static void kill_kprobe(struct kprobe *p)
 {
 	struct kprobe *kp;
 
@@ -1963,7 +1967,7 @@ static void __kprobes kill_kprobe(struct kprobe *p)
 }
 
 /* Disable one kprobe */
-int __kprobes disable_kprobe(struct kprobe *kp)
+int disable_kprobe(struct kprobe *kp)
 {
 	int ret = 0;
 
@@ -1979,7 +1983,7 @@ int __kprobes disable_kprobe(struct kprobe *kp)
 EXPORT_SYMBOL_GPL(disable_kprobe);
 
 /* Enable one kprobe */
-int __kprobes enable_kprobe(struct kprobe *kp)
+int enable_kprobe(struct kprobe *kp)
 {
 	int ret = 0;
 	struct kprobe *p;
@@ -2012,16 +2016,53 @@ out:
 }
 EXPORT_SYMBOL_GPL(enable_kprobe);
 
-void __kprobes dump_kprobe(struct kprobe *kp)
+void dump_kprobe(struct kprobe *kp)
 {
 	printk(KERN_WARNING "Dumping kprobe:\n");
 	printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
 	       kp->symbol_name, kp->addr, kp->offset);
 }
+NOKPROBE_SYMBOL(dump_kprobe);
+
+/*
+ * Lookup and populate the kprobe_blacklist.
+ *
+ * Unlike the kretprobe blacklist, we'll need to determine
+ * the range of addresses that belong to the said functions,
+ * since a kprobe need not necessarily be at the beginning
+ * of a function.
+ */
+static int __init populate_kprobe_blacklist(unsigned long *start,
+					     unsigned long *end)
+{
+	unsigned long *iter;
+	struct kprobe_blacklist_entry *ent;
+	unsigned long entry, offset = 0, size = 0;
+
+	for (iter = start; iter < end; iter++) {
+		entry = arch_deref_entry_point((void *)*iter);
+
+		if (!kernel_text_address(entry) ||
+		    !kallsyms_lookup_size_offset(entry, &size, &offset)) {
+			pr_err("Failed to find blacklist at %p\n",
+				(void *)entry);
+			continue;
+		}
+
+		ent = kmalloc(sizeof(*ent), GFP_KERNEL);
+		if (!ent)
+			return -ENOMEM;
+		ent->start_addr = entry;
+		ent->end_addr = entry + size;
+		INIT_LIST_HEAD(&ent->list);
+		list_add_tail(&ent->list, &kprobe_blacklist);
+	}
+	return 0;
+}
 
 /* Module notifier call back, checking kprobes on the module */
-static int __kprobes kprobes_module_callback(struct notifier_block *nb,
-					     unsigned long val, void *data)
+static int kprobes_module_callback(struct notifier_block *nb,
+				   unsigned long val, void *data)
 {
 	struct module *mod = data;
 	struct hlist_head *head;
@@ -2062,14 +2103,13 @@ static struct notifier_block kprobe_module_nb = {
 	.priority = 0
 };
 
+/* Markers of _kprobe_blacklist section */
+extern unsigned long __start_kprobe_blacklist[];
+extern unsigned long __stop_kprobe_blacklist[];
+
 static int __init init_kprobes(void)
 {
 	int i, err = 0;
-	unsigned long offset = 0, size = 0;
-	char *modname, namebuf[KSYM_NAME_LEN];
-	const char *symbol_name;
-	void *addr;
-	struct kprobe_blackpoint *kb;
 
 	/* FIXME allocate the probe table, currently defined statically */
 	/* initialize all list heads */
@@ -2079,26 +2119,11 @@ static int __init init_kprobes(void)
 		raw_spin_lock_init(&(kretprobe_table_locks[i].lock));
 	}
 
-	/*
-	 * Lookup and populate the kprobe_blacklist.
-	 *
-	 * Unlike the kretprobe blacklist, we'll need to determine
-	 * the range of addresses that belong to the said functions,
-	 * since a kprobe need not necessarily be at the beginning
-	 * of a function.
-	 */
-	for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
-		kprobe_lookup_name(kb->name, addr);
-		if (!addr)
-			continue;
-
-		kb->start_addr = (unsigned long)addr;
-		symbol_name = kallsyms_lookup(kb->start_addr,
-				&size, &offset, &modname, namebuf);
-		if (!symbol_name)
-			kb->range = 0;
-		else
-			kb->range = size;
+	err = populate_kprobe_blacklist(__start_kprobe_blacklist,
+					__stop_kprobe_blacklist);
+	if (err) {
+		pr_err("kprobes: failed to populate blacklist: %d\n", err);
+		pr_err("Please take care of using kprobes.\n");
 	}
 
 	if (kretprobe_blacklist_size) {
@@ -2138,7 +2163,7 @@ static int __init init_kprobes(void)
 }
 
 #ifdef CONFIG_DEBUG_FS
-static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
+static void report_probe(struct seq_file *pi, struct kprobe *p,
 		const char *sym, int offset, char *modname, struct kprobe *pp)
 {
 	char *kprobe_type;
@@ -2167,12 +2192,12 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
 		(kprobe_ftrace(pp) ? "[FTRACE]" : ""));
 }
 
-static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
+static void *kprobe_seq_start(struct seq_file *f, loff_t *pos)
 {
 	return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL;
 }
 
-static void __kprobes *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos)
+static void *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos)
 {
 	(*pos)++;
 	if (*pos >= KPROBE_TABLE_SIZE)
@@ -2180,12 +2205,12 @@ static void __kprobes *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos)
 	return pos;
 }
 
-static void __kprobes kprobe_seq_stop(struct seq_file *f, void *v)
+static void kprobe_seq_stop(struct seq_file *f, void *v)
 {
 	/* Nothing to do */
 }
 
-static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
+static int show_kprobe_addr(struct seq_file *pi, void *v)
 {
 	struct hlist_head *head;
 	struct kprobe *p, *kp;
@@ -2216,7 +2241,7 @@ static const struct seq_operations kprobes_seq_ops = {
 	.show  = show_kprobe_addr
 };
 
-static int __kprobes kprobes_open(struct inode *inode, struct file *filp)
+static int kprobes_open(struct inode *inode, struct file *filp)
 {
 	return seq_open(filp, &kprobes_seq_ops);
 }
@@ -2228,7 +2253,47 @@ static const struct file_operations debugfs_kprobes_operations = {
 	.release        = seq_release,
 };
 
-static void __kprobes arm_all_kprobes(void)
+/* kprobes/blacklist -- shows which functions can not be probed */
+static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos)
+{
+	return seq_list_start(&kprobe_blacklist, *pos);
+}
+
+static void *kprobe_blacklist_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return seq_list_next(v, &kprobe_blacklist, pos);
+}
+
+static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
+{
+	struct kprobe_blacklist_entry *ent =
+		list_entry(v, struct kprobe_blacklist_entry, list);
+
+	seq_printf(m, "0x%p-0x%p\t%ps\n", (void *)ent->start_addr,
+		   (void *)ent->end_addr, (void *)ent->start_addr);
+	return 0;
+}
+
+static const struct seq_operations kprobe_blacklist_seq_ops = {
+	.start = kprobe_blacklist_seq_start,
+	.next  = kprobe_blacklist_seq_next,
+	.stop  = kprobe_seq_stop,	/* Reuse void function */
+	.show  = kprobe_blacklist_seq_show,
+};
+
+static int kprobe_blacklist_open(struct inode *inode, struct file *filp)
+{
+	return seq_open(filp, &kprobe_blacklist_seq_ops);
+}
+
+static const struct file_operations debugfs_kprobe_blacklist_ops = {
+	.open           = kprobe_blacklist_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release        = seq_release,
+};
+
+static void arm_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
@@ -2256,7 +2321,7 @@ already_enabled:
 	return;
 }
 
-static void __kprobes disarm_all_kprobes(void)
+static void disarm_all_kprobes(void)
 {
 	struct hlist_head *head;
 	struct kprobe *p;
@@ -2340,7 +2405,7 @@ static const struct file_operations fops_kp = {
 	.llseek =	default_llseek,
 };
 
-static int __kprobes debugfs_kprobe_init(void)
+static int __init debugfs_kprobe_init(void)
 {
 	struct dentry *dir, *file;
 	unsigned int value = 1;
@@ -2351,19 +2416,24 @@ static int __kprobes debugfs_kprobe_init(void)
 
 	file = debugfs_create_file("list", 0444, dir, NULL,
 				&debugfs_kprobes_operations);
-	if (!file) {
-		debugfs_remove(dir);
-		return -ENOMEM;
-	}
+	if (!file)
+		goto error;
 
 	file = debugfs_create_file("enabled", 0600, dir,
 					&value, &fops_kp);
-	if (!file) {
-		debugfs_remove(dir);
-		return -ENOMEM;
-	}
+	if (!file)
+		goto error;
+
+	file = debugfs_create_file("blacklist", 0444, dir, NULL,
+				&debugfs_kprobe_blacklist_ops);
+	if (!file)
+		goto error;
 
 	return 0;
+
+error:
+	debugfs_remove(dir);
+	return -ENOMEM;
 }
 
 late_initcall(debugfs_kprobe_init);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index c2390f41307..ef483220e85 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -591,7 +591,7 @@ static void insert_kthread_work(struct kthread_worker *worker,
 
 	list_add_tail(&work->node, pos);
 	work->worker = worker;
-	if (likely(worker->task))
+	if (!worker->current_work && likely(worker->task))
 		wake_up_process(worker->task);
 }
 
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index b8bdcd4785b..8541bfdfd23 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -24,4 +24,5 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
 obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
+obj-$(CONFIG_QUEUE_RWLOCK) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index d24e4339b46..88d0d4420ad 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -384,7 +384,9 @@ static void print_lockdep_off(const char *bug_msg)
 {
 	printk(KERN_DEBUG "%s\n", bug_msg);
 	printk(KERN_DEBUG "turning off the locking correctness validator.\n");
+#ifdef CONFIG_LOCK_STAT
 	printk(KERN_DEBUG "Please attach the output of /proc/lock_stat to the bug report\n");
+#endif
 }
 
 static int save_trace(struct stack_trace *trace)
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
index 838dc9e0066..9887a905a76 100644
--- a/kernel/locking/mcs_spinlock.c
+++ b/kernel/locking/mcs_spinlock.c
@@ -1,6 +1,4 @@
-
 #include <linux/percpu.h>
-#include <linux/mutex.h>
 #include <linux/sched.h>
 #include "mcs_spinlock.h"
 
@@ -14,21 +12,47 @@
  * called from interrupt context and we have preemption disabled while
  * spinning.
  */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
+
+/*
+ * We use the value 0 to represent "no CPU", thus the encoded value
+ * will be the CPU number incremented by 1.
+ */
+static inline int encode_cpu(int cpu_nr)
+{
+	return cpu_nr + 1;
+}
+
+static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
+{
+	int cpu_nr = encoded_cpu_val - 1;
+
+	return per_cpu_ptr(&osq_node, cpu_nr);
+}
 
 /*
  * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
  * Can return NULL in case we were the last queued and we updated @lock instead.
  */
-static inline struct optimistic_spin_queue *
-osq_wait_next(struct optimistic_spin_queue **lock,
-	      struct optimistic_spin_queue *node,
-	      struct optimistic_spin_queue *prev)
+static inline struct optimistic_spin_node *
+osq_wait_next(struct optimistic_spin_queue *lock,
+	      struct optimistic_spin_node *node,
+	      struct optimistic_spin_node *prev)
 {
-	struct optimistic_spin_queue *next = NULL;
+	struct optimistic_spin_node *next = NULL;
+	int curr = encode_cpu(smp_processor_id());
+	int old;
+
+	/*
+	 * If there is a prev node in queue, then the 'old' value will be
+	 * the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
+	 * we're currently last in queue, then the queue will then become empty.
+	 */
+	old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
 
 	for (;;) {
-		if (*lock == node && cmpxchg(lock, node, prev) == node) {
+		if (atomic_read(&lock->tail) == curr &&
+		    atomic_cmpxchg(&lock->tail, curr, old) == curr) {
 			/*
 			 * We were the last queued, we moved @lock back. @prev
 			 * will now observe @lock and will complete its
@@ -53,24 +77,29 @@ osq_wait_next(struct optimistic_spin_queue **lock,
 				break;
 		}
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 
 	return next;
 }
 
-bool osq_lock(struct optimistic_spin_queue **lock)
+bool osq_lock(struct optimistic_spin_queue *lock)
 {
-	struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
-	struct optimistic_spin_queue *prev, *next;
+	struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
+	struct optimistic_spin_node *prev, *next;
+	int curr = encode_cpu(smp_processor_id());
+	int old;
 
 	node->locked = 0;
 	node->next = NULL;
+	node->cpu = curr;
 
-	node->prev = prev = xchg(lock, node);
-	if (likely(prev == NULL))
+	old = atomic_xchg(&lock->tail, curr);
+	if (old == OSQ_UNLOCKED_VAL)
 		return true;
 
+	prev = decode_cpu(old);
+	node->prev = prev;
 	ACCESS_ONCE(prev->next) = node;
 
 	/*
@@ -89,7 +118,7 @@ bool osq_lock(struct optimistic_spin_queue **lock)
 		if (need_resched())
 			goto unqueue;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	return true;
 
@@ -115,7 +144,7 @@ unqueue:
 		if (smp_load_acquire(&node->locked))
 			return true;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 
 		/*
 		 * Or we race against a concurrent unqueue()'s step-B, in which
@@ -149,20 +178,21 @@ unqueue:
 	return false;
 }
 
-void osq_unlock(struct optimistic_spin_queue **lock)
+void osq_unlock(struct optimistic_spin_queue *lock)
 {
-	struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
-	struct optimistic_spin_queue *next;
+	struct optimistic_spin_node *node, *next;
+	int curr = encode_cpu(smp_processor_id());
 
 	/*
 	 * Fast path for the uncontended case.
 	 */
-	if (likely(cmpxchg(lock, node, NULL) == node))
+	if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr))
 		return;
 
 	/*
 	 * Second most likely case.
 	 */
+	node = this_cpu_ptr(&osq_node);
 	next = xchg(&node->next, NULL);
 	if (next) {
 		ACCESS_ONCE(next->locked) = 1;
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index a2dbac4aca6..23e89c5930e 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -27,7 +27,7 @@ struct mcs_spinlock {
 #define arch_mcs_spin_lock_contended(l)					\
 do {									\
 	while (!(smp_load_acquire(l)))					\
-		arch_mutex_cpu_relax();					\
+		cpu_relax_lowlatency();					\
 } while (0)
 #endif
 
@@ -104,7 +104,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 			return;
 		/* Wait until the next pointer is set */
 		while (!(next = ACCESS_ONCE(node->next)))
-			arch_mutex_cpu_relax();
+			cpu_relax_lowlatency();
 	}
 
 	/* Pass lock to next waiter. */
@@ -118,12 +118,13 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
  * mutex_lock()/rwsem_down_{read,write}() etc.
  */
 
-struct optimistic_spin_queue {
-	struct optimistic_spin_queue *next, *prev;
+struct optimistic_spin_node {
+	struct optimistic_spin_node *next, *prev;
 	int locked; /* 1 if lock acquired */
+	int cpu; /* encoded CPU # value */
 };
 
-extern bool osq_lock(struct optimistic_spin_queue **lock);
-extern void osq_unlock(struct optimistic_spin_queue **lock);
+extern bool osq_lock(struct optimistic_spin_queue *lock);
+extern void osq_unlock(struct optimistic_spin_queue *lock);
 
 #endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index bc73d33c676..ae712b25e49 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -46,12 +46,6 @@
 # include <asm/mutex.h>
 #endif
 
-/*
- * A negative mutex count indicates that waiters are sleeping waiting for the
- * mutex.
- */
-#define	MUTEX_SHOW_NO_WAITER(mutex)	(atomic_read(&(mutex)->count) >= 0)
-
 void
 __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 {
@@ -60,7 +54,7 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 	INIT_LIST_HEAD(&lock->wait_list);
 	mutex_clear_owner(lock);
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	lock->osq = NULL;
+	osq_lock_init(&lock->osq);
 #endif
 
 	debug_mutex_init(lock, name, key);
@@ -152,7 +146,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 		if (need_resched())
 			break;
 
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	rcu_read_unlock();
 
@@ -388,12 +382,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	/*
 	 * Optimistic spinning.
 	 *
-	 * We try to spin for acquisition when we find that there are no
-	 * pending waiters and the lock owner is currently running on a
-	 * (different) CPU.
-	 *
-	 * The rationale is that if the lock owner is running, it is likely to
-	 * release the lock soon.
+	 * We try to spin for acquisition when we find that the lock owner
+	 * is currently running on a (different) CPU and while we don't
+	 * need to reschedule. The rationale is that if the lock owner is
+	 * running, it is likely to release the lock soon.
 	 *
 	 * Since this needs the lock owner, and this mutex implementation
 	 * doesn't track the owner atomically in the lock field, we need to
@@ -440,7 +432,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		if (owner && !mutex_spin_on_owner(lock, owner))
 			break;
 
-		if ((atomic_read(&lock->count) == 1) &&
+		/* Try to acquire the mutex if it is unlocked. */
+		if (!mutex_is_locked(lock) &&
 		    (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
 			lock_acquired(&lock->dep_map, ip);
 			if (use_ww_ctx) {
@@ -471,7 +464,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		arch_mutex_cpu_relax();
+		cpu_relax_lowlatency();
 	}
 	osq_unlock(&lock->osq);
 slowpath:
@@ -485,8 +478,11 @@ slowpath:
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);
 
-	/* once more, can we acquire the lock? */
-	if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, 0) == 1))
+	/*
+	 * Once more, try to acquire the lock. Only try-lock the mutex if
+	 * it is unlocked to reduce unnecessary xchg() operations.
+	 */
+	if (!mutex_is_locked(lock) && (atomic_xchg(&lock->count, 0) == 1))
 		goto skip_wait;
 
 	debug_mutex_lock_common(lock, &waiter);
@@ -506,9 +502,10 @@ slowpath:
 		 * it's unlocked. Later on, if we sleep, this is the
 		 * operation that gives us the lock. We xchg it to -1, so
 		 * that when we release the lock, we properly wake up the
-		 * other waiters:
+		 * other waiters. We only attempt the xchg if the count is
+		 * non-negative in order to avoid unnecessary xchg operations:
 		 */
-		if (MUTEX_SHOW_NO_WAITER(lock) &&
+		if (atomic_read(&lock->count) >= 0 &&
 		    (atomic_xchg(&lock->count, -1) == 1))
 			break;
 
@@ -823,6 +820,10 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
 	unsigned long flags;
 	int prev;
 
+	/* No need to trylock if the mutex is locked. */
+	if (mutex_is_locked(lock))
+		return 0;
+
 	spin_lock_mutex(&lock->wait_lock, flags);
 
 	prev = atomic_xchg(&lock->count, -1);
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
new file mode 100644
index 00000000000..f956ede7f90
--- /dev/null
+++ b/kernel/locking/qrwlock.c
@@ -0,0 +1,132 @@
+/*
+ * Queue read/write lock
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P.
+ *
+ * Authors: Waiman Long <waiman.long@hp.com>
+ */
+#include <linux/smp.h>
+#include <linux/bug.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <asm/qrwlock.h>
+
+/**
+ * rspin_until_writer_unlock - inc reader count & spin until writer is gone
+ * @lock  : Pointer to queue rwlock structure
+ * @writer: Current queue rwlock writer status byte
+ *
+ * In interrupt context or at the head of the queue, the reader will just
+ * increment the reader count & wait until the writer releases the lock.
+ */
+static __always_inline void
+rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts)
+{
+	while ((cnts & _QW_WMASK) == _QW_LOCKED) {
+		cpu_relax_lowlatency();
+		cnts = smp_load_acquire((u32 *)&lock->cnts);
+	}
+}
+
+/**
+ * queue_read_lock_slowpath - acquire read lock of a queue rwlock
+ * @lock: Pointer to queue rwlock structure
+ */
+void queue_read_lock_slowpath(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	/*
+	 * Readers come here when they cannot get the lock without waiting
+	 */
+	if (unlikely(in_interrupt())) {
+		/*
+		 * Readers in interrupt context will spin until the lock is
+		 * available without waiting in the queue.
+		 */
+		cnts = smp_load_acquire((u32 *)&lock->cnts);
+		rspin_until_writer_unlock(lock, cnts);
+		return;
+	}
+	atomic_sub(_QR_BIAS, &lock->cnts);
+
+	/*
+	 * Put the reader into the wait queue
+	 */
+	arch_spin_lock(&lock->lock);
+
+	/*
+	 * At the head of the wait queue now, wait until the writer state
+	 * goes to 0 and then try to increment the reader count and get
+	 * the lock. It is possible that an incoming writer may steal the
+	 * lock in the interim, so it is necessary to check the writer byte
+	 * to make sure that the write lock isn't taken.
+	 */
+	while (atomic_read(&lock->cnts) & _QW_WMASK)
+		cpu_relax_lowlatency();
+
+	cnts = atomic_add_return(_QR_BIAS, &lock->cnts) - _QR_BIAS;
+	rspin_until_writer_unlock(lock, cnts);
+
+	/*
+	 * Signal the next one in queue to become queue head
+	 */
+	arch_spin_unlock(&lock->lock);
+}
+EXPORT_SYMBOL(queue_read_lock_slowpath);
+
+/**
+ * queue_write_lock_slowpath - acquire write lock of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ */
+void queue_write_lock_slowpath(struct qrwlock *lock)
+{
+	u32 cnts;
+
+	/* Put the writer into the wait queue */
+	arch_spin_lock(&lock->lock);
+
+	/* Try to acquire the lock directly if no reader is present */
+	if (!atomic_read(&lock->cnts) &&
+	    (atomic_cmpxchg(&lock->cnts, 0, _QW_LOCKED) == 0))
+		goto unlock;
+
+	/*
+	 * Set the waiting flag to notify readers that a writer is pending,
+	 * or wait for a previous writer to go away.
+	 */
+	for (;;) {
+		cnts = atomic_read(&lock->cnts);
+		if (!(cnts & _QW_WMASK) &&
+		    (atomic_cmpxchg(&lock->cnts, cnts,
+				    cnts | _QW_WAITING) == cnts))
+			break;
+
+		cpu_relax_lowlatency();
+	}
+
+	/* When no more readers, set the locked flag */
+	for (;;) {
+		cnts = atomic_read(&lock->cnts);
+		if ((cnts == _QW_WAITING) &&
+		    (atomic_cmpxchg(&lock->cnts, _QW_WAITING,
+				    _QW_LOCKED) == _QW_WAITING))
+			break;
+
+		cpu_relax_lowlatency();
+	}
+unlock:
+	arch_spin_unlock(&lock->lock);
+}
+EXPORT_SYMBOL(queue_write_lock_slowpath);
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 49b2ed3dced..62b6cee8ea7 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -66,12 +66,13 @@ void rt_mutex_debug_task_free(struct task_struct *task)
  * the deadlock. We print when we return. act_waiter can be NULL in
  * case of a remove waiter operation.
  */
-void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter,
+void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+			     struct rt_mutex_waiter *act_waiter,
 			     struct rt_mutex *lock)
 {
 	struct task_struct *task;
 
-	if (!debug_locks || detect || !act_waiter)
+	if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter)
 		return;
 
 	task = rt_mutex_owner(act_waiter->lock);
diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index 14193d596d7..d0519c3432b 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -20,14 +20,20 @@ extern void debug_rt_mutex_unlock(struct rt_mutex *lock);
 extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock,
 				      struct task_struct *powner);
 extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock);
-extern void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *waiter,
+extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+				    struct rt_mutex_waiter *waiter,
 				    struct rt_mutex *lock);
 extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter);
 # define debug_rt_mutex_reset_waiter(w)			\
 	do { (w)->deadlock_lock = NULL; } while (0)
 
-static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
-						 int detect)
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
+						  enum rtmutex_chainwalk walk)
 {
 	return (waiter != NULL);
 }
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	debug_rt_mutex_print_deadlock(w);
+}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index a620d4d08ca..a0ea2a141b3 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -83,6 +83,47 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 		owner = *p;
 	} while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner);
 }
+
+/*
+ * Safe fastpath aware unlock:
+ * 1) Clear the waiters bit
+ * 2) Drop lock->wait_lock
+ * 3) Try to unlock the lock with cmpxchg
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	struct task_struct *owner = rt_mutex_owner(lock);
+
+	clear_rt_mutex_waiters(lock);
+	raw_spin_unlock(&lock->wait_lock);
+	/*
+	 * If a new waiter comes in between the unlock and the cmpxchg
+	 * we have two situations:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 * cmpxchg(p, owner, 0) == owner
+	 *					mark_rt_mutex_waiters(lock);
+	 *					acquire(lock);
+	 * or:
+	 *
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					mark_rt_mutex_waiters(lock);
+	 *
+	 * cmpxchg(p, owner, 0) != owner
+	 *					enqueue_waiter();
+	 *					unlock(wait_lock);
+	 * lock(wait_lock);
+	 * wake waiter();
+	 * unlock(wait_lock);
+	 *					lock(wait_lock);
+	 *					acquire(lock);
+	 */
+	return rt_mutex_cmpxchg(lock, owner, NULL);
+}
+
 #else
 # define rt_mutex_cmpxchg(l,c,n)	(0)
 static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
@@ -90,6 +131,17 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 	lock->owner = (struct task_struct *)
 			((unsigned long)lock->owner | RT_MUTEX_HAS_WAITERS);
 }
+
+/*
+ * Simple slow path only version: lock->owner is protected by lock->wait_lock.
+ */
+static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock)
+	__releases(lock->wait_lock)
+{
+	lock->owner = NULL;
+	raw_spin_unlock(&lock->wait_lock);
+	return true;
+}
 #endif
 
 static inline int
@@ -256,41 +308,120 @@ static void rt_mutex_adjust_prio(struct task_struct *task)
 }
 
 /*
+ * Deadlock detection is conditional:
+ *
+ * If CONFIG_DEBUG_RT_MUTEXES=n, deadlock detection is only conducted
+ * if the detect argument is == RT_MUTEX_FULL_CHAINWALK.
+ *
+ * If CONFIG_DEBUG_RT_MUTEXES=y, deadlock detection is always
+ * conducted independent of the detect argument.
+ *
+ * If the waiter argument is NULL this indicates the deboost path and
+ * deadlock detection is disabled independent of the detect argument
+ * and the config settings.
+ */
+static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter,
+					  enum rtmutex_chainwalk chwalk)
+{
+	/*
+	 * This is just a wrapper function for the following call,
+	 * because debug_rt_mutex_detect_deadlock() smells like a magic
+	 * debug feature and I wanted to keep the cond function in the
+	 * main source file along with the comments instead of having
+	 * two of the same in the headers.
+	 */
+	return debug_rt_mutex_detect_deadlock(waiter, chwalk);
+}
+
+/*
  * Max number of times we'll walk the boosting chain:
  */
 int max_lock_depth = 1024;
 
+static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
+{
+	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+}
+
 /*
  * Adjust the priority chain. Also used for deadlock detection.
  * Decreases task's usage by one - may thus free the task.
  *
- * @task: the task owning the mutex (owner) for which a chain walk is probably
- *	  needed
+ * @task:	the task owning the mutex (owner) for which a chain walk is
+ *		probably needed
  * @deadlock_detect: do we have to carry out deadlock detection?
- * @orig_lock: the mutex (can be NULL if we are walking the chain to recheck
- * 	       things for a task that has just got its priority adjusted, and
- *	       is waiting on a mutex)
+ * @orig_lock:	the mutex (can be NULL if we are walking the chain to recheck
+ *		things for a task that has just got its priority adjusted, and
+ *		is waiting on a mutex)
+ * @next_lock:	the mutex on which the owner of @orig_lock was blocked before
+ *		we dropped its pi_lock. Is never dereferenced, only used for
+ *		comparison to detect lock chain changes.
  * @orig_waiter: rt_mutex_waiter struct for the task that has just donated
- *		 its priority to the mutex owner (can be NULL in the case
- *		 depicted above or if the top waiter is gone away and we are
- *		 actually deboosting the owner)
- * @top_task: the current top waiter
+ *		its priority to the mutex owner (can be NULL in the case
+ *		depicted above or if the top waiter is gone away and we are
+ *		actually deboosting the owner)
+ * @top_task:	the current top waiter
  *
  * Returns 0 or -EDEADLK.
+ *
+ * Chain walk basics and protection scope
+ *
+ * [R] refcount on task
+ * [P] task->pi_lock held
+ * [L] rtmutex->wait_lock held
+ *
+ * Step	Description				Protected by
+ *	function arguments:
+ *	@task					[R]
+ *	@orig_lock if != NULL			@top_task is blocked on it
+ *	@next_lock				Unprotected. Cannot be
+ *						dereferenced. Only used for
+ *						comparison.
+ *	@orig_waiter if != NULL			@top_task is blocked on it
+ *	@top_task				current, or in case of proxy
+ *						locking protected by calling
+ *						code
+ *	again:
+ *	  loop_sanity_check();
+ *	retry:
+ * [1]	  lock(task->pi_lock);			[R] acquire [P]
+ * [2]	  waiter = task->pi_blocked_on;		[P]
+ * [3]	  check_exit_conditions_1();		[P]
+ * [4]	  lock = waiter->lock;			[P]
+ * [5]	  if (!try_lock(lock->wait_lock)) {	[P] try to acquire [L]
+ *	    unlock(task->pi_lock);		release [P]
+ *	    goto retry;
+ *	  }
+ * [6]	  check_exit_conditions_2();		[P] + [L]
+ * [7]	  requeue_lock_waiter(lock, waiter);	[P] + [L]
+ * [8]	  unlock(task->pi_lock);		release [P]
+ *	  put_task_struct(task);		release [R]
+ * [9]	  check_exit_conditions_3();		[L]
+ * [10]	  task = owner(lock);			[L]
+ *	  get_task_struct(task);		[L] acquire [R]
+ *	  lock(task->pi_lock);			[L] acquire [P]
+ * [11]	  requeue_pi_waiter(tsk, waiters(lock));[P] + [L]
+ * [12]	  check_exit_conditions_4();		[P] + [L]
+ * [13]	  unlock(task->pi_lock);		release [P]
+ *	  unlock(lock->wait_lock);		release [L]
+ *	  goto again;
  */
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
-				      int deadlock_detect,
+				      enum rtmutex_chainwalk chwalk,
 				      struct rt_mutex *orig_lock,
+				      struct rt_mutex *next_lock,
 				      struct rt_mutex_waiter *orig_waiter,
 				      struct task_struct *top_task)
 {
-	struct rt_mutex *lock;
 	struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
-	int detect_deadlock, ret = 0, depth = 0;
+	struct rt_mutex_waiter *prerequeue_top_waiter;
+	int ret = 0, depth = 0;
+	struct rt_mutex *lock;
+	bool detect_deadlock;
 	unsigned long flags;
+	bool requeue = true;
 
-	detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,
-							 deadlock_detect);
+	detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);
 
 	/*
 	 * The (de)boosting is a step by step approach with a lot of
@@ -299,6 +430,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * carefully whether things change under us.
 	 */
  again:
+	/*
+	 * We limit the lock chain length for each invocation.
+	 */
 	if (++depth > max_lock_depth) {
 		static int prev_max;
 
@@ -314,15 +448,30 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		}
 		put_task_struct(task);
 
-		return deadlock_detect ? -EDEADLK : 0;
+		return -EDEADLK;
 	}
+
+	/*
+	 * We are fully preemptible here and only hold the refcount on
+	 * @task. So everything can have changed under us since the
+	 * caller or our own code below (goto retry/again) dropped all
+	 * locks.
+	 */
  retry:
 	/*
-	 * Task can not go away as we did a get_task() before !
+	 * [1] Task cannot go away as we did a get_task() before !
 	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
+	/*
+	 * [2] Get the waiter on which @task is blocked on.
+	 */
 	waiter = task->pi_blocked_on;
+
+	/*
+	 * [3] check_exit_conditions_1() protected by task->pi_lock.
+	 */
+
 	/*
 	 * Check whether the end of the boosting chain has been
 	 * reached or the state of the chain has changed while we
@@ -339,6 +488,18 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto out_unlock_pi;
 
 	/*
+	 * We dropped all locks after taking a refcount on @task, so
+	 * the task might have moved on in the lock chain or even left
+	 * the chain completely and blocks now on an unrelated lock or
+	 * on @orig_lock.
+	 *
+	 * We stored the lock on which @task was blocked in @next_lock,
+	 * so we can detect the chain change.
+	 */
+	if (next_lock != waiter->lock)
+		goto out_unlock_pi;
+
+	/*
 	 * Drop out, when the task has no waiters. Note,
 	 * top_waiter can be NULL, when we are in the deboosting
 	 * mode!
@@ -348,20 +509,41 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 			goto out_unlock_pi;
 		/*
 		 * If deadlock detection is off, we stop here if we
-		 * are not the top pi waiter of the task.
+		 * are not the top pi waiter of the task. If deadlock
+		 * detection is enabled we continue, but stop the
+		 * requeueing in the chain walk.
 		 */
-		if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
-			goto out_unlock_pi;
+		if (top_waiter != task_top_pi_waiter(task)) {
+			if (!detect_deadlock)
+				goto out_unlock_pi;
+			else
+				requeue = false;
+		}
 	}
 
 	/*
-	 * When deadlock detection is off then we check, if further
-	 * priority adjustment is necessary.
+	 * If the waiter priority is the same as the task priority
+	 * then there is no further priority adjustment necessary.  If
+	 * deadlock detection is off, we stop the chain walk. If its
+	 * enabled we continue, but stop the requeueing in the chain
+	 * walk.
 	 */
-	if (!detect_deadlock && waiter->prio == task->prio)
-		goto out_unlock_pi;
+	if (waiter->prio == task->prio) {
+		if (!detect_deadlock)
+			goto out_unlock_pi;
+		else
+			requeue = false;
+	}
 
+	/*
+	 * [4] Get the next lock
+	 */
 	lock = waiter->lock;
+	/*
+	 * [5] We need to trylock here as we are holding task->pi_lock,
+	 * which is the reverse lock order versus the other rtmutex
+	 * operations.
+	 */
 	if (!raw_spin_trylock(&lock->wait_lock)) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		cpu_relax();
@@ -369,64 +551,180 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	}
 
 	/*
+	 * [6] check_exit_conditions_2() protected by task->pi_lock and
+	 * lock->wait_lock.
+	 *
 	 * Deadlock detection. If the lock is the same as the original
 	 * lock which caused us to walk the lock chain or if the
 	 * current lock is owned by the task which initiated the chain
 	 * walk, we detected a deadlock.
 	 */
 	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
-		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
+		debug_rt_mutex_deadlock(chwalk, orig_waiter, lock);
 		raw_spin_unlock(&lock->wait_lock);
-		ret = deadlock_detect ? -EDEADLK : 0;
+		ret = -EDEADLK;
 		goto out_unlock_pi;
 	}
 
-	top_waiter = rt_mutex_top_waiter(lock);
+	/*
+	 * If we just follow the lock chain for deadlock detection, no
+	 * need to do all the requeue operations. To avoid a truckload
+	 * of conditionals around the various places below, just do the
+	 * minimum chain walk checks.
+	 */
+	if (!requeue) {
+		/*
+		 * No requeue[7] here. Just release @task [8]
+		 */
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		put_task_struct(task);
+
+		/*
+		 * [9] check_exit_conditions_3 protected by lock->wait_lock.
+		 * If there is no owner of the lock, end of chain.
+		 */
+		if (!rt_mutex_owner(lock)) {
+			raw_spin_unlock(&lock->wait_lock);
+			return 0;
+		}
+
+		/* [10] Grab the next task, i.e. owner of @lock */
+		task = rt_mutex_owner(lock);
+		get_task_struct(task);
+		raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+		/*
+		 * No requeue [11] here. We just do deadlock detection.
+		 *
+		 * [12] Store whether owner is blocked
+		 * itself. Decision is made after dropping the locks
+		 */
+		next_lock = task_blocked_on_lock(task);
+		/*
+		 * Get the top waiter for the next iteration
+		 */
+		top_waiter = rt_mutex_top_waiter(lock);
+
+		/* [13] Drop locks */
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		raw_spin_unlock(&lock->wait_lock);
+
+		/* If owner is not blocked, end of chain. */
+		if (!next_lock)
+			goto out_put_task;
+		goto again;
+	}
+
+	/*
+	 * Store the current top waiter before doing the requeue
+	 * operation on @lock. We need it for the boost/deboost
+	 * decision below.
+	 */
+	prerequeue_top_waiter = rt_mutex_top_waiter(lock);
 
-	/* Requeue the waiter */
+	/* [7] Requeue the waiter in the lock waiter list. */
 	rt_mutex_dequeue(lock, waiter);
 	waiter->prio = task->prio;
 	rt_mutex_enqueue(lock, waiter);
 
-	/* Release the task */
+	/* [8] Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	put_task_struct(task);
+
+	/*
+	 * [9] check_exit_conditions_3 protected by lock->wait_lock.
+	 *
+	 * We must abort the chain walk if there is no lock owner even
+	 * in the dead lock detection case, as we have nothing to
+	 * follow here. This is the end of the chain we are walking.
+	 */
 	if (!rt_mutex_owner(lock)) {
 		/*
-		 * If the requeue above changed the top waiter, then we need
-		 * to wake the new top waiter up to try to get the lock.
+		 * If the requeue [7] above changed the top waiter,
+		 * then we need to wake the new top waiter up to try
+		 * to get the lock.
 		 */
-
-		if (top_waiter != rt_mutex_top_waiter(lock))
+		if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
 			wake_up_process(rt_mutex_top_waiter(lock)->task);
 		raw_spin_unlock(&lock->wait_lock);
-		goto out_put_task;
+		return 0;
 	}
-	put_task_struct(task);
 
-	/* Grab the next task */
+	/* [10] Grab the next task, i.e. the owner of @lock */
 	task = rt_mutex_owner(lock);
 	get_task_struct(task);
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
+	/* [11] requeue the pi waiters if necessary */
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		/* Boost the owner */
-		rt_mutex_dequeue_pi(task, top_waiter);
+		/*
+		 * The waiter became the new top (highest priority)
+		 * waiter on the lock. Replace the previous top waiter
+		 * in the owner tasks pi waiters list with this waiter
+		 * and adjust the priority of the owner.
+		 */
+		rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
 		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 
-	} else if (top_waiter == waiter) {
-		/* Deboost the owner */
+	} else if (prerequeue_top_waiter == waiter) {
+		/*
+		 * The waiter was the top waiter on the lock, but is
+		 * no longer the top prority waiter. Replace waiter in
+		 * the owner tasks pi waiters list with the new top
+		 * (highest priority) waiter and adjust the priority
+		 * of the owner.
+		 * The new top waiter is stored in @waiter so that
+		 * @waiter == @top_waiter evaluates to true below and
+		 * we continue to deboost the rest of the chain.
+		 */
 		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
 		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
+	} else {
+		/*
+		 * Nothing changed. No need to do any priority
+		 * adjustment.
+		 */
 	}
 
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-
+	/*
+	 * [12] check_exit_conditions_4() protected by task->pi_lock
+	 * and lock->wait_lock. The actual decisions are made after we
+	 * dropped the locks.
+	 *
+	 * Check whether the task which owns the current lock is pi
+	 * blocked itself. If yes we store a pointer to the lock for
+	 * the lock chain change detection above. After we dropped
+	 * task->pi_lock next_lock cannot be dereferenced anymore.
+	 */
+	next_lock = task_blocked_on_lock(task);
+	/*
+	 * Store the top waiter of @lock for the end of chain walk
+	 * decision below.
+	 */
 	top_waiter = rt_mutex_top_waiter(lock);
+
+	/* [13] Drop the locks */
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	raw_spin_unlock(&lock->wait_lock);
 
+	/*
+	 * Make the actual exit decisions [12], based on the stored
+	 * values.
+	 *
+	 * We reached the end of the lock chain. Stop right here. No
+	 * point to go back just to figure that out.
+	 */
+	if (!next_lock)
+		goto out_put_task;
+
+	/*
+	 * If the current waiter is not the top waiter on the lock,
+	 * then we can stop the chain walk here if we are not in full
+	 * deadlock detection mode.
+	 */
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
 
@@ -445,76 +743,119 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
  *
  * Must be called with lock->wait_lock held.
  *
- * @lock:   the lock to be acquired.
- * @task:   the task which wants to acquire the lock
- * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
+ * @lock:   The lock to be acquired.
+ * @task:   The task which wants to acquire the lock
+ * @waiter: The waiter that is queued to the lock's wait list if the
+ *	    callsite called task_blocked_on_lock(), otherwise NULL
  */
 static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
-		struct rt_mutex_waiter *waiter)
+				struct rt_mutex_waiter *waiter)
 {
+	unsigned long flags;
+
 	/*
-	 * We have to be careful here if the atomic speedups are
-	 * enabled, such that, when
-	 *  - no other waiter is on the lock
-	 *  - the lock has been released since we did the cmpxchg
-	 * the lock can be released or taken while we are doing the
-	 * checks and marking the lock with RT_MUTEX_HAS_WAITERS.
+	 * Before testing whether we can acquire @lock, we set the
+	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
+	 * other tasks which try to modify @lock into the slow path
+	 * and they serialize on @lock->wait_lock.
+	 *
+	 * The RT_MUTEX_HAS_WAITERS bit can have a transitional state
+	 * as explained at the top of this file if and only if:
 	 *
-	 * The atomic acquire/release aware variant of
-	 * mark_rt_mutex_waiters uses a cmpxchg loop. After setting
-	 * the WAITERS bit, the atomic release / acquire can not
-	 * happen anymore and lock->wait_lock protects us from the
-	 * non-atomic case.
+	 * - There is a lock owner. The caller must fixup the
+	 *   transient state if it does a trylock or leaves the lock
+	 *   function due to a signal or timeout.
 	 *
-	 * Note, that this might set lock->owner =
-	 * RT_MUTEX_HAS_WAITERS in the case the lock is not contended
-	 * any more. This is fixed up when we take the ownership.
-	 * This is the transitional state explained at the top of this file.
+	 * - @task acquires the lock and there are no other
+	 *   waiters. This is undone in rt_mutex_set_owner(@task) at
+	 *   the end of this function.
 	 */
 	mark_rt_mutex_waiters(lock);
 
+	/*
+	 * If @lock has an owner, give up.
+	 */
 	if (rt_mutex_owner(lock))
 		return 0;
 
 	/*
-	 * It will get the lock because of one of these conditions:
-	 * 1) there is no waiter
-	 * 2) higher priority than waiters
-	 * 3) it is top waiter
+	 * If @waiter != NULL, @task has already enqueued the waiter
+	 * into @lock waiter list. If @waiter == NULL then this is a
+	 * trylock attempt.
 	 */
-	if (rt_mutex_has_waiters(lock)) {
-		if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
-			if (!waiter || waiter != rt_mutex_top_waiter(lock))
-				return 0;
-		}
-	}
-
-	if (waiter || rt_mutex_has_waiters(lock)) {
-		unsigned long flags;
-		struct rt_mutex_waiter *top;
-
-		raw_spin_lock_irqsave(&task->pi_lock, flags);
+	if (waiter) {
+		/*
+		 * If waiter is not the highest priority waiter of
+		 * @lock, give up.
+		 */
+		if (waiter != rt_mutex_top_waiter(lock))
+			return 0;
 
-		/* remove the queued waiter. */
-		if (waiter) {
-			rt_mutex_dequeue(lock, waiter);
-			task->pi_blocked_on = NULL;
-		}
+		/*
+		 * We can acquire the lock. Remove the waiter from the
+		 * lock waiters list.
+		 */
+		rt_mutex_dequeue(lock, waiter);
 
+	} else {
 		/*
-		 * We have to enqueue the top waiter(if it exists) into
-		 * task->pi_waiters list.
+		 * If the lock has waiters already we check whether @task is
+		 * eligible to take over the lock.
+		 *
+		 * If there are no other waiters, @task can acquire
+		 * the lock.  @task->pi_blocked_on is NULL, so it does
+		 * not need to be dequeued.
 		 */
 		if (rt_mutex_has_waiters(lock)) {
-			top = rt_mutex_top_waiter(lock);
-			rt_mutex_enqueue_pi(task, top);
+			/*
+			 * If @task->prio is greater than or equal to
+			 * the top waiter priority (kernel view),
+			 * @task lost.
+			 */
+			if (task->prio >= rt_mutex_top_waiter(lock)->prio)
+				return 0;
+
+			/*
+			 * The current top waiter stays enqueued. We
+			 * don't have to change anything in the lock
+			 * waiters order.
+			 */
+		} else {
+			/*
+			 * No waiters. Take the lock without the
+			 * pi_lock dance.@task->pi_blocked_on is NULL
+			 * and we have no waiters to enqueue in @task
+			 * pi waiters list.
+			 */
+			goto takeit;
 		}
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
 
+	/*
+	 * Clear @task->pi_blocked_on. Requires protection by
+	 * @task->pi_lock. Redundant operation for the @waiter == NULL
+	 * case, but conditionals are more expensive than a redundant
+	 * store.
+	 */
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	task->pi_blocked_on = NULL;
+	/*
+	 * Finish the lock acquisition. @task is the new owner. If
+	 * other waiters exist we have to insert the highest priority
+	 * waiter into @task->pi_waiters list.
+	 */
+	if (rt_mutex_has_waiters(lock))
+		rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+takeit:
 	/* We got the lock. */
 	debug_rt_mutex_lock(lock);
 
+	/*
+	 * This either preserves the RT_MUTEX_HAS_WAITERS bit if there
+	 * are still waiters or clears it.
+	 */
 	rt_mutex_set_owner(lock, task);
 
 	rt_mutex_deadlock_account_lock(lock, task);
@@ -532,12 +873,13 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 				   struct rt_mutex_waiter *waiter,
 				   struct task_struct *task,
-				   int detect_deadlock)
+				   enum rtmutex_chainwalk chwalk)
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
-	unsigned long flags;
+	struct rt_mutex *next_lock;
 	int chain_walk = 0, res;
+	unsigned long flags;
 
 	/*
 	 * Early deadlock detection. We really don't want the task to
@@ -548,7 +890,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	 * which is wrong, as the other waiter is not in a deadlock
 	 * situation.
 	 */
-	if (detect_deadlock && owner == task)
+	if (owner == task)
 		return -EDEADLK;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -569,20 +911,28 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	if (!owner)
 		return 0;
 
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 		rt_mutex_dequeue_pi(owner, top_waiter);
 		rt_mutex_enqueue_pi(owner, waiter);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
 			chain_walk = 1;
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
-	else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
+	} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
 		chain_walk = 1;
+	}
+
+	/* Store the lock on which owner is blocked or NULL */
+	next_lock = task_blocked_on_lock(owner);
 
-	if (!chain_walk)
+	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+	/*
+	 * Even if full deadlock detection is on, if the owner is not
+	 * blocked itself, we can avoid finding this out in the chain
+	 * walk.
+	 */
+	if (!chain_walk || !next_lock)
 		return 0;
 
 	/*
@@ -594,8 +944,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
-					 task);
+	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
+					 next_lock, waiter, task);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -605,7 +955,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 /*
  * Wake up the next waiter on the lock.
  *
- * Remove the top waiter from the current tasks waiter list and wake it up.
+ * Remove the top waiter from the current tasks pi waiter list and
+ * wake it up.
  *
  * Called with lock->wait_lock held.
  */
@@ -626,10 +977,23 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 */
 	rt_mutex_dequeue_pi(current, waiter);
 
-	rt_mutex_set_owner(lock, NULL);
+	/*
+	 * As we are waking up the top waiter, and the waiter stays
+	 * queued on the lock until it gets the lock, this lock
+	 * obviously has waiters. Just set the bit here and this has
+	 * the added benefit of forcing all new tasks into the
+	 * slow path making sure no task of lower priority than
+	 * the top waiter can steal this lock.
+	 */
+	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
 
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
+	/*
+	 * It's safe to dereference waiter as it cannot go away as
+	 * long as we hold lock->wait_lock. The waiter task needs to
+	 * acquire it in order to dequeue the waiter.
+	 */
 	wake_up_process(waiter->task);
 }
 
@@ -642,40 +1006,42 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 static void remove_waiter(struct rt_mutex *lock,
 			  struct rt_mutex_waiter *waiter)
 {
-	int first = (waiter == rt_mutex_top_waiter(lock));
+	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
+	struct rt_mutex *next_lock;
 	unsigned long flags;
-	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
 	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-	if (!owner)
+	/*
+	 * Only update priority if the waiter was the highest priority
+	 * waiter of the lock and there is an owner to update.
+	 */
+	if (!owner || !is_top_waiter)
 		return;
 
-	if (first) {
-
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
-		rt_mutex_dequeue_pi(owner, waiter);
+	rt_mutex_dequeue_pi(owner, waiter);
 
-		if (rt_mutex_has_waiters(lock)) {
-			struct rt_mutex_waiter *next;
+	if (rt_mutex_has_waiters(lock))
+		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
 
-			next = rt_mutex_top_waiter(lock);
-			rt_mutex_enqueue_pi(owner, next);
-		}
-		__rt_mutex_adjust_prio(owner);
+	__rt_mutex_adjust_prio(owner);
 
-		if (owner->pi_blocked_on)
-			chain_walk = 1;
+	/* Store the lock on which owner is blocked or NULL */
+	next_lock = task_blocked_on_lock(owner);
 
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
+	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 
-	if (!chain_walk)
+	/*
+	 * Don't walk the chain, if the owner task is not blocked
+	 * itself.
+	 */
+	if (!next_lock)
 		return;
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
@@ -683,7 +1049,8 @@ static void remove_waiter(struct rt_mutex *lock,
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	rt_mutex_adjust_prio_chain(owner, 0, lock, NULL, current);
+	rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
+				   next_lock, NULL, current);
 
 	raw_spin_lock(&lock->wait_lock);
 }
@@ -696,6 +1063,7 @@ static void remove_waiter(struct rt_mutex *lock,
 void rt_mutex_adjust_pi(struct task_struct *task)
 {
 	struct rt_mutex_waiter *waiter;
+	struct rt_mutex *next_lock;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
@@ -706,12 +1074,14 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
-
+	next_lock = waiter->lock;
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
-	rt_mutex_adjust_prio_chain(task, 0, NULL, NULL, task);
+
+	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
+				   next_lock, NULL, task);
 }
 
 /**
@@ -763,13 +1133,33 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	return ret;
 }
 
+static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
+				     struct rt_mutex_waiter *w)
+{
+	/*
+	 * If the result is not -EDEADLOCK or the caller requested
+	 * deadlock detection, nothing to do here.
+	 */
+	if (res != -EDEADLOCK || detect_deadlock)
+		return;
+
+	/*
+	 * Yell lowdly and stop the task right here.
+	 */
+	rt_mutex_print_deadlock(w);
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+}
+
 /*
  * Slow path lock function:
  */
 static int __sched
 rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		  struct hrtimer_sleeper *timeout,
-		  int detect_deadlock)
+		  enum rtmutex_chainwalk chwalk)
 {
 	struct rt_mutex_waiter waiter;
 	int ret = 0;
@@ -795,15 +1185,17 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 			timeout->task = NULL;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
 
 	if (likely(!ret))
 		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
 
 	set_current_state(TASK_RUNNING);
 
-	if (unlikely(ret))
+	if (unlikely(ret)) {
 		remove_waiter(lock, &waiter);
+		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
+	}
 
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit
@@ -825,22 +1217,31 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 /*
  * Slow path try-lock function:
  */
-static inline int
-rt_mutex_slowtrylock(struct rt_mutex *lock)
+static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
-	int ret = 0;
+	int ret;
 
+	/*
+	 * If the lock already has an owner we fail to get the lock.
+	 * This can be done without taking the @lock->wait_lock as
+	 * it is only being read, and this is a trylock anyway.
+	 */
+	if (rt_mutex_owner(lock))
+		return 0;
+
+	/*
+	 * The mutex has currently no owner. Lock the wait lock and
+	 * try to acquire the lock.
+	 */
 	raw_spin_lock(&lock->wait_lock);
 
-	if (likely(rt_mutex_owner(lock) != current)) {
+	ret = try_to_take_rt_mutex(lock, current, NULL);
 
-		ret = try_to_take_rt_mutex(lock, current, NULL);
-		/*
-		 * try_to_take_rt_mutex() sets the lock waiters
-		 * bit unconditionally. Clean this up.
-		 */
-		fixup_rt_mutex_waiters(lock);
-	}
+	/*
+	 * try_to_take_rt_mutex() sets the lock waiters bit
+	 * unconditionally. Clean this up.
+	 */
+	fixup_rt_mutex_waiters(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
 
@@ -859,12 +1260,49 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
 
 	rt_mutex_deadlock_account_unlock(current);
 
-	if (!rt_mutex_has_waiters(lock)) {
-		lock->owner = NULL;
-		raw_spin_unlock(&lock->wait_lock);
-		return;
+	/*
+	 * We must be careful here if the fast path is enabled. If we
+	 * have no waiters queued we cannot set owner to NULL here
+	 * because of:
+	 *
+	 * foo->lock->owner = NULL;
+	 *			rtmutex_lock(foo->lock);   <- fast path
+	 *			free = atomic_dec_and_test(foo->refcnt);
+	 *			rtmutex_unlock(foo->lock); <- fast path
+	 *			if (free)
+	 *				kfree(foo);
+	 * raw_spin_unlock(foo->lock->wait_lock);
+	 *
+	 * So for the fastpath enabled kernel:
+	 *
+	 * Nothing can set the waiters bit as long as we hold
+	 * lock->wait_lock. So we do the following sequence:
+	 *
+	 *	owner = rt_mutex_owner(lock);
+	 *	clear_rt_mutex_waiters(lock);
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 *	if (cmpxchg(&lock->owner, owner, 0) == owner)
+	 *		return;
+	 *	goto retry;
+	 *
+	 * The fastpath disabled variant is simple as all access to
+	 * lock->owner is serialized by lock->wait_lock:
+	 *
+	 *	lock->owner = NULL;
+	 *	raw_spin_unlock(&lock->wait_lock);
+	 */
+	while (!rt_mutex_has_waiters(lock)) {
+		/* Drops lock->wait_lock ! */
+		if (unlock_rt_mutex_safe(lock) == true)
+			return;
+		/* Relock the rtmutex and try again */
+		raw_spin_lock(&lock->wait_lock);
 	}
 
+	/*
+	 * The wakeup next waiter path does not suffer from the above
+	 * race. See the comments there.
+	 */
 	wakeup_next_waiter(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
@@ -881,30 +1319,31 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
  */
 static inline int
 rt_mutex_fastlock(struct rt_mutex *lock, int state,
-		  int detect_deadlock,
 		  int (*slowfn)(struct rt_mutex *lock, int state,
 				struct hrtimer_sleeper *timeout,
-				int detect_deadlock))
+				enum rtmutex_chainwalk chwalk))
 {
-	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+	if (likely(rt_mutex_cmpxchg(lock, NULL, current))) {
 		rt_mutex_deadlock_account_lock(lock, current);
 		return 0;
 	} else
-		return slowfn(lock, state, NULL, detect_deadlock);
+		return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
 }
 
 static inline int
 rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
-			struct hrtimer_sleeper *timeout, int detect_deadlock,
+			struct hrtimer_sleeper *timeout,
+			enum rtmutex_chainwalk chwalk,
 			int (*slowfn)(struct rt_mutex *lock, int state,
 				      struct hrtimer_sleeper *timeout,
-				      int detect_deadlock))
+				      enum rtmutex_chainwalk chwalk))
 {
-	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
+	    likely(rt_mutex_cmpxchg(lock, NULL, current))) {
 		rt_mutex_deadlock_account_lock(lock, current);
 		return 0;
 	} else
-		return slowfn(lock, state, timeout, detect_deadlock);
+		return slowfn(lock, state, timeout, chwalk);
 }
 
 static inline int
@@ -937,54 +1376,61 @@ void __sched rt_mutex_lock(struct rt_mutex *lock)
 {
 	might_sleep();
 
-	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, rt_mutex_slowlock);
+	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock);
 
 /**
  * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
  *
- * @lock: 		the rt_mutex to be locked
- * @detect_deadlock:	deadlock detection on/off
+ * @lock:		the rt_mutex to be locked
  *
  * Returns:
- *  0 		on success
- * -EINTR 	when interrupted by a signal
- * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
+ *  0		on success
+ * -EINTR	when interrupted by a signal
  */
-int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock,
-						 int detect_deadlock)
+int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 {
 	might_sleep();
 
-	return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE,
-				 detect_deadlock, rt_mutex_slowlock);
+	return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
+/*
+ * Futex variant with full deadlock detection.
+ */
+int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
+			      struct hrtimer_sleeper *timeout)
+{
+	might_sleep();
+
+	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
+				       RT_MUTEX_FULL_CHAINWALK,
+				       rt_mutex_slowlock);
+}
+
 /**
  * rt_mutex_timed_lock - lock a rt_mutex interruptible
  *			the timeout structure is provided
  *			by the caller
  *
- * @lock: 		the rt_mutex to be locked
+ * @lock:		the rt_mutex to be locked
  * @timeout:		timeout structure or NULL (no timeout)
- * @detect_deadlock:	deadlock detection on/off
  *
  * Returns:
- *  0 		on success
- * -EINTR 	when interrupted by a signal
+ *  0		on success
+ * -EINTR	when interrupted by a signal
  * -ETIMEDOUT	when the timeout expired
- * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
  */
 int
-rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout,
-		    int detect_deadlock)
+rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
 {
 	might_sleep();
 
 	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
-				       detect_deadlock, rt_mutex_slowlock);
+				       RT_MUTEX_MIN_CHAINWALK,
+				       rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
 
@@ -1090,7 +1536,6 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
  * @lock:		the rt_mutex to take
  * @waiter:		the pre-initialized rt_mutex_waiter
  * @task:		the task to prepare
- * @detect_deadlock:	perform deadlock detection (1) or not (0)
  *
  * Returns:
  *  0 - task blocked on lock
@@ -1101,7 +1546,7 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
  */
 int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
-			      struct task_struct *task, int detect_deadlock)
+			      struct task_struct *task)
 {
 	int ret;
 
@@ -1112,7 +1557,9 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		return 1;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
+	/* We enforce deadlock detection for futexes */
+	ret = task_blocks_on_rt_mutex(lock, waiter, task,
+				      RT_MUTEX_FULL_CHAINWALK);
 
 	if (ret && !rt_mutex_owner(lock)) {
 		/*
@@ -1158,22 +1605,20 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
  * rt_mutex_finish_proxy_lock() - Complete lock acquisition
  * @lock:		the rt_mutex we were woken on
  * @to:			the timeout, null if none. hrtimer should already have
- * 			been started.
+ *			been started.
  * @waiter:		the pre-initialized rt_mutex_waiter
- * @detect_deadlock:	perform deadlock detection (1) or not (0)
  *
  * Complete the lock acquisition started our behalf by another thread.
  *
  * Returns:
  *  0 - success
- * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
+ * <0 - error, one of -EINTR, -ETIMEDOUT
  *
  * Special API call for PI-futex requeue support
  */
 int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *to,
-			       struct rt_mutex_waiter *waiter,
-			       int detect_deadlock)
+			       struct rt_mutex_waiter *waiter)
 {
 	int ret;
 
diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h
index a1a1dd06421..c4060584c40 100644
--- a/kernel/locking/rtmutex.h
+++ b/kernel/locking/rtmutex.h
@@ -22,5 +22,15 @@
 #define debug_rt_mutex_init(m, n)			do { } while (0)
 #define debug_rt_mutex_deadlock(d, a ,l)		do { } while (0)
 #define debug_rt_mutex_print_deadlock(w)		do { } while (0)
-#define debug_rt_mutex_detect_deadlock(w,d)		(d)
 #define debug_rt_mutex_reset_waiter(w)			do { } while (0)
+
+static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
+{
+	WARN(1, "rtmutex deadlock detected\n");
+}
+
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w,
+						  enum rtmutex_chainwalk walk)
+{
+	return walk == RT_MUTEX_FULL_CHAINWALK;
+}
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 7431a9c86f3..85521250140 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -102,6 +102,21 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 }
 
 /*
+ * Constants for rt mutex functions which have a selectable deadlock
+ * detection.
+ *
+ * RT_MUTEX_MIN_CHAINWALK:	Stops the lock chain walk when there are
+ *				no further PI adjustments to be made.
+ *
+ * RT_MUTEX_FULL_CHAINWALK:	Invoke deadlock detection with a full
+ *				walk of the lock chain.
+ */
+enum rtmutex_chainwalk {
+	RT_MUTEX_MIN_CHAINWALK,
+	RT_MUTEX_FULL_CHAINWALK,
+};
+
+/*
  * PI-futex support (proxy locking functions, etc.):
  */
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
@@ -111,12 +126,11 @@ extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
-				     struct task_struct *task,
-				     int detect_deadlock);
+				     struct task_struct *task);
 extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 				      struct hrtimer_sleeper *to,
-				      struct rt_mutex_waiter *waiter,
-				      int detect_deadlock);
+				      struct rt_mutex_waiter *waiter);
+extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 9be8a914497..2c93571162c 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -26,7 +26,7 @@ int rwsem_is_locked(struct rw_semaphore *sem)
 	unsigned long flags;
 
 	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
-		ret = (sem->activity != 0);
+		ret = (sem->count != 0);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 	}
 	return ret;
@@ -46,7 +46,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
 	lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
-	sem->activity = 0;
+	sem->count = 0;
 	raw_spin_lock_init(&sem->wait_lock);
 	INIT_LIST_HEAD(&sem->wait_list);
 }
@@ -95,7 +95,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
 		waiter = list_entry(next, struct rwsem_waiter, list);
 	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
 
-	sem->activity += woken;
+	sem->count += woken;
 
  out:
 	return sem;
@@ -126,9 +126,9 @@ void __sched __down_read(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
 		/* granted */
-		sem->activity++;
+		sem->count++;
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		goto out;
 	}
@@ -170,9 +170,9 @@ int __down_read_trylock(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
 		/* granted */
-		sem->activity++;
+		sem->count++;
 		ret = 1;
 	}
 
@@ -206,7 +206,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 		 * itself into sleep and waiting for system woke it or someone
 		 * else in the head of the wait list up.
 		 */
-		if (sem->activity == 0)
+		if (sem->count == 0)
 			break;
 		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
@@ -214,7 +214,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 		raw_spin_lock_irqsave(&sem->wait_lock, flags);
 	}
 	/* got the lock */
-	sem->activity = -1;
+	sem->count = -1;
 	list_del(&waiter.list);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
@@ -235,9 +235,9 @@ int __down_write_trylock(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	if (sem->activity == 0) {
+	if (sem->count == 0) {
 		/* got the lock */
-		sem->activity = -1;
+		sem->count = -1;
 		ret = 1;
 	}
 
@@ -255,7 +255,7 @@ void __up_read(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	if (--sem->activity == 0 && !list_empty(&sem->wait_list))
+	if (--sem->count == 0 && !list_empty(&sem->wait_list))
 		sem = __rwsem_wake_one_writer(sem);
 
 	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
@@ -270,7 +270,7 @@ void __up_write(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	sem->activity = 0;
+	sem->count = 0;
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 1);
 
@@ -287,7 +287,7 @@ void __downgrade_write(struct rw_semaphore *sem)
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
-	sem->activity = 1;
+	sem->count = 1;
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 0);
 
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index b4219ff87b8..d6203faf2eb 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -5,11 +5,17 @@
  *
  * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
  * and Michel Lespinasse <walken@google.com>
+ *
+ * Optimistic spinning by Tim Chen <tim.c.chen@intel.com>
+ * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes.
  */
 #include <linux/rwsem.h>
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/export.h>
+#include <linux/sched/rt.h>
+
+#include "mcs_spinlock.h"
 
 /*
  * Guide to the rw_semaphore's count field for common values.
@@ -76,6 +82,10 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	sem->count = RWSEM_UNLOCKED_VALUE;
 	raw_spin_lock_init(&sem->wait_lock);
 	INIT_LIST_HEAD(&sem->wait_list);
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+	sem->owner = NULL;
+	osq_lock_init(&sem->osq);
+#endif
 }
 
 EXPORT_SYMBOL(__init_rwsem);
@@ -190,7 +200,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
 }
 
 /*
- * wait for the read lock to be granted
+ * Wait for the read lock to be granted
  */
 __visible
 struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
@@ -237,64 +247,221 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 	return sem;
 }
 
+static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
+{
+	if (!(count & RWSEM_ACTIVE_MASK)) {
+		/* try acquiring the write lock */
+		if (sem->count == RWSEM_WAITING_BIAS &&
+		    cmpxchg(&sem->count, RWSEM_WAITING_BIAS,
+			    RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) {
+			if (!list_is_singular(&sem->wait_list))
+				rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
+			return true;
+		}
+	}
+	return false;
+}
+
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 /*
- * wait until we successfully acquire the write lock
+ * Try to acquire write lock before the writer has been put on wait queue.
+ */
+static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
+{
+	long old, count = ACCESS_ONCE(sem->count);
+
+	while (true) {
+		if (!(count == 0 || count == RWSEM_WAITING_BIAS))
+			return false;
+
+		old = cmpxchg(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS);
+		if (old == count)
+			return true;
+
+		count = old;
+	}
+}
+
+static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
+{
+	struct task_struct *owner;
+	bool on_cpu = false;
+
+	if (need_resched())
+		return false;
+
+	rcu_read_lock();
+	owner = ACCESS_ONCE(sem->owner);
+	if (owner)
+		on_cpu = owner->on_cpu;
+	rcu_read_unlock();
+
+	/*
+	 * If sem->owner is not set, yet we have just recently entered the
+	 * slowpath, then there is a possibility reader(s) may have the lock.
+	 * To be safe, avoid spinning in these situations.
+	 */
+	return on_cpu;
+}
+
+static inline bool owner_running(struct rw_semaphore *sem,
+				 struct task_struct *owner)
+{
+	if (sem->owner != owner)
+		return false;
+
+	/*
+	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
+	 * sem->owner still matches owner, if that fails, owner might
+	 * point to free()d memory, if it still matches, the rcu_read_lock()
+	 * ensures the memory stays valid.
+	 */
+	barrier();
+
+	return owner->on_cpu;
+}
+
+static noinline
+bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
+{
+	rcu_read_lock();
+	while (owner_running(sem, owner)) {
+		if (need_resched())
+			break;
+
+		cpu_relax_lowlatency();
+	}
+	rcu_read_unlock();
+
+	/*
+	 * We break out the loop above on need_resched() or when the
+	 * owner changed, which is a sign for heavy contention. Return
+	 * success only when sem->owner is NULL.
+	 */
+	return sem->owner == NULL;
+}
+
+static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
+{
+	struct task_struct *owner;
+	bool taken = false;
+
+	preempt_disable();
+
+	/* sem->wait_lock should not be held when doing optimistic spinning */
+	if (!rwsem_can_spin_on_owner(sem))
+		goto done;
+
+	if (!osq_lock(&sem->osq))
+		goto done;
+
+	while (true) {
+		owner = ACCESS_ONCE(sem->owner);
+		if (owner && !rwsem_spin_on_owner(sem, owner))
+			break;
+
+		/* wait_lock will be acquired if write_lock is obtained */
+		if (rwsem_try_write_lock_unqueued(sem)) {
+			taken = true;
+			break;
+		}
+
+		/*
+		 * When there's no owner, we might have preempted between the
+		 * owner acquiring the lock and setting the owner field. If
+		 * we're an RT task that will live-lock because we won't let
+		 * the owner complete.
+		 */
+		if (!owner && (need_resched() || rt_task(current)))
+			break;
+
+		/*
+		 * The cpu_relax() call is a compiler barrier which forces
+		 * everything in this loop to be re-loaded. We don't need
+		 * memory barriers as we'll eventually observe the right
+		 * values at the cost of a few extra spins.
+		 */
+		cpu_relax_lowlatency();
+	}
+	osq_unlock(&sem->osq);
+done:
+	preempt_enable();
+	return taken;
+}
+
+#else
+static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
+{
+	return false;
+}
+#endif
+
+/*
+ * Wait until we successfully acquire the write lock
  */
 __visible
 struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 {
-	long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS;
+	long count;
+	bool waiting = true; /* any queued threads before us */
 	struct rwsem_waiter waiter;
-	struct task_struct *tsk = current;
 
-	/* set up my own style of waitqueue */
-	waiter.task = tsk;
+	/* undo write bias from down_write operation, stop active locking */
+	count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem);
+
+	/* do optimistic spinning and steal lock if possible */
+	if (rwsem_optimistic_spin(sem))
+		return sem;
+
+	/*
+	 * Optimistic spinning failed, proceed to the slowpath
+	 * and block until we can acquire the sem.
+	 */
+	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_WRITE;
 
 	raw_spin_lock_irq(&sem->wait_lock);
+
+	/* account for this before adding a new element to the list */
 	if (list_empty(&sem->wait_list))
-		adjustment += RWSEM_WAITING_BIAS;
+		waiting = false;
+
 	list_add_tail(&waiter.list, &sem->wait_list);
 
 	/* we're now waiting on the lock, but no longer actively locking */
-	count = rwsem_atomic_update(adjustment, sem);
+	if (waiting) {
+		count = ACCESS_ONCE(sem->count);
 
-	/* If there were already threads queued before us and there are no
-	 * active writers, the lock must be read owned; so we try to wake
-	 * any read locks that were queued ahead of us. */
-	if (count > RWSEM_WAITING_BIAS &&
-	    adjustment == -RWSEM_ACTIVE_WRITE_BIAS)
-		sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS);
+		/*
+		 * If there were already threads queued before us and there are
+		 * no active writers, the lock must be read owned; so we try to
+		 * wake any read locks that were queued ahead of us.
+		 */
+		if (count > RWSEM_WAITING_BIAS)
+			sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS);
+
+	} else
+		count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
 
 	/* wait until we successfully acquire the lock */
-	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	set_current_state(TASK_UNINTERRUPTIBLE);
 	while (true) {
-		if (!(count & RWSEM_ACTIVE_MASK)) {
-			/* Try acquiring the write lock. */
-			count = RWSEM_ACTIVE_WRITE_BIAS;
-			if (!list_is_singular(&sem->wait_list))
-				count += RWSEM_WAITING_BIAS;
-
-			if (sem->count == RWSEM_WAITING_BIAS &&
-			    cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) ==
-							RWSEM_WAITING_BIAS)
-				break;
-		}
-
+		if (rwsem_try_write_lock(count, sem))
+			break;
 		raw_spin_unlock_irq(&sem->wait_lock);
 
 		/* Block until there are no active lockers. */
 		do {
 			schedule();
-			set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+			set_current_state(TASK_UNINTERRUPTIBLE);
 		} while ((count = sem->count) & RWSEM_ACTIVE_MASK);
 
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
+	__set_current_state(TASK_RUNNING);
 
 	list_del(&waiter.list);
 	raw_spin_unlock_irq(&sem->wait_lock);
-	tsk->state = TASK_RUNNING;
 
 	return sem;
 }
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index cfff1435bdf..e2d3bc7f03b 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -12,6 +12,27 @@
 
 #include <linux/atomic.h>
 
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+static inline void rwsem_set_owner(struct rw_semaphore *sem)
+{
+	sem->owner = current;
+}
+
+static inline void rwsem_clear_owner(struct rw_semaphore *sem)
+{
+	sem->owner = NULL;
+}
+
+#else
+static inline void rwsem_set_owner(struct rw_semaphore *sem)
+{
+}
+
+static inline void rwsem_clear_owner(struct rw_semaphore *sem)
+{
+}
+#endif
+
 /*
  * lock for reading
  */
@@ -48,6 +69,7 @@ void __sched down_write(struct rw_semaphore *sem)
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
+	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(down_write);
@@ -59,8 +81,11 @@ int down_write_trylock(struct rw_semaphore *sem)
 {
 	int ret = __down_write_trylock(sem);
 
-	if (ret == 1)
+	if (ret == 1) {
 		rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_);
+		rwsem_set_owner(sem);
+	}
+
 	return ret;
 }
 
@@ -85,6 +110,7 @@ void up_write(struct rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, 1, _RET_IP_);
 
+	rwsem_clear_owner(sem);
 	__up_write(sem);
 }
 
@@ -99,6 +125,7 @@ void downgrade_write(struct rw_semaphore *sem)
 	 * lockdep: a downgraded write will live on as a write
 	 * dependency.
 	 */
+	rwsem_clear_owner(sem);
 	__downgrade_write(sem);
 }
 
@@ -122,6 +149,7 @@ void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
 	rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
+	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(_down_write_nest_lock);
@@ -141,6 +169,7 @@ void down_write_nested(struct rw_semaphore *sem, int subclass)
 	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
+	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(down_write_nested);
diff --git a/kernel/module.c b/kernel/module.c
index 079c4615607..ae79ce615cb 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -60,7 +60,6 @@
 #include <linux/jump_label.h>
 #include <linux/pfn.h>
 #include <linux/bsearch.h>
-#include <linux/fips.h>
 #include <uapi/linux/module.h>
 #include "module-internal.h"
 
@@ -2448,9 +2447,6 @@ static int module_sig_check(struct load_info *info)
 	}
 
 	/* Not having a signature is only an error if we're strict. */
-	if (err < 0 && fips_enabled)
-		panic("Module verification failed with error %d in FIPS mode\n",
-		      err);
 	if (err == -ENOKEY && !sig_enforce)
 		err = 0;
 
@@ -3020,21 +3016,6 @@ static int do_init_module(struct module *mod)
 	 */
 	current->flags &= ~PF_USED_ASYNC;
 
-	blocking_notifier_call_chain(&module_notify_list,
-			MODULE_STATE_COMING, mod);
-
-	/* Set RO and NX regions for core */
-	set_section_ro_nx(mod->module_core,
-				mod->core_text_size,
-				mod->core_ro_size,
-				mod->core_size);
-
-	/* Set RO and NX regions for init */
-	set_section_ro_nx(mod->module_init,
-				mod->init_text_size,
-				mod->init_ro_size,
-				mod->init_size);
-
 	do_mod_ctors(mod);
 	/* Start the module */
 	if (mod->init != NULL)
@@ -3165,9 +3146,26 @@ static int complete_formation(struct module *mod, struct load_info *info)
 	/* This relies on module_mutex for list integrity. */
 	module_bug_finalize(info->hdr, info->sechdrs, mod);
 
+	/* Set RO and NX regions for core */
+	set_section_ro_nx(mod->module_core,
+				mod->core_text_size,
+				mod->core_ro_size,
+				mod->core_size);
+
+	/* Set RO and NX regions for init */
+	set_section_ro_nx(mod->module_init,
+				mod->init_text_size,
+				mod->init_ro_size,
+				mod->init_size);
+
 	/* Mark state as coming so strong_try_module_get() ignores us,
 	 * but kallsyms etc. can see us. */
 	mod->state = MODULE_STATE_COMING;
+	mutex_unlock(&module_mutex);
+
+	blocking_notifier_call_chain(&module_notify_list,
+				     MODULE_STATE_COMING, mod);
+	return 0;
 
 out:
 	mutex_unlock(&module_mutex);
@@ -3190,6 +3188,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 {
 	struct module *mod;
 	long err;
+	char *after_dashes;
 
 	err = module_sig_check(info);
 	if (err)
@@ -3277,10 +3276,15 @@ static int load_module(struct load_info *info, const char __user *uargs,
 		goto ddebug_cleanup;
 
 	/* Module is ready to execute: parsing args may do that. */
-	err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp,
-			 -32768, 32767, unknown_module_param_cb);
-	if (err < 0)
+	after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp,
+				  -32768, 32767, unknown_module_param_cb);
+	if (IS_ERR(after_dashes)) {
+		err = PTR_ERR(after_dashes);
 		goto bug_cleanup;
+	} else if (after_dashes) {
+		pr_warn("%s: parameters '%s' after `--' ignored\n",
+		       mod->name, after_dashes);
+	}
 
 	/* Link in to syfs. */
 	err = mod_sysfs_setup(mod, info, mod->kp, mod->num_kp);
diff --git a/kernel/notifier.c b/kernel/notifier.c
index db4c8b08a50..4803da6eab6 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -71,9 +71,9 @@ static int notifier_chain_unregister(struct notifier_block **nl,
  *	@returns:	notifier_call_chain returns the value returned by the
  *			last notifier function called.
  */
-static int __kprobes notifier_call_chain(struct notifier_block **nl,
-					unsigned long val, void *v,
-					int nr_to_call,	int *nr_calls)
+static int notifier_call_chain(struct notifier_block **nl,
+			       unsigned long val, void *v,
+			       int nr_to_call, int *nr_calls)
 {
 	int ret = NOTIFY_DONE;
 	struct notifier_block *nb, *next_nb;
@@ -102,6 +102,7 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl,
 	}
 	return ret;
 }
+NOKPROBE_SYMBOL(notifier_call_chain);
 
 /*
  *	Atomic notifier chain routines.  Registration and unregistration
@@ -172,9 +173,9 @@ EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
  *	Otherwise the return value is the return value
  *	of the last notifier function called.
  */
-int __kprobes __atomic_notifier_call_chain(struct atomic_notifier_head *nh,
-					unsigned long val, void *v,
-					int nr_to_call, int *nr_calls)
+int __atomic_notifier_call_chain(struct atomic_notifier_head *nh,
+				 unsigned long val, void *v,
+				 int nr_to_call, int *nr_calls)
 {
 	int ret;
 
@@ -184,13 +185,15 @@ int __kprobes __atomic_notifier_call_chain(struct atomic_notifier_head *nh,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(__atomic_notifier_call_chain);
+NOKPROBE_SYMBOL(__atomic_notifier_call_chain);
 
-int __kprobes atomic_notifier_call_chain(struct atomic_notifier_head *nh,
-		unsigned long val, void *v)
+int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
+			       unsigned long val, void *v)
 {
 	return __atomic_notifier_call_chain(nh, val, v, -1, NULL);
 }
 EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);
+NOKPROBE_SYMBOL(atomic_notifier_call_chain);
 
 /*
  *	Blocking notifier chain routines.  All access to the chain is
@@ -527,7 +530,7 @@ EXPORT_SYMBOL_GPL(srcu_init_notifier_head);
 
 static ATOMIC_NOTIFIER_HEAD(die_chain);
 
-int notrace __kprobes notify_die(enum die_val val, const char *str,
+int notrace notify_die(enum die_val val, const char *str,
 	       struct pt_regs *regs, long err, int trap, int sig)
 {
 	struct die_args args = {
@@ -540,6 +543,7 @@ int notrace __kprobes notify_die(enum die_val val, const char *str,
 	};
 	return atomic_notifier_call_chain(&die_chain, val, &args);
 }
+NOKPROBE_SYMBOL(notify_die);
 
 int register_die_notifier(struct notifier_block *nb)
 {
diff --git a/kernel/params.c b/kernel/params.c
index b00142e7f3b..1e52ca233fd 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -177,13 +177,13 @@ static char *next_arg(char *args, char **param, char **val)
 }
 
 /* Args looks like "foo=bar,bar2 baz=fuz wiz". */
-int parse_args(const char *doing,
-	       char *args,
-	       const struct kernel_param *params,
-	       unsigned num,
-	       s16 min_level,
-	       s16 max_level,
-	       int (*unknown)(char *param, char *val, const char *doing))
+char *parse_args(const char *doing,
+		 char *args,
+		 const struct kernel_param *params,
+		 unsigned num,
+		 s16 min_level,
+		 s16 max_level,
+		 int (*unknown)(char *param, char *val, const char *doing))
 {
 	char *param, *val;
 
@@ -198,6 +198,9 @@ int parse_args(const char *doing,
 		int irq_was_disabled;
 
 		args = next_arg(args, &param, &val);
+		/* Stop at -- */
+		if (!val && strcmp(param, "--") == 0)
+			return args;
 		irq_was_disabled = irqs_disabled();
 		ret = parse_one(param, val, doing, params, num,
 				min_level, max_level, unknown);
@@ -208,22 +211,22 @@ int parse_args(const char *doing,
 		switch (ret) {
 		case -ENOENT:
 			pr_err("%s: Unknown parameter `%s'\n", doing, param);
-			return ret;
+			return ERR_PTR(ret);
 		case -ENOSPC:
 			pr_err("%s: `%s' too large for parameter `%s'\n",
 			       doing, val ?: "", param);
-			return ret;
+			return ERR_PTR(ret);
 		case 0:
 			break;
 		default:
 			pr_err("%s: `%s' invalid for parameter `%s'\n",
 			       doing, val ?: "", param);
-			return ret;
+			return ERR_PTR(ret);
 		}
 	}
 
 	/* All parsed OK. */
-	return 0;
+	return NULL;
 }
 
 /* Lazy bastard, eh? */
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index df88d55dc43..a9dfa79b6ba 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -28,12 +28,14 @@
 #include <linux/syscore_ops.h>
 #include <linux/ctype.h>
 #include <linux/genhd.h>
+#include <trace/events/power.h>
 
 #include "power.h"
 
 
 static int nocompress;
 static int noresume;
+static int nohibernate;
 static int resume_wait;
 static unsigned int resume_delay;
 static char resume_file[256] = CONFIG_PM_STD_PARTITION;
@@ -61,6 +63,11 @@ bool freezer_test_done;
 
 static const struct platform_hibernation_ops *hibernation_ops;
 
+bool hibernation_available(void)
+{
+	return (nohibernate == 0);
+}
+
 /**
  * hibernation_set_ops - Set the global hibernate operations.
  * @ops: Hibernation operations to use in subsequent hibernation transitions.
@@ -292,7 +299,9 @@ static int create_image(int platform_mode)
 
 	in_suspend = 1;
 	save_processor_state();
+	trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true);
 	error = swsusp_arch_suspend();
+	trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
 	if (error)
 		printk(KERN_ERR "PM: Error %d creating hibernation image\n",
 			error);
@@ -362,7 +371,6 @@ int hibernation_snapshot(int platform_mode)
 	}
 
 	suspend_console();
-	ftrace_stop();
 	pm_restrict_gfp_mask();
 
 	error = dpm_suspend(PMSG_FREEZE);
@@ -388,7 +396,6 @@ int hibernation_snapshot(int platform_mode)
 	if (error || !in_suspend)
 		pm_restore_gfp_mask();
 
-	ftrace_start();
 	resume_console();
 	dpm_complete(msg);
 
@@ -491,7 +498,6 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	suspend_console();
-	ftrace_stop();
 	pm_restrict_gfp_mask();
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
@@ -499,7 +505,6 @@ int hibernation_restore(int platform_mode)
 		dpm_resume_end(PMSG_RECOVER);
 	}
 	pm_restore_gfp_mask();
-	ftrace_start();
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -526,7 +531,6 @@ int hibernation_platform_enter(void)
 
 	entering_platform_hibernation = true;
 	suspend_console();
-	ftrace_stop();
 	error = dpm_suspend_start(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
@@ -570,7 +574,6 @@ int hibernation_platform_enter(void)
  Resume_devices:
 	entering_platform_hibernation = false;
 	dpm_resume_end(PMSG_RESTORE);
-	ftrace_start();
 	resume_console();
 
  Close:
@@ -639,6 +642,11 @@ int hibernate(void)
 {
 	int error;
 
+	if (!hibernation_available()) {
+		pr_debug("PM: Hibernation not available.\n");
+		return -EPERM;
+	}
+
 	lock_system_sleep();
 	/* The snapshot device should not be opened while we're running */
 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
@@ -731,7 +739,7 @@ static int software_resume(void)
 	/*
 	 * If the user said "noresume".. bail out early.
 	 */
-	if (noresume)
+	if (noresume || !hibernation_available())
 		return 0;
 
 	/*
@@ -897,6 +905,9 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
 	int i;
 	char *start = buf;
 
+	if (!hibernation_available())
+		return sprintf(buf, "[disabled]\n");
+
 	for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) {
 		if (!hibernation_modes[i])
 			continue;
@@ -931,6 +942,9 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 	char *p;
 	int mode = HIBERNATION_INVALID;
 
+	if (!hibernation_available())
+		return -EPERM;
+
 	p = memchr(buf, '\n', n);
 	len = p ? p - buf : n;
 
@@ -1098,6 +1112,10 @@ static int __init hibernate_setup(char *str)
 		noresume = 1;
 	else if (!strncmp(str, "nocompress", 10))
 		nocompress = 1;
+	else if (!strncmp(str, "no", 2)) {
+		noresume = 1;
+		nohibernate = 1;
+	}
 	return 1;
 }
 
@@ -1122,9 +1140,23 @@ static int __init resumedelay_setup(char *str)
 	return 1;
 }
 
+static int __init nohibernate_setup(char *str)
+{
+	noresume = 1;
+	nohibernate = 1;
+	return 1;
+}
+
+static int __init kaslr_nohibernate_setup(char *str)
+{
+	return nohibernate_setup(str);
+}
+
 __setup("noresume", noresume_setup);
 __setup("resume_offset=", resume_offset_setup);
 __setup("resume=", resume_setup);
 __setup("hibernate=", hibernate_setup);
 __setup("resumewait", resumewait_setup);
 __setup("resumedelay=", resumedelay_setup);
+__setup("nohibernate", nohibernate_setup);
+__setup("kaslr", kaslr_nohibernate_setup);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 573410d6647..8e90f330f13 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -300,13 +300,11 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
 			s += sprintf(s,"%s ", pm_states[i].label);
 
 #endif
-#ifdef CONFIG_HIBERNATION
-	s += sprintf(s, "%s\n", "disk");
-#else
+	if (hibernation_available())
+		s += sprintf(s, "disk ");
 	if (s != buf)
 		/* convert the last space to a newline */
 		*(s-1) = '\n';
-#endif
 	return (s - buf);
 }
 
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 06ec8869dbf..4ee194eb524 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -17,6 +17,7 @@
 #include <linux/delay.h>
 #include <linux/workqueue.h>
 #include <linux/kmod.h>
+#include <trace/events/power.h>
 
 /* 
  * Timeout for stopping processes
@@ -175,6 +176,7 @@ void thaw_processes(void)
 	struct task_struct *g, *p;
 	struct task_struct *curr = current;
 
+	trace_suspend_resume(TPS("thaw_processes"), 0, true);
 	if (pm_freezing)
 		atomic_dec(&system_freezing_cnt);
 	pm_freezing = false;
@@ -184,6 +186,7 @@ void thaw_processes(void)
 
 	printk("Restarting tasks ... ");
 
+	__usermodehelper_set_disable_depth(UMH_FREEZING);
 	thaw_workqueues();
 
 	read_lock(&tasklist_lock);
@@ -201,6 +204,7 @@ void thaw_processes(void)
 
 	schedule();
 	printk("done.\n");
+	trace_suspend_resume(TPS("thaw_processes"), 0, false);
 }
 
 void thaw_kernel_threads(void)
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 963e6d0f050..4b736b4dfa9 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -177,7 +177,9 @@ static int suspend_prepare(suspend_state_t state)
 	if (error)
 		goto Finish;
 
+	trace_suspend_resume(TPS("freeze_processes"), 0, true);
 	error = suspend_freeze_processes();
+	trace_suspend_resume(TPS("freeze_processes"), 0, false);
 	if (!error)
 		return 0;
 
@@ -240,11 +242,12 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	 * all the devices are suspended.
 	 */
 	if (state == PM_SUSPEND_FREEZE) {
+		trace_suspend_resume(TPS("machine_suspend"), state, true);
 		freeze_enter();
+		trace_suspend_resume(TPS("machine_suspend"), state, false);
 		goto Platform_wake;
 	}
 
-	ftrace_stop();
 	error = disable_nonboot_cpus();
 	if (error || suspend_test(TEST_CPUS))
 		goto Enable_cpus;
@@ -256,7 +259,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	if (!error) {
 		*wakeup = pm_wakeup_pending();
 		if (!(suspend_test(TEST_CORE) || *wakeup)) {
+			trace_suspend_resume(TPS("machine_suspend"),
+				state, true);
 			error = suspend_ops->enter(state);
+			trace_suspend_resume(TPS("machine_suspend"),
+				state, false);
 			events_check_enabled = false;
 		}
 		syscore_resume();
@@ -267,7 +274,6 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 
  Enable_cpus:
 	enable_nonboot_cpus();
-	ftrace_start();
 
  Platform_wake:
 	if (need_suspend_ops(state) && suspend_ops->wake)
@@ -294,12 +300,11 @@ int suspend_devices_and_enter(suspend_state_t state)
 	if (need_suspend_ops(state) && !suspend_ops)
 		return -ENOSYS;
 
-	trace_machine_suspend(state);
 	if (need_suspend_ops(state) && suspend_ops->begin) {
 		error = suspend_ops->begin(state);
 		if (error)
 			goto Close;
-	} else if (state == PM_SUSPEND_FREEZE && freeze_ops->begin) {
+	} else if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->begin) {
 		error = freeze_ops->begin();
 		if (error)
 			goto Close;
@@ -328,10 +333,9 @@ int suspend_devices_and_enter(suspend_state_t state)
  Close:
 	if (need_suspend_ops(state) && suspend_ops->end)
 		suspend_ops->end();
-	else if (state == PM_SUSPEND_FREEZE && freeze_ops->end)
+	else if (state == PM_SUSPEND_FREEZE && freeze_ops && freeze_ops->end)
 		freeze_ops->end();
 
-	trace_machine_suspend(PWR_EVENT_EXIT);
 	return error;
 
  Recover_platform:
@@ -365,6 +369,7 @@ static int enter_state(suspend_state_t state)
 {
 	int error;
 
+	trace_suspend_resume(TPS("suspend_enter"), state, true);
 	if (state == PM_SUSPEND_FREEZE) {
 #ifdef CONFIG_PM_DEBUG
 		if (pm_test_level != TEST_NONE && pm_test_level <= TEST_CPUS) {
@@ -382,9 +387,11 @@ static int enter_state(suspend_state_t state)
 	if (state == PM_SUSPEND_FREEZE)
 		freeze_begin();
 
+	trace_suspend_resume(TPS("sync_filesystems"), 0, true);
 	printk(KERN_INFO "PM: Syncing filesystems ... ");
 	sys_sync();
 	printk("done.\n");
+	trace_suspend_resume(TPS("sync_filesystems"), 0, false);
 
 	pr_debug("PM: Preparing system for %s sleep\n", pm_states[state].label);
 	error = suspend_prepare(state);
@@ -394,6 +401,7 @@ static int enter_state(suspend_state_t state)
 	if (suspend_test(TEST_FREEZER))
 		goto Finish;
 
+	trace_suspend_resume(TPS("suspend_enter"), state, false);
 	pr_debug("PM: Entering %s sleep\n", pm_states[state].label);
 	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 98d357584cd..526e8911460 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -49,6 +49,9 @@ static int snapshot_open(struct inode *inode, struct file *filp)
 	struct snapshot_data *data;
 	int error;
 
+	if (!hibernation_available())
+		return -EPERM;
+
 	lock_system_sleep();
 
 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ea2d5f6962e..13e839dbca0 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1416,9 +1416,10 @@ static int have_callable_console(void)
 /*
  * Can we actually use the console at this time on this cpu?
  *
- * Console drivers may assume that per-cpu resources have been allocated. So
- * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't
- * call them until this CPU is officially up.
+ * Console drivers may assume that per-cpu resources have
+ * been allocated. So unless they're explicitly marked as
+ * being able to cope (CON_ANYTIME) don't call them until
+ * this CPU is officially up.
  */
 static inline int can_use_console(unsigned int cpu)
 {
@@ -1431,10 +1432,8 @@ static inline int can_use_console(unsigned int cpu)
  * console_lock held, and 'console_locked' set) if it
  * is successful, false otherwise.
  */
-static int console_trylock_for_printk(void)
+static int console_trylock_for_printk(unsigned int cpu)
 {
-	unsigned int cpu = smp_processor_id();
-
 	if (!console_trylock())
 		return 0;
 	/*
@@ -1609,8 +1608,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 		 */
 		if (!oops_in_progress && !lockdep_recursing(current)) {
 			recursion_bug = 1;
-			local_irq_restore(flags);
-			return 0;
+			goto out_restore_irqs;
 		}
 		zap_locks();
 	}
@@ -1718,27 +1716,21 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	logbuf_cpu = UINT_MAX;
 	raw_spin_unlock(&logbuf_lock);
-	lockdep_on();
-	local_irq_restore(flags);
 
 	/* If called from the scheduler, we can not call up(). */
-	if (in_sched)
-		return printed_len;
-
-	/*
-	 * Disable preemption to avoid being preempted while holding
-	 * console_sem which would prevent anyone from printing to console
-	 */
-	preempt_disable();
-	/*
-	 * Try to acquire and then immediately release the console semaphore.
-	 * The release will print out buffers and wake up /dev/kmsg and syslog()
-	 * users.
-	 */
-	if (console_trylock_for_printk())
-		console_unlock();
-	preempt_enable();
+	if (!in_sched) {
+		/*
+		 * Try to acquire and then immediately release the console
+		 * semaphore.  The release will print out buffers and wake up
+		 * /dev/kmsg and syslog() users.
+		 */
+		if (console_trylock_for_printk(this_cpu))
+			console_unlock();
+	}
 
+	lockdep_on();
+out_restore_irqs:
+	local_irq_restore(flags);
 	return printed_len;
 }
 EXPORT_SYMBOL(vprintk_emit);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index adf98622cb3..54e75226c2c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -28,12 +28,6 @@
 #include <linux/compat.h>
 
 
-static int ptrace_trapping_sleep_fn(void *flags)
-{
-	schedule();
-	return 0;
-}
-
 /*
  * ptrace a task: make the debugger its new parent and
  * move it to the ptrace list.
@@ -371,7 +365,7 @@ unlock_creds:
 out:
 	if (!retval) {
 		wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT,
-			    ptrace_trapping_sleep_fn, TASK_UNINTERRUPTIBLE);
+			    TASK_UNINTERRUPTIBLE);
 		proc_ptrace_connector(task, PTRACE_ATTACH);
 	}
 
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index bfda2726ca4..ff1a6de62f1 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -99,6 +99,10 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 
 void kfree(const void *);
 
+/*
+ * Reclaim the specified callback, either by invoking it (non-lazy case)
+ * or freeing it directly (lazy case).  Return true if lazy, false otherwise.
+ */
 static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 {
 	unsigned long offset = (unsigned long)head->func;
@@ -108,12 +112,12 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 		RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
 		kfree((void *)head - offset);
 		rcu_lock_release(&rcu_callback_map);
-		return 1;
+		return true;
 	} else {
 		RCU_TRACE(trace_rcu_invoke_callback(rn, head));
 		head->func(head);
 		rcu_lock_release(&rcu_callback_map);
-		return 0;
+		return false;
 	}
 }
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 7fa34f86e5b..948a7693748 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -18,7 +18,7 @@
  * Copyright (C) IBM Corporation, 2005, 2006
  *
  * Authors: Paul E. McKenney <paulmck@us.ibm.com>
- *	  Josh Triplett <josh@freedesktop.org>
+ *	  Josh Triplett <josh@joshtriplett.org>
  *
  * See also:  Documentation/RCU/torture.txt
  */
@@ -51,7 +51,7 @@
 #include <linux/torture.h>
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>");
+MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
 
 torture_param(int, fqs_duration, 0,
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index c639556f3fa..e037f3eb2f7 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -298,9 +298,9 @@ int __srcu_read_lock(struct srcu_struct *sp)
 
 	idx = ACCESS_ONCE(sp->completed) & 0x1;
 	preempt_disable();
-	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1;
+	__this_cpu_inc(sp->per_cpu_ref->c[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
-	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1;
+	__this_cpu_inc(sp->per_cpu_ref->seq[idx]);
 	preempt_enable();
 	return idx;
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f1ba77363fb..1b70cb6fbe3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -206,6 +206,70 @@ void rcu_bh_qs(int cpu)
 	rdp->passed_quiesce = 1;
 }
 
+static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
+
+static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
+	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
+	.dynticks = ATOMIC_INIT(1),
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+	.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
+	.dynticks_idle = ATOMIC_INIT(1),
+#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+};
+
+/*
+ * Let the RCU core know that this CPU has gone through the scheduler,
+ * which is a quiescent state.  This is called when the need for a
+ * quiescent state is urgent, so we burn an atomic operation and full
+ * memory barriers to let the RCU core know about it, regardless of what
+ * this CPU might (or might not) do in the near future.
+ *
+ * We inform the RCU core by emulating a zero-duration dyntick-idle
+ * period, which we in turn do by incrementing the ->dynticks counter
+ * by two.
+ */
+static void rcu_momentary_dyntick_idle(void)
+{
+	unsigned long flags;
+	struct rcu_data *rdp;
+	struct rcu_dynticks *rdtp;
+	int resched_mask;
+	struct rcu_state *rsp;
+
+	local_irq_save(flags);
+
+	/*
+	 * Yes, we can lose flag-setting operations.  This is OK, because
+	 * the flag will be set again after some delay.
+	 */
+	resched_mask = raw_cpu_read(rcu_sched_qs_mask);
+	raw_cpu_write(rcu_sched_qs_mask, 0);
+
+	/* Find the flavor that needs a quiescent state. */
+	for_each_rcu_flavor(rsp) {
+		rdp = raw_cpu_ptr(rsp->rda);
+		if (!(resched_mask & rsp->flavor_mask))
+			continue;
+		smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
+		if (ACCESS_ONCE(rdp->mynode->completed) !=
+		    ACCESS_ONCE(rdp->cond_resched_completed))
+			continue;
+
+		/*
+		 * Pretend to be momentarily idle for the quiescent state.
+		 * This allows the grace-period kthread to record the
+		 * quiescent state, with no need for this CPU to do anything
+		 * further.
+		 */
+		rdtp = this_cpu_ptr(&rcu_dynticks);
+		smp_mb__before_atomic(); /* Earlier stuff before QS. */
+		atomic_add(2, &rdtp->dynticks);  /* QS. */
+		smp_mb__after_atomic(); /* Later stuff after QS. */
+		break;
+	}
+	local_irq_restore(flags);
+}
+
 /*
  * Note a context switch.  This is a quiescent state for RCU-sched,
  * and requires special handling for preemptible RCU.
@@ -216,19 +280,12 @@ void rcu_note_context_switch(int cpu)
 	trace_rcu_utilization(TPS("Start context switch"));
 	rcu_sched_qs(cpu);
 	rcu_preempt_note_context_switch(cpu);
+	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+		rcu_momentary_dyntick_idle();
 	trace_rcu_utilization(TPS("End context switch"));
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
-static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
-	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
-	.dynticks = ATOMIC_INIT(1),
-#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
-	.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
-	.dynticks_idle = ATOMIC_INIT(1),
-#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
-};
-
 static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
 static long qhimark = 10000;	/* If this many pending, ignore blimit. */
 static long qlowmark = 100;	/* Once only this many pending, use blimit. */
@@ -243,6 +300,13 @@ static ulong jiffies_till_next_fqs = ULONG_MAX;
 module_param(jiffies_till_first_fqs, ulong, 0644);
 module_param(jiffies_till_next_fqs, ulong, 0644);
 
+/*
+ * How long the grace period must be before we start recruiting
+ * quiescent-state help from rcu_note_context_switch().
+ */
+static ulong jiffies_till_sched_qs = HZ / 20;
+module_param(jiffies_till_sched_qs, ulong, 0644);
+
 static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 				  struct rcu_data *rdp);
 static void force_qs_rnp(struct rcu_state *rsp,
@@ -853,6 +917,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 				    bool *isidle, unsigned long *maxj)
 {
 	unsigned int curr;
+	int *rcrmp;
 	unsigned int snap;
 
 	curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
@@ -893,27 +958,43 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	}
 
 	/*
-	 * There is a possibility that a CPU in adaptive-ticks state
-	 * might run in the kernel with the scheduling-clock tick disabled
-	 * for an extended time period.  Invoke rcu_kick_nohz_cpu() to
-	 * force the CPU to restart the scheduling-clock tick in this
-	 * CPU is in this state.
-	 */
-	rcu_kick_nohz_cpu(rdp->cpu);
-
-	/*
-	 * Alternatively, the CPU might be running in the kernel
-	 * for an extended period of time without a quiescent state.
-	 * Attempt to force the CPU through the scheduler to gain the
-	 * needed quiescent state, but only if the grace period has gone
-	 * on for an uncommonly long time.  If there are many stuck CPUs,
-	 * we will beat on the first one until it gets unstuck, then move
-	 * to the next.  Only do this for the primary flavor of RCU.
+	 * A CPU running for an extended time within the kernel can
+	 * delay RCU grace periods.  When the CPU is in NO_HZ_FULL mode,
+	 * even context-switching back and forth between a pair of
+	 * in-kernel CPU-bound tasks cannot advance grace periods.
+	 * So if the grace period is old enough, make the CPU pay attention.
+	 * Note that the unsynchronized assignments to the per-CPU
+	 * rcu_sched_qs_mask variable are safe.  Yes, setting of
+	 * bits can be lost, but they will be set again on the next
+	 * force-quiescent-state pass.  So lost bit sets do not result
+	 * in incorrect behavior, merely in a grace period lasting
+	 * a few jiffies longer than it might otherwise.  Because
+	 * there are at most four threads involved, and because the
+	 * updates are only once every few jiffies, the probability of
+	 * lossage (and thus of slight grace-period extension) is
+	 * quite low.
+	 *
+	 * Note that if the jiffies_till_sched_qs boot/sysfs parameter
+	 * is set too high, we override with half of the RCU CPU stall
+	 * warning delay.
 	 */
-	if (rdp->rsp == rcu_state_p &&
+	rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
+	if (ULONG_CMP_GE(jiffies,
+			 rdp->rsp->gp_start + jiffies_till_sched_qs) ||
 	    ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
-		rdp->rsp->jiffies_resched += 5;
-		resched_cpu(rdp->cpu);
+		if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
+			ACCESS_ONCE(rdp->cond_resched_completed) =
+				ACCESS_ONCE(rdp->mynode->completed);
+			smp_mb(); /* ->cond_resched_completed before *rcrmp. */
+			ACCESS_ONCE(*rcrmp) =
+				ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask;
+			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
+			rdp->rsp->jiffies_resched += 5; /* Enable beating. */
+		} else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
+			/* Time to beat on that CPU again! */
+			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
+			rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
+		}
 	}
 
 	return 0;
@@ -932,10 +1013,7 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 }
 
 /*
- * Dump stacks of all tasks running on stalled CPUs.  This is a fallback
- * for architectures that do not implement trigger_all_cpu_backtrace().
- * The NMI-triggered stack traces are more accurate because they are
- * printed by the target CPU.
+ * Dump stacks of all tasks running on stalled CPUs.
  */
 static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 {
@@ -1013,7 +1091,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
 	if (ndetected == 0)
 		pr_err("INFO: Stall ended before state dump start\n");
-	else if (!trigger_all_cpu_backtrace())
+	else
 		rcu_dump_cpu_stacks(rsp);
 
 	/* Complain about tasks blocking the grace period. */
@@ -1044,8 +1122,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
 		jiffies - rsp->gp_start,
 		(long)rsp->gpnum, (long)rsp->completed, totqlen);
-	if (!trigger_all_cpu_backtrace())
-		dump_stack();
+	rcu_dump_cpu_stacks(rsp);
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall)))
@@ -1224,10 +1301,16 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	 * believe that a grace period is in progress, then we must wait
 	 * for the one following, which is in "c".  Because our request
 	 * will be noticed at the end of the current grace period, we don't
-	 * need to explicitly start one.
+	 * need to explicitly start one.  We only do the lockless check
+	 * of rnp_root's fields if the current rcu_node structure thinks
+	 * there is no grace period in flight, and because we hold rnp->lock,
+	 * the only possible change is when rnp_root's two fields are
+	 * equal, in which case rnp_root->gpnum might be concurrently
+	 * incremented.  But that is OK, as it will just result in our
+	 * doing some extra useless work.
 	 */
 	if (rnp->gpnum != rnp->completed ||
-	    ACCESS_ONCE(rnp->gpnum) != ACCESS_ONCE(rnp->completed)) {
+	    ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) {
 		rnp->need_future_gp[c & 0x1]++;
 		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
 		goto out;
@@ -1564,11 +1647,6 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
-#ifdef CONFIG_PROVE_RCU_DELAY
-		if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 &&
-		    system_state == SYSTEM_RUNNING)
-			udelay(200);
-#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		cond_resched();
 	}
 
@@ -2266,7 +2344,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 	smp_mb(); /* List handling before counting for rcu_barrier(). */
 	rdp->qlen_lazy -= count_lazy;
-	ACCESS_ONCE(rdp->qlen) -= count;
+	ACCESS_ONCE(rdp->qlen) = rdp->qlen - count;
 	rdp->n_cbs_invoked += count;
 
 	/* Reinstate batch limit if we have worked down the excess. */
@@ -2404,14 +2482,14 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	struct rcu_node *rnp_old = NULL;
 
 	/* Funnel through hierarchy to reduce memory contention. */
-	rnp = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode;
+	rnp = __this_cpu_read(rsp->rda->mynode);
 	for (; rnp != NULL; rnp = rnp->parent) {
 		ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
 		      !raw_spin_trylock(&rnp->fqslock);
 		if (rnp_old != NULL)
 			raw_spin_unlock(&rnp_old->fqslock);
 		if (ret) {
-			ACCESS_ONCE(rsp->n_force_qs_lh)++;
+			rsp->n_force_qs_lh++;
 			return;
 		}
 		rnp_old = rnp;
@@ -2423,7 +2501,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
-		ACCESS_ONCE(rsp->n_force_qs_lh)++;
+		rsp->n_force_qs_lh++;
 		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 		return;  /* Someone beat us to it. */
 	}
@@ -2581,7 +2659,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	unsigned long flags;
 	struct rcu_data *rdp;
 
-	WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */
+	WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */
 	if (debug_rcu_head_queue(head)) {
 		/* Probable double call_rcu(), so leak the callback. */
 		ACCESS_ONCE(head->func) = rcu_leak_callback;
@@ -2612,7 +2690,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 		local_irq_restore(flags);
 		return;
 	}
-	ACCESS_ONCE(rdp->qlen)++;
+	ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1;
 	if (lazy)
 		rdp->qlen_lazy++;
 	else
@@ -3176,7 +3254,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 	 * ACCESS_ONCE() to prevent the compiler from speculating
 	 * the increment to precede the early-exit check.
 	 */
-	ACCESS_ONCE(rsp->n_barrier_done)++;
+	ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
 	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1);
 	_rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done);
 	smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */
@@ -3226,7 +3304,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 
 	/* Increment ->n_barrier_done to prevent duplicate work. */
 	smp_mb(); /* Keep increment after above mechanism. */
-	ACCESS_ONCE(rsp->n_barrier_done)++;
+	ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
 	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0);
 	_rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done);
 	smp_mb(); /* Keep increment before caller's subsequent code. */
@@ -3483,14 +3561,17 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
 static void __init rcu_init_one(struct rcu_state *rsp,
 		struct rcu_data __percpu *rda)
 {
-	static char *buf[] = { "rcu_node_0",
-			       "rcu_node_1",
-			       "rcu_node_2",
-			       "rcu_node_3" };  /* Match MAX_RCU_LVLS */
-	static char *fqs[] = { "rcu_node_fqs_0",
-			       "rcu_node_fqs_1",
-			       "rcu_node_fqs_2",
-			       "rcu_node_fqs_3" };  /* Match MAX_RCU_LVLS */
+	static const char * const buf[] = {
+		"rcu_node_0",
+		"rcu_node_1",
+		"rcu_node_2",
+		"rcu_node_3" };  /* Match MAX_RCU_LVLS */
+	static const char * const fqs[] = {
+		"rcu_node_fqs_0",
+		"rcu_node_fqs_1",
+		"rcu_node_fqs_2",
+		"rcu_node_fqs_3" };  /* Match MAX_RCU_LVLS */
+	static u8 fl_mask = 0x1;
 	int cpustride = 1;
 	int i;
 	int j;
@@ -3509,6 +3590,8 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 	for (i = 1; i < rcu_num_lvls; i++)
 		rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
 	rcu_init_levelspread(rsp);
+	rsp->flavor_mask = fl_mask;
+	fl_mask <<= 1;
 
 	/* Initialize the elements themselves, starting from the leaves. */
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index bf2c1e66969..71e64c718f7 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -172,6 +172,14 @@ struct rcu_node {
 				/*  queued on this rcu_node structure that */
 				/*  are blocking the current grace period, */
 				/*  there can be no such task. */
+	struct completion boost_completion;
+				/* Used to ensure that the rt_mutex used */
+				/*  to carry out the boosting is fully */
+				/*  released with no future boostee accesses */
+				/*  before that rt_mutex is re-initialized. */
+	struct rt_mutex boost_mtx;
+				/* Used only for the priority-boosting */
+				/*  side effect, not as a lock. */
 	unsigned long boost_time;
 				/* When to start boosting (jiffies). */
 	struct task_struct *boost_kthread_task;
@@ -307,6 +315,9 @@ struct rcu_data {
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
 	unsigned long dynticks_fqs;	/* Kicked due to dynticks idle. */
 	unsigned long offline_fqs;	/* Kicked due to being offline. */
+	unsigned long cond_resched_completed;
+					/* Grace period that needs help */
+					/*  from cond_resched(). */
 
 	/* 5) __rcu_pending() statistics. */
 	unsigned long n_rcu_pending;	/* rcu_pending() calls since boot. */
@@ -331,11 +342,29 @@ struct rcu_data {
 	struct rcu_head **nocb_tail;
 	atomic_long_t nocb_q_count;	/* # CBs waiting for kthread */
 	atomic_long_t nocb_q_count_lazy; /*  (approximate). */
+	struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */
+	struct rcu_head **nocb_follower_tail;
+	atomic_long_t nocb_follower_count; /* # CBs ready to invoke. */
+	atomic_long_t nocb_follower_count_lazy; /*  (approximate). */
 	int nocb_p_count;		/* # CBs being invoked by kthread */
 	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
 	bool nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
+
+	/* The following fields are used by the leader, hence own cacheline. */
+	struct rcu_head *nocb_gp_head ____cacheline_internodealigned_in_smp;
+					/* CBs waiting for GP. */
+	struct rcu_head **nocb_gp_tail;
+	long nocb_gp_count;
+	long nocb_gp_count_lazy;
+	bool nocb_leader_wake;		/* Is the nocb leader thread awake? */
+	struct rcu_data *nocb_next_follower;
+					/* Next follower in wakeup chain. */
+
+	/* The following fields are used by the follower, hence new cachline. */
+	struct rcu_data *nocb_leader ____cacheline_internodealigned_in_smp;
+					/* Leader CPU takes GP-end wakeups. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* 8) RCU CPU stall data. */
@@ -392,6 +421,7 @@ struct rcu_state {
 	struct rcu_node *level[RCU_NUM_LVLS];	/* Hierarchy levels. */
 	u32 levelcnt[MAX_RCU_LVLS + 1];		/* # nodes in each level. */
 	u8 levelspread[RCU_NUM_LVLS];		/* kids/node in each level. */
+	u8 flavor_mask;				/* bit in flavor mask. */
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	void (*call)(struct rcu_head *head,	/* call_rcu() flavor. */
 		     void (*func)(struct rcu_head *head));
@@ -563,7 +593,7 @@ static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
 static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
-static void rcu_kick_nohz_cpu(int cpu);
+static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
 static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq);
 static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq);
@@ -583,8 +613,14 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
 /* Sum up queue lengths for tracing. */
 static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 {
-	*ql = atomic_long_read(&rdp->nocb_q_count) + rdp->nocb_p_count;
-	*qll = atomic_long_read(&rdp->nocb_q_count_lazy) + rdp->nocb_p_count_lazy;
+	*ql = atomic_long_read(&rdp->nocb_q_count) +
+	      rdp->nocb_p_count +
+	      atomic_long_read(&rdp->nocb_follower_count) +
+	      rdp->nocb_p_count + rdp->nocb_gp_count;
+	*qll = atomic_long_read(&rdp->nocb_q_count_lazy) +
+	       rdp->nocb_p_count_lazy +
+	       atomic_long_read(&rdp->nocb_follower_count_lazy) +
+	       rdp->nocb_p_count_lazy + rdp->nocb_gp_count_lazy;
 }
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index cbc2c45265e..00dc411e967 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -33,6 +33,7 @@
 #define RCU_KTHREAD_PRIO 1
 
 #ifdef CONFIG_RCU_BOOST
+#include "../locking/rtmutex_common.h"
 #define RCU_BOOST_PRIO CONFIG_RCU_BOOST_PRIO
 #else
 #define RCU_BOOST_PRIO RCU_KTHREAD_PRIO
@@ -336,7 +337,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	unsigned long flags;
 	struct list_head *np;
 #ifdef CONFIG_RCU_BOOST
-	struct rt_mutex *rbmp = NULL;
+	bool drop_boost_mutex = false;
 #endif /* #ifdef CONFIG_RCU_BOOST */
 	struct rcu_node *rnp;
 	int special;
@@ -398,11 +399,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 #ifdef CONFIG_RCU_BOOST
 		if (&t->rcu_node_entry == rnp->boost_tasks)
 			rnp->boost_tasks = np;
-		/* Snapshot/clear ->rcu_boost_mutex with rcu_node lock held. */
-		if (t->rcu_boost_mutex) {
-			rbmp = t->rcu_boost_mutex;
-			t->rcu_boost_mutex = NULL;
-		}
+		/* Snapshot ->boost_mtx ownership with rcu_node lock held. */
+		drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
 		/*
@@ -427,8 +425,10 @@ void rcu_read_unlock_special(struct task_struct *t)
 
 #ifdef CONFIG_RCU_BOOST
 		/* Unboost if we were boosted. */
-		if (rbmp)
-			rt_mutex_unlock(rbmp);
+		if (drop_boost_mutex) {
+			rt_mutex_unlock(&rnp->boost_mtx);
+			complete(&rnp->boost_completion);
+		}
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
 		/*
@@ -988,6 +988,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 
 /* Because preemptible RCU does not exist, no quieting of tasks. */
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
 {
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -1149,7 +1150,6 @@ static void rcu_wake_cond(struct task_struct *t, int status)
 static int rcu_boost(struct rcu_node *rnp)
 {
 	unsigned long flags;
-	struct rt_mutex mtx;
 	struct task_struct *t;
 	struct list_head *tb;
 
@@ -1200,11 +1200,15 @@ static int rcu_boost(struct rcu_node *rnp)
 	 * section.
 	 */
 	t = container_of(tb, struct task_struct, rcu_node_entry);
-	rt_mutex_init_proxy_locked(&mtx, t);
-	t->rcu_boost_mutex = &mtx;
+	rt_mutex_init_proxy_locked(&rnp->boost_mtx, t);
+	init_completion(&rnp->boost_completion);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	rt_mutex_lock(&mtx);  /* Side effect: boosts task t's priority. */
-	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
+	/* Lock only for side effect: boosts task t's priority. */
+	rt_mutex_lock(&rnp->boost_mtx);
+	rt_mutex_unlock(&rnp->boost_mtx);  /* Then keep lockdep happy. */
+
+	/* Wait for boostee to be done w/boost_mtx before reinitializing. */
+	wait_for_completion(&rnp->boost_completion);
 
 	return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
 	       ACCESS_ONCE(rnp->boost_tasks) != NULL;
@@ -1256,6 +1260,7 @@ static int rcu_boost_kthread(void *arg)
  * about it going away.
  */
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
 {
 	struct task_struct *t;
 
@@ -1491,6 +1496,7 @@ static void rcu_prepare_kthreads(int cpu)
 #else /* #ifdef CONFIG_RCU_BOOST */
 
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
 {
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -2060,6 +2066,22 @@ bool rcu_is_nocb_cpu(int cpu)
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
+ * Kick the leader kthread for this NOCB group.
+ */
+static void wake_nocb_leader(struct rcu_data *rdp, bool force)
+{
+	struct rcu_data *rdp_leader = rdp->nocb_leader;
+
+	if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
+		return;
+	if (!ACCESS_ONCE(rdp_leader->nocb_leader_wake) || force) {
+		/* Prior xchg orders against prior callback enqueue. */
+		ACCESS_ONCE(rdp_leader->nocb_leader_wake) = true;
+		wake_up(&rdp_leader->nocb_wq);
+	}
+}
+
+/*
  * Enqueue the specified string of rcu_head structures onto the specified
  * CPU's no-CBs lists.  The CPU is specified by rdp, the head of the
  * string by rhp, and the tail of the string by rhtp.  The non-lazy/lazy
@@ -2093,7 +2115,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 	len = atomic_long_read(&rdp->nocb_q_count);
 	if (old_rhpp == &rdp->nocb_head) {
 		if (!irqs_disabled_flags(flags)) {
-			wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */
+			/* ... if queue was empty ... */
+			wake_nocb_leader(rdp, false);
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("WakeEmpty"));
 		} else {
@@ -2103,7 +2126,8 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 		}
 		rdp->qlen_last_fqs_check = 0;
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
-		wake_up_process(t); /* ... or if many callbacks queued. */
+		/* ... or if many callbacks queued. */
+		wake_nocb_leader(rdp, true);
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf"));
 	} else {
@@ -2213,13 +2237,150 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 }
 
 /*
+ * Leaders come here to wait for additional callbacks to show up.
+ * This function does not return until callbacks appear.
+ */
+static void nocb_leader_wait(struct rcu_data *my_rdp)
+{
+	bool firsttime = true;
+	bool gotcbs;
+	struct rcu_data *rdp;
+	struct rcu_head **tail;
+
+wait_again:
+
+	/* Wait for callbacks to appear. */
+	if (!rcu_nocb_poll) {
+		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
+		wait_event_interruptible(my_rdp->nocb_wq,
+					 ACCESS_ONCE(my_rdp->nocb_leader_wake));
+		/* Memory barrier handled by smp_mb() calls below and repoll. */
+	} else if (firsttime) {
+		firsttime = false; /* Don't drown trace log with "Poll"! */
+		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Poll");
+	}
+
+	/*
+	 * Each pass through the following loop checks a follower for CBs.
+	 * We are our own first follower.  Any CBs found are moved to
+	 * nocb_gp_head, where they await a grace period.
+	 */
+	gotcbs = false;
+	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
+		rdp->nocb_gp_head = ACCESS_ONCE(rdp->nocb_head);
+		if (!rdp->nocb_gp_head)
+			continue;  /* No CBs here, try next follower. */
+
+		/* Move callbacks to wait-for-GP list, which is empty. */
+		ACCESS_ONCE(rdp->nocb_head) = NULL;
+		rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
+		rdp->nocb_gp_count = atomic_long_xchg(&rdp->nocb_q_count, 0);
+		rdp->nocb_gp_count_lazy =
+			atomic_long_xchg(&rdp->nocb_q_count_lazy, 0);
+		gotcbs = true;
+	}
+
+	/*
+	 * If there were no callbacks, sleep a bit, rescan after a
+	 * memory barrier, and go retry.
+	 */
+	if (unlikely(!gotcbs)) {
+		if (!rcu_nocb_poll)
+			trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu,
+					    "WokeEmpty");
+		flush_signals(current);
+		schedule_timeout_interruptible(1);
+
+		/* Rescan in case we were a victim of memory ordering. */
+		my_rdp->nocb_leader_wake = false;
+		smp_mb();  /* Ensure _wake false before scan. */
+		for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
+			if (ACCESS_ONCE(rdp->nocb_head)) {
+				/* Found CB, so short-circuit next wait. */
+				my_rdp->nocb_leader_wake = true;
+				break;
+			}
+		goto wait_again;
+	}
+
+	/* Wait for one grace period. */
+	rcu_nocb_wait_gp(my_rdp);
+
+	/*
+	 * We left ->nocb_leader_wake set to reduce cache thrashing.
+	 * We clear it now, but recheck for new callbacks while
+	 * traversing our follower list.
+	 */
+	my_rdp->nocb_leader_wake = false;
+	smp_mb(); /* Ensure _wake false before scan of ->nocb_head. */
+
+	/* Each pass through the following loop wakes a follower, if needed. */
+	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
+		if (ACCESS_ONCE(rdp->nocb_head))
+			my_rdp->nocb_leader_wake = true; /* No need to wait. */
+		if (!rdp->nocb_gp_head)
+			continue; /* No CBs, so no need to wake follower. */
+
+		/* Append callbacks to follower's "done" list. */
+		tail = xchg(&rdp->nocb_follower_tail, rdp->nocb_gp_tail);
+		*tail = rdp->nocb_gp_head;
+		atomic_long_add(rdp->nocb_gp_count, &rdp->nocb_follower_count);
+		atomic_long_add(rdp->nocb_gp_count_lazy,
+				&rdp->nocb_follower_count_lazy);
+		if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
+			/*
+			 * List was empty, wake up the follower.
+			 * Memory barriers supplied by atomic_long_add().
+			 */
+			wake_up(&rdp->nocb_wq);
+		}
+	}
+
+	/* If we (the leader) don't have CBs, go wait some more. */
+	if (!my_rdp->nocb_follower_head)
+		goto wait_again;
+}
+
+/*
+ * Followers come here to wait for additional callbacks to show up.
+ * This function does not return until callbacks appear.
+ */
+static void nocb_follower_wait(struct rcu_data *rdp)
+{
+	bool firsttime = true;
+
+	for (;;) {
+		if (!rcu_nocb_poll) {
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    "FollowerSleep");
+			wait_event_interruptible(rdp->nocb_wq,
+						 ACCESS_ONCE(rdp->nocb_follower_head));
+		} else if (firsttime) {
+			/* Don't drown trace log with "Poll"! */
+			firsttime = false;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "Poll");
+		}
+		if (smp_load_acquire(&rdp->nocb_follower_head)) {
+			/* ^^^ Ensure CB invocation follows _head test. */
+			return;
+		}
+		if (!rcu_nocb_poll)
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    "WokeEmpty");
+		flush_signals(current);
+		schedule_timeout_interruptible(1);
+	}
+}
+
+/*
  * Per-rcu_data kthread, but only for no-CBs CPUs.  Each kthread invokes
- * callbacks queued by the corresponding no-CBs CPU.
+ * callbacks queued by the corresponding no-CBs CPU, however, there is
+ * an optional leader-follower relationship so that the grace-period
+ * kthreads don't have to do quite so many wakeups.
  */
 static int rcu_nocb_kthread(void *arg)
 {
 	int c, cl;
-	bool firsttime = 1;
 	struct rcu_head *list;
 	struct rcu_head *next;
 	struct rcu_head **tail;
@@ -2227,41 +2388,22 @@ static int rcu_nocb_kthread(void *arg)
 
 	/* Each pass through this loop invokes one batch of callbacks */
 	for (;;) {
-		/* If not polling, wait for next batch of callbacks. */
-		if (!rcu_nocb_poll) {
-			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-					    TPS("Sleep"));
-			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
-			/* Memory barrier provide by xchg() below. */
-		} else if (firsttime) {
-			firsttime = 0;
-			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-					    TPS("Poll"));
-		}
-		list = ACCESS_ONCE(rdp->nocb_head);
-		if (!list) {
-			if (!rcu_nocb_poll)
-				trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-						    TPS("WokeEmpty"));
-			schedule_timeout_interruptible(1);
-			flush_signals(current);
-			continue;
-		}
-		firsttime = 1;
-		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-				    TPS("WokeNonEmpty"));
-
-		/*
-		 * Extract queued callbacks, update counts, and wait
-		 * for a grace period to elapse.
-		 */
-		ACCESS_ONCE(rdp->nocb_head) = NULL;
-		tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
-		c = atomic_long_xchg(&rdp->nocb_q_count, 0);
-		cl = atomic_long_xchg(&rdp->nocb_q_count_lazy, 0);
-		ACCESS_ONCE(rdp->nocb_p_count) += c;
-		ACCESS_ONCE(rdp->nocb_p_count_lazy) += cl;
-		rcu_nocb_wait_gp(rdp);
+		/* Wait for callbacks. */
+		if (rdp->nocb_leader == rdp)
+			nocb_leader_wait(rdp);
+		else
+			nocb_follower_wait(rdp);
+
+		/* Pull the ready-to-invoke callbacks onto local list. */
+		list = ACCESS_ONCE(rdp->nocb_follower_head);
+		BUG_ON(!list);
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty");
+		ACCESS_ONCE(rdp->nocb_follower_head) = NULL;
+		tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head);
+		c = atomic_long_xchg(&rdp->nocb_follower_count, 0);
+		cl = atomic_long_xchg(&rdp->nocb_follower_count_lazy, 0);
+		rdp->nocb_p_count += c;
+		rdp->nocb_p_count_lazy += cl;
 
 		/* Each pass through the following loop invokes a callback. */
 		trace_rcu_batch_start(rdp->rsp->name, cl, c, -1);
@@ -2305,7 +2447,7 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 	if (!rcu_nocb_need_deferred_wakeup(rdp))
 		return;
 	ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
-	wake_up(&rdp->nocb_wq);
+	wake_nocb_leader(rdp, false);
 	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
 }
 
@@ -2314,19 +2456,57 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 	rdp->nocb_tail = &rdp->nocb_head;
 	init_waitqueue_head(&rdp->nocb_wq);
+	rdp->nocb_follower_tail = &rdp->nocb_follower_head;
 }
 
-/* Create a kthread for each RCU flavor for each no-CBs CPU. */
+/* How many follower CPU IDs per leader?  Default of -1 for sqrt(nr_cpu_ids). */
+static int rcu_nocb_leader_stride = -1;
+module_param(rcu_nocb_leader_stride, int, 0444);
+
+/*
+ * Create a kthread for each RCU flavor for each no-CBs CPU.
+ * Also initialize leader-follower relationships.
+ */
 static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 {
 	int cpu;
+	int ls = rcu_nocb_leader_stride;
+	int nl = 0;  /* Next leader. */
 	struct rcu_data *rdp;
+	struct rcu_data *rdp_leader = NULL;  /* Suppress misguided gcc warn. */
+	struct rcu_data *rdp_prev = NULL;
 	struct task_struct *t;
 
 	if (rcu_nocb_mask == NULL)
 		return;
+#if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL)
+	if (tick_nohz_full_running)
+		cpumask_or(rcu_nocb_mask, rcu_nocb_mask, tick_nohz_full_mask);
+#endif /* #if defined(CONFIG_NO_HZ_FULL) && !defined(CONFIG_NO_HZ_FULL_ALL) */
+	if (ls == -1) {
+		ls = int_sqrt(nr_cpu_ids);
+		rcu_nocb_leader_stride = ls;
+	}
+
+	/*
+	 * Each pass through this loop sets up one rcu_data structure and
+	 * spawns one rcu_nocb_kthread().
+	 */
 	for_each_cpu(cpu, rcu_nocb_mask) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);
+		if (rdp->cpu >= nl) {
+			/* New leader, set up for followers & next leader. */
+			nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls;
+			rdp->nocb_leader = rdp;
+			rdp_leader = rdp;
+		} else {
+			/* Another follower, link to previous leader. */
+			rdp->nocb_leader = rdp_leader;
+			rdp_prev->nocb_next_follower = rdp;
+		}
+		rdp_prev = rdp;
+
+		/* Spawn the kthread for this CPU. */
 		t = kthread_run(rcu_nocb_kthread, rdp,
 				"rcuo%c/%d", rsp->abbr, cpu);
 		BUG_ON(IS_ERR(t));
@@ -2404,7 +2584,7 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
  * if an adaptive-ticks CPU is failing to respond to the current grace
  * period and has not be idle from an RCU perspective, kick it.
  */
-static void rcu_kick_nohz_cpu(int cpu)
+static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
 {
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_cpu(cpu))
@@ -2843,12 +3023,16 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
  */
 static void rcu_bind_gp_kthread(void)
 {
-#ifdef CONFIG_NO_HZ_FULL
-	int cpu = ACCESS_ONCE(tick_do_timer_cpu);
+	int __maybe_unused cpu;
 
-	if (cpu < 0 || cpu >= nr_cpu_ids)
+	if (!tick_nohz_full_enabled())
 		return;
-	if (raw_smp_processor_id() != cpu)
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+	cpu = tick_do_timer_cpu;
+	if (cpu >= 0 && cpu < nr_cpu_ids && raw_smp_processor_id() != cpu)
 		set_cpus_allowed_ptr(current, cpumask_of(cpu));
-#endif /* #ifdef CONFIG_NO_HZ_FULL */
+#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+	if (!is_housekeeping_cpu(raw_smp_processor_id()))
+		housekeeping_affine(current);
+#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 }
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index a2aeb4df0f6..4056d7992a6 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -90,9 +90,6 @@ void __rcu_read_unlock(void)
 	} else {
 		barrier();  /* critical section before exit code. */
 		t->rcu_read_lock_nesting = INT_MIN;
-#ifdef CONFIG_PROVE_RCU_DELAY
-		udelay(10); /* Make preemption more probable. */
-#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */
 		barrier();  /* assign before ->rcu_read_unlock_special load */
 		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
 			rcu_read_unlock_special(t);
@@ -200,12 +197,12 @@ void wait_rcu_gp(call_rcu_func_t crf)
 EXPORT_SYMBOL_GPL(wait_rcu_gp);
 
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-static inline void debug_init_rcu_head(struct rcu_head *head)
+void init_rcu_head(struct rcu_head *head)
 {
 	debug_object_init(head, &rcuhead_debug_descr);
 }
 
-static inline void debug_rcu_head_free(struct rcu_head *head)
+void destroy_rcu_head(struct rcu_head *head)
 {
 	debug_object_free(head, &rcuhead_debug_descr);
 }
@@ -350,21 +347,3 @@ static int __init check_cpu_stall_init(void)
 early_initcall(check_cpu_stall_init);
 
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
-
-/*
- * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings.
- */
-
-DEFINE_PER_CPU(int, rcu_cond_resched_count);
-
-/*
- * Report a set of RCU quiescent states, for use by cond_resched()
- * and friends.  Out of line due to being called infrequently.
- */
-void rcu_resched(void)
-{
-	preempt_disable();
-	__this_cpu_write(rcu_cond_resched_count, 0);
-	rcu_note_context_switch(smp_processor_id());
-	preempt_enable();
-}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 48e78b657d2..1211575a220 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -139,6 +139,8 @@ void update_rq_clock(struct rq *rq)
 		return;
 
 	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+	if (delta < 0)
+		return;
 	rq->clock += delta;
 	update_rq_clock_task(rq, delta);
 }
@@ -243,6 +245,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 	char buf[64];
 	char *cmp;
 	int i;
+	struct inode *inode;
 
 	if (cnt > 63)
 		cnt = 63;
@@ -253,7 +256,11 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 	buf[cnt] = 0;
 	cmp = strstrip(buf);
 
+	/* Ensure the static_key remains in a consistent state */
+	inode = file_inode(filp);
+	mutex_lock(&inode->i_mutex);
 	i = sched_feat_set(cmp);
+	mutex_unlock(&inode->i_mutex);
 	if (i == __SCHED_FEAT_NR)
 		return -EINVAL;
 
@@ -535,7 +542,7 @@ static inline void init_hrtick(void)
  	__old;								\
 })
 
-#ifdef TIF_POLLING_NRFLAG
+#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
 /*
  * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
  * this avoids any races wrt polling state changes and thereby avoids
@@ -546,40 +553,75 @@ static bool set_nr_and_not_polling(struct task_struct *p)
 	struct thread_info *ti = task_thread_info(p);
 	return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
 }
+
+/*
+ * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
+ *
+ * If this returns true, then the idle task promises to call
+ * sched_ttwu_pending() and reschedule soon.
+ */
+static bool set_nr_if_polling(struct task_struct *p)
+{
+	struct thread_info *ti = task_thread_info(p);
+	typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags);
+
+	for (;;) {
+		if (!(val & _TIF_POLLING_NRFLAG))
+			return false;
+		if (val & _TIF_NEED_RESCHED)
+			return true;
+		old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED);
+		if (old == val)
+			break;
+		val = old;
+	}
+	return true;
+}
+
 #else
 static bool set_nr_and_not_polling(struct task_struct *p)
 {
 	set_tsk_need_resched(p);
 	return true;
 }
+
+#ifdef CONFIG_SMP
+static bool set_nr_if_polling(struct task_struct *p)
+{
+	return false;
+}
+#endif
 #endif
 
 /*
- * resched_task - mark a task 'to be rescheduled now'.
+ * resched_curr - mark rq's current task 'to be rescheduled now'.
  *
  * On UP this means the setting of the need_resched flag, on SMP it
  * might also involve a cross-CPU call to trigger the scheduler on
  * the target CPU.
  */
-void resched_task(struct task_struct *p)
+void resched_curr(struct rq *rq)
 {
+	struct task_struct *curr = rq->curr;
 	int cpu;
 
-	lockdep_assert_held(&task_rq(p)->lock);
+	lockdep_assert_held(&rq->lock);
 
-	if (test_tsk_need_resched(p))
+	if (test_tsk_need_resched(curr))
 		return;
 
-	cpu = task_cpu(p);
+	cpu = cpu_of(rq);
 
 	if (cpu == smp_processor_id()) {
-		set_tsk_need_resched(p);
+		set_tsk_need_resched(curr);
 		set_preempt_need_resched();
 		return;
 	}
 
-	if (set_nr_and_not_polling(p))
+	if (set_nr_and_not_polling(curr))
 		smp_send_reschedule(cpu);
+	else
+		trace_sched_wake_idle_without_ipi(cpu);
 }
 
 void resched_cpu(int cpu)
@@ -589,7 +631,7 @@ void resched_cpu(int cpu)
 
 	if (!raw_spin_trylock_irqsave(&rq->lock, flags))
 		return;
-	resched_task(cpu_curr(cpu));
+	resched_curr(rq);
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
@@ -642,35 +684,24 @@ static void wake_up_idle_cpu(int cpu)
 	if (cpu == smp_processor_id())
 		return;
 
-	/*
-	 * This is safe, as this function is called with the timer
-	 * wheel base lock of (cpu) held. When the CPU is on the way
-	 * to idle and has not yet set rq->curr to idle then it will
-	 * be serialized on the timer wheel base lock and take the new
-	 * timer into account automatically.
-	 */
-	if (rq->curr != rq->idle)
-		return;
-
-	/*
-	 * We can set TIF_RESCHED on the idle task of the other CPU
-	 * lockless. The worst case is that the other CPU runs the
-	 * idle task through an additional NOOP schedule()
-	 */
-	set_tsk_need_resched(rq->idle);
-
-	/* NEED_RESCHED must be visible before we test polling */
-	smp_mb();
-	if (!tsk_is_polling(rq->idle))
+	if (set_nr_and_not_polling(rq->idle))
 		smp_send_reschedule(cpu);
+	else
+		trace_sched_wake_idle_without_ipi(cpu);
 }
 
 static bool wake_up_full_nohz_cpu(int cpu)
 {
+	/*
+	 * We just need the target to call irq_exit() and re-evaluate
+	 * the next tick. The nohz full kick at least implies that.
+	 * If needed we can still optimize that later with an
+	 * empty IRQ.
+	 */
 	if (tick_nohz_full_cpu(cpu)) {
 		if (cpu != smp_processor_id() ||
 		    tick_nohz_tick_stopped())
-			smp_send_reschedule(cpu);
+			tick_nohz_full_kick_cpu(cpu);
 		return true;
 	}
 
@@ -713,18 +744,15 @@ static inline bool got_nohz_idle_kick(void)
 #ifdef CONFIG_NO_HZ_FULL
 bool sched_can_stop_tick(void)
 {
-       struct rq *rq;
-
-       rq = this_rq();
-
-       /* Make sure rq->nr_running update is visible after the IPI */
-       smp_rmb();
-
-       /* More than one running task need preemption */
-       if (rq->nr_running > 1)
-               return false;
+	/*
+	 * More than one running task need preemption.
+	 * nr_running update is assumed to be visible
+	 * after IPI is sent from wakers.
+	 */
+	if (this_rq()->nr_running > 1)
+		return false;
 
-       return true;
+	return true;
 }
 #endif /* CONFIG_NO_HZ_FULL */
 
@@ -888,7 +916,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 	rq->clock_task += delta;
 
 #if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	if ((irq_delta + steal) && sched_feat(NONTASK_POWER))
+	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
 		sched_rt_avg_update(rq, irq_delta + steal);
 #endif
 }
@@ -1005,7 +1033,7 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 			if (class == rq->curr->sched_class)
 				break;
 			if (class == p->sched_class) {
-				resched_task(rq->curr);
+				resched_curr(rq);
 				break;
 			}
 		}
@@ -1521,13 +1549,17 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 }
 
 #ifdef CONFIG_SMP
-static void sched_ttwu_pending(void)
+void sched_ttwu_pending(void)
 {
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
 	struct task_struct *p;
+	unsigned long flags;
 
-	raw_spin_lock(&rq->lock);
+	if (!llist)
+		return;
+
+	raw_spin_lock_irqsave(&rq->lock, flags);
 
 	while (llist) {
 		p = llist_entry(llist, struct task_struct, wake_entry);
@@ -1535,7 +1567,7 @@ static void sched_ttwu_pending(void)
 		ttwu_do_activate(rq, p, 0);
 	}
 
-	raw_spin_unlock(&rq->lock);
+	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
 void scheduler_ipi(void)
@@ -1547,9 +1579,7 @@ void scheduler_ipi(void)
 	 */
 	preempt_fold_need_resched();
 
-	if (llist_empty(&this_rq()->wake_list)
-			&& !tick_nohz_full_cpu(smp_processor_id())
-			&& !got_nohz_idle_kick())
+	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
 		return;
 
 	/*
@@ -1566,7 +1596,6 @@ void scheduler_ipi(void)
 	 * somewhat pessimize the simple resched case.
 	 */
 	irq_enter();
-	tick_nohz_full_check();
 	sched_ttwu_pending();
 
 	/*
@@ -1581,8 +1610,14 @@ void scheduler_ipi(void)
 
 static void ttwu_queue_remote(struct task_struct *p, int cpu)
 {
-	if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list))
-		smp_send_reschedule(cpu);
+	struct rq *rq = cpu_rq(cpu);
+
+	if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) {
+		if (!set_nr_if_polling(rq->idle))
+			smp_send_reschedule(cpu);
+		else
+			trace_sched_wake_idle_without_ipi(cpu);
+	}
 }
 
 bool cpus_share_cache(int this_cpu, int that_cpu)
@@ -2404,7 +2439,12 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
 {
 	u64 ns = 0;
 
-	if (task_current(rq, p)) {
+	/*
+	 * Must be ->curr _and_ ->on_rq.  If dequeued, we would
+	 * project cycles that may never be accounted to this
+	 * thread, breaking clock_gettime().
+	 */
+	if (task_current(rq, p) && p->on_rq) {
 		update_rq_clock(rq);
 		ns = rq_clock_task(rq) - p->se.exec_start;
 		if ((s64)ns < 0)
@@ -2447,8 +2487,10 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	 * If we race with it leaving cpu, we'll take a lock. So we're correct.
 	 * If we race with it entering cpu, unaccounted time is 0. This is
 	 * indistinguishable from the read occurring a few cycles earlier.
+	 * If we see ->on_cpu without ->on_rq, the task is leaving, and has
+	 * been accounted, so we're correct here as well.
 	 */
-	if (!p->on_cpu)
+	if (!p->on_cpu || !p->on_rq)
 		return p->se.sum_exec_runtime;
 #endif
 
@@ -2527,7 +2569,7 @@ notrace unsigned long get_parent_ip(unsigned long addr)
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
 				defined(CONFIG_PREEMPT_TRACER))
 
-void __kprobes preempt_count_add(int val)
+void preempt_count_add(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
@@ -2553,8 +2595,9 @@ void __kprobes preempt_count_add(int val)
 	}
 }
 EXPORT_SYMBOL(preempt_count_add);
+NOKPROBE_SYMBOL(preempt_count_add);
 
-void __kprobes preempt_count_sub(int val)
+void preempt_count_sub(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
 	/*
@@ -2575,6 +2618,7 @@ void __kprobes preempt_count_sub(int val)
 	__preempt_count_sub(val);
 }
 EXPORT_SYMBOL(preempt_count_sub);
+NOKPROBE_SYMBOL(preempt_count_sub);
 
 #endif
 
@@ -2857,6 +2901,7 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 		barrier();
 	} while (need_resched());
 }
+NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
 #endif /* CONFIG_PREEMPT */
 
@@ -2941,7 +2986,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	}
 
 	trace_sched_pi_setprio(p, prio);
-	p->pi_top_task = rt_mutex_get_top_task(p);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
 	on_rq = p->on_rq;
@@ -2961,8 +3005,9 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	 *          running task
 	 */
 	if (dl_prio(prio)) {
-		if (!dl_prio(p->normal_prio) || (p->pi_top_task &&
-			dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) {
+		struct task_struct *pi_task = rt_mutex_get_top_task(p);
+		if (!dl_prio(p->normal_prio) ||
+		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			p->dl.dl_throttled = 0;
 			enqueue_flag = ENQUEUE_REPLENISH;
@@ -3034,7 +3079,7 @@ void set_user_nice(struct task_struct *p, long nice)
 		 * lowered its priority, then reschedule its CPU:
 		 */
 		if (delta < 0 || (delta > 0 && task_running(rq, p)))
-			resched_task(rq->curr);
+			resched_curr(rq);
 	}
 out_unlock:
 	task_rq_unlock(rq, p, &flags);
@@ -3173,12 +3218,18 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_yielded = 0;
 }
 
+/*
+ * sched_setparam() passes in -1 for its policy, to let the functions
+ * it calls know not to change it.
+ */
+#define SETPARAM_POLICY	-1
+
 static void __setscheduler_params(struct task_struct *p,
 		const struct sched_attr *attr)
 {
 	int policy = attr->sched_policy;
 
-	if (policy == -1) /* setparam */
+	if (policy == SETPARAM_POLICY)
 		policy = p->policy;
 
 	p->policy = policy;
@@ -3527,10 +3578,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
 		.sched_nice	= PRIO_TO_NICE(p->static_prio),
 	};
 
-	/*
-	 * Fixup the legacy SCHED_RESET_ON_FORK hack
-	 */
-	if (policy & SCHED_RESET_ON_FORK) {
+	/* Fixup the legacy SCHED_RESET_ON_FORK hack. */
+	if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
 		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
 		policy &= ~SCHED_RESET_ON_FORK;
 		attr.sched_policy = policy;
@@ -3700,7 +3749,7 @@ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
  */
 SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 {
-	return do_sched_setscheduler(pid, -1, param);
+	return do_sched_setscheduler(pid, SETPARAM_POLICY, param);
 }
 
 /**
@@ -4117,7 +4166,6 @@ static void __cond_resched(void)
 
 int __sched _cond_resched(void)
 {
-	rcu_cond_resched();
 	if (should_resched()) {
 		__cond_resched();
 		return 1;
@@ -4136,18 +4184,15 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
-	bool need_rcu_resched = rcu_should_resched();
 	int resched = should_resched();
 	int ret = 0;
 
 	lockdep_assert_held(lock);
 
-	if (spin_needbreak(lock) || resched || need_rcu_resched) {
+	if (spin_needbreak(lock) || resched) {
 		spin_unlock(lock);
 		if (resched)
 			__cond_resched();
-		else if (unlikely(need_rcu_resched))
-			rcu_resched();
 		else
 			cpu_relax();
 		ret = 1;
@@ -4161,7 +4206,6 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	rcu_cond_resched();  /* BH disabled OK, just recording QSes. */
 	if (should_resched()) {
 		local_bh_enable();
 		__cond_resched();
@@ -4216,7 +4260,7 @@ EXPORT_SYMBOL(yield);
  *	false (0) if we failed to boost the target.
  *	-ESRCH if there's no task to yield to.
  */
-bool __sched yield_to(struct task_struct *p, bool preempt)
+int __sched yield_to(struct task_struct *p, bool preempt)
 {
 	struct task_struct *curr = current;
 	struct rq *rq, *p_rq;
@@ -4260,7 +4304,7 @@ again:
 		 * fairness.
 		 */
 		if (preempt && rq != p_rq)
-			resched_task(p_rq->curr);
+			resched_curr(p_rq);
 	}
 
 out_unlock:
@@ -5242,14 +5286,13 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		}
 
 		/*
-		 * Even though we initialize ->power to something semi-sane,
-		 * we leave power_orig unset. This allows us to detect if
+		 * Even though we initialize ->capacity to something semi-sane,
+		 * we leave capacity_orig unset. This allows us to detect if
 		 * domain iteration is still funny without causing /0 traps.
 		 */
-		if (!group->sgp->power_orig) {
+		if (!group->sgc->capacity_orig) {
 			printk(KERN_CONT "\n");
-			printk(KERN_ERR "ERROR: domain->cpu_power not "
-					"set\n");
+			printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n");
 			break;
 		}
 
@@ -5271,9 +5314,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
 
 		printk(KERN_CONT " %s", str);
-		if (group->sgp->power != SCHED_POWER_SCALE) {
-			printk(KERN_CONT " (cpu_power = %d)",
-				group->sgp->power);
+		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
+			printk(KERN_CONT " (cpu_capacity = %d)",
+				group->sgc->capacity);
 		}
 
 		group = group->next;
@@ -5331,7 +5374,7 @@ static int sd_degenerate(struct sched_domain *sd)
 			 SD_BALANCE_NEWIDLE |
 			 SD_BALANCE_FORK |
 			 SD_BALANCE_EXEC |
-			 SD_SHARE_CPUPOWER |
+			 SD_SHARE_CPUCAPACITY |
 			 SD_SHARE_PKG_RESOURCES |
 			 SD_SHARE_POWERDOMAIN)) {
 		if (sd->groups != sd->groups->next)
@@ -5362,7 +5405,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 				SD_BALANCE_NEWIDLE |
 				SD_BALANCE_FORK |
 				SD_BALANCE_EXEC |
-				SD_SHARE_CPUPOWER |
+				SD_SHARE_CPUCAPACITY |
 				SD_SHARE_PKG_RESOURCES |
 				SD_PREFER_SIBLING |
 				SD_SHARE_POWERDOMAIN);
@@ -5487,7 +5530,7 @@ static struct root_domain *alloc_rootdomain(void)
 	return rd;
 }
 
-static void free_sched_groups(struct sched_group *sg, int free_sgp)
+static void free_sched_groups(struct sched_group *sg, int free_sgc)
 {
 	struct sched_group *tmp, *first;
 
@@ -5498,8 +5541,8 @@ static void free_sched_groups(struct sched_group *sg, int free_sgp)
 	do {
 		tmp = sg->next;
 
-		if (free_sgp && atomic_dec_and_test(&sg->sgp->ref))
-			kfree(sg->sgp);
+		if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
+			kfree(sg->sgc);
 
 		kfree(sg);
 		sg = tmp;
@@ -5517,7 +5560,7 @@ static void free_sched_domain(struct rcu_head *rcu)
 	if (sd->flags & SD_OVERLAP) {
 		free_sched_groups(sd->groups, 1);
 	} else if (atomic_dec_and_test(&sd->groups->ref)) {
-		kfree(sd->groups->sgp);
+		kfree(sd->groups->sgc);
 		kfree(sd->groups);
 	}
 	kfree(sd);
@@ -5728,17 +5771,17 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 
 		cpumask_or(covered, covered, sg_span);
 
-		sg->sgp = *per_cpu_ptr(sdd->sgp, i);
-		if (atomic_inc_return(&sg->sgp->ref) == 1)
+		sg->sgc = *per_cpu_ptr(sdd->sgc, i);
+		if (atomic_inc_return(&sg->sgc->ref) == 1)
 			build_group_mask(sd, sg);
 
 		/*
-		 * Initialize sgp->power such that even if we mess up the
+		 * Initialize sgc->capacity such that even if we mess up the
 		 * domains and no possible iteration will get us here, we won't
 		 * die on a /0 trap.
 		 */
-		sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
-		sg->sgp->power_orig = sg->sgp->power;
+		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+		sg->sgc->capacity_orig = sg->sgc->capacity;
 
 		/*
 		 * Make sure the first group of this domain contains the
@@ -5776,8 +5819,8 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
 
 	if (sg) {
 		*sg = *per_cpu_ptr(sdd->sg, cpu);
-		(*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu);
-		atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */
+		(*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+		atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */
 	}
 
 	return cpu;
@@ -5786,7 +5829,7 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
 /*
  * build_sched_groups will build a circular linked list of the groups
  * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_power to 0.
+ * and ->cpu_capacity to 0.
  *
  * Assumes the sched_domain tree is fully constructed
  */
@@ -5840,16 +5883,16 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 }
 
 /*
- * Initialize sched groups cpu_power.
+ * Initialize sched groups cpu_capacity.
  *
- * cpu_power indicates the capacity of sched group, which is used while
+ * cpu_capacity indicates the capacity of sched group, which is used while
  * distributing the load between different sched groups in a sched domain.
- * Typically cpu_power for all the groups in a sched domain will be same unless
- * there are asymmetries in the topology. If there are asymmetries, group
- * having more cpu_power will pickup more load compared to the group having
- * less cpu_power.
+ * Typically cpu_capacity for all the groups in a sched domain will be same
+ * unless there are asymmetries in the topology. If there are asymmetries,
+ * group having more cpu_capacity will pickup more load compared to the
+ * group having less cpu_capacity.
  */
-static void init_sched_groups_power(int cpu, struct sched_domain *sd)
+static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
 {
 	struct sched_group *sg = sd->groups;
 
@@ -5863,8 +5906,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 	if (cpu != group_balance_cpu(sg))
 		return;
 
-	update_group_power(sd, cpu);
-	atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight);
+	update_group_capacity(sd, cpu);
+	atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight);
 }
 
 /*
@@ -5955,8 +5998,8 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
 	if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
 		*per_cpu_ptr(sdd->sg, cpu) = NULL;
 
-	if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref))
-		*per_cpu_ptr(sdd->sgp, cpu) = NULL;
+	if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref))
+		*per_cpu_ptr(sdd->sgc, cpu) = NULL;
 }
 
 #ifdef CONFIG_NUMA
@@ -5969,7 +6012,7 @@ static int sched_domains_curr_level;
 /*
  * SD_flags allowed in topology descriptions.
  *
- * SD_SHARE_CPUPOWER      - describes SMT topologies
+ * SD_SHARE_CPUCAPACITY      - describes SMT topologies
  * SD_SHARE_PKG_RESOURCES - describes shared caches
  * SD_NUMA                - describes NUMA topologies
  * SD_SHARE_POWERDOMAIN   - describes shared power domain
@@ -5978,7 +6021,7 @@ static int sched_domains_curr_level;
  * SD_ASYM_PACKING        - describes SMT quirks
  */
 #define TOPOLOGY_SD_FLAGS		\
-	(SD_SHARE_CPUPOWER |		\
+	(SD_SHARE_CPUCAPACITY |		\
 	 SD_SHARE_PKG_RESOURCES |	\
 	 SD_NUMA |			\
 	 SD_ASYM_PACKING |		\
@@ -6024,7 +6067,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 					| 1*SD_BALANCE_FORK
 					| 0*SD_BALANCE_WAKE
 					| 1*SD_WAKE_AFFINE
-					| 0*SD_SHARE_CPUPOWER
+					| 0*SD_SHARE_CPUCAPACITY
 					| 0*SD_SHARE_PKG_RESOURCES
 					| 0*SD_SERIALIZE
 					| 0*SD_PREFER_SIBLING
@@ -6046,7 +6089,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 	 * Convert topological properties into behaviour.
 	 */
 
-	if (sd->flags & SD_SHARE_CPUPOWER) {
+	if (sd->flags & SD_SHARE_CPUCAPACITY) {
 		sd->imbalance_pct = 110;
 		sd->smt_gain = 1178; /* ~15% */
 
@@ -6358,14 +6401,14 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 		if (!sdd->sg)
 			return -ENOMEM;
 
-		sdd->sgp = alloc_percpu(struct sched_group_power *);
-		if (!sdd->sgp)
+		sdd->sgc = alloc_percpu(struct sched_group_capacity *);
+		if (!sdd->sgc)
 			return -ENOMEM;
 
 		for_each_cpu(j, cpu_map) {
 			struct sched_domain *sd;
 			struct sched_group *sg;
-			struct sched_group_power *sgp;
+			struct sched_group_capacity *sgc;
 
 		       	sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
 					GFP_KERNEL, cpu_to_node(j));
@@ -6383,12 +6426,12 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 
 			*per_cpu_ptr(sdd->sg, j) = sg;
 
-			sgp = kzalloc_node(sizeof(struct sched_group_power) + cpumask_size(),
+			sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(),
 					GFP_KERNEL, cpu_to_node(j));
-			if (!sgp)
+			if (!sgc)
 				return -ENOMEM;
 
-			*per_cpu_ptr(sdd->sgp, j) = sgp;
+			*per_cpu_ptr(sdd->sgc, j) = sgc;
 		}
 	}
 
@@ -6415,15 +6458,15 @@ static void __sdt_free(const struct cpumask *cpu_map)
 
 			if (sdd->sg)
 				kfree(*per_cpu_ptr(sdd->sg, j));
-			if (sdd->sgp)
-				kfree(*per_cpu_ptr(sdd->sgp, j));
+			if (sdd->sgc)
+				kfree(*per_cpu_ptr(sdd->sgc, j));
 		}
 		free_percpu(sdd->sd);
 		sdd->sd = NULL;
 		free_percpu(sdd->sg);
 		sdd->sg = NULL;
-		free_percpu(sdd->sgp);
-		sdd->sgp = NULL;
+		free_percpu(sdd->sgc);
+		sdd->sgc = NULL;
 	}
 }
 
@@ -6441,6 +6484,20 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		sched_domain_level_max = max(sched_domain_level_max, sd->level);
 		child->parent = sd;
 		sd->child = child;
+
+		if (!cpumask_subset(sched_domain_span(child),
+				    sched_domain_span(sd))) {
+			pr_err("BUG: arch topology borken\n");
+#ifdef CONFIG_SCHED_DEBUG
+			pr_err("     the %s domain not a subset of the %s domain\n",
+					child->name, sd->name);
+#endif
+			/* Fixup, ensure @sd has at least @child cpus. */
+			cpumask_or(sched_domain_span(sd),
+				   sched_domain_span(sd),
+				   sched_domain_span(child));
+		}
+
 	}
 	set_domain_attribute(sd, attr);
 
@@ -6493,14 +6550,14 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 		}
 	}
 
-	/* Calculate CPU power for physical packages and nodes */
+	/* Calculate CPU capacity for physical packages and nodes */
 	for (i = nr_cpumask_bits-1; i >= 0; i--) {
 		if (!cpumask_test_cpu(i, cpu_map))
 			continue;
 
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
 			claim_allocations(i, sd);
-			init_sched_groups_power(i, sd);
+			init_sched_groups_capacity(i, sd);
 		}
 	}
 
@@ -6943,7 +7000,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
-		rq->cpu_power = SCHED_POWER_SCALE;
+		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
 		rq->post_schedule = 0;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
@@ -7068,7 +7125,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p)
 	__setscheduler(rq, p, &attr);
 	if (on_rq) {
 		enqueue_task(rq, p, 0);
-		resched_task(rq->curr);
+		resched_curr(rq);
 	}
 
 	check_class_changed(rq, p, prev_class, old_prio);
@@ -7669,7 +7726,7 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
-	struct task_group *parent = css_tg(css_parent(css));
+	struct task_group *parent = css_tg(css->parent);
 
 	if (parent)
 		sched_online_group(tg, parent);
@@ -7779,6 +7836,11 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 	if (period > max_cfs_quota_period)
 		return -EINVAL;
 
+	/*
+	 * Prevent race between setting of cfs_rq->runtime_enabled and
+	 * unthrottle_offline_cfs_rqs().
+	 */
+	get_online_cpus();
 	mutex_lock(&cfs_constraints_mutex);
 	ret = __cfs_schedulable(tg, period, quota);
 	if (ret)
@@ -7804,7 +7866,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 	}
 	raw_spin_unlock_irq(&cfs_b->lock);
 
-	for_each_possible_cpu(i) {
+	for_each_online_cpu(i) {
 		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
 		struct rq *rq = cfs_rq->rq;
 
@@ -7820,6 +7882,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 		cfs_bandwidth_usage_dec();
 out_unlock:
 	mutex_unlock(&cfs_constraints_mutex);
+	put_online_cpus();
 
 	return ret;
 }
@@ -8059,7 +8122,7 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,
-	.base_cftypes	= cpu_files,
+	.legacy_cftypes	= cpu_files,
 	.early_init	= 1,
 };
 
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index c143ee380e3..dd7cbb55bbf 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -46,7 +46,7 @@ static inline struct cpuacct *task_ca(struct task_struct *tsk)
 
 static inline struct cpuacct *parent_ca(struct cpuacct *ca)
 {
-	return css_ca(css_parent(&ca->css));
+	return css_ca(ca->css.parent);
 }
 
 static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage);
@@ -278,6 +278,6 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val)
 struct cgroup_subsys cpuacct_cgrp_subsys = {
 	.css_alloc	= cpuacct_css_alloc,
 	.css_free	= cpuacct_css_free,
-	.base_cftypes	= files,
+	.legacy_cftypes	= files,
 	.early_init	= 1,
 };
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 2b8cbf09d1a..255ce138b65 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -57,8 +57,6 @@ void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
 	dl_b->dl_runtime = runtime;
 }
 
-extern unsigned long to_ratio(u64 period, u64 runtime);
-
 void init_dl_bw(struct dl_bw *dl_b)
 {
 	raw_spin_lock_init(&dl_b->lock);
@@ -308,7 +306,7 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
  * the overrunning entity can't interfere with other entity in the system and
  * can't make them miss their deadlines. Reasons why this kind of overruns
  * could happen are, typically, a entity voluntarily trying to overcome its
- * runtime, or it just underestimated it during sched_setscheduler_ex().
+ * runtime, or it just underestimated it during sched_setattr().
  */
 static void replenish_dl_entity(struct sched_dl_entity *dl_se,
 				struct sched_dl_entity *pi_se)
@@ -537,7 +535,7 @@ again:
 		if (task_has_dl_policy(rq->curr))
 			check_preempt_curr_dl(rq, p, 0);
 		else
-			resched_task(rq->curr);
+			resched_curr(rq);
 #ifdef CONFIG_SMP
 		/*
 		 * Queueing this task back might have overloaded rq,
@@ -636,7 +634,7 @@ static void update_curr_dl(struct rq *rq)
 			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
 
 		if (!is_leftmost(curr, &rq->dl))
-			resched_task(curr);
+			resched_curr(rq);
 	}
 
 	/*
@@ -966,7 +964,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 	    cpudl_find(&rq->rd->cpudl, p, NULL) != -1)
 		return;
 
-	resched_task(rq->curr);
+	resched_curr(rq);
 }
 
 static int pull_dl_task(struct rq *this_rq);
@@ -981,7 +979,7 @@ static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
 				  int flags)
 {
 	if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
-		resched_task(rq->curr);
+		resched_curr(rq);
 		return;
 	}
 
@@ -1335,7 +1333,7 @@ retry:
 	if (dl_task(rq->curr) &&
 	    dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
 	    rq->curr->nr_cpus_allowed > 1) {
-		resched_task(rq->curr);
+		resched_curr(rq);
 		return 0;
 	}
 
@@ -1375,7 +1373,7 @@ retry:
 	set_task_cpu(next_task, later_rq->cpu);
 	activate_task(later_rq, next_task, 0);
 
-	resched_task(later_rq->curr);
+	resched_curr(later_rq);
 
 	double_unlock_balance(rq, later_rq);
 
@@ -1634,14 +1632,14 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 		 */
 		if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) &&
 		    rq->curr == p)
-			resched_task(p);
+			resched_curr(rq);
 #else
 		/*
 		 * Again, we don't know if p has a earlier
 		 * or later deadline, so let's blindly set a
 		 * (maybe not needed) rescheduling point.
 		 */
-		resched_task(p);
+		resched_curr(rq);
 #endif /* CONFIG_SMP */
 	} else
 		switched_to_dl(rq, p);
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 695f9773bb6..627b3c34b82 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -608,7 +608,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
-			do_div(avg_atom, nr_switches);
+			avg_atom = div64_ul(avg_atom, nr_switches);
 		else
 			avg_atom = -1LL;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 17de1956dda..bfa3c86d0d6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1017,7 +1017,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 static unsigned long weighted_cpuload(const int cpu);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
-static unsigned long power_of(int cpu);
+static unsigned long capacity_of(int cpu);
 static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
 
 /* Cached statistics for all CPUs within a node */
@@ -1026,11 +1026,11 @@ struct numa_stats {
 	unsigned long load;
 
 	/* Total compute capacity of CPUs on a node */
-	unsigned long power;
+	unsigned long compute_capacity;
 
 	/* Approximate capacity in terms of runnable tasks on a node */
-	unsigned long capacity;
-	int has_capacity;
+	unsigned long task_capacity;
+	int has_free_capacity;
 };
 
 /*
@@ -1046,7 +1046,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 
 		ns->nr_running += rq->nr_running;
 		ns->load += weighted_cpuload(cpu);
-		ns->power += power_of(cpu);
+		ns->compute_capacity += capacity_of(cpu);
 
 		cpus++;
 	}
@@ -1056,15 +1056,15 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	 * the @ns structure is NULL'ed and task_numa_compare() will
 	 * not find this node attractive.
 	 *
-	 * We'll either bail at !has_capacity, or we'll detect a huge imbalance
-	 * and bail there.
+	 * We'll either bail at !has_free_capacity, or we'll detect a huge
+	 * imbalance and bail there.
 	 */
 	if (!cpus)
 		return;
 
-	ns->load = (ns->load * SCHED_POWER_SCALE) / ns->power;
-	ns->capacity = DIV_ROUND_CLOSEST(ns->power, SCHED_POWER_SCALE);
-	ns->has_capacity = (ns->nr_running < ns->capacity);
+	ns->task_capacity =
+		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE);
+	ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
 }
 
 struct task_numa_env {
@@ -1095,18 +1095,30 @@ static void task_numa_assign(struct task_numa_env *env,
 	env->best_cpu = env->dst_cpu;
 }
 
-static bool load_too_imbalanced(long orig_src_load, long orig_dst_load,
-				long src_load, long dst_load,
+static bool load_too_imbalanced(long src_load, long dst_load,
 				struct task_numa_env *env)
 {
 	long imb, old_imb;
+	long orig_src_load, orig_dst_load;
+	long src_capacity, dst_capacity;
+
+	/*
+	 * The load is corrected for the CPU capacity available on each node.
+	 *
+	 * src_load        dst_load
+	 * ------------ vs ---------
+	 * src_capacity    dst_capacity
+	 */
+	src_capacity = env->src_stats.compute_capacity;
+	dst_capacity = env->dst_stats.compute_capacity;
 
 	/* We care about the slope of the imbalance, not the direction. */
 	if (dst_load < src_load)
 		swap(dst_load, src_load);
 
 	/* Is the difference below the threshold? */
-	imb = dst_load * 100 - src_load * env->imbalance_pct;
+	imb = dst_load * src_capacity * 100 -
+	      src_load * dst_capacity * env->imbalance_pct;
 	if (imb <= 0)
 		return false;
 
@@ -1114,13 +1126,17 @@ static bool load_too_imbalanced(long orig_src_load, long orig_dst_load,
 	 * The imbalance is above the allowed threshold.
 	 * Compare it with the old imbalance.
 	 */
+	orig_src_load = env->src_stats.load;
+	orig_dst_load = env->dst_stats.load;
+
 	if (orig_dst_load < orig_src_load)
 		swap(orig_dst_load, orig_src_load);
 
-	old_imb = orig_dst_load * 100 - orig_src_load * env->imbalance_pct;
+	old_imb = orig_dst_load * src_capacity * 100 -
+		  orig_src_load * dst_capacity * env->imbalance_pct;
 
 	/* Would this change make things worse? */
-	return (old_imb > imb);
+	return (imb > old_imb);
 }
 
 /*
@@ -1135,10 +1151,10 @@ static void task_numa_compare(struct task_numa_env *env,
 	struct rq *src_rq = cpu_rq(env->src_cpu);
 	struct rq *dst_rq = cpu_rq(env->dst_cpu);
 	struct task_struct *cur;
-	long orig_src_load, src_load;
-	long orig_dst_load, dst_load;
+	long src_load, dst_load;
 	long load;
-	long imp = (groupimp > 0) ? groupimp : taskimp;
+	long imp = env->p->numa_group ? groupimp : taskimp;
+	long moveimp = imp;
 
 	rcu_read_lock();
 	cur = ACCESS_ONCE(dst_rq->curr);
@@ -1176,11 +1192,6 @@ static void task_numa_compare(struct task_numa_env *env,
 			 * itself (not part of a group), use the task weight
 			 * instead.
 			 */
-			if (env->p->numa_group)
-				imp = groupimp;
-			else
-				imp = taskimp;
-
 			if (cur->numa_group)
 				imp += group_weight(cur, env->src_nid) -
 				       group_weight(cur, env->dst_nid);
@@ -1190,33 +1201,47 @@ static void task_numa_compare(struct task_numa_env *env,
 		}
 	}
 
-	if (imp < env->best_imp)
+	if (imp <= env->best_imp && moveimp <= env->best_imp)
 		goto unlock;
 
 	if (!cur) {
 		/* Is there capacity at our destination? */
-		if (env->src_stats.has_capacity &&
-		    !env->dst_stats.has_capacity)
+		if (env->src_stats.has_free_capacity &&
+		    !env->dst_stats.has_free_capacity)
 			goto unlock;
 
 		goto balance;
 	}
 
 	/* Balance doesn't matter much if we're running a task per cpu */
-	if (src_rq->nr_running == 1 && dst_rq->nr_running == 1)
+	if (imp > env->best_imp && src_rq->nr_running == 1 &&
+			dst_rq->nr_running == 1)
 		goto assign;
 
 	/*
 	 * In the overloaded case, try and keep the load balanced.
 	 */
 balance:
-	orig_dst_load = env->dst_stats.load;
-	orig_src_load = env->src_stats.load;
-
-	/* XXX missing power terms */
 	load = task_h_load(env->p);
-	dst_load = orig_dst_load + load;
-	src_load = orig_src_load - load;
+	dst_load = env->dst_stats.load + load;
+	src_load = env->src_stats.load - load;
+
+	if (moveimp > imp && moveimp > env->best_imp) {
+		/*
+		 * If the improvement from just moving env->p direction is
+		 * better than swapping tasks around, check if a move is
+		 * possible. Store a slightly smaller score than moveimp,
+		 * so an actually idle CPU will win.
+		 */
+		if (!load_too_imbalanced(src_load, dst_load, env)) {
+			imp = moveimp - 1;
+			cur = NULL;
+			goto assign;
+		}
+	}
+
+	if (imp <= env->best_imp)
+		goto unlock;
 
 	if (cur) {
 		load = task_h_load(cur);
@@ -1224,8 +1249,7 @@ balance:
 		src_load += load;
 	}
 
-	if (load_too_imbalanced(orig_src_load, orig_dst_load,
-				src_load, dst_load, env))
+	if (load_too_imbalanced(src_load, dst_load, env))
 		goto unlock;
 
 assign:
@@ -1301,9 +1325,8 @@ static int task_numa_migrate(struct task_struct *p)
 	groupimp = group_weight(p, env.dst_nid) - groupweight;
 	update_numa_stats(&env.dst_stats, env.dst_nid);
 
-	/* If the preferred nid has capacity, try to use it. */
-	if (env.dst_stats.has_capacity)
-		task_numa_find_cpu(&env, taskimp, groupimp);
+	/* Try to find a spot on the preferred nid. */
+	task_numa_find_cpu(&env, taskimp, groupimp);
 
 	/* No space available on the preferred nid. Look elsewhere. */
 	if (env.best_cpu == -1) {
@@ -1323,10 +1346,6 @@ static int task_numa_migrate(struct task_struct *p)
 		}
 	}
 
-	/* No better CPU than the current one was found. */
-	if (env.best_cpu == -1)
-		return -EAGAIN;
-
 	/*
 	 * If the task is part of a workload that spans multiple NUMA nodes,
 	 * and is migrating into one of the workload's active nodes, remember
@@ -1335,8 +1354,19 @@ static int task_numa_migrate(struct task_struct *p)
 	 * A task that migrated to a second choice node will be better off
 	 * trying for a better one later. Do not set the preferred node here.
 	 */
-	if (p->numa_group && node_isset(env.dst_nid, p->numa_group->active_nodes))
-		sched_setnuma(p, env.dst_nid);
+	if (p->numa_group) {
+		if (env.best_cpu == -1)
+			nid = env.src_nid;
+		else
+			nid = env.dst_nid;
+
+		if (node_isset(nid, p->numa_group->active_nodes))
+			sched_setnuma(p, env.dst_nid);
+	}
+
+	/* No better CPU than the current one was found. */
+	if (env.best_cpu == -1)
+		return -EAGAIN;
 
 	/*
 	 * Reset the scan period if the task is being rescheduled on an
@@ -1414,12 +1444,12 @@ static void update_numa_active_node_mask(struct numa_group *numa_group)
 /*
  * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS
  * increments. The more local the fault statistics are, the higher the scan
- * period will be for the next scan window. If local/remote ratio is below
- * NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) the
- * scan period will decrease
+ * period will be for the next scan window. If local/(local+remote) ratio is
+ * below NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS)
+ * the scan period will decrease. Aim for 70% local accesses.
  */
 #define NUMA_PERIOD_SLOTS 10
-#define NUMA_PERIOD_THRESHOLD 3
+#define NUMA_PERIOD_THRESHOLD 7
 
 /*
  * Increase the scan period (slow down scanning) if the majority of
@@ -1594,30 +1624,17 @@ static void task_numa_placement(struct task_struct *p)
 
 	if (p->numa_group) {
 		update_numa_active_node_mask(p->numa_group);
-		/*
-		 * If the preferred task and group nids are different,
-		 * iterate over the nodes again to find the best place.
-		 */
-		if (max_nid != max_group_nid) {
-			unsigned long weight, max_weight = 0;
-
-			for_each_online_node(nid) {
-				weight = task_weight(p, nid) + group_weight(p, nid);
-				if (weight > max_weight) {
-					max_weight = weight;
-					max_nid = nid;
-				}
-			}
-		}
-
 		spin_unlock_irq(group_lock);
+		max_nid = max_group_nid;
 	}
 
-	/* Preferred node as the node with the most faults */
-	if (max_faults && max_nid != p->numa_preferred_nid) {
-		/* Update the preferred nid and migrate task if possible */
-		sched_setnuma(p, max_nid);
-		numa_migrate_preferred(p);
+	if (max_faults) {
+		/* Set the new preferred node */
+		if (max_nid != p->numa_preferred_nid)
+			sched_setnuma(p, max_nid);
+
+		if (task_node(p) != p->numa_preferred_nid)
+			numa_migrate_preferred(p);
 	}
 }
 
@@ -2898,7 +2915,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 	ideal_runtime = sched_slice(cfs_rq, curr);
 	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
 	if (delta_exec > ideal_runtime) {
-		resched_task(rq_of(cfs_rq)->curr);
+		resched_curr(rq_of(cfs_rq));
 		/*
 		 * The current task ran long enough, ensure it doesn't get
 		 * re-elected due to buddy favours.
@@ -2922,7 +2939,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		return;
 
 	if (delta > ideal_runtime)
-		resched_task(rq_of(cfs_rq)->curr);
+		resched_curr(rq_of(cfs_rq));
 }
 
 static void
@@ -3062,7 +3079,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	 * validating it and just reschedule.
 	 */
 	if (queued) {
-		resched_task(rq_of(cfs_rq)->curr);
+		resched_curr(rq_of(cfs_rq));
 		return;
 	}
 	/*
@@ -3225,10 +3242,12 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	 * has not truly expired.
 	 *
 	 * Fortunately we can check determine whether this the case by checking
-	 * whether the global deadline has advanced.
+	 * whether the global deadline has advanced. It is valid to compare
+	 * cfs_b->runtime_expires without any locks since we only care about
+	 * exact equality, so a partial write will still work.
 	 */
 
-	if ((s64)(cfs_rq->runtime_expires - cfs_b->runtime_expires) >= 0) {
+	if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
 		/* extend local deadline, drift is bounded above by 2 ticks */
 		cfs_rq->runtime_expires += TICK_NSEC;
 	} else {
@@ -3251,7 +3270,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 	 * hierarchy can be throttled
 	 */
 	if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
-		resched_task(rq_of(cfs_rq)->curr);
+		resched_curr(rq_of(cfs_rq));
 }
 
 static __always_inline
@@ -3357,7 +3376,11 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	cfs_rq->throttled = 1;
 	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
-	list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+	/*
+	 * Add to the _head_ of the list, so that an already-started
+	 * distribute_cfs_runtime will not see us
+	 */
+	list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
 	if (!cfs_b->timer_active)
 		__start_cfs_bandwidth(cfs_b, false);
 	raw_spin_unlock(&cfs_b->lock);
@@ -3407,14 +3430,15 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	/* determine whether we need to wake up potentially idle cpu */
 	if (rq->curr == rq->idle && rq->cfs.nr_running)
-		resched_task(rq->curr);
+		resched_curr(rq);
 }
 
 static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
 		u64 remaining, u64 expires)
 {
 	struct cfs_rq *cfs_rq;
-	u64 runtime = remaining;
+	u64 runtime;
+	u64 starting_runtime = remaining;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
@@ -3445,7 +3469,7 @@ next:
 	}
 	rcu_read_unlock();
 
-	return remaining;
+	return starting_runtime - remaining;
 }
 
 /*
@@ -3457,21 +3481,21 @@ next:
 static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 {
 	u64 runtime, runtime_expires;
-	int idle = 1, throttled;
+	int throttled;
 
-	raw_spin_lock(&cfs_b->lock);
 	/* no need to continue the timer with no bandwidth constraint */
 	if (cfs_b->quota == RUNTIME_INF)
-		goto out_unlock;
+		goto out_deactivate;
 
 	throttled = !list_empty(&cfs_b->throttled_cfs_rq);
-	/* idle depends on !throttled (for the case of a large deficit) */
-	idle = cfs_b->idle && !throttled;
 	cfs_b->nr_periods += overrun;
 
-	/* if we're going inactive then everything else can be deferred */
-	if (idle)
-		goto out_unlock;
+	/*
+	 * idle depends on !throttled (for the case of a large deficit), and if
+	 * we're going inactive then everything else can be deferred
+	 */
+	if (cfs_b->idle && !throttled)
+		goto out_deactivate;
 
 	/*
 	 * if we have relooped after returning idle once, we need to update our
@@ -3485,28 +3509,23 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	if (!throttled) {
 		/* mark as potentially idle for the upcoming period */
 		cfs_b->idle = 1;
-		goto out_unlock;
+		return 0;
 	}
 
 	/* account preceding periods in which throttling occurred */
 	cfs_b->nr_throttled += overrun;
 
-	/*
-	 * There are throttled entities so we must first use the new bandwidth
-	 * to unthrottle them before making it generally available.  This
-	 * ensures that all existing debts will be paid before a new cfs_rq is
-	 * allowed to run.
-	 */
-	runtime = cfs_b->runtime;
 	runtime_expires = cfs_b->runtime_expires;
-	cfs_b->runtime = 0;
 
 	/*
-	 * This check is repeated as we are holding onto the new bandwidth
-	 * while we unthrottle.  This can potentially race with an unthrottled
-	 * group trying to acquire new bandwidth from the global pool.
+	 * This check is repeated as we are holding onto the new bandwidth while
+	 * we unthrottle. This can potentially race with an unthrottled group
+	 * trying to acquire new bandwidth from the global pool. This can result
+	 * in us over-using our runtime if it is all used during this loop, but
+	 * only by limited amounts in that extreme case.
 	 */
-	while (throttled && runtime > 0) {
+	while (throttled && cfs_b->runtime > 0) {
+		runtime = cfs_b->runtime;
 		raw_spin_unlock(&cfs_b->lock);
 		/* we can't nest cfs_b->lock while distributing bandwidth */
 		runtime = distribute_cfs_runtime(cfs_b, runtime,
@@ -3514,10 +3533,10 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 		raw_spin_lock(&cfs_b->lock);
 
 		throttled = !list_empty(&cfs_b->throttled_cfs_rq);
+
+		cfs_b->runtime -= min(runtime, cfs_b->runtime);
 	}
 
-	/* return (any) remaining runtime */
-	cfs_b->runtime = runtime;
 	/*
 	 * While we are ensured activity in the period following an
 	 * unthrottle, this also covers the case in which the new bandwidth is
@@ -3525,12 +3544,12 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
 	 * timer to remain active while there are any throttled entities.)
 	 */
 	cfs_b->idle = 0;
-out_unlock:
-	if (idle)
-		cfs_b->timer_active = 0;
-	raw_spin_unlock(&cfs_b->lock);
 
-	return idle;
+	return 0;
+
+out_deactivate:
+	cfs_b->timer_active = 0;
+	return 1;
 }
 
 /* a cfs_rq won't donate quota below this amount */
@@ -3628,10 +3647,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 		return;
 	}
 
-	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) {
+	if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice)
 		runtime = cfs_b->runtime;
-		cfs_b->runtime = 0;
-	}
+
 	expires = cfs_b->runtime_expires;
 	raw_spin_unlock(&cfs_b->lock);
 
@@ -3642,7 +3660,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
 
 	raw_spin_lock(&cfs_b->lock);
 	if (expires == cfs_b->runtime_expires)
-		cfs_b->runtime = runtime;
+		cfs_b->runtime -= min(runtime, cfs_b->runtime);
 	raw_spin_unlock(&cfs_b->lock);
 }
 
@@ -3707,6 +3725,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 	int overrun;
 	int idle = 0;
 
+	raw_spin_lock(&cfs_b->lock);
 	for (;;) {
 		now = hrtimer_cb_get_time(timer);
 		overrun = hrtimer_forward(timer, now, cfs_b->period);
@@ -3716,6 +3735,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 
 		idle = do_sched_cfs_period_timer(cfs_b, overrun);
 	}
+	raw_spin_unlock(&cfs_b->lock);
 
 	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
 }
@@ -3770,13 +3790,24 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
 
-static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
+static void __maybe_unused update_runtime_enabled(struct rq *rq)
 {
 	struct cfs_rq *cfs_rq;
 
 	for_each_leaf_cfs_rq(rq, cfs_rq) {
-		struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
+		struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+
+		raw_spin_lock(&cfs_b->lock);
+		cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
+		raw_spin_unlock(&cfs_b->lock);
+	}
+}
 
+static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
+{
+	struct cfs_rq *cfs_rq;
+
+	for_each_leaf_cfs_rq(rq, cfs_rq) {
 		if (!cfs_rq->runtime_enabled)
 			continue;
 
@@ -3784,7 +3815,13 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 		 * clock_task is not advancing so we just need to make sure
 		 * there's some valid quota amount
 		 */
-		cfs_rq->runtime_remaining = cfs_b->quota;
+		cfs_rq->runtime_remaining = 1;
+		/*
+		 * Offline rq is schedulable till cpu is completely disabled
+		 * in take_cpu_down(), so we prevent new cfs throttling here.
+		 */
+		cfs_rq->runtime_enabled = 0;
+
 		if (cfs_rq_throttled(cfs_rq))
 			unthrottle_cfs_rq(cfs_rq);
 	}
@@ -3828,6 +3865,7 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
 	return NULL;
 }
 static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
+static inline void update_runtime_enabled(struct rq *rq) {}
 static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
 
 #endif /* CONFIG_CFS_BANDWIDTH */
@@ -3851,7 +3889,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 
 		if (delta < 0) {
 			if (rq->curr == p)
-				resched_task(p);
+				resched_curr(rq);
 			return;
 		}
 
@@ -4041,9 +4079,9 @@ static unsigned long target_load(int cpu, int type)
 	return max(rq->cpu_load[type-1], total);
 }
 
-static unsigned long power_of(int cpu)
+static unsigned long capacity_of(int cpu)
 {
-	return cpu_rq(cpu)->cpu_power;
+	return cpu_rq(cpu)->cpu_capacity;
 }
 
 static unsigned long cpu_avg_load_per_task(int cpu)
@@ -4065,7 +4103,7 @@ static void record_wakee(struct task_struct *p)
 	 * about the boundary, really active task won't care
 	 * about the loss.
 	 */
-	if (jiffies > current->wakee_flip_decay_ts + HZ) {
+	if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) {
 		current->wakee_flips >>= 1;
 		current->wakee_flip_decay_ts = jiffies;
 	}
@@ -4286,12 +4324,12 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 		s64 this_eff_load, prev_eff_load;
 
 		this_eff_load = 100;
-		this_eff_load *= power_of(prev_cpu);
+		this_eff_load *= capacity_of(prev_cpu);
 		this_eff_load *= this_load +
 			effective_load(tg, this_cpu, weight, weight);
 
 		prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
-		prev_eff_load *= power_of(this_cpu);
+		prev_eff_load *= capacity_of(this_cpu);
 		prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight);
 
 		balanced = this_eff_load <= prev_eff_load;
@@ -4367,8 +4405,8 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 			avg_load += load;
 		}
 
-		/* Adjust by relative CPU power of the group */
-		avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power;
+		/* Adjust by relative CPU capacity of the group */
+		avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity;
 
 		if (local_group) {
 			this_load = avg_load;
@@ -4720,7 +4758,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	return;
 
 preempt:
-	resched_task(curr);
+	resched_curr(rq);
 	/*
 	 * Only set the backward buddy when the current task is still
 	 * on the rq. This can happen when a wakeup gets interleaved
@@ -4948,14 +4986,14 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp
  *
  *   W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0               (3)
  *
- * P_i is the cpu power (or compute capacity) of cpu i, typically it is the
+ * C_i is the compute capacity of cpu i, typically it is the
  * fraction of 'recent' time available for SCHED_OTHER task execution. But it
  * can also include other factors [XXX].
  *
  * To achieve this balance we define a measure of imbalance which follows
  * directly from (1):
  *
- *   imb_i,j = max{ avg(W/P), W_i/P_i } - min{ avg(W/P), W_j/P_j }    (4)
+ *   imb_i,j = max{ avg(W/C), W_i/C_i } - min{ avg(W/C), W_j/C_j }    (4)
  *
  * We them move tasks around to minimize the imbalance. In the continuous
  * function space it is obvious this converges, in the discrete case we get
@@ -5091,8 +5129,7 @@ static void move_task(struct task_struct *p, struct lb_env *env)
 /*
  * Is this task likely cache-hot:
  */
-static int
-task_hot(struct task_struct *p, u64 now)
+static int task_hot(struct task_struct *p, struct lb_env *env)
 {
 	s64 delta;
 
@@ -5105,7 +5142,7 @@ task_hot(struct task_struct *p, u64 now)
 	/*
 	 * Buddy candidates are cache hot:
 	 */
-	if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
+	if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running &&
 			(&p->se == cfs_rq_of(&p->se)->next ||
 			 &p->se == cfs_rq_of(&p->se)->last))
 		return 1;
@@ -5115,7 +5152,7 @@ task_hot(struct task_struct *p, u64 now)
 	if (sysctl_sched_migration_cost == 0)
 		return 0;
 
-	delta = now - p->se.exec_start;
+	delta = rq_clock_task(env->src_rq) - p->se.exec_start;
 
 	return delta < (s64)sysctl_sched_migration_cost;
 }
@@ -5269,7 +5306,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	 * 2) task is cache cold, or
 	 * 3) too many balance attempts have failed.
 	 */
-	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq));
+	tsk_cache_hot = task_hot(p, env);
 	if (!tsk_cache_hot)
 		tsk_cache_hot = migrate_degrades_locality(p, env);
 
@@ -5530,13 +5567,13 @@ struct sg_lb_stats {
 	unsigned long group_load; /* Total load over the CPUs of the group */
 	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
 	unsigned long load_per_task;
-	unsigned long group_power;
+	unsigned long group_capacity;
 	unsigned int sum_nr_running; /* Nr tasks running in the group */
-	unsigned int group_capacity;
+	unsigned int group_capacity_factor;
 	unsigned int idle_cpus;
 	unsigned int group_weight;
 	int group_imb; /* Is there an imbalance in the group ? */
-	int group_has_capacity; /* Is there extra capacity in the group? */
+	int group_has_free_capacity;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
 	unsigned int nr_preferred_running;
@@ -5551,7 +5588,7 @@ struct sd_lb_stats {
 	struct sched_group *busiest;	/* Busiest group in this sd */
 	struct sched_group *local;	/* Local group in this sd */
 	unsigned long total_load;	/* Total load of all groups in sd */
-	unsigned long total_pwr;	/* Total power of all groups in sd */
+	unsigned long total_capacity;	/* Total capacity of all groups in sd */
 	unsigned long avg_load;	/* Average load across all groups in sd */
 
 	struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */
@@ -5570,7 +5607,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds)
 		.busiest = NULL,
 		.local = NULL,
 		.total_load = 0UL,
-		.total_pwr = 0UL,
+		.total_capacity = 0UL,
 		.busiest_stat = {
 			.avg_load = 0UL,
 		},
@@ -5605,17 +5642,17 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 	return load_idx;
 }
 
-static unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
+static unsigned long default_scale_capacity(struct sched_domain *sd, int cpu)
 {
-	return SCHED_POWER_SCALE;
+	return SCHED_CAPACITY_SCALE;
 }
 
-unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
+unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
 {
-	return default_scale_freq_power(sd, cpu);
+	return default_scale_capacity(sd, cpu);
 }
 
-static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
+static unsigned long default_scale_smt_capacity(struct sched_domain *sd, int cpu)
 {
 	unsigned long weight = sd->span_weight;
 	unsigned long smt_gain = sd->smt_gain;
@@ -5625,12 +5662,12 @@ static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
 	return smt_gain;
 }
 
-unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
+unsigned long __weak arch_scale_smt_capacity(struct sched_domain *sd, int cpu)
 {
-	return default_scale_smt_power(sd, cpu);
+	return default_scale_smt_capacity(sd, cpu);
 }
 
-static unsigned long scale_rt_power(int cpu)
+static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	u64 total, available, age_stamp, avg;
@@ -5650,71 +5687,71 @@ static unsigned long scale_rt_power(int cpu)
 	total = sched_avg_period() + delta;
 
 	if (unlikely(total < avg)) {
-		/* Ensures that power won't end up being negative */
+		/* Ensures that capacity won't end up being negative */
 		available = 0;
 	} else {
 		available = total - avg;
 	}
 
-	if (unlikely((s64)total < SCHED_POWER_SCALE))
-		total = SCHED_POWER_SCALE;
+	if (unlikely((s64)total < SCHED_CAPACITY_SCALE))
+		total = SCHED_CAPACITY_SCALE;
 
-	total >>= SCHED_POWER_SHIFT;
+	total >>= SCHED_CAPACITY_SHIFT;
 
 	return div_u64(available, total);
 }
 
-static void update_cpu_power(struct sched_domain *sd, int cpu)
+static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
 	unsigned long weight = sd->span_weight;
-	unsigned long power = SCHED_POWER_SCALE;
+	unsigned long capacity = SCHED_CAPACITY_SCALE;
 	struct sched_group *sdg = sd->groups;
 
-	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-		if (sched_feat(ARCH_POWER))
-			power *= arch_scale_smt_power(sd, cpu);
+	if ((sd->flags & SD_SHARE_CPUCAPACITY) && weight > 1) {
+		if (sched_feat(ARCH_CAPACITY))
+			capacity *= arch_scale_smt_capacity(sd, cpu);
 		else
-			power *= default_scale_smt_power(sd, cpu);
+			capacity *= default_scale_smt_capacity(sd, cpu);
 
-		power >>= SCHED_POWER_SHIFT;
+		capacity >>= SCHED_CAPACITY_SHIFT;
 	}
 
-	sdg->sgp->power_orig = power;
+	sdg->sgc->capacity_orig = capacity;
 
-	if (sched_feat(ARCH_POWER))
-		power *= arch_scale_freq_power(sd, cpu);
+	if (sched_feat(ARCH_CAPACITY))
+		capacity *= arch_scale_freq_capacity(sd, cpu);
 	else
-		power *= default_scale_freq_power(sd, cpu);
+		capacity *= default_scale_capacity(sd, cpu);
 
-	power >>= SCHED_POWER_SHIFT;
+	capacity >>= SCHED_CAPACITY_SHIFT;
 
-	power *= scale_rt_power(cpu);
-	power >>= SCHED_POWER_SHIFT;
+	capacity *= scale_rt_capacity(cpu);
+	capacity >>= SCHED_CAPACITY_SHIFT;
 
-	if (!power)
-		power = 1;
+	if (!capacity)
+		capacity = 1;
 
-	cpu_rq(cpu)->cpu_power = power;
-	sdg->sgp->power = power;
+	cpu_rq(cpu)->cpu_capacity = capacity;
+	sdg->sgc->capacity = capacity;
 }
 
-void update_group_power(struct sched_domain *sd, int cpu)
+void update_group_capacity(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
-	unsigned long power, power_orig;
+	unsigned long capacity, capacity_orig;
 	unsigned long interval;
 
 	interval = msecs_to_jiffies(sd->balance_interval);
 	interval = clamp(interval, 1UL, max_load_balance_interval);
-	sdg->sgp->next_update = jiffies + interval;
+	sdg->sgc->next_update = jiffies + interval;
 
 	if (!child) {
-		update_cpu_power(sd, cpu);
+		update_cpu_capacity(sd, cpu);
 		return;
 	}
 
-	power_orig = power = 0;
+	capacity_orig = capacity = 0;
 
 	if (child->flags & SD_OVERLAP) {
 		/*
@@ -5723,31 +5760,31 @@ void update_group_power(struct sched_domain *sd, int cpu)
 		 */
 
 		for_each_cpu(cpu, sched_group_cpus(sdg)) {
-			struct sched_group_power *sgp;
+			struct sched_group_capacity *sgc;
 			struct rq *rq = cpu_rq(cpu);
 
 			/*
-			 * build_sched_domains() -> init_sched_groups_power()
+			 * build_sched_domains() -> init_sched_groups_capacity()
 			 * gets here before we've attached the domains to the
 			 * runqueues.
 			 *
-			 * Use power_of(), which is set irrespective of domains
-			 * in update_cpu_power().
+			 * Use capacity_of(), which is set irrespective of domains
+			 * in update_cpu_capacity().
 			 *
-			 * This avoids power/power_orig from being 0 and
+			 * This avoids capacity/capacity_orig from being 0 and
 			 * causing divide-by-zero issues on boot.
 			 *
-			 * Runtime updates will correct power_orig.
+			 * Runtime updates will correct capacity_orig.
 			 */
 			if (unlikely(!rq->sd)) {
-				power_orig += power_of(cpu);
-				power += power_of(cpu);
+				capacity_orig += capacity_of(cpu);
+				capacity += capacity_of(cpu);
 				continue;
 			}
 
-			sgp = rq->sd->groups->sgp;
-			power_orig += sgp->power_orig;
-			power += sgp->power;
+			sgc = rq->sd->groups->sgc;
+			capacity_orig += sgc->capacity_orig;
+			capacity += sgc->capacity;
 		}
 	} else  {
 		/*
@@ -5757,14 +5794,14 @@ void update_group_power(struct sched_domain *sd, int cpu)
 
 		group = child->groups;
 		do {
-			power_orig += group->sgp->power_orig;
-			power += group->sgp->power;
+			capacity_orig += group->sgc->capacity_orig;
+			capacity += group->sgc->capacity;
 			group = group->next;
 		} while (group != child->groups);
 	}
 
-	sdg->sgp->power_orig = power_orig;
-	sdg->sgp->power = power;
+	sdg->sgc->capacity_orig = capacity_orig;
+	sdg->sgc->capacity = capacity;
 }
 
 /*
@@ -5778,15 +5815,15 @@ static inline int
 fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
 {
 	/*
-	 * Only siblings can have significantly less than SCHED_POWER_SCALE
+	 * Only siblings can have significantly less than SCHED_CAPACITY_SCALE
 	 */
-	if (!(sd->flags & SD_SHARE_CPUPOWER))
+	if (!(sd->flags & SD_SHARE_CPUCAPACITY))
 		return 0;
 
 	/*
-	 * If ~90% of the cpu_power is still there, we're good.
+	 * If ~90% of the cpu_capacity is still there, we're good.
 	 */
-	if (group->sgp->power * 32 > group->sgp->power_orig * 29)
+	if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29)
 		return 1;
 
 	return 0;
@@ -5823,34 +5860,35 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
 
 static inline int sg_imbalanced(struct sched_group *group)
 {
-	return group->sgp->imbalance;
+	return group->sgc->imbalance;
 }
 
 /*
- * Compute the group capacity.
+ * Compute the group capacity factor.
  *
- * Avoid the issue where N*frac(smt_power) >= 1 creates 'phantom' cores by
+ * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by
  * first dividing out the smt factor and computing the actual number of cores
- * and limit power unit capacity with that.
+ * and limit unit capacity with that.
  */
-static inline int sg_capacity(struct lb_env *env, struct sched_group *group)
+static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group)
 {
-	unsigned int capacity, smt, cpus;
-	unsigned int power, power_orig;
+	unsigned int capacity_factor, smt, cpus;
+	unsigned int capacity, capacity_orig;
 
-	power = group->sgp->power;
-	power_orig = group->sgp->power_orig;
+	capacity = group->sgc->capacity;
+	capacity_orig = group->sgc->capacity_orig;
 	cpus = group->group_weight;
 
-	/* smt := ceil(cpus / power), assumes: 1 < smt_power < 2 */
-	smt = DIV_ROUND_UP(SCHED_POWER_SCALE * cpus, power_orig);
-	capacity = cpus / smt; /* cores */
+	/* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */
+	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig);
+	capacity_factor = cpus / smt; /* cores */
 
-	capacity = min_t(unsigned, capacity, DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE));
-	if (!capacity)
-		capacity = fix_small_capacity(env->sd, group);
+	capacity_factor = min_t(unsigned,
+		capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE));
+	if (!capacity_factor)
+		capacity_factor = fix_small_capacity(env->sd, group);
 
-	return capacity;
+	return capacity_factor;
 }
 
 /**
@@ -5860,10 +5898,12 @@ static inline int sg_capacity(struct lb_env *env, struct sched_group *group)
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
  * @local_group: Does group contain this_cpu.
  * @sgs: variable to hold the statistics for this group.
+ * @overload: Indicate more than one runnable task for any CPU.
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
 			struct sched_group *group, int load_idx,
-			int local_group, struct sg_lb_stats *sgs)
+			int local_group, struct sg_lb_stats *sgs,
+			bool *overload)
 {
 	unsigned long load;
 	int i;
@@ -5881,6 +5921,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 		sgs->group_load += load;
 		sgs->sum_nr_running += rq->nr_running;
+
+		if (rq->nr_running > 1)
+			*overload = true;
+
 #ifdef CONFIG_NUMA_BALANCING
 		sgs->nr_numa_running += rq->nr_numa_running;
 		sgs->nr_preferred_running += rq->nr_preferred_running;
@@ -5890,9 +5934,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			sgs->idle_cpus++;
 	}
 
-	/* Adjust by relative CPU power of the group */
-	sgs->group_power = group->sgp->power;
-	sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / sgs->group_power;
+	/* Adjust by relative CPU capacity of the group */
+	sgs->group_capacity = group->sgc->capacity;
+	sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity;
 
 	if (sgs->sum_nr_running)
 		sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
@@ -5900,10 +5944,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	sgs->group_weight = group->group_weight;
 
 	sgs->group_imb = sg_imbalanced(group);
-	sgs->group_capacity = sg_capacity(env, group);
+	sgs->group_capacity_factor = sg_capacity_factor(env, group);
 
-	if (sgs->group_capacity > sgs->sum_nr_running)
-		sgs->group_has_capacity = 1;
+	if (sgs->group_capacity_factor > sgs->sum_nr_running)
+		sgs->group_has_free_capacity = 1;
 }
 
 /**
@@ -5927,7 +5971,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 	if (sgs->avg_load <= sds->busiest_stat.avg_load)
 		return false;
 
-	if (sgs->sum_nr_running > sgs->group_capacity)
+	if (sgs->sum_nr_running > sgs->group_capacity_factor)
 		return true;
 
 	if (sgs->group_imb)
@@ -5991,6 +6035,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 	struct sched_group *sg = env->sd->groups;
 	struct sg_lb_stats tmp_sgs;
 	int load_idx, prefer_sibling = 0;
+	bool overload = false;
 
 	if (child && child->flags & SD_PREFER_SIBLING)
 		prefer_sibling = 1;
@@ -6007,28 +6052,29 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 			sgs = &sds->local_stat;
 
 			if (env->idle != CPU_NEWLY_IDLE ||
-			    time_after_eq(jiffies, sg->sgp->next_update))
-				update_group_power(env->sd, env->dst_cpu);
+			    time_after_eq(jiffies, sg->sgc->next_update))
+				update_group_capacity(env->sd, env->dst_cpu);
 		}
 
-		update_sg_lb_stats(env, sg, load_idx, local_group, sgs);
+		update_sg_lb_stats(env, sg, load_idx, local_group, sgs,
+						&overload);
 
 		if (local_group)
 			goto next_group;
 
 		/*
 		 * In case the child domain prefers tasks go to siblings
-		 * first, lower the sg capacity to one so that we'll try
+		 * first, lower the sg capacity factor to one so that we'll try
 		 * and move all the excess tasks away. We lower the capacity
 		 * of a group only if the local group has the capacity to fit
-		 * these excess tasks, i.e. nr_running < group_capacity. The
+		 * these excess tasks, i.e. nr_running < group_capacity_factor. The
 		 * extra check prevents the case where you always pull from the
 		 * heaviest group when it is already under-utilized (possible
 		 * with a large weight task outweighs the tasks on the system).
 		 */
 		if (prefer_sibling && sds->local &&
-		    sds->local_stat.group_has_capacity)
-			sgs->group_capacity = min(sgs->group_capacity, 1U);
+		    sds->local_stat.group_has_free_capacity)
+			sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U);
 
 		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
@@ -6038,13 +6084,20 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 next_group:
 		/* Now, start updating sd_lb_stats */
 		sds->total_load += sgs->group_load;
-		sds->total_pwr += sgs->group_power;
+		sds->total_capacity += sgs->group_capacity;
 
 		sg = sg->next;
 	} while (sg != env->sd->groups);
 
 	if (env->sd->flags & SD_NUMA)
 		env->fbq_type = fbq_classify_group(&sds->busiest_stat);
+
+	if (!env->sd->parent) {
+		/* update overload indicator if we are at root domain */
+		if (env->dst_rq->rd->overload != overload)
+			env->dst_rq->rd->overload = overload;
+	}
+
 }
 
 /**
@@ -6085,8 +6138,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
 		return 0;
 
 	env->imbalance = DIV_ROUND_CLOSEST(
-		sds->busiest_stat.avg_load * sds->busiest_stat.group_power,
-		SCHED_POWER_SCALE);
+		sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity,
+		SCHED_CAPACITY_SCALE);
 
 	return 1;
 }
@@ -6101,7 +6154,7 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
 static inline
 void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 {
-	unsigned long tmp, pwr_now = 0, pwr_move = 0;
+	unsigned long tmp, capa_now = 0, capa_move = 0;
 	unsigned int imbn = 2;
 	unsigned long scaled_busy_load_per_task;
 	struct sg_lb_stats *local, *busiest;
@@ -6115,8 +6168,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 		imbn = 1;
 
 	scaled_busy_load_per_task =
-		(busiest->load_per_task * SCHED_POWER_SCALE) /
-		busiest->group_power;
+		(busiest->load_per_task * SCHED_CAPACITY_SCALE) /
+		busiest->group_capacity;
 
 	if (busiest->avg_load + scaled_busy_load_per_task >=
 	    local->avg_load + (scaled_busy_load_per_task * imbn)) {
@@ -6126,38 +6179,38 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
 
 	/*
 	 * OK, we don't have enough imbalance to justify moving tasks,
-	 * however we may be able to increase total CPU power used by
+	 * however we may be able to increase total CPU capacity used by
 	 * moving them.
 	 */
 
-	pwr_now += busiest->group_power *
+	capa_now += busiest->group_capacity *
 			min(busiest->load_per_task, busiest->avg_load);
-	pwr_now += local->group_power *
+	capa_now += local->group_capacity *
 			min(local->load_per_task, local->avg_load);
-	pwr_now /= SCHED_POWER_SCALE;
+	capa_now /= SCHED_CAPACITY_SCALE;
 
 	/* Amount of load we'd subtract */
 	if (busiest->avg_load > scaled_busy_load_per_task) {
-		pwr_move += busiest->group_power *
+		capa_move += busiest->group_capacity *
 			    min(busiest->load_per_task,
 				busiest->avg_load - scaled_busy_load_per_task);
 	}
 
 	/* Amount of load we'd add */
-	if (busiest->avg_load * busiest->group_power <
-	    busiest->load_per_task * SCHED_POWER_SCALE) {
-		tmp = (busiest->avg_load * busiest->group_power) /
-		      local->group_power;
+	if (busiest->avg_load * busiest->group_capacity <
+	    busiest->load_per_task * SCHED_CAPACITY_SCALE) {
+		tmp = (busiest->avg_load * busiest->group_capacity) /
+		      local->group_capacity;
 	} else {
-		tmp = (busiest->load_per_task * SCHED_POWER_SCALE) /
-		      local->group_power;
+		tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) /
+		      local->group_capacity;
 	}
-	pwr_move += local->group_power *
+	capa_move += local->group_capacity *
 		    min(local->load_per_task, local->avg_load + tmp);
-	pwr_move /= SCHED_POWER_SCALE;
+	capa_move /= SCHED_CAPACITY_SCALE;
 
 	/* Move if we gain throughput */
-	if (pwr_move > pwr_now)
+	if (capa_move > capa_now)
 		env->imbalance = busiest->load_per_task;
 }
 
@@ -6187,7 +6240,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	/*
 	 * In the presence of smp nice balancing, certain scenarios can have
 	 * max load less than avg load(as we skip the groups at or below
-	 * its cpu_power, while calculating max_load..)
+	 * its cpu_capacity, while calculating max_load..)
 	 */
 	if (busiest->avg_load <= sds->avg_load ||
 	    local->avg_load >= sds->avg_load) {
@@ -6202,10 +6255,10 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 		 * have to drop below capacity to reach cpu-load equilibrium.
 		 */
 		load_above_capacity =
-			(busiest->sum_nr_running - busiest->group_capacity);
+			(busiest->sum_nr_running - busiest->group_capacity_factor);
 
-		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE);
-		load_above_capacity /= busiest->group_power;
+		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE);
+		load_above_capacity /= busiest->group_capacity;
 	}
 
 	/*
@@ -6220,9 +6273,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 
 	/* How much load to actually move to equalise the imbalance */
 	env->imbalance = min(
-		max_pull * busiest->group_power,
-		(sds->avg_load - local->avg_load) * local->group_power
-	) / SCHED_POWER_SCALE;
+		max_pull * busiest->group_capacity,
+		(sds->avg_load - local->avg_load) * local->group_capacity
+	) / SCHED_CAPACITY_SCALE;
 
 	/*
 	 * if *imbalance is less than the average load per runnable task
@@ -6276,7 +6329,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	if (!sds.busiest || busiest->sum_nr_running == 0)
 		goto out_balanced;
 
-	sds.avg_load = (SCHED_POWER_SCALE * sds.total_load) / sds.total_pwr;
+	sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load)
+						/ sds.total_capacity;
 
 	/*
 	 * If the busiest group is imbalanced the below checks don't
@@ -6287,8 +6341,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 		goto force_balance;
 
 	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
-	if (env->idle == CPU_NEWLY_IDLE && local->group_has_capacity &&
-	    !busiest->group_has_capacity)
+	if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity &&
+	    !busiest->group_has_free_capacity)
 		goto force_balance;
 
 	/*
@@ -6342,11 +6396,11 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 				     struct sched_group *group)
 {
 	struct rq *busiest = NULL, *rq;
-	unsigned long busiest_load = 0, busiest_power = 1;
+	unsigned long busiest_load = 0, busiest_capacity = 1;
 	int i;
 
 	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
-		unsigned long power, capacity, wl;
+		unsigned long capacity, capacity_factor, wl;
 		enum fbq_type rt;
 
 		rq = cpu_rq(i);
@@ -6374,34 +6428,34 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		if (rt > env->fbq_type)
 			continue;
 
-		power = power_of(i);
-		capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE);
-		if (!capacity)
-			capacity = fix_small_capacity(env->sd, group);
+		capacity = capacity_of(i);
+		capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE);
+		if (!capacity_factor)
+			capacity_factor = fix_small_capacity(env->sd, group);
 
 		wl = weighted_cpuload(i);
 
 		/*
 		 * When comparing with imbalance, use weighted_cpuload()
-		 * which is not scaled with the cpu power.
+		 * which is not scaled with the cpu capacity.
 		 */
-		if (capacity && rq->nr_running == 1 && wl > env->imbalance)
+		if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance)
 			continue;
 
 		/*
 		 * For the load comparisons with the other cpu's, consider
-		 * the weighted_cpuload() scaled with the cpu power, so that
-		 * the load can be moved away from the cpu that is potentially
-		 * running at a lower capacity.
+		 * the weighted_cpuload() scaled with the cpu capacity, so
+		 * that the load can be moved away from the cpu that is
+		 * potentially running at a lower capacity.
 		 *
-		 * Thus we're looking for max(wl_i / power_i), crosswise
+		 * Thus we're looking for max(wl_i / capacity_i), crosswise
 		 * multiplication to rid ourselves of the division works out
-		 * to: wl_i * power_j > wl_j * power_i;  where j is our
-		 * previous maximum.
+		 * to: wl_i * capacity_j > wl_j * capacity_i;  where j is
+		 * our previous maximum.
 		 */
-		if (wl * busiest_power > busiest_load * power) {
+		if (wl * busiest_capacity > busiest_load * capacity) {
 			busiest_load = wl;
-			busiest_power = power;
+			busiest_capacity = capacity;
 			busiest = rq;
 		}
 	}
@@ -6609,7 +6663,7 @@ more_balance:
 		 * We failed to reach balance because of affinity.
 		 */
 		if (sd_parent) {
-			int *group_imbalance = &sd_parent->groups->sgp->imbalance;
+			int *group_imbalance = &sd_parent->groups->sgc->imbalance;
 
 			if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) {
 				*group_imbalance = 1;
@@ -6762,7 +6816,8 @@ static int idle_balance(struct rq *this_rq)
 	 */
 	this_rq->idle_stamp = rq_clock(this_rq);
 
-	if (this_rq->avg_idle < sysctl_sched_migration_cost) {
+	if (this_rq->avg_idle < sysctl_sched_migration_cost ||
+	    !this_rq->rd->overload) {
 		rcu_read_lock();
 		sd = rcu_dereference_check_sched_domain(this_rq->sd);
 		if (sd)
@@ -6996,7 +7051,7 @@ static inline void set_cpu_sd_state_busy(void)
 		goto unlock;
 	sd->nohz_idle = 0;
 
-	atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+	atomic_inc(&sd->groups->sgc->nr_busy_cpus);
 unlock:
 	rcu_read_unlock();
 }
@@ -7013,7 +7068,7 @@ void set_cpu_sd_state_idle(void)
 		goto unlock;
 	sd->nohz_idle = 1;
 
-	atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+	atomic_dec(&sd->groups->sgc->nr_busy_cpus);
 unlock:
 	rcu_read_unlock();
 }
@@ -7192,12 +7247,17 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 
 		rq = cpu_rq(balance_cpu);
 
-		raw_spin_lock_irq(&rq->lock);
-		update_rq_clock(rq);
-		update_idle_cpu_load(rq);
-		raw_spin_unlock_irq(&rq->lock);
-
-		rebalance_domains(rq, CPU_IDLE);
+		/*
+		 * If time for next balance is due,
+		 * do the balance.
+		 */
+		if (time_after_eq(jiffies, rq->next_balance)) {
+			raw_spin_lock_irq(&rq->lock);
+			update_rq_clock(rq);
+			update_idle_cpu_load(rq);
+			raw_spin_unlock_irq(&rq->lock);
+			rebalance_domains(rq, CPU_IDLE);
+		}
 
 		if (time_after(this_rq->next_balance, rq->next_balance))
 			this_rq->next_balance = rq->next_balance;
@@ -7212,7 +7272,7 @@ end:
  * of an idle cpu is the system.
  *   - This rq has more than one task.
  *   - At any scheduler domain level, this cpu's scheduler group has multiple
- *     busy cpu's exceeding the group's power.
+ *     busy cpu's exceeding the group's capacity.
  *   - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
  *     domain span are idle.
  */
@@ -7220,7 +7280,7 @@ static inline int nohz_kick_needed(struct rq *rq)
 {
 	unsigned long now = jiffies;
 	struct sched_domain *sd;
-	struct sched_group_power *sgp;
+	struct sched_group_capacity *sgc;
 	int nr_busy, cpu = rq->cpu;
 
 	if (unlikely(rq->idle_balance))
@@ -7250,8 +7310,8 @@ static inline int nohz_kick_needed(struct rq *rq)
 	sd = rcu_dereference(per_cpu(sd_busy, cpu));
 
 	if (sd) {
-		sgp = sd->groups->sgp;
-		nr_busy = atomic_read(&sgp->nr_busy_cpus);
+		sgc = sd->groups->sgc;
+		nr_busy = atomic_read(&sgc->nr_busy_cpus);
 
 		if (nr_busy > 1)
 			goto need_kick_unlock;
@@ -7315,6 +7375,8 @@ void trigger_load_balance(struct rq *rq)
 static void rq_online_fair(struct rq *rq)
 {
 	update_sysctl();
+
+	update_runtime_enabled(rq);
 }
 
 static void rq_offline_fair(struct rq *rq)
@@ -7388,7 +7450,7 @@ static void task_fork_fair(struct task_struct *p)
 		 * 'current' within the tree based on its new key value.
 		 */
 		swap(curr->vruntime, se->vruntime);
-		resched_task(rq->curr);
+		resched_curr(rq);
 	}
 
 	se->vruntime -= cfs_rq->min_vruntime;
@@ -7413,7 +7475,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
 	 */
 	if (rq->curr == p) {
 		if (p->prio > oldprio)
-			resched_task(rq->curr);
+			resched_curr(rq);
 	} else
 		check_preempt_curr(rq, p, 0);
 }
@@ -7476,7 +7538,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
 	 * if we can still preempt the current task.
 	 */
 	if (rq->curr == p)
-		resched_task(rq->curr);
+		resched_curr(rq);
 	else
 		check_preempt_curr(rq, p, 0);
 }
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 5716929a2e3..90284d117fe 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -37,18 +37,18 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true)
 SCHED_FEAT(WAKEUP_PREEMPTION, true)
 
 /*
- * Use arch dependent cpu power functions
+ * Use arch dependent cpu capacity functions
  */
-SCHED_FEAT(ARCH_POWER, true)
+SCHED_FEAT(ARCH_CAPACITY, true)
 
 SCHED_FEAT(HRTICK, false)
 SCHED_FEAT(DOUBLE_TICK, false)
 SCHED_FEAT(LB_BIAS, true)
 
 /*
- * Decrement CPU power based on time not spent running tasks
+ * Decrement CPU capacity based on time not spent running tasks
  */
-SCHED_FEAT(NONTASK_POWER, true)
+SCHED_FEAT(NONTASK_CAPACITY, true)
 
 /*
  * Queue remote wakeups on the target CPU and process them
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 25b9423abce..9f1608f9981 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -12,6 +12,8 @@
 
 #include <trace/events/power.h>
 
+#include "sched.h"
+
 static int __read_mostly cpu_idle_force_poll;
 
 void cpu_idle_poll_ctrl(bool enable)
@@ -67,13 +69,17 @@ void __weak arch_cpu_idle(void)
  * cpuidle_idle_call - the main idle function
  *
  * NOTE: no locks or semaphores should be used here
+ *
+ * On archs that support TIF_POLLING_NRFLAG, is called with polling
+ * set, and it returns with polling set.  If it ever stops polling, it
+ * must clear the polling bit.
  */
 static void cpuidle_idle_call(void)
 {
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int next_state, entered_state;
-	bool broadcast;
+	unsigned int broadcast;
 
 	/*
 	 * Check if the idle task must be rescheduled. If it is the
@@ -129,7 +135,7 @@ use_default:
 		goto exit_idle;
 	}
 
-	broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);
+	broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP;
 
 	/*
 	 * Tell the time framework to switch to a broadcast timer
@@ -175,10 +181,22 @@ exit_idle:
 
 /*
  * Generic idle loop implementation
+ *
+ * Called with polling cleared.
  */
 static void cpu_idle_loop(void)
 {
 	while (1) {
+		/*
+		 * If the arch has a polling bit, we maintain an invariant:
+		 *
+		 * Our polling bit is clear if we're not scheduled (i.e. if
+		 * rq->curr != rq->idle).  This means that, if rq->idle has
+		 * the polling bit set, then setting need_resched is
+		 * guaranteed to cause the cpu to reschedule.
+		 */
+
+		__current_set_polling();
 		tick_nohz_idle_enter();
 
 		while (!need_resched()) {
@@ -218,6 +236,17 @@ static void cpu_idle_loop(void)
 		 */
 		preempt_set_need_resched();
 		tick_nohz_idle_exit();
+		__current_clr_polling();
+
+		/*
+		 * We promise to call sched_ttwu_pending and reschedule
+		 * if need_resched is set while polling is set.  That
+		 * means that clearing polling needs to be visible
+		 * before doing these things.
+		 */
+		smp_mb__after_atomic();
+
+		sched_ttwu_pending();
 		schedule_preempt_disabled();
 	}
 }
@@ -239,7 +268,6 @@ void cpu_startup_entry(enum cpuhp_state state)
 	 */
 	boot_init_stack_canary();
 #endif
-	__current_set_polling();
 	arch_cpu_idle_prepare();
 	cpu_idle_loop();
 }
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 879f2b75266..67ad4e7f506 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -20,7 +20,7 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
  */
 static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
 {
-	resched_task(rq->idle);
+	resched_curr(rq);
 }
 
 static struct task_struct *
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index b3512f1afce..5f6edca4faf 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -463,9 +463,10 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
 	struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
+	struct rq *rq = rq_of_rt_rq(rt_rq);
 	struct sched_rt_entity *rt_se;
 
-	int cpu = cpu_of(rq_of_rt_rq(rt_rq));
+	int cpu = cpu_of(rq);
 
 	rt_se = rt_rq->tg->rt_se[cpu];
 
@@ -476,7 +477,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 			enqueue_rt_entity(rt_se, false);
 
 		if (rt_rq->highest_prio.curr < curr->prio)
-			resched_task(curr);
+			resched_curr(rq);
 	}
 }
 
@@ -566,7 +567,7 @@ static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 		return;
 
 	enqueue_top_rt_rq(rt_rq);
-	resched_task(rq->curr);
+	resched_curr(rq);
 }
 
 static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
@@ -740,6 +741,9 @@ balanced:
 		rt_rq->rt_throttled = 0;
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 		raw_spin_unlock(&rt_b->rt_runtime_lock);
+
+		/* Make rt_rq available for pick_next_task() */
+		sched_rt_rq_enqueue(rt_rq);
 	}
 }
 
@@ -918,7 +922,6 @@ static void update_curr_rt(struct rq *rq)
 {
 	struct task_struct *curr = rq->curr;
 	struct sched_rt_entity *rt_se = &curr->rt;
-	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	u64 delta_exec;
 
 	if (curr->sched_class != &rt_sched_class)
@@ -943,13 +946,13 @@ static void update_curr_rt(struct rq *rq)
 		return;
 
 	for_each_sched_rt_entity(rt_se) {
-		rt_rq = rt_rq_of_se(rt_se);
+		struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 
 		if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
 			raw_spin_lock(&rt_rq->rt_runtime_lock);
 			rt_rq->rt_time += delta_exec;
 			if (sched_rt_runtime_exceeded(rt_rq))
-				resched_task(curr);
+				resched_curr(rq);
 			raw_spin_unlock(&rt_rq->rt_runtime_lock);
 		}
 	}
@@ -1364,7 +1367,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	 * to try and push current away:
 	 */
 	requeue_task_rt(rq, p, 1);
-	resched_task(rq->curr);
+	resched_curr(rq);
 }
 
 #endif /* CONFIG_SMP */
@@ -1375,7 +1378,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (p->prio < rq->curr->prio) {
-		resched_task(rq->curr);
+		resched_curr(rq);
 		return;
 	}
 
@@ -1691,7 +1694,7 @@ retry:
 	 * just reschedule current.
 	 */
 	if (unlikely(next_task->prio < rq->curr->prio)) {
-		resched_task(rq->curr);
+		resched_curr(rq);
 		return 0;
 	}
 
@@ -1738,7 +1741,7 @@ retry:
 	activate_task(lowest_rq, next_task, 0);
 	ret = 1;
 
-	resched_task(lowest_rq->curr);
+	resched_curr(lowest_rq);
 
 	double_unlock_balance(rq, lowest_rq);
 
@@ -1937,7 +1940,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
 		return;
 
 	if (pull_rt_task(rq))
-		resched_task(rq->curr);
+		resched_curr(rq);
 }
 
 void __init init_sched_rt_class(void)
@@ -1975,7 +1978,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 			check_resched = 0;
 #endif /* CONFIG_SMP */
 		if (check_resched && p->prio < rq->curr->prio)
-			resched_task(rq->curr);
+			resched_curr(rq);
 	}
 }
 
@@ -2004,11 +2007,11 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 		 * Only reschedule if p is still on the same runqueue.
 		 */
 		if (p->prio > rq->rt.highest_prio.curr && rq->curr == p)
-			resched_task(p);
+			resched_curr(rq);
 #else
 		/* For UP simply resched on drop of prio */
 		if (oldprio < p->prio)
-			resched_task(p);
+			resched_curr(rq);
 #endif /* CONFIG_SMP */
 	} else {
 		/*
@@ -2017,7 +2020,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 		 * then reschedule.
 		 */
 		if (p->prio < rq->curr->prio)
-			resched_task(rq->curr);
+			resched_curr(rq);
 	}
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e47679b04d1..579712f4e9d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -477,6 +477,9 @@ struct root_domain {
 	cpumask_var_t span;
 	cpumask_var_t online;
 
+	/* Indicate more than one runnable task for any CPU */
+	bool overload;
+
 	/*
 	 * The bit corresponding to a CPU gets set here if such CPU has more
 	 * than one runnable -deadline task (as it is below for RT tasks).
@@ -567,7 +570,7 @@ struct rq {
 	struct root_domain *rd;
 	struct sched_domain *sd;
 
-	unsigned long cpu_power;
+	unsigned long cpu_capacity;
 
 	unsigned char idle_balance;
 	/* For active balancing */
@@ -670,6 +673,8 @@ extern int migrate_swap(struct task_struct *, struct task_struct *);
 
 #ifdef CONFIG_SMP
 
+extern void sched_ttwu_pending(void);
+
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
 			      lockdep_is_held(&sched_domains_mutex))
@@ -728,15 +733,15 @@ DECLARE_PER_CPU(struct sched_domain *, sd_numa);
 DECLARE_PER_CPU(struct sched_domain *, sd_busy);
 DECLARE_PER_CPU(struct sched_domain *, sd_asym);
 
-struct sched_group_power {
+struct sched_group_capacity {
 	atomic_t ref;
 	/*
-	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
-	 * single CPU.
+	 * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity
+	 * for a single CPU.
 	 */
-	unsigned int power, power_orig;
+	unsigned int capacity, capacity_orig;
 	unsigned long next_update;
-	int imbalance; /* XXX unrelated to power but shared group state */
+	int imbalance; /* XXX unrelated to capacity but shared group state */
 	/*
 	 * Number of busy cpus in this group.
 	 */
@@ -750,7 +755,7 @@ struct sched_group {
 	atomic_t ref;
 
 	unsigned int group_weight;
-	struct sched_group_power *sgp;
+	struct sched_group_capacity *sgc;
 
 	/*
 	 * The CPUs this group covers.
@@ -773,7 +778,7 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
  */
 static inline struct cpumask *sched_group_mask(struct sched_group *sg)
 {
-	return to_cpumask(sg->sgp->cpumask);
+	return to_cpumask(sg->sgc->cpumask);
 }
 
 /**
@@ -787,6 +792,10 @@ static inline unsigned int group_first_cpu(struct sched_group *group)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
+#else
+
+static inline void sched_ttwu_pending(void) { }
+
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
@@ -878,20 +887,10 @@ enum {
 #undef SCHED_FEAT
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
-static __always_inline bool static_branch__true(struct static_key *key)
-{
-	return static_key_true(key); /* Not out of line branch. */
-}
-
-static __always_inline bool static_branch__false(struct static_key *key)
-{
-	return static_key_false(key); /* Out of line branch. */
-}
-
 #define SCHED_FEAT(name, enabled)					\
 static __always_inline bool static_branch_##name(struct static_key *key) \
 {									\
-	return static_branch__##enabled(key);				\
+	return static_key_##enabled(key);				\
 }
 
 #include "features.h"
@@ -1167,7 +1166,7 @@ extern const struct sched_class idle_sched_class;
 
 #ifdef CONFIG_SMP
 
-extern void update_group_power(struct sched_domain *sd, int cpu);
+extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
 
@@ -1190,7 +1189,7 @@ extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
 extern void init_sched_dl_class(void);
 
-extern void resched_task(struct task_struct *p);
+extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
 
 extern struct rt_bandwidth def_rt_bandwidth;
@@ -1212,15 +1211,26 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 
 	rq->nr_running = prev_nr + count;
 
-#ifdef CONFIG_NO_HZ_FULL
 	if (prev_nr < 2 && rq->nr_running >= 2) {
+#ifdef CONFIG_SMP
+		if (!rq->rd->overload)
+			rq->rd->overload = true;
+#endif
+
+#ifdef CONFIG_NO_HZ_FULL
 		if (tick_nohz_full_cpu(rq->cpu)) {
-			/* Order rq->nr_running write against the IPI */
-			smp_wmb();
-			smp_send_reschedule(rq->cpu);
+			/*
+			 * Tick is needed if more than one task runs on a CPU.
+			 * Send the target an IPI to kick it out of nohz mode.
+			 *
+			 * We assume that IPI implies full memory barrier and the
+			 * new value of rq->nr_running is visible on reception
+			 * from the target.
+			 */
+			tick_nohz_full_kick_cpu(rq->cpu);
 		}
-       }
 #endif
+	}
 }
 
 static inline void sub_nr_running(struct rq *rq, unsigned count)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 0ffa20ae657..15cab1a4f84 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -319,14 +319,14 @@ EXPORT_SYMBOL(wake_bit_function);
  */
 int __sched
 __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
-			int (*action)(void *), unsigned mode)
+	      wait_bit_action_f *action, unsigned mode)
 {
 	int ret = 0;
 
 	do {
 		prepare_to_wait(wq, &q->wait, mode);
 		if (test_bit(q->key.bit_nr, q->key.flags))
-			ret = (*action)(q->key.flags);
+			ret = (*action)(&q->key);
 	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
 	finish_wait(wq, &q->wait);
 	return ret;
@@ -334,7 +334,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
 EXPORT_SYMBOL(__wait_on_bit);
 
 int __sched out_of_line_wait_on_bit(void *word, int bit,
-					int (*action)(void *), unsigned mode)
+				    wait_bit_action_f *action, unsigned mode)
 {
 	wait_queue_head_t *wq = bit_waitqueue(word, bit);
 	DEFINE_WAIT_BIT(wait, word, bit);
@@ -345,7 +345,7 @@ EXPORT_SYMBOL(out_of_line_wait_on_bit);
 
 int __sched
 __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
-			int (*action)(void *), unsigned mode)
+			wait_bit_action_f *action, unsigned mode)
 {
 	do {
 		int ret;
@@ -353,7 +353,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
 		prepare_to_wait_exclusive(wq, &q->wait, mode);
 		if (!test_bit(q->key.bit_nr, q->key.flags))
 			continue;
-		ret = action(q->key.flags);
+		ret = action(&q->key);
 		if (!ret)
 			continue;
 		abort_exclusive_wait(wq, &q->wait, mode, &q->key);
@@ -365,7 +365,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
 EXPORT_SYMBOL(__wait_on_bit_lock);
 
 int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
-					int (*action)(void *), unsigned mode)
+					 wait_bit_action_f *action, unsigned mode)
 {
 	wait_queue_head_t *wq = bit_waitqueue(word, bit);
 	DEFINE_WAIT_BIT(wait, word, bit);
@@ -502,3 +502,21 @@ void wake_up_atomic_t(atomic_t *p)
 	__wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
 }
 EXPORT_SYMBOL(wake_up_atomic_t);
+
+__sched int bit_wait(struct wait_bit_key *word)
+{
+	if (signal_pending_state(current->state, current))
+		return 1;
+	schedule();
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait);
+
+__sched int bit_wait_io(struct wait_bit_key *word)
+{
+	if (signal_pending_state(current->state, current))
+		return 1;
+	io_schedule();
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait_io);
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index f6d76bebe69..301bbc24739 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -54,8 +54,7 @@
 struct seccomp_filter {
 	atomic_t usage;
 	struct seccomp_filter *prev;
-	unsigned short len;  /* Instruction count */
-	struct sock_filter_int insnsi[];
+	struct sk_filter *prog;
 };
 
 /* Limit any path through the tree to 256KB worth of instructions. */
@@ -104,60 +103,59 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 		u32 k = ftest->k;
 
 		switch (code) {
-		case BPF_S_LD_W_ABS:
+		case BPF_LD | BPF_W | BPF_ABS:
 			ftest->code = BPF_LDX | BPF_W | BPF_ABS;
 			/* 32-bit aligned and not out of bounds. */
 			if (k >= sizeof(struct seccomp_data) || k & 3)
 				return -EINVAL;
 			continue;
-		case BPF_S_LD_W_LEN:
+		case BPF_LD | BPF_W | BPF_LEN:
 			ftest->code = BPF_LD | BPF_IMM;
 			ftest->k = sizeof(struct seccomp_data);
 			continue;
-		case BPF_S_LDX_W_LEN:
+		case BPF_LDX | BPF_W | BPF_LEN:
 			ftest->code = BPF_LDX | BPF_IMM;
 			ftest->k = sizeof(struct seccomp_data);
 			continue;
 		/* Explicitly include allowed calls. */
-		case BPF_S_RET_K:
-		case BPF_S_RET_A:
-		case BPF_S_ALU_ADD_K:
-		case BPF_S_ALU_ADD_X:
-		case BPF_S_ALU_SUB_K:
-		case BPF_S_ALU_SUB_X:
-		case BPF_S_ALU_MUL_K:
-		case BPF_S_ALU_MUL_X:
-		case BPF_S_ALU_DIV_X:
-		case BPF_S_ALU_AND_K:
-		case BPF_S_ALU_AND_X:
-		case BPF_S_ALU_OR_K:
-		case BPF_S_ALU_OR_X:
-		case BPF_S_ALU_XOR_K:
-		case BPF_S_ALU_XOR_X:
-		case BPF_S_ALU_LSH_K:
-		case BPF_S_ALU_LSH_X:
-		case BPF_S_ALU_RSH_K:
-		case BPF_S_ALU_RSH_X:
-		case BPF_S_ALU_NEG:
-		case BPF_S_LD_IMM:
-		case BPF_S_LDX_IMM:
-		case BPF_S_MISC_TAX:
-		case BPF_S_MISC_TXA:
-		case BPF_S_ALU_DIV_K:
-		case BPF_S_LD_MEM:
-		case BPF_S_LDX_MEM:
-		case BPF_S_ST:
-		case BPF_S_STX:
-		case BPF_S_JMP_JA:
-		case BPF_S_JMP_JEQ_K:
-		case BPF_S_JMP_JEQ_X:
-		case BPF_S_JMP_JGE_K:
-		case BPF_S_JMP_JGE_X:
-		case BPF_S_JMP_JGT_K:
-		case BPF_S_JMP_JGT_X:
-		case BPF_S_JMP_JSET_K:
-		case BPF_S_JMP_JSET_X:
-			sk_decode_filter(ftest, ftest);
+		case BPF_RET | BPF_K:
+		case BPF_RET | BPF_A:
+		case BPF_ALU | BPF_ADD | BPF_K:
+		case BPF_ALU | BPF_ADD | BPF_X:
+		case BPF_ALU | BPF_SUB | BPF_K:
+		case BPF_ALU | BPF_SUB | BPF_X:
+		case BPF_ALU | BPF_MUL | BPF_K:
+		case BPF_ALU | BPF_MUL | BPF_X:
+		case BPF_ALU | BPF_DIV | BPF_K:
+		case BPF_ALU | BPF_DIV | BPF_X:
+		case BPF_ALU | BPF_AND | BPF_K:
+		case BPF_ALU | BPF_AND | BPF_X:
+		case BPF_ALU | BPF_OR | BPF_K:
+		case BPF_ALU | BPF_OR | BPF_X:
+		case BPF_ALU | BPF_XOR | BPF_K:
+		case BPF_ALU | BPF_XOR | BPF_X:
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_LSH | BPF_X:
+		case BPF_ALU | BPF_RSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_X:
+		case BPF_ALU | BPF_NEG:
+		case BPF_LD | BPF_IMM:
+		case BPF_LDX | BPF_IMM:
+		case BPF_MISC | BPF_TAX:
+		case BPF_MISC | BPF_TXA:
+		case BPF_LD | BPF_MEM:
+		case BPF_LDX | BPF_MEM:
+		case BPF_ST:
+		case BPF_STX:
+		case BPF_JMP | BPF_JA:
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
 			continue;
 		default:
 			return -EINVAL;
@@ -189,7 +187,8 @@ static u32 seccomp_run_filters(int syscall)
 	 * value always takes priority (ignoring the DATA).
 	 */
 	for (f = current->seccomp.filter; f; f = f->prev) {
-		u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi);
+		u32 cur_ret = SK_RUN_FILTER(f->prog, (void *)&sd);
+
 		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
 			ret = cur_ret;
 	}
@@ -215,7 +214,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 		return -EINVAL;
 
 	for (filter = current->seccomp.filter; filter; filter = filter->prev)
-		total_insns += filter->len + 4;  /* include a 4 instr penalty */
+		total_insns += filter->prog->len + 4;  /* include a 4 instr penalty */
 	if (total_insns > MAX_INSNS_PER_PATH)
 		return -ENOMEM;
 
@@ -256,19 +255,25 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 
 	/* Allocate a new seccomp_filter */
 	ret = -ENOMEM;
-	filter = kzalloc(sizeof(struct seccomp_filter) +
-			 sizeof(struct sock_filter_int) * new_len,
+	filter = kzalloc(sizeof(struct seccomp_filter),
 			 GFP_KERNEL|__GFP_NOWARN);
 	if (!filter)
 		goto free_prog;
 
-	ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len);
-	if (ret)
+	filter->prog = kzalloc(sk_filter_size(new_len),
+			       GFP_KERNEL|__GFP_NOWARN);
+	if (!filter->prog)
 		goto free_filter;
+
+	ret = sk_convert_filter(fp, fprog->len, filter->prog->insnsi, &new_len);
+	if (ret)
+		goto free_filter_prog;
 	kfree(fp);
 
 	atomic_set(&filter->usage, 1);
-	filter->len = new_len;
+	filter->prog->len = new_len;
+
+	sk_filter_select_runtime(filter->prog);
 
 	/*
 	 * If there is an existing filter, make it the prev and don't drop its
@@ -278,6 +283,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 	current->seccomp.filter = filter;
 	return 0;
 
+free_filter_prog:
+	kfree(filter->prog);
 free_filter:
 	kfree(filter);
 free_prog:
@@ -330,6 +337,7 @@ void put_seccomp_filter(struct task_struct *tsk)
 	while (orig && atomic_dec_and_test(&orig->usage)) {
 		struct seccomp_filter *freeme = orig;
 		orig = orig->prev;
+		sk_filter_free(freeme->prog);
 		kfree(freeme);
 	}
 }
diff --git a/kernel/signal.c b/kernel/signal.c
index a4077e90f19..40b76e351e6 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1263,6 +1263,10 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 	struct sighand_struct *sighand;
 
 	for (;;) {
+		/*
+		 * Disable interrupts early to avoid deadlocks.
+		 * See rcu_read_unlock() comment header for details.
+		 */
 		local_irq_save(*flags);
 		rcu_read_lock();
 		sighand = rcu_dereference(tsk->sighand);
diff --git a/kernel/smp.c b/kernel/smp.c
index 306f8180b0d..487653b5844 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -3,6 +3,7 @@
  *
  * (C) Jens Axboe <jens.axboe@oracle.com> 2008
  */
+#include <linux/irq_work.h>
 #include <linux/rcupdate.h>
 #include <linux/rculist.h>
 #include <linux/kernel.h>
@@ -29,6 +30,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue);
 
+static void flush_smp_call_function_queue(bool warn_cpu_offline);
+
 static int
 hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
@@ -51,12 +54,27 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
+		/* Fall-through to the CPU_DEAD[_FROZEN] case. */
 
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		free_cpumask_var(cfd->cpumask);
 		free_percpu(cfd->csd);
 		break;
+
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
+		/*
+		 * The IPIs for the smp-call-function callbacks queued by other
+		 * CPUs might arrive late, either due to hardware latencies or
+		 * because this CPU disabled interrupts (inside stop-machine)
+		 * before the IPIs were sent. So flush out any pending callbacks
+		 * explicitly (without waiting for the IPIs to arrive), to
+		 * ensure that the outgoing CPU doesn't go offline with work
+		 * still pending.
+		 */
+		flush_smp_call_function_queue(false);
+		break;
 #endif
 	};
 
@@ -177,23 +195,47 @@ static int generic_exec_single(int cpu, struct call_single_data *csd,
 	return 0;
 }
 
-/*
- * Invoked by arch to handle an IPI for call function single. Must be
- * called from the arch with interrupts disabled.
+/**
+ * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks
+ *
+ * Invoked by arch to handle an IPI for call function single.
+ * Must be called with interrupts disabled.
  */
 void generic_smp_call_function_single_interrupt(void)
 {
+	flush_smp_call_function_queue(true);
+}
+
+/**
+ * flush_smp_call_function_queue - Flush pending smp-call-function callbacks
+ *
+ * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an
+ *		      offline CPU. Skip this check if set to 'false'.
+ *
+ * Flush any pending smp-call-function callbacks queued on this CPU. This is
+ * invoked by the generic IPI handler, as well as by a CPU about to go offline,
+ * to ensure that all pending IPI callbacks are run before it goes completely
+ * offline.
+ *
+ * Loop through the call_single_queue and run all the queued callbacks.
+ * Must be called with interrupts disabled.
+ */
+static void flush_smp_call_function_queue(bool warn_cpu_offline)
+{
+	struct llist_head *head;
 	struct llist_node *entry;
 	struct call_single_data *csd, *csd_next;
 	static bool warned;
 
-	entry = llist_del_all(&__get_cpu_var(call_single_queue));
+	WARN_ON(!irqs_disabled());
+
+	head = &__get_cpu_var(call_single_queue);
+	entry = llist_del_all(head);
 	entry = llist_reverse_order(entry);
 
-	/*
-	 * Shouldn't receive this interrupt on a cpu that is not yet online.
-	 */
-	if (unlikely(!cpu_online(smp_processor_id()) && !warned)) {
+	/* There shouldn't be any pending callbacks on an offline CPU. */
+	if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) &&
+		     !warned && !llist_empty(head))) {
 		warned = true;
 		WARN(1, "IPI on offline CPU %d\n", smp_processor_id());
 
@@ -210,6 +252,14 @@ void generic_smp_call_function_single_interrupt(void)
 		csd->func(csd->info);
 		csd_unlock(csd);
 	}
+
+	/*
+	 * Handle irq works queued remotely by irq_work_queue_on().
+	 * Smp functions above are typically synchronous so they
+	 * better run first since some other CPUs may be busy waiting
+	 * for them.
+	 */
+	irq_work_run();
 }
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index db19e3e2aa4..75b22e22a72 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -136,7 +136,6 @@ static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
 static int maxolduid = 65535;
 static int minolduid;
-static int min_percpu_pagelist_fract = 8;
 
 static int ngroups_max = NGROUPS_MAX;
 static const int cap_last_cap = CAP_LAST_CAP;
@@ -152,10 +151,6 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
 #ifdef CONFIG_SPARC
 #endif
 
-#ifdef CONFIG_SPARC64
-extern int sysctl_tsb_ratio;
-#endif
-
 #ifdef __hppa__
 extern int pwrsw_enabled;
 #endif
@@ -865,6 +860,17 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
+#ifdef CONFIG_SMP
+	{
+		.procname	= "softlockup_all_cpu_backtrace",
+		.data		= &sysctl_softlockup_all_cpu_backtrace,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif /* CONFIG_SMP */
 	{
 		.procname       = "nmi_watchdog",
 		.data           = &watchdog_user_enabled,
@@ -1321,7 +1327,7 @@ static struct ctl_table vm_table[] = {
 		.maxlen		= sizeof(percpu_pagelist_fraction),
 		.mode		= 0644,
 		.proc_handler	= percpu_pagelist_fraction_sysctl_handler,
-		.extra1		= &min_percpu_pagelist_fract,
+		.extra1		= &zero,
 	},
 #ifdef CONFIG_MMU
 	{
@@ -2568,11 +2574,11 @@ int proc_do_large_bitmap(struct ctl_table *table, int write,
 	bool first = 1;
 	size_t left = *lenp;
 	unsigned long bitmap_len = table->maxlen;
-	unsigned long *bitmap = (unsigned long *) table->data;
+	unsigned long *bitmap = *(unsigned long **) table->data;
 	unsigned long *tmp_bitmap = NULL;
 	char tr_a[] = { '-', ',', '\n' }, tr_b[] = { ',', '\n', 0 }, c;
 
-	if (!bitmap_len || !left || (*ppos && !write)) {
+	if (!bitmap || !bitmap_len || !left || (*ppos && !write)) {
 		*lenp = 0;
 		return 0;
 	}
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 88c9c65a430..fe75444ae7e 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -585,9 +585,14 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 				struct itimerspec *new_setting,
 				struct itimerspec *old_setting)
 {
+	ktime_t exp;
+
 	if (!rtcdev)
 		return -ENOTSUPP;
 
+	if (flags & ~TIMER_ABSTIME)
+		return -EINVAL;
+
 	if (old_setting)
 		alarm_timer_get(timr, old_setting);
 
@@ -597,8 +602,16 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
 
 	/* start the timer */
 	timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
-	alarm_start(&timr->it.alarm.alarmtimer,
-			timespec_to_ktime(new_setting->it_value));
+	exp = timespec_to_ktime(new_setting->it_value);
+	/* Convert (if necessary) to absolute time */
+	if (flags != TIMER_ABSTIME) {
+		ktime_t now;
+
+		now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime();
+		exp = ktime_add(now, exp);
+	}
+
+	alarm_start(&timr->it.alarm.alarmtimer, exp);
 	return 0;
 }
 
@@ -730,6 +743,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	if (!alarmtimer_get_rtcdev())
 		return -ENOTSUPP;
 
+	if (flags & ~TIMER_ABSTIME)
+		return -EINVAL;
+
 	if (!capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index ad362c260ef..9c94c19f130 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -146,7 +146,8 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
 {
 	/* Nothing to do if we already reached the limit */
 	if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
-		printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n");
+		printk_deferred(KERN_WARNING
+				"CE: Reprogramming failure. Giving up\n");
 		dev->next_event.tv64 = KTIME_MAX;
 		return -ETIME;
 	}
@@ -159,9 +160,10 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
 	if (dev->min_delta_ns > MIN_DELTA_LIMIT)
 		dev->min_delta_ns = MIN_DELTA_LIMIT;
 
-	printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n",
-	       dev->name ? dev->name : "?",
-	       (unsigned long long) dev->min_delta_ns);
+	printk_deferred(KERN_WARNING
+			"CE: %s increased min_delta_ns to %llu nsec\n",
+			dev->name ? dev->name : "?",
+			(unsigned long long) dev->min_delta_ns);
 	return 0;
 }
 
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 445106d2c72..01d2d15aa66 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -191,7 +191,8 @@ void __init sched_clock_postinit(void)
 
 static int sched_clock_suspend(void)
 {
-	sched_clock_poll(&sched_clock_timer);
+	update_sched_clock();
+	hrtimer_cancel(&sched_clock_timer);
 	cd.suspended = true;
 	return 0;
 }
@@ -199,6 +200,7 @@ static int sched_clock_suspend(void)
 static void sched_clock_resume(void)
 {
 	cd.epoch_cyc = read_sched_clock();
+	hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
 	cd.suspended = false;
 }
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6558b7ac112..99aa6ee3908 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -154,6 +154,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 
 #ifdef CONFIG_NO_HZ_FULL
 cpumask_var_t tick_nohz_full_mask;
+cpumask_var_t housekeeping_mask;
 bool tick_nohz_full_running;
 
 static bool can_stop_full_tick(void)
@@ -224,13 +225,15 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
 };
 
 /*
- * Kick the current CPU if it's full dynticks in order to force it to
+ * Kick the CPU if it's full dynticks in order to force it to
  * re-evaluate its dependency on the tick and restart it if necessary.
  */
-void tick_nohz_full_kick(void)
+void tick_nohz_full_kick_cpu(int cpu)
 {
-	if (tick_nohz_full_cpu(smp_processor_id()))
-		irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
+	if (!tick_nohz_full_cpu(cpu))
+		return;
+
+	irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu);
 }
 
 static void nohz_full_kick_ipi(void *info)
@@ -281,6 +284,7 @@ static int __init tick_nohz_full_setup(char *str)
 	int cpu;
 
 	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
+	alloc_bootmem_cpumask_var(&housekeeping_mask);
 	if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
 		pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
 		return 1;
@@ -291,6 +295,8 @@ static int __init tick_nohz_full_setup(char *str)
 		pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
 		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
 	}
+	cpumask_andnot(housekeeping_mask,
+		       cpu_possible_mask, tick_nohz_full_mask);
 	tick_nohz_full_running = true;
 
 	return 1;
@@ -332,9 +338,15 @@ static int tick_nohz_init_all(void)
 		pr_err("NO_HZ: Can't allocate full dynticks cpumask\n");
 		return err;
 	}
+	if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) {
+		pr_err("NO_HZ: Can't allocate not-full dynticks cpumask\n");
+		return err;
+	}
 	err = 0;
 	cpumask_setall(tick_nohz_full_mask);
 	cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask);
+	cpumask_clear(housekeeping_mask);
+	cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
 	tick_nohz_full_running = true;
 #endif
 	return err;
diff --git a/kernel/torture.c b/kernel/torture.c
index 40bb511cca4..d600af21f02 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -708,7 +708,7 @@ int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
 	int ret = 0;
 
 	VERBOSE_TOROUT_STRING(m);
-	*tp = kthread_run(fn, arg, s);
+	*tp = kthread_run(fn, arg, "%s", s);
 	if (IS_ERR(*tp)) {
 		ret = PTR_ERR(*tp);
 		VERBOSE_TOROUT_ERRSTRING(f);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8639819f6ce..a5da09c899d 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -29,11 +29,6 @@ config HAVE_FUNCTION_GRAPH_FP_TEST
 	help
 	  See Documentation/trace/ftrace-design.txt
 
-config HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	bool
-	help
-	  See Documentation/trace/ftrace-design.txt
-
 config HAVE_DYNAMIC_FTRACE
 	bool
 	help
@@ -535,6 +530,36 @@ config MMIOTRACE_TEST
 
 	  Say N, unless you absolutely know what you are doing.
 
+config TRACEPOINT_BENCHMARK
+        bool "Add tracepoint that benchmarks tracepoints"
+	help
+	 This option creates the tracepoint "benchmark:benchmark_event".
+	 When the tracepoint is enabled, it kicks off a kernel thread that
+	 goes into an infinite loop (calling cond_sched() to let other tasks
+	 run), and calls the tracepoint. Each iteration will record the time
+	 it took to write to the tracepoint and the next iteration that
+	 data will be passed to the tracepoint itself. That is, the tracepoint
+	 will report the time it took to do the previous tracepoint.
+	 The string written to the tracepoint is a static string of 128 bytes
+	 to keep the time the same. The initial string is simply a write of
+	 "START". The second string records the cold cache time of the first
+	 write which is not added to the rest of the calculations.
+
+	 As it is a tight loop, it benchmarks as hot cache. That's fine because
+	 we care most about hot paths that are probably in cache already.
+
+	 An example of the output:
+
+	      START
+	      first=3672 [COLD CACHED]
+	      last=632 first=3672 max=632 min=632 avg=316 std=446 std^2=199712
+	      last=278 first=3672 max=632 min=278 avg=303 std=316 std^2=100337
+	      last=277 first=3672 max=632 min=277 avg=296 std=258 std^2=67064
+	      last=273 first=3672 max=632 min=273 avg=292 std=224 std^2=50411
+	      last=273 first=3672 max=632 min=273 avg=288 std=200 std^2=40389
+	      last=281 first=3672 max=632 min=273 avg=287 std=183 std^2=33666
+
+
 config RING_BUFFER_BENCHMARK
 	tristate "Ring buffer benchmark stress tester"
 	depends on RING_BUFFER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 1378e84fbe3..67d6369ddf8 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -17,6 +17,7 @@ ifdef CONFIG_TRACING_BRANCHES
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 endif
 
+CFLAGS_trace_benchmark.o := -I$(src)
 CFLAGS_trace_events_filter.o := -I$(src)
 
 obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o
@@ -27,6 +28,7 @@ obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o
 
 obj-$(CONFIG_TRACING) += trace.o
 obj-$(CONFIG_TRACING) += trace_output.o
+obj-$(CONFIG_TRACING) += trace_seq.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
@@ -62,4 +64,6 @@ endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
 obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
 
+obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
+
 libftrace-y := ftrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4a54a25afa2..1654b12c891 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -62,7 +62,7 @@
 #define FTRACE_HASH_DEFAULT_BITS 10
 #define FTRACE_HASH_MAX_BITS 12
 
-#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
+#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_CONTROL)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define INIT_REGEX_LOCK(opsname)	\
@@ -80,9 +80,6 @@ static struct ftrace_ops ftrace_list_end __read_mostly = {
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
 
-/* Quick disabling of function tracer. */
-int function_trace_stop __read_mostly;
-
 /* Current function tracing op */
 struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
 /* What to set function_trace_op to */
@@ -103,7 +100,6 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
@@ -171,23 +167,6 @@ int ftrace_nr_registered_ops(void)
 	return cnt;
 }
 
-static void
-ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
-			struct ftrace_ops *op, struct pt_regs *regs)
-{
-	int bit;
-
-	bit = trace_test_and_set_recursion(TRACE_GLOBAL_START, TRACE_GLOBAL_MAX);
-	if (bit < 0)
-		return;
-
-	do_for_each_ftrace_op(op, ftrace_global_list) {
-		op->func(ip, parent_ip, op, regs);
-	} while_for_each_ftrace_op(op);
-
-	trace_clear_recursion(bit);
-}
-
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 			    struct ftrace_ops *op, struct pt_regs *regs)
 {
@@ -237,43 +216,6 @@ static int control_ops_alloc(struct ftrace_ops *ops)
 	return 0;
 }
 
-static void update_global_ops(void)
-{
-	ftrace_func_t func = ftrace_global_list_func;
-	void *private = NULL;
-
-	/* The list has its own recursion protection. */
-	global_ops.flags |= FTRACE_OPS_FL_RECURSION_SAFE;
-
-	/*
-	 * If there's only one function registered, then call that
-	 * function directly. Otherwise, we need to iterate over the
-	 * registered callers.
-	 */
-	if (ftrace_global_list == &ftrace_list_end ||
-	    ftrace_global_list->next == &ftrace_list_end) {
-		func = ftrace_global_list->func;
-		private = ftrace_global_list->private;
-		/*
-		 * As we are calling the function directly.
-		 * If it does not have recursion protection,
-		 * the function_trace_op needs to be updated
-		 * accordingly.
-		 */
-		if (!(ftrace_global_list->flags & FTRACE_OPS_FL_RECURSION_SAFE))
-			global_ops.flags &= ~FTRACE_OPS_FL_RECURSION_SAFE;
-	}
-
-	/* If we filter on pids, update to use the pid function */
-	if (!list_empty(&ftrace_pids)) {
-		set_ftrace_pid_function(func);
-		func = ftrace_pid_func;
-	}
-
-	global_ops.func = func;
-	global_ops.private = private;
-}
-
 static void ftrace_sync(struct work_struct *work)
 {
 	/*
@@ -301,8 +243,6 @@ static void update_ftrace_function(void)
 {
 	ftrace_func_t func;
 
-	update_global_ops();
-
 	/*
 	 * If we are at the end of the list and this ops is
 	 * recursion safe and not dynamic and the arch supports passing ops,
@@ -314,10 +254,7 @@ static void update_ftrace_function(void)
 	     (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) &&
 	     !FTRACE_FORCE_LIST_FUNC)) {
 		/* Set the ftrace_ops that the arch callback uses */
-		if (ftrace_ops_list == &global_ops)
-			set_function_trace_op = ftrace_global_list;
-		else
-			set_function_trace_op = ftrace_ops_list;
+		set_function_trace_op = ftrace_ops_list;
 		func = ftrace_ops_list->func;
 	} else {
 		/* Just use the default ftrace_ops */
@@ -325,12 +262,12 @@ static void update_ftrace_function(void)
 		func = ftrace_ops_list_func;
 	}
 
+	update_function_graph_func();
+
 	/* If there's no change, then do nothing more here */
 	if (ftrace_trace_function == func)
 		return;
 
-	update_function_graph_func();
-
 	/*
 	 * If we are using the list function, it doesn't care
 	 * about the function_trace_ops.
@@ -373,6 +310,11 @@ static void update_ftrace_function(void)
 	ftrace_trace_function = func;
 }
 
+int using_ftrace_ops_list_func(void)
+{
+	return ftrace_trace_function == ftrace_ops_list_func;
+}
+
 static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 {
 	ops->next = *list;
@@ -434,16 +376,9 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	if (ops->flags & FTRACE_OPS_FL_DELETED)
 		return -EINVAL;
 
-	if (FTRACE_WARN_ON(ops == &global_ops))
-		return -EINVAL;
-
 	if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED))
 		return -EBUSY;
 
-	/* We don't support both control and global flags set. */
-	if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
-		return -EINVAL;
-
 #ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 	/*
 	 * If the ftrace_ops specifies SAVE_REGS, then it only can be used
@@ -461,10 +396,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	if (!core_kernel_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		add_ftrace_list_ops(&ftrace_global_list, &global_ops, ops);
-		ops->flags |= FTRACE_OPS_FL_ENABLED;
-	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+	if (ops->flags & FTRACE_OPS_FL_CONTROL) {
 		if (control_ops_alloc(ops))
 			return -ENOMEM;
 		add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops);
@@ -484,15 +416,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
 		return -EBUSY;
 
-	if (FTRACE_WARN_ON(ops == &global_ops))
-		return -EINVAL;
-
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		ret = remove_ftrace_list_ops(&ftrace_global_list,
-					     &global_ops, ops);
-		if (!ret)
-			ops->flags &= ~FTRACE_OPS_FL_ENABLED;
-	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+	if (ops->flags & FTRACE_OPS_FL_CONTROL) {
 		ret = remove_ftrace_list_ops(&ftrace_control_list,
 					     &control_ops, ops);
 	} else
@@ -895,7 +819,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip,
 
 	local_irq_save(flags);
 
-	stat = &__get_cpu_var(ftrace_profile_stats);
+	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
 		goto out;
 
@@ -926,7 +850,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	stat = &__get_cpu_var(ftrace_profile_stats);
+	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
 		goto out;
 
@@ -1115,6 +1039,8 @@ static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+static struct ftrace_ops *removed_ops;
+
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
 # error Dynamic ftrace depends on MCOUNT_RECORD
 #endif
@@ -1178,7 +1104,7 @@ struct ftrace_page {
 static struct ftrace_page	*ftrace_pages_start;
 static struct ftrace_page	*ftrace_pages;
 
-static bool ftrace_hash_empty(struct ftrace_hash *hash)
+static bool __always_inline ftrace_hash_empty(struct ftrace_hash *hash)
 {
 	return !hash || !hash->count;
 }
@@ -1377,25 +1303,15 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	struct ftrace_hash *new_hash;
 	int size = src->count;
 	int bits = 0;
-	int ret;
 	int i;
 
 	/*
-	 * Remove the current set, update the hash and add
-	 * them back.
-	 */
-	ftrace_hash_rec_disable(ops, enable);
-
-	/*
 	 * If the new source is empty, just free dst and assign it
 	 * the empty_hash.
 	 */
 	if (!src->count) {
-		free_ftrace_hash_rcu(*dst);
-		rcu_assign_pointer(*dst, EMPTY_HASH);
-		/* still need to update the function records */
-		ret = 0;
-		goto out;
+		new_hash = EMPTY_HASH;
+		goto update;
 	}
 
 	/*
@@ -1408,10 +1324,9 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	if (bits > FTRACE_HASH_MAX_BITS)
 		bits = FTRACE_HASH_MAX_BITS;
 
-	ret = -ENOMEM;
 	new_hash = alloc_ftrace_hash(bits);
 	if (!new_hash)
-		goto out;
+		return -ENOMEM;
 
 	size = 1 << src->size_bits;
 	for (i = 0; i < size; i++) {
@@ -1422,20 +1337,20 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 		}
 	}
 
+update:
+	/*
+	 * Remove the current set, update the hash and add
+	 * them back.
+	 */
+	ftrace_hash_rec_disable(ops, enable);
+
 	old_hash = *dst;
 	rcu_assign_pointer(*dst, new_hash);
 	free_ftrace_hash_rcu(old_hash);
 
-	ret = 0;
- out:
-	/*
-	 * Enable regardless of ret:
-	 *  On success, we enable the new hash.
-	 *  On failure, we re-enable the original hash.
-	 */
 	ftrace_hash_rec_enable(ops, enable);
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -1565,6 +1480,53 @@ int ftrace_text_reserved(const void *start, const void *end)
 	return (int)!!ret;
 }
 
+/* Test if ops registered to this rec needs regs */
+static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec)
+{
+	struct ftrace_ops *ops;
+	bool keep_regs = false;
+
+	for (ops = ftrace_ops_list;
+	     ops != &ftrace_list_end; ops = ops->next) {
+		/* pass rec in as regs to have non-NULL val */
+		if (ftrace_ops_test(ops, rec->ip, rec)) {
+			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+				keep_regs = true;
+				break;
+			}
+		}
+	}
+
+	return  keep_regs;
+}
+
+static void ftrace_remove_tramp(struct ftrace_ops *ops,
+				struct dyn_ftrace *rec)
+{
+	struct ftrace_func_entry *entry;
+
+	entry = ftrace_lookup_ip(ops->tramp_hash, rec->ip);
+	if (!entry)
+		return;
+
+	/*
+	 * The tramp_hash entry will be removed at time
+	 * of update.
+	 */
+	ops->nr_trampolines--;
+	rec->flags &= ~FTRACE_FL_TRAMP;
+}
+
+static void ftrace_clear_tramps(struct dyn_ftrace *rec)
+{
+	struct ftrace_ops *op;
+
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		if (op->nr_trampolines)
+			ftrace_remove_tramp(op, rec);
+	} while_for_each_ftrace_op(op);
+}
+
 static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)
@@ -1625,7 +1587,14 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			in_other_hash = !!ftrace_lookup_ip(other_hash, rec->ip);
 
 			/*
+			 * If filter_hash is set, we want to match all functions
+			 * that are in the hash but not in the other hash.
 			 *
+			 * If filter_hash is not set, then we are decrementing.
+			 * That means we match anything that is in the hash
+			 * and also in the other_hash. That is, we need to turn
+			 * off functions in the other hash because they are disabled
+			 * by this hash.
 			 */
 			if (filter_hash && in_hash && !in_other_hash)
 				match = 1;
@@ -1638,8 +1607,30 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 
 		if (inc) {
 			rec->flags++;
-			if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX))
+			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX))
 				return;
+
+			/*
+			 * If there's only a single callback registered to a
+			 * function, and the ops has a trampoline registered
+			 * for it, then we can call it directly.
+			 */
+			if (ftrace_rec_count(rec) == 1 && ops->trampoline) {
+				rec->flags |= FTRACE_FL_TRAMP;
+				ops->nr_trampolines++;
+			} else {
+				/*
+				 * If we are adding another function callback
+				 * to this function, and the previous had a
+				 * trampoline used, then we need to go back to
+				 * the default trampoline.
+				 */
+				rec->flags &= ~FTRACE_FL_TRAMP;
+
+				/* remove trampolines from any ops for this rec */
+				ftrace_clear_tramps(rec);
+			}
+
 			/*
 			 * If any ops wants regs saved for this function
 			 * then all ops will get saved regs.
@@ -1647,9 +1638,30 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 			if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
 				rec->flags |= FTRACE_FL_REGS;
 		} else {
-			if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0))
+			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0))
 				return;
 			rec->flags--;
+
+			if (ops->trampoline && !ftrace_rec_count(rec))
+				ftrace_remove_tramp(ops, rec);
+
+			/*
+			 * If the rec had REGS enabled and the ops that is
+			 * being removed had REGS set, then see if there is
+			 * still any ops for this record that wants regs.
+			 * If not, we can stop recording them.
+			 */
+			if (ftrace_rec_count(rec) > 0 &&
+			    rec->flags & FTRACE_FL_REGS &&
+			    ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+				if (!test_rec_ops_needs_regs(rec))
+					rec->flags &= ~FTRACE_FL_REGS;
+			}
+
+			/*
+			 * flags will be cleared in ftrace_check_record()
+			 * if rec count is zero.
+			 */
 		}
 		count++;
 		/* Shortcut, if we handled all records, we are done. */
@@ -1734,17 +1746,23 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 	 * If we are disabling calls, then disable all records that
 	 * are enabled.
 	 */
-	if (enable && (rec->flags & ~FTRACE_FL_MASK))
+	if (enable && ftrace_rec_count(rec))
 		flag = FTRACE_FL_ENABLED;
 
 	/*
-	 * If enabling and the REGS flag does not match the REGS_EN, then
-	 * do not ignore this record. Set flags to fail the compare against
-	 * ENABLED.
+	 * If enabling and the REGS flag does not match the REGS_EN, or
+	 * the TRAMP flag doesn't match the TRAMP_EN, then do not ignore
+	 * this record. Set flags to fail the compare against ENABLED.
 	 */
-	if (flag &&
-	    (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN)))
-		flag |= FTRACE_FL_REGS;
+	if (flag) {
+		if (!(rec->flags & FTRACE_FL_REGS) != 
+		    !(rec->flags & FTRACE_FL_REGS_EN))
+			flag |= FTRACE_FL_REGS;
+
+		if (!(rec->flags & FTRACE_FL_TRAMP) != 
+		    !(rec->flags & FTRACE_FL_TRAMP_EN))
+			flag |= FTRACE_FL_TRAMP;
+	}
 
 	/* If the state of this record hasn't changed, then do nothing */
 	if ((rec->flags & FTRACE_FL_ENABLED) == flag)
@@ -1762,29 +1780,31 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 				else
 					rec->flags &= ~FTRACE_FL_REGS_EN;
 			}
+			if (flag & FTRACE_FL_TRAMP) {
+				if (rec->flags & FTRACE_FL_TRAMP)
+					rec->flags |= FTRACE_FL_TRAMP_EN;
+				else
+					rec->flags &= ~FTRACE_FL_TRAMP_EN;
+			}
 		}
 
 		/*
 		 * If this record is being updated from a nop, then
 		 *   return UPDATE_MAKE_CALL.
-		 * Otherwise, if the EN flag is set, then return
-		 *   UPDATE_MODIFY_CALL_REGS to tell the caller to convert
-		 *   from the non-save regs, to a save regs function.
 		 * Otherwise,
 		 *   return UPDATE_MODIFY_CALL to tell the caller to convert
-		 *   from the save regs, to a non-save regs function.
+		 *   from the save regs, to a non-save regs function or
+		 *   vice versa, or from a trampoline call.
 		 */
 		if (flag & FTRACE_FL_ENABLED)
 			return FTRACE_UPDATE_MAKE_CALL;
-		else if (rec->flags & FTRACE_FL_REGS_EN)
-			return FTRACE_UPDATE_MODIFY_CALL_REGS;
-		else
-			return FTRACE_UPDATE_MODIFY_CALL;
+
+		return FTRACE_UPDATE_MODIFY_CALL;
 	}
 
 	if (update) {
 		/* If there's no more users, clear all flags */
-		if (!(rec->flags & ~FTRACE_FL_MASK))
+		if (!ftrace_rec_count(rec))
 			rec->flags = 0;
 		else
 			/* Just disable the record (keep REGS state) */
@@ -1821,6 +1841,107 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable)
 	return ftrace_check_record(rec, enable, 0);
 }
 
+static struct ftrace_ops *
+ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec)
+{
+	struct ftrace_ops *op;
+
+	/* Removed ops need to be tested first */
+	if (removed_ops && removed_ops->tramp_hash) {
+		if (ftrace_lookup_ip(removed_ops->tramp_hash, rec->ip))
+			return removed_ops;
+	}
+
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		if (!op->tramp_hash)
+			continue;
+
+		if (ftrace_lookup_ip(op->tramp_hash, rec->ip))
+			return op;
+
+	} while_for_each_ftrace_op(op);
+
+	return NULL;
+}
+
+static struct ftrace_ops *
+ftrace_find_tramp_ops_new(struct dyn_ftrace *rec)
+{
+	struct ftrace_ops *op;
+
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		/* pass rec in as regs to have non-NULL val */
+		if (ftrace_ops_test(op, rec->ip, rec))
+			return op;
+	} while_for_each_ftrace_op(op);
+
+	return NULL;
+}
+
+/**
+ * ftrace_get_addr_new - Get the call address to set to
+ * @rec:  The ftrace record descriptor
+ *
+ * If the record has the FTRACE_FL_REGS set, that means that it
+ * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
+ * is not not set, then it wants to convert to the normal callback.
+ *
+ * Returns the address of the trampoline to set to
+ */
+unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec)
+{
+	struct ftrace_ops *ops;
+
+	/* Trampolines take precedence over regs */
+	if (rec->flags & FTRACE_FL_TRAMP) {
+		ops = ftrace_find_tramp_ops_new(rec);
+		if (FTRACE_WARN_ON(!ops || !ops->trampoline)) {
+			pr_warning("Bad trampoline accounting at: %p (%pS)\n",
+				    (void *)rec->ip, (void *)rec->ip);
+			/* Ftrace is shutting down, return anything */
+			return (unsigned long)FTRACE_ADDR;
+		}
+		return ops->trampoline;
+	}
+
+	if (rec->flags & FTRACE_FL_REGS)
+		return (unsigned long)FTRACE_REGS_ADDR;
+	else
+		return (unsigned long)FTRACE_ADDR;
+}
+
+/**
+ * ftrace_get_addr_curr - Get the call address that is already there
+ * @rec:  The ftrace record descriptor
+ *
+ * The FTRACE_FL_REGS_EN is set when the record already points to
+ * a function that saves all the regs. Basically the '_EN' version
+ * represents the current state of the function.
+ *
+ * Returns the address of the trampoline that is currently being called
+ */
+unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec)
+{
+	struct ftrace_ops *ops;
+
+	/* Trampolines take precedence over regs */
+	if (rec->flags & FTRACE_FL_TRAMP_EN) {
+		ops = ftrace_find_tramp_ops_curr(rec);
+		if (FTRACE_WARN_ON(!ops)) {
+			pr_warning("Bad trampoline accounting at: %p (%pS)\n",
+				    (void *)rec->ip, (void *)rec->ip);
+			/* Ftrace is shutting down, return anything */
+			return (unsigned long)FTRACE_ADDR;
+		}
+		return ops->trampoline;
+	}
+
+	if (rec->flags & FTRACE_FL_REGS_EN)
+		return (unsigned long)FTRACE_REGS_ADDR;
+	else
+		return (unsigned long)FTRACE_ADDR;
+}
+
 static int
 __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
@@ -1828,12 +1949,12 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	unsigned long ftrace_addr;
 	int ret;
 
-	ret = ftrace_update_record(rec, enable);
+	ftrace_addr = ftrace_get_addr_new(rec);
 
-	if (rec->flags & FTRACE_FL_REGS)
-		ftrace_addr = (unsigned long)FTRACE_REGS_ADDR;
-	else
-		ftrace_addr = (unsigned long)FTRACE_ADDR;
+	/* This needs to be done before we call ftrace_update_record */
+	ftrace_old_addr = ftrace_get_addr_curr(rec);
+
+	ret = ftrace_update_record(rec, enable);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
@@ -1845,13 +1966,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	case FTRACE_UPDATE_MAKE_NOP:
 		return ftrace_make_nop(NULL, rec, ftrace_addr);
 
-	case FTRACE_UPDATE_MODIFY_CALL_REGS:
 	case FTRACE_UPDATE_MODIFY_CALL:
-		if (rec->flags & FTRACE_FL_REGS)
-			ftrace_old_addr = (unsigned long)FTRACE_ADDR;
-		else
-			ftrace_old_addr = (unsigned long)FTRACE_REGS_ADDR;
-
 		return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr);
 	}
 
@@ -2063,6 +2178,89 @@ void __weak arch_ftrace_update_code(int command)
 	ftrace_run_stop_machine(command);
 }
 
+static int ftrace_save_ops_tramp_hash(struct ftrace_ops *ops)
+{
+	struct ftrace_page *pg;
+	struct dyn_ftrace *rec;
+	int size, bits;
+	int ret;
+
+	size = ops->nr_trampolines;
+	bits = 0;
+	/*
+	 * Make the hash size about 1/2 the # found
+	 */
+	for (size /= 2; size; size >>= 1)
+		bits++;
+
+	ops->tramp_hash = alloc_ftrace_hash(bits);
+	/*
+	 * TODO: a failed allocation is going to screw up
+	 * the accounting of what needs to be modified
+	 * and not. For now, we kill ftrace if we fail
+	 * to allocate here. But there are ways around this,
+	 * but that will take a little more work.
+	 */
+	if (!ops->tramp_hash)
+		return -ENOMEM;
+
+	do_for_each_ftrace_rec(pg, rec) {
+		if (ftrace_rec_count(rec) == 1 &&
+		    ftrace_ops_test(ops, rec->ip, rec)) {
+
+			/*
+			 * If another ops adds to a rec, the rec will
+			 * lose its trampoline and never get it back
+			 * until all ops are off of it.
+			 */
+			if (!(rec->flags & FTRACE_FL_TRAMP))
+				continue;
+
+			/* This record had better have a trampoline */
+			if (FTRACE_WARN_ON(!(rec->flags & FTRACE_FL_TRAMP_EN)))
+				return -1;
+
+			ret = add_hash_entry(ops->tramp_hash, rec->ip);
+			if (ret < 0)
+				return ret;
+		}
+	} while_for_each_ftrace_rec();
+
+	/* The number of recs in the hash must match nr_trampolines */
+	FTRACE_WARN_ON(ops->tramp_hash->count != ops->nr_trampolines);
+
+	return 0;
+}
+
+static int ftrace_save_tramp_hashes(void)
+{
+	struct ftrace_ops *op;
+	int ret;
+
+	/*
+	 * Now that any trampoline is being used, we need to save the
+	 * hashes for the ops that have them. This allows the mapping
+	 * back from the record to the ops that has the trampoline to
+	 * know what code is being replaced. Modifying code must always
+	 * verify what it is changing.
+	 */
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+
+		/* The tramp_hash is recreated each time. */
+		free_ftrace_hash(op->tramp_hash);
+		op->tramp_hash = NULL;
+
+		if (op->nr_trampolines) {
+			ret = ftrace_save_ops_tramp_hash(op);
+			if (ret)
+				return ret;
+		}
+
+	} while_for_each_ftrace_op(op);
+
+	return 0;
+}
+
 static void ftrace_run_update_code(int command)
 {
 	int ret;
@@ -2071,11 +2269,6 @@ static void ftrace_run_update_code(int command)
 	FTRACE_WARN_ON(ret);
 	if (ret)
 		return;
-	/*
-	 * Do not call function tracer while we update the code.
-	 * We are in stop machine.
-	 */
-	function_trace_stop++;
 
 	/*
 	 * By default we use stop_machine() to modify the code.
@@ -2085,15 +2278,15 @@ static void ftrace_run_update_code(int command)
 	 */
 	arch_ftrace_update_code(command);
 
-	function_trace_stop--;
-
 	ret = ftrace_arch_code_modify_post_process();
 	FTRACE_WARN_ON(ret);
+
+	ret = ftrace_save_tramp_hashes();
+	FTRACE_WARN_ON(ret);
 }
 
 static ftrace_func_t saved_ftrace_func;
 static int ftrace_start_up;
-static int global_start_up;
 
 static void control_ops_free(struct ftrace_ops *ops)
 {
@@ -2115,7 +2308,6 @@ static void ftrace_startup_enable(int command)
 
 static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
-	bool hash_enable = true;
 	int ret;
 
 	if (unlikely(ftrace_disabled))
@@ -2128,18 +2320,9 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 	ftrace_start_up++;
 	command |= FTRACE_UPDATE_CALLS;
 
-	/* ops marked global share the filter hashes */
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		ops = &global_ops;
-		/* Don't update hash if global is already set */
-		if (global_start_up)
-			hash_enable = false;
-		global_start_up++;
-	}
-
 	ops->flags |= FTRACE_OPS_FL_ENABLED;
-	if (hash_enable)
-		ftrace_hash_rec_enable(ops, 1);
+
+	ftrace_hash_rec_enable(ops, 1);
 
 	ftrace_startup_enable(command);
 
@@ -2148,7 +2331,6 @@ static int ftrace_startup(struct ftrace_ops *ops, int command)
 
 static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 {
-	bool hash_disable = true;
 	int ret;
 
 	if (unlikely(ftrace_disabled))
@@ -2166,22 +2348,9 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 */
 	WARN_ON_ONCE(ftrace_start_up < 0);
 
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
-		ops = &global_ops;
-		global_start_up--;
-		WARN_ON_ONCE(global_start_up < 0);
-		/* Don't update hash if global still has users */
-		if (global_start_up) {
-			WARN_ON_ONCE(!ftrace_start_up);
-			hash_disable = false;
-		}
-	}
-
-	if (hash_disable)
-		ftrace_hash_rec_disable(ops, 1);
+	ftrace_hash_rec_disable(ops, 1);
 
-	if (ops != &global_ops || !global_start_up)
-		ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+	ops->flags &= ~FTRACE_OPS_FL_ENABLED;
 
 	command |= FTRACE_UPDATE_CALLS;
 
@@ -2202,8 +2371,16 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		return 0;
 	}
 
+	/*
+	 * If the ops uses a trampoline, then it needs to be
+	 * tested first on update.
+	 */
+	removed_ops = ops;
+
 	ftrace_run_update_code(command);
 
+	removed_ops = NULL;
+
 	/*
 	 * Dynamic ops may be freed, we must make sure that all
 	 * callers are done before leaving this function.
@@ -2461,7 +2638,8 @@ ftrace_allocate_pages(unsigned long num_to_init)
 	return start_pg;
 
  free_pages:
-	while (start_pg) {
+	pg = start_pg;
+	while (pg) {
 		order = get_count_order(pg->size / ENTRIES_PER_PAGE);
 		free_pages((unsigned long)pg->records, order);
 		start_pg = pg->next;
@@ -2658,8 +2836,10 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 	 * off, we can short cut and just print out that all
 	 * functions are enabled.
 	 */
-	if (iter->flags & FTRACE_ITER_FILTER &&
-	    ftrace_hash_empty(ops->filter_hash)) {
+	if ((iter->flags & FTRACE_ITER_FILTER &&
+	     ftrace_hash_empty(ops->filter_hash)) ||
+	    (iter->flags & FTRACE_ITER_NOTRACE &&
+	     ftrace_hash_empty(ops->notrace_hash))) {
 		if (*pos > 0)
 			return t_hash_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
@@ -2704,7 +2884,10 @@ static int t_show(struct seq_file *m, void *v)
 		return t_hash_show(m, iter);
 
 	if (iter->flags & FTRACE_ITER_PRINTALL) {
-		seq_printf(m, "#### all functions enabled ####\n");
+		if (iter->flags & FTRACE_ITER_NOTRACE)
+			seq_printf(m, "#### no functions disabled ####\n");
+		else
+			seq_printf(m, "#### all functions enabled ####\n");
 		return 0;
 	}
 
@@ -2714,10 +2897,22 @@ static int t_show(struct seq_file *m, void *v)
 		return 0;
 
 	seq_printf(m, "%ps", (void *)rec->ip);
-	if (iter->flags & FTRACE_ITER_ENABLED)
+	if (iter->flags & FTRACE_ITER_ENABLED) {
 		seq_printf(m, " (%ld)%s",
-			   rec->flags & ~FTRACE_FL_MASK,
-			   rec->flags & FTRACE_FL_REGS ? " R" : "");
+			   ftrace_rec_count(rec),
+			   rec->flags & FTRACE_FL_REGS ? " R" : "  ");
+		if (rec->flags & FTRACE_FL_TRAMP_EN) {
+			struct ftrace_ops *ops;
+
+			ops = ftrace_find_tramp_ops_curr(rec);
+			if (ops && ops->trampoline)
+				seq_printf(m, "\ttramp: %pS",
+					   (void *)ops->trampoline);
+			else
+				seq_printf(m, "\ttramp: ERROR!");
+		}
+	}	
+
 	seq_printf(m, "\n");
 
 	return 0;
@@ -2765,13 +2960,6 @@ ftrace_enabled_open(struct inode *inode, struct file *file)
 	return iter ? 0 : -ENOMEM;
 }
 
-static void ftrace_filter_reset(struct ftrace_hash *hash)
-{
-	mutex_lock(&ftrace_lock);
-	ftrace_hash_clear(hash);
-	mutex_unlock(&ftrace_lock);
-}
-
 /**
  * ftrace_regex_open - initialize function tracer filter files
  * @ops: The ftrace_ops that hold the hash filters
@@ -2821,7 +3009,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 		hash = ops->filter_hash;
 
 	if (file->f_mode & FMODE_WRITE) {
-		iter->hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, hash);
+		const int size_bits = FTRACE_HASH_DEFAULT_BITS;
+
+		if (file->f_flags & O_TRUNC)
+			iter->hash = alloc_ftrace_hash(size_bits);
+		else
+			iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash);
+
 		if (!iter->hash) {
 			trace_parser_put(&iter->parser);
 			kfree(iter);
@@ -2830,10 +3024,6 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 		}
 	}
 
-	if ((file->f_mode & FMODE_WRITE) &&
-	    (file->f_flags & O_TRUNC))
-		ftrace_filter_reset(iter->hash);
-
 	if (file->f_mode & FMODE_READ) {
 		iter->pg = ftrace_pages_start;
 
@@ -3524,10 +3714,6 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 	struct ftrace_hash *hash;
 	int ret;
 
-	/* All global ops uses the global ops filters */
-	if (ops->flags & FTRACE_OPS_FL_GLOBAL)
-		ops = &global_ops;
-
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
@@ -3538,14 +3724,16 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 	else
 		orig_hash = &ops->notrace_hash;
 
-	hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+	if (reset)
+		hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+	else
+		hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash);
+
 	if (!hash) {
 		ret = -ENOMEM;
 		goto out_regex_unlock;
 	}
 
-	if (reset)
-		ftrace_filter_reset(hash);
 	if (buf && !ftrace_match_records(hash, buf, len)) {
 		ret = -EINVAL;
 		goto out_regex_unlock;
@@ -3639,8 +3827,7 @@ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
 }
 EXPORT_SYMBOL_GPL(ftrace_set_notrace);
 /**
- * ftrace_set_filter - set a function to filter on in ftrace
- * @ops - the ops to set the filter with
+ * ftrace_set_global_filter - set a function to filter on with global tracers
  * @buf - the string that holds the function filter text.
  * @len - the length of the string.
  * @reset - non zero to reset all filters before applying this filter.
@@ -3655,8 +3842,7 @@ void ftrace_set_global_filter(unsigned char *buf, int len, int reset)
 EXPORT_SYMBOL_GPL(ftrace_set_global_filter);
 
 /**
- * ftrace_set_notrace - set a function to not trace in ftrace
- * @ops - the ops to set the notrace filter with
+ * ftrace_set_global_notrace - set a function to not trace with global tracers
  * @buf - the string that holds the function notrace text.
  * @len - the length of the string.
  * @reset - non zero to reset all filters before applying this filter.
@@ -3699,6 +3885,7 @@ __setup("ftrace_filter=", set_ftrace_filter);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata;
 static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer);
 
 static int __init set_graph_function(char *str)
@@ -3708,16 +3895,29 @@ static int __init set_graph_function(char *str)
 }
 __setup("ftrace_graph_filter=", set_graph_function);
 
-static void __init set_ftrace_early_graph(char *buf)
+static int __init set_graph_notrace_function(char *str)
+{
+	strlcpy(ftrace_graph_notrace_buf, str, FTRACE_FILTER_SIZE);
+	return 1;
+}
+__setup("ftrace_graph_notrace=", set_graph_notrace_function);
+
+static void __init set_ftrace_early_graph(char *buf, int enable)
 {
 	int ret;
 	char *func;
+	unsigned long *table = ftrace_graph_funcs;
+	int *count = &ftrace_graph_count;
+
+	if (!enable) {
+		table = ftrace_graph_notrace_funcs;
+		count = &ftrace_graph_notrace_count;
+	}
 
 	while (buf) {
 		func = strsep(&buf, ",");
 		/* we allow only one expression at a time */
-		ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count,
-				      FTRACE_GRAPH_MAX_FUNCS, func);
+		ret = ftrace_set_func(table, count, FTRACE_GRAPH_MAX_FUNCS, func);
 		if (ret)
 			printk(KERN_DEBUG "ftrace: function %s not "
 					  "traceable\n", func);
@@ -3746,7 +3946,9 @@ static void __init set_ftrace_early_filters(void)
 		ftrace_set_early_filter(&global_ops, ftrace_notrace_buf, 0);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (ftrace_graph_buf[0])
-		set_ftrace_early_graph(ftrace_graph_buf);
+		set_ftrace_early_graph(ftrace_graph_buf, 1);
+	if (ftrace_graph_notrace_buf[0])
+		set_ftrace_early_graph(ftrace_graph_notrace_buf, 0);
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 }
 
@@ -3888,7 +4090,12 @@ static int g_show(struct seq_file *m, void *v)
 		return 0;
 
 	if (ptr == (unsigned long *)1) {
-		seq_printf(m, "#### all functions enabled ####\n");
+		struct ftrace_graph_data *fgd = m->private;
+
+		if (fgd->table == ftrace_graph_funcs)
+			seq_printf(m, "#### all functions enabled ####\n");
+		else
+			seq_printf(m, "#### no functions disabled ####\n");
 		return 0;
 	}
 
@@ -4443,6 +4650,34 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip, void *regs)
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+__init void ftrace_init_global_array_ops(struct trace_array *tr)
+{
+	tr->ops = &global_ops;
+	tr->ops->private = tr;
+}
+
+void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func)
+{
+	/* If we filter on pids, update to use the pid function */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
+		if (WARN_ON(tr->ops->func != ftrace_stub))
+			printk("ftrace ops had %pS for function\n",
+			       tr->ops->func);
+		/* Only the top level instance does pid tracing */
+		if (!list_empty(&ftrace_pids)) {
+			set_ftrace_pid_function(func);
+			func = ftrace_pid_func;
+		}
+	}
+	tr->ops->func = func;
+	tr->ops->private = tr;
+}
+
+void ftrace_reset_array_ops(struct trace_array *tr)
+{
+	tr->ops->func = ftrace_stub;
+}
+
 static void
 ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 			struct ftrace_ops *op, struct pt_regs *regs)
@@ -4488,9 +4723,6 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	struct ftrace_ops *op;
 	int bit;
 
-	if (function_trace_stop)
-		return;
-
 	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
@@ -4501,9 +4733,15 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	 */
 	preempt_disable_notrace();
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
-		if (ftrace_ops_test(op, ip, regs))
+		if (ftrace_ops_test(op, ip, regs)) {
+			if (FTRACE_WARN_ON(!op->func)) {
+				pr_warn("op=%p %pS\n", op, op);
+				goto out;
+			}
 			op->func(ip, parent_ip, op, regs);
+		}
 	} while_for_each_ftrace_op(op);
+out:
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
 }
@@ -4908,7 +5146,6 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 static int ftrace_graph_active;
-static struct notifier_block ftrace_suspend_notifier;
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 {
@@ -5054,13 +5291,6 @@ ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state,
 	return NOTIFY_DONE;
 }
 
-/* Just a place holder for function graph */
-static struct ftrace_ops fgraph_ops __read_mostly = {
-	.func		= ftrace_stub,
-	.flags		= FTRACE_OPS_FL_STUB | FTRACE_OPS_FL_GLOBAL |
-				FTRACE_OPS_FL_RECURSION_SAFE,
-};
-
 static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
 {
 	if (!ftrace_ops_test(&global_ops, trace->func, NULL))
@@ -5085,6 +5315,10 @@ static void update_function_graph_func(void)
 		ftrace_graph_entry = ftrace_graph_entry_test;
 }
 
+static struct notifier_block ftrace_suspend_notifier = {
+	.notifier_call = ftrace_suspend_notifier_call,
+};
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -5098,7 +5332,6 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 		goto out;
 	}
 
-	ftrace_suspend_notifier.notifier_call = ftrace_suspend_notifier_call;
 	register_pm_notifier(&ftrace_suspend_notifier);
 
 	ftrace_graph_active++;
@@ -5120,7 +5353,16 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	ftrace_graph_entry = ftrace_graph_entry_test;
 	update_function_graph_func();
 
-	ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
+	/* Function graph doesn't use the .func field of global_ops */
+	global_ops.flags |= FTRACE_OPS_FL_STUB;
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* Optimize function graph calling (if implemented by arch) */
+	if (FTRACE_GRAPH_TRAMP_ADDR != 0)
+		global_ops.trampoline = FTRACE_GRAPH_TRAMP_ADDR;
+#endif
+
+	ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
 
 out:
 	mutex_unlock(&ftrace_lock);
@@ -5138,7 +5380,12 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
 	__ftrace_graph_entry = ftrace_graph_entry_stub;
-	ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
+	ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET);
+	global_ops.flags &= ~FTRACE_OPS_FL_STUB;
+#ifdef CONFIG_DYNAMIC_FTRACE
+	if (FTRACE_GRAPH_TRAMP_ADDR != 0)
+		global_ops.trampoline = 0;
+#endif
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
 
@@ -5218,9 +5465,4 @@ void ftrace_graph_exit_task(struct task_struct *t)
 
 	kfree(ret_stack);
 }
-
-void ftrace_graph_stop(void)
-{
-	ftrace_stop();
-}
 #endif
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index c634868c292..925f629658d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -543,7 +543,7 @@ static void rb_wake_up_waiters(struct irq_work *work)
  * as data is added to any of the @buffer's cpu buffers. Otherwise
  * it will wait for data to be added to a specific cpu buffer.
  */
-void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
+int ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
@@ -557,6 +557,8 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 	if (cpu == RING_BUFFER_ALL_CPUS)
 		work = &buffer->irq_work;
 	else {
+		if (!cpumask_test_cpu(cpu, buffer->cpumask))
+			return -ENODEV;
 		cpu_buffer = buffer->buffers[cpu];
 		work = &cpu_buffer->irq_work;
 	}
@@ -591,6 +593,7 @@ void ring_buffer_wait(struct ring_buffer *buffer, int cpu)
 		schedule();
 
 	finish_wait(&work->waiters, &wait);
+	return 0;
 }
 
 /**
@@ -613,10 +616,6 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct rb_irq_work *work;
 
-	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
-	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
-		return POLLIN | POLLRDNORM;
-
 	if (cpu == RING_BUFFER_ALL_CPUS)
 		work = &buffer->irq_work;
 	else {
@@ -1690,22 +1689,14 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 			if (!cpu_buffer->nr_pages_to_update)
 				continue;
 
-			/* The update must run on the CPU that is being updated. */
-			preempt_disable();
-			if (cpu == smp_processor_id() || !cpu_online(cpu)) {
+			/* Can't run something on an offline CPU. */
+			if (!cpu_online(cpu)) {
 				rb_update_pages(cpu_buffer);
 				cpu_buffer->nr_pages_to_update = 0;
 			} else {
-				/*
-				 * Can not disable preemption for schedule_work_on()
-				 * on PREEMPT_RT.
-				 */
-				preempt_enable();
 				schedule_work_on(cpu,
 						&cpu_buffer->update_pages_work);
-				preempt_disable();
 			}
-			preempt_enable();
 		}
 
 		/* wait for all the updates to complete */
@@ -1743,22 +1734,14 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 
 		get_online_cpus();
 
-		preempt_disable();
-		/* The update must run on the CPU that is being updated. */
-		if (cpu_id == smp_processor_id() || !cpu_online(cpu_id))
+		/* Can't run something on an offline CPU. */
+		if (!cpu_online(cpu_id))
 			rb_update_pages(cpu_buffer);
 		else {
-			/*
-			 * Can not disable preemption for schedule_work_on()
-			 * on PREEMPT_RT.
-			 */
-			preempt_enable();
 			schedule_work_on(cpu_id,
 					 &cpu_buffer->update_pages_work);
 			wait_for_completion(&cpu_buffer->update_done);
-			preempt_disable();
 		}
-		preempt_enable();
 
 		cpu_buffer->nr_pages_to_update = 0;
 		put_online_cpus();
@@ -3776,7 +3759,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	if (rb_per_cpu_empty(cpu_buffer))
 		return NULL;
 
-	if (iter->head >= local_read(&iter->head_page->page->commit)) {
+	if (iter->head >= rb_page_size(iter->head_page)) {
 		rb_inc_iter(iter);
 		goto again;
 	}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 737b0efa1a6..8bb80fe0876 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -275,7 +275,7 @@ int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
 }
 EXPORT_SYMBOL_GPL(call_filter_check_discard);
 
-cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
+static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 {
 	u64 ts;
 
@@ -466,6 +466,12 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	struct print_entry *entry;
 	unsigned long irq_flags;
 	int alloc;
+	int pc;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
@@ -475,7 +481,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, 
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -492,6 +498,7 @@ int __trace_puts(unsigned long ip, const char *str, int size)
 		entry->buf[size] = '\0';
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return size;
 }
@@ -509,6 +516,12 @@ int __trace_bputs(unsigned long ip, const char *str)
 	struct bputs_entry *entry;
 	unsigned long irq_flags;
 	int size = sizeof(struct bputs_entry);
+	int pc;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	pc = preempt_count();
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
@@ -516,7 +529,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	local_save_flags(irq_flags);
 	buffer = global_trace.trace_buffer.buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
-					  irq_flags, preempt_count());
+					  irq_flags, pc);
 	if (!event)
 		return 0;
 
@@ -525,6 +538,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	entry->str			= str;
 
 	__buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(buffer, irq_flags, 4, pc);
 
 	return 1;
 }
@@ -599,7 +613,7 @@ static int alloc_snapshot(struct trace_array *tr)
 	return 0;
 }
 
-void free_snapshot(struct trace_array *tr)
+static void free_snapshot(struct trace_array *tr)
 {
 	/*
 	 * We don't free the ring buffer. instead, resize it because
@@ -809,7 +823,7 @@ static struct {
 	{ trace_clock_local,	"local",	1 },
 	{ trace_clock_global,	"global",	1 },
 	{ trace_clock_counter,	"counter",	0 },
-	{ trace_clock_jiffies,	"uptime",	1 },
+	{ trace_clock_jiffies,	"uptime",	0 },
 	{ trace_clock,		"perf",		1 },
 	ARCH_TRACE_CLOCKS
 };
@@ -923,30 +937,6 @@ out:
 	return ret;
 }
 
-ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
-{
-	int len;
-	int ret;
-
-	if (!cnt)
-		return 0;
-
-	if (s->len <= s->readpos)
-		return -EBUSY;
-
-	len = s->len - s->readpos;
-	if (cnt > len)
-		cnt = len;
-	ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);
-	if (ret == cnt)
-		return -EFAULT;
-
-	cnt -= ret;
-
-	s->readpos += cnt;
-	return cnt;
-}
-
 static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 {
 	int len;
@@ -963,27 +953,9 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	return cnt;
 }
 
-/*
- * ftrace_max_lock is used to protect the swapping of buffers
- * when taking a max snapshot. The buffers themselves are
- * protected by per_cpu spinlocks. But the action of the swap
- * needs its own lock.
- *
- * This is defined as a arch_spinlock_t in order to help
- * with performance when lockdep debugging is enabled.
- *
- * It is also used in other places outside the update_max_tr
- * so it needs to be defined outside of the
- * CONFIG_TRACER_MAX_TRACE.
- */
-static arch_spinlock_t ftrace_max_lock =
-	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
-
 unsigned long __read_mostly	tracing_thresh;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-unsigned long __read_mostly	tracing_max_latency;
-
 /*
  * Copy the new maximum trace into the separate maximum-trace
  * structure. (this way the maximum trace is permanently saved,
@@ -1000,7 +972,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	max_buf->cpu = cpu;
 	max_buf->time_start = data->preempt_timestamp;
 
-	max_data->saved_latency = tracing_max_latency;
+	max_data->saved_latency = tr->max_latency;
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
 
@@ -1048,14 +1020,14 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 	}
 
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 
 	buf = tr->trace_buffer.buffer;
 	tr->trace_buffer.buffer = tr->max_buffer.buffer;
 	tr->max_buffer.buffer = buf;
 
 	__update_max_tr(tr, tsk, cpu);
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 }
 
 /**
@@ -1081,7 +1053,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 		return;
 	}
 
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 
 	ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu);
 
@@ -1099,17 +1071,17 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
 	__update_max_tr(tr, tsk, cpu);
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
-static void default_wait_pipe(struct trace_iterator *iter)
+static int wait_on_pipe(struct trace_iterator *iter)
 {
 	/* Iterators are static, they should be filled or empty */
 	if (trace_buffer_iter(iter, iter->cpu_file))
-		return;
+		return 0;
 
-	ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+	return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
 }
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
@@ -1220,8 +1192,6 @@ int register_tracer(struct tracer *type)
 	else
 		if (!type->flags->opts)
 			type->flags->opts = dummy_tracer_opt;
-	if (!type->wait_pipe)
-		type->wait_pipe = default_wait_pipe;
 
 	ret = run_tracer_selftest(type);
 	if (ret < 0)
@@ -1305,22 +1275,71 @@ void tracing_reset_all_online_cpus(void)
 	}
 }
 
-#define SAVED_CMDLINES 128
+#define SAVED_CMDLINES_DEFAULT 128
 #define NO_CMDLINE_MAP UINT_MAX
-static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
-static unsigned map_cmdline_to_pid[SAVED_CMDLINES];
-static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
-static int cmdline_idx;
 static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+struct saved_cmdlines_buffer {
+	unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1];
+	unsigned *map_cmdline_to_pid;
+	unsigned cmdline_num;
+	int cmdline_idx;
+	char *saved_cmdlines;
+};
+static struct saved_cmdlines_buffer *savedcmd;
 
 /* temporary disable recording */
 static atomic_t trace_record_cmdline_disabled __read_mostly;
 
-static void trace_init_cmdlines(void)
+static inline char *get_saved_cmdlines(int idx)
+{
+	return &savedcmd->saved_cmdlines[idx * TASK_COMM_LEN];
+}
+
+static inline void set_cmdline(int idx, const char *cmdline)
+{
+	memcpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
+}
+
+static int allocate_cmdlines_buffer(unsigned int val,
+				    struct saved_cmdlines_buffer *s)
 {
-	memset(&map_pid_to_cmdline, NO_CMDLINE_MAP, sizeof(map_pid_to_cmdline));
-	memset(&map_cmdline_to_pid, NO_CMDLINE_MAP, sizeof(map_cmdline_to_pid));
-	cmdline_idx = 0;
+	s->map_cmdline_to_pid = kmalloc(val * sizeof(*s->map_cmdline_to_pid),
+					GFP_KERNEL);
+	if (!s->map_cmdline_to_pid)
+		return -ENOMEM;
+
+	s->saved_cmdlines = kmalloc(val * TASK_COMM_LEN, GFP_KERNEL);
+	if (!s->saved_cmdlines) {
+		kfree(s->map_cmdline_to_pid);
+		return -ENOMEM;
+	}
+
+	s->cmdline_idx = 0;
+	s->cmdline_num = val;
+	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
+	       sizeof(s->map_pid_to_cmdline));
+	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
+	       val * sizeof(*s->map_cmdline_to_pid));
+
+	return 0;
+}
+
+static int trace_create_savedcmd(void)
+{
+	int ret;
+
+	savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL);
+	if (!savedcmd)
+		return -ENOMEM;
+
+	ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
+	if (ret < 0) {
+		kfree(savedcmd);
+		savedcmd = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 int is_tracing_stopped(void)
@@ -1353,7 +1372,7 @@ void tracing_start(void)
 	}
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&global_trace.max_lock);
 
 	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
@@ -1365,9 +1384,8 @@ void tracing_start(void)
 		ring_buffer_record_enable(buffer);
 #endif
 
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&global_trace.max_lock);
 
-	ftrace_start();
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
 }
@@ -1414,13 +1432,12 @@ void tracing_stop(void)
 	struct ring_buffer *buffer;
 	unsigned long flags;
 
-	ftrace_stop();
 	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
 	if (global_trace.stop_count++)
 		goto out;
 
 	/* Prevent the buffers from switching */
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&global_trace.max_lock);
 
 	buffer = global_trace.trace_buffer.buffer;
 	if (buffer)
@@ -1432,7 +1449,7 @@ void tracing_stop(void)
 		ring_buffer_record_disable(buffer);
 #endif
 
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&global_trace.max_lock);
 
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
@@ -1461,12 +1478,12 @@ static void tracing_stop_tr(struct trace_array *tr)
 
 void trace_stop_cmdline_recording(void);
 
-static void trace_save_cmdline(struct task_struct *tsk)
+static int trace_save_cmdline(struct task_struct *tsk)
 {
 	unsigned pid, idx;
 
 	if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT))
-		return;
+		return 0;
 
 	/*
 	 * It's not the end of the world if we don't get
@@ -1475,11 +1492,11 @@ static void trace_save_cmdline(struct task_struct *tsk)
 	 * so if we miss here, then better luck next time.
 	 */
 	if (!arch_spin_trylock(&trace_cmdline_lock))
-		return;
+		return 0;
 
-	idx = map_pid_to_cmdline[tsk->pid];
+	idx = savedcmd->map_pid_to_cmdline[tsk->pid];
 	if (idx == NO_CMDLINE_MAP) {
-		idx = (cmdline_idx + 1) % SAVED_CMDLINES;
+		idx = (savedcmd->cmdline_idx + 1) % savedcmd->cmdline_num;
 
 		/*
 		 * Check whether the cmdline buffer at idx has a pid
@@ -1487,22 +1504,24 @@ static void trace_save_cmdline(struct task_struct *tsk)
 		 * need to clear the map_pid_to_cmdline. Otherwise we
 		 * would read the new comm for the old pid.
 		 */
-		pid = map_cmdline_to_pid[idx];
+		pid = savedcmd->map_cmdline_to_pid[idx];
 		if (pid != NO_CMDLINE_MAP)
-			map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
+			savedcmd->map_pid_to_cmdline[pid] = NO_CMDLINE_MAP;
 
-		map_cmdline_to_pid[idx] = tsk->pid;
-		map_pid_to_cmdline[tsk->pid] = idx;
+		savedcmd->map_cmdline_to_pid[idx] = tsk->pid;
+		savedcmd->map_pid_to_cmdline[tsk->pid] = idx;
 
-		cmdline_idx = idx;
+		savedcmd->cmdline_idx = idx;
 	}
 
-	memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN);
+	set_cmdline(idx, tsk->comm);
 
 	arch_spin_unlock(&trace_cmdline_lock);
+
+	return 1;
 }
 
-void trace_find_cmdline(int pid, char comm[])
+static void __trace_find_cmdline(int pid, char comm[])
 {
 	unsigned map;
 
@@ -1521,13 +1540,19 @@ void trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
-	preempt_disable();
-	arch_spin_lock(&trace_cmdline_lock);
-	map = map_pid_to_cmdline[pid];
+	map = savedcmd->map_pid_to_cmdline[pid];
 	if (map != NO_CMDLINE_MAP)
-		strcpy(comm, saved_cmdlines[map]);
+		strcpy(comm, get_saved_cmdlines(map));
 	else
 		strcpy(comm, "<...>");
+}
+
+void trace_find_cmdline(int pid, char comm[])
+{
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+
+	__trace_find_cmdline(pid, comm);
 
 	arch_spin_unlock(&trace_cmdline_lock);
 	preempt_enable();
@@ -1541,9 +1566,8 @@ void tracing_record_cmdline(struct task_struct *tsk)
 	if (!__this_cpu_read(trace_cmdline_save))
 		return;
 
-	__this_cpu_write(trace_cmdline_save, false);
-
-	trace_save_cmdline(tsk);
+	if (trace_save_cmdline(tsk))
+		__this_cpu_write(trace_cmdline_save, false);
 }
 
 void
@@ -1746,7 +1770,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	 */
 	barrier();
 	if (use_stack == 1) {
-		trace.entries		= &__get_cpu_var(ftrace_stack).calls[0];
+		trace.entries		= this_cpu_ptr(ftrace_stack.calls);
 		trace.max_entries	= FTRACE_STACK_MAX_ENTRIES;
 
 		if (regs)
@@ -1995,7 +2019,21 @@ void trace_printk_init_buffers(void)
 	if (alloc_percpu_trace_buffer())
 		return;
 
-	pr_info("ftrace: Allocated trace_printk buffers\n");
+	/* trace_printk() is for debug use only. Don't use it in production. */
+
+	pr_warning("\n**********************************************************\n");
+	pr_warning("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("** trace_printk() being used. Allocating extra memory.  **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("** This means that this is a DEBUG kernel and it is     **\n");
+	pr_warning("** unsafe for produciton use.                           **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("** If you see this message and you are not debugging    **\n");
+	pr_warning("** the kernel, report this immediately to your vendor!  **\n");
+	pr_warning("**                                                      **\n");
+	pr_warning("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
+	pr_warning("**********************************************************\n");
 
 	/* Expand the buffers to set size */
 	tracing_update_buffers();
@@ -3333,7 +3371,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	mutex_lock(&tracing_cpumask_update_lock);
 
 	local_irq_disable();
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&tr->max_lock);
 	for_each_tracing_cpu(cpu) {
 		/*
 		 * Increase/decrease the disabled counter if we are
@@ -3350,7 +3388,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 			ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu);
 		}
 	}
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&tr->max_lock);
 	local_irq_enable();
 
 	cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new);
@@ -3592,6 +3630,7 @@ static const char readme_msg[] =
 	"  trace_options\t\t- Set format or modify how tracing happens\n"
 	"\t\t\t  Disable an option by adding a suffix 'no' to the\n"
 	"\t\t\t  option name\n"
+	"  saved_cmdlines_size\t- echo command number in here to store comm-pid list\n"
 #ifdef CONFIG_DYNAMIC_FTRACE
 	"\n  available_filter_functions - list of functions that can be filtered on\n"
 	"  set_ftrace_filter\t- echo function name in here to only trace these\n"
@@ -3636,6 +3675,7 @@ static const char readme_msg[] =
 #endif
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	"  set_graph_function\t- Trace the nested calls of a function (function_graph)\n"
+	"  set_graph_notrace\t- Do not trace the nested calls of a function (function_graph)\n"
 	"  max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n"
 #endif
 #ifdef CONFIG_TRACER_SNAPSHOT
@@ -3705,55 +3745,153 @@ static const struct file_operations tracing_readme_fops = {
 	.llseek		= generic_file_llseek,
 };
 
+static void *saved_cmdlines_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	unsigned int *ptr = v;
+
+	if (*pos || m->count)
+		ptr++;
+
+	(*pos)++;
+
+	for (; ptr < &savedcmd->map_cmdline_to_pid[savedcmd->cmdline_num];
+	     ptr++) {
+		if (*ptr == -1 || *ptr == NO_CMDLINE_MAP)
+			continue;
+
+		return ptr;
+	}
+
+	return NULL;
+}
+
+static void *saved_cmdlines_start(struct seq_file *m, loff_t *pos)
+{
+	void *v;
+	loff_t l = 0;
+
+	preempt_disable();
+	arch_spin_lock(&trace_cmdline_lock);
+
+	v = &savedcmd->map_cmdline_to_pid[0];
+	while (l <= *pos) {
+		v = saved_cmdlines_next(m, v, &l);
+		if (!v)
+			return NULL;
+	}
+
+	return v;
+}
+
+static void saved_cmdlines_stop(struct seq_file *m, void *v)
+{
+	arch_spin_unlock(&trace_cmdline_lock);
+	preempt_enable();
+}
+
+static int saved_cmdlines_show(struct seq_file *m, void *v)
+{
+	char buf[TASK_COMM_LEN];
+	unsigned int *pid = v;
+
+	__trace_find_cmdline(*pid, buf);
+	seq_printf(m, "%d %s\n", *pid, buf);
+	return 0;
+}
+
+static const struct seq_operations tracing_saved_cmdlines_seq_ops = {
+	.start		= saved_cmdlines_start,
+	.next		= saved_cmdlines_next,
+	.stop		= saved_cmdlines_stop,
+	.show		= saved_cmdlines_show,
+};
+
+static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp)
+{
+	if (tracing_disabled)
+		return -ENODEV;
+
+	return seq_open(filp, &tracing_saved_cmdlines_seq_ops);
+}
+
+static const struct file_operations tracing_saved_cmdlines_fops = {
+	.open		= tracing_saved_cmdlines_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 static ssize_t
-tracing_saved_cmdlines_read(struct file *file, char __user *ubuf,
-				size_t cnt, loff_t *ppos)
+tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
+				 size_t cnt, loff_t *ppos)
 {
-	char *buf_comm;
-	char *file_buf;
-	char *buf;
-	int len = 0;
-	int pid;
-	int i;
+	char buf[64];
+	int r;
+
+	arch_spin_lock(&trace_cmdline_lock);
+	r = scnprintf(buf, sizeof(buf), "%u\n", savedcmd->cmdline_num);
+	arch_spin_unlock(&trace_cmdline_lock);
 
-	file_buf = kmalloc(SAVED_CMDLINES*(16+TASK_COMM_LEN), GFP_KERNEL);
-	if (!file_buf)
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
+{
+	kfree(s->saved_cmdlines);
+	kfree(s->map_cmdline_to_pid);
+	kfree(s);
+}
+
+static int tracing_resize_saved_cmdlines(unsigned int val)
+{
+	struct saved_cmdlines_buffer *s, *savedcmd_temp;
+
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
 		return -ENOMEM;
 
-	buf_comm = kmalloc(TASK_COMM_LEN, GFP_KERNEL);
-	if (!buf_comm) {
-		kfree(file_buf);
+	if (allocate_cmdlines_buffer(val, s) < 0) {
+		kfree(s);
 		return -ENOMEM;
 	}
 
-	buf = file_buf;
+	arch_spin_lock(&trace_cmdline_lock);
+	savedcmd_temp = savedcmd;
+	savedcmd = s;
+	arch_spin_unlock(&trace_cmdline_lock);
+	free_saved_cmdlines_buffer(savedcmd_temp);
 
-	for (i = 0; i < SAVED_CMDLINES; i++) {
-		int r;
+	return 0;
+}
 
-		pid = map_cmdline_to_pid[i];
-		if (pid == -1 || pid == NO_CMDLINE_MAP)
-			continue;
+static ssize_t
+tracing_saved_cmdlines_size_write(struct file *filp, const char __user *ubuf,
+				  size_t cnt, loff_t *ppos)
+{
+	unsigned long val;
+	int ret;
 
-		trace_find_cmdline(pid, buf_comm);
-		r = sprintf(buf, "%d %s\n", pid, buf_comm);
-		buf += r;
-		len += r;
-	}
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
+		return ret;
 
-	len = simple_read_from_buffer(ubuf, cnt, ppos,
-				      file_buf, len);
+	/* must have at least 1 entry or less than PID_MAX_DEFAULT */
+	if (!val || val > PID_MAX_DEFAULT)
+		return -EINVAL;
 
-	kfree(file_buf);
-	kfree(buf_comm);
+	ret = tracing_resize_saved_cmdlines((unsigned int)val);
+	if (ret < 0)
+		return ret;
 
-	return len;
+	*ppos += cnt;
+
+	return cnt;
 }
 
-static const struct file_operations tracing_saved_cmdlines_fops = {
-    .open       = tracing_open_generic,
-    .read       = tracing_saved_cmdlines_read,
-    .llseek	= generic_file_llseek,
+static const struct file_operations tracing_saved_cmdlines_size_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_saved_cmdlines_size_read,
+	.write		= tracing_saved_cmdlines_size_write,
 };
 
 static ssize_t
@@ -4077,10 +4215,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 }
 
 static ssize_t
-tracing_max_lat_read(struct file *filp, char __user *ubuf,
-		     size_t cnt, loff_t *ppos)
+tracing_nsecs_read(unsigned long *ptr, char __user *ubuf,
+		   size_t cnt, loff_t *ppos)
 {
-	unsigned long *ptr = filp->private_data;
 	char buf[64];
 	int r;
 
@@ -4092,10 +4229,9 @@ tracing_max_lat_read(struct file *filp, char __user *ubuf,
 }
 
 static ssize_t
-tracing_max_lat_write(struct file *filp, const char __user *ubuf,
-		      size_t cnt, loff_t *ppos)
+tracing_nsecs_write(unsigned long *ptr, const char __user *ubuf,
+		    size_t cnt, loff_t *ppos)
 {
-	unsigned long *ptr = filp->private_data;
 	unsigned long val;
 	int ret;
 
@@ -4108,6 +4244,52 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
 	return cnt;
 }
 
+static ssize_t
+tracing_thresh_read(struct file *filp, char __user *ubuf,
+		    size_t cnt, loff_t *ppos)
+{
+	return tracing_nsecs_read(&tracing_thresh, ubuf, cnt, ppos);
+}
+
+static ssize_t
+tracing_thresh_write(struct file *filp, const char __user *ubuf,
+		     size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	int ret;
+
+	mutex_lock(&trace_types_lock);
+	ret = tracing_nsecs_write(&tracing_thresh, ubuf, cnt, ppos);
+	if (ret < 0)
+		goto out;
+
+	if (tr->current_trace->update_thresh) {
+		ret = tr->current_trace->update_thresh(tr);
+		if (ret < 0)
+			goto out;
+	}
+
+	ret = cnt;
+out:
+	mutex_unlock(&trace_types_lock);
+
+	return ret;
+}
+
+static ssize_t
+tracing_max_lat_read(struct file *filp, char __user *ubuf,
+		     size_t cnt, loff_t *ppos)
+{
+	return tracing_nsecs_read(filp->private_data, ubuf, cnt, ppos);
+}
+
+static ssize_t
+tracing_max_lat_write(struct file *filp, const char __user *ubuf,
+		      size_t cnt, loff_t *ppos)
+{
+	return tracing_nsecs_write(filp->private_data, ubuf, cnt, ppos);
+}
+
 static int tracing_open_pipe(struct inode *inode, struct file *filp)
 {
 	struct trace_array *tr = inode->i_private;
@@ -4225,29 +4407,11 @@ tracing_poll_pipe(struct file *filp, poll_table *poll_table)
 	return trace_poll(iter, filp, poll_table);
 }
 
-/*
- * This is a make-shift waitqueue.
- * A tracer might use this callback on some rare cases:
- *
- *  1) the current tracer might hold the runqueue lock when it wakes up
- *     a reader, hence a deadlock (sched, function, and function graph tracers)
- *  2) the function tracers, trace all functions, we don't want
- *     the overhead of calling wake_up and friends
- *     (and tracing them too)
- *
- *     Anyway, this is really very primitive wakeup.
- */
-void poll_wait_pipe(struct trace_iterator *iter)
-{
-	set_current_state(TASK_INTERRUPTIBLE);
-	/* sleep for 100 msecs, and try again. */
-	schedule_timeout(HZ / 10);
-}
-
 /* Must be called with trace_types_lock mutex held. */
 static int tracing_wait_pipe(struct file *filp)
 {
 	struct trace_iterator *iter = filp->private_data;
+	int ret;
 
 	while (trace_empty(iter)) {
 
@@ -4255,15 +4419,6 @@ static int tracing_wait_pipe(struct file *filp)
 			return -EAGAIN;
 		}
 
-		mutex_unlock(&iter->mutex);
-
-		iter->trace->wait_pipe(iter);
-
-		mutex_lock(&iter->mutex);
-
-		if (signal_pending(current))
-			return -EINTR;
-
 		/*
 		 * We block until we read something and tracing is disabled.
 		 * We still block if tracing is disabled, but we have never
@@ -4275,6 +4430,18 @@ static int tracing_wait_pipe(struct file *filp)
 		 */
 		if (!tracing_is_on() && iter->pos)
 			break;
+
+		mutex_unlock(&iter->mutex);
+
+		ret = wait_on_pipe(iter);
+
+		mutex_lock(&iter->mutex);
+
+		if (ret)
+			return ret;
+
+		if (signal_pending(current))
+			return -EINTR;
 	}
 
 	return 1;
@@ -5024,6 +5191,13 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp)
 #endif /* CONFIG_TRACER_SNAPSHOT */
 
 
+static const struct file_operations tracing_thresh_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_thresh_read,
+	.write		= tracing_thresh_write,
+	.llseek		= generic_file_llseek,
+};
+
 static const struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
@@ -5197,8 +5371,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 				goto out_unlock;
 			}
 			mutex_unlock(&trace_types_lock);
-			iter->trace->wait_pipe(iter);
+			ret = wait_on_pipe(iter);
 			mutex_lock(&trace_types_lock);
+			if (ret) {
+				size = ret;
+				goto out_unlock;
+			}
 			if (signal_pending(current)) {
 				size = -EINTR;
 				goto out_unlock;
@@ -5408,8 +5586,10 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			goto out;
 		}
 		mutex_unlock(&trace_types_lock);
-		iter->trace->wait_pipe(iter);
+		ret = wait_on_pipe(iter);
 		mutex_lock(&trace_types_lock);
+		if (ret)
+			goto out;
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			goto out;
@@ -5955,10 +6135,8 @@ destroy_trace_option_files(struct trace_option_dentry *topts)
 	if (!topts)
 		return;
 
-	for (cnt = 0; topts[cnt].opt; cnt++) {
-		if (topts[cnt].entry)
-			debugfs_remove(topts[cnt].entry);
-	}
+	for (cnt = 0; topts[cnt].opt; cnt++)
+		debugfs_remove(topts[cnt].entry);
 
 	kfree(topts);
 }
@@ -6102,6 +6280,28 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
 	return 0;
 }
 
+static void free_trace_buffer(struct trace_buffer *buf)
+{
+	if (buf->buffer) {
+		ring_buffer_free(buf->buffer);
+		buf->buffer = NULL;
+		free_percpu(buf->data);
+		buf->data = NULL;
+	}
+}
+
+static void free_trace_buffers(struct trace_array *tr)
+{
+	if (!tr)
+		return;
+
+	free_trace_buffer(&tr->trace_buffer);
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+	free_trace_buffer(&tr->max_buffer);
+#endif
+}
+
 static int new_instance_create(const char *name)
 {
 	struct trace_array *tr;
@@ -6131,6 +6331,8 @@ static int new_instance_create(const char *name)
 
 	raw_spin_lock_init(&tr->start_lock);
 
+	tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
 	tr->current_trace = &nop_trace;
 
 	INIT_LIST_HEAD(&tr->systems);
@@ -6158,8 +6360,7 @@ static int new_instance_create(const char *name)
 	return 0;
 
  out_free_tr:
-	if (tr->trace_buffer.buffer)
-		ring_buffer_free(tr->trace_buffer.buffer);
+	free_trace_buffers(tr);
 	free_cpumask_var(tr->tracing_cpumask);
 	kfree(tr->name);
 	kfree(tr);
@@ -6199,8 +6400,7 @@ static int instance_delete(const char *name)
 	event_trace_del_tracer(tr);
 	ftrace_destroy_function_files(tr);
 	debugfs_remove_recursive(tr->dir);
-	free_percpu(tr->trace_buffer.data);
-	ring_buffer_free(tr->trace_buffer.buffer);
+	free_trace_buffers(tr);
 
 	kfree(tr->name);
 	kfree(tr);
@@ -6328,6 +6528,11 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("tracing_on", 0644, d_tracer,
 			  tr, &rb_simple_fops);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
+	trace_create_file("tracing_max_latency", 0644, d_tracer,
+			&tr->max_latency, &tracing_max_lat_fops);
+#endif
+
 	if (ftrace_create_function_files(tr, d_tracer))
 		WARN(1, "Could not allocate function filter files");
 
@@ -6353,13 +6558,8 @@ static __init int tracer_init_debugfs(void)
 
 	init_tracer_debugfs(&global_trace, d_tracer);
 
-#ifdef CONFIG_TRACER_MAX_TRACE
-	trace_create_file("tracing_max_latency", 0644, d_tracer,
-			&tracing_max_latency, &tracing_max_lat_fops);
-#endif
-
 	trace_create_file("tracing_thresh", 0644, d_tracer,
-			&tracing_thresh, &tracing_max_lat_fops);
+			&global_trace, &tracing_thresh_fops);
 
 	trace_create_file("README", 0444, d_tracer,
 			NULL, &tracing_readme_fops);
@@ -6367,6 +6567,9 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("saved_cmdlines", 0444, d_tracer,
 			NULL, &tracing_saved_cmdlines_fops);
 
+	trace_create_file("saved_cmdlines_size", 0644, d_tracer,
+			  NULL, &tracing_saved_cmdlines_size_fops);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
@@ -6603,18 +6806,19 @@ __init static int tracer_alloc_buffers(void)
 	if (!temp_buffer)
 		goto out_free_cpumask;
 
+	if (trace_create_savedcmd() < 0)
+		goto out_free_temp_buffer;
+
 	/* TODO: make the number of buffers hot pluggable with CPUS */
 	if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
-		goto out_free_temp_buffer;
+		goto out_free_savedcmd;
 	}
 
 	if (global_trace.buffer_disabled)
 		tracing_off();
 
-	trace_init_cmdlines();
-
 	if (trace_boot_clock) {
 		ret = tracing_set_clock(&global_trace, trace_boot_clock);
 		if (ret < 0)
@@ -6629,6 +6833,10 @@ __init static int tracer_alloc_buffers(void)
 	 */
 	global_trace.current_trace = &nop_trace;
 
+	global_trace.max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+
+	ftrace_init_global_array_ops(&global_trace);
+
 	register_tracer(&nop_trace);
 
 	/* All seems OK, enable tracing */
@@ -6656,13 +6864,11 @@ __init static int tracer_alloc_buffers(void)
 
 	return 0;
 
+out_free_savedcmd:
+	free_saved_cmdlines_buffer(savedcmd);
 out_free_temp_buffer:
 	ring_buffer_free(temp_buffer);
 out_free_cpumask:
-	free_percpu(global_trace.trace_buffer.data);
-#ifdef CONFIG_TRACER_MAX_TRACE
-	free_percpu(global_trace.max_buffer.data);
-#endif
 	free_cpumask_var(global_trace.tracing_cpumask);
 out_free_buffer_mask:
 	free_cpumask_var(tracing_buffer_mask);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 2e29d7ba5a5..385391fb1d3 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -190,7 +190,22 @@ struct trace_array {
 	 */
 	struct trace_buffer	max_buffer;
 	bool			allocated_snapshot;
+	unsigned long		max_latency;
 #endif
+	/*
+	 * max_lock is used to protect the swapping of buffers
+	 * when taking a max snapshot. The buffers themselves are
+	 * protected by per_cpu spinlocks. But the action of the swap
+	 * needs its own lock.
+	 *
+	 * This is defined as a arch_spinlock_t in order to help
+	 * with performance when lockdep debugging is enabled.
+	 *
+	 * It is also used in other places outside the update_max_tr
+	 * so it needs to be defined outside of the
+	 * CONFIG_TRACER_MAX_TRACE.
+	 */
+	arch_spinlock_t		max_lock;
 	int			buffer_disabled;
 #ifdef CONFIG_FTRACE_SYSCALLS
 	int			sys_refcount_enter;
@@ -237,6 +252,9 @@ static inline struct trace_array *top_trace_array(void)
 {
 	struct trace_array *tr;
 
+	if (list_empty(&ftrace_trace_arrays))
+		return NULL;
+
 	tr = list_entry(ftrace_trace_arrays.prev,
 			typeof(*tr), list);
 	WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL));
@@ -321,9 +339,9 @@ struct tracer_flags {
  * @reset: called when one switches to another tracer
  * @start: called when tracing is unpaused (echo 1 > tracing_enabled)
  * @stop: called when tracing is paused (echo 0 > tracing_enabled)
+ * @update_thresh: called when tracing_thresh is updated
  * @open: called when the trace file is opened
  * @pipe_open: called when the trace_pipe file is opened
- * @wait_pipe: override how the user waits for traces on trace_pipe
  * @close: called when the trace file is released
  * @pipe_close: called when the trace_pipe file is released
  * @read: override the default read callback on trace_pipe
@@ -340,9 +358,9 @@ struct tracer {
 	void			(*reset)(struct trace_array *tr);
 	void			(*start)(struct trace_array *tr);
 	void			(*stop)(struct trace_array *tr);
+	int			(*update_thresh)(struct trace_array *tr);
 	void			(*open)(struct trace_iterator *iter);
 	void			(*pipe_open)(struct trace_iterator *iter);
-	void			(*wait_pipe)(struct trace_iterator *iter);
 	void			(*close)(struct trace_iterator *iter);
 	void			(*pipe_close)(struct trace_iterator *iter);
 	ssize_t			(*read)(struct trace_iterator *iter,
@@ -416,13 +434,7 @@ enum {
 	TRACE_FTRACE_IRQ_BIT,
 	TRACE_FTRACE_SIRQ_BIT,
 
-	/* GLOBAL_BITs must be greater than FTRACE_BITs */
-	TRACE_GLOBAL_BIT,
-	TRACE_GLOBAL_NMI_BIT,
-	TRACE_GLOBAL_IRQ_BIT,
-	TRACE_GLOBAL_SIRQ_BIT,
-
-	/* INTERNAL_BITs must be greater than GLOBAL_BITs */
+	/* INTERNAL_BITs must be greater than FTRACE_BITs */
 	TRACE_INTERNAL_BIT,
 	TRACE_INTERNAL_NMI_BIT,
 	TRACE_INTERNAL_IRQ_BIT,
@@ -449,9 +461,6 @@ enum {
 #define TRACE_FTRACE_START	TRACE_FTRACE_BIT
 #define TRACE_FTRACE_MAX	((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)
 
-#define TRACE_GLOBAL_START	TRACE_GLOBAL_BIT
-#define TRACE_GLOBAL_MAX	((1 << (TRACE_GLOBAL_START + TRACE_CONTEXT_BITS)) - 1)
-
 #define TRACE_LIST_START	TRACE_INTERNAL_BIT
 #define TRACE_LIST_MAX		((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
 
@@ -560,8 +569,6 @@ void trace_init_global_iter(struct trace_iterator *iter);
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu);
 
-void poll_wait_pipe(struct trace_iterator *iter);
-
 void tracing_sched_switch_trace(struct trace_array *tr,
 				struct task_struct *prev,
 				struct task_struct *next,
@@ -608,8 +615,6 @@ extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 extern unsigned long tracing_thresh;
 
 #ifdef CONFIG_TRACER_MAX_TRACE
-extern unsigned long tracing_max_latency;
-
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
@@ -724,6 +729,8 @@ extern unsigned long trace_flags;
 #define TRACE_GRAPH_PRINT_PROC          0x8
 #define TRACE_GRAPH_PRINT_DURATION      0x10
 #define TRACE_GRAPH_PRINT_ABS_TIME      0x20
+#define TRACE_GRAPH_PRINT_IRQS          0x40
+#define TRACE_GRAPH_PRINT_TAIL          0x80
 #define TRACE_GRAPH_PRINT_FILL_SHIFT	28
 #define TRACE_GRAPH_PRINT_FILL_MASK	(0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT)
 
@@ -823,6 +830,10 @@ extern int ftrace_is_dead(void);
 int ftrace_create_function_files(struct trace_array *tr,
 				 struct dentry *parent);
 void ftrace_destroy_function_files(struct trace_array *tr);
+void ftrace_init_global_array_ops(struct trace_array *tr);
+void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func);
+void ftrace_reset_array_ops(struct trace_array *tr);
+int using_ftrace_ops_list_func(void);
 #else
 static inline int ftrace_trace_task(struct task_struct *task)
 {
@@ -836,6 +847,11 @@ ftrace_create_function_files(struct trace_array *tr,
 	return 0;
 }
 static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
+static inline __init void
+ftrace_init_global_array_ops(struct trace_array *tr) { }
+static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
+/* ftace_func_t type is not defined, use macro instead of static inline */
+#define ftrace_init_array_ops(tr, func) do { } while (0)
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c
new file mode 100644
index 00000000000..40a14cbcf8e
--- /dev/null
+++ b/kernel/trace/trace_benchmark.c
@@ -0,0 +1,198 @@
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/trace_clock.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace_benchmark.h"
+
+static struct task_struct *bm_event_thread;
+
+static char bm_str[BENCHMARK_EVENT_STRLEN] = "START";
+
+static u64 bm_total;
+static u64 bm_totalsq;
+static u64 bm_last;
+static u64 bm_max;
+static u64 bm_min;
+static u64 bm_first;
+static u64 bm_cnt;
+static u64 bm_stddev;
+static unsigned int bm_avg;
+static unsigned int bm_std;
+
+/*
+ * This gets called in a loop recording the time it took to write
+ * the tracepoint. What it writes is the time statistics of the last
+ * tracepoint write. As there is nothing to write the first time
+ * it simply writes "START". As the first write is cold cache and
+ * the rest is hot, we save off that time in bm_first and it is
+ * reported as "first", which is shown in the second write to the
+ * tracepoint. The "first" field is writen within the statics from
+ * then on but never changes.
+ */
+static void trace_do_benchmark(void)
+{
+	u64 start;
+	u64 stop;
+	u64 delta;
+	u64 stddev;
+	u64 seed;
+	u64 last_seed;
+	unsigned int avg;
+	unsigned int std = 0;
+
+	/* Only run if the tracepoint is actually active */
+	if (!trace_benchmark_event_enabled())
+		return;
+
+	local_irq_disable();
+	start = trace_clock_local();
+	trace_benchmark_event(bm_str);
+	stop = trace_clock_local();
+	local_irq_enable();
+
+	bm_cnt++;
+
+	delta = stop - start;
+
+	/*
+	 * The first read is cold cached, keep it separate from the
+	 * other calculations.
+	 */
+	if (bm_cnt == 1) {
+		bm_first = delta;
+		scnprintf(bm_str, BENCHMARK_EVENT_STRLEN,
+			  "first=%llu [COLD CACHED]", bm_first);
+		return;
+	}
+
+	bm_last = delta;
+
+	if (delta > bm_max)
+		bm_max = delta;
+	if (!bm_min || delta < bm_min)
+		bm_min = delta;
+
+	/*
+	 * When bm_cnt is greater than UINT_MAX, it breaks the statistics
+	 * accounting. Freeze the statistics when that happens.
+	 * We should have enough data for the avg and stddev anyway.
+	 */
+	if (bm_cnt > UINT_MAX) {
+		scnprintf(bm_str, BENCHMARK_EVENT_STRLEN,
+		    "last=%llu first=%llu max=%llu min=%llu ** avg=%u std=%d std^2=%lld",
+			  bm_last, bm_first, bm_max, bm_min, bm_avg, bm_std, bm_stddev);
+		return;
+	}
+
+	bm_total += delta;
+	bm_totalsq += delta * delta;
+
+
+	if (bm_cnt > 1) {
+		/*
+		 * Apply Welford's method to calculate standard deviation:
+		 * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
+		 */
+		stddev = (u64)bm_cnt * bm_totalsq - bm_total * bm_total;
+		do_div(stddev, (u32)bm_cnt);
+		do_div(stddev, (u32)bm_cnt - 1);
+	} else
+		stddev = 0;
+
+	delta = bm_total;
+	do_div(delta, bm_cnt);
+	avg = delta;
+
+	if (stddev > 0) {
+		int i = 0;
+		/*
+		 * stddev is the square of standard deviation but
+		 * we want the actualy number. Use the average
+		 * as our seed to find the std.
+		 *
+		 * The next try is:
+		 *  x = (x + N/x) / 2
+		 *
+		 * Where N is the squared number to find the square
+		 * root of.
+		 */
+		seed = avg;
+		do {
+			last_seed = seed;
+			seed = stddev;
+			if (!last_seed)
+				break;
+			do_div(seed, last_seed);
+			seed += last_seed;
+			do_div(seed, 2);
+		} while (i++ < 10 && last_seed != seed);
+
+		std = seed;
+	}
+
+	scnprintf(bm_str, BENCHMARK_EVENT_STRLEN,
+		  "last=%llu first=%llu max=%llu min=%llu avg=%u std=%d std^2=%lld",
+		  bm_last, bm_first, bm_max, bm_min, avg, std, stddev);
+
+	bm_std = std;
+	bm_avg = avg;
+	bm_stddev = stddev;
+}
+
+static int benchmark_event_kthread(void *arg)
+{
+	/* sleep a bit to make sure the tracepoint gets activated */
+	msleep(100);
+
+	while (!kthread_should_stop()) {
+
+		trace_do_benchmark();
+
+		/*
+		 * We don't go to sleep, but let others
+		 * run as well.
+		 */
+		cond_resched();
+	}
+
+	return 0;
+}
+
+/*
+ * When the benchmark tracepoint is enabled, it calls this
+ * function and the thread that calls the tracepoint is created.
+ */
+void trace_benchmark_reg(void)
+{
+	bm_event_thread = kthread_run(benchmark_event_kthread,
+				      NULL, "event_benchmark");
+	WARN_ON(!bm_event_thread);
+}
+
+/*
+ * When the benchmark tracepoint is disabled, it calls this
+ * function and the thread that calls the tracepoint is deleted
+ * and all the numbers are reset.
+ */
+void trace_benchmark_unreg(void)
+{
+	if (!bm_event_thread)
+		return;
+
+	kthread_stop(bm_event_thread);
+
+	strcpy(bm_str, "START");
+	bm_total = 0;
+	bm_totalsq = 0;
+	bm_last = 0;
+	bm_max = 0;
+	bm_min = 0;
+	bm_cnt = 0;
+	/* These don't need to be reset but reset them anyway */
+	bm_first = 0;
+	bm_std = 0;
+	bm_avg = 0;
+	bm_stddev = 0;
+}
diff --git a/kernel/trace/trace_benchmark.h b/kernel/trace/trace_benchmark.h
new file mode 100644
index 00000000000..3c1df1df4e2
--- /dev/null
+++ b/kernel/trace/trace_benchmark.h
@@ -0,0 +1,41 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM benchmark
+
+#if !defined(_TRACE_BENCHMARK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BENCHMARK_H
+
+#include <linux/tracepoint.h>
+
+extern void trace_benchmark_reg(void);
+extern void trace_benchmark_unreg(void);
+
+#define BENCHMARK_EVENT_STRLEN		128
+
+TRACE_EVENT_FN(benchmark_event,
+
+	TP_PROTO(const char *str),
+
+	TP_ARGS(str),
+
+	TP_STRUCT__entry(
+		__array(	char,	str,	BENCHMARK_EVENT_STRLEN	)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->str, str, BENCHMARK_EVENT_STRLEN);
+	),
+
+	TP_printk("%s", __entry->str),
+
+	trace_benchmark_reg, trace_benchmark_unreg
+);
+
+#endif /* _TRACE_BENCHMARK_H */
+
+#undef TRACE_INCLUDE_FILE
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_benchmark
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 26dc348332b..57b67b1f24d 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -59,13 +59,14 @@ u64 notrace trace_clock(void)
 
 /*
  * trace_jiffy_clock(): Simply use jiffies as a clock counter.
+ * Note that this use of jiffies_64 is not completely safe on
+ * 32-bit systems. But the window is tiny, and the effect if
+ * we are affected is that we will have an obviously bogus
+ * timestamp on a trace event - i.e. not life threatening.
  */
 u64 notrace trace_clock_jiffies(void)
 {
-	u64 jiffy = jiffies - INITIAL_JIFFIES;
-
-	/* Return nsecs */
-	return (u64)jiffies_to_usecs(jiffy) * 1000ULL;
+	return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES);
 }
 
 /*
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index c894614de14..4b9c114ee9d 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -30,6 +30,18 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
 			return ret;
 	}
 
+	/*
+	 * We checked and allowed to create parent,
+	 * allow children without checking.
+	 */
+	if (p_event->parent)
+		return 0;
+
+	/*
+	 * It's ok to check current process (owner) permissions in here,
+	 * because code below is called only via perf_event_open syscall.
+	 */
+
 	/* The ftrace function trace is allowed only for root. */
 	if (ftrace_event_is_function(tp_event)) {
 		if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
@@ -248,8 +260,8 @@ void perf_trace_del(struct perf_event *p_event, int flags)
 	tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
 }
 
-__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
-				       struct pt_regs *regs, int *rctxp)
+void *perf_trace_buf_prepare(int size, unsigned short type,
+			     struct pt_regs *regs, int *rctxp)
 {
 	struct trace_entry *entry;
 	unsigned long flags;
@@ -281,6 +293,7 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	return raw_data;
 }
 EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
+NOKPROBE_SYMBOL(perf_trace_buf_prepare);
 
 #ifdef CONFIG_FUNCTION_TRACER
 static void
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 3ddfd8f62c0..ef06ce7e9cf 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -8,6 +8,8 @@
  *
  */
 
+#define pr_fmt(fmt) fmt
+
 #include <linux/workqueue.h>
 #include <linux/spinlock.h>
 #include <linux/kthread.h>
@@ -470,6 +472,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file)
 
 	list_del(&file->list);
 	remove_subsystem(file->system);
+	free_event_filter(file->filter);
 	kmem_cache_free(file_cachep, file);
 }
 
@@ -574,6 +577,9 @@ int trace_set_clr_event(const char *system, const char *event, int set)
 {
 	struct trace_array *tr = top_trace_array();
 
+	if (!tr)
+		return -ENODEV;
+
 	return __ftrace_set_clr_event(tr, NULL, system, event, set);
 }
 EXPORT_SYMBOL_GPL(trace_set_clr_event);
@@ -1487,7 +1493,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 
 	dir->entry = debugfs_create_dir(name, parent);
 	if (!dir->entry) {
-		pr_warning("Failed to create system directory %s\n", name);
+		pr_warn("Failed to create system directory %s\n", name);
 		__put_system(system);
 		goto out_free;
 	}
@@ -1503,7 +1509,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
 	if (!entry) {
 		kfree(system->filter);
 		system->filter = NULL;
-		pr_warning("Could not create debugfs '%s/filter' entry\n", name);
+		pr_warn("Could not create debugfs '%s/filter' entry\n", name);
 	}
 
 	trace_create_file("enable", 0644, dir->entry, dir,
@@ -1518,8 +1524,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
  out_fail:
 	/* Only print this message if failed on memory allocation */
 	if (!dir || !system)
-		pr_warning("No memory to create event subsystem %s\n",
-			   name);
+		pr_warn("No memory to create event subsystem %s\n", name);
 	return NULL;
 }
 
@@ -1547,8 +1552,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
 	name = ftrace_event_name(call);
 	file->dir = debugfs_create_dir(name, d_events);
 	if (!file->dir) {
-		pr_warning("Could not create debugfs '%s' directory\n",
-			   name);
+		pr_warn("Could not create debugfs '%s' directory\n", name);
 		return -1;
 	}
 
@@ -1571,8 +1575,8 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
 	if (list_empty(head)) {
 		ret = call->class->define_fields(call);
 		if (ret < 0) {
-			pr_warning("Could not initialize trace point"
-				   " events/%s\n", name);
+			pr_warn("Could not initialize trace point events/%s\n",
+				name);
 			return -1;
 		}
 	}
@@ -1617,7 +1621,6 @@ static void event_remove(struct ftrace_event_call *call)
 		if (file->event_call != call)
 			continue;
 		ftrace_event_enable_disable(file, 0);
-		destroy_preds(file);
 		/*
 		 * The do_for_each_event_file() is
 		 * a double loop. After finding the call for this
@@ -1645,8 +1648,7 @@ static int event_init(struct ftrace_event_call *call)
 	if (call->class->raw_init) {
 		ret = call->class->raw_init(call);
 		if (ret < 0 && ret != -ENOSYS)
-			pr_warn("Could not initialize trace events/%s\n",
-				name);
+			pr_warn("Could not initialize trace events/%s\n", name);
 	}
 
 	return ret;
@@ -1745,7 +1747,8 @@ static void __trace_remove_event_call(struct ftrace_event_call *call)
 {
 	event_remove(call);
 	trace_destroy_fields(call);
-	destroy_call_preds(call);
+	free_event_filter(call->filter);
+	call->filter = NULL;
 }
 
 static int probe_remove_event_call(struct ftrace_event_call *call)
@@ -1891,8 +1894,8 @@ __trace_add_event_dirs(struct trace_array *tr)
 	list_for_each_entry(call, &ftrace_events, list) {
 		ret = __trace_add_new_event(call, tr);
 		if (ret < 0)
-			pr_warning("Could not create directory for event %s\n",
-				   ftrace_event_name(call));
+			pr_warn("Could not create directory for event %s\n",
+				ftrace_event_name(call));
 	}
 }
 
@@ -2065,6 +2068,9 @@ event_enable_func(struct ftrace_hash *hash,
 	bool enable;
 	int ret;
 
+	if (!tr)
+		return -ENODEV;
+
 	/* hash funcs only work with set_ftrace_filter */
 	if (!enabled || !param)
 		return -EINVAL;
@@ -2201,8 +2207,8 @@ __trace_early_add_event_dirs(struct trace_array *tr)
 	list_for_each_entry(file, &tr->events, list) {
 		ret = event_create_dir(tr->event_dir, file);
 		if (ret < 0)
-			pr_warning("Could not create directory for event %s\n",
-				   ftrace_event_name(file->event_call));
+			pr_warn("Could not create directory for event %s\n",
+				ftrace_event_name(file->event_call));
 	}
 }
 
@@ -2225,8 +2231,8 @@ __trace_early_add_events(struct trace_array *tr)
 
 		ret = __trace_early_add_new_event(call, tr);
 		if (ret < 0)
-			pr_warning("Could not create early event %s\n",
-				   ftrace_event_name(call));
+			pr_warn("Could not create early event %s\n",
+				ftrace_event_name(call));
 	}
 }
 
@@ -2273,13 +2279,13 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
 	entry = debugfs_create_file("set_event", 0644, parent,
 				    tr, &ftrace_set_event_fops);
 	if (!entry) {
-		pr_warning("Could not create debugfs 'set_event' entry\n");
+		pr_warn("Could not create debugfs 'set_event' entry\n");
 		return -ENOMEM;
 	}
 
 	d_events = debugfs_create_dir("events", parent);
 	if (!d_events) {
-		pr_warning("Could not create debugfs 'events' directory\n");
+		pr_warn("Could not create debugfs 'events' directory\n");
 		return -ENOMEM;
 	}
 
@@ -2396,6 +2402,9 @@ static __init int event_trace_enable(void)
 	char *token;
 	int ret;
 
+	if (!tr)
+		return -ENODEV;
+
 	for_each_event(iter, __start_ftrace_events, __stop_ftrace_events) {
 
 		call = *iter;
@@ -2442,6 +2451,8 @@ static __init int event_trace_init(void)
 	int ret;
 
 	tr = top_trace_array();
+	if (!tr)
+		return -ENODEV;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -2450,11 +2461,10 @@ static __init int event_trace_init(void)
 	entry = debugfs_create_file("available_events", 0444, d_tracer,
 				    tr, &ftrace_avail_fops);
 	if (!entry)
-		pr_warning("Could not create debugfs "
-			   "'available_events' entry\n");
+		pr_warn("Could not create debugfs 'available_events' entry\n");
 
 	if (trace_define_common_fields())
-		pr_warning("tracing: Failed to allocate common fields");
+		pr_warn("tracing: Failed to allocate common fields");
 
 	ret = early_event_add_tracer(d_tracer, tr);
 	if (ret)
@@ -2463,7 +2473,7 @@ static __init int event_trace_init(void)
 #ifdef CONFIG_MODULES
 	ret = register_module_notifier(&trace_module_nb);
 	if (ret)
-		pr_warning("Failed to register trace events module notifier\n");
+		pr_warn("Failed to register trace events module notifier\n");
 #endif
 	return 0;
 }
@@ -2535,6 +2545,8 @@ static __init void event_trace_self_tests(void)
 	int ret;
 
 	tr = top_trace_array();
+	if (!tr)
+		return;
 
 	pr_info("Running tests on trace events:\n");
 
@@ -2565,7 +2577,7 @@ static __init void event_trace_self_tests(void)
 		 * it and the self test should not be on.
 		 */
 		if (file->flags & FTRACE_EVENT_FL_ENABLED) {
-			pr_warning("Enabled event during self test!\n");
+			pr_warn("Enabled event during self test!\n");
 			WARN_ON_ONCE(1);
 			continue;
 		}
@@ -2593,8 +2605,8 @@ static __init void event_trace_self_tests(void)
 
 		ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1);
 		if (WARN_ON_ONCE(ret)) {
-			pr_warning("error enabling system %s\n",
-				   system->name);
+			pr_warn("error enabling system %s\n",
+				system->name);
 			continue;
 		}
 
@@ -2602,8 +2614,8 @@ static __init void event_trace_self_tests(void)
 
 		ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0);
 		if (WARN_ON_ONCE(ret)) {
-			pr_warning("error disabling system %s\n",
-				   system->name);
+			pr_warn("error disabling system %s\n",
+				system->name);
 			continue;
 		}
 
@@ -2617,7 +2629,7 @@ static __init void event_trace_self_tests(void)
 
 	ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1);
 	if (WARN_ON_ONCE(ret)) {
-		pr_warning("error enabling all events\n");
+		pr_warn("error enabling all events\n");
 		return;
 	}
 
@@ -2626,7 +2638,7 @@ static __init void event_trace_self_tests(void)
 	/* reset sysname */
 	ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0);
 	if (WARN_ON_ONCE(ret)) {
-		pr_warning("error disabling all events\n");
+		pr_warn("error disabling all events\n");
 		return;
 	}
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 8a8631926a0..7a8c1528e14 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -774,17 +774,12 @@ static void __free_preds(struct event_filter *filter)
 	filter->n_preds = 0;
 }
 
-static void call_filter_disable(struct ftrace_event_call *call)
-{
-	call->flags &= ~TRACE_EVENT_FL_FILTERED;
-}
-
 static void filter_disable(struct ftrace_event_file *file)
 {
 	struct ftrace_event_call *call = file->event_call;
 
 	if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
-		call_filter_disable(call);
+		call->flags &= ~TRACE_EVENT_FL_FILTERED;
 	else
 		file->flags &= ~FTRACE_EVENT_FL_FILTERED;
 }
@@ -804,32 +799,6 @@ void free_event_filter(struct event_filter *filter)
 	__free_filter(filter);
 }
 
-void destroy_call_preds(struct ftrace_event_call *call)
-{
-	__free_filter(call->filter);
-	call->filter = NULL;
-}
-
-static void destroy_file_preds(struct ftrace_event_file *file)
-{
-	__free_filter(file->filter);
-	file->filter = NULL;
-}
-
-/*
- * Called when destroying the ftrace_event_file.
- * The file is being freed, so we do not need to worry about
- * the file being currently used. This is for module code removing
- * the tracepoints from within it.
- */
-void destroy_preds(struct ftrace_event_file *file)
-{
-	if (file->event_call->flags & TRACE_EVENT_FL_USE_CALL_FILTER)
-		destroy_call_preds(file->event_call);
-	else
-		destroy_file_preds(file);
-}
-
 static struct event_filter *__alloc_filter(void)
 {
 	struct event_filter *filter;
@@ -873,17 +842,14 @@ static inline void __remove_filter(struct ftrace_event_file *file)
 		remove_filter_string(file->filter);
 }
 
-static void filter_free_subsystem_preds(struct event_subsystem *system,
+static void filter_free_subsystem_preds(struct ftrace_subsystem_dir *dir,
 					struct trace_array *tr)
 {
 	struct ftrace_event_file *file;
-	struct ftrace_event_call *call;
 
 	list_for_each_entry(file, &tr->events, list) {
-		call = file->event_call;
-		if (strcmp(call->class->system, system->name) != 0)
+		if (file->system != dir)
 			continue;
-
 		__remove_filter(file);
 	}
 }
@@ -901,15 +867,13 @@ static inline void __free_subsystem_filter(struct ftrace_event_file *file)
 	}
 }
 
-static void filter_free_subsystem_filters(struct event_subsystem *system,
+static void filter_free_subsystem_filters(struct ftrace_subsystem_dir *dir,
 					  struct trace_array *tr)
 {
 	struct ftrace_event_file *file;
-	struct ftrace_event_call *call;
 
 	list_for_each_entry(file, &tr->events, list) {
-		call = file->event_call;
-		if (strcmp(call->class->system, system->name) != 0)
+		if (file->system != dir)
 			continue;
 		__free_subsystem_filter(file);
 	}
@@ -1582,7 +1546,6 @@ static int fold_pred_tree(struct event_filter *filter,
 static int replace_preds(struct ftrace_event_call *call,
 			 struct event_filter *filter,
 			 struct filter_parse_state *ps,
-			 char *filter_string,
 			 bool dry_run)
 {
 	char *operand1 = NULL, *operand2 = NULL;
@@ -1755,13 +1718,12 @@ struct filter_list {
 	struct event_filter	*filter;
 };
 
-static int replace_system_preds(struct event_subsystem *system,
+static int replace_system_preds(struct ftrace_subsystem_dir *dir,
 				struct trace_array *tr,
 				struct filter_parse_state *ps,
 				char *filter_string)
 {
 	struct ftrace_event_file *file;
-	struct ftrace_event_call *call;
 	struct filter_list *filter_item;
 	struct filter_list *tmp;
 	LIST_HEAD(filter_list);
@@ -1769,15 +1731,14 @@ static int replace_system_preds(struct event_subsystem *system,
 	int err;
 
 	list_for_each_entry(file, &tr->events, list) {
-		call = file->event_call;
-		if (strcmp(call->class->system, system->name) != 0)
+		if (file->system != dir)
 			continue;
 
 		/*
 		 * Try to see if the filter can be applied
 		 *  (filter arg is ignored on dry_run)
 		 */
-		err = replace_preds(call, NULL, ps, filter_string, true);
+		err = replace_preds(file->event_call, NULL, ps, true);
 		if (err)
 			event_set_no_set_filter_flag(file);
 		else
@@ -1787,9 +1748,7 @@ static int replace_system_preds(struct event_subsystem *system,
 	list_for_each_entry(file, &tr->events, list) {
 		struct event_filter *filter;
 
-		call = file->event_call;
-
-		if (strcmp(call->class->system, system->name) != 0)
+		if (file->system != dir)
 			continue;
 
 		if (event_no_set_filter_flag(file))
@@ -1811,7 +1770,7 @@ static int replace_system_preds(struct event_subsystem *system,
 		if (err)
 			goto fail_mem;
 
-		err = replace_preds(call, filter, ps, filter_string, false);
+		err = replace_preds(file->event_call, filter, ps, false);
 		if (err) {
 			filter_disable(file);
 			parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0);
@@ -1933,7 +1892,7 @@ static int create_filter(struct ftrace_event_call *call,
 
 	err = create_filter_start(filter_str, set_str, &ps, &filter);
 	if (!err) {
-		err = replace_preds(call, filter, ps, filter_str, false);
+		err = replace_preds(call, filter, ps, false);
 		if (err && set_str)
 			append_filter_err(ps, filter);
 	}
@@ -1959,7 +1918,7 @@ int create_event_filter(struct ftrace_event_call *call,
  * Identical to create_filter() except that it creates a subsystem filter
  * and always remembers @filter_str.
  */
-static int create_system_filter(struct event_subsystem *system,
+static int create_system_filter(struct ftrace_subsystem_dir *dir,
 				struct trace_array *tr,
 				char *filter_str, struct event_filter **filterp)
 {
@@ -1969,7 +1928,7 @@ static int create_system_filter(struct event_subsystem *system,
 
 	err = create_filter_start(filter_str, true, &ps, &filter);
 	if (!err) {
-		err = replace_system_preds(system, tr, ps, filter_str);
+		err = replace_system_preds(dir, tr, ps, filter_str);
 		if (!err) {
 			/* System filters just show a default message */
 			kfree(filter->filter_string);
@@ -2053,18 +2012,18 @@ int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
 	}
 
 	if (!strcmp(strstrip(filter_string), "0")) {
-		filter_free_subsystem_preds(system, tr);
+		filter_free_subsystem_preds(dir, tr);
 		remove_filter_string(system->filter);
 		filter = system->filter;
 		system->filter = NULL;
 		/* Ensure all filters are no longer used */
 		synchronize_sched();
-		filter_free_subsystem_filters(system, tr);
+		filter_free_subsystem_filters(dir, tr);
 		__free_filter(filter);
 		goto out_unlock;
 	}
 
-	err = create_system_filter(system, tr, filter_string, &filter);
+	err = create_system_filter(dir, tr, filter_string, &filter);
 	if (filter) {
 		/*
 		 * No event actually uses the system filter
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index ffd56351b52..57f0ec962d2 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -26,8 +26,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 static void
 function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 			  struct ftrace_ops *op, struct pt_regs *pt_regs);
-static struct ftrace_ops trace_ops;
-static struct ftrace_ops trace_stack_ops;
 static struct tracer_flags func_flags;
 
 /* Our option */
@@ -83,28 +81,24 @@ void ftrace_destroy_function_files(struct trace_array *tr)
 
 static int function_trace_init(struct trace_array *tr)
 {
-	struct ftrace_ops *ops;
-
-	if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
-		/* There's only one global tr */
-		if (!trace_ops.private) {
-			trace_ops.private = tr;
-			trace_stack_ops.private = tr;
-		}
+	ftrace_func_t func;
 
-		if (func_flags.val & TRACE_FUNC_OPT_STACK)
-			ops = &trace_stack_ops;
-		else
-			ops = &trace_ops;
-		tr->ops = ops;
-	} else if (!tr->ops) {
-		/*
-		 * Instance trace_arrays get their ops allocated
-		 * at instance creation. Unless it failed
-		 * the allocation.
-		 */
+	/*
+	 * Instance trace_arrays get their ops allocated
+	 * at instance creation. Unless it failed
+	 * the allocation.
+	 */
+	if (!tr->ops)
 		return -ENOMEM;
-	}
+
+	/* Currently only the global instance can do stack tracing */
+	if (tr->flags & TRACE_ARRAY_FL_GLOBAL &&
+	    func_flags.val & TRACE_FUNC_OPT_STACK)
+		func = function_stack_trace_call;
+	else
+		func = function_trace_call;
+
+	ftrace_init_array_ops(tr, func);
 
 	tr->trace_buffer.cpu = get_cpu();
 	put_cpu();
@@ -118,6 +112,7 @@ static void function_trace_reset(struct trace_array *tr)
 {
 	tracing_stop_function_trace(tr);
 	tracing_stop_cmdline_record();
+	ftrace_reset_array_ops(tr);
 }
 
 static void function_trace_start(struct trace_array *tr)
@@ -199,18 +194,6 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
 	local_irq_restore(flags);
 }
 
-static struct ftrace_ops trace_ops __read_mostly =
-{
-	.func = function_trace_call,
-	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
-};
-
-static struct ftrace_ops trace_stack_ops __read_mostly =
-{
-	.func = function_stack_trace_call,
-	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
-};
-
 static struct tracer_opt func_opts[] = {
 #ifdef CONFIG_STACKTRACE
 	{ TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) },
@@ -248,10 +231,10 @@ func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 		unregister_ftrace_function(tr->ops);
 
 		if (set) {
-			tr->ops = &trace_stack_ops;
+			tr->ops->func = function_stack_trace_call;
 			register_ftrace_function(tr->ops);
 		} else {
-			tr->ops = &trace_ops;
+			tr->ops->func = function_trace_call;
 			register_ftrace_function(tr->ops);
 		}
 
@@ -269,7 +252,6 @@ static struct tracer function_trace __tracer_data =
 	.init		= function_trace_init,
 	.reset		= function_trace_reset,
 	.start		= function_trace_start,
-	.wait_pipe	= poll_wait_pipe,
 	.flags		= &func_flags,
 	.set_flag	= func_set_flag,
 	.allow_instances = true,
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index deff1120026..f0a0c982cde 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -15,6 +15,33 @@
 #include "trace.h"
 #include "trace_output.h"
 
+static bool kill_ftrace_graph;
+
+/**
+ * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called
+ *
+ * ftrace_graph_stop() is called when a severe error is detected in
+ * the function graph tracing. This function is called by the critical
+ * paths of function graph to keep those paths from doing any more harm.
+ */
+bool ftrace_graph_is_dead(void)
+{
+	return kill_ftrace_graph;
+}
+
+/**
+ * ftrace_graph_stop - set to permanently disable function graph tracincg
+ *
+ * In case of an error int function graph tracing, this is called
+ * to try to keep function graph tracing from causing any more harm.
+ * Usually this is pretty severe and this is called to try to at least
+ * get a warning out to the user.
+ */
+void ftrace_graph_stop(void)
+{
+	kill_ftrace_graph = true;
+}
+
 /* When set, irq functions will be ignored */
 static int ftrace_graph_skip_irqs;
 
@@ -38,15 +65,6 @@ struct fgraph_data {
 
 #define TRACE_GRAPH_INDENT	2
 
-/* Flag options */
-#define TRACE_GRAPH_PRINT_OVERRUN	0x1
-#define TRACE_GRAPH_PRINT_CPU		0x2
-#define TRACE_GRAPH_PRINT_OVERHEAD	0x4
-#define TRACE_GRAPH_PRINT_PROC		0x8
-#define TRACE_GRAPH_PRINT_DURATION	0x10
-#define TRACE_GRAPH_PRINT_ABS_TIME	0x20
-#define TRACE_GRAPH_PRINT_IRQS		0x40
-
 static unsigned int max_depth;
 
 static struct tracer_opt trace_opts[] = {
@@ -64,11 +82,13 @@ static struct tracer_opt trace_opts[] = {
 	{ TRACER_OPT(funcgraph-abstime, TRACE_GRAPH_PRINT_ABS_TIME) },
 	/* Display interrupts */
 	{ TRACER_OPT(funcgraph-irqs, TRACE_GRAPH_PRINT_IRQS) },
+	/* Display function name after trailing } */
+	{ TRACER_OPT(funcgraph-tail, TRACE_GRAPH_PRINT_TAIL) },
 	{ } /* Empty entry */
 };
 
 static struct tracer_flags tracer_flags = {
-	/* Don't display overruns and proc by default */
+	/* Don't display overruns, proc, or tail by default */
 	.val = TRACE_GRAPH_PRINT_CPU | TRACE_GRAPH_PRINT_OVERHEAD |
 	       TRACE_GRAPH_PRINT_DURATION | TRACE_GRAPH_PRINT_IRQS,
 	.opts = trace_opts
@@ -99,6 +119,9 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
 	unsigned long long calltime;
 	int index;
 
+	if (unlikely(ftrace_graph_is_dead()))
+		return -EBUSY;
+
 	if (!current->ret_stack)
 		return -EBUSY;
 
@@ -330,7 +353,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	return ret;
 }
 
-int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
+static int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
 {
 	if (tracing_thresh)
 		return 1;
@@ -419,7 +442,7 @@ void set_graph_array(struct trace_array *tr)
 	smp_mb();
 }
 
-void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
+static void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
 {
 	if (tracing_thresh &&
 	    (trace->rettime - trace->calltime < tracing_thresh))
@@ -452,6 +475,12 @@ static void graph_trace_reset(struct trace_array *tr)
 	unregister_ftrace_graph();
 }
 
+static int graph_trace_update_thresh(struct trace_array *tr)
+{
+	graph_trace_reset(tr);
+	return graph_trace_init(tr);
+}
+
 static int max_bytes_for_cpu;
 
 static enum print_line_t
@@ -1176,9 +1205,10 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 	 * If the return function does not have a matching entry,
 	 * then the entry was lost. Instead of just printing
 	 * the '}' and letting the user guess what function this
-	 * belongs to, write out the function name.
+	 * belongs to, write out the function name. Always do
+	 * that if the funcgraph-tail option is enabled.
 	 */
-	if (func_match) {
+	if (func_match && !(flags & TRACE_GRAPH_PRINT_TAIL)) {
 		ret = trace_seq_puts(s, "}\n");
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
@@ -1405,7 +1435,7 @@ static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
 	seq_printf(s, "               |   |   |   |\n");
 }
 
-void print_graph_headers(struct seq_file *s)
+static void print_graph_headers(struct seq_file *s)
 {
 	print_graph_headers_flags(s, tracer_flags.val);
 }
@@ -1501,11 +1531,11 @@ static struct trace_event graph_trace_ret_event = {
 
 static struct tracer graph_trace __tracer_data = {
 	.name		= "function_graph",
+	.update_thresh	= graph_trace_update_thresh,
 	.open		= graph_trace_open,
 	.pipe_open	= graph_trace_open,
 	.close		= graph_trace_close,
 	.pipe_close	= graph_trace_close,
-	.wait_pipe	= poll_wait_pipe,
 	.init		= graph_trace_init,
 	.reset		= graph_trace_reset,
 	.print_line	= print_graph_function,
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 8ff02cbb892..9bb104f748d 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -151,12 +151,6 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
 
 	atomic_dec(&data->disabled);
 }
-
-static struct ftrace_ops trace_ops __read_mostly =
-{
-	.func = irqsoff_tracer_call,
-	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
-};
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -176,7 +170,7 @@ irqsoff_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 	for_each_possible_cpu(cpu)
 		per_cpu(tracing_cpu, cpu) = 0;
 
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	tracing_reset_online_cpus(&irqsoff_trace->trace_buffer);
 
 	return start_irqsoff_tracer(irqsoff_trace, set);
@@ -303,13 +297,13 @@ static void irqsoff_print_header(struct seq_file *s)
 /*
  * Should this new latency be reported/recorded?
  */
-static int report_latency(cycle_t delta)
+static int report_latency(struct trace_array *tr, cycle_t delta)
 {
 	if (tracing_thresh) {
 		if (delta < tracing_thresh)
 			return 0;
 	} else {
-		if (delta <= tracing_max_latency)
+		if (delta <= tr->max_latency)
 			return 0;
 	}
 	return 1;
@@ -333,13 +327,13 @@ check_critical_timing(struct trace_array *tr,
 
 	pc = preempt_count();
 
-	if (!report_latency(delta))
+	if (!report_latency(tr, delta))
 		goto out;
 
 	raw_spin_lock_irqsave(&max_trace_lock, flags);
 
 	/* check if we are still the max latency */
-	if (!report_latency(delta))
+	if (!report_latency(tr, delta))
 		goto out_unlock;
 
 	__trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
@@ -352,7 +346,7 @@ check_critical_timing(struct trace_array *tr,
 	data->critical_end = parent_ip;
 
 	if (likely(!is_tracing_stopped())) {
-		tracing_max_latency = delta;
+		tr->max_latency = delta;
 		update_max_tr_single(tr, current, cpu);
 	}
 
@@ -531,7 +525,7 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
-static int register_irqsoff_function(int graph, int set)
+static int register_irqsoff_function(struct trace_array *tr, int graph, int set)
 {
 	int ret;
 
@@ -543,7 +537,7 @@ static int register_irqsoff_function(int graph, int set)
 		ret = register_ftrace_graph(&irqsoff_graph_return,
 					    &irqsoff_graph_entry);
 	else
-		ret = register_ftrace_function(&trace_ops);
+		ret = register_ftrace_function(tr->ops);
 
 	if (!ret)
 		function_enabled = true;
@@ -551,7 +545,7 @@ static int register_irqsoff_function(int graph, int set)
 	return ret;
 }
 
-static void unregister_irqsoff_function(int graph)
+static void unregister_irqsoff_function(struct trace_array *tr, int graph)
 {
 	if (!function_enabled)
 		return;
@@ -559,17 +553,17 @@ static void unregister_irqsoff_function(int graph)
 	if (graph)
 		unregister_ftrace_graph();
 	else
-		unregister_ftrace_function(&trace_ops);
+		unregister_ftrace_function(tr->ops);
 
 	function_enabled = false;
 }
 
-static void irqsoff_function_set(int set)
+static void irqsoff_function_set(struct trace_array *tr, int set)
 {
 	if (set)
-		register_irqsoff_function(is_graph(), 1);
+		register_irqsoff_function(tr, is_graph(), 1);
 	else
-		unregister_irqsoff_function(is_graph());
+		unregister_irqsoff_function(tr, is_graph());
 }
 
 static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set)
@@ -577,7 +571,7 @@ static int irqsoff_flag_changed(struct trace_array *tr, u32 mask, int set)
 	struct tracer *tracer = tr->current_trace;
 
 	if (mask & TRACE_ITER_FUNCTION)
-		irqsoff_function_set(set);
+		irqsoff_function_set(tr, set);
 
 	return trace_keep_overwrite(tracer, mask, set);
 }
@@ -586,7 +580,7 @@ static int start_irqsoff_tracer(struct trace_array *tr, int graph)
 {
 	int ret;
 
-	ret = register_irqsoff_function(graph, 0);
+	ret = register_irqsoff_function(tr, graph, 0);
 
 	if (!ret && tracing_is_enabled())
 		tracer_enabled = 1;
@@ -600,25 +594,37 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph)
 {
 	tracer_enabled = 0;
 
-	unregister_irqsoff_function(graph);
+	unregister_irqsoff_function(tr, graph);
 }
 
-static void __irqsoff_tracer_init(struct trace_array *tr)
+static bool irqsoff_busy;
+
+static int __irqsoff_tracer_init(struct trace_array *tr)
 {
+	if (irqsoff_busy)
+		return -EBUSY;
+
 	save_flags = trace_flags;
 
 	/* non overwrite screws up the latency tracers */
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
 
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
 	tracing_reset_online_cpus(&tr->trace_buffer);
 
-	if (start_irqsoff_tracer(tr, is_graph()))
+	ftrace_init_array_ops(tr, irqsoff_tracer_call);
+
+	/* Only toplevel instance supports graph tracing */
+	if (start_irqsoff_tracer(tr, (tr->flags & TRACE_ARRAY_FL_GLOBAL &&
+				      is_graph())))
 		printk(KERN_ERR "failed to start irqsoff tracer\n");
+
+	irqsoff_busy = true;
+	return 0;
 }
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
@@ -630,6 +636,9 @@ static void irqsoff_tracer_reset(struct trace_array *tr)
 
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
+	ftrace_reset_array_ops(tr);
+
+	irqsoff_busy = false;
 }
 
 static void irqsoff_tracer_start(struct trace_array *tr)
@@ -647,8 +656,7 @@ static int irqsoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_IRQS_OFF;
 
-	__irqsoff_tracer_init(tr);
-	return 0;
+	return __irqsoff_tracer_init(tr);
 }
 static struct tracer irqsoff_tracer __read_mostly =
 {
@@ -668,6 +676,7 @@ static struct tracer irqsoff_tracer __read_mostly =
 #endif
 	.open           = irqsoff_trace_open,
 	.close          = irqsoff_trace_close,
+	.allow_instances = true,
 	.use_max_tr	= true,
 };
 # define register_irqsoff(trace) register_tracer(&trace)
@@ -680,8 +689,7 @@ static int preemptoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_PREEMPT_OFF;
 
-	__irqsoff_tracer_init(tr);
-	return 0;
+	return __irqsoff_tracer_init(tr);
 }
 
 static struct tracer preemptoff_tracer __read_mostly =
@@ -702,6 +710,7 @@ static struct tracer preemptoff_tracer __read_mostly =
 #endif
 	.open		= irqsoff_trace_open,
 	.close		= irqsoff_trace_close,
+	.allow_instances = true,
 	.use_max_tr	= true,
 };
 # define register_preemptoff(trace) register_tracer(&trace)
@@ -716,8 +725,7 @@ static int preemptirqsoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF;
 
-	__irqsoff_tracer_init(tr);
-	return 0;
+	return __irqsoff_tracer_init(tr);
 }
 
 static struct tracer preemptirqsoff_tracer __read_mostly =
@@ -738,6 +746,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 #endif
 	.open		= irqsoff_trace_open,
 	.close		= irqsoff_trace_close,
+	.allow_instances = true,
 	.use_max_tr	= true,
 };
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 903ae28962b..282f6e4e553 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -40,27 +40,27 @@ struct trace_kprobe {
 	(sizeof(struct probe_arg) * (n)))
 
 
-static __kprobes bool trace_kprobe_is_return(struct trace_kprobe *tk)
+static nokprobe_inline bool trace_kprobe_is_return(struct trace_kprobe *tk)
 {
 	return tk->rp.handler != NULL;
 }
 
-static __kprobes const char *trace_kprobe_symbol(struct trace_kprobe *tk)
+static nokprobe_inline const char *trace_kprobe_symbol(struct trace_kprobe *tk)
 {
 	return tk->symbol ? tk->symbol : "unknown";
 }
 
-static __kprobes unsigned long trace_kprobe_offset(struct trace_kprobe *tk)
+static nokprobe_inline unsigned long trace_kprobe_offset(struct trace_kprobe *tk)
 {
 	return tk->rp.kp.offset;
 }
 
-static __kprobes bool trace_kprobe_has_gone(struct trace_kprobe *tk)
+static nokprobe_inline bool trace_kprobe_has_gone(struct trace_kprobe *tk)
 {
 	return !!(kprobe_gone(&tk->rp.kp));
 }
 
-static __kprobes bool trace_kprobe_within_module(struct trace_kprobe *tk,
+static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk,
 						 struct module *mod)
 {
 	int len = strlen(mod->name);
@@ -68,7 +68,7 @@ static __kprobes bool trace_kprobe_within_module(struct trace_kprobe *tk,
 	return strncmp(mod->name, name, len) == 0 && name[len] == ':';
 }
 
-static __kprobes bool trace_kprobe_is_on_module(struct trace_kprobe *tk)
+static nokprobe_inline bool trace_kprobe_is_on_module(struct trace_kprobe *tk)
 {
 	return !!strchr(trace_kprobe_symbol(tk), ':');
 }
@@ -132,19 +132,21 @@ struct symbol_cache *alloc_symbol_cache(const char *sym, long offset)
  * Kprobes-specific fetch functions
  */
 #define DEFINE_FETCH_stack(type)					\
-static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
+static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,		\
 					  void *offset, void *dest)	\
 {									\
 	*(type *)dest = (type)regs_get_kernel_stack_nth(regs,		\
 				(unsigned int)((unsigned long)offset));	\
-}
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(stack, type));
+
 DEFINE_BASIC_FETCH_FUNCS(stack)
 /* No string on the stack entry */
 #define fetch_stack_string	NULL
 #define fetch_stack_string_size	NULL
 
 #define DEFINE_FETCH_memory(type)					\
-static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
+static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,		\
 					  void *addr, void *dest)	\
 {									\
 	type retval;							\
@@ -152,14 +154,16 @@ static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
 		*(type *)dest = 0;					\
 	else								\
 		*(type *)dest = retval;					\
-}
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, type));
+
 DEFINE_BASIC_FETCH_FUNCS(memory)
 /*
  * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
  * length and relative data location.
  */
-static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
-						      void *addr, void *dest)
+static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+					    void *addr, void *dest)
 {
 	long ret;
 	int maxlen = get_rloc_len(*(u32 *)dest);
@@ -193,10 +197,11 @@ static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
 					      get_rloc_offs(*(u32 *)dest));
 	}
 }
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string));
 
 /* Return the length of string -- including null terminal byte */
-static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
-							void *addr, void *dest)
+static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+						 void *addr, void *dest)
 {
 	mm_segment_t old_fs;
 	int ret, len = 0;
@@ -219,17 +224,19 @@ static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
 	else
 		*(u32 *)dest = len;
 }
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(memory, string_size));
 
 #define DEFINE_FETCH_symbol(type)					\
-__kprobes void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs,	\
-					  void *data, void *dest)	\
+void FETCH_FUNC_NAME(symbol, type)(struct pt_regs *regs, void *data, void *dest)\
 {									\
 	struct symbol_cache *sc = data;					\
 	if (sc->addr)							\
 		fetch_memory_##type(regs, (void *)sc->addr, dest);	\
 	else								\
 		*(type *)dest = 0;					\
-}
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(symbol, type));
+
 DEFINE_BASIC_FETCH_FUNCS(symbol)
 DEFINE_FETCH_symbol(string)
 DEFINE_FETCH_symbol(string_size)
@@ -907,7 +914,7 @@ static const struct file_operations kprobe_profile_ops = {
 };
 
 /* Kprobe handler */
-static __kprobes void
+static nokprobe_inline void
 __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
 		    struct ftrace_event_file *ftrace_file)
 {
@@ -943,7 +950,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
 					 entry, irq_flags, pc, regs);
 }
 
-static __kprobes void
+static void
 kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
 	struct event_file_link *link;
@@ -951,9 +958,10 @@ kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	list_for_each_entry_rcu(link, &tk->tp.files, list)
 		__kprobe_trace_func(tk, regs, link->file);
 }
+NOKPROBE_SYMBOL(kprobe_trace_func);
 
 /* Kretprobe handler */
-static __kprobes void
+static nokprobe_inline void
 __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		       struct pt_regs *regs,
 		       struct ftrace_event_file *ftrace_file)
@@ -991,7 +999,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 					 entry, irq_flags, pc, regs);
 }
 
-static __kprobes void
+static void
 kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		     struct pt_regs *regs)
 {
@@ -1000,6 +1008,7 @@ kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	list_for_each_entry_rcu(link, &tk->tp.files, list)
 		__kretprobe_trace_func(tk, ri, regs, link->file);
 }
+NOKPROBE_SYMBOL(kretprobe_trace_func);
 
 /* Event entry printers */
 static enum print_line_t
@@ -1131,7 +1140,7 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
 #ifdef CONFIG_PERF_EVENTS
 
 /* Kprobe profile handler */
-static __kprobes void
+static void
 kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 {
 	struct ftrace_event_call *call = &tk->tp.call;
@@ -1158,9 +1167,10 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
 }
+NOKPROBE_SYMBOL(kprobe_perf_func);
 
 /* Kretprobe profile handler */
-static __kprobes void
+static void
 kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		    struct pt_regs *regs)
 {
@@ -1188,6 +1198,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize);
 	perf_trace_buf_submit(entry, size, rctx, 0, 1, regs, head, NULL);
 }
+NOKPROBE_SYMBOL(kretprobe_perf_func);
 #endif	/* CONFIG_PERF_EVENTS */
 
 /*
@@ -1196,9 +1207,8 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
  * kprobe_trace_self_tests_init() does enable_trace_probe/disable_trace_probe
  * lockless, but we can't race with this __init function.
  */
-static __kprobes
-int kprobe_register(struct ftrace_event_call *event,
-		    enum trace_reg type, void *data)
+static int kprobe_register(struct ftrace_event_call *event,
+			   enum trace_reg type, void *data)
 {
 	struct trace_kprobe *tk = (struct trace_kprobe *)event->data;
 	struct ftrace_event_file *file = data;
@@ -1224,8 +1234,7 @@ int kprobe_register(struct ftrace_event_call *event,
 	return 0;
 }
 
-static __kprobes
-int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
+static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 {
 	struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp);
 
@@ -1239,9 +1248,10 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 #endif
 	return 0;	/* We don't tweek kernel, so just return 0 */
 }
+NOKPROBE_SYMBOL(kprobe_dispatcher);
 
-static __kprobes
-int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
+static int
+kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 {
 	struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp);
 
@@ -1255,6 +1265,7 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 #endif
 	return 0;	/* We don't tweek kernel, so just return 0 */
 }
+NOKPROBE_SYMBOL(kretprobe_dispatcher);
 
 static struct trace_event_functions kretprobe_funcs = {
 	.trace		= print_kretprobe_event
@@ -1377,6 +1388,9 @@ static __init int kprobe_trace_self_tests_init(void)
 	struct trace_kprobe *tk;
 	struct ftrace_event_file *file;
 
+	if (tracing_is_disabled())
+		return -ENODEV;
+
 	target = kprobe_trace_selftest_target;
 
 	pr_info("Testing kprobe tracing: ");
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 69a5cc94c01..fcf0a9e4891 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -91,7 +91,6 @@ struct tracer nop_trace __read_mostly =
 	.name		= "nop",
 	.init		= nop_trace_init,
 	.reset		= nop_trace_reset,
-	.wait_pipe	= poll_wait_pipe,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_nop,
 #endif
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index a436de18aa9..c6977d5a9b1 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -20,23 +20,6 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
 static int next_event_type = __TRACE_LAST_TYPE + 1;
 
-int trace_print_seq(struct seq_file *m, struct trace_seq *s)
-{
-	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
-	int ret;
-
-	ret = seq_write(m, s->buffer, len);
-
-	/*
-	 * Only reset this buffer if we successfully wrote to the
-	 * seq_file buffer.
-	 */
-	if (!ret)
-		trace_seq_init(s);
-
-	return ret;
-}
-
 enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter)
 {
 	struct trace_seq *s = &iter->seq;
@@ -85,229 +68,6 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter)
 	return TRACE_TYPE_HANDLED;
 }
 
-/**
- * trace_seq_printf - sequence printing of trace information
- * @s: trace sequence descriptor
- * @fmt: printf format string
- *
- * It returns 0 if the trace oversizes the buffer's free
- * space, 1 otherwise.
- *
- * The tracer may use either sequence operations or its own
- * copy to user routines. To simplify formating of a trace
- * trace_seq_printf is used to store strings into a special
- * buffer (@s). Then the output may be either used by
- * the sequencer or pulled into another buffer.
- */
-int
-trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
-{
-	int len = (PAGE_SIZE - 1) - s->len;
-	va_list ap;
-	int ret;
-
-	if (s->full || !len)
-		return 0;
-
-	va_start(ap, fmt);
-	ret = vsnprintf(s->buffer + s->len, len, fmt, ap);
-	va_end(ap);
-
-	/* If we can't write it all, don't bother writing anything */
-	if (ret >= len) {
-		s->full = 1;
-		return 0;
-	}
-
-	s->len += ret;
-
-	return 1;
-}
-EXPORT_SYMBOL_GPL(trace_seq_printf);
-
-/**
- * trace_seq_vprintf - sequence printing of trace information
- * @s: trace sequence descriptor
- * @fmt: printf format string
- *
- * The tracer may use either sequence operations or its own
- * copy to user routines. To simplify formating of a trace
- * trace_seq_printf is used to store strings into a special
- * buffer (@s). Then the output may be either used by
- * the sequencer or pulled into another buffer.
- */
-int
-trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
-{
-	int len = (PAGE_SIZE - 1) - s->len;
-	int ret;
-
-	if (s->full || !len)
-		return 0;
-
-	ret = vsnprintf(s->buffer + s->len, len, fmt, args);
-
-	/* If we can't write it all, don't bother writing anything */
-	if (ret >= len) {
-		s->full = 1;
-		return 0;
-	}
-
-	s->len += ret;
-
-	return len;
-}
-EXPORT_SYMBOL_GPL(trace_seq_vprintf);
-
-int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
-{
-	int len = (PAGE_SIZE - 1) - s->len;
-	int ret;
-
-	if (s->full || !len)
-		return 0;
-
-	ret = bstr_printf(s->buffer + s->len, len, fmt, binary);
-
-	/* If we can't write it all, don't bother writing anything */
-	if (ret >= len) {
-		s->full = 1;
-		return 0;
-	}
-
-	s->len += ret;
-
-	return len;
-}
-
-/**
- * trace_seq_puts - trace sequence printing of simple string
- * @s: trace sequence descriptor
- * @str: simple string to record
- *
- * The tracer may use either the sequence operations or its own
- * copy to user routines. This function records a simple string
- * into a special buffer (@s) for later retrieval by a sequencer
- * or other mechanism.
- */
-int trace_seq_puts(struct trace_seq *s, const char *str)
-{
-	int len = strlen(str);
-
-	if (s->full)
-		return 0;
-
-	if (len > ((PAGE_SIZE - 1) - s->len)) {
-		s->full = 1;
-		return 0;
-	}
-
-	memcpy(s->buffer + s->len, str, len);
-	s->len += len;
-
-	return len;
-}
-
-int trace_seq_putc(struct trace_seq *s, unsigned char c)
-{
-	if (s->full)
-		return 0;
-
-	if (s->len >= (PAGE_SIZE - 1)) {
-		s->full = 1;
-		return 0;
-	}
-
-	s->buffer[s->len++] = c;
-
-	return 1;
-}
-EXPORT_SYMBOL(trace_seq_putc);
-
-int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
-{
-	if (s->full)
-		return 0;
-
-	if (len > ((PAGE_SIZE - 1) - s->len)) {
-		s->full = 1;
-		return 0;
-	}
-
-	memcpy(s->buffer + s->len, mem, len);
-	s->len += len;
-
-	return len;
-}
-
-int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len)
-{
-	unsigned char hex[HEX_CHARS];
-	const unsigned char *data = mem;
-	int i, j;
-
-	if (s->full)
-		return 0;
-
-#ifdef __BIG_ENDIAN
-	for (i = 0, j = 0; i < len; i++) {
-#else
-	for (i = len-1, j = 0; i >= 0; i--) {
-#endif
-		hex[j++] = hex_asc_hi(data[i]);
-		hex[j++] = hex_asc_lo(data[i]);
-	}
-	hex[j++] = ' ';
-
-	return trace_seq_putmem(s, hex, j);
-}
-
-void *trace_seq_reserve(struct trace_seq *s, size_t len)
-{
-	void *ret;
-
-	if (s->full)
-		return NULL;
-
-	if (len > ((PAGE_SIZE - 1) - s->len)) {
-		s->full = 1;
-		return NULL;
-	}
-
-	ret = s->buffer + s->len;
-	s->len += len;
-
-	return ret;
-}
-
-int trace_seq_path(struct trace_seq *s, const struct path *path)
-{
-	unsigned char *p;
-
-	if (s->full)
-		return 0;
-
-	if (s->len >= (PAGE_SIZE - 1)) {
-		s->full = 1;
-		return 0;
-	}
-
-	p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
-	if (!IS_ERR(p)) {
-		p = mangle_path(s->buffer + s->len, p, "\n");
-		if (p) {
-			s->len = p - s->buffer;
-			return 1;
-		}
-	} else {
-		s->buffer[s->len++] = '?';
-		return 1;
-	}
-
-	s->full = 1;
-	return 0;
-}
-
 const char *
 ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
 		       unsigned long flags,
@@ -315,7 +75,7 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
 {
 	unsigned long mask;
 	const char *str;
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 	int i, first = 1;
 
 	for (i = 0;  flag_array[i].name && flags; i++) {
@@ -351,7 +111,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 			 const struct trace_print_flags *symbol_array)
 {
 	int i;
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 
 	for (i = 0;  symbol_array[i].name; i++) {
 
@@ -362,7 +122,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 		break;
 	}
 
-	if (ret == (const char *)(p->buffer + p->len))
+	if (ret == (const char *)(trace_seq_buffer_ptr(p)))
 		trace_seq_printf(p, "0x%lx", val);
 		
 	trace_seq_putc(p, 0);
@@ -377,7 +137,7 @@ ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
 			 const struct trace_print_flags_u64 *symbol_array)
 {
 	int i;
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 
 	for (i = 0;  symbol_array[i].name; i++) {
 
@@ -388,7 +148,7 @@ ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
 		break;
 	}
 
-	if (ret == (const char *)(p->buffer + p->len))
+	if (ret == (const char *)(trace_seq_buffer_ptr(p)))
 		trace_seq_printf(p, "0x%llx", val);
 
 	trace_seq_putc(p, 0);
@@ -399,10 +159,23 @@ EXPORT_SYMBOL(ftrace_print_symbols_seq_u64);
 #endif
 
 const char *
+ftrace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr,
+			 unsigned int bitmask_size)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+
+	trace_seq_bitmask(p, bitmask_ptr, bitmask_size * 8);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ftrace_print_bitmask_seq);
+
+const char *
 ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
 {
 	int i;
-	const char *ret = p->buffer + p->len;
+	const char *ret = trace_seq_buffer_ptr(p);
 
 	for (i = 0; i < buf_len; i++)
 		trace_seq_printf(p, "%s%2.2x", i == 0 ? "" : " ", buf[i]);
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index 127a9d8c835..80b25b585a7 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -35,9 +35,6 @@ trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
 extern int __unregister_ftrace_event(struct trace_event *event);
 extern struct rw_semaphore trace_event_sem;
 
-#define MAX_MEMHEX_BYTES	8
-#define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)
-
 #define SEQ_PUT_FIELD_RET(s, x)				\
 do {							\
 	if (!trace_seq_putmem(s, &(x), sizeof(x)))	\
@@ -46,7 +43,6 @@ do {							\
 
 #define SEQ_PUT_HEX_FIELD_RET(s, x)			\
 do {							\
-	BUILD_BUG_ON(sizeof(x) > MAX_MEMHEX_BYTES);	\
 	if (!trace_seq_putmem_hex(s, &(x), sizeof(x)))	\
 		return TRACE_TYPE_PARTIAL_LINE;		\
 } while (0)
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 8364a421b4d..d4b9fc22cd2 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -37,13 +37,13 @@ const char *reserved_field_names[] = {
 
 /* Printing  in basic type function template */
 #define DEFINE_BASIC_PRINT_TYPE_FUNC(type, fmt)				\
-__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s,	\
-						const char *name,	\
-						void *data, void *ent)	\
+int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name,	\
+				void *data, void *ent)			\
 {									\
 	return trace_seq_printf(s, " %s=" fmt, name, *(type *)data);	\
 }									\
-const char PRINT_TYPE_FMT_NAME(type)[] = fmt;
+const char PRINT_TYPE_FMT_NAME(type)[] = fmt;				\
+NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(type));
 
 DEFINE_BASIC_PRINT_TYPE_FUNC(u8 , "0x%x")
 DEFINE_BASIC_PRINT_TYPE_FUNC(u16, "0x%x")
@@ -55,9 +55,8 @@ DEFINE_BASIC_PRINT_TYPE_FUNC(s32, "%d")
 DEFINE_BASIC_PRINT_TYPE_FUNC(s64, "%Ld")
 
 /* Print type function for string type */
-__kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
-						  const char *name,
-						  void *data, void *ent)
+int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, const char *name,
+				 void *data, void *ent)
 {
 	int len = *(u32 *)data >> 16;
 
@@ -67,6 +66,7 @@ __kprobes int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s,
 		return trace_seq_printf(s, " %s=\"%s\"", name,
 					(const char *)get_loc_data(data, ent));
 }
+NOKPROBE_SYMBOL(PRINT_TYPE_FUNC_NAME(string));
 
 const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
 
@@ -81,23 +81,24 @@ const char PRINT_TYPE_FMT_NAME(string)[] = "\\\"%s\\\"";
 
 /* Data fetch function templates */
 #define DEFINE_FETCH_reg(type)						\
-__kprobes void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs,		\
-					void *offset, void *dest)	\
+void FETCH_FUNC_NAME(reg, type)(struct pt_regs *regs, void *offset, void *dest)	\
 {									\
 	*(type *)dest = (type)regs_get_register(regs,			\
 				(unsigned int)((unsigned long)offset));	\
-}
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(reg, type));
 DEFINE_BASIC_FETCH_FUNCS(reg)
 /* No string on the register */
 #define fetch_reg_string	NULL
 #define fetch_reg_string_size	NULL
 
 #define DEFINE_FETCH_retval(type)					\
-__kprobes void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,	\
-					  void *dummy, void *dest)	\
+void FETCH_FUNC_NAME(retval, type)(struct pt_regs *regs,		\
+				   void *dummy, void *dest)		\
 {									\
 	*(type *)dest = (type)regs_return_value(regs);			\
-}
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(retval, type));
 DEFINE_BASIC_FETCH_FUNCS(retval)
 /* No string on the retval */
 #define fetch_retval_string		NULL
@@ -112,8 +113,8 @@ struct deref_fetch_param {
 };
 
 #define DEFINE_FETCH_deref(type)					\
-__kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,	\
-					    void *data, void *dest)	\
+void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,			\
+				  void *data, void *dest)		\
 {									\
 	struct deref_fetch_param *dprm = data;				\
 	unsigned long addr;						\
@@ -123,12 +124,13 @@ __kprobes void FETCH_FUNC_NAME(deref, type)(struct pt_regs *regs,	\
 		dprm->fetch(regs, (void *)addr, dest);			\
 	} else								\
 		*(type *)dest = 0;					\
-}
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, type));
 DEFINE_BASIC_FETCH_FUNCS(deref)
 DEFINE_FETCH_deref(string)
 
-__kprobes void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs,
-						   void *data, void *dest)
+void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs,
+					 void *data, void *dest)
 {
 	struct deref_fetch_param *dprm = data;
 	unsigned long addr;
@@ -140,16 +142,18 @@ __kprobes void FETCH_FUNC_NAME(deref, string_size)(struct pt_regs *regs,
 	} else
 		*(string_size *)dest = 0;
 }
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(deref, string_size));
 
-static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
+static void update_deref_fetch_param(struct deref_fetch_param *data)
 {
 	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
 		update_deref_fetch_param(data->orig.data);
 	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
 		update_symbol_cache(data->orig.data);
 }
+NOKPROBE_SYMBOL(update_deref_fetch_param);
 
-static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
+static void free_deref_fetch_param(struct deref_fetch_param *data)
 {
 	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
 		free_deref_fetch_param(data->orig.data);
@@ -157,6 +161,7 @@ static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 		free_symbol_cache(data->orig.data);
 	kfree(data);
 }
+NOKPROBE_SYMBOL(free_deref_fetch_param);
 
 /* Bitfield fetch function */
 struct bitfield_fetch_param {
@@ -166,8 +171,8 @@ struct bitfield_fetch_param {
 };
 
 #define DEFINE_FETCH_bitfield(type)					\
-__kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,	\
-					    void *data, void *dest)	\
+void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,		\
+				     void *data, void *dest)		\
 {									\
 	struct bitfield_fetch_param *bprm = data;			\
 	type buf = 0;							\
@@ -177,13 +182,13 @@ __kprobes void FETCH_FUNC_NAME(bitfield, type)(struct pt_regs *regs,	\
 		buf >>= bprm->low_shift;				\
 	}								\
 	*(type *)dest = buf;						\
-}
-
+}									\
+NOKPROBE_SYMBOL(FETCH_FUNC_NAME(bitfield, type));
 DEFINE_BASIC_FETCH_FUNCS(bitfield)
 #define fetch_bitfield_string		NULL
 #define fetch_bitfield_string_size	NULL
 
-static __kprobes void
+static void
 update_bitfield_fetch_param(struct bitfield_fetch_param *data)
 {
 	/*
@@ -196,7 +201,7 @@ update_bitfield_fetch_param(struct bitfield_fetch_param *data)
 		update_symbol_cache(data->orig.data);
 }
 
-static __kprobes void
+static void
 free_bitfield_fetch_param(struct bitfield_fetch_param *data)
 {
 	/*
@@ -255,17 +260,17 @@ fail:
 }
 
 /* Special function : only accept unsigned long */
-static __kprobes void fetch_kernel_stack_address(struct pt_regs *regs,
-						 void *dummy, void *dest)
+static void fetch_kernel_stack_address(struct pt_regs *regs, void *dummy, void *dest)
 {
 	*(unsigned long *)dest = kernel_stack_pointer(regs);
 }
+NOKPROBE_SYMBOL(fetch_kernel_stack_address);
 
-static __kprobes void fetch_user_stack_address(struct pt_regs *regs,
-					       void *dummy, void *dest)
+static void fetch_user_stack_address(struct pt_regs *regs, void *dummy, void *dest)
 {
 	*(unsigned long *)dest = user_stack_pointer(regs);
 }
+NOKPROBE_SYMBOL(fetch_user_stack_address);
 
 static fetch_func_t get_fetch_size_function(const struct fetch_type *type,
 					    fetch_func_t orig_fn,
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index fb1ab5dfbd4..4f815fbce16 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -81,13 +81,13 @@
  */
 #define convert_rloc_to_loc(dl, offs)	((u32)(dl) + (offs))
 
-static inline void *get_rloc_data(u32 *dl)
+static nokprobe_inline void *get_rloc_data(u32 *dl)
 {
 	return (u8 *)dl + get_rloc_offs(*dl);
 }
 
 /* For data_loc conversion */
-static inline void *get_loc_data(u32 *dl, void *ent)
+static nokprobe_inline void *get_loc_data(u32 *dl, void *ent)
 {
 	return (u8 *)ent + get_rloc_offs(*dl);
 }
@@ -136,9 +136,8 @@ typedef u32 string_size;
 
 /* Printing  in basic type function template */
 #define DECLARE_BASIC_PRINT_TYPE_FUNC(type)				\
-__kprobes int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s,		\
-					 const char *name,		\
-					 void *data, void *ent);	\
+int PRINT_TYPE_FUNC_NAME(type)(struct trace_seq *s, const char *name,	\
+				void *data, void *ent);			\
 extern const char PRINT_TYPE_FMT_NAME(type)[]
 
 DECLARE_BASIC_PRINT_TYPE_FUNC(u8);
@@ -303,7 +302,7 @@ static inline bool trace_probe_is_registered(struct trace_probe *tp)
 	return !!(tp->flags & TP_FLAG_REGISTERED);
 }
 
-static inline __kprobes void call_fetch(struct fetch_param *fprm,
+static nokprobe_inline void call_fetch(struct fetch_param *fprm,
 				 struct pt_regs *regs, void *dest)
 {
 	return fprm->fn(regs, fprm->data, dest);
@@ -351,7 +350,7 @@ extern ssize_t traceprobe_probes_write(struct file *file,
 extern int traceprobe_command(const char *buf, int (*createfn)(int, char**));
 
 /* Sum up total data length for dynamic arraies (strings) */
-static inline __kprobes int
+static nokprobe_inline int
 __get_data_size(struct trace_probe *tp, struct pt_regs *regs)
 {
 	int i, ret = 0;
@@ -367,7 +366,7 @@ __get_data_size(struct trace_probe *tp, struct pt_regs *regs)
 }
 
 /* Store the value of each argument */
-static inline __kprobes void
+static nokprobe_inline void
 store_trace_args(int ent_size, struct trace_probe *tp, struct pt_regs *regs,
 		 u8 *data, int maxlen)
 {
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index e14da5e97a6..19bd8928ce9 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -130,15 +130,9 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
 	atomic_dec(&data->disabled);
 	preempt_enable_notrace();
 }
-
-static struct ftrace_ops trace_ops __read_mostly =
-{
-	.func = wakeup_tracer_call,
-	.flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
-};
 #endif /* CONFIG_FUNCTION_TRACER */
 
-static int register_wakeup_function(int graph, int set)
+static int register_wakeup_function(struct trace_array *tr, int graph, int set)
 {
 	int ret;
 
@@ -150,7 +144,7 @@ static int register_wakeup_function(int graph, int set)
 		ret = register_ftrace_graph(&wakeup_graph_return,
 					    &wakeup_graph_entry);
 	else
-		ret = register_ftrace_function(&trace_ops);
+		ret = register_ftrace_function(tr->ops);
 
 	if (!ret)
 		function_enabled = true;
@@ -158,7 +152,7 @@ static int register_wakeup_function(int graph, int set)
 	return ret;
 }
 
-static void unregister_wakeup_function(int graph)
+static void unregister_wakeup_function(struct trace_array *tr, int graph)
 {
 	if (!function_enabled)
 		return;
@@ -166,17 +160,17 @@ static void unregister_wakeup_function(int graph)
 	if (graph)
 		unregister_ftrace_graph();
 	else
-		unregister_ftrace_function(&trace_ops);
+		unregister_ftrace_function(tr->ops);
 
 	function_enabled = false;
 }
 
-static void wakeup_function_set(int set)
+static void wakeup_function_set(struct trace_array *tr, int set)
 {
 	if (set)
-		register_wakeup_function(is_graph(), 1);
+		register_wakeup_function(tr, is_graph(), 1);
 	else
-		unregister_wakeup_function(is_graph());
+		unregister_wakeup_function(tr, is_graph());
 }
 
 static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set)
@@ -184,16 +178,16 @@ static int wakeup_flag_changed(struct trace_array *tr, u32 mask, int set)
 	struct tracer *tracer = tr->current_trace;
 
 	if (mask & TRACE_ITER_FUNCTION)
-		wakeup_function_set(set);
+		wakeup_function_set(tr, set);
 
 	return trace_keep_overwrite(tracer, mask, set);
 }
 
-static int start_func_tracer(int graph)
+static int start_func_tracer(struct trace_array *tr, int graph)
 {
 	int ret;
 
-	ret = register_wakeup_function(graph, 0);
+	ret = register_wakeup_function(tr, graph, 0);
 
 	if (!ret && tracing_is_enabled())
 		tracer_enabled = 1;
@@ -203,11 +197,11 @@ static int start_func_tracer(int graph)
 	return ret;
 }
 
-static void stop_func_tracer(int graph)
+static void stop_func_tracer(struct trace_array *tr, int graph)
 {
 	tracer_enabled = 0;
 
-	unregister_wakeup_function(graph);
+	unregister_wakeup_function(tr, graph);
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -221,12 +215,12 @@ wakeup_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 	if (!(is_graph() ^ set))
 		return 0;
 
-	stop_func_tracer(!set);
+	stop_func_tracer(tr, !set);
 
 	wakeup_reset(wakeup_trace);
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 
-	return start_func_tracer(set);
+	return start_func_tracer(tr, set);
 }
 
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
@@ -350,13 +344,13 @@ static void wakeup_print_header(struct seq_file *s)
 /*
  * Should this new latency be reported/recorded?
  */
-static int report_latency(cycle_t delta)
+static int report_latency(struct trace_array *tr, cycle_t delta)
 {
 	if (tracing_thresh) {
 		if (delta < tracing_thresh)
 			return 0;
 	} else {
-		if (delta <= tracing_max_latency)
+		if (delta <= tr->max_latency)
 			return 0;
 	}
 	return 1;
@@ -424,11 +418,11 @@ probe_wakeup_sched_switch(void *ignore,
 	T1 = ftrace_now(cpu);
 	delta = T1-T0;
 
-	if (!report_latency(delta))
+	if (!report_latency(wakeup_trace, delta))
 		goto out_unlock;
 
 	if (likely(!is_tracing_stopped())) {
-		tracing_max_latency = delta;
+		wakeup_trace->max_latency = delta;
 		update_max_tr(wakeup_trace, wakeup_task, wakeup_cpu);
 	}
 
@@ -587,7 +581,7 @@ static void start_wakeup_tracer(struct trace_array *tr)
 	 */
 	smp_wmb();
 
-	if (start_func_tracer(is_graph()))
+	if (start_func_tracer(tr, is_graph()))
 		printk(KERN_ERR "failed to start wakeup tracer\n");
 
 	return;
@@ -600,13 +594,15 @@ fail_deprobe:
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
 	tracer_enabled = 0;
-	stop_func_tracer(is_graph());
+	stop_func_tracer(tr, is_graph());
 	unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
 	unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
 	unregister_trace_sched_wakeup(probe_wakeup, NULL);
 	unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
 }
 
+static bool wakeup_busy;
+
 static int __wakeup_tracer_init(struct trace_array *tr)
 {
 	save_flags = trace_flags;
@@ -615,14 +611,20 @@ static int __wakeup_tracer_init(struct trace_array *tr)
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1);
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1);
 
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	wakeup_trace = tr;
+	ftrace_init_array_ops(tr, wakeup_tracer_call);
 	start_wakeup_tracer(tr);
+
+	wakeup_busy = true;
 	return 0;
 }
 
 static int wakeup_tracer_init(struct trace_array *tr)
 {
+	if (wakeup_busy)
+		return -EBUSY;
+
 	wakeup_dl = 0;
 	wakeup_rt = 0;
 	return __wakeup_tracer_init(tr);
@@ -630,6 +632,9 @@ static int wakeup_tracer_init(struct trace_array *tr)
 
 static int wakeup_rt_tracer_init(struct trace_array *tr)
 {
+	if (wakeup_busy)
+		return -EBUSY;
+
 	wakeup_dl = 0;
 	wakeup_rt = 1;
 	return __wakeup_tracer_init(tr);
@@ -637,6 +642,9 @@ static int wakeup_rt_tracer_init(struct trace_array *tr)
 
 static int wakeup_dl_tracer_init(struct trace_array *tr)
 {
+	if (wakeup_busy)
+		return -EBUSY;
+
 	wakeup_dl = 1;
 	wakeup_rt = 0;
 	return __wakeup_tracer_init(tr);
@@ -653,6 +661,8 @@ static void wakeup_tracer_reset(struct trace_array *tr)
 
 	set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag);
 	set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag);
+	ftrace_reset_array_ops(tr);
+	wakeup_busy = false;
 }
 
 static void wakeup_tracer_start(struct trace_array *tr)
@@ -684,6 +694,7 @@ static struct tracer wakeup_tracer __read_mostly =
 #endif
 	.open		= wakeup_trace_open,
 	.close		= wakeup_trace_close,
+	.allow_instances = true,
 	.use_max_tr	= true,
 };
 
@@ -694,7 +705,6 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.reset		= wakeup_tracer_reset,
 	.start		= wakeup_tracer_start,
 	.stop		= wakeup_tracer_stop,
-	.wait_pipe	= poll_wait_pipe,
 	.print_max	= true,
 	.print_header	= wakeup_print_header,
 	.print_line	= wakeup_print_line,
@@ -706,6 +716,7 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 #endif
 	.open		= wakeup_trace_open,
 	.close		= wakeup_trace_close,
+	.allow_instances = true,
 	.use_max_tr	= true,
 };
 
@@ -716,7 +727,6 @@ static struct tracer wakeup_dl_tracer __read_mostly =
 	.reset		= wakeup_tracer_reset,
 	.start		= wakeup_tracer_start,
 	.stop		= wakeup_tracer_stop,
-	.wait_pipe	= poll_wait_pipe,
 	.print_max	= true,
 	.print_header	= wakeup_print_header,
 	.print_line	= wakeup_print_line,
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index e98fca60974..5ef60499dc8 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -65,7 +65,7 @@ static int trace_test_buffer(struct trace_buffer *buf, unsigned long *count)
 
 	/* Don't allow flipping of max traces now */
 	local_irq_save(flags);
-	arch_spin_lock(&ftrace_max_lock);
+	arch_spin_lock(&buf->tr->max_lock);
 
 	cnt = ring_buffer_entries(buf->buffer);
 
@@ -83,7 +83,7 @@ static int trace_test_buffer(struct trace_buffer *buf, unsigned long *count)
 			break;
 	}
 	tracing_on();
-	arch_spin_unlock(&ftrace_max_lock);
+	arch_spin_unlock(&buf->tr->max_lock);
 	local_irq_restore(flags);
 
 	if (count)
@@ -161,11 +161,6 @@ static struct ftrace_ops test_probe3 = {
 	.flags			= FTRACE_OPS_FL_RECURSION_SAFE,
 };
 
-static struct ftrace_ops test_global = {
-	.func		= trace_selftest_test_global_func,
-	.flags		= FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
-};
-
 static void print_counts(void)
 {
 	printk("(%d %d %d %d %d) ",
@@ -185,7 +180,7 @@ static void reset_counts(void)
 	trace_selftest_test_dyn_cnt = 0;
 }
 
-static int trace_selftest_ops(int cnt)
+static int trace_selftest_ops(struct trace_array *tr, int cnt)
 {
 	int save_ftrace_enabled = ftrace_enabled;
 	struct ftrace_ops *dyn_ops;
@@ -220,7 +215,11 @@ static int trace_selftest_ops(int cnt)
 	register_ftrace_function(&test_probe1);
 	register_ftrace_function(&test_probe2);
 	register_ftrace_function(&test_probe3);
-	register_ftrace_function(&test_global);
+	/* First time we are running with main function */
+	if (cnt > 1) {
+		ftrace_init_array_ops(tr, trace_selftest_test_global_func);
+		register_ftrace_function(tr->ops);
+	}
 
 	DYN_FTRACE_TEST_NAME();
 
@@ -232,8 +231,10 @@ static int trace_selftest_ops(int cnt)
 		goto out;
 	if (trace_selftest_test_probe3_cnt != 1)
 		goto out;
-	if (trace_selftest_test_global_cnt == 0)
-		goto out;
+	if (cnt > 1) {
+		if (trace_selftest_test_global_cnt == 0)
+			goto out;
+	}
 
 	DYN_FTRACE_TEST_NAME2();
 
@@ -269,8 +270,10 @@ static int trace_selftest_ops(int cnt)
 		goto out_free;
 	if (trace_selftest_test_probe3_cnt != 3)
 		goto out_free;
-	if (trace_selftest_test_global_cnt == 0)
-		goto out;
+	if (cnt > 1) {
+		if (trace_selftest_test_global_cnt == 0)
+			goto out;
+	}
 	if (trace_selftest_test_dyn_cnt == 0)
 		goto out_free;
 
@@ -295,7 +298,9 @@ static int trace_selftest_ops(int cnt)
 	unregister_ftrace_function(&test_probe1);
 	unregister_ftrace_function(&test_probe2);
 	unregister_ftrace_function(&test_probe3);
-	unregister_ftrace_function(&test_global);
+	if (cnt > 1)
+		unregister_ftrace_function(tr->ops);
+	ftrace_reset_array_ops(tr);
 
 	/* Make sure everything is off */
 	reset_counts();
@@ -315,9 +320,9 @@ static int trace_selftest_ops(int cnt)
 }
 
 /* Test dynamic code modification and ftrace filters */
-int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
-					   struct trace_array *tr,
-					   int (*func)(void))
+static int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
+						  struct trace_array *tr,
+						  int (*func)(void))
 {
 	int save_ftrace_enabled = ftrace_enabled;
 	unsigned long count;
@@ -388,7 +393,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	}
 
 	/* Test the ops with global tracing running */
-	ret = trace_selftest_ops(1);
+	ret = trace_selftest_ops(tr, 1);
 	trace->reset(tr);
 
  out:
@@ -399,7 +404,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 
 	/* Test the ops with global tracing off */
 	if (!ret)
-		ret = trace_selftest_ops(2);
+		ret = trace_selftest_ops(tr, 2);
 
 	return ret;
 }
@@ -802,7 +807,7 @@ out:
 int
 trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 {
-	unsigned long save_max = tracing_max_latency;
+	unsigned long save_max = tr->max_latency;
 	unsigned long count;
 	int ret;
 
@@ -814,7 +819,7 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 	}
 
 	/* reset the max latency */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	/* disable interrupts for a bit */
 	local_irq_disable();
 	udelay(100);
@@ -841,7 +846,7 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 		ret = -1;
 	}
 
-	tracing_max_latency = save_max;
+	tr->max_latency = save_max;
 
 	return ret;
 }
@@ -851,7 +856,7 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 int
 trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 {
-	unsigned long save_max = tracing_max_latency;
+	unsigned long save_max = tr->max_latency;
 	unsigned long count;
 	int ret;
 
@@ -876,7 +881,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	}
 
 	/* reset the max latency */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	/* disable preemption for a bit */
 	preempt_disable();
 	udelay(100);
@@ -903,7 +908,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 		ret = -1;
 	}
 
-	tracing_max_latency = save_max;
+	tr->max_latency = save_max;
 
 	return ret;
 }
@@ -913,7 +918,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 int
 trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *tr)
 {
-	unsigned long save_max = tracing_max_latency;
+	unsigned long save_max = tr->max_latency;
 	unsigned long count;
 	int ret;
 
@@ -938,7 +943,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	}
 
 	/* reset the max latency */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 
 	/* disable preemption and interrupts for a bit */
 	preempt_disable();
@@ -973,7 +978,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	}
 
 	/* do the test by disabling interrupts first this time */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 	tracing_start();
 	trace->start(tr);
 
@@ -1004,7 +1009,7 @@ out:
 	tracing_start();
 out_no_start:
 	trace->reset(tr);
-	tracing_max_latency = save_max;
+	tr->max_latency = save_max;
 
 	return ret;
 }
@@ -1057,7 +1062,7 @@ static int trace_wakeup_test_thread(void *data)
 int
 trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 {
-	unsigned long save_max = tracing_max_latency;
+	unsigned long save_max = tr->max_latency;
 	struct task_struct *p;
 	struct completion is_ready;
 	unsigned long count;
@@ -1083,7 +1088,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	}
 
 	/* reset the max latency */
-	tracing_max_latency = 0;
+	tr->max_latency = 0;
 
 	while (p->on_rq) {
 		/*
@@ -1113,7 +1118,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	trace->reset(tr);
 	tracing_start();
 
-	tracing_max_latency = save_max;
+	tr->max_latency = save_max;
 
 	/* kill the thread */
 	kthread_stop(p);
diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c
new file mode 100644
index 00000000000..1f24ed99dca
--- /dev/null
+++ b/kernel/trace/trace_seq.c
@@ -0,0 +1,428 @@
+/*
+ * trace_seq.c
+ *
+ * Copyright (C) 2008-2014 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * The trace_seq is a handy tool that allows you to pass a descriptor around
+ * to a buffer that other functions can write to. It is similar to the
+ * seq_file functionality but has some differences.
+ *
+ * To use it, the trace_seq must be initialized with trace_seq_init().
+ * This will set up the counters within the descriptor. You can call
+ * trace_seq_init() more than once to reset the trace_seq to start
+ * from scratch.
+ * 
+ * The buffer size is currently PAGE_SIZE, although it may become dynamic
+ * in the future.
+ *
+ * A write to the buffer will either succed or fail. That is, unlike
+ * sprintf() there will not be a partial write (well it may write into
+ * the buffer but it wont update the pointers). This allows users to
+ * try to write something into the trace_seq buffer and if it fails
+ * they can flush it and try again.
+ *
+ */
+#include <linux/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/trace_seq.h>
+
+/* How much buffer is left on the trace_seq? */
+#define TRACE_SEQ_BUF_LEFT(s) ((PAGE_SIZE - 1) - (s)->len)
+
+/* How much buffer is written? */
+#define TRACE_SEQ_BUF_USED(s) min((s)->len, (unsigned int)(PAGE_SIZE - 1))
+
+/**
+ * trace_print_seq - move the contents of trace_seq into a seq_file
+ * @m: the seq_file descriptor that is the destination
+ * @s: the trace_seq descriptor that is the source.
+ *
+ * Returns 0 on success and non zero on error. If it succeeds to
+ * write to the seq_file it will reset the trace_seq, otherwise
+ * it does not modify the trace_seq to let the caller try again.
+ */
+int trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+	unsigned int len = TRACE_SEQ_BUF_USED(s);
+	int ret;
+
+	ret = seq_write(m, s->buffer, len);
+
+	/*
+	 * Only reset this buffer if we successfully wrote to the
+	 * seq_file buffer. This lets the caller try again or
+	 * do something else with the contents.
+	 */
+	if (!ret)
+		trace_seq_init(s);
+
+	return ret;
+}
+
+/**
+ * trace_seq_printf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf() is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ *
+ * Returns 1 if we successfully written all the contents to
+ *   the buffer.
+  * Returns 0 if we the length to write is bigger than the
+ *   reserved buffer space. In this case, nothing gets written.
+ */
+int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+{
+	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
+	va_list ap;
+	int ret;
+
+	if (s->full || !len)
+		return 0;
+
+	va_start(ap, fmt);
+	ret = vsnprintf(s->buffer + s->len, len, fmt, ap);
+	va_end(ap);
+
+	/* If we can't write it all, don't bother writing anything */
+	if (ret >= len) {
+		s->full = 1;
+		return 0;
+	}
+
+	s->len += ret;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(trace_seq_printf);
+
+/**
+ * trace_seq_bitmask - write a bitmask array in its ASCII representation
+ * @s:		trace sequence descriptor
+ * @maskp:	points to an array of unsigned longs that represent a bitmask
+ * @nmaskbits:	The number of bits that are valid in @maskp
+ *
+ * Writes a ASCII representation of a bitmask string into @s.
+ *
+ * Returns 1 if we successfully written all the contents to
+ *   the buffer.
+ * Returns 0 if we the length to write is bigger than the
+ *   reserved buffer space. In this case, nothing gets written.
+ */
+int trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp,
+		      int nmaskbits)
+{
+	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
+	int ret;
+
+	if (s->full || !len)
+		return 0;
+
+	ret = bitmap_scnprintf(s->buffer, len, maskp, nmaskbits);
+	s->len += ret;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(trace_seq_bitmask);
+
+/**
+ * trace_seq_vprintf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ *
+ * Returns how much it wrote to the buffer.
+ */
+int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+{
+	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
+	int ret;
+
+	if (s->full || !len)
+		return 0;
+
+	ret = vsnprintf(s->buffer + s->len, len, fmt, args);
+
+	/* If we can't write it all, don't bother writing anything */
+	if (ret >= len) {
+		s->full = 1;
+		return 0;
+	}
+
+	s->len += ret;
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(trace_seq_vprintf);
+
+/**
+ * trace_seq_bprintf - Write the printf string from binary arguments
+ * @s: trace sequence descriptor
+ * @fmt: The format string for the @binary arguments
+ * @binary: The binary arguments for @fmt.
+ *
+ * When recording in a fast path, a printf may be recorded with just
+ * saving the format and the arguments as they were passed to the
+ * function, instead of wasting cycles converting the arguments into
+ * ASCII characters. Instead, the arguments are saved in a 32 bit
+ * word array that is defined by the format string constraints.
+ *
+ * This function will take the format and the binary array and finish
+ * the conversion into the ASCII string within the buffer.
+ *
+ * Returns how much it wrote to the buffer.
+ */
+int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
+{
+	unsigned int len = TRACE_SEQ_BUF_LEFT(s);
+	int ret;
+
+	if (s->full || !len)
+		return 0;
+
+	ret = bstr_printf(s->buffer + s->len, len, fmt, binary);
+
+	/* If we can't write it all, don't bother writing anything */
+	if (ret >= len) {
+		s->full = 1;
+		return 0;
+	}
+
+	s->len += ret;
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(trace_seq_bprintf);
+
+/**
+ * trace_seq_puts - trace sequence printing of simple string
+ * @s: trace sequence descriptor
+ * @str: simple string to record
+ *
+ * The tracer may use either the sequence operations or its own
+ * copy to user routines. This function records a simple string
+ * into a special buffer (@s) for later retrieval by a sequencer
+ * or other mechanism.
+ *
+ * Returns how much it wrote to the buffer.
+ */
+int trace_seq_puts(struct trace_seq *s, const char *str)
+{
+	unsigned int len = strlen(str);
+
+	if (s->full)
+		return 0;
+
+	if (len > TRACE_SEQ_BUF_LEFT(s)) {
+		s->full = 1;
+		return 0;
+	}
+
+	memcpy(s->buffer + s->len, str, len);
+	s->len += len;
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(trace_seq_puts);
+
+/**
+ * trace_seq_putc - trace sequence printing of simple character
+ * @s: trace sequence descriptor
+ * @c: simple character to record
+ *
+ * The tracer may use either the sequence operations or its own
+ * copy to user routines. This function records a simple charater
+ * into a special buffer (@s) for later retrieval by a sequencer
+ * or other mechanism.
+ *
+ * Returns how much it wrote to the buffer.
+ */
+int trace_seq_putc(struct trace_seq *s, unsigned char c)
+{
+	if (s->full)
+		return 0;
+
+	if (TRACE_SEQ_BUF_LEFT(s) < 1) {
+		s->full = 1;
+		return 0;
+	}
+
+	s->buffer[s->len++] = c;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(trace_seq_putc);
+
+/**
+ * trace_seq_putmem - write raw data into the trace_seq buffer
+ * @s: trace sequence descriptor
+ * @mem: The raw memory to copy into the buffer
+ * @len: The length of the raw memory to copy (in bytes)
+ *
+ * There may be cases where raw memory needs to be written into the
+ * buffer and a strcpy() would not work. Using this function allows
+ * for such cases.
+ *
+ * Returns how much it wrote to the buffer.
+ */
+int trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len)
+{
+	if (s->full)
+		return 0;
+
+	if (len > TRACE_SEQ_BUF_LEFT(s)) {
+		s->full = 1;
+		return 0;
+	}
+
+	memcpy(s->buffer + s->len, mem, len);
+	s->len += len;
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(trace_seq_putmem);
+
+#define MAX_MEMHEX_BYTES	8U
+#define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)
+
+/**
+ * trace_seq_putmem_hex - write raw memory into the buffer in ASCII hex
+ * @s: trace sequence descriptor
+ * @mem: The raw memory to write its hex ASCII representation of
+ * @len: The length of the raw memory to copy (in bytes)
+ *
+ * This is similar to trace_seq_putmem() except instead of just copying the
+ * raw memory into the buffer it writes its ASCII representation of it
+ * in hex characters.
+ *
+ * Returns how much it wrote to the buffer.
+ */
+int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+			 unsigned int len)
+{
+	unsigned char hex[HEX_CHARS];
+	const unsigned char *data = mem;
+	unsigned int start_len;
+	int i, j;
+	int cnt = 0;
+
+	if (s->full)
+		return 0;
+
+	while (len) {
+		start_len = min(len, HEX_CHARS - 1);
+#ifdef __BIG_ENDIAN
+		for (i = 0, j = 0; i < start_len; i++) {
+#else
+		for (i = start_len-1, j = 0; i >= 0; i--) {
+#endif
+			hex[j++] = hex_asc_hi(data[i]);
+			hex[j++] = hex_asc_lo(data[i]);
+		}
+		if (WARN_ON_ONCE(j == 0 || j/2 > len))
+			break;
+
+		/* j increments twice per loop */
+		len -= j / 2;
+		hex[j++] = ' ';
+
+		cnt += trace_seq_putmem(s, hex, j);
+	}
+	return cnt;
+}
+EXPORT_SYMBOL_GPL(trace_seq_putmem_hex);
+
+/**
+ * trace_seq_path - copy a path into the sequence buffer
+ * @s: trace sequence descriptor
+ * @path: path to write into the sequence buffer.
+ *
+ * Write a path name into the sequence buffer.
+ *
+ * Returns 1 if we successfully written all the contents to
+ *   the buffer.
+ * Returns 0 if we the length to write is bigger than the
+ *   reserved buffer space. In this case, nothing gets written.
+ */
+int trace_seq_path(struct trace_seq *s, const struct path *path)
+{
+	unsigned char *p;
+
+	if (s->full)
+		return 0;
+
+	if (TRACE_SEQ_BUF_LEFT(s) < 1) {
+		s->full = 1;
+		return 0;
+	}
+
+	p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
+	if (!IS_ERR(p)) {
+		p = mangle_path(s->buffer + s->len, p, "\n");
+		if (p) {
+			s->len = p - s->buffer;
+			return 1;
+		}
+	} else {
+		s->buffer[s->len++] = '?';
+		return 1;
+	}
+
+	s->full = 1;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(trace_seq_path);
+
+/**
+ * trace_seq_to_user - copy the squence buffer to user space
+ * @s: trace sequence descriptor
+ * @ubuf: The userspace memory location to copy to
+ * @cnt: The amount to copy
+ *
+ * Copies the sequence buffer into the userspace memory pointed to
+ * by @ubuf. It starts from the last read position (@s->readpos)
+ * and writes up to @cnt characters or till it reaches the end of
+ * the content in the buffer (@s->len), which ever comes first.
+ *
+ * On success, it returns a positive number of the number of bytes
+ * it copied.
+ *
+ * On failure it returns -EBUSY if all of the content in the
+ * sequence has been already read, which includes nothing in the
+ * sequenc (@s->len == @s->readpos).
+ *
+ * Returns -EFAULT if the copy to userspace fails.
+ */
+int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt)
+{
+	int len;
+	int ret;
+
+	if (!cnt)
+		return 0;
+
+	if (s->len <= s->readpos)
+		return -EBUSY;
+
+	len = s->len - s->readpos;
+	if (cnt > len)
+		cnt = len;
+	ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);
+	if (ret == cnt)
+		return -EFAULT;
+
+	cnt -= ret;
+
+	s->readpos += cnt;
+	return cnt;
+}
+EXPORT_SYMBOL_GPL(trace_seq_to_user);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 21b320e5d16..8a4e5cb66a4 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -51,11 +51,33 @@ static DEFINE_MUTEX(stack_sysctl_mutex);
 int stack_tracer_enabled;
 static int last_stack_tracer_enabled;
 
+static inline void print_max_stack(void)
+{
+	long i;
+	int size;
+
+	pr_emerg("        Depth    Size   Location    (%d entries)\n"
+			   "        -----    ----   --------\n",
+			   max_stack_trace.nr_entries - 1);
+
+	for (i = 0; i < max_stack_trace.nr_entries; i++) {
+		if (stack_dump_trace[i] == ULONG_MAX)
+			break;
+		if (i+1 == max_stack_trace.nr_entries ||
+				stack_dump_trace[i+1] == ULONG_MAX)
+			size = stack_dump_index[i];
+		else
+			size = stack_dump_index[i] - stack_dump_index[i+1];
+
+		pr_emerg("%3ld) %8d   %5d   %pS\n", i, stack_dump_index[i],
+				size, (void *)stack_dump_trace[i]);
+	}
+}
+
 static inline void
 check_stack(unsigned long ip, unsigned long *stack)
 {
-	unsigned long this_size, flags;
-	unsigned long *p, *top, *start;
+	unsigned long this_size, flags; unsigned long *p, *top, *start;
 	static int tracer_frame;
 	int frame_size = ACCESS_ONCE(tracer_frame);
 	int i;
@@ -85,8 +107,12 @@ check_stack(unsigned long ip, unsigned long *stack)
 
 	max_stack_size = this_size;
 
-	max_stack_trace.nr_entries	= 0;
-	max_stack_trace.skip		= 3;
+	max_stack_trace.nr_entries = 0;
+
+	if (using_ftrace_ops_list_func())
+		max_stack_trace.skip = 4;
+	else
+		max_stack_trace.skip = 3;
 
 	save_stack_trace(&max_stack_trace);
 
@@ -145,8 +171,12 @@ check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
-	BUG_ON(current != &init_task &&
-		*(end_of_stack(current)) != STACK_END_MAGIC);
+	if ((current != &init_task &&
+		*(end_of_stack(current)) != STACK_END_MAGIC)) {
+		print_max_stack();
+		BUG();
+	}
+
  out:
 	arch_spin_unlock(&max_stack_lock);
 	local_irq_restore(flags);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c082a744134..33ff6a24b80 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -108,8 +108,8 @@ static unsigned long get_user_stack_nth(struct pt_regs *regs, unsigned int n)
  * Uprobes-specific fetch functions
  */
 #define DEFINE_FETCH_stack(type)					\
-static __kprobes void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,\
-					  void *offset, void *dest)	\
+static void FETCH_FUNC_NAME(stack, type)(struct pt_regs *regs,		\
+					 void *offset, void *dest)	\
 {									\
 	*(type *)dest = (type)get_user_stack_nth(regs,			\
 					      ((unsigned long)offset)); \
@@ -120,8 +120,8 @@ DEFINE_BASIC_FETCH_FUNCS(stack)
 #define fetch_stack_string_size	NULL
 
 #define DEFINE_FETCH_memory(type)					\
-static __kprobes void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,\
-						void *addr, void *dest) \
+static void FETCH_FUNC_NAME(memory, type)(struct pt_regs *regs,		\
+					  void *addr, void *dest)	\
 {									\
 	type retval;							\
 	void __user *vaddr = (void __force __user *) addr;		\
@@ -136,8 +136,8 @@ DEFINE_BASIC_FETCH_FUNCS(memory)
  * Fetch a null-terminated string. Caller MUST set *(u32 *)dest with max
  * length and relative data location.
  */
-static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
-						      void *addr, void *dest)
+static void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
+					    void *addr, void *dest)
 {
 	long ret;
 	u32 rloc = *(u32 *)dest;
@@ -158,8 +158,8 @@ static __kprobes void FETCH_FUNC_NAME(memory, string)(struct pt_regs *regs,
 	}
 }
 
-static __kprobes void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
-						      void *addr, void *dest)
+static void FETCH_FUNC_NAME(memory, string_size)(struct pt_regs *regs,
+						 void *addr, void *dest)
 {
 	int len;
 	void __user *vaddr = (void __force __user *) addr;
@@ -184,8 +184,8 @@ static unsigned long translate_user_vaddr(void *file_offset)
 }
 
 #define DEFINE_FETCH_file_offset(type)					\
-static __kprobes void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs,\
-					void *offset, void *dest) 	\
+static void FETCH_FUNC_NAME(file_offset, type)(struct pt_regs *regs,	\
+					       void *offset, void *dest)\
 {									\
 	void *vaddr = (void *)translate_user_vaddr(offset);		\
 									\
@@ -265,7 +265,6 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret)
 	if (is_ret)
 		tu->consumer.ret_handler = uretprobe_dispatcher;
 	init_trace_uprobe_filter(&tu->filter);
-	tu->tp.call.flags |= TRACE_EVENT_FL_USE_CALL_FILTER;
 	return tu;
 
 error:
@@ -893,6 +892,9 @@ probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file,
 	int ret;
 
 	if (file) {
+		if (tu->tp.flags & TP_FLAG_PROFILE)
+			return -EINTR;
+
 		link = kmalloc(sizeof(*link), GFP_KERNEL);
 		if (!link)
 			return -ENOMEM;
@@ -901,29 +903,40 @@ probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file,
 		list_add_tail_rcu(&link->list, &tu->tp.files);
 
 		tu->tp.flags |= TP_FLAG_TRACE;
-	} else
-		tu->tp.flags |= TP_FLAG_PROFILE;
+	} else {
+		if (tu->tp.flags & TP_FLAG_TRACE)
+			return -EINTR;
 
-	ret = uprobe_buffer_enable();
-	if (ret < 0)
-		return ret;
+		tu->tp.flags |= TP_FLAG_PROFILE;
+	}
 
 	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
 	if (enabled)
 		return 0;
 
+	ret = uprobe_buffer_enable();
+	if (ret)
+		goto err_flags;
+
 	tu->consumer.filter = filter;
 	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
-	if (ret) {
-		if (file) {
-			list_del(&link->list);
-			kfree(link);
-			tu->tp.flags &= ~TP_FLAG_TRACE;
-		} else
-			tu->tp.flags &= ~TP_FLAG_PROFILE;
-	}
+	if (ret)
+		goto err_buffer;
+
+	return 0;
 
+ err_buffer:
+	uprobe_buffer_disable();
+
+ err_flags:
+	if (file) {
+		list_del(&link->list);
+		kfree(link);
+		tu->tp.flags &= ~TP_FLAG_TRACE;
+	} else {
+		tu->tp.flags &= ~TP_FLAG_PROFILE;
+	}
 	return ret;
 }
 
@@ -1009,56 +1022,60 @@ uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
 	return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm);
 }
 
-static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
+static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
 {
 	bool done;
 
 	write_lock(&tu->filter.rwlock);
 	if (event->hw.tp_target) {
-		/*
-		 * event->parent != NULL means copy_process(), we can avoid
-		 * uprobe_apply(). current->mm must be probed and we can rely
-		 * on dup_mmap() which preserves the already installed bp's.
-		 *
-		 * attr.enable_on_exec means that exec/mmap will install the
-		 * breakpoints we need.
-		 */
+		list_del(&event->hw.tp_list);
 		done = tu->filter.nr_systemwide ||
-			event->parent || event->attr.enable_on_exec ||
+			(event->hw.tp_target->flags & PF_EXITING) ||
 			uprobe_filter_event(tu, event);
-		list_add(&event->hw.tp_list, &tu->filter.perf_events);
 	} else {
+		tu->filter.nr_systemwide--;
 		done = tu->filter.nr_systemwide;
-		tu->filter.nr_systemwide++;
 	}
 	write_unlock(&tu->filter.rwlock);
 
 	if (!done)
-		uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+		return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
 
 	return 0;
 }
 
-static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
+static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
 {
 	bool done;
+	int err;
 
 	write_lock(&tu->filter.rwlock);
 	if (event->hw.tp_target) {
-		list_del(&event->hw.tp_list);
+		/*
+		 * event->parent != NULL means copy_process(), we can avoid
+		 * uprobe_apply(). current->mm must be probed and we can rely
+		 * on dup_mmap() which preserves the already installed bp's.
+		 *
+		 * attr.enable_on_exec means that exec/mmap will install the
+		 * breakpoints we need.
+		 */
 		done = tu->filter.nr_systemwide ||
-			(event->hw.tp_target->flags & PF_EXITING) ||
+			event->parent || event->attr.enable_on_exec ||
 			uprobe_filter_event(tu, event);
+		list_add(&event->hw.tp_list, &tu->filter.perf_events);
 	} else {
-		tu->filter.nr_systemwide--;
 		done = tu->filter.nr_systemwide;
+		tu->filter.nr_systemwide++;
 	}
 	write_unlock(&tu->filter.rwlock);
 
-	if (!done)
-		uprobe_apply(tu->inode, tu->offset, &tu->consumer, false);
-
-	return 0;
+	err = 0;
+	if (!done) {
+		err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true);
+		if (err)
+			uprobe_perf_close(tu, event);
+	}
+	return err;
 }
 
 static bool uprobe_perf_filter(struct uprobe_consumer *uc,
@@ -1197,12 +1214,6 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 
 	current->utask->vaddr = (unsigned long) &udd;
 
-#ifdef CONFIG_PERF_EVENTS
-	if ((tu->tp.flags & TP_FLAG_TRACE) == 0 &&
-	    !uprobe_perf_filter(&tu->consumer, 0, current->mm))
-		return UPROBE_HANDLER_REMOVE;
-#endif
-
 	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
 		return 0;
 
@@ -1280,7 +1291,7 @@ static int register_uprobe_event(struct trace_uprobe *tu)
 		kfree(call->print_fmt);
 		return -ENODEV;
 	}
-	call->flags = 0;
+
 	call->class->reg = trace_uprobe_register;
 	call->data = tu;
 	ret = trace_add_event_call(call);
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 33cbd8c203f..3490407dc7b 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -492,33 +492,29 @@ static int sys_tracepoint_refcount;
 
 void syscall_regfunc(void)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	struct task_struct *p, *t;
 
 	if (!sys_tracepoint_refcount) {
-		read_lock_irqsave(&tasklist_lock, flags);
-		do_each_thread(g, t) {
-			/* Skip kernel threads. */
-			if (t->mm)
-				set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
-		} while_each_thread(g, t);
-		read_unlock_irqrestore(&tasklist_lock, flags);
+		read_lock(&tasklist_lock);
+		for_each_process_thread(p, t) {
+			set_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
+		}
+		read_unlock(&tasklist_lock);
 	}
 	sys_tracepoint_refcount++;
 }
 
 void syscall_unregfunc(void)
 {
-	unsigned long flags;
-	struct task_struct *g, *t;
+	struct task_struct *p, *t;
 
 	sys_tracepoint_refcount--;
 	if (!sys_tracepoint_refcount) {
-		read_lock_irqsave(&tasklist_lock, flags);
-		do_each_thread(g, t) {
+		read_lock(&tasklist_lock);
+		for_each_process_thread(p, t) {
 			clear_tsk_thread_flag(t, TIF_SYSCALL_TRACEPOINT);
-		} while_each_thread(g, t);
-		read_unlock_irqrestore(&tasklist_lock, flags);
+		}
+		read_unlock(&tasklist_lock);
 	}
 }
 #endif
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 516203e665f..c3319bd1b04 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -31,6 +31,12 @@
 
 int watchdog_user_enabled = 1;
 int __read_mostly watchdog_thresh = 10;
+#ifdef CONFIG_SMP
+int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+#else
+#define sysctl_softlockup_all_cpu_backtrace 0
+#endif
+
 static int __read_mostly watchdog_running;
 static u64 __read_mostly sample_period;
 
@@ -47,6 +53,7 @@ static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
+static unsigned long soft_lockup_nmi_warn;
 
 /* boot commands */
 /*
@@ -95,6 +102,15 @@ static int __init nosoftlockup_setup(char *str)
 }
 __setup("nosoftlockup", nosoftlockup_setup);
 /*  */
+#ifdef CONFIG_SMP
+static int __init softlockup_all_cpu_backtrace_setup(char *str)
+{
+	sysctl_softlockup_all_cpu_backtrace =
+		!!simple_strtol(str, NULL, 0);
+	return 1;
+}
+__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
+#endif
 
 /*
  * Hard-lockup warnings should be triggered after just a few seconds. Soft-
@@ -271,6 +287,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts);
 	struct pt_regs *regs = get_irq_regs();
 	int duration;
+	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
 
 	/* kick the hardlockup detector */
 	watchdog_interrupt_count();
@@ -317,6 +334,17 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		if (__this_cpu_read(soft_watchdog_warn) == true)
 			return HRTIMER_RESTART;
 
+		if (softlockup_all_cpu_backtrace) {
+			/* Prevent multiple soft-lockup reports if one cpu is already
+			 * engaged in dumping cpu back traces
+			 */
+			if (test_and_set_bit(0, &soft_lockup_nmi_warn)) {
+				/* Someone else will report us. Let's give up */
+				__this_cpu_write(soft_watchdog_warn, true);
+				return HRTIMER_RESTART;
+			}
+		}
+
 		printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
@@ -327,6 +355,17 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		else
 			dump_stack();
 
+		if (softlockup_all_cpu_backtrace) {
+			/* Avoid generating two back traces for current
+			 * given that one is already made above
+			 */
+			trigger_allbutself_cpu_backtrace();
+
+			clear_bit(0, &soft_lockup_nmi_warn);
+			/* Barrier to sync with other cpus */
+			smp_mb__after_atomic();
+		}
+
 		if (softlockup_panic)
 			panic("softlockup: hung tasks");
 		__this_cpu_write(soft_watchdog_warn, true);
@@ -527,10 +566,8 @@ static void update_timers_all_cpus(void)
 	int cpu;
 
 	get_online_cpus();
-	preempt_disable();
 	for_each_online_cpu(cpu)
 		update_timers(cpu);
-	preempt_enable();
 	put_online_cpus();
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index a4bab46cd38..5dbe22aa3ef 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -65,15 +65,12 @@ enum {
 	 * be executing on any CPU.  The pool behaves as an unbound one.
 	 *
 	 * Note that DISASSOCIATED should be flipped only while holding
-	 * manager_mutex to avoid changing binding state while
-	 * create_worker() is in progress.
+	 * attach_mutex to avoid changing binding state while
+	 * worker_attach_to_pool() is in progress.
 	 */
-	POOL_MANAGE_WORKERS	= 1 << 0,	/* need to manage workers */
 	POOL_DISASSOCIATED	= 1 << 2,	/* cpu can't serve workers */
-	POOL_FREEZING		= 1 << 3,	/* freeze in progress */
 
 	/* worker flags */
-	WORKER_STARTED		= 1 << 0,	/* started */
 	WORKER_DIE		= 1 << 1,	/* die die die */
 	WORKER_IDLE		= 1 << 2,	/* is idle */
 	WORKER_PREP		= 1 << 3,	/* preparing to run works */
@@ -124,8 +121,7 @@ enum {
  *    cpu or grabbing pool->lock is enough for read access.  If
  *    POOL_DISASSOCIATED is set, it's identical to L.
  *
- * MG: pool->manager_mutex and pool->lock protected.  Writes require both
- *     locks.  Reads can happen under either lock.
+ * A: pool->attach_mutex protected.
  *
  * PL: wq_pool_mutex protected.
  *
@@ -163,8 +159,11 @@ struct worker_pool {
 
 	/* see manage_workers() for details on the two manager mutexes */
 	struct mutex		manager_arb;	/* manager arbitration */
-	struct mutex		manager_mutex;	/* manager exclusion */
-	struct idr		worker_idr;	/* MG: worker IDs and iteration */
+	struct mutex		attach_mutex;	/* attach/detach exclusion */
+	struct list_head	workers;	/* A: attached workers */
+	struct completion	*detach_completion; /* all workers detached */
+
+	struct ida		worker_ida;	/* worker IDs for task name */
 
 	struct workqueue_attrs	*attrs;		/* I: worker attributes */
 	struct hlist_node	hash_node;	/* PL: unbound_pool_hash node */
@@ -266,7 +265,6 @@ struct workqueue_struct {
 
 static struct kmem_cache *pwq_cache;
 
-static int wq_numa_tbl_len;		/* highest possible NUMA node id + 1 */
 static cpumask_var_t *wq_numa_possible_cpumask;
 					/* possible CPUs of each node */
 
@@ -340,16 +338,6 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to,
 			   lockdep_is_held(&wq->mutex),			\
 			   "sched RCU or wq->mutex should be held")
 
-#ifdef CONFIG_LOCKDEP
-#define assert_manager_or_pool_lock(pool)				\
-	WARN_ONCE(debug_locks &&					\
-		  !lockdep_is_held(&(pool)->manager_mutex) &&		\
-		  !lockdep_is_held(&(pool)->lock),			\
-		  "pool->manager_mutex or ->lock should be held")
-#else
-#define assert_manager_or_pool_lock(pool)	do { } while (0)
-#endif
-
 #define for_each_cpu_worker_pool(pool, cpu)				\
 	for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0];		\
 	     (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \
@@ -375,17 +363,16 @@ static void copy_workqueue_attrs(struct workqueue_attrs *to,
 /**
  * for_each_pool_worker - iterate through all workers of a worker_pool
  * @worker: iteration cursor
- * @wi: integer used for iteration
  * @pool: worker_pool to iterate workers of
  *
- * This must be called with either @pool->manager_mutex or ->lock held.
+ * This must be called with @pool->attach_mutex.
  *
  * The if/else clause exists only for the lockdep assertion and can be
  * ignored.
  */
-#define for_each_pool_worker(worker, wi, pool)				\
-	idr_for_each_entry(&(pool)->worker_idr, (worker), (wi))		\
-		if (({ assert_manager_or_pool_lock((pool)); false; })) { } \
+#define for_each_pool_worker(worker, pool)				\
+	list_for_each_entry((worker), &(pool)->workers, node)		\
+		if (({ lockdep_assert_held(&pool->attach_mutex); false; })) { } \
 		else
 
 /**
@@ -763,13 +750,6 @@ static bool need_to_create_worker(struct worker_pool *pool)
 	return need_more_worker(pool) && !may_start_working(pool);
 }
 
-/* Do I need to be the manager? */
-static bool need_to_manage_workers(struct worker_pool *pool)
-{
-	return need_to_create_worker(pool) ||
-		(pool->flags & POOL_MANAGE_WORKERS);
-}
-
 /* Do we have too many workers and should some go away? */
 static bool too_many_workers(struct worker_pool *pool)
 {
@@ -777,13 +757,6 @@ static bool too_many_workers(struct worker_pool *pool)
 	int nr_idle = pool->nr_idle + managing; /* manager is considered idle */
 	int nr_busy = pool->nr_workers - nr_idle;
 
-	/*
-	 * nr_idle and idle_list may disagree if idle rebinding is in
-	 * progress.  Never return %true if idle_list is empty.
-	 */
-	if (list_empty(&pool->idle_list))
-		return false;
-
 	return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy;
 }
 
@@ -791,8 +764,8 @@ static bool too_many_workers(struct worker_pool *pool)
  * Wake up functions.
  */
 
-/* Return the first worker.  Safe with preemption disabled */
-static struct worker *first_worker(struct worker_pool *pool)
+/* Return the first idle worker.  Safe with preemption disabled */
+static struct worker *first_idle_worker(struct worker_pool *pool)
 {
 	if (unlikely(list_empty(&pool->idle_list)))
 		return NULL;
@@ -811,7 +784,7 @@ static struct worker *first_worker(struct worker_pool *pool)
  */
 static void wake_up_worker(struct worker_pool *pool)
 {
-	struct worker *worker = first_worker(pool);
+	struct worker *worker = first_idle_worker(pool);
 
 	if (likely(worker))
 		wake_up_process(worker->task);
@@ -869,7 +842,7 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu)
 	pool = worker->pool;
 
 	/* this can only happen on the local cpu */
-	if (WARN_ON_ONCE(cpu != raw_smp_processor_id()))
+	if (WARN_ON_ONCE(cpu != raw_smp_processor_id() || pool->cpu != cpu))
 		return NULL;
 
 	/*
@@ -885,7 +858,7 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu)
 	 */
 	if (atomic_dec_and_test(&pool->nr_running) &&
 	    !list_empty(&pool->worklist))
-		to_wakeup = first_worker(pool);
+		to_wakeup = first_idle_worker(pool);
 	return to_wakeup ? to_wakeup->task : NULL;
 }
 
@@ -893,35 +866,22 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task, int cpu)
  * worker_set_flags - set worker flags and adjust nr_running accordingly
  * @worker: self
  * @flags: flags to set
- * @wakeup: wakeup an idle worker if necessary
  *
- * Set @flags in @worker->flags and adjust nr_running accordingly.  If
- * nr_running becomes zero and @wakeup is %true, an idle worker is
- * woken up.
+ * Set @flags in @worker->flags and adjust nr_running accordingly.
  *
  * CONTEXT:
  * spin_lock_irq(pool->lock)
  */
-static inline void worker_set_flags(struct worker *worker, unsigned int flags,
-				    bool wakeup)
+static inline void worker_set_flags(struct worker *worker, unsigned int flags)
 {
 	struct worker_pool *pool = worker->pool;
 
 	WARN_ON_ONCE(worker->task != current);
 
-	/*
-	 * If transitioning into NOT_RUNNING, adjust nr_running and
-	 * wake up an idle worker as necessary if requested by
-	 * @wakeup.
-	 */
+	/* If transitioning into NOT_RUNNING, adjust nr_running. */
 	if ((flags & WORKER_NOT_RUNNING) &&
 	    !(worker->flags & WORKER_NOT_RUNNING)) {
-		if (wakeup) {
-			if (atomic_dec_and_test(&pool->nr_running) &&
-			    !list_empty(&pool->worklist))
-				wake_up_worker(pool);
-		} else
-			atomic_dec(&pool->nr_running);
+		atomic_dec(&pool->nr_running);
 	}
 
 	worker->flags |= flags;
@@ -1251,7 +1211,7 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork,
 			pwq_activate_delayed_work(work);
 
 		list_del_init(&work->entry);
-		pwq_dec_nr_in_flight(get_work_pwq(work), get_work_color(work));
+		pwq_dec_nr_in_flight(pwq, get_work_color(work));
 
 		/* work->data points to pwq iff queued, point to pool */
 		set_work_pool_and_keep_pending(work, pool->id);
@@ -1579,7 +1539,7 @@ static void worker_enter_idle(struct worker *worker)
 			 (worker->hentry.next || worker->hentry.pprev)))
 		return;
 
-	/* can't use worker_set_flags(), also called from start_worker() */
+	/* can't use worker_set_flags(), also called from create_worker() */
 	worker->flags |= WORKER_IDLE;
 	pool->nr_idle++;
 	worker->last_active = jiffies;
@@ -1621,78 +1581,15 @@ static void worker_leave_idle(struct worker *worker)
 	list_del_init(&worker->entry);
 }
 
-/**
- * worker_maybe_bind_and_lock - try to bind %current to worker_pool and lock it
- * @pool: target worker_pool
- *
- * Bind %current to the cpu of @pool if it is associated and lock @pool.
- *
- * Works which are scheduled while the cpu is online must at least be
- * scheduled to a worker which is bound to the cpu so that if they are
- * flushed from cpu callbacks while cpu is going down, they are
- * guaranteed to execute on the cpu.
- *
- * This function is to be used by unbound workers and rescuers to bind
- * themselves to the target cpu and may race with cpu going down or
- * coming online.  kthread_bind() can't be used because it may put the
- * worker to already dead cpu and set_cpus_allowed_ptr() can't be used
- * verbatim as it's best effort and blocking and pool may be
- * [dis]associated in the meantime.
- *
- * This function tries set_cpus_allowed() and locks pool and verifies the
- * binding against %POOL_DISASSOCIATED which is set during
- * %CPU_DOWN_PREPARE and cleared during %CPU_ONLINE, so if the worker
- * enters idle state or fetches works without dropping lock, it can
- * guarantee the scheduling requirement described in the first paragraph.
- *
- * CONTEXT:
- * Might sleep.  Called without any lock but returns with pool->lock
- * held.
- *
- * Return:
- * %true if the associated pool is online (@worker is successfully
- * bound), %false if offline.
- */
-static bool worker_maybe_bind_and_lock(struct worker_pool *pool)
-__acquires(&pool->lock)
-{
-	while (true) {
-		/*
-		 * The following call may fail, succeed or succeed
-		 * without actually migrating the task to the cpu if
-		 * it races with cpu hotunplug operation.  Verify
-		 * against POOL_DISASSOCIATED.
-		 */
-		if (!(pool->flags & POOL_DISASSOCIATED))
-			set_cpus_allowed_ptr(current, pool->attrs->cpumask);
-
-		spin_lock_irq(&pool->lock);
-		if (pool->flags & POOL_DISASSOCIATED)
-			return false;
-		if (task_cpu(current) == pool->cpu &&
-		    cpumask_equal(&current->cpus_allowed, pool->attrs->cpumask))
-			return true;
-		spin_unlock_irq(&pool->lock);
-
-		/*
-		 * We've raced with CPU hot[un]plug.  Give it a breather
-		 * and retry migration.  cond_resched() is required here;
-		 * otherwise, we might deadlock against cpu_stop trying to
-		 * bring down the CPU on non-preemptive kernel.
-		 */
-		cpu_relax();
-		cond_resched();
-	}
-}
-
-static struct worker *alloc_worker(void)
+static struct worker *alloc_worker(int node)
 {
 	struct worker *worker;
 
-	worker = kzalloc(sizeof(*worker), GFP_KERNEL);
+	worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node);
 	if (worker) {
 		INIT_LIST_HEAD(&worker->entry);
 		INIT_LIST_HEAD(&worker->scheduled);
+		INIT_LIST_HEAD(&worker->node);
 		/* on creation a worker is in !idle && prep state */
 		worker->flags = WORKER_PREP;
 	}
@@ -1700,12 +1597,70 @@ static struct worker *alloc_worker(void)
 }
 
 /**
+ * worker_attach_to_pool() - attach a worker to a pool
+ * @worker: worker to be attached
+ * @pool: the target pool
+ *
+ * Attach @worker to @pool.  Once attached, the %WORKER_UNBOUND flag and
+ * cpu-binding of @worker are kept coordinated with the pool across
+ * cpu-[un]hotplugs.
+ */
+static void worker_attach_to_pool(struct worker *worker,
+				   struct worker_pool *pool)
+{
+	mutex_lock(&pool->attach_mutex);
+
+	/*
+	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
+	 * online CPUs.  It'll be re-applied when any of the CPUs come up.
+	 */
+	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
+
+	/*
+	 * The pool->attach_mutex ensures %POOL_DISASSOCIATED remains
+	 * stable across this function.  See the comments above the
+	 * flag definition for details.
+	 */
+	if (pool->flags & POOL_DISASSOCIATED)
+		worker->flags |= WORKER_UNBOUND;
+
+	list_add_tail(&worker->node, &pool->workers);
+
+	mutex_unlock(&pool->attach_mutex);
+}
+
+/**
+ * worker_detach_from_pool() - detach a worker from its pool
+ * @worker: worker which is attached to its pool
+ * @pool: the pool @worker is attached to
+ *
+ * Undo the attaching which had been done in worker_attach_to_pool().  The
+ * caller worker shouldn't access to the pool after detached except it has
+ * other reference to the pool.
+ */
+static void worker_detach_from_pool(struct worker *worker,
+				    struct worker_pool *pool)
+{
+	struct completion *detach_completion = NULL;
+
+	mutex_lock(&pool->attach_mutex);
+	list_del(&worker->node);
+	if (list_empty(&pool->workers))
+		detach_completion = pool->detach_completion;
+	mutex_unlock(&pool->attach_mutex);
+
+	/* clear leftover flags without pool->lock after it is detached */
+	worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND);
+
+	if (detach_completion)
+		complete(detach_completion);
+}
+
+/**
  * create_worker - create a new workqueue worker
  * @pool: pool the new worker will belong to
  *
- * Create a new worker which is bound to @pool.  The returned worker
- * can be started by calling start_worker() or destroyed using
- * destroy_worker().
+ * Create and start a new worker which is attached to @pool.
  *
  * CONTEXT:
  * Might sleep.  Does GFP_KERNEL allocations.
@@ -1719,23 +1674,12 @@ static struct worker *create_worker(struct worker_pool *pool)
 	int id = -1;
 	char id_buf[16];
 
-	lockdep_assert_held(&pool->manager_mutex);
-
-	/*
-	 * ID is needed to determine kthread name.  Allocate ID first
-	 * without installing the pointer.
-	 */
-	idr_preload(GFP_KERNEL);
-	spin_lock_irq(&pool->lock);
-
-	id = idr_alloc(&pool->worker_idr, NULL, 0, 0, GFP_NOWAIT);
-
-	spin_unlock_irq(&pool->lock);
-	idr_preload_end();
+	/* ID is needed to determine kthread name */
+	id = ida_simple_get(&pool->worker_ida, 0, 0, GFP_KERNEL);
 	if (id < 0)
 		goto fail;
 
-	worker = alloc_worker();
+	worker = alloc_worker(pool->node);
 	if (!worker)
 		goto fail;
 
@@ -1758,124 +1702,53 @@ static struct worker *create_worker(struct worker_pool *pool)
 	/* prevent userland from meddling with cpumask of workqueue workers */
 	worker->task->flags |= PF_NO_SETAFFINITY;
 
-	/*
-	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
-	 * online CPUs.  It'll be re-applied when any of the CPUs come up.
-	 */
-	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
+	/* successful, attach the worker to the pool */
+	worker_attach_to_pool(worker, pool);
 
-	/*
-	 * The caller is responsible for ensuring %POOL_DISASSOCIATED
-	 * remains stable across this function.  See the comments above the
-	 * flag definition for details.
-	 */
-	if (pool->flags & POOL_DISASSOCIATED)
-		worker->flags |= WORKER_UNBOUND;
-
-	/* successful, commit the pointer to idr */
+	/* start the newly created worker */
 	spin_lock_irq(&pool->lock);
-	idr_replace(&pool->worker_idr, worker, worker->id);
+	worker->pool->nr_workers++;
+	worker_enter_idle(worker);
+	wake_up_process(worker->task);
 	spin_unlock_irq(&pool->lock);
 
 	return worker;
 
 fail:
-	if (id >= 0) {
-		spin_lock_irq(&pool->lock);
-		idr_remove(&pool->worker_idr, id);
-		spin_unlock_irq(&pool->lock);
-	}
+	if (id >= 0)
+		ida_simple_remove(&pool->worker_ida, id);
 	kfree(worker);
 	return NULL;
 }
 
 /**
- * start_worker - start a newly created worker
- * @worker: worker to start
- *
- * Make the pool aware of @worker and start it.
- *
- * CONTEXT:
- * spin_lock_irq(pool->lock).
- */
-static void start_worker(struct worker *worker)
-{
-	worker->flags |= WORKER_STARTED;
-	worker->pool->nr_workers++;
-	worker_enter_idle(worker);
-	wake_up_process(worker->task);
-}
-
-/**
- * create_and_start_worker - create and start a worker for a pool
- * @pool: the target pool
- *
- * Grab the managership of @pool and create and start a new worker for it.
- *
- * Return: 0 on success. A negative error code otherwise.
- */
-static int create_and_start_worker(struct worker_pool *pool)
-{
-	struct worker *worker;
-
-	mutex_lock(&pool->manager_mutex);
-
-	worker = create_worker(pool);
-	if (worker) {
-		spin_lock_irq(&pool->lock);
-		start_worker(worker);
-		spin_unlock_irq(&pool->lock);
-	}
-
-	mutex_unlock(&pool->manager_mutex);
-
-	return worker ? 0 : -ENOMEM;
-}
-
-/**
  * destroy_worker - destroy a workqueue worker
  * @worker: worker to be destroyed
  *
- * Destroy @worker and adjust @pool stats accordingly.
+ * Destroy @worker and adjust @pool stats accordingly.  The worker should
+ * be idle.
  *
  * CONTEXT:
- * spin_lock_irq(pool->lock) which is released and regrabbed.
+ * spin_lock_irq(pool->lock).
  */
 static void destroy_worker(struct worker *worker)
 {
 	struct worker_pool *pool = worker->pool;
 
-	lockdep_assert_held(&pool->manager_mutex);
 	lockdep_assert_held(&pool->lock);
 
 	/* sanity check frenzy */
 	if (WARN_ON(worker->current_work) ||
-	    WARN_ON(!list_empty(&worker->scheduled)))
+	    WARN_ON(!list_empty(&worker->scheduled)) ||
+	    WARN_ON(!(worker->flags & WORKER_IDLE)))
 		return;
 
-	if (worker->flags & WORKER_STARTED)
-		pool->nr_workers--;
-	if (worker->flags & WORKER_IDLE)
-		pool->nr_idle--;
-
-	/*
-	 * Once WORKER_DIE is set, the kworker may destroy itself at any
-	 * point.  Pin to ensure the task stays until we're done with it.
-	 */
-	get_task_struct(worker->task);
+	pool->nr_workers--;
+	pool->nr_idle--;
 
 	list_del_init(&worker->entry);
 	worker->flags |= WORKER_DIE;
-
-	idr_remove(&pool->worker_idr, worker->id);
-
-	spin_unlock_irq(&pool->lock);
-
-	kthread_stop(worker->task);
-	put_task_struct(worker->task);
-	kfree(worker);
-
-	spin_lock_irq(&pool->lock);
+	wake_up_process(worker->task);
 }
 
 static void idle_worker_timeout(unsigned long __pool)
@@ -1884,7 +1757,7 @@ static void idle_worker_timeout(unsigned long __pool)
 
 	spin_lock_irq(&pool->lock);
 
-	if (too_many_workers(pool)) {
+	while (too_many_workers(pool)) {
 		struct worker *worker;
 		unsigned long expires;
 
@@ -1892,13 +1765,12 @@ static void idle_worker_timeout(unsigned long __pool)
 		worker = list_entry(pool->idle_list.prev, struct worker, entry);
 		expires = worker->last_active + IDLE_WORKER_TIMEOUT;
 
-		if (time_before(jiffies, expires))
+		if (time_before(jiffies, expires)) {
 			mod_timer(&pool->idle_timer, expires);
-		else {
-			/* it's been idle for too long, wake up manager */
-			pool->flags |= POOL_MANAGE_WORKERS;
-			wake_up_worker(pool);
+			break;
 		}
+
+		destroy_worker(worker);
 	}
 
 	spin_unlock_irq(&pool->lock);
@@ -1987,23 +1859,10 @@ restart:
 	mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT);
 
 	while (true) {
-		struct worker *worker;
-
-		worker = create_worker(pool);
-		if (worker) {
-			del_timer_sync(&pool->mayday_timer);
-			spin_lock_irq(&pool->lock);
-			start_worker(worker);
-			if (WARN_ON_ONCE(need_to_create_worker(pool)))
-				goto restart;
-			return true;
-		}
-
-		if (!need_to_create_worker(pool))
+		if (create_worker(pool) || !need_to_create_worker(pool))
 			break;
 
-		__set_current_state(TASK_INTERRUPTIBLE);
-		schedule_timeout(CREATE_COOLDOWN);
+		schedule_timeout_interruptible(CREATE_COOLDOWN);
 
 		if (!need_to_create_worker(pool))
 			break;
@@ -2011,50 +1870,17 @@ restart:
 
 	del_timer_sync(&pool->mayday_timer);
 	spin_lock_irq(&pool->lock);
+	/*
+	 * This is necessary even after a new worker was just successfully
+	 * created as @pool->lock was dropped and the new worker might have
+	 * already become busy.
+	 */
 	if (need_to_create_worker(pool))
 		goto restart;
 	return true;
 }
 
 /**
- * maybe_destroy_worker - destroy workers which have been idle for a while
- * @pool: pool to destroy workers for
- *
- * Destroy @pool workers which have been idle for longer than
- * IDLE_WORKER_TIMEOUT.
- *
- * LOCKING:
- * spin_lock_irq(pool->lock) which may be released and regrabbed
- * multiple times.  Called only from manager.
- *
- * Return:
- * %false if no action was taken and pool->lock stayed locked, %true
- * otherwise.
- */
-static bool maybe_destroy_workers(struct worker_pool *pool)
-{
-	bool ret = false;
-
-	while (too_many_workers(pool)) {
-		struct worker *worker;
-		unsigned long expires;
-
-		worker = list_entry(pool->idle_list.prev, struct worker, entry);
-		expires = worker->last_active + IDLE_WORKER_TIMEOUT;
-
-		if (time_before(jiffies, expires)) {
-			mod_timer(&pool->idle_timer, expires);
-			break;
-		}
-
-		destroy_worker(worker);
-		ret = true;
-	}
-
-	return ret;
-}
-
-/**
  * manage_workers - manage worker pool
  * @worker: self
  *
@@ -2083,8 +1909,6 @@ static bool manage_workers(struct worker *worker)
 	bool ret = false;
 
 	/*
-	 * Managership is governed by two mutexes - manager_arb and
-	 * manager_mutex.  manager_arb handles arbitration of manager role.
 	 * Anyone who successfully grabs manager_arb wins the arbitration
 	 * and becomes the manager.  mutex_trylock() on pool->manager_arb
 	 * failure while holding pool->lock reliably indicates that someone
@@ -2093,40 +1917,12 @@ static bool manage_workers(struct worker *worker)
 	 * grabbing manager_arb is responsible for actually performing
 	 * manager duties.  If manager_arb is grabbed and released without
 	 * actual management, the pool may stall indefinitely.
-	 *
-	 * manager_mutex is used for exclusion of actual management
-	 * operations.  The holder of manager_mutex can be sure that none
-	 * of management operations, including creation and destruction of
-	 * workers, won't take place until the mutex is released.  Because
-	 * manager_mutex doesn't interfere with manager role arbitration,
-	 * it is guaranteed that the pool's management, while may be
-	 * delayed, won't be disturbed by someone else grabbing
-	 * manager_mutex.
 	 */
 	if (!mutex_trylock(&pool->manager_arb))
 		return ret;
 
-	/*
-	 * With manager arbitration won, manager_mutex would be free in
-	 * most cases.  trylock first without dropping @pool->lock.
-	 */
-	if (unlikely(!mutex_trylock(&pool->manager_mutex))) {
-		spin_unlock_irq(&pool->lock);
-		mutex_lock(&pool->manager_mutex);
-		spin_lock_irq(&pool->lock);
-		ret = true;
-	}
-
-	pool->flags &= ~POOL_MANAGE_WORKERS;
-
-	/*
-	 * Destroy and then create so that may_start_working() is true
-	 * on return.
-	 */
-	ret |= maybe_destroy_workers(pool);
 	ret |= maybe_create_worker(pool);
 
-	mutex_unlock(&pool->manager_mutex);
 	mutex_unlock(&pool->manager_arb);
 	return ret;
 }
@@ -2166,13 +1962,8 @@ __acquires(&pool->lock)
 
 	lockdep_copy_map(&lockdep_map, &work->lockdep_map);
 #endif
-	/*
-	 * Ensure we're on the correct CPU.  DISASSOCIATED test is
-	 * necessary to avoid spurious warnings from rescuers servicing the
-	 * unbound or a disassociated pool.
-	 */
-	WARN_ON_ONCE(!(worker->flags & WORKER_UNBOUND) &&
-		     !(pool->flags & POOL_DISASSOCIATED) &&
+	/* ensure we're on the correct CPU */
+	WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) &&
 		     raw_smp_processor_id() != pool->cpu);
 
 	/*
@@ -2198,17 +1989,22 @@ __acquires(&pool->lock)
 	list_del_init(&work->entry);
 
 	/*
-	 * CPU intensive works don't participate in concurrency
-	 * management.  They're the scheduler's responsibility.
+	 * CPU intensive works don't participate in concurrency management.
+	 * They're the scheduler's responsibility.  This takes @worker out
+	 * of concurrency management and the next code block will chain
+	 * execution of the pending work items.
 	 */
 	if (unlikely(cpu_intensive))
-		worker_set_flags(worker, WORKER_CPU_INTENSIVE, true);
+		worker_set_flags(worker, WORKER_CPU_INTENSIVE);
 
 	/*
-	 * Unbound pool isn't concurrency managed and work items should be
-	 * executed ASAP.  Wake up another worker if necessary.
+	 * Wake up another worker if necessary.  The condition is always
+	 * false for normal per-cpu workers since nr_running would always
+	 * be >= 1 at this point.  This is used to chain execution of the
+	 * pending work items for WORKER_NOT_RUNNING workers such as the
+	 * UNBOUND and CPU_INTENSIVE ones.
 	 */
-	if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool))
+	if (need_more_worker(pool))
 		wake_up_worker(pool);
 
 	/*
@@ -2314,6 +2110,11 @@ woke_up:
 		spin_unlock_irq(&pool->lock);
 		WARN_ON_ONCE(!list_empty(&worker->entry));
 		worker->task->flags &= ~PF_WQ_WORKER;
+
+		set_task_comm(worker->task, "kworker/dying");
+		ida_simple_remove(&pool->worker_ida, worker->id);
+		worker_detach_from_pool(worker, pool);
+		kfree(worker);
 		return 0;
 	}
 
@@ -2359,11 +2160,8 @@ recheck:
 		}
 	} while (keep_working(pool));
 
-	worker_set_flags(worker, WORKER_PREP, false);
+	worker_set_flags(worker, WORKER_PREP);
 sleep:
-	if (unlikely(need_to_manage_workers(pool)) && manage_workers(worker))
-		goto recheck;
-
 	/*
 	 * pool->lock is held and there's no work to process and no need to
 	 * manage, sleep.  Workers are woken up only while holding
@@ -2440,8 +2238,9 @@ repeat:
 
 		spin_unlock_irq(&wq_mayday_lock);
 
-		/* migrate to the target cpu if possible */
-		worker_maybe_bind_and_lock(pool);
+		worker_attach_to_pool(rescuer, pool);
+
+		spin_lock_irq(&pool->lock);
 		rescuer->pool = pool;
 
 		/*
@@ -2457,21 +2256,24 @@ repeat:
 
 		/*
 		 * Put the reference grabbed by send_mayday().  @pool won't
-		 * go away while we're holding its lock.
+		 * go away while we're still attached to it.
 		 */
 		put_pwq(pwq);
 
 		/*
-		 * Leave this pool.  If keep_working() is %true, notify a
+		 * Leave this pool.  If need_more_worker() is %true, notify a
 		 * regular worker; otherwise, we end up with 0 concurrency
 		 * and stalling the execution.
 		 */
-		if (keep_working(pool))
+		if (need_more_worker(pool))
 			wake_up_worker(pool);
 
 		rescuer->pool = NULL;
-		spin_unlock(&pool->lock);
-		spin_lock(&wq_mayday_lock);
+		spin_unlock_irq(&pool->lock);
+
+		worker_detach_from_pool(rescuer, pool);
+
+		spin_lock_irq(&wq_mayday_lock);
 	}
 
 	spin_unlock_irq(&wq_mayday_lock);
@@ -3422,6 +3224,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 		}
 	}
 
+	dev_set_uevent_suppress(&wq_dev->dev, false);
 	kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD);
 	return 0;
 }
@@ -3550,9 +3353,10 @@ static int init_worker_pool(struct worker_pool *pool)
 		    (unsigned long)pool);
 
 	mutex_init(&pool->manager_arb);
-	mutex_init(&pool->manager_mutex);
-	idr_init(&pool->worker_idr);
+	mutex_init(&pool->attach_mutex);
+	INIT_LIST_HEAD(&pool->workers);
 
+	ida_init(&pool->worker_ida);
 	INIT_HLIST_NODE(&pool->hash_node);
 	pool->refcnt = 1;
 
@@ -3567,7 +3371,7 @@ static void rcu_free_pool(struct rcu_head *rcu)
 {
 	struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu);
 
-	idr_destroy(&pool->worker_idr);
+	ida_destroy(&pool->worker_ida);
 	free_workqueue_attrs(pool->attrs);
 	kfree(pool);
 }
@@ -3585,6 +3389,7 @@ static void rcu_free_pool(struct rcu_head *rcu)
  */
 static void put_unbound_pool(struct worker_pool *pool)
 {
+	DECLARE_COMPLETION_ONSTACK(detach_completion);
 	struct worker *worker;
 
 	lockdep_assert_held(&wq_pool_mutex);
@@ -3593,7 +3398,7 @@ static void put_unbound_pool(struct worker_pool *pool)
 		return;
 
 	/* sanity checks */
-	if (WARN_ON(!(pool->flags & POOL_DISASSOCIATED)) ||
+	if (WARN_ON(!(pool->cpu < 0)) ||
 	    WARN_ON(!list_empty(&pool->worklist)))
 		return;
 
@@ -3605,18 +3410,24 @@ static void put_unbound_pool(struct worker_pool *pool)
 	/*
 	 * Become the manager and destroy all workers.  Grabbing
 	 * manager_arb prevents @pool's workers from blocking on
-	 * manager_mutex.
+	 * attach_mutex.
 	 */
 	mutex_lock(&pool->manager_arb);
-	mutex_lock(&pool->manager_mutex);
-	spin_lock_irq(&pool->lock);
 
-	while ((worker = first_worker(pool)))
+	spin_lock_irq(&pool->lock);
+	while ((worker = first_idle_worker(pool)))
 		destroy_worker(worker);
 	WARN_ON(pool->nr_workers || pool->nr_idle);
-
 	spin_unlock_irq(&pool->lock);
-	mutex_unlock(&pool->manager_mutex);
+
+	mutex_lock(&pool->attach_mutex);
+	if (!list_empty(&pool->workers))
+		pool->detach_completion = &detach_completion;
+	mutex_unlock(&pool->attach_mutex);
+
+	if (pool->detach_completion)
+		wait_for_completion(pool->detach_completion);
+
 	mutex_unlock(&pool->manager_arb);
 
 	/* shut down the timers */
@@ -3653,7 +3464,7 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
 	hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) {
 		if (wqattrs_equal(pool->attrs, attrs)) {
 			pool->refcnt++;
-			goto out_unlock;
+			return pool;
 		}
 	}
 
@@ -3662,9 +3473,6 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
 	if (!pool || init_worker_pool(pool) < 0)
 		goto fail;
 
-	if (workqueue_freezing)
-		pool->flags |= POOL_FREEZING;
-
 	lockdep_set_subclass(&pool->lock, 1);	/* see put_pwq() */
 	copy_workqueue_attrs(pool->attrs, attrs);
 
@@ -3689,12 +3497,12 @@ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs)
 		goto fail;
 
 	/* create and start the initial worker */
-	if (create_and_start_worker(pool) < 0)
+	if (!create_worker(pool))
 		goto fail;
 
 	/* install */
 	hash_add(unbound_pool_hash, &pool->hash_node, hash);
-out_unlock:
+
 	return pool;
 fail:
 	if (pool)
@@ -3723,11 +3531,6 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
 	if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
 		return;
 
-	/*
-	 * Unlink @pwq.  Synchronization against wq->mutex isn't strictly
-	 * necessary on release but do it anyway.  It's easier to verify
-	 * and consistent with the linking path.
-	 */
 	mutex_lock(&wq->mutex);
 	list_del_rcu(&pwq->pwqs_node);
 	is_last = list_empty(&wq->pwqs);
@@ -3771,7 +3574,12 @@ static void pwq_adjust_max_active(struct pool_workqueue *pwq)
 
 	spin_lock_irq(&pwq->pool->lock);
 
-	if (!freezable || !(pwq->pool->flags & POOL_FREEZING)) {
+	/*
+	 * During [un]freezing, the caller is responsible for ensuring that
+	 * this function is called at least once after @workqueue_freezing
+	 * is updated and visible.
+	 */
+	if (!freezable || !workqueue_freezing) {
 		pwq->max_active = wq->saved_max_active;
 
 		while (!list_empty(&pwq->delayed_works) &&
@@ -3819,10 +3627,7 @@ static void link_pwq(struct pool_workqueue *pwq)
 	if (!list_empty(&pwq->pwqs_node))
 		return;
 
-	/*
-	 * Set the matching work_color.  This is synchronized with
-	 * wq->mutex to avoid confusing flush_workqueue().
-	 */
+	/* set the matching work_color */
 	pwq->work_color = wq->work_color;
 
 	/* sync max_active to the current setting */
@@ -3959,7 +3764,7 @@ int apply_workqueue_attrs(struct workqueue_struct *wq,
 	if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)))
 		return -EINVAL;
 
-	pwq_tbl = kzalloc(wq_numa_tbl_len * sizeof(pwq_tbl[0]), GFP_KERNEL);
+	pwq_tbl = kzalloc(nr_node_ids * sizeof(pwq_tbl[0]), GFP_KERNEL);
 	new_attrs = alloc_workqueue_attrs(GFP_KERNEL);
 	tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL);
 	if (!pwq_tbl || !new_attrs || !tmp_attrs)
@@ -4103,17 +3908,13 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	 * Let's determine what needs to be done.  If the target cpumask is
 	 * different from wq's, we need to compare it to @pwq's and create
 	 * a new one if they don't match.  If the target cpumask equals
-	 * wq's, the default pwq should be used.  If @pwq is already the
-	 * default one, nothing to do; otherwise, install the default one.
+	 * wq's, the default pwq should be used.
 	 */
 	if (wq_calc_node_cpumask(wq->unbound_attrs, node, cpu_off, cpumask)) {
 		if (cpumask_equal(cpumask, pwq->pool->attrs->cpumask))
 			goto out_unlock;
 	} else {
-		if (pwq == wq->dfl_pwq)
-			goto out_unlock;
-		else
-			goto use_dfl_pwq;
+		goto use_dfl_pwq;
 	}
 
 	mutex_unlock(&wq->mutex);
@@ -4121,8 +3922,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	/* create a new pwq */
 	pwq = alloc_unbound_pwq(wq, target_attrs);
 	if (!pwq) {
-		pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
-			   wq->name);
+		pr_warn("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
+			wq->name);
 		mutex_lock(&wq->mutex);
 		goto use_dfl_pwq;
 	}
@@ -4211,7 +4012,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 
 	/* allocate wq and format name */
 	if (flags & WQ_UNBOUND)
-		tbl_size = wq_numa_tbl_len * sizeof(wq->numa_pwq_tbl[0]);
+		tbl_size = nr_node_ids * sizeof(wq->numa_pwq_tbl[0]);
 
 	wq = kzalloc(sizeof(*wq) + tbl_size, GFP_KERNEL);
 	if (!wq)
@@ -4253,7 +4054,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	if (flags & WQ_MEM_RECLAIM) {
 		struct worker *rescuer;
 
-		rescuer = alloc_worker();
+		rescuer = alloc_worker(NUMA_NO_NODE);
 		if (!rescuer)
 			goto err_destroy;
 
@@ -4599,28 +4400,25 @@ static void wq_unbind_fn(struct work_struct *work)
 	int cpu = smp_processor_id();
 	struct worker_pool *pool;
 	struct worker *worker;
-	int wi;
 
 	for_each_cpu_worker_pool(pool, cpu) {
-		WARN_ON_ONCE(cpu != smp_processor_id());
-
-		mutex_lock(&pool->manager_mutex);
+		mutex_lock(&pool->attach_mutex);
 		spin_lock_irq(&pool->lock);
 
 		/*
-		 * We've blocked all manager operations.  Make all workers
+		 * We've blocked all attach/detach operations. Make all workers
 		 * unbound and set DISASSOCIATED.  Before this, all workers
 		 * except for the ones which are still executing works from
 		 * before the last CPU down must be on the cpu.  After
 		 * this, they may become diasporas.
 		 */
-		for_each_pool_worker(worker, wi, pool)
+		for_each_pool_worker(worker, pool)
 			worker->flags |= WORKER_UNBOUND;
 
 		pool->flags |= POOL_DISASSOCIATED;
 
 		spin_unlock_irq(&pool->lock);
-		mutex_unlock(&pool->manager_mutex);
+		mutex_unlock(&pool->attach_mutex);
 
 		/*
 		 * Call schedule() so that we cross rq->lock and thus can
@@ -4660,9 +4458,8 @@ static void wq_unbind_fn(struct work_struct *work)
 static void rebind_workers(struct worker_pool *pool)
 {
 	struct worker *worker;
-	int wi;
 
-	lockdep_assert_held(&pool->manager_mutex);
+	lockdep_assert_held(&pool->attach_mutex);
 
 	/*
 	 * Restore CPU affinity of all workers.  As all idle workers should
@@ -4671,13 +4468,14 @@ static void rebind_workers(struct worker_pool *pool)
 	 * of all workers first and then clear UNBOUND.  As we're called
 	 * from CPU_ONLINE, the following shouldn't fail.
 	 */
-	for_each_pool_worker(worker, wi, pool)
+	for_each_pool_worker(worker, pool)
 		WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
 						  pool->attrs->cpumask) < 0);
 
 	spin_lock_irq(&pool->lock);
+	pool->flags &= ~POOL_DISASSOCIATED;
 
-	for_each_pool_worker(worker, wi, pool) {
+	for_each_pool_worker(worker, pool) {
 		unsigned int worker_flags = worker->flags;
 
 		/*
@@ -4729,9 +4527,8 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
 {
 	static cpumask_t cpumask;
 	struct worker *worker;
-	int wi;
 
-	lockdep_assert_held(&pool->manager_mutex);
+	lockdep_assert_held(&pool->attach_mutex);
 
 	/* is @cpu allowed for @pool? */
 	if (!cpumask_test_cpu(cpu, pool->attrs->cpumask))
@@ -4743,7 +4540,7 @@ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu)
 		return;
 
 	/* as we're called from CPU_ONLINE, the following shouldn't fail */
-	for_each_pool_worker(worker, wi, pool)
+	for_each_pool_worker(worker, pool)
 		WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
 						  pool->attrs->cpumask) < 0);
 }
@@ -4766,7 +4563,7 @@ static int workqueue_cpu_up_callback(struct notifier_block *nfb,
 		for_each_cpu_worker_pool(pool, cpu) {
 			if (pool->nr_workers)
 				continue;
-			if (create_and_start_worker(pool) < 0)
+			if (!create_worker(pool))
 				return NOTIFY_BAD;
 		}
 		break;
@@ -4776,19 +4573,14 @@ static int workqueue_cpu_up_callback(struct notifier_block *nfb,
 		mutex_lock(&wq_pool_mutex);
 
 		for_each_pool(pool, pi) {
-			mutex_lock(&pool->manager_mutex);
-
-			if (pool->cpu == cpu) {
-				spin_lock_irq(&pool->lock);
-				pool->flags &= ~POOL_DISASSOCIATED;
-				spin_unlock_irq(&pool->lock);
+			mutex_lock(&pool->attach_mutex);
 
+			if (pool->cpu == cpu)
 				rebind_workers(pool);
-			} else if (pool->cpu < 0) {
+			else if (pool->cpu < 0)
 				restore_unbound_workers_cpumask(pool, cpu);
-			}
 
-			mutex_unlock(&pool->manager_mutex);
+			mutex_unlock(&pool->attach_mutex);
 		}
 
 		/* update NUMA affinity of unbound workqueues */
@@ -4887,24 +4679,14 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
  */
 void freeze_workqueues_begin(void)
 {
-	struct worker_pool *pool;
 	struct workqueue_struct *wq;
 	struct pool_workqueue *pwq;
-	int pi;
 
 	mutex_lock(&wq_pool_mutex);
 
 	WARN_ON_ONCE(workqueue_freezing);
 	workqueue_freezing = true;
 
-	/* set FREEZING */
-	for_each_pool(pool, pi) {
-		spin_lock_irq(&pool->lock);
-		WARN_ON_ONCE(pool->flags & POOL_FREEZING);
-		pool->flags |= POOL_FREEZING;
-		spin_unlock_irq(&pool->lock);
-	}
-
 	list_for_each_entry(wq, &workqueues, list) {
 		mutex_lock(&wq->mutex);
 		for_each_pwq(pwq, wq)
@@ -4974,21 +4756,13 @@ void thaw_workqueues(void)
 {
 	struct workqueue_struct *wq;
 	struct pool_workqueue *pwq;
-	struct worker_pool *pool;
-	int pi;
 
 	mutex_lock(&wq_pool_mutex);
 
 	if (!workqueue_freezing)
 		goto out_unlock;
 
-	/* clear FREEZING */
-	for_each_pool(pool, pi) {
-		spin_lock_irq(&pool->lock);
-		WARN_ON_ONCE(!(pool->flags & POOL_FREEZING));
-		pool->flags &= ~POOL_FREEZING;
-		spin_unlock_irq(&pool->lock);
-	}
+	workqueue_freezing = false;
 
 	/* restore max_active and repopulate worklist */
 	list_for_each_entry(wq, &workqueues, list) {
@@ -4998,7 +4772,6 @@ void thaw_workqueues(void)
 		mutex_unlock(&wq->mutex);
 	}
 
-	workqueue_freezing = false;
 out_unlock:
 	mutex_unlock(&wq_pool_mutex);
 }
@@ -5009,10 +4782,6 @@ static void __init wq_numa_init(void)
 	cpumask_var_t *tbl;
 	int node, cpu;
 
-	/* determine NUMA pwq table len - highest node id + 1 */
-	for_each_node(node)
-		wq_numa_tbl_len = max(wq_numa_tbl_len, node + 1);
-
 	if (num_possible_nodes() <= 1)
 		return;
 
@@ -5029,11 +4798,11 @@ static void __init wq_numa_init(void)
 	 * available.  Build one from cpu_to_node() which should have been
 	 * fully initialized by now.
 	 */
-	tbl = kzalloc(wq_numa_tbl_len * sizeof(tbl[0]), GFP_KERNEL);
+	tbl = kzalloc(nr_node_ids * sizeof(tbl[0]), GFP_KERNEL);
 	BUG_ON(!tbl);
 
 	for_each_node(node)
-		BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
+		BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
 				node_online(node) ? node : NUMA_NO_NODE));
 
 	for_each_possible_cpu(cpu) {
@@ -5089,7 +4858,7 @@ static int __init init_workqueues(void)
 
 		for_each_cpu_worker_pool(pool, cpu) {
 			pool->flags &= ~POOL_DISASSOCIATED;
-			BUG_ON(create_and_start_worker(pool) < 0);
+			BUG_ON(!create_worker(pool));
 		}
 	}
 
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 7e2204db0b1..45215870ac6 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -37,6 +37,8 @@ struct worker {
 	struct task_struct	*task;		/* I: worker task */
 	struct worker_pool	*pool;		/* I: the associated pool */
 						/* L: for rescuers */
+	struct list_head	node;		/* A: anchored at pool->workers */
+						/* A: runs through worker->node */
 
 	unsigned long		last_active;	/* L: last active timestamp */
 	unsigned int		flags;		/* X: flags */
diff --git a/lib/Kconfig b/lib/Kconfig
index 4771fb3f4da..334f7722a99 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -331,6 +331,20 @@ config TEXTSEARCH_FSM
 config BTREE
 	boolean
 
+config INTERVAL_TREE
+	boolean
+	help
+	  Simple, embeddable, interval-tree. Can find the start of an
+	  overlapping range in log(n) time and then iterate over all
+	  overlapping nodes. The algorithm is implemented as an
+	  augmented rbtree.
+
+	  See:
+
+		Documentation/rbtree.txt
+
+	  for more information.
+
 config ASSOCIATIVE_ARRAY
 	bool
 	help
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ccca3226474..901096d31c6 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -835,7 +835,7 @@ config DEBUG_RT_MUTEXES
 
 config RT_MUTEX_TESTER
 	bool "Built-in scriptable tester for rt-mutexes"
-	depends on DEBUG_KERNEL && RT_MUTEXES
+	depends on DEBUG_KERNEL && RT_MUTEXES && BROKEN
 	help
 	  This option enables a rt-mutex tester.
 
@@ -930,7 +930,7 @@ config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC
+	select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !SCORE
 	select KALLSYMS
 	select KALLSYMS_ALL
 
@@ -1131,20 +1131,6 @@ config PROVE_RCU_REPEATEDLY
 
 	 Say N if you are unsure.
 
-config PROVE_RCU_DELAY
-	bool "RCU debugging: preemptible RCU race provocation"
-	depends on DEBUG_KERNEL && PREEMPT_RCU
-	default n
-	help
-	 There is a class of races that involve an unlikely preemption
-	 of __rcu_read_unlock() just after ->rcu_read_lock_nesting has
-	 been set to INT_MIN.  This feature inserts a delay at that
-	 point to increase the probability of these races.
-
-	 Say Y to increase probability of preemption of __rcu_read_unlock().
-
-	 Say N if you are unsure.
-
 config SPARSE_RCU_POINTER
 	bool "RCU debugging: sparse-based checks for pointer usage"
 	default n
@@ -1408,7 +1394,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
 	depends on !X86_64
 	select STACKTRACE
-	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC
+	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !SCORE
 	help
 	  Provide stacktrace filter for fault-injection capabilities
 
@@ -1511,6 +1497,7 @@ config RBTREE_TEST
 config INTERVAL_TREE_TEST
 	tristate "Interval tree test"
 	depends on m && DEBUG_KERNEL
+	select INTERVAL_TREE
 	help
 	  A benchmark measuring the performance of the interval tree library
 
@@ -1635,6 +1622,19 @@ config TEST_USER_COPY
 
 	  If unsure, say N.
 
+config TEST_BPF
+	tristate "Test BPF filter functionality"
+	default n
+	depends on m && NET
+	help
+	  This builds the "test_bpf" module that runs various test vectors
+	  against the BPF interpreter or BPF JIT compiler depending on the
+	  current setting. This is in particular useful for BPF JIT compiler
+	  development, but also to run regression tests against changes in
+	  the interpreter code.
+
+	  If unsure, say N.
+
 source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
diff --git a/lib/Makefile b/lib/Makefile
index 74a32dc49a9..ba967a19edb 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -33,6 +33,7 @@ obj-y += kstrtox.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 obj-$(CONFIG_TEST_MODULE) += test_module.o
 obj-$(CONFIG_TEST_USER_COPY) += test_user_copy.o
+obj-$(CONFIG_TEST_BPF) += test_bpf.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
@@ -50,6 +51,7 @@ CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 
 obj-$(CONFIG_BTREE) += btree.o
+obj-$(CONFIG_INTERVAL_TREE) += interval_tree.o
 obj-$(CONFIG_ASSOCIATIVE_ARRAY) += assoc_array.o
 obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
 obj-$(CONFIG_DEBUG_LIST) += list_debug.o
@@ -157,8 +159,6 @@ lib-$(CONFIG_LIBFDT) += $(libfdt_files)
 obj-$(CONFIG_RBTREE_TEST) += rbtree_test.o
 obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o
 
-interval_tree_test-objs := interval_tree_test_main.o interval_tree.o
-
 obj-$(CONFIG_PERCPU_TEST) += percpu_test.o
 
 obj-$(CONFIG_ASN1) += asn1_decoder.o
diff --git a/lib/cpumask.c b/lib/cpumask.c
index b810b753c60..b6513a9f289 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -164,3 +164,66 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
 	memblock_free_early(__pa(mask), cpumask_size());
 }
 #endif
+
+/**
+ * cpumask_set_cpu_local_first - set i'th cpu with local numa cpu's first
+ *
+ * @i: index number
+ * @numa_node: local numa_node
+ * @dstp: cpumask with the relevant cpu bit set according to the policy
+ *
+ * This function sets the cpumask according to a numa aware policy.
+ * cpumask could be used as an affinity hint for the IRQ related to a
+ * queue. When the policy is to spread queues across cores - local cores
+ * first.
+ *
+ * Returns 0 on success, -ENOMEM for no memory, and -EAGAIN when failed to set
+ * the cpu bit and need to re-call the function.
+ */
+int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
+{
+	cpumask_var_t mask;
+	int cpu;
+	int ret = 0;
+
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	i %= num_online_cpus();
+
+	if (numa_node == -1 || !cpumask_of_node(numa_node)) {
+		/* Use all online cpu's for non numa aware system */
+		cpumask_copy(mask, cpu_online_mask);
+	} else {
+		int n;
+
+		cpumask_and(mask,
+			    cpumask_of_node(numa_node), cpu_online_mask);
+
+		n = cpumask_weight(mask);
+		if (i >= n) {
+			i -= n;
+
+			/* If index > number of local cpu's, mask out local
+			 * cpu's
+			 */
+			cpumask_andnot(mask, cpu_online_mask, mask);
+		}
+	}
+
+	for_each_cpu(cpu, mask) {
+		if (--i < 0)
+			goto out;
+	}
+
+	ret = -EAGAIN;
+
+out:
+	free_cpumask_var(mask);
+
+	if (!ret)
+		cpumask_set_cpu(cpu, dstp);
+
+	return ret;
+}
+EXPORT_SYMBOL(cpumask_set_cpu_local_first);
diff --git a/lib/crc7.c b/lib/crc7.c
index f1c3a144cec..bf6255e2391 100644
--- a/lib/crc7.c
+++ b/lib/crc7.c
@@ -10,42 +10,47 @@
 #include <linux/crc7.h>
 
 
-/* Table for CRC-7 (polynomial x^7 + x^3 + 1) */
-const u8 crc7_syndrome_table[256] = {
-	0x00, 0x09, 0x12, 0x1b, 0x24, 0x2d, 0x36, 0x3f,
-	0x48, 0x41, 0x5a, 0x53, 0x6c, 0x65, 0x7e, 0x77,
-	0x19, 0x10, 0x0b, 0x02, 0x3d, 0x34, 0x2f, 0x26,
-	0x51, 0x58, 0x43, 0x4a, 0x75, 0x7c, 0x67, 0x6e,
-	0x32, 0x3b, 0x20, 0x29, 0x16, 0x1f, 0x04, 0x0d,
-	0x7a, 0x73, 0x68, 0x61, 0x5e, 0x57, 0x4c, 0x45,
-	0x2b, 0x22, 0x39, 0x30, 0x0f, 0x06, 0x1d, 0x14,
-	0x63, 0x6a, 0x71, 0x78, 0x47, 0x4e, 0x55, 0x5c,
-	0x64, 0x6d, 0x76, 0x7f, 0x40, 0x49, 0x52, 0x5b,
-	0x2c, 0x25, 0x3e, 0x37, 0x08, 0x01, 0x1a, 0x13,
-	0x7d, 0x74, 0x6f, 0x66, 0x59, 0x50, 0x4b, 0x42,
-	0x35, 0x3c, 0x27, 0x2e, 0x11, 0x18, 0x03, 0x0a,
-	0x56, 0x5f, 0x44, 0x4d, 0x72, 0x7b, 0x60, 0x69,
-	0x1e, 0x17, 0x0c, 0x05, 0x3a, 0x33, 0x28, 0x21,
-	0x4f, 0x46, 0x5d, 0x54, 0x6b, 0x62, 0x79, 0x70,
-	0x07, 0x0e, 0x15, 0x1c, 0x23, 0x2a, 0x31, 0x38,
-	0x41, 0x48, 0x53, 0x5a, 0x65, 0x6c, 0x77, 0x7e,
-	0x09, 0x00, 0x1b, 0x12, 0x2d, 0x24, 0x3f, 0x36,
-	0x58, 0x51, 0x4a, 0x43, 0x7c, 0x75, 0x6e, 0x67,
-	0x10, 0x19, 0x02, 0x0b, 0x34, 0x3d, 0x26, 0x2f,
-	0x73, 0x7a, 0x61, 0x68, 0x57, 0x5e, 0x45, 0x4c,
-	0x3b, 0x32, 0x29, 0x20, 0x1f, 0x16, 0x0d, 0x04,
-	0x6a, 0x63, 0x78, 0x71, 0x4e, 0x47, 0x5c, 0x55,
-	0x22, 0x2b, 0x30, 0x39, 0x06, 0x0f, 0x14, 0x1d,
-	0x25, 0x2c, 0x37, 0x3e, 0x01, 0x08, 0x13, 0x1a,
-	0x6d, 0x64, 0x7f, 0x76, 0x49, 0x40, 0x5b, 0x52,
-	0x3c, 0x35, 0x2e, 0x27, 0x18, 0x11, 0x0a, 0x03,
-	0x74, 0x7d, 0x66, 0x6f, 0x50, 0x59, 0x42, 0x4b,
-	0x17, 0x1e, 0x05, 0x0c, 0x33, 0x3a, 0x21, 0x28,
-	0x5f, 0x56, 0x4d, 0x44, 0x7b, 0x72, 0x69, 0x60,
-	0x0e, 0x07, 0x1c, 0x15, 0x2a, 0x23, 0x38, 0x31,
-	0x46, 0x4f, 0x54, 0x5d, 0x62, 0x6b, 0x70, 0x79
+/*
+ * Table for CRC-7 (polynomial x^7 + x^3 + 1).
+ * This is a big-endian CRC (msbit is highest power of x),
+ * aligned so the msbit of the byte is the x^6 coefficient
+ * and the lsbit is not used.
+ */
+const u8 crc7_be_syndrome_table[256] = {
+	0x00, 0x12, 0x24, 0x36, 0x48, 0x5a, 0x6c, 0x7e,
+	0x90, 0x82, 0xb4, 0xa6, 0xd8, 0xca, 0xfc, 0xee,
+	0x32, 0x20, 0x16, 0x04, 0x7a, 0x68, 0x5e, 0x4c,
+	0xa2, 0xb0, 0x86, 0x94, 0xea, 0xf8, 0xce, 0xdc,
+	0x64, 0x76, 0x40, 0x52, 0x2c, 0x3e, 0x08, 0x1a,
+	0xf4, 0xe6, 0xd0, 0xc2, 0xbc, 0xae, 0x98, 0x8a,
+	0x56, 0x44, 0x72, 0x60, 0x1e, 0x0c, 0x3a, 0x28,
+	0xc6, 0xd4, 0xe2, 0xf0, 0x8e, 0x9c, 0xaa, 0xb8,
+	0xc8, 0xda, 0xec, 0xfe, 0x80, 0x92, 0xa4, 0xb6,
+	0x58, 0x4a, 0x7c, 0x6e, 0x10, 0x02, 0x34, 0x26,
+	0xfa, 0xe8, 0xde, 0xcc, 0xb2, 0xa0, 0x96, 0x84,
+	0x6a, 0x78, 0x4e, 0x5c, 0x22, 0x30, 0x06, 0x14,
+	0xac, 0xbe, 0x88, 0x9a, 0xe4, 0xf6, 0xc0, 0xd2,
+	0x3c, 0x2e, 0x18, 0x0a, 0x74, 0x66, 0x50, 0x42,
+	0x9e, 0x8c, 0xba, 0xa8, 0xd6, 0xc4, 0xf2, 0xe0,
+	0x0e, 0x1c, 0x2a, 0x38, 0x46, 0x54, 0x62, 0x70,
+	0x82, 0x90, 0xa6, 0xb4, 0xca, 0xd8, 0xee, 0xfc,
+	0x12, 0x00, 0x36, 0x24, 0x5a, 0x48, 0x7e, 0x6c,
+	0xb0, 0xa2, 0x94, 0x86, 0xf8, 0xea, 0xdc, 0xce,
+	0x20, 0x32, 0x04, 0x16, 0x68, 0x7a, 0x4c, 0x5e,
+	0xe6, 0xf4, 0xc2, 0xd0, 0xae, 0xbc, 0x8a, 0x98,
+	0x76, 0x64, 0x52, 0x40, 0x3e, 0x2c, 0x1a, 0x08,
+	0xd4, 0xc6, 0xf0, 0xe2, 0x9c, 0x8e, 0xb8, 0xaa,
+	0x44, 0x56, 0x60, 0x72, 0x0c, 0x1e, 0x28, 0x3a,
+	0x4a, 0x58, 0x6e, 0x7c, 0x02, 0x10, 0x26, 0x34,
+	0xda, 0xc8, 0xfe, 0xec, 0x92, 0x80, 0xb6, 0xa4,
+	0x78, 0x6a, 0x5c, 0x4e, 0x30, 0x22, 0x14, 0x06,
+	0xe8, 0xfa, 0xcc, 0xde, 0xa0, 0xb2, 0x84, 0x96,
+	0x2e, 0x3c, 0x0a, 0x18, 0x66, 0x74, 0x42, 0x50,
+	0xbe, 0xac, 0x9a, 0x88, 0xf6, 0xe4, 0xd2, 0xc0,
+	0x1c, 0x0e, 0x38, 0x2a, 0x54, 0x46, 0x70, 0x62,
+	0x8c, 0x9e, 0xa8, 0xba, 0xc4, 0xd6, 0xe0, 0xf2
 };
-EXPORT_SYMBOL(crc7_syndrome_table);
+EXPORT_SYMBOL(crc7_be_syndrome_table);
 
 /**
  * crc7 - update the CRC7 for the data buffer
@@ -55,14 +60,17 @@ EXPORT_SYMBOL(crc7_syndrome_table);
  * Context: any
  *
  * Returns the updated CRC7 value.
+ * The CRC7 is left-aligned in the byte (the lsbit is always 0), as that
+ * makes the computation easier, and all callers want it in that form.
+ *
  */
-u8 crc7(u8 crc, const u8 *buffer, size_t len)
+u8 crc7_be(u8 crc, const u8 *buffer, size_t len)
 {
 	while (len--)
-		crc = crc7_byte(crc, *buffer++);
+		crc = crc7_be_byte(crc, *buffer++);
 	return crc;
 }
-EXPORT_SYMBOL(crc7);
+EXPORT_SYMBOL(crc7_be);
 
 MODULE_DESCRIPTION("CRC7 calculations");
 MODULE_LICENSE("GPL");
diff --git a/lib/interval_tree.c b/lib/interval_tree.c
index e6eb406f2d6..f367f9ad544 100644
--- a/lib/interval_tree.c
+++ b/lib/interval_tree.c
@@ -1,6 +1,7 @@
 #include <linux/init.h>
 #include <linux/interval_tree.h>
 #include <linux/interval_tree_generic.h>
+#include <linux/module.h>
 
 #define START(node) ((node)->start)
 #define LAST(node)  ((node)->last)
@@ -8,3 +9,8 @@
 INTERVAL_TREE_DEFINE(struct interval_tree_node, rb,
 		     unsigned long, __subtree_last,
 		     START, LAST,, interval_tree)
+
+EXPORT_SYMBOL_GPL(interval_tree_insert);
+EXPORT_SYMBOL_GPL(interval_tree_remove);
+EXPORT_SYMBOL_GPL(interval_tree_iter_first);
+EXPORT_SYMBOL_GPL(interval_tree_iter_next);
diff --git a/lib/interval_tree_test_main.c b/lib/interval_tree_test.c
index 245900b98c8..245900b98c8 100644
--- a/lib/interval_tree_test_main.c
+++ b/lib/interval_tree_test.c
diff --git a/lib/iovec.c b/lib/iovec.c
index 454baa88bf2..7a7c2da4cdd 100644
--- a/lib/iovec.c
+++ b/lib/iovec.c
@@ -51,3 +51,58 @@ int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len)
 	return 0;
 }
 EXPORT_SYMBOL(memcpy_toiovec);
+
+/*
+ *	Copy kernel to iovec. Returns -EFAULT on error.
+ */
+
+int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
+		      int offset, int len)
+{
+	int copy;
+	for (; len > 0; ++iov) {
+		/* Skip over the finished iovecs */
+		if (unlikely(offset >= iov->iov_len)) {
+			offset -= iov->iov_len;
+			continue;
+		}
+		copy = min_t(unsigned int, iov->iov_len - offset, len);
+		if (copy_to_user(iov->iov_base + offset, kdata, copy))
+			return -EFAULT;
+		offset = 0;
+		kdata += copy;
+		len -= copy;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(memcpy_toiovecend);
+
+/*
+ *	Copy iovec to kernel. Returns -EFAULT on error.
+ */
+
+int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
+			int offset, int len)
+{
+	/* Skip over the finished iovecs */
+	while (offset >= iov->iov_len) {
+		offset -= iov->iov_len;
+		iov++;
+	}
+
+	while (len > 0) {
+		u8 __user *base = iov->iov_base + offset;
+		int copy = min_t(unsigned int, len, iov->iov_len - offset);
+
+		offset = 0;
+		if (copy_from_user(kdata, base, copy))
+			return -EFAULT;
+		len -= copy;
+		kdata += copy;
+		iov++;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(memcpy_fromiovecend);
diff --git a/lib/lockref.c b/lib/lockref.c
index f07a40d3387..d2233de9a86 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -1,6 +1,5 @@
 #include <linux/export.h>
 #include <linux/lockref.h>
-#include <linux/mutex.h>
 
 #if USE_CMPXCHG_LOCKREF
 
@@ -29,7 +28,7 @@
 		if (likely(old.lock_count == prev.lock_count)) {		\
 			SUCCESS;						\
 		}								\
-		arch_mutex_cpu_relax();						\
+		cpu_relax_lowlatency();						\
 	}									\
 } while (0)
 
diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c
index df6839e3ce0..7a85967060a 100644
--- a/lib/lz4/lz4_decompress.c
+++ b/lib/lz4/lz4_decompress.c
@@ -72,6 +72,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 			len = *ip++;
 			for (; len == 255; length += 255)
 				len = *ip++;
+			if (unlikely(length > (size_t)(length + len)))
+				goto _output_error;
 			length += len;
 		}
 
@@ -106,6 +108,8 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 		if (length == ML_MASK) {
 			for (; *ip == 255; length += 255)
 				ip++;
+			if (unlikely(length > (size_t)(length + *ip)))
+				goto _output_error;
 			length += *ip++;
 		}
 
@@ -155,7 +159,7 @@ static int lz4_uncompress(const char *source, char *dest, int osize)
 
 	/* write overflow error detected */
 _output_error:
-	return (int) (-(((char *)ip) - source));
+	return -1;
 }
 
 static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
@@ -188,6 +192,8 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 			int s = 255;
 			while ((ip < iend) && (s == 255)) {
 				s = *ip++;
+				if (unlikely(length > (size_t)(length + s)))
+					goto _output_error;
 				length += s;
 			}
 		}
@@ -228,6 +234,8 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 		if (length == ML_MASK) {
 			while (ip < iend) {
 				int s = *ip++;
+				if (unlikely(length > (size_t)(length + s)))
+					goto _output_error;
 				length += s;
 				if (s == 255)
 					continue;
@@ -280,7 +288,7 @@ static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
 
 	/* write overflow error detected */
 _output_error:
-	return (int) (-(((char *) ip) - source));
+	return -1;
 }
 
 int lz4_decompress(const unsigned char *src, size_t *src_len,
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 569985d522d..8563081e8da 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -19,11 +19,31 @@
 #include <linux/lzo.h>
 #include "lzodefs.h"
 
-#define HAVE_IP(x)      ((size_t)(ip_end - ip) >= (size_t)(x))
-#define HAVE_OP(x)      ((size_t)(op_end - op) >= (size_t)(x))
-#define NEED_IP(x)      if (!HAVE_IP(x)) goto input_overrun
-#define NEED_OP(x)      if (!HAVE_OP(x)) goto output_overrun
-#define TEST_LB(m_pos)  if ((m_pos) < out) goto lookbehind_overrun
+#define HAVE_IP(t, x)					\
+	(((size_t)(ip_end - ip) >= (size_t)(t + x)) &&	\
+	 (((t + x) >= t) && ((t + x) >= x)))
+
+#define HAVE_OP(t, x)					\
+	(((size_t)(op_end - op) >= (size_t)(t + x)) &&	\
+	 (((t + x) >= t) && ((t + x) >= x)))
+
+#define NEED_IP(t, x)					\
+	do {						\
+		if (!HAVE_IP(t, x))			\
+			goto input_overrun;		\
+	} while (0)
+
+#define NEED_OP(t, x)					\
+	do {						\
+		if (!HAVE_OP(t, x))			\
+			goto output_overrun;		\
+	} while (0)
+
+#define TEST_LB(m_pos)					\
+	do {						\
+		if ((m_pos) < out)			\
+			goto lookbehind_overrun;	\
+	} while (0)
 
 int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 			  unsigned char *out, size_t *out_len)
@@ -58,14 +78,14 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 					while (unlikely(*ip == 0)) {
 						t += 255;
 						ip++;
-						NEED_IP(1);
+						NEED_IP(1, 0);
 					}
 					t += 15 + *ip++;
 				}
 				t += 3;
 copy_literal_run:
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-				if (likely(HAVE_IP(t + 15) && HAVE_OP(t + 15))) {
+				if (likely(HAVE_IP(t, 15) && HAVE_OP(t, 15))) {
 					const unsigned char *ie = ip + t;
 					unsigned char *oe = op + t;
 					do {
@@ -81,8 +101,8 @@ copy_literal_run:
 				} else
 #endif
 				{
-					NEED_OP(t);
-					NEED_IP(t + 3);
+					NEED_OP(t, 0);
+					NEED_IP(t, 3);
 					do {
 						*op++ = *ip++;
 					} while (--t > 0);
@@ -95,7 +115,7 @@ copy_literal_run:
 				m_pos -= t >> 2;
 				m_pos -= *ip++ << 2;
 				TEST_LB(m_pos);
-				NEED_OP(2);
+				NEED_OP(2, 0);
 				op[0] = m_pos[0];
 				op[1] = m_pos[1];
 				op += 2;
@@ -119,10 +139,10 @@ copy_literal_run:
 				while (unlikely(*ip == 0)) {
 					t += 255;
 					ip++;
-					NEED_IP(1);
+					NEED_IP(1, 0);
 				}
 				t += 31 + *ip++;
-				NEED_IP(2);
+				NEED_IP(2, 0);
 			}
 			m_pos = op - 1;
 			next = get_unaligned_le16(ip);
@@ -137,10 +157,10 @@ copy_literal_run:
 				while (unlikely(*ip == 0)) {
 					t += 255;
 					ip++;
-					NEED_IP(1);
+					NEED_IP(1, 0);
 				}
 				t += 7 + *ip++;
-				NEED_IP(2);
+				NEED_IP(2, 0);
 			}
 			next = get_unaligned_le16(ip);
 			ip += 2;
@@ -154,7 +174,7 @@ copy_literal_run:
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
 		if (op - m_pos >= 8) {
 			unsigned char *oe = op + t;
-			if (likely(HAVE_OP(t + 15))) {
+			if (likely(HAVE_OP(t, 15))) {
 				do {
 					COPY8(op, m_pos);
 					op += 8;
@@ -164,7 +184,7 @@ copy_literal_run:
 					m_pos += 8;
 				} while (op < oe);
 				op = oe;
-				if (HAVE_IP(6)) {
+				if (HAVE_IP(6, 0)) {
 					state = next;
 					COPY4(op, ip);
 					op += next;
@@ -172,7 +192,7 @@ copy_literal_run:
 					continue;
 				}
 			} else {
-				NEED_OP(t);
+				NEED_OP(t, 0);
 				do {
 					*op++ = *m_pos++;
 				} while (op < oe);
@@ -181,7 +201,7 @@ copy_literal_run:
 #endif
 		{
 			unsigned char *oe = op + t;
-			NEED_OP(t);
+			NEED_OP(t, 0);
 			op[0] = m_pos[0];
 			op[1] = m_pos[1];
 			op += 2;
@@ -194,15 +214,15 @@ match_next:
 		state = next;
 		t = next;
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
-		if (likely(HAVE_IP(6) && HAVE_OP(4))) {
+		if (likely(HAVE_IP(6, 0) && HAVE_OP(4, 0))) {
 			COPY4(op, ip);
 			op += t;
 			ip += t;
 		} else
 #endif
 		{
-			NEED_IP(t + 3);
-			NEED_OP(t);
+			NEED_IP(t, 3);
+			NEED_OP(t, 0);
 			while (t > 0) {
 				*op++ = *ip++;
 				t--;
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 963b7034a51..fe5a3342e96 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -31,6 +31,11 @@
 
 #define PCPU_COUNT_BIAS		(1U << 31)
 
+static unsigned __percpu *pcpu_count_ptr(struct percpu_ref *ref)
+{
+	return (unsigned __percpu *)(ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
+}
+
 /**
  * percpu_ref_init - initialize a percpu refcount
  * @ref: percpu_ref to initialize
@@ -46,8 +51,8 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release)
 {
 	atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);
 
-	ref->pcpu_count = alloc_percpu(unsigned);
-	if (!ref->pcpu_count)
+	ref->pcpu_count_ptr = (unsigned long)alloc_percpu(unsigned);
+	if (!ref->pcpu_count_ptr)
 		return -ENOMEM;
 
 	ref->release = release;
@@ -56,53 +61,71 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release)
 EXPORT_SYMBOL_GPL(percpu_ref_init);
 
 /**
- * percpu_ref_cancel_init - cancel percpu_ref_init()
- * @ref: percpu_ref to cancel init for
+ * percpu_ref_reinit - re-initialize a percpu refcount
+ * @ref: perpcu_ref to re-initialize
  *
- * Once a percpu_ref is initialized, its destruction is initiated by
- * percpu_ref_kill() and completes asynchronously, which can be painful to
- * do when destroying a half-constructed object in init failure path.
+ * Re-initialize @ref so that it's in the same state as when it finished
+ * percpu_ref_init().  @ref must have been initialized successfully, killed
+ * and reached 0 but not exited.
  *
- * This function destroys @ref without invoking @ref->release and the
- * memory area containing it can be freed immediately on return.  To
- * prevent accidental misuse, it's required that @ref has finished
- * percpu_ref_init(), whether successful or not, but never used.
- *
- * The weird name and usage restriction are to prevent people from using
- * this function by mistake for normal shutdown instead of
- * percpu_ref_kill().
+ * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while
+ * this function is in progress.
  */
-void percpu_ref_cancel_init(struct percpu_ref *ref)
+void percpu_ref_reinit(struct percpu_ref *ref)
 {
-	unsigned __percpu *pcpu_count = ref->pcpu_count;
+	unsigned __percpu *pcpu_count = pcpu_count_ptr(ref);
 	int cpu;
 
-	WARN_ON_ONCE(atomic_read(&ref->count) != 1 + PCPU_COUNT_BIAS);
+	BUG_ON(!pcpu_count);
+	WARN_ON(!percpu_ref_is_zero(ref));
+
+	atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+
+	/*
+	 * Restore per-cpu operation.  smp_store_release() is paired with
+	 * smp_read_barrier_depends() in __pcpu_ref_alive() and guarantees
+	 * that the zeroing is visible to all percpu accesses which can see
+	 * the following PCPU_REF_DEAD clearing.
+	 */
+	for_each_possible_cpu(cpu)
+		*per_cpu_ptr(pcpu_count, cpu) = 0;
+
+	smp_store_release(&ref->pcpu_count_ptr,
+			  ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
+}
+EXPORT_SYMBOL_GPL(percpu_ref_reinit);
+
+/**
+ * percpu_ref_exit - undo percpu_ref_init()
+ * @ref: percpu_ref to exit
+ *
+ * This function exits @ref.  The caller is responsible for ensuring that
+ * @ref is no longer in active use.  The usual places to invoke this
+ * function from are the @ref->release() callback or in init failure path
+ * where percpu_ref_init() succeeded but other parts of the initialization
+ * of the embedding object failed.
+ */
+void percpu_ref_exit(struct percpu_ref *ref)
+{
+	unsigned __percpu *pcpu_count = pcpu_count_ptr(ref);
 
 	if (pcpu_count) {
-		for_each_possible_cpu(cpu)
-			WARN_ON_ONCE(*per_cpu_ptr(pcpu_count, cpu));
-		free_percpu(ref->pcpu_count);
+		free_percpu(pcpu_count);
+		ref->pcpu_count_ptr = PCPU_REF_DEAD;
 	}
 }
-EXPORT_SYMBOL_GPL(percpu_ref_cancel_init);
+EXPORT_SYMBOL_GPL(percpu_ref_exit);
 
 static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 {
 	struct percpu_ref *ref = container_of(rcu, struct percpu_ref, rcu);
-	unsigned __percpu *pcpu_count = ref->pcpu_count;
+	unsigned __percpu *pcpu_count = pcpu_count_ptr(ref);
 	unsigned count = 0;
 	int cpu;
 
-	/* Mask out PCPU_REF_DEAD */
-	pcpu_count = (unsigned __percpu *)
-		(((unsigned long) pcpu_count) & ~PCPU_STATUS_MASK);
-
 	for_each_possible_cpu(cpu)
 		count += *per_cpu_ptr(pcpu_count, cpu);
 
-	free_percpu(pcpu_count);
-
 	pr_debug("global %i pcpu %i", atomic_read(&ref->count), (int) count);
 
 	/*
@@ -152,11 +175,10 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu)
 void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 				 percpu_ref_func_t *confirm_kill)
 {
-	WARN_ONCE(REF_STATUS(ref->pcpu_count) == PCPU_REF_DEAD,
+	WARN_ONCE(ref->pcpu_count_ptr & PCPU_REF_DEAD,
 		  "percpu_ref_kill() called more than once!\n");
 
-	ref->pcpu_count = (unsigned __percpu *)
-		(((unsigned long) ref->pcpu_count)|PCPU_REF_DEAD);
+	ref->pcpu_count_ptr |= PCPU_REF_DEAD;
 	ref->confirm_kill = confirm_kill;
 
 	call_rcu_sched(&ref->rcu, percpu_ref_kill_rcu);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 649d097853a..4abda074ea4 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -86,6 +86,7 @@ static unsigned int io_tlb_index;
  * We need to save away the original address corresponding to a mapped entry
  * for the sync operations.
  */
+#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
 static phys_addr_t *io_tlb_orig_addr;
 
 /*
@@ -188,12 +189,14 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 	io_tlb_list = memblock_virt_alloc(
 				PAGE_ALIGN(io_tlb_nslabs * sizeof(int)),
 				PAGE_SIZE);
-	for (i = 0; i < io_tlb_nslabs; i++)
- 		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
-	io_tlb_index = 0;
 	io_tlb_orig_addr = memblock_virt_alloc(
 				PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)),
 				PAGE_SIZE);
+	for (i = 0; i < io_tlb_nslabs; i++) {
+		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+	}
+	io_tlb_index = 0;
 
 	if (verbose)
 		swiotlb_print_info();
@@ -313,10 +316,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	if (!io_tlb_list)
 		goto cleanup3;
 
-	for (i = 0; i < io_tlb_nslabs; i++)
- 		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
-	io_tlb_index = 0;
-
 	io_tlb_orig_addr = (phys_addr_t *)
 		__get_free_pages(GFP_KERNEL,
 				 get_order(io_tlb_nslabs *
@@ -324,7 +323,11 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 	if (!io_tlb_orig_addr)
 		goto cleanup4;
 
-	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(phys_addr_t));
+	for (i = 0; i < io_tlb_nslabs; i++) {
+		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+	}
+	io_tlb_index = 0;
 
 	swiotlb_print_info();
 
@@ -556,7 +559,8 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	/*
 	 * First, sync the memory before unmapping the entry
 	 */
-	if (orig_addr && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+	if (orig_addr != INVALID_PHYS_ADDR &&
+	    ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
 
 	/*
@@ -573,8 +577,10 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 		 * Step 1: return the slots to the free list, merging the
 		 * slots with superceeding slots
 		 */
-		for (i = index + nslots - 1; i >= index; i--)
+		for (i = index + nslots - 1; i >= index; i--) {
 			io_tlb_list[i] = ++count;
+			io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+		}
 		/*
 		 * Step 2: merge the returned slots with the preceding slots,
 		 * if available (non zero)
@@ -593,6 +599,8 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	phys_addr_t orig_addr = io_tlb_orig_addr[index];
 
+	if (orig_addr == INVALID_PHYS_ADDR)
+		return;
 	orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
 
 	switch (target) {
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
new file mode 100644
index 00000000000..c579e0f5881
--- /dev/null
+++ b/lib/test_bpf.c
@@ -0,0 +1,1929 @@
+/*
+ * Testsuite for BPF interpreter and BPF JIT compiler
+ *
+ * Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/filter.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+
+/* General test specific settings */
+#define MAX_SUBTESTS	3
+#define MAX_TESTRUNS	10000
+#define MAX_DATA	128
+#define MAX_INSNS	512
+#define MAX_K		0xffffFFFF
+
+/* Few constants used to init test 'skb' */
+#define SKB_TYPE	3
+#define SKB_MARK	0x1234aaaa
+#define SKB_HASH	0x1234aaab
+#define SKB_QUEUE_MAP	123
+#define SKB_VLAN_TCI	0xffff
+#define SKB_DEV_IFINDEX	577
+#define SKB_DEV_TYPE	588
+
+/* Redefine REGs to make tests less verbose */
+#define R0		BPF_REG_0
+#define R1		BPF_REG_1
+#define R2		BPF_REG_2
+#define R3		BPF_REG_3
+#define R4		BPF_REG_4
+#define R5		BPF_REG_5
+#define R6		BPF_REG_6
+#define R7		BPF_REG_7
+#define R8		BPF_REG_8
+#define R9		BPF_REG_9
+#define R10		BPF_REG_10
+
+/* Flags that can be passed to test cases */
+#define FLAG_NO_DATA		BIT(0)
+#define FLAG_EXPECTED_FAIL	BIT(1)
+
+enum {
+	CLASSIC  = BIT(6),	/* Old BPF instructions only. */
+	INTERNAL = BIT(7),	/* Extended instruction set.  */
+};
+
+#define TEST_TYPE_MASK		(CLASSIC | INTERNAL)
+
+struct bpf_test {
+	const char *descr;
+	union {
+		struct sock_filter insns[MAX_INSNS];
+		struct sock_filter_int insns_int[MAX_INSNS];
+	} u;
+	__u8 aux;
+	__u8 data[MAX_DATA];
+	struct {
+		int data_size;
+		__u32 result;
+	} test[MAX_SUBTESTS];
+};
+
+static struct bpf_test tests[] = {
+	{
+		"TAX",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_ALU | BPF_NEG, 0), /* A == -3 */
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_LEN, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0), /* X == len - 3 */
+			BPF_STMT(BPF_LD | BPF_B | BPF_IND, 1),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ 10, 20, 30, 40, 50 },
+		{ { 2, 10 }, { 3, 20 }, { 4, 30 } },
+	},
+	{
+		"TXA",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_LEN, 0),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0) /* A == len * 2 */
+		},
+		CLASSIC,
+		{ 10, 20, 30, 40, 50 },
+		{ { 1, 2 }, { 3, 6 }, { 4, 8 } },
+	},
+	{
+		"ADD_SUB_MUL_K",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 1),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 2),
+			BPF_STMT(BPF_LDX | BPF_IMM, 3),
+			BPF_STMT(BPF_ALU | BPF_SUB | BPF_X, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 0xffffffff),
+			BPF_STMT(BPF_ALU | BPF_MUL | BPF_K, 3),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0xfffffffd } }
+	},
+	{
+		"DIV_KX",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 8),
+			BPF_STMT(BPF_ALU | BPF_DIV | BPF_K, 2),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffffffff),
+			BPF_STMT(BPF_ALU | BPF_DIV | BPF_X, 0),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_IMM, 0xffffffff),
+			BPF_STMT(BPF_ALU | BPF_DIV | BPF_K, 0x70000000),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0x40000001 } }
+	},
+	{
+		"AND_OR_LSH_K",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0xff),
+			BPF_STMT(BPF_ALU | BPF_AND | BPF_K, 0xf0),
+			BPF_STMT(BPF_ALU | BPF_LSH | BPF_K, 27),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_IMM, 0xf),
+			BPF_STMT(BPF_ALU | BPF_OR | BPF_K, 0xf0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0x800000ff }, { 1, 0x800000ff } },
+	},
+	{
+		"LD_IMM_0",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 0), /* ld #0 */
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 0),
+			BPF_STMT(BPF_RET | BPF_K, 1),
+		},
+		CLASSIC,
+		{ },
+		{ { 1, 1 } },
+	},
+	{
+		"LD_IND",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_LEN, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_IND, MAX_K),
+			BPF_STMT(BPF_RET | BPF_K, 1)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, 0 }, { 10, 0 }, { 60, 0 } },
+	},
+	{
+		"LD_ABS",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS, 1000),
+			BPF_STMT(BPF_RET | BPF_K, 1)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, 0 }, { 10, 0 }, { 60, 0 } },
+	},
+	{
+		"LD_ABS_LL",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, SKF_LL_OFF),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, SKF_LL_OFF + 1),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ 1, 2, 3 },
+		{ { 1, 0 }, { 2, 3 } },
+	},
+	{
+		"LD_IND_LL",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, SKF_LL_OFF - 1),
+			BPF_STMT(BPF_LDX | BPF_LEN, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_B | BPF_IND, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ 1, 2, 3, 0xff },
+		{ { 1, 1 }, { 3, 3 }, { 4, 0xff } },
+	},
+	{
+		"LD_ABS_NET",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, SKF_NET_OFF),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, SKF_NET_OFF + 1),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 2, 3 },
+		{ { 15, 0 }, { 16, 3 } },
+	},
+	{
+		"LD_IND_NET",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, SKF_NET_OFF - 15),
+			BPF_STMT(BPF_LDX | BPF_LEN, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_B | BPF_IND, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 2, 3 },
+		{ { 14, 0 }, { 15, 1 }, { 17, 3 } },
+	},
+	{
+		"LD_PKTTYPE",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_PKTTYPE),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, SKB_TYPE, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 1),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_PKTTYPE),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, SKB_TYPE, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 1),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_PKTTYPE),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, SKB_TYPE, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 1),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, 3 }, { 10, 3 } },
+	},
+	{
+		"LD_MARK",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_MARK),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, SKB_MARK}, { 10, SKB_MARK} },
+	},
+	{
+		"LD_RXHASH",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_RXHASH),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, SKB_HASH}, { 10, SKB_HASH} },
+	},
+	{
+		"LD_QUEUE",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_QUEUE),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, SKB_QUEUE_MAP }, { 10, SKB_QUEUE_MAP } },
+	},
+	{
+		"LD_PROTOCOL",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 1),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 20, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 0),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_PROTOCOL),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 2),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 30, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 0),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ 10, 20, 30 },
+		{ { 10, ETH_P_IP }, { 100, ETH_P_IP } },
+	},
+	{
+		"LD_VLAN_TAG",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_VLAN_TAG),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{
+			{ 1, SKB_VLAN_TCI & ~VLAN_TAG_PRESENT },
+			{ 10, SKB_VLAN_TCI & ~VLAN_TAG_PRESENT }
+		},
+	},
+	{
+		"LD_VLAN_TAG_PRESENT",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{
+			{ 1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
+			{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
+		},
+	},
+	{
+		"LD_IFINDEX",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_IFINDEX),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, SKB_DEV_IFINDEX }, { 10, SKB_DEV_IFINDEX } },
+	},
+	{
+		"LD_HATYPE",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_HATYPE),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, SKB_DEV_TYPE }, { 10, SKB_DEV_TYPE } },
+	},
+	{
+		"LD_CPU",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_CPU),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_CPU),
+			BPF_STMT(BPF_ALU | BPF_SUB | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, 0 }, { 10, 0 } },
+	},
+	{
+		"LD_NLATTR",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 2),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_LDX | BPF_IMM, 3),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_NLATTR),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+#ifdef __BIG_ENDIAN
+		{ 0xff, 0xff, 0, 4, 0, 2, 0, 4, 0, 3 },
+#else
+		{ 0xff, 0xff, 4, 0, 2, 0, 4, 0, 3, 0 },
+#endif
+		{ { 4, 0 }, { 20, 6 } },
+	},
+	{
+		"LD_NLATTR_NEST",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_LDX | BPF_IMM, 3),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_NLATTR_NEST),
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_NLATTR_NEST),
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_NLATTR_NEST),
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_NLATTR_NEST),
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_NLATTR_NEST),
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_NLATTR_NEST),
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_NLATTR_NEST),
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_NLATTR_NEST),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+#ifdef __BIG_ENDIAN
+		{ 0xff, 0xff, 0, 12, 0, 1, 0, 4, 0, 2, 0, 4, 0, 3 },
+#else
+		{ 0xff, 0xff, 12, 0, 1, 0, 4, 0, 2, 0, 4, 0, 3, 0 },
+#endif
+		{ { 4, 0 }, { 20, 10 } },
+	},
+	{
+		"LD_PAYLOAD_OFF",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_PAY_OFFSET),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_PAY_OFFSET),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_PAY_OFFSET),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_PAY_OFFSET),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_PAY_OFFSET),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		/* 00:00:00:00:00:00 > 00:00:00:00:00:00, ethtype IPv4 (0x0800),
+		 * length 98: 127.0.0.1 > 127.0.0.1: ICMP echo request,
+		 * id 9737, seq 1, length 64
+		 */
+		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		  0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		  0x08, 0x00,
+		  0x45, 0x00, 0x00, 0x54, 0xac, 0x8b, 0x40, 0x00, 0x40,
+		  0x01, 0x90, 0x1b, 0x7f, 0x00, 0x00, 0x01 },
+		{ { 30, 0 }, { 100, 42 } },
+	},
+	{
+		"LD_ANC_XOR",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 10),
+			BPF_STMT(BPF_LDX | BPF_IMM, 300),
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_ALU_XOR_X),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ { 4, 10 ^ 300 }, { 20, 10 ^ 300 } },
+	},
+	{
+		"SPILL_FILL",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_LEN, 0),
+			BPF_STMT(BPF_LD | BPF_IMM, 2),
+			BPF_STMT(BPF_ALU | BPF_RSH, 1),
+			BPF_STMT(BPF_ALU | BPF_XOR | BPF_X, 0),
+			BPF_STMT(BPF_ST, 1), /* M1 = 1 ^ len */
+			BPF_STMT(BPF_ALU | BPF_XOR | BPF_K, 0x80000000),
+			BPF_STMT(BPF_ST, 2), /* M2 = 1 ^ len ^ 0x80000000 */
+			BPF_STMT(BPF_STX, 15), /* M3 = len */
+			BPF_STMT(BPF_LDX | BPF_MEM, 1),
+			BPF_STMT(BPF_LD | BPF_MEM, 2),
+			BPF_STMT(BPF_ALU | BPF_XOR | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 15),
+			BPF_STMT(BPF_ALU | BPF_XOR | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ { 1, 0x80000001 }, { 2, 0x80000002 }, { 60, 0x80000000 ^ 60 } }
+	},
+	{
+		"JEQ",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_LEN, 0),
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 2),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 1),
+			BPF_STMT(BPF_RET | BPF_K, 1),
+			BPF_STMT(BPF_RET | BPF_K, MAX_K)
+		},
+		CLASSIC,
+		{ 3, 3, 3, 3, 3 },
+		{ { 1, 0 }, { 3, 1 }, { 4, MAX_K } },
+	},
+	{
+		"JGT",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_LEN, 0),
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 2),
+			BPF_JUMP(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 1),
+			BPF_STMT(BPF_RET | BPF_K, 1),
+			BPF_STMT(BPF_RET | BPF_K, MAX_K)
+		},
+		CLASSIC,
+		{ 4, 4, 4, 3, 3 },
+		{ { 2, 0 }, { 3, 1 }, { 4, MAX_K } },
+	},
+	{
+		"JGE",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_LEN, 0),
+			BPF_STMT(BPF_LD | BPF_B | BPF_IND, MAX_K),
+			BPF_JUMP(BPF_JMP | BPF_JGE | BPF_K, 1, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 10),
+			BPF_JUMP(BPF_JMP | BPF_JGE | BPF_K, 2, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 20),
+			BPF_JUMP(BPF_JMP | BPF_JGE | BPF_K, 3, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 30),
+			BPF_JUMP(BPF_JMP | BPF_JGE | BPF_K, 4, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 40),
+			BPF_STMT(BPF_RET | BPF_K, MAX_K)
+		},
+		CLASSIC,
+		{ 1, 2, 3, 4, 5 },
+		{ { 1, 20 }, { 3, 40 }, { 5, MAX_K } },
+	},
+	{
+		"JSET",
+		.u.insns = {
+			BPF_JUMP(BPF_JMP | BPF_JA, 0, 0, 0),
+			BPF_JUMP(BPF_JMP | BPF_JA, 1, 1, 1),
+			BPF_JUMP(BPF_JMP | BPF_JA, 0, 0, 0),
+			BPF_JUMP(BPF_JMP | BPF_JA, 0, 0, 0),
+			BPF_STMT(BPF_LDX | BPF_LEN, 0),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_SUB | BPF_K, 4),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_LD | BPF_W | BPF_IND, 0),
+			BPF_JUMP(BPF_JMP | BPF_JSET | BPF_K, 1, 0, 1),
+			BPF_STMT(BPF_RET | BPF_K, 10),
+			BPF_JUMP(BPF_JMP | BPF_JSET | BPF_K, 0x80000000, 0, 1),
+			BPF_STMT(BPF_RET | BPF_K, 20),
+			BPF_JUMP(BPF_JMP | BPF_JSET | BPF_K, 0xffffff, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 30),
+			BPF_JUMP(BPF_JMP | BPF_JSET | BPF_K, 0xffffff, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 30),
+			BPF_JUMP(BPF_JMP | BPF_JSET | BPF_K, 0xffffff, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 30),
+			BPF_JUMP(BPF_JMP | BPF_JSET | BPF_K, 0xffffff, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 30),
+			BPF_JUMP(BPF_JMP | BPF_JSET | BPF_K, 0xffffff, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 30),
+			BPF_STMT(BPF_RET | BPF_K, MAX_K)
+		},
+		CLASSIC,
+		{ 0, 0xAA, 0x55, 1 },
+		{ { 4, 10 }, { 5, 20 }, { 6, MAX_K } },
+	},
+	{
+		"tcpdump port 22",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 12),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x86dd, 0, 8), /* IPv6 */
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 20),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x84, 2, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x6, 1, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x11, 0, 17),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 54),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 22, 14, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 56),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 22, 12, 13),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x0800, 0, 12), /* IPv4 */
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 23),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x84, 2, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x6, 1, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x11, 0, 8),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 20),
+			BPF_JUMP(BPF_JMP | BPF_JSET | BPF_K, 0x1fff, 6, 0),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 14),
+			BPF_STMT(BPF_LD | BPF_H | BPF_IND, 14),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 22, 2, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_IND, 16),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 22, 0, 1),
+			BPF_STMT(BPF_RET | BPF_K, 0xffff),
+			BPF_STMT(BPF_RET | BPF_K, 0),
+		},
+		CLASSIC,
+		/* 3c:07:54:43:e5:76 > 10:bf:48:d6:43:d6, ethertype IPv4(0x0800)
+		 * length 114: 10.1.1.149.49700 > 10.1.2.10.22: Flags [P.],
+		 * seq 1305692979:1305693027, ack 3650467037, win 65535,
+		 * options [nop,nop,TS val 2502645400 ecr 3971138], length 48
+		 */
+		{ 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6,
+		  0x3c, 0x07, 0x54, 0x43, 0xe5, 0x76,
+		  0x08, 0x00,
+		  0x45, 0x10, 0x00, 0x64, 0x75, 0xb5,
+		  0x40, 0x00, 0x40, 0x06, 0xad, 0x2e, /* IP header */
+		  0x0a, 0x01, 0x01, 0x95, /* ip src */
+		  0x0a, 0x01, 0x02, 0x0a, /* ip dst */
+		  0xc2, 0x24,
+		  0x00, 0x16 /* dst port */ },
+		{ { 10, 0 }, { 30, 0 }, { 100, 65535 } },
+	},
+	{
+		"tcpdump complex",
+		.u.insns = {
+			/* tcpdump -nei eth0 'tcp port 22 and (((ip[2:2] -
+			 * ((ip[0]&0xf)<<2)) - ((tcp[12]&0xf0)>>2)) != 0) and
+			 * (len > 115 or len < 30000000000)' -d
+			 */
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 12),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x86dd, 30, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x800, 0, 29),
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 23),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 0x6, 0, 27),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 20),
+			BPF_JUMP(BPF_JMP | BPF_JSET | BPF_K, 0x1fff, 25, 0),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 14),
+			BPF_STMT(BPF_LD | BPF_H | BPF_IND, 14),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 22, 2, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_IND, 16),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 22, 0, 20),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 16),
+			BPF_STMT(BPF_ST, 1),
+			BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 14),
+			BPF_STMT(BPF_ALU | BPF_AND | BPF_K, 0xf),
+			BPF_STMT(BPF_ALU | BPF_LSH | BPF_K, 2),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0x5), /* libpcap emits K on TAX */
+			BPF_STMT(BPF_LD | BPF_MEM, 1),
+			BPF_STMT(BPF_ALU | BPF_SUB | BPF_X, 0),
+			BPF_STMT(BPF_ST, 5),
+			BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 14),
+			BPF_STMT(BPF_LD | BPF_B | BPF_IND, 26),
+			BPF_STMT(BPF_ALU | BPF_AND | BPF_K, 0xf0),
+			BPF_STMT(BPF_ALU | BPF_RSH | BPF_K, 2),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0x9), /* libpcap emits K on TAX */
+			BPF_STMT(BPF_LD | BPF_MEM, 5),
+			BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_X, 0, 4, 0),
+			BPF_STMT(BPF_LD | BPF_LEN, 0),
+			BPF_JUMP(BPF_JMP | BPF_JGT | BPF_K, 0x73, 1, 0),
+			BPF_JUMP(BPF_JMP | BPF_JGE | BPF_K, 0xfc23ac00, 1, 0),
+			BPF_STMT(BPF_RET | BPF_K, 0xffff),
+			BPF_STMT(BPF_RET | BPF_K, 0),
+		},
+		CLASSIC,
+		{ 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6,
+		  0x3c, 0x07, 0x54, 0x43, 0xe5, 0x76,
+		  0x08, 0x00,
+		  0x45, 0x10, 0x00, 0x64, 0x75, 0xb5,
+		  0x40, 0x00, 0x40, 0x06, 0xad, 0x2e, /* IP header */
+		  0x0a, 0x01, 0x01, 0x95, /* ip src */
+		  0x0a, 0x01, 0x02, 0x0a, /* ip dst */
+		  0xc2, 0x24,
+		  0x00, 0x16 /* dst port */ },
+		{ { 10, 0 }, { 30, 0 }, { 100, 65535 } },
+	},
+	{
+		"RET_A",
+		.u.insns = {
+			/* check that unitialized X and A contain zeros */
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0)
+		},
+		CLASSIC,
+		{ },
+		{ {1, 0}, {2, 0} },
+	},
+	{
+		"INT: ADD trivial",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R1, 1),
+			BPF_ALU64_IMM(BPF_ADD, R1, 2),
+			BPF_ALU64_IMM(BPF_MOV, R2, 3),
+			BPF_ALU64_REG(BPF_SUB, R1, R2),
+			BPF_ALU64_IMM(BPF_ADD, R1, -1),
+			BPF_ALU64_IMM(BPF_MUL, R1, 3),
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffd } }
+	},
+	{
+		"INT: MUL_X",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, -1),
+			BPF_ALU64_IMM(BPF_MOV, R1, -1),
+			BPF_ALU64_IMM(BPF_MOV, R2, 3),
+			BPF_ALU64_REG(BPF_MUL, R1, R2),
+			BPF_JMP_IMM(BPF_JEQ, R1, 0xfffffffd, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
+		"INT: MUL_X2",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -1),
+			BPF_ALU32_IMM(BPF_MOV, R1, -1),
+			BPF_ALU32_IMM(BPF_MOV, R2, 3),
+			BPF_ALU64_REG(BPF_MUL, R1, R2),
+			BPF_ALU64_IMM(BPF_RSH, R1, 8),
+			BPF_JMP_IMM(BPF_JEQ, R1, 0x2ffffff, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
+		"INT: MUL32_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -1),
+			BPF_ALU64_IMM(BPF_MOV, R1, -1),
+			BPF_ALU32_IMM(BPF_MOV, R2, 3),
+			BPF_ALU32_REG(BPF_MUL, R1, R2),
+			BPF_ALU64_IMM(BPF_RSH, R1, 8),
+			BPF_JMP_IMM(BPF_JEQ, R1, 0xffffff, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
+		/* Have to test all register combinations, since
+		 * JITing of different registers will produce
+		 * different asm code.
+		 */
+		"INT: ADD 64-bit",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, 0),
+			BPF_ALU64_IMM(BPF_MOV, R1, 1),
+			BPF_ALU64_IMM(BPF_MOV, R2, 2),
+			BPF_ALU64_IMM(BPF_MOV, R3, 3),
+			BPF_ALU64_IMM(BPF_MOV, R4, 4),
+			BPF_ALU64_IMM(BPF_MOV, R5, 5),
+			BPF_ALU64_IMM(BPF_MOV, R6, 6),
+			BPF_ALU64_IMM(BPF_MOV, R7, 7),
+			BPF_ALU64_IMM(BPF_MOV, R8, 8),
+			BPF_ALU64_IMM(BPF_MOV, R9, 9),
+			BPF_ALU64_IMM(BPF_ADD, R0, 20),
+			BPF_ALU64_IMM(BPF_ADD, R1, 20),
+			BPF_ALU64_IMM(BPF_ADD, R2, 20),
+			BPF_ALU64_IMM(BPF_ADD, R3, 20),
+			BPF_ALU64_IMM(BPF_ADD, R4, 20),
+			BPF_ALU64_IMM(BPF_ADD, R5, 20),
+			BPF_ALU64_IMM(BPF_ADD, R6, 20),
+			BPF_ALU64_IMM(BPF_ADD, R7, 20),
+			BPF_ALU64_IMM(BPF_ADD, R8, 20),
+			BPF_ALU64_IMM(BPF_ADD, R9, 20),
+			BPF_ALU64_IMM(BPF_SUB, R0, 10),
+			BPF_ALU64_IMM(BPF_SUB, R1, 10),
+			BPF_ALU64_IMM(BPF_SUB, R2, 10),
+			BPF_ALU64_IMM(BPF_SUB, R3, 10),
+			BPF_ALU64_IMM(BPF_SUB, R4, 10),
+			BPF_ALU64_IMM(BPF_SUB, R5, 10),
+			BPF_ALU64_IMM(BPF_SUB, R6, 10),
+			BPF_ALU64_IMM(BPF_SUB, R7, 10),
+			BPF_ALU64_IMM(BPF_SUB, R8, 10),
+			BPF_ALU64_IMM(BPF_SUB, R9, 10),
+			BPF_ALU64_REG(BPF_ADD, R0, R0),
+			BPF_ALU64_REG(BPF_ADD, R0, R1),
+			BPF_ALU64_REG(BPF_ADD, R0, R2),
+			BPF_ALU64_REG(BPF_ADD, R0, R3),
+			BPF_ALU64_REG(BPF_ADD, R0, R4),
+			BPF_ALU64_REG(BPF_ADD, R0, R5),
+			BPF_ALU64_REG(BPF_ADD, R0, R6),
+			BPF_ALU64_REG(BPF_ADD, R0, R7),
+			BPF_ALU64_REG(BPF_ADD, R0, R8),
+			BPF_ALU64_REG(BPF_ADD, R0, R9), /* R0 == 155 */
+			BPF_JMP_IMM(BPF_JEQ, R0, 155, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_ADD, R1, R0),
+			BPF_ALU64_REG(BPF_ADD, R1, R1),
+			BPF_ALU64_REG(BPF_ADD, R1, R2),
+			BPF_ALU64_REG(BPF_ADD, R1, R3),
+			BPF_ALU64_REG(BPF_ADD, R1, R4),
+			BPF_ALU64_REG(BPF_ADD, R1, R5),
+			BPF_ALU64_REG(BPF_ADD, R1, R6),
+			BPF_ALU64_REG(BPF_ADD, R1, R7),
+			BPF_ALU64_REG(BPF_ADD, R1, R8),
+			BPF_ALU64_REG(BPF_ADD, R1, R9), /* R1 == 456 */
+			BPF_JMP_IMM(BPF_JEQ, R1, 456, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_ADD, R2, R0),
+			BPF_ALU64_REG(BPF_ADD, R2, R1),
+			BPF_ALU64_REG(BPF_ADD, R2, R2),
+			BPF_ALU64_REG(BPF_ADD, R2, R3),
+			BPF_ALU64_REG(BPF_ADD, R2, R4),
+			BPF_ALU64_REG(BPF_ADD, R2, R5),
+			BPF_ALU64_REG(BPF_ADD, R2, R6),
+			BPF_ALU64_REG(BPF_ADD, R2, R7),
+			BPF_ALU64_REG(BPF_ADD, R2, R8),
+			BPF_ALU64_REG(BPF_ADD, R2, R9), /* R2 == 1358 */
+			BPF_JMP_IMM(BPF_JEQ, R2, 1358, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_ADD, R3, R0),
+			BPF_ALU64_REG(BPF_ADD, R3, R1),
+			BPF_ALU64_REG(BPF_ADD, R3, R2),
+			BPF_ALU64_REG(BPF_ADD, R3, R3),
+			BPF_ALU64_REG(BPF_ADD, R3, R4),
+			BPF_ALU64_REG(BPF_ADD, R3, R5),
+			BPF_ALU64_REG(BPF_ADD, R3, R6),
+			BPF_ALU64_REG(BPF_ADD, R3, R7),
+			BPF_ALU64_REG(BPF_ADD, R3, R8),
+			BPF_ALU64_REG(BPF_ADD, R3, R9), /* R3 == 4063 */
+			BPF_JMP_IMM(BPF_JEQ, R3, 4063, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_ADD, R4, R0),
+			BPF_ALU64_REG(BPF_ADD, R4, R1),
+			BPF_ALU64_REG(BPF_ADD, R4, R2),
+			BPF_ALU64_REG(BPF_ADD, R4, R3),
+			BPF_ALU64_REG(BPF_ADD, R4, R4),
+			BPF_ALU64_REG(BPF_ADD, R4, R5),
+			BPF_ALU64_REG(BPF_ADD, R4, R6),
+			BPF_ALU64_REG(BPF_ADD, R4, R7),
+			BPF_ALU64_REG(BPF_ADD, R4, R8),
+			BPF_ALU64_REG(BPF_ADD, R4, R9), /* R4 == 12177 */
+			BPF_JMP_IMM(BPF_JEQ, R4, 12177, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_ADD, R5, R0),
+			BPF_ALU64_REG(BPF_ADD, R5, R1),
+			BPF_ALU64_REG(BPF_ADD, R5, R2),
+			BPF_ALU64_REG(BPF_ADD, R5, R3),
+			BPF_ALU64_REG(BPF_ADD, R5, R4),
+			BPF_ALU64_REG(BPF_ADD, R5, R5),
+			BPF_ALU64_REG(BPF_ADD, R5, R6),
+			BPF_ALU64_REG(BPF_ADD, R5, R7),
+			BPF_ALU64_REG(BPF_ADD, R5, R8),
+			BPF_ALU64_REG(BPF_ADD, R5, R9), /* R5 == 36518 */
+			BPF_JMP_IMM(BPF_JEQ, R5, 36518, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_ADD, R6, R0),
+			BPF_ALU64_REG(BPF_ADD, R6, R1),
+			BPF_ALU64_REG(BPF_ADD, R6, R2),
+			BPF_ALU64_REG(BPF_ADD, R6, R3),
+			BPF_ALU64_REG(BPF_ADD, R6, R4),
+			BPF_ALU64_REG(BPF_ADD, R6, R5),
+			BPF_ALU64_REG(BPF_ADD, R6, R6),
+			BPF_ALU64_REG(BPF_ADD, R6, R7),
+			BPF_ALU64_REG(BPF_ADD, R6, R8),
+			BPF_ALU64_REG(BPF_ADD, R6, R9), /* R6 == 109540 */
+			BPF_JMP_IMM(BPF_JEQ, R6, 109540, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_ADD, R7, R0),
+			BPF_ALU64_REG(BPF_ADD, R7, R1),
+			BPF_ALU64_REG(BPF_ADD, R7, R2),
+			BPF_ALU64_REG(BPF_ADD, R7, R3),
+			BPF_ALU64_REG(BPF_ADD, R7, R4),
+			BPF_ALU64_REG(BPF_ADD, R7, R5),
+			BPF_ALU64_REG(BPF_ADD, R7, R6),
+			BPF_ALU64_REG(BPF_ADD, R7, R7),
+			BPF_ALU64_REG(BPF_ADD, R7, R8),
+			BPF_ALU64_REG(BPF_ADD, R7, R9), /* R7 == 328605 */
+			BPF_JMP_IMM(BPF_JEQ, R7, 328605, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_ADD, R8, R0),
+			BPF_ALU64_REG(BPF_ADD, R8, R1),
+			BPF_ALU64_REG(BPF_ADD, R8, R2),
+			BPF_ALU64_REG(BPF_ADD, R8, R3),
+			BPF_ALU64_REG(BPF_ADD, R8, R4),
+			BPF_ALU64_REG(BPF_ADD, R8, R5),
+			BPF_ALU64_REG(BPF_ADD, R8, R6),
+			BPF_ALU64_REG(BPF_ADD, R8, R7),
+			BPF_ALU64_REG(BPF_ADD, R8, R8),
+			BPF_ALU64_REG(BPF_ADD, R8, R9), /* R8 == 985799 */
+			BPF_JMP_IMM(BPF_JEQ, R8, 985799, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_ADD, R9, R0),
+			BPF_ALU64_REG(BPF_ADD, R9, R1),
+			BPF_ALU64_REG(BPF_ADD, R9, R2),
+			BPF_ALU64_REG(BPF_ADD, R9, R3),
+			BPF_ALU64_REG(BPF_ADD, R9, R4),
+			BPF_ALU64_REG(BPF_ADD, R9, R5),
+			BPF_ALU64_REG(BPF_ADD, R9, R6),
+			BPF_ALU64_REG(BPF_ADD, R9, R7),
+			BPF_ALU64_REG(BPF_ADD, R9, R8),
+			BPF_ALU64_REG(BPF_ADD, R9, R9), /* R9 == 2957380 */
+			BPF_ALU64_REG(BPF_MOV, R0, R9),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2957380 } }
+	},
+	{
+		"INT: ADD 32-bit",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 20),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R2, 2),
+			BPF_ALU32_IMM(BPF_MOV, R3, 3),
+			BPF_ALU32_IMM(BPF_MOV, R4, 4),
+			BPF_ALU32_IMM(BPF_MOV, R5, 5),
+			BPF_ALU32_IMM(BPF_MOV, R6, 6),
+			BPF_ALU32_IMM(BPF_MOV, R7, 7),
+			BPF_ALU32_IMM(BPF_MOV, R8, 8),
+			BPF_ALU32_IMM(BPF_MOV, R9, 9),
+			BPF_ALU64_IMM(BPF_ADD, R1, 10),
+			BPF_ALU64_IMM(BPF_ADD, R2, 10),
+			BPF_ALU64_IMM(BPF_ADD, R3, 10),
+			BPF_ALU64_IMM(BPF_ADD, R4, 10),
+			BPF_ALU64_IMM(BPF_ADD, R5, 10),
+			BPF_ALU64_IMM(BPF_ADD, R6, 10),
+			BPF_ALU64_IMM(BPF_ADD, R7, 10),
+			BPF_ALU64_IMM(BPF_ADD, R8, 10),
+			BPF_ALU64_IMM(BPF_ADD, R9, 10),
+			BPF_ALU32_REG(BPF_ADD, R0, R1),
+			BPF_ALU32_REG(BPF_ADD, R0, R2),
+			BPF_ALU32_REG(BPF_ADD, R0, R3),
+			BPF_ALU32_REG(BPF_ADD, R0, R4),
+			BPF_ALU32_REG(BPF_ADD, R0, R5),
+			BPF_ALU32_REG(BPF_ADD, R0, R6),
+			BPF_ALU32_REG(BPF_ADD, R0, R7),
+			BPF_ALU32_REG(BPF_ADD, R0, R8),
+			BPF_ALU32_REG(BPF_ADD, R0, R9), /* R0 == 155 */
+			BPF_JMP_IMM(BPF_JEQ, R0, 155, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_REG(BPF_ADD, R1, R0),
+			BPF_ALU32_REG(BPF_ADD, R1, R1),
+			BPF_ALU32_REG(BPF_ADD, R1, R2),
+			BPF_ALU32_REG(BPF_ADD, R1, R3),
+			BPF_ALU32_REG(BPF_ADD, R1, R4),
+			BPF_ALU32_REG(BPF_ADD, R1, R5),
+			BPF_ALU32_REG(BPF_ADD, R1, R6),
+			BPF_ALU32_REG(BPF_ADD, R1, R7),
+			BPF_ALU32_REG(BPF_ADD, R1, R8),
+			BPF_ALU32_REG(BPF_ADD, R1, R9), /* R1 == 456 */
+			BPF_JMP_IMM(BPF_JEQ, R1, 456, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_REG(BPF_ADD, R2, R0),
+			BPF_ALU32_REG(BPF_ADD, R2, R1),
+			BPF_ALU32_REG(BPF_ADD, R2, R2),
+			BPF_ALU32_REG(BPF_ADD, R2, R3),
+			BPF_ALU32_REG(BPF_ADD, R2, R4),
+			BPF_ALU32_REG(BPF_ADD, R2, R5),
+			BPF_ALU32_REG(BPF_ADD, R2, R6),
+			BPF_ALU32_REG(BPF_ADD, R2, R7),
+			BPF_ALU32_REG(BPF_ADD, R2, R8),
+			BPF_ALU32_REG(BPF_ADD, R2, R9), /* R2 == 1358 */
+			BPF_JMP_IMM(BPF_JEQ, R2, 1358, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_REG(BPF_ADD, R3, R0),
+			BPF_ALU32_REG(BPF_ADD, R3, R1),
+			BPF_ALU32_REG(BPF_ADD, R3, R2),
+			BPF_ALU32_REG(BPF_ADD, R3, R3),
+			BPF_ALU32_REG(BPF_ADD, R3, R4),
+			BPF_ALU32_REG(BPF_ADD, R3, R5),
+			BPF_ALU32_REG(BPF_ADD, R3, R6),
+			BPF_ALU32_REG(BPF_ADD, R3, R7),
+			BPF_ALU32_REG(BPF_ADD, R3, R8),
+			BPF_ALU32_REG(BPF_ADD, R3, R9), /* R3 == 4063 */
+			BPF_JMP_IMM(BPF_JEQ, R3, 4063, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_REG(BPF_ADD, R4, R0),
+			BPF_ALU32_REG(BPF_ADD, R4, R1),
+			BPF_ALU32_REG(BPF_ADD, R4, R2),
+			BPF_ALU32_REG(BPF_ADD, R4, R3),
+			BPF_ALU32_REG(BPF_ADD, R4, R4),
+			BPF_ALU32_REG(BPF_ADD, R4, R5),
+			BPF_ALU32_REG(BPF_ADD, R4, R6),
+			BPF_ALU32_REG(BPF_ADD, R4, R7),
+			BPF_ALU32_REG(BPF_ADD, R4, R8),
+			BPF_ALU32_REG(BPF_ADD, R4, R9), /* R4 == 12177 */
+			BPF_JMP_IMM(BPF_JEQ, R4, 12177, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_REG(BPF_ADD, R5, R0),
+			BPF_ALU32_REG(BPF_ADD, R5, R1),
+			BPF_ALU32_REG(BPF_ADD, R5, R2),
+			BPF_ALU32_REG(BPF_ADD, R5, R3),
+			BPF_ALU32_REG(BPF_ADD, R5, R4),
+			BPF_ALU32_REG(BPF_ADD, R5, R5),
+			BPF_ALU32_REG(BPF_ADD, R5, R6),
+			BPF_ALU32_REG(BPF_ADD, R5, R7),
+			BPF_ALU32_REG(BPF_ADD, R5, R8),
+			BPF_ALU32_REG(BPF_ADD, R5, R9), /* R5 == 36518 */
+			BPF_JMP_IMM(BPF_JEQ, R5, 36518, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_REG(BPF_ADD, R6, R0),
+			BPF_ALU32_REG(BPF_ADD, R6, R1),
+			BPF_ALU32_REG(BPF_ADD, R6, R2),
+			BPF_ALU32_REG(BPF_ADD, R6, R3),
+			BPF_ALU32_REG(BPF_ADD, R6, R4),
+			BPF_ALU32_REG(BPF_ADD, R6, R5),
+			BPF_ALU32_REG(BPF_ADD, R6, R6),
+			BPF_ALU32_REG(BPF_ADD, R6, R7),
+			BPF_ALU32_REG(BPF_ADD, R6, R8),
+			BPF_ALU32_REG(BPF_ADD, R6, R9), /* R6 == 109540 */
+			BPF_JMP_IMM(BPF_JEQ, R6, 109540, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_REG(BPF_ADD, R7, R0),
+			BPF_ALU32_REG(BPF_ADD, R7, R1),
+			BPF_ALU32_REG(BPF_ADD, R7, R2),
+			BPF_ALU32_REG(BPF_ADD, R7, R3),
+			BPF_ALU32_REG(BPF_ADD, R7, R4),
+			BPF_ALU32_REG(BPF_ADD, R7, R5),
+			BPF_ALU32_REG(BPF_ADD, R7, R6),
+			BPF_ALU32_REG(BPF_ADD, R7, R7),
+			BPF_ALU32_REG(BPF_ADD, R7, R8),
+			BPF_ALU32_REG(BPF_ADD, R7, R9), /* R7 == 328605 */
+			BPF_JMP_IMM(BPF_JEQ, R7, 328605, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_REG(BPF_ADD, R8, R0),
+			BPF_ALU32_REG(BPF_ADD, R8, R1),
+			BPF_ALU32_REG(BPF_ADD, R8, R2),
+			BPF_ALU32_REG(BPF_ADD, R8, R3),
+			BPF_ALU32_REG(BPF_ADD, R8, R4),
+			BPF_ALU32_REG(BPF_ADD, R8, R5),
+			BPF_ALU32_REG(BPF_ADD, R8, R6),
+			BPF_ALU32_REG(BPF_ADD, R8, R7),
+			BPF_ALU32_REG(BPF_ADD, R8, R8),
+			BPF_ALU32_REG(BPF_ADD, R8, R9), /* R8 == 985799 */
+			BPF_JMP_IMM(BPF_JEQ, R8, 985799, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU32_REG(BPF_ADD, R9, R0),
+			BPF_ALU32_REG(BPF_ADD, R9, R1),
+			BPF_ALU32_REG(BPF_ADD, R9, R2),
+			BPF_ALU32_REG(BPF_ADD, R9, R3),
+			BPF_ALU32_REG(BPF_ADD, R9, R4),
+			BPF_ALU32_REG(BPF_ADD, R9, R5),
+			BPF_ALU32_REG(BPF_ADD, R9, R6),
+			BPF_ALU32_REG(BPF_ADD, R9, R7),
+			BPF_ALU32_REG(BPF_ADD, R9, R8),
+			BPF_ALU32_REG(BPF_ADD, R9, R9), /* R9 == 2957380 */
+			BPF_ALU32_REG(BPF_MOV, R0, R9),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 2957380 } }
+	},
+	{	/* Mainly checking JIT here. */
+		"INT: SUB",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, 0),
+			BPF_ALU64_IMM(BPF_MOV, R1, 1),
+			BPF_ALU64_IMM(BPF_MOV, R2, 2),
+			BPF_ALU64_IMM(BPF_MOV, R3, 3),
+			BPF_ALU64_IMM(BPF_MOV, R4, 4),
+			BPF_ALU64_IMM(BPF_MOV, R5, 5),
+			BPF_ALU64_IMM(BPF_MOV, R6, 6),
+			BPF_ALU64_IMM(BPF_MOV, R7, 7),
+			BPF_ALU64_IMM(BPF_MOV, R8, 8),
+			BPF_ALU64_IMM(BPF_MOV, R9, 9),
+			BPF_ALU64_REG(BPF_SUB, R0, R0),
+			BPF_ALU64_REG(BPF_SUB, R0, R1),
+			BPF_ALU64_REG(BPF_SUB, R0, R2),
+			BPF_ALU64_REG(BPF_SUB, R0, R3),
+			BPF_ALU64_REG(BPF_SUB, R0, R4),
+			BPF_ALU64_REG(BPF_SUB, R0, R5),
+			BPF_ALU64_REG(BPF_SUB, R0, R6),
+			BPF_ALU64_REG(BPF_SUB, R0, R7),
+			BPF_ALU64_REG(BPF_SUB, R0, R8),
+			BPF_ALU64_REG(BPF_SUB, R0, R9),
+			BPF_ALU64_IMM(BPF_SUB, R0, 10),
+			BPF_JMP_IMM(BPF_JEQ, R0, -55, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_SUB, R1, R0),
+			BPF_ALU64_REG(BPF_SUB, R1, R2),
+			BPF_ALU64_REG(BPF_SUB, R1, R3),
+			BPF_ALU64_REG(BPF_SUB, R1, R4),
+			BPF_ALU64_REG(BPF_SUB, R1, R5),
+			BPF_ALU64_REG(BPF_SUB, R1, R6),
+			BPF_ALU64_REG(BPF_SUB, R1, R7),
+			BPF_ALU64_REG(BPF_SUB, R1, R8),
+			BPF_ALU64_REG(BPF_SUB, R1, R9),
+			BPF_ALU64_IMM(BPF_SUB, R1, 10),
+			BPF_ALU64_REG(BPF_SUB, R2, R0),
+			BPF_ALU64_REG(BPF_SUB, R2, R1),
+			BPF_ALU64_REG(BPF_SUB, R2, R3),
+			BPF_ALU64_REG(BPF_SUB, R2, R4),
+			BPF_ALU64_REG(BPF_SUB, R2, R5),
+			BPF_ALU64_REG(BPF_SUB, R2, R6),
+			BPF_ALU64_REG(BPF_SUB, R2, R7),
+			BPF_ALU64_REG(BPF_SUB, R2, R8),
+			BPF_ALU64_REG(BPF_SUB, R2, R9),
+			BPF_ALU64_IMM(BPF_SUB, R2, 10),
+			BPF_ALU64_REG(BPF_SUB, R3, R0),
+			BPF_ALU64_REG(BPF_SUB, R3, R1),
+			BPF_ALU64_REG(BPF_SUB, R3, R2),
+			BPF_ALU64_REG(BPF_SUB, R3, R4),
+			BPF_ALU64_REG(BPF_SUB, R3, R5),
+			BPF_ALU64_REG(BPF_SUB, R3, R6),
+			BPF_ALU64_REG(BPF_SUB, R3, R7),
+			BPF_ALU64_REG(BPF_SUB, R3, R8),
+			BPF_ALU64_REG(BPF_SUB, R3, R9),
+			BPF_ALU64_IMM(BPF_SUB, R3, 10),
+			BPF_ALU64_REG(BPF_SUB, R4, R0),
+			BPF_ALU64_REG(BPF_SUB, R4, R1),
+			BPF_ALU64_REG(BPF_SUB, R4, R2),
+			BPF_ALU64_REG(BPF_SUB, R4, R3),
+			BPF_ALU64_REG(BPF_SUB, R4, R5),
+			BPF_ALU64_REG(BPF_SUB, R4, R6),
+			BPF_ALU64_REG(BPF_SUB, R4, R7),
+			BPF_ALU64_REG(BPF_SUB, R4, R8),
+			BPF_ALU64_REG(BPF_SUB, R4, R9),
+			BPF_ALU64_IMM(BPF_SUB, R4, 10),
+			BPF_ALU64_REG(BPF_SUB, R5, R0),
+			BPF_ALU64_REG(BPF_SUB, R5, R1),
+			BPF_ALU64_REG(BPF_SUB, R5, R2),
+			BPF_ALU64_REG(BPF_SUB, R5, R3),
+			BPF_ALU64_REG(BPF_SUB, R5, R4),
+			BPF_ALU64_REG(BPF_SUB, R5, R6),
+			BPF_ALU64_REG(BPF_SUB, R5, R7),
+			BPF_ALU64_REG(BPF_SUB, R5, R8),
+			BPF_ALU64_REG(BPF_SUB, R5, R9),
+			BPF_ALU64_IMM(BPF_SUB, R5, 10),
+			BPF_ALU64_REG(BPF_SUB, R6, R0),
+			BPF_ALU64_REG(BPF_SUB, R6, R1),
+			BPF_ALU64_REG(BPF_SUB, R6, R2),
+			BPF_ALU64_REG(BPF_SUB, R6, R3),
+			BPF_ALU64_REG(BPF_SUB, R6, R4),
+			BPF_ALU64_REG(BPF_SUB, R6, R5),
+			BPF_ALU64_REG(BPF_SUB, R6, R7),
+			BPF_ALU64_REG(BPF_SUB, R6, R8),
+			BPF_ALU64_REG(BPF_SUB, R6, R9),
+			BPF_ALU64_IMM(BPF_SUB, R6, 10),
+			BPF_ALU64_REG(BPF_SUB, R7, R0),
+			BPF_ALU64_REG(BPF_SUB, R7, R1),
+			BPF_ALU64_REG(BPF_SUB, R7, R2),
+			BPF_ALU64_REG(BPF_SUB, R7, R3),
+			BPF_ALU64_REG(BPF_SUB, R7, R4),
+			BPF_ALU64_REG(BPF_SUB, R7, R5),
+			BPF_ALU64_REG(BPF_SUB, R7, R6),
+			BPF_ALU64_REG(BPF_SUB, R7, R8),
+			BPF_ALU64_REG(BPF_SUB, R7, R9),
+			BPF_ALU64_IMM(BPF_SUB, R7, 10),
+			BPF_ALU64_REG(BPF_SUB, R8, R0),
+			BPF_ALU64_REG(BPF_SUB, R8, R1),
+			BPF_ALU64_REG(BPF_SUB, R8, R2),
+			BPF_ALU64_REG(BPF_SUB, R8, R3),
+			BPF_ALU64_REG(BPF_SUB, R8, R4),
+			BPF_ALU64_REG(BPF_SUB, R8, R5),
+			BPF_ALU64_REG(BPF_SUB, R8, R6),
+			BPF_ALU64_REG(BPF_SUB, R8, R7),
+			BPF_ALU64_REG(BPF_SUB, R8, R9),
+			BPF_ALU64_IMM(BPF_SUB, R8, 10),
+			BPF_ALU64_REG(BPF_SUB, R9, R0),
+			BPF_ALU64_REG(BPF_SUB, R9, R1),
+			BPF_ALU64_REG(BPF_SUB, R9, R2),
+			BPF_ALU64_REG(BPF_SUB, R9, R3),
+			BPF_ALU64_REG(BPF_SUB, R9, R4),
+			BPF_ALU64_REG(BPF_SUB, R9, R5),
+			BPF_ALU64_REG(BPF_SUB, R9, R6),
+			BPF_ALU64_REG(BPF_SUB, R9, R7),
+			BPF_ALU64_REG(BPF_SUB, R9, R8),
+			BPF_ALU64_IMM(BPF_SUB, R9, 10),
+			BPF_ALU64_IMM(BPF_SUB, R0, 10),
+			BPF_ALU64_IMM(BPF_NEG, R0, 0),
+			BPF_ALU64_REG(BPF_SUB, R0, R1),
+			BPF_ALU64_REG(BPF_SUB, R0, R2),
+			BPF_ALU64_REG(BPF_SUB, R0, R3),
+			BPF_ALU64_REG(BPF_SUB, R0, R4),
+			BPF_ALU64_REG(BPF_SUB, R0, R5),
+			BPF_ALU64_REG(BPF_SUB, R0, R6),
+			BPF_ALU64_REG(BPF_SUB, R0, R7),
+			BPF_ALU64_REG(BPF_SUB, R0, R8),
+			BPF_ALU64_REG(BPF_SUB, R0, R9),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 11 } }
+	},
+	{	/* Mainly checking JIT here. */
+		"INT: XOR",
+		.u.insns_int = {
+			BPF_ALU64_REG(BPF_SUB, R0, R0),
+			BPF_ALU64_REG(BPF_XOR, R1, R1),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_MOV, R0, 10),
+			BPF_ALU64_IMM(BPF_MOV, R1, -1),
+			BPF_ALU64_REG(BPF_SUB, R1, R1),
+			BPF_ALU64_REG(BPF_XOR, R2, R2),
+			BPF_JMP_REG(BPF_JEQ, R1, R2, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_SUB, R2, R2),
+			BPF_ALU64_REG(BPF_XOR, R3, R3),
+			BPF_ALU64_IMM(BPF_MOV, R0, 10),
+			BPF_ALU64_IMM(BPF_MOV, R1, -1),
+			BPF_JMP_REG(BPF_JEQ, R2, R3, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_SUB, R3, R3),
+			BPF_ALU64_REG(BPF_XOR, R4, R4),
+			BPF_ALU64_IMM(BPF_MOV, R2, 1),
+			BPF_ALU64_IMM(BPF_MOV, R5, -1),
+			BPF_JMP_REG(BPF_JEQ, R3, R4, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_SUB, R4, R4),
+			BPF_ALU64_REG(BPF_XOR, R5, R5),
+			BPF_ALU64_IMM(BPF_MOV, R3, 1),
+			BPF_ALU64_IMM(BPF_MOV, R7, -1),
+			BPF_JMP_REG(BPF_JEQ, R5, R4, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_MOV, R5, 1),
+			BPF_ALU64_REG(BPF_SUB, R5, R5),
+			BPF_ALU64_REG(BPF_XOR, R6, R6),
+			BPF_ALU64_IMM(BPF_MOV, R1, 1),
+			BPF_ALU64_IMM(BPF_MOV, R8, -1),
+			BPF_JMP_REG(BPF_JEQ, R5, R6, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_SUB, R6, R6),
+			BPF_ALU64_REG(BPF_XOR, R7, R7),
+			BPF_JMP_REG(BPF_JEQ, R7, R6, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_SUB, R7, R7),
+			BPF_ALU64_REG(BPF_XOR, R8, R8),
+			BPF_JMP_REG(BPF_JEQ, R7, R8, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_SUB, R8, R8),
+			BPF_ALU64_REG(BPF_XOR, R9, R9),
+			BPF_JMP_REG(BPF_JEQ, R9, R8, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_SUB, R9, R9),
+			BPF_ALU64_REG(BPF_XOR, R0, R0),
+			BPF_JMP_REG(BPF_JEQ, R9, R0, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_SUB, R1, R1),
+			BPF_ALU64_REG(BPF_XOR, R0, R0),
+			BPF_JMP_REG(BPF_JEQ, R9, R0, 2),
+			BPF_ALU64_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{	/* Mainly checking JIT here. */
+		"INT: MUL",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, 11),
+			BPF_ALU64_IMM(BPF_MOV, R1, 1),
+			BPF_ALU64_IMM(BPF_MOV, R2, 2),
+			BPF_ALU64_IMM(BPF_MOV, R3, 3),
+			BPF_ALU64_IMM(BPF_MOV, R4, 4),
+			BPF_ALU64_IMM(BPF_MOV, R5, 5),
+			BPF_ALU64_IMM(BPF_MOV, R6, 6),
+			BPF_ALU64_IMM(BPF_MOV, R7, 7),
+			BPF_ALU64_IMM(BPF_MOV, R8, 8),
+			BPF_ALU64_IMM(BPF_MOV, R9, 9),
+			BPF_ALU64_REG(BPF_MUL, R0, R0),
+			BPF_ALU64_REG(BPF_MUL, R0, R1),
+			BPF_ALU64_REG(BPF_MUL, R0, R2),
+			BPF_ALU64_REG(BPF_MUL, R0, R3),
+			BPF_ALU64_REG(BPF_MUL, R0, R4),
+			BPF_ALU64_REG(BPF_MUL, R0, R5),
+			BPF_ALU64_REG(BPF_MUL, R0, R6),
+			BPF_ALU64_REG(BPF_MUL, R0, R7),
+			BPF_ALU64_REG(BPF_MUL, R0, R8),
+			BPF_ALU64_REG(BPF_MUL, R0, R9),
+			BPF_ALU64_IMM(BPF_MUL, R0, 10),
+			BPF_JMP_IMM(BPF_JEQ, R0, 439084800, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_MUL, R1, R0),
+			BPF_ALU64_REG(BPF_MUL, R1, R2),
+			BPF_ALU64_REG(BPF_MUL, R1, R3),
+			BPF_ALU64_REG(BPF_MUL, R1, R4),
+			BPF_ALU64_REG(BPF_MUL, R1, R5),
+			BPF_ALU64_REG(BPF_MUL, R1, R6),
+			BPF_ALU64_REG(BPF_MUL, R1, R7),
+			BPF_ALU64_REG(BPF_MUL, R1, R8),
+			BPF_ALU64_REG(BPF_MUL, R1, R9),
+			BPF_ALU64_IMM(BPF_MUL, R1, 10),
+			BPF_ALU64_REG(BPF_MOV, R2, R1),
+			BPF_ALU64_IMM(BPF_RSH, R2, 32),
+			BPF_JMP_IMM(BPF_JEQ, R2, 0x5a924, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_LSH, R1, 32),
+			BPF_ALU64_IMM(BPF_ARSH, R1, 32),
+			BPF_JMP_IMM(BPF_JEQ, R1, 0xebb90000, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_REG(BPF_MUL, R2, R0),
+			BPF_ALU64_REG(BPF_MUL, R2, R1),
+			BPF_ALU64_REG(BPF_MUL, R2, R3),
+			BPF_ALU64_REG(BPF_MUL, R2, R4),
+			BPF_ALU64_REG(BPF_MUL, R2, R5),
+			BPF_ALU64_REG(BPF_MUL, R2, R6),
+			BPF_ALU64_REG(BPF_MUL, R2, R7),
+			BPF_ALU64_REG(BPF_MUL, R2, R8),
+			BPF_ALU64_REG(BPF_MUL, R2, R9),
+			BPF_ALU64_IMM(BPF_MUL, R2, 10),
+			BPF_ALU64_IMM(BPF_RSH, R2, 32),
+			BPF_ALU64_REG(BPF_MOV, R0, R2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x35d97ef2 } }
+	},
+	{
+		"INT: ALU MIX",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, 11),
+			BPF_ALU64_IMM(BPF_ADD, R0, -1),
+			BPF_ALU64_IMM(BPF_MOV, R2, 2),
+			BPF_ALU64_IMM(BPF_XOR, R2, 3),
+			BPF_ALU64_REG(BPF_DIV, R0, R2),
+			BPF_JMP_IMM(BPF_JEQ, R0, 10, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_MOD, R0, 3),
+			BPF_JMP_IMM(BPF_JEQ, R0, 1, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_MOV, R0, -1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } }
+	},
+	{
+		"INT: DIV + ABS",
+		.u.insns_int = {
+			BPF_ALU64_REG(BPF_MOV, R6, R1),
+			BPF_LD_ABS(BPF_B, 3),
+			BPF_ALU64_IMM(BPF_MOV, R2, 2),
+			BPF_ALU32_REG(BPF_DIV, R0, R2),
+			BPF_ALU64_REG(BPF_MOV, R8, R0),
+			BPF_LD_ABS(BPF_B, 4),
+			BPF_ALU64_REG(BPF_ADD, R8, R0),
+			BPF_LD_IND(BPF_B, R8, -70),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ 10, 20, 30, 40, 50 },
+		{ { 4, 0 }, { 5, 10 } }
+	},
+	{
+		"INT: DIV by zero",
+		.u.insns_int = {
+			BPF_ALU64_REG(BPF_MOV, R6, R1),
+			BPF_ALU64_IMM(BPF_MOV, R7, 0),
+			BPF_LD_ABS(BPF_B, 3),
+			BPF_ALU32_REG(BPF_DIV, R0, R7),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ 10, 20, 30, 40, 50 },
+		{ { 3, 0 }, { 4, 0 } }
+	},
+	{
+		"check: missing ret",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_IMM, 1),
+		},
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+		{ },
+		{ }
+	},
+	{
+		"check: div_k_0",
+		.u.insns = {
+			BPF_STMT(BPF_ALU | BPF_DIV | BPF_K, 0),
+			BPF_STMT(BPF_RET | BPF_K, 0)
+		},
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+		{ },
+		{ }
+	},
+	{
+		"check: unknown insn",
+		.u.insns = {
+			/* seccomp insn, rejected in socket filter */
+			BPF_STMT(BPF_LDX | BPF_W | BPF_ABS, 0),
+			BPF_STMT(BPF_RET | BPF_K, 0)
+		},
+		CLASSIC | FLAG_EXPECTED_FAIL,
+		{ },
+		{ }
+	},
+	{
+		"check: out of range spill/fill",
+		.u.insns = {
+			BPF_STMT(BPF_STX, 16),
+			BPF_STMT(BPF_RET | BPF_K, 0)
+		},
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+		{ },
+		{ }
+	},
+	{
+		"JUMPS + HOLES",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_JUMP(BPF_JMP | BPF_JGE, 0, 13, 15),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ, 0x90c2894d, 3, 4),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ, 0x90c2894d, 1, 2),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_JUMP(BPF_JMP | BPF_JGE, 0, 14, 15),
+			BPF_JUMP(BPF_JMP | BPF_JGE, 0, 13, 14),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ, 0x2ac28349, 2, 3),
+			BPF_JUMP(BPF_JMP | BPF_JEQ, 0x2ac28349, 1, 2),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_JUMP(BPF_JMP | BPF_JGE, 0, 14, 15),
+			BPF_JUMP(BPF_JMP | BPF_JGE, 0, 13, 14),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_JUMP(BPF_JMP | BPF_JEQ, 0x90d2ff41, 2, 3),
+			BPF_JUMP(BPF_JMP | BPF_JEQ, 0x90d2ff41, 1, 2),
+			BPF_STMT(BPF_LD | BPF_H | BPF_ABS, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0),
+		},
+		CLASSIC,
+		{ 0x00, 0x1b, 0x21, 0x3c, 0x9d, 0xf8,
+		  0x90, 0xe2, 0xba, 0x0a, 0x56, 0xb4,
+		  0x08, 0x00,
+		  0x45, 0x00, 0x00, 0x28, 0x00, 0x00,
+		  0x20, 0x00, 0x40, 0x11, 0x00, 0x00, /* IP header */
+		  0xc0, 0xa8, 0x33, 0x01,
+		  0xc0, 0xa8, 0x33, 0x02,
+		  0xbb, 0xb6,
+		  0xa9, 0xfa,
+		  0x00, 0x14, 0x00, 0x00,
+		  0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc,
+		  0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc,
+		  0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc,
+		  0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc,
+		  0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc,
+		  0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc,
+		  0xcc, 0xcc, 0xcc, 0xcc, 0xcc, 0xcc,
+		  0xcc, 0xcc, 0xcc, 0xcc },
+		{ { 88, 0x001b } }
+	},
+	{
+		"check: RET X",
+		.u.insns = {
+			BPF_STMT(BPF_RET | BPF_X, 0),
+		},
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+		{ },
+		{ },
+	},
+	{
+		"check: LDX + RET X",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 42),
+			BPF_STMT(BPF_RET | BPF_X, 0),
+		},
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+		{ },
+		{ },
+	},
+	{	/* Mainly checking JIT here. */
+		"M[]: alt STX + LDX",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 100),
+			BPF_STMT(BPF_STX, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 0),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 1),
+			BPF_STMT(BPF_LDX | BPF_MEM, 1),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 2),
+			BPF_STMT(BPF_LDX | BPF_MEM, 2),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 3),
+			BPF_STMT(BPF_LDX | BPF_MEM, 3),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 4),
+			BPF_STMT(BPF_LDX | BPF_MEM, 4),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 5),
+			BPF_STMT(BPF_LDX | BPF_MEM, 5),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 6),
+			BPF_STMT(BPF_LDX | BPF_MEM, 6),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 7),
+			BPF_STMT(BPF_LDX | BPF_MEM, 7),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 8),
+			BPF_STMT(BPF_LDX | BPF_MEM, 8),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 9),
+			BPF_STMT(BPF_LDX | BPF_MEM, 9),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 10),
+			BPF_STMT(BPF_LDX | BPF_MEM, 10),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 11),
+			BPF_STMT(BPF_LDX | BPF_MEM, 11),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 12),
+			BPF_STMT(BPF_LDX | BPF_MEM, 12),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 13),
+			BPF_STMT(BPF_LDX | BPF_MEM, 13),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 14),
+			BPF_STMT(BPF_LDX | BPF_MEM, 14),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_STX, 15),
+			BPF_STMT(BPF_LDX | BPF_MEM, 15),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 1),
+			BPF_STMT(BPF_MISC | BPF_TAX, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 116 } },
+	},
+	{	/* Mainly checking JIT here. */
+		"M[]: full STX + full LDX",
+		.u.insns = {
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xbadfeedb),
+			BPF_STMT(BPF_STX, 0),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xecabedae),
+			BPF_STMT(BPF_STX, 1),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xafccfeaf),
+			BPF_STMT(BPF_STX, 2),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xbffdcedc),
+			BPF_STMT(BPF_STX, 3),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xfbbbdccb),
+			BPF_STMT(BPF_STX, 4),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xfbabcbda),
+			BPF_STMT(BPF_STX, 5),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xaedecbdb),
+			BPF_STMT(BPF_STX, 6),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xadebbade),
+			BPF_STMT(BPF_STX, 7),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xfcfcfaec),
+			BPF_STMT(BPF_STX, 8),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xbcdddbdc),
+			BPF_STMT(BPF_STX, 9),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xfeefdfac),
+			BPF_STMT(BPF_STX, 10),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xcddcdeea),
+			BPF_STMT(BPF_STX, 11),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xaccfaebb),
+			BPF_STMT(BPF_STX, 12),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xbdcccdcf),
+			BPF_STMT(BPF_STX, 13),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xaaedecde),
+			BPF_STMT(BPF_STX, 14),
+			BPF_STMT(BPF_LDX | BPF_IMM, 0xfaeacdad),
+			BPF_STMT(BPF_STX, 15),
+			BPF_STMT(BPF_LDX | BPF_MEM, 0),
+			BPF_STMT(BPF_MISC | BPF_TXA, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 1),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 2),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 3),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 4),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 5),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 6),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 7),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 8),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 9),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 10),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 11),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 12),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 13),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 14),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_LDX | BPF_MEM, 15),
+			BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0),
+			BPF_STMT(BPF_RET | BPF_A, 0),
+		},
+		CLASSIC | FLAG_NO_DATA,
+		{ },
+		{ { 0, 0x2a5a5e5 } },
+	},
+	{
+		"check: SKF_AD_MAX",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF + SKF_AD_MAX),
+			BPF_STMT(BPF_RET | BPF_A, 0),
+		},
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+		{ },
+		{ },
+	},
+	{	/* Passes checker but fails during runtime. */
+		"LD [SKF_AD_OFF-1]",
+		.u.insns = {
+			BPF_STMT(BPF_LD | BPF_W | BPF_ABS,
+				 SKF_AD_OFF - 1),
+			BPF_STMT(BPF_RET | BPF_K, 1),
+		},
+		CLASSIC,
+		{ },
+		{ { 1, 0 } },
+	},
+};
+
+static struct net_device dev;
+
+static struct sk_buff *populate_skb(char *buf, int size)
+{
+	struct sk_buff *skb;
+
+	if (size >= MAX_DATA)
+		return NULL;
+
+	skb = alloc_skb(MAX_DATA, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	memcpy(__skb_put(skb, size), buf, size);
+
+	/* Initialize a fake skb with test pattern. */
+	skb_reset_mac_header(skb);
+	skb->protocol = htons(ETH_P_IP);
+	skb->pkt_type = SKB_TYPE;
+	skb->mark = SKB_MARK;
+	skb->hash = SKB_HASH;
+	skb->queue_mapping = SKB_QUEUE_MAP;
+	skb->vlan_tci = SKB_VLAN_TCI;
+	skb->dev = &dev;
+	skb->dev->ifindex = SKB_DEV_IFINDEX;
+	skb->dev->type = SKB_DEV_TYPE;
+	skb_set_network_header(skb, min(size, ETH_HLEN));
+
+	return skb;
+}
+
+static void *generate_test_data(struct bpf_test *test, int sub)
+{
+	if (test->aux & FLAG_NO_DATA)
+		return NULL;
+
+	/* Test case expects an skb, so populate one. Various
+	 * subtests generate skbs of different sizes based on
+	 * the same data.
+	 */
+	return populate_skb(test->data, test->test[sub].data_size);
+}
+
+static void release_test_data(const struct bpf_test *test, void *data)
+{
+	if (test->aux & FLAG_NO_DATA)
+		return;
+
+	kfree_skb(data);
+}
+
+static int probe_filter_length(struct sock_filter *fp)
+{
+	int len = 0;
+
+	for (len = MAX_INSNS - 1; len > 0; --len)
+		if (fp[len].code != 0 || fp[len].k != 0)
+			break;
+
+	return len + 1;
+}
+
+static struct sk_filter *generate_filter(int which, int *err)
+{
+	struct sk_filter *fp;
+	struct sock_fprog_kern fprog;
+	unsigned int flen = probe_filter_length(tests[which].u.insns);
+	__u8 test_type = tests[which].aux & TEST_TYPE_MASK;
+
+	switch (test_type) {
+	case CLASSIC:
+		fprog.filter = tests[which].u.insns;
+		fprog.len = flen;
+
+		*err = sk_unattached_filter_create(&fp, &fprog);
+		if (tests[which].aux & FLAG_EXPECTED_FAIL) {
+			if (*err == -EINVAL) {
+				pr_cont("PASS\n");
+				/* Verifier rejected filter as expected. */
+				*err = 0;
+				return NULL;
+			} else {
+				pr_cont("UNEXPECTED_PASS\n");
+				/* Verifier didn't reject the test that's
+				 * bad enough, just return!
+				 */
+				*err = -EINVAL;
+				return NULL;
+			}
+		}
+		/* We don't expect to fail. */
+		if (*err) {
+			pr_cont("FAIL to attach err=%d len=%d\n",
+				*err, fprog.len);
+			return NULL;
+		}
+		break;
+
+	case INTERNAL:
+		fp = kzalloc(sk_filter_size(flen), GFP_KERNEL);
+		if (fp == NULL) {
+			pr_cont("UNEXPECTED_FAIL no memory left\n");
+			*err = -ENOMEM;
+			return NULL;
+		}
+
+		fp->len = flen;
+		memcpy(fp->insnsi, tests[which].u.insns_int,
+		       fp->len * sizeof(struct sock_filter_int));
+
+		sk_filter_select_runtime(fp);
+		break;
+	}
+
+	*err = 0;
+	return fp;
+}
+
+static void release_filter(struct sk_filter *fp, int which)
+{
+	__u8 test_type = tests[which].aux & TEST_TYPE_MASK;
+
+	switch (test_type) {
+	case CLASSIC:
+		sk_unattached_filter_destroy(fp);
+		break;
+	case INTERNAL:
+		sk_filter_free(fp);
+		break;
+	}
+}
+
+static int __run_one(const struct sk_filter *fp, const void *data,
+		     int runs, u64 *duration)
+{
+	u64 start, finish;
+	int ret, i;
+
+	start = ktime_to_us(ktime_get());
+
+	for (i = 0; i < runs; i++)
+		ret = SK_RUN_FILTER(fp, data);
+
+	finish = ktime_to_us(ktime_get());
+
+	*duration = (finish - start) * 1000ULL;
+	do_div(*duration, runs);
+
+	return ret;
+}
+
+static int run_one(const struct sk_filter *fp, struct bpf_test *test)
+{
+	int err_cnt = 0, i, runs = MAX_TESTRUNS;
+
+	for (i = 0; i < MAX_SUBTESTS; i++) {
+		void *data;
+		u64 duration;
+		u32 ret;
+
+		if (test->test[i].data_size == 0 &&
+		    test->test[i].result == 0)
+			break;
+
+		data = generate_test_data(test, i);
+		ret = __run_one(fp, data, runs, &duration);
+		release_test_data(test, data);
+
+		if (ret == test->test[i].result) {
+			pr_cont("%lld ", duration);
+		} else {
+			pr_cont("ret %d != %d ", ret,
+				test->test[i].result);
+			err_cnt++;
+		}
+	}
+
+	return err_cnt;
+}
+
+static __init int test_bpf(void)
+{
+	int i, err_cnt = 0, pass_cnt = 0;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		struct sk_filter *fp;
+		int err;
+
+		pr_info("#%d %s ", i, tests[i].descr);
+
+		fp = generate_filter(i, &err);
+		if (fp == NULL) {
+			if (err == 0) {
+				pass_cnt++;
+				continue;
+			}
+
+			return err;
+		}
+		err = run_one(fp, &tests[i]);
+		release_filter(fp, i);
+
+		if (err) {
+			pr_cont("FAIL (%d times)\n", err);
+			err_cnt++;
+		} else {
+			pr_cont("PASS\n");
+			pass_cnt++;
+		}
+	}
+
+	pr_info("Summary: %d PASSED, %d FAILED\n", pass_cnt, err_cnt);
+	return err_cnt ? -EINVAL : 0;
+}
+
+static int __init test_bpf_init(void)
+{
+	return test_bpf();
+}
+
+static void __exit test_bpf_exit(void)
+{
+}
+
+module_init(test_bpf_init);
+module_exit(test_bpf_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/mm/filemap.c b/mm/filemap.c
index 7fadf1c6283..65d44fd88c7 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -241,18 +241,6 @@ void delete_from_page_cache(struct page *page)
 }
 EXPORT_SYMBOL(delete_from_page_cache);
 
-static int sleep_on_page(void *word)
-{
-	io_schedule();
-	return 0;
-}
-
-static int sleep_on_page_killable(void *word)
-{
-	sleep_on_page(word);
-	return fatal_signal_pending(current) ? -EINTR : 0;
-}
-
 static int filemap_check_errors(struct address_space *mapping)
 {
 	int ret = 0;
@@ -692,7 +680,7 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
 
 	if (test_bit(bit_nr, &page->flags))
-		__wait_on_bit(page_waitqueue(page), &wait, sleep_on_page,
+		__wait_on_bit(page_waitqueue(page), &wait, bit_wait_io,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(wait_on_page_bit);
@@ -705,7 +693,7 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr)
 		return 0;
 
 	return __wait_on_bit(page_waitqueue(page), &wait,
-			     sleep_on_page_killable, TASK_KILLABLE);
+			     bit_wait_io, TASK_KILLABLE);
 }
 
 /**
@@ -806,7 +794,7 @@ void __lock_page(struct page *page)
 {
 	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
 
-	__wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page,
+	__wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io,
 							TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_page);
@@ -816,7 +804,7 @@ int __lock_page_killable(struct page *page)
 	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
 
 	return __wait_on_bit_lock(page_waitqueue(page), &wait,
-					sleep_on_page_killable, TASK_KILLABLE);
+					bit_wait_io, TASK_KILLABLE);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
@@ -1031,18 +1019,21 @@ EXPORT_SYMBOL(find_lock_entry);
  * @mapping: the address_space to search
  * @offset: the page index
  * @fgp_flags: PCG flags
- * @gfp_mask: gfp mask to use if a page is to be allocated
+ * @cache_gfp_mask: gfp mask to use for the page cache data page allocation
+ * @radix_gfp_mask: gfp mask to use for radix tree node allocation
  *
  * Looks up the page cache slot at @mapping & @offset.
  *
- * PCG flags modify how the page is returned
+ * PCG flags modify how the page is returned.
  *
  * FGP_ACCESSED: the page will be marked accessed
  * FGP_LOCK: Page is return locked
  * FGP_CREAT: If page is not present then a new page is allocated using
- *		@gfp_mask and added to the page cache and the VM's LRU
- *		list. The page is returned locked and with an increased
- *		refcount. Otherwise, %NULL is returned.
+ *		@cache_gfp_mask and added to the page cache and the VM's LRU
+ *		list. If radix tree nodes are allocated during page cache
+ *		insertion then @radix_gfp_mask is used. The page is returned
+ *		locked and with an increased refcount. Otherwise, %NULL is
+ *		returned.
  *
  * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even
  * if the GFP flags specified for FGP_CREAT are atomic.
@@ -1665,96 +1656,42 @@ out:
 	return written ? written : error;
 }
 
-/*
- * Performs necessary checks before doing a write
- * @iov:	io vector request
- * @nr_segs:	number of segments in the iovec
- * @count:	number of bytes to write
- * @access_flags: type of access: %VERIFY_READ or %VERIFY_WRITE
- *
- * Adjust number of segments and amount of bytes to write (nr_segs should be
- * properly initialized first). Returns appropriate error code that caller
- * should return or zero in case that write should be allowed.
- */
-int generic_segment_checks(const struct iovec *iov,
-			unsigned long *nr_segs, size_t *count, int access_flags)
-{
-	unsigned long   seg;
-	size_t cnt = 0;
-	for (seg = 0; seg < *nr_segs; seg++) {
-		const struct iovec *iv = &iov[seg];
-
-		/*
-		 * If any segment has a negative length, or the cumulative
-		 * length ever wraps negative then return -EINVAL.
-		 */
-		cnt += iv->iov_len;
-		if (unlikely((ssize_t)(cnt|iv->iov_len) < 0))
-			return -EINVAL;
-		if (access_ok(access_flags, iv->iov_base, iv->iov_len))
-			continue;
-		if (seg == 0)
-			return -EFAULT;
-		*nr_segs = seg;
-		cnt -= iv->iov_len;	/* This segment is no good */
-		break;
-	}
-	*count = cnt;
-	return 0;
-}
-EXPORT_SYMBOL(generic_segment_checks);
-
 /**
- * generic_file_aio_read - generic filesystem read routine
+ * generic_file_read_iter - generic filesystem read routine
  * @iocb:	kernel I/O control block
- * @iov:	io vector request
- * @nr_segs:	number of segments in the iovec
- * @pos:	current file position
+ * @iter:	destination for the data read
  *
- * This is the "read()" routine for all filesystems
+ * This is the "read_iter()" routine for all filesystems
  * that can use the page cache directly.
  */
 ssize_t
-generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos)
+generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	struct file *filp = iocb->ki_filp;
-	ssize_t retval;
-	size_t count;
+	struct file *file = iocb->ki_filp;
+	ssize_t retval = 0;
 	loff_t *ppos = &iocb->ki_pos;
-	struct iov_iter i;
-
-	count = 0;
-	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
-	if (retval)
-		return retval;
-	iov_iter_init(&i, iov, nr_segs, count, 0);
+	loff_t pos = *ppos;
 
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
-	if (filp->f_flags & O_DIRECT) {
+	if (file->f_flags & O_DIRECT) {
+		struct address_space *mapping = file->f_mapping;
+		struct inode *inode = mapping->host;
+		size_t count = iov_iter_count(iter);
 		loff_t size;
-		struct address_space *mapping;
-		struct inode *inode;
 
-		mapping = filp->f_mapping;
-		inode = mapping->host;
 		if (!count)
 			goto out; /* skip atime */
 		size = i_size_read(inode);
 		retval = filemap_write_and_wait_range(mapping, pos,
-					pos + iov_length(iov, nr_segs) - 1);
+					pos + count - 1);
 		if (!retval) {
-			retval = mapping->a_ops->direct_IO(READ, iocb,
-							   iov, pos, nr_segs);
+			struct iov_iter data = *iter;
+			retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos);
 		}
+
 		if (retval > 0) {
 			*ppos = pos + retval;
-			count -= retval;
-			/*
-			 * If we did a short DIO read we need to skip the
-			 * section of the iov that we've already read data into.
-			 */
-			iov_iter_advance(&i, retval);
+			iov_iter_advance(iter, retval);
 		}
 
 		/*
@@ -1765,17 +1702,17 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		 * and return.  Otherwise fallthrough to buffered io for
 		 * the rest of the read.
 		 */
-		if (retval < 0 || !count || *ppos >= size) {
-			file_accessed(filp);
+		if (retval < 0 || !iov_iter_count(iter) || *ppos >= size) {
+			file_accessed(file);
 			goto out;
 		}
 	}
 
-	retval = do_generic_file_read(filp, ppos, &i, retval);
+	retval = do_generic_file_read(file, ppos, iter, retval);
 out:
 	return retval;
 }
-EXPORT_SYMBOL(generic_file_aio_read);
+EXPORT_SYMBOL(generic_file_read_iter);
 
 #ifdef CONFIG_MMU
 /**
@@ -2386,9 +2323,7 @@ int pagecache_write_end(struct file *file, struct address_space *mapping,
 EXPORT_SYMBOL(pagecache_write_end);
 
 ssize_t
-generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long *nr_segs, loff_t pos,
-		size_t count, size_t ocount)
+generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
 {
 	struct file	*file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
@@ -2396,11 +2331,9 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t		written;
 	size_t		write_len;
 	pgoff_t		end;
+	struct iov_iter data;
 
-	if (count != ocount)
-		*nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count);
-
-	write_len = iov_length(iov, *nr_segs);
+	write_len = iov_iter_count(from);
 	end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT;
 
 	written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
@@ -2427,7 +2360,8 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 		}
 	}
 
-	written = mapping->a_ops->direct_IO(WRITE, iocb, iov, pos, *nr_segs);
+	data = *from;
+	written = mapping->a_ops->direct_IO(WRITE, iocb, &data, pos);
 
 	/*
 	 * Finally, try again to invalidate clean pages which might have been
@@ -2444,6 +2378,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 
 	if (written > 0) {
 		pos += written;
+		iov_iter_advance(from, written);
 		if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
 			i_size_write(inode, pos);
 			mark_inode_dirty(inode);
@@ -2568,10 +2503,9 @@ again:
 EXPORT_SYMBOL(generic_perform_write);
 
 /**
- * __generic_file_aio_write - write data to a file
+ * __generic_file_write_iter - write data to a file
  * @iocb:	IO state structure (file, offset, etc.)
- * @iov:	vector with data to write
- * @nr_segs:	number of segments in the vector
+ * @from:	iov_iter with data to write
  *
  * This function does all the work needed for actually writing data to a
  * file. It does all basic checks, removes SUID from the file, updates
@@ -2585,26 +2519,16 @@ EXPORT_SYMBOL(generic_perform_write);
  * A caller has to handle it. This is mainly due to the fact that we want to
  * avoid syncing under i_mutex.
  */
-ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				 unsigned long nr_segs)
+ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space * mapping = file->f_mapping;
-	size_t ocount;		/* original count */
-	size_t count;		/* after file limit checks */
 	struct inode 	*inode = mapping->host;
 	loff_t		pos = iocb->ki_pos;
 	ssize_t		written = 0;
 	ssize_t		err;
 	ssize_t		status;
-	struct iov_iter from;
-
-	ocount = 0;
-	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
-	if (err)
-		return err;
-
-	count = ocount;
+	size_t		count = iov_iter_count(from);
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
@@ -2615,6 +2539,8 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (count == 0)
 		goto out;
 
+	iov_iter_truncate(from, count);
+
 	err = file_remove_suid(file);
 	if (err)
 		goto out;
@@ -2623,17 +2549,13 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (err)
 		goto out;
 
-	iov_iter_init(&from, iov, nr_segs, count, 0);
-
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (unlikely(file->f_flags & O_DIRECT)) {
 		loff_t endbyte;
 
-		written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos,
-							count, ocount);
+		written = generic_file_direct_write(iocb, from, pos);
 		if (written < 0 || written == count)
 			goto out;
-		iov_iter_advance(&from, written);
 
 		/*
 		 * direct-io write to a hole: fall through to buffered I/O
@@ -2642,7 +2564,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		pos += written;
 		count -= written;
 
-		status = generic_perform_write(file, &from, pos);
+		status = generic_perform_write(file, from, pos);
 		/*
 		 * If generic_perform_write() returned a synchronous error
 		 * then we want to return the number of bytes which were
@@ -2674,7 +2596,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			 */
 		}
 	} else {
-		written = generic_perform_write(file, &from, pos);
+		written = generic_perform_write(file, from, pos);
 		if (likely(written >= 0))
 			iocb->ki_pos = pos + written;
 	}
@@ -2682,30 +2604,25 @@ out:
 	current->backing_dev_info = NULL;
 	return written ? written : err;
 }
-EXPORT_SYMBOL(__generic_file_aio_write);
+EXPORT_SYMBOL(__generic_file_write_iter);
 
 /**
- * generic_file_aio_write - write data to a file
+ * generic_file_write_iter - write data to a file
  * @iocb:	IO state structure
- * @iov:	vector with data to write
- * @nr_segs:	number of segments in the vector
- * @pos:	position in file where to write
+ * @from:	iov_iter with data to write
  *
- * This is a wrapper around __generic_file_aio_write() to be used by most
+ * This is a wrapper around __generic_file_write_iter() to be used by most
  * filesystems. It takes care of syncing the file in case of O_SYNC file
  * and acquires i_mutex as needed.
  */
-ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos)
+ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	ssize_t ret;
 
-	BUG_ON(iocb->ki_pos != pos);
-
 	mutex_lock(&inode->i_mutex);
-	ret = __generic_file_aio_write(iocb, iov, nr_segs);
+	ret = __generic_file_write_iter(iocb, from);
 	mutex_unlock(&inode->i_mutex);
 
 	if (ret > 0) {
@@ -2717,7 +2634,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	}
 	return ret;
 }
-EXPORT_SYMBOL(generic_file_aio_write);
+EXPORT_SYMBOL(generic_file_write_iter);
 
 /**
  * try_to_release_page() - release old fs-specific metadata on a page
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e60837dc785..33514d88fef 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -941,6 +941,37 @@ unlock:
 	spin_unlock(ptl);
 }
 
+/*
+ * Save CONFIG_DEBUG_PAGEALLOC from faulting falsely on tail pages
+ * during copy_user_huge_page()'s copy_page_rep(): in the case when
+ * the source page gets split and a tail freed before copy completes.
+ * Called under pmd_lock of checked pmd, so safe from splitting itself.
+ */
+static void get_user_huge_page(struct page *page)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
+		struct page *endpage = page + HPAGE_PMD_NR;
+
+		atomic_add(HPAGE_PMD_NR, &page->_count);
+		while (++page < endpage)
+			get_huge_page_tail(page);
+	} else {
+		get_page(page);
+	}
+}
+
+static void put_user_huge_page(struct page *page)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) {
+		struct page *endpage = page + HPAGE_PMD_NR;
+
+		while (page < endpage)
+			put_page(page++);
+	} else {
+		put_page(page);
+	}
+}
+
 static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long address,
@@ -1074,7 +1105,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		ret |= VM_FAULT_WRITE;
 		goto out_unlock;
 	}
-	get_page(page);
+	get_user_huge_page(page);
 	spin_unlock(ptl);
 alloc:
 	if (transparent_hugepage_enabled(vma) &&
@@ -1095,7 +1126,7 @@ alloc:
 				split_huge_page(page);
 				ret |= VM_FAULT_FALLBACK;
 			}
-			put_page(page);
+			put_user_huge_page(page);
 		}
 		count_vm_event(THP_FAULT_FALLBACK);
 		goto out;
@@ -1105,7 +1136,7 @@ alloc:
 		put_page(new_page);
 		if (page) {
 			split_huge_page(page);
-			put_page(page);
+			put_user_huge_page(page);
 		} else
 			split_huge_page_pmd(vma, address, pmd);
 		ret |= VM_FAULT_FALLBACK;
@@ -1127,7 +1158,7 @@ alloc:
 
 	spin_lock(ptl);
 	if (page)
-		put_page(page);
+		put_user_huge_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
 		spin_unlock(ptl);
 		mem_cgroup_uncharge_page(new_page);
@@ -2392,8 +2423,6 @@ static void collapse_huge_page(struct mm_struct *mm,
 	pmd = mm_find_pmd(mm, address);
 	if (!pmd)
 		goto out;
-	if (pmd_trans_huge(*pmd))
-		goto out;
 
 	anon_vma_lock_write(vma->anon_vma);
 
@@ -2492,8 +2521,6 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	pmd = mm_find_pmd(mm, address);
 	if (!pmd)
 		goto out;
-	if (pmd_trans_huge(*pmd))
-		goto out;
 
 	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
@@ -2846,12 +2873,22 @@ void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
 static void split_huge_page_address(struct mm_struct *mm,
 				    unsigned long address)
 {
+	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 
 	VM_BUG_ON(!(address & ~HPAGE_PMD_MASK));
 
-	pmd = mm_find_pmd(mm, address);
-	if (!pmd)
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
+		return;
+
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		return;
+
+	pmd = pmd_offset(pud, address);
+	if (!pmd_present(*pmd))
 		return;
 	/*
 	 * Caller holds the mmap_sem write mode, so a huge pmd cannot
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 226910cb7c9..7a0a73d2fcf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -856,7 +856,7 @@ struct hstate *size_to_hstate(unsigned long size)
 	return NULL;
 }
 
-static void free_huge_page(struct page *page)
+void free_huge_page(struct page *page)
 {
 	/*
 	 * Can't pass hstate in here because it is called from the
@@ -2520,6 +2520,31 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 		update_mmu_cache(vma, address, ptep);
 }
 
+static int is_hugetlb_entry_migration(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_migration_entry(swp))
+		return 1;
+	else
+		return 0;
+}
+
+static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
+		return 1;
+	else
+		return 0;
+}
 
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
@@ -2559,7 +2584,24 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		dst_ptl = huge_pte_lock(h, dst, dst_pte);
 		src_ptl = huge_pte_lockptr(h, src, src_pte);
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
-		if (!huge_pte_none(huge_ptep_get(src_pte))) {
+		entry = huge_ptep_get(src_pte);
+		if (huge_pte_none(entry)) { /* skip none entry */
+			;
+		} else if (unlikely(is_hugetlb_entry_migration(entry) ||
+				    is_hugetlb_entry_hwpoisoned(entry))) {
+			swp_entry_t swp_entry = pte_to_swp_entry(entry);
+
+			if (is_write_migration_entry(swp_entry) && cow) {
+				/*
+				 * COW mappings require pages in both
+				 * parent and child to be set to read.
+				 */
+				make_migration_entry_read(&swp_entry);
+				entry = swp_entry_to_pte(swp_entry);
+				set_huge_pte_at(src, addr, src_pte, entry);
+			}
+			set_huge_pte_at(dst, addr, dst_pte, entry);
+		} else {
 			if (cow)
 				huge_ptep_set_wrprotect(src, addr, src_pte);
 			entry = huge_ptep_get(src_pte);
@@ -2578,32 +2620,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	return ret;
 }
 
-static int is_hugetlb_entry_migration(pte_t pte)
-{
-	swp_entry_t swp;
-
-	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
-	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_migration_entry(swp))
-		return 1;
-	else
-		return 0;
-}
-
-static int is_hugetlb_entry_hwpoisoned(pte_t pte)
-{
-	swp_entry_t swp;
-
-	if (huge_pte_none(pte) || pte_present(pte))
-		return 0;
-	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
-		return 1;
-	else
-		return 0;
-}
-
 void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			    unsigned long start, unsigned long end,
 			    struct page *ref_page)
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 595d7fd795e..9aae6f47433 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -52,7 +52,7 @@ static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg)
 static inline struct hugetlb_cgroup *
 parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg)
 {
-	return hugetlb_cgroup_from_css(css_parent(&h_cg->css));
+	return hugetlb_cgroup_from_css(h_cg->css.parent);
 }
 
 static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
@@ -181,7 +181,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 again:
 	rcu_read_lock();
 	h_cg = hugetlb_cgroup_from_task(current);
-	if (!css_tryget(&h_cg->css)) {
+	if (!css_tryget_online(&h_cg->css)) {
 		rcu_read_unlock();
 		goto again;
 	}
@@ -253,15 +253,16 @@ static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 	return res_counter_read_u64(&h_cg->hugepage[idx], name);
 }
 
-static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
-				struct cftype *cft, char *buffer)
+static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
 {
 	int idx, name, ret;
 	unsigned long long val;
-	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
-	idx = MEMFILE_IDX(cft->private);
-	name = MEMFILE_ATTR(cft->private);
+	buf = strstrip(buf);
+	idx = MEMFILE_IDX(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
 
 	switch (name) {
 	case RES_LIMIT:
@@ -271,7 +272,7 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
 			break;
 		}
 		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buffer, &val);
+		ret = res_counter_memparse_write_strategy(buf, &val);
 		if (ret)
 			break;
 		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
@@ -280,17 +281,17 @@ static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
 		ret = -EINVAL;
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
-static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css,
-				unsigned int event)
+static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes, loff_t off)
 {
 	int idx, name, ret = 0;
-	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
-	idx = MEMFILE_IDX(event);
-	name = MEMFILE_ATTR(event);
+	idx = MEMFILE_IDX(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
 
 	switch (name) {
 	case RES_MAX_USAGE:
@@ -303,7 +304,7 @@ static int hugetlb_cgroup_reset(struct cgroup_subsys_state *css,
 		ret = -EINVAL;
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
 static char *mem_fmt(char *buf, int size, unsigned long hsize)
@@ -331,7 +332,7 @@ static void __init __hugetlb_cgroup_file_init(int idx)
 	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf);
 	cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT);
 	cft->read_u64 = hugetlb_cgroup_read_u64;
-	cft->write_string = hugetlb_cgroup_write;
+	cft->write = hugetlb_cgroup_write;
 
 	/* Add the usage file */
 	cft = &h->cgroup_files[1];
@@ -343,23 +344,22 @@ static void __init __hugetlb_cgroup_file_init(int idx)
 	cft = &h->cgroup_files[2];
 	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf);
 	cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE);
-	cft->trigger = hugetlb_cgroup_reset;
+	cft->write = hugetlb_cgroup_reset;
 	cft->read_u64 = hugetlb_cgroup_read_u64;
 
 	/* Add the failcntfile */
 	cft = &h->cgroup_files[3];
 	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf);
 	cft->private  = MEMFILE_PRIVATE(idx, RES_FAILCNT);
-	cft->trigger  = hugetlb_cgroup_reset;
+	cft->write = hugetlb_cgroup_reset;
 	cft->read_u64 = hugetlb_cgroup_read_u64;
 
 	/* NULL terminate the last cft */
 	cft = &h->cgroup_files[4];
 	memset(cft, 0, sizeof(*cft));
 
-	WARN_ON(cgroup_add_cftypes(&hugetlb_cgrp_subsys, h->cgroup_files));
-
-	return;
+	WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys,
+					  h->cgroup_files));
 }
 
 void __init hugetlb_cgroup_file_init(void)
diff --git a/mm/iov_iter.c b/mm/iov_iter.c
index 10e46cd721d..7b5dbd1517b 100644
--- a/mm/iov_iter.c
+++ b/mm/iov_iter.c
@@ -1,8 +1,10 @@
 #include <linux/export.h>
 #include <linux/uio.h>
 #include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 
-size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
+static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes,
 			 struct iov_iter *i)
 {
 	size_t skip, copy, left, wanted;
@@ -72,13 +74,97 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
 	}
 	kunmap(page);
 done:
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+	void *kaddr, *to;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	if (!fault_in_pages_readable(buf, copy)) {
+		kaddr = kmap_atomic(page);
+		to = kaddr + offset;
+
+		/* first chunk, usually the only one */
+		left = __copy_from_user_inatomic(to, buf, copy);
+		copy -= left;
+		skip += copy;
+		to += copy;
+		bytes -= copy;
+
+		while (unlikely(!left && bytes)) {
+			iov++;
+			buf = iov->iov_base;
+			copy = min(bytes, iov->iov_len);
+			left = __copy_from_user_inatomic(to, buf, copy);
+			copy -= left;
+			skip = copy;
+			to += copy;
+			bytes -= copy;
+		}
+		if (likely(!bytes)) {
+			kunmap_atomic(kaddr);
+			goto done;
+		}
+		offset = to - kaddr;
+		buf += copy;
+		kunmap_atomic(kaddr);
+		copy = min(bytes, iov->iov_len - skip);
+	}
+	/* Too bad - revert to non-atomic kmap */
+	kaddr = kmap(page);
+	to = kaddr + offset;
+	left = __copy_from_user(to, buf, copy);
+	copy -= left;
+	skip += copy;
+	to += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_from_user(to, buf, copy);
+		copy -= left;
+		skip = copy;
+		to += copy;
+		bytes -= copy;
+	}
+	kunmap(page);
+done:
+	if (skip == iov->iov_len) {
+		iov++;
+		skip = 0;
+	}
 	i->count -= wanted - bytes;
 	i->nr_segs -= iov - i->iov;
 	i->iov = iov;
 	i->iov_offset = skip;
 	return wanted - bytes;
 }
-EXPORT_SYMBOL(copy_page_to_iter);
 
 static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 			const struct iovec *iov, size_t base, size_t bytes)
@@ -107,7 +193,7 @@ static size_t __iovec_copy_from_user_inatomic(char *vaddr,
  * were successfully copied.  If a fault is encountered then return the number of
  * bytes which were copied.
  */
-size_t iov_iter_copy_from_user_atomic(struct page *page,
+static size_t copy_from_user_atomic_iovec(struct page *page,
 		struct iov_iter *i, unsigned long offset, size_t bytes)
 {
 	char *kaddr;
@@ -127,36 +213,8 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
 
 	return copied;
 }
-EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
-
-/*
- * This has the same sideeffects and return value as
- * iov_iter_copy_from_user_atomic().
- * The difference is that it attempts to resolve faults.
- * Page must not be locked.
- */
-size_t iov_iter_copy_from_user(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes)
-{
-	char *kaddr;
-	size_t copied;
-
-	kaddr = kmap(page);
-	if (likely(i->nr_segs == 1)) {
-		int left;
-		char __user *buf = i->iov->iov_base + i->iov_offset;
-		left = __copy_from_user(kaddr + offset, buf, bytes);
-		copied = bytes - left;
-	} else {
-		copied = __iovec_copy_from_user_inatomic(kaddr + offset,
-						i->iov, i->iov_offset, bytes);
-	}
-	kunmap(page);
-	return copied;
-}
-EXPORT_SYMBOL(iov_iter_copy_from_user);
 
-void iov_iter_advance(struct iov_iter *i, size_t bytes)
+static void advance_iovec(struct iov_iter *i, size_t bytes)
 {
 	BUG_ON(i->count < bytes);
 
@@ -191,7 +249,6 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes)
 		i->nr_segs = nr_segs;
 	}
 }
-EXPORT_SYMBOL(iov_iter_advance);
 
 /*
  * Fault in the first iovec of the given iov_iter, to a maximum length
@@ -204,21 +261,483 @@ EXPORT_SYMBOL(iov_iter_advance);
  */
 int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
 {
-	char __user *buf = i->iov->iov_base + i->iov_offset;
-	bytes = min(bytes, i->iov->iov_len - i->iov_offset);
-	return fault_in_pages_readable(buf, bytes);
+	if (!(i->type & ITER_BVEC)) {
+		char __user *buf = i->iov->iov_base + i->iov_offset;
+		bytes = min(bytes, i->iov->iov_len - i->iov_offset);
+		return fault_in_pages_readable(buf, bytes);
+	}
+	return 0;
 }
 EXPORT_SYMBOL(iov_iter_fault_in_readable);
 
+static unsigned long alignment_iovec(const struct iov_iter *i)
+{
+	const struct iovec *iov = i->iov;
+	unsigned long res;
+	size_t size = i->count;
+	size_t n;
+
+	if (!size)
+		return 0;
+
+	res = (unsigned long)iov->iov_base + i->iov_offset;
+	n = iov->iov_len - i->iov_offset;
+	if (n >= size)
+		return res | size;
+	size -= n;
+	res |= n;
+	while (size > (++iov)->iov_len) {
+		res |= (unsigned long)iov->iov_base | iov->iov_len;
+		size -= iov->iov_len;
+	}
+	res |= (unsigned long)iov->iov_base | size;
+	return res;
+}
+
+void iov_iter_init(struct iov_iter *i, int direction,
+			const struct iovec *iov, unsigned long nr_segs,
+			size_t count)
+{
+	/* It will get better.  Eventually... */
+	if (segment_eq(get_fs(), KERNEL_DS))
+		direction |= ITER_KVEC;
+	i->type = direction;
+	i->iov = iov;
+	i->nr_segs = nr_segs;
+	i->iov_offset = 0;
+	i->count = count;
+}
+EXPORT_SYMBOL(iov_iter_init);
+
+static ssize_t get_pages_iovec(struct iov_iter *i,
+		   struct page **pages, size_t maxsize,
+		   size_t *start)
+{
+	size_t offset = i->iov_offset;
+	const struct iovec *iov = i->iov;
+	size_t len;
+	unsigned long addr;
+	int n;
+	int res;
+
+	len = iov->iov_len - offset;
+	if (len > i->count)
+		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
+	addr = (unsigned long)iov->iov_base + offset;
+	len += *start = addr & (PAGE_SIZE - 1);
+	addr &= ~(PAGE_SIZE - 1);
+	n = (len + PAGE_SIZE - 1) / PAGE_SIZE;
+	res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages);
+	if (unlikely(res < 0))
+		return res;
+	return (res == n ? len : res * PAGE_SIZE) - *start;
+}
+
+static ssize_t get_pages_alloc_iovec(struct iov_iter *i,
+		   struct page ***pages, size_t maxsize,
+		   size_t *start)
+{
+	size_t offset = i->iov_offset;
+	const struct iovec *iov = i->iov;
+	size_t len;
+	unsigned long addr;
+	void *p;
+	int n;
+	int res;
+
+	len = iov->iov_len - offset;
+	if (len > i->count)
+		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
+	addr = (unsigned long)iov->iov_base + offset;
+	len += *start = addr & (PAGE_SIZE - 1);
+	addr &= ~(PAGE_SIZE - 1);
+	n = (len + PAGE_SIZE - 1) / PAGE_SIZE;
+	
+	p = kmalloc(n * sizeof(struct page *), GFP_KERNEL);
+	if (!p)
+		p = vmalloc(n * sizeof(struct page *));
+	if (!p)
+		return -ENOMEM;
+
+	res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p);
+	if (unlikely(res < 0)) {
+		kvfree(p);
+		return res;
+	}
+	*pages = p;
+	return (res == n ? len : res * PAGE_SIZE) - *start;
+}
+
+static int iov_iter_npages_iovec(const struct iov_iter *i, int maxpages)
+{
+	size_t offset = i->iov_offset;
+	size_t size = i->count;
+	const struct iovec *iov = i->iov;
+	int npages = 0;
+	int n;
+
+	for (n = 0; size && n < i->nr_segs; n++, iov++) {
+		unsigned long addr = (unsigned long)iov->iov_base + offset;
+		size_t len = iov->iov_len - offset;
+		offset = 0;
+		if (unlikely(!len))	/* empty segment */
+			continue;
+		if (len > size)
+			len = size;
+		npages += (addr + len + PAGE_SIZE - 1) / PAGE_SIZE
+			  - addr / PAGE_SIZE;
+		if (npages >= maxpages)	/* don't bother going further */
+			return maxpages;
+		size -= len;
+		offset = 0;
+	}
+	return min(npages, maxpages);
+}
+
+static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len)
+{
+	char *from = kmap_atomic(page);
+	memcpy(to, from + offset, len);
+	kunmap_atomic(from);
+}
+
+static void memcpy_to_page(struct page *page, size_t offset, char *from, size_t len)
+{
+	char *to = kmap_atomic(page);
+	memcpy(to + offset, from, len);
+	kunmap_atomic(to);
+}
+
+static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	size_t skip, copy, wanted;
+	const struct bio_vec *bvec;
+	void *kaddr, *from;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	bvec = i->bvec;
+	skip = i->iov_offset;
+	copy = min_t(size_t, bytes, bvec->bv_len - skip);
+
+	kaddr = kmap_atomic(page);
+	from = kaddr + offset;
+	memcpy_to_page(bvec->bv_page, skip + bvec->bv_offset, from, copy);
+	skip += copy;
+	from += copy;
+	bytes -= copy;
+	while (bytes) {
+		bvec++;
+		copy = min(bytes, (size_t)bvec->bv_len);
+		memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, copy);
+		skip = copy;
+		from += copy;
+		bytes -= copy;
+	}
+	kunmap_atomic(kaddr);
+	if (skip == bvec->bv_len) {
+		bvec++;
+		skip = 0;
+	}
+	i->count -= wanted - bytes;
+	i->nr_segs -= bvec - i->bvec;
+	i->bvec = bvec;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+
+static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	size_t skip, copy, wanted;
+	const struct bio_vec *bvec;
+	void *kaddr, *to;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	bvec = i->bvec;
+	skip = i->iov_offset;
+
+	kaddr = kmap_atomic(page);
+
+	to = kaddr + offset;
+
+	copy = min(bytes, bvec->bv_len - skip);
+
+	memcpy_from_page(to, bvec->bv_page, bvec->bv_offset + skip, copy);
+
+	to += copy;
+	skip += copy;
+	bytes -= copy;
+
+	while (bytes) {
+		bvec++;
+		copy = min(bytes, (size_t)bvec->bv_len);
+		memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, copy);
+		skip = copy;
+		to += copy;
+		bytes -= copy;
+	}
+	kunmap_atomic(kaddr);
+	if (skip == bvec->bv_len) {
+		bvec++;
+		skip = 0;
+	}
+	i->count -= wanted;
+	i->nr_segs -= bvec - i->bvec;
+	i->bvec = bvec;
+	i->iov_offset = skip;
+	return wanted;
+}
+
+static size_t copy_from_user_bvec(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+	char *kaddr;
+	size_t left;
+	const struct bio_vec *bvec;
+	size_t base = i->iov_offset;
+
+	kaddr = kmap_atomic(page);
+	for (left = bytes, bvec = i->bvec; left; bvec++, base = 0) {
+		size_t copy = min(left, bvec->bv_len - base);
+		if (!bvec->bv_len)
+			continue;
+		memcpy_from_page(kaddr + offset, bvec->bv_page,
+				 bvec->bv_offset + base, copy);
+		offset += copy;
+		left -= copy;
+	}
+	kunmap_atomic(kaddr);
+	return bytes;
+}
+
+static void advance_bvec(struct iov_iter *i, size_t bytes)
+{
+	BUG_ON(i->count < bytes);
+
+	if (likely(i->nr_segs == 1)) {
+		i->iov_offset += bytes;
+		i->count -= bytes;
+	} else {
+		const struct bio_vec *bvec = i->bvec;
+		size_t base = i->iov_offset;
+		unsigned long nr_segs = i->nr_segs;
+
+		/*
+		 * The !iov->iov_len check ensures we skip over unlikely
+		 * zero-length segments (without overruning the iovec).
+		 */
+		while (bytes || unlikely(i->count && !bvec->bv_len)) {
+			int copy;
+
+			copy = min(bytes, bvec->bv_len - base);
+			BUG_ON(!i->count || i->count < copy);
+			i->count -= copy;
+			bytes -= copy;
+			base += copy;
+			if (bvec->bv_len == base) {
+				bvec++;
+				nr_segs--;
+				base = 0;
+			}
+		}
+		i->bvec = bvec;
+		i->iov_offset = base;
+		i->nr_segs = nr_segs;
+	}
+}
+
+static unsigned long alignment_bvec(const struct iov_iter *i)
+{
+	const struct bio_vec *bvec = i->bvec;
+	unsigned long res;
+	size_t size = i->count;
+	size_t n;
+
+	if (!size)
+		return 0;
+
+	res = bvec->bv_offset + i->iov_offset;
+	n = bvec->bv_len - i->iov_offset;
+	if (n >= size)
+		return res | size;
+	size -= n;
+	res |= n;
+	while (size > (++bvec)->bv_len) {
+		res |= bvec->bv_offset | bvec->bv_len;
+		size -= bvec->bv_len;
+	}
+	res |= bvec->bv_offset | size;
+	return res;
+}
+
+static ssize_t get_pages_bvec(struct iov_iter *i,
+		   struct page **pages, size_t maxsize,
+		   size_t *start)
+{
+	const struct bio_vec *bvec = i->bvec;
+	size_t len = bvec->bv_len - i->iov_offset;
+	if (len > i->count)
+		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
+	*start = bvec->bv_offset + i->iov_offset;
+
+	get_page(*pages = bvec->bv_page);
+
+	return len;
+}
+
+static ssize_t get_pages_alloc_bvec(struct iov_iter *i,
+		   struct page ***pages, size_t maxsize,
+		   size_t *start)
+{
+	const struct bio_vec *bvec = i->bvec;
+	size_t len = bvec->bv_len - i->iov_offset;
+	if (len > i->count)
+		len = i->count;
+	if (len > maxsize)
+		len = maxsize;
+	*start = bvec->bv_offset + i->iov_offset;
+
+	*pages = kmalloc(sizeof(struct page *), GFP_KERNEL);
+	if (!*pages)
+		return -ENOMEM;
+
+	get_page(**pages = bvec->bv_page);
+
+	return len;
+}
+
+static int iov_iter_npages_bvec(const struct iov_iter *i, int maxpages)
+{
+	size_t offset = i->iov_offset;
+	size_t size = i->count;
+	const struct bio_vec *bvec = i->bvec;
+	int npages = 0;
+	int n;
+
+	for (n = 0; size && n < i->nr_segs; n++, bvec++) {
+		size_t len = bvec->bv_len - offset;
+		offset = 0;
+		if (unlikely(!len))	/* empty segment */
+			continue;
+		if (len > size)
+			len = size;
+		npages++;
+		if (npages >= maxpages)	/* don't bother going further */
+			return maxpages;
+		size -= len;
+		offset = 0;
+	}
+	return min(npages, maxpages);
+}
+
+size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_page_to_iter_bvec(page, offset, bytes, i);
+	else
+		return copy_page_to_iter_iovec(page, offset, bytes, i);
+}
+EXPORT_SYMBOL(copy_page_to_iter);
+
+size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return copy_page_from_iter_bvec(page, offset, bytes, i);
+	else
+		return copy_page_from_iter_iovec(page, offset, bytes, i);
+}
+EXPORT_SYMBOL(copy_page_from_iter);
+
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes)
+{
+	if (i->type & ITER_BVEC)
+		return copy_from_user_bvec(page, i, offset, bytes);
+	else
+		return copy_from_user_atomic_iovec(page, i, offset, bytes);
+}
+EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
+
+void iov_iter_advance(struct iov_iter *i, size_t size)
+{
+	if (i->type & ITER_BVEC)
+		advance_bvec(i, size);
+	else
+		advance_iovec(i, size);
+}
+EXPORT_SYMBOL(iov_iter_advance);
+
 /*
  * Return the count of just the current iov_iter segment.
  */
 size_t iov_iter_single_seg_count(const struct iov_iter *i)
 {
-	const struct iovec *iov = i->iov;
 	if (i->nr_segs == 1)
 		return i->count;
+	else if (i->type & ITER_BVEC)
+		return min(i->count, i->iov->iov_len - i->iov_offset);
 	else
-		return min(i->count, iov->iov_len - i->iov_offset);
+		return min(i->count, i->bvec->bv_len - i->iov_offset);
 }
 EXPORT_SYMBOL(iov_iter_single_seg_count);
+
+unsigned long iov_iter_alignment(const struct iov_iter *i)
+{
+	if (i->type & ITER_BVEC)
+		return alignment_bvec(i);
+	else
+		return alignment_iovec(i);
+}
+EXPORT_SYMBOL(iov_iter_alignment);
+
+ssize_t iov_iter_get_pages(struct iov_iter *i,
+		   struct page **pages, size_t maxsize,
+		   size_t *start)
+{
+	if (i->type & ITER_BVEC)
+		return get_pages_bvec(i, pages, maxsize, start);
+	else
+		return get_pages_iovec(i, pages, maxsize, start);
+}
+EXPORT_SYMBOL(iov_iter_get_pages);
+
+ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
+		   struct page ***pages, size_t maxsize,
+		   size_t *start)
+{
+	if (i->type & ITER_BVEC)
+		return get_pages_alloc_bvec(i, pages, maxsize, start);
+	else
+		return get_pages_alloc_iovec(i, pages, maxsize, start);
+}
+EXPORT_SYMBOL(iov_iter_get_pages_alloc);
+
+int iov_iter_npages(const struct iov_iter *i, int maxpages)
+{
+	if (i->type & ITER_BVEC)
+		return iov_iter_npages_bvec(i, maxpages);
+	else
+		return iov_iter_npages_iovec(i, maxpages);
+}
+EXPORT_SYMBOL(iov_iter_npages);
diff --git a/mm/ksm.c b/mm/ksm.c
index 68710e80994..fb759022270 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -945,7 +945,6 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	pmd = mm_find_pmd(mm, addr);
 	if (!pmd)
 		goto out;
-	BUG_ON(pmd_trans_huge(*pmd));
 
 	mmun_start = addr;
 	mmun_end   = addr + PAGE_SIZE;
@@ -1979,18 +1978,12 @@ void ksm_migrate_page(struct page *newpage, struct page *oldpage)
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-static int just_wait(void *word)
-{
-	schedule();
-	return 0;
-}
-
 static void wait_while_offlining(void)
 {
 	while (ksm_run & KSM_RUN_OFFLINE) {
 		mutex_unlock(&ksm_thread_mutex);
 		wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE),
-				just_wait, TASK_UNINTERRUPTIBLE);
+			    TASK_UNINTERRUPTIBLE);
 		mutex_lock(&ksm_thread_mutex);
 	}
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a9559b91603..f009a14918d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -526,18 +526,14 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 
 static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 {
-	/*
-	 * The ID of the root cgroup is 0, but memcg treat 0 as an
-	 * invalid ID, so we return (cgroup_id + 1).
-	 */
-	return memcg->css.cgroup->id + 1;
+	return memcg->css.id;
 }
 
 static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
 {
 	struct cgroup_subsys_state *css;
 
-	css = css_from_id(id - 1, &memory_cgrp_subsys);
+	css = css_from_id(id, &memory_cgrp_subsys);
 	return mem_cgroup_from_css(css);
 }
 
@@ -570,7 +566,8 @@ void sock_update_memcg(struct sock *sk)
 		memcg = mem_cgroup_from_task(current);
 		cg_proto = sk->sk_prot->proto_cgroup(memcg);
 		if (!mem_cgroup_is_root(memcg) &&
-		    memcg_proto_active(cg_proto) && css_tryget(&memcg->css)) {
+		    memcg_proto_active(cg_proto) &&
+		    css_tryget_online(&memcg->css)) {
 			sk->sk_cgrp = cg_proto;
 		}
 		rcu_read_unlock();
@@ -831,7 +828,7 @@ retry:
 	 */
 	__mem_cgroup_remove_exceeded(mz, mctz);
 	if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
-		!css_tryget(&mz->memcg->css))
+	    !css_tryget_online(&mz->memcg->css))
 		goto retry;
 done:
 	return mz;
@@ -1073,7 +1070,7 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 			if (unlikely(!memcg))
 				memcg = root_mem_cgroup;
 		}
-	} while (!css_tryget(&memcg->css));
+	} while (!css_tryget_online(&memcg->css));
 	rcu_read_unlock();
 	return memcg;
 }
@@ -1110,7 +1107,8 @@ skip_node:
 	 */
 	if (next_css) {
 		if ((next_css == &root->css) ||
-		    ((next_css->flags & CSS_ONLINE) && css_tryget(next_css)))
+		    ((next_css->flags & CSS_ONLINE) &&
+		     css_tryget_online(next_css)))
 			return mem_cgroup_from_css(next_css);
 
 		prev_css = next_css;
@@ -1156,7 +1154,7 @@ mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter,
 		 * would be returned all the time.
 		 */
 		if (position && position != root &&
-				!css_tryget(&position->css))
+		    !css_tryget_online(&position->css))
 			position = NULL;
 	}
 	return position;
@@ -1533,7 +1531,7 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
 int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 {
 	/* root ? */
-	if (mem_cgroup_disabled() || !css_parent(&memcg->css))
+	if (mem_cgroup_disabled() || !memcg->css.parent)
 		return vm_swappiness;
 
 	return memcg->swappiness;
@@ -2769,9 +2767,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
 
 /*
  * A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock().  The caller is responsible for calling css_tryget if
- * the mem_cgroup is used for charging. (dropping refcnt from swap can be
- * called against removed memcg.)
+ * rcu_read_lock().  The caller is responsible for calling
+ * css_tryget_online() if the mem_cgroup is used for charging. (dropping
+ * refcnt from swap can be called against removed memcg.)
  */
 static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 {
@@ -2794,14 +2792,14 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
 		memcg = pc->mem_cgroup;
-		if (memcg && !css_tryget(&memcg->css))
+		if (memcg && !css_tryget_online(&memcg->css))
 			memcg = NULL;
 	} else if (PageSwapCache(page)) {
 		ent.val = page_private(page);
 		id = lookup_swap_cgroup_id(ent);
 		rcu_read_lock();
 		memcg = mem_cgroup_lookup(id);
-		if (memcg && !css_tryget(&memcg->css))
+		if (memcg && !css_tryget_online(&memcg->css))
 			memcg = NULL;
 		rcu_read_unlock();
 	}
@@ -3365,7 +3363,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
 	}
 
 	/* The corresponding put will be done in the workqueue. */
-	if (!css_tryget(&memcg->css))
+	if (!css_tryget_online(&memcg->css))
 		goto out;
 	rcu_read_unlock();
 
@@ -4125,8 +4123,8 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent)
 	memcg = mem_cgroup_lookup(id);
 	if (memcg) {
 		/*
-		 * We uncharge this because swap is freed.
-		 * This memcg can be obsolete one. We avoid calling css_tryget
+		 * We uncharge this because swap is freed.  This memcg can
+		 * be obsolete one. We avoid calling css_tryget_online().
 		 */
 		if (!mem_cgroup_is_root(memcg))
 			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
@@ -4711,18 +4709,28 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 	} while (usage > 0);
 }
 
+/*
+ * Test whether @memcg has children, dead or alive.  Note that this
+ * function doesn't care whether @memcg has use_hierarchy enabled and
+ * returns %true if there are child csses according to the cgroup
+ * hierarchy.  Testing use_hierarchy is the caller's responsiblity.
+ */
 static inline bool memcg_has_children(struct mem_cgroup *memcg)
 {
-	lockdep_assert_held(&memcg_create_mutex);
+	bool ret;
+
 	/*
-	 * The lock does not prevent addition or deletion to the list
-	 * of children, but it prevents a new child from being
-	 * initialized based on this parent in css_online(), so it's
-	 * enough to decide whether hierarchically inherited
-	 * attributes can still be changed or not.
+	 * The lock does not prevent addition or deletion of children, but
+	 * it prevents a new child from being initialized based on this
+	 * parent in css_online(), so it's enough to decide whether
+	 * hierarchically inherited attributes can still be changed or not.
 	 */
-	return memcg->use_hierarchy &&
-		!list_empty(&memcg->css.cgroup->children);
+	lockdep_assert_held(&memcg_create_mutex);
+
+	rcu_read_lock();
+	ret = css_next_child(NULL, &memcg->css);
+	rcu_read_unlock();
+	return ret;
 }
 
 /*
@@ -4734,11 +4742,6 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg)
 static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 {
 	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-	struct cgroup *cgrp = memcg->css.cgroup;
-
-	/* returns EBUSY if there is a task or if we come here twice. */
-	if (cgroup_has_tasks(cgrp) || !list_empty(&cgrp->children))
-		return -EBUSY;
 
 	/* we call try-to-free pages for make this cgroup empty */
 	lru_add_drain_all();
@@ -4758,20 +4761,19 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 		}
 
 	}
-	lru_add_drain();
-	mem_cgroup_reparent_charges(memcg);
 
 	return 0;
 }
 
-static int mem_cgroup_force_empty_write(struct cgroup_subsys_state *css,
-					unsigned int event)
+static ssize_t mem_cgroup_force_empty_write(struct kernfs_open_file *of,
+					    char *buf, size_t nbytes,
+					    loff_t off)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 
 	if (mem_cgroup_is_root(memcg))
 		return -EINVAL;
-	return mem_cgroup_force_empty(memcg);
+	return mem_cgroup_force_empty(memcg) ?: nbytes;
 }
 
 static u64 mem_cgroup_hierarchy_read(struct cgroup_subsys_state *css,
@@ -4785,7 +4787,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
 {
 	int retval = 0;
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	struct mem_cgroup *parent_memcg = mem_cgroup_from_css(css_parent(&memcg->css));
+	struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent);
 
 	mutex_lock(&memcg_create_mutex);
 
@@ -4802,7 +4804,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
 	 */
 	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
 				(val == 1 || val == 0)) {
-		if (list_empty(&memcg->css.cgroup->children))
+		if (!memcg_has_children(memcg))
 			memcg->use_hierarchy = val;
 		else
 			retval = -EBUSY;
@@ -4919,7 +4921,8 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg,
 	 * of course permitted.
 	 */
 	mutex_lock(&memcg_create_mutex);
-	if (cgroup_has_tasks(memcg->css.cgroup) || memcg_has_children(memcg))
+	if (cgroup_has_tasks(memcg->css.cgroup) ||
+	    (memcg->use_hierarchy && memcg_has_children(memcg)))
 		err = -EBUSY;
 	mutex_unlock(&memcg_create_mutex);
 	if (err)
@@ -5021,17 +5024,18 @@ static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
  * The user of this function is...
  * RES_LIMIT.
  */
-static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buffer)
+static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	enum res_type type;
 	int name;
 	unsigned long long val;
 	int ret;
 
-	type = MEMFILE_TYPE(cft->private);
-	name = MEMFILE_ATTR(cft->private);
+	buf = strstrip(buf);
+	type = MEMFILE_TYPE(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
 
 	switch (name) {
 	case RES_LIMIT:
@@ -5040,7 +5044,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
 			break;
 		}
 		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buffer, &val);
+		ret = res_counter_memparse_write_strategy(buf, &val);
 		if (ret)
 			break;
 		if (type == _MEM)
@@ -5053,7 +5057,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
 			return -EINVAL;
 		break;
 	case RES_SOFT_LIMIT:
-		ret = res_counter_memparse_write_strategy(buffer, &val);
+		ret = res_counter_memparse_write_strategy(buf, &val);
 		if (ret)
 			break;
 		/*
@@ -5070,7 +5074,7 @@ static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
 		ret = -EINVAL; /* should be BUG() ? */
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
 static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
@@ -5083,8 +5087,8 @@ static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
 	if (!memcg->use_hierarchy)
 		goto out;
 
-	while (css_parent(&memcg->css)) {
-		memcg = mem_cgroup_from_css(css_parent(&memcg->css));
+	while (memcg->css.parent) {
+		memcg = mem_cgroup_from_css(memcg->css.parent);
 		if (!memcg->use_hierarchy)
 			break;
 		tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
@@ -5097,14 +5101,15 @@ out:
 	*memsw_limit = min_memsw_limit;
 }
 
-static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
+static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
+				size_t nbytes, loff_t off)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	int name;
 	enum res_type type;
 
-	type = MEMFILE_TYPE(event);
-	name = MEMFILE_ATTR(event);
+	type = MEMFILE_TYPE(of_cft(of)->private);
+	name = MEMFILE_ATTR(of_cft(of)->private);
 
 	switch (name) {
 	case RES_MAX_USAGE:
@@ -5129,7 +5134,7 @@ static int mem_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 		break;
 	}
 
-	return 0;
+	return nbytes;
 }
 
 static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css,
@@ -5322,7 +5327,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
 	if (val > 100)
 		return -EINVAL;
 
-	if (css_parent(css))
+	if (css->parent)
 		memcg->swappiness = val;
 	else
 		vm_swappiness = val;
@@ -5410,8 +5415,12 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
 {
 	struct mem_cgroup_eventfd_list *ev;
 
+	spin_lock(&memcg_oom_lock);
+
 	list_for_each_entry(ev, &memcg->oom_notify, list)
 		eventfd_signal(ev->eventfd, 1);
+
+	spin_unlock(&memcg_oom_lock);
 	return 0;
 }
 
@@ -5659,7 +5668,7 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
 	/* cannot set to root cgroup and only 0 and 1 are allowed */
-	if (!css_parent(css) || !((val == 0) || (val == 1)))
+	if (!css->parent || !((val == 0) || (val == 1)))
 		return -EINVAL;
 
 	memcg->oom_kill_disable = val;
@@ -5705,10 +5714,10 @@ static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
 	 * which is then paired with css_put during uncharge resp. here.
 	 *
 	 * Although this might sound strange as this path is called from
-	 * css_offline() when the referencemight have dropped down to 0
-	 * and shouldn't be incremented anymore (css_tryget would fail)
-	 * we do not have other options because of the kmem allocations
-	 * lifetime.
+	 * css_offline() when the referencemight have dropped down to 0 and
+	 * shouldn't be incremented anymore (css_tryget_online() would
+	 * fail) we do not have other options because of the kmem
+	 * allocations lifetime.
 	 */
 	css_get(&memcg->css);
 
@@ -5827,9 +5836,10 @@ static void memcg_event_ptable_queue_proc(struct file *file,
  * Input must be in format '<event_fd> <control_fd> <args>'.
  * Interpretation of args is defined by control file implementation.
  */
-static int memcg_write_event_control(struct cgroup_subsys_state *css,
-				     struct cftype *cft, char *buffer)
+static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
+					 char *buf, size_t nbytes, loff_t off)
 {
+	struct cgroup_subsys_state *css = of_css(of);
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_event *event;
 	struct cgroup_subsys_state *cfile_css;
@@ -5840,15 +5850,17 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css,
 	char *endp;
 	int ret;
 
-	efd = simple_strtoul(buffer, &endp, 10);
+	buf = strstrip(buf);
+
+	efd = simple_strtoul(buf, &endp, 10);
 	if (*endp != ' ')
 		return -EINVAL;
-	buffer = endp + 1;
+	buf = endp + 1;
 
-	cfd = simple_strtoul(buffer, &endp, 10);
+	cfd = simple_strtoul(buf, &endp, 10);
 	if ((*endp != ' ') && (*endp != '\0'))
 		return -EINVAL;
-	buffer = endp + 1;
+	buf = endp + 1;
 
 	event = kzalloc(sizeof(*event), GFP_KERNEL);
 	if (!event)
@@ -5916,8 +5928,8 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css,
 	 * automatically removed on cgroup destruction but the removal is
 	 * asynchronous, so take an extra ref on @css.
 	 */
-	cfile_css = css_tryget_from_dir(cfile.file->f_dentry->d_parent,
-					&memory_cgrp_subsys);
+	cfile_css = css_tryget_online_from_dir(cfile.file->f_dentry->d_parent,
+					       &memory_cgrp_subsys);
 	ret = -EINVAL;
 	if (IS_ERR(cfile_css))
 		goto out_put_cfile;
@@ -5926,7 +5938,7 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css,
 		goto out_put_cfile;
 	}
 
-	ret = event->register_event(memcg, event->eventfd, buffer);
+	ret = event->register_event(memcg, event->eventfd, buf);
 	if (ret)
 		goto out_put_css;
 
@@ -5939,7 +5951,7 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css,
 	fdput(cfile);
 	fdput(efile);
 
-	return 0;
+	return nbytes;
 
 out_put_css:
 	css_put(css);
@@ -5964,25 +5976,25 @@ static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "max_usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{
 		.name = "limit_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
-		.write_string = mem_cgroup_write,
+		.write = mem_cgroup_write,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{
 		.name = "soft_limit_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT),
-		.write_string = mem_cgroup_write,
+		.write = mem_cgroup_write,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{
 		.name = "failcnt",
 		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{
@@ -5991,17 +6003,16 @@ static struct cftype mem_cgroup_files[] = {
 	},
 	{
 		.name = "force_empty",
-		.trigger = mem_cgroup_force_empty_write,
+		.write = mem_cgroup_force_empty_write,
 	},
 	{
 		.name = "use_hierarchy",
-		.flags = CFTYPE_INSANE,
 		.write_u64 = mem_cgroup_hierarchy_write,
 		.read_u64 = mem_cgroup_hierarchy_read,
 	},
 	{
 		.name = "cgroup.event_control",		/* XXX: for compat */
-		.write_string = memcg_write_event_control,
+		.write = memcg_write_event_control,
 		.flags = CFTYPE_NO_PREFIX,
 		.mode = S_IWUGO,
 	},
@@ -6034,7 +6045,7 @@ static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "kmem.limit_in_bytes",
 		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
-		.write_string = mem_cgroup_write,
+		.write = mem_cgroup_write,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{
@@ -6045,13 +6056,13 @@ static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "kmem.failcnt",
 		.private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{
 		.name = "kmem.max_usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 #ifdef CONFIG_SLABINFO
@@ -6074,19 +6085,19 @@ static struct cftype memsw_cgroup_files[] = {
 	{
 		.name = "memsw.max_usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{
 		.name = "memsw.limit_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
-		.write_string = mem_cgroup_write,
+		.write = mem_cgroup_write,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{
 		.name = "memsw.failcnt",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
-		.trigger = mem_cgroup_reset,
+		.write = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read_u64,
 	},
 	{ },	/* terminate */
@@ -6264,9 +6275,9 @@ static int
 mem_cgroup_css_online(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css));
+	struct mem_cgroup *parent = mem_cgroup_from_css(css->parent);
 
-	if (css->cgroup->id > MEM_CGROUP_ID_MAX)
+	if (css->id > MEM_CGROUP_ID_MAX)
 		return -ENOSPC;
 
 	if (!parent)
@@ -6361,7 +6372,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 	/*
 	 * XXX: css_offline() would be where we should reparent all
 	 * memory to prepare the cgroup for destruction.  However,
-	 * memcg does not do css_tryget() and res_counter charging
+	 * memcg does not do css_tryget_online() and res_counter charging
 	 * under the same RCU lock region, which means that charging
 	 * could race with offlining.  Offlining only happens to
 	 * cgroups with no tasks in them but charges can show up
@@ -6375,9 +6386,9 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 	 *                           lookup_swap_cgroup_id()
 	 *                           rcu_read_lock()
 	 *                           mem_cgroup_lookup()
-	 *                           css_tryget()
+	 *                           css_tryget_online()
 	 *                           rcu_read_unlock()
-	 * disable css_tryget()
+	 * disable css_tryget_online()
 	 * call_rcu()
 	 *   offline_css()
 	 *     reparent_charges()
@@ -6399,6 +6410,29 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 	__mem_cgroup_free(memcg);
 }
 
+/**
+ * mem_cgroup_css_reset - reset the states of a mem_cgroup
+ * @css: the target css
+ *
+ * Reset the states of the mem_cgroup associated with @css.  This is
+ * invoked when the userland requests disabling on the default hierarchy
+ * but the memcg is pinned through dependency.  The memcg should stop
+ * applying policies and should revert to the vanilla state as it may be
+ * made visible again.
+ *
+ * The current implementation only resets the essential configurations.
+ * This needs to be expanded to cover all the visible parts.
+ */
+static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	mem_cgroup_resize_limit(memcg, ULLONG_MAX);
+	mem_cgroup_resize_memsw_limit(memcg, ULLONG_MAX);
+	memcg_update_kmem_limit(memcg, ULLONG_MAX);
+	res_counter_set_soft_limit(&memcg->res, ULLONG_MAX);
+}
+
 #ifdef CONFIG_MMU
 /* Handlers for move charge at task migration. */
 #define PRECHARGE_COUNT_AT_ONCE	256
@@ -6993,16 +7027,17 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
 
 /*
  * Cgroup retains root cgroups across [un]mount cycles making it necessary
- * to verify sane_behavior flag on each mount attempt.
+ * to verify whether we're attached to the default hierarchy on each mount
+ * attempt.
  */
 static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
 {
 	/*
-	 * use_hierarchy is forced with sane_behavior.  cgroup core
+	 * use_hierarchy is forced on the default hierarchy.  cgroup core
 	 * guarantees that @root doesn't have any children, so turning it
 	 * on for the root memcg is enough.
 	 */
-	if (cgroup_sane_behavior(root_css->cgroup))
+	if (cgroup_on_dfl(root_css->cgroup))
 		mem_cgroup_from_css(root_css)->use_hierarchy = true;
 }
 
@@ -7011,11 +7046,12 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.css_online = mem_cgroup_css_online,
 	.css_offline = mem_cgroup_css_offline,
 	.css_free = mem_cgroup_css_free,
+	.css_reset = mem_cgroup_css_reset,
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.attach = mem_cgroup_move_task,
 	.bind = mem_cgroup_bind,
-	.base_cftypes = mem_cgroup_files,
+	.legacy_cftypes = mem_cgroup_files,
 	.early_init = 0,
 };
 
@@ -7032,7 +7068,8 @@ __setup("swapaccount=", enable_swap_account);
 
 static void __init memsw_file_init(void)
 {
-	WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, memsw_cgroup_files));
+	WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys,
+					  memsw_cgroup_files));
 }
 
 static void __init enable_swap_cgroup(void)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index cd8989c1027..a013bc94ebb 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -435,7 +435,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	if (av == NULL)	/* Not actually mapped anymore */
 		return;
 
-	pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	pgoff = page_to_pgoff(page);
 	read_lock(&tasklist_lock);
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
@@ -469,7 +469,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	mutex_lock(&mapping->i_mmap_mutex);
 	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
-		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+		pgoff_t pgoff = page_to_pgoff(page);
 		struct task_struct *t = task_early_kill(tsk, force_early);
 
 		if (!t)
@@ -895,8 +895,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	struct page *hpage = *hpagep;
 	struct page *ppage;
 
+	/*
+	 * Here we are interested only in user-mapped pages, so skip any
+	 * other types of pages.
+	 */
 	if (PageReserved(p) || PageSlab(p))
 		return SWAP_SUCCESS;
+	if (!(PageLRU(hpage) || PageHuge(p)))
+		return SWAP_SUCCESS;
 
 	/*
 	 * This check implies we don't kill processes if their pages
@@ -905,8 +911,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	if (!page_mapped(hpage))
 		return SWAP_SUCCESS;
 
-	if (PageKsm(p))
+	if (PageKsm(p)) {
+		pr_err("MCE %#lx: can't handle KSM pages.\n", pfn);
 		return SWAP_FAIL;
+	}
 
 	if (PageSwapCache(p)) {
 		printk(KERN_ERR
@@ -1159,9 +1167,6 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 					action_result(pfn, "free buddy, 2nd try", DELAYED);
 				return 0;
 			}
-			action_result(pfn, "non LRU", IGNORED);
-			put_page(p);
-			return -EBUSY;
 		}
 	}
 
@@ -1194,6 +1199,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 		return 0;
 	}
 
+	if (!PageHuge(p) && !PageTransTail(p) && !PageLRU(p))
+		goto identify_page_state;
+
 	/*
 	 * For error on the tail page, we should set PG_hwpoison
 	 * on the head page to show that the hugepage is hwpoisoned
@@ -1229,7 +1237,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 */
 	if (hwpoison_user_mappings(p, pfn, trapno, flags, &hpage)
 	    != SWAP_SUCCESS) {
-		printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn);
+		action_result(pfn, "unmapping failed", IGNORED);
 		res = -EBUSY;
 		goto out;
 	}
@@ -1243,6 +1251,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 		goto out;
 	}
 
+identify_page_state:
 	res = -EBUSY;
 	/*
 	 * The first check uses the current page flags which may not have any
diff --git a/mm/memory.c b/mm/memory.c
index d67fd9fcf1f..8b44f765b64 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2758,23 +2758,18 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 	update_mmu_cache(vma, address, pte);
 }
 
-static unsigned long fault_around_bytes = 65536;
+static unsigned long fault_around_bytes = rounddown_pow_of_two(65536);
 
-/*
- * fault_around_pages() and fault_around_mask() round down fault_around_bytes
- * to nearest page order. It's what do_fault_around() expects to see.
- */
 static inline unsigned long fault_around_pages(void)
 {
-	return rounddown_pow_of_two(fault_around_bytes) / PAGE_SIZE;
+	return fault_around_bytes >> PAGE_SHIFT;
 }
 
 static inline unsigned long fault_around_mask(void)
 {
-	return ~(rounddown_pow_of_two(fault_around_bytes) - 1) & PAGE_MASK;
+	return ~(fault_around_bytes - 1) & PAGE_MASK;
 }
 
-
 #ifdef CONFIG_DEBUG_FS
 static int fault_around_bytes_get(void *data, u64 *val)
 {
@@ -2782,11 +2777,19 @@ static int fault_around_bytes_get(void *data, u64 *val)
 	return 0;
 }
 
+/*
+ * fault_around_pages() and fault_around_mask() expects fault_around_bytes
+ * rounded down to nearest page order. It's what do_fault_around() expects to
+ * see.
+ */
 static int fault_around_bytes_set(void *data, u64 val)
 {
 	if (val / PAGE_SIZE > PTRS_PER_PTE)
 		return -EINVAL;
-	fault_around_bytes = val;
+	if (val > PAGE_SIZE)
+		fault_around_bytes = rounddown_pow_of_two(val);
+	else
+		fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */
 	return 0;
 }
 DEFINE_SIMPLE_ATTRIBUTE(fault_around_bytes_fops,
@@ -2882,7 +2885,8 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * if page by the offset is not ready to be mapped (cold cache or
 	 * something).
 	 */
-	if (vma->vm_ops->map_pages && fault_around_pages() > 1) {
+	if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) &&
+	    fault_around_pages() > 1) {
 		pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 		do_fault_around(vma, address, pte, pgoff, flags);
 		if (!pte_same(*pte, orig_pte))
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 28497423045..8f5330d74f4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -656,19 +656,18 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma,
  * @nodes and @flags,) it's isolated and queued to the pagelist which is
  * passed via @private.)
  */
-static struct vm_area_struct *
+static int
 queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 		const nodemask_t *nodes, unsigned long flags, void *private)
 {
-	int err;
-	struct vm_area_struct *first, *vma, *prev;
-
+	int err = 0;
+	struct vm_area_struct *vma, *prev;
 
-	first = find_vma(mm, start);
-	if (!first)
-		return ERR_PTR(-EFAULT);
+	vma = find_vma(mm, start);
+	if (!vma)
+		return -EFAULT;
 	prev = NULL;
-	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
+	for (; vma && vma->vm_start < end; vma = vma->vm_next) {
 		unsigned long endvma = vma->vm_end;
 
 		if (endvma > end)
@@ -678,9 +677,9 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
 			if (!vma->vm_next && vma->vm_end < end)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 			if (prev && prev->vm_end < vma->vm_start)
-				return ERR_PTR(-EFAULT);
+				return -EFAULT;
 		}
 
 		if (flags & MPOL_MF_LAZY) {
@@ -694,15 +693,13 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 
 			err = queue_pages_pgd_range(vma, start, endvma, nodes,
 						flags, private);
-			if (err) {
-				first = ERR_PTR(err);
+			if (err)
 				break;
-			}
 		}
 next:
 		prev = vma;
 	}
-	return first;
+	return err;
 }
 
 /*
@@ -1156,16 +1153,17 @@ out:
 
 /*
  * Allocate a new page for page migration based on vma policy.
- * Start assuming that page is mapped by vma pointed to by @private.
+ * Start by assuming the page is mapped by the same vma as contains @start.
  * Search forward from there, if not.  N.B., this assumes that the
  * list of pages handed to migrate_pages()--which is how we get here--
  * is in virtual address order.
  */
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
-	struct vm_area_struct *vma = (struct vm_area_struct *)private;
+	struct vm_area_struct *vma;
 	unsigned long uninitialized_var(address);
 
+	vma = find_vma(current->mm, start);
 	while (vma) {
 		address = page_address_in_vma(page, vma);
 		if (address != -EFAULT)
@@ -1195,7 +1193,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	return -ENOSYS;
 }
 
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
 {
 	return NULL;
 }
@@ -1205,7 +1203,6 @@ static long do_mbind(unsigned long start, unsigned long len,
 		     unsigned short mode, unsigned short mode_flags,
 		     nodemask_t *nmask, unsigned long flags)
 {
-	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
 	struct mempolicy *new;
 	unsigned long end;
@@ -1271,11 +1268,9 @@ static long do_mbind(unsigned long start, unsigned long len,
 	if (err)
 		goto mpol_out;
 
-	vma = queue_pages_range(mm, start, end, nmask,
+	err = queue_pages_range(mm, start, end, nmask,
 			  flags | MPOL_MF_INVERT, &pagelist);
-
-	err = PTR_ERR(vma);	/* maybe ... */
-	if (!IS_ERR(vma))
+	if (!err)
 		err = mbind_range(mm, start, end, new);
 
 	if (!err) {
@@ -1283,9 +1278,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 		if (!list_empty(&pagelist)) {
 			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
-			nr_failed = migrate_pages(&pagelist, new_vma_page,
-					NULL, (unsigned long)vma,
-					MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
+			nr_failed = migrate_pages(&pagelist, new_page, NULL,
+				start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
 			if (nr_failed)
 				putback_movable_pages(&pagelist);
 		}
@@ -2145,7 +2139,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 	} else
 		*new = *old;
 
-	rcu_read_lock();
 	if (current_cpuset_is_being_rebound()) {
 		nodemask_t mems = cpuset_mems_allowed(current);
 		if (new->flags & MPOL_F_REBINDING)
@@ -2153,7 +2146,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 		else
 			mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE);
 	}
-	rcu_read_unlock();
 	atomic_set(&new->refcnt, 1);
 	return new;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 63f0cd55999..be6dbf995c0 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -120,8 +120,6 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 		pmd = mm_find_pmd(mm, addr);
 		if (!pmd)
 			goto out;
-		if (pmd_trans_huge(*pmd))
-			goto out;
 
 		ptep = pte_offset_map(pmd, addr);
 
@@ -990,9 +988,10 @@ out:
 	 * it.  Otherwise, putback_lru_page() will drop the reference grabbed
 	 * during isolation.
 	 */
-	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
+	if (rc != MIGRATEPAGE_SUCCESS && put_new_page) {
+		ClearPageSwapBacked(newpage);
 		put_new_page(newpage, private);
-	else
+	} else
 		putback_lru_page(newpage);
 
 	if (result) {
diff --git a/mm/msync.c b/mm/msync.c
index a5c673669ca..992a1673d48 100644
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -78,7 +78,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
 			goto out_unlock;
 		}
 		file = vma->vm_file;
-		fstart = start + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+		fstart = (start - vma->vm_start) +
+			 ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 		fend = fstart + (min(end, vma->vm_end) - start) - 1;
 		start = vma->vm_end;
 		if ((flags & MS_SYNC) && file &&
diff --git a/mm/nommu.c b/mm/nommu.c
index b78e3a8f5ee..4a852f6c570 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -786,7 +786,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 	for (i = 0; i < VMACACHE_SIZE; i++) {
 		/* if the vma is cached, invalidate the entire cache */
 		if (curr->vmacache[i] == vma) {
-			vmacache_invalidate(curr->mm);
+			vmacache_invalidate(mm);
 			break;
 		}
 	}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7d9a4ef0a07..e0c943014eb 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1306,9 +1306,9 @@ static inline void bdi_dirty_limits(struct backing_dev_info *bdi,
 	*bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
 
 	if (bdi_bg_thresh)
-		*bdi_bg_thresh = div_u64((u64)*bdi_thresh *
-					 background_thresh,
-					 dirty_thresh);
+		*bdi_bg_thresh = dirty_thresh ? div_u64((u64)*bdi_thresh *
+							background_thresh,
+							dirty_thresh) : 0;
 
 	/*
 	 * In order to avoid the stacked BDI deadlock we need
@@ -2380,7 +2380,7 @@ int test_clear_page_writeback(struct page *page)
 	return ret;
 }
 
-int test_set_page_writeback(struct page *page)
+int __test_set_page_writeback(struct page *page, bool keep_write)
 {
 	struct address_space *mapping = page_mapping(page);
 	int ret;
@@ -2405,9 +2405,10 @@ int test_set_page_writeback(struct page *page)
 			radix_tree_tag_clear(&mapping->page_tree,
 						page_index(page),
 						PAGECACHE_TAG_DIRTY);
-		radix_tree_tag_clear(&mapping->page_tree,
-				     page_index(page),
-				     PAGECACHE_TAG_TOWRITE);
+		if (!keep_write)
+			radix_tree_tag_clear(&mapping->page_tree,
+						page_index(page),
+						PAGECACHE_TAG_TOWRITE);
 		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	} else {
 		ret = TestSetPageWriteback(page);
@@ -2418,7 +2419,7 @@ int test_set_page_writeback(struct page *page)
 	return ret;
 
 }
-EXPORT_SYMBOL(test_set_page_writeback);
+EXPORT_SYMBOL(__test_set_page_writeback);
 
 /*
  * Return true if any of the pages in the mapping are marked with the
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4f59fa29eda..ef44ad736ca 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,6 +69,7 @@
 
 /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
 static DEFINE_MUTEX(pcp_batch_high_lock);
+#define MIN_PERCPU_PAGELIST_FRACTION	(8)
 
 #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
 DEFINE_PER_CPU(int, numa_node);
@@ -815,9 +816,21 @@ void __init init_cma_reserved_pageblock(struct page *page)
 		set_page_count(p, 0);
 	} while (++p, --i);
 
-	set_page_refcounted(page);
 	set_pageblock_migratetype(page, MIGRATE_CMA);
-	__free_pages(page, pageblock_order);
+
+	if (pageblock_order >= MAX_ORDER) {
+		i = pageblock_nr_pages;
+		p = page;
+		do {
+			set_page_refcounted(p);
+			__free_pages(p, MAX_ORDER - 1);
+			p += MAX_ORDER_NR_PAGES;
+		} while (i -= MAX_ORDER_NR_PAGES);
+	} else {
+		set_page_refcounted(page);
+		__free_pages(page, pageblock_order);
+	}
+
 	adjust_managed_page_count(page, pageblock_nr_pages);
 }
 #endif
@@ -2434,7 +2447,7 @@ static inline int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
 	int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
-	const gfp_t wait = gfp_mask & __GFP_WAIT;
+	const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
 
 	/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
 	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2443,20 +2456,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	 * The caller may dip into page reserves a bit more if the caller
 	 * cannot run direct reclaim, or if the caller has realtime scheduling
 	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
-	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
+	 * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
 	 */
 	alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
 
-	if (!wait) {
+	if (atomic) {
 		/*
-		 * Not worth trying to allocate harder for
-		 * __GFP_NOMEMALLOC even if it can't schedule.
+		 * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
+		 * if it can't schedule.
 		 */
-		if  (!(gfp_mask & __GFP_NOMEMALLOC))
+		if (!(gfp_mask & __GFP_NOMEMALLOC))
 			alloc_flags |= ALLOC_HARDER;
 		/*
-		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
-		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
+		 * comment for __cpuset_node_allowed_softwall().
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
@@ -4145,7 +4158,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
 #endif
 
-static int __meminit zone_batchsize(struct zone *zone)
+static int zone_batchsize(struct zone *zone)
 {
 #ifdef CONFIG_MMU
 	int batch;
@@ -4261,8 +4274,8 @@ static void pageset_set_high(struct per_cpu_pageset *p,
 	pageset_update(&p->pcp, high, batch);
 }
 
-static void __meminit pageset_set_high_and_batch(struct zone *zone,
-		struct per_cpu_pageset *pcp)
+static void pageset_set_high_and_batch(struct zone *zone,
+				       struct per_cpu_pageset *pcp)
 {
 	if (percpu_pagelist_fraction)
 		pageset_set_high(pcp,
@@ -5881,23 +5894,38 @@ int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write,
 	void __user *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
-	unsigned int cpu;
+	int old_percpu_pagelist_fraction;
 	int ret;
 
+	mutex_lock(&pcp_batch_high_lock);
+	old_percpu_pagelist_fraction = percpu_pagelist_fraction;
+
 	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
-	if (!write || (ret < 0))
-		return ret;
+	if (!write || ret < 0)
+		goto out;
+
+	/* Sanity checking to avoid pcp imbalance */
+	if (percpu_pagelist_fraction &&
+	    percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) {
+		percpu_pagelist_fraction = old_percpu_pagelist_fraction;
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* No change? */
+	if (percpu_pagelist_fraction == old_percpu_pagelist_fraction)
+		goto out;
 
-	mutex_lock(&pcp_batch_high_lock);
 	for_each_populated_zone(zone) {
-		unsigned long  high;
-		high = zone->managed_pages / percpu_pagelist_fraction;
+		unsigned int cpu;
+
 		for_each_possible_cpu(cpu)
-			pageset_set_high(per_cpu_ptr(zone->pageset, cpu),
-					 high);
+			pageset_set_high_and_batch(zone,
+					per_cpu_ptr(zone->pageset, cpu));
 	}
+out:
 	mutex_unlock(&pcp_batch_high_lock);
-	return 0;
+	return ret;
 }
 
 int hashdist = HASHDIST_DEFAULT;
@@ -6034,11 +6062,13 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
 }
 
 /**
- * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages
+ * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
  * @page: The page within the block of interest
- * @start_bitidx: The first bit of interest to retrieve
- * @end_bitidx: The last bit of interest
- * returns pageblock_bits flags
+ * @pfn: The target page frame number
+ * @end_bitidx: The last bit of interest to retrieve
+ * @mask: mask of bits that the caller is interested in
+ *
+ * Return: pageblock_bits flags
  */
 unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
 					unsigned long end_bitidx,
@@ -6063,9 +6093,10 @@ unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
 /**
  * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
  * @page: The page within the block of interest
- * @start_bitidx: The first bit of interest
- * @end_bitidx: The last bit of interest
  * @flags: The flags to set
+ * @pfn: The target page frame number
+ * @end_bitidx: The last bit of interest
+ * @mask: mask of bits that the caller is interested in
  */
 void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
 					unsigned long pfn,
diff --git a/mm/page_io.c b/mm/page_io.c
index 58b50d2901f..955db8b0d49 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -264,10 +264,18 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		struct kiocb kiocb;
 		struct file *swap_file = sis->swap_file;
 		struct address_space *mapping = swap_file->f_mapping;
-		struct iovec iov = {
-			.iov_base = kmap(page),
-			.iov_len  = PAGE_SIZE,
+		struct bio_vec bv = {
+			.bv_page = page,
+			.bv_len  = PAGE_SIZE,
+			.bv_offset = 0
 		};
+		struct iov_iter from = {
+			.type = ITER_BVEC | WRITE,
+			.count = PAGE_SIZE,
+			.iov_offset = 0,
+			.nr_segs = 1,
+		};
+		from.bvec = &bv;	/* older gcc versions are broken */
 
 		init_sync_kiocb(&kiocb, swap_file);
 		kiocb.ki_pos = page_file_offset(page);
@@ -275,10 +283,9 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 
 		set_page_writeback(page);
 		unlock_page(page);
-		ret = mapping->a_ops->direct_IO(KERNEL_WRITE,
-						&kiocb, &iov,
-						kiocb.ki_pos, 1);
-		kunmap(page);
+		ret = mapping->a_ops->direct_IO(ITER_BVEC | WRITE,
+						&kiocb, &from,
+						kiocb.ki_pos);
 		if (ret == PAGE_SIZE) {
 			count_vm_event(PSWPOUT);
 			ret = 0;
diff --git a/mm/percpu.c b/mm/percpu.c
index 2ddf9a990db..2139e30a4b4 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -720,8 +720,7 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved)
 	if (unlikely(align < 2))
 		align = 2;
 
-	if (unlikely(size & 1))
-		size++;
+	size = ALIGN(size, 2);
 
 	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
 		WARN(true, "illegal size (%zu) or align (%zu) for "
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 8505c9262b3..5077afcd9e1 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -46,11 +46,7 @@ static int process_vm_rw_pages(struct page **pages,
 			copy = len;
 
 		if (vm_write) {
-			if (copy > iov_iter_count(iter))
-				copy = iov_iter_count(iter);
-			copied = iov_iter_copy_from_user(page, iter,
-					offset, copy);
-			iov_iter_advance(iter, copied);
+			copied = copy_page_from_iter(page, offset, copy, iter);
 			set_page_dirty_lock(page);
 		} else {
 			copied = copy_page_to_iter(page, offset, copy, iter);
@@ -278,7 +274,7 @@ static ssize_t process_vm_rw(pid_t pid,
 	if (rc <= 0)
 		goto free_iovecs;
 
-	iov_iter_init(&iter, iov_l, liovcnt, rc, 0);
+	iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
 
 	rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
 				   iovstack_r, &iov_r);
@@ -341,7 +337,7 @@ compat_process_vm_rw(compat_pid_t pid,
 						  &iov_l);
 	if (rc <= 0)
 		goto free_iovecs;
-	iov_iter_init(&iter, iov_l, liovcnt, rc, 0);
+	iov_iter_init(&iter, vm_write ? WRITE : READ, iov_l, liovcnt, rc);
 	rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
 					  UIO_FASTIOV, iovstack_r,
 					  &iov_r);
diff --git a/mm/rmap.c b/mm/rmap.c
index bf05fc872ae..22a4a7699cd 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -517,11 +517,7 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
 static inline unsigned long
 __vma_address(struct page *page, struct vm_area_struct *vma)
 {
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-
-	if (unlikely(is_vm_hugetlb_page(vma)))
-		pgoff = page->index << huge_page_order(page_hstate(page));
-
+	pgoff_t pgoff = page_to_pgoff(page);
 	return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
 }
 
@@ -569,6 +565,7 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd = NULL;
+	pmd_t pmde;
 
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
@@ -579,7 +576,13 @@ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
 		goto out;
 
 	pmd = pmd_offset(pud, address);
-	if (!pmd_present(*pmd))
+	/*
+	 * Some THP functions use the sequence pmdp_clear_flush(), set_pmd_at()
+	 * without holding anon_vma lock for write.  So when looking for a
+	 * genuine pmde (in which to find pte), test present and !THP together.
+	 */
+	pmde = ACCESS_ONCE(*pmd);
+	if (!pmd_present(pmde) || pmd_trans_huge(pmde))
 		pmd = NULL;
 out:
 	return pmd;
@@ -615,9 +618,6 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 	if (!pmd)
 		return NULL;
 
-	if (pmd_trans_huge(*pmd))
-		return NULL;
-
 	pte = pte_offset_map(pmd, address);
 	/* Make a quick check before getting the lock */
 	if (!sync && !pte_present(*pte)) {
@@ -1635,7 +1635,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page,
 static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc)
 {
 	struct anon_vma *anon_vma;
-	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	pgoff_t pgoff = page_to_pgoff(page);
 	struct anon_vma_chain *avc;
 	int ret = SWAP_AGAIN;
 
@@ -1676,7 +1676,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc)
 static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 {
 	struct address_space *mapping = page->mapping;
-	pgoff_t pgoff = page->index << compound_order(page);
+	pgoff_t pgoff = page_to_pgoff(page);
 	struct vm_area_struct *vma;
 	int ret = SWAP_AGAIN;
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 5402481c28d..af68b15a8fc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -80,11 +80,12 @@ static struct vfsmount *shm_mnt;
 #define SHORT_SYMLINK_LEN 128
 
 /*
- * shmem_fallocate and shmem_writepage communicate via inode->i_private
- * (with i_mutex making sure that it has only one user at a time):
- * we would prefer not to enlarge the shmem inode just for that.
+ * shmem_fallocate communicates with shmem_fault or shmem_writepage via
+ * inode->i_private (with i_mutex making sure that it has only one user at
+ * a time): we would prefer not to enlarge the shmem inode just for that.
  */
 struct shmem_falloc {
+	wait_queue_head_t *waitq; /* faults into hole wait for punch to end */
 	pgoff_t start;		/* start of range currently being fallocated */
 	pgoff_t next;		/* the next page offset to be fallocated */
 	pgoff_t nr_falloced;	/* how many new pages have been fallocated */
@@ -467,23 +468,20 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		return;
 
 	index = start;
-	for ( ; ; ) {
+	while (index < end) {
 		cond_resched();
 
 		pvec.nr = find_get_entries(mapping, index,
 				min(end - index, (pgoff_t)PAGEVEC_SIZE),
 				pvec.pages, indices);
 		if (!pvec.nr) {
-			if (index == start || unfalloc)
+			/* If all gone or hole-punch or unfalloc, we're done */
+			if (index == start || end != -1)
 				break;
+			/* But if truncating, restart to make sure all gone */
 			index = start;
 			continue;
 		}
-		if ((index == start || unfalloc) && indices[0] >= end) {
-			pagevec_remove_exceptionals(&pvec);
-			pagevec_release(&pvec);
-			break;
-		}
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
@@ -495,8 +493,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if (radix_tree_exceptional_entry(page)) {
 				if (unfalloc)
 					continue;
-				nr_swaps_freed += !shmem_free_swap(mapping,
-								index, page);
+				if (shmem_free_swap(mapping, index, page)) {
+					/* Swap was replaced by page: retry */
+					index--;
+					break;
+				}
+				nr_swaps_freed++;
 				continue;
 			}
 
@@ -505,6 +507,11 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 				if (page->mapping == mapping) {
 					VM_BUG_ON_PAGE(PageWriteback(page), page);
 					truncate_inode_page(mapping, page);
+				} else {
+					/* Page was replaced by swap: retry */
+					unlock_page(page);
+					index--;
+					break;
 				}
 			}
 			unlock_page(page);
@@ -759,6 +766,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 			spin_lock(&inode->i_lock);
 			shmem_falloc = inode->i_private;
 			if (shmem_falloc &&
+			    !shmem_falloc->waitq &&
 			    index >= shmem_falloc->start &&
 			    index < shmem_falloc->next)
 				shmem_falloc->nr_unswapped++;
@@ -1027,6 +1035,9 @@ repeat:
 		goto failed;
 	}
 
+	if (page && sgp == SGP_WRITE)
+		mark_page_accessed(page);
+
 	/* fallocated page? */
 	if (page && !PageUptodate(page)) {
 		if (sgp != SGP_READ)
@@ -1108,6 +1119,9 @@ repeat:
 		shmem_recalc_inode(inode);
 		spin_unlock(&info->lock);
 
+		if (sgp == SGP_WRITE)
+			mark_page_accessed(page);
+
 		delete_from_swap_cache(page);
 		set_page_dirty(page);
 		swap_free(swap);
@@ -1134,6 +1148,9 @@ repeat:
 
 		__SetPageSwapBacked(page);
 		__set_page_locked(page);
+		if (sgp == SGP_WRITE)
+			init_page_accessed(page);
+
 		error = mem_cgroup_charge_file(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
 		if (error)
@@ -1233,6 +1250,64 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	int error;
 	int ret = VM_FAULT_LOCKED;
 
+	/*
+	 * Trinity finds that probing a hole which tmpfs is punching can
+	 * prevent the hole-punch from ever completing: which in turn
+	 * locks writers out with its hold on i_mutex.  So refrain from
+	 * faulting pages into the hole while it's being punched.  Although
+	 * shmem_undo_range() does remove the additions, it may be unable to
+	 * keep up, as each new page needs its own unmap_mapping_range() call,
+	 * and the i_mmap tree grows ever slower to scan if new vmas are added.
+	 *
+	 * It does not matter if we sometimes reach this check just before the
+	 * hole-punch begins, so that one fault then races with the punch:
+	 * we just need to make racing faults a rare case.
+	 *
+	 * The implementation below would be much simpler if we just used a
+	 * standard mutex or completion: but we cannot take i_mutex in fault,
+	 * and bloating every shmem inode for this unlikely case would be sad.
+	 */
+	if (unlikely(inode->i_private)) {
+		struct shmem_falloc *shmem_falloc;
+
+		spin_lock(&inode->i_lock);
+		shmem_falloc = inode->i_private;
+		if (shmem_falloc &&
+		    shmem_falloc->waitq &&
+		    vmf->pgoff >= shmem_falloc->start &&
+		    vmf->pgoff < shmem_falloc->next) {
+			wait_queue_head_t *shmem_falloc_waitq;
+			DEFINE_WAIT(shmem_fault_wait);
+
+			ret = VM_FAULT_NOPAGE;
+			if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
+			   !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+				/* It's polite to up mmap_sem if we can */
+				up_read(&vma->vm_mm->mmap_sem);
+				ret = VM_FAULT_RETRY;
+			}
+
+			shmem_falloc_waitq = shmem_falloc->waitq;
+			prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
+					TASK_UNINTERRUPTIBLE);
+			spin_unlock(&inode->i_lock);
+			schedule();
+
+			/*
+			 * shmem_falloc_waitq points into the shmem_fallocate()
+			 * stack of the hole-punching task: shmem_falloc_waitq
+			 * is usually invalid by the time we reach here, but
+			 * finish_wait() does not dereference it in that case;
+			 * though i_lock needed lest racing with wake_up_all().
+			 */
+			spin_lock(&inode->i_lock);
+			finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
+			spin_unlock(&inode->i_lock);
+			return ret;
+		}
+		spin_unlock(&inode->i_lock);
+	}
+
 	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
 	if (error)
 		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
@@ -1372,13 +1447,9 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
 {
-	int ret;
 	struct inode *inode = mapping->host;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	ret = shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
-	if (ret == 0 && *pagep)
-		init_page_accessed(*pagep);
-	return ret;
+	return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
 }
 
 static int
@@ -1406,8 +1477,7 @@ shmem_write_end(struct file *file, struct address_space *mapping,
 	return copied;
 }
 
-static ssize_t shmem_file_aio_read(struct kiocb *iocb,
-		const struct iovec *iov, unsigned long nr_segs, loff_t pos)
+static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
@@ -1416,15 +1486,8 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb,
 	unsigned long offset;
 	enum sgp_type sgp = SGP_READ;
 	int error = 0;
-	ssize_t retval;
-	size_t count;
+	ssize_t retval = 0;
 	loff_t *ppos = &iocb->ki_pos;
-	struct iov_iter iter;
-
-	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
-	if (retval)
-		return retval;
-	iov_iter_init(&iter, iov, nr_segs, count, 0);
 
 	/*
 	 * Might this read be for a stacking filesystem?  Then when reading
@@ -1500,14 +1563,14 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb,
 		 * Ok, we have the page, and it's up-to-date, so
 		 * now we can copy it to user space...
 		 */
-		ret = copy_page_to_iter(page, offset, nr, &iter);
+		ret = copy_page_to_iter(page, offset, nr, to);
 		retval += ret;
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
 
 		page_cache_release(page);
-		if (!iov_iter_count(&iter))
+		if (!iov_iter_count(to))
 			break;
 		if (ret < nr) {
 			error = -EFAULT;
@@ -1732,18 +1795,34 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 	pgoff_t start, index, end;
 	int error;
 
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
 	mutex_lock(&inode->i_mutex);
 
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		struct address_space *mapping = file->f_mapping;
 		loff_t unmap_start = round_up(offset, PAGE_SIZE);
 		loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
+		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
+
+		shmem_falloc.waitq = &shmem_falloc_waitq;
+		shmem_falloc.start = unmap_start >> PAGE_SHIFT;
+		shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
+		spin_lock(&inode->i_lock);
+		inode->i_private = &shmem_falloc;
+		spin_unlock(&inode->i_lock);
 
 		if ((u64)unmap_end > (u64)unmap_start)
 			unmap_mapping_range(mapping, unmap_start,
 					    1 + unmap_end - unmap_start, 0);
 		shmem_truncate_range(inode, offset, offset + len - 1);
 		/* No need to unmap again: hole-punching leaves COWed pages */
+
+		spin_lock(&inode->i_lock);
+		inode->i_private = NULL;
+		wake_up_all(&shmem_falloc_waitq);
+		spin_unlock(&inode->i_lock);
 		error = 0;
 		goto out;
 	}
@@ -1761,6 +1840,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 		goto out;
 	}
 
+	shmem_falloc.waitq = NULL;
 	shmem_falloc.start = start;
 	shmem_falloc.next  = start;
 	shmem_falloc.nr_falloced = 0;
@@ -2629,13 +2709,13 @@ static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
 #ifdef CONFIG_TMPFS
 	.llseek		= shmem_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= shmem_file_aio_read,
-	.aio_write	= generic_file_aio_write,
+	.read		= new_sync_read,
+	.write		= new_sync_write,
+	.read_iter	= shmem_file_read_iter,
+	.write_iter	= generic_file_write_iter,
 	.fsync		= noop_fsync,
 	.splice_read	= shmem_file_splice_read,
-	.splice_write	= generic_file_splice_write,
+	.splice_write	= iter_file_splice_write,
 	.fallocate	= shmem_fallocate,
 #endif
 };
diff --git a/mm/slab.c b/mm/slab.c
index 9ca3b87edab..3070b929a1b 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -386,6 +386,39 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
 
 #endif
 
+#define OBJECT_FREE (0)
+#define OBJECT_ACTIVE (1)
+
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+
+static void set_obj_status(struct page *page, int idx, int val)
+{
+	int freelist_size;
+	char *status;
+	struct kmem_cache *cachep = page->slab_cache;
+
+	freelist_size = cachep->num * sizeof(freelist_idx_t);
+	status = (char *)page->freelist + freelist_size;
+	status[idx] = val;
+}
+
+static inline unsigned int get_obj_status(struct page *page, int idx)
+{
+	int freelist_size;
+	char *status;
+	struct kmem_cache *cachep = page->slab_cache;
+
+	freelist_size = cachep->num * sizeof(freelist_idx_t);
+	status = (char *)page->freelist + freelist_size;
+
+	return status[idx];
+}
+
+#else
+static inline void set_obj_status(struct page *page, int idx, int val) {}
+
+#endif
+
 /*
  * Do not go above this order unless 0 objects fit into the slab or
  * overridden on the command line.
@@ -576,12 +609,30 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 	return cachep->array[smp_processor_id()];
 }
 
+static size_t calculate_freelist_size(int nr_objs, size_t align)
+{
+	size_t freelist_size;
+
+	freelist_size = nr_objs * sizeof(freelist_idx_t);
+	if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
+		freelist_size += nr_objs * sizeof(char);
+
+	if (align)
+		freelist_size = ALIGN(freelist_size, align);
+
+	return freelist_size;
+}
+
 static int calculate_nr_objs(size_t slab_size, size_t buffer_size,
 				size_t idx_size, size_t align)
 {
 	int nr_objs;
+	size_t remained_size;
 	size_t freelist_size;
+	int extra_space = 0;
 
+	if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
+		extra_space = sizeof(char);
 	/*
 	 * Ignore padding for the initial guess. The padding
 	 * is at most @align-1 bytes, and @buffer_size is at
@@ -590,14 +641,15 @@ static int calculate_nr_objs(size_t slab_size, size_t buffer_size,
 	 * into the memory allocation when taking the padding
 	 * into account.
 	 */
-	nr_objs = slab_size / (buffer_size + idx_size);
+	nr_objs = slab_size / (buffer_size + idx_size + extra_space);
 
 	/*
 	 * This calculated number will be either the right
 	 * amount, or one greater than what we want.
 	 */
-	freelist_size = slab_size - nr_objs * buffer_size;
-	if (freelist_size < ALIGN(nr_objs * idx_size, align))
+	remained_size = slab_size - nr_objs * buffer_size;
+	freelist_size = calculate_freelist_size(nr_objs, align);
+	if (remained_size < freelist_size)
 		nr_objs--;
 
 	return nr_objs;
@@ -635,7 +687,7 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 	} else {
 		nr_objs = calculate_nr_objs(slab_size, buffer_size,
 					sizeof(freelist_idx_t), align);
-		mgmt_size = ALIGN(nr_objs * sizeof(freelist_idx_t), align);
+		mgmt_size = calculate_freelist_size(nr_objs, align);
 	}
 	*num = nr_objs;
 	*left_over = slab_size - nr_objs*buffer_size - mgmt_size;
@@ -2041,13 +2093,16 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 			break;
 
 		if (flags & CFLGS_OFF_SLAB) {
+			size_t freelist_size_per_obj = sizeof(freelist_idx_t);
 			/*
 			 * Max number of objs-per-slab for caches which
 			 * use off-slab slabs. Needed to avoid a possible
 			 * looping condition in cache_grow().
 			 */
+			if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
+				freelist_size_per_obj += sizeof(char);
 			offslab_limit = size;
-			offslab_limit /= sizeof(freelist_idx_t);
+			offslab_limit /= freelist_size_per_obj;
 
  			if (num > offslab_limit)
 				break;
@@ -2294,8 +2349,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 	if (!cachep->num)
 		return -E2BIG;
 
-	freelist_size =
-		ALIGN(cachep->num * sizeof(freelist_idx_t), cachep->align);
+	freelist_size = calculate_freelist_size(cachep->num, cachep->align);
 
 	/*
 	 * If the slab has been placed off-slab, and we have enough space then
@@ -2308,7 +2362,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 
 	if (flags & CFLGS_OFF_SLAB) {
 		/* really off slab. No need for manual alignment */
-		freelist_size = cachep->num * sizeof(freelist_idx_t);
+		freelist_size = calculate_freelist_size(cachep->num, 0);
 
 #ifdef CONFIG_PAGE_POISONING
 		/* If we're going to use the generic kernel_map_pages()
@@ -2612,6 +2666,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
 		if (cachep->ctor)
 			cachep->ctor(objp);
 #endif
+		set_obj_status(page, i, OBJECT_FREE);
 		set_free_obj(page, i, i);
 	}
 }
@@ -2820,6 +2875,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	BUG_ON(objnr >= cachep->num);
 	BUG_ON(objp != index_to_obj(cachep, page, objnr));
 
+	set_obj_status(page, objnr, OBJECT_FREE);
 	if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
 		if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
@@ -2953,6 +3009,8 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
 static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 				gfp_t flags, void *objp, unsigned long caller)
 {
+	struct page *page;
+
 	if (!objp)
 		return objp;
 	if (cachep->flags & SLAB_POISON) {
@@ -2983,6 +3041,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 		*dbg_redzone1(cachep, objp) = RED_ACTIVE;
 		*dbg_redzone2(cachep, objp) = RED_ACTIVE;
 	}
+
+	page = virt_to_head_page(objp);
+	set_obj_status(page, obj_to_index(cachep, page, objp), OBJECT_ACTIVE);
 	objp += obj_offset(cachep);
 	if (cachep->ctor && cachep->flags & SLAB_POISON)
 		cachep->ctor(objp);
@@ -4219,21 +4280,12 @@ static void handle_slab(unsigned long *n, struct kmem_cache *c,
 						struct page *page)
 {
 	void *p;
-	int i, j;
+	int i;
 
 	if (n[0] == n[1])
 		return;
 	for (i = 0, p = page->s_mem; i < c->num; i++, p += c->size) {
-		bool active = true;
-
-		for (j = page->active; j < c->num; j++) {
-			/* Skip freed item */
-			if (get_free_obj(page, j) == i) {
-				active = false;
-				break;
-			}
-		}
-		if (!active)
+		if (get_obj_status(page, i) != OBJECT_ACTIVE)
 			continue;
 
 		if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 735e01a0db6..d31c4bacc6a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -55,7 +55,7 @@ static int kmem_cache_sanity_check(const char *name, size_t size)
 			continue;
 		}
 
-#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON)
+#if !defined(CONFIG_SLUB)
 		if (!strcmp(s->name, name)) {
 			pr_err("%s (%s): Cache name already exists.\n",
 			       __func__, name);
diff --git a/mm/slub.c b/mm/slub.c
index b2b047327d7..73004808537 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1881,7 +1881,7 @@ redo:
 
 	new.frozen = 0;
 
-	if (!new.inuse && n->nr_partial > s->min_partial)
+	if (!new.inuse && n->nr_partial >= s->min_partial)
 		m = M_FREE;
 	else if (new.freelist) {
 		m = M_PARTIAL;
@@ -1992,7 +1992,7 @@ static void unfreeze_partials(struct kmem_cache *s,
 				new.freelist, new.counters,
 				"unfreezing slab"));
 
-		if (unlikely(!new.inuse && n->nr_partial > s->min_partial)) {
+		if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) {
 			page->next = discard_page;
 			discard_page = page;
 		} else {
@@ -2620,7 +2620,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
                 return;
         }
 
-	if (unlikely(!new.inuse && n->nr_partial > s->min_partial))
+	if (unlikely(!new.inuse && n->nr_partial >= s->min_partial))
 		goto slab_empty;
 
 	/*
diff --git a/mm/truncate.c b/mm/truncate.c
index 6a78c814beb..eda24730716 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -355,14 +355,16 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	for ( ; ; ) {
 		cond_resched();
 		if (!pagevec_lookup_entries(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE),
-			indices)) {
+			min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) {
+			/* If all gone from start onwards, we're done */
 			if (index == start)
 				break;
+			/* Otherwise restart to make sure all gone */
 			index = start;
 			continue;
 		}
 		if (index == start && indices[0] >= end) {
+			/* All gone out of hole to be punched, we're done */
 			pagevec_remove_exceptionals(&pvec);
 			pagevec_release(&pvec);
 			break;
@@ -373,8 +375,11 @@ void truncate_inode_pages_range(struct address_space *mapping,
 
 			/* We rely upon deletion not changing page->index */
 			index = indices[i];
-			if (index >= end)
+			if (index >= end) {
+				/* Restart punch to make sure all gone */
+				index = start - 1;
 				break;
+			}
 
 			if (radix_tree_exceptional_entry(page)) {
 				clear_exceptional_entry(mapping, index, page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 71f23c0c109..0f16ffe8eb6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -464,7 +464,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 	 * stalls if we need to run get_block().  We could test
 	 * PagePrivate for that.
 	 *
-	 * If this process is currently in __generic_file_aio_write() against
+	 * If this process is currently in __generic_file_write_iter() against
 	 * this page's queue, we can perform writeback even if that
 	 * will block.
 	 *
@@ -1573,20 +1573,18 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		 * If dirty pages are scanned that are not queued for IO, it
 		 * implies that flushers are not keeping up. In this case, flag
 		 * the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
-		 * pages from reclaim context. It will forcibly stall in the
-		 * next check.
+		 * pages from reclaim context.
 		 */
 		if (nr_unqueued_dirty == nr_taken)
 			zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
 
 		/*
-		 * In addition, if kswapd scans pages marked marked for
-		 * immediate reclaim and under writeback (nr_immediate), it
-		 * implies that pages are cycling through the LRU faster than
+		 * If kswapd scans pages marked marked for immediate
+		 * reclaim and under writeback (nr_immediate), it implies
+		 * that pages are cycling through the LRU faster than
 		 * they are written so also forcibly stall.
 		 */
-		if ((nr_unqueued_dirty == nr_taken || nr_immediate) &&
-		    current_may_throttle())
+		if (nr_immediate && current_may_throttle())
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 3c32bd257b7..75d42776399 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -63,7 +63,7 @@ bool vlan_do_receive(struct sk_buff **skbp)
 }
 
 /* Must be invoked with rcu_read_lock. */
-struct net_device *__vlan_find_dev_deep(struct net_device *dev,
+struct net_device *__vlan_find_dev_deep_rcu(struct net_device *dev,
 					__be16 vlan_proto, u16 vlan_id)
 {
 	struct vlan_info *vlan_info = rcu_dereference(dev->vlan_info);
@@ -81,13 +81,13 @@ struct net_device *__vlan_find_dev_deep(struct net_device *dev,
 
 		upper_dev = netdev_master_upper_dev_get_rcu(dev);
 		if (upper_dev)
-			return __vlan_find_dev_deep(upper_dev,
+			return __vlan_find_dev_deep_rcu(upper_dev,
 						    vlan_proto, vlan_id);
 	}
 
 	return NULL;
 }
-EXPORT_SYMBOL(__vlan_find_dev_deep);
+EXPORT_SYMBOL(__vlan_find_dev_deep_rcu);
 
 struct net_device *vlan_dev_real_dev(const struct net_device *dev)
 {
@@ -114,8 +114,11 @@ EXPORT_SYMBOL(vlan_dev_vlan_proto);
 
 static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
 {
-	if (skb_cow(skb, skb_headroom(skb)) < 0)
+	if (skb_cow(skb, skb_headroom(skb)) < 0) {
+		kfree_skb(skb);
 		return NULL;
+	}
+
 	memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN);
 	skb->mac_header += VLAN_HLEN;
 	return skb;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 019efb79708..dd11f612e03 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -627,8 +627,6 @@ static void vlan_dev_uninit(struct net_device *dev)
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	int i;
 
-	free_percpu(vlan->vlan_pcpu_stats);
-	vlan->vlan_pcpu_stats = NULL;
 	for (i = 0; i < ARRAY_SIZE(vlan->egress_priority_map); i++) {
 		while ((pm = vlan->egress_priority_map[i]) != NULL) {
 			vlan->egress_priority_map[i] = pm->next;
@@ -643,9 +641,9 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev,
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	netdev_features_t old_features = features;
 
-	features &= real_dev->vlan_features;
+	features = netdev_intersect_features(features, real_dev->vlan_features);
 	features |= NETIF_F_RXCSUM;
-	features &= real_dev->features;
+	features = netdev_intersect_features(features, real_dev->features);
 
 	features |= old_features & NETIF_F_SOFT_FEATURES;
 	features |= NETIF_F_LLTX;
@@ -671,38 +669,36 @@ static void vlan_ethtool_get_drvinfo(struct net_device *dev,
 
 static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
+	struct vlan_pcpu_stats *p;
+	u32 rx_errors = 0, tx_dropped = 0;
+	int i;
 
-	if (vlan_dev_priv(dev)->vlan_pcpu_stats) {
-		struct vlan_pcpu_stats *p;
-		u32 rx_errors = 0, tx_dropped = 0;
-		int i;
-
-		for_each_possible_cpu(i) {
-			u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes;
-			unsigned int start;
-
-			p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
-			do {
-				start = u64_stats_fetch_begin_irq(&p->syncp);
-				rxpackets	= p->rx_packets;
-				rxbytes		= p->rx_bytes;
-				rxmulticast	= p->rx_multicast;
-				txpackets	= p->tx_packets;
-				txbytes		= p->tx_bytes;
-			} while (u64_stats_fetch_retry_irq(&p->syncp, start));
-
-			stats->rx_packets	+= rxpackets;
-			stats->rx_bytes		+= rxbytes;
-			stats->multicast	+= rxmulticast;
-			stats->tx_packets	+= txpackets;
-			stats->tx_bytes		+= txbytes;
-			/* rx_errors & tx_dropped are u32 */
-			rx_errors	+= p->rx_errors;
-			tx_dropped	+= p->tx_dropped;
-		}
-		stats->rx_errors  = rx_errors;
-		stats->tx_dropped = tx_dropped;
+	for_each_possible_cpu(i) {
+		u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes;
+		unsigned int start;
+
+		p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
+		do {
+			start = u64_stats_fetch_begin_irq(&p->syncp);
+			rxpackets	= p->rx_packets;
+			rxbytes		= p->rx_bytes;
+			rxmulticast	= p->rx_multicast;
+			txpackets	= p->tx_packets;
+			txbytes		= p->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
+
+		stats->rx_packets	+= rxpackets;
+		stats->rx_bytes		+= rxbytes;
+		stats->multicast	+= rxmulticast;
+		stats->tx_packets	+= txpackets;
+		stats->tx_bytes		+= txbytes;
+		/* rx_errors & tx_dropped are u32 */
+		rx_errors	+= p->rx_errors;
+		tx_dropped	+= p->tx_dropped;
 	}
+	stats->rx_errors  = rx_errors;
+	stats->tx_dropped = tx_dropped;
+
 	return stats;
 }
 
@@ -787,6 +783,15 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_get_lock_subclass  = vlan_dev_get_lock_subclass,
 };
 
+static void vlan_dev_free(struct net_device *dev)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+
+	free_percpu(vlan->vlan_pcpu_stats);
+	vlan->vlan_pcpu_stats = NULL;
+	free_netdev(dev);
+}
+
 void vlan_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -796,7 +801,7 @@ void vlan_setup(struct net_device *dev)
 	dev->tx_queue_len	= 0;
 
 	dev->netdev_ops		= &vlan_netdev_ops;
-	dev->destructor		= free_netdev;
+	dev->destructor		= vlan_dev_free;
 	dev->ethtool_ops	= &vlan_ethtool_ops;
 
 	memset(dev->broadcast, 0, ETH_ALEN);
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 786ee2f83d5..bfcf6be1d66 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1489,8 +1489,6 @@ static int atalk_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 
 	/* Queue packet (standard) */
-	skb->sk = sock;
-
 	if (sock_queue_rcv_skb(sock, skb) < 0)
 		goto drop;
 
@@ -1644,7 +1642,6 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 	if (!skb)
 		goto out;
 
-	skb->sk = sk;
 	skb_reserve(skb, ddp_dl->header_length);
 	skb_reserve(skb, dev->hard_header_len);
 	skb->dev = dev;
@@ -1669,7 +1666,7 @@ static int atalk_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr
 		goto out;
 	}
 
-	if (sk->sk_no_check == 1)
+	if (sk->sk_no_check_tx)
 		ddp->deh_sum = 0;
 	else
 		ddp->deh_sum = atalk_checksum(skb, len + sizeof(*ddp));
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 1281049c135..d8e5d0c2ebb 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -263,17 +263,11 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr,
 			goto out;
 		}
 	}
-/*
- * Not supported yet
- *
- * #ifndef CONFIG_SINGLE_SIGITF
- */
+
 	vcc->qos.txtp.max_pcr = SELECT_TOP_PCR(vcc->qos.txtp);
 	vcc->qos.txtp.pcr = 0;
 	vcc->qos.txtp.min_pcr = 0;
-/*
- * #endif
- */
+
 	error = vcc_connect(sock, vcc->itf, vcc->vpi, vcc->vci);
 	if (!error)
 		sock->state = SS_CONNECTED;
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 6f0d9ec3795..a957c814072 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -800,11 +800,6 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv,
 	bla_dst = (struct batadv_bla_claim_dst *)hw_dst;
 	bla_dst_own = &bat_priv->bla.claim_dest;
 
-	/* check if it is a claim packet in general */
-	if (memcmp(bla_dst->magic, bla_dst_own->magic,
-		   sizeof(bla_dst->magic)) != 0)
-		return 0;
-
 	/* if announcement packet, use the source,
 	 * otherwise assume it is in the hw_src
 	 */
@@ -866,12 +861,13 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
 				    struct batadv_hard_iface *primary_if,
 				    struct sk_buff *skb)
 {
-	struct batadv_bla_claim_dst *bla_dst;
+	struct batadv_bla_claim_dst *bla_dst, *bla_dst_own;
 	uint8_t *hw_src, *hw_dst;
-	struct vlan_ethhdr *vhdr;
+	struct vlan_hdr *vhdr, vhdr_buf;
 	struct ethhdr *ethhdr;
 	struct arphdr *arphdr;
 	unsigned short vid;
+	int vlan_depth = 0;
 	__be16 proto;
 	int headlen;
 	int ret;
@@ -882,9 +878,24 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
 	proto = ethhdr->h_proto;
 	headlen = ETH_HLEN;
 	if (vid & BATADV_VLAN_HAS_TAG) {
-		vhdr = vlan_eth_hdr(skb);
-		proto = vhdr->h_vlan_encapsulated_proto;
-		headlen += VLAN_HLEN;
+		/* Traverse the VLAN/Ethertypes.
+		 *
+		 * At this point it is known that the first protocol is a VLAN
+		 * header, so start checking at the encapsulated protocol.
+		 *
+		 * The depth of the VLAN headers is recorded to drop BLA claim
+		 * frames encapsulated into multiple VLAN headers (QinQ).
+		 */
+		do {
+			vhdr = skb_header_pointer(skb, headlen, VLAN_HLEN,
+						  &vhdr_buf);
+			if (!vhdr)
+				return 0;
+
+			proto = vhdr->h_vlan_encapsulated_proto;
+			headlen += VLAN_HLEN;
+			vlan_depth++;
+		} while (proto == htons(ETH_P_8021Q));
 	}
 
 	if (proto != htons(ETH_P_ARP))
@@ -914,6 +925,19 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
 	hw_src = (uint8_t *)arphdr + sizeof(struct arphdr);
 	hw_dst = hw_src + ETH_ALEN + 4;
 	bla_dst = (struct batadv_bla_claim_dst *)hw_dst;
+	bla_dst_own = &bat_priv->bla.claim_dest;
+
+	/* check if it is a claim frame in general */
+	if (memcmp(bla_dst->magic, bla_dst_own->magic,
+		   sizeof(bla_dst->magic)) != 0)
+		return 0;
+
+	/* check if there is a claim frame encapsulated deeper in (QinQ) and
+	 * drop that, as this is not supported by BLA but should also not be
+	 * sent via the mesh.
+	 */
+	if (vlan_depth > 1)
+		return 1;
 
 	/* check if it is a claim frame. */
 	ret = batadv_check_claim_group(bat_priv, primary_if, hw_src, hw_dst,
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index b758881be10..a12e25efaf6 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -245,6 +245,7 @@ static int batadv_algorithms_open(struct inode *inode, struct file *file)
 static int batadv_originators_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_orig_seq_print_text, net_dev);
 }
 
@@ -258,18 +259,21 @@ static int batadv_originators_hardif_open(struct inode *inode,
 					  struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_orig_hardif_seq_print_text, net_dev);
 }
 
 static int batadv_gateways_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_gw_client_seq_print_text, net_dev);
 }
 
 static int batadv_transtable_global_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_tt_global_seq_print_text, net_dev);
 }
 
@@ -277,6 +281,7 @@ static int batadv_transtable_global_open(struct inode *inode, struct file *file)
 static int batadv_bla_claim_table_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_bla_claim_table_seq_print_text,
 			   net_dev);
 }
@@ -285,6 +290,7 @@ static int batadv_bla_backbone_table_open(struct inode *inode,
 					  struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_bla_backbone_table_seq_print_text,
 			   net_dev);
 }
@@ -300,6 +306,7 @@ static int batadv_bla_backbone_table_open(struct inode *inode,
 static int batadv_dat_cache_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_dat_cache_seq_print_text, net_dev);
 }
 #endif
@@ -307,6 +314,7 @@ static int batadv_dat_cache_open(struct inode *inode, struct file *file)
 static int batadv_transtable_local_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_tt_local_seq_print_text, net_dev);
 }
 
@@ -319,6 +327,7 @@ struct batadv_debuginfo {
 static int batadv_nc_nodes_open(struct inode *inode, struct file *file)
 {
 	struct net_device *net_dev = (struct net_device *)inode->i_private;
+
 	return single_open(file, batadv_nc_nodes_seq_print_text, net_dev);
 }
 #endif
@@ -333,7 +342,7 @@ struct batadv_debuginfo batadv_debuginfo_##_name = {	\
 		  .llseek = seq_lseek,			\
 		  .release = single_release,		\
 		}					\
-};
+}
 
 /* the following attributes are general and therefore they will be directly
  * placed in the BATADV_DEBUGFS_SUBDIR subdirectory of debugfs
@@ -395,7 +404,7 @@ struct batadv_debuginfo batadv_hardif_debuginfo_##_name = {	\
 		.llseek = seq_lseek,				\
 		.release = single_release,			\
 	},							\
-};
+}
 static BATADV_HARDIF_DEBUGINFO(originators, S_IRUGO,
 			       batadv_originators_hardif_open);
 
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index aa5d4946d0d..f2c066b2171 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -594,7 +594,7 @@ static bool batadv_dat_send_data(struct batadv_priv *bat_priv,
 		if (!neigh_node)
 			goto free_orig;
 
-		tmp_skb = pskb_copy(skb, GFP_ATOMIC);
+		tmp_skb = pskb_copy_for_clone(skb, GFP_ATOMIC);
 		if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, tmp_skb,
 							   cand[i].orig_node,
 							   packet_subtype)) {
@@ -662,6 +662,7 @@ static void batadv_dat_tvlv_container_update(struct batadv_priv *bat_priv)
 void batadv_dat_status_update(struct net_device *net_dev)
 {
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);
+
 	batadv_dat_tvlv_container_update(bat_priv);
 }
 
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 770dc890cee..118b990bae2 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -24,7 +24,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2014.2.0"
+#define BATADV_SOURCE_VERSION "2014.3.0"
 #endif
 
 /* B.A.T.M.A.N. parameters */
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index a9546fe541e..8d04d174669 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -86,6 +86,7 @@ static void batadv_nc_tvlv_container_update(struct batadv_priv *bat_priv)
 void batadv_nc_status_update(struct net_device *net_dev)
 {
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);
+
 	batadv_nc_tvlv_container_update(bat_priv);
 }
 
@@ -1343,7 +1344,7 @@ static void batadv_nc_skb_store_before_coding(struct batadv_priv *bat_priv,
 	struct ethhdr *ethhdr;
 
 	/* Copy skb header to change the mac header */
-	skb = pskb_copy(skb, GFP_ATOMIC);
+	skb = pskb_copy_for_clone(skb, GFP_ATOMIC);
 	if (!skb)
 		return;
 
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 744a59b85e1..cbd677f48c0 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -448,10 +448,15 @@ out:
  *  possibly free it
  * @softif_vlan: the vlan object to release
  */
-void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *softif_vlan)
+void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *vlan)
 {
-	if (atomic_dec_and_test(&softif_vlan->refcount))
-		kfree_rcu(softif_vlan, rcu);
+	if (atomic_dec_and_test(&vlan->refcount)) {
+		spin_lock_bh(&vlan->bat_priv->softif_vlan_list_lock);
+		hlist_del_rcu(&vlan->list);
+		spin_unlock_bh(&vlan->bat_priv->softif_vlan_list_lock);
+
+		kfree_rcu(vlan, rcu);
+	}
 }
 
 /**
@@ -505,6 +510,7 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 	if (!vlan)
 		return -ENOMEM;
 
+	vlan->bat_priv = bat_priv;
 	vlan->vid = vid;
 	atomic_set(&vlan->refcount, 1);
 
@@ -516,6 +522,10 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 		return err;
 	}
 
+	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
+	hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
+	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
+
 	/* add a new TT local entry. This one will be marked with the NOPURGE
 	 * flag
 	 */
@@ -523,10 +533,6 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 			    bat_priv->soft_iface->dev_addr, vid,
 			    BATADV_NULL_IFINDEX, BATADV_NO_MARK);
 
-	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
-	hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
-	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
-
 	return 0;
 }
 
@@ -538,18 +544,13 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 static void batadv_softif_destroy_vlan(struct batadv_priv *bat_priv,
 				       struct batadv_softif_vlan *vlan)
 {
-	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
-	hlist_del_rcu(&vlan->list);
-	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
-
-	batadv_sysfs_del_vlan(bat_priv, vlan);
-
 	/* explicitly remove the associated TT local entry because it is marked
 	 * with the NOPURGE flag
 	 */
 	batadv_tt_local_remove(bat_priv, bat_priv->soft_iface->dev_addr,
 			       vlan->vid, "vlan interface destroyed", false);
 
+	batadv_sysfs_del_vlan(bat_priv, vlan);
 	batadv_softif_vlan_free_ref(vlan);
 }
 
@@ -567,6 +568,8 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
 				    unsigned short vid)
 {
 	struct batadv_priv *bat_priv = netdev_priv(dev);
+	struct batadv_softif_vlan *vlan;
+	int ret;
 
 	/* only 802.1Q vlans are supported.
 	 * batman-adv does not know how to handle other types
@@ -576,7 +579,36 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
 
 	vid |= BATADV_VLAN_HAS_TAG;
 
-	return batadv_softif_create_vlan(bat_priv, vid);
+	/* if a new vlan is getting created and it already exists, it means that
+	 * it was not deleted yet. batadv_softif_vlan_get() increases the
+	 * refcount in order to revive the object.
+	 *
+	 * if it does not exist then create it.
+	 */
+	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	if (!vlan)
+		return batadv_softif_create_vlan(bat_priv, vid);
+
+	/* recreate the sysfs object if it was already destroyed (and it should
+	 * be since we received a kill_vid() for this vlan
+	 */
+	if (!vlan->kobj) {
+		ret = batadv_sysfs_add_vlan(bat_priv->soft_iface, vlan);
+		if (ret) {
+			batadv_softif_vlan_free_ref(vlan);
+			return ret;
+		}
+	}
+
+	/* add a new TT local entry. This one will be marked with the NOPURGE
+	 * flag. This must be added again, even if the vlan object already
+	 * exists, because the entry was deleted by kill_vid()
+	 */
+	batadv_tt_local_add(bat_priv->soft_iface,
+			    bat_priv->soft_iface->dev_addr, vid,
+			    BATADV_NULL_IFINDEX, BATADV_NO_MARK);
+
+	return 0;
 }
 
 /**
@@ -884,7 +916,7 @@ static void batadv_softif_init_early(struct net_device *dev)
 	/* generate random address */
 	eth_hw_addr_random(dev);
 
-	SET_ETHTOOL_OPS(dev, &batadv_ethtool_ops);
+	dev->ethtool_ops = &batadv_ethtool_ops;
 
 	memset(priv, 0, sizeof(*priv));
 }
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 1ebb0d9e2ea..fc47baa888c 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -29,12 +29,14 @@
 static struct net_device *batadv_kobj_to_netdev(struct kobject *obj)
 {
 	struct device *dev = container_of(obj->parent, struct device, kobj);
+
 	return to_net_dev(dev);
 }
 
 static struct batadv_priv *batadv_kobj_to_batpriv(struct kobject *obj)
 {
 	struct net_device *net_dev = batadv_kobj_to_netdev(obj);
+
 	return netdev_priv(net_dev);
 }
 
@@ -106,7 +108,7 @@ struct batadv_attribute batadv_attr_vlan_##_name = {	\
 		 .mode = _mode },			\
 	.show   = _show,				\
 	.store  = _store,				\
-};
+}
 
 /* Use this, if you have customized show and store functions */
 #define BATADV_ATTR(_name, _mode, _show, _store)	\
@@ -115,7 +117,7 @@ struct batadv_attribute batadv_attr_##_name = {		\
 		 .mode = _mode },			\
 	.show   = _show,				\
 	.store  = _store,				\
-};
+}
 
 #define BATADV_ATTR_SIF_STORE_BOOL(_name, _post_func)			\
 ssize_t batadv_store_##_name(struct kobject *kobj,			\
@@ -124,6 +126,7 @@ ssize_t batadv_store_##_name(struct kobject *kobj,			\
 {									\
 	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);	\
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);		\
+									\
 	return __batadv_store_bool_attr(buff, count, _post_func, attr,	\
 					&bat_priv->_name, net_dev);	\
 }
@@ -133,6 +136,7 @@ ssize_t batadv_show_##_name(struct kobject *kobj,			\
 			    struct attribute *attr, char *buff)		\
 {									\
 	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);	\
+									\
 	return sprintf(buff, "%s\n",					\
 		       atomic_read(&bat_priv->_name) == 0 ?		\
 		       "disabled" : "enabled");				\
@@ -155,6 +159,7 @@ ssize_t batadv_store_##_name(struct kobject *kobj,			\
 {									\
 	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);	\
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);		\
+									\
 	return __batadv_store_uint_attr(buff, count, _min, _max,	\
 					_post_func, attr,		\
 					&bat_priv->_name, net_dev);	\
@@ -165,6 +170,7 @@ ssize_t batadv_show_##_name(struct kobject *kobj,			\
 			    struct attribute *attr, char *buff)		\
 {									\
 	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);	\
+									\
 	return sprintf(buff, "%i\n", atomic_read(&bat_priv->_name));	\
 }									\
 
@@ -188,6 +194,7 @@ ssize_t batadv_store_vlan_##_name(struct kobject *kobj,			\
 	size_t res = __batadv_store_bool_attr(buff, count, _post_func,	\
 					      attr, &vlan->_name,	\
 					      bat_priv->soft_iface);	\
+									\
 	batadv_softif_vlan_free_ref(vlan);				\
 	return res;							\
 }
@@ -202,6 +209,7 @@ ssize_t batadv_show_vlan_##_name(struct kobject *kobj,			\
 	size_t res = sprintf(buff, "%s\n",				\
 			     atomic_read(&vlan->_name) == 0 ?		\
 			     "disabled" : "enabled");			\
+									\
 	batadv_softif_vlan_free_ref(vlan);				\
 	return res;							\
 }
@@ -324,12 +332,14 @@ static ssize_t batadv_show_bat_algo(struct kobject *kobj,
 				    struct attribute *attr, char *buff)
 {
 	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
+
 	return sprintf(buff, "%s\n", bat_priv->bat_algo_ops->name);
 }
 
 static void batadv_post_gw_reselect(struct net_device *net_dev)
 {
 	struct batadv_priv *bat_priv = netdev_priv(net_dev);
+
 	batadv_gw_reselect(bat_priv);
 }
 
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index d636bde72c9..5f59e7f899a 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -511,6 +511,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
 	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
 	struct batadv_tt_local_entry *tt_local;
 	struct batadv_tt_global_entry *tt_global = NULL;
+	struct batadv_softif_vlan *vlan;
 	struct net_device *in_dev = NULL;
 	struct hlist_head *head;
 	struct batadv_tt_orig_list_entry *orig_entry;
@@ -572,6 +573,9 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
 	if (!tt_local)
 		goto out;
 
+	/* increase the refcounter of the related vlan */
+	vlan = batadv_softif_vlan_get(bat_priv, vid);
+
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n",
 		   addr, BATADV_PRINT_VID(vid),
@@ -604,6 +608,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
 	if (unlikely(hash_added != 0)) {
 		/* remove the reference for the hash */
 		batadv_tt_local_entry_free_ref(tt_local);
+		batadv_softif_vlan_free_ref(vlan);
 		goto out;
 	}
 
@@ -1009,6 +1014,7 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv,
 {
 	struct batadv_tt_local_entry *tt_local_entry;
 	uint16_t flags, curr_flags = BATADV_NO_FLAGS;
+	struct batadv_softif_vlan *vlan;
 
 	tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid);
 	if (!tt_local_entry)
@@ -1039,6 +1045,11 @@ uint16_t batadv_tt_local_remove(struct batadv_priv *bat_priv,
 	hlist_del_rcu(&tt_local_entry->common.hash_entry);
 	batadv_tt_local_entry_free_ref(tt_local_entry);
 
+	/* decrease the reference held for this vlan */
+	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	batadv_softif_vlan_free_ref(vlan);
+	batadv_softif_vlan_free_ref(vlan);
+
 out:
 	if (tt_local_entry)
 		batadv_tt_local_entry_free_ref(tt_local_entry);
@@ -1111,6 +1122,7 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv)
 	spinlock_t *list_lock; /* protects write access to the hash lists */
 	struct batadv_tt_common_entry *tt_common_entry;
 	struct batadv_tt_local_entry *tt_local;
+	struct batadv_softif_vlan *vlan;
 	struct hlist_node *node_tmp;
 	struct hlist_head *head;
 	uint32_t i;
@@ -1131,6 +1143,13 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv)
 			tt_local = container_of(tt_common_entry,
 						struct batadv_tt_local_entry,
 						common);
+
+			/* decrease the reference held for this vlan */
+			vlan = batadv_softif_vlan_get(bat_priv,
+						      tt_common_entry->vid);
+			batadv_softif_vlan_free_ref(vlan);
+			batadv_softif_vlan_free_ref(vlan);
+
 			batadv_tt_local_entry_free_ref(tt_local);
 		}
 		spin_unlock_bh(list_lock);
@@ -3139,6 +3158,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)
 	struct batadv_hashtable *hash = bat_priv->tt.local_hash;
 	struct batadv_tt_common_entry *tt_common;
 	struct batadv_tt_local_entry *tt_local;
+	struct batadv_softif_vlan *vlan;
 	struct hlist_node *node_tmp;
 	struct hlist_head *head;
 	spinlock_t *list_lock; /* protects write access to the hash lists */
@@ -3167,6 +3187,12 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)
 			tt_local = container_of(tt_common,
 						struct batadv_tt_local_entry,
 						common);
+
+			/* decrease the reference held for this vlan */
+			vlan = batadv_softif_vlan_get(bat_priv, tt_common->vid);
+			batadv_softif_vlan_free_ref(vlan);
+			batadv_softif_vlan_free_ref(vlan);
+
 			batadv_tt_local_entry_free_ref(tt_local);
 		}
 		spin_unlock_bh(list_lock);
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 34891a56773..8854c05622a 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -687,6 +687,7 @@ struct batadv_priv_nc {
 
 /**
  * struct batadv_softif_vlan - per VLAN attributes set
+ * @bat_priv: pointer to the mesh object
  * @vid: VLAN identifier
  * @kobj: kobject for sysfs vlan subdirectory
  * @ap_isolation: AP isolation state
@@ -696,6 +697,7 @@ struct batadv_priv_nc {
  * @rcu: struct used for freeing in a RCU-safe manner
  */
 struct batadv_softif_vlan {
+	struct batadv_priv *bat_priv;
 	unsigned short vid;
 	struct kobject *kobj;
 	atomic_t ap_isolation;		/* boolean */
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 73492b91105..8796ffa08b4 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -420,12 +420,18 @@ static int conn_send(struct l2cap_conn *conn,
 	return 0;
 }
 
-static void get_dest_bdaddr(struct in6_addr *ip6_daddr,
-			    bdaddr_t *addr, u8 *addr_type)
+static u8 get_addr_type_from_eui64(u8 byte)
 {
-	u8 *eui64;
+	/* Is universal(0) or local(1) bit,  */
+	if (byte & 0x02)
+		return ADDR_LE_DEV_RANDOM;
 
-	eui64 = ip6_daddr->s6_addr + 8;
+	return ADDR_LE_DEV_PUBLIC;
+}
+
+static void copy_to_bdaddr(struct in6_addr *ip6_daddr, bdaddr_t *addr)
+{
+	u8 *eui64 = ip6_daddr->s6_addr + 8;
 
 	addr->b[0] = eui64[7];
 	addr->b[1] = eui64[6];
@@ -433,16 +439,19 @@ static void get_dest_bdaddr(struct in6_addr *ip6_daddr,
 	addr->b[3] = eui64[2];
 	addr->b[4] = eui64[1];
 	addr->b[5] = eui64[0];
+}
 
-	addr->b[5] ^= 2;
+static void convert_dest_bdaddr(struct in6_addr *ip6_daddr,
+				bdaddr_t *addr, u8 *addr_type)
+{
+	copy_to_bdaddr(ip6_daddr, addr);
 
-	/* Set universal/local bit to 0 */
-	if (addr->b[5] & 1) {
-		addr->b[5] &= ~1;
-		*addr_type = ADDR_LE_DEV_PUBLIC;
-	} else {
-		*addr_type = ADDR_LE_DEV_RANDOM;
-	}
+	/* We need to toggle the U/L bit that we got from IPv6 address
+	 * so that we get the proper address and type of the BD address.
+	 */
+	addr->b[5] ^= 0x02;
+
+	*addr_type = get_addr_type_from_eui64(addr->b[5]);
 }
 
 static int header_create(struct sk_buff *skb, struct net_device *netdev,
@@ -473,9 +482,11 @@ static int header_create(struct sk_buff *skb, struct net_device *netdev,
 		/* Get destination BT device from skb.
 		 * If there is no such peer then discard the packet.
 		 */
-		get_dest_bdaddr(&hdr->daddr, &addr, &addr_type);
+		convert_dest_bdaddr(&hdr->daddr, &addr, &addr_type);
 
-		BT_DBG("dest addr %pMR type %d", &addr, addr_type);
+		BT_DBG("dest addr %pMR type %s IP %pI6c", &addr,
+		       addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM",
+		       &hdr->daddr);
 
 		read_lock_irqsave(&devices_lock, flags);
 		peer = peer_lookup_ba(dev, &addr, addr_type);
@@ -556,7 +567,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 	} else {
 		unsigned long flags;
 
-		get_dest_bdaddr(&lowpan_cb(skb)->addr, &addr, &addr_type);
+		convert_dest_bdaddr(&lowpan_cb(skb)->addr, &addr, &addr_type);
 		eui64_addr = lowpan_cb(skb)->addr.s6_addr + 8;
 		dev = lowpan_dev(netdev);
 
@@ -564,8 +575,10 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 		peer = peer_lookup_ba(dev, &addr, addr_type);
 		read_unlock_irqrestore(&devices_lock, flags);
 
-		BT_DBG("xmit from %s to %pMR (%pI6c) peer %p", netdev->name,
-		       &addr, &lowpan_cb(skb)->addr, peer);
+		BT_DBG("xmit %s to %pMR type %s IP %pI6c peer %p",
+		       netdev->name, &addr,
+		       addr_type == ADDR_LE_DEV_PUBLIC ? "PUBLIC" : "RANDOM",
+		       &lowpan_cb(skb)->addr, peer);
 
 		if (peer && peer->conn)
 			err = send_pkt(peer->conn, netdev->dev_addr,
@@ -620,13 +633,13 @@ static void set_addr(u8 *eui, u8 *addr, u8 addr_type)
 	eui[6] = addr[1];
 	eui[7] = addr[0];
 
-	eui[0] ^= 2;
-
-	/* Universal/local bit set, RFC 4291 */
+	/* Universal/local bit set, BT 6lowpan draft ch. 3.2.1 */
 	if (addr_type == ADDR_LE_DEV_PUBLIC)
-		eui[0] |= 1;
+		eui[0] &= ~0x02;
 	else
-		eui[0] &= ~1;
+		eui[0] |= 0x02;
+
+	BT_DBG("type %d addr %*phC", addr_type, 8, eui);
 }
 
 static void set_dev_addr(struct net_device *netdev, bdaddr_t *addr,
@@ -634,7 +647,6 @@ static void set_dev_addr(struct net_device *netdev, bdaddr_t *addr,
 {
 	netdev->addr_assign_type = NET_ADDR_PERM;
 	set_addr(netdev->dev_addr, addr->b, addr_type);
-	netdev->dev_addr[0] ^= 2;
 }
 
 static void ifup(struct net_device *netdev)
@@ -684,13 +696,6 @@ static int add_peer_conn(struct l2cap_conn *conn, struct lowpan_dev *dev)
 
 	memcpy(&peer->eui64_addr, (u8 *)&peer->peer_addr.s6_addr + 8,
 	       EUI64_ADDR_LEN);
-	peer->eui64_addr[0] ^= 2; /* second bit-flip (Universe/Local)
-				   * is done according RFC2464
-				   */
-
-	raw_dump_inline(__func__, "peer IPv6 address",
-			(unsigned char *)&peer->peer_addr, 16);
-	raw_dump_inline(__func__, "peer EUI64 address", peer->eui64_addr, 8);
 
 	write_lock_irqsave(&devices_lock, flags);
 	INIT_LIST_HEAD(&peer->list);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 521fd4f3985..a7a27bc2c0b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -28,6 +28,7 @@
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/l2cap.h>
 
 #include "smp.h"
 #include "a2mp.h"
@@ -288,10 +289,20 @@ static void hci_conn_timeout(struct work_struct *work)
 {
 	struct hci_conn *conn = container_of(work, struct hci_conn,
 					     disc_work.work);
+	int refcnt = atomic_read(&conn->refcnt);
 
 	BT_DBG("hcon %p state %s", conn, state_to_string(conn->state));
 
-	if (atomic_read(&conn->refcnt))
+	WARN_ON(refcnt < 0);
+
+	/* FIXME: It was observed that in pairing failed scenario, refcnt
+	 * drops below 0. Probably this is because l2cap_conn_del calls
+	 * l2cap_chan_del for each channel, and inside l2cap_chan_del conn is
+	 * dropped. After that loop hci_chan_del is called which also drops
+	 * conn. For now make sure that ACL is alive if refcnt is higher then 0,
+	 * otherwise drop it.
+	 */
+	if (refcnt > 0)
 		return;
 
 	switch (conn->state) {
@@ -367,9 +378,23 @@ static void le_conn_timeout(struct work_struct *work)
 {
 	struct hci_conn *conn = container_of(work, struct hci_conn,
 					     le_conn_timeout.work);
+	struct hci_dev *hdev = conn->hdev;
 
 	BT_DBG("");
 
+	/* We could end up here due to having done directed advertising,
+	 * so clean up the state if necessary. This should however only
+	 * happen with broken hardware or if low duty cycle was used
+	 * (which doesn't have a timeout of its own).
+	 */
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
+		u8 enable = 0x00;
+		hci_send_cmd(hdev, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable),
+			     &enable);
+		hci_le_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT);
+		return;
+	}
+
 	hci_le_create_connection_cancel(conn);
 }
 
@@ -393,6 +418,8 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 	conn->io_capability = hdev->io_capability;
 	conn->remote_auth = 0xff;
 	conn->key_type = 0xff;
+	conn->tx_power = HCI_TX_POWER_INVALID;
+	conn->max_tx_power = HCI_TX_POWER_INVALID;
 
 	set_bit(HCI_CONN_POWER_SAVE, &conn->flags);
 	conn->disc_timeout = HCI_DISCONN_TIMEOUT;
@@ -401,6 +428,10 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst)
 	case ACL_LINK:
 		conn->pkt_type = hdev->pkt_type & ACL_PTYPE_MASK;
 		break;
+	case LE_LINK:
+		/* conn->src should reflect the local identity address */
+		hci_copy_identity_address(hdev, &conn->src, &conn->src_type);
+		break;
 	case SCO_LINK:
 		if (lmp_esco_capable(hdev))
 			conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) |
@@ -545,6 +576,11 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status)
 	 * favor of connection establishment, we should restart it.
 	 */
 	hci_update_background_scan(hdev);
+
+	/* Re-enable advertising in case this was a failed connection
+	 * attempt as a peripheral.
+	 */
+	mgmt_reenable_advertising(hdev);
 }
 
 static void create_le_conn_complete(struct hci_dev *hdev, u8 status)
@@ -584,11 +620,6 @@ static void hci_req_add_le_create_conn(struct hci_request *req,
 	if (hci_update_random_address(req, false, &own_addr_type))
 		return;
 
-	/* Save the address type used for this connnection attempt so we able
-	 * to retrieve this information if we need it.
-	 */
-	conn->src_type = own_addr_type;
-
 	cp.scan_interval = cpu_to_le16(hdev->le_scan_interval);
 	cp.scan_window = cpu_to_le16(hdev->le_scan_window);
 	bacpy(&cp.peer_addr, &conn->dst);
@@ -605,6 +636,45 @@ static void hci_req_add_le_create_conn(struct hci_request *req,
 	conn->state = BT_CONNECT;
 }
 
+static void hci_req_directed_advertising(struct hci_request *req,
+					 struct hci_conn *conn)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_cp_le_set_adv_param cp;
+	u8 own_addr_type;
+	u8 enable;
+
+	enable = 0x00;
+	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
+
+	/* Clear the HCI_ADVERTISING bit temporarily so that the
+	 * hci_update_random_address knows that it's safe to go ahead
+	 * and write a new random address. The flag will be set back on
+	 * as soon as the SET_ADV_ENABLE HCI command completes.
+	 */
+	clear_bit(HCI_ADVERTISING, &hdev->dev_flags);
+
+	/* Set require_privacy to false so that the remote device has a
+	 * chance of identifying us.
+	 */
+	if (hci_update_random_address(req, false, &own_addr_type) < 0)
+		return;
+
+	memset(&cp, 0, sizeof(cp));
+	cp.type = LE_ADV_DIRECT_IND;
+	cp.own_address_type = own_addr_type;
+	cp.direct_addr_type = conn->dst_type;
+	bacpy(&cp.direct_addr, &conn->dst);
+	cp.channel_map = hdev->le_adv_channel_map;
+
+	hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp);
+
+	enable = 0x01;
+	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
+
+	conn->state = BT_CONNECT;
+}
+
 struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 				u8 dst_type, u8 sec_level, u8 auth_type)
 {
@@ -614,9 +684,6 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	struct hci_request req;
 	int err;
 
-	if (test_bit(HCI_ADVERTISING, &hdev->flags))
-		return ERR_PTR(-ENOTSUPP);
-
 	/* Some devices send ATT messages as soon as the physical link is
 	 * established. To be able to handle these ATT messages, the user-
 	 * space first establishes the connection and then starts the pairing
@@ -664,13 +731,20 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 		return ERR_PTR(-ENOMEM);
 
 	conn->dst_type = dst_type;
-
-	conn->out = true;
-	conn->link_mode |= HCI_LM_MASTER;
 	conn->sec_level = BT_SECURITY_LOW;
 	conn->pending_sec_level = sec_level;
 	conn->auth_type = auth_type;
 
+	hci_req_init(&req, hdev);
+
+	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags)) {
+		hci_req_directed_advertising(&req, conn);
+		goto create_conn;
+	}
+
+	conn->out = true;
+	conn->link_mode |= HCI_LM_MASTER;
+
 	params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type);
 	if (params) {
 		conn->le_conn_min_interval = params->conn_min_interval;
@@ -680,8 +754,6 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 		conn->le_conn_max_interval = hdev->le_conn_max_interval;
 	}
 
-	hci_req_init(&req, hdev);
-
 	/* If controller is scanning, we stop it since some controllers are
 	 * not able to scan and connect at the same time. Also set the
 	 * HCI_LE_SCAN_INTERRUPTED flag so that the command complete
@@ -695,6 +767,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 
 	hci_req_add_le_create_conn(&req, conn);
 
+create_conn:
 	err = hci_req_run(&req, create_le_conn_complete);
 	if (err) {
 		hci_conn_del(conn);
@@ -826,7 +899,7 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 		/* If we're already encrypted set the REAUTH_PEND flag,
 		 * otherwise set the ENCRYPT_PEND.
 		 */
-		if (conn->key_type != 0xff)
+		if (conn->link_mode & HCI_LM_ENCRYPT)
 			set_bit(HCI_CONN_REAUTH_PEND, &conn->flags);
 		else
 			set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 1c6ffaa8902..e090bffe1bf 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -34,6 +34,7 @@
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/l2cap.h>
 
 #include "smp.h"
 
@@ -579,6 +580,62 @@ static int sniff_max_interval_get(void *data, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(sniff_max_interval_fops, sniff_max_interval_get,
 			sniff_max_interval_set, "%llu\n");
 
+static int conn_info_min_age_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val == 0 || val > hdev->conn_info_max_age)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->conn_info_min_age = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int conn_info_min_age_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->conn_info_min_age;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(conn_info_min_age_fops, conn_info_min_age_get,
+			conn_info_min_age_set, "%llu\n");
+
+static int conn_info_max_age_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val == 0 || val < hdev->conn_info_min_age)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->conn_info_max_age = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int conn_info_max_age_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->conn_info_max_age;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(conn_info_max_age_fops, conn_info_max_age_get,
+			conn_info_max_age_set, "%llu\n");
+
 static int identity_show(struct seq_file *f, void *p)
 {
 	struct hci_dev *hdev = f->private;
@@ -955,14 +1012,9 @@ static ssize_t le_auto_conn_write(struct file *file, const char __user *data,
 	if (count < 3)
 		return -EINVAL;
 
-	buf = kzalloc(count, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, data, count)) {
-		err = -EFAULT;
-		goto done;
-	}
+	buf = memdup_user(data, count);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
 
 	if (memcmp(buf, "add", 3) == 0) {
 		n = sscanf(&buf[4], "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu %hhu",
@@ -1759,6 +1811,11 @@ static int __hci_init(struct hci_dev *hdev)
 			    &blacklist_fops);
 	debugfs_create_file("uuids", 0444, hdev->debugfs, hdev, &uuids_fops);
 
+	debugfs_create_file("conn_info_min_age", 0644, hdev->debugfs, hdev,
+			    &conn_info_min_age_fops);
+	debugfs_create_file("conn_info_max_age", 0644, hdev->debugfs, hdev,
+			    &conn_info_max_age_fops);
+
 	if (lmp_bredr_capable(hdev)) {
 		debugfs_create_file("inquiry_cache", 0444, hdev->debugfs,
 				    hdev, &inquiry_cache_fops);
@@ -1828,6 +1885,9 @@ static int __hci_init(struct hci_dev *hdev)
 				    &lowpan_debugfs_fops);
 		debugfs_create_file("le_auto_conn", 0644, hdev->debugfs, hdev,
 				    &le_auto_conn_fops);
+		debugfs_create_u16("discov_interleaved_timeout", 0644,
+				   hdev->debugfs,
+				   &hdev->discov_interleaved_timeout);
 	}
 
 	return 0;
@@ -2033,12 +2093,11 @@ bool hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data,
 
 	hci_remove_remote_oob_data(hdev, &data->bdaddr);
 
-	if (ssp)
-		*ssp = data->ssp_mode;
+	*ssp = data->ssp_mode;
 
 	ie = hci_inquiry_cache_lookup(hdev, &data->bdaddr);
 	if (ie) {
-		if (ie->data.ssp_mode && ssp)
+		if (ie->data.ssp_mode)
 			*ssp = true;
 
 		if (ie->name_state == NAME_NEEDED &&
@@ -2127,12 +2186,6 @@ static void hci_inq_req(struct hci_request *req, unsigned long opt)
 	hci_req_add(req, HCI_OP_INQUIRY, sizeof(cp), &cp);
 }
 
-static int wait_inquiry(void *word)
-{
-	schedule();
-	return signal_pending(current);
-}
-
 int hci_inquiry(void __user *arg)
 {
 	__u8 __user *ptr = arg;
@@ -2183,7 +2236,7 @@ int hci_inquiry(void __user *arg)
 		/* Wait until Inquiry procedure finishes (HCI_INQUIRY flag is
 		 * cleared). If it is interrupted by a signal, return -EINTR.
 		 */
-		if (wait_on_bit(&hdev->flags, HCI_INQUIRY, wait_inquiry,
+		if (wait_on_bit(&hdev->flags, HCI_INQUIRY,
 				TASK_INTERRUPTIBLE))
 			return -EINTR;
 	}
@@ -3791,6 +3844,9 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->le_conn_max_interval = 0x0038;
 
 	hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT;
+	hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT;
+	hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE;
+	hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE;
 
 	mutex_init(&hdev->lock);
 	mutex_init(&hdev->req_lock);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 682f33a3836..640c54ec1bd 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -48,6 +48,10 @@ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb)
 	smp_mb__after_atomic(); /* wake_up_bit advises about this barrier */
 	wake_up_bit(&hdev->flags, HCI_INQUIRY);
 
+	hci_dev_lock(hdev);
+	hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+	hci_dev_unlock(hdev);
+
 	hci_conn_check_pending(hdev);
 }
 
@@ -991,10 +995,25 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!sent)
 		return;
 
+	if (status)
+		return;
+
 	hci_dev_lock(hdev);
 
-	if (!status)
-		mgmt_advertising(hdev, *sent);
+	/* If we're doing connection initation as peripheral. Set a
+	 * timeout in case something goes wrong.
+	 */
+	if (*sent) {
+		struct hci_conn *conn;
+
+		conn = hci_conn_hash_lookup_state(hdev, LE_LINK, BT_CONNECT);
+		if (conn)
+			queue_delayed_work(hdev->workqueue,
+					   &conn->le_conn_timeout,
+					   HCI_LE_CONN_TIMEOUT);
+	}
+
+	mgmt_advertising(hdev, *sent);
 
 	hci_dev_unlock(hdev);
 }
@@ -1018,6 +1037,33 @@ static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_unlock(hdev);
 }
 
+static bool has_pending_adv_report(struct hci_dev *hdev)
+{
+	struct discovery_state *d = &hdev->discovery;
+
+	return bacmp(&d->last_adv_addr, BDADDR_ANY);
+}
+
+static void clear_pending_adv_report(struct hci_dev *hdev)
+{
+	struct discovery_state *d = &hdev->discovery;
+
+	bacpy(&d->last_adv_addr, BDADDR_ANY);
+	d->last_adv_data_len = 0;
+}
+
+static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr,
+				     u8 bdaddr_type, s8 rssi, u8 *data, u8 len)
+{
+	struct discovery_state *d = &hdev->discovery;
+
+	bacpy(&d->last_adv_addr, bdaddr);
+	d->last_adv_addr_type = bdaddr_type;
+	d->last_adv_rssi = rssi;
+	memcpy(d->last_adv_data, data, len);
+	d->last_adv_data_len = len;
+}
+
 static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 				      struct sk_buff *skb)
 {
@@ -1036,9 +1082,25 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 	switch (cp->enable) {
 	case LE_SCAN_ENABLE:
 		set_bit(HCI_LE_SCAN, &hdev->dev_flags);
+		if (hdev->le_scan_type == LE_SCAN_ACTIVE)
+			clear_pending_adv_report(hdev);
 		break;
 
 	case LE_SCAN_DISABLE:
+		/* We do this here instead of when setting DISCOVERY_STOPPED
+		 * since the latter would potentially require waiting for
+		 * inquiry to stop too.
+		 */
+		if (has_pending_adv_report(hdev)) {
+			struct discovery_state *d = &hdev->discovery;
+
+			mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK,
+					  d->last_adv_addr_type, NULL,
+					  d->last_adv_rssi, 0, 1,
+					  d->last_adv_data,
+					  d->last_adv_data_len, NULL, 0);
+		}
+
 		/* Cancel this timer so that we don't try to disable scanning
 		 * when it's already disabled.
 		 */
@@ -1187,6 +1249,59 @@ static void hci_cc_write_remote_amp_assoc(struct hci_dev *hdev,
 	amp_write_rem_assoc_continue(hdev, rp->phy_handle);
 }
 
+static void hci_cc_read_rssi(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_rp_read_rssi *rp = (void *) skb->data;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle));
+	if (conn)
+		conn->rssi = rp->rssi;
+
+	hci_dev_unlock(hdev);
+}
+
+static void hci_cc_read_tx_power(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_cp_read_tx_power *sent;
+	struct hci_rp_read_tx_power *rp = (void *) skb->data;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_READ_TX_POWER);
+	if (!sent)
+		return;
+
+	hci_dev_lock(hdev);
+
+	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(rp->handle));
+	if (!conn)
+		goto unlock;
+
+	switch (sent->type) {
+	case 0x00:
+		conn->tx_power = rp->tx_power;
+		break;
+	case 0x01:
+		conn->max_tx_power = rp->tx_power;
+		break;
+	}
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status)
 {
 	BT_DBG("%s status 0x%2.2x", hdev->name, status);
@@ -1342,6 +1457,7 @@ static int hci_outgoing_auth_needed(struct hci_dev *hdev,
 	 * is requested.
 	 */
 	if (!hci_conn_ssp_enabled(conn) && !(conn->auth_type & 0x01) &&
+	    conn->pending_sec_level != BT_SECURITY_FIPS &&
 	    conn->pending_sec_level != BT_SECURITY_HIGH &&
 	    conn->pending_sec_level != BT_SECURITY_MEDIUM)
 		return 0;
@@ -1827,7 +1943,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		name_known = hci_inquiry_cache_update(hdev, &data, false, &ssp);
 		mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00,
 				  info->dev_class, 0, !name_known, ssp, NULL,
-				  0);
+				  0, NULL, 0);
 	}
 
 	hci_dev_unlock(hdev);
@@ -2579,6 +2695,14 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_cc_write_remote_amp_assoc(hdev, skb);
 		break;
 
+	case HCI_OP_READ_RSSI:
+		hci_cc_read_rssi(hdev, skb);
+		break;
+
+	case HCI_OP_READ_TX_POWER:
+		hci_cc_read_tx_power(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode);
 		break;
@@ -2957,7 +3081,8 @@ static void hci_link_key_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		}
 
 		if (key->type == HCI_LK_COMBINATION && key->pin_len < 16 &&
-		    conn->pending_sec_level == BT_SECURITY_HIGH) {
+		    (conn->pending_sec_level == BT_SECURITY_HIGH ||
+		     conn->pending_sec_level == BT_SECURITY_FIPS)) {
 			BT_DBG("%s ignoring key unauthenticated for high security",
 			       hdev->name);
 			goto not_found;
@@ -3102,7 +3227,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 							      false, &ssp);
 			mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00,
 					  info->dev_class, info->rssi,
-					  !name_known, ssp, NULL, 0);
+					  !name_known, ssp, NULL, 0, NULL, 0);
 		}
 	} else {
 		struct inquiry_info_with_rssi *info = (void *) (skb->data + 1);
@@ -3120,7 +3245,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev,
 							      false, &ssp);
 			mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00,
 					  info->dev_class, info->rssi,
-					  !name_known, ssp, NULL, 0);
+					  !name_known, ssp, NULL, 0, NULL, 0);
 		}
 	}
 
@@ -3309,7 +3434,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev,
 		eir_len = eir_get_length(info->data, sizeof(info->data));
 		mgmt_device_found(hdev, &info->bdaddr, ACL_LINK, 0x00,
 				  info->dev_class, info->rssi, !name_known,
-				  ssp, info->data, eir_len);
+				  ssp, info->data, eir_len, NULL, 0);
 	}
 
 	hci_dev_unlock(hdev);
@@ -3367,24 +3492,20 @@ unlock:
 
 static u8 hci_get_auth_req(struct hci_conn *conn)
 {
-	/* If remote requests dedicated bonding follow that lead */
-	if (conn->remote_auth == HCI_AT_DEDICATED_BONDING ||
-	    conn->remote_auth == HCI_AT_DEDICATED_BONDING_MITM) {
-		/* If both remote and local IO capabilities allow MITM
-		 * protection then require it, otherwise don't */
-		if (conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT ||
-		    conn->io_capability == HCI_IO_NO_INPUT_OUTPUT)
-			return HCI_AT_DEDICATED_BONDING;
-		else
-			return HCI_AT_DEDICATED_BONDING_MITM;
-	}
-
 	/* If remote requests no-bonding follow that lead */
 	if (conn->remote_auth == HCI_AT_NO_BONDING ||
 	    conn->remote_auth == HCI_AT_NO_BONDING_MITM)
 		return conn->remote_auth | (conn->auth_type & 0x01);
 
-	return conn->auth_type;
+	/* If both remote and local have enough IO capabilities, require
+	 * MITM protection
+	 */
+	if (conn->remote_cap != HCI_IO_NO_INPUT_OUTPUT &&
+	    conn->io_capability != HCI_IO_NO_INPUT_OUTPUT)
+		return conn->remote_auth | 0x01;
+
+	/* No MITM protection possible so ignore remote requirement */
+	return (conn->remote_auth & ~0x01) | (conn->auth_type & 0x01);
 }
 
 static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
@@ -3414,8 +3535,25 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		 * to DisplayYesNo as it is not supported by BT spec. */
 		cp.capability = (conn->io_capability == 0x04) ?
 				HCI_IO_DISPLAY_YESNO : conn->io_capability;
-		conn->auth_type = hci_get_auth_req(conn);
-		cp.authentication = conn->auth_type;
+
+		/* If we are initiators, there is no remote information yet */
+		if (conn->remote_auth == 0xff) {
+			cp.authentication = conn->auth_type;
+
+			/* Request MITM protection if our IO caps allow it
+			 * except for the no-bonding case.
+			 * conn->auth_type is not updated here since
+			 * that might cause the user confirmation to be
+			 * rejected in case the remote doesn't have the
+			 * IO capabilities for MITM.
+			 */
+			if (conn->io_capability != HCI_IO_NO_INPUT_OUTPUT &&
+			    cp.authentication != HCI_AT_NO_BONDING)
+				cp.authentication |= 0x01;
+		} else {
+			conn->auth_type = hci_get_auth_req(conn);
+			cp.authentication = conn->auth_type;
+		}
 
 		if (hci_find_remote_oob_data(hdev, &conn->dst) &&
 		    (conn->out || test_bit(HCI_CONN_REMOTE_OOB, &conn->flags)))
@@ -3483,12 +3621,9 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 	rem_mitm = (conn->remote_auth & 0x01);
 
 	/* If we require MITM but the remote device can't provide that
-	 * (it has NoInputNoOutput) then reject the confirmation
-	 * request. The only exception is when we're dedicated bonding
-	 * initiators (connect_cfm_cb set) since then we always have the MITM
-	 * bit set. */
-	if (!conn->connect_cfm_cb && loc_mitm &&
-	    conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT) {
+	 * (it has NoInputNoOutput) then reject the confirmation request
+	 */
+	if (loc_mitm && conn->remote_cap == HCI_IO_NO_INPUT_OUTPUT) {
 		BT_DBG("Rejecting request: remote device can't provide MITM");
 		hci_send_cmd(hdev, HCI_OP_USER_CONFIRM_NEG_REPLY,
 			     sizeof(ev->bdaddr), &ev->bdaddr);
@@ -3501,8 +3636,11 @@ static void hci_user_confirm_request_evt(struct hci_dev *hdev,
 
 		/* If we're not the initiators request authorization to
 		 * proceed from user space (mgmt_user_confirm with
-		 * confirm_hint set to 1). */
-		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags)) {
+		 * confirm_hint set to 1). The exception is if neither
+		 * side had MITM in which case we do auto-accept.
+		 */
+		if (!test_bit(HCI_CONN_AUTH_PEND, &conn->flags) &&
+		    (loc_mitm || rem_mitm)) {
 			BT_DBG("Confirming auto-accept as acceptor");
 			confirm_hint = 1;
 			goto confirm;
@@ -3846,17 +3984,6 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 		conn->dst_type = ev->bdaddr_type;
 
-		/* The advertising parameters for own address type
-		 * define which source address and source address
-		 * type this connections has.
-		 */
-		if (bacmp(&conn->src, BDADDR_ANY)) {
-			conn->src_type = ADDR_LE_DEV_PUBLIC;
-		} else {
-			bacpy(&conn->src, &hdev->static_addr);
-			conn->src_type = ADDR_LE_DEV_RANDOM;
-		}
-
 		if (ev->role == LE_CONN_ROLE_MASTER) {
 			conn->out = true;
 			conn->link_mode |= HCI_LM_MASTER;
@@ -3881,27 +4008,24 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 							  &conn->init_addr,
 							  &conn->init_addr_type);
 			}
-		} else {
-			/* Set the responder (our side) address type based on
-			 * the advertising address type.
-			 */
-			conn->resp_addr_type = hdev->adv_addr_type;
-			if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM)
-				bacpy(&conn->resp_addr, &hdev->random_addr);
-			else
-				bacpy(&conn->resp_addr, &hdev->bdaddr);
-
-			conn->init_addr_type = ev->bdaddr_type;
-			bacpy(&conn->init_addr, &ev->bdaddr);
 		}
 	} else {
 		cancel_delayed_work(&conn->le_conn_timeout);
 	}
 
-	/* Ensure that the hci_conn contains the identity address type
-	 * regardless of which address the connection was made with.
-	 */
-	hci_copy_identity_address(hdev, &conn->src, &conn->src_type);
+	if (!conn->out) {
+		/* Set the responder (our side) address type based on
+		 * the advertising address type.
+		 */
+		conn->resp_addr_type = hdev->adv_addr_type;
+		if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM)
+			bacpy(&conn->resp_addr, &hdev->random_addr);
+		else
+			bacpy(&conn->resp_addr, &hdev->bdaddr);
+
+		conn->init_addr_type = ev->bdaddr_type;
+		bacpy(&conn->init_addr, &ev->bdaddr);
+	}
 
 	/* Lookup the identity address from the stored connection
 	 * address and address type.
@@ -3981,25 +4105,97 @@ static void check_pending_le_conn(struct hci_dev *hdev, bdaddr_t *addr,
 	}
 }
 
+static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr,
+			       u8 bdaddr_type, s8 rssi, u8 *data, u8 len)
+{
+	struct discovery_state *d = &hdev->discovery;
+	bool match;
+
+	/* Passive scanning shouldn't trigger any device found events */
+	if (hdev->le_scan_type == LE_SCAN_PASSIVE) {
+		if (type == LE_ADV_IND || type == LE_ADV_DIRECT_IND)
+			check_pending_le_conn(hdev, bdaddr, bdaddr_type);
+		return;
+	}
+
+	/* If there's nothing pending either store the data from this
+	 * event or send an immediate device found event if the data
+	 * should not be stored for later.
+	 */
+	if (!has_pending_adv_report(hdev)) {
+		/* If the report will trigger a SCAN_REQ store it for
+		 * later merging.
+		 */
+		if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) {
+			store_pending_adv_report(hdev, bdaddr, bdaddr_type,
+						 rssi, data, len);
+			return;
+		}
+
+		mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL,
+				  rssi, 0, 1, data, len, NULL, 0);
+		return;
+	}
+
+	/* Check if the pending report is for the same device as the new one */
+	match = (!bacmp(bdaddr, &d->last_adv_addr) &&
+		 bdaddr_type == d->last_adv_addr_type);
+
+	/* If the pending data doesn't match this report or this isn't a
+	 * scan response (e.g. we got a duplicate ADV_IND) then force
+	 * sending of the pending data.
+	 */
+	if (type != LE_ADV_SCAN_RSP || !match) {
+		/* Send out whatever is in the cache, but skip duplicates */
+		if (!match)
+			mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK,
+					  d->last_adv_addr_type, NULL,
+					  d->last_adv_rssi, 0, 1,
+					  d->last_adv_data,
+					  d->last_adv_data_len, NULL, 0);
+
+		/* If the new report will trigger a SCAN_REQ store it for
+		 * later merging.
+		 */
+		if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) {
+			store_pending_adv_report(hdev, bdaddr, bdaddr_type,
+						 rssi, data, len);
+			return;
+		}
+
+		/* The advertising reports cannot be merged, so clear
+		 * the pending report and send out a device found event.
+		 */
+		clear_pending_adv_report(hdev);
+		mgmt_device_found(hdev, bdaddr, LE_LINK, bdaddr_type, NULL,
+				  rssi, 0, 1, data, len, NULL, 0);
+		return;
+	}
+
+	/* If we get here we've got a pending ADV_IND or ADV_SCAN_IND and
+	 * the new event is a SCAN_RSP. We can therefore proceed with
+	 * sending a merged device found event.
+	 */
+	mgmt_device_found(hdev, &d->last_adv_addr, LE_LINK,
+			  d->last_adv_addr_type, NULL, rssi, 0, 1, data, len,
+			  d->last_adv_data, d->last_adv_data_len);
+	clear_pending_adv_report(hdev);
+}
+
 static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	u8 num_reports = skb->data[0];
 	void *ptr = &skb->data[1];
-	s8 rssi;
 
 	hci_dev_lock(hdev);
 
 	while (num_reports--) {
 		struct hci_ev_le_advertising_info *ev = ptr;
-
-		if (ev->evt_type == LE_ADV_IND ||
-		    ev->evt_type == LE_ADV_DIRECT_IND)
-			check_pending_le_conn(hdev, &ev->bdaddr,
-					      ev->bdaddr_type);
+		s8 rssi;
 
 		rssi = ev->data[ev->length];
-		mgmt_device_found(hdev, &ev->bdaddr, LE_LINK, ev->bdaddr_type,
-				  NULL, rssi, 0, 1, ev->data, ev->length);
+		process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
+				   ev->bdaddr_type, rssi, ev->data, ev->length);
 
 		ptr += sizeof(*ev) + ev->length + 1;
 	}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index b9a418e578e..80d25c150a6 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -143,7 +143,7 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
 
 		if (!skb_copy) {
 			/* Create a private copy with headroom */
-			skb_copy = __pskb_copy(skb, 1, GFP_ATOMIC);
+			skb_copy = __pskb_copy_fclone(skb, 1, GFP_ATOMIC, true);
 			if (!skb_copy)
 				continue;
 
@@ -247,8 +247,8 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
 			struct hci_mon_hdr *hdr;
 
 			/* Create a private copy with headroom */
-			skb_copy = __pskb_copy(skb, HCI_MON_HDR_SIZE,
-					       GFP_ATOMIC);
+			skb_copy = __pskb_copy_fclone(skb, HCI_MON_HDR_SIZE,
+						      GFP_ATOMIC, true);
 			if (!skb_copy)
 				continue;
 
@@ -524,16 +524,7 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
 	case HCISETRAW:
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
-
-		if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
-			return -EPERM;
-
-		if (arg)
-			set_bit(HCI_RAW, &hdev->flags);
-		else
-			clear_bit(HCI_RAW, &hdev->flags);
-
-		return 0;
+		return -EOPNOTSUPP;
 
 	case HCIGETCONNINFO:
 		return hci_get_conn_info(hdev, (void __user *) arg);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index dc4d301d3a7..323f23cd2c3 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -471,8 +471,14 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan)
 	chan->max_tx = L2CAP_DEFAULT_MAX_TX;
 	chan->tx_win = L2CAP_DEFAULT_TX_WINDOW;
 	chan->tx_win_max = L2CAP_DEFAULT_TX_WINDOW;
+	chan->remote_max_tx = chan->max_tx;
+	chan->remote_tx_win = chan->tx_win;
 	chan->ack_win = L2CAP_DEFAULT_TX_WINDOW;
 	chan->sec_level = BT_SECURITY_LOW;
+	chan->flush_to = L2CAP_DEFAULT_FLUSH_TO;
+	chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO;
+	chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO;
+	chan->conf_state = 0;
 
 	set_bit(FLAG_FORCE_ACTIVE, &chan->flags);
 }
@@ -1657,7 +1663,13 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err)
 	kfree_skb(conn->rx_skb);
 
 	skb_queue_purge(&conn->pending_rx);
-	flush_work(&conn->pending_rx_work);
+
+	/* We can not call flush_work(&conn->pending_rx_work) here since we
+	 * might block if we are running on a worker from the same workqueue
+	 * pending_rx_work is waiting on.
+	 */
+	if (work_pending(&conn->pending_rx_work))
+		cancel_work_sync(&conn->pending_rx_work);
 
 	l2cap_unregister_all_users(conn);
 
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index ef5e5b04f34..e1378693cc9 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -787,11 +787,6 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
 
 		/*change security for LE channels */
 		if (chan->scid == L2CAP_CID_ATT) {
-			if (!conn->hcon->out) {
-				err = -EINVAL;
-				break;
-			}
-
 			if (smp_conn_security(conn->hcon, sec.level))
 				break;
 			sk->sk_state = BT_CONFIG;
@@ -1180,13 +1175,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan)
 	/* Check for backlog size */
 	if (sk_acceptq_is_full(parent)) {
 		BT_DBG("backlog full %d", parent->sk_ack_backlog);
+		release_sock(parent);
 		return NULL;
 	}
 
 	sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP,
 			      GFP_ATOMIC);
-	if (!sk)
+	if (!sk) {
+		release_sock(parent);
 		return NULL;
+        }
 
 	bt_sock_reclassify_lock(sk, BTPROTO_L2CAP);
 
diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c
index b3fbc73516c..941ad7530ed 100644
--- a/net/bluetooth/lib.c
+++ b/net/bluetooth/lib.c
@@ -58,6 +58,7 @@ int bt_to_errno(__u16 code)
 		return EIO;
 
 	case 0x04:
+	case 0x3c:
 		return EHOSTDOWN;
 
 	case 0x05:
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d2d4e0d5aed..af8e0a6243b 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -29,12 +29,13 @@
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/l2cap.h>
 #include <net/bluetooth/mgmt.h>
 
 #include "smp.h"
 
 #define MGMT_VERSION	1
-#define MGMT_REVISION	5
+#define MGMT_REVISION	6
 
 static const u16 mgmt_commands[] = {
 	MGMT_OP_READ_INDEX_LIST,
@@ -83,6 +84,7 @@ static const u16 mgmt_commands[] = {
 	MGMT_OP_SET_DEBUG_KEYS,
 	MGMT_OP_SET_PRIVACY,
 	MGMT_OP_LOAD_IRKS,
+	MGMT_OP_GET_CONN_INFO,
 };
 
 static const u16 mgmt_events[] = {
@@ -1045,6 +1047,43 @@ static void clean_up_hci_complete(struct hci_dev *hdev, u8 status)
 	}
 }
 
+static void hci_stop_discovery(struct hci_request *req)
+{
+	struct hci_dev *hdev = req->hdev;
+	struct hci_cp_remote_name_req_cancel cp;
+	struct inquiry_entry *e;
+
+	switch (hdev->discovery.state) {
+	case DISCOVERY_FINDING:
+		if (test_bit(HCI_INQUIRY, &hdev->flags)) {
+			hci_req_add(req, HCI_OP_INQUIRY_CANCEL, 0, NULL);
+		} else {
+			cancel_delayed_work(&hdev->le_scan_disable);
+			hci_req_add_le_scan_disable(req);
+		}
+
+		break;
+
+	case DISCOVERY_RESOLVING:
+		e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY,
+						     NAME_PENDING);
+		if (!e)
+			return;
+
+		bacpy(&cp.bdaddr, &e->data.bdaddr);
+		hci_req_add(req, HCI_OP_REMOTE_NAME_REQ_CANCEL, sizeof(cp),
+			    &cp);
+
+		break;
+
+	default:
+		/* Passive scanning */
+		if (test_bit(HCI_LE_SCAN, &hdev->dev_flags))
+			hci_req_add_le_scan_disable(req);
+		break;
+	}
+}
+
 static int clean_up_hci_state(struct hci_dev *hdev)
 {
 	struct hci_request req;
@@ -1061,9 +1100,7 @@ static int clean_up_hci_state(struct hci_dev *hdev)
 	if (test_bit(HCI_ADVERTISING, &hdev->dev_flags))
 		disable_advertising(&req);
 
-	if (test_bit(HCI_LE_SCAN, &hdev->dev_flags)) {
-		hci_req_add_le_scan_disable(&req);
-	}
+	hci_stop_discovery(&req);
 
 	list_for_each_entry(conn, &hdev->conn_hash.list, list) {
 		struct hci_cp_disconnect dc;
@@ -2850,10 +2887,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 	}
 
 	sec_level = BT_SECURITY_MEDIUM;
-	if (cp->io_cap == 0x03)
-		auth_type = HCI_AT_DEDICATED_BONDING;
-	else
-		auth_type = HCI_AT_DEDICATED_BONDING_MITM;
+	auth_type = HCI_AT_DEDICATED_BONDING;
 
 	if (cp->addr.type == BDADDR_BREDR) {
 		conn = hci_connect_acl(hdev, &cp->addr.bdaddr, sec_level,
@@ -2997,8 +3031,13 @@ static int user_pairing_resp(struct sock *sk, struct hci_dev *hdev,
 	}
 
 	if (addr->type == BDADDR_LE_PUBLIC || addr->type == BDADDR_LE_RANDOM) {
-		/* Continue with pairing via SMP */
+		/* Continue with pairing via SMP. The hdev lock must be
+		 * released as SMP may try to recquire it for crypto
+		 * purposes.
+		 */
+		hci_dev_unlock(hdev);
 		err = smp_user_confirm_reply(conn, mgmt_op, passkey);
+		hci_dev_lock(hdev);
 
 		if (!err)
 			err = cmd_complete(sk, hdev->id, mgmt_op,
@@ -3351,6 +3390,8 @@ static int mgmt_start_discovery_failed(struct hci_dev *hdev, u8 status)
 
 static void start_discovery_complete(struct hci_dev *hdev, u8 status)
 {
+	unsigned long timeout = 0;
+
 	BT_DBG("status %d", status);
 
 	if (status) {
@@ -3366,13 +3407,11 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status)
 
 	switch (hdev->discovery.type) {
 	case DISCOV_TYPE_LE:
-		queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable,
-				   DISCOV_LE_TIMEOUT);
+		timeout = msecs_to_jiffies(DISCOV_LE_TIMEOUT);
 		break;
 
 	case DISCOV_TYPE_INTERLEAVED:
-		queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable,
-				   DISCOV_INTERLEAVED_TIMEOUT);
+		timeout = msecs_to_jiffies(hdev->discov_interleaved_timeout);
 		break;
 
 	case DISCOV_TYPE_BREDR:
@@ -3381,6 +3420,11 @@ static void start_discovery_complete(struct hci_dev *hdev, u8 status)
 	default:
 		BT_ERR("Invalid discovery type %d", hdev->discovery.type);
 	}
+
+	if (!timeout)
+		return;
+
+	queue_delayed_work(hdev->workqueue, &hdev->le_scan_disable, timeout);
 }
 
 static int start_discovery(struct sock *sk, struct hci_dev *hdev,
@@ -3570,8 +3614,6 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
 {
 	struct mgmt_cp_stop_discovery *mgmt_cp = data;
 	struct pending_cmd *cmd;
-	struct hci_cp_remote_name_req_cancel cp;
-	struct inquiry_entry *e;
 	struct hci_request req;
 	int err;
 
@@ -3601,52 +3643,22 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	hci_req_init(&req, hdev);
 
-	switch (hdev->discovery.state) {
-	case DISCOVERY_FINDING:
-		if (test_bit(HCI_INQUIRY, &hdev->flags)) {
-			hci_req_add(&req, HCI_OP_INQUIRY_CANCEL, 0, NULL);
-		} else {
-			cancel_delayed_work(&hdev->le_scan_disable);
-
-			hci_req_add_le_scan_disable(&req);
-		}
-
-		break;
-
-	case DISCOVERY_RESOLVING:
-		e = hci_inquiry_cache_lookup_resolve(hdev, BDADDR_ANY,
-						     NAME_PENDING);
-		if (!e) {
-			mgmt_pending_remove(cmd);
-			err = cmd_complete(sk, hdev->id,
-					   MGMT_OP_STOP_DISCOVERY, 0,
-					   &mgmt_cp->type,
-					   sizeof(mgmt_cp->type));
-			hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
-			goto unlock;
-		}
-
-		bacpy(&cp.bdaddr, &e->data.bdaddr);
-		hci_req_add(&req, HCI_OP_REMOTE_NAME_REQ_CANCEL, sizeof(cp),
-			    &cp);
-
-		break;
+	hci_stop_discovery(&req);
 
-	default:
-		BT_DBG("unknown discovery state %u", hdev->discovery.state);
-
-		mgmt_pending_remove(cmd);
-		err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY,
-				   MGMT_STATUS_FAILED, &mgmt_cp->type,
-				   sizeof(mgmt_cp->type));
+	err = hci_req_run(&req, stop_discovery_complete);
+	if (!err) {
+		hci_discovery_set_state(hdev, DISCOVERY_STOPPING);
 		goto unlock;
 	}
 
-	err = hci_req_run(&req, stop_discovery_complete);
-	if (err < 0)
-		mgmt_pending_remove(cmd);
-	else
-		hci_discovery_set_state(hdev, DISCOVERY_STOPPING);
+	mgmt_pending_remove(cmd);
+
+	/* If no HCI commands were sent we're done */
+	if (err == -ENODATA) {
+		err = cmd_complete(sk, hdev->id, MGMT_OP_STOP_DISCOVERY, 0,
+				   &mgmt_cp->type, sizeof(mgmt_cp->type));
+		hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+	}
 
 unlock:
 	hci_dev_unlock(hdev);
@@ -4530,7 +4542,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 
 	for (i = 0; i < key_count; i++) {
 		struct mgmt_ltk_info *key = &cp->keys[i];
-		u8 type, addr_type;
+		u8 type, addr_type, authenticated;
 
 		if (key->addr.type == BDADDR_LE_PUBLIC)
 			addr_type = ADDR_LE_DEV_PUBLIC;
@@ -4542,8 +4554,19 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 		else
 			type = HCI_SMP_LTK_SLAVE;
 
+		switch (key->type) {
+		case MGMT_LTK_UNAUTHENTICATED:
+			authenticated = 0x00;
+			break;
+		case MGMT_LTK_AUTHENTICATED:
+			authenticated = 0x01;
+			break;
+		default:
+			continue;
+		}
+
 		hci_add_ltk(hdev, &key->addr.bdaddr, addr_type, type,
-			    key->type, key->val, key->enc_size, key->ediv,
+			    authenticated, key->val, key->enc_size, key->ediv,
 			    key->rand);
 	}
 
@@ -4555,6 +4578,218 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
 	return err;
 }
 
+struct cmd_conn_lookup {
+	struct hci_conn *conn;
+	bool valid_tx_power;
+	u8 mgmt_status;
+};
+
+static void get_conn_info_complete(struct pending_cmd *cmd, void *data)
+{
+	struct cmd_conn_lookup *match = data;
+	struct mgmt_cp_get_conn_info *cp;
+	struct mgmt_rp_get_conn_info rp;
+	struct hci_conn *conn = cmd->user_data;
+
+	if (conn != match->conn)
+		return;
+
+	cp = (struct mgmt_cp_get_conn_info *) cmd->param;
+
+	memset(&rp, 0, sizeof(rp));
+	bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr);
+	rp.addr.type = cp->addr.type;
+
+	if (!match->mgmt_status) {
+		rp.rssi = conn->rssi;
+
+		if (match->valid_tx_power) {
+			rp.tx_power = conn->tx_power;
+			rp.max_tx_power = conn->max_tx_power;
+		} else {
+			rp.tx_power = HCI_TX_POWER_INVALID;
+			rp.max_tx_power = HCI_TX_POWER_INVALID;
+		}
+	}
+
+	cmd_complete(cmd->sk, cmd->index, MGMT_OP_GET_CONN_INFO,
+		     match->mgmt_status, &rp, sizeof(rp));
+
+	hci_conn_drop(conn);
+
+	mgmt_pending_remove(cmd);
+}
+
+static void conn_info_refresh_complete(struct hci_dev *hdev, u8 status)
+{
+	struct hci_cp_read_rssi *cp;
+	struct hci_conn *conn;
+	struct cmd_conn_lookup match;
+	u16 handle;
+
+	BT_DBG("status 0x%02x", status);
+
+	hci_dev_lock(hdev);
+
+	/* TX power data is valid in case request completed successfully,
+	 * otherwise we assume it's not valid. At the moment we assume that
+	 * either both or none of current and max values are valid to keep code
+	 * simple.
+	 */
+	match.valid_tx_power = !status;
+
+	/* Commands sent in request are either Read RSSI or Read Transmit Power
+	 * Level so we check which one was last sent to retrieve connection
+	 * handle.  Both commands have handle as first parameter so it's safe to
+	 * cast data on the same command struct.
+	 *
+	 * First command sent is always Read RSSI and we fail only if it fails.
+	 * In other case we simply override error to indicate success as we
+	 * already remembered if TX power value is actually valid.
+	 */
+	cp = hci_sent_cmd_data(hdev, HCI_OP_READ_RSSI);
+	if (!cp) {
+		cp = hci_sent_cmd_data(hdev, HCI_OP_READ_TX_POWER);
+		status = 0;
+	}
+
+	if (!cp) {
+		BT_ERR("invalid sent_cmd in response");
+		goto unlock;
+	}
+
+	handle = __le16_to_cpu(cp->handle);
+	conn = hci_conn_hash_lookup_handle(hdev, handle);
+	if (!conn) {
+		BT_ERR("unknown handle (%d) in response", handle);
+		goto unlock;
+	}
+
+	match.conn = conn;
+	match.mgmt_status = mgmt_status(status);
+
+	/* Cache refresh is complete, now reply for mgmt request for given
+	 * connection only.
+	 */
+	mgmt_pending_foreach(MGMT_OP_GET_CONN_INFO, hdev,
+			     get_conn_info_complete, &match);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static int get_conn_info(struct sock *sk, struct hci_dev *hdev, void *data,
+			 u16 len)
+{
+	struct mgmt_cp_get_conn_info *cp = data;
+	struct mgmt_rp_get_conn_info rp;
+	struct hci_conn *conn;
+	unsigned long conn_info_age;
+	int err = 0;
+
+	BT_DBG("%s", hdev->name);
+
+	memset(&rp, 0, sizeof(rp));
+	bacpy(&rp.addr.bdaddr, &cp->addr.bdaddr);
+	rp.addr.type = cp->addr.type;
+
+	if (!bdaddr_type_is_valid(cp->addr.type))
+		return cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+				    MGMT_STATUS_INVALID_PARAMS,
+				    &rp, sizeof(rp));
+
+	hci_dev_lock(hdev);
+
+	if (!hdev_is_powered(hdev)) {
+		err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+				   MGMT_STATUS_NOT_POWERED, &rp, sizeof(rp));
+		goto unlock;
+	}
+
+	if (cp->addr.type == BDADDR_BREDR)
+		conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK,
+					       &cp->addr.bdaddr);
+	else
+		conn = hci_conn_hash_lookup_ba(hdev, LE_LINK, &cp->addr.bdaddr);
+
+	if (!conn || conn->state != BT_CONNECTED) {
+		err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+				   MGMT_STATUS_NOT_CONNECTED, &rp, sizeof(rp));
+		goto unlock;
+	}
+
+	/* To avoid client trying to guess when to poll again for information we
+	 * calculate conn info age as random value between min/max set in hdev.
+	 */
+	conn_info_age = hdev->conn_info_min_age +
+			prandom_u32_max(hdev->conn_info_max_age -
+					hdev->conn_info_min_age);
+
+	/* Query controller to refresh cached values if they are too old or were
+	 * never read.
+	 */
+	if (time_after(jiffies, conn->conn_info_timestamp +
+		       msecs_to_jiffies(conn_info_age)) ||
+	    !conn->conn_info_timestamp) {
+		struct hci_request req;
+		struct hci_cp_read_tx_power req_txp_cp;
+		struct hci_cp_read_rssi req_rssi_cp;
+		struct pending_cmd *cmd;
+
+		hci_req_init(&req, hdev);
+		req_rssi_cp.handle = cpu_to_le16(conn->handle);
+		hci_req_add(&req, HCI_OP_READ_RSSI, sizeof(req_rssi_cp),
+			    &req_rssi_cp);
+
+		/* For LE links TX power does not change thus we don't need to
+		 * query for it once value is known.
+		 */
+		if (!bdaddr_type_is_le(cp->addr.type) ||
+		    conn->tx_power == HCI_TX_POWER_INVALID) {
+			req_txp_cp.handle = cpu_to_le16(conn->handle);
+			req_txp_cp.type = 0x00;
+			hci_req_add(&req, HCI_OP_READ_TX_POWER,
+				    sizeof(req_txp_cp), &req_txp_cp);
+		}
+
+		/* Max TX power needs to be read only once per connection */
+		if (conn->max_tx_power == HCI_TX_POWER_INVALID) {
+			req_txp_cp.handle = cpu_to_le16(conn->handle);
+			req_txp_cp.type = 0x01;
+			hci_req_add(&req, HCI_OP_READ_TX_POWER,
+				    sizeof(req_txp_cp), &req_txp_cp);
+		}
+
+		err = hci_req_run(&req, conn_info_refresh_complete);
+		if (err < 0)
+			goto unlock;
+
+		cmd = mgmt_pending_add(sk, MGMT_OP_GET_CONN_INFO, hdev,
+				       data, len);
+		if (!cmd) {
+			err = -ENOMEM;
+			goto unlock;
+		}
+
+		hci_conn_hold(conn);
+		cmd->user_data = conn;
+
+		conn->conn_info_timestamp = jiffies;
+	} else {
+		/* Cache is valid, just reply with values cached in hci_conn */
+		rp.rssi = conn->rssi;
+		rp.tx_power = conn->tx_power;
+		rp.max_tx_power = conn->max_tx_power;
+
+		err = cmd_complete(sk, hdev->id, MGMT_OP_GET_CONN_INFO,
+				   MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
+	}
+
+unlock:
+	hci_dev_unlock(hdev);
+	return err;
+}
+
 static const struct mgmt_handler {
 	int (*func) (struct sock *sk, struct hci_dev *hdev, void *data,
 		     u16 data_len);
@@ -4610,6 +4845,7 @@ static const struct mgmt_handler {
 	{ set_debug_keys,         false, MGMT_SETTING_SIZE },
 	{ set_privacy,            false, MGMT_SET_PRIVACY_SIZE },
 	{ load_irks,              true,  MGMT_LOAD_IRKS_SIZE },
+	{ get_conn_info,          false, MGMT_GET_CONN_INFO_SIZE },
 };
 
 
@@ -5005,6 +5241,14 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
 	mgmt_event(MGMT_EV_NEW_LINK_KEY, hdev, &ev, sizeof(ev), NULL);
 }
 
+static u8 mgmt_ltk_type(struct smp_ltk *ltk)
+{
+	if (ltk->authenticated)
+		return MGMT_LTK_AUTHENTICATED;
+
+	return MGMT_LTK_UNAUTHENTICATED;
+}
+
 void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent)
 {
 	struct mgmt_ev_new_long_term_key ev;
@@ -5030,7 +5274,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent)
 
 	bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
 	ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type);
-	ev.key.type = key->authenticated;
+	ev.key.type = mgmt_ltk_type(key);
 	ev.key.enc_size = key->enc_size;
 	ev.key.ediv = key->ediv;
 	ev.key.rand = key->rand;
@@ -5668,8 +5912,9 @@ void mgmt_read_local_oob_data_complete(struct hci_dev *hdev, u8 *hash192,
 }
 
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-		       u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name, u8
-		       ssp, u8 *eir, u16 eir_len)
+		       u8 addr_type, u8 *dev_class, s8 rssi, u8 cfm_name,
+		       u8 ssp, u8 *eir, u16 eir_len, u8 *scan_rsp,
+		       u8 scan_rsp_len)
 {
 	char buf[512];
 	struct mgmt_ev_device_found *ev = (void *) buf;
@@ -5679,8 +5924,10 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 	if (!hci_discovery_active(hdev))
 		return;
 
-	/* Leave 5 bytes for a potential CoD field */
-	if (sizeof(*ev) + eir_len + 5 > sizeof(buf))
+	/* Make sure that the buffer is big enough. The 5 extra bytes
+	 * are for the potential CoD field.
+	 */
+	if (sizeof(*ev) + eir_len + scan_rsp_len + 5 > sizeof(buf))
 		return;
 
 	memset(buf, 0, sizeof(buf));
@@ -5707,8 +5954,11 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		eir_len = eir_append_data(ev->eir, eir_len, EIR_CLASS_OF_DEV,
 					  dev_class, 3);
 
-	ev->eir_len = cpu_to_le16(eir_len);
-	ev_size = sizeof(*ev) + eir_len;
+	if (scan_rsp_len > 0)
+		memcpy(ev->eir + eir_len, scan_rsp, scan_rsp_len);
+
+	ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len);
+	ev_size = sizeof(*ev) + eir_len + scan_rsp_len;
 
 	mgmt_event(MGMT_EV_DEVICE_FOUND, hdev, ev, ev_size, NULL);
 }
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index cf620260aff..754b6fe4f74 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -307,7 +307,7 @@ struct rfcomm_dlc *rfcomm_dlc_alloc(gfp_t prio)
 	setup_timer(&d->timer, rfcomm_dlc_timeout, (unsigned long)d);
 
 	skb_queue_head_init(&d->tx_queue);
-	spin_lock_init(&d->lock);
+	mutex_init(&d->lock);
 	atomic_set(&d->refcnt, 1);
 
 	rfcomm_dlc_clear_state(d);
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 403ec09f480..8e385a0ae60 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -70,7 +70,7 @@ struct rfcomm_dev {
 };
 
 static LIST_HEAD(rfcomm_dev_list);
-static DEFINE_SPINLOCK(rfcomm_dev_lock);
+static DEFINE_MUTEX(rfcomm_dev_lock);
 
 static void rfcomm_dev_data_ready(struct rfcomm_dlc *dlc, struct sk_buff *skb);
 static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err);
@@ -96,9 +96,9 @@ static void rfcomm_dev_destruct(struct tty_port *port)
 	if (dev->tty_dev)
 		tty_unregister_device(rfcomm_tty_driver, dev->id);
 
-	spin_lock(&rfcomm_dev_lock);
+	mutex_lock(&rfcomm_dev_lock);
 	list_del(&dev->list);
-	spin_unlock(&rfcomm_dev_lock);
+	mutex_unlock(&rfcomm_dev_lock);
 
 	kfree(dev);
 
@@ -161,14 +161,14 @@ static struct rfcomm_dev *rfcomm_dev_get(int id)
 {
 	struct rfcomm_dev *dev;
 
-	spin_lock(&rfcomm_dev_lock);
+	mutex_lock(&rfcomm_dev_lock);
 
 	dev = __rfcomm_dev_lookup(id);
 
 	if (dev && !tty_port_get(&dev->port))
 		dev = NULL;
 
-	spin_unlock(&rfcomm_dev_lock);
+	mutex_unlock(&rfcomm_dev_lock);
 
 	return dev;
 }
@@ -224,7 +224,7 @@ static struct rfcomm_dev *__rfcomm_dev_add(struct rfcomm_dev_req *req,
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock(&rfcomm_dev_lock);
+	mutex_lock(&rfcomm_dev_lock);
 
 	if (req->dev_id < 0) {
 		dev->id = 0;
@@ -305,11 +305,11 @@ static struct rfcomm_dev *__rfcomm_dev_add(struct rfcomm_dev_req *req,
 	   holds reference to this module. */
 	__module_get(THIS_MODULE);
 
-	spin_unlock(&rfcomm_dev_lock);
+	mutex_unlock(&rfcomm_dev_lock);
 	return dev;
 
 out:
-	spin_unlock(&rfcomm_dev_lock);
+	mutex_unlock(&rfcomm_dev_lock);
 	kfree(dev);
 	return ERR_PTR(err);
 }
@@ -524,7 +524,7 @@ static int rfcomm_get_dev_list(void __user *arg)
 
 	di = dl->dev_info;
 
-	spin_lock(&rfcomm_dev_lock);
+	mutex_lock(&rfcomm_dev_lock);
 
 	list_for_each_entry(dev, &rfcomm_dev_list, list) {
 		if (!tty_port_get(&dev->port))
@@ -540,7 +540,7 @@ static int rfcomm_get_dev_list(void __user *arg)
 			break;
 	}
 
-	spin_unlock(&rfcomm_dev_lock);
+	mutex_unlock(&rfcomm_dev_lock);
 
 	dl->dev_num = n;
 	size = sizeof(*dl) + n * sizeof(*di);
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index dfb4e1161c1..e33a982161c 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -35,6 +35,33 @@
 
 #define AUTH_REQ_MASK   0x07
 
+#define SMP_FLAG_TK_VALID	1
+#define SMP_FLAG_CFM_PENDING	2
+#define SMP_FLAG_MITM_AUTH	3
+#define SMP_FLAG_COMPLETE	4
+#define SMP_FLAG_INITIATOR	5
+
+struct smp_chan {
+	struct l2cap_conn *conn;
+	u8		preq[7]; /* SMP Pairing Request */
+	u8		prsp[7]; /* SMP Pairing Response */
+	u8		prnd[16]; /* SMP Pairing Random (local) */
+	u8		rrnd[16]; /* SMP Pairing Random (remote) */
+	u8		pcnf[16]; /* SMP Pairing Confirm */
+	u8		tk[16]; /* SMP Temporary Key */
+	u8		enc_key_size;
+	u8		remote_key_dist;
+	bdaddr_t	id_addr;
+	u8		id_addr_type;
+	u8		irk[16];
+	struct smp_csrk	*csrk;
+	struct smp_csrk	*slave_csrk;
+	struct smp_ltk	*ltk;
+	struct smp_ltk	*slave_ltk;
+	struct smp_irk	*remote_irk;
+	unsigned long	flags;
+};
+
 static inline void swap128(const u8 src[16], u8 dst[16])
 {
 	int i;
@@ -358,6 +385,16 @@ static const u8 gen_method[5][5] = {
 	{ CFM_PASSKEY, CFM_PASSKEY, REQ_PASSKEY, JUST_WORKS, OVERLAP     },
 };
 
+static u8 get_auth_method(struct smp_chan *smp, u8 local_io, u8 remote_io)
+{
+	/* If either side has unknown io_caps, use JUST WORKS */
+	if (local_io > SMP_IO_KEYBOARD_DISPLAY ||
+	    remote_io > SMP_IO_KEYBOARD_DISPLAY)
+		return JUST_WORKS;
+
+	return gen_method[remote_io][local_io];
+}
+
 static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 						u8 local_io, u8 remote_io)
 {
@@ -369,38 +406,34 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 
 	/* Initialize key for JUST WORKS */
 	memset(smp->tk, 0, sizeof(smp->tk));
-	clear_bit(SMP_FLAG_TK_VALID, &smp->smp_flags);
+	clear_bit(SMP_FLAG_TK_VALID, &smp->flags);
 
 	BT_DBG("tk_request: auth:%d lcl:%d rem:%d", auth, local_io, remote_io);
 
 	/* If neither side wants MITM, use JUST WORKS */
-	/* If either side has unknown io_caps, use JUST WORKS */
 	/* Otherwise, look up method from the table */
-	if (!(auth & SMP_AUTH_MITM) ||
-	    local_io > SMP_IO_KEYBOARD_DISPLAY ||
-	    remote_io > SMP_IO_KEYBOARD_DISPLAY)
+	if (!(auth & SMP_AUTH_MITM))
 		method = JUST_WORKS;
 	else
-		method = gen_method[remote_io][local_io];
+		method = get_auth_method(smp, local_io, remote_io);
 
 	/* If not bonding, don't ask user to confirm a Zero TK */
 	if (!(auth & SMP_AUTH_BONDING) && method == JUST_CFM)
 		method = JUST_WORKS;
 
 	/* Don't confirm locally initiated pairing attempts */
-	if (method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR,
-					   &smp->smp_flags))
+	if (method == JUST_CFM && test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 		method = JUST_WORKS;
 
 	/* If Just Works, Continue with Zero TK */
 	if (method == JUST_WORKS) {
-		set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags);
+		set_bit(SMP_FLAG_TK_VALID, &smp->flags);
 		return 0;
 	}
 
 	/* Not Just Works/Confirm results in MITM Authentication */
 	if (method != JUST_CFM)
-		set_bit(SMP_FLAG_MITM_AUTH, &smp->smp_flags);
+		set_bit(SMP_FLAG_MITM_AUTH, &smp->flags);
 
 	/* If both devices have Keyoard-Display I/O, the master
 	 * Confirms and the slave Enters the passkey.
@@ -419,7 +452,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 		passkey %= 1000000;
 		put_unaligned_le32(passkey, smp->tk);
 		BT_DBG("PassKey: %d", passkey);
-		set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags);
+		set_bit(SMP_FLAG_TK_VALID, &smp->flags);
 	}
 
 	hci_dev_lock(hcon->hdev);
@@ -441,15 +474,13 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 	return ret;
 }
 
-static void confirm_work(struct work_struct *work)
+static u8 smp_confirm(struct smp_chan *smp)
 {
-	struct smp_chan *smp = container_of(work, struct smp_chan, confirm);
 	struct l2cap_conn *conn = smp->conn;
 	struct hci_dev *hdev = conn->hcon->hdev;
 	struct crypto_blkcipher *tfm = hdev->tfm_aes;
 	struct smp_cmd_pairing_confirm cp;
 	int ret;
-	u8 reason;
 
 	BT_DBG("conn %p", conn);
 
@@ -463,35 +494,27 @@ static void confirm_work(struct work_struct *work)
 
 	hci_dev_unlock(hdev);
 
-	if (ret) {
-		reason = SMP_UNSPECIFIED;
-		goto error;
-	}
+	if (ret)
+		return SMP_UNSPECIFIED;
 
-	clear_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags);
+	clear_bit(SMP_FLAG_CFM_PENDING, &smp->flags);
 
 	smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp);
 
-	return;
-
-error:
-	smp_failure(conn, reason);
+	return 0;
 }
 
-static void random_work(struct work_struct *work)
+static u8 smp_random(struct smp_chan *smp)
 {
-	struct smp_chan *smp = container_of(work, struct smp_chan, random);
 	struct l2cap_conn *conn = smp->conn;
 	struct hci_conn *hcon = conn->hcon;
 	struct hci_dev *hdev = hcon->hdev;
 	struct crypto_blkcipher *tfm = hdev->tfm_aes;
-	u8 reason, confirm[16];
+	u8 confirm[16];
 	int ret;
 
-	if (IS_ERR_OR_NULL(tfm)) {
-		reason = SMP_UNSPECIFIED;
-		goto error;
-	}
+	if (IS_ERR_OR_NULL(tfm))
+		return SMP_UNSPECIFIED;
 
 	BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave");
 
@@ -504,15 +527,12 @@ static void random_work(struct work_struct *work)
 
 	hci_dev_unlock(hdev);
 
-	if (ret) {
-		reason = SMP_UNSPECIFIED;
-		goto error;
-	}
+	if (ret)
+		return SMP_UNSPECIFIED;
 
 	if (memcmp(smp->pcnf, confirm, sizeof(smp->pcnf)) != 0) {
 		BT_ERR("Pairing failed (confirmation values mismatch)");
-		reason = SMP_CONFIRM_FAILED;
-		goto error;
+		return SMP_CONFIRM_FAILED;
 	}
 
 	if (hcon->out) {
@@ -525,15 +545,13 @@ static void random_work(struct work_struct *work)
 		memset(stk + smp->enc_key_size, 0,
 		       SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size);
 
-		if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->flags)) {
-			reason = SMP_UNSPECIFIED;
-			goto error;
-		}
+		if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->flags))
+			return SMP_UNSPECIFIED;
 
 		hci_le_start_enc(hcon, ediv, rand, stk);
 		hcon->enc_key_size = smp->enc_key_size;
 	} else {
-		u8 stk[16];
+		u8 stk[16], auth;
 		__le64 rand = 0;
 		__le16 ediv = 0;
 
@@ -545,15 +563,17 @@ static void random_work(struct work_struct *work)
 		memset(stk + smp->enc_key_size, 0,
 		       SMP_MAX_ENC_KEY_SIZE - smp->enc_key_size);
 
+		if (hcon->pending_sec_level == BT_SECURITY_HIGH)
+			auth = 1;
+		else
+			auth = 0;
+
 		hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type,
-			    HCI_SMP_STK_SLAVE, 0, stk, smp->enc_key_size,
+			    HCI_SMP_STK_SLAVE, auth, stk, smp->enc_key_size,
 			    ediv, rand);
 	}
 
-	return;
-
-error:
-	smp_failure(conn, reason);
+	return 0;
 }
 
 static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
@@ -564,9 +584,6 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn)
 	if (!smp)
 		return NULL;
 
-	INIT_WORK(&smp->confirm, confirm_work);
-	INIT_WORK(&smp->random, random_work);
-
 	smp->conn = conn;
 	conn->smp_chan = smp;
 	conn->hcon->smp_conn = conn;
@@ -583,7 +600,7 @@ void smp_chan_destroy(struct l2cap_conn *conn)
 
 	BUG_ON(!smp);
 
-	complete = test_bit(SMP_FLAG_COMPLETE, &smp->smp_flags);
+	complete = test_bit(SMP_FLAG_COMPLETE, &smp->flags);
 	mgmt_smp_complete(conn->hcon, complete);
 
 	kfree(smp->csrk);
@@ -634,7 +651,7 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 		put_unaligned_le32(value, smp->tk);
 		/* Fall Through */
 	case MGMT_OP_USER_CONFIRM_REPLY:
-		set_bit(SMP_FLAG_TK_VALID, &smp->smp_flags);
+		set_bit(SMP_FLAG_TK_VALID, &smp->flags);
 		break;
 	case MGMT_OP_USER_PASSKEY_NEG_REPLY:
 	case MGMT_OP_USER_CONFIRM_NEG_REPLY:
@@ -646,8 +663,11 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey)
 	}
 
 	/* If it is our turn to send Pairing Confirm, do so now */
-	if (test_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags))
-		queue_work(hcon->hdev->workqueue, &smp->confirm);
+	if (test_bit(SMP_FLAG_CFM_PENDING, &smp->flags)) {
+		u8 rsp = smp_confirm(smp);
+		if (rsp)
+			smp_failure(conn, rsp);
+	}
 
 	return 0;
 }
@@ -656,14 +676,13 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_pairing rsp, *req = (void *) skb->data;
 	struct smp_chan *smp;
-	u8 key_size;
-	u8 auth = SMP_AUTH_NONE;
+	u8 key_size, auth, sec_level;
 	int ret;
 
 	BT_DBG("conn %p", conn);
 
 	if (skb->len < sizeof(*req))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	if (conn->hcon->link_mode & HCI_LM_MASTER)
 		return SMP_CMD_NOTSUPP;
@@ -681,10 +700,21 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	skb_pull(skb, sizeof(*req));
 
 	/* We didn't start the pairing, so match remote */
-	if (req->auth_req & SMP_AUTH_BONDING)
-		auth = req->auth_req;
+	auth = req->auth_req;
+
+	sec_level = authreq_to_seclevel(auth);
+	if (sec_level > conn->hcon->pending_sec_level)
+		conn->hcon->pending_sec_level = sec_level;
 
-	conn->hcon->pending_sec_level = authreq_to_seclevel(auth);
+	/* If we need MITM check that it can be acheived */
+	if (conn->hcon->pending_sec_level >= BT_SECURITY_HIGH) {
+		u8 method;
+
+		method = get_auth_method(smp, conn->hcon->io_capability,
+					 req->io_capability);
+		if (method == JUST_WORKS || method == JUST_CFM)
+			return SMP_AUTH_REQUIREMENTS;
+	}
 
 	build_pairing_cmd(conn, req, &rsp, auth);
 
@@ -704,7 +734,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (ret)
 		return SMP_UNSPECIFIED;
 
-	clear_bit(SMP_FLAG_INITIATOR, &smp->smp_flags);
+	clear_bit(SMP_FLAG_INITIATOR, &smp->flags);
 
 	return 0;
 }
@@ -713,14 +743,13 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_pairing *req, *rsp = (void *) skb->data;
 	struct smp_chan *smp = conn->smp_chan;
-	struct hci_dev *hdev = conn->hcon->hdev;
 	u8 key_size, auth = SMP_AUTH_NONE;
 	int ret;
 
 	BT_DBG("conn %p", conn);
 
 	if (skb->len < sizeof(*rsp))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	if (!(conn->hcon->link_mode & HCI_LM_MASTER))
 		return SMP_CMD_NOTSUPP;
@@ -733,6 +762,16 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (check_enc_key_size(conn, key_size))
 		return SMP_ENC_KEY_SIZE;
 
+	/* If we need MITM check that it can be acheived */
+	if (conn->hcon->pending_sec_level >= BT_SECURITY_HIGH) {
+		u8 method;
+
+		method = get_auth_method(smp, req->io_capability,
+					 rsp->io_capability);
+		if (method == JUST_WORKS || method == JUST_CFM)
+			return SMP_AUTH_REQUIREMENTS;
+	}
+
 	get_random_bytes(smp->prnd, sizeof(smp->prnd));
 
 	smp->prsp[0] = SMP_CMD_PAIRING_RSP;
@@ -753,11 +792,11 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (ret)
 		return SMP_UNSPECIFIED;
 
-	set_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags);
+	set_bit(SMP_FLAG_CFM_PENDING, &smp->flags);
 
 	/* Can't compose response until we have been confirmed */
-	if (test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags))
-		queue_work(hdev->workqueue, &smp->confirm);
+	if (test_bit(SMP_FLAG_TK_VALID, &smp->flags))
+		return smp_confirm(smp);
 
 	return 0;
 }
@@ -765,12 +804,11 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_chan *smp = conn->smp_chan;
-	struct hci_dev *hdev = conn->hcon->hdev;
 
 	BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave");
 
 	if (skb->len < sizeof(smp->pcnf))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	memcpy(smp->pcnf, skb->data, sizeof(smp->pcnf));
 	skb_pull(skb, sizeof(smp->pcnf));
@@ -778,10 +816,10 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (conn->hcon->out)
 		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
 			     smp->prnd);
-	else if (test_bit(SMP_FLAG_TK_VALID, &smp->smp_flags))
-		queue_work(hdev->workqueue, &smp->confirm);
+	else if (test_bit(SMP_FLAG_TK_VALID, &smp->flags))
+		return smp_confirm(smp);
 	else
-		set_bit(SMP_FLAG_CFM_PENDING, &smp->smp_flags);
+		set_bit(SMP_FLAG_CFM_PENDING, &smp->flags);
 
 	return 0;
 }
@@ -789,19 +827,16 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_chan *smp = conn->smp_chan;
-	struct hci_dev *hdev = conn->hcon->hdev;
 
 	BT_DBG("conn %p", conn);
 
 	if (skb->len < sizeof(smp->rrnd))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	memcpy(smp->rrnd, skb->data, sizeof(smp->rrnd));
 	skb_pull(skb, sizeof(smp->rrnd));
 
-	queue_work(hdev->workqueue, &smp->random);
-
-	return 0;
+	return smp_random(smp);
 }
 
 static u8 smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level)
@@ -832,16 +867,19 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct smp_cmd_pairing cp;
 	struct hci_conn *hcon = conn->hcon;
 	struct smp_chan *smp;
+	u8 sec_level;
 
 	BT_DBG("conn %p", conn);
 
 	if (skb->len < sizeof(*rp))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	if (!(conn->hcon->link_mode & HCI_LM_MASTER))
 		return SMP_CMD_NOTSUPP;
 
-	hcon->pending_sec_level = authreq_to_seclevel(rp->auth_req);
+	sec_level = authreq_to_seclevel(rp->auth_req);
+	if (sec_level > hcon->pending_sec_level)
+		hcon->pending_sec_level = sec_level;
 
 	if (smp_ltk_encrypt(conn, hcon->pending_sec_level))
 		return 0;
@@ -861,7 +899,7 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
 
-	clear_bit(SMP_FLAG_INITIATOR, &smp->smp_flags);
+	clear_bit(SMP_FLAG_INITIATOR, &smp->flags);
 
 	return 0;
 }
@@ -895,9 +933,12 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 	if (smp_sufficient_security(hcon, sec_level))
 		return 1;
 
+	if (sec_level > hcon->pending_sec_level)
+		hcon->pending_sec_level = sec_level;
+
 	if (hcon->link_mode & HCI_LM_MASTER)
-		if (smp_ltk_encrypt(conn, sec_level))
-			goto done;
+		if (smp_ltk_encrypt(conn, hcon->pending_sec_level))
+			return 0;
 
 	if (test_and_set_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags))
 		return 0;
@@ -908,10 +949,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 
 	authreq = seclevel_to_authreq(sec_level);
 
-	/* hcon->auth_type is set by pair_device in mgmt.c. If the MITM
-	 * flag is set we should also set it for the SMP request.
+	/* Require MITM if IO Capability allows or the security level
+	 * requires it.
 	 */
-	if ((hcon->auth_type & 0x01))
+	if (hcon->io_capability != HCI_IO_NO_INPUT_OUTPUT ||
+	    hcon->pending_sec_level > BT_SECURITY_MEDIUM)
 		authreq |= SMP_AUTH_MITM;
 
 	if (hcon->link_mode & HCI_LM_MASTER) {
@@ -928,10 +970,7 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 		smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp);
 	}
 
-	set_bit(SMP_FLAG_INITIATOR, &smp->smp_flags);
-
-done:
-	hcon->pending_sec_level = sec_level;
+	set_bit(SMP_FLAG_INITIATOR, &smp->flags);
 
 	return 0;
 }
@@ -944,7 +983,7 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb)
 	BT_DBG("conn %p", conn);
 
 	if (skb->len < sizeof(*rp))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	/* Ignore this PDU if it wasn't requested */
 	if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY))
@@ -969,7 +1008,7 @@ static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb)
 	BT_DBG("conn %p", conn);
 
 	if (skb->len < sizeof(*rp))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	/* Ignore this PDU if it wasn't requested */
 	if (!(smp->remote_key_dist & SMP_DIST_ENC_KEY))
@@ -1001,7 +1040,7 @@ static int smp_cmd_ident_info(struct l2cap_conn *conn, struct sk_buff *skb)
 	BT_DBG("");
 
 	if (skb->len < sizeof(*info))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	/* Ignore this PDU if it wasn't requested */
 	if (!(smp->remote_key_dist & SMP_DIST_ID_KEY))
@@ -1025,7 +1064,7 @@ static int smp_cmd_ident_addr_info(struct l2cap_conn *conn,
 	BT_DBG("");
 
 	if (skb->len < sizeof(*info))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	/* Ignore this PDU if it wasn't requested */
 	if (!(smp->remote_key_dist & SMP_DIST_ID_KEY))
@@ -1075,7 +1114,7 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)
 	BT_DBG("conn %p", conn);
 
 	if (skb->len < sizeof(*rp))
-		return SMP_UNSPECIFIED;
+		return SMP_INVALID_PARAMS;
 
 	/* Ignore this PDU if it wasn't requested */
 	if (!(smp->remote_key_dist & SMP_DIST_SIGN))
@@ -1358,7 +1397,7 @@ int smp_distribute_keys(struct l2cap_conn *conn)
 
 	clear_bit(HCI_CONN_LE_SMP_PEND, &hcon->flags);
 	cancel_delayed_work_sync(&conn->security_timer);
-	set_bit(SMP_FLAG_COMPLETE, &smp->smp_flags);
+	set_bit(SMP_FLAG_COMPLETE, &smp->flags);
 	smp_notify_keys(conn);
 
 	smp_chan_destroy(conn);
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
index 1277147a915..5a8dc36460a 100644
--- a/net/bluetooth/smp.h
+++ b/net/bluetooth/smp.h
@@ -111,39 +111,11 @@ struct smp_cmd_security_req {
 #define SMP_CMD_NOTSUPP			0x07
 #define SMP_UNSPECIFIED			0x08
 #define SMP_REPEATED_ATTEMPTS		0x09
+#define SMP_INVALID_PARAMS		0x0a
 
 #define SMP_MIN_ENC_KEY_SIZE		7
 #define SMP_MAX_ENC_KEY_SIZE		16
 
-#define SMP_FLAG_TK_VALID	1
-#define SMP_FLAG_CFM_PENDING	2
-#define SMP_FLAG_MITM_AUTH	3
-#define SMP_FLAG_COMPLETE	4
-#define SMP_FLAG_INITIATOR	5
-
-struct smp_chan {
-	struct l2cap_conn *conn;
-	u8		preq[7]; /* SMP Pairing Request */
-	u8		prsp[7]; /* SMP Pairing Response */
-	u8		prnd[16]; /* SMP Pairing Random (local) */
-	u8		rrnd[16]; /* SMP Pairing Random (remote) */
-	u8		pcnf[16]; /* SMP Pairing Confirm */
-	u8		tk[16]; /* SMP Temporary Key */
-	u8		enc_key_size;
-	u8		remote_key_dist;
-	bdaddr_t	id_addr;
-	u8		id_addr_type;
-	u8		irk[16];
-	struct smp_csrk	*csrk;
-	struct smp_csrk	*slave_csrk;
-	struct smp_ltk	*ltk;
-	struct smp_ltk	*slave_ltk;
-	struct smp_irk	*remote_irk;
-	unsigned long	smp_flags;
-	struct work_struct confirm;
-	struct work_struct random;
-};
-
 /* SMP Commands */
 bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level);
 int smp_conn_security(struct hci_conn *hcon, __u8 sec_level);
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index e85498b2f16..8590b942bff 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_BRIDGE) += bridge.o
 
 bridge-y	:= br.o br_device.o br_fdb.o br_forward.o br_if.o br_input.o \
-			br_ioctl.o br_notify.o br_stp.o br_stp_bpdu.o \
+			br_ioctl.o br_stp.o br_stp_bpdu.o \
 			br_stp_if.o br_stp_timer.o br_netlink.o
 
 bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o
@@ -16,4 +16,4 @@ bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o
 
 bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o
 
-obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/
+obj-$(CONFIG_NETFILTER) += netfilter/
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 19311aafcf5..1a755a1e541 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -22,6 +22,104 @@
 
 #include "br_private.h"
 
+/*
+ * Handle changes in state of network devices enslaved to a bridge.
+ *
+ * Note: don't care about up/down if bridge itself is down, because
+ *     port state is checked when bridge is brought up.
+ */
+static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net_bridge_port *p;
+	struct net_bridge *br;
+	bool changed_addr;
+	int err;
+
+	/* register of bridge completed, add sysfs entries */
+	if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) {
+		br_sysfs_addbr(dev);
+		return NOTIFY_DONE;
+	}
+
+	/* not a port of a bridge */
+	p = br_port_get_rtnl(dev);
+	if (!p)
+		return NOTIFY_DONE;
+
+	br = p->br;
+
+	switch (event) {
+	case NETDEV_CHANGEMTU:
+		dev_set_mtu(br->dev, br_min_mtu(br));
+		break;
+
+	case NETDEV_CHANGEADDR:
+		spin_lock_bh(&br->lock);
+		br_fdb_changeaddr(p, dev->dev_addr);
+		changed_addr = br_stp_recalculate_bridge_id(br);
+		spin_unlock_bh(&br->lock);
+
+		if (changed_addr)
+			call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
+
+		break;
+
+	case NETDEV_CHANGE:
+		br_port_carrier_check(p);
+		break;
+
+	case NETDEV_FEAT_CHANGE:
+		netdev_update_features(br->dev);
+		break;
+
+	case NETDEV_DOWN:
+		spin_lock_bh(&br->lock);
+		if (br->dev->flags & IFF_UP)
+			br_stp_disable_port(p);
+		spin_unlock_bh(&br->lock);
+		break;
+
+	case NETDEV_UP:
+		if (netif_running(br->dev) && netif_oper_up(dev)) {
+			spin_lock_bh(&br->lock);
+			br_stp_enable_port(p);
+			spin_unlock_bh(&br->lock);
+		}
+		break;
+
+	case NETDEV_UNREGISTER:
+		br_del_if(br, dev);
+		break;
+
+	case NETDEV_CHANGENAME:
+		err = br_sysfs_renameif(p);
+		if (err)
+			return notifier_from_errno(err);
+		break;
+
+	case NETDEV_PRE_TYPE_CHANGE:
+		/* Forbid underlaying device to change its type. */
+		return NOTIFY_BAD;
+
+	case NETDEV_RESEND_IGMP:
+		/* Propagate to master device */
+		call_netdevice_notifiers(event, br->dev);
+		break;
+	}
+
+	/* Events that may cause spanning tree to refresh */
+	if (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
+	    event == NETDEV_CHANGE || event == NETDEV_DOWN)
+		br_ifinfo_notify(RTM_NEWLINK, p);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block br_device_notifier = {
+	.notifier_call = br_device_event
+};
+
 static void __net_exit br_net_exit(struct net *net)
 {
 	struct net_device *dev;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 3e2da2cb72d..568cccd39a3 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -112,6 +112,12 @@ static void br_dev_set_multicast_list(struct net_device *dev)
 {
 }
 
+static void br_dev_change_rx_flags(struct net_device *dev, int change)
+{
+	if (change & IFF_PROMISC)
+		br_manage_promisc(netdev_priv(dev));
+}
+
 static int br_dev_stop(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
@@ -309,6 +315,7 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_get_stats64	 = br_get_stats64,
 	.ndo_set_mac_address	 = br_set_mac_address,
 	.ndo_set_rx_mode	 = br_dev_set_multicast_list,
+	.ndo_change_rx_flags	 = br_dev_change_rx_flags,
 	.ndo_change_mtu		 = br_change_mtu,
 	.ndo_do_ioctl		 = br_dev_ioctl,
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -348,14 +355,15 @@ void br_dev_setup(struct net_device *dev)
 
 	dev->netdev_ops = &br_netdev_ops;
 	dev->destructor = br_dev_free;
-	SET_ETHTOOL_OPS(dev, &br_ethtool_ops);
+	dev->ethtool_ops = &br_ethtool_ops;
 	SET_NETDEV_DEVTYPE(dev, &br_type);
 	dev->tx_queue_len = 0;
 	dev->priv_flags = IFF_EBRIDGE;
 
 	dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL |
-			NETIF_F_HW_VLAN_CTAG_TX;
-	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX;
+			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
+			   NETIF_F_HW_VLAN_STAG_TX;
 	dev->vlan_features = COMMON_FEATURES;
 
 	br->dev = dev;
@@ -370,6 +378,7 @@ void br_dev_setup(struct net_device *dev)
 
 	br->stp_enabled = BR_NO_STP;
 	br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
+	br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;
 
 	br->designated_root = br->bridge_id;
 	br->bridge_max_age = br->max_age = 20 * HZ;
@@ -380,4 +389,5 @@ void br_dev_setup(struct net_device *dev)
 	br_netfilter_rtable_init(br);
 	br_stp_timer_init(br);
 	br_multicast_init(br);
+	br_vlan_init(br);
 }
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 474d36f9334..b524c36c127 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -85,8 +85,58 @@ static void fdb_rcu_free(struct rcu_head *head)
 	kmem_cache_free(br_fdb_cache, ent);
 }
 
+/* When a static FDB entry is added, the mac address from the entry is
+ * added to the bridge private HW address list and all required ports
+ * are then updated with the new information.
+ * Called under RTNL.
+ */
+static void fdb_add_hw(struct net_bridge *br, const unsigned char *addr)
+{
+	int err;
+	struct net_bridge_port *p, *tmp;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (!br_promisc_port(p)) {
+			err = dev_uc_add(p->dev, addr);
+			if (err)
+				goto undo;
+		}
+	}
+
+	return;
+undo:
+	list_for_each_entry(tmp, &br->port_list, list) {
+		if (tmp == p)
+			break;
+		if (!br_promisc_port(tmp))
+			dev_uc_del(tmp->dev, addr);
+	}
+}
+
+/* When a static FDB entry is deleted, the HW address from that entry is
+ * also removed from the bridge private HW address list and updates all
+ * the ports with needed information.
+ * Called under RTNL.
+ */
+static void fdb_del_hw(struct net_bridge *br, const unsigned char *addr)
+{
+	struct net_bridge_port *p;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (!br_promisc_port(p))
+			dev_uc_del(p->dev, addr);
+	}
+}
+
 static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
 {
+	if (f->is_static)
+		fdb_del_hw(br, f->addr.addr);
+
 	hlist_del_rcu(&f->hlist);
 	fdb_notify(br, f, RTM_DELNEIGH);
 	call_rcu(&f->rcu, fdb_rcu_free);
@@ -466,6 +516,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 		return -ENOMEM;
 
 	fdb->is_local = fdb->is_static = 1;
+	fdb_add_hw(br, addr);
 	fdb_notify(br, fdb, RTM_NEWNEIGH);
 	return 0;
 }
@@ -571,6 +622,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
 
 	if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr))
 		goto nla_put_failure;
+	if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex))
+		goto nla_put_failure;
 	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
 	ci.ndm_confirmed = 0;
 	ci.ndm_updated	 = jiffies_to_clock_t(now - fdb->updated);
@@ -592,6 +645,7 @@ static inline size_t fdb_nlmsg_size(void)
 {
 	return NLMSG_ALIGN(sizeof(struct ndmsg))
 		+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */
+		+ nla_total_size(sizeof(u32)) /* NDA_MASTER */
 		+ nla_total_size(sizeof(u16)) /* NDA_VLAN */
 		+ nla_total_size(sizeof(struct nda_cacheinfo));
 }
@@ -684,13 +738,25 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
 	}
 
 	if (fdb_to_nud(fdb) != state) {
-		if (state & NUD_PERMANENT)
-			fdb->is_local = fdb->is_static = 1;
-		else if (state & NUD_NOARP) {
+		if (state & NUD_PERMANENT) {
+			fdb->is_local = 1;
+			if (!fdb->is_static) {
+				fdb->is_static = 1;
+				fdb_add_hw(br, addr);
+			}
+		} else if (state & NUD_NOARP) {
 			fdb->is_local = 0;
-			fdb->is_static = 1;
-		} else
-			fdb->is_local = fdb->is_static = 0;
+			if (!fdb->is_static) {
+				fdb->is_static = 1;
+				fdb_add_hw(br, addr);
+			}
+		} else {
+			fdb->is_local = 0;
+			if (fdb->is_static) {
+				fdb->is_static = 0;
+				fdb_del_hw(br, addr);
+			}
+		}
 
 		modified = true;
 	}
@@ -880,3 +946,59 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 out:
 	return err;
 }
+
+int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p)
+{
+	struct net_bridge_fdb_entry *fdb, *tmp;
+	int i;
+	int err;
+
+	ASSERT_RTNL();
+
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		hlist_for_each_entry(fdb, &br->hash[i], hlist) {
+			/* We only care for static entries */
+			if (!fdb->is_static)
+				continue;
+
+			err = dev_uc_add(p->dev, fdb->addr.addr);
+			if (err)
+				goto rollback;
+		}
+	}
+	return 0;
+
+rollback:
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		hlist_for_each_entry(tmp, &br->hash[i], hlist) {
+			/* If we reached the fdb that failed, we can stop */
+			if (tmp == fdb)
+				break;
+
+			/* We only care for static entries */
+			if (!tmp->is_static)
+				continue;
+
+			dev_uc_del(p->dev, tmp->addr.addr);
+		}
+	}
+	return err;
+}
+
+void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p)
+{
+	struct net_bridge_fdb_entry *fdb;
+	int i;
+
+	ASSERT_RTNL();
+
+	for (i = 0; i < BR_HASH_SIZE; i++) {
+		hlist_for_each_entry_rcu(fdb, &br->hash[i], hlist) {
+			/* We only care for static entries */
+			if (!fdb->is_static)
+				continue;
+
+			dev_uc_del(p->dev, fdb->addr.addr);
+		}
+	}
+}
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 5262b8617eb..3eca3fdf8fe 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -85,6 +85,111 @@ void br_port_carrier_check(struct net_bridge_port *p)
 	spin_unlock_bh(&br->lock);
 }
 
+static void br_port_set_promisc(struct net_bridge_port *p)
+{
+	int err = 0;
+
+	if (br_promisc_port(p))
+		return;
+
+	err = dev_set_promiscuity(p->dev, 1);
+	if (err)
+		return;
+
+	br_fdb_unsync_static(p->br, p);
+	p->flags |= BR_PROMISC;
+}
+
+static void br_port_clear_promisc(struct net_bridge_port *p)
+{
+	int err;
+
+	/* Check if the port is already non-promisc or if it doesn't
+	 * support UNICAST filtering.  Without unicast filtering support
+	 * we'll end up re-enabling promisc mode anyway, so just check for
+	 * it here.
+	 */
+	if (!br_promisc_port(p) || !(p->dev->priv_flags & IFF_UNICAST_FLT))
+		return;
+
+	/* Since we'll be clearing the promisc mode, program the port
+	 * first so that we don't have interruption in traffic.
+	 */
+	err = br_fdb_sync_static(p->br, p);
+	if (err)
+		return;
+
+	dev_set_promiscuity(p->dev, -1);
+	p->flags &= ~BR_PROMISC;
+}
+
+/* When a port is added or removed or when certain port flags
+ * change, this function is called to automatically manage
+ * promiscuity setting of all the bridge ports.  We are always called
+ * under RTNL so can skip using rcu primitives.
+ */
+void br_manage_promisc(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+	bool set_all = false;
+
+	/* If vlan filtering is disabled or bridge interface is placed
+	 * into promiscuous mode, place all ports in promiscuous mode.
+	 */
+	if ((br->dev->flags & IFF_PROMISC) || !br_vlan_enabled(br))
+		set_all = true;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (set_all) {
+			br_port_set_promisc(p);
+		} else {
+			/* If the number of auto-ports is <= 1, then all other
+			 * ports will have their output configuration
+			 * statically specified through fdbs.  Since ingress
+			 * on the auto-port becomes forwarding/egress to other
+			 * ports and egress configuration is statically known,
+			 * we can say that ingress configuration of the
+			 * auto-port is also statically known.
+			 * This lets us disable promiscuous mode and write
+			 * this config to hw.
+			 */
+			if (br->auto_cnt == 0 ||
+			    (br->auto_cnt == 1 && br_auto_port(p)))
+				br_port_clear_promisc(p);
+			else
+				br_port_set_promisc(p);
+		}
+	}
+}
+
+static void nbp_update_port_count(struct net_bridge *br)
+{
+	struct net_bridge_port *p;
+	u32 cnt = 0;
+
+	list_for_each_entry(p, &br->port_list, list) {
+		if (br_auto_port(p))
+			cnt++;
+	}
+	if (br->auto_cnt != cnt) {
+		br->auto_cnt = cnt;
+		br_manage_promisc(br);
+	}
+}
+
+static void nbp_delete_promisc(struct net_bridge_port *p)
+{
+	/* If port is currently promiscuous, unset promiscuity.
+	 * Otherwise, it is a static port so remove all addresses
+	 * from it.
+	 */
+	dev_set_allmulti(p->dev, -1);
+	if (br_promisc_port(p))
+		dev_set_promiscuity(p->dev, -1);
+	else
+		br_fdb_unsync_static(p->br, p);
+}
+
 static void release_nbp(struct kobject *kobj)
 {
 	struct net_bridge_port *p
@@ -133,7 +238,7 @@ static void del_nbp(struct net_bridge_port *p)
 
 	sysfs_remove_link(br->ifobj, p->dev->name);
 
-	dev_set_promiscuity(dev, -1);
+	nbp_delete_promisc(p);
 
 	spin_lock_bh(&br->lock);
 	br_stp_disable_port(p);
@@ -141,10 +246,11 @@ static void del_nbp(struct net_bridge_port *p)
 
 	br_ifinfo_notify(RTM_DELLINK, p);
 
+	list_del_rcu(&p->list);
+
 	nbp_vlan_flush(p);
 	br_fdb_delete_by_port(br, p, 1);
-
-	list_del_rcu(&p->list);
+	nbp_update_port_count(br);
 
 	dev->priv_flags &= ~IFF_BRIDGE_PORT;
 
@@ -353,7 +459,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 
 	call_netdevice_notifiers(NETDEV_JOIN, dev);
 
-	err = dev_set_promiscuity(dev, 1);
+	err = dev_set_allmulti(dev, 1);
 	if (err)
 		goto put_back;
 
@@ -384,6 +490,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 
 	list_add_rcu(&p->list, &br->port_list);
 
+	nbp_update_port_count(br);
+
 	netdev_update_features(br->dev);
 
 	if (br->dev->needed_headroom < dev->needed_headroom)
@@ -421,7 +529,7 @@ err2:
 	kobject_put(&p->kobj);
 	p = NULL; /* kobject_put frees */
 err1:
-	dev_set_promiscuity(dev, -1);
+	dev_set_allmulti(dev, -1);
 put_back:
 	dev_put(dev);
 	kfree(p);
@@ -455,3 +563,11 @@ int br_del_if(struct net_bridge *br, struct net_device *dev)
 
 	return 0;
 }
+
+void br_port_flags_change(struct net_bridge_port *p, unsigned long mask)
+{
+	struct net_bridge *br = p->br;
+
+	if (mask & BR_AUTO_MASK)
+		nbp_update_port_count(br);
+}
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 04d6348fd53..366c4364907 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -177,6 +177,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 	p = br_port_get_rcu(skb->dev);
 
 	if (unlikely(is_link_local_ether_addr(dest))) {
+		u16 fwd_mask = p->br->group_fwd_mask_required;
+
 		/*
 		 * See IEEE 802.1D Table 7-10 Reserved addresses
 		 *
@@ -194,7 +196,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		case 0x00:	/* Bridge Group Address */
 			/* If STP is turned off,
 			   then must forward to keep loop detection */
-			if (p->br->stp_enabled == BR_NO_STP)
+			if (p->br->stp_enabled == BR_NO_STP ||
+			    fwd_mask & (1u << dest[5]))
 				goto forward;
 			break;
 
@@ -203,7 +206,8 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 
 		default:
 			/* Allow selective forwarding for most other protocols */
-			if (p->br->group_fwd_mask & (1u << dest[5]))
+			fwd_mask |= p->br->group_fwd_mask;
+			if (fwd_mask & (1u << dest[5]))
 				goto forward;
 		}
 
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index b7b1914dfa2..5df05269d17 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -418,13 +418,13 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP)) {
-		if (timer_pending(&br->ip4_querier.timer))
+		if (timer_pending(&br->ip4_other_query.timer))
 			return -EBUSY;
 
 		ip.u.ip4 = entry->addr.u.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
-		if (timer_pending(&br->ip6_querier.timer))
+		if (timer_pending(&br->ip6_other_query.timer))
 			return -EBUSY;
 
 		ip.u.ip6 = entry->addr.u.ip6;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 7b757b5dc77..abfa0b65a11 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/err.h>
+#include <linux/export.h>
 #include <linux/if_ether.h>
 #include <linux/igmp.h>
 #include <linux/jhash.h>
@@ -35,7 +36,7 @@
 #include "br_private.h"
 
 static void br_multicast_start_querier(struct net_bridge *br,
-				       struct bridge_mcast_query *query);
+				       struct bridge_mcast_own_query *query);
 unsigned int br_mdb_rehash_seq;
 
 static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
@@ -761,7 +762,7 @@ static void br_multicast_local_router_expired(unsigned long data)
 }
 
 static void br_multicast_querier_expired(struct net_bridge *br,
-					 struct bridge_mcast_query *query)
+					 struct bridge_mcast_own_query *query)
 {
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) || br->multicast_disabled)
@@ -777,7 +778,7 @@ static void br_ip4_multicast_querier_expired(unsigned long data)
 {
 	struct net_bridge *br = (void *)data;
 
-	br_multicast_querier_expired(br, &br->ip4_query);
+	br_multicast_querier_expired(br, &br->ip4_own_query);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -785,10 +786,22 @@ static void br_ip6_multicast_querier_expired(unsigned long data)
 {
 	struct net_bridge *br = (void *)data;
 
-	br_multicast_querier_expired(br, &br->ip6_query);
+	br_multicast_querier_expired(br, &br->ip6_own_query);
 }
 #endif
 
+static void br_multicast_select_own_querier(struct net_bridge *br,
+					    struct br_ip *ip,
+					    struct sk_buff *skb)
+{
+	if (ip->proto == htons(ETH_P_IP))
+		br->ip4_querier.addr.u.ip4 = ip_hdr(skb)->saddr;
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		br->ip6_querier.addr.u.ip6 = ipv6_hdr(skb)->saddr;
+#endif
+}
+
 static void __br_multicast_send_query(struct net_bridge *br,
 				      struct net_bridge_port *port,
 				      struct br_ip *ip)
@@ -804,17 +817,19 @@ static void __br_multicast_send_query(struct net_bridge *br,
 		skb->dev = port->dev;
 		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
 			dev_queue_xmit);
-	} else
+	} else {
+		br_multicast_select_own_querier(br, ip, skb);
 		netif_rx(skb);
+	}
 }
 
 static void br_multicast_send_query(struct net_bridge *br,
 				    struct net_bridge_port *port,
-				    struct bridge_mcast_query *query)
+				    struct bridge_mcast_own_query *own_query)
 {
 	unsigned long time;
 	struct br_ip br_group;
-	struct bridge_mcast_querier *querier = NULL;
+	struct bridge_mcast_other_query *other_query = NULL;
 
 	if (!netif_running(br->dev) || br->multicast_disabled ||
 	    !br->multicast_querier)
@@ -822,31 +837,32 @@ static void br_multicast_send_query(struct net_bridge *br,
 
 	memset(&br_group.u, 0, sizeof(br_group.u));
 
-	if (port ? (query == &port->ip4_query) :
-		   (query == &br->ip4_query)) {
-		querier = &br->ip4_querier;
+	if (port ? (own_query == &port->ip4_own_query) :
+		   (own_query == &br->ip4_own_query)) {
+		other_query = &br->ip4_other_query;
 		br_group.proto = htons(ETH_P_IP);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
-		querier = &br->ip6_querier;
+		other_query = &br->ip6_other_query;
 		br_group.proto = htons(ETH_P_IPV6);
 #endif
 	}
 
-	if (!querier || timer_pending(&querier->timer))
+	if (!other_query || timer_pending(&other_query->timer))
 		return;
 
 	__br_multicast_send_query(br, port, &br_group);
 
 	time = jiffies;
-	time += query->startup_sent < br->multicast_startup_query_count ?
+	time += own_query->startup_sent < br->multicast_startup_query_count ?
 		br->multicast_startup_query_interval :
 		br->multicast_query_interval;
-	mod_timer(&query->timer, time);
+	mod_timer(&own_query->timer, time);
 }
 
-static void br_multicast_port_query_expired(struct net_bridge_port *port,
-					    struct bridge_mcast_query *query)
+static void
+br_multicast_port_query_expired(struct net_bridge_port *port,
+				struct bridge_mcast_own_query *query)
 {
 	struct net_bridge *br = port->br;
 
@@ -868,7 +884,7 @@ static void br_ip4_multicast_port_query_expired(unsigned long data)
 {
 	struct net_bridge_port *port = (void *)data;
 
-	br_multicast_port_query_expired(port, &port->ip4_query);
+	br_multicast_port_query_expired(port, &port->ip4_own_query);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -876,7 +892,7 @@ static void br_ip6_multicast_port_query_expired(unsigned long data)
 {
 	struct net_bridge_port *port = (void *)data;
 
-	br_multicast_port_query_expired(port, &port->ip6_query);
+	br_multicast_port_query_expired(port, &port->ip6_own_query);
 }
 #endif
 
@@ -886,11 +902,11 @@ void br_multicast_add_port(struct net_bridge_port *port)
 
 	setup_timer(&port->multicast_router_timer, br_multicast_router_expired,
 		    (unsigned long)port);
-	setup_timer(&port->ip4_query.timer, br_ip4_multicast_port_query_expired,
-		    (unsigned long)port);
+	setup_timer(&port->ip4_own_query.timer,
+		    br_ip4_multicast_port_query_expired, (unsigned long)port);
 #if IS_ENABLED(CONFIG_IPV6)
-	setup_timer(&port->ip6_query.timer, br_ip6_multicast_port_query_expired,
-		    (unsigned long)port);
+	setup_timer(&port->ip6_own_query.timer,
+		    br_ip6_multicast_port_query_expired, (unsigned long)port);
 #endif
 }
 
@@ -899,7 +915,7 @@ void br_multicast_del_port(struct net_bridge_port *port)
 	del_timer_sync(&port->multicast_router_timer);
 }
 
-static void br_multicast_enable(struct bridge_mcast_query *query)
+static void br_multicast_enable(struct bridge_mcast_own_query *query)
 {
 	query->startup_sent = 0;
 
@@ -916,9 +932,9 @@ void br_multicast_enable_port(struct net_bridge_port *port)
 	if (br->multicast_disabled || !netif_running(br->dev))
 		goto out;
 
-	br_multicast_enable(&port->ip4_query);
+	br_multicast_enable(&port->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
-	br_multicast_enable(&port->ip6_query);
+	br_multicast_enable(&port->ip6_own_query);
 #endif
 
 out:
@@ -938,9 +954,9 @@ void br_multicast_disable_port(struct net_bridge_port *port)
 	if (!hlist_unhashed(&port->rlist))
 		hlist_del_init_rcu(&port->rlist);
 	del_timer(&port->multicast_router_timer);
-	del_timer(&port->ip4_query.timer);
+	del_timer(&port->ip4_own_query.timer);
 #if IS_ENABLED(CONFIG_IPV6)
-	del_timer(&port->ip6_query.timer);
+	del_timer(&port->ip6_own_query.timer);
 #endif
 	spin_unlock(&br->multicast_lock);
 }
@@ -1064,15 +1080,80 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 }
 #endif
 
+static bool br_ip4_multicast_select_querier(struct net_bridge *br,
+					    struct net_bridge_port *port,
+					    __be32 saddr)
+{
+	if (!timer_pending(&br->ip4_own_query.timer) &&
+	    !timer_pending(&br->ip4_other_query.timer))
+		goto update;
+
+	if (!br->ip4_querier.addr.u.ip4)
+		goto update;
+
+	if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.u.ip4))
+		goto update;
+
+	return false;
+
+update:
+	br->ip4_querier.addr.u.ip4 = saddr;
+
+	/* update protected by general multicast_lock by caller */
+	rcu_assign_pointer(br->ip4_querier.port, port);
+
+	return true;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static bool br_ip6_multicast_select_querier(struct net_bridge *br,
+					    struct net_bridge_port *port,
+					    struct in6_addr *saddr)
+{
+	if (!timer_pending(&br->ip6_own_query.timer) &&
+	    !timer_pending(&br->ip6_other_query.timer))
+		goto update;
+
+	if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.u.ip6) <= 0)
+		goto update;
+
+	return false;
+
+update:
+	br->ip6_querier.addr.u.ip6 = *saddr;
+
+	/* update protected by general multicast_lock by caller */
+	rcu_assign_pointer(br->ip6_querier.port, port);
+
+	return true;
+}
+#endif
+
+static bool br_multicast_select_querier(struct net_bridge *br,
+					struct net_bridge_port *port,
+					struct br_ip *saddr)
+{
+	switch (saddr->proto) {
+	case htons(ETH_P_IP):
+		return br_ip4_multicast_select_querier(br, port, saddr->u.ip4);
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		return br_ip6_multicast_select_querier(br, port, &saddr->u.ip6);
+#endif
+	}
+
+	return false;
+}
+
 static void
-br_multicast_update_querier_timer(struct net_bridge *br,
-				  struct bridge_mcast_querier *querier,
-				  unsigned long max_delay)
+br_multicast_update_query_timer(struct net_bridge *br,
+				struct bridge_mcast_other_query *query,
+				unsigned long max_delay)
 {
-	if (!timer_pending(&querier->timer))
-		querier->delay_time = jiffies + max_delay;
+	if (!timer_pending(&query->timer))
+		query->delay_time = jiffies + max_delay;
 
-	mod_timer(&querier->timer, jiffies + br->multicast_querier_interval);
+	mod_timer(&query->timer, jiffies + br->multicast_querier_interval);
 }
 
 /*
@@ -1125,16 +1206,14 @@ timer:
 
 static void br_multicast_query_received(struct net_bridge *br,
 					struct net_bridge_port *port,
-					struct bridge_mcast_querier *querier,
-					int saddr,
-					bool is_general_query,
+					struct bridge_mcast_other_query *query,
+					struct br_ip *saddr,
 					unsigned long max_delay)
 {
-	if (saddr && is_general_query)
-		br_multicast_update_querier_timer(br, querier, max_delay);
-	else if (timer_pending(&querier->timer))
+	if (!br_multicast_select_querier(br, port, saddr))
 		return;
 
+	br_multicast_update_query_timer(br, query, max_delay);
 	br_multicast_mark_router(br, port);
 }
 
@@ -1149,6 +1228,7 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 	struct igmpv3_query *ih3;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
+	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
 	__be32 group;
@@ -1190,11 +1270,14 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 		goto out;
 	}
 
-	br_multicast_query_received(br, port, &br->ip4_querier, !!iph->saddr,
-				    !group, max_delay);
+	if (!group) {
+		saddr.proto = htons(ETH_P_IP);
+		saddr.u.ip4 = iph->saddr;
 
-	if (!group)
+		br_multicast_query_received(br, port, &br->ip4_other_query,
+					    &saddr, max_delay);
 		goto out;
+	}
 
 	mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group, vid);
 	if (!mp)
@@ -1234,6 +1317,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	struct mld2_query *mld2q;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
+	struct br_ip saddr;
 	unsigned long max_delay;
 	unsigned long now = jiffies;
 	const struct in6_addr *group = NULL;
@@ -1282,12 +1366,16 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 		goto out;
 	}
 
-	br_multicast_query_received(br, port, &br->ip6_querier,
-				    !ipv6_addr_any(&ip6h->saddr),
-				    is_general_query, max_delay);
+	if (is_general_query) {
+		saddr.proto = htons(ETH_P_IPV6);
+		saddr.u.ip6 = ip6h->saddr;
 
-	if (!group)
+		br_multicast_query_received(br, port, &br->ip6_other_query,
+					    &saddr, max_delay);
+		goto out;
+	} else if (!group) {
 		goto out;
+	}
 
 	mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group, vid);
 	if (!mp)
@@ -1315,11 +1403,12 @@ out:
 }
 #endif
 
-static void br_multicast_leave_group(struct net_bridge *br,
-				     struct net_bridge_port *port,
-				     struct br_ip *group,
-				     struct bridge_mcast_querier *querier,
-				     struct bridge_mcast_query *query)
+static void
+br_multicast_leave_group(struct net_bridge *br,
+			 struct net_bridge_port *port,
+			 struct br_ip *group,
+			 struct bridge_mcast_other_query *other_query,
+			 struct bridge_mcast_own_query *own_query)
 {
 	struct net_bridge_mdb_htable *mdb;
 	struct net_bridge_mdb_entry *mp;
@@ -1330,7 +1419,7 @@ static void br_multicast_leave_group(struct net_bridge *br,
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) ||
 	    (port && port->state == BR_STATE_DISABLED) ||
-	    timer_pending(&querier->timer))
+	    timer_pending(&other_query->timer))
 		goto out;
 
 	mdb = mlock_dereference(br->mdb, br);
@@ -1344,7 +1433,7 @@ static void br_multicast_leave_group(struct net_bridge *br,
 		time = jiffies + br->multicast_last_member_count *
 				 br->multicast_last_member_interval;
 
-		mod_timer(&query->timer, time);
+		mod_timer(&own_query->timer, time);
 
 		for (p = mlock_dereference(mp->ports, br);
 		     p != NULL;
@@ -1425,17 +1514,19 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 					 __u16 vid)
 {
 	struct br_ip br_group;
-	struct bridge_mcast_query *query = port ? &port->ip4_query :
-						  &br->ip4_query;
+	struct bridge_mcast_own_query *own_query;
 
 	if (ipv4_is_local_multicast(group))
 		return;
 
+	own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
+
 	br_group.u.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
 
-	br_multicast_leave_group(br, port, &br_group, &br->ip4_querier, query);
+	br_multicast_leave_group(br, port, &br_group, &br->ip4_other_query,
+				 own_query);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1445,18 +1536,19 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 					 __u16 vid)
 {
 	struct br_ip br_group;
-	struct bridge_mcast_query *query = port ? &port->ip6_query :
-						  &br->ip6_query;
-
+	struct bridge_mcast_own_query *own_query;
 
 	if (ipv6_addr_is_ll_all_nodes(group))
 		return;
 
+	own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
+
 	br_group.u.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
 
-	br_multicast_leave_group(br, port, &br_group, &br->ip6_querier, query);
+	br_multicast_leave_group(br, port, &br_group, &br->ip6_other_query,
+				 own_query);
 }
 #endif
 
@@ -1723,12 +1815,14 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
 }
 
 static void br_multicast_query_expired(struct net_bridge *br,
-				       struct bridge_mcast_query *query)
+				       struct bridge_mcast_own_query *query,
+				       struct bridge_mcast_querier *querier)
 {
 	spin_lock(&br->multicast_lock);
 	if (query->startup_sent < br->multicast_startup_query_count)
 		query->startup_sent++;
 
+	rcu_assign_pointer(querier, NULL);
 	br_multicast_send_query(br, NULL, query);
 	spin_unlock(&br->multicast_lock);
 }
@@ -1737,7 +1831,7 @@ static void br_ip4_multicast_query_expired(unsigned long data)
 {
 	struct net_bridge *br = (void *)data;
 
-	br_multicast_query_expired(br, &br->ip4_query);
+	br_multicast_query_expired(br, &br->ip4_own_query, &br->ip4_querier);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1745,7 +1839,7 @@ static void br_ip6_multicast_query_expired(unsigned long data)
 {
 	struct net_bridge *br = (void *)data;
 
-	br_multicast_query_expired(br, &br->ip6_query);
+	br_multicast_query_expired(br, &br->ip6_own_query, &br->ip6_querier);
 }
 #endif
 
@@ -1767,28 +1861,30 @@ void br_multicast_init(struct net_bridge *br)
 	br->multicast_querier_interval = 255 * HZ;
 	br->multicast_membership_interval = 260 * HZ;
 
-	br->ip4_querier.delay_time = 0;
+	br->ip4_other_query.delay_time = 0;
+	br->ip4_querier.port = NULL;
 #if IS_ENABLED(CONFIG_IPV6)
-	br->ip6_querier.delay_time = 0;
+	br->ip6_other_query.delay_time = 0;
+	br->ip6_querier.port = NULL;
 #endif
 
 	spin_lock_init(&br->multicast_lock);
 	setup_timer(&br->multicast_router_timer,
 		    br_multicast_local_router_expired, 0);
-	setup_timer(&br->ip4_querier.timer, br_ip4_multicast_querier_expired,
-		    (unsigned long)br);
-	setup_timer(&br->ip4_query.timer, br_ip4_multicast_query_expired,
+	setup_timer(&br->ip4_other_query.timer,
+		    br_ip4_multicast_querier_expired, (unsigned long)br);
+	setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired,
 		    (unsigned long)br);
 #if IS_ENABLED(CONFIG_IPV6)
-	setup_timer(&br->ip6_querier.timer, br_ip6_multicast_querier_expired,
-		    (unsigned long)br);
-	setup_timer(&br->ip6_query.timer, br_ip6_multicast_query_expired,
+	setup_timer(&br->ip6_other_query.timer,
+		    br_ip6_multicast_querier_expired, (unsigned long)br);
+	setup_timer(&br->ip6_own_query.timer, br_ip6_multicast_query_expired,
 		    (unsigned long)br);
 #endif
 }
 
 static void __br_multicast_open(struct net_bridge *br,
-				struct bridge_mcast_query *query)
+				struct bridge_mcast_own_query *query)
 {
 	query->startup_sent = 0;
 
@@ -1800,9 +1896,9 @@ static void __br_multicast_open(struct net_bridge *br,
 
 void br_multicast_open(struct net_bridge *br)
 {
-	__br_multicast_open(br, &br->ip4_query);
+	__br_multicast_open(br, &br->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
-	__br_multicast_open(br, &br->ip6_query);
+	__br_multicast_open(br, &br->ip6_own_query);
 #endif
 }
 
@@ -1815,11 +1911,11 @@ void br_multicast_stop(struct net_bridge *br)
 	int i;
 
 	del_timer_sync(&br->multicast_router_timer);
-	del_timer_sync(&br->ip4_querier.timer);
-	del_timer_sync(&br->ip4_query.timer);
+	del_timer_sync(&br->ip4_other_query.timer);
+	del_timer_sync(&br->ip4_own_query.timer);
 #if IS_ENABLED(CONFIG_IPV6)
-	del_timer_sync(&br->ip6_querier.timer);
-	del_timer_sync(&br->ip6_query.timer);
+	del_timer_sync(&br->ip6_other_query.timer);
+	del_timer_sync(&br->ip6_own_query.timer);
 #endif
 
 	spin_lock_bh(&br->multicast_lock);
@@ -1923,7 +2019,7 @@ unlock:
 }
 
 static void br_multicast_start_querier(struct net_bridge *br,
-				       struct bridge_mcast_query *query)
+				       struct bridge_mcast_own_query *query)
 {
 	struct net_bridge_port *port;
 
@@ -1934,11 +2030,11 @@ static void br_multicast_start_querier(struct net_bridge *br,
 		    port->state == BR_STATE_BLOCKING)
 			continue;
 
-		if (query == &br->ip4_query)
-			br_multicast_enable(&port->ip4_query);
+		if (query == &br->ip4_own_query)
+			br_multicast_enable(&port->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
 		else
-			br_multicast_enable(&port->ip6_query);
+			br_multicast_enable(&port->ip6_own_query);
 #endif
 	}
 }
@@ -1974,9 +2070,9 @@ rollback:
 			goto rollback;
 	}
 
-	br_multicast_start_querier(br, &br->ip4_query);
+	br_multicast_start_querier(br, &br->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
-	br_multicast_start_querier(br, &br->ip6_query);
+	br_multicast_start_querier(br, &br->ip6_own_query);
 #endif
 
 unlock:
@@ -2001,16 +2097,16 @@ int br_multicast_set_querier(struct net_bridge *br, unsigned long val)
 
 	max_delay = br->multicast_query_response_interval;
 
-	if (!timer_pending(&br->ip4_querier.timer))
-		br->ip4_querier.delay_time = jiffies + max_delay;
+	if (!timer_pending(&br->ip4_other_query.timer))
+		br->ip4_other_query.delay_time = jiffies + max_delay;
 
-	br_multicast_start_querier(br, &br->ip4_query);
+	br_multicast_start_querier(br, &br->ip4_own_query);
 
 #if IS_ENABLED(CONFIG_IPV6)
-	if (!timer_pending(&br->ip6_querier.timer))
-		br->ip6_querier.delay_time = jiffies + max_delay;
+	if (!timer_pending(&br->ip6_other_query.timer))
+		br->ip6_other_query.delay_time = jiffies + max_delay;
 
-	br_multicast_start_querier(br, &br->ip6_query);
+	br_multicast_start_querier(br, &br->ip6_own_query);
 #endif
 
 unlock:
@@ -2061,3 +2157,109 @@ unlock:
 
 	return err;
 }
+
+/**
+ * br_multicast_list_adjacent - Returns snooped multicast addresses
+ * @dev:	The bridge port adjacent to which to retrieve addresses
+ * @br_ip_list:	The list to store found, snooped multicast IP addresses in
+ *
+ * Creates a list of IP addresses (struct br_ip_list) sensed by the multicast
+ * snooping feature on all bridge ports of dev's bridge device, excluding
+ * the addresses from dev itself.
+ *
+ * Returns the number of items added to br_ip_list.
+ *
+ * Notes:
+ * - br_ip_list needs to be initialized by caller
+ * - br_ip_list might contain duplicates in the end
+ *   (needs to be taken care of by caller)
+ * - br_ip_list needs to be freed by caller
+ */
+int br_multicast_list_adjacent(struct net_device *dev,
+			       struct list_head *br_ip_list)
+{
+	struct net_bridge *br;
+	struct net_bridge_port *port;
+	struct net_bridge_port_group *group;
+	struct br_ip_list *entry;
+	int count = 0;
+
+	rcu_read_lock();
+	if (!br_ip_list || !br_port_exists(dev))
+		goto unlock;
+
+	port = br_port_get_rcu(dev);
+	if (!port || !port->br)
+		goto unlock;
+
+	br = port->br;
+
+	list_for_each_entry_rcu(port, &br->port_list, list) {
+		if (!port->dev || port->dev == dev)
+			continue;
+
+		hlist_for_each_entry_rcu(group, &port->mglist, mglist) {
+			entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+			if (!entry)
+				goto unlock;
+
+			entry->addr = group->addr;
+			list_add(&entry->list, br_ip_list);
+			count++;
+		}
+	}
+
+unlock:
+	rcu_read_unlock();
+	return count;
+}
+EXPORT_SYMBOL_GPL(br_multicast_list_adjacent);
+
+/**
+ * br_multicast_has_querier_adjacent - Checks for a querier behind a bridge port
+ * @dev: The bridge port adjacent to which to check for a querier
+ * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6
+ *
+ * Checks whether the given interface has a bridge on top and if so returns
+ * true if a selected querier is behind one of the other ports of this
+ * bridge. Otherwise returns false.
+ */
+bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto)
+{
+	struct net_bridge *br;
+	struct net_bridge_port *port;
+	bool ret = false;
+
+	rcu_read_lock();
+	if (!br_port_exists(dev))
+		goto unlock;
+
+	port = br_port_get_rcu(dev);
+	if (!port || !port->br)
+		goto unlock;
+
+	br = port->br;
+
+	switch (proto) {
+	case ETH_P_IP:
+		if (!timer_pending(&br->ip4_other_query.timer) ||
+		    rcu_dereference(br->ip4_querier.port) == port)
+			goto unlock;
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case ETH_P_IPV6:
+		if (!timer_pending(&br->ip6_other_query.timer) ||
+		    rcu_dereference(br->ip6_querier.port) == port)
+			goto unlock;
+		break;
+#endif
+	default:
+		goto unlock;
+	}
+
+	ret = true;
+unlock:
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent);
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 2acf7fa1fec..a615264cf01 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -535,7 +535,7 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct
 	if (brnf_pass_vlan_indev == 0 || !vlan_tx_tag_present(skb))
 		return br;
 
-	vlan = __vlan_find_dev_deep(br, skb->vlan_proto,
+	vlan = __vlan_find_dev_deep_rcu(br, skb->vlan_proto,
 				    vlan_tx_tag_get(skb) & VLAN_VID_MASK);
 
 	return vlan ? vlan : br;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index e8844d975b3..26edb518b83 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -328,6 +328,7 @@ static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[],
 static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 {
 	int err;
+	unsigned long old_flags = p->flags;
 
 	br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE);
 	br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD);
@@ -353,6 +354,8 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 		if (err)
 			return err;
 	}
+
+	br_port_flags_change(p, old_flags ^ p->flags);
 	return 0;
 }
 
diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c
deleted file mode 100644
index 2998dd1769a..00000000000
--- a/net/bridge/br_notify.c
+++ /dev/null
@@ -1,118 +0,0 @@
-/*
- *	Device event handling
- *	Linux ethernet bridge
- *
- *	Authors:
- *	Lennert Buytenhek		<buytenh@gnu.org>
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/rtnetlink.h>
-#include <net/net_namespace.h>
-
-#include "br_private.h"
-
-static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr);
-
-struct notifier_block br_device_notifier = {
-	.notifier_call = br_device_event
-};
-
-/*
- * Handle changes in state of network devices enslaved to a bridge.
- *
- * Note: don't care about up/down if bridge itself is down, because
- *     port state is checked when bridge is brought up.
- */
-static int br_device_event(struct notifier_block *unused, unsigned long event, void *ptr)
-{
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
-	struct net_bridge_port *p;
-	struct net_bridge *br;
-	bool changed_addr;
-	int err;
-
-	/* register of bridge completed, add sysfs entries */
-	if ((dev->priv_flags & IFF_EBRIDGE) && event == NETDEV_REGISTER) {
-		br_sysfs_addbr(dev);
-		return NOTIFY_DONE;
-	}
-
-	/* not a port of a bridge */
-	p = br_port_get_rtnl(dev);
-	if (!p)
-		return NOTIFY_DONE;
-
-	br = p->br;
-
-	switch (event) {
-	case NETDEV_CHANGEMTU:
-		dev_set_mtu(br->dev, br_min_mtu(br));
-		break;
-
-	case NETDEV_CHANGEADDR:
-		spin_lock_bh(&br->lock);
-		br_fdb_changeaddr(p, dev->dev_addr);
-		changed_addr = br_stp_recalculate_bridge_id(br);
-		spin_unlock_bh(&br->lock);
-
-		if (changed_addr)
-			call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev);
-
-		break;
-
-	case NETDEV_CHANGE:
-		br_port_carrier_check(p);
-		break;
-
-	case NETDEV_FEAT_CHANGE:
-		netdev_update_features(br->dev);
-		break;
-
-	case NETDEV_DOWN:
-		spin_lock_bh(&br->lock);
-		if (br->dev->flags & IFF_UP)
-			br_stp_disable_port(p);
-		spin_unlock_bh(&br->lock);
-		break;
-
-	case NETDEV_UP:
-		if (netif_running(br->dev) && netif_oper_up(dev)) {
-			spin_lock_bh(&br->lock);
-			br_stp_enable_port(p);
-			spin_unlock_bh(&br->lock);
-		}
-		break;
-
-	case NETDEV_UNREGISTER:
-		br_del_if(br, dev);
-		break;
-
-	case NETDEV_CHANGENAME:
-		err = br_sysfs_renameif(p);
-		if (err)
-			return notifier_from_errno(err);
-		break;
-
-	case NETDEV_PRE_TYPE_CHANGE:
-		/* Forbid underlaying device to change its type. */
-		return NOTIFY_BAD;
-
-	case NETDEV_RESEND_IGMP:
-		/* Propagate to master device */
-		call_netdevice_notifiers(event, br->dev);
-		break;
-	}
-
-	/* Events that may cause spanning tree to refresh */
-	if (event == NETDEV_CHANGEADDR || event == NETDEV_UP ||
-	    event == NETDEV_CHANGE || event == NETDEV_DOWN)
-		br_ifinfo_notify(RTM_NEWLINK, p);
-
-	return NOTIFY_DONE;
-}
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 59d3a85c587..23caf5b0309 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -35,6 +35,8 @@
 #define BR_GROUPFWD_DEFAULT	0
 /* Don't allow forwarding control protocols like STP and LLDP */
 #define BR_GROUPFWD_RESTRICTED	0x4007u
+/* The Nearest Customer Bridge Group Address, 01-80-C2-00-00-[00,0B,0C,0D,0F] */
+#define BR_GROUPFWD_8021AD	0xB801u
 
 /* Path to usermode spanning tree program */
 #define BR_STP_PROG	"/sbin/bridge-stp"
@@ -54,30 +56,24 @@ struct mac_addr
 	unsigned char	addr[ETH_ALEN];
 };
 
-struct br_ip
-{
-	union {
-		__be32	ip4;
-#if IS_ENABLED(CONFIG_IPV6)
-		struct in6_addr ip6;
-#endif
-	} u;
-	__be16		proto;
-	__u16		vid;
-};
-
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
 /* our own querier */
-struct bridge_mcast_query {
+struct bridge_mcast_own_query {
 	struct timer_list	timer;
 	u32			startup_sent;
 };
 
 /* other querier */
-struct bridge_mcast_querier {
+struct bridge_mcast_other_query {
 	struct timer_list		timer;
 	unsigned long			delay_time;
 };
+
+/* selected querier */
+struct bridge_mcast_querier {
+	struct br_ip addr;
+	struct net_bridge_port __rcu	*port;
+};
 #endif
 
 struct net_port_vlans {
@@ -174,11 +170,13 @@ struct net_bridge_port
 #define BR_ADMIN_COST		0x00000010
 #define BR_LEARNING		0x00000020
 #define BR_FLOOD		0x00000040
+#define BR_AUTO_MASK (BR_FLOOD | BR_LEARNING)
+#define BR_PROMISC		0x00000080
 
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
-	struct bridge_mcast_query	ip4_query;
+	struct bridge_mcast_own_query	ip4_own_query;
 #if IS_ENABLED(CONFIG_IPV6)
-	struct bridge_mcast_query	ip6_query;
+	struct bridge_mcast_own_query	ip6_own_query;
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 	unsigned char			multicast_router;
 	struct timer_list		multicast_router_timer;
@@ -198,6 +196,9 @@ struct net_bridge_port
 #endif
 };
 
+#define br_auto_port(p) ((p)->flags & BR_AUTO_MASK)
+#define br_promisc_port(p) ((p)->flags & BR_PROMISC)
+
 #define br_port_exists(dev) (dev->priv_flags & IFF_BRIDGE_PORT)
 
 static inline struct net_bridge_port *br_port_get_rcu(const struct net_device *dev)
@@ -227,6 +228,7 @@ struct net_bridge
 	bool				nf_call_arptables;
 #endif
 	u16				group_fwd_mask;
+	u16				group_fwd_mask_required;
 
 	/* STP */
 	bridge_id			designated_root;
@@ -241,6 +243,7 @@ struct net_bridge
 	unsigned long			bridge_forward_delay;
 
 	u8				group_addr[ETH_ALEN];
+	bool				group_addr_set;
 	u16				root_port;
 
 	enum {
@@ -277,11 +280,13 @@ struct net_bridge
 	struct hlist_head		router_list;
 
 	struct timer_list		multicast_router_timer;
+	struct bridge_mcast_other_query	ip4_other_query;
+	struct bridge_mcast_own_query	ip4_own_query;
 	struct bridge_mcast_querier	ip4_querier;
-	struct bridge_mcast_query	ip4_query;
 #if IS_ENABLED(CONFIG_IPV6)
+	struct bridge_mcast_other_query	ip6_other_query;
+	struct bridge_mcast_own_query	ip6_own_query;
 	struct bridge_mcast_querier	ip6_querier;
-	struct bridge_mcast_query	ip6_query;
 #endif /* IS_ENABLED(CONFIG_IPV6) */
 #endif
 
@@ -290,8 +295,10 @@ struct net_bridge
 	struct timer_list		topology_change_timer;
 	struct timer_list		gc_timer;
 	struct kobject			*ifobj;
+	u32				auto_cnt;
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
 	u8				vlan_enabled;
+	__be16				vlan_proto;
 	struct net_port_vlans __rcu	*vlan_info;
 #endif
 };
@@ -327,8 +334,6 @@ struct br_input_skb_cb {
 #define br_debug(br, format, args...)			\
 	pr_debug("%s: " format,  (br)->dev->name, ##args)
 
-extern struct notifier_block br_device_notifier;
-
 /* called under bridge lock */
 static inline int br_is_root_bridge(const struct net_bridge *br)
 {
@@ -395,6 +400,8 @@ int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev,
 	       const unsigned char *addr, u16 nlh_flags);
 int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		struct net_device *dev, int idx);
+int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p);
+void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p);
 
 /* br_forward.c */
 void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb);
@@ -415,6 +422,8 @@ int br_del_if(struct net_bridge *br, struct net_device *dev);
 int br_min_mtu(const struct net_bridge *br);
 netdev_features_t br_features_recompute(struct net_bridge *br,
 					netdev_features_t features);
+void br_port_flags_change(struct net_bridge_port *port, unsigned long mask);
+void br_manage_promisc(struct net_bridge *br);
 
 /* br_input.c */
 int br_handle_frame_finish(struct sk_buff *skb);
@@ -485,7 +494,7 @@ static inline bool br_multicast_is_router(struct net_bridge *br)
 
 static inline bool
 __br_multicast_querier_exists(struct net_bridge *br,
-			      struct bridge_mcast_querier *querier)
+			      struct bridge_mcast_other_query *querier)
 {
 	return time_is_before_jiffies(querier->delay_time) &&
 	       (br->multicast_querier || timer_pending(&querier->timer));
@@ -496,10 +505,10 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 {
 	switch (eth->h_proto) {
 	case (htons(ETH_P_IP)):
-		return __br_multicast_querier_exists(br, &br->ip4_querier);
+		return __br_multicast_querier_exists(br, &br->ip4_other_query);
 #if IS_ENABLED(CONFIG_IPV6)
 	case (htons(ETH_P_IPV6)):
-		return __br_multicast_querier_exists(br, &br->ip6_querier);
+		return __br_multicast_querier_exists(br, &br->ip6_other_query);
 #endif
 	default:
 		return false;
@@ -589,7 +598,10 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags);
 int br_vlan_delete(struct net_bridge *br, u16 vid);
 void br_vlan_flush(struct net_bridge *br);
 bool br_vlan_find(struct net_bridge *br, u16 vid);
+void br_recalculate_fwd_mask(struct net_bridge *br);
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val);
+int br_vlan_set_proto(struct net_bridge *br, unsigned long val);
+void br_vlan_init(struct net_bridge *br);
 int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags);
 int nbp_vlan_delete(struct net_bridge_port *port, u16 vid);
 void nbp_vlan_flush(struct net_bridge_port *port);
@@ -633,6 +645,10 @@ static inline u16 br_get_pvid(const struct net_port_vlans *v)
 	return v->pvid ?: VLAN_N_VID;
 }
 
+static inline int br_vlan_enabled(struct net_bridge *br)
+{
+	return br->vlan_enabled;
+}
 #else
 static inline bool br_allowed_ingress(struct net_bridge *br,
 				      struct net_port_vlans *v,
@@ -681,6 +697,14 @@ static inline bool br_vlan_find(struct net_bridge *br, u16 vid)
 	return false;
 }
 
+static inline void br_recalculate_fwd_mask(struct net_bridge *br)
+{
+}
+
+static inline void br_vlan_init(struct net_bridge *br)
+{
+}
+
 static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags)
 {
 	return -EOPNOTSUPP;
@@ -719,6 +743,11 @@ static inline u16 br_get_pvid(const struct net_port_vlans *v)
 {
 	return VLAN_N_VID;	/* Returns invalid vid */
 }
+
+static inline int br_vlan_enabled(struct net_bridge *br)
+{
+	return 0;
+}
 #endif
 
 /* br_netfilter.c */
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 8dac65552f1..c9e2572b15f 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -312,10 +312,19 @@ static ssize_t group_addr_store(struct device *d,
 	    new_addr[5] == 3)		/* 802.1X PAE address */
 		return -EINVAL;
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
 	spin_lock_bh(&br->lock);
 	for (i = 0; i < 6; i++)
 		br->group_addr[i] = new_addr[i];
 	spin_unlock_bh(&br->lock);
+
+	br->group_addr_set = true;
+	br_recalculate_fwd_mask(br);
+
+	rtnl_unlock();
+
 	return len;
 }
 
@@ -700,6 +709,22 @@ static ssize_t vlan_filtering_store(struct device *d,
 	return store_bridge_parm(d, buf, len, br_vlan_filter_toggle);
 }
 static DEVICE_ATTR_RW(vlan_filtering);
+
+static ssize_t vlan_protocol_show(struct device *d,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	struct net_bridge *br = to_bridge(d);
+	return sprintf(buf, "%#06x\n", ntohs(br->vlan_proto));
+}
+
+static ssize_t vlan_protocol_store(struct device *d,
+				   struct device_attribute *attr,
+				   const char *buf, size_t len)
+{
+	return store_bridge_parm(d, buf, len, br_vlan_set_proto);
+}
+static DEVICE_ATTR_RW(vlan_protocol);
 #endif
 
 static struct attribute *bridge_attrs[] = {
@@ -745,6 +770,7 @@ static struct attribute *bridge_attrs[] = {
 #endif
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
 	&dev_attr_vlan_filtering.attr,
+	&dev_attr_vlan_protocol.attr,
 #endif
 	NULL
 };
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index dd595bd7fa8..e561cd59b8a 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -41,20 +41,30 @@ static ssize_t show_##_name(struct net_bridge_port *p, char *buf) \
 }								\
 static int store_##_name(struct net_bridge_port *p, unsigned long v) \
 {								\
-	unsigned long flags = p->flags;				\
-	if (v)							\
-		flags |= _mask;					\
-	else							\
-		flags &= ~_mask;				\
-	if (flags != p->flags) {				\
-		p->flags = flags;				\
-		br_ifinfo_notify(RTM_NEWLINK, p);		\
-	}							\
-	return 0;						\
+	return store_flag(p, v, _mask);				\
 }								\
 static BRPORT_ATTR(_name, S_IRUGO | S_IWUSR,			\
 		   show_##_name, store_##_name)
 
+static int store_flag(struct net_bridge_port *p, unsigned long v,
+		      unsigned long mask)
+{
+	unsigned long flags;
+
+	flags = p->flags;
+
+	if (v)
+		flags |= mask;
+	else
+		flags &= ~mask;
+
+	if (flags != p->flags) {
+		p->flags = flags;
+		br_port_flags_change(p, mask);
+		br_ifinfo_notify(RTM_NEWLINK, p);
+	}
+	return 0;
+}
 
 static ssize_t show_path_cost(struct net_bridge_port *p, char *buf)
 {
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 5fee2feaf29..2b2774fe070 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -60,7 +60,7 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags)
 		 * that ever changes this code will allow tagged
 		 * traffic to enter the bridge.
 		 */
-		err = vlan_vid_add(dev, htons(ETH_P_8021Q), vid);
+		err = vlan_vid_add(dev, br->vlan_proto, vid);
 		if (err)
 			return err;
 	}
@@ -80,7 +80,7 @@ static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags)
 
 out_filt:
 	if (p)
-		vlan_vid_del(dev, htons(ETH_P_8021Q), vid);
+		vlan_vid_del(dev, br->vlan_proto, vid);
 	return err;
 }
 
@@ -92,8 +92,10 @@ static int __vlan_del(struct net_port_vlans *v, u16 vid)
 	__vlan_delete_pvid(v, vid);
 	clear_bit(vid, v->untagged_bitmap);
 
-	if (v->port_idx)
-		vlan_vid_del(v->parent.port->dev, htons(ETH_P_8021Q), vid);
+	if (v->port_idx) {
+		struct net_bridge_port *p = v->parent.port;
+		vlan_vid_del(p->dev, p->br->vlan_proto, vid);
+	}
 
 	clear_bit(vid, v->vlan_bitmap);
 	v->num_vlans--;
@@ -158,7 +160,8 @@ out:
 bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 			struct sk_buff *skb, u16 *vid)
 {
-	int err;
+	bool tagged;
+	__be16 proto;
 
 	/* If VLAN filtering is disabled on the bridge, all packets are
 	 * permitted.
@@ -172,19 +175,41 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 	if (!v)
 		goto drop;
 
+	proto = br->vlan_proto;
+
 	/* If vlan tx offload is disabled on bridge device and frame was
 	 * sent from vlan device on the bridge device, it does not have
 	 * HW accelerated vlan tag.
 	 */
 	if (unlikely(!vlan_tx_tag_present(skb) &&
-		     (skb->protocol == htons(ETH_P_8021Q) ||
-		      skb->protocol == htons(ETH_P_8021AD)))) {
+		     skb->protocol == proto)) {
 		skb = vlan_untag(skb);
 		if (unlikely(!skb))
 			return false;
 	}
 
-	err = br_vlan_get_tag(skb, vid);
+	if (!br_vlan_get_tag(skb, vid)) {
+		/* Tagged frame */
+		if (skb->vlan_proto != proto) {
+			/* Protocol-mismatch, empty out vlan_tci for new tag */
+			skb_push(skb, ETH_HLEN);
+			skb = __vlan_put_tag(skb, skb->vlan_proto,
+					     vlan_tx_tag_get(skb));
+			if (unlikely(!skb))
+				return false;
+
+			skb_pull(skb, ETH_HLEN);
+			skb_reset_mac_len(skb);
+			*vid = 0;
+			tagged = false;
+		} else {
+			tagged = true;
+		}
+	} else {
+		/* Untagged frame */
+		tagged = false;
+	}
+
 	if (!*vid) {
 		u16 pvid = br_get_pvid(v);
 
@@ -199,9 +224,9 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v,
 		 * ingress frame is considered to belong to this vlan.
 		 */
 		*vid = pvid;
-		if (likely(err))
+		if (likely(!tagged))
 			/* Untagged Frame. */
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), pvid);
+			__vlan_hwaccel_put_tag(skb, proto, pvid);
 		else
 			/* Priority-tagged Frame.
 			 * At this point, We know that skb->vlan_tci had
@@ -254,7 +279,9 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid)
 	if (!v)
 		return false;
 
-	br_vlan_get_tag(skb, vid);
+	if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto)
+		*vid = 0;
+
 	if (!*vid) {
 		*vid = br_get_pvid(v);
 		if (*vid == VLAN_N_VID)
@@ -351,6 +378,33 @@ out:
 	return found;
 }
 
+/* Must be protected by RTNL. */
+static void recalculate_group_addr(struct net_bridge *br)
+{
+	if (br->group_addr_set)
+		return;
+
+	spin_lock_bh(&br->lock);
+	if (!br->vlan_enabled || br->vlan_proto == htons(ETH_P_8021Q)) {
+		/* Bridge Group Address */
+		br->group_addr[5] = 0x00;
+	} else { /* vlan_enabled && ETH_P_8021AD */
+		/* Provider Bridge Group Address */
+		br->group_addr[5] = 0x08;
+	}
+	spin_unlock_bh(&br->lock);
+}
+
+/* Must be protected by RTNL. */
+void br_recalculate_fwd_mask(struct net_bridge *br)
+{
+	if (!br->vlan_enabled || br->vlan_proto == htons(ETH_P_8021Q))
+		br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;
+	else /* vlan_enabled && ETH_P_8021AD */
+		br->group_fwd_mask_required = BR_GROUPFWD_8021AD &
+					      ~(1u << br->group_addr[5]);
+}
+
 int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val)
 {
 	if (!rtnl_trylock())
@@ -360,12 +414,88 @@ int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val)
 		goto unlock;
 
 	br->vlan_enabled = val;
+	br_manage_promisc(br);
+	recalculate_group_addr(br);
+	br_recalculate_fwd_mask(br);
 
 unlock:
 	rtnl_unlock();
 	return 0;
 }
 
+int br_vlan_set_proto(struct net_bridge *br, unsigned long val)
+{
+	int err = 0;
+	struct net_bridge_port *p;
+	struct net_port_vlans *pv;
+	__be16 proto, oldproto;
+	u16 vid, errvid;
+
+	if (val != ETH_P_8021Q && val != ETH_P_8021AD)
+		return -EPROTONOSUPPORT;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	proto = htons(val);
+	if (br->vlan_proto == proto)
+		goto unlock;
+
+	/* Add VLANs for the new proto to the device filter. */
+	list_for_each_entry(p, &br->port_list, list) {
+		pv = rtnl_dereference(p->vlan_info);
+		if (!pv)
+			continue;
+
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) {
+			err = vlan_vid_add(p->dev, proto, vid);
+			if (err)
+				goto err_filt;
+		}
+	}
+
+	oldproto = br->vlan_proto;
+	br->vlan_proto = proto;
+
+	recalculate_group_addr(br);
+	br_recalculate_fwd_mask(br);
+
+	/* Delete VLANs for the old proto from the device filter. */
+	list_for_each_entry(p, &br->port_list, list) {
+		pv = rtnl_dereference(p->vlan_info);
+		if (!pv)
+			continue;
+
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
+			vlan_vid_del(p->dev, oldproto, vid);
+	}
+
+unlock:
+	rtnl_unlock();
+	return err;
+
+err_filt:
+	errvid = vid;
+	for_each_set_bit(vid, pv->vlan_bitmap, errvid)
+		vlan_vid_del(p->dev, proto, vid);
+
+	list_for_each_entry_continue_reverse(p, &br->port_list, list) {
+		pv = rtnl_dereference(p->vlan_info);
+		if (!pv)
+			continue;
+
+		for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
+			vlan_vid_del(p->dev, proto, vid);
+	}
+
+	goto unlock;
+}
+
+void br_vlan_init(struct net_bridge *br)
+{
+	br->vlan_proto = htons(ETH_P_8021Q);
+}
+
 /* Must be protected by RTNL.
  * Must be called with vid in range from 1 to 4094 inclusive.
  */
@@ -432,7 +562,7 @@ void nbp_vlan_flush(struct net_bridge_port *port)
 		return;
 
 	for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID)
-		vlan_vid_del(port->dev, htons(ETH_P_8021Q), vid);
+		vlan_vid_del(port->dev, port->br->vlan_proto, vid);
 
 	__vlan_flush(pv);
 }
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index 5ca74a0e595..629dc77874a 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -2,14 +2,23 @@
 # Bridge netfilter configuration
 #
 #
-config NF_TABLES_BRIDGE
-	depends on NF_TABLES
+menuconfig NF_TABLES_BRIDGE
+	depends on BRIDGE && NETFILTER && NF_TABLES
 	tristate "Ethernet Bridge nf_tables support"
 
+if NF_TABLES_BRIDGE
+
+config NFT_BRIDGE_META
+	tristate "Netfilter nf_table bridge meta support"
+	depends on NFT_META
+	help
+	  Add support for bridge dedicated meta key.
+
+endif # NF_TABLES_BRIDGE
+
 menuconfig BRIDGE_NF_EBTABLES
 	tristate "Ethernet Bridge tables (ebtables) support"
-	depends on BRIDGE && NETFILTER
-	select NETFILTER_XTABLES
+	depends on BRIDGE && NETFILTER && NETFILTER_XTABLES
 	help
 	  ebtables is a general, extensible frame/packet identification
 	  framework. Say 'Y' or 'M' here if you want to do Ethernet
diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile
index ea7629f58b3..6f2f3943d66 100644
--- a/net/bridge/netfilter/Makefile
+++ b/net/bridge/netfilter/Makefile
@@ -3,6 +3,7 @@
 #
 
 obj-$(CONFIG_NF_TABLES_BRIDGE) += nf_tables_bridge.o
+obj-$(CONFIG_NFT_BRIDGE_META)  += nft_meta_bridge.o
 
 obj-$(CONFIG_BRIDGE_NF_EBTABLES) += ebtables.o
 
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
new file mode 100644
index 00000000000..4f02109d708
--- /dev/null
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -0,0 +1,139 @@
+/*
+ * Copyright (c) 2014 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_meta.h>
+
+#include "../br_private.h"
+
+static void nft_meta_bridge_get_eval(const struct nft_expr *expr,
+				     struct nft_data data[NFT_REG_MAX + 1],
+				     const struct nft_pktinfo *pkt)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+	const struct net_device *in = pkt->in, *out = pkt->out;
+	struct nft_data *dest = &data[priv->dreg];
+	const struct net_bridge_port *p;
+
+	switch (priv->key) {
+	case NFT_META_BRI_IIFNAME:
+		if (in == NULL || (p = br_port_get_rcu(in)) == NULL)
+			goto err;
+		break;
+	case NFT_META_BRI_OIFNAME:
+		if (out == NULL || (p = br_port_get_rcu(out)) == NULL)
+			goto err;
+		break;
+	default:
+		goto out;
+	}
+
+	strncpy((char *)dest->data, p->br->dev->name, sizeof(dest->data));
+	return;
+out:
+	return nft_meta_get_eval(expr, data, pkt);
+err:
+	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
+}
+
+static int nft_meta_bridge_get_init(const struct nft_ctx *ctx,
+				    const struct nft_expr *expr,
+				    const struct nlattr * const tb[])
+{
+	struct nft_meta *priv = nft_expr_priv(expr);
+	int err;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+	switch (priv->key) {
+	case NFT_META_BRI_IIFNAME:
+	case NFT_META_BRI_OIFNAME:
+		break;
+	default:
+		return nft_meta_get_init(ctx, expr, tb);
+	}
+
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+
+	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static struct nft_expr_type nft_meta_bridge_type;
+static const struct nft_expr_ops nft_meta_bridge_get_ops = {
+	.type		= &nft_meta_bridge_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.eval		= nft_meta_bridge_get_eval,
+	.init		= nft_meta_bridge_get_init,
+	.dump		= nft_meta_get_dump,
+};
+
+static const struct nft_expr_ops nft_meta_bridge_set_ops = {
+	.type		= &nft_meta_bridge_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
+	.eval		= nft_meta_set_eval,
+	.init		= nft_meta_set_init,
+	.dump		= nft_meta_set_dump,
+};
+
+static const struct nft_expr_ops *
+nft_meta_bridge_select_ops(const struct nft_ctx *ctx,
+			   const struct nlattr * const tb[])
+{
+	if (tb[NFTA_META_KEY] == NULL)
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG])
+		return ERR_PTR(-EINVAL);
+
+	if (tb[NFTA_META_DREG])
+		return &nft_meta_bridge_get_ops;
+
+	if (tb[NFTA_META_SREG])
+		return &nft_meta_bridge_set_ops;
+
+	return ERR_PTR(-EINVAL);
+}
+
+static struct nft_expr_type nft_meta_bridge_type __read_mostly = {
+	.family         = NFPROTO_BRIDGE,
+	.name           = "meta",
+	.select_ops     = &nft_meta_bridge_select_ops,
+	.policy         = nft_meta_policy,
+	.maxattr        = NFTA_META_MAX,
+	.owner          = THIS_MODULE,
+};
+
+static int __init nft_meta_bridge_module_init(void)
+{
+	return nft_register_expr(&nft_meta_bridge_type);
+}
+
+static void __exit nft_meta_bridge_module_exit(void)
+{
+	nft_unregister_expr(&nft_meta_bridge_type);
+}
+
+module_init(nft_meta_bridge_module_init);
+module_exit(nft_meta_bridge_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta");
diff --git a/net/can/af_can.c b/net/can/af_can.c
index a27f8aad9e9..ce82337521f 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -338,6 +338,29 @@ static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev)
 }
 
 /**
+ * effhash - hash function for 29 bit CAN identifier reduction
+ * @can_id: 29 bit CAN identifier
+ *
+ * Description:
+ *  To reduce the linear traversal in one linked list of _single_ EFF CAN
+ *  frame subscriptions the 29 bit identifier is mapped to 10 bits.
+ *  (see CAN_EFF_RCV_HASH_BITS definition)
+ *
+ * Return:
+ *  Hash value from 0x000 - 0x3FF ( enforced by CAN_EFF_RCV_HASH_BITS mask )
+ */
+static unsigned int effhash(canid_t can_id)
+{
+	unsigned int hash;
+
+	hash = can_id;
+	hash ^= can_id >> CAN_EFF_RCV_HASH_BITS;
+	hash ^= can_id >> (2 * CAN_EFF_RCV_HASH_BITS);
+
+	return hash & ((1 << CAN_EFF_RCV_HASH_BITS) - 1);
+}
+
+/**
  * find_rcv_list - determine optimal filterlist inside device filter struct
  * @can_id: pointer to CAN identifier of a given can_filter
  * @mask: pointer to CAN mask of a given can_filter
@@ -400,10 +423,8 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
 	    !(*can_id & CAN_RTR_FLAG)) {
 
 		if (*can_id & CAN_EFF_FLAG) {
-			if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS)) {
-				/* RFC: a future use-case for hash-tables? */
-				return &d->rx[RX_EFF];
-			}
+			if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS))
+				return &d->rx_eff[effhash(*can_id)];
 		} else {
 			if (*mask == (CAN_SFF_MASK | CAN_EFF_RTR_FLAGS))
 				return &d->rx_sff[*can_id];
@@ -632,7 +653,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb)
 		return matches;
 
 	if (can_id & CAN_EFF_FLAG) {
-		hlist_for_each_entry_rcu(r, &d->rx[RX_EFF], list) {
+		hlist_for_each_entry_rcu(r, &d->rx_eff[effhash(can_id)], list) {
 			if (r->can_id == can_id) {
 				deliver(skb, r);
 				matches++;
diff --git a/net/can/af_can.h b/net/can/af_can.h
index 6de58b40535..fca0fe9fc45 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -59,12 +59,17 @@ struct receiver {
 	char *ident;
 };
 
-enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_EFF, RX_MAX };
+#define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS)
+#define CAN_EFF_RCV_HASH_BITS 10
+#define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS)
+
+enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX };
 
 /* per device receive filters linked at dev->ml_priv */
 struct dev_rcv_lists {
 	struct hlist_head rx[RX_MAX];
-	struct hlist_head rx_sff[0x800];
+	struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ];
+	struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ];
 	int remove_on_zero_entries;
 	int entries;
 };
diff --git a/net/can/proc.c b/net/can/proc.c
index b543470c8f8..1a19b985a86 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -80,7 +80,6 @@ static const char rx_list_name[][8] = {
 	[RX_ALL] = "rx_all",
 	[RX_FIL] = "rx_fil",
 	[RX_INV] = "rx_inv",
-	[RX_EFF] = "rx_eff",
 };
 
 /*
@@ -389,25 +388,26 @@ static const struct file_operations can_rcvlist_proc_fops = {
 	.release	= single_release,
 };
 
-static inline void can_rcvlist_sff_proc_show_one(struct seq_file *m,
-						 struct net_device *dev,
-						 struct dev_rcv_lists *d)
+static inline void can_rcvlist_proc_show_array(struct seq_file *m,
+					       struct net_device *dev,
+					       struct hlist_head *rcv_array,
+					       unsigned int rcv_array_sz)
 {
-	int i;
+	unsigned int i;
 	int all_empty = 1;
 
 	/* check whether at least one list is non-empty */
-	for (i = 0; i < 0x800; i++)
-		if (!hlist_empty(&d->rx_sff[i])) {
+	for (i = 0; i < rcv_array_sz; i++)
+		if (!hlist_empty(&rcv_array[i])) {
 			all_empty = 0;
 			break;
 		}
 
 	if (!all_empty) {
 		can_print_recv_banner(m);
-		for (i = 0; i < 0x800; i++) {
-			if (!hlist_empty(&d->rx_sff[i]))
-				can_print_rcvlist(m, &d->rx_sff[i], dev);
+		for (i = 0; i < rcv_array_sz; i++) {
+			if (!hlist_empty(&rcv_array[i]))
+				can_print_rcvlist(m, &rcv_array[i], dev);
 		}
 	} else
 		seq_printf(m, "  (%s: no entry)\n", DNAME(dev));
@@ -425,12 +425,15 @@ static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v)
 
 	/* sff receive list for 'all' CAN devices (dev == NULL) */
 	d = &can_rx_alldev_list;
-	can_rcvlist_sff_proc_show_one(m, NULL, d);
+	can_rcvlist_proc_show_array(m, NULL, d->rx_sff, ARRAY_SIZE(d->rx_sff));
 
 	/* sff receive list for registered CAN devices */
 	for_each_netdev_rcu(&init_net, dev) {
-		if (dev->type == ARPHRD_CAN && dev->ml_priv)
-			can_rcvlist_sff_proc_show_one(m, dev, dev->ml_priv);
+		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
+			d = dev->ml_priv;
+			can_rcvlist_proc_show_array(m, dev, d->rx_sff,
+						    ARRAY_SIZE(d->rx_sff));
+		}
 	}
 
 	rcu_read_unlock();
@@ -452,6 +455,49 @@ static const struct file_operations can_rcvlist_sff_proc_fops = {
 	.release	= single_release,
 };
 
+
+static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v)
+{
+	struct net_device *dev;
+	struct dev_rcv_lists *d;
+
+	/* RX_EFF */
+	seq_puts(m, "\nreceive list 'rx_eff':\n");
+
+	rcu_read_lock();
+
+	/* eff receive list for 'all' CAN devices (dev == NULL) */
+	d = &can_rx_alldev_list;
+	can_rcvlist_proc_show_array(m, NULL, d->rx_eff, ARRAY_SIZE(d->rx_eff));
+
+	/* eff receive list for registered CAN devices */
+	for_each_netdev_rcu(&init_net, dev) {
+		if (dev->type == ARPHRD_CAN && dev->ml_priv) {
+			d = dev->ml_priv;
+			can_rcvlist_proc_show_array(m, dev, d->rx_eff,
+						    ARRAY_SIZE(d->rx_eff));
+		}
+	}
+
+	rcu_read_unlock();
+
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static int can_rcvlist_eff_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, can_rcvlist_eff_proc_show, NULL);
+}
+
+static const struct file_operations can_rcvlist_eff_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= can_rcvlist_eff_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 /*
  * proc utility functions
  */
@@ -491,8 +537,8 @@ void can_init_proc(void)
 					   &can_rcvlist_proc_fops, (void *)RX_FIL);
 	pde_rcvlist_inv = proc_create_data(CAN_PROC_RCVLIST_INV, 0644, can_dir,
 					   &can_rcvlist_proc_fops, (void *)RX_INV);
-	pde_rcvlist_eff = proc_create_data(CAN_PROC_RCVLIST_EFF, 0644, can_dir,
-					   &can_rcvlist_proc_fops, (void *)RX_EFF);
+	pde_rcvlist_eff = proc_create(CAN_PROC_RCVLIST_EFF, 0644, can_dir,
+				      &can_rcvlist_eff_proc_fops);
 	pde_rcvlist_sff = proc_create(CAN_PROC_RCVLIST_SFF, 0644, can_dir,
 				      &can_rcvlist_sff_proc_fops);
 }
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 67d7721d237..1675021d8c1 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -72,6 +72,8 @@ const char *ceph_msg_type_name(int type)
 	case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
 	case CEPH_MSG_STATFS: return "statfs";
 	case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
+	case CEPH_MSG_MON_GET_VERSION: return "mon_get_version";
+	case CEPH_MSG_MON_GET_VERSION_REPLY: return "mon_get_version_reply";
 	case CEPH_MSG_MDS_MAP: return "mds_map";
 	case CEPH_MSG_CLIENT_SESSION: return "client_session";
 	case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 10421a4b76f..d1a62c69a9f 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -126,9 +126,13 @@ static int monc_show(struct seq_file *s, void *p)
 		req = rb_entry(rp, struct ceph_mon_generic_request, node);
 		op = le16_to_cpu(req->request->hdr.type);
 		if (op == CEPH_MSG_STATFS)
-			seq_printf(s, "%lld statfs\n", req->tid);
+			seq_printf(s, "%llu statfs\n", req->tid);
+		else if (op == CEPH_MSG_POOLOP)
+			seq_printf(s, "%llu poolop\n", req->tid);
+		else if (op == CEPH_MSG_MON_GET_VERSION)
+			seq_printf(s, "%llu mon_get_version", req->tid);
 		else
-			seq_printf(s, "%lld unknown\n", req->tid);
+			seq_printf(s, "%llu unknown\n", req->tid);
 	}
 
 	mutex_unlock(&monc->mutex);
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 2ac9ef35110..067d3af2eaf 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -296,6 +296,33 @@ void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc)
 		__send_subscribe(monc);
 	mutex_unlock(&monc->mutex);
 }
+EXPORT_SYMBOL(ceph_monc_request_next_osdmap);
+
+int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
+			  unsigned long timeout)
+{
+	unsigned long started = jiffies;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	while (monc->have_osdmap < epoch) {
+		mutex_unlock(&monc->mutex);
+
+		if (timeout != 0 && time_after_eq(jiffies, started + timeout))
+			return -ETIMEDOUT;
+
+		ret = wait_event_interruptible_timeout(monc->client->auth_wq,
+					 monc->have_osdmap >= epoch, timeout);
+		if (ret < 0)
+			return ret;
+
+		mutex_lock(&monc->mutex);
+	}
+
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+EXPORT_SYMBOL(ceph_monc_wait_osdmap);
 
 /*
  *
@@ -477,14 +504,13 @@ static struct ceph_msg *get_generic_reply(struct ceph_connection *con,
 	return m;
 }
 
-static int do_generic_request(struct ceph_mon_client *monc,
-			      struct ceph_mon_generic_request *req)
+static int __do_generic_request(struct ceph_mon_client *monc, u64 tid,
+				struct ceph_mon_generic_request *req)
 {
 	int err;
 
 	/* register request */
-	mutex_lock(&monc->mutex);
-	req->tid = ++monc->last_tid;
+	req->tid = tid != 0 ? tid : ++monc->last_tid;
 	req->request->hdr.tid = cpu_to_le64(req->tid);
 	__insert_generic_request(monc, req);
 	monc->num_generic_requests++;
@@ -496,13 +522,24 @@ static int do_generic_request(struct ceph_mon_client *monc,
 	mutex_lock(&monc->mutex);
 	rb_erase(&req->node, &monc->generic_request_tree);
 	monc->num_generic_requests--;
-	mutex_unlock(&monc->mutex);
 
 	if (!err)
 		err = req->result;
 	return err;
 }
 
+static int do_generic_request(struct ceph_mon_client *monc,
+			      struct ceph_mon_generic_request *req)
+{
+	int err;
+
+	mutex_lock(&monc->mutex);
+	err = __do_generic_request(monc, 0, req);
+	mutex_unlock(&monc->mutex);
+
+	return err;
+}
+
 /*
  * statfs
  */
@@ -579,6 +616,96 @@ out:
 }
 EXPORT_SYMBOL(ceph_monc_do_statfs);
 
+static void handle_get_version_reply(struct ceph_mon_client *monc,
+				     struct ceph_msg *msg)
+{
+	struct ceph_mon_generic_request *req;
+	u64 tid = le64_to_cpu(msg->hdr.tid);
+	void *p = msg->front.iov_base;
+	void *end = p + msg->front_alloc_len;
+	u64 handle;
+
+	dout("%s %p tid %llu\n", __func__, msg, tid);
+
+	ceph_decode_need(&p, end, 2*sizeof(u64), bad);
+	handle = ceph_decode_64(&p);
+	if (tid != 0 && tid != handle)
+		goto bad;
+
+	mutex_lock(&monc->mutex);
+	req = __lookup_generic_req(monc, handle);
+	if (req) {
+		*(u64 *)req->buf = ceph_decode_64(&p);
+		req->result = 0;
+		get_generic_request(req);
+	}
+	mutex_unlock(&monc->mutex);
+	if (req) {
+		complete_all(&req->completion);
+		put_generic_request(req);
+	}
+
+	return;
+bad:
+	pr_err("corrupt mon_get_version reply\n");
+	ceph_msg_dump(msg);
+}
+
+/*
+ * Send MMonGetVersion and wait for the reply.
+ *
+ * @what: one of "mdsmap", "osdmap" or "monmap"
+ */
+int ceph_monc_do_get_version(struct ceph_mon_client *monc, const char *what,
+			     u64 *newest)
+{
+	struct ceph_mon_generic_request *req;
+	void *p, *end;
+	u64 tid;
+	int err;
+
+	req = kzalloc(sizeof(*req), GFP_NOFS);
+	if (!req)
+		return -ENOMEM;
+
+	kref_init(&req->kref);
+	req->buf = newest;
+	req->buf_len = sizeof(*newest);
+	init_completion(&req->completion);
+
+	req->request = ceph_msg_new(CEPH_MSG_MON_GET_VERSION,
+				    sizeof(u64) + sizeof(u32) + strlen(what),
+				    GFP_NOFS, true);
+	if (!req->request) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	req->reply = ceph_msg_new(CEPH_MSG_MON_GET_VERSION_REPLY, 1024,
+				  GFP_NOFS, true);
+	if (!req->reply) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	p = req->request->front.iov_base;
+	end = p + req->request->front_alloc_len;
+
+	/* fill out request */
+	mutex_lock(&monc->mutex);
+	tid = ++monc->last_tid;
+	ceph_encode_64(&p, tid); /* handle */
+	ceph_encode_string(&p, end, what, strlen(what));
+
+	err = __do_generic_request(monc, tid, req);
+
+	mutex_unlock(&monc->mutex);
+out:
+	kref_put(&req->kref, release_generic_request);
+	return err;
+}
+EXPORT_SYMBOL(ceph_monc_do_get_version);
+
 /*
  * pool ops
  */
@@ -981,6 +1108,10 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 		handle_statfs_reply(monc, msg);
 		break;
 
+	case CEPH_MSG_MON_GET_VERSION_REPLY:
+		handle_get_version_reply(monc, msg);
+		break;
+
 	case CEPH_MSG_POOLOP_REPLY:
 		handle_poolop_reply(monc, msg);
 		break;
@@ -1029,6 +1160,15 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con,
 	case CEPH_MSG_AUTH_REPLY:
 		m = ceph_msg_get(monc->m_auth_reply);
 		break;
+	case CEPH_MSG_MON_GET_VERSION_REPLY:
+		if (le64_to_cpu(hdr->tid) != 0)
+			return get_generic_reply(con, hdr, skip);
+
+		/*
+		 * Older OSDs don't set reply tid even if the orignal
+		 * request had a non-zero tid.  Workaround this weirdness
+		 * by falling through to the allocate case.
+		 */
 	case CEPH_MSG_MON_MAP:
 	case CEPH_MSG_MDS_MAP:
 	case CEPH_MSG_OSD_MAP:
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index b0dfce77656..05be0c18169 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -2491,7 +2491,7 @@ EXPORT_SYMBOL(ceph_osdc_sync);
  * Call all pending notify callbacks - for use after a watch is
  * unregistered, to make sure no more callbacks for it will be invoked
  */
-extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
+void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc)
 {
 	flush_workqueue(osdc->notify_wq);
 }
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 815a2249cfa..555013034f7 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -53,7 +53,10 @@ void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty)
 			set_page_dirty_lock(pages[i]);
 		put_page(pages[i]);
 	}
-	kfree(pages);
+	if (is_vmalloc_addr(pages))
+		vfree(pages);
+	else
+		kfree(pages);
 }
 EXPORT_SYMBOL(ceph_put_page_vector);
 
@@ -165,36 +168,6 @@ void ceph_copy_from_page_vector(struct page **pages,
 EXPORT_SYMBOL(ceph_copy_from_page_vector);
 
 /*
- * copy user data from a page vector into a user pointer
- */
-int ceph_copy_page_vector_to_user(struct page **pages,
-					 void __user *data,
-					 loff_t off, size_t len)
-{
-	int i = 0;
-	int po = off & ~PAGE_CACHE_MASK;
-	int left = len;
-	int l, bad;
-
-	while (left > 0) {
-		l = min_t(int, left, PAGE_CACHE_SIZE-po);
-		bad = copy_to_user(data, page_address(pages[i]) + po, l);
-		if (bad == l)
-			return -EFAULT;
-		data += l - bad;
-		left -= l - bad;
-		if (po) {
-			po += l - bad;
-			if (po == PAGE_CACHE_SIZE)
-				po = 0;
-		}
-		i++;
-	}
-	return len;
-}
-EXPORT_SYMBOL(ceph_copy_page_vector_to_user);
-
-/*
  * Zero an extent within a page vector.  Offset is relative to the
  * start of the first page.
  */
diff --git a/net/compat.c b/net/compat.c
index 9a76eaf6318..bc8aeefddf3 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -85,7 +85,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 {
 	int tot_len;
 
-	if (kern_msg->msg_namelen) {
+	if (kern_msg->msg_name && kern_msg->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			int err = move_addr_to_kernel(kern_msg->msg_name,
 						      kern_msg->msg_namelen,
@@ -93,10 +93,11 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
 			if (err < 0)
 				return err;
 		}
-		if (kern_msg->msg_name)
-			kern_msg->msg_name = kern_address;
-	} else
+		kern_msg->msg_name = kern_address;
+	} else {
 		kern_msg->msg_name = NULL;
+		kern_msg->msg_namelen = 0;
+	}
 
 	tot_len = iov_from_user_compat_to_kern(kern_iov,
 					  (struct compat_iovec __user *)kern_msg->msg_iov,
diff --git a/net/core/Makefile b/net/core/Makefile
index 826b925aa45..71093d94ad2 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 
 obj-y		     += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
 			neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
-			sock_diag.o dev_ioctl.o
+			sock_diag.o dev_ioctl.o tso.o
 
 obj-$(CONFIG_XFRM) += flow.o
 obj-y += net-sysfs.o
diff --git a/net/core/datagram.c b/net/core/datagram.c
index a16ed7bbe37..488dd1a825c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -740,17 +740,37 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 
 	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
 	if (likely(!sum)) {
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
 			netdev_rx_csum_fault(skb->dev);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
+	skb->csum_valid = !sum;
 	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete_head);
 
 __sum16 __skb_checksum_complete(struct sk_buff *skb)
 {
-	return __skb_checksum_complete_head(skb, skb->len);
+	__wsum csum;
+	__sum16 sum;
+
+	csum = skb_checksum(skb, 0, skb->len, 0);
+
+	/* skb->csum holds pseudo checksum */
+	sum = csum_fold(csum_add(skb->csum, csum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+
+	/* Save full packet checksum */
+	skb->csum = csum;
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	skb->csum_complete_sw = 1;
+	skb->csum_valid = !sum;
+
+	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 8908a68db44..367a586d0c8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -148,6 +148,9 @@ struct list_head ptype_all __read_mostly;	/* Taps */
 static struct list_head offload_base __read_mostly;
 
 static int netif_rx_internal(struct sk_buff *skb);
+static int call_netdevice_notifiers_info(unsigned long val,
+					 struct net_device *dev,
+					 struct netdev_notifier_info *info);
 
 /*
  * The @dev_base_head list is protected by @dev_base_lock and the rtnl
@@ -1207,7 +1210,11 @@ EXPORT_SYMBOL(netdev_features_change);
 void netdev_state_change(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
-		call_netdevice_notifiers(NETDEV_CHANGE, dev);
+		struct netdev_notifier_change_info change_info;
+
+		change_info.flags_changed = 0;
+		call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+					      &change_info.info);
 		rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL);
 	}
 }
@@ -1661,6 +1668,29 @@ bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
+		if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
+			atomic_long_inc(&dev->rx_dropped);
+			kfree_skb(skb);
+			return NET_RX_DROP;
+		}
+	}
+
+	if (unlikely(!is_skb_forwardable(dev, skb))) {
+		atomic_long_inc(&dev->rx_dropped);
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+
+	skb_scrub_packet(skb, true);
+	skb->protocol = eth_type_trans(skb, dev);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__dev_forward_skb);
+
 /**
  * dev_forward_skb - loopback an skb to another netif
  *
@@ -1681,24 +1711,7 @@ EXPORT_SYMBOL_GPL(is_skb_forwardable);
  */
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
-		if (skb_copy_ubufs(skb, GFP_ATOMIC)) {
-			atomic_long_inc(&dev->rx_dropped);
-			kfree_skb(skb);
-			return NET_RX_DROP;
-		}
-	}
-
-	if (unlikely(!is_skb_forwardable(dev, skb))) {
-		atomic_long_inc(&dev->rx_dropped);
-		kfree_skb(skb);
-		return NET_RX_DROP;
-	}
-
-	skb_scrub_packet(skb, true);
-	skb->protocol = eth_type_trans(skb, dev);
-
-	return netif_rx_internal(skb);
+	return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
 
@@ -2507,13 +2520,39 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 	return 0;
 }
 
+/* If MPLS offload request, verify we are testing hardware MPLS features
+ * instead of standard features for the netdev.
+ */
+#ifdef CONFIG_NET_MPLS_GSO
+static netdev_features_t net_mpls_features(struct sk_buff *skb,
+					   netdev_features_t features,
+					   __be16 type)
+{
+	if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC))
+		features &= skb->dev->mpls_features;
+
+	return features;
+}
+#else
+static netdev_features_t net_mpls_features(struct sk_buff *skb,
+					   netdev_features_t features,
+					   __be16 type)
+{
+	return features;
+}
+#endif
+
 static netdev_features_t harmonize_features(struct sk_buff *skb,
 	netdev_features_t features)
 {
 	int tmp;
+	__be16 type;
+
+	type = skb_network_protocol(skb, &tmp);
+	features = net_mpls_features(skb, features, type);
 
 	if (skb->ip_summed != CHECKSUM_NONE &&
-	    !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
+	    !can_checksum_protocol(features, type)) {
 		features &= ~NETIF_F_ALL_CSUM;
 	} else if (illegal_highdma(skb->dev, skb)) {
 		features &= ~NETIF_F_SG;
@@ -4057,6 +4096,8 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+	skb->encapsulation = 0;
+	skb_shinfo(skb)->gso_type = 0;
 	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 
 	napi->skb = skb;
@@ -4195,9 +4236,8 @@ static int process_backlog(struct napi_struct *napi, int quota)
 #endif
 	napi->weight = weight_p;
 	local_irq_disable();
-	while (work < quota) {
+	while (1) {
 		struct sk_buff *skb;
-		unsigned int qlen;
 
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
 			local_irq_enable();
@@ -4211,24 +4251,24 @@ static int process_backlog(struct napi_struct *napi, int quota)
 		}
 
 		rps_lock(sd);
-		qlen = skb_queue_len(&sd->input_pkt_queue);
-		if (qlen)
-			skb_queue_splice_tail_init(&sd->input_pkt_queue,
-						   &sd->process_queue);
-
-		if (qlen < quota - work) {
+		if (skb_queue_empty(&sd->input_pkt_queue)) {
 			/*
 			 * Inline a custom version of __napi_complete().
 			 * only current cpu owns and manipulates this napi,
-			 * and NAPI_STATE_SCHED is the only possible flag set on backlog.
-			 * we can use a plain write instead of clear_bit(),
+			 * and NAPI_STATE_SCHED is the only possible flag set
+			 * on backlog.
+			 * We can use a plain write instead of clear_bit(),
 			 * and we dont need an smp_mb() memory barrier.
 			 */
 			list_del(&napi->poll_list);
 			napi->state = 0;
+			rps_unlock(sd);
 
-			quota = work + qlen;
+			break;
 		}
+
+		skb_queue_splice_tail_init(&sd->input_pkt_queue,
+					   &sd->process_queue);
 		rps_unlock(sd);
 	}
 	local_irq_enable();
@@ -5689,10 +5729,6 @@ static void rollback_registered_many(struct list_head *head)
 		*/
 		call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 
-		if (!dev->rtnl_link_ops ||
-		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
-			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
-
 		/*
 		 *	Flush the unicast and multicast chains
 		 */
@@ -5702,6 +5738,10 @@ static void rollback_registered_many(struct list_head *head)
 		if (dev->netdev_ops->ndo_uninit)
 			dev->netdev_ops->ndo_uninit(dev);
 
+		if (!dev->rtnl_link_ops ||
+		    dev->rtnl_link_state == RTNL_LINK_INITIALIZED)
+			rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL);
+
 		/* Notifier chain MUST detach us all upper devices. */
 		WARN_ON(netdev_has_any_upper_dev(dev));
 
@@ -5927,10 +5967,7 @@ static void netdev_init_one_queue(struct net_device *dev,
 
 static void netif_free_tx_queues(struct net_device *dev)
 {
-	if (is_vmalloc_addr(dev->_tx))
-		vfree(dev->_tx);
-	else
-		kfree(dev->_tx);
+	kvfree(dev->_tx);
 }
 
 static int netif_alloc_netdev_queues(struct net_device *dev)
@@ -6404,10 +6441,7 @@ void netdev_freemem(struct net_device *dev)
 {
 	char *addr = (char *)dev - dev->padded;
 
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
+	kvfree(addr);
 }
 
 /**
@@ -6512,11 +6546,6 @@ free_all:
 
 free_pcpu:
 	free_percpu(dev->pcpu_refcnt);
-	netif_free_tx_queues(dev);
-#ifdef CONFIG_SYSFS
-	kfree(dev->_rx);
-#endif
-
 free_dev:
 	netdev_freemem(dev);
 	return NULL;
@@ -6613,6 +6642,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue);
 /**
  *	unregister_netdevice_many - unregister many devices
  *	@head: list of devices
+ *
+ *  Note: As most callers use a stack allocated list_head,
+ *  we force a list_del() to make sure stack wont be corrupted later.
  */
 void unregister_netdevice_many(struct list_head *head)
 {
@@ -6622,6 +6654,7 @@ void unregister_netdevice_many(struct list_head *head)
 		rollback_registered_many(head);
 		list_for_each_entry(dev, head, unreg_list)
 			net_set_todo(dev);
+		list_del(head);
 	}
 }
 EXPORT_SYMBOL(unregister_netdevice_many);
@@ -7077,7 +7110,6 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
 		}
 	}
 	unregister_netdevice_many(&dev_kill_list);
-	list_del(&dev_kill_list);
 	rtnl_unlock();
 }
 
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 329d5794e7d..b6b230600b9 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -225,6 +225,91 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
 }
 EXPORT_SYMBOL(__hw_addr_unsync);
 
+/**
+ *  __hw_addr_sync_dev - Synchonize device's multicast list
+ *  @list: address list to syncronize
+ *  @dev:  device to sync
+ *  @sync: function to call if address should be added
+ *  @unsync: function to call if address should be removed
+ *
+ *  This funciton is intended to be called from the ndo_set_rx_mode
+ *  function of devices that require explicit address add/remove
+ *  notifications.  The unsync function may be NULL in which case
+ *  the addresses requiring removal will simply be removed without
+ *  any notification to the device.
+ **/
+int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
+		       struct net_device *dev,
+		       int (*sync)(struct net_device *, const unsigned char *),
+		       int (*unsync)(struct net_device *,
+				     const unsigned char *))
+{
+	struct netdev_hw_addr *ha, *tmp;
+	int err;
+
+	/* first go through and flush out any stale entries */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (!ha->sync_cnt || ha->refcount != 1)
+			continue;
+
+		/* if unsync is defined and fails defer unsyncing address */
+		if (unsync && unsync(dev, ha->addr))
+			continue;
+
+		ha->sync_cnt--;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+
+	/* go through and sync new entries to the list */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (ha->sync_cnt)
+			continue;
+
+		err = sync(dev, ha->addr);
+		if (err)
+			return err;
+
+		ha->sync_cnt++;
+		ha->refcount++;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(__hw_addr_sync_dev);
+
+/**
+ *  __hw_addr_unsync_dev - Remove synchonized addresses from device
+ *  @list: address list to remove syncronized addresses from
+ *  @dev:  device to sync
+ *  @unsync: function to call if address should be removed
+ *
+ *  Remove all addresses that were added to the device by __hw_addr_sync_dev().
+ *  This function is intended to be called from the ndo_stop or ndo_open
+ *  functions on devices that require explicit address add/remove
+ *  notifications.  If the unsync function pointer is NULL then this function
+ *  can be used to just reset the sync_cnt for the addresses in the list.
+ **/
+void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
+			  struct net_device *dev,
+			  int (*unsync)(struct net_device *,
+					const unsigned char *))
+{
+	struct netdev_hw_addr *ha, *tmp;
+
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (!ha->sync_cnt)
+			continue;
+
+		/* if unsync is defined and fails defer unsyncing address */
+		if (unsync && unsync(dev, ha->addr))
+			continue;
+
+		ha->sync_cnt--;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+}
+EXPORT_SYMBOL(__hw_addr_unsync_dev);
+
 static void __hw_addr_flush(struct netdev_hw_addr_list *list)
 {
 	struct netdev_hw_addr *ha, *tmp;
diff --git a/net/core/dst.c b/net/core/dst.c
index 80d6286c8b6..a028409ee43 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -269,6 +269,15 @@ again:
 }
 EXPORT_SYMBOL(dst_destroy);
 
+static void dst_destroy_rcu(struct rcu_head *head)
+{
+	struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
+
+	dst = dst_destroy(dst);
+	if (dst)
+		__dst_free(dst);
+}
+
 void dst_release(struct dst_entry *dst)
 {
 	if (dst) {
@@ -276,11 +285,8 @@ void dst_release(struct dst_entry *dst)
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
 		WARN_ON(newrefcnt < 0);
-		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) {
-			dst = dst_destroy(dst);
-			if (dst)
-				__dst_free(dst);
-		}
+		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
 }
 EXPORT_SYMBOL(dst_release);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 640ba0e5831..17cb912793f 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -557,6 +557,23 @@ err_out:
 	return ret;
 }
 
+static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr,
+					struct ethtool_rxnfc *rx_rings,
+					u32 size)
+{
+	int i;
+
+	if (copy_from_user(indir, useraddr, size * sizeof(indir[0])))
+		return -EFAULT;
+
+	/* Validate ring indices */
+	for (i = 0; i < size; i++)
+		if (indir[i] >= rx_rings->data)
+			return -EINVAL;
+
+	return 0;
+}
+
 static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
@@ -565,7 +582,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 	int ret;
 
 	if (!dev->ethtool_ops->get_rxfh_indir_size ||
-	    !dev->ethtool_ops->get_rxfh_indir)
+	    !dev->ethtool_ops->get_rxfh)
 		return -EOPNOTSUPP;
 	dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
 	if (dev_size == 0)
@@ -591,7 +608,7 @@ static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 	if (!indir)
 		return -ENOMEM;
 
-	ret = dev->ethtool_ops->get_rxfh_indir(dev, indir);
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL);
 	if (ret)
 		goto out;
 
@@ -613,8 +630,9 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 	u32 *indir;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	int ret;
+	u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]);
 
-	if (!ops->get_rxfh_indir_size || !ops->set_rxfh_indir ||
+	if (!ops->get_rxfh_indir_size || !ops->set_rxfh ||
 	    !ops->get_rxnfc)
 		return -EOPNOTSUPP;
 
@@ -643,28 +661,184 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 		for (i = 0; i < dev_size; i++)
 			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
 	} else {
-		if (copy_from_user(indir,
-				  useraddr +
-				  offsetof(struct ethtool_rxfh_indir,
-					   ring_index[0]),
-				  dev_size * sizeof(indir[0]))) {
+		ret = ethtool_copy_validate_indir(indir,
+						  useraddr + ringidx_offset,
+						  &rx_rings,
+						  dev_size);
+		if (ret)
+			goto out;
+	}
+
+	ret = ops->set_rxfh(dev, indir, NULL);
+
+out:
+	kfree(indir);
+	return ret;
+}
+
+static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
+					       void __user *useraddr)
+{
+	int ret;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	u32 user_indir_size, user_key_size;
+	u32 dev_indir_size = 0, dev_key_size = 0;
+	struct ethtool_rxfh rxfh;
+	u32 total_size;
+	u32 indir_bytes;
+	u32 *indir = NULL;
+	u8 *hkey = NULL;
+	u8 *rss_config;
+
+	if (!(dev->ethtool_ops->get_rxfh_indir_size ||
+	      dev->ethtool_ops->get_rxfh_key_size) ||
+	      !dev->ethtool_ops->get_rxfh)
+		return -EOPNOTSUPP;
+
+	if (ops->get_rxfh_indir_size)
+		dev_indir_size = ops->get_rxfh_indir_size(dev);
+	if (ops->get_rxfh_key_size)
+		dev_key_size = ops->get_rxfh_key_size(dev);
+
+	if ((dev_key_size + dev_indir_size) == 0)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
+		return -EFAULT;
+	user_indir_size = rxfh.indir_size;
+	user_key_size = rxfh.key_size;
+
+	/* Check that reserved fields are 0 for now */
+	if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+		return -EINVAL;
+
+	rxfh.indir_size = dev_indir_size;
+	rxfh.key_size = dev_key_size;
+	if (copy_to_user(useraddr, &rxfh, sizeof(rxfh)))
+		return -EFAULT;
+
+	/* If the user buffer size is 0, this is just a query for the
+	 * device table size and key size.  Otherwise, if the User size is
+	 * not equal to device table size or key size it's an error.
+	 */
+	if (!user_indir_size && !user_key_size)
+		return 0;
+
+	if ((user_indir_size && (user_indir_size != dev_indir_size)) ||
+	    (user_key_size && (user_key_size != dev_key_size)))
+		return -EINVAL;
+
+	indir_bytes = user_indir_size * sizeof(indir[0]);
+	total_size = indir_bytes + user_key_size;
+	rss_config = kzalloc(total_size, GFP_USER);
+	if (!rss_config)
+		return -ENOMEM;
+
+	if (user_indir_size)
+		indir = (u32 *)rss_config;
+
+	if (user_key_size)
+		hkey = rss_config + indir_bytes;
+
+	ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey);
+	if (!ret) {
+		if (copy_to_user(useraddr +
+				 offsetof(struct ethtool_rxfh, rss_config[0]),
+				 rss_config, total_size))
 			ret = -EFAULT;
+	}
+
+	kfree(rss_config);
+
+	return ret;
+}
+
+static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
+					       void __user *useraddr)
+{
+	int ret;
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxnfc rx_rings;
+	struct ethtool_rxfh rxfh;
+	u32 dev_indir_size = 0, dev_key_size = 0, i;
+	u32 *indir = NULL, indir_bytes = 0;
+	u8 *hkey = NULL;
+	u8 *rss_config;
+	u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
+
+	if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size) ||
+	    !ops->get_rxnfc || !ops->set_rxfh)
+		return -EOPNOTSUPP;
+
+	if (ops->get_rxfh_indir_size)
+		dev_indir_size = ops->get_rxfh_indir_size(dev);
+	if (ops->get_rxfh_key_size)
+		dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev);
+	if ((dev_key_size + dev_indir_size) == 0)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&rxfh, useraddr, sizeof(rxfh)))
+		return -EFAULT;
+
+	/* Check that reserved fields are 0 for now */
+	if (rxfh.rss_context || rxfh.rsvd[0] || rxfh.rsvd[1])
+		return -EINVAL;
+
+	/* If either indir or hash key is valid, proceed further.
+	 * It is not valid to request that both be unchanged.
+	 */
+	if ((rxfh.indir_size &&
+	     rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE &&
+	     rxfh.indir_size != dev_indir_size) ||
+	    (rxfh.key_size && (rxfh.key_size != dev_key_size)) ||
+	    (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE &&
+	     rxfh.key_size == 0))
+		return -EINVAL;
+
+	if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
+		indir_bytes = dev_indir_size * sizeof(indir[0]);
+
+	rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER);
+	if (!rss_config)
+		return -ENOMEM;
+
+	rx_rings.cmd = ETHTOOL_GRXRINGS;
+	ret = ops->get_rxnfc(dev, &rx_rings, NULL);
+	if (ret)
+		goto out;
+
+	/* rxfh.indir_size == 0 means reset the indir table to default.
+	 * rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE means leave it unchanged.
+	 */
+	if (rxfh.indir_size &&
+	    rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
+		indir = (u32 *)rss_config;
+		ret = ethtool_copy_validate_indir(indir,
+						  useraddr + rss_cfg_offset,
+						  &rx_rings,
+						  rxfh.indir_size);
+		if (ret)
 			goto out;
-		}
+	} else if (rxfh.indir_size == 0) {
+		indir = (u32 *)rss_config;
+		for (i = 0; i < dev_indir_size; i++)
+			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
+	}
 
-		/* Validate ring indices */
-		for (i = 0; i < dev_size; i++) {
-			if (indir[i] >= rx_rings.data) {
-				ret = -EINVAL;
-				goto out;
-			}
+	if (rxfh.key_size) {
+		hkey = rss_config + indir_bytes;
+		if (copy_from_user(hkey,
+				   useraddr + rss_cfg_offset + indir_bytes,
+				   rxfh.key_size)) {
+			ret = -EFAULT;
+			goto out;
 		}
 	}
 
-	ret = ops->set_rxfh_indir(dev, indir);
+	ret = ops->set_rxfh(dev, indir, hkey);
 
 out:
-	kfree(indir);
+	kfree(rss_config);
 	return ret;
 }
 
@@ -1491,6 +1665,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_GRXCLSRULE:
 	case ETHTOOL_GRXCLSRLALL:
 	case ETHTOOL_GRXFHINDIR:
+	case ETHTOOL_GRSSH:
 	case ETHTOOL_GFEATURES:
 	case ETHTOOL_GCHANNELS:
 	case ETHTOOL_GET_TS_INFO:
@@ -1628,6 +1803,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 	case ETHTOOL_SRXFHINDIR:
 		rc = ethtool_set_rxfh_indir(dev, useraddr);
 		break;
+	case ETHTOOL_GRSSH:
+		rc = ethtool_get_rxfh(dev, useraddr);
+		break;
+	case ETHTOOL_SRSSH:
+		rc = ethtool_set_rxfh(dev, useraddr);
+		break;
 	case ETHTOOL_GFEATURES:
 		rc = ethtool_get_features(dev, useraddr);
 		break;
diff --git a/net/core/filter.c b/net/core/filter.c
index 4aec7b93f1a..1dbf6462f76 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -45,6 +45,27 @@
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
 
+/* Registers */
+#define BPF_R0	regs[BPF_REG_0]
+#define BPF_R1	regs[BPF_REG_1]
+#define BPF_R2	regs[BPF_REG_2]
+#define BPF_R3	regs[BPF_REG_3]
+#define BPF_R4	regs[BPF_REG_4]
+#define BPF_R5	regs[BPF_REG_5]
+#define BPF_R6	regs[BPF_REG_6]
+#define BPF_R7	regs[BPF_REG_7]
+#define BPF_R8	regs[BPF_REG_8]
+#define BPF_R9	regs[BPF_REG_9]
+#define BPF_R10	regs[BPF_REG_10]
+
+/* Named registers */
+#define DST	regs[insn->dst_reg]
+#define SRC	regs[insn->src_reg]
+#define FP	regs[BPF_REG_FP]
+#define ARG1	regs[BPF_REG_ARG1]
+#define CTX	regs[BPF_REG_CTX]
+#define IMM	insn->imm
+
 /* No hurry in this branch
  *
  * Exported for the bpf jit load helper.
@@ -57,9 +78,9 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns
 		ptr = skb_network_header(skb) + k - SKF_NET_OFF;
 	else if (k >= SKF_LL_OFF)
 		ptr = skb_mac_header(skb) + k - SKF_LL_OFF;
-
 	if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb))
 		return ptr;
+
 	return NULL;
 }
 
@@ -68,6 +89,7 @@ static inline void *load_pointer(const struct sk_buff *skb, int k,
 {
 	if (k >= 0)
 		return skb_header_pointer(skb, k, size, buffer);
+
 	return bpf_internal_load_pointer_neg_helper(skb, k, size);
 }
 
@@ -122,13 +144,6 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 	return 0;
 }
 
-/* Register mappings for user programs. */
-#define A_REG		0
-#define X_REG		7
-#define TMP_REG		8
-#define ARG2_REG	2
-#define ARG3_REG	3
-
 /**
  *	__sk_run_filter - run a filter on a given context
  *	@ctx: buffer to run the filter on
@@ -138,447 +153,442 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
  * keep, 0 for none. @ctx is the data we are operating on, @insn is the
  * array of filter instructions.
  */
-unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
+static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
 {
 	u64 stack[MAX_BPF_STACK / sizeof(u64)];
 	u64 regs[MAX_BPF_REG], tmp;
-	void *ptr;
-	int off;
-
-#define K  insn->imm
-#define A  regs[insn->a_reg]
-#define X  regs[insn->x_reg]
-#define R0 regs[0]
-
-#define CONT	 ({insn++; goto select_insn; })
-#define CONT_JMP ({insn++; goto select_insn; })
-
 	static const void *jumptable[256] = {
 		[0 ... 255] = &&default_label,
 		/* Now overwrite non-defaults ... */
-#define DL(A, B, C)	[A|B|C] = &&A##_##B##_##C
-		DL(BPF_ALU, BPF_ADD, BPF_X),
-		DL(BPF_ALU, BPF_ADD, BPF_K),
-		DL(BPF_ALU, BPF_SUB, BPF_X),
-		DL(BPF_ALU, BPF_SUB, BPF_K),
-		DL(BPF_ALU, BPF_AND, BPF_X),
-		DL(BPF_ALU, BPF_AND, BPF_K),
-		DL(BPF_ALU, BPF_OR, BPF_X),
-		DL(BPF_ALU, BPF_OR, BPF_K),
-		DL(BPF_ALU, BPF_LSH, BPF_X),
-		DL(BPF_ALU, BPF_LSH, BPF_K),
-		DL(BPF_ALU, BPF_RSH, BPF_X),
-		DL(BPF_ALU, BPF_RSH, BPF_K),
-		DL(BPF_ALU, BPF_XOR, BPF_X),
-		DL(BPF_ALU, BPF_XOR, BPF_K),
-		DL(BPF_ALU, BPF_MUL, BPF_X),
-		DL(BPF_ALU, BPF_MUL, BPF_K),
-		DL(BPF_ALU, BPF_MOV, BPF_X),
-		DL(BPF_ALU, BPF_MOV, BPF_K),
-		DL(BPF_ALU, BPF_DIV, BPF_X),
-		DL(BPF_ALU, BPF_DIV, BPF_K),
-		DL(BPF_ALU, BPF_MOD, BPF_X),
-		DL(BPF_ALU, BPF_MOD, BPF_K),
-		DL(BPF_ALU, BPF_NEG, 0),
-		DL(BPF_ALU, BPF_END, BPF_TO_BE),
-		DL(BPF_ALU, BPF_END, BPF_TO_LE),
-		DL(BPF_ALU64, BPF_ADD, BPF_X),
-		DL(BPF_ALU64, BPF_ADD, BPF_K),
-		DL(BPF_ALU64, BPF_SUB, BPF_X),
-		DL(BPF_ALU64, BPF_SUB, BPF_K),
-		DL(BPF_ALU64, BPF_AND, BPF_X),
-		DL(BPF_ALU64, BPF_AND, BPF_K),
-		DL(BPF_ALU64, BPF_OR, BPF_X),
-		DL(BPF_ALU64, BPF_OR, BPF_K),
-		DL(BPF_ALU64, BPF_LSH, BPF_X),
-		DL(BPF_ALU64, BPF_LSH, BPF_K),
-		DL(BPF_ALU64, BPF_RSH, BPF_X),
-		DL(BPF_ALU64, BPF_RSH, BPF_K),
-		DL(BPF_ALU64, BPF_XOR, BPF_X),
-		DL(BPF_ALU64, BPF_XOR, BPF_K),
-		DL(BPF_ALU64, BPF_MUL, BPF_X),
-		DL(BPF_ALU64, BPF_MUL, BPF_K),
-		DL(BPF_ALU64, BPF_MOV, BPF_X),
-		DL(BPF_ALU64, BPF_MOV, BPF_K),
-		DL(BPF_ALU64, BPF_ARSH, BPF_X),
-		DL(BPF_ALU64, BPF_ARSH, BPF_K),
-		DL(BPF_ALU64, BPF_DIV, BPF_X),
-		DL(BPF_ALU64, BPF_DIV, BPF_K),
-		DL(BPF_ALU64, BPF_MOD, BPF_X),
-		DL(BPF_ALU64, BPF_MOD, BPF_K),
-		DL(BPF_ALU64, BPF_NEG, 0),
-		DL(BPF_JMP, BPF_CALL, 0),
-		DL(BPF_JMP, BPF_JA, 0),
-		DL(BPF_JMP, BPF_JEQ, BPF_X),
-		DL(BPF_JMP, BPF_JEQ, BPF_K),
-		DL(BPF_JMP, BPF_JNE, BPF_X),
-		DL(BPF_JMP, BPF_JNE, BPF_K),
-		DL(BPF_JMP, BPF_JGT, BPF_X),
-		DL(BPF_JMP, BPF_JGT, BPF_K),
-		DL(BPF_JMP, BPF_JGE, BPF_X),
-		DL(BPF_JMP, BPF_JGE, BPF_K),
-		DL(BPF_JMP, BPF_JSGT, BPF_X),
-		DL(BPF_JMP, BPF_JSGT, BPF_K),
-		DL(BPF_JMP, BPF_JSGE, BPF_X),
-		DL(BPF_JMP, BPF_JSGE, BPF_K),
-		DL(BPF_JMP, BPF_JSET, BPF_X),
-		DL(BPF_JMP, BPF_JSET, BPF_K),
-		DL(BPF_JMP, BPF_EXIT, 0),
-		DL(BPF_STX, BPF_MEM, BPF_B),
-		DL(BPF_STX, BPF_MEM, BPF_H),
-		DL(BPF_STX, BPF_MEM, BPF_W),
-		DL(BPF_STX, BPF_MEM, BPF_DW),
-		DL(BPF_STX, BPF_XADD, BPF_W),
-		DL(BPF_STX, BPF_XADD, BPF_DW),
-		DL(BPF_ST, BPF_MEM, BPF_B),
-		DL(BPF_ST, BPF_MEM, BPF_H),
-		DL(BPF_ST, BPF_MEM, BPF_W),
-		DL(BPF_ST, BPF_MEM, BPF_DW),
-		DL(BPF_LDX, BPF_MEM, BPF_B),
-		DL(BPF_LDX, BPF_MEM, BPF_H),
-		DL(BPF_LDX, BPF_MEM, BPF_W),
-		DL(BPF_LDX, BPF_MEM, BPF_DW),
-		DL(BPF_LD, BPF_ABS, BPF_W),
-		DL(BPF_LD, BPF_ABS, BPF_H),
-		DL(BPF_LD, BPF_ABS, BPF_B),
-		DL(BPF_LD, BPF_IND, BPF_W),
-		DL(BPF_LD, BPF_IND, BPF_H),
-		DL(BPF_LD, BPF_IND, BPF_B),
-#undef DL
+		/* 32 bit ALU operations */
+		[BPF_ALU | BPF_ADD | BPF_X] = &&ALU_ADD_X,
+		[BPF_ALU | BPF_ADD | BPF_K] = &&ALU_ADD_K,
+		[BPF_ALU | BPF_SUB | BPF_X] = &&ALU_SUB_X,
+		[BPF_ALU | BPF_SUB | BPF_K] = &&ALU_SUB_K,
+		[BPF_ALU | BPF_AND | BPF_X] = &&ALU_AND_X,
+		[BPF_ALU | BPF_AND | BPF_K] = &&ALU_AND_K,
+		[BPF_ALU | BPF_OR | BPF_X]  = &&ALU_OR_X,
+		[BPF_ALU | BPF_OR | BPF_K]  = &&ALU_OR_K,
+		[BPF_ALU | BPF_LSH | BPF_X] = &&ALU_LSH_X,
+		[BPF_ALU | BPF_LSH | BPF_K] = &&ALU_LSH_K,
+		[BPF_ALU | BPF_RSH | BPF_X] = &&ALU_RSH_X,
+		[BPF_ALU | BPF_RSH | BPF_K] = &&ALU_RSH_K,
+		[BPF_ALU | BPF_XOR | BPF_X] = &&ALU_XOR_X,
+		[BPF_ALU | BPF_XOR | BPF_K] = &&ALU_XOR_K,
+		[BPF_ALU | BPF_MUL | BPF_X] = &&ALU_MUL_X,
+		[BPF_ALU | BPF_MUL | BPF_K] = &&ALU_MUL_K,
+		[BPF_ALU | BPF_MOV | BPF_X] = &&ALU_MOV_X,
+		[BPF_ALU | BPF_MOV | BPF_K] = &&ALU_MOV_K,
+		[BPF_ALU | BPF_DIV | BPF_X] = &&ALU_DIV_X,
+		[BPF_ALU | BPF_DIV | BPF_K] = &&ALU_DIV_K,
+		[BPF_ALU | BPF_MOD | BPF_X] = &&ALU_MOD_X,
+		[BPF_ALU | BPF_MOD | BPF_K] = &&ALU_MOD_K,
+		[BPF_ALU | BPF_NEG] = &&ALU_NEG,
+		[BPF_ALU | BPF_END | BPF_TO_BE] = &&ALU_END_TO_BE,
+		[BPF_ALU | BPF_END | BPF_TO_LE] = &&ALU_END_TO_LE,
+		/* 64 bit ALU operations */
+		[BPF_ALU64 | BPF_ADD | BPF_X] = &&ALU64_ADD_X,
+		[BPF_ALU64 | BPF_ADD | BPF_K] = &&ALU64_ADD_K,
+		[BPF_ALU64 | BPF_SUB | BPF_X] = &&ALU64_SUB_X,
+		[BPF_ALU64 | BPF_SUB | BPF_K] = &&ALU64_SUB_K,
+		[BPF_ALU64 | BPF_AND | BPF_X] = &&ALU64_AND_X,
+		[BPF_ALU64 | BPF_AND | BPF_K] = &&ALU64_AND_K,
+		[BPF_ALU64 | BPF_OR | BPF_X] = &&ALU64_OR_X,
+		[BPF_ALU64 | BPF_OR | BPF_K] = &&ALU64_OR_K,
+		[BPF_ALU64 | BPF_LSH | BPF_X] = &&ALU64_LSH_X,
+		[BPF_ALU64 | BPF_LSH | BPF_K] = &&ALU64_LSH_K,
+		[BPF_ALU64 | BPF_RSH | BPF_X] = &&ALU64_RSH_X,
+		[BPF_ALU64 | BPF_RSH | BPF_K] = &&ALU64_RSH_K,
+		[BPF_ALU64 | BPF_XOR | BPF_X] = &&ALU64_XOR_X,
+		[BPF_ALU64 | BPF_XOR | BPF_K] = &&ALU64_XOR_K,
+		[BPF_ALU64 | BPF_MUL | BPF_X] = &&ALU64_MUL_X,
+		[BPF_ALU64 | BPF_MUL | BPF_K] = &&ALU64_MUL_K,
+		[BPF_ALU64 | BPF_MOV | BPF_X] = &&ALU64_MOV_X,
+		[BPF_ALU64 | BPF_MOV | BPF_K] = &&ALU64_MOV_K,
+		[BPF_ALU64 | BPF_ARSH | BPF_X] = &&ALU64_ARSH_X,
+		[BPF_ALU64 | BPF_ARSH | BPF_K] = &&ALU64_ARSH_K,
+		[BPF_ALU64 | BPF_DIV | BPF_X] = &&ALU64_DIV_X,
+		[BPF_ALU64 | BPF_DIV | BPF_K] = &&ALU64_DIV_K,
+		[BPF_ALU64 | BPF_MOD | BPF_X] = &&ALU64_MOD_X,
+		[BPF_ALU64 | BPF_MOD | BPF_K] = &&ALU64_MOD_K,
+		[BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
+		/* Call instruction */
+		[BPF_JMP | BPF_CALL] = &&JMP_CALL,
+		/* Jumps */
+		[BPF_JMP | BPF_JA] = &&JMP_JA,
+		[BPF_JMP | BPF_JEQ | BPF_X] = &&JMP_JEQ_X,
+		[BPF_JMP | BPF_JEQ | BPF_K] = &&JMP_JEQ_K,
+		[BPF_JMP | BPF_JNE | BPF_X] = &&JMP_JNE_X,
+		[BPF_JMP | BPF_JNE | BPF_K] = &&JMP_JNE_K,
+		[BPF_JMP | BPF_JGT | BPF_X] = &&JMP_JGT_X,
+		[BPF_JMP | BPF_JGT | BPF_K] = &&JMP_JGT_K,
+		[BPF_JMP | BPF_JGE | BPF_X] = &&JMP_JGE_X,
+		[BPF_JMP | BPF_JGE | BPF_K] = &&JMP_JGE_K,
+		[BPF_JMP | BPF_JSGT | BPF_X] = &&JMP_JSGT_X,
+		[BPF_JMP | BPF_JSGT | BPF_K] = &&JMP_JSGT_K,
+		[BPF_JMP | BPF_JSGE | BPF_X] = &&JMP_JSGE_X,
+		[BPF_JMP | BPF_JSGE | BPF_K] = &&JMP_JSGE_K,
+		[BPF_JMP | BPF_JSET | BPF_X] = &&JMP_JSET_X,
+		[BPF_JMP | BPF_JSET | BPF_K] = &&JMP_JSET_K,
+		/* Program return */
+		[BPF_JMP | BPF_EXIT] = &&JMP_EXIT,
+		/* Store instructions */
+		[BPF_STX | BPF_MEM | BPF_B] = &&STX_MEM_B,
+		[BPF_STX | BPF_MEM | BPF_H] = &&STX_MEM_H,
+		[BPF_STX | BPF_MEM | BPF_W] = &&STX_MEM_W,
+		[BPF_STX | BPF_MEM | BPF_DW] = &&STX_MEM_DW,
+		[BPF_STX | BPF_XADD | BPF_W] = &&STX_XADD_W,
+		[BPF_STX | BPF_XADD | BPF_DW] = &&STX_XADD_DW,
+		[BPF_ST | BPF_MEM | BPF_B] = &&ST_MEM_B,
+		[BPF_ST | BPF_MEM | BPF_H] = &&ST_MEM_H,
+		[BPF_ST | BPF_MEM | BPF_W] = &&ST_MEM_W,
+		[BPF_ST | BPF_MEM | BPF_DW] = &&ST_MEM_DW,
+		/* Load instructions */
+		[BPF_LDX | BPF_MEM | BPF_B] = &&LDX_MEM_B,
+		[BPF_LDX | BPF_MEM | BPF_H] = &&LDX_MEM_H,
+		[BPF_LDX | BPF_MEM | BPF_W] = &&LDX_MEM_W,
+		[BPF_LDX | BPF_MEM | BPF_DW] = &&LDX_MEM_DW,
+		[BPF_LD | BPF_ABS | BPF_W] = &&LD_ABS_W,
+		[BPF_LD | BPF_ABS | BPF_H] = &&LD_ABS_H,
+		[BPF_LD | BPF_ABS | BPF_B] = &&LD_ABS_B,
+		[BPF_LD | BPF_IND | BPF_W] = &&LD_IND_W,
+		[BPF_LD | BPF_IND | BPF_H] = &&LD_IND_H,
+		[BPF_LD | BPF_IND | BPF_B] = &&LD_IND_B,
 	};
+	void *ptr;
+	int off;
+
+#define CONT	 ({ insn++; goto select_insn; })
+#define CONT_JMP ({ insn++; goto select_insn; })
 
-	regs[FP_REG]  = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
-	regs[ARG1_REG] = (u64) (unsigned long) ctx;
-	regs[A_REG] = 0;
-	regs[X_REG] = 0;
+	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
+	ARG1 = (u64) (unsigned long) ctx;
+
+	/* Registers used in classic BPF programs need to be reset first. */
+	regs[BPF_REG_A] = 0;
+	regs[BPF_REG_X] = 0;
 
 select_insn:
 	goto *jumptable[insn->code];
 
 	/* ALU */
 #define ALU(OPCODE, OP)			\
-	BPF_ALU64_##OPCODE##_BPF_X:	\
-		A = A OP X;		\
+	ALU64_##OPCODE##_X:		\
+		DST = DST OP SRC;	\
 		CONT;			\
-	BPF_ALU_##OPCODE##_BPF_X:	\
-		A = (u32) A OP (u32) X;	\
+	ALU_##OPCODE##_X:		\
+		DST = (u32) DST OP (u32) SRC;	\
 		CONT;			\
-	BPF_ALU64_##OPCODE##_BPF_K:	\
-		A = A OP K;		\
+	ALU64_##OPCODE##_K:		\
+		DST = DST OP IMM;		\
 		CONT;			\
-	BPF_ALU_##OPCODE##_BPF_K:	\
-		A = (u32) A OP (u32) K;	\
+	ALU_##OPCODE##_K:		\
+		DST = (u32) DST OP (u32) IMM;	\
 		CONT;
 
-	ALU(BPF_ADD,  +)
-	ALU(BPF_SUB,  -)
-	ALU(BPF_AND,  &)
-	ALU(BPF_OR,   |)
-	ALU(BPF_LSH, <<)
-	ALU(BPF_RSH, >>)
-	ALU(BPF_XOR,  ^)
-	ALU(BPF_MUL,  *)
+	ALU(ADD,  +)
+	ALU(SUB,  -)
+	ALU(AND,  &)
+	ALU(OR,   |)
+	ALU(LSH, <<)
+	ALU(RSH, >>)
+	ALU(XOR,  ^)
+	ALU(MUL,  *)
 #undef ALU
-	BPF_ALU_BPF_NEG_0:
-		A = (u32) -A;
+	ALU_NEG:
+		DST = (u32) -DST;
 		CONT;
-	BPF_ALU64_BPF_NEG_0:
-		A = -A;
+	ALU64_NEG:
+		DST = -DST;
 		CONT;
-	BPF_ALU_BPF_MOV_BPF_X:
-		A = (u32) X;
+	ALU_MOV_X:
+		DST = (u32) SRC;
 		CONT;
-	BPF_ALU_BPF_MOV_BPF_K:
-		A = (u32) K;
+	ALU_MOV_K:
+		DST = (u32) IMM;
 		CONT;
-	BPF_ALU64_BPF_MOV_BPF_X:
-		A = X;
+	ALU64_MOV_X:
+		DST = SRC;
 		CONT;
-	BPF_ALU64_BPF_MOV_BPF_K:
-		A = K;
+	ALU64_MOV_K:
+		DST = IMM;
 		CONT;
-	BPF_ALU64_BPF_ARSH_BPF_X:
-		(*(s64 *) &A) >>= X;
+	ALU64_ARSH_X:
+		(*(s64 *) &DST) >>= SRC;
 		CONT;
-	BPF_ALU64_BPF_ARSH_BPF_K:
-		(*(s64 *) &A) >>= K;
+	ALU64_ARSH_K:
+		(*(s64 *) &DST) >>= IMM;
 		CONT;
-	BPF_ALU64_BPF_MOD_BPF_X:
-		if (unlikely(X == 0))
+	ALU64_MOD_X:
+		if (unlikely(SRC == 0))
 			return 0;
-		tmp = A;
-		A = do_div(tmp, X);
+		tmp = DST;
+		DST = do_div(tmp, SRC);
 		CONT;
-	BPF_ALU_BPF_MOD_BPF_X:
-		if (unlikely(X == 0))
+	ALU_MOD_X:
+		if (unlikely(SRC == 0))
 			return 0;
-		tmp = (u32) A;
-		A = do_div(tmp, (u32) X);
+		tmp = (u32) DST;
+		DST = do_div(tmp, (u32) SRC);
 		CONT;
-	BPF_ALU64_BPF_MOD_BPF_K:
-		tmp = A;
-		A = do_div(tmp, K);
+	ALU64_MOD_K:
+		tmp = DST;
+		DST = do_div(tmp, IMM);
 		CONT;
-	BPF_ALU_BPF_MOD_BPF_K:
-		tmp = (u32) A;
-		A = do_div(tmp, (u32) K);
+	ALU_MOD_K:
+		tmp = (u32) DST;
+		DST = do_div(tmp, (u32) IMM);
 		CONT;
-	BPF_ALU64_BPF_DIV_BPF_X:
-		if (unlikely(X == 0))
+	ALU64_DIV_X:
+		if (unlikely(SRC == 0))
 			return 0;
-		do_div(A, X);
+		do_div(DST, SRC);
 		CONT;
-	BPF_ALU_BPF_DIV_BPF_X:
-		if (unlikely(X == 0))
+	ALU_DIV_X:
+		if (unlikely(SRC == 0))
 			return 0;
-		tmp = (u32) A;
-		do_div(tmp, (u32) X);
-		A = (u32) tmp;
+		tmp = (u32) DST;
+		do_div(tmp, (u32) SRC);
+		DST = (u32) tmp;
 		CONT;
-	BPF_ALU64_BPF_DIV_BPF_K:
-		do_div(A, K);
+	ALU64_DIV_K:
+		do_div(DST, IMM);
 		CONT;
-	BPF_ALU_BPF_DIV_BPF_K:
-		tmp = (u32) A;
-		do_div(tmp, (u32) K);
-		A = (u32) tmp;
+	ALU_DIV_K:
+		tmp = (u32) DST;
+		do_div(tmp, (u32) IMM);
+		DST = (u32) tmp;
 		CONT;
-	BPF_ALU_BPF_END_BPF_TO_BE:
-		switch (K) {
+	ALU_END_TO_BE:
+		switch (IMM) {
 		case 16:
-			A = (__force u16) cpu_to_be16(A);
+			DST = (__force u16) cpu_to_be16(DST);
 			break;
 		case 32:
-			A = (__force u32) cpu_to_be32(A);
+			DST = (__force u32) cpu_to_be32(DST);
 			break;
 		case 64:
-			A = (__force u64) cpu_to_be64(A);
+			DST = (__force u64) cpu_to_be64(DST);
 			break;
 		}
 		CONT;
-	BPF_ALU_BPF_END_BPF_TO_LE:
-		switch (K) {
+	ALU_END_TO_LE:
+		switch (IMM) {
 		case 16:
-			A = (__force u16) cpu_to_le16(A);
+			DST = (__force u16) cpu_to_le16(DST);
 			break;
 		case 32:
-			A = (__force u32) cpu_to_le32(A);
+			DST = (__force u32) cpu_to_le32(DST);
 			break;
 		case 64:
-			A = (__force u64) cpu_to_le64(A);
+			DST = (__force u64) cpu_to_le64(DST);
 			break;
 		}
 		CONT;
 
 	/* CALL */
-	BPF_JMP_BPF_CALL_0:
-		/* Function call scratches R1-R5 registers, preserves R6-R9,
-		 * and stores return value into R0.
+	JMP_CALL:
+		/* Function call scratches BPF_R1-BPF_R5 registers,
+		 * preserves BPF_R6-BPF_R9, and stores return value
+		 * into BPF_R0.
 		 */
-		R0 = (__bpf_call_base + insn->imm)(regs[1], regs[2], regs[3],
-						   regs[4], regs[5]);
+		BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3,
+						       BPF_R4, BPF_R5);
 		CONT;
 
 	/* JMP */
-	BPF_JMP_BPF_JA_0:
+	JMP_JA:
 		insn += insn->off;
 		CONT;
-	BPF_JMP_BPF_JEQ_BPF_X:
-		if (A == X) {
+	JMP_JEQ_X:
+		if (DST == SRC) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JEQ_BPF_K:
-		if (A == K) {
+	JMP_JEQ_K:
+		if (DST == IMM) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JNE_BPF_X:
-		if (A != X) {
+	JMP_JNE_X:
+		if (DST != SRC) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JNE_BPF_K:
-		if (A != K) {
+	JMP_JNE_K:
+		if (DST != IMM) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JGT_BPF_X:
-		if (A > X) {
+	JMP_JGT_X:
+		if (DST > SRC) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JGT_BPF_K:
-		if (A > K) {
+	JMP_JGT_K:
+		if (DST > IMM) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JGE_BPF_X:
-		if (A >= X) {
+	JMP_JGE_X:
+		if (DST >= SRC) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JGE_BPF_K:
-		if (A >= K) {
+	JMP_JGE_K:
+		if (DST >= IMM) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JSGT_BPF_X:
-		if (((s64)A) > ((s64)X)) {
+	JMP_JSGT_X:
+		if (((s64) DST) > ((s64) SRC)) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JSGT_BPF_K:
-		if (((s64)A) > ((s64)K)) {
+	JMP_JSGT_K:
+		if (((s64) DST) > ((s64) IMM)) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JSGE_BPF_X:
-		if (((s64)A) >= ((s64)X)) {
+	JMP_JSGE_X:
+		if (((s64) DST) >= ((s64) SRC)) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JSGE_BPF_K:
-		if (((s64)A) >= ((s64)K)) {
+	JMP_JSGE_K:
+		if (((s64) DST) >= ((s64) IMM)) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JSET_BPF_X:
-		if (A & X) {
+	JMP_JSET_X:
+		if (DST & SRC) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_JSET_BPF_K:
-		if (A & K) {
+	JMP_JSET_K:
+		if (DST & IMM) {
 			insn += insn->off;
 			CONT_JMP;
 		}
 		CONT;
-	BPF_JMP_BPF_EXIT_0:
-		return R0;
+	JMP_EXIT:
+		return BPF_R0;
 
 	/* STX and ST and LDX*/
-#define LDST(SIZEOP, SIZE)					\
-	BPF_STX_BPF_MEM_##SIZEOP:				\
-		*(SIZE *)(unsigned long) (A + insn->off) = X;	\
-		CONT;						\
-	BPF_ST_BPF_MEM_##SIZEOP:				\
-		*(SIZE *)(unsigned long) (A + insn->off) = K;	\
-		CONT;						\
-	BPF_LDX_BPF_MEM_##SIZEOP:				\
-		A = *(SIZE *)(unsigned long) (X + insn->off);	\
+#define LDST(SIZEOP, SIZE)						\
+	STX_MEM_##SIZEOP:						\
+		*(SIZE *)(unsigned long) (DST + insn->off) = SRC;	\
+		CONT;							\
+	ST_MEM_##SIZEOP:						\
+		*(SIZE *)(unsigned long) (DST + insn->off) = IMM;	\
+		CONT;							\
+	LDX_MEM_##SIZEOP:						\
+		DST = *(SIZE *)(unsigned long) (SRC + insn->off);	\
 		CONT;
 
-	LDST(BPF_B,   u8)
-	LDST(BPF_H,  u16)
-	LDST(BPF_W,  u32)
-	LDST(BPF_DW, u64)
+	LDST(B,   u8)
+	LDST(H,  u16)
+	LDST(W,  u32)
+	LDST(DW, u64)
 #undef LDST
-	BPF_STX_BPF_XADD_BPF_W: /* lock xadd *(u32 *)(A + insn->off) += X */
-		atomic_add((u32) X, (atomic_t *)(unsigned long)
-			   (A + insn->off));
+	STX_XADD_W: /* lock xadd *(u32 *)(dst_reg + off16) += src_reg */
+		atomic_add((u32) SRC, (atomic_t *)(unsigned long)
+			   (DST + insn->off));
 		CONT;
-	BPF_STX_BPF_XADD_BPF_DW: /* lock xadd *(u64 *)(A + insn->off) += X */
-		atomic64_add((u64) X, (atomic64_t *)(unsigned long)
-			     (A + insn->off));
+	STX_XADD_DW: /* lock xadd *(u64 *)(dst_reg + off16) += src_reg */
+		atomic64_add((u64) SRC, (atomic64_t *)(unsigned long)
+			     (DST + insn->off));
 		CONT;
-	BPF_LD_BPF_ABS_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + K)) */
-		off = K;
+	LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */
+		off = IMM;
 load_word:
-		/* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
-		 * appearing in the programs where ctx == skb. All programs
-		 * keep 'ctx' in regs[CTX_REG] == R6, sk_convert_filter()
-		 * saves it in R6, internal BPF verifier will check that
-		 * R6 == ctx.
+		/* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are
+		 * only appearing in the programs where ctx ==
+		 * skb. All programs keep 'ctx' in regs[BPF_REG_CTX]
+		 * == BPF_R6, sk_convert_filter() saves it in BPF_R6,
+		 * internal BPF verifier will check that BPF_R6 ==
+		 * ctx.
 		 *
-		 * BPF_ABS and BPF_IND are wrappers of function calls, so
-		 * they scratch R1-R5 registers, preserve R6-R9, and store
-		 * return value into R0.
+		 * BPF_ABS and BPF_IND are wrappers of function calls,
+		 * so they scratch BPF_R1-BPF_R5 registers, preserve
+		 * BPF_R6-BPF_R9, and store return value into BPF_R0.
 		 *
 		 * Implicit input:
-		 *   ctx
+		 *   ctx == skb == BPF_R6 == CTX
 		 *
 		 * Explicit input:
-		 *   X == any register
-		 *   K == 32-bit immediate
+		 *   SRC == any register
+		 *   IMM == 32-bit immediate
 		 *
 		 * Output:
-		 *   R0 - 8/16/32-bit skb data converted to cpu endianness
+		 *   BPF_R0 - 8/16/32-bit skb data converted to cpu endianness
 		 */
-		ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp);
+
+		ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp);
 		if (likely(ptr != NULL)) {
-			R0 = get_unaligned_be32(ptr);
+			BPF_R0 = get_unaligned_be32(ptr);
 			CONT;
 		}
+
 		return 0;
-	BPF_LD_BPF_ABS_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + K)) */
-		off = K;
+	LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */
+		off = IMM;
 load_half:
-		ptr = load_pointer((struct sk_buff *) ctx, off, 2, &tmp);
+		ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp);
 		if (likely(ptr != NULL)) {
-			R0 = get_unaligned_be16(ptr);
+			BPF_R0 = get_unaligned_be16(ptr);
 			CONT;
 		}
+
 		return 0;
-	BPF_LD_BPF_ABS_BPF_B: /* R0 = *(u8 *) (ctx + K) */
-		off = K;
+	LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */
+		off = IMM;
 load_byte:
-		ptr = load_pointer((struct sk_buff *) ctx, off, 1, &tmp);
+		ptr = load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp);
 		if (likely(ptr != NULL)) {
-			R0 = *(u8 *)ptr;
+			BPF_R0 = *(u8 *)ptr;
 			CONT;
 		}
+
 		return 0;
-	BPF_LD_BPF_IND_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + X + K)) */
-		off = K + X;
+	LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */
+		off = IMM + SRC;
 		goto load_word;
-	BPF_LD_BPF_IND_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + X + K)) */
-		off = K + X;
+	LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */
+		off = IMM + SRC;
 		goto load_half;
-	BPF_LD_BPF_IND_BPF_B: /* R0 = *(u8 *) (skb->data + X + K) */
-		off = K + X;
+	LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */
+		off = IMM + SRC;
 		goto load_byte;
 
 	default_label:
 		/* If we ever reach this, we have a bug somewhere. */
 		WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
 		return 0;
-#undef CONT_JMP
-#undef CONT
-
-#undef R0
-#undef X
-#undef A
-#undef K
 }
 
-u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx,
-			      const struct sock_filter_int *insni)
-    __attribute__ ((alias ("__sk_run_filter")));
-
-u32 sk_run_filter_int_skb(const struct sk_buff *ctx,
-			  const struct sock_filter_int *insni)
-    __attribute__ ((alias ("__sk_run_filter")));
-EXPORT_SYMBOL_GPL(sk_run_filter_int_skb);
-
 /* Helper to find the offset of pkt_type in sk_buff structure. We want
  * to make sure its still a 3bit field starting at a byte boundary;
  * taken from arch/x86/net/bpf_jit_comp.c.
  */
+#ifdef __BIG_ENDIAN_BITFIELD
+#define PKT_TYPE_MAX	(7 << 5)
+#else
 #define PKT_TYPE_MAX	7
+#endif
 static unsigned int pkt_type_offset(void)
 {
 	struct sk_buff skb_probe = { .pkt_type = ~0, };
@@ -594,16 +604,14 @@ static unsigned int pkt_type_offset(void)
 	return -1;
 }
 
-static u64 __skb_get_pay_offset(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {
-	struct sk_buff *skb = (struct sk_buff *)(long) ctx;
-
-	return __skb_get_poff(skb);
+	return __skb_get_poff((struct sk_buff *)(unsigned long) ctx);
 }
 
-static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {
-	struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+	struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx;
 	struct nlattr *nla;
 
 	if (skb_is_nonlinear(skb))
@@ -612,19 +620,19 @@ static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
 	if (skb->len < sizeof(struct nlattr))
 		return 0;
 
-	if (A > skb->len - sizeof(struct nlattr))
+	if (a > skb->len - sizeof(struct nlattr))
 		return 0;
 
-	nla = nla_find((struct nlattr *) &skb->data[A], skb->len - A, X);
+	nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x);
 	if (nla)
 		return (void *) nla - (void *) skb->data;
 
 	return 0;
 }
 
-static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+static u64 __skb_get_nlattr_nest(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {
-	struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+	struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx;
 	struct nlattr *nla;
 
 	if (skb_is_nonlinear(skb))
@@ -633,25 +641,31 @@ static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
 	if (skb->len < sizeof(struct nlattr))
 		return 0;
 
-	if (A > skb->len - sizeof(struct nlattr))
+	if (a > skb->len - sizeof(struct nlattr))
 		return 0;
 
-	nla = (struct nlattr *) &skb->data[A];
-	if (nla->nla_len > skb->len - A)
+	nla = (struct nlattr *) &skb->data[a];
+	if (nla->nla_len > skb->len - a)
 		return 0;
 
-	nla = nla_find_nested(nla, X);
+	nla = nla_find_nested(nla, x);
 	if (nla)
 		return (void *) nla - (void *) skb->data;
 
 	return 0;
 }
 
-static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
 {
 	return raw_smp_processor_id();
 }
 
+/* note that this only generates 32-bit random numbers */
+static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
+{
+	return prandom_u32();
+}
+
 static bool convert_bpf_extensions(struct sock_filter *fp,
 				   struct sock_filter_int **insnp)
 {
@@ -661,119 +675,83 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
 	case SKF_AD_OFF + SKF_AD_PROTOCOL:
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
 
-		insn->code = BPF_LDX | BPF_MEM | BPF_H;
-		insn->a_reg = A_REG;
-		insn->x_reg = CTX_REG;
-		insn->off = offsetof(struct sk_buff, protocol);
-		insn++;
-
+		/* A = *(u16 *) (CTX + offsetof(protocol)) */
+		*insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
+				      offsetof(struct sk_buff, protocol));
 		/* A = ntohs(A) [emitting a nop or swap16] */
-		insn->code = BPF_ALU | BPF_END | BPF_FROM_BE;
-		insn->a_reg = A_REG;
-		insn->imm = 16;
+		*insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16);
 		break;
 
 	case SKF_AD_OFF + SKF_AD_PKTTYPE:
-		insn->code = BPF_LDX | BPF_MEM | BPF_B;
-		insn->a_reg = A_REG;
-		insn->x_reg = CTX_REG;
-		insn->off = pkt_type_offset();
+		*insn = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX,
+				    pkt_type_offset());
 		if (insn->off < 0)
 			return false;
 		insn++;
-
-		insn->code = BPF_ALU | BPF_AND | BPF_K;
-		insn->a_reg = A_REG;
-		insn->imm = PKT_TYPE_MAX;
+		*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX);
+#ifdef __BIG_ENDIAN_BITFIELD
+		insn++;
+                *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 5);
+#endif
 		break;
 
 	case SKF_AD_OFF + SKF_AD_IFINDEX:
 	case SKF_AD_OFF + SKF_AD_HATYPE:
-		if (FIELD_SIZEOF(struct sk_buff, dev) == 8)
-			insn->code = BPF_LDX | BPF_MEM | BPF_DW;
-		else
-			insn->code = BPF_LDX | BPF_MEM | BPF_W;
-		insn->a_reg = TMP_REG;
-		insn->x_reg = CTX_REG;
-		insn->off = offsetof(struct sk_buff, dev);
-		insn++;
-
-		insn->code = BPF_JMP | BPF_JNE | BPF_K;
-		insn->a_reg = TMP_REG;
-		insn->imm = 0;
-		insn->off = 1;
-		insn++;
-
-		insn->code = BPF_JMP | BPF_EXIT;
-		insn++;
-
 		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
 		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2);
-
-		insn->a_reg = A_REG;
-		insn->x_reg = TMP_REG;
-
-		if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) {
-			insn->code = BPF_LDX | BPF_MEM | BPF_W;
-			insn->off = offsetof(struct net_device, ifindex);
-		} else {
-			insn->code = BPF_LDX | BPF_MEM | BPF_H;
-			insn->off = offsetof(struct net_device, type);
-		}
+		BUILD_BUG_ON(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)) < 0);
+
+		*insn++ = BPF_LDX_MEM(bytes_to_bpf_size(FIELD_SIZEOF(struct sk_buff, dev)),
+				      BPF_REG_TMP, BPF_REG_CTX,
+				      offsetof(struct sk_buff, dev));
+		/* if (tmp != 0) goto pc + 1 */
+		*insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1);
+		*insn++ = BPF_EXIT_INSN();
+		if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX)
+			*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP,
+					    offsetof(struct net_device, ifindex));
+		else
+			*insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP,
+					    offsetof(struct net_device, type));
 		break;
 
 	case SKF_AD_OFF + SKF_AD_MARK:
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
 
-		insn->code = BPF_LDX | BPF_MEM | BPF_W;
-		insn->a_reg = A_REG;
-		insn->x_reg = CTX_REG;
-		insn->off = offsetof(struct sk_buff, mark);
+		*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX,
+				    offsetof(struct sk_buff, mark));
 		break;
 
 	case SKF_AD_OFF + SKF_AD_RXHASH:
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
 
-		insn->code = BPF_LDX | BPF_MEM | BPF_W;
-		insn->a_reg = A_REG;
-		insn->x_reg = CTX_REG;
-		insn->off = offsetof(struct sk_buff, hash);
+		*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX,
+				    offsetof(struct sk_buff, hash));
 		break;
 
 	case SKF_AD_OFF + SKF_AD_QUEUE:
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
 
-		insn->code = BPF_LDX | BPF_MEM | BPF_H;
-		insn->a_reg = A_REG;
-		insn->x_reg = CTX_REG;
-		insn->off = offsetof(struct sk_buff, queue_mapping);
+		*insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
+				    offsetof(struct sk_buff, queue_mapping));
 		break;
 
 	case SKF_AD_OFF + SKF_AD_VLAN_TAG:
 	case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT:
 		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
-
-		insn->code = BPF_LDX | BPF_MEM | BPF_H;
-		insn->a_reg = A_REG;
-		insn->x_reg = CTX_REG;
-		insn->off = offsetof(struct sk_buff, vlan_tci);
-		insn++;
-
 		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
 
+		/* A = *(u16 *) (CTX + offsetof(vlan_tci)) */
+		*insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX,
+				      offsetof(struct sk_buff, vlan_tci));
 		if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) {
-			insn->code = BPF_ALU | BPF_AND | BPF_K;
-			insn->a_reg = A_REG;
-			insn->imm = ~VLAN_TAG_PRESENT;
+			*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A,
+					      ~VLAN_TAG_PRESENT);
 		} else {
-			insn->code = BPF_ALU | BPF_RSH | BPF_K;
-			insn->a_reg = A_REG;
-			insn->imm = 12;
-			insn++;
-
-			insn->code = BPF_ALU | BPF_AND | BPF_K;
-			insn->a_reg = A_REG;
-			insn->imm = 1;
+			/* A >>= 12 */
+			*insn++ = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12);
+			/* A &= 1 */
+			*insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1);
 		}
 		break;
 
@@ -781,46 +759,36 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
 	case SKF_AD_OFF + SKF_AD_NLATTR:
 	case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
 	case SKF_AD_OFF + SKF_AD_CPU:
-		/* arg1 = ctx */
-		insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
-		insn->a_reg = ARG1_REG;
-		insn->x_reg = CTX_REG;
-		insn++;
-
+	case SKF_AD_OFF + SKF_AD_RANDOM:
+		/* arg1 = CTX */
+		*insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX);
 		/* arg2 = A */
-		insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
-		insn->a_reg = ARG2_REG;
-		insn->x_reg = A_REG;
-		insn++;
-
+		*insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A);
 		/* arg3 = X */
-		insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
-		insn->a_reg = ARG3_REG;
-		insn->x_reg = X_REG;
-		insn++;
-
-		/* Emit call(ctx, arg2=A, arg3=X) */
-		insn->code = BPF_JMP | BPF_CALL;
+		*insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X);
+		/* Emit call(arg1=CTX, arg2=A, arg3=X) */
 		switch (fp->k) {
 		case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
-			insn->imm = __skb_get_pay_offset - __bpf_call_base;
+			*insn = BPF_EMIT_CALL(__skb_get_pay_offset);
 			break;
 		case SKF_AD_OFF + SKF_AD_NLATTR:
-			insn->imm = __skb_get_nlattr - __bpf_call_base;
+			*insn = BPF_EMIT_CALL(__skb_get_nlattr);
 			break;
 		case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
-			insn->imm = __skb_get_nlattr_nest - __bpf_call_base;
+			*insn = BPF_EMIT_CALL(__skb_get_nlattr_nest);
 			break;
 		case SKF_AD_OFF + SKF_AD_CPU:
-			insn->imm = __get_raw_cpu_id - __bpf_call_base;
+			*insn = BPF_EMIT_CALL(__get_raw_cpu_id);
+			break;
+		case SKF_AD_OFF + SKF_AD_RANDOM:
+			*insn = BPF_EMIT_CALL(__get_random_u32);
 			break;
 		}
 		break;
 
 	case SKF_AD_OFF + SKF_AD_ALU_XOR_X:
-		insn->code = BPF_ALU | BPF_XOR | BPF_X;
-		insn->a_reg = A_REG;
-		insn->x_reg = X_REG;
+		/* A ^= X */
+		*insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X);
 		break;
 
 	default:
@@ -870,13 +838,13 @@ int sk_convert_filter(struct sock_filter *prog, int len,
 	u8 bpf_src;
 
 	BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK);
-	BUILD_BUG_ON(FP_REG + 1 != MAX_BPF_REG);
+	BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
 
-	if (len <= 0 || len >= BPF_MAXINSNS)
+	if (len <= 0 || len > BPF_MAXINSNS)
 		return -EINVAL;
 
 	if (new_prog) {
-		addrs = kzalloc(len * sizeof(*addrs), GFP_KERNEL);
+		addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL);
 		if (!addrs)
 			return -ENOMEM;
 	}
@@ -885,11 +853,8 @@ do_pass:
 	new_insn = new_prog;
 	fp = prog;
 
-	if (new_insn) {
-		new_insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
-		new_insn->a_reg = CTX_REG;
-		new_insn->x_reg = ARG1_REG;
-	}
+	if (new_insn)
+		*new_insn = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1);
 	new_insn++;
 
 	for (i = 0; i < len; fp++, i++) {
@@ -937,17 +902,16 @@ do_pass:
 			    convert_bpf_extensions(fp, &insn))
 				break;
 
-			insn->code = fp->code;
-			insn->a_reg = A_REG;
-			insn->x_reg = X_REG;
-			insn->imm = fp->k;
+			*insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k);
 			break;
 
-		/* Jump opcodes map as-is, but offsets need adjustment. */
-		case BPF_JMP | BPF_JA:
-			target = i + fp->k + 1;
-			insn->code = fp->code;
-#define EMIT_JMP							\
+		/* Jump transformation cannot use BPF block macros
+		 * everywhere as offset calculation and target updates
+		 * require a bit more work than the rest, i.e. jump
+		 * opcodes map as-is, but offsets need adjustment.
+		 */
+
+#define BPF_EMIT_JMP							\
 	do {								\
 		if (target >= len || target < 0)			\
 			goto err;					\
@@ -956,7 +920,10 @@ do_pass:
 		insn->off -= insn - tmp_insns;				\
 	} while (0)
 
-			EMIT_JMP;
+		case BPF_JMP | BPF_JA:
+			target = i + fp->k + 1;
+			insn->code = fp->code;
+			BPF_EMIT_JMP;
 			break;
 
 		case BPF_JMP | BPF_JEQ | BPF_K:
@@ -972,17 +939,14 @@ do_pass:
 				 * immediate into tmp register and use it
 				 * in compare insn.
 				 */
-				insn->code = BPF_ALU | BPF_MOV | BPF_K;
-				insn->a_reg = TMP_REG;
-				insn->imm = fp->k;
-				insn++;
+				*insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k);
 
-				insn->a_reg = A_REG;
-				insn->x_reg = TMP_REG;
+				insn->dst_reg = BPF_REG_A;
+				insn->src_reg = BPF_REG_TMP;
 				bpf_src = BPF_X;
 			} else {
-				insn->a_reg = A_REG;
-				insn->x_reg = X_REG;
+				insn->dst_reg = BPF_REG_A;
+				insn->src_reg = BPF_REG_X;
 				insn->imm = fp->k;
 				bpf_src = BPF_SRC(fp->code);
 			}
@@ -991,7 +955,7 @@ do_pass:
 			if (fp->jf == 0) {
 				insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
 				target = i + fp->jt + 1;
-				EMIT_JMP;
+				BPF_EMIT_JMP;
 				break;
 			}
 
@@ -999,127 +963,94 @@ do_pass:
 			if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) {
 				insn->code = BPF_JMP | BPF_JNE | bpf_src;
 				target = i + fp->jf + 1;
-				EMIT_JMP;
+				BPF_EMIT_JMP;
 				break;
 			}
 
 			/* Other jumps are mapped into two insns: Jxx and JA. */
 			target = i + fp->jt + 1;
 			insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
-			EMIT_JMP;
+			BPF_EMIT_JMP;
 			insn++;
 
 			insn->code = BPF_JMP | BPF_JA;
 			target = i + fp->jf + 1;
-			EMIT_JMP;
+			BPF_EMIT_JMP;
 			break;
 
 		/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
 		case BPF_LDX | BPF_MSH | BPF_B:
-			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
-			insn->a_reg = TMP_REG;
-			insn->x_reg = A_REG;
-			insn++;
-
-			insn->code = BPF_LD | BPF_ABS | BPF_B;
-			insn->a_reg = A_REG;
-			insn->imm = fp->k;
-			insn++;
-
-			insn->code = BPF_ALU | BPF_AND | BPF_K;
-			insn->a_reg = A_REG;
-			insn->imm = 0xf;
-			insn++;
-
-			insn->code = BPF_ALU | BPF_LSH | BPF_K;
-			insn->a_reg = A_REG;
-			insn->imm = 2;
-			insn++;
-
-			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
-			insn->a_reg = X_REG;
-			insn->x_reg = A_REG;
-			insn++;
-
-			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
-			insn->a_reg = A_REG;
-			insn->x_reg = TMP_REG;
+			/* tmp = A */
+			*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A);
+			/* A = BPF_R0 = *(u8 *) (skb->data + K) */
+			*insn++ = BPF_LD_ABS(BPF_B, fp->k);
+			/* A &= 0xf */
+			*insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf);
+			/* A <<= 2 */
+			*insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2);
+			/* X = A */
+			*insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
+			/* A = tmp */
+			*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP);
 			break;
 
 		/* RET_K, RET_A are remaped into 2 insns. */
 		case BPF_RET | BPF_A:
 		case BPF_RET | BPF_K:
-			insn->code = BPF_ALU | BPF_MOV |
-				     (BPF_RVAL(fp->code) == BPF_K ?
-				      BPF_K : BPF_X);
-			insn->a_reg = 0;
-			insn->x_reg = A_REG;
-			insn->imm = fp->k;
-			insn++;
-
-			insn->code = BPF_JMP | BPF_EXIT;
+			*insn++ = BPF_MOV32_RAW(BPF_RVAL(fp->code) == BPF_K ?
+						BPF_K : BPF_X, BPF_REG_0,
+						BPF_REG_A, fp->k);
+			*insn = BPF_EXIT_INSN();
 			break;
 
 		/* Store to stack. */
 		case BPF_ST:
 		case BPF_STX:
-			insn->code = BPF_STX | BPF_MEM | BPF_W;
-			insn->a_reg = FP_REG;
-			insn->x_reg = fp->code == BPF_ST ? A_REG : X_REG;
-			insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+			*insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) ==
+					    BPF_ST ? BPF_REG_A : BPF_REG_X,
+					    -(BPF_MEMWORDS - fp->k) * 4);
 			break;
 
 		/* Load from stack. */
 		case BPF_LD | BPF_MEM:
 		case BPF_LDX | BPF_MEM:
-			insn->code = BPF_LDX | BPF_MEM | BPF_W;
-			insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
-				      A_REG : X_REG;
-			insn->x_reg = FP_REG;
-			insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+			*insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD  ?
+					    BPF_REG_A : BPF_REG_X, BPF_REG_FP,
+					    -(BPF_MEMWORDS - fp->k) * 4);
 			break;
 
 		/* A = K or X = K */
 		case BPF_LD | BPF_IMM:
 		case BPF_LDX | BPF_IMM:
-			insn->code = BPF_ALU | BPF_MOV | BPF_K;
-			insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
-				      A_REG : X_REG;
-			insn->imm = fp->k;
+			*insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ?
+					      BPF_REG_A : BPF_REG_X, fp->k);
 			break;
 
 		/* X = A */
 		case BPF_MISC | BPF_TAX:
-			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
-			insn->a_reg = X_REG;
-			insn->x_reg = A_REG;
+			*insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A);
 			break;
 
 		/* A = X */
 		case BPF_MISC | BPF_TXA:
-			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
-			insn->a_reg = A_REG;
-			insn->x_reg = X_REG;
+			*insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X);
 			break;
 
 		/* A = skb->len or X = skb->len */
 		case BPF_LD | BPF_W | BPF_LEN:
 		case BPF_LDX | BPF_W | BPF_LEN:
-			insn->code = BPF_LDX | BPF_MEM | BPF_W;
-			insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
-				      A_REG : X_REG;
-			insn->x_reg = CTX_REG;
-			insn->off = offsetof(struct sk_buff, len);
+			*insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ?
+					    BPF_REG_A : BPF_REG_X, BPF_REG_CTX,
+					    offsetof(struct sk_buff, len));
 			break;
 
-		/* access seccomp_data fields */
+		/* Access seccomp_data fields. */
 		case BPF_LDX | BPF_ABS | BPF_W:
-			insn->code = BPF_LDX | BPF_MEM | BPF_W;
-			insn->a_reg = A_REG;
-			insn->x_reg = CTX_REG;
-			insn->off = fp->k;
+			/* A = *(u32 *) (ctx + K) */
+			*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k);
 			break;
 
+		/* Unkown instruction. */
 		default:
 			goto err;
 		}
@@ -1128,7 +1059,6 @@ do_pass:
 		if (new_prog)
 			memcpy(new_insn, tmp_insns,
 			       sizeof(*insn) * (insn - tmp_insns));
-
 		new_insn += insn - tmp_insns;
 	}
 
@@ -1143,7 +1073,6 @@ do_pass:
 		new_flen = new_insn - new_prog;
 		if (pass > 2)
 			goto err;
-
 		goto do_pass;
 	}
 
@@ -1167,44 +1096,46 @@ err:
  */
 static int check_load_and_stores(struct sock_filter *filter, int flen)
 {
-	u16 *masks, memvalid = 0; /* one bit per cell, 16 cells */
+	u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */
 	int pc, ret = 0;
 
 	BUILD_BUG_ON(BPF_MEMWORDS > 16);
-	masks = kmalloc(flen * sizeof(*masks), GFP_KERNEL);
+
+	masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL);
 	if (!masks)
 		return -ENOMEM;
+
 	memset(masks, 0xff, flen * sizeof(*masks));
 
 	for (pc = 0; pc < flen; pc++) {
 		memvalid &= masks[pc];
 
 		switch (filter[pc].code) {
-		case BPF_S_ST:
-		case BPF_S_STX:
+		case BPF_ST:
+		case BPF_STX:
 			memvalid |= (1 << filter[pc].k);
 			break;
-		case BPF_S_LD_MEM:
-		case BPF_S_LDX_MEM:
+		case BPF_LD | BPF_MEM:
+		case BPF_LDX | BPF_MEM:
 			if (!(memvalid & (1 << filter[pc].k))) {
 				ret = -EINVAL;
 				goto error;
 			}
 			break;
-		case BPF_S_JMP_JA:
-			/* a jump must set masks on target */
+		case BPF_JMP | BPF_JA:
+			/* A jump must set masks on target */
 			masks[pc + 1 + filter[pc].k] &= memvalid;
 			memvalid = ~0;
 			break;
-		case BPF_S_JMP_JEQ_K:
-		case BPF_S_JMP_JEQ_X:
-		case BPF_S_JMP_JGE_K:
-		case BPF_S_JMP_JGE_X:
-		case BPF_S_JMP_JGT_K:
-		case BPF_S_JMP_JGT_X:
-		case BPF_S_JMP_JSET_X:
-		case BPF_S_JMP_JSET_K:
-			/* a jump must set masks on targets */
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
+			/* A jump must set masks on targets */
 			masks[pc + 1 + filter[pc].jt] &= memvalid;
 			masks[pc + 1 + filter[pc].jf] &= memvalid;
 			memvalid = ~0;
@@ -1216,6 +1147,72 @@ error:
 	return ret;
 }
 
+static bool chk_code_allowed(u16 code_to_probe)
+{
+	static const bool codes[] = {
+		/* 32 bit ALU operations */
+		[BPF_ALU | BPF_ADD | BPF_K] = true,
+		[BPF_ALU | BPF_ADD | BPF_X] = true,
+		[BPF_ALU | BPF_SUB | BPF_K] = true,
+		[BPF_ALU | BPF_SUB | BPF_X] = true,
+		[BPF_ALU | BPF_MUL | BPF_K] = true,
+		[BPF_ALU | BPF_MUL | BPF_X] = true,
+		[BPF_ALU | BPF_DIV | BPF_K] = true,
+		[BPF_ALU | BPF_DIV | BPF_X] = true,
+		[BPF_ALU | BPF_MOD | BPF_K] = true,
+		[BPF_ALU | BPF_MOD | BPF_X] = true,
+		[BPF_ALU | BPF_AND | BPF_K] = true,
+		[BPF_ALU | BPF_AND | BPF_X] = true,
+		[BPF_ALU | BPF_OR | BPF_K] = true,
+		[BPF_ALU | BPF_OR | BPF_X] = true,
+		[BPF_ALU | BPF_XOR | BPF_K] = true,
+		[BPF_ALU | BPF_XOR | BPF_X] = true,
+		[BPF_ALU | BPF_LSH | BPF_K] = true,
+		[BPF_ALU | BPF_LSH | BPF_X] = true,
+		[BPF_ALU | BPF_RSH | BPF_K] = true,
+		[BPF_ALU | BPF_RSH | BPF_X] = true,
+		[BPF_ALU | BPF_NEG] = true,
+		/* Load instructions */
+		[BPF_LD | BPF_W | BPF_ABS] = true,
+		[BPF_LD | BPF_H | BPF_ABS] = true,
+		[BPF_LD | BPF_B | BPF_ABS] = true,
+		[BPF_LD | BPF_W | BPF_LEN] = true,
+		[BPF_LD | BPF_W | BPF_IND] = true,
+		[BPF_LD | BPF_H | BPF_IND] = true,
+		[BPF_LD | BPF_B | BPF_IND] = true,
+		[BPF_LD | BPF_IMM] = true,
+		[BPF_LD | BPF_MEM] = true,
+		[BPF_LDX | BPF_W | BPF_LEN] = true,
+		[BPF_LDX | BPF_B | BPF_MSH] = true,
+		[BPF_LDX | BPF_IMM] = true,
+		[BPF_LDX | BPF_MEM] = true,
+		/* Store instructions */
+		[BPF_ST] = true,
+		[BPF_STX] = true,
+		/* Misc instructions */
+		[BPF_MISC | BPF_TAX] = true,
+		[BPF_MISC | BPF_TXA] = true,
+		/* Return instructions */
+		[BPF_RET | BPF_K] = true,
+		[BPF_RET | BPF_A] = true,
+		/* Jump instructions */
+		[BPF_JMP | BPF_JA] = true,
+		[BPF_JMP | BPF_JEQ | BPF_K] = true,
+		[BPF_JMP | BPF_JEQ | BPF_X] = true,
+		[BPF_JMP | BPF_JGE | BPF_K] = true,
+		[BPF_JMP | BPF_JGE | BPF_X] = true,
+		[BPF_JMP | BPF_JGT | BPF_K] = true,
+		[BPF_JMP | BPF_JGT | BPF_X] = true,
+		[BPF_JMP | BPF_JSET | BPF_K] = true,
+		[BPF_JMP | BPF_JSET | BPF_X] = true,
+	};
+
+	if (code_to_probe >= ARRAY_SIZE(codes))
+		return false;
+
+	return codes[code_to_probe];
+}
+
 /**
  *	sk_chk_filter - verify socket filter code
  *	@filter: filter to verify
@@ -1232,153 +1229,76 @@ error:
  */
 int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
 {
-	/*
-	 * Valid instructions are initialized to non-0.
-	 * Invalid instructions are initialized to 0.
-	 */
-	static const u8 codes[] = {
-		[BPF_ALU|BPF_ADD|BPF_K]  = BPF_S_ALU_ADD_K,
-		[BPF_ALU|BPF_ADD|BPF_X]  = BPF_S_ALU_ADD_X,
-		[BPF_ALU|BPF_SUB|BPF_K]  = BPF_S_ALU_SUB_K,
-		[BPF_ALU|BPF_SUB|BPF_X]  = BPF_S_ALU_SUB_X,
-		[BPF_ALU|BPF_MUL|BPF_K]  = BPF_S_ALU_MUL_K,
-		[BPF_ALU|BPF_MUL|BPF_X]  = BPF_S_ALU_MUL_X,
-		[BPF_ALU|BPF_DIV|BPF_X]  = BPF_S_ALU_DIV_X,
-		[BPF_ALU|BPF_MOD|BPF_K]  = BPF_S_ALU_MOD_K,
-		[BPF_ALU|BPF_MOD|BPF_X]  = BPF_S_ALU_MOD_X,
-		[BPF_ALU|BPF_AND|BPF_K]  = BPF_S_ALU_AND_K,
-		[BPF_ALU|BPF_AND|BPF_X]  = BPF_S_ALU_AND_X,
-		[BPF_ALU|BPF_OR|BPF_K]   = BPF_S_ALU_OR_K,
-		[BPF_ALU|BPF_OR|BPF_X]   = BPF_S_ALU_OR_X,
-		[BPF_ALU|BPF_XOR|BPF_K]  = BPF_S_ALU_XOR_K,
-		[BPF_ALU|BPF_XOR|BPF_X]  = BPF_S_ALU_XOR_X,
-		[BPF_ALU|BPF_LSH|BPF_K]  = BPF_S_ALU_LSH_K,
-		[BPF_ALU|BPF_LSH|BPF_X]  = BPF_S_ALU_LSH_X,
-		[BPF_ALU|BPF_RSH|BPF_K]  = BPF_S_ALU_RSH_K,
-		[BPF_ALU|BPF_RSH|BPF_X]  = BPF_S_ALU_RSH_X,
-		[BPF_ALU|BPF_NEG]        = BPF_S_ALU_NEG,
-		[BPF_LD|BPF_W|BPF_ABS]   = BPF_S_LD_W_ABS,
-		[BPF_LD|BPF_H|BPF_ABS]   = BPF_S_LD_H_ABS,
-		[BPF_LD|BPF_B|BPF_ABS]   = BPF_S_LD_B_ABS,
-		[BPF_LD|BPF_W|BPF_LEN]   = BPF_S_LD_W_LEN,
-		[BPF_LD|BPF_W|BPF_IND]   = BPF_S_LD_W_IND,
-		[BPF_LD|BPF_H|BPF_IND]   = BPF_S_LD_H_IND,
-		[BPF_LD|BPF_B|BPF_IND]   = BPF_S_LD_B_IND,
-		[BPF_LD|BPF_IMM]         = BPF_S_LD_IMM,
-		[BPF_LDX|BPF_W|BPF_LEN]  = BPF_S_LDX_W_LEN,
-		[BPF_LDX|BPF_B|BPF_MSH]  = BPF_S_LDX_B_MSH,
-		[BPF_LDX|BPF_IMM]        = BPF_S_LDX_IMM,
-		[BPF_MISC|BPF_TAX]       = BPF_S_MISC_TAX,
-		[BPF_MISC|BPF_TXA]       = BPF_S_MISC_TXA,
-		[BPF_RET|BPF_K]          = BPF_S_RET_K,
-		[BPF_RET|BPF_A]          = BPF_S_RET_A,
-		[BPF_ALU|BPF_DIV|BPF_K]  = BPF_S_ALU_DIV_K,
-		[BPF_LD|BPF_MEM]         = BPF_S_LD_MEM,
-		[BPF_LDX|BPF_MEM]        = BPF_S_LDX_MEM,
-		[BPF_ST]                 = BPF_S_ST,
-		[BPF_STX]                = BPF_S_STX,
-		[BPF_JMP|BPF_JA]         = BPF_S_JMP_JA,
-		[BPF_JMP|BPF_JEQ|BPF_K]  = BPF_S_JMP_JEQ_K,
-		[BPF_JMP|BPF_JEQ|BPF_X]  = BPF_S_JMP_JEQ_X,
-		[BPF_JMP|BPF_JGE|BPF_K]  = BPF_S_JMP_JGE_K,
-		[BPF_JMP|BPF_JGE|BPF_X]  = BPF_S_JMP_JGE_X,
-		[BPF_JMP|BPF_JGT|BPF_K]  = BPF_S_JMP_JGT_K,
-		[BPF_JMP|BPF_JGT|BPF_X]  = BPF_S_JMP_JGT_X,
-		[BPF_JMP|BPF_JSET|BPF_K] = BPF_S_JMP_JSET_K,
-		[BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X,
-	};
-	int pc;
 	bool anc_found;
+	int pc;
 
 	if (flen == 0 || flen > BPF_MAXINSNS)
 		return -EINVAL;
 
-	/* check the filter code now */
+	/* Check the filter code now */
 	for (pc = 0; pc < flen; pc++) {
 		struct sock_filter *ftest = &filter[pc];
-		u16 code = ftest->code;
 
-		if (code >= ARRAY_SIZE(codes))
-			return -EINVAL;
-		code = codes[code];
-		if (!code)
+		/* May we actually operate on this code? */
+		if (!chk_code_allowed(ftest->code))
 			return -EINVAL;
+
 		/* Some instructions need special checks */
-		switch (code) {
-		case BPF_S_ALU_DIV_K:
-		case BPF_S_ALU_MOD_K:
-			/* check for division by zero */
+		switch (ftest->code) {
+		case BPF_ALU | BPF_DIV | BPF_K:
+		case BPF_ALU | BPF_MOD | BPF_K:
+			/* Check for division by zero */
 			if (ftest->k == 0)
 				return -EINVAL;
 			break;
-		case BPF_S_LD_MEM:
-		case BPF_S_LDX_MEM:
-		case BPF_S_ST:
-		case BPF_S_STX:
-			/* check for invalid memory addresses */
+		case BPF_LD | BPF_MEM:
+		case BPF_LDX | BPF_MEM:
+		case BPF_ST:
+		case BPF_STX:
+			/* Check for invalid memory addresses */
 			if (ftest->k >= BPF_MEMWORDS)
 				return -EINVAL;
 			break;
-		case BPF_S_JMP_JA:
-			/*
-			 * Note, the large ftest->k might cause loops.
+		case BPF_JMP | BPF_JA:
+			/* Note, the large ftest->k might cause loops.
 			 * Compare this with conditional jumps below,
 			 * where offsets are limited. --ANK (981016)
 			 */
-			if (ftest->k >= (unsigned int)(flen-pc-1))
+			if (ftest->k >= (unsigned int)(flen - pc - 1))
 				return -EINVAL;
 			break;
-		case BPF_S_JMP_JEQ_K:
-		case BPF_S_JMP_JEQ_X:
-		case BPF_S_JMP_JGE_K:
-		case BPF_S_JMP_JGE_X:
-		case BPF_S_JMP_JGT_K:
-		case BPF_S_JMP_JGT_X:
-		case BPF_S_JMP_JSET_X:
-		case BPF_S_JMP_JSET_K:
-			/* for conditionals both must be safe */
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
+			/* Both conditionals must be safe */
 			if (pc + ftest->jt + 1 >= flen ||
 			    pc + ftest->jf + 1 >= flen)
 				return -EINVAL;
 			break;
-		case BPF_S_LD_W_ABS:
-		case BPF_S_LD_H_ABS:
-		case BPF_S_LD_B_ABS:
+		case BPF_LD | BPF_W | BPF_ABS:
+		case BPF_LD | BPF_H | BPF_ABS:
+		case BPF_LD | BPF_B | BPF_ABS:
 			anc_found = false;
-#define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE:	\
-				code = BPF_S_ANC_##CODE;	\
-				anc_found = true;		\
-				break
-			switch (ftest->k) {
-			ANCILLARY(PROTOCOL);
-			ANCILLARY(PKTTYPE);
-			ANCILLARY(IFINDEX);
-			ANCILLARY(NLATTR);
-			ANCILLARY(NLATTR_NEST);
-			ANCILLARY(MARK);
-			ANCILLARY(QUEUE);
-			ANCILLARY(HATYPE);
-			ANCILLARY(RXHASH);
-			ANCILLARY(CPU);
-			ANCILLARY(ALU_XOR_X);
-			ANCILLARY(VLAN_TAG);
-			ANCILLARY(VLAN_TAG_PRESENT);
-			ANCILLARY(PAY_OFFSET);
-			}
-
-			/* ancillary operation unknown or unsupported */
+			if (bpf_anc_helper(ftest) & BPF_ANC)
+				anc_found = true;
+			/* Ancillary operation unknown or unsupported */
 			if (anc_found == false && ftest->k >= SKF_AD_OFF)
 				return -EINVAL;
 		}
-		ftest->code = code;
 	}
 
-	/* last instruction must be a RET code */
+	/* Last instruction must be a RET code */
 	switch (filter[flen - 1].code) {
-	case BPF_S_RET_K:
-	case BPF_S_RET_A:
+	case BPF_RET | BPF_K:
+	case BPF_RET | BPF_A:
 		return check_load_and_stores(filter, flen);
 	}
+
 	return -EINVAL;
 }
 EXPORT_SYMBOL(sk_chk_filter);
@@ -1423,7 +1343,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu)
 	struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
 
 	sk_release_orig_filter(fp);
-	bpf_jit_free(fp);
+	sk_filter_free(fp);
 }
 
 /**
@@ -1461,8 +1381,8 @@ static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp,
 
 	fp_new = sock_kmalloc(sk, len, GFP_KERNEL);
 	if (fp_new) {
-		memcpy(fp_new, fp, sizeof(struct sk_filter));
-		/* As we're kepping orig_prog in fp_new along,
+		*fp_new = *fp;
+		/* As we're keeping orig_prog in fp_new along,
 		 * we need to make sure we're not evicting it
 		 * from the old fp.
 		 */
@@ -1478,7 +1398,7 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
 {
 	struct sock_filter *old_prog;
 	struct sk_filter *old_fp;
-	int i, err, new_len, old_len = fp->len;
+	int err, new_len, old_len = fp->len;
 
 	/* We are free to overwrite insns et al right here as it
 	 * won't be used at this point in time anymore internally
@@ -1488,13 +1408,6 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
 	BUILD_BUG_ON(sizeof(struct sock_filter) !=
 		     sizeof(struct sock_filter_int));
 
-	/* For now, we need to unfiddle BPF_S_* identifiers in place.
-	 * This can sooner or later on be subject to removal, e.g. when
-	 * JITs have been converted.
-	 */
-	for (i = 0; i < fp->len; i++)
-		sk_decode_filter(&fp->insns[i], &fp->insns[i]);
-
 	/* Conversion cannot happen on overlapping memory areas,
 	 * so we need to keep the user BPF around until the 2nd
 	 * pass. At this time, the user BPF is stored in fp->insns.
@@ -1523,7 +1436,6 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
 		goto out_err_free;
 	}
 
-	fp->bpf_func = sk_run_filter_int_skb;
 	fp->len = new_len;
 
 	/* 2nd pass: remap sock_filter insns into sock_filter_int insns. */
@@ -1536,6 +1448,8 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
 		 */
 		goto out_err_free;
 
+	sk_filter_select_runtime(fp);
+
 	kfree(old_prog);
 	return fp;
 
@@ -1550,6 +1464,33 @@ out_err:
 	return ERR_PTR(err);
 }
 
+void __weak bpf_int_jit_compile(struct sk_filter *prog)
+{
+}
+
+/**
+ *	sk_filter_select_runtime - select execution runtime for BPF program
+ *	@fp: sk_filter populated with internal BPF program
+ *
+ * try to JIT internal BPF program, if JIT is not available select interpreter
+ * BPF program will be executed via SK_RUN_FILTER() macro
+ */
+void sk_filter_select_runtime(struct sk_filter *fp)
+{
+	fp->bpf_func = (void *) __sk_run_filter;
+
+	/* Probe if internal BPF can be JITed */
+	bpf_int_jit_compile(fp);
+}
+EXPORT_SYMBOL_GPL(sk_filter_select_runtime);
+
+/* free internal BPF program */
+void sk_filter_free(struct sk_filter *fp)
+{
+	bpf_jit_free(fp);
+}
+EXPORT_SYMBOL_GPL(sk_filter_free);
+
 static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
 					     struct sock *sk)
 {
@@ -1583,8 +1524,8 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
 
 /**
  *	sk_unattached_filter_create - create an unattached filter
- *	@fprog: the filter program
  *	@pfp: the unattached filter that is created
+ *	@fprog: the filter program
  *
  * Create a filter independent of any socket. We first run some
  * sanity checks on it to make sure it does not explode on us later.
@@ -1592,7 +1533,7 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
  * a negative errno code is returned. On success the return is zero.
  */
 int sk_unattached_filter_create(struct sk_filter **pfp,
-				struct sock_fprog *fprog)
+				struct sock_fprog_kern *fprog)
 {
 	unsigned int fsize = sk_filter_proglen(fprog);
 	struct sk_filter *fp;
@@ -1713,83 +1654,6 @@ int sk_detach_filter(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sk_detach_filter);
 
-void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
-{
-	static const u16 decodes[] = {
-		[BPF_S_ALU_ADD_K]	= BPF_ALU|BPF_ADD|BPF_K,
-		[BPF_S_ALU_ADD_X]	= BPF_ALU|BPF_ADD|BPF_X,
-		[BPF_S_ALU_SUB_K]	= BPF_ALU|BPF_SUB|BPF_K,
-		[BPF_S_ALU_SUB_X]	= BPF_ALU|BPF_SUB|BPF_X,
-		[BPF_S_ALU_MUL_K]	= BPF_ALU|BPF_MUL|BPF_K,
-		[BPF_S_ALU_MUL_X]	= BPF_ALU|BPF_MUL|BPF_X,
-		[BPF_S_ALU_DIV_X]	= BPF_ALU|BPF_DIV|BPF_X,
-		[BPF_S_ALU_MOD_K]	= BPF_ALU|BPF_MOD|BPF_K,
-		[BPF_S_ALU_MOD_X]	= BPF_ALU|BPF_MOD|BPF_X,
-		[BPF_S_ALU_AND_K]	= BPF_ALU|BPF_AND|BPF_K,
-		[BPF_S_ALU_AND_X]	= BPF_ALU|BPF_AND|BPF_X,
-		[BPF_S_ALU_OR_K]	= BPF_ALU|BPF_OR|BPF_K,
-		[BPF_S_ALU_OR_X]	= BPF_ALU|BPF_OR|BPF_X,
-		[BPF_S_ALU_XOR_K]	= BPF_ALU|BPF_XOR|BPF_K,
-		[BPF_S_ALU_XOR_X]	= BPF_ALU|BPF_XOR|BPF_X,
-		[BPF_S_ALU_LSH_K]	= BPF_ALU|BPF_LSH|BPF_K,
-		[BPF_S_ALU_LSH_X]	= BPF_ALU|BPF_LSH|BPF_X,
-		[BPF_S_ALU_RSH_K]	= BPF_ALU|BPF_RSH|BPF_K,
-		[BPF_S_ALU_RSH_X]	= BPF_ALU|BPF_RSH|BPF_X,
-		[BPF_S_ALU_NEG]		= BPF_ALU|BPF_NEG,
-		[BPF_S_LD_W_ABS]	= BPF_LD|BPF_W|BPF_ABS,
-		[BPF_S_LD_H_ABS]	= BPF_LD|BPF_H|BPF_ABS,
-		[BPF_S_LD_B_ABS]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_PROTOCOL]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_PKTTYPE]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_IFINDEX]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_NLATTR]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_NLATTR_NEST]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_MARK]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_QUEUE]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_HATYPE]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_RXHASH]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_CPU]		= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_ALU_XOR_X]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_VLAN_TAG]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_ANC_PAY_OFFSET]	= BPF_LD|BPF_B|BPF_ABS,
-		[BPF_S_LD_W_LEN]	= BPF_LD|BPF_W|BPF_LEN,
-		[BPF_S_LD_W_IND]	= BPF_LD|BPF_W|BPF_IND,
-		[BPF_S_LD_H_IND]	= BPF_LD|BPF_H|BPF_IND,
-		[BPF_S_LD_B_IND]	= BPF_LD|BPF_B|BPF_IND,
-		[BPF_S_LD_IMM]		= BPF_LD|BPF_IMM,
-		[BPF_S_LDX_W_LEN]	= BPF_LDX|BPF_W|BPF_LEN,
-		[BPF_S_LDX_B_MSH]	= BPF_LDX|BPF_B|BPF_MSH,
-		[BPF_S_LDX_IMM]		= BPF_LDX|BPF_IMM,
-		[BPF_S_MISC_TAX]	= BPF_MISC|BPF_TAX,
-		[BPF_S_MISC_TXA]	= BPF_MISC|BPF_TXA,
-		[BPF_S_RET_K]		= BPF_RET|BPF_K,
-		[BPF_S_RET_A]		= BPF_RET|BPF_A,
-		[BPF_S_ALU_DIV_K]	= BPF_ALU|BPF_DIV|BPF_K,
-		[BPF_S_LD_MEM]		= BPF_LD|BPF_MEM,
-		[BPF_S_LDX_MEM]		= BPF_LDX|BPF_MEM,
-		[BPF_S_ST]		= BPF_ST,
-		[BPF_S_STX]		= BPF_STX,
-		[BPF_S_JMP_JA]		= BPF_JMP|BPF_JA,
-		[BPF_S_JMP_JEQ_K]	= BPF_JMP|BPF_JEQ|BPF_K,
-		[BPF_S_JMP_JEQ_X]	= BPF_JMP|BPF_JEQ|BPF_X,
-		[BPF_S_JMP_JGE_K]	= BPF_JMP|BPF_JGE|BPF_K,
-		[BPF_S_JMP_JGE_X]	= BPF_JMP|BPF_JGE|BPF_X,
-		[BPF_S_JMP_JGT_K]	= BPF_JMP|BPF_JGT|BPF_K,
-		[BPF_S_JMP_JGT_X]	= BPF_JMP|BPF_JGT|BPF_X,
-		[BPF_S_JMP_JSET_K]	= BPF_JMP|BPF_JSET|BPF_K,
-		[BPF_S_JMP_JSET_X]	= BPF_JMP|BPF_JSET|BPF_X,
-	};
-	u16 code;
-
-	code = filt->code;
-
-	to->code = decodes[code];
-	to->jt = filt->jt;
-	to->jf = filt->jf;
-	to->k = filt->k;
-}
-
 int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
 		  unsigned int len)
 {
diff --git a/net/core/iovec.c b/net/core/iovec.c
index b61869429f4..e1ec45ab1e6 100644
--- a/net/core/iovec.c
+++ b/net/core/iovec.c
@@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 {
 	int size, ct, err;
 
-	if (m->msg_namelen) {
+	if (m->msg_name && m->msg_namelen) {
 		if (mode == VERIFY_READ) {
 			void __user *namep;
 			namep = (void __user __force *) m->msg_name;
@@ -48,10 +48,10 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 			if (err < 0)
 				return err;
 		}
-		if (m->msg_name)
-			m->msg_name = address;
+		m->msg_name = address;
 	} else {
 		m->msg_name = NULL;
+		m->msg_namelen = 0;
 	}
 
 	size = m->msg_iovlen * sizeof(struct iovec);
@@ -75,61 +75,6 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a
 }
 
 /*
- *	Copy kernel to iovec. Returns -EFAULT on error.
- */
-
-int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata,
-		      int offset, int len)
-{
-	int copy;
-	for (; len > 0; ++iov) {
-		/* Skip over the finished iovecs */
-		if (unlikely(offset >= iov->iov_len)) {
-			offset -= iov->iov_len;
-			continue;
-		}
-		copy = min_t(unsigned int, iov->iov_len - offset, len);
-		if (copy_to_user(iov->iov_base + offset, kdata, copy))
-			return -EFAULT;
-		offset = 0;
-		kdata += copy;
-		len -= copy;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_toiovecend);
-
-/*
- *	Copy iovec to kernel. Returns -EFAULT on error.
- */
-
-int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
-			int offset, int len)
-{
-	/* Skip over the finished iovecs */
-	while (offset >= iov->iov_len) {
-		offset -= iov->iov_len;
-		iov++;
-	}
-
-	while (len > 0) {
-		u8 __user *base = iov->iov_base + offset;
-		int copy = min_t(unsigned int, len, iov->iov_len - offset);
-
-		offset = 0;
-		if (copy_from_user(kdata, base, copy))
-			return -EFAULT;
-		len -= copy;
-		kdata += copy;
-		iov++;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(memcpy_fromiovecend);
-
-/*
  *	And now for the all-in-one: copy and checksum from a user iovec
  *	directly to a datagram
  *	Calls to csum_partial but the last must be in 32 bit chunks
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 32d872eec7f..ef31fef25e5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2249,7 +2249,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
 	ndm->ndm_pad1    = 0;
 	ndm->ndm_pad2    = 0;
 	ndm->ndm_flags	 = pn->flags | NTF_PROXY;
-	ndm->ndm_type	 = NDA_DST;
+	ndm->ndm_type	 = RTN_UNICAST;
 	ndm->ndm_ifindex = pn->dev->ifindex;
 	ndm->ndm_state	 = NUD_NONE;
 
@@ -3059,11 +3059,12 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
 		memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0,
 		       sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL]));
 	} else {
+		struct neigh_table *tbl = p->tbl;
 		dev_name_source = "default";
-		t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1);
-		t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1;
-		t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2;
-		t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3;
+		t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = &tbl->gc_interval;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = &tbl->gc_thresh1;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = &tbl->gc_thresh2;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = &tbl->gc_thresh3;
 	}
 
 	if (handler) {
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7c8ffd97496..85b62691f4f 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -273,7 +273,7 @@ static void cleanup_net(struct work_struct *work)
 {
 	const struct pernet_operations *ops;
 	struct net *net, *tmp;
-	LIST_HEAD(net_kill_list);
+	struct list_head net_kill_list;
 	LIST_HEAD(net_exit_list);
 
 	/* Atomically snapshot the list of namespaces to cleanup */
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 22931e1b99b..1f2a126f4ff 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -42,7 +42,7 @@ cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
 static int cgrp_css_online(struct cgroup_subsys_state *css)
 {
 	struct cgroup_cls_state *cs = css_cls_state(css);
-	struct cgroup_cls_state *parent = css_cls_state(css_parent(css));
+	struct cgroup_cls_state *parent = css_cls_state(css->parent);
 
 	if (parent)
 		cs->classid = parent->classid;
@@ -107,5 +107,5 @@ struct cgroup_subsys net_cls_cgrp_subsys = {
 	.css_online		= cgrp_css_online,
 	.css_free		= cgrp_css_free,
 	.attach			= cgrp_attach,
-	.base_cftypes		= ss_files,
+	.legacy_cftypes		= ss_files,
 };
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 3825f669147..cbd0a199bf5 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -140,7 +140,7 @@ cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
 
 static int cgrp_css_online(struct cgroup_subsys_state *css)
 {
-	struct cgroup_subsys_state *parent_css = css_parent(css);
+	struct cgroup_subsys_state *parent_css = css->parent;
 	struct net_device *dev;
 	int ret = 0;
 
@@ -185,15 +185,15 @@ static int read_priomap(struct seq_file *sf, void *v)
 	return 0;
 }
 
-static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft,
-			 char *buffer)
+static ssize_t write_priomap(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
 {
 	char devname[IFNAMSIZ + 1];
 	struct net_device *dev;
 	u32 prio;
 	int ret;
 
-	if (sscanf(buffer, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
+	if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
 		return -EINVAL;
 
 	dev = dev_get_by_name(&init_net, devname);
@@ -202,11 +202,11 @@ static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft,
 
 	rtnl_lock();
 
-	ret = netprio_set_prio(css, dev, prio);
+	ret = netprio_set_prio(of_css(of), dev, prio);
 
 	rtnl_unlock();
 	dev_put(dev);
-	return ret;
+	return ret ?: nbytes;
 }
 
 static int update_netprio(const void *v, struct file *file, unsigned n)
@@ -239,7 +239,7 @@ static struct cftype ss_files[] = {
 	{
 		.name = "ifpriomap",
 		.seq_show = read_priomap,
-		.write_string = write_priomap,
+		.write = write_priomap,
 	},
 	{ }	/* terminate */
 };
@@ -249,7 +249,7 @@ struct cgroup_subsys net_prio_cgrp_subsys = {
 	.css_online	= cgrp_css_online,
 	.css_free	= cgrp_css_free,
 	.attach		= net_prio_attach,
-	.base_cftypes	= ss_files,
+	.legacy_cftypes	= ss_files,
 };
 
 static int netprio_device_event(struct notifier_block *unused,
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 0304f981f7f..fc17a9d309a 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -573,7 +573,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 		   is_zero_ether_addr(pkt_dev->src_mac) ?
 			     pkt_dev->odev->dev_addr : pkt_dev->src_mac);
 
-	seq_printf(seq, "dst_mac: ");
+	seq_puts(seq, "dst_mac: ");
 	seq_printf(seq, "%pM\n", pkt_dev->dst_mac);
 
 	seq_printf(seq,
@@ -588,7 +588,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 
 	if (pkt_dev->nr_labels) {
 		unsigned int i;
-		seq_printf(seq, "     mpls: ");
+		seq_puts(seq, "     mpls: ");
 		for (i = 0; i < pkt_dev->nr_labels; i++)
 			seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]),
 				   i == pkt_dev->nr_labels-1 ? "\n" : ", ");
@@ -613,67 +613,67 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 	if (pkt_dev->node >= 0)
 		seq_printf(seq, "     node: %d\n", pkt_dev->node);
 
-	seq_printf(seq, "     Flags: ");
+	seq_puts(seq, "     Flags: ");
 
 	if (pkt_dev->flags & F_IPV6)
-		seq_printf(seq, "IPV6  ");
+		seq_puts(seq, "IPV6  ");
 
 	if (pkt_dev->flags & F_IPSRC_RND)
-		seq_printf(seq, "IPSRC_RND  ");
+		seq_puts(seq, "IPSRC_RND  ");
 
 	if (pkt_dev->flags & F_IPDST_RND)
-		seq_printf(seq, "IPDST_RND  ");
+		seq_puts(seq, "IPDST_RND  ");
 
 	if (pkt_dev->flags & F_TXSIZE_RND)
-		seq_printf(seq, "TXSIZE_RND  ");
+		seq_puts(seq, "TXSIZE_RND  ");
 
 	if (pkt_dev->flags & F_UDPSRC_RND)
-		seq_printf(seq, "UDPSRC_RND  ");
+		seq_puts(seq, "UDPSRC_RND  ");
 
 	if (pkt_dev->flags & F_UDPDST_RND)
-		seq_printf(seq, "UDPDST_RND  ");
+		seq_puts(seq, "UDPDST_RND  ");
 
 	if (pkt_dev->flags & F_UDPCSUM)
-		seq_printf(seq, "UDPCSUM  ");
+		seq_puts(seq, "UDPCSUM  ");
 
 	if (pkt_dev->flags & F_MPLS_RND)
-		seq_printf(seq,  "MPLS_RND  ");
+		seq_puts(seq,  "MPLS_RND  ");
 
 	if (pkt_dev->flags & F_QUEUE_MAP_RND)
-		seq_printf(seq,  "QUEUE_MAP_RND  ");
+		seq_puts(seq,  "QUEUE_MAP_RND  ");
 
 	if (pkt_dev->flags & F_QUEUE_MAP_CPU)
-		seq_printf(seq,  "QUEUE_MAP_CPU  ");
+		seq_puts(seq,  "QUEUE_MAP_CPU  ");
 
 	if (pkt_dev->cflows) {
 		if (pkt_dev->flags & F_FLOW_SEQ)
-			seq_printf(seq,  "FLOW_SEQ  "); /*in sequence flows*/
+			seq_puts(seq,  "FLOW_SEQ  "); /*in sequence flows*/
 		else
-			seq_printf(seq,  "FLOW_RND  ");
+			seq_puts(seq,  "FLOW_RND  ");
 	}
 
 #ifdef CONFIG_XFRM
 	if (pkt_dev->flags & F_IPSEC_ON) {
-		seq_printf(seq,  "IPSEC  ");
+		seq_puts(seq,  "IPSEC  ");
 		if (pkt_dev->spi)
 			seq_printf(seq, "spi:%u", pkt_dev->spi);
 	}
 #endif
 
 	if (pkt_dev->flags & F_MACSRC_RND)
-		seq_printf(seq, "MACSRC_RND  ");
+		seq_puts(seq, "MACSRC_RND  ");
 
 	if (pkt_dev->flags & F_MACDST_RND)
-		seq_printf(seq, "MACDST_RND  ");
+		seq_puts(seq, "MACDST_RND  ");
 
 	if (pkt_dev->flags & F_VID_RND)
-		seq_printf(seq, "VID_RND  ");
+		seq_puts(seq, "VID_RND  ");
 
 	if (pkt_dev->flags & F_SVID_RND)
-		seq_printf(seq, "SVID_RND  ");
+		seq_puts(seq, "SVID_RND  ");
 
 	if (pkt_dev->flags & F_NODE)
-		seq_printf(seq, "NODE_ALLOC  ");
+		seq_puts(seq, "NODE_ALLOC  ");
 
 	seq_puts(seq, "\n");
 
@@ -716,7 +716,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 	if (pkt_dev->result[0])
 		seq_printf(seq, "Result: %s\n", pkt_dev->result);
 	else
-		seq_printf(seq, "Result: Idle\n");
+		seq_puts(seq, "Result: Idle\n");
 
 	return 0;
 }
@@ -1735,14 +1735,14 @@ static int pktgen_thread_show(struct seq_file *seq, void *v)
 
 	BUG_ON(!t);
 
-	seq_printf(seq, "Running: ");
+	seq_puts(seq, "Running: ");
 
 	if_lock(t);
 	list_for_each_entry(pkt_dev, &t->if_list, list)
 		if (pkt_dev->running)
 			seq_printf(seq, "%s ", pkt_dev->odevname);
 
-	seq_printf(seq, "\nStopped: ");
+	seq_puts(seq, "\nStopped: ");
 
 	list_for_each_entry(pkt_dev, &t->if_list, list)
 		if (!pkt_dev->running)
@@ -1751,7 +1751,7 @@ static int pktgen_thread_show(struct seq_file *seq, void *v)
 	if (t->result[0])
 		seq_printf(seq, "\nResult: %s\n", t->result);
 	else
-		seq_printf(seq, "\nResult: NA\n");
+		seq_puts(seq, "\nResult: NA\n");
 
 	if_unlock(t);
 
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
index eaba0f68f86..d3027a73fd4 100644
--- a/net/core/ptp_classifier.c
+++ b/net/core/ptp_classifier.c
@@ -88,7 +88,7 @@ EXPORT_SYMBOL_GPL(ptp_classify_raw);
 
 void __init ptp_classifier_init(void)
 {
-	static struct sock_filter ptp_filter[] = {
+	static struct sock_filter ptp_filter[] __initdata = {
 		{ 0x28,  0,  0, 0x0000000c },
 		{ 0x15,  0, 12, 0x00000800 },
 		{ 0x30,  0,  0, 0x00000017 },
@@ -133,7 +133,7 @@ void __init ptp_classifier_init(void)
 		{ 0x16,  0,  0, 0x00000000 },
 		{ 0x06,  0,  0, 0x00000000 },
 	};
-	struct sock_fprog ptp_prog = {
+	struct sock_fprog_kern ptp_prog = {
 		.len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
 	};
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 2d8d8fcfa06..1063996f831 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -798,8 +798,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 		size += num_vfs *
 			(nla_total_size(sizeof(struct ifla_vf_mac)) +
 			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
-			 nla_total_size(sizeof(struct ifla_vf_tx_rate)) +
-			 nla_total_size(sizeof(struct ifla_vf_spoofchk)));
+			 nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
+			 nla_total_size(sizeof(struct ifla_vf_rate)));
 		return size;
 	} else
 		return 0;
@@ -1065,6 +1065,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			struct ifla_vf_info ivi;
 			struct ifla_vf_mac vf_mac;
 			struct ifla_vf_vlan vf_vlan;
+			struct ifla_vf_rate vf_rate;
 			struct ifla_vf_tx_rate vf_tx_rate;
 			struct ifla_vf_spoofchk vf_spoofchk;
 			struct ifla_vf_link_state vf_linkstate;
@@ -1085,6 +1086,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				break;
 			vf_mac.vf =
 				vf_vlan.vf =
+				vf_rate.vf =
 				vf_tx_rate.vf =
 				vf_spoofchk.vf =
 				vf_linkstate.vf = ivi.vf;
@@ -1092,7 +1094,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
 			vf_vlan.vlan = ivi.vlan;
 			vf_vlan.qos = ivi.qos;
-			vf_tx_rate.rate = ivi.tx_rate;
+			vf_tx_rate.rate = ivi.max_tx_rate;
+			vf_rate.min_tx_rate = ivi.min_tx_rate;
+			vf_rate.max_tx_rate = ivi.max_tx_rate;
 			vf_spoofchk.setting = ivi.spoofchk;
 			vf_linkstate.link_state = ivi.linkstate;
 			vf = nla_nest_start(skb, IFLA_VF_INFO);
@@ -1102,6 +1106,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			}
 			if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
 			    nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) ||
+			    nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate),
+				    &vf_rate) ||
 			    nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
 				    &vf_tx_rate) ||
 			    nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
@@ -1208,6 +1214,10 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 				    .len = sizeof(struct ifla_vf_tx_rate) },
 	[IFLA_VF_SPOOFCHK]	= { .type = NLA_BINARY,
 				    .len = sizeof(struct ifla_vf_spoofchk) },
+	[IFLA_VF_RATE]		= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_rate) },
+	[IFLA_VF_LINK_STATE]	= { .type = NLA_BINARY,
+				    .len = sizeof(struct ifla_vf_link_state) },
 };
 
 static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
@@ -1234,6 +1244,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	int err;
+	int hdrlen;
 
 	s_h = cb->args[0];
 	s_idx = cb->args[1];
@@ -1241,8 +1252,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
 	rcu_read_lock();
 	cb->seq = net->dev_base_seq;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	/* A hack to preserve kernel<->userspace interface.
+	 * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
+	 * However, before Linux v3.9 the code here assumed rtgenmsg and that's
+	 * what iproute2 < v3.9.0 used.
+	 * We can detect the old iproute2. Even including the IFLA_EXT_MASK
+	 * attribute, its netlink message is shorter than struct ifinfomsg.
+	 */
+	hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+	if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
@@ -1367,11 +1387,29 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
 		}
 		case IFLA_VF_TX_RATE: {
 			struct ifla_vf_tx_rate *ivt;
+			struct ifla_vf_info ivf;
 			ivt = nla_data(vf);
 			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_tx_rate)
-				err = ops->ndo_set_vf_tx_rate(dev, ivt->vf,
-							      ivt->rate);
+			if (ops->ndo_get_vf_config)
+				err = ops->ndo_get_vf_config(dev, ivt->vf,
+							     &ivf);
+			if (err)
+				break;
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_rate)
+				err = ops->ndo_set_vf_rate(dev, ivt->vf,
+							   ivf.min_tx_rate,
+							   ivt->rate);
+			break;
+		}
+		case IFLA_VF_RATE: {
+			struct ifla_vf_rate *ivt;
+			ivt = nla_data(vf);
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_rate)
+				err = ops->ndo_set_vf_rate(dev, ivt->vf,
+							   ivt->min_tx_rate,
+							   ivt->max_tx_rate);
 			break;
 		}
 		case IFLA_VF_SPOOFCHK: {
@@ -1744,7 +1782,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	ops->dellink(dev, &list_kill);
 	unregister_netdevice_many(&list_kill);
-	list_del(&list_kill);
 	return 0;
 }
 
@@ -2019,11 +2056,15 @@ replay:
 		if (ops->newlink) {
 			err = ops->newlink(net, dev, tb, data);
 			/* Drivers should call free_netdev() in ->destructor
-			 * and unregister it on failure so that device could be
-			 * finally freed in rtnl_unlock.
+			 * and unregister it on failure after registration
+			 * so that device could be finally freed in rtnl_unlock.
 			 */
-			if (err < 0)
+			if (err < 0) {
+				/* If device is not registered at all, free it now */
+				if (dev->reg_state == NETREG_UNINITIALIZED)
+					free_netdev(dev);
 				goto out;
+			}
 		} else {
 			err = register_netdevice(dev);
 			if (err < 0) {
@@ -2095,9 +2136,13 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
 	u16 min_ifinfo_dump_size = 0;
+	int hdrlen;
+
+	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
+	hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
+		 sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
 
-	if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
-			ifla_policy) >= 0) {
+	if (nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy) >= 0) {
 		if (tb[IFLA_EXT_MASK])
 			ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
 	}
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 897da56f3af..ba71212f025 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -85,31 +85,6 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
 #endif
 
 #ifdef CONFIG_INET
-__u32 secure_ip_id(__be32 daddr)
-{
-	u32 hash[MD5_DIGEST_WORDS];
-
-	net_secret_init();
-	hash[0] = (__force __u32) daddr;
-	hash[1] = net_secret[13];
-	hash[2] = net_secret[14];
-	hash[3] = net_secret[15];
-
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
-
-__u32 secure_ipv6_id(const __be32 daddr[4])
-{
-	__u32 hash[4];
-
-	net_secret_init();
-	memcpy(hash, daddr, 16);
-	md5_transform(hash, net_secret);
-
-	return hash[0];
-}
 
 __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
 				 __be16 sport, __be16 dport)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8383b2bddeb..c1a33033cbe 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -689,12 +689,15 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->ooo_okay		= old->ooo_okay;
 	new->no_fcs		= old->no_fcs;
 	new->encapsulation	= old->encapsulation;
+	new->encap_hdr_csum	= old->encap_hdr_csum;
+	new->csum_valid		= old->csum_valid;
+	new->csum_complete_sw	= old->csum_complete_sw;
 #ifdef CONFIG_XFRM
 	new->sp			= secpath_get(old->sp);
 #endif
 	memcpy(new->cb, old->cb, sizeof(old->cb));
 	new->csum		= old->csum;
-	new->local_df		= old->local_df;
+	new->ignore_df		= old->ignore_df;
 	new->pkt_type		= old->pkt_type;
 	new->ip_summed		= old->ip_summed;
 	skb_copy_queue_mapping(new, old);
@@ -951,10 +954,13 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
 EXPORT_SYMBOL(skb_copy);
 
 /**
- *	__pskb_copy	-	create copy of an sk_buff with private head.
+ *	__pskb_copy_fclone	-  create copy of an sk_buff with private head.
  *	@skb: buffer to copy
  *	@headroom: headroom of new skb
  *	@gfp_mask: allocation priority
+ *	@fclone: if true allocate the copy of the skb from the fclone
+ *	cache instead of the head cache; it is recommended to set this
+ *	to true for the cases where the copy will likely be cloned
  *
  *	Make a copy of both an &sk_buff and part of its data, located
  *	in header. Fragmented data remain shared. This is used when
@@ -964,11 +970,12 @@ EXPORT_SYMBOL(skb_copy);
  *	The returned buffer has a reference count of 1.
  */
 
-struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
+struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom,
+				   gfp_t gfp_mask, bool fclone)
 {
 	unsigned int size = skb_headlen(skb) + headroom;
-	struct sk_buff *n = __alloc_skb(size, gfp_mask,
-					skb_alloc_rx_flag(skb), NUMA_NO_NODE);
+	int flags = skb_alloc_rx_flag(skb) | (fclone ? SKB_ALLOC_FCLONE : 0);
+	struct sk_buff *n = __alloc_skb(size, gfp_mask, flags, NUMA_NO_NODE);
 
 	if (!n)
 		goto out;
@@ -1008,7 +1015,7 @@ struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
 out:
 	return n;
 }
-EXPORT_SYMBOL(__pskb_copy);
+EXPORT_SYMBOL(__pskb_copy_fclone);
 
 /**
  *	pskb_expand_head - reallocate header of &sk_buff
@@ -2881,12 +2888,14 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 	int pos;
 	int dummy;
 
+	__skb_push(head_skb, doffset);
 	proto = skb_network_protocol(head_skb, &dummy);
 	if (unlikely(!proto))
 		return ERR_PTR(-EINVAL);
 
-	csum = !!can_checksum_protocol(features, proto);
-	__skb_push(head_skb, doffset);
+	csum = !head_skb->encap_hdr_csum &&
+	    !!can_checksum_protocol(features, proto);
+
 	headroom = skb_headroom(head_skb);
 	pos = skb_headlen(head_skb);
 
@@ -2983,6 +2992,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 			nskb->csum = skb_copy_and_csum_bits(head_skb, offset,
 							    skb_put(nskb, len),
 							    len, 0);
+			SKB_GSO_CB(nskb)->csum_start =
+			    skb_headroom(nskb) + doffset;
 			continue;
 		}
 
@@ -3052,6 +3063,8 @@ perform_csum_check:
 			nskb->csum = skb_checksum(nskb, doffset,
 						  nskb->len - doffset, 0);
 			nskb->ip_summed = CHECKSUM_NONE;
+			SKB_GSO_CB(nskb)->csum_start =
+			    skb_headroom(nskb) + doffset;
 		}
 	} while ((offset += len) < head_skb->len);
 
@@ -3913,7 +3926,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->tstamp.tv64 = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->skb_iif = 0;
-	skb->local_df = 0;
+	skb->ignore_df = 0;
 	skb_dst_drop(skb);
 	skb->mark = 0;
 	secpath_reset(skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index 664ee4295b6..026e01f7027 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -784,7 +784,7 @@ set_rcvbuf:
 		break;
 
 	case SO_NO_CHECK:
-		sk->sk_no_check = valbool;
+		sk->sk_no_check_tx = valbool;
 		break;
 
 	case SO_PRIORITY:
@@ -1064,7 +1064,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_NO_CHECK:
-		v.val = sk->sk_no_check;
+		v.val = sk->sk_no_check_tx;
 		break;
 
 	case SO_PRIORITY:
diff --git a/net/core/tso.c b/net/core/tso.c
new file mode 100644
index 00000000000..8c3203c585b
--- /dev/null
+++ b/net/core/tso.c
@@ -0,0 +1,77 @@
+#include <linux/export.h>
+#include <net/ip.h>
+#include <net/tso.h>
+
+/* Calculate expected number of TX descriptors */
+int tso_count_descs(struct sk_buff *skb)
+{
+	/* The Marvell Way */
+	return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags;
+}
+EXPORT_SYMBOL(tso_count_descs);
+
+void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
+		   int size, bool is_last)
+{
+	struct iphdr *iph;
+	struct tcphdr *tcph;
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int mac_hdr_len = skb_network_offset(skb);
+
+	memcpy(hdr, skb->data, hdr_len);
+	iph = (struct iphdr *)(hdr + mac_hdr_len);
+	iph->id = htons(tso->ip_id);
+	iph->tot_len = htons(size + hdr_len - mac_hdr_len);
+	tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb));
+	tcph->seq = htonl(tso->tcp_seq);
+	tso->ip_id++;
+
+	if (!is_last) {
+		/* Clear all special flags for not last packet */
+		tcph->psh = 0;
+		tcph->fin = 0;
+		tcph->rst = 0;
+	}
+}
+EXPORT_SYMBOL(tso_build_hdr);
+
+void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size)
+{
+	tso->tcp_seq += size;
+	tso->size -= size;
+	tso->data += size;
+
+	if ((tso->size == 0) &&
+	    (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx];
+
+		/* Move to next segment */
+		tso->size = frag->size;
+		tso->data = page_address(frag->page.p) + frag->page_offset;
+		tso->next_frag_idx++;
+	}
+}
+EXPORT_SYMBOL(tso_build_data);
+
+void tso_start(struct sk_buff *skb, struct tso_t *tso)
+{
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+
+	tso->ip_id = ntohs(ip_hdr(skb)->id);
+	tso->tcp_seq = ntohl(tcp_hdr(skb)->seq);
+	tso->next_frag_idx = 0;
+
+	/* Build first data */
+	tso->size = skb_headlen(skb) - hdr_len;
+	tso->data = skb->data + hdr_len;
+	if ((tso->size == 0) &&
+	    (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx];
+
+		/* Move to next segment */
+		tso->size = frag->size;
+		tso->data = page_address(frag->page.p) + frag->page_offset;
+		tso->next_frag_idx++;
+	}
+}
+EXPORT_SYMBOL(tso_start);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 22b5d818b20..6ca645c4b48 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -1024,7 +1024,6 @@ static struct inet_protosw dccp_v4_protosw = {
 	.protocol	= IPPROTO_DCCP,
 	.prot		= &dccp_v4_prot,
 	.ops		= &inet_dccp_ops,
-	.no_check	= 0,
 	.flags		= INET_PROTOSW_ICSK,
 };
 
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index eb892b4f481..de2c1e71930 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -1084,14 +1084,15 @@ EXPORT_SYMBOL_GPL(dccp_shutdown);
 
 static inline int dccp_mib_init(void)
 {
-	return snmp_mib_init((void __percpu **)dccp_statistics,
-			     sizeof(struct dccp_mib),
-			     __alignof__(struct dccp_mib));
+	dccp_statistics = alloc_percpu(struct dccp_mib);
+	if (!dccp_statistics)
+		return -ENOMEM;
+	return 0;
 }
 
 static inline void dccp_mib_exit(void)
 {
-	snmp_mib_free((void __percpu **)dccp_statistics);
+	free_percpu(dccp_statistics);
 }
 
 static int thash_entries;
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index 607ab71b5a0..53731e45403 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -20,6 +20,7 @@
 
 /* Boundary values */
 static int		zero     = 0,
+			one      = 1,
 			u8_max   = 0xFF;
 static unsigned long	seqw_min = DCCPF_SEQ_WMIN,
 			seqw_max = 0xFFFFFFFF;		/* maximum on 32 bit */
@@ -58,7 +59,7 @@ static struct ctl_table dccp_default_table[] = {
 		.maxlen		= sizeof(sysctl_dccp_request_retries),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
+		.extra1		= &one,
 		.extra2		= &u8_max,
 	},
 	{
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 16f0b223102..1cd46a345cb 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -280,7 +280,7 @@ static ktime_t dccp_timestamp_seed;
  */
 u32 dccp_timestamp(void)
 {
-	s64 delta = ktime_us_delta(ktime_get_real(), dccp_timestamp_seed);
+	u64 delta = (u64)ktime_us_delta(ktime_get_real(), dccp_timestamp_seed);
 
 	do_div(delta, 10);
 	return delta;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 4c04848953b..ae011b46c07 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -481,7 +481,7 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
 
 	sk->sk_backlog_rcv = dn_nsp_backlog_rcv;
 	sk->sk_destruct    = dn_destruct;
-	sk->sk_no_check    = 1;
+	sk->sk_no_check_tx = 1;
 	sk->sk_family      = PF_DECnet;
 	sk->sk_protocol    = 0;
 	sk->sk_allocation  = gfp;
diff --git a/net/dns_resolver/dns_query.c b/net/dns_resolver/dns_query.c
index e7b6d53eef8..dd8696a3dbe 100644
--- a/net/dns_resolver/dns_query.c
+++ b/net/dns_resolver/dns_query.c
@@ -93,8 +93,8 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	}
 
 	if (!namelen)
-		namelen = strlen(name);
-	if (namelen < 3)
+		namelen = strnlen(name, 256);
+	if (namelen < 3 || namelen > 255)
 		return -EINVAL;
 	desclen += namelen + 1;
 
@@ -149,7 +149,9 @@ int dns_query(const char *type, const char *name, size_t namelen,
 	if (!*_result)
 		goto put;
 
-	memcpy(*_result, upayload->data, len + 1);
+	memcpy(*_result, upayload->data, len);
+	(*_result)[len] = '\0';
+
 	if (_expiry)
 		*_expiry = rkey->expiry;
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 02c0e1716f6..64c5af0a10d 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -346,7 +346,7 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent,
 		return slave_dev;
 
 	slave_dev->features = master->vlan_features;
-	SET_ETHTOOL_OPS(slave_dev, &dsa_slave_ethtool_ops);
+	slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
 	eth_hw_addr_inherit(slave_dev, master);
 	slave_dev->tx_queue_len = 0;
 
diff --git a/net/ieee802154/6lowpan_rtnl.c b/net/ieee802154/6lowpan_rtnl.c
index 0f5a69ed746..fe6bd7a7108 100644
--- a/net/ieee802154/6lowpan_rtnl.c
+++ b/net/ieee802154/6lowpan_rtnl.c
@@ -92,6 +92,7 @@ static int lowpan_header_create(struct sk_buff *skb,
 	const u8 *saddr = _saddr;
 	const u8 *daddr = _daddr;
 	struct ieee802154_addr sa, da;
+	struct ieee802154_mac_cb *cb = mac_cb_init(skb);
 
 	/* TODO:
 	 * if this package isn't ipv6 one, where should it be routed?
@@ -115,8 +116,7 @@ static int lowpan_header_create(struct sk_buff *skb,
 	 * from MAC subif of the 'dev' and 'real_dev' network devices, but
 	 * this isn't implemented in mainline yet, so currently we assign 0xff
 	 */
-	mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA;
-	mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev);
+	cb->type = IEEE802154_FC_TYPE_DATA;
 
 	/* prepare wpan address data */
 	sa.mode = IEEE802154_ADDR_LONG;
@@ -135,11 +135,10 @@ static int lowpan_header_create(struct sk_buff *skb,
 	} else {
 		da.mode = IEEE802154_ADDR_LONG;
 		da.extended_addr = ieee802154_devaddr_from_raw(daddr);
-
-		/* request acknowledgment */
-		mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ;
 	}
 
+	cb->ackreq = !lowpan_is_addr_broadcast(daddr);
+
 	return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev,
 			type, (void *)&da, (void *)&sa, 0);
 }
@@ -221,139 +220,149 @@ static int lowpan_set_address(struct net_device *dev, void *p)
 	return 0;
 }
 
-static int
-lowpan_fragment_xmit(struct sk_buff *skb, u8 *head,
-		     int mlen, int plen, int offset, int type)
+static struct sk_buff*
+lowpan_alloc_frag(struct sk_buff *skb, int size,
+		  const struct ieee802154_hdr *master_hdr)
 {
+	struct net_device *real_dev = lowpan_dev_info(skb->dev)->real_dev;
 	struct sk_buff *frag;
-	int hlen;
-
-	hlen = (type == LOWPAN_DISPATCH_FRAG1) ?
-			LOWPAN_FRAG1_HEAD_SIZE : LOWPAN_FRAGN_HEAD_SIZE;
-
-	raw_dump_inline(__func__, "6lowpan fragment header", head, hlen);
+	int rc;
+
+	frag = alloc_skb(real_dev->hard_header_len +
+			 real_dev->needed_tailroom + size,
+			 GFP_ATOMIC);
+
+	if (likely(frag)) {
+		frag->dev = real_dev;
+		frag->priority = skb->priority;
+		skb_reserve(frag, real_dev->hard_header_len);
+		skb_reset_network_header(frag);
+		*mac_cb(frag) = *mac_cb(skb);
+
+		rc = dev_hard_header(frag, real_dev, 0, &master_hdr->dest,
+				     &master_hdr->source, size);
+		if (rc < 0) {
+			kfree_skb(frag);
+			return ERR_PTR(-rc);
+		}
+	} else {
+		frag = ERR_PTR(ENOMEM);
+	}
 
-	frag = netdev_alloc_skb(skb->dev,
-				hlen + mlen + plen + IEEE802154_MFR_SIZE);
-	if (!frag)
-		return -ENOMEM;
+	return frag;
+}
 
-	frag->priority = skb->priority;
+static int
+lowpan_xmit_fragment(struct sk_buff *skb, const struct ieee802154_hdr *wpan_hdr,
+		     u8 *frag_hdr, int frag_hdrlen,
+		     int offset, int len)
+{
+	struct sk_buff *frag;
 
-	/* copy header, MFR and payload */
-	skb_put(frag, mlen);
-	skb_copy_to_linear_data(frag, skb_mac_header(skb), mlen);
+	raw_dump_inline(__func__, " fragment header", frag_hdr, frag_hdrlen);
 
-	skb_put(frag, hlen);
-	skb_copy_to_linear_data_offset(frag, mlen, head, hlen);
+	frag = lowpan_alloc_frag(skb, frag_hdrlen + len, wpan_hdr);
+	if (IS_ERR(frag))
+		return -PTR_ERR(frag);
 
-	skb_put(frag, plen);
-	skb_copy_to_linear_data_offset(frag, mlen + hlen,
-				       skb_network_header(skb) + offset, plen);
+	memcpy(skb_put(frag, frag_hdrlen), frag_hdr, frag_hdrlen);
+	memcpy(skb_put(frag, len), skb_network_header(skb) + offset, len);
 
-	raw_dump_table(__func__, " raw fragment dump", frag->data, frag->len);
+	raw_dump_table(__func__, " fragment dump", frag->data, frag->len);
 
 	return dev_queue_xmit(frag);
 }
 
 static int
-lowpan_skb_fragmentation(struct sk_buff *skb, struct net_device *dev)
+lowpan_xmit_fragmented(struct sk_buff *skb, struct net_device *dev,
+		       const struct ieee802154_hdr *wpan_hdr)
 {
-	int err;
-	u16 dgram_offset, dgram_size, payload_length, header_length,
-	    lowpan_size, frag_plen, offset;
-	__be16 tag;
-	u8 head[5];
-
-	header_length = skb->mac_len;
-	payload_length = skb->len - header_length;
-	tag = lowpan_dev_info(dev)->fragment_tag++;
-	lowpan_size = skb_network_header_len(skb);
+	u16 dgram_size, dgram_offset;
+	__be16 frag_tag;
+	u8 frag_hdr[5];
+	int frag_cap, frag_len, payload_cap, rc;
+	int skb_unprocessed, skb_offset;
+
 	dgram_size = lowpan_uncompress_size(skb, &dgram_offset) -
-		     header_length;
+		     skb->mac_len;
+	frag_tag = lowpan_dev_info(dev)->fragment_tag++;
 
-	/* first fragment header */
-	head[0] = LOWPAN_DISPATCH_FRAG1 | ((dgram_size >> 8) & 0x7);
-	head[1] = dgram_size & 0xff;
-	memcpy(head + 2, &tag, sizeof(tag));
+	frag_hdr[0] = LOWPAN_DISPATCH_FRAG1 | ((dgram_size >> 8) & 0x07);
+	frag_hdr[1] = dgram_size & 0xff;
+	memcpy(frag_hdr + 2, &frag_tag, sizeof(frag_tag));
 
-	/* calc the nearest payload length(divided to 8) for first fragment
-	 * which fits into a IEEE802154_MTU
-	 */
-	frag_plen = round_down(IEEE802154_MTU - header_length -
-			       LOWPAN_FRAG1_HEAD_SIZE - lowpan_size -
-			       IEEE802154_MFR_SIZE, 8);
-
-	err = lowpan_fragment_xmit(skb, head, header_length,
-				   frag_plen + lowpan_size, 0,
-				   LOWPAN_DISPATCH_FRAG1);
-	if (err) {
-		pr_debug("%s unable to send FRAG1 packet (tag: %d)",
-			 __func__, tag);
-		goto exit;
-	}
+	payload_cap = ieee802154_max_payload(wpan_hdr);
 
-	offset = lowpan_size + frag_plen;
-	dgram_offset += frag_plen;
+	frag_len = round_down(payload_cap - LOWPAN_FRAG1_HEAD_SIZE -
+			      skb_network_header_len(skb), 8);
 
-	/* next fragment header */
-	head[0] &= ~LOWPAN_DISPATCH_FRAG1;
-	head[0] |= LOWPAN_DISPATCH_FRAGN;
+	skb_offset = skb_network_header_len(skb);
+	skb_unprocessed = skb->len - skb->mac_len - skb_offset;
 
-	frag_plen = round_down(IEEE802154_MTU - header_length -
-			       LOWPAN_FRAGN_HEAD_SIZE - IEEE802154_MFR_SIZE, 8);
+	rc = lowpan_xmit_fragment(skb, wpan_hdr, frag_hdr,
+				  LOWPAN_FRAG1_HEAD_SIZE, 0,
+				  frag_len + skb_network_header_len(skb));
+	if (rc) {
+		pr_debug("%s unable to send FRAG1 packet (tag: %d)",
+			 __func__, frag_tag);
+		goto err;
+	}
 
-	while (payload_length - offset > 0) {
-		int len = frag_plen;
+	frag_hdr[0] &= ~LOWPAN_DISPATCH_FRAG1;
+	frag_hdr[0] |= LOWPAN_DISPATCH_FRAGN;
+	frag_cap = round_down(payload_cap - LOWPAN_FRAGN_HEAD_SIZE, 8);
 
-		head[4] = dgram_offset >> 3;
+	do {
+		dgram_offset += frag_len;
+		skb_offset += frag_len;
+		skb_unprocessed -= frag_len;
+		frag_len = min(frag_cap, skb_unprocessed);
 
-		if (payload_length - offset < len)
-			len = payload_length - offset;
+		frag_hdr[4] = dgram_offset >> 3;
 
-		err = lowpan_fragment_xmit(skb, head, header_length, len,
-					   offset, LOWPAN_DISPATCH_FRAGN);
-		if (err) {
+		rc = lowpan_xmit_fragment(skb, wpan_hdr, frag_hdr,
+					  LOWPAN_FRAGN_HEAD_SIZE, skb_offset,
+					  frag_len);
+		if (rc) {
 			pr_debug("%s unable to send a FRAGN packet. (tag: %d, offset: %d)\n",
-				 __func__, tag, offset);
-			goto exit;
+				 __func__, frag_tag, skb_offset);
+			goto err;
 		}
+	} while (skb_unprocessed > frag_cap);
 
-		offset += len;
-		dgram_offset += len;
-	}
+	consume_skb(skb);
+	return NET_XMIT_SUCCESS;
 
-exit:
-	return err;
+err:
+	kfree_skb(skb);
+	return rc;
 }
 
 static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	int err = -1;
+	struct ieee802154_hdr wpan_hdr;
+	int max_single;
 
 	pr_debug("package xmit\n");
 
-	skb->dev = lowpan_dev_info(dev)->real_dev;
-	if (skb->dev == NULL) {
-		pr_debug("ERROR: no real wpan device found\n");
-		goto error;
+	if (ieee802154_hdr_peek(skb, &wpan_hdr) < 0) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
 	}
 
-	/* Send directly if less than the MTU minus the 2 checksum bytes. */
-	if (skb->len <= IEEE802154_MTU - IEEE802154_MFR_SIZE) {
-		err = dev_queue_xmit(skb);
-		goto out;
-	}
+	max_single = ieee802154_max_payload(&wpan_hdr);
 
-	pr_debug("frame is too big, fragmentation is needed\n");
-	err = lowpan_skb_fragmentation(skb, dev);
-error:
-	dev_kfree_skb(skb);
-out:
-	if (err)
-		pr_debug("ERROR: xmit failed\n");
+	if (skb_tail_pointer(skb) - skb_network_header(skb) <= max_single) {
+		skb->dev = lowpan_dev_info(dev)->real_dev;
+		return dev_queue_xmit(skb);
+	} else {
+		netdev_tx_t rc;
+
+		pr_debug("frame is too big, fragmentation is needed\n");
+		rc = lowpan_xmit_fragmented(skb, dev, &wpan_hdr);
 
-	return (err < 0) ? NET_XMIT_DROP : err;
+		return rc < 0 ? NET_XMIT_DROP : rc;
+	}
 }
 
 static struct wpan_phy *lowpan_get_phy(const struct net_device *dev)
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index 786437bc0c0..4f0ed878019 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -21,6 +21,7 @@
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
  */
 
+#include <linux/capability.h>
 #include <linux/net.h>
 #include <linux/module.h>
 #include <linux/if_arp.h>
@@ -45,7 +46,12 @@ struct dgram_sock {
 	struct ieee802154_addr dst_addr;
 
 	unsigned int bound:1;
+	unsigned int connected:1;
 	unsigned int want_ack:1;
+	unsigned int secen:1;
+	unsigned int secen_override:1;
+	unsigned int seclevel:3;
+	unsigned int seclevel_override:1;
 };
 
 static inline struct dgram_sock *dgram_sk(const struct sock *sk)
@@ -73,10 +79,7 @@ static int dgram_init(struct sock *sk)
 {
 	struct dgram_sock *ro = dgram_sk(sk);
 
-	ro->dst_addr.mode = IEEE802154_ADDR_LONG;
-	ro->dst_addr.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
 	ro->want_ack = 1;
-	memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN);
 	return 0;
 }
 
@@ -183,6 +186,7 @@ static int dgram_connect(struct sock *sk, struct sockaddr *uaddr,
 	}
 
 	ieee802154_addr_from_sa(&ro->dst_addr, &addr->addr);
+	ro->connected = 1;
 
 out:
 	release_sock(sk);
@@ -194,10 +198,7 @@ static int dgram_disconnect(struct sock *sk, int flags)
 	struct dgram_sock *ro = dgram_sk(sk);
 
 	lock_sock(sk);
-
-	ro->dst_addr.mode = IEEE802154_ADDR_LONG;
-	memset(&ro->dst_addr.extended_addr, 0xff, IEEE802154_ADDR_LEN);
-
+	ro->connected = 0;
 	release_sock(sk);
 
 	return 0;
@@ -209,7 +210,9 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 	struct net_device *dev;
 	unsigned int mtu;
 	struct sk_buff *skb;
+	struct ieee802154_mac_cb *cb;
 	struct dgram_sock *ro = dgram_sk(sk);
+	struct ieee802154_addr dst_addr;
 	int hlen, tlen;
 	int err;
 
@@ -218,6 +221,11 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 		return -EOPNOTSUPP;
 	}
 
+	if (!ro->connected && !msg->msg_name)
+		return -EDESTADDRREQ;
+	else if (ro->connected && msg->msg_name)
+		return -EISCONN;
+
 	if (!ro->bound)
 		dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154);
 	else
@@ -249,18 +257,28 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 
 	skb_reset_network_header(skb);
 
-	mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA;
-	if (ro->want_ack)
-		mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ;
+	cb = mac_cb_init(skb);
+	cb->type = IEEE802154_FC_TYPE_DATA;
+	cb->ackreq = ro->want_ack;
+
+	if (msg->msg_name) {
+		DECLARE_SOCKADDR(struct sockaddr_ieee802154*, daddr, msg->msg_name);
 
-	mac_cb(skb)->seq = ieee802154_mlme_ops(dev)->get_dsn(dev);
-	err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &ro->dst_addr,
-			ro->bound ? &ro->src_addr : NULL, size);
+		ieee802154_addr_from_sa(&dst_addr, &daddr->addr);
+	} else {
+		dst_addr = ro->dst_addr;
+	}
+
+	cb->secen = ro->secen;
+	cb->secen_override = ro->secen_override;
+	cb->seclevel = ro->seclevel;
+	cb->seclevel_override = ro->seclevel_override;
+
+	err = dev_hard_header(skb, dev, ETH_P_IEEE802154, &dst_addr,
+			      ro->bound ? &ro->src_addr : NULL, size);
 	if (err < 0)
 		goto out_skb;
 
-	skb_reset_mac_header(skb);
-
 	err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
 	if (err < 0)
 		goto out_skb;
@@ -419,6 +437,20 @@ static int dgram_getsockopt(struct sock *sk, int level, int optname,
 	case WPAN_WANTACK:
 		val = ro->want_ack;
 		break;
+	case WPAN_SECURITY:
+		if (!ro->secen_override)
+			val = WPAN_SECURITY_DEFAULT;
+		else if (ro->secen)
+			val = WPAN_SECURITY_ON;
+		else
+			val = WPAN_SECURITY_OFF;
+		break;
+	case WPAN_SECURITY_LEVEL:
+		if (!ro->seclevel_override)
+			val = WPAN_SECURITY_LEVEL_DEFAULT;
+		else
+			val = ro->seclevel;
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -434,6 +466,7 @@ static int dgram_setsockopt(struct sock *sk, int level, int optname,
 		    char __user *optval, unsigned int optlen)
 {
 	struct dgram_sock *ro = dgram_sk(sk);
+	struct net *net = sock_net(sk);
 	int val;
 	int err = 0;
 
@@ -449,6 +482,47 @@ static int dgram_setsockopt(struct sock *sk, int level, int optname,
 	case WPAN_WANTACK:
 		ro->want_ack = !!val;
 		break;
+	case WPAN_SECURITY:
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN) &&
+		    !ns_capable(net->user_ns, CAP_NET_RAW)) {
+			err = -EPERM;
+			break;
+		}
+
+		switch (val) {
+		case WPAN_SECURITY_DEFAULT:
+			ro->secen_override = 0;
+			break;
+		case WPAN_SECURITY_ON:
+			ro->secen_override = 1;
+			ro->secen = 1;
+			break;
+		case WPAN_SECURITY_OFF:
+			ro->secen_override = 1;
+			ro->secen = 0;
+			break;
+		default:
+			err = -EINVAL;
+			break;
+		}
+		break;
+	case WPAN_SECURITY_LEVEL:
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN) &&
+		    !ns_capable(net->user_ns, CAP_NET_RAW)) {
+			err = -EPERM;
+			break;
+		}
+
+		if (val < WPAN_SECURITY_LEVEL_DEFAULT ||
+		    val > IEEE802154_SCF_SECLEVEL_ENC_MIC128) {
+			err = -EINVAL;
+		} else if (val == WPAN_SECURITY_LEVEL_DEFAULT) {
+			ro->seclevel_override = 0;
+		} else {
+			ro->seclevel_override = 1;
+			ro->seclevel = val;
+		}
+		break;
 	default:
 		err = -ENOPROTOOPT;
 		break;
diff --git a/net/ieee802154/header_ops.c b/net/ieee802154/header_ops.c
index bed42a48408..c09294e39ca 100644
--- a/net/ieee802154/header_ops.c
+++ b/net/ieee802154/header_ops.c
@@ -195,15 +195,16 @@ ieee802154_hdr_get_sechdr(const u8 *buf, struct ieee802154_sechdr *hdr)
 	return pos;
 }
 
+static int ieee802154_sechdr_lengths[4] = {
+	[IEEE802154_SCF_KEY_IMPLICIT] = 5,
+	[IEEE802154_SCF_KEY_INDEX] = 6,
+	[IEEE802154_SCF_KEY_SHORT_INDEX] = 10,
+	[IEEE802154_SCF_KEY_HW_INDEX] = 14,
+};
+
 static int ieee802154_hdr_sechdr_len(u8 sc)
 {
-	switch (IEEE802154_SCF_KEY_ID_MODE(sc)) {
-	case IEEE802154_SCF_KEY_IMPLICIT: return 5;
-	case IEEE802154_SCF_KEY_INDEX: return 6;
-	case IEEE802154_SCF_KEY_SHORT_INDEX: return 10;
-	case IEEE802154_SCF_KEY_HW_INDEX: return 14;
-	default: return -EINVAL;
-	}
+	return ieee802154_sechdr_lengths[IEEE802154_SCF_KEY_ID_MODE(sc)];
 }
 
 static int ieee802154_hdr_minlen(const struct ieee802154_hdr *hdr)
@@ -285,3 +286,40 @@ ieee802154_hdr_peek_addrs(const struct sk_buff *skb, struct ieee802154_hdr *hdr)
 	return pos;
 }
 EXPORT_SYMBOL_GPL(ieee802154_hdr_peek_addrs);
+
+int
+ieee802154_hdr_peek(const struct sk_buff *skb, struct ieee802154_hdr *hdr)
+{
+	const u8 *buf = skb_mac_header(skb);
+	int pos;
+
+	pos = ieee802154_hdr_peek_addrs(skb, hdr);
+	if (pos < 0)
+		return -EINVAL;
+
+	if (hdr->fc.security_enabled) {
+		u8 key_id_mode = IEEE802154_SCF_KEY_ID_MODE(*(buf + pos));
+		int want = pos + ieee802154_sechdr_lengths[key_id_mode];
+
+		if (buf + want > skb_tail_pointer(skb))
+			return -EINVAL;
+
+		pos += ieee802154_hdr_get_sechdr(buf + pos, &hdr->sec);
+	}
+
+	return pos;
+}
+EXPORT_SYMBOL_GPL(ieee802154_hdr_peek);
+
+int ieee802154_max_payload(const struct ieee802154_hdr *hdr)
+{
+	int hlen = ieee802154_hdr_minlen(hdr);
+
+	if (hdr->fc.security_enabled) {
+		hlen += ieee802154_sechdr_lengths[hdr->sec.key_id_mode] - 1;
+		hlen += ieee802154_sechdr_authtag_len(&hdr->sec);
+	}
+
+	return IEEE802154_MTU - hlen - IEEE802154_MFR_SIZE;
+}
+EXPORT_SYMBOL_GPL(ieee802154_max_payload);
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index 6693a5cf01c..8b83a231299 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -68,4 +68,23 @@ int ieee802154_list_iface(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb);
 int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info);
 
+int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_setparams(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_add_key(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_del_key(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_dump_keys(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int ieee802154_llsec_add_dev(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_del_dev(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_dump_devs(struct sk_buff *skb,
+			       struct netlink_callback *cb);
+int ieee802154_llsec_add_devkey(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_del_devkey(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_dump_devkeys(struct sk_buff *skb,
+				  struct netlink_callback *cb);
+int ieee802154_llsec_add_seclevel(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_del_seclevel(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_llsec_dump_seclevels(struct sk_buff *skb,
+				    struct netlink_callback *cb);
+
 #endif
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 04b20589d97..26efcf4fd2f 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -124,6 +124,26 @@ static const struct genl_ops ieee8021154_ops[] = {
 	IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface,
 			ieee802154_dump_iface),
 	IEEE802154_OP(IEEE802154_SET_MACPARAMS, ieee802154_set_macparams),
+	IEEE802154_OP(IEEE802154_LLSEC_GETPARAMS, ieee802154_llsec_getparams),
+	IEEE802154_OP(IEEE802154_LLSEC_SETPARAMS, ieee802154_llsec_setparams),
+	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_KEY, NULL,
+			ieee802154_llsec_dump_keys),
+	IEEE802154_OP(IEEE802154_LLSEC_ADD_KEY, ieee802154_llsec_add_key),
+	IEEE802154_OP(IEEE802154_LLSEC_DEL_KEY, ieee802154_llsec_del_key),
+	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEV, NULL,
+			ieee802154_llsec_dump_devs),
+	IEEE802154_OP(IEEE802154_LLSEC_ADD_DEV, ieee802154_llsec_add_dev),
+	IEEE802154_OP(IEEE802154_LLSEC_DEL_DEV, ieee802154_llsec_del_dev),
+	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_DEVKEY, NULL,
+			ieee802154_llsec_dump_devkeys),
+	IEEE802154_OP(IEEE802154_LLSEC_ADD_DEVKEY, ieee802154_llsec_add_devkey),
+	IEEE802154_OP(IEEE802154_LLSEC_DEL_DEVKEY, ieee802154_llsec_del_devkey),
+	IEEE802154_DUMP(IEEE802154_LLSEC_LIST_SECLEVEL, NULL,
+			ieee802154_llsec_dump_seclevels),
+	IEEE802154_OP(IEEE802154_LLSEC_ADD_SECLEVEL,
+		      ieee802154_llsec_add_seclevel),
+	IEEE802154_OP(IEEE802154_LLSEC_DEL_SECLEVEL,
+		      ieee802154_llsec_del_seclevel),
 };
 
 static const struct genl_multicast_group ieee802154_mcgrps[] = {
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 5d285498c0f..a3281b8bfd5 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -715,3 +715,812 @@ out:
 	dev_put(dev);
 	return rc;
 }
+
+
+
+static int
+ieee802154_llsec_parse_key_id(struct genl_info *info,
+			      struct ieee802154_llsec_key_id *desc)
+{
+	memset(desc, 0, sizeof(*desc));
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE])
+		return -EINVAL;
+
+	desc->mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]);
+
+	if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) {
+		if (!info->attrs[IEEE802154_ATTR_PAN_ID] &&
+		    !(info->attrs[IEEE802154_ATTR_SHORT_ADDR] ||
+		      info->attrs[IEEE802154_ATTR_HW_ADDR]))
+			return -EINVAL;
+
+		desc->device_addr.pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]);
+
+		if (info->attrs[IEEE802154_ATTR_SHORT_ADDR]) {
+			desc->device_addr.mode = IEEE802154_ADDR_SHORT;
+			desc->device_addr.short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]);
+		} else {
+			desc->device_addr.mode = IEEE802154_ADDR_LONG;
+			desc->device_addr.extended_addr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+		}
+	}
+
+	if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_ID])
+		return -EINVAL;
+
+	if (desc->mode == IEEE802154_SCF_KEY_SHORT_INDEX &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT])
+		return -EINVAL;
+
+	if (desc->mode == IEEE802154_SCF_KEY_HW_INDEX &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED])
+		return -EINVAL;
+
+	if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT)
+		desc->id = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_ID]);
+
+	switch (desc->mode) {
+	case IEEE802154_SCF_KEY_SHORT_INDEX:
+	{
+		u32 source = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT]);
+		desc->short_source = cpu_to_le32(source);
+		break;
+	}
+	case IEEE802154_SCF_KEY_HW_INDEX:
+		desc->extended_source = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED]);
+		break;
+	}
+
+	return 0;
+}
+
+static int
+ieee802154_llsec_fill_key_id(struct sk_buff *msg,
+			     const struct ieee802154_llsec_key_id *desc)
+{
+	if (nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_MODE, desc->mode))
+		return -EMSGSIZE;
+
+	if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) {
+		if (nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID,
+				      desc->device_addr.pan_id))
+			return -EMSGSIZE;
+
+		if (desc->device_addr.mode == IEEE802154_ADDR_SHORT &&
+		    nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR,
+				      desc->device_addr.short_addr))
+			return -EMSGSIZE;
+
+		if (desc->device_addr.mode == IEEE802154_ADDR_LONG &&
+		    nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR,
+				   desc->device_addr.extended_addr))
+			return -EMSGSIZE;
+	}
+
+	if (desc->mode != IEEE802154_SCF_KEY_IMPLICIT &&
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_ID, desc->id))
+		return -EMSGSIZE;
+
+	if (desc->mode == IEEE802154_SCF_KEY_SHORT_INDEX &&
+	    nla_put_u32(msg, IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT,
+			le32_to_cpu(desc->short_source)))
+		return -EMSGSIZE;
+
+	if (desc->mode == IEEE802154_SCF_KEY_HW_INDEX &&
+	    nla_put_hwaddr(msg, IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED,
+			   desc->extended_source))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *msg;
+	struct net_device *dev = NULL;
+	int rc = -ENOBUFS;
+	struct ieee802154_mlme_ops *ops;
+	void *hdr;
+	struct ieee802154_llsec_params params;
+
+	pr_debug("%s\n", __func__);
+
+	dev = ieee802154_nl_get_dev(info);
+	if (!dev)
+		return -ENODEV;
+
+	ops = ieee802154_mlme_ops(dev);
+	if (!ops->llsec) {
+		rc = -EOPNOTSUPP;
+		goto out_dev;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		goto out_dev;
+
+	hdr = genlmsg_put(msg, 0, info->snd_seq, &nl802154_family, 0,
+		IEEE802154_LLSEC_GETPARAMS);
+	if (!hdr)
+		goto out_free;
+
+	rc = ops->llsec->get_params(dev, &params);
+	if (rc < 0)
+		goto out_free;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_ENABLED, params.enabled) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVEL, params.out_level) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER,
+			be32_to_cpu(params.frame_counter)) ||
+	    ieee802154_llsec_fill_key_id(msg, &params.out_key))
+		goto out_free;
+
+	dev_put(dev);
+
+	return ieee802154_nl_reply(msg, info);
+out_free:
+	nlmsg_free(msg);
+out_dev:
+	dev_put(dev);
+	return rc;
+}
+
+int ieee802154_llsec_setparams(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_device *dev = NULL;
+	int rc = -EINVAL;
+	struct ieee802154_mlme_ops *ops;
+	struct ieee802154_llsec_params params;
+	int changed = 0;
+
+	pr_debug("%s\n", __func__);
+
+	dev = ieee802154_nl_get_dev(info);
+	if (!dev)
+		return -ENODEV;
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_ENABLED] &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE] &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL])
+		goto out;
+
+	ops = ieee802154_mlme_ops(dev);
+	if (!ops->llsec) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL] &&
+	    nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) > 7)
+		goto out;
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_ENABLED]) {
+		params.enabled = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_ENABLED]);
+		changed |= IEEE802154_LLSEC_PARAM_ENABLED;
+	}
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]) {
+		if (ieee802154_llsec_parse_key_id(info, &params.out_key))
+			goto out;
+
+		changed |= IEEE802154_LLSEC_PARAM_OUT_KEY;
+	}
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]) {
+		params.out_level = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVEL]);
+		changed |= IEEE802154_LLSEC_PARAM_OUT_LEVEL;
+	}
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]) {
+		u32 fc = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]);
+
+		params.frame_counter = cpu_to_be32(fc);
+		changed |= IEEE802154_LLSEC_PARAM_FRAME_COUNTER;
+	}
+
+	rc = ops->llsec->set_params(dev, &params, changed);
+
+	dev_put(dev);
+
+	return rc;
+out:
+	dev_put(dev);
+	return rc;
+}
+
+
+
+struct llsec_dump_data {
+	struct sk_buff *skb;
+	int s_idx, s_idx2;
+	int portid;
+	int nlmsg_seq;
+	struct net_device *dev;
+	struct ieee802154_mlme_ops *ops;
+	struct ieee802154_llsec_table *table;
+};
+
+static int
+ieee802154_llsec_dump_table(struct sk_buff *skb, struct netlink_callback *cb,
+			    int (*step)(struct llsec_dump_data*))
+{
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	struct llsec_dump_data data;
+	int idx = 0;
+	int first_dev = cb->args[0];
+	int rc;
+
+	for_each_netdev(net, dev) {
+		if (idx < first_dev || dev->type != ARPHRD_IEEE802154)
+			goto skip;
+
+		data.ops = ieee802154_mlme_ops(dev);
+		if (!data.ops->llsec)
+			goto skip;
+
+		data.skb = skb;
+		data.s_idx = cb->args[1];
+		data.s_idx2 = cb->args[2];
+		data.dev = dev;
+		data.portid = NETLINK_CB(cb->skb).portid;
+		data.nlmsg_seq = cb->nlh->nlmsg_seq;
+
+		data.ops->llsec->lock_table(dev);
+		data.ops->llsec->get_table(data.dev, &data.table);
+		rc = step(&data);
+		data.ops->llsec->unlock_table(dev);
+
+		if (rc < 0)
+			break;
+
+skip:
+		idx++;
+	}
+	cb->args[0] = idx;
+
+	return skb->len;
+}
+
+static int
+ieee802154_nl_llsec_change(struct sk_buff *skb, struct genl_info *info,
+			   int (*fn)(struct net_device*, struct genl_info*))
+{
+	struct net_device *dev = NULL;
+	int rc = -EINVAL;
+
+	dev = ieee802154_nl_get_dev(info);
+	if (!dev)
+		return -ENODEV;
+
+	if (!ieee802154_mlme_ops(dev)->llsec)
+		rc = -EOPNOTSUPP;
+	else
+		rc = fn(dev, info);
+
+	dev_put(dev);
+	return rc;
+}
+
+
+
+static int
+ieee802154_llsec_parse_key(struct genl_info *info,
+			   struct ieee802154_llsec_key *key)
+{
+	u8 frames;
+	u32 commands[256 / 32];
+
+	memset(key, 0, sizeof(*key));
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_BYTES])
+		return -EINVAL;
+
+	frames = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES]);
+	if ((frames & BIT(IEEE802154_FC_TYPE_MAC_CMD)) &&
+	    !info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS])
+		return -EINVAL;
+
+	if (info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS]) {
+		nla_memcpy(commands,
+			   info->attrs[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS],
+			   256 / 8);
+
+		if (commands[0] || commands[1] || commands[2] || commands[3] ||
+		    commands[4] || commands[5] || commands[6] ||
+		    commands[7] >= BIT(IEEE802154_CMD_GTS_REQ + 1))
+			return -EINVAL;
+
+		key->cmd_frame_ids = commands[7];
+	}
+
+	key->frame_types = frames;
+
+	nla_memcpy(key->key, info->attrs[IEEE802154_ATTR_LLSEC_KEY_BYTES],
+		   IEEE802154_LLSEC_KEY_SIZE);
+
+	return 0;
+}
+
+static int llsec_add_key(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_key key;
+	struct ieee802154_llsec_key_id id;
+
+	if (ieee802154_llsec_parse_key(info, &key) ||
+	    ieee802154_llsec_parse_key_id(info, &id))
+		return -EINVAL;
+
+	return ops->llsec->add_key(dev, &id, &key);
+}
+
+int ieee802154_llsec_add_key(struct sk_buff *skb, struct genl_info *info)
+{
+	if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) !=
+	    (NLM_F_CREATE | NLM_F_EXCL))
+		return -EINVAL;
+
+	return ieee802154_nl_llsec_change(skb, info, llsec_add_key);
+}
+
+static int llsec_remove_key(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_key_id id;
+
+	if (ieee802154_llsec_parse_key_id(info, &id))
+		return -EINVAL;
+
+	return ops->llsec->del_key(dev, &id);
+}
+
+int ieee802154_llsec_del_key(struct sk_buff *skb, struct genl_info *info)
+{
+	return ieee802154_nl_llsec_change(skb, info, llsec_remove_key);
+}
+
+static int
+ieee802154_nl_fill_key(struct sk_buff *msg, u32 portid, u32 seq,
+		       const struct ieee802154_llsec_key_entry *key,
+		       const struct net_device *dev)
+{
+	void *hdr;
+	u32 commands[256 / 32];
+
+	hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI,
+			  IEEE802154_LLSEC_LIST_KEY);
+	if (!hdr)
+		goto out;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    ieee802154_llsec_fill_key_id(msg, &key->id) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES,
+		       key->key->frame_types))
+		goto nla_put_failure;
+
+	if (key->key->frame_types & BIT(IEEE802154_FC_TYPE_MAC_CMD)) {
+		memset(commands, 0, sizeof(commands));
+		commands[7] = key->key->cmd_frame_ids;
+		if (nla_put(msg, IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS,
+			    sizeof(commands), commands))
+			goto nla_put_failure;
+	}
+
+	if (nla_put(msg, IEEE802154_ATTR_LLSEC_KEY_BYTES,
+		    IEEE802154_LLSEC_KEY_SIZE, key->key->key))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+out:
+	return -EMSGSIZE;
+}
+
+static int llsec_iter_keys(struct llsec_dump_data *data)
+{
+	struct ieee802154_llsec_key_entry *pos;
+	int rc = 0, idx = 0;
+
+	list_for_each_entry(pos, &data->table->keys, list) {
+		if (idx++ < data->s_idx)
+			continue;
+
+		if (ieee802154_nl_fill_key(data->skb, data->portid,
+					   data->nlmsg_seq, pos, data->dev)) {
+			rc = -EMSGSIZE;
+			break;
+		}
+
+		data->s_idx++;
+	}
+
+	return rc;
+}
+
+int ieee802154_llsec_dump_keys(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return ieee802154_llsec_dump_table(skb, cb, llsec_iter_keys);
+}
+
+
+
+static int
+llsec_parse_dev(struct genl_info *info,
+		struct ieee802154_llsec_device *dev)
+{
+	memset(dev, 0, sizeof(*dev));
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] ||
+	    !info->attrs[IEEE802154_ATTR_HW_ADDR] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE] ||
+	    (!!info->attrs[IEEE802154_ATTR_PAN_ID] !=
+	     !!info->attrs[IEEE802154_ATTR_SHORT_ADDR]))
+		return -EINVAL;
+
+	if (info->attrs[IEEE802154_ATTR_PAN_ID]) {
+		dev->pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]);
+		dev->short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]);
+	} else {
+		dev->short_addr = cpu_to_le16(IEEE802154_ADDR_UNDEF);
+	}
+
+	dev->hwaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+	dev->frame_counter = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]);
+	dev->seclevel_exempt = !!nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]);
+	dev->key_mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE]);
+
+	if (dev->key_mode >= __IEEE802154_LLSEC_DEVKEY_MAX)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int llsec_add_dev(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_device desc;
+
+	if (llsec_parse_dev(info, &desc))
+		return -EINVAL;
+
+	return ops->llsec->add_dev(dev, &desc);
+}
+
+int ieee802154_llsec_add_dev(struct sk_buff *skb, struct genl_info *info)
+{
+	if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) !=
+	    (NLM_F_CREATE | NLM_F_EXCL))
+		return -EINVAL;
+
+	return ieee802154_nl_llsec_change(skb, info, llsec_add_dev);
+}
+
+static int llsec_del_dev(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	__le64 devaddr;
+
+	if (!info->attrs[IEEE802154_ATTR_HW_ADDR])
+		return -EINVAL;
+
+	devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+
+	return ops->llsec->del_dev(dev, devaddr);
+}
+
+int ieee802154_llsec_del_dev(struct sk_buff *skb, struct genl_info *info)
+{
+	return ieee802154_nl_llsec_change(skb, info, llsec_del_dev);
+}
+
+static int
+ieee802154_nl_fill_dev(struct sk_buff *msg, u32 portid, u32 seq,
+		       const struct ieee802154_llsec_device *desc,
+		       const struct net_device *dev)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI,
+			  IEEE802154_LLSEC_LIST_DEV);
+	if (!hdr)
+		goto out;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, desc->pan_id) ||
+	    nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR,
+			      desc->short_addr) ||
+	    nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, desc->hwaddr) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER,
+			desc->frame_counter) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_OVERRIDE,
+		       desc->seclevel_exempt) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_KEY_MODE, desc->key_mode))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+out:
+	return -EMSGSIZE;
+}
+
+static int llsec_iter_devs(struct llsec_dump_data *data)
+{
+	struct ieee802154_llsec_device *pos;
+	int rc = 0, idx = 0;
+
+	list_for_each_entry(pos, &data->table->devices, list) {
+		if (idx++ < data->s_idx)
+			continue;
+
+		if (ieee802154_nl_fill_dev(data->skb, data->portid,
+					   data->nlmsg_seq, pos, data->dev)) {
+			rc = -EMSGSIZE;
+			break;
+		}
+
+		data->s_idx++;
+	}
+
+	return rc;
+}
+
+int ieee802154_llsec_dump_devs(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return ieee802154_llsec_dump_table(skb, cb, llsec_iter_devs);
+}
+
+
+
+static int llsec_add_devkey(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_device_key key;
+	__le64 devaddr;
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] ||
+	    !info->attrs[IEEE802154_ATTR_HW_ADDR] ||
+	    ieee802154_llsec_parse_key_id(info, &key.key_id))
+		return -EINVAL;
+
+	devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+	key.frame_counter = nla_get_u32(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_COUNTER]);
+
+	return ops->llsec->add_devkey(dev, devaddr, &key);
+}
+
+int ieee802154_llsec_add_devkey(struct sk_buff *skb, struct genl_info *info)
+{
+	if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) !=
+	    (NLM_F_CREATE | NLM_F_EXCL))
+		return -EINVAL;
+
+	return ieee802154_nl_llsec_change(skb, info, llsec_add_devkey);
+}
+
+static int llsec_del_devkey(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_device_key key;
+	__le64 devaddr;
+
+	if (!info->attrs[IEEE802154_ATTR_HW_ADDR] ||
+	    ieee802154_llsec_parse_key_id(info, &key.key_id))
+		return -EINVAL;
+
+	devaddr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
+
+	return ops->llsec->del_devkey(dev, devaddr, &key);
+}
+
+int ieee802154_llsec_del_devkey(struct sk_buff *skb, struct genl_info *info)
+{
+	return ieee802154_nl_llsec_change(skb, info, llsec_del_devkey);
+}
+
+static int
+ieee802154_nl_fill_devkey(struct sk_buff *msg, u32 portid, u32 seq,
+			  __le64 devaddr,
+			  const struct ieee802154_llsec_device_key *devkey,
+			  const struct net_device *dev)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI,
+			  IEEE802154_LLSEC_LIST_DEVKEY);
+	if (!hdr)
+		goto out;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    nla_put_hwaddr(msg, IEEE802154_ATTR_HW_ADDR, devaddr) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER,
+			devkey->frame_counter) ||
+	    ieee802154_llsec_fill_key_id(msg, &devkey->key_id))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+out:
+	return -EMSGSIZE;
+}
+
+static int llsec_iter_devkeys(struct llsec_dump_data *data)
+{
+	struct ieee802154_llsec_device *dpos;
+	struct ieee802154_llsec_device_key *kpos;
+	int rc = 0, idx = 0, idx2;
+
+	list_for_each_entry(dpos, &data->table->devices, list) {
+		if (idx++ < data->s_idx)
+			continue;
+
+		idx2 = 0;
+
+		list_for_each_entry(kpos, &dpos->keys, list) {
+			if (idx2++ < data->s_idx2)
+				continue;
+
+			if (ieee802154_nl_fill_devkey(data->skb, data->portid,
+						      data->nlmsg_seq,
+						      dpos->hwaddr, kpos,
+						      data->dev)) {
+				return rc = -EMSGSIZE;
+			}
+
+			data->s_idx2++;
+		}
+
+		data->s_idx++;
+	}
+
+	return rc;
+}
+
+int ieee802154_llsec_dump_devkeys(struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	return ieee802154_llsec_dump_table(skb, cb, llsec_iter_devkeys);
+}
+
+
+
+static int
+llsec_parse_seclevel(struct genl_info *info,
+		     struct ieee802154_llsec_seclevel *sl)
+{
+	memset(sl, 0, sizeof(*sl));
+
+	if (!info->attrs[IEEE802154_ATTR_LLSEC_FRAME_TYPE] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_SECLEVELS] ||
+	    !info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE])
+		return -EINVAL;
+
+	sl->frame_type = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_FRAME_TYPE]);
+	if (sl->frame_type == IEEE802154_FC_TYPE_MAC_CMD) {
+		if (!info->attrs[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID])
+			return -EINVAL;
+
+		sl->cmd_frame_id = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID]);
+	}
+
+	sl->sec_levels = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_SECLEVELS]);
+	sl->device_override = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE]);
+
+	return 0;
+}
+
+static int llsec_add_seclevel(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_seclevel sl;
+
+	if (llsec_parse_seclevel(info, &sl))
+		return -EINVAL;
+
+	return ops->llsec->add_seclevel(dev, &sl);
+}
+
+int ieee802154_llsec_add_seclevel(struct sk_buff *skb, struct genl_info *info)
+{
+	if ((info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) !=
+	    (NLM_F_CREATE | NLM_F_EXCL))
+		return -EINVAL;
+
+	return ieee802154_nl_llsec_change(skb, info, llsec_add_seclevel);
+}
+
+static int llsec_del_seclevel(struct net_device *dev, struct genl_info *info)
+{
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	struct ieee802154_llsec_seclevel sl;
+
+	if (llsec_parse_seclevel(info, &sl))
+		return -EINVAL;
+
+	return ops->llsec->del_seclevel(dev, &sl);
+}
+
+int ieee802154_llsec_del_seclevel(struct sk_buff *skb, struct genl_info *info)
+{
+	return ieee802154_nl_llsec_change(skb, info, llsec_del_seclevel);
+}
+
+static int
+ieee802154_nl_fill_seclevel(struct sk_buff *msg, u32 portid, u32 seq,
+			    const struct ieee802154_llsec_seclevel *sl,
+			    const struct net_device *dev)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, 0, seq, &nl802154_family, NLM_F_MULTI,
+			  IEEE802154_LLSEC_LIST_SECLEVEL);
+	if (!hdr)
+		goto out;
+
+	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
+	    nla_put_u32(msg, IEEE802154_ATTR_DEV_INDEX, dev->ifindex) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_FRAME_TYPE, sl->frame_type) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVELS, sl->sec_levels) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_DEV_OVERRIDE,
+		       sl->device_override))
+		goto nla_put_failure;
+
+	if (sl->frame_type == IEEE802154_FC_TYPE_MAC_CMD &&
+	    nla_put_u8(msg, IEEE802154_ATTR_LLSEC_CMD_FRAME_ID,
+		       sl->cmd_frame_id))
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+out:
+	return -EMSGSIZE;
+}
+
+static int llsec_iter_seclevels(struct llsec_dump_data *data)
+{
+	struct ieee802154_llsec_seclevel *pos;
+	int rc = 0, idx = 0;
+
+	list_for_each_entry(pos, &data->table->security_levels, list) {
+		if (idx++ < data->s_idx)
+			continue;
+
+		if (ieee802154_nl_fill_seclevel(data->skb, data->portid,
+						data->nlmsg_seq, pos,
+						data->dev)) {
+			rc = -EMSGSIZE;
+			break;
+		}
+
+		data->s_idx++;
+	}
+
+	return rc;
+}
+
+int ieee802154_llsec_dump_seclevels(struct sk_buff *skb,
+				    struct netlink_callback *cb)
+{
+	return ieee802154_llsec_dump_table(skb, cb, llsec_iter_seclevels);
+}
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index fd7be5e45ce..3a703ab8834 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -62,5 +62,21 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_CSMA_MAX_BE] = { .type = NLA_U8, },
 
 	[IEEE802154_ATTR_FRAME_RETRIES] = { .type = NLA_S8, },
+
+	[IEEE802154_ATTR_LLSEC_ENABLED] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_SECLEVEL] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_KEY_MODE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_KEY_SOURCE_SHORT] = { .type = NLA_U32, },
+	[IEEE802154_ATTR_LLSEC_KEY_SOURCE_EXTENDED] = { .type = NLA_HW_ADDR, },
+	[IEEE802154_ATTR_LLSEC_KEY_ID] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_FRAME_COUNTER] = { .type = NLA_U32 },
+	[IEEE802154_ATTR_LLSEC_KEY_BYTES] = { .len = 16, },
+	[IEEE802154_ATTR_LLSEC_KEY_USAGE_FRAME_TYPES] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_KEY_USAGE_COMMANDS] = { .len = 258 / 8 },
+	[IEEE802154_ATTR_LLSEC_FRAME_TYPE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_CMD_FRAME_ID] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_SECLEVELS] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE] = { .type = NLA_U8, },
 };
 
diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c
index ef2d54372b1..6f1428c4870 100644
--- a/net/ieee802154/reassembly.c
+++ b/net/ieee802154/reassembly.c
@@ -36,7 +36,7 @@ struct lowpan_frag_info {
 	u8 d_offset;
 };
 
-struct lowpan_frag_info *lowpan_cb(struct sk_buff *skb)
+static struct lowpan_frag_info *lowpan_cb(struct sk_buff *skb)
 {
 	return (struct lowpan_frag_info *)skb->cb;
 }
@@ -120,6 +120,8 @@ fq_find(struct net *net, const struct lowpan_frag_info *frag_info,
 	struct inet_frag_queue *q;
 	struct lowpan_create_arg arg;
 	unsigned int hash;
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
 
 	arg.tag = frag_info->d_tag;
 	arg.d_size = frag_info->d_size;
@@ -129,7 +131,7 @@ fq_find(struct net *net, const struct lowpan_frag_info *frag_info,
 	read_lock(&lowpan_frags.lock);
 	hash = lowpan_hash_frag(frag_info->d_tag, frag_info->d_size, src, dst);
 
-	q = inet_frag_find(&net->ieee802154_lowpan.frags,
+	q = inet_frag_find(&ieee802154_lowpan->frags,
 			   &lowpan_frags, &arg, hash);
 	if (IS_ERR_OR_NULL(q)) {
 		inet_frag_maybe_warn_overflow(q, pr_fmt());
@@ -357,6 +359,8 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type)
 	struct net *net = dev_net(skb->dev);
 	struct lowpan_frag_info *frag_info = lowpan_cb(skb);
 	struct ieee802154_addr source, dest;
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
 	int err;
 
 	source = mac_cb(skb)->source;
@@ -366,10 +370,10 @@ int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type)
 	if (err < 0)
 		goto err;
 
-	if (frag_info->d_size > net->ieee802154_lowpan.max_dsize)
+	if (frag_info->d_size > ieee802154_lowpan->max_dsize)
 		goto err;
 
-	inet_frag_evictor(&net->ieee802154_lowpan.frags, &lowpan_frags, false);
+	inet_frag_evictor(&ieee802154_lowpan->frags, &lowpan_frags, false);
 
 	fq = fq_find(net, frag_info, &source, &dest);
 	if (fq != NULL) {
@@ -436,6 +440,8 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net)
 {
 	struct ctl_table *table;
 	struct ctl_table_header *hdr;
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
 
 	table = lowpan_frags_ns_ctl_table;
 	if (!net_eq(net, &init_net)) {
@@ -444,10 +450,10 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net)
 		if (table == NULL)
 			goto err_alloc;
 
-		table[0].data = &net->ieee802154_lowpan.frags.high_thresh;
-		table[1].data = &net->ieee802154_lowpan.frags.low_thresh;
-		table[2].data = &net->ieee802154_lowpan.frags.timeout;
-		table[3].data = &net->ieee802154_lowpan.max_dsize;
+		table[0].data = &ieee802154_lowpan->frags.high_thresh;
+		table[1].data = &ieee802154_lowpan->frags.low_thresh;
+		table[2].data = &ieee802154_lowpan->frags.timeout;
+		table[3].data = &ieee802154_lowpan->max_dsize;
 
 		/* Don't export sysctls to unprivileged users */
 		if (net->user_ns != &init_user_ns)
@@ -458,7 +464,7 @@ static int __net_init lowpan_frags_ns_sysctl_register(struct net *net)
 	if (hdr == NULL)
 		goto err_reg;
 
-	net->ieee802154_lowpan.sysctl.frags_hdr = hdr;
+	ieee802154_lowpan->sysctl.frags_hdr = hdr;
 	return 0;
 
 err_reg:
@@ -471,9 +477,11 @@ err_alloc:
 static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net)
 {
 	struct ctl_table *table;
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
 
-	table = net->ieee802154_lowpan.sysctl.frags_hdr->ctl_table_arg;
-	unregister_net_sysctl_table(net->ieee802154_lowpan.sysctl.frags_hdr);
+	table = ieee802154_lowpan->sysctl.frags_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(ieee802154_lowpan->sysctl.frags_hdr);
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
@@ -514,20 +522,26 @@ static inline void lowpan_frags_sysctl_unregister(void)
 
 static int __net_init lowpan_frags_init_net(struct net *net)
 {
-	net->ieee802154_lowpan.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
-	net->ieee802154_lowpan.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
-	net->ieee802154_lowpan.frags.timeout = IPV6_FRAG_TIMEOUT;
-	net->ieee802154_lowpan.max_dsize = 0xFFFF;
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
 
-	inet_frags_init_net(&net->ieee802154_lowpan.frags);
+	ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+	ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH;
+	ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;
+	ieee802154_lowpan->max_dsize = 0xFFFF;
+
+	inet_frags_init_net(&ieee802154_lowpan->frags);
 
 	return lowpan_frags_ns_sysctl_register(net);
 }
 
 static void __net_exit lowpan_frags_exit_net(struct net *net)
 {
+	struct netns_ieee802154_lowpan *ieee802154_lowpan =
+		net_ieee802154_lowpan(net);
+
 	lowpan_frags_ns_sysctl_unregister(net);
-	inet_frags_exit_net(&net->ieee802154_lowpan.frags, &lowpan_frags);
+	inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags);
 }
 
 static struct pernet_operations lowpan_frags_ops = {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6d6dd345bc4..d156b3c5f36 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -254,7 +254,6 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
 	struct inet_sock *inet;
 	struct proto *answer_prot;
 	unsigned char answer_flags;
-	char answer_no_check;
 	int try_loading_module = 0;
 	int err;
 
@@ -312,7 +311,6 @@ lookup_protocol:
 
 	sock->ops = answer->ops;
 	answer_prot = answer->prot;
-	answer_no_check = answer->no_check;
 	answer_flags = answer->flags;
 	rcu_read_unlock();
 
@@ -324,7 +322,6 @@ lookup_protocol:
 		goto out;
 
 	err = 0;
-	sk->sk_no_check = answer_no_check;
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
@@ -1002,7 +999,6 @@ static struct inet_protosw inetsw_array[] =
 		.protocol =   IPPROTO_TCP,
 		.prot =       &tcp_prot,
 		.ops =        &inet_stream_ops,
-		.no_check =   0,
 		.flags =      INET_PROTOSW_PERMANENT |
 			      INET_PROTOSW_ICSK,
 	},
@@ -1012,7 +1008,6 @@ static struct inet_protosw inetsw_array[] =
 		.protocol =   IPPROTO_UDP,
 		.prot =       &udp_prot,
 		.ops =        &inet_dgram_ops,
-		.no_check =   UDP_CSUM_DEFAULT,
 		.flags =      INET_PROTOSW_PERMANENT,
        },
 
@@ -1021,7 +1016,6 @@ static struct inet_protosw inetsw_array[] =
 		.protocol =   IPPROTO_ICMP,
 		.prot =       &ping_prot,
 		.ops =        &inet_dgram_ops,
-		.no_check =   UDP_CSUM_DEFAULT,
 		.flags =      INET_PROTOSW_REUSE,
        },
 
@@ -1030,7 +1024,6 @@ static struct inet_protosw inetsw_array[] =
 	       .protocol =   IPPROTO_IP,	/* wild card */
 	       .prot =       &raw_prot,
 	       .ops =        &inet_sockraw_ops,
-	       .no_check =   UDP_CSUM_DEFAULT,
 	       .flags =      INET_PROTOSW_REUSE,
        }
 };
@@ -1261,10 +1254,12 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
+		       SKB_GSO_GRE_CSUM |
 		       SKB_GSO_IPIP |
 		       SKB_GSO_SIT |
 		       SKB_GSO_TCPV6 |
 		       SKB_GSO_UDP_TUNNEL |
+		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_MPLS |
 		       0)))
 		goto out;
@@ -1434,6 +1429,9 @@ static int inet_gro_complete(struct sk_buff *skb, int nhoff)
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
+	if (skb->encapsulation)
+		skb_set_inner_network_header(skb, nhoff);
+
 	csum_replace2(&iph->check, iph->tot_len, newlen);
 	iph->tot_len = newlen;
 
@@ -1476,22 +1474,20 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
 }
 EXPORT_SYMBOL_GPL(inet_ctl_sock_create);
 
-unsigned long snmp_fold_field(void __percpu *mib[], int offt)
+unsigned long snmp_fold_field(void __percpu *mib, int offt)
 {
 	unsigned long res = 0;
-	int i, j;
+	int i;
 
-	for_each_possible_cpu(i) {
-		for (j = 0; j < SNMP_ARRAY_SZ; j++)
-			res += *(((unsigned long *) per_cpu_ptr(mib[j], i)) + offt);
-	}
+	for_each_possible_cpu(i)
+		res += *(((unsigned long *) per_cpu_ptr(mib, i)) + offt);
 	return res;
 }
 EXPORT_SYMBOL_GPL(snmp_fold_field);
 
 #if BITS_PER_LONG==32
 
-u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
+u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset)
 {
 	u64 res = 0;
 	int cpu;
@@ -1502,7 +1498,7 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
 		u64 v;
 		unsigned int start;
 
-		bhptr = per_cpu_ptr(mib[0], cpu);
+		bhptr = per_cpu_ptr(mib, cpu);
 		syncp = (struct u64_stats_sync *)(bhptr + syncp_offset);
 		do {
 			start = u64_stats_fetch_begin_irq(syncp);
@@ -1516,25 +1512,6 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
 EXPORT_SYMBOL_GPL(snmp_fold_field64);
 #endif
 
-int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align)
-{
-	BUG_ON(ptr == NULL);
-	ptr[0] = __alloc_percpu(mibsize, align);
-	if (!ptr[0])
-		return -ENOMEM;
-
-#if SNMP_ARRAY_SZ == 2
-	ptr[1] = __alloc_percpu(mibsize, align);
-	if (!ptr[1]) {
-		free_percpu(ptr[0]);
-		ptr[0] = NULL;
-		return -ENOMEM;
-	}
-#endif
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snmp_mib_init);
-
 #ifdef CONFIG_IP_MULTICAST
 static const struct net_protocol igmp_protocol = {
 	.handler =	igmp_rcv,
@@ -1570,40 +1547,30 @@ static __net_init int ipv4_mib_init_net(struct net *net)
 {
 	int i;
 
-	if (snmp_mib_init((void __percpu **)net->mib.tcp_statistics,
-			  sizeof(struct tcp_mib),
-			  __alignof__(struct tcp_mib)) < 0)
+	net->mib.tcp_statistics = alloc_percpu(struct tcp_mib);
+	if (!net->mib.tcp_statistics)
 		goto err_tcp_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.ip_statistics,
-			  sizeof(struct ipstats_mib),
-			  __alignof__(struct ipstats_mib)) < 0)
+	net->mib.ip_statistics = alloc_percpu(struct ipstats_mib);
+	if (!net->mib.ip_statistics)
 		goto err_ip_mib;
 
 	for_each_possible_cpu(i) {
 		struct ipstats_mib *af_inet_stats;
-		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[0], i);
+		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics, i);
 		u64_stats_init(&af_inet_stats->syncp);
-#if SNMP_ARRAY_SZ == 2
-		af_inet_stats = per_cpu_ptr(net->mib.ip_statistics[1], i);
-		u64_stats_init(&af_inet_stats->syncp);
-#endif
 	}
 
-	if (snmp_mib_init((void __percpu **)net->mib.net_statistics,
-			  sizeof(struct linux_mib),
-			  __alignof__(struct linux_mib)) < 0)
+	net->mib.net_statistics = alloc_percpu(struct linux_mib);
+	if (!net->mib.net_statistics)
 		goto err_net_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.udp_statistics,
-			  sizeof(struct udp_mib),
-			  __alignof__(struct udp_mib)) < 0)
+	net->mib.udp_statistics = alloc_percpu(struct udp_mib);
+	if (!net->mib.udp_statistics)
 		goto err_udp_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.udplite_statistics,
-			  sizeof(struct udp_mib),
-			  __alignof__(struct udp_mib)) < 0)
+	net->mib.udplite_statistics = alloc_percpu(struct udp_mib);
+	if (!net->mib.udplite_statistics)
 		goto err_udplite_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.icmp_statistics,
-			  sizeof(struct icmp_mib),
-			  __alignof__(struct icmp_mib)) < 0)
+	net->mib.icmp_statistics = alloc_percpu(struct icmp_mib);
+	if (!net->mib.icmp_statistics)
 		goto err_icmp_mib;
 	net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib),
 					      GFP_KERNEL);
@@ -1614,17 +1581,17 @@ static __net_init int ipv4_mib_init_net(struct net *net)
 	return 0;
 
 err_icmpmsg_mib:
-	snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
+	free_percpu(net->mib.icmp_statistics);
 err_icmp_mib:
-	snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
+	free_percpu(net->mib.udplite_statistics);
 err_udplite_mib:
-	snmp_mib_free((void __percpu **)net->mib.udp_statistics);
+	free_percpu(net->mib.udp_statistics);
 err_udp_mib:
-	snmp_mib_free((void __percpu **)net->mib.net_statistics);
+	free_percpu(net->mib.net_statistics);
 err_net_mib:
-	snmp_mib_free((void __percpu **)net->mib.ip_statistics);
+	free_percpu(net->mib.ip_statistics);
 err_ip_mib:
-	snmp_mib_free((void __percpu **)net->mib.tcp_statistics);
+	free_percpu(net->mib.tcp_statistics);
 err_tcp_mib:
 	return -ENOMEM;
 }
@@ -1632,12 +1599,12 @@ err_tcp_mib:
 static __net_exit void ipv4_mib_exit_net(struct net *net)
 {
 	kfree(net->mib.icmpmsg_statistics);
-	snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
-	snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
-	snmp_mib_free((void __percpu **)net->mib.udp_statistics);
-	snmp_mib_free((void __percpu **)net->mib.net_statistics);
-	snmp_mib_free((void __percpu **)net->mib.ip_statistics);
-	snmp_mib_free((void __percpu **)net->mib.tcp_statistics);
+	free_percpu(net->mib.icmp_statistics);
+	free_percpu(net->mib.udplite_statistics);
+	free_percpu(net->mib.udp_statistics);
+	free_percpu(net->mib.net_statistics);
+	free_percpu(net->mib.ip_statistics);
+	free_percpu(net->mib.tcp_statistics);
 }
 
 static __net_initdata struct pernet_operations ipv4_mib_ops = {
@@ -1736,13 +1703,9 @@ static int __init inet_init(void)
 
 	BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb));
 
-	sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
-	if (!sysctl_local_reserved_ports)
-		goto out;
-
 	rc = proto_register(&tcp_prot, 1);
 	if (rc)
-		goto out_free_reserved_ports;
+		goto out;
 
 	rc = proto_register(&udp_prot, 1);
 	if (rc)
@@ -1852,8 +1815,6 @@ out_unregister_udp_proto:
 	proto_unregister(&udp_prot);
 out_unregister_tcp_proto:
 	proto_unregister(&tcp_prot);
-out_free_reserved_ports:
-	kfree(sysctl_local_reserved_ports);
 	goto out;
 }
 
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 8b5134c582f..a3095fdefbe 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -86,18 +86,26 @@ out:
 }
 EXPORT_SYMBOL(ip4_datagram_connect);
 
+/* Because UDP xmit path can manipulate sk_dst_cache without holding
+ * socket lock, we need to use sk_dst_set() here,
+ * even if we own the socket lock.
+ */
 void ip4_datagram_release_cb(struct sock *sk)
 {
 	const struct inet_sock *inet = inet_sk(sk);
 	const struct ip_options_rcu *inet_opt;
 	__be32 daddr = inet->inet_daddr;
+	struct dst_entry *dst;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
-	if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0))
-		return;
-
 	rcu_read_lock();
+
+	dst = __sk_dst_get(sk);
+	if (!dst || !dst->obsolete || dst->ops->check(dst, 0)) {
+		rcu_read_unlock();
+		return;
+	}
 	inet_opt = rcu_dereference(inet->inet_opt);
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;
@@ -105,8 +113,10 @@ void ip4_datagram_release_cb(struct sock *sk)
 				   inet->inet_saddr, inet->inet_dport,
 				   inet->inet_sport, sk->sk_protocol,
 				   RT_CONN_FLAGS(sk), sk->sk_bound_dev_if);
-	if (!IS_ERR(rt))
-		__sk_dst_set(sk, &rt->dst);
+
+	dst = !IS_ERR(rt) ? &rt->dst : NULL;
+	sk_dst_set(sk, dst);
+
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(ip4_datagram_release_cb);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index bdbf68bb2e2..e9449376b58 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -106,7 +106,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
 #define IN4_ADDR_HSIZE		(1U << IN4_ADDR_HSIZE_SHIFT)
 
 static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE];
-static DEFINE_SPINLOCK(inet_addr_hash_lock);
 
 static u32 inet_addr_hash(struct net *net, __be32 addr)
 {
@@ -119,16 +118,14 @@ static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa)
 {
 	u32 hash = inet_addr_hash(net, ifa->ifa_local);
 
-	spin_lock(&inet_addr_hash_lock);
+	ASSERT_RTNL();
 	hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]);
-	spin_unlock(&inet_addr_hash_lock);
 }
 
 static void inet_hash_remove(struct in_ifaddr *ifa)
 {
-	spin_lock(&inet_addr_hash_lock);
+	ASSERT_RTNL();
 	hlist_del_init_rcu(&ifa->hash);
-	spin_unlock(&inet_addr_hash_lock);
 }
 
 /**
@@ -830,7 +827,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	ifa_existing = find_matching_ifa(ifa);
 	if (!ifa_existing) {
 		/* It would be best to check for !NLM_F_CREATE here but
-		 * userspace alreay relies on not having to provide this.
+		 * userspace already relies on not having to provide this.
 		 */
 		set_ifa_lifetime(ifa, valid_lft, prefered_lft);
 		return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid);
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 250be7421ab..0485bf7f8f0 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -68,6 +68,7 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 
 	skb_push(skb, hdr_len);
 
+	skb_reset_transport_header(skb);
 	greh = (struct gre_base_hdr *)skb->data;
 	greh->flags = tnl_flags_to_gre_flags(tpi->flags);
 	greh->protocol = tpi->proto;
@@ -84,7 +85,8 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 			ptr--;
 		}
 		if (tpi->flags&TUNNEL_CSUM &&
-		    !(skb_shinfo(skb)->gso_type & SKB_GSO_GRE)) {
+		    !(skb_shinfo(skb)->gso_type &
+		      (SKB_GSO_GRE|SKB_GSO_GRE_CSUM))) {
 			*ptr = 0;
 			*(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0,
 								 skb->len, 0));
@@ -93,28 +95,6 @@ void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi,
 }
 EXPORT_SYMBOL_GPL(gre_build_header);
 
-static __sum16 check_checksum(struct sk_buff *skb)
-{
-	__sum16 csum = 0;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		csum = csum_fold(skb->csum);
-
-		if (!csum)
-			break;
-		/* Fall through. */
-
-	case CHECKSUM_NONE:
-		skb->csum = 0;
-		csum = __skb_checksum_complete(skb);
-		skb->ip_summed = CHECKSUM_COMPLETE;
-		break;
-	}
-
-	return csum;
-}
-
 static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			    bool *csum_err)
 {
@@ -141,7 +121,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 
 	options = (__be32 *)(greh + 1);
 	if (greh->flags & GRE_CSUM) {
-		if (check_checksum(skb)) {
+		if (skb_checksum_simple_validate(skb)) {
 			*csum_err = true;
 			return -EINVAL;
 		}
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index f1d32280cb5..f0bdd47bbbc 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -42,6 +42,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
+				  SKB_GSO_GRE_CSUM |
 				  SKB_GSO_IPIP)))
 		goto out;
 
@@ -55,6 +56,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 		goto out;
 
 	csum = !!(greh->flags & GRE_CSUM);
+	if (csum)
+		skb->encap_hdr_csum = 1;
 
 	if (unlikely(!pskb_may_pull(skb, ghl)))
 		goto out;
@@ -94,10 +97,13 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 				}
 			}
 
-			greh = (struct gre_base_hdr *)(skb->data);
+			skb_reset_transport_header(skb);
+
+			greh = (struct gre_base_hdr *)
+			    skb_transport_header(skb);
 			pcsum = (__be32 *)(greh + 1);
 			*pcsum = 0;
-			*(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
+			*(__sum16 *)pcsum = gso_make_checksum(skb, 0);
 		}
 		__skb_push(skb, tnl_hlen - ghl);
 
@@ -125,10 +131,12 @@ static __sum16 gro_skb_checksum(struct sk_buff *skb)
 		csum_partial(skb->data, skb_gro_offset(skb), 0));
 	sum = csum_fold(NAPI_GRO_CB(skb)->csum);
 	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) {
-		if (unlikely(!sum))
+		if (unlikely(!sum) && !skb->csum_complete_sw)
 			netdev_rx_csum_fault(skb->dev);
-	} else
+	} else {
 		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum_complete_sw = 1;
+	}
 
 	return sum;
 }
@@ -255,6 +263,9 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff)
 	int err = -ENOENT;
 	__be16 type;
 
+	skb->encapsulation = 1;
+	skb_shinfo(skb)->gso_type = SKB_GSO_GRE;
+
 	type = greh->protocol;
 	if (greh->flags & GRE_KEY)
 		grehlen += GRE_HEADER_SECTION;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 0134663fdbc..42b7bcf8045 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -337,6 +337,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	struct sock *sk;
 	struct inet_sock *inet;
 	__be32 daddr, saddr;
+	u32 mark = IP4_REPLY_MARK(net, skb->mark);
 
 	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb))
 		return;
@@ -349,6 +350,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	icmp_param->data.icmph.checksum = 0;
 
 	inet->tos = ip_hdr(skb)->tos;
+	sk->sk_mark = mark;
 	daddr = ipc.addr = ip_hdr(skb)->saddr;
 	saddr = fib_compute_spec_dst(skb);
 	ipc.opt = NULL;
@@ -364,6 +366,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
+	fl4.flowi4_mark = mark;
 	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 	fl4.flowi4_proto = IPPROTO_ICMP;
 	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
@@ -382,7 +385,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 					struct flowi4 *fl4,
 					struct sk_buff *skb_in,
 					const struct iphdr *iph,
-					__be32 saddr, u8 tos,
+					__be32 saddr, u8 tos, u32 mark,
 					int type, int code,
 					struct icmp_bxm *param)
 {
@@ -394,6 +397,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->daddr = (param->replyopts.opt.opt.srr ?
 		      param->replyopts.opt.opt.faddr : iph->saddr);
 	fl4->saddr = saddr;
+	fl4->flowi4_mark = mark;
 	fl4->flowi4_tos = RT_TOS(tos);
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
@@ -491,6 +495,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	struct flowi4 fl4;
 	__be32 saddr;
 	u8  tos;
+	u32 mark;
 	struct net *net;
 	struct sock *sk;
 
@@ -592,6 +597,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
 					   IPTOS_PREC_INTERNETCONTROL) :
 					  iph->tos;
+	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
 	if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb_in))
 		goto out_unlock;
@@ -608,13 +614,14 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	icmp_param->skb	  = skb_in;
 	icmp_param->offset = skb_network_offset(skb_in);
 	inet_sk(sk)->tos = tos;
+	sk->sk_mark = mark;
 	ipc.addr = iph->saddr;
 	ipc.opt = &icmp_param->replyopts.opt;
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
 
-	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
+	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
 			       type, code, icmp_param);
 	if (IS_ERR(rt))
 		goto out_unlock;
@@ -732,8 +739,6 @@ static void icmp_unreach(struct sk_buff *skb)
 				/* fall through */
 			case 0:
 				info = ntohs(icmph->un.frag.mtu);
-				if (!info)
-					goto out;
 			}
 			break;
 		case ICMP_SR_FAILED:
@@ -908,16 +913,8 @@ int icmp_rcv(struct sk_buff *skb)
 
 	ICMP_INC_STATS_BH(net, ICMP_MIB_INMSGS);
 
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (!csum_fold(skb->csum))
-			break;
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = 0;
-		if (__skb_checksum_complete(skb))
-			goto csum_error;
-	}
+	if (skb_checksum_simple_validate(skb))
+		goto csum_error;
 
 	if (!pskb_pull(skb, sizeof(*icmph)))
 		goto error;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 97e4d1655d2..db710b059ba 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	pip->saddr    = fl4.saddr;
 	pip->protocol = IPPROTO_IGMP;
 	pip->tot_len  = 0;	/* filled in later */
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8 *)&pip[1])[0] = IPOPT_RA;
 	((u8 *)&pip[1])[1] = 4;
 	((u8 *)&pip[1])[2] = 0;
@@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	iph->daddr    = dst;
 	iph->saddr    = fl4.saddr;
 	iph->protocol = IPPROTO_IGMP;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 	((u8 *)&iph[1])[0] = IPOPT_RA;
 	((u8 *)&iph[1])[1] = 4;
 	((u8 *)&iph[1])[2] = 0;
@@ -988,16 +988,8 @@ int igmp_rcv(struct sk_buff *skb)
 	if (!pskb_may_pull(skb, sizeof(struct igmphdr)))
 		goto drop;
 
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (!csum_fold(skb->csum))
-			break;
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = 0;
-		if (__skb_checksum_complete(skb))
-			goto drop;
-	}
+	if (skb_checksum_simple_validate(skb))
+		goto drop;
 
 	ih = igmp_hdr(skb);
 	switch (ih->type) {
@@ -1952,6 +1944,10 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
 	rtnl_lock();
 	in_dev = ip_mc_find_dev(net, imr);
+	if (!in_dev) {
+		ret = -ENODEV;
+		goto out;
+	}
 	ifindex = imr->imr_ifindex;
 	for (imlp = &inet->mc_list;
 	     (iml = rtnl_dereference(*imlp)) != NULL;
@@ -1969,16 +1965,14 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
 
 		*imlp = iml->next_rcu;
 
-		if (in_dev)
-			ip_mc_dec_group(in_dev, group);
+		ip_mc_dec_group(in_dev, group);
 		rtnl_unlock();
 		/* decrease mem now to avoid the memleak warning */
 		atomic_sub(sizeof(*iml), &sk->sk_omem_alloc);
 		kfree_rcu(iml, rcu);
 		return 0;
 	}
-	if (!in_dev)
-		ret = -ENODEV;
+out:
 	rtnl_unlock();
 	return ret;
 }
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index a56b8e6e866..14d02ea905b 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -29,9 +29,6 @@ const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
 EXPORT_SYMBOL(inet_csk_timer_bug_msg);
 #endif
 
-unsigned long *sysctl_local_reserved_ports;
-EXPORT_SYMBOL(sysctl_local_reserved_ports);
-
 void inet_get_local_port_range(struct net *net, int *low, int *high)
 {
 	unsigned int seq;
@@ -113,7 +110,7 @@ again:
 
 		smallest_size = -1;
 		do {
-			if (inet_is_reserved_local_port(rover))
+			if (inet_is_local_reserved_port(net, rover))
 				goto next_nolock;
 			head = &hashinfo->bhash[inet_bhashfn(net, rover,
 					hashinfo->bhash_size)];
@@ -408,7 +405,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	struct net *net = sock_net(sk);
 	int flags = inet_sk_flowi_flags(sk);
 
-	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(fl4, sk->sk_bound_dev_if, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol,
 			   flags,
@@ -445,7 +442,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 
 	rcu_read_lock();
 	opt = rcu_dereference(newinet->inet_opt);
-	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(fl4, sk->sk_bound_dev_if, inet_rsk(req)->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk),
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
@@ -680,6 +677,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
 		newsk->sk_write_space = sk_stream_write_space;
 
+		newsk->sk_mark = inet_rsk(req)->ir_mark;
+
 		newicsk->icsk_retransmits = 0;
 		newicsk->icsk_backoff	  = 0;
 		newicsk->icsk_probes_out  = 0;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 8b9cf279450..43116e8c8e1 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -274,7 +274,7 @@ struct sock *__inet_lookup_established(struct net *net,
 				  const __be32 daddr, const u16 hnum,
 				  const int dif)
 {
-	INET_ADDR_COOKIE(acookie, saddr, daddr)
+	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
 	struct sock *sk;
 	const struct hlist_nulls_node *node;
@@ -327,7 +327,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	__be32 daddr = inet->inet_rcv_saddr;
 	__be32 saddr = inet->inet_daddr;
 	int dif = sk->sk_bound_dev_if;
-	INET_ADDR_COOKIE(acookie, saddr, daddr)
+	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
 	struct net *net = sock_net(sk);
 	unsigned int hash = inet_ehashfn(net, daddr, lport,
@@ -500,7 +500,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		local_bh_disable();
 		for (i = 1; i <= remaining; i++) {
 			port = low + (i + offset) % remaining;
-			if (inet_is_reserved_local_port(port))
+			if (inet_is_local_reserved_port(net, port))
 				continue;
 			head = &hinfo->bhash[inet_bhashfn(net, port,
 					hinfo->bhash_size)];
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 56cd458a1b8..bd5f5928167 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -26,20 +26,7 @@
  *  Theory of operations.
  *  We keep one entry for each peer IP address.  The nodes contains long-living
  *  information about the peer which doesn't depend on routes.
- *  At this moment this information consists only of ID field for the next
- *  outgoing IP packet.  This field is incremented with each packet as encoded
- *  in inet_getid() function (include/net/inetpeer.h).
- *  At the moment of writing this notes identifier of IP packets is generated
- *  to be unpredictable using this code only for packets subjected
- *  (actually or potentially) to defragmentation.  I.e. DF packets less than
- *  PMTU in size when local fragmentation is disabled use a constant ID and do
- *  not use this code (see ip_select_ident() in include/net/ip.h).
  *
- *  Route cache entries hold references to our nodes.
- *  New cache entries get references via lookup by destination IP address in
- *  the avl tree.  The reference is grabbed only when it's needed i.e. only
- *  when we try to output IP packet which needs an unpredictable ID (see
- *  __ip_select_ident() in net/ipv4/route.c).
  *  Nodes are removed only when reference counter goes to 0.
  *  When it's happened the node may be removed when a sufficient amount of
  *  time has been passed since its last use.  The less-recently-used entry can
@@ -62,7 +49,6 @@
  *		refcnt: atomically against modifications on other CPU;
  *		   usually under some other lock to prevent node disappearing
  *		daddr: unchangeable
- *		ip_id_count: atomic value (no lock needed)
  */
 
 static struct kmem_cache *peer_cachep __read_mostly;
@@ -120,7 +106,7 @@ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ;	/* usual time to live: 10 min
 static void inetpeer_gc_worker(struct work_struct *work)
 {
 	struct inet_peer *p, *n, *c;
-	LIST_HEAD(list);
+	struct list_head list;
 
 	spin_lock_bh(&gc_lock);
 	list_replace_init(&gc_list, &list);
@@ -497,10 +483,6 @@ relookup:
 		p->daddr = *daddr;
 		atomic_set(&p->refcnt, 1);
 		atomic_set(&p->rid, 0);
-		atomic_set(&p->ip_id_count,
-				(daddr->family == AF_INET) ?
-					secure_ip_id(daddr->addr.a4) :
-					secure_ipv6_id(daddr->addr.a6));
 		p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
 		p->rate_tokens = 0;
 		/* 60*HZ is arbitrary, but chosen enough high so that the first
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 6f111e48e11..3a83ce5efa8 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -42,7 +42,7 @@
 static bool ip_may_fragment(const struct sk_buff *skb)
 {
 	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
-		skb->local_df;
+		skb->ignore_df;
 }
 
 static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 94213c89156..9b842544aea 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -410,7 +410,7 @@ static int ipgre_open(struct net_device *dev)
 		struct flowi4 fl4;
 		struct rtable *rt;
 
-		rt = ip_route_output_gre(dev_net(dev), &fl4,
+		rt = ip_route_output_gre(t->net, &fl4,
 					 t->parms.iph.daddr,
 					 t->parms.iph.saddr,
 					 t->parms.o_key,
@@ -434,7 +434,7 @@ static int ipgre_close(struct net_device *dev)
 
 	if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) {
 		struct in_device *in_dev;
-		in_dev = inetdev_by_index(dev_net(dev), t->mlink);
+		in_dev = inetdev_by_index(t->net, t->mlink);
 		if (in_dev)
 			ip_mc_dec_group(in_dev, t->parms.iph.daddr);
 	}
@@ -478,7 +478,7 @@ static void __gre_tunnel_init(struct net_device *dev)
 	dev->needed_headroom	= LL_MAX_HEADER + sizeof(struct iphdr) + 4;
 	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr) - 4;
 
-	dev->features		|= NETIF_F_NETNS_LOCAL | GRE_FEATURES;
+	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
 
 	if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
@@ -649,6 +649,7 @@ static void ipgre_tap_setup(struct net_device *dev)
 {
 	ether_setup(dev);
 	dev->netdev_ops		= &gre_tap_netdev_ops;
+	dev->priv_flags 	|= IFF_LIVE_ADDR_CHANGE;
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index f4ab72e19af..ad382499bac 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -288,6 +288,10 @@ int ip_options_compile(struct net *net,
 			optptr++;
 			continue;
 		}
+		if (unlikely(l < 2)) {
+			pp_ptr = optptr;
+			goto error;
+		}
 		optlen = optptr[1];
 		if (optlen < 2 || optlen > l) {
 			pp_ptr = optptr;
@@ -364,7 +368,7 @@ int ip_options_compile(struct net *net,
 			}
 			if (optptr[2] <= optlen) {
 				unsigned char *timeptr = NULL;
-				if (optptr[2]+3 > optptr[1]) {
+				if (optptr[2]+3 > optlen) {
 					pp_ptr = optptr + 2;
 					goto error;
 				}
@@ -376,7 +380,7 @@ int ip_options_compile(struct net *net,
 					optptr[2] += 4;
 					break;
 				case IPOPT_TS_TSANDADDR:
-					if (optptr[2]+7 > optptr[1]) {
+					if (optptr[2]+7 > optlen) {
 						pp_ptr = optptr + 2;
 						goto error;
 					}
@@ -390,7 +394,7 @@ int ip_options_compile(struct net *net,
 					optptr[2] += 8;
 					break;
 				case IPOPT_TS_PRESPEC:
-					if (optptr[2]+7 > optptr[1]) {
+					if (optptr[2]+7 > optlen) {
 						pp_ptr = optptr + 2;
 						goto error;
 					}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a52f50187b5..8d3b6b0e985 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
 	iph->protocol = sk->sk_protocol;
-	ip_select_ident(skb, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt && opt->opt.optlen) {
 		iph->ihl += opt->opt.optlen>>2;
@@ -415,7 +415,7 @@ packet_routed:
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
 	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
-	if (ip_dont_fragment(sk, &rt->dst) && !skb->local_df)
+	if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
 		iph->frag_off = htons(IP_DF);
 	else
 		iph->frag_off = 0;
@@ -430,8 +430,7 @@ packet_routed:
 		ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
 	}
 
-	ip_select_ident_more(skb, &rt->dst, sk,
-			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1);
 
 	/* TODO : should we use skb->sk here instead of sk ? */
 	skb->priority = sk->sk_priority;
@@ -501,7 +500,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	iph = ip_hdr(skb);
 
 	mtu = ip_skb_dst_mtu(skb);
-	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) ||
+	if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) ||
 		     (IPCB(skb)->frag_max_size &&
 		      IPCB(skb)->frag_max_size > mtu))) {
 		IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
@@ -866,7 +865,7 @@ static int __ip_append_data(struct sock *sk,
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
-	maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu;
+	maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
 
 	if (cork->length + length > maxnonfragsize - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
@@ -1189,7 +1188,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
-	maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu;
+	maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
 
 	if (cork->length + size > maxnonfragsize - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
@@ -1350,10 +1349,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	 * to fragment the frame generated here. No matter, what transforms
 	 * how transforms change size of the packet, it will come out.
 	 */
-	skb->local_df = ip_sk_local_df(sk);
+	skb->ignore_df = ip_sk_ignore_df(sk);
 
 	/* DF bit is set when we want to see DF on outgoing frames.
-	 * If local_df is set too, we still allow to fragment this frame
+	 * If ignore_df is set too, we still allow to fragment this frame
 	 * locally. */
 	if (inet->pmtudisc == IP_PMTUDISC_DO ||
 	    inet->pmtudisc == IP_PMTUDISC_PROBE ||
@@ -1379,7 +1378,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
 	ip_copy_addrs(iph, fl4);
-	ip_select_ident(skb, &rt->dst, sk);
+	ip_select_ident(skb, sk);
 
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
@@ -1546,7 +1545,8 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,
 			daddr = replyopts.opt.opt.faddr;
 	}
 
-	flowi4_init_output(&fl4, arg->bound_dev_if, 0,
+	flowi4_init_output(&fl4, arg->bound_dev_if,
+			   IP4_REPLY_MARK(net, skb->mark),
 			   RT_TOS(arg->tos),
 			   RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
 			   ip_reply_arg_flowi_flags(arg),
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 2acc2337d38..6f9de61dce5 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -73,12 +73,7 @@ static void __tunnel_dst_set(struct ip_tunnel_dst *idst,
 {
 	struct dst_entry *old_dst;
 
-	if (dst) {
-		if (dst->flags & DST_NOCACHE)
-			dst = NULL;
-		else
-			dst_clone(dst);
-	}
+	dst_clone(dst);
 	old_dst = xchg((__force struct dst_entry **)&idst->dst, dst);
 	dst_release(old_dst);
 }
@@ -108,13 +103,14 @@ static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
 
 	rcu_read_lock();
 	dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst);
+	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+		dst = NULL;
 	if (dst) {
 		if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
-			rcu_read_unlock();
 			tunnel_dst_reset(t);
-			return NULL;
+			dst_release(dst);
+			dst = NULL;
 		}
-		dst_hold(dst);
 	}
 	rcu_read_unlock();
 	return (struct rtable *)dst;
@@ -173,6 +169,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (remote != t->parms.iph.daddr ||
+		    t->parms.iph.saddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -189,10 +186,11 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 	head = &itn->tunnels[hash];
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
-		if ((local != t->parms.iph.saddr &&
-		     (local != t->parms.iph.daddr ||
-		      !ipv4_is_multicast(local))) ||
-		    !(t->dev->flags & IFF_UP))
+		if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) &&
+		    (local != t->parms.iph.daddr || !ipv4_is_multicast(local)))
+			continue;
+
+		if (!(t->dev->flags & IFF_UP))
 			continue;
 
 		if (!ip_tunnel_key_match(&t->parms, flags, key))
@@ -209,6 +207,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (t->parms.i_key != key ||
+		    t->parms.iph.saddr != 0 ||
+		    t->parms.iph.daddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -268,6 +268,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
 	__be32 remote = parms->iph.daddr;
 	__be32 local = parms->iph.saddr;
 	__be32 key = parms->i_key;
+	__be16 flags = parms->i_flags;
 	int link = parms->link;
 	struct ip_tunnel *t = NULL;
 	struct hlist_head *head = ip_bucket(itn, parms);
@@ -275,9 +276,9 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
-		    key == t->parms.i_key &&
 		    link == t->parms.link &&
-		    type == t->dev->type)
+		    type == t->dev->type &&
+		    ip_tunnel_key_match(&t->parms, flags, key))
 			break;
 	}
 	return t;
@@ -395,11 +396,10 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 					  struct ip_tunnel_net *itn,
 					  struct ip_tunnel_parm *parms)
 {
-	struct ip_tunnel *nt, *fbt;
+	struct ip_tunnel *nt;
 	struct net_device *dev;
 
 	BUG_ON(!itn->fb_tunnel_dev);
-	fbt = netdev_priv(itn->fb_tunnel_dev);
 	dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
 	if (IS_ERR(dev))
 		return ERR_CAST(dev);
@@ -668,6 +668,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		dev->needed_headroom = max_headroom;
 
 	if (skb_cow_head(skb, dev->needed_headroom)) {
+		ip_rt_put(rt);
 		dev->stats.tx_dropped++;
 		kfree_skb(skb);
 		return;
@@ -747,19 +748,19 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 			goto done;
 		if (p->iph.ttl)
 			p->iph.frag_off |= htons(IP_DF);
-		if (!(p->i_flags&TUNNEL_KEY))
-			p->i_key = 0;
-		if (!(p->o_flags&TUNNEL_KEY))
-			p->o_key = 0;
+		if (!(p->i_flags & VTI_ISVTI)) {
+			if (!(p->i_flags & TUNNEL_KEY))
+				p->i_key = 0;
+			if (!(p->o_flags & TUNNEL_KEY))
+				p->o_key = 0;
+		}
 
 		t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
 
 		if (!t && (cmd == SIOCADDTUNNEL)) {
 			t = ip_tunnel_create(net, itn, p);
-			if (IS_ERR(t)) {
-				err = PTR_ERR(t);
-				break;
-			}
+			err = PTR_ERR_OR_ZERO(t);
+			break;
 		}
 		if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
 			if (t != NULL) {
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index bcf206c7900..f4c987bb7e9 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -74,7 +74,7 @@ int iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 	iph->daddr	=	dst;
 	iph->saddr	=	src;
 	iph->ttl	=	ttl;
-	__ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
+	__ip_select_ident(iph, skb_shinfo(skb)->gso_segs ?: 1);
 
 	err = ip_local_out_sk(sk, skb);
 	if (unlikely(net_xmit_eval(err)))
@@ -135,6 +135,14 @@ struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb,
 		return skb;
 	}
 
+	/* If packet is not gso and we are resolving any partial checksum,
+	 * clear encapsulation flag. This allows setting CHECKSUM_PARTIAL
+	 * on the outer header without confusing devices that implement
+	 * NETIF_F_IP_CSUM with encapsulation.
+	 */
+	if (csum_help)
+		skb->encapsulation = 0;
+
 	if (skb->ip_summed == CHECKSUM_PARTIAL && csum_help) {
 		err = skb_checksum_help(skb);
 		if (unlikely(err))
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 13ef00f1e17..b8960f3527f 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -313,7 +313,13 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			return -EINVAL;
 	}
 
-	p.i_flags |= VTI_ISVTI;
+	if (!(p.i_flags & GRE_KEY))
+		p.i_key = 0;
+	if (!(p.o_flags & GRE_KEY))
+		p.o_key = 0;
+
+	p.i_flags = VTI_ISVTI;
+
 	err = ip_tunnel_ioctl(dev, &p, cmd);
 	if (err)
 		return err;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 812b1835146..62eaa005e14 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -149,13 +149,13 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPIP, 0);
+				 t->parms.link, 0, IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPIP, 0);
 		err = 0;
 		goto out;
@@ -486,4 +486,5 @@ static void __exit ipip_fini(void)
 module_init(ipip_init);
 module_exit(ipip_fini);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ipip");
 MODULE_ALIAS_NETDEV("tunl0");
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index d84dc8d4c91..65bcaa78904 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -484,7 +484,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->type		= ARPHRD_PIMREG;
 	dev->mtu		= ETH_DATA_LEN - sizeof(struct iphdr) - 8;
 	dev->flags		= IFF_NOARP;
-	dev->netdev_ops		= &reg_vif_netdev_ops,
+	dev->netdev_ops		= &reg_vif_netdev_ops;
 	dev->destructor		= free_netdev;
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 }
@@ -1663,7 +1663,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr)
 	iph->protocol	=	IPPROTO_IPIP;
 	iph->ihl	=	5;
 	iph->tot_len	=	htons(skb->len);
-	ip_select_ident(skb, skb_dst(skb), NULL);
+	ip_select_ident(skb, NULL);
 	ip_send_check(iph);
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index ee2886126e3..f1787c04a4d 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -91,17 +91,9 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops,
 	if (nf_ct_is_untracked(ct))
 		return NF_ACCEPT;
 
-	nat = nfct_nat(ct);
-	if (!nat) {
-		/* NAT module was loaded late. */
-		if (nf_ct_is_confirmed(ct))
-			return NF_ACCEPT;
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL) {
-			pr_debug("failed to add NAT extension\n");
-			return NF_ACCEPT;
-		}
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index f40f321b41f..b8f6381c7d0 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -34,7 +34,7 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 
 	if (!err) {
 		ip_send_check(ip_hdr(skb));
-		skb->local_df = 1;
+		skb->ignore_df = 1;
 	}
 
 	return err;
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index b5b256d45e6..3964157d826 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -48,15 +48,9 @@ static unsigned int nf_nat_fn(const struct nf_hook_ops *ops,
 
 	NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)));
 
-	nat = nfct_nat(ct);
-	if (nat == NULL) {
-		/* Conntrack module was loaded late, can't add extension. */
-		if (nf_ct_is_confirmed(ct))
-			return NF_ACCEPT;
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL)
-			return NF_ACCEPT;
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index ad737fad6d8..ae0af9386f7 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -345,15 +345,15 @@ static void icmp_put(struct seq_file *seq)
 	for (i = 0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " Out%s", icmpmibmap[i].name);
 	seq_printf(seq, "\nIcmp: %lu %lu %lu",
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INMSGS),
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS),
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS));
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INMSGS),
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_INERRORS),
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_CSUMERRORS));
 	for (i = 0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
 			   atomic_long_read(ptr + icmpmibmap[i].index));
 	seq_printf(seq, " %lu %lu",
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
-		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
+		snmp_fold_field(net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
 	for (i = 0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
 			   atomic_long_read(ptr + (icmpmibmap[i].index | 0x100)));
@@ -379,7 +379,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 	BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0);
 	for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
 		seq_printf(seq, " %llu",
-			   snmp_fold_field64((void __percpu **)net->mib.ip_statistics,
+			   snmp_fold_field64(net->mib.ip_statistics,
 					     snmp4_ipstats_list[i].entry,
 					     offsetof(struct ipstats_mib, syncp)));
 
@@ -395,11 +395,11 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 		/* MaxConn field is signed, RFC 2012 */
 		if (snmp4_tcp_list[i].entry == TCP_MIB_MAXCONN)
 			seq_printf(seq, " %ld",
-				   snmp_fold_field((void __percpu **)net->mib.tcp_statistics,
+				   snmp_fold_field(net->mib.tcp_statistics,
 						   snmp4_tcp_list[i].entry));
 		else
 			seq_printf(seq, " %lu",
-				   snmp_fold_field((void __percpu **)net->mib.tcp_statistics,
+				   snmp_fold_field(net->mib.tcp_statistics,
 						   snmp4_tcp_list[i].entry));
 	}
 
@@ -410,7 +410,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nUdp:");
 	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
-			   snmp_fold_field((void __percpu **)net->mib.udp_statistics,
+			   snmp_fold_field(net->mib.udp_statistics,
 					   snmp4_udp_list[i].entry));
 
 	/* the UDP and UDP-Lite MIBs are the same */
@@ -421,7 +421,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nUdpLite:");
 	for (i = 0; snmp4_udp_list[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
-			   snmp_fold_field((void __percpu **)net->mib.udplite_statistics,
+			   snmp_fold_field(net->mib.udplite_statistics,
 					   snmp4_udp_list[i].entry));
 
 	seq_putc(seq, '\n');
@@ -458,7 +458,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nTcpExt:");
 	for (i = 0; snmp4_net_list[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
-			   snmp_fold_field((void __percpu **)net->mib.net_statistics,
+			   snmp_fold_field(net->mib.net_statistics,
 					   snmp4_net_list[i].entry));
 
 	seq_puts(seq, "\nIpExt:");
@@ -468,7 +468,7 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 	seq_puts(seq, "\nIpExt:");
 	for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
 		seq_printf(seq, " %llu",
-			   snmp_fold_field64((void __percpu **)net->mib.ip_statistics,
+			   snmp_fold_field64(net->mib.ip_statistics,
 					     snmp4_ipextstats_list[i].entry,
 					     offsetof(struct ipstats_mib, syncp)));
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index a9dbe58bdfe..2c65160565e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -389,7 +389,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		iph->check   = 0;
 		iph->tot_len = htons(length);
 		if (!iph->id)
-			ip_select_ident(skb, &rt->dst, NULL);
+			ip_select_ident(skb, NULL);
 
 		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5e676be3dae..190199851c9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -89,6 +89,7 @@
 #include <linux/rcupdate.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/jhash.h>
 #include <net/dst.h>
 #include <net/net_namespace.h>
 #include <net/protocol.h>
@@ -456,39 +457,45 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 	return neigh_create(&arp_tbl, pkey, dev);
 }
 
-/*
- * Peer allocation may fail only in serious out-of-memory conditions.  However
- * we still can generate some output.
- * Random ID selection looks a bit dangerous because we have no chances to
- * select ID being unique in a reasonable period of time.
- * But broken packet identifier may be better than no packet at all.
+#define IP_IDENTS_SZ 2048u
+struct ip_ident_bucket {
+	atomic_t	id;
+	u32		stamp32;
+};
+
+static struct ip_ident_bucket *ip_idents __read_mostly;
+
+/* In order to protect privacy, we add a perturbation to identifiers
+ * if one generator is seldom used. This makes hard for an attacker
+ * to infer how many packets were sent between two points in time.
  */
-static void ip_select_fb_ident(struct iphdr *iph)
+u32 ip_idents_reserve(u32 hash, int segs)
 {
-	static DEFINE_SPINLOCK(ip_fb_id_lock);
-	static u32 ip_fallback_id;
-	u32 salt;
+	struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
+	u32 old = ACCESS_ONCE(bucket->stamp32);
+	u32 now = (u32)jiffies;
+	u32 delta = 0;
 
-	spin_lock_bh(&ip_fb_id_lock);
-	salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
-	iph->id = htons(salt & 0xFFFF);
-	ip_fallback_id = salt;
-	spin_unlock_bh(&ip_fb_id_lock);
+	if (old != now && cmpxchg(&bucket->stamp32, old, now) == old)
+		delta = prandom_u32_max(now - old);
+
+	return atomic_add_return(segs + delta, &bucket->id) - segs;
 }
+EXPORT_SYMBOL(ip_idents_reserve);
 
-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
+void __ip_select_ident(struct iphdr *iph, int segs)
 {
-	struct net *net = dev_net(dst->dev);
-	struct inet_peer *peer;
+	static u32 ip_idents_hashrnd __read_mostly;
+	u32 hash, id;
 
-	peer = inet_getpeer_v4(net->ipv4.peers, iph->daddr, 1);
-	if (peer) {
-		iph->id = htons(inet_getid(peer, more));
-		inet_putpeer(peer);
-		return;
-	}
+	net_get_random_once(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd));
 
-	ip_select_fb_ident(iph);
+	hash = jhash_3words((__force u32)iph->daddr,
+			    (__force u32)iph->saddr,
+			    iph->protocol,
+			    ip_idents_hashrnd);
+	id = ip_idents_reserve(hash, segs);
+	iph->id = htons(id);
 }
 EXPORT_SYMBOL(__ip_select_ident);
 
@@ -993,6 +1000,9 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
 	struct flowi4 fl4;
 	struct rtable *rt;
 
+	if (!mark)
+		mark = IP4_REPLY_MARK(net, skb->mark);
+
 	__build_flow_key(&fl4, NULL, iph, oif,
 			 RT_TOS(iph->tos), protocol, mark, flow_flags);
 	rt = __ip_route_output_key(net, &fl4);
@@ -1010,6 +1020,10 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	struct rtable *rt;
 
 	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+
+	if (!fl4.flowi4_mark)
+		fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark);
+
 	rt = __ip_route_output_key(sock_net(sk), &fl4);
 	if (!IS_ERR(rt)) {
 		__ip_rt_update_pmtu(rt, &fl4, mtu);
@@ -1022,7 +1036,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	const struct iphdr *iph = (const struct iphdr *) skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
-	struct dst_entry *dst;
+	struct dst_entry *odst = NULL;
 	bool new = false;
 
 	bh_lock_sock(sk);
@@ -1030,16 +1044,17 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	if (!ip_sk_accept_pmtu(sk))
 		goto out;
 
-	rt = (struct rtable *) __sk_dst_get(sk);
+	odst = sk_dst_get(sk);
 
-	if (sock_owned_by_user(sk) || !rt) {
+	if (sock_owned_by_user(sk) || !odst) {
 		__ipv4_sk_update_pmtu(skb, sk, mtu);
 		goto out;
 	}
 
 	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
 
-	if (!__sk_dst_check(sk, 0)) {
+	rt = (struct rtable *)odst;
+	if (odst->obsolete && odst->ops->check(odst, 0) == NULL) {
 		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
 		if (IS_ERR(rt))
 			goto out;
@@ -1049,8 +1064,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 
 	__ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu);
 
-	dst = dst_check(&rt->dst, 0);
-	if (!dst) {
+	if (!dst_check(&rt->dst, 0)) {
 		if (new)
 			dst_release(&rt->dst);
 
@@ -1062,10 +1076,11 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	}
 
 	if (new)
-		__sk_dst_set(sk, &rt->dst);
+		sk_dst_set(sk, &rt->dst);
 
 out:
 	bh_unlock_sock(sk);
+	dst_release(odst);
 }
 EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
 
@@ -2704,6 +2719,12 @@ int __init ip_rt_init(void)
 {
 	int rc = 0;
 
+	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
+	if (!ip_idents)
+		panic("IP: failed to allocate ip_idents\n");
+
+	prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
 	if (!ip_rt_acct)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f2ed13c2125..c86624b36a6 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -303,6 +303,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	ireq->ir_rmt_port	= th->source;
 	ireq->ir_loc_addr	= ip_hdr(skb)->daddr;
 	ireq->ir_rmt_addr	= ip_hdr(skb)->saddr;
+	ireq->ir_mark		= inet_request_mark(sk, skb);
 	ireq->ecn_ok		= ecn_ok;
 	ireq->snd_wscale	= tcp_opt.snd_wscale;
 	ireq->sack_ok		= tcp_opt.sack_ok;
@@ -339,7 +340,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	 * hasn't changed since we received the original syn, but I see
 	 * no easy way to do this.
 	 */
-	flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark,
+	flowi4_init_output(&fl4, sk->sk_bound_dev_if, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
 			   inet_sk_flowi_flags(sk),
 			   (opt && opt->srr) ? opt->faddr : ireq->ir_rmt_addr,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 5cde8f263d4..79a007c5255 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -437,13 +437,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "ip_local_reserved_ports",
-		.data		= NULL, /* initialized in sysctl_ipv4_init */
-		.maxlen		= 65536,
-		.mode		= 0644,
-		.proc_handler	= proc_do_large_bitmap,
-	},
-	{
 		.procname	= "igmp_max_memberships",
 		.data		= &sysctl_igmp_max_memberships,
 		.maxlen		= sizeof(int),
@@ -825,6 +818,13 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= ipv4_local_port_range,
 	},
 	{
+		.procname	= "ip_local_reserved_ports",
+		.data		= &init_net.ipv4.sysctl_local_reserved_ports,
+		.maxlen		= 65536,
+		.mode		= 0644,
+		.proc_handler	= proc_do_large_bitmap,
+	},
+	{
 		.procname	= "ip_no_pmtu_disc",
 		.data		= &init_net.ipv4.sysctl_ip_no_pmtu_disc,
 		.maxlen		= sizeof(int),
@@ -838,6 +838,20 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "fwmark_reflect",
+		.data		= &init_net.ipv4.sysctl_fwmark_reflect,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "tcp_fwmark_accept",
+		.data		= &init_net.ipv4.sysctl_tcp_fwmark_accept,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{ }
 };
 
@@ -862,8 +876,14 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 	if (net->ipv4.ipv4_hdr == NULL)
 		goto err_reg;
 
+	net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL);
+	if (!net->ipv4.sysctl_local_reserved_ports)
+		goto err_ports;
+
 	return 0;
 
+err_ports:
+	unregister_net_sysctl_table(net->ipv4.ipv4_hdr);
 err_reg:
 	if (!net_eq(net, &init_net))
 		kfree(table);
@@ -875,6 +895,7 @@ static __net_exit void ipv4_sysctl_exit_net(struct net *net)
 {
 	struct ctl_table *table;
 
+	kfree(net->ipv4.sysctl_local_reserved_ports);
 	table = net->ipv4.ipv4_hdr->ctl_table_arg;
 	unregister_net_sysctl_table(net->ipv4.ipv4_hdr);
 	kfree(table);
@@ -888,16 +909,6 @@ static __net_initdata struct pernet_operations ipv4_sysctl_ops = {
 static __init int sysctl_ipv4_init(void)
 {
 	struct ctl_table_header *hdr;
-	struct ctl_table *i;
-
-	for (i = ipv4_table; i->procname; i++) {
-		if (strcmp(i->procname, "ip_local_reserved_ports") == 0) {
-			i->data = sysctl_local_reserved_ports;
-			break;
-		}
-	}
-	if (!i->procname)
-		return -EINVAL;
 
 	hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table);
 	if (hdr == NULL)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4bd6d52eeff..9d2118e5fbc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1108,7 +1108,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (unlikely(tp->repair)) {
 		if (tp->repair_queue == TCP_RECV_QUEUE) {
 			copied = tcp_send_rcvq(sk, msg, size);
-			goto out;
+			goto out_nopush;
 		}
 
 		err = -EINVAL;
@@ -1282,6 +1282,7 @@ wait_for_memory:
 out:
 	if (copied)
 		tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
+out_nopush:
 	release_sock(sk);
 	return copied + copied_syn;
 
@@ -2916,6 +2917,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 	case TCP_USER_TIMEOUT:
 		val = jiffies_to_msecs(icsk->icsk_user_timeout);
 		break;
+
+	case TCP_FASTOPEN:
+		if (icsk->icsk_accept_queue.fastopenq != NULL)
+			val = icsk->icsk_accept_queue.fastopenq->max_qlen;
+		else
+			val = 0;
+		break;
+
 	case TCP_TIMESTAMP:
 		val = tcp_time_stamp + tp->tsoffset;
 		break;
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 821846fb0a7..d5de69bc04f 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -140,13 +140,12 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 		ca->cnt = 1;
 }
 
-static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-			      u32 in_flight)
+static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 2b9464c93b8..7b09d8b49fa 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -276,26 +276,6 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 	return err;
 }
 
-/* RFC2861 Check whether we are limited by application or congestion window
- * This is the inverse of cwnd check in tcp_tso_should_defer
- */
-bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-	u32 left;
-
-	if (in_flight >= tp->snd_cwnd)
-		return true;
-
-	left = tp->snd_cwnd - in_flight;
-	if (sk_can_gso(sk) &&
-	    left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
-	    left < tp->xmit_size_goal_segs)
-		return true;
-	return left <= tcp_max_tso_deferred_mss(tp);
-}
-EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited);
-
 /* Slow start is used when congestion window is no greater than the slow start
  * threshold. We base on RFC2581 and also handle stretch ACKs properly.
  * We do not implement RFC3465 Appropriate Byte Counting (ABC) per se but
@@ -337,11 +317,11 @@ EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
 /* This is Jacobson's slow start and congestion avoidance.
  * SIGCOMM '88, p. 328.
  */
-void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
+void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	/* In "safe" area, increase. */
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index b4f1b29b08b..a9bd8a4828a 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -304,13 +304,12 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 		ca->cnt = 1;
 }
 
-static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-			      u32 in_flight)
+static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh) {
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f195d9316e5..9771563ab56 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -72,25 +72,224 @@ error:		kfree(ctx);
 	return err;
 }
 
-/* Computes the fastopen cookie for the IP path.
- * The path is a 128 bits long (pad with zeros for IPv4).
- *
- * The caller must check foc->len to determine if a valid cookie
- * has been generated successfully.
-*/
-void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
-			     struct tcp_fastopen_cookie *foc)
+static bool __tcp_fastopen_cookie_gen(const void *path,
+				      struct tcp_fastopen_cookie *foc)
 {
-	__be32 path[4] = { src, dst, 0, 0 };
 	struct tcp_fastopen_context *ctx;
+	bool ok = false;
 
 	tcp_fastopen_init_key_once(true);
 
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
-		crypto_cipher_encrypt_one(ctx->tfm, foc->val, (__u8 *)path);
+		crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
 		foc->len = TCP_FASTOPEN_COOKIE_SIZE;
+		ok = true;
 	}
 	rcu_read_unlock();
+	return ok;
+}
+
+/* Generate the fastopen cookie by doing aes128 encryption on both
+ * the source and destination addresses. Pad 0s for IPv4 or IPv4-mapped-IPv6
+ * addresses. For the longer IPv6 addresses use CBC-MAC.
+ *
+ * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
+ */
+static bool tcp_fastopen_cookie_gen(struct request_sock *req,
+				    struct sk_buff *syn,
+				    struct tcp_fastopen_cookie *foc)
+{
+	if (req->rsk_ops->family == AF_INET) {
+		const struct iphdr *iph = ip_hdr(syn);
+
+		__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
+		return __tcp_fastopen_cookie_gen(path, foc);
+	}
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (req->rsk_ops->family == AF_INET6) {
+		const struct ipv6hdr *ip6h = ipv6_hdr(syn);
+		struct tcp_fastopen_cookie tmp;
+
+		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
+			struct in6_addr *buf = (struct in6_addr *) tmp.val;
+			int i = 4;
+
+			for (i = 0; i < 4; i++)
+				buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
+			return __tcp_fastopen_cookie_gen(buf, foc);
+		}
+	}
+#endif
+	return false;
+}
+
+static bool tcp_fastopen_create_child(struct sock *sk,
+				      struct sk_buff *skb,
+				      struct dst_entry *dst,
+				      struct request_sock *req)
+{
+	struct tcp_sock *tp;
+	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
+	struct sock *child;
+
+	req->num_retrans = 0;
+	req->num_timeout = 0;
+	req->sk = NULL;
+
+	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
+	if (child == NULL)
+		return false;
+
+	spin_lock(&queue->fastopenq->lock);
+	queue->fastopenq->qlen++;
+	spin_unlock(&queue->fastopenq->lock);
+
+	/* Initialize the child socket. Have to fix some values to take
+	 * into account the child is a Fast Open socket and is created
+	 * only out of the bits carried in the SYN packet.
+	 */
+	tp = tcp_sk(child);
+
+	tp->fastopen_rsk = req;
+	/* Do a hold on the listner sk so that if the listener is being
+	 * closed, the child that has been accepted can live on and still
+	 * access listen_lock.
+	 */
+	sock_hold(sk);
+	tcp_rsk(req)->listener = sk;
+
+	/* RFC1323: The window in SYN & SYN/ACK segments is never
+	 * scaled. So correct it appropriately.
+	 */
+	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+
+	/* Activate the retrans timer so that SYNACK can be retransmitted.
+	 * The request socket is not added to the SYN table of the parent
+	 * because it's been added to the accept queue directly.
+	 */
+	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
+				  TCP_TIMEOUT_INIT, TCP_RTO_MAX);
+
+	/* Add the child socket directly into the accept queue */
+	inet_csk_reqsk_queue_add(sk, req, child);
+
+	/* Now finish processing the fastopen child socket. */
+	inet_csk(child)->icsk_af_ops->rebuild_header(child);
+	tcp_init_congestion_control(child);
+	tcp_mtup_init(child);
+	tcp_init_metrics(child);
+	tcp_init_buffer_space(child);
+
+	/* Queue the data carried in the SYN packet. We need to first
+	 * bump skb's refcnt because the caller will attempt to free it.
+	 *
+	 * XXX (TFO) - we honor a zero-payload TFO request for now,
+	 * (any reason not to?) but no need to queue the skb since
+	 * there is no data. How about SYN+FIN?
+	 */
+	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) {
+		skb = skb_get(skb);
+		skb_dst_drop(skb);
+		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
+		skb_set_owner_r(skb, child);
+		__skb_queue_tail(&child->sk_receive_queue, skb);
+		tp->syn_data_acked = 1;
+	}
+	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+	sk->sk_data_ready(sk);
+	bh_unlock_sock(child);
+	sock_put(child);
+	WARN_ON(req->sk == NULL);
+	return true;
+}
+EXPORT_SYMBOL(tcp_fastopen_create_child);
+
+static bool tcp_fastopen_queue_check(struct sock *sk)
+{
+	struct fastopen_queue *fastopenq;
+
+	/* Make sure the listener has enabled fastopen, and we don't
+	 * exceed the max # of pending TFO requests allowed before trying
+	 * to validating the cookie in order to avoid burning CPU cycles
+	 * unnecessarily.
+	 *
+	 * XXX (TFO) - The implication of checking the max_qlen before
+	 * processing a cookie request is that clients can't differentiate
+	 * between qlen overflow causing Fast Open to be disabled
+	 * temporarily vs a server not supporting Fast Open at all.
+	 */
+	fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
+	if (fastopenq == NULL || fastopenq->max_qlen == 0)
+		return false;
+
+	if (fastopenq->qlen >= fastopenq->max_qlen) {
+		struct request_sock *req1;
+		spin_lock(&fastopenq->lock);
+		req1 = fastopenq->rskq_rst_head;
+		if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
+			spin_unlock(&fastopenq->lock);
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
+			return false;
+		}
+		fastopenq->rskq_rst_head = req1->dl_next;
+		fastopenq->qlen--;
+		spin_unlock(&fastopenq->lock);
+		reqsk_free(req1);
+	}
+	return true;
+}
+
+/* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
+ * may be updated and return the client in the SYN-ACK later. E.g., Fast Open
+ * cookie request (foc->len == 0).
+ */
+bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
+		      struct request_sock *req,
+		      struct tcp_fastopen_cookie *foc,
+		      struct dst_entry *dst)
+{
+	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
+	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
+
+	if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+	      (syn_data || foc->len >= 0) &&
+	      tcp_fastopen_queue_check(sk))) {
+		foc->len = -1;
+		return false;
+	}
+
+	if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+		goto fastopen;
+
+	if (tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+	    foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
+	    foc->len == valid_foc.len &&
+	    !memcmp(foc->val, valid_foc.val, foc->len)) {
+		/* Cookie is valid. Create a (full) child socket to accept
+		 * the data in SYN before returning a SYN-ACK to ack the
+		 * data. If we fail to create the socket, fall back and
+		 * ack the ISN only but includes the same cookie.
+		 *
+		 * Note: Data-less SYN with valid cookie is allowed to send
+		 * data in SYN_RECV state.
+		 */
+fastopen:
+		if (tcp_fastopen_create_child(sk, skb, dst, req)) {
+			foc->len = -1;
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPFASTOPENPASSIVE);
+			return true;
+		}
+	}
+
+	NET_INC_STATS_BH(sock_net(sk), foc->len ?
+			 LINUX_MIB_TCPFASTOPENPASSIVEFAIL :
+			 LINUX_MIB_TCPFASTOPENCOOKIEREQD);
+	*foc = valid_foc;
+	return false;
 }
+EXPORT_SYMBOL(tcp_try_fastopen);
diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c
index 8b9e7bad77c..1c4908280d9 100644
--- a/net/ipv4/tcp_highspeed.c
+++ b/net/ipv4/tcp_highspeed.c
@@ -109,12 +109,12 @@ static void hstcp_init(struct sock *sk)
 	tp->snd_cwnd_clamp = min_t(u32, tp->snd_cwnd_clamp, 0xffffffff/128);
 }
 
-static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
+static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct hstcp *ca = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 4a194acfd92..031361311a8 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -227,12 +227,12 @@ static u32 htcp_recalc_ssthresh(struct sock *sk)
 	return max((tp->snd_cwnd * ca->beta) >> 7, 2U);
 }
 
-static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
+static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct htcp *ca = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c
index a15a799bf76..d8f8f05a495 100644
--- a/net/ipv4/tcp_hybla.c
+++ b/net/ipv4/tcp_hybla.c
@@ -87,8 +87,7 @@ static inline u32 hybla_fraction(u32 odds)
  *     o Give cwnd a new value based on the model proposed
  *     o remember increments <1
  */
-static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-			     u32 in_flight)
+static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct hybla *ca = inet_csk_ca(sk);
@@ -101,11 +100,11 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 		ca->minrtt_us = tp->srtt_us;
 	}
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (!ca->hybla_en) {
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 		return;
 	}
 
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 863d105e301..5999b3972e6 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -255,8 +255,7 @@ static void tcp_illinois_state(struct sock *sk, u8 new_state)
 /*
  * Increase window in response to successful acknowledgment.
  */
-static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				    u32 in_flight)
+static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct illinois *ca = inet_csk_ca(sk);
@@ -265,7 +264,7 @@ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 		update_params(sk);
 
 	/* RFC2861 only increase cwnd if fully utilized */
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	/* In slow start */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3a26b3b23f1..40639c288dc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1106,7 +1106,7 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
 	}
 
 	/* D-SACK for already forgotten data... Do dumb counting. */
-	if (dup_sack && tp->undo_marker && tp->undo_retrans &&
+	if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
 	    !after(end_seq_0, prior_snd_una) &&
 	    after(end_seq_0, tp->undo_marker))
 		tp->undo_retrans--;
@@ -1162,12 +1162,12 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 			unsigned int new_len = (pkt_len / mss) * mss;
 			if (!in_sack && new_len < pkt_len) {
 				new_len += mss;
-				if (new_len > skb->len)
+				if (new_len >= skb->len)
 					return 0;
 			}
 			pkt_len = new_len;
 		}
-		err = tcp_fragment(sk, skb, pkt_len, mss);
+		err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
 		if (err < 0)
 			return err;
 	}
@@ -1187,7 +1187,7 @@ static u8 tcp_sacktag_one(struct sock *sk,
 
 	/* Account D-SACK for retransmitted packet. */
 	if (dup_sack && (sacked & TCPCB_RETRANS)) {
-		if (tp->undo_marker && tp->undo_retrans &&
+		if (tp->undo_marker && tp->undo_retrans > 0 &&
 		    after(end_seq, tp->undo_marker))
 			tp->undo_retrans--;
 		if (sacked & TCPCB_SACKED_ACKED)
@@ -1893,7 +1893,7 @@ static void tcp_clear_retrans_partial(struct tcp_sock *tp)
 	tp->lost_out = 0;
 
 	tp->undo_marker = 0;
-	tp->undo_retrans = 0;
+	tp->undo_retrans = -1;
 }
 
 void tcp_clear_retrans(struct tcp_sock *tp)
@@ -2241,7 +2241,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 				break;
 
 			mss = skb_shinfo(skb)->gso_size;
-			err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, mss);
+			err = tcp_fragment(sk, skb, (packets - oldcnt) * mss,
+					   mss, GFP_ATOMIC);
 			if (err < 0)
 				break;
 			cnt = packets;
@@ -2664,7 +2665,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 
 	tp->prior_ssthresh = 0;
 	tp->undo_marker = tp->snd_una;
-	tp->undo_retrans = tp->retrans_out;
+	tp->undo_retrans = tp->retrans_out ? : -1;
 
 	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
 		if (!ece_ack)
@@ -2937,10 +2938,11 @@ static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp)
 		tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L);
 }
 
-static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
+static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	icsk->icsk_ca_ops->cong_avoid(sk, ack, acked, in_flight);
+
+	icsk->icsk_ca_ops->cong_avoid(sk, ack, acked);
 	tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp;
 }
 
@@ -3363,7 +3365,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 	bool is_dupack = false;
-	u32 prior_in_flight;
 	u32 prior_fackets;
 	int prior_packets = tp->packets_out;
 	const int prior_unsacked = tp->packets_out - tp->sacked_out;
@@ -3396,7 +3397,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		flag |= FLAG_SND_UNA_ADVANCED;
 
 	prior_fackets = tp->fackets_out;
-	prior_in_flight = tcp_packets_in_flight(tp);
 
 	/* ts_recent update must be made after we are sure that the packet
 	 * is in window.
@@ -3451,7 +3451,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	/* Advance cwnd if state allows */
 	if (tcp_may_raise_cwnd(sk, flag))
-		tcp_cong_avoid(sk, ack, acked, prior_in_flight);
+		tcp_cong_avoid(sk, ack, acked);
 
 	if (tcp_ack_is_dubious(sk, flag)) {
 		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
@@ -4702,28 +4702,6 @@ static int tcp_prune_queue(struct sock *sk)
 	return -1;
 }
 
-/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto.
- * As additional protections, we do not touch cwnd in retransmission phases,
- * and if application hit its sndbuf limit recently.
- */
-void tcp_cwnd_application_limited(struct sock *sk)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
-	    sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
-		/* Limited by application or receiver window. */
-		u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
-		u32 win_used = max(tp->snd_cwnd_used, init_win);
-		if (win_used < tp->snd_cwnd) {
-			tp->snd_ssthresh = tcp_current_ssthresh(sk);
-			tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1;
-		}
-		tp->snd_cwnd_used = 0;
-	}
-	tp->snd_cwnd_stamp = tcp_time_stamp;
-}
-
 static bool tcp_should_expand_sndbuf(const struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 438f3b95143..77cccda1ad0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -336,8 +336,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	const int code = icmp_hdr(icmp_skb)->code;
 	struct sock *sk;
 	struct sk_buff *skb;
-	struct request_sock *req;
-	__u32 seq;
+	struct request_sock *fastopen;
+	__u32 seq, snd_una;
 	__u32 remaining;
 	int err;
 	struct net *net = dev_net(icmp_skb->dev);
@@ -378,12 +378,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	icsk = inet_csk(sk);
 	tp = tcp_sk(sk);
-	req = tp->fastopen_rsk;
 	seq = ntohl(th->seq);
+	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
+	fastopen = tp->fastopen_rsk;
+	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
-	    !between(seq, tp->snd_una, tp->snd_nxt) &&
-	    (req == NULL || seq != tcp_rsk(req)->snt_isn)) {
-		/* For a Fast Open socket, allow seq to be snt_isn. */
+	    !between(seq, snd_una, tp->snd_nxt)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 		goto out;
 	}
@@ -426,11 +426,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH)
 			break;
 		if (seq != tp->snd_una  || !icsk->icsk_retransmits ||
-		    !icsk->icsk_backoff)
+		    !icsk->icsk_backoff || fastopen)
 			break;
 
-		/* XXX (TFO) - revisit the following logic for TFO */
-
 		if (sock_owned_by_user(sk))
 			break;
 
@@ -462,14 +460,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		goto out;
 	}
 
-	/* XXX (TFO) - if it's a TFO socket and has been accepted, rather
-	 * than following the TCP_SYN_RECV case and closing the socket,
-	 * we ignore the ICMP error and keep trying like a fully established
-	 * socket. Is this the right thing to do?
-	 */
-	if (req && req->sk == NULL)
-		goto out;
-
 	switch (sk->sk_state) {
 		struct request_sock *req, **prev;
 	case TCP_LISTEN:
@@ -502,10 +492,13 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		goto out;
 
 	case TCP_SYN_SENT:
-	case TCP_SYN_RECV:  /* Cannot happen.
-			       It can f.e. if SYNs crossed,
-			       or Fast Open.
-			     */
+	case TCP_SYN_RECV:
+		/* Only in fast or simultaneous open. If a fast open socket is
+		 * is already accepted it is treated as a connected one below.
+		 */
+		if (fastopen && fastopen->sk == NULL)
+			break;
+
 		if (!sock_owned_by_user(sk)) {
 			sk->sk_err = err;
 
@@ -822,7 +815,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
  */
 static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 			      struct request_sock *req,
-			      u16 queue_mapping)
+			      u16 queue_mapping,
+			      struct tcp_fastopen_cookie *foc)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct flowi4 fl4;
@@ -833,7 +827,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
 		return -1;
 
-	skb = tcp_make_synack(sk, dst, req, NULL);
+	skb = tcp_make_synack(sk, dst, req, foc);
 
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
@@ -852,7 +846,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 
 static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req)
 {
-	int res = tcp_v4_send_synack(sk, NULL, req, 0);
+	int res = tcp_v4_send_synack(sk, NULL, req, 0, NULL);
 
 	if (!res) {
 		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
@@ -1260,187 +1254,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 };
 #endif
 
-static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
-			       struct request_sock *req,
-			       struct tcp_fastopen_cookie *foc,
-			       struct tcp_fastopen_cookie *valid_foc)
-{
-	bool skip_cookie = false;
-	struct fastopen_queue *fastopenq;
-
-	if (likely(!fastopen_cookie_present(foc))) {
-		/* See include/net/tcp.h for the meaning of these knobs */
-		if ((sysctl_tcp_fastopen & TFO_SERVER_ALWAYS) ||
-		    ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) &&
-		    (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1)))
-			skip_cookie = true; /* no cookie to validate */
-		else
-			return false;
-	}
-	fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
-	/* A FO option is present; bump the counter. */
-	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE);
-
-	/* Make sure the listener has enabled fastopen, and we don't
-	 * exceed the max # of pending TFO requests allowed before trying
-	 * to validating the cookie in order to avoid burning CPU cycles
-	 * unnecessarily.
-	 *
-	 * XXX (TFO) - The implication of checking the max_qlen before
-	 * processing a cookie request is that clients can't differentiate
-	 * between qlen overflow causing Fast Open to be disabled
-	 * temporarily vs a server not supporting Fast Open at all.
-	 */
-	if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) == 0 ||
-	    fastopenq == NULL || fastopenq->max_qlen == 0)
-		return false;
-
-	if (fastopenq->qlen >= fastopenq->max_qlen) {
-		struct request_sock *req1;
-		spin_lock(&fastopenq->lock);
-		req1 = fastopenq->rskq_rst_head;
-		if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
-			spin_unlock(&fastopenq->lock);
-			NET_INC_STATS_BH(sock_net(sk),
-			    LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
-			/* Avoid bumping LINUX_MIB_TCPFASTOPENPASSIVEFAIL*/
-			foc->len = -1;
-			return false;
-		}
-		fastopenq->rskq_rst_head = req1->dl_next;
-		fastopenq->qlen--;
-		spin_unlock(&fastopenq->lock);
-		reqsk_free(req1);
-	}
-	if (skip_cookie) {
-		tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-		return true;
-	}
-
-	if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) {
-		if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) {
-			tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
-						ip_hdr(skb)->daddr, valid_foc);
-			if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) ||
-			    memcmp(&foc->val[0], &valid_foc->val[0],
-			    TCP_FASTOPEN_COOKIE_SIZE) != 0)
-				return false;
-			valid_foc->len = -1;
-		}
-		/* Acknowledge the data received from the peer. */
-		tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-		return true;
-	} else if (foc->len == 0) { /* Client requesting a cookie */
-		tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
-					ip_hdr(skb)->daddr, valid_foc);
-		NET_INC_STATS_BH(sock_net(sk),
-		    LINUX_MIB_TCPFASTOPENCOOKIEREQD);
-	} else {
-		/* Client sent a cookie with wrong size. Treat it
-		 * the same as invalid and return a valid one.
-		 */
-		tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
-					ip_hdr(skb)->daddr, valid_foc);
-	}
-	return false;
-}
-
-static int tcp_v4_conn_req_fastopen(struct sock *sk,
-				    struct sk_buff *skb,
-				    struct sk_buff *skb_synack,
-				    struct request_sock *req)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
-	const struct inet_request_sock *ireq = inet_rsk(req);
-	struct sock *child;
-	int err;
-
-	req->num_retrans = 0;
-	req->num_timeout = 0;
-	req->sk = NULL;
-
-	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
-	if (child == NULL) {
-		NET_INC_STATS_BH(sock_net(sk),
-				 LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
-		kfree_skb(skb_synack);
-		return -1;
-	}
-	err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
-				    ireq->ir_rmt_addr, ireq->opt);
-	err = net_xmit_eval(err);
-	if (!err)
-		tcp_rsk(req)->snt_synack = tcp_time_stamp;
-	/* XXX (TFO) - is it ok to ignore error and continue? */
-
-	spin_lock(&queue->fastopenq->lock);
-	queue->fastopenq->qlen++;
-	spin_unlock(&queue->fastopenq->lock);
-
-	/* Initialize the child socket. Have to fix some values to take
-	 * into account the child is a Fast Open socket and is created
-	 * only out of the bits carried in the SYN packet.
-	 */
-	tp = tcp_sk(child);
-
-	tp->fastopen_rsk = req;
-	/* Do a hold on the listner sk so that if the listener is being
-	 * closed, the child that has been accepted can live on and still
-	 * access listen_lock.
-	 */
-	sock_hold(sk);
-	tcp_rsk(req)->listener = sk;
-
-	/* RFC1323: The window in SYN & SYN/ACK segments is never
-	 * scaled. So correct it appropriately.
-	 */
-	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
-
-	/* Activate the retrans timer so that SYNACK can be retransmitted.
-	 * The request socket is not added to the SYN table of the parent
-	 * because it's been added to the accept queue directly.
-	 */
-	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
-	    TCP_TIMEOUT_INIT, TCP_RTO_MAX);
-
-	/* Add the child socket directly into the accept queue */
-	inet_csk_reqsk_queue_add(sk, req, child);
-
-	/* Now finish processing the fastopen child socket. */
-	inet_csk(child)->icsk_af_ops->rebuild_header(child);
-	tcp_init_congestion_control(child);
-	tcp_mtup_init(child);
-	tcp_init_metrics(child);
-	tcp_init_buffer_space(child);
-
-	/* Queue the data carried in the SYN packet. We need to first
-	 * bump skb's refcnt because the caller will attempt to free it.
-	 *
-	 * XXX (TFO) - we honor a zero-payload TFO request for now.
-	 * (Any reason not to?)
-	 */
-	if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq + 1) {
-		/* Don't queue the skb if there is no payload in SYN.
-		 * XXX (TFO) - How about SYN+FIN?
-		 */
-		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-	} else {
-		skb = skb_get(skb);
-		skb_dst_drop(skb);
-		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
-		skb_set_owner_r(skb, child);
-		__skb_queue_tail(&child->sk_receive_queue, skb);
-		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-		tp->syn_data_acked = 1;
-	}
-	sk->sk_data_ready(sk);
-	bh_unlock_sock(child);
-	sock_put(child);
-	WARN_ON(req->sk == NULL);
-	return 0;
-}
-
 int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_options_received tmp_opt;
@@ -1451,12 +1264,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	__be32 saddr = ip_hdr(skb)->saddr;
 	__be32 daddr = ip_hdr(skb)->daddr;
 	__u32 isn = TCP_SKB_CB(skb)->when;
-	bool want_cookie = false;
+	bool want_cookie = false, fastopen;
 	struct flowi4 fl4;
 	struct tcp_fastopen_cookie foc = { .len = -1 };
-	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
-	struct sk_buff *skb_synack;
-	int do_fastopen;
+	int err;
 
 	/* Never answer to SYNs send to broadcast or multicast */
 	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -1507,6 +1318,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	ireq->ir_rmt_addr = saddr;
 	ireq->no_srccheck = inet_sk(sk)->transparent;
 	ireq->opt = tcp_v4_save_options(skb);
+	ireq->ir_mark = inet_request_mark(sk, skb);
 
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_free;
@@ -1555,52 +1367,24 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 
 		isn = tcp_v4_init_sequence(skb);
 	}
-	tcp_rsk(req)->snt_isn = isn;
-
-	if (dst == NULL) {
-		dst = inet_csk_route_req(sk, &fl4, req);
-		if (dst == NULL)
-			goto drop_and_free;
-	}
-	do_fastopen = tcp_fastopen_check(sk, skb, req, &foc, &valid_foc);
-
-	/* We don't call tcp_v4_send_synack() directly because we need
-	 * to make sure a child socket can be created successfully before
-	 * sending back synack!
-	 *
-	 * XXX (TFO) - Ideally one would simply call tcp_v4_send_synack()
-	 * (or better yet, call tcp_send_synack() in the child context
-	 * directly, but will have to fix bunch of other code first)
-	 * after syn_recv_sock() except one will need to first fix the
-	 * latter to remove its dependency on the current implementation
-	 * of tcp_v4_send_synack()->tcp_select_initial_window().
-	 */
-	skb_synack = tcp_make_synack(sk, dst, req,
-	    fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL);
-
-	if (skb_synack) {
-		__tcp_v4_send_check(skb_synack, ireq->ir_loc_addr, ireq->ir_rmt_addr);
-		skb_set_queue_mapping(skb_synack, skb_get_queue_mapping(skb));
-	} else
+	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
 		goto drop_and_free;
 
-	if (likely(!do_fastopen)) {
-		int err;
-		err = ip_build_and_send_pkt(skb_synack, sk, ireq->ir_loc_addr,
-		     ireq->ir_rmt_addr, ireq->opt);
-		err = net_xmit_eval(err);
+	tcp_rsk(req)->snt_isn = isn;
+	tcp_rsk(req)->snt_synack = tcp_time_stamp;
+	tcp_openreq_init_rwin(req, sk, dst);
+	fastopen = !want_cookie &&
+		   tcp_try_fastopen(sk, skb, req, &foc, dst);
+	err = tcp_v4_send_synack(sk, dst, req,
+				 skb_get_queue_mapping(skb), &foc);
+	if (!fastopen) {
 		if (err || want_cookie)
 			goto drop_and_free;
 
 		tcp_rsk(req)->snt_synack = tcp_time_stamp;
 		tcp_rsk(req)->listener = NULL;
-		/* Add the request_sock to the SYN table */
 		inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
-		if (fastopen_cookie_present(&foc) && foc.len != 0)
-			NET_INC_STATS_BH(sock_net(sk),
-			    LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
-	} else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req))
-		goto drop_and_free;
+	}
 
 	return 0;
 
@@ -1744,28 +1528,6 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
 	return sk;
 }
 
-static __sum16 tcp_v4_checksum_init(struct sk_buff *skb)
-{
-	const struct iphdr *iph = ip_hdr(skb);
-
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		if (!tcp_v4_check(skb->len, iph->saddr,
-				  iph->daddr, skb->csum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			return 0;
-		}
-	}
-
-	skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-				       skb->len, IPPROTO_TCP, 0);
-
-	if (skb->len <= 76) {
-		return __skb_checksum_complete(skb);
-	}
-	return 0;
-}
-
-
 /* The socket must have it's spinlock held when we get
  * here.
  *
@@ -1960,7 +1722,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	 * Packet length and doff are validated by header prediction,
 	 * provided case of th->doff==0 is eliminated.
 	 * So, we defer the checks. */
-	if (!skb_csum_unnecessary(skb) && tcp_v4_checksum_init(skb))
+
+	if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo))
 		goto csum_error;
 
 	th = tcp_hdr(skb);
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index c9aecae3132..1e70fa8fa79 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -115,13 +115,12 @@ static void tcp_lp_init(struct sock *sk)
  * Will only call newReno CA when away from inference.
  * From TCP-LP's paper, this will be handled in additive increasement.
  */
-static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-			      u32 in_flight)
+static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct lp *lp = inet_csk_ca(sk);
 
 	if (!(lp->flag & LP_WITHIN_INF))
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 }
 
 /**
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index d4f015ad6c8..3af522622fa 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -102,17 +102,19 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	return 0;
 }
 
-static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			    char *buffer)
+static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
 	unsigned long long val;
 	int ret = 0;
 
-	switch (cft->private) {
+	buf = strstrip(buf);
+
+	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = res_counter_memparse_write_strategy(buffer, &val);
+		ret = res_counter_memparse_write_strategy(buf, &val);
 		if (ret)
 			break;
 		ret = tcp_update_limit(memcg, val);
@@ -121,7 +123,7 @@ static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
 		ret = -EINVAL;
 		break;
 	}
-	return ret;
+	return ret ?: nbytes;
 }
 
 static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
@@ -168,17 +170,18 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
 	return val;
 }
 
-static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
+static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
+				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg;
 	struct cg_proto *cg_proto;
 
-	memcg = mem_cgroup_from_css(css);
+	memcg = mem_cgroup_from_css(of_css(of));
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
-		return 0;
+		return nbytes;
 
-	switch (event) {
+	switch (of_cft(of)->private) {
 	case RES_MAX_USAGE:
 		res_counter_reset_max(&cg_proto->memory_allocated);
 		break;
@@ -187,13 +190,13 @@ static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
 		break;
 	}
 
-	return 0;
+	return nbytes;
 }
 
 static struct cftype tcp_files[] = {
 	{
 		.name = "kmem.tcp.limit_in_bytes",
-		.write_string = tcp_cgroup_write,
+		.write = tcp_cgroup_write,
 		.read_u64 = tcp_cgroup_read,
 		.private = RES_LIMIT,
 	},
@@ -205,13 +208,13 @@ static struct cftype tcp_files[] = {
 	{
 		.name = "kmem.tcp.failcnt",
 		.private = RES_FAILCNT,
-		.trigger = tcp_cgroup_reset,
+		.write = tcp_cgroup_reset,
 		.read_u64 = tcp_cgroup_read,
 	},
 	{
 		.name = "kmem.tcp.max_usage_in_bytes",
 		.private = RES_MAX_USAGE,
-		.trigger = tcp_cgroup_reset,
+		.write = tcp_cgroup_reset,
 		.read_u64 = tcp_cgroup_read,
 	},
 	{ }	/* terminate */
@@ -219,7 +222,7 @@ static struct cftype tcp_files[] = {
 
 static int __init tcp_memcontrol_init(void)
 {
-	WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, tcp_files));
+	WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, tcp_files));
 	return 0;
 }
 __initcall(tcp_memcontrol_init);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index dcaf72f1021..4fe04180598 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -1159,10 +1159,7 @@ static void __net_exit tcp_net_metrics_exit(struct net *net)
 			tm = next;
 		}
 	}
-	if (is_vmalloc_addr(net->ipv4.tcp_metrics_hash))
-		vfree(net->ipv4.tcp_metrics_hash);
-	else
-		kfree(net->ipv4.tcp_metrics_hash);
+	kvfree(net->ipv4.tcp_metrics_hash);
 }
 
 static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 05c1b155251..e68e0d4af6c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -362,6 +362,37 @@ void tcp_twsk_destructor(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
 
+void tcp_openreq_init_rwin(struct request_sock *req,
+			   struct sock *sk, struct dst_entry *dst)
+{
+	struct inet_request_sock *ireq = inet_rsk(req);
+	struct tcp_sock *tp = tcp_sk(sk);
+	__u8 rcv_wscale;
+	int mss = dst_metric_advmss(dst);
+
+	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
+		mss = tp->rx_opt.user_mss;
+
+	/* Set this up on the first call only */
+	req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
+
+	/* limit the window selection if the user enforce a smaller rx buffer */
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+	    (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
+		req->window_clamp = tcp_full_space(sk);
+
+	/* tcp_full_space because it is guaranteed to be the first packet */
+	tcp_select_initial_window(tcp_full_space(sk),
+		mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
+		&req->rcv_wnd,
+		&req->window_clamp,
+		ireq->wscale_ok,
+		&rcv_wscale,
+		dst_metric(dst, RTAX_INITRWND));
+	ireq->rcv_wscale = rcv_wscale;
+}
+EXPORT_SYMBOL(tcp_openreq_init_rwin);
+
 static inline void TCP_ECN_openreq_child(struct tcp_sock *tp,
 					 struct request_sock *req)
 {
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index b92b81718ca..55046ecd083 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -57,10 +57,12 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 			       SKB_GSO_TCP_ECN |
 			       SKB_GSO_TCPV6 |
 			       SKB_GSO_GRE |
+			       SKB_GSO_GRE_CSUM |
 			       SKB_GSO_IPIP |
 			       SKB_GSO_SIT |
 			       SKB_GSO_MPLS |
 			       SKB_GSO_UDP_TUNNEL |
+			       SKB_GSO_UDP_TUNNEL_CSUM |
 			       0) ||
 			     !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
 			goto out;
@@ -97,9 +99,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 		th->check = newcheck;
 
 		if (skb->ip_summed != CHECKSUM_PARTIAL)
-			th->check =
-			     csum_fold(csum_partial(skb_transport_header(skb),
-						    thlen, skb->csum));
+			th->check = gso_make_checksum(skb, ~th->check);
 
 		seq += mss;
 		if (copy_destructor) {
@@ -133,8 +133,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
 				(__force u32)delta));
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
-		th->check = csum_fold(csum_partial(skb_transport_header(skb),
-						   thlen, skb->csum));
+		th->check = gso_make_checksum(skb, ~th->check);
 out:
 	return segs;
 }
@@ -310,7 +309,7 @@ static int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 
 	th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr,
 				  iph->daddr, 0);
-	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4;
 
 	return tcp_gro_complete(skb);
 }
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 2d340bd2cd3..179b51e6bda 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -627,7 +627,7 @@ static unsigned int tcp_synack_options(struct sock *sk,
 		if (unlikely(!ireq->tstamp_ok))
 			remaining -= TCPOLEN_SACKPERM_ALIGNED;
 	}
-	if (foc != NULL) {
+	if (foc != NULL && foc->len >= 0) {
 		u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len;
 		need = (need + 3) & ~3U;  /* Align to 32 bits */
 		if (remaining >= need) {
@@ -878,15 +878,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	BUG_ON(!skb || !tcp_skb_pcount(skb));
 
 	if (clone_it) {
-		const struct sk_buff *fclone = skb + 1;
-
 		skb_mstamp_get(&skb->skb_mstamp);
 
-		if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
-			     fclone->fclone == SKB_FCLONE_CLONE))
-			NET_INC_STATS(sock_net(sk),
-				      LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
-
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
 		else
@@ -1081,7 +1074,7 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de
  * Remember, these are still headerless SKBs at this point.
  */
 int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
-		 unsigned int mss_now)
+		 unsigned int mss_now, gfp_t gfp)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *buff;
@@ -1096,11 +1089,11 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	if (nsize < 0)
 		nsize = 0;
 
-	if (skb_unclone(skb, GFP_ATOMIC))
+	if (skb_unclone(skb, gfp))
 		return -ENOMEM;
 
 	/* Get a new skb... force flag on. */
-	buff = sk_stream_alloc_skb(sk, nsize, GFP_ATOMIC);
+	buff = sk_stream_alloc_skb(sk, nsize, gfp);
 	if (buff == NULL)
 		return -ENOMEM; /* We'll just try again later. */
 
@@ -1387,12 +1380,43 @@ unsigned int tcp_current_mss(struct sock *sk)
 	return mss_now;
 }
 
-/* Congestion window validation. (RFC2861) */
-static void tcp_cwnd_validate(struct sock *sk)
+/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto.
+ * As additional protections, we do not touch cwnd in retransmission phases,
+ * and if application hit its sndbuf limit recently.
+ */
+static void tcp_cwnd_application_limited(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tp->packets_out >= tp->snd_cwnd) {
+	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
+	    sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
+		/* Limited by application or receiver window. */
+		u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
+		u32 win_used = max(tp->snd_cwnd_used, init_win);
+		if (win_used < tp->snd_cwnd) {
+			tp->snd_ssthresh = tcp_current_ssthresh(sk);
+			tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1;
+		}
+		tp->snd_cwnd_used = 0;
+	}
+	tp->snd_cwnd_stamp = tcp_time_stamp;
+}
+
+static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	/* Track the maximum number of outstanding packets in each
+	 * window, and remember whether we were cwnd-limited then.
+	 */
+	if (!before(tp->snd_una, tp->max_packets_seq) ||
+	    tp->packets_out > tp->max_packets_out) {
+		tp->max_packets_out = tp->packets_out;
+		tp->max_packets_seq = tp->snd_nxt;
+		tp->is_cwnd_limited = is_cwnd_limited;
+	}
+
+	if (tcp_is_cwnd_limited(sk)) {
 		/* Network is feed fully. */
 		tp->snd_cwnd_used = 0;
 		tp->snd_cwnd_stamp = tcp_time_stamp;
@@ -1601,7 +1625,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 
 	/* All of a TSO frame must be composed of paged data.  */
 	if (skb->len != skb->data_len)
-		return tcp_fragment(sk, skb, len, mss_now);
+		return tcp_fragment(sk, skb, len, mss_now, gfp);
 
 	buff = sk_stream_alloc_skb(sk, 0, gfp);
 	if (unlikely(buff == NULL))
@@ -1644,7 +1668,8 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
  *
  * This algorithm is from John Heffner.
  */
-static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
+static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
+				 bool *is_cwnd_limited)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1708,6 +1733,9 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 	if (!tp->tso_deferred)
 		tp->tso_deferred = 1 | (jiffies << 1);
 
+	if (cong_win < send_win && cong_win < skb->len)
+		*is_cwnd_limited = true;
+
 	return true;
 
 send_now:
@@ -1868,6 +1896,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	unsigned int tso_segs, sent_pkts;
 	int cwnd_quota;
 	int result;
+	bool is_cwnd_limited = false;
 
 	sent_pkts = 0;
 
@@ -1892,6 +1921,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 
 		cwnd_quota = tcp_cwnd_test(tp, skb);
 		if (!cwnd_quota) {
+			is_cwnd_limited = true;
 			if (push_one == 2)
 				/* Force out a loss probe pkt. */
 				cwnd_quota = 1;
@@ -1908,7 +1938,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 						      nonagle : TCP_NAGLE_PUSH))))
 				break;
 		} else {
-			if (!push_one && tcp_tso_should_defer(sk, skb))
+			if (!push_one &&
+			    tcp_tso_should_defer(sk, skb, &is_cwnd_limited))
 				break;
 		}
 
@@ -1973,7 +2004,7 @@ repair:
 		/* Send one loss probe per tail loss episode. */
 		if (push_one != 2)
 			tcp_schedule_loss_probe(sk);
-		tcp_cwnd_validate(sk);
+		tcp_cwnd_validate(sk, is_cwnd_limited);
 		return false;
 	}
 	return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));
@@ -2037,6 +2068,25 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	return true;
 }
 
+/* Thanks to skb fast clones, we can detect if a prior transmit of
+ * a packet is still in a qdisc or driver queue.
+ * In this case, there is very little point doing a retransmit !
+ * Note: This is called from BH context only.
+ */
+static bool skb_still_in_host_queue(const struct sock *sk,
+				    const struct sk_buff *skb)
+{
+	const struct sk_buff *fclone = skb + 1;
+
+	if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
+		     fclone->fclone == SKB_FCLONE_CLONE)) {
+		NET_INC_STATS_BH(sock_net(sk),
+				 LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES);
+		return true;
+	}
+	return false;
+}
+
 /* When probe timeout (PTO) fires, send a new segment if one exists, else
  * retransmit the last segment.
  */
@@ -2062,12 +2112,16 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (WARN_ON(!skb))
 		goto rearm_timer;
 
+	if (skb_still_in_host_queue(sk, skb))
+		goto rearm_timer;
+
 	pcount = tcp_skb_pcount(skb);
 	if (WARN_ON(!pcount))
 		goto rearm_timer;
 
 	if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) {
-		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss)))
+		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss,
+					  GFP_ATOMIC)))
 			goto rearm_timer;
 		skb = tcp_write_queue_tail(sk);
 	}
@@ -2075,9 +2129,7 @@ void tcp_send_loss_probe(struct sock *sk)
 	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
 		goto rearm_timer;
 
-	/* Probe with zero data doesn't trigger fast recovery. */
-	if (skb->len > 0)
-		err = __tcp_retransmit_skb(sk, skb);
+	err = __tcp_retransmit_skb(sk, skb);
 
 	/* Record snd_nxt for loss detection. */
 	if (likely(!err))
@@ -2383,6 +2435,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	    min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
 		return -EAGAIN;
 
+	if (skb_still_in_host_queue(sk, skb))
+		return -EBUSY;
+
 	if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
 		if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
 			BUG();
@@ -2405,7 +2460,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		return -EAGAIN;
 
 	if (skb->len > cur_mss) {
-		if (tcp_fragment(sk, skb, cur_mss, cur_mss))
+		if (tcp_fragment(sk, skb, cur_mss, cur_mss, GFP_ATOMIC))
 			return -ENOMEM; /* We'll try again later. */
 	} else {
 		int oldpcount = tcp_skb_pcount(skb);
@@ -2470,15 +2525,17 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		if (!tp->retrans_stamp)
 			tp->retrans_stamp = TCP_SKB_CB(skb)->when;
 
-		tp->undo_retrans += tcp_skb_pcount(skb);
-
 		/* snd_nxt is stored to detect loss of retransmitted segment,
 		 * see tcp_input.c tcp_sacktag_write_queue().
 		 */
 		TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
-	} else {
+	} else if (err != -EBUSY) {
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
 	}
+
+	if (tp->undo_retrans < 0)
+		tp->undo_retrans = 0;
+	tp->undo_retrans += tcp_skb_pcount(skb);
 	return err;
 }
 
@@ -2754,27 +2811,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
 		mss = tp->rx_opt.user_mss;
 
-	if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
-		__u8 rcv_wscale;
-		/* Set this up on the first call only */
-		req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
-
-		/* limit the window selection if the user enforce a smaller rx buffer */
-		if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
-		    (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
-			req->window_clamp = tcp_full_space(sk);
-
-		/* tcp_full_space because it is guaranteed to be the first packet */
-		tcp_select_initial_window(tcp_full_space(sk),
-			mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
-			&req->rcv_wnd,
-			&req->window_clamp,
-			ireq->wscale_ok,
-			&rcv_wscale,
-			dst_metric(dst, RTAX_INITRWND));
-		ireq->rcv_wscale = rcv_wscale;
-	}
-
 	memset(&opts, 0, sizeof(opts));
 #ifdef CONFIG_SYN_COOKIES
 	if (unlikely(req->cookie_ts))
@@ -3207,7 +3243,7 @@ int tcp_write_wakeup(struct sock *sk)
 		    skb->len > mss) {
 			seg_size = min(seg_size, mss);
 			TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
-			if (tcp_fragment(sk, skb, seg_size, mss))
+			if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC))
 				return -1;
 		} else if (!tcp_skb_pcount(skb))
 			tcp_set_skb_tso_segs(sk, skb, mss);
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 0ac50836da4..8250949b885 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -15,12 +15,11 @@
 #define TCP_SCALABLE_AI_CNT	50U
 #define TCP_SCALABLE_MD_SCALE	3
 
-static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				    u32 in_flight)
+static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 48539fff635..9a5e05f27f4 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -163,14 +163,13 @@ static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp)
 	return  min(tp->snd_ssthresh, tp->snd_cwnd-1);
 }
 
-static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				 u32 in_flight)
+static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct vegas *vegas = inet_csk_ca(sk);
 
 	if (!vegas->doing_vegas_now) {
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 		return;
 	}
 
@@ -195,7 +194,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 			/* We don't have enough RTT samples to do the Vegas
 			 * calculation, so we'll behave like Reno.
 			 */
-			tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+			tcp_reno_cong_avoid(sk, ack, acked);
 		} else {
 			u32 rtt, diff;
 			u64 target_cwnd;
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 1b8e28fcd7e..27b9825753d 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -114,19 +114,18 @@ static void tcp_veno_cwnd_event(struct sock *sk, enum tcp_ca_event event)
 		tcp_veno_init(sk);
 }
 
-static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				u32 in_flight)
+static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct veno *veno = inet_csk_ca(sk);
 
 	if (!veno->doing_veno_now) {
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 		return;
 	}
 
 	/* limited by applications */
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	/* We do the Veno calculations only if we got enough rtt samples */
@@ -134,7 +133,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 		/* We don't have enough rtt samples to do the Veno
 		 * calculation, so we'll behave like Reno.
 		 */
-		tcp_reno_cong_avoid(sk, ack, acked, in_flight);
+		tcp_reno_cong_avoid(sk, ack, acked);
 	} else {
 		u64 target_cwnd;
 		u32 rtt;
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 5ede0e72794..599b79b8eac 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -69,13 +69,12 @@ static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, s32 rtt_us)
 	tcp_vegas_pkts_acked(sk, pkts_acked, rtt_us);
 }
 
-static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked,
-				u32 in_flight)
+static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct yeah *yeah = inet_csk_ca(sk);
 
-	if (!tcp_is_cwnd_limited(sk, in_flight))
+	if (!tcp_is_cwnd_limited(sk))
 		return;
 
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4468e1adc09..7d5a8661df7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -246,7 +246,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 			do {
 				if (low <= snum && snum <= high &&
 				    !test_bit(snum >> udptable->log, bitmap) &&
-				    !inet_is_reserved_local_port(snum))
+				    !inet_is_local_reserved_port(net, snum))
 					goto found;
 				snum += rand;
 			} while (snum != first);
@@ -727,13 +727,12 @@ EXPORT_SYMBOL(udp_flush_pending_frames);
 void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 {
 	struct udphdr *uh = udp_hdr(skb);
-	struct sk_buff *frags = skb_shinfo(skb)->frag_list;
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
 	int hlen = len;
 	__wsum csum = 0;
 
-	if (!frags) {
+	if (!skb_has_frag_list(skb)) {
 		/*
 		 * Only one fragment on the socket.
 		 */
@@ -742,15 +741,17 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 		uh->check = ~csum_tcpudp_magic(src, dst, len,
 					       IPPROTO_UDP, 0);
 	} else {
+		struct sk_buff *frags;
+
 		/*
 		 * HW-checksum won't work as there are two or more
 		 * fragments on the socket so that all csums of sk_buffs
 		 * should be together
 		 */
-		do {
+		skb_walk_frags(skb, frags) {
 			csum = csum_add(csum, frags->csum);
 			hlen -= frags->len;
-		} while ((frags = frags->next));
+		}
 
 		csum = skb_checksum(skb, offset, hlen, csum);
 		skb->ip_summed = CHECKSUM_NONE;
@@ -762,6 +763,43 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 }
 EXPORT_SYMBOL_GPL(udp4_hwcsum);
 
+/* Function to set UDP checksum for an IPv4 UDP packet. This is intended
+ * for the simple case like when setting the checksum for a UDP tunnel.
+ */
+void udp_set_csum(bool nocheck, struct sk_buff *skb,
+		  __be32 saddr, __be32 daddr, int len)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	if (nocheck)
+		uh->check = 0;
+	else if (skb_is_gso(skb))
+		uh->check = ~udp_v4_check(len, saddr, daddr, 0);
+	else if (skb_dst(skb) && skb_dst(skb)->dev &&
+		 (skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) {
+
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
+
+		skb->ip_summed = CHECKSUM_PARTIAL;
+		skb->csum_start = skb_transport_header(skb) - skb->head;
+		skb->csum_offset = offsetof(struct udphdr, check);
+		uh->check = ~udp_v4_check(len, saddr, daddr, 0);
+	} else {
+		__wsum csum;
+
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, len, 0);
+		uh->check = udp_v4_check(len, saddr, daddr, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
+}
+EXPORT_SYMBOL(udp_set_csum);
+
 static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 {
 	struct sock *sk = skb->sk;
@@ -785,7 +823,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 	if (is_udplite)  				 /*     UDP-Lite      */
 		csum = udplite_csum(skb);
 
-	else if (sk->sk_no_check == UDP_CSUM_NOXMIT) {   /* UDP csum disabled */
+	else if (sk->sk_no_check_tx) {   /* UDP csum disabled */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
@@ -1495,6 +1533,10 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) {
 			int ret;
 
+			/* Verify checksum before giving to encap */
+			if (udp_lib_checksum_complete(skb))
+				goto csum_error;
+
 			ret = encap_rcv(sk, skb);
 			if (ret <= 0) {
 				UDP_INC_STATS_BH(sock_net(sk),
@@ -1546,8 +1588,11 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		goto csum_error;
 
 
-	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf))
+	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) {
+		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+				 is_udplite);
 		goto drop;
+	}
 
 	rc = 0;
 
@@ -1672,7 +1717,6 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 				 int proto)
 {
-	const struct iphdr *iph;
 	int err;
 
 	UDP_SKB_CB(skb)->partial_cov = 0;
@@ -1684,22 +1728,8 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 			return err;
 	}
 
-	iph = ip_hdr(skb);
-	if (uh->check == 0) {
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-	} else if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
-				      proto, skb->csum))
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-	}
-	if (!skb_csum_unnecessary(skb))
-		skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-					       skb->len, proto, 0);
-	/* Probably, we should checksum udp header (it should be in cache
-	 * in any case) and data in tiny packets (< rx copybreak).
-	 */
-
-	return 0;
+	return skb_checksum_init_zero_check(skb, proto, uh->check,
+					    inet_compute_pseudo);
 }
 
 /*
@@ -1834,6 +1864,10 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 	unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
 	struct udp_hslot *hslot = &udp_table.hash[slot];
 
+	/* Do not bother scanning a too big list */
+	if (hslot->count > 10)
+		return NULL;
+
 	rcu_read_lock();
 begin:
 	count = 0;
@@ -1886,7 +1920,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 	unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
 	unsigned int slot2 = hash2 & udp_table.mask;
 	struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
-	INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr)
+	INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr);
 	const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
 
 	rcu_read_lock();
@@ -1979,7 +2013,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		       int (*push_pending_frames)(struct sock *))
 {
 	struct udp_sock *up = udp_sk(sk);
-	int val;
+	int val, valbool;
 	int err = 0;
 	int is_udplite = IS_UDPLITE(sk);
 
@@ -1989,6 +2023,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 	if (get_user(val, (int __user *)optval))
 		return -EFAULT;
 
+	valbool = val ? 1 : 0;
+
 	switch (optname) {
 	case UDP_CORK:
 		if (val != 0) {
@@ -2018,6 +2054,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		}
 		break;
 
+	case UDP_NO_CHECK6_TX:
+		up->no_check6_tx = valbool;
+		break;
+
+	case UDP_NO_CHECK6_RX:
+		up->no_check6_rx = valbool;
+		break;
+
 	/*
 	 * 	UDP-Lite's partial checksum coverage (RFC 3828).
 	 */
@@ -2100,6 +2144,14 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 		val = up->encap_type;
 		break;
 
+	case UDP_NO_CHECK6_TX:
+		val = up->no_check6_tx;
+		break;
+
+	case UDP_NO_CHECK6_RX:
+		val = up->no_check6_rx;
+		break;
+
 	/* The following two cannot be changed on UDP sockets, the return is
 	 * always 0 (which corresponds to the full checksum coverage of UDP). */
 	case UDPLITE_SEND_CSCOV:
@@ -2484,7 +2536,11 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
 	__be16 protocol = skb->protocol;
 	netdev_features_t enc_features;
-	int outer_hlen;
+	int udp_offset, outer_hlen;
+	unsigned int oldlen;
+	bool need_csum;
+
+	oldlen = (u16)~skb->len;
 
 	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
 		goto out;
@@ -2496,6 +2552,10 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	skb->mac_len = skb_inner_network_offset(skb);
 	skb->protocol = htons(ETH_P_TEB);
 
+	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
+	if (need_csum)
+		skb->encap_hdr_csum = 1;
+
 	/* segment inner packet. */
 	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
 	segs = skb_mac_gso_segment(skb, enc_features);
@@ -2506,10 +2566,11 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	}
 
 	outer_hlen = skb_tnl_header_len(skb);
+	udp_offset = outer_hlen - tnl_hlen;
 	skb = segs;
 	do {
 		struct udphdr *uh;
-		int udp_offset = outer_hlen - tnl_hlen;
+		int len;
 
 		skb_reset_inner_headers(skb);
 		skb->encapsulation = 1;
@@ -2520,31 +2581,20 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 		skb_reset_mac_header(skb);
 		skb_set_network_header(skb, mac_len);
 		skb_set_transport_header(skb, udp_offset);
+		len = skb->len - udp_offset;
 		uh = udp_hdr(skb);
-		uh->len = htons(skb->len - udp_offset);
-
-		/* csum segment if tunnel sets skb with csum. */
-		if (protocol == htons(ETH_P_IP) && unlikely(uh->check)) {
-			struct iphdr *iph = ip_hdr(skb);
+		uh->len = htons(len);
 
-			uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
-						       skb->len - udp_offset,
-						       IPPROTO_UDP, 0);
-			uh->check = csum_fold(skb_checksum(skb, udp_offset,
-							   skb->len - udp_offset, 0));
-			if (uh->check == 0)
-				uh->check = CSUM_MANGLED_0;
+		if (need_csum) {
+			__be32 delta = htonl(oldlen + len);
 
-		} else if (protocol == htons(ETH_P_IPV6)) {
-			struct ipv6hdr *ipv6h = ipv6_hdr(skb);
-			u32 len = skb->len - udp_offset;
+			uh->check = ~csum_fold((__force __wsum)
+					       ((__force u32)uh->check +
+						(__force u32)delta));
+			uh->check = gso_make_checksum(skb, ~uh->check);
 
-			uh->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
-						     len, IPPROTO_UDP, 0);
-			uh->check = csum_fold(skb_checksum(skb, udp_offset, len, 0));
 			if (uh->check == 0)
 				uh->check = CSUM_MANGLED_0;
-			skb->ip_summed = CHECKSUM_NONE;
 		}
 
 		skb->protocol = protocol;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 88b4023ecfc..546d2d439dd 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -56,7 +56,8 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	__wsum csum;
 
 	if (skb->encapsulation &&
-	    skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) {
+	    (skb_shinfo(skb)->gso_type &
+	     (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) {
 		segs = skb_udp_tunnel_segment(skb, features);
 		goto out;
 	}
@@ -71,8 +72,10 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 
 		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
+				      SKB_GSO_UDP_TUNNEL_CSUM |
 				      SKB_GSO_IPIP |
-				      SKB_GSO_GRE | SKB_GSO_MPLS) ||
+				      SKB_GSO_GRE | SKB_GSO_GRE_CSUM |
+				      SKB_GSO_MPLS) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 
@@ -197,6 +200,7 @@ unflush:
 	}
 
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
+	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
 	pp = uo_priv->offload->callbacks.gro_receive(head, skb);
 
 out_unlock:
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 2c46acd4cc3..3b3efbda48e 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -70,7 +70,6 @@ static struct inet_protosw udplite4_protosw = {
 	.protocol	=  IPPROTO_UDPLITE,
 	.prot		=  &udplite_prot,
 	.ops		=  &inet_dgram_ops,
-	.no_check	=  0,		/* must checksum (RFC 3828) */
 	.flags		=  INET_PROTOSW_PERMANENT,
 };
 
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 05f2b484954..91771a7c802 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -58,12 +58,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
 		0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
-	ip_select_ident(skb, dst->child, NULL);
 
 	top_iph->ttl = ip4_dst_hoplimit(dst->child);
 
 	top_iph->saddr = x->props.saddr.a4;
 	top_iph->daddr = x->id.daddr.a4;
+	ip_select_ident(skb, NULL);
 
 	return 0;
 }
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 186a8ecf92f..d5f6bd9a210 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -25,7 +25,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb)
 	if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE)
 		goto out;
 
-	if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->local_df)
+	if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->ignore_df)
 		goto out;
 
 	mtu = dst_mtu(skb_dst(skb));
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6c7fa0853fc..5667b3003af 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -275,19 +275,14 @@ static int snmp6_alloc_dev(struct inet6_dev *idev)
 {
 	int i;
 
-	if (snmp_mib_init((void __percpu **)idev->stats.ipv6,
-			  sizeof(struct ipstats_mib),
-			  __alignof__(struct ipstats_mib)) < 0)
+	idev->stats.ipv6 = alloc_percpu(struct ipstats_mib);
+	if (!idev->stats.ipv6)
 		goto err_ip;
 
 	for_each_possible_cpu(i) {
 		struct ipstats_mib *addrconf_stats;
-		addrconf_stats = per_cpu_ptr(idev->stats.ipv6[0], i);
+		addrconf_stats = per_cpu_ptr(idev->stats.ipv6, i);
 		u64_stats_init(&addrconf_stats->syncp);
-#if SNMP_ARRAY_SZ == 2
-		addrconf_stats = per_cpu_ptr(idev->stats.ipv6[1], i);
-		u64_stats_init(&addrconf_stats->syncp);
-#endif
 	}
 
 
@@ -305,7 +300,7 @@ static int snmp6_alloc_dev(struct inet6_dev *idev)
 err_icmpmsg:
 	kfree(idev->stats.icmpv6dev);
 err_icmp:
-	snmp_mib_free((void __percpu **)idev->stats.ipv6);
+	free_percpu(idev->stats.ipv6);
 err_ip:
 	return -ENOMEM;
 }
@@ -2504,8 +2499,8 @@ static int inet6_addr_add(struct net *net, int ifindex,
 	return PTR_ERR(ifp);
 }
 
-static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *pfx,
-			  unsigned int plen)
+static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
+			  const struct in6_addr *pfx, unsigned int plen)
 {
 	struct inet6_ifaddr *ifp;
 	struct inet6_dev *idev;
@@ -2528,7 +2523,12 @@ static int inet6_addr_del(struct net *net, int ifindex, const struct in6_addr *p
 			in6_ifa_hold(ifp);
 			read_unlock_bh(&idev->lock);
 
+			if (!(ifp->flags & IFA_F_TEMPORARY) &&
+			    (ifa_flags & IFA_F_MANAGETEMPADDR))
+				manage_tempaddrs(idev, ifp, 0, 0, false,
+						 jiffies);
 			ipv6_del_addr(ifp);
+			addrconf_verify_rtnl();
 			return 0;
 		}
 	}
@@ -2568,7 +2568,7 @@ int addrconf_del_ifaddr(struct net *net, void __user *arg)
 		return -EFAULT;
 
 	rtnl_lock();
-	err = inet6_addr_del(net, ireq.ifr6_ifindex, &ireq.ifr6_addr,
+	err = inet6_addr_del(net, ireq.ifr6_ifindex, 0, &ireq.ifr6_addr,
 			     ireq.ifr6_prefixlen);
 	rtnl_unlock();
 	return err;
@@ -2813,18 +2813,6 @@ static void addrconf_gre_config(struct net_device *dev)
 }
 #endif
 
-static inline int
-ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev)
-{
-	struct in6_addr lladdr;
-
-	if (!ipv6_get_lladdr(link_dev, &lladdr, IFA_F_TENTATIVE)) {
-		addrconf_add_linklocal(idev, &lladdr);
-		return 0;
-	}
-	return -1;
-}
-
 static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			   void *ptr)
 {
@@ -3743,6 +3731,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	struct ifaddrmsg *ifm;
 	struct nlattr *tb[IFA_MAX+1];
 	struct in6_addr *pfx, *peer_pfx;
+	u32 ifa_flags;
 	int err;
 
 	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy);
@@ -3754,7 +3743,13 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh)
 	if (pfx == NULL)
 		return -EINVAL;
 
-	return inet6_addr_del(net, ifm->ifa_index, pfx, ifm->ifa_prefixlen);
+	ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags;
+
+	/* We ignore other flags so far. */
+	ifa_flags &= IFA_F_MANAGETEMPADDR;
+
+	return inet6_addr_del(net, ifm->ifa_index, ifa_flags, pfx,
+			      ifm->ifa_prefixlen);
 }
 
 static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
@@ -4363,7 +4358,7 @@ static inline void __snmp6_fill_statsdev(u64 *stats, atomic_long_t *mib,
 	memset(&stats[items], 0, pad);
 }
 
-static inline void __snmp6_fill_stats64(u64 *stats, void __percpu **mib,
+static inline void __snmp6_fill_stats64(u64 *stats, void __percpu *mib,
 				      int items, int bytes, size_t syncpoff)
 {
 	int i;
@@ -4383,7 +4378,7 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
 {
 	switch (attrtype) {
 	case IFLA_INET6_STATS:
-		__snmp6_fill_stats64(stats, (void __percpu **)idev->stats.ipv6,
+		__snmp6_fill_stats64(stats, idev->stats.ipv6,
 				     IPSTATS_MIB_MAX, bytes, offsetof(struct ipstats_mib, syncp));
 		break;
 	case IFLA_INET6_ICMP6STATS:
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 4c11cbcf830..e6960457f62 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -123,7 +123,7 @@ static void snmp6_free_dev(struct inet6_dev *idev)
 {
 	kfree(idev->stats.icmpv6msgdev);
 	kfree(idev->stats.icmpv6dev);
-	snmp_mib_free((void __percpu **)idev->stats.ipv6);
+	free_percpu(idev->stats.ipv6);
 }
 
 /* Nobody refers to this device, we may destroy it. */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d935889f100..7cb4392690d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -106,7 +106,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	struct inet_protosw *answer;
 	struct proto *answer_prot;
 	unsigned char answer_flags;
-	char answer_no_check;
 	int try_loading_module = 0;
 	int err;
 
@@ -162,7 +161,6 @@ lookup_protocol:
 
 	sock->ops = answer->ops;
 	answer_prot = answer->prot;
-	answer_no_check = answer->no_check;
 	answer_flags = answer->flags;
 	rcu_read_unlock();
 
@@ -176,7 +174,6 @@ lookup_protocol:
 	sock_init_data(sock, sk);
 
 	err = 0;
-	sk->sk_no_check = answer_no_check;
 	if (INET_PROTOSW_REUSE & answer_flags)
 		sk->sk_reuse = SK_CAN_REUSE;
 
@@ -715,33 +712,25 @@ static int __net_init ipv6_init_mibs(struct net *net)
 {
 	int i;
 
-	if (snmp_mib_init((void __percpu **)net->mib.udp_stats_in6,
-			  sizeof(struct udp_mib),
-			  __alignof__(struct udp_mib)) < 0)
+	net->mib.udp_stats_in6 = alloc_percpu(struct udp_mib);
+	if (!net->mib.udp_stats_in6)
 		return -ENOMEM;
-	if (snmp_mib_init((void __percpu **)net->mib.udplite_stats_in6,
-			  sizeof(struct udp_mib),
-			  __alignof__(struct udp_mib)) < 0)
+	net->mib.udplite_stats_in6 = alloc_percpu(struct udp_mib);
+	if (!net->mib.udplite_stats_in6)
 		goto err_udplite_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.ipv6_statistics,
-			  sizeof(struct ipstats_mib),
-			  __alignof__(struct ipstats_mib)) < 0)
+	net->mib.ipv6_statistics = alloc_percpu(struct ipstats_mib);
+	if (!net->mib.ipv6_statistics)
 		goto err_ip_mib;
 
 	for_each_possible_cpu(i) {
 		struct ipstats_mib *af_inet6_stats;
-		af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[0], i);
+		af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics, i);
 		u64_stats_init(&af_inet6_stats->syncp);
-#if SNMP_ARRAY_SZ == 2
-		af_inet6_stats = per_cpu_ptr(net->mib.ipv6_statistics[1], i);
-		u64_stats_init(&af_inet6_stats->syncp);
-#endif
 	}
 
 
-	if (snmp_mib_init((void __percpu **)net->mib.icmpv6_statistics,
-			  sizeof(struct icmpv6_mib),
-			  __alignof__(struct icmpv6_mib)) < 0)
+	net->mib.icmpv6_statistics = alloc_percpu(struct icmpv6_mib);
+	if (!net->mib.icmpv6_statistics)
 		goto err_icmp_mib;
 	net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib),
 						GFP_KERNEL);
@@ -750,22 +739,22 @@ static int __net_init ipv6_init_mibs(struct net *net)
 	return 0;
 
 err_icmpmsg_mib:
-	snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics);
+	free_percpu(net->mib.icmpv6_statistics);
 err_icmp_mib:
-	snmp_mib_free((void __percpu **)net->mib.ipv6_statistics);
+	free_percpu(net->mib.ipv6_statistics);
 err_ip_mib:
-	snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);
+	free_percpu(net->mib.udplite_stats_in6);
 err_udplite_mib:
-	snmp_mib_free((void __percpu **)net->mib.udp_stats_in6);
+	free_percpu(net->mib.udp_stats_in6);
 	return -ENOMEM;
 }
 
 static void ipv6_cleanup_mibs(struct net *net)
 {
-	snmp_mib_free((void __percpu **)net->mib.udp_stats_in6);
-	snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);
-	snmp_mib_free((void __percpu **)net->mib.ipv6_statistics);
-	snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics);
+	free_percpu(net->mib.udp_stats_in6);
+	free_percpu(net->mib.udplite_stats_in6);
+	free_percpu(net->mib.ipv6_statistics);
+	free_percpu(net->mib.icmpv6_statistics);
 	kfree(net->mib.icmpv6msg_statistics);
 }
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 7b326529e6a..f6c84a6eb23 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -400,6 +400,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	int len;
 	int hlimit;
 	int err = 0;
+	u32 mark = IP6_REPLY_MARK(net, skb->mark);
 
 	if ((u8 *)hdr < skb->head ||
 	    (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
@@ -466,6 +467,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	fl6.daddr = hdr->saddr;
 	if (saddr)
 		fl6.saddr = *saddr;
+	fl6.flowi6_mark = mark;
 	fl6.flowi6_oif = iif;
 	fl6.fl6_icmp_type = type;
 	fl6.fl6_icmp_code = code;
@@ -474,6 +476,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	sk = icmpv6_xmit_lock(net);
 	if (sk == NULL)
 		return;
+	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
 	if (!icmpv6_xrlim_allow(sk, type, &fl6))
@@ -493,12 +496,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 	if (IS_ERR(dst))
 		goto out;
 
-	if (ipv6_addr_is_multicast(&fl6.daddr))
-		hlimit = np->mcast_hops;
-	else
-		hlimit = np->hop_limit;
-	if (hlimit < 0)
-		hlimit = ip6_dst_hoplimit(dst);
+	hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	msg.skb = skb;
 	msg.offset = skb_network_offset(skb);
@@ -556,6 +554,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	int err = 0;
 	int hlimit;
 	u8 tclass;
+	u32 mark = IP6_REPLY_MARK(net, skb->mark);
 
 	saddr = &ipv6_hdr(skb)->daddr;
 
@@ -574,11 +573,13 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 		fl6.saddr = *saddr;
 	fl6.flowi6_oif = skb->dev->ifindex;
 	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
+	fl6.flowi6_mark = mark;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
 	if (sk == NULL)
 		return;
+	sk->sk_mark = mark;
 	np = inet6_sk(sk);
 
 	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
@@ -593,12 +594,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	if (IS_ERR(dst))
 		goto out;
 
-	if (ipv6_addr_is_multicast(&fl6.daddr))
-		hlimit = np->mcast_hops;
-	else
-		hlimit = np->hop_limit;
-	if (hlimit < 0)
-		hlimit = ip6_dst_hoplimit(dst);
+	hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	idev = __in6_dev_get(skb->dev);
 
@@ -702,22 +698,11 @@ static int icmpv6_rcv(struct sk_buff *skb)
 	saddr = &ipv6_hdr(skb)->saddr;
 	daddr = &ipv6_hdr(skb)->daddr;
 
-	/* Perform checksum. */
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
-				     skb->csum))
-			break;
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len,
-					     IPPROTO_ICMPV6, 0));
-		if (__skb_checksum_complete(skb)) {
-			LIMIT_NETDEBUG(KERN_DEBUG
-				       "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
-				       saddr, daddr);
-			goto csum_error;
-		}
+	if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) {
+		LIMIT_NETDEBUG(KERN_DEBUG
+			       "ICMPv6 checksum failed [%pI6c > %pI6c]\n",
+			       saddr, daddr);
+		goto csum_error;
 	}
 
 	if (!pskb_pull(skb, sizeof(*hdr)))
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index d4ade34ab37..a245e5ddffb 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -81,7 +81,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 	final_p = fl6_update_dst(fl6, np->opt, &final);
 	fl6->saddr = ireq->ir_v6_loc_addr;
 	fl6->flowi6_oif = ireq->ir_iif;
-	fl6->flowi6_mark = sk->sk_mark;
+	fl6->flowi6_mark = ireq->ir_mark;
 	fl6->fl6_dport = ireq->ir_rmt_port;
 	fl6->fl6_sport = htons(ireq->ir_num);
 	security_req_classify_flow(req, flowi6_to_flowi(fl6));
diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c
index ee7a97f510c..9a4d7322fb2 100644
--- a/net/ipv6/ip6_checksum.c
+++ b/net/ipv6/ip6_checksum.c
@@ -75,25 +75,50 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
 			return err;
 	}
 
-	if (uh->check == 0) {
-		/* RFC 2460 section 8.1 says that we SHOULD log
-		   this error. Well, it is reasonable.
-		 */
-		LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
-			       &ipv6_hdr(skb)->saddr, ntohs(uh->source),
-			       &ipv6_hdr(skb)->daddr, ntohs(uh->dest));
-		return 1;
-	}
-	if (skb->ip_summed == CHECKSUM_COMPLETE &&
-	    !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
-			     skb->len, proto, skb->csum))
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	/* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels)
+	 * we accept a checksum of zero here. When we find the socket
+	 * for the UDP packet we'll check if that socket allows zero checksum
+	 * for IPv6 (set by socket option).
+	 */
+	return skb_checksum_init_zero_check(skb, proto, uh->check,
+					   ip6_compute_pseudo);
+}
+EXPORT_SYMBOL(udp6_csum_init);
+
+/* Function to set UDP checksum for an IPv6 UDP packet. This is intended
+ * for the simple case like when setting the checksum for a UDP tunnel.
+ */
+void udp6_set_csum(bool nocheck, struct sk_buff *skb,
+		   const struct in6_addr *saddr,
+		   const struct in6_addr *daddr, int len)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	if (nocheck)
+		uh->check = 0;
+	else if (skb_is_gso(skb))
+		uh->check = ~udp_v6_check(len, saddr, daddr, 0);
+	else if (skb_dst(skb) && skb_dst(skb)->dev &&
+		 (skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) {
 
-	if (!skb_csum_unnecessary(skb))
-		skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-							 &ipv6_hdr(skb)->daddr,
-							 skb->len, proto, 0));
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
 
-	return 0;
+		skb->ip_summed = CHECKSUM_PARTIAL;
+		skb->csum_start = skb_transport_header(skb) - skb->head;
+		skb->csum_offset = offsetof(struct udphdr, check);
+		uh->check = ~udp_v6_check(len, saddr, daddr, 0);
+	} else {
+		__wsum csum;
+
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, len, 0);
+		uh->check = udp_v6_check(len, saddr, daddr, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
 }
-EXPORT_SYMBOL(udp6_csum_init);
+EXPORT_SYMBOL(udp6_set_csum);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 87891f5f57b..cb4459bd1d2 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -71,8 +71,7 @@ static DEFINE_RWLOCK(fib6_walker_lock);
 #define FWS_INIT FWS_L
 #endif
 
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
-			      struct rt6_info *rt);
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn);
 static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn);
 static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_node *fn);
 static int fib6_walk(struct fib6_walker_t *w);
@@ -941,7 +940,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
 	if (!err) {
 		fib6_start_gc(info->nl_net, rt);
 		if (!(rt->rt6i_flags & RTF_CACHE))
-			fib6_prune_clones(info->nl_net, pn, rt);
+			fib6_prune_clones(info->nl_net, pn);
 	}
 
 out:
@@ -1375,7 +1374,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
 			pn = pn->parent;
 		}
 #endif
-		fib6_prune_clones(info->nl_net, pn, rt);
+		fib6_prune_clones(info->nl_net, pn);
 	}
 
 	/*
@@ -1601,10 +1600,9 @@ static int fib6_prune_clone(struct rt6_info *rt, void *arg)
 	return 0;
 }
 
-static void fib6_prune_clones(struct net *net, struct fib6_node *fn,
-			      struct rt6_info *rt)
+static void fib6_prune_clones(struct net *net, struct fib6_node *fn)
 {
-	fib6_clean_tree(net, fn, fib6_prune_clone, 1, rt);
+	fib6_clean_tree(net, fn, fib6_prune_clone, 1, NULL);
 }
 
 /*
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 0961b5ef866..4052694c6f2 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -26,7 +26,6 @@
 #include <net/sock.h>
 
 #include <net/ipv6.h>
-#include <net/addrconf.h>
 #include <net/rawv6.h>
 #include <net/transp_v6.h>
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 9d921462b57..3873181ed85 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -72,6 +72,7 @@ struct ip6gre_net {
 };
 
 static struct rtnl_link_ops ip6gre_link_ops __read_mostly;
+static struct rtnl_link_ops ip6gre_tap_ops __read_mostly;
 static int ip6gre_tunnel_init(struct net_device *dev);
 static void ip6gre_tunnel_setup(struct net_device *dev);
 static void ip6gre_tunnel_link(struct ip6gre_net *ign, struct ip6_tnl *t);
@@ -353,10 +354,10 @@ failed_free:
 
 static void ip6gre_tunnel_uninit(struct net_device *dev)
 {
-	struct net *net = dev_net(dev);
-	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 
-	ip6gre_tunnel_unlink(ign, netdev_priv(dev));
+	ip6gre_tunnel_unlink(ign, t);
 	dev_put(dev);
 }
 
@@ -467,17 +468,7 @@ static int ip6gre_rcv(struct sk_buff *skb)
 			goto drop;
 
 		if (flags&GRE_CSUM) {
-			switch (skb->ip_summed) {
-			case CHECKSUM_COMPLETE:
-				csum = csum_fold(skb->csum);
-				if (!csum)
-					break;
-				/* fall through */
-			case CHECKSUM_NONE:
-				skb->csum = 0;
-				csum = __skb_checksum_complete(skb);
-				skb->ip_summed = CHECKSUM_COMPLETE;
-			}
+			csum = skb_checksum_simple_validate(skb);
 			offset += 4;
 		}
 		if (flags&GRE_KEY) {
@@ -611,8 +602,8 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
 			 int encap_limit,
 			 __u32 *pmtu)
 {
-	struct net *net = dev_net(dev);
 	struct ip6_tnl *tunnel = netdev_priv(dev);
+	struct net *net = tunnel->net;
 	struct net_device *tdev;    /* Device to other host */
 	struct ipv6hdr  *ipv6h;     /* Our new IP header */
 	unsigned int max_headroom = 0; /* The extra header space needed */
@@ -979,7 +970,7 @@ static void ip6gre_tnl_link_config(struct ip6_tnl *t, int set_mtu)
 		int strict = (ipv6_addr_type(&p->raddr) &
 			      (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
 
-		struct rt6_info *rt = rt6_lookup(dev_net(dev),
+		struct rt6_info *rt = rt6_lookup(t->net,
 						 &p->raddr, &p->laddr,
 						 p->link, strict);
 
@@ -1063,13 +1054,12 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 	int err = 0;
 	struct ip6_tnl_parm2 p;
 	struct __ip6_tnl_parm p1;
-	struct ip6_tnl *t;
-	struct net *net = dev_net(dev);
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct net *net = t->net;
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 
 	switch (cmd) {
 	case SIOCGETTUNNEL:
-		t = NULL;
 		if (dev == ign->fb_tunnel_dev) {
 			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
 				err = -EFAULT;
@@ -1077,9 +1067,9 @@ static int ip6gre_tunnel_ioctl(struct net_device *dev,
 			}
 			ip6gre_tnl_parm_from_user(&p1, &p);
 			t = ip6gre_tunnel_locate(net, &p1, 0);
+			if (t == NULL)
+				t = netdev_priv(dev);
 		}
-		if (t == NULL)
-			t = netdev_priv(dev);
 		memset(&p, 0, sizeof(p));
 		ip6gre_tnl_parm_to_user(&p, &t->parms);
 		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
@@ -1242,7 +1232,6 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
 	dev->flags |= IFF_NOARP;
 	dev->iflink = 0;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->features |= NETIF_F_NETNS_LOCAL;
 	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
 }
 
@@ -1297,11 +1286,17 @@ static struct inet6_protocol ip6gre_protocol __read_mostly = {
 	.flags       = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
 };
 
-static void ip6gre_destroy_tunnels(struct ip6gre_net *ign,
-	struct list_head *head)
+static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head)
 {
+	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
+	struct net_device *dev, *aux;
 	int prio;
 
+	for_each_netdev_safe(net, dev, aux)
+		if (dev->rtnl_link_ops == &ip6gre_link_ops ||
+		    dev->rtnl_link_ops == &ip6gre_tap_ops)
+			unregister_netdevice_queue(dev, head);
+
 	for (prio = 0; prio < 4; prio++) {
 		int h;
 		for (h = 0; h < HASH_SIZE; h++) {
@@ -1310,7 +1305,12 @@ static void ip6gre_destroy_tunnels(struct ip6gre_net *ign,
 			t = rtnl_dereference(ign->tunnels[prio][h]);
 
 			while (t != NULL) {
-				unregister_netdevice_queue(t->dev, head);
+				/* If dev is in the same netns, it has already
+				 * been added to the list by the previous loop.
+				 */
+				if (!net_eq(dev_net(t->dev), net))
+					unregister_netdevice_queue(t->dev,
+								   head);
 				t = rtnl_dereference(t->next);
 			}
 		}
@@ -1329,6 +1329,11 @@ static int __net_init ip6gre_init_net(struct net *net)
 		goto err_alloc_dev;
 	}
 	dev_net_set(ign->fb_tunnel_dev, net);
+	/* FB netdevice is special: we have one, and only one per netns.
+	 * Allowing to move it to another netns is clearly unsafe.
+	 */
+	ign->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+
 
 	ip6gre_fb_tunnel_init(ign->fb_tunnel_dev);
 	ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops;
@@ -1349,12 +1354,10 @@ err_alloc_dev:
 
 static void __net_exit ip6gre_exit_net(struct net *net)
 {
-	struct ip6gre_net *ign;
 	LIST_HEAD(list);
 
-	ign = net_generic(net, ip6gre_net_id);
 	rtnl_lock();
-	ip6gre_destroy_tunnels(ign, &list);
+	ip6gre_destroy_tunnels(net, &list);
 	unregister_netdevice_many(&list);
 	rtnl_unlock();
 }
@@ -1531,15 +1534,14 @@ out:
 static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct nlattr *data[])
 {
-	struct ip6_tnl *t, *nt;
-	struct net *net = dev_net(dev);
+	struct ip6_tnl *t, *nt = netdev_priv(dev);
+	struct net *net = nt->net;
 	struct ip6gre_net *ign = net_generic(net, ip6gre_net_id);
 	struct __ip6_tnl_parm p;
 
 	if (dev == ign->fb_tunnel_dev)
 		return -EINVAL;
 
-	nt = netdev_priv(dev);
 	ip6gre_netlink_parms(data, &p);
 
 	t = ip6gre_tunnel_locate(net, &p, 0);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index b2f091566f8..65eda2a8af4 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -97,9 +97,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 		       SKB_GSO_DODGY |
 		       SKB_GSO_TCP_ECN |
 		       SKB_GSO_GRE |
+		       SKB_GSO_GRE_CSUM |
 		       SKB_GSO_IPIP |
 		       SKB_GSO_SIT |
 		       SKB_GSO_UDP_TUNNEL |
+		       SKB_GSO_UDP_TUNNEL_CSUM |
 		       SKB_GSO_MPLS |
 		       SKB_GSO_TCPV6 |
 		       0)))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index fbf11562b54..45702b8cd14 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -219,7 +219,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	skb->mark = sk->sk_mark;
 
 	mtu = dst_mtu(dst);
-	if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
+	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
 		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			      IPSTATS_MIB_OUT, skb->len);
 		return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
@@ -347,11 +347,11 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 	if (skb->len <= mtu)
 		return false;
 
-	/* ipv6 conntrack defrag sets max_frag_size + local_df */
+	/* ipv6 conntrack defrag sets max_frag_size + ignore_df */
 	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
 		return true;
 
-	if (skb->local_df)
+	if (skb->ignore_df)
 		return false;
 
 	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
@@ -537,6 +537,20 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
+static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 hash, id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
+	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
+
+	id = ip_idents_reserve(hash, 1);
+	fhdr->identification = htonl(id);
+}
+
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
@@ -559,7 +573,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	/* We must not fragment if the socket is set to force MTU discovery
 	 * or if the skb it not generated by a local socket.
 	 */
-	if (unlikely(!skb->local_df && skb->len > mtu) ||
+	if (unlikely(!skb->ignore_df && skb->len > mtu) ||
 		     (IP6CB(skb)->frag_max_size &&
 		      IP6CB(skb)->frag_max_size > mtu)) {
 		if (skb->sk && dst_allfrag(skb_dst(skb)))
@@ -1234,7 +1248,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 			      sizeof(struct frag_hdr) : 0) +
 			     rt->rt6i_nfheader_len;
 
-		if (ip6_sk_local_df(sk))
+		if (ip6_sk_ignore_df(sk))
 			maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
 		else
 			maxnonfragsize = mtu;
@@ -1544,7 +1558,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	}
 
 	/* Allow local fragmentation. */
-	skb->local_df = ip6_sk_local_df(sk);
+	skb->ignore_df = ip6_sk_ignore_df(sk);
 
 	*final_dst = fl6->daddr;
 	__skb_pull(skb, skb_network_header_len(skb));
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index f6a66bb4114..afa08245836 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -61,6 +61,7 @@
 MODULE_AUTHOR("Ville Nuorvala");
 MODULE_DESCRIPTION("IPv6 tunneling device");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ip6tnl");
 MODULE_ALIAS_NETDEV("ip6tnl0");
 
 #ifdef IP6_TNL_DEBUG
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 6cc9f9371cc..9aaa6bb229e 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -795,15 +795,12 @@ static const struct net_device_ops vti6_netdev_ops = {
  **/
 static void vti6_dev_setup(struct net_device *dev)
 {
-	struct ip6_tnl *t;
-
 	dev->netdev_ops = &vti6_netdev_ops;
 	dev->destructor = vti6_dev_free;
 
 	dev->type = ARPHRD_TUNNEL6;
 	dev->hard_header_len = LL_MAX_HEADER + sizeof(struct ipv6hdr);
 	dev->mtu = ETH_DATA_LEN;
-	t = netdev_priv(dev);
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
 	dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 08b367c6b9c..617f0958e16 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1301,8 +1301,17 @@ int igmp6_event_query(struct sk_buff *skb)
 	len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr);
 	len -= skb_network_header_len(skb);
 
-	/* Drop queries with not link local source */
-	if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL))
+	/* RFC3810 6.2
+	 * Upon reception of an MLD message that contains a Query, the node
+	 * checks if the source address of the message is a valid link-local
+	 * address, if the Hop Limit is set to 1, and if the Router Alert
+	 * option is present in the Hop-By-Hop Options header of the IPv6
+	 * packet.  If any of these checks fails, the packet is dropped.
+	 */
+	if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) ||
+	    ipv6_hdr(skb)->hop_limit != 1 ||
+	    !(IP6CB(skb)->flags & IP6SKB_ROUTERALERT) ||
+	    IP6CB(skb)->ra != htons(IPV6_OPT_ROUTERALERT_MLD))
 		return -EINVAL;
 
 	idev = __in6_dev_get(skb->dev);
diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
index 84c7f33d0cf..387d8b8fc18 100644
--- a/net/ipv6/netfilter/ip6table_nat.c
+++ b/net/ipv6/netfilter/ip6table_nat.c
@@ -90,17 +90,9 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
 	if (nf_ct_is_untracked(ct))
 		return NF_ACCEPT;
 
-	nat = nfct_nat(ct);
-	if (!nat) {
-		/* NAT module was loaded late. */
-		if (nf_ct_is_confirmed(ct))
-			return NF_ACCEPT;
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL) {
-			pr_debug("failed to add NAT extension\n");
-			return NF_ACCEPT;
-		}
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 767ab8da821..0d5279fd852 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -451,7 +451,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
 	}
 	sub_frag_mem_limit(&fq->q, head->truesize);
 
-	head->local_df = 1;
+	head->ignore_df = 1;
 	head->next = NULL;
 	head->dev = dev;
 	head->tstamp = fq->q.stamp;
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
index 9c3297a768f..d189fcb437f 100644
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
@@ -47,15 +47,9 @@ static unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops,
 	if (ct == NULL || nf_ct_is_untracked(ct))
 		return NF_ACCEPT;
 
-	nat = nfct_nat(ct);
-	if (nat == NULL) {
-		/* Conntrack module was loaded late, can't add extension. */
-		if (nf_ct_is_confirmed(ct))
-			return NF_ACCEPT;
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL)
-			return NF_ACCEPT;
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	switch (ctinfo) {
 	case IP_CT_RELATED:
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 56596ce390a..5ec867e4a8b 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -8,32 +8,6 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
-void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static atomic_t ipv6_fragmentation_id;
-	struct in6_addr addr;
-	int ident;
-
-#if IS_ENABLED(CONFIG_IPV6)
-	struct inet_peer *peer;
-	struct net *net;
-
-	net = dev_net(rt->dst.dev);
-	peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
-	if (peer) {
-		fhdr->identification = htonl(inet_getid(peer, 0));
-		inet_putpeer(peer);
-		return;
-	}
-#endif
-	ident = atomic_inc_return(&ipv6_fragmentation_id);
-
-	addr = rt->rt6i_dst.addr;
-	addr.s6_addr32[0] ^= (__force __be32)ident;
-	fhdr->identification = htonl(secure_ipv6_id(addr.s6_addr32));
-}
-EXPORT_SYMBOL(ipv6_select_ident);
-
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
@@ -104,6 +78,7 @@ int __ip6_local_out(struct sk_buff *skb)
 	if (len > IPV6_MAXPLEN)
 		len = 0;
 	ipv6_hdr(skb)->payload_len = htons(len);
+	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
 	return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
 		       skb_dst(skb)->dev, dst_output);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index bda74291c3e..5b7a1ed2aba 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -51,7 +51,6 @@ static struct inet_protosw pingv6_protosw = {
 	.protocol =  IPPROTO_ICMPV6,
 	.prot =      &pingv6_prot,
 	.ops =       &inet6_dgram_ops,
-	.no_check =  UDP_CSUM_DEFAULT,
 	.flags =     INET_PROTOSW_REUSE,
 };
 
@@ -168,12 +167,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	pfh.wcheck = 0;
 	pfh.family = AF_INET6;
 
-	if (ipv6_addr_is_multicast(&fl6.daddr))
-		hlimit = np->mcast_hops;
-	else
-		hlimit = np->hop_limit;
-	if (hlimit < 0)
-		hlimit = ip6_dst_hoplimit(dst);
+	hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	lock_sock(sk);
 	err = ip6_append_data(sk, ping_getfrag, &pfh, len,
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 091d066a57b..3317440ea34 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -186,7 +186,7 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, atomic_long_t *smib)
 /* can be called either with percpu mib (pcpumib != NULL),
  * or shared one (smib != NULL)
  */
-static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **pcpumib,
+static void snmp6_seq_show_item(struct seq_file *seq, void __percpu *pcpumib,
 				atomic_long_t *smib,
 				const struct snmp_mib *itemlist)
 {
@@ -201,7 +201,7 @@ static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **pcpumib,
 	}
 }
 
-static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu **mib,
+static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib,
 				  const struct snmp_mib *itemlist, size_t syncpoff)
 {
 	int i;
@@ -215,14 +215,14 @@ static int snmp6_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = (struct net *)seq->private;
 
-	snmp6_seq_show_item64(seq, (void __percpu **)net->mib.ipv6_statistics,
+	snmp6_seq_show_item64(seq, net->mib.ipv6_statistics,
 			    snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp));
-	snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics,
+	snmp6_seq_show_item(seq, net->mib.icmpv6_statistics,
 			    NULL, snmp6_icmp6_list);
 	snmp6_seq_show_icmpv6msg(seq, net->mib.icmpv6msg_statistics->mibs);
-	snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6,
+	snmp6_seq_show_item(seq, net->mib.udp_stats_in6,
 			    NULL, snmp6_udp6_list);
-	snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6,
+	snmp6_seq_show_item(seq, net->mib.udplite_stats_in6,
 			    NULL, snmp6_udplite6_list);
 	return 0;
 }
@@ -245,7 +245,7 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
 	struct inet6_dev *idev = (struct inet6_dev *)seq->private;
 
 	seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex);
-	snmp6_seq_show_item64(seq, (void __percpu **)idev->stats.ipv6,
+	snmp6_seq_show_item64(seq, idev->stats.ipv6,
 			    snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp));
 	snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs,
 			    snmp6_icmp6_list);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 1f29996e368..b2dc60b0c76 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -873,14 +873,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		err = PTR_ERR(dst);
 		goto out;
 	}
-	if (hlimit < 0) {
-		if (ipv6_addr_is_multicast(&fl6.daddr))
-			hlimit = np->mcast_hops;
-		else
-			hlimit = np->hop_limit;
-		if (hlimit < 0)
-			hlimit = ip6_dst_hoplimit(dst);
-	}
+	if (hlimit < 0)
+		hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	if (tclass < 0)
 		tclass = np->tclass;
@@ -1328,7 +1322,6 @@ static struct inet_protosw rawv6_protosw = {
 	.protocol	= IPPROTO_IP,	/* wild card */
 	.prot		= &rawv6_prot,
 	.ops		= &inet6_sockraw_ops,
-	.no_check	= UDP_CSUM_DEFAULT,
 	.flags		= INET_PROTOSW_REUSE,
 };
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6ebdb7b6744..f23fbd28a50 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1176,7 +1176,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_oif = oif;
-	fl6.flowi6_mark = mark;
+	fl6.flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark);
 	fl6.daddr = iph->daddr;
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = ip6_flowinfo(iph);
@@ -1455,7 +1455,7 @@ static int ip6_dst_gc(struct dst_ops *ops)
 		goto out;
 
 	net->ipv6.ip6_rt_gc_expire++;
-	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size);
+	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true);
 	entries = dst_entries_get_slow(ops);
 	if (entries < ops->gc_thresh)
 		net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e5a453ca302..4f408176dc6 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -560,12 +560,12 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+				 t->parms.link, 0, IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
 	}
 	if (type == ICMP_REDIRECT) {
-		ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
+		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
 			      IPPROTO_IPV6, 0);
 		err = 0;
 		goto out;
@@ -1828,4 +1828,5 @@ xfrm_tunnel_failed:
 module_init(sit_init);
 module_exit(sit_cleanup);
 MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("sit");
 MODULE_ALIAS_NETDEV("sit0");
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bb53a5e73c1..a822b880689 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -216,6 +216,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
 		ireq->ir_iif = inet6_iif(skb);
 
+	ireq->ir_mark = inet_request_mark(sk, skb);
+
 	req->expires = 0UL;
 	req->num_retrans = 0;
 	ireq->ecn_ok		= ecn_ok;
@@ -242,7 +244,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		final_p = fl6_update_dst(&fl6, np->opt, &final);
 		fl6.saddr = ireq->ir_v6_loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
-		fl6.flowi6_mark = sk->sk_mark;
+		fl6.flowi6_mark = ireq->ir_mark;
 		fl6.fl6_dport = ireq->ir_rmt_port;
 		fl6.fl6_sport = inet_sk(sk)->inet_sport;
 		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c
index 7f405a16882..058f3eca2e5 100644
--- a/net/ipv6/sysctl_net_ipv6.c
+++ b/net/ipv6/sysctl_net_ipv6.c
@@ -38,6 +38,13 @@ static struct ctl_table ipv6_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "fwmark_reflect",
+		.data		= &init_net.ipv6.sysctl.fwmark_reflect,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 	{ }
 };
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e289830ed6e..229239ad96b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -340,7 +340,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct sock *sk;
 	int err;
 	struct tcp_sock *tp;
-	__u32 seq;
+	struct request_sock *fastopen;
+	__u32 seq, snd_una;
 	struct net *net = dev_net(skb->dev);
 
 	sk = inet6_lookup(net, &tcp_hashinfo, &hdr->daddr,
@@ -371,8 +372,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	tp = tcp_sk(sk);
 	seq = ntohl(th->seq);
+	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
+	fastopen = tp->fastopen_rsk;
+	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
-	    !between(seq, tp->snd_una, tp->snd_nxt)) {
+	    !between(seq, snd_una, tp->snd_nxt)) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
 		goto out;
 	}
@@ -436,8 +440,13 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		goto out;
 
 	case TCP_SYN_SENT:
-	case TCP_SYN_RECV:  /* Cannot happen.
-			       It can, it SYNs are crossed. --ANK */
+	case TCP_SYN_RECV:
+		/* Only in fast or simultaneous open. If a fast open socket is
+		 * is already accepted it is treated as a connected one below.
+		 */
+		if (fastopen && fastopen->sk == NULL)
+			break;
+
 		if (!sock_owned_by_user(sk)) {
 			sk->sk_err = err;
 			sk->sk_error_report(sk);		/* Wake people up to see the error (see connect in sock.c) */
@@ -463,7 +472,8 @@ out:
 static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 			      struct flowi6 *fl6,
 			      struct request_sock *req,
-			      u16 queue_mapping)
+			      u16 queue_mapping,
+			      struct tcp_fastopen_cookie *foc)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -474,7 +484,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
 	if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL)
 		goto done;
 
-	skb = tcp_make_synack(sk, dst, req, NULL);
+	skb = tcp_make_synack(sk, dst, req, foc);
 
 	if (skb) {
 		__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
@@ -498,7 +508,7 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req)
 	struct flowi6 fl6;
 	int res;
 
-	res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0);
+	res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0, NULL);
 	if (!res) {
 		TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
 		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
@@ -802,6 +812,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 		fl6.flowi6_oif = inet6_iif(skb);
 	else
 		fl6.flowi6_oif = oif;
+	fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark);
 	fl6.fl6_dport = t1->dest;
 	fl6.fl6_sport = t1->source;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
@@ -917,7 +928,12 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req)
 {
-	tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1,
+	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
+	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
+	 */
+	tcp_v6_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
+			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+			tcp_rsk(req)->rcv_nxt,
 			req->rcv_wnd, tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
 			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
 			0, 0);
@@ -969,8 +985,10 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	__u32 isn = TCP_SKB_CB(skb)->when;
 	struct dst_entry *dst = NULL;
+	struct tcp_fastopen_cookie foc = { .len = -1 };
+	bool want_cookie = false, fastopen;
 	struct flowi6 fl6;
-	bool want_cookie = false;
+	int err;
 
 	if (skb->protocol == htons(ETH_P_IP))
 		return tcp_v4_conn_request(sk, skb);
@@ -1001,7 +1019,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_clear_options(&tmp_opt);
 	tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
 	tmp_opt.user_mss = tp->rx_opt.user_mss;
-	tcp_parse_options(skb, &tmp_opt, 0, NULL);
+	tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
 
 	if (want_cookie && !tmp_opt.saw_tstamp)
 		tcp_clear_options(&tmp_opt);
@@ -1016,6 +1034,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		TCP_ECN_create_request(req, skb, sock_net(sk));
 
 	ireq->ir_iif = sk->sk_bound_dev_if;
+	ireq->ir_mark = inet_request_mark(sk, skb);
 
 	/* So that link locals have meaning */
 	if (!sk->sk_bound_dev_if &&
@@ -1074,19 +1093,27 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		isn = tcp_v6_init_sequence(skb);
 	}
 have_isn:
-	tcp_rsk(req)->snt_isn = isn;
 
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_release;
 
-	if (tcp_v6_send_synack(sk, dst, &fl6, req,
-			       skb_get_queue_mapping(skb)) ||
-	    want_cookie)
+	if (!dst && (dst = inet6_csk_route_req(sk, &fl6, req)) == NULL)
 		goto drop_and_free;
 
+	tcp_rsk(req)->snt_isn = isn;
 	tcp_rsk(req)->snt_synack = tcp_time_stamp;
-	tcp_rsk(req)->listener = NULL;
-	inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+	tcp_openreq_init_rwin(req, sk, dst);
+	fastopen = !want_cookie &&
+		   tcp_try_fastopen(sk, skb, req, &foc, dst);
+	err = tcp_v6_send_synack(sk, dst, &fl6, req,
+				 skb_get_queue_mapping(skb), &foc);
+	if (!fastopen) {
+		if (err || want_cookie)
+			goto drop_and_free;
+
+		tcp_rsk(req)->listener = NULL;
+		inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+	}
 	return 0;
 
 drop_and_release:
@@ -1294,25 +1321,6 @@ out:
 	return NULL;
 }
 
-static __sum16 tcp_v6_checksum_init(struct sk_buff *skb)
-{
-	if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		if (!tcp_v6_check(skb->len, &ipv6_hdr(skb)->saddr,
-				  &ipv6_hdr(skb)->daddr, skb->csum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			return 0;
-		}
-	}
-
-	skb->csum = ~csum_unfold(tcp_v6_check(skb->len,
-					      &ipv6_hdr(skb)->saddr,
-					      &ipv6_hdr(skb)->daddr, 0));
-
-	if (skb->len <= 76)
-		return __skb_checksum_complete(skb);
-	return 0;
-}
-
 /* The socket must have it's spinlock held when we get
  * here.
  *
@@ -1486,7 +1494,7 @@ static int tcp_v6_rcv(struct sk_buff *skb)
 	if (!pskb_may_pull(skb, th->doff*4))
 		goto discard_it;
 
-	if (!skb_csum_unnecessary(skb) && tcp_v6_checksum_init(skb))
+	if (skb_checksum_init(skb, IPPROTO_TCP, ip6_compute_pseudo))
 		goto csum_error;
 
 	th = tcp_hdr(skb);
@@ -1779,6 +1787,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	const struct inet_sock *inet = inet_sk(sp);
 	const struct tcp_sock *tp = tcp_sk(sp);
 	const struct inet_connection_sock *icsk = inet_csk(sp);
+	struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq;
 
 	dest  = &sp->sk_v6_daddr;
 	src   = &sp->sk_v6_rcv_saddr;
@@ -1821,7 +1830,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		   jiffies_to_clock_t(icsk->icsk_ack.ato),
 		   (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
 		   tp->snd_cwnd,
-		   tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh
+		   sp->sk_state == TCP_LISTEN ?
+			(fastopenq ? fastopenq->max_qlen : 0) :
+			(tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)
 		   );
 }
 
@@ -1981,7 +1992,6 @@ static struct inet_protosw tcpv6_protosw = {
 	.protocol	=	IPPROTO_TCP,
 	.prot		=	&tcpv6_prot,
 	.ops		=	&inet6_stream_ops,
-	.no_check	=	0,
 	.flags		=	INET_PROTOSW_PERMANENT |
 				INET_PROTOSW_ICSK,
 };
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 8517d3cd1ae..01b0ff9a0c2 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -73,7 +73,7 @@ static int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 
 	th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr,
 				  &iph->daddr, 0);
-	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
 
 	return tcp_gro_complete(skb);
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1e586d92260..7092ff78fd8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -634,6 +634,10 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) {
 			int ret;
 
+			/* Verify checksum before giving to encap */
+			if (udp_lib_checksum_complete(skb))
+				goto csum_error;
+
 			ret = encap_rcv(sk, skb);
 			if (ret <= 0) {
 				UDP_INC_STATS_BH(sock_net(sk),
@@ -670,8 +674,11 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 			goto csum_error;
 	}
 
-	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf))
+	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) {
+		UDP6_INC_STATS_BH(sock_net(sk),
+				  UDP_MIB_RCVBUFERRORS, is_udplite);
 		goto drop;
+	}
 
 	skb_dst_drop(skb);
 
@@ -686,6 +693,7 @@ int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	bh_unlock_sock(sk);
 
 	return rc;
+
 csum_error:
 	UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 drop:
@@ -701,17 +709,16 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 				      int dif)
 {
 	struct hlist_nulls_node *node;
-	struct sock *s = sk;
 	unsigned short num = ntohs(loc_port);
 
-	sk_nulls_for_each_from(s, node) {
-		struct inet_sock *inet = inet_sk(s);
+	sk_nulls_for_each_from(sk, node) {
+		struct inet_sock *inet = inet_sk(sk);
 
-		if (!net_eq(sock_net(s), net))
+		if (!net_eq(sock_net(sk), net))
 			continue;
 
-		if (udp_sk(s)->udp_port_hash == num &&
-		    s->sk_family == PF_INET6) {
+		if (udp_sk(sk)->udp_port_hash == num &&
+		    sk->sk_family == PF_INET6) {
 			if (inet->inet_dport) {
 				if (inet->inet_dport != rmt_port)
 					continue;
@@ -720,16 +727,16 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
 			    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
 				continue;
 
-			if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
+			if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
 				continue;
 
 			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
 				if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
 					continue;
 			}
-			if (!inet6_mc_check(s, loc_addr, rmt_addr))
+			if (!inet6_mc_check(sk, loc_addr, rmt_addr))
 				continue;
-			return s;
+			return sk;
 		}
 	}
 	return NULL;
@@ -760,6 +767,17 @@ static void flush_stack(struct sock **stack, unsigned int count,
 	if (unlikely(skb1))
 		kfree_skb(skb1);
 }
+
+static void udp6_csum_zero_error(struct sk_buff *skb)
+{
+	/* RFC 2460 section 8.1 says that we SHOULD log
+	 * this error. Well, it is reasonable.
+	 */
+	LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
+		       &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source),
+		       &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest));
+}
+
 /*
  * Note: called only from the BH handler context,
  * so we don't need to lock the hashes.
@@ -779,7 +797,12 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 	dif = inet6_iif(skb);
 	sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
 	while (sk) {
-		stack[count++] = sk;
+		/* If zero checksum and no_check is not on for
+		 * the socket then skip it.
+		 */
+		if (uh->check || udp_sk(sk)->no_check6_rx)
+			stack[count++] = sk;
+
 		sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr,
 				       uh->source, saddr, dif);
 		if (unlikely(count == ARRAY_SIZE(stack))) {
@@ -867,6 +890,12 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (sk != NULL) {
 		int ret;
 
+		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
+			sock_put(sk);
+			udp6_csum_zero_error(skb);
+			goto csum_error;
+		}
+
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
@@ -879,6 +908,11 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		return 0;
 	}
 
+	if (!uh->check) {
+		udp6_csum_zero_error(skb);
+		goto csum_error;
+	}
+
 	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto discard;
 
@@ -1006,7 +1040,10 @@ static int udp_v6_push_pending_frames(struct sock *sk)
 
 	if (is_udplite)
 		csum = udplite_csum_outgoing(sk, skb);
-	else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
+	else if (up->no_check6_tx) {   /* UDP csum disabled */
+		skb->ip_summed = CHECKSUM_NONE;
+		goto send;
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
 		udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr,
 				     up->len);
 		goto send;
@@ -1232,14 +1269,8 @@ do_udp_sendmsg:
 		goto out;
 	}
 
-	if (hlimit < 0) {
-		if (ipv6_addr_is_multicast(&fl6.daddr))
-			hlimit = np->mcast_hops;
-		else
-			hlimit = np->hop_limit;
-		if (hlimit < 0)
-			hlimit = ip6_dst_hoplimit(dst);
-	}
+	if (hlimit < 0)
+		hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	if (tclass < 0)
 		tclass = np->tclass;
@@ -1479,7 +1510,6 @@ static struct inet_protosw udpv6_protosw = {
 	.protocol =  IPPROTO_UDP,
 	.prot =      &udpv6_prot,
 	.ops =       &inet6_dgram_ops,
-	.no_check =  UDP_CSUM_DEFAULT,
 	.flags =     INET_PROTOSW_PERMANENT,
 };
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b261ee8b83f..0ae3d98f83e 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -63,7 +63,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		if (unlikely(type & ~(SKB_GSO_UDP |
 				      SKB_GSO_DODGY |
 				      SKB_GSO_UDP_TUNNEL |
+				      SKB_GSO_UDP_TUNNEL_CSUM |
 				      SKB_GSO_GRE |
+				      SKB_GSO_GRE_CSUM |
 				      SKB_GSO_IPIP |
 				      SKB_GSO_SIT |
 				      SKB_GSO_MPLS) ||
@@ -76,7 +78,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		goto out;
 	}
 
-	if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
+	if (skb->encapsulation && skb_shinfo(skb)->gso_type &
+	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
 		segs = skb_udp_tunnel_segment(skb, features);
 	else {
 		/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index dfcc4be4689..9cf097e206e 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -64,7 +64,6 @@ static struct inet_protosw udplite6_protosw = {
 	.protocol	= IPPROTO_UDPLITE,
 	.prot		= &udplitev6_prot,
 	.ops		= &inet6_dgram_ops,
-	.no_check	= 0,
 	.flags		= INET_PROTOSW_PERMANENT,
 };
 
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index b930d080c66..433672d07d0 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -78,7 +78,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb)
 	if (mtu < IPV6_MIN_MTU)
 		mtu = IPV6_MIN_MTU;
 
-	if (!skb->local_df && skb->len > mtu) {
+	if (!skb->ignore_df && skb->len > mtu) {
 		skb->dev = dst->dev;
 
 		if (xfrm6_local_dontfrag(skb))
@@ -114,7 +114,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	return x->outer_mode->output2(x, skb);
 }
@@ -153,7 +153,7 @@ static int __xfrm6_output(struct sk_buff *skb)
 	if (skb->len > mtu && xfrm6_local_dontfrag(skb)) {
 		xfrm6_local_rxpmtu(skb, mtu);
 		return -EMSGSIZE;
-	} else if (!skb->local_df && skb->len > mtu && skb->sk) {
+	} else if (!skb->ignore_df && skb->len > mtu && skb->sk) {
 		xfrm_local_error(skb, mtu);
 		return -EMSGSIZE;
 	}
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 41e4e93cb3a..91729b807c7 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -1353,7 +1353,7 @@ static int ipx_create(struct net *net, struct socket *sock, int protocol,
 
 	sk_refcnt_debug_inc(sk);
 	sock_init_data(sock, sk);
-	sk->sk_no_check = 1;		/* Checksum off by default */
+	sk->sk_no_check_tx = 1;		/* Checksum off by default */
 	sock->ops = &ipx_dgram_ops;
 	rc = 0;
 out:
diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c
index c1f03185c5e..67e7ad3d46b 100644
--- a/net/ipx/ipx_route.c
+++ b/net/ipx/ipx_route.c
@@ -236,7 +236,8 @@ int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx,
 	}
 
 	/* Apply checksum. Not allowed on 802.3 links. */
-	if (sk->sk_no_check || intrfc->if_dlink_type == htons(IPX_FRAME_8023))
+	if (sk->sk_no_check_tx ||
+	    intrfc->if_dlink_type == htons(IPX_FRAME_8023))
 		ipx->ipx_checksum = htons(0xFFFF);
 	else
 		ipx->ipx_checksum = ipx_cksum(ipx, len + sizeof(struct ipxhdr));
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 8c9d7302c84..7a95fa4a3de 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -682,6 +682,18 @@ struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock)
 	return NULL;
 }
 
+static void __iucv_auto_name(struct iucv_sock *iucv)
+{
+	char name[12];
+
+	sprintf(name, "%08x", atomic_inc_return(&iucv_sk_list.autobind_name));
+	while (__iucv_get_sock_by_name(name)) {
+		sprintf(name, "%08x",
+			atomic_inc_return(&iucv_sk_list.autobind_name));
+	}
+	memcpy(iucv->src_name, name, 8);
+}
+
 /* Bind an unbound socket */
 static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
 			  int addr_len)
@@ -724,8 +736,12 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
 	rcu_read_lock();
 	for_each_netdev_rcu(&init_net, dev) {
 		if (!memcmp(dev->perm_addr, uid, 8)) {
-			memcpy(iucv->src_name, sa->siucv_name, 8);
 			memcpy(iucv->src_user_id, sa->siucv_user_id, 8);
+			/* Check for unitialized siucv_name */
+			if (strncmp(sa->siucv_name, "        ", 8) == 0)
+				__iucv_auto_name(iucv);
+			else
+				memcpy(iucv->src_name, sa->siucv_name, 8);
 			sk->sk_bound_dev_if = dev->ifindex;
 			iucv->hs_dev = dev;
 			dev_hold(dev);
@@ -763,7 +779,6 @@ done:
 static int iucv_sock_autobind(struct sock *sk)
 {
 	struct iucv_sock *iucv = iucv_sk(sk);
-	char name[12];
 	int err = 0;
 
 	if (unlikely(!pr_iucv))
@@ -772,17 +787,9 @@ static int iucv_sock_autobind(struct sock *sk)
 	memcpy(iucv->src_user_id, iucv_userid, 8);
 
 	write_lock_bh(&iucv_sk_list.lock);
-
-	sprintf(name, "%08x", atomic_inc_return(&iucv_sk_list.autobind_name));
-	while (__iucv_get_sock_by_name(name)) {
-		sprintf(name, "%08x",
-			atomic_inc_return(&iucv_sk_list.autobind_name));
-	}
-
+	__iucv_auto_name(iucv);
 	write_unlock_bh(&iucv_sk_list.lock);
 
-	memcpy(&iucv->src_name, name, 8);
-
 	if (!iucv->msglimit)
 		iucv->msglimit = IUCV_QUEUELEN_DEFAULT;
 
@@ -1936,11 +1943,10 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb)
 	    sk_acceptq_is_full(sk) ||
 	    !nsk) {
 		/* error on server socket - connection refused */
-		if (nsk)
-			sk_free(nsk);
 		afiucv_swap_src_dest(skb);
 		trans_hdr->flags = AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_FIN;
 		err = dev_queue_xmit(skb);
+		iucv_sock_kill(nsk);
 		bh_unlock_sock(sk);
 		goto out;
 	}
diff --git a/net/key/af_key.c b/net/key/af_key.c
index f3c83073afc..ba2a2f95911 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1476,9 +1476,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, const struct sadb_msg
 	else
 		err = xfrm_state_update(x);
 
-	xfrm_audit_state_add(x, err ? 0 : 1,
-			     audit_get_loginuid(current),
-			     audit_get_sessionid(current), 0);
+	xfrm_audit_state_add(x, err ? 0 : 1, true);
 
 	if (err < 0) {
 		x->km.state = XFRM_STATE_DEAD;
@@ -1532,9 +1530,7 @@ static int pfkey_delete(struct sock *sk, struct sk_buff *skb, const struct sadb_
 	c.event = XFRM_MSG_DELSA;
 	km_state_notify(x, &c);
 out:
-	xfrm_audit_state_delete(x, err ? 0 : 1,
-				audit_get_loginuid(current),
-				audit_get_sessionid(current), 0);
+	xfrm_audit_state_delete(x, err ? 0 : 1, true);
 	xfrm_state_put(x);
 
 	return err;
@@ -1726,17 +1722,13 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m
 	struct net *net = sock_net(sk);
 	unsigned int proto;
 	struct km_event c;
-	struct xfrm_audit audit_info;
 	int err, err2;
 
 	proto = pfkey_satype2proto(hdr->sadb_msg_satype);
 	if (proto == 0)
 		return -EINVAL;
 
-	audit_info.loginuid = audit_get_loginuid(current);
-	audit_info.sessionid = audit_get_sessionid(current);
-	audit_info.secid = 0;
-	err = xfrm_state_flush(net, proto, &audit_info);
+	err = xfrm_state_flush(net, proto, true);
 	err2 = unicast_flush_resp(sk, hdr);
 	if (err || err2) {
 		if (err == -ESRCH) /* empty table - go quietly */
@@ -2288,9 +2280,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_
 	err = xfrm_policy_insert(pol->sadb_x_policy_dir-1, xp,
 				 hdr->sadb_msg_type != SADB_X_SPDUPDATE);
 
-	xfrm_audit_policy_add(xp, err ? 0 : 1,
-			      audit_get_loginuid(current),
-			      audit_get_sessionid(current), 0);
+	xfrm_audit_policy_add(xp, err ? 0 : 1, true);
 
 	if (err)
 		goto out;
@@ -2372,9 +2362,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa
 	if (xp == NULL)
 		return -ENOENT;
 
-	xfrm_audit_policy_delete(xp, err ? 0 : 1,
-				 audit_get_loginuid(current),
-				 audit_get_sessionid(current), 0);
+	xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
 
 	if (err)
 		goto out;
@@ -2553,7 +2541,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb,
 		sel.sport_mask = htons(0xffff);
 
 	/* set destination address info of selector */
-	sa = ext_hdrs[SADB_EXT_ADDRESS_DST - 1],
+	sa = ext_hdrs[SADB_EXT_ADDRESS_DST - 1];
 	pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr);
 	sel.prefixlen_d = sa->sadb_address_prefixlen;
 	sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto);
@@ -2622,9 +2610,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_
 		return -ENOENT;
 
 	if (delete) {
-		xfrm_audit_policy_delete(xp, err ? 0 : 1,
-				audit_get_loginuid(current),
-				audit_get_sessionid(current), 0);
+		xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
 
 		if (err)
 			goto out;
@@ -2733,13 +2719,9 @@ static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, const struct sad
 {
 	struct net *net = sock_net(sk);
 	struct km_event c;
-	struct xfrm_audit audit_info;
 	int err, err2;
 
-	audit_info.loginuid = audit_get_loginuid(current);
-	audit_info.sessionid = audit_get_sessionid(current);
-	audit_info.secid = 0;
-	err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info);
+	err = xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, true);
 	err2 = unicast_flush_resp(sk, hdr);
 	if (err || err2) {
 		if (err == -ESRCH) /* empty table - old silent behavior */
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index a4e37d7158d..bea25904320 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -495,52 +495,6 @@ out:
 	spin_unlock_bh(&session->reorder_q.lock);
 }
 
-static inline int l2tp_verify_udp_checksum(struct sock *sk,
-					   struct sk_buff *skb)
-{
-	struct udphdr *uh = udp_hdr(skb);
-	u16 ulen = ntohs(uh->len);
-	__wsum psum;
-
-	if (sk->sk_no_check || skb_csum_unnecessary(skb))
-		return 0;
-
-#if IS_ENABLED(CONFIG_IPV6)
-	if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) {
-		if (!uh->check) {
-			LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n");
-			return 1;
-		}
-		if ((skb->ip_summed == CHECKSUM_COMPLETE) &&
-		    !csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-				     &ipv6_hdr(skb)->daddr, ulen,
-				     IPPROTO_UDP, skb->csum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			return 0;
-		}
-		skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
-							 &ipv6_hdr(skb)->daddr,
-							 skb->len, IPPROTO_UDP,
-							 0));
-	} else
-#endif
-	{
-		struct inet_sock *inet;
-		if (!uh->check)
-			return 0;
-		inet = inet_sk(sk);
-		psum = csum_tcpudp_nofold(inet->inet_saddr, inet->inet_daddr,
-					  ulen, IPPROTO_UDP, 0);
-
-		if ((skb->ip_summed == CHECKSUM_COMPLETE) &&
-		    !csum_fold(csum_add(psum, skb->csum)))
-			return 0;
-		skb->csum = psum;
-	}
-
-	return __skb_checksum_complete(skb);
-}
-
 static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr)
 {
 	u32 nws;
@@ -895,8 +849,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 	u16 version;
 	int length;
 
-	if (tunnel->sock && l2tp_verify_udp_checksum(tunnel->sock, skb))
-		goto discard_bad_csum;
+	/* UDP has verifed checksum */
 
 	/* UDP always verifies the packet length. */
 	__skb_pull(skb, sizeof(struct udphdr));
@@ -979,14 +932,6 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 
 	return 0;
 
-discard_bad_csum:
-	LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name);
-	UDP_INC_STATS_USER(tunnel->l2tp_net, UDP_MIB_INERRORS, 0);
-	atomic_long_inc(&tunnel->stats.rx_errors);
-	kfree_skb(skb);
-
-	return 0;
-
 error:
 	/* Put UDP header back */
 	__skb_push(skb, sizeof(struct udphdr));
@@ -1128,7 +1073,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 	}
 
 	/* Queue the packet to IP for output */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped)
 		error = inet6_csk_xmit(tunnel->sock, skb, NULL);
@@ -1150,31 +1095,6 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 	return 0;
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
-static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb,
-				int udp_len)
-{
-	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct udphdr *uh = udp_hdr(skb);
-
-	if (!skb_dst(skb) || !skb_dst(skb)->dev ||
-	    !(skb_dst(skb)->dev->features & NETIF_F_IPV6_CSUM)) {
-		__wsum csum = skb_checksum(skb, 0, udp_len, 0);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		uh->check = csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr, udp_len,
-					    IPPROTO_UDP, csum);
-		if (uh->check == 0)
-			uh->check = CSUM_MANGLED_0;
-	} else {
-		skb->ip_summed = CHECKSUM_PARTIAL;
-		skb->csum_start = skb_transport_header(skb) - skb->head;
-		skb->csum_offset = offsetof(struct udphdr, check);
-		uh->check = ~csum_ipv6_magic(&np->saddr, &sk->sk_v6_daddr,
-					     udp_len, IPPROTO_UDP, 0);
-	}
-}
-#endif
-
 /* If caller requires the skb to have a ppp header, the header must be
  * inserted in the skb data before calling this function.
  */
@@ -1186,7 +1106,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 	struct flowi *fl;
 	struct udphdr *uh;
 	struct inet_sock *inet;
-	__wsum csum;
 	int headroom;
 	int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
 	int udp_len;
@@ -1235,33 +1154,17 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		uh->dest = inet->inet_dport;
 		udp_len = uhlen + hdr_len + data_len;
 		uh->len = htons(udp_len);
-		uh->check = 0;
 
 		/* Calculate UDP checksum if configured to do so */
 #if IS_ENABLED(CONFIG_IPV6)
 		if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
-			l2tp_xmit_ipv6_csum(sk, skb, udp_len);
+			udp6_set_csum(udp_get_no_check6_tx(sk),
+				      skb, &inet6_sk(sk)->saddr,
+				      &sk->sk_v6_daddr, udp_len);
 		else
 #endif
-		if (sk->sk_no_check == UDP_CSUM_NOXMIT)
-			skb->ip_summed = CHECKSUM_NONE;
-		else if ((skb_dst(skb) && skb_dst(skb)->dev) &&
-			 (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) {
-			skb->ip_summed = CHECKSUM_COMPLETE;
-			csum = skb_checksum(skb, 0, udp_len, 0);
-			uh->check = csum_tcpudp_magic(inet->inet_saddr,
-						      inet->inet_daddr,
-						      udp_len, IPPROTO_UDP, csum);
-			if (uh->check == 0)
-				uh->check = CSUM_MANGLED_0;
-		} else {
-			skb->ip_summed = CHECKSUM_PARTIAL;
-			skb->csum_start = skb_transport_header(skb) - skb->head;
-			skb->csum_offset = offsetof(struct udphdr, check);
-			uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
-						       inet->inet_daddr,
-						       udp_len, IPPROTO_UDP, 0);
-		}
+		udp_set_csum(sk->sk_no_check_tx, skb, inet->inet_saddr,
+			     inet->inet_daddr, udp_len);
 		break;
 
 	case L2TP_ENCAPTYPE_IP:
@@ -1490,6 +1393,11 @@ static int l2tp_tunnel_sock_create(struct net *net,
 					     sizeof(udp6_addr), 0);
 			if (err < 0)
 				goto out;
+
+			if (cfg->udp6_zero_tx_checksums)
+				udp_set_no_check6_tx(sock->sk, true);
+			if (cfg->udp6_zero_rx_checksums)
+				udp_set_no_check6_rx(sock->sk, true);
 		} else
 #endif
 		{
@@ -1518,7 +1426,7 @@ static int l2tp_tunnel_sock_create(struct net *net,
 		}
 
 		if (!cfg->use_udp_checksums)
-			sock->sk->sk_no_check = UDP_CSUM_NOXMIT;
+			sock->sk->sk_no_check_tx = 1;
 
 		break;
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 3f93ccd6ba9..68aa9ffd4ae 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -162,7 +162,9 @@ struct l2tp_tunnel_cfg {
 #endif
 	u16			local_udp_port;
 	u16			peer_udp_port;
-	unsigned int		use_udp_checksums:1;
+	unsigned int		use_udp_checksums:1,
+				udp6_zero_tx_checksums:1,
+				udp6_zero_rx_checksums:1;
 };
 
 struct l2tp_tunnel {
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 3397fe6897c..369a9822488 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -606,7 +606,6 @@ static struct inet_protosw l2tp_ip_protosw = {
 	.protocol	= IPPROTO_L2TP,
 	.prot		= &l2tp_ip_prot,
 	.ops		= &l2tp_ip_ops,
-	.no_check	= 0,
 };
 
 static struct net_protocol l2tp_ip_protocol __read_mostly = {
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 7704ea9502f..f3f98a156ce 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -605,14 +605,8 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		goto out;
 	}
 
-	if (hlimit < 0) {
-		if (ipv6_addr_is_multicast(&fl6.daddr))
-			hlimit = np->mcast_hops;
-		else
-			hlimit = np->hop_limit;
-		if (hlimit < 0)
-			hlimit = ip6_dst_hoplimit(dst);
-	}
+	if (hlimit < 0)
+		hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
 	if (tclass < 0)
 		tclass = np->tclass;
@@ -761,7 +755,6 @@ static struct inet_protosw l2tp_ip6_protosw = {
 	.protocol	= IPPROTO_L2TP,
 	.prot		= &l2tp_ip6_prot,
 	.ops		= &l2tp_ip6_ops,
-	.no_check	= 0,
 };
 
 static struct inet6_protocol l2tp_ip6_protocol __read_mostly = {
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index bd7387adea9..0ac907adb2f 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -161,6 +161,13 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 			cfg.peer_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_DPORT]);
 		if (info->attrs[L2TP_ATTR_UDP_CSUM])
 			cfg.use_udp_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_CSUM]);
+
+#if IS_ENABLED(CONFIG_IPV6)
+		if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX])
+			cfg.udp6_zero_tx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX]);
+		if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX])
+			cfg.udp6_zero_rx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX]);
+#endif
 	}
 
 	if (info->attrs[L2TP_ATTR_DEBUG])
@@ -297,8 +304,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	case L2TP_ENCAPTYPE_UDP:
 		if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) ||
 		    nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)) ||
-		    nla_put_u8(skb, L2TP_ATTR_UDP_CSUM,
-			       (sk->sk_no_check != UDP_CSUM_NOXMIT)))
+		    nla_put_u8(skb, L2TP_ATTR_UDP_CSUM, !sk->sk_no_check_tx))
 			goto nla_put_failure;
 		/* NOBREAK */
 	case L2TP_ENCAPTYPE_IP:
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 950909f04ee..13752d96275 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1365,7 +1365,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
 	int err;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
@@ -1491,7 +1491,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname,
 	struct pppol2tp_session *ps;
 
 	if (level != SOL_PPPOL2TP)
-		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+		return -EINVAL;
 
 	if (get_user(len, optlen))
 		return -EFAULT;
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 9d7d840aac6..1e46ffa6916 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -25,7 +25,8 @@ mac80211-y := \
 	wme.o \
 	event.o \
 	chan.o \
-	trace.o mlme.o
+	trace.o mlme.o \
+	tdls.o
 
 mac80211-$(CONFIG_MAC80211_LEDS) += led.o
 mac80211-$(CONFIG_MAC80211_DEBUGFS) += \
diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c
index 7c7df475a40..ec24378caaa 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aes_ccm.c
@@ -23,12 +23,13 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 			       u8 *data, size_t data_len, u8 *mic)
 {
 	struct scatterlist assoc, pt, ct[2];
-	struct {
-		struct aead_request	req;
-		u8			priv[crypto_aead_reqsize(tfm)];
-	} aead_req;
 
-	memset(&aead_req, 0, sizeof(aead_req));
+	char aead_req_data[sizeof(struct aead_request) +
+			   crypto_aead_reqsize(tfm)]
+		__aligned(__alignof__(struct aead_request));
+	struct aead_request *aead_req = (void *) aead_req_data;
+
+	memset(aead_req, 0, sizeof(aead_req_data));
 
 	sg_init_one(&pt, data, data_len);
 	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
@@ -36,23 +37,23 @@ void ieee80211_aes_ccm_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 	sg_set_buf(&ct[0], data, data_len);
 	sg_set_buf(&ct[1], mic, IEEE80211_CCMP_MIC_LEN);
 
-	aead_request_set_tfm(&aead_req.req, tfm);
-	aead_request_set_assoc(&aead_req.req, &assoc, assoc.length);
-	aead_request_set_crypt(&aead_req.req, &pt, ct, data_len, b_0);
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_assoc(aead_req, &assoc, assoc.length);
+	aead_request_set_crypt(aead_req, &pt, ct, data_len, b_0);
 
-	crypto_aead_encrypt(&aead_req.req);
+	crypto_aead_encrypt(aead_req);
 }
 
 int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 			      u8 *data, size_t data_len, u8 *mic)
 {
 	struct scatterlist assoc, pt, ct[2];
-	struct {
-		struct aead_request	req;
-		u8			priv[crypto_aead_reqsize(tfm)];
-	} aead_req;
+	char aead_req_data[sizeof(struct aead_request) +
+			   crypto_aead_reqsize(tfm)]
+		__aligned(__alignof__(struct aead_request));
+	struct aead_request *aead_req = (void *) aead_req_data;
 
-	memset(&aead_req, 0, sizeof(aead_req));
+	memset(aead_req, 0, sizeof(aead_req_data));
 
 	sg_init_one(&pt, data, data_len);
 	sg_init_one(&assoc, &aad[2], be16_to_cpup((__be16 *)aad));
@@ -60,12 +61,12 @@ int ieee80211_aes_ccm_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad,
 	sg_set_buf(&ct[0], data, data_len);
 	sg_set_buf(&ct[1], mic, IEEE80211_CCMP_MIC_LEN);
 
-	aead_request_set_tfm(&aead_req.req, tfm);
-	aead_request_set_assoc(&aead_req.req, &assoc, assoc.length);
-	aead_request_set_crypt(&aead_req.req, ct, &pt,
+	aead_request_set_tfm(aead_req, tfm);
+	aead_request_set_assoc(aead_req, &assoc, assoc.length);
+	aead_request_set_crypt(aead_req, ct, &pt,
 			       data_len + IEEE80211_CCMP_MIC_LEN, b_0);
 
-	return crypto_aead_decrypt(&aead_req.req);
+	return crypto_aead_decrypt(aead_req);
 }
 
 struct crypto_aead *ieee80211_aes_key_setup_encrypt(const u8 key[])
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index aaa59d71959..592f4b152ba 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -109,6 +109,15 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
 static int ieee80211_start_p2p_device(struct wiphy *wiphy,
 				      struct wireless_dev *wdev)
 {
+	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
+	int ret;
+
+	mutex_lock(&sdata->local->chanctx_mtx);
+	ret = ieee80211_check_combinations(sdata, NULL, 0, 0);
+	mutex_unlock(&sdata->local->chanctx_mtx);
+	if (ret < 0)
+		return ret;
+
 	return ieee80211_do_open(wdev, true);
 }
 
@@ -463,10 +472,15 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 {
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
+	struct rate_control_ref *ref = NULL;
 	struct timespec uptime;
 	u64 packets = 0;
+	u32 thr = 0;
 	int i, ac;
 
+	if (test_sta_flag(sta, WLAN_STA_RATE_CONTROL))
+		ref = local->rate_ctrl;
+
 	sinfo->generation = sdata->local->sta_generation;
 
 	sinfo->filled = STATION_INFO_INACTIVE_TIME |
@@ -578,6 +592,17 @@ static void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo)
 		sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_ASSOCIATED);
 	if (test_sta_flag(sta, WLAN_STA_TDLS_PEER))
 		sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_TDLS_PEER);
+
+	/* check if the driver has a SW RC implementation */
+	if (ref && ref->ops->get_expected_throughput)
+		thr = ref->ops->get_expected_throughput(sta->rate_ctrl_priv);
+	else
+		thr = drv_get_expected_throughput(local, &sta->sta);
+
+	if (thr != 0) {
+		sinfo->filled |= STATION_INFO_EXPECTED_THROUGHPUT;
+		sinfo->expected_throughput = thr;
+	}
 }
 
 static const char ieee80211_gstrings_sta_stats[][ETH_GSTRING_LEN] = {
@@ -768,7 +793,7 @@ static void ieee80211_get_et_strings(struct wiphy *wiphy,
 }
 
 static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev,
-				 int idx, u8 *mac, struct station_info *sinfo)
+				  int idx, u8 *mac, struct station_info *sinfo)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
@@ -798,7 +823,7 @@ static int ieee80211_dump_survey(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev,
-				 u8 *mac, struct station_info *sinfo)
+				 const u8 *mac, struct station_info *sinfo)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
@@ -972,13 +997,13 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	sdata->needed_rx_chains = sdata->local->rx_chains;
 
 	mutex_lock(&local->mtx);
-	sdata->radar_required = params->radar_required;
 	err = ieee80211_vif_use_channel(sdata, &params->chandef,
 					IEEE80211_CHANCTX_SHARED);
+	if (!err)
+		ieee80211_vif_copy_chanctx_to_vlans(sdata, false);
 	mutex_unlock(&local->mtx);
 	if (err)
 		return err;
-	ieee80211_vif_copy_chanctx_to_vlans(sdata, false);
 
 	/*
 	 * Apply control port protocol, this allows us to
@@ -1075,6 +1100,31 @@ static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
 	return 0;
 }
 
+bool ieee80211_csa_needs_block_tx(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	lockdep_assert_held(&local->mtx);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+		if (!ieee80211_sdata_running(sdata))
+			continue;
+
+		if (!sdata->vif.csa_active)
+			continue;
+
+		if (!sdata->csa_block_tx)
+			continue;
+
+		rcu_read_unlock();
+		return true;
+	}
+	rcu_read_unlock();
+
+	return false;
+}
+
 static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
@@ -1092,7 +1142,14 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	old_probe_resp = sdata_dereference(sdata->u.ap.probe_resp, sdata);
 
 	/* abort any running channel switch */
+	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
+
 	kfree(sdata->u.ap.next_beacon);
 	sdata->u.ap.next_beacon = NULL;
 
@@ -1131,8 +1188,8 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf);
 	skb_queue_purge(&sdata->u.ap.ps.bc_buf);
 
-	ieee80211_vif_copy_chanctx_to_vlans(sdata, true);
 	mutex_lock(&local->mtx);
+	ieee80211_vif_copy_chanctx_to_vlans(sdata, true);
 	ieee80211_vif_release_channel(sdata);
 	mutex_unlock(&local->mtx);
 
@@ -1416,7 +1473,8 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 }
 
 static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
-				 u8 *mac, struct station_parameters *params)
+				 const u8 *mac,
+				 struct station_parameters *params)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
 	struct sta_info *sta;
@@ -1450,6 +1508,8 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
 	if (!(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))) {
 		sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
 		sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
+	} else {
+		sta->sta.tdls = true;
 	}
 
 	err = sta_apply_parameters(local, sta, params);
@@ -1483,7 +1543,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev,
-				 u8 *mac)
+				 const u8 *mac)
 {
 	struct ieee80211_sub_if_data *sdata;
 
@@ -1497,7 +1557,7 @@ static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_change_station(struct wiphy *wiphy,
-				    struct net_device *dev, u8 *mac,
+				    struct net_device *dev, const u8 *mac,
 				    struct station_parameters *params)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
@@ -1566,7 +1626,7 @@ static int ieee80211_change_station(struct wiphy *wiphy,
 
 		if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
 		    sta->sdata->u.vlan.sta) {
-			rcu_assign_pointer(sta->sdata->u.vlan.sta, NULL);
+			RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL);
 			prev_4addr = true;
 		}
 
@@ -1622,7 +1682,7 @@ out_err:
 
 #ifdef CONFIG_MAC80211_MESH
 static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev,
-				 u8 *dst, u8 *next_hop)
+			       const u8 *dst, const u8 *next_hop)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct mesh_path *mpath;
@@ -1650,7 +1710,7 @@ static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *dst)
+			       const u8 *dst)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
@@ -1661,9 +1721,8 @@ static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev,
 	return 0;
 }
 
-static int ieee80211_change_mpath(struct wiphy *wiphy,
-				    struct net_device *dev,
-				    u8 *dst, u8 *next_hop)
+static int ieee80211_change_mpath(struct wiphy *wiphy, struct net_device *dev,
+				  const u8 *dst, const u8 *next_hop)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct mesh_path *mpath;
@@ -1755,8 +1814,8 @@ static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev,
 }
 
 static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev,
-				 int idx, u8 *dst, u8 *next_hop,
-				 struct mpath_info *pinfo)
+				int idx, u8 *dst, u8 *next_hop,
+				struct mpath_info *pinfo)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct mesh_path *mpath;
@@ -2930,7 +2989,6 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 	/* whatever, but channel contexts should not complain about that one */
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
 	sdata->needed_rx_chains = local->rx_chains;
-	sdata->radar_required = true;
 
 	err = ieee80211_vif_use_channel(sdata, chandef,
 					IEEE80211_CHANCTX_SHARED);
@@ -3011,26 +3069,11 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif)
 }
 EXPORT_SYMBOL(ieee80211_csa_finish);
 
-static void ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
+static int ieee80211_set_after_csa_beacon(struct ieee80211_sub_if_data *sdata,
+					  u32 *changed)
 {
-	struct ieee80211_local *local = sdata->local;
-	int err, changed = 0;
-
-	sdata_assert_lock(sdata);
-
-	mutex_lock(&local->mtx);
-	sdata->radar_required = sdata->csa_radar_required;
-	err = ieee80211_vif_change_channel(sdata, &changed);
-	mutex_unlock(&local->mtx);
-	if (WARN_ON(err < 0))
-		return;
-
-	if (!local->use_chanctx) {
-		local->_oper_chandef = sdata->csa_chandef;
-		ieee80211_hw_config(local, 0);
-	}
+	int err;
 
-	sdata->vif.csa_active = false;
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP:
 		err = ieee80211_assign_beacon(sdata, sdata->u.ap.next_beacon);
@@ -3038,35 +3081,74 @@ static void ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
 		sdata->u.ap.next_beacon = NULL;
 
 		if (err < 0)
-			return;
-		changed |= err;
+			return err;
+		*changed |= err;
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		err = ieee80211_ibss_finish_csa(sdata);
 		if (err < 0)
-			return;
-		changed |= err;
+			return err;
+		*changed |= err;
 		break;
 #ifdef CONFIG_MAC80211_MESH
 	case NL80211_IFTYPE_MESH_POINT:
 		err = ieee80211_mesh_finish_csa(sdata);
 		if (err < 0)
-			return;
-		changed |= err;
+			return err;
+		*changed |= err;
 		break;
 #endif
 	default:
 		WARN_ON(1);
-		return;
+		return -EINVAL;
 	}
 
+	return 0;
+}
+
+static int __ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	u32 changed = 0;
+	int err;
+
+	sdata_assert_lock(sdata);
+	lockdep_assert_held(&local->mtx);
+
+	sdata->radar_required = sdata->csa_radar_required;
+	err = ieee80211_vif_change_channel(sdata, &changed);
+	if (err < 0)
+		return err;
+
+	if (!local->use_chanctx) {
+		local->_oper_chandef = sdata->csa_chandef;
+		ieee80211_hw_config(local, 0);
+	}
+
+	sdata->vif.csa_active = false;
+
+	err = ieee80211_set_after_csa_beacon(sdata, &changed);
+	if (err)
+		return err;
+
 	ieee80211_bss_info_change_notify(sdata, changed);
+	cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef);
 
-	ieee80211_wake_queues_by_reason(&sdata->local->hw,
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
 					IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_CSA);
 
-	cfg80211_ch_switch_notify(sdata->dev, &sdata->csa_chandef);
+	return 0;
+}
+
+static void ieee80211_csa_finalize(struct ieee80211_sub_if_data *sdata)
+{
+	if (__ieee80211_csa_finalize(sdata)) {
+		sdata_info(sdata, "failed to finalize CSA, disconnecting\n");
+		cfg80211_stop_iface(sdata->local->hw.wiphy, &sdata->wdev,
+				    GFP_KERNEL);
+	}
 }
 
 void ieee80211_csa_finalize_work(struct work_struct *work)
@@ -3074,8 +3156,11 @@ void ieee80211_csa_finalize_work(struct work_struct *work)
 	struct ieee80211_sub_if_data *sdata =
 		container_of(work, struct ieee80211_sub_if_data,
 			     csa_finalize_work);
+	struct ieee80211_local *local = sdata->local;
 
 	sdata_lock(sdata);
+	mutex_lock(&local->mtx);
+
 	/* AP might have been stopped while waiting for the lock. */
 	if (!sdata->vif.csa_active)
 		goto unlock;
@@ -3086,6 +3171,7 @@ void ieee80211_csa_finalize_work(struct work_struct *work)
 	ieee80211_csa_finalize(sdata);
 
 unlock:
+	mutex_unlock(&local->mtx);
 	sdata_unlock(sdata);
 }
 
@@ -3121,9 +3207,25 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
 		if (params->count <= 1)
 			break;
 
-		sdata->csa_counter_offset_beacon =
-			params->counter_offset_beacon;
-		sdata->csa_counter_offset_presp = params->counter_offset_presp;
+		if ((params->n_counter_offsets_beacon >
+		     IEEE80211_MAX_CSA_COUNTERS_NUM) ||
+		    (params->n_counter_offsets_presp >
+		     IEEE80211_MAX_CSA_COUNTERS_NUM))
+			return -EINVAL;
+
+		/* make sure we don't have garbage in other counters */
+		memset(sdata->csa_counter_offset_beacon, 0,
+		       sizeof(sdata->csa_counter_offset_beacon));
+		memset(sdata->csa_counter_offset_presp, 0,
+		       sizeof(sdata->csa_counter_offset_presp));
+
+		memcpy(sdata->csa_counter_offset_beacon,
+		       params->counter_offsets_beacon,
+		       params->n_counter_offsets_beacon * sizeof(u16));
+		memcpy(sdata->csa_counter_offset_presp,
+		       params->counter_offsets_presp,
+		       params->n_counter_offsets_presp * sizeof(u16));
+
 		err = ieee80211_assign_beacon(sdata, &params->beacon_csa);
 		if (err < 0) {
 			kfree(sdata->u.ap.next_beacon);
@@ -3212,16 +3314,18 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
-int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
-			     struct cfg80211_csa_settings *params)
+static int
+__ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
+			   struct cfg80211_csa_settings *params)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_chanctx_conf *chanctx_conf;
+	struct ieee80211_chanctx_conf *conf;
 	struct ieee80211_chanctx *chanctx;
 	int err, num_chanctx, changed = 0;
 
 	sdata_assert_lock(sdata);
+	lockdep_assert_held(&local->mtx);
 
 	if (!list_empty(&local->roc_list) || local->scanning)
 		return -EBUSY;
@@ -3233,23 +3337,24 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 				       &sdata->vif.bss_conf.chandef))
 		return -EINVAL;
 
-	rcu_read_lock();
-	chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
-	if (!chanctx_conf) {
-		rcu_read_unlock();
+	mutex_lock(&local->chanctx_mtx);
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	if (!conf) {
+		mutex_unlock(&local->chanctx_mtx);
 		return -EBUSY;
 	}
 
 	/* don't handle for multi-VIF cases */
-	chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf);
-	if (chanctx->refcount > 1) {
-		rcu_read_unlock();
+	chanctx = container_of(conf, struct ieee80211_chanctx, conf);
+	if (ieee80211_chanctx_refcount(local, chanctx) > 1) {
+		mutex_unlock(&local->chanctx_mtx);
 		return -EBUSY;
 	}
 	num_chanctx = 0;
 	list_for_each_entry_rcu(chanctx, &local->chanctx_list, list)
 		num_chanctx++;
-	rcu_read_unlock();
+	mutex_unlock(&local->chanctx_mtx);
 
 	if (num_chanctx > 1)
 		return -EBUSY;
@@ -3263,15 +3368,16 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		return err;
 
 	sdata->csa_radar_required = params->radar_required;
-
-	if (params->block_tx)
-		ieee80211_stop_queues_by_reason(&local->hw,
-				IEEE80211_MAX_QUEUE_MAP,
-				IEEE80211_QUEUE_STOP_REASON_CSA);
-
 	sdata->csa_chandef = params->chandef;
+	sdata->csa_block_tx = params->block_tx;
+	sdata->csa_current_counter = params->count;
 	sdata->vif.csa_active = true;
 
+	if (sdata->csa_block_tx)
+		ieee80211_stop_queues_by_reason(&local->hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+
 	if (changed) {
 		ieee80211_bss_info_change_notify(sdata, changed);
 		drv_channel_switch_beacon(sdata, &params->chandef);
@@ -3283,6 +3389,20 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 	return 0;
 }
 
+int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
+			     struct cfg80211_csa_settings *params)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	int err;
+
+	mutex_lock(&local->mtx);
+	err = __ieee80211_channel_switch(wiphy, dev, params);
+	mutex_unlock(&local->mtx);
+
+	return err;
+}
+
 static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 			     struct cfg80211_mgmt_tx_params *params,
 			     u64 *cookie)
@@ -3295,6 +3415,7 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	bool need_offchan = false;
 	u32 flags;
 	int ret;
+	u8 *data;
 
 	if (params->dont_wait_for_ack)
 		flags = IEEE80211_TX_CTL_NO_ACK;
@@ -3388,7 +3509,20 @@ static int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	}
 	skb_reserve(skb, local->hw.extra_tx_headroom);
 
-	memcpy(skb_put(skb, params->len), params->buf, params->len);
+	data = skb_put(skb, params->len);
+	memcpy(data, params->buf, params->len);
+
+	/* Update CSA counters */
+	if (sdata->vif.csa_active &&
+	    (sdata->vif.type == NL80211_IFTYPE_AP ||
+	     sdata->vif.type == NL80211_IFTYPE_ADHOC) &&
+	    params->n_csa_offsets) {
+		int i;
+		u8 c = sdata->csa_current_counter;
+
+		for (i = 0; i < params->n_csa_offsets; i++)
+			data[params->csa_offsets[i]] = c;
+	}
 
 	IEEE80211_SKB_CB(skb)->flags = flags;
 
@@ -3497,320 +3631,6 @@ static int ieee80211_set_rekey_data(struct wiphy *wiphy,
 	return 0;
 }
 
-static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb)
-{
-	u8 *pos = (void *)skb_put(skb, 7);
-
-	*pos++ = WLAN_EID_EXT_CAPABILITY;
-	*pos++ = 5; /* len */
-	*pos++ = 0x0;
-	*pos++ = 0x0;
-	*pos++ = 0x0;
-	*pos++ = 0x0;
-	*pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED;
-}
-
-static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata)
-{
-	struct ieee80211_local *local = sdata->local;
-	u16 capab;
-
-	capab = 0;
-	if (ieee80211_get_sdata_band(sdata) != IEEE80211_BAND_2GHZ)
-		return capab;
-
-	if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE))
-		capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME;
-	if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE))
-		capab |= WLAN_CAPABILITY_SHORT_PREAMBLE;
-
-	return capab;
-}
-
-static void ieee80211_tdls_add_link_ie(struct sk_buff *skb, u8 *src_addr,
-				       u8 *peer, u8 *bssid)
-{
-	struct ieee80211_tdls_lnkie *lnkid;
-
-	lnkid = (void *)skb_put(skb, sizeof(struct ieee80211_tdls_lnkie));
-
-	lnkid->ie_type = WLAN_EID_LINK_ID;
-	lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2;
-
-	memcpy(lnkid->bssid, bssid, ETH_ALEN);
-	memcpy(lnkid->init_sta, src_addr, ETH_ALEN);
-	memcpy(lnkid->resp_sta, peer, ETH_ALEN);
-}
-
-static int
-ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *peer, u8 action_code, u8 dialog_token,
-			       u16 status_code, struct sk_buff *skb)
-{
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
-	struct ieee80211_tdls_data *tf;
-
-	tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u));
-
-	memcpy(tf->da, peer, ETH_ALEN);
-	memcpy(tf->sa, sdata->vif.addr, ETH_ALEN);
-	tf->ether_type = cpu_to_be16(ETH_P_TDLS);
-	tf->payload_type = WLAN_TDLS_SNAP_RFTYPE;
-
-	switch (action_code) {
-	case WLAN_TDLS_SETUP_REQUEST:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_SETUP_REQUEST;
-
-		skb_put(skb, sizeof(tf->u.setup_req));
-		tf->u.setup_req.dialog_token = dialog_token;
-		tf->u.setup_req.capability =
-			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
-
-		ieee80211_add_srates_ie(sdata, skb, false, band);
-		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
-		ieee80211_tdls_add_ext_capab(skb);
-		break;
-	case WLAN_TDLS_SETUP_RESPONSE:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_SETUP_RESPONSE;
-
-		skb_put(skb, sizeof(tf->u.setup_resp));
-		tf->u.setup_resp.status_code = cpu_to_le16(status_code);
-		tf->u.setup_resp.dialog_token = dialog_token;
-		tf->u.setup_resp.capability =
-			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
-
-		ieee80211_add_srates_ie(sdata, skb, false, band);
-		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
-		ieee80211_tdls_add_ext_capab(skb);
-		break;
-	case WLAN_TDLS_SETUP_CONFIRM:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_SETUP_CONFIRM;
-
-		skb_put(skb, sizeof(tf->u.setup_cfm));
-		tf->u.setup_cfm.status_code = cpu_to_le16(status_code);
-		tf->u.setup_cfm.dialog_token = dialog_token;
-		break;
-	case WLAN_TDLS_TEARDOWN:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_TEARDOWN;
-
-		skb_put(skb, sizeof(tf->u.teardown));
-		tf->u.teardown.reason_code = cpu_to_le16(status_code);
-		break;
-	case WLAN_TDLS_DISCOVERY_REQUEST:
-		tf->category = WLAN_CATEGORY_TDLS;
-		tf->action_code = WLAN_TDLS_DISCOVERY_REQUEST;
-
-		skb_put(skb, sizeof(tf->u.discover_req));
-		tf->u.discover_req.dialog_token = dialog_token;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int
-ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev,
-			   u8 *peer, u8 action_code, u8 dialog_token,
-			   u16 status_code, struct sk_buff *skb)
-{
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
-	struct ieee80211_mgmt *mgmt;
-
-	mgmt = (void *)skb_put(skb, 24);
-	memset(mgmt, 0, 24);
-	memcpy(mgmt->da, peer, ETH_ALEN);
-	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
-	memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN);
-
-	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
-					  IEEE80211_STYPE_ACTION);
-
-	switch (action_code) {
-	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
-		skb_put(skb, 1 + sizeof(mgmt->u.action.u.tdls_discover_resp));
-		mgmt->u.action.category = WLAN_CATEGORY_PUBLIC;
-		mgmt->u.action.u.tdls_discover_resp.action_code =
-			WLAN_PUB_ACTION_TDLS_DISCOVER_RES;
-		mgmt->u.action.u.tdls_discover_resp.dialog_token =
-			dialog_token;
-		mgmt->u.action.u.tdls_discover_resp.capability =
-			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
-
-		ieee80211_add_srates_ie(sdata, skb, false, band);
-		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
-		ieee80211_tdls_add_ext_capab(skb);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *peer, u8 action_code, u8 dialog_token,
-			       u16 status_code, u32 peer_capability,
-			       const u8 *extra_ies, size_t extra_ies_len)
-{
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-	struct ieee80211_local *local = sdata->local;
-	struct sk_buff *skb = NULL;
-	bool send_direct;
-	int ret;
-
-	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
-		return -ENOTSUPP;
-
-	/* make sure we are in managed mode, and associated */
-	if (sdata->vif.type != NL80211_IFTYPE_STATION ||
-	    !sdata->u.mgd.associated)
-		return -EINVAL;
-
-	tdls_dbg(sdata, "TDLS mgmt action %d peer %pM\n",
-		 action_code, peer);
-
-	skb = dev_alloc_skb(local->hw.extra_tx_headroom +
-			    max(sizeof(struct ieee80211_mgmt),
-				sizeof(struct ieee80211_tdls_data)) +
-			    50 + /* supported rates */
-			    7 + /* ext capab */
-			    extra_ies_len +
-			    sizeof(struct ieee80211_tdls_lnkie));
-	if (!skb)
-		return -ENOMEM;
-
-	skb_reserve(skb, local->hw.extra_tx_headroom);
-
-	switch (action_code) {
-	case WLAN_TDLS_SETUP_REQUEST:
-	case WLAN_TDLS_SETUP_RESPONSE:
-	case WLAN_TDLS_SETUP_CONFIRM:
-	case WLAN_TDLS_TEARDOWN:
-	case WLAN_TDLS_DISCOVERY_REQUEST:
-		ret = ieee80211_prep_tdls_encap_data(wiphy, dev, peer,
-						     action_code, dialog_token,
-						     status_code, skb);
-		send_direct = false;
-		break;
-	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
-		ret = ieee80211_prep_tdls_direct(wiphy, dev, peer, action_code,
-						 dialog_token, status_code,
-						 skb);
-		send_direct = true;
-		break;
-	default:
-		ret = -ENOTSUPP;
-		break;
-	}
-
-	if (ret < 0)
-		goto fail;
-
-	if (extra_ies_len)
-		memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len);
-
-	/* the TDLS link IE is always added last */
-	switch (action_code) {
-	case WLAN_TDLS_SETUP_REQUEST:
-	case WLAN_TDLS_SETUP_CONFIRM:
-	case WLAN_TDLS_TEARDOWN:
-	case WLAN_TDLS_DISCOVERY_REQUEST:
-		/* we are the initiator */
-		ieee80211_tdls_add_link_ie(skb, sdata->vif.addr, peer,
-					   sdata->u.mgd.bssid);
-		break;
-	case WLAN_TDLS_SETUP_RESPONSE:
-	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
-		/* we are the responder */
-		ieee80211_tdls_add_link_ie(skb, peer, sdata->vif.addr,
-					   sdata->u.mgd.bssid);
-		break;
-	default:
-		ret = -ENOTSUPP;
-		goto fail;
-	}
-
-	if (send_direct) {
-		ieee80211_tx_skb(sdata, skb);
-		return 0;
-	}
-
-	/*
-	 * According to 802.11z: Setup req/resp are sent in AC_BK, otherwise
-	 * we should default to AC_VI.
-	 */
-	switch (action_code) {
-	case WLAN_TDLS_SETUP_REQUEST:
-	case WLAN_TDLS_SETUP_RESPONSE:
-		skb_set_queue_mapping(skb, IEEE80211_AC_BK);
-		skb->priority = 2;
-		break;
-	default:
-		skb_set_queue_mapping(skb, IEEE80211_AC_VI);
-		skb->priority = 5;
-		break;
-	}
-
-	/* disable bottom halves when entering the Tx path */
-	local_bh_disable();
-	ret = ieee80211_subif_start_xmit(skb, dev);
-	local_bh_enable();
-
-	return ret;
-
-fail:
-	dev_kfree_skb(skb);
-	return ret;
-}
-
-static int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
-			       u8 *peer, enum nl80211_tdls_operation oper)
-{
-	struct sta_info *sta;
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-
-	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
-		return -ENOTSUPP;
-
-	if (sdata->vif.type != NL80211_IFTYPE_STATION)
-		return -EINVAL;
-
-	tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer);
-
-	switch (oper) {
-	case NL80211_TDLS_ENABLE_LINK:
-		rcu_read_lock();
-		sta = sta_info_get(sdata, peer);
-		if (!sta) {
-			rcu_read_unlock();
-			return -ENOLINK;
-		}
-
-		set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH);
-		rcu_read_unlock();
-		break;
-	case NL80211_TDLS_DISABLE_LINK:
-		return sta_info_destroy_addr(sdata, peer);
-	case NL80211_TDLS_TEARDOWN:
-	case NL80211_TDLS_SETUP:
-	case NL80211_TDLS_DISCOVERY_REQ:
-		/* We don't support in-driver setup/teardown/discovery */
-		return -ENOTSUPP;
-	default:
-		return -ENOTSUPP;
-	}
-
-	return 0;
-}
-
 static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 				  const u8 *peer, u64 *cookie)
 {
@@ -3949,6 +3769,21 @@ static int ieee80211_set_qos_map(struct wiphy *wiphy,
 	return 0;
 }
 
+static int ieee80211_set_ap_chanwidth(struct wiphy *wiphy,
+				      struct net_device *dev,
+				      struct cfg80211_chan_def *chandef)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	int ret;
+	u32 changed = 0;
+
+	ret = ieee80211_vif_change_bandwidth(sdata, chandef, &changed);
+	if (ret == 0)
+		ieee80211_bss_info_change_notify(sdata, changed);
+
+	return ret;
+}
+
 const struct cfg80211_ops mac80211_config_ops = {
 	.add_virtual_intf = ieee80211_add_iface,
 	.del_virtual_intf = ieee80211_del_iface,
@@ -4029,4 +3864,5 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.start_radar_detection = ieee80211_start_radar_detection,
 	.channel_switch = ieee80211_channel_switch,
 	.set_qos_map = ieee80211_set_qos_map,
+	.set_ap_chanwidth = ieee80211_set_ap_chanwidth,
 };
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 75b5dd2c926..a310e33972d 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -9,6 +9,170 @@
 #include "ieee80211_i.h"
 #include "driver-ops.h"
 
+static int ieee80211_chanctx_num_assigned(struct ieee80211_local *local,
+					  struct ieee80211_chanctx *ctx)
+{
+	struct ieee80211_sub_if_data *sdata;
+	int num = 0;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(sdata, &ctx->assigned_vifs, assigned_chanctx_list)
+		num++;
+
+	return num;
+}
+
+static int ieee80211_chanctx_num_reserved(struct ieee80211_local *local,
+					  struct ieee80211_chanctx *ctx)
+{
+	struct ieee80211_sub_if_data *sdata;
+	int num = 0;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(sdata, &ctx->reserved_vifs, reserved_chanctx_list)
+		num++;
+
+	return num;
+}
+
+int ieee80211_chanctx_refcount(struct ieee80211_local *local,
+			       struct ieee80211_chanctx *ctx)
+{
+	return ieee80211_chanctx_num_assigned(local, ctx) +
+	       ieee80211_chanctx_num_reserved(local, ctx);
+}
+
+static int ieee80211_num_chanctx(struct ieee80211_local *local)
+{
+	struct ieee80211_chanctx *ctx;
+	int num = 0;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(ctx, &local->chanctx_list, list)
+		num++;
+
+	return num;
+}
+
+static bool ieee80211_can_create_new_chanctx(struct ieee80211_local *local)
+{
+	lockdep_assert_held(&local->chanctx_mtx);
+	return ieee80211_num_chanctx(local) < ieee80211_max_num_channels(local);
+}
+
+static const struct cfg80211_chan_def *
+ieee80211_chanctx_reserved_chandef(struct ieee80211_local *local,
+				   struct ieee80211_chanctx *ctx,
+				   const struct cfg80211_chan_def *compat)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(sdata, &ctx->reserved_vifs,
+			    reserved_chanctx_list) {
+		if (!compat)
+			compat = &sdata->reserved_chandef;
+
+		compat = cfg80211_chandef_compatible(&sdata->reserved_chandef,
+						     compat);
+		if (!compat)
+			break;
+	}
+
+	return compat;
+}
+
+static const struct cfg80211_chan_def *
+ieee80211_chanctx_non_reserved_chandef(struct ieee80211_local *local,
+				       struct ieee80211_chanctx *ctx,
+				       const struct cfg80211_chan_def *compat)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(sdata, &ctx->assigned_vifs,
+			    assigned_chanctx_list) {
+		if (sdata->reserved_chanctx != NULL)
+			continue;
+
+		if (!compat)
+			compat = &sdata->vif.bss_conf.chandef;
+
+		compat = cfg80211_chandef_compatible(
+				&sdata->vif.bss_conf.chandef, compat);
+		if (!compat)
+			break;
+	}
+
+	return compat;
+}
+
+static const struct cfg80211_chan_def *
+ieee80211_chanctx_combined_chandef(struct ieee80211_local *local,
+				   struct ieee80211_chanctx *ctx,
+				   const struct cfg80211_chan_def *compat)
+{
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	compat = ieee80211_chanctx_reserved_chandef(local, ctx, compat);
+	if (!compat)
+		return NULL;
+
+	compat = ieee80211_chanctx_non_reserved_chandef(local, ctx, compat);
+	if (!compat)
+		return NULL;
+
+	return compat;
+}
+
+static bool
+ieee80211_chanctx_can_reserve_chandef(struct ieee80211_local *local,
+				      struct ieee80211_chanctx *ctx,
+				      const struct cfg80211_chan_def *def)
+{
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	if (ieee80211_chanctx_combined_chandef(local, ctx, def))
+		return true;
+
+	if (!list_empty(&ctx->reserved_vifs) &&
+	    ieee80211_chanctx_reserved_chandef(local, ctx, def))
+		return true;
+
+	return false;
+}
+
+static struct ieee80211_chanctx *
+ieee80211_find_reservation_chanctx(struct ieee80211_local *local,
+				   const struct cfg80211_chan_def *chandef,
+				   enum ieee80211_chanctx_mode mode)
+{
+	struct ieee80211_chanctx *ctx;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	if (mode == IEEE80211_CHANCTX_EXCLUSIVE)
+		return NULL;
+
+	list_for_each_entry(ctx, &local->chanctx_list, list) {
+		if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE)
+			continue;
+
+		if (!ieee80211_chanctx_can_reserve_chandef(local, ctx,
+							   chandef))
+			continue;
+
+		return ctx;
+	}
+
+	return NULL;
+}
+
 static enum nl80211_chan_width ieee80211_get_sta_bw(struct ieee80211_sta *sta)
 {
 	switch (sta->bandwidth) {
@@ -190,6 +354,11 @@ ieee80211_find_chanctx(struct ieee80211_local *local,
 		if (!compat)
 			continue;
 
+		compat = ieee80211_chanctx_reserved_chandef(local, ctx,
+							    compat);
+		if (!compat)
+			continue;
+
 		ieee80211_change_chanctx(local, ctx, compat);
 
 		return ctx;
@@ -217,62 +386,91 @@ static bool ieee80211_is_radar_required(struct ieee80211_local *local)
 }
 
 static struct ieee80211_chanctx *
-ieee80211_new_chanctx(struct ieee80211_local *local,
-		      const struct cfg80211_chan_def *chandef,
-		      enum ieee80211_chanctx_mode mode)
+ieee80211_alloc_chanctx(struct ieee80211_local *local,
+			const struct cfg80211_chan_def *chandef,
+			enum ieee80211_chanctx_mode mode)
 {
 	struct ieee80211_chanctx *ctx;
-	u32 changed;
-	int err;
 
 	lockdep_assert_held(&local->chanctx_mtx);
 
 	ctx = kzalloc(sizeof(*ctx) + local->hw.chanctx_data_size, GFP_KERNEL);
 	if (!ctx)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
+	INIT_LIST_HEAD(&ctx->assigned_vifs);
+	INIT_LIST_HEAD(&ctx->reserved_vifs);
 	ctx->conf.def = *chandef;
 	ctx->conf.rx_chains_static = 1;
 	ctx->conf.rx_chains_dynamic = 1;
 	ctx->mode = mode;
 	ctx->conf.radar_enabled = ieee80211_is_radar_required(local);
 	ieee80211_recalc_chanctx_min_def(local, ctx);
+
+	return ctx;
+}
+
+static int ieee80211_add_chanctx(struct ieee80211_local *local,
+				 struct ieee80211_chanctx *ctx)
+{
+	u32 changed;
+	int err;
+
+	lockdep_assert_held(&local->mtx);
+	lockdep_assert_held(&local->chanctx_mtx);
+
 	if (!local->use_chanctx)
 		local->hw.conf.radar_enabled = ctx->conf.radar_enabled;
 
-	/* we hold the mutex to prevent idle from changing */
-	lockdep_assert_held(&local->mtx);
 	/* turn idle off *before* setting channel -- some drivers need that */
 	changed = ieee80211_idle_off(local);
 	if (changed)
 		ieee80211_hw_config(local, changed);
 
 	if (!local->use_chanctx) {
-		local->_oper_chandef = *chandef;
+		local->_oper_chandef = ctx->conf.def;
 		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
 	} else {
 		err = drv_add_chanctx(local, ctx);
 		if (err) {
-			kfree(ctx);
 			ieee80211_recalc_idle(local);
-			return ERR_PTR(err);
+			return err;
 		}
 	}
 
-	/* and keep the mutex held until the new chanctx is on the list */
-	list_add_rcu(&ctx->list, &local->chanctx_list);
+	return 0;
+}
 
+static struct ieee80211_chanctx *
+ieee80211_new_chanctx(struct ieee80211_local *local,
+		      const struct cfg80211_chan_def *chandef,
+		      enum ieee80211_chanctx_mode mode)
+{
+	struct ieee80211_chanctx *ctx;
+	int err;
+
+	lockdep_assert_held(&local->mtx);
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	ctx = ieee80211_alloc_chanctx(local, chandef, mode);
+	if (!ctx)
+		return ERR_PTR(-ENOMEM);
+
+	err = ieee80211_add_chanctx(local, ctx);
+	if (err) {
+		kfree(ctx);
+		return ERR_PTR(err);
+	}
+
+	list_add_rcu(&ctx->list, &local->chanctx_list);
 	return ctx;
 }
 
-static void ieee80211_free_chanctx(struct ieee80211_local *local,
-				   struct ieee80211_chanctx *ctx)
+static void ieee80211_del_chanctx(struct ieee80211_local *local,
+				  struct ieee80211_chanctx *ctx)
 {
-	bool check_single_channel = false;
 	lockdep_assert_held(&local->chanctx_mtx);
 
-	WARN_ON_ONCE(ctx->refcount != 0);
-
 	if (!local->use_chanctx) {
 		struct cfg80211_chan_def *chandef = &local->_oper_chandef;
 		chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
@@ -282,8 +480,9 @@ static void ieee80211_free_chanctx(struct ieee80211_local *local,
 		/* NOTE: Disabling radar is only valid here for
 		 * single channel context. To be sure, check it ...
 		 */
-		if (local->hw.conf.radar_enabled)
-			check_single_channel = true;
+		WARN_ON(local->hw.conf.radar_enabled &&
+			!list_empty(&local->chanctx_list));
+
 		local->hw.conf.radar_enabled = false;
 
 		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL);
@@ -291,39 +490,19 @@ static void ieee80211_free_chanctx(struct ieee80211_local *local,
 		drv_remove_chanctx(local, ctx);
 	}
 
-	list_del_rcu(&ctx->list);
-	kfree_rcu(ctx, rcu_head);
-
-	/* throw a warning if this wasn't the only channel context. */
-	WARN_ON(check_single_channel && !list_empty(&local->chanctx_list));
-
 	ieee80211_recalc_idle(local);
 }
 
-static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
-					struct ieee80211_chanctx *ctx)
+static void ieee80211_free_chanctx(struct ieee80211_local *local,
+				   struct ieee80211_chanctx *ctx)
 {
-	struct ieee80211_local *local = sdata->local;
-	int ret;
-
 	lockdep_assert_held(&local->chanctx_mtx);
 
-	ret = drv_assign_vif_chanctx(local, sdata, ctx);
-	if (ret)
-		return ret;
+	WARN_ON_ONCE(ieee80211_chanctx_refcount(local, ctx) != 0);
 
-	rcu_assign_pointer(sdata->vif.chanctx_conf, &ctx->conf);
-	ctx->refcount++;
-
-	ieee80211_recalc_txpower(sdata);
-	ieee80211_recalc_chanctx_min_def(local, ctx);
-	sdata->vif.bss_conf.idle = false;
-
-	if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
-	    sdata->vif.type != NL80211_IFTYPE_MONITOR)
-		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IDLE);
-
-	return 0;
+	list_del_rcu(&ctx->list);
+	ieee80211_del_chanctx(local, ctx);
+	kfree_rcu(ctx, rcu_head);
 }
 
 static void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local,
@@ -384,30 +563,58 @@ static void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local,
 	drv_change_chanctx(local, chanctx, IEEE80211_CHANCTX_CHANGE_RADAR);
 }
 
-static void ieee80211_unassign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
-					   struct ieee80211_chanctx *ctx)
+static int ieee80211_assign_vif_chanctx(struct ieee80211_sub_if_data *sdata,
+					struct ieee80211_chanctx *new_ctx)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *conf;
+	struct ieee80211_chanctx *curr_ctx = NULL;
+	int ret = 0;
 
-	lockdep_assert_held(&local->chanctx_mtx);
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
 
-	ctx->refcount--;
-	rcu_assign_pointer(sdata->vif.chanctx_conf, NULL);
+	if (conf) {
+		curr_ctx = container_of(conf, struct ieee80211_chanctx, conf);
 
-	sdata->vif.bss_conf.idle = true;
+		drv_unassign_vif_chanctx(local, sdata, curr_ctx);
+		conf = NULL;
+		list_del(&sdata->assigned_chanctx_list);
+	}
 
-	if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
-	    sdata->vif.type != NL80211_IFTYPE_MONITOR)
-		ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IDLE);
+	if (new_ctx) {
+		ret = drv_assign_vif_chanctx(local, sdata, new_ctx);
+		if (ret)
+			goto out;
 
-	drv_unassign_vif_chanctx(local, sdata, ctx);
+		conf = &new_ctx->conf;
+		list_add(&sdata->assigned_chanctx_list,
+			 &new_ctx->assigned_vifs);
+	}
+
+out:
+	rcu_assign_pointer(sdata->vif.chanctx_conf, conf);
+
+	sdata->vif.bss_conf.idle = !conf;
+
+	if (curr_ctx && ieee80211_chanctx_num_assigned(local, curr_ctx) > 0) {
+		ieee80211_recalc_chanctx_chantype(local, curr_ctx);
+		ieee80211_recalc_smps_chanctx(local, curr_ctx);
+		ieee80211_recalc_radar_chanctx(local, curr_ctx);
+		ieee80211_recalc_chanctx_min_def(local, curr_ctx);
+	}
 
-	if (ctx->refcount > 0) {
-		ieee80211_recalc_chanctx_chantype(sdata->local, ctx);
-		ieee80211_recalc_smps_chanctx(local, ctx);
-		ieee80211_recalc_radar_chanctx(local, ctx);
-		ieee80211_recalc_chanctx_min_def(local, ctx);
+	if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) {
+		ieee80211_recalc_txpower(sdata);
+		ieee80211_recalc_chanctx_min_def(local, new_ctx);
 	}
+
+	if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
+	    sdata->vif.type != NL80211_IFTYPE_MONITOR)
+		ieee80211_bss_info_change_notify(sdata,
+						 BSS_CHANGED_IDLE);
+
+	return ret;
 }
 
 static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
@@ -425,8 +632,11 @@ static void __ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata)
 
 	ctx = container_of(conf, struct ieee80211_chanctx, conf);
 
-	ieee80211_unassign_vif_chanctx(sdata, ctx);
-	if (ctx->refcount == 0)
+	if (sdata->reserved_chanctx)
+		ieee80211_vif_unreserve_chanctx(sdata);
+
+	ieee80211_assign_vif_chanctx(sdata, NULL);
+	if (ieee80211_chanctx_refcount(local, ctx) == 0)
 		ieee80211_free_chanctx(local, ctx);
 }
 
@@ -526,6 +736,7 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_chanctx *ctx;
+	u8 radar_detect_width = 0;
 	int ret;
 
 	lockdep_assert_held(&local->mtx);
@@ -533,6 +744,22 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 	WARN_ON(sdata->dev && netif_carrier_ok(sdata->dev));
 
 	mutex_lock(&local->chanctx_mtx);
+
+	ret = cfg80211_chandef_dfs_required(local->hw.wiphy,
+					    chandef,
+					    sdata->wdev.iftype);
+	if (ret < 0)
+		goto out;
+	if (ret > 0)
+		radar_detect_width = BIT(chandef->width);
+
+	sdata->radar_required = ret;
+
+	ret = ieee80211_check_combinations(sdata, chandef, mode,
+					   radar_detect_width);
+	if (ret < 0)
+		goto out;
+
 	__ieee80211_vif_release_channel(sdata);
 
 	ctx = ieee80211_find_chanctx(local, chandef, mode);
@@ -548,7 +775,7 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 	ret = ieee80211_assign_vif_chanctx(sdata, ctx);
 	if (ret) {
 		/* if assign fails refcount stays the same */
-		if (ctx->refcount == 0)
+		if (ieee80211_chanctx_refcount(local, ctx) == 0)
 			ieee80211_free_chanctx(local, ctx);
 		goto out;
 	}
@@ -560,15 +787,47 @@ int ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 	return ret;
 }
 
+static int __ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata,
+					  struct ieee80211_chanctx *ctx,
+					  u32 *changed)
+{
+	struct ieee80211_local *local = sdata->local;
+	const struct cfg80211_chan_def *chandef = &sdata->csa_chandef;
+	u32 chanctx_changed = 0;
+
+	if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef,
+				     IEEE80211_CHAN_DISABLED))
+		return -EINVAL;
+
+	if (ieee80211_chanctx_refcount(local, ctx) != 1)
+		return -EINVAL;
+
+	if (sdata->vif.bss_conf.chandef.width != chandef->width) {
+		chanctx_changed = IEEE80211_CHANCTX_CHANGE_WIDTH;
+		*changed |= BSS_CHANGED_BANDWIDTH;
+	}
+
+	sdata->vif.bss_conf.chandef = *chandef;
+	ctx->conf.def = *chandef;
+
+	chanctx_changed |= IEEE80211_CHANCTX_CHANGE_CHANNEL;
+	drv_change_chanctx(local, ctx, chanctx_changed);
+
+	ieee80211_recalc_chanctx_chantype(local, ctx);
+	ieee80211_recalc_smps_chanctx(local, ctx);
+	ieee80211_recalc_radar_chanctx(local, ctx);
+	ieee80211_recalc_chanctx_min_def(local, ctx);
+
+	return 0;
+}
+
 int ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata,
 				 u32 *changed)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_chanctx_conf *conf;
 	struct ieee80211_chanctx *ctx;
-	const struct cfg80211_chan_def *chandef = &sdata->csa_chandef;
 	int ret;
-	u32 chanctx_changed = 0;
 
 	lockdep_assert_held(&local->mtx);
 
@@ -576,11 +835,94 @@ int ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata,
 	if (WARN_ON(!sdata->vif.csa_active))
 		return -EINVAL;
 
-	if (!cfg80211_chandef_usable(sdata->local->hw.wiphy, chandef,
-				     IEEE80211_CHAN_DISABLED))
+	mutex_lock(&local->chanctx_mtx);
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	if (!conf) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ctx = container_of(conf, struct ieee80211_chanctx, conf);
+
+	ret = __ieee80211_vif_change_channel(sdata, ctx, changed);
+ out:
+	mutex_unlock(&local->chanctx_mtx);
+	return ret;
+}
+
+static void
+__ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata,
+				      bool clear)
+{
+	struct ieee80211_local *local __maybe_unused = sdata->local;
+	struct ieee80211_sub_if_data *vlan;
+	struct ieee80211_chanctx_conf *conf;
+
+	if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP))
+		return;
+
+	lockdep_assert_held(&local->mtx);
+
+	/* Check that conf exists, even when clearing this function
+	 * must be called with the AP's channel context still there
+	 * as it would otherwise cause VLANs to have an invalid
+	 * channel context pointer for a while, possibly pointing
+	 * to a channel context that has already been freed.
+	 */
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	WARN_ON(!conf);
+
+	if (clear)
+		conf = NULL;
+
+	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
+		rcu_assign_pointer(vlan->vif.chanctx_conf, conf);
+}
+
+void ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata,
+					 bool clear)
+{
+	struct ieee80211_local *local = sdata->local;
+
+	mutex_lock(&local->chanctx_mtx);
+
+	__ieee80211_vif_copy_chanctx_to_vlans(sdata, clear);
+
+	mutex_unlock(&local->chanctx_mtx);
+}
+
+int ieee80211_vif_unreserve_chanctx(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_chanctx *ctx = sdata->reserved_chanctx;
+
+	lockdep_assert_held(&sdata->local->chanctx_mtx);
+
+	if (WARN_ON(!ctx))
 		return -EINVAL;
 
+	list_del(&sdata->reserved_chanctx_list);
+	sdata->reserved_chanctx = NULL;
+
+	if (ieee80211_chanctx_refcount(sdata->local, ctx) == 0)
+		ieee80211_free_chanctx(sdata->local, ctx);
+
+	return 0;
+}
+
+int ieee80211_vif_reserve_chanctx(struct ieee80211_sub_if_data *sdata,
+				  const struct cfg80211_chan_def *chandef,
+				  enum ieee80211_chanctx_mode mode,
+				  bool radar_required)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx_conf *conf;
+	struct ieee80211_chanctx *new_ctx, *curr_ctx;
+	int ret = 0;
+
 	mutex_lock(&local->chanctx_mtx);
+
 	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
 					 lockdep_is_held(&local->chanctx_mtx));
 	if (!conf) {
@@ -588,30 +930,108 @@ int ieee80211_vif_change_channel(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
-	ctx = container_of(conf, struct ieee80211_chanctx, conf);
-	if (ctx->refcount != 1) {
+	curr_ctx = container_of(conf, struct ieee80211_chanctx, conf);
+
+	new_ctx = ieee80211_find_reservation_chanctx(local, chandef, mode);
+	if (!new_ctx) {
+		if (ieee80211_chanctx_refcount(local, curr_ctx) == 1 &&
+		    (local->hw.flags & IEEE80211_HW_CHANGE_RUNNING_CHANCTX)) {
+			/* if we're the only users of the chanctx and
+			 * the driver supports changing a running
+			 * context, reserve our current context
+			 */
+			new_ctx = curr_ctx;
+		} else if (ieee80211_can_create_new_chanctx(local)) {
+			/* create a new context and reserve it */
+			new_ctx = ieee80211_new_chanctx(local, chandef, mode);
+			if (IS_ERR(new_ctx)) {
+				ret = PTR_ERR(new_ctx);
+				goto out;
+			}
+		} else {
+			ret = -EBUSY;
+			goto out;
+		}
+	}
+
+	list_add(&sdata->reserved_chanctx_list, &new_ctx->reserved_vifs);
+	sdata->reserved_chanctx = new_ctx;
+	sdata->reserved_chandef = *chandef;
+	sdata->reserved_radar_required = radar_required;
+out:
+	mutex_unlock(&local->chanctx_mtx);
+	return ret;
+}
+
+int ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata,
+				       u32 *changed)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_chanctx *ctx;
+	struct ieee80211_chanctx *old_ctx;
+	struct ieee80211_chanctx_conf *conf;
+	int ret;
+	u32 tmp_changed = *changed;
+
+	/* TODO: need to recheck if the chandef is usable etc.? */
+
+	lockdep_assert_held(&local->mtx);
+
+	mutex_lock(&local->chanctx_mtx);
+
+	ctx = sdata->reserved_chanctx;
+	if (WARN_ON(!ctx)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (sdata->vif.bss_conf.chandef.width != chandef->width) {
-		chanctx_changed = IEEE80211_CHANCTX_CHANGE_WIDTH;
-		*changed |= BSS_CHANGED_BANDWIDTH;
+	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
+					 lockdep_is_held(&local->chanctx_mtx));
+	if (!conf) {
+		ret = -EINVAL;
+		goto out;
 	}
 
-	sdata->vif.bss_conf.chandef = *chandef;
-	ctx->conf.def = *chandef;
+	old_ctx = container_of(conf, struct ieee80211_chanctx, conf);
 
-	chanctx_changed |= IEEE80211_CHANCTX_CHANGE_CHANNEL;
-	drv_change_chanctx(local, ctx, chanctx_changed);
+	if (sdata->vif.bss_conf.chandef.width != sdata->reserved_chandef.width)
+		tmp_changed |= BSS_CHANGED_BANDWIDTH;
+
+	sdata->vif.bss_conf.chandef = sdata->reserved_chandef;
+
+	/* unref our reservation */
+	sdata->reserved_chanctx = NULL;
+	sdata->radar_required = sdata->reserved_radar_required;
+	list_del(&sdata->reserved_chanctx_list);
+
+	if (old_ctx == ctx) {
+		/* This is our own context, just change it */
+		ret = __ieee80211_vif_change_channel(sdata, old_ctx,
+						     &tmp_changed);
+		if (ret)
+			goto out;
+	} else {
+		ret = ieee80211_assign_vif_chanctx(sdata, ctx);
+		if (ieee80211_chanctx_refcount(local, old_ctx) == 0)
+			ieee80211_free_chanctx(local, old_ctx);
+		if (ret) {
+			/* if assign fails refcount stays the same */
+			if (ieee80211_chanctx_refcount(local, ctx) == 0)
+				ieee80211_free_chanctx(local, ctx);
+			goto out;
+		}
+
+		if (sdata->vif.type == NL80211_IFTYPE_AP)
+			__ieee80211_vif_copy_chanctx_to_vlans(sdata, false);
+	}
+
+	*changed = tmp_changed;
 
 	ieee80211_recalc_chanctx_chantype(local, ctx);
 	ieee80211_recalc_smps_chanctx(local, ctx);
 	ieee80211_recalc_radar_chanctx(local, ctx);
 	ieee80211_recalc_chanctx_min_def(local, ctx);
-
-	ret = 0;
- out:
+out:
 	mutex_unlock(&local->chanctx_mtx);
 	return ret;
 }
@@ -695,40 +1115,6 @@ void ieee80211_vif_vlan_copy_chanctx(struct ieee80211_sub_if_data *sdata)
 	mutex_unlock(&local->chanctx_mtx);
 }
 
-void ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata,
-					 bool clear)
-{
-	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_sub_if_data *vlan;
-	struct ieee80211_chanctx_conf *conf;
-
-	ASSERT_RTNL();
-
-	if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_AP))
-		return;
-
-	mutex_lock(&local->chanctx_mtx);
-
-	/*
-	 * Check that conf exists, even when clearing this function
-	 * must be called with the AP's channel context still there
-	 * as it would otherwise cause VLANs to have an invalid
-	 * channel context pointer for a while, possibly pointing
-	 * to a channel context that has already been freed.
-	 */
-	conf = rcu_dereference_protected(sdata->vif.chanctx_conf,
-				lockdep_is_held(&local->chanctx_mtx));
-	WARN_ON(!conf);
-
-	if (clear)
-		conf = NULL;
-
-	list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list)
-		rcu_assign_pointer(vlan->vif.chanctx_conf, conf);
-
-	mutex_unlock(&local->chanctx_mtx);
-}
-
 void ieee80211_iter_chan_contexts_atomic(
 	struct ieee80211_hw *hw,
 	void (*iter)(struct ieee80211_hw *hw,
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index fa16e54980a..0e963bc1cea 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -128,7 +128,7 @@ static ssize_t sta_tx_latency_stat_write(struct file *file,
 	if (!strcmp(buf, TX_LATENCY_DISABLED)) {
 		if (!tx_latency)
 			goto unlock;
-		rcu_assign_pointer(local->tx_latency, NULL);
+		RCU_INIT_POINTER(local->tx_latency, NULL);
 		synchronize_rcu();
 		kfree(tx_latency);
 		goto unlock;
diff --git a/net/mac80211/debugfs.h b/net/mac80211/debugfs.h
index 214ed4ecd73..60c35afee29 100644
--- a/net/mac80211/debugfs.h
+++ b/net/mac80211/debugfs.h
@@ -1,6 +1,8 @@
 #ifndef __MAC80211_DEBUGFS_H
 #define __MAC80211_DEBUGFS_H
 
+#include "ieee80211_i.h"
+
 #ifdef CONFIG_MAC80211_DEBUGFS
 void debugfs_hw_add(struct ieee80211_local *local);
 int __printf(4, 5) mac80211_format_buffer(char __user *userbuf, size_t count,
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 40a64893898..e205ebabfa5 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -34,8 +34,7 @@ static ssize_t ieee80211_if_read(
 	ssize_t ret = -EINVAL;
 
 	read_lock(&dev_base_lock);
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*format)(sdata, buf, sizeof(buf));
+	ret = (*format)(sdata, buf, sizeof(buf));
 	read_unlock(&dev_base_lock);
 
 	if (ret >= 0)
@@ -62,8 +61,7 @@ static ssize_t ieee80211_if_write(
 
 	ret = -ENODEV;
 	rtnl_lock();
-	if (sdata->dev->reg_state == NETREG_REGISTERED)
-		ret = (*write)(sdata, buf, count);
+	ret = (*write)(sdata, buf, count);
 	rtnl_unlock();
 
 	return ret;
diff --git a/net/mac80211/debugfs_netdev.h b/net/mac80211/debugfs_netdev.h
index 79025e79f4d..9f5501a9a79 100644
--- a/net/mac80211/debugfs_netdev.h
+++ b/net/mac80211/debugfs_netdev.h
@@ -3,6 +3,8 @@
 #ifndef __IEEE80211_DEBUGFS_NETDEV_H
 #define __IEEE80211_DEBUGFS_NETDEV_H
 
+#include "ieee80211_i.h"
+
 #ifdef CONFIG_MAC80211_DEBUGFS
 void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata);
 void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index fc689f5d971..bd782dcffcc 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -5,11 +5,11 @@
 #include "ieee80211_i.h"
 #include "trace.h"
 
-static inline void check_sdata_in_driver(struct ieee80211_sub_if_data *sdata)
+static inline bool check_sdata_in_driver(struct ieee80211_sub_if_data *sdata)
 {
-	WARN(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER),
-	     "%s:  Failed check-sdata-in-driver check, flags: 0x%x\n",
-	     sdata->dev ? sdata->dev->name : sdata->name, sdata->flags);
+	return !WARN(!(sdata->flags & IEEE80211_SDATA_IN_DRIVER),
+		     "%s:  Failed check-sdata-in-driver check, flags: 0x%x\n",
+		     sdata->dev ? sdata->dev->name : sdata->name, sdata->flags);
 }
 
 static inline struct ieee80211_sub_if_data *
@@ -168,7 +168,8 @@ static inline int drv_change_interface(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_change_interface(local, sdata, type, p2p);
 	ret = local->ops->change_interface(&local->hw, &sdata->vif, type, p2p);
@@ -181,7 +182,8 @@ static inline void drv_remove_interface(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_remove_interface(local, sdata);
 	local->ops->remove_interface(&local->hw, &sdata->vif);
@@ -219,7 +221,8 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local,
 			 sdata->vif.type == NL80211_IFTYPE_MONITOR))
 		return;
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_bss_info_changed(local, sdata, info, changed);
 	if (local->ops->bss_info_changed)
@@ -278,7 +281,8 @@ static inline int drv_set_key(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_set_key(local, cmd, sdata, sta, key);
 	ret = local->ops->set_key(&local->hw, cmd, &sdata->vif, sta, key);
@@ -298,7 +302,8 @@ static inline void drv_update_tkip_key(struct ieee80211_local *local,
 		ista = &sta->sta;
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_update_tkip_key(local, sdata, conf, ista, iv32);
 	if (local->ops->update_tkip_key)
@@ -315,7 +320,8 @@ static inline int drv_hw_scan(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_hw_scan(local, sdata);
 	ret = local->ops->hw_scan(&local->hw, &sdata->vif, req);
@@ -328,7 +334,8 @@ static inline void drv_cancel_hw_scan(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_cancel_hw_scan(local, sdata);
 	local->ops->cancel_hw_scan(&local->hw, &sdata->vif);
@@ -345,7 +352,8 @@ drv_sched_scan_start(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_sched_scan_start(local, sdata);
 	ret = local->ops->sched_scan_start(&local->hw, &sdata->vif,
@@ -361,7 +369,8 @@ static inline int drv_sched_scan_stop(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_sched_scan_stop(local, sdata);
 	ret = local->ops->sched_scan_stop(&local->hw, &sdata->vif);
@@ -462,7 +471,8 @@ static inline void drv_sta_notify(struct ieee80211_local *local,
 				  struct ieee80211_sta *sta)
 {
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_sta_notify(local, sdata, cmd, sta);
 	if (local->ops->sta_notify)
@@ -479,7 +489,8 @@ static inline int drv_sta_add(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_sta_add(local, sdata, sta);
 	if (local->ops->sta_add)
@@ -497,7 +508,8 @@ static inline void drv_sta_remove(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_sta_remove(local, sdata, sta);
 	if (local->ops->sta_remove)
@@ -515,7 +527,8 @@ static inline void drv_sta_add_debugfs(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	if (local->ops->sta_add_debugfs)
 		local->ops->sta_add_debugfs(&local->hw, &sdata->vif,
@@ -545,7 +558,8 @@ static inline void drv_sta_pre_rcu_remove(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_sta_pre_rcu_remove(local, sdata, &sta->sta);
 	if (local->ops->sta_pre_rcu_remove)
@@ -566,7 +580,8 @@ int drv_sta_state(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_sta_state(local, sdata, &sta->sta, old_state, new_state);
 	if (local->ops->sta_state) {
@@ -590,7 +605,8 @@ static inline void drv_sta_rc_update(struct ieee80211_local *local,
 				     struct ieee80211_sta *sta, u32 changed)
 {
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	WARN_ON(changed & IEEE80211_RC_SUPP_RATES_CHANGED &&
 		(sdata->vif.type != NL80211_IFTYPE_ADHOC &&
@@ -612,7 +628,8 @@ static inline int drv_conf_tx(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_conf_tx(local, sdata, ac, params);
 	if (local->ops->conf_tx)
@@ -629,7 +646,8 @@ static inline u64 drv_get_tsf(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return ret;
 
 	trace_drv_get_tsf(local, sdata);
 	if (local->ops->get_tsf)
@@ -644,7 +662,8 @@ static inline void drv_set_tsf(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_set_tsf(local, sdata, tsf);
 	if (local->ops->set_tsf)
@@ -657,7 +676,8 @@ static inline void drv_reset_tsf(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_reset_tsf(local, sdata);
 	if (local->ops->reset_tsf)
@@ -689,7 +709,8 @@ static inline int drv_ampdu_action(struct ieee80211_local *local,
 	might_sleep();
 
 	sdata = get_bss_sdata(sdata);
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn, buf_size);
 
@@ -726,13 +747,19 @@ static inline void drv_rfkill_poll(struct ieee80211_local *local)
 }
 
 static inline void drv_flush(struct ieee80211_local *local,
+			     struct ieee80211_sub_if_data *sdata,
 			     u32 queues, bool drop)
 {
+	struct ieee80211_vif *vif = sdata ? &sdata->vif : NULL;
+
 	might_sleep();
 
+	if (sdata && !check_sdata_in_driver(sdata))
+		return;
+
 	trace_drv_flush(local, queues, drop);
 	if (local->ops->flush)
-		local->ops->flush(&local->hw, queues, drop);
+		local->ops->flush(&local->hw, vif, queues, drop);
 	trace_drv_return_void(local);
 }
 
@@ -848,7 +875,8 @@ static inline int drv_set_bitrate_mask(struct ieee80211_local *local,
 
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_set_bitrate_mask(local, sdata, mask);
 	if (local->ops->set_bitrate_mask)
@@ -863,7 +891,8 @@ static inline void drv_set_rekey_data(struct ieee80211_local *local,
 				      struct ieee80211_sub_if_data *sdata,
 				      struct cfg80211_gtk_rekey_data *data)
 {
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_set_rekey_data(local, sdata, data);
 	if (local->ops->set_rekey_data)
@@ -931,7 +960,8 @@ static inline void drv_mgd_prepare_tx(struct ieee80211_local *local,
 {
 	might_sleep();
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 	WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION);
 
 	trace_drv_mgd_prepare_tx(local, sdata);
@@ -958,6 +988,9 @@ static inline int drv_add_chanctx(struct ieee80211_local *local,
 static inline void drv_remove_chanctx(struct ieee80211_local *local,
 				      struct ieee80211_chanctx *ctx)
 {
+	if (WARN_ON(!ctx->driver_present))
+		return;
+
 	trace_drv_remove_chanctx(local, ctx);
 	if (local->ops->remove_chanctx)
 		local->ops->remove_chanctx(&local->hw, &ctx->conf);
@@ -983,7 +1016,8 @@ static inline int drv_assign_vif_chanctx(struct ieee80211_local *local,
 {
 	int ret = 0;
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_assign_vif_chanctx(local, sdata, ctx);
 	if (local->ops->assign_vif_chanctx) {
@@ -1001,7 +1035,8 @@ static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local,
 					    struct ieee80211_sub_if_data *sdata,
 					    struct ieee80211_chanctx *ctx)
 {
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_unassign_vif_chanctx(local, sdata, ctx);
 	if (local->ops->unassign_vif_chanctx) {
@@ -1013,12 +1048,66 @@ static inline void drv_unassign_vif_chanctx(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline int
+drv_switch_vif_chanctx(struct ieee80211_local *local,
+		       struct ieee80211_vif_chanctx_switch *vifs,
+		       int n_vifs,
+		       enum ieee80211_chanctx_switch_mode mode)
+{
+	int ret = 0;
+	int i;
+
+	if (!local->ops->switch_vif_chanctx)
+		return -EOPNOTSUPP;
+
+	for (i = 0; i < n_vifs; i++) {
+		struct ieee80211_chanctx *new_ctx =
+			container_of(vifs[i].new_ctx,
+				     struct ieee80211_chanctx,
+				     conf);
+		struct ieee80211_chanctx *old_ctx =
+			container_of(vifs[i].old_ctx,
+				     struct ieee80211_chanctx,
+				     conf);
+
+		WARN_ON_ONCE(!old_ctx->driver_present);
+		WARN_ON_ONCE((mode == CHANCTX_SWMODE_SWAP_CONTEXTS &&
+			      new_ctx->driver_present) ||
+			     (mode == CHANCTX_SWMODE_REASSIGN_VIF &&
+			      !new_ctx->driver_present));
+	}
+
+	trace_drv_switch_vif_chanctx(local, vifs, n_vifs, mode);
+	ret = local->ops->switch_vif_chanctx(&local->hw,
+					     vifs, n_vifs, mode);
+	trace_drv_return_int(local, ret);
+
+	if (!ret && mode == CHANCTX_SWMODE_SWAP_CONTEXTS) {
+		for (i = 0; i < n_vifs; i++) {
+			struct ieee80211_chanctx *new_ctx =
+				container_of(vifs[i].new_ctx,
+					     struct ieee80211_chanctx,
+					     conf);
+			struct ieee80211_chanctx *old_ctx =
+				container_of(vifs[i].old_ctx,
+					     struct ieee80211_chanctx,
+					     conf);
+
+			new_ctx->driver_present = true;
+			old_ctx->driver_present = false;
+		}
+	}
+
+	return ret;
+}
+
 static inline int drv_start_ap(struct ieee80211_local *local,
 			       struct ieee80211_sub_if_data *sdata)
 {
 	int ret = 0;
 
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_start_ap(local, sdata, &sdata->vif.bss_conf);
 	if (local->ops->start_ap)
@@ -1030,7 +1119,8 @@ static inline int drv_start_ap(struct ieee80211_local *local,
 static inline void drv_stop_ap(struct ieee80211_local *local,
 			       struct ieee80211_sub_if_data *sdata)
 {
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_stop_ap(local, sdata);
 	if (local->ops->stop_ap)
@@ -1053,7 +1143,8 @@ drv_set_default_unicast_key(struct ieee80211_local *local,
 			    struct ieee80211_sub_if_data *sdata,
 			    int key_idx)
 {
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	WARN_ON_ONCE(key_idx < -1 || key_idx > 3);
 
@@ -1095,7 +1186,8 @@ static inline int drv_join_ibss(struct ieee80211_local *local,
 	int ret = 0;
 
 	might_sleep();
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return -EIO;
 
 	trace_drv_join_ibss(local, sdata, &sdata->vif.bss_conf);
 	if (local->ops->join_ibss)
@@ -1108,7 +1200,8 @@ static inline void drv_leave_ibss(struct ieee80211_local *local,
 				  struct ieee80211_sub_if_data *sdata)
 {
 	might_sleep();
-	check_sdata_in_driver(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
 
 	trace_drv_leave_ibss(local, sdata);
 	if (local->ops->leave_ibss)
@@ -1116,4 +1209,17 @@ static inline void drv_leave_ibss(struct ieee80211_local *local,
 	trace_drv_return_void(local);
 }
 
+static inline u32 drv_get_expected_throughput(struct ieee80211_local *local,
+					      struct ieee80211_sta *sta)
+{
+	u32 ret = 0;
+
+	trace_drv_get_expected_throughput(sta);
+	if (local->ops->get_expected_throughput)
+		ret = local->ops->get_expected_throughput(sta);
+	trace_drv_return_u32(local, ret);
+
+	return ret;
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index c150b68436d..15702ff64a4 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -31,6 +31,18 @@ static void __check_htcap_disable(struct ieee80211_ht_cap *ht_capa,
 	}
 }
 
+static void __check_htcap_enable(struct ieee80211_ht_cap *ht_capa,
+				  struct ieee80211_ht_cap *ht_capa_mask,
+				  struct ieee80211_sta_ht_cap *ht_cap,
+				  u16 flag)
+{
+	__le16 le_flag = cpu_to_le16(flag);
+
+	if ((ht_capa_mask->cap_info & le_flag) &&
+	    (ht_capa->cap_info & le_flag))
+		ht_cap->cap |= flag;
+}
+
 void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
 				     struct ieee80211_sta_ht_cap *ht_cap)
 {
@@ -59,7 +71,7 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
 	smask = (u8 *)(&ht_capa_mask->mcs.rx_mask);
 
 	/* NOTE:  If you add more over-rides here, update register_hw
-	 * ht_capa_mod_msk logic in main.c as well.
+	 * ht_capa_mod_mask logic in main.c as well.
 	 * And, if this method can ever change ht_cap.ht_supported, fix
 	 * the check in ieee80211_add_ht_ie.
 	 */
@@ -86,6 +98,14 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
 	__check_htcap_disable(ht_capa, ht_capa_mask, ht_cap,
 			      IEEE80211_HT_CAP_MAX_AMSDU);
 
+	/* Allow user to disable LDPC */
+	__check_htcap_disable(ht_capa, ht_capa_mask, ht_cap,
+			      IEEE80211_HT_CAP_LDPC_CODING);
+
+	/* Allow user to enable 40 MHz intolerant bit. */
+	__check_htcap_enable(ht_capa, ht_capa_mask, ht_cap,
+			     IEEE80211_HT_CAP_40MHZ_INTOLERANT);
+
 	/* Allow user to decrease AMPDU factor */
 	if (ht_capa_mask->ampdu_params_info &
 	    IEEE80211_HT_AMPDU_PARM_FACTOR) {
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 06d28787945..18ee0a256b1 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -143,7 +143,7 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata,
 		*pos++ = csa_settings->block_tx ? 1 : 0;
 		*pos++ = ieee80211_frequency_to_channel(
 				csa_settings->chandef.chan->center_freq);
-		sdata->csa_counter_offset_beacon = (pos - presp->head);
+		sdata->csa_counter_offset_beacon[0] = (pos - presp->head);
 		*pos++ = csa_settings->count;
 	}
 
@@ -228,7 +228,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	struct beacon_data *presp;
 	enum nl80211_bss_scan_width scan_width;
 	bool have_higher_than_11mbit;
-	bool radar_required = false;
+	bool radar_required;
 	int err;
 
 	sdata_assert_lock(sdata);
@@ -253,7 +253,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 
 	presp = rcu_dereference_protected(ifibss->presp,
 					  lockdep_is_held(&sdata->wdev.mtx));
-	rcu_assign_pointer(ifibss->presp, NULL);
+	RCU_INIT_POINTER(ifibss->presp, NULL);
 	if (presp)
 		kfree_rcu(presp, rcu_head);
 
@@ -262,7 +262,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	/* make a copy of the chandef, it could be modified below. */
 	chandef = *req_chandef;
 	chan = chandef.chan;
-	if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef)) {
+	if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef,
+				     NL80211_IFTYPE_ADHOC)) {
 		if (chandef.width == NL80211_CHAN_WIDTH_5 ||
 		    chandef.width == NL80211_CHAN_WIDTH_10 ||
 		    chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
@@ -274,7 +275,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 		chandef.width = NL80211_CHAN_WIDTH_20;
 		chandef.center_freq1 = chan->center_freq;
 		/* check again for downgraded chandef */
-		if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef)) {
+		if (!cfg80211_reg_can_beacon(local->hw.wiphy, &chandef,
+					     NL80211_IFTYPE_ADHOC)) {
 			sdata_info(sdata,
 				   "Failed to join IBSS, beacons forbidden\n");
 			return;
@@ -282,21 +284,20 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
 	}
 
 	err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy,
-					    &chandef);
+					    &chandef, NL80211_IFTYPE_ADHOC);
 	if (err < 0) {
 		sdata_info(sdata,
 			   "Failed to join IBSS, invalid chandef\n");
 		return;
 	}
-	if (err > 0) {
-		if (!ifibss->userspace_handles_dfs) {
-			sdata_info(sdata,
-				   "Failed to join IBSS, DFS channel without control program\n");
-			return;
-		}
-		radar_required = true;
+	if (err > 0 && !ifibss->userspace_handles_dfs) {
+		sdata_info(sdata,
+			   "Failed to join IBSS, DFS channel without control program\n");
+		return;
 	}
 
+	radar_required = err;
+
 	mutex_lock(&local->mtx);
 	if (ieee80211_vif_use_channel(sdata, &chandef,
 				      ifibss->fixed_channel ?
@@ -775,7 +776,8 @@ static void ieee80211_ibss_csa_mark_radar(struct ieee80211_sub_if_data *sdata)
 	 * unavailable.
 	 */
 	err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy,
-					    &ifibss->chandef);
+					    &ifibss->chandef,
+					    NL80211_IFTYPE_ADHOC);
 	if (err > 0)
 		cfg80211_radar_event(sdata->local->hw.wiphy, &ifibss->chandef,
 				     GFP_ATOMIC);
@@ -861,7 +863,8 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		goto disconnect;
 	}
 
-	if (!cfg80211_reg_can_beacon(sdata->local->hw.wiphy, &params.chandef)) {
+	if (!cfg80211_reg_can_beacon(sdata->local->hw.wiphy, &params.chandef,
+				     NL80211_IFTYPE_ADHOC)) {
 		sdata_info(sdata,
 			   "IBSS %pM switches to unsupported channel (%d MHz, width:%d, CF1/2: %d/%d MHz), disconnecting\n",
 			   ifibss->bssid,
@@ -873,17 +876,17 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	}
 
 	err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy,
-					    &params.chandef);
+					    &params.chandef,
+					    NL80211_IFTYPE_ADHOC);
 	if (err < 0)
 		goto disconnect;
-	if (err) {
+	if (err > 0 && !ifibss->userspace_handles_dfs) {
 		/* IBSS-DFS only allowed with a control program */
-		if (!ifibss->userspace_handles_dfs)
-			goto disconnect;
-
-		params.radar_required = true;
+		goto disconnect;
 	}
 
+	params.radar_required = err;
+
 	if (cfg80211_chandef_identical(&params.chandef,
 				       &sdata->vif.bss_conf.chandef)) {
 		ibss_dbg(sdata,
@@ -1636,7 +1639,33 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	u32 changed = 0;
 	u32 rate_flags;
 	struct ieee80211_supported_band *sband;
+	enum ieee80211_chanctx_mode chanmode;
+	struct ieee80211_local *local = sdata->local;
+	int radar_detect_width = 0;
 	int i;
+	int ret;
+
+	ret = cfg80211_chandef_dfs_required(local->hw.wiphy,
+					    &params->chandef,
+					    sdata->wdev.iftype);
+	if (ret < 0)
+		return ret;
+
+	if (ret > 0) {
+		if (!params->userspace_handles_dfs)
+			return -EINVAL;
+		radar_detect_width = BIT(params->chandef.width);
+	}
+
+	chanmode = (params->channel_fixed && !ret) ?
+		IEEE80211_CHANCTX_SHARED : IEEE80211_CHANCTX_EXCLUSIVE;
+
+	mutex_lock(&local->chanctx_mtx);
+	ret = ieee80211_check_combinations(sdata, &params->chandef, chanmode,
+					   radar_detect_width);
+	mutex_unlock(&local->chanctx_mtx);
+	if (ret < 0)
+		return ret;
 
 	if (params->bssid) {
 		memcpy(sdata->u.ibss.bssid, params->bssid, ETH_ALEN);
@@ -1648,10 +1677,11 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	sdata->u.ibss.control_port = params->control_port;
 	sdata->u.ibss.userspace_handles_dfs = params->userspace_handles_dfs;
 	sdata->u.ibss.basic_rates = params->basic_rates;
+	sdata->u.ibss.last_scan_completed = jiffies;
 
 	/* fix basic_rates if channel does not support these rates */
 	rate_flags = ieee80211_chandef_rate_flags(&params->chandef);
-	sband = sdata->local->hw.wiphy->bands[params->chandef.chan->band];
+	sband = local->hw.wiphy->bands[params->chandef.chan->band];
 	for (i = 0; i < sband->n_bitrates; i++) {
 		if ((rate_flags & sband->bitrates[i].flags) != rate_flags)
 			sdata->u.ibss.basic_rates &= ~BIT(i);
@@ -1700,9 +1730,9 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
 	ieee80211_bss_info_change_notify(sdata, changed);
 
 	sdata->smps_mode = IEEE80211_SMPS_OFF;
-	sdata->needed_rx_chains = sdata->local->rx_chains;
+	sdata->needed_rx_chains = local->rx_chains;
 
-	ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+	ieee80211_queue_work(&local->hw, &sdata->work);
 
 	return 0;
 }
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index f169b6ee94e..ac9836e0aab 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -260,7 +260,7 @@ struct ieee80211_if_ap {
 
 	/* to be used after channel switch. */
 	struct cfg80211_beacon_data *next_beacon;
-	struct list_head vlans;
+	struct list_head vlans; /* write-protected with RTNL and local->mtx */
 
 	struct ps_data ps;
 	atomic_t num_mcast_sta; /* number of stations receiving multicast */
@@ -276,7 +276,7 @@ struct ieee80211_if_wds {
 };
 
 struct ieee80211_if_vlan {
-	struct list_head list;
+	struct list_head list; /* write-protected with RTNL and local->mtx */
 
 	/* used for all tx if the VLAN is configured to 4-addr mode */
 	struct sta_info __rcu *sta;
@@ -692,8 +692,10 @@ struct ieee80211_chanctx {
 	struct list_head list;
 	struct rcu_head rcu_head;
 
+	struct list_head assigned_vifs;
+	struct list_head reserved_vifs;
+
 	enum ieee80211_chanctx_mode mode;
-	int refcount;
 	bool driver_present;
 
 	struct ieee80211_chanctx_conf conf;
@@ -752,11 +754,21 @@ struct ieee80211_sub_if_data {
 	struct mac80211_qos_map __rcu *qos_map;
 
 	struct work_struct csa_finalize_work;
-	int csa_counter_offset_beacon;
-	int csa_counter_offset_presp;
+	u16 csa_counter_offset_beacon[IEEE80211_MAX_CSA_COUNTERS_NUM];
+	u16 csa_counter_offset_presp[IEEE80211_MAX_CSA_COUNTERS_NUM];
 	bool csa_radar_required;
+	bool csa_block_tx; /* write-protected by sdata_lock and local->mtx */
 	struct cfg80211_chan_def csa_chandef;
 
+	struct list_head assigned_chanctx_list; /* protected by chanctx_mtx */
+	struct list_head reserved_chanctx_list; /* protected by chanctx_mtx */
+
+	/* context reservation -- protected with chanctx_mtx */
+	struct ieee80211_chanctx *reserved_chanctx;
+	struct cfg80211_chan_def reserved_chandef;
+	bool reserved_radar_required;
+	u8 csa_current_counter;
+
 	/* used to reconfigure hardware SM PS */
 	struct work_struct recalc_smps;
 
@@ -1449,6 +1461,7 @@ __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
 int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
 				       struct cfg80211_sched_scan_request *req);
 int ieee80211_request_sched_scan_stop(struct ieee80211_sub_if_data *sdata);
+void ieee80211_sched_scan_end(struct ieee80211_local *local);
 void ieee80211_sched_scan_stopped_work(struct work_struct *work);
 
 /* off-channel helpers */
@@ -1463,6 +1476,7 @@ void ieee80211_sw_roc_work(struct work_struct *work);
 void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc);
 
 /* channel switch handling */
+bool ieee80211_csa_needs_block_tx(struct ieee80211_local *local);
 void ieee80211_csa_finalize_work(struct work_struct *work);
 int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 			     struct cfg80211_csa_settings *params);
@@ -1772,6 +1786,16 @@ ieee80211_vif_use_channel(struct ieee80211_sub_if_data *sdata,
 			  const struct cfg80211_chan_def *chandef,
 			  enum ieee80211_chanctx_mode mode);
 int __must_check
+ieee80211_vif_reserve_chanctx(struct ieee80211_sub_if_data *sdata,
+			      const struct cfg80211_chan_def *chandef,
+			      enum ieee80211_chanctx_mode mode,
+			      bool radar_required);
+int __must_check
+ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata,
+				   u32 *changed);
+int ieee80211_vif_unreserve_chanctx(struct ieee80211_sub_if_data *sdata);
+
+int __must_check
 ieee80211_vif_change_bandwidth(struct ieee80211_sub_if_data *sdata,
 			       const struct cfg80211_chan_def *chandef,
 			       u32 *changed);
@@ -1783,6 +1807,8 @@ void ieee80211_vif_release_channel(struct ieee80211_sub_if_data *sdata);
 void ieee80211_vif_vlan_copy_chanctx(struct ieee80211_sub_if_data *sdata);
 void ieee80211_vif_copy_chanctx_to_vlans(struct ieee80211_sub_if_data *sdata,
 					 bool clear);
+int ieee80211_chanctx_refcount(struct ieee80211_local *local,
+			       struct ieee80211_chanctx *ctx);
 
 void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
 				   struct ieee80211_chanctx *chanctx);
@@ -1806,6 +1832,20 @@ int ieee80211_cs_headroom(struct ieee80211_local *local,
 			  enum nl80211_iftype iftype);
 void ieee80211_recalc_dtim(struct ieee80211_local *local,
 			   struct ieee80211_sub_if_data *sdata);
+int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
+				 const struct cfg80211_chan_def *chandef,
+				 enum ieee80211_chanctx_mode chanmode,
+				 u8 radar_detect);
+int ieee80211_max_num_channels(struct ieee80211_local *local);
+
+/* TDLS */
+int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
+			const u8 *peer, u8 action_code, u8 dialog_token,
+			u16 status_code, u32 peer_capability,
+			const u8 *extra_ies, size_t extra_ies_len);
+int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
+			const u8 *peer, enum nl80211_tdls_operation oper);
+
 
 #ifdef CONFIG_MAC80211_NOINLINE
 #define debug_noinline noinline
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index b8d331e7d88..388b863e821 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -250,6 +250,7 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_sub_if_data *nsdata;
+	int ret;
 
 	ASSERT_RTNL();
 
@@ -300,7 +301,10 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
-	return 0;
+	mutex_lock(&local->chanctx_mtx);
+	ret = ieee80211_check_combinations(sdata, NULL, 0, 0);
+	mutex_unlock(&local->chanctx_mtx);
+	return ret;
 }
 
 static int ieee80211_check_queues(struct ieee80211_sub_if_data *sdata,
@@ -395,6 +399,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
 	sdata->vif.type = NL80211_IFTYPE_MONITOR;
 	snprintf(sdata->name, IFNAMSIZ, "%s-monitor",
 		 wiphy_name(local->hw.wiphy));
+	sdata->wdev.iftype = NL80211_IFTYPE_MONITOR;
 
 	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
 
@@ -423,7 +428,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
 	mutex_unlock(&local->mtx);
 	if (ret) {
 		mutex_lock(&local->iflist_mtx);
-		rcu_assign_pointer(local->monitor_sdata, NULL);
+		RCU_INIT_POINTER(local->monitor_sdata, NULL);
 		mutex_unlock(&local->iflist_mtx);
 		synchronize_net();
 		drv_remove_interface(local, sdata);
@@ -452,7 +457,7 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local)
 		return;
 	}
 
-	rcu_assign_pointer(local->monitor_sdata, NULL);
+	RCU_INIT_POINTER(local->monitor_sdata, NULL);
 	mutex_unlock(&local->iflist_mtx);
 
 	synchronize_net();
@@ -492,7 +497,9 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		if (!sdata->bss)
 			return -ENOLINK;
 
+		mutex_lock(&local->mtx);
 		list_add(&sdata->u.vlan.list, &sdata->bss->vlans);
+		mutex_unlock(&local->mtx);
 
 		master = container_of(sdata->bss,
 				      struct ieee80211_sub_if_data, u.ap);
@@ -722,8 +729,11 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		drv_stop(local);
  err_del_bss:
 	sdata->bss = NULL;
-	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+		mutex_lock(&local->mtx);
 		list_del(&sdata->u.vlan.list);
+		mutex_unlock(&local->mtx);
+	}
 	/* might already be clear but that doesn't matter */
 	clear_bit(SDATA_STATE_RUNNING, &sdata->state);
 	return res;
@@ -829,8 +839,15 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 
 	cancel_work_sync(&sdata->recalc_smps);
 	sdata_lock(sdata);
+	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
 	sdata_unlock(sdata);
+
 	cancel_work_sync(&sdata->csa_finalize_work);
 
 	cancel_delayed_work_sync(&sdata->dfs_cac_timer_work);
@@ -875,8 +892,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP_VLAN:
+		mutex_lock(&local->mtx);
 		list_del(&sdata->u.vlan.list);
-		rcu_assign_pointer(sdata->vif.chanctx_conf, NULL);
+		mutex_unlock(&local->mtx);
+		RCU_INIT_POINTER(sdata->vif.chanctx_conf, NULL);
 		/* no need to tell driver */
 		break;
 	case NL80211_IFTYPE_MONITOR:
@@ -895,7 +914,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 		break;
 	case NL80211_IFTYPE_P2P_DEVICE:
 		/* relies on synchronize_rcu() below */
-		rcu_assign_pointer(local->p2p_sdata, NULL);
+		RCU_INIT_POINTER(local->p2p_sdata, NULL);
 		/* fall through */
 	default:
 		cancel_work_sync(&sdata->work);
@@ -1267,6 +1286,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	sdata->control_port_protocol = cpu_to_be16(ETH_P_PAE);
 	sdata->control_port_no_encrypt = false;
 	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
+	sdata->vif.bss_conf.idle = true;
 
 	sdata->noack_map = 0;
 
@@ -1280,6 +1300,8 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	INIT_WORK(&sdata->work, ieee80211_iface_work);
 	INIT_WORK(&sdata->recalc_smps, ieee80211_recalc_smps_work);
 	INIT_WORK(&sdata->csa_finalize_work, ieee80211_csa_finalize_work);
+	INIT_LIST_HEAD(&sdata->assigned_chanctx_list);
+	INIT_LIST_HEAD(&sdata->reserved_chanctx_list);
 
 	switch (type) {
 	case NL80211_IFTYPE_P2P_GO:
@@ -1758,7 +1780,6 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local)
 	}
 	mutex_unlock(&local->iflist_mtx);
 	unregister_netdevice_many(&unreg_list);
-	list_del(&unreg_list);
 
 	list_for_each_entry_safe(sdata, tmp, &wdev_list, list) {
 		list_del(&sdata->list);
@@ -1774,20 +1795,19 @@ static int netdev_notify(struct notifier_block *nb,
 	struct ieee80211_sub_if_data *sdata;
 
 	if (state != NETDEV_CHANGENAME)
-		return 0;
+		return NOTIFY_DONE;
 
 	if (!dev->ieee80211_ptr || !dev->ieee80211_ptr->wiphy)
-		return 0;
+		return NOTIFY_DONE;
 
 	if (dev->ieee80211_ptr->wiphy->privid != mac80211_wiphy_privid)
-		return 0;
+		return NOTIFY_DONE;
 
 	sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-
 	memcpy(sdata->name, dev->name, IFNAMSIZ);
-
 	ieee80211_debugfs_rename_netdev(sdata);
-	return 0;
+
+	return NOTIFY_OK;
 }
 
 static struct notifier_block mac80211_netdev_notifier = {
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 6ff65a1ebaa..16d97f044a2 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -325,7 +325,8 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len,
 	struct ieee80211_key *key;
 	int i, j, err;
 
-	BUG_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS);
+	if (WARN_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS))
+		return ERR_PTR(-EINVAL);
 
 	key = kzalloc(sizeof(struct ieee80211_key) + key_len, GFP_KERNEL);
 	if (!key)
@@ -481,8 +482,8 @@ int ieee80211_key_link(struct ieee80211_key *key,
 	int idx, ret;
 	bool pairwise;
 
-	BUG_ON(!sdata);
-	BUG_ON(!key);
+	if (WARN_ON(!sdata || !key))
+		return -EINVAL;
 
 	pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE;
 	idx = key->conf.keyidx;
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 4c1bf61bc77..d17c26d6e36 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -340,7 +340,7 @@ static int ieee80211_ifa_changed(struct notifier_block *nb,
 
 	sdata_unlock(sdata);
 
-	return NOTIFY_DONE;
+	return NOTIFY_OK;
 }
 #endif
 
@@ -371,7 +371,7 @@ static int ieee80211_ifa6_changed(struct notifier_block *nb,
 
 	drv_ipv6_addr_change(local, sdata, idev);
 
-	return NOTIFY_DONE;
+	return NOTIFY_OK;
 }
 #endif
 
@@ -446,7 +446,9 @@ static const struct ieee80211_ht_cap mac80211_ht_capa_mod_mask = {
 	.cap_info = cpu_to_le16(IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
 				IEEE80211_HT_CAP_MAX_AMSDU |
 				IEEE80211_HT_CAP_SGI_20 |
-				IEEE80211_HT_CAP_SGI_40),
+				IEEE80211_HT_CAP_SGI_40 |
+				IEEE80211_HT_CAP_LDPC_CODING |
+				IEEE80211_HT_CAP_40MHZ_INTOLERANT),
 	.mcs = {
 		.rx_mask = { 0xff, 0xff, 0xff, 0xff, 0xff,
 			     0xff, 0xff, 0xff, 0xff, 0xff, },
@@ -954,6 +956,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	if (local->hw.wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)
 		local->hw.wiphy->flags |= WIPHY_FLAG_TDLS_EXTERNAL_SETUP;
 
+	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM;
+
 	result = wiphy_register(local->hw.wiphy);
 	if (result < 0)
 		goto fail_wiphy_register;
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index f70e9cd1055..6495a3f0428 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -366,20 +366,15 @@ int mesh_add_rsn_ie(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb)
 		return 0;
 
 	/* find RSN IE */
-	data = ifmsh->ie;
-	while (data < ifmsh->ie + ifmsh->ie_len) {
-		if (*data == WLAN_EID_RSN) {
-			len = data[1] + 2;
-			break;
-		}
-		data++;
-	}
+	data = cfg80211_find_ie(WLAN_EID_RSN, ifmsh->ie, ifmsh->ie_len);
+	if (!data)
+		return 0;
 
-	if (len) {
-		if (skb_tailroom(skb) < len)
-			return -ENOMEM;
-		memcpy(skb_put(skb, len), data, len);
-	}
+	len = data[1] + 2;
+
+	if (skb_tailroom(skb) < len)
+		return -ENOMEM;
+	memcpy(skb_put(skb, len), data, len);
 
 	return 0;
 }
@@ -684,7 +679,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 		*pos++ = 0x0;
 		*pos++ = ieee80211_frequency_to_channel(
 				csa->settings.chandef.chan->center_freq);
-		sdata->csa_counter_offset_beacon = hdr_len + 6;
+		sdata->csa_counter_offset_beacon[0] = hdr_len + 6;
 		*pos++ = csa->settings.count;
 		*pos++ = WLAN_EID_CHAN_SWITCH_PARAM;
 		*pos++ = 6;
@@ -829,7 +824,7 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata)
 	ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED);
 	bcn = rcu_dereference_protected(ifmsh->beacon,
 					lockdep_is_held(&sdata->wdev.mtx));
-	rcu_assign_pointer(ifmsh->beacon, NULL);
+	RCU_INIT_POINTER(ifmsh->beacon, NULL);
 	kfree_rcu(bcn, rcu_head);
 
 	/* flush STAs and mpaths on this iface */
@@ -903,14 +898,15 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata,
 	}
 
 	err = cfg80211_chandef_dfs_required(sdata->local->hw.wiphy,
-					    &params.chandef);
+					    &params.chandef,
+					    NL80211_IFTYPE_MESH_POINT);
 	if (err < 0)
 		return false;
-	if (err) {
-		params.radar_required = true;
+	if (err > 0)
 		/* TODO: DFS not (yet) supported */
 		return false;
-	}
+
+	params.radar_required = err;
 
 	if (cfg80211_chandef_identical(&params.chandef,
 				       &sdata->vif.bss_conf.chandef)) {
@@ -1068,7 +1064,7 @@ int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata)
 
 	/* Remove the CSA and MCSP elements from the beacon */
 	tmp_csa_settings = rcu_dereference(ifmsh->csa);
-	rcu_assign_pointer(ifmsh->csa, NULL);
+	RCU_INIT_POINTER(ifmsh->csa, NULL);
 	if (tmp_csa_settings)
 		kfree_rcu(tmp_csa_settings, rcu_head);
 	ret = ieee80211_mesh_rebuild_beacon(sdata);
@@ -1102,7 +1098,7 @@ int ieee80211_mesh_csa_beacon(struct ieee80211_sub_if_data *sdata,
 	ret = ieee80211_mesh_rebuild_beacon(sdata);
 	if (ret) {
 		tmp_csa_settings = rcu_dereference(ifmsh->csa);
-		rcu_assign_pointer(ifmsh->csa, NULL);
+		RCU_INIT_POINTER(ifmsh->csa, NULL);
 		kfree_rcu(tmp_csa_settings, rcu_head);
 		return ret;
 	}
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index f9514685d45..94758b9c9ed 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -37,7 +37,7 @@ static inline u32 u32_field_get(const u8 *preq_elem, int offset, bool ae)
 	return get_unaligned_le32(preq_elem + offset);
 }
 
-static inline u32 u16_field_get(const u8 *preq_elem, int offset, bool ae)
+static inline u16 u16_field_get(const u8 *preq_elem, int offset, bool ae)
 {
 	if (ae)
 		offset += 6;
@@ -544,9 +544,10 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
 		if (time_after(jiffies, ifmsh->last_sn_update +
 					net_traversal_jiffies(sdata)) ||
 		    time_before(jiffies, ifmsh->last_sn_update)) {
-			target_sn = ++ifmsh->sn;
+			++ifmsh->sn;
 			ifmsh->last_sn_update = jiffies;
 		}
+		target_sn = ifmsh->sn;
 	} else if (is_broadcast_ether_addr(target_addr) &&
 		   (target_flags & IEEE80211_PREQ_TO_FLAG)) {
 		rcu_read_lock();
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 7d050ed6fe5..cf032a8db9d 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -287,8 +287,10 @@ static void mesh_path_move_to_queue(struct mesh_path *gate_mpath,
 	struct sk_buff_head failq;
 	unsigned long flags;
 
-	BUG_ON(gate_mpath == from_mpath);
-	BUG_ON(!gate_mpath->next_hop);
+	if (WARN_ON(gate_mpath == from_mpath))
+		return;
+	if (WARN_ON(!gate_mpath->next_hop))
+		return;
 
 	__skb_queue_head_init(&failq);
 
diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c
index 2bc5dc25d5a..09625d6205c 100644
--- a/net/mac80211/mesh_sync.c
+++ b/net/mac80211/mesh_sync.c
@@ -171,7 +171,7 @@ static void mesh_sync_offset_adjust_tbtt(struct ieee80211_sub_if_data *sdata,
 	u8 cap;
 
 	WARN_ON(ifmsh->mesh_sp_id != IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET);
-	BUG_ON(!rcu_read_lock_held());
+	WARN_ON(!rcu_read_lock_held());
 	cap = beacon->meshconf->meshconf_cap;
 
 	spin_lock_bh(&ifmsh->sync_offset_lock);
diff --git a/net/mac80211/michael.h b/net/mac80211/michael.h
index 3b848dad958..0e4886f881f 100644
--- a/net/mac80211/michael.h
+++ b/net/mac80211/michael.h
@@ -11,6 +11,7 @@
 #define MICHAEL_H
 
 #include <linux/types.h>
+#include <linux/ieee80211.h>
 
 #define MICHAEL_MIC_LEN 8
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 27600a9808b..3345401be1b 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -975,16 +975,23 @@ static void ieee80211_chswitch_work(struct work_struct *work)
 	/* XXX: shouldn't really modify cfg80211-owned data! */
 	ifmgd->associated->channel = sdata->csa_chandef.chan;
 
+	ieee80211_bss_info_change_notify(sdata, changed);
+
+	mutex_lock(&local->mtx);
+	sdata->vif.csa_active = false;
 	/* XXX: wait for a beacon first? */
-	ieee80211_wake_queues_by_reason(&local->hw,
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
 					IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
 
-	ieee80211_bss_info_change_notify(sdata, changed);
-
- out:
-	sdata->vif.csa_active = false;
 	ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED;
+
+	ieee80211_sta_reset_beacon_monitor(sdata);
+	ieee80211_sta_reset_conn_monitor(sdata);
+
+out:
 	sdata_unlock(sdata);
 }
 
@@ -1089,7 +1096,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	}
 	chanctx = container_of(rcu_access_pointer(sdata->vif.chanctx_conf),
 			       struct ieee80211_chanctx, conf);
-	if (chanctx->refcount > 1) {
+	if (ieee80211_chanctx_refcount(local, chanctx) > 1) {
 		sdata_info(sdata,
 			   "channel switch with multiple interfaces on the same channel, disconnecting\n");
 		ieee80211_queue_work(&local->hw,
@@ -1100,12 +1107,16 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	mutex_unlock(&local->chanctx_mtx);
 
 	sdata->csa_chandef = csa_ie.chandef;
+
+	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = true;
+	sdata->csa_block_tx = csa_ie.mode;
 
-	if (csa_ie.mode)
+	if (sdata->csa_block_tx)
 		ieee80211_stop_queues_by_reason(&local->hw,
-				IEEE80211_MAX_QUEUE_MAP,
-				IEEE80211_QUEUE_STOP_REASON_CSA);
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
 
 	if (local->ops->channel_switch) {
 		/* use driver's channel switch callback */
@@ -1817,6 +1828,12 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	ifmgd->flags = 0;
 	mutex_lock(&local->mtx);
 	ieee80211_vif_release_channel(sdata);
+
+	sdata->vif.csa_active = false;
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_CSA);
 	mutex_unlock(&local->mtx);
 
 	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
@@ -2045,6 +2062,7 @@ EXPORT_SYMBOL(ieee80211_ap_probereq_get);
 
 static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 {
+	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
 
@@ -2058,10 +2076,14 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 			       WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
 			       true, frame_buf);
 	ifmgd->flags &= ~IEEE80211_STA_CSA_RECEIVED;
+
+	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
-	ieee80211_wake_queues_by_reason(&sdata->local->hw,
+	if (!ieee80211_csa_needs_block_tx(local))
+		ieee80211_wake_queues_by_reason(&local->hw,
 					IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_CSA);
+	mutex_unlock(&local->mtx);
 
 	cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
 			      IEEE80211_DEAUTH_FRAME_LEN);
@@ -3546,6 +3568,9 @@ static void ieee80211_sta_bcn_mon_timer(unsigned long data)
 	if (local->quiescing)
 		return;
 
+	if (sdata->vif.csa_active)
+		return;
+
 	sdata->u.mgd.connection_loss = false;
 	ieee80211_queue_work(&sdata->local->hw,
 			     &sdata->u.mgd.beacon_connection_loss_work);
@@ -3561,6 +3586,9 @@ static void ieee80211_sta_conn_mon_timer(unsigned long data)
 	if (local->quiescing)
 		return;
 
+	if (sdata->vif.csa_active)
+		return;
+
 	ieee80211_queue_work(&local->hw, &ifmgd->monitor_work);
 }
 
@@ -3707,7 +3735,7 @@ int ieee80211_max_network_latency(struct notifier_block *nb,
 	ieee80211_recalc_ps(local, latency_usec);
 	mutex_unlock(&local->iflist_mtx);
 
-	return 0;
+	return NOTIFY_OK;
 }
 
 static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 26fd94fa0ae..1c1469c36dc 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -657,6 +657,17 @@ minstrel_free(void *priv)
 	kfree(priv);
 }
 
+static u32 minstrel_get_expected_throughput(void *priv_sta)
+{
+	struct minstrel_sta_info *mi = priv_sta;
+	int idx = mi->max_tp_rate[0];
+
+	/* convert pkt per sec in kbps (1200 is the average pkt size used for
+	 * computing cur_tp
+	 */
+	return MINSTREL_TRUNC(mi->r[idx].cur_tp) * 1200 * 8 / 1024;
+}
+
 const struct rate_control_ops mac80211_minstrel = {
 	.name = "minstrel",
 	.tx_status = minstrel_tx_status,
@@ -670,6 +681,7 @@ const struct rate_control_ops mac80211_minstrel = {
 	.add_sta_debugfs = minstrel_add_sta_debugfs,
 	.remove_sta_debugfs = minstrel_remove_sta_debugfs,
 #endif
+	.get_expected_throughput = minstrel_get_expected_throughput,
 };
 
 int __init
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index bccaf854a30..85c1e74b771 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -22,7 +22,7 @@
 #define MCS_NBITS (AVG_PKT_SIZE << 3)
 
 /* Number of symbols for a packet with (bps) bits per symbol */
-#define MCS_NSYMS(bps) ((MCS_NBITS + (bps) - 1) / (bps))
+#define MCS_NSYMS(bps) DIV_ROUND_UP(MCS_NBITS, (bps))
 
 /* Transmission time (nanoseconds) for a packet containing (syms) symbols */
 #define MCS_SYMBOL_TIME(sgi, syms)					\
@@ -226,8 +226,9 @@ minstrel_ht_calc_tp(struct minstrel_ht_sta *mi, int group, int rate)
 		nsecs = 1000 * mi->overhead / MINSTREL_TRUNC(mi->avg_ampdu_len);
 
 	nsecs += minstrel_mcs_groups[group].duration[rate];
-	tp = 1000000 * ((prob * 1000) / nsecs);
 
+	/* prob is scaled - see MINSTREL_FRAC above */
+	tp = 1000000 * ((prob * 1000) / nsecs);
 	mr->cur_tp = MINSTREL_TRUNC(tp);
 }
 
@@ -1031,6 +1032,22 @@ minstrel_ht_free(void *priv)
 	mac80211_minstrel.free(priv);
 }
 
+static u32 minstrel_ht_get_expected_throughput(void *priv_sta)
+{
+	struct minstrel_ht_sta_priv *msp = priv_sta;
+	struct minstrel_ht_sta *mi = &msp->ht;
+	int i, j;
+
+	if (!msp->is_ht)
+		return mac80211_minstrel.get_expected_throughput(priv_sta);
+
+	i = mi->max_tp_rate / MCS_GROUP_RATES;
+	j = mi->max_tp_rate % MCS_GROUP_RATES;
+
+	/* convert cur_tp from pkt per second in kbps */
+	return mi->groups[i].rates[j].cur_tp * AVG_PKT_SIZE * 8 / 1024;
+}
+
 static const struct rate_control_ops mac80211_minstrel_ht = {
 	.name = "minstrel_ht",
 	.tx_status = minstrel_ht_tx_status,
@@ -1045,6 +1062,7 @@ static const struct rate_control_ops mac80211_minstrel_ht = {
 	.add_sta_debugfs = minstrel_ht_add_sta_debugfs,
 	.remove_sta_debugfs = minstrel_ht_remove_sta_debugfs,
 #endif
+	.get_expected_throughput = minstrel_ht_get_expected_throughput,
 };
 
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 2b608b2b70e..394e201cde6 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -54,24 +54,25 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local,
 	return skb;
 }
 
-static inline int should_drop_frame(struct sk_buff *skb, int present_fcs_len)
+static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len)
 {
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
-	struct ieee80211_hdr *hdr;
-
-	hdr = (void *)(skb->data);
+	struct ieee80211_hdr *hdr = (void *)skb->data;
 
 	if (status->flag & (RX_FLAG_FAILED_FCS_CRC |
 			    RX_FLAG_FAILED_PLCP_CRC |
 			    RX_FLAG_AMPDU_IS_ZEROLEN))
-		return 1;
+		return true;
+
 	if (unlikely(skb->len < 16 + present_fcs_len))
-		return 1;
+		return true;
+
 	if (ieee80211_is_ctl(hdr->frame_control) &&
 	    !ieee80211_is_pspoll(hdr->frame_control) &&
 	    !ieee80211_is_back_req(hdr->frame_control))
-		return 1;
-	return 0;
+		return true;
+
+	return false;
 }
 
 static int
@@ -3191,7 +3192,7 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx,
 }
 
 /*
- * This is the actual Rx frames handler. as it blongs to Rx path it must
+ * This is the actual Rx frames handler. as it belongs to Rx path it must
  * be called with rcu_read_lock protection.
  */
 static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 3ce7f2c8539..f40661eb75b 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -309,7 +309,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 	if (local->scan_req != local->int_scan_req)
 		cfg80211_scan_done(local->scan_req, aborted);
 	local->scan_req = NULL;
-	rcu_assign_pointer(local->scan_sdata, NULL);
+	RCU_INIT_POINTER(local->scan_sdata, NULL);
 
 	local->scanning = 0;
 	local->scan_chandef.chan = NULL;
@@ -559,7 +559,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 		ieee80211_recalc_idle(local);
 
 		local->scan_req = NULL;
-		rcu_assign_pointer(local->scan_sdata, NULL);
+		RCU_INIT_POINTER(local->scan_sdata, NULL);
 	}
 
 	return rc;
@@ -773,7 +773,7 @@ void ieee80211_scan_work(struct work_struct *work)
 		int rc;
 
 		local->scan_req = NULL;
-		rcu_assign_pointer(local->scan_sdata, NULL);
+		RCU_INIT_POINTER(local->scan_sdata, NULL);
 
 		rc = __ieee80211_start_scan(sdata, req);
 		if (rc) {
@@ -1014,7 +1014,7 @@ out_free:
 
 	if (ret) {
 		/* Clean in case of failure after HW restart or upon resume. */
-		rcu_assign_pointer(local->sched_scan_sdata, NULL);
+		RCU_INIT_POINTER(local->sched_scan_sdata, NULL);
 		local->sched_scan_req = NULL;
 	}
 
@@ -1076,12 +1076,8 @@ void ieee80211_sched_scan_results(struct ieee80211_hw *hw)
 }
 EXPORT_SYMBOL(ieee80211_sched_scan_results);
 
-void ieee80211_sched_scan_stopped_work(struct work_struct *work)
+void ieee80211_sched_scan_end(struct ieee80211_local *local)
 {
-	struct ieee80211_local *local =
-		container_of(work, struct ieee80211_local,
-			     sched_scan_stopped_work);
-
 	mutex_lock(&local->mtx);
 
 	if (!rcu_access_pointer(local->sched_scan_sdata)) {
@@ -1089,7 +1085,7 @@ void ieee80211_sched_scan_stopped_work(struct work_struct *work)
 		return;
 	}
 
-	rcu_assign_pointer(local->sched_scan_sdata, NULL);
+	RCU_INIT_POINTER(local->sched_scan_sdata, NULL);
 
 	/* If sched scan was aborted by the driver. */
 	local->sched_scan_req = NULL;
@@ -1099,6 +1095,15 @@ void ieee80211_sched_scan_stopped_work(struct work_struct *work)
 	cfg80211_sched_scan_stopped(local->hw.wiphy);
 }
 
+void ieee80211_sched_scan_stopped_work(struct work_struct *work)
+{
+	struct ieee80211_local *local =
+		container_of(work, struct ieee80211_local,
+			     sched_scan_stopped_work);
+
+	ieee80211_sched_scan_end(local);
+}
+
 void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 847d92f6bef..a9b46d8ea22 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -240,6 +240,7 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 
 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
 
+	kfree(rcu_dereference_raw(sta->sta.rates));
 	kfree(sta);
 }
 
@@ -552,7 +553,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
 int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU)
 {
 	struct ieee80211_local *local = sta->local;
-	int err = 0;
+	int err;
 
 	might_sleep();
 
@@ -570,7 +571,6 @@ int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU)
 
 	return 0;
  out_free:
-	BUG_ON(!err);
 	sta_info_free(local, sta);
 	return err;
 }
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 60cb7a66597..ba29ebc8614 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -541,6 +541,23 @@ static void ieee80211_tx_latency_end_msrmnt(struct ieee80211_local *local,
  */
 #define STA_LOST_PKT_THRESHOLD	50
 
+static void ieee80211_lost_packet(struct sta_info *sta, struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+	/* This packet was aggregated but doesn't carry status info */
+	if ((info->flags & IEEE80211_TX_CTL_AMPDU) &&
+	    !(info->flags & IEEE80211_TX_STAT_AMPDU))
+		return;
+
+	if (++sta->lost_packets < STA_LOST_PKT_THRESHOLD)
+		return;
+
+	cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr,
+				    sta->lost_packets, GFP_ATOMIC);
+	sta->lost_packets = 0;
+}
+
 void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 {
 	struct sk_buff *skb2;
@@ -680,12 +697,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 			if (info->flags & IEEE80211_TX_STAT_ACK) {
 				if (sta->lost_packets)
 					sta->lost_packets = 0;
-			} else if (++sta->lost_packets >= STA_LOST_PKT_THRESHOLD) {
-				cfg80211_cqm_pktloss_notify(sta->sdata->dev,
-							    sta->sta.addr,
-							    sta->lost_packets,
-							    GFP_ATOMIC);
-				sta->lost_packets = 0;
+			} else {
+				ieee80211_lost_packet(sta, skb);
 			}
 		}
 
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
new file mode 100644
index 00000000000..652813b2d3d
--- /dev/null
+++ b/net/mac80211/tdls.c
@@ -0,0 +1,325 @@
+/*
+ * mac80211 TDLS handling code
+ *
+ * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright 2014, Intel Corporation
+ *
+ * This file is GPLv2 as found in COPYING.
+ */
+
+#include <linux/ieee80211.h>
+#include "ieee80211_i.h"
+
+static void ieee80211_tdls_add_ext_capab(struct sk_buff *skb)
+{
+	u8 *pos = (void *)skb_put(skb, 7);
+
+	*pos++ = WLAN_EID_EXT_CAPABILITY;
+	*pos++ = 5; /* len */
+	*pos++ = 0x0;
+	*pos++ = 0x0;
+	*pos++ = 0x0;
+	*pos++ = 0x0;
+	*pos++ = WLAN_EXT_CAPA5_TDLS_ENABLED;
+}
+
+static u16 ieee80211_get_tdls_sta_capab(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	u16 capab;
+
+	capab = 0;
+	if (ieee80211_get_sdata_band(sdata) != IEEE80211_BAND_2GHZ)
+		return capab;
+
+	if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_SLOT_INCAPABLE))
+		capab |= WLAN_CAPABILITY_SHORT_SLOT_TIME;
+	if (!(local->hw.flags & IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE))
+		capab |= WLAN_CAPABILITY_SHORT_PREAMBLE;
+
+	return capab;
+}
+
+static void ieee80211_tdls_add_link_ie(struct sk_buff *skb, const u8 *src_addr,
+				       const u8 *peer, const u8 *bssid)
+{
+	struct ieee80211_tdls_lnkie *lnkid;
+
+	lnkid = (void *)skb_put(skb, sizeof(struct ieee80211_tdls_lnkie));
+
+	lnkid->ie_type = WLAN_EID_LINK_ID;
+	lnkid->ie_len = sizeof(struct ieee80211_tdls_lnkie) - 2;
+
+	memcpy(lnkid->bssid, bssid, ETH_ALEN);
+	memcpy(lnkid->init_sta, src_addr, ETH_ALEN);
+	memcpy(lnkid->resp_sta, peer, ETH_ALEN);
+}
+
+static int
+ieee80211_prep_tdls_encap_data(struct wiphy *wiphy, struct net_device *dev,
+			       const u8 *peer, u8 action_code, u8 dialog_token,
+			       u16 status_code, struct sk_buff *skb)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
+	struct ieee80211_tdls_data *tf;
+
+	tf = (void *)skb_put(skb, offsetof(struct ieee80211_tdls_data, u));
+
+	memcpy(tf->da, peer, ETH_ALEN);
+	memcpy(tf->sa, sdata->vif.addr, ETH_ALEN);
+	tf->ether_type = cpu_to_be16(ETH_P_TDLS);
+	tf->payload_type = WLAN_TDLS_SNAP_RFTYPE;
+
+	switch (action_code) {
+	case WLAN_TDLS_SETUP_REQUEST:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_SETUP_REQUEST;
+
+		skb_put(skb, sizeof(tf->u.setup_req));
+		tf->u.setup_req.dialog_token = dialog_token;
+		tf->u.setup_req.capability =
+			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
+
+		ieee80211_add_srates_ie(sdata, skb, false, band);
+		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
+		ieee80211_tdls_add_ext_capab(skb);
+		break;
+	case WLAN_TDLS_SETUP_RESPONSE:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_SETUP_RESPONSE;
+
+		skb_put(skb, sizeof(tf->u.setup_resp));
+		tf->u.setup_resp.status_code = cpu_to_le16(status_code);
+		tf->u.setup_resp.dialog_token = dialog_token;
+		tf->u.setup_resp.capability =
+			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
+
+		ieee80211_add_srates_ie(sdata, skb, false, band);
+		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
+		ieee80211_tdls_add_ext_capab(skb);
+		break;
+	case WLAN_TDLS_SETUP_CONFIRM:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_SETUP_CONFIRM;
+
+		skb_put(skb, sizeof(tf->u.setup_cfm));
+		tf->u.setup_cfm.status_code = cpu_to_le16(status_code);
+		tf->u.setup_cfm.dialog_token = dialog_token;
+		break;
+	case WLAN_TDLS_TEARDOWN:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_TEARDOWN;
+
+		skb_put(skb, sizeof(tf->u.teardown));
+		tf->u.teardown.reason_code = cpu_to_le16(status_code);
+		break;
+	case WLAN_TDLS_DISCOVERY_REQUEST:
+		tf->category = WLAN_CATEGORY_TDLS;
+		tf->action_code = WLAN_TDLS_DISCOVERY_REQUEST;
+
+		skb_put(skb, sizeof(tf->u.discover_req));
+		tf->u.discover_req.dialog_token = dialog_token;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+ieee80211_prep_tdls_direct(struct wiphy *wiphy, struct net_device *dev,
+			   const u8 *peer, u8 action_code, u8 dialog_token,
+			   u16 status_code, struct sk_buff *skb)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	enum ieee80211_band band = ieee80211_get_sdata_band(sdata);
+	struct ieee80211_mgmt *mgmt;
+
+	mgmt = (void *)skb_put(skb, 24);
+	memset(mgmt, 0, 24);
+	memcpy(mgmt->da, peer, ETH_ALEN);
+	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
+	memcpy(mgmt->bssid, sdata->u.mgd.bssid, ETH_ALEN);
+
+	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
+					  IEEE80211_STYPE_ACTION);
+
+	switch (action_code) {
+	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
+		skb_put(skb, 1 + sizeof(mgmt->u.action.u.tdls_discover_resp));
+		mgmt->u.action.category = WLAN_CATEGORY_PUBLIC;
+		mgmt->u.action.u.tdls_discover_resp.action_code =
+			WLAN_PUB_ACTION_TDLS_DISCOVER_RES;
+		mgmt->u.action.u.tdls_discover_resp.dialog_token =
+			dialog_token;
+		mgmt->u.action.u.tdls_discover_resp.capability =
+			cpu_to_le16(ieee80211_get_tdls_sta_capab(sdata));
+
+		ieee80211_add_srates_ie(sdata, skb, false, band);
+		ieee80211_add_ext_srates_ie(sdata, skb, false, band);
+		ieee80211_tdls_add_ext_capab(skb);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int ieee80211_tdls_mgmt(struct wiphy *wiphy, struct net_device *dev,
+			const u8 *peer, u8 action_code, u8 dialog_token,
+			u16 status_code, u32 peer_capability,
+			const u8 *extra_ies, size_t extra_ies_len)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ieee80211_local *local = sdata->local;
+	struct sk_buff *skb = NULL;
+	bool send_direct;
+	int ret;
+
+	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
+		return -ENOTSUPP;
+
+	/* make sure we are in managed mode, and associated */
+	if (sdata->vif.type != NL80211_IFTYPE_STATION ||
+	    !sdata->u.mgd.associated)
+		return -EINVAL;
+
+	tdls_dbg(sdata, "TDLS mgmt action %d peer %pM\n",
+		 action_code, peer);
+
+	skb = dev_alloc_skb(local->hw.extra_tx_headroom +
+			    max(sizeof(struct ieee80211_mgmt),
+				sizeof(struct ieee80211_tdls_data)) +
+			    50 + /* supported rates */
+			    7 + /* ext capab */
+			    extra_ies_len +
+			    sizeof(struct ieee80211_tdls_lnkie));
+	if (!skb)
+		return -ENOMEM;
+
+	skb_reserve(skb, local->hw.extra_tx_headroom);
+
+	switch (action_code) {
+	case WLAN_TDLS_SETUP_REQUEST:
+	case WLAN_TDLS_SETUP_RESPONSE:
+	case WLAN_TDLS_SETUP_CONFIRM:
+	case WLAN_TDLS_TEARDOWN:
+	case WLAN_TDLS_DISCOVERY_REQUEST:
+		ret = ieee80211_prep_tdls_encap_data(wiphy, dev, peer,
+						     action_code, dialog_token,
+						     status_code, skb);
+		send_direct = false;
+		break;
+	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
+		ret = ieee80211_prep_tdls_direct(wiphy, dev, peer, action_code,
+						 dialog_token, status_code,
+						 skb);
+		send_direct = true;
+		break;
+	default:
+		ret = -ENOTSUPP;
+		break;
+	}
+
+	if (ret < 0)
+		goto fail;
+
+	if (extra_ies_len)
+		memcpy(skb_put(skb, extra_ies_len), extra_ies, extra_ies_len);
+
+	/* the TDLS link IE is always added last */
+	switch (action_code) {
+	case WLAN_TDLS_SETUP_REQUEST:
+	case WLAN_TDLS_SETUP_CONFIRM:
+	case WLAN_TDLS_TEARDOWN:
+	case WLAN_TDLS_DISCOVERY_REQUEST:
+		/* we are the initiator */
+		ieee80211_tdls_add_link_ie(skb, sdata->vif.addr, peer,
+					   sdata->u.mgd.bssid);
+		break;
+	case WLAN_TDLS_SETUP_RESPONSE:
+	case WLAN_PUB_ACTION_TDLS_DISCOVER_RES:
+		/* we are the responder */
+		ieee80211_tdls_add_link_ie(skb, peer, sdata->vif.addr,
+					   sdata->u.mgd.bssid);
+		break;
+	default:
+		ret = -ENOTSUPP;
+		goto fail;
+	}
+
+	if (send_direct) {
+		ieee80211_tx_skb(sdata, skb);
+		return 0;
+	}
+
+	/*
+	 * According to 802.11z: Setup req/resp are sent in AC_BK, otherwise
+	 * we should default to AC_VI.
+	 */
+	switch (action_code) {
+	case WLAN_TDLS_SETUP_REQUEST:
+	case WLAN_TDLS_SETUP_RESPONSE:
+		skb_set_queue_mapping(skb, IEEE80211_AC_BK);
+		skb->priority = 2;
+		break;
+	default:
+		skb_set_queue_mapping(skb, IEEE80211_AC_VI);
+		skb->priority = 5;
+		break;
+	}
+
+	/* disable bottom halves when entering the Tx path */
+	local_bh_disable();
+	ret = ieee80211_subif_start_xmit(skb, dev);
+	local_bh_enable();
+
+	return ret;
+
+fail:
+	dev_kfree_skb(skb);
+	return ret;
+}
+
+int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev,
+			const u8 *peer, enum nl80211_tdls_operation oper)
+{
+	struct sta_info *sta;
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+	if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS))
+		return -ENOTSUPP;
+
+	if (sdata->vif.type != NL80211_IFTYPE_STATION)
+		return -EINVAL;
+
+	tdls_dbg(sdata, "TDLS oper %d peer %pM\n", oper, peer);
+
+	switch (oper) {
+	case NL80211_TDLS_ENABLE_LINK:
+		rcu_read_lock();
+		sta = sta_info_get(sdata, peer);
+		if (!sta) {
+			rcu_read_unlock();
+			return -ENOLINK;
+		}
+
+		set_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH);
+		rcu_read_unlock();
+		break;
+	case NL80211_TDLS_DISABLE_LINK:
+		return sta_info_destroy_addr(sdata, peer);
+	case NL80211_TDLS_TEARDOWN:
+	case NL80211_TDLS_SETUP:
+	case NL80211_TDLS_DISCOVERY_REQ:
+		/* We don't support in-driver setup/teardown/discovery */
+		return -ENOTSUPP;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return 0;
+}
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index cec5b60487a..cfe1a0688b5 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -184,6 +184,20 @@ TRACE_EVENT(drv_return_bool,
 		  "true" : "false")
 );
 
+TRACE_EVENT(drv_return_u32,
+	TP_PROTO(struct ieee80211_local *local, u32 ret),
+	TP_ARGS(local, ret),
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		__field(u32, ret)
+	),
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		__entry->ret = ret;
+	),
+	TP_printk(LOCAL_PR_FMT " - %u", LOCAL_PR_ARG, __entry->ret)
+);
+
 TRACE_EVENT(drv_return_u64,
 	TP_PROTO(struct ieee80211_local *local, u64 ret),
 	TP_ARGS(local, ret),
@@ -1375,6 +1389,91 @@ TRACE_EVENT(drv_change_chanctx,
 	)
 );
 
+#if !defined(__TRACE_VIF_ENTRY)
+#define __TRACE_VIF_ENTRY
+struct trace_vif_entry {
+	enum nl80211_iftype vif_type;
+	bool p2p;
+	char vif_name[IFNAMSIZ];
+} __packed;
+
+struct trace_chandef_entry {
+	u32 control_freq;
+	u32 chan_width;
+	u32 center_freq1;
+	u32 center_freq2;
+} __packed;
+
+struct trace_switch_entry {
+	struct trace_vif_entry vif;
+	struct trace_chandef_entry old_chandef;
+	struct trace_chandef_entry new_chandef;
+} __packed;
+
+#define SWITCH_ENTRY_ASSIGN(to, from) local_vifs[i].to = vifs[i].from
+#endif
+
+TRACE_EVENT(drv_switch_vif_chanctx,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_vif_chanctx_switch *vifs,
+		 int n_vifs, enum ieee80211_chanctx_switch_mode mode),
+	    TP_ARGS(local, vifs, n_vifs, mode),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		__field(int, n_vifs)
+		__field(u32, mode)
+		__dynamic_array(u8, vifs,
+				sizeof(struct trace_switch_entry) * n_vifs)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		__entry->n_vifs = n_vifs;
+		__entry->mode = mode;
+		{
+			struct trace_switch_entry *local_vifs =
+				__get_dynamic_array(vifs);
+			int i;
+
+			for (i = 0; i < n_vifs; i++) {
+				struct ieee80211_sub_if_data *sdata;
+
+				sdata = container_of(vifs[i].vif,
+						struct ieee80211_sub_if_data,
+						vif);
+
+				SWITCH_ENTRY_ASSIGN(vif.vif_type, vif->type);
+				SWITCH_ENTRY_ASSIGN(vif.p2p, vif->p2p);
+				strncpy(local_vifs[i].vif.vif_name,
+					sdata->name,
+					sizeof(local_vifs[i].vif.vif_name));
+				SWITCH_ENTRY_ASSIGN(old_chandef.control_freq,
+						old_ctx->def.chan->center_freq);
+				SWITCH_ENTRY_ASSIGN(old_chandef.chan_width,
+						    old_ctx->def.width);
+				SWITCH_ENTRY_ASSIGN(old_chandef.center_freq1,
+						    old_ctx->def.center_freq1);
+				SWITCH_ENTRY_ASSIGN(old_chandef.center_freq2,
+						    old_ctx->def.center_freq2);
+				SWITCH_ENTRY_ASSIGN(new_chandef.control_freq,
+						new_ctx->def.chan->center_freq);
+				SWITCH_ENTRY_ASSIGN(new_chandef.chan_width,
+						    new_ctx->def.width);
+				SWITCH_ENTRY_ASSIGN(new_chandef.center_freq1,
+						    new_ctx->def.center_freq1);
+				SWITCH_ENTRY_ASSIGN(new_chandef.center_freq2,
+						    new_ctx->def.center_freq2);
+			}
+		}
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT " n_vifs:%d mode:%d",
+		LOCAL_PR_ARG, __entry->n_vifs, __entry->mode
+	)
+);
+
 DECLARE_EVENT_CLASS(local_sdata_chanctx,
 	TP_PROTO(struct ieee80211_local *local,
 		 struct ieee80211_sub_if_data *sdata,
@@ -1499,6 +1598,24 @@ DEFINE_EVENT(local_sdata_evt, drv_leave_ibss,
 	TP_ARGS(local, sdata)
 );
 
+TRACE_EVENT(drv_get_expected_throughput,
+	TP_PROTO(struct ieee80211_sta *sta),
+
+	TP_ARGS(sta),
+
+	TP_STRUCT__entry(
+		STA_ENTRY
+	),
+
+	TP_fast_assign(
+		STA_ASSIGN;
+	),
+
+	TP_printk(
+		STA_PR_FMT, STA_PR_ARG
+	)
+);
+
 /*
  * Tracing for API calls that drivers call.
  */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 19d36d4117e..1a252c606ad 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -414,6 +414,9 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx)
 	if (ieee80211_has_order(hdr->frame_control))
 		return TX_CONTINUE;
 
+	if (ieee80211_is_probe_req(hdr->frame_control))
+		return TX_CONTINUE;
+
 	if (tx->local->hw.flags & IEEE80211_HW_QUEUE_CONTROL)
 		info->hw_queue = tx->sdata->vif.cab_queue;
 
@@ -463,6 +466,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 {
 	struct sta_info *sta = tx->sta;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
 	struct ieee80211_local *local = tx->local;
 
 	if (unlikely(!sta))
@@ -473,6 +477,12 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		     !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) {
 		int ac = skb_get_queue_mapping(tx->skb);
 
+		if (ieee80211_is_mgmt(hdr->frame_control) &&
+		    !ieee80211_is_bufferable_mmpdu(hdr->frame_control)) {
+			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
+			return TX_CONTINUE;
+		}
+
 		ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n",
 		       sta->sta.addr, sta->sta.aid, ac);
 		if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
@@ -531,19 +541,9 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 static ieee80211_tx_result debug_noinline
 ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx)
 {
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
-
 	if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED))
 		return TX_CONTINUE;
 
-	if (ieee80211_is_mgmt(hdr->frame_control) &&
-	    !ieee80211_is_bufferable_mmpdu(hdr->frame_control)) {
-		if (tx->flags & IEEE80211_TX_UNICAST)
-			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
-		return TX_CONTINUE;
-	}
-
 	if (tx->flags & IEEE80211_TX_UNICAST)
 		return ieee80211_tx_h_unicast_ps_buf(tx);
 	else
@@ -2328,7 +2328,8 @@ void ieee80211_tx_pending(unsigned long data)
 /* functions for drivers to get certain frames */
 
 static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
-				       struct ps_data *ps, struct sk_buff *skb)
+				       struct ps_data *ps, struct sk_buff *skb,
+				       bool is_template)
 {
 	u8 *pos, *tim;
 	int aid0 = 0;
@@ -2341,11 +2342,12 @@ static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
 		 * checking byte-for-byte */
 		have_bits = !bitmap_empty((unsigned long *)ps->tim,
 					  IEEE80211_MAX_AID+1);
-
-	if (ps->dtim_count == 0)
-		ps->dtim_count = sdata->vif.bss_conf.dtim_period - 1;
-	else
-		ps->dtim_count--;
+	if (!is_template) {
+		if (ps->dtim_count == 0)
+			ps->dtim_count = sdata->vif.bss_conf.dtim_period - 1;
+		else
+			ps->dtim_count--;
+	}
 
 	tim = pos = (u8 *) skb_put(skb, 6);
 	*pos++ = WLAN_EID_TIM;
@@ -2391,7 +2393,8 @@ static void __ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
 }
 
 static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
-				    struct ps_data *ps, struct sk_buff *skb)
+				    struct ps_data *ps, struct sk_buff *skb,
+				    bool is_template)
 {
 	struct ieee80211_local *local = sdata->local;
 
@@ -2403,24 +2406,24 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
 	 * of the tim bitmap in mac80211 and the driver.
 	 */
 	if (local->tim_in_locked_section) {
-		__ieee80211_beacon_add_tim(sdata, ps, skb);
+		__ieee80211_beacon_add_tim(sdata, ps, skb, is_template);
 	} else {
 		spin_lock_bh(&local->tim_lock);
-		__ieee80211_beacon_add_tim(sdata, ps, skb);
+		__ieee80211_beacon_add_tim(sdata, ps, skb, is_template);
 		spin_unlock_bh(&local->tim_lock);
 	}
 
 	return 0;
 }
 
-static void ieee80211_update_csa(struct ieee80211_sub_if_data *sdata,
-				 struct beacon_data *beacon)
+static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata,
+			      struct beacon_data *beacon)
 {
 	struct probe_resp *resp;
-	int counter_offset_beacon = sdata->csa_counter_offset_beacon;
-	int counter_offset_presp = sdata->csa_counter_offset_presp;
 	u8 *beacon_data;
 	size_t beacon_data_len;
+	int i;
+	u8 count = sdata->csa_current_counter;
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP:
@@ -2438,40 +2441,57 @@ static void ieee80211_update_csa(struct ieee80211_sub_if_data *sdata,
 	default:
 		return;
 	}
-	if (WARN_ON(counter_offset_beacon >= beacon_data_len))
-		return;
 
-	/* Warn if the driver did not check for/react to csa
-	 * completeness.  A beacon with CSA counter set to 0 should
-	 * never occur, because a counter of 1 means switch just
-	 * before the next beacon.
-	 */
-	if (WARN_ON(beacon_data[counter_offset_beacon] == 1))
-		return;
+	for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; ++i) {
+		u16 counter_offset_beacon =
+			sdata->csa_counter_offset_beacon[i];
+		u16 counter_offset_presp = sdata->csa_counter_offset_presp[i];
 
-	beacon_data[counter_offset_beacon]--;
+		if (counter_offset_beacon) {
+			if (WARN_ON(counter_offset_beacon >= beacon_data_len))
+				return;
 
-	if (sdata->vif.type == NL80211_IFTYPE_AP && counter_offset_presp) {
-		rcu_read_lock();
-		resp = rcu_dereference(sdata->u.ap.probe_resp);
+			beacon_data[counter_offset_beacon] = count;
+		}
 
-		/* if nl80211 accepted the offset, this should not happen. */
-		if (WARN_ON(!resp)) {
+		if (sdata->vif.type == NL80211_IFTYPE_AP &&
+		    counter_offset_presp) {
+			rcu_read_lock();
+			resp = rcu_dereference(sdata->u.ap.probe_resp);
+
+			/* If nl80211 accepted the offset, this should
+			 * not happen.
+			 */
+			if (WARN_ON(!resp)) {
+				rcu_read_unlock();
+				return;
+			}
+			resp->data[counter_offset_presp] = count;
 			rcu_read_unlock();
-			return;
 		}
-		resp->data[counter_offset_presp]--;
-		rcu_read_unlock();
 	}
 }
 
+u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	sdata->csa_current_counter--;
+
+	/* the counter should never reach 0 */
+	WARN_ON(!sdata->csa_current_counter);
+
+	return sdata->csa_current_counter;
+}
+EXPORT_SYMBOL(ieee80211_csa_update_counter);
+
 bool ieee80211_csa_is_complete(struct ieee80211_vif *vif)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct beacon_data *beacon = NULL;
 	u8 *beacon_data;
 	size_t beacon_data_len;
-	int counter_beacon = sdata->csa_counter_offset_beacon;
+	int counter_beacon = sdata->csa_counter_offset_beacon[0];
 	int ret = false;
 
 	if (!ieee80211_sdata_running(sdata))
@@ -2521,9 +2541,11 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif)
 }
 EXPORT_SYMBOL(ieee80211_csa_is_complete);
 
-struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
-					 struct ieee80211_vif *vif,
-					 u16 *tim_offset, u16 *tim_length)
+static struct sk_buff *
+__ieee80211_beacon_get(struct ieee80211_hw *hw,
+		       struct ieee80211_vif *vif,
+		       struct ieee80211_mutable_offsets *offs,
+		       bool is_template)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
 	struct sk_buff *skb = NULL;
@@ -2532,6 +2554,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 	enum ieee80211_band band;
 	struct ieee80211_tx_rate_control txrc;
 	struct ieee80211_chanctx_conf *chanctx_conf;
+	int csa_off_base = 0;
 
 	rcu_read_lock();
 
@@ -2541,18 +2564,20 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 	if (!ieee80211_sdata_running(sdata) || !chanctx_conf)
 		goto out;
 
-	if (tim_offset)
-		*tim_offset = 0;
-	if (tim_length)
-		*tim_length = 0;
+	if (offs)
+		memset(offs, 0, sizeof(*offs));
 
 	if (sdata->vif.type == NL80211_IFTYPE_AP) {
 		struct ieee80211_if_ap *ap = &sdata->u.ap;
 		struct beacon_data *beacon = rcu_dereference(ap->beacon);
 
 		if (beacon) {
-			if (sdata->vif.csa_active)
-				ieee80211_update_csa(sdata, beacon);
+			if (sdata->vif.csa_active) {
+				if (!is_template)
+					ieee80211_csa_update_counter(vif);
+
+				ieee80211_set_csa(sdata, beacon);
+			}
 
 			/*
 			 * headroom, head length,
@@ -2569,12 +2594,16 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 			memcpy(skb_put(skb, beacon->head_len), beacon->head,
 			       beacon->head_len);
 
-			ieee80211_beacon_add_tim(sdata, &ap->ps, skb);
+			ieee80211_beacon_add_tim(sdata, &ap->ps, skb,
+						 is_template);
 
-			if (tim_offset)
-				*tim_offset = beacon->head_len;
-			if (tim_length)
-				*tim_length = skb->len - beacon->head_len;
+			if (offs) {
+				offs->tim_offset = beacon->head_len;
+				offs->tim_length = skb->len - beacon->head_len;
+
+				/* for AP the csa offsets are from tail */
+				csa_off_base = skb->len;
+			}
 
 			if (beacon->tail)
 				memcpy(skb_put(skb, beacon->tail_len),
@@ -2589,9 +2618,12 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 		if (!presp)
 			goto out;
 
-		if (sdata->vif.csa_active)
-			ieee80211_update_csa(sdata, presp);
+		if (sdata->vif.csa_active) {
+			if (!is_template)
+				ieee80211_csa_update_counter(vif);
 
+			ieee80211_set_csa(sdata, presp);
+		}
 
 		skb = dev_alloc_skb(local->tx_headroom + presp->head_len +
 				    local->hw.extra_beacon_tailroom);
@@ -2611,8 +2643,17 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 		if (!bcn)
 			goto out;
 
-		if (sdata->vif.csa_active)
-			ieee80211_update_csa(sdata, bcn);
+		if (sdata->vif.csa_active) {
+			if (!is_template)
+				/* TODO: For mesh csa_counter is in TU, so
+				 * decrementing it by one isn't correct, but
+				 * for now we leave it consistent with overall
+				 * mac80211's behavior.
+				 */
+				ieee80211_csa_update_counter(vif);
+
+			ieee80211_set_csa(sdata, bcn);
+		}
 
 		if (ifmsh->sync_ops)
 			ifmsh->sync_ops->adjust_tbtt(sdata, bcn);
@@ -2626,13 +2667,33 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 			goto out;
 		skb_reserve(skb, local->tx_headroom);
 		memcpy(skb_put(skb, bcn->head_len), bcn->head, bcn->head_len);
-		ieee80211_beacon_add_tim(sdata, &ifmsh->ps, skb);
+		ieee80211_beacon_add_tim(sdata, &ifmsh->ps, skb, is_template);
+
+		if (offs) {
+			offs->tim_offset = bcn->head_len;
+			offs->tim_length = skb->len - bcn->head_len;
+		}
+
 		memcpy(skb_put(skb, bcn->tail_len), bcn->tail, bcn->tail_len);
 	} else {
 		WARN_ON(1);
 		goto out;
 	}
 
+	/* CSA offsets */
+	if (offs) {
+		int i;
+
+		for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; i++) {
+			u16 csa_off = sdata->csa_counter_offset_beacon[i];
+
+			if (!csa_off)
+				continue;
+
+			offs->csa_counter_offs[i] = csa_off_base + csa_off;
+		}
+	}
+
 	band = chanctx_conf->def.chan->band;
 
 	info = IEEE80211_SKB_CB(skb);
@@ -2663,6 +2724,32 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
  out:
 	rcu_read_unlock();
 	return skb;
+
+}
+
+struct sk_buff *
+ieee80211_beacon_get_template(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_mutable_offsets *offs)
+{
+	return __ieee80211_beacon_get(hw, vif, offs, true);
+}
+EXPORT_SYMBOL(ieee80211_beacon_get_template);
+
+struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
+					 struct ieee80211_vif *vif,
+					 u16 *tim_offset, u16 *tim_length)
+{
+	struct ieee80211_mutable_offsets offs = {};
+	struct sk_buff *bcn = __ieee80211_beacon_get(hw, vif, &offs, false);
+
+	if (tim_offset)
+		*tim_offset = offs.tim_offset;
+
+	if (tim_length)
+		*tim_length = offs.tim_length;
+
+	return bcn;
 }
 EXPORT_SYMBOL(ieee80211_beacon_get_tim);
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 3c365837e91..a6cda52ed92 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -554,7 +554,7 @@ void ieee80211_flush_queues(struct ieee80211_local *local,
 	ieee80211_stop_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_FLUSH);
 
-	drv_flush(local, queues, false);
+	drv_flush(local, sdata, queues, false);
 
 	ieee80211_wake_queues_by_reason(&local->hw, IEEE80211_MAX_QUEUE_MAP,
 					IEEE80211_QUEUE_STOP_REASON_FLUSH);
@@ -1096,11 +1096,12 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 	int err;
 
 	/* 24 + 6 = header + auth_algo + auth_transaction + status_code */
-	skb = dev_alloc_skb(local->hw.extra_tx_headroom + 24 + 6 + extra_len);
+	skb = dev_alloc_skb(local->hw.extra_tx_headroom + IEEE80211_WEP_IV_LEN +
+			    24 + 6 + extra_len + IEEE80211_WEP_ICV_LEN);
 	if (!skb)
 		return;
 
-	skb_reserve(skb, local->hw.extra_tx_headroom);
+	skb_reserve(skb, local->hw.extra_tx_headroom + IEEE80211_WEP_IV_LEN);
 
 	mgmt = (struct ieee80211_mgmt *) skb_put(skb, 24 + 6);
 	memset(mgmt, 0, 24 + 6);
@@ -1457,6 +1458,44 @@ void ieee80211_stop_device(struct ieee80211_local *local)
 	drv_stop(local);
 }
 
+static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+	struct ieee80211_chanctx *ctx;
+
+	/*
+	 * We get here if during resume the device can't be restarted properly.
+	 * We might also get here if this happens during HW reset, which is a
+	 * slightly different situation and we need to drop all connections in
+	 * the latter case.
+	 *
+	 * Ask cfg80211 to turn off all interfaces, this will result in more
+	 * warnings but at least we'll then get into a clean stopped state.
+	 */
+
+	local->resuming = false;
+	local->suspended = false;
+	local->started = false;
+
+	/* scheduled scan clearly can't be running any more, but tell
+	 * cfg80211 and clear local state
+	 */
+	ieee80211_sched_scan_end(local);
+
+	list_for_each_entry(sdata, &local->interfaces, list)
+		sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER;
+
+	/* Mark channel contexts as not being in the driver any more to avoid
+	 * removing them from the driver during the shutdown process...
+	 */
+	mutex_lock(&local->chanctx_mtx);
+	list_for_each_entry(ctx, &local->chanctx_list, list)
+		ctx->driver_present = false;
+	mutex_unlock(&local->chanctx_mtx);
+
+	cfg80211_shutdown_all_interfaces(local->hw.wiphy);
+}
+
 static void ieee80211_assign_chanctx(struct ieee80211_local *local,
 				     struct ieee80211_sub_if_data *sdata)
 {
@@ -1520,9 +1559,11 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	 */
 	res = drv_start(local);
 	if (res) {
-		WARN(local->suspended, "Hardware became unavailable "
-		     "upon resume. This could be a software issue "
-		     "prior to suspend or a hardware issue.\n");
+		if (local->suspended)
+			WARN(1, "Hardware became unavailable upon resume. This could be a software issue prior to suspend or a hardware issue.\n");
+		else
+			WARN(1, "Hardware became unavailable during restart.\n");
+		ieee80211_handle_reconfig_failure(local);
 		return res;
 	}
 
@@ -1546,7 +1587,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		WARN_ON(local->resuming);
 		res = drv_add_interface(local, sdata);
 		if (WARN_ON(res)) {
-			rcu_assign_pointer(local->monitor_sdata, NULL);
+			RCU_INIT_POINTER(local->monitor_sdata, NULL);
 			synchronize_net();
 			kfree(sdata);
 		}
@@ -1565,17 +1606,17 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		list_for_each_entry(ctx, &local->chanctx_list, list)
 			WARN_ON(drv_add_chanctx(local, ctx));
 		mutex_unlock(&local->chanctx_mtx);
-	}
 
-	list_for_each_entry(sdata, &local->interfaces, list) {
-		if (!ieee80211_sdata_running(sdata))
-			continue;
-		ieee80211_assign_chanctx(local, sdata);
-	}
+		list_for_each_entry(sdata, &local->interfaces, list) {
+			if (!ieee80211_sdata_running(sdata))
+				continue;
+			ieee80211_assign_chanctx(local, sdata);
+		}
 
-	sdata = rtnl_dereference(local->monitor_sdata);
-	if (sdata && ieee80211_sdata_running(sdata))
-		ieee80211_assign_chanctx(local, sdata);
+		sdata = rtnl_dereference(local->monitor_sdata);
+		if (sdata && ieee80211_sdata_running(sdata))
+			ieee80211_assign_chanctx(local, sdata);
+	}
 
 	/* add STAs back */
 	mutex_lock(&local->sta_mtx);
@@ -1671,13 +1712,10 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 			}
 			break;
 		case NL80211_IFTYPE_WDS:
-			break;
 		case NL80211_IFTYPE_AP_VLAN:
 		case NL80211_IFTYPE_MONITOR:
-			/* ignore virtual */
-			break;
 		case NL80211_IFTYPE_P2P_DEVICE:
-			changed = BSS_CHANGED_IDLE;
+			/* nothing to do */
 			break;
 		case NL80211_IFTYPE_UNSPECIFIED:
 		case NUM_NL80211_IFTYPES:
@@ -2797,3 +2835,121 @@ void ieee80211_recalc_dtim(struct ieee80211_local *local,
 
 	ps->dtim_count = dtim_count;
 }
+
+int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
+				 const struct cfg80211_chan_def *chandef,
+				 enum ieee80211_chanctx_mode chanmode,
+				 u8 radar_detect)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_sub_if_data *sdata_iter;
+	enum nl80211_iftype iftype = sdata->wdev.iftype;
+	int num[NUM_NL80211_IFTYPES];
+	struct ieee80211_chanctx *ctx;
+	int num_different_channels = 0;
+	int total = 1;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	if (WARN_ON(hweight32(radar_detect) > 1))
+		return -EINVAL;
+
+	if (WARN_ON(chandef && chanmode == IEEE80211_CHANCTX_SHARED &&
+		    !chandef->chan))
+		return -EINVAL;
+
+	if (chandef)
+		num_different_channels = 1;
+
+	if (WARN_ON(iftype >= NUM_NL80211_IFTYPES))
+		return -EINVAL;
+
+	/* Always allow software iftypes */
+	if (local->hw.wiphy->software_iftypes & BIT(iftype)) {
+		if (radar_detect)
+			return -EINVAL;
+		return 0;
+	}
+
+	memset(num, 0, sizeof(num));
+
+	if (iftype != NL80211_IFTYPE_UNSPECIFIED)
+		num[iftype] = 1;
+
+	list_for_each_entry(ctx, &local->chanctx_list, list) {
+		if (ctx->conf.radar_enabled)
+			radar_detect |= BIT(ctx->conf.def.width);
+		if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) {
+			num_different_channels++;
+			continue;
+		}
+		if (chandef && chanmode == IEEE80211_CHANCTX_SHARED &&
+		    cfg80211_chandef_compatible(chandef,
+						&ctx->conf.def))
+			continue;
+		num_different_channels++;
+	}
+
+	list_for_each_entry_rcu(sdata_iter, &local->interfaces, list) {
+		struct wireless_dev *wdev_iter;
+
+		wdev_iter = &sdata_iter->wdev;
+
+		if (sdata_iter == sdata ||
+		    rcu_access_pointer(sdata_iter->vif.chanctx_conf) == NULL ||
+		    local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype))
+			continue;
+
+		num[wdev_iter->iftype]++;
+		total++;
+	}
+
+	if (total == 1 && !radar_detect)
+		return 0;
+
+	return cfg80211_check_combinations(local->hw.wiphy,
+					   num_different_channels,
+					   radar_detect, num);
+}
+
+static void
+ieee80211_iter_max_chans(const struct ieee80211_iface_combination *c,
+			 void *data)
+{
+	u32 *max_num_different_channels = data;
+
+	*max_num_different_channels = max(*max_num_different_channels,
+					  c->num_different_channels);
+}
+
+int ieee80211_max_num_channels(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+	int num[NUM_NL80211_IFTYPES] = {};
+	struct ieee80211_chanctx *ctx;
+	int num_different_channels = 0;
+	u8 radar_detect = 0;
+	u32 max_num_different_channels = 1;
+	int err;
+
+	lockdep_assert_held(&local->chanctx_mtx);
+
+	list_for_each_entry(ctx, &local->chanctx_list, list) {
+		num_different_channels++;
+
+		if (ctx->conf.radar_enabled)
+			radar_detect |= BIT(ctx->conf.def.width);
+	}
+
+	list_for_each_entry_rcu(sdata, &local->interfaces, list)
+		num[sdata->wdev.iftype]++;
+
+	err = cfg80211_iter_combinations(local->hw.wiphy,
+					 num_different_channels, radar_detect,
+					 num, ieee80211_iter_max_chans,
+					 &max_num_different_channels);
+	if (err < 0)
+		return err;
+
+	return max_num_different_channels;
+}
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index b8600e3c29c..9b3dcc20114 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -406,7 +406,10 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb)
 
 	if (info->control.hw_key &&
 	    !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_GENERATE_IV) &&
-	    !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) {
+	    !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) &&
+	    !((info->control.hw_key->flags &
+	       IEEE80211_KEY_FLAG_GENERATE_IV_MGMT) &&
+	      ieee80211_is_mgmt(hdr->frame_control))) {
 		/*
 		 * hwaccel has no need for preallocated room for CCMP
 		 * header or MIC fields
diff --git a/net/mac802154/Kconfig b/net/mac802154/Kconfig
index b33dd76d430..1818a99b308 100644
--- a/net/mac802154/Kconfig
+++ b/net/mac802154/Kconfig
@@ -2,6 +2,10 @@ config MAC802154
 	tristate "Generic IEEE 802.15.4 Soft Networking Stack (mac802154)"
 	depends on IEEE802154
 	select CRC_CCITT
+	select CRYPTO_AUTHENC
+	select CRYPTO_CCM
+	select CRYPTO_CTR
+	select CRYPTO_AES
 	---help---
 	  This option enables the hardware independent IEEE 802.15.4
 	  networking stack for SoftMAC devices (the ones implementing
diff --git a/net/mac802154/Makefile b/net/mac802154/Makefile
index 15d62df5218..9723d6f3f3e 100644
--- a/net/mac802154/Makefile
+++ b/net/mac802154/Makefile
@@ -1,4 +1,5 @@
 obj-$(CONFIG_MAC802154)	+= mac802154.o
-mac802154-objs		:= ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o monitor.o wpan.o
+mac802154-objs		:= ieee802154_dev.o rx.o tx.o mac_cmd.o mib.o \
+			   monitor.o wpan.o llsec.o
 
 ccflags-y += -D__CHECK_ENDIAN__
diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
new file mode 100644
index 00000000000..1456f73b02b
--- /dev/null
+++ b/net/mac802154/llsec.c
@@ -0,0 +1,1070 @@
+/*
+ * Copyright (C) 2014 Fraunhofer ITWM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Written by:
+ * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
+ */
+
+#include <linux/err.h>
+#include <linux/bug.h>
+#include <linux/completion.h>
+#include <net/ieee802154.h>
+#include <crypto/algapi.h>
+
+#include "mac802154.h"
+#include "llsec.h"
+
+static void llsec_key_put(struct mac802154_llsec_key *key);
+static bool llsec_key_id_equal(const struct ieee802154_llsec_key_id *a,
+			       const struct ieee802154_llsec_key_id *b);
+
+static void llsec_dev_free(struct mac802154_llsec_device *dev);
+
+void mac802154_llsec_init(struct mac802154_llsec *sec)
+{
+	memset(sec, 0, sizeof(*sec));
+
+	memset(&sec->params.default_key_source, 0xFF, IEEE802154_ADDR_LEN);
+
+	INIT_LIST_HEAD(&sec->table.security_levels);
+	INIT_LIST_HEAD(&sec->table.devices);
+	INIT_LIST_HEAD(&sec->table.keys);
+	hash_init(sec->devices_short);
+	hash_init(sec->devices_hw);
+	rwlock_init(&sec->lock);
+}
+
+void mac802154_llsec_destroy(struct mac802154_llsec *sec)
+{
+	struct ieee802154_llsec_seclevel *sl, *sn;
+	struct ieee802154_llsec_device *dev, *dn;
+	struct ieee802154_llsec_key_entry *key, *kn;
+
+	list_for_each_entry_safe(sl, sn, &sec->table.security_levels, list) {
+		struct mac802154_llsec_seclevel *msl;
+
+		msl = container_of(sl, struct mac802154_llsec_seclevel, level);
+		list_del(&sl->list);
+		kfree(msl);
+	}
+
+	list_for_each_entry_safe(dev, dn, &sec->table.devices, list) {
+		struct mac802154_llsec_device *mdev;
+
+		mdev = container_of(dev, struct mac802154_llsec_device, dev);
+		list_del(&dev->list);
+		llsec_dev_free(mdev);
+	}
+
+	list_for_each_entry_safe(key, kn, &sec->table.keys, list) {
+		struct mac802154_llsec_key *mkey;
+
+		mkey = container_of(key->key, struct mac802154_llsec_key, key);
+		list_del(&key->list);
+		llsec_key_put(mkey);
+		kfree(key);
+	}
+}
+
+
+
+int mac802154_llsec_get_params(struct mac802154_llsec *sec,
+			       struct ieee802154_llsec_params *params)
+{
+	read_lock_bh(&sec->lock);
+	*params = sec->params;
+	read_unlock_bh(&sec->lock);
+
+	return 0;
+}
+
+int mac802154_llsec_set_params(struct mac802154_llsec *sec,
+			       const struct ieee802154_llsec_params *params,
+			       int changed)
+{
+	write_lock_bh(&sec->lock);
+
+	if (changed & IEEE802154_LLSEC_PARAM_ENABLED)
+		sec->params.enabled = params->enabled;
+	if (changed & IEEE802154_LLSEC_PARAM_FRAME_COUNTER)
+		sec->params.frame_counter = params->frame_counter;
+	if (changed & IEEE802154_LLSEC_PARAM_OUT_LEVEL)
+		sec->params.out_level = params->out_level;
+	if (changed & IEEE802154_LLSEC_PARAM_OUT_KEY)
+		sec->params.out_key = params->out_key;
+	if (changed & IEEE802154_LLSEC_PARAM_KEY_SOURCE)
+		sec->params.default_key_source = params->default_key_source;
+	if (changed & IEEE802154_LLSEC_PARAM_PAN_ID)
+		sec->params.pan_id = params->pan_id;
+	if (changed & IEEE802154_LLSEC_PARAM_HWADDR)
+		sec->params.hwaddr = params->hwaddr;
+	if (changed & IEEE802154_LLSEC_PARAM_COORD_HWADDR)
+		sec->params.coord_hwaddr = params->coord_hwaddr;
+	if (changed & IEEE802154_LLSEC_PARAM_COORD_SHORTADDR)
+		sec->params.coord_shortaddr = params->coord_shortaddr;
+
+	write_unlock_bh(&sec->lock);
+
+	return 0;
+}
+
+
+
+static struct mac802154_llsec_key*
+llsec_key_alloc(const struct ieee802154_llsec_key *template)
+{
+	const int authsizes[3] = { 4, 8, 16 };
+	struct mac802154_llsec_key *key;
+	int i;
+
+	key = kzalloc(sizeof(*key), GFP_KERNEL);
+	if (!key)
+		return NULL;
+
+	kref_init(&key->ref);
+	key->key = *template;
+
+	BUILD_BUG_ON(ARRAY_SIZE(authsizes) != ARRAY_SIZE(key->tfm));
+
+	for (i = 0; i < ARRAY_SIZE(key->tfm); i++) {
+		key->tfm[i] = crypto_alloc_aead("ccm(aes)", 0,
+						CRYPTO_ALG_ASYNC);
+		if (!key->tfm[i])
+			goto err_tfm;
+		if (crypto_aead_setkey(key->tfm[i], template->key,
+				       IEEE802154_LLSEC_KEY_SIZE))
+			goto err_tfm;
+		if (crypto_aead_setauthsize(key->tfm[i], authsizes[i]))
+			goto err_tfm;
+	}
+
+	key->tfm0 = crypto_alloc_blkcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (!key->tfm0)
+		goto err_tfm;
+
+	if (crypto_blkcipher_setkey(key->tfm0, template->key,
+				    IEEE802154_LLSEC_KEY_SIZE))
+		goto err_tfm0;
+
+	return key;
+
+err_tfm0:
+	crypto_free_blkcipher(key->tfm0);
+err_tfm:
+	for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
+		if (key->tfm[i])
+			crypto_free_aead(key->tfm[i]);
+
+	kfree(key);
+	return NULL;
+}
+
+static void llsec_key_release(struct kref *ref)
+{
+	struct mac802154_llsec_key *key;
+	int i;
+
+	key = container_of(ref, struct mac802154_llsec_key, ref);
+
+	for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
+		crypto_free_aead(key->tfm[i]);
+
+	crypto_free_blkcipher(key->tfm0);
+	kfree(key);
+}
+
+static struct mac802154_llsec_key*
+llsec_key_get(struct mac802154_llsec_key *key)
+{
+	kref_get(&key->ref);
+	return key;
+}
+
+static void llsec_key_put(struct mac802154_llsec_key *key)
+{
+	kref_put(&key->ref, llsec_key_release);
+}
+
+static bool llsec_key_id_equal(const struct ieee802154_llsec_key_id *a,
+			       const struct ieee802154_llsec_key_id *b)
+{
+	if (a->mode != b->mode)
+		return false;
+
+	if (a->mode == IEEE802154_SCF_KEY_IMPLICIT)
+		return ieee802154_addr_equal(&a->device_addr, &b->device_addr);
+
+	if (a->id != b->id)
+		return false;
+
+	switch (a->mode) {
+	case IEEE802154_SCF_KEY_INDEX:
+		return true;
+	case IEEE802154_SCF_KEY_SHORT_INDEX:
+		return a->short_source == b->short_source;
+	case IEEE802154_SCF_KEY_HW_INDEX:
+		return a->extended_source == b->extended_source;
+	}
+
+	return false;
+}
+
+int mac802154_llsec_key_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *id,
+			    const struct ieee802154_llsec_key *key)
+{
+	struct mac802154_llsec_key *mkey = NULL;
+	struct ieee802154_llsec_key_entry *pos, *new;
+
+	if (!(key->frame_types & (1 << IEEE802154_FC_TYPE_MAC_CMD)) &&
+	    key->cmd_frame_ids)
+		return -EINVAL;
+
+	list_for_each_entry(pos, &sec->table.keys, list) {
+		if (llsec_key_id_equal(&pos->id, id))
+			return -EEXIST;
+
+		if (memcmp(pos->key->key, key->key,
+			   IEEE802154_LLSEC_KEY_SIZE))
+			continue;
+
+		mkey = container_of(pos->key, struct mac802154_llsec_key, key);
+
+		/* Don't allow multiple instances of the same AES key to have
+		 * different allowed frame types/command frame ids, as this is
+		 * not possible in the 802.15.4 PIB.
+		 */
+		if (pos->key->frame_types != key->frame_types ||
+		    pos->key->cmd_frame_ids != key->cmd_frame_ids)
+			return -EEXIST;
+
+		break;
+	}
+
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	if (!mkey)
+		mkey = llsec_key_alloc(key);
+	else
+		mkey = llsec_key_get(mkey);
+
+	if (!mkey)
+		goto fail;
+
+	new->id = *id;
+	new->key = &mkey->key;
+
+	list_add_rcu(&new->list, &sec->table.keys);
+
+	return 0;
+
+fail:
+	kfree(new);
+	return -ENOMEM;
+}
+
+int mac802154_llsec_key_del(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *key)
+{
+	struct ieee802154_llsec_key_entry *pos;
+
+	list_for_each_entry(pos, &sec->table.keys, list) {
+		struct mac802154_llsec_key *mkey;
+
+		mkey = container_of(pos->key, struct mac802154_llsec_key, key);
+
+		if (llsec_key_id_equal(&pos->id, key)) {
+			list_del_rcu(&pos->list);
+			llsec_key_put(mkey);
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+
+
+static bool llsec_dev_use_shortaddr(__le16 short_addr)
+{
+	return short_addr != cpu_to_le16(IEEE802154_ADDR_UNDEF) &&
+		short_addr != cpu_to_le16(0xffff);
+}
+
+static u32 llsec_dev_hash_short(__le16 short_addr, __le16 pan_id)
+{
+	return ((__force u16) short_addr) << 16 | (__force u16) pan_id;
+}
+
+static u64 llsec_dev_hash_long(__le64 hwaddr)
+{
+	return (__force u64) hwaddr;
+}
+
+static struct mac802154_llsec_device*
+llsec_dev_find_short(struct mac802154_llsec *sec, __le16 short_addr,
+		     __le16 pan_id)
+{
+	struct mac802154_llsec_device *dev;
+	u32 key = llsec_dev_hash_short(short_addr, pan_id);
+
+	hash_for_each_possible_rcu(sec->devices_short, dev, bucket_s, key) {
+		if (dev->dev.short_addr == short_addr &&
+		    dev->dev.pan_id == pan_id)
+			return dev;
+	}
+
+	return NULL;
+}
+
+static struct mac802154_llsec_device*
+llsec_dev_find_long(struct mac802154_llsec *sec, __le64 hwaddr)
+{
+	struct mac802154_llsec_device *dev;
+	u64 key = llsec_dev_hash_long(hwaddr);
+
+	hash_for_each_possible_rcu(sec->devices_hw, dev, bucket_hw, key) {
+		if (dev->dev.hwaddr == hwaddr)
+			return dev;
+	}
+
+	return NULL;
+}
+
+static void llsec_dev_free(struct mac802154_llsec_device *dev)
+{
+	struct ieee802154_llsec_device_key *pos, *pn;
+	struct mac802154_llsec_device_key *devkey;
+
+	list_for_each_entry_safe(pos, pn, &dev->dev.keys, list) {
+		devkey = container_of(pos, struct mac802154_llsec_device_key,
+				      devkey);
+
+		list_del(&pos->list);
+		kfree(devkey);
+	}
+
+	kfree(dev);
+}
+
+int mac802154_llsec_dev_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_device *dev)
+{
+	struct mac802154_llsec_device *entry;
+	u32 skey = llsec_dev_hash_short(dev->short_addr, dev->pan_id);
+	u64 hwkey = llsec_dev_hash_long(dev->hwaddr);
+
+	BUILD_BUG_ON(sizeof(hwkey) != IEEE802154_ADDR_LEN);
+
+	if ((llsec_dev_use_shortaddr(dev->short_addr) &&
+	     llsec_dev_find_short(sec, dev->short_addr, dev->pan_id)) ||
+	     llsec_dev_find_long(sec, dev->hwaddr))
+		return -EEXIST;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->dev = *dev;
+	spin_lock_init(&entry->lock);
+	INIT_LIST_HEAD(&entry->dev.keys);
+
+	if (llsec_dev_use_shortaddr(dev->short_addr))
+		hash_add_rcu(sec->devices_short, &entry->bucket_s, skey);
+	else
+		INIT_HLIST_NODE(&entry->bucket_s);
+
+	hash_add_rcu(sec->devices_hw, &entry->bucket_hw, hwkey);
+	list_add_tail_rcu(&entry->dev.list, &sec->table.devices);
+
+	return 0;
+}
+
+static void llsec_dev_free_rcu(struct rcu_head *rcu)
+{
+	llsec_dev_free(container_of(rcu, struct mac802154_llsec_device, rcu));
+}
+
+int mac802154_llsec_dev_del(struct mac802154_llsec *sec, __le64 device_addr)
+{
+	struct mac802154_llsec_device *pos;
+
+	pos = llsec_dev_find_long(sec, device_addr);
+	if (!pos)
+		return -ENOENT;
+
+	hash_del_rcu(&pos->bucket_s);
+	hash_del_rcu(&pos->bucket_hw);
+	call_rcu(&pos->rcu, llsec_dev_free_rcu);
+
+	return 0;
+}
+
+
+
+static struct mac802154_llsec_device_key*
+llsec_devkey_find(struct mac802154_llsec_device *dev,
+		  const struct ieee802154_llsec_key_id *key)
+{
+	struct ieee802154_llsec_device_key *devkey;
+
+	list_for_each_entry_rcu(devkey, &dev->dev.keys, list) {
+		if (!llsec_key_id_equal(key, &devkey->key_id))
+			continue;
+
+		return container_of(devkey, struct mac802154_llsec_device_key,
+				    devkey);
+	}
+
+	return NULL;
+}
+
+int mac802154_llsec_devkey_add(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key)
+{
+	struct mac802154_llsec_device *dev;
+	struct mac802154_llsec_device_key *devkey;
+
+	dev = llsec_dev_find_long(sec, dev_addr);
+
+	if (!dev)
+		return -ENOENT;
+
+	if (llsec_devkey_find(dev, &key->key_id))
+		return -EEXIST;
+
+	devkey = kmalloc(sizeof(*devkey), GFP_KERNEL);
+	if (!devkey)
+		return -ENOMEM;
+
+	devkey->devkey = *key;
+	list_add_tail_rcu(&devkey->devkey.list, &dev->dev.keys);
+	return 0;
+}
+
+int mac802154_llsec_devkey_del(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key)
+{
+	struct mac802154_llsec_device *dev;
+	struct mac802154_llsec_device_key *devkey;
+
+	dev = llsec_dev_find_long(sec, dev_addr);
+
+	if (!dev)
+		return -ENOENT;
+
+	devkey = llsec_devkey_find(dev, &key->key_id);
+	if (!devkey)
+		return -ENOENT;
+
+	list_del_rcu(&devkey->devkey.list);
+	kfree_rcu(devkey, rcu);
+	return 0;
+}
+
+
+
+static struct mac802154_llsec_seclevel*
+llsec_find_seclevel(const struct mac802154_llsec *sec,
+		    const struct ieee802154_llsec_seclevel *sl)
+{
+	struct ieee802154_llsec_seclevel *pos;
+
+	list_for_each_entry(pos, &sec->table.security_levels, list) {
+		if (pos->frame_type != sl->frame_type ||
+		    (pos->frame_type == IEEE802154_FC_TYPE_MAC_CMD &&
+		     pos->cmd_frame_id != sl->cmd_frame_id) ||
+		    pos->device_override != sl->device_override ||
+		    pos->sec_levels != sl->sec_levels)
+			continue;
+
+		return container_of(pos, struct mac802154_llsec_seclevel,
+				    level);
+	}
+
+	return NULL;
+}
+
+int mac802154_llsec_seclevel_add(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl)
+{
+	struct mac802154_llsec_seclevel *entry;
+
+	if (llsec_find_seclevel(sec, sl))
+		return -EEXIST;
+
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->level = *sl;
+
+	list_add_tail_rcu(&entry->level.list, &sec->table.security_levels);
+
+	return 0;
+}
+
+int mac802154_llsec_seclevel_del(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl)
+{
+	struct mac802154_llsec_seclevel *pos;
+
+	pos = llsec_find_seclevel(sec, sl);
+	if (!pos)
+		return -ENOENT;
+
+	list_del_rcu(&pos->level.list);
+	kfree_rcu(pos, rcu);
+
+	return 0;
+}
+
+
+
+static int llsec_recover_addr(struct mac802154_llsec *sec,
+			      struct ieee802154_addr *addr)
+{
+	__le16 caddr = sec->params.coord_shortaddr;
+	addr->pan_id = sec->params.pan_id;
+
+	if (caddr == cpu_to_le16(IEEE802154_ADDR_BROADCAST)) {
+		return -EINVAL;
+	} else if (caddr == cpu_to_le16(IEEE802154_ADDR_UNDEF)) {
+		addr->extended_addr = sec->params.coord_hwaddr;
+		addr->mode = IEEE802154_ADDR_LONG;
+	} else {
+		addr->short_addr = sec->params.coord_shortaddr;
+		addr->mode = IEEE802154_ADDR_SHORT;
+	}
+
+	return 0;
+}
+
+static struct mac802154_llsec_key*
+llsec_lookup_key(struct mac802154_llsec *sec,
+		 const struct ieee802154_hdr *hdr,
+		 const struct ieee802154_addr *addr,
+		 struct ieee802154_llsec_key_id *key_id)
+{
+	struct ieee802154_addr devaddr = *addr;
+	u8 key_id_mode = hdr->sec.key_id_mode;
+	struct ieee802154_llsec_key_entry *key_entry;
+	struct mac802154_llsec_key *key;
+
+	if (key_id_mode == IEEE802154_SCF_KEY_IMPLICIT &&
+	    devaddr.mode == IEEE802154_ADDR_NONE) {
+		if (hdr->fc.type == IEEE802154_FC_TYPE_BEACON) {
+			devaddr.extended_addr = sec->params.coord_hwaddr;
+			devaddr.mode = IEEE802154_ADDR_LONG;
+		} else if (llsec_recover_addr(sec, &devaddr) < 0) {
+			return NULL;
+		}
+	}
+
+	list_for_each_entry_rcu(key_entry, &sec->table.keys, list) {
+		const struct ieee802154_llsec_key_id *id = &key_entry->id;
+
+		if (!(key_entry->key->frame_types & BIT(hdr->fc.type)))
+			continue;
+
+		if (id->mode != key_id_mode)
+			continue;
+
+		if (key_id_mode == IEEE802154_SCF_KEY_IMPLICIT) {
+			if (ieee802154_addr_equal(&devaddr, &id->device_addr))
+				goto found;
+		} else {
+			if (id->id != hdr->sec.key_id)
+				continue;
+
+			if ((key_id_mode == IEEE802154_SCF_KEY_INDEX) ||
+			    (key_id_mode == IEEE802154_SCF_KEY_SHORT_INDEX &&
+			     id->short_source == hdr->sec.short_src) ||
+			    (key_id_mode == IEEE802154_SCF_KEY_HW_INDEX &&
+			     id->extended_source == hdr->sec.extended_src))
+				goto found;
+		}
+	}
+
+	return NULL;
+
+found:
+	key = container_of(key_entry->key, struct mac802154_llsec_key, key);
+	if (key_id)
+		*key_id = key_entry->id;
+	return llsec_key_get(key);
+}
+
+
+static void llsec_geniv(u8 iv[16], __le64 addr,
+			const struct ieee802154_sechdr *sec)
+{
+	__be64 addr_bytes = (__force __be64) swab64((__force u64) addr);
+	__be32 frame_counter = (__force __be32) swab32((__force u32) sec->frame_counter);
+
+	iv[0] = 1; /* L' = L - 1 = 1 */
+	memcpy(iv + 1, &addr_bytes, sizeof(addr_bytes));
+	memcpy(iv + 9, &frame_counter, sizeof(frame_counter));
+	iv[13] = sec->level;
+	iv[14] = 0;
+	iv[15] = 1;
+}
+
+static int
+llsec_do_encrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec,
+			const struct ieee802154_hdr *hdr,
+			struct mac802154_llsec_key *key)
+{
+	u8 iv[16];
+	struct scatterlist src;
+	struct blkcipher_desc req = {
+		.tfm = key->tfm0,
+		.info = iv,
+		.flags = 0,
+	};
+
+	llsec_geniv(iv, sec->params.hwaddr, &hdr->sec);
+	sg_init_one(&src, skb->data, skb->len);
+	return crypto_blkcipher_encrypt_iv(&req, &src, &src, skb->len);
+}
+
+static struct crypto_aead*
+llsec_tfm_by_len(struct mac802154_llsec_key *key, int authlen)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
+		if (crypto_aead_authsize(key->tfm[i]) == authlen)
+			return key->tfm[i];
+
+	BUG();
+}
+
+static int
+llsec_do_encrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
+		      const struct ieee802154_hdr *hdr,
+		      struct mac802154_llsec_key *key)
+{
+	u8 iv[16];
+	unsigned char *data;
+	int authlen, assoclen, datalen, rc;
+	struct scatterlist src, assoc[2], dst[2];
+	struct aead_request *req;
+
+	authlen = ieee802154_sechdr_authtag_len(&hdr->sec);
+	llsec_geniv(iv, sec->params.hwaddr, &hdr->sec);
+
+	req = aead_request_alloc(llsec_tfm_by_len(key, authlen), GFP_ATOMIC);
+	if (!req)
+		return -ENOMEM;
+
+	sg_init_table(assoc, 2);
+	sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len);
+	assoclen = skb->mac_len;
+
+	data = skb_mac_header(skb) + skb->mac_len;
+	datalen = skb_tail_pointer(skb) - data;
+
+	if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) {
+		sg_set_buf(&assoc[1], data, 0);
+	} else {
+		sg_set_buf(&assoc[1], data, datalen);
+		assoclen += datalen;
+		datalen = 0;
+	}
+
+	sg_init_one(&src, data, datalen);
+
+	sg_init_table(dst, 2);
+	sg_set_buf(&dst[0], data, datalen);
+	sg_set_buf(&dst[1], skb_put(skb, authlen), authlen);
+
+	aead_request_set_callback(req, 0, NULL, NULL);
+	aead_request_set_assoc(req, assoc, assoclen);
+	aead_request_set_crypt(req, &src, dst, datalen, iv);
+
+	rc = crypto_aead_encrypt(req);
+
+	kfree(req);
+
+	return rc;
+}
+
+static int llsec_do_encrypt(struct sk_buff *skb,
+			    const struct mac802154_llsec *sec,
+			    const struct ieee802154_hdr *hdr,
+			    struct mac802154_llsec_key *key)
+{
+	if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC)
+		return llsec_do_encrypt_unauth(skb, sec, hdr, key);
+	else
+		return llsec_do_encrypt_auth(skb, sec, hdr, key);
+}
+
+int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb)
+{
+	struct ieee802154_hdr hdr;
+	int rc, authlen, hlen;
+	struct mac802154_llsec_key *key;
+	u32 frame_ctr;
+
+	hlen = ieee802154_hdr_pull(skb, &hdr);
+
+	if (hlen < 0 || hdr.fc.type != IEEE802154_FC_TYPE_DATA)
+		return -EINVAL;
+
+	if (!hdr.fc.security_enabled || hdr.sec.level == 0) {
+		skb_push(skb, hlen);
+		return 0;
+	}
+
+	authlen = ieee802154_sechdr_authtag_len(&hdr.sec);
+
+	if (skb->len + hlen + authlen + IEEE802154_MFR_SIZE > IEEE802154_MTU)
+		return -EMSGSIZE;
+
+	rcu_read_lock();
+
+	read_lock_bh(&sec->lock);
+
+	if (!sec->params.enabled) {
+		rc = -EINVAL;
+		goto fail_read;
+	}
+
+	key = llsec_lookup_key(sec, &hdr, &hdr.dest, NULL);
+	if (!key) {
+		rc = -ENOKEY;
+		goto fail_read;
+	}
+
+	read_unlock_bh(&sec->lock);
+
+	write_lock_bh(&sec->lock);
+
+	frame_ctr = be32_to_cpu(sec->params.frame_counter);
+	hdr.sec.frame_counter = cpu_to_le32(frame_ctr);
+	if (frame_ctr == 0xFFFFFFFF) {
+		write_unlock_bh(&sec->lock);
+		llsec_key_put(key);
+		rc = -EOVERFLOW;
+		goto fail;
+	}
+
+	sec->params.frame_counter = cpu_to_be32(frame_ctr + 1);
+
+	write_unlock_bh(&sec->lock);
+
+	rcu_read_unlock();
+
+	skb->mac_len = ieee802154_hdr_push(skb, &hdr);
+	skb_reset_mac_header(skb);
+
+	rc = llsec_do_encrypt(skb, sec, &hdr, key);
+	llsec_key_put(key);
+
+	return rc;
+
+fail_read:
+	read_unlock_bh(&sec->lock);
+fail:
+	rcu_read_unlock();
+	return rc;
+}
+
+
+
+static struct mac802154_llsec_device*
+llsec_lookup_dev(struct mac802154_llsec *sec,
+		 const struct ieee802154_addr *addr)
+{
+	struct ieee802154_addr devaddr = *addr;
+	struct mac802154_llsec_device *dev = NULL;
+
+	if (devaddr.mode == IEEE802154_ADDR_NONE &&
+	    llsec_recover_addr(sec, &devaddr) < 0)
+		return NULL;
+
+	if (devaddr.mode == IEEE802154_ADDR_SHORT) {
+		u32 key = llsec_dev_hash_short(devaddr.short_addr,
+					       devaddr.pan_id);
+
+		hash_for_each_possible_rcu(sec->devices_short, dev,
+					   bucket_s, key) {
+			if (dev->dev.pan_id == devaddr.pan_id &&
+			    dev->dev.short_addr == devaddr.short_addr)
+				return dev;
+		}
+	} else {
+		u64 key = llsec_dev_hash_long(devaddr.extended_addr);
+
+		hash_for_each_possible_rcu(sec->devices_hw, dev,
+					   bucket_hw, key) {
+			if (dev->dev.hwaddr == devaddr.extended_addr)
+				return dev;
+		}
+	}
+
+	return NULL;
+}
+
+static int
+llsec_lookup_seclevel(const struct mac802154_llsec *sec,
+		      u8 frame_type, u8 cmd_frame_id,
+		      struct ieee802154_llsec_seclevel *rlevel)
+{
+	struct ieee802154_llsec_seclevel *level;
+
+	list_for_each_entry_rcu(level, &sec->table.security_levels, list) {
+		if (level->frame_type == frame_type &&
+		    (frame_type != IEEE802154_FC_TYPE_MAC_CMD ||
+		     level->cmd_frame_id == cmd_frame_id)) {
+			*rlevel = *level;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int
+llsec_do_decrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec,
+			const struct ieee802154_hdr *hdr,
+			struct mac802154_llsec_key *key, __le64 dev_addr)
+{
+	u8 iv[16];
+	unsigned char *data;
+	int datalen;
+	struct scatterlist src;
+	struct blkcipher_desc req = {
+		.tfm = key->tfm0,
+		.info = iv,
+		.flags = 0,
+	};
+
+	llsec_geniv(iv, dev_addr, &hdr->sec);
+	data = skb_mac_header(skb) + skb->mac_len;
+	datalen = skb_tail_pointer(skb) - data;
+
+	sg_init_one(&src, data, datalen);
+
+	return crypto_blkcipher_decrypt_iv(&req, &src, &src, datalen);
+}
+
+static int
+llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
+		      const struct ieee802154_hdr *hdr,
+		      struct mac802154_llsec_key *key, __le64 dev_addr)
+{
+	u8 iv[16];
+	unsigned char *data;
+	int authlen, datalen, assoclen, rc;
+	struct scatterlist src, assoc[2];
+	struct aead_request *req;
+
+	authlen = ieee802154_sechdr_authtag_len(&hdr->sec);
+	llsec_geniv(iv, dev_addr, &hdr->sec);
+
+	req = aead_request_alloc(llsec_tfm_by_len(key, authlen), GFP_ATOMIC);
+	if (!req)
+		return -ENOMEM;
+
+	sg_init_table(assoc, 2);
+	sg_set_buf(&assoc[0], skb_mac_header(skb), skb->mac_len);
+	assoclen = skb->mac_len;
+
+	data = skb_mac_header(skb) + skb->mac_len;
+	datalen = skb_tail_pointer(skb) - data;
+
+	if (hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC) {
+		sg_set_buf(&assoc[1], data, 0);
+	} else {
+		sg_set_buf(&assoc[1], data, datalen - authlen);
+		assoclen += datalen - authlen;
+		data += datalen - authlen;
+		datalen = authlen;
+	}
+
+	sg_init_one(&src, data, datalen);
+
+	aead_request_set_callback(req, 0, NULL, NULL);
+	aead_request_set_assoc(req, assoc, assoclen);
+	aead_request_set_crypt(req, &src, &src, datalen, iv);
+
+	rc = crypto_aead_decrypt(req);
+
+	kfree(req);
+	skb_trim(skb, skb->len - authlen);
+
+	return rc;
+}
+
+static int
+llsec_do_decrypt(struct sk_buff *skb, const struct mac802154_llsec *sec,
+		 const struct ieee802154_hdr *hdr,
+		 struct mac802154_llsec_key *key, __le64 dev_addr)
+{
+	if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC)
+		return llsec_do_decrypt_unauth(skb, sec, hdr, key, dev_addr);
+	else
+		return llsec_do_decrypt_auth(skb, sec, hdr, key, dev_addr);
+}
+
+static int
+llsec_update_devkey_record(struct mac802154_llsec_device *dev,
+			   const struct ieee802154_llsec_key_id *in_key)
+{
+	struct mac802154_llsec_device_key *devkey;
+
+	devkey = llsec_devkey_find(dev, in_key);
+
+	if (!devkey) {
+		struct mac802154_llsec_device_key *next;
+
+		next = kzalloc(sizeof(*devkey), GFP_ATOMIC);
+		if (!next)
+			return -ENOMEM;
+
+		next->devkey.key_id = *in_key;
+
+		spin_lock_bh(&dev->lock);
+
+		devkey = llsec_devkey_find(dev, in_key);
+		if (!devkey)
+			list_add_rcu(&next->devkey.list, &dev->dev.keys);
+		else
+			kfree(next);
+
+		spin_unlock_bh(&dev->lock);
+	}
+
+	return 0;
+}
+
+static int
+llsec_update_devkey_info(struct mac802154_llsec_device *dev,
+			 const struct ieee802154_llsec_key_id *in_key,
+			 u32 frame_counter)
+{
+	struct mac802154_llsec_device_key *devkey = NULL;
+
+	if (dev->dev.key_mode == IEEE802154_LLSEC_DEVKEY_RESTRICT) {
+		devkey = llsec_devkey_find(dev, in_key);
+		if (!devkey)
+			return -ENOENT;
+	}
+
+	if (dev->dev.key_mode == IEEE802154_LLSEC_DEVKEY_RECORD) {
+		int rc = llsec_update_devkey_record(dev, in_key);
+
+		if (rc < 0)
+			return rc;
+	}
+
+	spin_lock_bh(&dev->lock);
+
+	if ((!devkey && frame_counter < dev->dev.frame_counter) ||
+	    (devkey && frame_counter < devkey->devkey.frame_counter)) {
+		spin_unlock_bh(&dev->lock);
+		return -EINVAL;
+	}
+
+	if (devkey)
+		devkey->devkey.frame_counter = frame_counter + 1;
+	else
+		dev->dev.frame_counter = frame_counter + 1;
+
+	spin_unlock_bh(&dev->lock);
+
+	return 0;
+}
+
+int mac802154_llsec_decrypt(struct mac802154_llsec *sec, struct sk_buff *skb)
+{
+	struct ieee802154_hdr hdr;
+	struct mac802154_llsec_key *key;
+	struct ieee802154_llsec_key_id key_id;
+	struct mac802154_llsec_device *dev;
+	struct ieee802154_llsec_seclevel seclevel;
+	int err;
+	__le64 dev_addr;
+	u32 frame_ctr;
+
+	if (ieee802154_hdr_peek(skb, &hdr) < 0)
+		return -EINVAL;
+	if (!hdr.fc.security_enabled)
+		return 0;
+	if (hdr.fc.version == 0)
+		return -EINVAL;
+
+	read_lock_bh(&sec->lock);
+	if (!sec->params.enabled) {
+		read_unlock_bh(&sec->lock);
+		return -EINVAL;
+	}
+	read_unlock_bh(&sec->lock);
+
+	rcu_read_lock();
+
+	key = llsec_lookup_key(sec, &hdr, &hdr.source, &key_id);
+	if (!key) {
+		err = -ENOKEY;
+		goto fail;
+	}
+
+	dev = llsec_lookup_dev(sec, &hdr.source);
+	if (!dev) {
+		err = -EINVAL;
+		goto fail_dev;
+	}
+
+	if (llsec_lookup_seclevel(sec, hdr.fc.type, 0, &seclevel) < 0) {
+		err = -EINVAL;
+		goto fail_dev;
+	}
+
+	if (!(seclevel.sec_levels & BIT(hdr.sec.level)) &&
+	    (hdr.sec.level == 0 && seclevel.device_override &&
+	     !dev->dev.seclevel_exempt)) {
+		err = -EINVAL;
+		goto fail_dev;
+	}
+
+	frame_ctr = le32_to_cpu(hdr.sec.frame_counter);
+
+	if (frame_ctr == 0xffffffff) {
+		err = -EOVERFLOW;
+		goto fail_dev;
+	}
+
+	err = llsec_update_devkey_info(dev, &key_id, frame_ctr);
+	if (err)
+		goto fail_dev;
+
+	dev_addr = dev->dev.hwaddr;
+
+	rcu_read_unlock();
+
+	err = llsec_do_decrypt(skb, sec, &hdr, key, dev_addr);
+	llsec_key_put(key);
+	return err;
+
+fail_dev:
+	llsec_key_put(key);
+fail:
+	rcu_read_unlock();
+	return err;
+}
diff --git a/net/mac802154/llsec.h b/net/mac802154/llsec.h
new file mode 100644
index 00000000000..950578e1d7b
--- /dev/null
+++ b/net/mac802154/llsec.h
@@ -0,0 +1,108 @@
+/*
+ * Copyright (C) 2014 Fraunhofer ITWM
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Written by:
+ * Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
+ */
+
+#ifndef MAC802154_LLSEC_H
+#define MAC802154_LLSEC_H
+
+#include <linux/slab.h>
+#include <linux/hashtable.h>
+#include <linux/crypto.h>
+#include <linux/kref.h>
+#include <linux/spinlock.h>
+#include <net/af_ieee802154.h>
+#include <net/ieee802154_netdev.h>
+
+struct mac802154_llsec_key {
+	struct ieee802154_llsec_key key;
+
+	/* one tfm for each authsize (4/8/16) */
+	struct crypto_aead *tfm[3];
+	struct crypto_blkcipher *tfm0;
+
+	struct kref ref;
+};
+
+struct mac802154_llsec_device_key {
+	struct ieee802154_llsec_device_key devkey;
+
+	struct rcu_head rcu;
+};
+
+struct mac802154_llsec_device {
+	struct ieee802154_llsec_device dev;
+
+	struct hlist_node bucket_s;
+	struct hlist_node bucket_hw;
+
+	/* protects dev.frame_counter and the elements of dev.keys */
+	spinlock_t lock;
+
+	struct rcu_head rcu;
+};
+
+struct mac802154_llsec_seclevel {
+	struct ieee802154_llsec_seclevel level;
+
+	struct rcu_head rcu;
+};
+
+struct mac802154_llsec {
+	struct ieee802154_llsec_params params;
+	struct ieee802154_llsec_table table;
+
+	DECLARE_HASHTABLE(devices_short, 6);
+	DECLARE_HASHTABLE(devices_hw, 6);
+
+	/* protects params, all other fields are fine with RCU */
+	rwlock_t lock;
+};
+
+void mac802154_llsec_init(struct mac802154_llsec *sec);
+void mac802154_llsec_destroy(struct mac802154_llsec *sec);
+
+int mac802154_llsec_get_params(struct mac802154_llsec *sec,
+			       struct ieee802154_llsec_params *params);
+int mac802154_llsec_set_params(struct mac802154_llsec *sec,
+			       const struct ieee802154_llsec_params *params,
+			       int changed);
+
+int mac802154_llsec_key_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *id,
+			    const struct ieee802154_llsec_key *key);
+int mac802154_llsec_key_del(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_key_id *key);
+
+int mac802154_llsec_dev_add(struct mac802154_llsec *sec,
+			    const struct ieee802154_llsec_device *dev);
+int mac802154_llsec_dev_del(struct mac802154_llsec *sec,
+			    __le64 device_addr);
+
+int mac802154_llsec_devkey_add(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key);
+int mac802154_llsec_devkey_del(struct mac802154_llsec *sec,
+			       __le64 dev_addr,
+			       const struct ieee802154_llsec_device_key *key);
+
+int mac802154_llsec_seclevel_add(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl);
+int mac802154_llsec_seclevel_del(struct mac802154_llsec *sec,
+				 const struct ieee802154_llsec_seclevel *sl);
+
+int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb);
+int mac802154_llsec_decrypt(struct mac802154_llsec *sec, struct sk_buff *skb);
+
+#endif /* MAC802154_LLSEC_H */
diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h
index 28ef59c566e..762a6f849c6 100644
--- a/net/mac802154/mac802154.h
+++ b/net/mac802154/mac802154.h
@@ -23,8 +23,12 @@
 #ifndef MAC802154_H
 #define MAC802154_H
 
+#include <linux/mutex.h>
+#include <net/mac802154.h>
 #include <net/ieee802154_netdev.h>
 
+#include "llsec.h"
+
 /* mac802154 device private data */
 struct mac802154_priv {
 	struct ieee802154_dev hw;
@@ -90,6 +94,13 @@ struct mac802154_sub_if_data {
 	u8 bsn;
 	/* MAC DSN field */
 	u8 dsn;
+
+	/* protects sec from concurrent access by netlink. access by
+	 * encrypt/decrypt/header_create safe without additional protection.
+	 */
+	struct mutex sec_mtx;
+
+	struct mac802154_llsec sec;
 };
 
 #define mac802154_to_priv(_hw)	container_of(_hw, struct mac802154_priv, hw)
@@ -125,4 +136,37 @@ int mac802154_set_mac_params(struct net_device *dev,
 void mac802154_get_mac_params(struct net_device *dev,
 			      struct ieee802154_mac_params *params);
 
+int mac802154_get_params(struct net_device *dev,
+			 struct ieee802154_llsec_params *params);
+int mac802154_set_params(struct net_device *dev,
+			 const struct ieee802154_llsec_params *params,
+			 int changed);
+
+int mac802154_add_key(struct net_device *dev,
+		      const struct ieee802154_llsec_key_id *id,
+		      const struct ieee802154_llsec_key *key);
+int mac802154_del_key(struct net_device *dev,
+		      const struct ieee802154_llsec_key_id *id);
+
+int mac802154_add_dev(struct net_device *dev,
+		      const struct ieee802154_llsec_device *llsec_dev);
+int mac802154_del_dev(struct net_device *dev, __le64 dev_addr);
+
+int mac802154_add_devkey(struct net_device *dev,
+			 __le64 device_addr,
+			 const struct ieee802154_llsec_device_key *key);
+int mac802154_del_devkey(struct net_device *dev,
+			 __le64 device_addr,
+			 const struct ieee802154_llsec_device_key *key);
+
+int mac802154_add_seclevel(struct net_device *dev,
+			   const struct ieee802154_llsec_seclevel *sl);
+int mac802154_del_seclevel(struct net_device *dev,
+			   const struct ieee802154_llsec_seclevel *sl);
+
+void mac802154_lock_table(struct net_device *dev);
+void mac802154_get_table(struct net_device *dev,
+			 struct ieee802154_llsec_table **t);
+void mac802154_unlock_table(struct net_device *dev);
+
 #endif /* MAC802154_H */
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index d40c0928bc6..bf809131eef 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -40,6 +40,9 @@ static int mac802154_mlme_start_req(struct net_device *dev,
 				    u8 pan_coord, u8 blx,
 				    u8 coord_realign)
 {
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	int rc = 0;
+
 	BUG_ON(addr->mode != IEEE802154_ADDR_SHORT);
 
 	mac802154_dev_set_pan_id(dev, addr->pan_id);
@@ -47,12 +50,31 @@ static int mac802154_mlme_start_req(struct net_device *dev,
 	mac802154_dev_set_ieee_addr(dev);
 	mac802154_dev_set_page_channel(dev, page, channel);
 
+	if (ops->llsec) {
+		struct ieee802154_llsec_params params;
+		int changed = 0;
+
+		params.coord_shortaddr = addr->short_addr;
+		changed |= IEEE802154_LLSEC_PARAM_COORD_SHORTADDR;
+
+		params.pan_id = addr->pan_id;
+		changed |= IEEE802154_LLSEC_PARAM_PAN_ID;
+
+		params.hwaddr = ieee802154_devaddr_from_raw(dev->dev_addr);
+		changed |= IEEE802154_LLSEC_PARAM_HWADDR;
+
+		params.coord_hwaddr = params.hwaddr;
+		changed |= IEEE802154_LLSEC_PARAM_COORD_HWADDR;
+
+		rc = ops->llsec->set_params(dev, &params, changed);
+	}
+
 	/* FIXME: add validation for unused parameters to be sane
 	 * for SoftMAC
 	 */
 	ieee802154_nl_start_confirm(dev, IEEE802154_SUCCESS);
 
-	return 0;
+	return rc;
 }
 
 static struct wpan_phy *mac802154_get_phy(const struct net_device *dev)
@@ -64,6 +86,22 @@ static struct wpan_phy *mac802154_get_phy(const struct net_device *dev)
 	return to_phy(get_device(&priv->hw->phy->dev));
 }
 
+static struct ieee802154_llsec_ops mac802154_llsec_ops = {
+	.get_params = mac802154_get_params,
+	.set_params = mac802154_set_params,
+	.add_key = mac802154_add_key,
+	.del_key = mac802154_del_key,
+	.add_dev = mac802154_add_dev,
+	.del_dev = mac802154_del_dev,
+	.add_devkey = mac802154_add_devkey,
+	.del_devkey = mac802154_del_devkey,
+	.add_seclevel = mac802154_add_seclevel,
+	.del_seclevel = mac802154_del_seclevel,
+	.lock_table = mac802154_lock_table,
+	.get_table = mac802154_get_table,
+	.unlock_table = mac802154_unlock_table,
+};
+
 struct ieee802154_reduced_mlme_ops mac802154_mlme_reduced = {
 	.get_phy = mac802154_get_phy,
 };
@@ -75,6 +113,8 @@ struct ieee802154_mlme_ops mac802154_mlme_wpan = {
 	.get_short_addr = mac802154_dev_get_short_addr,
 	.get_dsn = mac802154_dev_get_dsn,
 
+	.llsec = &mac802154_llsec_ops,
+
 	.set_mac_params = mac802154_set_mac_params,
 	.get_mac_params = mac802154_get_mac_params,
 };
diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c
index f0991f2344d..15aa2f2b03a 100644
--- a/net/mac802154/mib.c
+++ b/net/mac802154/mib.c
@@ -213,3 +213,190 @@ void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan)
 	} else
 		mutex_unlock(&priv->hw->phy->pib_lock);
 }
+
+
+int mac802154_get_params(struct net_device *dev,
+			 struct ieee802154_llsec_params *params)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_get_params(&priv->sec, params);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_set_params(struct net_device *dev,
+			 const struct ieee802154_llsec_params *params,
+			 int changed)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_set_params(&priv->sec, params, changed);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+int mac802154_add_key(struct net_device *dev,
+		      const struct ieee802154_llsec_key_id *id,
+		      const struct ieee802154_llsec_key *key)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_key_add(&priv->sec, id, key);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_del_key(struct net_device *dev,
+		      const struct ieee802154_llsec_key_id *id)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_key_del(&priv->sec, id);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+int mac802154_add_dev(struct net_device *dev,
+		      const struct ieee802154_llsec_device *llsec_dev)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_dev_add(&priv->sec, llsec_dev);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_del_dev(struct net_device *dev, __le64 dev_addr)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_dev_del(&priv->sec, dev_addr);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+int mac802154_add_devkey(struct net_device *dev,
+			 __le64 device_addr,
+			 const struct ieee802154_llsec_device_key *key)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_devkey_add(&priv->sec, device_addr, key);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_del_devkey(struct net_device *dev,
+			 __le64 device_addr,
+			 const struct ieee802154_llsec_device_key *key)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_devkey_del(&priv->sec, device_addr, key);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+int mac802154_add_seclevel(struct net_device *dev,
+			   const struct ieee802154_llsec_seclevel *sl)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_seclevel_add(&priv->sec, sl);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+int mac802154_del_seclevel(struct net_device *dev,
+			   const struct ieee802154_llsec_seclevel *sl)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	int res;
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+	res = mac802154_llsec_seclevel_del(&priv->sec, sl);
+	mutex_unlock(&priv->sec_mtx);
+
+	return res;
+}
+
+
+void mac802154_lock_table(struct net_device *dev)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_lock(&priv->sec_mtx);
+}
+
+void mac802154_get_table(struct net_device *dev,
+			 struct ieee802154_llsec_table **t)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	*t = &priv->sec.table;
+}
+
+void mac802154_unlock_table(struct net_device *dev)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	BUG_ON(dev->type != ARPHRD_IEEE802154);
+
+	mutex_unlock(&priv->sec_mtx);
+}
diff --git a/net/mac802154/monitor.c b/net/mac802154/monitor.c
index 434a26f76a8..a68230e2b25 100644
--- a/net/mac802154/monitor.c
+++ b/net/mac802154/monitor.c
@@ -70,7 +70,8 @@ void mac802154_monitors_rx(struct mac802154_priv *priv, struct sk_buff *skb)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdata, &priv->slaves, list) {
-		if (sdata->type != IEEE802154_DEV_MONITOR)
+		if (sdata->type != IEEE802154_DEV_MONITOR ||
+		    !netif_running(sdata->dev))
 			continue;
 
 		skb2 = skb_clone(skb, GFP_ATOMIC);
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index 03855b0677c..7f820a108a9 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -59,27 +59,28 @@ mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi)
 	skb->protocol = htons(ETH_P_IEEE802154);
 	skb_reset_mac_header(skb);
 
-	BUILD_BUG_ON(sizeof(struct ieee802154_mac_cb) > sizeof(skb->cb));
-
 	if (!(priv->hw.flags & IEEE802154_HW_OMIT_CKSUM)) {
 		u16 crc;
 
 		if (skb->len < 2) {
 			pr_debug("got invalid frame\n");
-			goto out;
+			goto fail;
 		}
 		crc = crc_ccitt(0, skb->data, skb->len);
 		if (crc) {
 			pr_debug("CRC mismatch\n");
-			goto out;
+			goto fail;
 		}
 		skb_trim(skb, skb->len - 2); /* CRC */
 	}
 
 	mac802154_monitors_rx(priv, skb);
 	mac802154_wpans_rx(priv, skb);
-out:
-	dev_kfree_skb(skb);
+
+	return;
+
+fail:
+	kfree_skb(skb);
 }
 
 static void mac802154_rx_worker(struct work_struct *work)
diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c
index 1df7a6a5738..3c3069fd697 100644
--- a/net/mac802154/wpan.c
+++ b/net/mac802154/wpan.c
@@ -35,6 +35,28 @@
 
 #include "mac802154.h"
 
+static int mac802154_wpan_update_llsec(struct net_device *dev)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_mlme_ops *ops = ieee802154_mlme_ops(dev);
+	int rc = 0;
+
+	if (ops->llsec) {
+		struct ieee802154_llsec_params params;
+		int changed = 0;
+
+		params.pan_id = priv->pan_id;
+		changed |= IEEE802154_LLSEC_PARAM_PAN_ID;
+
+		params.hwaddr = priv->extended_addr;
+		changed |= IEEE802154_LLSEC_PARAM_HWADDR;
+
+		rc = ops->llsec->set_params(dev, &params, changed);
+	}
+
+	return rc;
+}
+
 static int
 mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
@@ -81,7 +103,7 @@ mac802154_wpan_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		priv->pan_id = cpu_to_le16(sa->addr.pan_id);
 		priv->short_addr = cpu_to_le16(sa->addr.short_addr);
 
-		err = 0;
+		err = mac802154_wpan_update_llsec(dev);
 		break;
 	}
 
@@ -99,7 +121,7 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p)
 	/* FIXME: validate addr */
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
 	mac802154_dev_set_ieee_addr(dev);
-	return 0;
+	return mac802154_wpan_update_llsec(dev);
 }
 
 int mac802154_set_mac_params(struct net_device *dev,
@@ -124,7 +146,7 @@ void mac802154_get_mac_params(struct net_device *dev,
 	mutex_unlock(&priv->hw->slaves_mtx);
 }
 
-int mac802154_wpan_open(struct net_device *dev)
+static int mac802154_wpan_open(struct net_device *dev)
 {
 	int rc;
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
@@ -183,6 +205,38 @@ out:
 	return rc;
 }
 
+static int mac802154_set_header_security(struct mac802154_sub_if_data *priv,
+					 struct ieee802154_hdr *hdr,
+					 const struct ieee802154_mac_cb *cb)
+{
+	struct ieee802154_llsec_params params;
+	u8 level;
+
+	mac802154_llsec_get_params(&priv->sec, &params);
+
+	if (!params.enabled && cb->secen_override && cb->secen)
+		return -EINVAL;
+	if (!params.enabled ||
+	    (cb->secen_override && !cb->secen) ||
+	    !params.out_level)
+		return 0;
+	if (cb->seclevel_override && !cb->seclevel)
+		return -EINVAL;
+
+	level = cb->seclevel_override ? cb->seclevel : params.out_level;
+
+	hdr->fc.security_enabled = 1;
+	hdr->sec.level = level;
+	hdr->sec.key_id_mode = params.out_key.mode;
+	if (params.out_key.mode == IEEE802154_SCF_KEY_SHORT_INDEX)
+		hdr->sec.short_src = params.out_key.short_source;
+	else if (params.out_key.mode == IEEE802154_SCF_KEY_HW_INDEX)
+		hdr->sec.extended_src = params.out_key.extended_source;
+	hdr->sec.key_id = params.out_key.id;
+
+	return 0;
+}
+
 static int mac802154_header_create(struct sk_buff *skb,
 				   struct net_device *dev,
 				   unsigned short type,
@@ -192,15 +246,20 @@ static int mac802154_header_create(struct sk_buff *skb,
 {
 	struct ieee802154_hdr hdr;
 	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct ieee802154_mac_cb *cb = mac_cb(skb);
 	int hlen;
 
 	if (!daddr)
 		return -EINVAL;
 
 	memset(&hdr.fc, 0, sizeof(hdr.fc));
-	hdr.fc.type = mac_cb_type(skb);
-	hdr.fc.security_enabled = mac_cb_is_secen(skb);
-	hdr.fc.ack_request = mac_cb_is_ackreq(skb);
+	hdr.fc.type = cb->type;
+	hdr.fc.security_enabled = cb->secen;
+	hdr.fc.ack_request = cb->ackreq;
+	hdr.seq = ieee802154_mlme_ops(dev)->get_dsn(dev);
+
+	if (mac802154_set_header_security(priv, &hdr, cb) < 0)
+		return -EINVAL;
 
 	if (!saddr) {
 		spin_lock_bh(&priv->mib_lock);
@@ -231,7 +290,7 @@ static int mac802154_header_create(struct sk_buff *skb,
 	skb_reset_mac_header(skb);
 	skb->mac_len = hlen;
 
-	if (hlen + len + 2 > dev->mtu)
+	if (len > ieee802154_max_payload(&hdr))
 		return -EMSGSIZE;
 
 	return hlen;
@@ -257,6 +316,7 @@ mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mac802154_sub_if_data *priv;
 	u8 chan, page;
+	int rc;
 
 	priv = netdev_priv(dev);
 
@@ -272,6 +332,13 @@ mac802154_wpan_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
+	rc = mac802154_llsec_encrypt(&priv->sec, skb);
+	if (rc) {
+		pr_warn("encryption failed: %i\n", rc);
+		kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
 	skb->skb_iif = dev->ifindex;
 	dev->stats.tx_packets++;
 	dev->stats.tx_bytes += skb->len;
@@ -292,6 +359,15 @@ static const struct net_device_ops mac802154_wpan_ops = {
 	.ndo_set_mac_address	= mac802154_wpan_mac_addr,
 };
 
+static void mac802154_wpan_free(struct net_device *dev)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	mac802154_llsec_destroy(&priv->sec);
+
+	free_netdev(dev);
+}
+
 void mac802154_wpan_setup(struct net_device *dev)
 {
 	struct mac802154_sub_if_data *priv;
@@ -301,14 +377,14 @@ void mac802154_wpan_setup(struct net_device *dev)
 
 	dev->hard_header_len	= MAC802154_FRAME_HARD_HEADER_LEN;
 	dev->header_ops		= &mac802154_header_ops;
-	dev->needed_tailroom	= 2; /* FCS */
+	dev->needed_tailroom	= 2 + 16; /* FCS + MIC */
 	dev->mtu		= IEEE802154_MTU;
 	dev->tx_queue_len	= 300;
 	dev->type		= ARPHRD_IEEE802154;
 	dev->flags		= IFF_NOARP | IFF_BROADCAST;
 	dev->watchdog_timeo	= 0;
 
-	dev->destructor		= free_netdev;
+	dev->destructor		= mac802154_wpan_free;
 	dev->netdev_ops		= &mac802154_wpan_ops;
 	dev->ml_priv		= &mac802154_mlme_wpan;
 
@@ -319,6 +395,7 @@ void mac802154_wpan_setup(struct net_device *dev)
 	priv->page = 0;
 
 	spin_lock_init(&priv->mib_lock);
+	mutex_init(&priv->sec_mtx);
 
 	get_random_bytes(&priv->bsn, 1);
 	get_random_bytes(&priv->dsn, 1);
@@ -331,6 +408,8 @@ void mac802154_wpan_setup(struct net_device *dev)
 
 	priv->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
 	priv->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
+
+	mac802154_llsec_init(&priv->sec);
 }
 
 static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb)
@@ -339,9 +418,11 @@ static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb)
 }
 
 static int
-mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb)
+mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb,
+		      const struct ieee802154_hdr *hdr)
 {
 	__le16 span, sshort;
+	int rc;
 
 	pr_debug("getting packet via slave interface %s\n", sdata->dev->name);
 
@@ -388,15 +469,22 @@ mac802154_subif_frame(struct mac802154_sub_if_data *sdata, struct sk_buff *skb)
 
 	skb->dev = sdata->dev;
 
+	rc = mac802154_llsec_decrypt(&sdata->sec, skb);
+	if (rc) {
+		pr_debug("decryption failed: %i\n", rc);
+		kfree_skb(skb);
+		return NET_RX_DROP;
+	}
+
 	sdata->dev->stats.rx_packets++;
 	sdata->dev->stats.rx_bytes += skb->len;
 
-	switch (mac_cb_type(skb)) {
+	switch (mac_cb(skb)->type) {
 	case IEEE802154_FC_TYPE_DATA:
 		return mac802154_process_data(sdata->dev, skb);
 	default:
 		pr_warn("ieee802154: bad frame received (type = %d)\n",
-			mac_cb_type(skb));
+			mac_cb(skb)->type);
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
@@ -419,62 +507,58 @@ static void mac802154_print_addr(const char *name,
 	}
 }
 
-static int mac802154_parse_frame_start(struct sk_buff *skb)
+static int mac802154_parse_frame_start(struct sk_buff *skb,
+				       struct ieee802154_hdr *hdr)
 {
 	int hlen;
-	struct ieee802154_hdr hdr;
+	struct ieee802154_mac_cb *cb = mac_cb_init(skb);
 
-	hlen = ieee802154_hdr_pull(skb, &hdr);
+	hlen = ieee802154_hdr_pull(skb, hdr);
 	if (hlen < 0)
 		return -EINVAL;
 
 	skb->mac_len = hlen;
 
-	pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr.fc),
-		 hdr.seq);
-
-	mac_cb(skb)->flags = hdr.fc.type;
+	pr_debug("fc: %04x dsn: %02x\n", le16_to_cpup((__le16 *)&hdr->fc),
+		 hdr->seq);
 
-	if (hdr.fc.ack_request)
-		mac_cb(skb)->flags |= MAC_CB_FLAG_ACKREQ;
-	if (hdr.fc.security_enabled)
-		mac_cb(skb)->flags |= MAC_CB_FLAG_SECEN;
+	cb->type = hdr->fc.type;
+	cb->ackreq = hdr->fc.ack_request;
+	cb->secen = hdr->fc.security_enabled;
 
-	mac802154_print_addr("destination", &hdr.dest);
-	mac802154_print_addr("source", &hdr.source);
+	mac802154_print_addr("destination", &hdr->dest);
+	mac802154_print_addr("source", &hdr->source);
 
-	mac_cb(skb)->source = hdr.source;
-	mac_cb(skb)->dest = hdr.dest;
+	cb->source = hdr->source;
+	cb->dest = hdr->dest;
 
-	if (hdr.fc.security_enabled) {
+	if (hdr->fc.security_enabled) {
 		u64 key;
 
-		pr_debug("seclevel %i\n", hdr.sec.level);
+		pr_debug("seclevel %i\n", hdr->sec.level);
 
-		switch (hdr.sec.key_id_mode) {
+		switch (hdr->sec.key_id_mode) {
 		case IEEE802154_SCF_KEY_IMPLICIT:
 			pr_debug("implicit key\n");
 			break;
 
 		case IEEE802154_SCF_KEY_INDEX:
-			pr_debug("key %02x\n", hdr.sec.key_id);
+			pr_debug("key %02x\n", hdr->sec.key_id);
 			break;
 
 		case IEEE802154_SCF_KEY_SHORT_INDEX:
 			pr_debug("key %04x:%04x %02x\n",
-				 le32_to_cpu(hdr.sec.short_src) >> 16,
-				 le32_to_cpu(hdr.sec.short_src) & 0xffff,
-				 hdr.sec.key_id);
+				 le32_to_cpu(hdr->sec.short_src) >> 16,
+				 le32_to_cpu(hdr->sec.short_src) & 0xffff,
+				 hdr->sec.key_id);
 			break;
 
 		case IEEE802154_SCF_KEY_HW_INDEX:
-			key = swab64((__force u64) hdr.sec.extended_src);
+			key = swab64((__force u64) hdr->sec.extended_src);
 			pr_debug("key source %8phC %02x\n", &key,
-				 hdr.sec.key_id);
+				 hdr->sec.key_id);
 			break;
 		}
-
-		return -EINVAL;
 	}
 
 	return 0;
@@ -483,10 +567,10 @@ static int mac802154_parse_frame_start(struct sk_buff *skb)
 void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb)
 {
 	int ret;
-	struct sk_buff *sskb;
 	struct mac802154_sub_if_data *sdata;
+	struct ieee802154_hdr hdr;
 
-	ret = mac802154_parse_frame_start(skb);
+	ret = mac802154_parse_frame_start(skb, &hdr);
 	if (ret) {
 		pr_debug("got invalid frame\n");
 		return;
@@ -494,12 +578,16 @@ void mac802154_wpans_rx(struct mac802154_priv *priv, struct sk_buff *skb)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdata, &priv->slaves, list) {
-		if (sdata->type != IEEE802154_DEV_WPAN)
+		if (sdata->type != IEEE802154_DEV_WPAN ||
+		    !netif_running(sdata->dev))
 			continue;
 
-		sskb = skb_clone(skb, GFP_ATOMIC);
-		if (sskb)
-			mac802154_subif_frame(sdata, sskb);
+		mac802154_subif_frame(sdata, skb, &hdr);
+		skb = NULL;
+		break;
 	}
 	rcu_read_unlock();
+
+	if (skb)
+		kfree_skb(skb);
 }
diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c
index 851cd880b0c..6b38d083e1c 100644
--- a/net/mpls/mpls_gso.c
+++ b/net/mpls/mpls_gso.c
@@ -33,6 +33,7 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
 				  SKB_GSO_DODGY |
 				  SKB_GSO_TCP_ECN |
 				  SKB_GSO_GRE |
+				  SKB_GSO_GRE_CSUM |
 				  SKB_GSO_IPIP |
 				  SKB_GSO_MPLS)))
 		goto out;
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 117208321f1..ec8114fae50 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -271,10 +271,7 @@ ip_set_free(void *members)
 {
 	pr_debug("%p: free with %s\n", members,
 		 is_vmalloc_addr(members) ? "vfree" : "kfree");
-	if (is_vmalloc_addr(members))
-		vfree(members);
-	else
-		kfree(members);
+	kvfree(members);
 }
 EXPORT_SYMBOL_GPL(ip_set_free);
 
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index a8eb0a89326..610e19c0e13 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -797,7 +797,6 @@ static void ip_vs_conn_expire(unsigned long data)
 			ip_vs_control_del(cp);
 
 		if (cp->flags & IP_VS_CONN_F_NFCT) {
-			ip_vs_conn_drop_conntrack(cp);
 			/* Do not access conntracks during subsys cleanup
 			 * because nf_conntrack_find_get can not be used after
 			 * conntrack cleanup for the net.
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 3d2d2c8108c..e6836755c45 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -97,7 +97,7 @@ const char *ip_vs_proto_name(unsigned int proto)
 		return "ICMPv6";
 #endif
 	default:
-		sprintf(buf, "IP_%d", proto);
+		sprintf(buf, "IP_%u", proto);
 		return buf;
 	}
 }
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c42e83d2751..581a6584ed0 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3778,6 +3778,7 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
 	cancel_delayed_work_sync(&ipvs->defense_work);
 	cancel_work_sync(&ipvs->defense_work.work);
 	unregister_net_sysctl_table(ipvs->sysctl_hdr);
+	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 }
 
 #else
@@ -3840,7 +3841,6 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	ip_vs_trash_cleanup(net);
-	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 	ip_vs_control_net_cleanup_sysctl(net);
 	remove_proc_entry("ip_vs_stats_percpu", net->proc_net);
 	remove_proc_entry("ip_vs_stats", net->proc_net);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index c47444e4cf8..73ba1cc7a88 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -562,7 +562,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	ip_send_check(iph);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
 	rcu_read_unlock();
@@ -590,7 +590,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 		goto tx_error;
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
 	rcu_read_unlock();
@@ -684,7 +684,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	   MTU problem. */
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
 	rcu_read_unlock();
@@ -774,7 +774,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	   MTU problem. */
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
 	rcu_read_unlock();
@@ -883,10 +883,10 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->daddr		=	cp->daddr.ip;
 	iph->saddr		=	saddr;
 	iph->ttl		=	old_iph->ttl;
-	ip_select_ident(skb, &rt->dst, NULL);
+	ip_select_ident(skb, NULL);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ret = ip_vs_tunnel_xmit_prepare(skb, cp);
 	if (ret == NF_ACCEPT)
@@ -974,7 +974,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	iph->hop_limit		=	old_iph->hop_limit;
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ret = ip_vs_tunnel_xmit_prepare(skb, cp);
 	if (ret == NF_ACCEPT)
@@ -1023,7 +1023,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	ip_send_check(ip_hdr(skb));
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
 	rcu_read_unlock();
@@ -1060,7 +1060,7 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	}
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
 	rcu_read_unlock();
@@ -1157,7 +1157,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	ip_vs_nat_icmp(skb, pp, cp, 0);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
 	rcu_read_unlock();
@@ -1249,7 +1249,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	ip_vs_nat_icmp_v6(skb, pp, cp, 0);
 
 	/* Another hack: avoid icmp_send in ip_fragment */
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
 	rcu_read_unlock();
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 58579634427..300ed1eec72 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -597,6 +597,9 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */
 #endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	       + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */
+#endif
 	       + ctnetlink_proto_size(ct)
 	       + ctnetlink_label_size(ct)
 	       ;
@@ -1150,7 +1153,7 @@ static int ctnetlink_done_list(struct netlink_callback *cb)
 static int
 ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying)
 {
-	struct nf_conn *ct, *last = NULL;
+	struct nf_conn *ct, *last;
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
@@ -1163,8 +1166,7 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
 	if (cb->args[2])
 		return 0;
 
-	if (cb->args[0] == nr_cpu_ids)
-		return 0;
+	last = (struct nf_conn *)cb->args[1];
 
 	for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) {
 		struct ct_pcpu *pcpu;
@@ -1174,7 +1176,6 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
 
 		pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
 		spin_lock_bh(&pcpu->lock);
-		last = (struct nf_conn *)cb->args[1];
 		list = dying ? &pcpu->dying : &pcpu->unconfirmed;
 restart:
 		hlist_nulls_for_each_entry(h, n, list, hnnode) {
@@ -1193,7 +1194,9 @@ restart:
 						  ct);
 			rcu_read_unlock();
 			if (res < 0) {
-				nf_conntrack_get(&ct->ct_general);
+				if (!atomic_inc_not_zero(&ct->ct_general.use))
+					continue;
+				cb->args[0] = cpu;
 				cb->args[1] = (unsigned long)ct;
 				spin_unlock_bh(&pcpu->lock);
 				goto out;
@@ -1202,10 +1205,10 @@ restart:
 		if (cb->args[1]) {
 			cb->args[1] = 0;
 			goto restart;
-		} else
-			cb->args[2] = 1;
+		}
 		spin_unlock_bh(&pcpu->lock);
 	}
+	cb->args[2] = 1;
 out:
 	if (last)
 		nf_ct_put(last);
@@ -2040,6 +2043,9 @@ ctnetlink_nfqueue_build_size(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */
 #endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	       + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */
+#endif
 	       + ctnetlink_proto_size(ct)
 	       ;
 }
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 52ca952b802..a49907b1dab 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -358,6 +358,19 @@ out:
 	rcu_read_unlock();
 }
 
+struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct)
+{
+	struct nf_conn_nat *nat = nfct_nat(ct);
+	if (nat)
+		return nat;
+
+	if (!nf_ct_is_confirmed(ct))
+		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
+
+	return nat;
+}
+EXPORT_SYMBOL_GPL(nf_ct_nat_ext_add);
+
 unsigned int
 nf_nat_setup_info(struct nf_conn *ct,
 		  const struct nf_nat_range *range,
@@ -368,14 +381,9 @@ nf_nat_setup_info(struct nf_conn *ct,
 	struct nf_conn_nat *nat;
 
 	/* nat helper or nfctnetlink also setup binding */
-	nat = nfct_nat(ct);
-	if (!nat) {
-		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
-		if (nat == NULL) {
-			pr_debug("failed to add NAT extension\n");
-			return NF_ACCEPT;
-		}
-	}
+	nat = nf_ct_nat_ext_add(ct);
+	if (nat == NULL)
+		return NF_ACCEPT;
 
 	NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC ||
 		     maniptype == NF_NAT_MANIP_DST);
@@ -517,6 +525,39 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 	return i->status & IPS_NAT_MASK ? 1 : 0;
 }
 
+static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
+{
+	struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (nf_nat_proto_remove(ct, data))
+		return 1;
+
+	if (!nat || !nat->ct)
+		return 0;
+
+	/* This netns is being destroyed, and conntrack has nat null binding.
+	 * Remove it from bysource hash, as the table will be freed soon.
+	 *
+	 * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
+	 * will delete entry from already-freed table.
+	 */
+	if (!del_timer(&ct->timeout))
+		return 1;
+
+	spin_lock_bh(&nf_nat_lock);
+	hlist_del_rcu(&nat->bysource);
+	ct->status &= ~IPS_NAT_DONE_MASK;
+	nat->ct = NULL;
+	spin_unlock_bh(&nf_nat_lock);
+
+	add_timer(&ct->timeout);
+
+	/* don't delete conntrack.  Although that would make things a lot
+	 * simpler, we'd end up flushing all conntracks on nat rmmod.
+	 */
+	return 0;
+}
+
 static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
 {
 	struct nf_nat_proto_clean clean = {
@@ -787,7 +828,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	struct nf_nat_proto_clean clean = {};
 
-	nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean, 0, 0);
+	nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0);
 	synchronize_rcu();
 	nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
 }
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3fd159db9f0..8746ff9a835 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -35,7 +35,7 @@ int nft_register_afinfo(struct net *net, struct nft_af_info *afi)
 {
 	INIT_LIST_HEAD(&afi->tables);
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_add_tail(&afi->list, &net->nft.af_info);
+	list_add_tail_rcu(&afi->list, &net->nft.af_info);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	return 0;
 }
@@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(nft_register_afinfo);
 void nft_unregister_afinfo(struct nft_af_info *afi)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_del(&afi->list);
+	list_del_rcu(&afi->list);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
 EXPORT_SYMBOL_GPL(nft_unregister_afinfo);
@@ -88,6 +88,45 @@ nf_tables_afinfo_lookup(struct net *net, int family, bool autoload)
 	return ERR_PTR(-EAFNOSUPPORT);
 }
 
+static void nft_ctx_init(struct nft_ctx *ctx,
+			 const struct sk_buff *skb,
+			 const struct nlmsghdr *nlh,
+			 struct nft_af_info *afi,
+			 struct nft_table *table,
+			 struct nft_chain *chain,
+			 const struct nlattr * const *nla)
+{
+	ctx->net	= sock_net(skb->sk);
+	ctx->afi	= afi;
+	ctx->table	= table;
+	ctx->chain	= chain;
+	ctx->nla   	= nla;
+	ctx->portid	= NETLINK_CB(skb).portid;
+	ctx->report	= nlmsg_report(nlh);
+	ctx->seq	= nlh->nlmsg_seq;
+}
+
+static struct nft_trans *nft_trans_alloc(struct nft_ctx *ctx, int msg_type,
+					 u32 size)
+{
+	struct nft_trans *trans;
+
+	trans = kzalloc(sizeof(struct nft_trans) + size, GFP_KERNEL);
+	if (trans == NULL)
+		return NULL;
+
+	trans->msg_type = msg_type;
+	trans->ctx	= *ctx;
+
+	return trans;
+}
+
+static void nft_trans_destroy(struct nft_trans *trans)
+{
+	list_del(&trans->list);
+	kfree(trans);
+}
+
 /*
  * Tables
  */
@@ -197,20 +236,13 @@ nla_put_failure:
 	return -1;
 }
 
-static int nf_tables_table_notify(const struct sk_buff *oskb,
-				  const struct nlmsghdr *nlh,
-				  const struct nft_table *table,
-				  int event, int family)
+static int nf_tables_table_notify(const struct nft_ctx *ctx, int event)
 {
 	struct sk_buff *skb;
-	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
-	u32 seq = nlh ? nlh->nlmsg_seq : 0;
-	struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
-	bool report;
 	int err;
 
-	report = nlh ? nlmsg_report(nlh) : false;
-	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+	if (!ctx->report &&
+	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return 0;
 
 	err = -ENOBUFS;
@@ -218,18 +250,20 @@ static int nf_tables_table_notify(const struct sk_buff *oskb,
 	if (skb == NULL)
 		goto err;
 
-	err = nf_tables_fill_table_info(skb, portid, seq, event, 0,
-					family, table);
+	err = nf_tables_fill_table_info(skb, ctx->portid, ctx->seq, event, 0,
+					ctx->afi->family, ctx->table);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
-			     GFP_KERNEL);
+	err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+			     ctx->report, GFP_KERNEL);
 err:
-	if (err < 0)
-		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	if (err < 0) {
+		nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+				  err);
+	}
 	return err;
 }
 
@@ -243,11 +277,14 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	list_for_each_entry(afi, &net->nft.af_info, list) {
+	rcu_read_lock();
+	cb->seq = net->nft.base_seq;
+
+	list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
 			continue;
 
-		list_for_each_entry(table, &afi->tables, list) {
+		list_for_each_entry_rcu(table, &afi->tables, list) {
 			if (idx < s_idx)
 				goto cont;
 			if (idx > s_idx)
@@ -260,15 +297,21 @@ static int nf_tables_dump_tables(struct sk_buff *skb,
 						      NLM_F_MULTI,
 						      afi->family, table) < 0)
 				goto done;
+
+			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 			idx++;
 		}
 	}
 done:
+	rcu_read_unlock();
 	cb->args[0] = idx;
 	return skb->len;
 }
 
+/* Internal table flags */
+#define NFT_TABLE_INACTIVE	(1 << 15)
+
 static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
@@ -295,6 +338,8 @@ static int nf_tables_gettable(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2)
@@ -343,7 +388,7 @@ err:
 	return err;
 }
 
-static int nf_tables_table_disable(const struct nft_af_info *afi,
+static void nf_tables_table_disable(const struct nft_af_info *afi,
 				   struct nft_table *table)
 {
 	struct nft_chain *chain;
@@ -353,45 +398,66 @@ static int nf_tables_table_disable(const struct nft_af_info *afi,
 			nf_unregister_hooks(nft_base_chain(chain)->ops,
 					    afi->nops);
 	}
-
-	return 0;
 }
 
-static int nf_tables_updtable(struct sock *nlsk, struct sk_buff *skb,
-			      const struct nlmsghdr *nlh,
-			      const struct nlattr * const nla[],
-			      struct nft_af_info *afi, struct nft_table *table)
+static int nf_tables_updtable(struct nft_ctx *ctx)
 {
-	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	int family = nfmsg->nfgen_family, ret = 0;
+	struct nft_trans *trans;
+	u32 flags;
+	int ret = 0;
 
-	if (nla[NFTA_TABLE_FLAGS]) {
-		u32 flags;
+	if (!ctx->nla[NFTA_TABLE_FLAGS])
+		return 0;
 
-		flags = ntohl(nla_get_be32(nla[NFTA_TABLE_FLAGS]));
-		if (flags & ~NFT_TABLE_F_DORMANT)
-			return -EINVAL;
+	flags = ntohl(nla_get_be32(ctx->nla[NFTA_TABLE_FLAGS]));
+	if (flags & ~NFT_TABLE_F_DORMANT)
+		return -EINVAL;
+
+	if (flags == ctx->table->flags)
+		return 0;
 
-		if ((flags & NFT_TABLE_F_DORMANT) &&
-		    !(table->flags & NFT_TABLE_F_DORMANT)) {
-			ret = nf_tables_table_disable(afi, table);
-			if (ret >= 0)
-				table->flags |= NFT_TABLE_F_DORMANT;
-		} else if (!(flags & NFT_TABLE_F_DORMANT) &&
-			   table->flags & NFT_TABLE_F_DORMANT) {
-			ret = nf_tables_table_enable(afi, table);
-			if (ret >= 0)
-				table->flags &= ~NFT_TABLE_F_DORMANT;
+	trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE,
+				sizeof(struct nft_trans_table));
+	if (trans == NULL)
+		return -ENOMEM;
+
+	if ((flags & NFT_TABLE_F_DORMANT) &&
+	    !(ctx->table->flags & NFT_TABLE_F_DORMANT)) {
+		nft_trans_table_enable(trans) = false;
+	} else if (!(flags & NFT_TABLE_F_DORMANT) &&
+		   ctx->table->flags & NFT_TABLE_F_DORMANT) {
+		ret = nf_tables_table_enable(ctx->afi, ctx->table);
+		if (ret >= 0) {
+			ctx->table->flags &= ~NFT_TABLE_F_DORMANT;
+			nft_trans_table_enable(trans) = true;
 		}
-		if (ret < 0)
-			goto err;
 	}
+	if (ret < 0)
+		goto err;
 
-	nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family);
+	nft_trans_table_update(trans) = true;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+	return 0;
 err:
+	nft_trans_destroy(trans);
 	return ret;
 }
 
+static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type)
+{
+	struct nft_trans *trans;
+
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_table));
+	if (trans == NULL)
+		return -ENOMEM;
+
+	if (msg_type == NFT_MSG_NEWTABLE)
+		ctx->table->flags |= NFT_TABLE_INACTIVE;
+
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+	return 0;
+}
+
 static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
@@ -403,6 +469,8 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 	u32 flags = 0;
+	struct nft_ctx ctx;
+	int err;
 
 	afi = nf_tables_afinfo_lookup(net, family, true);
 	if (IS_ERR(afi))
@@ -417,11 +485,15 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	}
 
 	if (table != NULL) {
+		if (table->flags & NFT_TABLE_INACTIVE)
+			return -ENOENT;
 		if (nlh->nlmsg_flags & NLM_F_EXCL)
 			return -EEXIST;
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
-		return nf_tables_updtable(nlsk, skb, nlh, nla, afi, table);
+
+		nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+		return nf_tables_updtable(&ctx);
 	}
 
 	if (nla[NFTA_TABLE_FLAGS]) {
@@ -444,8 +516,14 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	INIT_LIST_HEAD(&table->sets);
 	table->flags = flags;
 
-	list_add_tail(&table->list, &afi->tables);
-	nf_tables_table_notify(skb, nlh, table, NFT_MSG_NEWTABLE, family);
+	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+	err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE);
+	if (err < 0) {
+		kfree(table);
+		module_put(afi->owner);
+		return err;
+	}
+	list_add_tail_rcu(&table->list, &afi->tables);
 	return 0;
 }
 
@@ -457,7 +535,8 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_af_info *afi;
 	struct nft_table *table;
 	struct net *net = sock_net(skb->sk);
-	int family = nfmsg->nfgen_family;
+	int family = nfmsg->nfgen_family, err;
+	struct nft_ctx ctx;
 
 	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
@@ -466,17 +545,28 @@ static int nf_tables_deltable(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_TABLE_NAME]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
-
-	if (!list_empty(&table->chains) || !list_empty(&table->sets))
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
+	if (table->use > 0)
 		return -EBUSY;
 
-	list_del(&table->list);
-	nf_tables_table_notify(skb, nlh, table, NFT_MSG_DELTABLE, family);
-	kfree(table);
-	module_put(afi->owner);
+	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
+	err = nft_trans_table_add(&ctx, NFT_MSG_DELTABLE);
+	if (err < 0)
+		return err;
+
+	list_del_rcu(&table->list);
 	return 0;
 }
 
+static void nf_tables_table_destroy(struct nft_ctx *ctx)
+{
+	BUG_ON(ctx->table->use > 0);
+
+	kfree(ctx->table);
+	module_put(ctx->afi->owner);
+}
+
 int nft_register_chain_type(const struct nf_chain_type *ctype)
 {
 	int err = 0;
@@ -541,7 +631,7 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
 	[NFTA_CHAIN_HOOK]	= { .type = NLA_NESTED },
 	[NFTA_CHAIN_POLICY]	= { .type = NLA_U32 },
-	[NFTA_CHAIN_TYPE]	= { .type = NLA_NUL_STRING },
+	[NFTA_CHAIN_TYPE]	= { .type = NLA_STRING },
 	[NFTA_CHAIN_COUNTERS]	= { .type = NLA_NESTED },
 };
 
@@ -554,13 +644,20 @@ static int nft_dump_stats(struct sk_buff *skb, struct nft_stats __percpu *stats)
 {
 	struct nft_stats *cpu_stats, total;
 	struct nlattr *nest;
+	unsigned int seq;
+	u64 pkts, bytes;
 	int cpu;
 
 	memset(&total, 0, sizeof(total));
 	for_each_possible_cpu(cpu) {
 		cpu_stats = per_cpu_ptr(stats, cpu);
-		total.pkts += cpu_stats->pkts;
-		total.bytes += cpu_stats->bytes;
+		do {
+			seq = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
+			pkts = cpu_stats->pkts;
+			bytes = cpu_stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, seq));
+		total.pkts += pkts;
+		total.bytes += bytes;
 	}
 	nest = nla_nest_start(skb, NFTA_CHAIN_COUNTERS);
 	if (nest == NULL)
@@ -637,21 +734,13 @@ nla_put_failure:
 	return -1;
 }
 
-static int nf_tables_chain_notify(const struct sk_buff *oskb,
-				  const struct nlmsghdr *nlh,
-				  const struct nft_table *table,
-				  const struct nft_chain *chain,
-				  int event, int family)
+static int nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
 {
 	struct sk_buff *skb;
-	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
-	struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
-	u32 seq = nlh ? nlh->nlmsg_seq : 0;
-	bool report;
 	int err;
 
-	report = nlh ? nlmsg_report(nlh) : false;
-	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+	if (!ctx->report &&
+	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return 0;
 
 	err = -ENOBUFS;
@@ -659,18 +748,21 @@ static int nf_tables_chain_notify(const struct sk_buff *oskb,
 	if (skb == NULL)
 		goto err;
 
-	err = nf_tables_fill_chain_info(skb, portid, seq, event, 0, family,
-					table, chain);
+	err = nf_tables_fill_chain_info(skb, ctx->portid, ctx->seq, event, 0,
+					ctx->afi->family, ctx->table,
+					ctx->chain);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
-			     GFP_KERNEL);
+	err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+			     ctx->report, GFP_KERNEL);
 err:
-	if (err < 0)
-		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	if (err < 0) {
+		nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+				  err);
+	}
 	return err;
 }
 
@@ -685,12 +777,15 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
 
-	list_for_each_entry(afi, &net->nft.af_info, list) {
+	rcu_read_lock();
+	cb->seq = net->nft.base_seq;
+
+	list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
 			continue;
 
-		list_for_each_entry(table, &afi->tables, list) {
-			list_for_each_entry(chain, &table->chains, list) {
+		list_for_each_entry_rcu(table, &afi->tables, list) {
+			list_for_each_entry_rcu(chain, &table->chains, list) {
 				if (idx < s_idx)
 					goto cont;
 				if (idx > s_idx)
@@ -702,17 +797,19 @@ static int nf_tables_dump_chains(struct sk_buff *skb,
 							      NLM_F_MULTI,
 							      afi->family, table, chain) < 0)
 					goto done;
+
+				nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 				idx++;
 			}
 		}
 	}
 done:
+	rcu_read_unlock();
 	cb->args[0] = idx;
 	return skb->len;
 }
 
-
 static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
@@ -740,10 +837,14 @@ static int nf_tables_getchain(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
 	chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]);
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
+	if (chain->flags & NFT_CHAIN_INACTIVE)
+		return -ENOENT;
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2)
@@ -767,8 +868,7 @@ static const struct nla_policy nft_counter_policy[NFTA_COUNTER_MAX + 1] = {
 	[NFTA_COUNTER_BYTES]	= { .type = NLA_U64 },
 };
 
-static int
-nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr)
+static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr)
 {
 	struct nlattr *tb[NFTA_COUNTER_MAX+1];
 	struct nft_stats __percpu *newstats;
@@ -777,14 +877,14 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr)
 
 	err = nla_parse_nested(tb, NFTA_COUNTER_MAX, attr, nft_counter_policy);
 	if (err < 0)
-		return err;
+		return ERR_PTR(err);
 
 	if (!tb[NFTA_COUNTER_BYTES] || !tb[NFTA_COUNTER_PACKETS])
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
-	newstats = alloc_percpu(struct nft_stats);
+	newstats = netdev_alloc_pcpu_stats(struct nft_stats);
 	if (newstats == NULL)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	/* Restore old counters on this cpu, no problem. Per-cpu statistics
 	 * are not exposed to userspace.
@@ -793,6 +893,12 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr)
 	stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
 	stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
 
+	return newstats;
+}
+
+static void nft_chain_stats_replace(struct nft_base_chain *chain,
+				    struct nft_stats __percpu *newstats)
+{
 	if (chain->stats) {
 		struct nft_stats __percpu *oldstats =
 				nft_dereference(chain->stats);
@@ -802,17 +908,43 @@ nf_tables_counters(struct nft_base_chain *chain, const struct nlattr *attr)
 		free_percpu(oldstats);
 	} else
 		rcu_assign_pointer(chain->stats, newstats);
+}
+
+static int nft_trans_chain_add(struct nft_ctx *ctx, int msg_type)
+{
+	struct nft_trans *trans;
+
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_chain));
+	if (trans == NULL)
+		return -ENOMEM;
+
+	if (msg_type == NFT_MSG_NEWCHAIN)
+		ctx->chain->flags |= NFT_CHAIN_INACTIVE;
 
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
 }
 
+static void nf_tables_chain_destroy(struct nft_chain *chain)
+{
+	BUG_ON(chain->use > 0);
+
+	if (chain->flags & NFT_BASE_CHAIN) {
+		module_put(nft_base_chain(chain)->type->owner);
+		free_percpu(nft_base_chain(chain)->stats);
+		kfree(nft_base_chain(chain));
+	} else {
+		kfree(chain);
+	}
+}
+
 static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlmsghdr *nlh,
 			      const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nlattr * uninitialized_var(name);
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_base_chain *basechain = NULL;
@@ -822,8 +954,10 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	u8 policy = NF_ACCEPT;
 	u64 handle = 0;
 	unsigned int i;
+	struct nft_stats __percpu *stats;
 	int err;
 	bool create;
+	struct nft_ctx ctx;
 
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
@@ -869,6 +1003,11 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	}
 
 	if (chain != NULL) {
+		struct nft_stats *stats = NULL;
+		struct nft_trans *trans;
+
+		if (chain->flags & NFT_CHAIN_INACTIVE)
+			return -ENOENT;
 		if (nlh->nlmsg_flags & NLM_F_EXCL)
 			return -EEXIST;
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
@@ -882,19 +1021,31 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			if (!(chain->flags & NFT_BASE_CHAIN))
 				return -EOPNOTSUPP;
 
-			err = nf_tables_counters(nft_base_chain(chain),
-						 nla[NFTA_CHAIN_COUNTERS]);
-			if (err < 0)
-				return err;
+			stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
+			if (IS_ERR(stats))
+				return PTR_ERR(stats);
 		}
 
-		if (nla[NFTA_CHAIN_POLICY])
-			nft_base_chain(chain)->policy = policy;
+		nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+		trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN,
+					sizeof(struct nft_trans_chain));
+		if (trans == NULL)
+			return -ENOMEM;
+
+		nft_trans_chain_stats(trans) = stats;
+		nft_trans_chain_update(trans) = true;
 
-		if (nla[NFTA_CHAIN_HANDLE] && name)
-			nla_strlcpy(chain->name, name, NFT_CHAIN_MAXNAMELEN);
+		if (nla[NFTA_CHAIN_POLICY])
+			nft_trans_chain_policy(trans) = policy;
+		else
+			nft_trans_chain_policy(trans) = -1;
 
-		goto notify;
+		if (nla[NFTA_CHAIN_HANDLE] && name) {
+			nla_strlcpy(nft_trans_chain_name(trans), name,
+				    NFT_CHAIN_MAXNAMELEN);
+		}
+		list_add_tail(&trans->list, &net->nft.commit_list);
+		return 0;
 	}
 
 	if (table->use == UINT_MAX)
@@ -939,23 +1090,21 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			return -ENOMEM;
 
 		if (nla[NFTA_CHAIN_COUNTERS]) {
-			err = nf_tables_counters(basechain,
-						 nla[NFTA_CHAIN_COUNTERS]);
-			if (err < 0) {
+			stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
+			if (IS_ERR(stats)) {
 				module_put(type->owner);
 				kfree(basechain);
-				return err;
+				return PTR_ERR(stats);
 			}
+			basechain->stats = stats;
 		} else {
-			struct nft_stats __percpu *newstats;
-
-			newstats = alloc_percpu(struct nft_stats);
-			if (newstats == NULL) {
+			stats = netdev_alloc_pcpu_stats(struct nft_stats);
+			if (IS_ERR(stats)) {
 				module_put(type->owner);
 				kfree(basechain);
-				return -ENOMEM;
+				return PTR_ERR(stats);
 			}
-			rcu_assign_pointer(basechain->stats, newstats);
+			rcu_assign_pointer(basechain->stats, stats);
 		}
 
 		basechain->type = type;
@@ -992,31 +1141,27 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
 	    chain->flags & NFT_BASE_CHAIN) {
 		err = nf_register_hooks(nft_base_chain(chain)->ops, afi->nops);
-		if (err < 0) {
-			module_put(basechain->type->owner);
-			free_percpu(basechain->stats);
-			kfree(basechain);
-			return err;
-		}
+		if (err < 0)
+			goto err1;
 	}
-	list_add_tail(&chain->list, &table->chains);
-	table->use++;
-notify:
-	nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_NEWCHAIN,
-			       family);
-	return 0;
-}
 
-static void nf_tables_chain_destroy(struct nft_chain *chain)
-{
-	BUG_ON(chain->use > 0);
+	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+	err = nft_trans_chain_add(&ctx, NFT_MSG_NEWCHAIN);
+	if (err < 0)
+		goto err2;
 
-	if (chain->flags & NFT_BASE_CHAIN) {
-		module_put(nft_base_chain(chain)->type->owner);
-		free_percpu(nft_base_chain(chain)->stats);
-		kfree(nft_base_chain(chain));
-	} else
-		kfree(chain);
+	table->use++;
+	list_add_tail_rcu(&chain->list, &table->chains);
+	return 0;
+err2:
+	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
+	    chain->flags & NFT_BASE_CHAIN) {
+		nf_unregister_hooks(nft_base_chain(chain)->ops,
+				    afi->nops);
+	}
+err1:
+	nf_tables_chain_destroy(chain);
+	return err;
 }
 
 static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
@@ -1024,11 +1169,13 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 			      const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
+	struct nft_ctx ctx;
+	int err;
 
 	afi = nf_tables_afinfo_lookup(net, family, false);
 	if (IS_ERR(afi))
@@ -1037,48 +1184,27 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_CHAIN_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
 	chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME]);
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
-
-	if (!list_empty(&chain->rules) || chain->use > 0)
+	if (chain->flags & NFT_CHAIN_INACTIVE)
+		return -ENOENT;
+	if (chain->use > 0)
 		return -EBUSY;
 
-	list_del(&chain->list);
-	table->use--;
-
-	if (!(table->flags & NFT_TABLE_F_DORMANT) &&
-	    chain->flags & NFT_BASE_CHAIN)
-		nf_unregister_hooks(nft_base_chain(chain)->ops, afi->nops);
-
-	nf_tables_chain_notify(skb, nlh, table, chain, NFT_MSG_DELCHAIN,
-			       family);
-
-	/* Make sure all rule references are gone before this is released */
-	synchronize_rcu();
+	nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
+	err = nft_trans_chain_add(&ctx, NFT_MSG_DELCHAIN);
+	if (err < 0)
+		return err;
 
-	nf_tables_chain_destroy(chain);
+	table->use--;
+	list_del_rcu(&chain->list);
 	return 0;
 }
 
-static void nft_ctx_init(struct nft_ctx *ctx,
-			 const struct sk_buff *skb,
-			 const struct nlmsghdr *nlh,
-			 const struct nft_af_info *afi,
-			 const struct nft_table *table,
-			 const struct nft_chain *chain,
-			 const struct nlattr * const *nla)
-{
-	ctx->net   = sock_net(skb->sk);
-	ctx->skb   = skb;
-	ctx->nlh   = nlh;
-	ctx->afi   = afi;
-	ctx->table = table;
-	ctx->chain = chain;
-	ctx->nla   = nla;
-}
-
 /*
  * Expressions
  */
@@ -1093,7 +1219,10 @@ static void nft_ctx_init(struct nft_ctx *ctx,
 int nft_register_expr(struct nft_expr_type *type)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_add_tail(&type->list, &nf_tables_expressions);
+	if (type->family == NFPROTO_UNSPEC)
+		list_add_tail_rcu(&type->list, &nf_tables_expressions);
+	else
+		list_add_rcu(&type->list, &nf_tables_expressions);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	return 0;
 }
@@ -1108,7 +1237,7 @@ EXPORT_SYMBOL_GPL(nft_register_expr);
 void nft_unregister_expr(struct nft_expr_type *type)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_del(&type->list);
+	list_del_rcu(&type->list);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
 EXPORT_SYMBOL_GPL(nft_unregister_expr);
@@ -1361,22 +1490,15 @@ nla_put_failure:
 	return -1;
 }
 
-static int nf_tables_rule_notify(const struct sk_buff *oskb,
-				 const struct nlmsghdr *nlh,
-				 const struct nft_table *table,
-				 const struct nft_chain *chain,
+static int nf_tables_rule_notify(const struct nft_ctx *ctx,
 				 const struct nft_rule *rule,
-				 int event, u32 flags, int family)
+				 int event)
 {
 	struct sk_buff *skb;
-	u32 portid = NETLINK_CB(oskb).portid;
-	struct net *net = oskb ? sock_net(oskb->sk) : &init_net;
-	u32 seq = nlh->nlmsg_seq;
-	bool report;
 	int err;
 
-	report = nlmsg_report(nlh);
-	if (!report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+	if (!ctx->report &&
+	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return 0;
 
 	err = -ENOBUFS;
@@ -1384,18 +1506,21 @@ static int nf_tables_rule_notify(const struct sk_buff *oskb,
 	if (skb == NULL)
 		goto err;
 
-	err = nf_tables_fill_rule_info(skb, portid, seq, event, flags,
-				       family, table, chain, rule);
+	err = nf_tables_fill_rule_info(skb, ctx->portid, ctx->seq, event, 0,
+				       ctx->afi->family, ctx->table,
+				       ctx->chain, rule);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report,
-			     GFP_KERNEL);
+	err = nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+			     ctx->report, GFP_KERNEL);
 err:
-	if (err < 0)
-		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	if (err < 0) {
+		nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES,
+				  err);
+	}
 	return err;
 }
 
@@ -1445,16 +1570,17 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 	unsigned int idx = 0, s_idx = cb->args[0];
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
-	u8 genctr = ACCESS_ONCE(net->nft.genctr);
-	u8 gencursor = ACCESS_ONCE(net->nft.gencursor);
 
-	list_for_each_entry(afi, &net->nft.af_info, list) {
+	rcu_read_lock();
+	cb->seq = net->nft.base_seq;
+
+	list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
 		if (family != NFPROTO_UNSPEC && family != afi->family)
 			continue;
 
-		list_for_each_entry(table, &afi->tables, list) {
-			list_for_each_entry(chain, &table->chains, list) {
-				list_for_each_entry(rule, &chain->rules, list) {
+		list_for_each_entry_rcu(table, &afi->tables, list) {
+			list_for_each_entry_rcu(chain, &table->chains, list) {
+				list_for_each_entry_rcu(rule, &chain->rules, list) {
 					if (!nft_rule_is_active(net, rule))
 						goto cont;
 					if (idx < s_idx)
@@ -1468,6 +1594,8 @@ static int nf_tables_dump_rules(struct sk_buff *skb,
 								      NLM_F_MULTI | NLM_F_APPEND,
 								      afi->family, table, chain, rule) < 0)
 						goto done;
+
+					nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 					idx++;
 				}
@@ -1475,9 +1603,7 @@ cont:
 		}
 	}
 done:
-	/* Invalidate this dump, a transition to the new generation happened */
-	if (gencursor != net->nft.gencursor || genctr != net->nft.genctr)
-		return -EBUSY;
+	rcu_read_unlock();
 
 	cb->args[0] = idx;
 	return skb->len;
@@ -1511,10 +1637,14 @@ static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
 	chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
+	if (chain->flags & NFT_CHAIN_INACTIVE)
+		return -ENOENT;
 
 	rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
 	if (IS_ERR(rule))
@@ -1554,37 +1684,36 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	kfree(rule);
 }
 
-#define NFT_RULE_MAXEXPRS	128
-
-static struct nft_expr_info *info;
-
-static struct nft_rule_trans *
-nf_tables_trans_add(struct nft_ctx *ctx, struct nft_rule *rule)
+static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type,
+					    struct nft_rule *rule)
 {
-	struct nft_rule_trans *rupd;
+	struct nft_trans *trans;
 
-	rupd = kmalloc(sizeof(struct nft_rule_trans), GFP_KERNEL);
-	if (rupd == NULL)
-	       return NULL;
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_rule));
+	if (trans == NULL)
+		return NULL;
 
-	rupd->ctx = *ctx;
-	rupd->rule = rule;
-	list_add_tail(&rupd->list, &ctx->net->nft.commit_list);
+	nft_trans_rule(trans) = rule;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 
-	return rupd;
+	return trans;
 }
 
+#define NFT_RULE_MAXEXPRS	128
+
+static struct nft_expr_info *info;
+
 static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 			     const struct nlmsghdr *nlh,
 			     const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct net *net = sock_net(skb->sk);
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule, *old_rule = NULL;
-	struct nft_rule_trans *repl = NULL;
+	struct nft_trans *trans = NULL;
 	struct nft_expr *expr;
 	struct nft_ctx ctx;
 	struct nlattr *tmp;
@@ -1623,6 +1752,9 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 		if (!create || nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EINVAL;
 		handle = nf_tables_alloc_handle(table);
+
+		if (chain->use == UINT_MAX)
+			return -EOVERFLOW;
 	}
 
 	if (nla[NFTA_RULE_POSITION]) {
@@ -1682,13 +1814,15 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
 		if (nft_rule_is_active_next(net, old_rule)) {
-			repl = nf_tables_trans_add(&ctx, old_rule);
-			if (repl == NULL) {
+			trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
+						   old_rule);
+			if (trans == NULL) {
 				err = -ENOMEM;
 				goto err2;
 			}
 			nft_rule_disactivate_next(net, old_rule);
-			list_add_tail(&rule->list, &old_rule->list);
+			chain->use--;
+			list_add_tail_rcu(&rule->list, &old_rule->list);
 		} else {
 			err = -ENOENT;
 			goto err2;
@@ -1705,19 +1839,20 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 			list_add_rcu(&rule->list, &chain->rules);
 	}
 
-	if (nf_tables_trans_add(&ctx, rule) == NULL) {
+	if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
 		err = -ENOMEM;
 		goto err3;
 	}
+	chain->use++;
 	return 0;
 
 err3:
 	list_del_rcu(&rule->list);
-	if (repl) {
-		list_del_rcu(&repl->rule->list);
-		list_del(&repl->list);
-		nft_rule_clear(net, repl->rule);
-		kfree(repl);
+	if (trans) {
+		list_del_rcu(&nft_trans_rule(trans)->list);
+		nft_rule_clear(net, nft_trans_rule(trans));
+		nft_trans_destroy(trans);
+		chain->use++;
 	}
 err2:
 	nf_tables_rule_destroy(&ctx, rule);
@@ -1734,9 +1869,10 @@ nf_tables_delrule_one(struct nft_ctx *ctx, struct nft_rule *rule)
 {
 	/* You cannot delete the same rule twice */
 	if (nft_rule_is_active_next(ctx->net, rule)) {
-		if (nf_tables_trans_add(ctx, rule) == NULL)
+		if (nft_trans_rule_add(ctx, NFT_MSG_DELRULE, rule) == NULL)
 			return -ENOMEM;
 		nft_rule_disactivate_next(ctx->net, rule);
+		ctx->chain->use--;
 		return 0;
 	}
 	return -ENOENT;
@@ -1760,9 +1896,9 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 			     const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct net *net = sock_net(skb->sk);
-	const struct nft_table *table;
+	struct nft_table *table;
 	struct nft_chain *chain = NULL;
 	struct nft_rule *rule;
 	int family = nfmsg->nfgen_family, err = 0;
@@ -1775,6 +1911,8 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 	table = nf_tables_table_lookup(afi, nla[NFTA_RULE_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (table->flags & NFT_TABLE_INACTIVE)
+		return -ENOENT;
 
 	if (nla[NFTA_RULE_CHAIN]) {
 		chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN]);
@@ -1807,88 +1945,6 @@ static int nf_tables_delrule(struct sock *nlsk, struct sk_buff *skb,
 	return err;
 }
 
-static int nf_tables_commit(struct sk_buff *skb)
-{
-	struct net *net = sock_net(skb->sk);
-	struct nft_rule_trans *rupd, *tmp;
-
-	/* Bump generation counter, invalidate any dump in progress */
-	net->nft.genctr++;
-
-	/* A new generation has just started */
-	net->nft.gencursor = gencursor_next(net);
-
-	/* Make sure all packets have left the previous generation before
-	 * purging old rules.
-	 */
-	synchronize_rcu();
-
-	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		/* This rule was inactive in the past and just became active.
-		 * Clear the next bit of the genmask since its meaning has
-		 * changed, now it is the future.
-		 */
-		if (nft_rule_is_active(net, rupd->rule)) {
-			nft_rule_clear(net, rupd->rule);
-			nf_tables_rule_notify(skb, rupd->ctx.nlh,
-					      rupd->ctx.table, rupd->ctx.chain,
-					      rupd->rule, NFT_MSG_NEWRULE, 0,
-					      rupd->ctx.afi->family);
-			list_del(&rupd->list);
-			kfree(rupd);
-			continue;
-		}
-
-		/* This rule is in the past, get rid of it */
-		list_del_rcu(&rupd->rule->list);
-		nf_tables_rule_notify(skb, rupd->ctx.nlh,
-				      rupd->ctx.table, rupd->ctx.chain,
-				      rupd->rule, NFT_MSG_DELRULE, 0,
-				      rupd->ctx.afi->family);
-	}
-
-	/* Make sure we don't see any packet traversing old rules */
-	synchronize_rcu();
-
-	/* Now we can safely release unused old rules */
-	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		nf_tables_rule_destroy(&rupd->ctx, rupd->rule);
-		list_del(&rupd->list);
-		kfree(rupd);
-	}
-
-	return 0;
-}
-
-static int nf_tables_abort(struct sk_buff *skb)
-{
-	struct net *net = sock_net(skb->sk);
-	struct nft_rule_trans *rupd, *tmp;
-
-	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		if (!nft_rule_is_active_next(net, rupd->rule)) {
-			nft_rule_clear(net, rupd->rule);
-			list_del(&rupd->list);
-			kfree(rupd);
-			continue;
-		}
-
-		/* This rule is inactive, get rid of it */
-		list_del_rcu(&rupd->rule->list);
-	}
-
-	/* Make sure we don't see any packet accessing aborted rules */
-	synchronize_rcu();
-
-	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		nf_tables_rule_destroy(&rupd->ctx, rupd->rule);
-		list_del(&rupd->list);
-		kfree(rupd);
-	}
-
-	return 0;
-}
-
 /*
  * Sets
  */
@@ -1898,7 +1954,7 @@ static LIST_HEAD(nf_tables_set_ops);
 int nft_register_set(struct nft_set_ops *ops)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_add_tail(&ops->list, &nf_tables_set_ops);
+	list_add_tail_rcu(&ops->list, &nf_tables_set_ops);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 	return 0;
 }
@@ -1907,14 +1963,23 @@ EXPORT_SYMBOL_GPL(nft_register_set);
 void nft_unregister_set(struct nft_set_ops *ops)
 {
 	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_del(&ops->list);
+	list_del_rcu(&ops->list);
 	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 }
 EXPORT_SYMBOL_GPL(nft_unregister_set);
 
-static const struct nft_set_ops *nft_select_set_ops(const struct nlattr * const nla[])
+/*
+ * Select a set implementation based on the data characteristics and the
+ * given policy. The total memory use might not be known if no size is
+ * given, in that case the amount of memory per element is used.
+ */
+static const struct nft_set_ops *
+nft_select_set_ops(const struct nlattr * const nla[],
+		   const struct nft_set_desc *desc,
+		   enum nft_set_policies policy)
 {
-	const struct nft_set_ops *ops;
+	const struct nft_set_ops *ops, *bops;
+	struct nft_set_estimate est, best;
 	u32 features;
 
 #ifdef CONFIG_MODULES
@@ -1932,15 +1997,45 @@ static const struct nft_set_ops *nft_select_set_ops(const struct nlattr * const
 		features &= NFT_SET_INTERVAL | NFT_SET_MAP;
 	}
 
-	// FIXME: implement selection properly
+	bops	   = NULL;
+	best.size  = ~0;
+	best.class = ~0;
+
 	list_for_each_entry(ops, &nf_tables_set_ops, list) {
 		if ((ops->features & features) != features)
 			continue;
+		if (!ops->estimate(desc, features, &est))
+			continue;
+
+		switch (policy) {
+		case NFT_SET_POL_PERFORMANCE:
+			if (est.class < best.class)
+				break;
+			if (est.class == best.class && est.size < best.size)
+				break;
+			continue;
+		case NFT_SET_POL_MEMORY:
+			if (est.size < best.size)
+				break;
+			if (est.size == best.size && est.class < best.class)
+				break;
+			continue;
+		default:
+			break;
+		}
+
 		if (!try_module_get(ops->owner))
 			continue;
-		return ops;
+		if (bops != NULL)
+			module_put(bops->owner);
+
+		bops = ops;
+		best = est;
 	}
 
+	if (bops != NULL)
+		return bops;
+
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
@@ -1953,6 +2048,13 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
 	[NFTA_SET_KEY_LEN]		= { .type = NLA_U32 },
 	[NFTA_SET_DATA_TYPE]		= { .type = NLA_U32 },
 	[NFTA_SET_DATA_LEN]		= { .type = NLA_U32 },
+	[NFTA_SET_POLICY]		= { .type = NLA_U32 },
+	[NFTA_SET_DESC]			= { .type = NLA_NESTED },
+	[NFTA_SET_ID]			= { .type = NLA_U32 },
+};
+
+static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
+	[NFTA_SET_DESC_SIZE]		= { .type = NLA_U32 },
 };
 
 static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
@@ -1962,8 +2064,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
 {
 	struct net *net = sock_net(skb->sk);
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi = NULL;
-	const struct nft_table *table = NULL;
+	struct nft_af_info *afi = NULL;
+	struct nft_table *table = NULL;
 
 	if (nfmsg->nfgen_family != NFPROTO_UNSPEC) {
 		afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
@@ -1978,6 +2080,8 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
 		table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]);
 		if (IS_ERR(table))
 			return PTR_ERR(table);
+		if (table->flags & NFT_TABLE_INACTIVE)
+			return -ENOENT;
 	}
 
 	nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
@@ -1999,13 +2103,27 @@ struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
 	return ERR_PTR(-ENOENT);
 }
 
+struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
+					  const struct nlattr *nla)
+{
+	struct nft_trans *trans;
+	u32 id = ntohl(nla_get_be32(nla));
+
+	list_for_each_entry(trans, &net->nft.commit_list, list) {
+		if (trans->msg_type == NFT_MSG_NEWSET &&
+		    id == nft_trans_set_id(trans))
+			return nft_trans_set(trans);
+	}
+	return ERR_PTR(-ENOENT);
+}
+
 static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 				    const char *name)
 {
 	const struct nft_set *i;
 	const char *p;
 	unsigned long *inuse;
-	unsigned int n = 0;
+	unsigned int n = 0, min = 0;
 
 	p = strnchr(name, IFNAMSIZ, '%');
 	if (p != NULL) {
@@ -2015,23 +2133,28 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 		inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL);
 		if (inuse == NULL)
 			return -ENOMEM;
-
+cont:
 		list_for_each_entry(i, &ctx->table->sets, list) {
 			int tmp;
 
 			if (!sscanf(i->name, name, &tmp))
 				continue;
-			if (tmp < 0 || tmp >= BITS_PER_BYTE * PAGE_SIZE)
+			if (tmp < min || tmp >= min + BITS_PER_BYTE * PAGE_SIZE)
 				continue;
 
-			set_bit(tmp, inuse);
+			set_bit(tmp - min, inuse);
 		}
 
 		n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE);
+		if (n >= BITS_PER_BYTE * PAGE_SIZE) {
+			min += BITS_PER_BYTE * PAGE_SIZE;
+			memset(inuse, 0, PAGE_SIZE);
+			goto cont;
+		}
 		free_page((unsigned long)inuse);
 	}
 
-	snprintf(set->name, sizeof(set->name), name, n);
+	snprintf(set->name, sizeof(set->name), name, min + n);
 	list_for_each_entry(i, &ctx->table->sets, list) {
 		if (!strcmp(set->name, i->name))
 			return -ENFILE;
@@ -2044,8 +2167,9 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 {
 	struct nfgenmsg *nfmsg;
 	struct nlmsghdr *nlh;
-	u32 portid = NETLINK_CB(ctx->skb).portid;
-	u32 seq = ctx->nlh->nlmsg_seq;
+	struct nlattr *desc;
+	u32 portid = ctx->portid;
+	u32 seq = ctx->seq;
 
 	event |= NFNL_SUBSYS_NFTABLES << 8;
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
@@ -2077,6 +2201,14 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			goto nla_put_failure;
 	}
 
+	desc = nla_nest_start(skb, NFTA_SET_DESC);
+	if (desc == NULL)
+		goto nla_put_failure;
+	if (set->size &&
+	    nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size)))
+		goto nla_put_failure;
+	nla_nest_end(skb, desc);
+
 	return nlmsg_end(skb, nlh);
 
 nla_put_failure:
@@ -2086,19 +2218,18 @@ nla_put_failure:
 
 static int nf_tables_set_notify(const struct nft_ctx *ctx,
 				const struct nft_set *set,
-				int event)
+				int event, gfp_t gfp_flags)
 {
 	struct sk_buff *skb;
-	u32 portid = NETLINK_CB(ctx->skb).portid;
-	bool report;
+	u32 portid = ctx->portid;
 	int err;
 
-	report = nlmsg_report(ctx->nlh);
-	if (!report && !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
+	if (!ctx->report &&
+	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return 0;
 
 	err = -ENOBUFS;
-	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	skb = nlmsg_new(NLMSG_GOODSIZE, gfp_flags);
 	if (skb == NULL)
 		goto err;
 
@@ -2108,8 +2239,8 @@ static int nf_tables_set_notify(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	err = nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, report,
-			     GFP_KERNEL);
+	err = nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES,
+			     ctx->report, gfp_flags);
 err:
 	if (err < 0)
 		nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, err);
@@ -2125,7 +2256,10 @@ static int nf_tables_dump_sets_table(struct nft_ctx *ctx, struct sk_buff *skb,
 	if (cb->args[1])
 		return skb->len;
 
-	list_for_each_entry(set, &ctx->table->sets, list) {
+	rcu_read_lock();
+	cb->seq = ctx->net->nft.base_seq;
+
+	list_for_each_entry_rcu(set, &ctx->table->sets, list) {
 		if (idx < s_idx)
 			goto cont;
 		if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET,
@@ -2133,11 +2267,13 @@ static int nf_tables_dump_sets_table(struct nft_ctx *ctx, struct sk_buff *skb,
 			cb->args[0] = idx;
 			goto done;
 		}
+		nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 		idx++;
 	}
 	cb->args[1] = 1;
 done:
+	rcu_read_unlock();
 	return skb->len;
 }
 
@@ -2151,7 +2287,10 @@ static int nf_tables_dump_sets_family(struct nft_ctx *ctx, struct sk_buff *skb,
 	if (cb->args[1])
 		return skb->len;
 
-	list_for_each_entry(table, &ctx->afi->tables, list) {
+	rcu_read_lock();
+	cb->seq = ctx->net->nft.base_seq;
+
+	list_for_each_entry_rcu(table, &ctx->afi->tables, list) {
 		if (cur_table) {
 			if (cur_table != table)
 				continue;
@@ -2160,7 +2299,7 @@ static int nf_tables_dump_sets_family(struct nft_ctx *ctx, struct sk_buff *skb,
 		}
 		ctx->table = table;
 		idx = 0;
-		list_for_each_entry(set, &ctx->table->sets, list) {
+		list_for_each_entry_rcu(set, &ctx->table->sets, list) {
 			if (idx < s_idx)
 				goto cont;
 			if (nf_tables_fill_set(skb, ctx, set, NFT_MSG_NEWSET,
@@ -2169,12 +2308,14 @@ static int nf_tables_dump_sets_family(struct nft_ctx *ctx, struct sk_buff *skb,
 				cb->args[2] = (unsigned long) table;
 				goto done;
 			}
+			nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 			idx++;
 		}
 	}
 	cb->args[1] = 1;
 done:
+	rcu_read_unlock();
 	return skb->len;
 }
 
@@ -2183,7 +2324,7 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
 {
 	const struct nft_set *set;
 	unsigned int idx, s_idx = cb->args[0];
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2];
 	struct net *net = sock_net(skb->sk);
 	int cur_family = cb->args[3];
@@ -2191,7 +2332,10 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
 	if (cb->args[1])
 		return skb->len;
 
-	list_for_each_entry(afi, &net->nft.af_info, list) {
+	rcu_read_lock();
+	cb->seq = net->nft.base_seq;
+
+	list_for_each_entry_rcu(afi, &net->nft.af_info, list) {
 		if (cur_family) {
 			if (afi->family != cur_family)
 				continue;
@@ -2199,7 +2343,7 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
 			cur_family = 0;
 		}
 
-		list_for_each_entry(table, &afi->tables, list) {
+		list_for_each_entry_rcu(table, &afi->tables, list) {
 			if (cur_table) {
 				if (cur_table != table)
 					continue;
@@ -2210,7 +2354,7 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
 			ctx->table = table;
 			ctx->afi = afi;
 			idx = 0;
-			list_for_each_entry(set, &ctx->table->sets, list) {
+			list_for_each_entry_rcu(set, &ctx->table->sets, list) {
 				if (idx < s_idx)
 					goto cont;
 				if (nf_tables_fill_set(skb, ctx, set,
@@ -2221,6 +2365,7 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
 					cb->args[3] = afi->family;
 					goto done;
 				}
+				nl_dump_check_consistent(cb, nlmsg_hdr(skb));
 cont:
 				idx++;
 			}
@@ -2230,6 +2375,7 @@ cont:
 	}
 	cb->args[1] = 1;
 done:
+	rcu_read_unlock();
 	return skb->len;
 }
 
@@ -2260,6 +2406,8 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb)
 	return ret;
 }
 
+#define NFT_SET_INACTIVE	(1 << 15)	/* Internal set flag */
+
 static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
 			    const struct nlmsghdr *nlh,
 			    const struct nlattr * const nla[])
@@ -2289,6 +2437,8 @@ static int nf_tables_getset(struct sock *nlsk, struct sk_buff *skb,
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
+	if (set->flags & NFT_SET_INACTIVE)
+		return -ENOENT;
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (skb2 == NULL)
@@ -2305,13 +2455,50 @@ err:
 	return err;
 }
 
+static int nf_tables_set_desc_parse(const struct nft_ctx *ctx,
+				    struct nft_set_desc *desc,
+				    const struct nlattr *nla)
+{
+	struct nlattr *da[NFTA_SET_DESC_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(da, NFTA_SET_DESC_MAX, nla, nft_set_desc_policy);
+	if (err < 0)
+		return err;
+
+	if (da[NFTA_SET_DESC_SIZE] != NULL)
+		desc->size = ntohl(nla_get_be32(da[NFTA_SET_DESC_SIZE]));
+
+	return 0;
+}
+
+static int nft_trans_set_add(struct nft_ctx *ctx, int msg_type,
+			     struct nft_set *set)
+{
+	struct nft_trans *trans;
+
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_set));
+	if (trans == NULL)
+		return -ENOMEM;
+
+	if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) {
+		nft_trans_set_id(trans) =
+			ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID]));
+		set->flags |= NFT_SET_INACTIVE;
+	}
+	nft_trans_set(trans) = set;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
+
+	return 0;
+}
+
 static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 			    const struct nlmsghdr *nlh,
 			    const struct nlattr * const nla[])
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	const struct nft_set_ops *ops;
-	const struct nft_af_info *afi;
+	struct nft_af_info *afi;
 	struct net *net = sock_net(skb->sk);
 	struct nft_table *table;
 	struct nft_set *set;
@@ -2319,14 +2506,18 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	char name[IFNAMSIZ];
 	unsigned int size;
 	bool create;
-	u32 ktype, klen, dlen, dtype, flags;
+	u32 ktype, dtype, flags, policy;
+	struct nft_set_desc desc;
 	int err;
 
 	if (nla[NFTA_SET_TABLE] == NULL ||
 	    nla[NFTA_SET_NAME] == NULL ||
-	    nla[NFTA_SET_KEY_LEN] == NULL)
+	    nla[NFTA_SET_KEY_LEN] == NULL ||
+	    nla[NFTA_SET_ID] == NULL)
 		return -EINVAL;
 
+	memset(&desc, 0, sizeof(desc));
+
 	ktype = NFT_DATA_VALUE;
 	if (nla[NFTA_SET_KEY_TYPE] != NULL) {
 		ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
@@ -2334,8 +2525,8 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 			return -EINVAL;
 	}
 
-	klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN]));
-	if (klen == 0 || klen > FIELD_SIZEOF(struct nft_data, data))
+	desc.klen = ntohl(nla_get_be32(nla[NFTA_SET_KEY_LEN]));
+	if (desc.klen == 0 || desc.klen > FIELD_SIZEOF(struct nft_data, data))
 		return -EINVAL;
 
 	flags = 0;
@@ -2347,7 +2538,6 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	}
 
 	dtype = 0;
-	dlen  = 0;
 	if (nla[NFTA_SET_DATA_TYPE] != NULL) {
 		if (!(flags & NFT_SET_MAP))
 			return -EINVAL;
@@ -2360,15 +2550,25 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 		if (dtype != NFT_DATA_VERDICT) {
 			if (nla[NFTA_SET_DATA_LEN] == NULL)
 				return -EINVAL;
-			dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
-			if (dlen == 0 ||
-			    dlen > FIELD_SIZEOF(struct nft_data, data))
+			desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
+			if (desc.dlen == 0 ||
+			    desc.dlen > FIELD_SIZEOF(struct nft_data, data))
 				return -EINVAL;
 		} else
-			dlen = sizeof(struct nft_data);
+			desc.dlen = sizeof(struct nft_data);
 	} else if (flags & NFT_SET_MAP)
 		return -EINVAL;
 
+	policy = NFT_SET_POL_PERFORMANCE;
+	if (nla[NFTA_SET_POLICY] != NULL)
+		policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
+
+	if (nla[NFTA_SET_DESC] != NULL) {
+		err = nf_tables_set_desc_parse(&ctx, &desc, nla[NFTA_SET_DESC]);
+		if (err < 0)
+			return err;
+	}
+
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
 	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, create);
@@ -2399,7 +2599,7 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	if (!(nlh->nlmsg_flags & NLM_F_CREATE))
 		return -ENOENT;
 
-	ops = nft_select_set_ops(nla);
+	ops = nft_select_set_ops(nla, &desc, policy);
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
 
@@ -2420,17 +2620,22 @@ static int nf_tables_newset(struct sock *nlsk, struct sk_buff *skb,
 	INIT_LIST_HEAD(&set->bindings);
 	set->ops   = ops;
 	set->ktype = ktype;
-	set->klen  = klen;
+	set->klen  = desc.klen;
 	set->dtype = dtype;
-	set->dlen  = dlen;
+	set->dlen  = desc.dlen;
 	set->flags = flags;
+	set->size  = desc.size;
+
+	err = ops->init(set, &desc, nla);
+	if (err < 0)
+		goto err2;
 
-	err = ops->init(set, nla);
+	err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
 	if (err < 0)
 		goto err2;
 
-	list_add_tail(&set->list, &table->sets);
-	nf_tables_set_notify(&ctx, set, NFT_MSG_NEWSET);
+	list_add_tail_rcu(&set->list, &table->sets);
+	table->use++;
 	return 0;
 
 err2:
@@ -2440,16 +2645,20 @@ err1:
 	return err;
 }
 
-static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
+static void nft_set_destroy(struct nft_set *set)
 {
-	list_del(&set->list);
-	nf_tables_set_notify(ctx, set, NFT_MSG_DELSET);
-
 	set->ops->destroy(set);
 	module_put(set->ops->owner);
 	kfree(set);
 }
 
+static void nf_tables_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
+{
+	list_del_rcu(&set->list);
+	nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC);
+	nft_set_destroy(set);
+}
+
 static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
 			    const struct nlmsghdr *nlh,
 			    const struct nlattr * const nla[])
@@ -2471,10 +2680,17 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
+	if (set->flags & NFT_SET_INACTIVE)
+		return -ENOENT;
 	if (!list_empty(&set->bindings))
 		return -EBUSY;
 
-	nf_tables_set_destroy(&ctx, set);
+	err = nft_trans_set_add(&ctx, NFT_MSG_DELSET, set);
+	if (err < 0)
+		return err;
+
+	list_del_rcu(&set->list);
+	ctx.table->use--;
 	return 0;
 }
 
@@ -2525,16 +2741,17 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
 	}
 bind:
 	binding->chain = ctx->chain;
-	list_add_tail(&binding->list, &set->bindings);
+	list_add_tail_rcu(&binding->list, &set->bindings);
 	return 0;
 }
 
 void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
 			  struct nft_set_binding *binding)
 {
-	list_del(&binding->list);
+	list_del_rcu(&binding->list);
 
-	if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS)
+	if (list_empty(&set->bindings) && set->flags & NFT_SET_ANONYMOUS &&
+	    !(set->flags & NFT_SET_INACTIVE))
 		nf_tables_set_destroy(ctx, set);
 }
 
@@ -2552,16 +2769,18 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX +
 	[NFTA_SET_ELEM_LIST_TABLE]	= { .type = NLA_STRING },
 	[NFTA_SET_ELEM_LIST_SET]	= { .type = NLA_STRING },
 	[NFTA_SET_ELEM_LIST_ELEMENTS]	= { .type = NLA_NESTED },
+	[NFTA_SET_ELEM_LIST_SET_ID]	= { .type = NLA_U32 },
 };
 
 static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
 				      const struct sk_buff *skb,
 				      const struct nlmsghdr *nlh,
-				      const struct nlattr * const nla[])
+				      const struct nlattr * const nla[],
+				      bool trans)
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nft_af_info *afi;
-	const struct nft_table *table;
+	struct nft_af_info *afi;
+	struct nft_table *table;
 	struct net *net = sock_net(skb->sk);
 
 	afi = nf_tables_afinfo_lookup(net, nfmsg->nfgen_family, false);
@@ -2571,6 +2790,8 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx,
 	table = nf_tables_table_lookup(afi, nla[NFTA_SET_ELEM_LIST_TABLE]);
 	if (IS_ERR(table))
 		return PTR_ERR(table);
+	if (!trans && (table->flags & NFT_TABLE_INACTIVE))
+		return -ENOENT;
 
 	nft_ctx_init(ctx, skb, nlh, afi, table, NULL, nla);
 	return 0;
@@ -2644,13 +2865,16 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 	if (err < 0)
 		return err;
 
-	err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla);
+	err = nft_ctx_init_from_elemattr(&ctx, cb->skb, cb->nlh, (void *)nla,
+					 false);
 	if (err < 0)
 		return err;
 
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
+	if (set->flags & NFT_SET_INACTIVE)
+		return -ENOENT;
 
 	event  = NFT_MSG_NEWSETELEM;
 	event |= NFNL_SUBSYS_NFTABLES << 8;
@@ -2663,7 +2887,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 		goto nla_put_failure;
 
 	nfmsg = nlmsg_data(nlh);
-	nfmsg->nfgen_family = NFPROTO_UNSPEC;
+	nfmsg->nfgen_family = ctx.afi->family;
 	nfmsg->version      = NFNETLINK_V0;
 	nfmsg->res_id       = 0;
 
@@ -2707,13 +2931,15 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_ctx ctx;
 	int err;
 
-	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla);
+	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false);
 	if (err < 0)
 		return err;
 
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
+	if (set->flags & NFT_SET_INACTIVE)
+		return -ENOENT;
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
@@ -2724,7 +2950,98 @@ static int nf_tables_getsetelem(struct sock *nlsk, struct sk_buff *skb,
 	return -EOPNOTSUPP;
 }
 
-static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
+static int nf_tables_fill_setelem_info(struct sk_buff *skb,
+				       const struct nft_ctx *ctx, u32 seq,
+				       u32 portid, int event, u16 flags,
+				       const struct nft_set *set,
+				       const struct nft_set_elem *elem)
+{
+	struct nfgenmsg *nfmsg;
+	struct nlmsghdr *nlh;
+	struct nlattr *nest;
+	int err;
+
+	event |= NFNL_SUBSYS_NFTABLES << 8;
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
+			flags);
+	if (nlh == NULL)
+		goto nla_put_failure;
+
+	nfmsg = nlmsg_data(nlh);
+	nfmsg->nfgen_family	= ctx->afi->family;
+	nfmsg->version		= NFNETLINK_V0;
+	nfmsg->res_id		= 0;
+
+	if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name))
+		goto nla_put_failure;
+	if (nla_put_string(skb, NFTA_SET_NAME, set->name))
+		goto nla_put_failure;
+
+	nest = nla_nest_start(skb, NFTA_SET_ELEM_LIST_ELEMENTS);
+	if (nest == NULL)
+		goto nla_put_failure;
+
+	err = nf_tables_fill_setelem(skb, set, elem);
+	if (err < 0)
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_trim(skb, nlh);
+	return -1;
+}
+
+static int nf_tables_setelem_notify(const struct nft_ctx *ctx,
+				    const struct nft_set *set,
+				    const struct nft_set_elem *elem,
+				    int event, u16 flags)
+{
+	struct net *net = ctx->net;
+	u32 portid = ctx->portid;
+	struct sk_buff *skb;
+	int err;
+
+	if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
+		return 0;
+
+	err = -ENOBUFS;
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (skb == NULL)
+		goto err;
+
+	err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags,
+					  set, elem);
+	if (err < 0) {
+		kfree_skb(skb);
+		goto err;
+	}
+
+	err = nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, ctx->report,
+			     GFP_KERNEL);
+err:
+	if (err < 0)
+		nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, err);
+	return err;
+}
+
+static struct nft_trans *nft_trans_elem_alloc(struct nft_ctx *ctx,
+					      int msg_type,
+					      struct nft_set *set)
+{
+	struct nft_trans *trans;
+
+	trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_elem));
+	if (trans == NULL)
+		return NULL;
+
+	nft_trans_elem_set(trans) = set;
+	return trans;
+}
+
+static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			    const struct nlattr *attr)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
@@ -2732,8 +3049,12 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
 	struct nft_set_elem elem;
 	struct nft_set_binding *binding;
 	enum nft_registers dreg;
+	struct nft_trans *trans;
 	int err;
 
+	if (set->size && set->nelems == set->size)
+		return -ENFILE;
+
 	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
 			       nft_set_elem_policy);
 	if (err < 0)
@@ -2786,7 +3107,7 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
 			struct nft_ctx bind_ctx = {
 				.afi	= ctx->afi,
 				.table	= ctx->table,
-				.chain	= binding->chain,
+				.chain	= (struct nft_chain *)binding->chain,
 			};
 
 			err = nft_validate_data_load(&bind_ctx, dreg,
@@ -2796,12 +3117,20 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
 		}
 	}
 
+	trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
+	if (trans == NULL)
+		goto err3;
+
 	err = set->ops->insert(set, &elem);
 	if (err < 0)
-		goto err3;
+		goto err4;
 
+	nft_trans_elem(trans) = elem;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
 
+err4:
+	kfree(trans);
 err3:
 	if (nla[NFTA_SET_ELEM_DATA] != NULL)
 		nft_data_uninit(&elem.data, d2.type);
@@ -2815,35 +3144,46 @@ static int nf_tables_newsetelem(struct sock *nlsk, struct sk_buff *skb,
 				const struct nlmsghdr *nlh,
 				const struct nlattr * const nla[])
 {
+	struct net *net = sock_net(skb->sk);
 	const struct nlattr *attr;
 	struct nft_set *set;
 	struct nft_ctx ctx;
-	int rem, err;
+	int rem, err = 0;
 
-	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla);
+	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, true);
 	if (err < 0)
 		return err;
 
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET]);
-	if (IS_ERR(set))
-		return PTR_ERR(set);
+	if (IS_ERR(set)) {
+		if (nla[NFTA_SET_ELEM_LIST_SET_ID]) {
+			set = nf_tables_set_lookup_byid(net,
+					nla[NFTA_SET_ELEM_LIST_SET_ID]);
+		}
+		if (IS_ERR(set))
+			return PTR_ERR(set);
+	}
+
 	if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT)
 		return -EBUSY;
 
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
 		err = nft_add_set_elem(&ctx, set, attr);
 		if (err < 0)
-			return err;
+			break;
+
+		set->nelems++;
 	}
-	return 0;
+	return err;
 }
 
-static int nft_del_setelem(const struct nft_ctx *ctx, struct nft_set *set,
+static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 			   const struct nlattr *attr)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
 	struct nft_data_desc desc;
 	struct nft_set_elem elem;
+	struct nft_trans *trans;
 	int err;
 
 	err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr,
@@ -2867,7 +3207,12 @@ static int nft_del_setelem(const struct nft_ctx *ctx, struct nft_set *set,
 	if (err < 0)
 		goto err2;
 
-	set->ops->remove(set, &elem);
+	trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set);
+	if (trans == NULL)
+		goto err2;
+
+	nft_trans_elem(trans) = elem;
+	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 
 	nft_data_uninit(&elem.key, NFT_DATA_VALUE);
 	if (set->flags & NFT_SET_MAP)
@@ -2886,9 +3231,9 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
 	const struct nlattr *attr;
 	struct nft_set *set;
 	struct nft_ctx ctx;
-	int rem, err;
+	int rem, err = 0;
 
-	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla);
+	err = nft_ctx_init_from_elemattr(&ctx, skb, nlh, nla, false);
 	if (err < 0)
 		return err;
 
@@ -2901,14 +3246,16 @@ static int nf_tables_delsetelem(struct sock *nlsk, struct sk_buff *skb,
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
 		err = nft_del_setelem(&ctx, set, attr);
 		if (err < 0)
-			return err;
+			break;
+
+		set->nelems--;
 	}
-	return 0;
+	return err;
 }
 
 static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 	[NFT_MSG_NEWTABLE] = {
-		.call		= nf_tables_newtable,
+		.call_batch	= nf_tables_newtable,
 		.attr_count	= NFTA_TABLE_MAX,
 		.policy		= nft_table_policy,
 	},
@@ -2918,12 +3265,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_table_policy,
 	},
 	[NFT_MSG_DELTABLE] = {
-		.call		= nf_tables_deltable,
+		.call_batch	= nf_tables_deltable,
 		.attr_count	= NFTA_TABLE_MAX,
 		.policy		= nft_table_policy,
 	},
 	[NFT_MSG_NEWCHAIN] = {
-		.call		= nf_tables_newchain,
+		.call_batch	= nf_tables_newchain,
 		.attr_count	= NFTA_CHAIN_MAX,
 		.policy		= nft_chain_policy,
 	},
@@ -2933,7 +3280,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_chain_policy,
 	},
 	[NFT_MSG_DELCHAIN] = {
-		.call		= nf_tables_delchain,
+		.call_batch	= nf_tables_delchain,
 		.attr_count	= NFTA_CHAIN_MAX,
 		.policy		= nft_chain_policy,
 	},
@@ -2953,7 +3300,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_rule_policy,
 	},
 	[NFT_MSG_NEWSET] = {
-		.call		= nf_tables_newset,
+		.call_batch	= nf_tables_newset,
 		.attr_count	= NFTA_SET_MAX,
 		.policy		= nft_set_policy,
 	},
@@ -2963,12 +3310,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_set_policy,
 	},
 	[NFT_MSG_DELSET] = {
-		.call		= nf_tables_delset,
+		.call_batch	= nf_tables_delset,
 		.attr_count	= NFTA_SET_MAX,
 		.policy		= nft_set_policy,
 	},
 	[NFT_MSG_NEWSETELEM] = {
-		.call		= nf_tables_newsetelem,
+		.call_batch	= nf_tables_newsetelem,
 		.attr_count	= NFTA_SET_ELEM_LIST_MAX,
 		.policy		= nft_set_elem_list_policy,
 	},
@@ -2978,12 +3325,282 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
 		.policy		= nft_set_elem_list_policy,
 	},
 	[NFT_MSG_DELSETELEM] = {
-		.call		= nf_tables_delsetelem,
+		.call_batch	= nf_tables_delsetelem,
 		.attr_count	= NFTA_SET_ELEM_LIST_MAX,
 		.policy		= nft_set_elem_list_policy,
 	},
 };
 
+static void nft_chain_commit_update(struct nft_trans *trans)
+{
+	struct nft_base_chain *basechain;
+
+	if (nft_trans_chain_name(trans)[0])
+		strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans));
+
+	if (!(trans->ctx.chain->flags & NFT_BASE_CHAIN))
+		return;
+
+	basechain = nft_base_chain(trans->ctx.chain);
+	nft_chain_stats_replace(basechain, nft_trans_chain_stats(trans));
+
+	switch (nft_trans_chain_policy(trans)) {
+	case NF_DROP:
+	case NF_ACCEPT:
+		basechain->policy = nft_trans_chain_policy(trans);
+		break;
+	}
+}
+
+/* Schedule objects for release via rcu to make sure no packets are accesing
+ * removed rules.
+ */
+static void nf_tables_commit_release_rcu(struct rcu_head *rt)
+{
+	struct nft_trans *trans = container_of(rt, struct nft_trans, rcu_head);
+
+	switch (trans->msg_type) {
+	case NFT_MSG_DELTABLE:
+		nf_tables_table_destroy(&trans->ctx);
+		break;
+	case NFT_MSG_DELCHAIN:
+		nf_tables_chain_destroy(trans->ctx.chain);
+		break;
+	case NFT_MSG_DELRULE:
+		nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
+		break;
+	case NFT_MSG_DELSET:
+		nft_set_destroy(nft_trans_set(trans));
+		break;
+	}
+	kfree(trans);
+}
+
+static int nf_tables_commit(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nft_trans *trans, *next;
+	struct nft_set *set;
+
+	/* Bump generation counter, invalidate any dump in progress */
+	while (++net->nft.base_seq == 0);
+
+	/* A new generation has just started */
+	net->nft.gencursor = gencursor_next(net);
+
+	/* Make sure all packets have left the previous generation before
+	 * purging old rules.
+	 */
+	synchronize_rcu();
+
+	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWTABLE:
+			if (nft_trans_table_update(trans)) {
+				if (!nft_trans_table_enable(trans)) {
+					nf_tables_table_disable(trans->ctx.afi,
+								trans->ctx.table);
+					trans->ctx.table->flags |= NFT_TABLE_F_DORMANT;
+				}
+			} else {
+				trans->ctx.table->flags &= ~NFT_TABLE_INACTIVE;
+			}
+			nf_tables_table_notify(&trans->ctx, NFT_MSG_NEWTABLE);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELTABLE:
+			nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE);
+			break;
+		case NFT_MSG_NEWCHAIN:
+			if (nft_trans_chain_update(trans))
+				nft_chain_commit_update(trans);
+			else
+				trans->ctx.chain->flags &= ~NFT_CHAIN_INACTIVE;
+
+			nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELCHAIN:
+			nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN);
+			if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT) &&
+			    trans->ctx.chain->flags & NFT_BASE_CHAIN) {
+				nf_unregister_hooks(nft_base_chain(trans->ctx.chain)->ops,
+						    trans->ctx.afi->nops);
+			}
+			break;
+		case NFT_MSG_NEWRULE:
+			nft_rule_clear(trans->ctx.net, nft_trans_rule(trans));
+			nf_tables_rule_notify(&trans->ctx,
+					      nft_trans_rule(trans),
+					      NFT_MSG_NEWRULE);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELRULE:
+			list_del_rcu(&nft_trans_rule(trans)->list);
+			nf_tables_rule_notify(&trans->ctx,
+					      nft_trans_rule(trans),
+					      NFT_MSG_DELRULE);
+			break;
+		case NFT_MSG_NEWSET:
+			nft_trans_set(trans)->flags &= ~NFT_SET_INACTIVE;
+			/* This avoids hitting -EBUSY when deleting the table
+			 * from the transaction.
+			 */
+			if (nft_trans_set(trans)->flags & NFT_SET_ANONYMOUS &&
+			    !list_empty(&nft_trans_set(trans)->bindings))
+				trans->ctx.table->use--;
+
+			nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
+					     NFT_MSG_NEWSET, GFP_KERNEL);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELSET:
+			nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
+					     NFT_MSG_DELSET, GFP_KERNEL);
+			break;
+		case NFT_MSG_NEWSETELEM:
+			nf_tables_setelem_notify(&trans->ctx,
+						 nft_trans_elem_set(trans),
+						 &nft_trans_elem(trans),
+						 NFT_MSG_NEWSETELEM, 0);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELSETELEM:
+			nf_tables_setelem_notify(&trans->ctx,
+						 nft_trans_elem_set(trans),
+						 &nft_trans_elem(trans),
+						 NFT_MSG_DELSETELEM, 0);
+			set = nft_trans_elem_set(trans);
+			set->ops->get(set, &nft_trans_elem(trans));
+			set->ops->remove(set, &nft_trans_elem(trans));
+			nft_trans_destroy(trans);
+			break;
+		}
+	}
+
+	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+		list_del(&trans->list);
+		trans->ctx.nla = NULL;
+		call_rcu(&trans->rcu_head, nf_tables_commit_release_rcu);
+	}
+
+	return 0;
+}
+
+/* Schedule objects for release via rcu to make sure no packets are accesing
+ * aborted rules.
+ */
+static void nf_tables_abort_release_rcu(struct rcu_head *rt)
+{
+	struct nft_trans *trans = container_of(rt, struct nft_trans, rcu_head);
+
+	switch (trans->msg_type) {
+	case NFT_MSG_NEWTABLE:
+		nf_tables_table_destroy(&trans->ctx);
+		break;
+	case NFT_MSG_NEWCHAIN:
+		nf_tables_chain_destroy(trans->ctx.chain);
+		break;
+	case NFT_MSG_NEWRULE:
+		nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
+		break;
+	case NFT_MSG_NEWSET:
+		nft_set_destroy(nft_trans_set(trans));
+		break;
+	}
+	kfree(trans);
+}
+
+static int nf_tables_abort(struct sk_buff *skb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nft_trans *trans, *next;
+	struct nft_set *set;
+
+	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWTABLE:
+			if (nft_trans_table_update(trans)) {
+				if (nft_trans_table_enable(trans)) {
+					nf_tables_table_disable(trans->ctx.afi,
+								trans->ctx.table);
+					trans->ctx.table->flags |= NFT_TABLE_F_DORMANT;
+				}
+				nft_trans_destroy(trans);
+			} else {
+				list_del_rcu(&trans->ctx.table->list);
+			}
+			break;
+		case NFT_MSG_DELTABLE:
+			list_add_tail_rcu(&trans->ctx.table->list,
+					  &trans->ctx.afi->tables);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_NEWCHAIN:
+			if (nft_trans_chain_update(trans)) {
+				if (nft_trans_chain_stats(trans))
+					free_percpu(nft_trans_chain_stats(trans));
+
+				nft_trans_destroy(trans);
+			} else {
+				trans->ctx.table->use--;
+				list_del_rcu(&trans->ctx.chain->list);
+				if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT) &&
+				    trans->ctx.chain->flags & NFT_BASE_CHAIN) {
+					nf_unregister_hooks(nft_base_chain(trans->ctx.chain)->ops,
+							    trans->ctx.afi->nops);
+				}
+			}
+			break;
+		case NFT_MSG_DELCHAIN:
+			trans->ctx.table->use++;
+			list_add_tail_rcu(&trans->ctx.chain->list,
+					  &trans->ctx.table->chains);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_NEWRULE:
+			trans->ctx.chain->use--;
+			list_del_rcu(&nft_trans_rule(trans)->list);
+			break;
+		case NFT_MSG_DELRULE:
+			trans->ctx.chain->use++;
+			nft_rule_clear(trans->ctx.net, nft_trans_rule(trans));
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_NEWSET:
+			trans->ctx.table->use--;
+			list_del_rcu(&nft_trans_set(trans)->list);
+			break;
+		case NFT_MSG_DELSET:
+			trans->ctx.table->use++;
+			list_add_tail_rcu(&nft_trans_set(trans)->list,
+					  &trans->ctx.table->sets);
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_NEWSETELEM:
+			nft_trans_elem_set(trans)->nelems--;
+			set = nft_trans_elem_set(trans);
+			set->ops->get(set, &nft_trans_elem(trans));
+			set->ops->remove(set, &nft_trans_elem(trans));
+			nft_trans_destroy(trans);
+			break;
+		case NFT_MSG_DELSETELEM:
+			nft_trans_elem_set(trans)->nelems++;
+			nft_trans_destroy(trans);
+			break;
+		}
+	}
+
+	list_for_each_entry_safe_reverse(trans, next,
+					 &net->nft.commit_list, list) {
+		list_del(&trans->list);
+		trans->ctx.nla = NULL;
+		call_rcu(&trans->rcu_head, nf_tables_abort_release_rcu);
+	}
+
+	return 0;
+}
+
 static const struct nfnetlink_subsystem nf_tables_subsys = {
 	.name		= "nf_tables",
 	.subsys_id	= NFNL_SUBSYS_NFTABLES,
@@ -3371,6 +3988,7 @@ static int nf_tables_init_net(struct net *net)
 {
 	INIT_LIST_HEAD(&net->nft.af_info);
 	INIT_LIST_HEAD(&net->nft.commit_list);
+	net->nft.base_seq = 1;
 	return 0;
 }
 
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 345acfb1720..3b90eb2b2c5 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -109,7 +109,7 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 	struct nft_data data[NFT_REG_MAX + 1];
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
-	struct nft_stats __percpu *stats;
+	struct nft_stats *stats;
 	int rulenum;
 	/*
 	 * Cache cursor to avoid problems in case that the cursor is updated
@@ -205,9 +205,11 @@ next_rule:
 		nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY);
 
 	rcu_read_lock_bh();
-	stats = rcu_dereference(nft_base_chain(basechain)->stats);
-	__this_cpu_inc(stats->pkts);
-	__this_cpu_add(stats->bytes, pkt->skb->len);
+	stats = this_cpu_ptr(rcu_dereference(nft_base_chain(basechain)->stats));
+	u64_stats_update_begin(&stats->syncp);
+	stats->pkts++;
+	stats->bytes += pkt->skb->len;
+	u64_stats_update_end(&stats->syncp);
 	rcu_read_unlock_bh();
 
 	return nft_base_chain(basechain)->policy;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 23ef77c60ff..c138b8fbe28 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -399,19 +399,17 @@ static void nfnetlink_rcv(struct sk_buff *skb)
 }
 
 #ifdef CONFIG_MODULES
-static void nfnetlink_bind(int group)
+static int nfnetlink_bind(int group)
 {
 	const struct nfnetlink_subsystem *ss;
 	int type = nfnl_group2type[group];
 
 	rcu_read_lock();
 	ss = nfnetlink_get_subsys(type);
-	if (!ss) {
-		rcu_read_unlock();
-		request_module("nfnetlink-subsys-%d", type);
-		return;
-	}
 	rcu_read_unlock();
+	if (!ss)
+		request_module("nfnetlink-subsys-%d", type);
+	return 0;
 }
 #endif
 
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index c7b6d466a66..2baa125c2e8 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -32,18 +32,24 @@ static LIST_HEAD(nfnl_acct_list);
 struct nf_acct {
 	atomic64_t		pkts;
 	atomic64_t		bytes;
+	unsigned long		flags;
 	struct list_head	head;
 	atomic_t		refcnt;
 	char			name[NFACCT_NAME_MAX];
 	struct rcu_head		rcu_head;
+	char			data[0];
 };
 
+#define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES)
+
 static int
 nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb,
 	     const struct nlmsghdr *nlh, const struct nlattr * const tb[])
 {
 	struct nf_acct *nfacct, *matching = NULL;
 	char *acct_name;
+	unsigned int size = 0;
+	u32 flags = 0;
 
 	if (!tb[NFACCT_NAME])
 		return -EINVAL;
@@ -68,15 +74,38 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb,
 			/* reset counters if you request a replacement. */
 			atomic64_set(&matching->pkts, 0);
 			atomic64_set(&matching->bytes, 0);
+			smp_mb__before_atomic();
+			/* reset overquota flag if quota is enabled. */
+			if ((matching->flags & NFACCT_F_QUOTA))
+				clear_bit(NFACCT_F_OVERQUOTA, &matching->flags);
 			return 0;
 		}
 		return -EBUSY;
 	}
 
-	nfacct = kzalloc(sizeof(struct nf_acct), GFP_KERNEL);
+	if (tb[NFACCT_FLAGS]) {
+		flags = ntohl(nla_get_be32(tb[NFACCT_FLAGS]));
+		if (flags & ~NFACCT_F_QUOTA)
+			return -EOPNOTSUPP;
+		if ((flags & NFACCT_F_QUOTA) == NFACCT_F_QUOTA)
+			return -EINVAL;
+		if (flags & NFACCT_F_OVERQUOTA)
+			return -EINVAL;
+
+		size += sizeof(u64);
+	}
+
+	nfacct = kzalloc(sizeof(struct nf_acct) + size, GFP_KERNEL);
 	if (nfacct == NULL)
 		return -ENOMEM;
 
+	if (flags & NFACCT_F_QUOTA) {
+		u64 *quota = (u64 *)nfacct->data;
+
+		*quota = be64_to_cpu(nla_get_be64(tb[NFACCT_QUOTA]));
+		nfacct->flags = flags;
+	}
+
 	strncpy(nfacct->name, nla_data(tb[NFACCT_NAME]), NFACCT_NAME_MAX);
 
 	if (tb[NFACCT_BYTES]) {
@@ -117,6 +146,9 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	if (type == NFNL_MSG_ACCT_GET_CTRZERO) {
 		pkts = atomic64_xchg(&acct->pkts, 0);
 		bytes = atomic64_xchg(&acct->bytes, 0);
+		smp_mb__before_atomic();
+		if (acct->flags & NFACCT_F_QUOTA)
+			clear_bit(NFACCT_F_OVERQUOTA, &acct->flags);
 	} else {
 		pkts = atomic64_read(&acct->pkts);
 		bytes = atomic64_read(&acct->bytes);
@@ -125,7 +157,13 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	    nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes)) ||
 	    nla_put_be32(skb, NFACCT_USE, htonl(atomic_read(&acct->refcnt))))
 		goto nla_put_failure;
+	if (acct->flags & NFACCT_F_QUOTA) {
+		u64 *quota = (u64 *)acct->data;
 
+		if (nla_put_be32(skb, NFACCT_FLAGS, htonl(acct->flags)) ||
+		    nla_put_be64(skb, NFACCT_QUOTA, cpu_to_be64(*quota)))
+			goto nla_put_failure;
+	}
 	nlmsg_end(skb, nlh);
 	return skb->len;
 
@@ -270,6 +308,8 @@ static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = {
 	[NFACCT_NAME] = { .type = NLA_NUL_STRING, .len = NFACCT_NAME_MAX-1 },
 	[NFACCT_BYTES] = { .type = NLA_U64 },
 	[NFACCT_PKTS] = { .type = NLA_U64 },
+	[NFACCT_FLAGS] = { .type = NLA_U32 },
+	[NFACCT_QUOTA] = { .type = NLA_U64 },
 };
 
 static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = {
@@ -336,6 +376,50 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct)
 }
 EXPORT_SYMBOL_GPL(nfnl_acct_update);
 
+static void nfnl_overquota_report(struct nf_acct *nfacct)
+{
+	int ret;
+	struct sk_buff *skb;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (skb == NULL)
+		return;
+
+	ret = nfnl_acct_fill_info(skb, 0, 0, NFNL_MSG_ACCT_OVERQUOTA, 0,
+				  nfacct);
+	if (ret <= 0) {
+		kfree_skb(skb);
+		return;
+	}
+	netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA,
+			  GFP_ATOMIC);
+}
+
+int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct)
+{
+	u64 now;
+	u64 *quota;
+	int ret = NFACCT_UNDERQUOTA;
+
+	/* no place here if we don't have a quota */
+	if (!(nfacct->flags & NFACCT_F_QUOTA))
+		return NFACCT_NO_QUOTA;
+
+	quota = (u64 *)nfacct->data;
+	now = (nfacct->flags & NFACCT_F_QUOTA_PKTS) ?
+	       atomic64_read(&nfacct->pkts) : atomic64_read(&nfacct->bytes);
+
+	ret = now > *quota;
+
+	if (now >= *quota &&
+	    !test_and_set_bit(NFACCT_F_OVERQUOTA, &nfacct->flags)) {
+		nfnl_overquota_report(nfacct);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nfnl_acct_overquota);
+
 static int __init nfnl_acct_init(void)
 {
 	int ret;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 8a779be832f..1840989092e 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -195,6 +195,15 @@ static void
 nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
 {
 	struct xt_target *target = expr->ops->data;
+	void *info = nft_expr_priv(expr);
+	struct xt_tgdtor_param par;
+
+	par.net = ctx->net;
+	par.target = target;
+	par.targinfo = info;
+	par.family = ctx->afi->family;
+	if (par.target->destroy != NULL)
+		par.target->destroy(&par);
 
 	module_put(target->me);
 }
@@ -382,6 +391,15 @@ static void
 nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
 {
 	struct xt_match *match = expr->ops->data;
+	void *info = nft_expr_priv(expr);
+	struct xt_mtdtor_param par;
+
+	par.net = ctx->net;
+	par.match = match;
+	par.matchinfo = info;
+	par.family = ctx->afi->family;
+	if (par.match->destroy != NULL)
+		par.match->destroy(&par);
 
 	module_put(match->me);
 }
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index bd0d41e6934..cc560301624 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -215,22 +215,14 @@ static void nft_ct_l3proto_module_put(uint8_t family)
 		nf_ct_l3proto_module_put(family);
 }
 
-static int nft_ct_init_validate_get(const struct nft_expr *expr,
-				    const struct nlattr * const tb[])
+static int nft_ct_get_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
 {
 	struct nft_ct *priv = nft_expr_priv(expr);
+	int err;
 
-	if (tb[NFTA_CT_DIRECTION] != NULL) {
-		priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]);
-		switch (priv->dir) {
-		case IP_CT_DIR_ORIGINAL:
-		case IP_CT_DIR_REPLY:
-			break;
-		default:
-			return -EINVAL;
-		}
-	}
-
+	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
 	switch (priv->key) {
 	case NFT_CT_STATE:
 	case NFT_CT_DIRECTION:
@@ -262,55 +254,55 @@ static int nft_ct_init_validate_get(const struct nft_expr *expr,
 		return -EOPNOTSUPP;
 	}
 
-	return 0;
-}
-
-static int nft_ct_init_validate_set(uint32_t key)
-{
-	switch (key) {
-	case NFT_CT_MARK:
-		break;
-	default:
-		return -EOPNOTSUPP;
+	if (tb[NFTA_CT_DIRECTION] != NULL) {
+		priv->dir = nla_get_u8(tb[NFTA_CT_DIRECTION]);
+		switch (priv->dir) {
+		case IP_CT_DIR_ORIGINAL:
+		case IP_CT_DIR_REPLY:
+			break;
+		default:
+			return -EINVAL;
+		}
 	}
 
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+
+	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	if (err < 0)
+		return err;
+
+	err = nft_ct_l3proto_try_module_get(ctx->afi->family);
+	if (err < 0)
+		return err;
+
 	return 0;
 }
 
-static int nft_ct_init(const struct nft_ctx *ctx,
-		       const struct nft_expr *expr,
-		       const struct nlattr * const tb[])
+static int nft_ct_set_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
 {
 	struct nft_ct *priv = nft_expr_priv(expr);
 	int err;
 
 	priv->key = ntohl(nla_get_be32(tb[NFTA_CT_KEY]));
-
-	if (tb[NFTA_CT_DREG]) {
-		err = nft_ct_init_validate_get(expr, tb);
-		if (err < 0)
-			return err;
-
-		priv->dreg = ntohl(nla_get_be32(tb[NFTA_CT_DREG]));
-		err = nft_validate_output_register(priv->dreg);
-		if (err < 0)
-			return err;
-
-		err = nft_validate_data_load(ctx, priv->dreg, NULL,
-					     NFT_DATA_VALUE);
-		if (err < 0)
-			return err;
-	} else {
-		err = nft_ct_init_validate_set(priv->key);
-		if (err < 0)
-			return err;
-
-		priv->sreg = ntohl(nla_get_be32(tb[NFTA_CT_SREG]));
-		err = nft_validate_input_register(priv->sreg);
-		if (err < 0)
-			return err;
+	switch (priv->key) {
+#ifdef CONFIG_NF_CONNTRACK_MARK
+	case NFT_CT_MARK:
+		break;
+#endif
+	default:
+		return -EOPNOTSUPP;
 	}
 
+	priv->sreg = ntohl(nla_get_be32(tb[NFTA_CT_SREG]));
+	err = nft_validate_input_register(priv->sreg);
+	if (err < 0)
+		return err;
+
 	err = nft_ct_l3proto_try_module_get(ctx->afi->family);
 	if (err < 0)
 		return err;
@@ -370,7 +362,7 @@ static const struct nft_expr_ops nft_ct_get_ops = {
 	.type		= &nft_ct_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ct)),
 	.eval		= nft_ct_get_eval,
-	.init		= nft_ct_init,
+	.init		= nft_ct_get_init,
 	.destroy	= nft_ct_destroy,
 	.dump		= nft_ct_get_dump,
 };
@@ -379,7 +371,7 @@ static const struct nft_expr_ops nft_ct_set_ops = {
 	.type		= &nft_ct_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ct)),
 	.eval		= nft_ct_set_eval,
-	.init		= nft_ct_init,
+	.init		= nft_ct_set_init,
 	.destroy	= nft_ct_destroy,
 	.dump		= nft_ct_set_dump,
 };
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 3b1ad876d6b..4080ed6a072 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/list.h>
+#include <linux/log2.h>
 #include <linux/jhash.h>
 #include <linux/netlink.h>
 #include <linux/vmalloc.h>
@@ -19,7 +20,7 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 
-#define NFT_HASH_MIN_SIZE	4
+#define NFT_HASH_MIN_SIZE	4UL
 
 struct nft_hash {
 	struct nft_hash_table __rcu	*tbl;
@@ -27,7 +28,6 @@ struct nft_hash {
 
 struct nft_hash_table {
 	unsigned int			size;
-	unsigned int			elements;
 	struct nft_hash_elem __rcu	*buckets[];
 };
 
@@ -76,10 +76,12 @@ static bool nft_hash_lookup(const struct nft_set *set,
 
 static void nft_hash_tbl_free(const struct nft_hash_table *tbl)
 {
-	if (is_vmalloc_addr(tbl))
-		vfree(tbl);
-	else
-		kfree(tbl);
+	kvfree(tbl);
+}
+
+static unsigned int nft_hash_tbl_size(unsigned int nelem)
+{
+	return max(roundup_pow_of_two(nelem * 4 / 3), NFT_HASH_MIN_SIZE);
 }
 
 static struct nft_hash_table *nft_hash_tbl_alloc(unsigned int nbuckets)
@@ -161,7 +163,6 @@ static int nft_hash_tbl_expand(const struct nft_set *set, struct nft_hash *priv)
 			break;
 		}
 	}
-	ntbl->elements = tbl->elements;
 
 	/* Publish new table */
 	rcu_assign_pointer(priv->tbl, ntbl);
@@ -201,7 +202,6 @@ static int nft_hash_tbl_shrink(const struct nft_set *set, struct nft_hash *priv)
 			;
 		RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]);
 	}
-	ntbl->elements = tbl->elements;
 
 	/* Publish new table */
 	rcu_assign_pointer(priv->tbl, ntbl);
@@ -237,10 +237,9 @@ static int nft_hash_insert(const struct nft_set *set,
 	h = nft_hash_data(&he->key, tbl->size, set->klen);
 	RCU_INIT_POINTER(he->next, tbl->buckets[h]);
 	rcu_assign_pointer(tbl->buckets[h], he);
-	tbl->elements++;
 
 	/* Expand table when exceeding 75% load */
-	if (tbl->elements > tbl->size / 4 * 3)
+	if (set->nelems + 1 > tbl->size / 4 * 3)
 		nft_hash_tbl_expand(set, priv);
 
 	return 0;
@@ -268,10 +267,9 @@ static void nft_hash_remove(const struct nft_set *set,
 	RCU_INIT_POINTER(*pprev, he->next);
 	synchronize_rcu();
 	kfree(he);
-	tbl->elements--;
 
 	/* Shrink table beneath 30% load */
-	if (tbl->elements < tbl->size * 3 / 10 &&
+	if (set->nelems - 1 < tbl->size * 3 / 10 &&
 	    tbl->size > NFT_HASH_MIN_SIZE)
 		nft_hash_tbl_shrink(set, priv);
 }
@@ -335,17 +333,23 @@ static unsigned int nft_hash_privsize(const struct nlattr * const nla[])
 }
 
 static int nft_hash_init(const struct nft_set *set,
+			 const struct nft_set_desc *desc,
 			 const struct nlattr * const tb[])
 {
 	struct nft_hash *priv = nft_set_priv(set);
 	struct nft_hash_table *tbl;
+	unsigned int size;
 
 	if (unlikely(!nft_hash_rnd_initted)) {
 		get_random_bytes(&nft_hash_rnd, 4);
 		nft_hash_rnd_initted = true;
 	}
 
-	tbl = nft_hash_tbl_alloc(NFT_HASH_MIN_SIZE);
+	size = NFT_HASH_MIN_SIZE;
+	if (desc->size)
+		size = nft_hash_tbl_size(desc->size);
+
+	tbl = nft_hash_tbl_alloc(size);
 	if (tbl == NULL)
 		return -ENOMEM;
 	RCU_INIT_POINTER(priv->tbl, tbl);
@@ -369,8 +373,37 @@ static void nft_hash_destroy(const struct nft_set *set)
 	kfree(tbl);
 }
 
+static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features,
+			      struct nft_set_estimate *est)
+{
+	unsigned int esize;
+
+	esize = sizeof(struct nft_hash_elem);
+	if (features & NFT_SET_MAP)
+		esize += FIELD_SIZEOF(struct nft_hash_elem, data[0]);
+
+	if (desc->size) {
+		est->size = sizeof(struct nft_hash) +
+			    nft_hash_tbl_size(desc->size) *
+			    sizeof(struct nft_hash_elem *) +
+			    desc->size * esize;
+	} else {
+		/* Resizing happens when the load drops below 30% or goes
+		 * above 75%. The average of 52.5% load (approximated by 50%)
+		 * is used for the size estimation of the hash buckets,
+		 * meaning we calculate two buckets per element.
+		 */
+		est->size = esize + 2 * sizeof(struct nft_hash_elem *);
+	}
+
+	est->class = NFT_SET_CLASS_O_1;
+
+	return true;
+}
+
 static struct nft_set_ops nft_hash_ops __read_mostly = {
 	.privsize       = nft_hash_privsize,
+	.estimate	= nft_hash_estimate,
 	.init		= nft_hash_init,
 	.destroy	= nft_hash_destroy,
 	.get		= nft_hash_get,
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 7fd2bea8aa2..6404a726d17 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -56,8 +56,14 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 		return -EINVAL;
 
 	set = nf_tables_set_lookup(ctx->table, tb[NFTA_LOOKUP_SET]);
-	if (IS_ERR(set))
-		return PTR_ERR(set);
+	if (IS_ERR(set)) {
+		if (tb[NFTA_LOOKUP_SET_ID]) {
+			set = nf_tables_set_lookup_byid(ctx->net,
+							tb[NFTA_LOOKUP_SET_ID]);
+		}
+		if (IS_ERR(set))
+			return PTR_ERR(set);
+	}
 
 	priv->sreg = ntohl(nla_get_be32(tb[NFTA_LOOKUP_SREG]));
 	err = nft_validate_input_register(priv->sreg);
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 425cf39af89..852b178c6ae 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -18,18 +18,11 @@
 #include <net/sock.h>
 #include <net/tcp_states.h> /* for TCP_TIME_WAIT */
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_meta.h>
 
-struct nft_meta {
-	enum nft_meta_keys	key:8;
-	union {
-		enum nft_registers	dreg:8;
-		enum nft_registers	sreg:8;
-	};
-};
-
-static void nft_meta_get_eval(const struct nft_expr *expr,
-			      struct nft_data data[NFT_REG_MAX + 1],
-			      const struct nft_pktinfo *pkt)
+void nft_meta_get_eval(const struct nft_expr *expr,
+		       struct nft_data data[NFT_REG_MAX + 1],
+		       const struct nft_pktinfo *pkt)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 	const struct sk_buff *skb = pkt->skb;
@@ -140,10 +133,11 @@ static void nft_meta_get_eval(const struct nft_expr *expr,
 err:
 	data[NFT_REG_VERDICT].verdict = NFT_BREAK;
 }
+EXPORT_SYMBOL_GPL(nft_meta_get_eval);
 
-static void nft_meta_set_eval(const struct nft_expr *expr,
-			      struct nft_data data[NFT_REG_MAX + 1],
-			      const struct nft_pktinfo *pkt)
+void nft_meta_set_eval(const struct nft_expr *expr,
+		       struct nft_data data[NFT_REG_MAX + 1],
+		       const struct nft_pktinfo *pkt)
 {
 	const struct nft_meta *meta = nft_expr_priv(expr);
 	struct sk_buff *skb = pkt->skb;
@@ -163,28 +157,24 @@ static void nft_meta_set_eval(const struct nft_expr *expr,
 		WARN_ON(1);
 	}
 }
+EXPORT_SYMBOL_GPL(nft_meta_set_eval);
 
-static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
+const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = {
 	[NFTA_META_DREG]	= { .type = NLA_U32 },
 	[NFTA_META_KEY]		= { .type = NLA_U32 },
 	[NFTA_META_SREG]	= { .type = NLA_U32 },
 };
+EXPORT_SYMBOL_GPL(nft_meta_policy);
 
-static int nft_meta_init_validate_set(uint32_t key)
+int nft_meta_get_init(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nlattr * const tb[])
 {
-	switch (key) {
-	case NFT_META_MARK:
-	case NFT_META_PRIORITY:
-	case NFT_META_NFTRACE:
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+	struct nft_meta *priv = nft_expr_priv(expr);
+	int err;
 
-static int nft_meta_init_validate_get(uint32_t key)
-{
-	switch (key) {
+	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
+	switch (priv->key) {
 	case NFT_META_LEN:
 	case NFT_META_PROTOCOL:
 	case NFT_META_NFPROTO:
@@ -205,39 +195,41 @@ static int nft_meta_init_validate_get(uint32_t key)
 #ifdef CONFIG_NETWORK_SECMARK
 	case NFT_META_SECMARK:
 #endif
-		return 0;
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
+	priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG]));
+	err = nft_validate_output_register(priv->dreg);
+	if (err < 0)
+		return err;
+
+	err = nft_validate_data_load(ctx, priv->dreg, NULL, NFT_DATA_VALUE);
+	if (err < 0)
+		return err;
+
+	return 0;
 }
+EXPORT_SYMBOL_GPL(nft_meta_get_init);
 
-static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			 const struct nlattr * const tb[])
+int nft_meta_set_init(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nlattr * const tb[])
 {
 	struct nft_meta *priv = nft_expr_priv(expr);
 	int err;
 
 	priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
-
-	if (tb[NFTA_META_DREG]) {
-		err = nft_meta_init_validate_get(priv->key);
-		if (err < 0)
-			return err;
-
-		priv->dreg = ntohl(nla_get_be32(tb[NFTA_META_DREG]));
-		err = nft_validate_output_register(priv->dreg);
-		if (err < 0)
-			return err;
-
-		return nft_validate_data_load(ctx, priv->dreg, NULL,
-					      NFT_DATA_VALUE);
+	switch (priv->key) {
+	case NFT_META_MARK:
+	case NFT_META_PRIORITY:
+	case NFT_META_NFTRACE:
+		break;
+	default:
+		return -EOPNOTSUPP;
 	}
 
-	err = nft_meta_init_validate_set(priv->key);
-	if (err < 0)
-		return err;
-
 	priv->sreg = ntohl(nla_get_be32(tb[NFTA_META_SREG]));
 	err = nft_validate_input_register(priv->sreg);
 	if (err < 0)
@@ -245,9 +237,10 @@ static int nft_meta_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nft_meta_set_init);
 
-static int nft_meta_get_dump(struct sk_buff *skb,
-			     const struct nft_expr *expr)
+int nft_meta_get_dump(struct sk_buff *skb,
+		      const struct nft_expr *expr)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 
@@ -260,9 +253,10 @@ static int nft_meta_get_dump(struct sk_buff *skb,
 nla_put_failure:
 	return -1;
 }
+EXPORT_SYMBOL_GPL(nft_meta_get_dump);
 
-static int nft_meta_set_dump(struct sk_buff *skb,
-			     const struct nft_expr *expr)
+int nft_meta_set_dump(struct sk_buff *skb,
+		      const struct nft_expr *expr)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 
@@ -276,13 +270,14 @@ static int nft_meta_set_dump(struct sk_buff *skb,
 nla_put_failure:
 	return -1;
 }
+EXPORT_SYMBOL_GPL(nft_meta_set_dump);
 
 static struct nft_expr_type nft_meta_type;
 static const struct nft_expr_ops nft_meta_get_ops = {
 	.type		= &nft_meta_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
 	.eval		= nft_meta_get_eval,
-	.init		= nft_meta_init,
+	.init		= nft_meta_get_init,
 	.dump		= nft_meta_get_dump,
 };
 
@@ -290,7 +285,7 @@ static const struct nft_expr_ops nft_meta_set_ops = {
 	.type		= &nft_meta_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
 	.eval		= nft_meta_set_eval,
-	.init		= nft_meta_init,
+	.init		= nft_meta_set_init,
 	.dump		= nft_meta_set_dump,
 };
 
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index a0195d28bcf..79ff58cd36d 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -175,12 +175,14 @@ static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
 	if (nla_put_be32(skb,
 			 NFTA_NAT_REG_ADDR_MAX, htonl(priv->sreg_addr_max)))
 		goto nla_put_failure;
-	if (nla_put_be32(skb,
-			 NFTA_NAT_REG_PROTO_MIN, htonl(priv->sreg_proto_min)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb,
-			 NFTA_NAT_REG_PROTO_MAX, htonl(priv->sreg_proto_max)))
-		goto nla_put_failure;
+	if (priv->sreg_proto_min) {
+		if (nla_put_be32(skb, NFTA_NAT_REG_PROTO_MIN,
+				 htonl(priv->sreg_proto_min)))
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFTA_NAT_REG_PROTO_MAX,
+				 htonl(priv->sreg_proto_max)))
+			goto nla_put_failure;
+	}
 	return 0;
 
 nla_put_failure:
diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c
index e21d69d1350..e1836ff8819 100644
--- a/net/netfilter/nft_rbtree.c
+++ b/net/netfilter/nft_rbtree.c
@@ -18,6 +18,8 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 
+static DEFINE_SPINLOCK(nft_rbtree_lock);
+
 struct nft_rbtree {
 	struct rb_root		root;
 };
@@ -38,6 +40,7 @@ static bool nft_rbtree_lookup(const struct nft_set *set,
 	const struct rb_node *parent = priv->root.rb_node;
 	int d;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
@@ -53,6 +56,8 @@ found:
 				goto out;
 			if (set->flags & NFT_SET_MAP)
 				nft_data_copy(data, rbe->data);
+
+			spin_unlock_bh(&nft_rbtree_lock);
 			return true;
 		}
 	}
@@ -62,6 +67,7 @@ found:
 		goto found;
 	}
 out:
+	spin_unlock_bh(&nft_rbtree_lock);
 	return false;
 }
 
@@ -124,9 +130,12 @@ static int nft_rbtree_insert(const struct nft_set *set,
 	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 		nft_data_copy(rbe->data, &elem->data);
 
+	spin_lock_bh(&nft_rbtree_lock);
 	err = __nft_rbtree_insert(set, rbe);
 	if (err < 0)
 		kfree(rbe);
+
+	spin_unlock_bh(&nft_rbtree_lock);
 	return err;
 }
 
@@ -136,7 +145,9 @@ static void nft_rbtree_remove(const struct nft_set *set,
 	struct nft_rbtree *priv = nft_set_priv(set);
 	struct nft_rbtree_elem *rbe = elem->cookie;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	rb_erase(&rbe->node, &priv->root);
+	spin_unlock_bh(&nft_rbtree_lock);
 	kfree(rbe);
 }
 
@@ -147,6 +158,7 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
 	struct nft_rbtree_elem *rbe;
 	int d;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	while (parent != NULL) {
 		rbe = rb_entry(parent, struct nft_rbtree_elem, node);
 
@@ -161,9 +173,11 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
 			    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 				nft_data_copy(&elem->data, rbe->data);
 			elem->flags = rbe->flags;
+			spin_unlock_bh(&nft_rbtree_lock);
 			return 0;
 		}
 	}
+	spin_unlock_bh(&nft_rbtree_lock);
 	return -ENOENT;
 }
 
@@ -176,6 +190,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 	struct nft_set_elem elem;
 	struct rb_node *node;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) {
 		if (iter->count < iter->skip)
 			goto cont;
@@ -188,11 +203,14 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 		elem.flags = rbe->flags;
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
-		if (iter->err < 0)
+		if (iter->err < 0) {
+			spin_unlock_bh(&nft_rbtree_lock);
 			return;
+		}
 cont:
 		iter->count++;
 	}
+	spin_unlock_bh(&nft_rbtree_lock);
 }
 
 static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[])
@@ -201,6 +219,7 @@ static unsigned int nft_rbtree_privsize(const struct nlattr * const nla[])
 }
 
 static int nft_rbtree_init(const struct nft_set *set,
+			   const struct nft_set_desc *desc,
 			   const struct nlattr * const nla[])
 {
 	struct nft_rbtree *priv = nft_set_priv(set);
@@ -215,15 +234,37 @@ static void nft_rbtree_destroy(const struct nft_set *set)
 	struct nft_rbtree_elem *rbe;
 	struct rb_node *node;
 
+	spin_lock_bh(&nft_rbtree_lock);
 	while ((node = priv->root.rb_node) != NULL) {
 		rb_erase(node, &priv->root);
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 		nft_rbtree_elem_destroy(set, rbe);
 	}
+	spin_unlock_bh(&nft_rbtree_lock);
+}
+
+static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
+				struct nft_set_estimate *est)
+{
+	unsigned int nsize;
+
+	nsize = sizeof(struct nft_rbtree_elem);
+	if (features & NFT_SET_MAP)
+		nsize += FIELD_SIZEOF(struct nft_rbtree_elem, data[0]);
+
+	if (desc->size)
+		est->size = sizeof(struct nft_rbtree) + desc->size * nsize;
+	else
+		est->size = nsize;
+
+	est->class = NFT_SET_CLASS_O_LOG_N;
+
+	return true;
 }
 
 static struct nft_set_ops nft_rbtree_ops __read_mostly = {
 	.privsize	= nft_rbtree_privsize,
+	.estimate	= nft_rbtree_estimate,
 	.init		= nft_rbtree_init,
 	.destroy	= nft_rbtree_destroy,
 	.insert		= nft_rbtree_insert,
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 12d4da8e6c7..bbffdbdaf60 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -23,10 +23,11 @@ MODULE_ALIAS("ip6t_bpf");
 static int bpf_mt_check(const struct xt_mtchk_param *par)
 {
 	struct xt_bpf_info *info = par->matchinfo;
-	struct sock_fprog program;
+	struct sock_fprog_kern program;
 
 	program.len = info->bpf_program_num_elem;
-	program.filter = (struct sock_filter __user *) info->bpf_program;
+	program.filter = info->bpf_program;
+
 	if (sk_unattached_filter_create(&info->filter, &program)) {
 		pr_info("bpf: check failed: parse error\n");
 		return -EINVAL;
diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c
index b3be0ef21f1..8c646ed9c92 100644
--- a/net/netfilter/xt_nfacct.c
+++ b/net/netfilter/xt_nfacct.c
@@ -21,11 +21,14 @@ MODULE_ALIAS("ip6t_nfacct");
 
 static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par)
 {
+	int overquota;
 	const struct xt_nfacct_match_info *info = par->targinfo;
 
 	nfnl_acct_update(skb, info->nfacct);
 
-	return true;
+	overquota = nfnl_acct_overquota(skb, info->nfacct);
+
+	return overquota == NFACCT_UNDERQUOTA ? false : true;
 }
 
 static int
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 1e657cf715c..a9faae89f95 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -313,10 +313,7 @@ out:
 
 static void recent_table_free(void *addr)
 {
-	if (is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
+	kvfree(addr);
 }
 
 static int recent_mt_check(const struct xt_mtchk_param *par,
diff --git a/net/netfilter/xt_repldata.h b/net/netfilter/xt_repldata.h
index 6efe4e5a81c..8fd324116e6 100644
--- a/net/netfilter/xt_repldata.h
+++ b/net/netfilter/xt_repldata.h
@@ -5,23 +5,35 @@
  * they serve as the hanging-off data accessed through repl.data[].
  */
 
+/* tbl has the following structure equivalent, but is C99 compliant:
+ * struct {
+ *	struct type##_replace repl;
+ *	struct type##_standard entries[nhooks];
+ *	struct type##_error term;
+ * } *tbl;
+ */
+
 #define xt_alloc_initial_table(type, typ2) ({ \
 	unsigned int hook_mask = info->valid_hooks; \
 	unsigned int nhooks = hweight32(hook_mask); \
 	unsigned int bytes = 0, hooknum = 0, i = 0; \
 	struct { \
 		struct type##_replace repl; \
-		struct type##_standard entries[nhooks]; \
-		struct type##_error term; \
-	} *tbl = kzalloc(sizeof(*tbl), GFP_KERNEL); \
+		struct type##_standard entries[]; \
+	} *tbl; \
+	struct type##_error *term; \
+	size_t term_offset = (offsetof(typeof(*tbl), entries[nhooks]) + \
+		__alignof__(*term) - 1) & ~(__alignof__(*term) - 1); \
+	tbl = kzalloc(term_offset + sizeof(*term), GFP_KERNEL); \
 	if (tbl == NULL) \
 		return NULL; \
+	term = (struct type##_error *)&(((char *)tbl)[term_offset]); \
 	strncpy(tbl->repl.name, info->name, sizeof(tbl->repl.name)); \
-	tbl->term = (struct type##_error)typ2##_ERROR_INIT;  \
+	*term = (struct type##_error)typ2##_ERROR_INIT;  \
 	tbl->repl.valid_hooks = hook_mask; \
 	tbl->repl.num_entries = nhooks + 1; \
 	tbl->repl.size = nhooks * sizeof(struct type##_standard) + \
-	                 sizeof(struct type##_error); \
+			 sizeof(struct type##_error); \
 	for (; hook_mask != 0; hook_mask >>= 1, ++hooknum) { \
 		if (!(hook_mask & 1)) \
 			continue; \
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f22757a29cd..e6fac7e3db5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -636,7 +636,7 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock,
 		while (nlk->cb_running && netlink_dump_space(nlk)) {
 			err = netlink_dump(sk);
 			if (err < 0) {
-				sk->sk_err = err;
+				sk->sk_err = -err;
 				sk->sk_error_report(sk);
 				break;
 			}
@@ -1206,7 +1206,8 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	struct module *module = NULL;
 	struct mutex *cb_mutex;
 	struct netlink_sock *nlk;
-	void (*bind)(int group);
+	int (*bind)(int group);
+	void (*unbind)(int group);
 	int err = 0;
 
 	sock->state = SS_UNCONNECTED;
@@ -1232,6 +1233,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 		err = -EPROTONOSUPPORT;
 	cb_mutex = nl_table[protocol].cb_mutex;
 	bind = nl_table[protocol].bind;
+	unbind = nl_table[protocol].unbind;
 	netlink_unlock_table();
 
 	if (err < 0)
@@ -1248,6 +1250,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	nlk = nlk_sk(sock->sk);
 	nlk->module = module;
 	nlk->netlink_bind = bind;
+	nlk->netlink_unbind = unbind;
 out:
 	return err;
 
@@ -1301,6 +1304,7 @@ static int netlink_release(struct socket *sock)
 			kfree_rcu(old, rcu);
 			nl_table[sk->sk_protocol].module = NULL;
 			nl_table[sk->sk_protocol].bind = NULL;
+			nl_table[sk->sk_protocol].unbind = NULL;
 			nl_table[sk->sk_protocol].flags = 0;
 			nl_table[sk->sk_protocol].registered = 0;
 		}
@@ -1478,6 +1482,19 @@ static int netlink_realloc_groups(struct sock *sk)
 	return err;
 }
 
+static void netlink_unbind(int group, long unsigned int groups,
+			   struct netlink_sock *nlk)
+{
+	int undo;
+
+	if (!nlk->netlink_unbind)
+		return;
+
+	for (undo = 0; undo < group; undo++)
+		if (test_bit(group, &groups))
+			nlk->netlink_unbind(undo);
+}
+
 static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			int addr_len)
 {
@@ -1486,6 +1503,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
+	long unsigned int groups = nladdr->nl_groups;
 
 	if (addr_len < sizeof(struct sockaddr_nl))
 		return -EINVAL;
@@ -1494,7 +1512,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		return -EINVAL;
 
 	/* Only superuser is allowed to listen multicasts */
-	if (nladdr->nl_groups) {
+	if (groups) {
 		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
@@ -1502,37 +1520,45 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			return err;
 	}
 
-	if (nlk->portid) {
+	if (nlk->portid)
 		if (nladdr->nl_pid != nlk->portid)
 			return -EINVAL;
-	} else {
+
+	if (nlk->netlink_bind && groups) {
+		int group;
+
+		for (group = 0; group < nlk->ngroups; group++) {
+			if (!test_bit(group, &groups))
+				continue;
+			err = nlk->netlink_bind(group);
+			if (!err)
+				continue;
+			netlink_unbind(group, groups, nlk);
+			return err;
+		}
+	}
+
+	if (!nlk->portid) {
 		err = nladdr->nl_pid ?
 			netlink_insert(sk, net, nladdr->nl_pid) :
 			netlink_autobind(sock);
-		if (err)
+		if (err) {
+			netlink_unbind(nlk->ngroups - 1, groups, nlk);
 			return err;
+		}
 	}
 
-	if (!nladdr->nl_groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
+	if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
 		return 0;
 
 	netlink_table_grab();
 	netlink_update_subscriptions(sk, nlk->subscriptions +
-					 hweight32(nladdr->nl_groups) -
+					 hweight32(groups) -
 					 hweight32(nlk->groups[0]));
-	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups;
+	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups;
 	netlink_update_listeners(sk);
 	netlink_table_ungrab();
 
-	if (nlk->netlink_bind && nlk->groups[0]) {
-		int i;
-
-		for (i = 0; i < nlk->ngroups; i++) {
-			if (test_bit(i, nlk->groups))
-				nlk->netlink_bind(i);
-		}
-	}
-
 	return 0;
 }
 
@@ -2170,13 +2196,17 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			return err;
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
+		if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) {
+			err = nlk->netlink_bind(val);
+			if (err)
+				return err;
+		}
 		netlink_table_grab();
 		netlink_update_socket_mc(nlk, val,
 					 optname == NETLINK_ADD_MEMBERSHIP);
 		netlink_table_ungrab();
-
-		if (nlk->netlink_bind)
-			nlk->netlink_bind(val);
+		if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
+			nlk->netlink_unbind(val);
 
 		err = 0;
 		break;
@@ -2453,7 +2483,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	    atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
 		ret = netlink_dump(sk);
 		if (ret) {
-			sk->sk_err = ret;
+			sk->sk_err = -ret;
 			sk->sk_error_report(sk);
 		}
 	}
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index ed13a790b00..0b59d441f5b 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -38,7 +38,8 @@ struct netlink_sock {
 	struct mutex		*cb_mutex;
 	struct mutex		cb_def_mutex;
 	void			(*netlink_rcv)(struct sk_buff *skb);
-	void			(*netlink_bind)(int group);
+	int			(*netlink_bind)(int group);
+	void			(*netlink_unbind)(int group);
 	struct module		*module;
 #ifdef CONFIG_NETLINK_MMAP
 	struct mutex		pg_vec_lock;
@@ -74,7 +75,8 @@ struct netlink_table {
 	unsigned int		groups;
 	struct mutex		*cb_mutex;
 	struct module		*module;
-	void			(*bind)(int group);
+	int			(*bind)(int group);
+	void			(*unbind)(int group);
 	bool			(*compare)(struct net *net, struct sock *sock);
 	int			registered;
 };
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index a3ba3ca0ff9..76393f2f4b2 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -317,7 +317,7 @@ static void genl_unregister_mc_groups(struct genl_family *family)
 	}
 }
 
-static int genl_validate_ops(struct genl_family *family)
+static int genl_validate_ops(const struct genl_family *family)
 {
 	const struct genl_ops *ops = family->ops;
 	unsigned int n_ops = family->n_ops;
@@ -337,10 +337,6 @@ static int genl_validate_ops(struct genl_family *family)
 				return -EINVAL;
 	}
 
-	/* family is not registered yet, so no locking needed */
-	family->ops = ops;
-	family->n_ops = n_ops;
-
 	return 0;
 }
 
diff --git a/net/nfc/digital.h b/net/nfc/digital.h
index 3759add68b1..71ad7eefddd 100644
--- a/net/nfc/digital.h
+++ b/net/nfc/digital.h
@@ -71,6 +71,7 @@ static inline int digital_in_send_cmd(struct nfc_digital_dev *ddev,
 void digital_poll_next_tech(struct nfc_digital_dev *ddev);
 
 int digital_in_send_sens_req(struct nfc_digital_dev *ddev, u8 rf_tech);
+int digital_in_send_sensb_req(struct nfc_digital_dev *ddev, u8 rf_tech);
 int digital_in_send_sensf_req(struct nfc_digital_dev *ddev, u8 rf_tech);
 int digital_in_send_iso15693_inv_req(struct nfc_digital_dev *ddev, u8 rf_tech);
 
diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index e01e15dbf1a..a6ce3c627e4 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -22,6 +22,8 @@
 #define DIGITAL_PROTO_NFCA_RF_TECH \
 	(NFC_PROTO_JEWEL_MASK | NFC_PROTO_MIFARE_MASK | NFC_PROTO_NFC_DEP_MASK)
 
+#define DIGITAL_PROTO_NFCB_RF_TECH	NFC_PROTO_ISO14443_B_MASK
+
 #define DIGITAL_PROTO_NFCF_RF_TECH \
 	(NFC_PROTO_FELICA_MASK | NFC_PROTO_NFC_DEP_MASK)
 
@@ -345,6 +347,12 @@ int digital_target_found(struct nfc_digital_dev *ddev,
 		add_crc = digital_skb_add_crc_a;
 		break;
 
+	case NFC_PROTO_ISO14443_B:
+		framing = NFC_DIGITAL_FRAMING_NFCB_T4T;
+		check_crc = digital_skb_check_crc_b;
+		add_crc = digital_skb_add_crc_b;
+		break;
+
 	default:
 		pr_err("Invalid protocol %d\n", protocol);
 		return -EINVAL;
@@ -378,6 +386,8 @@ int digital_target_found(struct nfc_digital_dev *ddev,
 
 void digital_poll_next_tech(struct nfc_digital_dev *ddev)
 {
+	u8 rand_mod;
+
 	digital_switch_rf(ddev, 0);
 
 	mutex_lock(&ddev->poll_lock);
@@ -387,8 +397,8 @@ void digital_poll_next_tech(struct nfc_digital_dev *ddev)
 		return;
 	}
 
-	ddev->poll_tech_index = (ddev->poll_tech_index + 1) %
-				ddev->poll_tech_count;
+	get_random_bytes(&rand_mod, sizeof(rand_mod));
+	ddev->poll_tech_index = rand_mod % ddev->poll_tech_count;
 
 	mutex_unlock(&ddev->poll_lock);
 
@@ -475,6 +485,10 @@ static int digital_start_poll(struct nfc_dev *nfc_dev, __u32 im_protocols,
 		digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106A,
 				      digital_in_send_sens_req);
 
+	if (matching_im_protocols & DIGITAL_PROTO_NFCB_RF_TECH)
+		digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_106B,
+				      digital_in_send_sensb_req);
+
 	if (matching_im_protocols & DIGITAL_PROTO_NFCF_RF_TECH) {
 		digital_add_poll_tech(ddev, NFC_DIGITAL_RF_TECH_212F,
 				      digital_in_send_sensf_req);
@@ -635,7 +649,8 @@ static void digital_in_send_complete(struct nfc_digital_dev *ddev, void *arg,
 		goto done;
 	}
 
-	if (ddev->curr_protocol == NFC_PROTO_ISO14443) {
+	if ((ddev->curr_protocol == NFC_PROTO_ISO14443) ||
+	    (ddev->curr_protocol == NFC_PROTO_ISO14443_B)) {
 		rc = digital_in_iso_dep_pull_sod(ddev, resp);
 		if (rc)
 			goto done;
@@ -676,7 +691,8 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target,
 		goto exit;
 	}
 
-	if (ddev->curr_protocol == NFC_PROTO_ISO14443) {
+	if ((ddev->curr_protocol == NFC_PROTO_ISO14443) ||
+	    (ddev->curr_protocol == NFC_PROTO_ISO14443_B)) {
 		rc = digital_in_iso_dep_push_sod(ddev, skb);
 		if (rc)
 			goto exit;
@@ -747,6 +763,8 @@ struct nfc_digital_dev *nfc_digital_allocate_device(struct nfc_digital_ops *ops,
 		ddev->protocols |= NFC_PROTO_ISO15693_MASK;
 	if (supported_protocols & NFC_PROTO_ISO14443_MASK)
 		ddev->protocols |= NFC_PROTO_ISO14443_MASK;
+	if (supported_protocols & NFC_PROTO_ISO14443_B_MASK)
+		ddev->protocols |= NFC_PROTO_ISO14443_B_MASK;
 
 	ddev->tx_headroom = tx_headroom + DIGITAL_MAX_HEADER_LEN;
 	ddev->tx_tailroom = tx_tailroom + DIGITAL_CRC_LEN;
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index d4ed25ff723..171cb9949ab 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -224,9 +224,8 @@ int digital_in_send_atr_req(struct nfc_digital_dev *ddev,
 
 	ddev->skb_add_crc(skb);
 
-	digital_in_send_cmd(ddev, skb, 500, digital_in_recv_atr_res, target);
-
-	return 0;
+	return digital_in_send_cmd(ddev, skb, 500, digital_in_recv_atr_res,
+				   target);
 }
 
 static int digital_in_send_rtox(struct nfc_digital_dev *ddev,
diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c
index 278c3fed27e..c2c1c0189b7 100644
--- a/net/nfc/digital_technology.c
+++ b/net/nfc/digital_technology.c
@@ -41,6 +41,24 @@
 #define DIGITAL_MIFARE_READ_RES_LEN 16
 #define DIGITAL_MIFARE_ACK_RES	0x0A
 
+#define DIGITAL_CMD_SENSB_REQ			0x05
+#define DIGITAL_SENSB_ADVANCED			BIT(5)
+#define DIGITAL_SENSB_EXTENDED			BIT(4)
+#define DIGITAL_SENSB_ALLB_REQ			BIT(3)
+#define DIGITAL_SENSB_N(n)			((n) & 0x7)
+
+#define DIGITAL_CMD_SENSB_RES			0x50
+
+#define DIGITAL_CMD_ATTRIB_REQ			0x1D
+#define DIGITAL_ATTRIB_P1_TR0_DEFAULT		(0x0 << 6)
+#define DIGITAL_ATTRIB_P1_TR1_DEFAULT		(0x0 << 4)
+#define DIGITAL_ATTRIB_P1_SUPRESS_EOS		BIT(3)
+#define DIGITAL_ATTRIB_P1_SUPRESS_SOS		BIT(2)
+#define DIGITAL_ATTRIB_P2_LISTEN_POLL_1		(0x0 << 6)
+#define DIGITAL_ATTRIB_P2_POLL_LISTEN_1		(0x0 << 4)
+#define DIGITAL_ATTRIB_P2_MAX_FRAME_256		0x8
+#define DIGITAL_ATTRIB_P4_DID(n)		((n) & 0xf)
+
 #define DIGITAL_CMD_SENSF_REQ	0x00
 #define DIGITAL_CMD_SENSF_RES	0x01
 
@@ -75,6 +93,7 @@ static const u8 digital_ats_fsc[] = {
 };
 
 #define DIGITAL_ATS_FSCI(t0) ((t0) & 0x0F)
+#define DIGITAL_SENSB_FSCI(pi2) (((pi2) & 0xF0) >> 4)
 #define DIGITAL_ATS_MAX_FSC  256
 
 #define DIGITAL_RATS_BYTE1 0xE0
@@ -92,6 +111,32 @@ struct digital_sel_req {
 	u8 bcc;
 } __packed;
 
+struct digital_sensb_req {
+	u8 cmd;
+	u8 afi;
+	u8 param;
+} __packed;
+
+struct digital_sensb_res {
+	u8 cmd;
+	u8 nfcid0[4];
+	u8 app_data[4];
+	u8 proto_info[3];
+} __packed;
+
+struct digital_attrib_req {
+	u8 cmd;
+	u8 nfcid0[4];
+	u8 param1;
+	u8 param2;
+	u8 param3;
+	u8 param4;
+} __packed;
+
+struct digital_attrib_res {
+	u8 mbli_did;
+} __packed;
+
 struct digital_sensf_req {
 	u8 cmd;
 	u8 sc1;
@@ -531,6 +576,175 @@ int digital_in_recv_mifare_res(struct sk_buff *resp)
 	return -EIO;
 }
 
+static void digital_in_recv_attrib_res(struct nfc_digital_dev *ddev, void *arg,
+				       struct sk_buff *resp)
+{
+	struct nfc_target *target = arg;
+	struct digital_attrib_res *attrib_res;
+	int rc;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		resp = NULL;
+		goto exit;
+	}
+
+	if (resp->len < sizeof(*attrib_res)) {
+		PROTOCOL_ERR("12.6.2");
+		rc = -EIO;
+		goto exit;
+	}
+
+	attrib_res = (struct digital_attrib_res *)resp->data;
+
+	if (attrib_res->mbli_did & 0x0f) {
+		PROTOCOL_ERR("12.6.2.1");
+		rc = -EIO;
+		goto exit;
+	}
+
+	rc = digital_target_found(ddev, target, NFC_PROTO_ISO14443_B);
+
+exit:
+	dev_kfree_skb(resp);
+	kfree(target);
+
+	if (rc)
+		digital_poll_next_tech(ddev);
+}
+
+static int digital_in_send_attrib_req(struct nfc_digital_dev *ddev,
+			       struct nfc_target *target,
+			       struct digital_sensb_res *sensb_res)
+{
+	struct digital_attrib_req *attrib_req;
+	struct sk_buff *skb;
+	int rc;
+
+	skb = digital_skb_alloc(ddev, sizeof(*attrib_req));
+	if (!skb)
+		return -ENOMEM;
+
+	attrib_req = (struct digital_attrib_req *)skb_put(skb,
+							  sizeof(*attrib_req));
+
+	attrib_req->cmd = DIGITAL_CMD_ATTRIB_REQ;
+	memcpy(attrib_req->nfcid0, sensb_res->nfcid0,
+	       sizeof(attrib_req->nfcid0));
+	attrib_req->param1 = DIGITAL_ATTRIB_P1_TR0_DEFAULT |
+			     DIGITAL_ATTRIB_P1_TR1_DEFAULT;
+	attrib_req->param2 = DIGITAL_ATTRIB_P2_LISTEN_POLL_1 |
+			     DIGITAL_ATTRIB_P2_POLL_LISTEN_1 |
+			     DIGITAL_ATTRIB_P2_MAX_FRAME_256;
+	attrib_req->param3 = sensb_res->proto_info[1] & 0x07;
+	attrib_req->param4 = DIGITAL_ATTRIB_P4_DID(0);
+
+	rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_attrib_res,
+				 target);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
+static void digital_in_recv_sensb_res(struct nfc_digital_dev *ddev, void *arg,
+				      struct sk_buff *resp)
+{
+	struct nfc_target *target = NULL;
+	struct digital_sensb_res *sensb_res;
+	u8 fsci;
+	int rc;
+
+	if (IS_ERR(resp)) {
+		rc = PTR_ERR(resp);
+		resp = NULL;
+		goto exit;
+	}
+
+	if (resp->len != sizeof(*sensb_res)) {
+		PROTOCOL_ERR("5.6.2.1");
+		rc = -EIO;
+		goto exit;
+	}
+
+	sensb_res = (struct digital_sensb_res *)resp->data;
+
+	if (sensb_res->cmd != DIGITAL_CMD_SENSB_RES) {
+		PROTOCOL_ERR("5.6.2");
+		rc = -EIO;
+		goto exit;
+	}
+
+	if (!(sensb_res->proto_info[1] & BIT(0))) {
+		PROTOCOL_ERR("5.6.2.12");
+		rc = -EIO;
+		goto exit;
+	}
+
+	if (sensb_res->proto_info[1] & BIT(3)) {
+		PROTOCOL_ERR("5.6.2.16");
+		rc = -EIO;
+		goto exit;
+	}
+
+	fsci = DIGITAL_SENSB_FSCI(sensb_res->proto_info[1]);
+	if (fsci >= 8)
+		ddev->target_fsc = DIGITAL_ATS_MAX_FSC;
+	else
+		ddev->target_fsc = digital_ats_fsc[fsci];
+
+	target = kzalloc(sizeof(struct nfc_target), GFP_KERNEL);
+	if (!target) {
+		rc = -ENOMEM;
+		goto exit;
+	}
+
+	rc = digital_in_send_attrib_req(ddev, target, sensb_res);
+
+exit:
+	dev_kfree_skb(resp);
+
+	if (rc) {
+		kfree(target);
+		digital_poll_next_tech(ddev);
+	}
+}
+
+int digital_in_send_sensb_req(struct nfc_digital_dev *ddev, u8 rf_tech)
+{
+	struct digital_sensb_req *sensb_req;
+	struct sk_buff *skb;
+	int rc;
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_RF_TECH,
+				     NFC_DIGITAL_RF_TECH_106B);
+	if (rc)
+		return rc;
+
+	rc = digital_in_configure_hw(ddev, NFC_DIGITAL_CONFIG_FRAMING,
+				     NFC_DIGITAL_FRAMING_NFCB);
+	if (rc)
+		return rc;
+
+	skb = digital_skb_alloc(ddev, sizeof(*sensb_req));
+	if (!skb)
+		return -ENOMEM;
+
+	sensb_req = (struct digital_sensb_req *)skb_put(skb,
+							sizeof(*sensb_req));
+
+	sensb_req->cmd = DIGITAL_CMD_SENSB_REQ;
+	sensb_req->afi = 0x00; /* All families and sub-families */
+	sensb_req->param = DIGITAL_SENSB_N(0);
+
+	rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sensb_res,
+				 NULL);
+	if (rc)
+		kfree_skb(skb);
+
+	return rc;
+}
+
 static void digital_in_recv_sensf_res(struct nfc_digital_dev *ddev, void *arg,
 				   struct sk_buff *resp)
 {
@@ -877,6 +1091,18 @@ exit:
 	dev_kfree_skb(resp);
 }
 
+static void digital_tg_recv_atr_or_sensf_req(struct nfc_digital_dev *ddev,
+		void *arg, struct sk_buff *resp)
+{
+	if (!IS_ERR(resp) && (resp->len >= 2) &&
+			(resp->data[1] == DIGITAL_CMD_SENSF_REQ))
+		digital_tg_recv_sensf_req(ddev, arg, resp);
+	else
+		digital_tg_recv_atr_req(ddev, arg, resp);
+
+	return;
+}
+
 static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev,
 			      struct digital_sensf_req *sensf_req)
 {
@@ -887,7 +1113,7 @@ static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev,
 
 	size = sizeof(struct digital_sensf_res);
 
-	if (sensf_req->rc != DIGITAL_SENSF_REQ_RC_NONE)
+	if (sensf_req->rc == DIGITAL_SENSF_REQ_RC_NONE)
 		size -= sizeof(sensf_res->rd);
 
 	skb = digital_skb_alloc(ddev, size);
@@ -922,7 +1148,7 @@ static int digital_tg_send_sensf_res(struct nfc_digital_dev *ddev,
 		digital_skb_add_crc_f(skb);
 
 	rc = digital_tg_send_cmd(ddev, skb, 300,
-				 digital_tg_recv_atr_req, NULL);
+				 digital_tg_recv_atr_or_sensf_req, NULL);
 	if (rc)
 		kfree_skb(skb);
 
diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c
index a9f4d2e62d8..677d24bb70f 100644
--- a/net/nfc/hci/command.c
+++ b/net/nfc/hci/command.c
@@ -26,6 +26,8 @@
 
 #include "hci.h"
 
+#define MAX_FWI 4949
+
 static int nfc_hci_execute_cmd_async(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 			       const u8 *param, size_t param_len,
 			       data_exchange_cb_t cb, void *cb_context)
@@ -37,7 +39,7 @@ static int nfc_hci_execute_cmd_async(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 	 * for all commands?
 	 */
 	return nfc_hci_hcp_message_tx(hdev, pipe, NFC_HCI_HCP_COMMAND, cmd,
-				      param, param_len, cb, cb_context, 3000);
+				      param, param_len, cb, cb_context, MAX_FWI);
 }
 
 /*
@@ -82,7 +84,7 @@ static int nfc_hci_execute_cmd(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd,
 						    NFC_HCI_HCP_COMMAND, cmd,
 						    param, param_len,
 						    nfc_hci_execute_cb, &hcp_ew,
-						    3000);
+						    MAX_FWI);
 	if (hcp_ew.exec_result < 0)
 		return hcp_ew.exec_result;
 
diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c
index d45b638e77c..47403705197 100644
--- a/net/nfc/hci/core.c
+++ b/net/nfc/hci/core.c
@@ -225,7 +225,7 @@ int nfc_hci_target_discovered(struct nfc_hci_dev *hdev, u8 gate)
 			goto exit;
 		}
 
-		targets->sens_res = be16_to_cpu(*(u16 *)atqa_skb->data);
+		targets->sens_res = be16_to_cpu(*(__be16 *)atqa_skb->data);
 		targets->sel_res = sak_skb->data[0];
 
 		r = nfc_hci_get_param(hdev, NFC_HCI_RF_READER_A_GATE,
@@ -380,34 +380,31 @@ static int hci_dev_session_init(struct nfc_hci_dev *hdev)
 	if (r < 0)
 		goto disconnect_all;
 
-	if (skb->len && skb->len == strlen(hdev->init_data.session_id))
-		if (memcmp(hdev->init_data.session_id, skb->data,
-			   skb->len) == 0) {
-			/* TODO ELa: restore gate<->pipe table from
-			 * some TBD location.
-			 * note: it doesn't seem possible to get the chip
-			 * currently open gate/pipe table.
-			 * It is only possible to obtain the supported
-			 * gate list.
-			 */
+	if (skb->len && skb->len == strlen(hdev->init_data.session_id) &&
+		(memcmp(hdev->init_data.session_id, skb->data,
+			   skb->len) == 0) && hdev->ops->load_session) {
+		/* Restore gate<->pipe table from some proprietary location. */
 
-			/* goto exit
-			 * For now, always do a full initialization */
-		}
+		r = hdev->ops->load_session(hdev);
 
-	r = nfc_hci_disconnect_all_gates(hdev);
-	if (r < 0)
-		goto exit;
+		if (r < 0)
+			goto disconnect_all;
+	} else {
 
-	r = hci_dev_connect_gates(hdev, hdev->init_data.gate_count,
-				  hdev->init_data.gates);
-	if (r < 0)
-		goto disconnect_all;
+		r = nfc_hci_disconnect_all_gates(hdev);
+		if (r < 0)
+			goto exit;
 
-	r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE,
-			      NFC_HCI_ADMIN_SESSION_IDENTITY,
-			      hdev->init_data.session_id,
-			      strlen(hdev->init_data.session_id));
+		r = hci_dev_connect_gates(hdev, hdev->init_data.gate_count,
+					  hdev->init_data.gates);
+		if (r < 0)
+			goto disconnect_all;
+
+		r = nfc_hci_set_param(hdev, NFC_HCI_ADMIN_GATE,
+				NFC_HCI_ADMIN_SESSION_IDENTITY,
+				hdev->init_data.session_id,
+				strlen(hdev->init_data.session_id));
+	}
 	if (r == 0)
 		goto exit;
 
diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index bec6ed15f50..a3ad69a4c64 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -387,7 +387,7 @@ int nfc_llcp_send_symm(struct nfc_dev *dev)
 
 	__net_timestamp(skb);
 
-	nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_TX);
+	nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_TX);
 
 	return nfc_data_exchange(dev, local->target_idx, skb,
 				 nfc_llcp_recv, local);
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index b4671958fcf..51e78879731 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -680,16 +680,17 @@ void nfc_llcp_send_to_raw_sock(struct nfc_llcp_local *local,
 			continue;
 
 		if (skb_copy == NULL) {
-			skb_copy = __pskb_copy(skb, NFC_LLCP_RAW_HEADER_SIZE,
-					       GFP_ATOMIC);
+			skb_copy = __pskb_copy_fclone(skb, NFC_RAW_HEADER_SIZE,
+						      GFP_ATOMIC, true);
 
 			if (skb_copy == NULL)
 				continue;
 
-			data = skb_push(skb_copy, NFC_LLCP_RAW_HEADER_SIZE);
+			data = skb_push(skb_copy, NFC_RAW_HEADER_SIZE);
 
 			data[0] = local->dev ? local->dev->idx : 0xFF;
-			data[1] = direction;
+			data[1] = direction & 0x01;
+			data[1] |= (RAW_PAYLOAD_LLCP << 1);
 		}
 
 		nskb = skb_clone(skb_copy, GFP_ATOMIC);
@@ -747,7 +748,7 @@ static void nfc_llcp_tx_work(struct work_struct *work)
 			__net_timestamp(skb);
 
 			nfc_llcp_send_to_raw_sock(local, skb,
-						  NFC_LLCP_DIRECTION_TX);
+						  NFC_DIRECTION_TX);
 
 			ret = nfc_data_exchange(local->dev, local->target_idx,
 						skb, nfc_llcp_recv, local);
@@ -1476,7 +1477,7 @@ static void nfc_llcp_rx_work(struct work_struct *work)
 
 	__net_timestamp(skb);
 
-	nfc_llcp_send_to_raw_sock(local, skb, NFC_LLCP_DIRECTION_RX);
+	nfc_llcp_send_to_raw_sock(local, skb, NFC_DIRECTION_RX);
 
 	nfc_llcp_rx_skb(local, skb);
 
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 6c34ac97850..2b400e1a869 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -861,6 +861,10 @@ static int nci_send_frame(struct nci_dev *ndev, struct sk_buff *skb)
 	/* Get rid of skb owner, prior to sending to the driver. */
 	skb_orphan(skb);
 
+	/* Send copy to sniffer */
+	nfc_send_to_raw_sock(ndev->nfc_dev, skb,
+			     RAW_PAYLOAD_NCI, NFC_DIRECTION_TX);
+
 	return ndev->ops->send(ndev, skb);
 }
 
@@ -935,6 +939,11 @@ static void nci_rx_work(struct work_struct *work)
 	struct sk_buff *skb;
 
 	while ((skb = skb_dequeue(&ndev->rx_q))) {
+
+		/* Send copy to sniffer */
+		nfc_send_to_raw_sock(ndev->nfc_dev, skb,
+				     RAW_PAYLOAD_NCI, NFC_DIRECTION_RX);
+
 		/* Process frame */
 		switch (nci_mt(skb->data)) {
 		case NCI_MT_RSP_PKT:
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 1e905097456..f8f6af23138 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -366,7 +366,6 @@ static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev,
 			struct nci_rf_intf_activated_ntf *ntf, __u8 *data)
 {
 	struct activation_params_poll_nfc_dep *poll;
-	int i;
 
 	switch (ntf->activation_rf_tech_and_mode) {
 	case NCI_NFC_A_PASSIVE_POLL_MODE:
@@ -374,10 +373,8 @@ static int nci_extract_activation_params_nfc_dep(struct nci_dev *ndev,
 		poll = &ntf->activation_params.poll_nfc_dep;
 		poll->atr_res_len = min_t(__u8, *data++, 63);
 		pr_debug("atr_res_len %d\n", poll->atr_res_len);
-		if (poll->atr_res_len > 0) {
-			for (i = 0; i < poll->atr_res_len; i++)
-				poll->atr_res[poll->atr_res_len-1-i] = data[i];
-		}
+		if (poll->atr_res_len > 0)
+			memcpy(poll->atr_res, data, poll->atr_res_len);
 		break;
 
 	default:
diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h
index 9d6e74f7e6b..88d60064890 100644
--- a/net/nfc/nfc.h
+++ b/net/nfc/nfc.h
@@ -40,6 +40,12 @@ struct nfc_rawsock {
 	struct work_struct tx_work;
 	bool tx_work_scheduled;
 };
+
+struct nfc_sock_list {
+	struct hlist_head head;
+	rwlock_t          lock;
+};
+
 #define nfc_rawsock(sk) ((struct nfc_rawsock *) sk)
 #define to_rawsock_sk(_tx_work) \
 	((struct sock *) container_of(_tx_work, struct nfc_rawsock, tx_work))
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index c27a6e86cae..11c3544ea54 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -27,6 +27,24 @@
 
 #include "nfc.h"
 
+static struct nfc_sock_list raw_sk_list = {
+	.lock = __RW_LOCK_UNLOCKED(raw_sk_list.lock)
+};
+
+static void nfc_sock_link(struct nfc_sock_list *l, struct sock *sk)
+{
+	write_lock(&l->lock);
+	sk_add_node(sk, &l->head);
+	write_unlock(&l->lock);
+}
+
+static void nfc_sock_unlink(struct nfc_sock_list *l, struct sock *sk)
+{
+	write_lock(&l->lock);
+	sk_del_node_init(sk);
+	write_unlock(&l->lock);
+}
+
 static void rawsock_write_queue_purge(struct sock *sk)
 {
 	pr_debug("sk=%p\n", sk);
@@ -57,6 +75,9 @@ static int rawsock_release(struct socket *sock)
 	if (!sk)
 		return 0;
 
+	if (sock->type == SOCK_RAW)
+		nfc_sock_unlink(&raw_sk_list, sk);
+
 	sock_orphan(sk);
 	sock_put(sk);
 
@@ -275,6 +296,26 @@ static const struct proto_ops rawsock_ops = {
 	.mmap           = sock_no_mmap,
 };
 
+static const struct proto_ops rawsock_raw_ops = {
+	.family         = PF_NFC,
+	.owner          = THIS_MODULE,
+	.release        = rawsock_release,
+	.bind           = sock_no_bind,
+	.connect        = sock_no_connect,
+	.socketpair     = sock_no_socketpair,
+	.accept         = sock_no_accept,
+	.getname        = sock_no_getname,
+	.poll           = datagram_poll,
+	.ioctl          = sock_no_ioctl,
+	.listen         = sock_no_listen,
+	.shutdown       = sock_no_shutdown,
+	.setsockopt     = sock_no_setsockopt,
+	.getsockopt     = sock_no_getsockopt,
+	.sendmsg        = sock_no_sendmsg,
+	.recvmsg        = rawsock_recvmsg,
+	.mmap           = sock_no_mmap,
+};
+
 static void rawsock_destruct(struct sock *sk)
 {
 	pr_debug("sk=%p\n", sk);
@@ -300,10 +341,13 @@ static int rawsock_create(struct net *net, struct socket *sock,
 
 	pr_debug("sock=%p\n", sock);
 
-	if (sock->type != SOCK_SEQPACKET)
+	if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW))
 		return -ESOCKTNOSUPPORT;
 
-	sock->ops = &rawsock_ops;
+	if (sock->type == SOCK_RAW)
+		sock->ops = &rawsock_raw_ops;
+	else
+		sock->ops = &rawsock_ops;
 
 	sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto);
 	if (!sk)
@@ -313,13 +357,53 @@ static int rawsock_create(struct net *net, struct socket *sock,
 	sk->sk_protocol = nfc_proto->id;
 	sk->sk_destruct = rawsock_destruct;
 	sock->state = SS_UNCONNECTED;
-
-	INIT_WORK(&nfc_rawsock(sk)->tx_work, rawsock_tx_work);
-	nfc_rawsock(sk)->tx_work_scheduled = false;
+	if (sock->type == SOCK_RAW)
+		nfc_sock_link(&raw_sk_list, sk);
+	else {
+		INIT_WORK(&nfc_rawsock(sk)->tx_work, rawsock_tx_work);
+		nfc_rawsock(sk)->tx_work_scheduled = false;
+	}
 
 	return 0;
 }
 
+void nfc_send_to_raw_sock(struct nfc_dev *dev, struct sk_buff *skb,
+			  u8 payload_type, u8 direction)
+{
+	struct sk_buff *skb_copy = NULL, *nskb;
+	struct sock *sk;
+	u8 *data;
+
+	read_lock(&raw_sk_list.lock);
+
+	sk_for_each(sk, &raw_sk_list.head) {
+		if (!skb_copy) {
+			skb_copy = __pskb_copy_fclone(skb, NFC_RAW_HEADER_SIZE,
+						      GFP_ATOMIC, true);
+			if (!skb_copy)
+				continue;
+
+			data = skb_push(skb_copy, NFC_RAW_HEADER_SIZE);
+
+			data[0] = dev ? dev->idx : 0xFF;
+			data[1] = direction & 0x01;
+			data[1] |= (payload_type << 1);
+		}
+
+		nskb = skb_clone(skb_copy, GFP_ATOMIC);
+		if (!nskb)
+			continue;
+
+		if (sock_queue_rcv_skb(sk, nskb))
+			kfree_skb(nskb);
+	}
+
+	read_unlock(&raw_sk_list.lock);
+
+	kfree_skb(skb_copy);
+}
+EXPORT_SYMBOL(nfc_send_to_raw_sock);
+
 static struct proto rawsock_proto = {
 	.name     = "NFC_RAW",
 	.owner    = THIS_MODULE,
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 2c77e7b1a91..e70d8b18e96 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -134,8 +134,8 @@ static int set_eth_addr(struct sk_buff *skb,
 
 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
-	memcpy(eth_hdr(skb)->h_source, eth_key->eth_src, ETH_ALEN);
-	memcpy(eth_hdr(skb)->h_dest, eth_key->eth_dst, ETH_ALEN);
+	ether_addr_copy(eth_hdr(skb)->h_source, eth_key->eth_src);
+	ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst);
 
 	ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
 
@@ -551,6 +551,8 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 		case OVS_ACTION_ATTR_SAMPLE:
 			err = sample(dp, skb, a);
+			if (unlikely(err)) /* skb already freed. */
+				return err;
 			break;
 		}
 
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index a3276e3c4fe..9db4bf6740d 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -44,11 +44,11 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/inetdevice.h>
 #include <linux/list.h>
-#include <linux/lockdep.h>
 #include <linux/openvswitch.h>
 #include <linux/rculist.h>
 #include <linux/dmi.h>
-#include <linux/workqueue.h>
+#include <linux/genetlink.h>
+#include <net/genetlink.h>
 #include <net/genetlink.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
@@ -62,6 +62,31 @@
 
 int ovs_net_id __read_mostly;
 
+static struct genl_family dp_packet_genl_family;
+static struct genl_family dp_flow_genl_family;
+static struct genl_family dp_datapath_genl_family;
+
+static struct genl_multicast_group ovs_dp_flow_multicast_group = {
+	.name = OVS_FLOW_MCGROUP
+};
+
+static struct genl_multicast_group ovs_dp_datapath_multicast_group = {
+	.name = OVS_DATAPATH_MCGROUP
+};
+
+struct genl_multicast_group ovs_dp_vport_multicast_group = {
+	.name = OVS_VPORT_MCGROUP
+};
+
+/* Check if need to build a reply message.
+ * OVS userspace sets the NLM_F_ECHO flag if it needs the reply. */
+static bool ovs_must_notify(struct genl_info *info,
+			    const struct genl_multicast_group *grp)
+{
+	return info->nlhdr->nlmsg_flags & NLM_F_ECHO ||
+		netlink_has_listeners(genl_info_net(info)->genl_sock, 0);
+}
+
 static void ovs_notify(struct genl_family *family,
 		       struct sk_buff *skb, struct genl_info *info)
 {
@@ -173,6 +198,7 @@ static struct hlist_head *vport_hash_bucket(const struct datapath *dp,
 	return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)];
 }
 
+/* Called with ovs_mutex or RCU read lock. */
 struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no)
 {
 	struct vport *vport;
@@ -250,7 +276,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
 	OVS_CB(skb)->flow = flow;
 	OVS_CB(skb)->pkt_key = &key;
 
-	ovs_flow_stats_update(OVS_CB(skb)->flow, skb);
+	ovs_flow_stats_update(OVS_CB(skb)->flow, key.tp.flags, skb);
 	ovs_execute_actions(dp, skb);
 	stats_counter = &stats->n_hit;
 
@@ -262,16 +288,6 @@ out:
 	u64_stats_update_end(&stats->syncp);
 }
 
-static struct genl_family dp_packet_genl_family = {
-	.id = GENL_ID_GENERATE,
-	.hdrsize = sizeof(struct ovs_header),
-	.name = OVS_PACKET_FAMILY,
-	.version = OVS_PACKET_VERSION,
-	.maxattr = OVS_PACKET_ATTR_MAX,
-	.netnsok = true,
-	.parallel_ops = true,
-};
-
 int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
 		  const struct dp_upcall_info *upcall_info)
 {
@@ -524,7 +540,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 		packet->protocol = htons(ETH_P_802_2);
 
 	/* Build an sw_flow for sending this packet. */
-	flow = ovs_flow_alloc(false);
+	flow = ovs_flow_alloc();
 	err = PTR_ERR(flow);
 	if (IS_ERR(flow))
 		goto err_kfree_skb;
@@ -590,6 +606,18 @@ static const struct genl_ops dp_packet_genl_ops[] = {
 	}
 };
 
+static struct genl_family dp_packet_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_PACKET_FAMILY,
+	.version = OVS_PACKET_VERSION,
+	.maxattr = OVS_PACKET_ATTR_MAX,
+	.netnsok = true,
+	.parallel_ops = true,
+	.ops = dp_packet_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_packet_genl_ops),
+};
+
 static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
 			 struct ovs_dp_megaflow_stats *mega_stats)
 {
@@ -621,26 +649,6 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
 	}
 }
 
-static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
-	[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
-	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
-	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
-};
-
-static struct genl_family dp_flow_genl_family = {
-	.id = GENL_ID_GENERATE,
-	.hdrsize = sizeof(struct ovs_header),
-	.name = OVS_FLOW_FAMILY,
-	.version = OVS_FLOW_VERSION,
-	.maxattr = OVS_FLOW_ATTR_MAX,
-	.netnsok = true,
-	.parallel_ops = true,
-};
-
-static struct genl_multicast_group ovs_dp_flow_multicast_group = {
-	.name = OVS_FLOW_MCGROUP
-};
-
 static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
 {
 	return NLMSG_ALIGN(sizeof(struct ovs_header))
@@ -652,8 +660,8 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts)
 		+ nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */
 }
 
-/* Called with ovs_mutex. */
-static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
+/* Called with ovs_mutex or RCU read lock. */
+static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex,
 				  struct sk_buff *skb, u32 portid,
 				  u32 seq, u32 flags, u8 cmd)
 {
@@ -670,7 +678,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
 	if (!ovs_header)
 		return -EMSGSIZE;
 
-	ovs_header->dp_ifindex = get_dpifindex(dp);
+	ovs_header->dp_ifindex = dp_ifindex;
 
 	/* Fill flow key. */
 	nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
@@ -693,6 +701,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
 	nla_nest_end(skb, nla);
 
 	ovs_flow_stats_get(flow, &stats, &used, &tcp_flags);
+
 	if (used &&
 	    nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used)))
 		goto nla_put_failure;
@@ -720,9 +729,9 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
 		const struct sw_flow_actions *sf_acts;
 
 		sf_acts = rcu_dereference_ovsl(flow->sf_acts);
-
 		err = ovs_nla_put_actions(sf_acts->actions,
 					  sf_acts->actions_len, skb);
+
 		if (!err)
 			nla_nest_end(skb, start);
 		else {
@@ -743,113 +752,128 @@ error:
 	return err;
 }
 
-static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow,
-					       struct genl_info *info)
+/* May not be called with RCU read lock. */
+static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *acts,
+					       struct genl_info *info,
+					       bool always)
 {
-	size_t len;
+	struct sk_buff *skb;
+
+	if (!always && !ovs_must_notify(info, &ovs_dp_flow_multicast_group))
+		return NULL;
 
-	len = ovs_flow_cmd_msg_size(ovsl_dereference(flow->sf_acts));
+	skb = genlmsg_new_unicast(ovs_flow_cmd_msg_size(acts), info, GFP_KERNEL);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
 
-	return genlmsg_new_unicast(len, info, GFP_KERNEL);
+	return skb;
 }
 
-static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow,
-					       struct datapath *dp,
-					       struct genl_info *info,
-					       u8 cmd)
+/* Called with ovs_mutex. */
+static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow,
+					       int dp_ifindex,
+					       struct genl_info *info, u8 cmd,
+					       bool always)
 {
 	struct sk_buff *skb;
 	int retval;
 
-	skb = ovs_flow_cmd_alloc_info(flow, info);
-	if (!skb)
-		return ERR_PTR(-ENOMEM);
+	skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info,
+				      always);
+	if (!skb || IS_ERR(skb))
+		return skb;
 
-	retval = ovs_flow_cmd_fill_info(flow, dp, skb, info->snd_portid,
-					info->snd_seq, 0, cmd);
+	retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb,
+					info->snd_portid, info->snd_seq, 0,
+					cmd);
 	BUG_ON(retval < 0);
 	return skb;
 }
 
-static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
+static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr **a = info->attrs;
 	struct ovs_header *ovs_header = info->userhdr;
-	struct sw_flow_key key, masked_key;
-	struct sw_flow *flow = NULL;
+	struct sw_flow *flow, *new_flow;
 	struct sw_flow_mask mask;
 	struct sk_buff *reply;
 	struct datapath *dp;
-	struct sw_flow_actions *acts = NULL;
+	struct sw_flow_actions *acts;
 	struct sw_flow_match match;
-	bool exact_5tuple;
 	int error;
 
-	/* Extract key. */
+	/* Must have key and actions. */
 	error = -EINVAL;
 	if (!a[OVS_FLOW_ATTR_KEY])
 		goto error;
+	if (!a[OVS_FLOW_ATTR_ACTIONS])
+		goto error;
 
-	ovs_match_init(&match, &key, &mask);
-	error = ovs_nla_get_match(&match, &exact_5tuple,
+	/* Most of the time we need to allocate a new flow, do it before
+	 * locking.
+	 */
+	new_flow = ovs_flow_alloc();
+	if (IS_ERR(new_flow)) {
+		error = PTR_ERR(new_flow);
+		goto error;
+	}
+
+	/* Extract key. */
+	ovs_match_init(&match, &new_flow->unmasked_key, &mask);
+	error = ovs_nla_get_match(&match,
 				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
 	if (error)
-		goto error;
+		goto err_kfree_flow;
+
+	ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask);
 
 	/* Validate actions. */
-	if (a[OVS_FLOW_ATTR_ACTIONS]) {
-		acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
-		error = PTR_ERR(acts);
-		if (IS_ERR(acts))
-			goto error;
+	acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
+	error = PTR_ERR(acts);
+	if (IS_ERR(acts))
+		goto err_kfree_flow;
 
-		ovs_flow_mask_key(&masked_key, &key, &mask);
-		error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS],
-					     &masked_key, 0, &acts);
-		if (error) {
-			OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
-			goto err_kfree;
-		}
-	} else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) {
-		error = -EINVAL;
-		goto error;
+	error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key,
+				     0, &acts);
+	if (error) {
+		OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
+		goto err_kfree_acts;
+	}
+
+	reply = ovs_flow_cmd_alloc_info(acts, info, false);
+	if (IS_ERR(reply)) {
+		error = PTR_ERR(reply);
+		goto err_kfree_acts;
 	}
 
 	ovs_lock();
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
-	error = -ENODEV;
-	if (!dp)
+	if (unlikely(!dp)) {
+		error = -ENODEV;
 		goto err_unlock_ovs;
-
+	}
 	/* Check if this is a duplicate flow */
-	flow = ovs_flow_tbl_lookup(&dp->table, &key);
-	if (!flow) {
-		/* Bail out if we're not allowed to create a new flow. */
-		error = -ENOENT;
-		if (info->genlhdr->cmd == OVS_FLOW_CMD_SET)
-			goto err_unlock_ovs;
-
-		/* Allocate flow. */
-		flow = ovs_flow_alloc(!exact_5tuple);
-		if (IS_ERR(flow)) {
-			error = PTR_ERR(flow);
-			goto err_unlock_ovs;
-		}
-
-		flow->key = masked_key;
-		flow->unmasked_key = key;
-		rcu_assign_pointer(flow->sf_acts, acts);
+	flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->unmasked_key);
+	if (likely(!flow)) {
+		rcu_assign_pointer(new_flow->sf_acts, acts);
 
 		/* Put flow in bucket. */
-		error = ovs_flow_tbl_insert(&dp->table, flow, &mask);
-		if (error) {
+		error = ovs_flow_tbl_insert(&dp->table, new_flow, &mask);
+		if (unlikely(error)) {
 			acts = NULL;
-			goto err_flow_free;
+			goto err_unlock_ovs;
 		}
 
-		reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW);
+		if (unlikely(reply)) {
+			error = ovs_flow_cmd_fill_info(new_flow,
+						       ovs_header->dp_ifindex,
+						       reply, info->snd_portid,
+						       info->snd_seq, 0,
+						       OVS_FLOW_CMD_NEW);
+			BUG_ON(error < 0);
+		}
+		ovs_unlock();
 	} else {
-		/* We found a matching flow. */
 		struct sw_flow_actions *old_acts;
 
 		/* Bail out if we're not allowed to modify an existing flow.
@@ -858,40 +882,153 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
 		 * request.  We also accept NLM_F_EXCL in case that bug ever
 		 * gets fixed.
 		 */
-		error = -EEXIST;
-		if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW &&
-		    info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL))
+		if (unlikely(info->nlhdr->nlmsg_flags & (NLM_F_CREATE
+							 | NLM_F_EXCL))) {
+			error = -EEXIST;
 			goto err_unlock_ovs;
-
+		}
 		/* The unmasked key has to be the same for flow updates. */
-		if (!ovs_flow_cmp_unmasked_key(flow, &match))
-			goto err_unlock_ovs;
-
+		if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) {
+			flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+			if (!flow) {
+				error = -ENOENT;
+				goto err_unlock_ovs;
+			}
+		}
 		/* Update actions. */
 		old_acts = ovsl_dereference(flow->sf_acts);
 		rcu_assign_pointer(flow->sf_acts, acts);
+
+		if (unlikely(reply)) {
+			error = ovs_flow_cmd_fill_info(flow,
+						       ovs_header->dp_ifindex,
+						       reply, info->snd_portid,
+						       info->snd_seq, 0,
+						       OVS_FLOW_CMD_NEW);
+			BUG_ON(error < 0);
+		}
+		ovs_unlock();
+
 		ovs_nla_free_flow_actions(old_acts);
+		ovs_flow_free(new_flow, false);
+	}
+
+	if (reply)
+		ovs_notify(&dp_flow_genl_family, reply, info);
+	return 0;
+
+err_unlock_ovs:
+	ovs_unlock();
+	kfree_skb(reply);
+err_kfree_acts:
+	kfree(acts);
+err_kfree_flow:
+	ovs_flow_free(new_flow, false);
+error:
+	return error;
+}
+
+static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct sw_flow_key key, masked_key;
+	struct sw_flow *flow;
+	struct sw_flow_mask mask;
+	struct sk_buff *reply = NULL;
+	struct datapath *dp;
+	struct sw_flow_actions *old_acts = NULL, *acts = NULL;
+	struct sw_flow_match match;
+	int error;
+
+	/* Extract key. */
+	error = -EINVAL;
+	if (!a[OVS_FLOW_ATTR_KEY])
+		goto error;
+
+	ovs_match_init(&match, &key, &mask);
+	error = ovs_nla_get_match(&match,
+				  a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]);
+	if (error)
+		goto error;
+
+	/* Validate actions. */
+	if (a[OVS_FLOW_ATTR_ACTIONS]) {
+		acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
+		error = PTR_ERR(acts);
+		if (IS_ERR(acts))
+			goto error;
+
+		ovs_flow_mask_key(&masked_key, &key, &mask);
+		error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS],
+					     &masked_key, 0, &acts);
+		if (error) {
+			OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
+			goto err_kfree_acts;
+		}
+	}
+
+	/* Can allocate before locking if have acts. */
+	if (acts) {
+		reply = ovs_flow_cmd_alloc_info(acts, info, false);
+		if (IS_ERR(reply)) {
+			error = PTR_ERR(reply);
+			goto err_kfree_acts;
+		}
+	}
+
+	ovs_lock();
+	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
+	if (unlikely(!dp)) {
+		error = -ENODEV;
+		goto err_unlock_ovs;
+	}
+	/* Check that the flow exists. */
+	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (unlikely(!flow)) {
+		error = -ENOENT;
+		goto err_unlock_ovs;
+	}
 
-		reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW);
+	/* Update actions, if present. */
+	if (likely(acts)) {
+		old_acts = ovsl_dereference(flow->sf_acts);
+		rcu_assign_pointer(flow->sf_acts, acts);
 
-		/* Clear stats. */
-		if (a[OVS_FLOW_ATTR_CLEAR])
-			ovs_flow_stats_clear(flow);
+		if (unlikely(reply)) {
+			error = ovs_flow_cmd_fill_info(flow,
+						       ovs_header->dp_ifindex,
+						       reply, info->snd_portid,
+						       info->snd_seq, 0,
+						       OVS_FLOW_CMD_NEW);
+			BUG_ON(error < 0);
+		}
+	} else {
+		/* Could not alloc without acts before locking. */
+		reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex,
+						info, OVS_FLOW_CMD_NEW, false);
+		if (unlikely(IS_ERR(reply))) {
+			error = PTR_ERR(reply);
+			goto err_unlock_ovs;
+		}
 	}
+
+	/* Clear stats. */
+	if (a[OVS_FLOW_ATTR_CLEAR])
+		ovs_flow_stats_clear(flow);
 	ovs_unlock();
 
-	if (!IS_ERR(reply))
+	if (reply)
 		ovs_notify(&dp_flow_genl_family, reply, info);
-	else
-		genl_set_err(&dp_flow_genl_family, sock_net(skb->sk), 0,
-			     0, PTR_ERR(reply));
+	if (old_acts)
+		ovs_nla_free_flow_actions(old_acts);
+
 	return 0;
 
-err_flow_free:
-	ovs_flow_free(flow, false);
 err_unlock_ovs:
 	ovs_unlock();
-err_kfree:
+	kfree_skb(reply);
+err_kfree_acts:
 	kfree(acts);
 error:
 	return error;
@@ -914,7 +1051,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	ovs_match_init(&match, &key, NULL);
-	err = ovs_nla_get_match(&match, NULL, a[OVS_FLOW_ATTR_KEY], NULL);
+	err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
 	if (err)
 		return err;
 
@@ -925,13 +1062,14 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
 		goto unlock;
 	}
 
-	flow = ovs_flow_tbl_lookup(&dp->table, &key);
-	if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
+	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (!flow) {
 		err = -ENOENT;
 		goto unlock;
 	}
 
-	reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW);
+	reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info,
+					OVS_FLOW_CMD_NEW, true);
 	if (IS_ERR(reply)) {
 		err = PTR_ERR(reply);
 		goto unlock;
@@ -955,45 +1093,53 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct sw_flow_match match;
 	int err;
 
+	if (likely(a[OVS_FLOW_ATTR_KEY])) {
+		ovs_match_init(&match, &key, NULL);
+		err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL);
+		if (unlikely(err))
+			return err;
+	}
+
 	ovs_lock();
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
-	if (!dp) {
+	if (unlikely(!dp)) {
 		err = -ENODEV;
 		goto unlock;
 	}
 
-	if (!a[OVS_FLOW_ATTR_KEY]) {
+	if (unlikely(!a[OVS_FLOW_ATTR_KEY])) {
 		err = ovs_flow_tbl_flush(&dp->table);
 		goto unlock;
 	}
 
-	ovs_match_init(&match, &key, NULL);
-	err = ovs_nla_get_match(&match, NULL, a[OVS_FLOW_ATTR_KEY], NULL);
-	if (err)
-		goto unlock;
-
-	flow = ovs_flow_tbl_lookup(&dp->table, &key);
-	if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) {
+	flow = ovs_flow_tbl_lookup_exact(&dp->table, &match);
+	if (unlikely(!flow)) {
 		err = -ENOENT;
 		goto unlock;
 	}
 
-	reply = ovs_flow_cmd_alloc_info(flow, info);
-	if (!reply) {
-		err = -ENOMEM;
-		goto unlock;
-	}
-
 	ovs_flow_tbl_remove(&dp->table, flow);
+	ovs_unlock();
 
-	err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid,
-				     info->snd_seq, 0, OVS_FLOW_CMD_DEL);
-	BUG_ON(err < 0);
+	reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts,
+					info, false);
+	if (likely(reply)) {
+		if (likely(!IS_ERR(reply))) {
+			rcu_read_lock();	/*To keep RCU checker happy. */
+			err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex,
+						     reply, info->snd_portid,
+						     info->snd_seq, 0,
+						     OVS_FLOW_CMD_DEL);
+			rcu_read_unlock();
+			BUG_ON(err < 0);
+
+			ovs_notify(&dp_flow_genl_family, reply, info);
+		} else {
+			netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply));
+		}
+	}
 
 	ovs_flow_free(flow, true);
-	ovs_unlock();
-
-	ovs_notify(&dp_flow_genl_family, reply, info);
 	return 0;
 unlock:
 	ovs_unlock();
@@ -1024,7 +1170,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		if (!flow)
 			break;
 
-		if (ovs_flow_cmd_fill_info(flow, dp, skb,
+		if (ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, skb,
 					   NETLINK_CB(cb->skb).portid,
 					   cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					   OVS_FLOW_CMD_NEW) < 0)
@@ -1037,11 +1183,17 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-static const struct genl_ops dp_flow_genl_ops[] = {
+static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
+	[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
+};
+
+static struct genl_ops dp_flow_genl_ops[] = {
 	{ .cmd = OVS_FLOW_CMD_NEW,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .policy = flow_policy,
-	  .doit = ovs_flow_cmd_new_or_set
+	  .doit = ovs_flow_cmd_new
 	},
 	{ .cmd = OVS_FLOW_CMD_DEL,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -1057,28 +1209,22 @@ static const struct genl_ops dp_flow_genl_ops[] = {
 	{ .cmd = OVS_FLOW_CMD_SET,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .policy = flow_policy,
-	  .doit = ovs_flow_cmd_new_or_set,
+	  .doit = ovs_flow_cmd_set,
 	},
 };
 
-static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
-	[OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
-	[OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
-	[OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
-};
-
-static struct genl_family dp_datapath_genl_family = {
+static struct genl_family dp_flow_genl_family = {
 	.id = GENL_ID_GENERATE,
 	.hdrsize = sizeof(struct ovs_header),
-	.name = OVS_DATAPATH_FAMILY,
-	.version = OVS_DATAPATH_VERSION,
-	.maxattr = OVS_DP_ATTR_MAX,
+	.name = OVS_FLOW_FAMILY,
+	.version = OVS_FLOW_VERSION,
+	.maxattr = OVS_FLOW_ATTR_MAX,
 	.netnsok = true,
 	.parallel_ops = true,
-};
-
-static struct genl_multicast_group ovs_dp_datapath_multicast_group = {
-	.name = OVS_DATAPATH_MCGROUP
+	.ops = dp_flow_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_flow_genl_ops),
+	.mcgrps = &ovs_dp_flow_multicast_group,
+	.n_mcgrps = 1,
 };
 
 static size_t ovs_dp_cmd_msg_size(void)
@@ -1093,6 +1239,7 @@ static size_t ovs_dp_cmd_msg_size(void)
 	return msgsize;
 }
 
+/* Called with ovs_mutex or RCU read lock. */
 static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 				u32 portid, u32 seq, u32 flags, u8 cmd)
 {
@@ -1108,9 +1255,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 
 	ovs_header->dp_ifindex = get_dpifindex(dp);
 
-	rcu_read_lock();
 	err = nla_put_string(skb, OVS_DP_ATTR_NAME, ovs_dp_name(dp));
-	rcu_read_unlock();
 	if (err)
 		goto nla_put_failure;
 
@@ -1135,25 +1280,12 @@ error:
 	return -EMSGSIZE;
 }
 
-static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp,
-					     struct genl_info *info, u8 cmd)
+static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info)
 {
-	struct sk_buff *skb;
-	int retval;
-
-	skb = genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL);
-	if (!skb)
-		return ERR_PTR(-ENOMEM);
-
-	retval = ovs_dp_cmd_fill_info(dp, skb, info->snd_portid, info->snd_seq, 0, cmd);
-	if (retval < 0) {
-		kfree_skb(skb);
-		return ERR_PTR(retval);
-	}
-	return skb;
+	return genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL);
 }
 
-/* Called with ovs_mutex. */
+/* Called with rcu_read_lock or ovs_mutex. */
 static struct datapath *lookup_datapath(struct net *net,
 					struct ovs_header *ovs_header,
 					struct nlattr *a[OVS_DP_ATTR_MAX + 1])
@@ -1165,10 +1297,8 @@ static struct datapath *lookup_datapath(struct net *net,
 	else {
 		struct vport *vport;
 
-		rcu_read_lock();
 		vport = ovs_vport_locate(net, nla_data(a[OVS_DP_ATTR_NAME]));
 		dp = vport && vport->port_no == OVSP_LOCAL ? vport->dp : NULL;
-		rcu_read_unlock();
 	}
 	return dp ? dp : ERR_PTR(-ENODEV);
 }
@@ -1205,12 +1335,14 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID])
 		goto err;
 
-	ovs_lock();
+	reply = ovs_dp_cmd_alloc_info(info);
+	if (!reply)
+		return -ENOMEM;
 
 	err = -ENOMEM;
 	dp = kzalloc(sizeof(*dp), GFP_KERNEL);
 	if (dp == NULL)
-		goto err_unlock_ovs;
+		goto err_free_reply;
 
 	ovs_dp_set_net(dp, hold_net(sock_net(skb->sk)));
 
@@ -1245,6 +1377,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 
 	ovs_dp_change(dp, a);
 
+	/* So far only local changes have been made, now need the lock. */
+	ovs_lock();
+
 	vport = new_vport(&parms);
 	if (IS_ERR(vport)) {
 		err = PTR_ERR(vport);
@@ -1263,10 +1398,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 		goto err_destroy_ports_array;
 	}
 
-	reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW);
-	err = PTR_ERR(reply);
-	if (IS_ERR(reply))
-		goto err_destroy_local_port;
+	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+				   info->snd_seq, 0, OVS_DP_CMD_NEW);
+	BUG_ON(err < 0);
 
 	ovs_net = net_generic(ovs_dp_get_net(dp), ovs_net_id);
 	list_add_tail_rcu(&dp->list_node, &ovs_net->dps);
@@ -1276,9 +1410,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
-err_destroy_local_port:
-	ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL));
 err_destroy_ports_array:
+	ovs_unlock();
 	kfree(dp->ports);
 err_destroy_percpu:
 	free_percpu(dp->stats_percpu);
@@ -1287,8 +1420,8 @@ err_destroy_table:
 err_free_dp:
 	release_net(ovs_dp_get_net(dp));
 	kfree(dp);
-err_unlock_ovs:
-	ovs_unlock();
+err_free_reply:
+	kfree_skb(reply);
 err:
 	return err;
 }
@@ -1326,16 +1459,19 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	int err;
 
+	reply = ovs_dp_cmd_alloc_info(info);
+	if (!reply)
+		return -ENOMEM;
+
 	ovs_lock();
 	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
 	err = PTR_ERR(dp);
 	if (IS_ERR(dp))
-		goto unlock;
+		goto err_unlock_free;
 
-	reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_DEL);
-	err = PTR_ERR(reply);
-	if (IS_ERR(reply))
-		goto unlock;
+	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+				   info->snd_seq, 0, OVS_DP_CMD_DEL);
+	BUG_ON(err < 0);
 
 	__dp_destroy(dp);
 	ovs_unlock();
@@ -1343,8 +1479,10 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 
 	return 0;
-unlock:
+
+err_unlock_free:
 	ovs_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1354,29 +1492,30 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	int err;
 
+	reply = ovs_dp_cmd_alloc_info(info);
+	if (!reply)
+		return -ENOMEM;
+
 	ovs_lock();
 	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
 	err = PTR_ERR(dp);
 	if (IS_ERR(dp))
-		goto unlock;
+		goto err_unlock_free;
 
 	ovs_dp_change(dp, info->attrs);
 
-	reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW);
-	if (IS_ERR(reply)) {
-		err = PTR_ERR(reply);
-		genl_set_err(&dp_datapath_genl_family, sock_net(skb->sk), 0,
-			     0, err);
-		err = 0;
-		goto unlock;
-	}
+	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+				   info->snd_seq, 0, OVS_DP_CMD_NEW);
+	BUG_ON(err < 0);
 
 	ovs_unlock();
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 
 	return 0;
-unlock:
+
+err_unlock_free:
 	ovs_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1386,24 +1525,26 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	int err;
 
-	ovs_lock();
+	reply = ovs_dp_cmd_alloc_info(info);
+	if (!reply)
+		return -ENOMEM;
+
+	rcu_read_lock();
 	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
 	if (IS_ERR(dp)) {
 		err = PTR_ERR(dp);
-		goto unlock;
-	}
-
-	reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW);
-	if (IS_ERR(reply)) {
-		err = PTR_ERR(reply);
-		goto unlock;
+		goto err_unlock_free;
 	}
+	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
+				   info->snd_seq, 0, OVS_DP_CMD_NEW);
+	BUG_ON(err < 0);
+	rcu_read_unlock();
 
-	ovs_unlock();
 	return genlmsg_reply(reply, info);
 
-unlock:
-	ovs_unlock();
+err_unlock_free:
+	rcu_read_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1430,7 +1571,13 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-static const struct genl_ops dp_datapath_genl_ops[] = {
+static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
+	[OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+	[OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+	[OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
+};
+
+static struct genl_ops dp_datapath_genl_ops[] = {
 	{ .cmd = OVS_DP_CMD_NEW,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .policy = datapath_policy,
@@ -1454,27 +1601,18 @@ static const struct genl_ops dp_datapath_genl_ops[] = {
 	},
 };
 
-static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
-	[OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
-	[OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
-	[OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
-	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
-	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
-	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
-};
-
-struct genl_family dp_vport_genl_family = {
+static struct genl_family dp_datapath_genl_family = {
 	.id = GENL_ID_GENERATE,
 	.hdrsize = sizeof(struct ovs_header),
-	.name = OVS_VPORT_FAMILY,
-	.version = OVS_VPORT_VERSION,
-	.maxattr = OVS_VPORT_ATTR_MAX,
+	.name = OVS_DATAPATH_FAMILY,
+	.version = OVS_DATAPATH_VERSION,
+	.maxattr = OVS_DP_ATTR_MAX,
 	.netnsok = true,
 	.parallel_ops = true,
-};
-
-static struct genl_multicast_group ovs_dp_vport_multicast_group = {
-	.name = OVS_VPORT_MCGROUP
+	.ops = dp_datapath_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_datapath_genl_ops),
+	.mcgrps = &ovs_dp_datapath_multicast_group,
+	.n_mcgrps = 1,
 };
 
 /* Called with ovs_mutex or RCU read lock. */
@@ -1516,7 +1654,12 @@ error:
 	return err;
 }
 
-/* Called with ovs_mutex or RCU read lock. */
+static struct sk_buff *ovs_vport_cmd_alloc_info(void)
+{
+	return nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+}
+
+/* Called with ovs_mutex, only via ovs_dp_notify_wq(). */
 struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
 					 u32 seq, u8 cmd)
 {
@@ -1578,33 +1721,35 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	u32 port_no;
 	int err;
 
-	err = -EINVAL;
 	if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
 	    !a[OVS_VPORT_ATTR_UPCALL_PID])
-		goto exit;
+		return -EINVAL;
+
+	port_no = a[OVS_VPORT_ATTR_PORT_NO]
+		? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0;
+	if (port_no >= DP_MAX_PORTS)
+		return -EFBIG;
+
+	reply = ovs_vport_cmd_alloc_info();
+	if (!reply)
+		return -ENOMEM;
 
 	ovs_lock();
 	dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex);
 	err = -ENODEV;
 	if (!dp)
-		goto exit_unlock;
-
-	if (a[OVS_VPORT_ATTR_PORT_NO]) {
-		port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
-
-		err = -EFBIG;
-		if (port_no >= DP_MAX_PORTS)
-			goto exit_unlock;
+		goto exit_unlock_free;
 
+	if (port_no) {
 		vport = ovs_vport_ovsl(dp, port_no);
 		err = -EBUSY;
 		if (vport)
-			goto exit_unlock;
+			goto exit_unlock_free;
 	} else {
 		for (port_no = 1; ; port_no++) {
 			if (port_no >= DP_MAX_PORTS) {
 				err = -EFBIG;
-				goto exit_unlock;
+				goto exit_unlock_free;
 			}
 			vport = ovs_vport_ovsl(dp, port_no);
 			if (!vport)
@@ -1622,22 +1767,19 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	vport = new_vport(&parms);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
-		goto exit_unlock;
+		goto exit_unlock_free;
 
-	err = 0;
-	reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq,
-					 OVS_VPORT_CMD_NEW);
-	if (IS_ERR(reply)) {
-		err = PTR_ERR(reply);
-		ovs_dp_detach_port(vport);
-		goto exit_unlock;
-	}
+	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	BUG_ON(err < 0);
+	ovs_unlock();
 
 	ovs_notify(&dp_vport_genl_family, reply, info);
+	return 0;
 
-exit_unlock:
+exit_unlock_free:
 	ovs_unlock();
-exit:
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1648,28 +1790,26 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	struct vport *vport;
 	int err;
 
+	reply = ovs_vport_cmd_alloc_info();
+	if (!reply)
+		return -ENOMEM;
+
 	ovs_lock();
 	vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
-		goto exit_unlock;
+		goto exit_unlock_free;
 
 	if (a[OVS_VPORT_ATTR_TYPE] &&
 	    nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) {
 		err = -EINVAL;
-		goto exit_unlock;
-	}
-
-	reply = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!reply) {
-		err = -ENOMEM;
-		goto exit_unlock;
+		goto exit_unlock_free;
 	}
 
 	if (a[OVS_VPORT_ATTR_OPTIONS]) {
 		err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]);
 		if (err)
-			goto exit_free;
+			goto exit_unlock_free;
 	}
 
 	if (a[OVS_VPORT_ATTR_UPCALL_PID])
@@ -1683,10 +1823,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_vport_genl_family, reply, info);
 	return 0;
 
-exit_free:
-	kfree_skb(reply);
-exit_unlock:
+exit_unlock_free:
 	ovs_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1697,30 +1836,33 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	struct vport *vport;
 	int err;
 
+	reply = ovs_vport_cmd_alloc_info();
+	if (!reply)
+		return -ENOMEM;
+
 	ovs_lock();
 	vport = lookup_vport(sock_net(skb->sk), info->userhdr, a);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
-		goto exit_unlock;
+		goto exit_unlock_free;
 
 	if (vport->port_no == OVSP_LOCAL) {
 		err = -EINVAL;
-		goto exit_unlock;
+		goto exit_unlock_free;
 	}
 
-	reply = ovs_vport_cmd_build_info(vport, info->snd_portid,
-					 info->snd_seq, OVS_VPORT_CMD_DEL);
-	err = PTR_ERR(reply);
-	if (IS_ERR(reply))
-		goto exit_unlock;
-
-	err = 0;
+	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+				      info->snd_seq, 0, OVS_VPORT_CMD_DEL);
+	BUG_ON(err < 0);
 	ovs_dp_detach_port(vport);
+	ovs_unlock();
 
 	ovs_notify(&dp_vport_genl_family, reply, info);
+	return 0;
 
-exit_unlock:
+exit_unlock_free:
 	ovs_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1732,24 +1874,25 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
 	struct vport *vport;
 	int err;
 
+	reply = ovs_vport_cmd_alloc_info();
+	if (!reply)
+		return -ENOMEM;
+
 	rcu_read_lock();
 	vport = lookup_vport(sock_net(skb->sk), ovs_header, a);
 	err = PTR_ERR(vport);
 	if (IS_ERR(vport))
-		goto exit_unlock;
-
-	reply = ovs_vport_cmd_build_info(vport, info->snd_portid,
-					 info->snd_seq, OVS_VPORT_CMD_NEW);
-	err = PTR_ERR(reply);
-	if (IS_ERR(reply))
-		goto exit_unlock;
-
+		goto exit_unlock_free;
+	err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
+				      info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+	BUG_ON(err < 0);
 	rcu_read_unlock();
 
 	return genlmsg_reply(reply, info);
 
-exit_unlock:
+exit_unlock_free:
 	rcu_read_unlock();
+	kfree_skb(reply);
 	return err;
 }
 
@@ -1792,7 +1935,16 @@ out:
 	return skb->len;
 }
 
-static const struct genl_ops dp_vport_genl_ops[] = {
+static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
+	[OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+	[OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
+	[OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
+};
+
+static struct genl_ops dp_vport_genl_ops[] = {
 	{ .cmd = OVS_VPORT_CMD_NEW,
 	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
 	  .policy = vport_policy,
@@ -1816,26 +1968,25 @@ static const struct genl_ops dp_vport_genl_ops[] = {
 	},
 };
 
-struct genl_family_and_ops {
-	struct genl_family *family;
-	const struct genl_ops *ops;
-	int n_ops;
-	const struct genl_multicast_group *group;
+struct genl_family dp_vport_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_VPORT_FAMILY,
+	.version = OVS_VPORT_VERSION,
+	.maxattr = OVS_VPORT_ATTR_MAX,
+	.netnsok = true,
+	.parallel_ops = true,
+	.ops = dp_vport_genl_ops,
+	.n_ops = ARRAY_SIZE(dp_vport_genl_ops),
+	.mcgrps = &ovs_dp_vport_multicast_group,
+	.n_mcgrps = 1,
 };
 
-static const struct genl_family_and_ops dp_genl_families[] = {
-	{ &dp_datapath_genl_family,
-	  dp_datapath_genl_ops, ARRAY_SIZE(dp_datapath_genl_ops),
-	  &ovs_dp_datapath_multicast_group },
-	{ &dp_vport_genl_family,
-	  dp_vport_genl_ops, ARRAY_SIZE(dp_vport_genl_ops),
-	  &ovs_dp_vport_multicast_group },
-	{ &dp_flow_genl_family,
-	  dp_flow_genl_ops, ARRAY_SIZE(dp_flow_genl_ops),
-	  &ovs_dp_flow_multicast_group },
-	{ &dp_packet_genl_family,
-	  dp_packet_genl_ops, ARRAY_SIZE(dp_packet_genl_ops),
-	  NULL },
+static struct genl_family * const dp_genl_families[] = {
+	&dp_datapath_genl_family,
+	&dp_vport_genl_family,
+	&dp_flow_genl_family,
+	&dp_packet_genl_family,
 };
 
 static void dp_unregister_genl(int n_families)
@@ -1843,33 +1994,25 @@ static void dp_unregister_genl(int n_families)
 	int i;
 
 	for (i = 0; i < n_families; i++)
-		genl_unregister_family(dp_genl_families[i].family);
+		genl_unregister_family(dp_genl_families[i]);
 }
 
 static int dp_register_genl(void)
 {
-	int n_registered;
 	int err;
 	int i;
 
-	n_registered = 0;
 	for (i = 0; i < ARRAY_SIZE(dp_genl_families); i++) {
-		const struct genl_family_and_ops *f = &dp_genl_families[i];
 
-		f->family->ops = f->ops;
-		f->family->n_ops = f->n_ops;
-		f->family->mcgrps = f->group;
-		f->family->n_mcgrps = f->group ? 1 : 0;
-		err = genl_register_family(f->family);
+		err = genl_register_family(dp_genl_families[i]);
 		if (err)
 			goto error;
-		n_registered++;
 	}
 
 	return 0;
 
 error:
-	dp_unregister_genl(n_registered);
+	dp_unregister_genl(i);
 	return err;
 }
 
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 05317380fc0..7ede507500d 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -194,7 +194,9 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
 int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb);
 void ovs_dp_notify_wq(struct work_struct *work);
 
-#define OVS_NLERR(fmt, ...) \
-	pr_info_once("netlink: " fmt, ##__VA_ARGS__)
-
+#define OVS_NLERR(fmt, ...)					\
+do {								\
+	if (net_ratelimit())					\
+		pr_info("netlink: " fmt, ##__VA_ARGS__);	\
+} while (0)
 #endif /* datapath.h */
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 2998989e76d..d07ab538fc9 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -61,91 +61,113 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
 
 #define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))
 
-void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb)
+void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
+			   struct sk_buff *skb)
 {
 	struct flow_stats *stats;
-	__be16 tcp_flags = 0;
-
-	if (!flow->stats.is_percpu)
-		stats = flow->stats.stat;
-	else
-		stats = this_cpu_ptr(flow->stats.cpu_stats);
-
-	if ((flow->key.eth.type == htons(ETH_P_IP) ||
-	     flow->key.eth.type == htons(ETH_P_IPV6)) &&
-	    flow->key.ip.frag != OVS_FRAG_TYPE_LATER &&
-	    flow->key.ip.proto == IPPROTO_TCP &&
-	    likely(skb->len >= skb_transport_offset(skb) + sizeof(struct tcphdr))) {
-		tcp_flags = TCP_FLAGS_BE16(tcp_hdr(skb));
+	int node = numa_node_id();
+
+	stats = rcu_dereference(flow->stats[node]);
+
+	/* Check if already have node-specific stats. */
+	if (likely(stats)) {
+		spin_lock(&stats->lock);
+		/* Mark if we write on the pre-allocated stats. */
+		if (node == 0 && unlikely(flow->stats_last_writer != node))
+			flow->stats_last_writer = node;
+	} else {
+		stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */
+		spin_lock(&stats->lock);
+
+		/* If the current NUMA-node is the only writer on the
+		 * pre-allocated stats keep using them.
+		 */
+		if (unlikely(flow->stats_last_writer != node)) {
+			/* A previous locker may have already allocated the
+			 * stats, so we need to check again.  If node-specific
+			 * stats were already allocated, we update the pre-
+			 * allocated stats as we have already locked them.
+			 */
+			if (likely(flow->stats_last_writer != NUMA_NO_NODE)
+			    && likely(!rcu_dereference(flow->stats[node]))) {
+				/* Try to allocate node-specific stats. */
+				struct flow_stats *new_stats;
+
+				new_stats =
+					kmem_cache_alloc_node(flow_stats_cache,
+							      GFP_THISNODE |
+							      __GFP_NOMEMALLOC,
+							      node);
+				if (likely(new_stats)) {
+					new_stats->used = jiffies;
+					new_stats->packet_count = 1;
+					new_stats->byte_count = skb->len;
+					new_stats->tcp_flags = tcp_flags;
+					spin_lock_init(&new_stats->lock);
+
+					rcu_assign_pointer(flow->stats[node],
+							   new_stats);
+					goto unlock;
+				}
+			}
+			flow->stats_last_writer = node;
+		}
 	}
 
-	spin_lock(&stats->lock);
 	stats->used = jiffies;
 	stats->packet_count++;
 	stats->byte_count += skb->len;
 	stats->tcp_flags |= tcp_flags;
+unlock:
 	spin_unlock(&stats->lock);
 }
 
-static void stats_read(struct flow_stats *stats,
-		       struct ovs_flow_stats *ovs_stats,
-		       unsigned long *used, __be16 *tcp_flags)
-{
-	spin_lock(&stats->lock);
-	if (!*used || time_after(stats->used, *used))
-		*used = stats->used;
-	*tcp_flags |= stats->tcp_flags;
-	ovs_stats->n_packets += stats->packet_count;
-	ovs_stats->n_bytes += stats->byte_count;
-	spin_unlock(&stats->lock);
-}
-
-void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats,
+/* Must be called with rcu_read_lock or ovs_mutex. */
+void ovs_flow_stats_get(const struct sw_flow *flow,
+			struct ovs_flow_stats *ovs_stats,
 			unsigned long *used, __be16 *tcp_flags)
 {
-	int cpu;
+	int node;
 
 	*used = 0;
 	*tcp_flags = 0;
 	memset(ovs_stats, 0, sizeof(*ovs_stats));
 
-	local_bh_disable();
-	if (!flow->stats.is_percpu) {
-		stats_read(flow->stats.stat, ovs_stats, used, tcp_flags);
-	} else {
-		for_each_possible_cpu(cpu) {
-			struct flow_stats *stats;
+	for_each_node(node) {
+		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]);
 
-			stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
-			stats_read(stats, ovs_stats, used, tcp_flags);
+		if (stats) {
+			/* Local CPU may write on non-local stats, so we must
+			 * block bottom-halves here.
+			 */
+			spin_lock_bh(&stats->lock);
+			if (!*used || time_after(stats->used, *used))
+				*used = stats->used;
+			*tcp_flags |= stats->tcp_flags;
+			ovs_stats->n_packets += stats->packet_count;
+			ovs_stats->n_bytes += stats->byte_count;
+			spin_unlock_bh(&stats->lock);
 		}
 	}
-	local_bh_enable();
-}
-
-static void stats_reset(struct flow_stats *stats)
-{
-	spin_lock(&stats->lock);
-	stats->used = 0;
-	stats->packet_count = 0;
-	stats->byte_count = 0;
-	stats->tcp_flags = 0;
-	spin_unlock(&stats->lock);
 }
 
+/* Called with ovs_mutex. */
 void ovs_flow_stats_clear(struct sw_flow *flow)
 {
-	int cpu;
-
-	local_bh_disable();
-	if (!flow->stats.is_percpu) {
-		stats_reset(flow->stats.stat);
-	} else {
-		for_each_possible_cpu(cpu) {
-			stats_reset(per_cpu_ptr(flow->stats.cpu_stats, cpu));
+	int node;
+
+	for_each_node(node) {
+		struct flow_stats *stats = ovsl_dereference(flow->stats[node]);
+
+		if (stats) {
+			spin_lock_bh(&stats->lock);
+			stats->used = 0;
+			stats->packet_count = 0;
+			stats->byte_count = 0;
+			stats->tcp_flags = 0;
+			spin_unlock_bh(&stats->lock);
 		}
 	}
-	local_bh_enable();
 }
 
 static int check_header(struct sk_buff *skb, int len)
@@ -332,8 +354,8 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
 	/* The ICMPv6 type and code fields use the 16-bit transport port
 	 * fields, so we need to store them in 16-bit network byte order.
 	 */
-	key->ipv6.tp.src = htons(icmp->icmp6_type);
-	key->ipv6.tp.dst = htons(icmp->icmp6_code);
+	key->tp.src = htons(icmp->icmp6_type);
+	key->tp.dst = htons(icmp->icmp6_code);
 
 	if (icmp->icmp6_code == 0 &&
 	    (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
@@ -372,14 +394,14 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
 			    && opt_len == 8) {
 				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll)))
 					goto invalid;
-				memcpy(key->ipv6.nd.sll,
-				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+				ether_addr_copy(key->ipv6.nd.sll,
+						&nd->opt[offset+sizeof(*nd_opt)]);
 			} else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR
 				   && opt_len == 8) {
 				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll)))
 					goto invalid;
-				memcpy(key->ipv6.nd.tll,
-				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+				ether_addr_copy(key->ipv6.nd.tll,
+						&nd->opt[offset+sizeof(*nd_opt)]);
 			}
 
 			icmp_len -= opt_len;
@@ -439,8 +461,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 	 * header in the linear data area.
 	 */
 	eth = eth_hdr(skb);
-	memcpy(key->eth.src, eth->h_source, ETH_ALEN);
-	memcpy(key->eth.dst, eth->h_dest, ETH_ALEN);
+	ether_addr_copy(key->eth.src, eth->h_source);
+	ether_addr_copy(key->eth.dst, eth->h_dest);
 
 	__skb_pull(skb, 2 * ETH_ALEN);
 	/* We are going to push all headers that we pull, so no need to
@@ -495,21 +517,21 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 		if (key->ip.proto == IPPROTO_TCP) {
 			if (tcphdr_ok(skb)) {
 				struct tcphdr *tcp = tcp_hdr(skb);
-				key->ipv4.tp.src = tcp->source;
-				key->ipv4.tp.dst = tcp->dest;
-				key->ipv4.tp.flags = TCP_FLAGS_BE16(tcp);
+				key->tp.src = tcp->source;
+				key->tp.dst = tcp->dest;
+				key->tp.flags = TCP_FLAGS_BE16(tcp);
 			}
 		} else if (key->ip.proto == IPPROTO_UDP) {
 			if (udphdr_ok(skb)) {
 				struct udphdr *udp = udp_hdr(skb);
-				key->ipv4.tp.src = udp->source;
-				key->ipv4.tp.dst = udp->dest;
+				key->tp.src = udp->source;
+				key->tp.dst = udp->dest;
 			}
 		} else if (key->ip.proto == IPPROTO_SCTP) {
 			if (sctphdr_ok(skb)) {
 				struct sctphdr *sctp = sctp_hdr(skb);
-				key->ipv4.tp.src = sctp->source;
-				key->ipv4.tp.dst = sctp->dest;
+				key->tp.src = sctp->source;
+				key->tp.dst = sctp->dest;
 			}
 		} else if (key->ip.proto == IPPROTO_ICMP) {
 			if (icmphdr_ok(skb)) {
@@ -517,8 +539,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 				/* The ICMP type and code fields use the 16-bit
 				 * transport port fields, so we need to store
 				 * them in 16-bit network byte order. */
-				key->ipv4.tp.src = htons(icmp->type);
-				key->ipv4.tp.dst = htons(icmp->code);
+				key->tp.src = htons(icmp->type);
+				key->tp.dst = htons(icmp->code);
 			}
 		}
 
@@ -538,8 +560,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 				key->ip.proto = ntohs(arp->ar_op);
 			memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
 			memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
-			memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN);
-			memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN);
+			ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha);
+			ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha);
 		}
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		int nh_len;             /* IPv6 Header + Extensions */
@@ -564,21 +586,21 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key)
 		if (key->ip.proto == NEXTHDR_TCP) {
 			if (tcphdr_ok(skb)) {
 				struct tcphdr *tcp = tcp_hdr(skb);
-				key->ipv6.tp.src = tcp->source;
-				key->ipv6.tp.dst = tcp->dest;
-				key->ipv6.tp.flags = TCP_FLAGS_BE16(tcp);
+				key->tp.src = tcp->source;
+				key->tp.dst = tcp->dest;
+				key->tp.flags = TCP_FLAGS_BE16(tcp);
 			}
 		} else if (key->ip.proto == NEXTHDR_UDP) {
 			if (udphdr_ok(skb)) {
 				struct udphdr *udp = udp_hdr(skb);
-				key->ipv6.tp.src = udp->source;
-				key->ipv6.tp.dst = udp->dest;
+				key->tp.src = udp->source;
+				key->tp.dst = udp->dest;
 			}
 		} else if (key->ip.proto == NEXTHDR_SCTP) {
 			if (sctphdr_ok(skb)) {
 				struct sctphdr *sctp = sctp_hdr(skb);
-				key->ipv6.tp.src = sctp->source;
-				key->ipv6.tp.dst = sctp->dest;
+				key->tp.src = sctp->source;
+				key->tp.dst = sctp->dest;
 			}
 		} else if (key->ip.proto == NEXTHDR_ICMP) {
 			if (icmp6hdr_ok(skb)) {
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 2d770e28a3a..5e5aaed3a85 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of version 2 of the GNU General Public
@@ -47,7 +47,7 @@ struct ovs_key_ipv4_tunnel {
 	__be16 tun_flags;
 	u8   ipv4_tos;
 	u8   ipv4_ttl;
-};
+} __packed __aligned(4); /* Minimize padding. */
 
 static inline void ovs_flow_tun_key_init(struct ovs_key_ipv4_tunnel *tun_key,
 					 const struct iphdr *iph, __be64 tun_id,
@@ -71,7 +71,7 @@ struct sw_flow_key {
 		u32	priority;	/* Packet QoS priority. */
 		u32	skb_mark;	/* SKB mark. */
 		u16	in_port;	/* Input switch port (or DP_MAX_PORTS). */
-	} phy;
+	} __packed phy; /* Safe when right after 'tun_key'. */
 	struct {
 		u8     src[ETH_ALEN];	/* Ethernet source address. */
 		u8     dst[ETH_ALEN];	/* Ethernet destination address. */
@@ -84,23 +84,21 @@ struct sw_flow_key {
 		u8     ttl;		/* IP TTL/hop limit. */
 		u8     frag;		/* One of OVS_FRAG_TYPE_*. */
 	} ip;
+	struct {
+		__be16 src;		/* TCP/UDP/SCTP source port. */
+		__be16 dst;		/* TCP/UDP/SCTP destination port. */
+		__be16 flags;		/* TCP flags. */
+	} tp;
 	union {
 		struct {
 			struct {
 				__be32 src;	/* IP source address. */
 				__be32 dst;	/* IP destination address. */
 			} addr;
-			union {
-				struct {
-					__be16 src;		/* TCP/UDP/SCTP source port. */
-					__be16 dst;		/* TCP/UDP/SCTP destination port. */
-					__be16 flags;		/* TCP flags. */
-				} tp;
-				struct {
-					u8 sha[ETH_ALEN];	/* ARP source hardware address. */
-					u8 tha[ETH_ALEN];	/* ARP target hardware address. */
-				} arp;
-			};
+			struct {
+				u8 sha[ETH_ALEN];	/* ARP source hardware address. */
+				u8 tha[ETH_ALEN];	/* ARP target hardware address. */
+			} arp;
 		} ipv4;
 		struct {
 			struct {
@@ -109,11 +107,6 @@ struct sw_flow_key {
 			} addr;
 			__be32 label;			/* IPv6 flow label. */
 			struct {
-				__be16 src;		/* TCP/UDP/SCTP source port. */
-				__be16 dst;		/* TCP/UDP/SCTP destination port. */
-				__be16 flags;		/* TCP flags. */
-			} tp;
-			struct {
 				struct in6_addr target;	/* ND target address. */
 				u8 sll[ETH_ALEN];	/* ND source link layer address. */
 				u8 tll[ETH_ALEN];	/* ND target link layer address. */
@@ -155,24 +148,22 @@ struct flow_stats {
 	__be16 tcp_flags;		/* Union of seen TCP flags. */
 };
 
-struct sw_flow_stats {
-	bool is_percpu;
-	union {
-		struct flow_stats *stat;
-		struct flow_stats __percpu *cpu_stats;
-	};
-};
-
 struct sw_flow {
 	struct rcu_head rcu;
 	struct hlist_node hash_node[2];
 	u32 hash;
-
+	int stats_last_writer;		/* NUMA-node id of the last writer on
+					 * 'stats[0]'.
+					 */
 	struct sw_flow_key key;
 	struct sw_flow_key unmasked_key;
 	struct sw_flow_mask *mask;
 	struct sw_flow_actions __rcu *sf_acts;
-	struct sw_flow_stats stats;
+	struct flow_stats __rcu *stats[]; /* One for each NUMA node.  First one
+					   * is allocated at flow creation time,
+					   * the rest are allocated on demand
+					   * while holding the 'stats[0].lock'.
+					   */
 };
 
 struct arp_eth_header {
@@ -189,10 +180,11 @@ struct arp_eth_header {
 	unsigned char       ar_tip[4];		/* target IP address        */
 } __packed;
 
-void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb);
-void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *stats,
+void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags,
+			   struct sk_buff *);
+void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *,
 			unsigned long *used, __be16 *tcp_flags);
-void ovs_flow_stats_clear(struct sw_flow *flow);
+void ovs_flow_stats_clear(struct sw_flow *);
 u64 ovs_flow_used_time(unsigned long flow_jiffies);
 
 int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 4d000acaed0..d757848da89 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -16,6 +16,8 @@
  * 02110-1301, USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include "flow.h"
 #include "datapath.h"
 #include <linux/uaccess.h>
@@ -202,11 +204,11 @@ static bool match_validate(const struct sw_flow_match *match,
 				if (match->mask && (match->mask->key.ip.proto == 0xff))
 					mask_allowed |= 1 << OVS_KEY_ATTR_ICMPV6;
 
-				if (match->key->ipv6.tp.src ==
+				if (match->key->tp.src ==
 						htons(NDISC_NEIGHBOUR_SOLICITATION) ||
-				    match->key->ipv6.tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
+				    match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
 					key_expected |= 1 << OVS_KEY_ATTR_ND;
-					if (match->mask && (match->mask->key.ipv6.tp.src == htons(0xffff)))
+					if (match->mask && (match->mask->key.tp.src == htons(0xffff)))
 						mask_allowed |= 1 << OVS_KEY_ATTR_ND;
 				}
 			}
@@ -216,14 +218,14 @@ static bool match_validate(const struct sw_flow_match *match,
 	if ((key_attrs & key_expected) != key_expected) {
 		/* Key attributes check failed. */
 		OVS_NLERR("Missing expected key attributes (key_attrs=%llx, expected=%llx).\n",
-				key_attrs, key_expected);
+				(unsigned long long)key_attrs, (unsigned long long)key_expected);
 		return false;
 	}
 
 	if ((mask_attrs & mask_allowed) != mask_attrs) {
 		/* Mask attributes check failed. */
 		OVS_NLERR("Contain more than allowed mask fields (mask_attrs=%llx, mask_allowed=%llx).\n",
-				mask_attrs, mask_allowed);
+				(unsigned long long)mask_attrs, (unsigned long long)mask_allowed);
 		return false;
 	}
 
@@ -266,20 +268,6 @@ static bool is_all_zero(const u8 *fp, size_t size)
 	return true;
 }
 
-static bool is_all_set(const u8 *fp, size_t size)
-{
-	int i;
-
-	if (!fp)
-		return false;
-
-	for (i = 0; i < size; i++)
-		if (fp[i] != 0xff)
-			return false;
-
-	return true;
-}
-
 static int __parse_flow_nlattrs(const struct nlattr *attr,
 				const struct nlattr *a[],
 				u64 *attrsp, bool nz)
@@ -501,9 +489,8 @@ static int metadata_from_nlattrs(struct sw_flow_match *match,  u64 *attrs,
 	return 0;
 }
 
-static int ovs_key_from_nlattrs(struct sw_flow_match *match,  bool *exact_5tuple,
-				u64 attrs, const struct nlattr **a,
-				bool is_mask)
+static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
+				const struct nlattr **a, bool is_mask)
 {
 	int err;
 	u64 orig_attrs = attrs;
@@ -560,11 +547,6 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  bool *exact_5tuple
 		SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
 	}
 
-	if (is_mask && exact_5tuple) {
-		if (match->mask->key.eth.type != htons(0xffff))
-			*exact_5tuple = false;
-	}
-
 	if (attrs & (1 << OVS_KEY_ATTR_IPV4)) {
 		const struct ovs_key_ipv4 *ipv4_key;
 
@@ -587,13 +569,6 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  bool *exact_5tuple
 		SW_FLOW_KEY_PUT(match, ipv4.addr.dst,
 				ipv4_key->ipv4_dst, is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_IPV4);
-
-		if (is_mask && exact_5tuple && *exact_5tuple) {
-			if (ipv4_key->ipv4_proto != 0xff ||
-			    ipv4_key->ipv4_src != htonl(0xffffffff) ||
-			    ipv4_key->ipv4_dst != htonl(0xffffffff))
-				*exact_5tuple = false;
-		}
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_IPV6)) {
@@ -625,13 +600,6 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  bool *exact_5tuple
 				is_mask);
 
 		attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
-
-		if (is_mask && exact_5tuple && *exact_5tuple) {
-			if (ipv6_key->ipv6_proto != 0xff ||
-			    !is_all_set((u8 *)ipv6_key->ipv6_src, sizeof(match->key->ipv6.addr.src)) ||
-			    !is_all_set((u8 *)ipv6_key->ipv6_dst, sizeof(match->key->ipv6.addr.dst)))
-				*exact_5tuple = false;
-		}
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_ARP)) {
@@ -662,32 +630,18 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  bool *exact_5tuple
 		const struct ovs_key_tcp *tcp_key;
 
 		tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
-		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
-			SW_FLOW_KEY_PUT(match, ipv4.tp.src,
-					tcp_key->tcp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
-					tcp_key->tcp_dst, is_mask);
-		} else {
-			SW_FLOW_KEY_PUT(match, ipv6.tp.src,
-					tcp_key->tcp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
-					tcp_key->tcp_dst, is_mask);
-		}
+		SW_FLOW_KEY_PUT(match, tp.src, tcp_key->tcp_src, is_mask);
+		SW_FLOW_KEY_PUT(match, tp.dst, tcp_key->tcp_dst, is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_TCP);
-
-		if (is_mask && exact_5tuple && *exact_5tuple &&
-		    (tcp_key->tcp_src != htons(0xffff) ||
-		     tcp_key->tcp_dst != htons(0xffff)))
-			*exact_5tuple = false;
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) {
 		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
-			SW_FLOW_KEY_PUT(match, ipv4.tp.flags,
+			SW_FLOW_KEY_PUT(match, tp.flags,
 					nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
 					is_mask);
 		} else {
-			SW_FLOW_KEY_PUT(match, ipv6.tp.flags,
+			SW_FLOW_KEY_PUT(match, tp.flags,
 					nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
 					is_mask);
 		}
@@ -698,40 +652,17 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  bool *exact_5tuple
 		const struct ovs_key_udp *udp_key;
 
 		udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
-		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
-			SW_FLOW_KEY_PUT(match, ipv4.tp.src,
-					udp_key->udp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
-					udp_key->udp_dst, is_mask);
-		} else {
-			SW_FLOW_KEY_PUT(match, ipv6.tp.src,
-					udp_key->udp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
-					udp_key->udp_dst, is_mask);
-		}
+		SW_FLOW_KEY_PUT(match, tp.src, udp_key->udp_src, is_mask);
+		SW_FLOW_KEY_PUT(match, tp.dst, udp_key->udp_dst, is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_UDP);
-
-		if (is_mask && exact_5tuple && *exact_5tuple &&
-		    (udp_key->udp_src != htons(0xffff) ||
-		     udp_key->udp_dst != htons(0xffff)))
-			*exact_5tuple = false;
 	}
 
 	if (attrs & (1 << OVS_KEY_ATTR_SCTP)) {
 		const struct ovs_key_sctp *sctp_key;
 
 		sctp_key = nla_data(a[OVS_KEY_ATTR_SCTP]);
-		if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) {
-			SW_FLOW_KEY_PUT(match, ipv4.tp.src,
-					sctp_key->sctp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
-					sctp_key->sctp_dst, is_mask);
-		} else {
-			SW_FLOW_KEY_PUT(match, ipv6.tp.src,
-					sctp_key->sctp_src, is_mask);
-			SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
-					sctp_key->sctp_dst, is_mask);
-		}
+		SW_FLOW_KEY_PUT(match, tp.src, sctp_key->sctp_src, is_mask);
+		SW_FLOW_KEY_PUT(match, tp.dst, sctp_key->sctp_dst, is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_SCTP);
 	}
 
@@ -739,9 +670,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  bool *exact_5tuple
 		const struct ovs_key_icmp *icmp_key;
 
 		icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]);
-		SW_FLOW_KEY_PUT(match, ipv4.tp.src,
+		SW_FLOW_KEY_PUT(match, tp.src,
 				htons(icmp_key->icmp_type), is_mask);
-		SW_FLOW_KEY_PUT(match, ipv4.tp.dst,
+		SW_FLOW_KEY_PUT(match, tp.dst,
 				htons(icmp_key->icmp_code), is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_ICMP);
 	}
@@ -750,9 +681,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match,  bool *exact_5tuple
 		const struct ovs_key_icmpv6 *icmpv6_key;
 
 		icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]);
-		SW_FLOW_KEY_PUT(match, ipv6.tp.src,
+		SW_FLOW_KEY_PUT(match, tp.src,
 				htons(icmpv6_key->icmpv6_type), is_mask);
-		SW_FLOW_KEY_PUT(match, ipv6.tp.dst,
+		SW_FLOW_KEY_PUT(match, tp.dst,
 				htons(icmpv6_key->icmpv6_code), is_mask);
 		attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6);
 	}
@@ -800,7 +731,6 @@ static void sw_flow_mask_set(struct sw_flow_mask *mask,
  * attribute specifies the mask field of the wildcarded flow.
  */
 int ovs_nla_get_match(struct sw_flow_match *match,
-		      bool *exact_5tuple,
 		      const struct nlattr *key,
 		      const struct nlattr *mask)
 {
@@ -848,13 +778,10 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 		}
 	}
 
-	err = ovs_key_from_nlattrs(match, NULL, key_attrs, a, false);
+	err = ovs_key_from_nlattrs(match, key_attrs, a, false);
 	if (err)
 		return err;
 
-	if (exact_5tuple)
-		*exact_5tuple = true;
-
 	if (mask) {
 		err = parse_flow_mask_nlattrs(mask, a, &mask_attrs);
 		if (err)
@@ -892,7 +819,7 @@ int ovs_nla_get_match(struct sw_flow_match *match,
 			}
 		}
 
-		err = ovs_key_from_nlattrs(match, exact_5tuple, mask_attrs, a, true);
+		err = ovs_key_from_nlattrs(match, mask_attrs, a, true);
 		if (err)
 			return err;
 	} else {
@@ -982,8 +909,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 		goto nla_put_failure;
 
 	eth_key = nla_data(nla);
-	memcpy(eth_key->eth_src, output->eth.src, ETH_ALEN);
-	memcpy(eth_key->eth_dst, output->eth.dst, ETH_ALEN);
+	ether_addr_copy(eth_key->eth_src, output->eth.src);
+	ether_addr_copy(eth_key->eth_dst, output->eth.dst);
 
 	if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) {
 		__be16 eth_type;
@@ -1055,8 +982,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 		arp_key->arp_sip = output->ipv4.addr.src;
 		arp_key->arp_tip = output->ipv4.addr.dst;
 		arp_key->arp_op = htons(output->ip.proto);
-		memcpy(arp_key->arp_sha, output->ipv4.arp.sha, ETH_ALEN);
-		memcpy(arp_key->arp_tha, output->ipv4.arp.tha, ETH_ALEN);
+		ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
+		ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
 	}
 
 	if ((swkey->eth.type == htons(ETH_P_IP) ||
@@ -1070,19 +997,11 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			tcp_key = nla_data(nla);
-			if (swkey->eth.type == htons(ETH_P_IP)) {
-				tcp_key->tcp_src = output->ipv4.tp.src;
-				tcp_key->tcp_dst = output->ipv4.tp.dst;
-				if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
-						 output->ipv4.tp.flags))
-					goto nla_put_failure;
-			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-				tcp_key->tcp_src = output->ipv6.tp.src;
-				tcp_key->tcp_dst = output->ipv6.tp.dst;
-				if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
-						 output->ipv6.tp.flags))
-					goto nla_put_failure;
-			}
+			tcp_key->tcp_src = output->tp.src;
+			tcp_key->tcp_dst = output->tp.dst;
+			if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
+					 output->tp.flags))
+				goto nla_put_failure;
 		} else if (swkey->ip.proto == IPPROTO_UDP) {
 			struct ovs_key_udp *udp_key;
 
@@ -1090,13 +1009,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			udp_key = nla_data(nla);
-			if (swkey->eth.type == htons(ETH_P_IP)) {
-				udp_key->udp_src = output->ipv4.tp.src;
-				udp_key->udp_dst = output->ipv4.tp.dst;
-			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-				udp_key->udp_src = output->ipv6.tp.src;
-				udp_key->udp_dst = output->ipv6.tp.dst;
-			}
+			udp_key->udp_src = output->tp.src;
+			udp_key->udp_dst = output->tp.dst;
 		} else if (swkey->ip.proto == IPPROTO_SCTP) {
 			struct ovs_key_sctp *sctp_key;
 
@@ -1104,13 +1018,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			sctp_key = nla_data(nla);
-			if (swkey->eth.type == htons(ETH_P_IP)) {
-				sctp_key->sctp_src = swkey->ipv4.tp.src;
-				sctp_key->sctp_dst = swkey->ipv4.tp.dst;
-			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
-				sctp_key->sctp_src = swkey->ipv6.tp.src;
-				sctp_key->sctp_dst = swkey->ipv6.tp.dst;
-			}
+			sctp_key->sctp_src = output->tp.src;
+			sctp_key->sctp_dst = output->tp.dst;
 		} else if (swkey->eth.type == htons(ETH_P_IP) &&
 			   swkey->ip.proto == IPPROTO_ICMP) {
 			struct ovs_key_icmp *icmp_key;
@@ -1119,8 +1028,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			icmp_key = nla_data(nla);
-			icmp_key->icmp_type = ntohs(output->ipv4.tp.src);
-			icmp_key->icmp_code = ntohs(output->ipv4.tp.dst);
+			icmp_key->icmp_type = ntohs(output->tp.src);
+			icmp_key->icmp_code = ntohs(output->tp.dst);
 		} else if (swkey->eth.type == htons(ETH_P_IPV6) &&
 			   swkey->ip.proto == IPPROTO_ICMPV6) {
 			struct ovs_key_icmpv6 *icmpv6_key;
@@ -1130,8 +1039,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 			if (!nla)
 				goto nla_put_failure;
 			icmpv6_key = nla_data(nla);
-			icmpv6_key->icmpv6_type = ntohs(output->ipv6.tp.src);
-			icmpv6_key->icmpv6_code = ntohs(output->ipv6.tp.dst);
+			icmpv6_key->icmpv6_type = ntohs(output->tp.src);
+			icmpv6_key->icmpv6_code = ntohs(output->tp.dst);
 
 			if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
 			    icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
@@ -1143,8 +1052,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
 				nd_key = nla_data(nla);
 				memcpy(nd_key->nd_target, &output->ipv6.nd.target,
 							sizeof(nd_key->nd_target));
-				memcpy(nd_key->nd_sll, output->ipv6.nd.sll, ETH_ALEN);
-				memcpy(nd_key->nd_tll, output->ipv6.nd.tll, ETH_ALEN);
+				ether_addr_copy(nd_key->nd_sll, output->ipv6.nd.sll);
+				ether_addr_copy(nd_key->nd_tll, output->ipv6.nd.tll);
 			}
 		}
 	}
@@ -1309,13 +1218,10 @@ static int validate_and_copy_sample(const struct nlattr *attr,
 
 static int validate_tp_port(const struct sw_flow_key *flow_key)
 {
-	if (flow_key->eth.type == htons(ETH_P_IP)) {
-		if (flow_key->ipv4.tp.src || flow_key->ipv4.tp.dst)
-			return 0;
-	} else if (flow_key->eth.type == htons(ETH_P_IPV6)) {
-		if (flow_key->ipv6.tp.src || flow_key->ipv6.tp.dst)
-			return 0;
-	}
+	if ((flow_key->eth.type == htons(ETH_P_IP) ||
+	     flow_key->eth.type == htons(ETH_P_IPV6)) &&
+	    (flow_key->tp.src || flow_key->tp.dst))
+		return 0;
 
 	return -EINVAL;
 }
diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h
index b31fbe28bc7..440151045d3 100644
--- a/net/openvswitch/flow_netlink.h
+++ b/net/openvswitch/flow_netlink.h
@@ -45,7 +45,6 @@ int ovs_nla_put_flow(const struct sw_flow_key *,
 int ovs_nla_get_flow_metadata(struct sw_flow *flow,
 			      const struct nlattr *attr);
 int ovs_nla_get_match(struct sw_flow_match *match,
-		      bool *exact_5tuple,
 		      const struct nlattr *,
 		      const struct nlattr *);
 
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 3c268b3d71c..cf2d853646f 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -48,6 +48,7 @@
 #define REHASH_INTERVAL		(10 * 60 * HZ)
 
 static struct kmem_cache *flow_cache;
+struct kmem_cache *flow_stats_cache __read_mostly;
 
 static u16 range_n_bytes(const struct sw_flow_key_range *range)
 {
@@ -57,8 +58,10 @@ static u16 range_n_bytes(const struct sw_flow_key_range *range)
 void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 		       const struct sw_flow_mask *mask)
 {
-	const long *m = (long *)((u8 *)&mask->key + mask->range.start);
-	const long *s = (long *)((u8 *)src + mask->range.start);
+	const long *m = (const long *)((const u8 *)&mask->key +
+				mask->range.start);
+	const long *s = (const long *)((const u8 *)src +
+				mask->range.start);
 	long *d = (long *)((u8 *)dst + mask->range.start);
 	int i;
 
@@ -70,10 +73,11 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 		*d++ = *s++ & *m++;
 }
 
-struct sw_flow *ovs_flow_alloc(bool percpu_stats)
+struct sw_flow *ovs_flow_alloc(void)
 {
 	struct sw_flow *flow;
-	int cpu;
+	struct flow_stats *stats;
+	int node;
 
 	flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
 	if (!flow)
@@ -81,27 +85,22 @@ struct sw_flow *ovs_flow_alloc(bool percpu_stats)
 
 	flow->sf_acts = NULL;
 	flow->mask = NULL;
+	flow->stats_last_writer = NUMA_NO_NODE;
 
-	flow->stats.is_percpu = percpu_stats;
+	/* Initialize the default stat node. */
+	stats = kmem_cache_alloc_node(flow_stats_cache,
+				      GFP_KERNEL | __GFP_ZERO, 0);
+	if (!stats)
+		goto err;
 
-	if (!percpu_stats) {
-		flow->stats.stat = kzalloc(sizeof(*flow->stats.stat), GFP_KERNEL);
-		if (!flow->stats.stat)
-			goto err;
+	spin_lock_init(&stats->lock);
 
-		spin_lock_init(&flow->stats.stat->lock);
-	} else {
-		flow->stats.cpu_stats = alloc_percpu(struct flow_stats);
-		if (!flow->stats.cpu_stats)
-			goto err;
+	RCU_INIT_POINTER(flow->stats[0], stats);
 
-		for_each_possible_cpu(cpu) {
-			struct flow_stats *cpu_stats;
+	for_each_node(node)
+		if (node != 0)
+			RCU_INIT_POINTER(flow->stats[node], NULL);
 
-			cpu_stats = per_cpu_ptr(flow->stats.cpu_stats, cpu);
-			spin_lock_init(&cpu_stats->lock);
-		}
-	}
 	return flow;
 err:
 	kmem_cache_free(flow_cache, flow);
@@ -138,11 +137,13 @@ static struct flex_array *alloc_buckets(unsigned int n_buckets)
 
 static void flow_free(struct sw_flow *flow)
 {
-	kfree((struct sf_flow_acts __force *)flow->sf_acts);
-	if (flow->stats.is_percpu)
-		free_percpu(flow->stats.cpu_stats);
-	else
-		kfree(flow->stats.stat);
+	int node;
+
+	kfree((struct sw_flow_actions __force *)flow->sf_acts);
+	for_each_node(node)
+		if (flow->stats[node])
+			kmem_cache_free(flow_stats_cache,
+					(struct flow_stats __force *)flow->stats[node]);
 	kmem_cache_free(flow_cache, flow);
 }
 
@@ -158,25 +159,6 @@ void ovs_flow_free(struct sw_flow *flow, bool deferred)
 	if (!flow)
 		return;
 
-	if (flow->mask) {
-		struct sw_flow_mask *mask = flow->mask;
-
-		/* ovs-lock is required to protect mask-refcount and
-		 * mask list.
-		 */
-		ASSERT_OVSL();
-		BUG_ON(!mask->ref_count);
-		mask->ref_count--;
-
-		if (!mask->ref_count) {
-			list_del_rcu(&mask->list);
-			if (deferred)
-				kfree_rcu(mask, rcu);
-			else
-				kfree(mask);
-		}
-	}
-
 	if (deferred)
 		call_rcu(&flow->rcu, rcu_free_flow_callback);
 	else
@@ -375,7 +357,7 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table)
 static u32 flow_hash(const struct sw_flow_key *key, int key_start,
 		     int key_end)
 {
-	u32 *hash_key = (u32 *)((u8 *)key + key_start);
+	const u32 *hash_key = (const u32 *)((const u8 *)key + key_start);
 	int hash_u32s = (key_end - key_start) >> 2;
 
 	/* Make sure number of hash bytes are multiple of u32. */
@@ -397,8 +379,8 @@ static bool cmp_key(const struct sw_flow_key *key1,
 		    const struct sw_flow_key *key2,
 		    int key_start, int key_end)
 {
-	const long *cp1 = (long *)((u8 *)key1 + key_start);
-	const long *cp2 = (long *)((u8 *)key2 + key_start);
+	const long *cp1 = (const long *)((const u8 *)key1 + key_start);
+	const long *cp2 = (const long *)((const u8 *)key2 + key_start);
 	long diffs = 0;
 	int i;
 
@@ -474,6 +456,22 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
 	return ovs_flow_tbl_lookup_stats(tbl, key, &n_mask_hit);
 }
 
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+					  struct sw_flow_match *match)
+{
+	struct table_instance *ti = rcu_dereference_ovsl(tbl->ti);
+	struct sw_flow_mask *mask;
+	struct sw_flow *flow;
+
+	/* Always called under ovs-mutex. */
+	list_for_each_entry(mask, &tbl->mask_list, list) {
+		flow = masked_flow_lookup(ti, match->key, mask);
+		if (flow && ovs_flow_cmp_unmasked_key(flow, match))  /* Found */
+			return flow;
+	}
+	return NULL;
+}
+
 int ovs_flow_tbl_num_masks(const struct flow_table *table)
 {
 	struct sw_flow_mask *mask;
@@ -490,6 +488,25 @@ static struct table_instance *table_instance_expand(struct table_instance *ti)
 	return table_instance_rehash(ti, ti->n_buckets * 2);
 }
 
+/* Remove 'mask' from the mask list, if it is not needed any more. */
+static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask)
+{
+	if (mask) {
+		/* ovs-lock is required to protect mask-refcount and
+		 * mask list.
+		 */
+		ASSERT_OVSL();
+		BUG_ON(!mask->ref_count);
+		mask->ref_count--;
+
+		if (!mask->ref_count) {
+			list_del_rcu(&mask->list);
+			kfree_rcu(mask, rcu);
+		}
+	}
+}
+
+/* Must be called with OVS mutex held. */
 void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
 {
 	struct table_instance *ti = ovsl_dereference(table->ti);
@@ -497,6 +514,11 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
 	BUG_ON(table->count == 0);
 	hlist_del_rcu(&flow->hash_node[ti->node_ver]);
 	table->count--;
+
+	/* RCU delete the mask. 'flow->mask' is not NULLed, as it should be
+	 * accessible as long as the RCU read lock is held.
+	 */
+	flow_mask_remove(table, flow->mask);
 }
 
 static struct sw_flow_mask *mask_alloc(void)
@@ -513,8 +535,8 @@ static struct sw_flow_mask *mask_alloc(void)
 static bool mask_equal(const struct sw_flow_mask *a,
 		       const struct sw_flow_mask *b)
 {
-	u8 *a_ = (u8 *)&a->key + a->range.start;
-	u8 *b_ = (u8 *)&b->key + b->range.start;
+	const u8 *a_ = (const u8 *)&a->key + a->range.start;
+	const u8 *b_ = (const u8 *)&b->key + b->range.start;
 
 	return  (a->range.end == b->range.end)
 		&& (a->range.start == b->range.start)
@@ -559,6 +581,7 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow,
 	return 0;
 }
 
+/* Must be called with OVS mutex held. */
 int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow,
 			struct sw_flow_mask *mask)
 {
@@ -597,16 +620,28 @@ int ovs_flow_init(void)
 	BUILD_BUG_ON(__alignof__(struct sw_flow_key) % __alignof__(long));
 	BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long));
 
-	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow), 0,
-					0, NULL);
+	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
+				       + (num_possible_nodes()
+					  * sizeof(struct flow_stats *)),
+				       0, 0, NULL);
 	if (flow_cache == NULL)
 		return -ENOMEM;
 
+	flow_stats_cache
+		= kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats),
+				    0, SLAB_HWCACHE_ALIGN, NULL);
+	if (flow_stats_cache == NULL) {
+		kmem_cache_destroy(flow_cache);
+		flow_cache = NULL;
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
 /* Uninitializes the flow module. */
 void ovs_flow_exit(void)
 {
+	kmem_cache_destroy(flow_stats_cache);
 	kmem_cache_destroy(flow_cache);
 }
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index baaeb101924..5918bff7f3f 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -52,10 +52,12 @@ struct flow_table {
 	unsigned int count;
 };
 
+extern struct kmem_cache *flow_stats_cache;
+
 int ovs_flow_init(void);
 void ovs_flow_exit(void);
 
-struct sw_flow *ovs_flow_alloc(bool percpu_stats);
+struct sw_flow *ovs_flow_alloc(void);
 void ovs_flow_free(struct sw_flow *, bool deferred);
 
 int ovs_flow_tbl_init(struct flow_table *);
@@ -74,7 +76,8 @@ struct sw_flow *ovs_flow_tbl_lookup_stats(struct flow_table *,
 				    u32 *n_mask_hit);
 struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *,
 				    const struct sw_flow_key *);
-
+struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
+					  struct sw_flow_match *match);
 bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow,
 			       struct sw_flow_match *match);
 
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index ebb6e244255..f49148a07da 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -110,6 +110,22 @@ static int gre_rcv(struct sk_buff *skb,
 	return PACKET_RCVD;
 }
 
+/* Called with rcu_read_lock and BH disabled. */
+static int gre_err(struct sk_buff *skb, u32 info,
+		   const struct tnl_ptk_info *tpi)
+{
+	struct ovs_net *ovs_net;
+	struct vport *vport;
+
+	ovs_net = net_generic(dev_net(skb->dev), ovs_net_id);
+	vport = rcu_dereference(ovs_net->vport_net.gre_vport);
+
+	if (unlikely(!vport))
+		return PACKET_REJECT;
+	else
+		return PACKET_RCVD;
+}
+
 static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 {
 	struct net *net = ovs_dp_get_net(vport->dp);
@@ -172,7 +188,7 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
 	df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
 		htons(IP_DF) : 0;
 
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	return iptunnel_xmit(skb->sk, rt, skb, fl.saddr,
 			     OVS_CB(skb)->tun_key->ipv4_dst, IPPROTO_GRE,
@@ -186,6 +202,7 @@ error:
 
 static struct gre_cisco_protocol gre_protocol = {
 	.handler        = gre_rcv,
+	.err_handler    = gre_err,
 	.priority       = 1,
 };
 
@@ -256,7 +273,7 @@ static void gre_tnl_destroy(struct vport *vport)
 
 	ovs_net = net_generic(net, ovs_net_id);
 
-	rcu_assign_pointer(ovs_net->vport_net.gre_vport, NULL);
+	RCU_INIT_POINTER(ovs_net->vport_net.gre_vport, NULL);
 	ovs_vport_deferred_free(vport);
 	gre_exit();
 }
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 729c68763fe..789af9280e7 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -130,7 +130,7 @@ static void do_setup(struct net_device *netdev)
 	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	netdev->destructor = internal_dev_destructor;
-	SET_ETHTOOL_OPS(netdev, &internal_dev_ethtool_ops);
+	netdev->ethtool_ops = &internal_dev_ethtool_ops;
 	netdev->tx_queue_len = 0;
 
 	netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index e797a50ac2b..0edbd95c60e 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -122,7 +122,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
 	vxlan_port = vxlan_vport(vport);
 	strncpy(vxlan_port->name, parms->name, IFNAMSIZ);
 
-	vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, false);
+	vs = vxlan_sock_add(net, htons(dst_port), vxlan_rcv, vport, true, 0);
 	if (IS_ERR(vs)) {
 		ovs_vport_free(vport);
 		return (void *)vs;
@@ -170,7 +170,7 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 	df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
 		htons(IP_DF) : 0;
 
-	skb->local_df = 1;
+	skb->ignore_df = 1;
 
 	inet_get_local_port_range(net, &port_min, &port_max);
 	src_port = vxlan_src_port(port_min, port_max, skb);
@@ -180,7 +180,8 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
 			     OVS_CB(skb)->tun_key->ipv4_tos,
 			     OVS_CB(skb)->tun_key->ipv4_ttl, df,
 			     src_port, dst_port,
-			     htonl(be64_to_cpu(OVS_CB(skb)->tun_key->tun_id) << 8));
+			     htonl(be64_to_cpu(OVS_CB(skb)->tun_key->tun_id) << 8),
+			     false);
 	if (err < 0)
 		ip_rt_put(rt);
 error:
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index d7e50a17396..8d721e62f38 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -172,7 +172,7 @@ void ovs_vport_deferred_free(struct vport *vport);
  */
 static inline void *vport_priv(const struct vport *vport)
 {
-	return (u8 *)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN);
+	return (u8 *)(uintptr_t)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN);
 }
 
 /**
@@ -185,9 +185,9 @@ static inline void *vport_priv(const struct vport *vport)
  * the result of a hash table lookup.  @priv must point to the start of the
  * private data area.
  */
-static inline struct vport *vport_from_priv(const void *priv)
+static inline struct vport *vport_from_priv(void *priv)
 {
-	return (struct vport *)(priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
+	return (struct vport *)((u8 *)priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
 }
 
 void ovs_vport_receive(struct vport *, struct sk_buff *,
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 37be6e226d1..1dde91e3dc7 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -298,7 +298,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context)
 		rds_ib_stats_inc(s_ib_tx_cq_event);
 
 		if (wc.wr_id == RDS_IB_ACK_WR_ID) {
-			if (ic->i_ack_queued + HZ/2 < jiffies)
+			if (time_after(jiffies, ic->i_ack_queued + HZ/2))
 				rds_ib_stats_inc(s_ib_tx_stalled);
 			rds_ib_ack_send_complete(ic);
 			continue;
@@ -315,7 +315,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context)
 
 			rm = rds_ib_send_unmap_op(ic, send, wc.status);
 
-			if (send->s_queued + HZ/2 < jiffies)
+			if (time_after(jiffies, send->s_queued + HZ/2))
 				rds_ib_stats_inc(s_ib_tx_stalled);
 
 			if (send->s_op) {
diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c
index e40c3c5db2c..9105ea03aec 100644
--- a/net/rds/iw_send.c
+++ b/net/rds/iw_send.c
@@ -232,7 +232,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context)
 		}
 
 		if (wc.wr_id == RDS_IW_ACK_WR_ID) {
-			if (ic->i_ack_queued + HZ/2 < jiffies)
+			if (time_after(jiffies, ic->i_ack_queued + HZ/2))
 				rds_iw_stats_inc(s_iw_tx_stalled);
 			rds_iw_ack_send_complete(ic);
 			continue;
@@ -267,7 +267,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context)
 
 			send->s_wr.opcode = 0xdead;
 			send->s_wr.num_sge = 1;
-			if (send->s_queued + HZ/2 < jiffies)
+			if (time_after(jiffies, send->s_queued + HZ/2))
 				rds_iw_stats_inc(s_iw_tx_stalled);
 
 			/* If a RDMA operation produced an error, signal this right
diff --git a/net/rds/iw_sysctl.c b/net/rds/iw_sysctl.c
index 89c91515ed0..139239d2cb2 100644
--- a/net/rds/iw_sysctl.c
+++ b/net/rds/iw_sysctl.c
@@ -111,8 +111,7 @@ static struct ctl_table rds_iw_sysctl_table[] = {
 
 void rds_iw_sysctl_exit(void)
 {
-	if (rds_iw_sysctl_hdr)
-		unregister_net_sysctl_table(rds_iw_sysctl_hdr);
+	unregister_net_sysctl_table(rds_iw_sysctl_hdr);
 }
 
 int rds_iw_sysctl_init(void)
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index c2be901d19e..6cd9d1deafc 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -168,7 +168,7 @@ static int rds_rdma_listen_init(void)
 		return ret;
 	}
 
-	sin.sin_family = AF_INET,
+	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY);
 	sin.sin_port = (__force u16)htons(RDS_PORT);
 
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index b5cb2aa08f3..c3b0cd43eb5 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -94,8 +94,7 @@ static struct ctl_table rds_sysctl_rds_table[] = {
 
 void rds_sysctl_exit(void)
 {
-	if (rds_sysctl_reg_table)
-		unregister_net_sysctl_table(rds_sysctl_reg_table);
+	unregister_net_sysctl_table(rds_sysctl_reg_table);
 }
 
 int rds_sysctl_init(void)
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 4e638f85118..23ab4dcd1d9 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -153,7 +153,7 @@ int rds_tcp_listen_init(void)
 	sock->sk->sk_data_ready = rds_tcp_listen_data_ready;
 	write_unlock_bh(&sock->sk->sk_callback_lock);
 
-	sin.sin_family = PF_INET,
+	sin.sin_family = PF_INET;
 	sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY);
 	sin.sin_port = (__force u16)htons(RDS_TCP_PORT);
 
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index bd2a5b90400..14c98e48f26 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -36,8 +36,6 @@ struct rfkill_gpio_data {
 	struct gpio_desc	*shutdown_gpio;
 
 	struct rfkill		*rfkill_dev;
-	char			*reset_name;
-	char			*shutdown_name;
 	struct clk		*clk;
 
 	bool			clk_enabled;
@@ -47,17 +45,14 @@ static int rfkill_gpio_set_power(void *data, bool blocked)
 {
 	struct rfkill_gpio_data *rfkill = data;
 
-	if (blocked) {
-		gpiod_set_value(rfkill->shutdown_gpio, 0);
-		gpiod_set_value(rfkill->reset_gpio, 0);
-		if (!IS_ERR(rfkill->clk) && rfkill->clk_enabled)
-			clk_disable(rfkill->clk);
-	} else {
-		if (!IS_ERR(rfkill->clk) && !rfkill->clk_enabled)
-			clk_enable(rfkill->clk);
-		gpiod_set_value(rfkill->reset_gpio, 1);
-		gpiod_set_value(rfkill->shutdown_gpio, 1);
-	}
+	if (!blocked && !IS_ERR(rfkill->clk) && !rfkill->clk_enabled)
+		clk_enable(rfkill->clk);
+
+	gpiod_set_value_cansleep(rfkill->shutdown_gpio, !blocked);
+	gpiod_set_value_cansleep(rfkill->reset_gpio, !blocked);
+
+	if (blocked && !IS_ERR(rfkill->clk) && rfkill->clk_enabled)
+		clk_disable(rfkill->clk);
 
 	rfkill->clk_enabled = blocked;
 
@@ -87,10 +82,8 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 {
 	struct rfkill_gpio_platform_data *pdata = pdev->dev.platform_data;
 	struct rfkill_gpio_data *rfkill;
-	const char *clk_name = NULL;
 	struct gpio_desc *gpio;
 	int ret;
-	int len;
 
 	rfkill = devm_kzalloc(&pdev->dev, sizeof(*rfkill), GFP_KERNEL);
 	if (!rfkill)
@@ -101,28 +94,15 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 	} else if (pdata) {
-		clk_name = pdata->power_clk_name;
 		rfkill->name = pdata->name;
 		rfkill->type = pdata->type;
 	} else {
 		return -ENODEV;
 	}
 
-	len = strlen(rfkill->name);
-	rfkill->reset_name = devm_kzalloc(&pdev->dev, len + 7, GFP_KERNEL);
-	if (!rfkill->reset_name)
-		return -ENOMEM;
-
-	rfkill->shutdown_name = devm_kzalloc(&pdev->dev, len + 10, GFP_KERNEL);
-	if (!rfkill->shutdown_name)
-		return -ENOMEM;
+	rfkill->clk = devm_clk_get(&pdev->dev, NULL);
 
-	snprintf(rfkill->reset_name, len + 6 , "%s_reset", rfkill->name);
-	snprintf(rfkill->shutdown_name, len + 9, "%s_shutdown", rfkill->name);
-
-	rfkill->clk = devm_clk_get(&pdev->dev, clk_name);
-
-	gpio = devm_gpiod_get_index(&pdev->dev, rfkill->reset_name, 0);
+	gpio = devm_gpiod_get_index(&pdev->dev, "reset", 0);
 	if (!IS_ERR(gpio)) {
 		ret = gpiod_direction_output(gpio, 0);
 		if (ret)
@@ -130,7 +110,7 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 		rfkill->reset_gpio = gpio;
 	}
 
-	gpio = devm_gpiod_get_index(&pdev->dev, rfkill->shutdown_name, 1);
+	gpio = devm_gpiod_get_index(&pdev->dev, "shutdown", 1);
 	if (!IS_ERR(gpio)) {
 		ret = gpiod_direction_output(gpio, 0);
 		if (ret)
@@ -146,14 +126,6 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	if (pdata && pdata->gpio_runtime_setup) {
-		ret = pdata->gpio_runtime_setup(pdev);
-		if (ret) {
-			dev_err(&pdev->dev, "can't set up gpio\n");
-			return ret;
-		}
-	}
-
 	rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev,
 					  rfkill->type, &rfkill_gpio_ops,
 					  rfkill);
@@ -174,20 +146,23 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 static int rfkill_gpio_remove(struct platform_device *pdev)
 {
 	struct rfkill_gpio_data *rfkill = platform_get_drvdata(pdev);
-	struct rfkill_gpio_platform_data *pdata = pdev->dev.platform_data;
 
-	if (pdata && pdata->gpio_runtime_close)
-		pdata->gpio_runtime_close(pdev);
 	rfkill_unregister(rfkill->rfkill_dev);
 	rfkill_destroy(rfkill->rfkill_dev);
 
 	return 0;
 }
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id rfkill_acpi_match[] = {
+	{ "BCM2E1A", RFKILL_TYPE_BLUETOOTH },
+	{ "BCM2E39", RFKILL_TYPE_BLUETOOTH },
+	{ "BCM2E3D", RFKILL_TYPE_BLUETOOTH },
 	{ "BCM4752", RFKILL_TYPE_GPS },
+	{ "LNV4752", RFKILL_TYPE_GPS },
 	{ },
 };
+#endif
 
 static struct platform_driver rfkill_gpio_driver = {
 	.probe = rfkill_gpio_probe,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index bdbdb1a7920..45527e6b52d 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -134,7 +134,8 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n)
 	int err;
 	int tp_created = 0;
 
-	if ((n->nlmsg_type != RTM_GETTFILTER) && !netlink_capable(skb, CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTFILTER) &&
+	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
@@ -317,7 +318,8 @@ replay:
 		}
 	}
 
-	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh);
+	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
+			      n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE);
 	if (err == 0) {
 		if (tp_created) {
 			spin_lock_bh(root_lock);
@@ -504,7 +506,7 @@ void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts)
 EXPORT_SYMBOL(tcf_exts_destroy);
 
 int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
-		  struct nlattr *rate_tlv, struct tcf_exts *exts)
+		  struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	{
@@ -513,7 +515,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 		INIT_LIST_HEAD(&exts->actions);
 		if (exts->police && tb[exts->police]) {
 			act = tcf_action_init_1(net, tb[exts->police], rate_tlv,
-						"police", TCA_ACT_NOREPLACE,
+						"police", ovr,
 						TCA_ACT_BIND);
 			if (IS_ERR(act))
 				return PTR_ERR(act);
@@ -523,7 +525,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 		} else if (exts->action && tb[exts->action]) {
 			int err;
 			err = tcf_action_init(net, tb[exts->action], rate_tlv,
-					      NULL, TCA_ACT_NOREPLACE,
+					      NULL, ovr,
 					      TCA_ACT_BIND, &exts->actions);
 			if (err)
 				return err;
@@ -543,14 +545,12 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
 		     struct tcf_exts *src)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	if (!list_empty(&src->actions)) {
-		LIST_HEAD(tmp);
-		tcf_tree_lock(tp);
-		list_splice_init(&dst->actions, &tmp);
-		list_splice(&src->actions, &dst->actions);
-		tcf_tree_unlock(tp);
-		tcf_action_destroy(&tmp, TCA_ACT_UNBIND);
-	}
+	LIST_HEAD(tmp);
+	tcf_tree_lock(tp);
+	list_splice_init(&dst->actions, &tmp);
+	list_splice(&src->actions, &dst->actions);
+	tcf_tree_unlock(tp);
+	tcf_action_destroy(&tmp, TCA_ACT_UNBIND);
 #endif
 }
 EXPORT_SYMBOL(tcf_exts_change);
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index e98ca99c202..0ae1813e3e9 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -130,14 +130,14 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = {
 static int basic_set_parms(struct net *net, struct tcf_proto *tp,
 			   struct basic_filter *f, unsigned long base,
 			   struct nlattr **tb,
-			   struct nlattr *est)
+			   struct nlattr *est, bool ovr)
 {
 	int err;
 	struct tcf_exts e;
 	struct tcf_ematch_tree t;
 
 	tcf_exts_init(&e, TCA_BASIC_ACT, TCA_BASIC_POLICE);
-	err = tcf_exts_validate(net, tp, tb, est, &e);
+	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -161,7 +161,7 @@ errout:
 
 static int basic_change(struct net *net, struct sk_buff *in_skb,
 			struct tcf_proto *tp, unsigned long base, u32 handle,
-			struct nlattr **tca, unsigned long *arg)
+			struct nlattr **tca, unsigned long *arg, bool ovr)
 {
 	int err;
 	struct basic_head *head = tp->root;
@@ -179,7 +179,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 	if (f != NULL) {
 		if (handle && f->handle != handle)
 			return -EINVAL;
-		return basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE]);
+		return basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr);
 	}
 
 	err = -ENOBUFS;
@@ -206,7 +206,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 		f->handle = head->hgenerator;
 	}
 
-	err = basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE]);
+	err = basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 8e3cf49118e..13f64df2c71 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -156,11 +156,11 @@ static void cls_bpf_put(struct tcf_proto *tp, unsigned long f)
 static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 				   struct cls_bpf_prog *prog,
 				   unsigned long base, struct nlattr **tb,
-				   struct nlattr *est)
+				   struct nlattr *est, bool ovr)
 {
 	struct sock_filter *bpf_ops, *bpf_old;
 	struct tcf_exts exts;
-	struct sock_fprog tmp;
+	struct sock_fprog_kern tmp;
 	struct sk_filter *fp, *fp_old;
 	u16 bpf_size, bpf_len;
 	u32 classid;
@@ -170,7 +170,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 		return -EINVAL;
 
 	tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE);
-	ret = tcf_exts_validate(net, tp, tb, est, &exts);
+	ret = tcf_exts_validate(net, tp, tb, est, &exts, ovr);
 	if (ret < 0)
 		return ret;
 
@@ -191,7 +191,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 	memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
 
 	tmp.len = bpf_len;
-	tmp.filter = (struct sock_filter __user *) bpf_ops;
+	tmp.filter = bpf_ops;
 
 	ret = sk_unattached_filter_create(&fp, &tmp);
 	if (ret)
@@ -242,7 +242,7 @@ static u32 cls_bpf_grab_new_handle(struct tcf_proto *tp,
 static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 			  struct tcf_proto *tp, unsigned long base,
 			  u32 handle, struct nlattr **tca,
-			  unsigned long *arg)
+			  unsigned long *arg, bool ovr)
 {
 	struct cls_bpf_head *head = tp->root;
 	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) *arg;
@@ -260,7 +260,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		if (handle && prog->handle != handle)
 			return -EINVAL;
 		return cls_bpf_modify_existing(net, tp, prog, base, tb,
-					       tca[TCA_RATE]);
+					       tca[TCA_RATE], ovr);
 	}
 
 	prog = kzalloc(sizeof(*prog), GFP_KERNEL);
@@ -277,7 +277,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		goto errout;
 	}
 
-	ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE]);
+	ret = cls_bpf_modify_existing(net, tp, prog, base, tb, tca[TCA_RATE], ovr);
 	if (ret < 0)
 		goto errout;
 
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 8e2158ab551..cacf01bd04f 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -83,7 +83,7 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
 static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 			     struct tcf_proto *tp, unsigned long base,
 			     u32 handle, struct nlattr **tca,
-			     unsigned long *arg)
+			     unsigned long *arg, bool ovr)
 {
 	struct nlattr *tb[TCA_CGROUP_MAX + 1];
 	struct cls_cgroup_head *head = tp->root;
@@ -119,7 +119,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 		return err;
 
 	tcf_exts_init(&e, TCA_CGROUP_ACT, TCA_CGROUP_POLICE);
-	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e);
+	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 257029c5433..35be16f7c19 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -349,7 +349,7 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = {
 static int flow_change(struct net *net, struct sk_buff *in_skb,
 		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle, struct nlattr **tca,
-		       unsigned long *arg)
+		       unsigned long *arg, bool ovr)
 {
 	struct flow_head *head = tp->root;
 	struct flow_filter *f;
@@ -393,7 +393,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 	}
 
 	tcf_exts_init(&e, TCA_FLOW_ACT, TCA_FLOW_POLICE);
-	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e);
+	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 63a3ce75c02..861b03ccfed 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -169,7 +169,7 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = {
 
 static int
 fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f,
-	struct nlattr **tb, struct nlattr **tca, unsigned long base)
+	struct nlattr **tb, struct nlattr **tca, unsigned long base, bool ovr)
 {
 	struct fw_head *head = tp->root;
 	struct tcf_exts e;
@@ -177,7 +177,7 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f,
 	int err;
 
 	tcf_exts_init(&e, TCA_FW_ACT, TCA_FW_POLICE);
-	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e);
+	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -218,7 +218,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 		     struct tcf_proto *tp, unsigned long base,
 		     u32 handle,
 		     struct nlattr **tca,
-		     unsigned long *arg)
+		     unsigned long *arg, bool ovr)
 {
 	struct fw_head *head = tp->root;
 	struct fw_filter *f = (struct fw_filter *) *arg;
@@ -236,7 +236,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	if (f != NULL) {
 		if (f->id != handle && handle)
 			return -EINVAL;
-		return fw_change_attrs(net, tp, f, tb, tca, base);
+		return fw_change_attrs(net, tp, f, tb, tca, base, ovr);
 	}
 
 	if (!handle)
@@ -264,7 +264,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 	tcf_exts_init(&f->exts, TCA_FW_ACT, TCA_FW_POLICE);
 	f->id = handle;
 
-	err = fw_change_attrs(net, tp, f, tb, tca, base);
+	err = fw_change_attrs(net, tp, f, tb, tca, base, ovr);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 1ad3068f2ce..dd9fc2523c7 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -333,7 +333,8 @@ static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = {
 static int route4_set_parms(struct net *net, struct tcf_proto *tp,
 			    unsigned long base, struct route4_filter *f,
 			    u32 handle, struct route4_head *head,
-			    struct nlattr **tb, struct nlattr *est, int new)
+			    struct nlattr **tb, struct nlattr *est, int new,
+			    bool ovr)
 {
 	int err;
 	u32 id = 0, to = 0, nhandle = 0x8000;
@@ -343,7 +344,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
 	struct tcf_exts e;
 
 	tcf_exts_init(&e, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE);
-	err = tcf_exts_validate(net, tp, tb, est, &e);
+	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -428,7 +429,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle,
 		       struct nlattr **tca,
-		       unsigned long *arg)
+		       unsigned long *arg, bool ovr)
 {
 	struct route4_head *head = tp->root;
 	struct route4_filter *f, *f1, **fp;
@@ -455,7 +456,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 			old_handle = f->handle;
 
 		err = route4_set_parms(net, tp, base, f, handle, head, tb,
-			tca[TCA_RATE], 0);
+			tca[TCA_RATE], 0, ovr);
 		if (err < 0)
 			return err;
 
@@ -479,7 +480,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 
 	tcf_exts_init(&f->exts, TCA_ROUTE4_ACT, TCA_ROUTE4_POLICE);
 	err = route4_set_parms(net, tp, base, f, handle, head, tb,
-		tca[TCA_RATE], 1);
+		tca[TCA_RATE], 1, ovr);
 	if (err < 0)
 		goto errout;
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 19f8e5dfa8b..1020e233a5d 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -415,7 +415,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
 		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle,
 		       struct nlattr **tca,
-		       unsigned long *arg)
+		       unsigned long *arg, bool ovr)
 {
 	struct rsvp_head *data = tp->root;
 	struct rsvp_filter *f, **fp;
@@ -436,7 +436,7 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb,
 		return err;
 
 	tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE);
-	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e);
+	err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr);
 	if (err < 0)
 		return err;
 
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index f435a88d899..c721cd4a469 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -198,7 +198,7 @@ static int
 tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		  u32 handle, struct tcindex_data *p,
 		  struct tcindex_filter_result *r, struct nlattr **tb,
-		 struct nlattr *est)
+		  struct nlattr *est, bool ovr)
 {
 	int err, balloc = 0;
 	struct tcindex_filter_result new_filter_result, *old_r = r;
@@ -208,7 +208,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	struct tcf_exts e;
 
 	tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
-	err = tcf_exts_validate(net, tp, tb, est, &e);
+	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -341,7 +341,7 @@ errout:
 static int
 tcindex_change(struct net *net, struct sk_buff *in_skb,
 	       struct tcf_proto *tp, unsigned long base, u32 handle,
-	       struct nlattr **tca, unsigned long *arg)
+	       struct nlattr **tca, unsigned long *arg, bool ovr)
 {
 	struct nlattr *opt = tca[TCA_OPTIONS];
 	struct nlattr *tb[TCA_TCINDEX_MAX + 1];
@@ -361,7 +361,7 @@ tcindex_change(struct net *net, struct sk_buff *in_skb,
 		return err;
 
 	return tcindex_set_parms(net, tp, base, handle, p, r, tb,
-				 tca[TCA_RATE]);
+				 tca[TCA_RATE], ovr);
 }
 
 
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 84c28daff84..70c0be8d012 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -38,6 +38,7 @@
 #include <linux/errno.h>
 #include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
+#include <linux/bitmap.h>
 #include <net/netlink.h>
 #include <net/act_api.h>
 #include <net/pkt_cls.h>
@@ -460,17 +461,25 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg)
 	return 0;
 }
 
+#define NR_U32_NODE (1<<12)
 static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle)
 {
 	struct tc_u_knode *n;
-	unsigned int i = 0x7FF;
+	unsigned long i;
+	unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long),
+					GFP_KERNEL);
+	if (!bitmap)
+		return handle | 0xFFF;
 
 	for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next)
-		if (i < TC_U32_NODE(n->handle))
-			i = TC_U32_NODE(n->handle);
-	i++;
+		set_bit(TC_U32_NODE(n->handle), bitmap);
 
-	return handle | (i > 0xFFF ? 0xFFF : i);
+	i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800);
+	if (i >= NR_U32_NODE)
+		i = find_next_zero_bit(bitmap, NR_U32_NODE, 1);
+
+	kfree(bitmap);
+	return handle | (i >= NR_U32_NODE ? 0xFFF : i);
 }
 
 static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
@@ -486,13 +495,13 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
 static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 			 unsigned long base, struct tc_u_hnode *ht,
 			 struct tc_u_knode *n, struct nlattr **tb,
-			 struct nlattr *est)
+			 struct nlattr *est, bool ovr)
 {
 	int err;
 	struct tcf_exts e;
 
 	tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE);
-	err = tcf_exts_validate(net, tp, tb, est, &e);
+	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
 	if (err < 0)
 		return err;
 
@@ -545,7 +554,7 @@ errout:
 static int u32_change(struct net *net, struct sk_buff *in_skb,
 		      struct tcf_proto *tp, unsigned long base, u32 handle,
 		      struct nlattr **tca,
-		      unsigned long *arg)
+		      unsigned long *arg, bool ovr)
 {
 	struct tc_u_common *tp_c = tp->data;
 	struct tc_u_hnode *ht;
@@ -569,7 +578,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 
 		return u32_set_parms(net, tp, base, n->ht_up, n, tb,
-				     tca[TCA_RATE]);
+				     tca[TCA_RATE], ovr);
 	}
 
 	if (tb[TCA_U32_DIVISOR]) {
@@ -656,7 +665,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 #endif
 
-	err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE]);
+	err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr);
 	if (err == 0) {
 		struct tc_u_knode **ins;
 		for (ins = &ht->ht[TC_U32_HASH(handle)]; *ins; ins = &(*ins)->next)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 400769014bb..58bed7599db 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -563,7 +563,7 @@ out:
 }
 EXPORT_SYMBOL(__qdisc_calculate_pkt_len);
 
-void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc)
+void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc)
 {
 	if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
 		pr_warn("%s: %s qdisc %X: is non-work-conserving?\n",
@@ -1084,7 +1084,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 	struct Qdisc *p = NULL;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETQDISC) && !netlink_capable(skb, CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETQDISC) &&
+	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
@@ -1151,7 +1152,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n)
 	struct Qdisc *q, *p;
 	int err;
 
-	if (!netlink_capable(skb, CAP_NET_ADMIN))
+	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
@@ -1490,7 +1491,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n)
 	u32 qid;
 	int err;
 
-	if ((n->nlmsg_type != RTM_GETTCLASS) && !netlink_capable(skb, CAP_NET_ADMIN))
+	if ((n->nlmsg_type != RTM_GETTCLASS) &&
+	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL);
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 2aee02802c2..ed30e436128 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -391,12 +391,7 @@ static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = {
 
 static void choke_free(void *addr)
 {
-	if (addr) {
-		if (is_vmalloc_addr(addr))
-			vfree(addr);
-		else
-			kfree(addr);
-	}
+	kvfree(addr);
 }
 
 static int choke_change(struct Qdisc *sch, struct nlattr *opt)
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 8302717ea30..7bbbfe11219 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -391,8 +391,10 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
 	while (1) {
 		cl = list_first_entry(&q->active, struct drr_class, alist);
 		skb = cl->qdisc->ops->peek(cl->qdisc);
-		if (skb == NULL)
+		if (skb == NULL) {
+			qdisc_warn_nonwc(__func__, cl->qdisc);
 			goto out;
+		}
 
 		len = qdisc_pkt_len(skb);
 		if (len <= cl->deficit) {
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 23c682b42f9..ba32c2b005d 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -591,10 +591,7 @@ static void *fq_alloc_node(size_t sz, int node)
 
 static void fq_free(void *addr)
 {
-	if (addr && is_vmalloc_addr(addr))
-		vfree(addr);
-	else
-		kfree(addr);
+	kvfree(addr);
 }
 
 static int fq_resize(struct Qdisc *sch, u32 log)
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 0bf432c782c..063b726bf1f 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -365,12 +365,7 @@ static void *fq_codel_zalloc(size_t sz)
 
 static void fq_codel_free(void *addr)
 {
-	if (addr) {
-		if (is_vmalloc_addr(addr))
-			vfree(addr);
-		else
-			kfree(addr);
-	}
+	kvfree(addr);
 }
 
 static void fq_codel_destroy(struct Qdisc *sch)
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 6e957c3b985..d85b6812a7d 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -414,7 +414,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		}
 		bucket->deficit = weight * q->quantum;
 	}
-	if (++sch->q.qlen < sch->limit)
+	if (++sch->q.qlen <= sch->limit)
 		return NET_XMIT_SUCCESS;
 
 	q->drop_overlimit++;
@@ -494,12 +494,7 @@ static void *hhf_zalloc(size_t sz)
 
 static void hhf_free(void *addr)
 {
-	if (addr) {
-		if (is_vmalloc_addr(addr))
-			vfree(addr);
-		else
-			kfree(addr);
-	}
+	kvfree(addr);
 }
 
 static void hhf_destroy(struct Qdisc *sch)
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index f1669a00f57..111d70fddae 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -648,12 +648,7 @@ static void netem_reset(struct Qdisc *sch)
 
 static void dist_free(struct disttable *d)
 {
-	if (d) {
-		if (is_vmalloc_addr(d))
-			vfree(d);
-		else
-			kfree(d);
-	}
+	kvfree(d);
 }
 
 /*
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 87317ff0b4e..1af2f73906d 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -716,12 +716,7 @@ static void *sfq_alloc(size_t sz)
 
 static void sfq_free(void *addr)
 {
-	if (addr) {
-		if (is_vmalloc_addr(addr))
-			vfree(addr);
-		else
-			kfree(addr);
-	}
+	kvfree(addr);
 }
 
 static void sfq_destroy(struct Qdisc *sch)
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 39579c3e0d1..06a9ee6b2d3 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -55,6 +55,7 @@
 #include <net/sctp/sm.h>
 
 /* Forward declarations for internal functions. */
+static void sctp_select_active_and_retran_path(struct sctp_association *asoc);
 static void sctp_assoc_bh_rcv(struct work_struct *work);
 static void sctp_assoc_free_asconf_acks(struct sctp_association *asoc);
 static void sctp_assoc_free_asconf_queue(struct sctp_association *asoc);
@@ -330,7 +331,7 @@ void sctp_association_free(struct sctp_association *asoc)
 	/* Only real associations count against the endpoint, so
 	 * don't bother for if this is a temporary association.
 	 */
-	if (!asoc->temp) {
+	if (!list_empty(&asoc->asocs)) {
 		list_del(&asoc->asocs);
 
 		/* Decrement the backlog value for a TCP-style listening
@@ -774,9 +775,6 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 				  sctp_transport_cmd_t command,
 				  sctp_sn_error_t error)
 {
-	struct sctp_transport *t = NULL;
-	struct sctp_transport *first;
-	struct sctp_transport *second;
 	struct sctp_ulpevent *event;
 	struct sockaddr_storage addr;
 	int spc_state = 0;
@@ -829,13 +827,14 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 		return;
 	}
 
-	/* Generate and send a SCTP_PEER_ADDR_CHANGE notification to the
-	 * user.
+	/* Generate and send a SCTP_PEER_ADDR_CHANGE notification
+	 * to the user.
 	 */
 	if (ulp_notify) {
 		memset(&addr, 0, sizeof(struct sockaddr_storage));
 		memcpy(&addr, &transport->ipaddr,
 		       transport->af_specific->sockaddr_len);
+
 		event = sctp_ulpevent_make_peer_addr_change(asoc, &addr,
 					0, spc_state, error, GFP_ATOMIC);
 		if (event)
@@ -843,60 +842,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
 	}
 
 	/* Select new active and retran paths. */
-
-	/* Look for the two most recently used active transports.
-	 *
-	 * This code produces the wrong ordering whenever jiffies
-	 * rolls over, but we still get usable transports, so we don't
-	 * worry about it.
-	 */
-	first = NULL; second = NULL;
-
-	list_for_each_entry(t, &asoc->peer.transport_addr_list,
-			transports) {
-
-		if ((t->state == SCTP_INACTIVE) ||
-		    (t->state == SCTP_UNCONFIRMED) ||
-		    (t->state == SCTP_PF))
-			continue;
-		if (!first || t->last_time_heard > first->last_time_heard) {
-			second = first;
-			first = t;
-		} else if (!second ||
-			   t->last_time_heard > second->last_time_heard)
-			second = t;
-	}
-
-	/* RFC 2960 6.4 Multi-Homed SCTP Endpoints
-	 *
-	 * By default, an endpoint should always transmit to the
-	 * primary path, unless the SCTP user explicitly specifies the
-	 * destination transport address (and possibly source
-	 * transport address) to use.
-	 *
-	 * [If the primary is active but not most recent, bump the most
-	 * recently used transport.]
-	 */
-	if (((asoc->peer.primary_path->state == SCTP_ACTIVE) ||
-	     (asoc->peer.primary_path->state == SCTP_UNKNOWN)) &&
-	    first != asoc->peer.primary_path) {
-		second = first;
-		first = asoc->peer.primary_path;
-	}
-
-	if (!second)
-		second = first;
-	/* If we failed to find a usable transport, just camp on the
-	 * primary, even if it is inactive.
-	 */
-	if (!first) {
-		first = asoc->peer.primary_path;
-		second = asoc->peer.primary_path;
-	}
-
-	/* Set the active and retran transports.  */
-	asoc->peer.active_path = first;
-	asoc->peer.retran_path = second;
+	sctp_select_active_and_retran_path(asoc);
 }
 
 /* Hold a reference to an association. */
@@ -1090,7 +1036,7 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
 		}
 
 		if (chunk->transport)
-			chunk->transport->last_time_heard = jiffies;
+			chunk->transport->last_time_heard = ktime_get();
 
 		/* Run through the state machine. */
 		error = sctp_do_sm(net, SCTP_EVENT_T_CHUNK, subtype,
@@ -1151,6 +1097,7 @@ void sctp_assoc_update(struct sctp_association *asoc,
 	asoc->c = new->c;
 	asoc->peer.rwnd = new->peer.rwnd;
 	asoc->peer.sack_needed = new->peer.sack_needed;
+	asoc->peer.auth_capable = new->peer.auth_capable;
 	asoc->peer.i = new->peer.i;
 	sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL,
 			 asoc->peer.i.initial_tsn, GFP_ATOMIC);
@@ -1278,13 +1225,41 @@ static u8 sctp_trans_score(const struct sctp_transport *trans)
 	return sctp_trans_state_to_prio_map[trans->state];
 }
 
+static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1,
+						   struct sctp_transport *trans2)
+{
+	if (trans1->error_count > trans2->error_count) {
+		return trans2;
+	} else if (trans1->error_count == trans2->error_count &&
+		   ktime_after(trans2->last_time_heard,
+			       trans1->last_time_heard)) {
+		return trans2;
+	} else {
+		return trans1;
+	}
+}
+
 static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr,
 						    struct sctp_transport *best)
 {
+	u8 score_curr, score_best;
+
 	if (best == NULL)
 		return curr;
 
-	return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best;
+	score_curr = sctp_trans_score(curr);
+	score_best = sctp_trans_score(best);
+
+	/* First, try a score-based selection if both transport states
+	 * differ. If we're in a tie, lets try to make a more clever
+	 * decision here based on error counts and last time heard.
+	 */
+	if (score_curr > score_best)
+		return curr;
+	else if (score_curr == score_best)
+		return sctp_trans_elect_tie(curr, best);
+	else
+		return best;
 }
 
 void sctp_assoc_update_retran_path(struct sctp_association *asoc)
@@ -1325,6 +1300,76 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
 		 __func__, asoc, &asoc->peer.retran_path->ipaddr.sa);
 }
 
+static void sctp_select_active_and_retran_path(struct sctp_association *asoc)
+{
+	struct sctp_transport *trans, *trans_pri = NULL, *trans_sec = NULL;
+	struct sctp_transport *trans_pf = NULL;
+
+	/* Look for the two most recently used active transports. */
+	list_for_each_entry(trans, &asoc->peer.transport_addr_list,
+			    transports) {
+		/* Skip uninteresting transports. */
+		if (trans->state == SCTP_INACTIVE ||
+		    trans->state == SCTP_UNCONFIRMED)
+			continue;
+		/* Keep track of the best PF transport from our
+		 * list in case we don't find an active one.
+		 */
+		if (trans->state == SCTP_PF) {
+			trans_pf = sctp_trans_elect_best(trans, trans_pf);
+			continue;
+		}
+		/* For active transports, pick the most recent ones. */
+		if (trans_pri == NULL ||
+		    ktime_after(trans->last_time_heard,
+				trans_pri->last_time_heard)) {
+			trans_sec = trans_pri;
+			trans_pri = trans;
+		} else if (trans_sec == NULL ||
+			   ktime_after(trans->last_time_heard,
+				       trans_sec->last_time_heard)) {
+			trans_sec = trans;
+		}
+	}
+
+	/* RFC 2960 6.4 Multi-Homed SCTP Endpoints
+	 *
+	 * By default, an endpoint should always transmit to the primary
+	 * path, unless the SCTP user explicitly specifies the
+	 * destination transport address (and possibly source transport
+	 * address) to use. [If the primary is active but not most recent,
+	 * bump the most recently used transport.]
+	 */
+	if ((asoc->peer.primary_path->state == SCTP_ACTIVE ||
+	     asoc->peer.primary_path->state == SCTP_UNKNOWN) &&
+	     asoc->peer.primary_path != trans_pri) {
+		trans_sec = trans_pri;
+		trans_pri = asoc->peer.primary_path;
+	}
+
+	/* We did not find anything useful for a possible retransmission
+	 * path; either primary path that we found is the the same as
+	 * the current one, or we didn't generally find an active one.
+	 */
+	if (trans_sec == NULL)
+		trans_sec = trans_pri;
+
+	/* If we failed to find a usable transport, just camp on the
+	 * primary or retran, even if they are inactive, if possible
+	 * pick a PF iff it's the better choice.
+	 */
+	if (trans_pri == NULL) {
+		trans_pri = sctp_trans_elect_best(asoc->peer.primary_path,
+						  asoc->peer.retran_path);
+		trans_pri = sctp_trans_elect_best(trans_pri, trans_pf);
+		trans_sec = asoc->peer.primary_path;
+	}
+
+	/* Set the active and retran transports. */
+	asoc->peer.active_path = trans_pri;
+	asoc->peer.retran_path = trans_sec;
+}
+
 struct sctp_transport *
 sctp_assoc_choose_alter_transport(struct sctp_association *asoc,
 				  struct sctp_transport *last_sent_to)
@@ -1547,7 +1592,7 @@ int sctp_assoc_lookup_laddr(struct sctp_association *asoc,
 /* Set an association id for a given association */
 int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp)
 {
-	bool preload = gfp & __GFP_WAIT;
+	bool preload = !!(gfp & __GFP_WAIT);
 	int ret;
 
 	/* If the id is already assigned, keep it. */
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 3d9f429858d..9da76ba4d10 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -481,7 +481,7 @@ normal:
 		}
 
 		if (chunk->transport)
-			chunk->transport->last_time_heard = jiffies;
+			chunk->transport->last_time_heard = ktime_get();
 
 		error = sctp_do_sm(net, SCTP_EVENT_T_CHUNK, subtype, state,
 				   ep, asoc, chunk, GFP_ATOMIC);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 2b1738ef939..1999592ba88 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -216,7 +216,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 	IP6_ECN_flow_xmit(sk, fl6->flowlabel);
 
 	if (!(transport->param_flags & SPP_PMTUD_ENABLE))
-		skb->local_df = 1;
+		skb->ignore_df = 1;
 
 	SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
 
@@ -943,7 +943,6 @@ static struct inet_protosw sctpv6_seqpacket_protosw = {
 	.protocol      = IPPROTO_SCTP,
 	.prot 	       = &sctpv6_prot,
 	.ops           = &inet6_seqpacket_ops,
-	.no_check      = 0,
 	.flags         = SCTP_PROTOSW_FLAG
 };
 static struct inet_protosw sctpv6_stream_protosw = {
@@ -951,7 +950,6 @@ static struct inet_protosw sctpv6_stream_protosw = {
 	.protocol      = IPPROTO_SCTP,
 	.prot 	       = &sctpv6_prot,
 	.ops           = &inet6_seqpacket_ops,
-	.no_check      = 0,
 	.flags         = SCTP_PROTOSW_FLAG,
 };
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 0f4d15fc262..01ab8e0723f 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -591,7 +591,7 @@ int sctp_packet_transmit(struct sctp_packet *packet)
 
 	pr_debug("***sctp_transmit_packet*** skb->len:%d\n", nskb->len);
 
-	nskb->local_df = packet->ipfragok;
+	nskb->ignore_df = packet->ipfragok;
 	tp->af_specific->sctp_xmit(nskb, tp);
 
 out:
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index 0947f1e15eb..34229ee7f37 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -78,7 +78,7 @@ static int sctp_snmp_seq_show(struct seq_file *seq, void *v)
 
 	for (i = 0; sctp_snmp_list[i].name != NULL; i++)
 		seq_printf(seq, "%-32s\t%ld\n", sctp_snmp_list[i].name,
-			   snmp_fold_field((void __percpu **)net->sctp.sctp_statistics,
+			   snmp_fold_field(net->sctp.sctp_statistics,
 				      sctp_snmp_list[i].entry));
 
 	return 0;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 44cbb54c857..6789d785e69 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1017,7 +1017,6 @@ static struct inet_protosw sctp_seqpacket_protosw = {
 	.protocol   = IPPROTO_SCTP,
 	.prot       = &sctp_prot,
 	.ops        = &inet_seqpacket_ops,
-	.no_check   = 0,
 	.flags      = SCTP_PROTOSW_FLAG
 };
 static struct inet_protosw sctp_stream_protosw = {
@@ -1025,7 +1024,6 @@ static struct inet_protosw sctp_stream_protosw = {
 	.protocol   = IPPROTO_SCTP,
 	.prot       = &sctp_prot,
 	.ops        = &inet_seqpacket_ops,
-	.no_check   = 0,
 	.flags      = SCTP_PROTOSW_FLAG
 };
 
@@ -1105,14 +1103,15 @@ int sctp_register_pf(struct sctp_pf *pf, sa_family_t family)
 
 static inline int init_sctp_mibs(struct net *net)
 {
-	return snmp_mib_init((void __percpu **)net->sctp.sctp_statistics,
-			     sizeof(struct sctp_mib),
-			     __alignof__(struct sctp_mib));
+	net->sctp.sctp_statistics = alloc_percpu(struct sctp_mib);
+	if (!net->sctp.sctp_statistics)
+		return -ENOMEM;
+	return 0;
 }
 
 static inline void cleanup_sctp_mibs(struct net *net)
 {
-	snmp_mib_free((void __percpu **)net->sctp.sctp_statistics);
+	free_percpu(net->sctp.sctp_statistics);
 }
 
 static void sctp_v4_pf_init(void)
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index fee5552ddf9..ae0e616a7ca 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1782,7 +1782,7 @@ no_hmac:
 	else
 		kt = ktime_get();
 
-	if (!asoc && ktime_compare(bear_cookie->expiration, kt) < 0) {
+	if (!asoc && ktime_before(bear_cookie->expiration, kt)) {
 		/*
 		 * Section 3.3.10.3 Stale Cookie Error (3)
 		 *
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fee06b99a4d..42989968940 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -71,6 +71,7 @@
 #include <net/route.h>
 #include <net/ipv6.h>
 #include <net/inet_common.h>
+#include <net/busy_poll.h>
 
 #include <linux/socket.h> /* for sa_family_t */
 #include <linux/export.h>
@@ -5945,8 +5946,9 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 		/* Search for an available port. */
 		int low, high, remaining, index;
 		unsigned int rover;
+		struct net *net = sock_net(sk);
 
-		inet_get_local_port_range(sock_net(sk), &low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
 		rover = prandom_u32() % remaining + low;
 
@@ -5954,7 +5956,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 			rover++;
 			if ((rover < low) || (rover > high))
 				rover = low;
-			if (inet_is_reserved_local_port(rover))
+			if (inet_is_local_reserved_port(net, rover))
 				continue;
 			index = sctp_phashfn(sock_net(sk), rover);
 			head = &sctp_port_hashtable[index];
@@ -6557,6 +6559,10 @@ static struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			break;
 
+		if (sk_can_busy_loop(sk) &&
+		    sk_busy_loop(sk, noblock))
+			continue;
+
 		/* User doesn't want to wait.  */
 		error = -EAGAIN;
 		if (!timeo)
@@ -6940,7 +6946,8 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newsk->sk_type = sk->sk_type;
 	newsk->sk_bound_dev_if = sk->sk_bound_dev_if;
 	newsk->sk_flags = sk->sk_flags;
-	newsk->sk_no_check = sk->sk_no_check;
+	newsk->sk_no_check_tx = sk->sk_no_check_tx;
+	newsk->sk_no_check_rx = sk->sk_no_check_rx;
 	newsk->sk_reuse = sk->sk_reuse;
 
 	newsk->sk_shutdown = sk->sk_shutdown;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index c82fdc1eab7..12c7e01c267 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -34,6 +34,8 @@
  *    Sridhar Samudrala     <sri@us.ibm.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <net/sctp/structs.h>
 #include <net/sctp/sctp.h>
 #include <linux/sysctl.h>
@@ -46,6 +48,11 @@ static int sack_timer_min = 1;
 static int sack_timer_max = 500;
 static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */
 static int rwnd_scale_max = 16;
+static int rto_alpha_min = 0;
+static int rto_beta_min = 0;
+static int rto_alpha_max = 1000;
+static int rto_beta_max = 1000;
+
 static unsigned long max_autoclose_min = 0;
 static unsigned long max_autoclose_max =
 	(MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX)
@@ -64,6 +71,9 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 				void __user *buffer, size_t *lenp,
 				loff_t *ppos);
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos);
 static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 			     void __user *buffer, size_t *lenp,
 			     loff_t *ppos);
@@ -126,15 +136,19 @@ static struct ctl_table sctp_net_table[] = {
 		.procname	= "rto_alpha_exp_divisor",
 		.data		= &init_net.sctp.rto_alpha,
 		.maxlen		= sizeof(int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_alpha_min,
+		.extra2		= &rto_alpha_max,
 	},
 	{
 		.procname	= "rto_beta_exp_divisor",
 		.data		= &init_net.sctp.rto_beta,
 		.maxlen		= sizeof(int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_alpha_beta,
+		.extra1		= &rto_beta_min,
+		.extra2		= &rto_beta_max,
 	},
 	{
 		.procname	= "max_burst",
@@ -307,41 +321,40 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write,
 				loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
-	char tmp[8];
 	struct ctl_table tbl;
-	int ret;
-	int changed = 0;
+	bool changed = false;
 	char *none = "none";
+	char tmp[8];
+	int ret;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
 
 	if (write) {
 		tbl.data = tmp;
-		tbl.maxlen = 8;
+		tbl.maxlen = sizeof(tmp);
 	} else {
 		tbl.data = net->sctp.sctp_hmac_alg ? : none;
 		tbl.maxlen = strlen(tbl.data);
 	}
-		ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
 
-	if (write) {
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
 #ifdef CONFIG_CRYPTO_MD5
 		if (!strncmp(tmp, "md5", 3)) {
 			net->sctp.sctp_hmac_alg = "md5";
-			changed = 1;
+			changed = true;
 		}
 #endif
 #ifdef CONFIG_CRYPTO_SHA1
 		if (!strncmp(tmp, "sha1", 4)) {
 			net->sctp.sctp_hmac_alg = "sha1";
-			changed = 1;
+			changed = true;
 		}
 #endif
 		if (!strncmp(tmp, "none", 4)) {
 			net->sctp.sctp_hmac_alg = NULL;
-			changed = 1;
+			changed = true;
 		}
-
 		if (!changed)
 			ret = -EINVAL;
 	}
@@ -354,11 +367,10 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 				loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
-	int new_value;
-	struct ctl_table tbl;
 	unsigned int min = *(unsigned int *) ctl->extra1;
 	unsigned int max = *(unsigned int *) ctl->extra2;
-	int ret;
+	struct ctl_table tbl;
+	int ret, new_value;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
 	tbl.maxlen = sizeof(unsigned int);
@@ -367,12 +379,15 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 		tbl.data = &new_value;
 	else
 		tbl.data = &net->sctp.rto_min;
+
 	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
-	if (write) {
-		if (ret || new_value > max || new_value < min)
+	if (write && ret == 0) {
+		if (new_value > max || new_value < min)
 			return -EINVAL;
+
 		net->sctp.rto_min = new_value;
 	}
+
 	return ret;
 }
 
@@ -381,11 +396,10 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 				loff_t *ppos)
 {
 	struct net *net = current->nsproxy->net_ns;
-	int new_value;
-	struct ctl_table tbl;
 	unsigned int min = *(unsigned int *) ctl->extra1;
 	unsigned int max = *(unsigned int *) ctl->extra2;
-	int ret;
+	struct ctl_table tbl;
+	int ret, new_value;
 
 	memset(&tbl, 0, sizeof(struct ctl_table));
 	tbl.maxlen = sizeof(unsigned int);
@@ -394,15 +408,28 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 		tbl.data = &new_value;
 	else
 		tbl.data = &net->sctp.rto_max;
+
 	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
-	if (write) {
-		if (ret || new_value > max || new_value < min)
+	if (write && ret == 0) {
+		if (new_value > max || new_value < min)
 			return -EINVAL;
+
 		net->sctp.rto_max = new_value;
 	}
+
 	return ret;
 }
 
+static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	pr_warn_once("Changing rto_alpha or rto_beta may lead to "
+		     "suboptimal rtt/srtt estimations!\n");
+
+	return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos);
+}
+
 static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 			     void __user *buffer, size_t *lenp,
 			     loff_t *ppos)
@@ -420,8 +447,7 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 		tbl.data = &net->sctp.auth_enable;
 
 	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
-
-	if (write) {
+	if (write && ret == 0) {
 		struct sock *sk = net->sctp.ctl_sock;
 
 		net->sctp.auth_enable = new_value;
@@ -436,20 +462,21 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 
 int sctp_sysctl_net_register(struct net *net)
 {
-	struct ctl_table *table = sctp_net_table;
-
-	if (!net_eq(net, &init_net)) {
-		int i;
+	struct ctl_table *table;
+	int i;
 
-		table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
-		if (!table)
-			return -ENOMEM;
+	table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
 
-		for (i = 0; table[i].data; i++)
-			table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
-	}
+	for (i = 0; table[i].data; i++)
+		table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
 
 	net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
+	if (net->sctp.sysctl_header == NULL) {
+		kfree(table);
+		return -ENOMEM;
+	}
 	return 0;
 }
 
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 1d348d15b33..7dd672fa651 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -72,7 +72,7 @@ static struct sctp_transport *sctp_transport_init(struct net *net,
 	 */
 	peer->rto = msecs_to_jiffies(net->sctp.rto_initial);
 
-	peer->last_time_heard = jiffies;
+	peer->last_time_heard = ktime_get();
 	peer->last_time_ecne_reduced = jiffies;
 
 	peer->param_flags = SPP_HB_DISABLE |
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 85c64658bd0..b6842fdb53d 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -366,9 +366,10 @@ fail:
  * specification [SCTP] and any extensions for a list of possible
  * error formats.
  */
-struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
-	const struct sctp_association *asoc, struct sctp_chunk *chunk,
-	__u16 flags, gfp_t gfp)
+struct sctp_ulpevent *
+sctp_ulpevent_make_remote_error(const struct sctp_association *asoc,
+				struct sctp_chunk *chunk, __u16 flags,
+				gfp_t gfp)
 {
 	struct sctp_ulpevent *event;
 	struct sctp_remote_error *sre;
@@ -387,8 +388,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
 	/* Copy the skb to a new skb with room for us to prepend
 	 * notification with.
 	 */
-	skb = skb_copy_expand(chunk->skb, sizeof(struct sctp_remote_error),
-			      0, gfp);
+	skb = skb_copy_expand(chunk->skb, sizeof(*sre), 0, gfp);
 
 	/* Pull off the rest of the cause TLV from the chunk.  */
 	skb_pull(chunk->skb, elen);
@@ -399,62 +399,21 @@ struct sctp_ulpevent *sctp_ulpevent_make_remote_error(
 	event = sctp_skb2event(skb);
 	sctp_ulpevent_init(event, MSG_NOTIFICATION, skb->truesize);
 
-	sre = (struct sctp_remote_error *)
-		skb_push(skb, sizeof(struct sctp_remote_error));
+	sre = (struct sctp_remote_error *) skb_push(skb, sizeof(*sre));
 
 	/* Trim the buffer to the right length.  */
-	skb_trim(skb, sizeof(struct sctp_remote_error) + elen);
+	skb_trim(skb, sizeof(*sre) + elen);
 
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_type:
-	 *   It should be SCTP_REMOTE_ERROR.
-	 */
+	/* RFC6458, Section 6.1.3. SCTP_REMOTE_ERROR */
+	memset(sre, 0, sizeof(*sre));
 	sre->sre_type = SCTP_REMOTE_ERROR;
-
-	/*
-	 * Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_flags: 16 bits (unsigned integer)
-	 *   Currently unused.
-	 */
 	sre->sre_flags = 0;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_length: sizeof (__u32)
-	 *
-	 * This field is the total length of the notification data,
-	 * including the notification header.
-	 */
 	sre->sre_length = skb->len;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_error: 16 bits (unsigned integer)
-	 * This value represents one of the Operational Error causes defined in
-	 * the SCTP specification, in network byte order.
-	 */
 	sre->sre_error = cause;
-
-	/* Socket Extensions for SCTP
-	 * 5.3.1.3 SCTP_REMOTE_ERROR
-	 *
-	 * sre_assoc_id: sizeof (sctp_assoc_t)
-	 *
-	 * The association id field, holds the identifier for the association.
-	 * All notifications for a given association have the same association
-	 * identifier.  For TCP style socket, this field is ignored.
-	 */
 	sctp_ulpevent_set_owner(event, asoc);
 	sre->sre_assoc_id = sctp_assoc2id(asoc);
 
 	return event;
-
 fail:
 	return NULL;
 }
@@ -899,7 +858,9 @@ __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event)
 	return notification->sn_header.sn_type;
 }
 
-/* Copy out the sndrcvinfo into a msghdr.  */
+/* RFC6458, Section 5.3.2. SCTP Header Information Structure
+ * (SCTP_SNDRCV, DEPRECATED)
+ */
 void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 				   struct msghdr *msghdr)
 {
@@ -908,74 +869,21 @@ void sctp_ulpevent_read_sndrcvinfo(const struct sctp_ulpevent *event,
 	if (sctp_ulpevent_is_notification(event))
 		return;
 
-	/* Sockets API Extensions for SCTP
-	 * Section 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV)
-	 *
-	 * sinfo_stream: 16 bits (unsigned integer)
-	 *
-	 * For recvmsg() the SCTP stack places the message's stream number in
-	 * this value.
-	*/
+	memset(&sinfo, 0, sizeof(sinfo));
 	sinfo.sinfo_stream = event->stream;
-	/* sinfo_ssn: 16 bits (unsigned integer)
-	 *
-	 * For recvmsg() this value contains the stream sequence number that
-	 * the remote endpoint placed in the DATA chunk.  For fragmented
-	 * messages this is the same number for all deliveries of the message
-	 * (if more than one recvmsg() is needed to read the message).
-	 */
 	sinfo.sinfo_ssn = event->ssn;
-	/* sinfo_ppid: 32 bits (unsigned integer)
-	 *
-	 * In recvmsg() this value is
-	 * the same information that was passed by the upper layer in the peer
-	 * application.  Please note that byte order issues are NOT accounted
-	 * for and this information is passed opaquely by the SCTP stack from
-	 * one end to the other.
-	 */
 	sinfo.sinfo_ppid = event->ppid;
-	/* sinfo_flags: 16 bits (unsigned integer)
-	 *
-	 * This field may contain any of the following flags and is composed of
-	 * a bitwise OR of these values.
-	 *
-	 * recvmsg() flags:
-	 *
-	 * SCTP_UNORDERED - This flag is present when the message was sent
-	 *                 non-ordered.
-	 */
 	sinfo.sinfo_flags = event->flags;
-	/* sinfo_tsn: 32 bit (unsigned integer)
-	 *
-	 * For the receiving side, this field holds a TSN that was
-	 * assigned to one of the SCTP Data Chunks.
-	 */
 	sinfo.sinfo_tsn = event->tsn;
-	/* sinfo_cumtsn: 32 bit (unsigned integer)
-	 *
-	 * This field will hold the current cumulative TSN as
-	 * known by the underlying SCTP layer.  Note this field is
-	 * ignored when sending and only valid for a receive
-	 * operation when sinfo_flags are set to SCTP_UNORDERED.
-	 */
 	sinfo.sinfo_cumtsn = event->cumtsn;
-	/* sinfo_assoc_id: sizeof (sctp_assoc_t)
-	 *
-	 * The association handle field, sinfo_assoc_id, holds the identifier
-	 * for the association announced in the COMMUNICATION_UP notification.
-	 * All notifications for a given association have the same identifier.
-	 * Ignored for one-to-one style sockets.
-	 */
 	sinfo.sinfo_assoc_id = sctp_assoc2id(event->asoc);
-
-	/* context value that is set via SCTP_CONTEXT socket option. */
+	/* Context value that is set via SCTP_CONTEXT socket option. */
 	sinfo.sinfo_context = event->asoc->default_rcv_context;
-
 	/* These fields are not used while receiving. */
 	sinfo.sinfo_timetolive = 0;
 
 	put_cmsg(msghdr, IPPROTO_SCTP, SCTP_SNDRCV,
-		 sizeof(struct sctp_sndrcvinfo), (void *)&sinfo);
+		 sizeof(sinfo), &sinfo);
 }
 
 /* Do accounting for bytes received and hold a reference to the association
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 7144eb6a1b9..d49dc2ed30a 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -38,6 +38,7 @@
 #include <linux/types.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
+#include <net/busy_poll.h>
 #include <net/sctp/structs.h>
 #include <net/sctp/sctp.h>
 #include <net/sctp/sm.h>
@@ -204,6 +205,9 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 	if (sock_flag(sk, SOCK_DEAD) || (sk->sk_shutdown & RCV_SHUTDOWN))
 		goto out_free;
 
+	if (!sctp_ulpevent_is_notification(event))
+		sk_mark_napi_id(sk, skb);
+
 	/* Check if the user wishes to receive this event.  */
 	if (!sctp_ulpevent_is_enabled(event, &sctp_sk(sk)->subscribe))
 		goto out_free;
diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c
index 247e973544b..f7736671742 100644
--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -592,6 +592,7 @@ rpcauth_lookupcred(struct rpc_auth *auth, int flags)
 	put_group_info(acred.group_info);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(rpcauth_lookupcred);
 
 void
 rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred,
diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c
index 27ce2624093..92d5ab99fbf 100644
--- a/net/sunrpc/auth_gss/gss_mech_switch.c
+++ b/net/sunrpc/auth_gss/gss_mech_switch.c
@@ -218,10 +218,8 @@ static struct gss_api_mech *_gss_mech_get_by_pseudoflavor(u32 pseudoflavor)
 
 	spin_lock(&registered_mechs_lock);
 	list_for_each_entry(pos, &registered_mechs, gm_list) {
-		if (!mech_supports_pseudoflavor(pos, pseudoflavor)) {
-			module_put(pos->gm_owner);
+		if (!mech_supports_pseudoflavor(pos, pseudoflavor))
 			continue;
-		}
 		if (try_module_get(pos->gm_owner))
 			gm = pos;
 		break;
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 0f73f450774..4ce5eccec1f 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1503,6 +1503,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
 			if (unwrap_integ_data(rqstp, &rqstp->rq_arg,
 					gc->gc_seq, rsci->mechctx))
 				goto garbage_args;
+			rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE;
 			break;
 		case RPC_GSS_SVC_PRIVACY:
 			/* placeholders for length and seq. number: */
@@ -1511,6 +1512,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
 			if (unwrap_priv_data(rqstp, &rqstp->rq_arg,
 					gc->gc_seq, rsci->mechctx))
 				goto garbage_args;
+			rqstp->rq_auth_slack = RPC_MAX_AUTH_SIZE * 2;
 			break;
 		default:
 			goto auth_err;
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index ae333c1845b..06636214113 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -374,7 +374,7 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd)
 	}
 	return;
 out:
-	printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name);
+	printk(KERN_ERR "RPC: failed to unregister %s cache\n", cd->name);
 }
 EXPORT_SYMBOL_GPL(sunrpc_destroy_cache_detail);
 
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 25578afe154..9358c79fd58 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -250,7 +250,7 @@ void rpc_destroy_wait_queue(struct rpc_wait_queue *queue)
 }
 EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue);
 
-static int rpc_wait_bit_killable(void *word)
+static int rpc_wait_bit_killable(struct wait_bit_key *key)
 {
 	if (fatal_signal_pending(current))
 		return -ERESTARTSYS;
@@ -309,7 +309,7 @@ static int rpc_complete_task(struct rpc_task *task)
  * to enforce taking of the wq->lock and hence avoid races with
  * rpc_complete_task().
  */
-int __rpc_wait_for_completion_task(struct rpc_task *task, int (*action)(void *))
+int __rpc_wait_for_completion_task(struct rpc_task *task, wait_bit_action_f *action)
 {
 	if (action == NULL)
 		action = rpc_wait_bit_killable;
@@ -832,7 +832,8 @@ static void rpc_async_schedule(struct work_struct *work)
  * @size: requested byte size
  *
  * To prevent rpciod from hanging, this allocator never sleeps,
- * returning NULL if the request cannot be serviced immediately.
+ * returning NULL and suppressing warning if the request cannot be serviced
+ * immediately.
  * The caller can arrange to sleep in a way that is safe for rpciod.
  *
  * Most requests are 'small' (under 2KiB) and can be serviced from a
@@ -845,7 +846,7 @@ static void rpc_async_schedule(struct work_struct *work)
 void *rpc_malloc(struct rpc_task *task, size_t size)
 {
 	struct rpc_buffer *buf;
-	gfp_t gfp = GFP_NOWAIT;
+	gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN;
 
 	if (RPC_IS_SWAPPER(task))
 		gfp |= __GFP_MEMALLOC;
diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
index 0a648c502fc..2df87f78e51 100644
--- a/net/sunrpc/socklib.c
+++ b/net/sunrpc/socklib.c
@@ -173,7 +173,8 @@ int csum_partial_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
 		return -1;
 	if (csum_fold(desc.csum))
 		return -1;
-	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
+	if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+	    !skb->csum_complete_sw)
 		netdev_rx_csum_fault(skb->dev);
 	return 0;
 no_checksum:
diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h
index 14c9f6d1c5f..f2b7cb540e6 100644
--- a/net/sunrpc/sunrpc.h
+++ b/net/sunrpc/sunrpc.h
@@ -43,6 +43,19 @@ static inline int rpc_reply_expected(struct rpc_task *task)
 		(task->tk_msg.rpc_proc->p_decode != NULL);
 }
 
+static inline int sock_is_loopback(struct sock *sk)
+{
+	struct dst_entry *dst;
+	int loopback = 0;
+	rcu_read_lock();
+	dst = rcu_dereference(sk->sk_dst_cache);
+	if (dst && dst->dev &&
+	    (dst->dev->features & NETIF_F_LOOPBACK))
+		loopback = 1;
+	rcu_read_unlock();
+	return loopback;
+}
+
 int svc_send_common(struct socket *sock, struct xdr_buf *xdr,
 		    struct page *headpage, unsigned long headoffset,
 		    struct page *tailpage, unsigned long tailoffset);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 06c6ff0cb91..b4737fbdec1 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -597,6 +597,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
 			}
 			rqstp->rq_pages[i] = p;
 		}
+	rqstp->rq_page_end = &rqstp->rq_pages[i];
 	rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */
 
 	/* Make arg->head point to first page and arg->pages point to rest */
@@ -730,6 +731,8 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 		newxpt = xprt->xpt_ops->xpo_accept(xprt);
 		if (newxpt)
 			svc_add_new_temp_xprt(serv, newxpt);
+		else
+			module_put(xprt->xpt_class->xcl_owner);
 	} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
 		/* XPT_DATA|XPT_DEFERRED case: */
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
@@ -793,7 +796,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 
 	clear_bit(XPT_OLD, &xprt->xpt_flags);
 
-	rqstp->rq_secure = svc_port_is_privileged(svc_addr(rqstp));
+	rqstp->rq_secure = xprt->xpt_ops->xpo_secure_port(rqstp);
 	rqstp->rq_chandle.defer = svc_defer;
 
 	if (serv->sv_stats)
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index 2af7b0cba43..79c0f3459b5 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -54,6 +54,8 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
 	}
 	spin_unlock(&authtab_lock);
 
+	rqstp->rq_auth_slack = 0;
+
 	rqstp->rq_authop = aops;
 	return aops->accept(rqstp, authp);
 }
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 43bcb4699d6..b507cd327d9 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -400,6 +400,12 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
 	release_sock(sock->sk);
 #endif
 }
+
+static int svc_sock_secure_port(struct svc_rqst *rqstp)
+{
+	return svc_port_is_privileged(svc_addr(rqstp));
+}
+
 /*
  * INET callback when data has been received on the socket.
  */
@@ -678,6 +684,7 @@ static struct svc_xprt_ops svc_udp_ops = {
 	.xpo_prep_reply_hdr = svc_udp_prep_reply_hdr,
 	.xpo_has_wspace = svc_udp_has_wspace,
 	.xpo_accept = svc_udp_accept,
+	.xpo_secure_port = svc_sock_secure_port,
 };
 
 static struct svc_xprt_class svc_udp_class = {
@@ -842,8 +849,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	 * tell us anything.  For now just warn about unpriv connections.
 	 */
 	if (!svc_port_is_privileged(sin)) {
-		dprintk(KERN_WARNING
-			"%s: connect from unprivileged port: %s\n",
+		dprintk("%s: connect from unprivileged port: %s\n",
 			serv->sv_name,
 			__svc_print_addr(sin, buf, sizeof(buf)));
 	}
@@ -867,6 +873,10 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	}
 	svc_xprt_set_local(&newsvsk->sk_xprt, sin, slen);
 
+	if (sock_is_loopback(newsock->sk))
+		set_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags);
+	else
+		clear_bit(XPT_LOCAL, &newsvsk->sk_xprt.xpt_flags);
 	if (serv->sv_stats)
 		serv->sv_stats->nettcpconn++;
 
@@ -1112,6 +1122,7 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 
 	rqstp->rq_xprt_ctxt   = NULL;
 	rqstp->rq_prot	      = IPPROTO_TCP;
+	rqstp->rq_local	      = !!test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags);
 
 	p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
 	calldir = p[1];
@@ -1234,6 +1245,7 @@ static struct svc_xprt_ops svc_tcp_bc_ops = {
 	.xpo_detach = svc_bc_tcp_sock_detach,
 	.xpo_free = svc_bc_sock_free,
 	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
+	.xpo_secure_port = svc_sock_secure_port,
 };
 
 static struct svc_xprt_class svc_tcp_bc_class = {
@@ -1272,6 +1284,7 @@ static struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
 	.xpo_has_wspace = svc_tcp_has_wspace,
 	.xpo_accept = svc_tcp_accept,
+	.xpo_secure_port = svc_sock_secure_port,
 };
 
 static struct svc_xprt_class svc_tcp_class = {
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index dd97ba3c445..23fb4e75e24 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -462,6 +462,7 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
 	struct kvec *iov = buf->head;
 	int scratch_len = buf->buflen - buf->page_len - buf->tail[0].iov_len;
 
+	xdr_set_scratch_buffer(xdr, NULL, 0);
 	BUG_ON(scratch_len < 0);
 	xdr->buf = buf;
 	xdr->iov = iov;
@@ -482,6 +483,73 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
 EXPORT_SYMBOL_GPL(xdr_init_encode);
 
 /**
+ * xdr_commit_encode - Ensure all data is written to buffer
+ * @xdr: pointer to xdr_stream
+ *
+ * We handle encoding across page boundaries by giving the caller a
+ * temporary location to write to, then later copying the data into
+ * place; xdr_commit_encode does that copying.
+ *
+ * Normally the caller doesn't need to call this directly, as the
+ * following xdr_reserve_space will do it.  But an explicit call may be
+ * required at the end of encoding, or any other time when the xdr_buf
+ * data might be read.
+ */
+void xdr_commit_encode(struct xdr_stream *xdr)
+{
+	int shift = xdr->scratch.iov_len;
+	void *page;
+
+	if (shift == 0)
+		return;
+	page = page_address(*xdr->page_ptr);
+	memcpy(xdr->scratch.iov_base, page, shift);
+	memmove(page, page + shift, (void *)xdr->p - page);
+	xdr->scratch.iov_len = 0;
+}
+EXPORT_SYMBOL_GPL(xdr_commit_encode);
+
+__be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, size_t nbytes)
+{
+	static __be32 *p;
+	int space_left;
+	int frag1bytes, frag2bytes;
+
+	if (nbytes > PAGE_SIZE)
+		return NULL; /* Bigger buffers require special handling */
+	if (xdr->buf->len + nbytes > xdr->buf->buflen)
+		return NULL; /* Sorry, we're totally out of space */
+	frag1bytes = (xdr->end - xdr->p) << 2;
+	frag2bytes = nbytes - frag1bytes;
+	if (xdr->iov)
+		xdr->iov->iov_len += frag1bytes;
+	else
+		xdr->buf->page_len += frag1bytes;
+	xdr->page_ptr++;
+	xdr->iov = NULL;
+	/*
+	 * If the last encode didn't end exactly on a page boundary, the
+	 * next one will straddle boundaries.  Encode into the next
+	 * page, then copy it back later in xdr_commit_encode.  We use
+	 * the "scratch" iov to track any temporarily unused fragment of
+	 * space at the end of the previous buffer:
+	 */
+	xdr->scratch.iov_base = xdr->p;
+	xdr->scratch.iov_len = frag1bytes;
+	p = page_address(*xdr->page_ptr);
+	/*
+	 * Note this is where the next encode will start after we've
+	 * shifted this one back:
+	 */
+	xdr->p = (void *)p + frag2bytes;
+	space_left = xdr->buf->buflen - xdr->buf->len;
+	xdr->end = (void *)p + min_t(int, space_left, PAGE_SIZE);
+	xdr->buf->page_len += frag2bytes;
+	xdr->buf->len += nbytes;
+	return p;
+}
+
+/**
  * xdr_reserve_space - Reserve buffer space for sending
  * @xdr: pointer to xdr_stream
  * @nbytes: number of bytes to reserve
@@ -495,20 +563,122 @@ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
 	__be32 *p = xdr->p;
 	__be32 *q;
 
+	xdr_commit_encode(xdr);
 	/* align nbytes on the next 32-bit boundary */
 	nbytes += 3;
 	nbytes &= ~3;
 	q = p + (nbytes >> 2);
 	if (unlikely(q > xdr->end || q < p))
-		return NULL;
+		return xdr_get_next_encode_buffer(xdr, nbytes);
 	xdr->p = q;
-	xdr->iov->iov_len += nbytes;
+	if (xdr->iov)
+		xdr->iov->iov_len += nbytes;
+	else
+		xdr->buf->page_len += nbytes;
 	xdr->buf->len += nbytes;
 	return p;
 }
 EXPORT_SYMBOL_GPL(xdr_reserve_space);
 
 /**
+ * xdr_truncate_encode - truncate an encode buffer
+ * @xdr: pointer to xdr_stream
+ * @len: new length of buffer
+ *
+ * Truncates the xdr stream, so that xdr->buf->len == len,
+ * and xdr->p points at offset len from the start of the buffer, and
+ * head, tail, and page lengths are adjusted to correspond.
+ *
+ * If this means moving xdr->p to a different buffer, we assume that
+ * that the end pointer should be set to the end of the current page,
+ * except in the case of the head buffer when we assume the head
+ * buffer's current length represents the end of the available buffer.
+ *
+ * This is *not* safe to use on a buffer that already has inlined page
+ * cache pages (as in a zero-copy server read reply), except for the
+ * simple case of truncating from one position in the tail to another.
+ *
+ */
+void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
+{
+	struct xdr_buf *buf = xdr->buf;
+	struct kvec *head = buf->head;
+	struct kvec *tail = buf->tail;
+	int fraglen;
+	int new, old;
+
+	if (len > buf->len) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+	xdr_commit_encode(xdr);
+
+	fraglen = min_t(int, buf->len - len, tail->iov_len);
+	tail->iov_len -= fraglen;
+	buf->len -= fraglen;
+	if (tail->iov_len && buf->len == len) {
+		xdr->p = tail->iov_base + tail->iov_len;
+		/* xdr->end, xdr->iov should be set already */
+		return;
+	}
+	WARN_ON_ONCE(fraglen);
+	fraglen = min_t(int, buf->len - len, buf->page_len);
+	buf->page_len -= fraglen;
+	buf->len -= fraglen;
+
+	new = buf->page_base + buf->page_len;
+	old = new + fraglen;
+	xdr->page_ptr -= (old >> PAGE_SHIFT) - (new >> PAGE_SHIFT);
+
+	if (buf->page_len && buf->len == len) {
+		xdr->p = page_address(*xdr->page_ptr);
+		xdr->end = (void *)xdr->p + PAGE_SIZE;
+		xdr->p = (void *)xdr->p + (new % PAGE_SIZE);
+		/* xdr->iov should already be NULL */
+		return;
+	}
+	if (fraglen) {
+		xdr->end = head->iov_base + head->iov_len;
+		xdr->page_ptr--;
+	}
+	/* (otherwise assume xdr->end is already set) */
+	head->iov_len = len;
+	buf->len = len;
+	xdr->p = head->iov_base + head->iov_len;
+	xdr->iov = buf->head;
+}
+EXPORT_SYMBOL(xdr_truncate_encode);
+
+/**
+ * xdr_restrict_buflen - decrease available buffer space
+ * @xdr: pointer to xdr_stream
+ * @newbuflen: new maximum number of bytes available
+ *
+ * Adjust our idea of how much space is available in the buffer.
+ * If we've already used too much space in the buffer, returns -1.
+ * If the available space is already smaller than newbuflen, returns 0
+ * and does nothing.  Otherwise, adjusts xdr->buf->buflen to newbuflen
+ * and ensures xdr->end is set at most offset newbuflen from the start
+ * of the buffer.
+ */
+int xdr_restrict_buflen(struct xdr_stream *xdr, int newbuflen)
+{
+	struct xdr_buf *buf = xdr->buf;
+	int left_in_this_buf = (void *)xdr->end - (void *)xdr->p;
+	int end_offset = buf->len + left_in_this_buf;
+
+	if (newbuflen < 0 || newbuflen < buf->len)
+		return -1;
+	if (newbuflen > buf->buflen)
+		return 0;
+	if (newbuflen < end_offset)
+		xdr->end = (void *)xdr->end + newbuflen - end_offset;
+	buf->buflen = newbuflen;
+	return 0;
+}
+EXPORT_SYMBOL(xdr_restrict_buflen);
+
+/**
  * xdr_write_pages - Insert a list of pages into an XDR buffer for sending
  * @xdr: pointer to xdr_stream
  * @pages: list of pages
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 89d051de6b3..c3b2b3369e5 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -71,24 +71,6 @@ static void	 xprt_destroy(struct rpc_xprt *xprt);
 static DEFINE_SPINLOCK(xprt_list_lock);
 static LIST_HEAD(xprt_list);
 
-/*
- * The transport code maintains an estimate on the maximum number of out-
- * standing RPC requests, using a smoothed version of the congestion
- * avoidance implemented in 44BSD. This is basically the Van Jacobson
- * congestion algorithm: If a retransmit occurs, the congestion window is
- * halved; otherwise, it is incremented by 1/cwnd when
- *
- *	-	a reply is received and
- *	-	a full number of requests are outstanding and
- *	-	the congestion window hasn't been updated recently.
- */
-#define RPC_CWNDSHIFT		(8U)
-#define RPC_CWNDSCALE		(1U << RPC_CWNDSHIFT)
-#define RPC_INITCWND		RPC_CWNDSCALE
-#define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)
-
-#define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
-
 /**
  * xprt_register_transport - register a transport implementation
  * @transport: transport to register
@@ -446,7 +428,15 @@ EXPORT_SYMBOL_GPL(xprt_release_rqst_cong);
  * @task: recently completed RPC request used to adjust window
  * @result: result code of completed RPC request
  *
- * We use a time-smoothed congestion estimator to avoid heavy oscillation.
+ * The transport code maintains an estimate on the maximum number of out-
+ * standing RPC requests, using a smoothed version of the congestion
+ * avoidance implemented in 44BSD. This is basically the Van Jacobson
+ * congestion algorithm: If a retransmit occurs, the congestion window is
+ * halved; otherwise, it is incremented by 1/cwnd when
+ *
+ *	-	a reply is received and
+ *	-	a full number of requests are outstanding and
+ *	-	the congestion window hasn't been updated recently.
  */
 void xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result)
 {
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 96ead526b12..693966d3f33 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -78,8 +78,7 @@ static const char transfertypes[][12] = {
  * elements. Segments are then coalesced when registered, if possible
  * within the selected memreg mode.
  *
- * Note, this routine is never called if the connection's memory
- * registration strategy is 0 (bounce buffers).
+ * Returns positive number of segments converted, or a negative errno.
  */
 
 static int
@@ -102,10 +101,17 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 	page_base = xdrbuf->page_base & ~PAGE_MASK;
 	p = 0;
 	while (len && n < nsegs) {
+		if (!ppages[p]) {
+			/* alloc the pagelist for receiving buffer */
+			ppages[p] = alloc_page(GFP_ATOMIC);
+			if (!ppages[p])
+				return -ENOMEM;
+		}
 		seg[n].mr_page = ppages[p];
 		seg[n].mr_offset = (void *)(unsigned long) page_base;
 		seg[n].mr_len = min_t(u32, PAGE_SIZE - page_base, len);
-		BUG_ON(seg[n].mr_len > PAGE_SIZE);
+		if (seg[n].mr_len > PAGE_SIZE)
+			return -EIO;
 		len -= seg[n].mr_len;
 		++n;
 		++p;
@@ -114,7 +120,7 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 
 	/* Message overflows the seg array */
 	if (len && n == nsegs)
-		return 0;
+		return -EIO;
 
 	if (xdrbuf->tail[0].iov_len) {
 		/* the rpcrdma protocol allows us to omit any trailing
@@ -123,7 +129,7 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
 			return n;
 		if (n == nsegs)
 			/* Tail remains, but we're out of segments */
-			return 0;
+			return -EIO;
 		seg[n].mr_page = NULL;
 		seg[n].mr_offset = xdrbuf->tail[0].iov_base;
 		seg[n].mr_len = xdrbuf->tail[0].iov_len;
@@ -164,15 +170,17 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
  *  Reply chunk (a counted array):
  *   N elements:
  *    1 - N - HLOO - HLOO - ... - HLOO
+ *
+ * Returns positive RPC/RDMA header size, or negative errno.
  */
 
-static unsigned int
+static ssize_t
 rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 		struct rpcrdma_msg *headerp, enum rpcrdma_chunktype type)
 {
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
-	int nsegs, nchunks = 0;
+	int n, nsegs, nchunks = 0;
 	unsigned int pos;
 	struct rpcrdma_mr_seg *seg = req->rl_segments;
 	struct rpcrdma_read_chunk *cur_rchunk = NULL;
@@ -198,12 +206,11 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 		pos = target->head[0].iov_len;
 
 	nsegs = rpcrdma_convert_iovs(target, pos, type, seg, RPCRDMA_MAX_SEGS);
-	if (nsegs == 0)
-		return 0;
+	if (nsegs < 0)
+		return nsegs;
 
 	do {
-		/* bind/register the memory, then build chunk from result. */
-		int n = rpcrdma_register_external(seg, nsegs,
+		n = rpcrdma_register_external(seg, nsegs,
 						cur_wchunk != NULL, r_xprt);
 		if (n <= 0)
 			goto out;
@@ -248,10 +255,6 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	/* success. all failures return above */
 	req->rl_nchunks = nchunks;
 
-	BUG_ON(nchunks == 0);
-	BUG_ON((r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
-	       && (nchunks > 3));
-
 	/*
 	 * finish off header. If write, marshal discrim and nchunks.
 	 */
@@ -278,8 +281,8 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 out:
 	for (pos = 0; nchunks--;)
 		pos += rpcrdma_deregister_external(
-				&req->rl_segments[pos], r_xprt, NULL);
-	return 0;
+				&req->rl_segments[pos], r_xprt);
+	return n;
 }
 
 /*
@@ -361,6 +364,8 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad)
  *  [1] -- the RPC header/data, marshaled by RPC and the NFS protocol.
  *  [2] -- optional padding.
  *  [3] -- if padded, header only in [1] and data here.
+ *
+ * Returns zero on success, otherwise a negative errno.
  */
 
 int
@@ -370,7 +375,8 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	char *base;
-	size_t hdrlen, rpclen, padlen;
+	size_t rpclen, padlen;
+	ssize_t hdrlen;
 	enum rpcrdma_chunktype rtype, wtype;
 	struct rpcrdma_msg *headerp;
 
@@ -441,14 +447,10 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 	/* The following simplification is not true forever */
 	if (rtype != rpcrdma_noch && wtype == rpcrdma_replych)
 		wtype = rpcrdma_noch;
-	BUG_ON(rtype != rpcrdma_noch && wtype != rpcrdma_noch);
-
-	if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_BOUNCEBUFFERS &&
-	    (rtype != rpcrdma_noch || wtype != rpcrdma_noch)) {
-		/* forced to "pure inline"? */
-		dprintk("RPC:       %s: too much data (%d/%d) for inline\n",
-			__func__, rqst->rq_rcv_buf.len, rqst->rq_snd_buf.len);
-		return -1;
+	if (rtype != rpcrdma_noch && wtype != rpcrdma_noch) {
+		dprintk("RPC:       %s: cannot marshal multiple chunk lists\n",
+			__func__);
+		return -EIO;
 	}
 
 	hdrlen = 28; /*sizeof *headerp;*/
@@ -474,8 +476,11 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			headerp->rm_body.rm_padded.rm_pempty[1] = xdr_zero;
 			headerp->rm_body.rm_padded.rm_pempty[2] = xdr_zero;
 			hdrlen += 2 * sizeof(u32); /* extra words in padhdr */
-			BUG_ON(wtype != rpcrdma_noch);
-
+			if (wtype != rpcrdma_noch) {
+				dprintk("RPC:       %s: invalid chunk list\n",
+					__func__);
+				return -EIO;
+			}
 		} else {
 			headerp->rm_body.rm_nochunks.rm_empty[0] = xdr_zero;
 			headerp->rm_body.rm_nochunks.rm_empty[1] = xdr_zero;
@@ -492,8 +497,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 			 * on receive. Therefore, we request a reply chunk
 			 * for non-writes wherever feasible and efficient.
 			 */
-			if (wtype == rpcrdma_noch &&
-			    r_xprt->rx_ia.ri_memreg_strategy > RPCRDMA_REGISTER)
+			if (wtype == rpcrdma_noch)
 				wtype = rpcrdma_replych;
 		}
 	}
@@ -511,9 +515,8 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst)
 		hdrlen = rpcrdma_create_chunks(rqst,
 					&rqst->rq_rcv_buf, headerp, wtype);
 	}
-
-	if (hdrlen == 0)
-		return -1;
+	if (hdrlen < 0)
+		return hdrlen;
 
 	dprintk("RPC:       %s: %s: hdrlen %zd rpclen %zd padlen %zd"
 		" headerp 0x%p base 0x%p lkey 0x%x\n",
@@ -680,15 +683,11 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
 	rqst->rq_private_buf = rqst->rq_rcv_buf;
 }
 
-/*
- * This function is called when an async event is posted to
- * the connection which changes the connection state. All it
- * does at this point is mark the connection up/down, the rpc
- * timers do the rest.
- */
 void
-rpcrdma_conn_func(struct rpcrdma_ep *ep)
+rpcrdma_connect_worker(struct work_struct *work)
 {
+	struct rpcrdma_ep *ep =
+		container_of(work, struct rpcrdma_ep, rep_connect_worker.work);
 	struct rpc_xprt *xprt = ep->rep_xprt;
 
 	spin_lock_bh(&xprt->transport_lock);
@@ -705,13 +704,15 @@ rpcrdma_conn_func(struct rpcrdma_ep *ep)
 }
 
 /*
- * This function is called when memory window unbind which we are waiting
- * for completes. Just use rr_func (zeroed by upcall) to signal completion.
+ * This function is called when an async event is posted to
+ * the connection which changes the connection state. All it
+ * does at this point is mark the connection up/down, the rpc
+ * timers do the rest.
  */
-static void
-rpcrdma_unbind_func(struct rpcrdma_rep *rep)
+void
+rpcrdma_conn_func(struct rpcrdma_ep *ep)
 {
-	wake_up(&rep->rr_unbind);
+	schedule_delayed_work(&ep->rep_connect_worker, 0);
 }
 
 /*
@@ -728,7 +729,8 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	struct rpc_xprt *xprt = rep->rr_xprt;
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	__be32 *iptr;
-	int i, rdmalen, status;
+	int rdmalen, status;
+	unsigned long cwnd;
 
 	/* Check status. If bad, signal disconnect and return rep to pool */
 	if (rep->rr_len == ~0U) {
@@ -783,6 +785,7 @@ repost:
 
 	/* from here on, the reply is no longer an orphan */
 	req->rl_reply = rep;
+	xprt->reestablish_timeout = 0;
 
 	/* check for expected message types */
 	/* The order of some of these tests is important. */
@@ -857,26 +860,10 @@ badheader:
 		break;
 	}
 
-	/* If using mw bind, start the deregister process now. */
-	/* (Note: if mr_free(), cannot perform it here, in tasklet context) */
-	if (req->rl_nchunks) switch (r_xprt->rx_ia.ri_memreg_strategy) {
-	case RPCRDMA_MEMWINDOWS:
-		for (i = 0; req->rl_nchunks-- > 1;)
-			i += rpcrdma_deregister_external(
-				&req->rl_segments[i], r_xprt, NULL);
-		/* Optionally wait (not here) for unbinds to complete */
-		rep->rr_func = rpcrdma_unbind_func;
-		(void) rpcrdma_deregister_external(&req->rl_segments[i],
-						   r_xprt, rep);
-		break;
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-		for (i = 0; req->rl_nchunks--;)
-			i += rpcrdma_deregister_external(&req->rl_segments[i],
-							 r_xprt, NULL);
-		break;
-	default:
-		break;
-	}
+	cwnd = xprt->cwnd;
+	xprt->cwnd = atomic_read(&r_xprt->rx_buf.rb_credits) << RPC_CWNDSHIFT;
+	if (xprt->cwnd > cwnd)
+		xprt_release_rqst_cong(rqst->rq_task);
 
 	dprintk("RPC:       %s: xprt_complete_rqst(0x%p, 0x%p, %d)\n",
 			__func__, xprt, rqst, status);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 8d904e4eef1..8f92a61ee2d 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved.
  * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -69,7 +70,8 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 
 	/* Set up the XDR head */
 	rqstp->rq_arg.head[0].iov_base = page_address(page);
-	rqstp->rq_arg.head[0].iov_len = min(byte_count, ctxt->sge[0].length);
+	rqstp->rq_arg.head[0].iov_len =
+		min_t(size_t, byte_count, ctxt->sge[0].length);
 	rqstp->rq_arg.len = byte_count;
 	rqstp->rq_arg.buflen = byte_count;
 
@@ -85,7 +87,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 		page = ctxt->pages[sge_no];
 		put_page(rqstp->rq_pages[sge_no]);
 		rqstp->rq_pages[sge_no] = page;
-		bc -= min(bc, ctxt->sge[sge_no].length);
+		bc -= min_t(u32, bc, ctxt->sge[sge_no].length);
 		rqstp->rq_arg.buflen += ctxt->sge[sge_no].length;
 		sge_no++;
 	}
@@ -113,291 +115,265 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	rqstp->rq_arg.tail[0].iov_len = 0;
 }
 
-/* Encode a read-chunk-list as an array of IB SGE
- *
- * Assumptions:
- * - chunk[0]->position points to pages[0] at an offset of 0
- * - pages[] is not physically or virtually contiguous and consists of
- *   PAGE_SIZE elements.
- *
- * Output:
- * - sge array pointing into pages[] array.
- * - chunk_sge array specifying sge index and count for each
- *   chunk in the read list
- *
- */
-static int map_read_chunks(struct svcxprt_rdma *xprt,
-			   struct svc_rqst *rqstp,
-			   struct svc_rdma_op_ctxt *head,
-			   struct rpcrdma_msg *rmsgp,
-			   struct svc_rdma_req_map *rpl_map,
-			   struct svc_rdma_req_map *chl_map,
-			   int ch_count,
-			   int byte_count)
+static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count)
 {
-	int sge_no;
-	int sge_bytes;
-	int page_off;
-	int page_no;
-	int ch_bytes;
-	int ch_no;
-	struct rpcrdma_read_chunk *ch;
+	if (rdma_node_get_transport(xprt->sc_cm_id->device->node_type) ==
+	     RDMA_TRANSPORT_IWARP)
+		return 1;
+	else
+		return min_t(int, sge_count, xprt->sc_max_sge);
+}
 
-	sge_no = 0;
-	page_no = 0;
-	page_off = 0;
-	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-	ch_no = 0;
-	ch_bytes = ntohl(ch->rc_target.rs_length);
-	head->arg.head[0] = rqstp->rq_arg.head[0];
-	head->arg.tail[0] = rqstp->rq_arg.tail[0];
-	head->arg.pages = &head->pages[head->count];
-	head->hdr_count = head->count; /* save count of hdr pages */
-	head->arg.page_base = 0;
-	head->arg.page_len = ch_bytes;
-	head->arg.len = rqstp->rq_arg.len + ch_bytes;
-	head->arg.buflen = rqstp->rq_arg.buflen + ch_bytes;
-	head->count++;
-	chl_map->ch[0].start = 0;
-	while (byte_count) {
-		rpl_map->sge[sge_no].iov_base =
-			page_address(rqstp->rq_arg.pages[page_no]) + page_off;
-		sge_bytes = min_t(int, PAGE_SIZE-page_off, ch_bytes);
-		rpl_map->sge[sge_no].iov_len = sge_bytes;
-		/*
-		 * Don't bump head->count here because the same page
-		 * may be used by multiple SGE.
-		 */
-		head->arg.pages[page_no] = rqstp->rq_arg.pages[page_no];
-		rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1];
+typedef int (*rdma_reader_fn)(struct svcxprt_rdma *xprt,
+			      struct svc_rqst *rqstp,
+			      struct svc_rdma_op_ctxt *head,
+			      int *page_no,
+			      u32 *page_offset,
+			      u32 rs_handle,
+			      u32 rs_length,
+			      u64 rs_offset,
+			      int last);
+
+/* Issue an RDMA_READ using the local lkey to map the data sink */
+static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
+			       struct svc_rqst *rqstp,
+			       struct svc_rdma_op_ctxt *head,
+			       int *page_no,
+			       u32 *page_offset,
+			       u32 rs_handle,
+			       u32 rs_length,
+			       u64 rs_offset,
+			       int last)
+{
+	struct ib_send_wr read_wr;
+	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
+	struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
+	int ret, read, pno;
+	u32 pg_off = *page_offset;
+	u32 pg_no = *page_no;
+
+	ctxt->direction = DMA_FROM_DEVICE;
+	ctxt->read_hdr = head;
+	pages_needed =
+		min_t(int, pages_needed, rdma_read_max_sge(xprt, pages_needed));
+	read = min_t(int, pages_needed << PAGE_SHIFT, rs_length);
+
+	for (pno = 0; pno < pages_needed; pno++) {
+		int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
+
+		head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no];
+		head->arg.page_len += len;
+		head->arg.len += len;
+		if (!pg_off)
+			head->count++;
+		rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
 		rqstp->rq_next_page = rqstp->rq_respages + 1;
+		ctxt->sge[pno].addr =
+			ib_dma_map_page(xprt->sc_cm_id->device,
+					head->arg.pages[pg_no], pg_off,
+					PAGE_SIZE - pg_off,
+					DMA_FROM_DEVICE);
+		ret = ib_dma_mapping_error(xprt->sc_cm_id->device,
+					   ctxt->sge[pno].addr);
+		if (ret)
+			goto err;
+		atomic_inc(&xprt->sc_dma_used);
 
-		byte_count -= sge_bytes;
-		ch_bytes -= sge_bytes;
-		sge_no++;
-		/*
-		 * If all bytes for this chunk have been mapped to an
-		 * SGE, move to the next SGE
-		 */
-		if (ch_bytes == 0) {
-			chl_map->ch[ch_no].count =
-				sge_no - chl_map->ch[ch_no].start;
-			ch_no++;
-			ch++;
-			chl_map->ch[ch_no].start = sge_no;
-			ch_bytes = ntohl(ch->rc_target.rs_length);
-			/* If bytes remaining account for next chunk */
-			if (byte_count) {
-				head->arg.page_len += ch_bytes;
-				head->arg.len += ch_bytes;
-				head->arg.buflen += ch_bytes;
-			}
+		/* The lkey here is either a local dma lkey or a dma_mr lkey */
+		ctxt->sge[pno].lkey = xprt->sc_dma_lkey;
+		ctxt->sge[pno].length = len;
+		ctxt->count++;
+
+		/* adjust offset and wrap to next page if needed */
+		pg_off += len;
+		if (pg_off == PAGE_SIZE) {
+			pg_off = 0;
+			pg_no++;
 		}
-		/*
-		 * If this SGE consumed all of the page, move to the
-		 * next page
-		 */
-		if ((sge_bytes + page_off) == PAGE_SIZE) {
-			page_no++;
-			page_off = 0;
-			/*
-			 * If there are still bytes left to map, bump
-			 * the page count
-			 */
-			if (byte_count)
-				head->count++;
-		} else
-			page_off += sge_bytes;
+		rs_length -= len;
 	}
-	BUG_ON(byte_count != 0);
-	return sge_no;
+
+	if (last && rs_length == 0)
+		set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
+	else
+		clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
+
+	memset(&read_wr, 0, sizeof(read_wr));
+	read_wr.wr_id = (unsigned long)ctxt;
+	read_wr.opcode = IB_WR_RDMA_READ;
+	ctxt->wr_op = read_wr.opcode;
+	read_wr.send_flags = IB_SEND_SIGNALED;
+	read_wr.wr.rdma.rkey = rs_handle;
+	read_wr.wr.rdma.remote_addr = rs_offset;
+	read_wr.sg_list = ctxt->sge;
+	read_wr.num_sge = pages_needed;
+
+	ret = svc_rdma_send(xprt, &read_wr);
+	if (ret) {
+		pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
+		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+		goto err;
+	}
+
+	/* return current location in page array */
+	*page_no = pg_no;
+	*page_offset = pg_off;
+	ret = read;
+	atomic_inc(&rdma_stat_read);
+	return ret;
+ err:
+	svc_rdma_unmap_dma(ctxt);
+	svc_rdma_put_context(ctxt, 0);
+	return ret;
 }
 
-/* Map a read-chunk-list to an XDR and fast register the page-list.
- *
- * Assumptions:
- * - chunk[0]	position points to pages[0] at an offset of 0
- * - pages[]	will be made physically contiguous by creating a one-off memory
- *		region using the fastreg verb.
- * - byte_count is # of bytes in read-chunk-list
- * - ch_count	is # of chunks in read-chunk-list
- *
- * Output:
- * - sge array pointing into pages[] array.
- * - chunk_sge array specifying sge index and count for each
- *   chunk in the read list
- */
-static int fast_reg_read_chunks(struct svcxprt_rdma *xprt,
+/* Issue an RDMA_READ using an FRMR to map the data sink */
+static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
 				struct svc_rqst *rqstp,
 				struct svc_rdma_op_ctxt *head,
-				struct rpcrdma_msg *rmsgp,
-				struct svc_rdma_req_map *rpl_map,
-				struct svc_rdma_req_map *chl_map,
-				int ch_count,
-				int byte_count)
+				int *page_no,
+				u32 *page_offset,
+				u32 rs_handle,
+				u32 rs_length,
+				u64 rs_offset,
+				int last)
 {
-	int page_no;
-	int ch_no;
-	u32 offset;
-	struct rpcrdma_read_chunk *ch;
-	struct svc_rdma_fastreg_mr *frmr;
-	int ret = 0;
+	struct ib_send_wr read_wr;
+	struct ib_send_wr inv_wr;
+	struct ib_send_wr fastreg_wr;
+	u8 key;
+	int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
+	struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
+	struct svc_rdma_fastreg_mr *frmr = svc_rdma_get_frmr(xprt);
+	int ret, read, pno;
+	u32 pg_off = *page_offset;
+	u32 pg_no = *page_no;
 
-	frmr = svc_rdma_get_frmr(xprt);
 	if (IS_ERR(frmr))
 		return -ENOMEM;
 
-	head->frmr = frmr;
-	head->arg.head[0] = rqstp->rq_arg.head[0];
-	head->arg.tail[0] = rqstp->rq_arg.tail[0];
-	head->arg.pages = &head->pages[head->count];
-	head->hdr_count = head->count; /* save count of hdr pages */
-	head->arg.page_base = 0;
-	head->arg.page_len = byte_count;
-	head->arg.len = rqstp->rq_arg.len + byte_count;
-	head->arg.buflen = rqstp->rq_arg.buflen + byte_count;
+	ctxt->direction = DMA_FROM_DEVICE;
+	ctxt->frmr = frmr;
+	pages_needed = min_t(int, pages_needed, xprt->sc_frmr_pg_list_len);
+	read = min_t(int, pages_needed << PAGE_SHIFT, rs_length);
 
-	/* Fast register the page list */
-	frmr->kva = page_address(rqstp->rq_arg.pages[0]);
+	frmr->kva = page_address(rqstp->rq_arg.pages[pg_no]);
 	frmr->direction = DMA_FROM_DEVICE;
 	frmr->access_flags = (IB_ACCESS_LOCAL_WRITE|IB_ACCESS_REMOTE_WRITE);
-	frmr->map_len = byte_count;
-	frmr->page_list_len = PAGE_ALIGN(byte_count) >> PAGE_SHIFT;
-	for (page_no = 0; page_no < frmr->page_list_len; page_no++) {
-		frmr->page_list->page_list[page_no] =
+	frmr->map_len = pages_needed << PAGE_SHIFT;
+	frmr->page_list_len = pages_needed;
+
+	for (pno = 0; pno < pages_needed; pno++) {
+		int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
+
+		head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no];
+		head->arg.page_len += len;
+		head->arg.len += len;
+		if (!pg_off)
+			head->count++;
+		rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
+		rqstp->rq_next_page = rqstp->rq_respages + 1;
+		frmr->page_list->page_list[pno] =
 			ib_dma_map_page(xprt->sc_cm_id->device,
-					rqstp->rq_arg.pages[page_no], 0,
+					head->arg.pages[pg_no], 0,
 					PAGE_SIZE, DMA_FROM_DEVICE);
-		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-					 frmr->page_list->page_list[page_no]))
-			goto fatal_err;
+		ret = ib_dma_mapping_error(xprt->sc_cm_id->device,
+					   frmr->page_list->page_list[pno]);
+		if (ret)
+			goto err;
 		atomic_inc(&xprt->sc_dma_used);
-		head->arg.pages[page_no] = rqstp->rq_arg.pages[page_no];
-	}
-	head->count += page_no;
-
-	/* rq_respages points one past arg pages */
-	rqstp->rq_respages = &rqstp->rq_arg.pages[page_no];
-	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
-	/* Create the reply and chunk maps */
-	offset = 0;
-	ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-	for (ch_no = 0; ch_no < ch_count; ch_no++) {
-		int len = ntohl(ch->rc_target.rs_length);
-		rpl_map->sge[ch_no].iov_base = frmr->kva + offset;
-		rpl_map->sge[ch_no].iov_len = len;
-		chl_map->ch[ch_no].count = 1;
-		chl_map->ch[ch_no].start = ch_no;
-		offset += len;
-		ch++;
+		/* adjust offset and wrap to next page if needed */
+		pg_off += len;
+		if (pg_off == PAGE_SIZE) {
+			pg_off = 0;
+			pg_no++;
+		}
+		rs_length -= len;
 	}
 
-	ret = svc_rdma_fastreg(xprt, frmr);
-	if (ret)
-		goto fatal_err;
-
-	return ch_no;
-
- fatal_err:
-	printk("svcrdma: error fast registering xdr for xprt %p", xprt);
-	svc_rdma_put_frmr(xprt, frmr);
-	return -EIO;
-}
-
-static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt,
-			     struct svc_rdma_op_ctxt *ctxt,
-			     struct svc_rdma_fastreg_mr *frmr,
-			     struct kvec *vec,
-			     u64 *sgl_offset,
-			     int count)
-{
-	int i;
-	unsigned long off;
+	if (last && rs_length == 0)
+		set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
+	else
+		clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
 
-	ctxt->count = count;
-	ctxt->direction = DMA_FROM_DEVICE;
-	for (i = 0; i < count; i++) {
-		ctxt->sge[i].length = 0; /* in case map fails */
-		if (!frmr) {
-			BUG_ON(!virt_to_page(vec[i].iov_base));
-			off = (unsigned long)vec[i].iov_base & ~PAGE_MASK;
-			ctxt->sge[i].addr =
-				ib_dma_map_page(xprt->sc_cm_id->device,
-						virt_to_page(vec[i].iov_base),
-						off,
-						vec[i].iov_len,
-						DMA_FROM_DEVICE);
-			if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-						 ctxt->sge[i].addr))
-				return -EINVAL;
-			ctxt->sge[i].lkey = xprt->sc_dma_lkey;
-			atomic_inc(&xprt->sc_dma_used);
-		} else {
-			ctxt->sge[i].addr = (unsigned long)vec[i].iov_base;
-			ctxt->sge[i].lkey = frmr->mr->lkey;
-		}
-		ctxt->sge[i].length = vec[i].iov_len;
-		*sgl_offset = *sgl_offset + vec[i].iov_len;
+	/* Bump the key */
+	key = (u8)(frmr->mr->lkey & 0x000000FF);
+	ib_update_fast_reg_key(frmr->mr, ++key);
+
+	ctxt->sge[0].addr = (unsigned long)frmr->kva + *page_offset;
+	ctxt->sge[0].lkey = frmr->mr->lkey;
+	ctxt->sge[0].length = read;
+	ctxt->count = 1;
+	ctxt->read_hdr = head;
+
+	/* Prepare FASTREG WR */
+	memset(&fastreg_wr, 0, sizeof(fastreg_wr));
+	fastreg_wr.opcode = IB_WR_FAST_REG_MR;
+	fastreg_wr.send_flags = IB_SEND_SIGNALED;
+	fastreg_wr.wr.fast_reg.iova_start = (unsigned long)frmr->kva;
+	fastreg_wr.wr.fast_reg.page_list = frmr->page_list;
+	fastreg_wr.wr.fast_reg.page_list_len = frmr->page_list_len;
+	fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
+	fastreg_wr.wr.fast_reg.length = frmr->map_len;
+	fastreg_wr.wr.fast_reg.access_flags = frmr->access_flags;
+	fastreg_wr.wr.fast_reg.rkey = frmr->mr->lkey;
+	fastreg_wr.next = &read_wr;
+
+	/* Prepare RDMA_READ */
+	memset(&read_wr, 0, sizeof(read_wr));
+	read_wr.send_flags = IB_SEND_SIGNALED;
+	read_wr.wr.rdma.rkey = rs_handle;
+	read_wr.wr.rdma.remote_addr = rs_offset;
+	read_wr.sg_list = ctxt->sge;
+	read_wr.num_sge = 1;
+	if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_READ_W_INV) {
+		read_wr.opcode = IB_WR_RDMA_READ_WITH_INV;
+		read_wr.wr_id = (unsigned long)ctxt;
+		read_wr.ex.invalidate_rkey = ctxt->frmr->mr->lkey;
+	} else {
+		read_wr.opcode = IB_WR_RDMA_READ;
+		read_wr.next = &inv_wr;
+		/* Prepare invalidate */
+		memset(&inv_wr, 0, sizeof(inv_wr));
+		inv_wr.wr_id = (unsigned long)ctxt;
+		inv_wr.opcode = IB_WR_LOCAL_INV;
+		inv_wr.send_flags = IB_SEND_SIGNALED | IB_SEND_FENCE;
+		inv_wr.ex.invalidate_rkey = frmr->mr->lkey;
+	}
+	ctxt->wr_op = read_wr.opcode;
+
+	/* Post the chain */
+	ret = svc_rdma_send(xprt, &fastreg_wr);
+	if (ret) {
+		pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
+		set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+		goto err;
 	}
-	return 0;
-}
 
-static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count)
-{
-	if ((rdma_node_get_transport(xprt->sc_cm_id->device->node_type) ==
-	     RDMA_TRANSPORT_IWARP) &&
-	    sge_count > 1)
-		return 1;
-	else
-		return min_t(int, sge_count, xprt->sc_max_sge);
+	/* return current location in page array */
+	*page_no = pg_no;
+	*page_offset = pg_off;
+	ret = read;
+	atomic_inc(&rdma_stat_read);
+	return ret;
+ err:
+	svc_rdma_unmap_dma(ctxt);
+	svc_rdma_put_context(ctxt, 0);
+	svc_rdma_put_frmr(xprt, frmr);
+	return ret;
 }
 
-/*
- * Use RDMA_READ to read data from the advertised client buffer into the
- * XDR stream starting at rq_arg.head[0].iov_base.
- * Each chunk in the array
- * contains the following fields:
- * discrim      - '1', This isn't used for data placement
- * position     - The xdr stream offset (the same for every chunk)
- * handle       - RMR for client memory region
- * length       - data transfer length
- * offset       - 64 bit tagged offset in remote memory region
- *
- * On our side, we need to read into a pagelist. The first page immediately
- * follows the RPC header.
- *
- * This function returns:
- * 0 - No error and no read-list found.
- *
- * 1 - Successful read-list processing. The data is not yet in
- * the pagelist and therefore the RPC request must be deferred. The
- * I/O completion will enqueue the transport again and
- * svc_rdma_recvfrom will complete the request.
- *
- * <0 - Error processing/posting read-list.
- *
- * NOTE: The ctxt must not be touched after the last WR has been posted
- * because the I/O completion processing may occur on another
- * processor and free / modify the context. Ne touche pas!
- */
-static int rdma_read_xdr(struct svcxprt_rdma *xprt,
-			 struct rpcrdma_msg *rmsgp,
-			 struct svc_rqst *rqstp,
-			 struct svc_rdma_op_ctxt *hdr_ctxt)
+static int rdma_read_chunks(struct svcxprt_rdma *xprt,
+			    struct rpcrdma_msg *rmsgp,
+			    struct svc_rqst *rqstp,
+			    struct svc_rdma_op_ctxt *head)
 {
-	struct ib_send_wr read_wr;
-	struct ib_send_wr inv_wr;
-	int err = 0;
-	int ch_no;
-	int ch_count;
-	int byte_count;
-	int sge_count;
-	u64 sgl_offset;
+	int page_no, ch_count, ret;
 	struct rpcrdma_read_chunk *ch;
-	struct svc_rdma_op_ctxt *ctxt = NULL;
-	struct svc_rdma_req_map *rpl_map;
-	struct svc_rdma_req_map *chl_map;
+	u32 page_offset, byte_count;
+	u64 rs_offset;
+	rdma_reader_fn reader;
 
 	/* If no read list is present, return 0 */
 	ch = svc_rdma_get_read_chunk(rmsgp);
@@ -408,122 +384,55 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt,
 	if (ch_count > RPCSVC_MAXPAGES)
 		return -EINVAL;
 
-	/* Allocate temporary reply and chunk maps */
-	rpl_map = svc_rdma_get_req_map();
-	chl_map = svc_rdma_get_req_map();
+	/* The request is completed when the RDMA_READs complete. The
+	 * head context keeps all the pages that comprise the
+	 * request.
+	 */
+	head->arg.head[0] = rqstp->rq_arg.head[0];
+	head->arg.tail[0] = rqstp->rq_arg.tail[0];
+	head->arg.pages = &head->pages[head->count];
+	head->hdr_count = head->count;
+	head->arg.page_base = 0;
+	head->arg.page_len = 0;
+	head->arg.len = rqstp->rq_arg.len;
+	head->arg.buflen = rqstp->rq_arg.buflen;
 
-	if (!xprt->sc_frmr_pg_list_len)
-		sge_count = map_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp,
-					    rpl_map, chl_map, ch_count,
-					    byte_count);
+	/* Use FRMR if supported */
+	if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)
+		reader = rdma_read_chunk_frmr;
 	else
-		sge_count = fast_reg_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp,
-						 rpl_map, chl_map, ch_count,
-						 byte_count);
-	if (sge_count < 0) {
-		err = -EIO;
-		goto out;
-	}
-
-	sgl_offset = 0;
-	ch_no = 0;
+		reader = rdma_read_chunk_lcl;
 
+	page_no = 0; page_offset = 0;
 	for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
-	     ch->rc_discrim != 0; ch++, ch_no++) {
-		u64 rs_offset;
-next_sge:
-		ctxt = svc_rdma_get_context(xprt);
-		ctxt->direction = DMA_FROM_DEVICE;
-		ctxt->frmr = hdr_ctxt->frmr;
-		ctxt->read_hdr = NULL;
-		clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
-		clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
+	     ch->rc_discrim != 0; ch++) {
 
-		/* Prepare READ WR */
-		memset(&read_wr, 0, sizeof read_wr);
-		read_wr.wr_id = (unsigned long)ctxt;
-		read_wr.opcode = IB_WR_RDMA_READ;
-		ctxt->wr_op = read_wr.opcode;
-		read_wr.send_flags = IB_SEND_SIGNALED;
-		read_wr.wr.rdma.rkey = ntohl(ch->rc_target.rs_handle);
 		xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
 				 &rs_offset);
-		read_wr.wr.rdma.remote_addr = rs_offset + sgl_offset;
-		read_wr.sg_list = ctxt->sge;
-		read_wr.num_sge =
-			rdma_read_max_sge(xprt, chl_map->ch[ch_no].count);
-		err = rdma_set_ctxt_sge(xprt, ctxt, hdr_ctxt->frmr,
-					&rpl_map->sge[chl_map->ch[ch_no].start],
-					&sgl_offset,
-					read_wr.num_sge);
-		if (err) {
-			svc_rdma_unmap_dma(ctxt);
-			svc_rdma_put_context(ctxt, 0);
-			goto out;
-		}
-		if (((ch+1)->rc_discrim == 0) &&
-		    (read_wr.num_sge == chl_map->ch[ch_no].count)) {
-			/*
-			 * Mark the last RDMA_READ with a bit to
-			 * indicate all RPC data has been fetched from
-			 * the client and the RPC needs to be enqueued.
-			 */
-			set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
-			if (hdr_ctxt->frmr) {
-				set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
-				/*
-				 * Invalidate the local MR used to map the data
-				 * sink.
-				 */
-				if (xprt->sc_dev_caps &
-				    SVCRDMA_DEVCAP_READ_W_INV) {
-					read_wr.opcode =
-						IB_WR_RDMA_READ_WITH_INV;
-					ctxt->wr_op = read_wr.opcode;
-					read_wr.ex.invalidate_rkey =
-						ctxt->frmr->mr->lkey;
-				} else {
-					/* Prepare INVALIDATE WR */
-					memset(&inv_wr, 0, sizeof inv_wr);
-					inv_wr.opcode = IB_WR_LOCAL_INV;
-					inv_wr.send_flags = IB_SEND_SIGNALED;
-					inv_wr.ex.invalidate_rkey =
-						hdr_ctxt->frmr->mr->lkey;
-					read_wr.next = &inv_wr;
-				}
-			}
-			ctxt->read_hdr = hdr_ctxt;
-		}
-		/* Post the read */
-		err = svc_rdma_send(xprt, &read_wr);
-		if (err) {
-			printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n",
-			       err);
-			set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
-			svc_rdma_unmap_dma(ctxt);
-			svc_rdma_put_context(ctxt, 0);
-			goto out;
+		byte_count = ntohl(ch->rc_target.rs_length);
+
+		while (byte_count > 0) {
+			ret = reader(xprt, rqstp, head,
+				     &page_no, &page_offset,
+				     ntohl(ch->rc_target.rs_handle),
+				     byte_count, rs_offset,
+				     ((ch+1)->rc_discrim == 0) /* last */
+				     );
+			if (ret < 0)
+				goto err;
+			byte_count -= ret;
+			rs_offset += ret;
+			head->arg.buflen += ret;
 		}
-		atomic_inc(&rdma_stat_read);
-
-		if (read_wr.num_sge < chl_map->ch[ch_no].count) {
-			chl_map->ch[ch_no].count -= read_wr.num_sge;
-			chl_map->ch[ch_no].start += read_wr.num_sge;
-			goto next_sge;
-		}
-		sgl_offset = 0;
-		err = 1;
 	}
-
- out:
-	svc_rdma_put_req_map(rpl_map);
-	svc_rdma_put_req_map(chl_map);
-
+	ret = 1;
+ err:
 	/* Detach arg pages. svc_recv will replenish them */
-	for (ch_no = 0; &rqstp->rq_pages[ch_no] < rqstp->rq_respages; ch_no++)
-		rqstp->rq_pages[ch_no] = NULL;
+	for (page_no = 0;
+	     &rqstp->rq_pages[page_no] < rqstp->rq_respages; page_no++)
+		rqstp->rq_pages[page_no] = NULL;
 
-	return err;
+	return ret;
 }
 
 static int rdma_read_complete(struct svc_rqst *rqstp,
@@ -595,13 +504,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 				  struct svc_rdma_op_ctxt,
 				  dto_q);
 		list_del_init(&ctxt->dto_q);
-	}
-	if (ctxt) {
 		spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock);
 		return rdma_read_complete(rqstp, ctxt);
-	}
-
-	if (!list_empty(&rdma_xprt->sc_rq_dto_q)) {
+	} else if (!list_empty(&rdma_xprt->sc_rq_dto_q)) {
 		ctxt = list_entry(rdma_xprt->sc_rq_dto_q.next,
 				  struct svc_rdma_op_ctxt,
 				  dto_q);
@@ -621,7 +526,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		if (test_bit(XPT_CLOSE, &xprt->xpt_flags))
 			goto close_out;
 
-		BUG_ON(ret);
 		goto out;
 	}
 	dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p, status=%d\n",
@@ -644,12 +548,11 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	}
 
 	/* Read read-list data. */
-	ret = rdma_read_xdr(rdma_xprt, rmsgp, rqstp, ctxt);
+	ret = rdma_read_chunks(rdma_xprt, rmsgp, rqstp, ctxt);
 	if (ret > 0) {
 		/* read-list posted, defer until data received from client. */
 		goto defer;
-	}
-	if (ret < 0) {
+	} else if (ret < 0) {
 		/* Post of read-list failed, free context. */
 		svc_rdma_put_context(ctxt, 1);
 		return 0;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 7e024a51617..49fd21a5c21 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved.
  * Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -49,152 +50,6 @@
 
 #define RPCDBG_FACILITY	RPCDBG_SVCXPRT
 
-/* Encode an XDR as an array of IB SGE
- *
- * Assumptions:
- * - head[0] is physically contiguous.
- * - tail[0] is physically contiguous.
- * - pages[] is not physically or virtually contiguous and consists of
- *   PAGE_SIZE elements.
- *
- * Output:
- * SGE[0]              reserved for RCPRDMA header
- * SGE[1]              data from xdr->head[]
- * SGE[2..sge_count-2] data from xdr->pages[]
- * SGE[sge_count-1]    data from xdr->tail.
- *
- * The max SGE we need is the length of the XDR / pagesize + one for
- * head + one for tail + one for RPCRDMA header. Since RPCSVC_MAXPAGES
- * reserves a page for both the request and the reply header, and this
- * array is only concerned with the reply we are assured that we have
- * on extra page for the RPCRMDA header.
- */
-static int fast_reg_xdr(struct svcxprt_rdma *xprt,
-			struct xdr_buf *xdr,
-			struct svc_rdma_req_map *vec)
-{
-	int sge_no;
-	u32 sge_bytes;
-	u32 page_bytes;
-	u32 page_off;
-	int page_no = 0;
-	u8 *frva;
-	struct svc_rdma_fastreg_mr *frmr;
-
-	frmr = svc_rdma_get_frmr(xprt);
-	if (IS_ERR(frmr))
-		return -ENOMEM;
-	vec->frmr = frmr;
-
-	/* Skip the RPCRDMA header */
-	sge_no = 1;
-
-	/* Map the head. */
-	frva = (void *)((unsigned long)(xdr->head[0].iov_base) & PAGE_MASK);
-	vec->sge[sge_no].iov_base = xdr->head[0].iov_base;
-	vec->sge[sge_no].iov_len = xdr->head[0].iov_len;
-	vec->count = 2;
-	sge_no++;
-
-	/* Map the XDR head */
-	frmr->kva = frva;
-	frmr->direction = DMA_TO_DEVICE;
-	frmr->access_flags = 0;
-	frmr->map_len = PAGE_SIZE;
-	frmr->page_list_len = 1;
-	page_off = (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK;
-	frmr->page_list->page_list[page_no] =
-		ib_dma_map_page(xprt->sc_cm_id->device,
-				virt_to_page(xdr->head[0].iov_base),
-				page_off,
-				PAGE_SIZE - page_off,
-				DMA_TO_DEVICE);
-	if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-				 frmr->page_list->page_list[page_no]))
-		goto fatal_err;
-	atomic_inc(&xprt->sc_dma_used);
-
-	/* Map the XDR page list */
-	page_off = xdr->page_base;
-	page_bytes = xdr->page_len + page_off;
-	if (!page_bytes)
-		goto encode_tail;
-
-	/* Map the pages */
-	vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off;
-	vec->sge[sge_no].iov_len = page_bytes;
-	sge_no++;
-	while (page_bytes) {
-		struct page *page;
-
-		page = xdr->pages[page_no++];
-		sge_bytes = min_t(u32, page_bytes, (PAGE_SIZE - page_off));
-		page_bytes -= sge_bytes;
-
-		frmr->page_list->page_list[page_no] =
-			ib_dma_map_page(xprt->sc_cm_id->device,
-					page, page_off,
-					sge_bytes, DMA_TO_DEVICE);
-		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-					 frmr->page_list->page_list[page_no]))
-			goto fatal_err;
-
-		atomic_inc(&xprt->sc_dma_used);
-		page_off = 0; /* reset for next time through loop */
-		frmr->map_len += PAGE_SIZE;
-		frmr->page_list_len++;
-	}
-	vec->count++;
-
- encode_tail:
-	/* Map tail */
-	if (0 == xdr->tail[0].iov_len)
-		goto done;
-
-	vec->count++;
-	vec->sge[sge_no].iov_len = xdr->tail[0].iov_len;
-
-	if (((unsigned long)xdr->tail[0].iov_base & PAGE_MASK) ==
-	    ((unsigned long)xdr->head[0].iov_base & PAGE_MASK)) {
-		/*
-		 * If head and tail use the same page, we don't need
-		 * to map it again.
-		 */
-		vec->sge[sge_no].iov_base = xdr->tail[0].iov_base;
-	} else {
-		void *va;
-
-		/* Map another page for the tail */
-		page_off = (unsigned long)xdr->tail[0].iov_base & ~PAGE_MASK;
-		va = (void *)((unsigned long)xdr->tail[0].iov_base & PAGE_MASK);
-		vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off;
-
-		frmr->page_list->page_list[page_no] =
-		    ib_dma_map_page(xprt->sc_cm_id->device, virt_to_page(va),
-				    page_off,
-				    PAGE_SIZE,
-				    DMA_TO_DEVICE);
-		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-					 frmr->page_list->page_list[page_no]))
-			goto fatal_err;
-		atomic_inc(&xprt->sc_dma_used);
-		frmr->map_len += PAGE_SIZE;
-		frmr->page_list_len++;
-	}
-
- done:
-	if (svc_rdma_fastreg(xprt, frmr))
-		goto fatal_err;
-
-	return 0;
-
- fatal_err:
-	printk("svcrdma: Error fast registering memory for xprt %p\n", xprt);
-	vec->frmr = NULL;
-	svc_rdma_put_frmr(xprt, frmr);
-	return -EIO;
-}
-
 static int map_xdr(struct svcxprt_rdma *xprt,
 		   struct xdr_buf *xdr,
 		   struct svc_rdma_req_map *vec)
@@ -208,9 +63,6 @@ static int map_xdr(struct svcxprt_rdma *xprt,
 	BUG_ON(xdr->len !=
 	       (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len));
 
-	if (xprt->sc_frmr_pg_list_len)
-		return fast_reg_xdr(xprt, xdr, vec);
-
 	/* Skip the first sge, this is for the RPCRDMA header */
 	sge_no = 1;
 
@@ -282,8 +134,6 @@ static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt,
 }
 
 /* Assumptions:
- * - We are using FRMR
- *     - or -
  * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE
  */
 static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
@@ -327,23 +177,16 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 		sge_bytes = min_t(size_t,
 			  bc, vec->sge[xdr_sge_no].iov_len-sge_off);
 		sge[sge_no].length = sge_bytes;
-		if (!vec->frmr) {
-			sge[sge_no].addr =
-				dma_map_xdr(xprt, &rqstp->rq_res, xdr_off,
-					    sge_bytes, DMA_TO_DEVICE);
-			xdr_off += sge_bytes;
-			if (ib_dma_mapping_error(xprt->sc_cm_id->device,
-						 sge[sge_no].addr))
-				goto err;
-			atomic_inc(&xprt->sc_dma_used);
-			sge[sge_no].lkey = xprt->sc_dma_lkey;
-		} else {
-			sge[sge_no].addr = (unsigned long)
-				vec->sge[xdr_sge_no].iov_base + sge_off;
-			sge[sge_no].lkey = vec->frmr->mr->lkey;
-		}
+		sge[sge_no].addr =
+			dma_map_xdr(xprt, &rqstp->rq_res, xdr_off,
+				    sge_bytes, DMA_TO_DEVICE);
+		xdr_off += sge_bytes;
+		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
+					 sge[sge_no].addr))
+			goto err;
+		atomic_inc(&xprt->sc_dma_used);
+		sge[sge_no].lkey = xprt->sc_dma_lkey;
 		ctxt->count++;
-		ctxt->frmr = vec->frmr;
 		sge_off = 0;
 		sge_no++;
 		xdr_sge_no++;
@@ -369,7 +212,6 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 	return 0;
  err:
 	svc_rdma_unmap_dma(ctxt);
-	svc_rdma_put_frmr(xprt, vec->frmr);
 	svc_rdma_put_context(ctxt, 0);
 	/* Fatal error, close transport */
 	return -EIO;
@@ -397,10 +239,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt,
 	res_ary = (struct rpcrdma_write_array *)
 		&rdma_resp->rm_body.rm_chunks[1];
 
-	if (vec->frmr)
-		max_write = vec->frmr->map_len;
-	else
-		max_write = xprt->sc_max_sge * PAGE_SIZE;
+	max_write = xprt->sc_max_sge * PAGE_SIZE;
 
 	/* Write chunks start at the pagelist */
 	for (xdr_off = rqstp->rq_res.head[0].iov_len, chunk_no = 0;
@@ -472,10 +311,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt,
 	res_ary = (struct rpcrdma_write_array *)
 		&rdma_resp->rm_body.rm_chunks[2];
 
-	if (vec->frmr)
-		max_write = vec->frmr->map_len;
-	else
-		max_write = xprt->sc_max_sge * PAGE_SIZE;
+	max_write = xprt->sc_max_sge * PAGE_SIZE;
 
 	/* xdr offset starts at RPC message */
 	nchunks = ntohl(arg_ary->wc_nchunks);
@@ -545,7 +381,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		      int byte_count)
 {
 	struct ib_send_wr send_wr;
-	struct ib_send_wr inv_wr;
 	int sge_no;
 	int sge_bytes;
 	int page_no;
@@ -559,7 +394,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		       "svcrdma: could not post a receive buffer, err=%d."
 		       "Closing transport %p.\n", ret, rdma);
 		set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
-		svc_rdma_put_frmr(rdma, vec->frmr);
 		svc_rdma_put_context(ctxt, 0);
 		return -ENOTCONN;
 	}
@@ -567,11 +401,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	/* Prepare the context */
 	ctxt->pages[0] = page;
 	ctxt->count = 1;
-	ctxt->frmr = vec->frmr;
-	if (vec->frmr)
-		set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
-	else
-		clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
 
 	/* Prepare the SGE for the RPCRDMA Header */
 	ctxt->sge[0].lkey = rdma->sc_dma_lkey;
@@ -590,21 +419,15 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		int xdr_off = 0;
 		sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
 		byte_count -= sge_bytes;
-		if (!vec->frmr) {
-			ctxt->sge[sge_no].addr =
-				dma_map_xdr(rdma, &rqstp->rq_res, xdr_off,
-					    sge_bytes, DMA_TO_DEVICE);
-			xdr_off += sge_bytes;
-			if (ib_dma_mapping_error(rdma->sc_cm_id->device,
-						 ctxt->sge[sge_no].addr))
-				goto err;
-			atomic_inc(&rdma->sc_dma_used);
-			ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey;
-		} else {
-			ctxt->sge[sge_no].addr = (unsigned long)
-				vec->sge[sge_no].iov_base;
-			ctxt->sge[sge_no].lkey = vec->frmr->mr->lkey;
-		}
+		ctxt->sge[sge_no].addr =
+			dma_map_xdr(rdma, &rqstp->rq_res, xdr_off,
+				    sge_bytes, DMA_TO_DEVICE);
+		xdr_off += sge_bytes;
+		if (ib_dma_mapping_error(rdma->sc_cm_id->device,
+					 ctxt->sge[sge_no].addr))
+			goto err;
+		atomic_inc(&rdma->sc_dma_used);
+		ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey;
 		ctxt->sge[sge_no].length = sge_bytes;
 	}
 	BUG_ON(byte_count != 0);
@@ -627,6 +450,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
 			ctxt->sge[page_no+1].length = 0;
 	}
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
+
 	BUG_ON(sge_no > rdma->sc_max_sge);
 	memset(&send_wr, 0, sizeof send_wr);
 	ctxt->wr_op = IB_WR_SEND;
@@ -635,15 +459,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	send_wr.num_sge = sge_no;
 	send_wr.opcode = IB_WR_SEND;
 	send_wr.send_flags =  IB_SEND_SIGNALED;
-	if (vec->frmr) {
-		/* Prepare INVALIDATE WR */
-		memset(&inv_wr, 0, sizeof inv_wr);
-		inv_wr.opcode = IB_WR_LOCAL_INV;
-		inv_wr.send_flags = IB_SEND_SIGNALED;
-		inv_wr.ex.invalidate_rkey =
-			vec->frmr->mr->lkey;
-		send_wr.next = &inv_wr;
-	}
 
 	ret = svc_rdma_send(rdma, &send_wr);
 	if (ret)
@@ -653,7 +468,6 @@ static int send_reply(struct svcxprt_rdma *rdma,
 
  err:
 	svc_rdma_unmap_dma(ctxt);
-	svc_rdma_put_frmr(rdma, vec->frmr);
 	svc_rdma_put_context(ctxt, 1);
 	return -EIO;
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 25688fa2207..e7323fbbd34 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved.
  * Copyright (c) 2005-2007 Network Appliance, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -65,6 +66,7 @@ static void dto_tasklet_func(unsigned long data);
 static void svc_rdma_detach(struct svc_xprt *xprt);
 static void svc_rdma_free(struct svc_xprt *xprt);
 static int svc_rdma_has_wspace(struct svc_xprt *xprt);
+static int svc_rdma_secure_port(struct svc_rqst *);
 static void rq_cq_reap(struct svcxprt_rdma *xprt);
 static void sq_cq_reap(struct svcxprt_rdma *xprt);
 
@@ -82,6 +84,7 @@ static struct svc_xprt_ops svc_rdma_ops = {
 	.xpo_prep_reply_hdr = svc_rdma_prep_reply_hdr,
 	.xpo_has_wspace = svc_rdma_has_wspace,
 	.xpo_accept = svc_rdma_accept,
+	.xpo_secure_port = svc_rdma_secure_port,
 };
 
 struct svc_xprt_class svc_rdma_class = {
@@ -160,7 +163,6 @@ struct svc_rdma_req_map *svc_rdma_get_req_map(void)
 		schedule_timeout_uninterruptible(msecs_to_jiffies(500));
 	}
 	map->count = 0;
-	map->frmr = NULL;
 	return map;
 }
 
@@ -336,22 +338,21 @@ static void process_context(struct svcxprt_rdma *xprt,
 
 	switch (ctxt->wr_op) {
 	case IB_WR_SEND:
-		if (test_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags))
-			svc_rdma_put_frmr(xprt, ctxt->frmr);
+		BUG_ON(ctxt->frmr);
 		svc_rdma_put_context(ctxt, 1);
 		break;
 
 	case IB_WR_RDMA_WRITE:
+		BUG_ON(ctxt->frmr);
 		svc_rdma_put_context(ctxt, 0);
 		break;
 
 	case IB_WR_RDMA_READ:
 	case IB_WR_RDMA_READ_WITH_INV:
+		svc_rdma_put_frmr(xprt, ctxt->frmr);
 		if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) {
 			struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr;
 			BUG_ON(!read_hdr);
-			if (test_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags))
-				svc_rdma_put_frmr(xprt, ctxt->frmr);
 			spin_lock_bh(&xprt->sc_rq_dto_lock);
 			set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags);
 			list_add_tail(&read_hdr->dto_q,
@@ -363,6 +364,7 @@ static void process_context(struct svcxprt_rdma *xprt,
 		break;
 
 	default:
+		BUG_ON(1);
 		printk(KERN_ERR "svcrdma: unexpected completion type, "
 		       "opcode=%d\n",
 		       ctxt->wr_op);
@@ -378,29 +380,42 @@ static void process_context(struct svcxprt_rdma *xprt,
 static void sq_cq_reap(struct svcxprt_rdma *xprt)
 {
 	struct svc_rdma_op_ctxt *ctxt = NULL;
-	struct ib_wc wc;
+	struct ib_wc wc_a[6];
+	struct ib_wc *wc;
 	struct ib_cq *cq = xprt->sc_sq_cq;
 	int ret;
 
+	memset(wc_a, 0, sizeof(wc_a));
+
 	if (!test_and_clear_bit(RDMAXPRT_SQ_PENDING, &xprt->sc_flags))
 		return;
 
 	ib_req_notify_cq(xprt->sc_sq_cq, IB_CQ_NEXT_COMP);
 	atomic_inc(&rdma_stat_sq_poll);
-	while ((ret = ib_poll_cq(cq, 1, &wc)) > 0) {
-		if (wc.status != IB_WC_SUCCESS)
-			/* Close the transport */
-			set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+	while ((ret = ib_poll_cq(cq, ARRAY_SIZE(wc_a), wc_a)) > 0) {
+		int i;
 
-		/* Decrement used SQ WR count */
-		atomic_dec(&xprt->sc_sq_count);
-		wake_up(&xprt->sc_send_wait);
+		for (i = 0; i < ret; i++) {
+			wc = &wc_a[i];
+			if (wc->status != IB_WC_SUCCESS) {
+				dprintk("svcrdma: sq wc err status %d\n",
+					wc->status);
 
-		ctxt = (struct svc_rdma_op_ctxt *)(unsigned long)wc.wr_id;
-		if (ctxt)
-			process_context(xprt, ctxt);
+				/* Close the transport */
+				set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+			}
 
-		svc_xprt_put(&xprt->sc_xprt);
+			/* Decrement used SQ WR count */
+			atomic_dec(&xprt->sc_sq_count);
+			wake_up(&xprt->sc_send_wait);
+
+			ctxt = (struct svc_rdma_op_ctxt *)
+				(unsigned long)wc->wr_id;
+			if (ctxt)
+				process_context(xprt, ctxt);
+
+			svc_xprt_put(&xprt->sc_xprt);
+		}
 	}
 
 	if (ctxt)
@@ -993,7 +1008,11 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 			need_dma_mr = 0;
 		break;
 	case RDMA_TRANSPORT_IB:
-		if (!(devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)) {
+		if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)) {
+			need_dma_mr = 1;
+			dma_mr_acc = IB_ACCESS_LOCAL_WRITE;
+		} else if (!(devattr.device_cap_flags &
+			     IB_DEVICE_LOCAL_DMA_LKEY)) {
 			need_dma_mr = 1;
 			dma_mr_acc = IB_ACCESS_LOCAL_WRITE;
 		} else
@@ -1190,14 +1209,7 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt)
 		container_of(xprt, struct svcxprt_rdma, sc_xprt);
 
 	/*
-	 * If there are fewer SQ WR available than required to send a
-	 * simple response, return false.
-	 */
-	if ((rdma->sc_sq_depth - atomic_read(&rdma->sc_sq_count) < 3))
-		return 0;
-
-	/*
-	 * ...or there are already waiters on the SQ,
+	 * If there are already waiters on the SQ,
 	 * return false.
 	 */
 	if (waitqueue_active(&rdma->sc_send_wait))
@@ -1207,6 +1219,11 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt)
 	return 1;
 }
 
+static int svc_rdma_secure_port(struct svc_rqst *rqstp)
+{
+	return 1;
+}
+
 /*
  * Attempt to register the kvec representing the RPC memory with the
  * device.
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 1eb9c468d0c..66f91f0d071 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -149,6 +149,11 @@ static struct ctl_table sunrpc_table[] = {
 
 #endif
 
+#define RPCRDMA_BIND_TO		(60U * HZ)
+#define RPCRDMA_INIT_REEST_TO	(5U * HZ)
+#define RPCRDMA_MAX_REEST_TO	(30U * HZ)
+#define RPCRDMA_IDLE_DISC_TO	(5U * 60 * HZ)
+
 static struct rpc_xprt_ops xprt_rdma_procs;	/* forward reference */
 
 static void
@@ -229,7 +234,6 @@ static void
 xprt_rdma_destroy(struct rpc_xprt *xprt)
 {
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
-	int rc;
 
 	dprintk("RPC:       %s: called\n", __func__);
 
@@ -238,10 +242,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
 	xprt_clear_connected(xprt);
 
 	rpcrdma_buffer_destroy(&r_xprt->rx_buf);
-	rc = rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia);
-	if (rc)
-		dprintk("RPC:       %s: rpcrdma_ep_destroy returned %i\n",
-			__func__, rc);
+	rpcrdma_ep_destroy(&r_xprt->rx_ep, &r_xprt->rx_ia);
 	rpcrdma_ia_close(&r_xprt->rx_ia);
 
 	xprt_rdma_free_addresses(xprt);
@@ -289,9 +290,9 @@ xprt_setup_rdma(struct xprt_create *args)
 
 	/* 60 second timeout, no retries */
 	xprt->timeout = &xprt_rdma_default_timeout;
-	xprt->bind_timeout = (60U * HZ);
-	xprt->reestablish_timeout = (5U * HZ);
-	xprt->idle_timeout = (5U * 60 * HZ);
+	xprt->bind_timeout = RPCRDMA_BIND_TO;
+	xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
+	xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO;
 
 	xprt->resvport = 0;		/* privileged port not needed */
 	xprt->tsh_size = 0;		/* RPC-RDMA handles framing */
@@ -391,7 +392,7 @@ out4:
 	xprt_rdma_free_addresses(xprt);
 	rc = -EINVAL;
 out3:
-	(void) rpcrdma_ep_destroy(new_ep, &new_xprt->rx_ia);
+	rpcrdma_ep_destroy(new_ep, &new_xprt->rx_ia);
 out2:
 	rpcrdma_ia_close(&new_xprt->rx_ia);
 out1:
@@ -436,10 +437,10 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 		schedule_delayed_work(&r_xprt->rdma_connect,
 			xprt->reestablish_timeout);
 		xprt->reestablish_timeout <<= 1;
-		if (xprt->reestablish_timeout > (30 * HZ))
-			xprt->reestablish_timeout = (30 * HZ);
-		else if (xprt->reestablish_timeout < (5 * HZ))
-			xprt->reestablish_timeout = (5 * HZ);
+		if (xprt->reestablish_timeout > RPCRDMA_MAX_REEST_TO)
+			xprt->reestablish_timeout = RPCRDMA_MAX_REEST_TO;
+		else if (xprt->reestablish_timeout < RPCRDMA_INIT_REEST_TO)
+			xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
 	} else {
 		schedule_delayed_work(&r_xprt->rdma_connect, 0);
 		if (!RPC_IS_ASYNC(task))
@@ -447,23 +448,6 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 	}
 }
 
-static int
-xprt_rdma_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task)
-{
-	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
-	int credits = atomic_read(&r_xprt->rx_buf.rb_credits);
-
-	/* == RPC_CWNDSCALE @ init, but *after* setup */
-	if (r_xprt->rx_buf.rb_cwndscale == 0UL) {
-		r_xprt->rx_buf.rb_cwndscale = xprt->cwnd;
-		dprintk("RPC:       %s: cwndscale %lu\n", __func__,
-			r_xprt->rx_buf.rb_cwndscale);
-		BUG_ON(r_xprt->rx_buf.rb_cwndscale <= 0);
-	}
-	xprt->cwnd = credits * r_xprt->rx_buf.rb_cwndscale;
-	return xprt_reserve_xprt_cong(xprt, task);
-}
-
 /*
  * The RDMA allocate/free functions need the task structure as a place
  * to hide the struct rpcrdma_req, which is necessary for the actual send/recv
@@ -479,7 +463,8 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
 	struct rpcrdma_req *req, *nreq;
 
 	req = rpcrdma_buffer_get(&rpcx_to_rdmax(xprt)->rx_buf);
-	BUG_ON(NULL == req);
+	if (req == NULL)
+		return NULL;
 
 	if (size > req->rl_size) {
 		dprintk("RPC:       %s: size %zd too large for buffer[%zd]: "
@@ -503,18 +488,6 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
 		 * If the allocation or registration fails, the RPC framework
 		 * will (doggedly) retry.
 		 */
-		if (rpcx_to_rdmax(xprt)->rx_ia.ri_memreg_strategy ==
-				RPCRDMA_BOUNCEBUFFERS) {
-			/* forced to "pure inline" */
-			dprintk("RPC:       %s: too much data (%zd) for inline "
-					"(r/w max %d/%d)\n", __func__, size,
-					rpcx_to_rdmad(xprt).inline_rsize,
-					rpcx_to_rdmad(xprt).inline_wsize);
-			size = req->rl_size;
-			rpc_exit(task, -EIO);		/* fail the operation */
-			rpcx_to_rdmax(xprt)->rx_stats.failed_marshal_count++;
-			goto out;
-		}
 		if (task->tk_flags & RPC_TASK_SWAPPER)
 			nreq = kmalloc(sizeof *req + size, GFP_ATOMIC);
 		else
@@ -543,7 +516,6 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
 		req = nreq;
 	}
 	dprintk("RPC:       %s: size %zd, request 0x%p\n", __func__, size, req);
-out:
 	req->rl_connect_cookie = 0;	/* our reserved value */
 	return req->rl_xdr_buf;
 
@@ -579,9 +551,7 @@ xprt_rdma_free(void *buffer)
 		__func__, rep, (rep && rep->rr_func) ? " (with waiter)" : "");
 
 	/*
-	 * Finish the deregistration. When using mw bind, this was
-	 * begun in rpcrdma_reply_handler(). In all other modes, we
-	 * do it here, in thread context. The process is considered
+	 * Finish the deregistration.  The process is considered
 	 * complete when the rr_func vector becomes NULL - this
 	 * was put in place during rpcrdma_reply_handler() - the wait
 	 * call below will not block if the dereg is "done". If
@@ -590,12 +560,7 @@ xprt_rdma_free(void *buffer)
 	for (i = 0; req->rl_nchunks;) {
 		--req->rl_nchunks;
 		i += rpcrdma_deregister_external(
-			&req->rl_segments[i], r_xprt, NULL);
-	}
-
-	if (rep && wait_event_interruptible(rep->rr_unbind, !rep->rr_func)) {
-		rep->rr_func = NULL;	/* abandon the callback */
-		req->rl_reply = NULL;
+			&req->rl_segments[i], r_xprt);
 	}
 
 	if (req->rl_iov.length == 0) {	/* see allocate above */
@@ -630,13 +595,12 @@ xprt_rdma_send_request(struct rpc_task *task)
 	struct rpc_xprt *xprt = rqst->rq_xprt;
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	int rc;
 
-	/* marshal the send itself */
-	if (req->rl_niovs == 0 && rpcrdma_marshal_req(rqst) != 0) {
-		r_xprt->rx_stats.failed_marshal_count++;
-		dprintk("RPC:       %s: rpcrdma_marshal_req failed\n",
-			__func__);
-		return -EIO;
+	if (req->rl_niovs == 0) {
+		rc = rpcrdma_marshal_req(rqst);
+		if (rc < 0)
+			goto failed_marshal;
 	}
 
 	if (req->rl_reply == NULL) 		/* e.g. reconnection */
@@ -660,6 +624,12 @@ xprt_rdma_send_request(struct rpc_task *task)
 	rqst->rq_bytes_sent = 0;
 	return 0;
 
+failed_marshal:
+	r_xprt->rx_stats.failed_marshal_count++;
+	dprintk("RPC:       %s: rpcrdma_marshal_req failed, status %i\n",
+		__func__, rc);
+	if (rc == -EIO)
+		return -EIO;
 drop_connection:
 	xprt_disconnect_done(xprt);
 	return -ENOTCONN;	/* implies disconnect */
@@ -705,7 +675,7 @@ static void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
  */
 
 static struct rpc_xprt_ops xprt_rdma_procs = {
-	.reserve_xprt		= xprt_rdma_reserve_xprt,
+	.reserve_xprt		= xprt_reserve_xprt_cong,
 	.release_xprt		= xprt_release_xprt_cong, /* sunrpc/xprt.c */
 	.alloc_slot		= xprt_alloc_slot,
 	.release_request	= xprt_release_rqst_cong,       /* ditto */
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 93726560eaa..13dbd1c389f 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -48,8 +48,8 @@
  */
 
 #include <linux/interrupt.h>
-#include <linux/pci.h>	/* for Tavor hack below */
 #include <linux/slab.h>
+#include <asm/bitops.h>
 
 #include "xprt_rdma.h"
 
@@ -142,98 +142,139 @@ rpcrdma_cq_async_error_upcall(struct ib_event *event, void *context)
 	}
 }
 
-static inline
-void rpcrdma_event_process(struct ib_wc *wc)
+static void
+rpcrdma_sendcq_process_wc(struct ib_wc *wc)
 {
-	struct rpcrdma_mw *frmr;
-	struct rpcrdma_rep *rep =
-			(struct rpcrdma_rep *)(unsigned long) wc->wr_id;
+	struct rpcrdma_mw *frmr = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
 
-	dprintk("RPC:       %s: event rep %p status %X opcode %X length %u\n",
-		__func__, rep, wc->status, wc->opcode, wc->byte_len);
+	dprintk("RPC:       %s: frmr %p status %X opcode %d\n",
+		__func__, frmr, wc->status, wc->opcode);
 
-	if (!rep) /* send or bind completion that we don't care about */
+	if (wc->wr_id == 0ULL)
 		return;
-
-	if (IB_WC_SUCCESS != wc->status) {
-		dprintk("RPC:       %s: WC opcode %d status %X, connection lost\n",
-			__func__, wc->opcode, wc->status);
-		rep->rr_len = ~0U;
-		if (wc->opcode != IB_WC_FAST_REG_MR && wc->opcode != IB_WC_LOCAL_INV)
-			rpcrdma_schedule_tasklet(rep);
+	if (wc->status != IB_WC_SUCCESS)
 		return;
-	}
 
-	switch (wc->opcode) {
-	case IB_WC_FAST_REG_MR:
-		frmr = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+	if (wc->opcode == IB_WC_FAST_REG_MR)
 		frmr->r.frmr.state = FRMR_IS_VALID;
-		break;
-	case IB_WC_LOCAL_INV:
-		frmr = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+	else if (wc->opcode == IB_WC_LOCAL_INV)
 		frmr->r.frmr.state = FRMR_IS_INVALID;
-		break;
-	case IB_WC_RECV:
-		rep->rr_len = wc->byte_len;
-		ib_dma_sync_single_for_cpu(
-			rdmab_to_ia(rep->rr_buffer)->ri_id->device,
-			rep->rr_iov.addr, rep->rr_len, DMA_FROM_DEVICE);
-		/* Keep (only) the most recent credits, after check validity */
-		if (rep->rr_len >= 16) {
-			struct rpcrdma_msg *p =
-					(struct rpcrdma_msg *) rep->rr_base;
-			unsigned int credits = ntohl(p->rm_credit);
-			if (credits == 0) {
-				dprintk("RPC:       %s: server"
-					" dropped credits to 0!\n", __func__);
-				/* don't deadlock */
-				credits = 1;
-			} else if (credits > rep->rr_buffer->rb_max_requests) {
-				dprintk("RPC:       %s: server"
-					" over-crediting: %d (%d)\n",
-					__func__, credits,
-					rep->rr_buffer->rb_max_requests);
-				credits = rep->rr_buffer->rb_max_requests;
-			}
-			atomic_set(&rep->rr_buffer->rb_credits, credits);
-		}
-		/* fall through */
-	case IB_WC_BIND_MW:
-		rpcrdma_schedule_tasklet(rep);
-		break;
-	default:
-		dprintk("RPC:       %s: unexpected WC event %X\n",
-			__func__, wc->opcode);
-		break;
-	}
 }
 
-static inline int
-rpcrdma_cq_poll(struct ib_cq *cq)
+static int
+rpcrdma_sendcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
 {
-	struct ib_wc wc;
-	int rc;
+	struct ib_wc *wcs;
+	int budget, count, rc;
 
-	for (;;) {
-		rc = ib_poll_cq(cq, 1, &wc);
-		if (rc < 0) {
-			dprintk("RPC:       %s: ib_poll_cq failed %i\n",
-				__func__, rc);
+	budget = RPCRDMA_WC_BUDGET / RPCRDMA_POLLSIZE;
+	do {
+		wcs = ep->rep_send_wcs;
+
+		rc = ib_poll_cq(cq, RPCRDMA_POLLSIZE, wcs);
+		if (rc <= 0)
 			return rc;
-		}
-		if (rc == 0)
-			break;
 
-		rpcrdma_event_process(&wc);
+		count = rc;
+		while (count-- > 0)
+			rpcrdma_sendcq_process_wc(wcs++);
+	} while (rc == RPCRDMA_POLLSIZE && --budget);
+	return 0;
+}
+
+/*
+ * Handle send, fast_reg_mr, and local_inv completions.
+ *
+ * Send events are typically suppressed and thus do not result
+ * in an upcall. Occasionally one is signaled, however. This
+ * prevents the provider's completion queue from wrapping and
+ * losing a completion.
+ */
+static void
+rpcrdma_sendcq_upcall(struct ib_cq *cq, void *cq_context)
+{
+	struct rpcrdma_ep *ep = (struct rpcrdma_ep *)cq_context;
+	int rc;
+
+	rc = rpcrdma_sendcq_poll(cq, ep);
+	if (rc) {
+		dprintk("RPC:       %s: ib_poll_cq failed: %i\n",
+			__func__, rc);
+		return;
 	}
 
+	rc = ib_req_notify_cq(cq,
+			IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
+	if (rc == 0)
+		return;
+	if (rc < 0) {
+		dprintk("RPC:       %s: ib_req_notify_cq failed: %i\n",
+			__func__, rc);
+		return;
+	}
+
+	rpcrdma_sendcq_poll(cq, ep);
+}
+
+static void
+rpcrdma_recvcq_process_wc(struct ib_wc *wc)
+{
+	struct rpcrdma_rep *rep =
+			(struct rpcrdma_rep *)(unsigned long)wc->wr_id;
+
+	dprintk("RPC:       %s: rep %p status %X opcode %X length %u\n",
+		__func__, rep, wc->status, wc->opcode, wc->byte_len);
+
+	if (wc->status != IB_WC_SUCCESS) {
+		rep->rr_len = ~0U;
+		goto out_schedule;
+	}
+	if (wc->opcode != IB_WC_RECV)
+		return;
+
+	rep->rr_len = wc->byte_len;
+	ib_dma_sync_single_for_cpu(rdmab_to_ia(rep->rr_buffer)->ri_id->device,
+			rep->rr_iov.addr, rep->rr_len, DMA_FROM_DEVICE);
+
+	if (rep->rr_len >= 16) {
+		struct rpcrdma_msg *p = (struct rpcrdma_msg *)rep->rr_base;
+		unsigned int credits = ntohl(p->rm_credit);
+
+		if (credits == 0)
+			credits = 1;	/* don't deadlock */
+		else if (credits > rep->rr_buffer->rb_max_requests)
+			credits = rep->rr_buffer->rb_max_requests;
+		atomic_set(&rep->rr_buffer->rb_credits, credits);
+	}
+
+out_schedule:
+	rpcrdma_schedule_tasklet(rep);
+}
+
+static int
+rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
+{
+	struct ib_wc *wcs;
+	int budget, count, rc;
+
+	budget = RPCRDMA_WC_BUDGET / RPCRDMA_POLLSIZE;
+	do {
+		wcs = ep->rep_recv_wcs;
+
+		rc = ib_poll_cq(cq, RPCRDMA_POLLSIZE, wcs);
+		if (rc <= 0)
+			return rc;
+
+		count = rc;
+		while (count-- > 0)
+			rpcrdma_recvcq_process_wc(wcs++);
+	} while (rc == RPCRDMA_POLLSIZE && --budget);
 	return 0;
 }
 
 /*
- * rpcrdma_cq_event_upcall
+ * Handle receive completions.
  *
- * This upcall handles recv, send, bind and unbind events.
  * It is reentrant but processes single events in order to maintain
  * ordering of receives to keep server credits.
  *
@@ -242,26 +283,31 @@ rpcrdma_cq_poll(struct ib_cq *cq)
  * connection shutdown. That is, the structures required for
  * the completion of the reply handler must remain intact until
  * all memory has been reclaimed.
- *
- * Note that send events are suppressed and do not result in an upcall.
  */
 static void
-rpcrdma_cq_event_upcall(struct ib_cq *cq, void *context)
+rpcrdma_recvcq_upcall(struct ib_cq *cq, void *cq_context)
 {
+	struct rpcrdma_ep *ep = (struct rpcrdma_ep *)cq_context;
 	int rc;
 
-	rc = rpcrdma_cq_poll(cq);
-	if (rc)
+	rc = rpcrdma_recvcq_poll(cq, ep);
+	if (rc) {
+		dprintk("RPC:       %s: ib_poll_cq failed: %i\n",
+			__func__, rc);
 		return;
+	}
 
-	rc = ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
-	if (rc) {
-		dprintk("RPC:       %s: ib_req_notify_cq failed %i\n",
+	rc = ib_req_notify_cq(cq,
+			IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
+	if (rc == 0)
+		return;
+	if (rc < 0) {
+		dprintk("RPC:       %s: ib_req_notify_cq failed: %i\n",
 			__func__, rc);
 		return;
 	}
 
-	rpcrdma_cq_poll(cq);
+	rpcrdma_recvcq_poll(cq, ep);
 }
 
 #ifdef RPC_DEBUG
@@ -493,54 +539,32 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 		ia->ri_dma_lkey = ia->ri_id->device->local_dma_lkey;
 	}
 
-	switch (memreg) {
-	case RPCRDMA_MEMWINDOWS:
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-		if (!(devattr.device_cap_flags & IB_DEVICE_MEM_WINDOW)) {
-			dprintk("RPC:       %s: MEMWINDOWS registration "
-				"specified but not supported by adapter, "
-				"using slower RPCRDMA_REGISTER\n",
-				__func__);
-			memreg = RPCRDMA_REGISTER;
-		}
-		break;
-	case RPCRDMA_MTHCAFMR:
-		if (!ia->ri_id->device->alloc_fmr) {
-#if RPCRDMA_PERSISTENT_REGISTRATION
-			dprintk("RPC:       %s: MTHCAFMR registration "
-				"specified but not supported by adapter, "
-				"using riskier RPCRDMA_ALLPHYSICAL\n",
-				__func__);
-			memreg = RPCRDMA_ALLPHYSICAL;
-#else
-			dprintk("RPC:       %s: MTHCAFMR registration "
-				"specified but not supported by adapter, "
-				"using slower RPCRDMA_REGISTER\n",
-				__func__);
-			memreg = RPCRDMA_REGISTER;
-#endif
-		}
-		break;
-	case RPCRDMA_FRMR:
+	if (memreg == RPCRDMA_FRMR) {
 		/* Requires both frmr reg and local dma lkey */
 		if ((devattr.device_cap_flags &
 		     (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) !=
 		    (IB_DEVICE_MEM_MGT_EXTENSIONS|IB_DEVICE_LOCAL_DMA_LKEY)) {
-#if RPCRDMA_PERSISTENT_REGISTRATION
 			dprintk("RPC:       %s: FRMR registration "
-				"specified but not supported by adapter, "
-				"using riskier RPCRDMA_ALLPHYSICAL\n",
-				__func__);
+				"not supported by HCA\n", __func__);
+			memreg = RPCRDMA_MTHCAFMR;
+		} else {
+			/* Mind the ia limit on FRMR page list depth */
+			ia->ri_max_frmr_depth = min_t(unsigned int,
+				RPCRDMA_MAX_DATA_SEGS,
+				devattr.max_fast_reg_page_list_len);
+		}
+	}
+	if (memreg == RPCRDMA_MTHCAFMR) {
+		if (!ia->ri_id->device->alloc_fmr) {
+			dprintk("RPC:       %s: MTHCAFMR registration "
+				"not supported by HCA\n", __func__);
+#if RPCRDMA_PERSISTENT_REGISTRATION
 			memreg = RPCRDMA_ALLPHYSICAL;
 #else
-			dprintk("RPC:       %s: FRMR registration "
-				"specified but not supported by adapter, "
-				"using slower RPCRDMA_REGISTER\n",
-				__func__);
-			memreg = RPCRDMA_REGISTER;
+			rc = -ENOMEM;
+			goto out2;
 #endif
 		}
-		break;
 	}
 
 	/*
@@ -552,8 +576,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 	 * adapter.
 	 */
 	switch (memreg) {
-	case RPCRDMA_BOUNCEBUFFERS:
-	case RPCRDMA_REGISTER:
 	case RPCRDMA_FRMR:
 		break;
 #if RPCRDMA_PERSISTENT_REGISTRATION
@@ -563,30 +585,26 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
 				IB_ACCESS_REMOTE_READ;
 		goto register_setup;
 #endif
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		mem_priv = IB_ACCESS_LOCAL_WRITE |
-				IB_ACCESS_MW_BIND;
-		goto register_setup;
 	case RPCRDMA_MTHCAFMR:
 		if (ia->ri_have_dma_lkey)
 			break;
 		mem_priv = IB_ACCESS_LOCAL_WRITE;
+#if RPCRDMA_PERSISTENT_REGISTRATION
 	register_setup:
+#endif
 		ia->ri_bind_mem = ib_get_dma_mr(ia->ri_pd, mem_priv);
 		if (IS_ERR(ia->ri_bind_mem)) {
 			printk(KERN_ALERT "%s: ib_get_dma_mr for "
-				"phys register failed with %lX\n\t"
-				"Will continue with degraded performance\n",
+				"phys register failed with %lX\n",
 				__func__, PTR_ERR(ia->ri_bind_mem));
-			memreg = RPCRDMA_REGISTER;
-			ia->ri_bind_mem = NULL;
+			rc = -ENOMEM;
+			goto out2;
 		}
 		break;
 	default:
-		printk(KERN_ERR "%s: invalid memory registration mode %d\n",
-				__func__, memreg);
-		rc = -EINVAL;
+		printk(KERN_ERR "RPC: Unsupported memory "
+				"registration mode: %d\n", memreg);
+		rc = -ENOMEM;
 		goto out2;
 	}
 	dprintk("RPC:       %s: memory registration strategy is %d\n",
@@ -640,6 +658,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 				struct rpcrdma_create_data_internal *cdata)
 {
 	struct ib_device_attr devattr;
+	struct ib_cq *sendcq, *recvcq;
 	int rc, err;
 
 	rc = ib_query_device(ia->ri_id->device, &devattr);
@@ -659,32 +678,42 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	ep->rep_attr.srq = NULL;
 	ep->rep_attr.cap.max_send_wr = cdata->max_requests;
 	switch (ia->ri_memreg_strategy) {
-	case RPCRDMA_FRMR:
+	case RPCRDMA_FRMR: {
+		int depth = 7;
+
 		/* Add room for frmr register and invalidate WRs.
 		 * 1. FRMR reg WR for head
 		 * 2. FRMR invalidate WR for head
-		 * 3. FRMR reg WR for pagelist
-		 * 4. FRMR invalidate WR for pagelist
+		 * 3. N FRMR reg WRs for pagelist
+		 * 4. N FRMR invalidate WRs for pagelist
 		 * 5. FRMR reg WR for tail
 		 * 6. FRMR invalidate WR for tail
 		 * 7. The RDMA_SEND WR
 		 */
-		ep->rep_attr.cap.max_send_wr *= 7;
+
+		/* Calculate N if the device max FRMR depth is smaller than
+		 * RPCRDMA_MAX_DATA_SEGS.
+		 */
+		if (ia->ri_max_frmr_depth < RPCRDMA_MAX_DATA_SEGS) {
+			int delta = RPCRDMA_MAX_DATA_SEGS -
+				    ia->ri_max_frmr_depth;
+
+			do {
+				depth += 2; /* FRMR reg + invalidate */
+				delta -= ia->ri_max_frmr_depth;
+			} while (delta > 0);
+
+		}
+		ep->rep_attr.cap.max_send_wr *= depth;
 		if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr) {
-			cdata->max_requests = devattr.max_qp_wr / 7;
+			cdata->max_requests = devattr.max_qp_wr / depth;
 			if (!cdata->max_requests)
 				return -EINVAL;
-			ep->rep_attr.cap.max_send_wr = cdata->max_requests * 7;
+			ep->rep_attr.cap.max_send_wr = cdata->max_requests *
+						       depth;
 		}
 		break;
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		/* Add room for mw_binds+unbinds - overkill! */
-		ep->rep_attr.cap.max_send_wr++;
-		ep->rep_attr.cap.max_send_wr *= (2 * RPCRDMA_MAX_SEGS);
-		if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr)
-			return -EINVAL;
-		break;
+	}
 	default:
 		break;
 	}
@@ -705,46 +734,51 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 		ep->rep_attr.cap.max_recv_sge);
 
 	/* set trigger for requesting send completion */
-	ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 /*  - 1*/;
-	switch (ia->ri_memreg_strategy) {
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		ep->rep_cqinit -= RPCRDMA_MAX_SEGS;
-		break;
-	default:
-		break;
-	}
+	ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1;
 	if (ep->rep_cqinit <= 2)
 		ep->rep_cqinit = 0;
 	INIT_CQCOUNT(ep);
 	ep->rep_ia = ia;
 	init_waitqueue_head(&ep->rep_connect_wait);
+	INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker);
 
-	/*
-	 * Create a single cq for receive dto and mw_bind (only ever
-	 * care about unbind, really). Send completions are suppressed.
-	 * Use single threaded tasklet upcalls to maintain ordering.
-	 */
-	ep->rep_cq = ib_create_cq(ia->ri_id->device, rpcrdma_cq_event_upcall,
-				  rpcrdma_cq_async_error_upcall, NULL,
-				  ep->rep_attr.cap.max_recv_wr +
+	sendcq = ib_create_cq(ia->ri_id->device, rpcrdma_sendcq_upcall,
+				  rpcrdma_cq_async_error_upcall, ep,
 				  ep->rep_attr.cap.max_send_wr + 1, 0);
-	if (IS_ERR(ep->rep_cq)) {
-		rc = PTR_ERR(ep->rep_cq);
-		dprintk("RPC:       %s: ib_create_cq failed: %i\n",
+	if (IS_ERR(sendcq)) {
+		rc = PTR_ERR(sendcq);
+		dprintk("RPC:       %s: failed to create send CQ: %i\n",
 			__func__, rc);
 		goto out1;
 	}
 
-	rc = ib_req_notify_cq(ep->rep_cq, IB_CQ_NEXT_COMP);
+	rc = ib_req_notify_cq(sendcq, IB_CQ_NEXT_COMP);
+	if (rc) {
+		dprintk("RPC:       %s: ib_req_notify_cq failed: %i\n",
+			__func__, rc);
+		goto out2;
+	}
+
+	recvcq = ib_create_cq(ia->ri_id->device, rpcrdma_recvcq_upcall,
+				  rpcrdma_cq_async_error_upcall, ep,
+				  ep->rep_attr.cap.max_recv_wr + 1, 0);
+	if (IS_ERR(recvcq)) {
+		rc = PTR_ERR(recvcq);
+		dprintk("RPC:       %s: failed to create recv CQ: %i\n",
+			__func__, rc);
+		goto out2;
+	}
+
+	rc = ib_req_notify_cq(recvcq, IB_CQ_NEXT_COMP);
 	if (rc) {
 		dprintk("RPC:       %s: ib_req_notify_cq failed: %i\n",
 			__func__, rc);
+		ib_destroy_cq(recvcq);
 		goto out2;
 	}
 
-	ep->rep_attr.send_cq = ep->rep_cq;
-	ep->rep_attr.recv_cq = ep->rep_cq;
+	ep->rep_attr.send_cq = sendcq;
+	ep->rep_attr.recv_cq = recvcq;
 
 	/* Initialize cma parameters */
 
@@ -754,9 +788,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 
 	/* Client offers RDMA Read but does not initiate */
 	ep->rep_remote_cma.initiator_depth = 0;
-	if (ia->ri_memreg_strategy == RPCRDMA_BOUNCEBUFFERS)
-		ep->rep_remote_cma.responder_resources = 0;
-	else if (devattr.max_qp_rd_atom > 32)	/* arbitrary but <= 255 */
+	if (devattr.max_qp_rd_atom > 32)	/* arbitrary but <= 255 */
 		ep->rep_remote_cma.responder_resources = 32;
 	else
 		ep->rep_remote_cma.responder_resources = devattr.max_qp_rd_atom;
@@ -768,7 +800,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	return 0;
 
 out2:
-	err = ib_destroy_cq(ep->rep_cq);
+	err = ib_destroy_cq(sendcq);
 	if (err)
 		dprintk("RPC:       %s: ib_destroy_cq returned %i\n",
 			__func__, err);
@@ -782,11 +814,8 @@ out1:
  * Disconnect and destroy endpoint. After this, the only
  * valid operations on the ep are to free it (if dynamically
  * allocated) or re-create it.
- *
- * The caller's error handling must be sure to not leak the endpoint
- * if this function fails.
  */
-int
+void
 rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 {
 	int rc;
@@ -794,6 +823,8 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 	dprintk("RPC:       %s: entering, connected is %d\n",
 		__func__, ep->rep_connected);
 
+	cancel_delayed_work_sync(&ep->rep_connect_worker);
+
 	if (ia->ri_id->qp) {
 		rc = rpcrdma_ep_disconnect(ep, ia);
 		if (rc)
@@ -809,13 +840,17 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 		ep->rep_pad_mr = NULL;
 	}
 
-	rpcrdma_clean_cq(ep->rep_cq);
-	rc = ib_destroy_cq(ep->rep_cq);
+	rpcrdma_clean_cq(ep->rep_attr.recv_cq);
+	rc = ib_destroy_cq(ep->rep_attr.recv_cq);
 	if (rc)
 		dprintk("RPC:       %s: ib_destroy_cq returned %i\n",
 			__func__, rc);
 
-	return rc;
+	rpcrdma_clean_cq(ep->rep_attr.send_cq);
+	rc = ib_destroy_cq(ep->rep_attr.send_cq);
+	if (rc)
+		dprintk("RPC:       %s: ib_destroy_cq returned %i\n",
+			__func__, rc);
 }
 
 /*
@@ -831,17 +866,20 @@ rpcrdma_ep_connect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 	if (ep->rep_connected != 0) {
 		struct rpcrdma_xprt *xprt;
 retry:
+		dprintk("RPC:       %s: reconnecting...\n", __func__);
 		rc = rpcrdma_ep_disconnect(ep, ia);
 		if (rc && rc != -ENOTCONN)
 			dprintk("RPC:       %s: rpcrdma_ep_disconnect"
 				" status %i\n", __func__, rc);
-		rpcrdma_clean_cq(ep->rep_cq);
+
+		rpcrdma_clean_cq(ep->rep_attr.recv_cq);
+		rpcrdma_clean_cq(ep->rep_attr.send_cq);
 
 		xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);
 		id = rpcrdma_create_id(xprt, ia,
 				(struct sockaddr *)&xprt->rx_data.addr);
 		if (IS_ERR(id)) {
-			rc = PTR_ERR(id);
+			rc = -EHOSTUNREACH;
 			goto out;
 		}
 		/* TEMP TEMP TEMP - fail if new device:
@@ -855,35 +893,32 @@ retry:
 			printk("RPC:       %s: can't reconnect on "
 				"different device!\n", __func__);
 			rdma_destroy_id(id);
-			rc = -ENETDOWN;
+			rc = -ENETUNREACH;
 			goto out;
 		}
 		/* END TEMP */
+		rc = rdma_create_qp(id, ia->ri_pd, &ep->rep_attr);
+		if (rc) {
+			dprintk("RPC:       %s: rdma_create_qp failed %i\n",
+				__func__, rc);
+			rdma_destroy_id(id);
+			rc = -ENETUNREACH;
+			goto out;
+		}
 		rdma_destroy_qp(ia->ri_id);
 		rdma_destroy_id(ia->ri_id);
 		ia->ri_id = id;
+	} else {
+		dprintk("RPC:       %s: connecting...\n", __func__);
+		rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr);
+		if (rc) {
+			dprintk("RPC:       %s: rdma_create_qp failed %i\n",
+				__func__, rc);
+			/* do not update ep->rep_connected */
+			return -ENETUNREACH;
+		}
 	}
 
-	rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr);
-	if (rc) {
-		dprintk("RPC:       %s: rdma_create_qp failed %i\n",
-			__func__, rc);
-		goto out;
-	}
-
-/* XXX Tavor device performs badly with 2K MTU! */
-if (strnicmp(ia->ri_id->device->dma_device->bus->name, "pci", 3) == 0) {
-	struct pci_dev *pcid = to_pci_dev(ia->ri_id->device->dma_device);
-	if (pcid->device == PCI_DEVICE_ID_MELLANOX_TAVOR &&
-	    (pcid->vendor == PCI_VENDOR_ID_MELLANOX ||
-	     pcid->vendor == PCI_VENDOR_ID_TOPSPIN)) {
-		struct ib_qp_attr attr = {
-			.path_mtu = IB_MTU_1024
-		};
-		rc = ib_modify_qp(ia->ri_id->qp, &attr, IB_QP_PATH_MTU);
-	}
-}
-
 	ep->rep_connected = 0;
 
 	rc = rdma_connect(ia->ri_id, &ep->rep_remote_cma);
@@ -944,7 +979,8 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
 {
 	int rc;
 
-	rpcrdma_clean_cq(ep->rep_cq);
+	rpcrdma_clean_cq(ep->rep_attr.recv_cq);
+	rpcrdma_clean_cq(ep->rep_attr.send_cq);
 	rc = rdma_disconnect(ia->ri_id);
 	if (!rc) {
 		/* returns without wait if not connected */
@@ -967,7 +1003,7 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 	struct rpcrdma_ia *ia, struct rpcrdma_create_data_internal *cdata)
 {
 	char *p;
-	size_t len;
+	size_t len, rlen, wlen;
 	int i, rc;
 	struct rpcrdma_mw *r;
 
@@ -997,11 +1033,6 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 		len += (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS *
 				sizeof(struct rpcrdma_mw);
 		break;
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		len += (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS *
-				sizeof(struct rpcrdma_mw);
-		break;
 	default:
 		break;
 	}
@@ -1032,32 +1063,29 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 	}
 	p += cdata->padding;
 
-	/*
-	 * Allocate the fmr's, or mw's for mw_bind chunk registration.
-	 * We "cycle" the mw's in order to minimize rkey reuse,
-	 * and also reduce unbind-to-bind collision.
-	 */
 	INIT_LIST_HEAD(&buf->rb_mws);
 	r = (struct rpcrdma_mw *)p;
 	switch (ia->ri_memreg_strategy) {
 	case RPCRDMA_FRMR:
 		for (i = buf->rb_max_requests * RPCRDMA_MAX_SEGS; i; i--) {
 			r->r.frmr.fr_mr = ib_alloc_fast_reg_mr(ia->ri_pd,
-							 RPCRDMA_MAX_SEGS);
+						ia->ri_max_frmr_depth);
 			if (IS_ERR(r->r.frmr.fr_mr)) {
 				rc = PTR_ERR(r->r.frmr.fr_mr);
 				dprintk("RPC:       %s: ib_alloc_fast_reg_mr"
 					" failed %i\n", __func__, rc);
 				goto out;
 			}
-			r->r.frmr.fr_pgl =
-				ib_alloc_fast_reg_page_list(ia->ri_id->device,
-							    RPCRDMA_MAX_SEGS);
+			r->r.frmr.fr_pgl = ib_alloc_fast_reg_page_list(
+						ia->ri_id->device,
+						ia->ri_max_frmr_depth);
 			if (IS_ERR(r->r.frmr.fr_pgl)) {
 				rc = PTR_ERR(r->r.frmr.fr_pgl);
 				dprintk("RPC:       %s: "
 					"ib_alloc_fast_reg_page_list "
 					"failed %i\n", __func__, rc);
+
+				ib_dereg_mr(r->r.frmr.fr_mr);
 				goto out;
 			}
 			list_add(&r->mw_list, &buf->rb_mws);
@@ -1082,21 +1110,6 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 			++r;
 		}
 		break;
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		/* Allocate one extra request's worth, for full cycling */
-		for (i = (buf->rb_max_requests+1) * RPCRDMA_MAX_SEGS; i; i--) {
-			r->r.mw = ib_alloc_mw(ia->ri_pd, IB_MW_TYPE_1);
-			if (IS_ERR(r->r.mw)) {
-				rc = PTR_ERR(r->r.mw);
-				dprintk("RPC:       %s: ib_alloc_mw"
-					" failed %i\n", __func__, rc);
-				goto out;
-			}
-			list_add(&r->mw_list, &buf->rb_mws);
-			++r;
-		}
-		break;
 	default:
 		break;
 	}
@@ -1105,16 +1118,16 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 	 * Allocate/init the request/reply buffers. Doing this
 	 * using kmalloc for now -- one for each buf.
 	 */
+	wlen = 1 << fls(cdata->inline_wsize + sizeof(struct rpcrdma_req));
+	rlen = 1 << fls(cdata->inline_rsize + sizeof(struct rpcrdma_rep));
+	dprintk("RPC:       %s: wlen = %zu, rlen = %zu\n",
+		__func__, wlen, rlen);
+
 	for (i = 0; i < buf->rb_max_requests; i++) {
 		struct rpcrdma_req *req;
 		struct rpcrdma_rep *rep;
 
-		len = cdata->inline_wsize + sizeof(struct rpcrdma_req);
-		/* RPC layer requests *double* size + 1K RPC_SLACK_SPACE! */
-		/* Typical ~2400b, so rounding up saves work later */
-		if (len < 4096)
-			len = 4096;
-		req = kmalloc(len, GFP_KERNEL);
+		req = kmalloc(wlen, GFP_KERNEL);
 		if (req == NULL) {
 			dprintk("RPC:       %s: request buffer %d alloc"
 				" failed\n", __func__, i);
@@ -1126,16 +1139,16 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 		buf->rb_send_bufs[i]->rl_buffer = buf;
 
 		rc = rpcrdma_register_internal(ia, req->rl_base,
-				len - offsetof(struct rpcrdma_req, rl_base),
+				wlen - offsetof(struct rpcrdma_req, rl_base),
 				&buf->rb_send_bufs[i]->rl_handle,
 				&buf->rb_send_bufs[i]->rl_iov);
 		if (rc)
 			goto out;
 
-		buf->rb_send_bufs[i]->rl_size = len-sizeof(struct rpcrdma_req);
+		buf->rb_send_bufs[i]->rl_size = wlen -
+						sizeof(struct rpcrdma_req);
 
-		len = cdata->inline_rsize + sizeof(struct rpcrdma_rep);
-		rep = kmalloc(len, GFP_KERNEL);
+		rep = kmalloc(rlen, GFP_KERNEL);
 		if (rep == NULL) {
 			dprintk("RPC:       %s: reply buffer %d alloc failed\n",
 				__func__, i);
@@ -1145,10 +1158,9 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
 		memset(rep, 0, sizeof(struct rpcrdma_rep));
 		buf->rb_recv_bufs[i] = rep;
 		buf->rb_recv_bufs[i]->rr_buffer = buf;
-		init_waitqueue_head(&rep->rr_unbind);
 
 		rc = rpcrdma_register_internal(ia, rep->rr_base,
-				len - offsetof(struct rpcrdma_rep, rr_base),
+				rlen - offsetof(struct rpcrdma_rep, rr_base),
 				&buf->rb_recv_bufs[i]->rr_handle,
 				&buf->rb_recv_bufs[i]->rr_iov);
 		if (rc)
@@ -1179,7 +1191,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 
 	/* clean up in reverse order from create
 	 *   1.  recv mr memory (mr free, then kfree)
-	 *   1a. bind mw memory
 	 *   2.  send mr memory (mr free, then kfree)
 	 *   3.  padding (if any) [moved to rpcrdma_ep_destroy]
 	 *   4.  arrays
@@ -1194,41 +1205,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 			kfree(buf->rb_recv_bufs[i]);
 		}
 		if (buf->rb_send_bufs && buf->rb_send_bufs[i]) {
-			while (!list_empty(&buf->rb_mws)) {
-				r = list_entry(buf->rb_mws.next,
-					struct rpcrdma_mw, mw_list);
-				list_del(&r->mw_list);
-				switch (ia->ri_memreg_strategy) {
-				case RPCRDMA_FRMR:
-					rc = ib_dereg_mr(r->r.frmr.fr_mr);
-					if (rc)
-						dprintk("RPC:       %s:"
-							" ib_dereg_mr"
-							" failed %i\n",
-							__func__, rc);
-					ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
-					break;
-				case RPCRDMA_MTHCAFMR:
-					rc = ib_dealloc_fmr(r->r.fmr);
-					if (rc)
-						dprintk("RPC:       %s:"
-							" ib_dealloc_fmr"
-							" failed %i\n",
-							__func__, rc);
-					break;
-				case RPCRDMA_MEMWINDOWS_ASYNC:
-				case RPCRDMA_MEMWINDOWS:
-					rc = ib_dealloc_mw(r->r.mw);
-					if (rc)
-						dprintk("RPC:       %s:"
-							" ib_dealloc_mw"
-							" failed %i\n",
-							__func__, rc);
-					break;
-				default:
-					break;
-				}
-			}
 			rpcrdma_deregister_internal(ia,
 					buf->rb_send_bufs[i]->rl_handle,
 					&buf->rb_send_bufs[i]->rl_iov);
@@ -1236,6 +1212,33 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
 		}
 	}
 
+	while (!list_empty(&buf->rb_mws)) {
+		r = list_entry(buf->rb_mws.next,
+			struct rpcrdma_mw, mw_list);
+		list_del(&r->mw_list);
+		switch (ia->ri_memreg_strategy) {
+		case RPCRDMA_FRMR:
+			rc = ib_dereg_mr(r->r.frmr.fr_mr);
+			if (rc)
+				dprintk("RPC:       %s:"
+					" ib_dereg_mr"
+					" failed %i\n",
+					__func__, rc);
+			ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
+			break;
+		case RPCRDMA_MTHCAFMR:
+			rc = ib_dealloc_fmr(r->r.fmr);
+			if (rc)
+				dprintk("RPC:       %s:"
+					" ib_dealloc_fmr"
+					" failed %i\n",
+					__func__, rc);
+			break;
+		default:
+			break;
+		}
+	}
+
 	kfree(buf->rb_pool);
 }
 
@@ -1299,21 +1302,17 @@ rpcrdma_buffer_put(struct rpcrdma_req *req)
 	int i;
 	unsigned long flags;
 
-	BUG_ON(req->rl_nchunks != 0);
 	spin_lock_irqsave(&buffers->rb_lock, flags);
 	buffers->rb_send_bufs[--buffers->rb_send_index] = req;
 	req->rl_niovs = 0;
 	if (req->rl_reply) {
 		buffers->rb_recv_bufs[--buffers->rb_recv_index] = req->rl_reply;
-		init_waitqueue_head(&req->rl_reply->rr_unbind);
 		req->rl_reply->rr_func = NULL;
 		req->rl_reply = NULL;
 	}
 	switch (ia->ri_memreg_strategy) {
 	case RPCRDMA_FRMR:
 	case RPCRDMA_MTHCAFMR:
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
 		/*
 		 * Cycle mw's back in reverse order, and "spin" them.
 		 * This delays and scrambles reuse as much as possible.
@@ -1358,8 +1357,7 @@ rpcrdma_recv_buffer_get(struct rpcrdma_req *req)
 
 /*
  * Put reply buffers back into pool when not attached to
- * request. This happens in error conditions, and when
- * aborting unbinds. Pre-decrement counter/array index.
+ * request. This happens in error conditions.
  */
 void
 rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep)
@@ -1498,8 +1496,8 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	seg1->mr_offset -= pageoff;	/* start of page */
 	seg1->mr_len += pageoff;
 	len = -pageoff;
-	if (*nsegs > RPCRDMA_MAX_DATA_SEGS)
-		*nsegs = RPCRDMA_MAX_DATA_SEGS;
+	if (*nsegs > ia->ri_max_frmr_depth)
+		*nsegs = ia->ri_max_frmr_depth;
 	for (page_no = i = 0; i < *nsegs;) {
 		rpcrdma_map_one(ia, seg, writing);
 		pa = seg->mr_dma;
@@ -1536,10 +1534,6 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	} else
 		post_wr = &frmr_wr;
 
-	/* Bump the key */
-	key = (u8)(seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey & 0x000000FF);
-	ib_update_fast_reg_key(seg1->mr_chunk.rl_mw->r.frmr.fr_mr, ++key);
-
 	/* Prepare FRMR WR */
 	memset(&frmr_wr, 0, sizeof frmr_wr);
 	frmr_wr.wr_id = (unsigned long)(void *)seg1->mr_chunk.rl_mw;
@@ -1550,7 +1544,16 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	frmr_wr.wr.fast_reg.page_list_len = page_no;
 	frmr_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
 	frmr_wr.wr.fast_reg.length = page_no << PAGE_SHIFT;
-	BUG_ON(frmr_wr.wr.fast_reg.length < len);
+	if (frmr_wr.wr.fast_reg.length < len) {
+		while (seg1->mr_nsegs--)
+			rpcrdma_unmap_one(ia, seg++);
+		return -EIO;
+	}
+
+	/* Bump the key */
+	key = (u8)(seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey & 0x000000FF);
+	ib_update_fast_reg_key(seg1->mr_chunk.rl_mw->r.frmr.fr_mr, ++key);
+
 	frmr_wr.wr.fast_reg.access_flags = (writing ?
 				IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
 				IB_ACCESS_REMOTE_READ);
@@ -1661,135 +1664,6 @@ rpcrdma_deregister_fmr_external(struct rpcrdma_mr_seg *seg,
 	return rc;
 }
 
-static int
-rpcrdma_register_memwin_external(struct rpcrdma_mr_seg *seg,
-			int *nsegs, int writing, struct rpcrdma_ia *ia,
-			struct rpcrdma_xprt *r_xprt)
-{
-	int mem_priv = (writing ? IB_ACCESS_REMOTE_WRITE :
-				  IB_ACCESS_REMOTE_READ);
-	struct ib_mw_bind param;
-	int rc;
-
-	*nsegs = 1;
-	rpcrdma_map_one(ia, seg, writing);
-	param.bind_info.mr = ia->ri_bind_mem;
-	param.wr_id = 0ULL;	/* no send cookie */
-	param.bind_info.addr = seg->mr_dma;
-	param.bind_info.length = seg->mr_len;
-	param.send_flags = 0;
-	param.bind_info.mw_access_flags = mem_priv;
-
-	DECR_CQCOUNT(&r_xprt->rx_ep);
-	rc = ib_bind_mw(ia->ri_id->qp, seg->mr_chunk.rl_mw->r.mw, &param);
-	if (rc) {
-		dprintk("RPC:       %s: failed ib_bind_mw "
-			"%u@0x%llx status %i\n",
-			__func__, seg->mr_len,
-			(unsigned long long)seg->mr_dma, rc);
-		rpcrdma_unmap_one(ia, seg);
-	} else {
-		seg->mr_rkey = seg->mr_chunk.rl_mw->r.mw->rkey;
-		seg->mr_base = param.bind_info.addr;
-		seg->mr_nsegs = 1;
-	}
-	return rc;
-}
-
-static int
-rpcrdma_deregister_memwin_external(struct rpcrdma_mr_seg *seg,
-			struct rpcrdma_ia *ia,
-			struct rpcrdma_xprt *r_xprt, void **r)
-{
-	struct ib_mw_bind param;
-	LIST_HEAD(l);
-	int rc;
-
-	BUG_ON(seg->mr_nsegs != 1);
-	param.bind_info.mr = ia->ri_bind_mem;
-	param.bind_info.addr = 0ULL;	/* unbind */
-	param.bind_info.length = 0;
-	param.bind_info.mw_access_flags = 0;
-	if (*r) {
-		param.wr_id = (u64) (unsigned long) *r;
-		param.send_flags = IB_SEND_SIGNALED;
-		INIT_CQCOUNT(&r_xprt->rx_ep);
-	} else {
-		param.wr_id = 0ULL;
-		param.send_flags = 0;
-		DECR_CQCOUNT(&r_xprt->rx_ep);
-	}
-	rc = ib_bind_mw(ia->ri_id->qp, seg->mr_chunk.rl_mw->r.mw, &param);
-	rpcrdma_unmap_one(ia, seg);
-	if (rc)
-		dprintk("RPC:       %s: failed ib_(un)bind_mw,"
-			" status %i\n", __func__, rc);
-	else
-		*r = NULL;	/* will upcall on completion */
-	return rc;
-}
-
-static int
-rpcrdma_register_default_external(struct rpcrdma_mr_seg *seg,
-			int *nsegs, int writing, struct rpcrdma_ia *ia)
-{
-	int mem_priv = (writing ? IB_ACCESS_REMOTE_WRITE :
-				  IB_ACCESS_REMOTE_READ);
-	struct rpcrdma_mr_seg *seg1 = seg;
-	struct ib_phys_buf ipb[RPCRDMA_MAX_DATA_SEGS];
-	int len, i, rc = 0;
-
-	if (*nsegs > RPCRDMA_MAX_DATA_SEGS)
-		*nsegs = RPCRDMA_MAX_DATA_SEGS;
-	for (len = 0, i = 0; i < *nsegs;) {
-		rpcrdma_map_one(ia, seg, writing);
-		ipb[i].addr = seg->mr_dma;
-		ipb[i].size = seg->mr_len;
-		len += seg->mr_len;
-		++seg;
-		++i;
-		/* Check for holes */
-		if ((i < *nsegs && offset_in_page(seg->mr_offset)) ||
-		    offset_in_page((seg-1)->mr_offset+(seg-1)->mr_len))
-			break;
-	}
-	seg1->mr_base = seg1->mr_dma;
-	seg1->mr_chunk.rl_mr = ib_reg_phys_mr(ia->ri_pd,
-				ipb, i, mem_priv, &seg1->mr_base);
-	if (IS_ERR(seg1->mr_chunk.rl_mr)) {
-		rc = PTR_ERR(seg1->mr_chunk.rl_mr);
-		dprintk("RPC:       %s: failed ib_reg_phys_mr "
-			"%u@0x%llx (%d)... status %i\n",
-			__func__, len,
-			(unsigned long long)seg1->mr_dma, i, rc);
-		while (i--)
-			rpcrdma_unmap_one(ia, --seg);
-	} else {
-		seg1->mr_rkey = seg1->mr_chunk.rl_mr->rkey;
-		seg1->mr_nsegs = i;
-		seg1->mr_len = len;
-	}
-	*nsegs = i;
-	return rc;
-}
-
-static int
-rpcrdma_deregister_default_external(struct rpcrdma_mr_seg *seg,
-			struct rpcrdma_ia *ia)
-{
-	struct rpcrdma_mr_seg *seg1 = seg;
-	int rc;
-
-	rc = ib_dereg_mr(seg1->mr_chunk.rl_mr);
-	seg1->mr_chunk.rl_mr = NULL;
-	while (seg1->mr_nsegs--)
-		rpcrdma_unmap_one(ia, seg++);
-	if (rc)
-		dprintk("RPC:       %s: failed ib_dereg_mr,"
-			" status %i\n", __func__, rc);
-	return rc;
-}
-
 int
 rpcrdma_register_external(struct rpcrdma_mr_seg *seg,
 			int nsegs, int writing, struct rpcrdma_xprt *r_xprt)
@@ -1819,16 +1693,8 @@ rpcrdma_register_external(struct rpcrdma_mr_seg *seg,
 		rc = rpcrdma_register_fmr_external(seg, &nsegs, writing, ia);
 		break;
 
-	/* Registration using memory windows */
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		rc = rpcrdma_register_memwin_external(seg, &nsegs, writing, ia, r_xprt);
-		break;
-
-	/* Default registration each time */
 	default:
-		rc = rpcrdma_register_default_external(seg, &nsegs, writing, ia);
-		break;
+		return -1;
 	}
 	if (rc)
 		return -1;
@@ -1838,7 +1704,7 @@ rpcrdma_register_external(struct rpcrdma_mr_seg *seg,
 
 int
 rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg,
-		struct rpcrdma_xprt *r_xprt, void *r)
+		struct rpcrdma_xprt *r_xprt)
 {
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	int nsegs = seg->mr_nsegs, rc;
@@ -1847,9 +1713,7 @@ rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg,
 
 #if RPCRDMA_PERSISTENT_REGISTRATION
 	case RPCRDMA_ALLPHYSICAL:
-		BUG_ON(nsegs != 1);
 		rpcrdma_unmap_one(ia, seg);
-		rc = 0;
 		break;
 #endif
 
@@ -1861,21 +1725,9 @@ rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg,
 		rc = rpcrdma_deregister_fmr_external(seg, ia);
 		break;
 
-	case RPCRDMA_MEMWINDOWS_ASYNC:
-	case RPCRDMA_MEMWINDOWS:
-		rc = rpcrdma_deregister_memwin_external(seg, ia, r_xprt, &r);
-		break;
-
 	default:
-		rc = rpcrdma_deregister_default_external(seg, ia);
 		break;
 	}
-	if (r) {
-		struct rpcrdma_rep *rep = r;
-		void (*func)(struct rpcrdma_rep *) = rep->rr_func;
-		rep->rr_func = NULL;
-		func(rep);	/* dereg done, callback now */
-	}
 	return nsegs;
 }
 
@@ -1950,7 +1802,6 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia,
 	ib_dma_sync_single_for_cpu(ia->ri_id->device,
 		rep->rr_iov.addr, rep->rr_iov.length, DMA_BIDIRECTIONAL);
 
-	DECR_CQCOUNT(ep);
 	rc = ib_post_recv(ia->ri_id->qp, &recv_wr, &recv_wr_fail);
 
 	if (rc)
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index cc1445dc1d1..89e7cd47970 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -43,6 +43,7 @@
 #include <linux/wait.h> 		/* wait_queue_head_t, etc */
 #include <linux/spinlock.h> 		/* spinlock_t, etc */
 #include <linux/atomic.h>			/* atomic_t, etc */
+#include <linux/workqueue.h>		/* struct work_struct */
 
 #include <rdma/rdma_cm.h>		/* RDMA connection api */
 #include <rdma/ib_verbs.h>		/* RDMA verbs api */
@@ -66,18 +67,21 @@ struct rpcrdma_ia {
 	struct completion	ri_done;
 	int			ri_async_rc;
 	enum rpcrdma_memreg	ri_memreg_strategy;
+	unsigned int		ri_max_frmr_depth;
 };
 
 /*
  * RDMA Endpoint -- one per transport instance
  */
 
+#define RPCRDMA_WC_BUDGET	(128)
+#define RPCRDMA_POLLSIZE	(16)
+
 struct rpcrdma_ep {
 	atomic_t		rep_cqcount;
 	int			rep_cqinit;
 	int			rep_connected;
 	struct rpcrdma_ia	*rep_ia;
-	struct ib_cq		*rep_cq;
 	struct ib_qp_init_attr	rep_attr;
 	wait_queue_head_t 	rep_connect_wait;
 	struct ib_sge		rep_pad;	/* holds zeroed pad */
@@ -86,6 +90,9 @@ struct rpcrdma_ep {
 	struct rpc_xprt		*rep_xprt;	/* for rep_func */
 	struct rdma_conn_param	rep_remote_cma;
 	struct sockaddr_storage	rep_remote_addr;
+	struct delayed_work	rep_connect_worker;
+	struct ib_wc		rep_send_wcs[RPCRDMA_POLLSIZE];
+	struct ib_wc		rep_recv_wcs[RPCRDMA_POLLSIZE];
 };
 
 #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit)
@@ -124,7 +131,6 @@ struct rpcrdma_rep {
 	struct rpc_xprt	*rr_xprt;	/* needed for request/reply matching */
 	void (*rr_func)(struct rpcrdma_rep *);/* called by tasklet in softint */
 	struct list_head rr_list;	/* tasklet list */
-	wait_queue_head_t rr_unbind;	/* optional unbind wait */
 	struct ib_sge	rr_iov;		/* for posting */
 	struct ib_mr	*rr_handle;	/* handle for mem in rr_iov */
 	char	rr_base[MAX_RPCRDMAHDR]; /* minimal inline receive buffer */
@@ -159,7 +165,6 @@ struct rpcrdma_mr_seg {		/* chunk descriptors */
 		struct ib_mr	*rl_mr;		/* if registered directly */
 		struct rpcrdma_mw {		/* if registered from region */
 			union {
-				struct ib_mw	*mw;
 				struct ib_fmr	*fmr;
 				struct {
 					struct ib_fast_reg_page_list *fr_pgl;
@@ -207,7 +212,6 @@ struct rpcrdma_req {
 struct rpcrdma_buffer {
 	spinlock_t	rb_lock;	/* protects indexes */
 	atomic_t	rb_credits;	/* most recent server credits */
-	unsigned long	rb_cwndscale;	/* cached framework rpc_cwndscale */
 	int		rb_max_requests;/* client max requests */
 	struct list_head rb_mws;	/* optional memory windows/fmrs/frmrs */
 	int		rb_send_index;
@@ -300,7 +304,7 @@ void rpcrdma_ia_close(struct rpcrdma_ia *);
  */
 int rpcrdma_ep_create(struct rpcrdma_ep *, struct rpcrdma_ia *,
 				struct rpcrdma_create_data_internal *);
-int rpcrdma_ep_destroy(struct rpcrdma_ep *, struct rpcrdma_ia *);
+void rpcrdma_ep_destroy(struct rpcrdma_ep *, struct rpcrdma_ia *);
 int rpcrdma_ep_connect(struct rpcrdma_ep *, struct rpcrdma_ia *);
 int rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *);
 
@@ -330,11 +334,12 @@ int rpcrdma_deregister_internal(struct rpcrdma_ia *,
 int rpcrdma_register_external(struct rpcrdma_mr_seg *,
 				int, int, struct rpcrdma_xprt *);
 int rpcrdma_deregister_external(struct rpcrdma_mr_seg *,
-				struct rpcrdma_xprt *, void *);
+				struct rpcrdma_xprt *);
 
 /*
  * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c
  */
+void rpcrdma_connect_worker(struct work_struct *);
 void rpcrdma_conn_func(struct rpcrdma_ep *);
 void rpcrdma_reply_handler(struct rpcrdma_rep *);
 
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 402a7e9a16b..be8bbd5d65e 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -866,8 +866,6 @@ static void xs_reset_transport(struct sock_xprt *transport)
 	xs_restore_old_callbacks(transport, sk);
 	write_unlock_bh(&sk->sk_callback_lock);
 
-	sk->sk_no_check = 0;
-
 	trace_rpc_socket_close(&transport->xprt, sock);
 	sock_release(sock);
 }
@@ -2046,7 +2044,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		sk->sk_user_data = xprt;
 		sk->sk_data_ready = xs_udp_data_ready;
 		sk->sk_write_space = xs_udp_write_space;
-		sk->sk_no_check = UDP_CSUM_NORCV;
 		sk->sk_allocation = GFP_ATOMIC;
 
 		xprt_set_connected(xprt);
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index b282f7130d2..a080c66d819 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -5,7 +5,7 @@
 obj-$(CONFIG_TIPC) := tipc.o
 
 tipc-y	+= addr.o bcast.o bearer.o config.o \
-	   core.o handler.o link.o discover.o msg.o  \
+	   core.o link.o discover.o msg.o  \
 	   name_distr.o  subscr.o name_table.o net.o  \
 	   netlink.o node.o node_subscr.o port.o ref.o  \
 	   socket.o log.o eth_media.o server.o
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 95ab5ef9292..55c6c9d3e1c 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -71,7 +71,7 @@ struct tipc_bcbearer_pair {
  * Note: The fields labelled "temporary" are incorporated into the bearer
  * to avoid consuming potentially limited stack space through the use of
  * large local variables within multicast routines.  Concurrent access is
- * prevented through use of the spinlock "bc_lock".
+ * prevented through use of the spinlock "bclink_lock".
  */
 struct tipc_bcbearer {
 	struct tipc_bearer bearer;
@@ -84,34 +84,64 @@ struct tipc_bcbearer {
 
 /**
  * struct tipc_bclink - link used for broadcast messages
+ * @lock: spinlock governing access to structure
  * @link: (non-standard) broadcast link structure
  * @node: (non-standard) node structure representing b'cast link's peer node
+ * @flags: represent bclink states
  * @bcast_nodes: map of broadcast-capable nodes
  * @retransmit_to: node that most recently requested a retransmit
  *
  * Handles sequence numbering, fragmentation, bundling, etc.
  */
 struct tipc_bclink {
+	spinlock_t lock;
 	struct tipc_link link;
 	struct tipc_node node;
+	unsigned int flags;
 	struct tipc_node_map bcast_nodes;
 	struct tipc_node *retransmit_to;
 };
 
-static struct tipc_bcbearer bcast_bearer;
-static struct tipc_bclink bcast_link;
-
-static struct tipc_bcbearer *bcbearer = &bcast_bearer;
-static struct tipc_bclink *bclink = &bcast_link;
-static struct tipc_link *bcl = &bcast_link.link;
-
-static DEFINE_SPINLOCK(bc_lock);
+static struct tipc_bcbearer *bcbearer;
+static struct tipc_bclink *bclink;
+static struct tipc_link *bcl;
 
 const char tipc_bclink_name[] = "broadcast-link";
 
 static void tipc_nmap_diff(struct tipc_node_map *nm_a,
 			   struct tipc_node_map *nm_b,
 			   struct tipc_node_map *nm_diff);
+static void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node);
+static void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node);
+
+static void tipc_bclink_lock(void)
+{
+	spin_lock_bh(&bclink->lock);
+}
+
+static void tipc_bclink_unlock(void)
+{
+	struct tipc_node *node = NULL;
+
+	if (likely(!bclink->flags)) {
+		spin_unlock_bh(&bclink->lock);
+		return;
+	}
+
+	if (bclink->flags & TIPC_BCLINK_RESET) {
+		bclink->flags &= ~TIPC_BCLINK_RESET;
+		node = tipc_bclink_retransmit_to();
+	}
+	spin_unlock_bh(&bclink->lock);
+
+	if (node)
+		tipc_link_reset_all(node);
+}
+
+void tipc_bclink_set_flags(unsigned int flags)
+{
+	bclink->flags |= flags;
+}
 
 static u32 bcbuf_acks(struct sk_buff *buf)
 {
@@ -130,16 +160,16 @@ static void bcbuf_decr_acks(struct sk_buff *buf)
 
 void tipc_bclink_add_node(u32 addr)
 {
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 	tipc_nmap_add(&bclink->bcast_nodes, addr);
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 }
 
 void tipc_bclink_remove_node(u32 addr)
 {
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 	tipc_nmap_remove(&bclink->bcast_nodes, addr);
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 }
 
 static void bclink_set_last_sent(void)
@@ -165,7 +195,7 @@ static void bclink_update_last_sent(struct tipc_node *node, u32 seqno)
 /**
  * tipc_bclink_retransmit_to - get most recent node to request retransmission
  *
- * Called with bc_lock locked
+ * Called with bclink_lock locked
  */
 struct tipc_node *tipc_bclink_retransmit_to(void)
 {
@@ -177,7 +207,7 @@ struct tipc_node *tipc_bclink_retransmit_to(void)
  * @after: sequence number of last packet to *not* retransmit
  * @to: sequence number of last packet to retransmit
  *
- * Called with bc_lock locked
+ * Called with bclink_lock locked
  */
 static void bclink_retransmit_pkt(u32 after, u32 to)
 {
@@ -194,7 +224,7 @@ static void bclink_retransmit_pkt(u32 after, u32 to)
  * @n_ptr: node that sent acknowledgement info
  * @acked: broadcast sequence # that has been acknowledged
  *
- * Node is locked, bc_lock unlocked.
+ * Node is locked, bclink_lock unlocked.
  */
 void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
 {
@@ -202,8 +232,7 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
 	struct sk_buff *next;
 	unsigned int released = 0;
 
-	spin_lock_bh(&bc_lock);
-
+	tipc_bclink_lock();
 	/* Bail out if tx queue is empty (no clean up is required) */
 	crs = bcl->first_out;
 	if (!crs)
@@ -267,13 +296,13 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked)
 	if (unlikely(released && !list_empty(&bcl->waiting_ports)))
 		tipc_link_wakeup_ports(bcl, 0);
 exit:
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 }
 
 /**
  * tipc_bclink_update_link_state - update broadcast link state
  *
- * tipc_net_lock and node lock set
+ * RCU and node lock set
  */
 void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent)
 {
@@ -320,10 +349,10 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent)
 				 ? buf_seqno(n_ptr->bclink.deferred_head) - 1
 				 : n_ptr->bclink.last_sent);
 
-		spin_lock_bh(&bc_lock);
-		tipc_bearer_send(&bcbearer->bearer, buf, NULL);
+		tipc_bclink_lock();
+		tipc_bearer_send(MAX_BEARERS, buf, NULL);
 		bcl->stats.sent_nacks++;
-		spin_unlock_bh(&bc_lock);
+		tipc_bclink_unlock();
 		kfree_skb(buf);
 
 		n_ptr->bclink.oos_state++;
@@ -335,8 +364,6 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent)
  *
  * Delay any upcoming NACK by this node if another node has already
  * requested the first message this node is going to ask for.
- *
- * Only tipc_net_lock set.
  */
 static void bclink_peek_nack(struct tipc_msg *msg)
 {
@@ -362,7 +389,7 @@ int tipc_bclink_xmit(struct sk_buff *buf)
 {
 	int res;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 
 	if (!bclink->bcast_nodes.count) {
 		res = msg_data_sz(buf_msg(buf));
@@ -377,14 +404,14 @@ int tipc_bclink_xmit(struct sk_buff *buf)
 		bcl->stats.accu_queue_sz += bcl->out_queue_size;
 	}
 exit:
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 	return res;
 }
 
 /**
  * bclink_accept_pkt - accept an incoming, in-sequence broadcast packet
  *
- * Called with both sending node's lock and bc_lock taken.
+ * Called with both sending node's lock and bclink_lock taken.
  */
 static void bclink_accept_pkt(struct tipc_node *node, u32 seqno)
 {
@@ -408,7 +435,7 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno)
 /**
  * tipc_bclink_rcv - receive a broadcast packet, and deliver upwards
  *
- * tipc_net_lock is read_locked, no other locks set
+ * RCU is locked, no other locks set
  */
 void tipc_bclink_rcv(struct sk_buff *buf)
 {
@@ -439,12 +466,12 @@ void tipc_bclink_rcv(struct sk_buff *buf)
 		if (msg_destnode(msg) == tipc_own_addr) {
 			tipc_bclink_acknowledge(node, msg_bcast_ack(msg));
 			tipc_node_unlock(node);
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bcl->stats.recv_nacks++;
 			bclink->retransmit_to = node;
 			bclink_retransmit_pkt(msg_bcgap_after(msg),
 					      msg_bcgap_to(msg));
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 		} else {
 			tipc_node_unlock(node);
 			bclink_peek_nack(msg);
@@ -462,51 +489,47 @@ receive:
 		/* Deliver message to destination */
 
 		if (likely(msg_isdata(msg))) {
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
 			if (likely(msg_mcast(msg)))
 				tipc_port_mcast_rcv(buf, NULL);
 			else
 				kfree_skb(buf);
 		} else if (msg_user(msg) == MSG_BUNDLER) {
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
 			bcl->stats.recv_bundles++;
 			bcl->stats.recv_bundled += msg_msgcnt(msg);
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
 			tipc_link_bundle_rcv(buf);
 		} else if (msg_user(msg) == MSG_FRAGMENTER) {
-			int ret;
-			ret = tipc_link_frag_rcv(&node->bclink.reasm_head,
-						 &node->bclink.reasm_tail,
-						 &buf);
-			if (ret == LINK_REASM_ERROR)
+			tipc_buf_append(&node->bclink.reasm_buf, &buf);
+			if (unlikely(!buf && !node->bclink.reasm_buf))
 				goto unlock;
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
 			bcl->stats.recv_fragments++;
-			if (ret == LINK_REASM_COMPLETE) {
+			if (buf) {
 				bcl->stats.recv_fragmented++;
-				/* Point msg to inner header */
 				msg = buf_msg(buf);
-				spin_unlock_bh(&bc_lock);
+				tipc_bclink_unlock();
 				goto receive;
 			}
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
 		} else if (msg_user(msg) == NAME_DISTRIBUTOR) {
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
 			tipc_named_rcv(buf);
 		} else {
-			spin_lock_bh(&bc_lock);
+			tipc_bclink_lock();
 			bclink_accept_pkt(node, seqno);
-			spin_unlock_bh(&bc_lock);
+			tipc_bclink_unlock();
 			tipc_node_unlock(node);
 			kfree_skb(buf);
 		}
@@ -536,6 +559,7 @@ receive:
 
 		buf = node->bclink.deferred_head;
 		node->bclink.deferred_head = buf->next;
+		buf->next = NULL;
 		node->bclink.deferred_size--;
 		goto receive;
 	}
@@ -552,14 +576,14 @@ receive:
 	} else
 		deferred = 0;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 
 	if (deferred)
 		bcl->stats.deferred_recv++;
 	else
 		bcl->stats.duplicates++;
 
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 
 unlock:
 	tipc_node_unlock(node);
@@ -627,13 +651,13 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1,
 
 		if (bp_index == 0) {
 			/* Use original buffer for first bearer */
-			tipc_bearer_send(b, buf, &b->bcast_addr);
+			tipc_bearer_send(b->identity, buf, &b->bcast_addr);
 		} else {
 			/* Avoid concurrent buffer access */
-			tbuf = pskb_copy(buf, GFP_ATOMIC);
+			tbuf = pskb_copy_for_clone(buf, GFP_ATOMIC);
 			if (!tbuf)
 				break;
-			tipc_bearer_send(b, tbuf, &b->bcast_addr);
+			tipc_bearer_send(b->identity, tbuf, &b->bcast_addr);
 			kfree_skb(tbuf); /* Bearer keeps a clone */
 		}
 
@@ -655,20 +679,27 @@ static int tipc_bcbearer_send(struct sk_buff *buf, struct tipc_bearer *unused1,
 /**
  * tipc_bcbearer_sort - create sets of bearer pairs used by broadcast bearer
  */
-void tipc_bcbearer_sort(void)
+void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action)
 {
 	struct tipc_bcbearer_pair *bp_temp = bcbearer->bpairs_temp;
 	struct tipc_bcbearer_pair *bp_curr;
+	struct tipc_bearer *b;
 	int b_index;
 	int pri;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
+
+	if (action)
+		tipc_nmap_add(nm_ptr, node);
+	else
+		tipc_nmap_remove(nm_ptr, node);
 
 	/* Group bearers by priority (can assume max of two per priority) */
 	memset(bp_temp, 0, sizeof(bcbearer->bpairs_temp));
 
+	rcu_read_lock();
 	for (b_index = 0; b_index < MAX_BEARERS; b_index++) {
-		struct tipc_bearer *b = bearer_list[b_index];
+		b = rcu_dereference_rtnl(bearer_list[b_index]);
 		if (!b || !b->nodes.count)
 			continue;
 
@@ -677,6 +708,7 @@ void tipc_bcbearer_sort(void)
 		else
 			bp_temp[b->priority].secondary = b;
 	}
+	rcu_read_unlock();
 
 	/* Create array of bearer pairs for broadcasting */
 	bp_curr = bcbearer->bpairs;
@@ -702,7 +734,7 @@ void tipc_bcbearer_sort(void)
 		bp_curr++;
 	}
 
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 }
 
 
@@ -714,7 +746,7 @@ int tipc_bclink_stats(char *buf, const u32 buf_size)
 	if (!bcl)
 		return 0;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 
 	s = &bcl->stats;
 
@@ -743,7 +775,7 @@ int tipc_bclink_stats(char *buf, const u32 buf_size)
 			     s->queue_sz_counts ?
 			     (s->accu_queue_sz / s->queue_sz_counts) : 0);
 
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 	return ret;
 }
 
@@ -752,9 +784,9 @@ int tipc_bclink_reset_stats(void)
 	if (!bcl)
 		return -ENOPROTOOPT;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 	memset(&bcl->stats, 0, sizeof(bcl->stats));
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 	return 0;
 }
 
@@ -765,46 +797,59 @@ int tipc_bclink_set_queue_limits(u32 limit)
 	if ((limit < TIPC_MIN_LINK_WIN) || (limit > TIPC_MAX_LINK_WIN))
 		return -EINVAL;
 
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 	tipc_link_set_queue_limits(bcl, limit);
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 	return 0;
 }
 
-void tipc_bclink_init(void)
+int tipc_bclink_init(void)
 {
+	bcbearer = kzalloc(sizeof(*bcbearer), GFP_ATOMIC);
+	if (!bcbearer)
+		return -ENOMEM;
+
+	bclink = kzalloc(sizeof(*bclink), GFP_ATOMIC);
+	if (!bclink) {
+		kfree(bcbearer);
+		return -ENOMEM;
+	}
+
+	bcl = &bclink->link;
 	bcbearer->bearer.media = &bcbearer->media;
 	bcbearer->media.send_msg = tipc_bcbearer_send;
 	sprintf(bcbearer->media.name, "tipc-broadcast");
 
+	spin_lock_init(&bclink->lock);
 	INIT_LIST_HEAD(&bcl->waiting_ports);
 	bcl->next_out_no = 1;
 	spin_lock_init(&bclink->node.lock);
 	bcl->owner = &bclink->node;
 	bcl->max_pkt = MAX_PKT_DEFAULT_MCAST;
 	tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT);
-	bcl->b_ptr = &bcbearer->bearer;
-	bearer_list[BCBEARER] = &bcbearer->bearer;
+	bcl->bearer_id = MAX_BEARERS;
+	rcu_assign_pointer(bearer_list[MAX_BEARERS], &bcbearer->bearer);
 	bcl->state = WORKING_WORKING;
 	strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME);
+	return 0;
 }
 
 void tipc_bclink_stop(void)
 {
-	spin_lock_bh(&bc_lock);
+	tipc_bclink_lock();
 	tipc_link_purge_queues(bcl);
-	spin_unlock_bh(&bc_lock);
+	tipc_bclink_unlock();
 
-	bearer_list[BCBEARER] = NULL;
-	memset(bclink, 0, sizeof(*bclink));
-	memset(bcbearer, 0, sizeof(*bcbearer));
+	RCU_INIT_POINTER(bearer_list[BCBEARER], NULL);
+	synchronize_net();
+	kfree(bcbearer);
+	kfree(bclink);
 }
 
-
 /**
  * tipc_nmap_add - add a node to a node map
  */
-void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node)
+static void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node)
 {
 	int n = tipc_node(node);
 	int w = n / WSIZE;
@@ -819,7 +864,7 @@ void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node)
 /**
  * tipc_nmap_remove - remove a node from a node map
  */
-void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node)
+static void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node)
 {
 	int n = tipc_node(node);
 	int w = n / WSIZE;
diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h
index a80ef54b818..00330c45df3 100644
--- a/net/tipc/bcast.h
+++ b/net/tipc/bcast.h
@@ -39,6 +39,7 @@
 
 #define MAX_NODES 4096
 #define WSIZE 32
+#define TIPC_BCLINK_RESET 1
 
 /**
  * struct tipc_node_map - set of node identifiers
@@ -69,9 +70,6 @@ struct tipc_node;
 
 extern const char tipc_bclink_name[];
 
-void tipc_nmap_add(struct tipc_node_map *nm_ptr, u32 node);
-void tipc_nmap_remove(struct tipc_node_map *nm_ptr, u32 node);
-
 /**
  * tipc_nmap_equal - test for equality of node maps
  */
@@ -84,8 +82,9 @@ static inline int tipc_nmap_equal(struct tipc_node_map *nm_a,
 void tipc_port_list_add(struct tipc_port_list *pl_ptr, u32 port);
 void tipc_port_list_free(struct tipc_port_list *pl_ptr);
 
-void tipc_bclink_init(void);
+int tipc_bclink_init(void);
 void tipc_bclink_stop(void);
+void tipc_bclink_set_flags(unsigned int flags);
 void tipc_bclink_add_node(u32 addr);
 void tipc_bclink_remove_node(u32 addr);
 struct tipc_node *tipc_bclink_retransmit_to(void);
@@ -98,6 +97,6 @@ void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent);
 int  tipc_bclink_stats(char *stats_buf, const u32 buf_size);
 int  tipc_bclink_reset_stats(void);
 int  tipc_bclink_set_queue_limits(u32 limit);
-void tipc_bcbearer_sort(void);
+void tipc_bcbearer_sort(struct tipc_node_map *nm_ptr, u32 node, bool action);
 
 #endif
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 3fef7eb776d..264474394f9 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -49,7 +49,7 @@ static struct tipc_media * const media_info_array[] = {
 	NULL
 };
 
-struct tipc_bearer *bearer_list[MAX_BEARERS + 1];
+struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1];
 
 static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down);
 
@@ -178,7 +178,7 @@ struct tipc_bearer *tipc_bearer_find(const char *name)
 	u32 i;
 
 	for (i = 0; i < MAX_BEARERS; i++) {
-		b_ptr = bearer_list[i];
+		b_ptr = rtnl_dereference(bearer_list[i]);
 		if (b_ptr && (!strcmp(b_ptr->name, name)))
 			return b_ptr;
 	}
@@ -198,10 +198,9 @@ struct sk_buff *tipc_bearer_get_names(void)
 	if (!buf)
 		return NULL;
 
-	read_lock_bh(&tipc_net_lock);
 	for (i = 0; media_info_array[i] != NULL; i++) {
 		for (j = 0; j < MAX_BEARERS; j++) {
-			b = bearer_list[j];
+			b = rtnl_dereference(bearer_list[j]);
 			if (!b)
 				continue;
 			if (b->media == media_info_array[i]) {
@@ -211,22 +210,33 @@ struct sk_buff *tipc_bearer_get_names(void)
 			}
 		}
 	}
-	read_unlock_bh(&tipc_net_lock);
 	return buf;
 }
 
-void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest)
+void tipc_bearer_add_dest(u32 bearer_id, u32 dest)
 {
-	tipc_nmap_add(&b_ptr->nodes, dest);
-	tipc_bcbearer_sort();
-	tipc_disc_add_dest(b_ptr->link_req);
+	struct tipc_bearer *b_ptr;
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]);
+	if (b_ptr) {
+		tipc_bcbearer_sort(&b_ptr->nodes, dest, true);
+		tipc_disc_add_dest(b_ptr->link_req);
+	}
+	rcu_read_unlock();
 }
 
-void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest)
+void tipc_bearer_remove_dest(u32 bearer_id, u32 dest)
 {
-	tipc_nmap_remove(&b_ptr->nodes, dest);
-	tipc_bcbearer_sort();
-	tipc_disc_remove_dest(b_ptr->link_req);
+	struct tipc_bearer *b_ptr;
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]);
+	if (b_ptr) {
+		tipc_bcbearer_sort(&b_ptr->nodes, dest, false);
+		tipc_disc_remove_dest(b_ptr->link_req);
+	}
+	rcu_read_unlock();
 }
 
 /**
@@ -271,13 +281,11 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority)
 		return -EINVAL;
 	}
 
-	write_lock_bh(&tipc_net_lock);
-
 	m_ptr = tipc_media_find(b_names.media_name);
 	if (!m_ptr) {
 		pr_warn("Bearer <%s> rejected, media <%s> not registered\n",
 			name, b_names.media_name);
-		goto exit;
+		return -EINVAL;
 	}
 
 	if (priority == TIPC_MEDIA_LINK_PRI)
@@ -287,7 +295,7 @@ restart:
 	bearer_id = MAX_BEARERS;
 	with_this_prio = 1;
 	for (i = MAX_BEARERS; i-- != 0; ) {
-		b_ptr = bearer_list[i];
+		b_ptr = rtnl_dereference(bearer_list[i]);
 		if (!b_ptr) {
 			bearer_id = i;
 			continue;
@@ -295,14 +303,14 @@ restart:
 		if (!strcmp(name, b_ptr->name)) {
 			pr_warn("Bearer <%s> rejected, already enabled\n",
 				name);
-			goto exit;
+			return -EINVAL;
 		}
 		if ((b_ptr->priority == priority) &&
 		    (++with_this_prio > 2)) {
 			if (priority-- == 0) {
 				pr_warn("Bearer <%s> rejected, duplicate priority\n",
 					name);
-				goto exit;
+				return -EINVAL;
 			}
 			pr_warn("Bearer <%s> priority adjustment required %u->%u\n",
 				name, priority + 1, priority);
@@ -312,21 +320,20 @@ restart:
 	if (bearer_id >= MAX_BEARERS) {
 		pr_warn("Bearer <%s> rejected, bearer limit reached (%u)\n",
 			name, MAX_BEARERS);
-		goto exit;
+		return -EINVAL;
 	}
 
 	b_ptr = kzalloc(sizeof(*b_ptr), GFP_ATOMIC);
-	if (!b_ptr) {
-		res = -ENOMEM;
-		goto exit;
-	}
+	if (!b_ptr)
+		return -ENOMEM;
+
 	strcpy(b_ptr->name, name);
 	b_ptr->media = m_ptr;
 	res = m_ptr->enable_media(b_ptr);
 	if (res) {
 		pr_warn("Bearer <%s> rejected, enable failure (%d)\n",
 			name, -res);
-		goto exit;
+		return -EINVAL;
 	}
 
 	b_ptr->identity = bearer_id;
@@ -341,16 +348,14 @@ restart:
 		bearer_disable(b_ptr, false);
 		pr_warn("Bearer <%s> rejected, discovery object creation failed\n",
 			name);
-		goto exit;
+		return -EINVAL;
 	}
 
-	bearer_list[bearer_id] = b_ptr;
+	rcu_assign_pointer(bearer_list[bearer_id], b_ptr);
 
 	pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n",
 		name,
 		tipc_addr_string_fill(addr_string, disc_domain), priority);
-exit:
-	write_unlock_bh(&tipc_net_lock);
 	return res;
 }
 
@@ -359,19 +364,16 @@ exit:
  */
 static int tipc_reset_bearer(struct tipc_bearer *b_ptr)
 {
-	read_lock_bh(&tipc_net_lock);
 	pr_info("Resetting bearer <%s>\n", b_ptr->name);
-	tipc_disc_delete(b_ptr->link_req);
 	tipc_link_reset_list(b_ptr->identity);
-	tipc_disc_create(b_ptr, &b_ptr->bcast_addr);
-	read_unlock_bh(&tipc_net_lock);
+	tipc_disc_reset(b_ptr);
 	return 0;
 }
 
 /**
  * bearer_disable
  *
- * Note: This routine assumes caller holds tipc_net_lock.
+ * Note: This routine assumes caller holds RTNL lock.
  */
 static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down)
 {
@@ -385,12 +387,12 @@ static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down)
 		tipc_disc_delete(b_ptr->link_req);
 
 	for (i = 0; i < MAX_BEARERS; i++) {
-		if (b_ptr == bearer_list[i]) {
-			bearer_list[i] = NULL;
+		if (b_ptr == rtnl_dereference(bearer_list[i])) {
+			RCU_INIT_POINTER(bearer_list[i], NULL);
 			break;
 		}
 	}
-	kfree(b_ptr);
+	kfree_rcu(b_ptr, rcu);
 }
 
 int tipc_disable_bearer(const char *name)
@@ -398,7 +400,6 @@ int tipc_disable_bearer(const char *name)
 	struct tipc_bearer *b_ptr;
 	int res;
 
-	write_lock_bh(&tipc_net_lock);
 	b_ptr = tipc_bearer_find(name);
 	if (b_ptr == NULL) {
 		pr_warn("Attempt to disable unknown bearer <%s>\n", name);
@@ -407,32 +408,9 @@ int tipc_disable_bearer(const char *name)
 		bearer_disable(b_ptr, false);
 		res = 0;
 	}
-	write_unlock_bh(&tipc_net_lock);
 	return res;
 }
 
-
-/* tipc_l2_media_addr_set - initialize Ethernet media address structure
- *
- * Media-dependent "value" field stores MAC address in first 6 bytes
- * and zeroes out the remaining bytes.
- */
-void tipc_l2_media_addr_set(const struct tipc_bearer *b,
-			    struct tipc_media_addr *a, char *mac)
-{
-	int len = b->media->hwaddr_len;
-
-	if (unlikely(sizeof(a->value) < len)) {
-		WARN_ONCE(1, "Media length invalid\n");
-		return;
-	}
-
-	memcpy(a->value, mac, len);
-	memset(a->value + len, 0, sizeof(a->value) - len);
-	a->media_id = b->media->type_id;
-	a->broadcast = !memcmp(mac, b->bcast_addr.value, len);
-}
-
 int tipc_enable_l2_media(struct tipc_bearer *b)
 {
 	struct net_device *dev;
@@ -443,33 +421,37 @@ int tipc_enable_l2_media(struct tipc_bearer *b)
 	if (!dev)
 		return -ENODEV;
 
-	/* Associate TIPC bearer with Ethernet bearer */
-	b->media_ptr = dev;
-	memset(b->bcast_addr.value, 0, sizeof(b->bcast_addr.value));
+	/* Associate TIPC bearer with L2 bearer */
+	rcu_assign_pointer(b->media_ptr, dev);
+	memset(&b->bcast_addr, 0, sizeof(b->bcast_addr));
 	memcpy(b->bcast_addr.value, dev->broadcast, b->media->hwaddr_len);
 	b->bcast_addr.media_id = b->media->type_id;
 	b->bcast_addr.broadcast = 1;
 	b->mtu = dev->mtu;
-	tipc_l2_media_addr_set(b, &b->addr, (char *)dev->dev_addr);
+	b->media->raw2addr(b, &b->addr, (char *)dev->dev_addr);
 	rcu_assign_pointer(dev->tipc_ptr, b);
 	return 0;
 }
 
-/* tipc_disable_l2_media - detach TIPC bearer from an Ethernet interface
+/* tipc_disable_l2_media - detach TIPC bearer from an L2 interface
  *
- * Mark Ethernet bearer as inactive so that incoming buffers are thrown away,
+ * Mark L2 bearer as inactive so that incoming buffers are thrown away,
  * then get worker thread to complete bearer cleanup.  (Can't do cleanup
  * here because cleanup code needs to sleep and caller holds spinlocks.)
  */
 void tipc_disable_l2_media(struct tipc_bearer *b)
 {
-	struct net_device *dev = (struct net_device *)b->media_ptr;
+	struct net_device *dev;
+
+	dev = (struct net_device *)rtnl_dereference(b->media_ptr);
+	RCU_INIT_POINTER(b->media_ptr, NULL);
 	RCU_INIT_POINTER(dev->tipc_ptr, NULL);
+	synchronize_net();
 	dev_put(dev);
 }
 
 /**
- * tipc_l2_send_msg - send a TIPC packet out over an Ethernet interface
+ * tipc_l2_send_msg - send a TIPC packet out over an L2 interface
  * @buf: the packet to be sent
  * @b_ptr: the bearer through which the packet is to be sent
  * @dest: peer destination address
@@ -478,8 +460,12 @@ int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b,
 		     struct tipc_media_addr *dest)
 {
 	struct sk_buff *clone;
+	struct net_device *dev;
 	int delta;
-	struct net_device *dev = (struct net_device *)b->media_ptr;
+
+	dev = (struct net_device *)rcu_dereference_rtnl(b->media_ptr);
+	if (!dev)
+		return 0;
 
 	clone = skb_clone(buf, GFP_ATOMIC);
 	if (!clone)
@@ -507,10 +493,16 @@ int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b,
  * The media send routine must not alter the buffer being passed in
  * as it may be needed for later retransmission!
  */
-void tipc_bearer_send(struct tipc_bearer *b, struct sk_buff *buf,
+void tipc_bearer_send(u32 bearer_id, struct sk_buff *buf,
 		      struct tipc_media_addr *dest)
 {
-	b->media->send_msg(buf, b, dest);
+	struct tipc_bearer *b_ptr;
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[bearer_id]);
+	if (likely(b_ptr))
+		b_ptr->media->send_msg(buf, b_ptr, dest);
+	rcu_read_unlock();
 }
 
 /**
@@ -535,7 +527,7 @@ static int tipc_l2_rcv_msg(struct sk_buff *buf, struct net_device *dev,
 	}
 
 	rcu_read_lock();
-	b_ptr = rcu_dereference(dev->tipc_ptr);
+	b_ptr = rcu_dereference_rtnl(dev->tipc_ptr);
 	if (likely(b_ptr)) {
 		if (likely(buf->pkt_type <= PACKET_BROADCAST)) {
 			buf->next = NULL;
@@ -568,12 +560,9 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
 	if (!net_eq(dev_net(dev), &init_net))
 		return NOTIFY_DONE;
 
-	rcu_read_lock();
-	b_ptr = rcu_dereference(dev->tipc_ptr);
-	if (!b_ptr) {
-		rcu_read_unlock();
+	b_ptr = rtnl_dereference(dev->tipc_ptr);
+	if (!b_ptr)
 		return NOTIFY_DONE;
-	}
 
 	b_ptr->mtu = dev->mtu;
 
@@ -586,17 +575,15 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
 		tipc_reset_bearer(b_ptr);
 		break;
 	case NETDEV_CHANGEADDR:
-		tipc_l2_media_addr_set(b_ptr, &b_ptr->addr,
+		b_ptr->media->raw2addr(b_ptr, &b_ptr->addr,
 				       (char *)dev->dev_addr);
 		tipc_reset_bearer(b_ptr);
 		break;
 	case NETDEV_UNREGISTER:
 	case NETDEV_CHANGENAME:
-		tipc_disable_bearer(b_ptr->name);
+		bearer_disable(b_ptr, false);
 		break;
 	}
-	rcu_read_unlock();
-
 	return NOTIFY_OK;
 }
 
@@ -633,7 +620,7 @@ void tipc_bearer_stop(void)
 	u32 i;
 
 	for (i = 0; i < MAX_BEARERS; i++) {
-		b_ptr = bearer_list[i];
+		b_ptr = rtnl_dereference(bearer_list[i]);
 		if (b_ptr) {
 			bearer_disable(b_ptr, true);
 			bearer_list[i] = NULL;
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index ba48145e871..78fccc49de2 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -42,14 +42,12 @@
 #define MAX_BEARERS	2
 #define MAX_MEDIA	2
 
-/*
- * Identifiers associated with TIPC message header media address info
- *
- * - address info field is 20 bytes long
- * - media type identifier located at offset 3
- * - remaining bytes vary according to media type
+/* Identifiers associated with TIPC message header media address info
+ * - address info field is 32 bytes long
+ * - the field's actual content and length is defined per media
+ * - remaining unused bytes in the field are set to zero
  */
-#define TIPC_MEDIA_ADDR_SIZE	20
+#define TIPC_MEDIA_ADDR_SIZE	32
 #define TIPC_MEDIA_TYPE_OFFSET	3
 
 /*
@@ -77,9 +75,10 @@ struct tipc_bearer;
  * @send_msg: routine which handles buffer transmission
  * @enable_media: routine which enables a media
  * @disable_media: routine which disables a media
- * @addr2str: routine which converts media address to string
- * @addr2msg: routine which converts media address to protocol message area
- * @msg2addr: routine which converts media address from protocol message area
+ * @addr2str: convert media address format to string
+ * @addr2msg: convert from media addr format to discovery msg addr format
+ * @msg2addr: convert from discovery msg addr format to media addr format
+ * @raw2addr: convert from raw addr format to media addr format
  * @priority: default link (and bearer) priority
  * @tolerance: default time (in ms) before declaring link failure
  * @window: default window (in packets) before declaring link congestion
@@ -93,10 +92,16 @@ struct tipc_media {
 			struct tipc_media_addr *dest);
 	int (*enable_media)(struct tipc_bearer *b_ptr);
 	void (*disable_media)(struct tipc_bearer *b_ptr);
-	int (*addr2str)(struct tipc_media_addr *a, char *str_buf, int str_size);
-	int (*addr2msg)(struct tipc_media_addr *a, char *msg_area);
-	int (*msg2addr)(const struct tipc_bearer *b_ptr,
-			struct tipc_media_addr *a, char *msg_area);
+	int (*addr2str)(struct tipc_media_addr *addr,
+			char *strbuf,
+			int bufsz);
+	int (*addr2msg)(char *msg, struct tipc_media_addr *addr);
+	int (*msg2addr)(struct tipc_bearer *b,
+			struct tipc_media_addr *addr,
+			char *msg);
+	int (*raw2addr)(struct tipc_bearer *b,
+			struct tipc_media_addr *addr,
+			char *raw);
 	u32 priority;
 	u32 tolerance;
 	u32 window;
@@ -113,6 +118,7 @@ struct tipc_media {
  * @name: bearer name (format = media:interface)
  * @media: ptr to media structure associated with bearer
  * @bcast_addr: media address used in broadcasting
+ * @rcu: rcu struct for tipc_bearer
  * @priority: default link priority for bearer
  * @window: default window size for bearer
  * @tolerance: default link tolerance for bearer
@@ -127,12 +133,13 @@ struct tipc_media {
  * care of initializing all other fields.
  */
 struct tipc_bearer {
-	void *media_ptr;			/* initalized by media */
+	void __rcu *media_ptr;			/* initalized by media */
 	u32 mtu;				/* initalized by media */
 	struct tipc_media_addr addr;		/* initalized by media */
 	char name[TIPC_MAX_BEARER_NAME];
 	struct tipc_media *media;
 	struct tipc_media_addr bcast_addr;
+	struct rcu_head rcu;
 	u32 priority;
 	u32 window;
 	u32 tolerance;
@@ -150,7 +157,7 @@ struct tipc_bearer_names {
 
 struct tipc_link;
 
-extern struct tipc_bearer *bearer_list[];
+extern struct tipc_bearer __rcu *bearer_list[];
 
 /*
  * TIPC routines available to supported media types
@@ -173,22 +180,20 @@ int tipc_media_set_priority(const char *name, u32 new_value);
 int tipc_media_set_window(const char *name, u32 new_value);
 void tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a);
 struct sk_buff *tipc_media_get_names(void);
-void tipc_l2_media_addr_set(const struct tipc_bearer *b,
-			    struct tipc_media_addr *a, char *mac);
 int tipc_enable_l2_media(struct tipc_bearer *b);
 void tipc_disable_l2_media(struct tipc_bearer *b);
 int tipc_l2_send_msg(struct sk_buff *buf, struct tipc_bearer *b,
 		     struct tipc_media_addr *dest);
 
 struct sk_buff *tipc_bearer_get_names(void);
-void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest);
-void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest);
+void tipc_bearer_add_dest(u32 bearer_id, u32 dest);
+void tipc_bearer_remove_dest(u32 bearer_id, u32 dest);
 struct tipc_bearer *tipc_bearer_find(const char *name);
 struct tipc_media *tipc_media_find(const char *name);
 int tipc_bearer_setup(void);
 void tipc_bearer_cleanup(void);
 void tipc_bearer_stop(void);
-void tipc_bearer_send(struct tipc_bearer *b, struct sk_buff *buf,
+void tipc_bearer_send(u32 bearer_id, struct sk_buff *buf,
 		      struct tipc_media_addr *dest);
 
 #endif	/* _TIPC_BEARER_H */
diff --git a/net/tipc/config.c b/net/tipc/config.c
index 4b981c05382..2b42403ad33 100644
--- a/net/tipc/config.c
+++ b/net/tipc/config.c
@@ -42,8 +42,6 @@
 
 #define REPLY_TRUNCATED "<truncated>\n"
 
-static DEFINE_MUTEX(config_mutex);
-
 static const void *req_tlv_area;	/* request message TLV area */
 static int req_tlv_space;		/* request message TLV area size */
 static int rep_headroom;		/* reply message headroom to use */
@@ -179,8 +177,10 @@ static struct sk_buff *cfg_set_own_addr(void)
 	if (tipc_own_addr)
 		return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED
 						   " (cannot change node address once assigned)");
-	tipc_net_start(addr);
-	return tipc_cfg_reply_none();
+	if (!tipc_net_start(addr))
+		return tipc_cfg_reply_none();
+
+	return tipc_cfg_reply_error_string("cannot change to network mode");
 }
 
 static struct sk_buff *cfg_set_max_ports(void)
@@ -223,7 +223,7 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 {
 	struct sk_buff *rep_tlv_buf;
 
-	mutex_lock(&config_mutex);
+	rtnl_lock();
 
 	/* Save request and reply details in a well-known location */
 	req_tlv_area = request_area;
@@ -337,6 +337,6 @@ struct sk_buff *tipc_cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area
 
 	/* Return reply buffer */
 exit:
-	mutex_unlock(&config_mutex);
+	rtnl_unlock();
 	return rep_tlv_buf;
 }
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 50d57429ebc..676d18015dd 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -80,7 +80,6 @@ struct sk_buff *tipc_buf_acquire(u32 size)
  */
 static void tipc_core_stop(void)
 {
-	tipc_handler_stop();
 	tipc_net_stop();
 	tipc_bearer_cleanup();
 	tipc_netlink_stop();
@@ -100,10 +99,6 @@ static int tipc_core_start(void)
 
 	get_random_bytes(&tipc_random, sizeof(tipc_random));
 
-	err = tipc_handler_start();
-	if (err)
-		goto out_handler;
-
 	err = tipc_ref_table_init(tipc_max_ports, tipc_random);
 	if (err)
 		goto out_reftbl;
@@ -146,8 +141,6 @@ out_netlink:
 out_nametbl:
 	tipc_ref_table_stop();
 out_reftbl:
-	tipc_handler_stop();
-out_handler:
 	return err;
 }
 
@@ -161,10 +154,11 @@ static int __init tipc_init(void)
 	tipc_max_ports = CONFIG_TIPC_PORTS;
 	tipc_net_id = 4711;
 
-	sysctl_tipc_rmem[0] = CONN_OVERLOAD_LIMIT >> 4 << TIPC_LOW_IMPORTANCE;
-	sysctl_tipc_rmem[1] = CONN_OVERLOAD_LIMIT >> 4 <<
+	sysctl_tipc_rmem[0] = TIPC_CONN_OVERLOAD_LIMIT >> 4 <<
+			      TIPC_LOW_IMPORTANCE;
+	sysctl_tipc_rmem[1] = TIPC_CONN_OVERLOAD_LIMIT >> 4 <<
 			      TIPC_CRITICAL_IMPORTANCE;
-	sysctl_tipc_rmem[2] = CONN_OVERLOAD_LIMIT;
+	sysctl_tipc_rmem[2] = TIPC_CONN_OVERLOAD_LIMIT;
 
 	res = tipc_core_start();
 	if (res)
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 8985bbcb942..bb26ed1ee96 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -56,7 +56,8 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-
+#include <linux/rtnetlink.h>
+#include <linux/etherdevice.h>
 
 #define TIPC_MOD_VER "2.0.0"
 
@@ -89,8 +90,6 @@ extern int tipc_random __read_mostly;
 /*
  * Routines available to privileged subsystems
  */
-int tipc_handler_start(void);
-void tipc_handler_stop(void);
 int tipc_netlink_start(void);
 void tipc_netlink_stop(void);
 int tipc_socket_init(void);
@@ -109,12 +108,10 @@ void tipc_unregister_sysctl(void);
 #endif
 
 /*
- * TIPC timer and signal code
+ * TIPC timer code
  */
 typedef void (*Handler) (unsigned long);
 
-u32 tipc_k_signal(Handler routine, unsigned long argument);
-
 /**
  * k_init_timer - initialize a timer
  * @timer: pointer to timer structure
@@ -191,6 +188,7 @@ static inline void k_term_timer(struct timer_list *timer)
 struct tipc_skb_cb {
 	void *handle;
 	bool deferred;
+	struct sk_buff *tail;
 };
 
 #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 542fe3413dc..aa722a42ef8 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/discover.c
  *
- * Copyright (c) 2003-2006, Ericsson AB
+ * Copyright (c) 2003-2006, 2014, Ericsson AB
  * Copyright (c) 2005-2006, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -46,8 +46,9 @@
 
 /**
  * struct tipc_link_req - information about an ongoing link setup request
- * @bearer: bearer issuing requests
+ * @bearer_id: identity of bearer issuing requests
  * @dest: destination address for request messages
+ * @domain: network domain to which links can be established
  * @num_nodes: number of nodes currently discovered (i.e. with an active link)
  * @lock: spinlock for controlling access to requests
  * @buf: request message to be (repeatedly) sent
@@ -55,8 +56,9 @@
  * @timer_intv: current interval between requests (in ms)
  */
 struct tipc_link_req {
-	struct tipc_bearer *bearer;
+	u32 bearer_id;
 	struct tipc_media_addr dest;
+	u32 domain;
 	int num_nodes;
 	spinlock_t lock;
 	struct sk_buff *buf;
@@ -69,22 +71,19 @@ struct tipc_link_req {
  * @type: message type (request or response)
  * @b_ptr: ptr to bearer issuing message
  */
-static struct sk_buff *tipc_disc_init_msg(u32 type, struct tipc_bearer *b_ptr)
+static void tipc_disc_init_msg(struct sk_buff *buf, u32 type,
+			       struct tipc_bearer *b_ptr)
 {
-	struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE);
 	struct tipc_msg *msg;
 	u32 dest_domain = b_ptr->domain;
 
-	if (buf) {
-		msg = buf_msg(buf);
-		tipc_msg_init(msg, LINK_CONFIG, type, INT_H_SIZE, dest_domain);
-		msg_set_non_seq(msg, 1);
-		msg_set_node_sig(msg, tipc_random);
-		msg_set_dest_domain(msg, dest_domain);
-		msg_set_bc_netid(msg, tipc_net_id);
-		b_ptr->media->addr2msg(&b_ptr->addr, msg_media_addr(msg));
-	}
-	return buf;
+	msg = buf_msg(buf);
+	tipc_msg_init(msg, LINK_CONFIG, type, INT_H_SIZE, dest_domain);
+	msg_set_non_seq(msg, 1);
+	msg_set_node_sig(msg, tipc_random);
+	msg_set_dest_domain(msg, dest_domain);
+	msg_set_bc_netid(msg, tipc_net_id);
+	b_ptr->media->addr2msg(msg_media_addr(msg), &b_ptr->addr);
 }
 
 /**
@@ -107,146 +106,150 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr,
 }
 
 /**
- * tipc_disc_rcv - handle incoming link setup message (request or response)
+ * tipc_disc_rcv - handle incoming discovery message (request or response)
  * @buf: buffer containing message
- * @b_ptr: bearer that message arrived on
+ * @bearer: bearer that message arrived on
  */
-void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr)
+void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *bearer)
 {
-	struct tipc_node *n_ptr;
+	struct tipc_node *node;
 	struct tipc_link *link;
-	struct tipc_media_addr media_addr;
+	struct tipc_media_addr maddr;
 	struct sk_buff *rbuf;
 	struct tipc_msg *msg = buf_msg(buf);
-	u32 dest = msg_dest_domain(msg);
-	u32 orig = msg_prevnode(msg);
+	u32 ddom = msg_dest_domain(msg);
+	u32 onode = msg_prevnode(msg);
 	u32 net_id = msg_bc_netid(msg);
-	u32 type = msg_type(msg);
+	u32 mtyp = msg_type(msg);
 	u32 signature = msg_node_sig(msg);
-	int addr_mismatch;
-	int link_fully_up;
-
-	media_addr.broadcast = 1;
-	b_ptr->media->msg2addr(b_ptr, &media_addr, msg_media_addr(msg));
+	bool addr_match = false;
+	bool sign_match = false;
+	bool link_up = false;
+	bool accept_addr = false;
+	bool accept_sign = false;
+	bool respond = false;
+
+	bearer->media->msg2addr(bearer, &maddr, msg_media_addr(msg));
 	kfree_skb(buf);
 
 	/* Ensure message from node is valid and communication is permitted */
 	if (net_id != tipc_net_id)
 		return;
-	if (media_addr.broadcast)
+	if (maddr.broadcast)
 		return;
-	if (!tipc_addr_domain_valid(dest))
+	if (!tipc_addr_domain_valid(ddom))
 		return;
-	if (!tipc_addr_node_valid(orig))
+	if (!tipc_addr_node_valid(onode))
 		return;
-	if (orig == tipc_own_addr) {
-		if (memcmp(&media_addr, &b_ptr->addr, sizeof(media_addr)))
-			disc_dupl_alert(b_ptr, tipc_own_addr, &media_addr);
+
+	if (in_own_node(onode)) {
+		if (memcmp(&maddr, &bearer->addr, sizeof(maddr)))
+			disc_dupl_alert(bearer, tipc_own_addr, &maddr);
 		return;
 	}
-	if (!tipc_in_scope(dest, tipc_own_addr))
+	if (!tipc_in_scope(ddom, tipc_own_addr))
 		return;
-	if (!tipc_in_scope(b_ptr->domain, orig))
+	if (!tipc_in_scope(bearer->domain, onode))
 		return;
 
-	/* Locate structure corresponding to requesting node */
-	n_ptr = tipc_node_find(orig);
-	if (!n_ptr) {
-		n_ptr = tipc_node_create(orig);
-		if (!n_ptr)
-			return;
-	}
-	tipc_node_lock(n_ptr);
+	/* Locate, or if necessary, create, node: */
+	node = tipc_node_find(onode);
+	if (!node)
+		node = tipc_node_create(onode);
+	if (!node)
+		return;
 
-	/* Prepare to validate requesting node's signature and media address */
-	link = n_ptr->links[b_ptr->identity];
-	addr_mismatch = (link != NULL) &&
-		memcmp(&link->media_addr, &media_addr, sizeof(media_addr));
+	tipc_node_lock(node);
+	link = node->links[bearer->identity];
 
-	/*
-	 * Ensure discovery message's signature is correct
-	 *
-	 * If signature is incorrect and there is no working link to the node,
-	 * accept the new signature but invalidate all existing links to the
-	 * node so they won't re-activate without a new discovery message.
-	 *
-	 * If signature is incorrect and the requested link to the node is
-	 * working, accept the new signature. (This is an instance of delayed
-	 * rediscovery, where a link endpoint was able to re-establish contact
-	 * with its peer endpoint on a node that rebooted before receiving a
-	 * discovery message from that node.)
-	 *
-	 * If signature is incorrect and there is a working link to the node
-	 * that is not the requested link, reject the request (must be from
-	 * a duplicate node).
-	 */
-	if (signature != n_ptr->signature) {
-		if (n_ptr->working_links == 0) {
-			struct tipc_link *curr_link;
-			int i;
-
-			for (i = 0; i < MAX_BEARERS; i++) {
-				curr_link = n_ptr->links[i];
-				if (curr_link) {
-					memset(&curr_link->media_addr, 0,
-					       sizeof(media_addr));
-					tipc_link_reset(curr_link);
-				}
-			}
-			addr_mismatch = (link != NULL);
-		} else if (tipc_link_is_up(link) && !addr_mismatch) {
-			/* delayed rediscovery */
-		} else {
-			disc_dupl_alert(b_ptr, orig, &media_addr);
-			tipc_node_unlock(n_ptr);
-			return;
-		}
-		n_ptr->signature = signature;
+	/* Prepare to validate requesting node's signature and media address */
+	sign_match = (signature == node->signature);
+	addr_match = link && !memcmp(&link->media_addr, &maddr, sizeof(maddr));
+	link_up = link && tipc_link_is_up(link);
+
+
+	/* These three flags give us eight permutations: */
+
+	if (sign_match && addr_match && link_up) {
+		/* All is fine. Do nothing. */
+	} else if (sign_match && addr_match && !link_up) {
+		/* Respond. The link will come up in due time */
+		respond = true;
+	} else if (sign_match && !addr_match && link_up) {
+		/* Peer has changed i/f address without rebooting.
+		 * If so, the link will reset soon, and the next
+		 * discovery will be accepted. So we can ignore it.
+		 * It may also be an cloned or malicious peer having
+		 * chosen the same node address and signature as an
+		 * existing one.
+		 * Ignore requests until the link goes down, if ever.
+		 */
+		disc_dupl_alert(bearer, onode, &maddr);
+	} else if (sign_match && !addr_match && !link_up) {
+		/* Peer link has changed i/f address without rebooting.
+		 * It may also be a cloned or malicious peer; we can't
+		 * distinguish between the two.
+		 * The signature is correct, so we must accept.
+		 */
+		accept_addr = true;
+		respond = true;
+	} else if (!sign_match && addr_match && link_up) {
+		/* Peer node rebooted. Two possibilities:
+		 *  - Delayed re-discovery; this link endpoint has already
+		 *    reset and re-established contact with the peer, before
+		 *    receiving a discovery message from that node.
+		 *    (The peer happened to receive one from this node first).
+		 *  - The peer came back so fast that our side has not
+		 *    discovered it yet. Probing from this side will soon
+		 *    reset the link, since there can be no working link
+		 *    endpoint at the peer end, and the link will re-establish.
+		 *  Accept the signature, since it comes from a known peer.
+		 */
+		accept_sign = true;
+	} else if (!sign_match && addr_match && !link_up) {
+		/*  The peer node has rebooted.
+		 *  Accept signature, since it is a known peer.
+		 */
+		accept_sign = true;
+		respond = true;
+	} else if (!sign_match && !addr_match && link_up) {
+		/* Peer rebooted with new address, or a new/duplicate peer.
+		 * Ignore until the link goes down, if ever.
+		 */
+		disc_dupl_alert(bearer, onode, &maddr);
+	} else if (!sign_match && !addr_match && !link_up) {
+		/* Peer rebooted with new address, or it is a new peer.
+		 * Accept signature and address.
+		*/
+		accept_sign = true;
+		accept_addr = true;
+		respond = true;
 	}
 
-	/*
-	 * Ensure requesting node's media address is correct
-	 *
-	 * If media address doesn't match and the link is working, reject the
-	 * request (must be from a duplicate node).
-	 *
-	 * If media address doesn't match and the link is not working, accept
-	 * the new media address and reset the link to ensure it starts up
-	 * cleanly.
-	 */
-	if (addr_mismatch) {
-		if (tipc_link_is_up(link)) {
-			disc_dupl_alert(b_ptr, orig, &media_addr);
-			tipc_node_unlock(n_ptr);
-			return;
-		} else {
-			memcpy(&link->media_addr, &media_addr,
-			       sizeof(media_addr));
-			tipc_link_reset(link);
-		}
-	}
+	if (accept_sign)
+		node->signature = signature;
 
-	/* Create a link endpoint for this bearer, if necessary */
-	if (!link) {
-		link = tipc_link_create(n_ptr, b_ptr, &media_addr);
-		if (!link) {
-			tipc_node_unlock(n_ptr);
-			return;
+	if (accept_addr) {
+		if (!link)
+			link = tipc_link_create(node, bearer, &maddr);
+		if (link) {
+			memcpy(&link->media_addr, &maddr, sizeof(maddr));
+			tipc_link_reset(link);
+		} else {
+			respond = false;
 		}
 	}
 
-	/* Accept discovery message & send response, if necessary */
-	link_fully_up = link_working_working(link);
-
-	if ((type == DSC_REQ_MSG) && !link_fully_up) {
-		rbuf = tipc_disc_init_msg(DSC_RESP_MSG, b_ptr);
+	/* Send response, if necessary */
+	if (respond && (mtyp == DSC_REQ_MSG)) {
+		rbuf = tipc_buf_acquire(INT_H_SIZE);
 		if (rbuf) {
-			tipc_bearer_send(b_ptr, rbuf, &media_addr);
+			tipc_disc_init_msg(rbuf, DSC_RESP_MSG, bearer);
+			tipc_bearer_send(bearer->identity, rbuf, &maddr);
 			kfree_skb(rbuf);
 		}
 	}
-
-	tipc_node_unlock(n_ptr);
+	tipc_node_unlock(node);
 }
 
 /**
@@ -303,7 +306,7 @@ static void disc_timeout(struct tipc_link_req *req)
 	spin_lock_bh(&req->lock);
 
 	/* Stop searching if only desired node has been found */
-	if (tipc_node(req->bearer->domain) && req->num_nodes) {
+	if (tipc_node(req->domain) && req->num_nodes) {
 		req->timer_intv = TIPC_LINK_REQ_INACTIVE;
 		goto exit;
 	}
@@ -315,7 +318,7 @@ static void disc_timeout(struct tipc_link_req *req)
 	 * hold at fast polling rate if don't have any associated nodes,
 	 * otherwise hold at slow polling rate
 	 */
-	tipc_bearer_send(req->bearer, req->buf, &req->dest);
+	tipc_bearer_send(req->bearer_id, req->buf, &req->dest);
 
 
 	req->timer_intv *= 2;
@@ -347,21 +350,23 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest)
 	if (!req)
 		return -ENOMEM;
 
-	req->buf = tipc_disc_init_msg(DSC_REQ_MSG, b_ptr);
+	req->buf = tipc_buf_acquire(INT_H_SIZE);
 	if (!req->buf) {
 		kfree(req);
-		return -ENOMSG;
+		return -ENOMEM;
 	}
 
+	tipc_disc_init_msg(req->buf, DSC_REQ_MSG, b_ptr);
 	memcpy(&req->dest, dest, sizeof(*dest));
-	req->bearer = b_ptr;
+	req->bearer_id = b_ptr->identity;
+	req->domain = b_ptr->domain;
 	req->num_nodes = 0;
 	req->timer_intv = TIPC_LINK_REQ_INIT;
 	spin_lock_init(&req->lock);
 	k_init_timer(&req->timer, (Handler)disc_timeout, (unsigned long)req);
 	k_start_timer(&req->timer, req->timer_intv);
 	b_ptr->link_req = req;
-	tipc_bearer_send(req->bearer, req->buf, &req->dest);
+	tipc_bearer_send(req->bearer_id, req->buf, &req->dest);
 	return 0;
 }
 
@@ -376,3 +381,23 @@ void tipc_disc_delete(struct tipc_link_req *req)
 	kfree_skb(req->buf);
 	kfree(req);
 }
+
+/**
+ * tipc_disc_reset - reset object to send periodic link setup requests
+ * @b_ptr: ptr to bearer issuing requests
+ * @dest_domain: network domain to which links can be established
+ */
+void tipc_disc_reset(struct tipc_bearer *b_ptr)
+{
+	struct tipc_link_req *req = b_ptr->link_req;
+
+	spin_lock_bh(&req->lock);
+	tipc_disc_init_msg(req->buf, DSC_REQ_MSG, b_ptr);
+	req->bearer_id = b_ptr->identity;
+	req->domain = b_ptr->domain;
+	req->num_nodes = 0;
+	req->timer_intv = TIPC_LINK_REQ_INIT;
+	k_start_timer(&req->timer, req->timer_intv);
+	tipc_bearer_send(req->bearer_id, req->buf, &req->dest);
+	spin_unlock_bh(&req->lock);
+}
diff --git a/net/tipc/discover.h b/net/tipc/discover.h
index 07f34729459..515b57392f4 100644
--- a/net/tipc/discover.h
+++ b/net/tipc/discover.h
@@ -41,6 +41,7 @@ struct tipc_link_req;
 
 int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest);
 void tipc_disc_delete(struct tipc_link_req *req);
+void tipc_disc_reset(struct tipc_bearer *b_ptr);
 void tipc_disc_add_dest(struct tipc_link_req *req);
 void tipc_disc_remove_dest(struct tipc_link_req *req);
 void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr);
diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c
index 67cf3f935db..5e1426f1751 100644
--- a/net/tipc/eth_media.c
+++ b/net/tipc/eth_media.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/eth_media.c: Ethernet bearer support for TIPC
  *
- * Copyright (c) 2001-2007, 2013, Ericsson AB
+ * Copyright (c) 2001-2007, 2013-2014, Ericsson AB
  * Copyright (c) 2005-2008, 2011-2013, Wind River Systems
  * All rights reserved.
  *
@@ -37,39 +37,52 @@
 #include "core.h"
 #include "bearer.h"
 
-#define ETH_ADDR_OFFSET	4	/* message header offset of MAC address */
+#define ETH_ADDR_OFFSET  4  /* MAC addr position inside address field */
 
-/* convert Ethernet address to string */
-static int tipc_eth_addr2str(struct tipc_media_addr *a, char *str_buf,
-			     int str_size)
+/* Convert Ethernet address (media address format) to string */
+static int tipc_eth_addr2str(struct tipc_media_addr *addr,
+			     char *strbuf, int bufsz)
 {
-	if (str_size < 18)	/* 18 = strlen("aa:bb:cc:dd:ee:ff\0") */
+	if (bufsz < 18)	/* 18 = strlen("aa:bb:cc:dd:ee:ff\0") */
 		return 1;
 
-	sprintf(str_buf, "%pM", a->value);
+	sprintf(strbuf, "%pM", addr->value);
 	return 0;
 }
 
-/* convert Ethernet address format to message header format */
-static int tipc_eth_addr2msg(struct tipc_media_addr *a, char *msg_area)
+/* Convert from media address format to discovery message addr format */
+static int tipc_eth_addr2msg(char *msg, struct tipc_media_addr *addr)
 {
-	memset(msg_area, 0, TIPC_MEDIA_ADDR_SIZE);
-	msg_area[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH;
-	memcpy(msg_area + ETH_ADDR_OFFSET, a->value, ETH_ALEN);
+	memset(msg, 0, TIPC_MEDIA_ADDR_SIZE);
+	msg[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_ETH;
+	memcpy(msg + ETH_ADDR_OFFSET, addr->value, ETH_ALEN);
 	return 0;
 }
 
-/* convert message header address format to Ethernet format */
-static int tipc_eth_msg2addr(const struct tipc_bearer *tb_ptr,
-			     struct tipc_media_addr *a, char *msg_area)
+/* Convert raw mac address format to media addr format */
+static int tipc_eth_raw2addr(struct tipc_bearer *b,
+			     struct tipc_media_addr *addr,
+			     char *msg)
 {
-	if (msg_area[TIPC_MEDIA_TYPE_OFFSET] != TIPC_MEDIA_TYPE_ETH)
-		return 1;
+	char bcast_mac[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
 
-	tipc_l2_media_addr_set(tb_ptr, a, msg_area + ETH_ADDR_OFFSET);
+	memset(addr, 0, sizeof(*addr));
+	ether_addr_copy(addr->value, msg);
+	addr->media_id = TIPC_MEDIA_TYPE_ETH;
+	addr->broadcast = !memcmp(addr->value, bcast_mac, ETH_ALEN);
 	return 0;
 }
 
+/* Convert discovery msg addr format to Ethernet media addr format */
+static int tipc_eth_msg2addr(struct tipc_bearer *b,
+			     struct tipc_media_addr *addr,
+			     char *msg)
+{
+	/* Skip past preamble: */
+	msg += ETH_ADDR_OFFSET;
+	return tipc_eth_raw2addr(b, addr, msg);
+}
+
 /* Ethernet media registration info */
 struct tipc_media eth_media_info = {
 	.send_msg	= tipc_l2_send_msg,
@@ -78,6 +91,7 @@ struct tipc_media eth_media_info = {
 	.addr2str	= tipc_eth_addr2str,
 	.addr2msg	= tipc_eth_addr2msg,
 	.msg2addr	= tipc_eth_msg2addr,
+	.raw2addr	= tipc_eth_raw2addr,
 	.priority	= TIPC_DEF_LINK_PRI,
 	.tolerance	= TIPC_DEF_LINK_TOL,
 	.window		= TIPC_DEF_LINK_WIN,
@@ -85,4 +99,3 @@ struct tipc_media eth_media_info = {
 	.hwaddr_len	= ETH_ALEN,
 	.name		= "eth"
 };
-
diff --git a/net/tipc/handler.c b/net/tipc/handler.c
deleted file mode 100644
index 1fabf160501..00000000000
--- a/net/tipc/handler.c
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- * net/tipc/handler.c: TIPC signal handling
- *
- * Copyright (c) 2000-2006, Ericsson AB
- * Copyright (c) 2005, Wind River Systems
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include "core.h"
-
-struct queue_item {
-	struct list_head next_signal;
-	void (*handler) (unsigned long);
-	unsigned long data;
-};
-
-static struct kmem_cache *tipc_queue_item_cache;
-static struct list_head signal_queue_head;
-static DEFINE_SPINLOCK(qitem_lock);
-static int handler_enabled __read_mostly;
-
-static void process_signal_queue(unsigned long dummy);
-
-static DECLARE_TASKLET_DISABLED(tipc_tasklet, process_signal_queue, 0);
-
-
-unsigned int tipc_k_signal(Handler routine, unsigned long argument)
-{
-	struct queue_item *item;
-
-	spin_lock_bh(&qitem_lock);
-	if (!handler_enabled) {
-		spin_unlock_bh(&qitem_lock);
-		return -ENOPROTOOPT;
-	}
-
-	item = kmem_cache_alloc(tipc_queue_item_cache, GFP_ATOMIC);
-	if (!item) {
-		pr_err("Signal queue out of memory\n");
-		spin_unlock_bh(&qitem_lock);
-		return -ENOMEM;
-	}
-	item->handler = routine;
-	item->data = argument;
-	list_add_tail(&item->next_signal, &signal_queue_head);
-	spin_unlock_bh(&qitem_lock);
-	tasklet_schedule(&tipc_tasklet);
-	return 0;
-}
-
-static void process_signal_queue(unsigned long dummy)
-{
-	struct queue_item *__volatile__ item;
-	struct list_head *l, *n;
-
-	spin_lock_bh(&qitem_lock);
-	list_for_each_safe(l, n, &signal_queue_head) {
-		item = list_entry(l, struct queue_item, next_signal);
-		list_del(&item->next_signal);
-		spin_unlock_bh(&qitem_lock);
-		item->handler(item->data);
-		spin_lock_bh(&qitem_lock);
-		kmem_cache_free(tipc_queue_item_cache, item);
-	}
-	spin_unlock_bh(&qitem_lock);
-}
-
-int tipc_handler_start(void)
-{
-	tipc_queue_item_cache =
-		kmem_cache_create("tipc_queue_items", sizeof(struct queue_item),
-				  0, SLAB_HWCACHE_ALIGN, NULL);
-	if (!tipc_queue_item_cache)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&signal_queue_head);
-	tasklet_enable(&tipc_tasklet);
-	handler_enabled = 1;
-	return 0;
-}
-
-void tipc_handler_stop(void)
-{
-	struct list_head *l, *n;
-	struct queue_item *item;
-
-	spin_lock_bh(&qitem_lock);
-	if (!handler_enabled) {
-		spin_unlock_bh(&qitem_lock);
-		return;
-	}
-	handler_enabled = 0;
-	spin_unlock_bh(&qitem_lock);
-
-	tasklet_kill(&tipc_tasklet);
-
-	spin_lock_bh(&qitem_lock);
-	list_for_each_safe(l, n, &signal_queue_head) {
-		item = list_entry(l, struct queue_item, next_signal);
-		list_del(&item->next_signal);
-		kmem_cache_free(tipc_queue_item_cache, item);
-	}
-	spin_unlock_bh(&qitem_lock);
-
-	kmem_cache_destroy(tipc_queue_item_cache);
-}
diff --git a/net/tipc/ib_media.c b/net/tipc/ib_media.c
index 844a77e2582..8522eef9c13 100644
--- a/net/tipc/ib_media.c
+++ b/net/tipc/ib_media.c
@@ -42,7 +42,7 @@
 #include "core.h"
 #include "bearer.h"
 
-/* convert InfiniBand address to string */
+/* convert InfiniBand address (media address format) media address to string */
 static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf,
 			    int str_size)
 {
@@ -54,23 +54,35 @@ static int tipc_ib_addr2str(struct tipc_media_addr *a, char *str_buf,
 	return 0;
 }
 
-/* convert InfiniBand address format to message header format */
-static int tipc_ib_addr2msg(struct tipc_media_addr *a, char *msg_area)
+/* Convert from media address format to discovery message addr format */
+static int tipc_ib_addr2msg(char *msg, struct tipc_media_addr *addr)
 {
-	memset(msg_area, 0, TIPC_MEDIA_ADDR_SIZE);
-	msg_area[TIPC_MEDIA_TYPE_OFFSET] = TIPC_MEDIA_TYPE_IB;
-	memcpy(msg_area, a->value, INFINIBAND_ALEN);
+	memset(msg, 0, TIPC_MEDIA_ADDR_SIZE);
+	memcpy(msg, addr->value, INFINIBAND_ALEN);
 	return 0;
 }
 
-/* convert message header address format to InfiniBand format */
-static int tipc_ib_msg2addr(const struct tipc_bearer *tb_ptr,
-			    struct tipc_media_addr *a, char *msg_area)
+/* Convert raw InfiniBand address format to media addr format */
+static int tipc_ib_raw2addr(struct tipc_bearer *b,
+			    struct tipc_media_addr *addr,
+			    char *msg)
 {
-	tipc_l2_media_addr_set(tb_ptr, a, msg_area);
+	memset(addr, 0, sizeof(*addr));
+	memcpy(addr->value, msg, INFINIBAND_ALEN);
+	addr->media_id = TIPC_MEDIA_TYPE_IB;
+	addr->broadcast = !memcmp(msg, b->bcast_addr.value,
+				  INFINIBAND_ALEN);
 	return 0;
 }
 
+/* Convert discovery msg addr format to InfiniBand media addr format */
+static int tipc_ib_msg2addr(struct tipc_bearer *b,
+			    struct tipc_media_addr *addr,
+			    char *msg)
+{
+	return tipc_ib_raw2addr(b, addr, msg);
+}
+
 /* InfiniBand media registration info */
 struct tipc_media ib_media_info = {
 	.send_msg	= tipc_l2_send_msg,
@@ -79,6 +91,7 @@ struct tipc_media ib_media_info = {
 	.addr2str	= tipc_ib_addr2str,
 	.addr2msg	= tipc_ib_addr2msg,
 	.msg2addr	= tipc_ib_msg2addr,
+	.raw2addr	= tipc_ib_raw2addr,
 	.priority	= TIPC_DEF_LINK_PRI,
 	.tolerance	= TIPC_DEF_LINK_TOL,
 	.window		= TIPC_DEF_LINK_WIN,
@@ -86,4 +99,3 @@ struct tipc_media ib_media_info = {
 	.hwaddr_len	= INFINIBAND_ALEN,
 	.name		= "ib"
 };
-
diff --git a/net/tipc/link.c b/net/tipc/link.c
index c5190ab7529..ad2c57f5868 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -37,6 +37,7 @@
 #include "core.h"
 #include "link.h"
 #include "port.h"
+#include "socket.h"
 #include "name_distr.h"
 #include "discover.h"
 #include "config.h"
@@ -101,9 +102,18 @@ static unsigned int align(unsigned int i)
 
 static void link_init_max_pkt(struct tipc_link *l_ptr)
 {
+	struct tipc_bearer *b_ptr;
 	u32 max_pkt;
 
-	max_pkt = (l_ptr->b_ptr->mtu & ~3);
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[l_ptr->bearer_id]);
+	if (!b_ptr) {
+		rcu_read_unlock();
+		return;
+	}
+	max_pkt = (b_ptr->mtu & ~3);
+	rcu_read_unlock();
+
 	if (max_pkt > MAX_MSG_SIZE)
 		max_pkt = MAX_MSG_SIZE;
 
@@ -248,7 +258,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
 	l_ptr->owner = n_ptr;
 	l_ptr->checkpoint = 1;
 	l_ptr->peer_session = INVALID_SESSION;
-	l_ptr->b_ptr = b_ptr;
+	l_ptr->bearer_id = b_ptr->identity;
 	link_set_supervision_props(l_ptr, b_ptr->tolerance);
 	l_ptr->state = RESET_UNKNOWN;
 
@@ -263,6 +273,7 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr,
 	l_ptr->priority = b_ptr->priority;
 	tipc_link_set_queue_limits(l_ptr, b_ptr->window);
 
+	l_ptr->net_plane = b_ptr->net_plane;
 	link_init_max_pkt(l_ptr);
 
 	l_ptr->next_out_no = 1;
@@ -287,14 +298,14 @@ void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
-		spin_lock_bh(&n_ptr->lock);
+		tipc_node_lock(n_ptr);
 		l_ptr = n_ptr->links[bearer_id];
 		if (l_ptr) {
 			tipc_link_reset(l_ptr);
 			if (shutting_down || !tipc_node_is_up(n_ptr)) {
 				tipc_node_detach_link(l_ptr->owner, l_ptr);
 				tipc_link_reset_fragments(l_ptr);
-				spin_unlock_bh(&n_ptr->lock);
+				tipc_node_unlock(n_ptr);
 
 				/* Nobody else can access this link now: */
 				del_timer_sync(&l_ptr->timer);
@@ -302,12 +313,12 @@ void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down)
 			} else {
 				/* Detach/delete when failover is finished: */
 				l_ptr->flags |= LINK_STOPPED;
-				spin_unlock_bh(&n_ptr->lock);
+				tipc_node_unlock(n_ptr);
 				del_timer_sync(&l_ptr->timer);
 			}
 			continue;
 		}
-		spin_unlock_bh(&n_ptr->lock);
+		tipc_node_unlock(n_ptr);
 	}
 	rcu_read_unlock();
 }
@@ -388,9 +399,8 @@ static void link_release_outqueue(struct tipc_link *l_ptr)
  */
 void tipc_link_reset_fragments(struct tipc_link *l_ptr)
 {
-	kfree_skb(l_ptr->reasm_head);
-	l_ptr->reasm_head = NULL;
-	l_ptr->reasm_tail = NULL;
+	kfree_skb(l_ptr->reasm_buf);
+	l_ptr->reasm_buf = NULL;
 }
 
 /**
@@ -426,7 +436,7 @@ void tipc_link_reset(struct tipc_link *l_ptr)
 		return;
 
 	tipc_node_link_down(l_ptr->owner, l_ptr);
-	tipc_bearer_remove_dest(l_ptr->b_ptr, l_ptr->addr);
+	tipc_bearer_remove_dest(l_ptr->bearer_id, l_ptr->addr);
 
 	if (was_active_link && tipc_node_active_links(l_ptr->owner)) {
 		l_ptr->reset_checkpoint = checkpoint;
@@ -464,11 +474,11 @@ void tipc_link_reset_list(unsigned int bearer_id)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
-		spin_lock_bh(&n_ptr->lock);
+		tipc_node_lock(n_ptr);
 		l_ptr = n_ptr->links[bearer_id];
 		if (l_ptr)
 			tipc_link_reset(l_ptr);
-		spin_unlock_bh(&n_ptr->lock);
+		tipc_node_unlock(n_ptr);
 	}
 	rcu_read_unlock();
 }
@@ -477,7 +487,7 @@ static void link_activate(struct tipc_link *l_ptr)
 {
 	l_ptr->next_in_no = l_ptr->stats.recv_info = 1;
 	tipc_node_link_up(l_ptr->owner, l_ptr);
-	tipc_bearer_add_dest(l_ptr->b_ptr, l_ptr->addr);
+	tipc_bearer_add_dest(l_ptr->bearer_id, l_ptr->addr);
 }
 
 /**
@@ -777,7 +787,7 @@ int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf)
 	if (likely(!link_congested(l_ptr))) {
 		link_add_to_outqueue(l_ptr, buf, msg);
 
-		tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+		tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 		l_ptr->unacked_window = 0;
 		return dsz;
 	}
@@ -825,7 +835,6 @@ int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector)
 	struct tipc_node *n_ptr;
 	int res = -ELINKCONG;
 
-	read_lock_bh(&tipc_net_lock);
 	n_ptr = tipc_node_find(dest);
 	if (n_ptr) {
 		tipc_node_lock(n_ptr);
@@ -838,7 +847,6 @@ int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector)
 	} else {
 		kfree_skb(buf);
 	}
-	read_unlock_bh(&tipc_net_lock);
 	return res;
 }
 
@@ -902,7 +910,6 @@ void tipc_link_names_xmit(struct list_head *message_list, u32 dest)
 	if (list_empty(message_list))
 		return;
 
-	read_lock_bh(&tipc_net_lock);
 	n_ptr = tipc_node_find(dest);
 	if (n_ptr) {
 		tipc_node_lock(n_ptr);
@@ -917,7 +924,6 @@ void tipc_link_names_xmit(struct list_head *message_list, u32 dest)
 		}
 		tipc_node_unlock(n_ptr);
 	}
-	read_unlock_bh(&tipc_net_lock);
 
 	/* discard the messages if they couldn't be sent */
 	list_for_each_safe(buf, temp_buf, ((struct sk_buff *)message_list)) {
@@ -941,7 +947,7 @@ static int tipc_link_xmit_fast(struct tipc_link *l_ptr, struct sk_buff *buf,
 	if (likely(!link_congested(l_ptr))) {
 		if (likely(msg_size(msg) <= l_ptr->max_pkt)) {
 			link_add_to_outqueue(l_ptr, buf, msg);
-			tipc_bearer_send(l_ptr->b_ptr, buf,
+			tipc_bearer_send(l_ptr->bearer_id, buf,
 					 &l_ptr->media_addr);
 			l_ptr->unacked_window = 0;
 			return res;
@@ -979,7 +985,6 @@ again:
 	if (unlikely(res < 0))
 		return res;
 
-	read_lock_bh(&tipc_net_lock);
 	node = tipc_node_find(destaddr);
 	if (likely(node)) {
 		tipc_node_lock(node);
@@ -990,7 +995,6 @@ again:
 							  &sender->max_pkt);
 exit:
 				tipc_node_unlock(node);
-				read_unlock_bh(&tipc_net_lock);
 				return res;
 			}
 
@@ -1007,7 +1011,6 @@ exit:
 			 */
 			sender->max_pkt = l_ptr->max_pkt;
 			tipc_node_unlock(node);
-			read_unlock_bh(&tipc_net_lock);
 
 
 			if ((msg_hdr_sz(hdr) + res) <= sender->max_pkt)
@@ -1018,7 +1021,6 @@ exit:
 		}
 		tipc_node_unlock(node);
 	}
-	read_unlock_bh(&tipc_net_lock);
 
 	/* Couldn't find a link to the destination node */
 	kfree_skb(buf);
@@ -1204,7 +1206,7 @@ static u32 tipc_link_push_packet(struct tipc_link *l_ptr)
 	if (r_q_size && buf) {
 		msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1));
 		msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in);
-		tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+		tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 		l_ptr->retransm_queue_head = mod(++r_q_head);
 		l_ptr->retransm_queue_size = --r_q_size;
 		l_ptr->stats.retransmitted++;
@@ -1216,7 +1218,7 @@ static u32 tipc_link_push_packet(struct tipc_link *l_ptr)
 	if (buf) {
 		msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1));
 		msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in);
-		tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+		tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 		l_ptr->unacked_window = 0;
 		kfree_skb(buf);
 		l_ptr->proto_msg_queue = NULL;
@@ -1233,7 +1235,8 @@ static u32 tipc_link_push_packet(struct tipc_link *l_ptr)
 		if (mod(next - first) < l_ptr->queue_limit[0]) {
 			msg_set_ack(msg, mod(l_ptr->next_in_no - 1));
 			msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in);
-			tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+			tipc_bearer_send(l_ptr->bearer_id, buf,
+					 &l_ptr->media_addr);
 			if (msg_user(msg) == MSG_BUNDLER)
 				msg_set_type(msg, CLOSED_MSG);
 			l_ptr->next_out = buf->next;
@@ -1256,33 +1259,24 @@ void tipc_link_push_queue(struct tipc_link *l_ptr)
 	} while (!res);
 }
 
-static void link_reset_all(unsigned long addr)
+void tipc_link_reset_all(struct tipc_node *node)
 {
-	struct tipc_node *n_ptr;
 	char addr_string[16];
 	u32 i;
 
-	read_lock_bh(&tipc_net_lock);
-	n_ptr = tipc_node_find((u32)addr);
-	if (!n_ptr) {
-		read_unlock_bh(&tipc_net_lock);
-		return;	/* node no longer exists */
-	}
-
-	tipc_node_lock(n_ptr);
+	tipc_node_lock(node);
 
 	pr_warn("Resetting all links to %s\n",
-		tipc_addr_string_fill(addr_string, n_ptr->addr));
+		tipc_addr_string_fill(addr_string, node->addr));
 
 	for (i = 0; i < MAX_BEARERS; i++) {
-		if (n_ptr->links[i]) {
-			link_print(n_ptr->links[i], "Resetting link\n");
-			tipc_link_reset(n_ptr->links[i]);
+		if (node->links[i]) {
+			link_print(node->links[i], "Resetting link\n");
+			tipc_link_reset(node->links[i]);
 		}
 	}
 
-	tipc_node_unlock(n_ptr);
-	read_unlock_bh(&tipc_net_lock);
+	tipc_node_unlock(node);
 }
 
 static void link_retransmit_failure(struct tipc_link *l_ptr,
@@ -1319,10 +1313,9 @@ static void link_retransmit_failure(struct tipc_link *l_ptr,
 			n_ptr->bclink.oos_state,
 			n_ptr->bclink.last_sent);
 
-		tipc_k_signal((Handler)link_reset_all, (unsigned long)n_ptr->addr);
-
 		tipc_node_unlock(n_ptr);
 
+		tipc_bclink_set_flags(TIPC_BCLINK_RESET);
 		l_ptr->stale_count = 0;
 	}
 }
@@ -1352,7 +1345,7 @@ void tipc_link_retransmit(struct tipc_link *l_ptr, struct sk_buff *buf,
 		msg = buf_msg(buf);
 		msg_set_ack(msg, mod(l_ptr->next_in_no - 1));
 		msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in);
-		tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+		tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 		buf = buf->next;
 		retransmits--;
 		l_ptr->stats.retransmitted++;
@@ -1440,14 +1433,13 @@ static int link_recv_buf_validate(struct sk_buff *buf)
 /**
  * tipc_rcv - process TIPC packets/messages arriving from off-node
  * @head: pointer to message buffer chain
- * @tb_ptr: pointer to bearer message arrived on
+ * @b_ptr: pointer to bearer message arrived on
  *
  * Invoked with no locks held.  Bearer pointer must point to a valid bearer
  * structure (i.e. cannot be NULL), but bearer can be inactive.
  */
 void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr)
 {
-	read_lock_bh(&tipc_net_lock);
 	while (head) {
 		struct tipc_node *n_ptr;
 		struct tipc_link *l_ptr;
@@ -1497,14 +1489,14 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr)
 			goto unlock_discard;
 
 		/* Verify that communication with node is currently allowed */
-		if ((n_ptr->block_setup & WAIT_PEER_DOWN) &&
-			msg_user(msg) == LINK_PROTOCOL &&
-			(msg_type(msg) == RESET_MSG ||
-			 msg_type(msg) == ACTIVATE_MSG) &&
-			!msg_redundant_link(msg))
-			n_ptr->block_setup &= ~WAIT_PEER_DOWN;
-
-		if (n_ptr->block_setup)
+		if ((n_ptr->action_flags & TIPC_WAIT_PEER_LINKS_DOWN) &&
+		    msg_user(msg) == LINK_PROTOCOL &&
+		    (msg_type(msg) == RESET_MSG ||
+		    msg_type(msg) == ACTIVATE_MSG) &&
+		    !msg_redundant_link(msg))
+			n_ptr->action_flags &= ~TIPC_WAIT_PEER_LINKS_DOWN;
+
+		if (tipc_node_blocked(n_ptr))
 			goto unlock_discard;
 
 		/* Validate message sequence number info */
@@ -1581,17 +1573,12 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr)
 			}
 			msg = buf_msg(buf);
 		} else if (msg_user(msg) == MSG_FRAGMENTER) {
-			int rc;
-
 			l_ptr->stats.recv_fragments++;
-			rc = tipc_link_frag_rcv(&l_ptr->reasm_head,
-						&l_ptr->reasm_tail,
-						&buf);
-			if (rc == LINK_REASM_COMPLETE) {
+			if (tipc_buf_append(&l_ptr->reasm_buf, &buf)) {
 				l_ptr->stats.recv_fragmented++;
 				msg = buf_msg(buf);
 			} else {
-				if (rc == LINK_REASM_ERROR)
+				if (!l_ptr->reasm_buf)
 					tipc_link_reset(l_ptr);
 				tipc_node_unlock(n_ptr);
 				continue;
@@ -1604,7 +1591,7 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr)
 		case TIPC_HIGH_IMPORTANCE:
 		case TIPC_CRITICAL_IMPORTANCE:
 			tipc_node_unlock(n_ptr);
-			tipc_port_rcv(buf);
+			tipc_sk_rcv(buf);
 			continue;
 		case MSG_BUNDLER:
 			l_ptr->stats.recv_bundles++;
@@ -1635,7 +1622,6 @@ unlock_discard:
 discard:
 		kfree_skb(buf);
 	}
-	read_unlock_bh(&tipc_net_lock);
 }
 
 /**
@@ -1747,12 +1733,12 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg,
 		return;
 
 	/* Abort non-RESET send if communication with node is prohibited */
-	if ((l_ptr->owner->block_setup) && (msg_typ != RESET_MSG))
+	if ((tipc_node_blocked(l_ptr->owner)) && (msg_typ != RESET_MSG))
 		return;
 
 	/* Create protocol message with "out-of-sequence" sequence number */
 	msg_set_type(msg, msg_typ);
-	msg_set_net_plane(msg, l_ptr->b_ptr->net_plane);
+	msg_set_net_plane(msg, l_ptr->net_plane);
 	msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in);
 	msg_set_last_bcast(msg, tipc_bclink_get_last_sent());
 
@@ -1818,7 +1804,7 @@ void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg,
 	skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg));
 	buf->priority = TC_PRIO_CONTROL;
 
-	tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr);
+	tipc_bearer_send(l_ptr->bearer_id, buf, &l_ptr->media_addr);
 	l_ptr->unacked_window = 0;
 	kfree_skb(buf);
 }
@@ -1840,12 +1826,9 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf)
 	if (l_ptr->exp_msg_count)
 		goto exit;
 
-	/* record unnumbered packet arrival (force mismatch on next timeout) */
-	l_ptr->checkpoint--;
-
-	if (l_ptr->b_ptr->net_plane != msg_net_plane(msg))
+	if (l_ptr->net_plane != msg_net_plane(msg))
 		if (tipc_own_addr > msg_prevnode(msg))
-			l_ptr->b_ptr->net_plane = msg_net_plane(msg);
+			l_ptr->net_plane = msg_net_plane(msg);
 
 	switch (msg_type(msg)) {
 
@@ -1862,7 +1845,7 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf)
 			 * peer has lost contact -- don't allow peer's links
 			 * to reactivate before we recognize loss & clean up
 			 */
-			l_ptr->owner->block_setup = WAIT_NODE_DOWN;
+			l_ptr->owner->action_flags |= TIPC_WAIT_OWN_LINKS_DOWN;
 		}
 
 		link_state_event(l_ptr, RESET_MSG);
@@ -1918,6 +1901,10 @@ static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf)
 			tipc_link_reset(l_ptr); /* Enforce change to take effect */
 			break;
 		}
+
+		/* Record reception; force mismatch at next timeout: */
+		l_ptr->checkpoint--;
+
 		link_state_event(l_ptr, TRAFFIC_MSG_EVT);
 		l_ptr->stats.recv_states++;
 		if (link_reset_unknown(l_ptr))
@@ -2177,9 +2164,7 @@ static struct sk_buff *tipc_link_failover_rcv(struct tipc_link *l_ptr,
 		}
 		if (msg_user(msg) == MSG_FRAGMENTER) {
 			l_ptr->stats.recv_fragments++;
-			tipc_link_frag_rcv(&l_ptr->reasm_head,
-					   &l_ptr->reasm_tail,
-					   &buf);
+			tipc_buf_append(&l_ptr->reasm_buf, &buf);
 		}
 	}
 exit:
@@ -2317,53 +2302,6 @@ static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf)
 	return dsz;
 }
 
-/* tipc_link_frag_rcv(): Called with node lock on. Returns
- * the reassembled buffer if message is complete.
- */
-int tipc_link_frag_rcv(struct sk_buff **head, struct sk_buff **tail,
-		       struct sk_buff **fbuf)
-{
-	struct sk_buff *frag = *fbuf;
-	struct tipc_msg *msg = buf_msg(frag);
-	u32 fragid = msg_type(msg);
-	bool headstolen;
-	int delta;
-
-	skb_pull(frag, msg_hdr_sz(msg));
-	if (fragid == FIRST_FRAGMENT) {
-		if (*head || skb_unclone(frag, GFP_ATOMIC))
-			goto out_free;
-		*head = frag;
-		skb_frag_list_init(*head);
-		*fbuf = NULL;
-		return 0;
-	} else if (*head &&
-		   skb_try_coalesce(*head, frag, &headstolen, &delta)) {
-		kfree_skb_partial(frag, headstolen);
-	} else {
-		if (!*head)
-			goto out_free;
-		if (!skb_has_frag_list(*head))
-			skb_shinfo(*head)->frag_list = frag;
-		else
-			(*tail)->next = frag;
-		*tail = frag;
-		(*head)->truesize += frag->truesize;
-	}
-	if (fragid == LAST_FRAGMENT) {
-		*fbuf = *head;
-		*tail = *head = NULL;
-		return LINK_REASM_COMPLETE;
-	}
-	*fbuf = NULL;
-	return 0;
-out_free:
-	pr_warn_ratelimited("Link unable to reassemble fragmented message\n");
-	kfree_skb(*fbuf);
-	*fbuf = NULL;
-	return LINK_REASM_ERROR;
-}
-
 static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance)
 {
 	if ((tolerance < TIPC_MIN_LINK_TOL) || (tolerance > TIPC_MAX_LINK_TOL))
@@ -2397,8 +2335,6 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window)
 /* tipc_link_find_owner - locate owner node of link by link's name
  * @name: pointer to link name string
  * @bearer_id: pointer to index in 'node->links' array where the link was found.
- * Caller must hold 'tipc_net_lock' to ensure node and bearer are not deleted;
- * this also prevents link deletion.
  *
  * Returns pointer to node owning the link, or 0 if no matching link is found.
  */
@@ -2460,7 +2396,7 @@ static int link_value_is_valid(u16 cmd, u32 new_value)
  * @new_value: new value of link, bearer, or media setting
  * @cmd: which link, bearer, or media attribute to set (TIPC_CMD_SET_LINK_*)
  *
- * Caller must hold 'tipc_net_lock' to ensure link/bearer/media is not deleted.
+ * Caller must hold RTNL lock to ensure link/bearer/media is not deleted.
  *
  * Returns 0 if value updated and negative value on error.
  */
@@ -2566,9 +2502,7 @@ struct sk_buff *tipc_link_cmd_config(const void *req_tlv_area, int req_tlv_space
 						   " (cannot change setting on broadcast link)");
 	}
 
-	read_lock_bh(&tipc_net_lock);
 	res = link_cmd_set_value(args->name, new_value, cmd);
-	read_unlock_bh(&tipc_net_lock);
 	if (res)
 		return tipc_cfg_reply_error_string("cannot change link setting");
 
@@ -2602,22 +2536,18 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_
 			return tipc_cfg_reply_error_string("link not found");
 		return tipc_cfg_reply_none();
 	}
-	read_lock_bh(&tipc_net_lock);
 	node = tipc_link_find_owner(link_name, &bearer_id);
-	if (!node) {
-		read_unlock_bh(&tipc_net_lock);
+	if (!node)
 		return tipc_cfg_reply_error_string("link not found");
-	}
+
 	tipc_node_lock(node);
 	l_ptr = node->links[bearer_id];
 	if (!l_ptr) {
 		tipc_node_unlock(node);
-		read_unlock_bh(&tipc_net_lock);
 		return tipc_cfg_reply_error_string("link not found");
 	}
 	link_reset_statistics(l_ptr);
 	tipc_node_unlock(node);
-	read_unlock_bh(&tipc_net_lock);
 	return tipc_cfg_reply_none();
 }
 
@@ -2650,18 +2580,15 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size)
 	if (!strcmp(name, tipc_bclink_name))
 		return tipc_bclink_stats(buf, buf_size);
 
-	read_lock_bh(&tipc_net_lock);
 	node = tipc_link_find_owner(name, &bearer_id);
-	if (!node) {
-		read_unlock_bh(&tipc_net_lock);
+	if (!node)
 		return 0;
-	}
+
 	tipc_node_lock(node);
 
 	l = node->links[bearer_id];
 	if (!l) {
 		tipc_node_unlock(node);
-		read_unlock_bh(&tipc_net_lock);
 		return 0;
 	}
 
@@ -2727,7 +2654,6 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size)
 			     (s->accu_queue_sz / s->queue_sz_counts) : 0);
 
 	tipc_node_unlock(node);
-	read_unlock_bh(&tipc_net_lock);
 	return ret;
 }
 
@@ -2778,7 +2704,6 @@ u32 tipc_link_get_max_pkt(u32 dest, u32 selector)
 	if (dest == tipc_own_addr)
 		return MAX_MSG_SIZE;
 
-	read_lock_bh(&tipc_net_lock);
 	n_ptr = tipc_node_find(dest);
 	if (n_ptr) {
 		tipc_node_lock(n_ptr);
@@ -2787,13 +2712,18 @@ u32 tipc_link_get_max_pkt(u32 dest, u32 selector)
 			res = l_ptr->max_pkt;
 		tipc_node_unlock(n_ptr);
 	}
-	read_unlock_bh(&tipc_net_lock);
 	return res;
 }
 
 static void link_print(struct tipc_link *l_ptr, const char *str)
 {
-	pr_info("%s Link %x<%s>:", str, l_ptr->addr, l_ptr->b_ptr->name);
+	struct tipc_bearer *b_ptr;
+
+	rcu_read_lock();
+	b_ptr = rcu_dereference_rtnl(bearer_list[l_ptr->bearer_id]);
+	if (b_ptr)
+		pr_info("%s Link %x<%s>:", str, l_ptr->addr, b_ptr->name);
+	rcu_read_unlock();
 
 	if (link_working_unknown(l_ptr))
 		pr_cont(":WU\n");
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 8c0b49b5b2e..200d518b218 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -40,11 +40,6 @@
 #include "msg.h"
 #include "node.h"
 
-/* Link reassembly status codes
- */
-#define LINK_REASM_ERROR	-1
-#define LINK_REASM_COMPLETE	1
-
 /* Out-of-range value for link sequence numbers
  */
 #define INVALID_LINK_SEQ 0x10000
@@ -107,7 +102,7 @@ struct tipc_stats {
  * @checkpoint: reference point for triggering link continuity checking
  * @peer_session: link session # being used by peer end of link
  * @peer_bearer_id: bearer id used by link's peer endpoint
- * @b_ptr: pointer to bearer used by link
+ * @bearer_id: local bearer id used by link
  * @tolerance: minimum link continuity loss needed to reset link [in ms]
  * @continuity_interval: link continuity testing interval [in ms]
  * @abort_limit: # of unacknowledged continuity probes needed to reset link
@@ -116,6 +111,7 @@ struct tipc_stats {
  * @proto_msg: template for control messages generated by link
  * @pmsg: convenience pointer to "proto_msg" field
  * @priority: current link priority
+ * @net_plane: current link network plane ('A' through 'H')
  * @queue_limit: outbound message queue congestion thresholds (indexed by user)
  * @exp_msg_count: # of tunnelled messages expected during link changeover
  * @reset_checkpoint: seq # of last acknowledged message at time of link reset
@@ -139,8 +135,7 @@ struct tipc_stats {
  * @next_out: ptr to first unsent outbound message in queue
  * @waiting_ports: linked list of ports waiting for link congestion to abate
  * @long_msg_seq_no: next identifier to use for outbound fragmented messages
- * @reasm_head: list head of partially reassembled inbound message fragments
- * @reasm_tail: last fragment received
+ * @reasm_buf: head of partially reassembled inbound message fragments
  * @stats: collects statistics regarding link activity
  */
 struct tipc_link {
@@ -155,7 +150,7 @@ struct tipc_link {
 	u32 checkpoint;
 	u32 peer_session;
 	u32 peer_bearer_id;
-	struct tipc_bearer *b_ptr;
+	u32 bearer_id;
 	u32 tolerance;
 	u32 continuity_interval;
 	u32 abort_limit;
@@ -167,6 +162,7 @@ struct tipc_link {
 	} proto_msg;
 	struct tipc_msg *pmsg;
 	u32 priority;
+	char net_plane;
 	u32 queue_limit[15];	/* queue_limit[0]==window limit */
 
 	/* Changeover */
@@ -202,8 +198,7 @@ struct tipc_link {
 
 	/* Fragmentation/reassembly */
 	u32 long_msg_seq_no;
-	struct sk_buff *reasm_head;
-	struct sk_buff *reasm_tail;
+	struct sk_buff *reasm_buf;
 
 	/* Statistics */
 	struct tipc_stats stats;
@@ -228,6 +223,7 @@ struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area,
 					 int req_tlv_space);
 struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area,
 					  int req_tlv_space);
+void tipc_link_reset_all(struct tipc_node *node);
 void tipc_link_reset(struct tipc_link *l_ptr);
 void tipc_link_reset_list(unsigned int bearer_id);
 int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector);
@@ -239,9 +235,6 @@ int tipc_link_iovec_xmit_fast(struct tipc_port *sender,
 			      struct iovec const *msg_sect,
 			      unsigned int len, u32 destnode);
 void tipc_link_bundle_rcv(struct sk_buff *buf);
-int tipc_link_frag_rcv(struct sk_buff **reasm_head,
-		       struct sk_buff **reasm_tail,
-		       struct sk_buff **fbuf);
 void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob,
 			  u32 gap, u32 tolerance, u32 priority, u32 acked_mtu);
 void tipc_link_push_queue(struct tipc_link *l_ptr);
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index e525f8ce1de..0a37a472c29 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -1,7 +1,7 @@
 /*
  * net/tipc/msg.c: TIPC message header routines
  *
- * Copyright (c) 2000-2006, Ericsson AB
+ * Copyright (c) 2000-2006, 2014, Ericsson AB
  * Copyright (c) 2005, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -99,3 +99,61 @@ int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect,
 	}
 	return dsz;
 }
+
+/* tipc_buf_append(): Append a buffer to the fragment list of another buffer
+ * @*headbuf: in:  NULL for first frag, otherwise value returned from prev call
+ *            out: set when successful non-complete reassembly, otherwise NULL
+ * @*buf:     in:  the buffer to append. Always defined
+ *            out: head buf after sucessful complete reassembly, otherwise NULL
+ * Returns 1 when reassembly complete, otherwise 0
+ */
+int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
+{
+	struct sk_buff *head = *headbuf;
+	struct sk_buff *frag = *buf;
+	struct sk_buff *tail;
+	struct tipc_msg *msg = buf_msg(frag);
+	u32 fragid = msg_type(msg);
+	bool headstolen;
+	int delta;
+
+	skb_pull(frag, msg_hdr_sz(msg));
+
+	if (fragid == FIRST_FRAGMENT) {
+		if (head || skb_unclone(frag, GFP_ATOMIC))
+			goto out_free;
+		head = *headbuf = frag;
+		skb_frag_list_init(head);
+		*buf = NULL;
+		return 0;
+	}
+	if (!head)
+		goto out_free;
+	tail = TIPC_SKB_CB(head)->tail;
+	if (skb_try_coalesce(head, frag, &headstolen, &delta)) {
+		kfree_skb_partial(frag, headstolen);
+	} else {
+		if (!skb_has_frag_list(head))
+			skb_shinfo(head)->frag_list = frag;
+		else
+			tail->next = frag;
+		head->truesize += frag->truesize;
+		head->data_len += frag->len;
+		head->len += frag->len;
+		TIPC_SKB_CB(head)->tail = frag;
+	}
+	if (fragid == LAST_FRAGMENT) {
+		*buf = head;
+		TIPC_SKB_CB(head)->tail = NULL;
+		*headbuf = NULL;
+		return 1;
+	}
+	*buf = NULL;
+	return 0;
+out_free:
+	pr_warn_ratelimited("Unable to build fragment list\n");
+	kfree_skb(*buf);
+	kfree_skb(*headbuf);
+	*buf = *headbuf = NULL;
+	return 0;
+}
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 76d1269b944..503511903d1 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -1,7 +1,7 @@
 /*
  * net/tipc/msg.h: Include file for TIPC message header routines
  *
- * Copyright (c) 2000-2007, Ericsson AB
+ * Copyright (c) 2000-2007, 2014, Ericsson AB
  * Copyright (c) 2005-2008, 2010-2011, Wind River Systems
  * All rights reserved.
  *
@@ -711,4 +711,7 @@ void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize,
 		   u32 destnode);
 int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect,
 		   unsigned int len, int max_size, struct sk_buff **buf);
+
+int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf);
+
 #endif
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index aff8041dc15..8ce730984aa 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -38,34 +38,6 @@
 #include "link.h"
 #include "name_distr.h"
 
-#define ITEM_SIZE sizeof(struct distr_item)
-
-/**
- * struct distr_item - publication info distributed to other nodes
- * @type: name sequence type
- * @lower: name sequence lower bound
- * @upper: name sequence upper bound
- * @ref: publishing port reference
- * @key: publication key
- *
- * ===> All fields are stored in network byte order. <===
- *
- * First 3 fields identify (name or) name sequence being published.
- * Reference field uniquely identifies port that published name sequence.
- * Key field uniquely identifies publication, in the event a port has
- * multiple publications of the same name sequence.
- *
- * Note: There is no field that identifies the publishing node because it is
- * the same for all items contained within a publication message.
- */
-struct distr_item {
-	__be32 type;
-	__be32 lower;
-	__be32 upper;
-	__be32 ref;
-	__be32 key;
-};
-
 /**
  * struct publ_list - list of publications made by this node
  * @list: circular list of publications
@@ -127,7 +99,7 @@ static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest)
 	return buf;
 }
 
-static void named_cluster_distribute(struct sk_buff *buf)
+void named_cluster_distribute(struct sk_buff *buf)
 {
 	struct sk_buff *buf_copy;
 	struct tipc_node *n_ptr;
@@ -135,18 +107,18 @@ static void named_cluster_distribute(struct sk_buff *buf)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(n_ptr, &tipc_node_list, list) {
-		spin_lock_bh(&n_ptr->lock);
+		tipc_node_lock(n_ptr);
 		l_ptr = n_ptr->active_links[n_ptr->addr & 1];
 		if (l_ptr) {
 			buf_copy = skb_copy(buf, GFP_ATOMIC);
 			if (!buf_copy) {
-				spin_unlock_bh(&n_ptr->lock);
+				tipc_node_unlock(n_ptr);
 				break;
 			}
 			msg_set_destnode(buf_msg(buf_copy), n_ptr->addr);
 			__tipc_link_xmit(l_ptr, buf_copy);
 		}
-		spin_unlock_bh(&n_ptr->lock);
+		tipc_node_unlock(n_ptr);
 	}
 	rcu_read_unlock();
 
@@ -156,7 +128,7 @@ static void named_cluster_distribute(struct sk_buff *buf)
 /**
  * tipc_named_publish - tell other nodes about a new publication by this node
  */
-void tipc_named_publish(struct publication *publ)
+struct sk_buff *tipc_named_publish(struct publication *publ)
 {
 	struct sk_buff *buf;
 	struct distr_item *item;
@@ -165,23 +137,23 @@ void tipc_named_publish(struct publication *publ)
 	publ_lists[publ->scope]->size++;
 
 	if (publ->scope == TIPC_NODE_SCOPE)
-		return;
+		return NULL;
 
 	buf = named_prepare_buf(PUBLICATION, ITEM_SIZE, 0);
 	if (!buf) {
 		pr_warn("Publication distribution failure\n");
-		return;
+		return NULL;
 	}
 
 	item = (struct distr_item *)msg_data(buf_msg(buf));
 	publ_to_item(item, publ);
-	named_cluster_distribute(buf);
+	return buf;
 }
 
 /**
  * tipc_named_withdraw - tell other nodes about a withdrawn publication by this node
  */
-void tipc_named_withdraw(struct publication *publ)
+struct sk_buff *tipc_named_withdraw(struct publication *publ)
 {
 	struct sk_buff *buf;
 	struct distr_item *item;
@@ -190,17 +162,17 @@ void tipc_named_withdraw(struct publication *publ)
 	publ_lists[publ->scope]->size--;
 
 	if (publ->scope == TIPC_NODE_SCOPE)
-		return;
+		return NULL;
 
 	buf = named_prepare_buf(WITHDRAWAL, ITEM_SIZE, 0);
 	if (!buf) {
 		pr_warn("Withdrawal distribution failure\n");
-		return;
+		return NULL;
 	}
 
 	item = (struct distr_item *)msg_data(buf_msg(buf));
 	publ_to_item(item, publ);
-	named_cluster_distribute(buf);
+	return buf;
 }
 
 /*
@@ -239,31 +211,9 @@ static void named_distribute(struct list_head *message_list, u32 node,
 /**
  * tipc_named_node_up - tell specified node about all publications by this node
  */
-void tipc_named_node_up(unsigned long nodearg)
+void tipc_named_node_up(u32 max_item_buf, u32 node)
 {
-	struct tipc_node *n_ptr;
-	struct tipc_link *l_ptr;
-	struct list_head message_list;
-	u32 node = (u32)nodearg;
-	u32 max_item_buf = 0;
-
-	/* compute maximum amount of publication data to send per message */
-	read_lock_bh(&tipc_net_lock);
-	n_ptr = tipc_node_find(node);
-	if (n_ptr) {
-		tipc_node_lock(n_ptr);
-		l_ptr = n_ptr->active_links[0];
-		if (l_ptr)
-			max_item_buf = ((l_ptr->max_pkt - INT_H_SIZE) /
-				ITEM_SIZE) * ITEM_SIZE;
-		tipc_node_unlock(n_ptr);
-	}
-	read_unlock_bh(&tipc_net_lock);
-	if (!max_item_buf)
-		return;
-
-	/* create list of publication messages, then send them as a unit */
-	INIT_LIST_HEAD(&message_list);
+	LIST_HEAD(message_list);
 
 	read_lock_bh(&tipc_nametbl_lock);
 	named_distribute(&message_list, node, &publ_cluster, max_item_buf);
diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h
index 9b312ccfd43..b2eed4ec152 100644
--- a/net/tipc/name_distr.h
+++ b/net/tipc/name_distr.h
@@ -39,9 +39,38 @@
 
 #include "name_table.h"
 
-void tipc_named_publish(struct publication *publ);
-void tipc_named_withdraw(struct publication *publ);
-void tipc_named_node_up(unsigned long node);
+#define ITEM_SIZE sizeof(struct distr_item)
+
+/**
+ * struct distr_item - publication info distributed to other nodes
+ * @type: name sequence type
+ * @lower: name sequence lower bound
+ * @upper: name sequence upper bound
+ * @ref: publishing port reference
+ * @key: publication key
+ *
+ * ===> All fields are stored in network byte order. <===
+ *
+ * First 3 fields identify (name or) name sequence being published.
+ * Reference field uniquely identifies port that published name sequence.
+ * Key field uniquely identifies publication, in the event a port has
+ * multiple publications of the same name sequence.
+ *
+ * Note: There is no field that identifies the publishing node because it is
+ * the same for all items contained within a publication message.
+ */
+struct distr_item {
+	__be32 type;
+	__be32 lower;
+	__be32 upper;
+	__be32 ref;
+	__be32 key;
+};
+
+struct sk_buff *tipc_named_publish(struct publication *publ);
+struct sk_buff *tipc_named_withdraw(struct publication *publ);
+void named_cluster_distribute(struct sk_buff *buf);
+void tipc_named_node_up(u32 max_item_buf, u32 node);
 void tipc_named_rcv(struct sk_buff *buf);
 void tipc_named_reinit(void);
 
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 042e8e3cabc..9d7d37d9518 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -664,6 +664,7 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
 					 u32 scope, u32 port_ref, u32 key)
 {
 	struct publication *publ;
+	struct sk_buff *buf = NULL;
 
 	if (table.local_publ_count >= TIPC_MAX_PUBLICATIONS) {
 		pr_warn("Publication failed, local publication limit reached (%u)\n",
@@ -676,9 +677,12 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
 				   tipc_own_addr, port_ref, key);
 	if (likely(publ)) {
 		table.local_publ_count++;
-		tipc_named_publish(publ);
+		buf = tipc_named_publish(publ);
 	}
 	write_unlock_bh(&tipc_nametbl_lock);
+
+	if (buf)
+		named_cluster_distribute(buf);
 	return publ;
 }
 
@@ -688,15 +692,19 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper,
 int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key)
 {
 	struct publication *publ;
+	struct sk_buff *buf;
 
 	write_lock_bh(&tipc_nametbl_lock);
 	publ = tipc_nametbl_remove_publ(type, lower, tipc_own_addr, ref, key);
 	if (likely(publ)) {
 		table.local_publ_count--;
-		tipc_named_withdraw(publ);
+		buf = tipc_named_withdraw(publ);
 		write_unlock_bh(&tipc_nametbl_lock);
 		list_del_init(&publ->pport_list);
 		kfree(publ);
+
+		if (buf)
+			named_cluster_distribute(buf);
 		return 1;
 	}
 	write_unlock_bh(&tipc_nametbl_lock);
@@ -961,6 +969,7 @@ static void tipc_purge_publications(struct name_seq *seq)
 	list_for_each_entry_safe(publ, safe, &info->zone_list, zone_list) {
 		tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node,
 					 publ->ref, publ->key);
+		kfree(publ);
 	}
 }
 
@@ -982,7 +991,6 @@ void tipc_nametbl_stop(void)
 		hlist_for_each_entry_safe(seq, safe, seq_head, ns_list) {
 			tipc_purge_publications(seq);
 		}
-		continue;
 	}
 	kfree(table.types);
 	table.types = NULL;
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 4c564eb69e1..f64375e7f99 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -39,45 +39,41 @@
 #include "name_distr.h"
 #include "subscr.h"
 #include "port.h"
+#include "socket.h"
 #include "node.h"
 #include "config.h"
 
 /*
  * The TIPC locking policy is designed to ensure a very fine locking
  * granularity, permitting complete parallel access to individual
- * port and node/link instances. The code consists of three major
+ * port and node/link instances. The code consists of four major
  * locking domains, each protected with their own disjunct set of locks.
  *
- * 1: The routing hierarchy.
- *    Comprises the structures 'zone', 'cluster', 'node', 'link'
- *    and 'bearer'. The whole hierarchy is protected by a big
- *    read/write lock, tipc_net_lock, to enssure that nothing is added
- *    or removed while code is accessing any of these structures.
- *    This layer must not be called from the two others while they
- *    hold any of their own locks.
- *    Neither must it itself do any upcalls to the other two before
- *    it has released tipc_net_lock and other protective locks.
+ * 1: The bearer level.
+ *    RTNL lock is used to serialize the process of configuring bearer
+ *    on update side, and RCU lock is applied on read side to make
+ *    bearer instance valid on both paths of message transmission and
+ *    reception.
  *
- *   Within the tipc_net_lock domain there are two sub-domains;'node' and
- *   'bearer', where local write operations are permitted,
- *   provided that those are protected by individual spin_locks
- *   per instance. Code holding tipc_net_lock(read) and a node spin_lock
- *   is permitted to poke around in both the node itself and its
- *   subordinate links. I.e, it can update link counters and queues,
- *   change link state, send protocol messages, and alter the
- *   "active_links" array in the node; but it can _not_ remove a link
- *   or a node from the overall structure.
- *   Correspondingly, individual bearers may change status within a
- *   tipc_net_lock(read), protected by an individual spin_lock ber bearer
- *   instance, but it needs tipc_net_lock(write) to remove/add any bearers.
+ * 2: The node and link level.
+ *    All node instances are saved into two tipc_node_list and node_htable
+ *    lists. The two lists are protected by node_list_lock on write side,
+ *    and they are guarded with RCU lock on read side. Especially node
+ *    instance is destroyed only when TIPC module is removed, and we can
+ *    confirm that there has no any user who is accessing the node at the
+ *    moment. Therefore, Except for iterating the two lists within RCU
+ *    protection, it's no needed to hold RCU that we access node instance
+ *    in other places.
  *
+ *    In addition, all members in node structure including link instances
+ *    are protected by node spin lock.
  *
- *  2: The transport level of the protocol.
- *     This consists of the structures port, (and its user level
- *     representations, such as user_port and tipc_sock), reference and
- *     tipc_user (port.c, reg.c, socket.c).
+ * 3: The transport level of the protocol.
+ *    This consists of the structures port, (and its user level
+ *    representations, such as user_port and tipc_sock), reference and
+ *    tipc_user (port.c, reg.c, socket.c).
  *
- *     This layer has four different locks:
+ *    This layer has four different locks:
  *     - The tipc_port spin_lock. This is protecting each port instance
  *       from parallel data access and removal. Since we can not place
  *       this lock in the port itself, it has been placed in the
@@ -96,7 +92,7 @@
  *       There are two such lists; 'port_list', which is used for management,
  *       and 'wait_list', which is used to queue ports during congestion.
  *
- *  3: The name table (name_table.c, name_distr.c, subscription.c)
+ *  4: The name table (name_table.c, name_distr.c, subscription.c)
  *     - There is one big read/write-lock (tipc_nametbl_lock) protecting the
  *       overall name table structure. Nothing must be added/removed to
  *       this structure without holding write access to it.
@@ -108,8 +104,6 @@
  *     - A local spin_lock protecting the queue of subscriber events.
 */
 
-DEFINE_RWLOCK(tipc_net_lock);
-
 static void net_route_named_msg(struct sk_buff *buf)
 {
 	struct tipc_msg *msg = buf_msg(buf);
@@ -148,7 +142,7 @@ void tipc_net_route_msg(struct sk_buff *buf)
 			if (msg_mcast(msg))
 				tipc_port_mcast_rcv(buf, NULL);
 			else if (msg_destport(msg))
-				tipc_port_rcv(buf);
+				tipc_sk_rcv(buf);
 			else
 				net_route_named_msg(buf);
 			return;
@@ -171,22 +165,25 @@ void tipc_net_route_msg(struct sk_buff *buf)
 	tipc_link_xmit(buf, dnode, msg_link_selector(msg));
 }
 
-void tipc_net_start(u32 addr)
+int tipc_net_start(u32 addr)
 {
 	char addr_string[16];
+	int res;
 
-	write_lock_bh(&tipc_net_lock);
 	tipc_own_addr = addr;
 	tipc_named_reinit();
 	tipc_port_reinit();
-	tipc_bclink_init();
-	write_unlock_bh(&tipc_net_lock);
+	res = tipc_bclink_init();
+	if (res)
+		return res;
 
 	tipc_nametbl_publish(TIPC_CFG_SRV, tipc_own_addr, tipc_own_addr,
 			     TIPC_ZONE_SCOPE, 0, tipc_own_addr);
+
 	pr_info("Started in network mode\n");
 	pr_info("Own node address %s, network identity %u\n",
 		tipc_addr_string_fill(addr_string, tipc_own_addr), tipc_net_id);
+	return 0;
 }
 
 void tipc_net_stop(void)
@@ -195,11 +192,11 @@ void tipc_net_stop(void)
 		return;
 
 	tipc_nametbl_withdraw(TIPC_CFG_SRV, tipc_own_addr, 0, tipc_own_addr);
-	write_lock_bh(&tipc_net_lock);
+	rtnl_lock();
 	tipc_bearer_stop();
 	tipc_bclink_stop();
 	tipc_node_stop();
-	write_unlock_bh(&tipc_net_lock);
+	rtnl_unlock();
 
 	pr_info("Left network mode\n");
 }
diff --git a/net/tipc/net.h b/net/tipc/net.h
index 079daadb3f7..c6c2b46f7c2 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -37,11 +37,9 @@
 #ifndef _TIPC_NET_H
 #define _TIPC_NET_H
 
-extern rwlock_t tipc_net_lock;
-
 void tipc_net_route_msg(struct sk_buff *buf);
 
-void tipc_net_start(u32 addr);
+int tipc_net_start(u32 addr);
 void tipc_net_stop(void);
 
 #endif
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 1d3a4999a70..5b44c3041be 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -108,7 +108,7 @@ struct tipc_node *tipc_node_create(u32 addr)
 			break;
 	}
 	list_add_tail_rcu(&n_ptr->list, &temp_node->list);
-	n_ptr->block_setup = WAIT_PEER_DOWN;
+	n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN;
 	n_ptr->signature = INVALID_NODE_SIG;
 
 	tipc_num_nodes++;
@@ -144,11 +144,13 @@ void tipc_node_stop(void)
 void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 {
 	struct tipc_link **active = &n_ptr->active_links[0];
+	u32 addr = n_ptr->addr;
 
 	n_ptr->working_links++;
-
+	tipc_nametbl_publish(TIPC_LINK_STATE, addr, addr, TIPC_NODE_SCOPE,
+			     l_ptr->bearer_id, addr);
 	pr_info("Established link <%s> on network plane %c\n",
-		l_ptr->name, l_ptr->b_ptr->net_plane);
+		l_ptr->name, l_ptr->net_plane);
 
 	if (!active[0]) {
 		active[0] = active[1] = l_ptr;
@@ -203,16 +205,18 @@ static void node_select_active_links(struct tipc_node *n_ptr)
 void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 {
 	struct tipc_link **active;
+	u32 addr = n_ptr->addr;
 
 	n_ptr->working_links--;
+	tipc_nametbl_withdraw(TIPC_LINK_STATE, addr, l_ptr->bearer_id, addr);
 
 	if (!tipc_link_is_active(l_ptr)) {
 		pr_info("Lost standby link <%s> on network plane %c\n",
-			l_ptr->name, l_ptr->b_ptr->net_plane);
+			l_ptr->name, l_ptr->net_plane);
 		return;
 	}
 	pr_info("Lost link <%s> on network plane %c\n",
-		l_ptr->name, l_ptr->b_ptr->net_plane);
+		l_ptr->name, l_ptr->net_plane);
 
 	active = &n_ptr->active_links[0];
 	if (active[0] == l_ptr)
@@ -239,7 +243,7 @@ int tipc_node_is_up(struct tipc_node *n_ptr)
 
 void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 {
-	n_ptr->links[l_ptr->b_ptr->identity] = l_ptr;
+	n_ptr->links[l_ptr->bearer_id] = l_ptr;
 	spin_lock_bh(&node_list_lock);
 	tipc_num_links++;
 	spin_unlock_bh(&node_list_lock);
@@ -263,26 +267,12 @@ void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
 
 static void node_established_contact(struct tipc_node *n_ptr)
 {
-	tipc_k_signal((Handler)tipc_named_node_up, n_ptr->addr);
+	n_ptr->action_flags |= TIPC_NOTIFY_NODE_UP;
 	n_ptr->bclink.oos_state = 0;
 	n_ptr->bclink.acked = tipc_bclink_get_last_sent();
 	tipc_bclink_add_node(n_ptr->addr);
 }
 
-static void node_name_purge_complete(unsigned long node_addr)
-{
-	struct tipc_node *n_ptr;
-
-	read_lock_bh(&tipc_net_lock);
-	n_ptr = tipc_node_find(node_addr);
-	if (n_ptr) {
-		tipc_node_lock(n_ptr);
-		n_ptr->block_setup &= ~WAIT_NAMES_GONE;
-		tipc_node_unlock(n_ptr);
-	}
-	read_unlock_bh(&tipc_net_lock);
-}
-
 static void node_lost_contact(struct tipc_node *n_ptr)
 {
 	char addr_string[16];
@@ -296,10 +286,9 @@ static void node_lost_contact(struct tipc_node *n_ptr)
 		kfree_skb_list(n_ptr->bclink.deferred_head);
 		n_ptr->bclink.deferred_size = 0;
 
-		if (n_ptr->bclink.reasm_head) {
-			kfree_skb(n_ptr->bclink.reasm_head);
-			n_ptr->bclink.reasm_head = NULL;
-			n_ptr->bclink.reasm_tail = NULL;
+		if (n_ptr->bclink.reasm_buf) {
+			kfree_skb(n_ptr->bclink.reasm_buf);
+			n_ptr->bclink.reasm_buf = NULL;
 		}
 
 		tipc_bclink_remove_node(n_ptr->addr);
@@ -318,12 +307,13 @@ static void node_lost_contact(struct tipc_node *n_ptr)
 		tipc_link_reset_fragments(l_ptr);
 	}
 
-	/* Notify subscribers */
-	tipc_nodesub_notify(n_ptr);
+	n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN;
 
-	/* Prevent re-contact with node until cleanup is done */
-	n_ptr->block_setup = WAIT_PEER_DOWN | WAIT_NAMES_GONE;
-	tipc_k_signal((Handler)node_name_purge_complete, n_ptr->addr);
+	/* Notify subscribers and prevent re-contact with node until
+	 * cleanup is done.
+	 */
+	n_ptr->action_flags |= TIPC_WAIT_PEER_LINKS_DOWN |
+			       TIPC_NOTIFY_NODE_DOWN;
 }
 
 struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space)
@@ -436,3 +426,63 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space)
 	rcu_read_unlock();
 	return buf;
 }
+
+/**
+ * tipc_node_get_linkname - get the name of a link
+ *
+ * @bearer_id: id of the bearer
+ * @node: peer node address
+ * @linkname: link name output buffer
+ *
+ * Returns 0 on success
+ */
+int tipc_node_get_linkname(u32 bearer_id, u32 addr, char *linkname, size_t len)
+{
+	struct tipc_link *link;
+	struct tipc_node *node = tipc_node_find(addr);
+
+	if ((bearer_id >= MAX_BEARERS) || !node)
+		return -EINVAL;
+	tipc_node_lock(node);
+	link = node->links[bearer_id];
+	if (link) {
+		strncpy(linkname, link->name, len);
+		tipc_node_unlock(node);
+		return 0;
+	}
+	tipc_node_unlock(node);
+	return -EINVAL;
+}
+
+void tipc_node_unlock(struct tipc_node *node)
+{
+	LIST_HEAD(nsub_list);
+	struct tipc_link *link;
+	int pkt_sz = 0;
+	u32 addr = 0;
+
+	if (likely(!node->action_flags)) {
+		spin_unlock_bh(&node->lock);
+		return;
+	}
+
+	if (node->action_flags & TIPC_NOTIFY_NODE_DOWN) {
+		list_replace_init(&node->nsub, &nsub_list);
+		node->action_flags &= ~TIPC_NOTIFY_NODE_DOWN;
+	}
+	if (node->action_flags & TIPC_NOTIFY_NODE_UP) {
+		link = node->active_links[0];
+		node->action_flags &= ~TIPC_NOTIFY_NODE_UP;
+		if (link) {
+			pkt_sz = ((link->max_pkt - INT_H_SIZE) / ITEM_SIZE) *
+				  ITEM_SIZE;
+			addr = node->addr;
+		}
+	}
+	spin_unlock_bh(&node->lock);
+
+	if (!list_empty(&nsub_list))
+		tipc_nodesub_notify(&nsub_list);
+	if (pkt_sz)
+		tipc_named_node_up(pkt_sz, addr);
+}
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 7cbb8cec1a9..9087063793f 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -47,62 +47,73 @@
  */
 #define INVALID_NODE_SIG 0x10000
 
-/* Flags used to block (re)establishment of contact with a neighboring node */
-#define WAIT_PEER_DOWN	0x0001	/* wait to see that peer's links are down */
-#define WAIT_NAMES_GONE	0x0002	/* wait for peer's publications to be purged */
-#define WAIT_NODE_DOWN	0x0004	/* wait until peer node is declared down */
+/* Flags used to take different actions according to flag type
+ * TIPC_WAIT_PEER_LINKS_DOWN: wait to see that peer's links are down
+ * TIPC_WAIT_OWN_LINKS_DOWN: wait until peer node is declared down
+ * TIPC_NOTIFY_NODE_DOWN: notify node is down
+ * TIPC_NOTIFY_NODE_UP: notify node is up
+ */
+enum {
+	TIPC_WAIT_PEER_LINKS_DOWN	= (1 << 1),
+	TIPC_WAIT_OWN_LINKS_DOWN	= (1 << 2),
+	TIPC_NOTIFY_NODE_DOWN		= (1 << 3),
+	TIPC_NOTIFY_NODE_UP		= (1 << 4)
+};
+
+/**
+ * struct tipc_node_bclink - TIPC node bclink structure
+ * @acked: sequence # of last outbound b'cast message acknowledged by node
+ * @last_in: sequence # of last in-sequence b'cast message received from node
+ * @last_sent: sequence # of last b'cast message sent by node
+ * @oos_state: state tracker for handling OOS b'cast messages
+ * @deferred_size: number of OOS b'cast messages in deferred queue
+ * @deferred_head: oldest OOS b'cast message received from node
+ * @deferred_tail: newest OOS b'cast message received from node
+ * @reasm_buf: broadcast reassembly queue head from node
+ * @recv_permitted: true if node is allowed to receive b'cast messages
+ */
+struct tipc_node_bclink {
+	u32 acked;
+	u32 last_in;
+	u32 last_sent;
+	u32 oos_state;
+	u32 deferred_size;
+	struct sk_buff *deferred_head;
+	struct sk_buff *deferred_tail;
+	struct sk_buff *reasm_buf;
+	bool recv_permitted;
+};
 
 /**
  * struct tipc_node - TIPC node structure
  * @addr: network address of node
  * @lock: spinlock governing access to structure
  * @hash: links to adjacent nodes in unsorted hash chain
- * @list: links to adjacent nodes in sorted list of cluster's nodes
- * @nsub: list of "node down" subscriptions monitoring node
  * @active_links: pointers to active links to node
  * @links: pointers to all links to node
+ * @action_flags: bit mask of different types of node actions
+ * @bclink: broadcast-related info
+ * @list: links to adjacent nodes in sorted list of cluster's nodes
  * @working_links: number of working links to node (both active and standby)
- * @block_setup: bit mask of conditions preventing link establishment to node
  * @link_cnt: number of links to node
  * @signature: node instance identifier
- * @bclink: broadcast-related info
+ * @nsub: list of "node down" subscriptions monitoring node
  * @rcu: rcu struct for tipc_node
- *    @acked: sequence # of last outbound b'cast message acknowledged by node
- *    @last_in: sequence # of last in-sequence b'cast message received from node
- *    @last_sent: sequence # of last b'cast message sent by node
- *    @oos_state: state tracker for handling OOS b'cast messages
- *    @deferred_size: number of OOS b'cast messages in deferred queue
- *    @deferred_head: oldest OOS b'cast message received from node
- *    @deferred_tail: newest OOS b'cast message received from node
- *    @reasm_head: broadcast reassembly queue head from node
- *    @reasm_tail: last broadcast fragment received from node
- *    @recv_permitted: true if node is allowed to receive b'cast messages
  */
 struct tipc_node {
 	u32 addr;
 	spinlock_t lock;
 	struct hlist_node hash;
-	struct list_head list;
-	struct list_head nsub;
 	struct tipc_link *active_links[2];
 	struct tipc_link *links[MAX_BEARERS];
+	unsigned int action_flags;
+	struct tipc_node_bclink bclink;
+	struct list_head list;
 	int link_cnt;
 	int working_links;
-	int block_setup;
 	u32 signature;
+	struct list_head nsub;
 	struct rcu_head rcu;
-	struct {
-		u32 acked;
-		u32 last_in;
-		u32 last_sent;
-		u32 oos_state;
-		u32 deferred_size;
-		struct sk_buff *deferred_head;
-		struct sk_buff *deferred_tail;
-		struct sk_buff *reasm_head;
-		struct sk_buff *reasm_tail;
-		bool recv_permitted;
-	} bclink;
 };
 
 extern struct list_head tipc_node_list;
@@ -118,15 +129,18 @@ int tipc_node_active_links(struct tipc_node *n_ptr);
 int tipc_node_is_up(struct tipc_node *n_ptr);
 struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space);
 struct sk_buff *tipc_node_get_nodes(const void *req_tlv_area, int req_tlv_space);
+int tipc_node_get_linkname(u32 bearer_id, u32 node, char *linkname, size_t len);
+void tipc_node_unlock(struct tipc_node *node);
 
-static inline void tipc_node_lock(struct tipc_node *n_ptr)
+static inline void tipc_node_lock(struct tipc_node *node)
 {
-	spin_lock_bh(&n_ptr->lock);
+	spin_lock_bh(&node->lock);
 }
 
-static inline void tipc_node_unlock(struct tipc_node *n_ptr)
+static inline bool tipc_node_blocked(struct tipc_node *node)
 {
-	spin_unlock_bh(&n_ptr->lock);
+	return (node->action_flags & (TIPC_WAIT_PEER_LINKS_DOWN |
+		TIPC_NOTIFY_NODE_DOWN | TIPC_WAIT_OWN_LINKS_DOWN));
 }
 
 #endif
diff --git a/net/tipc/node_subscr.c b/net/tipc/node_subscr.c
index 8a7384c04ad..7c59ab1d6ec 100644
--- a/net/tipc/node_subscr.c
+++ b/net/tipc/node_subscr.c
@@ -81,14 +81,13 @@ void tipc_nodesub_unsubscribe(struct tipc_node_subscr *node_sub)
  *
  * Note: node is locked by caller
  */
-void tipc_nodesub_notify(struct tipc_node *node)
+void tipc_nodesub_notify(struct list_head *nsub_list)
 {
-	struct tipc_node_subscr *ns;
+	struct tipc_node_subscr *ns, *safe;
 
-	list_for_each_entry(ns, &node->nsub, nodesub_list) {
+	list_for_each_entry_safe(ns, safe, nsub_list, nodesub_list) {
 		if (ns->handle_node_down) {
-			tipc_k_signal((Handler)ns->handle_node_down,
-				      (unsigned long)ns->usr_handle);
+			ns->handle_node_down(ns->usr_handle);
 			ns->handle_node_down = NULL;
 		}
 	}
diff --git a/net/tipc/node_subscr.h b/net/tipc/node_subscr.h
index c95d20727de..d91b8cc81e3 100644
--- a/net/tipc/node_subscr.h
+++ b/net/tipc/node_subscr.h
@@ -58,6 +58,6 @@ struct tipc_node_subscr {
 void tipc_nodesub_subscribe(struct tipc_node_subscr *node_sub, u32 addr,
 			    void *usr_handle, net_ev_handler handle_down);
 void tipc_nodesub_unsubscribe(struct tipc_node_subscr *node_sub);
-void tipc_nodesub_notify(struct tipc_node *node);
+void tipc_nodesub_notify(struct list_head *nsub_list);
 
 #endif
diff --git a/net/tipc/port.c b/net/tipc/port.c
index 5c14c7801ee..5fd7acce01e 100644
--- a/net/tipc/port.c
+++ b/net/tipc/port.c
@@ -165,7 +165,7 @@ void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp)
 		msg_set_destnode(msg, tipc_own_addr);
 		if (dp->count == 1) {
 			msg_set_destport(msg, dp->ports[0]);
-			tipc_port_rcv(buf);
+			tipc_sk_rcv(buf);
 			tipc_port_list_free(dp);
 			return;
 		}
@@ -180,7 +180,7 @@ void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp)
 			if ((index == 0) && (cnt != 0))
 				item = item->next;
 			msg_set_destport(buf_msg(b), item->ports[index]);
-			tipc_port_rcv(b);
+			tipc_sk_rcv(b);
 		}
 	}
 exit:
@@ -343,7 +343,7 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err)
 	/* send returned message & dispose of rejected message */
 	src_node = msg_prevnode(msg);
 	if (in_own_node(src_node))
-		tipc_port_rcv(rbuf);
+		tipc_sk_rcv(rbuf);
 	else
 		tipc_link_xmit(rbuf, src_node, msg_link_selector(rmsg));
 exit:
@@ -754,37 +754,6 @@ int tipc_port_shutdown(u32 ref)
 	return tipc_port_disconnect(ref);
 }
 
-/**
- * tipc_port_rcv - receive message from lower layer and deliver to port user
- */
-int tipc_port_rcv(struct sk_buff *buf)
-{
-	struct tipc_port *p_ptr;
-	struct tipc_msg *msg = buf_msg(buf);
-	u32 destport = msg_destport(msg);
-	u32 dsz = msg_data_sz(msg);
-	u32 err;
-
-	/* forward unresolved named message */
-	if (unlikely(!destport)) {
-		tipc_net_route_msg(buf);
-		return dsz;
-	}
-
-	/* validate destination & pass to port, otherwise reject message */
-	p_ptr = tipc_port_lock(destport);
-	if (likely(p_ptr)) {
-		err = tipc_sk_rcv(&tipc_port_to_sock(p_ptr)->sk, buf);
-		tipc_port_unlock(p_ptr);
-		if (likely(!err))
-			return dsz;
-	} else {
-		err = TIPC_ERR_NO_PORT;
-	}
-
-	return tipc_reject_msg(buf, err);
-}
-
 /*
  *  tipc_port_iovec_rcv: Concatenate and deliver sectioned
  *                       message for this node.
@@ -798,7 +767,7 @@ static int tipc_port_iovec_rcv(struct tipc_port *sender,
 
 	res = tipc_msg_build(&sender->phdr, msg_sect, len, MAX_MSG_SIZE, &buf);
 	if (likely(buf))
-		tipc_port_rcv(buf);
+		tipc_sk_rcv(buf);
 	return res;
 }
 
diff --git a/net/tipc/port.h b/net/tipc/port.h
index a00397393bd..cf4ca5b1d9a 100644
--- a/net/tipc/port.h
+++ b/net/tipc/port.h
@@ -42,9 +42,10 @@
 #include "msg.h"
 #include "node_subscr.h"
 
-#define TIPC_FLOW_CONTROL_WIN 512
-#define CONN_OVERLOAD_LIMIT	((TIPC_FLOW_CONTROL_WIN * 2 + 1) * \
-				SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE))
+#define TIPC_CONNACK_INTV         256
+#define TIPC_FLOWCTRL_WIN        (TIPC_CONNACK_INTV * 2)
+#define TIPC_CONN_OVERLOAD_LIMIT ((TIPC_FLOWCTRL_WIN * 2 + 1) * \
+				  SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE))
 
 /**
  * struct tipc_port - TIPC port structure
@@ -134,7 +135,6 @@ int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg);
 /*
  * TIPC messaging routines
  */
-int tipc_port_rcv(struct sk_buff *buf);
 
 int tipc_send(struct tipc_port *port,
 	      struct iovec const *msg_sect,
@@ -187,7 +187,7 @@ static inline void tipc_port_unlock(struct tipc_port *p_ptr)
 
 static inline int tipc_port_congested(struct tipc_port *p_ptr)
 {
-	return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2);
+	return ((p_ptr->sent - p_ptr->acked) >= TIPC_FLOWCTRL_WIN);
 }
 
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3c0256962f7..ef0475568f9 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -36,6 +36,7 @@
 
 #include "core.h"
 #include "port.h"
+#include "node.h"
 
 #include <linux/export.h>
 
@@ -44,7 +45,7 @@
 
 #define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */
 
-static int backlog_rcv(struct sock *sk, struct sk_buff *skb);
+static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 static void tipc_data_ready(struct sock *sk);
 static void tipc_write_space(struct sock *sk);
 static int tipc_release(struct socket *sock);
@@ -195,11 +196,12 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	sock->state = state;
 
 	sock_init_data(sock, sk);
-	sk->sk_backlog_rcv = backlog_rcv;
+	sk->sk_backlog_rcv = tipc_backlog_rcv;
 	sk->sk_rcvbuf = sysctl_tipc_rmem[1];
 	sk->sk_data_ready = tipc_data_ready;
 	sk->sk_write_space = tipc_write_space;
-	tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT;
+	tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
+	atomic_set(&tsk->dupl_rcvcnt, 0);
 	tipc_port_unlock(port);
 
 	if (sock->state == SS_READY) {
@@ -983,10 +985,11 @@ static int anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 	return 0;
 }
 
-static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo)
+static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 {
 	struct sock *sk = sock->sk;
 	DEFINE_WAIT(wait);
+	long timeo = *timeop;
 	int err;
 
 	for (;;) {
@@ -1011,6 +1014,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo)
 			break;
 	}
 	finish_wait(sk_sleep(sk), &wait);
+	*timeop = timeo;
 	return err;
 }
 
@@ -1054,7 +1058,7 @@ static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock,
 restart:
 
 	/* Look for a message in receive queue; wait if necessary */
-	res = tipc_wait_for_rcvmsg(sock, timeo);
+	res = tipc_wait_for_rcvmsg(sock, &timeo);
 	if (res)
 		goto exit;
 
@@ -1100,7 +1104,7 @@ restart:
 	/* Consume received message (optional) */
 	if (likely(!(flags & MSG_PEEK))) {
 		if ((sock->state != SS_READY) &&
-		    (++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
+		    (++port->conn_unacked >= TIPC_CONNACK_INTV))
 			tipc_acknowledge(port->ref, port->conn_unacked);
 		advance_rx_queue(sk);
 	}
@@ -1152,7 +1156,7 @@ static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock,
 
 restart:
 	/* Look for a message in receive queue; wait if necessary */
-	res = tipc_wait_for_rcvmsg(sock, timeo);
+	res = tipc_wait_for_rcvmsg(sock, &timeo);
 	if (res)
 		goto exit;
 
@@ -1209,7 +1213,7 @@ restart:
 
 	/* Consume received message (optional) */
 	if (likely(!(flags & MSG_PEEK))) {
-		if (unlikely(++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN))
+		if (unlikely(++port->conn_unacked >= TIPC_CONNACK_INTV))
 			tipc_acknowledge(port->ref, port->conn_unacked);
 		advance_rx_queue(sk);
 	}
@@ -1415,7 +1419,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
 }
 
 /**
- * backlog_rcv - handle incoming message from backlog queue
+ * tipc_backlog_rcv - handle incoming message from backlog queue
  * @sk: socket
  * @buf: message
  *
@@ -1423,47 +1427,74 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
  *
  * Returns 0
  */
-static int backlog_rcv(struct sock *sk, struct sk_buff *buf)
+static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *buf)
 {
 	u32 res;
+	struct tipc_sock *tsk = tipc_sk(sk);
+	uint truesize = buf->truesize;
 
 	res = filter_rcv(sk, buf);
-	if (res)
+	if (unlikely(res))
 		tipc_reject_msg(buf, res);
+
+	if (atomic_read(&tsk->dupl_rcvcnt) < TIPC_CONN_OVERLOAD_LIMIT)
+		atomic_add(truesize, &tsk->dupl_rcvcnt);
+
 	return 0;
 }
 
 /**
  * tipc_sk_rcv - handle incoming message
- * @sk:  socket receiving message
- * @buf: message
- *
- * Called with port lock already taken.
- *
- * Returns TIPC error status code (TIPC_OK if message is not to be rejected)
+ * @buf: buffer containing arriving message
+ * Consumes buffer
+ * Returns 0 if success, or errno: -EHOSTUNREACH
  */
-u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf)
+int tipc_sk_rcv(struct sk_buff *buf)
 {
-	u32 res;
+	struct tipc_sock *tsk;
+	struct tipc_port *port;
+	struct sock *sk;
+	u32 dport = msg_destport(buf_msg(buf));
+	int err = TIPC_OK;
+	uint limit;
 
-	/*
-	 * Process message if socket is unlocked; otherwise add to backlog queue
-	 *
-	 * This code is based on sk_receive_skb(), but must be distinct from it
-	 * since a TIPC-specific filter/reject mechanism is utilized
-	 */
+	/* Forward unresolved named message */
+	if (unlikely(!dport)) {
+		tipc_net_route_msg(buf);
+		return 0;
+	}
+
+	/* Validate destination */
+	port = tipc_port_lock(dport);
+	if (unlikely(!port)) {
+		err = TIPC_ERR_NO_PORT;
+		goto exit;
+	}
+
+	tsk = tipc_port_to_sock(port);
+	sk = &tsk->sk;
+
+	/* Queue message */
 	bh_lock_sock(sk);
+
 	if (!sock_owned_by_user(sk)) {
-		res = filter_rcv(sk, buf);
+		err = filter_rcv(sk, buf);
 	} else {
-		if (sk_add_backlog(sk, buf, rcvbuf_limit(sk, buf)))
-			res = TIPC_ERR_OVERLOAD;
-		else
-			res = TIPC_OK;
+		if (sk->sk_backlog.len == 0)
+			atomic_set(&tsk->dupl_rcvcnt, 0);
+		limit = rcvbuf_limit(sk, buf) + atomic_read(&tsk->dupl_rcvcnt);
+		if (sk_add_backlog(sk, buf, limit))
+			err = TIPC_ERR_OVERLOAD;
 	}
+
 	bh_unlock_sock(sk);
+	tipc_port_unlock(port);
 
-	return res;
+	if (likely(!err))
+		return 0;
+exit:
+	tipc_reject_msg(buf, err);
+	return -EHOSTUNREACH;
 }
 
 static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
@@ -1905,6 +1936,28 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
 	return put_user(sizeof(value), ol);
 }
 
+int tipc_ioctl(struct socket *sk, unsigned int cmd, unsigned long arg)
+{
+	struct tipc_sioc_ln_req lnr;
+	void __user *argp = (void __user *)arg;
+
+	switch (cmd) {
+	case SIOCGETLINKNAME:
+		if (copy_from_user(&lnr, argp, sizeof(lnr)))
+			return -EFAULT;
+		if (!tipc_node_get_linkname(lnr.bearer_id, lnr.peer,
+					    lnr.linkname, TIPC_MAX_LINK_NAME)) {
+			if (copy_to_user(argp, &lnr, sizeof(lnr)))
+				return -EFAULT;
+			return 0;
+		}
+		return -EADDRNOTAVAIL;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
 /* Protocol switches for the various types of TIPC sockets */
 
 static const struct proto_ops msg_ops = {
@@ -1917,7 +1970,7 @@ static const struct proto_ops msg_ops = {
 	.accept		= sock_no_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
-	.ioctl		= sock_no_ioctl,
+	.ioctl		= tipc_ioctl,
 	.listen		= sock_no_listen,
 	.shutdown	= tipc_shutdown,
 	.setsockopt	= tipc_setsockopt,
@@ -1938,7 +1991,7 @@ static const struct proto_ops packet_ops = {
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
-	.ioctl		= sock_no_ioctl,
+	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
 	.setsockopt	= tipc_setsockopt,
@@ -1959,7 +2012,7 @@ static const struct proto_ops stream_ops = {
 	.accept		= tipc_accept,
 	.getname	= tipc_getname,
 	.poll		= tipc_poll,
-	.ioctl		= sock_no_ioctl,
+	.ioctl		= tipc_ioctl,
 	.listen		= tipc_listen,
 	.shutdown	= tipc_shutdown,
 	.setsockopt	= tipc_setsockopt,
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index 74e5c7f195a..3afcd2a70b3 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -44,12 +44,14 @@
  * @port: port - interacts with 'sk' and with the rest of the TIPC stack
  * @peer_name: the peer of the connection, if any
  * @conn_timeout: the time we can wait for an unresponded setup request
+ * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
  */
 
 struct tipc_sock {
 	struct sock sk;
 	struct tipc_port port;
 	unsigned int conn_timeout;
+	atomic_t dupl_rcvcnt;
 };
 
 static inline struct tipc_sock *tipc_sk(const struct sock *sk)
@@ -67,6 +69,6 @@ static inline void tipc_sock_wakeup(struct tipc_sock *tsk)
 	tsk->sk.sk_write_space(&tsk->sk);
 }
 
-u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf);
+int tipc_sk_rcv(struct sk_buff *buf);
 
 #endif
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 749f80c21e2..e9688438073 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1492,10 +1492,14 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (len > sk->sk_sndbuf - 32)
 		goto out;
 
-	if (len > SKB_MAX_ALLOC)
+	if (len > SKB_MAX_ALLOC) {
 		data_len = min_t(size_t,
 				 len - SKB_MAX_ALLOC,
 				 MAX_SKB_FRAGS * PAGE_SIZE);
+		data_len = PAGE_ALIGN(data_len);
+
+		BUILD_BUG_ON(SKB_MAX_ALLOC < PAGE_SIZE);
+	}
 
 	skb = sock_alloc_send_pskb(sk, len - data_len, data_len,
 				   msg->msg_flags & MSG_DONTWAIT, &err,
@@ -1670,6 +1674,8 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
 		data_len = max_t(int, 0, size - SKB_MAX_HEAD(0));
 
+		data_len = min_t(size_t, size, PAGE_ALIGN(data_len));
+
 		skb = sock_alloc_send_pskb(sk, size - data_len, data_len,
 					   msg->msg_flags & MSG_DONTWAIT, &err,
 					   get_order(UNIX_SKB_FRAGS_SZ));
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index 16d08b39921..405f3c4cf70 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -95,6 +95,43 @@ config CFG80211_CERTIFICATION_ONUS
 	  you are a wireless researcher and are working in a controlled
 	  and approved environment by your local regulatory agency.
 
+config CFG80211_REG_CELLULAR_HINTS
+	bool "cfg80211 regulatory support for cellular base station hints"
+	depends on CFG80211_CERTIFICATION_ONUS
+	---help---
+	  This option enables support for parsing regulatory hints
+	  from cellular base stations. If enabled and at least one driver
+	  claims support for parsing cellular base station hints the
+	  regulatory core will allow and parse these regulatory hints.
+	  The regulatory core will only apply these regulatory hints on
+	  drivers that support this feature. You should only enable this
+	  feature if you have tested and validated this feature on your
+	  systems.
+
+config CFG80211_REG_RELAX_NO_IR
+	bool "cfg80211 support for NO_IR relaxation"
+	depends on CFG80211_CERTIFICATION_ONUS
+	---help---
+	 This option enables support for relaxation of the NO_IR flag for
+	 situations that certain regulatory bodies have provided clarifications
+	 on how relaxation can occur. This feature has an inherent dependency on
+	 userspace features which must have been properly tested and as such is
+	 not enabled by default.
+
+	 A relaxation feature example is allowing the operation of a P2P group
+	 owner (GO) on channels marked with NO_IR if there is an additional BSS
+	 interface which associated to an AP which userspace assumes or confirms
+	 to be an authorized master, i.e., with radar detection support and DFS
+	 capabilities. However, note that in order to not create daisy chain
+	 scenarios, this relaxation is not allowed in cases that the BSS client
+	 is associated to P2P GO and in addition the P2P GO instantiated on
+	 a channel due to this relaxation should not allow connection from
+	 non P2P clients.
+
+	 The regulatory core will apply these relaxations only for drivers that
+	 support this feature by declaring the appropriate channel flags and
+	 capabilities in their registration flow.
+
 config CFG80211_DEFAULT_PS
 	bool "enable powersave by default"
 	depends on CFG80211
diff --git a/net/wireless/ap.c b/net/wireless/ap.c
index 3e02ade508d..bdad1f95156 100644
--- a/net/wireless/ap.c
+++ b/net/wireless/ap.c
@@ -6,8 +6,8 @@
 #include "rdev-ops.h"
 
 
-static int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
-			      struct net_device *dev, bool notify)
+int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
+		       struct net_device *dev, bool notify)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	int err;
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 9c9501a35fb..992b34070bc 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -326,28 +326,57 @@ static int cfg80211_get_chans_dfs_required(struct wiphy *wiphy,
 
 
 int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
-				  const struct cfg80211_chan_def *chandef)
+				  const struct cfg80211_chan_def *chandef,
+				  enum nl80211_iftype iftype)
 {
 	int width;
-	int r;
+	int ret;
 
 	if (WARN_ON(!cfg80211_chandef_valid(chandef)))
 		return -EINVAL;
 
-	width = cfg80211_chandef_get_width(chandef);
-	if (width < 0)
-		return -EINVAL;
+	switch (iftype) {
+	case NL80211_IFTYPE_ADHOC:
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_P2P_GO:
+	case NL80211_IFTYPE_MESH_POINT:
+		width = cfg80211_chandef_get_width(chandef);
+		if (width < 0)
+			return -EINVAL;
 
-	r = cfg80211_get_chans_dfs_required(wiphy, chandef->center_freq1,
-					    width);
-	if (r)
-		return r;
+		ret = cfg80211_get_chans_dfs_required(wiphy,
+						      chandef->center_freq1,
+						      width);
+		if (ret < 0)
+			return ret;
+		else if (ret > 0)
+			return BIT(chandef->width);
 
-	if (!chandef->center_freq2)
-		return 0;
+		if (!chandef->center_freq2)
+			return 0;
+
+		ret = cfg80211_get_chans_dfs_required(wiphy,
+						      chandef->center_freq2,
+						      width);
+		if (ret < 0)
+			return ret;
+		else if (ret > 0)
+			return BIT(chandef->width);
 
-	return cfg80211_get_chans_dfs_required(wiphy, chandef->center_freq2,
-					       width);
+		break;
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_P2P_CLIENT:
+	case NL80211_IFTYPE_MONITOR:
+	case NL80211_IFTYPE_AP_VLAN:
+	case NL80211_IFTYPE_WDS:
+	case NL80211_IFTYPE_P2P_DEVICE:
+		break;
+	case NL80211_IFTYPE_UNSPECIFIED:
+	case NUM_NL80211_IFTYPES:
+		WARN_ON(1);
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL(cfg80211_chandef_dfs_required);
 
@@ -587,12 +616,14 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 		width = 5;
 		break;
 	case NL80211_CHAN_WIDTH_10:
+		prohibited_flags |= IEEE80211_CHAN_NO_10MHZ;
 		width = 10;
 		break;
 	case NL80211_CHAN_WIDTH_20:
 		if (!ht_cap->ht_supported)
 			return false;
 	case NL80211_CHAN_WIDTH_20_NOHT:
+		prohibited_flags |= IEEE80211_CHAN_NO_20MHZ;
 		width = 20;
 		break;
 	case NL80211_CHAN_WIDTH_40:
@@ -661,17 +692,111 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL(cfg80211_chandef_usable);
 
+/*
+ * For GO only, check if the channel can be used under permissive conditions
+ * mandated by the some regulatory bodies, i.e., the channel is marked with
+ * IEEE80211_CHAN_GO_CONCURRENT and there is an additional station interface
+ * associated to an AP on the same channel or on the same UNII band
+ * (assuming that the AP is an authorized master).
+ * In addition allow the GO to operate on a channel on which indoor operation is
+ * allowed, iff we are currently operating in an indoor environment.
+ */
+static bool cfg80211_go_permissive_chan(struct cfg80211_registered_device *rdev,
+					struct ieee80211_channel *chan)
+{
+	struct wireless_dev *wdev_iter;
+	struct wiphy *wiphy = wiphy_idx_to_wiphy(rdev->wiphy_idx);
+
+	ASSERT_RTNL();
+
+	if (!config_enabled(CONFIG_CFG80211_REG_RELAX_NO_IR) ||
+	    !(wiphy->regulatory_flags & REGULATORY_ENABLE_RELAX_NO_IR))
+		return false;
+
+	if (regulatory_indoor_allowed() &&
+	    (chan->flags & IEEE80211_CHAN_INDOOR_ONLY))
+		return true;
+
+	if (!(chan->flags & IEEE80211_CHAN_GO_CONCURRENT))
+		return false;
+
+	/*
+	 * Generally, it is possible to rely on another device/driver to allow
+	 * the GO concurrent relaxation, however, since the device can further
+	 * enforce the relaxation (by doing a similar verifications as this),
+	 * and thus fail the GO instantiation, consider only the interfaces of
+	 * the current registered device.
+	 */
+	list_for_each_entry(wdev_iter, &rdev->wdev_list, list) {
+		struct ieee80211_channel *other_chan = NULL;
+		int r1, r2;
+
+		if (wdev_iter->iftype != NL80211_IFTYPE_STATION ||
+		    !netif_running(wdev_iter->netdev))
+			continue;
+
+		wdev_lock(wdev_iter);
+		if (wdev_iter->current_bss)
+			other_chan = wdev_iter->current_bss->pub.channel;
+		wdev_unlock(wdev_iter);
+
+		if (!other_chan)
+			continue;
+
+		if (chan == other_chan)
+			return true;
+
+		if (chan->band != IEEE80211_BAND_5GHZ)
+			continue;
+
+		r1 = cfg80211_get_unii(chan->center_freq);
+		r2 = cfg80211_get_unii(other_chan->center_freq);
+
+		if (r1 != -EINVAL && r1 == r2) {
+			/*
+			 * At some locations channels 149-165 are considered a
+			 * bundle, but at other locations, e.g., Indonesia,
+			 * channels 149-161 are considered a bundle while
+			 * channel 165 is left out and considered to be in a
+			 * different bundle. Thus, in case that there is a
+			 * station interface connected to an AP on channel 165,
+			 * it is assumed that channels 149-161 are allowed for
+			 * GO operations. However, having a station interface
+			 * connected to an AP on channels 149-161, does not
+			 * allow GO operation on channel 165.
+			 */
+			if (chan->center_freq == 5825 &&
+			    other_chan->center_freq != 5825)
+				continue;
+			return true;
+		}
+	}
+
+	return false;
+}
+
 bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
-			     struct cfg80211_chan_def *chandef)
+			     struct cfg80211_chan_def *chandef,
+			     enum nl80211_iftype iftype)
 {
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	bool res;
 	u32 prohibited_flags = IEEE80211_CHAN_DISABLED |
-			       IEEE80211_CHAN_NO_IR |
 			       IEEE80211_CHAN_RADAR;
 
-	trace_cfg80211_reg_can_beacon(wiphy, chandef);
+	trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype);
 
-	if (cfg80211_chandef_dfs_required(wiphy, chandef) > 0 &&
+	/*
+	 * Under certain conditions suggested by the some regulatory bodies
+	 * a GO can operate on channels marked with IEEE80211_NO_IR
+	 * so set this flag only if such relaxations are not enabled and
+	 * the conditions are not met.
+	 */
+	if (iftype != NL80211_IFTYPE_P2P_GO ||
+	    !cfg80211_go_permissive_chan(rdev, chandef->chan))
+		prohibited_flags |= IEEE80211_CHAN_NO_IR;
+
+	if (cfg80211_chandef_dfs_required(wiphy, chandef, iftype) > 0 &&
 	    cfg80211_chandef_dfs_available(wiphy, chandef)) {
 		/* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */
 		prohibited_flags = IEEE80211_CHAN_DISABLED;
@@ -701,6 +826,8 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 		        enum cfg80211_chan_mode *chanmode,
 		        u8 *radar_detect)
 {
+	int ret;
+
 	*chan = NULL;
 	*chanmode = CHAN_MODE_UNDEFINED;
 
@@ -743,8 +870,11 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 			*chan = wdev->chandef.chan;
 			*chanmode = CHAN_MODE_SHARED;
 
-			if (cfg80211_chandef_dfs_required(wdev->wiphy,
-							  &wdev->chandef))
+			ret = cfg80211_chandef_dfs_required(wdev->wiphy,
+							    &wdev->chandef,
+							    wdev->iftype);
+			WARN_ON(ret < 0);
+			if (ret > 0)
 				*radar_detect |= BIT(wdev->chandef.width);
 		}
 		return;
@@ -753,8 +883,11 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 			*chan = wdev->chandef.chan;
 			*chanmode = CHAN_MODE_SHARED;
 
-			if (cfg80211_chandef_dfs_required(wdev->wiphy,
-							  &wdev->chandef))
+			ret = cfg80211_chandef_dfs_required(wdev->wiphy,
+							    &wdev->chandef,
+							    wdev->iftype);
+			WARN_ON(ret < 0);
+			if (ret > 0)
 				*radar_detect |= BIT(wdev->chandef.width);
 		}
 		return;
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 086cddd03ba..a1c40654dd9 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -69,7 +69,7 @@ struct cfg80211_registered_device *cfg80211_rdev_by_wiphy_idx(int wiphy_idx)
 
 int get_wiphy_idx(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	return rdev->wiphy_idx;
 }
@@ -130,7 +130,7 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
 			    newname))
 		pr_err("failed to rename debugfs dir to %s!\n", newname);
 
-	nl80211_notify_dev_rename(rdev);
+	nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
 
 	return 0;
 }
@@ -210,15 +210,12 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev,
 	}
 }
 
-static int cfg80211_rfkill_set_block(void *data, bool blocked)
+void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = data;
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct wireless_dev *wdev;
 
-	if (!blocked)
-		return 0;
-
-	rtnl_lock();
+	ASSERT_RTNL();
 
 	list_for_each_entry(wdev, &rdev->wdev_list, list) {
 		if (wdev->netdev) {
@@ -234,7 +231,18 @@ static int cfg80211_rfkill_set_block(void *data, bool blocked)
 			break;
 		}
 	}
+}
+EXPORT_SYMBOL_GPL(cfg80211_shutdown_all_interfaces);
+
+static int cfg80211_rfkill_set_block(void *data, bool blocked)
+{
+	struct cfg80211_registered_device *rdev = data;
+
+	if (!blocked)
+		return 0;
 
+	rtnl_lock();
+	cfg80211_shutdown_all_interfaces(&rdev->wiphy);
 	rtnl_unlock();
 
 	return 0;
@@ -260,6 +268,45 @@ static void cfg80211_event_work(struct work_struct *work)
 	rtnl_unlock();
 }
 
+void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev)
+{
+	struct cfg80211_iface_destroy *item;
+
+	ASSERT_RTNL();
+
+	spin_lock_irq(&rdev->destroy_list_lock);
+	while ((item = list_first_entry_or_null(&rdev->destroy_list,
+						struct cfg80211_iface_destroy,
+						list))) {
+		struct wireless_dev *wdev, *tmp;
+		u32 nlportid = item->nlportid;
+
+		list_del(&item->list);
+		kfree(item);
+		spin_unlock_irq(&rdev->destroy_list_lock);
+
+		list_for_each_entry_safe(wdev, tmp, &rdev->wdev_list, list) {
+			if (nlportid == wdev->owner_nlportid)
+				rdev_del_virtual_intf(rdev, wdev);
+		}
+
+		spin_lock_irq(&rdev->destroy_list_lock);
+	}
+	spin_unlock_irq(&rdev->destroy_list_lock);
+}
+
+static void cfg80211_destroy_iface_wk(struct work_struct *work)
+{
+	struct cfg80211_registered_device *rdev;
+
+	rdev = container_of(work, struct cfg80211_registered_device,
+			    destroy_work);
+
+	rtnl_lock();
+	cfg80211_destroy_ifaces(rdev);
+	rtnl_unlock();
+}
+
 /* exported functions */
 
 struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
@@ -318,6 +365,10 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 	rdev->wiphy.dev.class = &ieee80211_class;
 	rdev->wiphy.dev.platform_data = rdev;
 
+	INIT_LIST_HEAD(&rdev->destroy_list);
+	spin_lock_init(&rdev->destroy_list_lock);
+	INIT_WORK(&rdev->destroy_work, cfg80211_destroy_iface_wk);
+
 #ifdef CONFIG_CFG80211_DEFAULT_PS
 	rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
 #endif
@@ -351,6 +402,8 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv)
 	rdev->wiphy.rts_threshold = (u32) -1;
 	rdev->wiphy.coverage_class = 0;
 
+	rdev->wiphy.max_num_csa_counters = 1;
+
 	return &rdev->wiphy;
 }
 EXPORT_SYMBOL(wiphy_new);
@@ -396,10 +449,7 @@ static int wiphy_verify_combinations(struct wiphy *wiphy)
 		for (j = 0; j < c->n_limits; j++) {
 			u16 types = c->limits[j].types;
 
-			/*
-			 * interface types shouldn't overlap, this is
-			 * used in cfg80211_can_change_interface()
-			 */
+			/* interface types shouldn't overlap */
 			if (WARN_ON(types & all_iftypes))
 				return -EINVAL;
 			all_iftypes |= types;
@@ -435,7 +485,7 @@ static int wiphy_verify_combinations(struct wiphy *wiphy)
 
 int wiphy_register(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	int res;
 	enum ieee80211_band band;
 	struct ieee80211_supported_band *sband;
@@ -610,13 +660,15 @@ int wiphy_register(struct wiphy *wiphy)
 		return res;
 	}
 
+	nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY);
+
 	return 0;
 }
 EXPORT_SYMBOL(wiphy_register);
 
 void wiphy_rfkill_start_polling(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	if (!rdev->ops->rfkill_poll)
 		return;
@@ -627,7 +679,7 @@ EXPORT_SYMBOL(wiphy_rfkill_start_polling);
 
 void wiphy_rfkill_stop_polling(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	rfkill_pause_polling(rdev->rfkill);
 }
@@ -635,7 +687,7 @@ EXPORT_SYMBOL(wiphy_rfkill_stop_polling);
 
 void wiphy_unregister(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	wait_event(rdev->dev_wait, ({
 		int __count;
@@ -648,9 +700,10 @@ void wiphy_unregister(struct wiphy *wiphy)
 		rfkill_unregister(rdev->rfkill);
 
 	rtnl_lock();
+	nl80211_notify_wiphy(rdev, NL80211_CMD_DEL_WIPHY);
 	rdev->wiphy.registered = false;
 
-	BUG_ON(!list_empty(&rdev->wdev_list));
+	WARN_ON(!list_empty(&rdev->wdev_list));
 
 	/*
 	 * First remove the hardware from everywhere, this makes
@@ -675,6 +728,7 @@ void wiphy_unregister(struct wiphy *wiphy)
 	cancel_work_sync(&rdev->conn_work);
 	flush_work(&rdev->event_work);
 	cancel_delayed_work_sync(&rdev->dfs_update_channels_wk);
+	flush_work(&rdev->destroy_work);
 
 #ifdef CONFIG_PM
 	if (rdev->wiphy.wowlan_config && rdev->ops->set_wakeup)
@@ -707,7 +761,7 @@ EXPORT_SYMBOL(wiphy_free);
 
 void wiphy_rfkill_set_hw_state(struct wiphy *wiphy, bool blocked)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	if (rfkill_set_hw_state(rdev->rfkill, blocked))
 		schedule_work(&rdev->rfkill_sync);
@@ -716,7 +770,7 @@ EXPORT_SYMBOL(wiphy_rfkill_set_hw_state);
 
 void cfg80211_unregister_wdev(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	ASSERT_RTNL();
 
@@ -751,23 +805,23 @@ void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev,
 		rdev->num_running_monitor_ifaces += num;
 }
 
-void cfg80211_leave(struct cfg80211_registered_device *rdev,
-		    struct wireless_dev *wdev)
+void __cfg80211_leave(struct cfg80211_registered_device *rdev,
+		      struct wireless_dev *wdev)
 {
 	struct net_device *dev = wdev->netdev;
 
 	ASSERT_RTNL();
+	ASSERT_WDEV_LOCK(wdev);
 
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_ADHOC:
-		cfg80211_leave_ibss(rdev, dev, true);
+		__cfg80211_leave_ibss(rdev, dev, true);
 		break;
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_STATION:
 		if (rdev->sched_scan_req && dev == rdev->sched_scan_req->dev)
 			__cfg80211_stop_sched_scan(rdev, false);
 
-		wdev_lock(wdev);
 #ifdef CONFIG_CFG80211_WEXT
 		kfree(wdev->wext.ie);
 		wdev->wext.ie = NULL;
@@ -776,32 +830,60 @@ void cfg80211_leave(struct cfg80211_registered_device *rdev,
 #endif
 		cfg80211_disconnect(rdev, dev,
 				    WLAN_REASON_DEAUTH_LEAVING, true);
-		wdev_unlock(wdev);
 		break;
 	case NL80211_IFTYPE_MESH_POINT:
-		cfg80211_leave_mesh(rdev, dev);
+		__cfg80211_leave_mesh(rdev, dev);
 		break;
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
-		cfg80211_stop_ap(rdev, dev, true);
+		__cfg80211_stop_ap(rdev, dev, true);
 		break;
 	default:
 		break;
 	}
 }
 
+void cfg80211_leave(struct cfg80211_registered_device *rdev,
+		    struct wireless_dev *wdev)
+{
+	wdev_lock(wdev);
+	__cfg80211_leave(rdev, wdev);
+	wdev_unlock(wdev);
+}
+
+void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev,
+			 gfp_t gfp)
+{
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
+	struct cfg80211_event *ev;
+	unsigned long flags;
+
+	trace_cfg80211_stop_iface(wiphy, wdev);
+
+	ev = kzalloc(sizeof(*ev), gfp);
+	if (!ev)
+		return;
+
+	ev->type = EVENT_STOPPED;
+
+	spin_lock_irqsave(&wdev->event_lock, flags);
+	list_add_tail(&ev->list, &wdev->event_list);
+	spin_unlock_irqrestore(&wdev->event_lock, flags);
+	queue_work(cfg80211_wq, &rdev->event_work);
+}
+EXPORT_SYMBOL(cfg80211_stop_iface);
+
 static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 					 unsigned long state, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev;
-	int ret;
 
 	if (!wdev)
 		return NOTIFY_DONE;
 
-	rdev = wiphy_to_dev(wdev->wiphy);
+	rdev = wiphy_to_rdev(wdev->wiphy);
 
 	WARN_ON(wdev->iftype == NL80211_IFTYPE_UNSPECIFIED);
 
@@ -959,13 +1041,14 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 	case NETDEV_PRE_UP:
 		if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)))
 			return notifier_from_errno(-EOPNOTSUPP);
-		ret = cfg80211_can_add_interface(rdev, wdev->iftype);
-		if (ret)
-			return notifier_from_errno(ret);
+		if (rfkill_blocked(rdev->rfkill))
+			return notifier_from_errno(-ERFKILL);
 		break;
+	default:
+		return NOTIFY_DONE;
 	}
 
-	return NOTIFY_DONE;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block cfg80211_netdev_notifier = {
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 5b1fdcadd46..7e3a3cef7df 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -80,13 +80,17 @@ struct cfg80211_registered_device {
 
 	struct cfg80211_coalesce *coalesce;
 
+	spinlock_t destroy_list_lock;
+	struct list_head destroy_list;
+	struct work_struct destroy_work;
+
 	/* must be last because of the way we do wiphy_priv(),
 	 * and it should at least be aligned to NETDEV_ALIGN */
 	struct wiphy wiphy __aligned(NETDEV_ALIGN);
 };
 
 static inline
-struct cfg80211_registered_device *wiphy_to_dev(struct wiphy *wiphy)
+struct cfg80211_registered_device *wiphy_to_rdev(struct wiphy *wiphy)
 {
 	BUG_ON(!wiphy);
 	return container_of(wiphy, struct cfg80211_registered_device, wiphy);
@@ -181,6 +185,7 @@ enum cfg80211_event_type {
 	EVENT_ROAMED,
 	EVENT_DISCONNECTED,
 	EVENT_IBSS_JOINED,
+	EVENT_STOPPED,
 };
 
 struct cfg80211_event {
@@ -232,6 +237,13 @@ struct cfg80211_beacon_registration {
 	u32 nlportid;
 };
 
+struct cfg80211_iface_destroy {
+	struct list_head list;
+	u32 nlportid;
+};
+
+void cfg80211_destroy_ifaces(struct cfg80211_registered_device *rdev);
+
 /* free object */
 void cfg80211_dev_free(struct cfg80211_registered_device *rdev);
 
@@ -240,8 +252,8 @@ int cfg80211_dev_rename(struct cfg80211_registered_device *rdev,
 
 void ieee80211_set_bitrate_flags(struct wiphy *wiphy);
 
-void cfg80211_bss_expire(struct cfg80211_registered_device *dev);
-void cfg80211_bss_age(struct cfg80211_registered_device *dev,
+void cfg80211_bss_expire(struct cfg80211_registered_device *rdev);
+void cfg80211_bss_age(struct cfg80211_registered_device *rdev,
                       unsigned long age_secs);
 
 /* IBSS */
@@ -270,6 +282,8 @@ int cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 		       struct net_device *dev,
 		       struct mesh_setup *setup,
 		       const struct mesh_config *conf);
+int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
+			  struct net_device *dev);
 int cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
 			struct net_device *dev);
 int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
@@ -277,6 +291,8 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
 			      struct cfg80211_chan_def *chandef);
 
 /* AP */
+int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
+		       struct net_device *dev, bool notify);
 int cfg80211_stop_ap(struct cfg80211_registered_device *rdev,
 		     struct net_device *dev, bool notify);
 
@@ -401,35 +417,6 @@ unsigned int
 cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy,
 			      const struct cfg80211_chan_def *chandef);
 
-static inline int
-cfg80211_can_change_interface(struct cfg80211_registered_device *rdev,
-			      struct wireless_dev *wdev,
-			      enum nl80211_iftype iftype)
-{
-	return cfg80211_can_use_iftype_chan(rdev, wdev, iftype, NULL,
-					    CHAN_MODE_UNDEFINED, 0);
-}
-
-static inline int
-cfg80211_can_add_interface(struct cfg80211_registered_device *rdev,
-			   enum nl80211_iftype iftype)
-{
-	if (rfkill_blocked(rdev->rfkill))
-		return -ERFKILL;
-
-	return cfg80211_can_change_interface(rdev, NULL, iftype);
-}
-
-static inline int
-cfg80211_can_use_chan(struct cfg80211_registered_device *rdev,
-		      struct wireless_dev *wdev,
-		      struct ieee80211_channel *chan,
-		      enum cfg80211_chan_mode chanmode)
-{
-	return cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
-					    chan, chanmode, 0);
-}
-
 static inline unsigned int elapsed_jiffies_msecs(unsigned long start)
 {
 	unsigned long end = jiffies;
@@ -437,7 +424,7 @@ static inline unsigned int elapsed_jiffies_msecs(unsigned long start)
 	if (end >= start)
 		return jiffies_to_msecs(end - start);
 
-	return jiffies_to_msecs(end + (MAX_JIFFY_OFFSET - start) + 1);
+	return jiffies_to_msecs(end + (ULONG_MAX - start) + 1);
 }
 
 void
@@ -459,6 +446,8 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
 void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev,
 			       enum nl80211_iftype iftype, int num);
 
+void __cfg80211_leave(struct cfg80211_registered_device *rdev,
+		      struct wireless_dev *wdev);
 void cfg80211_leave(struct cfg80211_registered_device *rdev,
 		    struct wireless_dev *wdev);
 
diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c
index e37862f1b12..d4860bfc020 100644
--- a/net/wireless/ethtool.c
+++ b/net/wireless/ethtool.c
@@ -43,7 +43,7 @@ static void cfg80211_get_ringparam(struct net_device *dev,
 				   struct ethtool_ringparam *rp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	memset(rp, 0, sizeof(*rp));
 
@@ -56,7 +56,7 @@ static int cfg80211_set_ringparam(struct net_device *dev,
 				  struct ethtool_ringparam *rp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (rp->rx_mini_pending != 0 || rp->rx_jumbo_pending != 0)
 		return -EINVAL;
@@ -70,7 +70,7 @@ static int cfg80211_set_ringparam(struct net_device *dev,
 static int cfg80211_get_sset_count(struct net_device *dev, int sset)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	if (rdev->ops->get_et_sset_count)
 		return rdev_get_et_sset_count(rdev, dev, sset);
 	return -EOPNOTSUPP;
@@ -80,7 +80,7 @@ static void cfg80211_get_stats(struct net_device *dev,
 			       struct ethtool_stats *stats, u64 *data)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	if (rdev->ops->get_et_stats)
 		rdev_get_et_stats(rdev, dev, stats, data);
 }
@@ -88,7 +88,7 @@ static void cfg80211_get_stats(struct net_device *dev,
 static void cfg80211_get_strings(struct net_device *dev, u32 sset, u8 *data)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	if (rdev->ops->get_et_strings)
 		rdev_get_et_strings(rdev, dev, sset, data);
 }
diff --git a/net/wireless/genregdb.awk b/net/wireless/genregdb.awk
index b35da8dc85d..40c37fc5b67 100644
--- a/net/wireless/genregdb.awk
+++ b/net/wireless/genregdb.awk
@@ -68,17 +68,7 @@ function parse_reg_rule()
 	sub(/,/, "", units)
 	dfs_cac = $9
 	if (units == "mW") {
-		if (power == 100) {
-			power = 20
-		} else if (power == 200) {
-			power = 23
-		} else if (power == 500) {
-			power = 27
-		} else if (power == 1000) {
-			power = 30
-		} else {
-			print "Unknown power value in database!"
-		}
+		power = 10 * log(power)/log(10)
 	} else {
 		dfs_cac = $8
 	}
@@ -117,7 +107,7 @@ function parse_reg_rule()
 
 	}
 	flags = flags "0"
-	printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %d, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags
+	printf "\t\tREG_RULE_EXT(%d, %d, %d, %d, %.0f, %d, %s),\n", start, end, bw, gain, power, dfs_cac, flags
 	rules++
 }
 
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index a6b5bdad039..8f345da3ea5 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -45,7 +45,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid,
 
 	cfg80211_upload_connect_keys(wdev);
 
-	nl80211_send_ibss_bssid(wiphy_to_dev(wdev->wiphy), dev, bssid,
+	nl80211_send_ibss_bssid(wiphy_to_rdev(wdev->wiphy), dev, bssid,
 				GFP_KERNEL);
 #ifdef CONFIG_CFG80211_WEXT
 	memset(&wrqu, 0, sizeof(wrqu));
@@ -58,7 +58,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid,
 			  struct ieee80211_channel *channel, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
 
@@ -88,8 +88,6 @@ static int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 				struct cfg80211_cached_keys *connkeys)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct ieee80211_channel *check_chan;
-	u8 radar_detect_width = 0;
 	int err;
 
 	ASSERT_WDEV_LOCK(wdev);
@@ -126,28 +124,6 @@ static int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 #ifdef CONFIG_CFG80211_WEXT
 	wdev->wext.ibss.chandef = params->chandef;
 #endif
-	check_chan = params->chandef.chan;
-	if (params->userspace_handles_dfs) {
-		/* Check for radar even if the current channel is not
-		 * a radar channel - it might decide to change to DFS
-		 * channel later.
-		 */
-		radar_detect_width = BIT(params->chandef.width);
-	}
-
-	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
-					   check_chan,
-					   (params->channel_fixed &&
-					    !radar_detect_width)
-					   ? CHAN_MODE_SHARED
-					   : CHAN_MODE_EXCLUSIVE,
-					   radar_detect_width);
-
-	if (err) {
-		wdev->connect_keys = NULL;
-		return err;
-	}
-
 	err = rdev_join_ibss(rdev, dev, params);
 	if (err) {
 		wdev->connect_keys = NULL;
@@ -180,7 +156,7 @@ int cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int i;
 
 	ASSERT_WDEV_LOCK(wdev);
@@ -335,7 +311,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 			       struct iw_freq *wextfreq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_channel *chan = NULL;
 	int err, freq;
 
@@ -346,7 +322,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev,
 	if (!rdev->ops->join_ibss)
 		return -EOPNOTSUPP;
 
-	freq = cfg80211_wext_freq(wdev->wiphy, wextfreq);
+	freq = cfg80211_wext_freq(wextfreq);
 	if (freq < 0)
 		return freq;
 
@@ -420,7 +396,7 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev,
 				struct iw_point *data, char *ssid)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	size_t len = data->length;
 	int err;
 
@@ -444,8 +420,8 @@ int cfg80211_ibss_wext_siwessid(struct net_device *dev,
 	if (len > 0 && ssid[len - 1] == '\0')
 		len--;
 
+	memcpy(wdev->ssid, ssid, len);
 	wdev->wext.ibss.ssid = wdev->ssid;
-	memcpy(wdev->wext.ibss.ssid, ssid, len);
 	wdev->wext.ibss.ssid_len = len;
 
 	wdev_lock(wdev);
@@ -487,7 +463,7 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev,
 			     struct sockaddr *ap_addr, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u8 *bssid = ap_addr->sa_data;
 	int err;
 
@@ -505,6 +481,9 @@ int cfg80211_ibss_wext_siwap(struct net_device *dev,
 	if (is_zero_ether_addr(bssid) || is_broadcast_ether_addr(bssid))
 		bssid = NULL;
 
+	if (bssid && !is_valid_ether_addr(bssid))
+		return -EINVAL;
+
 	/* both automatic */
 	if (!bssid && !wdev->wext.ibss.bssid)
 		return 0;
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index 5af5cc6b2c4..092300b30c3 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -99,7 +99,6 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 			 const struct mesh_config *conf)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	u8 radar_detect_width = 0;
 	int err;
 
 	BUILD_BUG_ON(IEEE80211_MAX_SSID_LEN != IEEE80211_MAX_MESH_ID_LEN);
@@ -175,22 +174,10 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 							       scan_width);
 	}
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &setup->chandef,
+				     NL80211_IFTYPE_MESH_POINT))
 		return -EINVAL;
 
-	err = cfg80211_chandef_dfs_required(wdev->wiphy, &setup->chandef);
-	if (err < 0)
-		return err;
-	if (err)
-		radar_detect_width = BIT(setup->chandef.width);
-
-	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
-					   setup->chandef.chan,
-					   CHAN_MODE_SHARED,
-					   radar_detect_width);
-	if (err)
-		return err;
-
 	err = rdev_join_mesh(rdev, dev, conf, setup);
 	if (!err) {
 		memcpy(wdev->ssid, setup->mesh_id, setup->mesh_id_len);
@@ -236,17 +223,6 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
 		if (!netif_running(wdev->netdev))
 			return -ENETDOWN;
 
-		/* cfg80211_can_use_chan() calls
-		 * cfg80211_can_use_iftype_chan() with no radar
-		 * detection, so if we're trying to use a radar
-		 * channel here, something is wrong.
-		 */
-		WARN_ON_ONCE(chandef->chan->flags & IEEE80211_CHAN_RADAR);
-		err = cfg80211_can_use_chan(rdev, wdev, chandef->chan,
-					    CHAN_MODE_SHARED);
-		if (err)
-			return err;
-
 		err = rdev_libertas_set_mesh_channel(rdev, wdev->netdev,
 						     chandef->chan);
 		if (!err)
@@ -262,8 +238,8 @@ int cfg80211_set_mesh_channel(struct cfg80211_registered_device *rdev,
 	return 0;
 }
 
-static int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
-				 struct net_device *dev)
+int __cfg80211_leave_mesh(struct cfg80211_registered_device *rdev,
+			  struct net_device *dev)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	int err;
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index c52ff59a3e9..266766b8d80 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -23,7 +23,7 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	u8 *ie = mgmt->u.assoc_resp.variable;
 	int ieoffs = offsetof(struct ieee80211_mgmt, u.assoc_resp.variable);
@@ -54,7 +54,7 @@ EXPORT_SYMBOL(cfg80211_rx_assoc_resp);
 static void cfg80211_process_auth(struct wireless_dev *wdev,
 				  const u8 *buf, size_t len)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	nl80211_send_rx_auth(rdev, wdev->netdev, buf, len, GFP_KERNEL);
 	cfg80211_sme_rx_auth(wdev, buf, len);
@@ -63,7 +63,7 @@ static void cfg80211_process_auth(struct wireless_dev *wdev,
 static void cfg80211_process_deauth(struct wireless_dev *wdev,
 				    const u8 *buf, size_t len)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	const u8 *bssid = mgmt->bssid;
 	u16 reason_code = le16_to_cpu(mgmt->u.deauth.reason_code);
@@ -82,7 +82,7 @@ static void cfg80211_process_deauth(struct wireless_dev *wdev,
 static void cfg80211_process_disassoc(struct wireless_dev *wdev,
 				      const u8 *buf, size_t len)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	const u8 *bssid = mgmt->bssid;
 	u16 reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code);
@@ -123,7 +123,7 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_send_auth_timeout(dev, addr);
 
@@ -136,7 +136,7 @@ void cfg80211_assoc_timeout(struct net_device *dev, struct cfg80211_bss *bss)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_send_assoc_timeout(dev, bss->bssid);
 
@@ -172,7 +172,7 @@ void cfg80211_michael_mic_failure(struct net_device *dev, const u8 *addr,
 				  const u8 *tsc, gfp_t gfp)
 {
 	struct wiphy *wiphy = dev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 #ifdef CONFIG_CFG80211_WEXT
 	union iwreq_data wrqu;
 	char *buf = kmalloc(128, gfp);
@@ -233,14 +233,8 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev,
 	if (!req.bss)
 		return -ENOENT;
 
-	err = cfg80211_can_use_chan(rdev, wdev, req.bss->channel,
-				    CHAN_MODE_SHARED);
-	if (err)
-		goto out;
-
 	err = rdev_auth(rdev, dev, &req);
 
-out:
 	cfg80211_put_bss(&rdev->wiphy, req.bss);
 	return err;
 }
@@ -306,16 +300,10 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev,
 	if (!req->bss)
 		return -ENOENT;
 
-	err = cfg80211_can_use_chan(rdev, wdev, chan, CHAN_MODE_SHARED);
-	if (err)
-		goto out;
-
 	err = rdev_assoc(rdev, dev, req);
 	if (!err)
 		cfg80211_hold_bss(bss_from_pub(req->bss));
-
-out:
-	if (err)
+	else
 		cfg80211_put_bss(&rdev->wiphy, req->bss);
 
 	return err;
@@ -414,7 +402,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
 				int match_len)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_mgmt_registration *reg, *nreg;
 	int err = 0;
 	u16 mgmt_type;
@@ -473,7 +461,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
 void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_mgmt_registration *reg, *tmp;
 
 	spin_lock_bh(&wdev->mgmt_registrations_lock);
@@ -620,7 +608,7 @@ bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm,
 		      const u8 *buf, size_t len, u32 flags, gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_mgmt_registration *reg;
 	const struct ieee80211_txrx_stypes *stypes =
 		&wiphy->mgmt_stypes[wdev->iftype];
@@ -739,7 +727,7 @@ void cfg80211_radar_event(struct wiphy *wiphy,
 			  struct cfg80211_chan_def *chandef,
 			  gfp_t gfp)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	unsigned long timeout;
 
 	trace_cfg80211_radar_event(wiphy, chandef);
@@ -764,7 +752,7 @@ void cfg80211_cac_event(struct net_device *netdev,
 {
 	struct wireless_dev *wdev = netdev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	unsigned long timeout;
 
 	trace_cfg80211_cac_event(netdev, event);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 052c1bf8ffa..6668daf6932 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -168,8 +168,8 @@ __cfg80211_rdev_from_attrs(struct net *netns, struct nlattr **attrs)
 		netdev = __dev_get_by_index(netns, ifindex);
 		if (netdev) {
 			if (netdev->ieee80211_ptr)
-				tmp = wiphy_to_dev(
-						netdev->ieee80211_ptr->wiphy);
+				tmp = wiphy_to_rdev(
+					netdev->ieee80211_ptr->wiphy);
 			else
 				tmp = NULL;
 
@@ -371,8 +371,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 },
 	[NL80211_ATTR_CH_SWITCH_BLOCK_TX] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CSA_IES] = { .type = NLA_NESTED },
-	[NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_U16 },
-	[NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_U16 },
+	[NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_BINARY },
+	[NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_BINARY },
 	[NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY },
 	[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY },
 	[NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG },
@@ -385,6 +385,8 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
 	[NL80211_ATTR_MAC_HINT] = { .len = ETH_ALEN },
 	[NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 },
 	[NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 },
+	[NL80211_ATTR_IFACE_SOCKET_OWNER] = { .type = NLA_FLAG },
+	[NL80211_ATTR_CSA_C_OFFSETS_TX] = { .type = NLA_BINARY },
 };
 
 /* policy for the key attributes */
@@ -484,7 +486,7 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 			err = PTR_ERR(*wdev);
 			goto out_unlock;
 		}
-		*rdev = wiphy_to_dev((*wdev)->wiphy);
+		*rdev = wiphy_to_rdev((*wdev)->wiphy);
 		/* 0 is the first index - add 1 to parse only once */
 		cb->args[0] = (*rdev)->wiphy_idx + 1;
 		cb->args[1] = (*wdev)->identifier;
@@ -497,7 +499,7 @@ static int nl80211_prepare_wdev_dump(struct sk_buff *skb,
 			err = -ENODEV;
 			goto out_unlock;
 		}
-		*rdev = wiphy_to_dev(wiphy);
+		*rdev = wiphy_to_rdev(wiphy);
 		*wdev = NULL;
 
 		list_for_each_entry(tmp, &(*rdev)->wdev_list, list) {
@@ -566,6 +568,13 @@ static int nl80211_msg_put_channel(struct sk_buff *msg,
 				   struct ieee80211_channel *chan,
 				   bool large)
 {
+	/* Some channels must be completely excluded from the
+	 * list to protect old user-space tools from breaking
+	 */
+	if (!large && chan->flags &
+	    (IEEE80211_CHAN_NO_10MHZ | IEEE80211_CHAN_NO_20MHZ))
+		return 0;
+
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_FREQ,
 			chan->center_freq))
 		goto nla_put_failure;
@@ -613,6 +622,18 @@ static int nl80211_msg_put_channel(struct sk_buff *msg,
 		if ((chan->flags & IEEE80211_CHAN_NO_160MHZ) &&
 		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_160MHZ))
 			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_INDOOR_ONLY) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_INDOOR_ONLY))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_GO_CONCURRENT) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_GO_CONCURRENT))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_NO_20MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_20MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_NO_10MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_10MHZ))
+			goto nla_put_failure;
 	}
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
@@ -950,8 +971,10 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy,
 				c->max_interfaces))
 			goto nla_put_failure;
 		if (large &&
-		    nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS,
-				c->radar_detect_widths))
+		    (nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS,
+				c->radar_detect_widths) ||
+		     nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_REGIONS,
+				c->radar_detect_regions)))
 			goto nla_put_failure;
 
 		nla_nest_end(msg, nl_combi);
@@ -1006,42 +1029,42 @@ static int nl80211_send_wowlan_tcp_caps(struct cfg80211_registered_device *rdev,
 }
 
 static int nl80211_send_wowlan(struct sk_buff *msg,
-			       struct cfg80211_registered_device *dev,
+			       struct cfg80211_registered_device *rdev,
 			       bool large)
 {
 	struct nlattr *nl_wowlan;
 
-	if (!dev->wiphy.wowlan)
+	if (!rdev->wiphy.wowlan)
 		return 0;
 
 	nl_wowlan = nla_nest_start(msg, NL80211_ATTR_WOWLAN_TRIGGERS_SUPPORTED);
 	if (!nl_wowlan)
 		return -ENOBUFS;
 
-	if (((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_ANY) &&
+	if (((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_ANY) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_ANY)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_DISCONNECT) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_DISCONNECT) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_DISCONNECT)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_MAGIC_PKT) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_MAGIC_PKT) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_MAGIC_PKT)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_SUPPORTS_GTK_REKEY) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_SUPPORTS_GTK_REKEY) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_SUPPORTED)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_GTK_REKEY_FAILURE) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_GTK_REKEY_FAILURE)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_EAP_IDENTITY_REQ) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_EAP_IDENTITY_REQ) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_EAP_IDENT_REQUEST)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_4WAY_HANDSHAKE) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_4WAY_HANDSHAKE) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_4WAY_HANDSHAKE)) ||
-	    ((dev->wiphy.wowlan->flags & WIPHY_WOWLAN_RFKILL_RELEASE) &&
+	    ((rdev->wiphy.wowlan->flags & WIPHY_WOWLAN_RFKILL_RELEASE) &&
 	     nla_put_flag(msg, NL80211_WOWLAN_TRIG_RFKILL_RELEASE)))
 		return -ENOBUFS;
 
-	if (dev->wiphy.wowlan->n_patterns) {
+	if (rdev->wiphy.wowlan->n_patterns) {
 		struct nl80211_pattern_support pat = {
-			.max_patterns = dev->wiphy.wowlan->n_patterns,
-			.min_pattern_len = dev->wiphy.wowlan->pattern_min_len,
-			.max_pattern_len = dev->wiphy.wowlan->pattern_max_len,
-			.max_pkt_offset = dev->wiphy.wowlan->max_pkt_offset,
+			.max_patterns = rdev->wiphy.wowlan->n_patterns,
+			.min_pattern_len = rdev->wiphy.wowlan->pattern_min_len,
+			.max_pattern_len = rdev->wiphy.wowlan->pattern_max_len,
+			.max_pkt_offset = rdev->wiphy.wowlan->max_pkt_offset,
 		};
 
 		if (nla_put(msg, NL80211_WOWLAN_TRIG_PKT_PATTERN,
@@ -1049,7 +1072,7 @@ static int nl80211_send_wowlan(struct sk_buff *msg,
 			return -ENOBUFS;
 	}
 
-	if (large && nl80211_send_wowlan_tcp_caps(dev, msg))
+	if (large && nl80211_send_wowlan_tcp_caps(rdev, msg))
 		return -ENOBUFS;
 
 	nla_nest_end(msg, nl_wowlan);
@@ -1059,19 +1082,19 @@ static int nl80211_send_wowlan(struct sk_buff *msg,
 #endif
 
 static int nl80211_send_coalesce(struct sk_buff *msg,
-				 struct cfg80211_registered_device *dev)
+				 struct cfg80211_registered_device *rdev)
 {
 	struct nl80211_coalesce_rule_support rule;
 
-	if (!dev->wiphy.coalesce)
+	if (!rdev->wiphy.coalesce)
 		return 0;
 
-	rule.max_rules = dev->wiphy.coalesce->n_rules;
-	rule.max_delay = dev->wiphy.coalesce->max_delay;
-	rule.pat.max_patterns = dev->wiphy.coalesce->n_patterns;
-	rule.pat.min_pattern_len = dev->wiphy.coalesce->pattern_min_len;
-	rule.pat.max_pattern_len = dev->wiphy.coalesce->pattern_max_len;
-	rule.pat.max_pkt_offset = dev->wiphy.coalesce->max_pkt_offset;
+	rule.max_rules = rdev->wiphy.coalesce->n_rules;
+	rule.max_delay = rdev->wiphy.coalesce->max_delay;
+	rule.pat.max_patterns = rdev->wiphy.coalesce->n_patterns;
+	rule.pat.min_pattern_len = rdev->wiphy.coalesce->pattern_min_len;
+	rule.pat.max_pattern_len = rdev->wiphy.coalesce->pattern_max_len;
+	rule.pat.max_pkt_offset = rdev->wiphy.coalesce->max_pkt_offset;
 
 	if (nla_put(msg, NL80211_ATTR_COALESCE_RULE, sizeof(rule), &rule))
 		return -ENOBUFS;
@@ -1202,7 +1225,8 @@ struct nl80211_dump_wiphy_state {
 	bool split;
 };
 
-static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
+static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
+			      enum nl80211_commands cmd,
 			      struct sk_buff *msg, u32 portid, u32 seq,
 			      int flags, struct nl80211_dump_wiphy_state *state)
 {
@@ -1214,63 +1238,66 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 	struct ieee80211_channel *chan;
 	int i;
 	const struct ieee80211_txrx_stypes *mgmt_stypes =
-				dev->wiphy.mgmt_stypes;
+				rdev->wiphy.mgmt_stypes;
 	u32 features;
 
-	hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_WIPHY);
+	hdr = nl80211hdr_put(msg, portid, seq, flags, cmd);
 	if (!hdr)
 		return -ENOBUFS;
 
 	if (WARN_ON(!state))
 		return -EINVAL;
 
-	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, dev->wiphy_idx) ||
+	if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) ||
 	    nla_put_string(msg, NL80211_ATTR_WIPHY_NAME,
-			   wiphy_name(&dev->wiphy)) ||
+			   wiphy_name(&rdev->wiphy)) ||
 	    nla_put_u32(msg, NL80211_ATTR_GENERATION,
 			cfg80211_rdev_list_generation))
 		goto nla_put_failure;
 
+	if (cmd != NL80211_CMD_NEW_WIPHY)
+		goto finish;
+
 	switch (state->split_start) {
 	case 0:
 		if (nla_put_u8(msg, NL80211_ATTR_WIPHY_RETRY_SHORT,
-			       dev->wiphy.retry_short) ||
+			       rdev->wiphy.retry_short) ||
 		    nla_put_u8(msg, NL80211_ATTR_WIPHY_RETRY_LONG,
-			       dev->wiphy.retry_long) ||
+			       rdev->wiphy.retry_long) ||
 		    nla_put_u32(msg, NL80211_ATTR_WIPHY_FRAG_THRESHOLD,
-				dev->wiphy.frag_threshold) ||
+				rdev->wiphy.frag_threshold) ||
 		    nla_put_u32(msg, NL80211_ATTR_WIPHY_RTS_THRESHOLD,
-				dev->wiphy.rts_threshold) ||
+				rdev->wiphy.rts_threshold) ||
 		    nla_put_u8(msg, NL80211_ATTR_WIPHY_COVERAGE_CLASS,
-			       dev->wiphy.coverage_class) ||
+			       rdev->wiphy.coverage_class) ||
 		    nla_put_u8(msg, NL80211_ATTR_MAX_NUM_SCAN_SSIDS,
-			       dev->wiphy.max_scan_ssids) ||
+			       rdev->wiphy.max_scan_ssids) ||
 		    nla_put_u8(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_SSIDS,
-			       dev->wiphy.max_sched_scan_ssids) ||
+			       rdev->wiphy.max_sched_scan_ssids) ||
 		    nla_put_u16(msg, NL80211_ATTR_MAX_SCAN_IE_LEN,
-				dev->wiphy.max_scan_ie_len) ||
+				rdev->wiphy.max_scan_ie_len) ||
 		    nla_put_u16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN,
-				dev->wiphy.max_sched_scan_ie_len) ||
+				rdev->wiphy.max_sched_scan_ie_len) ||
 		    nla_put_u8(msg, NL80211_ATTR_MAX_MATCH_SETS,
-			       dev->wiphy.max_match_sets))
+			       rdev->wiphy.max_match_sets))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) &&
 		    nla_put_flag(msg, NL80211_ATTR_SUPPORT_IBSS_RSN))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_MESH_AUTH) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_MESH_AUTH) &&
 		    nla_put_flag(msg, NL80211_ATTR_SUPPORT_MESH_AUTH))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_AP_UAPSD) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_AP_UAPSD) &&
 		    nla_put_flag(msg, NL80211_ATTR_SUPPORT_AP_UAPSD))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_FW_ROAM) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_FW_ROAM) &&
 		    nla_put_flag(msg, NL80211_ATTR_ROAM_SUPPORT))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) &&
 		    nla_put_flag(msg, NL80211_ATTR_TDLS_SUPPORT))
 			goto nla_put_failure;
-		if ((dev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_TDLS_EXTERNAL_SETUP) &&
 		    nla_put_flag(msg, NL80211_ATTR_TDLS_EXTERNAL_SETUP))
 			goto nla_put_failure;
 		state->split_start++;
@@ -1278,35 +1305,35 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 			break;
 	case 1:
 		if (nla_put(msg, NL80211_ATTR_CIPHER_SUITES,
-			    sizeof(u32) * dev->wiphy.n_cipher_suites,
-			    dev->wiphy.cipher_suites))
+			    sizeof(u32) * rdev->wiphy.n_cipher_suites,
+			    rdev->wiphy.cipher_suites))
 			goto nla_put_failure;
 
 		if (nla_put_u8(msg, NL80211_ATTR_MAX_NUM_PMKIDS,
-			       dev->wiphy.max_num_pmkids))
+			       rdev->wiphy.max_num_pmkids))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_CONTROL_PORT_PROTOCOL) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_CONTROL_PORT_PROTOCOL) &&
 		    nla_put_flag(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE))
 			goto nla_put_failure;
 
 		if (nla_put_u32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_TX,
-				dev->wiphy.available_antennas_tx) ||
+				rdev->wiphy.available_antennas_tx) ||
 		    nla_put_u32(msg, NL80211_ATTR_WIPHY_ANTENNA_AVAIL_RX,
-				dev->wiphy.available_antennas_rx))
+				rdev->wiphy.available_antennas_rx))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD) &&
 		    nla_put_u32(msg, NL80211_ATTR_PROBE_RESP_OFFLOAD,
-				dev->wiphy.probe_resp_offload))
+				rdev->wiphy.probe_resp_offload))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.available_antennas_tx ||
-		     dev->wiphy.available_antennas_rx) &&
-		    dev->ops->get_antenna) {
+		if ((rdev->wiphy.available_antennas_tx ||
+		     rdev->wiphy.available_antennas_rx) &&
+		    rdev->ops->get_antenna) {
 			u32 tx_ant = 0, rx_ant = 0;
 			int res;
-			res = rdev_get_antenna(dev, &tx_ant, &rx_ant);
+			res = rdev_get_antenna(rdev, &tx_ant, &rx_ant);
 			if (!res) {
 				if (nla_put_u32(msg,
 						NL80211_ATTR_WIPHY_ANTENNA_TX,
@@ -1323,7 +1350,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 			break;
 	case 2:
 		if (nl80211_put_iftypes(msg, NL80211_ATTR_SUPPORTED_IFTYPES,
-					dev->wiphy.interface_modes))
+					rdev->wiphy.interface_modes))
 				goto nla_put_failure;
 		state->split_start++;
 		if (state->split)
@@ -1337,7 +1364,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		     band < IEEE80211_NUM_BANDS; band++) {
 			struct ieee80211_supported_band *sband;
 
-			sband = dev->wiphy.bands[band];
+			sband = rdev->wiphy.bands[band];
 
 			if (!sband)
 				continue;
@@ -1414,7 +1441,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		i = 0;
 #define CMD(op, n)							\
 		 do {							\
-			if (dev->ops->op) {				\
+			if (rdev->ops->op) {				\
 				i++;					\
 				if (nla_put_u32(msg, i, NL80211_CMD_ ## n)) \
 					goto nla_put_failure;		\
@@ -1438,59 +1465,58 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		CMD(set_pmksa, SET_PMKSA);
 		CMD(del_pmksa, DEL_PMKSA);
 		CMD(flush_pmksa, FLUSH_PMKSA);
-		if (dev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)
+		if (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL)
 			CMD(remain_on_channel, REMAIN_ON_CHANNEL);
 		CMD(set_bitrate_mask, SET_TX_BITRATE_MASK);
 		CMD(mgmt_tx, FRAME);
 		CMD(mgmt_tx_cancel_wait, FRAME_WAIT_CANCEL);
-		if (dev->wiphy.flags & WIPHY_FLAG_NETNS_OK) {
+		if (rdev->wiphy.flags & WIPHY_FLAG_NETNS_OK) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_SET_WIPHY_NETNS))
 				goto nla_put_failure;
 		}
-		if (dev->ops->set_monitor_channel || dev->ops->start_ap ||
-		    dev->ops->join_mesh) {
+		if (rdev->ops->set_monitor_channel || rdev->ops->start_ap ||
+		    rdev->ops->join_mesh) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL))
 				goto nla_put_failure;
 		}
 		CMD(set_wds_peer, SET_WDS_PEER);
-		if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) {
+		if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) {
 			CMD(tdls_mgmt, TDLS_MGMT);
 			CMD(tdls_oper, TDLS_OPER);
 		}
-		if (dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
+		if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN)
 			CMD(sched_scan_start, START_SCHED_SCAN);
 		CMD(probe_client, PROBE_CLIENT);
 		CMD(set_noack_map, SET_NOACK_MAP);
-		if (dev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS) {
+		if (rdev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_REGISTER_BEACONS))
 				goto nla_put_failure;
 		}
 		CMD(start_p2p_device, START_P2P_DEVICE);
 		CMD(set_mcast_rate, SET_MCAST_RATE);
+#ifdef CONFIG_NL80211_TESTMODE
+		CMD(testmode_cmd, TESTMODE);
+#endif
 		if (state->split) {
 			CMD(crit_proto_start, CRIT_PROTOCOL_START);
 			CMD(crit_proto_stop, CRIT_PROTOCOL_STOP);
-			if (dev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)
+			if (rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH)
 				CMD(channel_switch, CHANNEL_SWITCH);
+			CMD(set_qos_map, SET_QOS_MAP);
 		}
-		CMD(set_qos_map, SET_QOS_MAP);
-
-#ifdef CONFIG_NL80211_TESTMODE
-		CMD(testmode_cmd, TESTMODE);
-#endif
-
+		/* add into the if now */
 #undef CMD
 
-		if (dev->ops->connect || dev->ops->auth) {
+		if (rdev->ops->connect || rdev->ops->auth) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_CONNECT))
 				goto nla_put_failure;
 		}
 
-		if (dev->ops->disconnect || dev->ops->deauth) {
+		if (rdev->ops->disconnect || rdev->ops->deauth) {
 			i++;
 			if (nla_put_u32(msg, i, NL80211_CMD_DISCONNECT))
 				goto nla_put_failure;
@@ -1501,14 +1527,14 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		if (state->split)
 			break;
 	case 5:
-		if (dev->ops->remain_on_channel &&
-		    (dev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) &&
+		if (rdev->ops->remain_on_channel &&
+		    (rdev->wiphy.flags & WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL) &&
 		    nla_put_u32(msg,
 				NL80211_ATTR_MAX_REMAIN_ON_CHANNEL_DURATION,
-				dev->wiphy.max_remain_on_channel_duration))
+				rdev->wiphy.max_remain_on_channel_duration))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_OFFCHAN_TX) &&
 		    nla_put_flag(msg, NL80211_ATTR_OFFCHANNEL_TX_OK))
 			goto nla_put_failure;
 
@@ -1519,7 +1545,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 			break;
 	case 6:
 #ifdef CONFIG_PM
-		if (nl80211_send_wowlan(msg, dev, state->split))
+		if (nl80211_send_wowlan(msg, rdev, state->split))
 			goto nla_put_failure;
 		state->split_start++;
 		if (state->split)
@@ -1529,10 +1555,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 #endif
 	case 7:
 		if (nl80211_put_iftypes(msg, NL80211_ATTR_SOFTWARE_IFTYPES,
-					dev->wiphy.software_iftypes))
+					rdev->wiphy.software_iftypes))
 			goto nla_put_failure;
 
-		if (nl80211_put_iface_combinations(&dev->wiphy, msg,
+		if (nl80211_put_iface_combinations(&rdev->wiphy, msg,
 						   state->split))
 			goto nla_put_failure;
 
@@ -1540,12 +1566,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		if (state->split)
 			break;
 	case 8:
-		if ((dev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME) &&
 		    nla_put_u32(msg, NL80211_ATTR_DEVICE_AP_SME,
-				dev->wiphy.ap_sme_capa))
+				rdev->wiphy.ap_sme_capa))
 			goto nla_put_failure;
 
-		features = dev->wiphy.features;
+		features = rdev->wiphy.features;
 		/*
 		 * We can only add the per-channel limit information if the
 		 * dump is split, otherwise it makes it too big. Therefore
@@ -1556,16 +1582,16 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		if (nla_put_u32(msg, NL80211_ATTR_FEATURE_FLAGS, features))
 			goto nla_put_failure;
 
-		if (dev->wiphy.ht_capa_mod_mask &&
+		if (rdev->wiphy.ht_capa_mod_mask &&
 		    nla_put(msg, NL80211_ATTR_HT_CAPABILITY_MASK,
-			    sizeof(*dev->wiphy.ht_capa_mod_mask),
-			    dev->wiphy.ht_capa_mod_mask))
+			    sizeof(*rdev->wiphy.ht_capa_mod_mask),
+			    rdev->wiphy.ht_capa_mod_mask))
 			goto nla_put_failure;
 
-		if (dev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME &&
-		    dev->wiphy.max_acl_mac_addrs &&
+		if (rdev->wiphy.flags & WIPHY_FLAG_HAVE_AP_SME &&
+		    rdev->wiphy.max_acl_mac_addrs &&
 		    nla_put_u32(msg, NL80211_ATTR_MAC_ACL_MAX,
-				dev->wiphy.max_acl_mac_addrs))
+				rdev->wiphy.max_acl_mac_addrs))
 			goto nla_put_failure;
 
 		/*
@@ -1581,41 +1607,41 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 		state->split_start++;
 		break;
 	case 9:
-		if (dev->wiphy.extended_capabilities &&
+		if (rdev->wiphy.extended_capabilities &&
 		    (nla_put(msg, NL80211_ATTR_EXT_CAPA,
-			     dev->wiphy.extended_capabilities_len,
-			     dev->wiphy.extended_capabilities) ||
+			     rdev->wiphy.extended_capabilities_len,
+			     rdev->wiphy.extended_capabilities) ||
 		     nla_put(msg, NL80211_ATTR_EXT_CAPA_MASK,
-			     dev->wiphy.extended_capabilities_len,
-			     dev->wiphy.extended_capabilities_mask)))
+			     rdev->wiphy.extended_capabilities_len,
+			     rdev->wiphy.extended_capabilities_mask)))
 			goto nla_put_failure;
 
-		if (dev->wiphy.vht_capa_mod_mask &&
+		if (rdev->wiphy.vht_capa_mod_mask &&
 		    nla_put(msg, NL80211_ATTR_VHT_CAPABILITY_MASK,
-			    sizeof(*dev->wiphy.vht_capa_mod_mask),
-			    dev->wiphy.vht_capa_mod_mask))
+			    sizeof(*rdev->wiphy.vht_capa_mod_mask),
+			    rdev->wiphy.vht_capa_mod_mask))
 			goto nla_put_failure;
 
 		state->split_start++;
 		break;
 	case 10:
-		if (nl80211_send_coalesce(msg, dev))
+		if (nl80211_send_coalesce(msg, rdev))
 			goto nla_put_failure;
 
-		if ((dev->wiphy.flags & WIPHY_FLAG_SUPPORTS_5_10_MHZ) &&
+		if ((rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_5_10_MHZ) &&
 		    (nla_put_flag(msg, NL80211_ATTR_SUPPORT_5_MHZ) ||
 		     nla_put_flag(msg, NL80211_ATTR_SUPPORT_10_MHZ)))
 			goto nla_put_failure;
 
-		if (dev->wiphy.max_ap_assoc_sta &&
+		if (rdev->wiphy.max_ap_assoc_sta &&
 		    nla_put_u32(msg, NL80211_ATTR_MAX_AP_ASSOC_STA,
-				dev->wiphy.max_ap_assoc_sta))
+				rdev->wiphy.max_ap_assoc_sta))
 			goto nla_put_failure;
 
 		state->split_start++;
 		break;
 	case 11:
-		if (dev->wiphy.n_vendor_commands) {
+		if (rdev->wiphy.n_vendor_commands) {
 			const struct nl80211_vendor_cmd_info *info;
 			struct nlattr *nested;
 
@@ -1623,15 +1649,15 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 			if (!nested)
 				goto nla_put_failure;
 
-			for (i = 0; i < dev->wiphy.n_vendor_commands; i++) {
-				info = &dev->wiphy.vendor_commands[i].info;
+			for (i = 0; i < rdev->wiphy.n_vendor_commands; i++) {
+				info = &rdev->wiphy.vendor_commands[i].info;
 				if (nla_put(msg, i + 1, sizeof(*info), info))
 					goto nla_put_failure;
 			}
 			nla_nest_end(msg, nested);
 		}
 
-		if (dev->wiphy.n_vendor_events) {
+		if (rdev->wiphy.n_vendor_events) {
 			const struct nl80211_vendor_cmd_info *info;
 			struct nlattr *nested;
 
@@ -1640,18 +1666,26 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *dev,
 			if (!nested)
 				goto nla_put_failure;
 
-			for (i = 0; i < dev->wiphy.n_vendor_events; i++) {
-				info = &dev->wiphy.vendor_events[i];
+			for (i = 0; i < rdev->wiphy.n_vendor_events; i++) {
+				info = &rdev->wiphy.vendor_events[i];
 				if (nla_put(msg, i + 1, sizeof(*info), info))
 					goto nla_put_failure;
 			}
 			nla_nest_end(msg, nested);
 		}
+		state->split_start++;
+		break;
+	case 12:
+		if (rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH &&
+		    nla_put_u8(msg, NL80211_ATTR_MAX_CSA_COUNTERS,
+			       rdev->wiphy.max_num_csa_counters))
+			goto nla_put_failure;
 
 		/* done */
 		state->split_start = 0;
 		break;
 	}
+ finish:
 	return genlmsg_end(msg, hdr);
 
  nla_put_failure:
@@ -1684,7 +1718,7 @@ static int nl80211_dump_wiphy_parse(struct sk_buff *skb,
 		if (!netdev)
 			return -ENODEV;
 		if (netdev->ieee80211_ptr) {
-			rdev = wiphy_to_dev(
+			rdev = wiphy_to_rdev(
 				netdev->ieee80211_ptr->wiphy);
 			state->filter_wiphy = rdev->wiphy_idx;
 		}
@@ -1697,7 +1731,7 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	int idx = 0, ret;
 	struct nl80211_dump_wiphy_state *state = (void *)cb->args[0];
-	struct cfg80211_registered_device *dev;
+	struct cfg80211_registered_device *rdev;
 
 	rtnl_lock();
 	if (!state) {
@@ -1716,17 +1750,18 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb)
 		cb->args[0] = (long)state;
 	}
 
-	list_for_each_entry(dev, &cfg80211_rdev_list, list) {
-		if (!net_eq(wiphy_net(&dev->wiphy), sock_net(skb->sk)))
+	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
+		if (!net_eq(wiphy_net(&rdev->wiphy), sock_net(skb->sk)))
 			continue;
 		if (++idx <= state->start)
 			continue;
 		if (state->filter_wiphy != -1 &&
-		    state->filter_wiphy != dev->wiphy_idx)
+		    state->filter_wiphy != rdev->wiphy_idx)
 			continue;
 		/* attempt to fit multiple wiphy data chunks into the skb */
 		do {
-			ret = nl80211_send_wiphy(dev, skb,
+			ret = nl80211_send_wiphy(rdev, NL80211_CMD_NEW_WIPHY,
+						 skb,
 						 NETLINK_CB(cb->skb).portid,
 						 cb->nlh->nlmsg_seq,
 						 NLM_F_MULTI, state);
@@ -1774,14 +1809,15 @@ static int nl80211_dump_wiphy_done(struct netlink_callback *cb)
 static int nl80211_get_wiphy(struct sk_buff *skb, struct genl_info *info)
 {
 	struct sk_buff *msg;
-	struct cfg80211_registered_device *dev = info->user_ptr[0];
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct nl80211_dump_wiphy_state state = {};
 
 	msg = nlmsg_new(4096, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
 
-	if (nl80211_send_wiphy(dev, msg, info->snd_portid, info->snd_seq, 0,
+	if (nl80211_send_wiphy(rdev, NL80211_CMD_NEW_WIPHY, msg,
+			       info->snd_portid, info->snd_seq, 0,
 			       &state) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
@@ -1908,18 +1944,20 @@ static int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
 }
 
 static int __nl80211_set_channel(struct cfg80211_registered_device *rdev,
-				 struct wireless_dev *wdev,
+				 struct net_device *dev,
 				 struct genl_info *info)
 {
 	struct cfg80211_chan_def chandef;
 	int result;
 	enum nl80211_iftype iftype = NL80211_IFTYPE_MONITOR;
+	struct wireless_dev *wdev = NULL;
 
-	if (wdev)
-		iftype = wdev->iftype;
-
+	if (dev)
+		wdev = dev->ieee80211_ptr;
 	if (!nl80211_can_set_dev_channel(wdev))
 		return -EOPNOTSUPP;
+	if (wdev)
+		iftype = wdev->iftype;
 
 	result = nl80211_parse_chandef(rdev, info, &chandef);
 	if (result)
@@ -1928,14 +1966,27 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev,
 	switch (iftype) {
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
-		if (wdev->beacon_interval) {
-			result = -EBUSY;
-			break;
-		}
-		if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef)) {
+		if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef, iftype)) {
 			result = -EINVAL;
 			break;
 		}
+		if (wdev->beacon_interval) {
+			if (!dev || !rdev->ops->set_ap_chanwidth ||
+			    !(rdev->wiphy.features &
+			      NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE)) {
+				result = -EBUSY;
+				break;
+			}
+
+			/* Only allow dynamic channel width changes */
+			if (chandef.chan != wdev->preset_chandef.chan) {
+				result = -EBUSY;
+				break;
+			}
+			result = rdev_set_ap_chanwidth(rdev, dev, &chandef);
+			if (result)
+				break;
+		}
 		wdev->preset_chandef = chandef;
 		result = 0;
 		break;
@@ -1957,7 +2008,7 @@ static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *netdev = info->user_ptr[1];
 
-	return __nl80211_set_channel(rdev, netdev->ieee80211_ptr, info);
+	return __nl80211_set_channel(rdev, netdev, info);
 }
 
 static int nl80211_set_wds_peer(struct sk_buff *skb, struct genl_info *info)
@@ -2013,7 +2064,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 
 		netdev = __dev_get_by_index(genl_info_net(info), ifindex);
 		if (netdev && netdev->ieee80211_ptr)
-			rdev = wiphy_to_dev(netdev->ieee80211_ptr->wiphy);
+			rdev = wiphy_to_rdev(netdev->ieee80211_ptr->wiphy);
 		else
 			netdev = NULL;
 	}
@@ -2079,9 +2130,10 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) {
-		result = __nl80211_set_channel(rdev,
-				nl80211_can_set_dev_channel(wdev) ? wdev : NULL,
-				info);
+		result = __nl80211_set_channel(
+			rdev,
+			nl80211_can_set_dev_channel(wdev) ? netdev : NULL,
+			info);
 		if (result)
 			return result;
 	}
@@ -2229,7 +2281,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 static inline u64 wdev_id(struct wireless_dev *wdev)
 {
 	return (u64)wdev->identifier |
-	       ((u64)wiphy_to_dev(wdev->wiphy)->wiphy_idx << 32);
+	       ((u64)wiphy_to_rdev(wdev->wiphy)->wiphy_idx << 32);
 }
 
 static int nl80211_send_chandef(struct sk_buff *msg,
@@ -2355,7 +2407,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *
 static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info)
 {
 	struct sk_buff *msg;
-	struct cfg80211_registered_device *dev = info->user_ptr[0];
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct wireless_dev *wdev = info->user_ptr[1];
 
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
@@ -2363,7 +2415,7 @@ static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 
 	if (nl80211_send_iface(msg, info->snd_portid, info->snd_seq, 0,
-			       dev, wdev) < 0) {
+			       rdev, wdev) < 0) {
 		nlmsg_free(msg);
 		return -ENOBUFS;
 	}
@@ -2514,6 +2566,9 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 	enum nl80211_iftype type = NL80211_IFTYPE_UNSPECIFIED;
 	u32 flags;
 
+	/* to avoid failing a new interface creation due to pending removal */
+	cfg80211_destroy_ifaces(rdev);
+
 	memset(&params, 0, sizeof(params));
 
 	if (!info->attrs[NL80211_ATTR_IFNAME])
@@ -2563,6 +2618,9 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 		return PTR_ERR(wdev);
 	}
 
+	if (info->attrs[NL80211_ATTR_IFACE_SOCKET_OWNER])
+		wdev->owner_nlportid = info->snd_portid;
+
 	switch (type) {
 	case NL80211_IFTYPE_MESH_POINT:
 		if (!info->attrs[NL80211_ATTR_MESH_ID])
@@ -3142,7 +3200,6 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_ap_settings params;
 	int err;
-	u8 radar_detect_width = 0;
 
 	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP &&
 	    dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO)
@@ -3258,24 +3315,10 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	} else if (!nl80211_get_ap_channel(rdev, &params))
 		return -EINVAL;
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef,
+				     wdev->iftype))
 		return -EINVAL;
 
-	err = cfg80211_chandef_dfs_required(wdev->wiphy, &params.chandef);
-	if (err < 0)
-		return err;
-	if (err) {
-		radar_detect_width = BIT(params.chandef.width);
-		params.radar_required = true;
-	}
-
-	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
-					   params.chandef.chan,
-					   CHAN_MODE_SHARED,
-					   radar_detect_width);
-	if (err)
-		return err;
-
 	if (info->attrs[NL80211_ATTR_ACL_POLICY]) {
 		params.acl = parse_acl_data(&rdev->wiphy, info);
 		if (IS_ERR(params.acl))
@@ -3613,6 +3656,10 @@ static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq,
 	    nla_put_u32(msg, NL80211_STA_INFO_TX_FAILED,
 			sinfo->tx_failed))
 		goto nla_put_failure;
+	if ((sinfo->filled & STATION_INFO_EXPECTED_THROUGHPUT) &&
+	    nla_put_u32(msg, NL80211_STA_INFO_EXPECTED_THROUGHPUT,
+			sinfo->expected_throughput))
+		goto nla_put_failure;
 	if ((sinfo->filled & STATION_INFO_BEACON_LOSS_COUNT) &&
 	    nla_put_u32(msg, NL80211_STA_INFO_BEACON_LOSS,
 			sinfo->beacon_loss_count))
@@ -3675,13 +3722,13 @@ static int nl80211_dump_station(struct sk_buff *skb,
 				struct netlink_callback *cb)
 {
 	struct station_info sinfo;
-	struct cfg80211_registered_device *dev;
+	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
 	u8 mac_addr[ETH_ALEN];
 	int sta_idx = cb->args[2];
 	int err;
 
-	err = nl80211_prepare_wdev_dump(skb, cb, &dev, &wdev);
+	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
 		return err;
 
@@ -3690,14 +3737,14 @@ static int nl80211_dump_station(struct sk_buff *skb,
 		goto out_err;
 	}
 
-	if (!dev->ops->dump_station) {
+	if (!rdev->ops->dump_station) {
 		err = -EOPNOTSUPP;
 		goto out_err;
 	}
 
 	while (1) {
 		memset(&sinfo, 0, sizeof(sinfo));
-		err = rdev_dump_station(dev, wdev->netdev, sta_idx,
+		err = rdev_dump_station(rdev, wdev->netdev, sta_idx,
 					mac_addr, &sinfo);
 		if (err == -ENOENT)
 			break;
@@ -3707,7 +3754,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 		if (nl80211_send_station(skb,
 				NETLINK_CB(cb->skb).portid,
 				cb->nlh->nlmsg_seq, NLM_F_MULTI,
-				dev, wdev->netdev, mac_addr,
+				rdev, wdev->netdev, mac_addr,
 				&sinfo) < 0)
 			goto out;
 
@@ -3719,7 +3766,7 @@ static int nl80211_dump_station(struct sk_buff *skb,
 	cb->args[2] = sta_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(dev);
+	nl80211_finish_wdev_dump(rdev);
 
 	return err;
 }
@@ -4380,18 +4427,18 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 			      struct netlink_callback *cb)
 {
 	struct mpath_info pinfo;
-	struct cfg80211_registered_device *dev;
+	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
 	u8 dst[ETH_ALEN];
 	u8 next_hop[ETH_ALEN];
 	int path_idx = cb->args[2];
 	int err;
 
-	err = nl80211_prepare_wdev_dump(skb, cb, &dev, &wdev);
+	err = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (err)
 		return err;
 
-	if (!dev->ops->dump_mpath) {
+	if (!rdev->ops->dump_mpath) {
 		err = -EOPNOTSUPP;
 		goto out_err;
 	}
@@ -4402,7 +4449,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 	}
 
 	while (1) {
-		err = rdev_dump_mpath(dev, wdev->netdev, path_idx, dst,
+		err = rdev_dump_mpath(rdev, wdev->netdev, path_idx, dst,
 				      next_hop, &pinfo);
 		if (err == -ENOENT)
 			break;
@@ -4423,7 +4470,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb,
 	cb->args[2] = path_idx;
 	err = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(dev);
+	nl80211_finish_wdev_dump(rdev);
 	return err;
 }
 
@@ -4663,7 +4710,6 @@ static int parse_reg_rule(struct nlattr *tb[],
 
 static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 {
-	int r;
 	char *data = NULL;
 	enum nl80211_user_reg_hint_type user_reg_hint_type;
 
@@ -4676,11 +4722,6 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 	if (unlikely(!rcu_access_pointer(cfg80211_regdomain)))
 		return -EINPROGRESS;
 
-	if (!info->attrs[NL80211_ATTR_REG_ALPHA2])
-		return -EINVAL;
-
-	data = nla_data(info->attrs[NL80211_ATTR_REG_ALPHA2]);
-
 	if (info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE])
 		user_reg_hint_type =
 		  nla_get_u32(info->attrs[NL80211_ATTR_USER_REG_HINT_TYPE]);
@@ -4690,14 +4731,16 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info)
 	switch (user_reg_hint_type) {
 	case NL80211_USER_REG_HINT_USER:
 	case NL80211_USER_REG_HINT_CELL_BASE:
-		break;
+		if (!info->attrs[NL80211_ATTR_REG_ALPHA2])
+			return -EINVAL;
+
+		data = nla_data(info->attrs[NL80211_ATTR_REG_ALPHA2]);
+		return regulatory_hint_user(data, user_reg_hint_type);
+	case NL80211_USER_REG_HINT_INDOOR:
+		return regulatory_hint_indoor_user();
 	default:
 		return -EINVAL;
 	}
-
-	r = regulatory_hint_user(data, user_reg_hint_type);
-
-	return r;
 }
 
 static int nl80211_get_mesh_config(struct sk_buff *skb,
@@ -5796,7 +5839,8 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 	if (wdev->cac_started)
 		return -EBUSY;
 
-	err = cfg80211_chandef_dfs_required(wdev->wiphy, &chandef);
+	err = cfg80211_chandef_dfs_required(wdev->wiphy, &chandef,
+					    wdev->iftype);
 	if (err < 0)
 		return err;
 
@@ -5809,12 +5853,6 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 	if (!rdev->ops->start_radar_detection)
 		return -EOPNOTSUPP;
 
-	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
-					   chandef.chan, CHAN_MODE_SHARED,
-					   BIT(chandef.width));
-	if (err)
-		return err;
-
 	cac_time_ms = cfg80211_chandef_dfs_cac_time(&rdev->wiphy, &chandef);
 	if (WARN_ON(!cac_time_ms))
 		cac_time_ms = IEEE80211_DFS_MIN_CAC_TIME_MS;
@@ -5843,6 +5881,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 	u8 radar_detect_width = 0;
 	int err;
 	bool need_new_beacon = false;
+	int len, i;
 
 	if (!rdev->ops->channel_switch ||
 	    !(rdev->wiphy.flags & WIPHY_FLAG_HAS_CHANNEL_SWITCH))
@@ -5901,26 +5940,55 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 	if (!csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON])
 		return -EINVAL;
 
-	params.counter_offset_beacon =
-		nla_get_u16(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
-	if (params.counter_offset_beacon >= params.beacon_csa.tail_len)
+	len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
+	if (!len || (len % sizeof(u16)))
 		return -EINVAL;
 
-	/* sanity check - counters should be the same */
-	if (params.beacon_csa.tail[params.counter_offset_beacon] !=
-	    params.count)
+	params.n_counter_offsets_beacon = len / sizeof(u16);
+	if (rdev->wiphy.max_num_csa_counters &&
+	    (params.n_counter_offsets_beacon >
+	     rdev->wiphy.max_num_csa_counters))
 		return -EINVAL;
 
+	params.counter_offsets_beacon =
+		nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
+
+	/* sanity checks - counters should fit and be the same */
+	for (i = 0; i < params.n_counter_offsets_beacon; i++) {
+		u16 offset = params.counter_offsets_beacon[i];
+
+		if (offset >= params.beacon_csa.tail_len)
+			return -EINVAL;
+
+		if (params.beacon_csa.tail[offset] != params.count)
+			return -EINVAL;
+	}
+
 	if (csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]) {
-		params.counter_offset_presp =
-			nla_get_u16(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
-		if (params.counter_offset_presp >=
-		    params.beacon_csa.probe_resp_len)
+		len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
+		if (!len || (len % sizeof(u16)))
 			return -EINVAL;
 
-		if (params.beacon_csa.probe_resp[params.counter_offset_presp] !=
-		    params.count)
+		params.n_counter_offsets_presp = len / sizeof(u16);
+		if (rdev->wiphy.max_num_csa_counters &&
+		    (params.n_counter_offsets_beacon >
+		     rdev->wiphy.max_num_csa_counters))
 			return -EINVAL;
+
+		params.counter_offsets_presp =
+			nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
+
+		/* sanity checks - counters should fit and be the same */
+		for (i = 0; i < params.n_counter_offsets_presp; i++) {
+			u16 offset = params.counter_offsets_presp[i];
+
+			if (offset >= params.beacon_csa.probe_resp_len)
+				return -EINVAL;
+
+			if (params.beacon_csa.probe_resp[offset] !=
+			    params.count)
+				return -EINVAL;
+		}
 	}
 
 skip_beacons:
@@ -5928,27 +5996,25 @@ skip_beacons:
 	if (err)
 		return err;
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef,
+				     wdev->iftype))
 		return -EINVAL;
 
-	switch (dev->ieee80211_ptr->iftype) {
-	case NL80211_IFTYPE_AP:
-	case NL80211_IFTYPE_P2P_GO:
-	case NL80211_IFTYPE_ADHOC:
-	case NL80211_IFTYPE_MESH_POINT:
-		err = cfg80211_chandef_dfs_required(wdev->wiphy,
-						    &params.chandef);
-		if (err < 0)
-			return err;
-		if (err) {
-			radar_detect_width = BIT(params.chandef.width);
-			params.radar_required = true;
-		}
-		break;
-	default:
-		break;
+	err = cfg80211_chandef_dfs_required(wdev->wiphy,
+					    &params.chandef,
+					    wdev->iftype);
+	if (err < 0)
+		return err;
+
+	if (err > 0) {
+		radar_detect_width = BIT(params.chandef.width);
+		params.radar_required = true;
 	}
 
+	/* TODO: I left this here for now.  With channel switch, the
+	 * verification is a bit more complicated, because we only do
+	 * it later when the channel switch really happens.
+	 */
 	err = cfg80211_can_use_iftype_chan(rdev, wdev, wdev->iftype,
 					   params.chandef.chan,
 					   CHAN_MODE_SHARED,
@@ -6175,12 +6241,12 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 			struct netlink_callback *cb)
 {
 	struct survey_info survey;
-	struct cfg80211_registered_device *dev;
+	struct cfg80211_registered_device *rdev;
 	struct wireless_dev *wdev;
 	int survey_idx = cb->args[2];
 	int res;
 
-	res = nl80211_prepare_wdev_dump(skb, cb, &dev, &wdev);
+	res = nl80211_prepare_wdev_dump(skb, cb, &rdev, &wdev);
 	if (res)
 		return res;
 
@@ -6189,7 +6255,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 		goto out_err;
 	}
 
-	if (!dev->ops->dump_survey) {
+	if (!rdev->ops->dump_survey) {
 		res = -EOPNOTSUPP;
 		goto out_err;
 	}
@@ -6197,7 +6263,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 	while (1) {
 		struct ieee80211_channel *chan;
 
-		res = rdev_dump_survey(dev, wdev->netdev, survey_idx, &survey);
+		res = rdev_dump_survey(rdev, wdev->netdev, survey_idx, &survey);
 		if (res == -ENOENT)
 			break;
 		if (res)
@@ -6209,7 +6275,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 			goto out;
 		}
 
-		chan = ieee80211_get_channel(&dev->wiphy,
+		chan = ieee80211_get_channel(&rdev->wiphy,
 					     survey.channel->center_freq);
 		if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) {
 			survey_idx++;
@@ -6228,7 +6294,7 @@ static int nl80211_dump_survey(struct sk_buff *skb,
 	cb->args[2] = survey_idx;
 	res = skb->len;
  out_err:
-	nl80211_finish_wdev_dump(dev);
+	nl80211_finish_wdev_dump(rdev);
 	return res;
 }
 
@@ -6704,7 +6770,8 @@ static int nl80211_join_ibss(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &ibss.chandef))
+	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &ibss.chandef,
+				     NL80211_IFTYPE_ADHOC))
 		return -EINVAL;
 
 	switch (ibss.chandef.width) {
@@ -6879,7 +6946,7 @@ struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy,
 					   int vendor_event_idx,
 					   int approxlen, gfp_t gfp)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	const struct nl80211_vendor_cmd_info *info;
 
 	switch (cmd) {
@@ -7767,6 +7834,27 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 	if (!chandef.chan && params.offchan)
 		return -EINVAL;
 
+	params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]);
+	params.len = nla_len(info->attrs[NL80211_ATTR_FRAME]);
+
+	if (info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]) {
+		int len = nla_len(info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]);
+		int i;
+
+		if (len % sizeof(u16))
+			return -EINVAL;
+
+		params.n_csa_offsets = len / sizeof(u16);
+		params.csa_offsets =
+			nla_data(info->attrs[NL80211_ATTR_CSA_C_OFFSETS_TX]);
+
+		/* check that all the offsets fit the frame */
+		for (i = 0; i < params.n_csa_offsets; i++) {
+			if (params.csa_offsets[i] >= params.len)
+				return -EINVAL;
+		}
+	}
+
 	if (!params.dont_wait_for_ack) {
 		msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 		if (!msg)
@@ -7780,8 +7868,6 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	params.buf = nla_data(info->attrs[NL80211_ATTR_FRAME]);
-	params.len = nla_len(info->attrs[NL80211_ATTR_FRAME]);
 	params.chan = chandef.chan;
 	err = cfg80211_mlme_mgmt_tx(rdev, wdev, &params, &cookie);
 	if (err)
@@ -8478,6 +8564,8 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 
 		nla_for_each_nested(pat, tb[NL80211_WOWLAN_TRIG_PKT_PATTERN],
 				    rem) {
+			u8 *mask_pat;
+
 			nla_parse(pat_tb, MAX_NL80211_PKTPAT, nla_data(pat),
 				  nla_len(pat), NULL);
 			err = -EINVAL;
@@ -8501,19 +8589,18 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 				goto error;
 			new_triggers.patterns[i].pkt_offset = pkt_offset;
 
-			new_triggers.patterns[i].mask =
-				kmalloc(mask_len + pat_len, GFP_KERNEL);
-			if (!new_triggers.patterns[i].mask) {
+			mask_pat = kmalloc(mask_len + pat_len, GFP_KERNEL);
+			if (!mask_pat) {
 				err = -ENOMEM;
 				goto error;
 			}
-			new_triggers.patterns[i].pattern =
-				new_triggers.patterns[i].mask + mask_len;
-			memcpy(new_triggers.patterns[i].mask,
-			       nla_data(pat_tb[NL80211_PKTPAT_MASK]),
+			new_triggers.patterns[i].mask = mask_pat;
+			memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_MASK]),
 			       mask_len);
+			mask_pat += mask_len;
+			new_triggers.patterns[i].pattern = mask_pat;
 			new_triggers.patterns[i].pattern_len = pat_len;
-			memcpy(new_triggers.patterns[i].pattern,
+			memcpy(mask_pat,
 			       nla_data(pat_tb[NL80211_PKTPAT_PATTERN]),
 			       pat_len);
 			i++;
@@ -8705,6 +8792,8 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 
 	nla_for_each_nested(pat, tb[NL80211_ATTR_COALESCE_RULE_PKT_PATTERN],
 			    rem) {
+		u8 *mask_pat;
+
 		nla_parse(pat_tb, MAX_NL80211_PKTPAT, nla_data(pat),
 			  nla_len(pat), NULL);
 		if (!pat_tb[NL80211_PKTPAT_MASK] ||
@@ -8726,17 +8815,19 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 			return -EINVAL;
 		new_rule->patterns[i].pkt_offset = pkt_offset;
 
-		new_rule->patterns[i].mask =
-			kmalloc(mask_len + pat_len, GFP_KERNEL);
-		if (!new_rule->patterns[i].mask)
+		mask_pat = kmalloc(mask_len + pat_len, GFP_KERNEL);
+		if (!mask_pat)
 			return -ENOMEM;
-		new_rule->patterns[i].pattern =
-			new_rule->patterns[i].mask + mask_len;
-		memcpy(new_rule->patterns[i].mask,
-		       nla_data(pat_tb[NL80211_PKTPAT_MASK]), mask_len);
+
+		new_rule->patterns[i].mask = mask_pat;
+		memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_MASK]),
+		       mask_len);
+
+		mask_pat += mask_len;
+		new_rule->patterns[i].pattern = mask_pat;
 		new_rule->patterns[i].pattern_len = pat_len;
-		memcpy(new_rule->patterns[i].pattern,
-		       nla_data(pat_tb[NL80211_PKTPAT_PATTERN]), pat_len);
+		memcpy(mask_pat, nla_data(pat_tb[NL80211_PKTPAT_PATTERN]),
+		       pat_len);
 		i++;
 	}
 
@@ -8981,9 +9072,8 @@ static int nl80211_start_p2p_device(struct sk_buff *skb, struct genl_info *info)
 	if (wdev->p2p_started)
 		return 0;
 
-	err = cfg80211_can_add_interface(rdev, wdev->iftype);
-	if (err)
-		return err;
+	if (rfkill_blocked(rdev->rfkill))
+		return -ERFKILL;
 
 	err = rdev_start_p2p_device(rdev, wdev);
 	if (err)
@@ -9192,7 +9282,7 @@ struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy,
 					   enum nl80211_attrs attr,
 					   int approxlen)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	if (WARN_ON(!rdev->cur_cmd_info))
 		return NULL;
@@ -9316,7 +9406,7 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
 		}
 
 		dev = wdev->netdev;
-		rdev = wiphy_to_dev(wdev->wiphy);
+		rdev = wiphy_to_rdev(wdev->wiphy);
 
 		if (ops->internal_flags & NL80211_FLAG_NEED_NETDEV) {
 			if (!dev) {
@@ -10017,16 +10107,20 @@ static const struct genl_ops nl80211_ops[] = {
 
 /* notification functions */
 
-void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev)
+void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev,
+			  enum nl80211_commands cmd)
 {
 	struct sk_buff *msg;
 	struct nl80211_dump_wiphy_state state = {};
 
+	WARN_ON(cmd != NL80211_CMD_NEW_WIPHY &&
+		cmd != NL80211_CMD_DEL_WIPHY);
+
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return;
 
-	if (nl80211_send_wiphy(rdev, msg, 0, 0, 0, &state) < 0) {
+	if (nl80211_send_wiphy(rdev, cmd, msg, 0, 0, 0, &state) < 0) {
 		nlmsg_free(msg);
 		return;
 	}
@@ -10345,7 +10439,7 @@ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	const struct ieee80211_mgmt *mgmt = (void *)buf;
 	u32 cmd;
 
@@ -10567,7 +10661,7 @@ void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *addr,
 					const u8* ie, u8 ie_len, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -10747,7 +10841,7 @@ void cfg80211_ready_on_channel(struct wireless_dev *wdev, u64 cookie,
 			       unsigned int duration, gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_ready_on_channel(wdev, cookie, chan, duration);
 	nl80211_send_remain_on_chan_event(NL80211_CMD_REMAIN_ON_CHANNEL,
@@ -10761,7 +10855,7 @@ void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie,
 					gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_ready_on_channel_expired(wdev, cookie, chan);
 	nl80211_send_remain_on_chan_event(NL80211_CMD_CANCEL_REMAIN_ON_CHANNEL,
@@ -10773,7 +10867,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr,
 		      struct station_info *sinfo, gfp_t gfp)
 {
 	struct wiphy *wiphy = dev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 
 	trace_cfg80211_new_sta(dev, mac_addr, sinfo);
@@ -10796,7 +10890,7 @@ EXPORT_SYMBOL(cfg80211_new_sta);
 void cfg80211_del_sta(struct net_device *dev, const u8 *mac_addr, gfp_t gfp)
 {
 	struct wiphy *wiphy = dev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -10833,7 +10927,7 @@ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr,
 			  gfp_t gfp)
 {
 	struct wiphy *wiphy = dev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -10868,7 +10962,7 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd,
 				       const u8 *addr, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 	u32 nlportid = ACCESS_ONCE(wdev->ap_unexpected_nlportid);
@@ -10988,7 +11082,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 			     const u8 *buf, size_t len, bool ack, gfp_t gfp)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct net_device *netdev = wdev->netdev;
 	struct sk_buff *msg;
 	void *hdr;
@@ -11032,7 +11126,7 @@ void cfg80211_cqm_rssi_notify(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	struct nlattr *pinfoattr;
 	void *hdr;
@@ -11124,7 +11218,7 @@ void cfg80211_gtk_rekey_notify(struct net_device *dev, const u8 *bssid,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_gtk_rekey_notify(dev, bssid);
 	nl80211_gtk_rekey_notify(rdev, dev, bssid, replay_ctr, gfp);
@@ -11182,7 +11276,7 @@ void cfg80211_pmksa_candidate_notify(struct net_device *dev, int index,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	trace_cfg80211_pmksa_candidate_notify(dev, index, bssid, preauth);
 	nl80211_pmksa_candidate_notify(rdev, dev, index, bssid, preauth, gfp);
@@ -11229,7 +11323,7 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	ASSERT_WDEV_LOCK(wdev);
 
@@ -11253,7 +11347,7 @@ void cfg80211_cqm_txe_notify(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	struct nlattr *pinfoattr;
 	void *hdr;
@@ -11353,7 +11447,7 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	struct nlattr *pinfoattr;
 	void *hdr;
@@ -11400,7 +11494,7 @@ void cfg80211_probe_status(struct net_device *dev, const u8 *addr,
 			   u64 cookie, bool acked, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -11440,7 +11534,7 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy,
 				 const u8 *frame, size_t len,
 				 int freq, int sig_dbm)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 	struct cfg80211_beacon_registration *reg;
@@ -11487,7 +11581,7 @@ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev,
 				   struct cfg80211_wowlan_wakeup *wakeup,
 				   gfp_t gfp)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 	int size = 200;
@@ -11597,7 +11691,7 @@ void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer,
 				u16 reason_code, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -11649,9 +11743,15 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) {
-		list_for_each_entry_rcu(wdev, &rdev->wdev_list, list)
+		bool schedule_destroy_work = false;
+
+		list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) {
 			cfg80211_mlme_unregister_socket(wdev, notify->portid);
 
+			if (wdev->owner_nlportid == notify->portid)
+				schedule_destroy_work = true;
+		}
+
 		spin_lock_bh(&rdev->beacon_registrations_lock);
 		list_for_each_entry_safe(reg, tmp, &rdev->beacon_registrations,
 					 list) {
@@ -11662,11 +11762,24 @@ static int nl80211_netlink_notify(struct notifier_block * nb,
 			}
 		}
 		spin_unlock_bh(&rdev->beacon_registrations_lock);
+
+		if (schedule_destroy_work) {
+			struct cfg80211_iface_destroy *destroy;
+
+			destroy = kzalloc(sizeof(*destroy), GFP_ATOMIC);
+			if (destroy) {
+				destroy->nlportid = notify->portid;
+				spin_lock(&rdev->destroy_list_lock);
+				list_add(&destroy->list, &rdev->destroy_list);
+				spin_unlock(&rdev->destroy_list_lock);
+				schedule_work(&rdev->destroy_work);
+			}
+		}
 	}
 
 	rcu_read_unlock();
 
-	return NOTIFY_DONE;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block nl80211_netlink_notifier = {
@@ -11677,7 +11790,7 @@ void cfg80211_ft_event(struct net_device *netdev,
 		       struct cfg80211_ft_event_params *ft_event)
 {
 	struct wiphy *wiphy = netdev->ieee80211_ptr->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
@@ -11724,7 +11837,7 @@ void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp)
 	void *hdr;
 	u32 nlportid;
 
-	rdev = wiphy_to_dev(wdev->wiphy);
+	rdev = wiphy_to_rdev(wdev->wiphy);
 	if (!rdev->crit_proto_nlportid)
 		return;
 
@@ -11759,7 +11872,7 @@ EXPORT_SYMBOL(cfg80211_crit_proto_stopped);
 void nl80211_send_ap_stopped(struct wireless_dev *wdev)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct sk_buff *msg;
 	void *hdr;
 
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index 1e6df9630f4..49c9a482dd1 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -5,7 +5,8 @@
 
 int nl80211_init(void);
 void nl80211_exit(void);
-void nl80211_notify_dev_rename(struct cfg80211_registered_device *rdev);
+void nl80211_notify_wiphy(struct cfg80211_registered_device *rdev,
+			  enum nl80211_commands cmd);
 void nl80211_send_scan_start(struct cfg80211_registered_device *rdev,
 			     struct wireless_dev *wdev);
 struct sk_buff *nl80211_build_scan_msg(struct cfg80211_registered_device *rdev,
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 74d97d33c93..d95bbe34813 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -199,7 +199,7 @@ static inline int rdev_change_station(struct cfg80211_registered_device *rdev,
 }
 
 static inline int rdev_get_station(struct cfg80211_registered_device *rdev,
-				   struct net_device *dev, u8 *mac,
+				   struct net_device *dev, const u8 *mac,
 				   struct station_info *sinfo)
 {
 	int ret;
@@ -950,4 +950,17 @@ static inline int rdev_set_qos_map(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int
+rdev_set_ap_chanwidth(struct cfg80211_registered_device *rdev,
+		      struct net_device *dev, struct cfg80211_chan_def *chandef)
+{
+	int ret;
+
+	trace_rdev_set_ap_chanwidth(&rdev->wiphy, dev, chandef);
+	ret = rdev->ops->set_ap_chanwidth(&rdev->wiphy, dev, chandef);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+
+	return ret;
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index f59aaac586f..1afdf45db38 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -65,11 +65,26 @@
 #define REG_DBG_PRINT(args...)
 #endif
 
+/**
+ * enum reg_request_treatment - regulatory request treatment
+ *
+ * @REG_REQ_OK: continue processing the regulatory request
+ * @REG_REQ_IGNORE: ignore the regulatory request
+ * @REG_REQ_INTERSECT: the regulatory domain resulting from this request should
+ *	be intersected with the current one.
+ * @REG_REQ_ALREADY_SET: the regulatory request will not change the current
+ *	regulatory settings, and no further processing is required.
+ * @REG_REQ_USER_HINT_HANDLED: a non alpha2  user hint was handled and no
+ *	further processing is required, i.e., not need to update last_request
+ *	etc. This should be used for user hints that do not provide an alpha2
+ *	but some other type of regulatory hint, i.e., indoor operation.
+ */
 enum reg_request_treatment {
 	REG_REQ_OK,
 	REG_REQ_IGNORE,
 	REG_REQ_INTERSECT,
 	REG_REQ_ALREADY_SET,
+	REG_REQ_USER_HINT_HANDLED,
 };
 
 static struct regulatory_request core_request_world = {
@@ -106,6 +121,14 @@ const struct ieee80211_regdomain __rcu *cfg80211_regdomain;
  */
 static int reg_num_devs_support_basehint;
 
+/*
+ * State variable indicating if the platform on which the devices
+ * are attached is operating in an indoor environment. The state variable
+ * is relevant for all registered devices.
+ * (protected by RTNL)
+ */
+static bool reg_is_indoor;
+
 static const struct ieee80211_regdomain *get_cfg80211_regdom(void)
 {
 	return rtnl_dereference(cfg80211_regdomain);
@@ -240,8 +263,16 @@ static char user_alpha2[2];
 module_param(ieee80211_regdom, charp, 0444);
 MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code");
 
-static void reg_free_request(struct regulatory_request *lr)
+static void reg_free_request(struct regulatory_request *request)
 {
+	if (request != get_last_request())
+		kfree(request);
+}
+
+static void reg_free_last_request(void)
+{
+	struct regulatory_request *lr = get_last_request();
+
 	if (lr != &core_request_world && lr)
 		kfree_rcu(lr, rcu_head);
 }
@@ -254,7 +285,7 @@ static void reg_update_last_request(struct regulatory_request *request)
 	if (lr == request)
 		return;
 
-	reg_free_request(lr);
+	reg_free_last_request();
 	rcu_assign_pointer(last_request, request);
 }
 
@@ -873,6 +904,8 @@ static u32 map_regdom_flags(u32 rd_flags)
 		channel_flags |= IEEE80211_CHAN_RADAR;
 	if (rd_flags & NL80211_RRF_NO_OFDM)
 		channel_flags |= IEEE80211_CHAN_NO_OFDM;
+	if (rd_flags & NL80211_RRF_NO_OUTDOOR)
+		channel_flags |= IEEE80211_CHAN_INDOOR_ONLY;
 	return channel_flags;
 }
 
@@ -1071,6 +1104,13 @@ static void handle_channel(struct wiphy *wiphy,
 			(int) MBI_TO_DBI(power_rule->max_antenna_gain);
 		chan->max_reg_power = chan->max_power = chan->orig_mpwr =
 			(int) MBM_TO_DBM(power_rule->max_eirp);
+
+		if (chan->flags & IEEE80211_CHAN_RADAR) {
+			chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS;
+			if (reg_rule->dfs_cac_ms)
+				chan->dfs_cac_ms = reg_rule->dfs_cac_ms;
+		}
+
 		return;
 	}
 
@@ -1126,12 +1166,19 @@ static bool reg_request_cell_base(struct regulatory_request *request)
 	return request->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE;
 }
 
+static bool reg_request_indoor(struct regulatory_request *request)
+{
+	if (request->initiator != NL80211_REGDOM_SET_BY_USER)
+		return false;
+	return request->user_reg_hint_type == NL80211_USER_REG_HINT_INDOOR;
+}
+
 bool reg_last_request_cell_base(void)
 {
 	return reg_request_cell_base(get_last_request());
 }
 
-#ifdef CONFIG_CFG80211_CERTIFICATION_ONUS
+#ifdef CONFIG_CFG80211_REG_CELLULAR_HINTS
 /* Core specific check */
 static enum reg_request_treatment
 reg_ignore_cell_hint(struct regulatory_request *pending_request)
@@ -1568,6 +1615,11 @@ __reg_process_hint_user(struct regulatory_request *user_request)
 {
 	struct regulatory_request *lr = get_last_request();
 
+	if (reg_request_indoor(user_request)) {
+		reg_is_indoor = true;
+		return REG_REQ_USER_HINT_HANDLED;
+	}
+
 	if (reg_request_cell_base(user_request))
 		return reg_ignore_cell_hint(user_request);
 
@@ -1615,8 +1667,9 @@ reg_process_hint_user(struct regulatory_request *user_request)
 
 	treatment = __reg_process_hint_user(user_request);
 	if (treatment == REG_REQ_IGNORE ||
-	    treatment == REG_REQ_ALREADY_SET) {
-		kfree(user_request);
+	    treatment == REG_REQ_ALREADY_SET ||
+	    treatment == REG_REQ_USER_HINT_HANDLED) {
+		reg_free_request(user_request);
 		return treatment;
 	}
 
@@ -1676,14 +1729,15 @@ reg_process_hint_driver(struct wiphy *wiphy,
 	case REG_REQ_OK:
 		break;
 	case REG_REQ_IGNORE:
-		kfree(driver_request);
+	case REG_REQ_USER_HINT_HANDLED:
+		reg_free_request(driver_request);
 		return treatment;
 	case REG_REQ_INTERSECT:
 		/* fall through */
 	case REG_REQ_ALREADY_SET:
 		regd = reg_copy_regd(get_cfg80211_regdom());
 		if (IS_ERR(regd)) {
-			kfree(driver_request);
+			reg_free_request(driver_request);
 			return REG_REQ_IGNORE;
 		}
 		rcu_assign_pointer(wiphy->regd, regd);
@@ -1775,12 +1829,13 @@ reg_process_hint_country_ie(struct wiphy *wiphy,
 	case REG_REQ_OK:
 		break;
 	case REG_REQ_IGNORE:
+	case REG_REQ_USER_HINT_HANDLED:
 		/* fall through */
 	case REG_REQ_ALREADY_SET:
-		kfree(country_ie_request);
+		reg_free_request(country_ie_request);
 		return treatment;
 	case REG_REQ_INTERSECT:
-		kfree(country_ie_request);
+		reg_free_request(country_ie_request);
 		/*
 		 * This doesn't happen yet, not sure we
 		 * ever want to support it for this case.
@@ -1813,7 +1868,8 @@ static void reg_process_hint(struct regulatory_request *reg_request)
 	case NL80211_REGDOM_SET_BY_USER:
 		treatment = reg_process_hint_user(reg_request);
 		if (treatment == REG_REQ_IGNORE ||
-		    treatment == REG_REQ_ALREADY_SET)
+		    treatment == REG_REQ_ALREADY_SET ||
+		    treatment == REG_REQ_USER_HINT_HANDLED)
 			return;
 		queue_delayed_work(system_power_efficient_wq,
 				   &reg_timeout, msecs_to_jiffies(3142));
@@ -1841,7 +1897,7 @@ static void reg_process_hint(struct regulatory_request *reg_request)
 	return;
 
 out_free:
-	kfree(reg_request);
+	reg_free_request(reg_request);
 }
 
 /*
@@ -1857,7 +1913,7 @@ static void reg_process_pending_hints(void)
 
 	/* When last_request->processed becomes true this will be rescheduled */
 	if (lr && !lr->processed) {
-		REG_DBG_PRINT("Pending regulatory request, waiting for it to be processed...\n");
+		reg_process_hint(lr);
 		return;
 	}
 
@@ -1967,6 +2023,22 @@ int regulatory_hint_user(const char *alpha2,
 	return 0;
 }
 
+int regulatory_hint_indoor_user(void)
+{
+	struct regulatory_request *request;
+
+	request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL);
+	if (!request)
+		return -ENOMEM;
+
+	request->wiphy_idx = WIPHY_IDX_INVALID;
+	request->initiator = NL80211_REGDOM_SET_BY_USER;
+	request->user_reg_hint_type = NL80211_USER_REG_HINT_INDOOR;
+	queue_regulatory_request(request);
+
+	return 0;
+}
+
 /* Driver hints */
 int regulatory_hint(struct wiphy *wiphy, const char *alpha2)
 {
@@ -2134,6 +2206,8 @@ static void restore_regulatory_settings(bool reset_user)
 
 	ASSERT_RTNL();
 
+	reg_is_indoor = false;
+
 	reset_regdomains(true, &world_regdom);
 	restore_alpha2(alpha2, reset_user);
 
@@ -2594,7 +2668,7 @@ void wiphy_regulatory_deregister(struct wiphy *wiphy)
 		reg_num_devs_support_basehint--;
 
 	rcu_free_regdom(get_wiphy_regdom(wiphy));
-	rcu_assign_pointer(wiphy->regd, NULL);
+	RCU_INIT_POINTER(wiphy->regd, NULL);
 
 	if (lr)
 		request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx);
@@ -2614,6 +2688,40 @@ static void reg_timeout_work(struct work_struct *work)
 	rtnl_unlock();
 }
 
+/*
+ * See http://www.fcc.gov/document/5-ghz-unlicensed-spectrum-unii, for
+ * UNII band definitions
+ */
+int cfg80211_get_unii(int freq)
+{
+	/* UNII-1 */
+	if (freq >= 5150 && freq <= 5250)
+		return 0;
+
+	/* UNII-2A */
+	if (freq > 5250 && freq <= 5350)
+		return 1;
+
+	/* UNII-2B */
+	if (freq > 5350 && freq <= 5470)
+		return 2;
+
+	/* UNII-2C */
+	if (freq > 5470 && freq <= 5725)
+		return 3;
+
+	/* UNII-3 */
+	if (freq > 5725 && freq <= 5825)
+		return 4;
+
+	return -EINVAL;
+}
+
+bool regulatory_indoor_allowed(void)
+{
+	return reg_is_indoor;
+}
+
 int __init regulatory_init(void)
 {
 	int err = 0;
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index 37c180df34b..5e48031ccb9 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -25,6 +25,7 @@ enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy);
 
 int regulatory_hint_user(const char *alpha2,
 			 enum nl80211_user_reg_hint_type user_reg_hint_type);
+int regulatory_hint_indoor_user(void);
 
 void wiphy_regulatory_register(struct wiphy *wiphy);
 void wiphy_regulatory_deregister(struct wiphy *wiphy);
@@ -104,4 +105,21 @@ void regulatory_hint_country_ie(struct wiphy *wiphy,
  */
 void regulatory_hint_disconnect(void);
 
+/**
+ * cfg80211_get_unii - get the U-NII band for the frequency
+ * @freq: the frequency for which we want to get the UNII band.
+
+ * Get a value specifying the U-NII band frequency belongs to.
+ * U-NII bands are defined by the FCC in C.F.R 47 part 15.
+ *
+ * Returns -EINVAL if freq is invalid, 0 for UNII-1, 1 for UNII-2A,
+ * 2 for UNII-2B, 3 for UNII-2C and 4 for UNII-3.
+ */
+int cfg80211_get_unii(int freq);
+
+/**
+ * regulatory_indoor_allowed - is indoor operation allowed
+ */
+bool regulatory_indoor_allowed(void);
+
 #endif  /* __NET_WIRELESS_REG_H */
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 88f108edfb5..0798c62e608 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -81,10 +81,10 @@ static void bss_free(struct cfg80211_internal_bss *bss)
 	kfree(bss);
 }
 
-static inline void bss_ref_get(struct cfg80211_registered_device *dev,
+static inline void bss_ref_get(struct cfg80211_registered_device *rdev,
 			       struct cfg80211_internal_bss *bss)
 {
-	lockdep_assert_held(&dev->bss_lock);
+	lockdep_assert_held(&rdev->bss_lock);
 
 	bss->refcount++;
 	if (bss->pub.hidden_beacon_bss) {
@@ -95,10 +95,10 @@ static inline void bss_ref_get(struct cfg80211_registered_device *dev,
 	}
 }
 
-static inline void bss_ref_put(struct cfg80211_registered_device *dev,
+static inline void bss_ref_put(struct cfg80211_registered_device *rdev,
 			       struct cfg80211_internal_bss *bss)
 {
-	lockdep_assert_held(&dev->bss_lock);
+	lockdep_assert_held(&rdev->bss_lock);
 
 	if (bss->pub.hidden_beacon_bss) {
 		struct cfg80211_internal_bss *hbss;
@@ -114,10 +114,10 @@ static inline void bss_ref_put(struct cfg80211_registered_device *dev,
 		bss_free(bss);
 }
 
-static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *dev,
+static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *rdev,
 				  struct cfg80211_internal_bss *bss)
 {
-	lockdep_assert_held(&dev->bss_lock);
+	lockdep_assert_held(&rdev->bss_lock);
 
 	if (!list_empty(&bss->hidden_list)) {
 		/*
@@ -134,31 +134,31 @@ static bool __cfg80211_unlink_bss(struct cfg80211_registered_device *dev,
 	}
 
 	list_del_init(&bss->list);
-	rb_erase(&bss->rbn, &dev->bss_tree);
-	bss_ref_put(dev, bss);
+	rb_erase(&bss->rbn, &rdev->bss_tree);
+	bss_ref_put(rdev, bss);
 	return true;
 }
 
-static void __cfg80211_bss_expire(struct cfg80211_registered_device *dev,
+static void __cfg80211_bss_expire(struct cfg80211_registered_device *rdev,
 				  unsigned long expire_time)
 {
 	struct cfg80211_internal_bss *bss, *tmp;
 	bool expired = false;
 
-	lockdep_assert_held(&dev->bss_lock);
+	lockdep_assert_held(&rdev->bss_lock);
 
-	list_for_each_entry_safe(bss, tmp, &dev->bss_list, list) {
+	list_for_each_entry_safe(bss, tmp, &rdev->bss_list, list) {
 		if (atomic_read(&bss->hold))
 			continue;
 		if (!time_after(expire_time, bss->ts))
 			continue;
 
-		if (__cfg80211_unlink_bss(dev, bss))
+		if (__cfg80211_unlink_bss(rdev, bss))
 			expired = true;
 	}
 
 	if (expired)
-		dev->bss_generation++;
+		rdev->bss_generation++;
 }
 
 void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
@@ -238,11 +238,11 @@ void __cfg80211_scan_done(struct work_struct *wk)
 void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted)
 {
 	trace_cfg80211_scan_done(request, aborted);
-	WARN_ON(request != wiphy_to_dev(request->wiphy)->scan_req);
+	WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req);
 
 	request->aborted = aborted;
 	request->notified = true;
-	queue_work(cfg80211_wq, &wiphy_to_dev(request->wiphy)->scan_done_wk);
+	queue_work(cfg80211_wq, &wiphy_to_rdev(request->wiphy)->scan_done_wk);
 }
 EXPORT_SYMBOL(cfg80211_scan_done);
 
@@ -278,15 +278,15 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy)
 {
 	trace_cfg80211_sched_scan_results(wiphy);
 	/* ignore if we're not scanning */
-	if (wiphy_to_dev(wiphy)->sched_scan_req)
+	if (wiphy_to_rdev(wiphy)->sched_scan_req)
 		queue_work(cfg80211_wq,
-			   &wiphy_to_dev(wiphy)->sched_scan_results_wk);
+			   &wiphy_to_rdev(wiphy)->sched_scan_results_wk);
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_results);
 
 void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 
 	ASSERT_RTNL();
 
@@ -330,21 +330,21 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev,
 	return 0;
 }
 
-void cfg80211_bss_age(struct cfg80211_registered_device *dev,
+void cfg80211_bss_age(struct cfg80211_registered_device *rdev,
                       unsigned long age_secs)
 {
 	struct cfg80211_internal_bss *bss;
 	unsigned long age_jiffies = msecs_to_jiffies(age_secs * MSEC_PER_SEC);
 
-	spin_lock_bh(&dev->bss_lock);
-	list_for_each_entry(bss, &dev->bss_list, list)
+	spin_lock_bh(&rdev->bss_lock);
+	list_for_each_entry(bss, &rdev->bss_list, list)
 		bss->ts -= age_jiffies;
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 }
 
-void cfg80211_bss_expire(struct cfg80211_registered_device *dev)
+void cfg80211_bss_expire(struct cfg80211_registered_device *rdev)
 {
-	__cfg80211_bss_expire(dev, jiffies - IEEE80211_SCAN_RESULT_EXPIRE);
+	__cfg80211_bss_expire(rdev, jiffies - IEEE80211_SCAN_RESULT_EXPIRE);
 }
 
 const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len)
@@ -534,32 +534,34 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 				      const u8 *ssid, size_t ssid_len,
 				      u16 capa_mask, u16 capa_val)
 {
-	struct cfg80211_registered_device *dev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss, *res = NULL;
 	unsigned long now = jiffies;
 
 	trace_cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, capa_mask,
 			       capa_val);
 
-	spin_lock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
 
-	list_for_each_entry(bss, &dev->bss_list, list) {
+	list_for_each_entry(bss, &rdev->bss_list, list) {
 		if ((bss->pub.capability & capa_mask) != capa_val)
 			continue;
 		if (channel && bss->pub.channel != channel)
 			continue;
+		if (!is_valid_ether_addr(bss->pub.bssid))
+			continue;
 		/* Don't get expired BSS structs */
 		if (time_after(now, bss->ts + IEEE80211_SCAN_RESULT_EXPIRE) &&
 		    !atomic_read(&bss->hold))
 			continue;
 		if (is_bss(&bss->pub, bssid, ssid, ssid_len)) {
 			res = bss;
-			bss_ref_get(dev, res);
+			bss_ref_get(rdev, res);
 			break;
 		}
 	}
 
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 	if (!res)
 		return NULL;
 	trace_cfg80211_return_bss(&res->pub);
@@ -567,10 +569,10 @@ struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL(cfg80211_get_bss);
 
-static void rb_insert_bss(struct cfg80211_registered_device *dev,
+static void rb_insert_bss(struct cfg80211_registered_device *rdev,
 			  struct cfg80211_internal_bss *bss)
 {
-	struct rb_node **p = &dev->bss_tree.rb_node;
+	struct rb_node **p = &rdev->bss_tree.rb_node;
 	struct rb_node *parent = NULL;
 	struct cfg80211_internal_bss *tbss;
 	int cmp;
@@ -593,15 +595,15 @@ static void rb_insert_bss(struct cfg80211_registered_device *dev,
 	}
 
 	rb_link_node(&bss->rbn, parent, p);
-	rb_insert_color(&bss->rbn, &dev->bss_tree);
+	rb_insert_color(&bss->rbn, &rdev->bss_tree);
 }
 
 static struct cfg80211_internal_bss *
-rb_find_bss(struct cfg80211_registered_device *dev,
+rb_find_bss(struct cfg80211_registered_device *rdev,
 	    struct cfg80211_internal_bss *res,
 	    enum bss_compare_mode mode)
 {
-	struct rb_node *n = dev->bss_tree.rb_node;
+	struct rb_node *n = rdev->bss_tree.rb_node;
 	struct cfg80211_internal_bss *bss;
 	int r;
 
@@ -620,7 +622,7 @@ rb_find_bss(struct cfg80211_registered_device *dev,
 	return NULL;
 }
 
-static bool cfg80211_combine_bsses(struct cfg80211_registered_device *dev,
+static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
 				   struct cfg80211_internal_bss *new)
 {
 	const struct cfg80211_bss_ies *ies;
@@ -650,7 +652,7 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *dev,
 
 	/* This is the bad part ... */
 
-	list_for_each_entry(bss, &dev->bss_list, list) {
+	list_for_each_entry(bss, &rdev->bss_list, list) {
 		if (!ether_addr_equal(bss->pub.bssid, new->pub.bssid))
 			continue;
 		if (bss->pub.channel != new->pub.channel)
@@ -684,7 +686,7 @@ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *dev,
 
 /* Returned bss is reference counted and must be cleaned up appropriately. */
 static struct cfg80211_internal_bss *
-cfg80211_bss_update(struct cfg80211_registered_device *dev,
+cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 		    struct cfg80211_internal_bss *tmp,
 		    bool signal_valid)
 {
@@ -695,14 +697,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 
 	tmp->ts = jiffies;
 
-	spin_lock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
 
 	if (WARN_ON(!rcu_access_pointer(tmp->pub.ies))) {
-		spin_unlock_bh(&dev->bss_lock);
+		spin_unlock_bh(&rdev->bss_lock);
 		return NULL;
 	}
 
-	found = rb_find_bss(dev, tmp, BSS_CMP_REGULAR);
+	found = rb_find_bss(rdev, tmp, BSS_CMP_REGULAR);
 
 	if (found) {
 		/* Update IEs */
@@ -789,7 +791,7 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 		 * is allocated on the stack since it's not needed in the
 		 * more common case of an update
 		 */
-		new = kzalloc(sizeof(*new) + dev->wiphy.bss_priv_size,
+		new = kzalloc(sizeof(*new) + rdev->wiphy.bss_priv_size,
 			      GFP_ATOMIC);
 		if (!new) {
 			ies = (void *)rcu_dereference(tmp->pub.beacon_ies);
@@ -805,9 +807,9 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 		INIT_LIST_HEAD(&new->hidden_list);
 
 		if (rcu_access_pointer(tmp->pub.proberesp_ies)) {
-			hidden = rb_find_bss(dev, tmp, BSS_CMP_HIDE_ZLEN);
+			hidden = rb_find_bss(rdev, tmp, BSS_CMP_HIDE_ZLEN);
 			if (!hidden)
-				hidden = rb_find_bss(dev, tmp,
+				hidden = rb_find_bss(rdev, tmp,
 						     BSS_CMP_HIDE_NUL);
 			if (hidden) {
 				new->pub.hidden_beacon_bss = &hidden->pub;
@@ -824,24 +826,24 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 			 * expensive search for any probe responses that should
 			 * be grouped with this beacon for updates ...
 			 */
-			if (!cfg80211_combine_bsses(dev, new)) {
+			if (!cfg80211_combine_bsses(rdev, new)) {
 				kfree(new);
 				goto drop;
 			}
 		}
 
-		list_add_tail(&new->list, &dev->bss_list);
-		rb_insert_bss(dev, new);
+		list_add_tail(&new->list, &rdev->bss_list);
+		rb_insert_bss(rdev, new);
 		found = new;
 	}
 
-	dev->bss_generation++;
-	bss_ref_get(dev, found);
-	spin_unlock_bh(&dev->bss_lock);
+	rdev->bss_generation++;
+	bss_ref_get(rdev, found);
+	spin_unlock_bh(&rdev->bss_lock);
 
 	return found;
  drop:
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 	return NULL;
 }
 
@@ -889,6 +891,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 	struct cfg80211_bss_ies *ies;
 	struct ieee80211_channel *channel;
 	struct cfg80211_internal_bss tmp = {}, *res;
+	bool signal_valid;
 
 	if (WARN_ON(!wiphy))
 		return NULL;
@@ -925,8 +928,9 @@ cfg80211_inform_bss_width(struct wiphy *wiphy,
 	rcu_assign_pointer(tmp.pub.beacon_ies, ies);
 	rcu_assign_pointer(tmp.pub.ies, ies);
 
-	res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp,
-				  rx_channel == channel);
+	signal_valid = abs(rx_channel->center_freq - channel->center_freq) <=
+		wiphy->max_adj_channel_rssi_comp;
+	res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid);
 	if (!res)
 		return NULL;
 
@@ -950,6 +954,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy,
 	struct cfg80211_internal_bss tmp = {}, *res;
 	struct cfg80211_bss_ies *ies;
 	struct ieee80211_channel *channel;
+	bool signal_valid;
 	size_t ielen = len - offsetof(struct ieee80211_mgmt,
 				      u.probe_resp.variable);
 
@@ -997,8 +1002,9 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy,
 	tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
 	tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
 
-	res = cfg80211_bss_update(wiphy_to_dev(wiphy), &tmp,
-				  rx_channel == channel);
+	signal_valid = abs(rx_channel->center_freq - channel->center_freq) <=
+		wiphy->max_adj_channel_rssi_comp;
+	res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid);
 	if (!res)
 		return NULL;
 
@@ -1013,7 +1019,7 @@ EXPORT_SYMBOL(cfg80211_inform_bss_width_frame);
 
 void cfg80211_ref_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 {
-	struct cfg80211_registered_device *dev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss;
 
 	if (!pub)
@@ -1021,15 +1027,15 @@ void cfg80211_ref_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 
 	bss = container_of(pub, struct cfg80211_internal_bss, pub);
 
-	spin_lock_bh(&dev->bss_lock);
-	bss_ref_get(dev, bss);
-	spin_unlock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
+	bss_ref_get(rdev, bss);
+	spin_unlock_bh(&rdev->bss_lock);
 }
 EXPORT_SYMBOL(cfg80211_ref_bss);
 
 void cfg80211_put_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 {
-	struct cfg80211_registered_device *dev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss;
 
 	if (!pub)
@@ -1037,15 +1043,15 @@ void cfg80211_put_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 
 	bss = container_of(pub, struct cfg80211_internal_bss, pub);
 
-	spin_lock_bh(&dev->bss_lock);
-	bss_ref_put(dev, bss);
-	spin_unlock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
+	bss_ref_put(rdev, bss);
+	spin_unlock_bh(&rdev->bss_lock);
 }
 EXPORT_SYMBOL(cfg80211_put_bss);
 
 void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 {
-	struct cfg80211_registered_device *dev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct cfg80211_internal_bss *bss;
 
 	if (WARN_ON(!pub))
@@ -1053,12 +1059,12 @@ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *pub)
 
 	bss = container_of(pub, struct cfg80211_internal_bss, pub);
 
-	spin_lock_bh(&dev->bss_lock);
+	spin_lock_bh(&rdev->bss_lock);
 	if (!list_empty(&bss->list)) {
-		if (__cfg80211_unlink_bss(dev, bss))
-			dev->bss_generation++;
+		if (__cfg80211_unlink_bss(rdev, bss))
+			rdev->bss_generation++;
 	}
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 }
 EXPORT_SYMBOL(cfg80211_unlink_bss);
 
@@ -1075,7 +1081,7 @@ cfg80211_get_dev_from_ifindex(struct net *net, int ifindex)
 	if (!dev)
 		return ERR_PTR(-ENODEV);
 	if (dev->ieee80211_ptr)
-		rdev = wiphy_to_dev(dev->ieee80211_ptr->wiphy);
+		rdev = wiphy_to_rdev(dev->ieee80211_ptr->wiphy);
 	else
 		rdev = ERR_PTR(-ENODEV);
 	dev_put(dev);
@@ -1155,7 +1161,11 @@ int cfg80211_wext_siwscan(struct net_device *dev,
 				int k;
 				int wiphy_freq = wiphy->bands[band]->channels[j].center_freq;
 				for (k = 0; k < wreq->num_channels; k++) {
-					int wext_freq = cfg80211_wext_freq(wiphy, &wreq->channel_list[k]);
+					struct iw_freq *freq =
+						&wreq->channel_list[k];
+					int wext_freq =
+						cfg80211_wext_freq(freq);
+
 					if (wext_freq == wiphy_freq)
 						goto wext_freq_found;
 				}
@@ -1467,7 +1477,7 @@ ieee80211_bss(struct wiphy *wiphy, struct iw_request_info *info,
 }
 
 
-static int ieee80211_scan_results(struct cfg80211_registered_device *dev,
+static int ieee80211_scan_results(struct cfg80211_registered_device *rdev,
 				  struct iw_request_info *info,
 				  char *buf, size_t len)
 {
@@ -1475,18 +1485,18 @@ static int ieee80211_scan_results(struct cfg80211_registered_device *dev,
 	char *end_buf = buf + len;
 	struct cfg80211_internal_bss *bss;
 
-	spin_lock_bh(&dev->bss_lock);
-	cfg80211_bss_expire(dev);
+	spin_lock_bh(&rdev->bss_lock);
+	cfg80211_bss_expire(rdev);
 
-	list_for_each_entry(bss, &dev->bss_list, list) {
+	list_for_each_entry(bss, &rdev->bss_list, list) {
 		if (buf + len - current_ev <= IW_EV_ADDR_LEN) {
-			spin_unlock_bh(&dev->bss_lock);
+			spin_unlock_bh(&rdev->bss_lock);
 			return -E2BIG;
 		}
-		current_ev = ieee80211_bss(&dev->wiphy, info, bss,
+		current_ev = ieee80211_bss(&rdev->wiphy, info, bss,
 					   current_ev, end_buf);
 	}
-	spin_unlock_bh(&dev->bss_lock);
+	spin_unlock_bh(&rdev->bss_lock);
 	return current_ev - buf;
 }
 
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 3546a77033d..8bbeeb30221 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -59,7 +59,7 @@ static void cfg80211_sme_free(struct wireless_dev *wdev)
 
 static int cfg80211_conn_scan(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_scan_request *request;
 	int n_channels, err;
 
@@ -130,7 +130,7 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev)
 
 static int cfg80211_conn_do_work(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_connect_params *params;
 	struct cfg80211_assoc_request req = {};
 	int err;
@@ -149,7 +149,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev)
 	case CFG80211_CONN_SCAN_AGAIN:
 		return cfg80211_conn_scan(wdev);
 	case CFG80211_CONN_AUTHENTICATE_NEXT:
-		BUG_ON(!rdev->ops->auth);
+		if (WARN_ON(!rdev->ops->auth))
+			return -EOPNOTSUPP;
 		wdev->conn->state = CFG80211_CONN_AUTHENTICATING;
 		return cfg80211_mlme_auth(rdev, wdev->netdev,
 					  params->channel, params->auth_type,
@@ -161,7 +162,8 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev)
 	case CFG80211_CONN_AUTH_FAILED:
 		return -ENOTCONN;
 	case CFG80211_CONN_ASSOCIATE_NEXT:
-		BUG_ON(!rdev->ops->assoc);
+		if (WARN_ON(!rdev->ops->assoc))
+			return -EOPNOTSUPP;
 		wdev->conn->state = CFG80211_CONN_ASSOCIATING;
 		if (wdev->conn->prev_bssid_valid)
 			req.prev_bssid = wdev->conn->prev_bssid;
@@ -244,7 +246,7 @@ void cfg80211_conn_work(struct work_struct *work)
 /* Returned bss is reference counted and must be cleaned up appropriately. */
 static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_bss *bss;
 	u16 capa = WLAN_CAPABILITY_ESS;
 
@@ -274,7 +276,7 @@ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev)
 static void __cfg80211_sme_scan_done(struct net_device *dev)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_bss *bss;
 
 	ASSERT_WDEV_LOCK(wdev);
@@ -305,7 +307,7 @@ void cfg80211_sme_scan_done(struct net_device *dev)
 void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len)
 {
 	struct wiphy *wiphy = wdev->wiphy;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	u16 status_code = le16_to_cpu(mgmt->u.auth.status_code);
 
@@ -351,7 +353,7 @@ void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len)
 
 bool cfg80211_sme_rx_assoc_resp(struct wireless_dev *wdev, u16 status)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (!wdev->conn)
 		return false;
@@ -385,7 +387,7 @@ void cfg80211_sme_deauth(struct wireless_dev *wdev)
 
 void cfg80211_sme_auth_timeout(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (!wdev->conn)
 		return;
@@ -396,7 +398,7 @@ void cfg80211_sme_auth_timeout(struct wireless_dev *wdev)
 
 void cfg80211_sme_disassoc(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (!wdev->conn)
 		return;
@@ -407,7 +409,7 @@ void cfg80211_sme_disassoc(struct wireless_dev *wdev)
 
 void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (!wdev->conn)
 		return;
@@ -420,7 +422,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 				struct cfg80211_connect_params *connect,
 				const u8 *prev_bssid)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_bss *bss;
 	int err;
 
@@ -467,7 +469,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 	}
 
 	wdev->conn->params.ssid = wdev->ssid;
-	wdev->conn->params.ssid_len = connect->ssid_len;
+	wdev->conn->params.ssid_len = wdev->ssid_len;
 
 	/* see if we have the bss already */
 	bss = cfg80211_get_conn_bss(wdev);
@@ -479,7 +481,6 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 
 	/* we're good if we have a matching bss struct */
 	if (bss) {
-		wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT;
 		err = cfg80211_conn_do_work(wdev);
 		cfg80211_put_bss(wdev->wiphy, bss);
 	} else {
@@ -505,7 +506,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev,
 
 static int cfg80211_sme_disconnect(struct wireless_dev *wdev, u16 reason)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int err;
 
 	if (!wdev->conn)
@@ -593,7 +594,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 		return;
 	}
 
-	nl80211_send_connect_result(wiphy_to_dev(wdev->wiphy), dev,
+	nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev,
 				    bssid, req_ie, req_ie_len,
 				    resp_ie, resp_ie_len,
 				    status, GFP_KERNEL);
@@ -624,7 +625,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 #endif
 
 	if (!bss && (status == WLAN_STATUS_SUCCESS)) {
-		WARN_ON_ONCE(!wiphy_to_dev(wdev->wiphy)->ops->connect);
+		WARN_ON_ONCE(!wiphy_to_rdev(wdev->wiphy)->ops->connect);
 		bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid,
 				       wdev->ssid, wdev->ssid_len,
 				       WLAN_CAPABILITY_ESS,
@@ -687,7 +688,7 @@ void cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			     u16 status, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
 
@@ -742,7 +743,8 @@ void __cfg80211_roamed(struct wireless_dev *wdev,
 	cfg80211_hold_bss(bss_from_pub(bss));
 	wdev->current_bss = bss_from_pub(bss);
 
-	nl80211_send_roamed(wiphy_to_dev(wdev->wiphy), wdev->netdev, bss->bssid,
+	nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy),
+			    wdev->netdev, bss->bssid,
 			    req_ie, req_ie_len, resp_ie, resp_ie_len,
 			    GFP_KERNEL);
 
@@ -801,7 +803,7 @@ void cfg80211_roamed_bss(struct net_device *dev,
 			 size_t resp_ie_len, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
 
@@ -834,7 +836,7 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 			     size_t ie_len, u16 reason, bool from_ap)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int i;
 #ifdef CONFIG_CFG80211_WEXT
 	union iwreq_data wrqu;
@@ -877,10 +879,10 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie,
 }
 
 void cfg80211_disconnected(struct net_device *dev, u16 reason,
-			   u8 *ie, size_t ie_len, gfp_t gfp)
+			   const u8 *ie, size_t ie_len, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_event *ev;
 	unsigned long flags;
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index aabccf13e07..7cc887f9da1 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1876,29 +1876,33 @@ TRACE_EVENT(rdev_channel_switch,
 		WIPHY_ENTRY
 		NETDEV_ENTRY
 		CHAN_DEF_ENTRY
-		__field(u16, counter_offset_beacon)
-		__field(u16, counter_offset_presp)
 		__field(bool, radar_required)
 		__field(bool, block_tx)
 		__field(u8, count)
+		__dynamic_array(u16, bcn_ofs, params->n_counter_offsets_beacon)
+		__dynamic_array(u16, pres_ofs, params->n_counter_offsets_presp)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		NETDEV_ASSIGN;
 		CHAN_DEF_ASSIGN(&params->chandef);
-		__entry->counter_offset_beacon = params->counter_offset_beacon;
-		__entry->counter_offset_presp = params->counter_offset_presp;
 		__entry->radar_required = params->radar_required;
 		__entry->block_tx = params->block_tx;
 		__entry->count = params->count;
+		memcpy(__get_dynamic_array(bcn_ofs),
+		       params->counter_offsets_beacon,
+		       params->n_counter_offsets_beacon * sizeof(u16));
+
+		/* probe response offsets are optional */
+		if (params->n_counter_offsets_presp)
+			memcpy(__get_dynamic_array(pres_ofs),
+			       params->counter_offsets_presp,
+			       params->n_counter_offsets_presp * sizeof(u16));
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT
-		  ", block_tx: %d, count: %u, radar_required: %d"
-		  ", counter offsets (beacon/presp): %u/%u",
+		  ", block_tx: %d, count: %u, radar_required: %d",
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG,
-		  __entry->block_tx, __entry->count, __entry->radar_required,
-		  __entry->counter_offset_beacon,
-		  __entry->counter_offset_presp)
+		  __entry->block_tx, __entry->count, __entry->radar_required)
 );
 
 TRACE_EVENT(rdev_set_qos_map,
@@ -1919,6 +1923,24 @@ TRACE_EVENT(rdev_set_qos_map,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->num_des)
 );
 
+TRACE_EVENT(rdev_set_ap_chanwidth,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 struct cfg80211_chan_def *chandef),
+	TP_ARGS(wiphy, netdev, chandef),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+		CHAN_DEF_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+		CHAN_DEF_ASSIGN(chandef);
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT,
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG)
+);
+
 /*************************************************************
  *	     cfg80211 exported functions traces		     *
  *************************************************************/
@@ -2072,7 +2094,8 @@ TRACE_EVENT(cfg80211_michael_mic_failure,
 		MAC_ASSIGN(addr, addr);
 		__entry->key_type = key_type;
 		__entry->key_id = key_id;
-		memcpy(__entry->tsc, tsc, 6);
+		if (tsc)
+			memcpy(__entry->tsc, tsc, 6);
 	),
 	TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT ", key type: %d, key id: %d, tsc: %pm",
 		  NETDEV_PR_ARG, MAC_PR_ARG(addr), __entry->key_type,
@@ -2193,18 +2216,21 @@ TRACE_EVENT(cfg80211_cqm_rssi_notify,
 );
 
 TRACE_EVENT(cfg80211_reg_can_beacon,
-	TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef),
-	TP_ARGS(wiphy, chandef),
+	TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef,
+		 enum nl80211_iftype iftype),
+	TP_ARGS(wiphy, chandef, iftype),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		CHAN_DEF_ENTRY
+		__field(enum nl80211_iftype, iftype)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		CHAN_DEF_ASSIGN(chandef);
+		__entry->iftype = iftype;
 	),
-	TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT,
-		  WIPHY_PR_ARG, CHAN_DEF_PR_ARG)
+	TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d",
+		  WIPHY_PR_ARG, CHAN_DEF_PR_ARG, __entry->iftype)
 );
 
 TRACE_EVENT(cfg80211_chandef_dfs_required,
@@ -2615,6 +2641,21 @@ TRACE_EVENT(cfg80211_ft_event,
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(target_ap))
 );
 
+TRACE_EVENT(cfg80211_stop_iface,
+	TP_PROTO(struct wiphy *wiphy, struct wireless_dev *wdev),
+	TP_ARGS(wiphy, wdev),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		WDEV_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		WDEV_ASSIGN;
+	),
+	TP_printk(WIPHY_PR_FMT ", " WDEV_PR_FMT,
+		  WIPHY_PR_ARG, WDEV_PR_ARG)
+);
+
 #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/net/wireless/util.c b/net/wireless/util.c
index e5872ff2c27..728f1c0dc70 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -476,7 +476,8 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr,
 EXPORT_SYMBOL(ieee80211_data_to_8023);
 
 int ieee80211_data_from_8023(struct sk_buff *skb, const u8 *addr,
-			     enum nl80211_iftype iftype, u8 *bssid, bool qos)
+			     enum nl80211_iftype iftype,
+			     const u8 *bssid, bool qos)
 {
 	struct ieee80211_hdr hdr;
 	u16 hdrlen, ethertype;
@@ -770,7 +771,7 @@ EXPORT_SYMBOL(ieee80211_bss_get_ie);
 
 void cfg80211_upload_connect_keys(struct wireless_dev *wdev)
 {
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct net_device *dev = wdev->netdev;
 	int i;
 
@@ -839,6 +840,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev)
 			__cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid,
 					       ev->ij.channel);
 			break;
+		case EVENT_STOPPED:
+			__cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev);
+			break;
 		}
 		wdev_unlock(wdev);
 
@@ -888,11 +892,6 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 		return -EBUSY;
 
 	if (ntype != otype && netif_running(dev)) {
-		err = cfg80211_can_change_interface(rdev, dev->ieee80211_ptr,
-						    ntype);
-		if (err)
-			return err;
-
 		dev->ieee80211_ptr->use_4addr = false;
 		dev->ieee80211_ptr->mesh_id_up_len = 0;
 		wdev_lock(dev->ieee80211_ptr);
@@ -1268,6 +1267,120 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev,
 	return res;
 }
 
+int cfg80211_iter_combinations(struct wiphy *wiphy,
+			       const int num_different_channels,
+			       const u8 radar_detect,
+			       const int iftype_num[NUM_NL80211_IFTYPES],
+			       void (*iter)(const struct ieee80211_iface_combination *c,
+					    void *data),
+			       void *data)
+{
+	const struct ieee80211_regdomain *regdom;
+	enum nl80211_dfs_regions region = 0;
+	int i, j, iftype;
+	int num_interfaces = 0;
+	u32 used_iftypes = 0;
+
+	if (radar_detect) {
+		rcu_read_lock();
+		regdom = rcu_dereference(cfg80211_regdomain);
+		if (regdom)
+			region = regdom->dfs_region;
+		rcu_read_unlock();
+	}
+
+	for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
+		num_interfaces += iftype_num[iftype];
+		if (iftype_num[iftype] > 0 &&
+		    !(wiphy->software_iftypes & BIT(iftype)))
+			used_iftypes |= BIT(iftype);
+	}
+
+	for (i = 0; i < wiphy->n_iface_combinations; i++) {
+		const struct ieee80211_iface_combination *c;
+		struct ieee80211_iface_limit *limits;
+		u32 all_iftypes = 0;
+
+		c = &wiphy->iface_combinations[i];
+
+		if (num_interfaces > c->max_interfaces)
+			continue;
+		if (num_different_channels > c->num_different_channels)
+			continue;
+
+		limits = kmemdup(c->limits, sizeof(limits[0]) * c->n_limits,
+				 GFP_KERNEL);
+		if (!limits)
+			return -ENOMEM;
+
+		for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
+			if (wiphy->software_iftypes & BIT(iftype))
+				continue;
+			for (j = 0; j < c->n_limits; j++) {
+				all_iftypes |= limits[j].types;
+				if (!(limits[j].types & BIT(iftype)))
+					continue;
+				if (limits[j].max < iftype_num[iftype])
+					goto cont;
+				limits[j].max -= iftype_num[iftype];
+			}
+		}
+
+		if (radar_detect != (c->radar_detect_widths & radar_detect))
+			goto cont;
+
+		if (radar_detect && c->radar_detect_regions &&
+		    !(c->radar_detect_regions & BIT(region)))
+			goto cont;
+
+		/* Finally check that all iftypes that we're currently
+		 * using are actually part of this combination. If they
+		 * aren't then we can't use this combination and have
+		 * to continue to the next.
+		 */
+		if ((all_iftypes & used_iftypes) != used_iftypes)
+			goto cont;
+
+		/* This combination covered all interface types and
+		 * supported the requested numbers, so we're good.
+		 */
+
+		(*iter)(c, data);
+ cont:
+		kfree(limits);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(cfg80211_iter_combinations);
+
+static void
+cfg80211_iter_sum_ifcombs(const struct ieee80211_iface_combination *c,
+			  void *data)
+{
+	int *num = data;
+	(*num)++;
+}
+
+int cfg80211_check_combinations(struct wiphy *wiphy,
+				const int num_different_channels,
+				const u8 radar_detect,
+				const int iftype_num[NUM_NL80211_IFTYPES])
+{
+	int err, num = 0;
+
+	err = cfg80211_iter_combinations(wiphy, num_different_channels,
+					 radar_detect, iftype_num,
+					 cfg80211_iter_sum_ifcombs, &num);
+	if (err)
+		return err;
+	if (num == 0)
+		return -EBUSY;
+
+	return 0;
+}
+EXPORT_SYMBOL(cfg80211_check_combinations);
+
 int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 				 struct wireless_dev *wdev,
 				 enum nl80211_iftype iftype,
@@ -1276,7 +1389,6 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 				 u8 radar_detect)
 {
 	struct wireless_dev *wdev_iter;
-	u32 used_iftypes = BIT(iftype);
 	int num[NUM_NL80211_IFTYPES];
 	struct ieee80211_channel
 			*used_channels[CFG80211_MAX_NUM_DIFFERENT_CHANNELS];
@@ -1284,7 +1396,7 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 	enum cfg80211_chan_mode chmode;
 	int num_different_channels = 0;
 	int total = 1;
-	int i, j;
+	int i;
 
 	ASSERT_RTNL();
 
@@ -1306,6 +1418,11 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 
 	num[iftype] = 1;
 
+	/* TODO: We'll probably not need this anymore, since this
+	 * should only be called with CHAN_MODE_UNDEFINED. There are
+	 * still a couple of pending calls where other chanmodes are
+	 * used, but we should get rid of them.
+	 */
 	switch (chanmode) {
 	case CHAN_MODE_UNDEFINED:
 		break;
@@ -1369,65 +1486,13 @@ int cfg80211_can_use_iftype_chan(struct cfg80211_registered_device *rdev,
 
 		num[wdev_iter->iftype]++;
 		total++;
-		used_iftypes |= BIT(wdev_iter->iftype);
 	}
 
 	if (total == 1 && !radar_detect)
 		return 0;
 
-	for (i = 0; i < rdev->wiphy.n_iface_combinations; i++) {
-		const struct ieee80211_iface_combination *c;
-		struct ieee80211_iface_limit *limits;
-		u32 all_iftypes = 0;
-
-		c = &rdev->wiphy.iface_combinations[i];
-
-		if (total > c->max_interfaces)
-			continue;
-		if (num_different_channels > c->num_different_channels)
-			continue;
-
-		limits = kmemdup(c->limits, sizeof(limits[0]) * c->n_limits,
-				 GFP_KERNEL);
-		if (!limits)
-			return -ENOMEM;
-
-		for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
-			if (rdev->wiphy.software_iftypes & BIT(iftype))
-				continue;
-			for (j = 0; j < c->n_limits; j++) {
-				all_iftypes |= limits[j].types;
-				if (!(limits[j].types & BIT(iftype)))
-					continue;
-				if (limits[j].max < num[iftype])
-					goto cont;
-				limits[j].max -= num[iftype];
-			}
-		}
-
-		if (radar_detect && !(c->radar_detect_widths & radar_detect))
-			goto cont;
-
-		/*
-		 * Finally check that all iftypes that we're currently
-		 * using are actually part of this combination. If they
-		 * aren't then we can't use this combination and have
-		 * to continue to the next.
-		 */
-		if ((all_iftypes & used_iftypes) != used_iftypes)
-			goto cont;
-
-		/*
-		 * This combination covered all interface types and
-		 * supported the requested numbers, so we're good.
-		 */
-		kfree(limits);
-		return 0;
- cont:
-		kfree(limits);
-	}
-
-	return -EBUSY;
+	return cfg80211_check_combinations(&rdev->wiphy, num_different_channels,
+					   radar_detect, num);
 }
 
 int ieee80211_get_ratemask(struct ieee80211_supported_band *sband,
@@ -1481,6 +1546,24 @@ unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy)
 }
 EXPORT_SYMBOL(ieee80211_get_num_supported_channels);
 
+int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr,
+			 struct station_info *sinfo)
+{
+	struct cfg80211_registered_device *rdev;
+	struct wireless_dev *wdev;
+
+	wdev = dev->ieee80211_ptr;
+	if (!wdev)
+		return -EOPNOTSUPP;
+
+	rdev = wiphy_to_rdev(wdev->wiphy);
+	if (!rdev->ops->get_station)
+		return -EOPNOTSUPP;
+
+	return rdev_get_station(rdev, dev, mac_addr, sinfo);
+}
+EXPORT_SYMBOL(cfg80211_get_station);
+
 /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */
 /* Ethernet-II snap header (RFC1042 for most EtherTypes) */
 const unsigned char rfc1042_header[] __aligned(2) =
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 5661a54ac7e..11120bb1416 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -73,7 +73,7 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info,
 	struct vif_params vifparams;
 	enum nl80211_iftype type;
 
-	rdev = wiphy_to_dev(wdev->wiphy);
+	rdev = wiphy_to_rdev(wdev->wiphy);
 
 	switch (*mode) {
 	case IW_MODE_INFRA:
@@ -253,12 +253,12 @@ EXPORT_SYMBOL_GPL(cfg80211_wext_giwrange);
 
 /**
  * cfg80211_wext_freq - get wext frequency for non-"auto"
- * @wiphy: the wiphy
+ * @dev: the net device
  * @freq: the wext freq encoding
  *
  * Returns a frequency, or a negative error code, or 0 for auto.
  */
-int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq)
+int cfg80211_wext_freq(struct iw_freq *freq)
 {
 	/*
 	 * Parse frequency - return 0 for auto and
@@ -286,7 +286,7 @@ int cfg80211_wext_siwrts(struct net_device *dev,
 			 struct iw_param *rts, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u32 orts = wdev->wiphy->rts_threshold;
 	int err;
 
@@ -324,7 +324,7 @@ int cfg80211_wext_siwfrag(struct net_device *dev,
 			  struct iw_param *frag, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u32 ofrag = wdev->wiphy->frag_threshold;
 	int err;
 
@@ -364,7 +364,7 @@ static int cfg80211_wext_siwretry(struct net_device *dev,
 				  struct iw_param *retry, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u32 changed = 0;
 	u8 olong = wdev->wiphy->retry_long;
 	u8 oshort = wdev->wiphy->retry_short;
@@ -587,7 +587,7 @@ static int cfg80211_wext_siwencode(struct net_device *dev,
 				   struct iw_point *erq, char *keybuf)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int idx, err;
 	bool remove = false;
 	struct key_params params;
@@ -647,7 +647,7 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev,
 				      struct iw_point *erq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct iw_encode_ext *ext = (struct iw_encode_ext *) extra;
 	const u8 *addr;
 	int idx;
@@ -775,7 +775,7 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 				 struct iw_freq *wextfreq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_chan_def chandef = {
 		.width = NL80211_CHAN_WIDTH_20_NOHT,
 	};
@@ -787,7 +787,7 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 	case NL80211_IFTYPE_ADHOC:
 		return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra);
 	case NL80211_IFTYPE_MONITOR:
-		freq = cfg80211_wext_freq(wdev->wiphy, wextfreq);
+		freq = cfg80211_wext_freq(wextfreq);
 		if (freq < 0)
 			return freq;
 		if (freq == 0)
@@ -798,7 +798,7 @@ static int cfg80211_wext_siwfreq(struct net_device *dev,
 			return -EINVAL;
 		return cfg80211_set_monitor_channel(rdev, &chandef);
 	case NL80211_IFTYPE_MESH_POINT:
-		freq = cfg80211_wext_freq(wdev->wiphy, wextfreq);
+		freq = cfg80211_wext_freq(wextfreq);
 		if (freq < 0)
 			return freq;
 		if (freq == 0)
@@ -818,7 +818,7 @@ static int cfg80211_wext_giwfreq(struct net_device *dev,
 				 struct iw_freq *freq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_chan_def chandef;
 	int ret;
 
@@ -847,7 +847,7 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev,
 				    union iwreq_data *data, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	enum nl80211_tx_power_setting type;
 	int dbm = 0;
 
@@ -899,7 +899,7 @@ static int cfg80211_wext_giwtxpower(struct net_device *dev,
 				    union iwreq_data *data, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int err, val;
 
 	if ((data->txpower.flags & IW_TXPOW_TYPE) != IW_TXPOW_DBM)
@@ -1119,7 +1119,7 @@ static int cfg80211_wext_siwpower(struct net_device *dev,
 				  struct iw_param *wrq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	bool ps = wdev->ps;
 	int timeout = wdev->ps_timeout;
 	int err;
@@ -1177,7 +1177,7 @@ static int cfg80211_wds_wext_siwap(struct net_device *dev,
 				   struct sockaddr *addr, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	int err;
 
 	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS))
@@ -1221,7 +1221,7 @@ static int cfg80211_wext_siwrate(struct net_device *dev,
 				 struct iw_param *rate, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_bitrate_mask mask;
 	u32 fixed, maxrate;
 	struct ieee80211_supported_band *sband;
@@ -1272,7 +1272,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev,
 				 struct iw_param *rate, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	/* we are under RTNL - globally locked - so can use a static struct */
 	static struct station_info sinfo;
 	u8 addr[ETH_ALEN];
@@ -1310,7 +1310,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev,
 static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	/* we are under RTNL - globally locked - so can use static structs */
 	static struct iw_statistics wstats;
 	static struct station_info sinfo;
@@ -1449,7 +1449,7 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev,
 				  struct iw_point *data, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct cfg80211_pmksa cfg_pmksa;
 	struct iw_pmksa *pmksa = (struct iw_pmksa *)extra;
 
diff --git a/net/wireless/wext-compat.h b/net/wireless/wext-compat.h
index 5d766b0118e..ebcacca2f73 100644
--- a/net/wireless/wext-compat.h
+++ b/net/wireless/wext-compat.h
@@ -50,7 +50,7 @@ int cfg80211_wext_siwgenie(struct net_device *dev,
 			   struct iw_point *data, char *extra);
 
 
-int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq);
+int cfg80211_wext_freq(struct iw_freq *freq);
 
 
 extern const struct iw_handler_def cfg80211_wext_handler;
diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index 86c331a6566..c7e5c8eb4f2 100644
--- a/net/wireless/wext-sme.c
+++ b/net/wireless/wext-sme.c
@@ -67,7 +67,7 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev,
 			      struct iw_freq *wextfreq, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_channel *chan = NULL;
 	int err, freq;
 
@@ -75,7 +75,7 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev,
 	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION))
 		return -EINVAL;
 
-	freq = cfg80211_wext_freq(wdev->wiphy, wextfreq);
+	freq = cfg80211_wext_freq(wextfreq);
 	if (freq < 0)
 		return freq;
 
@@ -169,7 +169,7 @@ int cfg80211_mgd_wext_siwessid(struct net_device *dev,
 			       struct iw_point *data, char *ssid)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	size_t len = data->length;
 	int err;
 
@@ -260,7 +260,7 @@ int cfg80211_mgd_wext_siwap(struct net_device *dev,
 			    struct sockaddr *ap_addr, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u8 *bssid = ap_addr->sa_data;
 	int err;
 
@@ -333,7 +333,7 @@ int cfg80211_wext_siwgenie(struct net_device *dev,
 			   struct iw_point *data, char *extra)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	u8 *ie = extra;
 	int ie_len = data->length, err;
 
@@ -390,7 +390,7 @@ int cfg80211_wext_siwmlme(struct net_device *dev,
 	if (!wdev)
 		return -EOPNOTSUPP;
 
-	rdev = wiphy_to_dev(wdev->wiphy);
+	rdev = wiphy_to_rdev(wdev->wiphy);
 
 	if (wdev->iftype != NL80211_IFTYPE_STATION)
 		return -EINVAL;
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 3bb2cdc13b4..c51e8f7b865 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -199,6 +199,7 @@ int xfrm_output(struct sk_buff *skb)
 
 	return xfrm_output2(skb);
 }
+EXPORT_SYMBOL_GPL(xfrm_output);
 
 int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 {
@@ -213,6 +214,7 @@ int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
 		return -EAFNOSUPPORT;
 	return inner_mode->afinfo->extract_output(x, skb);
 }
+EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);
 
 void xfrm_local_error(struct sk_buff *skb, int mtu)
 {
@@ -233,7 +235,4 @@ void xfrm_local_error(struct sk_buff *skb, int mtu)
 	afinfo->local_error(skb, mtu);
 	xfrm_state_put_afinfo(afinfo);
 }
-
-EXPORT_SYMBOL_GPL(xfrm_output);
-EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);
 EXPORT_SYMBOL_GPL(xfrm_local_error);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c08fbd11cef..0525d78ba32 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -769,7 +769,7 @@ EXPORT_SYMBOL(xfrm_policy_byid);
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 static inline int
-xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info)
+xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 {
 	int dir, err = 0;
 
@@ -783,10 +783,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi
 				continue;
 			err = security_xfrm_policy_delete(pol->security);
 			if (err) {
-				xfrm_audit_policy_delete(pol, 0,
-							 audit_info->loginuid,
-							 audit_info->sessionid,
-							 audit_info->secid);
+				xfrm_audit_policy_delete(pol, 0, task_valid);
 				return err;
 			}
 		}
@@ -800,9 +797,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi
 								pol->security);
 				if (err) {
 					xfrm_audit_policy_delete(pol, 0,
-							audit_info->loginuid,
-							audit_info->sessionid,
-							audit_info->secid);
+								 task_valid);
 					return err;
 				}
 			}
@@ -812,19 +807,19 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi
 }
 #else
 static inline int
-xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info)
+xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 {
 	return 0;
 }
 #endif
 
-int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
+int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
 {
 	int dir, err = 0, cnt = 0;
 
 	write_lock_bh(&net->xfrm.xfrm_policy_lock);
 
-	err = xfrm_policy_flush_secctx_check(net, type, audit_info);
+	err = xfrm_policy_flush_secctx_check(net, type, task_valid);
 	if (err)
 		goto out;
 
@@ -841,9 +836,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 			write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 			cnt++;
 
-			xfrm_audit_policy_delete(pol, 1, audit_info->loginuid,
-						 audit_info->sessionid,
-						 audit_info->secid);
+			xfrm_audit_policy_delete(pol, 1, task_valid);
 
 			xfrm_policy_kill(pol);
 
@@ -862,10 +855,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info)
 				write_unlock_bh(&net->xfrm.xfrm_policy_lock);
 				cnt++;
 
-				xfrm_audit_policy_delete(pol, 1,
-							 audit_info->loginuid,
-							 audit_info->sessionid,
-							 audit_info->secid);
+				xfrm_audit_policy_delete(pol, 1, task_valid);
 				xfrm_policy_kill(pol);
 
 				write_lock_bh(&net->xfrm.xfrm_policy_lock);
@@ -2107,6 +2097,8 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 				goto no_transform;
 			}
 
+			dst_hold(&xdst->u.dst);
+			xdst->u.dst.flags |= DST_NOCACHE;
 			route = xdst->route;
 		}
 	}
@@ -2783,21 +2775,19 @@ static struct notifier_block xfrm_dev_notifier = {
 static int __net_init xfrm_statistics_init(struct net *net)
 {
 	int rv;
-
-	if (snmp_mib_init((void __percpu **)net->mib.xfrm_statistics,
-			  sizeof(struct linux_xfrm_mib),
-			  __alignof__(struct linux_xfrm_mib)) < 0)
+	net->mib.xfrm_statistics = alloc_percpu(struct linux_xfrm_mib);
+	if (!net->mib.xfrm_statistics)
 		return -ENOMEM;
 	rv = xfrm_proc_init(net);
 	if (rv < 0)
-		snmp_mib_free((void __percpu **)net->mib.xfrm_statistics);
+		free_percpu(net->mib.xfrm_statistics);
 	return rv;
 }
 
 static void xfrm_statistics_fini(struct net *net)
 {
 	xfrm_proc_fini(net);
-	snmp_mib_free((void __percpu **)net->mib.xfrm_statistics);
+	free_percpu(net->mib.xfrm_statistics);
 }
 #else
 static int __net_init xfrm_statistics_init(struct net *net)
@@ -2862,21 +2852,14 @@ out_byidx:
 
 static void xfrm_policy_fini(struct net *net)
 {
-	struct xfrm_audit audit_info;
 	unsigned int sz;
 	int dir;
 
 	flush_work(&net->xfrm.policy_hash_work);
 #ifdef CONFIG_XFRM_SUB_POLICY
-	audit_info.loginuid = INVALID_UID;
-	audit_info.sessionid = (unsigned int)-1;
-	audit_info.secid = 0;
-	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, &audit_info);
+	xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false);
 #endif
-	audit_info.loginuid = INVALID_UID;
-	audit_info.sessionid = (unsigned int)-1;
-	audit_info.secid = 0;
-	xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info);
+	xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false);
 
 	WARN_ON(!list_empty(&net->xfrm.policy_all));
 
@@ -2991,15 +2974,14 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp,
 	}
 }
 
-void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
-			   kuid_t auid, unsigned int sessionid, u32 secid)
+void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SPD-add");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	xfrm_audit_common_policyinfo(xp, audit_buf);
 	audit_log_end(audit_buf);
@@ -3007,14 +2989,14 @@ void xfrm_audit_policy_add(struct xfrm_policy *xp, int result,
 EXPORT_SYMBOL_GPL(xfrm_audit_policy_add);
 
 void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result,
-			      kuid_t auid, unsigned int sessionid, u32 secid)
+			      bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SPD-delete");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	xfrm_audit_common_policyinfo(xp, audit_buf);
 	audit_log_end(audit_buf);
diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c
index fc5abd0b456..9c4fbd8935f 100644
--- a/net/xfrm/xfrm_proc.c
+++ b/net/xfrm/xfrm_proc.c
@@ -54,8 +54,7 @@ static int xfrm_statistics_seq_show(struct seq_file *seq, void *v)
 	int i;
 	for (i = 0; xfrm_mib_list[i].name; i++)
 		seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name,
-			   snmp_fold_field((void __percpu **)
-					   net->mib.xfrm_statistics,
+			   snmp_fold_field(net->mib.xfrm_statistics,
 					   xfrm_mib_list[i].entry));
 	return 0;
 }
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 8e9c781a6bb..0ab54134bb4 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -463,9 +463,7 @@ expired:
 	if (!err)
 		km_state_expired(x, 1, 0);
 
-	xfrm_audit_state_delete(x, err ? 0 : 1,
-				audit_get_loginuid(current),
-				audit_get_sessionid(current), 0);
+	xfrm_audit_state_delete(x, err ? 0 : 1, true);
 
 out:
 	spin_unlock(&x->lock);
@@ -562,7 +560,7 @@ EXPORT_SYMBOL(xfrm_state_delete);
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 static inline int
-xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info)
+xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
 {
 	int i, err = 0;
 
@@ -572,10 +570,7 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi
 		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
 			if (xfrm_id_proto_match(x->id.proto, proto) &&
 			   (err = security_xfrm_state_delete(x)) != 0) {
-				xfrm_audit_state_delete(x, 0,
-							audit_info->loginuid,
-							audit_info->sessionid,
-							audit_info->secid);
+				xfrm_audit_state_delete(x, 0, task_valid);
 				return err;
 			}
 		}
@@ -585,18 +580,18 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi
 }
 #else
 static inline int
-xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info)
+xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid)
 {
 	return 0;
 }
 #endif
 
-int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info)
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
 {
 	int i, err = 0, cnt = 0;
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
-	err = xfrm_state_flush_secctx_check(net, proto, audit_info);
+	err = xfrm_state_flush_secctx_check(net, proto, task_valid);
 	if (err)
 		goto out;
 
@@ -612,9 +607,7 @@ restart:
 
 				err = xfrm_state_delete(x);
 				xfrm_audit_state_delete(x, err ? 0 : 1,
-							audit_info->loginuid,
-							audit_info->sessionid,
-							audit_info->secid);
+							task_valid);
 				xfrm_state_put(x);
 				if (!err)
 					cnt++;
@@ -2128,14 +2121,10 @@ out_bydst:
 
 void xfrm_state_fini(struct net *net)
 {
-	struct xfrm_audit audit_info;
 	unsigned int sz;
 
 	flush_work(&net->xfrm.state_hash_work);
-	audit_info.loginuid = INVALID_UID;
-	audit_info.sessionid = (unsigned int)-1;
-	audit_info.secid = 0;
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, &audit_info);
+	xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
 	flush_work(&net->xfrm.state_gc_work);
 
 	WARN_ON(!list_empty(&net->xfrm.state_all));
@@ -2198,30 +2187,28 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family,
 	}
 }
 
-void xfrm_audit_state_add(struct xfrm_state *x, int result,
-			  kuid_t auid, unsigned int sessionid, u32 secid)
+void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SAD-add");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	xfrm_audit_helper_sainfo(x, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	audit_log_end(audit_buf);
 }
 EXPORT_SYMBOL_GPL(xfrm_audit_state_add);
 
-void xfrm_audit_state_delete(struct xfrm_state *x, int result,
-			     kuid_t auid, unsigned int sessionid, u32 secid)
+void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid)
 {
 	struct audit_buffer *audit_buf;
 
 	audit_buf = xfrm_audit_start("SAD-delete");
 	if (audit_buf == NULL)
 		return;
-	xfrm_audit_helper_usrinfo(auid, sessionid, secid, audit_buf);
+	xfrm_audit_helper_usrinfo(task_valid, audit_buf);
 	xfrm_audit_helper_sainfo(x, audit_buf);
 	audit_log_format(audit_buf, " res=%u", result);
 	audit_log_end(audit_buf);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 51398ae6cda..d4db6ebb089 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -177,9 +177,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 		    attrs[XFRMA_ALG_AEAD]	||
 		    attrs[XFRMA_ALG_CRYPT]	||
 		    attrs[XFRMA_ALG_COMP]	||
-		    attrs[XFRMA_TFCPAD]		||
-		    (ntohl(p->id.spi) >= 0x10000))
-
+		    attrs[XFRMA_TFCPAD])
 			goto out;
 		break;
 
@@ -207,7 +205,8 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 		    attrs[XFRMA_ALG_AUTH]	||
 		    attrs[XFRMA_ALG_AUTH_TRUNC]	||
 		    attrs[XFRMA_ALG_CRYPT]	||
-		    attrs[XFRMA_TFCPAD])
+		    attrs[XFRMA_TFCPAD]		||
+		    (ntohl(p->id.spi) >= 0x10000))
 			goto out;
 		break;
 
@@ -597,9 +596,6 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_state *x;
 	int err;
 	struct km_event c;
-	kuid_t loginuid = audit_get_loginuid(current);
-	unsigned int sessionid = audit_get_sessionid(current);
-	u32 sid;
 
 	err = verify_newsa_info(p, attrs);
 	if (err)
@@ -615,8 +611,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	else
 		err = xfrm_state_update(x);
 
-	security_task_getsecid(current, &sid);
-	xfrm_audit_state_add(x, err ? 0 : 1, loginuid, sessionid, sid);
+	xfrm_audit_state_add(x, err ? 0 : 1, true);
 
 	if (err < 0) {
 		x->km.state = XFRM_STATE_DEAD;
@@ -676,9 +671,6 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err = -ESRCH;
 	struct km_event c;
 	struct xfrm_usersa_id *p = nlmsg_data(nlh);
-	kuid_t loginuid = audit_get_loginuid(current);
-	unsigned int sessionid = audit_get_sessionid(current);
-	u32 sid;
 
 	x = xfrm_user_state_lookup(net, p, attrs, &err);
 	if (x == NULL)
@@ -703,8 +695,7 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	km_state_notify(x, &c);
 
 out:
-	security_task_getsecid(current, &sid);
-	xfrm_audit_state_delete(x, err ? 0 : 1, loginuid, sessionid, sid);
+	xfrm_audit_state_delete(x, err ? 0 : 1, true);
 	xfrm_state_put(x);
 	return err;
 }
@@ -955,6 +946,20 @@ static struct sk_buff *xfrm_state_netlink(struct sk_buff *in_skb,
 	return skb;
 }
 
+/* A wrapper for nlmsg_multicast() checking that nlsk is still available.
+ * Must be called with RCU read lock.
+ */
+static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
+				       u32 pid, unsigned int group)
+{
+	struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
+
+	if (nlsk)
+		return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
+	else
+		return -1;
+}
+
 static inline size_t xfrm_spdinfo_msgsize(void)
 {
 	return NLMSG_ALIGN(4)
@@ -1414,9 +1419,6 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct km_event c;
 	int err;
 	int excl;
-	kuid_t loginuid = audit_get_loginuid(current);
-	unsigned int sessionid = audit_get_sessionid(current);
-	u32 sid;
 
 	err = verify_newpolicy_info(p);
 	if (err)
@@ -1435,8 +1437,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	 * a type XFRM_MSG_UPDPOLICY - JHS */
 	excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY;
 	err = xfrm_policy_insert(p->dir, xp, excl);
-	security_task_getsecid(current, &sid);
-	xfrm_audit_policy_add(xp, err ? 0 : 1, loginuid, sessionid, sid);
+	xfrm_audit_policy_add(xp, err ? 0 : 1, true);
 
 	if (err) {
 		security_xfrm_policy_free(xp->security);
@@ -1673,13 +1674,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 					    NETLINK_CB(skb).portid);
 		}
 	} else {
-		kuid_t loginuid = audit_get_loginuid(current);
-		unsigned int sessionid = audit_get_sessionid(current);
-		u32 sid;
-
-		security_task_getsecid(current, &sid);
-		xfrm_audit_policy_delete(xp, err ? 0 : 1, loginuid, sessionid,
-					 sid);
+		xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
 
 		if (err != 0)
 			goto out;
@@ -1704,13 +1699,9 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct km_event c;
 	struct xfrm_usersa_flush *p = nlmsg_data(nlh);
-	struct xfrm_audit audit_info;
 	int err;
 
-	audit_info.loginuid = audit_get_loginuid(current);
-	audit_info.sessionid = audit_get_sessionid(current);
-	security_task_getsecid(current, &audit_info.secid);
-	err = xfrm_state_flush(net, p->proto, &audit_info);
+	err = xfrm_state_flush(net, p->proto, true);
 	if (err) {
 		if (err == -ESRCH) /* empty table */
 			return 0;
@@ -1894,16 +1885,12 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct km_event c;
 	u8 type = XFRM_POLICY_TYPE_MAIN;
 	int err;
-	struct xfrm_audit audit_info;
 
 	err = copy_from_user_policy_type(&type, attrs);
 	if (err)
 		return err;
 
-	audit_info.loginuid = audit_get_loginuid(current);
-	audit_info.sessionid = audit_get_sessionid(current);
-	security_task_getsecid(current, &audit_info.secid);
-	err = xfrm_policy_flush(net, type, &audit_info);
+	err = xfrm_policy_flush(net, type, true);
 	if (err) {
 		if (err == -ESRCH) /* empty table */
 			return 0;
@@ -1969,14 +1956,8 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	err = 0;
 	if (up->hard) {
-		kuid_t loginuid = audit_get_loginuid(current);
-		unsigned int sessionid = audit_get_sessionid(current);
-		u32 sid;
-
-		security_task_getsecid(current, &sid);
 		xfrm_policy_delete(xp, p->dir);
-		xfrm_audit_policy_delete(xp, 1, loginuid, sessionid, sid);
-
+		xfrm_audit_policy_delete(xp, 1, true);
 	} else {
 		// reset the timers here?
 		WARN(1, "Dont know what to do with soft policy expire\n");
@@ -2012,13 +1993,8 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	km_state_expired(x, ue->hard, nlh->nlmsg_pid);
 
 	if (ue->hard) {
-		kuid_t loginuid = audit_get_loginuid(current);
-		unsigned int sessionid = audit_get_sessionid(current);
-		u32 sid;
-
-		security_task_getsecid(current, &sid);
 		__xfrm_state_delete(x);
-		xfrm_audit_state_delete(x, 1, loginuid, sessionid, sid);
+		xfrm_audit_state_delete(x, 1, true);
 	}
 	err = 0;
 out:
@@ -2265,7 +2241,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	if (build_migrate(skb, m, num_migrate, k, sel, dir, type) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MIGRATE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MIGRATE);
 }
 #else
 static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
@@ -2456,7 +2432,7 @@ static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c)
 		return -EMSGSIZE;
 	}
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
 }
 
 static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c)
@@ -2471,7 +2447,7 @@ static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event
 	if (build_aevent(skb, x, c) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_AEVENTS);
 }
 
 static int xfrm_notify_sa_flush(const struct km_event *c)
@@ -2497,7 +2473,7 @@ static int xfrm_notify_sa_flush(const struct km_event *c)
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
 }
 
 static inline size_t xfrm_sa_len(struct xfrm_state *x)
@@ -2584,7 +2560,7 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c)
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_SA);
 
 out_free_skb:
 	kfree_skb(skb);
@@ -2675,7 +2651,7 @@ static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt,
 	if (build_acquire(skb, x, xt, xp) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_ACQUIRE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_ACQUIRE);
 }
 
 /* User gives us xfrm_user_policy_info followed by an array of 0
@@ -2789,7 +2765,7 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct
 	if (build_polexpire(skb, xp, dir, c) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_EXPIRE);
 }
 
 static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c)
@@ -2851,7 +2827,7 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
 
 out_free_skb:
 	kfree_skb(skb);
@@ -2879,7 +2855,7 @@ static int xfrm_notify_policy_flush(const struct km_event *c)
 
 	nlmsg_end(skb, nlh);
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_POLICY);
 
 out_free_skb:
 	kfree_skb(skb);
@@ -2948,7 +2924,7 @@ static int xfrm_send_report(struct net *net, u8 proto,
 	if (build_report(skb, proto, sel, addr) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_REPORT, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_REPORT);
 }
 
 static inline size_t xfrm_mapping_msgsize(void)
@@ -3000,7 +2976,7 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr,
 	if (build_mapping(skb, x, ipaddr, sport) < 0)
 		BUG();
 
-	return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC);
+	return xfrm_nlmsg_multicast(net, skb, 0, XFRMNLGRP_MAPPING);
 }
 
 static bool xfrm_is_alive(const struct km_event *c)
diff --git a/samples/kobject/kobject-example.c b/samples/kobject/kobject-example.c
index 86ea0c3ad97..01562e0d499 100644
--- a/samples/kobject/kobject-example.c
+++ b/samples/kobject/kobject-example.c
@@ -40,8 +40,9 @@ static ssize_t foo_store(struct kobject *kobj, struct kobj_attribute *attr,
 	return count;
 }
 
+/* Sysfs attributes cannot be world-writable. */
 static struct kobj_attribute foo_attribute =
-	__ATTR(foo, 0666, foo_show, foo_store);
+	__ATTR(foo, 0664, foo_show, foo_store);
 
 /*
  * More complex function where we determine which variable is being accessed by
@@ -73,9 +74,9 @@ static ssize_t b_store(struct kobject *kobj, struct kobj_attribute *attr,
 }
 
 static struct kobj_attribute baz_attribute =
-	__ATTR(baz, 0666, b_show, b_store);
+	__ATTR(baz, 0664, b_show, b_store);
 static struct kobj_attribute bar_attribute =
-	__ATTR(bar, 0666, b_show, b_store);
+	__ATTR(bar, 0664, b_show, b_store);
 
 
 /*
diff --git a/samples/kobject/kset-example.c b/samples/kobject/kset-example.c
index 5dce351f131..ab5e447ec23 100644
--- a/samples/kobject/kset-example.c
+++ b/samples/kobject/kset-example.c
@@ -124,8 +124,9 @@ static ssize_t foo_store(struct foo_obj *foo_obj, struct foo_attribute *attr,
 	return count;
 }
 
+/* Sysfs attributes cannot be world-writable. */
 static struct foo_attribute foo_attribute =
-	__ATTR(foo, 0666, foo_show, foo_store);
+	__ATTR(foo, 0664, foo_show, foo_store);
 
 /*
  * More complex function where we determine which variable is being accessed by
@@ -157,9 +158,9 @@ static ssize_t b_store(struct foo_obj *foo_obj, struct foo_attribute *attr,
 }
 
 static struct foo_attribute baz_attribute =
-	__ATTR(baz, 0666, b_show, b_store);
+	__ATTR(baz, 0664, b_show, b_store);
 static struct foo_attribute bar_attribute =
-	__ATTR(bar, 0666, b_show, b_store);
+	__ATTR(bar, 0664, b_show, b_store);
 
 /*
  * Create a group of attributes so that we can create and destroy them all
diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h
index 6af373236d7..47642928138 100644
--- a/samples/trace_events/trace-events-sample.h
+++ b/samples/trace_events/trace-events-sample.h
@@ -56,7 +56,8 @@
  * struct:  This defines the way the data will be stored in the ring buffer.
  *    There are currently two types of elements. __field and __array.
  *    a __field is broken up into (type, name). Where type can be any
- *    type but an array.
+ *    primitive type (integer, long or pointer). __field_struct() can
+ *    be any static complex data value (struct, union, but not an array).
  *    For an array. there are three fields. (type, name, size). The
  *    type of elements in the array, the name of the field and the size
  *    of the array.
@@ -86,7 +87,7 @@ TRACE_EVENT(foo_bar,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->foo, foo, 10);
+		strlcpy(__entry->foo, foo, 10);
 		__entry->bar	= bar;
 	),
 
diff --git a/scripts/Makefile b/scripts/Makefile
index 1d07860f6c4..890df5c6adf 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -39,4 +39,4 @@ subdir-$(CONFIG_SECURITY_SELINUX) += selinux
 subdir-$(CONFIG_DTC)         += dtc
 
 # Let clean descend into subdirs
-subdir-	+= basic kconfig package selinux
+subdir-	+= basic kconfig package
diff --git a/scripts/Makefile.asm-generic b/scripts/Makefile.asm-generic
index d17e0ea911e..045e0098e96 100644
--- a/scripts/Makefile.asm-generic
+++ b/scripts/Makefile.asm-generic
@@ -21,4 +21,3 @@ all: $(patsubst %, $(obj)/%, $(generic-y))
 
 $(obj)/%.h:
 	$(call cmd,wrap)
-
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 003bc263105..bf3e6778cd7 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -50,67 +50,6 @@ ifeq ($(KBUILD_NOPEDANTIC),)
         endif
 endif
 
-#
-# make W=... settings
-#
-# W=1 - warnings that may be relevant and does not occur too often
-# W=2 - warnings that occur quite often but may still be relevant
-# W=3 - the more obscure warnings, can most likely be ignored
-#
-# $(call cc-option, -W...) handles gcc -W.. options which
-# are not supported by all versions of the compiler
-ifdef KBUILD_ENABLE_EXTRA_GCC_CHECKS
-warning-  := $(empty)
-
-warning-1 := -Wextra -Wunused -Wno-unused-parameter
-warning-1 += -Wmissing-declarations
-warning-1 += -Wmissing-format-attribute
-warning-1 += $(call cc-option, -Wmissing-prototypes)
-warning-1 += -Wold-style-definition
-warning-1 += $(call cc-option, -Wmissing-include-dirs)
-warning-1 += $(call cc-option, -Wunused-but-set-variable)
-warning-1 += $(call cc-disable-warning, missing-field-initializers)
-
-# Clang
-warning-1 += $(call cc-disable-warning, initializer-overrides)
-warning-1 += $(call cc-disable-warning, unused-value)
-warning-1 += $(call cc-disable-warning, format)
-warning-1 += $(call cc-disable-warning, unknown-warning-option)
-warning-1 += $(call cc-disable-warning, sign-compare)
-warning-1 += $(call cc-disable-warning, format-zero-length)
-warning-1 += $(call cc-disable-warning, uninitialized)
-warning-1 += $(call cc-option, -fcatch-undefined-behavior)
-
-warning-2 := -Waggregate-return
-warning-2 += -Wcast-align
-warning-2 += -Wdisabled-optimization
-warning-2 += -Wnested-externs
-warning-2 += -Wshadow
-warning-2 += $(call cc-option, -Wlogical-op)
-warning-2 += $(call cc-option, -Wmissing-field-initializers)
-
-warning-3 := -Wbad-function-cast
-warning-3 += -Wcast-qual
-warning-3 += -Wconversion
-warning-3 += -Wpacked
-warning-3 += -Wpadded
-warning-3 += -Wpointer-arith
-warning-3 += -Wredundant-decls
-warning-3 += -Wswitch-default
-warning-3 += $(call cc-option, -Wpacked-bitfield-compat)
-warning-3 += $(call cc-option, -Wvla)
-
-warning := $(warning-$(findstring 1, $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)))
-warning += $(warning-$(findstring 2, $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)))
-warning += $(warning-$(findstring 3, $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)))
-
-ifeq ("$(strip $(warning))","")
-        $(error W=$(KBUILD_ENABLE_EXTRA_GCC_CHECKS) is unknown)
-endif
-
-KBUILD_CFLAGS += $(warning)
-endif
-
 include scripts/Makefile.lib
 
 ifdef host-progs
@@ -342,7 +281,7 @@ $(real-objs-m)      : modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE)
 $(real-objs-m:.o=.s): modkern_aflags := $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE)
 
 quiet_cmd_as_s_S = CPP $(quiet_modtag) $@
-cmd_as_s_S       = $(CPP) $(a_flags)   -o $@ $< 
+cmd_as_s_S       = $(CPP) $(a_flags)   -o $@ $<
 
 $(obj)/%.s: $(src)/%.S FORCE
 	$(call if_changed_dep,as_s_S)
@@ -436,7 +375,7 @@ link_multi_deps =                     \
 $(filter $(addprefix $(obj)/,         \
 $($(subst $(obj)/,,$(@:.o=-objs)))    \
 $($(subst $(obj)/,,$(@:.o=-y)))), $^)
- 
+
 quiet_cmd_link_multi-y = LD      $@
 cmd_link_multi-y = $(LD) $(ld_flags) -r -o $@ $(link_multi_deps) $(cmd_secanalysis)
 
diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn
new file mode 100644
index 00000000000..65643506c71
--- /dev/null
+++ b/scripts/Makefile.extrawarn
@@ -0,0 +1,67 @@
+# ==========================================================================
+#
+# make W=... settings
+#
+# W=1 - warnings that may be relevant and does not occur too often
+# W=2 - warnings that occur quite often but may still be relevant
+# W=3 - the more obscure warnings, can most likely be ignored
+#
+# $(call cc-option, -W...) handles gcc -W.. options which
+# are not supported by all versions of the compiler
+# ==========================================================================
+
+ifeq ("$(origin W)", "command line")
+  export KBUILD_ENABLE_EXTRA_GCC_CHECKS := $(W)
+endif
+
+ifdef KBUILD_ENABLE_EXTRA_GCC_CHECKS
+warning-  := $(empty)
+
+warning-1 := -Wextra -Wunused -Wno-unused-parameter
+warning-1 += -Wmissing-declarations
+warning-1 += -Wmissing-format-attribute
+warning-1 += $(call cc-option, -Wmissing-prototypes)
+warning-1 += -Wold-style-definition
+warning-1 += $(call cc-option, -Wmissing-include-dirs)
+warning-1 += $(call cc-option, -Wunused-but-set-variable)
+warning-1 += $(call cc-disable-warning, missing-field-initializers)
+
+# Clang
+warning-1 += $(call cc-disable-warning, initializer-overrides)
+warning-1 += $(call cc-disable-warning, unused-value)
+warning-1 += $(call cc-disable-warning, format)
+warning-1 += $(call cc-disable-warning, unknown-warning-option)
+warning-1 += $(call cc-disable-warning, sign-compare)
+warning-1 += $(call cc-disable-warning, format-zero-length)
+warning-1 += $(call cc-disable-warning, uninitialized)
+warning-1 += $(call cc-option, -fcatch-undefined-behavior)
+
+warning-2 := -Waggregate-return
+warning-2 += -Wcast-align
+warning-2 += -Wdisabled-optimization
+warning-2 += -Wnested-externs
+warning-2 += -Wshadow
+warning-2 += $(call cc-option, -Wlogical-op)
+warning-2 += $(call cc-option, -Wmissing-field-initializers)
+
+warning-3 := -Wbad-function-cast
+warning-3 += -Wcast-qual
+warning-3 += -Wconversion
+warning-3 += -Wpacked
+warning-3 += -Wpadded
+warning-3 += -Wpointer-arith
+warning-3 += -Wredundant-decls
+warning-3 += -Wswitch-default
+warning-3 += $(call cc-option, -Wpacked-bitfield-compat)
+warning-3 += $(call cc-option, -Wvla)
+
+warning := $(warning-$(findstring 1, $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)))
+warning += $(warning-$(findstring 2, $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)))
+warning += $(warning-$(findstring 3, $(KBUILD_ENABLE_EXTRA_GCC_CHECKS)))
+
+ifeq ("$(strip $(warning))","")
+        $(error W=$(KBUILD_ENABLE_EXTRA_GCC_CHECKS) is unknown)
+endif
+
+KBUILD_CFLAGS += $(warning)
+endif
diff --git a/scripts/Makefile.fwinst b/scripts/Makefile.fwinst
index 4d908d16c03..d8e335eed22 100644
--- a/scripts/Makefile.fwinst
+++ b/scripts/Makefile.fwinst
@@ -18,31 +18,29 @@ include $(srctree)/$(obj)/Makefile
 include scripts/Makefile.host
 
 mod-fw := $(fw-shipped-m)
-# If CONFIG_FIRMWARE_IN_KERNEL isn't set, then install the 
+# If CONFIG_FIRMWARE_IN_KERNEL isn't set, then install the
 # firmware for in-kernel drivers too.
 ifndef CONFIG_FIRMWARE_IN_KERNEL
 mod-fw += $(fw-shipped-y)
 endif
 
+ifneq ($(KBUILD_SRC),)
+# Create output directory if not already present
+_dummy := $(shell [ -d $(obj) ] || mkdir -p $(obj))
+
+firmware-dirs := $(sort $(addprefix $(objtree)/$(obj)/,$(dir $(fw-external-y) $(fw-shipped-all))))
+# Create directories for firmware in subdirectories
+_dummy := $(foreach d,$(firmware-dirs), $(shell [ -d $(d) ] || mkdir -p $(d)))
+endif
+
 installed-mod-fw := $(addprefix $(INSTALL_FW_PATH)/,$(mod-fw))
 
 installed-fw := $(addprefix $(INSTALL_FW_PATH)/,$(fw-shipped-all))
-installed-fw-dirs := $(sort $(dir $(installed-fw))) $(INSTALL_FW_PATH)/./
-
-# Workaround for make < 3.81, where .SECONDEXPANSION doesn't work.
-PHONY += $(INSTALL_FW_PATH)/$$(%) install-all-dirs
-$(INSTALL_FW_PATH)/$$(%): install-all-dirs
-	@true
-install-all-dirs: $(installed-fw-dirs)
-	@true
 
 quiet_cmd_install = INSTALL $(subst $(srctree)/,,$@)
-      cmd_install = $(INSTALL) -m0644 $< $@
-
-$(installed-fw-dirs):
-	$(call cmd,mkdir)
+      cmd_install = mkdir -p $(@D); $(INSTALL) -m0644 $< $@
 
-$(installed-fw): $(INSTALL_FW_PATH)/%: $(obj)/% | $(INSTALL_FW_PATH)/$$(dir %)
+$(installed-fw): $(INSTALL_FW_PATH)/%: $(obj)/%
 	$(call cmd,install)
 
 PHONY +=  __fw_install __fw_modinst FORCE
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index 1ac414fd503..66893643fd7 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -166,5 +166,4 @@ $(host-cshlib): $(obj)/%: $(host-cshobjs) FORCE
 	$(call if_changed,host-cshlib)
 
 targets += $(host-csingle)  $(host-cmulti) $(host-cobjs)\
-	   $(host-cxxmulti) $(host-cxxobjs) $(host-cshlib) $(host-cshobjs) 
-
+	   $(host-cxxmulti) $(host-cxxobjs) $(host-cshlib) $(host-cshobjs)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 6a5b0decb79..260bf8acfce 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -27,7 +27,7 @@ lib-y := $(filter-out $(obj-y), $(sort $(lib-y) $(lib-m)))
 # ---------------------------------------------------------------------------
 # o if we encounter foo/ in $(obj-y), replace it by foo/built-in.o
 #   and add the directory to the list of dirs to descend into: $(subdir-y)
-# o if we encounter foo/ in $(obj-m), remove it from $(obj-m) 
+# o if we encounter foo/ in $(obj-m), remove it from $(obj-m)
 #   and add the directory to the list of dirs to descend into: $(subdir-m)
 
 # Determine modorder.
@@ -46,7 +46,7 @@ obj-m		:= $(filter-out %/, $(obj-m))
 
 subdir-ym	:= $(sort $(subdir-y) $(subdir-m))
 
-# if $(foo-objs) exists, foo.o is a composite object 
+# if $(foo-objs) exists, foo.o is a composite object
 multi-used-y := $(sort $(foreach m,$(obj-y), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y))), $(m))))
 multi-used-m := $(sort $(foreach m,$(obj-m), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y))), $(m))))
 multi-used   := $(multi-used-y) $(multi-used-m)
@@ -91,7 +91,7 @@ obj-dirs	:= $(addprefix $(obj)/,$(obj-dirs))
 
 # These flags are needed for modversions and compiling, so we define them here
 # already
-# $(modname_flags) #defines KBUILD_MODNAME as the name of the module it will 
+# $(modname_flags) #defines KBUILD_MODNAME as the name of the module it will
 # end up in (or would, if it gets compiled in)
 # Note: Files that end up in two or more modules are compiled without the
 #       KBUILD_MODNAME definition. The reason is that any made-up name would
@@ -212,7 +212,7 @@ $(obj)/%: $(src)/%_shipped
 
 # Commands useful for building a boot image
 # ===========================================================================
-# 
+#
 #	Use as following:
 #
 #	target: source(s) FORCE
@@ -226,7 +226,7 @@ $(obj)/%: $(src)/%_shipped
 
 quiet_cmd_ld = LD      $@
 cmd_ld = $(LD) $(LDFLAGS) $(ldflags-y) $(LDFLAGS_$(@F)) \
-	       $(filter-out FORCE,$^) -o $@ 
+	       $(filter-out FORCE,$^) -o $@
 
 # Objcopy
 # ---------------------------------------------------------------------------
diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c
index 078fe1d64e7..b30406860b7 100644
--- a/scripts/basic/fixdep.c
+++ b/scripts/basic/fixdep.c
@@ -409,10 +409,10 @@ static void print_deps(void)
 		exit(2);
 	}
 	if (fstat(fd, &st) < 0) {
-                fprintf(stderr, "fixdep: error fstat'ing depfile: ");
-                perror(depfile);
-                exit(2);
-        }
+		fprintf(stderr, "fixdep: error fstat'ing depfile: ");
+		perror(depfile);
+		exit(2);
+	}
 	if (st.st_size == 0) {
 		fprintf(stderr,"fixdep: %s is empty\n",depfile);
 		close(fd);
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 010b18ef4ea..182be0f1240 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -3476,12 +3476,17 @@ sub process {
 			}
 		}
 
-# unnecessary return in a void function? (a single leading tab, then return;)
-		if ($sline =~ /^\+\treturn\s*;\s*$/ &&
-		    $prevline =~ /^\+/) {
+# unnecessary return in a void function
+# at end-of-function, with the previous line a single leading tab, then return;
+# and the line before that not a goto label target like "out:"
+		if ($sline =~ /^[ \+]}\s*$/ &&
+		    $prevline =~ /^\+\treturn\s*;\s*$/ &&
+		    $linenr >= 3 &&
+		    $lines[$linenr - 3] =~ /^[ +]/ &&
+		    $lines[$linenr - 3] !~ /^[ +]\s*$Ident\s*:/) {
 			WARN("RETURN_VOID",
-			     "void function return statements are not generally useful\n" . $herecurr);
-		}
+			     "void function return statements are not generally useful\n" . $hereprev);
+               }
 
 # if statements using unnecessary parentheses - ie: if ((foo == bar))
 		if ($^V && $^V ge 5.10.0 &&
diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl
index 544aa56b620..c05d586b1fe 100755
--- a/scripts/checkstack.pl
+++ b/scripts/checkstack.pl
@@ -173,4 +173,3 @@ while (my $line = <STDIN>) {
 
 # Sort output by size (last field)
 print sort { ($b =~ /:\t*(\d+)$/)[0] <=> ($a =~ /:\t*(\d+)$/)[0] } @stack;
-
diff --git a/scripts/coccinelle/misc/of_table.cocci b/scripts/coccinelle/misc/of_table.cocci
new file mode 100644
index 00000000000..3c934046a06
--- /dev/null
+++ b/scripts/coccinelle/misc/of_table.cocci
@@ -0,0 +1,62 @@
+/// Make sure of_device_id tables are NULL terminated
+//
+// Keywords: of_table
+// Confidence: Medium
+// Options: --include-headers
+
+virtual patch
+virtual context
+virtual org
+virtual report
+
+@depends on context@
+identifier var, arr;
+expression E;
+@@
+struct of_device_id arr[] = {
+	...,
+	{
+	.var = E,
+*	}
+};
+
+@depends on patch@
+identifier var, arr;
+expression E;
+@@
+struct of_device_id arr[] = {
+	...,
+	{
+	.var = E,
+-	}
++	},
++	{ }
+};
+
+@r depends on org || report@
+position p1;
+identifier var, arr;
+expression E;
+@@
+struct of_device_id arr[] = {
+	...,
+	{
+	.var = E,
+	}
+	@p1
+};
+
+@script:python depends on org@
+p1 << r.p1;
+arr << r.arr;
+@@
+
+cocci.print_main(arr,p1)
+
+@script:python depends on report@
+p1 << r.p1;
+arr << r.arr;
+@@
+
+msg = "%s is not NULL terminated at line %s" % (arr, p1[0].line)
+coccilib.report.print_report(p1[0],msg)
diff --git a/scripts/coccinelle/misc/returnvar.cocci b/scripts/coccinelle/misc/returnvar.cocci
new file mode 100644
index 00000000000..605955a91c4
--- /dev/null
+++ b/scripts/coccinelle/misc/returnvar.cocci
@@ -0,0 +1,66 @@
+///
+/// Removes unneeded variable used to store return value.
+///
+// Confidence: Moderate
+// Copyright: (C) 2012 Peter Senna Tschudin, INRIA/LIP6.  GPLv2.
+// URL: http://coccinelle.lip6.fr/
+// Comments: Comments on code can be deleted if near code that is removed.
+//           "when strict" can be removed to get more hits, but adds false
+//           positives
+// Options: --no-includes --include-headers
+
+virtual patch
+virtual report
+virtual context
+virtual org
+
+@depends on patch@
+type T;
+constant C;
+identifier ret;
+@@
+- T ret = C;
+... when != ret
+    when strict
+return
+- ret
++ C
+;
+
+@depends on context@
+type T;
+constant C;
+identifier ret;
+@@
+* T ret = C;
+... when != ret
+    when strict
+* return ret;
+
+@r1 depends on report || org@
+type T;
+constant C;
+identifier ret;
+position p1, p2;
+@@
+T ret@p1 = C;
+... when != ret
+    when strict
+return ret@p2;
+
+@script:python depends on report@
+p1 << r1.p1;
+p2 << r1.p2;
+C << r1.C;
+ret << r1.ret;
+@@
+coccilib.report.print_report(p1[0], "Unneeded variable: \"" + ret + "\". Return \"" + C + "\" on line " + p2[0].line)
+
+@script:python depends on org@
+p1 << r1.p1;
+p2 << r1.p2;
+C << r1.C;
+ret << r1.ret;
+@@
+cocci.print_main("unneeded \"" + ret + "\" variable", p1)
+cocci.print_sec("return " + C + " here", p2)
diff --git a/scripts/config b/scripts/config
index 68041793698..026aeb4f32e 100755
--- a/scripts/config
+++ b/scripts/config
@@ -223,4 +223,3 @@ while [ "$1" != "" ] ; do
 		;;
 	esac
 done
-
diff --git a/scripts/conmakehash.c b/scripts/conmakehash.c
index 263a44d57fa..61bbda54cf1 100644
--- a/scripts/conmakehash.c
+++ b/scripts/conmakehash.c
@@ -104,7 +104,7 @@ int main(int argc, char *argv[])
 	}
     }
 
-  /* For now we assume the default font is always 256 characters. */    
+  /* For now we assume the default font is always 256 characters. */
   fontlen = 256;
 
   /* Initialize table */
@@ -236,15 +236,15 @@ int main(int argc, char *argv[])
     }
 
   /* Okay, we hit EOF, now output hash table */
-  
+
   fclose(ctbl);
-  
+
 
   /* Compute total size of Unicode list */
   nuni = 0;
   for ( i = 0 ; i < fontlen ; i++ )
     nuni += unicount[i];
-  
+
   printf("\
 /*\n\
  * Do not edit this file; it was automatically generated by\n\
@@ -268,9 +268,9 @@ u8 dfont_unicount[%d] = \n\
       else
         printf(", ");
     }
-  
+
   printf("\nu16 dfont_unitable[%d] = \n{\n\t", nuni);
-  
+
   fp0 = 0;
   nent = 0;
   for ( i = 0 ; i < nuni ; i++ )
diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
new file mode 100755
index 00000000000..515c4c00e95
--- /dev/null
+++ b/scripts/decode_stacktrace.sh
@@ -0,0 +1,126 @@
+#!/bin/bash
+# (c) 2014, Sasha Levin <sasha.levin@oracle.com>
+#set -x
+
+if [[ $# != 2 ]]; then
+	echo "Usage:"
+	echo "	$0 [vmlinux] [base path]"
+	exit 1
+fi
+
+vmlinux=$1
+basepath=$2
+declare -A cache
+
+parse_symbol() {
+	# The structure of symbol at this point is:
+	#   [name]+[offset]/[total length]
+	#
+	# For example:
+	#   do_basic_setup+0x9c/0xbf
+
+
+	# Strip the symbol name so that we could look it up
+	local name=${symbol%+*}
+
+	# Use 'nm vmlinux' to figure out the base address of said symbol.
+	# It's actually faster to call it every time than to load it
+	# all into bash.
+	if [[ "${cache[$name]+isset}" == "isset" ]]; then
+		local base_addr=${cache[$name]}
+	else
+		local base_addr=$(nm "$vmlinux" | grep -i ' t ' | awk "/ $name\$/ {print \$1}" | head -n1)
+		cache["$name"]="$base_addr"
+	fi
+	# Let's start doing the math to get the exact address into the
+	# symbol. First, strip out the symbol total length.
+	local expr=${symbol%/*}
+
+	# Now, replace the symbol name with the base address we found
+	# before.
+	expr=${expr/$name/0x$base_addr}
+
+	# Evaluate it to find the actual address
+	expr=$((expr))
+	local address=$(printf "%x\n" "$expr")
+
+	# Pass it to addr2line to get filename and line number
+        # Could get more than one result
+	if [[ "${cache[$address]+isset}" == "isset" ]]; then
+		local code=${cache[$address]}
+	else
+		local code=$(addr2line -i -e "$vmlinux" "$address")
+		cache[$address]=$code
+	fi
+
+	# addr2line doesn't return a proper error code if it fails, so
+	# we detect it using the value it prints so that we could preserve
+	# the offset/size into the function and bail out
+	if [[ $code == "??:0" ]]; then
+		return
+	fi
+
+	# Strip out the base of the path
+	code=${code//$basepath/""}
+
+	# In the case of inlines, move everything to same line
+	code=${code//$'\n'/' '}
+
+	# Replace old address with pretty line numbers
+	symbol="$name ($code)"
+}
+
+decode_code() {
+	local scripts=`dirname "${BASH_SOURCE[0]}"`
+
+	echo "$1" | $scripts/decodecode
+}
+
+handle_line() {
+	local words
+
+	# Tokenize
+	read -a words <<<"$1"
+
+	# Remove hex numbers. Do it ourselves until it happens in the
+	# kernel
+
+	# We need to know the index of the last element before we
+	# remove elements because arrays are sparse
+	local last=$(( ${#words[@]} - 1 ))
+
+	for i in "${!words[@]}"; do
+		# Remove the address
+		if [[ ${words[$i]} =~ \[\<([^]]+)\>\] ]]; then
+			unset words[$i]
+		fi
+
+		# Format timestamps with tabs
+		if [[ ${words[$i]} == \[ && ${words[$i+1]} == *\] ]]; then
+			unset words[$i]
+			words[$i+1]=$(printf "[%13s\n" "${words[$i+1]}")
+		fi
+	done
+
+	# The symbol is the last element, process it
+	symbol=${words[$last]}
+	unset words[$last]
+	parse_symbol # modifies $symbol
+
+	# Add up the line number to the symbol
+	echo "${words[@]}" "$symbol"
+}
+
+while read line; do
+	# Let's see if we have an address in the line
+	if [[ $line =~ \[\<([^]]+)\>\]  ]]; then
+		# Translate address to line numbers
+		handle_line "$line"
+	# Is it a code line?
+	elif [[ $line == *Code:* ]]; then
+                decode_code "$line"
+        else
+		# Nothing special in this line, show it as is
+		echo "$line"
+	fi
+done
diff --git a/scripts/docproc.c b/scripts/docproc.c
index 2b69eaf5b64..e267e621431 100644
--- a/scripts/docproc.c
+++ b/scripts/docproc.c
@@ -154,7 +154,7 @@ int symfilecnt = 0;
 static void add_new_symbol(struct symfile *sym, char * symname)
 {
 	sym->symbollist =
-          realloc(sym->symbollist, (sym->symbolcnt + 1) * sizeof(char *));
+	  realloc(sym->symbollist, (sym->symbolcnt + 1) * sizeof(char *));
 	sym->symbollist[sym->symbolcnt++].name = strdup(symname);
 }
 
@@ -215,7 +215,7 @@ static void find_export_symbols(char * filename)
 			char *p;
 			char *e;
 			if (((p = strstr(line, "EXPORT_SYMBOL_GPL")) != NULL) ||
-                            ((p = strstr(line, "EXPORT_SYMBOL")) != NULL)) {
+			    ((p = strstr(line, "EXPORT_SYMBOL")) != NULL)) {
 				/* Skip EXPORT_SYMBOL{_GPL} */
 				while (isalnum(*p) || *p == '_')
 					p++;
@@ -291,28 +291,28 @@ static void extfunc(char * filename) { docfunctions(filename, FUNCTION);   }
 static void singfunc(char * filename, char * line)
 {
 	char *vec[200]; /* Enough for specific functions */
-        int i, idx = 0;
-        int startofsym = 1;
+	int i, idx = 0;
+	int startofsym = 1;
 	vec[idx++] = KERNELDOC;
 	vec[idx++] = DOCBOOK;
 	vec[idx++] = SHOWNOTFOUND;
 
-        /* Split line up in individual parameters preceded by FUNCTION */
-        for (i=0; line[i]; i++) {
-                if (isspace(line[i])) {
-                        line[i] = '\0';
-                        startofsym = 1;
-                        continue;
-                }
-                if (startofsym) {
-                        startofsym = 0;
-                        vec[idx++] = FUNCTION;
-                        vec[idx++] = &line[i];
-                }
-        }
+	/* Split line up in individual parameters preceded by FUNCTION */
+	for (i=0; line[i]; i++) {
+		if (isspace(line[i])) {
+			line[i] = '\0';
+			startofsym = 1;
+			continue;
+		}
+		if (startofsym) {
+			startofsym = 0;
+			vec[idx++] = FUNCTION;
+			vec[idx++] = &line[i];
+		}
+	}
 	for (i = 0; i < idx; i++) {
-        	if (strcmp(vec[i], FUNCTION))
-        		continue;
+		if (strcmp(vec[i], FUNCTION))
+			continue;
 		consume_symbol(vec[i + 1]);
 	}
 	vec[idx++] = filename;
@@ -460,14 +460,14 @@ static void parse_file(FILE *infile)
 					break;
 				case 'D':
 					while (*s && !isspace(*s)) s++;
-                                        *s = '\0';
-                                        symbolsonly(line+2);
-                                        break;
+					*s = '\0';
+					symbolsonly(line+2);
+					break;
 				case 'F':
 					/* filename */
 					while (*s && !isspace(*s)) s++;
 					*s++ = '\0';
-                                        /* function names */
+					/* function names */
 					while (isspace(*s))
 						s++;
 					singlefunctions(line +2, s);
@@ -515,11 +515,11 @@ int main(int argc, char *argv[])
 	}
 	/* Open file, exit on error */
 	infile = fopen(argv[2], "r");
-        if (infile == NULL) {
-                fprintf(stderr, "docproc: ");
-                perror(argv[2]);
-                exit(2);
-        }
+	if (infile == NULL) {
+		fprintf(stderr, "docproc: ");
+		perror(argv[2]);
+		exit(2);
+	}
 
 	if (strcmp("doc", argv[1]) == 0) {
 		/* Need to do this in two passes.
diff --git a/scripts/dtc/.gitignore b/scripts/dtc/.gitignore
index 095acb49a37..cdabdc95a6e 100644
--- a/scripts/dtc/.gitignore
+++ b/scripts/dtc/.gitignore
@@ -2,4 +2,3 @@ dtc
 dtc-lexer.lex.c
 dtc-parser.tab.c
 dtc-parser.tab.h
-
diff --git a/scripts/dtc/fstree.c b/scripts/dtc/fstree.c
index f3774530170..e464727c880 100644
--- a/scripts/dtc/fstree.c
+++ b/scripts/dtc/fstree.c
@@ -88,4 +88,3 @@ struct boot_info *dt_from_fs(const char *dirname)
 
 	return build_boot_info(NULL, tree, guess_boot_cpuid(tree));
 }
-
diff --git a/scripts/dtc/libfdt/fdt_empty_tree.c b/scripts/dtc/libfdt/fdt_empty_tree.c
index f72d13b1d19..f2ae9b77c28 100644
--- a/scripts/dtc/libfdt/fdt_empty_tree.c
+++ b/scripts/dtc/libfdt/fdt_empty_tree.c
@@ -81,4 +81,3 @@ int fdt_create_empty_tree(void *buf, int bufsize)
 
 	return fdt_open_into(buf, buf, bufsize);
 }
-
diff --git a/scripts/dtc/treesource.c b/scripts/dtc/treesource.c
index 33eeba55fb4..5740e6992d3 100644
--- a/scripts/dtc/treesource.c
+++ b/scripts/dtc/treesource.c
@@ -281,4 +281,3 @@ void dt_to_source(FILE *f, struct boot_info *bi)
 
 	write_tree_source_node(f, bi->dt, 0);
 }
-
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 41987885bd3..d7016279ec2 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -21,6 +21,7 @@ my $lk_path = "./";
 my $email = 1;
 my $email_usename = 1;
 my $email_maintainer = 1;
+my $email_reviewer = 1;
 my $email_list = 1;
 my $email_subscriber_list = 0;
 my $email_git_penguin_chiefs = 0;
@@ -202,6 +203,7 @@ if (!GetOptions(
 		'remove-duplicates!' => \$email_remove_duplicates,
 		'mailmap!' => \$email_use_mailmap,
 		'm!' => \$email_maintainer,
+		'r!' => \$email_reviewer,
 		'n!' => \$email_usename,
 		'l!' => \$email_list,
 		's!' => \$email_subscriber_list,
@@ -260,7 +262,8 @@ if ($sections) {
 }
 
 if ($email &&
-    ($email_maintainer + $email_list + $email_subscriber_list +
+    ($email_maintainer + $email_reviewer +
+     $email_list + $email_subscriber_list +
      $email_git + $email_git_penguin_chiefs + $email_git_blame) == 0) {
     die "$P: Please select at least 1 email option\n";
 }
@@ -750,6 +753,7 @@ MAINTAINER field selection options:
     --hg-since => hg history to use (default: $email_hg_since)
     --interactive => display a menu (mostly useful if used with the --git option)
     --m => include maintainer(s) if any
+    --r => include reviewer(s) if any
     --n => include name 'Full Name <addr\@domain.tld>'
     --l => include list(s) if any
     --s => include subscriber only list(s) if any
@@ -1064,6 +1068,22 @@ sub add_categories {
 		    my $role = get_maintainer_role($i);
 		    push_email_addresses($pvalue, $role);
 		}
+	    } elsif ($ptype eq "R") {
+		my ($name, $address) = parse_email($pvalue);
+		if ($name eq "") {
+		    if ($i > 0) {
+			my $tv = $typevalue[$i - 1];
+			if ($tv =~ m/^(\C):\s*(.*)/) {
+			    if ($1 eq "P") {
+				$name = $2;
+				$pvalue = format_email($name, $address, $email_usename);
+			    }
+			}
+		    }
+		}
+		if ($email_reviewer) {
+		    push_email_addresses($pvalue, 'reviewer');
+		}
 	    } elsif ($ptype eq "T") {
 		push(@scm, $pvalue);
 	    } elsif ($ptype eq "W") {
diff --git a/scripts/headers.sh b/scripts/headers.sh
index 978b42b3acd..95ece06599a 100755
--- a/scripts/headers.sh
+++ b/scripts/headers.sh
@@ -28,5 +28,3 @@ for arch in ${archs}; do
 		;;
 	esac
 done
-
-
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 1237dd7fb4c..dc7aa45e80c 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -123,7 +123,7 @@ static int read_symbol(FILE *in, struct sym_entry *s)
 	}
 	if (strlen(str) > KSYM_NAME_LEN) {
 		fprintf(stderr, "Symbol %s too long for kallsyms (%zu vs %d).\n"
-                                "Please increase KSYM_NAME_LEN both in kernel and kallsyms.c\n",
+				"Please increase KSYM_NAME_LEN both in kernel and kallsyms.c\n",
 			str, strlen(str), KSYM_NAME_LEN);
 		return -1;
 	}
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 844bc9da08d..9c4d2412fb7 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -33,11 +33,11 @@ oldconfig: $(obj)/conf
 	$< --$@ $(Kconfig)
 
 silentoldconfig: $(obj)/conf
-	$(Q)mkdir -p include/generated
+	$(Q)mkdir -p include/config include/generated
 	$< --$@ $(Kconfig)
 
 localyesconfig localmodconfig: $(obj)/streamline_config.pl $(obj)/conf
-	$(Q)mkdir -p include/generated
+	$(Q)mkdir -p include/config include/generated
 	$(Q)perl $< --$@ $(srctree) $(Kconfig) > .tmp.config
 	$(Q)if [ -f .config ]; then 					\
 			cmp -s .tmp.config .config ||			\
@@ -319,4 +319,3 @@ $(obj)/%.moc: $(src)/%.h $(obj)/.tmp_qtcheck
 $(obj)/gconf.glade.h: $(obj)/gconf.glade
 	$(Q)intltool-extract --type=gettext/glade --srcdir=$(srctree) \
 	$(obj)/gconf.glade
-
diff --git a/scripts/kconfig/check.sh b/scripts/kconfig/check.sh
index 854d9c7c675..55b79ba1ba2 100755
--- a/scripts/kconfig/check.sh
+++ b/scripts/kconfig/check.sh
@@ -11,4 +11,3 @@ EOF
 if [ ! "$?" -eq "0"  ]; then
 	echo -DKBUILD_NO_NLS;
 fi
-
diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index d19944f9c3a..fef75fc756f 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -696,7 +696,7 @@ int main(int ac, char **av)
 	} else if (input_mode == savedefconfig) {
 		if (conf_write_defconfig(defconfig_file)) {
 			fprintf(stderr, _("n*** Error while saving defconfig to: %s\n\n"),
-			        defconfig_file);
+				defconfig_file);
 			return 1;
 		}
 	} else if (input_mode != listnewconfig) {
diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c
index f2bee70e26f..d0a35b21f30 100644
--- a/scripts/kconfig/gconf.c
+++ b/scripts/kconfig/gconf.c
@@ -1404,7 +1404,7 @@ static void display_tree(struct menu *menu)
 		    && (tree == tree2))
 			continue;
 /*
-                if (((menu != &rootmenu) && !(menu->flags & MENU_ROOT))
+		if (((menu != &rootmenu) && !(menu->flags & MENU_ROOT))
 		    || (view_mode == FULL_VIEW)
 		    || (view_mode == SPLIT_VIEW))*/
 
diff --git a/scripts/kconfig/lxdialog/checklist.c b/scripts/kconfig/lxdialog/checklist.c
index 3b15c08ec1f..8d016faa28d 100644
--- a/scripts/kconfig/lxdialog/checklist.c
+++ b/scripts/kconfig/lxdialog/checklist.c
@@ -168,13 +168,13 @@ do_resize:
 
 	/* create new window for the list */
 	list = subwin(dialog, list_height, list_width, y + box_y + 1,
-	              x + box_x + 1);
+		      x + box_x + 1);
 
 	keypad(list, TRUE);
 
 	/* draw a box around the list items */
 	draw_box(dialog, box_y, box_x, list_height + 2, list_width + 2,
-	         dlg.menubox_border.atr, dlg.menubox.atr);
+		 dlg.menubox_border.atr, dlg.menubox.atr);
 
 	/* Find length of longest item in order to center checklist */
 	check_x = 0;
diff --git a/scripts/kconfig/lxdialog/inputbox.c b/scripts/kconfig/lxdialog/inputbox.c
index 447a582198c..d58de1dc536 100644
--- a/scripts/kconfig/lxdialog/inputbox.c
+++ b/scripts/kconfig/lxdialog/inputbox.c
@@ -42,7 +42,7 @@ static void print_buttons(WINDOW * dialog, int height, int width, int selected)
  * Display a dialog box for inputing a string
  */
 int dialog_inputbox(const char *title, const char *prompt, int height, int width,
-                    const char *init)
+		    const char *init)
 {
 	int i, x, y, box_y, box_x, box_width;
 	int input_x = 0, key = 0, button = -1;
diff --git a/scripts/kconfig/lxdialog/menubox.c b/scripts/kconfig/lxdialog/menubox.c
index c93de0b2fac..11ae9ad7ac7 100644
--- a/scripts/kconfig/lxdialog/menubox.c
+++ b/scripts/kconfig/lxdialog/menubox.c
@@ -64,7 +64,7 @@ static int menu_width, item_x;
  * Print menu item
  */
 static void do_print_item(WINDOW * win, const char *item, int line_y,
-                          int selected, int hotkey)
+			  int selected, int hotkey)
 {
 	int j;
 	char *menu_item = malloc(menu_width + 1);
@@ -182,7 +182,7 @@ static void do_scroll(WINDOW *win, int *scroll, int n)
  * Display a menu for choosing among a number of options
  */
 int dialog_menu(const char *title, const char *prompt,
-                const void *selected, int *s_scroll)
+		const void *selected, int *s_scroll)
 {
 	int i, j, x, y, box_x, box_y;
 	int height, width, menu_height;
diff --git a/scripts/kconfig/lxdialog/util.c b/scripts/kconfig/lxdialog/util.c
index 58a8289dd65..f7abdeb92af 100644
--- a/scripts/kconfig/lxdialog/util.c
+++ b/scripts/kconfig/lxdialog/util.c
@@ -623,7 +623,7 @@ void item_make(const char *fmt, ...)
 void item_add_str(const char *fmt, ...)
 {
 	va_list ap;
-        size_t avail;
+	size_t avail;
 
 	avail = sizeof(item_cur->node.str) - strlen(item_cur->node.str);
 
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index 59184bb41ef..14cea7463a6 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -299,7 +299,7 @@ static void set_config_filename(const char *config_filename)
 	int size;
 
 	size = snprintf(menu_backtitle, sizeof(menu_backtitle),
-	                "%s - %s", config_filename, rootmenu.prompt->text);
+			"%s - %s", config_filename, rootmenu.prompt->text);
 	if (size >= sizeof(menu_backtitle))
 		menu_backtitle[sizeof(menu_backtitle)-1] = '\0';
 	set_dialog_backtitle(menu_backtitle);
@@ -1034,4 +1034,3 @@ int main(int ac, char **av)
 
 	return res;
 }
-
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 3ac2c9c6e28..a26cc5d2a9b 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -258,8 +258,8 @@ static void sym_check_prop(struct symbol *sym)
 				    "config symbol '%s' uses select, but is "
 				    "not boolean or tristate", sym->name);
 			else if (sym2->type != S_UNKNOWN &&
-			         sym2->type != S_BOOLEAN &&
-			         sym2->type != S_TRISTATE)
+				 sym2->type != S_BOOLEAN &&
+				 sym2->type != S_TRISTATE)
 				prop_warn(prop,
 				    "'%s' has wrong type. 'select' only "
 				    "accept arguments of boolean and "
@@ -268,7 +268,7 @@ static void sym_check_prop(struct symbol *sym)
 		case P_RANGE:
 			if (sym->type != S_INT && sym->type != S_HEX)
 				prop_warn(prop, "range is only allowed "
-				                "for int or hex symbols");
+						"for int or hex symbols");
 			if (!menu_validate_number(sym, prop->expr->left.sym) ||
 			    !menu_validate_number(sym, prop->expr->right.sym))
 				prop_warn(prop, "range is invalid");
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index 4fbecd2473b..984489ef2b4 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -1554,4 +1554,3 @@ int main(int ac, char **av)
 	endwin();
 	return 0;
 }
-
diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index 31331723e81..9cb8522d8d2 100644
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
@@ -589,7 +589,7 @@ while ($repeat) {
 
     # Now we need to see if we have to check selects;
     loop_select;
-}	    
+}
 
 my %setconfigs;
 
diff --git a/scripts/kconfig/util.c b/scripts/kconfig/util.c
index 6e7fbf19680..94f9c83e324 100644
--- a/scripts/kconfig/util.c
+++ b/scripts/kconfig/util.c
@@ -155,5 +155,3 @@ void *xcalloc(size_t nmemb, size_t size)
 	fprintf(stderr, "Out of memory.\n");
 	exit(1);
 }
-
-
diff --git a/scripts/kconfig/zconf.l b/scripts/kconfig/zconf.l
index 1a9f53e535c..6c62d93b4ff 100644
--- a/scripts/kconfig/zconf.l
+++ b/scripts/kconfig/zconf.l
@@ -27,8 +27,8 @@ static char *text;
 static int text_size, text_asize;
 
 struct buffer {
-        struct buffer *parent;
-        YY_BUFFER_STATE state;
+	struct buffer *parent;
+	YY_BUFFER_STATE state;
 };
 
 struct buffer *current_buf;
diff --git a/scripts/kconfig/zconf.lex.c_shipped b/scripts/kconfig/zconf.lex.c_shipped
index a0521aa5974..349a7f24315 100644
--- a/scripts/kconfig/zconf.lex.c_shipped
+++ b/scripts/kconfig/zconf.lex.c_shipped
@@ -789,8 +789,8 @@ static char *text;
 static int text_size, text_asize;
 
 struct buffer {
-        struct buffer *parent;
-        YY_BUFFER_STATE state;
+	struct buffer *parent;
+	YY_BUFFER_STATE state;
 };
 
 struct buffer *current_buf;
diff --git a/scripts/kconfig/zconf.tab.c_shipped b/scripts/kconfig/zconf.tab.c_shipped
index 25ae16ac75c..de5e84ed3f9 100644
--- a/scripts/kconfig/zconf.tab.c_shipped
+++ b/scripts/kconfig/zconf.tab.c_shipped
@@ -2314,7 +2314,7 @@ void conf_parse(const char *name)
 	for_all_symbols(i, sym) {
 		if (sym_check_deps(sym))
 			zconfnerrs++;
-        }
+	}
 	if (zconfnerrs)
 		exit(1);
 	sym_set_change_count(1);
diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y
index 0653886fac4..0f683cfa53e 100644
--- a/scripts/kconfig/zconf.y
+++ b/scripts/kconfig/zconf.y
@@ -510,7 +510,7 @@ void conf_parse(const char *name)
 	for_all_symbols(i, sym) {
 		if (sym_check_deps(sym))
 			zconfnerrs++;
-        }
+	}
 	if (zconfnerrs)
 		exit(1);
 	sym_set_change_count(1);
diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index da058da413e..16a07cfa4d3 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -2073,6 +2073,7 @@ sub check_return_section {
 sub dump_function($$) {
     my $prototype = shift;
     my $file = shift;
+    my $noret = 0;
 
     $prototype =~ s/^static +//;
     $prototype =~ s/^extern +//;
@@ -2086,7 +2087,7 @@ sub dump_function($$) {
     $prototype =~ s/__init_or_module +//;
     $prototype =~ s/__must_check +//;
     $prototype =~ s/__weak +//;
-    $prototype =~ s/^#\s*define\s+//; #ak added
+    my $define = $prototype =~ s/^#\s*define\s+//; #ak added
     $prototype =~ s/__attribute__\s*\(\([a-z,]*\)\)//;
 
     # Yes, this truly is vile.  We are looking for:
@@ -2105,7 +2106,15 @@ sub dump_function($$) {
     # - atomic_set (macro)
     # - pci_match_device, __copy_to_user (long return type)
 
-    if ($prototype =~ m/^()([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ ||
+    if ($define && $prototype =~ m/^()([a-zA-Z0-9_~:]+)\s+/) {
+        # This is an object-like macro, it has no return type and no parameter
+        # list.
+        # Function-like macros are not allowed to have spaces between
+        # declaration_name and opening parenthesis (notice the \s+).
+        $return_type = $1;
+        $declaration_name = $2;
+        $noret = 1;
+    } elsif ($prototype =~ m/^()([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ ||
 	$prototype =~ m/^(\w+)\s+([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ ||
 	$prototype =~ m/^(\w+\s*\*)\s*([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ ||
 	$prototype =~ m/^(\w+\s+\w+)\s+([a-zA-Z0-9_~:]+)\s*\(([^\(]*)\)/ ||
@@ -2140,7 +2149,7 @@ sub dump_function($$) {
         # of warnings goes sufficiently down, the check is only performed in
         # verbose mode.
         # TODO: always perform the check.
-        if ($verbose) {
+        if ($verbose && !$noret) {
                 check_return_section($file, $declaration_name, $return_type);
         }
 
diff --git a/scripts/markup_oops.pl b/scripts/markup_oops.pl
index 827896f5650..c21d16328d3 100644
--- a/scripts/markup_oops.pl
+++ b/scripts/markup_oops.pl
@@ -367,4 +367,3 @@ OPTION:
 EOT
 	exit;
 }
-
diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h
index cfb8440cc0b..6fdc97ef602 100755
--- a/scripts/mkcompile_h
+++ b/scripts/mkcompile_h
@@ -68,7 +68,7 @@ UTS_TRUNCATE="cut -b -$UTS_LEN"
 
 ( echo /\* This file is auto generated, version $VERSION \*/
   if [ -n "$CONFIG_FLAGS" ] ; then echo "/* $CONFIG_FLAGS */"; fi
-  
+
   echo \#define UTS_MACHINE \"$ARCH\"
 
   echo \#define UTS_VERSION \"`echo $UTS_VERSION | $UTS_TRUNCATE`\"
@@ -84,7 +84,7 @@ UTS_TRUNCATE="cut -b -$UTS_LEN"
 # recompilations.
 # We don't consider the file changed if only the date/time changed.
 # A kernel config change will increase the generation number, thus
-# causing compile.h to be updated (including date/time) due to the 
+# causing compile.h to be updated (including date/time) due to the
 # changed comment in the
 # first line.
 
diff --git a/scripts/mkmakefile b/scripts/mkmakefile
index 0cc04426074..84af27bf0f9 100644
--- a/scripts/mkmakefile
+++ b/scripts/mkmakefile
@@ -42,18 +42,11 @@ MAKEARGS += O=\$(if \$(patsubst /%,,\$(makedir)),\$(CURDIR)/)\$(patsubst %/,%,\$
 
 MAKEFLAGS += --no-print-directory
 
-.PHONY: all \$(MAKECMDGOALS)
+.PHONY: __sub-make \$(MAKECMDGOALS)
 
-all	:= \$(filter-out all Makefile,\$(MAKECMDGOALS))
+__sub-make:
+	\$(Q)\$(MAKE) \$(MAKEARGS) \$(MAKECMDGOALS)
 
-all:
-	\$(Q)\$(MAKE) \$(MAKEARGS) \$(all)
-
-Makefile:;
-
-\$(all): all
-	@:
-
-%/: all
+\$(filter-out __sub-make, \$(MAKECMDGOALS)): __sub-make
 	@:
 EOF
diff --git a/scripts/mksysmap b/scripts/mksysmap
index c1b6191ef87..7ada35a0f47 100644
--- a/scripts/mksysmap
+++ b/scripts/mksysmap
@@ -42,4 +42,3 @@
 # (At least sparc64 has __crc_ in the middle).
 
 $NM -n $1 | grep -v '\( [aNUw] \)\|\(__crc_\)\|\( \$[adt]\)' > $2
-
diff --git a/scripts/mod/.gitignore b/scripts/mod/.gitignore
index 33bae0df4de..3bd11b60317 100644
--- a/scripts/mod/.gitignore
+++ b/scripts/mod/.gitignore
@@ -2,4 +2,3 @@ elfconfig.h
 mk_elfconfig
 modpost
 devicetable-offsets.h
-
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 1924990a737..e614ef689ee 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -644,28 +644,26 @@ ADD_TO_DEVTABLE("pcmcia", pcmcia_device_id, do_pcmcia_entry);
 
 static int do_of_entry (const char *filename, void *symval, char *alias)
 {
-    int len;
-    char *tmp;
-    DEF_FIELD_ADDR(symval, of_device_id, name);
-    DEF_FIELD_ADDR(symval, of_device_id, type);
-    DEF_FIELD_ADDR(symval, of_device_id, compatible);
-
-    len = sprintf (alias, "of:N%sT%s",
-                    (*name)[0] ? *name : "*",
-                    (*type)[0] ? *type : "*");
-
-    if (compatible[0])
-        sprintf (&alias[len], "%sC%s",
-                     (*type)[0] ? "*" : "",
-                     *compatible);
-
-    /* Replace all whitespace with underscores */
-    for (tmp = alias; tmp && *tmp; tmp++)
-        if (isspace (*tmp))
-            *tmp = '_';
-
-    add_wildcard(alias);
-    return 1;
+	int len;
+	char *tmp;
+	DEF_FIELD_ADDR(symval, of_device_id, name);
+	DEF_FIELD_ADDR(symval, of_device_id, type);
+	DEF_FIELD_ADDR(symval, of_device_id, compatible);
+
+	len = sprintf(alias, "of:N%sT%s", (*name)[0] ? *name : "*",
+		      (*type)[0] ? *type : "*");
+
+	if (compatible[0])
+		sprintf(&alias[len], "%sC%s", (*type)[0] ? "*" : "",
+			*compatible);
+
+	/* Replace all whitespace with underscores */
+	for (tmp = alias; tmp && *tmp; tmp++)
+		if (isspace (*tmp))
+			*tmp = '_';
+
+	add_wildcard(alias);
+	return 1;
 }
 ADD_TO_DEVTABLE("of", of_device_id, do_of_entry);
 
diff --git a/scripts/mod/mk_elfconfig.c b/scripts/mod/mk_elfconfig.c
index 639bca7ba55..a4fd71d71d6 100644
--- a/scripts/mod/mk_elfconfig.c
+++ b/scripts/mod/mk_elfconfig.c
@@ -54,4 +54,3 @@ main(int argc, char **argv)
 
 	return 0;
 }
-
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index ea7f9530afa..9d9c5b905b3 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -862,7 +862,7 @@ static const char *section_white_list[] =
  * without "ax" / "aw".
  */
 static void check_section(const char *modname, struct elf_info *elf,
-                          Elf_Shdr *sechdr)
+			  Elf_Shdr *sechdr)
 {
 	const char *sec = sech_name(elf, sechdr);
 
@@ -1296,12 +1296,12 @@ static void print_section_list(const char * const list[20])
  */
 static void report_sec_mismatch(const char *modname,
 				const struct sectioncheck *mismatch,
-                                const char *fromsec,
-                                unsigned long long fromaddr,
-                                const char *fromsym,
-                                int from_is_func,
-                                const char *tosec, const char *tosym,
-                                int to_is_func)
+				const char *fromsec,
+				unsigned long long fromaddr,
+				const char *fromsym,
+				int from_is_func,
+				const char *tosec, const char *tosym,
+				int to_is_func)
 {
 	const char *from, *from_p;
 	const char *to, *to_p;
@@ -1441,7 +1441,7 @@ static void report_sec_mismatch(const char *modname,
 }
 
 static void check_section_mismatch(const char *modname, struct elf_info *elf,
-                                   Elf_Rela *r, Elf_Sym *sym, const char *fromsec)
+				   Elf_Rela *r, Elf_Sym *sym, const char *fromsec)
 {
 	const char *tosec;
 	const struct sectioncheck *mismatch;
@@ -1528,7 +1528,7 @@ static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
 	case R_ARM_ABS32:
 		/* From ARM ABI: (S + A) | T */
 		r->r_addend = (int)(long)
-		              (elf->symtab_start + ELF_R_SYM(r->r_info));
+			      (elf->symtab_start + ELF_R_SYM(r->r_info));
 		break;
 	case R_ARM_PC24:
 	case R_ARM_CALL:
@@ -1538,8 +1538,8 @@ static int addend_arm_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
 	case R_ARM_THM_JUMP19:
 		/* From ARM ABI: ((S + A) | T) - P */
 		r->r_addend = (int)(long)(elf->hdr +
-		              sechdr->sh_offset +
-		              (r->r_offset - sechdr->sh_addr));
+			      sechdr->sh_offset +
+			      (r->r_offset - sechdr->sh_addr));
 		break;
 	default:
 		return 1;
@@ -1571,7 +1571,7 @@ static int addend_mips_rel(struct elf_info *elf, Elf_Shdr *sechdr, Elf_Rela *r)
 }
 
 static void section_rela(const char *modname, struct elf_info *elf,
-                         Elf_Shdr *sechdr)
+			 Elf_Shdr *sechdr)
 {
 	Elf_Sym  *sym;
 	Elf_Rela *rela;
@@ -1615,7 +1615,7 @@ static void section_rela(const char *modname, struct elf_info *elf,
 }
 
 static void section_rel(const char *modname, struct elf_info *elf,
-                        Elf_Shdr *sechdr)
+			Elf_Shdr *sechdr)
 {
 	Elf_Sym *sym;
 	Elf_Rel *rel;
@@ -1685,7 +1685,7 @@ static void section_rel(const char *modname, struct elf_info *elf,
  * be discarded and warns about it.
  **/
 static void check_sec_ref(struct module *mod, const char *modname,
-                          struct elf_info *elf)
+			  struct elf_info *elf)
 {
 	int i;
 	Elf_Shdr *sechdrs = elf->sechdrs;
@@ -1945,7 +1945,7 @@ static int add_versions(struct buffer *b, struct module *mod)
 					     s->name, mod->name);
 				} else {
 					merror("\"%s\" [%s.ko] undefined!\n",
-					          s->name, mod->name);
+					       s->name, mod->name);
 					err = 1;
 				}
 			}
@@ -2113,8 +2113,10 @@ static void read_dump(const char *fname, unsigned int kernel)
 		s->preloaded = 1;
 		sym_update_crc(symname, mod, crc, export_no(export));
 	}
+	release_file(file, size);
 	return;
 fail:
+	release_file(file, size);
 	fatal("parse error in symbol dump file\n");
 }
 
diff --git a/scripts/mod/sumversion.c b/scripts/mod/sumversion.c
index deb2994b04c..944418da9fe 100644
--- a/scripts/mod/sumversion.c
+++ b/scripts/mod/sumversion.c
@@ -214,7 +214,7 @@ static void md4_final_ascii(struct md4_ctx *mctx, char *out, unsigned int len)
 	mctx->block[14] = mctx->byte_count << 3;
 	mctx->block[15] = mctx->byte_count >> 29;
 	le32_to_cpu_array(mctx->block, (sizeof(mctx->block) -
-	                  sizeof(uint64_t)) / sizeof(uint32_t));
+			  sizeof(uint64_t)) / sizeof(uint32_t));
 	md4_transform(mctx->hash, mctx->block);
 	cpu_to_le32_array(mctx->hash, sizeof(mctx->hash) / sizeof(uint32_t));
 
@@ -367,7 +367,7 @@ static int parse_source_files(const char *objfile, struct md4_ctx *md)
 			break;
 		/* Terminate line at first space, to get rid of final ' \' */
 		while (*p) {
-                       if (isspace(*p)) {
+			if (isspace(*p)) {
 				*p = '\0';
 				break;
 			}
diff --git a/scripts/objdiff b/scripts/objdiff
index b3e4f10bfc3..62e51dae213 100755
--- a/scripts/objdiff
+++ b/scripts/objdiff
@@ -25,25 +25,47 @@
 #
 # Note: 'make mrproper' will also remove .tmp_objdiff
 
-GIT_DIR="`git rev-parse --git-dir`"
+SRCTREE=$(cd $(git rev-parse --show-toplevel 2>/dev/null); pwd)
 
-if [ -d "$GIT_DIR" ]; then
-	TMPD="${GIT_DIR%git}tmp_objdiff"
-
-	[ -d "$TMPD" ] || mkdir "$TMPD"
-else
-	echo "ERROR: git directory not found."
+if [ -z "$SRCTREE" ]; then
+	echo >&2 "ERROR: Not a git repository."
 	exit 1
 fi
 
+TMPD=$SRCTREE/.tmp_objdiff
+
 usage() {
-	echo "Usage: $0 <command> <args>"
-	echo "  record    <list of object files>"
-	echo "  diff      <commitA> <commitB>"
-	echo "  clean     all | <commit>"
+	echo >&2 "Usage: $0 <command> <args>"
+	echo >&2 "  record    <list of object files or directories>"
+	echo >&2 "  diff      <commitA> <commitB>"
+	echo >&2 "  clean     all | <commit>"
 	exit 1
 }
 
+get_output_dir() {
+	dir=${1%/*}
+
+	if [ "$dir" = "$1" ]; then
+		dir=.
+	fi
+
+	dir=$(cd $dir; pwd)
+
+	echo $TMPD/$CMT${dir#$SRCTREE}
+}
+
+do_objdump() {
+	dir=$(get_output_dir $1)
+	base=${1##*/}
+	dis=$dir/${base%.o}.dis
+
+	[ ! -d "$dir" ] && mkdir -p $dir
+
+	# remove addresses for a cleaner diff
+	# http://dummdida.tumblr.com/post/60924060451/binary-diff-between-libc-from-scientificlinux-and
+	$OBJDUMP -D $1 | sed "s/^[[:space:]]\+[0-9a-f]\+//" > $dis
+}
+
 dorecord() {
 	[ $# -eq 0 ] && usage
 
@@ -52,20 +74,16 @@ dorecord() {
 	CMT="`git rev-parse --short HEAD`"
 
 	OBJDUMP="${CROSS_COMPILE}objdump"
-	OBJDIFFD="$TMPD/$CMT"
-
-	[ ! -d "$OBJDIFFD" ] && mkdir -p "$OBJDIFFD"
 
-	for f in $FILES; do
-		dn="${f%/*}"
-		bn="${f##*/}"
-
-		[ ! -d "$OBJDIFFD/$dn" ] && mkdir -p "$OBJDIFFD/$dn"
-
-		# remove addresses for a more clear diff
-		# http://dummdida.tumblr.com/post/60924060451/binary-diff-between-libc-from-scientificlinux-and
-		$OBJDUMP -D "$f" | sed "s/^[[:space:]]\+[0-9a-f]\+//" \
-			>"$OBJDIFFD/$dn/$bn"
+	for d in $FILES; do
+		if [ -d "$d" ]; then
+			for f in $(find $d -name '*.o')
+			do
+				do_objdump $f
+			done
+		else
+			do_objdump $d
+		fi
 	done
 }
 
@@ -90,12 +108,12 @@ dodiff() {
 	DSTD="$TMPD/$DST"
 
 	if [ ! -d "$SRCD" ]; then
-		echo "ERROR: $SRCD doesn't exist"
+		echo >&2 "ERROR: $SRCD doesn't exist"
 		exit 1
 	fi
 
 	if [ ! -d "$DSTD" ]; then
-		echo "ERROR: $DSTD doesn't exist"
+		echo >&2 "ERROR: $DSTD doesn't exist"
 		exit 1
 	fi
 
@@ -114,7 +132,7 @@ doclean() {
 		if [ -d "$TMPD/$CMT" ]; then
 			rm -rf $TMPD/$CMT
 		else
-			echo "$CMT not found"
+			echo >&2 "$CMT not found"
 		fi
 	fi
 }
@@ -135,7 +153,7 @@ case "$1" in
 		doclean $*
 		;;
 	*)
-		echo "Unrecognized command '$1'"
+		echo >&2 "Unrecognized command '$1'"
 		exit 1
 		;;
 esac
diff --git a/scripts/package/Makefile b/scripts/package/Makefile
index c5d47339381..99ca6e76eb0 100644
--- a/scripts/package/Makefile
+++ b/scripts/package/Makefile
@@ -143,4 +143,3 @@ help: FORCE
 	@echo '  perf-targz-src-pkg  - Build $(perf-tar).tar.gz source tarball'
 	@echo '  perf-tarbz2-src-pkg - Build $(perf-tar).tar.bz2 source tarball'
 	@echo '  perf-tarxz-src-pkg  - Build $(perf-tar).tar.xz source tarball'
-
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index f46e4dd0558..35d5a5877d0 100644
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -35,13 +35,15 @@ create_package() {
 	sparc*)
 		debarch=sparc ;;
 	s390*)
-		debarch=s390 ;;
+		debarch=s390$(grep -q CONFIG_64BIT=y $KCONFIG_CONFIG && echo x || true) ;;
 	ppc*)
 		debarch=powerpc ;;
 	parisc*)
 		debarch=hppa ;;
 	mips*)
 		debarch=mips$(grep -q CPU_LITTLE_ENDIAN=y $KCONFIG_CONFIG && echo el || true) ;;
+	arm64)
+		debarch=arm64 ;;
 	arm*)
 		debarch=arm$(grep -q CONFIG_AEABI=y $KCONFIG_CONFIG && echo el || true) ;;
 	*)
@@ -130,7 +132,7 @@ if [ "$ARCH" = "um" ] ; then
 	cp System.map "$tmpdir/usr/lib/uml/modules/$version/System.map"
 	cp $KCONFIG_CONFIG "$tmpdir/usr/share/doc/$packagename/config"
 	gzip "$tmpdir/usr/share/doc/$packagename/config"
-else 
+else
 	cp System.map "$tmpdir/boot/System.map-$version"
 	cp $KCONFIG_CONFIG "$tmpdir/boot/config-$version"
 fi
@@ -155,11 +157,11 @@ if grep -q '^CONFIG_MODULES=y' $KCONFIG_CONFIG ; then
 			for module in $(find lib/modules/ -name *.ko); do
 				mkdir -p $(dirname $dbg_dir/usr/lib/debug/$module)
 				# only keep debug symbols in the debug file
-				objcopy --only-keep-debug $module $dbg_dir/usr/lib/debug/$module
+				$OBJCOPY --only-keep-debug $module $dbg_dir/usr/lib/debug/$module
 				# strip original module from debug symbols
-				objcopy --strip-debug $module
+				$OBJCOPY --strip-debug $module
 				# then add a link to those
-				objcopy --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module
+				$OBJCOPY --add-gnu-debuglink=$dbg_dir/usr/lib/debug/$module $module
 			done
 		)
 	fi
@@ -287,14 +289,16 @@ EOF
 
 fi
 
-# Build header package
-(cd $srctree; find . -name Makefile\* -o -name Kconfig\* -o -name \*.pl > "$objtree/debian/hdrsrcfiles")
-(cd $srctree; find arch/$SRCARCH/include include scripts -type f >> "$objtree/debian/hdrsrcfiles")
-(cd $objtree; find arch/$SRCARCH/include Module.symvers include scripts -type f >> "$objtree/debian/hdrobjfiles")
+# Build kernel header package
+(cd $srctree; find . -name Makefile\* -o -name Kconfig\* -o -name \*.pl) > "$objtree/debian/hdrsrcfiles"
+(cd $srctree; find arch/$SRCARCH/include include scripts -type f) >> "$objtree/debian/hdrsrcfiles"
+(cd $srctree; find arch/$SRCARCH -name module.lds -o -name Kbuild.platforms -o -name Platform) >> "$objtree/debian/hdrsrcfiles"
+(cd $srctree; find $(find arch/$SRCARCH -name include -o -name scripts -type d) -type f) >> "$objtree/debian/hdrsrcfiles"
+(cd $objtree; find arch/$SRCARCH/include Module.symvers include scripts -type f) >> "$objtree/debian/hdrobjfiles"
 destdir=$kernel_headers_dir/usr/src/linux-headers-$version
 mkdir -p "$destdir"
-(cd $srctree; tar -c -f - -T "$objtree/debian/hdrsrcfiles") | (cd $destdir; tar -xf -)
-(cd $objtree; tar -c -f - -T "$objtree/debian/hdrobjfiles") | (cd $destdir; tar -xf -)
+(cd $srctree; tar -c -f - -T -) < "$objtree/debian/hdrsrcfiles" | (cd $destdir; tar -xf -)
+(cd $objtree; tar -c -f - -T -) < "$objtree/debian/hdrobjfiles" | (cd $destdir; tar -xf -)
 (cd $objtree; cp $KCONFIG_CONFIG $destdir/.config) # copy .config manually to be where it's expected to be
 ln -sf "/usr/src/linux-headers-$version" "$kernel_headers_dir/lib/modules/$version/build"
 rm -f "$objtree/debian/hdrsrcfiles" "$objtree/debian/hdrobjfiles"
diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index aa22f9447dd..e046bff3358 100644
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
@@ -125,15 +125,13 @@ esac
 # Create the tarball
 #
 (
-	cd "${tmpdir}"
 	opts=
 	if tar --owner=root --group=root --help >/dev/null 2>&1; then
 		opts="--owner=root --group=root"
 	fi
-	tar cf - boot/* lib/* $opts | ${compress} > "${tarball}${file_ext}"
+	tar cf - -C "$tmpdir" boot/ lib/ $opts | ${compress} > "${tarball}${file_ext}"
 )
 
 echo "Tarball successfully created in ${tarball}${file_ext}"
 
 exit 0
-
diff --git a/scripts/patch-kernel b/scripts/patch-kernel
index d000ea3a41f..49b4241e814 100755
--- a/scripts/patch-kernel
+++ b/scripts/patch-kernel
@@ -27,7 +27,7 @@
 #       Nick Holloway <Nick.Holloway@alfie.demon.co.uk>, 2nd January 1995.
 #
 # Added support for handling multiple types of compression. What includes
-# gzip, bzip, bzip2, zip, compress, and plaintext. 
+# gzip, bzip, bzip2, zip, compress, and plaintext.
 #
 #       Adam Sulmicki <adam@cfar.umd.edu>, 1st January 1997.
 #
@@ -159,7 +159,7 @@ applyPatch () {
   fi
   # Remove backup files
   find $sourcedir/ '(' -name '*.orig' -o -name '.*.orig' ')' -exec rm -f {} \;
- 
+
   return 0;
 }
 
diff --git a/scripts/pnmtologo.c b/scripts/pnmtologo.c
index 68bb4efc5af..4718d7895f0 100644
--- a/scripts/pnmtologo.c
+++ b/scripts/pnmtologo.c
@@ -512,4 +512,3 @@ int main(int argc, char *argv[])
     }
     exit(0);
 }
-
diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c
index e11aa4a156d..650ecc83d7d 100644
--- a/scripts/recordmcount.c
+++ b/scripts/recordmcount.c
@@ -487,5 +487,3 @@ main(int argc, char *argv[])
 	}
 	return !!n_error;
 }
-
-
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 9d1421e63ff..49b582a225b 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -163,11 +163,11 @@ static int mcount_adjust = 0;
 
 static int MIPS_is_fake_mcount(Elf_Rel const *rp)
 {
-	static Elf_Addr old_r_offset;
+	static Elf_Addr old_r_offset = ~(Elf_Addr)0;
 	Elf_Addr current_r_offset = _w(rp->r_offset);
 	int is_fake;
 
-	is_fake = old_r_offset &&
+	is_fake = (old_r_offset != ~(Elf_Addr)0) &&
 		(current_r_offset - old_r_offset == MIPS_FAKEMCOUNT_OFFSET);
 	old_r_offset = current_r_offset;
 
diff --git a/scripts/rt-tester/check-all.sh b/scripts/rt-tester/check-all.sh
index 43098afe743..6b5c83baf14 100644
--- a/scripts/rt-tester/check-all.sh
+++ b/scripts/rt-tester/check-all.sh
@@ -19,4 +19,3 @@ testit t3-l2-pi.tst
 testit t4-l2-pi-deboost.tst
 testit t5-l4-pi-boost-deboost.tst
 testit t5-l4-pi-boost-deboost-setsched.tst
-
diff --git a/scripts/rt-tester/rt-tester.py b/scripts/rt-tester/rt-tester.py
index 34186cac1d2..6d916c2a45a 100644
--- a/scripts/rt-tester/rt-tester.py
+++ b/scripts/rt-tester/rt-tester.py
@@ -216,5 +216,3 @@ while 1:
 # Normal exit pass
 print "Pass"
 sys.exit(0)
-
-
diff --git a/scripts/selinux/install_policy.sh b/scripts/selinux/install_policy.sh
index 7b9ccf61f8f..f6a0ce71015 100644
--- a/scripts/selinux/install_policy.sh
+++ b/scripts/selinux/install_policy.sh
@@ -66,4 +66,3 @@ if [ "eq$dodev" != "eq" ]; then
 	$SF file_contexts /dev
 	mount --move /mnt /dev
 fi
-
diff --git a/scripts/show_delta b/scripts/show_delta
index e25732b5d70..5b365009e6a 100755
--- a/scripts/show_delta
+++ b/scripts/show_delta
@@ -126,4 +126,3 @@ def main():
 		print (convert_line(line, base_time),)
 
 main()
-
diff --git a/scripts/tags.sh b/scripts/tags.sh
index f2c5b006a3d..e6b011fe1d0 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -25,6 +25,9 @@ else
 	tree=${srctree}/
 fi
 
+# ignore userspace tools
+ignore="$ignore ( -path ${tree}tools ) -prune -o"
+
 # Find all available archs
 find_all_archs()
 {
@@ -47,7 +50,8 @@ find_arch_sources()
 	for i in $archincludedir; do
 		prune="$prune -wholename $i -prune -o"
 	done
-	find ${tree}arch/$1 $ignore $subarchprune $prune -name "$2" -print;
+	find ${tree}arch/$1 $ignore $subarchprune $prune -name "$2" \
+		-not -type l -print;
 }
 
 # find sources in arch/$1/include
@@ -57,14 +61,15 @@ find_arch_include_sources()
 					-name include -type d -print);
 	if [ -n "$include" ]; then
 		archincludedir="$archincludedir $include"
-		find $include $ignore -name "$2" -print;
+		find $include $ignore -name "$2" -not -type l -print;
 	fi
 }
 
 # find sources in include/
 find_include_sources()
 {
-	find ${tree}include $ignore -name config -prune -o -name "$1" -print;
+	find ${tree}include $ignore -name config -prune -o -name "$1" \
+		-not -type l -print;
 }
 
 # find sources in rest of tree
@@ -73,7 +78,7 @@ find_other_sources()
 {
 	find ${tree}* $ignore \
 	     \( -name include -o -name arch -o -name '.tmp_*' \) -prune -o \
-	       -name "$1" -print;
+	       -name "$1" -not -type l -print;
 }
 
 find_sources()
@@ -187,6 +192,10 @@ exuberant()
 	--regex-c++='/TESTCLEARFLAG_FALSE\(([^,)]*).*/TestClearPage\1/' \
 	--regex-c++='/__TESTCLEARFLAG_FALSE\(([^,)]*).*/__TestClearPage\1/' \
 	--regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'		\
+	--regex-c++='/TESTPCGFLAG\(([^,)]*).*/PageCgroup\1/'		\
+	--regex-c++='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/'		\
+	--regex-c++='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/'	\
+	--regex-c++='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \
 	--regex-c='/PCI_OP_READ\((\w*).*[1-4]\)/pci_bus_read_config_\1/' \
 	--regex-c='/PCI_OP_WRITE\((\w*).*[1-4]\)/pci_bus_write_config_\1/' \
 	--regex-c='/DEFINE_(MUTEX|SEMAPHORE|SPINLOCK)\((\w*)/\2/v/'	\
@@ -201,7 +210,8 @@ exuberant()
 	--regex-c='/DECLARE_(TASKLET|WORK|DELAYED_WORK)\((\w*)/\2/v/'	\
 	--regex-c='/DEFINE_PCI_DEVICE_TABLE\((\w*)/\1/v/'		\
 	--regex-c='/(^\s)OFFSET\((\w*)/\2/v/'				\
-	--regex-c='/(^\s)DEFINE\((\w*)/\2/v/'
+	--regex-c='/(^\s)DEFINE\((\w*)/\2/v/'				\
+	--regex-c='/DEFINE_HASHTABLE\((\w*)/\1/v/'
 
 	all_kconfigs | xargs $1 -a                              \
 	--langdef=kconfig --language-force=kconfig              \
@@ -244,9 +254,14 @@ emacs()
 	--regex='/__CLEARPAGEFLAG_NOOP(\([^,)]*\).*/__ClearPage\1/' \
 	--regex='/TESTCLEARFLAG_FALSE(\([^,)]*\).*/TestClearPage\1/' \
 	--regex='/__TESTCLEARFLAG_FALSE(\([^,)]*\).*/__TestClearPage\1/' \
+	--regex='/TESTPCGFLAG\(([^,)]*).*/PageCgroup\1/'	\
+	--regex='/SETPCGFLAG\(([^,)]*).*/SetPageCgroup\1/'	\
+	--regex='/CLEARPCGFLAG\(([^,)]*).*/ClearPageCgroup\1/'	\
+	--regex='/TESTCLEARPCGFLAG\(([^,)]*).*/TestClearPageCgroup\1/' \
 	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'		\
 	--regex='/PCI_OP_READ(\([a-z]*[a-z]\).*[1-4])/pci_bus_read_config_\1/' \
-	--regex='/PCI_OP_WRITE(\([a-z]*[a-z]\).*[1-4])/pci_bus_write_config_\1/'
+	--regex='/PCI_OP_WRITE(\([a-z]*[a-z]\).*[1-4])/pci_bus_write_config_\1/'\
+	--regex='/DEFINE_HASHTABLE\((\w*)/\1/v/'
 
 	all_kconfigs | xargs $1 -a                              \
 	--regex='/^[ \t]*\(\(menu\)*config\)[ \t]+\([a-zA-Z0-9_]+\)/\3/'
@@ -266,7 +281,7 @@ xtags()
 		emacs $1
 	else
 		all_target_sources | xargs $1 -a
-        fi
+	fi
 }
 
 # Support um (which uses SUBARCH)
diff --git a/security/capability.c b/security/capability.c
index ad0d4de6994..e76373de312 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -879,7 +879,7 @@ static void cap_key_free(struct key *key)
 }
 
 static int cap_key_permission(key_ref_t key_ref, const struct cred *cred,
-			      key_perm_t perm)
+			      unsigned perm)
 {
 	return 0;
 }
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 9134dbf70d3..188c1d26393 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -182,7 +182,7 @@ static inline bool is_devcg_online(const struct dev_cgroup *devcg)
 static int devcgroup_online(struct cgroup_subsys_state *css)
 {
 	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
-	struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css_parent(css));
+	struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent);
 	int ret = 0;
 
 	mutex_lock(&devcgroup_mutex);
@@ -455,7 +455,7 @@ static bool verify_new_ex(struct dev_cgroup *dev_cgroup,
 static int parent_has_perm(struct dev_cgroup *childcg,
 				  struct dev_exception_item *ex)
 {
-	struct dev_cgroup *parent = css_to_devcgroup(css_parent(&childcg->css));
+	struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
 
 	if (!parent)
 		return 1;
@@ -476,7 +476,7 @@ static int parent_has_perm(struct dev_cgroup *childcg,
 static bool parent_allows_removal(struct dev_cgroup *childcg,
 				  struct dev_exception_item *ex)
 {
-	struct dev_cgroup *parent = css_to_devcgroup(css_parent(&childcg->css));
+	struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
 
 	if (!parent)
 		return true;
@@ -587,13 +587,6 @@ static int propagate_exception(struct dev_cgroup *devcg_root,
 	return rc;
 }
 
-static inline bool has_children(struct dev_cgroup *devcgroup)
-{
-	struct cgroup *cgrp = devcgroup->css.cgroup;
-
-	return !list_empty(&cgrp->children);
-}
-
 /*
  * Modify the exception list using allow/deny rules.
  * CAP_SYS_ADMIN is needed for this.  It's at least separate from CAP_MKNOD
@@ -614,7 +607,7 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	char temp[12];		/* 11 + 1 characters needed for a u32 */
 	int count, rc = 0;
 	struct dev_exception_item ex;
-	struct dev_cgroup *parent = css_to_devcgroup(css_parent(&devcgroup->css));
+	struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent);
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -626,7 +619,7 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	case 'a':
 		switch (filetype) {
 		case DEVCG_ALLOW:
-			if (has_children(devcgroup))
+			if (css_has_online_children(&devcgroup->css))
 				return -EINVAL;
 
 			if (!may_allow_all(parent))
@@ -642,7 +635,7 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 				return rc;
 			break;
 		case DEVCG_DENY:
-			if (has_children(devcgroup))
+			if (css_has_online_children(&devcgroup->css))
 				return -EINVAL;
 
 			dev_exception_clean(devcgroup);
@@ -767,27 +760,27 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 	return rc;
 }
 
-static int devcgroup_access_write(struct cgroup_subsys_state *css,
-				  struct cftype *cft, char *buffer)
+static ssize_t devcgroup_access_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
 {
 	int retval;
 
 	mutex_lock(&devcgroup_mutex);
-	retval = devcgroup_update_access(css_to_devcgroup(css),
-					 cft->private, buffer);
+	retval = devcgroup_update_access(css_to_devcgroup(of_css(of)),
+					 of_cft(of)->private, strstrip(buf));
 	mutex_unlock(&devcgroup_mutex);
-	return retval;
+	return retval ?: nbytes;
 }
 
 static struct cftype dev_cgroup_files[] = {
 	{
 		.name = "allow",
-		.write_string  = devcgroup_access_write,
+		.write = devcgroup_access_write,
 		.private = DEVCG_ALLOW,
 	},
 	{
 		.name = "deny",
-		.write_string = devcgroup_access_write,
+		.write = devcgroup_access_write,
 		.private = DEVCG_DENY,
 	},
 	{
@@ -803,7 +796,7 @@ struct cgroup_subsys devices_cgrp_subsys = {
 	.css_free = devcgroup_css_free,
 	.css_online = devcgroup_online,
 	.css_offline = devcgroup_offline,
-	.base_cftypes = dev_cgroup_files,
+	.legacy_cftypes = dev_cgroup_files,
 };
 
 /**
diff --git a/security/integrity/evm/Kconfig b/security/integrity/evm/Kconfig
index d35b4915b00..d606f3d12d6 100644
--- a/security/integrity/evm/Kconfig
+++ b/security/integrity/evm/Kconfig
@@ -12,15 +12,41 @@ config EVM
 
 	  If you are unsure how to answer this question, answer N.
 
-config EVM_HMAC_VERSION
-	int "EVM HMAC version"
+if EVM
+
+menu "EVM options"
+
+config EVM_ATTR_FSUUID
+	bool "FSUUID (version 2)"
+	default y
 	depends on EVM
-	default 2
 	help
-	  This options adds EVM HMAC version support.
-	  1 - original version
-	  2 - add per filesystem unique identifier (UUID) (default)
+	  Include filesystem UUID for HMAC calculation.
+
+	  Default value is 'selected', which is former version 2.
+	  if 'not selected', it is former version 1
 
-	  WARNING: changing the HMAC calculation method or adding 
+	  WARNING: changing the HMAC calculation method or adding
 	  additional info to the calculation, requires existing EVM
-	  labeled file systems to be relabeled.  
+	  labeled file systems to be relabeled.
+
+config EVM_EXTRA_SMACK_XATTRS
+	bool "Additional SMACK xattrs"
+	depends on EVM && SECURITY_SMACK
+	default n
+	help
+	  Include additional SMACK xattrs for HMAC calculation.
+
+	  In addition to the original security xattrs (eg. security.selinux,
+	  security.SMACK64, security.capability, and security.ima) included
+	  in the HMAC calculation, enabling this option includes newly defined
+	  Smack xattrs: security.SMACK64EXEC, security.SMACK64TRANSMUTE and
+	  security.SMACK64MMAP.
+
+	  WARNING: changing the HMAC calculation method or adding
+	  additional info to the calculation, requires existing EVM
+	  labeled file systems to be relabeled.
+
+endmenu
+
+endif
diff --git a/security/integrity/evm/evm.h b/security/integrity/evm/evm.h
index 37c88ddb3cf..88bfe77efa1 100644
--- a/security/integrity/evm/evm.h
+++ b/security/integrity/evm/evm.h
@@ -24,7 +24,10 @@
 extern int evm_initialized;
 extern char *evm_hmac;
 extern char *evm_hash;
-extern int evm_hmac_version;
+
+#define EVM_ATTR_FSUUID		0x0001
+
+extern int evm_hmac_attrs;
 
 extern struct crypto_shash *hmac_tfm;
 extern struct crypto_shash *hash_tfm;
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index 6b540f1822e..5e9687f02e1 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -112,7 +112,7 @@ static void hmac_add_misc(struct shash_desc *desc, struct inode *inode,
 	hmac_misc.gid = from_kgid(&init_user_ns, inode->i_gid);
 	hmac_misc.mode = inode->i_mode;
 	crypto_shash_update(desc, (const u8 *)&hmac_misc, sizeof(hmac_misc));
-	if (evm_hmac_version > 1)
+	if (evm_hmac_attrs & EVM_ATTR_FSUUID)
 		crypto_shash_update(desc, inode->i_sb->s_uuid,
 				    sizeof(inode->i_sb->s_uuid));
 	crypto_shash_final(desc, digest);
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 6e0bd933b6a..3bcb80df4d0 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -32,7 +32,7 @@ static char *integrity_status_msg[] = {
 };
 char *evm_hmac = "hmac(sha1)";
 char *evm_hash = "sha1";
-int evm_hmac_version = CONFIG_EVM_HMAC_VERSION;
+int evm_hmac_attrs;
 
 char *evm_config_xattrnames[] = {
 #ifdef CONFIG_SECURITY_SELINUX
@@ -40,6 +40,11 @@ char *evm_config_xattrnames[] = {
 #endif
 #ifdef CONFIG_SECURITY_SMACK
 	XATTR_NAME_SMACK,
+#ifdef CONFIG_EVM_EXTRA_SMACK_XATTRS
+	XATTR_NAME_SMACKEXEC,
+	XATTR_NAME_SMACKTRANSMUTE,
+	XATTR_NAME_SMACKMMAP,
+#endif
 #endif
 #ifdef CONFIG_IMA_APPRAISE
 	XATTR_NAME_IMA,
@@ -57,6 +62,14 @@ static int __init evm_set_fixmode(char *str)
 }
 __setup("evm=", evm_set_fixmode);
 
+static void __init evm_init_config(void)
+{
+#ifdef CONFIG_EVM_ATTR_FSUUID
+	evm_hmac_attrs |= EVM_ATTR_FSUUID;
+#endif
+	pr_info("HMAC attrs: 0x%x\n", evm_hmac_attrs);
+}
+
 static int evm_find_protected_xattrs(struct dentry *dentry)
 {
 	struct inode *inode = dentry->d_inode;
@@ -287,12 +300,20 @@ out:
  * @xattr_value: pointer to the new extended attribute value
  * @xattr_value_len: pointer to the new extended attribute value length
  *
- * Updating 'security.evm' requires CAP_SYS_ADMIN privileges and that
- * the current value is valid.
+ * Before allowing the 'security.evm' protected xattr to be updated,
+ * verify the existing value is valid.  As only the kernel should have
+ * access to the EVM encrypted key needed to calculate the HMAC, prevent
+ * userspace from writing HMAC value.  Writing 'security.evm' requires
+ * requires CAP_SYS_ADMIN privileges.
  */
 int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 		       const void *xattr_value, size_t xattr_value_len)
 {
+	const struct evm_ima_xattr_data *xattr_data = xattr_value;
+
+	if ((strcmp(xattr_name, XATTR_NAME_EVM) == 0)
+	    && (xattr_data->type == EVM_XATTR_HMAC))
+		return -EPERM;
 	return evm_protect_xattr(dentry, xattr_name, xattr_value,
 				 xattr_value_len);
 }
@@ -432,6 +453,8 @@ static int __init init_evm(void)
 {
 	int error;
 
+	evm_init_config();
+
 	error = evm_init_secfs();
 	if (error < 0) {
 		pr_info("Error registering secfs\n");
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index ba9e4d792dd..d9cd5ce14d2 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -199,6 +199,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 			    struct evm_ima_xattr_data **xattr_value,
 			    int *xattr_len)
 {
+	const char *audit_cause = "failed";
 	struct inode *inode = file_inode(file);
 	const char *filename = file->f_dentry->d_name.name;
 	int result = 0;
@@ -213,6 +214,12 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 	if (!(iint->flags & IMA_COLLECTED)) {
 		u64 i_version = file_inode(file)->i_version;
 
+		if (file->f_flags & O_DIRECT) {
+			audit_cause = "failed(directio)";
+			result = -EACCES;
+			goto out;
+		}
+
 		/* use default hash algorithm */
 		hash.hdr.algo = ima_hash_algo;
 
@@ -233,9 +240,10 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
 				result = -ENOMEM;
 		}
 	}
+out:
 	if (result)
 		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
-				    filename, "collect_data", "failed",
+				    filename, "collect_data", audit_cause,
 				    result, 0);
 	return result;
 }
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 291bf0f3a46..d3113d4aaa3 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -341,7 +341,7 @@ static int ima_protect_xattr(struct dentry *dentry, const char *xattr_name,
 	return 0;
 }
 
-static void ima_reset_appraise_flags(struct inode *inode)
+static void ima_reset_appraise_flags(struct inode *inode, int digsig)
 {
 	struct integrity_iint_cache *iint;
 
@@ -353,18 +353,22 @@ static void ima_reset_appraise_flags(struct inode *inode)
 		return;
 
 	iint->flags &= ~IMA_DONE_MASK;
+	if (digsig)
+		iint->flags |= IMA_DIGSIG;
 	return;
 }
 
 int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name,
 		       const void *xattr_value, size_t xattr_value_len)
 {
+	const struct evm_ima_xattr_data *xvalue = xattr_value;
 	int result;
 
 	result = ima_protect_xattr(dentry, xattr_name, xattr_value,
 				   xattr_value_len);
 	if (result == 1) {
-		ima_reset_appraise_flags(dentry->d_inode);
+		ima_reset_appraise_flags(dentry->d_inode,
+			 (xvalue->type == EVM_IMA_XATTR_DIGSIG) ? 1 : 0);
 		result = 0;
 	}
 	return result;
@@ -376,7 +380,7 @@ int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name)
 
 	result = ima_protect_xattr(dentry, xattr_name, NULL, 0);
 	if (result == 1) {
-		ima_reset_appraise_flags(dentry->d_inode);
+		ima_reset_appraise_flags(dentry->d_inode, 0);
 		result = 0;
 	}
 	return result;
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 1bde8e62776..ccd0ac8fa9a 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -27,6 +27,36 @@
 
 static struct crypto_shash *ima_shash_tfm;
 
+/**
+ * ima_kernel_read - read file content
+ *
+ * This is a function for reading file content instead of kernel_read().
+ * It does not perform locking checks to ensure it cannot be blocked.
+ * It does not perform security checks because it is irrelevant for IMA.
+ *
+ */
+static int ima_kernel_read(struct file *file, loff_t offset,
+			   char *addr, unsigned long count)
+{
+	mm_segment_t old_fs;
+	char __user *buf = addr;
+	ssize_t ret;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!file->f_op->read && !file->f_op->aio_read)
+		return -EINVAL;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, &offset);
+	else
+		ret = do_sync_read(file, buf, count, &offset);
+	set_fs(old_fs);
+	return ret;
+}
+
 int ima_init_crypto(void)
 {
 	long rc;
@@ -104,7 +134,7 @@ static int ima_calc_file_hash_tfm(struct file *file,
 	while (offset < i_size) {
 		int rbuf_len;
 
-		rbuf_len = kernel_read(file, offset, rbuf, PAGE_SIZE);
+		rbuf_len = ima_kernel_read(file, offset, rbuf, PAGE_SIZE);
 		if (rbuf_len < 0) {
 			rc = rbuf_len;
 			break;
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 52ac6cf41f8..09baa335ebc 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -81,7 +81,6 @@ static void ima_rdwr_violation_check(struct file *file)
 {
 	struct inode *inode = file_inode(file);
 	fmode_t mode = file->f_mode;
-	int must_measure;
 	bool send_tomtou = false, send_writers = false;
 	char *pathbuf = NULL;
 	const char *pathname;
@@ -92,18 +91,19 @@ static void ima_rdwr_violation_check(struct file *file)
 	mutex_lock(&inode->i_mutex);	/* file metadata: permissions, xattr */
 
 	if (mode & FMODE_WRITE) {
-		if (atomic_read(&inode->i_readcount) && IS_IMA(inode))
-			send_tomtou = true;
-		goto out;
+		if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) {
+			struct integrity_iint_cache *iint;
+			iint = integrity_iint_find(inode);
+			/* IMA_MEASURE is set from reader side */
+			if (iint && (iint->flags & IMA_MEASURE))
+				send_tomtou = true;
+		}
+	} else {
+		if ((atomic_read(&inode->i_writecount) > 0) &&
+		    ima_must_measure(inode, MAY_READ, FILE_CHECK))
+			send_writers = true;
 	}
 
-	must_measure = ima_must_measure(inode, MAY_READ, FILE_CHECK);
-	if (!must_measure)
-		goto out;
-
-	if (atomic_read(&inode->i_writecount) > 0)
-		send_writers = true;
-out:
 	mutex_unlock(&inode->i_mutex);
 
 	if (!send_tomtou && !send_writers)
@@ -214,8 +214,11 @@ static int process_measurement(struct file *file, const char *filename,
 		xattr_ptr = &xattr_value;
 
 	rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len);
-	if (rc != 0)
+	if (rc != 0) {
+		if (file->f_flags & O_DIRECT)
+			rc = (iint->flags & IMA_PERMIT_DIRECTIO) ? 0 : -EACCES;
 		goto out_digsig;
+	}
 
 	pathname = filename ?: ima_d_path(&file->f_path, &pathbuf);
 
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 93873a450ff..40a7488f672 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -353,7 +353,7 @@ enum {
 	Opt_obj_user, Opt_obj_role, Opt_obj_type,
 	Opt_subj_user, Opt_subj_role, Opt_subj_type,
 	Opt_func, Opt_mask, Opt_fsmagic, Opt_uid, Opt_fowner,
-	Opt_appraise_type, Opt_fsuuid
+	Opt_appraise_type, Opt_fsuuid, Opt_permit_directio
 };
 
 static match_table_t policy_tokens = {
@@ -375,6 +375,7 @@ static match_table_t policy_tokens = {
 	{Opt_uid, "uid=%s"},
 	{Opt_fowner, "fowner=%s"},
 	{Opt_appraise_type, "appraise_type=%s"},
+	{Opt_permit_directio, "permit_directio"},
 	{Opt_err, NULL}
 };
 
@@ -622,6 +623,9 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 			else
 				result = -EINVAL;
 			break;
+		case Opt_permit_directio:
+			entry->flags |= IMA_PERMIT_DIRECTIO;
+			break;
 		case Opt_err:
 			ima_log_string(ab, "UNKNOWN", p);
 			result = -EINVAL;
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index 2fb5e53e927..33c0a70f6b1 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -30,6 +30,7 @@
 #define IMA_ACTION_FLAGS	0xff000000
 #define IMA_DIGSIG		0x01000000
 #define IMA_DIGSIG_REQUIRED	0x02000000
+#define IMA_PERMIT_DIRECTIO	0x04000000
 
 #define IMA_DO_MASK		(IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \
 				 IMA_APPRAISE_SUBMASK)
diff --git a/security/keys/gc.c b/security/keys/gc.c
index d3222b6d7d5..9609a7f0fae 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -92,15 +92,6 @@ static void key_gc_timer_func(unsigned long data)
 }
 
 /*
- * wait_on_bit() sleep function for uninterruptible waiting
- */
-static int key_gc_wait_bit(void *flags)
-{
-	schedule();
-	return 0;
-}
-
-/*
  * Reap keys of dead type.
  *
  * We use three flags to make sure we see three complete cycles of the garbage
@@ -123,7 +114,7 @@ void key_gc_keytype(struct key_type *ktype)
 	schedule_work(&key_gc_work);
 
 	kdebug("sleep");
-	wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE, key_gc_wait_bit,
+	wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE,
 		    TASK_UNINTERRUPTIBLE);
 
 	key_gc_dead_keytype = NULL;
diff --git a/security/keys/internal.h b/security/keys/internal.h
index 80b2aac4f50..5f20da01fd8 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -176,20 +176,11 @@ extern int key_task_permission(const key_ref_t key_ref,
 /*
  * Check to see whether permission is granted to use a key in the desired way.
  */
-static inline int key_permission(const key_ref_t key_ref, key_perm_t perm)
+static inline int key_permission(const key_ref_t key_ref, unsigned perm)
 {
 	return key_task_permission(key_ref, current_cred(), perm);
 }
 
-/* required permissions */
-#define	KEY_VIEW	0x01	/* require permission to view attributes */
-#define	KEY_READ	0x02	/* require permission to read content */
-#define	KEY_WRITE	0x04	/* require permission to update / modify */
-#define	KEY_SEARCH	0x08	/* require permission to search (keyring) or find (key) */
-#define	KEY_LINK	0x10	/* require permission to link */
-#define	KEY_SETATTR	0x20	/* require permission to change attributes */
-#define	KEY_ALL		0x3f	/* all the above permissions */
-
 /*
  * Authorisation record for request_key().
  */
diff --git a/security/keys/key.c b/security/keys/key.c
index 6e21c11e48b..2048a110e7f 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -714,7 +714,7 @@ static inline key_ref_t __key_update(key_ref_t key_ref,
 	int ret;
 
 	/* need write permission on the key to update it */
-	ret = key_permission(key_ref, KEY_WRITE);
+	ret = key_permission(key_ref, KEY_NEED_WRITE);
 	if (ret < 0)
 		goto error;
 
@@ -838,7 +838,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref,
 
 	/* if we're going to allocate a new key, we're going to have
 	 * to modify the keyring */
-	ret = key_permission(keyring_ref, KEY_WRITE);
+	ret = key_permission(keyring_ref, KEY_NEED_WRITE);
 	if (ret < 0) {
 		key_ref = ERR_PTR(ret);
 		goto error_link_end;
@@ -928,7 +928,7 @@ int key_update(key_ref_t key_ref, const void *payload, size_t plen)
 	key_check(key);
 
 	/* the key must be writable */
-	ret = key_permission(key_ref, KEY_WRITE);
+	ret = key_permission(key_ref, KEY_NEED_WRITE);
 	if (ret < 0)
 		goto error;
 
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index cee72ce6422..cd5bd0cef25 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -111,7 +111,7 @@ SYSCALL_DEFINE5(add_key, const char __user *, _type,
 	}
 
 	/* find the target keyring (which must be writable) */
-	keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_WRITE);
+	keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
 	if (IS_ERR(keyring_ref)) {
 		ret = PTR_ERR(keyring_ref);
 		goto error3;
@@ -195,7 +195,7 @@ SYSCALL_DEFINE4(request_key, const char __user *, _type,
 	dest_ref = NULL;
 	if (destringid) {
 		dest_ref = lookup_user_key(destringid, KEY_LOOKUP_CREATE,
-					   KEY_WRITE);
+					   KEY_NEED_WRITE);
 		if (IS_ERR(dest_ref)) {
 			ret = PTR_ERR(dest_ref);
 			goto error3;
@@ -253,7 +253,7 @@ long keyctl_get_keyring_ID(key_serial_t id, int create)
 	long ret;
 
 	lflags = create ? KEY_LOOKUP_CREATE : 0;
-	key_ref = lookup_user_key(id, lflags, KEY_SEARCH);
+	key_ref = lookup_user_key(id, lflags, KEY_NEED_SEARCH);
 	if (IS_ERR(key_ref)) {
 		ret = PTR_ERR(key_ref);
 		goto error;
@@ -334,7 +334,7 @@ long keyctl_update_key(key_serial_t id,
 	}
 
 	/* find the target key (which must be writable) */
-	key_ref = lookup_user_key(id, 0, KEY_WRITE);
+	key_ref = lookup_user_key(id, 0, KEY_NEED_WRITE);
 	if (IS_ERR(key_ref)) {
 		ret = PTR_ERR(key_ref);
 		goto error2;
@@ -365,12 +365,12 @@ long keyctl_revoke_key(key_serial_t id)
 	key_ref_t key_ref;
 	long ret;
 
-	key_ref = lookup_user_key(id, 0, KEY_WRITE);
+	key_ref = lookup_user_key(id, 0, KEY_NEED_WRITE);
 	if (IS_ERR(key_ref)) {
 		ret = PTR_ERR(key_ref);
 		if (ret != -EACCES)
 			goto error;
-		key_ref = lookup_user_key(id, 0, KEY_SETATTR);
+		key_ref = lookup_user_key(id, 0, KEY_NEED_SETATTR);
 		if (IS_ERR(key_ref)) {
 			ret = PTR_ERR(key_ref);
 			goto error;
@@ -401,7 +401,7 @@ long keyctl_invalidate_key(key_serial_t id)
 
 	kenter("%d", id);
 
-	key_ref = lookup_user_key(id, 0, KEY_SEARCH);
+	key_ref = lookup_user_key(id, 0, KEY_NEED_SEARCH);
 	if (IS_ERR(key_ref)) {
 		ret = PTR_ERR(key_ref);
 		goto error;
@@ -428,7 +428,7 @@ long keyctl_keyring_clear(key_serial_t ringid)
 	key_ref_t keyring_ref;
 	long ret;
 
-	keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_WRITE);
+	keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
 	if (IS_ERR(keyring_ref)) {
 		ret = PTR_ERR(keyring_ref);
 
@@ -470,13 +470,13 @@ long keyctl_keyring_link(key_serial_t id, key_serial_t ringid)
 	key_ref_t keyring_ref, key_ref;
 	long ret;
 
-	keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_WRITE);
+	keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
 	if (IS_ERR(keyring_ref)) {
 		ret = PTR_ERR(keyring_ref);
 		goto error;
 	}
 
-	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_LINK);
+	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_NEED_LINK);
 	if (IS_ERR(key_ref)) {
 		ret = PTR_ERR(key_ref);
 		goto error2;
@@ -505,7 +505,7 @@ long keyctl_keyring_unlink(key_serial_t id, key_serial_t ringid)
 	key_ref_t keyring_ref, key_ref;
 	long ret;
 
-	keyring_ref = lookup_user_key(ringid, 0, KEY_WRITE);
+	keyring_ref = lookup_user_key(ringid, 0, KEY_NEED_WRITE);
 	if (IS_ERR(keyring_ref)) {
 		ret = PTR_ERR(keyring_ref);
 		goto error;
@@ -548,7 +548,7 @@ long keyctl_describe_key(key_serial_t keyid,
 	char *tmpbuf;
 	long ret;
 
-	key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_VIEW);
+	key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_NEED_VIEW);
 	if (IS_ERR(key_ref)) {
 		/* viewing a key under construction is permitted if we have the
 		 * authorisation token handy */
@@ -639,7 +639,7 @@ long keyctl_keyring_search(key_serial_t ringid,
 	}
 
 	/* get the keyring at which to begin the search */
-	keyring_ref = lookup_user_key(ringid, 0, KEY_SEARCH);
+	keyring_ref = lookup_user_key(ringid, 0, KEY_NEED_SEARCH);
 	if (IS_ERR(keyring_ref)) {
 		ret = PTR_ERR(keyring_ref);
 		goto error2;
@@ -649,7 +649,7 @@ long keyctl_keyring_search(key_serial_t ringid,
 	dest_ref = NULL;
 	if (destringid) {
 		dest_ref = lookup_user_key(destringid, KEY_LOOKUP_CREATE,
-					   KEY_WRITE);
+					   KEY_NEED_WRITE);
 		if (IS_ERR(dest_ref)) {
 			ret = PTR_ERR(dest_ref);
 			goto error3;
@@ -676,7 +676,7 @@ long keyctl_keyring_search(key_serial_t ringid,
 
 	/* link the resulting key to the destination keyring if we can */
 	if (dest_ref) {
-		ret = key_permission(key_ref, KEY_LINK);
+		ret = key_permission(key_ref, KEY_NEED_LINK);
 		if (ret < 0)
 			goto error6;
 
@@ -727,7 +727,7 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen)
 	key = key_ref_to_ptr(key_ref);
 
 	/* see if we can read it directly */
-	ret = key_permission(key_ref, KEY_READ);
+	ret = key_permission(key_ref, KEY_NEED_READ);
 	if (ret == 0)
 		goto can_read_key;
 	if (ret != -EACCES)
@@ -799,7 +799,7 @@ long keyctl_chown_key(key_serial_t id, uid_t user, gid_t group)
 		goto error;
 
 	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL,
-				  KEY_SETATTR);
+				  KEY_NEED_SETATTR);
 	if (IS_ERR(key_ref)) {
 		ret = PTR_ERR(key_ref);
 		goto error;
@@ -905,7 +905,7 @@ long keyctl_setperm_key(key_serial_t id, key_perm_t perm)
 		goto error;
 
 	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL,
-				  KEY_SETATTR);
+				  KEY_NEED_SETATTR);
 	if (IS_ERR(key_ref)) {
 		ret = PTR_ERR(key_ref);
 		goto error;
@@ -947,7 +947,7 @@ static long get_instantiation_keyring(key_serial_t ringid,
 
 	/* if a specific keyring is nominated by ID, then use that */
 	if (ringid > 0) {
-		dkref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_WRITE);
+		dkref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
 		if (IS_ERR(dkref))
 			return PTR_ERR(dkref);
 		*_dest_keyring = key_ref_to_ptr(dkref);
@@ -1315,7 +1315,7 @@ long keyctl_set_timeout(key_serial_t id, unsigned timeout)
 	long ret;
 
 	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL,
-				  KEY_SETATTR);
+				  KEY_NEED_SETATTR);
 	if (IS_ERR(key_ref)) {
 		/* setting the timeout on a key under construction is permitted
 		 * if we have the authorisation token handy */
@@ -1418,7 +1418,7 @@ long keyctl_get_security(key_serial_t keyid,
 	char *context;
 	long ret;
 
-	key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_VIEW);
+	key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_NEED_VIEW);
 	if (IS_ERR(key_ref)) {
 		if (PTR_ERR(key_ref) != -EACCES)
 			return PTR_ERR(key_ref);
@@ -1482,7 +1482,7 @@ long keyctl_session_to_parent(void)
 	struct cred *cred;
 	int ret;
 
-	keyring_r = lookup_user_key(KEY_SPEC_SESSION_KEYRING, 0, KEY_LINK);
+	keyring_r = lookup_user_key(KEY_SPEC_SESSION_KEYRING, 0, KEY_NEED_LINK);
 	if (IS_ERR(keyring_r))
 		return PTR_ERR(keyring_r);
 
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index 2fb2576dc64..9cf2575f0d9 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -541,7 +541,7 @@ static int keyring_search_iterator(const void *object, void *iterator_data)
 	/* key must have search permissions */
 	if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
 	    key_task_permission(make_key_ref(key, ctx->possessed),
-				ctx->cred, KEY_SEARCH) < 0) {
+				ctx->cred, KEY_NEED_SEARCH) < 0) {
 		ctx->result = ERR_PTR(-EACCES);
 		kleave(" = %d [!perm]", ctx->skipped_ret);
 		goto skipped;
@@ -721,7 +721,7 @@ ascend_to_node:
 		/* Search a nested keyring */
 		if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
 		    key_task_permission(make_key_ref(key, ctx->possessed),
-					ctx->cred, KEY_SEARCH) < 0)
+					ctx->cred, KEY_NEED_SEARCH) < 0)
 			continue;
 
 		/* stack the current position */
@@ -843,7 +843,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref,
 		return ERR_PTR(-ENOTDIR);
 
 	if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) {
-		err = key_task_permission(keyring_ref, ctx->cred, KEY_SEARCH);
+		err = key_task_permission(keyring_ref, ctx->cred, KEY_NEED_SEARCH);
 		if (err < 0)
 			return ERR_PTR(err);
 	}
@@ -973,7 +973,7 @@ struct key *find_keyring_by_name(const char *name, bool skip_perm_check)
 
 			if (!skip_perm_check &&
 			    key_permission(make_key_ref(keyring, 0),
-					   KEY_SEARCH) < 0)
+					   KEY_NEED_SEARCH) < 0)
 				continue;
 
 			/* we've got a match but we might end up racing with
diff --git a/security/keys/permission.c b/security/keys/permission.c
index efcc0c855a0..732cc0beffd 100644
--- a/security/keys/permission.c
+++ b/security/keys/permission.c
@@ -28,7 +28,7 @@
  * permissions bits or the LSM check.
  */
 int key_task_permission(const key_ref_t key_ref, const struct cred *cred,
-			key_perm_t perm)
+			unsigned perm)
 {
 	struct key *key;
 	key_perm_t kperm;
@@ -68,7 +68,7 @@ use_these_perms:
 	if (is_key_possessed(key_ref))
 		kperm |= key->perm >> 24;
 
-	kperm = kperm & perm & KEY_ALL;
+	kperm = kperm & perm & KEY_NEED_ALL;
 
 	if (kperm != perm)
 		return -EACCES;
diff --git a/security/keys/persistent.c b/security/keys/persistent.c
index 0ad3ee28378..c9fae5ea89f 100644
--- a/security/keys/persistent.c
+++ b/security/keys/persistent.c
@@ -108,7 +108,7 @@ static long key_get_persistent(struct user_namespace *ns, kuid_t uid,
 	return PTR_ERR(persistent_ref);
 
 found:
-	ret = key_task_permission(persistent_ref, current_cred(), KEY_LINK);
+	ret = key_task_permission(persistent_ref, current_cred(), KEY_NEED_LINK);
 	if (ret == 0) {
 		persistent = key_ref_to_ptr(persistent_ref);
 		ret = key_link(key_ref_to_ptr(dest_ref), persistent);
@@ -151,7 +151,7 @@ long keyctl_get_persistent(uid_t _uid, key_serial_t destid)
 	}
 
 	/* There must be a destination keyring */
-	dest_ref = lookup_user_key(destid, KEY_LOOKUP_CREATE, KEY_WRITE);
+	dest_ref = lookup_user_key(destid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
 	if (IS_ERR(dest_ref))
 		return PTR_ERR(dest_ref);
 	if (key_ref_to_ptr(dest_ref)->type != &key_type_keyring) {
diff --git a/security/keys/proc.c b/security/keys/proc.c
index 88e9a466940..d3f6f2fd21d 100644
--- a/security/keys/proc.c
+++ b/security/keys/proc.c
@@ -218,7 +218,7 @@ static int proc_keys_show(struct seq_file *m, void *v)
 	 * - the caller holds a spinlock, and thus the RCU read lock, making our
 	 *   access to __current_cred() safe
 	 */
-	rc = key_task_permission(key_ref, ctx.cred, KEY_VIEW);
+	rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW);
 	if (rc < 0)
 		return 0;
 
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 381411941cc..26a94f18af9 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -21,24 +21,6 @@
 
 #define key_negative_timeout	60	/* default timeout on a negative key's existence */
 
-/*
- * wait_on_bit() sleep function for uninterruptible waiting
- */
-static int key_wait_bit(void *flags)
-{
-	schedule();
-	return 0;
-}
-
-/*
- * wait_on_bit() sleep function for interruptible waiting
- */
-static int key_wait_bit_intr(void *flags)
-{
-	schedule();
-	return signal_pending(current) ? -ERESTARTSYS : 0;
-}
-
 /**
  * complete_request_key - Complete the construction of a key.
  * @cons: The key construction record.
@@ -592,10 +574,9 @@ int wait_for_key_construction(struct key *key, bool intr)
 	int ret;
 
 	ret = wait_on_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT,
-			  intr ? key_wait_bit_intr : key_wait_bit,
 			  intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
-	if (ret < 0)
-		return ret;
+	if (ret)
+		return -ERESTARTSYS;
 	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
 		smp_rmb();
 		return key->type_data.reject_error;
diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c
index 8c0af08760c..b68faa1a5cf 100644
--- a/security/keys/sysctl.c
+++ b/security/keys/sysctl.c
@@ -15,7 +15,7 @@
 
 static const int zero, one = 1, max = INT_MAX;
 
-ctl_table key_sysctls[] = {
+struct ctl_table key_sysctls[] = {
 	{
 		.procname = "maxkeys",
 		.data = &key_quota_maxkeys,
diff --git a/security/security.c b/security/security.c
index 8b774f362a3..31614e9e96e 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1425,7 +1425,7 @@ void security_key_free(struct key *key)
 }
 
 int security_key_permission(key_ref_t key_ref,
-			    const struct cred *cred, key_perm_t perm)
+			    const struct cred *cred, unsigned perm)
 {
 	return security_ops->key_permission(key_ref, cred, perm);
 }
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index fc3e6628a86..a18f1fa6440 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -444,11 +444,15 @@ static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
 	avc_dump_query(ab, ad->selinux_audit_data->ssid,
 			   ad->selinux_audit_data->tsid,
 			   ad->selinux_audit_data->tclass);
+	if (ad->selinux_audit_data->denied) {
+		audit_log_format(ab, " permissive=%u",
+				 ad->selinux_audit_data->result ? 0 : 1);
+	}
 }
 
 /* This is the slow part of avc audit with big stack footprint */
 noinline int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
-		u32 requested, u32 audited, u32 denied,
+		u32 requested, u32 audited, u32 denied, int result,
 		struct common_audit_data *a,
 		unsigned flags)
 {
@@ -477,6 +481,7 @@ noinline int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
 	sad.tsid = tsid;
 	sad.audited = audited;
 	sad.denied = denied;
+	sad.result = result;
 
 	a->selinux_audit_data = &sad;
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 2c7341dbc5d..83d06db34d0 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2123,11 +2123,13 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 		new_tsec->exec_sid = 0;
 
 		/*
-		 * Minimize confusion: if no_new_privs and a transition is
-		 * explicitly requested, then fail the exec.
+		 * Minimize confusion: if no_new_privs or nosuid and a
+		 * transition is explicitly requested, then fail the exec.
 		 */
 		if (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)
 			return -EPERM;
+		if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
+			return -EACCES;
 	} else {
 		/* Check for a default transition on this program. */
 		rc = security_transition_sid(old_tsec->sid, isec->sid,
@@ -2770,6 +2772,7 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct nameidata *na
 
 static noinline int audit_inode_permission(struct inode *inode,
 					   u32 perms, u32 audited, u32 denied,
+					   int result,
 					   unsigned flags)
 {
 	struct common_audit_data ad;
@@ -2780,7 +2783,7 @@ static noinline int audit_inode_permission(struct inode *inode,
 	ad.u.inode = inode;
 
 	rc = slow_avc_audit(current_sid(), isec->sid, isec->sclass, perms,
-			    audited, denied, &ad, flags);
+			    audited, denied, result, &ad, flags);
 	if (rc)
 		return rc;
 	return 0;
@@ -2822,7 +2825,7 @@ static int selinux_inode_permission(struct inode *inode, int mask)
 	if (likely(!audited))
 		return rc;
 
-	rc2 = audit_inode_permission(inode, perms, audited, denied, flags);
+	rc2 = audit_inode_permission(inode, perms, audited, denied, rc, flags);
 	if (rc2)
 		return rc2;
 	return rc;
@@ -5722,7 +5725,7 @@ static void selinux_key_free(struct key *k)
 
 static int selinux_key_permission(key_ref_t key_ref,
 				  const struct cred *cred,
-				  key_perm_t perm)
+				  unsigned perm)
 {
 	struct key *key;
 	struct key_security_struct *ksec;
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
index f53ee3c58d0..ddf8eec03f2 100644
--- a/security/selinux/include/avc.h
+++ b/security/selinux/include/avc.h
@@ -102,7 +102,7 @@ static inline u32 avc_audit_required(u32 requested,
 }
 
 int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
-		   u32 requested, u32 audited, u32 denied,
+		   u32 requested, u32 audited, u32 denied, int result,
 		   struct common_audit_data *a,
 		   unsigned flags);
 
@@ -137,7 +137,7 @@ static inline int avc_audit(u32 ssid, u32 tsid,
 	if (likely(!audited))
 		return 0;
 	return slow_avc_audit(ssid, tsid, tclass,
-			      requested, audited, denied,
+			      requested, audited, denied, result,
 			      a, 0);
 }
 
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index 14d04e63b1f..be491a74c1e 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -147,7 +147,7 @@ struct security_class_mapping secclass_map[] = {
 	{ "peer", { "recv", NULL } },
 	{ "capability2",
 	  { "mac_override", "mac_admin", "syslog", "wake_alarm", "block_suspend",
-	    NULL } },
+	    "audit_read", NULL } },
 	{ "kernel_service", { "use_as_override", "create_files_as", NULL } },
 	{ "tun_socket",
 	  { COMMON_SOCK_PERMS, "attach_queue", NULL } },
diff --git a/security/selinux/ss/hashtab.c b/security/selinux/ss/hashtab.c
index 933e735bb18..2cc49614984 100644
--- a/security/selinux/ss/hashtab.c
+++ b/security/selinux/ss/hashtab.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
+#include <linux/sched.h>
 #include "hashtab.h"
 
 struct hashtab *hashtab_create(u32 (*hash_value)(struct hashtab *h, const void *key),
@@ -40,6 +41,8 @@ int hashtab_insert(struct hashtab *h, void *key, void *datum)
 	u32 hvalue;
 	struct hashtab_node *prev, *cur, *newnode;
 
+	cond_resched();
+
 	if (!h || h->nel == HASHTAB_MAX_NODES)
 		return -EINVAL;
 
diff --git a/security/selinux/ss/mls.c b/security/selinux/ss/mls.c
index c85bc1ec040..d307b37ddc2 100644
--- a/security/selinux/ss/mls.c
+++ b/security/selinux/ss/mls.c
@@ -492,6 +492,8 @@ int mls_convert_context(struct policydb *oldp,
 			rc = ebitmap_set_bit(&bitmap, catdatum->value - 1, 1);
 			if (rc)
 				return rc;
+
+			cond_resched();
 		}
 		ebitmap_destroy(&c->range.level[l].cat);
 		c->range.level[l].cat = bitmap;
diff --git a/security/smack/smack.h b/security/smack/smack.h
index d072fd32212..020307ef097 100644
--- a/security/smack/smack.h
+++ b/security/smack/smack.h
@@ -80,8 +80,8 @@ struct superblock_smack {
 
 struct socket_smack {
 	struct smack_known	*smk_out;	/* outbound label */
-	char			*smk_in;	/* inbound label */
-	char			*smk_packet;	/* TCP peer label */
+	struct smack_known	*smk_in;	/* inbound label */
+	struct smack_known	*smk_packet;	/* TCP peer label */
 };
 
 /*
@@ -133,7 +133,7 @@ struct smk_port_label {
 	struct list_head	list;
 	struct sock		*smk_sock;	/* socket initialized on */
 	unsigned short		smk_port;	/* the port number */
-	char			*smk_in;	/* incoming label */
+	struct smack_known	*smk_in;	/* inbound label */
 	struct smack_known	*smk_out;	/* outgoing label */
 };
 
@@ -177,6 +177,14 @@ struct smk_port_label {
 #define SMACK_CIPSO_MAXCATNUM           184     /* 23 * 8 */
 
 /*
+ * Ptrace rules
+ */
+#define SMACK_PTRACE_DEFAULT	0
+#define SMACK_PTRACE_EXACT	1
+#define SMACK_PTRACE_DRACONIAN	2
+#define SMACK_PTRACE_MAX	SMACK_PTRACE_DRACONIAN
+
+/*
  * Flags for untraditional access modes.
  * It shouldn't be necessary to avoid conflicts with definitions
  * in fs.h, but do so anyway.
@@ -225,6 +233,7 @@ struct inode_smack *new_inode_smack(char *);
  */
 int smk_access_entry(char *, char *, struct list_head *);
 int smk_access(struct smack_known *, char *, int, struct smk_audit_info *);
+int smk_tskacc(struct task_smack *, char *, u32, struct smk_audit_info *);
 int smk_curacc(char *, u32, struct smk_audit_info *);
 struct smack_known *smack_from_secid(const u32);
 char *smk_parse_smack(const char *string, int len);
@@ -244,6 +253,7 @@ extern struct smack_known *smack_net_ambient;
 extern struct smack_known *smack_onlycap;
 extern struct smack_known *smack_syslog_label;
 extern const char *smack_cipso_option;
+extern int smack_ptrace_rule;
 
 extern struct smack_known smack_known_floor;
 extern struct smack_known smack_known_hat;
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c
index 14293cd9b1e..c062e9467b6 100644
--- a/security/smack/smack_access.c
+++ b/security/smack/smack_access.c
@@ -192,20 +192,21 @@ out_audit:
 }
 
 /**
- * smk_curacc - determine if current has a specific access to an object
+ * smk_tskacc - determine if a task has a specific access to an object
+ * @tsp: a pointer to the subject task
  * @obj_label: a pointer to the object's Smack label
  * @mode: the access requested, in "MAY" format
  * @a : common audit data
  *
- * This function checks the current subject label/object label pair
+ * This function checks the subject task's label/object label pair
  * in the access rule list and returns 0 if the access is permitted,
- * non zero otherwise. It allows that current may have the capability
+ * non zero otherwise. It allows that the task may have the capability
  * to override the rules.
  */
-int smk_curacc(char *obj_label, u32 mode, struct smk_audit_info *a)
+int smk_tskacc(struct task_smack *subject, char *obj_label,
+	       u32 mode, struct smk_audit_info *a)
 {
-	struct task_smack *tsp = current_security();
-	struct smack_known *skp = smk_of_task(tsp);
+	struct smack_known *skp = smk_of_task(subject);
 	int may;
 	int rc;
 
@@ -219,7 +220,7 @@ int smk_curacc(char *obj_label, u32 mode, struct smk_audit_info *a)
 		 * it can further restrict access.
 		 */
 		may = smk_access_entry(skp->smk_known, obj_label,
-					&tsp->smk_rules);
+					&subject->smk_rules);
 		if (may < 0)
 			goto out_audit;
 		if ((mode & may) == mode)
@@ -241,6 +242,24 @@ out_audit:
 	return rc;
 }
 
+/**
+ * smk_curacc - determine if current has a specific access to an object
+ * @obj_label: a pointer to the object's Smack label
+ * @mode: the access requested, in "MAY" format
+ * @a : common audit data
+ *
+ * This function checks the current subject label/object label pair
+ * in the access rule list and returns 0 if the access is permitted,
+ * non zero otherwise. It allows that current may have the capability
+ * to override the rules.
+ */
+int smk_curacc(char *obj_label, u32 mode, struct smk_audit_info *a)
+{
+	struct task_smack *tsp = current_security();
+
+	return smk_tskacc(tsp, obj_label, mode, a);
+}
+
 #ifdef CONFIG_AUDIT
 /**
  * smack_str_from_perm : helper to transalate an int to a
@@ -285,7 +304,10 @@ static void smack_log_callback(struct audit_buffer *ab, void *a)
 	audit_log_untrustedstring(ab, sad->subject);
 	audit_log_format(ab, " object=");
 	audit_log_untrustedstring(ab, sad->object);
-	audit_log_format(ab, " requested=%s", sad->request);
+	if (sad->request[0] == '\0')
+		audit_log_format(ab, " labels_differ");
+	else
+		audit_log_format(ab, " requested=%s", sad->request);
 }
 
 /**
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 14f52be78c7..f2c30801ce4 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -157,6 +157,74 @@ static int smk_copy_rules(struct list_head *nhead, struct list_head *ohead,
 	return rc;
 }
 
+/**
+ * smk_ptrace_mode - helper function for converting PTRACE_MODE_* into MAY_*
+ * @mode - input mode in form of PTRACE_MODE_*
+ *
+ * Returns a converted MAY_* mode usable by smack rules
+ */
+static inline unsigned int smk_ptrace_mode(unsigned int mode)
+{
+	switch (mode) {
+	case PTRACE_MODE_READ:
+		return MAY_READ;
+	case PTRACE_MODE_ATTACH:
+		return MAY_READWRITE;
+	}
+
+	return 0;
+}
+
+/**
+ * smk_ptrace_rule_check - helper for ptrace access
+ * @tracer: tracer process
+ * @tracee_label: label of the process that's about to be traced,
+ *                the pointer must originate from smack structures
+ * @mode: ptrace attachment mode (PTRACE_MODE_*)
+ * @func: name of the function that called us, used for audit
+ *
+ * Returns 0 on access granted, -error on error
+ */
+static int smk_ptrace_rule_check(struct task_struct *tracer, char *tracee_label,
+				 unsigned int mode, const char *func)
+{
+	int rc;
+	struct smk_audit_info ad, *saip = NULL;
+	struct task_smack *tsp;
+	struct smack_known *skp;
+
+	if ((mode & PTRACE_MODE_NOAUDIT) == 0) {
+		smk_ad_init(&ad, func, LSM_AUDIT_DATA_TASK);
+		smk_ad_setfield_u_tsk(&ad, tracer);
+		saip = &ad;
+	}
+
+	tsp = task_security(tracer);
+	skp = smk_of_task(tsp);
+
+	if ((mode & PTRACE_MODE_ATTACH) &&
+	    (smack_ptrace_rule == SMACK_PTRACE_EXACT ||
+	     smack_ptrace_rule == SMACK_PTRACE_DRACONIAN)) {
+		if (skp->smk_known == tracee_label)
+			rc = 0;
+		else if (smack_ptrace_rule == SMACK_PTRACE_DRACONIAN)
+			rc = -EACCES;
+		else if (capable(CAP_SYS_PTRACE))
+			rc = 0;
+		else
+			rc = -EACCES;
+
+		if (saip)
+			smack_log(skp->smk_known, tracee_label, 0, rc, saip);
+
+		return rc;
+	}
+
+	/* In case of rule==SMACK_PTRACE_DEFAULT or mode==PTRACE_MODE_READ */
+	rc = smk_tskacc(tsp, tracee_label, smk_ptrace_mode(mode), saip);
+	return rc;
+}
+
 /*
  * LSM hooks.
  * We he, that is fun!
@@ -165,16 +233,15 @@ static int smk_copy_rules(struct list_head *nhead, struct list_head *ohead,
 /**
  * smack_ptrace_access_check - Smack approval on PTRACE_ATTACH
  * @ctp: child task pointer
- * @mode: ptrace attachment mode
+ * @mode: ptrace attachment mode (PTRACE_MODE_*)
  *
  * Returns 0 if access is OK, an error code otherwise
  *
- * Do the capability checks, and require read and write.
+ * Do the capability checks.
  */
 static int smack_ptrace_access_check(struct task_struct *ctp, unsigned int mode)
 {
 	int rc;
-	struct smk_audit_info ad;
 	struct smack_known *skp;
 
 	rc = cap_ptrace_access_check(ctp, mode);
@@ -182,10 +249,8 @@ static int smack_ptrace_access_check(struct task_struct *ctp, unsigned int mode)
 		return rc;
 
 	skp = smk_of_task(task_security(ctp));
-	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
-	smk_ad_setfield_u_tsk(&ad, ctp);
 
-	rc = smk_curacc(skp->smk_known, mode, &ad);
+	rc = smk_ptrace_rule_check(current, skp->smk_known, mode, __func__);
 	return rc;
 }
 
@@ -195,23 +260,21 @@ static int smack_ptrace_access_check(struct task_struct *ctp, unsigned int mode)
  *
  * Returns 0 if access is OK, an error code otherwise
  *
- * Do the capability checks, and require read and write.
+ * Do the capability checks, and require PTRACE_MODE_ATTACH.
  */
 static int smack_ptrace_traceme(struct task_struct *ptp)
 {
 	int rc;
-	struct smk_audit_info ad;
 	struct smack_known *skp;
 
 	rc = cap_ptrace_traceme(ptp);
 	if (rc != 0)
 		return rc;
 
-	skp = smk_of_task(task_security(ptp));
-	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
-	smk_ad_setfield_u_tsk(&ad, ptp);
+	skp = smk_of_task(current_security());
 
-	rc = smk_curacc(skp->smk_known, MAY_READWRITE, &ad);
+	rc = smk_ptrace_rule_check(ptp, skp->smk_known,
+				   PTRACE_MODE_ATTACH, __func__);
 	return rc;
 }
 
@@ -413,9 +476,11 @@ static int smack_sb_kern_mount(struct super_block *sb, int flags, void *data)
 	 * Initialize the root inode.
 	 */
 	isp = inode->i_security;
-	if (inode->i_security == NULL) {
-		inode->i_security = new_inode_smack(sp->smk_root);
-		isp = inode->i_security;
+	if (isp == NULL) {
+		isp = new_inode_smack(sp->smk_root);
+		if (isp == NULL)
+			return -ENOMEM;
+		inode->i_security = isp;
 	} else
 		isp->smk_inode = sp->smk_root;
 
@@ -453,7 +518,7 @@ static int smack_sb_statfs(struct dentry *dentry)
  * smack_bprm_set_creds - set creds for exec
  * @bprm: the exec information
  *
- * Returns 0 if it gets a blob, -ENOMEM otherwise
+ * Returns 0 if it gets a blob, -EPERM if exec forbidden and -ENOMEM otherwise
  */
 static int smack_bprm_set_creds(struct linux_binprm *bprm)
 {
@@ -473,7 +538,22 @@ static int smack_bprm_set_creds(struct linux_binprm *bprm)
 	if (isp->smk_task == NULL || isp->smk_task == bsp->smk_task)
 		return 0;
 
-	if (bprm->unsafe)
+	if (bprm->unsafe & (LSM_UNSAFE_PTRACE | LSM_UNSAFE_PTRACE_CAP)) {
+		struct task_struct *tracer;
+		rc = 0;
+
+		rcu_read_lock();
+		tracer = ptrace_parent(current);
+		if (likely(tracer != NULL))
+			rc = smk_ptrace_rule_check(tracer,
+						   isp->smk_task->smk_known,
+						   PTRACE_MODE_ATTACH,
+						   __func__);
+		rcu_read_unlock();
+
+		if (rc != 0)
+			return rc;
+	} else if (bprm->unsafe)
 		return -EPERM;
 
 	bsp->smk_task = isp->smk_task;
@@ -880,18 +960,20 @@ static void smack_inode_post_setxattr(struct dentry *dentry, const char *name,
 		return;
 	}
 
-	skp = smk_import_entry(value, size);
 	if (strcmp(name, XATTR_NAME_SMACK) == 0) {
+		skp = smk_import_entry(value, size);
 		if (skp != NULL)
 			isp->smk_inode = skp->smk_known;
 		else
 			isp->smk_inode = smack_known_invalid.smk_known;
 	} else if (strcmp(name, XATTR_NAME_SMACKEXEC) == 0) {
+		skp = smk_import_entry(value, size);
 		if (skp != NULL)
 			isp->smk_task = skp;
 		else
 			isp->smk_task = &smack_known_invalid;
 	} else if (strcmp(name, XATTR_NAME_SMACKMMAP) == 0) {
+		skp = smk_import_entry(value, size);
 		if (skp != NULL)
 			isp->smk_mmap = skp;
 		else
@@ -938,24 +1020,37 @@ static int smack_inode_removexattr(struct dentry *dentry, const char *name)
 	    strcmp(name, XATTR_NAME_SMACKIPOUT) == 0 ||
 	    strcmp(name, XATTR_NAME_SMACKEXEC) == 0 ||
 	    strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0 ||
-	    strcmp(name, XATTR_NAME_SMACKMMAP)) {
+	    strcmp(name, XATTR_NAME_SMACKMMAP) == 0) {
 		if (!smack_privileged(CAP_MAC_ADMIN))
 			rc = -EPERM;
 	} else
 		rc = cap_inode_removexattr(dentry, name);
 
+	if (rc != 0)
+		return rc;
+
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
 	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
-	if (rc == 0)
-		rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
 
-	if (rc == 0) {
-		isp = dentry->d_inode->i_security;
+	rc = smk_curacc(smk_of_inode(dentry->d_inode), MAY_WRITE, &ad);
+	if (rc != 0)
+		return rc;
+
+	isp = dentry->d_inode->i_security;
+	/*
+	 * Don't do anything special for these.
+	 *	XATTR_NAME_SMACKIPIN
+	 *	XATTR_NAME_SMACKIPOUT
+	 *	XATTR_NAME_SMACKEXEC
+	 */
+	if (strcmp(name, XATTR_NAME_SMACK) == 0)
 		isp->smk_task = NULL;
+	else if (strcmp(name, XATTR_NAME_SMACKMMAP) == 0)
 		isp->smk_mmap = NULL;
-	}
+	else if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0)
+		isp->smk_flags &= ~SMK_INODE_TRANSMUTE;
 
-	return rc;
+	return 0;
 }
 
 /**
@@ -1000,7 +1095,7 @@ static int smack_inode_getsecurity(const struct inode *inode,
 	ssp = sock->sk->sk_security;
 
 	if (strcmp(name, XATTR_SMACK_IPIN) == 0)
-		isp = ssp->smk_in;
+		isp = ssp->smk_in->smk_known;
 	else if (strcmp(name, XATTR_SMACK_IPOUT) == 0)
 		isp = ssp->smk_out->smk_known;
 	else
@@ -1367,19 +1462,32 @@ static int smack_file_receive(struct file *file)
 /**
  * smack_file_open - Smack dentry open processing
  * @file: the object
- * @cred: unused
+ * @cred: task credential
  *
  * Set the security blob in the file structure.
+ * Allow the open only if the task has read access. There are
+ * many read operations (e.g. fstat) that you can do with an
+ * fd even if you have the file open write-only.
  *
  * Returns 0
  */
 static int smack_file_open(struct file *file, const struct cred *cred)
 {
+	struct task_smack *tsp = cred->security;
 	struct inode_smack *isp = file_inode(file)->i_security;
+	struct smk_audit_info ad;
+	int rc;
 
-	file->f_security = isp->smk_inode;
+	if (smack_privileged(CAP_MAC_OVERRIDE))
+		return 0;
 
-	return 0;
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
+	rc = smk_access(tsp->smk_task, isp->smk_inode, MAY_READ, &ad);
+	if (rc == 0)
+		file->f_security = isp->smk_inode;
+
+	return rc;
 }
 
 /*
@@ -1764,7 +1872,7 @@ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags)
 	if (ssp == NULL)
 		return -ENOMEM;
 
-	ssp->smk_in = skp->smk_known;
+	ssp->smk_in = skp;
 	ssp->smk_out = skp;
 	ssp->smk_packet = NULL;
 
@@ -2004,7 +2112,7 @@ static int smk_ipv6_port_check(struct sock *sk, struct sockaddr_in6 *address,
 
 	if (act == SMK_RECEIVING) {
 		skp = smack_net_ambient;
-		object = ssp->smk_in;
+		object = ssp->smk_in->smk_known;
 	} else {
 		skp = ssp->smk_out;
 		object = smack_net_ambient->smk_known;
@@ -2034,9 +2142,9 @@ static int smk_ipv6_port_check(struct sock *sk, struct sockaddr_in6 *address,
 	list_for_each_entry(spp, &smk_ipv6_port_list, list) {
 		if (spp->smk_port != port)
 			continue;
-		object = spp->smk_in;
+		object = spp->smk_in->smk_known;
 		if (act == SMK_CONNECTING)
-			ssp->smk_packet = spp->smk_out->smk_known;
+			ssp->smk_packet = spp->smk_out;
 		break;
 	}
 
@@ -2076,7 +2184,7 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name,
 	int rc = 0;
 
 	if (value == NULL || size > SMK_LONGLABEL || size == 0)
-		return -EACCES;
+		return -EINVAL;
 
 	skp = smk_import_entry(value, size);
 	if (skp == NULL)
@@ -2100,7 +2208,7 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name,
 	ssp = sock->sk->sk_security;
 
 	if (strcmp(name, XATTR_SMACK_IPIN) == 0)
-		ssp->smk_in = skp->smk_known;
+		ssp->smk_in = skp;
 	else if (strcmp(name, XATTR_SMACK_IPOUT) == 0) {
 		ssp->smk_out = skp;
 		if (sock->sk->sk_family == PF_INET) {
@@ -2713,6 +2821,15 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 	 * of the superblock.
 	 */
 	if (opt_dentry->d_parent == opt_dentry) {
+		if (sbp->s_magic == CGROUP_SUPER_MAGIC) {
+			/*
+			 * The cgroup filesystem is never mounted,
+			 * so there's no opportunity to set the mount
+			 * options.
+			 */
+			sbsp->smk_root = smack_known_star.smk_known;
+			sbsp->smk_default = smack_known_star.smk_known;
+		}
 		isp->smk_inode = sbsp->smk_root;
 		isp->smk_flags |= SMK_INODE_INSTANT;
 		goto unlockandout;
@@ -2726,16 +2843,20 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 	 */
 	switch (sbp->s_magic) {
 	case SMACK_MAGIC:
+	case PIPEFS_MAGIC:
+	case SOCKFS_MAGIC:
+	case CGROUP_SUPER_MAGIC:
 		/*
 		 * Casey says that it's a little embarrassing
 		 * that the smack file system doesn't do
 		 * extended attributes.
-		 */
-		final = smack_known_star.smk_known;
-		break;
-	case PIPEFS_MAGIC:
-		/*
+		 *
 		 * Casey says pipes are easy (?)
+		 *
+		 * Socket access is controlled by the socket
+		 * structures associated with the task involved.
+		 *
+		 * Cgroupfs is special
 		 */
 		final = smack_known_star.smk_known;
 		break;
@@ -2747,13 +2868,6 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
 		 */
 		final = ckp->smk_known;
 		break;
-	case SOCKFS_MAGIC:
-		/*
-		 * Socket access is controlled by the socket
-		 * structures associated with the task involved.
-		 */
-		final = smack_known_star.smk_known;
-		break;
 	case PROC_SUPER_MAGIC:
 		/*
 		 * Casey says procfs appears not to care.
@@ -2959,30 +3073,34 @@ static int smack_unix_stream_connect(struct sock *sock,
 				     struct sock *other, struct sock *newsk)
 {
 	struct smack_known *skp;
+	struct smack_known *okp;
 	struct socket_smack *ssp = sock->sk_security;
 	struct socket_smack *osp = other->sk_security;
 	struct socket_smack *nsp = newsk->sk_security;
 	struct smk_audit_info ad;
 	int rc = 0;
-
 #ifdef CONFIG_AUDIT
 	struct lsm_network_audit net;
-
-	smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
-	smk_ad_setfield_u_net_sk(&ad, other);
 #endif
 
 	if (!smack_privileged(CAP_MAC_OVERRIDE)) {
 		skp = ssp->smk_out;
-		rc = smk_access(skp, osp->smk_in, MAY_WRITE, &ad);
+		okp = osp->smk_out;
+#ifdef CONFIG_AUDIT
+		smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+		smk_ad_setfield_u_net_sk(&ad, other);
+#endif
+		rc = smk_access(skp, okp->smk_known, MAY_WRITE, &ad);
+		if (rc == 0)
+			rc = smk_access(okp, okp->smk_known, MAY_WRITE, NULL);
 	}
 
 	/*
 	 * Cross reference the peer labels for SO_PEERSEC.
 	 */
 	if (rc == 0) {
-		nsp->smk_packet = ssp->smk_out->smk_known;
-		ssp->smk_packet = osp->smk_out->smk_known;
+		nsp->smk_packet = ssp->smk_out;
+		ssp->smk_packet = osp->smk_out;
 	}
 
 	return rc;
@@ -3014,7 +3132,7 @@ static int smack_unix_may_send(struct socket *sock, struct socket *other)
 		return 0;
 
 	skp = ssp->smk_out;
-	return smk_access(skp, osp->smk_in, MAY_WRITE, &ad);
+	return smk_access(skp, osp->smk_in->smk_known, MAY_WRITE, &ad);
 }
 
 /**
@@ -3109,7 +3227,7 @@ static struct smack_known *smack_from_secattr(struct netlbl_lsm_secattr *sap,
 		if (found)
 			return skp;
 
-		if (ssp != NULL && ssp->smk_in == smack_known_star.smk_known)
+		if (ssp != NULL && ssp->smk_in == &smack_known_star)
 			return &smack_known_web;
 		return &smack_known_star;
 	}
@@ -3228,7 +3346,7 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		 * This is the simplist possible security model
 		 * for networking.
 		 */
-		rc = smk_access(skp, ssp->smk_in, MAY_WRITE, &ad);
+		rc = smk_access(skp, ssp->smk_in->smk_known, MAY_WRITE, &ad);
 		if (rc != 0)
 			netlbl_skbuff_err(skb, rc, 0);
 		break;
@@ -3263,7 +3381,7 @@ static int smack_socket_getpeersec_stream(struct socket *sock,
 
 	ssp = sock->sk->sk_security;
 	if (ssp->smk_packet != NULL) {
-		rcp = ssp->smk_packet;
+		rcp = ssp->smk_packet->smk_known;
 		slen = strlen(rcp) + 1;
 	}
 
@@ -3348,7 +3466,7 @@ static void smack_sock_graft(struct sock *sk, struct socket *parent)
 		return;
 
 	ssp = sk->sk_security;
-	ssp->smk_in = skp->smk_known;
+	ssp->smk_in = skp;
 	ssp->smk_out = skp;
 	/* cssp->smk_packet is already set in smack_inet_csk_clone() */
 }
@@ -3408,7 +3526,7 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb,
 	 * Receiving a packet requires that the other end be able to write
 	 * here. Read access is not required.
 	 */
-	rc = smk_access(skp, ssp->smk_in, MAY_WRITE, &ad);
+	rc = smk_access(skp, ssp->smk_in->smk_known, MAY_WRITE, &ad);
 	if (rc != 0)
 		return rc;
 
@@ -3452,7 +3570,7 @@ static void smack_inet_csk_clone(struct sock *sk,
 
 	if (req->peer_secid != 0) {
 		skp = smack_from_secid(req->peer_secid);
-		ssp->smk_packet = skp->smk_known;
+		ssp->smk_packet = skp;
 	} else
 		ssp->smk_packet = NULL;
 }
@@ -3506,11 +3624,12 @@ static void smack_key_free(struct key *key)
  * an error code otherwise
  */
 static int smack_key_permission(key_ref_t key_ref,
-				const struct cred *cred, key_perm_t perm)
+				const struct cred *cred, unsigned perm)
 {
 	struct key *keyp;
 	struct smk_audit_info ad;
 	struct smack_known *tkp = smk_of_task(cred->security);
+	int request = 0;
 
 	keyp = key_ref_to_ptr(key_ref);
 	if (keyp == NULL)
@@ -3531,7 +3650,11 @@ static int smack_key_permission(key_ref_t key_ref,
 	ad.a.u.key_struct.key = keyp->serial;
 	ad.a.u.key_struct.key_desc = keyp->description;
 #endif
-	return smk_access(tkp, keyp->security, MAY_READWRITE, &ad);
+	if (perm & KEY_NEED_READ)
+		request = MAY_READ;
+	if (perm & (KEY_NEED_WRITE | KEY_NEED_LINK | KEY_NEED_SETATTR))
+		request = MAY_WRITE;
+	return smk_access(tkp, keyp->security, request, &ad);
 }
 #endif /* CONFIG_KEYS */
 
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index 3198cfe1dcc..32b24882084 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -53,6 +53,7 @@ enum smk_inos {
 	SMK_REVOKE_SUBJ	= 18,	/* set rules with subject label to '-' */
 	SMK_CHANGE_RULE	= 19,	/* change or add rules (long labels) */
 	SMK_SYSLOG	= 20,	/* change syslog label) */
+	SMK_PTRACE	= 21,	/* set ptrace rule */
 };
 
 /*
@@ -101,6 +102,15 @@ struct smack_known *smack_onlycap;
 struct smack_known *smack_syslog_label;
 
 /*
+ * Ptrace current rule
+ * SMACK_PTRACE_DEFAULT    regular smack ptrace rules (/proc based)
+ * SMACK_PTRACE_EXACT      labels must match, but can be overriden with
+ *			   CAP_SYS_PTRACE
+ * SMACK_PTRACE_DRACONIAN  lables must match, CAP_SYS_PTRACE has no effect
+ */
+int smack_ptrace_rule = SMACK_PTRACE_DEFAULT;
+
+/*
  * Certain IP addresses may be designated as single label hosts.
  * Packets are sent there unlabeled, but only from tasks that
  * can write to the specified label.
@@ -1183,7 +1193,7 @@ static ssize_t smk_write_netlbladdr(struct file *file, const char __user *buf,
 
 	data[count] = '\0';
 
-	rc = sscanf(data, "%hhd.%hhd.%hhd.%hhd/%d %s",
+	rc = sscanf(data, "%hhd.%hhd.%hhd.%hhd/%u %s",
 		&host[0], &host[1], &host[2], &host[3], &m, smack);
 	if (rc != 6) {
 		rc = sscanf(data, "%hhd.%hhd.%hhd.%hhd %s",
@@ -2244,6 +2254,68 @@ static const struct file_operations smk_syslog_ops = {
 
 
 /**
+ * smk_read_ptrace - read() for /smack/ptrace
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @count: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_ptrace(struct file *filp, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	char temp[32];
+	ssize_t rc;
+
+	if (*ppos != 0)
+		return 0;
+
+	sprintf(temp, "%d\n", smack_ptrace_rule);
+	rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
+	return rc;
+}
+
+/**
+ * smk_write_ptrace - write() for /smack/ptrace
+ * @file: file pointer
+ * @buf: data from user space
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ */
+static ssize_t smk_write_ptrace(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char temp[32];
+	int i;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (*ppos != 0 || count >= sizeof(temp) || count == 0)
+		return -EINVAL;
+
+	if (copy_from_user(temp, buf, count) != 0)
+		return -EFAULT;
+
+	temp[count] = '\0';
+
+	if (sscanf(temp, "%d", &i) != 1)
+		return -EINVAL;
+	if (i < SMACK_PTRACE_DEFAULT || i > SMACK_PTRACE_MAX)
+		return -EINVAL;
+	smack_ptrace_rule = i;
+
+	return count;
+}
+
+static const struct file_operations smk_ptrace_ops = {
+	.write		= smk_write_ptrace,
+	.read		= smk_read_ptrace,
+	.llseek		= default_llseek,
+};
+
+/**
  * smk_fill_super - fill the smackfs superblock
  * @sb: the empty superblock
  * @data: unused
@@ -2296,6 +2368,8 @@ static int smk_fill_super(struct super_block *sb, void *data, int silent)
 			"change-rule", &smk_change_rule_ops, S_IRUGO|S_IWUSR},
 		[SMK_SYSLOG] = {
 			"syslog", &smk_syslog_ops, S_IRUGO|S_IWUSR},
+		[SMK_PTRACE] = {
+			"ptrace", &smk_ptrace_ops, S_IRUGO|S_IWUSR},
 		/* last one */
 			{""}
 	};
diff --git a/sound/core/control.c b/sound/core/control.c
index f038f5afafe..f0b0e14497a 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -288,6 +288,10 @@ static bool snd_ctl_remove_numid_conflict(struct snd_card *card,
 {
 	struct snd_kcontrol *kctl;
 
+	/* Make sure that the ids assigned to the control do not wrap around */
+	if (card->last_numid >= UINT_MAX - count)
+		card->last_numid = 0;
+
 	list_for_each_entry(kctl, &card->controls, list) {
 		if (kctl->id.numid < card->last_numid + 1 + count &&
 		    kctl->id.numid + kctl->count > card->last_numid + 1) {
@@ -330,6 +334,7 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 {
 	struct snd_ctl_elem_id id;
 	unsigned int idx;
+	unsigned int count;
 	int err = -EINVAL;
 
 	if (! kcontrol)
@@ -337,6 +342,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 	if (snd_BUG_ON(!card || !kcontrol->info))
 		goto error;
 	id = kcontrol->id;
+	if (id.index > UINT_MAX - kcontrol->count)
+		goto error;
+
 	down_write(&card->controls_rwsem);
 	if (snd_ctl_find_id(card, &id)) {
 		up_write(&card->controls_rwsem);
@@ -358,8 +366,9 @@ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol)
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -388,6 +397,7 @@ int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol,
 		    bool add_on_replace)
 {
 	struct snd_ctl_elem_id id;
+	unsigned int count;
 	unsigned int idx;
 	struct snd_kcontrol *old;
 	int ret;
@@ -423,8 +433,9 @@ add:
 	card->controls_count += kcontrol->count;
 	kcontrol->id.numid = card->last_numid + 1;
 	card->last_numid += kcontrol->count;
+	count = kcontrol->count;
 	up_write(&card->controls_rwsem);
-	for (idx = 0; idx < kcontrol->count; idx++, id.index++, id.numid++)
+	for (idx = 0; idx < count; idx++, id.index++, id.numid++)
 		snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id);
 	return 0;
 
@@ -897,9 +908,9 @@ static int snd_ctl_elem_write(struct snd_card *card, struct snd_ctl_file *file,
 			result = kctl->put(kctl, control);
 		}
 		if (result > 0) {
+			struct snd_ctl_elem_id id = control->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE,
-				       &control->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_VALUE, &id);
 			return 0;
 		}
 	}
@@ -991,6 +1002,7 @@ static int snd_ctl_elem_unlock(struct snd_ctl_file *file,
 
 struct user_element {
 	struct snd_ctl_elem_info info;
+	struct snd_card *card;
 	void *elem_data;		/* element data */
 	unsigned long elem_data_size;	/* size of element data in bytes */
 	void *tlv_data;			/* TLV data */
@@ -1034,7 +1046,9 @@ static int snd_ctl_elem_user_get(struct snd_kcontrol *kcontrol,
 {
 	struct user_element *ue = kcontrol->private_data;
 
+	mutex_lock(&ue->card->user_ctl_lock);
 	memcpy(&ucontrol->value, ue->elem_data, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return 0;
 }
 
@@ -1043,10 +1057,12 @@ static int snd_ctl_elem_user_put(struct snd_kcontrol *kcontrol,
 {
 	int change;
 	struct user_element *ue = kcontrol->private_data;
-	
+
+	mutex_lock(&ue->card->user_ctl_lock);
 	change = memcmp(&ucontrol->value, ue->elem_data, ue->elem_data_size) != 0;
 	if (change)
 		memcpy(ue->elem_data, &ucontrol->value, ue->elem_data_size);
+	mutex_unlock(&ue->card->user_ctl_lock);
 	return change;
 }
 
@@ -1066,19 +1082,32 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol,
 		new_data = memdup_user(tlv, size);
 		if (IS_ERR(new_data))
 			return PTR_ERR(new_data);
+		mutex_lock(&ue->card->user_ctl_lock);
 		change = ue->tlv_data_size != size;
 		if (!change)
 			change = memcmp(ue->tlv_data, new_data, size);
 		kfree(ue->tlv_data);
 		ue->tlv_data = new_data;
 		ue->tlv_data_size = size;
+		mutex_unlock(&ue->card->user_ctl_lock);
 	} else {
-		if (! ue->tlv_data_size || ! ue->tlv_data)
-			return -ENXIO;
-		if (size < ue->tlv_data_size)
-			return -ENOSPC;
+		int ret = 0;
+
+		mutex_lock(&ue->card->user_ctl_lock);
+		if (!ue->tlv_data_size || !ue->tlv_data) {
+			ret = -ENXIO;
+			goto err_unlock;
+		}
+		if (size < ue->tlv_data_size) {
+			ret = -ENOSPC;
+			goto err_unlock;
+		}
 		if (copy_to_user(tlv, ue->tlv_data, ue->tlv_data_size))
-			return -EFAULT;
+			ret = -EFAULT;
+err_unlock:
+		mutex_unlock(&ue->card->user_ctl_lock);
+		if (ret)
+			return ret;
 	}
 	return change;
 }
@@ -1136,8 +1165,6 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	struct user_element *ue;
 	int idx, err;
 
-	if (!replace && card->user_ctl_count >= MAX_USER_CONTROLS)
-		return -ENOMEM;
 	if (info->count < 1)
 		return -EINVAL;
 	access = info->access == 0 ? SNDRV_CTL_ELEM_ACCESS_READWRITE :
@@ -1146,21 +1173,16 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 				 SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE));
 	info->id.numid = 0;
 	memset(&kctl, 0, sizeof(kctl));
-	down_write(&card->controls_rwsem);
-	_kctl = snd_ctl_find_id(card, &info->id);
-	err = 0;
-	if (_kctl) {
-		if (replace)
-			err = snd_ctl_remove(card, _kctl);
-		else
-			err = -EBUSY;
-	} else {
-		if (replace)
-			err = -ENOENT;
+
+	if (replace) {
+		err = snd_ctl_remove_user_ctl(file, &info->id);
+		if (err)
+			return err;
 	}
-	up_write(&card->controls_rwsem);
-	if (err < 0)
-		return err;
+
+	if (card->user_ctl_count >= MAX_USER_CONTROLS)
+		return -ENOMEM;
+
 	memcpy(&kctl.id, &info->id, sizeof(info->id));
 	kctl.count = info->owner ? info->owner : 1;
 	access |= SNDRV_CTL_ELEM_ACCESS_USER;
@@ -1210,6 +1232,7 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file,
 	ue = kzalloc(sizeof(struct user_element) + private_size, GFP_KERNEL);
 	if (ue == NULL)
 		return -ENOMEM;
+	ue->card = card;
 	ue->info = *info;
 	ue->info.access = 0;
 	ue->elem_data = (char *)ue + sizeof(*ue);
@@ -1321,8 +1344,9 @@ static int snd_ctl_tlv_ioctl(struct snd_ctl_file *file,
 		}
 		err = kctl->tlv.c(kctl, op_flag, tlv.length, _tlv->tlv);
 		if (err > 0) {
+			struct snd_ctl_elem_id id = kctl->id;
 			up_read(&card->controls_rwsem);
-			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &kctl->id);
+			snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_TLV, &id);
 			return 0;
 		}
 	} else {
diff --git a/sound/core/init.c b/sound/core/init.c
index 5ee83845c5d..7bdfd19e24a 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -232,6 +232,7 @@ int snd_card_new(struct device *parent, int idx, const char *xid,
 	INIT_LIST_HEAD(&card->devices);
 	init_rwsem(&card->controls_rwsem);
 	rwlock_init(&card->ctl_files_rwlock);
+	mutex_init(&card->user_ctl_lock);
 	INIT_LIST_HEAD(&card->controls);
 	INIT_LIST_HEAD(&card->ctl_files);
 	spin_lock_init(&card->files_lock);
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 9ca5e647e54..225c73152ee 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -660,7 +660,7 @@ static int deliver_to_subscribers(struct snd_seq_client *client,
 				  int atomic, int hop)
 {
 	struct snd_seq_subscribers *subs;
-	int err = 0, num_ev = 0;
+	int err, result = 0, num_ev = 0;
 	struct snd_seq_event event_saved;
 	struct snd_seq_client_port *src_port;
 	struct snd_seq_port_subs_info *grp;
@@ -685,8 +685,12 @@ static int deliver_to_subscribers(struct snd_seq_client *client,
 						  subs->info.flags & SNDRV_SEQ_PORT_SUBS_TIME_REAL);
 		err = snd_seq_deliver_single_event(client, event,
 						   0, atomic, hop);
-		if (err < 0)
-			break;
+		if (err < 0) {
+			/* save first error that occurs and continue */
+			if (!result)
+				result = err;
+			continue;
+		}
 		num_ev++;
 		/* restore original event record */
 		*event = event_saved;
@@ -697,7 +701,7 @@ static int deliver_to_subscribers(struct snd_seq_client *client,
 		up_read(&grp->list_mutex);
 	*event = event_saved; /* restore */
 	snd_seq_port_unlock(src_port);
-	return (err < 0) ? err : num_ev;
+	return (result < 0) ? result : num_ev;
 }
 
 
@@ -709,7 +713,7 @@ static int port_broadcast_event(struct snd_seq_client *client,
 				struct snd_seq_event *event,
 				int atomic, int hop)
 {
-	int num_ev = 0, err = 0;
+	int num_ev = 0, err, result = 0;
 	struct snd_seq_client *dest_client;
 	struct snd_seq_client_port *port;
 
@@ -724,14 +728,18 @@ static int port_broadcast_event(struct snd_seq_client *client,
 		err = snd_seq_deliver_single_event(NULL, event,
 						   SNDRV_SEQ_FILTER_BROADCAST,
 						   atomic, hop);
-		if (err < 0)
-			break;
+		if (err < 0) {
+			/* save first error that occurs and continue */
+			if (!result)
+				result = err;
+			continue;
+		}
 		num_ev++;
 	}
 	read_unlock(&dest_client->ports_lock);
 	snd_seq_client_unlock(dest_client);
 	event->dest.port = SNDRV_SEQ_ADDRESS_BROADCAST; /* restore */
-	return (err < 0) ? err : num_ev;
+	return (result < 0) ? result : num_ev;
 }
 
 /*
@@ -741,7 +749,7 @@ static int port_broadcast_event(struct snd_seq_client *client,
 static int broadcast_event(struct snd_seq_client *client,
 			   struct snd_seq_event *event, int atomic, int hop)
 {
-	int err = 0, num_ev = 0;
+	int err, result = 0, num_ev = 0;
 	int dest;
 	struct snd_seq_addr addr;
 
@@ -760,12 +768,16 @@ static int broadcast_event(struct snd_seq_client *client,
 			err = snd_seq_deliver_single_event(NULL, event,
 							   SNDRV_SEQ_FILTER_BROADCAST,
 							   atomic, hop);
-		if (err < 0)
-			break;
+		if (err < 0) {
+			/* save first error that occurs and continue */
+			if (!result)
+				result = err;
+			continue;
+		}
 		num_ev += err;
 	}
 	event->dest = addr; /* restore */
-	return (err < 0) ? err : num_ev;
+	return (result < 0) ? result : num_ev;
 }
 
 
diff --git a/sound/core/seq/seq_fifo.c b/sound/core/seq/seq_fifo.c
index 559989992be..53a403e17c5 100644
--- a/sound/core/seq/seq_fifo.c
+++ b/sound/core/seq/seq_fifo.c
@@ -124,7 +124,7 @@ int snd_seq_fifo_event_in(struct snd_seq_fifo *f,
 	snd_use_lock_use(&f->use_lock);
 	err = snd_seq_event_dup(f->pool, event, &cell, 1, NULL); /* always non-blocking */
 	if (err < 0) {
-		if (err == -ENOMEM)
+		if ((err == -ENOMEM) || (err == -EAGAIN))
 			atomic_inc(&f->overflow);
 		snd_use_lock_free(&f->use_lock);
 		return err;
diff --git a/sound/core/timer.c b/sound/core/timer.c
index cfd455a8ac1..777a45e08e5 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -390,7 +390,7 @@ static void snd_timer_notify1(struct snd_timer_instance *ti, int event)
 	struct timespec tstamp;
 
 	if (timer_tstamp_monotonic)
-		do_posix_clock_monotonic_gettime(&tstamp);
+		ktime_get_ts(&tstamp);
 	else
 		getnstimeofday(&tstamp);
 	if (snd_BUG_ON(event < SNDRV_TIMER_EVENT_START ||
@@ -1203,7 +1203,7 @@ static void snd_timer_user_tinterrupt(struct snd_timer_instance *timeri,
 	}
 	if (tu->last_resolution != resolution || ticks > 0) {
 		if (timer_tstamp_monotonic)
-			do_posix_clock_monotonic_gettime(&tstamp);
+			ktime_get_ts(&tstamp);
 		else
 			getnstimeofday(&tstamp);
 	}
diff --git a/sound/firewire/bebob/bebob.h b/sound/firewire/bebob/bebob.h
index d1c93a1e097..e13eef99c27 100644
--- a/sound/firewire/bebob/bebob.h
+++ b/sound/firewire/bebob/bebob.h
@@ -208,8 +208,6 @@ int snd_bebob_stream_set_rate(struct snd_bebob *bebob, unsigned int rate);
 int snd_bebob_stream_check_internal_clock(struct snd_bebob *bebob,
 					  bool *internal);
 int snd_bebob_stream_discover(struct snd_bebob *bebob);
-int snd_bebob_stream_map(struct snd_bebob *bebob,
-			 struct amdtp_stream *stream);
 int snd_bebob_stream_init_duplex(struct snd_bebob *bebob);
 int snd_bebob_stream_start_duplex(struct snd_bebob *bebob, unsigned int rate);
 void snd_bebob_stream_stop_duplex(struct snd_bebob *bebob);
diff --git a/sound/firewire/bebob/bebob_maudio.c b/sound/firewire/bebob/bebob_maudio.c
index 6af50eb80ea..70faa3a3252 100644
--- a/sound/firewire/bebob/bebob_maudio.c
+++ b/sound/firewire/bebob/bebob_maudio.c
@@ -379,11 +379,11 @@ static int special_clk_ctl_put(struct snd_kcontrol *kctl,
 	struct special_params *params = bebob->maudio_special_quirk;
 	int err, id;
 
-	mutex_lock(&bebob->mutex);
-
 	id = uval->value.enumerated.item[0];
 	if (id >= ARRAY_SIZE(special_clk_labels))
-		return 0;
+		return -EINVAL;
+
+	mutex_lock(&bebob->mutex);
 
 	err = avc_maudio_set_special_clk(bebob, id,
 					 params->dig_in_fmt,
@@ -391,7 +391,10 @@ static int special_clk_ctl_put(struct snd_kcontrol *kctl,
 					 params->clk_lock);
 	mutex_unlock(&bebob->mutex);
 
-	return err >= 0;
+	if (err >= 0)
+		err = 1;
+
+	return err;
 }
 static struct snd_kcontrol_new special_clk_ctl = {
 	.name	= "Clock Source",
@@ -434,8 +437,8 @@ static struct snd_kcontrol_new special_sync_ctl = {
 	.get	= special_sync_ctl_get,
 };
 
-/* Digital interface control for special firmware */
-static char *const special_dig_iface_labels[] = {
+/* Digital input interface control for special firmware */
+static char *const special_dig_in_iface_labels[] = {
 	"S/PDIF Optical", "S/PDIF Coaxial", "ADAT Optical"
 };
 static int special_dig_in_iface_ctl_info(struct snd_kcontrol *kctl,
@@ -443,13 +446,13 @@ static int special_dig_in_iface_ctl_info(struct snd_kcontrol *kctl,
 {
 	einf->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED;
 	einf->count = 1;
-	einf->value.enumerated.items = ARRAY_SIZE(special_dig_iface_labels);
+	einf->value.enumerated.items = ARRAY_SIZE(special_dig_in_iface_labels);
 
 	if (einf->value.enumerated.item >= einf->value.enumerated.items)
 		einf->value.enumerated.item = einf->value.enumerated.items - 1;
 
 	strcpy(einf->value.enumerated.name,
-	       special_dig_iface_labels[einf->value.enumerated.item]);
+	       special_dig_in_iface_labels[einf->value.enumerated.item]);
 
 	return 0;
 }
@@ -491,26 +494,36 @@ static int special_dig_in_iface_ctl_set(struct snd_kcontrol *kctl,
 	unsigned int id, dig_in_fmt, dig_in_iface;
 	int err;
 
-	mutex_lock(&bebob->mutex);
-
 	id = uval->value.enumerated.item[0];
+	if (id >= ARRAY_SIZE(special_dig_in_iface_labels))
+		return -EINVAL;
 
 	/* decode user value */
 	dig_in_fmt = (id >> 1) & 0x01;
 	dig_in_iface = id & 0x01;
 
+	mutex_lock(&bebob->mutex);
+
 	err = avc_maudio_set_special_clk(bebob,
 					 params->clk_src,
 					 dig_in_fmt,
 					 params->dig_out_fmt,
 					 params->clk_lock);
-	if ((err < 0) || (params->dig_in_fmt > 0)) /* ADAT */
+	if (err < 0)
+		goto end;
+
+	/* For ADAT, optical interface is only available. */
+	if (params->dig_in_fmt > 0) {
+		err = 1;
 		goto end;
+	}
 
+	/* For S/PDIF, optical/coaxial interfaces are selectable. */
 	err = avc_audio_set_selector(bebob->unit, 0x00, 0x04, dig_in_iface);
 	if (err < 0)
 		dev_err(&bebob->unit->device,
 			"fail to set digital input interface: %d\n", err);
+	err = 1;
 end:
 	special_stream_formation_set(bebob);
 	mutex_unlock(&bebob->mutex);
@@ -525,18 +538,22 @@ static struct snd_kcontrol_new special_dig_in_iface_ctl = {
 	.put	= special_dig_in_iface_ctl_set
 };
 
+/* Digital output interface control for special firmware */
+static char *const special_dig_out_iface_labels[] = {
+	"S/PDIF Optical and Coaxial", "ADAT Optical"
+};
 static int special_dig_out_iface_ctl_info(struct snd_kcontrol *kctl,
 					  struct snd_ctl_elem_info *einf)
 {
 	einf->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED;
 	einf->count = 1;
-	einf->value.enumerated.items = ARRAY_SIZE(special_dig_iface_labels) - 1;
+	einf->value.enumerated.items = ARRAY_SIZE(special_dig_out_iface_labels);
 
 	if (einf->value.enumerated.item >= einf->value.enumerated.items)
 		einf->value.enumerated.item = einf->value.enumerated.items - 1;
 
 	strcpy(einf->value.enumerated.name,
-	       special_dig_iface_labels[einf->value.enumerated.item + 1]);
+	       special_dig_out_iface_labels[einf->value.enumerated.item]);
 
 	return 0;
 }
@@ -558,16 +575,20 @@ static int special_dig_out_iface_ctl_set(struct snd_kcontrol *kctl,
 	unsigned int id;
 	int err;
 
-	mutex_lock(&bebob->mutex);
-
 	id = uval->value.enumerated.item[0];
+	if (id >= ARRAY_SIZE(special_dig_out_iface_labels))
+		return -EINVAL;
+
+	mutex_lock(&bebob->mutex);
 
 	err = avc_maudio_set_special_clk(bebob,
 					 params->clk_src,
 					 params->dig_in_fmt,
 					 id, params->clk_lock);
-	if (err >= 0)
+	if (err >= 0) {
 		special_stream_formation_set(bebob);
+		err = 1;
+	}
 
 	mutex_unlock(&bebob->mutex);
 	return err;
diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c
index bc4f82776fd..ef4d0c9f657 100644
--- a/sound/firewire/bebob/bebob_stream.c
+++ b/sound/firewire/bebob/bebob_stream.c
@@ -655,8 +655,6 @@ void snd_bebob_stream_stop_duplex(struct snd_bebob *bebob)
 	struct amdtp_stream *master, *slave;
 	atomic_t *master_substreams, *slave_substreams;
 
-	mutex_lock(&bebob->mutex);
-
 	if (bebob->master == &bebob->rx_stream) {
 		slave  = &bebob->tx_stream;
 		master = &bebob->rx_stream;
@@ -669,6 +667,8 @@ void snd_bebob_stream_stop_duplex(struct snd_bebob *bebob)
 		master_substreams = &bebob->capture_substreams;
 	}
 
+	mutex_lock(&bebob->mutex);
+
 	if (atomic_read(slave_substreams) == 0) {
 		amdtp_stream_pcm_abort(slave);
 		amdtp_stream_stop(slave);
diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c
index 996fdc44c83..3e2ed8e82cb 100644
--- a/sound/firewire/fireworks/fireworks.c
+++ b/sound/firewire/fireworks/fireworks.c
@@ -346,7 +346,6 @@ static void __exit snd_efw_exit(void)
 {
 	snd_efw_transaction_unregister();
 	driver_unregister(&efw_driver.driver);
-	mutex_destroy(&devices_mutex);
 }
 
 module_init(snd_efw_init);
diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h
index d2b36be4d2f..4f0201a9522 100644
--- a/sound/firewire/fireworks/fireworks.h
+++ b/sound/firewire/fireworks/fireworks.h
@@ -162,7 +162,6 @@ enum snd_efw_grp_type {
 	SND_EFW_CH_TYPE_GUITAR			= 7,
 	SND_EFW_CH_TYPE_PIEZO_GUITAR		= 8,
 	SND_EFW_CH_TYPE_GUITAR_STRING		= 9,
-	SND_EFW_CH_TYPE_VIRTUAL			= 0x10000,
 	SND_EFW_CH_TYPE_DUMMY
 };
 struct snd_efw_phys_meters {
diff --git a/sound/firewire/fireworks/fireworks_hwdep.c b/sound/firewire/fireworks/fireworks_hwdep.c
index 4f8216fb6b6..33df8655fe8 100644
--- a/sound/firewire/fireworks/fireworks_hwdep.c
+++ b/sound/firewire/fireworks/fireworks_hwdep.c
@@ -58,7 +58,7 @@ hwdep_read_resp_buf(struct snd_efw *efw, char __user *buf, long remained,
 			efw->pull_ptr += till_end;
 			if (efw->pull_ptr >= efw->resp_buf +
 					     snd_efw_resp_buf_size)
-				efw->pull_ptr = efw->resp_buf;
+				efw->pull_ptr -= snd_efw_resp_buf_size;
 
 			length -= till_end;
 			buf += till_end;
diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c
index 541569022a7..b985fc5ebdc 100644
--- a/sound/firewire/fireworks/fireworks_stream.c
+++ b/sound/firewire/fireworks/fireworks_stream.c
@@ -284,8 +284,6 @@ void snd_efw_stream_stop_duplex(struct snd_efw *efw)
 	struct amdtp_stream *master, *slave;
 	atomic_t *master_substreams, *slave_substreams;
 
-	mutex_lock(&efw->mutex);
-
 	if (efw->master == &efw->rx_stream) {
 		slave  = &efw->tx_stream;
 		master = &efw->rx_stream;
@@ -298,6 +296,8 @@ void snd_efw_stream_stop_duplex(struct snd_efw *efw)
 		master_substreams = &efw->capture_substreams;
 	}
 
+	mutex_lock(&efw->mutex);
+
 	if (atomic_read(slave_substreams) == 0) {
 		stop_stream(efw, slave);
 
diff --git a/sound/firewire/fireworks/fireworks_transaction.c b/sound/firewire/fireworks/fireworks_transaction.c
index aa56b8ac537..255dabc6fc3 100644
--- a/sound/firewire/fireworks/fireworks_transaction.c
+++ b/sound/firewire/fireworks/fireworks_transaction.c
@@ -8,19 +8,19 @@
 
 /*
  * Fireworks have its own transaction. The transaction can be delivered by AV/C
- * Vendor Specific command. But at least Windows driver and firmware version 5.5
- * or later don't use it.
+ * Vendor Specific command frame or usual asynchronous transaction. At least,
+ * Windows driver and firmware version 5.5 or later don't use AV/C command.
  *
  * Transaction substance:
- *  At first, 6 data exist. Following to the 6 data, parameters for each
- *  commands exists. All of parameters are 32 bit alighed to big endian.
+ *  At first, 6 data exist. Following to the data, parameters for each command
+ *  exist. All of the parameters are 32 bit alighed to big endian.
  *   data[0]:	Length of transaction substance
  *   data[1]:	Transaction version
  *   data[2]:	Sequence number. This is incremented by the device
- *   data[3]:	transaction category
- *   data[4]:	transaction command
- *   data[5]:	return value in response.
- *   data[6-]:	parameters
+ *   data[3]:	Transaction category
+ *   data[4]:	Transaction command
+ *   data[5]:	Return value in response.
+ *   data[6-]:	Parameters
  *
  * Transaction address:
  *  command:	0xecc000000000
@@ -148,7 +148,7 @@ copy_resp_to_buf(struct snd_efw *efw, void *data, size_t length, int *rcode)
 
 		efw->push_ptr += till_end;
 		if (efw->push_ptr >= efw->resp_buf + snd_efw_resp_buf_size)
-			efw->push_ptr = efw->resp_buf;
+			efw->push_ptr -= snd_efw_resp_buf_size;
 
 		length -= till_end;
 		data += till_end;
diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c
index b684c6e4f30..dabe41975a9 100644
--- a/sound/pci/hda/hda_auto_parser.c
+++ b/sound/pci/hda/hda_auto_parser.c
@@ -898,6 +898,7 @@ void snd_hda_pick_fixup(struct hda_codec *codec,
 			if (!strcmp(codec->modelname, models->name)) {
 				codec->fixup_id = models->id;
 				codec->fixup_name = models->name;
+				codec->fixup_list = fixlist;
 				codec->fixup_forced = 1;
 				return;
 			}
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 480bbddbd80..6df04d91c93 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -193,7 +193,8 @@ azx_assign_device(struct azx *chip, struct snd_pcm_substream *substream)
 				dsp_unlock(azx_dev);
 				return azx_dev;
 			}
-			if (!res)
+			if (!res ||
+			    (chip->driver_caps & AZX_DCAPS_REVERSE_ASSIGN))
 				res = azx_dev;
 		}
 		dsp_unlock(azx_dev);
diff --git a/sound/pci/hda/hda_i915.c b/sound/pci/hda/hda_i915.c
index 9d07e4edacd..8b4940ba33d 100644
--- a/sound/pci/hda/hda_i915.c
+++ b/sound/pci/hda/hda_i915.c
@@ -20,24 +20,71 @@
 #include <linux/module.h>
 #include <sound/core.h>
 #include <drm/i915_powerwell.h>
+#include "hda_priv.h"
 #include "hda_i915.h"
 
-static void (*get_power)(void);
-static void (*put_power)(void);
+/* Intel HSW/BDW display HDA controller Extended Mode registers.
+ * EM4 (M value) and EM5 (N Value) are used to convert CDClk (Core Display
+ * Clock) to 24MHz BCLK: BCLK = CDCLK * M / N
+ * The values will be lost when the display power well is disabled.
+ */
+#define ICH6_REG_EM4			0x100c
+#define ICH6_REG_EM5			0x1010
+
+static int (*get_power)(void);
+static int (*put_power)(void);
+static int (*get_cdclk)(void);
 
-void hda_display_power(bool enable)
+int hda_display_power(bool enable)
 {
 	if (!get_power || !put_power)
-		return;
+		return -ENODEV;
 
 	pr_debug("HDA display power %s \n",
 			enable ? "Enable" : "Disable");
 	if (enable)
-		get_power();
+		return get_power();
 	else
-		put_power();
+		return put_power();
+}
+
+void haswell_set_bclk(struct azx *chip)
+{
+	int cdclk_freq;
+	unsigned int bclk_m, bclk_n;
+
+	if (!get_cdclk)
+		return;
+
+	cdclk_freq = get_cdclk();
+	switch (cdclk_freq) {
+	case 337500:
+		bclk_m = 16;
+		bclk_n = 225;
+		break;
+
+	case 450000:
+	default: /* default CDCLK 450MHz */
+		bclk_m = 4;
+		bclk_n = 75;
+		break;
+
+	case 540000:
+		bclk_m = 4;
+		bclk_n = 90;
+		break;
+
+	case 675000:
+		bclk_m = 8;
+		bclk_n = 225;
+		break;
+	}
+
+	azx_writew(chip, EM4, bclk_m);
+	azx_writew(chip, EM5, bclk_n);
 }
 
+
 int hda_i915_init(void)
 {
 	int err = 0;
@@ -55,6 +102,10 @@ int hda_i915_init(void)
 		return -ENODEV;
 	}
 
+	get_cdclk = symbol_request(i915_get_cdclk_freq);
+	if (!get_cdclk)	/* may have abnormal BCLK and audio playback rate */
+		pr_warn("hda-i915: get_cdclk symbol get fail\n");
+
 	pr_debug("HDA driver get symbol successfully from i915 module\n");
 
 	return err;
@@ -70,6 +121,10 @@ int hda_i915_exit(void)
 		symbol_put(i915_release_power_well);
 		put_power = NULL;
 	}
+	if (get_cdclk) {
+		symbol_put(i915_get_cdclk_freq);
+		get_cdclk = NULL;
+	}
 
 	return 0;
 }
diff --git a/sound/pci/hda/hda_i915.h b/sound/pci/hda/hda_i915.h
index 5a63da2c53e..e6072c62758 100644
--- a/sound/pci/hda/hda_i915.h
+++ b/sound/pci/hda/hda_i915.h
@@ -17,11 +17,13 @@
 #define __SOUND_HDA_I915_H
 
 #ifdef CONFIG_SND_HDA_I915
-void hda_display_power(bool enable);
+int hda_display_power(bool enable);
+void haswell_set_bclk(struct azx *chip);
 int hda_i915_init(void);
 int hda_i915_exit(void);
 #else
-static inline void hda_display_power(bool enable) {}
+static inline int hda_display_power(bool enable) { return 0; }
+static inline void haswell_set_bclk(struct azx *chip) { return; }
 static inline int hda_i915_init(void)
 {
 	return -ENODEV;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index cd77b9b19b7..83cd19017cf 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -62,9 +62,9 @@
 #include <linux/vga_switcheroo.h>
 #include <linux/firmware.h>
 #include "hda_codec.h"
-#include "hda_i915.h"
 #include "hda_controller.h"
 #include "hda_priv.h"
+#include "hda_i915.h"
 
 
 static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
@@ -227,7 +227,7 @@ enum {
 /* quirks for Intel PCH */
 #define AZX_DCAPS_INTEL_PCH_NOPM \
 	(AZX_DCAPS_SCH_SNOOP | AZX_DCAPS_BUFSIZE | \
-	 AZX_DCAPS_COUNT_LPIB_DELAY)
+	 AZX_DCAPS_COUNT_LPIB_DELAY | AZX_DCAPS_REVERSE_ASSIGN)
 
 #define AZX_DCAPS_INTEL_PCH \
 	(AZX_DCAPS_INTEL_PCH_NOPM | AZX_DCAPS_PM_RUNTIME)
@@ -237,6 +237,12 @@ enum {
 	 AZX_DCAPS_COUNT_LPIB_DELAY | AZX_DCAPS_PM_RUNTIME | \
 	 AZX_DCAPS_I915_POWERWELL)
 
+/* Broadwell HDMI can't use position buffer reliably, force to use LPIB */
+#define AZX_DCAPS_INTEL_BROADWELL \
+	(AZX_DCAPS_SCH_SNOOP | AZX_DCAPS_ALIGN_BUFSIZE | \
+	 AZX_DCAPS_POSFIX_LPIB | AZX_DCAPS_PM_RUNTIME | \
+	 AZX_DCAPS_I915_POWERWELL)
+
 /* quirks for ATI SB / AMD Hudson */
 #define AZX_DCAPS_PRESET_ATI_SB \
 	(AZX_DCAPS_ATI_SNOOP | AZX_DCAPS_NO_TCSEL | \
@@ -282,6 +288,11 @@ static char *driver_short_names[] = {
 	[AZX_DRIVER_GENERIC] = "HD-Audio Generic",
 };
 
+struct hda_intel {
+	struct azx chip;
+};
+
+
 #ifdef CONFIG_X86
 static void __mark_pages_wc(struct azx *chip, struct snd_dma_buffer *dmab, bool on)
 {
@@ -585,7 +596,7 @@ static int azx_suspend(struct device *dev)
 	struct azx *chip = card->private_data;
 	struct azx_pcm *p;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
 	snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
@@ -600,6 +611,7 @@ static int azx_suspend(struct device *dev)
 		free_irq(chip->irq, chip);
 		chip->irq = -1;
 	}
+
 	if (chip->msi)
 		pci_disable_msi(chip->pci);
 	pci_disable_device(pci);
@@ -616,11 +628,13 @@ static int azx_resume(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip = card->private_data;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
-	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
 		hda_display_power(true);
+		haswell_set_bclk(chip);
+	}
 	pci_set_power_state(pci, PCI_D0);
 	pci_restore_state(pci);
 	if (pci_enable_device(pci) < 0) {
@@ -651,7 +665,7 @@ static int azx_runtime_suspend(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip = card->private_data;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
 	if (!(chip->driver_caps & AZX_DCAPS_PM_RUNTIME))
@@ -666,6 +680,7 @@ static int azx_runtime_suspend(struct device *dev)
 	azx_clear_irq_pending(chip);
 	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
 		hda_display_power(false);
+
 	return 0;
 }
 
@@ -677,14 +692,16 @@ static int azx_runtime_resume(struct device *dev)
 	struct hda_codec *codec;
 	int status;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
 	if (!(chip->driver_caps & AZX_DCAPS_PM_RUNTIME))
 		return 0;
 
-	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
 		hda_display_power(true);
+		haswell_set_bclk(chip);
+	}
 
 	/* Read STATESTS before controller reset */
 	status = azx_readw(chip, STATESTS);
@@ -712,7 +729,7 @@ static int azx_runtime_idle(struct device *dev)
 	struct snd_card *card = dev_get_drvdata(dev);
 	struct azx *chip = card->private_data;
 
-	if (chip->disabled)
+	if (chip->disabled || chip->init_failed)
 		return 0;
 
 	if (!power_save_controller ||
@@ -877,6 +894,8 @@ static int register_vga_switcheroo(struct azx *chip)
 static int azx_free(struct azx *chip)
 {
 	struct pci_dev *pci = chip->pci;
+	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
+
 	int i;
 
 	if ((chip->driver_caps & AZX_DCAPS_PM_RUNTIME)
@@ -924,7 +943,7 @@ static int azx_free(struct azx *chip)
 		hda_display_power(false);
 		hda_i915_exit();
 	}
-	kfree(chip);
+	kfree(hda);
 
 	return 0;
 }
@@ -1168,6 +1187,7 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 	static struct snd_device_ops ops = {
 		.dev_free = azx_dev_free,
 	};
+	struct hda_intel *hda;
 	struct azx *chip;
 	int err;
 
@@ -1177,13 +1197,14 @@ static int azx_create(struct snd_card *card, struct pci_dev *pci,
 	if (err < 0)
 		return err;
 
-	chip = kzalloc(sizeof(*chip), GFP_KERNEL);
-	if (!chip) {
-		dev_err(card->dev, "Cannot allocate chip\n");
+	hda = kzalloc(sizeof(*hda), GFP_KERNEL);
+	if (!hda) {
+		dev_err(card->dev, "Cannot allocate hda\n");
 		pci_disable_device(pci);
 		return -ENOMEM;
 	}
 
+	chip = &hda->chip;
 	spin_lock_init(&chip->reg_lock);
 	mutex_init(&chip->open_mutex);
 	chip->card = card;
@@ -1367,14 +1388,12 @@ static int azx_first_init(struct azx *chip)
 	/* initialize streams */
 	azx_init_stream(chip);
 
-	/* workaround for Broadwell HDMI: the first stream is broken,
-	 * so mask it by keeping it as if opened
-	 */
-	if (pci->vendor == 0x8086 && pci->device == 0x160c)
-		chip->azx_dev[0].opened = 1;
-
 	/* initialize chip */
 	azx_init_pci(chip);
+
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL)
+		haswell_set_bclk(chip);
+
 	azx_init_chip(chip, (probe_only[dev] & 2) == 0);
 
 	/* codec detection */
@@ -1656,8 +1675,13 @@ static int azx_probe_continue(struct azx *chip)
 				"Error request power-well from i915\n");
 			goto out_free;
 		}
+		err = hda_display_power(true);
+		if (err < 0) {
+			dev_err(chip->card->dev,
+				"Cannot turn on display power on i915\n");
+			goto out_free;
+		}
 #endif
-		hda_display_power(true);
 	}
 
 	err = azx_first_init(chip);
@@ -1769,7 +1793,7 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_HASWELL },
 	/* Broadwell */
 	{ PCI_DEVICE(0x8086, 0x160c),
-	  .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_HASWELL },
+	  .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_BROADWELL },
 	/* 5 Series/3400 */
 	{ PCI_DEVICE(0x8086, 0x3b56),
 	  .driver_data = AZX_DRIVER_SCH | AZX_DCAPS_INTEL_PCH_NOPM },
diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
index ebd1fa6f015..4e2d4863daa 100644
--- a/sound/pci/hda/hda_local.h
+++ b/sound/pci/hda/hda_local.h
@@ -417,6 +417,27 @@ struct snd_hda_pin_quirk {
 	int value;			/* quirk value */
 };
 
+#ifdef CONFIG_SND_DEBUG_VERBOSE
+
+#define SND_HDA_PIN_QUIRK(_codec, _subvendor, _name, _value, _pins...) \
+	{ .codec = _codec,\
+	  .subvendor = _subvendor,\
+	  .name = _name,\
+	  .value = _value,\
+	  .pins = (const struct hda_pintbl[]) { _pins } \
+	}
+#else
+
+#define SND_HDA_PIN_QUIRK(_codec, _subvendor, _name, _value, _pins...) \
+	{ .codec = _codec,\
+	  .subvendor = _subvendor,\
+	  .value = _value,\
+	  .pins = (const struct hda_pintbl[]) { _pins } \
+	}
+
+#endif
+
+
 /* fixup types */
 enum {
 	HDA_FIXUP_INVALID,
diff --git a/sound/pci/hda/hda_priv.h b/sound/pci/hda/hda_priv.h
index 4a7cb01fa91..e9d1a5762a5 100644
--- a/sound/pci/hda/hda_priv.h
+++ b/sound/pci/hda/hda_priv.h
@@ -186,6 +186,7 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 #define AZX_DCAPS_BUFSIZE	(1 << 21)	/* no buffer size alignment */
 #define AZX_DCAPS_ALIGN_BUFSIZE	(1 << 22)	/* buffer size alignment */
 #define AZX_DCAPS_4K_BDLE_BOUNDARY (1 << 23)	/* BDLE in 4k boundary */
+#define AZX_DCAPS_REVERSE_ASSIGN (1 << 24)	/* Assign devices in reverse order */
 #define AZX_DCAPS_COUNT_LPIB_DELAY  (1 << 25)	/* Take LPIB as delay */
 #define AZX_DCAPS_PM_RUNTIME	(1 << 26)	/* runtime PM support */
 #define AZX_DCAPS_I915_POWERWELL (1 << 27)	/* HSW i915 powerwell support */
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index a366ba9293a..358414da641 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -236,6 +236,7 @@ disable_hda:
 	return rc;
 }
 
+#ifdef CONFIG_PM_SLEEP
 static void hda_tegra_disable_clocks(struct hda_tegra *data)
 {
 	clk_disable_unprepare(data->hda2hdmi_clk);
@@ -243,7 +244,6 @@ static void hda_tegra_disable_clocks(struct hda_tegra *data)
 	clk_disable_unprepare(data->hda_clk);
 }
 
-#ifdef CONFIG_PM_SLEEP
 /*
  * power management
  */
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index be0a9ee0b80..ba4ca52072f 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1594,10 +1594,18 @@ static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll)
 		 * Re-setup pin and infoframe. This is needed e.g. when
 		 * - sink is first plugged-in (infoframe is not set up if !monitor_present)
 		 * - transcoder can change during stream playback on Haswell
+		 *   and this can make HW reset converter selection on a pin.
 		 */
-		if (eld->eld_valid && !old_eld_valid && per_pin->setup)
+		if (eld->eld_valid && !old_eld_valid && per_pin->setup) {
+			if (is_haswell_plus(codec) || is_valleyview(codec)) {
+				intel_verify_pin_cvt_connect(codec, per_pin);
+				intel_not_share_assigned_cvt(codec, pin_nid,
+							per_pin->mux_idx);
+			}
+
 			hdmi_setup_audio_infoframe(codec, per_pin,
 						   per_pin->non_pcm);
+		}
 	}
 
 	if (eld_changed)
@@ -2196,7 +2204,7 @@ static int generic_hdmi_resume(struct hda_codec *codec)
 	struct hdmi_spec *spec = codec->spec;
 	int pin_idx;
 
-	generic_hdmi_init(codec);
+	codec->patch_ops.init(codec);
 	snd_hda_codec_resume_amp(codec);
 	snd_hda_codec_resume_cache(codec);
 
@@ -3329,6 +3337,7 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = {
 { .id = 0x10de0051, .name = "GPU 51 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0060, .name = "GPU 60 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0067, .name = "MCP67 HDMI",	.patch = patch_nvhdmi_2ch },
+{ .id = 0x10de0070, .name = "GPU 70 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0071, .name = "GPU 71 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de8001, .name = "MCP73 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x11069f80, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
@@ -3386,6 +3395,7 @@ MODULE_ALIAS("snd-hda-codec-id:10de0044");
 MODULE_ALIAS("snd-hda-codec-id:10de0051");
 MODULE_ALIAS("snd-hda-codec-id:10de0060");
 MODULE_ALIAS("snd-hda-codec-id:10de0067");
+MODULE_ALIAS("snd-hda-codec-id:10de0070");
 MODULE_ALIAS("snd-hda-codec-id:10de0071");
 MODULE_ALIAS("snd-hda-codec-id:10de8001");
 MODULE_ALIAS("snd-hda-codec-id:11069f80");
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 12fb411adf7..b60824e9040 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -929,6 +929,7 @@ struct alc_codec_rename_pci_table {
 };
 
 static struct alc_codec_rename_table rename_tbl[] = {
+	{ 0x10ec0221, 0xf00f, 0x1003, "ALC231" },
 	{ 0x10ec0269, 0xfff0, 0x3010, "ALC277" },
 	{ 0x10ec0269, 0xf0f0, 0x2010, "ALC259" },
 	{ 0x10ec0269, 0xf0f0, 0x3010, "ALC258" },
@@ -937,6 +938,7 @@ static struct alc_codec_rename_table rename_tbl[] = {
 	{ 0x10ec0269, 0xffff, 0x6023, "ALC281X" },
 	{ 0x10ec0269, 0x00f0, 0x0020, "ALC269VC" },
 	{ 0x10ec0269, 0x00f0, 0x0030, "ALC269VD" },
+	{ 0x10ec0662, 0xffff, 0x4020, "ALC656" },
 	{ 0x10ec0887, 0x00f0, 0x0030, "ALC887-VD" },
 	{ 0x10ec0888, 0x00f0, 0x0030, "ALC888-VD" },
 	{ 0x10ec0888, 0xf0f0, 0x3020, "ALC886" },
@@ -956,6 +958,19 @@ static struct alc_codec_rename_pci_table rename_pci_tbl[] = {
 	{ 0x10ec0293, 0x1028, 0, "ALC3235" },
 	{ 0x10ec0255, 0x1028, 0, "ALC3234" },
 	{ 0x10ec0668, 0x1028, 0, "ALC3661" },
+	{ 0x10ec0275, 0x1028, 0, "ALC3260" },
+	{ 0x10ec0899, 0x1028, 0, "ALC3861" },
+	{ 0x10ec0670, 0x1025, 0, "ALC669X" },
+	{ 0x10ec0676, 0x1025, 0, "ALC679X" },
+	{ 0x10ec0282, 0x1043, 0, "ALC3229" },
+	{ 0x10ec0233, 0x1043, 0, "ALC3236" },
+	{ 0x10ec0280, 0x103c, 0, "ALC3228" },
+	{ 0x10ec0282, 0x103c, 0, "ALC3227" },
+	{ 0x10ec0286, 0x103c, 0, "ALC3242" },
+	{ 0x10ec0290, 0x103c, 0, "ALC3241" },
+	{ 0x10ec0668, 0x103c, 0, "ALC3662" },
+	{ 0x10ec0283, 0x17aa, 0, "ALC3239" },
+	{ 0x10ec0292, 0x17aa, 0, "ALC3232" },
 	{ } /* terminator */
 };
 
@@ -1412,6 +1427,7 @@ static const struct snd_pci_quirk alc880_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x10c3, "ASUS W5A", ALC880_FIXUP_ASUS_W5A),
 	SND_PCI_QUIRK(0x1043, 0x1964, "ASUS Z71V", ALC880_FIXUP_Z71V),
 	SND_PCI_QUIRK_VENDOR(0x1043, "ASUS", ALC880_FIXUP_GPIO1),
+	SND_PCI_QUIRK(0x147b, 0x1045, "ABit AA8XE", ALC880_FIXUP_6ST_AUTOMUTE),
 	SND_PCI_QUIRK(0x1558, 0x5401, "Clevo GPIO2", ALC880_FIXUP_GPIO2),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo", ALC880_FIXUP_EAPD_COEF),
 	SND_PCI_QUIRK(0x1584, 0x9050, "Uniwill", ALC880_FIXUP_UNIWILL_DIG),
@@ -4230,6 +4246,7 @@ enum {
 	ALC269_FIXUP_HEADSET_MIC,
 	ALC269_FIXUP_QUANTA_MUTE,
 	ALC269_FIXUP_LIFEBOOK,
+	ALC269_FIXUP_LIFEBOOK_EXTMIC,
 	ALC269_FIXUP_AMIC,
 	ALC269_FIXUP_DMIC,
 	ALC269VB_FIXUP_AMIC,
@@ -4367,6 +4384,13 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_QUANTA_MUTE
 	},
+	[ALC269_FIXUP_LIFEBOOK_EXTMIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x01a1903c }, /* headset mic, with jack detect */
+			{ }
+		},
+	},
 	[ALC269_FIXUP_AMIC] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -4741,18 +4765,12 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0614, "Dell Inspiron 3135", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0615, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK),
-	SND_PCI_QUIRK(0x1028, 0x062c, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0638, "Dell Inspiron 5439", ALC290_FIXUP_MONO_SPEAKERS_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x063f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x064d, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0668, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0669, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0674, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x067e, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x067f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x0680, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0684, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
@@ -4764,14 +4782,24 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
 	/* ALC282 */
+	SND_PCI_QUIRK(0x103c, 0x220d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x220e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2210, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2211, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2212, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2214, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x226f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -4811,6 +4839,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2334, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -4834,6 +4866,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x104d, 0x9099, "Sony VAIO S13", ALC275_FIXUP_SONY_DISABLE_AAMIX),
 	SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO),
 	SND_PCI_QUIRK(0x10cf, 0x1475, "Lifebook", ALC269_FIXUP_LIFEBOOK),
+	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
 	SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
@@ -4847,6 +4880,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x2208, "Thinkpad T431s", ALC269_FIXUP_LENOVO_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x220c, "Thinkpad T440s", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x220e, "Thinkpad T440p", ALC292_FIXUP_TPT440_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x2210, "Thinkpad T540p", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -4929,208 +4963,141 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 };
 
 static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
-	{
-		.codec = 0x10ec0255,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x90a60140},
-			{0x14, 0x90170110},
-			{0x17, 0x40000000},
-			{0x18, 0x411111f0},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40700001},
-			{0x1e, 0x411111f0},
-			{0x21, 0x02211020},
-		},
-		.value = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-	},
-	{
-		.codec = 0x10ec0255,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x90a60160},
-			{0x14, 0x90170120},
-			{0x17, 0x40000000},
-			{0x18, 0x411111f0},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40700001},
-			{0x1e, 0x411111f0},
-			{0x21, 0x02211030},
-		},
-		.value = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-	},
-	{
-		.codec = 0x10ec0255,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x90a60160},
-			{0x14, 0x90170130},
-			{0x17, 0x40000000},
-			{0x18, 0x411111f0},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40700001},
-			{0x1e, 0x411111f0},
-			{0x21, 0x02211040},
-		},
-		.value = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-	},
-	{
-		.codec = 0x10ec0255,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x90a60160},
-			{0x14, 0x90170140},
-			{0x17, 0x40000000},
-			{0x18, 0x411111f0},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40700001},
-			{0x1e, 0x411111f0},
-			{0x21, 0x02211050},
-		},
-		.value = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-	},
-	{
-		.codec = 0x10ec0255,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x90a60170},
-			{0x14, 0x90170120},
-			{0x17, 0x40000000},
-			{0x18, 0x411111f0},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40700001},
-			{0x1e, 0x411111f0},
-			{0x21, 0x02211030},
-		},
-		.value = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-	},
-	{
-		.codec = 0x10ec0255,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x90a60170},
-			{0x14, 0x90170130},
-			{0x17, 0x40000000},
-			{0x18, 0x411111f0},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40700001},
-			{0x1e, 0x411111f0},
-			{0x21, 0x02211040},
-		},
-		.value = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
-	},
-	{
-		.codec = 0x10ec0283,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x90a60130},
-			{0x14, 0x90170110},
-			{0x17, 0x40020008},
-			{0x18, 0x411111f0},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40e00001},
-			{0x1e, 0x411111f0},
-			{0x21, 0x0321101f},
-		},
-		.value = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-	},
-	{
-		.codec = 0x10ec0283,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x90a60160},
-			{0x14, 0x90170120},
-			{0x17, 0x40000000},
-			{0x18, 0x411111f0},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40700001},
-			{0x1e, 0x411111f0},
-			{0x21, 0x02211030},
-		},
-		.value = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-	},
-	{
-		.codec = 0x10ec0292,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x90a60140},
-			{0x13, 0x411111f0},
-			{0x14, 0x90170110},
-			{0x15, 0x0221401f},
-			{0x16, 0x411111f0},
-			{0x18, 0x411111f0},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40700001},
-			{0x1e, 0x411111f0},
-		},
-		.value = ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
-	},
-	{
-		.codec = 0x10ec0293,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x40000000},
-			{0x13, 0x90a60140},
-			{0x14, 0x90170110},
-			{0x15, 0x0221401f},
-			{0x16, 0x21014020},
-			{0x18, 0x411111f0},
-			{0x19, 0x21a19030},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x40700001},
-			{0x1e, 0x411111f0},
-		},
-		.value = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
-	},
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60140},
+		{0x14, 0x90170110},
+		{0x17, 0x40000000},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0},
+		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60160},
+		{0x14, 0x90170120},
+		{0x17, 0x40000000},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0},
+		{0x21, 0x02211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60160},
+		{0x14, 0x90170120},
+		{0x17, 0x90170140},
+		{0x18, 0x40000000},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x41163b05},
+		{0x1e, 0x411111f0},
+		{0x21, 0x0321102f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60160},
+		{0x14, 0x90170130},
+		{0x17, 0x40000000},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0},
+		{0x21, 0x02211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60160},
+		{0x14, 0x90170140},
+		{0x17, 0x40000000},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0},
+		{0x21, 0x02211050}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60170},
+		{0x14, 0x90170120},
+		{0x17, 0x40000000},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0},
+		{0x21, 0x02211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60170},
+		{0x14, 0x90170130},
+		{0x17, 0x40000000},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0},
+		{0x21, 0x02211040}),
+	SND_HDA_PIN_QUIRK(0x10ec0283, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60130},
+		{0x14, 0x90170110},
+		{0x17, 0x40020008},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40e00001},
+		{0x1e, 0x411111f0},
+		{0x21, 0x0321101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0283, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x90a60160},
+		{0x14, 0x90170120},
+		{0x17, 0x40000000},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0},
+		{0x21, 0x02211030}),
+	SND_HDA_PIN_QUIRK(0x10ec0292, 0x1028, "Dell", ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
+		{0x12, 0x90a60140},
+		{0x13, 0x411111f0},
+		{0x14, 0x90170110},
+		{0x15, 0x0221401f},
+		{0x16, 0x411111f0},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0}),
+	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x40000000},
+		{0x13, 0x90a60140},
+		{0x14, 0x90170110},
+		{0x15, 0x0221401f},
+		{0x16, 0x21014020},
+		{0x18, 0x411111f0},
+		{0x19, 0x21a19030},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0}),
+	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x40000000},
+		{0x13, 0x90a60140},
+		{0x14, 0x90170110},
+		{0x15, 0x0221401f},
+		{0x16, 0x411111f0},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0}),
 	{}
 };
 
@@ -5986,69 +5953,66 @@ static const struct hda_model_fixup alc662_fixup_models[] = {
 };
 
 static const struct snd_hda_pin_quirk alc662_pin_fixup_tbl[] = {
-	{
-		.codec = 0x10ec0668,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x99a30130},
-			{0x14, 0x90170110},
-			{0x15, 0x0321101f},
-			{0x16, 0x03011020},
-			{0x18, 0x40000008},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x41000001},
-			{0x1e, 0x411111f0},
-			{0x1f, 0x411111f0},
-		},
-		.value = ALC668_FIXUP_AUTO_MUTE,
-	},
-	{
-		.codec = 0x10ec0668,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x99a30150},
-			{0x14, 0x90170110},
-			{0x15, 0x0321101f},
-			{0x16, 0x03011020},
-			{0x18, 0x40000008},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x41000001},
-			{0x1e, 0x411111f0},
-			{0x1f, 0x411111f0},
-		},
-		.value = ALC668_FIXUP_AUTO_MUTE,
-	},
-	{
-		.codec = 0x10ec0668,
-		.subvendor = 0x1028,
-#ifdef CONFIG_SND_DEBUG_VERBOSE
-		.name = "Dell",
-#endif
-		.pins = (const struct hda_pintbl[]) {
-			{0x12, 0x411111f0},
-			{0x14, 0x90170110},
-			{0x15, 0x0321101f},
-			{0x16, 0x03011020},
-			{0x18, 0x40000008},
-			{0x19, 0x411111f0},
-			{0x1a, 0x411111f0},
-			{0x1b, 0x411111f0},
-			{0x1d, 0x41000001},
-			{0x1e, 0x411111f0},
-			{0x1f, 0x411111f0},
-		},
-		.value = ALC668_FIXUP_AUTO_MUTE,
-	},
+	SND_HDA_PIN_QUIRK(0x10ec0668, 0x1028, "Dell", ALC668_FIXUP_AUTO_MUTE,
+		{0x12, 0x99a30130},
+		{0x14, 0x90170110},
+		{0x15, 0x0321101f},
+		{0x16, 0x03011020},
+		{0x18, 0x40000008},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x41000001},
+		{0x1e, 0x411111f0},
+		{0x1f, 0x411111f0}),
+	SND_HDA_PIN_QUIRK(0x10ec0668, 0x1028, "Dell", ALC668_FIXUP_AUTO_MUTE,
+		{0x12, 0x99a30140},
+		{0x14, 0x90170110},
+		{0x15, 0x0321101f},
+		{0x16, 0x03011020},
+		{0x18, 0x40000008},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x41000001},
+		{0x1e, 0x411111f0},
+		{0x1f, 0x411111f0}),
+	SND_HDA_PIN_QUIRK(0x10ec0668, 0x1028, "Dell", ALC668_FIXUP_AUTO_MUTE,
+		{0x12, 0x99a30150},
+		{0x14, 0x90170110},
+		{0x15, 0x0321101f},
+		{0x16, 0x03011020},
+		{0x18, 0x40000008},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x41000001},
+		{0x1e, 0x411111f0},
+		{0x1f, 0x411111f0}),
+	SND_HDA_PIN_QUIRK(0x10ec0668, 0x1028, "Dell", ALC668_FIXUP_AUTO_MUTE,
+		{0x12, 0x411111f0},
+		{0x14, 0x90170110},
+		{0x15, 0x0321101f},
+		{0x16, 0x03011020},
+		{0x18, 0x40000008},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x41000001},
+		{0x1e, 0x411111f0},
+		{0x1f, 0x411111f0}),
+	SND_HDA_PIN_QUIRK(0x10ec0668, 0x1028, "Dell XPS 15", ALC668_FIXUP_AUTO_MUTE,
+		{0x12, 0x90a60130},
+		{0x14, 0x90170110},
+		{0x15, 0x0321101f},
+		{0x16, 0x40000000},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x411111f0},
+		{0x1d, 0x40d6832d},
+		{0x1e, 0x411111f0},
+		{0x1f, 0x411111f0}),
 	{}
 };
 
@@ -6190,6 +6154,7 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	{ .id = 0x10ec0221, .name = "ALC221", .patch = patch_alc269 },
 	{ .id = 0x10ec0231, .name = "ALC231", .patch = patch_alc269 },
 	{ .id = 0x10ec0233, .name = "ALC233", .patch = patch_alc269 },
+	{ .id = 0x10ec0235, .name = "ALC233", .patch = patch_alc269 },
 	{ .id = 0x10ec0255, .name = "ALC255", .patch = patch_alc269 },
 	{ .id = 0x10ec0260, .name = "ALC260", .patch = patch_alc260 },
 	{ .id = 0x10ec0262, .name = "ALC262", .patch = patch_alc262 },
@@ -6223,10 +6188,12 @@ static const struct hda_codec_preset snd_hda_preset_realtek[] = {
 	  .patch = patch_alc662 },
 	{ .id = 0x10ec0663, .name = "ALC663", .patch = patch_alc662 },
 	{ .id = 0x10ec0665, .name = "ALC665", .patch = patch_alc662 },
+	{ .id = 0x10ec0667, .name = "ALC667", .patch = patch_alc662 },
 	{ .id = 0x10ec0668, .name = "ALC668", .patch = patch_alc662 },
 	{ .id = 0x10ec0670, .name = "ALC670", .patch = patch_alc662 },
 	{ .id = 0x10ec0671, .name = "ALC671", .patch = patch_alc662 },
 	{ .id = 0x10ec0680, .name = "ALC680", .patch = patch_alc680 },
+	{ .id = 0x10ec0867, .name = "ALC891", .patch = patch_alc882 },
 	{ .id = 0x10ec0880, .name = "ALC880", .patch = patch_alc880 },
 	{ .id = 0x10ec0882, .name = "ALC882", .patch = patch_alc882 },
 	{ .id = 0x10ec0883, .name = "ALC883", .patch = patch_alc882 },
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 7f40a150899..3744ea4e843 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -122,6 +122,12 @@ enum {
 };
 
 enum {
+	STAC_92HD95_HP_LED,
+	STAC_92HD95_HP_BASS,
+	STAC_92HD95_MODELS
+};
+
+enum {
 	STAC_925x_REF,
 	STAC_M1,
 	STAC_M1_2,
@@ -4128,6 +4134,48 @@ static const struct snd_pci_quirk stac9205_fixup_tbl[] = {
 	{} /* terminator */
 };
 
+static void stac92hd95_fixup_hp_led(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	struct sigmatel_spec *spec = codec->spec;
+
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+
+	if (find_mute_led_cfg(codec, spec->default_polarity))
+		codec_dbg(codec, "mute LED gpio %d polarity %d\n",
+				spec->gpio_led,
+				spec->gpio_led_polarity);
+}
+
+static const struct hda_fixup stac92hd95_fixups[] = {
+	[STAC_92HD95_HP_LED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = stac92hd95_fixup_hp_led,
+	},
+	[STAC_92HD95_HP_BASS] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			{0x1a, 0x795, 0x00}, /* HPF to 100Hz */
+			{}
+		},
+		.chained = true,
+		.chain_id = STAC_92HD95_HP_LED,
+	},
+};
+
+static const struct snd_pci_quirk stac92hd95_fixup_tbl[] = {
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1911, "HP Spectre 13", STAC_92HD95_HP_BASS),
+	{} /* terminator */
+};
+
+static const struct hda_model_fixup stac92hd95_models[] = {
+	{ .id = STAC_92HD95_HP_LED, .name = "hp-led" },
+	{ .id = STAC_92HD95_HP_BASS, .name = "hp-bass" },
+	{}
+};
+
+
 static int stac_parse_auto_config(struct hda_codec *codec)
 {
 	struct sigmatel_spec *spec = codec->spec;
@@ -4580,10 +4628,16 @@ static int patch_stac92hd95(struct hda_codec *codec)
 	spec->gen.beep_nid = 0x19; /* digital beep */
 	spec->pwr_nids = stac92hd95_pwr_nids;
 	spec->num_pwrs = ARRAY_SIZE(stac92hd95_pwr_nids);
-	spec->default_polarity = -1; /* no default cfg */
+	spec->default_polarity = 0;
 
 	codec->patch_ops = stac_patch_ops;
 
+	snd_hda_pick_fixup(codec, stac92hd95_models, stac92hd95_fixup_tbl,
+			   stac92hd95_fixups);
+	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
+
+	stac_setup_gpio(codec);
+
 	err = stac_parse_auto_config(codec);
 	if (err < 0) {
 		stac_free(codec);
@@ -4592,6 +4646,8 @@ static int patch_stac92hd95(struct hda_codec *codec)
 
 	codec->proc_widget_hook = stac92hd_proc_hook;
 
+	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
+
 	return 0;
 }
 
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 68340d7df76..c91860e0a28 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -2779,7 +2779,7 @@ static void intel8x0_measure_ac97_clock(struct intel8x0 *chip)
 	unsigned long port;
 	unsigned long pos, pos1, t;
 	int civ, timeout = 1000, attempt = 1;
-	struct timespec start_time, stop_time;
+	ktime_t start_time, stop_time;
 
 	if (chip->ac97_bus->clock != 48000)
 		return; /* specified in module option */
@@ -2813,7 +2813,7 @@ static void intel8x0_measure_ac97_clock(struct intel8x0 *chip)
 		iputbyte(chip, port + ICH_REG_OFF_CR, ICH_IOCE);
 		iputdword(chip, ICHREG(ALI_DMACR), 1 << ichdev->ali_slot);
 	}
-	do_posix_clock_monotonic_gettime(&start_time);
+	start_time = ktime_get();
 	spin_unlock_irq(&chip->reg_lock);
 	msleep(50);
 	spin_lock_irq(&chip->reg_lock);
@@ -2837,7 +2837,7 @@ static void intel8x0_measure_ac97_clock(struct intel8x0 *chip)
 		pos += ichdev->position;
 	}
 	chip->in_measurement = 0;
-	do_posix_clock_monotonic_gettime(&stop_time);
+	stop_time = ktime_get();
 	/* stop */
 	if (chip->device_type == DEVICE_ALI) {
 		iputdword(chip, ICHREG(ALI_DMACR), 1 << (ichdev->ali_slot + 16));
@@ -2865,9 +2865,7 @@ static void intel8x0_measure_ac97_clock(struct intel8x0 *chip)
 	}
 
 	pos /= 4;
-	t = stop_time.tv_sec - start_time.tv_sec;
-	t *= 1000000;
-	t += (stop_time.tv_nsec - start_time.tv_nsec) / 1000;
+	t = ktime_us_delta(stop_time, start_time);
 	dev_info(chip->card->dev,
 		 "%s: measured %lu usecs (%lu samples)\n", __func__, t, pos);
 	if (t == 0) {
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index cbfa1e18f65..0b9571c858f 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -225,11 +225,11 @@ config SND_SOC_ADAU1373
 config SND_SOC_ADAU1701
 	tristate "Analog Devices ADAU1701 CODEC"
 	depends on I2C
-	select SND_SOC_SIGMADSP
+	select SND_SOC_SIGMADSP_I2C
 
 config SND_SOC_ADAU17X1
 	tristate
-	select SND_SOC_SIGMADSP
+	select SND_SOC_SIGMADSP_REGMAP
 
 config SND_SOC_ADAU1761
 	tristate
@@ -476,6 +476,14 @@ config SND_SOC_SIGMADSP
 	tristate
 	select CRC32
 
+config SND_SOC_SIGMADSP_I2C
+	tristate
+	select SND_SOC_SIGMADSP
+
+config SND_SOC_SIGMADSP_REGMAP
+	tristate
+	select SND_SOC_SIGMADSP
+
 config SND_SOC_SIRF_AUDIO_CODEC
 	tristate "SiRF SoC internal audio codec"
 	select REGMAP_MMIO
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index be3377b8d73..1bd6e1cf6f8 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -77,6 +77,8 @@ snd-soc-sgtl5000-objs := sgtl5000.o
 snd-soc-alc5623-objs := alc5623.o
 snd-soc-alc5632-objs := alc5632.o
 snd-soc-sigmadsp-objs := sigmadsp.o
+snd-soc-sigmadsp-i2c-objs := sigmadsp-i2c.o
+snd-soc-sigmadsp-regmap-objs := sigmadsp-regmap.o
 snd-soc-si476x-objs := si476x.o
 snd-soc-sirf-audio-codec-objs := sirf-audio-codec.o
 snd-soc-sn95031-objs := sn95031.o
@@ -240,6 +242,8 @@ obj-$(CONFIG_SND_SOC_RT5651)	+= snd-soc-rt5651.o
 obj-$(CONFIG_SND_SOC_RT5677)	+= snd-soc-rt5677.o
 obj-$(CONFIG_SND_SOC_SGTL5000)  += snd-soc-sgtl5000.o
 obj-$(CONFIG_SND_SOC_SIGMADSP)	+= snd-soc-sigmadsp.o
+obj-$(CONFIG_SND_SOC_SIGMADSP_I2C)	+= snd-soc-sigmadsp-i2c.o
+obj-$(CONFIG_SND_SOC_SIGMADSP_REGMAP)	+= snd-soc-sigmadsp-regmap.o
 obj-$(CONFIG_SND_SOC_SI476X)	+= snd-soc-si476x.o
 obj-$(CONFIG_SND_SOC_SN95031)	+=snd-soc-sn95031.o
 obj-$(CONFIG_SND_SOC_SPDIF)	+= snd-soc-spdif-rx.o snd-soc-spdif-tx.o
diff --git a/sound/soc/codecs/sigmadsp-i2c.c b/sound/soc/codecs/sigmadsp-i2c.c
new file mode 100644
index 00000000000..246081aae8c
--- /dev/null
+++ b/sound/soc/codecs/sigmadsp-i2c.c
@@ -0,0 +1,35 @@
+/*
+ * Load Analog Devices SigmaStudio firmware files
+ *
+ * Copyright 2009-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/i2c.h>
+#include <linux/export.h>
+#include <linux/module.h>
+
+#include "sigmadsp.h"
+
+static int sigma_action_write_i2c(void *control_data,
+	const struct sigma_action *sa, size_t len)
+{
+	return i2c_master_send(control_data, (const unsigned char *)&sa->addr,
+		len);
+}
+
+int process_sigma_firmware(struct i2c_client *client, const char *name)
+{
+	struct sigma_firmware ssfw;
+
+	ssfw.control_data = client;
+	ssfw.write = sigma_action_write_i2c;
+
+	return _process_sigma_firmware(&client->dev, &ssfw, name);
+}
+EXPORT_SYMBOL(process_sigma_firmware);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("SigmaDSP I2C firmware loader");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/sigmadsp-regmap.c b/sound/soc/codecs/sigmadsp-regmap.c
new file mode 100644
index 00000000000..f78ed8d2cfb
--- /dev/null
+++ b/sound/soc/codecs/sigmadsp-regmap.c
@@ -0,0 +1,36 @@
+/*
+ * Load Analog Devices SigmaStudio firmware files
+ *
+ * Copyright 2009-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/regmap.h>
+#include <linux/export.h>
+#include <linux/module.h>
+
+#include "sigmadsp.h"
+
+static int sigma_action_write_regmap(void *control_data,
+	const struct sigma_action *sa, size_t len)
+{
+	return regmap_raw_write(control_data, be16_to_cpu(sa->addr),
+		sa->payload, len - 2);
+}
+
+int process_sigma_firmware_regmap(struct device *dev, struct regmap *regmap,
+	const char *name)
+{
+	struct sigma_firmware ssfw;
+
+	ssfw.control_data = regmap;
+	ssfw.write = sigma_action_write_regmap;
+
+	return _process_sigma_firmware(dev, &ssfw, name);
+}
+EXPORT_SYMBOL(process_sigma_firmware_regmap);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("SigmaDSP regmap firmware loader");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/sigmadsp.c b/sound/soc/codecs/sigmadsp.c
index 4068f249123..f2de7e049bc 100644
--- a/sound/soc/codecs/sigmadsp.c
+++ b/sound/soc/codecs/sigmadsp.c
@@ -34,23 +34,6 @@ enum {
 	SIGMA_ACTION_END,
 };
 
-struct sigma_action {
-	u8 instr;
-	u8 len_hi;
-	__le16 len;
-	__be16 addr;
-	unsigned char payload[];
-} __packed;
-
-struct sigma_firmware {
-	const struct firmware *fw;
-	size_t pos;
-
-	void *control_data;
-	int (*write)(void *control_data, const struct sigma_action *sa,
-			size_t len);
-};
-
 static inline u32 sigma_action_len(struct sigma_action *sa)
 {
 	return (sa->len_hi << 16) | le16_to_cpu(sa->len);
@@ -138,7 +121,7 @@ process_sigma_actions(struct sigma_firmware *ssfw)
 	return 0;
 }
 
-static int _process_sigma_firmware(struct device *dev,
+int _process_sigma_firmware(struct device *dev,
 	struct sigma_firmware *ssfw, const char *name)
 {
 	int ret;
@@ -197,50 +180,6 @@ static int _process_sigma_firmware(struct device *dev,
 
 	return ret;
 }
-
-#if IS_ENABLED(CONFIG_I2C)
-
-static int sigma_action_write_i2c(void *control_data,
-	const struct sigma_action *sa, size_t len)
-{
-	return i2c_master_send(control_data, (const unsigned char *)&sa->addr,
-		len);
-}
-
-int process_sigma_firmware(struct i2c_client *client, const char *name)
-{
-	struct sigma_firmware ssfw;
-
-	ssfw.control_data = client;
-	ssfw.write = sigma_action_write_i2c;
-
-	return _process_sigma_firmware(&client->dev, &ssfw, name);
-}
-EXPORT_SYMBOL(process_sigma_firmware);
-
-#endif
-
-#if IS_ENABLED(CONFIG_REGMAP)
-
-static int sigma_action_write_regmap(void *control_data,
-	const struct sigma_action *sa, size_t len)
-{
-	return regmap_raw_write(control_data, be16_to_cpu(sa->addr),
-		sa->payload, len - 2);
-}
-
-int process_sigma_firmware_regmap(struct device *dev, struct regmap *regmap,
-	const char *name)
-{
-	struct sigma_firmware ssfw;
-
-	ssfw.control_data = regmap;
-	ssfw.write = sigma_action_write_regmap;
-
-	return _process_sigma_firmware(dev, &ssfw, name);
-}
-EXPORT_SYMBOL(process_sigma_firmware_regmap);
-
-#endif
+EXPORT_SYMBOL_GPL(_process_sigma_firmware);
 
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/sigmadsp.h b/sound/soc/codecs/sigmadsp.h
index e439cbd7af7..c47cd23e982 100644
--- a/sound/soc/codecs/sigmadsp.h
+++ b/sound/soc/codecs/sigmadsp.h
@@ -12,6 +12,26 @@
 #include <linux/device.h>
 #include <linux/regmap.h>
 
+struct sigma_action {
+	u8 instr;
+	u8 len_hi;
+	__le16 len;
+	__be16 addr;
+	unsigned char payload[];
+} __packed;
+
+struct sigma_firmware {
+	const struct firmware *fw;
+	size_t pos;
+
+	void *control_data;
+	int (*write)(void *control_data, const struct sigma_action *sa,
+			size_t len);
+};
+
+int _process_sigma_firmware(struct device *dev,
+	struct sigma_firmware *ssfw, const char *name);
+
 struct i2c_client;
 
 extern int process_sigma_firmware(struct i2c_client *client, const char *name);
diff --git a/sound/soc/fsl/fsl_dma.c b/sound/soc/fsl/fsl_dma.c
index 6bb0ea59284..a609aafc994 100644
--- a/sound/soc/fsl/fsl_dma.c
+++ b/sound/soc/fsl/fsl_dma.c
@@ -923,8 +923,8 @@ static int fsl_soc_dma_probe(struct platform_device *pdev)
 	dma->dai.pcm_free = fsl_dma_free_dma_buffers;
 
 	/* Store the SSI-specific information that we need */
-	dma->ssi_stx_phys = res.start + offsetof(struct ccsr_ssi, stx0);
-	dma->ssi_srx_phys = res.start + offsetof(struct ccsr_ssi, srx0);
+	dma->ssi_stx_phys = res.start + CCSR_SSI_STX0;
+	dma->ssi_srx_phys = res.start + CCSR_SSI_SRX0;
 
 	iprop = of_get_property(ssi_np, "fsl,fifo-depth", NULL);
 	if (iprop)
diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c
index b912d45a2a4..d7a60614dd2 100644
--- a/sound/soc/fsl/fsl_spdif.c
+++ b/sound/soc/fsl/fsl_spdif.c
@@ -762,7 +762,7 @@ static int fsl_spdif_vbit_get(struct snd_kcontrol *kcontrol,
 	struct regmap *regmap = spdif_priv->regmap;
 	u32 val;
 
-	val = regmap_read(regmap, REG_SPDIF_SIS, &val);
+	regmap_read(regmap, REG_SPDIF_SIS, &val);
 	ucontrol->value.integer.value[0] = (val & INT_VAL_NOGOOD) != 0;
 	regmap_write(regmap, REG_SPDIF_SIC, INT_VAL_NOGOOD);
 
@@ -1076,7 +1076,7 @@ static u32 fsl_spdif_txclk_caldiv(struct fsl_spdif_priv *spdif_priv,
 				goto out;
 			} else if (arate / rate[index] == 1) {
 				/* A little bigger than expect */
-				sub = (arate - rate[index]) * 100000;
+				sub = (u64)(arate - rate[index]) * 100000;
 				do_div(sub, rate[index]);
 				if (sub >= savesub)
 					continue;
@@ -1086,7 +1086,7 @@ static u32 fsl_spdif_txclk_caldiv(struct fsl_spdif_priv *spdif_priv,
 				spdif_priv->txrate[index] = arate;
 			} else if (rate[index] / arate == 1) {
 				/* A little smaller than expect */
-				sub = (rate[index] - arate) * 100000;
+				sub = (u64)(rate[index] - arate) * 100000;
 				do_div(sub, rate[index]);
 				if (sub >= savesub)
 					continue;
diff --git a/sound/soc/fsl/imx-pcm-dma.c b/sound/soc/fsl/imx-pcm-dma.c
index 0849b7b83f0..0db94f492e9 100644
--- a/sound/soc/fsl/imx-pcm-dma.c
+++ b/sound/soc/fsl/imx-pcm-dma.c
@@ -59,7 +59,6 @@ int imx_pcm_dma_init(struct platform_device *pdev)
 {
 	return devm_snd_dmaengine_pcm_register(&pdev->dev,
 		&imx_dmaengine_pcm_config,
-		SND_DMAENGINE_PCM_FLAG_NO_RESIDUE |
 		SND_DMAENGINE_PCM_FLAG_COMPAT);
 }
 EXPORT_SYMBOL_GPL(imx_pcm_dma_init);
diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 6acb225ec6f..2434b6d6167 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -11,6 +11,7 @@ config SND_PXA2XX_SOC
 config SND_MMP_SOC
 	bool "Soc Audio for Marvell MMP chips"
 	depends on ARCH_MMP
+	select MMP_SRAM
 	select SND_SOC_GENERIC_DMAENGINE_PCM
 	select SND_ARM
 	help
@@ -40,7 +41,7 @@ config SND_MMP_SOC_SSPA
 
 config SND_PXA2XX_SOC_CORGI
 	tristate "SoC Audio support for Sharp Zaurus SL-C7x0"
-	depends on SND_PXA2XX_SOC && PXA_SHARP_C7xx
+	depends on SND_PXA2XX_SOC && PXA_SHARP_C7xx && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_SOC_WM8731
 	help
@@ -49,7 +50,7 @@ config SND_PXA2XX_SOC_CORGI
 
 config SND_PXA2XX_SOC_SPITZ
 	tristate "SoC Audio support for Sharp Zaurus SL-Cxx00"
-	depends on SND_PXA2XX_SOC && PXA_SHARP_Cxx00
+	depends on SND_PXA2XX_SOC && PXA_SHARP_Cxx00 && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_SOC_WM8750
 	help
@@ -58,7 +59,7 @@ config SND_PXA2XX_SOC_SPITZ
 
 config SND_PXA2XX_SOC_Z2
 	tristate "SoC Audio support for Zipit Z2"
-	depends on SND_PXA2XX_SOC && MACH_ZIPIT2
+	depends on SND_PXA2XX_SOC && MACH_ZIPIT2 && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_SOC_WM8750
 	help
@@ -66,7 +67,7 @@ config SND_PXA2XX_SOC_Z2
 
 config SND_PXA2XX_SOC_POODLE
 	tristate "SoC Audio support for Poodle"
-	depends on SND_PXA2XX_SOC && MACH_POODLE
+	depends on SND_PXA2XX_SOC && MACH_POODLE && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_SOC_WM8731
 	help
@@ -181,7 +182,7 @@ config SND_PXA2XX_SOC_HX4700
 
 config SND_PXA2XX_SOC_MAGICIAN
 	tristate "SoC Audio support for HTC Magician"
-	depends on SND_PXA2XX_SOC && MACH_MAGICIAN
+	depends on SND_PXA2XX_SOC && MACH_MAGICIAN && I2C
 	select SND_PXA2XX_SOC_I2S
 	select SND_PXA_SOC_SSP
 	select SND_SOC_UDA1380
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 91880156e1a..4e86265f625 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -315,7 +315,7 @@ static void rsnd_dma_of_name(struct rsnd_dma *dma,
 		dst_mod = mod[index];
 	} else {
 		src_mod = mod[index];
-		dst_mod = mod[index + 1];
+		dst_mod = mod[index - 1];
 	}
 
 	index = 0;
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index a74b9bf23d9..cdc837ed144 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -2755,7 +2755,7 @@ int snd_soc_dapm_put_volsw(struct snd_kcontrol *kcontrol,
 	unsigned int mask = (1 << fls(max)) - 1;
 	unsigned int invert = mc->invert;
 	unsigned int val;
-	int connect, change;
+	int connect, change, reg_change = 0;
 	struct snd_soc_dapm_update update;
 	int ret = 0;
 
@@ -2773,20 +2773,23 @@ int snd_soc_dapm_put_volsw(struct snd_kcontrol *kcontrol,
 	mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME);
 
 	change = dapm_kcontrol_set_value(kcontrol, val);
-	if (change) {
-		if (reg != SND_SOC_NOPM) {
-			mask = mask << shift;
-			val = val << shift;
-
-			if (snd_soc_test_bits(codec, reg, mask, val)) {
-				update.kcontrol = kcontrol;
-				update.reg = reg;
-				update.mask = mask;
-				update.val = val;
-				card->update = &update;
-			}
 
+	if (reg != SND_SOC_NOPM) {
+		mask = mask << shift;
+		val = val << shift;
+
+		reg_change = snd_soc_test_bits(codec, reg, mask, val);
+	}
+
+	if (change || reg_change) {
+		if (reg_change) {
+			update.kcontrol = kcontrol;
+			update.reg = reg;
+			update.mask = mask;
+			update.val = val;
+			card->update = &update;
 		}
+		change |= reg_change;
 
 		ret = soc_dapm_mixer_update_power(card, kcontrol, connect);
 
diff --git a/sound/usb/card.c b/sound/usb/card.c
index c3b5b7dca1c..a09e5f3519e 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -307,6 +307,11 @@ static int snd_usb_create_streams(struct snd_usb_audio *chip, int ctrlif)
 
 static int snd_usb_audio_free(struct snd_usb_audio *chip)
 {
+	struct list_head *p, *n;
+
+	list_for_each_safe(p, n, &chip->ep_list)
+		snd_usb_endpoint_free(p);
+
 	mutex_destroy(&chip->mutex);
 	kfree(chip);
 	return 0;
@@ -585,7 +590,7 @@ static void snd_usb_audio_disconnect(struct usb_device *dev,
 				     struct snd_usb_audio *chip)
 {
 	struct snd_card *card;
-	struct list_head *p, *n;
+	struct list_head *p;
 
 	if (chip == (void *)-1L)
 		return;
@@ -598,14 +603,16 @@ static void snd_usb_audio_disconnect(struct usb_device *dev,
 	mutex_lock(&register_mutex);
 	chip->num_interfaces--;
 	if (chip->num_interfaces <= 0) {
+		struct snd_usb_endpoint *ep;
+
 		snd_card_disconnect(card);
 		/* release the pcm resources */
 		list_for_each(p, &chip->pcm_list) {
 			snd_usb_stream_disconnect(p);
 		}
 		/* release the endpoint resources */
-		list_for_each_safe(p, n, &chip->ep_list) {
-			snd_usb_endpoint_free(p);
+		list_for_each_entry(ep, &chip->ep_list, list) {
+			snd_usb_endpoint_release(ep);
 		}
 		/* release the midi resources */
 		list_for_each(p, &chip->midi_list) {
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index 289f582c913..114e3e7ff51 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -987,19 +987,30 @@ void snd_usb_endpoint_deactivate(struct snd_usb_endpoint *ep)
 }
 
 /**
+ * snd_usb_endpoint_release: Tear down an snd_usb_endpoint
+ *
+ * @ep: the endpoint to release
+ *
+ * This function does not care for the endpoint's use count but will tear
+ * down all the streaming URBs immediately.
+ */
+void snd_usb_endpoint_release(struct snd_usb_endpoint *ep)
+{
+	release_urbs(ep, 1);
+}
+
+/**
  * snd_usb_endpoint_free: Free the resources of an snd_usb_endpoint
  *
  * @ep: the list header of the endpoint to free
  *
- * This function does not care for the endpoint's use count but will tear
- * down all the streaming URBs immediately and free all resources.
+ * This free all resources of the given ep.
  */
 void snd_usb_endpoint_free(struct list_head *head)
 {
 	struct snd_usb_endpoint *ep;
 
 	ep = list_entry(head, struct snd_usb_endpoint, list);
-	release_urbs(ep, 1);
 	kfree(ep);
 }
 
diff --git a/sound/usb/endpoint.h b/sound/usb/endpoint.h
index 1c7e8ee48ab..e61ee5c356a 100644
--- a/sound/usb/endpoint.h
+++ b/sound/usb/endpoint.h
@@ -23,6 +23,7 @@ void snd_usb_endpoint_stop(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_sync_pending_stop(struct snd_usb_endpoint *ep);
 int  snd_usb_endpoint_activate(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_deactivate(struct snd_usb_endpoint *ep);
+void snd_usb_endpoint_release(struct snd_usb_endpoint *ep);
 void snd_usb_endpoint_free(struct list_head *head);
 
 int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep);
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 5b5eb788996..c1b49c36a95 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -1,8 +1,10 @@
 /* TODO merge/factor in debugfs.c here */
 
+#include <ctype.h>
 #include <errno.h>
 #include <stdbool.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
 #include <sys/vfs.h>
 
@@ -96,12 +98,51 @@ static bool fs__check_mounts(struct fs *fs)
 	return false;
 }
 
+static void mem_toupper(char *f, size_t len)
+{
+	while (len) {
+		*f = toupper(*f);
+		f++;
+		len--;
+	}
+}
+
+/*
+ * Check for "NAME_PATH" environment variable to override fs location (for
+ * testing). This matches the recommendation in Documentation/sysfs-rules.txt
+ * for SYSFS_PATH.
+ */
+static bool fs__env_override(struct fs *fs)
+{
+	char *override_path;
+	size_t name_len = strlen(fs->name);
+	/* name + "_PATH" + '\0' */
+	char upper_name[name_len + 5 + 1];
+	memcpy(upper_name, fs->name, name_len);
+	mem_toupper(upper_name, name_len);
+	strcpy(&upper_name[name_len], "_PATH");
+
+	override_path = getenv(upper_name);
+	if (!override_path)
+		return false;
+
+	fs->found = true;
+	strncpy(fs->path, override_path, sizeof(fs->path));
+	return true;
+}
+
 static const char *fs__get_mountpoint(struct fs *fs)
 {
+	if (fs__env_override(fs))
+		return fs->path;
+
 	if (fs__check_mounts(fs))
 		return fs->path;
 
-	return fs__read_mounts(fs) ? fs->path : NULL;
+	if (fs__read_mounts(fs))
+		return fs->path;
+
+	return NULL;
 }
 
 static const char *fs__mountpoint(int idx)
diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h
index c342f708714..ee53a42818c 100644
--- a/tools/lib/lockdep/include/liblockdep/mutex.h
+++ b/tools/lib/lockdep/include/liblockdep/mutex.h
@@ -35,7 +35,7 @@ static inline int __mutex_init(liblockdep_pthread_mutex_t *lock,
 
 static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_mutex_lock(&lock->mutex);
 }
 
@@ -47,7 +47,7 @@ static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lo
 
 static inline int liblockdep_pthread_mutex_trylock(liblockdep_pthread_mutex_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_mutex_trylock(&lock->mutex) == 0 ? 1 : 0;
 }
 
diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h
index a680ab8c2e3..4ec03f86155 100644
--- a/tools/lib/lockdep/include/liblockdep/rwlock.h
+++ b/tools/lib/lockdep/include/liblockdep/rwlock.h
@@ -36,7 +36,7 @@ static inline int __rwlock_init(liblockdep_pthread_rwlock_t *lock,
 
 static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_rwlock_rdlock(&lock->rwlock);
 
 }
@@ -49,19 +49,19 @@ static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t *
 
 static inline int liblockdep_pthread_rwlock_wrlock(liblockdep_pthread_rwlock_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_rwlock_wrlock(&lock->rwlock);
 }
 
 static inline int liblockdep_pthread_rwlock_tryrdlock(liblockdep_pthread_rwlock_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_rwlock_tryrdlock(&lock->rwlock) == 0 ? 1 : 0;
 }
 
 static inline int liblockdep_pthread_rwlock_trywlock(liblockdep_pthread_rwlock_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_rwlock_trywlock(&lock->rwlock) == 0 ? 1 : 0;
 }
 
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 23bd69cb5ad..6f803609e49 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -92,7 +92,7 @@ enum { none, prepare, done, } __init_state;
 static void init_preload(void);
 static void try_init_preload(void)
 {
-	if (!__init_state != done)
+	if (__init_state != done)
 		init_preload();
 }
 
@@ -252,7 +252,7 @@ int pthread_mutex_lock(pthread_mutex_t *mutex)
 
 	try_init_preload();
 
-	lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL,
+	lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 1, NULL,
 			(unsigned long)_RET_IP_);
 	/*
 	 * Here's the thing with pthread mutexes: unlike the kernel variant,
@@ -281,7 +281,7 @@ int pthread_mutex_trylock(pthread_mutex_t *mutex)
 
 	try_init_preload();
 
-	lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_mutex_trylock(mutex);
 	if (r)
 		lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -303,7 +303,7 @@ int pthread_mutex_unlock(pthread_mutex_t *mutex)
 	 */
 	r = ll_pthread_mutex_unlock(mutex);
 	if (r)
-		lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+		lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -352,7 +352,7 @@ int pthread_rwlock_rdlock(pthread_rwlock_t *rwlock)
 
         init_preload();
 
-	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_rdlock(rwlock);
 	if (r)
 		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -366,7 +366,7 @@ int pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock)
 
         init_preload();
 
-	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_tryrdlock(rwlock);
 	if (r)
 		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -380,7 +380,7 @@ int pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock)
 
         init_preload();
 
-	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_trywrlock(rwlock);
 	if (r)
                 lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -394,7 +394,7 @@ int pthread_rwlock_wrlock(pthread_rwlock_t *rwlock)
 
         init_preload();
 
-	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_wrlock(rwlock);
 	if (r)
 		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -411,7 +411,7 @@ int pthread_rwlock_unlock(pthread_rwlock_t *rwlock)
 	lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_unlock(rwlock);
 	if (r)
-		lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+		lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -439,8 +439,6 @@ __attribute__((constructor)) static void init_preload(void)
 	ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock");
 #endif
 
-	printf("%p\n", ll_pthread_mutex_trylock);fflush(stdout);
-
 	lockdep_init();
 
 	__init_state = done;
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index b83184f2d48..cf3a44bf1ec 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -765,6 +765,9 @@ static void free_arg(struct print_arg *arg)
 	case PRINT_BSTRING:
 		free(arg->string.string);
 		break;
+	case PRINT_BITMASK:
+		free(arg->bitmask.bitmask);
+		break;
 	case PRINT_DYNAMIC_ARRAY:
 		free(arg->dynarray.index);
 		break;
@@ -2268,6 +2271,7 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 	case PRINT_FIELD ... PRINT_SYMBOL:
 	case PRINT_STRING:
 	case PRINT_BSTRING:
+	case PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		ret = 0;
@@ -2296,6 +2300,7 @@ static char *arg_eval (struct print_arg *arg)
 	case PRINT_FIELD ... PRINT_SYMBOL:
 	case PRINT_STRING:
 	case PRINT_BSTRING:
+	case PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		break;
@@ -2390,7 +2395,7 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
 	enum event_type type;
-	char *token;
+	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
 	arg->type = PRINT_FLAGS;
@@ -2443,7 +2448,7 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
 	enum event_type type;
-	char *token;
+	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
 	arg->type = PRINT_SYMBOL;
@@ -2482,7 +2487,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
 	enum event_type type;
-	char *token;
+	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
 	arg->type = PRINT_HEX;
@@ -2683,6 +2688,35 @@ process_str(struct event_format *event __maybe_unused, struct print_arg *arg,
 	return EVENT_ERROR;
 }
 
+static enum event_type
+process_bitmask(struct event_format *event __maybe_unused, struct print_arg *arg,
+	    char **tok)
+{
+	enum event_type type;
+	char *token;
+
+	if (read_expect_type(EVENT_ITEM, &token) < 0)
+		goto out_free;
+
+	arg->type = PRINT_BITMASK;
+	arg->bitmask.bitmask = token;
+	arg->bitmask.offset = -1;
+
+	if (read_expected(EVENT_DELIM, ")") < 0)
+		goto out_err;
+
+	type = read_token(&token);
+	*tok = token;
+
+	return type;
+
+ out_free:
+	free_token(token);
+ out_err:
+	*tok = NULL;
+	return EVENT_ERROR;
+}
+
 static struct pevent_function_handler *
 find_func_handler(struct pevent *pevent, char *func_name)
 {
@@ -2797,6 +2831,10 @@ process_function(struct event_format *event, struct print_arg *arg,
 		free_token(token);
 		return process_str(event, arg, tok);
 	}
+	if (strcmp(token, "__get_bitmask") == 0) {
+		free_token(token);
+		return process_bitmask(event, arg, tok);
+	}
 	if (strcmp(token, "__get_dynamic_array") == 0) {
 		free_token(token);
 		return process_dynamic_array(event, arg, tok);
@@ -3324,6 +3362,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		return eval_type(val, arg, 0);
 	case PRINT_STRING:
 	case PRINT_BSTRING:
+	case PRINT_BITMASK:
 		return 0;
 	case PRINT_FUNC: {
 		struct trace_seq s;
@@ -3556,6 +3595,60 @@ static void print_str_to_seq(struct trace_seq *s, const char *format,
 		trace_seq_printf(s, format, str);
 }
 
+static void print_bitmask_to_seq(struct pevent *pevent,
+				 struct trace_seq *s, const char *format,
+				 int len_arg, const void *data, int size)
+{
+	int nr_bits = size * 8;
+	int str_size = (nr_bits + 3) / 4;
+	int len = 0;
+	char buf[3];
+	char *str;
+	int index;
+	int i;
+
+	/*
+	 * The kernel likes to put in commas every 32 bits, we
+	 * can do the same.
+	 */
+	str_size += (nr_bits - 1) / 32;
+
+	str = malloc(str_size + 1);
+	if (!str) {
+		do_warning("%s: not enough memory!", __func__);
+		return;
+	}
+	str[str_size] = 0;
+
+	/* Start out with -2 for the two chars per byte */
+	for (i = str_size - 2; i >= 0; i -= 2) {
+		/*
+		 * data points to a bit mask of size bytes.
+		 * In the kernel, this is an array of long words, thus
+		 * endianess is very important.
+		 */
+		if (pevent->file_bigendian)
+			index = size - (len + 1);
+		else
+			index = len;
+
+		snprintf(buf, 3, "%02x", *((unsigned char *)data + index));
+		memcpy(str + i, buf, 2);
+		len++;
+		if (!(len & 3) && i > 0) {
+			i--;
+			str[i] = ',';
+		}
+	}
+
+	if (len_arg >= 0)
+		trace_seq_printf(s, format, len_arg, str);
+	else
+		trace_seq_printf(s, format, str);
+
+	free(str);
+}
+
 static void print_str_arg(struct trace_seq *s, void *data, int size,
 			  struct event_format *event, const char *format,
 			  int len_arg, struct print_arg *arg)
@@ -3691,6 +3784,23 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	case PRINT_BSTRING:
 		print_str_to_seq(s, format, len_arg, arg->string.string);
 		break;
+	case PRINT_BITMASK: {
+		int bitmask_offset;
+		int bitmask_size;
+
+		if (arg->bitmask.offset == -1) {
+			struct format_field *f;
+
+			f = pevent_find_any_field(event, arg->bitmask.bitmask);
+			arg->bitmask.offset = f->offset;
+		}
+		bitmask_offset = data2host4(pevent, data + arg->bitmask.offset);
+		bitmask_size = bitmask_offset >> 16;
+		bitmask_offset &= 0xffff;
+		print_bitmask_to_seq(pevent, s, format, len_arg,
+				     data + bitmask_offset, bitmask_size);
+		break;
+	}
 	case PRINT_OP:
 		/*
 		 * The only op for string should be ? :
@@ -4822,6 +4932,9 @@ static void print_args(struct print_arg *args)
 	case PRINT_BSTRING:
 		printf("__get_str(%s)", args->string.string);
 		break;
+	case PRINT_BITMASK:
+		printf("__get_bitmask(%s)", args->bitmask.bitmask);
+		break;
 	case PRINT_TYPE:
 		printf("(%s)", args->typecast.type);
 		print_args(args->typecast.item);
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index feab9428163..7a3873ff9a4 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -107,8 +107,8 @@ typedef int (*pevent_event_handler_func)(struct trace_seq *s,
 typedef int (*pevent_plugin_load_func)(struct pevent *pevent);
 typedef int (*pevent_plugin_unload_func)(struct pevent *pevent);
 
-struct plugin_option {
-	struct plugin_option		*next;
+struct pevent_plugin_option {
+	struct pevent_plugin_option	*next;
 	void				*handle;
 	char				*file;
 	char				*name;
@@ -135,7 +135,7 @@ struct plugin_option {
  * PEVENT_PLUGIN_OPTIONS:  (optional)
  *   Plugin options that can be set before loading
  *
- *   struct plugin_option PEVENT_PLUGIN_OPTIONS[] = {
+ *   struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = {
  *	{
  *		.name = "option-name",
  *		.plugin_alias = "overide-file-name", (optional)
@@ -208,6 +208,11 @@ struct print_arg_string {
 	int			offset;
 };
 
+struct print_arg_bitmask {
+	char			*bitmask;
+	int			offset;
+};
+
 struct print_arg_field {
 	char			*name;
 	struct format_field	*field;
@@ -274,6 +279,7 @@ enum print_arg_type {
 	PRINT_DYNAMIC_ARRAY,
 	PRINT_OP,
 	PRINT_FUNC,
+	PRINT_BITMASK,
 };
 
 struct print_arg {
@@ -288,6 +294,7 @@ struct print_arg {
 		struct print_arg_hex		hex;
 		struct print_arg_func		func;
 		struct print_arg_string		string;
+		struct print_arg_bitmask	bitmask;
 		struct print_arg_op		op;
 		struct print_arg_dynarray	dynarray;
 	};
@@ -354,6 +361,8 @@ enum pevent_func_arg_type {
 
 enum pevent_flag {
 	PEVENT_NSEC_OUTPUT		= 1,	/* output in NSECS */
+	PEVENT_DISABLE_SYS_PLUGINS	= 1 << 1,
+	PEVENT_DISABLE_PLUGINS		= 1 << 2,
 };
 
 #define PEVENT_ERRORS 							      \
@@ -410,9 +419,19 @@ enum pevent_errno {
 
 struct plugin_list;
 
+#define INVALID_PLUGIN_LIST_OPTION	((char **)((unsigned long)-1))
+
 struct plugin_list *traceevent_load_plugins(struct pevent *pevent);
 void traceevent_unload_plugins(struct plugin_list *plugin_list,
 			       struct pevent *pevent);
+char **traceevent_plugin_list_options(void);
+void traceevent_plugin_free_options_list(char **list);
+int traceevent_plugin_add_options(const char *name,
+				  struct pevent_plugin_option *options);
+void traceevent_plugin_remove_options(struct pevent_plugin_option *options);
+void traceevent_print_plugins(struct trace_seq *s,
+			      const char *prefix, const char *suffix,
+			      const struct plugin_list *list);
 
 struct cmdline;
 struct cmdline_list;
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index 0c8bf6780e4..136162c03af 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -18,6 +18,7 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#include <stdio.h>
 #include <string.h>
 #include <dlfcn.h>
 #include <stdlib.h>
@@ -30,12 +31,207 @@
 
 #define LOCAL_PLUGIN_DIR ".traceevent/plugins"
 
+static struct registered_plugin_options {
+	struct registered_plugin_options	*next;
+	struct pevent_plugin_option		*options;
+} *registered_options;
+
+static struct trace_plugin_options {
+	struct trace_plugin_options	*next;
+	char				*plugin;
+	char				*option;
+	char				*value;
+} *trace_plugin_options;
+
 struct plugin_list {
 	struct plugin_list	*next;
 	char			*name;
 	void			*handle;
 };
 
+/**
+ * traceevent_plugin_list_options - get list of plugin options
+ *
+ * Returns an array of char strings that list the currently registered
+ * plugin options in the format of <plugin>:<option>. This list can be
+ * used by toggling the option.
+ *
+ * Returns NULL if there's no options registered. On error it returns
+ * INVALID_PLUGIN_LIST_OPTION
+ *
+ * Must be freed with traceevent_plugin_free_options_list().
+ */
+char **traceevent_plugin_list_options(void)
+{
+	struct registered_plugin_options *reg;
+	struct pevent_plugin_option *op;
+	char **list = NULL;
+	char *name;
+	int count = 0;
+
+	for (reg = registered_options; reg; reg = reg->next) {
+		for (op = reg->options; op->name; op++) {
+			char *alias = op->plugin_alias ? op->plugin_alias : op->file;
+			char **temp = list;
+
+			name = malloc(strlen(op->name) + strlen(alias) + 2);
+			if (!name)
+				goto err;
+
+			sprintf(name, "%s:%s", alias, op->name);
+			list = realloc(list, count + 2);
+			if (!list) {
+				list = temp;
+				free(name);
+				goto err;
+			}
+			list[count++] = name;
+			list[count] = NULL;
+		}
+	}
+	return list;
+
+ err:
+	while (--count >= 0)
+		free(list[count]);
+	free(list);
+
+	return INVALID_PLUGIN_LIST_OPTION;
+}
+
+void traceevent_plugin_free_options_list(char **list)
+{
+	int i;
+
+	if (!list)
+		return;
+
+	if (list == INVALID_PLUGIN_LIST_OPTION)
+		return;
+
+	for (i = 0; list[i]; i++)
+		free(list[i]);
+
+	free(list);
+}
+
+static int
+update_option(const char *file, struct pevent_plugin_option *option)
+{
+	struct trace_plugin_options *op;
+	char *plugin;
+
+	if (option->plugin_alias) {
+		plugin = strdup(option->plugin_alias);
+		if (!plugin)
+			return -1;
+	} else {
+		char *p;
+		plugin = strdup(file);
+		if (!plugin)
+			return -1;
+		p = strstr(plugin, ".");
+		if (p)
+			*p = '\0';
+	}
+
+	/* first look for named options */
+	for (op = trace_plugin_options; op; op = op->next) {
+		if (!op->plugin)
+			continue;
+		if (strcmp(op->plugin, plugin) != 0)
+			continue;
+		if (strcmp(op->option, option->name) != 0)
+			continue;
+
+		option->value = op->value;
+		option->set ^= 1;
+		goto out;
+	}
+
+	/* first look for unnamed options */
+	for (op = trace_plugin_options; op; op = op->next) {
+		if (op->plugin)
+			continue;
+		if (strcmp(op->option, option->name) != 0)
+			continue;
+
+		option->value = op->value;
+		option->set ^= 1;
+		break;
+	}
+
+ out:
+	free(plugin);
+	return 0;
+}
+
+/**
+ * traceevent_plugin_add_options - Add a set of options by a plugin
+ * @name: The name of the plugin adding the options
+ * @options: The set of options being loaded
+ *
+ * Sets the options with the values that have been added by user.
+ */
+int traceevent_plugin_add_options(const char *name,
+				  struct pevent_plugin_option *options)
+{
+	struct registered_plugin_options *reg;
+
+	reg = malloc(sizeof(*reg));
+	if (!reg)
+		return -1;
+	reg->next = registered_options;
+	reg->options = options;
+	registered_options = reg;
+
+	while (options->name) {
+		update_option(name, options);
+		options++;
+	}
+	return 0;
+}
+
+/**
+ * traceevent_plugin_remove_options - remove plugin options that were registered
+ * @options: Options to removed that were registered with traceevent_plugin_add_options
+ */
+void traceevent_plugin_remove_options(struct pevent_plugin_option *options)
+{
+	struct registered_plugin_options **last;
+	struct registered_plugin_options *reg;
+
+	for (last = &registered_options; *last; last = &(*last)->next) {
+		if ((*last)->options == options) {
+			reg = *last;
+			*last = reg->next;
+			free(reg);
+			return;
+		}
+	}
+}
+
+/**
+ * traceevent_print_plugins - print out the list of plugins loaded
+ * @s: the trace_seq descripter to write to
+ * @prefix: The prefix string to add before listing the option name
+ * @suffix: The suffix string ot append after the option name
+ * @list: The list of plugins (usually returned by traceevent_load_plugins()
+ *
+ * Writes to the trace_seq @s the list of plugins (files) that is
+ * returned by traceevent_load_plugins(). Use @prefix and @suffix for formating:
+ * @prefix = "  ", @suffix = "\n".
+ */
+void traceevent_print_plugins(struct trace_seq *s,
+			      const char *prefix, const char *suffix,
+			      const struct plugin_list *list)
+{
+	while (list) {
+		trace_seq_printf(s, "%s%s%s", prefix, list->name, suffix);
+		list = list->next;
+	}
+}
+
 static void
 load_plugin(struct pevent *pevent, const char *path,
 	    const char *file, void *data)
@@ -148,12 +344,17 @@ load_plugins(struct pevent *pevent, const char *suffix,
 	char *path;
 	char *envdir;
 
+	if (pevent->flags & PEVENT_DISABLE_PLUGINS)
+		return;
+
 	/*
 	 * If a system plugin directory was defined,
 	 * check that first.
 	 */
 #ifdef PLUGIN_DIR
-	load_plugins_dir(pevent, suffix, PLUGIN_DIR, load_plugin, data);
+	if (!(pevent->flags & PEVENT_DISABLE_SYS_PLUGINS))
+		load_plugins_dir(pevent, suffix, PLUGIN_DIR,
+				 load_plugin, data);
 #endif
 
 	/*
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index c066b25905f..4592d843831 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -5,8 +5,7 @@
 #include "event-parse.h"
 
 static unsigned long long
-process___le16_to_cpup(struct trace_seq *s,
-		       unsigned long long *args)
+process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
 {
 	uint16_t *val = (uint16_t *) (unsigned long) args[0];
 	return val ? (long long) le16toh(*val) : 0;
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index 80ba4ff1fe8..a00ec190821 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -33,6 +33,29 @@ static int cpus = -1;
 
 #define STK_BLK 10
 
+struct pevent_plugin_option plugin_options[] =
+{
+	{
+		.name = "parent",
+		.plugin_alias = "ftrace",
+		.description =
+		"Print parent of functions for function events",
+	},
+	{
+		.name = "indent",
+		.plugin_alias = "ftrace",
+		.description =
+		"Try to show function call indents, based on parents",
+		.set = 1,
+	},
+	{
+		.name = NULL,
+	}
+};
+
+static struct pevent_plugin_option *ftrace_parent = &plugin_options[0];
+static struct pevent_plugin_option *ftrace_indent = &plugin_options[1];
+
 static void add_child(struct func_stack *stack, const char *child, int pos)
 {
 	int i;
@@ -119,7 +142,8 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
 
 	parent = pevent_find_function(pevent, pfunction);
 
-	index = add_and_get_index(parent, func, record->cpu);
+	if (parent && ftrace_indent->set)
+		index = add_and_get_index(parent, func, record->cpu);
 
 	trace_seq_printf(s, "%*s", index*3, "");
 
@@ -128,11 +152,13 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
 	else
 		trace_seq_printf(s, "0x%llx", function);
 
-	trace_seq_printf(s, " <-- ");
-	if (parent)
-		trace_seq_printf(s, "%s", parent);
-	else
-		trace_seq_printf(s, "0x%llx", pfunction);
+	if (ftrace_parent->set) {
+		trace_seq_printf(s, " <-- ");
+		if (parent)
+			trace_seq_printf(s, "%s", parent);
+		else
+			trace_seq_printf(s, "0x%llx", pfunction);
+	}
 
 	return 0;
 }
@@ -141,6 +167,9 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 {
 	pevent_register_event_handler(pevent, -1, "ftrace", "function",
 				      function_handler, NULL);
+
+	traceevent_plugin_add_options("ftrace", plugin_options);
+
 	return 0;
 }
 
@@ -157,6 +186,8 @@ void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
 		free(fstack[i].stack);
 	}
 
+	traceevent_plugin_remove_options(plugin_options);
+
 	free(fstack);
 	fstack = NULL;
 	cpus = -1;
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
index 0db714c721b..5c23d5bd27c 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -30,8 +30,7 @@
 #define MINOR(dev)	((unsigned int) ((dev) & MINORMASK))
 
 static unsigned long long
-process_jbd2_dev_to_name(struct trace_seq *s,
-			 unsigned long long *args)
+process_jbd2_dev_to_name(struct trace_seq *s, unsigned long long *args)
 {
 	unsigned int dev = args[0];
 
@@ -40,8 +39,7 @@ process_jbd2_dev_to_name(struct trace_seq *s,
 }
 
 static unsigned long long
-process_jiffies_to_msecs(struct trace_seq *s,
-			 unsigned long long *args)
+process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args)
 {
 	unsigned long long jiffies = args[0];
 
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 9e0e8c61b43..88fe83dff7c 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -240,25 +240,38 @@ static const char *find_exit_reason(unsigned isa, int val)
 	for (i = 0; strings[i].val >= 0; i++)
 		if (strings[i].val == val)
 			break;
-	if (strings[i].str)
-		return strings[i].str;
-	return "UNKNOWN";
+
+	return strings[i].str;
 }
 
-static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record,
-			    struct event_format *event, void *context)
+static int print_exit_reason(struct trace_seq *s, struct pevent_record *record,
+			     struct event_format *event, const char *field)
 {
 	unsigned long long isa;
 	unsigned long long val;
-	unsigned long long info1 = 0, info2 = 0;
+	const char *reason;
 
-	if (pevent_get_field_val(s, event, "exit_reason", record, &val, 1) < 0)
+	if (pevent_get_field_val(s, event, field, record, &val, 1) < 0)
 		return -1;
 
 	if (pevent_get_field_val(s, event, "isa", record, &isa, 0) < 0)
 		isa = 1;
 
-	trace_seq_printf(s, "reason %s", find_exit_reason(isa, val));
+	reason = find_exit_reason(isa, val);
+	if (reason)
+		trace_seq_printf(s, "reason %s", reason);
+	else
+		trace_seq_printf(s, "reason UNKNOWN (%llu)", val);
+	return 0;
+}
+
+static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record,
+			    struct event_format *event, void *context)
+{
+	unsigned long long info1 = 0, info2 = 0;
+
+	if (print_exit_reason(s, record, event, "exit_reason") < 0)
+		return -1;
 
 	pevent_print_num_field(s, " rip 0x%lx", event, "guest_rip", record, 1);
 
@@ -313,6 +326,29 @@ static int kvm_emulate_insn_handler(struct trace_seq *s,
 	return 0;
 }
 
+
+static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct pevent_record *record,
+					    struct event_format *event, void *context)
+{
+	if (print_exit_reason(s, record, event, "exit_code") < 0)
+		return -1;
+
+	pevent_print_num_field(s, " info1 %llx", event, "exit_info1", record, 1);
+	pevent_print_num_field(s, " info2 %llx", event, "exit_info2", record, 1);
+	pevent_print_num_field(s, " int_info %llx", event, "exit_int_info", record, 1);
+	pevent_print_num_field(s, " int_info_err %llx", event, "exit_int_info_err", record, 1);
+
+	return 0;
+}
+
+static int kvm_nested_vmexit_handler(struct trace_seq *s, struct pevent_record *record,
+				     struct event_format *event, void *context)
+{
+	pevent_print_num_field(s, "rip %llx ", event, "rip", record, 1);
+
+	return kvm_nested_vmexit_inject_handler(s, record, event, context);
+}
+
 union kvm_mmu_page_role {
 	unsigned word;
 	struct {
@@ -409,6 +445,12 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 	pevent_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
 				      kvm_emulate_insn_handler, NULL);
 
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+				      kvm_nested_vmexit_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+				      kvm_nested_vmexit_inject_handler, NULL);
+
 	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
 				      kvm_mmu_get_page_handler, NULL);
 
@@ -443,6 +485,12 @@ void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
 	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
 					kvm_emulate_insn_handler, NULL);
 
+	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+					kvm_nested_vmexit_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+					kvm_nested_vmexit_inject_handler, NULL);
+
 	pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
 					kvm_mmu_get_page_handler, NULL);
 
diff --git a/tools/net/bpf_exp.l b/tools/net/bpf_exp.l
index bf7be77ddd6..833a96611da 100644
--- a/tools/net/bpf_exp.l
+++ b/tools/net/bpf_exp.l
@@ -92,6 +92,7 @@ extern void yyerror(const char *str);
 "#"?("cpu")	{ return K_CPU; }
 "#"?("vlan_tci") { return K_VLANT; }
 "#"?("vlan_pr")	{ return K_VLANP; }
+"#"?("rand")	{ return K_RAND; }
 
 ":"		{ return ':'; }
 ","		{ return ','; }
diff --git a/tools/net/bpf_exp.y b/tools/net/bpf_exp.y
index d15efc989ef..e6306c51c26 100644
--- a/tools/net/bpf_exp.y
+++ b/tools/net/bpf_exp.y
@@ -56,7 +56,7 @@ static void bpf_set_jmp_label(char *label, enum jmp_type type);
 %token OP_LDXI
 
 %token K_PKT_LEN K_PROTO K_TYPE K_NLATTR K_NLATTR_NEST K_MARK K_QUEUE K_HATYPE
-%token K_RXHASH K_CPU K_IFIDX K_VLANT K_VLANP K_POFF
+%token K_RXHASH K_CPU K_IFIDX K_VLANT K_VLANP K_POFF K_RAND
 
 %token ':' ',' '[' ']' '(' ')' 'x' 'a' '+' 'M' '*' '&' '#' '%'
 
@@ -164,6 +164,9 @@ ldb
 	| OP_LDB K_POFF {
 		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
 				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
+	| OP_LDB K_RAND {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_RANDOM); }
 	;
 
 ldh
@@ -212,6 +215,9 @@ ldh
 	| OP_LDH K_POFF {
 		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
 				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
+	| OP_LDH K_RAND {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_RANDOM); }
 	;
 
 ldi
@@ -265,6 +271,9 @@ ld
 	| OP_LD K_POFF {
 		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
 				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
+	| OP_LD K_RAND {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_RANDOM); }
 	| OP_LD 'M' '[' number ']' {
 		bpf_set_curr_instr(BPF_LD | BPF_MEM, 0, 0, $4); }
 	| OP_LD '[' 'x' '+' number ']' {
diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c
index cfe0cdcda3d..c5baf9c591b 100644
--- a/tools/net/bpf_jit_disasm.c
+++ b/tools/net/bpf_jit_disasm.c
@@ -43,8 +43,7 @@ static void get_exec_path(char *tpath, size_t size)
 	free(path);
 }
 
-static void get_asm_insns(uint8_t *image, size_t len, unsigned long base,
-			  int opcodes)
+static void get_asm_insns(uint8_t *image, size_t len, int opcodes)
 {
 	int count, i, pc = 0;
 	char tpath[256];
@@ -107,13 +106,13 @@ static void put_klog_buff(char *buff)
 }
 
 static int get_last_jit_image(char *haystack, size_t hlen,
-			      uint8_t *image, size_t ilen,
-			      unsigned long *base)
+			      uint8_t *image, size_t ilen)
 {
 	char *ptr, *pptr, *tmp;
 	off_t off = 0;
 	int ret, flen, proglen, pass, ulen = 0;
 	regmatch_t pmatch[1];
+	unsigned long base;
 	regex_t regex;
 
 	if (hlen == 0)
@@ -136,7 +135,7 @@ static int get_last_jit_image(char *haystack, size_t hlen,
 
 	ptr = haystack + off - (pmatch[0].rm_eo - pmatch[0].rm_so);
 	ret = sscanf(ptr, "flen=%d proglen=%d pass=%d image=%lx",
-		     &flen, &proglen, &pass, base);
+		     &flen, &proglen, &pass, &base);
 	if (ret != 4)
 		return 0;
 
@@ -162,7 +161,7 @@ static int get_last_jit_image(char *haystack, size_t hlen,
 	assert(ulen == proglen);
 	printf("%d bytes emitted from JIT compiler (pass:%d, flen:%d)\n",
 	       proglen, pass, flen);
-	printf("%lx + <x>:\n", *base);
+	printf("%lx + <x>:\n", base);
 
 	regfree(&regex);
 	return ulen;
@@ -172,8 +171,7 @@ int main(int argc, char **argv)
 {
 	int len, klen, opcodes = 0;
 	char *kbuff;
-	unsigned long base;
-	uint8_t image[4096];
+	static uint8_t image[32768];
 
 	if (argc > 1) {
 		if (!strncmp("-o", argv[argc - 1], 2)) {
@@ -189,9 +187,9 @@ int main(int argc, char **argv)
 
 	kbuff = get_klog_buff(&klen);
 
-	len = get_last_jit_image(kbuff, klen, image, sizeof(image), &base);
-	if (len > 0 && base > 0)
-		get_asm_insns(image, len, base, opcodes);
+	len = get_last_jit_image(kbuff, klen, image, sizeof(image));
+	if (len > 0)
+		get_asm_insns(image, len, opcodes);
 
 	put_klog_buff(kbuff);
 
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index 4464ad770d5..f6480cbf309 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -16,6 +16,10 @@ This 'perf bench' command is a general framework for benchmark suites.
 
 COMMON OPTIONS
 --------------
+-r::
+--repeat=::
+Specify amount of times to repeat the run (default 10).
+
 -f::
 --format=::
 Specify format style.
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index a00a34276c5..dc7442cf3d7 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -41,6 +41,9 @@ OPTIONS
 	tasks slept. sched_switch contains a callchain where a task slept and
 	sched_stat contains a timeslice how long a task slept.
 
+--kallsyms=<file>::
+	kallsyms pathname
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 52276a6d2b7..6e689dc89a2 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -51,9 +51,9 @@ There are a couple of variants of perf kvm:
   'perf kvm stat <command>' to run a command and gather performance counter
   statistics.
   Especially, perf 'kvm stat record/report' generates a statistical analysis
-  of KVM events. Currently, vmexit, mmio and ioport events are supported.
-  'perf kvm stat record <command>' records kvm events and the events between
-  start and end <command>.
+  of KVM events. Currently, vmexit, mmio (x86 only) and ioport (x86 only)
+  events are supported. 'perf kvm stat record <command>' records kvm events
+  and the events between start and end <command>.
   And this command produces a file which contains tracing results of kvm
   events.
 
@@ -103,8 +103,8 @@ STAT REPORT OPTIONS
        analyze events which occures on this vcpu. (default: all vcpus)
 
 --event=<value>::
-       event to be analyzed. Possible values: vmexit, mmio, ioport.
-       (default: vmexit)
+       event to be analyzed. Possible values: vmexit, mmio (x86 only),
+       ioport (x86 only). (default: vmexit)
 -k::
 --key=<value>::
        Sorting key. Possible values: sample (default, sort by samples
@@ -138,7 +138,8 @@ STAT LIVE OPTIONS
 
 
 --event=<value>::
-       event to be analyzed. Possible values: vmexit, mmio, ioport.
+       event to be analyzed. Possible values: vmexit,
+       mmio (x86 only), ioport (x86 only).
        (default: vmexit)
 
 -k::
@@ -147,7 +148,8 @@ STAT LIVE OPTIONS
        number), time (sort by average time).
 
 --duration=<value>::
-       Show events other than HLT that take longer than duration usecs.
+       Show events other than HLT (x86 only) or Wait state (s390 only)
+       that take longer than duration usecs.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index c71b0f36d9e..d460049cae8 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -184,9 +184,10 @@ following filters are defined:
 	- in_tx: only when the target is in a hardware transaction
 	- no_tx: only when the target is not in a hardware transaction
 	- abort_tx: only when the target is a hardware transaction abort
+	- cond: conditional branches
 
 +
-The option requires at least one branch type among any, any_call, any_ret, ind_call.
+The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
 The privilege levels may be omitted, in which case, the privilege levels of the associated
 event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
 levels are subject to permissions.  When sampling on multiple events, branch stack sampling
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index a1b5185402d..d2b59af62bc 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -111,12 +111,28 @@ OPTIONS
 --fields=::
 	Specify output field - multiple keys can be specified in CSV format.
 	Following fields are available:
-	overhead, overhead_sys, overhead_us, sample and period.
+	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
 	Also it can contain any sort key(s).
 
 	By default, every sort keys not specified in -F will be appended
 	automatically.
 
+	If --mem-mode option is used, following sort keys are also available
+	(incompatible with --branch-stack):
+	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
+
+	- symbol_daddr: name of data symbol being executed on at the time of sample
+	- dso_daddr: name of library or module containing the data being executed
+	on at the time of sample
+	- locked: whether the bus was locked at the time of sample
+	- tlb: type of tlb access for the data at the time of sample
+	- mem: type of memory access for the data at the time of sample
+	- snoop: type of snoop (if any) for the data at the time of sample
+	- dcacheline: the cacheline the data address is on at the time of sample
+
+	And default sort keys are changed to local_weight, mem, sym, dso,
+	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
+
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this
@@ -163,6 +179,11 @@ OPTIONS
 
 	Default: fractal,0.5,callee,function.
 
+--children::
+	Accumulate callchain of children to parent entry so that then can
+	show up in the output.  The output will have a new "Children" column
+	and will be sorted on the data.  It requires callchains are recorded.
+
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
 	beyond the specified depth will be ignored. This is a trade-off
@@ -255,6 +276,13 @@ OPTIONS
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
 
+--mem-mode::
+	Use the data addresses of samples in addition to instruction addresses
+	to build the histograms.  To generate meaningful output, the perf.data
+	file must have been obtained using perf record -d -W and using a
+	special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
+	'perf mem' for simpler access.
+
 --percent-limit::
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index bc5990c33dc..df98d1c8268 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -15,10 +15,20 @@ DESCRIPTION
 There are two variants of perf timechart:
 
   'perf timechart record <command>' to record the system level events
-  of an arbitrary workload.
+  of an arbitrary workload. By default timechart records only scheduler
+  and CPU events (task switches, running times, CPU power states, etc),
+  but it's possible to record IO (disk, network) activity using -I argument.
 
   'perf timechart' to turn a trace into a Scalable Vector Graphics file,
-  that can be viewed with popular SVG viewers such as 'Inkscape'.
+  that can be viewed with popular SVG viewers such as 'Inkscape'. Depending
+  on the events in the perf.data file, timechart will contain scheduler/cpu
+  events or IO events.
+
+  In IO mode, every bar has two charts: upper and lower.
+  Upper bar shows incoming events (disk reads, ingress network packets).
+  Lower bar shows outgoing events (disk writes, egress network packets).
+  There are also poll bars which show how much time application spent
+  in poll/epoll/select syscalls.
 
 TIMECHART OPTIONS
 -----------------
@@ -43,27 +53,6 @@ TIMECHART OPTIONS
 
 --symfs=<directory>::
         Look for files with symbols relative to this directory.
-
-EXAMPLES
---------
-
-$ perf timechart record git pull
-
-  [ perf record: Woken up 13 times to write data ]
-  [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ]
-
-$ perf timechart
-
-  Written 10.2 seconds of trace to output.svg.
-
-Record system-wide timechart:
-
-  $ perf timechart record
-
-  then generate timechart and highlight 'gcc' tasks:
-
-  $ perf timechart --highlight gcc
-
 -n::
 --proc-num::
         Print task info for at least given number of tasks.
@@ -75,6 +64,19 @@ Record system-wide timechart:
 	duration or tasks with given name. If number is given it's interpreted
 	as number of nanoseconds. If non-numeric string is given it's
 	interpreted as task name.
+--io-skip-eagain::
+	Don't draw EAGAIN IO events.
+--io-min-time=<nsecs>::
+	Draw small events as if they lasted min-time. Useful when you need
+	to see very small and fast IO. It's possible to specify ms or us
+	suffix to specify time in milliseconds or microseconds.
+	Default value is 1ms.
+--io-merge-dist=<nsecs>::
+	Merge events that are merge-dist nanoseconds apart.
+	Reduces number of figures on the SVG and makes it more render-friendly.
+	It's possible to specify ms or us suffix to specify time in
+	milliseconds or microseconds.
+	Default value is 1us.
 
 RECORD OPTIONS
 --------------
@@ -84,10 +86,41 @@ RECORD OPTIONS
 -T::
 --tasks-only::
         Record only tasks-related events
+-I::
+--io-only::
+        Record only io-related events
 -g::
 --callchain::
         Do call-graph (stack chain/backtrace) recording
 
+EXAMPLES
+--------
+
+$ perf timechart record git pull
+
+  [ perf record: Woken up 13 times to write data ]
+  [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ]
+
+$ perf timechart
+
+  Written 10.2 seconds of trace to output.svg.
+
+Record system-wide timechart:
+
+  $ perf timechart record
+
+  then generate timechart and highlight 'gcc' tasks:
+
+  $ perf timechart --highlight gcc
+
+Record system-wide IO events:
+
+  $ perf timechart record -I
+
+  then generate timechart:
+
+  $ perf timechart
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index dcfa54c851e..180ae02137a 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -119,7 +119,7 @@ Default is to monitor all CPUS.
 --fields=::
 	Specify output field - multiple keys can be specified in CSV format.
 	Following fields are available:
-	overhead, overhead_sys, overhead_us, sample and period.
+	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
 	Also it can contain any sort key(s).
 
 	By default, every sort keys not specified in --field will be appended
@@ -161,6 +161,12 @@ Default is to monitor all CPUS.
 	Setup and enable call-graph (stack chain/backtrace) recording,
 	implies -g.
 
+--children::
+	Accumulate callchain of children to parent entry so that then can
+	show up in the output.  The output will have a new "Children" column
+	and will be sorted on the data.  It requires -g/--call-graph option
+	enabled.
+
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
 	beyond the specified depth will be ignored. This is a trade-off
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index fae38d9a44a..02aac831bdd 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -107,6 +107,52 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	Show tool stats such as number of times fd->pathname was discovered thru
 	hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
 
+-F=[all|min|maj]::
+--pf=[all|min|maj]::
+	Trace pagefaults. Optionally, you can specify whether you want minor,
+	major or all pagefaults. Default value is maj.
+
+--syscalls::
+	Trace system calls. This options is enabled by default.
+
+PAGEFAULTS
+----------
+
+When tracing pagefaults, the format of the trace is as follows:
+
+<min|maj>fault [<ip.symbol>+<ip.offset>] => <addr.dso@addr.offset> (<map type><addr level>).
+
+- min/maj indicates whether fault event is minor or major;
+- ip.symbol shows symbol for instruction pointer (the code that generated the
+  fault); if no debug symbols available, perf trace will print raw IP;
+- addr.dso shows DSO for the faulted address;
+- map type is either 'd' for non-executable maps or 'x' for executable maps;
+- addr level is either 'k' for kernel dso or '.' for user dso.
+
+For symbols resolution you may need to install debugging symbols.
+
+Please be aware that duration is currently always 0 and doesn't reflect actual
+time it took for fault to be handled!
+
+When --verbose specified, perf trace tries to print all available information
+for both IP and fault address in the form of dso@symbol+offset.
+
+EXAMPLES
+--------
+
+Trace only major pagefaults:
+
+ $ perf trace --no-syscalls -F
+
+Trace syscalls, major and minor pagefaults:
+
+ $ perf trace -F all
+
+  1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64-linux-gnu/libcrypto.so.1.0.0@0x61be0 (x.)
+
+  As you can see, there was major pagefault in python process, from
+  CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index 0eeb247dc7d..d240bb2e5b2 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -8,7 +8,15 @@ perf - Performance analysis tools for Linux
 SYNOPSIS
 --------
 [verse]
-'perf' [--version] [--help] COMMAND [ARGS]
+'perf' [--version] [--help] [OPTIONS] COMMAND [ARGS]
+
+OPTIONS
+-------
+--debug::
+	Setup debug variable (just verbose for now) in value
+	range (0, 10). Use like:
+	  --debug verbose   # sets verbose = 1
+	  --debug verbose=2 # sets verbose = 2
 
 DESCRIPTION
 -----------
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 45da209b6ed..344c4d3d0a4 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -37,3 +37,6 @@ arch/x86/include/asm/kvm_host.h
 arch/x86/include/uapi/asm/svm.h
 arch/x86/include/uapi/asm/vmx.h
 arch/x86/include/uapi/asm/kvm.h
+arch/x86/include/uapi/asm/kvm_perf.h
+arch/s390/include/uapi/asm/sie.h
+arch/s390/include/uapi/asm/kvm_perf.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 02f0a4dd1a8..2240974b774 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -295,11 +295,13 @@ LIB_H += util/intlist.h
 LIB_H += util/perf_regs.h
 LIB_H += util/unwind.h
 LIB_H += util/vdso.h
+LIB_H += util/tsc.h
 LIB_H += ui/helpline.h
 LIB_H += ui/progress.h
 LIB_H += ui/util.h
 LIB_H += ui/ui.h
 LIB_H += util/data.h
+LIB_H += util/kvm-stat.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -373,6 +375,8 @@ LIB_OBJS += $(OUTPUT)util/stat.o
 LIB_OBJS += $(OUTPUT)util/record.o
 LIB_OBJS += $(OUTPUT)util/srcline.o
 LIB_OBJS += $(OUTPUT)util/data.o
+LIB_OBJS += $(OUTPUT)util/tsc.o
+LIB_OBJS += $(OUTPUT)util/cloexec.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
@@ -400,6 +404,7 @@ LIB_OBJS += $(OUTPUT)tests/hists_common.o
 LIB_OBJS += $(OUTPUT)tests/hists_link.o
 LIB_OBJS += $(OUTPUT)tests/hists_filter.o
 LIB_OBJS += $(OUTPUT)tests/hists_output.o
+LIB_OBJS += $(OUTPUT)tests/hists_cumulate.o
 LIB_OBJS += $(OUTPUT)tests/python-use.o
 LIB_OBJS += $(OUTPUT)tests/bp_signal.o
 LIB_OBJS += $(OUTPUT)tests/bp_signal_overflow.o
@@ -788,8 +793,8 @@ help:
 	@echo ''
 	@echo 'Perf install targets:'
 	@echo '  NOTE: documentation build requires asciidoc, xmlto packages to be installed'
-	@echo '  HINT: use "make prefix=<path> <install target>" to install to a particular'
-	@echo '        path like make prefix=/usr/local install install-doc'
+	@echo '  HINT: use "prefix" or "DESTDIR" to install to a particular'
+	@echo '        path like "make prefix=/usr/local install install-doc"'
 	@echo '  install	- install compiled binaries'
 	@echo '  install-doc	- install *all* documentation'
 	@echo '  install-man	- install manpage documentation'
@@ -814,17 +819,20 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html
 $(DOC_TARGETS):
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all)
 
+TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol
+TAG_FILES= ../../include/uapi/linux/perf_event.h
+
 TAGS:
-	$(RM) TAGS
-	$(FIND) . -name '*.[hcS]' -print | xargs etags -a
+	$(QUIET_GEN)$(RM) TAGS; \
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES)
 
 tags:
-	$(RM) tags
-	$(FIND) . -name '*.[hcS]' -print | xargs ctags -a
+	$(QUIET_GEN)$(RM) tags; \
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES)
 
 cscope:
-	$(RM) cscope*
-	$(FIND) . -name '*.[hcS]' -print | xargs cscope -b
+	$(QUIET_GEN)$(RM) cscope*; \
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES)
 
 ### Detect prefix changes
 TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 744e629797b..b92219b1900 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -3,3 +3,4 @@ PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 2f7073d107f..6c1b8a75db0 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -5,9 +5,7 @@
 #include <string.h>
 
 #include "../../util/header.h"
-
-#define __stringify_1(x)        #x
-#define __stringify(x)          __stringify_1(x)
+#include "../../util/util.h"
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
new file mode 100644
index 00000000000..a7c23a4b377
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -0,0 +1,266 @@
+/*
+ * Use DWARF Debug information to skip unnecessary callchain entries.
+ *
+ * Copyright (C) 2014 Sukadev Bhattiprolu, IBM Corporation.
+ * Copyright (C) 2014 Ulrich Weigand, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <inttypes.h>
+#include <dwarf.h>
+#include <elfutils/libdwfl.h>
+
+#include "util/thread.h"
+#include "util/callchain.h"
+
+/*
+ * When saving the callchain on Power, the kernel conservatively saves
+ * excess entries in the callchain. A few of these entries are needed
+ * in some cases but not others. If the unnecessary entries are not
+ * ignored, we end up with duplicate arcs in the call-graphs. Use
+ * DWARF debug information to skip over any unnecessary callchain
+ * entries.
+ *
+ * See function header for arch_adjust_callchain() below for more details.
+ *
+ * The libdwfl code in this file is based on code from elfutils
+ * (libdwfl/argp-std.c, libdwfl/tests/addrcfi.c, etc).
+ */
+static char *debuginfo_path;
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.debuginfo_path = &debuginfo_path,
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+	.section_address = dwfl_offline_section_address,
+};
+
+
+/*
+ * Use the DWARF expression for the Call-frame-address and determine
+ * if return address is in LR and if a new frame was allocated.
+ */
+static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
+{
+	Dwarf_Op ops_mem[2];
+	Dwarf_Op dummy;
+	Dwarf_Op *ops = &dummy;
+	size_t nops;
+	int result;
+
+	result = dwarf_frame_register(frame, ra_regno, ops_mem, &ops, &nops);
+	if (result < 0) {
+		pr_debug("dwarf_frame_register() %s\n", dwarf_errmsg(-1));
+		return -1;
+	}
+
+	/*
+	 * Check if return address is on the stack.
+	 */
+	if (nops != 0 || ops != NULL)
+		return 0;
+
+	/*
+	 * Return address is in LR. Check if a frame was allocated
+	 * but not-yet used.
+	 */
+	result = dwarf_frame_cfa(frame, &ops, &nops);
+	if (result < 0) {
+		pr_debug("dwarf_frame_cfa() returns %d, %s\n", result,
+					dwarf_errmsg(-1));
+		return -1;
+	}
+
+	/*
+	 * If call frame address is in r1, no new frame was allocated.
+	 */
+	if (nops == 1 && ops[0].atom == DW_OP_bregx && ops[0].number == 1 &&
+				ops[0].number2 == 0)
+		return 1;
+
+	/*
+	 * A new frame was allocated but has not yet been used.
+	 */
+	return 2;
+}
+
+/*
+ * Get the DWARF frame from the .eh_frame section.
+ */
+static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc)
+{
+	int		result;
+	Dwarf_Addr	bias;
+	Dwarf_CFI	*cfi;
+	Dwarf_Frame	*frame;
+
+	cfi = dwfl_module_eh_cfi(mod, &bias);
+	if (!cfi) {
+		pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	result = dwarf_cfi_addrframe(cfi, pc, &frame);
+	if (result) {
+		pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	return frame;
+}
+
+/*
+ * Get the DWARF frame from the .debug_frame section.
+ */
+static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
+{
+	Dwarf_CFI       *cfi;
+	Dwarf_Addr      bias;
+	Dwarf_Frame     *frame;
+	int             result;
+
+	cfi = dwfl_module_dwarf_cfi(mod, &bias);
+	if (!cfi) {
+		pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	result = dwarf_cfi_addrframe(cfi, pc, &frame);
+	if (result) {
+		pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	return frame;
+}
+
+/*
+ * Return:
+ *	0 if return address for the program counter @pc is on stack
+ *	1 if return address is in LR and no new stack frame was allocated
+ *	2 if return address is in LR and a new frame was allocated (but not
+ *		yet used)
+ *	-1 in case of errors
+ */
+static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
+{
+	int		rc = -1;
+	Dwfl		*dwfl;
+	Dwfl_Module	*mod;
+	Dwarf_Frame	*frame;
+	int		ra_regno;
+	Dwarf_Addr	start = pc;
+	Dwarf_Addr	end = pc;
+	bool		signalp;
+
+	dwfl = dwfl_begin(&offline_callbacks);
+	if (!dwfl) {
+		pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
+		return -1;
+	}
+
+	if (dwfl_report_offline(dwfl, "",  exec_file, -1) == NULL) {
+		pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1));
+		goto out;
+	}
+
+	mod = dwfl_addrmodule(dwfl, pc);
+	if (!mod) {
+		pr_debug("dwfl_addrmodule() failed, %s\n", dwarf_errmsg(-1));
+		goto out;
+	}
+
+	/*
+	 * To work with split debug info files (eg: glibc), check both
+	 * .eh_frame and .debug_frame sections of the ELF header.
+	 */
+	frame = get_eh_frame(mod, pc);
+	if (!frame) {
+		frame = get_dwarf_frame(mod, pc);
+		if (!frame)
+			goto out;
+	}
+
+	ra_regno = dwarf_frame_info(frame, &start, &end, &signalp);
+	if (ra_regno < 0) {
+		pr_debug("Return address register unavailable: %s\n",
+				dwarf_errmsg(-1));
+		goto out;
+	}
+
+	rc = check_return_reg(ra_regno, frame);
+
+out:
+	dwfl_end(dwfl);
+	return rc;
+}
+
+/*
+ * The callchain saved by the kernel always includes the link register (LR).
+ *
+ *	0:	PERF_CONTEXT_USER
+ *	1:	Program counter (Next instruction pointer)
+ *	2:	LR value
+ *	3:	Caller's caller
+ *	4:	...
+ *
+ * The value in LR is only needed when it holds a return address. If the
+ * return address is on the stack, we should ignore the LR value.
+ *
+ * Further, when the return address is in the LR, if a new frame was just
+ * allocated but the LR was not saved into it, then the LR contains the
+ * caller, slot 4: contains the caller's caller and the contents of slot 3:
+ * (chain->ips[3]) is undefined and must be ignored.
+ *
+ * Use DWARF debug information to determine if any entries need to be skipped.
+ *
+ * Return:
+ *	index:	of callchain entry that needs to be ignored (if any)
+ *	-1	if no entry needs to be ignored or in case of errors
+ */
+int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
+				struct ip_callchain *chain)
+{
+	struct addr_location al;
+	struct dso *dso = NULL;
+	int rc;
+	u64 ip;
+	u64 skip_slot = -1;
+
+	if (chain->nr < 3)
+		return skip_slot;
+
+	ip = chain->ips[2];
+
+	thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER,
+			MAP__FUNCTION, ip, &al);
+
+	if (al.map)
+		dso = al.map->dso;
+
+	if (!dso) {
+		pr_debug("%" PRIx64 " dso is NULL\n", ip);
+		return skip_slot;
+	}
+
+	rc = check_return_addr(dso->long_name, ip);
+
+	pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
+				dso->long_name, chain->nr, ip, rc);
+
+	if (rc == 0) {
+		/*
+		 * Return address on stack. Ignore LR value in callchain
+		 */
+		skip_slot = 2;
+	} else if (rc == 2) {
+		/*
+		 * New frame allocated but return address still in LR.
+		 * Ignore the caller's caller entry in callchain.
+		 */
+		skip_slot = 3;
+	}
+	return skip_slot;
+}
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 15130b50dfe..798ac7379c5 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -2,3 +2,6 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
+HAVE_KVM_STAT_SUPPORT := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
new file mode 100644
index 00000000000..9fa6c3e5782
--- /dev/null
+++ b/tools/perf/arch/s390/util/header.c
@@ -0,0 +1,28 @@
+/*
+ * Implementation of get_cpuid().
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "../../util/header.h"
+
+int get_cpuid(char *buffer, size_t sz)
+{
+	const char *cpuid = "IBM/S390";
+
+	if (strlen(cpuid) + 1 > sz)
+		return -1;
+
+	strcpy(buffer, cpuid);
+	return 0;
+}
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
new file mode 100644
index 00000000000..a5dbc07ec9d
--- /dev/null
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -0,0 +1,105 @@
+/*
+ * Arch specific functions for perf kvm stat.
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#include "../../util/kvm-stat.h"
+#include <asm/kvm_perf.h>
+
+define_exit_reasons_table(sie_exit_reasons, sie_intercept_code);
+define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes);
+define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes);
+define_exit_reasons_table(sie_diagnose_codes, diagnose_codes);
+define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes);
+
+static void event_icpt_insn_get_key(struct perf_evsel *evsel,
+				    struct perf_sample *sample,
+				    struct event_key *key)
+{
+	unsigned long insn;
+
+	insn = perf_evsel__intval(evsel, sample, "instruction");
+	key->key = icpt_insn_decoder(insn);
+	key->exit_reasons = sie_icpt_insn_codes;
+}
+
+static void event_sigp_get_key(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->key = perf_evsel__intval(evsel, sample, "order_code");
+	key->exit_reasons = sie_sigp_order_codes;
+}
+
+static void event_diag_get_key(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->key = perf_evsel__intval(evsel, sample, "code");
+	key->exit_reasons = sie_diagnose_codes;
+}
+
+static void event_icpt_prog_get_key(struct perf_evsel *evsel,
+				    struct perf_sample *sample,
+				    struct event_key *key)
+{
+	key->key = perf_evsel__intval(evsel, sample, "code");
+	key->exit_reasons = sie_icpt_prog_codes;
+}
+
+static struct child_event_ops child_events[] = {
+	{ .name = "kvm:kvm_s390_intercept_instruction",
+	  .get_key = event_icpt_insn_get_key },
+	{ .name = "kvm:kvm_s390_handle_sigp",
+	  .get_key = event_sigp_get_key },
+	{ .name = "kvm:kvm_s390_handle_diag",
+	  .get_key = event_diag_get_key },
+	{ .name = "kvm:kvm_s390_intercept_prog",
+	  .get_key = event_icpt_prog_get_key },
+	{ NULL, NULL },
+};
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = exit_event_begin,
+	.is_end_event = exit_event_end,
+	.child_ops = child_events,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+const char * const kvm_events_tp[] = {
+	"kvm:kvm_s390_sie_enter",
+	"kvm:kvm_s390_sie_exit",
+	"kvm:kvm_s390_intercept_instruction",
+	"kvm:kvm_s390_handle_sigp",
+	"kvm:kvm_s390_handle_diag",
+	"kvm:kvm_s390_intercept_prog",
+	NULL,
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+	{ .name = "vmexit", .ops = &exit_events },
+	{ NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+	"Wait state",
+	NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
+{
+	if (strstr(cpuid, "IBM/S390")) {
+		kvm->exit_reasons = sie_exit_reasons;
+		kvm->exit_reasons_isa = "SIE";
+	} else
+		return -ENOTSUP;
+
+	return 0;
+}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 1641542e363..9b21881db52 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -15,3 +15,5 @@ endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
 LIB_H += arch/$(ARCH)/util/tsc.h
+HAVE_KVM_STAT_SUPPORT := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/kvm-stat.o
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 9f89f899ccc..d8bbf7ad168 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -3,6 +3,7 @@
 #include "thread.h"
 #include "map.h"
 #include "event.h"
+#include "debug.h"
 #include "tests/tests.h"
 
 #define STACK_SIZE 8192
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
new file mode 100644
index 00000000000..14e4e668fad
--- /dev/null
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -0,0 +1,156 @@
+#include "../../util/kvm-stat.h"
+#include <asm/kvm_perf.h>
+
+define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
+define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = exit_event_begin,
+	.is_end_event = exit_event_end,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+/*
+ * For the mmio events, we treat:
+ * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
+ * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
+ */
+static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
+			       struct event_key *key)
+{
+	key->key  = perf_evsel__intval(evsel, sample, "gpa");
+	key->info = perf_evsel__intval(evsel, sample, "type");
+}
+
+#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
+#define KVM_TRACE_MMIO_READ 1
+#define KVM_TRACE_MMIO_WRITE 2
+
+static bool mmio_event_begin(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key)
+{
+	/* MMIO read begin event in kernel. */
+	if (kvm_exit_event(evsel))
+		return true;
+
+	/* MMIO write begin event in kernel. */
+	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
+		mmio_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
+			   struct event_key *key)
+{
+	/* MMIO write end event in kernel. */
+	if (kvm_entry_event(evsel))
+		return true;
+
+	/* MMIO read end event in kernel.*/
+	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
+	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
+		mmio_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				  struct event_key *key,
+				  char *decode)
+{
+	scnprintf(decode, DECODE_STR_LEN, "%#lx:%s",
+		  (unsigned long)key->key,
+		  key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
+}
+
+static struct kvm_events_ops mmio_events = {
+	.is_begin_event = mmio_event_begin,
+	.is_end_event = mmio_event_end,
+	.decode_key = mmio_event_decode_key,
+	.name = "MMIO Access"
+};
+
+ /* The time of emulation pio access is from kvm_pio to kvm_entry. */
+static void ioport_event_get_key(struct perf_evsel *evsel,
+				 struct perf_sample *sample,
+				 struct event_key *key)
+{
+	key->key  = perf_evsel__intval(evsel, sample, "port");
+	key->info = perf_evsel__intval(evsel, sample, "rw");
+}
+
+static bool ioport_event_begin(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	if (!strcmp(evsel->name, "kvm:kvm_pio")) {
+		ioport_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool ioport_event_end(struct perf_evsel *evsel,
+			     struct perf_sample *sample __maybe_unused,
+			     struct event_key *key __maybe_unused)
+{
+	return kvm_entry_event(evsel);
+}
+
+static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				    struct event_key *key,
+				    char *decode)
+{
+	scnprintf(decode, DECODE_STR_LEN, "%#llx:%s",
+		  (unsigned long long)key->key,
+		  key->info ? "POUT" : "PIN");
+}
+
+static struct kvm_events_ops ioport_events = {
+	.is_begin_event = ioport_event_begin,
+	.is_end_event = ioport_event_end,
+	.decode_key = ioport_event_decode_key,
+	.name = "IO Port Access"
+};
+
+const char * const kvm_events_tp[] = {
+	"kvm:kvm_entry",
+	"kvm:kvm_exit",
+	"kvm:kvm_mmio",
+	"kvm:kvm_pio",
+	NULL,
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+	{ .name = "vmexit", .ops = &exit_events },
+	{ .name = "mmio", .ops = &mmio_events },
+	{ .name = "ioport", .ops = &ioport_events },
+	{ NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+	"HLT",
+	NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
+{
+	if (strstr(cpuid, "Intel")) {
+		kvm->exit_reasons = vmx_exit_reasons;
+		kvm->exit_reasons_isa = "VMX";
+	} else if (strstr(cpuid, "AMD")) {
+		kvm->exit_reasons = svm_exit_reasons;
+		kvm->exit_reasons_isa = "SVM";
+	} else
+		return -ENOTSUP;
+
+	return 0;
+}
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 40021fa3129..fd2868490d0 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -6,29 +6,9 @@
 #include "../../perf.h"
 #include <linux/types.h>
 #include "../../util/debug.h"
+#include "../../util/tsc.h"
 #include "tsc.h"
 
-u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
-{
-	u64 t, quot, rem;
-
-	t = ns - tc->time_zero;
-	quot = t / tc->time_mult;
-	rem  = t % tc->time_mult;
-	return (quot << tc->time_shift) +
-	       (rem << tc->time_shift) / tc->time_mult;
-}
-
-u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
-{
-	u64 quot, rem;
-
-	quot = cyc >> tc->time_shift;
-	rem  = cyc & ((1 << tc->time_shift) - 1);
-	return tc->time_zero + quot * tc->time_mult +
-	       ((rem * tc->time_mult) >> tc->time_shift);
-}
-
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 			     struct perf_tsc_conversion *tc)
 {
@@ -57,3 +37,12 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 
 	return 0;
 }
+
+u64 rdtsc(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h
index 2affe0366b5..2edc4d31065 100644
--- a/tools/perf/arch/x86/util/tsc.h
+++ b/tools/perf/arch/x86/util/tsc.h
@@ -14,7 +14,4 @@ struct perf_event_mmap_page;
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 			     struct perf_tsc_conversion *tc);
 
-u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
-u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
-
 #endif /* TOOLS_PERF_ARCH_X86_UTIL_TSC_H__ */
diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 3261f68c6a7..db25e93d989 100644
--- a/tools/perf/arch/x86/util/unwind-libunwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -3,6 +3,7 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
+#include "../../util/debug.h"
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT
 int libunwind__arch_reg_id(int regnum)
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index eba46709b27..3c4dd44d45c 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -43,5 +43,6 @@ extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
 #define BENCH_FORMAT_UNKNOWN		-1
 
 extern int bench_format;
+extern unsigned int bench_repeat;
 
 #endif
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index a16255876f1..732403bfd31 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -29,13 +29,6 @@ static u_int32_t futex1 = 0, futex2 = 0;
  */
 static unsigned int nrequeue = 1;
 
-/*
- * There can be significant variance from run to run,
- * the more repeats, the more exact the overall avg and
- * the better idea of the futex latency.
- */
-static unsigned int repeat = 10;
-
 static pthread_t *worker;
 static bool done = 0, silent = 0;
 static pthread_mutex_t thread_lock;
@@ -46,7 +39,6 @@ static unsigned int ncpus, threads_starting, nthreads = 0;
 static const struct option options[] = {
 	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
-	OPT_UINTEGER('r', "repeat",   &repeat,   "Specify amount of times to repeat the run"),
 	OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
 	OPT_END()
 };
@@ -146,7 +138,7 @@ int bench_futex_requeue(int argc, const char **argv,
 	pthread_cond_init(&thread_parent, NULL);
 	pthread_cond_init(&thread_worker, NULL);
 
-	for (j = 0; j < repeat && !done; j++) {
+	for (j = 0; j < bench_repeat && !done; j++) {
 		unsigned int nrequeued = 0;
 		struct timeval start, end, runtime;
 
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index d096169b161..50022cbce87 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -30,15 +30,8 @@ static u_int32_t futex1 = 0;
  */
 static unsigned int nwakes = 1;
 
-/*
- * There can be significant variance from run to run,
- * the more repeats, the more exact the overall avg and
- * the better idea of the futex latency.
- */
-static unsigned int repeat = 10;
-
 pthread_t *worker;
-static bool done = 0, silent = 0;
+static bool done = false, silent = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
@@ -47,7 +40,6 @@ static unsigned int ncpus, threads_starting, nthreads = 0;
 static const struct option options[] = {
 	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('w', "nwakes",  &nwakes,   "Specify amount of threads to wake at once"),
-	OPT_UINTEGER('r', "repeat",  &repeat,   "Specify amount of times to repeat the run"),
 	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
 	OPT_END()
 };
@@ -149,7 +141,7 @@ int bench_futex_wake(int argc, const char **argv,
 	pthread_cond_init(&thread_parent, NULL);
 	pthread_cond_init(&thread_worker, NULL);
 
-	for (j = 0; j < repeat && !done; j++) {
+	for (j = 0; j < bench_repeat && !done; j++) {
 		unsigned int nwoken = 0;
 		struct timeval start, end, runtime;
 
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 5ce71d3b72c..2465141b554 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -10,6 +10,7 @@
 #include "../util/util.h"
 #include "../util/parse-options.h"
 #include "../util/header.h"
+#include "../util/cloexec.h"
 #include "bench.h"
 #include "mem-memcpy-arch.h"
 
@@ -83,7 +84,8 @@ static struct perf_event_attr cycle_attr = {
 
 static void init_cycle(void)
 {
-	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
+	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1,
+				       perf_event_open_cloexec_flag());
 
 	if (cycle_fd < 0 && errno == ENOSYS)
 		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
@@ -189,6 +191,11 @@ int bench_mem_memcpy(int argc, const char **argv,
 	argc = parse_options(argc, argv, options,
 			     bench_mem_memcpy_usage, 0);
 
+	if (no_prefault && only_prefault) {
+		fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
+		return 1;
+	}
+
 	if (use_cycle)
 		init_cycle();
 
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index 9af79d2b18e..75fc3e65fb2 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -10,6 +10,7 @@
 #include "../util/util.h"
 #include "../util/parse-options.h"
 #include "../util/header.h"
+#include "../util/cloexec.h"
 #include "bench.h"
 #include "mem-memset-arch.h"
 
@@ -83,7 +84,8 @@ static struct perf_event_attr cycle_attr = {
 
 static void init_cycle(void)
 {
-	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
+	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1,
+				       perf_event_open_cloexec_flag());
 
 	if (cycle_fd < 0 && errno == ENOSYS)
 		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
@@ -181,6 +183,11 @@ int bench_mem_memset(int argc, const char **argv,
 	argc = parse_options(argc, argv, options,
 			     bench_mem_memset_usage, 0);
 
+	if (no_prefault && only_prefault) {
+		fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
+		return 1;
+	}
+
 	if (use_cycle)
 		init_cycle();
 
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index cc1190a0849..52a56599a54 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -28,6 +28,7 @@
 #include <sys/time.h>
 #include <sys/poll.h>
 #include <limits.h>
+#include <err.h>
 
 #define DATASIZE 100
 
@@ -50,12 +51,6 @@ struct receiver_context {
 	int wakefd;
 };
 
-static void barf(const char *msg)
-{
-	fprintf(stderr, "%s (error: %s)\n", msg, strerror(errno));
-	exit(1);
-}
-
 static void fdpair(int fds[2])
 {
 	if (use_pipes) {
@@ -66,7 +61,7 @@ static void fdpair(int fds[2])
 			return;
 	}
 
-	barf(use_pipes ? "pipe()" : "socketpair()");
+	err(EXIT_FAILURE, use_pipes ? "pipe()" : "socketpair()");
 }
 
 /* Block until we're ready to go */
@@ -77,11 +72,11 @@ static void ready(int ready_out, int wakefd)
 
 	/* Tell them we're ready. */
 	if (write(ready_out, &dummy, 1) != 1)
-		barf("CLIENT: ready write");
+		err(EXIT_FAILURE, "CLIENT: ready write");
 
 	/* Wait for "GO" signal */
 	if (poll(&pollfd, 1, -1) != 1)
-		barf("poll");
+		err(EXIT_FAILURE, "poll");
 }
 
 /* Sender sprays loops messages down each file descriptor */
@@ -101,7 +96,7 @@ again:
 			ret = write(ctx->out_fds[j], data + done,
 				    sizeof(data)-done);
 			if (ret < 0)
-				barf("SENDER: write");
+				err(EXIT_FAILURE, "SENDER: write");
 			done += ret;
 			if (done < DATASIZE)
 				goto again;
@@ -131,7 +126,7 @@ static void *receiver(struct receiver_context* ctx)
 again:
 		ret = read(ctx->in_fds[0], data + done, DATASIZE - done);
 		if (ret < 0)
-			barf("SERVER: read");
+			err(EXIT_FAILURE, "SERVER: read");
 		done += ret;
 		if (done < DATASIZE)
 			goto again;
@@ -144,14 +139,14 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *))
 {
 	pthread_attr_t attr;
 	pthread_t childid;
-	int err;
+	int ret;
 
 	if (!thread_mode) {
 		/* process mode */
 		/* Fork the receiver. */
 		switch (fork()) {
 		case -1:
-			barf("fork()");
+			err(EXIT_FAILURE, "fork()");
 			break;
 		case 0:
 			(*func) (ctx);
@@ -165,19 +160,17 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *))
 	}
 
 	if (pthread_attr_init(&attr) != 0)
-		barf("pthread_attr_init:");
+		err(EXIT_FAILURE, "pthread_attr_init:");
 
 #ifndef __ia64__
 	if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0)
-		barf("pthread_attr_setstacksize");
+		err(EXIT_FAILURE, "pthread_attr_setstacksize");
 #endif
 
-	err = pthread_create(&childid, &attr, func, ctx);
-	if (err != 0) {
-		fprintf(stderr, "pthread_create failed: %s (%d)\n",
-			strerror(err), err);
-		exit(-1);
-	}
+	ret = pthread_create(&childid, &attr, func, ctx);
+	if (ret != 0)
+		err(EXIT_FAILURE, "pthread_create failed");
+
 	return childid;
 }
 
@@ -207,14 +200,14 @@ static unsigned int group(pthread_t *pth,
 			+ num_fds * sizeof(int));
 
 	if (!snd_ctx)
-		barf("malloc()");
+		err(EXIT_FAILURE, "malloc()");
 
 	for (i = 0; i < num_fds; i++) {
 		int fds[2];
 		struct receiver_context *ctx = malloc(sizeof(*ctx));
 
 		if (!ctx)
-			barf("malloc()");
+			err(EXIT_FAILURE, "malloc()");
 
 
 		/* Create the pipe between client and server */
@@ -281,7 +274,7 @@ int bench_sched_messaging(int argc, const char **argv,
 
 	pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t));
 	if (!pth_tab)
-		barf("main:malloc()");
+		err(EXIT_FAILURE, "main:malloc()");
 
 	fdpair(readyfds);
 	fdpair(wakefds);
@@ -294,13 +287,13 @@ int bench_sched_messaging(int argc, const char **argv,
 	/* Wait for everyone to be ready */
 	for (i = 0; i < total_children; i++)
 		if (read(readyfds[0], &dummy, 1) != 1)
-			barf("Reading for readyfds");
+			err(EXIT_FAILURE, "Reading for readyfds");
 
 	gettimeofday(&start, NULL);
 
 	/* Kick them off */
 	if (write(wakefds[1], &dummy, 1) != 1)
-		barf("Writing to start them");
+		err(EXIT_FAILURE, "Writing to start them");
 
 	/* Reap them all */
 	for (i = 0; i < total_children; i++)
@@ -332,5 +325,7 @@ int bench_sched_messaging(int argc, const char **argv,
 		break;
 	}
 
+	free(pth_tab);
+
 	return 0;
 }
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index d30d2c2e2a7..1ec429fef2b 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -65,12 +65,13 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0);
+	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL, 1, 1, 0,
+				true);
 	if (he == NULL)
 		return -ENOMEM;
 
 	ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	hists__inc_nr_samples(&evsel->hists, true);
 	return ret;
 }
 
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 1e6e7771054..b9a56fa8333 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -104,9 +104,11 @@ static const char *bench_format_str;
 
 /* Output/formatting style, exported to benchmark modules: */
 int bench_format = BENCH_FORMAT_DEFAULT;
+unsigned int bench_repeat = 10; /* default number of times to repeat the run */
 
 static const struct option bench_options[] = {
 	OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"),
+	OPT_UINTEGER('r', "repeat",  &bench_repeat,   "Specify amount of times to repeat the run"),
 	OPT_END()
 };
 
@@ -226,6 +228,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto end;
 	}
 
+	if (bench_repeat == 0) {
+		printf("Invalid repeat option: Must specify a positive value\n");
+		goto end;
+	}
+
 	if (argc < 1) {
 		print_usage();
 		goto end;
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index b22dbb16f87..2a2c78f8087 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -125,7 +125,8 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
 	return ret;
 }
 
-static int build_id_cache__add_kcore(const char *filename, const char *debugdir)
+static int build_id_cache__add_kcore(const char *filename, const char *debugdir,
+				     bool force)
 {
 	char dir[32], sbuildid[BUILD_ID_SIZE * 2 + 1];
 	char from_dir[PATH_MAX], to_dir[PATH_MAX];
@@ -144,7 +145,8 @@ static int build_id_cache__add_kcore(const char *filename, const char *debugdir)
 	scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s",
 		  debugdir, sbuildid);
 
-	if (!build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
+	if (!force &&
+	    !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
 		pr_debug("same kcore found in %s\n", to_dir);
 		return 0;
 	}
@@ -389,7 +391,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	}
 
 	if (kcore_filename &&
-	    build_id_cache__add_kcore(kcore_filename, debugdir))
+	    build_id_cache__add_kcore(kcore_filename, debugdir, force))
 		pr_warning("Couldn't add %s\n", kcore_filename);
 
 	return ret;
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 8bff543acaa..9a5a035cb42 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -315,7 +315,7 @@ static int hists__add_entry(struct hists *hists,
 			    u64 weight, u64 transaction)
 {
 	if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight,
-			       transaction) != NULL)
+			       transaction, true) != NULL)
 		return 0;
 	return -ENOMEM;
 }
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index c99e0de7e54..66e12f55c05 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -15,6 +15,7 @@
 #include "util/parse-options.h"
 #include "util/session.h"
 #include "util/data.h"
+#include "util/debug.h"
 
 static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
 {
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 178b88ae3d2..0384d930480 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -11,6 +11,7 @@
 #include "util/parse-options.h"
 #include "util/run-command.h"
 #include "util/help.h"
+#include "util/debug.h"
 
 static struct man_viewer_list {
 	struct man_viewer_list *next;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 6a3af0013d6..9a02807387d 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -72,7 +72,7 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
 	if (ret)
 		return ret;
 
-	if (&inject->output.is_pipe)
+	if (!inject->output.is_pipe)
 		return 0;
 
 	return perf_event__repipe_synth(tool, event);
@@ -389,6 +389,9 @@ static int __cmd_inject(struct perf_inject *inject)
 	ret = perf_session__process_events(session, &inject->tool);
 
 	if (!file_out->is_pipe) {
+		if (inject->build_ids)
+			perf_header__set_feat(&session->header,
+					      HEADER_BUILD_ID);
 		session->header.data_size = inject->bytes_written;
 		perf_session__write_header(session, session->evlist, file_out->fd, true);
 	}
@@ -436,6 +439,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "where and how long tasks slept"),
 		OPT_INCR('v', "verbose", &verbose,
 			 "be more verbose (show build ids, etc)"),
+		OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
+			   "kallsyms pathname"),
 		OPT_END()
 	};
 	const char * const inject_usage[] = {
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 0f1e5a2f6ad..43367eb0051 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -29,114 +29,25 @@
 #include <pthread.h>
 #include <math.h>
 
-#if defined(__i386__) || defined(__x86_64__)
-#include <asm/svm.h>
-#include <asm/vmx.h>
-#include <asm/kvm.h>
-
-struct event_key {
-	#define INVALID_KEY     (~0ULL)
-	u64 key;
-	int info;
-};
-
-struct kvm_event_stats {
-	u64 time;
-	struct stats stats;
-};
-
-struct kvm_event {
-	struct list_head hash_entry;
-	struct rb_node rb;
-
-	struct event_key key;
-
-	struct kvm_event_stats total;
-
-	#define DEFAULT_VCPU_NUM 8
-	int max_vcpu;
-	struct kvm_event_stats *vcpu;
-};
-
-typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
-
-struct kvm_event_key {
-	const char *name;
-	key_cmp_fun key;
-};
-
-
-struct perf_kvm_stat;
-
-struct kvm_events_ops {
-	bool (*is_begin_event)(struct perf_evsel *evsel,
-			       struct perf_sample *sample,
-			       struct event_key *key);
-	bool (*is_end_event)(struct perf_evsel *evsel,
-			     struct perf_sample *sample, struct event_key *key);
-	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
-			   char decode[20]);
-	const char *name;
-};
-
-struct exit_reasons_table {
-	unsigned long exit_code;
-	const char *reason;
-};
+#ifdef HAVE_KVM_STAT_SUPPORT
+#include <asm/kvm_perf.h>
+#include "util/kvm-stat.h"
 
-#define EVENTS_BITS		12
-#define EVENTS_CACHE_SIZE	(1UL << EVENTS_BITS)
-
-struct perf_kvm_stat {
-	struct perf_tool    tool;
-	struct record_opts  opts;
-	struct perf_evlist  *evlist;
-	struct perf_session *session;
-
-	const char *file_name;
-	const char *report_event;
-	const char *sort_key;
-	int trace_vcpu;
-
-	struct exit_reasons_table *exit_reasons;
-	int exit_reasons_size;
-	const char *exit_reasons_isa;
-
-	struct kvm_events_ops *events_ops;
-	key_cmp_fun compare;
-	struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];
-
-	u64 total_time;
-	u64 total_count;
-	u64 lost_events;
-	u64 duration;
-
-	const char *pid_str;
-	struct intlist *pid_list;
-
-	struct rb_root result;
-
-	int timerfd;
-	unsigned int display_time;
-	bool live;
-};
-
-
-static void exit_event_get_key(struct perf_evsel *evsel,
-			       struct perf_sample *sample,
-			       struct event_key *key)
+void exit_event_get_key(struct perf_evsel *evsel,
+			struct perf_sample *sample,
+			struct event_key *key)
 {
 	key->info = 0;
-	key->key = perf_evsel__intval(evsel, sample, "exit_reason");
+	key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON);
 }
 
-static bool kvm_exit_event(struct perf_evsel *evsel)
+bool kvm_exit_event(struct perf_evsel *evsel)
 {
-	return !strcmp(evsel->name, "kvm:kvm_exit");
+	return !strcmp(evsel->name, KVM_EXIT_TRACE);
 }
 
-static bool exit_event_begin(struct perf_evsel *evsel,
-			     struct perf_sample *sample, struct event_key *key)
+bool exit_event_begin(struct perf_evsel *evsel,
+		      struct perf_sample *sample, struct event_key *key)
 {
 	if (kvm_exit_event(evsel)) {
 		exit_event_get_key(evsel, sample, key);
@@ -146,32 +57,23 @@ static bool exit_event_begin(struct perf_evsel *evsel,
 	return false;
 }
 
-static bool kvm_entry_event(struct perf_evsel *evsel)
+bool kvm_entry_event(struct perf_evsel *evsel)
 {
-	return !strcmp(evsel->name, "kvm:kvm_entry");
+	return !strcmp(evsel->name, KVM_ENTRY_TRACE);
 }
 
-static bool exit_event_end(struct perf_evsel *evsel,
-			   struct perf_sample *sample __maybe_unused,
-			   struct event_key *key __maybe_unused)
+bool exit_event_end(struct perf_evsel *evsel,
+		    struct perf_sample *sample __maybe_unused,
+		    struct event_key *key __maybe_unused)
 {
 	return kvm_entry_event(evsel);
 }
 
-static struct exit_reasons_table vmx_exit_reasons[] = {
-	VMX_EXIT_REASONS
-};
-
-static struct exit_reasons_table svm_exit_reasons[] = {
-	SVM_EXIT_REASONS
-};
-
-static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
+static const char *get_exit_reason(struct perf_kvm_stat *kvm,
+				   struct exit_reasons_table *tbl,
+				   u64 exit_code)
 {
-	int i = kvm->exit_reasons_size;
-	struct exit_reasons_table *tbl = kvm->exit_reasons;
-
-	while (i--) {
+	while (tbl->reason != NULL) {
 		if (tbl->exit_code == exit_code)
 			return tbl->reason;
 		tbl++;
@@ -182,148 +84,30 @@ static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
 	return "UNKNOWN";
 }
 
-static void exit_event_decode_key(struct perf_kvm_stat *kvm,
-				  struct event_key *key,
-				  char decode[20])
+void exit_event_decode_key(struct perf_kvm_stat *kvm,
+			   struct event_key *key,
+			   char *decode)
 {
-	const char *exit_reason = get_exit_reason(kvm, key->key);
+	const char *exit_reason = get_exit_reason(kvm, key->exit_reasons,
+						  key->key);
 
-	scnprintf(decode, 20, "%s", exit_reason);
+	scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason);
 }
 
-static struct kvm_events_ops exit_events = {
-	.is_begin_event = exit_event_begin,
-	.is_end_event = exit_event_end,
-	.decode_key = exit_event_decode_key,
-	.name = "VM-EXIT"
-};
-
-/*
- * For the mmio events, we treat:
- * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
- * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...).
- */
-static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample,
-			       struct event_key *key)
-{
-	key->key  = perf_evsel__intval(evsel, sample, "gpa");
-	key->info = perf_evsel__intval(evsel, sample, "type");
-}
-
-#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
-#define KVM_TRACE_MMIO_READ 1
-#define KVM_TRACE_MMIO_WRITE 2
-
-static bool mmio_event_begin(struct perf_evsel *evsel,
-			     struct perf_sample *sample, struct event_key *key)
-{
-	/* MMIO read begin event in kernel. */
-	if (kvm_exit_event(evsel))
-		return true;
-
-	/* MMIO write begin event in kernel. */
-	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
-	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_WRITE) {
-		mmio_event_get_key(evsel, sample, key);
-		return true;
-	}
-
-	return false;
-}
-
-static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample,
-			   struct event_key *key)
-{
-	/* MMIO write end event in kernel. */
-	if (kvm_entry_event(evsel))
-		return true;
-
-	/* MMIO read end event in kernel.*/
-	if (!strcmp(evsel->name, "kvm:kvm_mmio") &&
-	    perf_evsel__intval(evsel, sample, "type") == KVM_TRACE_MMIO_READ) {
-		mmio_event_get_key(evsel, sample, key);
-		return true;
-	}
-
-	return false;
-}
-
-static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
-				  struct event_key *key,
-				  char decode[20])
-{
-	scnprintf(decode, 20, "%#lx:%s", (unsigned long)key->key,
-				key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
-}
-
-static struct kvm_events_ops mmio_events = {
-	.is_begin_event = mmio_event_begin,
-	.is_end_event = mmio_event_end,
-	.decode_key = mmio_event_decode_key,
-	.name = "MMIO Access"
-};
-
- /* The time of emulation pio access is from kvm_pio to kvm_entry. */
-static void ioport_event_get_key(struct perf_evsel *evsel,
-				 struct perf_sample *sample,
-				 struct event_key *key)
+static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
 {
-	key->key  = perf_evsel__intval(evsel, sample, "port");
-	key->info = perf_evsel__intval(evsel, sample, "rw");
-}
+	struct kvm_reg_events_ops *events_ops = kvm_reg_events_ops;
 
-static bool ioport_event_begin(struct perf_evsel *evsel,
-			       struct perf_sample *sample,
-			       struct event_key *key)
-{
-	if (!strcmp(evsel->name, "kvm:kvm_pio")) {
-		ioport_event_get_key(evsel, sample, key);
-		return true;
+	for (events_ops = kvm_reg_events_ops; events_ops->name; events_ops++) {
+		if (!strcmp(events_ops->name, kvm->report_event)) {
+			kvm->events_ops = events_ops->ops;
+			return true;
+		}
 	}
 
 	return false;
 }
 
-static bool ioport_event_end(struct perf_evsel *evsel,
-			     struct perf_sample *sample __maybe_unused,
-			     struct event_key *key __maybe_unused)
-{
-	return kvm_entry_event(evsel);
-}
-
-static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
-				    struct event_key *key,
-				    char decode[20])
-{
-	scnprintf(decode, 20, "%#llx:%s", (unsigned long long)key->key,
-				key->info ? "POUT" : "PIN");
-}
-
-static struct kvm_events_ops ioport_events = {
-	.is_begin_event = ioport_event_begin,
-	.is_end_event = ioport_event_end,
-	.decode_key = ioport_event_decode_key,
-	.name = "IO Port Access"
-};
-
-static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
-{
-	bool ret = true;
-
-	if (!strcmp(kvm->report_event, "vmexit"))
-		kvm->events_ops = &exit_events;
-	else if (!strcmp(kvm->report_event, "mmio"))
-		kvm->events_ops = &mmio_events;
-	else if (!strcmp(kvm->report_event, "ioport"))
-		kvm->events_ops = &ioport_events;
-	else {
-		pr_err("Unknown report event:%s\n", kvm->report_event);
-		ret = false;
-	}
-
-	return ret;
-}
-
 struct vcpu_event_record {
 	int vcpu_id;
 	u64 start_time;
@@ -477,6 +261,54 @@ static bool update_kvm_event(struct kvm_event *event, int vcpu_id,
 	return true;
 }
 
+static bool is_child_event(struct perf_kvm_stat *kvm,
+			   struct perf_evsel *evsel,
+			   struct perf_sample *sample,
+			   struct event_key *key)
+{
+	struct child_event_ops *child_ops;
+
+	child_ops = kvm->events_ops->child_ops;
+
+	if (!child_ops)
+		return false;
+
+	for (; child_ops->name; child_ops++) {
+		if (!strcmp(evsel->name, child_ops->name)) {
+			child_ops->get_key(evsel, sample, key);
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static bool handle_child_event(struct perf_kvm_stat *kvm,
+			       struct vcpu_event_record *vcpu_record,
+			       struct event_key *key,
+			       struct perf_sample *sample __maybe_unused)
+{
+	struct kvm_event *event = NULL;
+
+	if (key->key != INVALID_KEY)
+		event = find_create_kvm_event(kvm, key);
+
+	vcpu_record->last_event = event;
+
+	return true;
+}
+
+static bool skip_event(const char *event)
+{
+	const char * const *skip_events;
+
+	for (skip_events = kvm_skip_events; *skip_events; skip_events++)
+		if (!strcmp(event, *skip_events))
+			return true;
+
+	return false;
+}
+
 static bool handle_end_event(struct perf_kvm_stat *kvm,
 			     struct vcpu_event_record *vcpu_record,
 			     struct event_key *key,
@@ -525,10 +357,10 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
 	time_diff = sample->time - time_begin;
 
 	if (kvm->duration && time_diff > kvm->duration) {
-		char decode[32];
+		char decode[DECODE_STR_LEN];
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
-		if (strcmp(decode, "HLT")) {
+		if (!skip_event(decode)) {
 			pr_info("%" PRIu64 " VM %d, vcpu %d: %s event took %" PRIu64 "usec\n",
 				 sample->time, sample->pid, vcpu_record->vcpu_id,
 				 decode, time_diff/1000);
@@ -553,7 +385,7 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
 			return NULL;
 		}
 
-		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, "vcpu_id");
+		vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
 		thread->priv = vcpu_record;
 	}
 
@@ -566,7 +398,8 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm,
 			     struct perf_sample *sample)
 {
 	struct vcpu_event_record *vcpu_record;
-	struct event_key key = {.key = INVALID_KEY};
+	struct event_key key = { .key = INVALID_KEY,
+				 .exit_reasons = kvm->exit_reasons };
 
 	vcpu_record = per_vcpu_record(thread, evsel, sample);
 	if (!vcpu_record)
@@ -580,6 +413,9 @@ static bool handle_kvm_event(struct perf_kvm_stat *kvm,
 	if (kvm->events_ops->is_begin_event(evsel, sample, &key))
 		return handle_begin_event(kvm, vcpu_record, &key, sample->time);
 
+	if (is_child_event(kvm, evsel, sample, &key))
+		return handle_child_event(kvm, vcpu_record, &key, sample);
+
 	if (kvm->events_ops->is_end_event(evsel, sample, &key))
 		return handle_end_event(kvm, vcpu_record, &key, sample);
 
@@ -740,7 +576,7 @@ static void show_timeofday(void)
 
 static void print_result(struct perf_kvm_stat *kvm)
 {
-	char decode[20];
+	char decode[DECODE_STR_LEN];
 	struct kvm_event *event;
 	int vcpu = kvm->trace_vcpu;
 
@@ -751,7 +587,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 
 	pr_info("\n\n");
 	print_vcpu_info(kvm);
-	pr_info("%20s ", kvm->events_ops->name);
+	pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name);
 	pr_info("%10s ", "Samples");
 	pr_info("%9s ", "Samples%");
 
@@ -770,7 +606,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 		min = get_event_min(event, vcpu);
 
 		kvm->events_ops->decode_key(kvm, &event->key, decode);
-		pr_info("%20s ", decode);
+		pr_info("%*s ", DECODE_STR_LEN, decode);
 		pr_info("%10llu ", (unsigned long long)ecount);
 		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
 		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
@@ -839,34 +675,28 @@ static int process_sample_event(struct perf_tool *tool,
 static int cpu_isa_config(struct perf_kvm_stat *kvm)
 {
 	char buf[64], *cpuid;
-	int err, isa;
+	int err;
 
 	if (kvm->live) {
 		err = get_cpuid(buf, sizeof(buf));
 		if (err != 0) {
-			pr_err("Failed to look up CPU type (Intel or AMD)\n");
+			pr_err("Failed to look up CPU type\n");
 			return err;
 		}
 		cpuid = buf;
 	} else
 		cpuid = kvm->session->header.env.cpuid;
 
-	if (strstr(cpuid, "Intel"))
-		isa = 1;
-	else if (strstr(cpuid, "AMD"))
-		isa = 0;
-	else {
-		pr_err("CPU %s is not supported.\n", cpuid);
-		return -ENOTSUP;
+	if (!cpuid) {
+		pr_err("Failed to look up CPU type\n");
+		return -EINVAL;
 	}
 
-	if (isa == 1) {
-		kvm->exit_reasons = vmx_exit_reasons;
-		kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons);
-		kvm->exit_reasons_isa = "VMX";
-	}
+	err = cpu_isa_init(kvm, cpuid);
+	if (err == -ENOTSUP)
+		pr_err("CPU %s is not supported.\n", cpuid);
 
-	return 0;
+	return err;
 }
 
 static bool verify_vcpu(int vcpu)
@@ -1300,13 +1130,6 @@ exit:
 	return ret;
 }
 
-static const char * const kvm_events_tp[] = {
-	"kvm:kvm_entry",
-	"kvm:kvm_exit",
-	"kvm:kvm_mmio",
-	"kvm:kvm_pio",
-};
-
 #define STRDUP_FAIL_EXIT(s)		\
 	({	char *_p;		\
 	_p = strdup(s);		\
@@ -1318,7 +1141,7 @@ static const char * const kvm_events_tp[] = {
 static int
 kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
-	unsigned int rec_argc, i, j;
+	unsigned int rec_argc, i, j, events_tp_size;
 	const char **rec_argv;
 	const char * const record_args[] = {
 		"record",
@@ -1326,9 +1149,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		"-m", "1024",
 		"-c", "1",
 	};
+	const char * const *events_tp;
+	events_tp_size = 0;
+
+	for (events_tp = kvm_events_tp; *events_tp; events_tp++)
+		events_tp_size++;
 
 	rec_argc = ARRAY_SIZE(record_args) + argc + 2 +
-		   2 * ARRAY_SIZE(kvm_events_tp);
+		   2 * events_tp_size;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
@@ -1337,7 +1165,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = STRDUP_FAIL_EXIT(record_args[i]);
 
-	for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
+	for (j = 0; j < events_tp_size; j++) {
 		rec_argv[i++] = "-e";
 		rec_argv[i++] = STRDUP_FAIL_EXIT(kvm_events_tp[j]);
 	}
@@ -1356,7 +1184,8 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
 	const struct option kvm_events_report_options[] = {
 		OPT_STRING(0, "event", &kvm->report_event, "report event",
-			    "event for reporting: vmexit, mmio, ioport"),
+			   "event for reporting: vmexit, "
+			   "mmio (x86 only), ioport (x86 only)"),
 		OPT_INTEGER(0, "vcpu", &kvm->trace_vcpu,
 			    "vcpu id to report"),
 		OPT_STRING('k', "key", &kvm->sort_key, "sort-key",
@@ -1391,16 +1220,16 @@ static struct perf_evlist *kvm_live_event_list(void)
 {
 	struct perf_evlist *evlist;
 	char *tp, *name, *sys;
-	unsigned int j;
 	int err = -1;
+	const char * const *events_tp;
 
 	evlist = perf_evlist__new();
 	if (evlist == NULL)
 		return NULL;
 
-	for (j = 0; j < ARRAY_SIZE(kvm_events_tp); j++) {
+	for (events_tp = kvm_events_tp; *events_tp; events_tp++) {
 
-		tp = strdup(kvm_events_tp[j]);
+		tp = strdup(*events_tp);
 		if (tp == NULL)
 			goto out;
 
@@ -1409,7 +1238,7 @@ static struct perf_evlist *kvm_live_event_list(void)
 		name = strchr(tp, ':');
 		if (name == NULL) {
 			pr_err("Error parsing %s tracepoint: subsystem delimiter not found\n",
-				kvm_events_tp[j]);
+			       *events_tp);
 			free(tp);
 			goto out;
 		}
@@ -1417,7 +1246,7 @@ static struct perf_evlist *kvm_live_event_list(void)
 		name++;
 
 		if (perf_evlist__add_newtp(evlist, sys, name, NULL)) {
-			pr_err("Failed to add %s tracepoint to the list\n", kvm_events_tp[j]);
+			pr_err("Failed to add %s tracepoint to the list\n", *events_tp);
 			free(tp);
 			goto out;
 		}
@@ -1462,7 +1291,9 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 			"key for sorting: sample(sort by samples number)"
 			" time (sort by avg time)"),
 		OPT_U64(0, "duration", &kvm->duration,
-		    "show events other than HALT that take longer than duration usecs"),
+			"show events other than"
+			" HLT (x86 only) or Wait state (s390 only)"
+			" that take longer than duration usecs"),
 		OPT_END()
 	};
 	const char * const live_usage[] = {
@@ -1585,9 +1416,6 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
 		.report_event	= "vmexit",
 		.sort_key	= "sample",
 
-		.exit_reasons = svm_exit_reasons,
-		.exit_reasons_size = ARRAY_SIZE(svm_exit_reasons),
-		.exit_reasons_isa = "SVM",
 	};
 
 	if (argc == 1) {
@@ -1609,7 +1437,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
 perf_stat:
 	return cmd_stat(argc, argv, NULL);
 }
-#endif
+#endif /* HAVE_KVM_STAT_SUPPORT */
 
 static int __cmd_record(const char *file_name, int argc, const char **argv)
 {
@@ -1726,7 +1554,7 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 		return cmd_top(argc, argv, NULL);
 	else if (!strncmp(argv[0], "buildid-list", 12))
 		return __cmd_buildid_list(file_name, argc, argv);
-#if defined(__i386__) || defined(__x86_64__)
+#ifdef HAVE_KVM_STAT_SUPPORT
 	else if (!strncmp(argv[0], "stat", 4))
 		return kvm_cmd_stat(file_name, argc, argv);
 #endif
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index cdcd4eb3a57..c63fa292507 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -288,6 +288,13 @@ static void cleanup_params(void)
 	memset(&params, 0, sizeof(params));
 }
 
+static void pr_err_with_code(const char *msg, int err)
+{
+	pr_err("%s", msg);
+	pr_debug(" Reason: %s (Code: %d)", strerror(-err), err);
+	pr_err("\n");
+}
+
 static int
 __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 {
@@ -379,7 +386,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 		ret = parse_probe_event_argv(argc, argv);
 		if (ret < 0) {
-			pr_err("  Error: Parse Error.  (%d)\n", ret);
+			pr_err_with_code("  Error: Command Parse Error.", ret);
 			return ret;
 		}
 	}
@@ -419,8 +426,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 		ret = show_perf_probe_events();
 		if (ret < 0)
-			pr_err("  Error: Failed to show event list. (%d)\n",
-			       ret);
+			pr_err_with_code("  Error: Failed to show event list.", ret);
 		return ret;
 	}
 	if (params.show_funcs) {
@@ -445,8 +451,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		strfilter__delete(params.filter);
 		params.filter = NULL;
 		if (ret < 0)
-			pr_err("  Error: Failed to show functions."
-			       " (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show functions.", ret);
 		return ret;
 	}
 
@@ -464,7 +469,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 
 		ret = show_line_range(&params.line_range, params.target);
 		if (ret < 0)
-			pr_err("  Error: Failed to show lines. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show lines.", ret);
 		return ret;
 	}
 	if (params.show_vars) {
@@ -485,7 +490,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		strfilter__delete(params.filter);
 		params.filter = NULL;
 		if (ret < 0)
-			pr_err("  Error: Failed to show vars. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show vars.", ret);
 		return ret;
 	}
 #endif
@@ -493,7 +498,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (params.dellist) {
 		ret = del_perf_probe_events(params.dellist);
 		if (ret < 0) {
-			pr_err("  Error: Failed to delete events. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to delete events.", ret);
 			return ret;
 		}
 	}
@@ -504,7 +509,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 					    params.target,
 					    params.force_add);
 		if (ret < 0) {
-			pr_err("  Error: Failed to add events. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
 	}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e4c85b8f46c..4869050e719 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -238,6 +238,7 @@ static struct perf_event_header finished_round_event = {
 
 static int record__mmap_read_all(struct record *rec)
 {
+	u64 bytes_written = rec->bytes_written;
 	int i;
 	int rc = 0;
 
@@ -250,7 +251,11 @@ static int record__mmap_read_all(struct record *rec)
 		}
 	}
 
-	if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
+	/*
+	 * Mark the round finished in case we wrote
+	 * at least one event.
+	 */
+	if (bytes_written != rec->bytes_written)
 		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
 out:
@@ -454,7 +459,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			if (done)
 				break;
 			err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
-			if (err < 0 && errno == EINTR)
+			/*
+			 * Propagate error, only if there's any. Ignore positive
+			 * number of returned events and interrupt error.
+			 */
+			if (err > 0 || (err < 0 && errno == EINTR))
 				err = 0;
 			waking++;
 		}
@@ -544,6 +553,7 @@ static const struct branch_mode branch_modes[] = {
 	BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
 	BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
 	BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
+	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
 	BRANCH_END
 };
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index bc0eec1ce4b..21d830bafff 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -72,6 +72,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
+	if (!strcmp(var, "report.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -85,156 +89,52 @@ static void report__inc_stats(struct report *rep, struct hist_entry *he)
 	 */
 	if (he->stat.nr_events == 1)
 		rep->nr_entries++;
-
-	/*
-	 * Only counts number of samples at this stage as it's more
-	 * natural to do it here and non-sample events are also
-	 * counted in perf_session_deliver_event().  The dump_trace
-	 * requires this info is ready before going to the output tree.
-	 */
-	hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		he->hists->stats.nr_non_filtered_samples++;
 }
 
-static int report__add_mem_hist_entry(struct report *rep, struct addr_location *al,
-				      struct perf_sample *sample, struct perf_evsel *evsel)
+static int hist_iter__report_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al, bool single,
+				      void *arg)
 {
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	struct mem_info *mi, *mx;
-	uint64_t cost;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
+	int err = 0;
+	struct report *rep = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct mem_info *mi;
+	struct branch_info *bi;
 
-	mi = sample__resolve_mem(sample, al);
-	if (!mi)
-		return -ENOMEM;
+	report__inc_stats(rep, he);
 
-	if (rep->hide_unresolved && !al->sym)
+	if (!ui__has_annotation())
 		return 0;
 
-	cost = sample->weight;
-	if (!cost)
-		cost = 1;
-
-	/*
-	 * must pass period=weight in order to get the correct
-	 * sorting from hists__collapse_resort() which is solely
-	 * based on periods. We want sorting be done on nr_events * weight
-	 * and this is indirectly achieved by passing period=weight here
-	 * and the he_stat__add_period() function.
-	 */
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, mi,
-				cost, cost, 0);
-	if (!he)
-		return -ENOMEM;
-
-	if (ui__has_annotation()) {
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-		if (err)
-			goto out;
-
-		mx = he->mem_info;
-		err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
+	if (sort__mode == SORT_MODE__BRANCH) {
+		bi = he->branch_info;
+		err = addr_map_symbol__inc_samples(&bi->from, evsel->idx);
 		if (err)
 			goto out;
-	}
-
-	report__inc_stats(rep, he);
-
-	err = hist_entry__append_callchain(he, sample);
-out:
-	return err;
-}
-
-static int report__add_branch_hist_entry(struct report *rep, struct addr_location *al,
-					 struct perf_sample *sample, struct perf_evsel *evsel)
-{
-	struct symbol *parent = NULL;
-	unsigned i;
-	struct hist_entry *he;
-	struct branch_info *bi, *bx;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
 
-	if (err)
-		return err;
-
-	bi = sample__resolve_bstack(sample, al);
-	if (!bi)
-		return -ENOMEM;
-
-	for (i = 0; i < sample->branch_stack->nr; i++) {
-		if (rep->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
-			continue;
+		err = addr_map_symbol__inc_samples(&bi->to, evsel->idx);
 
-		err = -ENOMEM;
-
-		/* overwrite the 'al' to branch-to info */
-		al->map = bi[i].to.map;
-		al->sym = bi[i].to.sym;
-		al->addr = bi[i].to.addr;
-		/*
-		 * The report shows the percentage of total branches captured
-		 * and not events sampled. Thus we use a pseudo period of 1.
-		 */
-		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
-					1, 1, 0);
-		if (he) {
-			if (ui__has_annotation()) {
-				bx = he->branch_info;
-				err = addr_map_symbol__inc_samples(&bx->from,
-								   evsel->idx);
-				if (err)
-					goto out;
-
-				err = addr_map_symbol__inc_samples(&bx->to,
-								   evsel->idx);
-				if (err)
-					goto out;
-			}
-			report__inc_stats(rep, he);
-		} else
+	} else if (rep->mem_mode) {
+		mi = he->mem_info;
+		err = addr_map_symbol__inc_samples(&mi->daddr, evsel->idx);
+		if (err)
 			goto out;
-	}
-	err = 0;
-out:
-	free(bi);
-	return err;
-}
-
-static int report__add_hist_entry(struct report *rep, struct perf_evsel *evsel,
-				  struct addr_location *al, struct perf_sample *sample)
-{
-	struct symbol *parent = NULL;
-	struct hist_entry *he;
-	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
-
-	if (err)
-		return err;
 
-	he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction);
-	if (he == NULL)
-		return -ENOMEM;
-
-	err = hist_entry__append_callchain(he, sample);
-	if (err)
-		goto out;
-
-	if (ui__has_annotation())
 		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 
-	report__inc_stats(rep, he);
+	} else if (symbol_conf.cumulate_callchain) {
+		if (single)
+			err = hist_entry__inc_addr_samples(he, evsel->idx,
+							   al->addr);
+	} else {
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	}
 
 out:
 	return err;
 }
 
-
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -243,6 +143,10 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
+	struct hist_entry_iter iter = {
+		.hide_unresolved = rep->hide_unresolved,
+		.add_entry_cb = hist_iter__report_callback,
+	};
 	int ret;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
@@ -257,22 +161,23 @@ static int process_sample_event(struct perf_tool *tool,
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
 		return 0;
 
-	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = report__add_branch_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding lbr entry, skipping event\n");
-	} else if (rep->mem_mode == 1) {
-		ret = report__add_mem_hist_entry(rep, &al, sample, evsel);
-		if (ret < 0)
-			pr_debug("problem adding mem entry, skipping event\n");
-	} else {
-		if (al.map != NULL)
-			al.map->dso->hit = 1;
+	if (sort__mode == SORT_MODE__BRANCH)
+		iter.ops = &hist_iter_branch;
+	else if (rep->mem_mode)
+		iter.ops = &hist_iter_mem;
+	else if (symbol_conf.cumulate_callchain)
+		iter.ops = &hist_iter_cumulative;
+	else
+		iter.ops = &hist_iter_normal;
+
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
+	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
+				   rep);
+	if (ret < 0)
+		pr_debug("problem adding hist entry, skipping event\n");
 
-		ret = report__add_hist_entry(rep, evsel, &al, sample);
-		if (ret < 0)
-			pr_debug("problem incrementing symbol period, skipping event\n");
-	}
 	return ret;
 }
 
@@ -329,6 +234,14 @@ static int report__setup_sample_type(struct report *rep)
 			}
 	}
 
+	if (symbol_conf.cumulate_callchain) {
+		/* Silently ignore if callchain is missing */
+		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			symbol_conf.cumulate_callchain = false;
+			perf_hpp__cancel_cumulate();
+		}
+	}
+
 	if (sort__mode == SORT_MODE__BRANCH) {
 		if (!is_pipe &&
 		    !(sample_type & PERF_SAMPLE_BRANCH_STACK)) {
@@ -712,6 +625,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
 		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
 		     "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
 	OPT_INTEGER(0, "max-stack", &report.max_stack,
 		    "Set the maximum stack depth when parsing the callchain, "
 		    "anything beyond the specified depth will be ignored. "
@@ -804,8 +719,10 @@ repeat:
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (branch_mode == -1 && has_br_stack)
+	if (branch_mode == -1 && has_br_stack) {
 		sort__mode = SORT_MODE__BRANCH;
+		symbol_conf.cumulate_callchain = false;
+	}
 
 	if (report.mem_mode) {
 		if (sort__mode == SORT_MODE__BRANCH) {
@@ -813,6 +730,7 @@ repeat:
 			goto error;
 		}
 		sort__mode = SORT_MODE__MEMORY;
+		symbol_conf.cumulate_callchain = false;
 	}
 
 	if (setup_sorting() < 0) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index d7176830b9b..f83c08c0dd8 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -10,6 +10,7 @@
 #include "util/header.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/cloexec.h"
 
 #include "util/parse-options.h"
 #include "util/trace-event.h"
@@ -434,7 +435,8 @@ static int self_open_counters(void)
 	attr.type = PERF_TYPE_SOFTWARE;
 	attr.config = PERF_COUNT_SW_TASK_CLOCK;
 
-	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	fd = sys_perf_event_open(&attr, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
 
 	if (fd < 0)
 		pr_err("Error: sys_perf_event_open() syscall returned "
@@ -935,8 +937,8 @@ static int latency_switch_event(struct perf_sched *sched,
 		return -1;
 	}
 
-	sched_out = machine__findnew_thread(machine, 0, prev_pid);
-	sched_in = machine__findnew_thread(machine, 0, next_pid);
+	sched_out = machine__findnew_thread(machine, -1, prev_pid);
+	sched_in = machine__findnew_thread(machine, -1, next_pid);
 
 	out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
 	if (!out_events) {
@@ -979,7 +981,7 @@ static int latency_runtime_event(struct perf_sched *sched,
 {
 	const u32 pid	   = perf_evsel__intval(evsel, sample, "pid");
 	const u64 runtime  = perf_evsel__intval(evsel, sample, "runtime");
-	struct thread *thread = machine__findnew_thread(machine, 0, pid);
+	struct thread *thread = machine__findnew_thread(machine, -1, pid);
 	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 	u64 timestamp = sample->time;
 	int cpu = sample->cpu;
@@ -1012,7 +1014,7 @@ static int latency_wakeup_event(struct perf_sched *sched,
 	struct thread *wakee;
 	u64 timestamp = sample->time;
 
-	wakee = machine__findnew_thread(machine, 0, pid);
+	wakee = machine__findnew_thread(machine, -1, pid);
 	atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, wakee))
@@ -1072,7 +1074,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 	if (sched->profile_cpu == -1)
 		return 0;
 
-	migrant = machine__findnew_thread(machine, 0, pid);
+	migrant = machine__findnew_thread(machine, -1, pid);
 	atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, migrant))
@@ -1290,7 +1292,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		return -1;
 	}
 
-	sched_in = machine__findnew_thread(machine, 0, next_pid);
+	sched_in = machine__findnew_thread(machine, -1, next_pid);
 
 	sched->curr_thread[this_cpu] = sched_in;
 
@@ -1428,7 +1430,7 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	int err = 0;
 
 	evsel->hists.stats.total_period += sample->period;
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	hists__inc_nr_samples(&evsel->hists, true);
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9e9c91f5b7f..f57035b89c1 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -358,27 +358,6 @@ static void print_sample_start(struct perf_sample *sample,
 	}
 }
 
-static bool is_bts_event(struct perf_event_attr *attr)
-{
-	return ((attr->type == PERF_TYPE_HARDWARE) &&
-		(attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
-		(attr->sample_period == 1));
-}
-
-static bool sample_addr_correlates_sym(struct perf_event_attr *attr)
-{
-	if ((attr->type == PERF_TYPE_SOFTWARE) &&
-	    ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) ||
-	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) ||
-	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)))
-		return true;
-
-	if (is_bts_event(attr))
-		return true;
-
-	return false;
-}
-
 static void print_sample_addr(union perf_event *event,
 			  struct perf_sample *sample,
 			  struct machine *machine,
@@ -386,24 +365,13 @@ static void print_sample_addr(union perf_event *event,
 			  struct perf_event_attr *attr)
 {
 	struct addr_location al;
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	printf("%16" PRIx64, sample->addr);
 
 	if (!sample_addr_correlates_sym(attr))
 		return;
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->addr, &al);
-	if (!al.map)
-		thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
-				      sample->addr, &al);
-
-	al.cpu = sample->cpu;
-	al.sym = NULL;
-
-	if (al.map)
-		al.sym = map__find_symbol(al.map, al.addr, NULL);
+	perf_event__preprocess_sample_addr(event, sample, machine, thread, &al);
 
 	if (PRINT_FIELD(SYM)) {
 		printf(" ");
@@ -427,25 +395,35 @@ static void print_sample_bts(union perf_event *event,
 			     struct addr_location *al)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	bool print_srcline_last = false;
 
 	/* print branch_from information */
 	if (PRINT_FIELD(IP)) {
-		if (!symbol_conf.use_callchain)
-			printf(" ");
-		else
+		unsigned int print_opts = output[attr->type].print_ip_opts;
+
+		if (symbol_conf.use_callchain && sample->callchain) {
 			printf("\n");
-		perf_evsel__print_ip(evsel, sample, al,
-				     output[attr->type].print_ip_opts,
+		} else {
+			printf(" ");
+			if (print_opts & PRINT_IP_OPT_SRCLINE) {
+				print_srcline_last = true;
+				print_opts &= ~PRINT_IP_OPT_SRCLINE;
+			}
+		}
+		perf_evsel__print_ip(evsel, sample, al, print_opts,
 				     PERF_MAX_STACK_DEPTH);
 	}
 
-	printf(" => ");
-
 	/* print branch_to information */
 	if (PRINT_FIELD(ADDR) ||
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
-	     !output[attr->type].user_set))
+	     !output[attr->type].user_set)) {
+		printf(" => ");
 		print_sample_addr(event, sample, al->machine, thread, attr);
+	}
+
+	if (print_srcline_last)
+		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 
 	printf("\n");
 }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 65a151e3606..3e80aa10cfd 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -184,7 +184,7 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat));
-	if (evsel == NULL)
+	if (evsel->priv == NULL)
 		return -ENOMEM;
 	perf_evsel__reset_stat_priv(evsel);
 	return 0;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 74db2568b86..2f1a5220c09 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -37,6 +37,7 @@
 #include "util/svghelper.h"
 #include "util/tool.h"
 #include "util/data.h"
+#include "util/debug.h"
 
 #define SUPPORT_OLD_POWER_EVENTS 1
 #define PWR_EVENT_EXIT -1
@@ -60,10 +61,17 @@ struct timechart {
 				tasks_only,
 				with_backtrace,
 				topology;
+	/* IO related settings */
+	u64			io_events;
+	bool			io_only,
+				skip_eagain;
+	u64			min_time,
+				merge_dist;
 };
 
 struct per_pidcomm;
 struct cpu_sample;
+struct io_sample;
 
 /*
  * Datastructure layout:
@@ -84,6 +92,7 @@ struct per_pid {
 	u64		start_time;
 	u64		end_time;
 	u64		total_time;
+	u64		total_bytes;
 	int		display;
 
 	struct per_pidcomm *all;
@@ -97,6 +106,8 @@ struct per_pidcomm {
 	u64		start_time;
 	u64		end_time;
 	u64		total_time;
+	u64		max_bytes;
+	u64		total_bytes;
 
 	int		Y;
 	int		display;
@@ -107,6 +118,7 @@ struct per_pidcomm {
 	char		*comm;
 
 	struct cpu_sample *samples;
+	struct io_sample  *io_samples;
 };
 
 struct sample_wrapper {
@@ -131,6 +143,27 @@ struct cpu_sample {
 	const char *backtrace;
 };
 
+enum {
+	IOTYPE_READ,
+	IOTYPE_WRITE,
+	IOTYPE_SYNC,
+	IOTYPE_TX,
+	IOTYPE_RX,
+	IOTYPE_POLL,
+};
+
+struct io_sample {
+	struct io_sample *next;
+
+	u64 start_time;
+	u64 end_time;
+	u64 bytes;
+	int type;
+	int fd;
+	int err;
+	int merges;
+};
+
 #define CSTATE 1
 #define PSTATE 2
 
@@ -213,7 +246,7 @@ static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp)
 		pid_set_comm(tchart, pid, pp->current->comm);
 
 	p->start_time = timestamp;
-	if (p->current) {
+	if (p->current && !p->current->start_time) {
 		p->current->start_time = timestamp;
 		p->current->state_since = timestamp;
 	}
@@ -682,6 +715,249 @@ static void end_sample_processing(struct timechart *tchart)
 	}
 }
 
+static int pid_begin_io_sample(struct timechart *tchart, int pid, int type,
+			       u64 start, int fd)
+{
+	struct per_pid *p = find_create_pid(tchart, pid);
+	struct per_pidcomm *c = p->current;
+	struct io_sample *sample;
+	struct io_sample *prev;
+
+	if (!c) {
+		c = zalloc(sizeof(*c));
+		if (!c)
+			return -ENOMEM;
+		p->current = c;
+		c->next = p->all;
+		p->all = c;
+	}
+
+	prev = c->io_samples;
+
+	if (prev && prev->start_time && !prev->end_time) {
+		pr_warning("Skip invalid start event: "
+			   "previous event already started!\n");
+
+		/* remove previous event that has been started,
+		 * we are not sure we will ever get an end for it */
+		c->io_samples = prev->next;
+		free(prev);
+		return 0;
+	}
+
+	sample = zalloc(sizeof(*sample));
+	if (!sample)
+		return -ENOMEM;
+	sample->start_time = start;
+	sample->type = type;
+	sample->fd = fd;
+	sample->next = c->io_samples;
+	c->io_samples = sample;
+
+	if (c->start_time == 0 || c->start_time > start)
+		c->start_time = start;
+
+	return 0;
+}
+
+static int pid_end_io_sample(struct timechart *tchart, int pid, int type,
+			     u64 end, long ret)
+{
+	struct per_pid *p = find_create_pid(tchart, pid);
+	struct per_pidcomm *c = p->current;
+	struct io_sample *sample, *prev;
+
+	if (!c) {
+		pr_warning("Invalid pidcomm!\n");
+		return -1;
+	}
+
+	sample = c->io_samples;
+
+	if (!sample) /* skip partially captured events */
+		return 0;
+
+	if (sample->end_time) {
+		pr_warning("Skip invalid end event: "
+			   "previous event already ended!\n");
+		return 0;
+	}
+
+	if (sample->type != type) {
+		pr_warning("Skip invalid end event: invalid event type!\n");
+		return 0;
+	}
+
+	sample->end_time = end;
+	prev = sample->next;
+
+	/* we want to be able to see small and fast transfers, so make them
+	 * at least min_time long, but don't overlap them */
+	if (sample->end_time - sample->start_time < tchart->min_time)
+		sample->end_time = sample->start_time + tchart->min_time;
+	if (prev && sample->start_time < prev->end_time) {
+		if (prev->err) /* try to make errors more visible */
+			sample->start_time = prev->end_time;
+		else
+			prev->end_time = sample->start_time;
+	}
+
+	if (ret < 0) {
+		sample->err = ret;
+	} else if (type == IOTYPE_READ || type == IOTYPE_WRITE ||
+		   type == IOTYPE_TX || type == IOTYPE_RX) {
+
+		if ((u64)ret > c->max_bytes)
+			c->max_bytes = ret;
+
+		c->total_bytes += ret;
+		p->total_bytes += ret;
+		sample->bytes = ret;
+	}
+
+	/* merge two requests to make svg smaller and render-friendly */
+	if (prev &&
+	    prev->type == sample->type &&
+	    prev->err == sample->err &&
+	    prev->fd == sample->fd &&
+	    prev->end_time + tchart->merge_dist >= sample->start_time) {
+
+		sample->bytes += prev->bytes;
+		sample->merges += prev->merges + 1;
+
+		sample->start_time = prev->start_time;
+		sample->next = prev->next;
+		free(prev);
+
+		if (!sample->err && sample->bytes > c->max_bytes)
+			c->max_bytes = sample->bytes;
+	}
+
+	tchart->io_events++;
+
+	return 0;
+}
+
+static int
+process_enter_read(struct timechart *tchart,
+		   struct perf_evsel *evsel,
+		   struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_READ,
+				   sample->time, fd);
+}
+
+static int
+process_exit_read(struct timechart *tchart,
+		  struct perf_evsel *evsel,
+		  struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_READ,
+				 sample->time, ret);
+}
+
+static int
+process_enter_write(struct timechart *tchart,
+		    struct perf_evsel *evsel,
+		    struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_WRITE,
+				   sample->time, fd);
+}
+
+static int
+process_exit_write(struct timechart *tchart,
+		   struct perf_evsel *evsel,
+		   struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_WRITE,
+				 sample->time, ret);
+}
+
+static int
+process_enter_sync(struct timechart *tchart,
+		   struct perf_evsel *evsel,
+		   struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_SYNC,
+				   sample->time, fd);
+}
+
+static int
+process_exit_sync(struct timechart *tchart,
+		  struct perf_evsel *evsel,
+		  struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_SYNC,
+				 sample->time, ret);
+}
+
+static int
+process_enter_tx(struct timechart *tchart,
+		 struct perf_evsel *evsel,
+		 struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_TX,
+				   sample->time, fd);
+}
+
+static int
+process_exit_tx(struct timechart *tchart,
+		struct perf_evsel *evsel,
+		struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_TX,
+				 sample->time, ret);
+}
+
+static int
+process_enter_rx(struct timechart *tchart,
+		 struct perf_evsel *evsel,
+		 struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_RX,
+				   sample->time, fd);
+}
+
+static int
+process_exit_rx(struct timechart *tchart,
+		struct perf_evsel *evsel,
+		struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_RX,
+				 sample->time, ret);
+}
+
+static int
+process_enter_poll(struct timechart *tchart,
+		   struct perf_evsel *evsel,
+		   struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_POLL,
+				   sample->time, fd);
+}
+
+static int
+process_exit_poll(struct timechart *tchart,
+		  struct perf_evsel *evsel,
+		  struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_POLL,
+				 sample->time, ret);
+}
+
 /*
  * Sort the pid datastructure
  */
@@ -852,6 +1128,121 @@ static void draw_cpu_usage(struct timechart *tchart)
 	}
 }
 
+static void draw_io_bars(struct timechart *tchart)
+{
+	const char *suf;
+	double bytes;
+	char comm[256];
+	struct per_pid *p;
+	struct per_pidcomm *c;
+	struct io_sample *sample;
+	int Y = 1;
+
+	p = tchart->all_data;
+	while (p) {
+		c = p->all;
+		while (c) {
+			if (!c->display) {
+				c->Y = 0;
+				c = c->next;
+				continue;
+			}
+
+			svg_box(Y, c->start_time, c->end_time, "process3");
+			sample = c->io_samples;
+			for (sample = c->io_samples; sample; sample = sample->next) {
+				double h = (double)sample->bytes / c->max_bytes;
+
+				if (tchart->skip_eagain &&
+				    sample->err == -EAGAIN)
+					continue;
+
+				if (sample->err)
+					h = 1;
+
+				if (sample->type == IOTYPE_SYNC)
+					svg_fbox(Y,
+						sample->start_time,
+						sample->end_time,
+						1,
+						sample->err ? "error" : "sync",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_POLL)
+					svg_fbox(Y,
+						sample->start_time,
+						sample->end_time,
+						1,
+						sample->err ? "error" : "poll",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_READ)
+					svg_ubox(Y,
+						sample->start_time,
+						sample->end_time,
+						h,
+						sample->err ? "error" : "disk",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_WRITE)
+					svg_lbox(Y,
+						sample->start_time,
+						sample->end_time,
+						h,
+						sample->err ? "error" : "disk",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_RX)
+					svg_ubox(Y,
+						sample->start_time,
+						sample->end_time,
+						h,
+						sample->err ? "error" : "net",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_TX)
+					svg_lbox(Y,
+						sample->start_time,
+						sample->end_time,
+						h,
+						sample->err ? "error" : "net",
+						sample->fd,
+						sample->err,
+						sample->merges);
+			}
+
+			suf = "";
+			bytes = c->total_bytes;
+			if (bytes > 1024) {
+				bytes = bytes / 1024;
+				suf = "K";
+			}
+			if (bytes > 1024) {
+				bytes = bytes / 1024;
+				suf = "M";
+			}
+			if (bytes > 1024) {
+				bytes = bytes / 1024;
+				suf = "G";
+			}
+
+
+			sprintf(comm, "%s:%i (%3.1f %sbytes)", c->comm ?: "", p->pid, bytes, suf);
+			svg_text(Y, c->start_time, comm);
+
+			c->Y = Y;
+			Y++;
+			c = c->next;
+		}
+		p = p->next;
+	}
+}
+
 static void draw_process_bars(struct timechart *tchart)
 {
 	struct per_pid *p;
@@ -987,9 +1378,6 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 	struct per_pidcomm *c;
 	int count = 0;
 
-	if (process_filter)
-		return determine_display_tasks_filtered(tchart);
-
 	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
@@ -1025,15 +1413,46 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 	return count;
 }
 
+static int determine_display_io_tasks(struct timechart *timechart, u64 threshold)
+{
+	struct per_pid *p;
+	struct per_pidcomm *c;
+	int count = 0;
+
+	p = timechart->all_data;
+	while (p) {
+		/* no exit marker, task kept running to the end */
+		if (p->end_time == 0)
+			p->end_time = timechart->last_time;
 
+		c = p->all;
 
+		while (c) {
+			c->display = 0;
+
+			if (c->total_bytes >= threshold) {
+				c->display = 1;
+				count++;
+			}
+
+			if (c->end_time == 0)
+				c->end_time = timechart->last_time;
+
+			c = c->next;
+		}
+		p = p->next;
+	}
+	return count;
+}
+
+#define BYTES_THRESH (1 * 1024 * 1024)
 #define TIME_THRESH 10000000
 
 static void write_svg_file(struct timechart *tchart, const char *filename)
 {
 	u64 i;
 	int count;
-	int thresh = TIME_THRESH;
+	int thresh = tchart->io_events ? BYTES_THRESH : TIME_THRESH;
 
 	if (tchart->power_only)
 		tchart->proc_num = 0;
@@ -1041,28 +1460,43 @@ static void write_svg_file(struct timechart *tchart, const char *filename)
 	/* We'd like to show at least proc_num tasks;
 	 * be less picky if we have fewer */
 	do {
-		count = determine_display_tasks(tchart, thresh);
+		if (process_filter)
+			count = determine_display_tasks_filtered(tchart);
+		else if (tchart->io_events)
+			count = determine_display_io_tasks(tchart, thresh);
+		else
+			count = determine_display_tasks(tchart, thresh);
 		thresh /= 10;
 	} while (!process_filter && thresh && count < tchart->proc_num);
 
 	if (!tchart->proc_num)
 		count = 0;
 
-	open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
+	if (tchart->io_events) {
+		open_svg(filename, 0, count, tchart->first_time, tchart->last_time);
 
-	svg_time_grid();
-	svg_legenda();
+		svg_time_grid(0.5);
+		svg_io_legenda();
+
+		draw_io_bars(tchart);
+	} else {
+		open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
 
-	for (i = 0; i < tchart->numcpus; i++)
-		svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
+		svg_time_grid(0);
 
-	draw_cpu_usage(tchart);
-	if (tchart->proc_num)
-		draw_process_bars(tchart);
-	if (!tchart->tasks_only)
-		draw_c_p_states(tchart);
-	if (tchart->proc_num)
-		draw_wakeups(tchart);
+		svg_legenda();
+
+		for (i = 0; i < tchart->numcpus; i++)
+			svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
+
+		draw_cpu_usage(tchart);
+		if (tchart->proc_num)
+			draw_process_bars(tchart);
+		if (!tchart->tasks_only)
+			draw_c_p_states(tchart);
+		if (tchart->proc_num)
+			draw_wakeups(tchart);
+	}
 
 	svg_close();
 }
@@ -1110,6 +1544,56 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 		{ "power:power_end",		process_sample_power_end },
 		{ "power:power_frequency",	process_sample_power_frequency },
 #endif
+
+		{ "syscalls:sys_enter_read",		process_enter_read },
+		{ "syscalls:sys_enter_pread64",		process_enter_read },
+		{ "syscalls:sys_enter_readv",		process_enter_read },
+		{ "syscalls:sys_enter_preadv",		process_enter_read },
+		{ "syscalls:sys_enter_write",		process_enter_write },
+		{ "syscalls:sys_enter_pwrite64",	process_enter_write },
+		{ "syscalls:sys_enter_writev",		process_enter_write },
+		{ "syscalls:sys_enter_pwritev",		process_enter_write },
+		{ "syscalls:sys_enter_sync",		process_enter_sync },
+		{ "syscalls:sys_enter_sync_file_range",	process_enter_sync },
+		{ "syscalls:sys_enter_fsync",		process_enter_sync },
+		{ "syscalls:sys_enter_msync",		process_enter_sync },
+		{ "syscalls:sys_enter_recvfrom",	process_enter_rx },
+		{ "syscalls:sys_enter_recvmmsg",	process_enter_rx },
+		{ "syscalls:sys_enter_recvmsg",		process_enter_rx },
+		{ "syscalls:sys_enter_sendto",		process_enter_tx },
+		{ "syscalls:sys_enter_sendmsg",		process_enter_tx },
+		{ "syscalls:sys_enter_sendmmsg",	process_enter_tx },
+		{ "syscalls:sys_enter_epoll_pwait",	process_enter_poll },
+		{ "syscalls:sys_enter_epoll_wait",	process_enter_poll },
+		{ "syscalls:sys_enter_poll",		process_enter_poll },
+		{ "syscalls:sys_enter_ppoll",		process_enter_poll },
+		{ "syscalls:sys_enter_pselect6",	process_enter_poll },
+		{ "syscalls:sys_enter_select",		process_enter_poll },
+
+		{ "syscalls:sys_exit_read",		process_exit_read },
+		{ "syscalls:sys_exit_pread64",		process_exit_read },
+		{ "syscalls:sys_exit_readv",		process_exit_read },
+		{ "syscalls:sys_exit_preadv",		process_exit_read },
+		{ "syscalls:sys_exit_write",		process_exit_write },
+		{ "syscalls:sys_exit_pwrite64",		process_exit_write },
+		{ "syscalls:sys_exit_writev",		process_exit_write },
+		{ "syscalls:sys_exit_pwritev",		process_exit_write },
+		{ "syscalls:sys_exit_sync",		process_exit_sync },
+		{ "syscalls:sys_exit_sync_file_range",	process_exit_sync },
+		{ "syscalls:sys_exit_fsync",		process_exit_sync },
+		{ "syscalls:sys_exit_msync",		process_exit_sync },
+		{ "syscalls:sys_exit_recvfrom",		process_exit_rx },
+		{ "syscalls:sys_exit_recvmmsg",		process_exit_rx },
+		{ "syscalls:sys_exit_recvmsg",		process_exit_rx },
+		{ "syscalls:sys_exit_sendto",		process_exit_tx },
+		{ "syscalls:sys_exit_sendmsg",		process_exit_tx },
+		{ "syscalls:sys_exit_sendmmsg",		process_exit_tx },
+		{ "syscalls:sys_exit_epoll_pwait",	process_exit_poll },
+		{ "syscalls:sys_exit_epoll_wait",	process_exit_poll },
+		{ "syscalls:sys_exit_poll",		process_exit_poll },
+		{ "syscalls:sys_exit_ppoll",		process_exit_poll },
+		{ "syscalls:sys_exit_pselect6",		process_exit_poll },
+		{ "syscalls:sys_exit_select",		process_exit_poll },
 	};
 	struct perf_data_file file = {
 		.path = input_name,
@@ -1154,6 +1638,139 @@ out_delete:
 	return ret;
 }
 
+static int timechart__io_record(int argc, const char **argv)
+{
+	unsigned int rec_argc, i;
+	const char **rec_argv;
+	const char **p;
+	char *filter = NULL;
+
+	const char * const common_args[] = {
+		"record", "-a", "-R", "-c", "1",
+	};
+	unsigned int common_args_nr = ARRAY_SIZE(common_args);
+
+	const char * const disk_events[] = {
+		"syscalls:sys_enter_read",
+		"syscalls:sys_enter_pread64",
+		"syscalls:sys_enter_readv",
+		"syscalls:sys_enter_preadv",
+		"syscalls:sys_enter_write",
+		"syscalls:sys_enter_pwrite64",
+		"syscalls:sys_enter_writev",
+		"syscalls:sys_enter_pwritev",
+		"syscalls:sys_enter_sync",
+		"syscalls:sys_enter_sync_file_range",
+		"syscalls:sys_enter_fsync",
+		"syscalls:sys_enter_msync",
+
+		"syscalls:sys_exit_read",
+		"syscalls:sys_exit_pread64",
+		"syscalls:sys_exit_readv",
+		"syscalls:sys_exit_preadv",
+		"syscalls:sys_exit_write",
+		"syscalls:sys_exit_pwrite64",
+		"syscalls:sys_exit_writev",
+		"syscalls:sys_exit_pwritev",
+		"syscalls:sys_exit_sync",
+		"syscalls:sys_exit_sync_file_range",
+		"syscalls:sys_exit_fsync",
+		"syscalls:sys_exit_msync",
+	};
+	unsigned int disk_events_nr = ARRAY_SIZE(disk_events);
+
+	const char * const net_events[] = {
+		"syscalls:sys_enter_recvfrom",
+		"syscalls:sys_enter_recvmmsg",
+		"syscalls:sys_enter_recvmsg",
+		"syscalls:sys_enter_sendto",
+		"syscalls:sys_enter_sendmsg",
+		"syscalls:sys_enter_sendmmsg",
+
+		"syscalls:sys_exit_recvfrom",
+		"syscalls:sys_exit_recvmmsg",
+		"syscalls:sys_exit_recvmsg",
+		"syscalls:sys_exit_sendto",
+		"syscalls:sys_exit_sendmsg",
+		"syscalls:sys_exit_sendmmsg",
+	};
+	unsigned int net_events_nr = ARRAY_SIZE(net_events);
+
+	const char * const poll_events[] = {
+		"syscalls:sys_enter_epoll_pwait",
+		"syscalls:sys_enter_epoll_wait",
+		"syscalls:sys_enter_poll",
+		"syscalls:sys_enter_ppoll",
+		"syscalls:sys_enter_pselect6",
+		"syscalls:sys_enter_select",
+
+		"syscalls:sys_exit_epoll_pwait",
+		"syscalls:sys_exit_epoll_wait",
+		"syscalls:sys_exit_poll",
+		"syscalls:sys_exit_ppoll",
+		"syscalls:sys_exit_pselect6",
+		"syscalls:sys_exit_select",
+	};
+	unsigned int poll_events_nr = ARRAY_SIZE(poll_events);
+
+	rec_argc = common_args_nr +
+		disk_events_nr * 4 +
+		net_events_nr * 4 +
+		poll_events_nr * 4 +
+		argc;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
+	if (asprintf(&filter, "common_pid != %d", getpid()) < 0)
+		return -ENOMEM;
+
+	p = rec_argv;
+	for (i = 0; i < common_args_nr; i++)
+		*p++ = strdup(common_args[i]);
+
+	for (i = 0; i < disk_events_nr; i++) {
+		if (!is_valid_tracepoint(disk_events[i])) {
+			rec_argc -= 4;
+			continue;
+		}
+
+		*p++ = "-e";
+		*p++ = strdup(disk_events[i]);
+		*p++ = "--filter";
+		*p++ = filter;
+	}
+	for (i = 0; i < net_events_nr; i++) {
+		if (!is_valid_tracepoint(net_events[i])) {
+			rec_argc -= 4;
+			continue;
+		}
+
+		*p++ = "-e";
+		*p++ = strdup(net_events[i]);
+		*p++ = "--filter";
+		*p++ = filter;
+	}
+	for (i = 0; i < poll_events_nr; i++) {
+		if (!is_valid_tracepoint(poll_events[i])) {
+			rec_argc -= 4;
+			continue;
+		}
+
+		*p++ = "-e";
+		*p++ = strdup(poll_events[i]);
+		*p++ = "--filter";
+		*p++ = filter;
+	}
+
+	for (i = 0; i < (unsigned int)argc; i++)
+		*p++ = argv[i];
+
+	return cmd_record(rec_argc, rec_argv, NULL);
+}
+
+
 static int timechart__record(struct timechart *tchart, int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
@@ -1270,6 +1887,30 @@ parse_highlight(const struct option *opt __maybe_unused, const char *arg,
 	return 0;
 }
 
+static int
+parse_time(const struct option *opt, const char *arg, int __maybe_unused unset)
+{
+	char unit = 'n';
+	u64 *value = opt->value;
+
+	if (sscanf(arg, "%" PRIu64 "%cs", value, &unit) > 0) {
+		switch (unit) {
+		case 'm':
+			*value *= 1000000;
+			break;
+		case 'u':
+			*value *= 1000;
+			break;
+		case 'n':
+			break;
+		default:
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
 int cmd_timechart(int argc, const char **argv,
 		  const char *prefix __maybe_unused)
 {
@@ -1282,6 +1923,8 @@ int cmd_timechart(int argc, const char **argv,
 			.ordered_samples = true,
 		},
 		.proc_num = 15,
+		.min_time = 1000000,
+		.merge_dist = 1000,
 	};
 	const char *output_name = "output.svg";
 	const struct option timechart_options[] = {
@@ -1303,6 +1946,14 @@ int cmd_timechart(int argc, const char **argv,
 		    "min. number of tasks to print"),
 	OPT_BOOLEAN('t', "topology", &tchart.topology,
 		    "sort CPUs according to topology"),
+	OPT_BOOLEAN(0, "io-skip-eagain", &tchart.skip_eagain,
+		    "skip EAGAIN errors"),
+	OPT_CALLBACK(0, "io-min-time", &tchart.min_time, "time",
+		     "all IO faster than min-time will visually appear longer",
+		     parse_time),
+	OPT_CALLBACK(0, "io-merge-dist", &tchart.merge_dist, "time",
+		     "merge events that are merge-dist us apart",
+		     parse_time),
 	OPT_END()
 	};
 	const char * const timechart_usage[] = {
@@ -1314,6 +1965,8 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
 	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
 		    "output processes data only"),
+	OPT_BOOLEAN('I', "io-only", &tchart.io_only,
+		    "record only IO data"),
 	OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
 	OPT_END()
 	};
@@ -1340,7 +1993,10 @@ int cmd_timechart(int argc, const char **argv,
 			return -1;
 		}
 
-		return timechart__record(&tchart, argc, argv);
+		if (tchart.io_only)
+			return timechart__io_record(argc, argv);
+		else
+			return timechart__record(&tchart, argc, argv);
 	} else if (argc)
 		usage_with_options(timechart_usage, timechart_options);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 5b389ce4cd1..377971dc89a 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -196,6 +196,12 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 
 	pthread_mutex_unlock(&notes->lock);
 
+	/*
+	 * This function is now called with he->hists->lock held.
+	 * Release it before going to sleep.
+	 */
+	pthread_mutex_unlock(&he->hists->lock);
+
 	if (err == -ERANGE && !he->ms.map->erange_warned)
 		ui__warn_map_erange(he->ms.map, sym, ip);
 	else if (err == -ENOMEM) {
@@ -203,6 +209,8 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 		       sym->name);
 		sleep(1);
 	}
+
+	pthread_mutex_lock(&he->hists->lock);
 }
 
 static void perf_top__show_details(struct perf_top *top)
@@ -238,27 +246,6 @@ out_unlock:
 	pthread_mutex_unlock(&notes->lock);
 }
 
-static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
-						     struct addr_location *al,
-						     struct perf_sample *sample)
-{
-	struct hist_entry *he;
-
-	pthread_mutex_lock(&evsel->hists.lock);
-	he = __hists__add_entry(&evsel->hists, al, NULL, NULL, NULL,
-				sample->period, sample->weight,
-				sample->transaction);
-	pthread_mutex_unlock(&evsel->hists.lock);
-	if (he == NULL)
-		return NULL;
-
-	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-	if (!he->filtered)
-		evsel->hists.stats.nr_non_filtered_samples++;
-
-	return he;
-}
-
 static void perf_top__print_sym_table(struct perf_top *top)
 {
 	char bf[160];
@@ -662,6 +649,26 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 	return 0;
 }
 
+static int hist_iter__top_callback(struct hist_entry_iter *iter,
+				   struct addr_location *al, bool single,
+				   void *arg)
+{
+	struct perf_top *top = arg;
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+
+	if (sort__has_sym && single) {
+		u64 ip = al->addr;
+
+		if (al->map)
+			ip = al->map->unmap_ip(al->map, ip);
+
+		perf_top__record_precise_ip(top, he, evsel->idx, ip);
+	}
+
+	return 0;
+}
+
 static void perf_event__process_sample(struct perf_tool *tool,
 				       const union perf_event *event,
 				       struct perf_evsel *evsel,
@@ -669,8 +676,6 @@ static void perf_event__process_sample(struct perf_tool *tool,
 				       struct machine *machine)
 {
 	struct perf_top *top = container_of(tool, struct perf_top, tool);
-	struct symbol *parent = NULL;
-	u64 ip = sample->ip;
 	struct addr_location al;
 	int err;
 
@@ -745,25 +750,23 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	}
 
 	if (al.sym == NULL || !al.sym->ignore) {
-		struct hist_entry *he;
+		struct hist_entry_iter iter = {
+			.add_entry_cb = hist_iter__top_callback,
+		};
 
-		err = sample__resolve_callchain(sample, &parent, evsel, &al,
-						top->max_stack);
-		if (err)
-			return;
+		if (symbol_conf.cumulate_callchain)
+			iter.ops = &hist_iter_cumulative;
+		else
+			iter.ops = &hist_iter_normal;
 
-		he = perf_evsel__add_hist_entry(evsel, &al, sample);
-		if (he == NULL) {
-			pr_err("Problem incrementing symbol period, skipping event\n");
-			return;
-		}
+		pthread_mutex_lock(&evsel->hists.lock);
 
-		err = hist_entry__append_callchain(he, sample);
-		if (err)
-			return;
+		err = hist_entry_iter__add(&iter, &al, evsel, sample,
+					   top->max_stack, top);
+		if (err < 0)
+			pr_err("Problem incrementing symbol period, skipping event\n");
 
-		if (sort__has_sym)
-			perf_top__record_precise_ip(top, he, evsel->idx, ip);
+		pthread_mutex_unlock(&evsel->hists.lock);
 	}
 
 	return;
@@ -1001,6 +1004,10 @@ static int perf_top_config(const char *var, const char *value, void *cb)
 
 	if (!strcmp(var, "top.call-graph"))
 		return record_parse_callchain(value, &top->record_opts);
+	if (!strcmp(var, "top.children")) {
+		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -1095,6 +1102,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK(0, "call-graph", &top.record_opts,
 		     "mode[,dump_size]", record_callchain_help,
 		     &parse_callchain_opt),
+	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
+		    "Accumulate callchains of children and show total overhead as well"),
 	OPT_INTEGER(0, "max-stack", &top.max_stack,
 		    "Set the maximum stack depth when parsing the callchain. "
 		    "Default: " __stringify(PERF_MAX_STACK_DEPTH)),
@@ -1200,6 +1209,11 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	top.sym_evsel = perf_evlist__first(top.evlist);
 
+	if (!symbol_conf.use_callchain) {
+		symbol_conf.cumulate_callchain = false;
+		perf_hpp__cancel_cumulate();
+	}
+
 	symbol_conf.priv_size = sizeof(struct annotation);
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f954c26de23..a6c375224f4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1108,6 +1108,7 @@ struct syscall {
 	struct event_format *tp_format;
 	const char	    *name;
 	bool		    filtered;
+	bool		    is_exit;
 	struct syscall_fmt  *fmt;
 	size_t		    (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
 	void		    **arg_parm;
@@ -1132,6 +1133,7 @@ struct thread_trace {
 	u64		  exit_time;
 	bool		  entry_pending;
 	unsigned long	  nr_events;
+	unsigned long	  pfmaj, pfmin;
 	char		  *entry_str;
 	double		  runtime_ms;
 	struct {
@@ -1177,6 +1179,9 @@ fail:
 	return NULL;
 }
 
+#define TRACE_PFMAJ		(1 << 0)
+#define TRACE_PFMIN		(1 << 1)
+
 struct trace {
 	struct perf_tool	tool;
 	struct {
@@ -1211,6 +1216,8 @@ struct trace {
 	bool			summary_only;
 	bool			show_comm;
 	bool			show_tool_stats;
+	bool			trace_syscalls;
+	int			trace_pgfaults;
 };
 
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
@@ -1276,11 +1283,11 @@ static const char *thread__fd_path(struct thread *thread, int fd,
 	if (fd < 0)
 		return NULL;
 
-	if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL))
+	if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) {
 		if (!trace->live)
 			return NULL;
 		++trace->stats.proc_getname;
-		if (thread__read_fd_path(thread, fd)) {
+		if (thread__read_fd_path(thread, fd))
 			return NULL;
 	}
 
@@ -1473,6 +1480,8 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	if (sc->tp_format == NULL)
 		return -1;
 
+	sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
+
 	return syscall__set_arg_fmts(sc);
 }
 
@@ -1535,6 +1544,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 }
 
 typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
+				  union perf_event *event,
 				  struct perf_sample *sample);
 
 static struct syscall *trace__syscall_info(struct trace *trace,
@@ -1607,6 +1617,7 @@ static void thread__update_stats(struct thread_trace *ttrace,
 }
 
 static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
+			    union perf_event *event __maybe_unused,
 			    struct perf_sample *sample)
 {
 	char *msg;
@@ -1629,7 +1640,6 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 		return -1;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	ttrace = thread->priv;
 
 	if (ttrace->entry_str == NULL) {
 		ttrace->entry_str = malloc(1024);
@@ -1644,7 +1654,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
 					   args, trace, thread);
 
-	if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
+	if (sc->is_exit) {
 		if (!trace->duration_filter && !trace->summary_only) {
 			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
 			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
@@ -1656,6 +1666,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 }
 
 static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
+			   union perf_event *event __maybe_unused,
 			   struct perf_sample *sample)
 {
 	int ret;
@@ -1687,8 +1698,6 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 		++trace->stats.vfs_getname;
 	}
 
-	ttrace = thread->priv;
-
 	ttrace->exit_time = sample->time;
 
 	if (ttrace->entry_time) {
@@ -1735,6 +1744,7 @@ out:
 }
 
 static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
+			      union perf_event *event __maybe_unused,
 			      struct perf_sample *sample)
 {
 	trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname");
@@ -1742,6 +1752,7 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 }
 
 static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
+				     union perf_event *event __maybe_unused,
 				     struct perf_sample *sample)
 {
         u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
@@ -1768,6 +1779,80 @@ out_dump:
 	return 0;
 }
 
+static void print_location(FILE *f, struct perf_sample *sample,
+			   struct addr_location *al,
+			   bool print_dso, bool print_sym)
+{
+
+	if ((verbose || print_dso) && al->map)
+		fprintf(f, "%s@", al->map->dso->long_name);
+
+	if ((verbose || print_sym) && al->sym)
+		fprintf(f, "%s+0x%" PRIx64, al->sym->name,
+			al->addr - al->sym->start);
+	else if (al->map)
+		fprintf(f, "0x%" PRIx64, al->addr);
+	else
+		fprintf(f, "0x%" PRIx64, sample->addr);
+}
+
+static int trace__pgfault(struct trace *trace,
+			  struct perf_evsel *evsel,
+			  union perf_event *event,
+			  struct perf_sample *sample)
+{
+	struct thread *thread;
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct addr_location al;
+	char map_type = 'd';
+	struct thread_trace *ttrace;
+
+	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	ttrace = thread__trace(thread, trace->output);
+	if (ttrace == NULL)
+		return -1;
+
+	if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
+		ttrace->pfmaj++;
+	else
+		ttrace->pfmin++;
+
+	if (trace->summary_only)
+		return 0;
+
+	thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION,
+			      sample->ip, &al);
+
+	trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);
+
+	fprintf(trace->output, "%sfault [",
+		evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ?
+		"maj" : "min");
+
+	print_location(trace->output, sample, &al, false, true);
+
+	fprintf(trace->output, "] => ");
+
+	thread__find_addr_location(thread, trace->host, cpumode, MAP__VARIABLE,
+				   sample->addr, &al);
+
+	if (!al.map) {
+		thread__find_addr_location(thread, trace->host, cpumode,
+					   MAP__FUNCTION, sample->addr, &al);
+
+		if (al.map)
+			map_type = 'x';
+		else
+			map_type = '?';
+	}
+
+	print_location(trace->output, sample, &al, true, false);
+
+	fprintf(trace->output, " (%c%c)\n", map_type, al.level);
+
+	return 0;
+}
+
 static bool skip_sample(struct trace *trace, struct perf_sample *sample)
 {
 	if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) ||
@@ -1781,7 +1866,7 @@ static bool skip_sample(struct trace *trace, struct perf_sample *sample)
 }
 
 static int trace__process_sample(struct perf_tool *tool,
-				 union perf_event *event __maybe_unused,
+				 union perf_event *event,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
 				 struct machine *machine __maybe_unused)
@@ -1799,7 +1884,7 @@ static int trace__process_sample(struct perf_tool *tool,
 
 	if (handler) {
 		++trace->nr_events;
-		handler(trace, evsel, sample);
+		handler(trace, evsel, event, sample);
 	}
 
 	return err;
@@ -1826,7 +1911,7 @@ static int parse_target_str(struct trace *trace)
 	return 0;
 }
 
-static int trace__record(int argc, const char **argv)
+static int trace__record(struct trace *trace, int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
@@ -1835,34 +1920,54 @@ static int trace__record(int argc, const char **argv)
 		"-R",
 		"-m", "1024",
 		"-c", "1",
-		"-e",
 	};
 
+	const char * const sc_args[] = { "-e", };
+	unsigned int sc_args_nr = ARRAY_SIZE(sc_args);
+	const char * const majpf_args[] = { "-e", "major-faults" };
+	unsigned int majpf_args_nr = ARRAY_SIZE(majpf_args);
+	const char * const minpf_args[] = { "-e", "minor-faults" };
+	unsigned int minpf_args_nr = ARRAY_SIZE(minpf_args);
+
 	/* +1 is for the event string below */
-	rec_argc = ARRAY_SIZE(record_args) + 1 + argc;
+	rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 1 +
+		majpf_args_nr + minpf_args_nr + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
 		return -ENOMEM;
 
+	j = 0;
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
-		rec_argv[i] = record_args[i];
-
-	/* event string may be different for older kernels - e.g., RHEL6 */
-	if (is_valid_tracepoint("raw_syscalls:sys_enter"))
-		rec_argv[i] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
-	else if (is_valid_tracepoint("syscalls:sys_enter"))
-		rec_argv[i] = "syscalls:sys_enter,syscalls:sys_exit";
-	else {
-		pr_err("Neither raw_syscalls nor syscalls events exist.\n");
-		return -1;
+		rec_argv[j++] = record_args[i];
+
+	if (trace->trace_syscalls) {
+		for (i = 0; i < sc_args_nr; i++)
+			rec_argv[j++] = sc_args[i];
+
+		/* event string may be different for older kernels - e.g., RHEL6 */
+		if (is_valid_tracepoint("raw_syscalls:sys_enter"))
+			rec_argv[j++] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
+		else if (is_valid_tracepoint("syscalls:sys_enter"))
+			rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit";
+		else {
+			pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+			return -1;
+		}
 	}
-	i++;
 
-	for (j = 0; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+	if (trace->trace_pgfaults & TRACE_PFMAJ)
+		for (i = 0; i < majpf_args_nr; i++)
+			rec_argv[j++] = majpf_args[i];
+
+	if (trace->trace_pgfaults & TRACE_PFMIN)
+		for (i = 0; i < minpf_args_nr; i++)
+			rec_argv[j++] = minpf_args[i];
+
+	for (i = 0; i < (unsigned int)argc; i++)
+		rec_argv[j++] = argv[i];
 
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(j, rec_argv, NULL);
 }
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
@@ -1882,6 +1987,30 @@ static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
 	perf_evlist__add(evlist, evsel);
 }
 
+static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
+				    u64 config)
+{
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.mmap_data = 1,
+	};
+
+	attr.config = config;
+	attr.sample_period = 1;
+
+	event_attr_init(&attr);
+
+	evsel = perf_evsel__new(&attr);
+	if (!evsel)
+		return -ENOMEM;
+
+	evsel->handler = trace__pgfault;
+	perf_evlist__add(evlist, evsel);
+
+	return 0;
+}
+
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
 	struct perf_evlist *evlist = perf_evlist__new();
@@ -1897,10 +2026,21 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out;
 	}
 
-	if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit))
+	if (trace->trace_syscalls &&
+	    perf_evlist__add_syscall_newtp(evlist, trace__sys_enter,
+					   trace__sys_exit))
 		goto out_error_tp;
 
-	perf_evlist__add_vfs_getname(evlist);
+	if (trace->trace_syscalls)
+		perf_evlist__add_vfs_getname(evlist);
+
+	if ((trace->trace_pgfaults & TRACE_PFMAJ) &&
+	    perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ))
+		goto out_error_tp;
+
+	if ((trace->trace_pgfaults & TRACE_PFMIN) &&
+	    perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN))
+		goto out_error_tp;
 
 	if (trace->sched &&
 		perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
@@ -1982,7 +2122,8 @@ again:
 				goto next_event;
 			}
 
-			if (sample.raw_data == NULL) {
+			if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
+			    sample.raw_data == NULL) {
 				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
 				       perf_evsel__name(evsel), sample.tid,
 				       sample.cpu, sample.raw_size);
@@ -1990,7 +2131,7 @@ again:
 			}
 
 			handler = evsel->handler;
-			handler(trace, evsel, &sample);
+			handler(trace, evsel, event, &sample);
 next_event:
 			perf_evlist__mmap_consume(evlist, i);
 
@@ -2093,13 +2234,10 @@ static int trace__replay(struct trace *trace)
 	if (evsel == NULL)
 		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 							     "syscalls:sys_enter");
-	if (evsel == NULL) {
-		pr_err("Data file does not have raw_syscalls:sys_enter event\n");
-		goto out;
-	}
 
-	if (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
-	    perf_evsel__init_sc_tp_ptr_field(evsel, args)) {
+	if (evsel &&
+	    (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
+	    perf_evsel__init_sc_tp_ptr_field(evsel, args))) {
 		pr_err("Error during initialize raw_syscalls:sys_enter event\n");
 		goto out;
 	}
@@ -2109,15 +2247,19 @@ static int trace__replay(struct trace *trace)
 	if (evsel == NULL)
 		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 							     "syscalls:sys_exit");
-	if (evsel == NULL) {
-		pr_err("Data file does not have raw_syscalls:sys_exit event\n");
+	if (evsel &&
+	    (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
+	    perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
+		pr_err("Error during initialize raw_syscalls:sys_exit event\n");
 		goto out;
 	}
 
-	if (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
-	    perf_evsel__init_sc_tp_uint_field(evsel, ret)) {
-		pr_err("Error during initialize raw_syscalls:sys_exit event\n");
-		goto out;
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.type == PERF_TYPE_SOFTWARE &&
+		    (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ||
+		     evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
+		     evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS))
+			evsel->handler = trace__pgfault;
 	}
 
 	err = parse_target_str(trace);
@@ -2217,6 +2359,10 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 	printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
 	printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
 	printed += fprintf(fp, "%.1f%%", ratio);
+	if (ttrace->pfmaj)
+		printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
+	if (ttrace->pfmin)
+		printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
 	printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
 	printed += thread__dump_stats(ttrace, trace, fp);
 
@@ -2264,6 +2410,23 @@ static int trace__open_output(struct trace *trace, const char *filename)
 	return trace->output == NULL ? -errno : 0;
 }
 
+static int parse_pagefaults(const struct option *opt, const char *str,
+			    int unset __maybe_unused)
+{
+	int *trace_pgfaults = opt->value;
+
+	if (strcmp(str, "all") == 0)
+		*trace_pgfaults |= TRACE_PFMAJ | TRACE_PFMIN;
+	else if (strcmp(str, "maj") == 0)
+		*trace_pgfaults |= TRACE_PFMAJ;
+	else if (strcmp(str, "min") == 0)
+		*trace_pgfaults |= TRACE_PFMIN;
+	else
+		return -1;
+
+	return 0;
+}
+
 int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char * const trace_usage[] = {
@@ -2293,6 +2456,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		},
 		.output = stdout,
 		.show_comm = true,
+		.trace_syscalls = true,
 	};
 	const char *output_name = NULL;
 	const char *ev_qualifier_str = NULL;
@@ -2330,20 +2494,34 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show only syscall summary with statistics"),
 	OPT_BOOLEAN('S', "with-summary", &trace.summary,
 		    "Show all syscalls and summary with statistics"),
+	OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
+		     "Trace pagefaults", parse_pagefaults, "maj"),
+	OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
 	OPT_END()
 	};
 	int err;
 	char bf[BUFSIZ];
 
-	if ((argc > 1) && (strcmp(argv[1], "record") == 0))
-		return trace__record(argc-2, &argv[2]);
+	argc = parse_options(argc, argv, trace_options, trace_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
 
-	argc = parse_options(argc, argv, trace_options, trace_usage, 0);
+	if (trace.trace_pgfaults) {
+		trace.opts.sample_address = true;
+		trace.opts.sample_time = true;
+	}
+
+	if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
+		return trace__record(&trace, argc-1, &argv[1]);
 
 	/* summary_only implies summary option, but don't overwrite summary if set */
 	if (trace.summary_only)
 		trace.summary = trace.summary_only;
 
+	if (!trace.trace_syscalls && !trace.trace_pgfaults) {
+		pr_err("Please specify something to trace.\n");
+		return -1;
+	}
+
 	if (output_name != NULL) {
 		err = trace__open_output(&trace, output_name);
 		if (err < 0) {
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 729bbdf5cec..1f67aa02d24 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -48,6 +48,10 @@ ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
+ifeq ($(ARCH),powerpc)
+  CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
+endif
+
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 else
@@ -160,6 +164,7 @@ CORE_FEATURE_TESTS =			\
 	backtrace			\
 	dwarf				\
 	fortify-source			\
+	sync-compare-and-swap		\
 	glibc				\
 	gtk2				\
 	gtk2-infobar			\
@@ -195,6 +200,7 @@ LIB_FEATURE_TESTS =			\
 VF_FEATURE_TESTS =			\
 	backtrace			\
 	fortify-source			\
+	sync-compare-and-swap		\
 	gtk2-infobar			\
 	libelf-getphdrnum		\
 	libelf-mmap			\
@@ -268,6 +274,10 @@ CFLAGS += -I$(LIB_INCLUDE)
 
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 
+ifeq ($(feature-sync-compare-and-swap), 1)
+  CFLAGS += -DHAVE_SYNC_COMPARE_AND_SWAP_SUPPORT
+endif
+
 ifndef NO_BIONIC
   $(call feature_check,bionic)
   ifeq ($(feature-bionic), 1)
@@ -299,7 +309,11 @@ else
       NO_LIBUNWIND := 1
       NO_LIBDW_DWARF_UNWIND := 1
     else
-      msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
+      ifneq ($(filter s% -static%,$(LDFLAGS),),)
+        msg := $(error No static glibc found, please install glibc-static);
+      else
+        msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]);
+      endif
     endif
   else
     ifndef NO_LIBDW_DWARF_UNWIND
@@ -447,6 +461,7 @@ else
   ifneq ($(feature-libperl), 1)
     CFLAGS += -DNO_LIBPERL
     NO_LIBPERL := 1
+    msg := $(warning Missing perl devel files. Disabling perl scripting support, consider installing perl-ExtUtils-Embed);
   else
     LDFLAGS += $(PERL_EMBED_LDFLAGS)
     EXTLIBS += $(PERL_EMBED_LIBADD)
@@ -585,6 +600,10 @@ ifndef NO_LIBNUMA
   endif
 endif
 
+ifdef HAVE_KVM_STAT_SUPPORT
+    CFLAGS += -DHAVE_KVM_STAT_SUPPORT
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir
@@ -599,7 +618,7 @@ endif
 
 # Make the path relative to DESTDIR, not to prefix
 ifndef DESTDIR
-prefix = $(HOME)
+prefix ?= $(HOME)
 endif
 bindir_relative = bin
 bindir = $(prefix)/$(bindir_relative)
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 64c84e5f051..6088f8d8a43 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -5,6 +5,7 @@ FILES=					\
 	test-bionic.bin			\
 	test-dwarf.bin			\
 	test-fortify-source.bin		\
+	test-sync-compare-and-swap.bin	\
 	test-glibc.bin			\
 	test-gtk2.bin			\
 	test-gtk2-infobar.bin		\
@@ -141,6 +142,9 @@ test-timerfd.bin:
 test-libdw-dwarf-unwind.bin:
 	$(BUILD)
 
+test-sync-compare-and-swap.bin:
+	$(BUILD) -Werror
+
 -include *.d
 
 ###############################
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index fe5c1e5c952..a7d022e161c 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -89,6 +89,10 @@
 # include "test-libdw-dwarf-unwind.c"
 #undef main
 
+#define main main_test_sync_compare_and_swap
+# include "test-sync-compare-and-swap.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -111,6 +115,7 @@ int main(int argc, char *argv[])
 	main_test_timerfd();
 	main_test_stackprotector_all();
 	main_test_libdw_dwarf_unwind();
+	main_test_sync_compare_and_swap(argc, argv);
 
 	return 0;
 }
diff --git a/tools/perf/config/feature-checks/test-sync-compare-and-swap.c b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c
new file mode 100644
index 00000000000..c34d4ca4af5
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-sync-compare-and-swap.c
@@ -0,0 +1,14 @@
+#include <stdint.h>
+
+volatile uint64_t x;
+
+int main(int argc, char *argv[])
+{
+	uint64_t old, new = argc;
+
+	argv = argv;
+	do {
+		old = __sync_val_compare_and_swap(&x, 0, 0);
+	} while (!__sync_bool_compare_and_swap(&x, old, new));
+	return old == new;
+}
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 5268a1481d2..937e4324ad9 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -54,6 +54,7 @@
 #define mb()		asm volatile("bcr 15,0" ::: "memory")
 #define wmb()		asm volatile("bcr 15,0" ::: "memory")
 #define rmb()		asm volatile("bcr 15,0" ::: "memory")
+#define CPUINFO_PROC	"vendor_id"
 #endif
 
 #ifdef __sh__
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 431798a4110..2282d41879a 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,11 +13,12 @@
 #include "util/quote.h"
 #include "util/run-command.h"
 #include "util/parse-events.h"
+#include "util/debug.h"
 #include <api/fs/debugfs.h>
 #include <pthread.h>
 
 const char perf_usage_string[] =
-	"perf [--version] [--help] COMMAND [ARGS]";
+	"perf [--version] [--help] [OPTIONS] COMMAND [ARGS]";
 
 const char perf_more_info_string[] =
 	"See 'perf help COMMAND' for more information on a specific command.";
@@ -212,6 +213,16 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 				printf("%s ", p->cmd);
 			}
 			exit(0);
+		} else if (!strcmp(cmd, "--debug")) {
+			if (*argc < 2) {
+				fprintf(stderr, "No variable specified for --debug.\n");
+				usage(perf_usage_string);
+			}
+			if (perf_debug_option((*argv)[1]))
+				usage(perf_usage_string);
+
+			(*argv)++;
+			(*argc)--;
 		} else {
 			fprintf(stderr, "Unknown option: %s\n", cmd);
 			usage(perf_usage_string);
@@ -458,6 +469,7 @@ int main(int argc, const char **argv)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
+	cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
 
 	cmd = perf_extract_argv0_path(argv[0]);
 	if (!cmd)
@@ -481,14 +493,18 @@ int main(int argc, const char **argv)
 		fprintf(stderr, "cannot handle %s internally", cmd);
 		goto out;
 	}
-#ifdef HAVE_LIBAUDIT_SUPPORT
 	if (!prefixcmp(cmd, "trace")) {
+#ifdef HAVE_LIBAUDIT_SUPPORT
 		set_buildid_dir();
 		setup_path();
 		argv[0] = "trace";
 		return cmd_trace(argc, argv, NULL);
-	}
+#else
+		fprintf(stderr,
+			"trace command not available: missing audit-libs devel package at build time.\n");
+		goto out;
 #endif
+	}
 	/* Look for flags.. */
 	argv++;
 	argc--;
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
index 8104895a7b6..74685f31837 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-record
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_exit $@
+(perf record -e raw_syscalls:sys_exit $@ || \
+ perf record -e syscalls:sys_exit $@) 2> /dev/null
diff --git a/tools/perf/scripts/perl/failed-syscalls.pl b/tools/perf/scripts/perl/failed-syscalls.pl
index 94bc25a347e..55e7ae4c5c8 100644
--- a/tools/perf/scripts/perl/failed-syscalls.pl
+++ b/tools/perf/scripts/perl/failed-syscalls.pl
@@ -26,6 +26,11 @@ sub raw_syscalls::sys_exit
 	}
 }
 
+sub syscalls::sys_exit
+{
+	raw_syscalls::sys_exit(@_)
+}
+
 sub trace_end
 {
     printf("\nfailed syscalls by comm:\n\n");
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index de7211e4fa4..38dfb720fb6 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -107,12 +107,13 @@ def taskState(state):
 
 class EventHeaders:
 	def __init__(self, common_cpu, common_secs, common_nsecs,
-		     common_pid, common_comm):
+		     common_pid, common_comm, common_callchain):
 		self.cpu = common_cpu
 		self.secs = common_secs
 		self.nsecs = common_nsecs
 		self.pid = common_pid
 		self.comm = common_comm
+		self.callchain = common_callchain
 
 	def ts(self):
 		return (self.secs * (10 ** 9)) + self.nsecs
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
index 8104895a7b6..74685f31837 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_exit $@
+(perf record -e raw_syscalls:sys_exit $@ || \
+ perf record -e syscalls:sys_exit $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
index 4efbfaa7f6a..d6940841e54 100644
--- a/tools/perf/scripts/python/bin/sctop-record
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_enter $@
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
index 4efbfaa7f6a..d6940841e54 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_enter $@
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
index 4efbfaa7f6a..d6940841e54 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_enter $@
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py
index 4647a7694cf..334599c6032 100644
--- a/tools/perf/scripts/python/check-perf-trace.py
+++ b/tools/perf/scripts/python/check-perf-trace.py
@@ -27,7 +27,7 @@ def trace_end():
 
 def irq__softirq_entry(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	vec):
+	common_callchain, vec):
 		print_header(event_name, common_cpu, common_secs, common_nsecs,
 			common_pid, common_comm)
 
@@ -38,7 +38,7 @@ def irq__softirq_entry(event_name, context, common_cpu,
 
 def kmem__kmalloc(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	call_site, ptr, bytes_req, bytes_alloc,
+	common_callchain, call_site, ptr, bytes_req, bytes_alloc,
 	gfp_flags):
 		print_header(event_name, common_cpu, common_secs, common_nsecs,
 			common_pid, common_comm)
diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py
index 85805fac411..cafeff3d74d 100644
--- a/tools/perf/scripts/python/failed-syscalls-by-pid.py
+++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py
@@ -39,7 +39,7 @@ def trace_end():
 
 def raw_syscalls__sys_exit(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	id, ret):
+	common_callchain, id, ret):
 	if (for_comm and common_comm != for_comm) or \
 	   (for_pid  and common_pid  != for_pid ):
 		return
@@ -50,6 +50,11 @@ def raw_syscalls__sys_exit(event_name, context, common_cpu,
 		except TypeError:
 			syscalls[common_comm][common_pid][id][ret] = 1
 
+def syscalls__sys_exit(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, ret):
+	raw_syscalls__sys_exit(**locals())
+
 def print_error_totals():
     if for_comm is not None:
 	    print "\nsyscall errors for %s:\n\n" % (for_comm),
diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py
index 11e70a388d4..0f5cf437b60 100644
--- a/tools/perf/scripts/python/futex-contention.py
+++ b/tools/perf/scripts/python/futex-contention.py
@@ -21,7 +21,7 @@ thread_blocktime = {}
 lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time
 process_names = {} # long-lived pid-to-execname mapping
 
-def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm,
+def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, callchain,
 			      nr, uaddr, op, val, utime, uaddr2, val3):
 	cmd = op & FUTEX_CMD_MASK
 	if cmd != FUTEX_WAIT:
@@ -31,7 +31,7 @@ def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm,
 	thread_thislock[tid] = uaddr
 	thread_blocktime[tid] = nsecs(s, ns)
 
-def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm,
+def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, callchain,
 			     nr, ret):
 	if thread_blocktime.has_key(tid):
 		elapsed = nsecs(s, ns) - thread_blocktime[tid]
diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py
index b5740599aab..0b6ce8c253e 100755
--- a/tools/perf/scripts/python/net_dropmonitor.py
+++ b/tools/perf/scripts/python/net_dropmonitor.py
@@ -66,7 +66,7 @@ def trace_end():
 	print_drop_table()
 
 # called from perf, when it finds a correspoinding event
-def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain,
 		   skbaddr, location, protocol):
 	slocation = str(location)
 	try:
diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py
index 9aa0a32972e..4d21ef2d601 100644
--- a/tools/perf/scripts/python/netdev-times.py
+++ b/tools/perf/scripts/python/netdev-times.py
@@ -224,75 +224,75 @@ def trace_end():
 			(len(rx_skb_list), of_count_rx_skb_list)
 
 # called from perf, when it finds a correspoinding event
-def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec):
+def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
 	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
 		return
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
 	all_event_list.append(event_info)
 
-def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec):
+def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
 	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
 		return
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
 	all_event_list.append(event_info)
 
-def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec):
+def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, callchain, vec):
 	if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX":
 		return
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec)
 	all_event_list.append(event_info)
 
 def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm,
-			irq, irq_name):
+			callchain, irq, irq_name):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
 			irq, irq_name)
 	all_event_list.append(event_info)
 
-def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret):
+def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, irq, ret):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret)
 	all_event_list.append(event_info)
 
-def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name):
+def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, dev_name):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
 			napi, dev_name)
 	all_event_list.append(event_info)
 
-def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr,
 			skblen, dev_name):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
 			skbaddr, skblen, dev_name)
 	all_event_list.append(event_info)
 
-def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr,
+def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr,
 			skblen, dev_name):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
 			skbaddr, skblen, dev_name)
 	all_event_list.append(event_info)
 
-def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm,
+def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, callchain,
 			skbaddr, skblen, dev_name):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
 			skbaddr, skblen, dev_name)
 	all_event_list.append(event_info)
 
-def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm,
+def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, callchain,
 			skbaddr, skblen, rc, dev_name):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
 			skbaddr, skblen, rc ,dev_name)
 	all_event_list.append(event_info)
 
-def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain,
 			skbaddr, protocol, location):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
 			skbaddr, protocol, location)
 	all_event_list.append(event_info)
 
-def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr):
+def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
 			skbaddr)
 	all_event_list.append(event_info)
 
-def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm,
+def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, callchain,
 	skbaddr, skblen):
 	event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm,
 			skbaddr, skblen)
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index 74d55ec08ae..de66cb3b72c 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -369,93 +369,92 @@ def trace_end():
 
 def sched__sched_stat_runtime(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, runtime, vruntime):
+	common_callchain, comm, pid, runtime, vruntime):
 	pass
 
 def sched__sched_stat_iowait(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, delay):
+	common_callchain, comm, pid, delay):
 	pass
 
 def sched__sched_stat_sleep(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, delay):
+	common_callchain, comm, pid, delay):
 	pass
 
 def sched__sched_stat_wait(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, delay):
+	common_callchain, comm, pid, delay):
 	pass
 
 def sched__sched_process_fork(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	parent_comm, parent_pid, child_comm, child_pid):
+	common_callchain, parent_comm, parent_pid, child_comm, child_pid):
 	pass
 
 def sched__sched_process_wait(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, prio):
+	common_callchain, comm, pid, prio):
 	pass
 
 def sched__sched_process_exit(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, prio):
+	common_callchain, comm, pid, prio):
 	pass
 
 def sched__sched_process_free(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, prio):
+	common_callchain, comm, pid, prio):
 	pass
 
 def sched__sched_migrate_task(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, prio, orig_cpu,
+	common_callchain, comm, pid, prio, orig_cpu,
 	dest_cpu):
 	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
-				common_pid, common_comm)
+				common_pid, common_comm, common_callchain)
 	parser.migrate(headers, pid, prio, orig_cpu, dest_cpu)
 
 def sched__sched_switch(event_name, context, common_cpu,
-	common_secs, common_nsecs, common_pid, common_comm,
+	common_secs, common_nsecs, common_pid, common_comm, common_callchain,
 	prev_comm, prev_pid, prev_prio, prev_state,
 	next_comm, next_pid, next_prio):
 
 	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
-				common_pid, common_comm)
+				common_pid, common_comm, common_callchain)
 	parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state,
 			 next_comm, next_pid, next_prio)
 
 def sched__sched_wakeup_new(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, prio, success,
+	common_callchain, comm, pid, prio, success,
 	target_cpu):
 	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
-				common_pid, common_comm)
+				common_pid, common_comm, common_callchain)
 	parser.wake_up(headers, comm, pid, success, target_cpu, 1)
 
 def sched__sched_wakeup(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, prio, success,
+	common_callchain, comm, pid, prio, success,
 	target_cpu):
 	headers = EventHeaders(common_cpu, common_secs, common_nsecs,
-				common_pid, common_comm)
+				common_pid, common_comm, common_callchain)
 	parser.wake_up(headers, comm, pid, success, target_cpu, 0)
 
 def sched__sched_wait_task(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid, prio):
+	common_callchain, comm, pid, prio):
 	pass
 
 def sched__sched_kthread_stop_ret(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	ret):
+	common_callchain, ret):
 	pass
 
 def sched__sched_kthread_stop(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	comm, pid):
+	common_callchain, comm, pid):
 	pass
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
 	pass
diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
index 42c267e292f..61621b93aff 100644
--- a/tools/perf/scripts/python/sctop.py
+++ b/tools/perf/scripts/python/sctop.py
@@ -44,7 +44,7 @@ def trace_begin():
 
 def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	id, args):
+	common_callchain, id, args):
 	if for_comm is not None:
 		if common_comm != for_comm:
 			return
@@ -53,6 +53,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	except TypeError:
 		syscalls[id] = 1
 
+def syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+	raw_syscalls__sys_enter(**locals())
+
 def print_syscall_totals(interval):
 	while 1:
 		clear_term()
diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py
index c64d1c55d74..daf314cc5dd 100644
--- a/tools/perf/scripts/python/syscall-counts-by-pid.py
+++ b/tools/perf/scripts/python/syscall-counts-by-pid.py
@@ -38,7 +38,7 @@ def trace_end():
 
 def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	id, args):
+	common_callchain, id, args):
 
 	if (for_comm and common_comm != for_comm) or \
 	   (for_pid  and common_pid  != for_pid ):
@@ -48,6 +48,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	except TypeError:
 		syscalls[common_comm][common_pid][id] = 1
 
+def syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+	raw_syscalls__sys_enter(**locals())
+
 def print_syscall_totals():
     if for_comm is not None:
 	    print "\nsyscall events for %s:\n\n" % (for_comm),
diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py
index b435d3f188e..e66a7730aeb 100644
--- a/tools/perf/scripts/python/syscall-counts.py
+++ b/tools/perf/scripts/python/syscall-counts.py
@@ -35,7 +35,7 @@ def trace_end():
 
 def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	common_secs, common_nsecs, common_pid, common_comm,
-	id, args):
+	common_callchain, id, args):
 	if for_comm is not None:
 		if common_comm != for_comm:
 			return
@@ -44,6 +44,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	except TypeError:
 		syscalls[id] = 1
 
+def syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+	raw_syscalls__sys_enter(**locals())
+
 def print_syscall_totals():
     if for_comm is not None:
 	    print "\nsyscall events for %s:\n\n" % (for_comm),
diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record
index e9bd6391f2a..f710b92ccff 100644
--- a/tools/perf/tests/attr/base-record
+++ b/tools/perf/tests/attr/base-record
@@ -1,7 +1,8 @@
 [event]
 fd=1
 group_fd=-1
-flags=0
+# 0 or PERF_FLAG_FD_CLOEXEC flag
+flags=0|8
 cpu=*
 type=0|1
 size=96
diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat
index 91cd48b399f..dc3ada2470c 100644
--- a/tools/perf/tests/attr/base-stat
+++ b/tools/perf/tests/attr/base-stat
@@ -1,7 +1,8 @@
 [event]
 fd=1
 group_fd=-1
-flags=0
+# 0 or PERF_FLAG_FD_CLOEXEC flag
+flags=0|8
 cpu=*
 type=0
 size=96
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index aba09548919..a02b035fd5a 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -25,6 +25,7 @@
 #include "tests.h"
 #include "debug.h"
 #include "perf.h"
+#include "cloexec.h"
 
 static int fd1;
 static int fd2;
@@ -78,7 +79,8 @@ static int bp_event(void *fn, int setup_signal)
 	pe.exclude_kernel = 1;
 	pe.exclude_hv = 1;
 
-	fd = sys_perf_event_open(&pe, 0, -1, -1, 0);
+	fd = sys_perf_event_open(&pe, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
 	if (fd < 0) {
 		pr_debug("failed opening event %llx\n", pe.config);
 		return TEST_FAIL;
diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c
index 44ac8217970..e7653772449 100644
--- a/tools/perf/tests/bp_signal_overflow.c
+++ b/tools/perf/tests/bp_signal_overflow.c
@@ -24,6 +24,7 @@
 #include "tests.h"
 #include "debug.h"
 #include "perf.h"
+#include "cloexec.h"
 
 static int overflows;
 
@@ -91,7 +92,8 @@ int test__bp_signal_overflow(void)
 	pe.exclude_kernel = 1;
 	pe.exclude_hv = 1;
 
-	fd = sys_perf_event_open(&pe, 0, -1, -1, 0);
+	fd = sys_perf_event_open(&pe, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
 	if (fd < 0) {
 		pr_debug("failed opening event %llx\n", pe.config);
 		return TEST_FAIL;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 831f52cae19..6f8b01bc603 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -3,6 +3,8 @@
  *
  * Builtin regression testing command: ever growing number of sanity tests
  */
+#include <unistd.h>
+#include <string.h>
 #include "builtin.h"
 #include "intlist.h"
 #include "tests.h"
@@ -50,10 +52,18 @@ static struct test {
 		.func = test__pmu,
 	},
 	{
-		.desc = "Test dso data interface",
+		.desc = "Test dso data read",
 		.func = test__dso_data,
 	},
 	{
+		.desc = "Test dso data cache",
+		.func = test__dso_data_cache,
+	},
+	{
+		.desc = "Test dso data reopen",
+		.func = test__dso_data_reopen,
+	},
+	{
 		.desc = "roundtrip evsel->name check",
 		.func = test__perf_evsel__roundtrip_name_test,
 	},
@@ -140,6 +150,10 @@ static struct test {
 		.func = test__hists_output,
 	},
 	{
+		.desc = "Test cumulation of child hist entries",
+		.func = test__hists_cumulate,
+	},
+	{
 		.func = NULL,
 	},
 };
@@ -168,6 +182,34 @@ static bool perf_test__matches(int curr, int argc, const char *argv[])
 	return false;
 }
 
+static int run_test(struct test *test)
+{
+	int status, err = -1, child = fork();
+
+	if (child < 0) {
+		pr_err("failed to fork test: %s\n", strerror(errno));
+		return -1;
+	}
+
+	if (!child) {
+		pr_debug("test child forked, pid %d\n", getpid());
+		err = test->func();
+		exit(err);
+	}
+
+	wait(&status);
+
+	if (WIFEXITED(status)) {
+		err = WEXITSTATUS(status);
+		pr_debug("test child finished with %d\n", err);
+	} else if (WIFSIGNALED(status)) {
+		err = -1;
+		pr_debug("test child interrupted\n");
+	}
+
+	return err;
+}
+
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
 	int i = 0;
@@ -196,7 +238,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		}
 
 		pr_debug("\n--- start ---\n");
-		err = tests[curr].func();
+		err = run_test(&tests[curr]);
 		pr_debug("---- end ----\n%s:", tests[curr].desc);
 
 		switch (err) {
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 3e6cb171e3d..caaf37f079b 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -1,22 +1,28 @@
-#include "util.h"
-
 #include <stdlib.h>
 #include <linux/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <string.h>
-
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <api/fs/fs.h>
+#include "util.h"
 #include "machine.h"
 #include "symbol.h"
 #include "tests.h"
+#include "debug.h"
 
 static char *test_file(int size)
 {
-	static char buf_templ[] = "/tmp/test-XXXXXX";
+#define TEMPL "/tmp/perf-test-XXXXXX"
+	static char buf_templ[sizeof(TEMPL)];
 	char *templ = buf_templ;
 	int fd, i;
 	unsigned char *buf;
 
+	strcpy(buf_templ, TEMPL);
+#undef TEMPL
+
 	fd = mkstemp(templ);
 	if (fd < 0) {
 		perror("mkstemp failed");
@@ -150,3 +156,204 @@ int test__dso_data(void)
 	unlink(file);
 	return 0;
 }
+
+static long open_files_cnt(void)
+{
+	char path[PATH_MAX];
+	struct dirent *dent;
+	DIR *dir;
+	long nr = 0;
+
+	scnprintf(path, PATH_MAX, "%s/self/fd", procfs__mountpoint());
+	pr_debug("fd path: %s\n", path);
+
+	dir = opendir(path);
+	TEST_ASSERT_VAL("failed to open fd directory", dir);
+
+	while ((dent = readdir(dir)) != NULL) {
+		if (!strcmp(dent->d_name, ".") ||
+		    !strcmp(dent->d_name, ".."))
+			continue;
+
+		nr++;
+	}
+
+	closedir(dir);
+	return nr - 1;
+}
+
+static struct dso **dsos;
+
+static int dsos__create(int cnt, int size)
+{
+	int i;
+
+	dsos = malloc(sizeof(dsos) * cnt);
+	TEST_ASSERT_VAL("failed to alloc dsos array", dsos);
+
+	for (i = 0; i < cnt; i++) {
+		char *file;
+
+		file = test_file(size);
+		TEST_ASSERT_VAL("failed to get dso file", file);
+
+		dsos[i] = dso__new(file);
+		TEST_ASSERT_VAL("failed to get dso", dsos[i]);
+	}
+
+	return 0;
+}
+
+static void dsos__delete(int cnt)
+{
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		struct dso *dso = dsos[i];
+
+		unlink(dso->name);
+		dso__delete(dso);
+	}
+
+	free(dsos);
+}
+
+static int set_fd_limit(int n)
+{
+	struct rlimit rlim;
+
+	if (getrlimit(RLIMIT_NOFILE, &rlim))
+		return -1;
+
+	pr_debug("file limit %ld, new %d\n", (long) rlim.rlim_cur, n);
+
+	rlim.rlim_cur = n;
+	return setrlimit(RLIMIT_NOFILE, &rlim);
+}
+
+int test__dso_data_cache(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int dso_cnt, limit, i, fd;
+
+	memset(&machine, 0, sizeof(machine));
+
+	/* set as system limit */
+	limit = nr * 4;
+	TEST_ASSERT_VAL("failed to set file limit", !set_fd_limit(limit));
+
+	/* and this is now our dso open FDs limit + 1 extra */
+	dso_cnt = limit / 2 + 1;
+	TEST_ASSERT_VAL("failed to create dsos\n",
+		!dsos__create(dso_cnt, TEST_FILE_SIZE));
+
+	for (i = 0; i < (dso_cnt - 1); i++) {
+		struct dso *dso = dsos[i];
+
+		/*
+		 * Open dsos via dso__data_fd or dso__data_read_offset.
+		 * Both opens the data file and keep it open.
+		 */
+		if (i % 2) {
+			fd = dso__data_fd(dso, &machine);
+			TEST_ASSERT_VAL("failed to get fd", fd > 0);
+		} else {
+			#define BUFSIZE 10
+			u8 buf[BUFSIZE];
+			ssize_t n;
+
+			n = dso__data_read_offset(dso, &machine, 0, buf, BUFSIZE);
+			TEST_ASSERT_VAL("failed to read dso", n == BUFSIZE);
+		}
+	}
+
+	/* open +1 dso over the allowed limit */
+	fd = dso__data_fd(dsos[i], &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* should force the first one to be closed */
+	TEST_ASSERT_VAL("failed to close dsos[0]", dsos[0]->data.fd == -1);
+
+	/* cleanup everything */
+	dsos__delete(dso_cnt);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
+
+int test__dso_data_reopen(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int fd, fd_extra;
+
+#define dso_0 (dsos[0])
+#define dso_1 (dsos[1])
+#define dso_2 (dsos[2])
+
+	memset(&machine, 0, sizeof(machine));
+
+	/*
+	 * Test scenario:
+	 * - create 3 dso objects
+	 * - set process file descriptor limit to current
+	 *   files count + 3
+	 * - test that the first dso gets closed when we
+	 *   reach the files count limit
+	 */
+
+	/* Make sure we are able to open 3 fds anyway */
+	TEST_ASSERT_VAL("failed to set file limit",
+			!set_fd_limit((nr + 3)));
+
+	TEST_ASSERT_VAL("failed to create dsos\n", !dsos__create(3, TEST_FILE_SIZE));
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* open dso_1 */
+	fd = dso__data_fd(dso_1, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * open extra file descriptor and we just
+	 * reached the files count limit
+	 */
+	fd_extra = open("/dev/null", O_RDONLY);
+	TEST_ASSERT_VAL("failed to open extra fd", fd_extra > 0);
+
+	/* open dso_2 */
+	fd = dso__data_fd(dso_2, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_0 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_0", dso_0->data.fd == -1);
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_1 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_1", dso_1->data.fd == -1);
+
+	/* cleanup everything */
+	close(fd_extra);
+	dsos__delete(3);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 108f0cd49f4..96adb730b74 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -15,7 +15,7 @@ static int mmap_handler(struct perf_tool *tool __maybe_unused,
 			struct perf_sample *sample __maybe_unused,
 			struct machine *machine)
 {
-	return machine__process_mmap_event(machine, event, NULL);
+	return machine__process_mmap2_event(machine, event, NULL);
 }
 
 static int init_live_machine(struct machine *machine)
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 465cdbc345c..b8d8341b383 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -2,6 +2,7 @@
 #include "evsel.h"
 #include "parse-events.h"
 #include "tests.h"
+#include "debug.h"
 
 static int perf_evsel__roundtrip_cache_name_test(void)
 {
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 35d7fdb2328..52162425c96 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -1,6 +1,7 @@
 #include <traceevent/event-parse.h>
 #include "evsel.h"
 #include "tests.h"
+#include "debug.h"
 
 static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 				  int size, bool should_be_signed)
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index e4e01aadc3b..a62c0913451 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -12,9 +12,9 @@ static struct {
 	u32 pid;
 	const char *comm;
 } fake_threads[] = {
-	{ 100, "perf" },
-	{ 200, "perf" },
-	{ 300, "bash" },
+	{ FAKE_PID_PERF1, "perf" },
+	{ FAKE_PID_PERF2, "perf" },
+	{ FAKE_PID_BASH,  "bash" },
 };
 
 static struct {
@@ -22,15 +22,15 @@ static struct {
 	u64 start;
 	const char *filename;
 } fake_mmap_info[] = {
-	{ 100, 0x40000, "perf" },
-	{ 100, 0x50000, "libc" },
-	{ 100, 0xf0000, "[kernel]" },
-	{ 200, 0x40000, "perf" },
-	{ 200, 0x50000, "libc" },
-	{ 200, 0xf0000, "[kernel]" },
-	{ 300, 0x40000, "bash" },
-	{ 300, 0x50000, "libc" },
-	{ 300, 0xf0000, "[kernel]" },
+	{ FAKE_PID_PERF1, FAKE_MAP_PERF,   "perf" },
+	{ FAKE_PID_PERF1, FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_PERF1, FAKE_MAP_KERNEL, "[kernel]" },
+	{ FAKE_PID_PERF2, FAKE_MAP_PERF,   "perf" },
+	{ FAKE_PID_PERF2, FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_PERF2, FAKE_MAP_KERNEL, "[kernel]" },
+	{ FAKE_PID_BASH,  FAKE_MAP_BASH,   "bash" },
+	{ FAKE_PID_BASH,  FAKE_MAP_LIBC,   "libc" },
+	{ FAKE_PID_BASH,  FAKE_MAP_KERNEL, "[kernel]" },
 };
 
 struct fake_sym {
@@ -40,27 +40,30 @@ struct fake_sym {
 };
 
 static struct fake_sym perf_syms[] = {
-	{ 700, 100, "main" },
-	{ 800, 100, "run_command" },
-	{ 900, 100, "cmd_record" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "run_command" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "cmd_record" },
 };
 
 static struct fake_sym bash_syms[] = {
-	{ 700, 100, "main" },
-	{ 800, 100, "xmalloc" },
-	{ 900, 100, "xfree" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "main" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "xmalloc" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "xfree" },
 };
 
 static struct fake_sym libc_syms[] = {
 	{ 700, 100, "malloc" },
 	{ 800, 100, "free" },
 	{ 900, 100, "realloc" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "malloc" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "free" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "realloc" },
 };
 
 static struct fake_sym kernel_syms[] = {
-	{ 700, 100, "schedule" },
-	{ 800, 100, "page_fault" },
-	{ 900, 100, "sys_perf_event_open" },
+	{ FAKE_SYM_OFFSET1, FAKE_SYM_LENGTH, "schedule" },
+	{ FAKE_SYM_OFFSET2, FAKE_SYM_LENGTH, "page_fault" },
+	{ FAKE_SYM_OFFSET3, FAKE_SYM_LENGTH, "sys_perf_event_open" },
 };
 
 static struct {
@@ -102,7 +105,7 @@ struct machine *setup_fake_machine(struct machines *machines)
 				.pid = fake_mmap_info[i].pid,
 				.tid = fake_mmap_info[i].pid,
 				.start = fake_mmap_info[i].start,
-				.len = 0x1000ULL,
+				.len = FAKE_MAP_LENGTH,
 				.pgoff = 0ULL,
 			},
 		};
@@ -193,10 +196,11 @@ void print_hists_out(struct hists *hists)
 		he = rb_entry(node, struct hist_entry, rb_node);
 
 		if (!he->filtered) {
-			pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"\n",
+			pr_info("%2d: entry: %8s:%5d [%-8s] %20s: period = %"PRIu64"/%"PRIu64"\n",
 				i, thread__comm_str(he->thread), he->thread->tid,
 				he->ms.map->dso->short_name,
-				he->ms.sym->name, he->stat.period);
+				he->ms.sym->name, he->stat.period,
+				he->stat_acc ? he->stat_acc->period : 0);
 		}
 
 		i++;
diff --git a/tools/perf/tests/hists_common.h b/tools/perf/tests/hists_common.h
index 1415ae69d7b..888254e8665 100644
--- a/tools/perf/tests/hists_common.h
+++ b/tools/perf/tests/hists_common.h
@@ -4,6 +4,34 @@
 struct machine;
 struct machines;
 
+#define FAKE_PID_PERF1  100
+#define FAKE_PID_PERF2  200
+#define FAKE_PID_BASH   300
+
+#define FAKE_MAP_PERF    0x400000
+#define FAKE_MAP_BASH    0x400000
+#define FAKE_MAP_LIBC    0x500000
+#define FAKE_MAP_KERNEL  0xf00000
+#define FAKE_MAP_LENGTH  0x100000
+
+#define FAKE_SYM_OFFSET1  700
+#define FAKE_SYM_OFFSET2  800
+#define FAKE_SYM_OFFSET3  900
+#define FAKE_SYM_LENGTH   100
+
+#define FAKE_IP_PERF_MAIN  FAKE_MAP_PERF + FAKE_SYM_OFFSET1
+#define FAKE_IP_PERF_RUN_COMMAND  FAKE_MAP_PERF + FAKE_SYM_OFFSET2
+#define FAKE_IP_PERF_CMD_RECORD  FAKE_MAP_PERF + FAKE_SYM_OFFSET3
+#define FAKE_IP_BASH_MAIN  FAKE_MAP_BASH + FAKE_SYM_OFFSET1
+#define FAKE_IP_BASH_XMALLOC  FAKE_MAP_BASH + FAKE_SYM_OFFSET2
+#define FAKE_IP_BASH_XFREE  FAKE_MAP_BASH + FAKE_SYM_OFFSET3
+#define FAKE_IP_LIBC_MALLOC  FAKE_MAP_LIBC + FAKE_SYM_OFFSET1
+#define FAKE_IP_LIBC_FREE  FAKE_MAP_LIBC + FAKE_SYM_OFFSET2
+#define FAKE_IP_LIBC_REALLOC  FAKE_MAP_LIBC + FAKE_SYM_OFFSET3
+#define FAKE_IP_KERNEL_SCHEDULE  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET1
+#define FAKE_IP_KERNEL_PAGE_FAULT  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET2
+#define FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN  FAKE_MAP_KERNEL + FAKE_SYM_OFFSET3
+
 /*
  * The setup_fake_machine() provides a test environment which consists
  * of 3 processes that have 3 mappings and in turn, have 3 symbols
@@ -13,7 +41,7 @@ struct machines;
  * .............  .............  ...................
  *    perf:  100           perf  main
  *    perf:  100           perf  run_command
- *    perf:  100           perf  comd_record
+ *    perf:  100           perf  cmd_record
  *    perf:  100           libc  malloc
  *    perf:  100           libc  free
  *    perf:  100           libc  realloc
@@ -22,7 +50,7 @@ struct machines;
  *    perf:  100       [kernel]  sys_perf_event_open
  *    perf:  200           perf  main
  *    perf:  200           perf  run_command
- *    perf:  200           perf  comd_record
+ *    perf:  200           perf  cmd_record
  *    perf:  200           libc  malloc
  *    perf:  200           libc  free
  *    perf:  200           libc  realloc
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
new file mode 100644
index 00000000000..0ac240db2e2
--- /dev/null
+++ b/tools/perf/tests/hists_cumulate.c
@@ -0,0 +1,726 @@
+#include "perf.h"
+#include "util/debug.h"
+#include "util/symbol.h"
+#include "util/sort.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/machine.h"
+#include "util/thread.h"
+#include "util/parse-events.h"
+#include "tests/tests.h"
+#include "tests/hists_common.h"
+
+struct sample {
+	u32 pid;
+	u64 ip;
+	struct thread *thread;
+	struct map *map;
+	struct symbol *sym;
+};
+
+/* For the numbers, see hists_common.c */
+static struct sample fake_samples[] = {
+	/* perf [kernel] schedule() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [perf]   cmd_record() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, },
+	/* perf [libc]   malloc() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
+	/* perf [libc]   free() */
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, },
+	/* perf [perf]   main() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
+	/* perf [kernel] page_fault() */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+	/* bash [bash]   main() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
+	/* bash [bash]   xmalloc() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
+	/* bash [kernel] page_fault() */
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
+};
+
+/*
+ * Will be casted to struct ip_callchain which has all 64 bit entries
+ * of nr and ips[].
+ */
+static u64 fake_callchains[][10] = {
+	/*   schedule => run_command => main */
+	{ 3, FAKE_IP_KERNEL_SCHEDULE, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
+	/*   main  */
+	{ 1, FAKE_IP_PERF_MAIN, },
+	/*   cmd_record => run_command => main */
+	{ 3, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
+	/*   malloc => cmd_record => run_command => main */
+	{ 4, FAKE_IP_LIBC_MALLOC, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND,
+	     FAKE_IP_PERF_MAIN, },
+	/*   free => cmd_record => run_command => main */
+	{ 4, FAKE_IP_LIBC_FREE, FAKE_IP_PERF_CMD_RECORD, FAKE_IP_PERF_RUN_COMMAND,
+	     FAKE_IP_PERF_MAIN, },
+	/*   main */
+	{ 1, FAKE_IP_PERF_MAIN, },
+	/*   page_fault => sys_perf_event_open => run_command => main */
+	{ 4, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN,
+	     FAKE_IP_PERF_RUN_COMMAND, FAKE_IP_PERF_MAIN, },
+	/*   main */
+	{ 1, FAKE_IP_BASH_MAIN, },
+	/*   xmalloc => malloc => xmalloc => malloc => xmalloc => main */
+	{ 6, FAKE_IP_BASH_XMALLOC, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC,
+	     FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_XMALLOC, FAKE_IP_BASH_MAIN, },
+	/*   page_fault => malloc => main */
+	{ 3, FAKE_IP_KERNEL_PAGE_FAULT, FAKE_IP_LIBC_MALLOC, FAKE_IP_BASH_MAIN, },
+};
+
+static int add_hist_entries(struct hists *hists, struct machine *machine)
+{
+	struct addr_location al;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	struct perf_sample sample = { .period = 1000, };
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(fake_samples); i++) {
+		const union perf_event event = {
+			.header = {
+				.misc = PERF_RECORD_MISC_USER,
+			},
+		};
+		struct hist_entry_iter iter = {
+			.hide_unresolved = false,
+		};
+
+		if (symbol_conf.cumulate_callchain)
+			iter.ops = &hist_iter_cumulative;
+		else
+			iter.ops = &hist_iter_normal;
+
+		sample.pid = fake_samples[i].pid;
+		sample.tid = fake_samples[i].pid;
+		sample.ip = fake_samples[i].ip;
+		sample.callchain = (struct ip_callchain *)fake_callchains[i];
+
+		if (perf_event__preprocess_sample(&event, machine, &al,
+						  &sample) < 0)
+			goto out;
+
+		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+					 PERF_MAX_STACK_DEPTH, NULL) < 0)
+			goto out;
+
+		fake_samples[i].thread = al.thread;
+		fake_samples[i].map = al.map;
+		fake_samples[i].sym = al.sym;
+	}
+
+	return TEST_OK;
+
+out:
+	pr_debug("Not enough memory for adding a hist entry\n");
+	return TEST_FAIL;
+}
+
+static void del_hist_entries(struct hists *hists)
+{
+	struct hist_entry *he;
+	struct rb_root *root_in;
+	struct rb_root *root_out;
+	struct rb_node *node;
+
+	if (sort__need_collapse)
+		root_in = &hists->entries_collapsed;
+	else
+		root_in = hists->entries_in;
+
+	root_out = &hists->entries;
+
+	while (!RB_EMPTY_ROOT(root_out)) {
+		node = rb_first(root_out);
+
+		he = rb_entry(node, struct hist_entry, rb_node);
+		rb_erase(node, root_out);
+		rb_erase(&he->rb_node_in, root_in);
+		hist_entry__free(he);
+	}
+}
+
+typedef int (*test_fn_t)(struct perf_evsel *, struct machine *);
+
+#define COMM(he)  (thread__comm_str(he->thread))
+#define DSO(he)   (he->ms.map->dso->short_name)
+#define SYM(he)   (he->ms.sym->name)
+#define CPU(he)   (he->cpu)
+#define PID(he)   (he->thread->tid)
+#define DEPTH(he) (he->callchain->max_depth)
+#define CDSO(cl)  (cl->ms.map->dso->short_name)
+#define CSYM(cl)  (cl->ms.sym->name)
+
+struct result {
+	u64 children;
+	u64 self;
+	const char *comm;
+	const char *dso;
+	const char *sym;
+};
+
+struct callchain_result {
+	u64 nr;
+	struct {
+		const char *dso;
+		const char *sym;
+	} node[10];
+};
+
+static int do_test(struct hists *hists, struct result *expected, size_t nr_expected,
+		   struct callchain_result *expected_callchain, size_t nr_callchain)
+{
+	char buf[32];
+	size_t i, c;
+	struct hist_entry *he;
+	struct rb_root *root;
+	struct rb_node *node;
+	struct callchain_node *cnode;
+	struct callchain_list *clist;
+
+	/*
+	 * adding and deleting hist entries must be done outside of this
+	 * function since TEST_ASSERT_VAL() returns in case of failure.
+	 */
+	hists__collapse_resort(hists, NULL);
+	hists__output_resort(hists);
+
+	if (verbose > 2) {
+		pr_info("use callchain: %d, cumulate callchain: %d\n",
+			symbol_conf.use_callchain,
+			symbol_conf.cumulate_callchain);
+		print_hists_out(hists);
+	}
+
+	root = &hists->entries;
+	for (node = rb_first(root), i = 0;
+	     node && (he = rb_entry(node, struct hist_entry, rb_node));
+	     node = rb_next(node), i++) {
+		scnprintf(buf, sizeof(buf), "Invalid hist entry #%zd", i);
+
+		TEST_ASSERT_VAL("Incorrect number of hist entry",
+				i < nr_expected);
+		TEST_ASSERT_VAL(buf, he->stat.period == expected[i].self &&
+				!strcmp(COMM(he), expected[i].comm) &&
+				!strcmp(DSO(he), expected[i].dso) &&
+				!strcmp(SYM(he), expected[i].sym));
+
+		if (symbol_conf.cumulate_callchain)
+			TEST_ASSERT_VAL(buf, he->stat_acc->period == expected[i].children);
+
+		if (!symbol_conf.use_callchain)
+			continue;
+
+		/* check callchain entries */
+		root = &he->callchain->node.rb_root;
+		cnode = rb_entry(rb_first(root), struct callchain_node, rb_node);
+
+		c = 0;
+		list_for_each_entry(clist, &cnode->val, list) {
+			scnprintf(buf, sizeof(buf), "Invalid callchain entry #%zd/%zd", i, c);
+
+			TEST_ASSERT_VAL("Incorrect number of callchain entry",
+					c < expected_callchain[i].nr);
+			TEST_ASSERT_VAL(buf,
+				!strcmp(CDSO(clist), expected_callchain[i].node[c].dso) &&
+				!strcmp(CSYM(clist), expected_callchain[i].node[c].sym));
+			c++;
+		}
+		/* TODO: handle multiple child nodes properly */
+		TEST_ASSERT_VAL("Incorrect number of callchain entry",
+				c <= expected_callchain[i].nr);
+	}
+	TEST_ASSERT_VAL("Incorrect number of hist entry",
+			i == nr_expected);
+	TEST_ASSERT_VAL("Incorrect number of callchain entry",
+			!symbol_conf.use_callchain || nr_expected == nr_callchain);
+	return 0;
+}
+
+/* NO callchain + NO children */
+static int test1(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	/*
+	 * expected output:
+	 *
+	 * Overhead  Command  Shared Object          Symbol
+	 * ========  =======  =============  ==============
+	 *   20.00%     perf  perf           [.] main
+	 *   10.00%     bash  [kernel]       [k] page_fault
+	 *   10.00%     bash  bash           [.] main
+	 *   10.00%     bash  bash           [.] xmalloc
+	 *   10.00%     perf  [kernel]       [k] page_fault
+	 *   10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%     perf  libc           [.] free
+	 *   10.00%     perf  libc           [.] malloc
+	 *   10.00%     perf  perf           [.] cmd_record
+	 */
+	struct result expected[] = {
+		{ 0, 2000, "perf", "perf",     "main" },
+		{ 0, 1000, "bash", "[kernel]", "page_fault" },
+		{ 0, 1000, "bash", "bash",     "main" },
+		{ 0, 1000, "bash", "bash",     "xmalloc" },
+		{ 0, 1000, "perf", "[kernel]", "page_fault" },
+		{ 0, 1000, "perf", "[kernel]", "schedule" },
+		{ 0, 1000, "perf", "libc",     "free" },
+		{ 0, 1000, "perf", "libc",     "malloc" },
+		{ 0, 1000, "perf", "perf",     "cmd_record" },
+	};
+
+	symbol_conf.use_callchain = false;
+	symbol_conf.cumulate_callchain = false;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* callcain + NO children */
+static int test2(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	/*
+	 * expected output:
+	 *
+	 * Overhead  Command  Shared Object          Symbol
+	 * ========  =======  =============  ==============
+	 *   20.00%     perf  perf           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   10.00%     bash  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  malloc
+	 *                  main
+	 *
+	 *   10.00%     bash  bash           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   10.00%     bash  bash           [.] xmalloc
+	 *              |
+	 *              --- xmalloc
+	 *                  malloc
+	 *                  xmalloc     <--- NOTE: there's a cycle
+	 *                  malloc
+	 *                  xmalloc
+	 *                  main
+	 *
+	 *   10.00%     perf  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  sys_perf_event_open
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  [kernel]       [k] schedule
+	 *              |
+	 *              --- schedule
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  libc           [.] free
+	 *              |
+	 *              --- free
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  libc           [.] malloc
+	 *              |
+	 *              --- malloc
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     perf  perf           [.] cmd_record
+	 *              |
+	 *              --- cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 */
+	struct result expected[] = {
+		{ 0, 2000, "perf", "perf",     "main" },
+		{ 0, 1000, "bash", "[kernel]", "page_fault" },
+		{ 0, 1000, "bash", "bash",     "main" },
+		{ 0, 1000, "bash", "bash",     "xmalloc" },
+		{ 0, 1000, "perf", "[kernel]", "page_fault" },
+		{ 0, 1000, "perf", "[kernel]", "schedule" },
+		{ 0, 1000, "perf", "libc",     "free" },
+		{ 0, 1000, "perf", "libc",     "malloc" },
+		{ 0, 1000, "perf", "perf",     "cmd_record" },
+	};
+	struct callchain_result expected_callchain[] = {
+		{
+			1, {	{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "page_fault" },
+				{ "libc",     "malloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			1, {	{ "bash",     "main" }, },
+		},
+		{
+			6, {	{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			4, {	{ "[kernel]", "page_fault" },
+				{ "[kernel]", "sys_perf_event_open" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "schedule" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "free" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "malloc" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+	};
+
+	symbol_conf.use_callchain = true;
+	symbol_conf.cumulate_callchain = false;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected),
+		      expected_callchain, ARRAY_SIZE(expected_callchain));
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* NO callchain + children */
+static int test3(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	/*
+	 * expected output:
+	 *
+	 * Children      Self  Command  Shared Object                   Symbol
+	 * ========  ========  =======  =============  =======================
+	 *   70.00%    20.00%     perf  perf           [.] main
+	 *   50.00%     0.00%     perf  perf           [.] run_command
+	 *   30.00%    10.00%     bash  bash           [.] main
+	 *   30.00%    10.00%     perf  perf           [.] cmd_record
+	 *   20.00%     0.00%     bash  libc           [.] malloc
+	 *   10.00%    10.00%     bash  [kernel]       [k] page_fault
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+	 *   10.00%    10.00%     perf  [kernel]       [k] page_fault
+	 *   10.00%    10.00%     perf  libc           [.] free
+	 *   10.00%    10.00%     perf  libc           [.] malloc
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
+	 */
+	struct result expected[] = {
+		{ 7000, 2000, "perf", "perf",     "main" },
+		{ 5000,    0, "perf", "perf",     "run_command" },
+		{ 3000, 1000, "bash", "bash",     "main" },
+		{ 3000, 1000, "perf", "perf",     "cmd_record" },
+		{ 2000,    0, "bash", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
+		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "libc",     "free" },
+		{ 1000, 1000, "perf", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
+	};
+
+	symbol_conf.use_callchain = false;
+	symbol_conf.cumulate_callchain = true;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected), NULL, 0);
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+/* callchain + children */
+static int test4(struct perf_evsel *evsel, struct machine *machine)
+{
+	int err;
+	struct hists *hists = &evsel->hists;
+	/*
+	 * expected output:
+	 *
+	 * Children      Self  Command  Shared Object                   Symbol
+	 * ========  ========  =======  =============  =======================
+	 *   70.00%    20.00%     perf  perf           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   50.00%     0.00%     perf  perf           [.] run_command
+	 *              |
+	 *              --- run_command
+	 *                  main
+	 *
+	 *   30.00%    10.00%     bash  bash           [.] main
+	 *              |
+	 *              --- main
+	 *
+	 *   30.00%    10.00%     perf  perf           [.] cmd_record
+	 *              |
+	 *              --- cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   20.00%     0.00%     bash  libc           [.] malloc
+	 *              |
+	 *              --- malloc
+	 *                 |
+	 *                 |--50.00%-- xmalloc
+	 *                 |           main
+	 *                  --50.00%-- main
+	 *
+	 *   10.00%    10.00%     bash  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  malloc
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  [kernel]       [k] schedule
+	 *              |
+	 *              --- schedule
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+	 *              |
+	 *              --- sys_perf_event_open
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  [kernel]       [k] page_fault
+	 *              |
+	 *              --- page_fault
+	 *                  sys_perf_event_open
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  libc           [.] free
+	 *              |
+	 *              --- free
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     perf  libc           [.] malloc
+	 *              |
+	 *              --- malloc
+	 *                  cmd_record
+	 *                  run_command
+	 *                  main
+	 *
+	 *   10.00%    10.00%     bash  bash           [.] xmalloc
+	 *              |
+	 *              --- xmalloc
+	 *                  malloc
+	 *                  xmalloc     <--- NOTE: there's a cycle
+	 *                  malloc
+	 *                  xmalloc
+	 *                  main
+	 *
+	 */
+	struct result expected[] = {
+		{ 7000, 2000, "perf", "perf",     "main" },
+		{ 5000,    0, "perf", "perf",     "run_command" },
+		{ 3000, 1000, "bash", "bash",     "main" },
+		{ 3000, 1000, "perf", "perf",     "cmd_record" },
+		{ 2000,    0, "bash", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "[kernel]", "schedule" },
+		{ 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+		{ 1000, 1000, "perf", "[kernel]", "page_fault" },
+		{ 1000, 1000, "perf", "libc",     "free" },
+		{ 1000, 1000, "perf", "libc",     "malloc" },
+		{ 1000, 1000, "bash", "bash",     "xmalloc" },
+	};
+	struct callchain_result expected_callchain[] = {
+		{
+			1, {	{ "perf",     "main" }, },
+		},
+		{
+			2, {	{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			1, {	{ "bash",     "main" }, },
+		},
+		{
+			3, {	{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" },
+				{ "bash",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "page_fault" },
+				{ "libc",     "malloc" },
+				{ "bash",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "schedule" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			3, {	{ "[kernel]", "sys_perf_event_open" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "[kernel]", "page_fault" },
+				{ "[kernel]", "sys_perf_event_open" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "free" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			4, {	{ "libc",     "malloc" },
+				{ "perf",     "cmd_record" },
+				{ "perf",     "run_command" },
+				{ "perf",     "main" }, },
+		},
+		{
+			6, {	{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "libc",     "malloc" },
+				{ "bash",     "xmalloc" },
+				{ "bash",     "main" }, },
+		},
+	};
+
+	symbol_conf.use_callchain = true;
+	symbol_conf.cumulate_callchain = true;
+
+	setup_sorting();
+	callchain_register_param(&callchain_param);
+
+	err = add_hist_entries(hists, machine);
+	if (err < 0)
+		goto out;
+
+	err = do_test(hists, expected, ARRAY_SIZE(expected),
+		      expected_callchain, ARRAY_SIZE(expected_callchain));
+
+out:
+	del_hist_entries(hists);
+	reset_output_field();
+	return err;
+}
+
+int test__hists_cumulate(void)
+{
+	int err = TEST_FAIL;
+	struct machines machines;
+	struct machine *machine;
+	struct perf_evsel *evsel;
+	struct perf_evlist *evlist = perf_evlist__new();
+	size_t i;
+	test_fn_t testcases[] = {
+		test1,
+		test2,
+		test3,
+		test4,
+	};
+
+	TEST_ASSERT_VAL("No memory", evlist);
+
+	err = parse_events(evlist, "cpu-clock");
+	if (err)
+		goto out;
+
+	machines__init(&machines);
+
+	/* setup threads/dso/map/symbols also */
+	machine = setup_fake_machine(&machines);
+	if (!machine)
+		goto out;
+
+	if (verbose > 1)
+		machine__fprintf(machine, stderr);
+
+	evsel = perf_evlist__first(evlist);
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+		err = testcases[i](evsel, machine);
+		if (err < 0)
+			break;
+	}
+
+out:
+	/* tear down everything */
+	perf_evlist__delete(evlist);
+	machines__exit(&machines);
+
+	return err;
+}
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index c5ba924a358..821f581fd93 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -21,33 +21,33 @@ struct sample {
 /* For the numbers, see hists_common.c */
 static struct sample fake_samples[] = {
 	/* perf [kernel] schedule() */
-	{ .pid = 100, .ip = 0xf0000 + 700, },
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
 	/* perf [perf]   main() */
-	{ .pid = 100, .ip = 0x40000 + 700, },
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
 	/* perf [libc]   malloc() */
-	{ .pid = 100, .ip = 0x50000 + 700, },
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
 	/* perf [perf]   main() */
-	{ .pid = 200, .ip = 0x40000 + 700, }, /* will be merged */
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, }, /* will be merged */
 	/* perf [perf]   cmd_record() */
-	{ .pid = 200, .ip = 0x40000 + 900, },
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, },
 	/* perf [kernel] page_fault() */
-	{ .pid = 200, .ip = 0xf0000 + 800, },
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 	/* bash [bash]   main() */
-	{ .pid = 300, .ip = 0x40000 + 700, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
 	/* bash [bash]   xmalloc() */
-	{ .pid = 300, .ip = 0x40000 + 800, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
 	/* bash [libc]   malloc() */
-	{ .pid = 300, .ip = 0x50000 + 700, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, },
 	/* bash [kernel] page_fault() */
-	{ .pid = 300, .ip = 0xf0000 + 800, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 };
 
-static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
+static int add_hist_entries(struct perf_evlist *evlist,
+			    struct machine *machine __maybe_unused)
 {
 	struct perf_evsel *evsel;
 	struct addr_location al;
-	struct hist_entry *he;
-	struct perf_sample sample = { .cpu = 0, };
+	struct perf_sample sample = { .period = 100, };
 	size_t i;
 
 	/*
@@ -62,6 +62,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 					.misc = PERF_RECORD_MISC_USER,
 				},
 			};
+			struct hist_entry_iter iter = {
+				.ops = &hist_iter_normal,
+				.hide_unresolved = false,
+			};
 
 			/* make sure it has no filter at first */
 			evsel->hists.thread_filter = NULL;
@@ -76,18 +80,13 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 							  &sample) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 100, 1, 0);
-			if (he == NULL)
+			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+						 PERF_MAX_STACK_DEPTH, NULL) < 0)
 				goto out;
 
 			fake_samples[i].thread = al.thread;
 			fake_samples[i].map = al.map;
 			fake_samples[i].sym = al.sym;
-
-			hists__inc_nr_events(he->hists, PERF_RECORD_SAMPLE);
-			if (!he->filtered)
-				he->hists->stats.nr_non_filtered_samples++;
 		}
 	}
 
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 5ffa2c3eb77..d4b34b0f50a 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -21,41 +21,41 @@ struct sample {
 /* For the numbers, see hists_common.c */
 static struct sample fake_common_samples[] = {
 	/* perf [kernel] schedule() */
-	{ .pid = 100, .ip = 0xf0000 + 700, },
+	{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
 	/* perf [perf]   main() */
-	{ .pid = 200, .ip = 0x40000 + 700, },
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
 	/* perf [perf]   cmd_record() */
-	{ .pid = 200, .ip = 0x40000 + 900, },
+	{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_CMD_RECORD, },
 	/* bash [bash]   xmalloc() */
-	{ .pid = 300, .ip = 0x40000 + 800, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
 	/* bash [libc]   malloc() */
-	{ .pid = 300, .ip = 0x50000 + 700, },
+	{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, },
 };
 
 static struct sample fake_samples[][5] = {
 	{
 		/* perf [perf]   run_command() */
-		{ .pid = 100, .ip = 0x40000 + 800, },
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_RUN_COMMAND, },
 		/* perf [libc]   malloc() */
-		{ .pid = 100, .ip = 0x50000 + 700, },
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
 		/* perf [kernel] page_fault() */
-		{ .pid = 100, .ip = 0xf0000 + 800, },
+		{ .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 		/* perf [kernel] sys_perf_event_open() */
-		{ .pid = 200, .ip = 0xf0000 + 900, },
+		{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_SYS_PERF_EVENT_OPEN, },
 		/* bash [libc]   free() */
-		{ .pid = 300, .ip = 0x50000 + 800, },
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_FREE, },
 	},
 	{
 		/* perf [libc]   free() */
-		{ .pid = 200, .ip = 0x50000 + 800, },
+		{ .pid = FAKE_PID_PERF2, .ip = FAKE_IP_LIBC_FREE, },
 		/* bash [libc]   malloc() */
-		{ .pid = 300, .ip = 0x50000 + 700, }, /* will be merged */
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_MALLOC, }, /* will be merged */
 		/* bash [bash]   xfee() */
-		{ .pid = 300, .ip = 0x40000 + 900, },
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XFREE, },
 		/* bash [libc]   realloc() */
-		{ .pid = 300, .ip = 0x50000 + 900, },
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_LIBC_REALLOC, },
 		/* bash [kernel] page_fault() */
-		{ .pid = 300, .ip = 0xf0000 + 800, },
+		{ .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 	},
 };
 
@@ -64,7 +64,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 	struct perf_evsel *evsel;
 	struct addr_location al;
 	struct hist_entry *he;
-	struct perf_sample sample = { .cpu = 0, };
+	struct perf_sample sample = { .period = 1, };
 	size_t i = 0, k;
 
 	/*
@@ -88,7 +88,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				goto out;
 
 			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 1, 1, 0);
+						NULL, NULL, 1, 1, 0, true);
 			if (he == NULL)
 				goto out;
 
@@ -112,7 +112,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 				goto out;
 
 			he = __hists__add_entry(&evsel->hists, &al, NULL,
-						NULL, NULL, 1, 1, 0);
+						NULL, NULL, 1, 1, 0, true);
 			if (he == NULL)
 				goto out;
 
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index a1685055179..e3bbd6c54c1 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -22,31 +22,31 @@ struct sample {
 /* For the numbers, see hists_common.c */
 static struct sample fake_samples[] = {
 	/* perf [kernel] schedule() */
-	{ .cpu = 0, .pid = 100, .ip = 0xf0000 + 700, },
+	{ .cpu = 0, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_KERNEL_SCHEDULE, },
 	/* perf [perf]   main() */
-	{ .cpu = 1, .pid = 100, .ip = 0x40000 + 700, },
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_MAIN, },
 	/* perf [perf]   cmd_record() */
-	{ .cpu = 1, .pid = 100, .ip = 0x40000 + 900, },
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_PERF_CMD_RECORD, },
 	/* perf [libc]   malloc() */
-	{ .cpu = 1, .pid = 100, .ip = 0x50000 + 700, },
+	{ .cpu = 1, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_MALLOC, },
 	/* perf [libc]   free() */
-	{ .cpu = 2, .pid = 100, .ip = 0x50000 + 800, },
+	{ .cpu = 2, .pid = FAKE_PID_PERF1, .ip = FAKE_IP_LIBC_FREE, },
 	/* perf [perf]   main() */
-	{ .cpu = 2, .pid = 200, .ip = 0x40000 + 700, },
+	{ .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_PERF_MAIN, },
 	/* perf [kernel] page_fault() */
-	{ .cpu = 2, .pid = 200, .ip = 0xf0000 + 800, },
+	{ .cpu = 2, .pid = FAKE_PID_PERF2, .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 	/* bash [bash]   main() */
-	{ .cpu = 3, .pid = 300, .ip = 0x40000 + 700, },
+	{ .cpu = 3, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_MAIN, },
 	/* bash [bash]   xmalloc() */
-	{ .cpu = 0, .pid = 300, .ip = 0x40000 + 800, },
+	{ .cpu = 0, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_BASH_XMALLOC, },
 	/* bash [kernel] page_fault() */
-	{ .cpu = 1, .pid = 300, .ip = 0xf0000 + 800, },
+	{ .cpu = 1, .pid = FAKE_PID_BASH,  .ip = FAKE_IP_KERNEL_PAGE_FAULT, },
 };
 
 static int add_hist_entries(struct hists *hists, struct machine *machine)
 {
 	struct addr_location al;
-	struct hist_entry *he;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
 	struct perf_sample sample = { .period = 100, };
 	size_t i;
 
@@ -56,6 +56,10 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 				.misc = PERF_RECORD_MISC_USER,
 			},
 		};
+		struct hist_entry_iter iter = {
+			.ops = &hist_iter_normal,
+			.hide_unresolved = false,
+		};
 
 		sample.cpu = fake_samples[i].cpu;
 		sample.pid = fake_samples[i].pid;
@@ -66,9 +70,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		he = __hists__add_entry(hists, &al, NULL, NULL, NULL,
-					sample.period, 1, 0);
-		if (he == NULL)
+		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
+					 PERF_MAX_STACK_DEPTH, NULL) < 0)
 			goto out;
 
 		fake_samples[i].thread = al.thread;
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 2f92d6e7ee0..69a71ff84e0 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -205,8 +205,7 @@ $(run):
 	( eval $$cmd ) >> $@ 2>&1; \
 	echo "  test: $(call test,$@)" >> $@ 2>&1; \
 	$(call test,$@) && \
-	rm -f $@ \
-	rm -rf $$TMP_DEST
+	rm -rf $@ $$TMP_DEST || (cat $@ ; false)
 
 $(run_O):
 	$(call clean)
@@ -217,9 +216,7 @@ $(run_O):
 	( eval $$cmd ) >> $@ 2>&1 && \
 	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
 	$(call test_O,$@) && \
-	rm -f $@ && \
-	rm -rf $$TMP_O \
-	rm -rf $$TMP_DEST
+	rm -rf $@ $$TMP_O $$TMP_DEST || (cat $@ ; false)
 
 tarpkg:
 	@cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index c505ef2af24..0785b64ffd6 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -3,6 +3,7 @@
 #include "evsel.h"
 #include "thread_map.h"
 #include "tests.h"
+#include "debug.h"
 
 int test__syscall_open_tp_fields(void)
 {
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index deba66955f8..5941927a4b7 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -5,6 +5,7 @@
 #include <api/fs/fs.h>
 #include <api/fs/debugfs.h>
 #include "tests.h"
+#include "debug.h"
 #include <linux/hw_breakpoint.h>
 
 #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 905019f9b74..2c63ea65854 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -7,6 +7,7 @@
 #include "evlist.h"
 #include "header.h"
 #include "util.h"
+#include "debug.h"
 
 static int process_event(struct perf_evlist **pevlist, union perf_event *event)
 {
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 3b7cd4d32dc..f238442b238 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -8,10 +8,9 @@
 #include "evsel.h"
 #include "thread_map.h"
 #include "cpumap.h"
+#include "tsc.h"
 #include "tests.h"
 
-#include "../arch/x86/util/tsc.h"
-
 #define CHECK__(x) {				\
 	while ((x) < 0) {			\
 		pr_debug(#x " failed!\n");	\
@@ -26,15 +25,6 @@
 	}					\
 }
 
-static u64 rdtsc(void)
-{
-	unsigned int low, high;
-
-	asm volatile("rdtsc" : "=a" (low), "=d" (high));
-
-	return low | ((u64)high) << 32;
-}
-
 /**
  * test__perf_time_to_tsc - test converting perf time to TSC.
  *
diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c
index e59143fd9e7..c04d1f26857 100644
--- a/tools/perf/tests/rdpmc.c
+++ b/tools/perf/tests/rdpmc.c
@@ -6,6 +6,7 @@
 #include "perf.h"
 #include "debug.h"
 #include "tests.h"
+#include "cloexec.h"
 
 #if defined(__x86_64__) || defined(__i386__)
 
@@ -104,7 +105,8 @@ static int __test__rdpmc(void)
 	sa.sa_sigaction = segfault_handler;
 	sigaction(SIGSEGV, &sa, NULL);
 
-	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	fd = sys_perf_event_open(&attr, 0, -1, -1,
+				 perf_event_open_cloexec_flag());
 	if (fd < 0) {
 		pr_err("Error: sys_perf_event_open() syscall returned "
 		       "with %d (%s)\n", fd, strerror(errno));
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 7ae8d17db3d..ca292f9a4ae 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -4,6 +4,7 @@
 #include "util.h"
 #include "event.h"
 #include "evsel.h"
+#include "debug.h"
 
 #include "tests.h"
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index d76c0e2e663..ed64790a395 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -28,6 +28,8 @@ int test__syscall_open_tp_fields(void);
 int test__pmu(void);
 int test__attr(void);
 int test__dso_data(void);
+int test__dso_data_cache(void);
+int test__dso_data_reopen(void);
 int test__parse_events(void);
 int test__hists_link(void);
 int test__python_use(void);
@@ -45,6 +47,7 @@ int test__hists_filter(void);
 int test__mmap_thread_lookup(void);
 int test__thread_mg_share(void);
 int test__hists_output(void);
+int test__hists_cumulate(void);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index 2b2e0dbe114..b028499dd3c 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -2,6 +2,7 @@
 #include "machine.h"
 #include "thread.h"
 #include "map.h"
+#include "debug.h"
 
 int test__thread_mg_share(void)
 {
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index d11541d4d7d..6680fa5cb9d 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -150,7 +150,7 @@ unsigned int ui_browser__rb_tree_refresh(struct ui_browser *browser)
 	while (nd != NULL) {
 		ui_browser__gotorc(browser, row, 0);
 		browser->write(browser, nd, row);
-		if (++row == browser->height)
+		if (++row == browser->rows)
 			break;
 		nd = rb_next(nd);
 	}
@@ -166,7 +166,7 @@ bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row)
 void ui_browser__refresh_dimensions(struct ui_browser *browser)
 {
 	browser->width = SLtt_Screen_Cols - 1;
-	browser->height = SLtt_Screen_Rows - 2;
+	browser->height = browser->rows = SLtt_Screen_Rows - 2;
 	browser->y = 1;
 	browser->x = 0;
 }
@@ -194,7 +194,7 @@ int ui_browser__warning(struct ui_browser *browser, int timeout,
 		ui_helpline__vpush(format, args);
 		va_end(args);
 	} else {
-		while ((key == ui__question_window("Warning!", text,
+		while ((key = ui__question_window("Warning!", text,
 						   "Press any key...",
 						   timeout)) == K_RESIZE)
 			ui_browser__handle_resize(browser);
@@ -250,7 +250,10 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
 	int err;
 	va_list ap;
 
-	ui_browser__refresh_dimensions(browser);
+	if (browser->refresh_dimensions == NULL)
+		browser->refresh_dimensions = ui_browser__refresh_dimensions;
+
+	browser->refresh_dimensions(browser);
 
 	pthread_mutex_lock(&ui__lock);
 	__ui_browser__show_title(browser, title);
@@ -279,7 +282,7 @@ static void ui_browser__scrollbar_set(struct ui_browser *browser)
 {
 	int height = browser->height, h = 0, pct = 0,
 	    col = browser->width,
-	    row = browser->y - 1;
+	    row = 0;
 
 	if (browser->nr_entries > 1) {
 		pct = ((browser->index * (browser->height - 1)) /
@@ -367,7 +370,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 
 		if (key == K_RESIZE) {
 			ui__refresh_dimensions(false);
-			ui_browser__refresh_dimensions(browser);
+			browser->refresh_dimensions(browser);
 			__ui_browser__show_title(browser, browser->title);
 			ui_helpline__puts(browser->helpline);
 			continue;
@@ -389,7 +392,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 			if (browser->index == browser->nr_entries - 1)
 				break;
 			++browser->index;
-			if (browser->index == browser->top_idx + browser->height) {
+			if (browser->index == browser->top_idx + browser->rows) {
 				++browser->top_idx;
 				browser->seek(browser, +1, SEEK_CUR);
 			}
@@ -405,10 +408,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 			break;
 		case K_PGDN:
 		case ' ':
-			if (browser->top_idx + browser->height > browser->nr_entries - 1)
+			if (browser->top_idx + browser->rows > browser->nr_entries - 1)
 				break;
 
-			offset = browser->height;
+			offset = browser->rows;
 			if (browser->index + offset > browser->nr_entries - 1)
 				offset = browser->nr_entries - 1 - browser->index;
 			browser->index += offset;
@@ -419,10 +422,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 			if (browser->top_idx == 0)
 				break;
 
-			if (browser->top_idx < browser->height)
+			if (browser->top_idx < browser->rows)
 				offset = browser->top_idx;
 			else
-				offset = browser->height;
+				offset = browser->rows;
 
 			browser->index -= offset;
 			browser->top_idx -= offset;
@@ -432,7 +435,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 			ui_browser__reset_index(browser);
 			break;
 		case K_END:
-			offset = browser->height - 1;
+			offset = browser->rows - 1;
 			if (offset >= browser->nr_entries)
 				offset = browser->nr_entries - 1;
 
@@ -462,7 +465,7 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *browser)
 		if (!browser->filter || !browser->filter(browser, pos)) {
 			ui_browser__gotorc(browser, row, 0);
 			browser->write(browser, pos, row);
-			if (++row == browser->height)
+			if (++row == browser->rows)
 				break;
 		}
 	}
@@ -587,7 +590,7 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser)
 		if (!browser->filter || !browser->filter(browser, *pos)) {
 			ui_browser__gotorc(browser, row, 0);
 			browser->write(browser, pos, row);
-			if (++row == browser->height)
+			if (++row == browser->rows)
 				break;
 		}
 
@@ -623,7 +626,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser,
 
 	SLsmg_set_char_set(1);
 
-	if (start < browser->top_idx + browser->height) {
+	if (start < browser->top_idx + browser->rows) {
 		row = start - browser->top_idx;
 		ui_browser__gotorc(browser, row, column);
 		SLsmg_write_char(SLSMG_LLCORN_CHAR);
@@ -633,7 +636,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser,
 		if (row-- == 0)
 			goto out;
 	} else
-		row = browser->height - 1;
+		row = browser->rows - 1;
 
 	if (end > browser->top_idx)
 		end_row = end - browser->top_idx;
@@ -675,8 +678,8 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 	} else
 		row = 0;
 
-	if (end >= browser->top_idx + browser->height)
-		end_row = browser->height - 1;
+	if (end >= browser->top_idx + browser->rows)
+		end_row = browser->rows - 1;
 	else
 		end_row = end - browser->top_idx;
 
@@ -684,7 +687,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 	SLsmg_draw_vline(end_row - row + 1);
 
 	ui_browser__gotorc(browser, end_row, column);
-	if (end < browser->top_idx + browser->height) {
+	if (end < browser->top_idx + browser->rows) {
 		SLsmg_write_char(SLSMG_LLCORN_CHAR);
 		ui_browser__gotorc(browser, end_row, column + 1);
 		SLsmg_write_char(SLSMG_HLINE_CHAR);
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 03d4d6295f1..92ae7211396 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -14,11 +14,12 @@
 struct ui_browser {
 	u64	      index, top_idx;
 	void	      *top, *entries;
-	u16	      y, x, width, height;
+	u16	      y, x, width, height, rows;
 	int	      current_color;
 	void	      *priv;
 	const char    *title;
 	char	      *helpline;
+	void 	      (*refresh_dimensions)(struct ui_browser *browser);
 	unsigned int  (*refresh)(struct ui_browser *browser);
 	void	      (*write)(struct ui_browser *browser, void *entry, int row);
 	void	      (*seek)(struct ui_browser *browser, off_t offset, int whence);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 1c331b934ff..a94b11fc5e0 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -17,6 +17,7 @@
 #include "../util.h"
 #include "../ui.h"
 #include "map.h"
+#include "annotate.h"
 
 struct hist_browser {
 	struct ui_browser   b;
@@ -25,6 +26,7 @@ struct hist_browser {
 	struct map_symbol   *selection;
 	int		     print_seq;
 	bool		     show_dso;
+	bool		     show_headers;
 	float		     min_pcnt;
 	u64		     nr_non_filtered_entries;
 	u64		     nr_callchain_rows;
@@ -32,12 +34,10 @@ struct hist_browser {
 
 extern void hist_browser__init_hpp(void);
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size,
-				const char *ev_name);
+static int hists__browser_title(struct hists *hists, char *bf, size_t size);
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
-					     struct hists *hists,
 					     float min_pcnt);
 
 static bool hist_browser__has_filter(struct hist_browser *hb)
@@ -57,11 +57,42 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
 	return nr_entries + hb->nr_callchain_rows;
 }
 
-static void hist_browser__refresh_dimensions(struct hist_browser *browser)
+static void hist_browser__update_rows(struct hist_browser *hb)
 {
+	struct ui_browser *browser = &hb->b;
+	u16 header_offset = hb->show_headers ? 1 : 0, index_row;
+
+	browser->rows = browser->height - header_offset;
+	/*
+	 * Verify if we were at the last line and that line isn't
+	 * visibe because we now show the header line(s).
+	 */
+	index_row = browser->index - browser->top_idx;
+	if (index_row >= browser->rows)
+		browser->index -= index_row - browser->rows + 1;
+}
+
+static void hist_browser__refresh_dimensions(struct ui_browser *browser)
+{
+	struct hist_browser *hb = container_of(browser, struct hist_browser, b);
+
 	/* 3 == +/- toggle symbol before actual hist_entry rendering */
-	browser->b.width = 3 + (hists__sort_list_width(browser->hists) +
-			     sizeof("[k]"));
+	browser->width = 3 + (hists__sort_list_width(hb->hists) + sizeof("[k]"));
+	/*
+ 	 * FIXME: Just keeping existing behaviour, but this really should be
+ 	 *	  before updating browser->width, as it will invalidate the
+ 	 *	  calculation above. Fix this and the fallout in another
+ 	 *	  changeset.
+ 	 */
+	ui_browser__refresh_dimensions(browser);
+	hist_browser__update_rows(hb);
+}
+
+static void hist_browser__gotorc(struct hist_browser *browser, int row, int column)
+{
+	u16 header_offset = browser->show_headers ? 1 : 0;
+
+	ui_browser__gotorc(&browser->b, row + header_offset, column);
 }
 
 static void hist_browser__reset(struct hist_browser *browser)
@@ -74,7 +105,7 @@ static void hist_browser__reset(struct hist_browser *browser)
 
 	hist_browser__update_nr_entries(browser);
 	browser->b.nr_entries = hist_browser__nr_entries(browser);
-	hist_browser__refresh_dimensions(browser);
+	hist_browser__refresh_dimensions(&browser->b);
 	ui_browser__reset_index(&browser->b);
 }
 
@@ -319,7 +350,7 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 	struct hists *hists = browser->hists;
 
 	for (nd = rb_first(&hists->entries);
-	     (nd = hists__filter_entries(nd, hists, browser->min_pcnt)) != NULL;
+	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
 	     nd = rb_next(nd)) {
 		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
 		hist_entry__set_folding(he, unfold);
@@ -346,7 +377,7 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
 		"Or reduce the sampling frequency.");
 }
 
-static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
+static int hist_browser__run(struct hist_browser *browser,
 			     struct hist_browser_timer *hbt)
 {
 	int key;
@@ -356,8 +387,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 	browser->b.entries = &browser->hists->entries;
 	browser->b.nr_entries = hist_browser__nr_entries(browser);
 
-	hist_browser__refresh_dimensions(browser);
-	hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+	hists__browser_title(browser->hists, title, sizeof(title));
 
 	if (ui_browser__show(&browser->b, title,
 			     "Press '?' for help on key bindings") < 0)
@@ -384,7 +414,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 				ui_browser__warn_lost_events(&browser->b);
 			}
 
-			hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+			hists__browser_title(browser->hists, title, sizeof(title));
 			ui_browser__show_title(&browser->b, title);
 			continue;
 		}
@@ -393,10 +423,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 			struct hist_entry *h = rb_entry(browser->b.top,
 							struct hist_entry, rb_node);
 			ui_helpline__pop();
-			ui_helpline__fpush("%d: nr_ent=(%d,%d), height=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
+			ui_helpline__fpush("%d: nr_ent=(%d,%d), rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
 					   seq++, browser->b.nr_entries,
 					   browser->hists->nr_entries,
-					   browser->b.height,
+					   browser->b.rows,
 					   browser->b.index,
 					   browser->b.top_idx,
 					   h->row_offset, h->nr_rows);
@@ -410,6 +440,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 			/* Expand the whole world. */
 			hist_browser__set_folding(browser, true);
 			break;
+		case 'H':
+			browser->show_headers = !browser->show_headers;
+			hist_browser__update_rows(browser);
+			break;
 		case K_ENTER:
 			if (hist_browser__toggle_fold(browser))
 				break;
@@ -509,13 +543,13 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
 			}
 
 			ui_browser__set_color(&browser->b, color);
-			ui_browser__gotorc(&browser->b, row, 0);
+			hist_browser__gotorc(browser, row, 0);
 			slsmg_write_nstring(" ", offset + extra_offset);
 			slsmg_printf("%c ", folded_sign);
 			slsmg_write_nstring(str, width);
 			free(alloc_str);
 
-			if (++row == browser->b.height)
+			if (++row == browser->b.rows)
 				goto out;
 do_next:
 			if (folded_sign == '+')
@@ -528,7 +562,7 @@ do_next:
 									 new_level, row, row_offset,
 									 is_current_entry);
 		}
-		if (row == browser->b.height)
+		if (row == browser->b.rows)
 			goto out;
 		node = next;
 	}
@@ -568,13 +602,13 @@ static int hist_browser__show_callchain_node(struct hist_browser *browser,
 
 		s = callchain_list__sym_name(chain, bf, sizeof(bf),
 					     browser->show_dso);
-		ui_browser__gotorc(&browser->b, row, 0);
+		hist_browser__gotorc(browser, row, 0);
 		ui_browser__set_color(&browser->b, color);
 		slsmg_write_nstring(" ", offset);
 		slsmg_printf("%c ", folded_sign);
 		slsmg_write_nstring(s, width - 2);
 
-		if (++row == browser->b.height)
+		if (++row == browser->b.rows)
 			goto out;
 	}
 
@@ -603,7 +637,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 		row += hist_browser__show_callchain_node(browser, node, level,
 							 row, row_offset,
 							 is_current_entry);
-		if (row == browser->b.height)
+		if (row == browser->b.rows)
 			break;
 	}
 
@@ -651,13 +685,36 @@ hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
 			  __hpp__slsmg_color_printf, true);		\
 }
 
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)			\
+static u64 __hpp_get_acc_##_field(struct hist_entry *he)		\
+{									\
+	return he->stat_acc->_field;					\
+}									\
+									\
+static int								\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+				struct perf_hpp *hpp,			\
+				struct hist_entry *he)			\
+{									\
+	if (!symbol_conf.cumulate_callchain) {				\
+		int ret = scnprintf(hpp->buf, hpp->size, "%8s", "N/A");	\
+		slsmg_printf("%s", hpp->buf);				\
+									\
+		return ret;						\
+	}								\
+	return __hpp__fmt(hpp, he, __hpp_get_acc_##_field, " %6.2f%%",	\
+			  __hpp__slsmg_color_printf, true);		\
+}
+
 __HPP_COLOR_PERCENT_FN(overhead, period)
 __HPP_COLOR_PERCENT_FN(overhead_sys, period_sys)
 __HPP_COLOR_PERCENT_FN(overhead_us, period_us)
 __HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys)
 __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
+__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period)
 
 #undef __HPP_COLOR_PERCENT_FN
+#undef __HPP_COLOR_ACC_PERCENT_FN
 
 void hist_browser__init_hpp(void)
 {
@@ -671,6 +728,8 @@ void hist_browser__init_hpp(void)
 				hist_browser__hpp_color_overhead_guest_sys;
 	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color =
 				hist_browser__hpp_color_overhead_guest_us;
+	perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color =
+				hist_browser__hpp_color_overhead_acc;
 }
 
 static int hist_browser__show_entry(struct hist_browser *browser,
@@ -708,7 +767,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.ptr		= &arg,
 		};
 
-		ui_browser__gotorc(&browser->b, row, 0);
+		hist_browser__gotorc(browser, row, 0);
 
 		perf_hpp__for_each_format(fmt) {
 			if (perf_hpp__should_skip(fmt))
@@ -752,7 +811,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	} else
 		--row_offset;
 
-	if (folded_sign == '-' && row != browser->b.height) {
+	if (folded_sign == '-' && row != browser->b.rows) {
 		printed += hist_browser__show_callchain(browser, &entry->sorted_chain,
 							1, row, &row_offset,
 							&current_entry);
@@ -763,6 +822,56 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	return printed;
 }
 
+static int advance_hpp_check(struct perf_hpp *hpp, int inc)
+{
+	advance_hpp(hpp, inc);
+	return hpp->size <= 0;
+}
+
+static int hists__scnprintf_headers(char *buf, size_t size, struct hists *hists)
+{
+	struct perf_hpp dummy_hpp = {
+		.buf    = buf,
+		.size   = size,
+	};
+	struct perf_hpp_fmt *fmt;
+	size_t ret = 0;
+
+	if (symbol_conf.use_callchain) {
+		ret = scnprintf(buf, size, "  ");
+		if (advance_hpp_check(&dummy_hpp, ret))
+			return ret;
+	}
+
+	perf_hpp__for_each_format(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
+
+		/* We need to add the length of the columns header. */
+		perf_hpp__reset_width(fmt, hists);
+
+		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+
+		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+	}
+
+	return ret;
+}
+
+static void hist_browser__show_headers(struct hist_browser *browser)
+{
+	char headers[1024];
+
+	hists__scnprintf_headers(headers, sizeof(headers), browser->hists);
+	ui_browser__gotorc(&browser->b, 0, 0);
+	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
+	slsmg_write_nstring(headers, browser->b.width + 1);
+}
+
 static void ui_browser__hists_init_top(struct ui_browser *browser)
 {
 	if (browser->top == NULL) {
@@ -776,44 +885,42 @@ static void ui_browser__hists_init_top(struct ui_browser *browser)
 static unsigned int hist_browser__refresh(struct ui_browser *browser)
 {
 	unsigned row = 0;
+	u16 header_offset = 0;
 	struct rb_node *nd;
 	struct hist_browser *hb = container_of(browser, struct hist_browser, b);
 
+	if (hb->show_headers) {
+		hist_browser__show_headers(hb);
+		header_offset = 1;
+	}
+
 	ui_browser__hists_init_top(browser);
 
 	for (nd = browser->top; nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		u64 total = hists__total_period(h->hists);
-		float percent = 0.0;
+		float percent;
 
 		if (h->filtered)
 			continue;
 
-		if (total)
-			percent = h->stat.period * 100.0 / total;
-
+		percent = hist_entry__get_percent_limit(h);
 		if (percent < hb->min_pcnt)
 			continue;
 
 		row += hist_browser__show_entry(hb, h, row);
-		if (row == browser->height)
+		if (row == browser->rows)
 			break;
 	}
 
-	return row;
+	return row + header_offset;
 }
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
-					     struct hists *hists,
 					     float min_pcnt)
 {
 	while (nd != NULL) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		u64 total = hists__total_period(hists);
-		float percent = 0.0;
-
-		if (total)
-			percent = h->stat.period * 100.0 / total;
+		float percent = hist_entry__get_percent_limit(h);
 
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
@@ -825,16 +932,11 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 }
 
 static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
-						  struct hists *hists,
 						  float min_pcnt)
 {
 	while (nd != NULL) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		u64 total = hists__total_period(hists);
-		float percent = 0.0;
-
-		if (total)
-			percent = h->stat.period * 100.0 / total;
+		float percent = hist_entry__get_percent_limit(h);
 
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
@@ -863,14 +965,14 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 	switch (whence) {
 	case SEEK_SET:
 		nd = hists__filter_entries(rb_first(browser->entries),
-					   hb->hists, hb->min_pcnt);
+					   hb->min_pcnt);
 		break;
 	case SEEK_CUR:
 		nd = browser->top;
 		goto do_offset;
 	case SEEK_END:
 		nd = hists__filter_prev_entries(rb_last(browser->entries),
-						hb->hists, hb->min_pcnt);
+						hb->min_pcnt);
 		first = false;
 		break;
 	default:
@@ -913,8 +1015,7 @@ do_offset:
 					break;
 				}
 			}
-			nd = hists__filter_entries(rb_next(nd), hb->hists,
-						   hb->min_pcnt);
+			nd = hists__filter_entries(rb_next(nd), hb->min_pcnt);
 			if (nd == NULL)
 				break;
 			--offset;
@@ -947,7 +1048,7 @@ do_offset:
 				}
 			}
 
-			nd = hists__filter_prev_entries(rb_prev(nd), hb->hists,
+			nd = hists__filter_prev_entries(rb_prev(nd),
 							hb->min_pcnt);
 			if (nd == NULL)
 				break;
@@ -1126,7 +1227,6 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 {
 	struct rb_node *nd = hists__filter_entries(rb_first(browser->b.entries),
-						   browser->hists,
 						   browser->min_pcnt);
 	int printed = 0;
 
@@ -1134,8 +1234,7 @@ static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
 		printed += hist_browser__fprintf_entry(browser, h, fp);
-		nd = hists__filter_entries(rb_next(nd), browser->hists,
-					   browser->min_pcnt);
+		nd = hists__filter_entries(rb_next(nd), browser->min_pcnt);
 	}
 
 	return printed;
@@ -1182,8 +1281,10 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
 	if (browser) {
 		browser->hists = hists;
 		browser->b.refresh = hist_browser__refresh;
+		browser->b.refresh_dimensions = hist_browser__refresh_dimensions;
 		browser->b.seek = ui_browser__hists_seek;
 		browser->b.use_navkeypressed = true;
+		browser->show_headers = symbol_conf.show_hist_headers;
 	}
 
 	return browser;
@@ -1204,8 +1305,7 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
 	return browser->he_selection->thread;
 }
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size,
-				const char *ev_name)
+static int hists__browser_title(struct hists *hists, char *bf, size_t size)
 {
 	char unit;
 	int printed;
@@ -1214,6 +1314,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 	u64 nr_events = hists->stats.total_period;
 	struct perf_evsel *evsel = hists_to_evsel(hists);
+	const char *ev_name = perf_evsel__name(evsel);
 	char buf[512];
 	size_t buflen = sizeof(buf);
 
@@ -1372,8 +1473,7 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
 		return;
 	}
 
-	while ((nd = hists__filter_entries(nd, hb->hists,
-					   hb->min_pcnt)) != NULL) {
+	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
 		nr_entries++;
 		nd = rb_next(nd);
 	}
@@ -1382,7 +1482,7 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
 }
 
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
-				    const char *helpline, const char *ev_name,
+				    const char *helpline,
 				    bool left_exits,
 				    struct hist_browser_timer *hbt,
 				    float min_pcnt,
@@ -1414,6 +1514,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"d             Zoom into current DSO\n"				\
 	"E             Expand all callchains\n"				\
 	"F             Toggle percentage of filtered entries\n"		\
+	"H             Display column headers\n"			\
 
 	/* help messages are sorted by lexical order of the hotkey */
 	const char report_help[] = HIST_BROWSER_HELP_COMMON
@@ -1457,7 +1558,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 		nr_options = 0;
 
-		key = hist_browser__run(browser, ev_name, hbt);
+		key = hist_browser__run(browser, hbt);
 
 		if (browser->he_selection != NULL) {
 			thread = hist_browser__selected_thread(browser);
@@ -1586,13 +1687,18 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					 bi->to.sym->name) > 0)
 				annotate_t = nr_options++;
 		} else {
-
 			if (browser->selection != NULL &&
 			    browser->selection->sym != NULL &&
-			    !browser->selection->map->dso->annotate_warned &&
-				asprintf(&options[nr_options], "Annotate %s",
-					 browser->selection->sym->name) > 0)
-				annotate = nr_options++;
+			    !browser->selection->map->dso->annotate_warned) {
+				struct annotation *notes;
+
+				notes = symbol__annotation(browser->selection->sym);
+
+				if (notes->src &&
+				    asprintf(&options[nr_options], "Annotate %s",
+						 browser->selection->sym->name) > 0)
+					annotate = nr_options++;
+			}
 		}
 
 		if (thread != NULL &&
@@ -1649,6 +1755,7 @@ retry_popup_menu:
 
 		if (choice == annotate || choice == annotate_t || choice == annotate_f) {
 			struct hist_entry *he;
+			struct annotation *notes;
 			int err;
 do_annotate:
 			if (!objdump_path && perf_session_env__lookup_objdump(env))
@@ -1672,6 +1779,10 @@ do_annotate:
 				he->ms.map = he->branch_info->to.map;
 			}
 
+			notes = symbol__annotation(he->ms.sym);
+			if (!notes->src)
+				continue;
+
 			/*
 			 * Don't let this be freed, say, by hists__decay_entry.
 			 */
@@ -1699,14 +1810,14 @@ zoom_dso:
 zoom_out_dso:
 				ui_helpline__pop();
 				browser->hists->dso_filter = NULL;
-				sort_dso.elide = false;
+				perf_hpp__set_elide(HISTC_DSO, false);
 			} else {
 				if (dso == NULL)
 					continue;
 				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
 						   dso->kernel ? "the Kernel" : dso->short_name);
 				browser->hists->dso_filter = dso;
-				sort_dso.elide = true;
+				perf_hpp__set_elide(HISTC_DSO, true);
 				pstack__push(fstack, &browser->hists->dso_filter);
 			}
 			hists__filter_by_dso(hists);
@@ -1718,13 +1829,13 @@ zoom_thread:
 zoom_out_thread:
 				ui_helpline__pop();
 				browser->hists->thread_filter = NULL;
-				sort_thread.elide = false;
+				perf_hpp__set_elide(HISTC_THREAD, false);
 			} else {
 				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
 						   thread->comm_set ? thread__comm_str(thread) : "",
 						   thread->tid);
 				browser->hists->thread_filter = thread;
-				sort_thread.elide = true;
+				perf_hpp__set_elide(HISTC_THREAD, false);
 				pstack__push(fstack, &browser->hists->thread_filter);
 			}
 			hists__filter_by_thread(hists);
@@ -1825,7 +1936,7 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 {
 	struct perf_evlist *evlist = menu->b.priv;
 	struct perf_evsel *pos;
-	const char *ev_name, *title = "Available samples";
+	const char *title = "Available samples";
 	int delay_secs = hbt ? hbt->refresh : 0;
 	int key;
 
@@ -1858,9 +1969,8 @@ browse_hists:
 			 */
 			if (hbt)
 				hbt->timer(hbt->arg);
-			ev_name = perf_evsel__name(pos);
 			key = perf_evsel__hists_browse(pos, nr_events, help,
-						       ev_name, true, hbt,
+						       true, hbt,
 						       menu->min_pcnt,
 						       menu->env);
 			ui_browser__show_title(&menu->b, title);
@@ -1964,10 +2074,9 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 single_entry:
 	if (nr_entries == 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
-		const char *ev_name = perf_evsel__name(first);
 
 		return perf_evsel__hists_browse(first, nr_entries, help,
-						ev_name, false, hbt, min_pcnt,
+						false, hbt, min_pcnt,
 						env);
 	}
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 9d90683914d..6ca60e482cd 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -47,11 +47,26 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,
 			  __percent_color_snprintf, true);			\
 }
 
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+static u64 he_get_acc_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat_acc->_field;						\
+}										\
+										\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+				       struct perf_hpp *hpp,			\
+				       struct hist_entry *he)			\
+{										\
+	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
+			      __percent_color_snprintf, true);			\
+}
+
 __HPP_COLOR_PERCENT_FN(overhead, period)
 __HPP_COLOR_PERCENT_FN(overhead_sys, period_sys)
 __HPP_COLOR_PERCENT_FN(overhead_us, period_us)
 __HPP_COLOR_PERCENT_FN(overhead_guest_sys, period_guest_sys)
 __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us)
+__HPP_COLOR_ACC_PERCENT_FN(overhead_acc, period)
 
 #undef __HPP_COLOR_PERCENT_FN
 
@@ -68,6 +83,8 @@ void perf_gtk__init_hpp(void)
 				perf_gtk__hpp_color_overhead_guest_sys;
 	perf_hpp__format[PERF_HPP__OVERHEAD_GUEST_US].color =
 				perf_gtk__hpp_color_overhead_guest_us;
+	perf_hpp__format[PERF_HPP__OVERHEAD_ACC].color =
+				perf_gtk__hpp_color_overhead_acc;
 }
 
 static void callchain_list__sym_name(struct callchain_list *cl,
@@ -181,6 +198,13 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		if (perf_hpp__should_skip(fmt))
 			continue;
 
+		/*
+		 * XXX no way to determine where symcol column is..
+		 *     Just use last column for now.
+		 */
+		if (perf_hpp__is_sort_entry(fmt))
+			sym_col = col_idx;
+
 		fmt->header(fmt, &hpp, hists_to_evsel(hists));
 
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
@@ -209,14 +233,12 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		GtkTreeIter iter;
 		u64 total = hists__total_period(h->hists);
-		float percent = 0.0;
+		float percent;
 
 		if (h->filtered)
 			continue;
 
-		if (total)
-			percent = h->stat.period * 100.0 / total;
-
+		percent = hist_entry__get_percent_limit(h);
 		if (percent < min_pcnt)
 			continue;
 
@@ -238,7 +260,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 		if (symbol_conf.use_callchain && sort__has_sym) {
 			if (callchain_param.mode == CHAIN_GRAPH_REL)
-				total = h->stat.period;
+				total = symbol_conf.cumulate_callchain ?
+					h->stat_acc->period : h->stat.period;
 
 			perf_gtk__add_callchain(&h->sorted_chain, store, &iter,
 						sym_col, total);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 4484f5bd1b1..498adb23c02 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -104,6 +104,18 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	return ret;
 }
 
+int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
+		   hpp_field_fn get_field, const char *fmt,
+		   hpp_snprint_fn print_fn, bool fmt_percent)
+{
+	if (!symbol_conf.cumulate_callchain) {
+		return snprintf(hpp->buf, hpp->size, "%*s",
+				fmt_percent ? 8 : 12, "N/A");
+	}
+
+	return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent);
+}
+
 static int field_cmp(u64 field_a, u64 field_b)
 {
 	if (field_a > field_b)
@@ -160,6 +172,24 @@ out:
 	return ret;
 }
 
+static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
+			   hpp_field_fn get_field)
+{
+	s64 ret = 0;
+
+	if (symbol_conf.cumulate_callchain) {
+		/*
+		 * Put caller above callee when they have equal period.
+		 */
+		ret = field_cmp(get_field(a), get_field(b));
+		if (ret)
+			return ret;
+
+		ret = b->callchain->max_depth - a->callchain->max_depth;
+	}
+	return ret;
+}
+
 #define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
 static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
 			       struct perf_hpp *hpp,			\
@@ -242,6 +272,34 @@ static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
 	return __hpp__sort(a, b, he_get_##_field);				\
 }
 
+#define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+static u64 he_get_acc_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat_acc->_field;						\
+}										\
+										\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
+			      hpp_color_scnprintf, true);			\
+}
+
+#define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
+static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
+	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt,		\
+			      hpp_entry_scnprintf, true);			\
+}
+
+#define __HPP_SORT_ACC_FN(_type, _field)					\
+static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
+{										\
+	return __hpp__sort_acc(a, b, he_get_acc_##_field);			\
+}
+
 #define __HPP_ENTRY_RAW_FN(_type, _field)					\
 static u64 he_get_raw_##_field(struct hist_entry *he)				\
 {										\
@@ -270,18 +328,27 @@ __HPP_COLOR_PERCENT_FN(_type, _field)					\
 __HPP_ENTRY_PERCENT_FN(_type, _field)					\
 __HPP_SORT_FN(_type, _field)
 
+#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\
+__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
+__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+__HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
+__HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
+__HPP_SORT_ACC_FN(_type, _field)
+
 #define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width)	\
 __HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
 __HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
 __HPP_ENTRY_RAW_FN(_type, _field)					\
 __HPP_SORT_RAW_FN(_type, _field)
 
+__HPP_HEADER_FN(overhead_self, "Self", 8, 8)
 
 HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
 HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
 HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
 HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
 HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
+HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8)
 
 HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
 HPP_RAW_FNS(period, "Period", period, 12, 12)
@@ -303,6 +370,17 @@ static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
 		.sort	= hpp__sort_ ## _name,		\
 	}
 
+#define HPP__COLOR_ACC_PRINT_FNS(_name)			\
+	{						\
+		.header	= hpp__header_ ## _name,	\
+		.width	= hpp__width_ ## _name,		\
+		.color	= hpp__color_ ## _name,		\
+		.entry	= hpp__entry_ ## _name,		\
+		.cmp	= hpp__nop_cmp,			\
+		.collapse = hpp__nop_cmp,		\
+		.sort	= hpp__sort_ ## _name,		\
+	}
+
 #define HPP__PRINT_FNS(_name)				\
 	{						\
 		.header	= hpp__header_ ## _name,	\
@@ -319,6 +397,7 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 	HPP__COLOR_PRINT_FNS(overhead_us),
 	HPP__COLOR_PRINT_FNS(overhead_guest_sys),
 	HPP__COLOR_PRINT_FNS(overhead_guest_us),
+	HPP__COLOR_ACC_PRINT_FNS(overhead_acc),
 	HPP__PRINT_FNS(samples),
 	HPP__PRINT_FNS(period)
 };
@@ -328,16 +407,23 @@ LIST_HEAD(perf_hpp__sort_list);
 
 
 #undef HPP__COLOR_PRINT_FNS
+#undef HPP__COLOR_ACC_PRINT_FNS
 #undef HPP__PRINT_FNS
 
 #undef HPP_PERCENT_FNS
+#undef HPP_PERCENT_ACC_FNS
 #undef HPP_RAW_FNS
 
 #undef __HPP_HEADER_FN
 #undef __HPP_WIDTH_FN
 #undef __HPP_COLOR_PERCENT_FN
 #undef __HPP_ENTRY_PERCENT_FN
+#undef __HPP_COLOR_ACC_PERCENT_FN
+#undef __HPP_ENTRY_ACC_PERCENT_FN
 #undef __HPP_ENTRY_RAW_FN
+#undef __HPP_SORT_FN
+#undef __HPP_SORT_ACC_FN
+#undef __HPP_SORT_RAW_FN
 
 
 void perf_hpp__init(void)
@@ -361,6 +447,13 @@ void perf_hpp__init(void)
 	if (field_order)
 		return;
 
+	if (symbol_conf.cumulate_callchain) {
+		perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC);
+
+		perf_hpp__format[PERF_HPP__OVERHEAD].header =
+						hpp__header_overhead_self;
+	}
+
 	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
 
 	if (symbol_conf.show_cpu_utilization) {
@@ -383,6 +476,12 @@ void perf_hpp__init(void)
 	list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
 	if (list_empty(list))
 		list_add(list, &perf_hpp__sort_list);
+
+	if (symbol_conf.cumulate_callchain) {
+		list = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC].sort_list;
+		if (list_empty(list))
+			list_add(list, &perf_hpp__sort_list);
+	}
 }
 
 void perf_hpp__column_register(struct perf_hpp_fmt *format)
@@ -390,6 +489,11 @@ void perf_hpp__column_register(struct perf_hpp_fmt *format)
 	list_add_tail(&format->list, &perf_hpp__list);
 }
 
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+{
+	list_del(&format->list);
+}
+
 void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
 {
 	list_add_tail(&format->sort_list, &perf_hpp__sort_list);
@@ -401,6 +505,21 @@ void perf_hpp__column_enable(unsigned col)
 	perf_hpp__column_register(&perf_hpp__format[col]);
 }
 
+void perf_hpp__column_disable(unsigned col)
+{
+	BUG_ON(col >= PERF_HPP__MAX_INDEX);
+	perf_hpp__column_unregister(&perf_hpp__format[col]);
+}
+
+void perf_hpp__cancel_cumulate(void)
+{
+	if (field_order)
+		return;
+
+	perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
+	perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead;
+}
+
 void perf_hpp__setup_output_field(void)
 {
 	struct perf_hpp_fmt *fmt;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 9f57991025a..40af0acb4fe 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -271,7 +271,9 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 {
 	switch (callchain_param.mode) {
 	case CHAIN_GRAPH_REL:
-		return callchain__fprintf_graph(fp, &he->sorted_chain, he->stat.period,
+		return callchain__fprintf_graph(fp, &he->sorted_chain,
+						symbol_conf.cumulate_callchain ?
+						he->stat_acc->period : he->stat.period,
 						left_margin);
 		break;
 	case CHAIN_GRAPH_ABS:
@@ -461,12 +463,12 @@ print_entries:
 
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-		float percent = h->stat.period * 100.0 /
-					hists->stats.total_period;
+		float percent;
 
 		if (h->filtered)
 			continue;
 
+		percent = hist_entry__get_percent_limit(h);
 		if (percent < min_pcnt)
 			continue;
 
@@ -477,7 +479,7 @@ print_entries:
 
 		if (h->ms.map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(h->thread->mg,
-						   MAP__FUNCTION, verbose, fp);
+						   MAP__FUNCTION, fp);
 			fprintf(fp, "%.10s end\n", graph_dotted_line);
 		}
 	}
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 9a42382b392..437ee09727e 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -616,7 +616,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 	if (sample->callchain == NULL)
 		return 0;
 
-	if (symbol_conf.use_callchain || sort__has_parent) {
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
+	    sort__has_parent) {
 		return machine__resolve_callchain(al->machine, evsel, al->thread,
 						  sample, parent, al, max_stack);
 	}
@@ -625,7 +626,49 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
 {
-	if (!symbol_conf.use_callchain)
+	if (!symbol_conf.use_callchain || sample->callchain == NULL)
 		return 0;
 	return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
+
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+			bool hide_unresolved)
+{
+	al->map = node->map;
+	al->sym = node->sym;
+	if (node->map)
+		al->addr = node->map->map_ip(node->map, node->ip);
+	else
+		al->addr = node->ip;
+
+	if (al->sym == NULL) {
+		if (hide_unresolved)
+			return 0;
+		if (al->map == NULL)
+			goto out;
+	}
+
+	if (al->map->groups == &al->machine->kmaps) {
+		if (machine__is_host(al->machine)) {
+			al->cpumode = PERF_RECORD_MISC_KERNEL;
+			al->level = 'k';
+		} else {
+			al->cpumode = PERF_RECORD_MISC_GUEST_KERNEL;
+			al->level = 'g';
+		}
+	} else {
+		if (machine__is_host(al->machine)) {
+			al->cpumode = PERF_RECORD_MISC_USER;
+			al->level = '.';
+		} else if (perf_guest) {
+			al->cpumode = PERF_RECORD_MISC_GUEST_USER;
+			al->level = 'u';
+		} else {
+			al->cpumode = PERF_RECORD_MISC_HYPERVISOR;
+			al->level = 'H';
+		}
+	}
+
+out:
+	return 1;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index bde2b0cc24c..da43619d617 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -162,7 +162,31 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 			      struct perf_evsel *evsel, struct addr_location *al,
 			      int max_stack);
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+			bool hide_unresolved);
 
 extern const char record_callchain_help[];
 int parse_callchain_report_opt(const char *arg);
+
+static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
+					     struct callchain_cursor *src)
+{
+	*dest = *src;
+
+	dest->first = src->curr;
+	dest->nr -= src->pos;
+}
+
+#ifdef HAVE_SKIP_CALLCHAIN_IDX
+extern int arch_skip_callchain_idx(struct machine *machine,
+			struct thread *thread, struct ip_callchain *chain);
+#else
+static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused,
+			struct thread *thread __maybe_unused,
+			struct ip_callchain *chain __maybe_unused)
+{
+	return -1;
+}
+#endif
+
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
new file mode 100644
index 00000000000..c5d05ec1722
--- /dev/null
+++ b/tools/perf/util/cloexec.c
@@ -0,0 +1,57 @@
+#include "util.h"
+#include "../perf.h"
+#include "cloexec.h"
+#include "asm/bug.h"
+
+static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
+
+static int perf_flag_probe(void)
+{
+	/* use 'safest' configuration as used in perf_evsel__fallback() */
+	struct perf_event_attr attr = {
+		.type = PERF_COUNT_SW_CPU_CLOCK,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+	};
+	int fd;
+	int err;
+
+	/* check cloexec flag */
+	fd = sys_perf_event_open(&attr, 0, -1, -1,
+				 PERF_FLAG_FD_CLOEXEC);
+	err = errno;
+
+	if (fd >= 0) {
+		close(fd);
+		return 1;
+	}
+
+	WARN_ONCE(err != EINVAL,
+		  "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n",
+		  err, strerror(err));
+
+	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
+	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	err = errno;
+
+	if (WARN_ONCE(fd < 0,
+		      "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
+		      err, strerror(err)))
+		return -1;
+
+	close(fd);
+
+	return 0;
+}
+
+unsigned long perf_event_open_cloexec_flag(void)
+{
+	static bool probed;
+
+	if (!probed) {
+		if (perf_flag_probe() <= 0)
+			flag = 0;
+		probed = true;
+	}
+
+	return flag;
+}
diff --git a/tools/perf/util/cloexec.h b/tools/perf/util/cloexec.h
new file mode 100644
index 00000000000..94a5a7d829d
--- /dev/null
+++ b/tools/perf/util/cloexec.h
@@ -0,0 +1,6 @@
+#ifndef __PERF_CLOEXEC_H
+#define __PERF_CLOEXEC_H
+
+unsigned long perf_event_open_cloexec_flag(void);
+
+#endif /* __PERF_CLOEXEC_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 24519e14ac5..1e5e2e5af6b 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -350,6 +350,16 @@ static int perf_default_core_config(const char *var __maybe_unused,
 	return 0;
 }
 
+static int perf_ui_config(const char *var, const char *value)
+{
+	/* Add other config variables here. */
+	if (!strcmp(var, "ui.show-headers")) {
+		symbol_conf.show_hist_headers = perf_config_bool(var, value);
+		return 0;
+	}
+	return 0;
+}
+
 int perf_default_config(const char *var, const char *value,
 			void *dummy __maybe_unused)
 {
@@ -359,6 +369,9 @@ int perf_default_config(const char *var, const char *value,
 	if (!prefixcmp(var, "hist."))
 		return perf_hist_config(var, value);
 
+	if (!prefixcmp(var, "ui."))
+		return perf_ui_config(var, value);
+
 	/* Add other config variables here. */
 	return 0;
 }
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 55de44ecebe..29d720cf584 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -7,6 +7,7 @@
 
 #include "data.h"
 #include "util.h"
+#include "debug.h"
 
 static bool check_pipe(struct perf_data_file *file)
 {
@@ -65,7 +66,7 @@ static int open_file_read(struct perf_data_file *file)
 		goto out_close;
 
 	if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
-		pr_err("file %s not owned by current user or root\n",
+		pr_err("File %s not owned by current user or root (use -f to override)\n",
 		       file->path);
 		goto out_close;
 	}
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 299b5558650..71d41936263 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -16,11 +16,11 @@
 int verbose;
 bool dump_trace = false, quiet = false;
 
-static int _eprintf(int level, const char *fmt, va_list args)
+static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
 	int ret = 0;
 
-	if (verbose >= level) {
+	if (var >= level) {
 		if (use_browser >= 1)
 			ui_helpline__vshow(fmt, args);
 		else
@@ -30,13 +30,13 @@ static int _eprintf(int level, const char *fmt, va_list args)
 	return ret;
 }
 
-int eprintf(int level, const char *fmt, ...)
+int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
 	int ret;
 
 	va_start(args, fmt);
-	ret = _eprintf(level, fmt, args);
+	ret = _eprintf(level, var, fmt, args);
 	va_end(args);
 
 	return ret;
@@ -51,9 +51,9 @@ void pr_stat(const char *fmt, ...)
 	va_list args;
 
 	va_start(args, fmt);
-	_eprintf(1, fmt, args);
+	_eprintf(1, verbose, fmt, args);
 	va_end(args);
-	eprintf(1, "\n");
+	eprintf(1, verbose, "\n");
 }
 
 int dump_printf(const char *fmt, ...)
@@ -105,3 +105,47 @@ void trace_event(union perf_event *event)
 	}
 	printf(".\n");
 }
+
+static struct debug_variable {
+	const char *name;
+	int *ptr;
+} debug_variables[] = {
+	{ .name = "verbose", .ptr = &verbose },
+	{ .name = NULL, }
+};
+
+int perf_debug_option(const char *str)
+{
+	struct debug_variable *var = &debug_variables[0];
+	char *vstr, *s = strdup(str);
+	int v = 1;
+
+	vstr = strchr(s, '=');
+	if (vstr)
+		*vstr++ = 0;
+
+	while (var->name) {
+		if (!strcmp(s, var->name))
+			break;
+		var++;
+	}
+
+	if (!var->name) {
+		pr_err("Unknown debug variable name '%s'\n", s);
+		free(s);
+		return -1;
+	}
+
+	if (vstr) {
+		v = atoi(vstr);
+		/*
+		 * Allow only values in range (0, 10),
+		 * otherwise set 0.
+		 */
+		v = (v < 0) || (v > 10) ? 0 : v;
+	}
+
+	*var->ptr = v;
+	free(s);
+	return 0;
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 443694c36b0..89fb6b0f7ab 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -11,6 +11,24 @@
 extern int verbose;
 extern bool quiet, dump_trace;
 
+#ifndef pr_fmt
+#define pr_fmt(fmt) fmt
+#endif
+
+#define pr_err(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warning(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+	eprintf(0, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug(fmt, ...) \
+	eprintf(1, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debugN(n, fmt, ...) \
+	eprintf(n, verbose, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
+
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
@@ -19,4 +37,8 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 
 void pr_stat(const char *fmt, ...);
 
+int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+
+int perf_debug_option(const char *str);
+
 #endif	/* __PERF_DEBUG_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 64453d63b97..90d02c661dd 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,3 +1,6 @@
+#include <asm/bug.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include "symbol.h"
 #include "dso.h"
 #include "machine.h"
@@ -136,7 +139,48 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	return ret;
 }
 
-static int open_dso(struct dso *dso, struct machine *machine)
+/*
+ * Global list of open DSOs and the counter.
+ */
+static LIST_HEAD(dso__data_open);
+static long dso__data_open_cnt;
+
+static void dso__list_add(struct dso *dso)
+{
+	list_add_tail(&dso->data.open_entry, &dso__data_open);
+	dso__data_open_cnt++;
+}
+
+static void dso__list_del(struct dso *dso)
+{
+	list_del(&dso->data.open_entry);
+	WARN_ONCE(dso__data_open_cnt <= 0,
+		  "DSO data fd counter out of bounds.");
+	dso__data_open_cnt--;
+}
+
+static void close_first_dso(void);
+
+static int do_open(char *name)
+{
+	int fd;
+
+	do {
+		fd = open(name, O_RDONLY);
+		if (fd >= 0)
+			return fd;
+
+		pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+		if (!dso__data_open_cnt || errno != EMFILE)
+			break;
+
+		close_first_dso();
+	} while (1);
+
+	return -1;
+}
+
+static int __open_dso(struct dso *dso, struct machine *machine)
 {
 	int fd;
 	char *root_dir = (char *)"";
@@ -154,11 +198,130 @@ static int open_dso(struct dso *dso, struct machine *machine)
 		return -EINVAL;
 	}
 
-	fd = open(name, O_RDONLY);
+	fd = do_open(name);
 	free(name);
 	return fd;
 }
 
+static void check_data_close(void);
+
+/**
+ * dso_close - Open DSO data file
+ * @dso: dso object
+ *
+ * Open @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+	int fd = __open_dso(dso, machine);
+
+	if (fd >= 0) {
+		dso__list_add(dso);
+		/*
+		 * Check if we crossed the allowed number
+		 * of opened DSOs and close one if needed.
+		 */
+		check_data_close();
+	}
+
+	return fd;
+}
+
+static void close_data_fd(struct dso *dso)
+{
+	if (dso->data.fd >= 0) {
+		close(dso->data.fd);
+		dso->data.fd = -1;
+		dso->data.file_size = 0;
+		dso__list_del(dso);
+	}
+}
+
+/**
+ * dso_close - Close DSO data file
+ * @dso: dso object
+ *
+ * Close @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static void close_dso(struct dso *dso)
+{
+	close_data_fd(dso);
+}
+
+static void close_first_dso(void)
+{
+	struct dso *dso;
+
+	dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
+	close_dso(dso);
+}
+
+static rlim_t get_fd_limit(void)
+{
+	struct rlimit l;
+	rlim_t limit = 0;
+
+	/* Allow half of the current open fd limit. */
+	if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+		if (l.rlim_cur == RLIM_INFINITY)
+			limit = l.rlim_cur;
+		else
+			limit = l.rlim_cur / 2;
+	} else {
+		pr_err("failed to get fd limit\n");
+		limit = 1;
+	}
+
+	return limit;
+}
+
+static bool may_cache_fd(void)
+{
+	static rlim_t limit;
+
+	if (!limit)
+		limit = get_fd_limit();
+
+	if (limit == RLIM_INFINITY)
+		return true;
+
+	return limit > (rlim_t) dso__data_open_cnt;
+}
+
+/*
+ * Check and close LRU dso if we crossed allowed limit
+ * for opened dso file descriptors. The limit is half
+ * of the RLIMIT_NOFILE files opened.
+*/
+static void check_data_close(void)
+{
+	bool cache_fd = may_cache_fd();
+
+	if (!cache_fd)
+		close_first_dso();
+}
+
+/**
+ * dso__data_close - Close DSO data file
+ * @dso: dso object
+ *
+ * External interface to close @dso's data file descriptor.
+ */
+void dso__data_close(struct dso *dso)
+{
+	close_dso(dso);
+}
+
+/**
+ * dso__data_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.
+ */
 int dso__data_fd(struct dso *dso, struct machine *machine)
 {
 	enum dso_binary_type binary_type_data[] = {
@@ -168,21 +331,44 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND)
-		return open_dso(dso, machine);
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
 
-	do {
-		int fd;
+	if (dso->data.fd >= 0)
+		goto out;
 
+	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
+		dso->data.fd = open_dso(dso, machine);
+		goto out;
+	}
+
+	do {
 		dso->binary_type = binary_type_data[i++];
 
-		fd = open_dso(dso, machine);
-		if (fd >= 0)
-			return fd;
+		dso->data.fd = open_dso(dso, machine);
+		if (dso->data.fd >= 0)
+			goto out;
 
 	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
+out:
+	if (dso->data.fd >= 0)
+		dso->data.status = DSO_DATA_STATUS_OK;
+	else
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+
+	return dso->data.fd;
+}
 
-	return -EINVAL;
+bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
+{
+	u32 flag = 1 << by;
+
+	if (dso->data.status_seen & flag)
+		return true;
+
+	dso->data.status_seen |= flag;
+
+	return false;
 }
 
 static void
@@ -260,16 +446,10 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 }
 
 static ssize_t
-dso_cache__read(struct dso *dso, struct machine *machine,
-		 u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 	ssize_t ret;
-	int fd;
-
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return -1;
 
 	do {
 		u64 cache_offset;
@@ -283,16 +463,16 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
 		ret = -EINVAL;
 
-		if (-1 == lseek(fd, cache_offset, SEEK_SET))
+		if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET))
 			break;
 
-		ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+		ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE);
 		if (ret <= 0)
 			break;
 
 		cache->offset = cache_offset;
 		cache->size   = ret;
-		dso_cache__insert(&dso->cache, cache);
+		dso_cache__insert(&dso->data.cache, cache);
 
 		ret = dso_cache__memcpy(cache, offset, data, size);
 
@@ -301,24 +481,27 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 	if (ret <= 0)
 		free(cache);
 
-	close(fd);
 	return ret;
 }
 
-static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
-			      u64 offset, u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, u64 offset,
+			      u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 
-	cache = dso_cache__find(&dso->cache, offset);
+	cache = dso_cache__find(&dso->data.cache, offset);
 	if (cache)
 		return dso_cache__memcpy(cache, offset, data, size);
 	else
-		return dso_cache__read(dso, machine, offset, data, size);
+		return dso_cache__read(dso, offset, data, size);
 }
 
-ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
-			      u64 offset, u8 *data, ssize_t size)
+/*
+ * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks
+ * in the rb_tree. Any read to already cached data is served
+ * by cached data.
+ */
+static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 {
 	ssize_t r = 0;
 	u8 *p = data;
@@ -326,7 +509,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 	do {
 		ssize_t ret;
 
-		ret = dso_cache_read(dso, machine, offset, p, size);
+		ret = dso_cache_read(dso, offset, p, size);
 		if (ret < 0)
 			return ret;
 
@@ -346,6 +529,89 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 	return r;
 }
 
+static int data_file_size(struct dso *dso)
+{
+	struct stat st;
+
+	if (!dso->data.file_size) {
+		if (fstat(dso->data.fd, &st)) {
+			pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+			return -1;
+		}
+		dso->data.file_size = st.st_size;
+	}
+
+	return 0;
+}
+
+/**
+ * dso__data_size - Return dso data size
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * Return: dso data size
+ */
+off_t dso__data_size(struct dso *dso, struct machine *machine)
+{
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return fd;
+
+	if (data_file_size(dso))
+		return -1;
+
+	/* For now just estimate dso data size is close to file size */
+	return dso->data.file_size;
+}
+
+static ssize_t data_read_offset(struct dso *dso, u64 offset,
+				u8 *data, ssize_t size)
+{
+	if (data_file_size(dso))
+		return -1;
+
+	/* Check the offset sanity. */
+	if (offset > dso->data.file_size)
+		return -1;
+
+	if (offset + size < offset)
+		return -1;
+
+	return cached_read(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_offset - Read data from dso file offset
+ * @dso: dso object
+ * @machine: machine object
+ * @offset: file offset
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso file offset. Open
+ * dso data file and use cached_read to get the data.
+ */
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	if (dso__data_fd(dso, machine) < 0)
+		return -1;
+
+	return data_read_offset(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_addr - Read data from dso address
+ * @dso: dso object
+ * @machine: machine object
+ * @add: virtual memory address
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso address.
+ */
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 			    struct machine *machine, u64 addr,
 			    u8 *data, ssize_t size)
@@ -473,9 +739,12 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(dso, dso->name, false);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
-		dso->cache = RB_ROOT;
+		dso->data.cache = RB_ROOT;
+		dso->data.fd = -1;
+		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->is_64_bit = (sizeof(void *) == 8);
 		dso->loaded = 0;
 		dso->rel = 0;
 		dso->sorted_by_name = 0;
@@ -485,6 +754,7 @@ struct dso *dso__new(const char *name)
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
+		INIT_LIST_HEAD(&dso->data.open_entry);
 	}
 
 	return dso;
@@ -506,7 +776,8 @@ void dso__delete(struct dso *dso)
 		dso->long_name_allocated = false;
 	}
 
-	dso_cache__free(&dso->cache);
+	dso__data_close(dso);
+	dso_cache__free(&dso->data.cache);
 	dso__free_a2l(dso);
 	zfree(&dso->symsrc_filename);
 	free(dso);
@@ -669,3 +940,14 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 
 	return ret;
 }
+
+enum dso_type dso__type(struct dso *dso, struct machine *machine)
+{
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return DSO__TYPE_UNKNOWN;
+
+	return dso__type_fd(fd);
+}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 38efe95a7fd..5e463c0964d 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -5,6 +5,7 @@
 #include <linux/rbtree.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include <linux/bitops.h>
 #include "map.h"
 #include "build-id.h"
 
@@ -40,6 +41,23 @@ enum dso_swap_type {
 	DSO_SWAP__YES,
 };
 
+enum dso_data_status {
+	DSO_DATA_STATUS_ERROR	= -1,
+	DSO_DATA_STATUS_UNKNOWN	= 0,
+	DSO_DATA_STATUS_OK	= 1,
+};
+
+enum dso_data_status_seen {
+	DSO_DATA_STATUS_SEEN_ITRACE,
+};
+
+enum dso_type {
+	DSO__TYPE_UNKNOWN,
+	DSO__TYPE_64BIT,
+	DSO__TYPE_32BIT,
+	DSO__TYPE_X32BIT,
+};
+
 #define DSO__SWAP(dso, type, val)			\
 ({							\
 	type ____r = val;				\
@@ -76,7 +94,6 @@ struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
-	struct rb_root	 cache;
 	void		 *a2l;
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;
@@ -91,6 +108,7 @@ struct dso {
 	u8		 annotate_warned:1;
 	u8		 short_name_allocated:1;
 	u8		 long_name_allocated:1;
+	u8		 is_64_bit:1;
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 rel;
@@ -99,6 +117,17 @@ struct dso {
 	const char	 *long_name;
 	u16		 long_name_len;
 	u16		 short_name_len;
+
+	/* dso data file */
+	struct {
+		struct rb_root	 cache;
+		int		 fd;
+		int		 status;
+		u32		 status_seen;
+		size_t		 file_size;
+		struct list_head open_entry;
+	} data;
+
 	char		 name[0];
 };
 
@@ -141,12 +170,55 @@ char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
 
+/*
+ * The dso__data_* external interface provides following functions:
+ *   dso__data_fd
+ *   dso__data_close
+ *   dso__data_size
+ *   dso__data_read_offset
+ *   dso__data_read_addr
+ *
+ * Please refer to the dso.c object code for each function and
+ * arguments documentation. Following text tries to explain the
+ * dso file descriptor caching.
+ *
+ * The dso__data* interface allows caching of opened file descriptors
+ * to speed up the dso data accesses. The idea is to leave the file
+ * descriptor opened ideally for the whole life of the dso object.
+ *
+ * The current usage of the dso__data_* interface is as follows:
+ *
+ * Get DSO's fd:
+ *   int fd = dso__data_fd(dso, machine);
+ *   USE 'fd' SOMEHOW
+ *
+ * Read DSO's data:
+ *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
+ *   n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE);
+ *
+ * Eventually close DSO's fd:
+ *   dso__data_close(dso);
+ *
+ * It is not necessary to close the DSO object data file. Each time new
+ * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once
+ * it is crossed, the oldest opened DSO object is closed.
+ *
+ * The dso__delete function calls close_dso function to ensure the
+ * data file descriptor gets closed/unmapped before the dso object
+ * is freed.
+ *
+ * TODO
+*/
 int dso__data_fd(struct dso *dso, struct machine *machine);
+void dso__data_close(struct dso *dso);
+
+off_t dso__data_size(struct dso *dso, struct machine *machine);
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size);
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 			    struct machine *machine, u64 addr,
 			    u8 *data, ssize_t size);
+bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by);
 
 struct map *dso__new_map(const char *name);
 struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
@@ -181,4 +253,6 @@ static inline bool dso__is_kcore(struct dso *dso)
 
 void dso__free_a2l(struct dso *dso);
 
+enum dso_type dso__type(struct dso *dso, struct machine *machine);
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 65795b835b3..1398c83d896 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,4 +1,5 @@
 #include <linux/types.h>
+#include <sys/mman.h>
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -178,13 +179,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		return -1;
 	}
 
-	event->header.type = PERF_RECORD_MMAP;
+	event->header.type = PERF_RECORD_MMAP2;
 
 	while (1) {
 		char bf[BUFSIZ];
 		char prot[5];
 		char execname[PATH_MAX];
 		char anonstr[] = "//anon";
+		unsigned int ino;
 		size_t size;
 		ssize_t n;
 
@@ -195,15 +197,20 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
-		       &event->mmap.start, &event->mmap.len, prot,
-		       &event->mmap.pgoff,
-		       execname);
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+		       &event->mmap2.start, &event->mmap2.len, prot,
+		       &event->mmap2.pgoff, &event->mmap2.maj,
+		       &event->mmap2.min,
+		       &ino, execname);
+
 		/*
  		 * Anon maps don't have the execname.
  		 */
-		if (n < 4)
+		if (n < 7)
 			continue;
+
+		event->mmap2.ino = (u64)ino;
+
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
 		 */
@@ -212,6 +219,21 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		else
 			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
 
+		/* map protection and flags bits */
+		event->mmap2.prot = 0;
+		event->mmap2.flags = 0;
+		if (prot[0] == 'r')
+			event->mmap2.prot |= PROT_READ;
+		if (prot[1] == 'w')
+			event->mmap2.prot |= PROT_WRITE;
+		if (prot[2] == 'x')
+			event->mmap2.prot |= PROT_EXEC;
+
+		if (prot[3] == 's')
+			event->mmap2.flags |= MAP_SHARED;
+		else
+			event->mmap2.flags |= MAP_PRIVATE;
+
 		if (prot[2] != 'x') {
 			if (!mmap_data || prot[0] != 'r')
 				continue;
@@ -223,15 +245,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			strcpy(execname, anonstr);
 
 		size = strlen(execname) + 1;
-		memcpy(event->mmap.filename, execname, size);
+		memcpy(event->mmap2.filename, execname, size);
 		size = PERF_ALIGN(size, sizeof(u64));
-		event->mmap.len -= event->mmap.start;
-		event->mmap.header.size = (sizeof(event->mmap) -
-					(sizeof(event->mmap.filename) - size));
-		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-		event->mmap.header.size += machine->id_hdr_size;
-		event->mmap.pid = tgid;
-		event->mmap.tid = pid;
+		event->mmap2.len -= event->mmap.start;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+		event->mmap2.header.size += machine->id_hdr_size;
+		event->mmap2.pid = tgid;
+		event->mmap2.tid = pid;
 
 		if (process(tool, event, &synth_sample, machine) != 0) {
 			rc = -1;
@@ -581,7 +603,14 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
 {
-	return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid);
+	const char *s;
+
+	if (event->header.misc & PERF_RECORD_MISC_COMM_EXEC)
+		s = " exec";
+	else
+		s = "";
+
+	return fprintf(fp, "%s: %s:%d\n", s, event->comm.comm, event->comm.tid);
 }
 
 int perf_event__process_comm(struct perf_tool *tool __maybe_unused,
@@ -612,12 +641,15 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
-			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c %s\n",
+			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n",
 		       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
 		       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
 		       event->mmap2.min, event->mmap2.ino,
 		       event->mmap2.ino_generation,
-		       (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
+		       (event->mmap2.prot & PROT_READ) ? 'r' : '-',
+		       (event->mmap2.prot & PROT_WRITE) ? 'w' : '-',
+		       (event->mmap2.prot & PROT_EXEC) ? 'x' : '-',
+		       (event->mmap2.flags & MAP_SHARED) ? 's' : 'p',
 		       event->mmap2.filename);
 }
 
@@ -756,6 +788,7 @@ try_again:
 		    cpumode == PERF_RECORD_MISC_USER &&
 		    machine && mg != &machine->kmaps) {
 			mg = &machine->kmaps;
+			load_map = true;
 			goto try_again;
 		}
 	} else {
@@ -841,3 +874,45 @@ int perf_event__preprocess_sample(const union perf_event *event,
 
 	return 0;
 }
+
+bool is_bts_event(struct perf_event_attr *attr)
+{
+	return attr->type == PERF_TYPE_HARDWARE &&
+	       (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
+	       attr->sample_period == 1;
+}
+
+bool sample_addr_correlates_sym(struct perf_event_attr *attr)
+{
+	if (attr->type == PERF_TYPE_SOFTWARE &&
+	    (attr->config == PERF_COUNT_SW_PAGE_FAULTS ||
+	     attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
+	     attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ))
+		return true;
+
+	if (is_bts_event(attr))
+		return true;
+
+	return false;
+}
+
+void perf_event__preprocess_sample_addr(union perf_event *event,
+					struct perf_sample *sample,
+					struct machine *machine,
+					struct thread *thread,
+					struct addr_location *al)
+{
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+			      sample->addr, al);
+	if (!al->map)
+		thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
+				      sample->addr, al);
+
+	al->cpu = sample->cpu;
+	al->sym = NULL;
+
+	if (al->map)
+		al->sym = map__find_symbol(al->map, al->addr, NULL);
+}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index d970232cb27..94d6976180d 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -7,6 +7,7 @@
 #include "../perf.h"
 #include "map.h"
 #include "build-id.h"
+#include "perf_regs.h"
 
 struct mmap_event {
 	struct perf_event_header header;
@@ -27,6 +28,8 @@ struct mmap2_event {
 	u32 min;
 	u64 ino;
 	u64 ino_generation;
+	u32 prot;
+	u32 flags;
 	char filename[PATH_MAX];
 };
 
@@ -87,6 +90,10 @@ struct regs_dump {
 	u64 abi;
 	u64 mask;
 	u64 *regs;
+
+	/* Cached values/mask filled by first register access. */
+	u64 cache_regs[PERF_REGS_MAX];
+	u64 cache_mask;
 };
 
 struct stack_dump {
@@ -281,6 +288,16 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  struct addr_location *al,
 				  struct perf_sample *sample);
 
+struct thread;
+
+bool is_bts_event(struct perf_event_attr *attr);
+bool sample_addr_correlates_sym(struct perf_event_attr *attr);
+void perf_event__preprocess_sample_addr(union perf_event *event,
+					struct perf_sample *sample,
+					struct machine *machine,
+					struct thread *thread,
+					struct addr_location *al);
+
 const char *perf_event__name(unsigned int id);
 
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 59ef2802fcf..814e954c131 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -606,12 +606,17 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist,
-			       int idx, int prot, int mask, int fd)
+struct mmap_params {
+	int prot;
+	int mask;
+};
+
+static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
+			       struct mmap_params *mp, int fd)
 {
 	evlist->mmap[idx].prev = 0;
-	evlist->mmap[idx].mask = mask;
-	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
+	evlist->mmap[idx].mask = mp->mask;
+	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
 				      MAP_SHARED, fd, 0);
 	if (evlist->mmap[idx].base == MAP_FAILED) {
 		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
@@ -625,8 +630,8 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-				       int prot, int mask, int cpu, int thread,
-				       int *output)
+				       struct mmap_params *mp, int cpu,
+				       int thread, int *output)
 {
 	struct perf_evsel *evsel;
 
@@ -635,8 +640,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 
 		if (*output == -1) {
 			*output = fd;
-			if (__perf_evlist__mmap(evlist, idx, prot, mask,
-						*output) < 0)
+			if (__perf_evlist__mmap(evlist, idx, mp, *output) < 0)
 				return -1;
 		} else {
 			if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, *output) != 0)
@@ -651,8 +655,8 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 	return 0;
 }
 
-static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
-				     int mask)
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
+				     struct mmap_params *mp)
 {
 	int cpu, thread;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
@@ -663,8 +667,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot,
 		int output = -1;
 
 		for (thread = 0; thread < nr_threads; thread++) {
-			if (perf_evlist__mmap_per_evsel(evlist, cpu, prot, mask,
-							cpu, thread, &output))
+			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
+							thread, &output))
 				goto out_unmap;
 		}
 	}
@@ -677,8 +681,8 @@ out_unmap:
 	return -1;
 }
 
-static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
-					int mask)
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
+					struct mmap_params *mp)
 {
 	int thread;
 	int nr_threads = thread_map__nr(evlist->threads);
@@ -687,8 +691,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot,
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 
-		if (perf_evlist__mmap_per_evsel(evlist, thread, prot, mask, 0,
-						thread, &output))
+		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
+						&output))
 			goto out_unmap;
 	}
 
@@ -793,7 +797,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
 	const struct thread_map *threads = evlist->threads;
-	int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask;
+	struct mmap_params mp = {
+		.prot = PROT_READ | (overwrite ? 0 : PROT_WRITE),
+	};
 
 	if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
 		return -ENOMEM;
@@ -804,7 +810,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	evlist->overwrite = overwrite;
 	evlist->mmap_len = perf_evlist__mmap_size(pages);
 	pr_debug("mmap size %zuB\n", evlist->mmap_len);
-	mask = evlist->mmap_len - page_size - 1;
+	mp.mask = evlist->mmap_len - page_size - 1;
 
 	evlist__for_each(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
@@ -814,9 +820,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	}
 
 	if (cpu_map__empty(cpus))
-		return perf_evlist__mmap_per_thread(evlist, prot, mask);
+		return perf_evlist__mmap_per_thread(evlist, &mp);
 
-	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
+	return perf_evlist__mmap_per_cpu(evlist, &mp);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
@@ -1214,10 +1220,11 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 					     "For your workloads it needs to be <= 1\nHint:\t");
 		}
 		printed += scnprintf(buf + printed, size - printed,
-				     "For system wide tracing it needs to be set to -1");
+				     "For system wide tracing it needs to be set to -1.\n");
 
 		printed += scnprintf(buf + printed, size - printed,
-				    ".\nHint:\tThe current value is %d.", value);
+				    "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n"
+				    "Hint:\tThe current value is %d.", value);
 		break;
 	default:
 		scnprintf(buf, size, "%s", emsg);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5c28d82b76c..21a373ebea2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -29,6 +29,7 @@ static struct {
 	bool sample_id_all;
 	bool exclude_guest;
 	bool mmap2;
+	bool cloexec;
 } perf_missing_features;
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
@@ -589,10 +590,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	}
 
 	/*
-	 * We default some events to a 1 default interval. But keep
+	 * We default some events to have a default interval. But keep
 	 * it a weak assumption overridable by the user.
 	 */
-	if (!attr->sample_period || (opts->user_freq != UINT_MAX &&
+	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
 				     opts->user_interval != ULLONG_MAX)) {
 		if (opts->freq) {
 			perf_evsel__set_sample_bit(evsel, PERIOD);
@@ -623,7 +624,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		attr->mmap_data = track;
 	}
 
-	if (opts->call_graph_enabled)
+	if (opts->call_graph_enabled && !evsel->no_aux_samples)
 		perf_evsel__config_callgraph(evsel, opts);
 
 	if (target__has_cpu(&opts->target))
@@ -637,7 +638,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	     target__has_cpu(&opts->target) || per_cpu))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
-	if (opts->raw_samples) {
+	if (opts->raw_samples && !evsel->no_aux_samples) {
 		perf_evsel__set_sample_bit(evsel, TIME);
 		perf_evsel__set_sample_bit(evsel, RAW);
 		perf_evsel__set_sample_bit(evsel, CPU);
@@ -650,7 +651,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		attr->watermark = 0;
 		attr->wakeup_events = 1;
 	}
-	if (opts->branch_stack) {
+	if (opts->branch_stack && !evsel->no_aux_samples) {
 		perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
 		attr->branch_sample_type = opts->branch_stack;
 	}
@@ -659,6 +660,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		perf_evsel__set_sample_bit(evsel, WEIGHT);
 
 	attr->mmap  = track;
+	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
 	if (opts->sample_transaction)
@@ -680,6 +682,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
 		!opts->initial_delay)
 		attr->enable_on_exec = 1;
+
+	if (evsel->immediate) {
+		attr->disabled = 0;
+		attr->enable_on_exec = 0;
+	}
 }
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -959,6 +966,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 	ret += PRINT_ATTR2(exclude_user, exclude_kernel);
 	ret += PRINT_ATTR2(exclude_hv, exclude_idle);
 	ret += PRINT_ATTR2(mmap, comm);
+	ret += PRINT_ATTR2(mmap2, comm_exec);
 	ret += PRINT_ATTR2(freq, inherit_stat);
 	ret += PRINT_ATTR2(enable_on_exec, task);
 	ret += PRINT_ATTR2(watermark, precise_ip);
@@ -966,7 +974,6 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 	ret += PRINT_ATTR2(exclude_host, exclude_guest);
 	ret += PRINT_ATTR2N("excl.callchain_kern", exclude_callchain_kernel,
 			    "excl.callchain_user", exclude_callchain_user);
-	ret += PRINT_ATTR_U32(mmap2);
 
 	ret += PRINT_ATTR_U32(wakeup_events);
 	ret += PRINT_ATTR_U32(wakeup_watermark);
@@ -988,7 +995,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			      struct thread_map *threads)
 {
 	int cpu, thread;
-	unsigned long flags = 0;
+	unsigned long flags = PERF_FLAG_FD_CLOEXEC;
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
@@ -997,11 +1004,13 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 		return -ENOMEM;
 
 	if (evsel->cgrp) {
-		flags = PERF_FLAG_PID_CGROUP;
+		flags |= PERF_FLAG_PID_CGROUP;
 		pid = evsel->cgrp->fd;
 	}
 
 fallback_missing_features:
+	if (perf_missing_features.cloexec)
+		flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
 	if (perf_missing_features.mmap2)
 		evsel->attr.mmap2 = 0;
 	if (perf_missing_features.exclude_guest)
@@ -1070,7 +1079,10 @@ try_fallback:
 	if (err != -EINVAL || cpu > 0 || thread > 0)
 		goto out_close;
 
-	if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
+	if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) {
+		perf_missing_features.cloexec = true;
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
 		perf_missing_features.mmap2 = true;
 		goto fallback_missing_features;
 	} else if (!perf_missing_features.exclude_guest &&
@@ -1939,6 +1951,7 @@ int perf_evsel__fprintf(struct perf_evsel *evsel,
 		if_print(mmap);
 		if_print(mmap2);
 		if_print(comm);
+		if_print(comm_exec);
 		if_print(freq);
 		if_print(inherit_stat);
 		if_print(enable_on_exec);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a52e9a5bb2d..d7f93ce0ebc 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -83,6 +83,8 @@ struct perf_evsel {
 	int			is_pos;
 	bool 			supported;
 	bool 			needs_swap;
+	bool			no_aux_samples;
+	bool			immediate;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 893f8e2df92..158c787ce0c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -200,6 +200,47 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id,
 	return write_padded(fd, name, name_len + 1, len);
 }
 
+static int __dsos__hit_all(struct list_head *head)
+{
+	struct dso *pos;
+
+	list_for_each_entry(pos, head, node)
+		pos->hit = true;
+
+	return 0;
+}
+
+static int machine__hit_all_dsos(struct machine *machine)
+{
+	int err;
+
+	err = __dsos__hit_all(&machine->kernel_dsos);
+	if (err)
+		return err;
+
+	return __dsos__hit_all(&machine->user_dsos);
+}
+
+int dsos__hit_all(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int err;
+
+	err = machine__hit_all_dsos(&session->machines.host);
+	if (err)
+		return err;
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+		err = machine__hit_all_dsos(pos);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int __dsos__write_buildid_table(struct list_head *head,
 				       struct machine *machine,
 				       pid_t pid, u16 misc, int fd)
@@ -215,9 +256,9 @@ static int __dsos__write_buildid_table(struct list_head *head,
 		if (!pos->hit)
 			continue;
 
-		if (is_vdso_map(pos->short_name)) {
-			name = (char *) VDSO__MAP_NAME;
-			name_len = sizeof(VDSO__MAP_NAME) + 1;
+		if (dso__is_vdso(pos)) {
+			name = pos->short_name;
+			name_len = pos->short_name_len + 1;
 		} else if (dso__is_kcore(pos)) {
 			machine__mmap_name(machine, nm, sizeof(nm));
 			name = nm;
@@ -298,7 +339,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 
 	len = scnprintf(filename, size, "%s%s%s",
 		       debugdir, slash ? "/" : "",
-		       is_vdso ? VDSO__MAP_NAME : realname);
+		       is_vdso ? DSO__NAME_VDSO : realname);
 	if (mkdir_p(filename, 0755))
 		goto out_free;
 
@@ -386,7 +427,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 			       const char *debugdir)
 {
 	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
-	bool is_vdso = is_vdso_map(dso->short_name);
+	bool is_vdso = dso__is_vdso(dso);
 	const char *name = dso->long_name;
 	char nm[PATH_MAX];
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index d08cfe49940..8f5cbaea64a 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -151,6 +151,8 @@ int perf_event__process_build_id(struct perf_tool *tool,
 				 struct perf_session *session);
 bool is_perf_magic(u64 magic);
 
+int dsos__hit_all(struct perf_session *session);
+
 /*
  * arch specific callback
  */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b262b44b7a6..30df6187ee0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -4,6 +4,7 @@
 #include "session.h"
 #include "sort.h"
 #include "evsel.h"
+#include "annotate.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -127,6 +128,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 			       + unresolved_col_width + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
 					   symlen);
+			hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+					   symlen + 1);
 		} else {
 			symlen = unresolved_col_width + 4 + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
@@ -231,6 +234,8 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 		return true;
 
 	he_stat__decay(&he->stat);
+	if (symbol_conf.cumulate_callchain)
+		he_stat__decay(he->stat_acc);
 
 	diff = prev_period - he->stat.period;
 
@@ -276,14 +281,31 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
  * histogram, sorted on item, collects periods
  */
 
-static struct hist_entry *hist_entry__new(struct hist_entry *template)
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+					  bool sample_self)
 {
-	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
-	struct hist_entry *he = zalloc(sizeof(*he) + callchain_size);
+	size_t callchain_size = 0;
+	struct hist_entry *he;
+
+	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+		callchain_size = sizeof(struct callchain_root);
+
+	he = zalloc(sizeof(*he) + callchain_size);
 
 	if (he != NULL) {
 		*he = *template;
 
+		if (symbol_conf.cumulate_callchain) {
+			he->stat_acc = malloc(sizeof(he->stat));
+			if (he->stat_acc == NULL) {
+				free(he);
+				return NULL;
+			}
+			memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+			if (!sample_self)
+				memset(&he->stat, 0, sizeof(he->stat));
+		}
+
 		if (he->ms.map)
 			he->ms.map->referenced = true;
 
@@ -295,6 +317,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
 			 */
 			he->branch_info = malloc(sizeof(*he->branch_info));
 			if (he->branch_info == NULL) {
+				free(he->stat_acc);
 				free(he);
 				return NULL;
 			}
@@ -333,7 +356,8 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 
 static struct hist_entry *add_hist_entry(struct hists *hists,
 					 struct hist_entry *entry,
-					 struct addr_location *al)
+					 struct addr_location *al,
+					 bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -357,7 +381,10 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			he_stat__add_period(&he->stat, period, weight);
+			if (sample_self)
+				he_stat__add_period(&he->stat, period, weight);
+			if (symbol_conf.cumulate_callchain)
+				he_stat__add_period(he->stat_acc, period, weight);
 
 			/*
 			 * This mem info was allocated from sample__resolve_mem
@@ -385,14 +412,17 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(entry);
+	he = hist_entry__new(entry, sample_self);
 	if (!he)
 		return NULL;
 
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
-	he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+	if (sample_self)
+		he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+	if (symbol_conf.cumulate_callchain)
+		he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period);
 	return he;
 }
 
@@ -401,7 +431,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct symbol *sym_parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi,
-				      u64 period, u64 weight, u64 transaction)
+				      u64 period, u64 weight, u64 transaction,
+				      bool sample_self)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -410,9 +441,10 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			.map	= al->map,
 			.sym	= al->sym,
 		},
-		.cpu	= al->cpu,
-		.ip	= al->addr,
-		.level	= al->level,
+		.cpu	 = al->cpu,
+		.cpumode = al->cpumode,
+		.ip	 = al->addr,
+		.level	 = al->level,
 		.stat = {
 			.nr_events = 1,
 			.period	= period,
@@ -426,7 +458,429 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al);
+	return add_hist_entry(hists, &entry, al, sample_self);
+}
+
+static int
+iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+		    struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+			struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_sample *sample = iter->sample;
+	struct mem_info *mi;
+
+	mi = sample__resolve_mem(sample, al);
+	if (mi == NULL)
+		return -ENOMEM;
+
+	iter->priv = mi;
+	return 0;
+}
+
+static int
+iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	u64 cost;
+	struct mem_info *mi = iter->priv;
+	struct hist_entry *he;
+
+	if (mi == NULL)
+		return -EINVAL;
+
+	cost = iter->sample->weight;
+	if (!cost)
+		cost = 1;
+
+	/*
+	 * must pass period=weight in order to get the correct
+	 * sorting from hists__collapse_resort() which is solely
+	 * based on periods. We want sorting be done on nr_events * weight
+	 * and this is indirectly achieved by passing period=weight here
+	 * and the he_stat__add_period() function.
+	 */
+	he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+				cost, cost, 0, true);
+	if (!he)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_mem_entry(struct hist_entry_iter *iter,
+		      struct addr_location *al __maybe_unused)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = iter->he;
+	int err = -EINVAL;
+
+	if (he == NULL)
+		goto out;
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	err = hist_entry__append_callchain(he, iter->sample);
+
+out:
+	/*
+	 * We don't need to free iter->priv (mem_info) here since
+	 * the mem info was either already freed in add_hist_entry() or
+	 * passed to a new hist entry by hist_entry__new().
+	 */
+	iter->priv = NULL;
+
+	iter->he = NULL;
+	return err;
+}
+
+static int
+iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi;
+	struct perf_sample *sample = iter->sample;
+
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return -ENOMEM;
+
+	iter->curr = 0;
+	iter->total = sample->branch_stack->nr;
+
+	iter->priv = bi;
+	return 0;
+}
+
+static int
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+			     struct addr_location *al __maybe_unused)
+{
+	/* to avoid calling callback function */
+	iter->he = NULL;
+
+	return 0;
+}
+
+static int
+iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi = iter->priv;
+	int i = iter->curr;
+
+	if (bi == NULL)
+		return 0;
+
+	if (iter->curr >= iter->total)
+		return 0;
+
+	al->map = bi[i].to.map;
+	al->sym = bi[i].to.sym;
+	al->addr = bi[i].to.addr;
+	return 1;
+}
+
+static int
+iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct branch_info *bi;
+	struct perf_evsel *evsel = iter->evsel;
+	struct hist_entry *he = NULL;
+	int i = iter->curr;
+	int err = 0;
+
+	bi = iter->priv;
+
+	if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+		goto out;
+
+	/*
+	 * The report shows the percentage of total branches captured
+	 * and not events sampled. Thus we use a pseudo period of 1.
+	 */
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
+				1, 1, 0, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+out:
+	iter->he = he;
+	iter->curr++;
+	return err;
+}
+
+static int
+iter_finish_branch_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return iter->curr >= iter->total ? 0 : -1;
+}
+
+static int
+iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused,
+			  struct addr_location *al __maybe_unused)
+{
+	return 0;
+}
+
+static int
+iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry *he;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	return 0;
+}
+
+static int
+iter_finish_normal_entry(struct hist_entry_iter *iter,
+			 struct addr_location *al __maybe_unused)
+{
+	struct hist_entry *he = iter->he;
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+
+	if (he == NULL)
+		return 0;
+
+	iter->he = NULL;
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return hist_entry__append_callchain(he, sample);
+}
+
+static int
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
+			      struct addr_location *al __maybe_unused)
+{
+	struct hist_entry **he_cache;
+
+	callchain_cursor_commit(&callchain_cursor);
+
+	/*
+	 * This is for detecting cycles or recursions so that they're
+	 * cumulated only one time to prevent entries more than 100%
+	 * overhead.
+	 */
+	he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
+	if (he_cache == NULL)
+		return -ENOMEM;
+
+	iter->priv = he_cache;
+	iter->curr = 0;
+
+	return 0;
+}
+
+static int
+iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
+				 struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry *he;
+	int err = 0;
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, true);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	he_cache[iter->curr++] = he;
+
+	callchain_append(he->callchain, &callchain_cursor, sample->period);
+
+	/*
+	 * We need to re-initialize the cursor since callchain_append()
+	 * advanced the cursor to the end.
+	 */
+	callchain_cursor_commit(&callchain_cursor);
+
+	hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+	return err;
+}
+
+static int
+iter_next_cumulative_entry(struct hist_entry_iter *iter,
+			   struct addr_location *al)
+{
+	struct callchain_cursor_node *node;
+
+	node = callchain_cursor_current(&callchain_cursor);
+	if (node == NULL)
+		return 0;
+
+	return fill_callchain_info(al, node, iter->hide_unresolved);
+}
+
+static int
+iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
+			       struct addr_location *al)
+{
+	struct perf_evsel *evsel = iter->evsel;
+	struct perf_sample *sample = iter->sample;
+	struct hist_entry **he_cache = iter->priv;
+	struct hist_entry *he;
+	struct hist_entry he_tmp = {
+		.cpu = al->cpu,
+		.thread = al->thread,
+		.comm = thread__comm(al->thread),
+		.ip = al->addr,
+		.ms = {
+			.map = al->map,
+			.sym = al->sym,
+		},
+		.parent = iter->parent,
+	};
+	int i;
+	struct callchain_cursor cursor;
+
+	callchain_cursor_snapshot(&cursor, &callchain_cursor);
+
+	callchain_cursor_advance(&callchain_cursor);
+
+	/*
+	 * Check if there's duplicate entries in the callchain.
+	 * It's possible that it has cycles or recursive calls.
+	 */
+	for (i = 0; i < iter->curr; i++) {
+		if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
+			/* to avoid calling callback function */
+			iter->he = NULL;
+			return 0;
+		}
+	}
+
+	he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+				sample->period, sample->weight,
+				sample->transaction, false);
+	if (he == NULL)
+		return -ENOMEM;
+
+	iter->he = he;
+	he_cache[iter->curr++] = he;
+
+	callchain_append(he->callchain, &cursor, sample->period);
+	return 0;
+}
+
+static int
+iter_finish_cumulative_entry(struct hist_entry_iter *iter,
+			     struct addr_location *al __maybe_unused)
+{
+	zfree(&iter->priv);
+	iter->he = NULL;
+
+	return 0;
+}
+
+const struct hist_iter_ops hist_iter_mem = {
+	.prepare_entry 		= iter_prepare_mem_entry,
+	.add_single_entry 	= iter_add_single_mem_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_mem_entry,
+};
+
+const struct hist_iter_ops hist_iter_branch = {
+	.prepare_entry 		= iter_prepare_branch_entry,
+	.add_single_entry 	= iter_add_single_branch_entry,
+	.next_entry 		= iter_next_branch_entry,
+	.add_next_entry 	= iter_add_next_branch_entry,
+	.finish_entry 		= iter_finish_branch_entry,
+};
+
+const struct hist_iter_ops hist_iter_normal = {
+	.prepare_entry 		= iter_prepare_normal_entry,
+	.add_single_entry 	= iter_add_single_normal_entry,
+	.next_entry 		= iter_next_nop_entry,
+	.add_next_entry 	= iter_add_next_nop_entry,
+	.finish_entry 		= iter_finish_normal_entry,
+};
+
+const struct hist_iter_ops hist_iter_cumulative = {
+	.prepare_entry 		= iter_prepare_cumulative_entry,
+	.add_single_entry 	= iter_add_single_cumulative_entry,
+	.next_entry 		= iter_next_cumulative_entry,
+	.add_next_entry 	= iter_add_next_cumulative_entry,
+	.finish_entry 		= iter_finish_cumulative_entry,
+};
+
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth, void *arg)
+{
+	int err, err2;
+
+	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
+					max_stack_depth);
+	if (err)
+		return err;
+
+	iter->evsel = evsel;
+	iter->sample = sample;
+
+	err = iter->ops->prepare_entry(iter, al);
+	if (err)
+		goto out;
+
+	err = iter->ops->add_single_entry(iter, al);
+	if (err)
+		goto out;
+
+	if (iter->he && iter->add_entry_cb) {
+		err = iter->add_entry_cb(iter, al, true, arg);
+		if (err)
+			goto out;
+	}
+
+	while (iter->ops->next_entry(iter, al)) {
+		err = iter->ops->add_next_entry(iter, al);
+		if (err)
+			break;
+
+		if (iter->he && iter->add_entry_cb) {
+			err = iter->add_entry_cb(iter, al, false, arg);
+			if (err)
+				goto out;
+		}
+	}
+
+out:
+	err2 = iter->ops->finish_entry(iter, al);
+	if (!err)
+		err = err2;
+
+	return err;
 }
 
 int64_t
@@ -469,6 +923,7 @@ void hist_entry__free(struct hist_entry *he)
 {
 	zfree(&he->branch_info);
 	zfree(&he->mem_info);
+	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	free(he);
 }
@@ -494,6 +949,8 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 
 		if (!cmp) {
 			he_stat__add_stat(&iter->stat, &he->stat);
+			if (symbol_conf.cumulate_callchain)
+				he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
 			if (symbol_conf.use_callchain) {
 				callchain_cursor_reset(&callchain_cursor);
@@ -800,6 +1257,13 @@ void hists__inc_nr_events(struct hists *hists, u32 type)
 	events_stats__inc(&hists->stats, type);
 }
 
+void hists__inc_nr_samples(struct hists *hists, bool filtered)
+{
+	events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE);
+	if (!filtered)
+		hists->stats.nr_non_filtered_samples++;
+}
+
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 						 struct hist_entry *pair)
 {
@@ -831,7 +1295,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 			p = &(*p)->rb_right;
 	}
 
-	he = hist_entry__new(pair);
+	he = hist_entry__new(pair, true);
 	if (he) {
 		memset(&he->stat, 0, sizeof(he->stat));
 		he->hists = hists;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index a8418d19808..742f49a8572 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -72,6 +72,7 @@ enum hist_column {
 	HISTC_MEM_TLB,
 	HISTC_MEM_LVL,
 	HISTC_MEM_SNOOP,
+	HISTC_MEM_DCACHELINE,
 	HISTC_TRANSACTION,
 	HISTC_NR_COLS, /* Last entry */
 };
@@ -96,12 +97,50 @@ struct hists {
 	u16			col_len[HISTC_NR_COLS];
 };
 
+struct hist_entry_iter;
+
+struct hist_iter_ops {
+	int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *);
+	int (*finish_entry)(struct hist_entry_iter *, struct addr_location *);
+};
+
+struct hist_entry_iter {
+	int total;
+	int curr;
+
+	bool hide_unresolved;
+
+	struct perf_evsel *evsel;
+	struct perf_sample *sample;
+	struct hist_entry *he;
+	struct symbol *parent;
+	void *priv;
+
+	const struct hist_iter_ops *ops;
+	/* user-defined callback function (optional) */
+	int (*add_entry_cb)(struct hist_entry_iter *iter,
+			    struct addr_location *al, bool single, void *arg);
+};
+
+extern const struct hist_iter_ops hist_iter_normal;
+extern const struct hist_iter_ops hist_iter_branch;
+extern const struct hist_iter_ops hist_iter_mem;
+extern const struct hist_iter_ops hist_iter_cumulative;
+
 struct hist_entry *__hists__add_entry(struct hists *hists,
 				      struct addr_location *al,
 				      struct symbol *parent,
 				      struct branch_info *bi,
 				      struct mem_info *mi, u64 period,
-				      u64 weight, u64 transaction);
+				      u64 weight, u64 transaction,
+				      bool sample_self);
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+			 struct perf_evsel *evsel, struct perf_sample *sample,
+			 int max_stack_depth, void *arg);
+
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__transaction_len(void);
@@ -119,6 +158,7 @@ u64 hists__total_period(struct hists *hists);
 void hists__reset_stats(struct hists *hists);
 void hists__inc_stats(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *hists, u32 type);
+void hists__inc_nr_samples(struct hists *hists, bool filtered);
 void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
@@ -166,6 +206,7 @@ struct perf_hpp_fmt {
 
 	struct list_head list;
 	struct list_head sort_list;
+	bool elide;
 };
 
 extern struct list_head perf_hpp__list;
@@ -192,6 +233,7 @@ enum {
 	PERF_HPP__OVERHEAD_US,
 	PERF_HPP__OVERHEAD_GUEST_SYS,
 	PERF_HPP__OVERHEAD_GUEST_US,
+	PERF_HPP__OVERHEAD_ACC,
 	PERF_HPP__SAMPLES,
 	PERF_HPP__PERIOD,
 
@@ -200,7 +242,11 @@ enum {
 
 void perf_hpp__init(void);
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
+void perf_hpp__column_disable(unsigned col);
+void perf_hpp__cancel_cumulate(void);
+
 void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
 void perf_hpp__setup_output_field(void);
 void perf_hpp__reset_output_field(void);
@@ -208,7 +254,12 @@ void perf_hpp__append_sort_keys(void);
 
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
-bool perf_hpp__should_skip(struct perf_hpp_fmt *format);
+
+static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+{
+	return format->elide;
+}
+
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
 
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
@@ -218,6 +269,9 @@ typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	       hpp_field_fn get_field, const char *fmt,
 	       hpp_snprint_fn print_fn, bool fmt_percent);
+int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
+		   hpp_field_fn get_field, const char *fmt,
+		   hpp_snprint_fn print_fn, bool fmt_percent);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index 9844c31b7c2..09e8e7aea7c 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -94,27 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
 	return (i >= ssize) ? (ssize - 1) : i;
 }
 
-int eprintf(int level,
-	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
-
-#ifndef pr_fmt
-#define pr_fmt(fmt) fmt
-#endif
-
-#define pr_err(fmt, ...) \
-	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warning(fmt, ...) \
-	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_info(fmt, ...) \
-	eprintf(0, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug(fmt, ...) \
-	eprintf(1, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debugN(n, fmt, ...) \
-	eprintf(n, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug2(fmt, ...) pr_debugN(2, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
-
 /*
  * This looks more complex than it should be. But we need to
  * get the type for the ~ right in round_down (it needs to be
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
new file mode 100644
index 00000000000..0b5a8cd2ee7
--- /dev/null
+++ b/tools/perf/util/kvm-stat.h
@@ -0,0 +1,140 @@
+#ifndef __PERF_KVM_STAT_H
+#define __PERF_KVM_STAT_H
+
+#include "../perf.h"
+#include "evsel.h"
+#include "evlist.h"
+#include "session.h"
+#include "tool.h"
+#include "stat.h"
+
+struct event_key {
+	#define INVALID_KEY     (~0ULL)
+	u64 key;
+	int info;
+	struct exit_reasons_table *exit_reasons;
+};
+
+struct kvm_event_stats {
+	u64 time;
+	struct stats stats;
+};
+
+struct kvm_event {
+	struct list_head hash_entry;
+	struct rb_node rb;
+
+	struct event_key key;
+
+	struct kvm_event_stats total;
+
+	#define DEFAULT_VCPU_NUM 8
+	int max_vcpu;
+	struct kvm_event_stats *vcpu;
+};
+
+typedef int (*key_cmp_fun)(struct kvm_event*, struct kvm_event*, int);
+
+struct kvm_event_key {
+	const char *name;
+	key_cmp_fun key;
+};
+
+struct perf_kvm_stat;
+
+struct child_event_ops {
+	void (*get_key)(struct perf_evsel *evsel,
+			struct perf_sample *sample,
+			struct event_key *key);
+	const char *name;
+};
+
+struct kvm_events_ops {
+	bool (*is_begin_event)(struct perf_evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key);
+	bool (*is_end_event)(struct perf_evsel *evsel,
+			     struct perf_sample *sample, struct event_key *key);
+	struct child_event_ops *child_ops;
+	void (*decode_key)(struct perf_kvm_stat *kvm, struct event_key *key,
+			   char *decode);
+	const char *name;
+};
+
+struct exit_reasons_table {
+	unsigned long exit_code;
+	const char *reason;
+};
+
+#define EVENTS_BITS		12
+#define EVENTS_CACHE_SIZE	(1UL << EVENTS_BITS)
+
+struct perf_kvm_stat {
+	struct perf_tool    tool;
+	struct record_opts  opts;
+	struct perf_evlist  *evlist;
+	struct perf_session *session;
+
+	const char *file_name;
+	const char *report_event;
+	const char *sort_key;
+	int trace_vcpu;
+
+	struct exit_reasons_table *exit_reasons;
+	const char *exit_reasons_isa;
+
+	struct kvm_events_ops *events_ops;
+	key_cmp_fun compare;
+	struct list_head kvm_events_cache[EVENTS_CACHE_SIZE];
+
+	u64 total_time;
+	u64 total_count;
+	u64 lost_events;
+	u64 duration;
+
+	const char *pid_str;
+	struct intlist *pid_list;
+
+	struct rb_root result;
+
+	int timerfd;
+	unsigned int display_time;
+	bool live;
+};
+
+struct kvm_reg_events_ops {
+	const char *name;
+	struct kvm_events_ops *ops;
+};
+
+void exit_event_get_key(struct perf_evsel *evsel,
+			struct perf_sample *sample,
+			struct event_key *key);
+bool exit_event_begin(struct perf_evsel *evsel,
+		      struct perf_sample *sample,
+		      struct event_key *key);
+bool exit_event_end(struct perf_evsel *evsel,
+		    struct perf_sample *sample,
+		    struct event_key *key);
+void exit_event_decode_key(struct perf_kvm_stat *kvm,
+			   struct event_key *key,
+			   char *decode);
+
+bool kvm_exit_event(struct perf_evsel *evsel);
+bool kvm_entry_event(struct perf_evsel *evsel);
+
+#define define_exit_reasons_table(name, symbols)	\
+	static struct exit_reasons_table name[] = {	\
+		symbols, { -1, NULL }			\
+	}
+
+/*
+ * arch specific callbacks and data structures
+ */
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid);
+
+extern const char * const kvm_events_tp[];
+extern struct kvm_reg_events_ops kvm_reg_events_ops[];
+extern const char * const kvm_skip_events[];
+
+#endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7409ac8de51..16bba9fff2c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -8,6 +8,7 @@
 #include "sort.h"
 #include "strlist.h"
 #include "thread.h"
+#include "vdso.h"
 #include <stdbool.h>
 #include <symbol/kallsyms.h>
 #include "unwind.h"
@@ -23,6 +24,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	INIT_LIST_HEAD(&machine->dead_threads);
 	machine->last_match = NULL;
 
+	machine->vdso_info = NULL;
+
 	machine->kmaps.machine = machine;
 	machine->pid = pid;
 
@@ -34,7 +37,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 		return -ENOMEM;
 
 	if (pid != HOST_KERNEL_ID) {
-		struct thread *thread = machine__findnew_thread(machine, 0,
+		struct thread *thread = machine__findnew_thread(machine, -1,
 								pid);
 		char comm[64];
 
@@ -45,6 +48,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 		thread__set_comm(thread, comm, 0);
 	}
 
+	machine->current_tid = NULL;
+
 	return 0;
 }
 
@@ -103,7 +108,9 @@ void machine__exit(struct machine *machine)
 	map_groups__exit(&machine->kmaps);
 	dsos__delete(&machine->user_dsos);
 	dsos__delete(&machine->kernel_dsos);
+	vdso__exit(machine);
 	zfree(&machine->root_dir);
+	zfree(&machine->current_tid);
 }
 
 void machine__delete(struct machine *machine)
@@ -272,6 +279,52 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 	return;
 }
 
+static void machine__update_thread_pid(struct machine *machine,
+				       struct thread *th, pid_t pid)
+{
+	struct thread *leader;
+
+	if (pid == th->pid_ || pid == -1 || th->pid_ != -1)
+		return;
+
+	th->pid_ = pid;
+
+	if (th->pid_ == th->tid)
+		return;
+
+	leader = machine__findnew_thread(machine, th->pid_, th->pid_);
+	if (!leader)
+		goto out_err;
+
+	if (!leader->mg)
+		leader->mg = map_groups__new();
+
+	if (!leader->mg)
+		goto out_err;
+
+	if (th->mg == leader->mg)
+		return;
+
+	if (th->mg) {
+		/*
+		 * Maps are created from MMAP events which provide the pid and
+		 * tid.  Consequently there never should be any maps on a thread
+		 * with an unknown pid.  Just print an error if there are.
+		 */
+		if (!map_groups__empty(th->mg))
+			pr_err("Discarding thread maps for %d:%d\n",
+			       th->pid_, th->tid);
+		map_groups__delete(th->mg);
+	}
+
+	th->mg = map_groups__get(leader->mg);
+
+	return;
+
+out_err:
+	pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
+}
+
 static struct thread *__machine__findnew_thread(struct machine *machine,
 						pid_t pid, pid_t tid,
 						bool create)
@@ -285,10 +338,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 	 * so most of the time we dont have to look up
 	 * the full rbtree:
 	 */
-	if (machine->last_match && machine->last_match->tid == tid) {
-		if (pid && pid != machine->last_match->pid_)
-			machine->last_match->pid_ = pid;
-		return machine->last_match;
+	th = machine->last_match;
+	if (th && th->tid == tid) {
+		machine__update_thread_pid(machine, th, pid);
+		return th;
 	}
 
 	while (*p != NULL) {
@@ -297,8 +350,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 
 		if (th->tid == tid) {
 			machine->last_match = th;
-			if (pid && pid != th->pid_)
-				th->pid_ = pid;
+			machine__update_thread_pid(machine, th, pid);
 			return th;
 		}
 
@@ -325,8 +377,10 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * within thread__init_map_groups to find the thread
 		 * leader and that would screwed the rb tree.
 		 */
-		if (thread__init_map_groups(th, machine))
+		if (thread__init_map_groups(th, machine)) {
+			thread__delete(th);
 			return NULL;
+		}
 	}
 
 	return th;
@@ -496,18 +550,6 @@ struct process_args {
 	u64 start;
 };
 
-static int symbol__in_kernel(void *arg, const char *name,
-			     char type __maybe_unused, u64 start)
-{
-	struct process_args *args = arg;
-
-	if (strchr(name, '['))
-		return 0;
-
-	args->start = start;
-	return 1;
-}
-
 static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
 					   size_t bufsz)
 {
@@ -517,27 +559,41 @@ static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
 		scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir);
 }
 
-/* Figure out the start address of kernel map from /proc/kallsyms */
-static u64 machine__get_kernel_start_addr(struct machine *machine)
+const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
+
+/* Figure out the start address of kernel map from /proc/kallsyms.
+ * Returns the name of the start symbol in *symbol_name. Pass in NULL as
+ * symbol_name if it's not that important.
+ */
+static u64 machine__get_kernel_start_addr(struct machine *machine,
+					  const char **symbol_name)
 {
 	char filename[PATH_MAX];
-	struct process_args args;
+	int i;
+	const char *name;
+	u64 addr = 0;
 
 	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return 0;
 
-	if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
-		return 0;
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr = kallsyms__get_function_start(filename, name);
+		if (addr)
+			break;
+	}
 
-	return args.start;
+	if (symbol_name)
+		*symbol_name = name;
+
+	return addr;
 }
 
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	enum map_type type;
-	u64 start = machine__get_kernel_start_addr(machine);
+	u64 start = machine__get_kernel_start_addr(machine, NULL);
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
@@ -852,23 +908,11 @@ static int machine__create_modules(struct machine *machine)
 	return 0;
 }
 
-const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
-
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
-	char filename[PATH_MAX];
 	const char *name;
-	u64 addr = 0;
-	int i;
-
-	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
-
-	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
-		addr = kallsyms__get_function_start(filename, name);
-		if (addr)
-			break;
-	}
+	u64 addr = machine__get_kernel_start_addr(machine, &name);
 	if (!addr)
 		return -1;
 
@@ -1055,12 +1099,14 @@ int machine__process_mmap2_event(struct machine *machine,
 	else
 		type = MAP__FUNCTION;
 
-	map = map__new(&machine->user_dsos, event->mmap2.start,
+	map = map__new(machine, event->mmap2.start,
 			event->mmap2.len, event->mmap2.pgoff,
 			event->mmap2.pid, event->mmap2.maj,
 			event->mmap2.min, event->mmap2.ino,
 			event->mmap2.ino_generation,
-			event->mmap2.filename, type);
+			event->mmap2.prot,
+			event->mmap2.flags,
+			event->mmap2.filename, type, thread);
 
 	if (map == NULL)
 		goto out_problem;
@@ -1103,11 +1149,11 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 	else
 		type = MAP__FUNCTION;
 
-	map = map__new(&machine->user_dsos, event->mmap.start,
+	map = map__new(machine, event->mmap.start,
 			event->mmap.len, event->mmap.pgoff,
-			event->mmap.pid, 0, 0, 0, 0,
+			event->mmap.pid, 0, 0, 0, 0, 0, 0,
 			event->mmap.filename,
-			type);
+			type, thread);
 
 	if (map == NULL)
 		goto out_problem;
@@ -1289,7 +1335,9 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 	u8 cpumode = PERF_RECORD_MISC_USER;
 	int chain_nr = min(max_stack, (int)chain->nr);
 	int i;
+	int j;
 	int err;
+	int skip_idx __maybe_unused;
 
 	callchain_cursor_reset(&callchain_cursor);
 
@@ -1298,14 +1346,26 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 		return 0;
 	}
 
+	/*
+	 * Based on DWARF debug information, some architectures skip
+	 * a callchain entry saved by the kernel.
+	 */
+	skip_idx = arch_skip_callchain_idx(machine, thread, chain);
+
 	for (i = 0; i < chain_nr; i++) {
 		u64 ip;
 		struct addr_location al;
 
 		if (callchain_param.order == ORDER_CALLEE)
-			ip = chain->ips[i];
+			j = i;
 		else
-			ip = chain->ips[chain->nr - i - 1];
+			j = chain->nr - i - 1;
+
+#ifdef HAVE_SKIP_CALLCHAIN_IDX
+		if (j == skip_idx)
+			continue;
+#endif
+		ip = chain->ips[j];
 
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {
@@ -1428,3 +1488,46 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too
 	/* command specified */
 	return 0;
 }
+
+pid_t machine__get_current_tid(struct machine *machine, int cpu)
+{
+	if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid)
+		return -1;
+
+	return machine->current_tid[cpu];
+}
+
+int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
+			     pid_t tid)
+{
+	struct thread *thread;
+
+	if (cpu < 0)
+		return -EINVAL;
+
+	if (!machine->current_tid) {
+		int i;
+
+		machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t));
+		if (!machine->current_tid)
+			return -ENOMEM;
+		for (i = 0; i < MAX_NR_CPUS; i++)
+			machine->current_tid[i] = -1;
+	}
+
+	if (cpu >= MAX_NR_CPUS) {
+		pr_err("Requested CPU %d too large. ", cpu);
+		pr_err("Consider raising MAX_NR_CPUS\n");
+		return -EINVAL;
+	}
+
+	machine->current_tid[cpu] = tid;
+
+	thread = machine__findnew_thread(machine, pid, tid);
+	if (!thread)
+		return -ENOMEM;
+
+	thread->cpu = cpu;
+
+	return 0;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index c8c74a11939..b972824e629 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -20,6 +20,8 @@ union perf_event;
 
 extern const char *ref_reloc_sym_names[];
 
+struct vdso_info;
+
 struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
@@ -28,11 +30,13 @@ struct machine {
 	struct rb_root	  threads;
 	struct list_head  dead_threads;
 	struct thread	  *last_match;
+	struct vdso_info  *vdso_info;
 	struct list_head  user_dsos;
 	struct list_head  kernel_dsos;
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
 	symbol_filter_t	  symbol_filter;
+	pid_t		  *current_tid;
 };
 
 static inline
@@ -191,4 +195,8 @@ int machine__synthesize_threads(struct machine *machine, struct target *target,
 					     perf_event__process, data_mmap);
 }
 
+pid_t machine__get_current_tid(struct machine *machine, int cpu);
+int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
+			     pid_t tid);
+
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8ccbb32eda2..31b8905dd86 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -12,6 +12,8 @@
 #include "vdso.h"
 #include "build-id.h"
 #include "util.h"
+#include "debug.h"
+#include "machine.h"
 #include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
@@ -136,10 +138,10 @@ void map__init(struct map *map, enum map_type type,
 	map->erange_warned = false;
 }
 
-struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
+struct map *map__new(struct machine *machine, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
-		     u64 ino_gen, char *filename,
-		     enum map_type type)
+		     u64 ino_gen, u32 prot, u32 flags, char *filename,
+		     enum map_type type, struct thread *thread)
 {
 	struct map *map = malloc(sizeof(*map));
 
@@ -157,6 +159,8 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		map->min = d_min;
 		map->ino = ino;
 		map->ino_generation = ino_gen;
+		map->prot = prot;
+		map->flags = flags;
 
 		if ((anon || no_dso) && type == MAP__FUNCTION) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
@@ -170,9 +174,9 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 
 		if (vdso) {
 			pgoff = 0;
-			dso = vdso__dso_findnew(dsos__list);
+			dso = vdso__dso_findnew(machine, thread);
 		} else
-			dso = __dsos__findnew(dsos__list, filename);
+			dso = __dsos__findnew(&machine->user_dsos, filename);
 
 		if (dso == NULL)
 			goto out_delete;
@@ -452,6 +456,20 @@ void map_groups__exit(struct map_groups *mg)
 	}
 }
 
+bool map_groups__empty(struct map_groups *mg)
+{
+	int i;
+
+	for (i = 0; i < MAP__NR_TYPES; ++i) {
+		if (maps__first(&mg->maps[i]))
+			return false;
+		if (!list_empty(&mg->removed_maps[i]))
+			return false;
+	}
+
+	return true;
+}
+
 struct map_groups *map_groups__new(void)
 {
 	struct map_groups *mg = malloc(sizeof(*mg));
@@ -552,8 +570,8 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 	return ams->sym ? 0 : -1;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg,
-				  enum map_type type, int verbose, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+				  FILE *fp)
 {
 	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
 	struct rb_node *nd;
@@ -571,17 +589,16 @@ size_t __map_groups__fprintf_maps(struct map_groups *mg,
 	return printed;
 }
 
-size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp)
+static size_t map_groups__fprintf_maps(struct map_groups *mg, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(mg, i, verbose, fp);
+		printed += __map_groups__fprintf_maps(mg, i, fp);
 	return printed;
 }
 
 static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
-						 enum map_type type,
-						 int verbose, FILE *fp)
+						 enum map_type type, FILE *fp)
 {
 	struct map *pos;
 	size_t printed = 0;
@@ -598,23 +615,23 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
 }
 
 static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
-					       int verbose, FILE *fp)
+					       FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp);
+		printed += __map_groups__fprintf_removed_maps(mg, i, fp);
 	return printed;
 }
 
-size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 {
-	size_t printed = map_groups__fprintf_maps(mg, verbose, fp);
+	size_t printed = map_groups__fprintf_maps(mg, fp);
 	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(mg, verbose, fp);
+	return printed + map_groups__fprintf_removed_maps(mg, fp);
 }
 
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-				   int verbose, FILE *fp)
+				   FILE *fp)
 {
 	struct rb_root *root = &mg->maps[map->type];
 	struct rb_node *next = rb_first(root);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index ae2d4511058..2f83954af05 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -35,6 +35,8 @@ struct map {
 	bool			referenced;
 	bool			erange_warned;
 	u32			priv;
+	u32			prot;
+	u32			flags;
 	u64			pgoff;
 	u64			reloc;
 	u32			maj, min; /* only valid for MMAP2 record */
@@ -64,6 +66,7 @@ struct map_groups {
 
 struct map_groups *map_groups__new(void);
 void map_groups__delete(struct map_groups *mg);
+bool map_groups__empty(struct map_groups *mg);
 
 static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
@@ -101,6 +104,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip);
 u64 map__objdump_2mem(struct map *map, u64 ip);
 
 struct symbol;
+struct thread;
 
 /* map__for_each_symbol - iterate over the symbols in the given map
  *
@@ -116,10 +120,10 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
-struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
+struct map *map__new(struct machine *machine, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
-		     u64 ino_gen,
-		     char *filename, enum map_type type);
+		     u64 ino_gen, u32 prot, u32 flags,
+		     char *filename, enum map_type type, struct thread *thread);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
 struct map *map__clone(struct map *map);
@@ -139,8 +143,8 @@ void map__fixup_end(struct map *map);
 
 void map__reloc_vmlinux(struct map *map);
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg,
-				  enum map_type type, int verbose, FILE *fp);
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+				  FILE *fp);
 void maps__insert(struct rb_root *maps, struct map *map);
 void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
@@ -150,8 +154,7 @@ void map_groups__init(struct map_groups *mg);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type);
-size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp);
-size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp);
+size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
 
 int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
 				     u64 addr);
@@ -208,7 +211,7 @@ struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
 }
 
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-				   int verbose, FILE *fp);
+				   FILE *fp);
 
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index d8dac8ac5f3..b59ba858e73 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -98,6 +98,7 @@ struct option {
 	parse_opt_cb *callback;
 	intptr_t defval;
 	bool *set;
+	void *data;
 };
 
 #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
@@ -131,6 +132,10 @@ struct option {
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
 	.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
 	.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
+#define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
+	  .value = (v), (a), .help = (h), .callback = (f), \
+	  .flags = PARSE_OPT_OPTARG, .data = (d) }
 
 /* parse_options() will filter out the processed options and leave the
  * non-option argments in argv[].
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index a3539ef30b1..43168fb0d9a 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,11 +1,15 @@
 #include <errno.h>
 #include "perf_regs.h"
+#include "event.h"
 
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
 	int i, idx = 0;
 	u64 mask = regs->mask;
 
+	if (regs->cache_mask & (1 << id))
+		goto out;
+
 	if (!(mask & (1 << id)))
 		return -EINVAL;
 
@@ -14,6 +18,10 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 			idx++;
 	}
 
-	*valp = regs->regs[idx];
+	regs->cache_mask |= (1 << id);
+	regs->cache_regs[id] = regs->regs[idx];
+
+out:
+	*valp = regs->cache_regs[id];
 	return 0;
 }
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 79c78f74e0c..980dbf76bc9 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -2,7 +2,8 @@
 #define __PERF_REGS_H
 
 #include <linux/types.h>
-#include "event.h"
+
+struct regs_dump;
 
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
@@ -11,6 +12,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
 
 #else
 #define PERF_REGS_MASK	0
+#define PERF_REGS_MAX	0
 
 static inline const char *perf_reg_name(int id __maybe_unused)
 {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 0d1542f33d8..9a0a1839a37 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -628,11 +628,11 @@ static int __show_line_range(struct line_range *lr, const char *module)
 
 	ret = debuginfo__find_line_range(dinfo, lr);
 	debuginfo__delete(dinfo);
-	if (ret == 0) {
+	if (ret == 0 || ret == -ENOENT) {
 		pr_warning("Specified source line is not found.\n");
 		return -ENOENT;
 	} else if (ret < 0) {
-		pr_warning("Debuginfo analysis failed. (%d)\n", ret);
+		pr_warning("Debuginfo analysis failed.\n");
 		return ret;
 	}
 
@@ -641,7 +641,7 @@ static int __show_line_range(struct line_range *lr, const char *module)
 	ret = get_real_path(tmp, lr->comp_dir, &lr->path);
 	free(tmp);	/* Free old path */
 	if (ret < 0) {
-		pr_warning("Failed to find source file. (%d)\n", ret);
+		pr_warning("Failed to find source file path.\n");
 		return ret;
 	}
 
@@ -721,9 +721,14 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
 						max_vls, externs);
 	if (ret <= 0) {
-		pr_err("Failed to find variables at %s (%d)\n", buf, ret);
+		if (ret == 0 || ret == -ENOENT) {
+			pr_err("Failed to find the address of %s\n", buf);
+			ret = -ENOENT;
+		} else
+			pr_warning("Debuginfo analysis failed.\n");
 		goto end;
 	}
+
 	/* Some variables are found */
 	fprintf(stdout, "Available variables at %s\n", buf);
 	for (i = 0; i < ret; i++) {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 9d8eb26f053..dca9145d704 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -26,7 +26,6 @@
 #include <errno.h>
 #include <stdio.h>
 #include <unistd.h>
-#include <getopt.h>
 #include <stdlib.h>
 #include <string.h>
 #include <stdarg.h>
@@ -573,14 +572,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 	if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
 		/* Search again in global variables */
 		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
+			pr_warning("Failed to find '%s' in this function.\n",
+				   pf->pvar->var);
 			ret = -ENOENT;
 	}
 	if (ret >= 0)
 		ret = convert_variable(&vr_die, pf);
 
-	if (ret < 0)
-		pr_warning("Failed to find '%s' in this function.\n",
-			   pf->pvar->var);
 	return ret;
 }
 
@@ -1281,7 +1279,11 @@ out:
 	return ret;
 }
 
-/* Find available variables at given probe point */
+/*
+ * Find available variables at given probe point
+ * Return the number of found probe points. Return 0 if there is no
+ * matched probe point. Return <0 if an error occurs.
+ */
 int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 				      struct perf_probe_event *pev,
 				      struct variable_list **vls,
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index daa17aeb6c6..a126e6cc6e7 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -6,6 +6,7 @@
 
 #include "util.h"
 #include "pstack.h"
+#include "debug.h"
 #include <linux/kernel.h>
 #include <stdlib.h>
 
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 122669c18ff..12aa9b0d0ba 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -14,12 +14,12 @@
  */
 int verbose;
 
-int eprintf(int level, const char *fmt, ...)
+int eprintf(int level, int var, const char *fmt, ...)
 {
 	va_list args;
 	int ret = 0;
 
-	if (verbose >= level) {
+	if (var >= level) {
 		va_start(args, fmt);
 		ret = vfprintf(stderr, fmt, args);
 		va_end(args);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 049e0a09ccd..fe8079edbdc 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -4,6 +4,7 @@
 #include "parse-events.h"
 #include <api/fs/fs.h>
 #include "util.h"
+#include "cloexec.h"
 
 typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
 
@@ -11,6 +12,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 {
 	struct perf_evlist *evlist;
 	struct perf_evsel *evsel;
+	unsigned long flags = perf_event_open_cloexec_flag();
 	int err = -EAGAIN, fd;
 
 	evlist = perf_evlist__new();
@@ -22,14 +24,14 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 
 	evsel = perf_evlist__first(evlist);
 
-	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags);
 	if (fd < 0)
 		goto out_delete;
 	close(fd);
 
 	fn(evsel);
 
-	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags);
 	if (fd < 0) {
 		if (errno == EINVAL)
 			err = -EINVAL;
@@ -69,15 +71,26 @@ static void perf_probe_sample_identifier(struct perf_evsel *evsel)
 	evsel->attr.sample_type |= PERF_SAMPLE_IDENTIFIER;
 }
 
+static void perf_probe_comm_exec(struct perf_evsel *evsel)
+{
+	evsel->attr.comm_exec = 1;
+}
+
 bool perf_can_sample_identifier(void)
 {
 	return perf_probe_api(perf_probe_sample_identifier);
 }
 
+static bool perf_can_comm_exec(void)
+{
+	return perf_probe_api(perf_probe_comm_exec);
+}
+
 void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 {
 	struct perf_evsel *evsel;
 	bool use_sample_identifier = false;
+	bool use_comm_exec;
 
 	/*
 	 * Set the evsel leader links before we configure attributes,
@@ -89,8 +102,13 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
 
-	evlist__for_each(evlist, evsel)
+	use_comm_exec = perf_can_comm_exec();
+
+	evlist__for_each(evlist, evsel) {
 		perf_evsel__config(evsel, opts);
+		if (!evsel->idx && use_comm_exec)
+			evsel->attr.comm_exec = 1;
+	}
 
 	if (evlist->nr_entries > 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
@@ -203,7 +221,8 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 		cpu = evlist->cpus->map[0];
 	}
 
-	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1,
+				 perf_event_open_cloexec_flag());
 	if (fd >= 0) {
 		close(fd);
 		ret = true;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e108207c5de..b2dba9c0a3a 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -34,6 +34,7 @@
 #include "../event.h"
 #include "../trace-event.h"
 #include "../evsel.h"
+#include "../debug.h"
 
 void boot_Perf__Trace__Context(pTHX_ CV *cv);
 void boot_DynaLoader(pTHX_ CV *cv);
@@ -215,6 +216,7 @@ static void define_event_symbols(struct event_format *event,
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_STRING:
+	case PRINT_BITMASK:
 		break;
 	case PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cd9774df375..cbce2545da4 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -27,11 +27,13 @@
 #include <errno.h>
 
 #include "../../perf.h"
+#include "../debug.h"
 #include "../evsel.h"
 #include "../util.h"
 #include "../event.h"
 #include "../thread.h"
 #include "../trace-event.h"
+#include "../machine.h"
 
 PyMODINIT_FUNC initperf_trace_context(void);
 
@@ -50,10 +52,14 @@ static int zero_flag_atom;
 
 static PyObject *main_module, *main_dict;
 
+static void handler_call_die(const char *handler_name) NORETURN;
 static void handler_call_die(const char *handler_name)
 {
 	PyErr_Print();
 	Py_FatalError("problem in Python trace event handler");
+	// Py_FatalError does not return
+	// but we have to make the compiler happy
+	abort();
 }
 
 /*
@@ -97,6 +103,7 @@ static void define_value(enum print_arg_type field_type,
 		retval = PyObject_CallObject(handler, t);
 		if (retval == NULL)
 			handler_call_die(handler_name);
+		Py_DECREF(retval);
 	}
 
 	Py_DECREF(t);
@@ -143,6 +150,7 @@ static void define_field(enum print_arg_type field_type,
 		retval = PyObject_CallObject(handler, t);
 		if (retval == NULL)
 			handler_call_die(handler_name);
+		Py_DECREF(retval);
 	}
 
 	Py_DECREF(t);
@@ -197,6 +205,7 @@ static void define_event_symbols(struct event_format *event,
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_FUNC:
+	case PRINT_BITMASK:
 		/* we should warn... */
 		return;
 	}
@@ -230,15 +239,133 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
 	return event;
 }
 
+static PyObject *get_field_numeric_entry(struct event_format *event,
+		struct format_field *field, void *data)
+{
+	bool is_array = field->flags & FIELD_IS_ARRAY;
+	PyObject *obj, *list = NULL;
+	unsigned long long val;
+	unsigned int item_size, n_items, i;
+
+	if (is_array) {
+		list = PyList_New(field->arraylen);
+		item_size = field->size / field->arraylen;
+		n_items = field->arraylen;
+	} else {
+		item_size = field->size;
+		n_items = 1;
+	}
+
+	for (i = 0; i < n_items; i++) {
+
+		val = read_size(event, data + field->offset + i * item_size,
+				item_size);
+		if (field->flags & FIELD_IS_SIGNED) {
+			if ((long long)val >= LONG_MIN &&
+					(long long)val <= LONG_MAX)
+				obj = PyInt_FromLong(val);
+			else
+				obj = PyLong_FromLongLong(val);
+		} else {
+			if (val <= LONG_MAX)
+				obj = PyInt_FromLong(val);
+			else
+				obj = PyLong_FromUnsignedLongLong(val);
+		}
+		if (is_array)
+			PyList_SET_ITEM(list, i, obj);
+	}
+	if (is_array)
+		obj = list;
+	return obj;
+}
+
+
+static PyObject *python_process_callchain(struct perf_sample *sample,
+					 struct perf_evsel *evsel,
+					 struct addr_location *al)
+{
+	PyObject *pylist;
+
+	pylist = PyList_New(0);
+	if (!pylist)
+		Py_FatalError("couldn't create Python list");
+
+	if (!symbol_conf.use_callchain || !sample->callchain)
+		goto exit;
+
+	if (machine__resolve_callchain(al->machine, evsel, al->thread,
+					   sample, NULL, NULL,
+					   PERF_MAX_STACK_DEPTH) != 0) {
+		pr_err("Failed to resolve callchain. Skipping\n");
+		goto exit;
+	}
+	callchain_cursor_commit(&callchain_cursor);
+
+
+	while (1) {
+		PyObject *pyelem;
+		struct callchain_cursor_node *node;
+		node = callchain_cursor_current(&callchain_cursor);
+		if (!node)
+			break;
+
+		pyelem = PyDict_New();
+		if (!pyelem)
+			Py_FatalError("couldn't create Python dictionary");
+
+
+		pydict_set_item_string_decref(pyelem, "ip",
+				PyLong_FromUnsignedLongLong(node->ip));
+
+		if (node->sym) {
+			PyObject *pysym  = PyDict_New();
+			if (!pysym)
+				Py_FatalError("couldn't create Python dictionary");
+			pydict_set_item_string_decref(pysym, "start",
+					PyLong_FromUnsignedLongLong(node->sym->start));
+			pydict_set_item_string_decref(pysym, "end",
+					PyLong_FromUnsignedLongLong(node->sym->end));
+			pydict_set_item_string_decref(pysym, "binding",
+					PyInt_FromLong(node->sym->binding));
+			pydict_set_item_string_decref(pysym, "name",
+					PyString_FromStringAndSize(node->sym->name,
+							node->sym->namelen));
+			pydict_set_item_string_decref(pyelem, "sym", pysym);
+		}
+
+		if (node->map) {
+			struct map *map = node->map;
+			const char *dsoname = "[unknown]";
+			if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+				if (symbol_conf.show_kernel_path && map->dso->long_name)
+					dsoname = map->dso->long_name;
+				else if (map->dso->name)
+					dsoname = map->dso->name;
+			}
+			pydict_set_item_string_decref(pyelem, "dso",
+					PyString_FromString(dsoname));
+		}
+
+		callchain_cursor_advance(&callchain_cursor);
+		PyList_Append(pylist, pyelem);
+		Py_DECREF(pyelem);
+	}
+
+exit:
+	return pylist;
+}
+
+
 static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
 				      struct thread *thread,
 				      struct addr_location *al)
 {
-	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
+	PyObject *handler, *retval, *context, *t, *obj, *callchain;
+	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
-	unsigned long long val;
 	unsigned long s, ns;
 	struct event_format *event;
 	unsigned n = 0;
@@ -279,18 +406,23 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
 	PyTuple_SetItem(t, n++, context);
 
+	/* ip unwinding */
+	callchain = python_process_callchain(sample, evsel, al);
+
 	if (handler) {
 		PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
 		PyTuple_SetItem(t, n++, PyInt_FromLong(s));
 		PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
 		PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
 		PyTuple_SetItem(t, n++, PyString_FromString(comm));
+		PyTuple_SetItem(t, n++, callchain);
 	} else {
 		pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu));
 		pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s));
 		pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns));
 		pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid));
 		pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm));
+		pydict_set_item_string_decref(dict, "common_callchain", callchain);
 	}
 	for (field = event->format.fields; field; field = field->next) {
 		if (field->flags & FIELD_IS_STRING) {
@@ -302,20 +434,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				offset = field->offset;
 			obj = PyString_FromString((char *)data + offset);
 		} else { /* FIELD_IS_NUMERIC */
-			val = read_size(event, data + field->offset,
-					field->size);
-			if (field->flags & FIELD_IS_SIGNED) {
-				if ((long long)val >= LONG_MIN &&
-				    (long long)val <= LONG_MAX)
-					obj = PyInt_FromLong(val);
-				else
-					obj = PyLong_FromLongLong(val);
-			} else {
-				if (val <= LONG_MAX)
-					obj = PyInt_FromLong(val);
-				else
-					obj = PyLong_FromUnsignedLongLong(val);
-			}
+			obj = get_field_numeric_entry(event, field, data);
 		}
 		if (handler)
 			PyTuple_SetItem(t, n++, obj);
@@ -323,6 +442,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 			pydict_set_item_string_decref(dict, field->name, obj);
 
 	}
+
 	if (!handler)
 		PyTuple_SetItem(t, n++, dict);
 
@@ -333,6 +453,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		retval = PyObject_CallObject(handler, t);
 		if (retval == NULL)
 			handler_call_die(handler_name);
+		Py_DECREF(retval);
 	} else {
 		handler = PyDict_GetItemString(main_dict, "trace_unhandled");
 		if (handler && PyCallable_Check(handler)) {
@@ -340,6 +461,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 			retval = PyObject_CallObject(handler, t);
 			if (retval == NULL)
 				handler_call_die("trace_unhandled");
+			Py_DECREF(retval);
 		}
 		Py_DECREF(dict);
 	}
@@ -352,7 +474,7 @@ static void python_process_general_event(struct perf_sample *sample,
 					 struct thread *thread,
 					 struct addr_location *al)
 {
-	PyObject *handler, *retval, *t, *dict;
+	PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample;
 	static char handler_name[64];
 	unsigned n = 0;
 
@@ -368,6 +490,10 @@ static void python_process_general_event(struct perf_sample *sample,
 	if (!dict)
 		Py_FatalError("couldn't create Python dictionary");
 
+	dict_sample = PyDict_New();
+	if (!dict_sample)
+		Py_FatalError("couldn't create Python dictionary");
+
 	snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
 
 	handler = PyDict_GetItemString(main_dict, handler_name);
@@ -377,8 +503,21 @@ static void python_process_general_event(struct perf_sample *sample,
 	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
 	pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
 			(const char *)&evsel->attr, sizeof(evsel->attr)));
-	pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize(
-			(const char *)sample, sizeof(*sample)));
+
+	pydict_set_item_string_decref(dict_sample, "pid",
+			PyInt_FromLong(sample->pid));
+	pydict_set_item_string_decref(dict_sample, "tid",
+			PyInt_FromLong(sample->tid));
+	pydict_set_item_string_decref(dict_sample, "cpu",
+			PyInt_FromLong(sample->cpu));
+	pydict_set_item_string_decref(dict_sample, "ip",
+			PyLong_FromUnsignedLongLong(sample->ip));
+	pydict_set_item_string_decref(dict_sample, "time",
+			PyLong_FromUnsignedLongLong(sample->time));
+	pydict_set_item_string_decref(dict_sample, "period",
+			PyLong_FromUnsignedLongLong(sample->period));
+	pydict_set_item_string_decref(dict, "sample", dict_sample);
+
 	pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
 			(const char *)sample->raw_data, sample->raw_size));
 	pydict_set_item_string_decref(dict, "comm",
@@ -392,6 +531,10 @@ static void python_process_general_event(struct perf_sample *sample,
 			PyString_FromString(al->sym->name));
 	}
 
+	/* ip unwinding */
+	callchain = python_process_callchain(sample, evsel, al);
+	pydict_set_item_string_decref(dict, "callchain", callchain);
+
 	PyTuple_SetItem(t, n++, dict);
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
@@ -399,6 +542,7 @@ static void python_process_general_event(struct perf_sample *sample,
 	retval = PyObject_CallObject(handler, t);
 	if (retval == NULL)
 		handler_call_die(handler_name);
+	Py_DECREF(retval);
 exit:
 	Py_DECREF(dict);
 	Py_DECREF(t);
@@ -520,8 +664,7 @@ static int python_stop_script(void)
 	retval = PyObject_CallObject(handler, NULL);
 	if (retval == NULL)
 		handler_call_die("trace_end");
-	else
-		Py_DECREF(retval);
+	Py_DECREF(retval);
 out:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
@@ -588,6 +731,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 		fprintf(ofp, "common_nsecs, ");
 		fprintf(ofp, "common_pid, ");
 		fprintf(ofp, "common_comm,\n\t");
+		fprintf(ofp, "common_callchain, ");
 
 		not_first = 0;
 		count = 0;
@@ -622,6 +766,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			fprintf(ofp, "%s=", f->name);
 			if (f->flags & FIELD_IS_STRING ||
 			    f->flags & FIELD_IS_FLAG ||
+			    f->flags & FIELD_IS_ARRAY ||
 			    f->flags & FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
 			else if (f->flags & FIELD_IS_SIGNED)
@@ -630,7 +775,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%%u");
 		}
 
-		fprintf(ofp, "\\n\" %% \\\n\t\t(");
+		fprintf(ofp, "\" %% \\\n\t\t(");
 
 		not_first = 0;
 		count = 0;
@@ -666,7 +811,15 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%s", f->name);
 		}
 
-		fprintf(ofp, "),\n\n");
+		fprintf(ofp, ")\n\n");
+
+		fprintf(ofp, "\t\tfor node in common_callchain:");
+		fprintf(ofp, "\n\t\t\tif 'sym' in node:");
+		fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+		fprintf(ofp, "\n\t\t\telse:");
+		fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
+		fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 64a186edc7b..88dfef70c13 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,7 +14,6 @@
 #include "util.h"
 #include "cpumap.h"
 #include "perf_regs.h"
-#include "vdso.h"
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -156,7 +155,6 @@ void perf_session__delete(struct perf_session *session)
 	if (session->file)
 		perf_data_file__close(session->file);
 	free(session);
-	vdso__exit();
 }
 
 static int process_event_synth_tracing_data_stub(struct perf_tool *tool
@@ -511,6 +509,7 @@ static int flush_sample_queue(struct perf_session *s,
 		os->last_flush = iter->timestamp;
 		list_del(&iter->list);
 		list_add(&iter->list, &os->sample_cache);
+		os->nr_samples--;
 
 		if (show_progress)
 			ui_progress__update(&prog, 1);
@@ -523,8 +522,6 @@ static int flush_sample_queue(struct perf_session *s,
 			list_entry(head->prev, struct sample_queue, list);
 	}
 
-	os->nr_samples = 0;
-
 	return 0;
 }
 
@@ -994,8 +991,10 @@ static int perf_session_deliver_event(struct perf_session *session,
 	}
 }
 
-static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
-					    struct perf_tool *tool, u64 file_offset)
+static s64 perf_session__process_user_event(struct perf_session *session,
+					    union perf_event *event,
+					    struct perf_tool *tool,
+					    u64 file_offset)
 {
 	int fd = perf_data_file__fd(session->file);
 	int err;
@@ -1037,7 +1036,7 @@ static void event_swap(union perf_event *event, bool sample_id_all)
 		swap(event, sample_id_all);
 }
 
-static int perf_session__process_event(struct perf_session *session,
+static s64 perf_session__process_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
 				       u64 file_offset)
@@ -1083,13 +1082,14 @@ void perf_event_header__bswap(struct perf_event_header *hdr)
 
 struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
 {
-	return machine__findnew_thread(&session->machines.host, 0, pid);
+	return machine__findnew_thread(&session->machines.host, -1, pid);
 }
 
 static struct thread *perf_session__register_idle_thread(struct perf_session *session)
 {
-	struct thread *thread = perf_session__findnew(session, 0);
+	struct thread *thread;
 
+	thread = machine__findnew_thread(&session->machines.host, 0, 0);
 	if (thread == NULL || thread__set_comm(thread, "swapper", 0)) {
 		pr_err("problem inserting idle task.\n");
 		thread = NULL;
@@ -1147,7 +1147,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session,
 	union perf_event *event;
 	uint32_t size, cur_size = 0;
 	void *buf = NULL;
-	int skip = 0;
+	s64 skip = 0;
 	u64 head;
 	ssize_t err;
 	void *p;
@@ -1276,13 +1276,13 @@ int __perf_session__process_events(struct perf_session *session,
 				   u64 file_size, struct perf_tool *tool)
 {
 	int fd = perf_data_file__fd(session->file);
-	u64 head, page_offset, file_offset, file_pos;
+	u64 head, page_offset, file_offset, file_pos, size;
 	int err, mmap_prot, mmap_flags, map_idx = 0;
 	size_t	mmap_size;
 	char *buf, *mmaps[NUM_MMAPS];
 	union perf_event *event;
-	uint32_t size;
 	struct ui_progress prog;
+	s64 skip;
 
 	perf_tool__fill_defaults(tool);
 
@@ -1296,8 +1296,10 @@ int __perf_session__process_events(struct perf_session *session,
 	ui_progress__init(&prog, file_size, "Processing events...");
 
 	mmap_size = MMAP_SIZE;
-	if (mmap_size > file_size)
+	if (mmap_size > file_size) {
 		mmap_size = file_size;
+		session->one_mmap = true;
+	}
 
 	memset(mmaps, 0, sizeof(mmaps));
 
@@ -1319,6 +1321,10 @@ remap:
 	mmaps[map_idx] = buf;
 	map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
 	file_pos = file_offset + head;
+	if (session->one_mmap) {
+		session->one_mmap_addr = buf;
+		session->one_mmap_offset = file_offset;
+	}
 
 more:
 	event = fetch_mmaped_event(session, head, mmap_size, buf);
@@ -1337,7 +1343,8 @@ more:
 	size = event->header.size;
 
 	if (size < sizeof(struct perf_event_header) ||
-	    perf_session__process_event(session, event, tool, file_pos) < 0) {
+	    (skip = perf_session__process_event(session, event, tool, file_pos))
+									< 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       file_offset + head, event->header.size,
 		       event->header.type);
@@ -1345,6 +1352,9 @@ more:
 		goto out_err;
 	}
 
+	if (skip)
+		size += skip;
+
 	head += size;
 	file_pos += size;
 
@@ -1364,6 +1374,7 @@ out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session, tool);
 	perf_session_free_sample_buffers(session);
+	session->one_mmap = false;
 	return err;
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 3140f8ae614..0321013bd9f 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -36,6 +36,9 @@ struct perf_session {
 	struct trace_event	tevent;
 	struct events_stats	stats;
 	bool			repipe;
+	bool			one_mmap;
+	void			*one_mmap_addr;
+	u64			one_mmap_offset;
 	struct ordered_samples	ordered_samples;
 	struct perf_data_file	*file;
 };
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 901b9bece2e..14e5a039bc4 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,3 +1,4 @@
+#include <sys/mman.h>
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
@@ -784,6 +785,104 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
+static inline  u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
+
+static int64_t
+sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	u64 l, r;
+	struct map *l_map, *r_map;
+
+	if (!left->mem_info)  return -1;
+	if (!right->mem_info) return 1;
+
+	/* group event types together */
+	if (left->cpumode > right->cpumode) return -1;
+	if (left->cpumode < right->cpumode) return 1;
+
+	l_map = left->mem_info->daddr.map;
+	r_map = right->mem_info->daddr.map;
+
+	/* if both are NULL, jump to sort on al_addr instead */
+	if (!l_map && !r_map)
+		goto addr;
+
+	if (!l_map) return -1;
+	if (!r_map) return 1;
+
+	if (l_map->maj > r_map->maj) return -1;
+	if (l_map->maj < r_map->maj) return 1;
+
+	if (l_map->min > r_map->min) return -1;
+	if (l_map->min < r_map->min) return 1;
+
+	if (l_map->ino > r_map->ino) return -1;
+	if (l_map->ino < r_map->ino) return 1;
+
+	if (l_map->ino_generation > r_map->ino_generation) return -1;
+	if (l_map->ino_generation < r_map->ino_generation) return 1;
+
+	/*
+	 * Addresses with no major/minor numbers are assumed to be
+	 * anonymous in userspace.  Sort those on pid then address.
+	 *
+	 * The kernel and non-zero major/minor mapped areas are
+	 * assumed to be unity mapped.  Sort those on address.
+	 */
+
+	if ((left->cpumode != PERF_RECORD_MISC_KERNEL) &&
+	    (!(l_map->flags & MAP_SHARED)) &&
+	    !l_map->maj && !l_map->min && !l_map->ino &&
+	    !l_map->ino_generation) {
+		/* userspace anonymous */
+
+		if (left->thread->pid_ > right->thread->pid_) return -1;
+		if (left->thread->pid_ < right->thread->pid_) return 1;
+	}
+
+addr:
+	/* al_addr does all the right addr - start + offset calculations */
+	l = cl_address(left->mem_info->daddr.al_addr);
+	r = cl_address(right->mem_info->daddr.al_addr);
+
+	if (l > r) return -1;
+	if (l < r) return 1;
+
+	return 0;
+}
+
+static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+
+	uint64_t addr = 0;
+	struct map *map = NULL;
+	struct symbol *sym = NULL;
+	char level = he->level;
+
+	if (he->mem_info) {
+		addr = cl_address(he->mem_info->daddr.al_addr);
+		map = he->mem_info->daddr.map;
+		sym = he->mem_info->daddr.sym;
+
+		/* print [s] for shared data mmaps */
+		if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
+		     map && (map->type == MAP__VARIABLE) &&
+		    (map->flags & MAP_SHARED) &&
+		    (map->maj || map->min || map->ino ||
+		     map->ino_generation))
+			level = 's';
+		else if (!map)
+			level = 'X';
+	}
+	return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size,
+					 width);
+}
+
 struct sort_entry sort_mispredict = {
 	.se_header	= "Branch Mispredicted",
 	.se_cmp		= sort__mispredict_cmp,
@@ -876,6 +975,13 @@ struct sort_entry sort_mem_snoop = {
 	.se_width_idx	= HISTC_MEM_SNOOP,
 };
 
+struct sort_entry sort_mem_dcacheline = {
+	.se_header	= "Data Cacheline",
+	.se_cmp		= sort__dcacheline_cmp,
+	.se_snprintf	= hist_entry__dcacheline_snprintf,
+	.se_width_idx	= HISTC_MEM_DCACHELINE,
+};
+
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1043,6 +1149,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
 	DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
 	DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
 	DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
+	DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
 };
 
 #undef DIM
@@ -1061,6 +1168,7 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
 	DIM(PERF_HPP__OVERHEAD_US, "overhead_us"),
 	DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"),
 	DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"),
+	DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
 	DIM(PERF_HPP__SAMPLES, "sample"),
 	DIM(PERF_HPP__PERIOD, "period"),
 };
@@ -1107,7 +1215,7 @@ static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 	len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
 
-	return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header);
+	return scnprintf(hpp->buf, hpp->size, "%-*s", len, hse->se->se_header);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
@@ -1156,6 +1264,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
+	hse->hpp.elide = false;
 
 	return hse;
 }
@@ -1363,27 +1472,64 @@ static int __setup_sorting(void)
 	return ret;
 }
 
-bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+void perf_hpp__set_elide(int idx, bool elide)
 {
-	if (perf_hpp__is_sort_entry(format)) {
-		struct hpp_sort_entry *hse;
+	struct perf_hpp_fmt *fmt;
+	struct hpp_sort_entry *hse;
+
+	perf_hpp__for_each_format(fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
 
-		hse = container_of(format, struct hpp_sort_entry, hpp);
-		return hse->se->elide;
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		if (hse->se->se_width_idx == idx) {
+			fmt->elide = elide;
+			break;
+		}
 	}
-	return false;
 }
 
-static void sort_entry__setup_elide(struct sort_entry *se,
-				    struct strlist *list,
-				    const char *list_name, FILE *fp)
+static bool __get_elide(struct strlist *list, const char *list_name, FILE *fp)
 {
 	if (list && strlist__nr_entries(list) == 1) {
 		if (fp != NULL)
 			fprintf(fp, "# %s: %s\n", list_name,
 				strlist__entry(list, 0)->s);
-		se->elide = true;
+		return true;
 	}
+	return false;
+}
+
+static bool get_elide(int idx, FILE *output)
+{
+	switch (idx) {
+	case HISTC_SYMBOL:
+		return __get_elide(symbol_conf.sym_list, "symbol", output);
+	case HISTC_DSO:
+		return __get_elide(symbol_conf.dso_list, "dso", output);
+	case HISTC_COMM:
+		return __get_elide(symbol_conf.comm_list, "comm", output);
+	default:
+		break;
+	}
+
+	if (sort__mode != SORT_MODE__BRANCH)
+		return false;
+
+	switch (idx) {
+	case HISTC_SYMBOL_FROM:
+		return __get_elide(symbol_conf.sym_from_list, "sym_from", output);
+	case HISTC_SYMBOL_TO:
+		return __get_elide(symbol_conf.sym_to_list, "sym_to", output);
+	case HISTC_DSO_FROM:
+		return __get_elide(symbol_conf.dso_from_list, "dso_from", output);
+	case HISTC_DSO_TO:
+		return __get_elide(symbol_conf.dso_to_list, "dso_to", output);
+	default:
+		break;
+	}
+
+	return false;
 }
 
 void sort__setup_elide(FILE *output)
@@ -1391,39 +1537,12 @@ void sort__setup_elide(FILE *output)
 	struct perf_hpp_fmt *fmt;
 	struct hpp_sort_entry *hse;
 
-	sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-				"dso", output);
-	sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list,
-				"comm", output);
-	sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list,
-				"symbol", output);
-
-	if (sort__mode == SORT_MODE__BRANCH) {
-		sort_entry__setup_elide(&sort_dso_from,
-					symbol_conf.dso_from_list,
-					"dso_from", output);
-		sort_entry__setup_elide(&sort_dso_to,
-					symbol_conf.dso_to_list,
-					"dso_to", output);
-		sort_entry__setup_elide(&sort_sym_from,
-					symbol_conf.sym_from_list,
-					"sym_from", output);
-		sort_entry__setup_elide(&sort_sym_to,
-					symbol_conf.sym_to_list,
-					"sym_to", output);
-	} else if (sort__mode == SORT_MODE__MEMORY) {
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"symbol_daddr", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"dso_daddr", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"mem", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"local_weight", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"tlb", output);
-		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-					"snoop", output);
+	perf_hpp__for_each_format(fmt) {
+		if (!perf_hpp__is_sort_entry(fmt))
+			continue;
+
+		hse = container_of(fmt, struct hpp_sort_entry, hpp);
+		fmt->elide = get_elide(hse->se->se_width_idx, output);
 	}
 
 	/*
@@ -1434,8 +1553,7 @@ void sort__setup_elide(FILE *output)
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
-		hse = container_of(fmt, struct hpp_sort_entry, hpp);
-		if (!hse->se->elide)
+		if (!fmt->elide)
 			return;
 	}
 
@@ -1443,8 +1561,7 @@ void sort__setup_elide(FILE *output)
 		if (!perf_hpp__is_sort_entry(fmt))
 			continue;
 
-		hse = container_of(fmt, struct hpp_sort_entry, hpp);
-		hse->se->elide = false;
+		fmt->elide = false;
 	}
 }
 
@@ -1581,6 +1698,9 @@ void reset_output_field(void)
 	sort__has_sym = 0;
 	sort__has_dso = 0;
 
+	field_order = NULL;
+	sort_order = NULL;
+
 	reset_dimensions();
 	perf_hpp__reset_output_field();
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 5f38d925e92..041f0c9cea2 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -20,7 +20,7 @@
 
 #include "parse-options.h"
 #include "parse-events.h"
-
+#include "hist.h"
 #include "thread.h"
 
 extern regex_t parent_regex;
@@ -82,12 +82,14 @@ struct hist_entry {
 		struct list_head head;
 	} pairs;
 	struct he_stat		stat;
+	struct he_stat		*stat_acc;
 	struct map_symbol	ms;
 	struct thread		*thread;
 	struct comm		*comm;
 	u64			ip;
 	u64			transaction;
 	s32			cpu;
+	u8			cpumode;
 
 	struct hist_entry_diff	diff;
 
@@ -130,6 +132,21 @@ static inline void hist_entry__add_pair(struct hist_entry *pair,
 	list_add_tail(&pair->pairs.node, &he->pairs.head);
 }
 
+static inline float hist_entry__get_percent_limit(struct hist_entry *he)
+{
+	u64 period = he->stat.period;
+	u64 total_period = hists__total_period(he->hists);
+
+	if (unlikely(total_period == 0))
+		return 0;
+
+	if (symbol_conf.cumulate_callchain)
+		period = he->stat_acc->period;
+
+	return period * 100.0 / total_period;
+}
+
+
 enum sort_mode {
 	SORT_MODE__NORMAL,
 	SORT_MODE__BRANCH,
@@ -169,6 +186,7 @@ enum sort_type {
 	SORT_MEM_TLB,
 	SORT_MEM_LVL,
 	SORT_MEM_SNOOP,
+	SORT_MEM_DCACHELINE,
 };
 
 /*
@@ -186,7 +204,6 @@ struct sort_entry {
 	int	(*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
 			       unsigned int width);
 	u8	se_width_idx;
-	bool	elide;
 };
 
 extern struct sort_entry sort_thread;
@@ -197,6 +214,7 @@ int setup_output_field(void);
 void reset_output_field(void);
 extern int sort_dimension__add(const char *);
 void sort__setup_elide(FILE *fp);
+void perf_hpp__set_elide(int idx, bool elide);
 
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 6a0a13d07a2..283d3e73e2f 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -30,6 +30,7 @@ static u64 turbo_frequency, max_freq;
 
 #define SLOT_MULT 30.0
 #define SLOT_HEIGHT 25.0
+#define SLOT_HALF (SLOT_HEIGHT / 2)
 
 int svg_page_width = 1000;
 u64 svg_highlight;
@@ -114,8 +115,14 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 	fprintf(svgfile, "      rect          { stroke-width: 1; }\n");
 	fprintf(svgfile, "      rect.process  { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.process3 { fill:rgb(180,180,180); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.sample   { fill:rgb(  0,  0,255); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.sample_hi{ fill:rgb(255,128,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.error    { fill:rgb(255,  0,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.net      { fill:rgb(  0,128,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.disk     { fill:rgb(  0,  0,255); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.sync     { fill:rgb(128,128,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.poll     { fill:rgb(  0,128,128); fill-opacity:0.2; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.blocked  { fill:rgb(255,  0,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.waiting  { fill:rgb(224,214,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.WAITING  { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
@@ -132,12 +139,81 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 	fprintf(svgfile, "    ]]>\n   </style>\n</defs>\n");
 }
 
+static double normalize_height(double height)
+{
+	if (height < 0.25)
+		return 0.25;
+	else if (height < 0.50)
+		return 0.50;
+	else if (height < 0.75)
+		return 0.75;
+	else
+		return 0.100;
+}
+
+void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges)
+{
+	double w = time2pixels(end) - time2pixels(start);
+	height = normalize_height(height);
+
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges);
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
+		time2pixels(start),
+		w,
+		Yslot * SLOT_MULT,
+		SLOT_HALF * height,
+		type);
+	fprintf(svgfile, "</g>\n");
+}
+
+void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges)
+{
+	double w = time2pixels(end) - time2pixels(start);
+	height = normalize_height(height);
+
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges);
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
+		time2pixels(start),
+		w,
+		Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HALF * height,
+		SLOT_HALF * height,
+		type);
+	fprintf(svgfile, "</g>\n");
+}
+
+void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges)
+{
+	double w = time2pixels(end) - time2pixels(start);
+	height = normalize_height(height);
+
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges);
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
+		time2pixels(start),
+		w,
+		Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HEIGHT * height,
+		SLOT_HEIGHT * height,
+		type);
+	fprintf(svgfile, "</g>\n");
+}
+
 void svg_box(int Yslot, u64 start, u64 end, const char *type)
 {
 	if (!svgfile)
 		return;
 
-	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type);
 }
 
@@ -174,7 +250,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 		cpu, time_to_string(end - start));
 	if (backtrace)
 		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
-	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT,
 		type);
 
@@ -186,7 +262,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 	text_size = round_text_size(text_size);
 
 	if (text_size > MIN_TEXT_SIZE)
-		fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n",
+		fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">%i</text>\n",
 			time2pixels(start), Yslot *  SLOT_MULT + SLOT_HEIGHT - 1, text_size,  cpu + 1);
 
 	fprintf(svgfile, "</g>\n");
@@ -202,10 +278,10 @@ static char *time_to_string(u64 duration)
 		return text;
 
 	if (duration < 1000 * 1000) { /* less than 1 msec */
-		sprintf(text, "%4.1f us", duration / 1000.0);
+		sprintf(text, "%.1f us", duration / 1000.0);
 		return text;
 	}
-	sprintf(text, "%4.1f ms", duration / 1000.0 / 1000);
+	sprintf(text, "%.1f ms", duration / 1000.0 / 1000);
 
 	return text;
 }
@@ -233,14 +309,14 @@ void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 
 	font_size = round_text_size(font_size);
 
-	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
+	fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
 	fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
 	if (backtrace)
 		fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace);
-	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
 	if (font_size > MIN_TEXT_SIZE)
-		fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%1.8fpt\"> %s</text>\n",
+		fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\"> %s</text>\n",
 			font_size, text);
 	fprintf(svgfile, "</g>\n");
 }
@@ -289,16 +365,16 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 
 	fprintf(svgfile, "<g>\n");
 
-	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n",
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"cpu\"/>\n",
 		time2pixels(first_time),
 		time2pixels(last_time)-time2pixels(first_time),
 		cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
 
 	sprintf(cpu_string, "CPU %i", (int)cpu);
-	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
+	fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string);
 
-	fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n",
+	fprintf(svgfile, "<text transform=\"translate(%.8f,%.8f)\" font-size=\"1.25pt\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model());
 
 	fprintf(svgfile, "</g>\n");
@@ -319,11 +395,11 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c
 	else
 		type = "sample";
 
-	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
+	fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), cpu2y(cpu));
 	fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start));
 	if (backtrace)
 		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
-	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
 	width = time2pixels(end)-time2pixels(start);
 	if (width > 6)
@@ -332,7 +408,7 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c
 	width = round_text_size(width);
 
 	if (width > MIN_TEXT_SIZE)
-		fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%3.8fpt\">%s</text>\n",
+		fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\">%s</text>\n",
 			width, name);
 
 	fprintf(svgfile, "</g>\n");
@@ -353,7 +429,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 		type = 6;
 	sprintf(style, "c%i", type);
 
-	fprintf(svgfile, "<rect class=\"%s\" x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\"/>\n",
+	fprintf(svgfile, "<rect class=\"%s\" x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\"/>\n",
 		style,
 		time2pixels(start), time2pixels(end)-time2pixels(start),
 		cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
@@ -365,7 +441,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 	width = round_text_size(width);
 
 	if (width > MIN_TEXT_SIZE)
-		fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n",
+		fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">C%i</text>\n",
 			time2pixels(start), cpu2y(cpu)+width, width, type);
 
 	fprintf(svgfile, "</g>\n");
@@ -407,9 +483,9 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	if (max_freq)
 		height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT);
 	height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height;
-	fprintf(svgfile, "<line x1=\"%4.8f\" x2=\"%4.8f\" y1=\"%4.1f\" y2=\"%4.1f\" class=\"pstate\"/>\n",
+	fprintf(svgfile, "<line x1=\"%.8f\" x2=\"%.8f\" y1=\"%.1f\" y2=\"%.1f\" class=\"pstate\"/>\n",
 		time2pixels(start), time2pixels(end), height, height);
-	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n",
+	fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"0.25pt\">%s</text>\n",
 		time2pixels(start), height+0.9, HzToHuman(freq));
 
 	fprintf(svgfile, "</g>\n");
@@ -435,32 +511,32 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 
 	if (row1 < row2) {
 		if (row1) {
-			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 				time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32);
 			if (desc2)
-				fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
+				fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
 					time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_HEIGHT/48, desc2);
 		}
 		if (row2) {
-			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 				time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32,  time2pixels(start), row2 * SLOT_MULT);
 			if (desc1)
-				fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
+				fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
 					time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, desc1);
 		}
 	} else {
 		if (row2) {
-			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 				time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32);
 			if (desc1)
-				fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
+				fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
 					time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/48, desc1);
 		}
 		if (row1) {
-			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 				time2pixels(start), row1 * SLOT_MULT - SLOT_MULT/32,  time2pixels(start), row1 * SLOT_MULT);
 			if (desc2)
-				fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
+				fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
 					time2pixels(start), row1 * SLOT_MULT - SLOT_HEIGHT/32, desc2);
 		}
 	}
@@ -468,7 +544,7 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 	if (row2 > row1)
 		height += SLOT_HEIGHT;
 	if (row1)
-		fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
+		fprintf(svgfile, "<circle  cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
 
 	fprintf(svgfile, "</g>\n");
@@ -488,16 +564,16 @@ void svg_wakeline(u64 start, int row1, int row2, const char *backtrace)
 		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
 
 	if (row1 < row2)
-		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+		fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 			time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT);
 	else
-		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+		fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 			time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row1 * SLOT_MULT);
 
 	height = row1 * SLOT_MULT;
 	if (row2 > row1)
 		height += SLOT_HEIGHT;
-	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
+	fprintf(svgfile, "<circle  cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
 
 	fprintf(svgfile, "</g>\n");
@@ -515,9 +591,9 @@ void svg_interrupt(u64 start, int row, const char *backtrace)
 	if (backtrace)
 		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
 
-	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
+	fprintf(svgfile, "<circle  cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT);
-	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
+	fprintf(svgfile, "<circle  cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT);
 
 	fprintf(svgfile, "</g>\n");
@@ -528,7 +604,7 @@ void svg_text(int Yslot, u64 start, const char *text)
 	if (!svgfile)
 		return;
 
-	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
+	fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n",
 		time2pixels(start), Yslot * SLOT_MULT+SLOT_HEIGHT/2, text);
 }
 
@@ -537,12 +613,26 @@ static void svg_legenda_box(int X, const char *text, const char *style)
 	double boxsize;
 	boxsize = SLOT_HEIGHT / 2;
 
-	fprintf(svgfile, "<rect x=\"%i\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"%i\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n",
 		X, boxsize, boxsize, style);
-	fprintf(svgfile, "<text transform=\"translate(%4.8f, %4.8f)\" font-size=\"%4.8fpt\">%s</text>\n",
+	fprintf(svgfile, "<text transform=\"translate(%.8f, %.8f)\" font-size=\"%.8fpt\">%s</text>\n",
 		X + boxsize + 5, boxsize, 0.8 * boxsize, text);
 }
 
+void svg_io_legenda(void)
+{
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	svg_legenda_box(0,	"Disk", "disk");
+	svg_legenda_box(100,	"Network", "net");
+	svg_legenda_box(200,	"Sync", "sync");
+	svg_legenda_box(300,	"Poll", "poll");
+	svg_legenda_box(400,	"Error", "error");
+	fprintf(svgfile, "</g>\n");
+}
+
 void svg_legenda(void)
 {
 	if (!svgfile)
@@ -559,7 +649,7 @@ void svg_legenda(void)
 	fprintf(svgfile, "</g>\n");
 }
 
-void svg_time_grid(void)
+void svg_time_grid(double min_thickness)
 {
 	u64 i;
 
@@ -579,8 +669,10 @@ void svg_time_grid(void)
 			color = 128;
 		}
 
-		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n",
-			time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness);
+		if (thickness >= min_thickness)
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%.3f\"/>\n",
+				time2pixels(i), SLOT_MULT/2, time2pixels(i),
+				total_height, color, color, color, thickness);
 
 		i += 10000000;
 	}
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e3aff5332e3..9292a529144 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -4,6 +4,9 @@
 #include <linux/types.h>
 
 extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
+extern void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+extern void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+extern void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
 extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
 extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
 extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
@@ -16,7 +19,8 @@ extern void svg_cstate(int cpu, u64 start, u64 end, int type);
 extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
 
-extern void svg_time_grid(void);
+extern void svg_time_grid(double min_thickness);
+extern void svg_io_legenda(void);
 extern void svg_legenda(void);
 extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
 extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 6864661a79d..d75349979e6 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -49,7 +49,8 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
 
 static inline int elf_sym__is_function(const GElf_Sym *sym)
 {
-	return elf_sym__type(sym) == STT_FUNC &&
+	return (elf_sym__type(sym) == STT_FUNC ||
+		elf_sym__type(sym) == STT_GNU_IFUNC) &&
 	       sym->st_name != 0 &&
 	       sym->st_shndx != SHN_UNDEF;
 }
@@ -598,6 +599,8 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 			goto out_elf_end;
 	}
 
+	ss->is_64_bit = (gelf_getclass(elf) == ELFCLASS64);
+
 	ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab",
 			NULL);
 	if (ss->symshdr.sh_type != SHT_SYMTAB)
@@ -619,7 +622,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		GElf_Shdr shdr;
 		ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
 				ehdr.e_type == ET_REL ||
-				is_vdso_map(dso->short_name) ||
+				dso__is_vdso(dso) ||
 				elf_section_by_name(elf, &ehdr, &shdr,
 						     ".gnu.prelink_undo",
 						     NULL) != NULL);
@@ -698,6 +701,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	bool remap_kernel = false, adjust_kernel_syms = false;
 
 	dso->symtab_type = syms_ss->type;
+	dso->is_64_bit = syms_ss->is_64_bit;
 	dso->rel = syms_ss->ehdr.e_type == ET_REL;
 
 	/*
@@ -1024,6 +1028,39 @@ int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
 	return err;
 }
 
+enum dso_type dso__type_fd(int fd)
+{
+	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
+	GElf_Ehdr ehdr;
+	Elf_Kind ek;
+	Elf *elf;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		goto out;
+
+	ek = elf_kind(elf);
+	if (ek != ELF_K_ELF)
+		goto out_end;
+
+	if (gelf_getclass(elf) == ELFCLASS64) {
+		dso_type = DSO__TYPE_64BIT;
+		goto out_end;
+	}
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		goto out_end;
+
+	if (ehdr.e_machine == EM_X86_64)
+		dso_type = DSO__TYPE_X32BIT;
+	else
+		dso_type = DSO__TYPE_32BIT;
+out_end:
+	elf_end(elf);
+out:
+	return dso_type;
+}
+
 static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len)
 {
 	ssize_t r;
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index bd15f490d04..c9541fea951 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -288,6 +288,44 @@ int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
 	return 0;
 }
 
+static int fd__is_64_bit(int fd)
+{
+	u8 e_ident[EI_NIDENT];
+
+	if (lseek(fd, 0, SEEK_SET))
+		return -1;
+
+	if (readn(fd, e_ident, sizeof(e_ident)) != sizeof(e_ident))
+		return -1;
+
+	if (memcmp(e_ident, ELFMAG, SELFMAG) ||
+	    e_ident[EI_VERSION] != EV_CURRENT)
+		return -1;
+
+	return e_ident[EI_CLASS] == ELFCLASS64;
+}
+
+enum dso_type dso__type_fd(int fd)
+{
+	Elf64_Ehdr ehdr;
+	int ret;
+
+	ret = fd__is_64_bit(fd);
+	if (ret < 0)
+		return DSO__TYPE_UNKNOWN;
+
+	if (ret)
+		return DSO__TYPE_64BIT;
+
+	if (readn(fd, &ehdr, sizeof(ehdr)) != sizeof(ehdr))
+		return DSO__TYPE_UNKNOWN;
+
+	if (ehdr.e_machine == EM_X86_64)
+		return DSO__TYPE_X32BIT;
+
+	return DSO__TYPE_32BIT;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 		  struct symsrc *ss,
 		  struct symsrc *runtime_ss __maybe_unused,
@@ -295,6 +333,11 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 		  int kmodule __maybe_unused)
 {
 	unsigned char *build_id[BUILD_ID_SIZE];
+	int ret;
+
+	ret = fd__is_64_bit(ss->fd);
+	if (ret >= 0)
+		dso->is_64_bit = ret;
 
 	if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) {
 		dso__set_build_id(dso, build_id);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 95e24977993..eb06746b06b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -29,11 +29,13 @@ int vmlinux_path__nr_entries;
 char **vmlinux_path;
 
 struct symbol_conf symbol_conf = {
-	.use_modules	  = true,
-	.try_vmlinux_path = true,
-	.annotate_src	  = true,
-	.demangle	  = true,
-	.symfs            = "",
+	.use_modules		= true,
+	.try_vmlinux_path	= true,
+	.annotate_src		= true,
+	.demangle		= true,
+	.cumulate_callchain	= true,
+	.show_hist_headers	= true,
+	.symfs			= "",
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
@@ -340,6 +342,16 @@ static struct symbol *symbols__first(struct rb_root *symbols)
 	return NULL;
 }
 
+static struct symbol *symbols__next(struct symbol *sym)
+{
+	struct rb_node *n = rb_next(&sym->rb_node);
+
+	if (n)
+		return rb_entry(n, struct symbol, rb_node);
+
+	return NULL;
+}
+
 struct symbol_name_rb_node {
 	struct rb_node	rb_node;
 	struct symbol	sym;
@@ -410,11 +422,16 @@ struct symbol *dso__find_symbol(struct dso *dso,
 	return symbols__find(&dso->symbols[type], addr);
 }
 
-static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
 {
 	return symbols__first(&dso->symbols[type]);
 }
 
+struct symbol *dso__next_symbol(struct symbol *sym)
+{
+	return symbols__next(sym);
+}
+
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name)
 {
@@ -1063,6 +1080,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			      &is_64_bit);
 	if (err)
 		goto out_err;
+	dso->is_64_bit = is_64_bit;
 
 	if (list_empty(&md.maps)) {
 		err = -EINVAL;
@@ -1661,6 +1679,7 @@ do_kallsyms:
 	free(kallsyms_allocated_filename);
 
 	if (err > 0 && !dso__is_kcore(dso)) {
+		dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
 		dso__set_long_name(dso, "[kernel.kallsyms]", false);
 		map__fixup_start(map);
 		map__fixup_end(map);
@@ -1708,6 +1727,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 	if (err > 0)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	if (err > 0 && !dso__is_kcore(dso)) {
+		dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
 		machine__mmap_name(machine, path, sizeof(path));
 		dso__set_long_name(dso, strdup(path), true);
 		map__fixup_start(map);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 33ede53fa6b..e7295e93cff 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -109,6 +109,7 @@ struct symbol_conf {
 			show_nr_samples,
 			show_total_period,
 			use_callchain,
+			cumulate_callchain,
 			exclude_other,
 			show_cpu_utilization,
 			initialized,
@@ -117,7 +118,8 @@ struct symbol_conf {
 			annotate_src,
 			event_group,
 			demangle,
-			filter_relative;
+			filter_relative,
+			show_hist_headers;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
@@ -214,6 +216,7 @@ struct symsrc {
 	GElf_Shdr dynshdr;
 
 	bool adjust_symbols;
+	bool is_64_bit;
 #endif
 };
 
@@ -237,6 +240,11 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
 
+struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
+struct symbol *dso__next_symbol(struct symbol *sym);
+
+enum dso_type dso__type_fd(int fd);
+
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 int modules__parse(const char *filename, void *arg,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2fde0d5e40b..12c7a253a63 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -13,7 +13,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
 	struct thread *leader;
 	pid_t pid = thread->pid_;
 
-	if (pid == thread->tid) {
+	if (pid == thread->tid || pid == -1) {
 		thread->mg = map_groups__new();
 	} else {
 		leader = machine__findnew_thread(machine, pid, pid);
@@ -34,6 +34,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->pid_ = pid;
 		thread->tid = tid;
 		thread->ppid = -1;
+		thread->cpu = -1;
 		INIT_LIST_HEAD(&thread->comm_list);
 
 		comm_str = malloc(32);
@@ -60,8 +61,10 @@ void thread__delete(struct thread *thread)
 {
 	struct comm *comm, *tmp;
 
-	map_groups__put(thread->mg);
-	thread->mg = NULL;
+	if (thread->mg) {
+		map_groups__put(thread->mg);
+		thread->mg = NULL;
+	}
 	list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
 		list_del(&comm->list);
 		comm__free(comm);
@@ -127,12 +130,12 @@ int thread__comm_len(struct thread *thread)
 size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
 	return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) +
-	       map_groups__fprintf(thread->mg, verbose, fp);
+	       map_groups__fprintf(thread->mg, fp);
 }
 
 void thread__insert_map(struct thread *thread, struct map *map)
 {
-	map_groups__fixup_overlappings(thread->mg, map, verbose, stderr);
+	map_groups__fixup_overlappings(thread->mg, map, stderr);
 	map_groups__insert(thread->mg, map);
 }
 
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 3c0c2724f82..716b7723cce 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -17,6 +17,7 @@ struct thread {
 	pid_t			pid_; /* Not all tools update this */
 	pid_t			tid;
 	pid_t			ppid;
+	int			cpu;
 	char			shortname[3];
 	bool			comm_set;
 	bool			dead; /* if set thread has exited */
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 7e6fcfe8b43..eb72716017a 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -40,6 +40,7 @@
 #include "trace-event.h"
 #include <api/fs/debugfs.h>
 #include "evsel.h"
+#include "debug.h"
 
 #define VERSION "0.5"
 
@@ -191,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 		    strcmp(dent->d_name, "..") == 0 ||
 		    !name_in_tp_list(dent->d_name, tps))
 			continue;
-		format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
-		if (!format) {
+		if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
 			err = -ENOMEM;
 			goto out;
 		}
-		sprintf(format, "%s/%s/format", sys, dent->d_name);
 		ret = stat(format, &st);
 		free(format);
 		if (ret < 0)
@@ -217,12 +216,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 		    strcmp(dent->d_name, "..") == 0 ||
 		    !name_in_tp_list(dent->d_name, tps))
 			continue;
-		format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
-		if (!format) {
+		if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
 			err = -ENOMEM;
 			goto out;
 		}
-		sprintf(format, "%s/%s/format", sys, dent->d_name);
 		ret = stat(format, &st);
 
 		if (ret >= 0) {
@@ -317,12 +314,10 @@ static int record_event_files(struct tracepoint_path *tps)
 		    strcmp(dent->d_name, "ftrace") == 0 ||
 		    !system_in_tp_list(dent->d_name, tps))
 			continue;
-		sys = malloc(strlen(path) + strlen(dent->d_name) + 2);
-		if (!sys) {
+		if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) {
 			err = -ENOMEM;
 			goto out;
 		}
-		sprintf(sys, "%s/%s", path, dent->d_name);
 		ret = stat(sys, &st);
 		if (ret >= 0) {
 			ssize_t size = strlen(dent->d_name) + 1;
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index e113e180c48..54d9e9b548a 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -22,7 +22,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <getopt.h>
 #include <stdarg.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -36,6 +35,7 @@
 #include "../perf.h"
 #include "util.h"
 #include "trace-event.h"
+#include "debug.h"
 
 static int input_fd;
 
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
new file mode 100644
index 00000000000..4d4210d4e13
--- /dev/null
+++ b/tools/perf/util/tsc.c
@@ -0,0 +1,30 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#include "tsc.h"
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc)
+{
+	u64 t, quot, rem;
+
+	t = ns - tc->time_zero;
+	quot = t / tc->time_mult;
+	rem  = t % tc->time_mult;
+	return (quot << tc->time_shift) +
+	       (rem << tc->time_shift) / tc->time_mult;
+}
+
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
+{
+	u64 quot, rem;
+
+	quot = cyc >> tc->time_shift;
+	rem  = cyc & ((1 << tc->time_shift) - 1);
+	return tc->time_zero + quot * tc->time_mult +
+	       ((rem * tc->time_mult) >> tc->time_shift);
+}
+
+u64 __weak rdtsc(void)
+{
+	return 0;
+}
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
new file mode 100644
index 00000000000..a8b78f1b324
--- /dev/null
+++ b/tools/perf/util/tsc.h
@@ -0,0 +1,12 @@
+#ifndef __PERF_TSC_H
+#define __PERF_TSC_H
+
+#include <linux/types.h>
+
+#include "../arch/x86/util/tsc.h"
+
+u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
+u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
+u64 rdtsc(void);
+
+#endif
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 5ec80a575b5..7419768c38b 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -3,6 +3,7 @@
 #include <elfutils/libdwfl.h>
 #include <inttypes.h>
 #include <errno.h>
+#include "debug.h"
 #include "unwind.h"
 #include "unwind-libdw.h"
 #include "machine.h"
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index bd5768d74f0..92b56db5247 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -30,6 +30,7 @@
 #include "unwind.h"
 #include "symbol.h"
 #include "util.h"
+#include "debug.h"
 
 extern int
 UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
@@ -250,7 +251,6 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 
 	/* Check the .eh_frame section for unwinding info */
 	offset = elf_section_offset(fd, ".eh_frame_hdr");
-	close(fd);
 
 	if (offset)
 		ret = unwind_spec_ehframe(dso, machine, offset,
@@ -271,7 +271,6 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 
 	/* Check the .debug_frame section for unwinding info */
 	*offset = elf_section_offset(fd, ".debug_frame");
-	close(fd);
 
 	if (*offset)
 		return 0;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7fff6be07f0..e52e7461911 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,5 +1,6 @@
 #include "../perf.h"
 #include "util.h"
+#include "debug.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
@@ -17,6 +18,7 @@
  * XXX We need to find a better place for these things...
  */
 unsigned int page_size;
+int cacheline_size;
 
 bool test_attr__enabled;
 
@@ -332,12 +334,9 @@ const char *find_tracing_dir(void)
 	if (!debugfs)
 		return NULL;
 
-	tracing = malloc(strlen(debugfs) + 9);
-	if (!tracing)
+	if (asprintf(&tracing, "%s/tracing", debugfs) < 0)
 		return NULL;
 
-	sprintf(tracing, "%s/tracing", debugfs);
-
 	tracing_found = 1;
 	return tracing;
 }
@@ -351,11 +350,9 @@ char *get_tracing_file(const char *name)
 	if (!tracing)
 		return NULL;
 
-	file = malloc(strlen(tracing) + strlen(name) + 2);
-	if (!file)
+	if (asprintf(&file, "%s/%s", tracing, name) < 0)
 		return NULL;
 
-	sprintf(file, "%s/%s", tracing, name);
 	return file;
 }
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b03da44e94e..66864364ccb 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -304,6 +304,7 @@ char *rtrim(char *s);
 void dump_stack(void);
 
 extern unsigned int page_size;
+extern int cacheline_size;
 
 void get_term_dimensions(struct winsize *ws);
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 0ddb3b8a89e..adca69384fc 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -11,10 +11,34 @@
 #include "vdso.h"
 #include "util.h"
 #include "symbol.h"
+#include "machine.h"
 #include "linux/string.h"
+#include "debug.h"
 
-static bool vdso_found;
-static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX";
+#define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
+
+struct vdso_file {
+	bool found;
+	bool error;
+	char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)];
+	const char *dso_name;
+};
+
+struct vdso_info {
+	struct vdso_file vdso;
+};
+
+static struct vdso_info *vdso_info__new(void)
+{
+	static const struct vdso_info vdso_info_init = {
+		.vdso    = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSO,
+		},
+	};
+
+	return memdup(&vdso_info_init, sizeof(vdso_info_init));
+}
 
 static int find_vdso_map(void **start, void **end)
 {
@@ -47,7 +71,7 @@ static int find_vdso_map(void **start, void **end)
 	return !found;
 }
 
-static char *get_file(void)
+static char *get_file(struct vdso_file *vdso_file)
 {
 	char *vdso = NULL;
 	char *buf = NULL;
@@ -55,10 +79,10 @@ static char *get_file(void)
 	size_t size;
 	int fd;
 
-	if (vdso_found)
-		return vdso_file;
+	if (vdso_file->found)
+		return vdso_file->temp_file_name;
 
-	if (find_vdso_map(&start, &end))
+	if (vdso_file->error || find_vdso_map(&start, &end))
 		return NULL;
 
 	size = end - start;
@@ -67,45 +91,78 @@ static char *get_file(void)
 	if (!buf)
 		return NULL;
 
-	fd = mkstemp(vdso_file);
+	fd = mkstemp(vdso_file->temp_file_name);
 	if (fd < 0)
 		goto out;
 
 	if (size == (size_t) write(fd, buf, size))
-		vdso = vdso_file;
+		vdso = vdso_file->temp_file_name;
 
 	close(fd);
 
  out:
 	free(buf);
 
-	vdso_found = (vdso != NULL);
+	vdso_file->found = (vdso != NULL);
+	vdso_file->error = !vdso_file->found;
 	return vdso;
 }
 
-void vdso__exit(void)
+void vdso__exit(struct machine *machine)
 {
-	if (vdso_found)
-		unlink(vdso_file);
+	struct vdso_info *vdso_info = machine->vdso_info;
+
+	if (!vdso_info)
+		return;
+
+	if (vdso_info->vdso.found)
+		unlink(vdso_info->vdso.temp_file_name);
+
+	zfree(&machine->vdso_info);
 }
 
-struct dso *vdso__dso_findnew(struct list_head *head)
+static struct dso *vdso__new(struct machine *machine, const char *short_name,
+			     const char *long_name)
 {
-	struct dso *dso = dsos__find(head, VDSO__MAP_NAME, true);
+	struct dso *dso;
 
+	dso = dso__new(short_name);
+	if (dso != NULL) {
+		dsos__add(&machine->user_dsos, dso);
+		dso__set_long_name(dso, long_name, false);
+	}
+
+	return dso;
+}
+
+struct dso *vdso__dso_findnew(struct machine *machine,
+			      struct thread *thread __maybe_unused)
+{
+	struct vdso_info *vdso_info;
+	struct dso *dso;
+
+	if (!machine->vdso_info)
+		machine->vdso_info = vdso_info__new();
+
+	vdso_info = machine->vdso_info;
+	if (!vdso_info)
+		return NULL;
+
+	dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
 	if (!dso) {
 		char *file;
 
-		file = get_file();
+		file = get_file(&vdso_info->vdso);
 		if (!file)
 			return NULL;
 
-		dso = dso__new(VDSO__MAP_NAME);
-		if (dso != NULL) {
-			dsos__add(head, dso);
-			dso__set_long_name(dso, file, false);
-		}
+		dso = vdso__new(machine, DSO__NAME_VDSO, file);
 	}
 
 	return dso;
 }
+
+bool dso__is_vdso(struct dso *dso)
+{
+	return !strcmp(dso->short_name, DSO__NAME_VDSO);
+}
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index 0f76e7caf6f..af9d6929a21 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -7,12 +7,21 @@
 
 #define VDSO__MAP_NAME "[vdso]"
 
+#define DSO__NAME_VDSO "[vdso]"
+
 static inline bool is_vdso_map(const char *filename)
 {
 	return !strcmp(filename, VDSO__MAP_NAME);
 }
 
-struct dso *vdso__dso_findnew(struct list_head *head);
-void vdso__exit(void);
+struct dso;
+
+bool dso__is_vdso(struct dso *dso);
+
+struct machine;
+struct thread;
+
+struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread);
+void vdso__exit(struct machine *machine);
 
 #endif /* __PERF_VDSO__ */
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 40631569a0f..55ab700f6ba 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -72,7 +72,7 @@ my %default = (
     "IGNORE_UNUSED"		=> 0,
 );
 
-my $ktest_config;
+my $ktest_config = "ktest.conf";
 my $version;
 my $have_version = 0;
 my $machine;
@@ -149,7 +149,6 @@ my $bisect_ret_abort;
 my $bisect_ret_default;
 my $in_patchcheck = 0;
 my $run_test;
-my $redirect;
 my $buildlog;
 my $testlog;
 my $dmesg;
@@ -522,7 +521,7 @@ sub read_ync {
     return read_prompt 1, $prompt;
 }
 
-sub get_ktest_config {
+sub get_mandatory_config {
     my ($config) = @_;
     my $ans;
 
@@ -553,29 +552,29 @@ sub get_ktest_config {
     }
 }
 
-sub get_ktest_configs {
-    get_ktest_config("MACHINE");
-    get_ktest_config("BUILD_DIR");
-    get_ktest_config("OUTPUT_DIR");
+sub get_mandatory_configs {
+    get_mandatory_config("MACHINE");
+    get_mandatory_config("BUILD_DIR");
+    get_mandatory_config("OUTPUT_DIR");
 
     if ($newconfig) {
-	get_ktest_config("BUILD_OPTIONS");
+	get_mandatory_config("BUILD_OPTIONS");
     }
 
     # options required for other than just building a kernel
     if (!$buildonly) {
-	get_ktest_config("POWER_CYCLE");
-	get_ktest_config("CONSOLE");
+	get_mandatory_config("POWER_CYCLE");
+	get_mandatory_config("CONSOLE");
     }
 
     # options required for install and more
     if ($buildonly != 1) {
-	get_ktest_config("SSH_USER");
-	get_ktest_config("BUILD_TARGET");
-	get_ktest_config("TARGET_IMAGE");
+	get_mandatory_config("SSH_USER");
+	get_mandatory_config("BUILD_TARGET");
+	get_mandatory_config("TARGET_IMAGE");
     }
 
-    get_ktest_config("LOCALVERSION");
+    get_mandatory_config("LOCALVERSION");
 
     return if ($buildonly);
 
@@ -583,7 +582,7 @@ sub get_ktest_configs {
 
     if (!defined($rtype)) {
 	if (!defined($opt{"GRUB_MENU"})) {
-	    get_ktest_config("REBOOT_TYPE");
+	    get_mandatory_config("REBOOT_TYPE");
 	    $rtype = $entered_configs{"REBOOT_TYPE"};
 	} else {
 	    $rtype = "grub";
@@ -591,16 +590,16 @@ sub get_ktest_configs {
     }
 
     if ($rtype eq "grub") {
-	get_ktest_config("GRUB_MENU");
+	get_mandatory_config("GRUB_MENU");
     }
 
     if ($rtype eq "grub2") {
-	get_ktest_config("GRUB_MENU");
-	get_ktest_config("GRUB_FILE");
+	get_mandatory_config("GRUB_MENU");
+	get_mandatory_config("GRUB_FILE");
     }
 
     if ($rtype eq "syslinux") {
-	get_ktest_config("SYSLINUX_LABEL");
+	get_mandatory_config("SYSLINUX_LABEL");
     }
 }
 
@@ -1090,7 +1089,7 @@ sub read_config {
     $test_case = __read_config $config, \$test_num;
 
     # make sure we have all mandatory configs
-    get_ktest_configs;
+    get_mandatory_configs;
 
     # was a test specified?
     if (!$test_case) {
@@ -1529,7 +1528,7 @@ sub fail {
 }
 
 sub run_command {
-    my ($command) = @_;
+    my ($command, $redirect) = @_;
     my $dolog = 0;
     my $dord = 0;
     my $pid;
@@ -2265,9 +2264,7 @@ sub build {
     # Run old config regardless, to enforce min configurations
     make_oldconfig;
 
-    $redirect = "$buildlog";
-    my $build_ret = run_command "$make $build_options";
-    undef $redirect;
+    my $build_ret = run_command "$make $build_options", $buildlog;
 
     if (defined($post_build)) {
 	# Because a post build may change the kernel version
@@ -2360,9 +2357,7 @@ sub child_run_test {
     $poweroff_on_error = 0;
     $die_on_failure = 1;
 
-    $redirect = "$testlog";
-    run_command $run_test or $failed = 1;
-    undef $redirect;
+    run_command $run_test, $testlog or $failed = 1;
 
     exit $failed;
 }
@@ -2789,12 +2784,17 @@ my %dependency;
 sub assign_configs {
     my ($hash, $config) = @_;
 
+    doprint "Reading configs from $config\n";
+
     open (IN, $config)
 	or dodie "Failed to read $config";
 
     while (<IN>) {
+	chomp;
 	if (/^((CONFIG\S*)=.*)/) {
 	    ${$hash}{$2} = $1;
+	} elsif (/^(# (CONFIG\S*) is not set)/) {
+	    ${$hash}{$2} = $1;
 	}
     }
 
@@ -2807,27 +2807,6 @@ sub process_config_ignore {
     assign_configs \%config_ignore, $config;
 }
 
-sub read_current_config {
-    my ($config_ref) = @_;
-
-    %{$config_ref} = ();
-    undef %{$config_ref};
-
-    my @key = keys %{$config_ref};
-    if ($#key >= 0) {
-	print "did not delete!\n";
-	exit;
-    }
-    open (IN, "$output_config");
-
-    while (<IN>) {
-	if (/^(CONFIG\S+)=(.*)/) {
-	    ${$config_ref}{$1} = $2;
-	}
-    }
-    close(IN);
-}
-
 sub get_dependencies {
     my ($config) = @_;
 
@@ -2846,53 +2825,97 @@ sub get_dependencies {
     return @deps;
 }
 
+sub save_config {
+    my ($pc, $file) = @_;
+
+    my %configs = %{$pc};
+
+    doprint "Saving configs into $file\n";
+
+    open(OUT, ">$file") or dodie "Can not write to $file";
+
+    foreach my $config (keys %configs) {
+	print OUT "$configs{$config}\n";
+    }
+    close(OUT);
+}
+
 sub create_config {
-    my @configs = @_;
+    my ($name, $pc) = @_;
 
-    open(OUT, ">$output_config") or dodie "Can not write to $output_config";
+    doprint "Creating old config from $name configs\n";
 
-    foreach my $config (@configs) {
-	print OUT "$config_set{$config}\n";
-	my @deps = get_dependencies $config;
-	foreach my $dep (@deps) {
-	    print OUT "$config_set{$dep}\n";
+    save_config $pc, $output_config;
+
+    make_oldconfig;
+}
+
+# compare two config hashes, and return configs with different vals.
+# It returns B's config values, but you can use A to see what A was.
+sub diff_config_vals {
+    my ($pa, $pb) = @_;
+
+    # crappy Perl way to pass in hashes.
+    my %a = %{$pa};
+    my %b = %{$pb};
+
+    my %ret;
+
+    foreach my $item (keys %a) {
+	if (defined($b{$item}) && $b{$item} ne $a{$item}) {
+	    $ret{$item} = $b{$item};
 	}
     }
 
-    # turn off configs to keep off
-    foreach my $config (keys %config_off) {
-	print OUT "# $config is not set\n";
-    }
+    return %ret;
+}
 
-    # turn off configs that should be off for now
-    foreach my $config (@config_off_tmp) {
-	print OUT "# $config is not set\n";
-    }
+# compare two config hashes and return the configs in B but not A
+sub diff_configs {
+    my ($pa, $pb) = @_;
+
+    my %ret;
+
+    # crappy Perl way to pass in hashes.
+    my %a = %{$pa};
+    my %b = %{$pb};
 
-    foreach my $config (keys %config_ignore) {
-	print OUT "$config_ignore{$config}\n";
+    foreach my $item (keys %b) {
+	if (!defined($a{$item})) {
+	    $ret{$item} = $b{$item};
+	}
     }
-    close(OUT);
 
-    make_oldconfig;
+    return %ret;
 }
 
+# return if two configs are equal or not
+# 0 is equal +1 b has something a does not
+# +1 if a and b have a different item.
+# -1 if a has something b does not
 sub compare_configs {
-    my (%a, %b) = @_;
+    my ($pa, $pb) = @_;
 
-    foreach my $item (keys %a) {
-	if (!defined($b{$item})) {
-	    print "diff $item\n";
+    my %ret;
+
+    # crappy Perl way to pass in hashes.
+    my %a = %{$pa};
+    my %b = %{$pb};
+
+    foreach my $item (keys %b) {
+	if (!defined($a{$item})) {
+	    return 1;
+	}
+	if ($a{$item} ne $b{$item}) {
 	    return 1;
 	}
-	delete $b{$item};
     }
 
-    my @keys = keys %b;
-    if ($#keys) {
-	print "diff2 $keys[0]\n";
+    foreach my $item (keys %a) {
+	if (!defined($b{$item})) {
+	    return -1;
+	}
     }
-    return -1 if ($#keys >= 0);
 
     return 0;
 }
@@ -2900,24 +2923,13 @@ sub compare_configs {
 sub run_config_bisect_test {
     my ($type) = @_;
 
-    return run_bisect_test $type, "oldconfig";
-}
+    my $ret = run_bisect_test $type, "oldconfig";
 
-sub process_passed {
-    my (%configs) = @_;
-
-    doprint "These configs had no failure: (Enabling them for further compiles)\n";
-    # Passed! All these configs are part of a good compile.
-    # Add them to the min options.
-    foreach my $config (keys %configs) {
-	if (defined($config_list{$config})) {
-	    doprint " removing $config\n";
-	    $config_ignore{$config} = $config_list{$config};
-	    delete $config_list{$config};
-	}
+    if ($bisect_manual) {
+	$ret = answer_bisect;
     }
-    doprint "config copied to $outputdir/config_good\n";
-    run_command "cp -f $output_config $outputdir/config_good";
+
+    return $ret;
 }
 
 sub process_failed {
@@ -2928,253 +2940,225 @@ sub process_failed {
     doprint "***************************************\n\n";
 }
 
-sub run_config_bisect {
+# used for config bisecting
+my $good_config;
+my $bad_config;
 
-    my @start_list = keys %config_list;
+sub process_new_config {
+    my ($tc, $nc, $gc, $bc) = @_;
 
-    if ($#start_list < 0) {
-	doprint "No more configs to test!!!\n";
-	return -1;
+    my %tmp_config = %{$tc};
+    my %good_configs = %{$gc};
+    my %bad_configs = %{$bc};
+
+    my %new_configs;
+
+    my $runtest = 1;
+    my $ret;
+
+    create_config "tmp_configs", \%tmp_config;
+    assign_configs \%new_configs, $output_config;
+
+    $ret = compare_configs \%new_configs, \%bad_configs;
+    if (!$ret) {
+	doprint "New config equals bad config, try next test\n";
+	$runtest = 0;
+    }
+
+    if ($runtest) {
+	$ret = compare_configs \%new_configs, \%good_configs;
+	if (!$ret) {
+	    doprint "New config equals good config, try next test\n";
+	    $runtest = 0;
+	}
     }
 
-    doprint "***** RUN TEST ***\n";
+    %{$nc} = %new_configs;
+
+    return $runtest;
+}
+
+sub run_config_bisect {
+    my ($pgood, $pbad) = @_;
+
     my $type = $config_bisect_type;
+
+    my %good_configs = %{$pgood};
+    my %bad_configs = %{$pbad};
+
+    my %diff_configs = diff_config_vals \%good_configs, \%bad_configs;
+    my %b_configs = diff_configs \%good_configs, \%bad_configs;
+    my %g_configs = diff_configs \%bad_configs, \%good_configs;
+
+    my @diff_arr = keys %diff_configs;
+    my $len_diff = $#diff_arr + 1;
+
+    my @b_arr = keys %b_configs;
+    my $len_b = $#b_arr + 1;
+
+    my @g_arr = keys %g_configs;
+    my $len_g = $#g_arr + 1;
+
+    my $runtest = 1;
+    my %new_configs;
     my $ret;
-    my %current_config;
 
-    my $count = $#start_list + 1;
-    doprint "  $count configs to test\n";
+    # First, lets get it down to a single subset.
+    # Is the problem with a difference in values?
+    # Is the problem with a missing config?
+    # Is the problem with a config that breaks things?
 
-    my $half = int($#start_list / 2);
+    # Enable all of one set and see if we get a new bad
+    # or good config.
 
-    do {
-	my @tophalf = @start_list[0 .. $half];
+    # first set the good config to the bad values.
 
-	# keep the bottom half off
-	if ($half < $#start_list) {
-	    @config_off_tmp = @start_list[$half + 1 .. $#start_list];
-	} else {
-	    @config_off_tmp = ();
-	}
+    doprint "d=$len_diff g=$len_g b=$len_b\n";
 
-	create_config @tophalf;
-	read_current_config \%current_config;
-
-	$count = $#tophalf + 1;
-	doprint "Testing $count configs\n";
-	my $found = 0;
-	# make sure we test something
-	foreach my $config (@tophalf) {
-	    if (defined($current_config{$config})) {
-		logit " $config\n";
-		$found = 1;
-	    }
-	}
-	if (!$found) {
-	    # try the other half
-	    doprint "Top half produced no set configs, trying bottom half\n";
-
-	    # keep the top half off
-	    @config_off_tmp = @tophalf;
-	    @tophalf = @start_list[$half + 1 .. $#start_list];
-
-	    create_config @tophalf;
-	    read_current_config \%current_config;
-	    foreach my $config (@tophalf) {
-		if (defined($current_config{$config})) {
-		    logit " $config\n";
-		    $found = 1;
-		}
-	    }
-	    if (!$found) {
-		doprint "Failed: Can't make new config with current configs\n";
-		foreach my $config (@start_list) {
-		    doprint "  CONFIG: $config\n";
-		}
-		return -1;
+    # first lets enable things in bad config that are enabled in good config
+
+    if ($len_diff > 0) {
+	if ($len_b > 0 || $len_g > 0) {
+	    my %tmp_config = %bad_configs;
+
+	    doprint "Set tmp config to be bad config with good config values\n";
+	    foreach my $item (@diff_arr) {
+		$tmp_config{$item} = $good_configs{$item};
 	    }
-	    $count = $#tophalf + 1;
-	    doprint "Testing $count configs\n";
-	}
 
-	$ret = run_config_bisect_test $type;
-	if ($bisect_manual) {
-	    $ret = answer_bisect;
-	}
-	if ($ret) {
-	    process_passed %current_config;
-	    return 0;
+	    $runtest = process_new_config \%tmp_config, \%new_configs,
+			    \%good_configs, \%bad_configs;
 	}
+    }
 
-	doprint "This config had a failure.\n";
-	doprint "Removing these configs that were not set in this config:\n";
-	doprint "config copied to $outputdir/config_bad\n";
-	run_command "cp -f $output_config $outputdir/config_bad";
+    if (!$runtest && $len_diff > 0) {
 
-	# A config exists in this group that was bad.
-	foreach my $config (keys %config_list) {
-	    if (!defined($current_config{$config})) {
-		doprint " removing $config\n";
-		delete $config_list{$config};
-	    }
+	if ($len_diff == 1) {
+	    process_failed $diff_arr[0];
+	    return 1;
 	}
+	my %tmp_config = %bad_configs;
 
-	@start_list = @tophalf;
+	my $half = int($#diff_arr / 2);
+	my @tophalf = @diff_arr[0 .. $half];
 
-	if ($#start_list == 0) {
-	    process_failed $start_list[0];
-	    return 1;
+	doprint "Settings bisect with top half:\n";
+	doprint "Set tmp config to be bad config with some good config values\n";
+	foreach my $item (@tophalf) {
+	    $tmp_config{$item} = $good_configs{$item};
 	}
 
-	# remove half the configs we are looking at and see if
-	# they are good.
-	$half = int($#start_list / 2);
-    } while ($#start_list > 0);
+	$runtest = process_new_config \%tmp_config, \%new_configs,
+			    \%good_configs, \%bad_configs;
 
-    # we found a single config, try it again unless we are running manually
+	if (!$runtest) {
+	    my %tmp_config = %bad_configs;
 
-    if ($bisect_manual) {
-	process_failed $start_list[0];
-	return 1;
-    }
+	    doprint "Try bottom half\n";
 
-    my @tophalf = @start_list[0 .. 0];
+	    my @bottomhalf = @diff_arr[$half+1 .. $#diff_arr];
 
-    $ret = run_config_bisect_test $type;
-    if ($ret) {
-	process_passed %current_config;
+	    foreach my $item (@bottomhalf) {
+		$tmp_config{$item} = $good_configs{$item};
+	    }
+
+	    $runtest = process_new_config \%tmp_config, \%new_configs,
+			    \%good_configs, \%bad_configs;
+	}
+    }
+
+    if ($runtest) {
+	$ret = run_config_bisect_test $type;
+	if ($ret) {
+	    doprint "NEW GOOD CONFIG\n";
+	    %good_configs = %new_configs;
+	    run_command "mv $good_config ${good_config}.last";
+	    save_config \%good_configs, $good_config;
+	    %{$pgood} = %good_configs;
+	} else {
+	    doprint "NEW BAD CONFIG\n";
+	    %bad_configs = %new_configs;
+	    run_command "mv $bad_config ${bad_config}.last";
+	    save_config \%bad_configs, $bad_config;
+	    %{$pbad} = %bad_configs;
+	}
 	return 0;
     }
 
-    process_failed $start_list[0];
-    return 1;
+    fail "Hmm, need to do a mix match?\n";
+    return -1;
 }
 
 sub config_bisect {
     my ($i) = @_;
 
-    my $start_config = $config_bisect;
+    my $type = $config_bisect_type;
+    my $ret;
 
-    my $tmpconfig = "$tmpdir/use_config";
+    $bad_config = $config_bisect;
 
     if (defined($config_bisect_good)) {
-	process_config_ignore $config_bisect_good;
-    }
-
-    # Make the file with the bad config and the min config
-    if (defined($minconfig)) {
-	# read the min config for things to ignore
-	run_command "cp $minconfig $tmpconfig" or
-	    dodie "failed to copy $minconfig to $tmpconfig";
+	$good_config = $config_bisect_good;
+    } elsif (defined($minconfig)) {
+	$good_config = $minconfig;
     } else {
-	unlink $tmpconfig;
-    }
-
-    if (-f $tmpconfig) {
-	load_force_config($tmpconfig);
-	process_config_ignore $tmpconfig;
-    }
-
-    # now process the start config
-    run_command "cp $start_config $output_config" or
-	dodie "failed to copy $start_config to $output_config";
-
-    # read directly what we want to check
-    my %config_check;
-    open (IN, $output_config)
-	or dodie "failed to open $output_config";
-
-    while (<IN>) {
-	if (/^((CONFIG\S*)=.*)/) {
-	    $config_check{$2} = $1;
+	doprint "No config specified, checking if defconfig works";
+	$ret = run_bisect_test $type, "defconfig";
+	if (!$ret) {
+	    fail "Have no good config to compare with, please set CONFIG_BISECT_GOOD";
+	    return 1;
 	}
+	$good_config = $output_config;
     }
-    close(IN);
 
-    # Now run oldconfig with the minconfig
-    make_oldconfig;
+    # we don't want min configs to cause issues here.
+    doprint "Disabling 'MIN_CONFIG' for this test\n";
+    undef $minconfig;
 
-    # check to see what we lost (or gained)
-    open (IN, $output_config)
-	or dodie "Failed to read $start_config";
+    my %good_configs;
+    my %bad_configs;
+    my %tmp_configs;
 
-    my %removed_configs;
-    my %added_configs;
+    doprint "Run good configs through make oldconfig\n";
+    assign_configs \%tmp_configs, $good_config;
+    create_config "$good_config", \%tmp_configs;
+    assign_configs \%good_configs, $output_config;
 
-    while (<IN>) {
-	if (/^((CONFIG\S*)=.*)/) {
-	    # save off all options
-	    $config_set{$2} = $1;
-	    if (defined($config_check{$2})) {
-		if (defined($config_ignore{$2})) {
-		    $removed_configs{$2} = $1;
-		} else {
-		    $config_list{$2} = $1;
-		}
-	    } elsif (!defined($config_ignore{$2})) {
-		$added_configs{$2} = $1;
-		$config_list{$2} = $1;
-	    }
-	} elsif (/^# ((CONFIG\S*).*)/) {
-	    # Keep these configs disabled
-	    $config_set{$2} = $1;
-	    $config_off{$2} = $1;
-	}
-    }
-    close(IN);
+    doprint "Run bad configs through make oldconfig\n";
+    assign_configs \%tmp_configs, $bad_config;
+    create_config "$bad_config", \%tmp_configs;
+    assign_configs \%bad_configs, $output_config;
 
-    my @confs = keys %removed_configs;
-    if ($#confs >= 0) {
-	doprint "Configs overridden by default configs and removed from check:\n";
-	foreach my $config (@confs) {
-	    doprint " $config\n";
-	}
-    }
-    @confs = keys %added_configs;
-    if ($#confs >= 0) {
-	doprint "Configs appearing in make oldconfig and added:\n";
-	foreach my $config (@confs) {
-	    doprint " $config\n";
-	}
-    }
+    $good_config = "$tmpdir/good_config";
+    $bad_config = "$tmpdir/bad_config";
+
+    save_config \%good_configs, $good_config;
+    save_config \%bad_configs, $bad_config;
 
-    my %config_test;
-    my $once = 0;
 
-    @config_off_tmp = ();
+    if (defined($config_bisect_check) && $config_bisect_check ne "0") {
+	if ($config_bisect_check ne "good") {
+	    doprint "Testing bad config\n";
 
-    # Sometimes kconfig does weird things. We must make sure
-    # that the config we autocreate has everything we need
-    # to test, otherwise we may miss testing configs, or
-    # may not be able to create a new config.
-    # Here we create a config with everything set.
-    create_config (keys %config_list);
-    read_current_config \%config_test;
-    foreach my $config (keys %config_list) {
-	if (!defined($config_test{$config})) {
-	    if (!$once) {
-		$once = 1;
-		doprint "Configs not produced by kconfig (will not be checked):\n";
+	    $ret = run_bisect_test $type, "useconfig:$bad_config";
+	    if ($ret) {
+		fail "Bad config succeeded when expected to fail!";
+		return 0;
 	    }
-	    doprint "  $config\n";
-	    delete $config_list{$config};
 	}
-    }
-    my $ret;
+	if ($config_bisect_check ne "bad") {
+	    doprint "Testing good config\n";
 
-    if (defined($config_bisect_check) && $config_bisect_check) {
-	doprint " Checking to make sure bad config with min config fails\n";
-	create_config keys %config_list;
-	$ret = run_config_bisect_test $config_bisect_type;
-	if ($ret) {
-	    doprint " FAILED! Bad config with min config boots fine\n";
-	    return -1;
+	    $ret = run_bisect_test $type, "useconfig:$good_config";
+	    if (!$ret) {
+		fail "Good config failed when expected to succeed!";
+		return 0;
+	    }
 	}
-	doprint " Bad config with min config fails as expected\n";
     }
 
     do {
-	$ret = run_config_bisect;
+	$ret = run_config_bisect \%good_configs, \%bad_configs;
     } while (!$ret);
 
     return $ret if ($ret < 0);
@@ -3455,29 +3439,6 @@ sub read_depends {
     read_kconfig($kconfig);
 }
 
-sub read_config_list {
-    my ($config) = @_;
-
-    open (IN, $config)
-	or dodie "Failed to read $config";
-
-    while (<IN>) {
-	if (/^((CONFIG\S*)=.*)/) {
-	    if (!defined($config_ignore{$2})) {
-		$config_list{$2} = $1;
-	    }
-	}
-    }
-
-    close(IN);
-}
-
-sub read_output_config {
-    my ($config) = @_;
-
-    assign_configs \%config_ignore, $config;
-}
-
 sub make_new_config {
     my @configs = @_;
 
@@ -3863,7 +3824,7 @@ sub make_warnings_file {
     success $i;
 }
 
-$#ARGV < 1 or die "ktest.pl version: $VERSION\n   usage: ktest.pl config-file\n";
+$#ARGV < 1 or die "ktest.pl version: $VERSION\n   usage: ktest.pl [config-file]\n";
 
 if ($#ARGV == 0) {
     $ktest_config = $ARGV[0];
@@ -3873,8 +3834,6 @@ if ($#ARGV == 0) {
 	    exit 0;
 	}
     }
-} else {
-    $ktest_config = "ktest.conf";
 }
 
 if (! -f $ktest_config) {
diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index 172eec4517f..911e45ad657 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -1098,49 +1098,35 @@
 #
 #  The way it works is this:
 #
-#   First it finds a config to work with. Since a different version, or
-#   MIN_CONFIG may cause different dependecies, it must run through this
-#   preparation.
+#   You can specify a good config with CONFIG_BISECT_GOOD, otherwise it
+#   will use the MIN_CONFIG, and if that's not specified, it will use
+#   the config that comes with "make defconfig".
 #
-#   Overwrites any config set in the bad config with a config set in
-#   either the MIN_CONFIG or ADD_CONFIG. Thus, make sure these configs
-#   are minimal and do not disable configs you want to test:
-#   (ie.  # CONFIG_FOO is not set).
+#   It runs both the good and bad configs through a make oldconfig to
+#   make sure that they are set up for the kernel that is checked out.
 #
-#   An oldconfig is run on the bad config and any new config that
-#   appears will be added to the configs to test.
+#   It then reads the configs that are set, as well as the ones that are
+#   not set for both the good and bad configs, and then compares them.
+#   It will set half of the good configs within the bad config (note,
+#   "set" means to make the bad config match the good config, a config
+#   in the good config that is off, will be turned off in the bad
+#   config. That is considered a "set").
 #
-#   Finally, it generates a config with the above result and runs it
-#   again through make oldconfig to produce a config that should be
-#   satisfied by kconfig.
+#   It tests this new config and if it works, it becomes the new good
+#   config, otherwise it becomes the new bad config. It continues this
+#   process until there's only one config left and it will report that
+#   config.
 #
-#   Then it starts the bisect.
+#   The "bad config" can also be a config that is needed to boot but was
+#   disabled because it depended on something that wasn't set.
 #
-#   The configs to test are cut in half. If all the configs in this
-#   half depend on a config in the other half, then the other half
-#   is tested instead. If no configs are enabled by either half, then
-#   this means a circular dependency exists and the test fails.
+#   During this process, it saves the current good and bad configs in
+#   ${TMP_DIR}/good_config and ${TMP_DIR}/bad_config respectively.
+#   If you stop the test, you can copy them to a new location to
+#   reuse them again.
 #
-#   A config is created with the test half, and the bisect test is run.
-#
-#   If the bisect succeeds, then all configs in the generated config
-#   are removed from the configs to test and added to the configs that
-#   will be enabled for all builds (they will be enabled, but not be part
-#   of the configs to examine).
-#
-#   If the bisect fails, then all test configs that were not enabled by
-#   the config file are removed from the test. These configs will not
-#   be enabled in future tests. Since current config failed, we consider
-#   this to be a subset of the config that we started with.
-#
-#   When we are down to one config, it is considered the bad config.
-#
-#   Note, the config chosen may not be the true bad config. Due to
-#   dependencies and selections of the kbuild system, mulitple
-#   configs may be needed to cause a failure. If you disable the
-#   config that was found and restart the test, if the test fails
-#   again, it is recommended to rerun the config_bisect with a new
-#   bad config without the found config enabled.
+#   Although the MIN_CONFIG may be the config it starts with, the
+#   MIN_CONFIG is ignored.
 #
 #  The option BUILD_TYPE will be ignored.
 #
@@ -1160,13 +1146,16 @@
 # CONFIG_BISECT_GOOD (optional)
 #  If you have a good config to start with, then you
 #  can specify it with CONFIG_BISECT_GOOD. Otherwise
-#  the MIN_CONFIG is the base.
+#  the MIN_CONFIG is the base, if MIN_CONFIG is not set
+#  It will build a config with "make defconfig"
 #
 # CONFIG_BISECT_CHECK (optional)
 #  Set this to 1 if you want to confirm that the config ktest
 #  generates (the bad config with the min config) is still bad.
 #  It may be that the min config fixes what broke the bad config
 #  and the test will not return a result.
+#  Set it to "good" to test only the good config and set it
+#  to "bad" to only test the bad config.
 #
 # Example:
 #   TEST_START
diff --git a/tools/testing/selftests/cpu-hotplug/Makefile b/tools/testing/selftests/cpu-hotplug/Makefile
index ae5faf9aade..790c23a9db4 100644
--- a/tools/testing/selftests/cpu-hotplug/Makefile
+++ b/tools/testing/selftests/cpu-hotplug/Makefile
@@ -1,6 +1,6 @@
 all:
 
 run_tests:
-	@/bin/sh ./on-off-test.sh || echo "cpu-hotplug selftests: [FAIL]"
+	@/bin/bash ./on-off-test.sh || echo "cpu-hotplug selftests: [FAIL]"
 
 clean:
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index aa290c0de6f..552f0810bff 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -193,6 +193,11 @@ int main(int argc, char **argv)
 	int msg, pid, err;
 	struct msgque_data msgque;
 
+	if (getuid() != 0) {
+		printf("Please run the test as root - Exiting.\n");
+		exit(1);
+	}
+
 	msgque.key = ftok(argv[0], 822155650);
 	if (msgque.key == -1) {
 		printf("Can't make key\n");
diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
index 350bfeda3aa..058c76f5d10 100644
--- a/tools/testing/selftests/memory-hotplug/Makefile
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -1,6 +1,6 @@
 all:
 
 run_tests:
-	@/bin/sh ./on-off-test.sh || echo "memory-hotplug selftests: [FAIL]"
+	@/bin/bash ./on-off-test.sh || echo "memory-hotplug selftests: [FAIL]"
 
 clean:
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 750512ba2c8..c7493b8f9b0 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -14,6 +14,12 @@ all: $(NET_PROGS)
 run_tests: all
 	@/bin/sh ./run_netsocktests || echo "sockettests: [FAIL]"
 	@/bin/sh ./run_afpackettests || echo "afpackettests: [FAIL]"
-
+	@if /sbin/modprobe test_bpf ; then \
+		/sbin/rmmod test_bpf; \
+		echo "test_bpf: ok"; \
+	else \
+		echo "test_bpf: [FAIL]"; \
+		exit 1; \
+	fi
 clean:
 	$(RM) $(NET_PROGS)
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 316194f26ff..54833a791a4 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -13,7 +13,7 @@ CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CUR
 
 export CC CFLAGS
 
-TARGETS = pmu copyloops
+TARGETS = pmu copyloops mm tm
 
 endif
 
diff --git a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h
index ccd9c84c4e3..d1dc3742551 100644
--- a/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h
+++ b/tools/testing/selftests/powerpc/copyloops/asm/ppc_asm.h
@@ -46,12 +46,15 @@
 #define R20 r20
 #define R21 r21
 #define R22 r22
+#define R29 r29
+#define R30 r30
+#define R31 r31
 
 #define STACKFRAMESIZE	256
-#define STK_PARAM(i)	(48 + ((i)-3)*8)
 #define STK_REG(i)	(112 + ((i)-14)*8)
 
 #define _GLOBAL(A) FUNC_START(test_ ## A)
+#define _GLOBAL_TOC(A) _GLOBAL(A)
 
 #define PPC_MTOCRF(A, B)	mtocrf A, B
 
diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c
index e80c42a584f..8ebc58a0931 100644
--- a/tools/testing/selftests/powerpc/harness.c
+++ b/tools/testing/selftests/powerpc/harness.c
@@ -30,12 +30,15 @@ int run_test(int (test_function)(void), char *name)
 
 	pid = fork();
 	if (pid == 0) {
+		setpgid(0, 0);
 		exit(test_function());
 	} else if (pid == -1) {
 		perror("fork");
 		return 1;
 	}
 
+	setpgid(pid, pid);
+
 	/* Wake us up in timeout seconds */
 	alarm(TIMEOUT);
 	terminated = false;
@@ -50,17 +53,20 @@ wait:
 
 		if (terminated) {
 			printf("!! force killing %s\n", name);
-			kill(pid, SIGKILL);
+			kill(-pid, SIGKILL);
 			return 1;
 		} else {
 			printf("!! killing %s\n", name);
-			kill(pid, SIGTERM);
+			kill(-pid, SIGTERM);
 			terminated = true;
 			alarm(KILL_TIMEOUT);
 			goto wait;
 		}
 	}
 
+	/* Kill anything else in the process group that is still running */
+	kill(-pid, SIGTERM);
+
 	if (WIFEXITED(status))
 		status = WEXITSTATUS(status);
 	else {
@@ -99,7 +105,10 @@ int test_harness(int (test_function)(void), char *name)
 
 	rc = run_test(test_function, name);
 
-	test_finish(name, rc);
+	if (rc == MAGIC_SKIP_RETURN_VALUE)
+		test_skip(name);
+	else
+		test_finish(name, rc);
 
 	return rc;
 }
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
new file mode 100644
index 00000000000..357ccbd6bad
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -0,0 +1,18 @@
+noarg:
+	$(MAKE) -C ../
+
+PROGS := hugetlb_vs_thp_test
+
+all: $(PROGS)
+
+$(PROGS): ../harness.c
+
+run_tests: all
+	@-for PROG in $(PROGS); do \
+		./$$PROG; \
+	done;
+
+clean:
+	rm -f $(PROGS)
+
+.PHONY: all run_tests clean
diff --git a/tools/testing/selftests/powerpc/mm/hugetlb_vs_thp_test.c b/tools/testing/selftests/powerpc/mm/hugetlb_vs_thp_test.c
new file mode 100644
index 00000000000..3d8e5b033e1
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/hugetlb_vs_thp_test.c
@@ -0,0 +1,72 @@
+#include <stdio.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+/* This must match the huge page & THP size */
+#define SIZE	(16 * 1024 * 1024)
+
+static int test_body(void)
+{
+	void *addr;
+	char *p;
+
+	addr = (void *)0xa0000000;
+
+	p = mmap(addr, SIZE, PROT_READ | PROT_WRITE,
+		 MAP_HUGETLB | MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (p != MAP_FAILED) {
+		/*
+		 * Typically the mmap will fail because no huge pages are
+		 * allocated on the system. But if there are huge pages
+		 * allocated the mmap will succeed. That's fine too, we just
+		 * munmap here before continuing.
+		 */
+		munmap(addr, SIZE);
+	}
+
+	p = mmap(addr, SIZE, PROT_READ | PROT_WRITE,
+		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (p == MAP_FAILED) {
+		printf("Mapping failed @ %p\n", addr);
+		perror("mmap");
+		return 1;
+	}
+
+	/*
+	 * Either a user or kernel access is sufficient to trigger the bug.
+	 * A kernel access is easier to spot & debug, as it will trigger the
+	 * softlockup or RCU stall detectors, and when the system is kicked
+	 * into xmon we get a backtrace in the kernel.
+	 *
+	 * A good option is:
+	 *  getcwd(p, SIZE);
+	 *
+	 * For the purposes of this testcase it's preferable to spin in
+	 * userspace, so the harness can kill us if we get stuck. That way we
+	 * see a test failure rather than a dead system.
+	 */
+	*p = 0xf;
+
+	munmap(addr, SIZE);
+
+	return 0;
+}
+
+static int test_main(void)
+{
+	int i;
+
+	/* 10,000 because it's a "bunch", and completes reasonably quickly */
+	for (i = 0; i < 10000; i++)
+		if (test_body())
+			return 1;
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_main, "hugetlb_vs_thp");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index 7216f009165..b9ff0db42c7 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -4,7 +4,7 @@ noarg:
 PROGS := count_instructions
 EXTRA_SOURCES := ../harness.c event.c
 
-all: $(PROGS)
+all: $(PROGS) sub_all
 
 $(PROGS): $(EXTRA_SOURCES)
 
@@ -12,12 +12,30 @@ $(PROGS): $(EXTRA_SOURCES)
 count_instructions: loop.S count_instructions.c $(EXTRA_SOURCES)
 	$(CC) $(CFLAGS) -m64 -o $@ $^
 
-run_tests: all
+run_tests: all sub_run_tests
 	@-for PROG in $(PROGS); do \
 		./$$PROG; \
 	done;
 
-clean:
+clean: sub_clean
 	rm -f $(PROGS) loop.o
 
-.PHONY: all run_tests clean
+
+SUB_TARGETS = ebb
+
+sub_all:
+	@for TARGET in $(SUB_TARGETS); do \
+		$(MAKE) -C $$TARGET all; \
+	done;
+
+sub_run_tests: all
+	@for TARGET in $(SUB_TARGETS); do \
+		$(MAKE) -C $$TARGET run_tests; \
+	done;
+
+sub_clean:
+	@for TARGET in $(SUB_TARGETS); do \
+		$(MAKE) -C $$TARGET clean; \
+	done;
+
+.PHONY: all run_tests clean sub_all sub_run_tests sub_clean
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
new file mode 100644
index 00000000000..edbba2affc2
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile
@@ -0,0 +1,32 @@
+noarg:
+	$(MAKE) -C ../../
+
+# The EBB handler is 64-bit code and everything links against it
+CFLAGS += -m64
+
+PROGS := reg_access_test event_attributes_test cycles_test	\
+	 cycles_with_freeze_test pmc56_overflow_test		\
+	 ebb_vs_cpu_event_test cpu_event_vs_ebb_test		\
+	 cpu_event_pinned_vs_ebb_test task_event_vs_ebb_test	\
+	 task_event_pinned_vs_ebb_test multi_ebb_procs_test	\
+	 multi_counter_test pmae_handling_test			\
+	 close_clears_pmcc_test instruction_count_test		\
+	 fork_cleanup_test ebb_on_child_test			\
+	 ebb_on_willing_child_test back_to_back_ebbs_test	\
+	 lost_exception_test no_handler_test
+
+all: $(PROGS)
+
+$(PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c
+
+instruction_count_test: ../loop.S
+
+lost_exception_test: ../lib.c
+
+run_tests: all
+	@-for PROG in $(PROGS); do \
+		./$$PROG; \
+	done;
+
+clean:
+	rm -f $(PROGS)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
new file mode 100644
index 00000000000..66ea765c0e7
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -0,0 +1,106 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "ebb.h"
+
+
+#define NUMBER_OF_EBBS	50
+
+/*
+ * Test that if we overflow the counter while in the EBB handler, we take
+ * another EBB on exiting from the handler.
+ *
+ * We do this by counting with a stupidly low sample period, causing us to
+ * overflow the PMU while we're still in the EBB handler, leading to another
+ * EBB.
+ *
+ * We get out of what would otherwise be an infinite loop by leaving the
+ * counter frozen once we've taken enough EBBs.
+ */
+
+static void ebb_callee(void)
+{
+	uint64_t siar, val;
+
+	val = mfspr(SPRN_BESCR);
+	if (!(val & BESCR_PMEO)) {
+		ebb_state.stats.spurious++;
+		goto out;
+	}
+
+	ebb_state.stats.ebb_count++;
+	trace_log_counter(ebb_state.trace, ebb_state.stats.ebb_count);
+
+	/* Resets the PMC */
+	count_pmc(1, sample_period);
+
+out:
+	if (ebb_state.stats.ebb_count == NUMBER_OF_EBBS)
+		/* Reset but leave counters frozen */
+		reset_ebb_with_clear_mask(MMCR0_PMAO);
+	else
+		/* Unfreezes */
+		reset_ebb();
+
+	/* Do some stuff to chew some cycles and pop the counter */
+	siar = mfspr(SPRN_SIAR);
+	trace_log_reg(ebb_state.trace, SPRN_SIAR, siar);
+
+	val = mfspr(SPRN_PMC1);
+	trace_log_reg(ebb_state.trace, SPRN_PMC1, val);
+
+	val = mfspr(SPRN_MMCR0);
+	trace_log_reg(ebb_state.trace, SPRN_MMCR0, val);
+}
+
+int back_to_back_ebbs(void)
+{
+	struct event event;
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+
+	setup_ebb_handler(ebb_callee);
+
+	FAIL_IF(ebb_event_enable(&event));
+
+	sample_period = 5;
+
+	ebb_freeze_pmcs();
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+	ebb_global_enable();
+	ebb_unfreeze_pmcs();
+
+	while (ebb_state.stats.ebb_count < NUMBER_OF_EBBS)
+		FAIL_IF(core_busy_loop());
+
+	ebb_global_disable();
+	ebb_freeze_pmcs();
+
+	count_pmc(1, sample_period);
+
+	dump_ebb_state();
+
+	event_close(&event);
+
+	FAIL_IF(ebb_state.stats.ebb_count != NUMBER_OF_EBBS);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(back_to_back_ebbs, "back_to_back_ebbs");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/close_clears_pmcc_test.c b/tools/testing/selftests/powerpc/pmu/ebb/close_clears_pmcc_test.c
new file mode 100644
index 00000000000..0f0423dba18
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/close_clears_pmcc_test.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <setjmp.h>
+#include <signal.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test that closing the EBB event clears MMCR0_PMCC, preventing further access
+ * by userspace to the PMU hardware.
+ */
+
+int close_clears_pmcc(void)
+{
+	struct event event;
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	FAIL_IF(event_open(&event));
+
+	ebb_enable_pmc_counting(1);
+	setup_ebb_handler(standard_ebb_callee);
+	ebb_global_enable();
+	FAIL_IF(ebb_event_enable(&event));
+
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+
+	while (ebb_state.stats.ebb_count < 1)
+		FAIL_IF(core_busy_loop());
+
+	ebb_global_disable();
+	event_close(&event);
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0);
+
+	/* The real test is here, do we take a SIGILL when writing PMU regs now
+	 * that we have closed the event. We expect that we will. */
+
+	FAIL_IF(catch_sigill(write_pmc1));
+
+	/* We should still be able to read EBB regs though */
+	mfspr(SPRN_EBBHR);
+	mfspr(SPRN_EBBRR);
+	mfspr(SPRN_BESCR);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(close_clears_pmcc, "close_clears_pmcc");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c
new file mode 100644
index 00000000000..d3ed64d5d6c
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_pinned_vs_ebb_test.c
@@ -0,0 +1,93 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "ebb.h"
+
+
+/*
+ * Tests a pinned cpu event vs an EBB - in that order. The pinned cpu event
+ * should remain and the EBB event should fail to enable.
+ */
+
+static int setup_cpu_event(struct event *event, int cpu)
+{
+	event_init_named(event, 0x400FA, "PM_RUN_INST_CMPL");
+
+	event->attr.pinned = 1;
+
+	event->attr.exclude_kernel = 1;
+	event->attr.exclude_hv = 1;
+	event->attr.exclude_idle = 1;
+
+	SKIP_IF(require_paranoia_below(1));
+	FAIL_IF(event_open_with_cpu(event, cpu));
+	FAIL_IF(event_enable(event));
+
+	return 0;
+}
+
+int cpu_event_pinned_vs_ebb(void)
+{
+	union pipe read_pipe, write_pipe;
+	struct event event;
+	int cpu, rc;
+	pid_t pid;
+
+	cpu = pick_online_cpu();
+	FAIL_IF(cpu < 0);
+	FAIL_IF(bind_to_cpu(cpu));
+
+	FAIL_IF(pipe(read_pipe.fds) == -1);
+	FAIL_IF(pipe(write_pipe.fds) == -1);
+
+	pid = fork();
+	if (pid == 0) {
+		/* NB order of pipes looks reversed */
+		exit(ebb_child(write_pipe, read_pipe));
+	}
+
+	/* We setup the cpu event first */
+	rc = setup_cpu_event(&event, cpu);
+	if (rc) {
+		kill_child_and_wait(pid);
+		return rc;
+	}
+
+	/* Signal the child to install its EBB event and wait */
+	if (sync_with_child(read_pipe, write_pipe))
+		/* If it fails, wait for it to exit */
+		goto wait;
+
+	/* Signal the child to run */
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+wait:
+	/* We expect it to fail to read the event */
+	FAIL_IF(wait_for_child(pid) != 2);
+
+	FAIL_IF(event_disable(&event));
+	FAIL_IF(event_read(&event));
+
+	event_report(&event);
+
+	/* The cpu event should have run */
+	FAIL_IF(event.result.value == 0);
+	FAIL_IF(event.result.enabled != event.result.running);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(cpu_event_pinned_vs_ebb, "cpu_event_pinned_vs_ebb");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c
new file mode 100644
index 00000000000..8b972c2aa39
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cpu_event_vs_ebb_test.c
@@ -0,0 +1,89 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "ebb.h"
+
+
+/*
+ * Tests a cpu event vs an EBB - in that order. The EBB should force the cpu
+ * event off the PMU.
+ */
+
+static int setup_cpu_event(struct event *event, int cpu)
+{
+	event_init_named(event, 0x400FA, "PM_RUN_INST_CMPL");
+
+	event->attr.exclude_kernel = 1;
+	event->attr.exclude_hv = 1;
+	event->attr.exclude_idle = 1;
+
+	SKIP_IF(require_paranoia_below(1));
+	FAIL_IF(event_open_with_cpu(event, cpu));
+	FAIL_IF(event_enable(event));
+
+	return 0;
+}
+
+int cpu_event_vs_ebb(void)
+{
+	union pipe read_pipe, write_pipe;
+	struct event event;
+	int cpu, rc;
+	pid_t pid;
+
+	cpu = pick_online_cpu();
+	FAIL_IF(cpu < 0);
+	FAIL_IF(bind_to_cpu(cpu));
+
+	FAIL_IF(pipe(read_pipe.fds) == -1);
+	FAIL_IF(pipe(write_pipe.fds) == -1);
+
+	pid = fork();
+	if (pid == 0) {
+		/* NB order of pipes looks reversed */
+		exit(ebb_child(write_pipe, read_pipe));
+	}
+
+	/* We setup the cpu event first */
+	rc = setup_cpu_event(&event, cpu);
+	if (rc) {
+		kill_child_and_wait(pid);
+		return rc;
+	}
+
+	/* Signal the child to install its EBB event and wait */
+	if (sync_with_child(read_pipe, write_pipe))
+		/* If it fails, wait for it to exit */
+		goto wait;
+
+	/* Signal the child to run */
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+wait:
+	/* We expect the child to succeed */
+	FAIL_IF(wait_for_child(pid));
+
+	FAIL_IF(event_disable(&event));
+	FAIL_IF(event_read(&event));
+
+	event_report(&event);
+
+	/* The cpu event may have run */
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(cpu_event_vs_ebb, "cpu_event_vs_ebb");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
new file mode 100644
index 00000000000..8590fc1bfc0
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -0,0 +1,58 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "ebb.h"
+
+
+/*
+ * Basic test that counts user cycles and takes EBBs.
+ */
+int cycles(void)
+{
+	struct event event;
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+
+	ebb_enable_pmc_counting(1);
+	setup_ebb_handler(standard_ebb_callee);
+	ebb_global_enable();
+	FAIL_IF(ebb_event_enable(&event));
+
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+
+	while (ebb_state.stats.ebb_count < 10) {
+		FAIL_IF(core_busy_loop());
+		FAIL_IF(ebb_check_mmcr0());
+	}
+
+	ebb_global_disable();
+	ebb_freeze_pmcs();
+
+	count_pmc(1, sample_period);
+
+	dump_ebb_state();
+
+	event_close(&event);
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0);
+	FAIL_IF(!ebb_check_count(1, sample_period, 100));
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(cycles, "cycles");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
new file mode 100644
index 00000000000..754b3f2008d
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -0,0 +1,117 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test of counting cycles while using MMCR0_FC (freeze counters) to only count
+ * parts of the code. This is complicated by the fact that FC is set by the
+ * hardware when the event overflows. We may take the EBB after we have set FC,
+ * so we have to be careful about whether we clear FC at the end of the EBB
+ * handler or not.
+ */
+
+static bool counters_frozen = false;
+static int ebbs_while_frozen = 0;
+
+static void ebb_callee(void)
+{
+	uint64_t mask, val;
+
+	mask = MMCR0_PMAO | MMCR0_FC;
+
+	val = mfspr(SPRN_BESCR);
+	if (!(val & BESCR_PMEO)) {
+		ebb_state.stats.spurious++;
+		goto out;
+	}
+
+	ebb_state.stats.ebb_count++;
+	trace_log_counter(ebb_state.trace, ebb_state.stats.ebb_count);
+
+	val = mfspr(SPRN_MMCR0);
+	trace_log_reg(ebb_state.trace, SPRN_MMCR0, val);
+
+	if (counters_frozen) {
+		trace_log_string(ebb_state.trace, "frozen");
+		ebbs_while_frozen++;
+		mask &= ~MMCR0_FC;
+	}
+
+	count_pmc(1, sample_period);
+out:
+	reset_ebb_with_clear_mask(mask);
+}
+
+int cycles_with_freeze(void)
+{
+	struct event event;
+	uint64_t val;
+	bool fc_cleared;
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+
+	setup_ebb_handler(ebb_callee);
+	ebb_global_enable();
+	FAIL_IF(ebb_event_enable(&event));
+
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+
+	fc_cleared = false;
+
+	/* Make sure we loop until we take at least one EBB */
+	while ((ebb_state.stats.ebb_count < 20 && !fc_cleared) ||
+		ebb_state.stats.ebb_count < 1)
+	{
+		counters_frozen = false;
+		mb();
+		mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC);
+
+		FAIL_IF(core_busy_loop());
+
+		counters_frozen = true;
+		mb();
+		mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) |  MMCR0_FC);
+
+		val = mfspr(SPRN_MMCR0);
+		if (! (val & MMCR0_FC)) {
+			printf("Outside of loop, FC NOT set MMCR0 0x%lx\n", val);
+			fc_cleared = true;
+		}
+	}
+
+	ebb_global_disable();
+	ebb_freeze_pmcs();
+
+	count_pmc(1, sample_period);
+
+	dump_ebb_state();
+
+	printf("EBBs while frozen %d\n", ebbs_while_frozen);
+
+	event_close(&event);
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0);
+	FAIL_IF(fc_cleared);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(cycles_with_freeze, "cycles_with_freeze");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
new file mode 100644
index 00000000000..1b46be94b64
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -0,0 +1,727 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#define _GNU_SOURCE	/* For CPU_ZERO etc. */
+
+#include <sched.h>
+#include <sys/wait.h>
+#include <setjmp.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "trace.h"
+#include "reg.h"
+#include "ebb.h"
+
+
+void (*ebb_user_func)(void);
+
+void ebb_hook(void)
+{
+	if (ebb_user_func)
+		ebb_user_func();
+}
+
+struct ebb_state ebb_state;
+
+u64 sample_period = 0x40000000ull;
+
+void reset_ebb_with_clear_mask(unsigned long mmcr0_clear_mask)
+{
+	u64 val;
+
+	/* 2) clear MMCR0[PMAO] - docs say BESCR[PMEO] should do this */
+	/* 3) set MMCR0[PMAE]	- docs say BESCR[PME] should do this */
+	val = mfspr(SPRN_MMCR0);
+	mtspr(SPRN_MMCR0, (val & ~mmcr0_clear_mask) | MMCR0_PMAE);
+
+	/* 4) clear BESCR[PMEO] */
+	mtspr(SPRN_BESCRR, BESCR_PMEO);
+
+	/* 5) set BESCR[PME] */
+	mtspr(SPRN_BESCRS, BESCR_PME);
+
+	/* 6) rfebb 1 - done in our caller */
+}
+
+void reset_ebb(void)
+{
+	reset_ebb_with_clear_mask(MMCR0_PMAO | MMCR0_FC);
+}
+
+/* Called outside of the EBB handler to check MMCR0 is sane */
+int ebb_check_mmcr0(void)
+{
+	u64 val;
+
+	val = mfspr(SPRN_MMCR0);
+	if ((val & (MMCR0_FC | MMCR0_PMAO)) == MMCR0_FC) {
+		/* It's OK if we see FC & PMAO, but not FC by itself */
+		printf("Outside of loop, only FC set 0x%llx\n", val);
+		return 1;
+	}
+
+	return 0;
+}
+
+bool ebb_check_count(int pmc, u64 sample_period, int fudge)
+{
+	u64 count, upper, lower;
+
+	count = ebb_state.stats.pmc_count[PMC_INDEX(pmc)];
+
+	lower = ebb_state.stats.ebb_count * (sample_period - fudge);
+
+	if (count < lower) {
+		printf("PMC%d count (0x%llx) below lower limit 0x%llx (-0x%llx)\n",
+			pmc, count, lower, lower - count);
+		return false;
+	}
+
+	upper = ebb_state.stats.ebb_count * (sample_period + fudge);
+
+	if (count > upper) {
+		printf("PMC%d count (0x%llx) above upper limit 0x%llx (+0x%llx)\n",
+			pmc, count, upper, count - upper);
+		return false;
+	}
+
+	printf("PMC%d count (0x%llx) is between 0x%llx and 0x%llx delta +0x%llx/-0x%llx\n",
+		pmc, count, lower, upper, count - lower, upper - count);
+
+	return true;
+}
+
+void standard_ebb_callee(void)
+{
+	int found, i;
+	u64 val;
+
+	val = mfspr(SPRN_BESCR);
+	if (!(val & BESCR_PMEO)) {
+		ebb_state.stats.spurious++;
+		goto out;
+	}
+
+	ebb_state.stats.ebb_count++;
+	trace_log_counter(ebb_state.trace, ebb_state.stats.ebb_count);
+
+	val = mfspr(SPRN_MMCR0);
+	trace_log_reg(ebb_state.trace, SPRN_MMCR0, val);
+
+	found = 0;
+	for (i = 1; i <= 6; i++) {
+		if (ebb_state.pmc_enable[PMC_INDEX(i)])
+			found += count_pmc(i, sample_period);
+	}
+
+	if (!found)
+		ebb_state.stats.no_overflow++;
+
+out:
+	reset_ebb();
+}
+
+extern void ebb_handler(void);
+
+void setup_ebb_handler(void (*callee)(void))
+{
+	u64 entry;
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+	entry = (u64)ebb_handler;
+#else
+	struct opd
+	{
+	    u64 entry;
+	    u64 toc;
+	} *opd;
+
+	opd = (struct opd *)ebb_handler;
+	entry = opd->entry;
+#endif
+	printf("EBB Handler is at %#llx\n", entry);
+
+	ebb_user_func = callee;
+
+	/* Ensure ebb_user_func is set before we set the handler */
+	mb();
+	mtspr(SPRN_EBBHR, entry);
+
+	/* Make sure the handler is set before we return */
+	mb();
+}
+
+void clear_ebb_stats(void)
+{
+	memset(&ebb_state.stats, 0, sizeof(ebb_state.stats));
+}
+
+void dump_summary_ebb_state(void)
+{
+	printf("ebb_state:\n"			\
+	       "  ebb_count    = %d\n"		\
+	       "  spurious     = %d\n"		\
+	       "  negative     = %d\n"		\
+	       "  no_overflow  = %d\n"		\
+	       "  pmc[1] count = 0x%llx\n"	\
+	       "  pmc[2] count = 0x%llx\n"	\
+	       "  pmc[3] count = 0x%llx\n"	\
+	       "  pmc[4] count = 0x%llx\n"	\
+	       "  pmc[5] count = 0x%llx\n"	\
+	       "  pmc[6] count = 0x%llx\n",
+		ebb_state.stats.ebb_count, ebb_state.stats.spurious,
+		ebb_state.stats.negative, ebb_state.stats.no_overflow,
+		ebb_state.stats.pmc_count[0], ebb_state.stats.pmc_count[1],
+		ebb_state.stats.pmc_count[2], ebb_state.stats.pmc_count[3],
+		ebb_state.stats.pmc_count[4], ebb_state.stats.pmc_count[5]);
+}
+
+static char *decode_mmcr0(u32 value)
+{
+	static char buf[16];
+
+	buf[0] = '\0';
+
+	if (value & (1 << 31))
+		strcat(buf, "FC ");
+	if (value & (1 << 26))
+		strcat(buf, "PMAE ");
+	if (value & (1 << 7))
+		strcat(buf, "PMAO ");
+
+	return buf;
+}
+
+static char *decode_bescr(u64 value)
+{
+	static char buf[16];
+
+	buf[0] = '\0';
+
+	if (value & (1ull << 63))
+		strcat(buf, "GE ");
+	if (value & (1ull << 32))
+		strcat(buf, "PMAE ");
+	if (value & 1)
+		strcat(buf, "PMAO ");
+
+	return buf;
+}
+
+void dump_ebb_hw_state(void)
+{
+	u64 bescr;
+	u32 mmcr0;
+
+	mmcr0 = mfspr(SPRN_MMCR0);
+	bescr = mfspr(SPRN_BESCR);
+
+	printf("HW state:\n"		\
+	       "MMCR0 0x%016x %s\n"	\
+	       "EBBHR 0x%016lx\n"	\
+	       "BESCR 0x%016llx %s\n"	\
+	       "PMC1  0x%016lx\n"	\
+	       "PMC2  0x%016lx\n"	\
+	       "PMC3  0x%016lx\n"	\
+	       "PMC4  0x%016lx\n"	\
+	       "PMC5  0x%016lx\n"	\
+	       "PMC6  0x%016lx\n"	\
+	       "SIAR  0x%016lx\n",
+	       mmcr0, decode_mmcr0(mmcr0), mfspr(SPRN_EBBHR), bescr,
+	       decode_bescr(bescr), mfspr(SPRN_PMC1), mfspr(SPRN_PMC2),
+	       mfspr(SPRN_PMC3), mfspr(SPRN_PMC4), mfspr(SPRN_PMC5),
+	       mfspr(SPRN_PMC6), mfspr(SPRN_SIAR));
+}
+
+void dump_ebb_state(void)
+{
+	dump_summary_ebb_state();
+
+	dump_ebb_hw_state();
+
+	trace_buffer_print(ebb_state.trace);
+}
+
+int count_pmc(int pmc, uint32_t sample_period)
+{
+	uint32_t start_value;
+	u64 val;
+
+	/* 0) Read PMC */
+	start_value = pmc_sample_period(sample_period);
+
+	val = read_pmc(pmc);
+	if (val < start_value)
+		ebb_state.stats.negative++;
+	else
+		ebb_state.stats.pmc_count[PMC_INDEX(pmc)] += val - start_value;
+
+	trace_log_reg(ebb_state.trace, SPRN_PMC1 + pmc - 1, val);
+
+	/* 1) Reset PMC */
+	write_pmc(pmc, start_value);
+
+	/* Report if we overflowed */
+	return val >= COUNTER_OVERFLOW;
+}
+
+int ebb_event_enable(struct event *e)
+{
+	int rc;
+
+	/* Ensure any SPR writes are ordered vs us */
+	mb();
+
+	rc = ioctl(e->fd, PERF_EVENT_IOC_ENABLE);
+	if (rc)
+		return rc;
+
+	rc = event_read(e);
+
+	/* Ditto */
+	mb();
+
+	return rc;
+}
+
+void ebb_freeze_pmcs(void)
+{
+	mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) | MMCR0_FC);
+	mb();
+}
+
+void ebb_unfreeze_pmcs(void)
+{
+	/* Unfreeze counters */
+	mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC);
+	mb();
+}
+
+void ebb_global_enable(void)
+{
+	/* Enable EBBs globally and PMU EBBs */
+	mtspr(SPRN_BESCR, 0x8000000100000000ull);
+	mb();
+}
+
+void ebb_global_disable(void)
+{
+	/* Disable EBBs & freeze counters, events are still scheduled */
+	mtspr(SPRN_BESCRR, BESCR_PME);
+	mb();
+}
+
+void event_ebb_init(struct event *e)
+{
+	e->attr.config |= (1ull << 63);
+}
+
+void event_bhrb_init(struct event *e, unsigned ifm)
+{
+	e->attr.config |= (1ull << 62) | ((u64)ifm << 60);
+}
+
+void event_leader_ebb_init(struct event *e)
+{
+	event_ebb_init(e);
+
+	e->attr.exclusive = 1;
+	e->attr.pinned = 1;
+}
+
+int core_busy_loop(void)
+{
+	int rc;
+
+	asm volatile (
+		"li  3,  0x3030\n"
+		"std 3,  -96(1)\n"
+		"li  4,  0x4040\n"
+		"std 4,  -104(1)\n"
+		"li  5,  0x5050\n"
+		"std 5,  -112(1)\n"
+		"li  6,  0x6060\n"
+		"std 6,  -120(1)\n"
+		"li  7,  0x7070\n"
+		"std 7,  -128(1)\n"
+		"li  8,  0x0808\n"
+		"std 8,  -136(1)\n"
+		"li  9,  0x0909\n"
+		"std 9,  -144(1)\n"
+		"li  10, 0x1010\n"
+		"std 10, -152(1)\n"
+		"li  11, 0x1111\n"
+		"std 11, -160(1)\n"
+		"li  14, 0x1414\n"
+		"std 14, -168(1)\n"
+		"li  15, 0x1515\n"
+		"std 15, -176(1)\n"
+		"li  16, 0x1616\n"
+		"std 16, -184(1)\n"
+		"li  17, 0x1717\n"
+		"std 17, -192(1)\n"
+		"li  18, 0x1818\n"
+		"std 18, -200(1)\n"
+		"li  19, 0x1919\n"
+		"std 19, -208(1)\n"
+		"li  20, 0x2020\n"
+		"std 20, -216(1)\n"
+		"li  21, 0x2121\n"
+		"std 21, -224(1)\n"
+		"li  22, 0x2222\n"
+		"std 22, -232(1)\n"
+		"li  23, 0x2323\n"
+		"std 23, -240(1)\n"
+		"li  24, 0x2424\n"
+		"std 24, -248(1)\n"
+		"li  25, 0x2525\n"
+		"std 25, -256(1)\n"
+		"li  26, 0x2626\n"
+		"std 26, -264(1)\n"
+		"li  27, 0x2727\n"
+		"std 27, -272(1)\n"
+		"li  28, 0x2828\n"
+		"std 28, -280(1)\n"
+		"li  29, 0x2929\n"
+		"std 29, -288(1)\n"
+		"li  30, 0x3030\n"
+		"li  31, 0x3131\n"
+
+		"li    3,  0\n"
+		"0: "
+		"addi  3, 3, 1\n"
+		"cmpwi 3, 100\n"
+		"blt   0b\n"
+
+		/* Return 1 (fail) unless we get through all the checks */
+		"li	0, 1\n"
+
+		/* Check none of our registers have been corrupted */
+		"cmpwi  4,  0x4040\n"
+		"bne	1f\n"
+		"cmpwi  5,  0x5050\n"
+		"bne	1f\n"
+		"cmpwi  6,  0x6060\n"
+		"bne	1f\n"
+		"cmpwi  7,  0x7070\n"
+		"bne	1f\n"
+		"cmpwi  8,  0x0808\n"
+		"bne	1f\n"
+		"cmpwi  9,  0x0909\n"
+		"bne	1f\n"
+		"cmpwi  10, 0x1010\n"
+		"bne	1f\n"
+		"cmpwi  11, 0x1111\n"
+		"bne	1f\n"
+		"cmpwi  14, 0x1414\n"
+		"bne	1f\n"
+		"cmpwi  15, 0x1515\n"
+		"bne	1f\n"
+		"cmpwi  16, 0x1616\n"
+		"bne	1f\n"
+		"cmpwi  17, 0x1717\n"
+		"bne	1f\n"
+		"cmpwi  18, 0x1818\n"
+		"bne	1f\n"
+		"cmpwi  19, 0x1919\n"
+		"bne	1f\n"
+		"cmpwi  20, 0x2020\n"
+		"bne	1f\n"
+		"cmpwi  21, 0x2121\n"
+		"bne	1f\n"
+		"cmpwi  22, 0x2222\n"
+		"bne	1f\n"
+		"cmpwi  23, 0x2323\n"
+		"bne	1f\n"
+		"cmpwi  24, 0x2424\n"
+		"bne	1f\n"
+		"cmpwi  25, 0x2525\n"
+		"bne	1f\n"
+		"cmpwi  26, 0x2626\n"
+		"bne	1f\n"
+		"cmpwi  27, 0x2727\n"
+		"bne	1f\n"
+		"cmpwi  28, 0x2828\n"
+		"bne	1f\n"
+		"cmpwi  29, 0x2929\n"
+		"bne	1f\n"
+		"cmpwi  30, 0x3030\n"
+		"bne	1f\n"
+		"cmpwi  31, 0x3131\n"
+		"bne	1f\n"
+
+		/* Load junk into all our registers before we reload them from the stack. */
+		"li  3,  0xde\n"
+		"li  4,  0xad\n"
+		"li  5,  0xbe\n"
+		"li  6,  0xef\n"
+		"li  7,  0xde\n"
+		"li  8,  0xad\n"
+		"li  9,  0xbe\n"
+		"li  10, 0xef\n"
+		"li  11, 0xde\n"
+		"li  14, 0xad\n"
+		"li  15, 0xbe\n"
+		"li  16, 0xef\n"
+		"li  17, 0xde\n"
+		"li  18, 0xad\n"
+		"li  19, 0xbe\n"
+		"li  20, 0xef\n"
+		"li  21, 0xde\n"
+		"li  22, 0xad\n"
+		"li  23, 0xbe\n"
+		"li  24, 0xef\n"
+		"li  25, 0xde\n"
+		"li  26, 0xad\n"
+		"li  27, 0xbe\n"
+		"li  28, 0xef\n"
+		"li  29, 0xdd\n"
+
+		"ld     3,  -96(1)\n"
+		"cmpwi  3,  0x3030\n"
+		"bne	1f\n"
+		"ld     4,  -104(1)\n"
+		"cmpwi  4,  0x4040\n"
+		"bne	1f\n"
+		"ld     5,  -112(1)\n"
+		"cmpwi  5,  0x5050\n"
+		"bne	1f\n"
+		"ld     6,  -120(1)\n"
+		"cmpwi  6,  0x6060\n"
+		"bne	1f\n"
+		"ld     7,  -128(1)\n"
+		"cmpwi  7,  0x7070\n"
+		"bne	1f\n"
+		"ld     8,  -136(1)\n"
+		"cmpwi  8,  0x0808\n"
+		"bne	1f\n"
+		"ld     9,  -144(1)\n"
+		"cmpwi  9,  0x0909\n"
+		"bne	1f\n"
+		"ld     10, -152(1)\n"
+		"cmpwi  10, 0x1010\n"
+		"bne	1f\n"
+		"ld     11, -160(1)\n"
+		"cmpwi  11, 0x1111\n"
+		"bne	1f\n"
+		"ld     14, -168(1)\n"
+		"cmpwi  14, 0x1414\n"
+		"bne	1f\n"
+		"ld     15, -176(1)\n"
+		"cmpwi  15, 0x1515\n"
+		"bne	1f\n"
+		"ld     16, -184(1)\n"
+		"cmpwi  16, 0x1616\n"
+		"bne	1f\n"
+		"ld     17, -192(1)\n"
+		"cmpwi  17, 0x1717\n"
+		"bne	1f\n"
+		"ld     18, -200(1)\n"
+		"cmpwi  18, 0x1818\n"
+		"bne	1f\n"
+		"ld     19, -208(1)\n"
+		"cmpwi  19, 0x1919\n"
+		"bne	1f\n"
+		"ld     20, -216(1)\n"
+		"cmpwi  20, 0x2020\n"
+		"bne	1f\n"
+		"ld     21, -224(1)\n"
+		"cmpwi  21, 0x2121\n"
+		"bne	1f\n"
+		"ld     22, -232(1)\n"
+		"cmpwi  22, 0x2222\n"
+		"bne	1f\n"
+		"ld     23, -240(1)\n"
+		"cmpwi  23, 0x2323\n"
+		"bne	1f\n"
+		"ld     24, -248(1)\n"
+		"cmpwi  24, 0x2424\n"
+		"bne	1f\n"
+		"ld     25, -256(1)\n"
+		"cmpwi  25, 0x2525\n"
+		"bne	1f\n"
+		"ld     26, -264(1)\n"
+		"cmpwi  26, 0x2626\n"
+		"bne	1f\n"
+		"ld     27, -272(1)\n"
+		"cmpwi  27, 0x2727\n"
+		"bne	1f\n"
+		"ld     28, -280(1)\n"
+		"cmpwi  28, 0x2828\n"
+		"bne	1f\n"
+		"ld     29, -288(1)\n"
+		"cmpwi  29, 0x2929\n"
+		"bne	1f\n"
+
+		/* Load 0 (success) to return */
+		"li	0, 0\n"
+
+		"1: 	mr %0, 0\n"
+
+		: "=r" (rc)
+		: /* no inputs */
+		: "3", "4", "5", "6", "7", "8", "9", "10", "11", "14",
+		  "15", "16", "17", "18", "19", "20", "21", "22", "23",
+		   "24", "25", "26", "27", "28", "29", "30", "31",
+		   "memory"
+	);
+
+	return rc;
+}
+
+int core_busy_loop_with_freeze(void)
+{
+	int rc;
+
+	mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC);
+	rc = core_busy_loop();
+	mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) |  MMCR0_FC);
+
+	return rc;
+}
+
+int ebb_child(union pipe read_pipe, union pipe write_pipe)
+{
+	struct event event;
+	uint64_t val;
+
+	FAIL_IF(wait_for_parent(read_pipe));
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+
+	ebb_enable_pmc_counting(1);
+	setup_ebb_handler(standard_ebb_callee);
+	ebb_global_enable();
+
+	FAIL_IF(event_enable(&event));
+
+	if (event_read(&event)) {
+		/*
+		 * Some tests expect to fail here, so don't report an error on
+		 * this line, and return a distinguisable error code. Tell the
+		 * parent an error happened.
+		 */
+		notify_parent_of_error(write_pipe);
+		return 2;
+	}
+
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+
+	FAIL_IF(notify_parent(write_pipe));
+	FAIL_IF(wait_for_parent(read_pipe));
+	FAIL_IF(notify_parent(write_pipe));
+
+	while (ebb_state.stats.ebb_count < 20) {
+		FAIL_IF(core_busy_loop());
+
+		/* To try and hit SIGILL case */
+		val  = mfspr(SPRN_MMCRA);
+		val |= mfspr(SPRN_MMCR2);
+		val |= mfspr(SPRN_MMCR0);
+	}
+
+	ebb_global_disable();
+	ebb_freeze_pmcs();
+
+	count_pmc(1, sample_period);
+
+	dump_ebb_state();
+
+	event_close(&event);
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0);
+
+	return 0;
+}
+
+static jmp_buf setjmp_env;
+
+static void sigill_handler(int signal)
+{
+	printf("Took sigill\n");
+	longjmp(setjmp_env, 1);
+}
+
+static struct sigaction sigill_action = {
+	.sa_handler = sigill_handler,
+};
+
+int catch_sigill(void (*func)(void))
+{
+	if (sigaction(SIGILL, &sigill_action, NULL)) {
+		perror("sigaction");
+		return 1;
+	}
+
+	if (setjmp(setjmp_env) == 0) {
+		func();
+		return 1;
+	}
+
+	return 0;
+}
+
+void write_pmc1(void)
+{
+	mtspr(SPRN_PMC1, 0);
+}
+
+void write_pmc(int pmc, u64 value)
+{
+	switch (pmc) {
+		case 1: mtspr(SPRN_PMC1, value); break;
+		case 2: mtspr(SPRN_PMC2, value); break;
+		case 3: mtspr(SPRN_PMC3, value); break;
+		case 4: mtspr(SPRN_PMC4, value); break;
+		case 5: mtspr(SPRN_PMC5, value); break;
+		case 6: mtspr(SPRN_PMC6, value); break;
+	}
+}
+
+u64 read_pmc(int pmc)
+{
+	switch (pmc) {
+		case 1: return mfspr(SPRN_PMC1);
+		case 2: return mfspr(SPRN_PMC2);
+		case 3: return mfspr(SPRN_PMC3);
+		case 4: return mfspr(SPRN_PMC4);
+		case 5: return mfspr(SPRN_PMC5);
+		case 6: return mfspr(SPRN_PMC6);
+	}
+
+	return 0;
+}
+
+static void term_handler(int signal)
+{
+	dump_summary_ebb_state();
+	dump_ebb_hw_state();
+	abort();
+}
+
+struct sigaction term_action = {
+	.sa_handler = term_handler,
+};
+
+static void __attribute__((constructor)) ebb_init(void)
+{
+	clear_ebb_stats();
+
+	if (sigaction(SIGTERM, &term_action, NULL))
+		perror("sigaction");
+
+	ebb_state.trace = trace_buffer_allocate(1 * 1024 * 1024);
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.h b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h
new file mode 100644
index 00000000000..e62bde05bf7
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#ifndef _SELFTESTS_POWERPC_PMU_EBB_EBB_H
+#define _SELFTESTS_POWERPC_PMU_EBB_EBB_H
+
+#include "../event.h"
+#include "../lib.h"
+#include "trace.h"
+#include "reg.h"
+
+#define PMC_INDEX(pmc)	((pmc)-1)
+
+#define NUM_PMC_VALUES	128
+
+struct ebb_state
+{
+	struct {
+		u64 pmc_count[6];
+		volatile int ebb_count;
+		int spurious;
+		int negative;
+		int no_overflow;
+	} stats;
+
+	bool pmc_enable[6];
+	struct trace_buffer *trace;
+};
+
+extern struct ebb_state ebb_state;
+
+#define COUNTER_OVERFLOW 0x80000000ull
+
+static inline uint32_t pmc_sample_period(uint32_t value)
+{
+	return COUNTER_OVERFLOW - value;
+}
+
+static inline void ebb_enable_pmc_counting(int pmc)
+{
+	ebb_state.pmc_enable[PMC_INDEX(pmc)] = true;
+}
+
+bool ebb_check_count(int pmc, u64 sample_period, int fudge);
+void event_leader_ebb_init(struct event *e);
+void event_ebb_init(struct event *e);
+void event_bhrb_init(struct event *e, unsigned ifm);
+void setup_ebb_handler(void (*callee)(void));
+void standard_ebb_callee(void);
+int ebb_event_enable(struct event *e);
+void ebb_global_enable(void);
+void ebb_global_disable(void);
+void ebb_freeze_pmcs(void);
+void ebb_unfreeze_pmcs(void);
+void event_ebb_init(struct event *e);
+void event_leader_ebb_init(struct event *e);
+int count_pmc(int pmc, uint32_t sample_period);
+void dump_ebb_state(void);
+void dump_summary_ebb_state(void);
+void dump_ebb_hw_state(void);
+void clear_ebb_stats(void);
+void write_pmc(int pmc, u64 value);
+u64 read_pmc(int pmc);
+void reset_ebb_with_clear_mask(unsigned long mmcr0_clear_mask);
+void reset_ebb(void);
+int ebb_check_mmcr0(void);
+
+extern u64 sample_period;
+
+int core_busy_loop(void);
+int core_busy_loop_with_freeze(void);
+int ebb_child(union pipe read_pipe, union pipe write_pipe);
+int catch_sigill(void (*func)(void));
+void write_pmc1(void);
+
+#endif /* _SELFTESTS_POWERPC_PMU_EBB_EBB_H */
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_handler.S b/tools/testing/selftests/powerpc/pmu/ebb/ebb_handler.S
new file mode 100644
index 00000000000..14274ea206e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_handler.S
@@ -0,0 +1,365 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <ppc-asm.h>
+#include "reg.h"
+
+
+/* ppc-asm.h defines most of the reg aliases, but not r1/r2. */
+#define r1 1
+#define r2 2
+
+#define RFEBB   .long 0x4c000924
+
+/* Stack layout:
+ *
+ *                   ^
+ *  User stack       |
+ *  Back chain ------+	<- r1		<-------+
+ *  ...						|
+ *  Red zone / ABI Gap				|
+ *  ...						|
+ *  vr63	<+				|
+ *  vr0		 |				|
+ *  VSCR	 |				|
+ *  FSCR	 |				|
+ *  r31		 | Save area			|
+ *  r0		 |				|
+ *  XER		 |				|
+ *  CTR		 |				|
+ *  LR		 |				|
+ *  CCR		<+				|
+ *  ...		<+				|
+ *  LR		 | Caller frame			|
+ *  CCR		 |				|
+ *  Back chain	<+	<- updated r1	--------+
+ *
+ */
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define ABIGAP		512
+#else
+#define ABIGAP		288
+#endif
+
+#define NR_GPR		32
+#define NR_SPR		6
+#define NR_VSR		64
+
+#define SAVE_AREA	((NR_GPR + NR_SPR) * 8 + (NR_VSR * 16))
+#define CALLER_FRAME	112
+
+#define STACK_FRAME	(ABIGAP + SAVE_AREA + CALLER_FRAME)
+
+#define CCR_SAVE	(CALLER_FRAME)
+#define LR_SAVE		(CCR_SAVE + 8)
+#define CTR_SAVE	(LR_SAVE  + 8)
+#define XER_SAVE	(CTR_SAVE + 8)
+#define GPR_SAVE(n)	(XER_SAVE + 8 + (8 * n))
+#define FSCR_SAVE	(GPR_SAVE(31) + 8)
+#define VSCR_SAVE	(FSCR_SAVE + 8)
+#define VSR_SAVE(n)	(VSCR_SAVE + 8 + (16 * n))
+
+#define SAVE_GPR(n)	std n,GPR_SAVE(n)(r1)
+#define REST_GPR(n)	ld  n,GPR_SAVE(n)(r1)
+#define TRASH_GPR(n)	lis n,0xaaaa
+
+#define SAVE_VSR(n, b)	li b, VSR_SAVE(n); stxvd2x n,b,r1
+#define LOAD_VSR(n, b)	li b, VSR_SAVE(n); lxvd2x  n,b,r1
+
+#define LOAD_REG_IMMEDIATE(reg,expr)	\
+	lis     reg,(expr)@highest;	\
+	ori     reg,reg,(expr)@higher;	\
+	rldicr  reg,reg,32,31;		\
+	oris    reg,reg,(expr)@h;	\
+	ori     reg,reg,(expr)@l;
+
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define ENTRY_POINT(name) \
+	.type FUNC_NAME(name),@function; \
+	.globl FUNC_NAME(name); \
+	FUNC_NAME(name):
+
+#define RESTORE_TOC(name)	\
+	/* Restore our TOC pointer using our entry point */	\
+	LOAD_REG_IMMEDIATE(r12, name)				\
+0:	addis	r2,r12,(.TOC.-0b)@ha;				\
+	addi	r2,r2,(.TOC.-0b)@l;
+
+#else
+#define ENTRY_POINT(name) FUNC_START(name)
+#define RESTORE_TOC(name)	\
+	/* Restore our TOC pointer via our opd entry */	\
+	LOAD_REG_IMMEDIATE(r2, name)			\
+	ld      r2,8(r2);
+#endif
+
+    .text
+
+ENTRY_POINT(ebb_handler)
+    stdu    r1,-STACK_FRAME(r1)
+    SAVE_GPR(0)
+    mflr    r0
+    std     r0,LR_SAVE(r1)
+    mfcr    r0
+    std     r0,CCR_SAVE(r1)
+    mfctr   r0
+    std     r0,CTR_SAVE(r1)
+    mfxer   r0
+    std     r0,XER_SAVE(r1)
+    SAVE_GPR(2)
+    SAVE_GPR(3)
+    SAVE_GPR(4)
+    SAVE_GPR(5)
+    SAVE_GPR(6)
+    SAVE_GPR(7)
+    SAVE_GPR(8)
+    SAVE_GPR(9)
+    SAVE_GPR(10)
+    SAVE_GPR(11)
+    SAVE_GPR(12)
+    SAVE_GPR(13)
+    SAVE_GPR(14)
+    SAVE_GPR(15)
+    SAVE_GPR(16)
+    SAVE_GPR(17)
+    SAVE_GPR(18)
+    SAVE_GPR(19)
+    SAVE_GPR(20)
+    SAVE_GPR(21)
+    SAVE_GPR(22)
+    SAVE_GPR(23)
+    SAVE_GPR(24)
+    SAVE_GPR(25)
+    SAVE_GPR(26)
+    SAVE_GPR(27)
+    SAVE_GPR(28)
+    SAVE_GPR(29)
+    SAVE_GPR(30)
+    SAVE_GPR(31)
+    SAVE_VSR(0, r3)
+    mffs     f0
+    stfd     f0, FSCR_SAVE(r1)
+    mfvscr   f0
+    stfd     f0, VSCR_SAVE(r1)
+    SAVE_VSR(1,  r3)
+    SAVE_VSR(2,  r3)
+    SAVE_VSR(3,  r3)
+    SAVE_VSR(4,  r3)
+    SAVE_VSR(5,  r3)
+    SAVE_VSR(6,  r3)
+    SAVE_VSR(7,  r3)
+    SAVE_VSR(8,  r3)
+    SAVE_VSR(9,  r3)
+    SAVE_VSR(10, r3)
+    SAVE_VSR(11, r3)
+    SAVE_VSR(12, r3)
+    SAVE_VSR(13, r3)
+    SAVE_VSR(14, r3)
+    SAVE_VSR(15, r3)
+    SAVE_VSR(16, r3)
+    SAVE_VSR(17, r3)
+    SAVE_VSR(18, r3)
+    SAVE_VSR(19, r3)
+    SAVE_VSR(20, r3)
+    SAVE_VSR(21, r3)
+    SAVE_VSR(22, r3)
+    SAVE_VSR(23, r3)
+    SAVE_VSR(24, r3)
+    SAVE_VSR(25, r3)
+    SAVE_VSR(26, r3)
+    SAVE_VSR(27, r3)
+    SAVE_VSR(28, r3)
+    SAVE_VSR(29, r3)
+    SAVE_VSR(30, r3)
+    SAVE_VSR(31, r3)
+    SAVE_VSR(32, r3)
+    SAVE_VSR(33, r3)
+    SAVE_VSR(34, r3)
+    SAVE_VSR(35, r3)
+    SAVE_VSR(36, r3)
+    SAVE_VSR(37, r3)
+    SAVE_VSR(38, r3)
+    SAVE_VSR(39, r3)
+    SAVE_VSR(40, r3)
+    SAVE_VSR(41, r3)
+    SAVE_VSR(42, r3)
+    SAVE_VSR(43, r3)
+    SAVE_VSR(44, r3)
+    SAVE_VSR(45, r3)
+    SAVE_VSR(46, r3)
+    SAVE_VSR(47, r3)
+    SAVE_VSR(48, r3)
+    SAVE_VSR(49, r3)
+    SAVE_VSR(50, r3)
+    SAVE_VSR(51, r3)
+    SAVE_VSR(52, r3)
+    SAVE_VSR(53, r3)
+    SAVE_VSR(54, r3)
+    SAVE_VSR(55, r3)
+    SAVE_VSR(56, r3)
+    SAVE_VSR(57, r3)
+    SAVE_VSR(58, r3)
+    SAVE_VSR(59, r3)
+    SAVE_VSR(60, r3)
+    SAVE_VSR(61, r3)
+    SAVE_VSR(62, r3)
+    SAVE_VSR(63, r3)
+
+    TRASH_GPR(2)
+    TRASH_GPR(3)
+    TRASH_GPR(4)
+    TRASH_GPR(5)
+    TRASH_GPR(6)
+    TRASH_GPR(7)
+    TRASH_GPR(8)
+    TRASH_GPR(9)
+    TRASH_GPR(10)
+    TRASH_GPR(11)
+    TRASH_GPR(12)
+    TRASH_GPR(14)
+    TRASH_GPR(15)
+    TRASH_GPR(16)
+    TRASH_GPR(17)
+    TRASH_GPR(18)
+    TRASH_GPR(19)
+    TRASH_GPR(20)
+    TRASH_GPR(21)
+    TRASH_GPR(22)
+    TRASH_GPR(23)
+    TRASH_GPR(24)
+    TRASH_GPR(25)
+    TRASH_GPR(26)
+    TRASH_GPR(27)
+    TRASH_GPR(28)
+    TRASH_GPR(29)
+    TRASH_GPR(30)
+    TRASH_GPR(31)
+
+    RESTORE_TOC(ebb_handler)
+
+    /*
+     * r13 is our TLS pointer. We leave whatever value was in there when the
+     * EBB fired. That seems to be OK because once set the TLS pointer is not
+     * changed - but presumably that could change in future.
+     */
+
+    bl      ebb_hook
+    nop
+
+    /* r2 may be changed here but we don't care */
+
+    lfd      f0, FSCR_SAVE(r1)
+    mtfsf    0xff,f0
+    lfd      f0, VSCR_SAVE(r1)
+    mtvscr   f0
+    LOAD_VSR(0, r3)
+    LOAD_VSR(1,  r3)
+    LOAD_VSR(2,  r3)
+    LOAD_VSR(3,  r3)
+    LOAD_VSR(4,  r3)
+    LOAD_VSR(5,  r3)
+    LOAD_VSR(6,  r3)
+    LOAD_VSR(7,  r3)
+    LOAD_VSR(8,  r3)
+    LOAD_VSR(9,  r3)
+    LOAD_VSR(10, r3)
+    LOAD_VSR(11, r3)
+    LOAD_VSR(12, r3)
+    LOAD_VSR(13, r3)
+    LOAD_VSR(14, r3)
+    LOAD_VSR(15, r3)
+    LOAD_VSR(16, r3)
+    LOAD_VSR(17, r3)
+    LOAD_VSR(18, r3)
+    LOAD_VSR(19, r3)
+    LOAD_VSR(20, r3)
+    LOAD_VSR(21, r3)
+    LOAD_VSR(22, r3)
+    LOAD_VSR(23, r3)
+    LOAD_VSR(24, r3)
+    LOAD_VSR(25, r3)
+    LOAD_VSR(26, r3)
+    LOAD_VSR(27, r3)
+    LOAD_VSR(28, r3)
+    LOAD_VSR(29, r3)
+    LOAD_VSR(30, r3)
+    LOAD_VSR(31, r3)
+    LOAD_VSR(32, r3)
+    LOAD_VSR(33, r3)
+    LOAD_VSR(34, r3)
+    LOAD_VSR(35, r3)
+    LOAD_VSR(36, r3)
+    LOAD_VSR(37, r3)
+    LOAD_VSR(38, r3)
+    LOAD_VSR(39, r3)
+    LOAD_VSR(40, r3)
+    LOAD_VSR(41, r3)
+    LOAD_VSR(42, r3)
+    LOAD_VSR(43, r3)
+    LOAD_VSR(44, r3)
+    LOAD_VSR(45, r3)
+    LOAD_VSR(46, r3)
+    LOAD_VSR(47, r3)
+    LOAD_VSR(48, r3)
+    LOAD_VSR(49, r3)
+    LOAD_VSR(50, r3)
+    LOAD_VSR(51, r3)
+    LOAD_VSR(52, r3)
+    LOAD_VSR(53, r3)
+    LOAD_VSR(54, r3)
+    LOAD_VSR(55, r3)
+    LOAD_VSR(56, r3)
+    LOAD_VSR(57, r3)
+    LOAD_VSR(58, r3)
+    LOAD_VSR(59, r3)
+    LOAD_VSR(60, r3)
+    LOAD_VSR(61, r3)
+    LOAD_VSR(62, r3)
+    LOAD_VSR(63, r3)
+
+    ld      r0,XER_SAVE(r1)
+    mtxer   r0
+    ld      r0,CTR_SAVE(r1)
+    mtctr   r0
+    ld      r0,LR_SAVE(r1)
+    mtlr    r0
+    ld      r0,CCR_SAVE(r1)
+    mtcr    r0
+    REST_GPR(0)
+    REST_GPR(2)
+    REST_GPR(3)
+    REST_GPR(4)
+    REST_GPR(5)
+    REST_GPR(6)
+    REST_GPR(7)
+    REST_GPR(8)
+    REST_GPR(9)
+    REST_GPR(10)
+    REST_GPR(11)
+    REST_GPR(12)
+    REST_GPR(13)
+    REST_GPR(14)
+    REST_GPR(15)
+    REST_GPR(16)
+    REST_GPR(17)
+    REST_GPR(18)
+    REST_GPR(19)
+    REST_GPR(20)
+    REST_GPR(21)
+    REST_GPR(22)
+    REST_GPR(23)
+    REST_GPR(24)
+    REST_GPR(25)
+    REST_GPR(26)
+    REST_GPR(27)
+    REST_GPR(28)
+    REST_GPR(29)
+    REST_GPR(30)
+    REST_GPR(31)
+    addi    r1,r1,STACK_FRAME
+    RFEBB
+FUNC_END(ebb_handler)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_child_test.c
new file mode 100644
index 00000000000..c45f948148e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_child_test.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "ebb.h"
+
+
+/*
+ * Tests we can setup an EBB on our child. Nothing interesting happens, because
+ * even though the event is enabled and running the child hasn't enabled the
+ * actual delivery of the EBBs.
+ */
+
+static int victim_child(union pipe read_pipe, union pipe write_pipe)
+{
+	int i;
+
+	FAIL_IF(wait_for_parent(read_pipe));
+	FAIL_IF(notify_parent(write_pipe));
+
+	/* Parent creates EBB event */
+
+	FAIL_IF(wait_for_parent(read_pipe));
+	FAIL_IF(notify_parent(write_pipe));
+
+	/* Check the EBB is enabled by writing PMC1 */
+	write_pmc1();
+
+	/* EBB event is enabled here */
+	for (i = 0; i < 1000000; i++) ;
+
+	return 0;
+}
+
+int ebb_on_child(void)
+{
+	union pipe read_pipe, write_pipe;
+	struct event event;
+	pid_t pid;
+
+	FAIL_IF(pipe(read_pipe.fds) == -1);
+	FAIL_IF(pipe(write_pipe.fds) == -1);
+
+	pid = fork();
+	if (pid == 0) {
+		/* NB order of pipes looks reversed */
+		exit(victim_child(write_pipe, read_pipe));
+	}
+
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+	/* Child is running now */
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open_with_pid(&event, pid));
+	FAIL_IF(ebb_event_enable(&event));
+
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+	/* Child should just exit happily */
+	FAIL_IF(wait_for_child(pid));
+
+	event_close(&event);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(ebb_on_child, "ebb_on_child");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
new file mode 100644
index 00000000000..11acf1d55f8
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -0,0 +1,92 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "ebb.h"
+
+
+/*
+ * Tests we can setup an EBB on our child. The child expects this and enables
+ * EBBs, which are then delivered to the child, even though the event is
+ * created by the parent.
+ */
+
+static int victim_child(union pipe read_pipe, union pipe write_pipe)
+{
+	FAIL_IF(wait_for_parent(read_pipe));
+
+	/* Setup our EBB handler, before the EBB event is created */
+	ebb_enable_pmc_counting(1);
+	setup_ebb_handler(standard_ebb_callee);
+	ebb_global_enable();
+
+	FAIL_IF(notify_parent(write_pipe));
+
+	while (ebb_state.stats.ebb_count < 20) {
+		FAIL_IF(core_busy_loop());
+	}
+
+	ebb_global_disable();
+	ebb_freeze_pmcs();
+
+	count_pmc(1, sample_period);
+
+	dump_ebb_state();
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0);
+
+	return 0;
+}
+
+/* Tests we can setup an EBB on our child - if it's expecting it */
+int ebb_on_willing_child(void)
+{
+	union pipe read_pipe, write_pipe;
+	struct event event;
+	pid_t pid;
+
+	FAIL_IF(pipe(read_pipe.fds) == -1);
+	FAIL_IF(pipe(write_pipe.fds) == -1);
+
+	pid = fork();
+	if (pid == 0) {
+		/* NB order of pipes looks reversed */
+		exit(victim_child(write_pipe, read_pipe));
+	}
+
+	/* Signal the child to setup its EBB handler */
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+	/* Child is running now */
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open_with_pid(&event, pid));
+	FAIL_IF(ebb_event_enable(&event));
+
+	/* Child show now take EBBs and then exit */
+	FAIL_IF(wait_for_child(pid));
+
+	event_close(&event);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(ebb_on_willing_child, "ebb_on_willing_child");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c
new file mode 100644
index 00000000000..be4dd5a4e98
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_vs_cpu_event_test.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "ebb.h"
+
+
+/*
+ * Tests an EBB vs a cpu event - in that order. The EBB should force the cpu
+ * event off the PMU.
+ */
+
+static int setup_cpu_event(struct event *event, int cpu)
+{
+	event_init_named(event, 0x400FA, "PM_RUN_INST_CMPL");
+
+	event->attr.exclude_kernel = 1;
+	event->attr.exclude_hv = 1;
+	event->attr.exclude_idle = 1;
+
+	SKIP_IF(require_paranoia_below(1));
+	FAIL_IF(event_open_with_cpu(event, cpu));
+	FAIL_IF(event_enable(event));
+
+	return 0;
+}
+
+int ebb_vs_cpu_event(void)
+{
+	union pipe read_pipe, write_pipe;
+	struct event event;
+	int cpu, rc;
+	pid_t pid;
+
+	cpu = pick_online_cpu();
+	FAIL_IF(cpu < 0);
+	FAIL_IF(bind_to_cpu(cpu));
+
+	FAIL_IF(pipe(read_pipe.fds) == -1);
+	FAIL_IF(pipe(write_pipe.fds) == -1);
+
+	pid = fork();
+	if (pid == 0) {
+		/* NB order of pipes looks reversed */
+		exit(ebb_child(write_pipe, read_pipe));
+	}
+
+	/* Signal the child to install its EBB event and wait */
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+	/* Now try to install our CPU event */
+	rc = setup_cpu_event(&event, cpu);
+	if (rc) {
+		kill_child_and_wait(pid);
+		return rc;
+	}
+
+	/* Signal the child to run */
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+	/* .. and wait for it to complete */
+	FAIL_IF(wait_for_child(pid));
+	FAIL_IF(event_disable(&event));
+	FAIL_IF(event_read(&event));
+
+	event_report(&event);
+
+	/* The cpu event may have run, but we don't expect 100% */
+	FAIL_IF(event.result.enabled >= event.result.running);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(ebb_vs_cpu_event, "ebb_vs_cpu_event");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/event_attributes_test.c b/tools/testing/selftests/powerpc/pmu/ebb/event_attributes_test.c
new file mode 100644
index 00000000000..7e78153f08e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/event_attributes_test.c
@@ -0,0 +1,131 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test various attributes of the EBB event are enforced.
+ */
+int event_attributes(void)
+{
+	struct event event, leader;
+
+	event_init(&event, 0x1001e);
+	event_leader_ebb_init(&event);
+	/* Expected to succeed */
+	FAIL_IF(event_open(&event));
+	event_close(&event);
+
+
+	event_init(&event, 0x001e); /* CYCLES - no PMC specified */
+	event_leader_ebb_init(&event);
+	/* Expected to fail, no PMC specified */
+	FAIL_IF(event_open(&event) == 0);
+
+
+	event_init(&event, 0x2001e);
+	event_leader_ebb_init(&event);
+	event.attr.exclusive = 0;
+	/* Expected to fail, not exclusive */
+	FAIL_IF(event_open(&event) == 0);
+
+
+	event_init(&event, 0x3001e);
+	event_leader_ebb_init(&event);
+	event.attr.freq = 1;
+	/* Expected to fail, sets freq */
+	FAIL_IF(event_open(&event) == 0);
+
+
+	event_init(&event, 0x4001e);
+	event_leader_ebb_init(&event);
+	event.attr.sample_period = 1;
+	/* Expected to fail, sets sample_period */
+	FAIL_IF(event_open(&event) == 0);
+
+
+	event_init(&event, 0x1001e);
+	event_leader_ebb_init(&event);
+	event.attr.enable_on_exec = 1;
+	/* Expected to fail, sets enable_on_exec */
+	FAIL_IF(event_open(&event) == 0);
+
+
+	event_init(&event, 0x1001e);
+	event_leader_ebb_init(&event);
+	event.attr.inherit = 1;
+	/* Expected to fail, sets inherit */
+	FAIL_IF(event_open(&event) == 0);
+
+
+	event_init(&leader, 0x1001e);
+	event_leader_ebb_init(&leader);
+	FAIL_IF(event_open(&leader));
+
+	event_init(&event, 0x20002);
+	event_ebb_init(&event);
+
+	/* Expected to succeed */
+	FAIL_IF(event_open_with_group(&event, leader.fd));
+	event_close(&leader);
+	event_close(&event);
+
+
+	event_init(&leader, 0x1001e);
+	event_leader_ebb_init(&leader);
+	FAIL_IF(event_open(&leader));
+
+	event_init(&event, 0x20002);
+
+	/* Expected to fail, event doesn't request EBB, leader does */
+	FAIL_IF(event_open_with_group(&event, leader.fd) == 0);
+	event_close(&leader);
+
+
+	event_init(&leader, 0x1001e);
+	event_leader_ebb_init(&leader);
+	/* Clear the EBB flag */
+	leader.attr.config &= ~(1ull << 63);
+
+	FAIL_IF(event_open(&leader));
+
+	event_init(&event, 0x20002);
+	event_ebb_init(&event);
+
+	/* Expected to fail, leader doesn't request EBB */
+	FAIL_IF(event_open_with_group(&event, leader.fd) == 0);
+	event_close(&leader);
+
+
+	event_init(&leader, 0x1001e);
+	event_leader_ebb_init(&leader);
+	leader.attr.exclusive = 0;
+	/* Expected to fail, leader isn't exclusive */
+	FAIL_IF(event_open(&leader) == 0);
+
+
+	event_init(&leader, 0x1001e);
+	event_leader_ebb_init(&leader);
+	leader.attr.pinned = 0;
+	/* Expected to fail, leader isn't pinned */
+	FAIL_IF(event_open(&leader) == 0);
+
+	event_init(&event, 0x1001e);
+	event_leader_ebb_init(&event);
+	/* Expected to fail, not a task event */
+	SKIP_IF(require_paranoia_below(1));
+	FAIL_IF(event_open_with_cpu(&event, 0) == 0);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(event_attributes, "event_attributes");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/fixed_instruction_loop.S b/tools/testing/selftests/powerpc/pmu/ebb/fixed_instruction_loop.S
new file mode 100644
index 00000000000..b866a0581d3
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/fixed_instruction_loop.S
@@ -0,0 +1,43 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <ppc-asm.h>
+
+	.text
+
+FUNC_START(thirty_two_instruction_loop)
+	cmpwi	r3,0
+	beqlr
+	addi	r4,r3,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1	# 28 addi's
+	subi	r3,r3,1
+	b	FUNC_NAME(thirty_two_instruction_loop)
+FUNC_END(thirty_two_instruction_loop)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/fork_cleanup_test.c b/tools/testing/selftests/powerpc/pmu/ebb/fork_cleanup_test.c
new file mode 100644
index 00000000000..9e7af6e7662
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/fork_cleanup_test.c
@@ -0,0 +1,79 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <setjmp.h>
+#include <signal.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test that a fork clears the PMU state of the child. eg. BESCR/EBBHR/EBBRR
+ * are cleared, and MMCR0_PMCC is reset, preventing the child from accessing
+ * the PMU.
+ */
+
+static struct event event;
+
+static int child(void)
+{
+	/* Even though we have EBE=0 we can still see the EBB regs */
+	FAIL_IF(mfspr(SPRN_BESCR) != 0);
+	FAIL_IF(mfspr(SPRN_EBBHR) != 0);
+	FAIL_IF(mfspr(SPRN_EBBRR) != 0);
+
+	FAIL_IF(catch_sigill(write_pmc1));
+
+	/* We can still read from the event, though it is on our parent */
+	FAIL_IF(event_read(&event));
+
+	return 0;
+}
+
+/* Tests that fork clears EBB state */
+int fork_cleanup(void)
+{
+	pid_t pid;
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	FAIL_IF(event_open(&event));
+
+	ebb_enable_pmc_counting(1);
+	setup_ebb_handler(standard_ebb_callee);
+	ebb_global_enable();
+
+	FAIL_IF(ebb_event_enable(&event));
+
+	mtspr(SPRN_MMCR0, MMCR0_FC);
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+
+	/* Don't need to actually take any EBBs */
+
+	pid = fork();
+	if (pid == 0)
+		exit(child());
+
+	/* Child does the actual testing */
+	FAIL_IF(wait_for_child(pid));
+
+	/* After fork */
+	event_close(&event);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(fork_cleanup, "fork_cleanup");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c
new file mode 100644
index 00000000000..f8190fa2959
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/instruction_count_test.c
@@ -0,0 +1,164 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <string.h>
+#include <sys/prctl.h>
+
+#include "ebb.h"
+
+
+/*
+ * Run a calibrated instruction loop and count instructions executed using
+ * EBBs. Make sure the counts look right.
+ */
+
+extern void thirty_two_instruction_loop(uint64_t loops);
+
+static bool counters_frozen = true;
+
+static int do_count_loop(struct event *event, uint64_t instructions,
+			 uint64_t overhead, bool report)
+{
+	int64_t difference, expected;
+	double percentage;
+
+	clear_ebb_stats();
+
+	counters_frozen = false;
+	mb();
+	mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC);
+
+	thirty_two_instruction_loop(instructions >> 5);
+
+	counters_frozen = true;
+	mb();
+	mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) | MMCR0_FC);
+
+	count_pmc(4, sample_period);
+
+	event->result.value = ebb_state.stats.pmc_count[4-1];
+	expected = instructions + overhead;
+	difference = event->result.value - expected;
+	percentage = (double)difference / event->result.value * 100;
+
+	if (report) {
+		printf("Looped for %lu instructions, overhead %lu\n", instructions, overhead);
+		printf("Expected %lu\n", expected);
+		printf("Actual   %llu\n", event->result.value);
+		printf("Error    %ld, %f%%\n", difference, percentage);
+		printf("Took %d EBBs\n", ebb_state.stats.ebb_count);
+	}
+
+	if (difference < 0)
+		difference = -difference;
+
+	/* Tolerate a difference of up to 0.0001 % */
+	difference *= 10000 * 100;
+	if (difference / event->result.value)
+		return -1;
+
+	return 0;
+}
+
+/* Count how many instructions it takes to do a null loop */
+static uint64_t determine_overhead(struct event *event)
+{
+	uint64_t current, overhead;
+	int i;
+
+	do_count_loop(event, 0, 0, false);
+	overhead = event->result.value;
+
+	for (i = 0; i < 100; i++) {
+		do_count_loop(event, 0, 0, false);
+		current = event->result.value;
+		if (current < overhead) {
+			printf("Replacing overhead %lu with %lu\n", overhead, current);
+			overhead = current;
+		}
+	}
+
+	return overhead;
+}
+
+static void pmc4_ebb_callee(void)
+{
+	uint64_t val;
+
+	val = mfspr(SPRN_BESCR);
+	if (!(val & BESCR_PMEO)) {
+		ebb_state.stats.spurious++;
+		goto out;
+	}
+
+	ebb_state.stats.ebb_count++;
+	count_pmc(4, sample_period);
+out:
+	if (counters_frozen)
+		reset_ebb_with_clear_mask(MMCR0_PMAO);
+	else
+		reset_ebb();
+}
+
+int instruction_count(void)
+{
+	struct event event;
+	uint64_t overhead;
+
+	event_init_named(&event, 0x400FA, "PM_RUN_INST_CMPL");
+	event_leader_ebb_init(&event);
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+	FAIL_IF(ebb_event_enable(&event));
+
+	sample_period = COUNTER_OVERFLOW;
+
+	setup_ebb_handler(pmc4_ebb_callee);
+	mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC);
+	ebb_global_enable();
+
+	overhead = determine_overhead(&event);
+	printf("Overhead of null loop: %lu instructions\n", overhead);
+
+	/* Run for 1M instructions */
+	FAIL_IF(do_count_loop(&event, 0x100000, overhead, true));
+
+	/* Run for 10M instructions */
+	FAIL_IF(do_count_loop(&event, 0xa00000, overhead, true));
+
+	/* Run for 100M instructions */
+	FAIL_IF(do_count_loop(&event, 0x6400000, overhead, true));
+
+	/* Run for 1G instructions */
+	FAIL_IF(do_count_loop(&event, 0x40000000, overhead, true));
+
+	/* Run for 16G instructions */
+	FAIL_IF(do_count_loop(&event, 0x400000000, overhead, true));
+
+	/* Run for 64G instructions */
+	FAIL_IF(do_count_loop(&event, 0x1000000000, overhead, true));
+
+	/* Run for 128G instructions */
+	FAIL_IF(do_count_loop(&event, 0x2000000000, overhead, true));
+
+	ebb_global_disable();
+	event_close(&event);
+
+	printf("Finished OK\n");
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(instruction_count, "instruction_count");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
new file mode 100644
index 00000000000..0c9dd9b2e39
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -0,0 +1,100 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test that tries to trigger CPU_FTR_PMAO_BUG. Which is a hardware defect
+ * where an exception triggers but we context switch before it is delivered and
+ * lose the exception.
+ */
+
+static int test_body(void)
+{
+	int i, orig_period, max_period;
+	struct event event;
+
+	/* We use PMC4 to make sure the kernel switches all counters correctly */
+	event_init_named(&event, 0x40002, "instructions");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+
+	ebb_enable_pmc_counting(4);
+	setup_ebb_handler(standard_ebb_callee);
+	ebb_global_enable();
+	FAIL_IF(ebb_event_enable(&event));
+
+	/*
+	 * We want a low sample period, but we also want to get out of the EBB
+	 * handler without tripping up again.
+	 *
+	 * This value picked after much experimentation.
+	 */
+	orig_period = max_period = sample_period = 400;
+
+	mtspr(SPRN_PMC4, pmc_sample_period(sample_period));
+
+	while (ebb_state.stats.ebb_count < 1000000) {
+		/*
+		 * We are trying to get the EBB exception to race exactly with
+		 * us entering the kernel to do the syscall. We then need the
+		 * kernel to decide our timeslice is up and context switch to
+		 * the other thread. When we come back our EBB will have been
+		 * lost and we'll spin in this while loop forever.
+		 */
+
+		for (i = 0; i < 100000; i++)
+			sched_yield();
+
+		/* Change the sample period slightly to try and hit the race */
+		if (sample_period >= (orig_period + 200))
+			sample_period = orig_period;
+		else
+			sample_period++;
+
+		if (sample_period > max_period)
+			max_period = sample_period;
+	}
+
+	ebb_freeze_pmcs();
+	ebb_global_disable();
+
+	count_pmc(4, sample_period);
+	mtspr(SPRN_PMC4, 0xdead);
+
+	dump_summary_ebb_state();
+	dump_ebb_hw_state();
+
+	event_close(&event);
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0);
+
+	/* We vary our sample period so we need extra fudge here */
+	FAIL_IF(!ebb_check_count(4, orig_period, 2 * (max_period - orig_period)));
+
+	return 0;
+}
+
+static int lost_exception(void)
+{
+	return eat_cpu(test_body);
+}
+
+int main(void)
+{
+	return test_harness(lost_exception, "lost_exception");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
new file mode 100644
index 00000000000..67d78af3284
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -0,0 +1,91 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/ioctl.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test counting multiple events using EBBs.
+ */
+int multi_counter(void)
+{
+	struct event events[6];
+	int i, group_fd;
+
+	event_init_named(&events[0], 0x1001C, "PM_CMPLU_STALL_THRD");
+	event_init_named(&events[1], 0x2D016, "PM_CMPLU_STALL_FXU");
+	event_init_named(&events[2], 0x30006, "PM_CMPLU_STALL_OTHER_CMPL");
+	event_init_named(&events[3], 0x4000A, "PM_CMPLU_STALL");
+	event_init_named(&events[4], 0x600f4, "PM_RUN_CYC");
+	event_init_named(&events[5], 0x500fa, "PM_RUN_INST_CMPL");
+
+	event_leader_ebb_init(&events[0]);
+	for (i = 1; i < 6; i++)
+		event_ebb_init(&events[i]);
+
+	group_fd = -1;
+	for (i = 0; i < 6; i++) {
+		events[i].attr.exclude_kernel = 1;
+		events[i].attr.exclude_hv = 1;
+		events[i].attr.exclude_idle = 1;
+
+		FAIL_IF(event_open_with_group(&events[i], group_fd));
+		if (group_fd == -1)
+			group_fd = events[0].fd;
+	}
+
+	ebb_enable_pmc_counting(1);
+	ebb_enable_pmc_counting(2);
+	ebb_enable_pmc_counting(3);
+	ebb_enable_pmc_counting(4);
+	ebb_enable_pmc_counting(5);
+	ebb_enable_pmc_counting(6);
+	setup_ebb_handler(standard_ebb_callee);
+
+	FAIL_IF(ioctl(events[0].fd, PERF_EVENT_IOC_ENABLE, PERF_IOC_FLAG_GROUP));
+	FAIL_IF(event_read(&events[0]));
+
+	ebb_global_enable();
+
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+	mtspr(SPRN_PMC2, pmc_sample_period(sample_period));
+	mtspr(SPRN_PMC3, pmc_sample_period(sample_period));
+	mtspr(SPRN_PMC4, pmc_sample_period(sample_period));
+	mtspr(SPRN_PMC5, pmc_sample_period(sample_period));
+	mtspr(SPRN_PMC6, pmc_sample_period(sample_period));
+
+	while (ebb_state.stats.ebb_count < 50) {
+		FAIL_IF(core_busy_loop());
+		FAIL_IF(ebb_check_mmcr0());
+	}
+
+	ebb_global_disable();
+	ebb_freeze_pmcs();
+
+	count_pmc(1, sample_period);
+	count_pmc(2, sample_period);
+	count_pmc(3, sample_period);
+	count_pmc(4, sample_period);
+	count_pmc(5, sample_period);
+	count_pmc(6, sample_period);
+
+	dump_ebb_state();
+
+	for (i = 0; i < 6; i++)
+		event_close(&events[i]);
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(multi_counter, "multi_counter");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
new file mode 100644
index 00000000000..b8dc371f933
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test running multiple EBB using processes at once on a single CPU. They
+ * should all run happily without interfering with each other.
+ */
+
+static bool child_should_exit;
+
+static void sigint_handler(int signal)
+{
+	child_should_exit = true;
+}
+
+struct sigaction sigint_action = {
+	.sa_handler = sigint_handler,
+};
+
+static int cycles_child(void)
+{
+	struct event event;
+
+	if (sigaction(SIGINT, &sigint_action, NULL)) {
+		perror("sigaction");
+		return 1;
+	}
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+
+	ebb_enable_pmc_counting(1);
+	setup_ebb_handler(standard_ebb_callee);
+	ebb_global_enable();
+
+	FAIL_IF(ebb_event_enable(&event));
+
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+
+	while (!child_should_exit) {
+		FAIL_IF(core_busy_loop());
+		FAIL_IF(ebb_check_mmcr0());
+	}
+
+	ebb_global_disable();
+	ebb_freeze_pmcs();
+
+	count_pmc(1, sample_period);
+
+	dump_summary_ebb_state();
+
+	event_close(&event);
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0);
+
+	return 0;
+}
+
+#define NR_CHILDREN	4
+
+int multi_ebb_procs(void)
+{
+	pid_t pids[NR_CHILDREN];
+	int cpu, rc, i;
+
+	cpu = pick_online_cpu();
+	FAIL_IF(cpu < 0);
+	FAIL_IF(bind_to_cpu(cpu));
+
+	for (i = 0; i < NR_CHILDREN; i++) {
+		pids[i] = fork();
+		if (pids[i] == 0)
+			exit(cycles_child());
+	}
+
+	/* Have them all run for "a while" */
+	sleep(10);
+
+	rc = 0;
+	for (i = 0; i < NR_CHILDREN; i++) {
+		/* Tell them to stop */
+		kill(pids[i], SIGINT);
+		/* And wait */
+		rc |= wait_for_child(pids[i]);
+	}
+
+	return rc;
+}
+
+int main(void)
+{
+	return test_harness(multi_ebb_procs, "multi_ebb_procs");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/no_handler_test.c b/tools/testing/selftests/powerpc/pmu/ebb/no_handler_test.c
new file mode 100644
index 00000000000..2f9bf8edfa6
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/no_handler_test.c
@@ -0,0 +1,61 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <setjmp.h>
+#include <signal.h>
+
+#include "ebb.h"
+
+
+/* Test that things work sanely if we have no handler */
+
+static int no_handler_test(void)
+{
+	struct event event;
+	u64 val;
+	int i;
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+	FAIL_IF(ebb_event_enable(&event));
+
+	val = mfspr(SPRN_EBBHR);
+	FAIL_IF(val != 0);
+
+	/* Make sure it overflows quickly */
+	sample_period = 1000;
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+
+	/* Spin to make sure the event has time to overflow */
+	for (i = 0; i < 1000; i++)
+		mb();
+
+	dump_ebb_state();
+
+	/* We expect to see the PMU frozen & PMAO set */
+	val = mfspr(SPRN_MMCR0);
+	FAIL_IF(val != 0x0000000080000080);
+
+	event_close(&event);
+
+	dump_ebb_state();
+
+	/* The real test is that we never took an EBB at 0x0 */
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(no_handler_test,"no_handler_test");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
new file mode 100644
index 00000000000..986500fd213
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -0,0 +1,106 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test that the kernel properly handles PMAE across context switches.
+ *
+ * We test this by calling into the kernel inside our EBB handler, where PMAE
+ * is clear. A cpu eater companion thread is running on the same CPU as us to
+ * encourage the scheduler to switch us.
+ *
+ * The kernel must make sure that when it context switches us back in, it
+ * honours the fact that we had PMAE clear.
+ *
+ * Observed to hit the failing case on the first EBB with a broken kernel.
+ */
+
+static bool mmcr0_mismatch;
+static uint64_t before, after;
+
+static void syscall_ebb_callee(void)
+{
+	uint64_t val;
+
+	val = mfspr(SPRN_BESCR);
+	if (!(val & BESCR_PMEO)) {
+		ebb_state.stats.spurious++;
+		goto out;
+	}
+
+	ebb_state.stats.ebb_count++;
+	count_pmc(1, sample_period);
+
+	before = mfspr(SPRN_MMCR0);
+
+	/* Try and get ourselves scheduled, to force a PMU context switch */
+	sched_yield();
+
+	after = mfspr(SPRN_MMCR0);
+	if (before != after)
+		mmcr0_mismatch = true;
+
+out:
+	reset_ebb();
+}
+
+static int test_body(void)
+{
+	struct event event;
+
+	event_init_named(&event, 0x1001e, "cycles");
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+
+	setup_ebb_handler(syscall_ebb_callee);
+	ebb_global_enable();
+
+	FAIL_IF(ebb_event_enable(&event));
+
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+
+	while (ebb_state.stats.ebb_count < 20 && !mmcr0_mismatch)
+		FAIL_IF(core_busy_loop());
+
+	ebb_global_disable();
+	ebb_freeze_pmcs();
+
+	count_pmc(1, sample_period);
+
+	dump_ebb_state();
+
+	if (mmcr0_mismatch)
+		printf("Saw MMCR0 before 0x%lx after 0x%lx\n", before, after);
+
+	event_close(&event);
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0);
+	FAIL_IF(mmcr0_mismatch);
+
+	return 0;
+}
+
+int pmae_handling(void)
+{
+	return eat_cpu(test_body);
+}
+
+int main(void)
+{
+	return test_harness(pmae_handling, "pmae_handling");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
new file mode 100644
index 00000000000..a503fa70c95
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -0,0 +1,93 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "ebb.h"
+
+
+/*
+ * Test that PMC5 & 6 are frozen (ie. don't overflow) when they are not being
+ * used. Tests the MMCR0_FC56 logic in the kernel.
+ */
+
+static int pmc56_overflowed;
+
+static void ebb_callee(void)
+{
+	uint64_t val;
+
+	val = mfspr(SPRN_BESCR);
+	if (!(val & BESCR_PMEO)) {
+		ebb_state.stats.spurious++;
+		goto out;
+	}
+
+	ebb_state.stats.ebb_count++;
+	count_pmc(2, sample_period);
+
+	val = mfspr(SPRN_PMC5);
+	if (val >= COUNTER_OVERFLOW)
+		pmc56_overflowed++;
+
+	count_pmc(5, COUNTER_OVERFLOW);
+
+	val = mfspr(SPRN_PMC6);
+	if (val >= COUNTER_OVERFLOW)
+		pmc56_overflowed++;
+
+	count_pmc(6, COUNTER_OVERFLOW);
+
+out:
+	reset_ebb();
+}
+
+int pmc56_overflow(void)
+{
+	struct event event;
+
+	/* Use PMC2 so we set PMCjCE, which enables PMC5/6 */
+	event_init(&event, 0x2001e);
+	event_leader_ebb_init(&event);
+
+	event.attr.exclude_kernel = 1;
+	event.attr.exclude_hv = 1;
+	event.attr.exclude_idle = 1;
+
+	FAIL_IF(event_open(&event));
+
+	setup_ebb_handler(ebb_callee);
+	ebb_global_enable();
+
+	FAIL_IF(ebb_event_enable(&event));
+
+	mtspr(SPRN_PMC1, pmc_sample_period(sample_period));
+	mtspr(SPRN_PMC5, 0);
+	mtspr(SPRN_PMC6, 0);
+
+	while (ebb_state.stats.ebb_count < 10)
+		FAIL_IF(core_busy_loop());
+
+	ebb_global_disable();
+	ebb_freeze_pmcs();
+
+	count_pmc(2, sample_period);
+
+	dump_ebb_state();
+
+	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
+
+	event_close(&event);
+
+	FAIL_IF(ebb_state.stats.ebb_count == 0 || pmc56_overflowed != 0);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(pmc56_overflow, "pmc56_overflow");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/reg.h b/tools/testing/selftests/powerpc/pmu/ebb/reg.h
new file mode 100644
index 00000000000..5921b0dfe2e
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/reg.h
@@ -0,0 +1,49 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#ifndef _SELFTESTS_POWERPC_REG_H
+#define _SELFTESTS_POWERPC_REG_H
+
+#define __stringify_1(x)        #x
+#define __stringify(x)          __stringify_1(x)
+
+#define mfspr(rn)       ({unsigned long rval; \
+                         asm volatile("mfspr %0," __stringify(rn) \
+                                 : "=r" (rval)); rval; })
+#define mtspr(rn, v)    asm volatile("mtspr " __stringify(rn) ",%0" : \
+                                    : "r" ((unsigned long)(v)) \
+                                    : "memory")
+
+#define mb()		asm volatile("sync" : : : "memory");
+
+#define SPRN_MMCR2     769
+#define SPRN_MMCRA     770
+#define SPRN_MMCR0     779
+#define   MMCR0_PMAO   0x00000080
+#define   MMCR0_PMAE   0x04000000
+#define   MMCR0_FC     0x80000000
+#define SPRN_EBBHR     804
+#define SPRN_EBBRR     805
+#define SPRN_BESCR     806     /* Branch event status & control register */
+#define SPRN_BESCRS    800     /* Branch event status & control set (1 bits set to 1) */
+#define SPRN_BESCRSU   801     /* Branch event status & control set upper */
+#define SPRN_BESCRR    802     /* Branch event status & control REset (1 bits set to 0) */
+#define SPRN_BESCRRU   803     /* Branch event status & control REset upper */
+
+#define BESCR_PMEO     0x1     /* PMU Event-based exception Occurred */
+#define BESCR_PME      (0x1ul << 32) /* PMU Event-based exception Enable */
+
+#define SPRN_PMC1      771
+#define SPRN_PMC2      772
+#define SPRN_PMC3      773
+#define SPRN_PMC4      774
+#define SPRN_PMC5      775
+#define SPRN_PMC6      776
+
+#define SPRN_SIAR      780
+#define SPRN_SDAR      781
+#define SPRN_SIER      768
+
+#endif /* _SELFTESTS_POWERPC_REG_H */
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c b/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c
new file mode 100644
index 00000000000..0cae66f659a
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/reg_access_test.c
@@ -0,0 +1,39 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "ebb.h"
+#include "reg.h"
+
+
+/*
+ * Test basic access to the EBB regs, they should be user accessible with no
+ * kernel interaction required.
+ */
+int reg_access(void)
+{
+	uint64_t val, expected;
+
+	expected = 0x8000000100000000ull;
+	mtspr(SPRN_BESCR, expected);
+	val = mfspr(SPRN_BESCR);
+
+	FAIL_IF(val != expected);
+
+	expected = 0x0000000001000000ull;
+	mtspr(SPRN_EBBHR, expected);
+	val = mfspr(SPRN_EBBHR);
+
+	FAIL_IF(val != expected);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(reg_access, "reg_access");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/task_event_pinned_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/task_event_pinned_vs_ebb_test.c
new file mode 100644
index 00000000000..d56607e4ffa
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/task_event_pinned_vs_ebb_test.c
@@ -0,0 +1,91 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "ebb.h"
+
+
+/*
+ * Tests a pinned per-task event vs an EBB - in that order. The pinned per-task
+ * event should prevent the EBB event from being enabled.
+ */
+
+static int setup_child_event(struct event *event, pid_t child_pid)
+{
+	event_init_named(event, 0x400FA, "PM_RUN_INST_CMPL");
+
+	event->attr.pinned = 1;
+
+	event->attr.exclude_kernel = 1;
+	event->attr.exclude_hv = 1;
+	event->attr.exclude_idle = 1;
+
+	FAIL_IF(event_open_with_pid(event, child_pid));
+	FAIL_IF(event_enable(event));
+
+	return 0;
+}
+
+int task_event_pinned_vs_ebb(void)
+{
+	union pipe read_pipe, write_pipe;
+	struct event event;
+	pid_t pid;
+	int rc;
+
+	FAIL_IF(pipe(read_pipe.fds) == -1);
+	FAIL_IF(pipe(write_pipe.fds) == -1);
+
+	pid = fork();
+	if (pid == 0) {
+		/* NB order of pipes looks reversed */
+		exit(ebb_child(write_pipe, read_pipe));
+	}
+
+	/* We setup the task event first */
+	rc = setup_child_event(&event, pid);
+	if (rc) {
+		kill_child_and_wait(pid);
+		return rc;
+	}
+
+	/* Signal the child to install its EBB event and wait */
+	if (sync_with_child(read_pipe, write_pipe))
+		/* If it fails, wait for it to exit */
+		goto wait;
+
+	/* Signal the child to run */
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+wait:
+	/* We expect it to fail to read the event */
+	FAIL_IF(wait_for_child(pid) != 2);
+	FAIL_IF(event_disable(&event));
+	FAIL_IF(event_read(&event));
+
+	event_report(&event);
+
+	FAIL_IF(event.result.value == 0);
+	/*
+	 * For reasons I don't understand enabled is usually just slightly
+	 * lower than running. Would be good to confirm why.
+	 */
+	FAIL_IF(event.result.enabled == 0);
+	FAIL_IF(event.result.running == 0);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(task_event_pinned_vs_ebb, "task_event_pinned_vs_ebb");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/task_event_vs_ebb_test.c b/tools/testing/selftests/powerpc/pmu/ebb/task_event_vs_ebb_test.c
new file mode 100644
index 00000000000..eba32196dbb
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/task_event_vs_ebb_test.c
@@ -0,0 +1,83 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "ebb.h"
+
+
+/*
+ * Tests a per-task event vs an EBB - in that order. The EBB should push the
+ * per-task event off the PMU.
+ */
+
+static int setup_child_event(struct event *event, pid_t child_pid)
+{
+	event_init_named(event, 0x400FA, "PM_RUN_INST_CMPL");
+
+	event->attr.exclude_kernel = 1;
+	event->attr.exclude_hv = 1;
+	event->attr.exclude_idle = 1;
+
+	FAIL_IF(event_open_with_pid(event, child_pid));
+	FAIL_IF(event_enable(event));
+
+	return 0;
+}
+
+int task_event_vs_ebb(void)
+{
+	union pipe read_pipe, write_pipe;
+	struct event event;
+	pid_t pid;
+	int rc;
+
+	FAIL_IF(pipe(read_pipe.fds) == -1);
+	FAIL_IF(pipe(write_pipe.fds) == -1);
+
+	pid = fork();
+	if (pid == 0) {
+		/* NB order of pipes looks reversed */
+		exit(ebb_child(write_pipe, read_pipe));
+	}
+
+	/* We setup the task event first */
+	rc = setup_child_event(&event, pid);
+	if (rc) {
+		kill_child_and_wait(pid);
+		return rc;
+	}
+
+	/* Signal the child to install its EBB event and wait */
+	if (sync_with_child(read_pipe, write_pipe))
+		/* If it fails, wait for it to exit */
+		goto wait;
+
+	/* Signal the child to run */
+	FAIL_IF(sync_with_child(read_pipe, write_pipe));
+
+wait:
+	/* The EBB event should push the task event off so the child should succeed */
+	FAIL_IF(wait_for_child(pid));
+	FAIL_IF(event_disable(&event));
+	FAIL_IF(event_read(&event));
+
+	event_report(&event);
+
+	/* The task event may have run, or not so we can't assert anything about it */
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(task_event_vs_ebb, "task_event_vs_ebb");
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/trace.c b/tools/testing/selftests/powerpc/pmu/ebb/trace.c
new file mode 100644
index 00000000000..251e66ab2aa
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/trace.c
@@ -0,0 +1,300 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+
+#include "trace.h"
+
+
+struct trace_buffer *trace_buffer_allocate(u64 size)
+{
+	struct trace_buffer *tb;
+
+	if (size < sizeof(*tb)) {
+		fprintf(stderr, "Error: trace buffer too small\n");
+		return NULL;
+	}
+
+	tb = mmap(NULL, size, PROT_READ | PROT_WRITE,
+		  MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (tb == MAP_FAILED) {
+		perror("mmap");
+		return NULL;
+	}
+
+	tb->size = size;
+	tb->tail = tb->data;
+	tb->overflow = false;
+
+	return tb;
+}
+
+static bool trace_check_bounds(struct trace_buffer *tb, void *p)
+{
+	return p < ((void *)tb + tb->size);
+}
+
+static bool trace_check_alloc(struct trace_buffer *tb, void *p)
+{
+	/*
+	 * If we ever overflowed don't allow any more input. This prevents us
+	 * from dropping a large item and then later logging a small one. The
+	 * buffer should just stop when overflow happened, not be patchy. If
+	 * you're overflowing, make your buffer bigger.
+	 */
+	if (tb->overflow)
+		return false;
+
+	if (!trace_check_bounds(tb, p)) {
+		tb->overflow = true;
+		return false;
+	}
+
+	return true;
+}
+
+static void *trace_alloc(struct trace_buffer *tb, int bytes)
+{
+	void *p, *newtail;
+
+	p = tb->tail;
+	newtail = tb->tail + bytes;
+	if (!trace_check_alloc(tb, newtail))
+		return NULL;
+
+	tb->tail = newtail;
+
+	return p;
+}
+
+static struct trace_entry *trace_alloc_entry(struct trace_buffer *tb, int payload_size)
+{
+	struct trace_entry *e;
+
+	e = trace_alloc(tb, sizeof(*e) + payload_size);
+	if (e)
+		e->length = payload_size;
+
+	return e;
+}
+
+int trace_log_reg(struct trace_buffer *tb, u64 reg, u64 value)
+{
+	struct trace_entry *e;
+	u64 *p;
+
+	e = trace_alloc_entry(tb, sizeof(reg) + sizeof(value));
+	if (!e)
+		return -ENOSPC;
+
+	e->type = TRACE_TYPE_REG;
+	p = (u64 *)e->data;
+	*p++ = reg;
+	*p++ = value;
+
+	return 0;
+}
+
+int trace_log_counter(struct trace_buffer *tb, u64 value)
+{
+	struct trace_entry *e;
+	u64 *p;
+
+	e = trace_alloc_entry(tb, sizeof(value));
+	if (!e)
+		return -ENOSPC;
+
+	e->type = TRACE_TYPE_COUNTER;
+	p = (u64 *)e->data;
+	*p++ = value;
+
+	return 0;
+}
+
+int trace_log_string(struct trace_buffer *tb, char *str)
+{
+	struct trace_entry *e;
+	char *p;
+	int len;
+
+	len = strlen(str);
+
+	/* We NULL terminate to make printing easier */
+	e = trace_alloc_entry(tb, len + 1);
+	if (!e)
+		return -ENOSPC;
+
+	e->type = TRACE_TYPE_STRING;
+	p = (char *)e->data;
+	memcpy(p, str, len);
+	p += len;
+	*p = '\0';
+
+	return 0;
+}
+
+int trace_log_indent(struct trace_buffer *tb)
+{
+	struct trace_entry *e;
+
+	e = trace_alloc_entry(tb, 0);
+	if (!e)
+		return -ENOSPC;
+
+	e->type = TRACE_TYPE_INDENT;
+
+	return 0;
+}
+
+int trace_log_outdent(struct trace_buffer *tb)
+{
+	struct trace_entry *e;
+
+	e = trace_alloc_entry(tb, 0);
+	if (!e)
+		return -ENOSPC;
+
+	e->type = TRACE_TYPE_OUTDENT;
+
+	return 0;
+}
+
+static void trace_print_header(int seq, int prefix)
+{
+	printf("%*s[%d]: ", prefix, "", seq);
+}
+
+static char *trace_decode_reg(int reg)
+{
+	switch (reg) {
+		case 769: return "SPRN_MMCR2"; break;
+		case 770: return "SPRN_MMCRA"; break;
+		case 779: return "SPRN_MMCR0"; break;
+		case 804: return "SPRN_EBBHR"; break;
+		case 805: return "SPRN_EBBRR"; break;
+		case 806: return "SPRN_BESCR"; break;
+		case 800: return "SPRN_BESCRS"; break;
+		case 801: return "SPRN_BESCRSU"; break;
+		case 802: return "SPRN_BESCRR"; break;
+		case 803: return "SPRN_BESCRRU"; break;
+		case 771: return "SPRN_PMC1"; break;
+		case 772: return "SPRN_PMC2"; break;
+		case 773: return "SPRN_PMC3"; break;
+		case 774: return "SPRN_PMC4"; break;
+		case 775: return "SPRN_PMC5"; break;
+		case 776: return "SPRN_PMC6"; break;
+		case 780: return "SPRN_SIAR"; break;
+		case 781: return "SPRN_SDAR"; break;
+		case 768: return "SPRN_SIER"; break;
+	}
+
+	return NULL;
+}
+
+static void trace_print_reg(struct trace_entry *e)
+{
+	u64 *p, *reg, *value;
+	char *name;
+
+	p = (u64 *)e->data;
+	reg = p++;
+	value = p;
+
+	name = trace_decode_reg(*reg);
+	if (name)
+		printf("register %-10s = 0x%016llx\n", name, *value);
+	else
+		printf("register %lld = 0x%016llx\n", *reg, *value);
+}
+
+static void trace_print_counter(struct trace_entry *e)
+{
+	u64 *value;
+
+	value = (u64 *)e->data;
+	printf("counter = %lld\n", *value);
+}
+
+static void trace_print_string(struct trace_entry *e)
+{
+	char *str;
+
+	str = (char *)e->data;
+	puts(str);
+}
+
+#define BASE_PREFIX	2
+#define PREFIX_DELTA	8
+
+static void trace_print_entry(struct trace_entry *e, int seq, int *prefix)
+{
+	switch (e->type) {
+	case TRACE_TYPE_REG:
+		trace_print_header(seq, *prefix);
+		trace_print_reg(e);
+		break;
+	case TRACE_TYPE_COUNTER:
+		trace_print_header(seq, *prefix);
+		trace_print_counter(e);
+		break;
+	case TRACE_TYPE_STRING:
+		trace_print_header(seq, *prefix);
+		trace_print_string(e);
+		break;
+	case TRACE_TYPE_INDENT:
+		trace_print_header(seq, *prefix);
+		puts("{");
+		*prefix += PREFIX_DELTA;
+		break;
+	case TRACE_TYPE_OUTDENT:
+		*prefix -= PREFIX_DELTA;
+		if (*prefix < BASE_PREFIX)
+			*prefix = BASE_PREFIX;
+		trace_print_header(seq, *prefix);
+		puts("}");
+		break;
+	default:
+		trace_print_header(seq, *prefix);
+		printf("entry @ %p type %d\n", e, e->type);
+		break;
+	}
+}
+
+void trace_buffer_print(struct trace_buffer *tb)
+{
+	struct trace_entry *e;
+	int i, prefix;
+	void *p;
+
+	printf("Trace buffer dump:\n");
+	printf("  address  %p \n", tb);
+	printf("  tail     %p\n", tb->tail);
+	printf("  size     %llu\n", tb->size);
+	printf("  overflow %s\n", tb->overflow ? "TRUE" : "false");
+	printf("  Content:\n");
+
+	p = tb->data;
+
+	i = 0;
+	prefix = BASE_PREFIX;
+
+	while (trace_check_bounds(tb, p) && p < tb->tail) {
+		e = p;
+
+		trace_print_entry(e, i, &prefix);
+
+		i++;
+		p = (void *)e + sizeof(*e) + e->length;
+	}
+}
+
+void trace_print_location(struct trace_buffer *tb)
+{
+	printf("Trace buffer 0x%llx bytes @ %p\n", tb->size, tb);
+}
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/trace.h b/tools/testing/selftests/powerpc/pmu/ebb/trace.h
new file mode 100644
index 00000000000..926458e28c8
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/ebb/trace.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#ifndef _SELFTESTS_POWERPC_PMU_EBB_TRACE_H
+#define _SELFTESTS_POWERPC_PMU_EBB_TRACE_H
+
+#include "utils.h"
+
+#define TRACE_TYPE_REG		1
+#define TRACE_TYPE_COUNTER	2
+#define TRACE_TYPE_STRING	3
+#define TRACE_TYPE_INDENT	4
+#define TRACE_TYPE_OUTDENT	5
+
+struct trace_entry
+{
+	u8 type;
+	u8 length;
+	u8 data[0];
+};
+
+struct trace_buffer
+{
+	u64  size;
+	bool overflow;
+	void *tail;
+	u8   data[0];
+};
+
+struct trace_buffer *trace_buffer_allocate(u64 size);
+int trace_log_reg(struct trace_buffer *tb, u64 reg, u64 value);
+int trace_log_counter(struct trace_buffer *tb, u64 value);
+int trace_log_string(struct trace_buffer *tb, char *str);
+int trace_log_indent(struct trace_buffer *tb);
+int trace_log_outdent(struct trace_buffer *tb);
+void trace_buffer_print(struct trace_buffer *tb);
+void trace_print_location(struct trace_buffer *tb);
+
+#endif /* _SELFTESTS_POWERPC_PMU_EBB_TRACE_H */
diff --git a/tools/testing/selftests/powerpc/pmu/event.c b/tools/testing/selftests/powerpc/pmu/event.c
index 2b2d11df245..184b36807d4 100644
--- a/tools/testing/selftests/powerpc/pmu/event.c
+++ b/tools/testing/selftests/powerpc/pmu/event.c
@@ -39,7 +39,13 @@ void event_init_named(struct event *e, u64 config, char *name)
 	event_init_opts(e, config, PERF_TYPE_RAW, name);
 }
 
+void event_init(struct event *e, u64 config)
+{
+	event_init_opts(e, config, PERF_TYPE_RAW, "event");
+}
+
 #define PERF_CURRENT_PID	0
+#define PERF_NO_PID		-1
 #define PERF_NO_CPU		-1
 #define PERF_NO_GROUP		-1
 
@@ -59,6 +65,16 @@ int event_open_with_group(struct event *e, int group_fd)
 	return event_open_with_options(e, PERF_CURRENT_PID, PERF_NO_CPU, group_fd);
 }
 
+int event_open_with_pid(struct event *e, pid_t pid)
+{
+	return event_open_with_options(e, pid, PERF_NO_CPU, PERF_NO_GROUP);
+}
+
+int event_open_with_cpu(struct event *e, int cpu)
+{
+	return event_open_with_options(e, PERF_NO_PID, cpu, PERF_NO_GROUP);
+}
+
 int event_open(struct event *e)
 {
 	return event_open_with_options(e, PERF_CURRENT_PID, PERF_NO_CPU, PERF_NO_GROUP);
@@ -69,6 +85,16 @@ void event_close(struct event *e)
 	close(e->fd);
 }
 
+int event_enable(struct event *e)
+{
+	return ioctl(e->fd, PERF_EVENT_IOC_ENABLE);
+}
+
+int event_disable(struct event *e)
+{
+	return ioctl(e->fd, PERF_EVENT_IOC_DISABLE);
+}
+
 int event_reset(struct event *e)
 {
 	return ioctl(e->fd, PERF_EVENT_IOC_RESET);
diff --git a/tools/testing/selftests/powerpc/pmu/event.h b/tools/testing/selftests/powerpc/pmu/event.h
index e6993192ff3..a0ea6b1eef7 100644
--- a/tools/testing/selftests/powerpc/pmu/event.h
+++ b/tools/testing/selftests/powerpc/pmu/event.h
@@ -29,8 +29,12 @@ void event_init_named(struct event *e, u64 config, char *name);
 void event_init_opts(struct event *e, u64 config, int type, char *name);
 int event_open_with_options(struct event *e, pid_t pid, int cpu, int group_fd);
 int event_open_with_group(struct event *e, int group_fd);
+int event_open_with_pid(struct event *e, pid_t pid);
+int event_open_with_cpu(struct event *e, int cpu);
 int event_open(struct event *e);
 void event_close(struct event *e);
+int event_enable(struct event *e);
+int event_disable(struct event *e);
 int event_reset(struct event *e);
 int event_read(struct event *e);
 void event_report_justified(struct event *e, int name_width, int result_width);
diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c
new file mode 100644
index 00000000000..0f6a4731d54
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/lib.c
@@ -0,0 +1,252 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#define _GNU_SOURCE	/* For CPU_ZERO etc. */
+
+#include <errno.h>
+#include <sched.h>
+#include <setjmp.h>
+#include <stdlib.h>
+#include <sys/wait.h>
+
+#include "utils.h"
+#include "lib.h"
+
+
+int pick_online_cpu(void)
+{
+	cpu_set_t mask;
+	int cpu;
+
+	CPU_ZERO(&mask);
+
+	if (sched_getaffinity(0, sizeof(mask), &mask)) {
+		perror("sched_getaffinity");
+		return -1;
+	}
+
+	/* We prefer a primary thread, but skip 0 */
+	for (cpu = 8; cpu < CPU_SETSIZE; cpu += 8)
+		if (CPU_ISSET(cpu, &mask))
+			return cpu;
+
+	/* Search for anything, but in reverse */
+	for (cpu = CPU_SETSIZE - 1; cpu >= 0; cpu--)
+		if (CPU_ISSET(cpu, &mask))
+			return cpu;
+
+	printf("No cpus in affinity mask?!\n");
+	return -1;
+}
+
+int bind_to_cpu(int cpu)
+{
+	cpu_set_t mask;
+
+	printf("Binding to cpu %d\n", cpu);
+
+	CPU_ZERO(&mask);
+	CPU_SET(cpu, &mask);
+
+	return sched_setaffinity(0, sizeof(mask), &mask);
+}
+
+#define PARENT_TOKEN	0xAA
+#define CHILD_TOKEN	0x55
+
+int sync_with_child(union pipe read_pipe, union pipe write_pipe)
+{
+	char c = PARENT_TOKEN;
+
+	FAIL_IF(write(write_pipe.write_fd, &c, 1) != 1);
+	FAIL_IF(read(read_pipe.read_fd, &c, 1) != 1);
+	if (c != CHILD_TOKEN) /* sometimes expected */
+		return 1;
+
+	return 0;
+}
+
+int wait_for_parent(union pipe read_pipe)
+{
+	char c;
+
+	FAIL_IF(read(read_pipe.read_fd, &c, 1) != 1);
+	FAIL_IF(c != PARENT_TOKEN);
+
+	return 0;
+}
+
+int notify_parent(union pipe write_pipe)
+{
+	char c = CHILD_TOKEN;
+
+	FAIL_IF(write(write_pipe.write_fd, &c, 1) != 1);
+
+	return 0;
+}
+
+int notify_parent_of_error(union pipe write_pipe)
+{
+	char c = ~CHILD_TOKEN;
+
+	FAIL_IF(write(write_pipe.write_fd, &c, 1) != 1);
+
+	return 0;
+}
+
+int wait_for_child(pid_t child_pid)
+{
+	int rc;
+
+	if (waitpid(child_pid, &rc, 0) == -1) {
+		perror("waitpid");
+		return 1;
+	}
+
+	if (WIFEXITED(rc))
+		rc = WEXITSTATUS(rc);
+	else
+		rc = 1; /* Signal or other */
+
+	return rc;
+}
+
+int kill_child_and_wait(pid_t child_pid)
+{
+	kill(child_pid, SIGTERM);
+
+	return wait_for_child(child_pid);
+}
+
+static int eat_cpu_child(union pipe read_pipe, union pipe write_pipe)
+{
+	volatile int i = 0;
+
+	/*
+	 * We are just here to eat cpu and die. So make sure we can be killed,
+	 * and also don't do any custom SIGTERM handling.
+	 */
+	signal(SIGTERM, SIG_DFL);
+
+	notify_parent(write_pipe);
+	wait_for_parent(read_pipe);
+
+	/* Soak up cpu forever */
+	while (1) i++;
+
+	return 0;
+}
+
+pid_t eat_cpu(int (test_function)(void))
+{
+	union pipe read_pipe, write_pipe;
+	int cpu, rc;
+	pid_t pid;
+
+	cpu = pick_online_cpu();
+	FAIL_IF(cpu < 0);
+	FAIL_IF(bind_to_cpu(cpu));
+
+	if (pipe(read_pipe.fds) == -1)
+		return -1;
+
+	if (pipe(write_pipe.fds) == -1)
+		return -1;
+
+	pid = fork();
+	if (pid == 0)
+		exit(eat_cpu_child(write_pipe, read_pipe));
+
+	if (sync_with_child(read_pipe, write_pipe)) {
+		rc = -1;
+		goto out;
+	}
+
+	printf("main test running as pid %d\n", getpid());
+
+	rc = test_function();
+out:
+	kill(pid, SIGKILL);
+
+	return rc;
+}
+
+struct addr_range libc, vdso;
+
+int parse_proc_maps(void)
+{
+	char execute, name[128];
+	uint64_t start, end;
+	FILE *f;
+	int rc;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!f) {
+		perror("fopen");
+		return -1;
+	}
+
+	do {
+		/* This skips line with no executable which is what we want */
+		rc = fscanf(f, "%lx-%lx %*c%*c%c%*c %*x %*d:%*d %*d %127s\n",
+			    &start, &end, &execute, name);
+		if (rc <= 0)
+			break;
+
+		if (execute != 'x')
+			continue;
+
+		if (strstr(name, "libc")) {
+			libc.first = start;
+			libc.last = end - 1;
+		} else if (strstr(name, "[vdso]")) {
+			vdso.first = start;
+			vdso.last = end - 1;
+		}
+	} while(1);
+
+	fclose(f);
+
+	return 0;
+}
+
+#define PARANOID_PATH	"/proc/sys/kernel/perf_event_paranoid"
+
+bool require_paranoia_below(int level)
+{
+	unsigned long current;
+	char *end, buf[16];
+	FILE *f;
+	int rc;
+
+	rc = -1;
+
+	f = fopen(PARANOID_PATH, "r");
+	if (!f) {
+		perror("fopen");
+		goto out;
+	}
+
+	if (!fgets(buf, sizeof(buf), f)) {
+		printf("Couldn't read " PARANOID_PATH "?\n");
+		goto out_close;
+	}
+
+	current = strtoul(buf, &end, 10);
+
+	if (end == buf) {
+		printf("Couldn't parse " PARANOID_PATH "?\n");
+		goto out_close;
+	}
+
+	if (current >= level)
+		goto out;
+
+	rc = 0;
+out_close:
+	fclose(f);
+out:
+	return rc;
+}
diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h
new file mode 100644
index 00000000000..ca5d72ae3be
--- /dev/null
+++ b/tools/testing/selftests/powerpc/pmu/lib.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2014, Michael Ellerman, IBM Corp.
+ * Licensed under GPLv2.
+ */
+
+#ifndef __SELFTESTS_POWERPC_PMU_LIB_H
+#define __SELFTESTS_POWERPC_PMU_LIB_H
+
+#include <stdio.h>
+#include <stdint.h>
+#include <string.h>
+#include <unistd.h>
+
+union pipe {
+	struct {
+		int read_fd;
+		int write_fd;
+	};
+	int fds[2];
+};
+
+extern int pick_online_cpu(void);
+extern int bind_to_cpu(int cpu);
+extern int kill_child_and_wait(pid_t child_pid);
+extern int wait_for_child(pid_t child_pid);
+extern int sync_with_child(union pipe read_pipe, union pipe write_pipe);
+extern int wait_for_parent(union pipe read_pipe);
+extern int notify_parent(union pipe write_pipe);
+extern int notify_parent_of_error(union pipe write_pipe);
+extern pid_t eat_cpu(int (test_function)(void));
+extern bool require_paranoia_below(int level);
+
+struct addr_range {
+	uint64_t first, last;
+};
+
+extern struct addr_range libc, vdso;
+
+int parse_proc_maps(void);
+
+#endif /* __SELFTESTS_POWERPC_PMU_LIB_H */
diff --git a/tools/testing/selftests/powerpc/pmu/loop.S b/tools/testing/selftests/powerpc/pmu/loop.S
index 8820e3df144..20c1f0876c4 100644
--- a/tools/testing/selftests/powerpc/pmu/loop.S
+++ b/tools/testing/selftests/powerpc/pmu/loop.S
@@ -3,44 +3,41 @@
  * Licensed under GPLv2.
  */
 
+#include <ppc-asm.h>
+
 	.text
 
-	.global thirty_two_instruction_loop
-	.type .thirty_two_instruction_loop,@function
-	.section ".opd","aw",@progbits
-thirty_two_instruction_loop:
-	.quad .thirty_two_instruction_loop, .TOC.@tocbase, 0
-	.previous
-.thirty_two_instruction_loop:
-	cmpwi	%r3,0
+FUNC_START(thirty_two_instruction_loop)
+	cmpdi	r3,0
 	beqlr
-	addi	%r4,%r3,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1
-	addi	%r4,%r4,1	# 28 addi's
-	subi	%r3,%r3,1
-	b	.thirty_two_instruction_loop
+	addi	r4,r3,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1
+	addi	r4,r4,1	# 28 addi's
+	subi	r3,r3,1
+	b	FUNC_NAME(thirty_two_instruction_loop)
+FUNC_END(thirty_two_instruction_loop)
diff --git a/tools/testing/selftests/powerpc/subunit.h b/tools/testing/selftests/powerpc/subunit.h
index 98a22920792..9c6c4e901ab 100644
--- a/tools/testing/selftests/powerpc/subunit.h
+++ b/tools/testing/selftests/powerpc/subunit.h
@@ -26,6 +26,11 @@ static inline void test_error(char *name)
 	printf("error: %s\n", name);
 }
 
+static inline void test_skip(char *name)
+{
+	printf("skip: %s\n", name);
+}
+
 static inline void test_success(char *name)
 {
 	printf("success: %s\n", name);
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
new file mode 100644
index 00000000000..2cede239a07
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -0,0 +1,15 @@
+PROGS := tm-resched-dscr
+
+all: $(PROGS)
+
+$(PROGS): ../harness.c
+
+run_tests: all
+	@-for PROG in $(PROGS); do \
+		./$$PROG; \
+	done;
+
+clean:
+	rm -f $(PROGS) *.o
+
+.PHONY: all run_tests clean
diff --git a/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
new file mode 100644
index 00000000000..42d4c8caad8
--- /dev/null
+++ b/tools/testing/selftests/powerpc/tm/tm-resched-dscr.c
@@ -0,0 +1,98 @@
+/* Test context switching to see if the DSCR SPR is correctly preserved
+ * when within a transaction.
+ *
+ * Note: We assume that the DSCR has been left at the default value (0)
+ * for all CPUs.
+ *
+ * Method:
+ *
+ * Set a value into the DSCR.
+ *
+ * Start a transaction, and suspend it (*).
+ *
+ * Hard loop checking to see if the transaction has become doomed.
+ *
+ * Now that we *may* have been preempted, record the DSCR and TEXASR SPRS.
+ *
+ * If the abort was because of a context switch, check the DSCR value.
+ * Otherwise, try again.
+ *
+ * (*) If the transaction is not suspended we can't see the problem because
+ * the transaction abort handler will restore the DSCR to it's checkpointed
+ * value before we regain control.
+ */
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <asm/tm.h>
+
+#include "utils.h"
+
+#define TBEGIN          ".long 0x7C00051D ;"
+#define TEND            ".long 0x7C00055D ;"
+#define TCHECK          ".long 0x7C00059C ;"
+#define TSUSPEND        ".long 0x7C0005DD ;"
+#define TRESUME         ".long 0x7C2005DD ;"
+#define SPRN_TEXASR     0x82
+#define SPRN_DSCR       0x03
+
+int test_body(void)
+{
+	uint64_t rv, dscr1 = 1, dscr2, texasr;
+
+	printf("Check DSCR TM context switch: ");
+	fflush(stdout);
+	for (;;) {
+		rv = 1;
+		asm __volatile__ (
+			/* set a known value into the DSCR */
+			"ld      3, %[dscr1];"
+			"mtspr   %[sprn_dscr], 3;"
+
+			/* start and suspend a transaction */
+			TBEGIN
+			"beq     1f;"
+			TSUSPEND
+
+			/* hard loop until the transaction becomes doomed */
+			"2: ;"
+			TCHECK
+			"bc      4, 0, 2b;"
+
+			/* record DSCR and TEXASR */
+			"mfspr   3, %[sprn_dscr];"
+			"std     3, %[dscr2];"
+			"mfspr   3, %[sprn_texasr];"
+			"std     3, %[texasr];"
+
+			TRESUME
+			TEND
+			"li      %[rv], 0;"
+			"1: ;"
+			: [rv]"=r"(rv), [dscr2]"=m"(dscr2), [texasr]"=m"(texasr)
+			: [dscr1]"m"(dscr1)
+			, [sprn_dscr]"i"(SPRN_DSCR), [sprn_texasr]"i"(SPRN_TEXASR)
+			: "memory", "r3"
+		);
+		assert(rv); /* make sure the transaction aborted */
+		if ((texasr >> 56) != TM_CAUSE_RESCHED) {
+			putchar('.');
+			fflush(stdout);
+			continue;
+		}
+		if (dscr2 != dscr1) {
+			printf(" FAIL\n");
+			return 1;
+		} else {
+			printf(" OK\n");
+			return 0;
+		}
+	}
+}
+
+int main(void)
+{
+	return test_harness(test_body, "tm_resched_dscr");
+}
diff --git a/tools/testing/selftests/powerpc/utils.h b/tools/testing/selftests/powerpc/utils.h
index 0de064406da..a93777ae068 100644
--- a/tools/testing/selftests/powerpc/utils.h
+++ b/tools/testing/selftests/powerpc/utils.h
@@ -31,6 +31,18 @@ do {								\
 	}							\
 } while (0)
 
+/* The test harness uses this, yes it's gross */
+#define MAGIC_SKIP_RETURN_VALUE	99
+
+#define SKIP_IF(x)						\
+do {								\
+	if ((x)) {						\
+		fprintf(stderr,					\
+		"[SKIP] Test skipped on line %d\n", __LINE__);	\
+		return MAGIC_SKIP_RETURN_VALUE;			\
+	}							\
+} while (0)
+
 #define _str(s) #s
 #define str(s) _str(s)
 
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index ee1f6cae3d7..3f6c9b78d17 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -54,10 +54,16 @@ do
 			if test -f "$i/qemu-cmd"
 			then
 				print_bug qemu failed
+				echo "   $i"
+			elif test -f "$i/buildonly"
+			then
+				echo Build-only run, no boot/test
+				configcheck.sh $i/.config $i/ConfigFragment
+				parse-build.sh $i/Make.out $configfile
 			else
 				print_bug Build failed
+				echo "   $i"
 			fi
-			echo "   $i"
 		fi
 	done
 done
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 27e544e2951..0f69dcbf9de 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -42,6 +42,7 @@ grace=120
 
 T=/tmp/kvm-test-1-run.sh.$$
 trap 'rm -rf $T' 0
+touch $T
 
 . $KVM/bin/functions.sh
 . $KVPATH/ver_functions.sh
@@ -131,7 +132,10 @@ boot_args=$6
 
 cd $KVM
 kstarttime=`awk 'BEGIN { print systime() }' < /dev/null`
-echo ' ---' `date`: Starting kernel
+if test -z "$TORTURE_BUILDONLY"
+then
+	echo ' ---' `date`: Starting kernel
+fi
 
 # Generate -smp qemu argument.
 qemu_args="-nographic $qemu_args"
@@ -157,12 +161,13 @@ boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
 # Generate kernel-version-specific boot parameters
 boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`"
 
-echo $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
 if test -n "$TORTURE_BUILDONLY"
 then
 	echo Build-only run specified, boot/test omitted.
+	touch $resdir/buildonly
 	exit 0
 fi
+echo $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
 ( $QEMU $qemu_args -m 512 -kernel $builddir/$BOOT_IMAGE -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) &
 qemu_pid=$!
 commandcompleted=0
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 40285c58653..589e9c38413 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -340,12 +340,18 @@ function dump(first, pastlast)
 	for (j = 1; j < jn; j++) {
 		builddir=KVM "/b" j
 		print "rm -f " builddir ".ready"
-		print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`";
-		print "echo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log";
+		print "if test -z \"$TORTURE_BUILDONLY\""
+		print "then"
+		print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date`";
+		print "\techo ----", cfr[j], cpusr[j] ovf ": Starting kernel. `date` >> " rd "/log";
+		print "fi"
 	}
 	print "wait"
-	print "echo ---- All kernel runs complete. `date`";
-	print "echo ---- All kernel runs complete. `date` >> " rd "/log";
+	print "if test -z \"$TORTURE_BUILDONLY\""
+	print "then"
+	print "\techo ---- All kernel runs complete. `date`";
+	print "\techo ---- All kernel runs complete. `date` >> " rd "/log";
+	print "fi"
 	for (j = 1; j < jn; j++) {
 		builddir=KVM "/b" j
 		print "echo ----", cfr[j], cpusr[j] ovf ": Build/run results:";
@@ -385,10 +391,7 @@ echo
 echo
 echo " --- `date` Test summary:"
 echo Results directory: $resdir/$ds
-if test -z "$TORTURE_BUILDONLY"
-then
-	kvm-recheck.sh $resdir/$ds
-fi
+kvm-recheck.sh $resdir/$ds
 ___EOF___
 
 if test "$dryrun" = script
@@ -403,7 +406,7 @@ then
 		sed -e 's/:.*$//' -e 's/^echo //'
 	exit 0
 else
-	# Not a dryru, so run the script.
+	# Not a dryrun, so run the script.
 	sh $T/script
 fi
 
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index 9c827ec59a9..063b7079c62 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -15,7 +15,6 @@ CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ZERO=y
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index 1a777b5f68b..ea119ba2f7d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=n
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=y
 CONFIG_RCU_BOOST=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
index 61c8d9ce5bb..19cf9485f48 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02-T
@@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=n
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=y
 CONFIG_RCU_BOOST=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
index c1f111c1561..f4567fb3e33 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
@@ -14,7 +14,6 @@ CONFIG_RCU_FANOUT_LEAF=4
 CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 7dbd27ce17a..0a262fbb0c1 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=y
 CONFIG_RCU_CPU_STALL_VERBOSE=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index d0f32e57474..3a06b97e9a7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -18,7 +18,6 @@ CONFIG_RCU_NOCB_CPU_NONE=y
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_PROVE_RCU=y
-CONFIG_PROVE_RCU_DELAY=y
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index 2e477dfb9c5..8f084cca91b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -19,7 +19,6 @@ CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_PROVE_RCU=y
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index 042f86ef362..ab622550690 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -17,7 +17,6 @@ CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_FANOUT_EXACT=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=y
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index 3438cee1e3c..69a2e255bf9 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ALL=y
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
index bf4523d3e44..a0f32fb8f17 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T
@@ -18,7 +18,6 @@ CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ALL=y
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
index 81e4f7c0bf0..b7a62a540ad 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
@@ -13,7 +13,6 @@ CONFIG_SUSPEND=n
 CONFIG_HIBERNATION=n
 CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_RCU_DELAY=n
 CONFIG_RCU_CPU_STALL_INFO=n
 CONFIG_RCU_CPU_STALL_VERBOSE=n
 CONFIG_RCU_BOOST=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
index ef624ce73d8..a55c00877fe 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v0.0/P5-U-T-NH-sd-SMP-hp
@@ -13,7 +13,6 @@ CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
 #CHECK#CONFIG_TREE_PREEMPT_RCU=y
 CONFIG_DEBUG_KERNEL=y
-CONFIG_PROVE_RCU_DELAY=y
 CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
 CONFIG_RT_MUTEXES=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
index ef624ce73d8..a55c00877fe 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.12/P5-U-T-NH-sd-SMP-hp
@@ -13,7 +13,6 @@ CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
 #CHECK#CONFIG_TREE_PREEMPT_RCU=y
 CONFIG_DEBUG_KERNEL=y
-CONFIG_PROVE_RCU_DELAY=y
 CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
 CONFIG_RT_MUTEXES=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
index ef624ce73d8..a55c00877fe 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.3/P5-U-T-NH-sd-SMP-hp
@@ -13,7 +13,6 @@ CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
 #CHECK#CONFIG_TREE_PREEMPT_RCU=y
 CONFIG_DEBUG_KERNEL=y
-CONFIG_PROVE_RCU_DELAY=y
 CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
 CONFIG_RT_MUTEXES=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
index ef624ce73d8..a55c00877fe 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
+++ b/tools/testing/selftests/rcutorture/configs/rcu/v3.5/P5-U-T-NH-sd-SMP-hp
@@ -13,7 +13,6 @@ CONFIG_PREEMPT_VOLUNTARY=n
 CONFIG_PREEMPT=y
 #CHECK#CONFIG_TREE_PREEMPT_RCU=y
 CONFIG_DEBUG_KERNEL=y
-CONFIG_PROVE_RCU_DELAY=y
 CONFIG_DEBUG_OBJECTS=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
 CONFIG_RT_MUTEXES=y
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index adbb76cffb4..3e588db86a1 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -14,7 +14,6 @@ CONFIG_NO_HZ_FULL_SYSIDLE -- Do one.
 CONFIG_PREEMPT -- Do half.  (First three and #8.)
 CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not.
 CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING.
-CONFIG_PROVE_RCU_DELAY -- Do one.
 CONFIG_RCU_BOOST -- one of TREE_PREEMPT_RCU.
 CONFIG_RCU_BOOST_PRIO -- set to 2 for _BOOST testing.
 CONFIG_RCU_CPU_STALL_INFO -- do one with and without _VERBOSE.
diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile
index 447321104ec..e775adcbd29 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -21,7 +21,7 @@ OBJS = tmon.o tui.o sysfs.o pid.o
 OBJS +=
 
 tmon: $(OBJS) Makefile tmon.h
-	$(CC) ${CFLAGS} $(LDFLAGS) $(OBJS)  -o $(TARGET) -lm -lpanel -lncursesw  -lpthread
+	$(CC) ${CFLAGS} $(LDFLAGS) $(OBJS)  -o $(TARGET) -lm -lpanel -lncursesw -ltinfo -lpthread
 
 valgrind: tmon
 	 sudo valgrind -v --track-origins=yes --tool=memcheck --leak-check=yes --show-reachable=yes --num-callers=20 --track-fds=yes ./$(TARGET)  1> /dev/null
diff --git a/tools/thermal/tmon/tmon.c b/tools/thermal/tmon/tmon.c
index b30f531173e..09b7c321833 100644
--- a/tools/thermal/tmon/tmon.c
+++ b/tools/thermal/tmon/tmon.c
@@ -142,6 +142,7 @@ static void start_syslog(void)
 static void prepare_logging(void)
 {
 	int i;
+	struct stat logstat;
 
 	if (!logging)
 		return;
@@ -152,6 +153,29 @@ static void prepare_logging(void)
 		return;
 	}
 
+	if (lstat(TMON_LOG_FILE, &logstat) < 0) {
+		syslog(LOG_ERR, "Unable to stat log file %s\n", TMON_LOG_FILE);
+		fclose(tmon_log);
+		tmon_log = NULL;
+		return;
+	}
+
+	/* The log file must be a regular file owned by us */
+	if (S_ISLNK(logstat.st_mode)) {
+		syslog(LOG_ERR, "Log file is a symlink.  Will not log\n");
+		fclose(tmon_log);
+		tmon_log = NULL;
+		return;
+	}
+
+	if (logstat.st_uid != getuid()) {
+		syslog(LOG_ERR, "We don't own the log file.  Not logging\n");
+		fclose(tmon_log);
+		tmon_log = NULL;
+		return;
+	}
+
+
 	fprintf(tmon_log, "#----------- THERMAL SYSTEM CONFIG -------------\n");
 	for (i = 0; i < ptdata.nr_tz_sensor; i++) {
 		char binding_str[33]; /* size of long + 1 */
@@ -331,7 +355,7 @@ static void start_daemon_mode()
 	disable_tui();
 
 	/* change the file mode mask */
-	umask(0);
+	umask(S_IWGRP | S_IWOTH);
 
 	/* new SID for the daemon process */
 	sid = setsid();
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index fe1e66b6ef4..a87e99f37c5 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -116,8 +116,8 @@ static const struct {
 	.header = {
 		.magic = cpu_to_le32(FUNCTIONFS_DESCRIPTORS_MAGIC),
 		.length = cpu_to_le32(sizeof descriptors),
-		.fs_count = 3,
-		.hs_count = 3,
+		.fs_count = cpu_to_le32(3),
+		.hs_count = cpu_to_le32(3),
 	},
 	.fs_descs = {
 		.intf = {
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 56ff9bebb57..476d3bf540a 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1526,17 +1526,33 @@ int kvm_vgic_hyp_init(void)
 		goto out_unmap;
 	}
 
-	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
-		 vctrl_res.start, vgic_maint_irq);
-	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
-
 	if (of_address_to_resource(vgic_node, 3, &vcpu_res)) {
 		kvm_err("Cannot obtain VCPU resource\n");
 		ret = -ENXIO;
 		goto out_unmap;
 	}
+
+	if (!PAGE_ALIGNED(vcpu_res.start)) {
+		kvm_err("GICV physical address 0x%llx not page aligned\n",
+			(unsigned long long)vcpu_res.start);
+		ret = -ENXIO;
+		goto out_unmap;
+	}
+
+	if (!PAGE_ALIGNED(resource_size(&vcpu_res))) {
+		kvm_err("GICV size 0x%llx not a multiple of page size 0x%lx\n",
+			(unsigned long long)resource_size(&vcpu_res),
+			PAGE_SIZE);
+		ret = -ENXIO;
+		goto out_unmap;
+	}
+
 	vgic_vcpu_base = vcpu_res.start;
 
+	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
+		 vctrl_res.start, vgic_maint_irq);
+	on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+
 	goto out;
 
 out_unmap:
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 2458a1dc2ba..e8ce34c9db3 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -254,10 +254,9 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
 	spin_lock(&ioapic->lock);
 	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
 		e = &ioapic->redirtbl[index];
-		if (!e->fields.mask &&
-			(e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
-			 kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC,
-				 index) || index == RTC_GSI)) {
+		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+		    kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
+		    index == RTC_GSI) {
 			if (kvm_apic_match_dest(vcpu, NULL, 0,
 				e->fields.dest_id, e->fields.dest_mode)) {
 				__set_bit(e->fields.vector,
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index ced4a542a03..a228ee82bad 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -323,13 +323,13 @@ out:
 
 #define IOAPIC_ROUTING_ENTRY(irq) \
 	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
-	  .u.irqchip.irqchip = KVM_IRQCHIP_IOAPIC, .u.irqchip.pin = (irq) }
+	  .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
 #define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
 
 #ifdef CONFIG_X86
 #  define PIC_ROUTING_ENTRY(irq) \
 	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
-	  .u.irqchip.irqchip = SELECT_PIC(irq), .u.irqchip.pin = (irq) % 8 }
+	  .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
 #  define ROUTING_ENTRY2(irq) \
 	IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
 #else
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c86be0f983d..4b6c01b477f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1714,11 +1714,11 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
 #endif /* !CONFIG_S390 */
 
-bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
+int kvm_vcpu_yield_to(struct kvm_vcpu *target)
 {
 	struct pid *pid;
 	struct task_struct *task = NULL;
-	bool ret = false;
+	int ret = 0;
 
 	rcu_read_lock();
 	pid = rcu_dereference(target->pid);